From 1715b6359c1ae37f24d6774f0bcd73b6bf839eaa Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 6 Oct 2023 16:14:54 -0300
Subject: [PATCH 0001/4076] perf beauty socket/prctl_option: Cope with extended
 regexp complaint by grep

Noticed on fedora 38, the extended regexp that so far was ok for both
grep and sed now gets complaints by grep, that says '/' doesn't need to
be escaped with '\'.

So stop using '/' in sed, use '%' instead and remove the \ before / in
the common extended regexp.

Link: https://x.com/SMT_Solvers/status/1710380010098344192?s=20
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZUEddFPTJHVLhH%2F6@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/prctl_option.sh | 4 ++--
 tools/perf/trace/beauty/socket.sh       | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 8059342ca4126..9455d9672f140 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -4,9 +4,9 @@
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
-regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*\/.*)?$'
+regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*/.*)?$'
 grep -E $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
-	sed -r "s/$regex/\2 \1/g"	| \
+	sed -E "s%$regex%\2 \1%g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
diff --git a/tools/perf/trace/beauty/socket.sh b/tools/perf/trace/beauty/socket.sh
index 8bc7ba62203e4..670c6db298ae0 100755
--- a/tools/perf/trace/beauty/socket.sh
+++ b/tools/perf/trace/beauty/socket.sh
@@ -18,10 +18,10 @@ grep -E $ipproto_regex ${uapi_header_dir}/in.h | \
 printf "};\n\n"
 
 printf "static const char *socket_level[] = {\n"
-socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+\/.*)?'
+socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+/.*)?'
 
 grep -E $socket_level_regex ${beauty_header_dir}/socket.h | \
-	sed -r "s/$socket_level_regex/\2 \1/g"	| \
+	sed -E "s%$socket_level_regex%\2 \1%g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n\n"
 
-- 
GitLab


From c8e3ade38bc6545faece71cc6c642ad744d4cea3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 6 Oct 2023 18:11:05 -0300
Subject: [PATCH 0002/4076] perf tests make: Remove the last egrep call, use
 'grep -E' instead

One last case, caught while testing with amazonlinux:2, centos:stream,
etc:

   4     7.28 amazonlinux:2                 : FAIL egrep: warning: egrep is obsolescent; using grep -E
gcc version 7.3.1 20180712 (Red Hat 7.3.1-17) (GCC)
   8    13.87 centos:stream                 : FAIL egrep: warning: egrep is obsolescent; using grep -E

Reviewed-by: Guilherme Amadio <amadio@gentoo.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZUEdtblE8qDAQkBK@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/make | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index d9945ed25bc5a..8a4da7eb637a8 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -183,7 +183,7 @@ run += make_install_prefix_slash
 # run += make_install_pdf
 run += make_minimal
 
-old_libbpf := $(shell echo '\#include <bpf/libbpf.h>' | $(CC) -E -dM -x c -| egrep -q "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}")
+old_libbpf := $(shell echo '\#include <bpf/libbpf.h>' | $(CC) -E -dM -x c -| grep -q -E "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}")
 
 ifneq ($(old_libbpf),)
 run += make_libbpf_dynamic
-- 
GitLab


From 851bbccf6b0c152d98ecf0ec83d75fc97aebf43c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 11 Oct 2023 18:14:52 -0300
Subject: [PATCH 0003/4076] perf build: Warn about missing libelf before
 warning about missing libbpf

As libelf is a requirement for libbpf if it is not available, as in some
container build tests where NO_LIBELF=1 is used, then better warn about
the most basic library first.

Ditto for libz, check its availability before libbpf too.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZUEehyDk0FkPnvMR@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b3e6ed10f40c6..8b6cffbc48583 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -680,15 +680,15 @@ ifndef BUILD_BPF_SKEL
 endif
 
 ifeq ($(BUILD_BPF_SKEL),1)
-  ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),)
-    dummy := $(warning Warning: Disabled BPF skeletons as libbpf is required)
-    BUILD_BPF_SKEL := 0
-  else ifeq ($(filter -DHAVE_LIBELF_SUPPORT, $(CFLAGS)),)
+  ifeq ($(filter -DHAVE_LIBELF_SUPPORT, $(CFLAGS)),)
     dummy := $(warning Warning: Disabled BPF skeletons as libelf is required by bpftool)
     BUILD_BPF_SKEL := 0
   else ifeq ($(filter -DHAVE_ZLIB_SUPPORT, $(CFLAGS)),)
     dummy := $(warning Warning: Disabled BPF skeletons as zlib is required by bpftool)
     BUILD_BPF_SKEL := 0
+  else ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),)
+    dummy := $(warning Warning: Disabled BPF skeletons as libbpf is required)
+    BUILD_BPF_SKEL := 0
   else ifeq ($(call get-executable,$(CLANG)),)
     dummy := $(warning Warning: Disabled BPF skeletons as clang ($(CLANG)) is missing)
     BUILD_BPF_SKEL := 0
-- 
GitLab


From 76db7aab1fca6688ddf9f388157521c442e0ffb8 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 25 Oct 2023 13:16:24 -0700
Subject: [PATCH 0004/4076] tools headers UAPI: Sync
 include/uapi/linux/perf_event.h header with the kernel

Sync the new sample type for the branch counters feature.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tinghao Zhang <tinghao.zhang@intel.com>
Link: https://lore.kernel.org/r/20231025201626.3000228-6-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 39c6a250dd1b9..3a64499b0f5d6 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -204,6 +204,8 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT	= 18, /* save privilege mode */
 
+	PERF_SAMPLE_BRANCH_COUNTERS_SHIFT	= 19, /* save occurrences of events on a branch */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -235,6 +237,8 @@ enum perf_branch_sample_type {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE	= 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT,
 
+	PERF_SAMPLE_BRANCH_COUNTERS	= 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -982,6 +986,12 @@ enum perf_event_type {
 	 *	{ u64                   nr;
 	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
 	 *        { u64 from, to, flags } lbr[nr];
+	 *        #
+	 *        # The format of the counters is decided by the
+	 *        # "branch_counter_nr" and "branch_counter_width",
+	 *        # which are defined in the ABI.
+	 *        #
+	 *        { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS
 	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
@@ -1427,6 +1437,9 @@ struct perf_branch_entry {
 		reserved:31;
 };
 
+/* Size of used info bits in struct perf_branch_entry */
+#define PERF_BRANCH_ENTRY_INFO_BITS_MAX		33
+
 union perf_sample_weight {
 	__u64		full;
 #if defined(__LITTLE_ENDIAN_BITFIELD)
-- 
GitLab


From ac9cd7245fffa0fc053afce3b345469e5afa533a Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 25 Oct 2023 13:16:25 -0700
Subject: [PATCH 0005/4076] perf header: Support num and width of branch
 counters

To support the branch counters feature, the information of the maximum
number of supported counters and the width of the counters is exposed in
the sysfs caps folder. The perf tool can use the information to parse
the logged counters in each branch.

Store the information in the perf_env for later usage.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tinghao Zhang <tinghao.zhang@intel.com>
Link: https://lore.kernel.org/r/20231025201626.3000228-7-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/env.h    |  5 +++++
 tools/perf/util/header.c | 18 +++++++++++++++---
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 4566c51f2fd95..48d7f8759a2a7 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -46,6 +46,9 @@ struct hybrid_node {
 struct pmu_caps {
 	int		nr_caps;
 	unsigned int    max_branches;
+	unsigned int	br_cntr_nr;
+	unsigned int	br_cntr_width;
+
 	char            **caps;
 	char            *pmu_name;
 };
@@ -62,6 +65,8 @@ struct perf_env {
 	unsigned long long	total_mem;
 	unsigned int		msr_pmu_type;
 	unsigned int		max_branches;
+	unsigned int		br_cntr_nr;
+	unsigned int		br_cntr_width;
 	int			kernel_is_64_bit;
 
 	int			nr_cmdline;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e86b9439ffee0..eeb96a1b63a7c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3259,7 +3259,9 @@ static int process_compressed(struct feat_fd *ff,
 }
 
 static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps,
-			      char ***caps, unsigned int *max_branches)
+			      char ***caps, unsigned int *max_branches,
+			      unsigned int *br_cntr_nr,
+			      unsigned int *br_cntr_width)
 {
 	char *name, *value, *ptr;
 	u32 nr_pmu_caps, i;
@@ -3294,6 +3296,12 @@ static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps,
 		if (!strcmp(name, "branches"))
 			*max_branches = atoi(value);
 
+		if (!strcmp(name, "branch_counter_nr"))
+			*br_cntr_nr = atoi(value);
+
+		if (!strcmp(name, "branch_counter_width"))
+			*br_cntr_width = atoi(value);
+
 		free(value);
 		free(name);
 	}
@@ -3318,7 +3326,9 @@ static int process_cpu_pmu_caps(struct feat_fd *ff,
 {
 	int ret = __process_pmu_caps(ff, &ff->ph->env.nr_cpu_pmu_caps,
 				     &ff->ph->env.cpu_pmu_caps,
-				     &ff->ph->env.max_branches);
+				     &ff->ph->env.max_branches,
+				     &ff->ph->env.br_cntr_nr,
+				     &ff->ph->env.br_cntr_width);
 
 	if (!ret && !ff->ph->env.cpu_pmu_caps)
 		pr_debug("cpu pmu capabilities not available\n");
@@ -3347,7 +3357,9 @@ static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused)
 	for (i = 0; i < nr_pmu; i++) {
 		ret = __process_pmu_caps(ff, &pmu_caps[i].nr_caps,
 					 &pmu_caps[i].caps,
-					 &pmu_caps[i].max_branches);
+					 &pmu_caps[i].max_branches,
+					 &pmu_caps[i].br_cntr_nr,
+					 &pmu_caps[i].br_cntr_width);
 		if (ret)
 			goto err;
 
-- 
GitLab


From ef5b6a542b1dbb718226a5f8208be09ef405983d Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 8 Nov 2023 04:40:35 -0500
Subject: [PATCH 0006/4076] selftests: kvm/s390x: use vm_create_barebones()

This function does the same but makes it clearer why one would use
the "____"-prefixed version of vm_create().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/s390x/cmma_test.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c
index c8e0a6495a63a..626a2b8a20372 100644
--- a/tools/testing/selftests/kvm/s390x/cmma_test.c
+++ b/tools/testing/selftests/kvm/s390x/cmma_test.c
@@ -94,11 +94,6 @@ static void guest_dirty_test_data(void)
 	);
 }
 
-static struct kvm_vm *create_vm(void)
-{
-	return ____vm_create(VM_MODE_DEFAULT);
-}
-
 static void create_main_memslot(struct kvm_vm *vm)
 {
 	int i;
@@ -157,7 +152,7 @@ static struct kvm_vm *create_vm_two_memslots(void)
 {
 	struct kvm_vm *vm;
 
-	vm = create_vm();
+	vm = vm_create_barebones();
 
 	create_memslots(vm);
 
@@ -276,7 +271,7 @@ static void assert_exit_was_hypercall(struct kvm_vcpu *vcpu)
 
 static void test_migration_mode(void)
 {
-	struct kvm_vm *vm = create_vm();
+	struct kvm_vm *vm = vm_create_barebones();
 	struct kvm_vcpu *vcpu;
 	u64 orig_psw;
 	int rc;
@@ -670,7 +665,7 @@ struct testdef {
  */
 static int machine_has_cmma(void)
 {
-	struct kvm_vm *vm = create_vm();
+	struct kvm_vm *vm = vm_create_barebones();
 	int r;
 
 	r = !__kvm_has_device_attr(vm->fd, KVM_S390_VM_MEM_CTRL, KVM_S390_VM_MEM_ENABLE_CMMA);
-- 
GitLab


From 9fbb4b02302b0ae618303565025412070d32f85e Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 25 Oct 2023 13:16:26 -0700
Subject: [PATCH 0007/4076] perf tools: Add branch counter knob

Add a new branch filter, "counter", for the branch counter option. It is
used to mark the events which should be logged in the branch. If it is
applied with the -j option, the counters of all the events should be
logged in the branch. If the legacy kernel doesn't support the new
branch sample type, switching off the branch counter filter.

The stored counter values in each branch are displayed right after the
regular branch stack information via perf report -D.

Usage examples:

  # perf record -e "{branch-instructions,branch-misses}:S" -j any,counter

Only the first event, branch-instructions, collect the LBR. Both
branch-instructions and branch-misses are marked as logged events.  The
occurrences information of them can be found in the branch stack
extension space of each branch.

  # perf record -e "{cpu/branch-instructions,branch_type=any/,cpu/branch-misses,branch_type=counter/}"

Only the first event, branch-instructions, collect the LBR. Only the
branch-misses event is marked as a logged event.

Committer notes:

I noticed 'perf test "Sample parsing"' failing, reported to the list and
Kan provided a patch that checks if the evsel has a leader and that
evsel->evlist is set, the comment in the source code further explains
it.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tinghao Zhang <tinghao.zhang@intel.com>
Link: https://lore.kernel.org/r/20231025201626.3000228-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-record.txt  |  4 +++
 tools/perf/util/evsel.c                   | 35 ++++++++++++++++++++++-
 tools/perf/util/evsel.h                   |  1 +
 tools/perf/util/parse-branch-options.c    |  1 +
 tools/perf/util/perf_event_attr_fprintf.c |  1 +
 tools/perf/util/sample.h                  |  1 +
 tools/perf/util/session.c                 | 15 ++++++++--
 7 files changed, 55 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 1889f66addf2a..6015fdd08fb63 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -445,6 +445,10 @@ following filters are defined:
 		     4th-Gen Xeon+ server), the save branch type is unconditionally enabled
 		     when the taken branch stack sampling is enabled.
 	- priv: save privilege state during sampling in case binary is not available later
+	- counter: save occurrences of the event since the last branch entry. Currently, the
+		   feature is only supported by a newer CPU, e.g., Intel Sierra Forest and
+		   later platforms. An error out is expected if it's used on the unsupported
+		   kernel or CPUs.
 
 +
 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 72a5dfc38d380..a5da74e3a517b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1832,6 +1832,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
+	if (perf_missing_features.branch_counters)
+		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS;
 	if (perf_missing_features.read_lost)
 		evsel->core.attr.read_format &= ~PERF_FORMAT_LOST;
 	if (perf_missing_features.weight_struct) {
@@ -1885,7 +1887,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.read_lost &&
+	if (!perf_missing_features.branch_counters &&
+	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
+		perf_missing_features.branch_counters = true;
+		pr_debug2("switching off branch counters support\n");
+		return true;
+	} else if (!perf_missing_features.read_lost &&
 	    (evsel->core.attr.read_format & PERF_FORMAT_LOST)) {
 		perf_missing_features.read_lost = true;
 		pr_debug2("switching off PERF_FORMAT_LOST support\n");
@@ -2318,6 +2325,22 @@ u64 evsel__bitfield_swap_branch_flags(u64 value)
 	return new_val;
 }
 
+static inline bool evsel__has_branch_counters(const struct evsel *evsel)
+{
+	struct evsel *cur, *leader = evsel__leader(evsel);
+
+	/* The branch counters feature only supports group */
+	if (!leader || !evsel->evlist)
+		return false;
+
+	evlist__for_each_entry(evsel->evlist, cur) {
+		if ((leader == evsel__leader(cur)) &&
+		    (cur->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS))
+			return true;
+	}
+	return false;
+}
+
 int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *data)
 {
@@ -2551,6 +2574,16 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 		OVERFLOW_CHECK(array, sz, max_size);
 		array = (void *)array + sz;
+
+		if (evsel__has_branch_counters(evsel)) {
+			OVERFLOW_CHECK_u64(array);
+
+			data->branch_stack_cntr = (u64 *)array;
+			sz = data->branch_stack->nr * sizeof(u64);
+
+			OVERFLOW_CHECK(array, sz, max_size);
+			array = (void *)array + sz;
+		}
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d791316a1792e..f19ac9f027efc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -191,6 +191,7 @@ struct perf_missing_features {
 	bool code_page_size;
 	bool weight_struct;
 	bool read_lost;
+	bool branch_counters;
 };
 
 extern struct perf_missing_features perf_missing_features;
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index fd67d204d720d..f7f7aff3d85a0 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -36,6 +36,7 @@ static const struct branch_mode branch_modes[] = {
 	BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK),
 	BRANCH_OPT("hw_index", PERF_SAMPLE_BRANCH_HW_INDEX),
 	BRANCH_OPT("priv", PERF_SAMPLE_BRANCH_PRIV_SAVE),
+	BRANCH_OPT("counter", PERF_SAMPLE_BRANCH_COUNTERS),
 	BRANCH_END
 };
 
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 2247991451f3a..8f04d3b7f3ec7 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -55,6 +55,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
 		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
 		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
 		bit_name(TYPE_SAVE), bit_name(HW_INDEX), bit_name(PRIV_SAVE),
+		bit_name(COUNTERS),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index c92ad0f51ecd9..70b2c3135555e 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -113,6 +113,7 @@ struct perf_sample {
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
+	u64 *branch_stack_cntr;
 	struct regs_dump  user_regs;
 	struct regs_dump  intr_regs;
 	struct stack_dump user_stack;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1e9aa8ed15b64..4a094ab0362b4 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1150,9 +1150,13 @@ static void callchain__printf(struct evsel *evsel,
 		       i, callchain->ips[i]);
 }
 
-static void branch_stack__printf(struct perf_sample *sample, bool callstack)
+static void branch_stack__printf(struct perf_sample *sample,
+				 struct evsel *evsel)
 {
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
+	bool callstack = evsel__has_branch_callstack(evsel);
+	u64 *branch_stack_cntr = sample->branch_stack_cntr;
+	struct perf_env *env = evsel__env(evsel);
 	uint64_t i;
 
 	if (!callstack) {
@@ -1194,6 +1198,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 			}
 		}
 	}
+
+	if (branch_stack_cntr) {
+		printf("... branch stack counters: nr:%" PRIu64 " (counter width: %u max counter nr:%u)\n",
+			sample->branch_stack->nr, env->br_cntr_width, env->br_cntr_nr);
+		for (i = 0; i < sample->branch_stack->nr; i++)
+			printf("..... %2"PRIu64": %016" PRIx64 "\n", i, branch_stack_cntr[i]);
+	}
 }
 
 static void regs_dump__printf(u64 mask, u64 *regs, const char *arch)
@@ -1355,7 +1366,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 		callchain__printf(evsel, sample);
 
 	if (evsel__has_br_stack(evsel))
-		branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
+		branch_stack__printf(sample, evsel);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample, arch);
-- 
GitLab


From 7ff7b7afe364af17362f2a08cccdc79905feb0bc Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 3 Oct 2023 08:49:11 +0100
Subject: [PATCH 0008/4076] perf tools: Fix spelling mistake "parametrized" ->
 "parameterized"

There are spelling mistakes in comments and a pr_debug message. Fix them.

Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-janitors@vger.kernel.org
Link: https://lore.kernel.org/r/20231003074911.220216-1-colin.i.king@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/parse-events.c        | 4 ++--
 tools/perf/tests/shell/stat_all_pmu.sh | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index f78be21a5999b..e52f45c7c3d1a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2549,7 +2549,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest
 			if (strchr(ent->d_name, '.'))
 				continue;
 
-			/* exclude parametrized ones (name contains '?') */
+			/* exclude parameterized ones (name contains '?') */
 			n = snprintf(pmu_event, sizeof(pmu_event), "%s%s", path, ent->d_name);
 			if (n >= PATH_MAX) {
 				pr_err("pmu event name crossed PATH_MAX(%d) size\n", PATH_MAX);
@@ -2578,7 +2578,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest
 			fclose(file);
 
 			if (is_event_parameterized == 1) {
-				pr_debug("skipping parametrized PMU event: %s which contains ?\n", pmu_event);
+				pr_debug("skipping parameterized PMU event: %s which contains ?\n", pmu_event);
 				continue;
 			}
 
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
index c779554191731..d2a3506e0d196 100755
--- a/tools/perf/tests/shell/stat_all_pmu.sh
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -4,7 +4,7 @@
 
 set -e
 
-# Test all PMU events; however exclude parametrized ones (name contains '?')
+# Test all PMU events; however exclude parameterized ones (name contains '?')
 for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g'); do
   echo "Testing $p"
   result=$(perf stat -e "$p" true 2>&1)
-- 
GitLab


From 1a27fc01700fbff2f205000edf0d1d315b5f85cc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 2 Nov 2023 10:56:44 -0700
Subject: [PATCH 0009/4076] perf record: Lazy load kernel symbols

Commit 5b7ba82a75915e73 ("perf symbols: Load kernel maps before using")
changed it so that loading a kernel DSO would cause the symbols for the
DSO to be eagerly loaded.

For 'perf record' this is overhead as the symbols won't be used. Add a
field to 'struct symbol_conf' to control the behavior and disable it for
'perf record' and 'perf inject'.

Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231102175735.2272696-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-inject.c   | 6 ++++++
 tools/perf/builtin-record.c   | 2 ++
 tools/perf/util/event.c       | 4 ++--
 tools/perf/util/symbol_conf.h | 3 ++-
 4 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index c8cf2fdd9cff9..eb3ef5c24b662 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -2265,6 +2265,12 @@ int cmd_inject(int argc, const char **argv)
 		"perf inject [<options>]",
 		NULL
 	};
+
+	if (!inject.itrace_synth_opts.set) {
+		/* Disable eager loading of kernel symbols that adds overhead to perf inject. */
+		symbol_conf.lazy_load_kernel_maps = true;
+	}
+
 #ifndef HAVE_JITDUMP
 	set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true);
 #endif
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dcf288a4fb9a9..8ec818568662e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -3989,6 +3989,8 @@ int cmd_record(int argc, const char **argv)
 # undef set_nobuild
 #endif
 
+	/* Disable eager loading of kernel symbols that adds overhead to perf record. */
+	symbol_conf.lazy_load_kernel_maps = true;
 	rec->opts.affinity = PERF_AFFINITY_SYS;
 
 	rec->evlist = evlist__new();
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 923c0fb151222..68f45e9e63b6e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -617,13 +617,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
 		al->level = 'k';
 		maps = machine__kernel_maps(machine);
-		load_map = true;
+		load_map = !symbol_conf.lazy_load_kernel_maps;
 	} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
 		al->level = '.';
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
 		al->level = 'g';
 		maps = machine__kernel_maps(machine);
-		load_map = true;
+		load_map = !symbol_conf.lazy_load_kernel_maps;
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
 		al->level = 'u';
 	} else {
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index 0b589570d1d09..2b2fb9e224b00 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -42,7 +42,8 @@ struct symbol_conf {
 			inline_name,
 			disable_add2line_warn,
 			buildid_mmap2,
-			guest_code;
+			guest_code,
+			lazy_load_kernel_maps;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
-- 
GitLab


From 9ffa6c7512ca7aaeb30e596e2c247cb1fae7123a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 2 Nov 2023 10:56:47 -0700
Subject: [PATCH 0010/4076] perf machine thread: Remove exited threads by
 default

'struct thread' values hold onto references to mmaps, DSOs, etc. When a
thread exits it is necessary to clean all of this memory up by removing
the thread from the machine's threads. Some tools require this doesn't
happen, such as auxtrace events, 'perf report' if offcpu events exist or
if a task list is being generated, so add a 'struct symbol_conf' member
to make the behavior optional. When an exited thread is left in the
machine's threads, mark it as exited.

This change relates to commit 40826c45eb0b8856 ("perf thread: Remove
notion of dead threads") . Dead threads were removed as they had a
reference count of 0 and were difficult to reason about with the
reference count checker. Here a thread is removed from threads when it
exits, unless via symbol_conf the exited thread isn't remove and is
marked as exited. Reference counting behaves as it normally does.

Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231102175735.2272696-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c   |  7 +++++++
 tools/perf/util/machine.c     | 10 +++++++---
 tools/perf/util/session.c     |  5 +++++
 tools/perf/util/symbol_conf.h |  3 ++-
 tools/perf/util/thread.h      | 14 ++++++++++++++
 5 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9cb1da2dc0c03..121a2781323c8 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1426,6 +1426,13 @@ int cmd_report(int argc, const char **argv)
 	if (ret < 0)
 		goto exit;
 
+	/*
+	 * tasks_mode require access to exited threads to list those that are in
+	 * the data file. Off-cpu events are synthesized after other events and
+	 * reference exited threads.
+	 */
+	symbol_conf.keep_exited_threads = true;
+
 	annotation_options__init(&report.annotation_opts);
 
 	ret = perf_config(report__config, &report);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 90c750150b19b..a985d004aa8d8 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2157,9 +2157,13 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
-	if (thread != NULL)
-		thread__put(thread);
-
+	if (thread != NULL) {
+		if (symbol_conf.keep_exited_threads)
+			thread__set_exited(thread, /*exited=*/true);
+		else
+			machine__remove_thread(machine, thread);
+	}
+	thread__put(thread);
 	return 0;
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 4a094ab0362b4..199d3e8df3158 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -115,6 +115,11 @@ static int perf_session__open(struct perf_session *session, int repipe_fd)
 		return -1;
 	}
 
+	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE)) {
+		/* Auxiliary events may reference exited threads, hold onto dead ones. */
+		symbol_conf.keep_exited_threads = true;
+	}
+
 	if (perf_data__is_pipe(data))
 		return 0;
 
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index 2b2fb9e224b00..6040286e07a65 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -43,7 +43,8 @@ struct symbol_conf {
 			disable_add2line_warn,
 			buildid_mmap2,
 			guest_code,
-			lazy_load_kernel_maps;
+			lazy_load_kernel_maps,
+			keep_exited_threads;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index e79225a0ea46b..0df775b5c1105 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -36,13 +36,22 @@ struct thread_rb_node {
 };
 
 DECLARE_RC_STRUCT(thread) {
+	/** @maps: mmaps associated with this thread. */
 	struct maps		*maps;
 	pid_t			pid_; /* Not all tools update this */
+	/** @tid: thread ID number unique to a machine. */
 	pid_t			tid;
+	/** @ppid: parent process of the process this thread belongs to. */
 	pid_t			ppid;
 	int			cpu;
 	int			guest_cpu; /* For QEMU thread */
 	refcount_t		refcnt;
+	/**
+	 * @exited: Has the thread had an exit event. Such threads are usually
+	 * removed from the machine's threads but some events/tools require
+	 * access to dead threads.
+	 */
+	bool			exited;
 	bool			comm_set;
 	int			comm_len;
 	struct list_head	namespaces_list;
@@ -189,6 +198,11 @@ static inline refcount_t *thread__refcnt(struct thread *thread)
 	return &RC_CHK_ACCESS(thread)->refcnt;
 }
 
+static inline void thread__set_exited(struct thread *thread, bool exited)
+{
+	RC_CHK_ACCESS(thread)->exited = exited;
+}
+
 static inline bool thread__comm_set(const struct thread *thread)
 {
 	return RC_CHK_ACCESS(thread)->comm_set;
-- 
GitLab


From 89d5c48c34c8a552acd9a2e3ee504b2f06879fea Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 3 Nov 2023 12:55:41 -0700
Subject: [PATCH 0011/4076] perf test: Simplify "object code reading" test

It tries cycles (or cpu-clock on s390) event with exclude_kernel bit to
open.  But other arch on a VM can fail with the hardware event and need
to fallback to the software event in the same way.

So let's get rid of the cpuid check and use generic fallback mechanism
using an array of event candidates.  Now event in the odd index excludes
the kernel so use that for the return value.

Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: James Clark <james.clark@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20231103195541.67788-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/code-reading.c | 76 ++++++++++-----------------------
 1 file changed, 23 insertions(+), 53 deletions(-)

diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 3af81012014ed..d6e845c579023 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -511,38 +511,6 @@ static void fs_something(void)
 	}
 }
 
-#ifdef __s390x__
-#include "header.h" // for get_cpuid()
-#endif
-
-static const char *do_determine_event(bool excl_kernel)
-{
-	const char *event = excl_kernel ? "cycles:u" : "cycles";
-
-#ifdef __s390x__
-	char cpuid[128], model[16], model_c[16], cpum_cf_v[16];
-	unsigned int family;
-	int ret, cpum_cf_a;
-
-	if (get_cpuid(cpuid, sizeof(cpuid)))
-		goto out_clocks;
-	ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%x", &family, model_c,
-		     model, cpum_cf_v, &cpum_cf_a);
-	if (ret != 5)		 /* Not available */
-		goto out_clocks;
-	if (excl_kernel && (cpum_cf_a & 4))
-		return event;
-	if (!excl_kernel && (cpum_cf_a & 2))
-		return event;
-
-	/* Fall through: missing authorization */
-out_clocks:
-	event = excl_kernel ? "cpu-clock:u" : "cpu-clock";
-
-#endif
-	return event;
-}
-
 static void do_something(void)
 {
 	fs_something();
@@ -583,8 +551,10 @@ static int do_test_code_reading(bool try_kcore)
 	int err = -1, ret;
 	pid_t pid;
 	struct map *map;
-	bool have_vmlinux, have_kcore, excl_kernel = false;
+	bool have_vmlinux, have_kcore;
 	struct dso *dso;
+	const char *events[] = { "cycles", "cycles:u", "cpu-clock", "cpu-clock:u", NULL };
+	int evidx = 0;
 
 	pid = getpid();
 
@@ -618,7 +588,7 @@ static int do_test_code_reading(bool try_kcore)
 
 	/* No point getting kernel events if there is no kernel object */
 	if (!have_vmlinux && !have_kcore)
-		excl_kernel = true;
+		evidx++;
 
 	threads = thread_map__new_by_tid(pid);
 	if (!threads) {
@@ -646,7 +616,7 @@ static int do_test_code_reading(bool try_kcore)
 		goto out_put;
 	}
 
-	while (1) {
+	while (events[evidx]) {
 		const char *str;
 
 		evlist = evlist__new();
@@ -657,7 +627,7 @@ static int do_test_code_reading(bool try_kcore)
 
 		perf_evlist__set_maps(&evlist->core, cpus, threads);
 
-		str = do_determine_event(excl_kernel);
+		str = events[evidx];
 		pr_debug("Parsing event '%s'\n", str);
 		ret = parse_event(evlist, str);
 		if (ret < 0) {
@@ -675,32 +645,32 @@ static int do_test_code_reading(bool try_kcore)
 
 		ret = evlist__open(evlist);
 		if (ret < 0) {
-			if (!excl_kernel) {
-				excl_kernel = true;
-				/*
-				 * Both cpus and threads are now owned by evlist
-				 * and will be freed by following perf_evlist__set_maps
-				 * call. Getting reference to keep them alive.
-				 */
-				perf_cpu_map__get(cpus);
-				perf_thread_map__get(threads);
-				perf_evlist__set_maps(&evlist->core, NULL, NULL);
-				evlist__delete(evlist);
-				evlist = NULL;
-				continue;
-			}
+			evidx++;
 
-			if (verbose > 0) {
+			if (events[evidx] == NULL && verbose > 0) {
 				char errbuf[512];
 				evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
 				pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
 			}
 
-			goto out_put;
+			/*
+			 * Both cpus and threads are now owned by evlist
+			 * and will be freed by following perf_evlist__set_maps
+			 * call. Getting reference to keep them alive.
+			 */
+			perf_cpu_map__get(cpus);
+			perf_thread_map__get(threads);
+			perf_evlist__set_maps(&evlist->core, NULL, NULL);
+			evlist__delete(evlist);
+			evlist = NULL;
+			continue;
 		}
 		break;
 	}
 
+	if (events[evidx] == NULL)
+		goto out_put;
+
 	ret = evlist__mmap(evlist, UINT_MAX);
 	if (ret < 0) {
 		pr_debug("evlist__mmap failed\n");
@@ -721,7 +691,7 @@ static int do_test_code_reading(bool try_kcore)
 		err = TEST_CODE_READING_NO_KERNEL_OBJ;
 	else if (!have_vmlinux && !try_kcore)
 		err = TEST_CODE_READING_NO_VMLINUX;
-	else if (excl_kernel)
+	else if (strstr(events[evidx], ":u"))
 		err = TEST_CODE_READING_NO_ACCESS;
 	else
 		err = TEST_CODE_READING_OK;
-- 
GitLab


From de2c7eb59c342d1a61124caaf2993e325a9becb7 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 3 Nov 2023 12:19:03 -0700
Subject: [PATCH 0012/4076] perf annotate: Split branch stack cycles
 information out of 'struct annotation_line'

The cycles info is used only when branch stack is provided.  Separate
them from 'struct annotation_line' into a separate struct and lazy
allocate them to save some memory.

Committer notes:

Make annotation__compute_ipc() check if the lazy allocation works,
bailing out if so, its callers already do error checking and
propagation.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231103191907.54531-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/browsers/annotate.c |  2 +-
 tools/perf/util/annotate.c        | 61 ++++++++++++++++++++++---------
 tools/perf/util/annotate.h        | 15 +++++---
 3 files changed, 54 insertions(+), 24 deletions(-)

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ccdb2cd11fbf0..d2470f87344d0 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -337,7 +337,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 				max_percent = percent;
 		}
 
-		if (max_percent < 0.01 && pos->al.ipc == 0) {
+		if (max_percent < 0.01 && (!pos->al.cycles || pos->al.cycles->ipc == 0)) {
 			RB_CLEAR_NODE(&pos->al.rb_node);
 			continue;
 		}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 82956adf99632..99ff3bb9cad8d 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1100,8 +1100,8 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 		for (offset = start; offset <= end; offset++) {
 			struct annotation_line *al = notes->offsets[offset];
 
-			if (al && al->ipc == 0.0) {
-				al->ipc = ipc;
+			if (al && al->cycles && al->cycles->ipc == 0.0) {
+				al->cycles->ipc = ipc;
 				cover_insn++;
 			}
 		}
@@ -1114,12 +1114,13 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 	}
 }
 
-void annotation__compute_ipc(struct annotation *notes, size_t size)
+static int annotation__compute_ipc(struct annotation *notes, size_t size)
 {
+	int err = 0;
 	s64 offset;
 
 	if (!notes->src || !notes->src->cycles_hist)
-		return;
+		return 0;
 
 	notes->total_insn = annotation__count_insn(notes, 0, size - 1);
 	notes->hit_cycles = 0;
@@ -1134,18 +1135,39 @@ void annotation__compute_ipc(struct annotation *notes, size_t size)
 		if (ch && ch->cycles) {
 			struct annotation_line *al;
 
+			al = notes->offsets[offset];
+			if (al && al->cycles == NULL) {
+				al->cycles = zalloc(sizeof(*al->cycles));
+				if (al->cycles == NULL) {
+					err = ENOMEM;
+					break;
+				}
+			}
 			if (ch->have_start)
 				annotation__count_and_fill(notes, ch->start, offset, ch);
-			al = notes->offsets[offset];
 			if (al && ch->num_aggr) {
-				al->cycles = ch->cycles_aggr / ch->num_aggr;
-				al->cycles_max = ch->cycles_max;
-				al->cycles_min = ch->cycles_min;
+				al->cycles->avg = ch->cycles_aggr / ch->num_aggr;
+				al->cycles->max = ch->cycles_max;
+				al->cycles->min = ch->cycles_min;
 			}
 			notes->have_cycles = true;
 		}
 	}
+
+	if (err) {
+		while (++offset < (s64)size) {
+			struct cyc_hist *ch = &notes->src->cycles_hist[offset];
+
+			if (ch && ch->cycles) {
+				struct annotation_line *al = notes->offsets[offset];
+				if (al)
+					zfree(&al->cycles);
+			}
+		}
+	}
+
 	annotation__unlock(notes);
+	return 0;
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
@@ -1225,6 +1247,7 @@ static void annotation_line__exit(struct annotation_line *al)
 {
 	zfree_srcline(&al->path);
 	zfree(&al->line);
+	zfree(&al->cycles);
 }
 
 static size_t disasm_line_size(int nr)
@@ -3083,8 +3106,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	int printed;
 
 	if (first_line && (al->offset == -1 || percent_max == 0.0)) {
-		if (notes->have_cycles) {
-			if (al->ipc == 0.0 && al->cycles == 0)
+		if (notes->have_cycles && al->cycles) {
+			if (al->cycles->ipc == 0.0 && al->cycles->avg == 0)
 				show_title = true;
 		} else
 			show_title = true;
@@ -3121,17 +3144,17 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	}
 
 	if (notes->have_cycles) {
-		if (al->ipc)
-			obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->ipc);
+		if (al->cycles && al->cycles->ipc)
+			obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->cycles->ipc);
 		else if (!show_title)
 			obj__printf(obj, "%*s", ANNOTATION__IPC_WIDTH, " ");
 		else
 			obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
 
 		if (!notes->options->show_minmax_cycle) {
-			if (al->cycles)
+			if (al->cycles && al->cycles->avg)
 				obj__printf(obj, "%*" PRIu64 " ",
-					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles);
+					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles->avg);
 			else if (!show_title)
 				obj__printf(obj, "%*s",
 					    ANNOTATION__CYCLES_WIDTH, " ");
@@ -3145,8 +3168,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 
 				scnprintf(str, sizeof(str),
 					"%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")",
-					al->cycles, al->cycles_min,
-					al->cycles_max);
+					al->cycles->avg, al->cycles->min,
+					al->cycles->max);
 
 				obj__printf(obj, "%*s ",
 					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
@@ -3264,7 +3287,11 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 
 	annotation__set_offsets(notes, size);
 	annotation__mark_jump_targets(notes, sym);
-	annotation__compute_ipc(notes, size);
+
+	err = annotation__compute_ipc(notes, size);
+	if (err)
+		goto out_free_offsets;
+
 	annotation__init_column_widths(notes, sym);
 	notes->nr_events = nr_pcnt;
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 9627805591760..19bc2f0391757 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -130,6 +130,13 @@ struct annotation_data {
 	struct sym_hist_entry	 he;
 };
 
+struct cycles_info {
+	float			 ipc;
+	u64			 avg;
+	u64			 max;
+	u64			 min;
+};
+
 struct annotation_line {
 	struct list_head	 node;
 	struct rb_node		 rb_node;
@@ -137,12 +144,9 @@ struct annotation_line {
 	char			*line;
 	int			 line_nr;
 	char			*fileloc;
-	int			 jump_sources;
-	float			 ipc;
-	u64			 cycles;
-	u64			 cycles_max;
-	u64			 cycles_min;
 	char			*path;
+	struct cycles_info	*cycles;
+	int			 jump_sources;
 	u32			 idx;
 	int			 idx_asm;
 	int			 data_nr;
@@ -325,7 +329,6 @@ static inline bool annotation_line__filter(struct annotation_line *al, struct an
 }
 
 void annotation__set_offsets(struct annotation *notes, s64 size);
-void annotation__compute_ipc(struct annotation *notes, size_t size);
 void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym);
 void annotation__update_column_widths(struct annotation *notes);
 void annotation__init_column_widths(struct annotation *notes, struct symbol *sym);
-- 
GitLab


From b7f87e32590bf48eca84f729d3422be7b8dc22d3 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 3 Nov 2023 12:19:04 -0700
Subject: [PATCH 0013/4076] perf annotate: Split branch stack cycles info from
 'struct annotation'

The cycles info is only meaningful when sample has branch stacks.  To
save the memory for normal cases, move those fields to a new 'struct
annotated_branch' and dynamically allocate it when needed.  Also move
cycles_hist from annotated_source as it's related here.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231103191907.54531-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c   | 99 ++++++++++++++++++++----------------
 tools/perf/util/annotate.h   | 17 ++++---
 tools/perf/util/block-info.c |  4 +-
 tools/perf/util/sort.c       | 14 ++---
 4 files changed, 73 insertions(+), 61 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 99ff3bb9cad8d..4e40c94c85d10 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -810,7 +810,6 @@ static __maybe_unused void annotated_source__delete(struct annotated_source *src
 	if (src == NULL)
 		return;
 	zfree(&src->histograms);
-	zfree(&src->cycles_hist);
 	free(src);
 }
 
@@ -845,18 +844,6 @@ static int annotated_source__alloc_histograms(struct annotated_source *src,
 	return src->histograms ? 0 : -1;
 }
 
-/* The cycles histogram is lazily allocated. */
-static int symbol__alloc_hist_cycles(struct symbol *sym)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	const size_t size = symbol__size(sym);
-
-	notes->src->cycles_hist = calloc(size, sizeof(struct cyc_hist));
-	if (notes->src->cycles_hist == NULL)
-		return -1;
-	return 0;
-}
-
 void symbol__annotate_zero_histograms(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -865,9 +852,10 @@ void symbol__annotate_zero_histograms(struct symbol *sym)
 	if (notes->src != NULL) {
 		memset(notes->src->histograms, 0,
 		       notes->src->nr_histograms * notes->src->sizeof_sym_hist);
-		if (notes->src->cycles_hist)
-			memset(notes->src->cycles_hist, 0,
-				symbol__size(sym) * sizeof(struct cyc_hist));
+	}
+	if (notes->branch && notes->branch->cycles_hist) {
+		memset(notes->branch->cycles_hist, 0,
+		       symbol__size(sym) * sizeof(struct cyc_hist));
 	}
 	annotation__unlock(notes);
 }
@@ -958,23 +946,33 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms,
 	return 0;
 }
 
+static struct annotated_branch *annotation__get_branch(struct annotation *notes)
+{
+	if (notes == NULL)
+		return NULL;
+
+	if (notes->branch == NULL)
+		notes->branch = zalloc(sizeof(*notes->branch));
+
+	return notes->branch;
+}
+
 static struct cyc_hist *symbol__cycles_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
+	struct annotated_branch *branch;
 
-	if (notes->src == NULL) {
-		notes->src = annotated_source__new();
-		if (notes->src == NULL)
-			return NULL;
-		goto alloc_cycles_hist;
-	}
+	branch = annotation__get_branch(notes);
+	if (branch == NULL)
+		return NULL;
+
+	if (branch->cycles_hist == NULL) {
+		const size_t size = symbol__size(sym);
 
-	if (!notes->src->cycles_hist) {
-alloc_cycles_hist:
-		symbol__alloc_hist_cycles(sym);
+		branch->cycles_hist = calloc(size, sizeof(struct cyc_hist));
 	}
 
-	return notes->src->cycles_hist;
+	return branch->cycles_hist;
 }
 
 struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists)
@@ -1083,6 +1081,14 @@ static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64
 	return n_insn;
 }
 
+static void annotated_branch__delete(struct annotated_branch *branch)
+{
+	if (branch) {
+		zfree(&branch->cycles_hist);
+		free(branch);
+	}
+}
+
 static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
 {
 	unsigned n_insn;
@@ -1091,6 +1097,7 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 
 	n_insn = annotation__count_insn(notes, start, end);
 	if (n_insn && ch->num && ch->cycles) {
+		struct annotated_branch *branch;
 		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
 
 		/* Hide data when there are too many overlaps. */
@@ -1106,10 +1113,11 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 			}
 		}
 
-		if (cover_insn) {
-			notes->hit_cycles += ch->cycles;
-			notes->hit_insn += n_insn * ch->num;
-			notes->cover_insn += cover_insn;
+		branch = annotation__get_branch(notes);
+		if (cover_insn && branch) {
+			branch->hit_cycles += ch->cycles;
+			branch->hit_insn += n_insn * ch->num;
+			branch->cover_insn += cover_insn;
 		}
 	}
 }
@@ -1119,19 +1127,19 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 	int err = 0;
 	s64 offset;
 
-	if (!notes->src || !notes->src->cycles_hist)
+	if (!notes->branch || !notes->branch->cycles_hist)
 		return 0;
 
-	notes->total_insn = annotation__count_insn(notes, 0, size - 1);
-	notes->hit_cycles = 0;
-	notes->hit_insn = 0;
-	notes->cover_insn = 0;
+	notes->branch->total_insn = annotation__count_insn(notes, 0, size - 1);
+	notes->branch->hit_cycles = 0;
+	notes->branch->hit_insn = 0;
+	notes->branch->cover_insn = 0;
 
 	annotation__lock(notes);
 	for (offset = size - 1; offset >= 0; --offset) {
 		struct cyc_hist *ch;
 
-		ch = &notes->src->cycles_hist[offset];
+		ch = &notes->branch->cycles_hist[offset];
 		if (ch && ch->cycles) {
 			struct annotation_line *al;
 
@@ -1150,13 +1158,12 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 				al->cycles->max = ch->cycles_max;
 				al->cycles->min = ch->cycles_min;
 			}
-			notes->have_cycles = true;
 		}
 	}
 
 	if (err) {
 		while (++offset < (s64)size) {
-			struct cyc_hist *ch = &notes->src->cycles_hist[offset];
+			struct cyc_hist *ch = &notes->branch->cycles_hist[offset];
 
 			if (ch && ch->cycles) {
 				struct annotation_line *al = notes->offsets[offset];
@@ -1322,6 +1329,7 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r
 void annotation__exit(struct annotation *notes)
 {
 	annotated_source__delete(notes->src);
+	annotated_branch__delete(notes->branch);
 }
 
 static struct sharded_mutex *sharded_mutex;
@@ -3075,13 +3083,14 @@ call_like:
 static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
 {
 	double ipc = 0.0, coverage = 0.0;
+	struct annotated_branch *branch = annotation__get_branch(notes);
 
-	if (notes->hit_cycles)
-		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+	if (branch && branch->hit_cycles)
+		ipc = branch->hit_insn / ((double)branch->hit_cycles);
 
-	if (notes->total_insn) {
-		coverage = notes->cover_insn * 100.0 /
-			((double)notes->total_insn);
+	if (branch && branch->total_insn) {
+		coverage = branch->cover_insn * 100.0 /
+			((double)branch->total_insn);
 	}
 
 	scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)",
@@ -3106,7 +3115,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	int printed;
 
 	if (first_line && (al->offset == -1 || percent_max == 0.0)) {
-		if (notes->have_cycles && al->cycles) {
+		if (notes->branch && al->cycles) {
 			if (al->cycles->ipc == 0.0 && al->cycles->avg == 0)
 				show_title = true;
 		} else
@@ -3143,7 +3152,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		}
 	}
 
-	if (notes->have_cycles) {
+	if (notes->branch) {
 		if (al->cycles && al->cycles->ipc)
 			obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->cycles->ipc);
 		else if (!show_title)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 19bc2f0391757..508b93d3dcde9 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -271,17 +271,20 @@ struct annotated_source {
 	struct list_head   source;
 	int    		   nr_histograms;
 	size_t		   sizeof_sym_hist;
-	struct cyc_hist	   *cycles_hist;
 	struct sym_hist	   *histograms;
 };
 
-struct LOCKABLE annotation {
-	u64			max_coverage;
-	u64			start;
+struct annotated_branch {
 	u64			hit_cycles;
 	u64			hit_insn;
 	unsigned int		total_insn;
 	unsigned int		cover_insn;
+	struct cyc_hist		*cycles_hist;
+};
+
+struct LOCKABLE annotation {
+	u64			max_coverage;
+	u64			start;
 	struct annotation_options *options;
 	struct annotation_line	**offsets;
 	int			nr_events;
@@ -297,8 +300,8 @@ struct LOCKABLE annotation {
 		u8		max_addr;
 		u8		max_ins_name;
 	} widths;
-	bool			have_cycles;
 	struct annotated_source *src;
+	struct annotated_branch *branch;
 };
 
 static inline void annotation__init(struct annotation *notes __maybe_unused)
@@ -312,10 +315,10 @@ bool annotation__trylock(struct annotation *notes) EXCLUSIVE_TRYLOCK_FUNCTION(tr
 
 static inline int annotation__cycles_width(struct annotation *notes)
 {
-	if (notes->have_cycles && notes->options->show_minmax_cycle)
+	if (notes->branch && notes->options->show_minmax_cycle)
 		return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH;
 
-	return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
+	return notes->branch ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
 }
 
 static inline int annotation__pcnt_width(struct annotation *notes)
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index 591fc1edd385c..08f82c1f166c3 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -129,9 +129,9 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
 	al.sym = he->ms.sym;
 
 	notes = symbol__annotation(he->ms.sym);
-	if (!notes || !notes->src || !notes->src->cycles_hist)
+	if (!notes || !notes->branch || !notes->branch->cycles_hist)
 		return 0;
-	ch = notes->src->cycles_hist;
+	ch = notes->branch->cycles_hist;
 	for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) {
 		if (ch[i].num_aggr) {
 			struct block_info *bi;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 80e4f61327401..27b123ccd2d15 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -583,21 +583,21 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
 {
 
 	struct symbol *sym = he->ms.sym;
-	struct annotation *notes;
+	struct annotated_branch *branch;
 	double ipc = 0.0, coverage = 0.0;
 	char tmp[64];
 
 	if (!sym)
 		return repsep_snprintf(bf, size, "%-*s", width, "-");
 
-	notes = symbol__annotation(sym);
+	branch = symbol__annotation(sym)->branch;
 
-	if (notes->hit_cycles)
-		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+	if (branch && branch->hit_cycles)
+		ipc = branch->hit_insn / ((double)branch->hit_cycles);
 
-	if (notes->total_insn) {
-		coverage = notes->cover_insn * 100.0 /
-			((double)notes->total_insn);
+	if (branch && branch->total_insn) {
+		coverage = branch->cover_insn * 100.0 /
+			((double)branch->total_insn);
 	}
 
 	snprintf(tmp, sizeof(tmp), "%-5.2f [%5.1f%%]", ipc, coverage);
-- 
GitLab


From 2b215ec71b888ec2f3ca86846ce3a7f20b0d5e4d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 3 Nov 2023 12:19:05 -0700
Subject: [PATCH 0014/4076] perf annotate: Move max_coverage from 'struct
 annotation' to 'struct annotated_branch'

The max_coverage field is only used when branch stack info is available
so it'd be natural to move to 'struct annotated_branch'.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231103191907.54531-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c | 7 +++++--
 tools/perf/util/annotate.c    | 2 +-
 tools/perf/util/annotate.h    | 4 +++-
 tools/perf/util/block-range.c | 7 ++++++-
 4 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index aeeb801f1ed7b..a9129b51d5118 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -94,6 +94,7 @@ static void process_basic_block(struct addr_map_symbol *start,
 	struct annotation *notes = sym ? symbol__annotation(sym) : NULL;
 	struct block_range_iter iter;
 	struct block_range *entry;
+	struct annotated_branch *branch;
 
 	/*
 	 * Sanity; NULL isn't executable and the CPU cannot execute backwards
@@ -105,6 +106,8 @@ static void process_basic_block(struct addr_map_symbol *start,
 	if (!block_range_iter__valid(&iter))
 		return;
 
+	branch = annotation__get_branch(notes);
+
 	/*
 	 * First block in range is a branch target.
 	 */
@@ -118,8 +121,8 @@ static void process_basic_block(struct addr_map_symbol *start,
 		entry->coverage++;
 		entry->sym = sym;
 
-		if (notes)
-			notes->max_coverage = max(notes->max_coverage, entry->coverage);
+		if (branch)
+			branch->max_coverage = max(branch->max_coverage, entry->coverage);
 
 	} while (block_range_iter__next(&iter));
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4e40c94c85d10..077a297f4dadc 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -946,7 +946,7 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms,
 	return 0;
 }
 
-static struct annotated_branch *annotation__get_branch(struct annotation *notes)
+struct annotated_branch *annotation__get_branch(struct annotation *notes)
 {
 	if (notes == NULL)
 		return NULL;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 508b93d3dcde9..8497130989538 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -280,10 +280,10 @@ struct annotated_branch {
 	unsigned int		total_insn;
 	unsigned int		cover_insn;
 	struct cyc_hist		*cycles_hist;
+	u64			max_coverage;
 };
 
 struct LOCKABLE annotation {
-	u64			max_coverage;
 	u64			start;
 	struct annotation_options *options;
 	struct annotation_line	**offsets;
@@ -355,6 +355,8 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
 				 struct evsel *evsel);
 
+struct annotated_branch *annotation__get_branch(struct annotation *notes);
+
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 				    struct addr_map_symbol *start,
 				    unsigned cycles);
diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c
index 680e92774d0cd..15c42196c24c8 100644
--- a/tools/perf/util/block-range.c
+++ b/tools/perf/util/block-range.c
@@ -311,6 +311,7 @@ done:
 double block_range__coverage(struct block_range *br)
 {
 	struct symbol *sym;
+	struct annotated_branch *branch;
 
 	if (!br) {
 		if (block_ranges.blocks)
@@ -323,5 +324,9 @@ double block_range__coverage(struct block_range *br)
 	if (!sym)
 		return -1;
 
-	return (double)br->coverage / symbol__annotation(sym)->max_coverage;
+	branch = symbol__annotation(sym)->branch;
+	if (!branch)
+		return -1;
+
+	return (double)br->coverage / branch->max_coverage;
 }
-- 
GitLab


From 0aae4c99c5f8f748c6cb5ca03bb3b3ae8cfb10df Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 3 Nov 2023 12:19:06 -0700
Subject: [PATCH 0015/4076] perf annotate: Move some source code related fields
 from 'struct annotation' to 'struct annotated_source'

Some fields in the 'struct annotation' are only used with 'struct
annotated_source' so better to be moved there in order to reduce memory
consumption for other symbols.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231103191907.54531-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/browsers/annotate.c | 12 ++++++------
 tools/perf/util/annotate.c        | 17 +++++++++--------
 tools/perf/util/annotate.h        | 14 +++++++-------
 3 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d2470f87344d0..1b42db70c9987 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -384,7 +384,7 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 		if (al->idx_asm < offset)
 			offset = al->idx;
 
-		browser->b.nr_entries = notes->nr_entries;
+		browser->b.nr_entries = notes->src->nr_entries;
 		notes->options->hide_src_code = false;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
 		browser->b.top_idx = al->idx - offset;
@@ -402,7 +402,7 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 		if (al->idx_asm < offset)
 			offset = al->idx_asm;
 
-		browser->b.nr_entries = notes->nr_asm_entries;
+		browser->b.nr_entries = notes->src->nr_asm_entries;
 		notes->options->hide_src_code = true;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
 		browser->b.top_idx = al->idx_asm - offset;
@@ -435,7 +435,7 @@ static void ui_browser__init_asm_mode(struct ui_browser *browser)
 {
 	struct annotation *notes = browser__annotation(browser);
 	ui_browser__reset_index(browser);
-	browser->nr_entries = notes->nr_asm_entries;
+	browser->nr_entries = notes->src->nr_asm_entries;
 }
 
 static int sym_title(struct symbol *sym, struct map *map, char *title,
@@ -860,7 +860,7 @@ show_help:
 					   browser->b.height,
 					   browser->b.index,
 					   browser->b.top_idx,
-					   notes->nr_asm_entries);
+					   notes->src->nr_asm_entries);
 		}
 			continue;
 		case K_ENTER:
@@ -991,8 +991,8 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 	ui_helpline__push("Press ESC to exit");
 
-	browser.b.width = notes->max_line_len;
-	browser.b.nr_entries = notes->nr_entries;
+	browser.b.width = notes->src->max_line_len;
+	browser.b.nr_entries = notes->src->nr_entries;
 	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 077a297f4dadc..23e68b1abc2fa 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2825,19 +2825,20 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 void annotation__set_offsets(struct annotation *notes, s64 size)
 {
 	struct annotation_line *al;
+	struct annotated_source *src = notes->src;
 
-	notes->max_line_len = 0;
-	notes->nr_entries = 0;
-	notes->nr_asm_entries = 0;
+	src->max_line_len = 0;
+	src->nr_entries = 0;
+	src->nr_asm_entries = 0;
 
-	list_for_each_entry(al, &notes->src->source, node) {
+	list_for_each_entry(al, &src->source, node) {
 		size_t line_len = strlen(al->line);
 
-		if (notes->max_line_len < line_len)
-			notes->max_line_len = line_len;
-		al->idx = notes->nr_entries++;
+		if (src->max_line_len < line_len)
+			src->max_line_len = line_len;
+		al->idx = src->nr_entries++;
 		if (al->offset != -1) {
-			al->idx_asm = notes->nr_asm_entries++;
+			al->idx_asm = src->nr_asm_entries++;
 			/*
 			 * FIXME: short term bandaid to cope with assembly
 			 * routines that comes with labels in the same column
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 8497130989538..9eb7b6d3fe958 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -268,10 +268,13 @@ struct cyc_hist {
  * returns.
  */
 struct annotated_source {
-	struct list_head   source;
-	int    		   nr_histograms;
-	size_t		   sizeof_sym_hist;
-	struct sym_hist	   *histograms;
+	struct list_head	source;
+	size_t			sizeof_sym_hist;
+	struct sym_hist		*histograms;
+	int    			nr_histograms;
+	int			nr_entries;
+	int			nr_asm_entries;
+	u16			max_line_len;
 };
 
 struct annotated_branch {
@@ -289,9 +292,6 @@ struct LOCKABLE annotation {
 	struct annotation_line	**offsets;
 	int			nr_events;
 	int			max_jump_sources;
-	int			nr_entries;
-	int			nr_asm_entries;
-	u16			max_line_len;
 	struct {
 		u8		addr;
 		u8		jumps;
-- 
GitLab


From b753d48f53f9dcea655d359f028c8adfdd9504b5 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 3 Nov 2023 12:19:07 -0700
Subject: [PATCH 0016/4076] perf annotate: Move offsets array from 'struct
 annotation' to 'struct annotated_source'

The offsets array keeps pointers to 'struct annotation_line' entries
which are available in the 'struct annotated_source'.  Let's move it to
there.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231103191907.54531-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/browsers/annotate.c |  4 ++--
 tools/perf/util/annotate.c        | 20 ++++++++++----------
 tools/perf/util/annotate.h        |  2 +-
 3 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 1b42db70c9987..163f916fff68e 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -188,7 +188,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	 *  name right after the '<' token and probably treating this like a
 	 *  'call' instruction.
 	 */
-	target = notes->offsets[cursor->ops.target.offset];
+	target = notes->src->offsets[cursor->ops.target.offset];
 	if (target == NULL) {
 		ui_helpline__printf("WARN: jump target inconsistency, press 'o', notes->offsets[%#x] = NULL\n",
 				    cursor->ops.target.offset);
@@ -1006,6 +1006,6 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 out_free_offsets:
 	if(not_annotated)
-		zfree(&notes->offsets);
+		zfree(&notes->src->offsets);
 	return ret;
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 23e68b1abc2fa..9b68b8e3791ca 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1075,7 +1075,7 @@ static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64
 	u64 offset;
 
 	for (offset = start; offset <= end; offset++) {
-		if (notes->offsets[offset])
+		if (notes->src->offsets[offset])
 			n_insn++;
 	}
 	return n_insn;
@@ -1105,7 +1105,7 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 			return;
 
 		for (offset = start; offset <= end; offset++) {
-			struct annotation_line *al = notes->offsets[offset];
+			struct annotation_line *al = notes->src->offsets[offset];
 
 			if (al && al->cycles && al->cycles->ipc == 0.0) {
 				al->cycles->ipc = ipc;
@@ -1143,7 +1143,7 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 		if (ch && ch->cycles) {
 			struct annotation_line *al;
 
-			al = notes->offsets[offset];
+			al = notes->src->offsets[offset];
 			if (al && al->cycles == NULL) {
 				al->cycles = zalloc(sizeof(*al->cycles));
 				if (al->cycles == NULL) {
@@ -1166,7 +1166,7 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 			struct cyc_hist *ch = &notes->branch->cycles_hist[offset];
 
 			if (ch && ch->cycles) {
-				struct annotation_line *al = notes->offsets[offset];
+				struct annotation_line *al = notes->src->offsets[offset];
 				if (al)
 					zfree(&al->cycles);
 			}
@@ -2800,7 +2800,7 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 		return;
 
 	for (offset = 0; offset < size; ++offset) {
-		struct annotation_line *al = notes->offsets[offset];
+		struct annotation_line *al = notes->src->offsets[offset];
 		struct disasm_line *dl;
 
 		dl = disasm_line(al);
@@ -2808,7 +2808,7 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 		if (!disasm_line__is_valid_local_jump(dl, sym))
 			continue;
 
-		al = notes->offsets[dl->ops.target.offset];
+		al = notes->src->offsets[dl->ops.target.offset];
 
 		/*
 		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
@@ -2847,7 +2847,7 @@ void annotation__set_offsets(struct annotation *notes, s64 size)
 			 * E.g. copy_user_generic_unrolled
  			 */
 			if (al->offset < size)
-				notes->offsets[al->offset] = al;
+				notes->src->offsets[al->offset] = al;
 		} else
 			al->idx_asm = -1;
 	}
@@ -3280,8 +3280,8 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	size_t size = symbol__size(sym);
 	int nr_pcnt = 1, err;
 
-	notes->offsets = zalloc(size * sizeof(struct annotation_line *));
-	if (notes->offsets == NULL)
+	notes->src->offsets = zalloc(size * sizeof(struct annotation_line *));
+	if (notes->src->offsets == NULL)
 		return ENOMEM;
 
 	if (evsel__is_group_event(evsel))
@@ -3311,7 +3311,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	return 0;
 
 out_free_offsets:
-	zfree(&notes->offsets);
+	zfree(&notes->src->offsets);
 	return err;
 }
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 9eb7b6d3fe958..de59c1aff08e8 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -271,6 +271,7 @@ struct annotated_source {
 	struct list_head	source;
 	size_t			sizeof_sym_hist;
 	struct sym_hist		*histograms;
+	struct annotation_line	**offsets;
 	int    			nr_histograms;
 	int			nr_entries;
 	int			nr_asm_entries;
@@ -289,7 +290,6 @@ struct annotated_branch {
 struct LOCKABLE annotation {
 	u64			start;
 	struct annotation_options *options;
-	struct annotation_line	**offsets;
 	int			nr_events;
 	int			max_jump_sources;
 	struct {
-- 
GitLab


From 4a5aaaf308b91e3da21c3b8f7e78dc5a256d9324 Mon Sep 17 00:00:00 2001
From: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Date: Mon, 30 Oct 2023 15:58:25 +0800
Subject: [PATCH 0017/4076] perf tests attr: Fix spelling mistake "whic" to
 "which"

There is a spelling mistake, Please fix it.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-janitors@vger.kernel.org
Link: https://lore.kernel.org/r/20231030075825.3701-1-zhaimingbing@cmss.chinamobile.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/attr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 61186d0d1cfa1..97e1bdd6ec0e9 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -188,7 +188,7 @@ static int test__attr(struct test_suite *test __maybe_unused, int subtest __mayb
 	if (perf_pmus__num_core_pmus() > 1) {
 		/*
 		 * TODO: Attribute tests hard code the PMU type. If there are >1
-		 * core PMU then each PMU will have a different type whic
+		 * core PMU then each PMU will have a different type which
 		 * requires additional support.
 		 */
 		pr_debug("Skip test on hybrid systems");
-- 
GitLab


From 36c70e44a37b84cbb4094bf6f5cdb01cfd6659df Mon Sep 17 00:00:00 2001
From: Yang Jihong <yangjihong1@huawei.com>
Date: Mon, 30 Oct 2023 11:14:38 +0000
Subject: [PATCH 0018/4076] perf tools: Add the python_ext_build directory to
 .gitignore

`python_ext_build` is the build directory for python.so, ignore it for
cleaner git status.

Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231030111438.1357962-2-yangjihong1@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index f533e76fb4800..ee5c14f3b8b19 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -49,3 +49,4 @@ libtraceevent/
 libtraceevent_plugins/
 fixdep
 Documentation/doc.dep
+python_ext_build/
-- 
GitLab


From b861fd7e0efc4dc2376e7212f59a9b32d1383c00 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 6 Nov 2023 10:16:27 +0100
Subject: [PATCH 0019/4076] perf tests offcpu: Adjust test case perf record
 offcpu profiling tests for s390

On s390 using linux-next the test case:

    87: perf record offcpu profiling tests

fails. The root cause is this command

  # ./perf  record --off-cpu -e dummy -- ./perf bench sched messaging -l 10
  # Running 'sched/messaging' benchmark:
  # 20 sender and receiver processes per group
  # 10 groups == 400 processes run

     Total time: 0.231 [sec]
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.077 MB perf.data (401 samples) ]
  #

It does not generate 800+ sample entries, on s390 usually around
40[1-9], sometimes a few more, but never more than 450. The higher the
number of CPUs the lower the number of samples.

Looking at function chain:

  bench_sched_messaging()
  +--> group()

the senders and receiver threads are created. The senders and receivers
call function ready() which writes one bytes and wait for a reply using
poll system() call.

As context switches are counted, the function ready() will trigger a
context switch when no input data is available after the write system
call. The write system call does not trigger context switches when the
data size is small. And writing 1000 bytes (10 iterations with
100 bytes) is not much and certainly won't block.

The 400+ context switch on s390 occur when the some receiver/sender
threads call ready() and wait for the response from function
bench_sched_messaging() being kicked off.

Lower the number of expected context switches to 400 to succeed on s390.

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Co-developed-by: Ilya Leoshkevich <iii@linux.ibm.com>
Link: https://lore.kernel.org/r/20231106091627.2022530-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record_offcpu.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
index a1ef8f0d2b5cc..67c925f3a15aa 100755
--- a/tools/perf/tests/shell/record_offcpu.sh
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -77,9 +77,9 @@ test_offcpu_child() {
     err=1
     return
   fi
-  # each process waits for read and write, so it should be more than 800 events
+  # each process waits at least for poll, so it should be more than 400 events
   if ! perf report -i ${perfdata} -s comm -q -n -t ';' --percent-limit=90 | \
-    awk -F ";" '{ if (NF > 3 && int($3) < 800) exit 1; }'
+    awk -F ";" '{ if (NF > 3 && int($3) < 400) exit 1; }'
   then
     echo "Child task off-cpu test [Failed invalid output]"
     err=1
-- 
GitLab


From 33ce9fc4f8ddba30b7040bd01cea11080f40b344 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 6 Nov 2023 15:10:48 +0000
Subject: [PATCH 0020/4076] perf test: Add option to change objdump binary

All of the other Perf subcommands that use objdump have an option to
specify the binary, so add the same option to 'perf test'.

This is useful if you have built the kernel with a different toolchain
to the system one, where the system objdump may fail to disassemble
vmlinux.

Now this can be fixed with something like this:

  $ perf test --objdump llvm-objdump "object code reading"

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Tom Rix <trix@redhat.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20231106151051.129440-2-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/builtin-test.c | 3 +++
 tools/perf/tests/code-reading.c | 2 +-
 tools/perf/tests/tests.h        | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index cb6f1dd00dc48..a8d17dd505888 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -32,6 +32,7 @@
 
 static bool dont_fork;
 const char *dso_to_test;
+const char *test_objdump_path = "objdump";
 
 /*
  * List of architecture specific tests. Not a weak symbol as the array length is
@@ -529,6 +530,8 @@ int cmd_test(int argc, const char **argv)
 		    "Do not fork for testcase"),
 	OPT_STRING('w', "workload", &workload, "work", "workload to run for testing"),
 	OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"),
+	OPT_STRING(0, "objdump", &test_objdump_path, "path",
+		   "objdump binary to use for disassembly and annotations"),
 	OPT_END()
 	};
 	const char * const test_subcommands[] = { "list", NULL };
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index d6e845c579023..8620146d03783 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -185,7 +185,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 	int ret;
 
 	fmt = "%s -z -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s";
-	ret = snprintf(cmd, sizeof(cmd), fmt, "objdump", addr, addr + len,
+	ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path, addr, addr + len,
 		       filename);
 	if (ret <= 0 || (size_t)ret >= sizeof(cmd))
 		return -1;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index b394f3ac2d667..dad3d7414142d 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -207,5 +207,6 @@ DECLARE_WORKLOAD(brstack);
 DECLARE_WORKLOAD(datasym);
 
 extern const char *dso_to_test;
+extern const char *test_objdump_path;
 
 #endif /* TESTS_H */
-- 
GitLab


From 6aad765d10c5cd8a62b258c359bae643ab2d45da Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 6 Nov 2023 15:10:49 +0000
Subject: [PATCH 0021/4076] perf test: Add support for setting objdump binary
 via perf config

Add a 'perf config' variable that does the same thing as "perf test
--objdump <x>".

Also update the man page.

Committer testing:

  # perf config test.objdump
  # perf test "object code reading"
   26: Object code reading                                             : Ok
  # perf config test.objdump=blah
  # perf config test.objdump
  test.objdump=blah
  # perf test "object code reading"
   26: Object code reading                                             : FAILED!
  # perf test -v "object code reading"
   26: Object code reading                                             :
  --- start ---
  test child forked, pid 600599
  Looking at the vmlinux_path (8 entries long)
  Using /proc/kcore for kernel data
  Using /proc/kallsyms for symbols
  Parsing event 'cycles'
  Using CPUID AuthenticAMD-25-21-0
  mmap size 528384B
  Reading object code for memory address: 0x4d9a02
  File is: /home/acme/bin/perf
  On file address is: 0xd9a02
  Objdump command is: blah -z -d --start-address=0x4d9a02 --stop-address=0x4d9a82 /home/acme/bin/perf
  objdump read too few bytes: 128
  Bytes read differ from those read by objdump
  buf1 (dso):
  0x48 0x85 0xff 0x74 0x29 0xe8 0x94 0xdf 0x07 0x00 0x8b 0x73 0x1c 0x48 0x8b 0x43
  0x08 0xeb 0xa5 0x0f 0x1f 0x00 0x48 0x8b 0x45 0xe8 0x64 0x48 0x2b 0x04 0x25 0x28
  0x00 0x00 0x00 0x75 0x0f 0x48 0x8b 0x5d 0xf8 0xc9 0xc3 0x0f 0x1f 0x00 0x48 0x8b
  0x43 0x08 0xeb 0x84 0xe8 0xc5 0x3e 0xf3 0xff 0x0f 0x1f 0x44 0x00 0x00 0x55 0x48
  0x89 0xe5 0x41 0x56 0x41 0x55 0x49 0x89 0xd5 0x41 0x54 0x49 0x89 0xfc 0x53 0x48
  0x89 0xf3 0x48 0x83 0xec 0x30 0x48 0x8b 0x7e 0x20 0x64 0x48 0x8b 0x04 0x25 0x28
  0x00 0x00 0x00 0x48 0x89 0x45 0xd8 0x31 0xc0 0x48 0x89 0x75 0xb0 0x48 0xc7 0x45
  0xb8 0x00 0x00 0x00 0x00 0x48 0xc7 0x45 0xc0 0x00 0x00 0x00 0x00 0xe8 0xad 0xfa

  buf2 (objdump):
  0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
  0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
  0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
  0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
  0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
  0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
  0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
  0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00

  test child finished with -1
  ---- end ----
  Object code reading: FAILED!
  # perf config test.objdump=/usr/bin/objdump
  # perf config test.objdump
  test.objdump=/usr/bin/objdump
  # perf test "object code reading"
   26: Object code reading                                             : Ok
  #

Signed-off-by: James Clark <james.clark@arm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Tom Rix <trix@redhat.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20231106151051.129440-3-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-config.txt |  4 ++++
 tools/perf/tests/builtin-test.c          | 12 ++++++++++++
 2 files changed, 16 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 0b4e79dbd3f68..16398babd1ef5 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -722,6 +722,10 @@ session-<NAME>.*::
 		Defines new record session for daemon. The value is record's
 		command line without the 'record' keyword.
 
+test.*::
+
+	test.objdump::
+		objdump binary to use for disassembly and annotations.
 
 SEE ALSO
 --------
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index a8d17dd505888..113e92119e1d1 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -14,6 +14,7 @@
 #include <sys/wait.h>
 #include <sys/stat.h>
 #include "builtin.h"
+#include "config.h"
 #include "hist.h"
 #include "intlist.h"
 #include "tests.h"
@@ -514,6 +515,15 @@ static int run_workload(const char *work, int argc, const char **argv)
 	return -1;
 }
 
+static int perf_test__config(const char *var, const char *value,
+			     void *data __maybe_unused)
+{
+	if (!strcmp(var, "test.objdump"))
+		test_objdump_path = value;
+
+	return 0;
+}
+
 int cmd_test(int argc, const char **argv)
 {
 	const char *test_usage[] = {
@@ -541,6 +551,8 @@ int cmd_test(int argc, const char **argv)
         if (ret < 0)
                 return ret;
 
+	perf_config(perf_test__config, NULL);
+
 	/* Unbuffered output */
 	setvbuf(stdout, NULL, _IONBF, 0);
 
-- 
GitLab


From 6512b6aa237db36d881a81cc312db39668e61853 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 2 Nov 2023 10:56:54 -0700
Subject: [PATCH 0022/4076] perf bpf: Don't synthesize BPF events when disabled

If BPF sideband events are disabled on the command line, don't
synthesize BPF events too.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Song Liu <song@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231102175735.2272696-13-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf-event.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 38fcf3ba5749d..830711cae30d3 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -386,6 +386,9 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 	int err;
 	int fd;
 
+	if (opts->no_bpf_event)
+		return 0;
+
 	event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
 	if (!event)
 		return -1;
-- 
GitLab


From a399ee6773d6a0203f9bd764f8bd9d978878cef1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 9 Nov 2023 16:34:09 -0300
Subject: [PATCH 0023/4076] tools: Disable __packed attribute compiler warning
 due to -Werror=attributes

Noticed on several perf tools cross build test containers:

  [perfbuilder@five ~]$ grep FAIL ~/dm.log/summary
    19    10.18 debian:experimental-x-mips    : FAIL gcc version 12.3.0 (Debian 12.3.0-6)
    20    11.21 debian:experimental-x-mips64  : FAIL gcc version 12.3.0 (Debian 12.3.0-6)
    21    11.30 debian:experimental-x-mipsel  : FAIL gcc version 12.3.0 (Debian 12.3.0-6)
    37    12.07 ubuntu:18.04-x-arm            : FAIL gcc version 7.5.0 (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04)
    42    11.91 ubuntu:18.04-x-riscv64        : FAIL gcc version 7.5.0 (Ubuntu 7.5.0-3ubuntu1~18.04)
    44    13.17 ubuntu:18.04-x-sh4            : FAIL gcc version 7.5.0 (Ubuntu 7.5.0-3ubuntu1~18.04)
    45    12.09 ubuntu:18.04-x-sparc64        : FAIL gcc version 7.5.0 (Ubuntu 7.5.0-3ubuntu1~18.04)
  [perfbuilder@five ~]$

  In file included from util/intel-pt-decoder/intel-pt-pkt-decoder.c:10:
  /tmp/perf-6.6.0-rc1/tools/include/asm-generic/unaligned.h: In function 'get_unaligned_le16':
  /tmp/perf-6.6.0-rc1/tools/include/asm-generic/unaligned.h:13:29: error: packed attribute causes inefficient alignment for 'x' [-Werror=attributes]
     13 |         const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);      \
        |                             ^
  /tmp/perf-6.6.0-rc1/tools/include/asm-generic/unaligned.h:27:28: note: in expansion of macro '__get_unaligned_t'
     27 |         return le16_to_cpu(__get_unaligned_t(__le16, p));
        |                            ^~~~~~~~~~~~~~~~~

This comes from the kernel, where the -Wattributes and -Wpacked isn't
used, -Wpacked is already disabled, do it for the attributes as well.

Fixes: a91c987254651443 ("perf tools: Add get_unaligned_leNN()")
Suggested-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/7c5b626c-1de9-4c12-a781-e44985b4a797@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/asm-generic/unaligned.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h
index 156743d399aed..2fd551915c202 100644
--- a/tools/include/asm-generic/unaligned.h
+++ b/tools/include/asm-generic/unaligned.h
@@ -8,6 +8,7 @@
  */
 #pragma GCC diagnostic push
 #pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
 
 #define __get_unaligned_t(type, ptr) ({						\
 	const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);	\
-- 
GitLab


From dd678532f913c1a742f1a2add6adacfb7ae2b166 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Tue, 7 Nov 2023 14:03:31 +0530
Subject: [PATCH 0024/4076] perf header: Additional note on AMD IBS for
 max_precise pmu cap

x86 core PMU exposes supported maximum precision level via max_precise
PMU capability. Although, AMD core PMU does not support precise mode,
certain core PMU events with precise_ip > 0 are allowed and forwarded to
IBS OP PMU.

Display a note about this in the 'perf report' header output and
document the details in the perf-list man page.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ross Zwisler <zwisler@chromium.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231107083331.901-2-ravi.bangoria@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-list.txt | 12 +++++++-----
 tools/perf/util/env.c                  | 18 ++++++++++++++++++
 tools/perf/util/env.h                  |  2 ++
 tools/perf/util/header.c               |  8 ++++++++
 4 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index d5f78e125efed..1b90575ee3c84 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -81,11 +81,13 @@ For Intel systems precise event sampling is implemented with PEBS
 which supports up to precise-level 2, and precise level 3 for
 some special cases
 
-On AMD systems it is implemented using IBS (up to precise-level 2).
-The precise modifier works with event types 0x76 (cpu-cycles, CPU
-clocks not halted) and 0xC1 (micro-ops retired). Both events map to
-IBS execution sampling (IBS op) with the IBS Op Counter Control bit
-(IbsOpCntCtl) set respectively (see the
+On AMD systems it is implemented using IBS OP (up to precise-level 2).
+Unlike Intel PEBS which provides levels of precision, AMD core pmu is
+inherently non-precise and IBS is inherently precise. (i.e. ibs_op//,
+ibs_op//p, ibs_op//pp and ibs_op//ppp are all same). The precise modifier
+works with event types 0x76 (cpu-cycles, CPU clocks not halted) and 0xC1
+(micro-ops retired). Both events map to IBS execution sampling (IBS op)
+with the IBS Op Counter Control bit (IbsOpCntCtl) set respectively (see the
 Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS)
 section of the [AMD Processor Programming Reference (PPR)] relevant to the
 family, model and stepping of the processor being used).
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 44140b7f596a3..cbc18b22ace52 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -531,6 +531,24 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
 	return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1;
 }
 
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name)
+{
+	char *pmu_mapping = env->pmu_mappings, *colon;
+
+	for (int i = 0; i < env->nr_pmu_mappings; ++i) {
+		if (strtoul(pmu_mapping, &colon, 0) == ULONG_MAX || *colon != ':')
+			goto out_error;
+
+		pmu_mapping = colon + 1;
+		if (strcmp(pmu_mapping, pmu_name) == 0)
+			return true;
+
+		pmu_mapping += strlen(pmu_mapping) + 1;
+	}
+out_error:
+	return false;
+}
+
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
 			     const char *cap)
 {
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 48d7f8759a2a7..94596ff124d54 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -179,4 +179,6 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
 			     const char *cap);
+
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index eeb96a1b63a7c..1c687b5789c0f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2145,6 +2145,14 @@ static void print_pmu_caps(struct feat_fd *ff, FILE *fp)
 		__print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps,
 				 pmu_caps->pmu_name);
 	}
+
+	if (strcmp(perf_env__arch(&ff->ph->env), "x86") == 0 &&
+	    perf_env__has_pmu_mapping(&ff->ph->env, "ibs_op")) {
+		char *max_precise = perf_env__find_pmu_cap(&ff->ph->env, "cpu", "max_precise");
+
+		if (max_precise != NULL && atoi(max_precise) == 0)
+			fprintf(fp, "# AMD systems uses ibs_op// PMU for some precise events, e.g.: cycles:p, see the 'perf list' man page for further details.\n");
+	}
 }
 
 static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
-- 
GitLab


From ded8c48497b825f15436048e8ea3a731a3f7dece Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:20 -0800
Subject: [PATCH 0025/4076] perf annotate: Pass "-l" option to objdump
 conditionally

The "-l" option is to print line numbers in the objdump output.  perf
annotate TUI only can show the line numbers later but it causes big slow
downs for the kernel binary.

Similarly, showing source code also takes a long time and it already has
an option to control it.

  $ time objdump ... -d -S -C vmlinux > /dev/null
  real	0m3.474s
  user	0m3.047s
  sys	0m0.428s

  $ time objdump ... -d -l -C vmlinux > /dev/null
  real	0m1.796s
  user	0m1.459s
  sys	0m0.338s

  $ time objdump ... -d -C vmlinux > /dev/null
  real	0m0.051s
  user	0m0.036s
  sys	0m0.016s

As it's not needed for data type profiling, let's make it conditional so
that it can skip the unnecessary work.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 9b68b8e3791ca..118195c787b94 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2144,12 +2144,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s %s %c%s%c %s%s -C \"$1\"",
+		 " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
+		 opts->show_linenr ? "-l" : "",
 		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
 		 opts->annotate_src ? "-S" : "",
 		 opts->prefix ? "--prefix " : "",
-- 
GitLab


From fb7fd2a14a503b9a23fe10303923fc0605c22288 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:21 -0800
Subject: [PATCH 0026/4076] perf annotate: Move raw_comment and raw_func_start
 fields out of 'struct ins_operands'

Thoese two fields are used only for the jump_ops, so move them into the
union to save some bytes.  Also add jump__delete() callback not to free
the fields as they didn't allocate new strings.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: WANG Rui <wangrui@loongson.cn>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../perf/arch/loongarch/annotate/instructions.c |  6 +++---
 tools/perf/util/annotate.c                      | 17 +++++++++++++----
 tools/perf/util/annotate.h                      |  6 ++++--
 3 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c
index 98e19c5366acf..21cc7e4149f72 100644
--- a/tools/perf/arch/loongarch/annotate/instructions.c
+++ b/tools/perf/arch/loongarch/annotate/instructions.c
@@ -61,10 +61,10 @@ static int loongarch_jump__parse(struct arch *arch, struct ins_operands *ops, st
 	const char *c = strchr(ops->raw, '#');
 	u64 start, end;
 
-	ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
-	ops->raw_func_start = strchr(ops->raw, '<');
+	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	ops->jump.raw_func_start = strchr(ops->raw, '<');
 
-	if (ops->raw_func_start && c > ops->raw_func_start)
+	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
 		c = NULL;
 
 	if (c++ != NULL)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 118195c787b94..3364edf30f50e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -340,10 +340,10 @@ bool ins__is_call(const struct ins *ins)
  */
 static inline const char *validate_comma(const char *c, struct ins_operands *ops)
 {
-	if (ops->raw_comment && c > ops->raw_comment)
+	if (ops->jump.raw_comment && c > ops->jump.raw_comment)
 		return NULL;
 
-	if (ops->raw_func_start && c > ops->raw_func_start)
+	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
 		return NULL;
 
 	return c;
@@ -359,8 +359,8 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s
 	const char *c = strchr(ops->raw, ',');
 	u64 start, end;
 
-	ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
-	ops->raw_func_start = strchr(ops->raw, '<');
+	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	ops->jump.raw_func_start = strchr(ops->raw, '<');
 
 	c = validate_comma(c, ops);
 
@@ -462,7 +462,16 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			 ops->target.offset);
 }
 
+static void jump__delete(struct ins_operands *ops __maybe_unused)
+{
+	/*
+	 * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
+	 * raw string, don't free them.
+	 */
+}
+
 static struct ins_ops jump_ops = {
+	.free	   = jump__delete,
 	.parse	   = jump__parse,
 	.scnprintf = jump__scnprintf,
 };
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index de59c1aff08e8..bc8b95e8b1be1 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -31,8 +31,6 @@ struct ins {
 
 struct ins_operands {
 	char	*raw;
-	char	*raw_comment;
-	char	*raw_func_start;
 	struct {
 		char	*raw;
 		char	*name;
@@ -52,6 +50,10 @@ struct ins_operands {
 			struct ins	    ins;
 			struct ins_operands *ops;
 		} locked;
+		struct {
+			char	*raw_comment;
+			char	*raw_func_start;
+		} jump;
 	};
 };
 
-- 
GitLab


From 6f1b6291cf73cb3223f6fb9ec16862a5fe7ed957 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:22 -0800
Subject: [PATCH 0027/4076] perf tools: Add util/debuginfo.[ch] files

Split debuginfo data structure and related functions into a separate
file so that it can be used by other components than the probe-finder.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build          |   1 +
 tools/perf/util/debuginfo.c    | 205 +++++++++++++++++++++++++++++++++
 tools/perf/util/debuginfo.h    |  64 ++++++++++
 tools/perf/util/probe-finder.c | 193 +------------------------------
 tools/perf/util/probe-finder.h |  19 +--
 5 files changed, 272 insertions(+), 210 deletions(-)
 create mode 100644 tools/perf/util/debuginfo.c
 create mode 100644 tools/perf/util/debuginfo.h

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 96058f949ec9f..73e3f194f949f 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -195,6 +195,7 @@ endif
 perf-$(CONFIG_DWARF) += probe-finder.o
 perf-$(CONFIG_DWARF) += dwarf-aux.o
 perf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_DWARF) += debuginfo.o
 
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c
new file mode 100644
index 0000000000000..19acf4775d358
--- /dev/null
+++ b/tools/perf/util/debuginfo.c
@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * DWARF debug information handling code.  Copied from probe-finder.c.
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/zalloc.h>
+
+#include "build-id.h"
+#include "dso.h"
+#include "debug.h"
+#include "debuginfo.h"
+#include "symbol.h"
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+#include <elfutils/debuginfod.h>
+#endif
+
+/* Dwarf FL wrappers */
+static char *debuginfo_path;	/* Currently dummy */
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.debuginfo_path = &debuginfo_path,
+
+	.section_address = dwfl_offline_section_address,
+
+	/* We use this table for core files too.  */
+	.find_elf = dwfl_build_id_find_elf,
+};
+
+/* Get a Dwarf from offline image */
+static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
+					 const char *path)
+{
+	GElf_Addr dummy;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	dbg->dwfl = dwfl_begin(&offline_callbacks);
+	if (!dbg->dwfl)
+		goto error;
+
+	dwfl_report_begin(dbg->dwfl);
+	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
+	if (!dbg->mod)
+		goto error;
+
+	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
+	if (!dbg->dbg)
+		goto error;
+
+	dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
+
+	dwfl_report_end(dbg->dwfl, NULL, NULL);
+
+	return 0;
+error:
+	if (dbg->dwfl)
+		dwfl_end(dbg->dwfl);
+	else
+		close(fd);
+	memset(dbg, 0, sizeof(*dbg));
+
+	return -ENOENT;
+}
+
+static struct debuginfo *__debuginfo__new(const char *path)
+{
+	struct debuginfo *dbg = zalloc(sizeof(*dbg));
+	if (!dbg)
+		return NULL;
+
+	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
+		zfree(&dbg);
+	if (dbg)
+		pr_debug("Open Debuginfo file: %s\n", path);
+	return dbg;
+}
+
+enum dso_binary_type distro_dwarf_types[] = {
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+struct debuginfo *debuginfo__new(const char *path)
+{
+	enum dso_binary_type *type;
+	char buf[PATH_MAX], nil = '\0';
+	struct dso *dso;
+	struct debuginfo *dinfo = NULL;
+	struct build_id bid;
+
+	/* Try to open distro debuginfo files */
+	dso = dso__new(path);
+	if (!dso)
+		goto out;
+
+	/* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */
+	if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0)
+		dso__set_build_id(dso, &bid);
+
+	for (type = distro_dwarf_types;
+	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
+	     type++) {
+		if (dso__read_binary_type_filename(dso, *type, &nil,
+						   buf, PATH_MAX) < 0)
+			continue;
+		dinfo = __debuginfo__new(buf);
+	}
+	dso__put(dso);
+
+out:
+	/* if failed to open all distro debuginfo, open given binary */
+	return dinfo ? : __debuginfo__new(path);
+}
+
+void debuginfo__delete(struct debuginfo *dbg)
+{
+	if (dbg) {
+		if (dbg->dwfl)
+			dwfl_end(dbg->dwfl);
+		free(dbg);
+	}
+}
+
+/* For the kernel module, we need a special code to get a DIE */
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+				bool adjust_offset)
+{
+	int n, i;
+	Elf32_Word shndx;
+	Elf_Scn *scn;
+	Elf *elf;
+	GElf_Shdr mem, *shdr;
+	const char *p;
+
+	elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
+	if (!elf)
+		return -EINVAL;
+
+	/* Get the number of relocations */
+	n = dwfl_module_relocations(dbg->mod);
+	if (n < 0)
+		return -ENOENT;
+	/* Search the relocation related .text section */
+	for (i = 0; i < n; i++) {
+		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
+		if (strcmp(p, ".text") == 0) {
+			/* OK, get the section header */
+			scn = elf_getscn(elf, shndx);
+			if (!scn)
+				return -ENOENT;
+			shdr = gelf_getshdr(scn, &mem);
+			if (!shdr)
+				return -ENOENT;
+			*offs = shdr->sh_addr;
+			if (adjust_offset)
+				*offs -= shdr->sh_offset;
+		}
+	}
+	return 0;
+}
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+int get_source_from_debuginfod(const char *raw_path,
+			       const char *sbuild_id, char **new_path)
+{
+	debuginfod_client *c = debuginfod_begin();
+	const char *p = raw_path;
+	int fd;
+
+	if (!c)
+		return -ENOMEM;
+
+	fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id,
+				0, p, new_path);
+	pr_debug("Search %s from debuginfod -> %d\n", p, fd);
+	if (fd >= 0)
+		close(fd);
+	debuginfod_end(c);
+	if (fd < 0) {
+		pr_debug("Failed to find %s in debuginfod (%s)\n",
+			raw_path, sbuild_id);
+		return -ENOENT;
+	}
+	pr_debug("Got a source %s\n", *new_path);
+
+	return 0;
+}
+#endif /* HAVE_DEBUGINFOD_SUPPORT */
diff --git a/tools/perf/util/debuginfo.h b/tools/perf/util/debuginfo.h
new file mode 100644
index 0000000000000..4d65b8c605fc5
--- /dev/null
+++ b/tools/perf/util/debuginfo.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _PERF_DEBUGINFO_H
+#define _PERF_DEBUGINFO_H
+
+#include <errno.h>
+#include <linux/compiler.h>
+
+#ifdef HAVE_DWARF_SUPPORT
+
+#include "dwarf-aux.h"
+
+/* debug information structure */
+struct debuginfo {
+	Dwarf		*dbg;
+	Dwfl_Module	*mod;
+	Dwfl		*dwfl;
+	Dwarf_Addr	bias;
+	const unsigned char	*build_id;
+};
+
+/* This also tries to open distro debuginfo */
+struct debuginfo *debuginfo__new(const char *path);
+void debuginfo__delete(struct debuginfo *dbg);
+
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+			       bool adjust_offset);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+/* dummy debug information structure */
+struct debuginfo {
+};
+
+static inline struct debuginfo *debuginfo__new(const char *path __maybe_unused)
+{
+	return NULL;
+}
+
+static inline void debuginfo__delete(struct debuginfo *dbg __maybe_unused)
+{
+}
+
+static inline int debuginfo__get_text_offset(struct debuginfo *dbg __maybe_unused,
+					     Dwarf_Addr *offs __maybe_unused,
+					     bool adjust_offset __maybe_unused)
+{
+	return -EINVAL;
+}
+
+#endif /* HAVE_DWARF_SUPPORT */
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+int get_source_from_debuginfod(const char *raw_path, const char *sbuild_id,
+			       char **new_path);
+#else /* HAVE_DEBUGINFOD_SUPPORT */
+static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused,
+					     const char *sbuild_id __maybe_unused,
+					     char **new_path __maybe_unused)
+{
+	return -ENOTSUP;
+}
+#endif /* HAVE_DEBUGINFOD_SUPPORT */
+
+#endif /* _PERF_DEBUGINFO_H */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index f171360b0ef4d..8d3dd85f9ff4c 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -23,6 +23,7 @@
 #include "event.h"
 #include "dso.h"
 #include "debug.h"
+#include "debuginfo.h"
 #include "intlist.h"
 #include "strbuf.h"
 #include "strlist.h"
@@ -31,128 +32,9 @@
 #include "probe-file.h"
 #include "string2.h"
 
-#ifdef HAVE_DEBUGINFOD_SUPPORT
-#include <elfutils/debuginfod.h>
-#endif
-
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS	64
 
-/* Dwarf FL wrappers */
-static char *debuginfo_path;	/* Currently dummy */
-
-static const Dwfl_Callbacks offline_callbacks = {
-	.find_debuginfo = dwfl_standard_find_debuginfo,
-	.debuginfo_path = &debuginfo_path,
-
-	.section_address = dwfl_offline_section_address,
-
-	/* We use this table for core files too.  */
-	.find_elf = dwfl_build_id_find_elf,
-};
-
-/* Get a Dwarf from offline image */
-static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
-					 const char *path)
-{
-	GElf_Addr dummy;
-	int fd;
-
-	fd = open(path, O_RDONLY);
-	if (fd < 0)
-		return fd;
-
-	dbg->dwfl = dwfl_begin(&offline_callbacks);
-	if (!dbg->dwfl)
-		goto error;
-
-	dwfl_report_begin(dbg->dwfl);
-	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
-	if (!dbg->mod)
-		goto error;
-
-	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
-	if (!dbg->dbg)
-		goto error;
-
-	dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
-
-	dwfl_report_end(dbg->dwfl, NULL, NULL);
-
-	return 0;
-error:
-	if (dbg->dwfl)
-		dwfl_end(dbg->dwfl);
-	else
-		close(fd);
-	memset(dbg, 0, sizeof(*dbg));
-
-	return -ENOENT;
-}
-
-static struct debuginfo *__debuginfo__new(const char *path)
-{
-	struct debuginfo *dbg = zalloc(sizeof(*dbg));
-	if (!dbg)
-		return NULL;
-
-	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
-		zfree(&dbg);
-	if (dbg)
-		pr_debug("Open Debuginfo file: %s\n", path);
-	return dbg;
-}
-
-enum dso_binary_type distro_dwarf_types[] = {
-	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
-	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
-	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
-	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
-	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
-	DSO_BINARY_TYPE__NOT_FOUND,
-};
-
-struct debuginfo *debuginfo__new(const char *path)
-{
-	enum dso_binary_type *type;
-	char buf[PATH_MAX], nil = '\0';
-	struct dso *dso;
-	struct debuginfo *dinfo = NULL;
-	struct build_id bid;
-
-	/* Try to open distro debuginfo files */
-	dso = dso__new(path);
-	if (!dso)
-		goto out;
-
-	/* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */
-	if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0)
-		dso__set_build_id(dso, &bid);
-
-	for (type = distro_dwarf_types;
-	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
-	     type++) {
-		if (dso__read_binary_type_filename(dso, *type, &nil,
-						   buf, PATH_MAX) < 0)
-			continue;
-		dinfo = __debuginfo__new(buf);
-	}
-	dso__put(dso);
-
-out:
-	/* if failed to open all distro debuginfo, open given binary */
-	return dinfo ? : __debuginfo__new(path);
-}
-
-void debuginfo__delete(struct debuginfo *dbg)
-{
-	if (dbg) {
-		if (dbg->dwfl)
-			dwfl_end(dbg->dwfl);
-		free(dbg);
-	}
-}
-
 /*
  * Probe finder related functions
  */
@@ -1677,44 +1559,6 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 	return (ret < 0) ? ret : af.nvls;
 }
 
-/* For the kernel module, we need a special code to get a DIE */
-int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
-				bool adjust_offset)
-{
-	int n, i;
-	Elf32_Word shndx;
-	Elf_Scn *scn;
-	Elf *elf;
-	GElf_Shdr mem, *shdr;
-	const char *p;
-
-	elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
-	if (!elf)
-		return -EINVAL;
-
-	/* Get the number of relocations */
-	n = dwfl_module_relocations(dbg->mod);
-	if (n < 0)
-		return -ENOENT;
-	/* Search the relocation related .text section */
-	for (i = 0; i < n; i++) {
-		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
-		if (strcmp(p, ".text") == 0) {
-			/* OK, get the section header */
-			scn = elf_getscn(elf, shndx);
-			if (!scn)
-				return -ENOENT;
-			shdr = gelf_getshdr(scn, &mem);
-			if (!shdr)
-				return -ENOENT;
-			*offs = shdr->sh_addr;
-			if (adjust_offset)
-				*offs -= shdr->sh_offset;
-		}
-	}
-	return 0;
-}
-
 /* Reverse search */
 int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 				struct perf_probe_point *ppt)
@@ -2009,41 +1853,6 @@ found:
 	return (ret < 0) ? ret : lf.found;
 }
 
-#ifdef HAVE_DEBUGINFOD_SUPPORT
-/* debuginfod doesn't require the comp_dir but buildid is required */
-static int get_source_from_debuginfod(const char *raw_path,
-				const char *sbuild_id, char **new_path)
-{
-	debuginfod_client *c = debuginfod_begin();
-	const char *p = raw_path;
-	int fd;
-
-	if (!c)
-		return -ENOMEM;
-
-	fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id,
-				0, p, new_path);
-	pr_debug("Search %s from debuginfod -> %d\n", p, fd);
-	if (fd >= 0)
-		close(fd);
-	debuginfod_end(c);
-	if (fd < 0) {
-		pr_debug("Failed to find %s in debuginfod (%s)\n",
-			raw_path, sbuild_id);
-		return -ENOENT;
-	}
-	pr_debug("Got a source %s\n", *new_path);
-
-	return 0;
-}
-#else
-static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused,
-				const char *sbuild_id __maybe_unused,
-				char **new_path __maybe_unused)
-{
-	return -ENOTSUP;
-}
-#endif
 /*
  * Find a src file from a DWARF tag path. Prepend optional source path prefix
  * and chop off leading directories that do not exist. Result is passed back as
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 8bc1c80d3c1c0..3add5ff516e12 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -24,21 +24,7 @@ static inline int is_c_varname(const char *name)
 #ifdef HAVE_DWARF_SUPPORT
 
 #include "dwarf-aux.h"
-
-/* TODO: export debuginfo data structure even if no dwarf support */
-
-/* debug information structure */
-struct debuginfo {
-	Dwarf		*dbg;
-	Dwfl_Module	*mod;
-	Dwfl		*dwfl;
-	Dwarf_Addr	bias;
-	const unsigned char	*build_id;
-};
-
-/* This also tries to open distro debuginfo */
-struct debuginfo *debuginfo__new(const char *path);
-void debuginfo__delete(struct debuginfo *dbg);
+#include "debuginfo.h"
 
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 int debuginfo__find_trace_events(struct debuginfo *dbg,
@@ -49,9 +35,6 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 				struct perf_probe_point *ppt);
 
-int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
-			       bool adjust_offset);
-
 /* Find a line range */
 int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
-- 
GitLab


From a65e8c0b7855e951138eff077af4a6a8721a7ef6 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:23 -0800
Subject: [PATCH 0028/4076] perf dwarf-aux: Fix die_get_typename() for void *

The die_get_typename() is to return a C-like type name from DWARF debug
entry and it follows data type if the target entry is a pointer type.

But I found that void pointers don't have the type attribute to follow
and then the function returns an error for that case.  This results in a
broken type string for void pointer types.

For example, the following type entries are pointer types.

 <1><48c>: Abbrev Number: 4 (DW_TAG_pointer_type)
    <48d>   DW_AT_byte_size   : 8
    <48d>   DW_AT_type        : <0x481>
 <1><491>: Abbrev Number: 211 (DW_TAG_pointer_type)
    <493>   DW_AT_byte_size   : 8
 <1><494>: Abbrev Number: 4 (DW_TAG_pointer_type)
    <495>   DW_AT_byte_size   : 8
    <495>   DW_AT_type        : <0x49e>

The first one at offset 48c and the third one at offset 494 have type
information.  Then they are pointer types for the referenced types.  But
the second one at offset 491 doesn't have the type attribute.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dwarf-aux.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 2941d88f2199c..4849c3bbfd95d 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1090,7 +1090,14 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 		return strbuf_addf(buf, "%s%s", tmp, name ?: "");
 	}
 	ret = die_get_typename(&type, buf);
-	return ret ? ret : strbuf_addstr(buf, tmp);
+	if (ret < 0) {
+		/* void pointer has no type attribute */
+		if (tag == DW_TAG_pointer_type && ret == -ENOENT)
+			return strbuf_addf(buf, "void*");
+
+		return ret;
+	}
+	return strbuf_addstr(buf, tmp);
 }
 
 /**
-- 
GitLab


From 3796eba7c137e073d1caa95b48d4a320fd2d9600 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:24 -0800
Subject: [PATCH 0029/4076] perf dwarf-aux: Move #else block of #ifdef
 HAVE_DWARF_GETLOCATIONS_SUPPORT code to the header file

It's a usual convention that the conditional code is handled in a header
file.  As I'm planning to add some more of them, let's move the current
code to the header first.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dwarf-aux.c |  7 -------
 tools/perf/util/dwarf-aux.h | 19 +++++++++++++++++--
 2 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 4849c3bbfd95d..adef2635587de 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1245,13 +1245,6 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 out:
 	return ret;
 }
-#else
-int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
-		      Dwarf_Die *vr_die __maybe_unused,
-		      struct strbuf *buf __maybe_unused)
-{
-	return -ENOTSUP;
-}
 #endif
 
 /*
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 7ec8bc1083bb3..4f5d0211ee4f2 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -121,7 +121,6 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
 int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
-int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Check if target program is compiled with optimization */
 bool die_is_optimized_target(Dwarf_Die *cu_die);
@@ -130,4 +129,20 @@ bool die_is_optimized_target(Dwarf_Die *cu_die);
 void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 		       Dwarf_Addr *entrypc);
 
-#endif
+#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
+
+/* Get byte offset range of given variable DIE */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
+
+#else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
+
+static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
+				    Dwarf_Die *vr_die __maybe_unused,
+				    struct strbuf *buf __maybe_unused)
+{
+	return -ENOTSUP;
+}
+
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
+
+#endif /* _DWARF_AUX_H */
-- 
GitLab


From 981620fd2776c45a514ed621a718e2a6941ad7c5 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:25 -0800
Subject: [PATCH 0030/4076] perf dwarf-aux: Add die_get_scopes() alternative to
 dwarf_getscopes()

The die_get_scopes() returns the number of enclosing DIEs for the given
address and it fills an array of DIEs like dwarf_getscopes().  But it
doesn't follow the abstract origin of inlined functions as we want
information of the concrete instance.  This is needed to check the
location of parameters and local variables properly.  Users can check
the origin separately if needed.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-7-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dwarf-aux.c | 53 +++++++++++++++++++++++++++++++++++++
 tools/perf/util/dwarf-aux.h |  3 +++
 2 files changed, 56 insertions(+)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index adef2635587de..10aa32334d6f2 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1425,3 +1425,56 @@ void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 
 	*entrypc = postprologue_addr;
 }
+
+/* Internal parameters for __die_find_scope_cb() */
+struct find_scope_data {
+	/* Target instruction address */
+	Dwarf_Addr pc;
+	/* Number of scopes found [output] */
+	int nr;
+	/* Array of scopes found, 0 for the outermost one. [output] */
+	Dwarf_Die *scopes;
+};
+
+static int __die_find_scope_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_scope_data *data = arg;
+
+	if (dwarf_haspc(die_mem, data->pc)) {
+		Dwarf_Die *tmp;
+
+		tmp = realloc(data->scopes, (data->nr + 1) * sizeof(*tmp));
+		if (tmp == NULL)
+			return DIE_FIND_CB_END;
+
+		memcpy(tmp + data->nr, die_mem, sizeof(*die_mem));
+		data->scopes = tmp;
+		data->nr++;
+		return DIE_FIND_CB_CHILD;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_get_scopes - Return a list of scopes including the address
+ * @cu_die: a compile unit DIE
+ * @pc: the address to find
+ * @scopes: the array of DIEs for scopes (result)
+ *
+ * This function does the same as the dwarf_getscopes() but doesn't follow
+ * the origins of inlined functions.  It returns the number of scopes saved
+ * in the @scopes argument.  The outer scope will be saved first (index 0) and
+ * the last one is the innermost scope at the @pc.
+ */
+int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes)
+{
+	struct find_scope_data data = {
+		.pc = pc,
+	};
+	Dwarf_Die die_mem;
+
+	die_find_child(cu_die, __die_find_scope_cb, &data, &die_mem);
+
+	*scopes = data.scopes;
+	return data.nr;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 4f5d0211ee4f2..f9d765f80fb02 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -129,6 +129,9 @@ bool die_is_optimized_target(Dwarf_Die *cu_die);
 void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 		       Dwarf_Addr *entrypc);
 
+/* Get the list of including scopes */
+int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes);
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 
 /* Get byte offset range of given variable DIE */
-- 
GitLab


From 3f5928e461e394d27bc1ed7d0785b1e63c43d6a1 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:26 -0800
Subject: [PATCH 0031/4076] perf dwarf-aux: Add die_find_variable_by_reg()
 helper

The die_find_variable_by_reg() will search for a variable or a parameter
sub-DIE in the given scope DIE where the location matches to the given
register.

For the simplest and most common case, memory access usually happens
with a base register and an offset to the field so the register holds a
pointer in a variable or function parameter.  Then we can find one if it
has a location expression at the (instruction) address.  This function
only handles such a simple case for now.

In this case, the expression has a DW_OP_regN operation where N < 32.
If the register index (N) is greater than or equal to 32, DW_OP_regx
operation with an operand which saves the value for the N would be used.
It rejects expressions with more operations.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-8-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dwarf-aux.c | 67 +++++++++++++++++++++++++++++++++++++
 tools/perf/util/dwarf-aux.h | 12 +++++++
 2 files changed, 79 insertions(+)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 10aa32334d6f2..652e6e7368a26 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1245,6 +1245,73 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 out:
 	return ret;
 }
+
+/* Interval parameters for __die_find_var_reg_cb() */
+struct find_var_data {
+	/* Target instruction address */
+	Dwarf_Addr pc;
+	/* Target register */
+	unsigned reg;
+};
+
+/* Max number of registers DW_OP_regN supports */
+#define DWARF_OP_DIRECT_REGS  32
+
+/* Only checks direct child DIEs in the given scope. */
+static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_var_data *data = arg;
+	int tag = dwarf_tag(die_mem);
+	ptrdiff_t off = 0;
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+
+	if (tag != DW_TAG_variable && tag != DW_TAG_formal_parameter)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+		/* Assuming the location list is sorted by address */
+		if (end < data->pc)
+			continue;
+		if (start > data->pc)
+			break;
+
+		/* Only match with a simple case */
+		if (data->reg < DWARF_OP_DIRECT_REGS) {
+			if (ops->atom == (DW_OP_reg0 + data->reg) && nops == 1)
+				return DIE_FIND_CB_END;
+		} else {
+			if (ops->atom == DW_OP_regx && ops->number == data->reg &&
+			    nops == 1)
+				return DIE_FIND_CB_END;
+		}
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_variable_by_reg - Find a variable saved in a register
+ * @sc_die: a scope DIE
+ * @pc: the program address to find
+ * @reg: the register number to find
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * Find the variable DIE accessed by the given register.
+ */
+Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
+				    Dwarf_Die *die_mem)
+{
+	struct find_var_data data = {
+		.pc = pc,
+		.reg = reg,
+	};
+	return die_find_child(sc_die, __die_find_var_reg_cb, &data, die_mem);
+}
 #endif
 
 /*
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index f9d765f80fb02..b6f430730bd13 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -137,6 +137,10 @@ int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes);
 /* Get byte offset range of given variable DIE */
 int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
 
+/* Find a variable saved in the 'reg' at given address */
+Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
+				    Dwarf_Die *die_mem);
+
 #else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
@@ -146,6 +150,14 @@ static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
 	return -ENOTSUP;
 }
 
+static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unused,
+						  Dwarf_Addr pc __maybe_unused,
+						  int reg __maybe_unused,
+						  Dwarf_Die *die_mem __maybe_unused)
+{
+	return NULL;
+}
+
 #endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 #endif /* _DWARF_AUX_H */
-- 
GitLab


From f67f2fda7d997a43e3323aec88d76f1b5e0ea5f2 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:27 -0800
Subject: [PATCH 0032/4076] perf build: Add feature check for dwarf_getcfi()

The dwarf_getcfi() is available on libdw 0.142+.  Instead of just
checking the version number, it'd be nice to have a config item to check
the feature at build time.

Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-9-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile.feature            | 1 +
 tools/build/feature/Makefile            | 4 ++++
 tools/build/feature/test-dwarf_getcfi.c | 9 +++++++++
 3 files changed, 14 insertions(+)
 create mode 100644 tools/build/feature/test-dwarf_getcfi.c

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 934e2777a2dbc..64df118376df6 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -32,6 +32,7 @@ FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
         dwarf                           \
         dwarf_getlocations              \
+        dwarf_getcfi                    \
         eventfd                         \
         fortify-source                  \
         get_current_dir_name            \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index dad79ede4e0ae..37722e509eb9f 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -7,6 +7,7 @@ FILES=                                          \
          test-bionic.bin                        \
          test-dwarf.bin                         \
          test-dwarf_getlocations.bin            \
+         test-dwarf_getcfi.bin                  \
          test-eventfd.bin                       \
          test-fortify-source.bin                \
          test-get_current_dir_name.bin          \
@@ -154,6 +155,9 @@ $(OUTPUT)test-dwarf.bin:
 $(OUTPUT)test-dwarf_getlocations.bin:
 	$(BUILD) $(DWARFLIBS)
 
+$(OUTPUT)test-dwarf_getcfi.bin:
+	$(BUILD) $(DWARFLIBS)
+
 $(OUTPUT)test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
 
diff --git a/tools/build/feature/test-dwarf_getcfi.c b/tools/build/feature/test-dwarf_getcfi.c
new file mode 100644
index 0000000000000..50e7d7cb7bdf9
--- /dev/null
+++ b/tools/build/feature/test-dwarf_getcfi.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <elfutils/libdw.h>
+
+int main(void)
+{
+	Dwarf *dwarf = NULL;
+	return dwarf_getcfi(dwarf) == NULL;
+}
-- 
GitLab


From c06547d02094e7eb81389e9485a45d91cc21914c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:28 -0800
Subject: [PATCH 0033/4076] perf probe: Convert to check dwarf_getcfi feature

Now it has a feature check for the dwarf_getcfi(), use it and convert
the code to check HAVE_DWARF_CFI_SUPPORT definition.

Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-10-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config     | 5 +++++
 tools/perf/util/probe-finder.c | 8 ++++----
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 8b6cffbc48583..aa55850fbc213 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -476,6 +476,11 @@ else
       else
         CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT
       endif # dwarf_getlocations
+      ifneq ($(feature-dwarf_getcfi), 1)
+        msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.142);
+      else
+        CFLAGS += -DHAVE_DWARF_CFI_SUPPORT
+      endif # dwarf_getcfi
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 8d3dd85f9ff4c..c8923375e30d6 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -604,7 +604,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
 	if (ret <= 0 || nops == 0) {
 		pf->fb_ops = NULL;
-#if _ELFUTILS_PREREQ(0, 142)
+#ifdef HAVE_DWARF_CFI_SUPPORT
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
 		   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
 		if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
@@ -615,7 +615,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 			free(frame);
 			return -ENOENT;
 		}
-#endif
+#endif /* HAVE_DWARF_CFI_SUPPORT */
 	}
 
 	/* Call finder's callback handler */
@@ -1140,7 +1140,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 	pf->machine = ehdr.e_machine;
 
-#if _ELFUTILS_PREREQ(0, 142)
+#ifdef HAVE_DWARF_CFI_SUPPORT
 	do {
 		GElf_Shdr shdr;
 
@@ -1150,7 +1150,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 		pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
 	} while (0);
-#endif
+#endif /* HAVE_DWARF_CFI_SUPPORT */
 
 	ret = debuginfo__find_probe_location(dbg, pf);
 	return ret;
-- 
GitLab


From e97b39c5c4362dc1cbc37a563ddac313b96c84f3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:43 -0700
Subject: [PATCH 0034/4076] KVM: Tweak kvm_hva_range and hva_handler_t to allow
 reusing for gfn ranges

Rework and rename "struct kvm_hva_range" into "kvm_mmu_notifier_range" so
that the structure can be used to handle notifications that operate on gfn
context, i.e. that aren't tied to a host virtual address.  Rename the
handler typedef too (arguably it should always have been gfn_handler_t).

Practically speaking, this is a nop for 64-bit kernels as the only
meaningful change is to store start+end as u64s instead of unsigned longs.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-2-seanjc@google.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 486800a7024b3..0524933856d42 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -541,18 +541,22 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 	return container_of(mn, struct kvm, mmu_notifier);
 }
 
-typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
+typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
 typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
 			     unsigned long end);
 
 typedef void (*on_unlock_fn_t)(struct kvm *kvm);
 
-struct kvm_hva_range {
-	unsigned long start;
-	unsigned long end;
+struct kvm_mmu_notifier_range {
+	/*
+	 * 64-bit addresses, as KVM notifiers can operate on host virtual
+	 * addresses (unsigned long) and guest physical addresses (64-bit).
+	 */
+	u64 start;
+	u64 end;
 	union kvm_mmu_notifier_arg arg;
-	hva_handler_t handler;
+	gfn_handler_t handler;
 	on_lock_fn_t on_lock;
 	on_unlock_fn_t on_unlock;
 	bool flush_on_ret;
@@ -581,7 +585,7 @@ static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;
 	     node = interval_tree_iter_next(node, start, last))	     \
 
 static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
-						  const struct kvm_hva_range *range)
+						  const struct kvm_mmu_notifier_range *range)
 {
 	bool ret = false, locked = false;
 	struct kvm_gfn_range gfn_range;
@@ -608,9 +612,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			unsigned long hva_start, hva_end;
 
 			slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]);
-			hva_start = max(range->start, slot->userspace_addr);
-			hva_end = min(range->end, slot->userspace_addr +
-						  (slot->npages << PAGE_SHIFT));
+			hva_start = max_t(unsigned long, range->start, slot->userspace_addr);
+			hva_end = min_t(unsigned long, range->end,
+					slot->userspace_addr + (slot->npages << PAGE_SHIFT));
 
 			/*
 			 * To optimize for the likely case where the address
@@ -660,10 +664,10 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 						unsigned long start,
 						unsigned long end,
 						union kvm_mmu_notifier_arg arg,
-						hva_handler_t handler)
+						gfn_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range range = {
+	const struct kvm_mmu_notifier_range range = {
 		.start		= start,
 		.end		= end,
 		.arg		= arg,
@@ -680,10 +684,10 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
 							 unsigned long start,
 							 unsigned long end,
-							 hva_handler_t handler)
+							 gfn_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range range = {
+	const struct kvm_mmu_notifier_range range = {
 		.start		= start,
 		.end		= end,
 		.handler	= handler,
@@ -771,7 +775,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range hva_range = {
+	const struct kvm_mmu_notifier_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
 		.handler	= kvm_unmap_gfn_range,
@@ -835,7 +839,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range hva_range = {
+	const struct kvm_mmu_notifier_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
 		.handler	= (void *)kvm_null_fn,
-- 
GitLab


From c0db19232c1ed6bd7fcb825c28b014c52732c19e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:44 -0700
Subject: [PATCH 0035/4076] KVM: Assert that mmu_invalidate_in_progress *never*
 goes negative

Move the assertion on the in-progress invalidation count from the primary
MMU's notifier path to KVM's common notification path, i.e. assert that
the count doesn't go negative even when the invalidation is coming from
KVM itself.

Opportunistically convert the assertion to a KVM_BUG_ON(), i.e. kill only
the affected VM, not the entire kernel.  A corrupted count is fatal to the
VM, e.g. the non-zero (negative) count will cause mmu_invalidate_retry()
to block any and all attempts to install new mappings.  But it's far from
guaranteed that an end() without a start() is fatal or even problematic to
anything other than the target VM, e.g. the underlying bug could simply be
a duplicate call to end().  And it's much more likely that a missed
invalidation, i.e. a potential use-after-free, would manifest as no
notification whatsoever, not an end() without a start().

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-3-seanjc@google.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0524933856d42..5a97e6c7d9c20 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -833,6 +833,7 @@ void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
 	 * in conjunction with the smp_rmb in mmu_invalidate_retry().
 	 */
 	kvm->mmu_invalidate_in_progress--;
+	KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm);
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
@@ -863,8 +864,6 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	 */
 	if (wake)
 		rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
-
-	BUG_ON(kvm->mmu_invalidate_in_progress < 0);
 }
 
 static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
-- 
GitLab


From 8569992d64b8f750e34b7858eac5d7daaf0f80fd Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:21:45 -0700
Subject: [PATCH 0036/4076] KVM: Use gfn instead of hva for mmu_notifier_retry

Currently in mmu_notifier invalidate path, hva range is recorded and then
checked against by mmu_invalidate_retry_hva() in the page fault handling
path. However, for the soon-to-be-introduced private memory, a page fault
may not have a hva associated, checking gfn(gpa) makes more sense.

For existing hva based shared memory, gfn is expected to also work. The
only downside is when aliasing multiple gfns to a single hva, the
current algorithm of checking multiple ranges could result in a much
larger range being rejected. Such aliasing should be uncommon, so the
impact is expected small.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
[sean: convert vmx_set_apic_access_page_addr() to gfn-based API]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Xu Yilun <yilun.xu@linux.intel.com>
Message-Id: <20231027182217.3615211-4-seanjc@google.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   | 10 ++++++----
 arch/x86/kvm/vmx/vmx.c   | 11 +++++-----
 include/linux/kvm_host.h | 33 +++++++++++++++++++-----------
 virt/kvm/kvm_main.c      | 43 +++++++++++++++++++++++++++++++---------
 4 files changed, 66 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b0f01d6056172..b2d916f786ca1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3056,7 +3056,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
  *
  * There are several ways to safely use this helper:
  *
- * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before
  *   consuming it.  In this case, mmu_lock doesn't need to be held during the
  *   lookup, but it does need to be held while checking the MMU notifier.
  *
@@ -4366,7 +4366,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 		return true;
 
 	return fault->slot &&
-	       mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva);
+	       mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn);
 }
 
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -6260,7 +6260,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	write_lock(&kvm->mmu_lock);
 
-	kvm_mmu_invalidate_begin(kvm, 0, -1ul);
+	kvm_mmu_invalidate_begin(kvm);
+
+	kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end);
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
@@ -6270,7 +6272,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 	if (flush)
 		kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
 
-	kvm_mmu_invalidate_end(kvm, 0, -1ul);
+	kvm_mmu_invalidate_end(kvm);
 
 	write_unlock(&kvm->mmu_lock);
 }
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index be20a60047b1f..40e3780d73aeb 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6757,10 +6757,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 		return;
 
 	/*
-	 * Grab the memslot so that the hva lookup for the mmu_notifier retry
-	 * is guaranteed to use the same memslot as the pfn lookup, i.e. rely
-	 * on the pfn lookup's validation of the memslot to ensure a valid hva
-	 * is used for the retry check.
+	 * Explicitly grab the memslot using KVM's internal slot ID to ensure
+	 * KVM doesn't unintentionally grab a userspace memslot.  It _should_
+	 * be impossible for userspace to create a memslot for the APIC when
+	 * APICv is enabled, but paranoia won't hurt in this case.
 	 */
 	slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
@@ -6785,8 +6785,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 		return;
 
 	read_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_invalidate_retry_hva(kvm, mmu_seq,
-				     gfn_to_hva_memslot(slot, gfn))) {
+	if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) {
 		kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 		read_unlock(&vcpu->kvm->mmu_lock);
 		goto out;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index fb6c6109fdcad..11d0916883460 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -787,8 +787,8 @@ struct kvm {
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
-	unsigned long mmu_invalidate_range_start;
-	unsigned long mmu_invalidate_range_end;
+	gfn_t mmu_invalidate_range_start;
+	gfn_t mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -1392,10 +1392,9 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end);
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm);
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
+void kvm_mmu_invalidate_end(struct kvm *kvm);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1970,9 +1969,9 @@ static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 	return 0;
 }
 
-static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
 					   unsigned long mmu_seq,
-					   unsigned long hva)
+					   gfn_t gfn)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
@@ -1981,10 +1980,20 @@ static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
 	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_invalidate_in_progress) &&
-	    hva >= kvm->mmu_invalidate_range_start &&
-	    hva < kvm->mmu_invalidate_range_end)
-		return 1;
+	if (unlikely(kvm->mmu_invalidate_in_progress)) {
+		/*
+		 * Dropping mmu_lock after bumping mmu_invalidate_in_progress
+		 * but before updating the range is a KVM bug.
+		 */
+		if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA ||
+				 kvm->mmu_invalidate_range_end == INVALID_GPA))
+			return 1;
+
+		if (gfn >= kvm->mmu_invalidate_range_start &&
+		    gfn < kvm->mmu_invalidate_range_end)
+			return 1;
+	}
+
 	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5a97e6c7d9c20..9cc57b23ec81f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -543,9 +543,7 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 
 typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
-typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
-			     unsigned long end);
-
+typedef void (*on_lock_fn_t)(struct kvm *kvm);
 typedef void (*on_unlock_fn_t)(struct kvm *kvm);
 
 struct kvm_mmu_notifier_range {
@@ -637,7 +635,8 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 				locked = true;
 				KVM_MMU_LOCK(kvm);
 				if (!IS_KVM_NULL_FN(range->on_lock))
-					range->on_lock(kvm, range->start, range->end);
+					range->on_lock(kvm);
+
 				if (IS_KVM_NULL_FN(range->handler))
 					break;
 			}
@@ -742,16 +741,29 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn);
 }
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end)
+void kvm_mmu_invalidate_begin(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_invalidate_in_progress++;
+
 	if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+		kvm->mmu_invalidate_range_start = INVALID_GPA;
+		kvm->mmu_invalidate_range_end = INVALID_GPA;
+	}
+}
+
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress);
+
+	if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) {
 		kvm->mmu_invalidate_range_start = start;
 		kvm->mmu_invalidate_range_end = end;
 	} else {
@@ -771,6 +783,12 @@ void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
 	}
 }
 
+static bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
+	return kvm_unmap_gfn_range(kvm, range);
+}
+
 static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
@@ -778,7 +796,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	const struct kvm_mmu_notifier_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
-		.handler	= kvm_unmap_gfn_range,
+		.handler	= kvm_mmu_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
 		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
@@ -817,9 +835,10 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	return 0;
 }
 
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end)
+void kvm_mmu_invalidate_end(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -834,6 +853,12 @@ void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
 	 */
 	kvm->mmu_invalidate_in_progress--;
 	KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm);
+
+	/*
+	 * Assert that at least one range was added between start() and end().
+	 * Not adding a range isn't fatal, but it is a KVM bug.
+	 */
+	WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA);
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
-- 
GitLab


From d497a0fab8b8457214fcc9b1a39530920ea7e95e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:46 -0700
Subject: [PATCH 0037/4076] KVM: WARN if there are dangling MMU invalidations
 at VM destruction

Add an assertion that there are no in-progress MMU invalidations when a
VM is being destroyed, with the exception of the scenario where KVM
unregisters its MMU notifier between an .invalidate_range_start() call and
the corresponding .invalidate_range_end().

KVM can't detect unpaired calls from the mmu_notifier due to the above
exception waiver, but the assertion can detect KVM bugs, e.g. such as the
bug that *almost* escaped initial guest_memfd development.

Link: https://lore.kernel.org/all/e397d30c-c6af-e68f-d18e-b4e3739c5389@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9cc57b23ec81f..5422ce20dcbac 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1358,9 +1358,16 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	 * No threads can be waiting in kvm_swap_active_memslots() as the
 	 * last reference on KVM has been dropped, but freeing
 	 * memslots would deadlock without this manual intervention.
+	 *
+	 * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU
+	 * notifier between a start() and end(), then there shouldn't be any
+	 * in-progress invalidations.
 	 */
 	WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
-	kvm->mn_active_invalidate_count = 0;
+	if (kvm->mn_active_invalidate_count)
+		kvm->mn_active_invalidate_count = 0;
+	else
+		WARN_ON(kvm->mmu_invalidate_in_progress);
 #else
 	kvm_flush_shadow_all(kvm);
 #endif
-- 
GitLab


From 1853d7502a19b34b2cfe4ea0698bee73323fec3a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:47 -0700
Subject: [PATCH 0038/4076] KVM: PPC: Drop dead code related to
 KVM_ARCH_WANT_MMU_NOTIFIER

Assert that both KVM_ARCH_WANT_MMU_NOTIFIER and CONFIG_MMU_NOTIFIER are
defined when KVM is enabled, and return '1' unconditionally for the
CONFIG_KVM_BOOK3S_HV_POSSIBLE=n path.  All flavors of PPC support for KVM
select MMU_NOTIFIER, and KVM_ARCH_WANT_MMU_NOTIFIER is unconditionally
defined by arch/powerpc/include/asm/kvm_host.h.

Effectively dropping use of KVM_ARCH_WANT_MMU_NOTIFIER will simplify a
future cleanup to turn KVM_ARCH_WANT_MMU_NOTIFIER into a Kconfig, i.e.
will allow combining all of the

  #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)

checks into a single

  #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER

without having to worry about PPC's "bare" usage of
KVM_ARCH_WANT_MMU_NOTIFIER.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/powerpc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 7197c8256668b..b0a512ede764f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -632,12 +632,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
+#if !defined(CONFIG_MMU_NOTIFIER) || !defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+		BUILD_BUG();
+#endif
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 		r = hv_enabled;
-#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-		r = 1;
 #else
-		r = 0;
+		r = 1;
 #endif
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-- 
GitLab


From 4a2e993faad3880962540ab8e3b68f22e48b18e8 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:48 -0700
Subject: [PATCH 0039/4076] KVM: PPC: Return '1' unconditionally for
 KVM_CAP_SYNC_MMU

Advertise that KVM's MMU is synchronized with the primary MMU for all
flavors of PPC KVM support, i.e. advertise that the MMU is synchronized
when CONFIG_KVM_BOOK3S_HV_POSSIBLE=y but the VM is not using hypervisor
mode (a.k.a. PR VMs).  PR VMs, via kvm_unmap_gfn_range_pr(), do the right
thing for mmu_notifier invalidation events, and more tellingly, KVM
returns '1' for KVM_CAP_SYNC_MMU when CONFIG_KVM_BOOK3S_HV_POSSIBLE=n
and CONFIG_KVM_BOOK3S_PR_POSSIBLE=y, i.e. KVM already advertises a
synchronized MMU for PR VMs, just not when CONFIG_KVM_BOOK3S_HV_POSSIBLE=y.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/powerpc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index b0a512ede764f..8d3ec483bc2b2 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -635,11 +635,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #if !defined(CONFIG_MMU_NOTIFIER) || !defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 		BUILD_BUG();
 #endif
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-		r = hv_enabled;
-#else
 		r = 1;
-#endif
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
-- 
GitLab


From f128cf8cfbecccf95e891ae90d9c917df5117c7a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:49 -0700
Subject: [PATCH 0040/4076] KVM: Convert KVM_ARCH_WANT_MMU_NOTIFIER to
 CONFIG_KVM_GENERIC_MMU_NOTIFIER

Convert KVM_ARCH_WANT_MMU_NOTIFIER into a Kconfig and select it where
appropriate to effectively maintain existing behavior.  Using a proper
Kconfig will simplify building more functionality on top of KVM's
mmu_notifier infrastructure.

Add a forward declaration of kvm_gfn_range to kvm_types.h so that
including arch/powerpc/include/asm/kvm_ppc.h's with CONFIG_KVM=n doesn't
generate warnings due to kvm_gfn_range being undeclared.  PPC defines
hooks for PR vs. HV without guarding them via #ifdeffery, e.g.

  bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range);
  bool (*age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
  bool (*test_age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
  bool (*set_spte_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);

Alternatively, PPC could forward declare kvm_gfn_range, but there's no
good reason not to define it in common KVM.

Acked-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/include/asm/kvm_host.h     |  2 --
 arch/arm64/kvm/Kconfig                |  2 +-
 arch/loongarch/include/asm/kvm_host.h |  1 -
 arch/loongarch/kvm/Kconfig            |  2 +-
 arch/mips/include/asm/kvm_host.h      |  2 --
 arch/mips/kvm/Kconfig                 |  2 +-
 arch/powerpc/include/asm/kvm_host.h   |  2 --
 arch/powerpc/kvm/Kconfig              |  8 ++++----
 arch/powerpc/kvm/powerpc.c            |  4 +---
 arch/riscv/include/asm/kvm_host.h     |  2 --
 arch/riscv/kvm/Kconfig                |  2 +-
 arch/x86/include/asm/kvm_host.h       |  2 --
 arch/x86/kvm/Kconfig                  |  2 +-
 include/linux/kvm_host.h              |  6 +++---
 include/linux/kvm_types.h             |  1 +
 virt/kvm/Kconfig                      |  4 ++++
 virt/kvm/kvm_main.c                   | 10 +++++-----
 17 files changed, 23 insertions(+), 31 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5653d3553e3ee..9029fe09f3f69 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -954,8 +954,6 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 83c1e09be42e5..1a777715199fa 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -22,7 +22,7 @@ menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
 	select KVM_GENERIC_HARDWARE_ENABLING
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 11328700d4fa8..b108301c2e5aa 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -183,7 +183,6 @@ void kvm_flush_tlb_all(void);
 void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa);
 int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index fda425babfb20..f22bae89b07d3 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -26,9 +26,9 @@ config KVM
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
+	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
-	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	help
 	  Support hosting virtualized guest machines using
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 54a85f1d4f2c8..179f320cc2313 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -810,8 +810,6 @@ int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn);
 pgd_t *kvm_pgd_alloc(void);
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 /* Emulation */
 enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause);
 int kvm_get_badinstr(u32 *opc, struct kvm_vcpu *vcpu, u32 *out);
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index a8cdba75f98dd..c04987d2ed2e3 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -25,7 +25,7 @@ config KVM
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select INTERVAL_TREE
 	select KVM_GENERIC_HARDWARE_ENABLING
 	help
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 14ee0dece8538..4b5c3f2acf78f 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -62,8 +62,6 @@
 
 #include <linux/mmu_notifier.h>
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 #define HPTEG_CACHE_NUM			(1 << 15)
 #define HPTEG_HASH_BITS_PTE		13
 #define HPTEG_HASH_BITS_PTE_LONG	12
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 902611954200d..b33358ee64244 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -42,7 +42,7 @@ config KVM_BOOK3S_64_HANDLER
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 
 config KVM_BOOK3S_HV_POSSIBLE
 	bool
@@ -85,7 +85,7 @@ config KVM_BOOK3S_64_HV
 	tristate "KVM for POWER7 and later using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select CMA
 	help
 	  Support running unmodified book3s_64 guest kernels in
@@ -194,7 +194,7 @@ config KVM_E500V2
 	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -211,7 +211,7 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500MC/E5500/E6500 guest kernels in
 	  virtual machines on E500MC/E5500/E6500 host processors.
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 8d3ec483bc2b2..aac75c98a9565 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -632,9 +632,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-#if !defined(CONFIG_MMU_NOTIFIER) || !defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-		BUILD_BUG();
-#endif
+		BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER));
 		r = 1;
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 0eefd9c991ae2..6964dd235e97f 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -267,8 +267,6 @@ struct kvm_vcpu_arch {
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
 
 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index dfc237d7875b5..ae2e05f050ece 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -30,7 +30,7 @@ config KVM
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	help
 	  Support hosting virtualized guest machines.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d7036982332e3..6f559fb75e6dd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2141,8 +2141,6 @@ enum {
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
 #endif
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_extint(struct kvm_vcpu *v);
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 950c12868d304..e61383674c756 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -24,7 +24,7 @@ config KVM
 	depends on HIGH_RES_TIMERS
 	depends on X86_LOCAL_APIC
 	select PREEMPT_NOTIFIERS
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
 	select HAVE_KVM_IRQFD
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 11d0916883460..5faba69403ac4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -253,7 +253,7 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	pte_t pte;
 };
@@ -783,7 +783,7 @@ struct kvm {
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
@@ -1946,7 +1946,7 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
 	if (unlikely(kvm->mmu_invalidate_in_progress))
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 6f4737d5046a4..9d1f7835d8c13 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -6,6 +6,7 @@
 struct kvm;
 struct kvm_async_pf;
 struct kvm_device_ops;
+struct kvm_gfn_range;
 struct kvm_interrupt;
 struct kvm_irq_routing_table;
 struct kvm_memory_slot;
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 484d0873061ca..ecae2914c97e4 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -92,3 +92,7 @@ config HAVE_KVM_PM_NOTIFIER
 
 config KVM_GENERIC_HARDWARE_ENABLING
        bool
+
+config KVM_GENERIC_MMU_NOTIFIER
+       select MMU_NOTIFIER
+       bool
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5422ce20dcbac..dc81279ea3850 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -535,7 +535,7 @@ void kvm_destroy_vcpus(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_destroy_vcpus);
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 {
 	return container_of(mn, struct kvm, mmu_notifier);
@@ -962,14 +962,14 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 	return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
 }
 
-#else  /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */
+#else  /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */
 
 static int kvm_init_mmu_notifier(struct kvm *kvm)
 {
 	return 0;
 }
 
-#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
+#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 static int kvm_pm_notifier_call(struct notifier_block *bl,
@@ -1289,7 +1289,7 @@ out_err:
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
 #endif
@@ -1349,7 +1349,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
 	/*
 	 * At this point, pending calls to invalidate_range_start()
-- 
GitLab


From bb58b90b1a8f753b582055adaf448214a8e22c31 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:50 -0700
Subject: [PATCH 0041/4076] KVM: Introduce KVM_SET_USER_MEMORY_REGION2

Introduce a "version 2" of KVM_SET_USER_MEMORY_REGION so that additional
information can be supplied without setting userspace up to fail.  The
padding in the new kvm_userspace_memory_region2 structure will be used to
pass a file descriptor in addition to the userspace_addr, i.e. allow
userspace to point at a file descriptor and map memory into a guest that
is NOT mapped into host userspace.

Alternatively, KVM could simply add "struct kvm_userspace_memory_region2"
without a new ioctl(), but as Paolo pointed out, adding a new ioctl()
makes detection of bad flags a bit more robust, e.g. if the new fd field
is guarded only by a flag and not a new ioctl(), then a userspace bug
(setting a "bad" flag) would generate out-of-bounds access instead of an
-EINVAL error.

Cc: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-9-seanjc@google.com>
Acked-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 22 +++++++++++++
 arch/x86/kvm/x86.c             |  2 +-
 include/linux/kvm_host.h       |  4 +--
 include/uapi/linux/kvm.h       | 13 ++++++++
 virt/kvm/kvm_main.c            | 57 +++++++++++++++++++++++++++++-----
 5 files changed, 87 insertions(+), 11 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 7025b37510279..9edd9e436bab4 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6192,6 +6192,28 @@ to know what fields can be changed for the system register described by
 ``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a
 superset of the features supported by the system.
 
+4.140 KVM_SET_USER_MEMORY_REGION2
+---------------------------------
+
+:Capability: KVM_CAP_USER_MEMORY2
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_userspace_memory_region2 (in)
+:Returns: 0 on success, -1 on error
+
+::
+
+  struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr; /* start of the userspace allocated memory */
+	__u64 pad[16];
+  };
+
+See KVM_SET_USER_MEMORY_REGION.
+
 5. The kvm_run structure
 ========================
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2c924075f6f11..7b389f27dffca 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12576,7 +12576,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 	}
 
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		struct kvm_userspace_memory_region m;
+		struct kvm_userspace_memory_region2 m;
 
 		m.slot = id | (i << 16);
 		m.flags = 0;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5faba69403ac4..4e741ff27af36 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1146,9 +1146,9 @@ enum kvm_mr_change {
 };
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+			  const struct kvm_userspace_memory_region2 *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
+			    const struct kvm_userspace_memory_region2 *mem);
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 211b86de35ac5..308cc70bd6ab8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -95,6 +95,16 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 pad[16];
+};
+
 /*
  * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
  * userspace, other bits are reserved for kvm internal use which are defined
@@ -1201,6 +1211,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1483,6 +1494,8 @@ struct kvm_vfio_spapr_tce {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dc81279ea3850..756b94ecd5110 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1580,7 +1580,15 @@ static void kvm_replace_memslot(struct kvm *kvm,
 	}
 }
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
+/*
+ * Flags that do not access any of the extra space of struct
+ * kvm_userspace_memory_region2.  KVM_SET_USER_MEMORY_REGION_V1_FLAGS
+ * only allows these.
+ */
+#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
+	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
+
+static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
@@ -1982,7 +1990,7 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
  * Must be called holding kvm->slots_lock for write.
  */
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem)
+			    const struct kvm_userspace_memory_region2 *mem)
 {
 	struct kvm_memory_slot *old, *new;
 	struct kvm_memslots *slots;
@@ -2086,7 +2094,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem)
+			  const struct kvm_userspace_memory_region2 *mem)
 {
 	int r;
 
@@ -2098,7 +2106,7 @@ int kvm_set_memory_region(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
 static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-					  struct kvm_userspace_memory_region *mem)
+					  struct kvm_userspace_memory_region2 *mem)
 {
 	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
@@ -4568,6 +4576,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 {
 	switch (arg) {
 	case KVM_CAP_USER_MEMORY:
+	case KVM_CAP_USER_MEMORY2:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
 	case KVM_CAP_INTERNAL_ERROR_DATA:
@@ -4823,6 +4832,14 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
 	return fd;
 }
 
+#define SANITY_CHECK_MEM_REGION_FIELD(field)					\
+do {										\
+	BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) !=		\
+		     offsetof(struct kvm_userspace_memory_region2, field));	\
+	BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) !=		\
+		     sizeof_field(struct kvm_userspace_memory_region2, field));	\
+} while (0)
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4845,15 +4862,39 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap);
 		break;
 	}
+	case KVM_SET_USER_MEMORY_REGION2:
 	case KVM_SET_USER_MEMORY_REGION: {
-		struct kvm_userspace_memory_region kvm_userspace_mem;
+		struct kvm_userspace_memory_region2 mem;
+		unsigned long size;
+
+		if (ioctl == KVM_SET_USER_MEMORY_REGION) {
+			/*
+			 * Fields beyond struct kvm_userspace_memory_region shouldn't be
+			 * accessed, but avoid leaking kernel memory in case of a bug.
+			 */
+			memset(&mem, 0, sizeof(mem));
+			size = sizeof(struct kvm_userspace_memory_region);
+		} else {
+			size = sizeof(struct kvm_userspace_memory_region2);
+		}
+
+		/* Ensure the common parts of the two structs are identical. */
+		SANITY_CHECK_MEM_REGION_FIELD(slot);
+		SANITY_CHECK_MEM_REGION_FIELD(flags);
+		SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr);
+		SANITY_CHECK_MEM_REGION_FIELD(memory_size);
+		SANITY_CHECK_MEM_REGION_FIELD(userspace_addr);
 
 		r = -EFAULT;
-		if (copy_from_user(&kvm_userspace_mem, argp,
-						sizeof(kvm_userspace_mem)))
+		if (copy_from_user(&mem, argp, size))
+			goto out;
+
+		r = -EINVAL;
+		if (ioctl == KVM_SET_USER_MEMORY_REGION &&
+		    (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
+		r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {
-- 
GitLab


From 16f95f3b95caded251a0440051e44a2fbe9e5f55 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:21:51 -0700
Subject: [PATCH 0042/4076] KVM: Add KVM_EXIT_MEMORY_FAULT exit to report
 faults to userspace

Add a new KVM exit type to allow userspace to handle memory faults that
KVM cannot resolve, but that userspace *may* be able to handle (without
terminating the guest).

KVM will initially use KVM_EXIT_MEMORY_FAULT to report implicit
conversions between private and shared memory.  With guest private memory,
there will be two kind of memory conversions:

  - explicit conversion: happens when the guest explicitly calls into KVM
    to map a range (as private or shared)

  - implicit conversion: happens when the guest attempts to access a gfn
    that is configured in the "wrong" state (private vs. shared)

On x86 (first architecture to support guest private memory), explicit
conversions will be reported via KVM_EXIT_HYPERCALL+KVM_HC_MAP_GPA_RANGE,
but reporting KVM_EXIT_HYPERCALL for implicit conversions is undesriable
as there is (obviously) no hypercall, and there is no guarantee that the
guest actually intends to convert between private and shared, i.e. what
KVM thinks is an implicit conversion "request" could actually be the
result of a guest code bug.

KVM_EXIT_MEMORY_FAULT will be used to report memory faults that appear to
be implicit conversions.

Note!  To allow for future possibilities where KVM reports
KVM_EXIT_MEMORY_FAULT and fills run->memory_fault on _any_ unresolved
fault, KVM returns "-EFAULT" (-1 with errno == EFAULT from userspace's
perspective), not '0'!  Due to historical baggage within KVM, exiting to
userspace with '0' from deep callstacks, e.g. in emulation paths, is
infeasible as doing so would require a near-complete overhaul of KVM,
whereas KVM already propagates -errno return codes to userspace even when
the -errno originated in a low level helper.

Report the gpa+size instead of a single gfn even though the initial usage
is expected to always report single pages.  It's entirely possible, likely
even, that KVM will someday support sub-page granularity faults, e.g.
Intel's sub-page protection feature allows for additional protections at
128-byte granularity.

Link: https://lore.kernel.org/all/20230908222905.1321305-5-amoorthy@google.com
Link: https://lore.kernel.org/all/ZQ3AmLO2SYv3DszH@google.com
Cc: Anish Moorthy <amoorthy@google.com>
Cc: David Matlack <dmatlack@google.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20231027182217.3615211-10-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 41 ++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.c             |  1 +
 include/linux/kvm_host.h       | 11 +++++++++
 include/uapi/linux/kvm.h       |  8 +++++++
 4 files changed, 61 insertions(+)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 9edd9e436bab4..27d945d5b4e49 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6846,6 +6846,26 @@ array field represents return values. The userspace should update the return
 values of SBI call before resuming the VCPU. For more details on RISC-V SBI
 spec refer, https://github.com/riscv/riscv-sbi-doc.
 
+::
+
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
+
+KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that
+could not be resolved by KVM.  The 'gpa' and 'size' (in bytes) describe the
+guest physical address range [gpa, gpa + size) of the fault.  The 'flags' field
+describes properties of the faulting access that are likely pertinent.
+Currently, no flags are defined.
+
+Note!  KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it
+accompanies a return code of '-1', not '0'!  errno will always be set to EFAULT
+or EHWPOISON when KVM exits with KVM_EXIT_MEMORY_FAULT, userspace should assume
+kvm_run.exit_reason is stale/undefined for all other error numbers.
+
 ::
 
     /* KVM_EXIT_NOTIFY */
@@ -7880,6 +7900,27 @@ This capability is aimed to mitigate the threat that malicious VMs can
 cause CPU stuck (due to event windows don't open up) and make the CPU
 unavailable to host or other VMs.
 
+7.34 KVM_CAP_MEMORY_FAULT_INFO
+------------------------------
+
+:Architectures: x86
+:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP.
+
+The presence of this capability indicates that KVM_RUN will fill
+kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if
+there is a valid memslot but no backing VMA for the corresponding host virtual
+address.
+
+The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns
+an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set
+to KVM_EXIT_MEMORY_FAULT.
+
+Note: Userspaces which attempt to resolve memory faults so that they can retry
+KVM_RUN are encouraged to guard against repeatedly receiving the same
+error/annotated fault.
+
+See KVM_EXIT_MEMORY_FAULT for more information.
+
 8. Other capabilities.
 ======================
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7b389f27dffca..8f9d8939b63bb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4625,6 +4625,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
 	case KVM_CAP_IRQFD_RESAMPLE:
+	case KVM_CAP_MEMORY_FAULT_INFO:
 		r = 1;
 		break;
 	case KVM_CAP_EXIT_HYPERCALL:
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4e741ff27af36..96aa930536b16 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2327,4 +2327,15 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
 /* Max number of entries allowed for each kvm dirty ring */
 #define  KVM_DIRTY_RING_MAX_ENTRIES  65536
 
+static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						 gpa_t gpa, gpa_t size)
+{
+	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+	vcpu->run->memory_fault.gpa = gpa;
+	vcpu->run->memory_fault.size = size;
+
+	/* Flags are not (yet) defined or communicated to userspace. */
+	vcpu->run->memory_fault.flags = 0;
+}
+
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 308cc70bd6ab8..59010a685007f 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -275,6 +275,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
+#define KVM_EXIT_MEMORY_FAULT     39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -528,6 +529,12 @@ struct kvm_run {
 #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
 			__u32 flags;
 		} notify;
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1212,6 +1219,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
 #define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
GitLab


From cec29eef0a815386d520d61c2cbe16d537931639 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:52 -0700
Subject: [PATCH 0043/4076] KVM: Add a dedicated mmu_notifier flag for
 reclaiming freed memory

Handle AMD SEV's kvm_arch_guest_memory_reclaimed() hook by having
__kvm_handle_hva_range() return whether or not an overlapping memslot
was found, i.e. mmu_lock was acquired.  Using the .on_unlock() hook
works, but kvm_arch_guest_memory_reclaimed() needs to run after dropping
mmu_lock, which makes .on_lock() and .on_unlock() asymmetrical.

Use a small struct to return the tuple of the notifier-specific return,
plus whether or not overlap was found.  Because the iteration helpers are
__always_inlined, practically speaking, the struct will never actually be
returned from a function call (not to mention the size of the struct will
be two bytes in practice).

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-11-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 53 +++++++++++++++++++++++++++++++--------------
 1 file changed, 37 insertions(+), 16 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 756b94ecd5110..e18a7f152c0b4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -561,6 +561,19 @@ struct kvm_mmu_notifier_range {
 	bool may_block;
 };
 
+/*
+ * The inner-most helper returns a tuple containing the return value from the
+ * arch- and action-specific handler, plus a flag indicating whether or not at
+ * least one memslot was found, i.e. if the handler found guest memory.
+ *
+ * Note, most notifiers are averse to booleans, so even though KVM tracks the
+ * return from arch code as a bool, outer helpers will cast it to an int. :-(
+ */
+typedef struct kvm_mmu_notifier_return {
+	bool ret;
+	bool found_memslot;
+} kvm_mn_ret_t;
+
 /*
  * Use a dedicated stub instead of NULL to indicate that there is no callback
  * function/handler.  The compiler technically can't guarantee that a real
@@ -582,22 +595,25 @@ static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;
 	     node;							     \
 	     node = interval_tree_iter_next(node, start, last))	     \
 
-static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
-						  const struct kvm_mmu_notifier_range *range)
+static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
+							   const struct kvm_mmu_notifier_range *range)
 {
-	bool ret = false, locked = false;
+	struct kvm_mmu_notifier_return r = {
+		.ret = false,
+		.found_memslot = false,
+	};
 	struct kvm_gfn_range gfn_range;
 	struct kvm_memory_slot *slot;
 	struct kvm_memslots *slots;
 	int i, idx;
 
 	if (WARN_ON_ONCE(range->end <= range->start))
-		return 0;
+		return r;
 
 	/* A null handler is allowed if and only if on_lock() is provided. */
 	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
 			 IS_KVM_NULL_FN(range->handler)))
-		return 0;
+		return r;
 
 	idx = srcu_read_lock(&kvm->srcu);
 
@@ -631,8 +647,8 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
 			gfn_range.slot = slot;
 
-			if (!locked) {
-				locked = true;
+			if (!r.found_memslot) {
+				r.found_memslot = true;
 				KVM_MMU_LOCK(kvm);
 				if (!IS_KVM_NULL_FN(range->on_lock))
 					range->on_lock(kvm);
@@ -640,14 +656,14 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 				if (IS_KVM_NULL_FN(range->handler))
 					break;
 			}
-			ret |= range->handler(kvm, &gfn_range);
+			r.ret |= range->handler(kvm, &gfn_range);
 		}
 	}
 
-	if (range->flush_on_ret && ret)
+	if (range->flush_on_ret && r.ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (locked) {
+	if (r.found_memslot) {
 		KVM_MMU_UNLOCK(kvm);
 		if (!IS_KVM_NULL_FN(range->on_unlock))
 			range->on_unlock(kvm);
@@ -655,8 +671,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
-	/* The notifiers are averse to booleans. :-( */
-	return (int)ret;
+	return r;
 }
 
 static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
@@ -677,7 +692,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.may_block	= false,
 	};
 
-	return __kvm_handle_hva_range(kvm, &range);
+	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
 static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
@@ -696,7 +711,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.may_block	= false,
 	};
 
-	return __kvm_handle_hva_range(kvm, &range);
+	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
 static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
@@ -798,7 +813,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.end		= range->end,
 		.handler	= kvm_mmu_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
-		.on_unlock	= kvm_arch_guest_memory_reclaimed,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -830,7 +845,13 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
 
-	__kvm_handle_hva_range(kvm, &hva_range);
+	/*
+	 * If one or more memslots were found and thus zapped, notify arch code
+	 * that guest memory has been reclaimed.  This needs to be done *after*
+	 * dropping mmu_lock, as x86's reclaim path is slooooow.
+	 */
+	if (__kvm_handle_hva_range(kvm, &hva_range).found_memslot)
+		kvm_arch_guest_memory_reclaimed(kvm);
 
 	return 0;
 }
-- 
GitLab


From 193bbfaacc84f9ee9c281ec0a8dd2ec8e4821e57 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:53 -0700
Subject: [PATCH 0044/4076] KVM: Drop .on_unlock() mmu_notifier hook

Drop the .on_unlock() mmu_notifer hook now that it's no longer used for
notifying arch code that memory has been reclaimed.  Adding .on_unlock()
and invoking it *after* dropping mmu_lock was a terrible idea, as doing so
resulted in .on_lock() and .on_unlock() having divergent and asymmetric
behavior, and set future developers up for failure, i.e. all but asked for
bugs where KVM relied on using .on_unlock() to try to run a callback while
holding mmu_lock.

Opportunistically add a lockdep assertion in kvm_mmu_invalidate_end() to
guard against future bugs of this nature.

Reported-by: Isaku Yamahata <isaku.yamahata@intel.com>
Link: https://lore.kernel.org/all/20230802203119.GB2021422@ls.amr.corp.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-12-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e18a7f152c0b4..7f3291dec7a6c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -544,7 +544,6 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
 typedef void (*on_lock_fn_t)(struct kvm *kvm);
-typedef void (*on_unlock_fn_t)(struct kvm *kvm);
 
 struct kvm_mmu_notifier_range {
 	/*
@@ -556,7 +555,6 @@ struct kvm_mmu_notifier_range {
 	union kvm_mmu_notifier_arg arg;
 	gfn_handler_t handler;
 	on_lock_fn_t on_lock;
-	on_unlock_fn_t on_unlock;
 	bool flush_on_ret;
 	bool may_block;
 };
@@ -663,11 +661,8 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
 	if (range->flush_on_ret && r.ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (r.found_memslot) {
+	if (r.found_memslot)
 		KVM_MMU_UNLOCK(kvm);
-		if (!IS_KVM_NULL_FN(range->on_unlock))
-			range->on_unlock(kvm);
-	}
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
@@ -687,7 +682,6 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.arg		= arg,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
 	};
@@ -706,7 +700,6 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.end		= end,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
 	};
@@ -813,7 +806,6 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.end		= range->end,
 		.handler	= kvm_mmu_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -891,7 +883,6 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 		.end		= range->end,
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_mmu_invalidate_end,
-		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
-- 
GitLab


From 5a475554db1e476a14216e742ea2bdb77362d5d5 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:21:55 -0700
Subject: [PATCH 0045/4076] KVM: Introduce per-page memory attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In confidential computing usages, whether a page is private or shared is
necessary information for KVM to perform operations like page fault
handling, page zapping etc. There are other potential use cases for
per-page memory attributes, e.g. to make memory read-only (or no-exec,
or exec-only, etc.) without having to modify memslots.

Introduce the KVM_SET_MEMORY_ATTRIBUTES ioctl, advertised by
KVM_CAP_MEMORY_ATTRIBUTES, to allow userspace to set the per-page memory
attributes to a guest memory range.

Use an xarray to store the per-page attributes internally, with a naive,
not fully optimized implementation, i.e. prioritize correctness over
performance for the initial implementation.

Use bit 3 for the PRIVATE attribute so that KVM can use bits 0-2 for RWX
attributes/protections in the future, e.g. to give userspace fine-grained
control over read, write, and execute protections for guest memory.

Provide arch hooks for handling attribute changes before and after common
code sets the new attributes, e.g. x86 will use the "pre" hook to zap all
relevant mappings, and the "post" hook to track whether or not hugepages
can be used to map the range.

To simplify the implementation wrap the entire sequence with
kvm_mmu_invalidate_{begin,end}() even though the operation isn't strictly
guaranteed to be an invalidation.  For the initial use case, x86 *will*
always invalidate memory, and preventing arch code from creating new
mappings while the attributes are in flux makes it much easier to reason
about the correctness of consuming attributes.

It's possible that future usages may not require an invalidation, e.g.
if KVM ends up supporting RWX protections and userspace grants _more_
protections, but again opt for simplicity and punt optimizations to
if/when they are needed.

Suggested-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/all/Y2WB48kD0J4VGynX@google.com
Cc: Fuad Tabba <tabba@google.com>
Cc: Xu Yilun <yilun.xu@intel.com>
Cc: Mickaël Salaün <mic@digikod.net>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-14-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst |  36 ++++++
 include/linux/kvm_host.h       |  19 +++
 include/uapi/linux/kvm.h       |  13 ++
 virt/kvm/Kconfig               |   4 +
 virt/kvm/kvm_main.c            | 216 +++++++++++++++++++++++++++++++++
 5 files changed, 288 insertions(+)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 27d945d5b4e49..081ef09d3148f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6214,6 +6214,42 @@ superset of the features supported by the system.
 
 See KVM_SET_USER_MEMORY_REGION.
 
+4.141 KVM_SET_MEMORY_ATTRIBUTES
+-------------------------------
+
+:Capability: KVM_CAP_MEMORY_ATTRIBUTES
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_memory_attributes (in)
+:Returns: 0 on success, <0 on error
+
+KVM_SET_MEMORY_ATTRIBUTES allows userspace to set memory attributes for a range
+of guest physical memory.
+
+::
+
+  struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+  };
+
+  #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+The address and size must be page aligned.  The supported attributes can be
+retrieved via ioctl(KVM_CHECK_EXTENSION) on KVM_CAP_MEMORY_ATTRIBUTES.  If
+executed on a VM, KVM_CAP_MEMORY_ATTRIBUTES precisely returns the attributes
+supported by that VM.  If executed at system scope, KVM_CAP_MEMORY_ATTRIBUTES
+returns all attributes supported by KVM.  The only attribute defined at this
+time is KVM_MEMORY_ATTRIBUTE_PRIVATE, which marks the associated gfn as being
+guest private memory.
+
+Note, there is no "get" API.  Userspace is responsible for explicitly tracking
+the state of a gfn/page as needed.
+
+The "flags" field is reserved for future extensions and must be '0'.
+
 5. The kvm_run structure
 ========================
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 96aa930536b16..68a144cb7dbc6 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -256,6 +256,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	pte_t pte;
+	unsigned long attributes;
 };
 
 struct kvm_gfn_range {
@@ -806,6 +807,10 @@ struct kvm {
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 	struct notifier_block pm_notifier;
+#endif
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	/* Protected by slots_locks (for writes) and RCU (for reads) */
+	struct xarray mem_attr_array;
 #endif
 	char stats_id[KVM_STATS_NAME_SIZE];
 };
@@ -2338,4 +2343,18 @@ static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
 	vcpu->run->memory_fault.flags = 0;
 }
 
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+	return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+}
+
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs);
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range);
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range);
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 59010a685007f..e8d167e549804 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1220,6 +1220,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
 #define KVM_CAP_USER_MEMORY2 231
 #define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -2288,4 +2289,16 @@ struct kvm_s390_zpci_op {
 /* flags for kvm_s390_zpci_op->u.reg_aen.flags */
 #define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
 
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES              _IOW(KVMIO,  0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
 #endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index ecae2914c97e4..5bd7fcaf9089c 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -96,3 +96,7 @@ config KVM_GENERIC_HARDWARE_ENABLING
 config KVM_GENERIC_MMU_NOTIFIER
        select MMU_NOTIFIER
        bool
+
+config KVM_GENERIC_MEMORY_ATTRIBUTES
+       select KVM_GENERIC_MMU_NOTIFIER
+       bool
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7f3291dec7a6c..f1a575d39b3bb 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1211,6 +1211,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	spin_lock_init(&kvm->mn_invalidate_lock);
 	rcuwait_init(&kvm->mn_memslots_update_rcuwait);
 	xa_init(&kvm->vcpu_array);
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	xa_init(&kvm->mem_attr_array);
+#endif
 
 	INIT_LIST_HEAD(&kvm->gpc_list);
 	spin_lock_init(&kvm->gpc_lock);
@@ -1391,6 +1394,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	}
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	xa_destroy(&kvm->mem_attr_array);
+#endif
 	kvm_arch_free_vm(kvm);
 	preempt_notifier_dec();
 	hardware_disable_all();
@@ -2397,6 +2403,200 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
 
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+/*
+ * Returns true if _all_ gfns in the range [@start, @end) have attributes
+ * matching @attrs.
+ */
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs)
+{
+	XA_STATE(xas, &kvm->mem_attr_array, start);
+	unsigned long index;
+	bool has_attrs;
+	void *entry;
+
+	rcu_read_lock();
+
+	if (!attrs) {
+		has_attrs = !xas_find(&xas, end - 1);
+		goto out;
+	}
+
+	has_attrs = true;
+	for (index = start; index < end; index++) {
+		do {
+			entry = xas_next(&xas);
+		} while (xas_retry(&xas, entry));
+
+		if (xas.xa_index != index || xa_to_value(entry) != attrs) {
+			has_attrs = false;
+			break;
+		}
+	}
+
+out:
+	rcu_read_unlock();
+	return has_attrs;
+}
+
+static u64 kvm_supported_mem_attributes(struct kvm *kvm)
+{
+	if (!kvm)
+		return KVM_MEMORY_ATTRIBUTE_PRIVATE;
+
+	return 0;
+}
+
+static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
+						 struct kvm_mmu_notifier_range *range)
+{
+	struct kvm_gfn_range gfn_range;
+	struct kvm_memory_slot *slot;
+	struct kvm_memslots *slots;
+	struct kvm_memslot_iter iter;
+	bool found_memslot = false;
+	bool ret = false;
+	int i;
+
+	gfn_range.arg = range->arg;
+	gfn_range.may_block = range->may_block;
+
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		slots = __kvm_memslots(kvm, i);
+
+		kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) {
+			slot = iter.slot;
+			gfn_range.slot = slot;
+
+			gfn_range.start = max(range->start, slot->base_gfn);
+			gfn_range.end = min(range->end, slot->base_gfn + slot->npages);
+			if (gfn_range.start >= gfn_range.end)
+				continue;
+
+			if (!found_memslot) {
+				found_memslot = true;
+				KVM_MMU_LOCK(kvm);
+				if (!IS_KVM_NULL_FN(range->on_lock))
+					range->on_lock(kvm);
+			}
+
+			ret |= range->handler(kvm, &gfn_range);
+		}
+	}
+
+	if (range->flush_on_ret && ret)
+		kvm_flush_remote_tlbs(kvm);
+
+	if (found_memslot)
+		KVM_MMU_UNLOCK(kvm);
+}
+
+static bool kvm_pre_set_memory_attributes(struct kvm *kvm,
+					  struct kvm_gfn_range *range)
+{
+	/*
+	 * Unconditionally add the range to the invalidation set, regardless of
+	 * whether or not the arch callback actually needs to zap SPTEs.  E.g.
+	 * if KVM supports RWX attributes in the future and the attributes are
+	 * going from R=>RW, zapping isn't strictly necessary.  Unconditionally
+	 * adding the range allows KVM to require that MMU invalidations add at
+	 * least one range between begin() and end(), e.g. allows KVM to detect
+	 * bugs where the add() is missed.  Relaxing the rule *might* be safe,
+	 * but it's not obvious that allowing new mappings while the attributes
+	 * are in flux is desirable or worth the complexity.
+	 */
+	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
+
+	return kvm_arch_pre_set_memory_attributes(kvm, range);
+}
+
+/* Set @attributes for the gfn range [@start, @end). */
+static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attributes)
+{
+	struct kvm_mmu_notifier_range pre_set_range = {
+		.start = start,
+		.end = end,
+		.handler = kvm_pre_set_memory_attributes,
+		.on_lock = kvm_mmu_invalidate_begin,
+		.flush_on_ret = true,
+		.may_block = true,
+	};
+	struct kvm_mmu_notifier_range post_set_range = {
+		.start = start,
+		.end = end,
+		.arg.attributes = attributes,
+		.handler = kvm_arch_post_set_memory_attributes,
+		.on_lock = kvm_mmu_invalidate_end,
+		.may_block = true,
+	};
+	unsigned long i;
+	void *entry;
+	int r = 0;
+
+	entry = attributes ? xa_mk_value(attributes) : NULL;
+
+	mutex_lock(&kvm->slots_lock);
+
+	/* Nothing to do if the entire range as the desired attributes. */
+	if (kvm_range_has_memory_attributes(kvm, start, end, attributes))
+		goto out_unlock;
+
+	/*
+	 * Reserve memory ahead of time to avoid having to deal with failures
+	 * partway through setting the new attributes.
+	 */
+	for (i = start; i < end; i++) {
+		r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
+		if (r)
+			goto out_unlock;
+	}
+
+	kvm_handle_gfn_range(kvm, &pre_set_range);
+
+	for (i = start; i < end; i++) {
+		r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
+				    GFP_KERNEL_ACCOUNT));
+		KVM_BUG_ON(r, kvm);
+	}
+
+	kvm_handle_gfn_range(kvm, &post_set_range);
+
+out_unlock:
+	mutex_unlock(&kvm->slots_lock);
+
+	return r;
+}
+static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
+					   struct kvm_memory_attributes *attrs)
+{
+	gfn_t start, end;
+
+	/* flags is currently not used. */
+	if (attrs->flags)
+		return -EINVAL;
+	if (attrs->attributes & ~kvm_supported_mem_attributes(kvm))
+		return -EINVAL;
+	if (attrs->size == 0 || attrs->address + attrs->size < attrs->address)
+		return -EINVAL;
+	if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size))
+		return -EINVAL;
+
+	start = attrs->address >> PAGE_SHIFT;
+	end = (attrs->address + attrs->size) >> PAGE_SHIFT;
+
+	/*
+	 * xarray tracks data using "unsigned long", and as a result so does
+	 * KVM.  For simplicity, supports generic attributes only on 64-bit
+	 * architectures.
+	 */
+	BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long));
+
+	return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
@@ -4641,6 +4841,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_BINARY_STATS_FD:
 	case KVM_CAP_SYSTEM_EVENT_DATA:
 		return 1;
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	case KVM_CAP_MEMORY_ATTRIBUTES:
+		return kvm_supported_mem_attributes(kvm);
+#endif
 	default:
 		break;
 	}
@@ -5034,6 +5238,18 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	case KVM_SET_MEMORY_ATTRIBUTES: {
+		struct kvm_memory_attributes attrs;
+
+		r = -EFAULT;
+		if (copy_from_user(&attrs, argp, sizeof(attrs)))
+			goto out;
+
+		r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs);
+		break;
+	}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 	case KVM_CREATE_DEVICE: {
 		struct kvm_create_device cd;
 
-- 
GitLab


From 0003e2a414687fff6a75250d381e4abf345d663f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:56 -0700
Subject: [PATCH 0046/4076] mm: Add AS_UNMOVABLE to mark mapping as completely
 unmovable

Add an "unmovable" flag for mappings that cannot be migrated under any
circumstance.  KVM will use the flag for its upcoming GUEST_MEMFD support,
which will not support compaction/migration, at least not in the
foreseeable future.

Test AS_UNMOVABLE under folio lock as already done for the async
compaction/dirty folio case, as the mapping can be removed by truncation
while compaction is running.  To avoid having to lock every folio with a
mapping, assume/require that unmovable mappings are also unevictable, and
have mapping_set_unmovable() also set AS_UNEVICTABLE.

Cc: Matthew Wilcox <willy@infradead.org>
Co-developed-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-15-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/pagemap.h | 19 +++++++++++++++++-
 mm/compaction.c         | 43 +++++++++++++++++++++++++++++------------
 mm/migrate.c            |  2 ++
 3 files changed, 51 insertions(+), 13 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 351c3b7f93a14..82c9bf506b79c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -203,7 +203,8 @@ enum mapping_flags {
 	/* writeback related tags are not used */
 	AS_NO_WRITEBACK_TAGS = 5,
 	AS_LARGE_FOLIO_SUPPORT = 6,
-	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
+	AS_RELEASE_ALWAYS = 7,	/* Call ->release_folio(), even if no private data */
+	AS_UNMOVABLE	= 8,	/* The mapping cannot be moved, ever */
 };
 
 /**
@@ -289,6 +290,22 @@ static inline void mapping_clear_release_always(struct address_space *mapping)
 	clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
 }
 
+static inline void mapping_set_unmovable(struct address_space *mapping)
+{
+	/*
+	 * It's expected unmovable mappings are also unevictable. Compaction
+	 * migrate scanner (isolate_migratepages_block()) relies on this to
+	 * reduce page locking.
+	 */
+	set_bit(AS_UNEVICTABLE, &mapping->flags);
+	set_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
+static inline bool mapping_unmovable(struct address_space *mapping)
+{
+	return test_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return mapping->gfp_mask;
diff --git a/mm/compaction.c b/mm/compaction.c
index 38c8d216c6a3b..12b828aed7c84 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -883,6 +883,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 	/* Time to isolate some pages for migration */
 	for (; low_pfn < end_pfn; low_pfn++) {
+		bool is_dirty, is_unevictable;
 
 		if (skip_on_failure && low_pfn >= next_skip_pfn) {
 			/*
@@ -1080,8 +1081,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!folio_test_lru(folio))
 			goto isolate_fail_put;
 
+		is_unevictable = folio_test_unevictable(folio);
+
 		/* Compaction might skip unevictable pages but CMA takes them */
-		if (!(mode & ISOLATE_UNEVICTABLE) && folio_test_unevictable(folio))
+		if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable)
 			goto isolate_fail_put;
 
 		/*
@@ -1093,26 +1096,42 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio))
 			goto isolate_fail_put;
 
-		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_dirty(folio)) {
-			bool migrate_dirty;
+		is_dirty = folio_test_dirty(folio);
+
+		if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) ||
+		    (mapping && is_unevictable)) {
+			bool migrate_dirty = true;
+			bool is_unmovable;
 
 			/*
 			 * Only folios without mappings or that have
-			 * a ->migrate_folio callback are possible to
-			 * migrate without blocking.  However, we may
-			 * be racing with truncation, which can free
-			 * the mapping.  Truncation holds the folio lock
-			 * until after the folio is removed from the page
-			 * cache so holding it ourselves is sufficient.
+			 * a ->migrate_folio callback are possible to migrate
+			 * without blocking.
+			 *
+			 * Folios from unmovable mappings are not migratable.
+			 *
+			 * However, we can be racing with truncation, which can
+			 * free the mapping that we need to check. Truncation
+			 * holds the folio lock until after the folio is removed
+			 * from the page so holding it ourselves is sufficient.
+			 *
+			 * To avoid locking the folio just to check unmovable,
+			 * assume every unmovable folio is also unevictable,
+			 * which is a cheaper test.  If our assumption goes
+			 * wrong, it's not a correctness bug, just potentially
+			 * wasted cycles.
 			 */
 			if (!folio_trylock(folio))
 				goto isolate_fail_put;
 
 			mapping = folio_mapping(folio);
-			migrate_dirty = !mapping ||
-					mapping->a_ops->migrate_folio;
+			if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) {
+				migrate_dirty = !mapping ||
+						mapping->a_ops->migrate_folio;
+			}
+			is_unmovable = mapping && mapping_unmovable(mapping);
 			folio_unlock(folio);
-			if (!migrate_dirty)
+			if (!migrate_dirty || is_unmovable)
 				goto isolate_fail_put;
 		}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 06086dc9da288..60f2ff6b36aa0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -956,6 +956,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
 
 		if (!mapping)
 			rc = migrate_folio(mapping, dst, src, mode);
+		else if (mapping_unmovable(mapping))
+			rc = -EOPNOTSUPP;
 		else if (mapping->a_ops->migrate_folio)
 			/*
 			 * Most folios have a mapping and most filesystems
-- 
GitLab


From b10a74b5c0c1497f510f91333652fbb060060b69 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:18 +0200
Subject: [PATCH 0047/4076] pinctrl: intel: Provide Intel pin control wide PM
 ops structure

With the help of EXPORT_NS_GPL_DEV_PM_OPS() and
NOIRQ_SYSTEM_SLEEP_PM_OPS() we may convert PM ops functions to become
static. This also takes into account the PM configuration options such
as CONFIG_PM and CONFIG_PM_SLEEP. Hence the first step is to provide
a generic PM ops structure that can be used by drivers directly.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 8 +++++---
 drivers/pinctrl/intel/pinctrl-intel.h | 4 ++--
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 652ba451f885f..b415bdbf87191 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -899,7 +899,7 @@ static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned int offset,
  *
  * Return: a GPIO offset, or negative error code if translation can't be done.
  */
-static __maybe_unused int intel_pin_to_gpio(struct intel_pinctrl *pctrl, int pin)
+static int intel_pin_to_gpio(struct intel_pinctrl *pctrl, int pin)
 {
 	const struct intel_community *community;
 	const struct intel_padgroup *padgrp;
@@ -1682,7 +1682,6 @@ const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_
 }
 EXPORT_SYMBOL_NS_GPL(intel_pinctrl_get_soc_data, PINCTRL_INTEL);
 
-#ifdef CONFIG_PM_SLEEP
 static bool __intel_gpio_is_direct_irq(u32 value)
 {
 	return (value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) &&
@@ -1883,7 +1882,10 @@ int intel_pinctrl_resume_noirq(struct device *dev)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(intel_pinctrl_resume_noirq);
-#endif
+
+EXPORT_NS_GPL_DEV_PM_OPS(intel_pinctrl_pm_ops, PINCTRL_INTEL) = {
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend_noirq, intel_pinctrl_resume_noirq)
+};
 
 MODULE_AUTHOR("Mathias Nyman <mathias.nyman@linux.intel.com>");
 MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index 2bb553598e8bd..d3f511f97ed9f 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -255,10 +255,8 @@ struct intel_pinctrl {
 int intel_pinctrl_probe_by_hid(struct platform_device *pdev);
 int intel_pinctrl_probe_by_uid(struct platform_device *pdev);
 
-#ifdef CONFIG_PM_SLEEP
 int intel_pinctrl_suspend_noirq(struct device *dev);
 int intel_pinctrl_resume_noirq(struct device *dev);
-#endif
 
 #define INTEL_PINCTRL_PM_OPS(_name)					\
 const struct dev_pm_ops _name = {					\
@@ -266,6 +264,8 @@ const struct dev_pm_ops _name = {					\
 				      intel_pinctrl_resume_noirq)	\
 }
 
+extern const struct dev_pm_ops intel_pinctrl_pm_ops;
+
 struct intel_community *intel_get_community(struct intel_pinctrl *pctrl, unsigned int pin);
 
 int intel_get_groups_count(struct pinctrl_dev *pctldev);
-- 
GitLab


From 33f1c0b0bf22c6c7922e9b49b9cbcc4e9c441640 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:19 +0200
Subject: [PATCH 0048/4076] pinctrl: alderlake: Switch to use Intel pin control
 PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-alderlake.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-alderlake.c b/drivers/pinctrl/intel/pinctrl-alderlake.c
index 4a37dc273d635..7d9948e5f422f 100644
--- a/drivers/pinctrl/intel/pinctrl-alderlake.c
+++ b/drivers/pinctrl/intel/pinctrl-alderlake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -733,14 +734,12 @@ static const struct acpi_device_id adl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, adl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(adl_pinctrl_pm_ops);
-
 static struct platform_driver adl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "alderlake-pinctrl",
 		.acpi_match_table = adl_pinctrl_acpi_match,
-		.pm = &adl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(adl_pinctrl_driver);
-- 
GitLab


From 4cc4ff1b24dd1621e6bf9a2ac69c5d7d5da4e8bf Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:20 +0200
Subject: [PATCH 0049/4076] pinctrl: broxton: Switch to use Intel pin control
 PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-broxton.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index 3118c7c8842fe..d99541676630d 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -1000,14 +1001,12 @@ static const struct platform_device_id bxt_pinctrl_platform_ids[] = {
 };
 MODULE_DEVICE_TABLE(platform, bxt_pinctrl_platform_ids);
 
-static INTEL_PINCTRL_PM_OPS(bxt_pinctrl_pm_ops);
-
 static struct platform_driver bxt_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_uid,
 	.driver = {
 		.name = "broxton-pinctrl",
 		.acpi_match_table = bxt_pinctrl_acpi_match,
-		.pm = &bxt_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 	.id_table = bxt_pinctrl_platform_ids,
 };
-- 
GitLab


From 020861b5ce169c6beb8f6507b926ba899c20e9f1 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:21 +0200
Subject: [PATCH 0050/4076] pinctrl: cannonlake: Switch to use Intel pin
 control PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-cannonlake.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c
index 95976abfb7850..1aa09f950be1e 100644
--- a/drivers/pinctrl/intel/pinctrl-cannonlake.c
+++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c
@@ -10,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -824,14 +825,12 @@ static const struct acpi_device_id cnl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, cnl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(cnl_pinctrl_pm_ops);
-
 static struct platform_driver cnl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "cannonlake-pinctrl",
 		.acpi_match_table = cnl_pinctrl_acpi_match,
-		.pm = &cnl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(cnl_pinctrl_driver);
-- 
GitLab


From a4f777ef3020c3ff39d1c3de70bfb2d95897e728 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:22 +0200
Subject: [PATCH 0051/4076] pinctrl: cedarfork: Switch to use Intel pin control
 PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-6-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-cedarfork.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-cedarfork.c b/drivers/pinctrl/intel/pinctrl-cedarfork.c
index a20465eb2dc68..48af8930dd1f9 100644
--- a/drivers/pinctrl/intel/pinctrl-cedarfork.c
+++ b/drivers/pinctrl/intel/pinctrl-cedarfork.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -319,8 +320,6 @@ static const struct intel_pinctrl_soc_data cdf_soc_data = {
 	.ncommunities = ARRAY_SIZE(cdf_communities),
 };
 
-static INTEL_PINCTRL_PM_OPS(cdf_pinctrl_pm_ops);
-
 static const struct acpi_device_id cdf_pinctrl_acpi_match[] = {
 	{ "INTC3001", (kernel_ulong_t)&cdf_soc_data },
 	{ }
@@ -332,7 +331,7 @@ static struct platform_driver cdf_pinctrl_driver = {
 	.driver = {
 		.name = "cedarfork-pinctrl",
 		.acpi_match_table = cdf_pinctrl_acpi_match,
-		.pm = &cdf_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 
-- 
GitLab


From 6dde85169a62ec71140dec3b0c85f78cd1a539e3 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:23 +0200
Subject: [PATCH 0052/4076] pinctrl: denverton: Switch to use Intel pin control
 PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-7-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-denverton.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-denverton.c b/drivers/pinctrl/intel/pinctrl-denverton.c
index 562a4f9188e4b..666507f54f276 100644
--- a/drivers/pinctrl/intel/pinctrl-denverton.c
+++ b/drivers/pinctrl/intel/pinctrl-denverton.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -249,8 +250,6 @@ static const struct intel_pinctrl_soc_data dnv_soc_data = {
 	.ncommunities = ARRAY_SIZE(dnv_communities),
 };
 
-static INTEL_PINCTRL_PM_OPS(dnv_pinctrl_pm_ops);
-
 static const struct acpi_device_id dnv_pinctrl_acpi_match[] = {
 	{ "INTC3000", (kernel_ulong_t)&dnv_soc_data },
 	{ }
@@ -268,7 +267,7 @@ static struct platform_driver dnv_pinctrl_driver = {
 	.driver = {
 		.name = "denverton-pinctrl",
 		.acpi_match_table = dnv_pinctrl_acpi_match,
-		.pm = &dnv_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 	.id_table = dnv_pinctrl_platform_ids,
 };
-- 
GitLab


From ec79e6e6fb069c84539efc5346c4fe687802c9f6 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:24 +0200
Subject: [PATCH 0053/4076] pinctrl: elkhartlake: Switch to use Intel pin
 control PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-8-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-elkhartlake.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-elkhartlake.c b/drivers/pinctrl/intel/pinctrl-elkhartlake.c
index 81581ab853167..1678634ebc06c 100644
--- a/drivers/pinctrl/intel/pinctrl-elkhartlake.c
+++ b/drivers/pinctrl/intel/pinctrl-elkhartlake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -485,14 +486,12 @@ static const struct acpi_device_id ehl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, ehl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(ehl_pinctrl_pm_ops);
-
 static struct platform_driver ehl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_uid,
 	.driver = {
 		.name = "elkhartlake-pinctrl",
 		.acpi_match_table = ehl_pinctrl_acpi_match,
-		.pm = &ehl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(ehl_pinctrl_driver);
-- 
GitLab


From e35ed82182f6963a2af7dfd151cdac6987133892 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:25 +0200
Subject: [PATCH 0054/4076] pinctrl: emmitsburg: Switch to use Intel pin
 control PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-9-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-emmitsburg.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-emmitsburg.c b/drivers/pinctrl/intel/pinctrl-emmitsburg.c
index 099ec8351d5fa..e4798d32492c5 100644
--- a/drivers/pinctrl/intel/pinctrl-emmitsburg.c
+++ b/drivers/pinctrl/intel/pinctrl-emmitsburg.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -358,14 +359,12 @@ static const struct acpi_device_id ebg_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, ebg_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(ebg_pinctrl_pm_ops);
-
 static struct platform_driver ebg_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "emmitsburg-pinctrl",
 		.acpi_match_table = ebg_pinctrl_acpi_match,
-		.pm = &ebg_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(ebg_pinctrl_driver);
-- 
GitLab


From 3f6791067ddab69589621d7efb3821adba70b4c7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:26 +0200
Subject: [PATCH 0055/4076] pinctrl: geminilake: Switch to use Intel pin
 control PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-10-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-geminilake.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-geminilake.c b/drivers/pinctrl/intel/pinctrl-geminilake.c
index 9effa06b61e91..6dcf0ac2059f5 100644
--- a/drivers/pinctrl/intel/pinctrl-geminilake.c
+++ b/drivers/pinctrl/intel/pinctrl-geminilake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -447,14 +448,12 @@ static const struct acpi_device_id glk_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, glk_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(glk_pinctrl_pm_ops);
-
 static struct platform_driver glk_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_uid,
 	.driver = {
 		.name = "geminilake-pinctrl",
 		.acpi_match_table = glk_pinctrl_acpi_match,
-		.pm = &glk_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 
-- 
GitLab


From b70c674cf40521275676af9d8d43819f25a41946 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:27 +0200
Subject: [PATCH 0056/4076] pinctrl: icelake: Switch to use Intel pin control
 PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-11-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-icelake.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-icelake.c b/drivers/pinctrl/intel/pinctrl-icelake.c
index 300e1538c8d05..fe3042de891a6 100644
--- a/drivers/pinctrl/intel/pinctrl-icelake.c
+++ b/drivers/pinctrl/intel/pinctrl-icelake.c
@@ -10,6 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -668,8 +669,6 @@ static const struct intel_pinctrl_soc_data icln_soc_data = {
 	.ncommunities = ARRAY_SIZE(icln_communities),
 };
 
-static INTEL_PINCTRL_PM_OPS(icl_pinctrl_pm_ops);
-
 static const struct acpi_device_id icl_pinctrl_acpi_match[] = {
 	{ "INT3455", (kernel_ulong_t)&icllp_soc_data },
 	{ "INT34C3", (kernel_ulong_t)&icln_soc_data },
@@ -682,7 +681,7 @@ static struct platform_driver icl_pinctrl_driver = {
 	.driver = {
 		.name = "icelake-pinctrl",
 		.acpi_match_table = icl_pinctrl_acpi_match,
-		.pm = &icl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(icl_pinctrl_driver);
-- 
GitLab


From 5ce3422e04135680697abb6f8ff577d38173247c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:28 +0200
Subject: [PATCH 0057/4076] pinctrl: jasperlake: Switch to use Intel pin
 control PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-12-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-jasperlake.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-jasperlake.c b/drivers/pinctrl/intel/pinctrl-jasperlake.c
index 50f137deed9c1..3525480428ea6 100644
--- a/drivers/pinctrl/intel/pinctrl-jasperlake.c
+++ b/drivers/pinctrl/intel/pinctrl-jasperlake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -326,14 +327,12 @@ static const struct acpi_device_id jsl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, jsl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(jsl_pinctrl_pm_ops);
-
 static struct platform_driver jsl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "jasperlake-pinctrl",
 		.acpi_match_table = jsl_pinctrl_acpi_match,
-		.pm = &jsl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(jsl_pinctrl_driver);
-- 
GitLab


From 8e5f001396dfb030ec10f3c4c8cdd23f7a51aa46 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:29 +0200
Subject: [PATCH 0058/4076] pinctrl: lakefield: Switch to use Intel pin control
 PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-13-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-lakefield.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-lakefield.c b/drivers/pinctrl/intel/pinctrl-lakefield.c
index 0b94e11b78ac2..adef85db82ca7 100644
--- a/drivers/pinctrl/intel/pinctrl-lakefield.c
+++ b/drivers/pinctrl/intel/pinctrl-lakefield.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -347,14 +348,12 @@ static const struct acpi_device_id lkf_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, lkf_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(lkf_pinctrl_pm_ops);
-
 static struct platform_driver lkf_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "lakefield-pinctrl",
 		.acpi_match_table = lkf_pinctrl_acpi_match,
-		.pm = &lkf_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(lkf_pinctrl_driver);
-- 
GitLab


From 5d5e83f973eddc4703efa85781329be6de87cb75 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:30 +0200
Subject: [PATCH 0059/4076] pinctrl: lewisburg: Switch to use Intel pin control
 PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-14-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-lewisburg.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-lewisburg.c b/drivers/pinctrl/intel/pinctrl-lewisburg.c
index aa725a5d62b9c..a304d30ea9ed3 100644
--- a/drivers/pinctrl/intel/pinctrl-lewisburg.c
+++ b/drivers/pinctrl/intel/pinctrl-lewisburg.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -301,8 +302,6 @@ static const struct intel_pinctrl_soc_data lbg_soc_data = {
 	.ncommunities = ARRAY_SIZE(lbg_communities),
 };
 
-static INTEL_PINCTRL_PM_OPS(lbg_pinctrl_pm_ops);
-
 static const struct acpi_device_id lbg_pinctrl_acpi_match[] = {
 	{ "INT3536", (kernel_ulong_t)&lbg_soc_data },
 	{ }
@@ -314,7 +313,7 @@ static struct platform_driver lbg_pinctrl_driver = {
 	.driver = {
 		.name = "lewisburg-pinctrl",
 		.acpi_match_table = lbg_pinctrl_acpi_match,
-		.pm = &lbg_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(lbg_pinctrl_driver);
-- 
GitLab


From 4a3b7e6a27127828f21f5f4c4577684e0c16ba94 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:31 +0200
Subject: [PATCH 0060/4076] pinctrl: meteorlake: Switch to use Intel pin
 control PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-15-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-meteorlake.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-meteorlake.c b/drivers/pinctrl/intel/pinctrl-meteorlake.c
index 7ced2b402dce0..cc44890c6699d 100644
--- a/drivers/pinctrl/intel/pinctrl-meteorlake.c
+++ b/drivers/pinctrl/intel/pinctrl-meteorlake.c
@@ -9,6 +9,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -589,14 +590,12 @@ static const struct acpi_device_id mtl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, mtl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(mtl_pinctrl_pm_ops);
-
 static struct platform_driver mtl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "meteorlake-pinctrl",
 		.acpi_match_table = mtl_pinctrl_acpi_match,
-		.pm = &mtl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(mtl_pinctrl_driver);
-- 
GitLab


From 0a327638cf4f324ff501adad922c1e7f5919c111 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:32 +0200
Subject: [PATCH 0061/4076] pinctrl: sunrisepoint: Switch to use Intel pin
 control PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-16-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-sunrisepoint.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index b7a40ab0bca8f..55df9d2cfb1be 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -10,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -579,14 +580,12 @@ static const struct acpi_device_id spt_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, spt_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(spt_pinctrl_pm_ops);
-
 static struct platform_driver spt_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "sunrisepoint-pinctrl",
 		.acpi_match_table = spt_pinctrl_acpi_match,
-		.pm = &spt_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 
-- 
GitLab


From ee4c71f5771dc232001e055c818d2f2ea7ebf911 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:33 +0200
Subject: [PATCH 0062/4076] pinctrl: tigerlake: Switch to use Intel pin control
 PM ops

The main driver conditionally exports the PM ops structure.
Switch this driver to use it instead of customly wrapped one.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-17-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-tigerlake.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-tigerlake.c b/drivers/pinctrl/intel/pinctrl-tigerlake.c
index 4768a69a92588..80cd7a06fe5ad 100644
--- a/drivers/pinctrl/intel/pinctrl-tigerlake.c
+++ b/drivers/pinctrl/intel/pinctrl-tigerlake.c
@@ -10,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 
 #include <linux/pinctrl/pinctrl.h>
 
@@ -743,14 +744,12 @@ static const struct acpi_device_id tgl_pinctrl_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, tgl_pinctrl_acpi_match);
 
-static INTEL_PINCTRL_PM_OPS(tgl_pinctrl_pm_ops);
-
 static struct platform_driver tgl_pinctrl_driver = {
 	.probe = intel_pinctrl_probe_by_hid,
 	.driver = {
 		.name = "tigerlake-pinctrl",
 		.acpi_match_table = tgl_pinctrl_acpi_match,
-		.pm = &tgl_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
 	},
 };
 module_platform_driver(tgl_pinctrl_driver);
-- 
GitLab


From 649e984f5ed8ca868f19a480966cc0820f76e22a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 14:07:34 +0200
Subject: [PATCH 0063/4076] pinctrl: intel: Make PM ops functions static

No more users outside of the main module.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231030120734.2831419-18-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 6 ++----
 drivers/pinctrl/intel/pinctrl-intel.h | 9 ---------
 2 files changed, 2 insertions(+), 13 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index b415bdbf87191..2015b711d0775 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1727,7 +1727,7 @@ static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int
 	return false;
 }
 
-int intel_pinctrl_suspend_noirq(struct device *dev)
+static int intel_pinctrl_suspend_noirq(struct device *dev)
 {
 	struct intel_pinctrl *pctrl = dev_get_drvdata(dev);
 	struct intel_community_context *communities;
@@ -1770,7 +1770,6 @@ int intel_pinctrl_suspend_noirq(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_pinctrl_suspend_noirq);
 
 static bool intel_gpio_update_reg(void __iomem *reg, u32 mask, u32 value)
 {
@@ -1837,7 +1836,7 @@ static void intel_restore_padcfg(struct intel_pinctrl *pctrl, unsigned int pin,
 	dev_dbg(dev, "restored pin %u padcfg%u %#08x\n", pin, n, readl(padcfg));
 }
 
-int intel_pinctrl_resume_noirq(struct device *dev)
+static int intel_pinctrl_resume_noirq(struct device *dev)
 {
 	struct intel_pinctrl *pctrl = dev_get_drvdata(dev);
 	const struct intel_community_context *communities;
@@ -1881,7 +1880,6 @@ int intel_pinctrl_resume_noirq(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_pinctrl_resume_noirq);
 
 EXPORT_NS_GPL_DEV_PM_OPS(intel_pinctrl_pm_ops, PINCTRL_INTEL) = {
 	NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend_noirq, intel_pinctrl_resume_noirq)
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index d3f511f97ed9f..e7d911a655842 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -255,15 +255,6 @@ struct intel_pinctrl {
 int intel_pinctrl_probe_by_hid(struct platform_device *pdev);
 int intel_pinctrl_probe_by_uid(struct platform_device *pdev);
 
-int intel_pinctrl_suspend_noirq(struct device *dev);
-int intel_pinctrl_resume_noirq(struct device *dev);
-
-#define INTEL_PINCTRL_PM_OPS(_name)					\
-const struct dev_pm_ops _name = {					\
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend_noirq,	\
-				      intel_pinctrl_resume_noirq)	\
-}
-
 extern const struct dev_pm_ops intel_pinctrl_pm_ops;
 
 struct intel_community *intel_get_community(struct intel_pinctrl *pctrl, unsigned int pin);
-- 
GitLab


From 2b9282afa8e9c34c42de42c2064a056a735fd7f0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 16:14:04 +0200
Subject: [PATCH 0064/4076] pinctrl: tangier: Enable 910 Ohm bias

Family 7 (I2C) supports special bias value, i.e. 910 Ohm.

Enable it for configuring pin.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-tangier.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/pinctrl/intel/pinctrl-tangier.c b/drivers/pinctrl/intel/pinctrl-tangier.c
index 40dd60c9e5267..007bca1cf2249 100644
--- a/drivers/pinctrl/intel/pinctrl-tangier.c
+++ b/drivers/pinctrl/intel/pinctrl-tangier.c
@@ -382,6 +382,9 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 		case 2000:
 			term = BUFCFG_PUPD_VAL_2K;
 			break;
+		case 910:
+			term = BUFCFG_PUPD_VAL_910;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -405,6 +408,9 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 		case 2000:
 			term = BUFCFG_PUPD_VAL_2K;
 			break;
+		case 910:
+			term = BUFCFG_PUPD_VAL_910;
+			break;
 		default:
 			return -EINVAL;
 		}
-- 
GitLab


From 0a4cfed79e4f4498c5f9d76c7e149e51a32d5be5 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 17:53:40 +0200
Subject: [PATCH 0065/4076] pinctrl: tangier: Move default strength assignment
 to a switch-case

iWhen ->pin_config_set() is called from the GPIO library (assumed
GpioIo() ACPI resource), the argument can be 1, when, for example,
PullDefault is provided. In such case we supply sane default in
the driver. Move that default assingment to a switch-case, so
it will be consolidated in one place.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-tangier.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-tangier.c b/drivers/pinctrl/intel/pinctrl-tangier.c
index 007bca1cf2249..26e34ec0a9720 100644
--- a/drivers/pinctrl/intel/pinctrl-tangier.c
+++ b/drivers/pinctrl/intel/pinctrl-tangier.c
@@ -368,14 +368,11 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 		break;
 
 	case PIN_CONFIG_BIAS_PULL_UP:
-		/* Set default strength value in case none is given */
-		if (arg == 1)
-			arg = 20000;
-
 		switch (arg) {
 		case 50000:
 			term = BUFCFG_PUPD_VAL_50K;
 			break;
+		case 1: /* Set default strength value in case none is given */
 		case 20000:
 			term = BUFCFG_PUPD_VAL_20K;
 			break;
@@ -394,14 +391,11 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 		break;
 
 	case PIN_CONFIG_BIAS_PULL_DOWN:
-		/* Set default strength value in case none is given */
-		if (arg == 1)
-			arg = 20000;
-
 		switch (arg) {
 		case 50000:
 			term = BUFCFG_PUPD_VAL_50K;
 			break;
+		case 1: /* Set default strength value in case none is given */
 		case 20000:
 			term = BUFCFG_PUPD_VAL_20K;
 			break;
-- 
GitLab


From 6217728b38580bd3a4c6db6f65359f93c52f5901 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 17:54:32 +0200
Subject: [PATCH 0066/4076] pinctrl: intel: Move default strength assignment to
 a switch-case

iWhen ->pin_config_set() is called from the GPIO library (assumed
GpioIo() ACPI resource), the argument can be 1, when, for example,
PullDefault is provided. In such case we supply sane default in
the driver. Move that default assingment to a switch-case, so
it will be consolidated in one place.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 2015b711d0775..e8b41a321fcb6 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -677,10 +677,6 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin,
 	u32 term = 0, up = 0, value;
 	void __iomem *padcfg1;
 
-	/* Set default strength value in case none is given */
-	if (arg == 1)
-		arg = 5000;
-
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
 		break;
@@ -690,6 +686,7 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin,
 		case 20000:
 			term = PADCFG1_TERM_20K;
 			break;
+		case 1: /* Set default strength value in case none is given */
 		case 5000:
 			term = PADCFG1_TERM_5K;
 			break;
@@ -716,6 +713,7 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin,
 		case 20000:
 			term = PADCFG1_TERM_20K;
 			break;
+		case 1: /* Set default strength value in case none is given */
 		case 5000:
 			term = PADCFG1_TERM_5K;
 			break;
-- 
GitLab


From a35c62ba7ae5f96f6e2683beed3f9c7ee37548cf Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 17:59:06 +0200
Subject: [PATCH 0067/4076] pinctrl: intel: Refactor
 intel_pinctrl_get_soc_data()

Refactor intel_pinctrl_get_soc_data() to drop initial assignment
of the data variable. It's only used in ACPI case and instead
we may always assign it there as the ACPI ID table has the terminator
entry that has driver data set to NULL.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index e8b41a321fcb6..62daf189d3f49 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1651,7 +1651,7 @@ EXPORT_SYMBOL_NS_GPL(intel_pinctrl_probe_by_uid, PINCTRL_INTEL);
 const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_device *pdev)
 {
 	const struct intel_pinctrl_soc_data * const *table;
-	const struct intel_pinctrl_soc_data *data = NULL;
+	const struct intel_pinctrl_soc_data *data;
 	struct device *dev = &pdev->dev;
 
 	table = device_get_match_data(dev);
@@ -1660,11 +1660,10 @@ const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_
 		unsigned int i;
 
 		for (i = 0; table[i]; i++) {
-			if (acpi_dev_uid_match(adev, table[i]->uid)) {
-				data = table[i];
+			if (acpi_dev_uid_match(adev, table[i]->uid))
 				break;
-			}
 		}
+		data = table[i];
 	} else {
 		const struct platform_device_id *id;
 
-- 
GitLab


From bf800ca415676085813ad53899264618a60db471 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 29 Sep 2023 14:21:01 +0200
Subject: [PATCH 0068/4076] pinctrl: tegra: Display pin function in
 pinconf-groups

The function that a pin is muxed to can be read from the top-level
pinctrl-maps debugfs file. However, this only reflects the values that
were specified in device tree, so they will only show deviations from
the hardware default setting. Display the current pinmux setting in the
per-controller pinconf-groups debugfs file along with the rest of the
per-pin configuration settings.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Tested-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://lore.kernel.org/r/20230929122101.466266-1-thierry.reding@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/tegra/pinctrl-tegra.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index 6bf8db424bec2..ccfa3870a67d3 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -636,6 +636,14 @@ static void tegra_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 		seq_printf(s, "\n\t%s=%u",
 			   strip_prefix(cfg_params[i].property), val);
 	}
+
+	if (g->mux_reg >= 0) {
+		/* read pinmux function and dump to seq_file */
+		val = pmx_readl(pmx, g->mux_bank, g->mux_reg);
+		val = g->funcs[(val >> g->mux_bit) & 0x3];
+
+		seq_printf(s, "\n\tfunction=%s", pmx->functions[val].name);
+	}
 }
 
 static void tegra_pinconf_config_dbg_show(struct pinctrl_dev *pctldev,
-- 
GitLab


From 2220638d375a15864ef6b933b9057a92dd566c07 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 27 Oct 2023 11:36:14 +0200
Subject: [PATCH 0069/4076] dt-bindings: pinctrl:
 qcom,sm8650-lpass-lpi-pinctrl: add SM8650 LPASS

Add bindings for the pin controller in Low Power Audio SubSystem (LPASS)
of Qualcomm SM8650 SoC.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231027093615.140656-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../qcom,sm8650-lpass-lpi-pinctrl.yaml        | 148 ++++++++++++++++++
 1 file changed, 148 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
new file mode 100644
index 0000000000000..f5736ed140ee7
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
@@ -0,0 +1,148 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm SM8650 SoC LPASS LPI TLMM
+
+maintainers:
+  - Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+  - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+
+description:
+  Top Level Mode Multiplexer pin controller in the Low Power Audio SubSystem
+  (LPASS) Low Power Island (LPI) of Qualcomm SM8650 SoC.
+
+properties:
+  compatible:
+    const: qcom,sm8650-lpass-lpi-pinctrl
+
+  reg:
+    items:
+      - description: LPASS LPI TLMM Control and Status registers
+
+  clocks:
+    items:
+      - description: LPASS Core voting clock
+      - description: LPASS Audio voting clock
+
+  clock-names:
+    items:
+      - const: core
+      - const: audio
+
+  gpio-controller: true
+
+  "#gpio-cells":
+    description: Specifying the pin number and flags, as defined in
+      include/dt-bindings/gpio/gpio.h
+    const: 2
+
+  gpio-ranges:
+    maxItems: 1
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-sm8650-lpass-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-sm8650-lpass-state"
+        additionalProperties: false
+
+$defs:
+  qcom-sm8650-lpass-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: /schemas/pinctrl/pincfg-node.yaml
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          pattern: "^gpio([0-9]|1[0-9]|2[0-2])$"
+
+      function:
+        enum: [ dmic1_clk, dmic1_data, dmic2_clk, dmic2_data, dmic3_clk,
+                dmic3_data, dmic4_clk, dmic4_data, ext_mclk1_a, ext_mclk1_b,
+                ext_mclk1_c, ext_mclk1_d, ext_mclk1_e, gpio, i2s0_clk,
+                i2s0_data, i2s0_ws, i2s1_clk, i2s1_data, i2s1_ws, i2s2_clk,
+                i2s2_data, i2s2_ws, i2s3_clk, i2s3_data, i2s3_ws, i2s4_clk,
+                i2s4_data, i2s4_ws, qca_swr_clk, qca_swr_data, slimbus_clk,
+                slimbus_data, swr_rx_clk, swr_rx_data, swr_tx_clk, swr_tx_data,
+                wsa_swr_clk, wsa_swr_data, wsa2_swr_clk, wsa2_swr_data ]
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+
+      drive-strength:
+        enum: [2, 4, 6, 8, 10, 12, 14, 16]
+        default: 2
+        description:
+          Selects the drive strength for the specified pins, in mA.
+
+      slew-rate:
+        enum: [0, 1, 2, 3]
+        default: 0
+        description: |
+          0: No adjustments
+          1: Higher Slew rate (faster edges)
+          2: Lower Slew rate (slower edges)
+          3: Reserved (No adjustments)
+
+      bias-bus-hold: true
+      bias-pull-down: true
+      bias-pull-up: true
+      bias-disable: true
+      input-enable: true
+      output-high: true
+      output-low: true
+
+    required:
+      - pins
+      - function
+
+    additionalProperties: false
+
+allOf:
+  - $ref: pinctrl.yaml#
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - gpio-controller
+  - "#gpio-cells"
+  - gpio-ranges
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/sound/qcom,q6dsp-lpass-ports.h>
+
+    lpass_tlmm: pinctrl@6e80000 {
+        compatible = "qcom,sm8650-lpass-lpi-pinctrl";
+        reg = <0x06e80000 0x20000>;
+
+        clocks = <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+                 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
+        clock-names = "core", "audio";
+
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&lpass_tlmm 0 0 23>;
+
+        tx-swr-sleep-clk-state {
+            pins = "gpio0";
+            function = "swr_tx_clk";
+            drive-strength = <2>;
+            bias-pull-down;
+        };
+    };
-- 
GitLab


From c4e47673853f2b020e2390832e9df83b3a84d7b0 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 27 Oct 2023 11:36:15 +0200
Subject: [PATCH 0070/4076] pinctrl: qcom: sm8650-lpass-lpi: add SM8650 LPASS

Add driver for the pin controller in Low Power Audio SubSystem (LPASS)
of Qualcomm SM8650 SoC.

Notable differences against SM8550 LPASS pin controller:
1. Additional address space for slew rate thus driver uses
   LPI_FLAG_SLEW_RATE_SAME_REG and sets slew rate via different
   register.

2. Two new pin mux functions: qca_swr_clk and qca_swr_data

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231027093615.140656-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig                  |  10 +
 drivers/pinctrl/qcom/Makefile                 |   1 +
 .../pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c   | 255 ++++++++++++++++++
 3 files changed, 266 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c

diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig
index f84c0d3b79517..e0f2829c15d6a 100644
--- a/drivers/pinctrl/qcom/Kconfig
+++ b/drivers/pinctrl/qcom/Kconfig
@@ -124,4 +124,14 @@ config PINCTRL_SM8550_LPASS_LPI
 	  (Low Power Island) found on the Qualcomm Technologies Inc SM8550
 	  platform.
 
+config PINCTRL_SM8650_LPASS_LPI
+	tristate "Qualcomm Technologies Inc SM8550 LPASS LPI pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	depends on PINCTRL_LPASS_LPI
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm Technologies Inc LPASS (Low Power Audio SubSystem) LPI
+	  (Low Power Island) found on the Qualcomm Technologies Inc SM8650
+	  platform.
+
 endif
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index 5910e08c84cec..f7b410e59bf1d 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -58,5 +58,6 @@ obj-$(CONFIG_PINCTRL_SM8450) += pinctrl-sm8450.o
 obj-$(CONFIG_PINCTRL_SM8450_LPASS_LPI) += pinctrl-sm8450-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SM8550) += pinctrl-sm8550.o
 obj-$(CONFIG_PINCTRL_SM8550_LPASS_LPI) += pinctrl-sm8550-lpass-lpi.o
+obj-$(CONFIG_PINCTRL_SM8650_LPASS_LPI) += pinctrl-sm8650-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SC8280XP_LPASS_LPI) += pinctrl-sc8280xp-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_LPASS_LPI) += pinctrl-lpass-lpi.o
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
new file mode 100644
index 0000000000000..6e4be91ff085d
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
@@ -0,0 +1,255 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022-2023 Linaro Ltd.
+ */
+
+#include <linux/gpio/driver.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-lpass-lpi.h"
+
+enum lpass_lpi_functions {
+	LPI_MUX_dmic1_clk,
+	LPI_MUX_dmic1_data,
+	LPI_MUX_dmic2_clk,
+	LPI_MUX_dmic2_data,
+	LPI_MUX_dmic3_clk,
+	LPI_MUX_dmic3_data,
+	LPI_MUX_dmic4_clk,
+	LPI_MUX_dmic4_data,
+	LPI_MUX_i2s0_clk,
+	LPI_MUX_i2s0_data,
+	LPI_MUX_i2s0_ws,
+	LPI_MUX_i2s1_clk,
+	LPI_MUX_i2s1_data,
+	LPI_MUX_i2s1_ws,
+	LPI_MUX_i2s2_clk,
+	LPI_MUX_i2s2_data,
+	LPI_MUX_i2s2_ws,
+	LPI_MUX_i2s3_clk,
+	LPI_MUX_i2s3_data,
+	LPI_MUX_i2s3_ws,
+	LPI_MUX_i2s4_clk,
+	LPI_MUX_i2s4_data,
+	LPI_MUX_i2s4_ws,
+	LPI_MUX_qca_swr_clk,
+	LPI_MUX_qca_swr_data,
+	LPI_MUX_slimbus_clk,
+	LPI_MUX_slimbus_data,
+	LPI_MUX_swr_rx_clk,
+	LPI_MUX_swr_rx_data,
+	LPI_MUX_swr_tx_clk,
+	LPI_MUX_swr_tx_data,
+	LPI_MUX_wsa_swr_clk,
+	LPI_MUX_wsa_swr_data,
+	LPI_MUX_wsa2_swr_clk,
+	LPI_MUX_wsa2_swr_data,
+	LPI_MUX_ext_mclk1_a,
+	LPI_MUX_ext_mclk1_b,
+	LPI_MUX_ext_mclk1_c,
+	LPI_MUX_ext_mclk1_d,
+	LPI_MUX_ext_mclk1_e,
+	LPI_MUX_gpio,
+	LPI_MUX__,
+};
+
+static int gpio0_pins[] = { 0 };
+static int gpio1_pins[] = { 1 };
+static int gpio2_pins[] = { 2 };
+static int gpio3_pins[] = { 3 };
+static int gpio4_pins[] = { 4 };
+static int gpio5_pins[] = { 5 };
+static int gpio6_pins[] = { 6 };
+static int gpio7_pins[] = { 7 };
+static int gpio8_pins[] = { 8 };
+static int gpio9_pins[] = { 9 };
+static int gpio10_pins[] = { 10 };
+static int gpio11_pins[] = { 11 };
+static int gpio12_pins[] = { 12 };
+static int gpio13_pins[] = { 13 };
+static int gpio14_pins[] = { 14 };
+static int gpio15_pins[] = { 15 };
+static int gpio16_pins[] = { 16 };
+static int gpio17_pins[] = { 17 };
+static int gpio18_pins[] = { 18 };
+static int gpio19_pins[] = { 19 };
+static int gpio20_pins[] = { 20 };
+static int gpio21_pins[] = { 21 };
+static int gpio22_pins[] = { 22 };
+
+static const struct pinctrl_pin_desc sm8650_lpi_pins[] = {
+	PINCTRL_PIN(0, "gpio0"),
+	PINCTRL_PIN(1, "gpio1"),
+	PINCTRL_PIN(2, "gpio2"),
+	PINCTRL_PIN(3, "gpio3"),
+	PINCTRL_PIN(4, "gpio4"),
+	PINCTRL_PIN(5, "gpio5"),
+	PINCTRL_PIN(6, "gpio6"),
+	PINCTRL_PIN(7, "gpio7"),
+	PINCTRL_PIN(8, "gpio8"),
+	PINCTRL_PIN(9, "gpio9"),
+	PINCTRL_PIN(10, "gpio10"),
+	PINCTRL_PIN(11, "gpio11"),
+	PINCTRL_PIN(12, "gpio12"),
+	PINCTRL_PIN(13, "gpio13"),
+	PINCTRL_PIN(14, "gpio14"),
+	PINCTRL_PIN(15, "gpio15"),
+	PINCTRL_PIN(16, "gpio16"),
+	PINCTRL_PIN(17, "gpio17"),
+	PINCTRL_PIN(18, "gpio18"),
+	PINCTRL_PIN(19, "gpio19"),
+	PINCTRL_PIN(20, "gpio20"),
+	PINCTRL_PIN(21, "gpio21"),
+	PINCTRL_PIN(22, "gpio22"),
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22",
+};
+
+static const char * const dmic1_clk_groups[] = { "gpio6" };
+static const char * const dmic1_data_groups[] = { "gpio7" };
+static const char * const dmic2_clk_groups[] = { "gpio8" };
+static const char * const dmic2_data_groups[] = { "gpio9" };
+static const char * const dmic3_clk_groups[] = { "gpio12" };
+static const char * const dmic3_data_groups[] = { "gpio13" };
+static const char * const dmic4_clk_groups[] = { "gpio17" };
+static const char * const dmic4_data_groups[] = { "gpio18" };
+static const char * const i2s0_clk_groups[] = { "gpio0" };
+static const char * const i2s0_ws_groups[] = { "gpio1" };
+static const char * const i2s0_data_groups[] = { "gpio2", "gpio3", "gpio4", "gpio5" };
+static const char * const i2s1_clk_groups[] = { "gpio6" };
+static const char * const i2s1_ws_groups[] = { "gpio7" };
+static const char * const i2s1_data_groups[] = { "gpio8", "gpio9" };
+static const char * const i2s2_clk_groups[] = { "gpio10" };
+static const char * const i2s2_ws_groups[] = { "gpio11" };
+static const char * const i2s2_data_groups[] = { "gpio15", "gpio16" };
+static const char * const i2s3_clk_groups[] = { "gpio12" };
+static const char * const i2s3_ws_groups[] = { "gpio13" };
+static const char * const i2s3_data_groups[] = { "gpio17", "gpio18" };
+static const char * const i2s4_clk_groups[] = { "gpio19"};
+static const char * const i2s4_ws_groups[] = { "gpio20"};
+static const char * const i2s4_data_groups[] = { "gpio21", "gpio22"};
+static const char * const qca_swr_clk_groups[] = { "gpio19" };
+static const char * const qca_swr_data_groups[] = { "gpio20" };
+static const char * const slimbus_clk_groups[] = { "gpio19"};
+static const char * const slimbus_data_groups[] = { "gpio20"};
+static const char * const swr_tx_clk_groups[] = { "gpio0" };
+static const char * const swr_tx_data_groups[] = { "gpio1", "gpio2", "gpio14" };
+static const char * const swr_rx_clk_groups[] = { "gpio3" };
+static const char * const swr_rx_data_groups[] = { "gpio4", "gpio5", "gpio15" };
+static const char * const wsa_swr_clk_groups[] = { "gpio10" };
+static const char * const wsa_swr_data_groups[] = { "gpio11" };
+static const char * const wsa2_swr_clk_groups[] = { "gpio15" };
+static const char * const wsa2_swr_data_groups[] = { "gpio16" };
+static const char * const ext_mclk1_c_groups[] = { "gpio5" };
+static const char * const ext_mclk1_b_groups[] = { "gpio9" };
+static const char * const ext_mclk1_a_groups[] = { "gpio13" };
+static const char * const ext_mclk1_d_groups[] = { "gpio14" };
+static const char * const ext_mclk1_e_groups[] = { "gpio22" };
+
+static const struct lpi_pingroup sm8650_groups[] = {
+	LPI_PINGROUP(0, 11, swr_tx_clk, i2s0_clk, _, _),
+	LPI_PINGROUP(1, 11, swr_tx_data, i2s0_ws, _, _),
+	LPI_PINGROUP(2, 11, swr_tx_data, i2s0_data, _, _),
+	LPI_PINGROUP(3, 11, swr_rx_clk, i2s0_data, _, _),
+	LPI_PINGROUP(4, 11, swr_rx_data, i2s0_data, _, _),
+	LPI_PINGROUP(5, 11, swr_rx_data, ext_mclk1_c, i2s0_data, _),
+	LPI_PINGROUP(6, LPI_NO_SLEW, dmic1_clk, i2s1_clk, _,  _),
+	LPI_PINGROUP(7, LPI_NO_SLEW, dmic1_data, i2s1_ws, _, _),
+	LPI_PINGROUP(8, LPI_NO_SLEW, dmic2_clk, i2s1_data, _, _),
+	LPI_PINGROUP(9, LPI_NO_SLEW, dmic2_data, i2s1_data, ext_mclk1_b, _),
+	LPI_PINGROUP(10, 11, i2s2_clk, wsa_swr_clk, _, _),
+	LPI_PINGROUP(11, 11, i2s2_ws, wsa_swr_data, _, _),
+	LPI_PINGROUP(12, LPI_NO_SLEW, dmic3_clk, i2s3_clk, _, _),
+	LPI_PINGROUP(13, LPI_NO_SLEW, dmic3_data, i2s3_ws, ext_mclk1_a, _),
+	LPI_PINGROUP(14, 11, swr_tx_data, ext_mclk1_d, _, _),
+	LPI_PINGROUP(15, 11, i2s2_data, wsa2_swr_clk, _, _),
+	LPI_PINGROUP(16, 11, i2s2_data, wsa2_swr_data, _, _),
+	LPI_PINGROUP(17, LPI_NO_SLEW, dmic4_clk, i2s3_data, _, _),
+	LPI_PINGROUP(18, LPI_NO_SLEW, dmic4_data, i2s3_data, _, _),
+	LPI_PINGROUP(19, 11, i2s4_clk, slimbus_clk, qca_swr_clk, _),
+	LPI_PINGROUP(20, 11, i2s4_ws, slimbus_data, qca_swr_data, _),
+	LPI_PINGROUP(21, LPI_NO_SLEW, i2s4_data, _, _, _),
+	LPI_PINGROUP(22, LPI_NO_SLEW, i2s4_data, ext_mclk1_e, _, _),
+};
+
+static const struct lpi_function sm8650_functions[] = {
+	LPI_FUNCTION(gpio),
+	LPI_FUNCTION(dmic1_clk),
+	LPI_FUNCTION(dmic1_data),
+	LPI_FUNCTION(dmic2_clk),
+	LPI_FUNCTION(dmic2_data),
+	LPI_FUNCTION(dmic3_clk),
+	LPI_FUNCTION(dmic3_data),
+	LPI_FUNCTION(dmic4_clk),
+	LPI_FUNCTION(dmic4_data),
+	LPI_FUNCTION(i2s0_clk),
+	LPI_FUNCTION(i2s0_data),
+	LPI_FUNCTION(i2s0_ws),
+	LPI_FUNCTION(i2s1_clk),
+	LPI_FUNCTION(i2s1_data),
+	LPI_FUNCTION(i2s1_ws),
+	LPI_FUNCTION(i2s2_clk),
+	LPI_FUNCTION(i2s2_data),
+	LPI_FUNCTION(i2s2_ws),
+	LPI_FUNCTION(i2s3_clk),
+	LPI_FUNCTION(i2s3_data),
+	LPI_FUNCTION(i2s3_ws),
+	LPI_FUNCTION(i2s4_clk),
+	LPI_FUNCTION(i2s4_data),
+	LPI_FUNCTION(i2s4_ws),
+	LPI_FUNCTION(qca_swr_clk),
+	LPI_FUNCTION(qca_swr_data),
+	LPI_FUNCTION(slimbus_clk),
+	LPI_FUNCTION(slimbus_data),
+	LPI_FUNCTION(swr_rx_clk),
+	LPI_FUNCTION(swr_rx_data),
+	LPI_FUNCTION(swr_tx_clk),
+	LPI_FUNCTION(swr_tx_data),
+	LPI_FUNCTION(wsa_swr_clk),
+	LPI_FUNCTION(wsa_swr_data),
+	LPI_FUNCTION(wsa2_swr_clk),
+	LPI_FUNCTION(wsa2_swr_data),
+	LPI_FUNCTION(ext_mclk1_a),
+	LPI_FUNCTION(ext_mclk1_b),
+	LPI_FUNCTION(ext_mclk1_c),
+	LPI_FUNCTION(ext_mclk1_d),
+	LPI_FUNCTION(ext_mclk1_e),
+};
+
+static const struct lpi_pinctrl_variant_data sm8650_lpi_data = {
+	.pins = sm8650_lpi_pins,
+	.npins = ARRAY_SIZE(sm8650_lpi_pins),
+	.groups = sm8650_groups,
+	.ngroups = ARRAY_SIZE(sm8650_groups),
+	.functions = sm8650_functions,
+	.nfunctions = ARRAY_SIZE(sm8650_functions),
+	.flags = LPI_FLAG_SLEW_RATE_SAME_REG,
+};
+
+static const struct of_device_id lpi_pinctrl_of_match[] = {
+	{
+	       .compatible = "qcom,sm8650-lpass-lpi-pinctrl",
+	       .data = &sm8650_lpi_data,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lpi_pinctrl_of_match);
+
+static struct platform_driver lpi_pinctrl_driver = {
+	.driver = {
+		   .name = "qcom-sm8650-lpass-lpi-pinctrl",
+		   .of_match_table = lpi_pinctrl_of_match,
+	},
+	.probe = lpi_pinctrl_probe,
+	.remove_new = lpi_pinctrl_remove,
+};
+
+module_platform_driver(lpi_pinctrl_driver);
+MODULE_DESCRIPTION("Qualcomm SM8650 LPI GPIO pin control driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From d92618caf9d05e78e0f9c4c6ff9201691acfe48c Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 6 Nov 2023 09:32:30 +0100
Subject: [PATCH 0071/4076] dt-bindings: pinctrl: document the SM8650 Top Level
 Mode Multiplexer

Document the Top Level Mode Multiplexer on the SM8650 Platform.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231106-topic-sm8650-upstream-tlmm-v3-1-0e179c368933@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,sm8650-tlmm.yaml    | 147 ++++++++++++++++++
 1 file changed, 147 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
new file mode 100644
index 0000000000000..30432be8fb07b
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
@@ -0,0 +1,147 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,sm8650-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. SM8650 TLMM block
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm SM8650 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,sm8650-tlmm
+
+  reg:
+    maxItems: 1
+
+  interrupts: true
+  interrupt-controller: true
+  "#interrupt-cells": true
+  gpio-controller: true
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 105
+
+  gpio-line-names:
+    maxItems: 210
+
+  "#gpio-cells": true
+  gpio-ranges: true
+  wakeup-parent: true
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-sm8650-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-sm8650-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-sm8650-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-9][0-9]|20[0-9])$"
+            - enum: [ ufs_reset, sdc2_clk, sdc2_cmd, sdc2_data ]
+        minItems: 1
+        maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ gpio, aoss_cti, atest_char, atest_usb, audio_ext_mclk0,
+                audio_ext_mclk1, audio_ref_clk, cam_aon_mclk2, cam_aon_mclk4,
+                cam_mclk, cci_async_in, cci_i2c_scl, cci_i2c_sda, cci_timer,
+                cmu_rng, coex_uart1_rx, coex_uart1_tx, coex_uart2_rx,
+                coex_uart2_tx, cri_trng, dbg_out_clk, ddr_bist_complete,
+                ddr_bist_fail, ddr_bist_start, ddr_bist_stop, ddr_pxi0,
+                ddr_pxi1, ddr_pxi2, ddr_pxi3, do_not, dp_hot, gcc_gp1,
+                gcc_gp2, gcc_gp3, gnss_adc0, gnss_adc1, i2chub0_se0,
+                i2chub0_se1, i2chub0_se2, i2chub0_se3, i2chub0_se4,
+                i2chub0_se5, i2chub0_se6, i2chub0_se7, i2chub0_se8,
+                i2chub0_se9, i2s0_data0, i2s0_data1, i2s0_sck, i2s0_ws,
+                i2s1_data0, i2s1_data1, i2s1_sck, i2s1_ws, ibi_i3c,
+                jitter_bist, mdp_vsync, mdp_vsync0_out, mdp_vsync1_out,
+                mdp_vsync2_out, mdp_vsync3_out, mdp_vsync_e, nav_gpio0,
+                nav_gpio1, nav_gpio2, nav_gpio3, pcie0_clk_req_n,
+                pcie1_clk_req_n, phase_flag, pll_bist_sync, pll_clk_aux,
+                prng_rosc0, prng_rosc1, prng_rosc2, prng_rosc3, qdss_cti,
+                qdss_gpio, qlink_big_enable, qlink_big_request,
+                qlink_little_enable, qlink_little_request, qlink_wmss,
+                qspi0, qspi1, qspi2, qspi3, qspi_clk, qspi_cs, qup1_se0,
+                qup1_se1, qup1_se2, qup1_se3, qup1_se4, qup1_se5, qup1_se6,
+                qup1_se7, qup2_se0, qup2_se1, qup2_se2, qup2_se3, qup2_se4,
+                qup2_se5, qup2_se6, qup2_se7, sd_write_protect, sdc40, sdc41,
+                sdc42, sdc43, sdc4_clk, sdc4_cmd, tb_trig_sdc2, tb_trig_sdc4,
+                tgu_ch0_trigout, tgu_ch1_trigout, tgu_ch2_trigout,
+                tgu_ch3_trigout, tmess_prng0, tmess_prng1, tmess_prng2,
+                tmess_prng3, tsense_pwm1, tsense_pwm2, tsense_pwm3, uim0_clk,
+                uim0_data, uim0_present, uim0_reset, uim1_clk, uim1_data,
+                uim1_present, uim1_reset, usb1_hs, usb_phy, vfr_0, vfr_1,
+                vsense_trigger_mirnat ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    tlmm: pinctrl@f100000 {
+        compatible = "qcom,sm8650-tlmm";
+        reg = <0x0f100000 0x300000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 211>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-wo-state {
+            pins = "gpio1";
+            function = "gpio";
+        };
+
+        uart-w-state {
+            rx-pins {
+                pins = "gpio60";
+                function = "qup1_se7";
+                bias-pull-up;
+            };
+
+            tx-pins {
+                pins = "gpio61";
+                function = "qup1_se7";
+                bias-disable;
+            };
+        };
+    };
+...
-- 
GitLab


From 76b446f5b86e93515602c3afef6ff74c7e6562de Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 6 Nov 2023 09:32:31 +0100
Subject: [PATCH 0072/4076] pinctrl: qcom: handle intr_target_reg
 wakeup_present/enable bits

New platforms uses a new set of bits to control the wakeirq
delivery to the PDC block.

The intr_wakeup_present_bit indicates if the GPIO supports
wakeirq and intr_wakeup_enable_bit enables wakeirq delivery
to the PDC block.

While the name seems to imply this only enables wakeup events,
it is required to allow interrupts events to the PDC block.

Enable this bit in the irq resource request/free if:
- gpio is in wakeirq map
- has the intr_wakeup_present_bit
- the intr_wakeup_enable_bit is set

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231106-topic-sm8650-upstream-tlmm-v3-2-0e179c368933@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-msm.c | 42 ++++++++++++++++++++++++++++++
 drivers/pinctrl/qcom/pinctrl-msm.h |  5 ++++
 2 files changed, 47 insertions(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 395040346d0f4..207b410185800 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -1196,6 +1196,8 @@ static int msm_gpio_irq_reqres(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct msm_pingroup *g = &pctrl->soc->groups[d->hwirq];
+	unsigned long flags;
 	int ret;
 
 	if (!try_module_get(gc->owner))
@@ -1221,6 +1223,28 @@ static int msm_gpio_irq_reqres(struct irq_data *d)
 	 */
 	irq_set_status_flags(d->irq, IRQ_DISABLE_UNLAZY);
 
+	/*
+	 * If the wakeup_enable bit is present and marked as available for the
+	 * requested GPIO, it should be enabled when the GPIO is marked as
+	 * wake irq in order to allow the interrupt event to be transfered to
+	 * the PDC HW.
+	 * While the name implies only the wakeup event, it's also required for
+	 * the interrupt event.
+	 */
+	if (test_bit(d->hwirq, pctrl->skip_wake_irqs) && g->intr_wakeup_present_bit) {
+		u32 intr_cfg;
+
+		raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+		intr_cfg = msm_readl_intr_cfg(pctrl, g);
+		if (intr_cfg & BIT(g->intr_wakeup_present_bit)) {
+			intr_cfg |= BIT(g->intr_wakeup_enable_bit);
+			msm_writel_intr_cfg(intr_cfg, pctrl, g);
+		}
+
+		raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	}
+
 	return 0;
 out:
 	module_put(gc->owner);
@@ -1230,6 +1254,24 @@ out:
 static void msm_gpio_irq_relres(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct msm_pingroup *g = &pctrl->soc->groups[d->hwirq];
+	unsigned long flags;
+
+	/* Disable the wakeup_enable bit if it has been set in msm_gpio_irq_reqres() */
+	if (test_bit(d->hwirq, pctrl->skip_wake_irqs) && g->intr_wakeup_present_bit) {
+		u32 intr_cfg;
+
+		raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+		intr_cfg = msm_readl_intr_cfg(pctrl, g);
+		if (intr_cfg & BIT(g->intr_wakeup_present_bit)) {
+			intr_cfg &= ~BIT(g->intr_wakeup_enable_bit);
+			msm_writel_intr_cfg(intr_cfg, pctrl, g);
+		}
+
+		raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	}
 
 	gpiochip_unlock_as_irq(gc, d->hwirq);
 	module_put(gc->owner);
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h
index 4968d08a384da..63852ed702957 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.h
+++ b/drivers/pinctrl/qcom/pinctrl-msm.h
@@ -58,6 +58,9 @@ struct pinctrl_pin_desc;
  * @intr_enable_bit:      Offset in @intr_cfg_reg for enabling the interrupt for this group.
  * @intr_status_bit:      Offset in @intr_status_reg for reading and acking the interrupt
  *                        status.
+ * @intr_wakeup_present_bit: Offset in @intr_target_reg specifying the GPIO can generate
+ *			  wakeup events.
+ * @intr_wakeup_enable_bit: Offset in @intr_target_reg to enable wakeup events for the GPIO.
  * @intr_target_bit:      Offset in @intr_target_reg for configuring the interrupt routing.
  * @intr_target_width:    Number of bits used for specifying interrupt routing target.
  * @intr_target_kpss_val: Value in @intr_target_bit for specifying that the interrupt from
@@ -100,6 +103,8 @@ struct msm_pingroup {
 	unsigned intr_status_bit:5;
 	unsigned intr_ack_high:1;
 
+	unsigned intr_wakeup_present_bit:5;
+	unsigned intr_wakeup_enable_bit:5;
 	unsigned intr_target_bit:5;
 	unsigned intr_target_width:5;
 	unsigned intr_target_kpss_val:5;
-- 
GitLab


From 22a4a9ed37d675c210d530f2de92cc6afbcf1daa Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 6 Nov 2023 09:32:32 +0100
Subject: [PATCH 0073/4076] pinctrl: qcom: Introduce the SM8650 Top Level Mode
 Multiplexer driver

Add Top Level Mode Multiplexer (pinctrl) support for the SM8650 platform.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231106-topic-sm8650-upstream-tlmm-v3-3-0e179c368933@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig.msm      |    8 +
 drivers/pinctrl/qcom/Makefile         |    1 +
 drivers/pinctrl/qcom/pinctrl-sm8650.c | 1762 +++++++++++++++++++++++++
 3 files changed, 1771 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-sm8650.c

diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index 01dd7b1343541..341491de406b4 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -366,4 +366,12 @@ config PINCTRL_SM8550
 	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
 	  Technologies Inc SM8550 platform.
 
+config PINCTRL_SM8650
+	tristate "Qualcomm Technologies Inc SM8650 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
+	  Technologies Inc SM8650 platform.
+
 endif
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index f7b410e59bf1d..9bcc1b63e8572 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -58,6 +58,7 @@ obj-$(CONFIG_PINCTRL_SM8450) += pinctrl-sm8450.o
 obj-$(CONFIG_PINCTRL_SM8450_LPASS_LPI) += pinctrl-sm8450-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SM8550) += pinctrl-sm8550.o
 obj-$(CONFIG_PINCTRL_SM8550_LPASS_LPI) += pinctrl-sm8550-lpass-lpi.o
+obj-$(CONFIG_PINCTRL_SM8650) += pinctrl-sm8650.o
 obj-$(CONFIG_PINCTRL_SM8650_LPASS_LPI) += pinctrl-sm8650-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SC8280XP_LPASS_LPI) += pinctrl-sc8280xp-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_LPASS_LPI) += pinctrl-lpass-lpi.o
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650.c b/drivers/pinctrl/qcom/pinctrl-sm8650.c
new file mode 100644
index 0000000000000..adaddd728662f
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650.c
@@ -0,0 +1,1762 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9, f10)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP("gpio" #id,	\
+			gpio##id##_pins,		\
+			ARRAY_SIZE(gpio##id##_pins)),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9,			\
+			msm_mux_##f10			\
+		},				        \
+		.nfuncs = 11,				\
+		.ctl_reg = REG_SIZE * id,			\
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,		\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.i2c_pull_bit = 13,		\
+		.egpio_enable = 12,		\
+		.egpio_present = 11,		\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_wakeup_present_bit = 6,   \
+		.intr_wakeup_enable_bit = 7,    \
+		.intr_target_bit = 8,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define UFS_RESET(pg_name, ctl, io)			\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = io,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+static const struct pinctrl_pin_desc sm8650_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "GPIO_136"),
+	PINCTRL_PIN(137, "GPIO_137"),
+	PINCTRL_PIN(138, "GPIO_138"),
+	PINCTRL_PIN(139, "GPIO_139"),
+	PINCTRL_PIN(140, "GPIO_140"),
+	PINCTRL_PIN(141, "GPIO_141"),
+	PINCTRL_PIN(142, "GPIO_142"),
+	PINCTRL_PIN(143, "GPIO_143"),
+	PINCTRL_PIN(144, "GPIO_144"),
+	PINCTRL_PIN(145, "GPIO_145"),
+	PINCTRL_PIN(146, "GPIO_146"),
+	PINCTRL_PIN(147, "GPIO_147"),
+	PINCTRL_PIN(148, "GPIO_148"),
+	PINCTRL_PIN(149, "GPIO_149"),
+	PINCTRL_PIN(150, "GPIO_150"),
+	PINCTRL_PIN(151, "GPIO_151"),
+	PINCTRL_PIN(152, "GPIO_152"),
+	PINCTRL_PIN(153, "GPIO_153"),
+	PINCTRL_PIN(154, "GPIO_154"),
+	PINCTRL_PIN(155, "GPIO_155"),
+	PINCTRL_PIN(156, "GPIO_156"),
+	PINCTRL_PIN(157, "GPIO_157"),
+	PINCTRL_PIN(158, "GPIO_158"),
+	PINCTRL_PIN(159, "GPIO_159"),
+	PINCTRL_PIN(160, "GPIO_160"),
+	PINCTRL_PIN(161, "GPIO_161"),
+	PINCTRL_PIN(162, "GPIO_162"),
+	PINCTRL_PIN(163, "GPIO_163"),
+	PINCTRL_PIN(164, "GPIO_164"),
+	PINCTRL_PIN(165, "GPIO_165"),
+	PINCTRL_PIN(166, "GPIO_166"),
+	PINCTRL_PIN(167, "GPIO_167"),
+	PINCTRL_PIN(168, "GPIO_168"),
+	PINCTRL_PIN(169, "GPIO_169"),
+	PINCTRL_PIN(170, "GPIO_170"),
+	PINCTRL_PIN(171, "GPIO_171"),
+	PINCTRL_PIN(172, "GPIO_172"),
+	PINCTRL_PIN(173, "GPIO_173"),
+	PINCTRL_PIN(174, "GPIO_174"),
+	PINCTRL_PIN(175, "GPIO_175"),
+	PINCTRL_PIN(176, "GPIO_176"),
+	PINCTRL_PIN(177, "GPIO_177"),
+	PINCTRL_PIN(178, "GPIO_178"),
+	PINCTRL_PIN(179, "GPIO_179"),
+	PINCTRL_PIN(180, "GPIO_180"),
+	PINCTRL_PIN(181, "GPIO_181"),
+	PINCTRL_PIN(182, "GPIO_182"),
+	PINCTRL_PIN(183, "GPIO_183"),
+	PINCTRL_PIN(184, "GPIO_184"),
+	PINCTRL_PIN(185, "GPIO_185"),
+	PINCTRL_PIN(186, "GPIO_186"),
+	PINCTRL_PIN(187, "GPIO_187"),
+	PINCTRL_PIN(188, "GPIO_188"),
+	PINCTRL_PIN(189, "GPIO_189"),
+	PINCTRL_PIN(190, "GPIO_190"),
+	PINCTRL_PIN(191, "GPIO_191"),
+	PINCTRL_PIN(192, "GPIO_192"),
+	PINCTRL_PIN(193, "GPIO_193"),
+	PINCTRL_PIN(194, "GPIO_194"),
+	PINCTRL_PIN(195, "GPIO_195"),
+	PINCTRL_PIN(196, "GPIO_196"),
+	PINCTRL_PIN(197, "GPIO_197"),
+	PINCTRL_PIN(198, "GPIO_198"),
+	PINCTRL_PIN(199, "GPIO_199"),
+	PINCTRL_PIN(200, "GPIO_200"),
+	PINCTRL_PIN(201, "GPIO_201"),
+	PINCTRL_PIN(202, "GPIO_202"),
+	PINCTRL_PIN(203, "GPIO_203"),
+	PINCTRL_PIN(204, "GPIO_204"),
+	PINCTRL_PIN(205, "GPIO_205"),
+	PINCTRL_PIN(206, "GPIO_206"),
+	PINCTRL_PIN(207, "GPIO_207"),
+	PINCTRL_PIN(208, "GPIO_208"),
+	PINCTRL_PIN(209, "GPIO_209"),
+	PINCTRL_PIN(210, "UFS_RESET"),
+	PINCTRL_PIN(211, "SDC2_CLK"),
+	PINCTRL_PIN(212, "SDC2_CMD"),
+	PINCTRL_PIN(213, "SDC2_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+DECLARE_MSM_GPIO_PINS(136);
+DECLARE_MSM_GPIO_PINS(137);
+DECLARE_MSM_GPIO_PINS(138);
+DECLARE_MSM_GPIO_PINS(139);
+DECLARE_MSM_GPIO_PINS(140);
+DECLARE_MSM_GPIO_PINS(141);
+DECLARE_MSM_GPIO_PINS(142);
+DECLARE_MSM_GPIO_PINS(143);
+DECLARE_MSM_GPIO_PINS(144);
+DECLARE_MSM_GPIO_PINS(145);
+DECLARE_MSM_GPIO_PINS(146);
+DECLARE_MSM_GPIO_PINS(147);
+DECLARE_MSM_GPIO_PINS(148);
+DECLARE_MSM_GPIO_PINS(149);
+DECLARE_MSM_GPIO_PINS(150);
+DECLARE_MSM_GPIO_PINS(151);
+DECLARE_MSM_GPIO_PINS(152);
+DECLARE_MSM_GPIO_PINS(153);
+DECLARE_MSM_GPIO_PINS(154);
+DECLARE_MSM_GPIO_PINS(155);
+DECLARE_MSM_GPIO_PINS(156);
+DECLARE_MSM_GPIO_PINS(157);
+DECLARE_MSM_GPIO_PINS(158);
+DECLARE_MSM_GPIO_PINS(159);
+DECLARE_MSM_GPIO_PINS(160);
+DECLARE_MSM_GPIO_PINS(161);
+DECLARE_MSM_GPIO_PINS(162);
+DECLARE_MSM_GPIO_PINS(163);
+DECLARE_MSM_GPIO_PINS(164);
+DECLARE_MSM_GPIO_PINS(165);
+DECLARE_MSM_GPIO_PINS(166);
+DECLARE_MSM_GPIO_PINS(167);
+DECLARE_MSM_GPIO_PINS(168);
+DECLARE_MSM_GPIO_PINS(169);
+DECLARE_MSM_GPIO_PINS(170);
+DECLARE_MSM_GPIO_PINS(171);
+DECLARE_MSM_GPIO_PINS(172);
+DECLARE_MSM_GPIO_PINS(173);
+DECLARE_MSM_GPIO_PINS(174);
+DECLARE_MSM_GPIO_PINS(175);
+DECLARE_MSM_GPIO_PINS(176);
+DECLARE_MSM_GPIO_PINS(177);
+DECLARE_MSM_GPIO_PINS(178);
+DECLARE_MSM_GPIO_PINS(179);
+DECLARE_MSM_GPIO_PINS(180);
+DECLARE_MSM_GPIO_PINS(181);
+DECLARE_MSM_GPIO_PINS(182);
+DECLARE_MSM_GPIO_PINS(183);
+DECLARE_MSM_GPIO_PINS(184);
+DECLARE_MSM_GPIO_PINS(185);
+DECLARE_MSM_GPIO_PINS(186);
+DECLARE_MSM_GPIO_PINS(187);
+DECLARE_MSM_GPIO_PINS(188);
+DECLARE_MSM_GPIO_PINS(189);
+DECLARE_MSM_GPIO_PINS(190);
+DECLARE_MSM_GPIO_PINS(191);
+DECLARE_MSM_GPIO_PINS(192);
+DECLARE_MSM_GPIO_PINS(193);
+DECLARE_MSM_GPIO_PINS(194);
+DECLARE_MSM_GPIO_PINS(195);
+DECLARE_MSM_GPIO_PINS(196);
+DECLARE_MSM_GPIO_PINS(197);
+DECLARE_MSM_GPIO_PINS(198);
+DECLARE_MSM_GPIO_PINS(199);
+DECLARE_MSM_GPIO_PINS(200);
+DECLARE_MSM_GPIO_PINS(201);
+DECLARE_MSM_GPIO_PINS(202);
+DECLARE_MSM_GPIO_PINS(203);
+DECLARE_MSM_GPIO_PINS(204);
+DECLARE_MSM_GPIO_PINS(205);
+DECLARE_MSM_GPIO_PINS(206);
+DECLARE_MSM_GPIO_PINS(207);
+DECLARE_MSM_GPIO_PINS(208);
+DECLARE_MSM_GPIO_PINS(209);
+
+static const unsigned int ufs_reset_pins[] = { 210 };
+static const unsigned int sdc2_clk_pins[] = { 211 };
+static const unsigned int sdc2_cmd_pins[] = { 212 };
+static const unsigned int sdc2_data_pins[] = { 213 };
+
+enum sm8650_functions {
+	msm_mux_gpio,
+	msm_mux_aoss_cti,
+	msm_mux_atest_char,
+	msm_mux_atest_usb,
+	msm_mux_audio_ext_mclk0,
+	msm_mux_audio_ext_mclk1,
+	msm_mux_audio_ref_clk,
+	msm_mux_cam_aon_mclk2,
+	msm_mux_cam_aon_mclk4,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async_in,
+	msm_mux_cci_i2c_scl,
+	msm_mux_cci_i2c_sda,
+	msm_mux_cci_timer,
+	msm_mux_cmu_rng,
+	msm_mux_coex_uart1_rx,
+	msm_mux_coex_uart1_tx,
+	msm_mux_coex_uart2_rx,
+	msm_mux_coex_uart2_tx,
+	msm_mux_cri_trng,
+	msm_mux_dbg_out_clk,
+	msm_mux_ddr_bist_complete,
+	msm_mux_ddr_bist_fail,
+	msm_mux_ddr_bist_start,
+	msm_mux_ddr_bist_stop,
+	msm_mux_ddr_pxi0,
+	msm_mux_ddr_pxi1,
+	msm_mux_ddr_pxi2,
+	msm_mux_ddr_pxi3,
+	msm_mux_do_not,
+	msm_mux_dp_hot,
+	msm_mux_egpio,
+	msm_mux_gcc_gp1,
+	msm_mux_gcc_gp2,
+	msm_mux_gcc_gp3,
+	msm_mux_gnss_adc0,
+	msm_mux_gnss_adc1,
+	msm_mux_i2chub0_se0,
+	msm_mux_i2chub0_se1,
+	msm_mux_i2chub0_se2,
+	msm_mux_i2chub0_se3,
+	msm_mux_i2chub0_se4,
+	msm_mux_i2chub0_se5,
+	msm_mux_i2chub0_se6,
+	msm_mux_i2chub0_se7,
+	msm_mux_i2chub0_se8,
+	msm_mux_i2chub0_se9,
+	msm_mux_i2s0_data0,
+	msm_mux_i2s0_data1,
+	msm_mux_i2s0_sck,
+	msm_mux_i2s0_ws,
+	msm_mux_i2s1_data0,
+	msm_mux_i2s1_data1,
+	msm_mux_i2s1_sck,
+	msm_mux_i2s1_ws,
+	msm_mux_ibi_i3c,
+	msm_mux_jitter_bist,
+	msm_mux_mdp_vsync,
+	msm_mux_mdp_vsync0_out,
+	msm_mux_mdp_vsync1_out,
+	msm_mux_mdp_vsync2_out,
+	msm_mux_mdp_vsync3_out,
+	msm_mux_mdp_vsync_e,
+	msm_mux_nav_gpio0,
+	msm_mux_nav_gpio1,
+	msm_mux_nav_gpio2,
+	msm_mux_nav_gpio3,
+	msm_mux_pcie0_clk_req_n,
+	msm_mux_pcie1_clk_req_n,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist_sync,
+	msm_mux_pll_clk_aux,
+	msm_mux_prng_rosc0,
+	msm_mux_prng_rosc1,
+	msm_mux_prng_rosc2,
+	msm_mux_prng_rosc3,
+	msm_mux_qdss_cti,
+	msm_mux_qdss_gpio,
+	msm_mux_qlink_big_enable,
+	msm_mux_qlink_big_request,
+	msm_mux_qlink_little_enable,
+	msm_mux_qlink_little_request,
+	msm_mux_qlink_wmss,
+	msm_mux_qspi0,
+	msm_mux_qspi1,
+	msm_mux_qspi2,
+	msm_mux_qspi3,
+	msm_mux_qspi_clk,
+	msm_mux_qspi_cs,
+	msm_mux_qup1_se0,
+	msm_mux_qup1_se1,
+	msm_mux_qup1_se2,
+	msm_mux_qup1_se3,
+	msm_mux_qup1_se4,
+	msm_mux_qup1_se5,
+	msm_mux_qup1_se6,
+	msm_mux_qup1_se7,
+	msm_mux_qup2_se0,
+	msm_mux_qup2_se1,
+	msm_mux_qup2_se2,
+	msm_mux_qup2_se3,
+	msm_mux_qup2_se4,
+	msm_mux_qup2_se5,
+	msm_mux_qup2_se6,
+	msm_mux_qup2_se7,
+	msm_mux_sd_write_protect,
+	msm_mux_sdc40,
+	msm_mux_sdc41,
+	msm_mux_sdc42,
+	msm_mux_sdc43,
+	msm_mux_sdc4_clk,
+	msm_mux_sdc4_cmd,
+	msm_mux_tb_trig_sdc2,
+	msm_mux_tb_trig_sdc4,
+	msm_mux_tgu_ch0_trigout,
+	msm_mux_tgu_ch1_trigout,
+	msm_mux_tgu_ch2_trigout,
+	msm_mux_tgu_ch3_trigout,
+	msm_mux_tmess_prng0,
+	msm_mux_tmess_prng1,
+	msm_mux_tmess_prng2,
+	msm_mux_tmess_prng3,
+	msm_mux_tsense_pwm1,
+	msm_mux_tsense_pwm2,
+	msm_mux_tsense_pwm3,
+	msm_mux_uim0_clk,
+	msm_mux_uim0_data,
+	msm_mux_uim0_present,
+	msm_mux_uim0_reset,
+	msm_mux_uim1_clk,
+	msm_mux_uim1_data,
+	msm_mux_uim1_present,
+	msm_mux_uim1_reset,
+	msm_mux_usb1_hs,
+	msm_mux_usb_phy,
+	msm_mux_vfr_0,
+	msm_mux_vfr_1,
+	msm_mux_vsense_trigger_mirnat,
+	msm_mux__,
+};
+
+static const char *const gpio_groups[] = {
+	"gpio0",   "gpio1",   "gpio2",   "gpio3",
+	"gpio4",   "gpio5",   "gpio6",   "gpio7",
+	"gpio8",   "gpio9",   "gpio10",  "gpio11",
+	"gpio12",  "gpio13",  "gpio14",  "gpio15",
+	"gpio16",  "gpio17",  "gpio18",  "gpio19",
+	"gpio20",  "gpio21",  "gpio22",  "gpio23",
+	"gpio24",  "gpio25",  "gpio26",  "gpio27",
+	"gpio28",  "gpio29",  "gpio30",  "gpio31",
+	"gpio32",  "gpio33",  "gpio34",  "gpio35",
+	"gpio36",  "gpio37",  "gpio38",  "gpio39",
+	"gpio40",  "gpio41",  "gpio42",  "gpio43",
+	"gpio44",  "gpio45",  "gpio46",  "gpio47",
+	"gpio48",  "gpio49",  "gpio50",  "gpio51",
+	"gpio52",  "gpio53",  "gpio54",  "gpio55",
+	"gpio56",  "gpio57",  "gpio58",  "gpio59",
+	"gpio60",  "gpio61",  "gpio62",  "gpio63",
+	"gpio64",  "gpio65",  "gpio66",  "gpio67",
+	"gpio68",  "gpio69",  "gpio70",  "gpio71",
+	"gpio72",  "gpio73",  "gpio74",  "gpio75",
+	"gpio76",  "gpio77",  "gpio78",  "gpio79",
+	"gpio80",  "gpio81",  "gpio82",  "gpio83",
+	"gpio84",  "gpio85",  "gpio86",  "gpio87",
+	"gpio88",  "gpio89",  "gpio90",  "gpio91",
+	"gpio92",  "gpio93",  "gpio94",  "gpio95",
+	"gpio96",  "gpio97",  "gpio98",  "gpio99",
+	"gpio100", "gpio101", "gpio102", "gpio103",
+	"gpio104", "gpio105", "gpio106", "gpio107",
+	"gpio108", "gpio109", "gpio110", "gpio111",
+	"gpio112", "gpio113", "gpio114", "gpio115",
+	"gpio116", "gpio117", "gpio118", "gpio119",
+	"gpio120", "gpio121", "gpio122", "gpio123",
+	"gpio124", "gpio125", "gpio126", "gpio127",
+	"gpio128", "gpio129", "gpio130", "gpio131",
+	"gpio132", "gpio133", "gpio134", "gpio135",
+	"gpio136", "gpio137", "gpio138", "gpio139",
+	"gpio140", "gpio141", "gpio142", "gpio143",
+	"gpio144", "gpio145", "gpio146", "gpio147",
+	"gpio148", "gpio149", "gpio150", "gpio151",
+	"gpio152", "gpio153", "gpio154", "gpio155",
+	"gpio156", "gpio157", "gpio158", "gpio159",
+	"gpio160", "gpio161", "gpio162", "gpio163",
+	"gpio164", "gpio165", "gpio166", "gpio167",
+	"gpio168", "gpio169", "gpio170", "gpio171",
+	"gpio172", "gpio173", "gpio174", "gpio175",
+	"gpio176", "gpio177", "gpio178", "gpio179",
+	"gpio180", "gpio181", "gpio182", "gpio183",
+	"gpio184", "gpio185", "gpio186", "gpio187",
+	"gpio188", "gpio189", "gpio190", "gpio191",
+	"gpio192", "gpio193", "gpio194", "gpio195",
+	"gpio196", "gpio197", "gpio198", "gpio199",
+	"gpio200", "gpio201", "gpio202", "gpio203",
+	"gpio204", "gpio205", "gpio206", "gpio207",
+	"gpio208", "gpio209",
+};
+
+static const char * const egpio_groups[] = {
+	"gpio0",   "gpio1",   "gpio2",   "gpio3",   "gpio4",   "gpio5",
+	"gpio6",   "gpio7",   "gpio165", "gpio166", "gpio167", "gpio168",
+	"gpio169", "gpio170", "gpio171", "gpio172", "gpio173", "gpio174",
+	"gpio175", "gpio176", "gpio177", "gpio178", "gpio179", "gpio180",
+	"gpio181", "gpio182", "gpio183", "gpio184", "gpio185", "gpio186",
+	"gpio187", "gpio188", "gpio189", "gpio190", "gpio191", "gpio192",
+	"gpio193", "gpio194", "gpio195", "gpio196", "gpio197", "gpio198",
+	"gpio199", "gpio200", "gpio201", "gpio202", "gpio203", "gpio204",
+	"gpio205", "gpio206", "gpio207", "gpio208", "gpio209",
+};
+
+static const char * const aoss_cti_groups[] = {
+	"gpio50", "gpio51", "gpio60", "gpio61",
+};
+
+static const char *const atest_char_groups[] = {
+	"gpio130", "gpio131", "gpio132", "gpio133",
+	"gpio137",
+};
+
+static const char *const atest_usb_groups[] = {
+	"gpio71", "gpio72", "gpio74", "gpio130",
+	"gpio131",
+};
+
+static const char *const audio_ext_mclk0_groups[] = {
+	"gpio125",
+};
+
+static const char *const audio_ext_mclk1_groups[] = {
+	"gpio124",
+};
+
+static const char *const audio_ref_clk_groups[] = {
+	"gpio124",
+};
+
+static const char *const cam_aon_mclk2_groups[] = {
+	"gpio102",
+};
+
+static const char *const cam_aon_mclk4_groups[] = {
+	"gpio104",
+};
+
+static const char *const cam_mclk_groups[] = {
+	"gpio100", "gpio101", "gpio103", "gpio105",
+	"gpio106", "gpio108",
+};
+
+static const char *const cci_async_in_groups[] = {
+	"gpio15", "gpio163", "gpio164",
+};
+
+static const char *const cci_i2c_scl_groups[] = {
+	"gpio13",  "gpio114", "gpio116", "gpio118",
+	"gpio120", "gpio153",
+};
+
+static const char *const cci_i2c_sda_groups[] = {
+	"gpio12",  "gpio112", "gpio113", "gpio115",
+	"gpio117", "gpio119",
+};
+
+static const char *const cci_timer_groups[] = {
+	"gpio10", "gpio11", "gpio109", "gpio110",
+	"gpio111",
+};
+
+static const char *const cmu_rng_groups[] = {
+	"gpio95",  "gpio96", "gpio112", "gpio127",
+	"gpio122", "gpio128",
+};
+
+static const char *const coex_uart1_rx_groups[] = {
+	"gpio148",
+};
+
+static const char *const coex_uart1_tx_groups[] = {
+	"gpio149",
+};
+
+static const char *const coex_uart2_rx_groups[] = {
+	"gpio150",
+};
+
+static const char *const coex_uart2_tx_groups[] = {
+	"gpio151",
+};
+
+static const char *const cri_trng_groups[] = {
+	"gpio187",
+};
+
+static const char *const dbg_out_clk_groups[] = {
+	"gpio92",
+};
+
+static const char *const ddr_bist_complete_groups[] = {
+	"gpio44",
+};
+
+static const char *const ddr_bist_fail_groups[] = {
+	"gpio40",
+};
+
+static const char *const ddr_bist_start_groups[] = {
+	"gpio41",
+};
+
+static const char *const ddr_bist_stop_groups[] = {
+	"gpio45",
+};
+
+static const char *const ddr_pxi0_groups[] = {
+	"gpio75", "gpio76",
+};
+
+static const char *const ddr_pxi1_groups[] = {
+	"gpio44", "gpio45",
+};
+
+static const char *const ddr_pxi2_groups[] = {
+	"gpio51", "gpio62",
+};
+
+static const char *const ddr_pxi3_groups[] = {
+	"gpio46", "gpio47",
+};
+
+static const char *const do_not_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+	"gpio134", "gpio135", "gpio136",
+};
+
+static const char *const dp_hot_groups[] = {
+	"gpio47",
+};
+
+static const char *const gcc_gp1_groups[] = {
+	"gpio86", "gpio134",
+};
+
+static const char *const gcc_gp2_groups[] = {
+	"gpio87", "gpio135",
+};
+
+static const char *const gcc_gp3_groups[] = {
+	"gpio88", "gpio136",
+};
+
+static const char *const gnss_adc0_groups[] = {
+	"gpio89", "gpio91",
+};
+
+static const char *const gnss_adc1_groups[] = {
+	"gpio90", "gpio92",
+};
+
+static const char *const i2chub0_se0_groups[] = {
+	"gpio64", "gpio65",
+};
+
+static const char *const i2chub0_se1_groups[] = {
+	"gpio66", "gpio67",
+};
+
+static const char *const i2chub0_se2_groups[] = {
+	"gpio68", "gpio69",
+};
+
+static const char *const i2chub0_se3_groups[] = {
+	"gpio70", "gpio71",
+};
+
+static const char *const i2chub0_se4_groups[] = {
+	"gpio72", "gpio73",
+};
+
+static const char *const i2chub0_se5_groups[] = {
+	"gpio74", "gpio75",
+};
+
+static const char *const i2chub0_se6_groups[] = {
+	"gpio76", "gpio77",
+};
+
+static const char *const i2chub0_se7_groups[] = {
+	"gpio78", "gpio79",
+};
+
+static const char *const i2chub0_se8_groups[] = {
+	"gpio206", "gpio207",
+};
+
+static const char *const i2chub0_se9_groups[] = {
+	"gpio80", "gpio81",
+};
+
+static const char *const i2s0_data0_groups[] = {
+	"gpio127",
+};
+
+static const char *const i2s0_data1_groups[] = {
+	"gpio128",
+};
+
+static const char *const i2s0_sck_groups[] = {
+	"gpio126",
+};
+
+static const char *const i2s0_ws_groups[] = {
+	"gpio129",
+};
+
+static const char *const i2s1_data0_groups[] = {
+	"gpio122",
+};
+
+static const char *const i2s1_data1_groups[] = {
+	"gpio124",
+};
+
+static const char *const i2s1_sck_groups[] = {
+	"gpio121",
+};
+
+static const char *const i2s1_ws_groups[] = {
+	"gpio123",
+};
+
+static const char *const ibi_i3c_groups[] = {
+	"gpio0",  "gpio1",  "gpio4",  "gpio5",
+	"gpio8",  "gpio9",  "gpio12", "gpio13",
+	"gpio32", "gpio33", "gpio36", "gpio37",
+	"gpio48", "gpio49", "gpio56", "gpio57",
+};
+
+static const char *const jitter_bist_groups[] = {
+	"gpio73",
+};
+
+static const char *const mdp_vsync_groups[] = {
+	"gpio86", "gpio87", "gpio133", "gpio137",
+};
+
+static const char *const mdp_vsync0_out_groups[] = {
+	"gpio86",
+};
+
+static const char *const mdp_vsync1_out_groups[] = {
+	"gpio86",
+};
+
+static const char *const mdp_vsync2_out_groups[] = {
+	"gpio87",
+};
+
+static const char *const mdp_vsync3_out_groups[] = {
+	"gpio87",
+};
+
+static const char *const mdp_vsync_e_groups[] = {
+	"gpio88",
+};
+
+static const char *const nav_gpio0_groups[] = {
+	"gpio154",
+};
+
+static const char *const nav_gpio1_groups[] = {
+	"gpio155",
+};
+
+static const char *const nav_gpio2_groups[] = {
+	"gpio152",
+};
+
+static const char *const nav_gpio3_groups[] = {
+	"gpio154",
+};
+
+static const char *const pcie0_clk_req_n_groups[] = {
+	"gpio95",
+};
+
+static const char *const pcie1_clk_req_n_groups[] = {
+	"gpio98",
+};
+
+static const char *const phase_flag_groups[] = {
+	"gpio0",   "gpio1",   "gpio3",   "gpio4",
+	"gpio5",   "gpio7",   "gpio8",   "gpio9",
+	"gpio11",  "gpio12",  "gpio13",  "gpio15",
+	"gpio16",  "gpio17",  "gpio19",  "gpio94",
+	"gpio95",  "gpio96",  "gpio109", "gpio111",
+	"gpio112", "gpio113", "gpio114", "gpio115",
+	"gpio116", "gpio117", "gpio118", "gpio119",
+	"gpio120", "gpio153", "gpio163", "gpio164",
+};
+
+static const char *const pll_bist_sync_groups[] = {
+	"gpio68",
+};
+
+static const char *const pll_clk_aux_groups[] = {
+	"gpio106",
+};
+
+static const char *const prng_rosc0_groups[] = {
+	"gpio186",
+};
+
+static const char *const prng_rosc1_groups[] = {
+	"gpio183",
+};
+
+static const char *const prng_rosc2_groups[] = {
+	"gpio182",
+};
+
+static const char *const prng_rosc3_groups[] = {
+	"gpio181",
+};
+
+static const char *const qdss_cti_groups[] = {
+	"gpio27", "gpio31", "gpio78",  "gpio79",
+	"gpio82", "gpio83", "gpio159", "gpio162",
+};
+
+static const char *const qdss_gpio_groups[] = {
+	"gpio3",   "gpio7",   "gpio8",   "gpio13",
+	"gpio15",  "gpio100", "gpio101", "gpio102",
+	"gpio103", "gpio104", "gpio105", "gpio113",
+	"gpio114", "gpio115", "gpio116", "gpio117",
+	"gpio118", "gpio140", "gpio141", "gpio142",
+	"gpio143", "gpio144", "gpio145", "gpio146",
+	"gpio147", "gpio148", "gpio149", "gpio150",
+	"gpio151", "gpio152", "gpio153", "gpio154",
+	"gpio155", "gpio156", "gpio157", "gpio158",
+};
+
+static const char *const qlink_big_enable_groups[] = {
+	"gpio160",
+};
+
+static const char *const qlink_big_request_groups[] = {
+	"gpio159",
+};
+
+static const char *const qlink_little_enable_groups[] = {
+	"gpio157",
+};
+
+static const char *const qlink_little_request_groups[] = {
+	"gpio156",
+};
+
+static const char *const qlink_wmss_groups[] = {
+	"gpio158",
+};
+
+static const char *const qspi0_groups[] = {
+	"gpio134",
+};
+
+static const char *const qspi1_groups[] = {
+	"gpio136",
+};
+
+static const char *const qspi2_groups[] = {
+	"gpio56",
+};
+
+static const char *const qspi3_groups[] = {
+	"gpio57",
+};
+
+static const char *const qspi_clk_groups[] = {
+	"gpio135",
+};
+
+static const char *const qspi_cs_groups[] = {
+	"gpio58", "gpio59",
+};
+
+static const char *const qup1_se0_groups[] = {
+	"gpio32", "gpio33", "gpio34", "gpio35",
+};
+
+static const char *const qup1_se1_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+
+static const char *const qup1_se2_groups[] = {
+	"gpio40", "gpio41", "gpio42", "gpio43",
+	"gpio44", "gpio45", "gpio46",
+};
+
+static const char *const qup1_se3_groups[] = {
+	"gpio44", "gpio45", "gpio46", "gpio47",
+};
+
+static const char *const qup1_se4_groups[] = {
+	"gpio48", "gpio49", "gpio50", "gpio51",
+};
+
+static const char *const qup1_se5_groups[] = {
+	"gpio52", "gpio53", "gpio54", "gpio55",
+};
+
+static const char *const qup1_se6_groups[] = {
+	"gpio56", "gpio57", "gpio58", "gpio59",
+};
+
+static const char *const qup1_se7_groups[] = {
+	"gpio60", "gpio61", "gpio62", "gpio63",
+};
+
+static const char *const qup2_se0_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+
+static const char *const qup2_se1_groups[] = {
+	"gpio4", "gpio5", "gpio6", "gpio7",
+};
+
+static const char *const qup2_se2_groups[] = {
+	"gpio8",  "gpio9",  "gpio10", "gpio11",
+	"gpio13", "gpio15", "gpio12",
+};
+
+static const char *const qup2_se3_groups[] = {
+	"gpio12", "gpio13", "gpio14", "gpio15",
+};
+
+static const char *const qup2_se4_groups[] = {
+	"gpio16", "gpio17", "gpio18", "gpio19",
+};
+
+static const char *const qup2_se5_groups[] = {
+	"gpio20", "gpio21", "gpio22", "gpio23",
+	"gpio23",
+};
+
+static const char *const qup2_se6_groups[] = {
+	"gpio24", "gpio25", "gpio26", "gpio27",
+};
+
+static const char *const qup2_se7_groups[] = {
+	"gpio28", "gpio29", "gpio30", "gpio31",
+};
+
+static const char *const sd_write_protect_groups[] = {
+	"gpio93",
+};
+
+static const char *const sdc40_groups[] = {
+	"gpio134",
+};
+
+static const char *const sdc41_groups[] = {
+	"gpio136",
+};
+
+static const char *const sdc42_groups[] = {
+	"gpio56",
+};
+
+static const char *const sdc43_groups[] = {
+	"gpio57",
+};
+
+static const char *const sdc4_clk_groups[] = {
+	"gpio135",
+};
+
+static const char *const sdc4_cmd_groups[] = {
+	"gpio59",
+};
+
+static const char *const tb_trig_sdc2_groups[] = {
+	"gpio8",
+};
+
+static const char *const tb_trig_sdc4_groups[] = {
+	"gpio58",
+};
+
+static const char *const tgu_ch0_trigout_groups[] = {
+	"gpio8",
+};
+
+static const char *const tgu_ch1_trigout_groups[] = {
+	"gpio9",
+};
+
+static const char *const tgu_ch2_trigout_groups[] = {
+	"gpio10",
+};
+
+static const char *const tgu_ch3_trigout_groups[] = {
+	"gpio11",
+};
+
+static const char *const tmess_prng0_groups[] = {
+	"gpio94",
+};
+
+static const char *const tmess_prng1_groups[] = {
+	"gpio95",
+};
+
+static const char *const tmess_prng2_groups[] = {
+	"gpio96",
+};
+
+static const char *const tmess_prng3_groups[] = {
+	"gpio109",
+};
+
+static const char *const tsense_pwm1_groups[] = {
+	"gpio58",
+};
+
+static const char *const tsense_pwm2_groups[] = {
+	"gpio58",
+};
+
+static const char *const tsense_pwm3_groups[] = {
+	"gpio58",
+};
+
+static const char *const uim0_clk_groups[] = {
+	"gpio131",
+};
+
+static const char *const uim0_data_groups[] = {
+	"gpio130",
+};
+
+static const char *const uim0_present_groups[] = {
+	"gpio47",
+};
+
+static const char *const uim0_reset_groups[] = {
+	"gpio132",
+};
+
+static const char *const uim1_clk_groups[] = {
+	"gpio135",
+};
+
+static const char *const uim1_data_groups[] = {
+	"gpio134",
+};
+
+static const char *const uim1_present_groups[] = {
+	"gpio76",
+};
+
+static const char *const uim1_reset_groups[] = {
+	"gpio136",
+};
+
+static const char *const usb1_hs_groups[] = {
+	"gpio89",
+};
+
+static const char *const usb_phy_groups[] = {
+	"gpio29", "gpio54",
+};
+
+static const char *const vfr_0_groups[] = {
+	"gpio150",
+};
+
+static const char *const vfr_1_groups[] = {
+	"gpio155",
+};
+
+static const char *const vsense_trigger_mirnat_groups[] = {
+	"gpio60",
+};
+
+static const struct pinfunction sm8650_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(aoss_cti),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_usb),
+	MSM_PIN_FUNCTION(audio_ext_mclk0),
+	MSM_PIN_FUNCTION(audio_ext_mclk1),
+	MSM_PIN_FUNCTION(audio_ref_clk),
+	MSM_PIN_FUNCTION(cam_aon_mclk2),
+	MSM_PIN_FUNCTION(cam_aon_mclk4),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async_in),
+	MSM_PIN_FUNCTION(cci_i2c_scl),
+	MSM_PIN_FUNCTION(cci_i2c_sda),
+	MSM_PIN_FUNCTION(cci_timer),
+	MSM_PIN_FUNCTION(cmu_rng),
+	MSM_PIN_FUNCTION(coex_uart1_rx),
+	MSM_PIN_FUNCTION(coex_uart1_tx),
+	MSM_PIN_FUNCTION(coex_uart2_rx),
+	MSM_PIN_FUNCTION(coex_uart2_tx),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(dbg_out_clk),
+	MSM_PIN_FUNCTION(ddr_bist_complete),
+	MSM_PIN_FUNCTION(ddr_bist_fail),
+	MSM_PIN_FUNCTION(ddr_bist_start),
+	MSM_PIN_FUNCTION(ddr_bist_stop),
+	MSM_PIN_FUNCTION(ddr_pxi0),
+	MSM_PIN_FUNCTION(ddr_pxi1),
+	MSM_PIN_FUNCTION(ddr_pxi2),
+	MSM_PIN_FUNCTION(ddr_pxi3),
+	MSM_PIN_FUNCTION(do_not),
+	MSM_PIN_FUNCTION(dp_hot),
+	MSM_PIN_FUNCTION(egpio),
+	MSM_PIN_FUNCTION(gcc_gp1),
+	MSM_PIN_FUNCTION(gcc_gp2),
+	MSM_PIN_FUNCTION(gcc_gp3),
+	MSM_PIN_FUNCTION(gnss_adc0),
+	MSM_PIN_FUNCTION(gnss_adc1),
+	MSM_PIN_FUNCTION(i2chub0_se0),
+	MSM_PIN_FUNCTION(i2chub0_se1),
+	MSM_PIN_FUNCTION(i2chub0_se2),
+	MSM_PIN_FUNCTION(i2chub0_se3),
+	MSM_PIN_FUNCTION(i2chub0_se4),
+	MSM_PIN_FUNCTION(i2chub0_se5),
+	MSM_PIN_FUNCTION(i2chub0_se6),
+	MSM_PIN_FUNCTION(i2chub0_se7),
+	MSM_PIN_FUNCTION(i2chub0_se8),
+	MSM_PIN_FUNCTION(i2chub0_se9),
+	MSM_PIN_FUNCTION(i2s0_data0),
+	MSM_PIN_FUNCTION(i2s0_data1),
+	MSM_PIN_FUNCTION(i2s0_sck),
+	MSM_PIN_FUNCTION(i2s0_ws),
+	MSM_PIN_FUNCTION(i2s1_data0),
+	MSM_PIN_FUNCTION(i2s1_data1),
+	MSM_PIN_FUNCTION(i2s1_sck),
+	MSM_PIN_FUNCTION(i2s1_ws),
+	MSM_PIN_FUNCTION(ibi_i3c),
+	MSM_PIN_FUNCTION(jitter_bist),
+	MSM_PIN_FUNCTION(mdp_vsync),
+	MSM_PIN_FUNCTION(mdp_vsync0_out),
+	MSM_PIN_FUNCTION(mdp_vsync1_out),
+	MSM_PIN_FUNCTION(mdp_vsync2_out),
+	MSM_PIN_FUNCTION(mdp_vsync3_out),
+	MSM_PIN_FUNCTION(mdp_vsync_e),
+	MSM_PIN_FUNCTION(nav_gpio0),
+	MSM_PIN_FUNCTION(nav_gpio1),
+	MSM_PIN_FUNCTION(nav_gpio2),
+	MSM_PIN_FUNCTION(nav_gpio3),
+	MSM_PIN_FUNCTION(pcie0_clk_req_n),
+	MSM_PIN_FUNCTION(pcie1_clk_req_n),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist_sync),
+	MSM_PIN_FUNCTION(pll_clk_aux),
+	MSM_PIN_FUNCTION(prng_rosc0),
+	MSM_PIN_FUNCTION(prng_rosc1),
+	MSM_PIN_FUNCTION(prng_rosc2),
+	MSM_PIN_FUNCTION(prng_rosc3),
+	MSM_PIN_FUNCTION(qdss_cti),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(qlink_big_enable),
+	MSM_PIN_FUNCTION(qlink_big_request),
+	MSM_PIN_FUNCTION(qlink_little_enable),
+	MSM_PIN_FUNCTION(qlink_little_request),
+	MSM_PIN_FUNCTION(qlink_wmss),
+	MSM_PIN_FUNCTION(qspi0),
+	MSM_PIN_FUNCTION(qspi1),
+	MSM_PIN_FUNCTION(qspi2),
+	MSM_PIN_FUNCTION(qspi3),
+	MSM_PIN_FUNCTION(qspi_clk),
+	MSM_PIN_FUNCTION(qspi_cs),
+	MSM_PIN_FUNCTION(qup1_se0),
+	MSM_PIN_FUNCTION(qup1_se1),
+	MSM_PIN_FUNCTION(qup1_se2),
+	MSM_PIN_FUNCTION(qup1_se3),
+	MSM_PIN_FUNCTION(qup1_se4),
+	MSM_PIN_FUNCTION(qup1_se5),
+	MSM_PIN_FUNCTION(qup1_se6),
+	MSM_PIN_FUNCTION(qup1_se7),
+	MSM_PIN_FUNCTION(qup2_se0),
+	MSM_PIN_FUNCTION(qup2_se1),
+	MSM_PIN_FUNCTION(qup2_se2),
+	MSM_PIN_FUNCTION(qup2_se3),
+	MSM_PIN_FUNCTION(qup2_se4),
+	MSM_PIN_FUNCTION(qup2_se5),
+	MSM_PIN_FUNCTION(qup2_se6),
+	MSM_PIN_FUNCTION(qup2_se7),
+	MSM_PIN_FUNCTION(sd_write_protect),
+	MSM_PIN_FUNCTION(sdc40),
+	MSM_PIN_FUNCTION(sdc41),
+	MSM_PIN_FUNCTION(sdc42),
+	MSM_PIN_FUNCTION(sdc43),
+	MSM_PIN_FUNCTION(sdc4_clk),
+	MSM_PIN_FUNCTION(sdc4_cmd),
+	MSM_PIN_FUNCTION(tb_trig_sdc2),
+	MSM_PIN_FUNCTION(tb_trig_sdc4),
+	MSM_PIN_FUNCTION(tgu_ch0_trigout),
+	MSM_PIN_FUNCTION(tgu_ch1_trigout),
+	MSM_PIN_FUNCTION(tgu_ch2_trigout),
+	MSM_PIN_FUNCTION(tgu_ch3_trigout),
+	MSM_PIN_FUNCTION(tmess_prng0),
+	MSM_PIN_FUNCTION(tmess_prng1),
+	MSM_PIN_FUNCTION(tmess_prng2),
+	MSM_PIN_FUNCTION(tmess_prng3),
+	MSM_PIN_FUNCTION(tsense_pwm1),
+	MSM_PIN_FUNCTION(tsense_pwm2),
+	MSM_PIN_FUNCTION(tsense_pwm3),
+	MSM_PIN_FUNCTION(uim0_clk),
+	MSM_PIN_FUNCTION(uim0_data),
+	MSM_PIN_FUNCTION(uim0_present),
+	MSM_PIN_FUNCTION(uim0_reset),
+	MSM_PIN_FUNCTION(uim1_clk),
+	MSM_PIN_FUNCTION(uim1_data),
+	MSM_PIN_FUNCTION(uim1_present),
+	MSM_PIN_FUNCTION(uim1_reset),
+	MSM_PIN_FUNCTION(usb1_hs),
+	MSM_PIN_FUNCTION(usb_phy),
+	MSM_PIN_FUNCTION(vfr_0),
+	MSM_PIN_FUNCTION(vfr_1),
+	MSM_PIN_FUNCTION(vsense_trigger_mirnat),
+};
+
+/*
+ * Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup sm8650_groups[] = {
+	[0] = PINGROUP(0, qup2_se0, ibi_i3c, phase_flag, _, _, _, _, _, _, egpio),
+	[1] = PINGROUP(1, qup2_se0, ibi_i3c, phase_flag, _, _, _, _, _, _, egpio),
+	[2] = PINGROUP(2, qup2_se0, _, _, _, _, _, _, _, _, egpio),
+	[3] = PINGROUP(3, qup2_se0, phase_flag, _, qdss_gpio, _, _, _, _, _, egpio),
+	[4] = PINGROUP(4, qup2_se1, ibi_i3c, phase_flag, _, _, _, _, _, _, egpio),
+	[5] = PINGROUP(5, qup2_se1, ibi_i3c, phase_flag, _, _, _, _, _, _, egpio),
+	[6] = PINGROUP(6, qup2_se1, _, _, _, _, _, _, _, _, egpio),
+	[7] = PINGROUP(7, qup2_se1, phase_flag, _, qdss_gpio, _, _, _, _, _, egpio),
+	[8] = PINGROUP(8, qup2_se2, ibi_i3c, tb_trig_sdc2, phase_flag, tgu_ch0_trigout, _, qdss_gpio, _, _, _),
+	[9] = PINGROUP(9, qup2_se2, ibi_i3c, phase_flag, tgu_ch1_trigout, _, _, _, _, _, _),
+	[10] = PINGROUP(10, qup2_se2, cci_timer, tgu_ch2_trigout, _, _, _, _, _, _, _),
+	[11] = PINGROUP(11, qup2_se2, cci_timer, phase_flag, tgu_ch3_trigout, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup2_se3, cci_i2c_sda, ibi_i3c, qup2_se2, phase_flag, _, _, _, _, _),
+	[13] = PINGROUP(13, qup2_se3, cci_i2c_scl, ibi_i3c, qup2_se2, phase_flag, _, qdss_gpio, _, _, _),
+	[14] = PINGROUP(14, qup2_se3, _, _, _, _, _, _, _, _, _),
+	[15] = PINGROUP(15, qup2_se3, cci_async_in, qup2_se2, phase_flag, _, qdss_gpio, _, _, _, _),
+	[16] = PINGROUP(16, qup2_se4, phase_flag, _, _, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup2_se4, phase_flag, _, _, _, _, _, _, _, _),
+	[18] = PINGROUP(18, qup2_se4, _, _, _, _, _, _, _, _, _),
+	[19] = PINGROUP(19, qup2_se4, phase_flag, _, _, _, _, _, _, _, _),
+	[20] = PINGROUP(20, qup2_se5, _, _, _, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup2_se5, _, _, _, _, _, _, _, _, _),
+	[22] = PINGROUP(22, qup2_se5, _, _, _, _, _, _, _, _, _),
+	[23] = PINGROUP(23, qup2_se5, qup2_se5, _, _, _, _, _, _, _, _),
+	[24] = PINGROUP(24, qup2_se6, _, _, _, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup2_se6, _, _, _, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup2_se6, _, _, _, _, _, _, _, _, _),
+	[27] = PINGROUP(27, qup2_se6, qdss_cti, _, _, _, _, _, _, _, _),
+	[28] = PINGROUP(28, qup2_se7, _, _, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, qup2_se7, usb_phy, _, _, _, _, _, _, _, _),
+	[30] = PINGROUP(30, qup2_se7, _, _, _, _, _, _, _, _, _),
+	[31] = PINGROUP(31, qup2_se7, qdss_cti, _, _, _, _, _, _, _, _),
+	[32] = PINGROUP(32, qup1_se0, ibi_i3c, _, _, _, _, _, _, _, _),
+	[33] = PINGROUP(33, qup1_se0, ibi_i3c, _, _, _, _, _, _, _, _),
+	[34] = PINGROUP(34, qup1_se0, _, _, _, _, _, _, _, _, _),
+	[35] = PINGROUP(35, qup1_se0, _, _, _, _, _, _, _, _, _),
+	[36] = PINGROUP(36, qup1_se1, do_not, ibi_i3c, _, _, _, _, _, _, _),
+	[37] = PINGROUP(37, qup1_se1, do_not, ibi_i3c, _, _, _, _, _, _, _),
+	[38] = PINGROUP(38, qup1_se1, do_not, _, _, _, _, _, _, _, _),
+	[39] = PINGROUP(39, qup1_se1, do_not, _, _, _, _, _, _, _, _),
+	[40] = PINGROUP(40, qup1_se2, ddr_bist_fail, _, _, _, _, _, _, _, _),
+	[41] = PINGROUP(41, qup1_se2, ddr_bist_start, _, _, _, _, _, _, _, _),
+	[42] = PINGROUP(42, qup1_se2, _, _, _, _, _, _, _, _, _),
+	[43] = PINGROUP(43, qup1_se2, _, _, _, _, _, _, _, _, _),
+	[44] = PINGROUP(44, qup1_se3, qup1_se2, ddr_bist_complete, ddr_pxi1, _, _, _, _, _, _),
+	[45] = PINGROUP(45, qup1_se3, qup1_se2, ddr_bist_stop, ddr_pxi1, _, _, _, _, _, _),
+	[46] = PINGROUP(46, qup1_se3, qup1_se2, ddr_pxi3, _, _, _, _, _, _, _),
+	[47] = PINGROUP(47, qup1_se3, uim0_present, dp_hot, ddr_pxi3, _, _, _, _, _, _),
+	[48] = PINGROUP(48, qup1_se4, ibi_i3c, _, _, _, _, _, _, _, _),
+	[49] = PINGROUP(49, qup1_se4, ibi_i3c, _, _, _, _, _, _, _, _),
+	[50] = PINGROUP(50, qup1_se4, aoss_cti, _, _, _, _, _, _, _, _),
+	[51] = PINGROUP(51, qup1_se4, aoss_cti, ddr_pxi2, _, _, _, _, _, _, _),
+	[52] = PINGROUP(52, qup1_se5, _, _, _, _, _, _, _, _, _),
+	[53] = PINGROUP(53, qup1_se5, _, _, _, _, _, _, _, _, _),
+	[54] = PINGROUP(54, qup1_se5, usb_phy, _, _, _, _, _, _, _, _),
+	[55] = PINGROUP(55, qup1_se5, _, _, _, _, _, _, _, _, _),
+	[56] = PINGROUP(56, qup1_se6, ibi_i3c, qspi2, sdc42, _, _, _, _, _, _),
+	[57] = PINGROUP(57, qup1_se6, ibi_i3c, qspi3, sdc43, _, _, _, _, _, _),
+	[58] = PINGROUP(58, qup1_se6, qspi_cs, tb_trig_sdc4, tsense_pwm1, tsense_pwm2, tsense_pwm3, _, _, _, _),
+	[59] = PINGROUP(59, qup1_se6, _, qspi_cs, sdc4_cmd, _, _, _, _, _, _),
+	[60] = PINGROUP(60, qup1_se7, aoss_cti, vsense_trigger_mirnat, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, qup1_se7, aoss_cti, _, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, qup1_se7, ddr_pxi2, _, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, qup1_se7, _, _, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, i2chub0_se0, _, _, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, i2chub0_se0, _, _, _, _, _, _, _, _, _),
+	[66] = PINGROUP(66, i2chub0_se1, _, _, _, _, _, _, _, _, _),
+	[67] = PINGROUP(67, i2chub0_se1, _, _, _, _, _, _, _, _, _),
+	[68] = PINGROUP(68, i2chub0_se2, pll_bist_sync, _, _, _, _, _, _, _, _),
+	[69] = PINGROUP(69, i2chub0_se2, _, _, _, _, _, _, _, _, _),
+	[70] = PINGROUP(70, i2chub0_se3, _, _, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, i2chub0_se3, _, atest_usb, _, _, _, _, _, _, _),
+	[72] = PINGROUP(72, i2chub0_se4, _, atest_usb, _, _, _, _, _, _, _),
+	[73] = PINGROUP(73, i2chub0_se4, jitter_bist, _, _, _, _, _, _, _, _),
+	[74] = PINGROUP(74, i2chub0_se5, atest_usb, _, _, _, _, _, _, _, _),
+	[75] = PINGROUP(75, i2chub0_se5, ddr_pxi0, _, _, _, _, _, _, _, _),
+	[76] = PINGROUP(76, i2chub0_se6, ddr_pxi0, uim1_present, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, i2chub0_se6, _, _, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, i2chub0_se7, qdss_cti, _, _, _, _, _, _, _, _),
+	[79] = PINGROUP(79, i2chub0_se7, qdss_cti, _, _, _, _, _, _, _, _),
+	[80] = PINGROUP(80, i2chub0_se9, _, _, _, _, _, _, _, _, _),
+	[81] = PINGROUP(81, i2chub0_se9, _, _, _, _, _, _, _, _, _),
+	[82] = PINGROUP(82, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[83] = PINGROUP(83, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[84] = PINGROUP(84, _, _, _, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, _, _, _, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, mdp_vsync, mdp_vsync0_out, mdp_vsync1_out, gcc_gp1, _, _, _, _, _, _),
+	[87] = PINGROUP(87, mdp_vsync, mdp_vsync2_out, mdp_vsync3_out, gcc_gp2, _, _, _, _, _, _),
+	[88] = PINGROUP(88, mdp_vsync_e, gcc_gp3, _, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, usb1_hs, gnss_adc0, _, _, _, _, _, _, _, _),
+	[90] = PINGROUP(90, gnss_adc1, _, _, _, _, _, _, _, _, _),
+	[91] = PINGROUP(91, _, gnss_adc0, _, _, _, _, _, _, _, _),
+	[92] = PINGROUP(92, dbg_out_clk, gnss_adc1, _, _, _, _, _, _, _, _),
+	[93] = PINGROUP(93, sd_write_protect, _, _, _, _, _, _, _, _, _),
+	[94] = PINGROUP(94, cmu_rng, phase_flag, tmess_prng0, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, pcie0_clk_req_n, cmu_rng, phase_flag, tmess_prng1, _, _, _, _, _, _),
+	[96] = PINGROUP(96, cmu_rng, phase_flag, tmess_prng2, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, _, _, _, _, _, _, _, _, _, _),
+	[98] = PINGROUP(98, pcie1_clk_req_n, _, _, _, _, _, _, _, _, _),
+	[99] = PINGROUP(99, _, _, _, _, _, _, _, _, _, _),
+	[100] = PINGROUP(100, cam_mclk, qdss_gpio, _, _, _, _, _, _, _, _),
+	[101] = PINGROUP(101, cam_mclk, qdss_gpio, _, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, cam_aon_mclk2, qdss_gpio, _, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, cam_mclk, qdss_gpio, _, _, _, _, _, _, _, _),
+	[104] = PINGROUP(104, cam_aon_mclk4, qdss_gpio, _, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, cam_mclk, qdss_gpio, _, _, _, _, _, _, _, _),
+	[106] = PINGROUP(106, cam_mclk, pll_clk_aux, _, _, _, _, _, _, _, _),
+	[107] = PINGROUP(107, _, _, _, _, _, _, _, _, _, _),
+	[108] = PINGROUP(108, cam_mclk, _, _, _, _, _, _, _, _, _),
+	[109] = PINGROUP(109, cci_timer, phase_flag, tmess_prng3, _, _, _, _, _, _, _),
+	[110] = PINGROUP(110, cci_timer, _, _, _, _, _, _, _, _, _),
+	[111] = PINGROUP(111, cci_timer, phase_flag, _, _, _, _, _, _, _, _),
+	[112] = PINGROUP(112, cci_i2c_sda, cmu_rng, phase_flag, _, _, _, _, _, _, _),
+	[113] = PINGROUP(113, cci_i2c_sda, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[114] = PINGROUP(114, cci_i2c_scl, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[115] = PINGROUP(115, cci_i2c_sda, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[116] = PINGROUP(116, cci_i2c_scl, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[117] = PINGROUP(117, cci_i2c_sda, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[118] = PINGROUP(118, cci_i2c_scl, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[119] = PINGROUP(119, cci_i2c_sda, phase_flag, _, _, _, _, _, _, _, _),
+	[120] = PINGROUP(120, cci_i2c_scl, phase_flag, _, _, _, _, _, _, _, _),
+	[121] = PINGROUP(121, i2s1_sck, _, _, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, i2s1_data0, cmu_rng, _, _, _, _, _, _, _, _),
+	[123] = PINGROUP(123, i2s1_ws, _, _, _, _, _, _, _, _, _),
+	[124] = PINGROUP(124, i2s1_data1, audio_ext_mclk1, audio_ref_clk, _, _, _, _, _, _, _),
+	[125] = PINGROUP(125, audio_ext_mclk0, _, _, _, _, _, _, _, _, _),
+	[126] = PINGROUP(126, i2s0_sck, _, _, _, _, _, _, _, _, _),
+	[127] = PINGROUP(127, i2s0_data0, cmu_rng, _, _, _, _, _, _, _, _),
+	[128] = PINGROUP(128, i2s0_data1, cmu_rng, _, _, _, _, _, _, _, _),
+	[129] = PINGROUP(129, i2s0_ws, cmu_rng, _, _, _, _, _, _, _, _),
+	[130] = PINGROUP(130, uim0_data, atest_usb, atest_char, _, _, _, _, _, _, _),
+	[131] = PINGROUP(131, uim0_clk, atest_usb, atest_char, _, _, _, _, _, _, _),
+	[132] = PINGROUP(132, uim0_reset, atest_char, _, _, _, _, _, _, _, _),
+	[133] = PINGROUP(133, mdp_vsync, atest_char, _, _, _, _, _, _, _, _),
+	[134] = PINGROUP(134, uim1_data, do_not, qspi0, sdc40, gcc_gp1, _, _, _, _, _),
+	[135] = PINGROUP(135, uim1_clk, do_not, qspi_clk, sdc4_clk, gcc_gp2, _, _, _, _, _),
+	[136] = PINGROUP(136, uim1_reset, do_not, qspi1, sdc41, gcc_gp3, _, _, _, _, _),
+	[137] = PINGROUP(137, mdp_vsync, atest_char, _, _, _, _, _, _, _, _),
+	[138] = PINGROUP(138, _, _, _, _, _, _, _, _, _, _),
+	[139] = PINGROUP(139, _, _, _, _, _, _, _, _, _, _),
+	[140] = PINGROUP(140, _, _, qdss_gpio, _, _, _, _, _, _, _),
+	[141] = PINGROUP(141, _, _, qdss_gpio, _, _, _, _, _, _, _),
+	[142] = PINGROUP(142, _, _, qdss_gpio, _, _, _, _, _, _, _),
+	[143] = PINGROUP(143, _, _, qdss_gpio, _, _, _, _, _, _, _),
+	[144] = PINGROUP(144, _, qdss_gpio, _, _, _, _, _, _, _, _),
+	[145] = PINGROUP(145, _, qdss_gpio, _, _, _, _, _, _, _, _),
+	[146] = PINGROUP(146, _, qdss_gpio, _, _, _, _, _, _, _, _),
+	[147] = PINGROUP(147, _, qdss_gpio, _, _, _, _, _, _, _, _),
+	[148] = PINGROUP(148, coex_uart1_rx, qdss_gpio, _, _, _, _, _, _, _, _),
+	[149] = PINGROUP(149, coex_uart1_tx, qdss_gpio, _, _, _, _, _, _, _, _),
+	[150] = PINGROUP(150, _, vfr_0, coex_uart2_rx, qdss_gpio, _, _, _, _, _, _),
+	[151] = PINGROUP(151, _, coex_uart2_tx, qdss_gpio, _, _, _, _, _, _, _),
+	[152] = PINGROUP(152, nav_gpio2, _, qdss_gpio, _, _, _, _, _, _, _),
+	[153] = PINGROUP(153, cci_i2c_scl, phase_flag, _, qdss_gpio, _, _, _, _, _, _),
+	[154] = PINGROUP(154, nav_gpio0, nav_gpio3, qdss_gpio, _, _, _, _, _, _, _),
+	[155] = PINGROUP(155, nav_gpio1, vfr_1, qdss_gpio, _, _, _, _, _, _, _),
+	[156] = PINGROUP(156, qlink_little_request, qdss_gpio, _, _, _, _, _, _, _, _),
+	[157] = PINGROUP(157, qlink_little_enable, qdss_gpio, _, _, _, _, _, _, _, _),
+	[158] = PINGROUP(158, qlink_wmss, qdss_gpio, _, _, _, _, _, _, _, _),
+	[159] = PINGROUP(159, qlink_big_request, qdss_cti, _, _, _, _, _, _, _, _),
+	[160] = PINGROUP(160, qlink_big_enable, _, _, _, _, _, _, _, _, _),
+	[161] = PINGROUP(161, _, _, _, _, _, _, _, _, _, _),
+	[162] = PINGROUP(162, qdss_cti, _, _, _, _, _, _, _, _, _),
+	[163] = PINGROUP(163, cci_async_in, phase_flag, _, _, _, _, _, _, _, _),
+	[164] = PINGROUP(164, cci_async_in, phase_flag, _, _, _, _, _, _, _, _),
+	[165] = PINGROUP(165, _, _, _, _, _, _, _, _, _, egpio),
+	[166] = PINGROUP(166, _, _, _, _, _, _, _, _, _, egpio),
+	[167] = PINGROUP(167, _, _, _, _, _, _, _, _, _, egpio),
+	[168] = PINGROUP(168, _, _, _, _, _, _, _, _, _, egpio),
+	[169] = PINGROUP(169, _, _, _, _, _, _, _, _, _, egpio),
+	[170] = PINGROUP(170, _, _, _, _, _, _, _, _, _, egpio),
+	[171] = PINGROUP(171, _, _, _, _, _, _, _, _, _, egpio),
+	[172] = PINGROUP(172, _, _, _, _, _, _, _, _, _, egpio),
+	[173] = PINGROUP(173, _, _, _, _, _, _, _, _, _, egpio),
+	[174] = PINGROUP(174, _, _, _, _, _, _, _, _, _, egpio),
+	[175] = PINGROUP(175, _, _, _, _, _, _, _, _, _, egpio),
+	[176] = PINGROUP(176, _, _, _, _, _, _, _, _, _, egpio),
+	[177] = PINGROUP(177, _, _, _, _, _, _, _, _, _, egpio),
+	[178] = PINGROUP(178, _, _, _, _, _, _, _, _, _, egpio),
+	[179] = PINGROUP(179, _, _, _, _, _, _, _, _, _, egpio),
+	[180] = PINGROUP(180, _, _, _, _, _, _, _, _, _, egpio),
+	[181] = PINGROUP(181, prng_rosc3, _, _, _, _, _, _, _, _, egpio),
+	[182] = PINGROUP(182, prng_rosc2, _, _, _, _, _, _, _, _, egpio),
+	[183] = PINGROUP(183, prng_rosc1, _, _, _, _, _, _, _, _, egpio),
+	[184] = PINGROUP(184, _, _, _, _, _, _, _, _, _, egpio),
+	[185] = PINGROUP(185, _, _, _, _, _, _, _, _, _, egpio),
+	[186] = PINGROUP(186, prng_rosc0, _, _, _, _, _, _, _, _, egpio),
+	[187] = PINGROUP(187, cri_trng, _, _, _, _, _, _, _, _, egpio),
+	[188] = PINGROUP(188, _, _, _, _, _, _, _, _, _, egpio),
+	[189] = PINGROUP(189, _, _, _, _, _, _, _, _, _, egpio),
+	[190] = PINGROUP(190, _, _, _, _, _, _, _, _, _, egpio),
+	[191] = PINGROUP(191, _, _, _, _, _, _, _, _, _, egpio),
+	[192] = PINGROUP(192, _, _, _, _, _, _, _, _, _, egpio),
+	[193] = PINGROUP(193, _, _, _, _, _, _, _, _, _, egpio),
+	[194] = PINGROUP(194, _, _, _, _, _, _, _, _, _, egpio),
+	[195] = PINGROUP(195, _, _, _, _, _, _, _, _, _, egpio),
+	[196] = PINGROUP(196, _, _, _, _, _, _, _, _, _, egpio),
+	[197] = PINGROUP(197, _, _, _, _, _, _, _, _, _, egpio),
+	[198] = PINGROUP(198, _, _, _, _, _, _, _, _, _, egpio),
+	[199] = PINGROUP(199, _, _, _, _, _, _, _, _, _, egpio),
+	[200] = PINGROUP(200, _, _, _, _, _, _, _, _, _, egpio),
+	[201] = PINGROUP(201, _, _, _, _, _, _, _, _, _, egpio),
+	[202] = PINGROUP(202, _, _, _, _, _, _, _, _, _, egpio),
+	[203] = PINGROUP(203, _, _, _, _, _, _, _, _, _, egpio),
+	[204] = PINGROUP(204, _, _, _, _, _, _, _, _, _, egpio),
+	[205] = PINGROUP(205, _, _, _, _, _, _, _, _, _, egpio),
+	[206] = PINGROUP(206, i2chub0_se8, _, _, _, _, _, _, _, _, egpio),
+	[207] = PINGROUP(207, i2chub0_se8, _, _, _, _, _, _, _, _, egpio),
+	[208] = PINGROUP(208, _, _, _, _, _, _, _, _, _, egpio),
+	[209] = PINGROUP(209, _, _, _, _, _, _, _, _, _, egpio),
+	[210] = UFS_RESET(ufs_reset, 0xde004, 0xdf000),
+	[211] = SDC_QDSD_PINGROUP(sdc2_clk, 0xd6000, 14, 6),
+	[212] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xd6000, 11, 3),
+	[213] = SDC_QDSD_PINGROUP(sdc2_data, 0xd6000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map sm8650_pdc_map[] = {
+	{ 0, 94 },    { 3, 105 },   { 4, 78 },    { 7, 67 },    { 8, 64 },
+	{ 11, 121 },  { 12, 71 },   { 15, 82 },   { 18, 75 },   { 19, 63 },
+	{ 20, 114 },  { 23, 84 },   { 27, 61 },   { 29, 112 },  { 31, 113 },
+	{ 32, 66 },   { 35, 52 },   { 36, 123 },  { 39, 56 },   { 43, 59 },
+	{ 46, 79 },   { 47, 124 },  { 48, 125 },  { 51, 93 },   { 54, 60 },
+	{ 55, 104 },  { 56, 72 },   { 57, 77 },   { 59, 51 },   { 63, 85 },
+	{ 64, 107 },  { 65, 108 },  { 66, 109 },  { 67, 83 },   { 68, 110 },
+	{ 69, 111 },  { 75, 96 },   { 76, 97 },   { 77, 98 },   { 80, 89 },
+	{ 81, 90 },   { 84, 106 },  { 85, 100 },  { 86, 87 },   { 87, 88 },
+	{ 88, 65 },   { 90, 92 },   { 92, 99 },   { 95, 118 },  { 96, 119 },
+	{ 98, 101 },  { 99, 62 },   { 112, 120 }, { 133, 80 },  { 136, 69 },
+	{ 137, 81 },  { 148, 57 },  { 150, 58 },  { 152, 127 }, { 153, 74 },
+	{ 154, 126 }, { 155, 73 },  { 156, 128 }, { 159, 129 }, { 162, 86 },
+	{ 163, 122 }, { 166, 139 }, { 169, 140 }, { 171, 141 }, { 172, 142 },
+	{ 174, 102 }, { 176, 143 }, { 177, 55 },  { 181, 144 }, { 182, 145 },
+	{ 185, 146 }, { 187, 95 },  { 188, 130 }, { 190, 131 }, { 191, 132 },
+	{ 192, 133 }, { 193, 134 }, { 195, 68 },  { 196, 135 }, { 197, 136 },
+	{ 198, 54 },  { 199, 103 }, { 200, 53 },  { 201, 137 }, { 202, 70 },
+	{ 203, 138 }, { 204, 76 },  { 205, 91 },
+};
+
+static const struct msm_pinctrl_soc_data sm8650_tlmm = {
+	.pins = sm8650_pins,
+	.npins = ARRAY_SIZE(sm8650_pins),
+	.functions = sm8650_functions,
+	.nfunctions = ARRAY_SIZE(sm8650_functions),
+	.groups = sm8650_groups,
+	.ngroups = ARRAY_SIZE(sm8650_groups),
+	.ngpios = 211,
+	.wakeirq_map = sm8650_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(sm8650_pdc_map),
+	.egpio_func = 10,
+};
+
+static int sm8650_tlmm_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &sm8650_tlmm);
+}
+
+static const struct of_device_id sm8650_tlmm_of_match[] = {
+	{ .compatible = "qcom,sm8650-tlmm", },
+	{},
+};
+
+static struct platform_driver sm8650_tlmm_driver = {
+	.driver = {
+		.name = "sm8650-tlmm",
+		.of_match_table = sm8650_tlmm_of_match,
+	},
+	.probe = sm8650_tlmm_probe,
+	.remove_new = msm_pinctrl_remove,
+};
+
+static int __init sm8650_tlmm_init(void)
+{
+	return platform_driver_register(&sm8650_tlmm_driver);
+}
+arch_initcall(sm8650_tlmm_init);
+
+static void __exit sm8650_tlmm_exit(void)
+{
+	platform_driver_unregister(&sm8650_tlmm_driver);
+}
+module_exit(sm8650_tlmm_exit);
+
+MODULE_DESCRIPTION("QTI SM8650 TLMM driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, sm8650_tlmm_of_match);
-- 
GitLab


From 22f57707fa0c17072851de60706d01f5836cd36b Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Mon, 13 Nov 2023 18:25:34 +0530
Subject: [PATCH 0074/4076] pinctrl: intel: allow independent COMPILE_TEST

Now that we have completed the transition to standard ACPI helpers for the
entire Intel pinctrl tree, we can detach COMPILE_TEST from ACPI dependency.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/intel/Kconfig b/drivers/pinctrl/intel/Kconfig
index d66f4f6932d8d..44b022d8aee1e 100644
--- a/drivers/pinctrl/intel/Kconfig
+++ b/drivers/pinctrl/intel/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Intel pin control drivers
 menu "Intel pinctrl drivers"
-	depends on ACPI && (X86 || COMPILE_TEST)
+	depends on (ACPI && X86) || COMPILE_TEST
 
 config PINCTRL_BAYTRAIL
 	bool "Intel Baytrail GPIO pin control"
-- 
GitLab


From fa72d143471d04ce3055d8dad9743b08c19e4060 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 1 Nov 2023 10:39:39 +0100
Subject: [PATCH 0075/4076] HSI: omap_ssi: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/d72106fc9de28ef8db2ed653febe366d141362a4.1698831563.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/hsi/controllers/omap_ssi_core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c
index 4c1a00f9929e4..6802efb4d6cdc 100644
--- a/drivers/hsi/controllers/omap_ssi_core.c
+++ b/drivers/hsi/controllers/omap_ssi_core.c
@@ -355,7 +355,7 @@ static int ssi_add_controller(struct hsi_controller *ssi,
 	if (!omap_ssi)
 		return -ENOMEM;
 
-	err = ida_simple_get(&platform_omap_ssi_ida, 0, 0, GFP_KERNEL);
+	err = ida_alloc(&platform_omap_ssi_ida, GFP_KERNEL);
 	if (err < 0)
 		return err;
 	ssi->id = err;
@@ -417,7 +417,7 @@ static int ssi_add_controller(struct hsi_controller *ssi,
 	return 0;
 
 out_err:
-	ida_simple_remove(&platform_omap_ssi_ida, ssi->id);
+	ida_free(&platform_omap_ssi_ida, ssi->id);
 	return err;
 }
 
@@ -451,7 +451,7 @@ static void ssi_remove_controller(struct hsi_controller *ssi)
 	tasklet_kill(&omap_ssi->gdd_tasklet);
 	hsi_unregister_controller(ssi);
 	clk_notifier_unregister(omap_ssi->fck, &omap_ssi->fck_nb);
-	ida_simple_remove(&platform_omap_ssi_ida, id);
+	ida_free(&platform_omap_ssi_ida, id);
 }
 
 static inline int ssi_of_get_available_ports_count(const struct device_node *np)
-- 
GitLab


From 28bb7c555c7ebcc810ef49e3361d60c5acbd7b36 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 13 Oct 2023 16:59:34 +0200
Subject: [PATCH 0076/4076] pinctrl: qcom: lpass-lpi: split slew rate set to
 separate function

Setting slew rate for each pin will grow with upcoming Qualcomm SoCs,
so split the code responsible for this into separate function for easier
readability and maintenance.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231013145935.220945-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-lpass-lpi.c | 53 +++++++++++++++---------
 1 file changed, 33 insertions(+), 20 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
index 9651aed048cf4..4fb808545f7f6 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
@@ -186,6 +186,35 @@ static int lpi_config_get(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
+static int lpi_config_set_slew_rate(struct lpi_pinctrl *pctrl,
+				    const struct lpi_pingroup *g,
+				    unsigned int group, unsigned int slew)
+{
+	unsigned long sval;
+	int slew_offset;
+
+	if (slew > LPI_SLEW_RATE_MAX) {
+		dev_err(pctrl->dev, "invalid slew rate %u for pin: %d\n",
+			slew, group);
+		return -EINVAL;
+	}
+
+	slew_offset = g->slew_offset;
+	if (slew_offset == LPI_NO_SLEW)
+		return 0;
+
+	mutex_lock(&pctrl->lock);
+
+	sval = ioread32(pctrl->slew_base + LPI_SLEW_RATE_CTL_REG);
+	sval &= ~(LPI_SLEW_RATE_MASK << slew_offset);
+	sval |= slew << slew_offset;
+	iowrite32(sval, pctrl->slew_base + LPI_SLEW_RATE_CTL_REG);
+
+	mutex_unlock(&pctrl->lock);
+
+	return 0;
+}
+
 static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group,
 			  unsigned long *configs, unsigned int nconfs)
 {
@@ -193,8 +222,7 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group,
 	unsigned int param, arg, pullup = LPI_GPIO_BIAS_DISABLE, strength = 2;
 	bool value, output_enabled = false;
 	const struct lpi_pingroup *g;
-	unsigned long sval;
-	int i, slew_offset;
+	int i, ret;
 	u32 val;
 
 	g = &pctrl->data->groups[group];
@@ -226,24 +254,9 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group,
 			strength = arg;
 			break;
 		case PIN_CONFIG_SLEW_RATE:
-			if (arg > LPI_SLEW_RATE_MAX) {
-				dev_err(pctldev->dev, "invalid slew rate %u for pin: %d\n",
-					arg, group);
-				return -EINVAL;
-			}
-
-			slew_offset = g->slew_offset;
-			if (slew_offset == LPI_NO_SLEW)
-				break;
-
-			mutex_lock(&pctrl->lock);
-
-			sval = ioread32(pctrl->slew_base + LPI_SLEW_RATE_CTL_REG);
-			sval &= ~(LPI_SLEW_RATE_MASK << slew_offset);
-			sval |= arg << slew_offset;
-			iowrite32(sval, pctrl->slew_base + LPI_SLEW_RATE_CTL_REG);
-
-			mutex_unlock(&pctrl->lock);
+			ret = lpi_config_set_slew_rate(pctrl, g, group, arg);
+			if (ret)
+				return ret;
 			break;
 		default:
 			return -EINVAL;
-- 
GitLab


From 6ea5c72b04cc6f45d57a2610113ad99a6755c8aa Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 13 Oct 2023 16:59:35 +0200
Subject: [PATCH 0077/4076] pinctrl: qcom: lpass-lpi: allow slew rate bit in
 main pin config register

Existing Qualcomm SoCs have the LPASS pin controller slew rate control
in separate register, however this will change with upcoming Qualcomm
SoCs.  The slew rate will be part of the main register for pin
configuration, thus second device IO address space is not needed.

Prepare for supporting new SoCs by adding flag customizing the driver
behavior for slew rate.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231013145935.220945-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-lpass-lpi.c | 20 ++++++++++++++------
 drivers/pinctrl/qcom/pinctrl-lpass-lpi.h |  7 +++++++
 2 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
index 4fb808545f7f6..9e410a281bfa9 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
@@ -191,6 +191,7 @@ static int lpi_config_set_slew_rate(struct lpi_pinctrl *pctrl,
 				    unsigned int group, unsigned int slew)
 {
 	unsigned long sval;
+	void __iomem *reg;
 	int slew_offset;
 
 	if (slew > LPI_SLEW_RATE_MAX) {
@@ -203,12 +204,17 @@ static int lpi_config_set_slew_rate(struct lpi_pinctrl *pctrl,
 	if (slew_offset == LPI_NO_SLEW)
 		return 0;
 
+	if (pctrl->data->flags & LPI_FLAG_SLEW_RATE_SAME_REG)
+		reg = pctrl->tlmm_base + LPI_TLMM_REG_OFFSET * group + LPI_GPIO_CFG_REG;
+	else
+		reg = pctrl->slew_base + LPI_SLEW_RATE_CTL_REG;
+
 	mutex_lock(&pctrl->lock);
 
-	sval = ioread32(pctrl->slew_base + LPI_SLEW_RATE_CTL_REG);
+	sval = ioread32(reg);
 	sval &= ~(LPI_SLEW_RATE_MASK << slew_offset);
 	sval |= slew << slew_offset;
-	iowrite32(sval, pctrl->slew_base + LPI_SLEW_RATE_CTL_REG);
+	iowrite32(sval, reg);
 
 	mutex_unlock(&pctrl->lock);
 
@@ -452,10 +458,12 @@ int lpi_pinctrl_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(pctrl->tlmm_base),
 				     "TLMM resource not provided\n");
 
-	pctrl->slew_base = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(pctrl->slew_base))
-		return dev_err_probe(dev, PTR_ERR(pctrl->slew_base),
-				     "Slew resource not provided\n");
+	if (!(data->flags & LPI_FLAG_SLEW_RATE_SAME_REG)) {
+		pctrl->slew_base = devm_platform_ioremap_resource(pdev, 1);
+		if (IS_ERR(pctrl->slew_base))
+			return dev_err_probe(dev, PTR_ERR(pctrl->slew_base),
+					     "Slew resource not provided\n");
+	}
 
 	ret = devm_clk_bulk_get_optional(dev, MAX_LPI_NUM_CLKS, pctrl->clks);
 	if (ret)
diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
index 387d83ee95b5d..206b2c0ca828c 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
@@ -60,6 +60,12 @@ struct pinctrl_pin_desc;
 		.nfuncs = 5,				\
 	}
 
+/*
+ * Slew rate control is done in the same register as rest of the
+ * pin configuration.
+ */
+#define LPI_FLAG_SLEW_RATE_SAME_REG			BIT(0)
+
 struct lpi_pingroup {
 	struct group_desc group;
 	unsigned int pin;
@@ -82,6 +88,7 @@ struct lpi_pinctrl_variant_data {
 	int ngroups;
 	const struct lpi_function *functions;
 	int nfunctions;
+	unsigned int flags;
 };
 
 int lpi_pinctrl_probe(struct platform_device *pdev);
-- 
GitLab


From 4c51ea957f08ea724e66f7b03c9091d3a5d99467 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 13 Nov 2023 14:28:47 +0200
Subject: [PATCH 0078/4076] pinctrl: intel: Revert "Unexport
 intel_pinctrl_probe()"

In order to prepare for a new coming driver export the original
intel_pinctrl_probe() again.

This reverts commit 0dd519e3784b13befa1cdfeff847a0885b06650f.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 5 +++--
 drivers/pinctrl/intel/pinctrl-intel.h | 3 +++
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 62daf189d3f49..2367c2747a83f 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1504,8 +1504,8 @@ static int intel_pinctrl_probe_pwm(struct intel_pinctrl *pctrl,
 	return PTR_ERR_OR_ZERO(pwm);
 }
 
-static int intel_pinctrl_probe(struct platform_device *pdev,
-			       const struct intel_pinctrl_soc_data *soc_data)
+int intel_pinctrl_probe(struct platform_device *pdev,
+			const struct intel_pinctrl_soc_data *soc_data)
 {
 	struct device *dev = &pdev->dev;
 	struct intel_pinctrl *pctrl;
@@ -1623,6 +1623,7 @@ static int intel_pinctrl_probe(struct platform_device *pdev,
 
 	return 0;
 }
+EXPORT_SYMBOL_NS_GPL(intel_pinctrl_probe, PINCTRL_INTEL);
 
 int intel_pinctrl_probe_by_hid(struct platform_device *pdev)
 {
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index e7d911a655842..fde65e18cd145 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -252,6 +252,9 @@ struct intel_pinctrl {
 	int irq;
 };
 
+int intel_pinctrl_probe(struct platform_device *pdev,
+			const struct intel_pinctrl_soc_data *soc_data);
+
 int intel_pinctrl_probe_by_hid(struct platform_device *pdev);
 int intel_pinctrl_probe_by_uid(struct platform_device *pdev);
 
-- 
GitLab


From c5860e4a2737a8b29dc426c800d01c5be6aad811 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 13 Nov 2023 14:28:48 +0200
Subject: [PATCH 0079/4076] pinctrl: intel: Add a generic Intel pin control
 platform driver

New generations of Intel platforms will provide better description
of the pin control devices in the ACPI tables. Hence, we may provide
a generic pin control platform driver to cover all of them. Currently
the following Intel SoCs / platforms require this to be functional:
- Lunar Lake

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/Kconfig                 |  10 +
 drivers/pinctrl/intel/Makefile                |   1 +
 .../pinctrl/intel/pinctrl-intel-platform.c    | 225 ++++++++++++++++++
 3 files changed, 236 insertions(+)
 create mode 100644 drivers/pinctrl/intel/pinctrl-intel-platform.c

diff --git a/drivers/pinctrl/intel/Kconfig b/drivers/pinctrl/intel/Kconfig
index 44b022d8aee1e..d9bdd0e0e8a2b 100644
--- a/drivers/pinctrl/intel/Kconfig
+++ b/drivers/pinctrl/intel/Kconfig
@@ -37,6 +37,16 @@ config PINCTRL_INTEL
 	select GPIOLIB
 	select GPIOLIB_IRQCHIP
 
+config PINCTRL_INTEL_PLATFORM
+	tristate "Intel pinctrl and GPIO platform driver"
+	depends on ACPI
+	select PINCTRL_INTEL
+	help
+	  This pinctrl driver provides an interface that allows configuring
+	  of Intel PCH pins and using them as GPIOs. Currently the following
+	  Intel SoCs / platforms require this to be functional:
+	  - Lunar Lake
+
 config PINCTRL_ALDERLAKE
 	tristate "Intel Alder Lake pinctrl and GPIO driver"
 	select PINCTRL_INTEL
diff --git a/drivers/pinctrl/intel/Makefile b/drivers/pinctrl/intel/Makefile
index f6d30f2d973a0..96c93ed4bd580 100644
--- a/drivers/pinctrl/intel/Makefile
+++ b/drivers/pinctrl/intel/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_PINCTRL_TANGIER)		+= pinctrl-tangier.o
 obj-$(CONFIG_PINCTRL_MERRIFIELD)	+= pinctrl-merrifield.o
 obj-$(CONFIG_PINCTRL_MOOREFIELD)	+= pinctrl-moorefield.o
 obj-$(CONFIG_PINCTRL_INTEL)		+= pinctrl-intel.o
+obj-$(CONFIG_PINCTRL_INTEL_PLATFORM)	+= pinctrl-intel-platform.o
 obj-$(CONFIG_PINCTRL_ALDERLAKE)		+= pinctrl-alderlake.o
 obj-$(CONFIG_PINCTRL_BROXTON)		+= pinctrl-broxton.o
 obj-$(CONFIG_PINCTRL_CANNONLAKE)	+= pinctrl-cannonlake.o
diff --git a/drivers/pinctrl/intel/pinctrl-intel-platform.c b/drivers/pinctrl/intel/pinctrl-intel-platform.c
new file mode 100644
index 0000000000000..4a19ab3b4ba74
--- /dev/null
+++ b/drivers/pinctrl/intel/pinctrl-intel-platform.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel PCH pinctrl/GPIO driver
+ *
+ * Copyright (C) 2021-2023, Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/property.h>
+#include <linux/string_helpers.h>
+
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-intel.h"
+
+struct intel_platform_pins {
+	struct pinctrl_pin_desc *pins;
+	size_t npins;
+};
+
+static int intel_platform_pinctrl_prepare_pins(struct device *dev, size_t base,
+					       const char *name, u32 size,
+					       struct intel_platform_pins *pins)
+{
+	struct pinctrl_pin_desc *descs;
+	char **pin_names;
+	unsigned int i;
+
+	pin_names = devm_kasprintf_strarray(dev, name, size);
+	if (IS_ERR(pin_names))
+		return PTR_ERR(pin_names);
+
+	descs = devm_krealloc_array(dev, pins->pins, base + size, sizeof(*descs), GFP_KERNEL);
+	if (!descs)
+		return -ENOMEM;
+
+	for (i = 0; i < size; i++) {
+		unsigned int pin_number = base + i;
+		char *pin_name = pin_names[i];
+		struct pinctrl_pin_desc *desc;
+
+		/* Unify delimiter for pin name */
+		strreplace(pin_name, '-', '_');
+
+		desc = &descs[pin_number];
+		desc->number = pin_number;
+		desc->name = pin_name;
+	}
+
+	pins->pins = descs;
+	pins->npins = base + size;
+
+	return 0;
+}
+
+static int intel_platform_pinctrl_prepare_group(struct device *dev,
+						struct fwnode_handle *child,
+						struct intel_padgroup *gpp,
+						struct intel_platform_pins *pins)
+{
+	size_t base = pins->npins;
+	const char *name;
+	u32 size;
+	int ret;
+
+	ret = fwnode_property_read_string(child, "intc-gpio-group-name", &name);
+	if (ret)
+		return ret;
+
+	ret = fwnode_property_read_u32(child, "intc-gpio-pad-count", &size);
+	if (ret)
+		return ret;
+
+	ret = intel_platform_pinctrl_prepare_pins(dev, base, name, size, pins);
+	if (ret)
+		return ret;
+
+	gpp->base = base;
+	gpp->size = size;
+	gpp->gpio_base = INTEL_GPIO_BASE_MATCH;
+
+	return 0;
+}
+
+static int intel_platform_pinctrl_prepare_community(struct device *dev,
+						    struct intel_community *community,
+						    struct intel_platform_pins *pins)
+{
+	struct fwnode_handle *child;
+	struct intel_padgroup *gpps;
+	unsigned int group;
+	size_t ngpps;
+	u32 offset;
+	int ret;
+
+	ret = device_property_read_u32(dev, "intc-gpio-pad-ownership-offset", &offset);
+	if (ret)
+		return ret;
+	community->padown_offset = offset;
+
+	ret = device_property_read_u32(dev, "intc-gpio-pad-configuration-lock-offset", &offset);
+	if (ret)
+		return ret;
+	community->padcfglock_offset = offset;
+
+	ret = device_property_read_u32(dev, "intc-gpio-host-software-pad-ownership-offset", &offset);
+	if (ret)
+		return ret;
+	community->hostown_offset = offset;
+
+	ret = device_property_read_u32(dev, "intc-gpio-gpi-interrupt-status-offset", &offset);
+	if (ret)
+		return ret;
+	community->is_offset = offset;
+
+	ret = device_property_read_u32(dev, "intc-gpio-gpi-interrupt-enable-offset", &offset);
+	if (ret)
+		return ret;
+	community->ie_offset = offset;
+
+	ngpps = device_get_child_node_count(dev);
+	if (!ngpps)
+		return -ENODEV;
+
+	gpps = devm_kcalloc(dev, ngpps, sizeof(*gpps), GFP_KERNEL);
+	if (!gpps)
+		return -ENOMEM;
+
+	group = 0;
+	device_for_each_child_node(dev, child) {
+		struct intel_padgroup *gpp = &gpps[group];
+
+		gpp->reg_num = group;
+
+		ret = intel_platform_pinctrl_prepare_group(dev, child, gpp, pins);
+		if (ret)
+			return ret;
+
+		group++;
+	}
+
+	community->ngpps = ngpps;
+	community->gpps = gpps;
+
+	return 0;
+}
+
+static int intel_platform_pinctrl_prepare_soc_data(struct device *dev,
+						   struct intel_pinctrl_soc_data *data)
+{
+	struct intel_platform_pins pins = {};
+	struct intel_community *communities;
+	size_t ncommunities;
+	unsigned int i;
+	int ret;
+
+	/* Version 1.0 of the specification assumes only a single community per device node */
+	ncommunities = 1,
+	communities = devm_kcalloc(dev, ncommunities, sizeof(*communities), GFP_KERNEL);
+	if (!communities)
+		return -ENOMEM;
+
+	for (i = 0; i < ncommunities; i++) {
+		struct intel_community *community = &communities[i];
+
+		community->barno = i;
+		community->pin_base = pins.npins;
+
+		ret = intel_platform_pinctrl_prepare_community(dev, community, &pins);
+		if (ret)
+			return ret;
+
+		community->npins = pins.npins - community->pin_base;
+	}
+
+	data->ncommunities = ncommunities;
+	data->communities = communities;
+
+	data->npins = pins.npins;
+	data->pins = pins.pins;
+
+	return 0;
+}
+
+static int intel_platform_pinctrl_probe(struct platform_device *pdev)
+{
+	struct intel_pinctrl_soc_data *data;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	ret = intel_platform_pinctrl_prepare_soc_data(dev, data);
+	if (ret)
+		return ret;
+
+	return intel_pinctrl_probe(pdev, data);
+}
+
+static const struct acpi_device_id intel_platform_pinctrl_acpi_match[] = {
+	{ "INTC105F" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, intel_platform_pinctrl_acpi_match);
+
+static struct platform_driver intel_platform_pinctrl_driver = {
+	.probe = intel_platform_pinctrl_probe,
+	.driver = {
+		.name = "intel-pinctrl",
+		.acpi_match_table = intel_platform_pinctrl_acpi_match,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
+	},
+};
+module_platform_driver(intel_platform_pinctrl_driver);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_DESCRIPTION("Intel PCH pinctrl/GPIO driver");
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(PINCTRL_INTEL);
-- 
GitLab


From 655b8af57d31e07340b023a807e43dadf81a0818 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Sat, 11 Nov 2023 20:15:43 +0000
Subject: [PATCH 0080/4076] thunderbolt: Remove duplicated re-assignment of
 pointer 'out'

The pointer 'out' is initialized and then a few statements later being
re-assigned the same value. The second re-assignment is redundant and
can be removed.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tunnel.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 7534cd3a81f45..8d45cb4f04abf 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -1313,8 +1313,6 @@ static void tb_dp_dump(struct tb_tunnel *tunnel)
 		      "DP IN maximum supported bandwidth %u Mb/s x%u = %u Mb/s\n",
 		      rate, lanes, tb_dp_bandwidth(rate, lanes));
 
-	out = tunnel->dst_port;
-
 	if (tb_port_read(out, &dp_cap, TB_CFG_PORT,
 			 out->cap_adap + DP_LOCAL_CAP, 1))
 		return;
-- 
GitLab


From 4f0b9194bc119a9850a99e5e824808e2f468c348 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 3 Nov 2023 06:47:51 -0400
Subject: [PATCH 0081/4076] fs: Rename anon_inode_getfile_secure() and
 anon_inode_getfd_secure()

The call to the inode_init_security_anon() LSM hook is not the sole
reason to use anon_inode_getfile_secure() or anon_inode_getfd_secure().
For example, the functions also allow one to create a file with non-zero
size, without needing a full-blown filesystem.  In this case, you don't
need a "secure" version, just unique inodes; the current name of the
functions is confusing and does not explain well the difference with
the more "standard" anon_inode_getfile() and anon_inode_getfd().

Of course, there is another side of the coin; neither io_uring nor
userfaultfd strictly speaking need distinct inodes, and it is not
that clear anymore that anon_inode_create_get{file,fd}() allow the LSM
to intercept and block the inode's creation.  If one was so inclined,
anon_inode_getfile_secure() and anon_inode_getfd_secure() could be kept,
using the shared inode or a new one depending on CONFIG_SECURITY.
However, this is probably overkill, and potentially a cause of bugs in
different configurations.  Therefore, just add a comment to io_uring
and userfaultfd explaining the choice of the function.

While at it, remove the export for what is now anon_inode_create_getfd().
There is no in-tree module that uses it, and the old name is gone anyway.
If anybody actually needs the symbol, they can ask or they can just use
anon_inode_create_getfile(), which will be exported very soon for use
in KVM.

Suggested-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 fs/anon_inodes.c            | 50 ++++++++++++++++++++++++-------------
 fs/userfaultfd.c            |  5 ++--
 include/linux/anon_inodes.h |  4 +--
 io_uring/io_uring.c         |  3 ++-
 4 files changed, 40 insertions(+), 22 deletions(-)

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 24192a7667edf..42b02dc364744 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -79,7 +79,7 @@ static struct file *__anon_inode_getfile(const char *name,
 					 const struct file_operations *fops,
 					 void *priv, int flags,
 					 const struct inode *context_inode,
-					 bool secure)
+					 bool make_inode)
 {
 	struct inode *inode;
 	struct file *file;
@@ -87,7 +87,7 @@ static struct file *__anon_inode_getfile(const char *name,
 	if (fops->owner && !try_module_get(fops->owner))
 		return ERR_PTR(-ENOENT);
 
-	if (secure) {
+	if (make_inode) {
 		inode =	anon_inode_make_secure_inode(name, context_inode);
 		if (IS_ERR(inode)) {
 			file = ERR_CAST(inode);
@@ -149,13 +149,10 @@ struct file *anon_inode_getfile(const char *name,
 EXPORT_SYMBOL_GPL(anon_inode_getfile);
 
 /**
- * anon_inode_getfile_secure - Like anon_inode_getfile(), but creates a new
+ * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new
  *                             !S_PRIVATE anon inode rather than reuse the
  *                             singleton anon inode and calls the
- *                             inode_init_security_anon() LSM hook.  This
- *                             allows for both the inode to have its own
- *                             security context and for the LSM to enforce
- *                             policy on the inode's creation.
+ *                             inode_init_security_anon() LSM hook.
  *
  * @name:    [in]    name of the "class" of the new file
  * @fops:    [in]    file operations for the new file
@@ -164,11 +161,21 @@ EXPORT_SYMBOL_GPL(anon_inode_getfile);
  * @context_inode:
  *           [in]    the logical relationship with the new inode (optional)
  *
+ * Create a new anonymous inode and file pair.  This can be done for two
+ * reasons:
+ *
+ * - for the inode to have its own security context, so that LSMs can enforce
+ *   policy on the inode's creation;
+ *
+ * - if the caller needs a unique inode, for example in order to customize
+ *   the size returned by fstat()
+ *
  * The LSM may use @context_inode in inode_init_security_anon(), but a
- * reference to it is not held.  Returns the newly created file* or an error
- * pointer.  See the anon_inode_getfile() documentation for more information.
+ * reference to it is not held.
+ *
+ * Returns the newly created file* or an error pointer.
  */
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_create_getfile(const char *name,
 				       const struct file_operations *fops,
 				       void *priv, int flags,
 				       const struct inode *context_inode)
@@ -181,7 +188,7 @@ static int __anon_inode_getfd(const char *name,
 			      const struct file_operations *fops,
 			      void *priv, int flags,
 			      const struct inode *context_inode,
-			      bool secure)
+			      bool make_inode)
 {
 	int error, fd;
 	struct file *file;
@@ -192,7 +199,7 @@ static int __anon_inode_getfd(const char *name,
 	fd = error;
 
 	file = __anon_inode_getfile(name, fops, priv, flags, context_inode,
-				    secure);
+				    make_inode);
 	if (IS_ERR(file)) {
 		error = PTR_ERR(file);
 		goto err_put_unused_fd;
@@ -231,10 +238,9 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops,
 EXPORT_SYMBOL_GPL(anon_inode_getfd);
 
 /**
- * anon_inode_getfd_secure - Like anon_inode_getfd(), but creates a new
+ * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new
  * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls
- * the inode_init_security_anon() LSM hook. This allows the inode to have its
- * own security context and for a LSM to reject creation of the inode.
+ * the inode_init_security_anon() LSM hook.
  *
  * @name:    [in]    name of the "class" of the new file
  * @fops:    [in]    file operations for the new file
@@ -243,16 +249,26 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd);
  * @context_inode:
  *           [in]    the logical relationship with the new inode (optional)
  *
+ * Create a new anonymous inode and file pair.  This can be done for two
+ * reasons:
+ *
+ * - for the inode to have its own security context, so that LSMs can enforce
+ *   policy on the inode's creation;
+ *
+ * - if the caller needs a unique inode, for example in order to customize
+ *   the size returned by fstat()
+ *
  * The LSM may use @context_inode in inode_init_security_anon(), but a
  * reference to it is not held.
+ *
+ * Returns a newly created file descriptor or an error code.
  */
-int anon_inode_getfd_secure(const char *name, const struct file_operations *fops,
+int anon_inode_create_getfd(const char *name, const struct file_operations *fops,
 			    void *priv, int flags,
 			    const struct inode *context_inode)
 {
 	return __anon_inode_getfd(name, fops, priv, flags, context_inode, true);
 }
-EXPORT_SYMBOL_GPL(anon_inode_getfd_secure);
 
 static int __init anon_inode_init(void)
 {
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 56eaae9dac1ab..7a1cf8bab5eb8 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1033,7 +1033,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *new,
 {
 	int fd;
 
-	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new,
+	fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new,
 			O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
 	if (fd < 0)
 		return fd;
@@ -2205,7 +2205,8 @@ static int new_userfaultfd(int flags)
 	/* prevent the mm struct to be freed */
 	mmgrab(ctx->mm);
 
-	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx,
+	/* Create a new inode so that the LSM can block the creation.  */
+	fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, ctx,
 			O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
 	if (fd < 0) {
 		mmdrop(ctx->mm);
diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h
index 5deaddbd79278..93a5f16d03f3f 100644
--- a/include/linux/anon_inodes.h
+++ b/include/linux/anon_inodes.h
@@ -15,13 +15,13 @@ struct inode;
 struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags);
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_create_getfile(const char *name,
 				       const struct file_operations *fops,
 				       void *priv, int flags,
 				       const struct inode *context_inode);
 int anon_inode_getfd(const char *name, const struct file_operations *fops,
 		     void *priv, int flags);
-int anon_inode_getfd_secure(const char *name,
+int anon_inode_create_getfd(const char *name,
 			    const struct file_operations *fops,
 			    void *priv, int flags,
 			    const struct inode *context_inode);
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 8d1bc6cdfe712..22b98f47bb289 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3835,7 +3835,8 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
 		return ERR_PTR(ret);
 #endif
 
-	file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
+	/* Create a new inode so that the LSM can block the creation.  */
+	file = anon_inode_create_getfile("[io_uring]", &io_uring_fops, ctx,
 					 O_RDWR | O_CLOEXEC, NULL);
 #if defined(CONFIG_UNIX)
 	if (IS_ERR(file)) {
-- 
GitLab


From a7800aa80ea4d5356b8474c2302812e9d4926fa6 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 13 Nov 2023 05:42:34 -0500
Subject: [PATCH 0082/4076] KVM: Add KVM_CREATE_GUEST_MEMFD ioctl() for
 guest-specific backing memory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce an ioctl(), KVM_CREATE_GUEST_MEMFD, to allow creating file-based
memory that is tied to a specific KVM virtual machine and whose primary
purpose is to serve guest memory.

A guest-first memory subsystem allows for optimizations and enhancements
that are kludgy or outright infeasible to implement/support in a generic
memory subsystem.  With guest_memfd, guest protections and mapping sizes
are fully decoupled from host userspace mappings.   E.g. KVM currently
doesn't support mapping memory as writable in the guest without it also
being writable in host userspace, as KVM's ABI uses VMA protections to
define the allow guest protection.  Userspace can fudge this by
establishing two mappings, a writable mapping for the guest and readable
one for itself, but that’s suboptimal on multiple fronts.

Similarly, KVM currently requires the guest mapping size to be a strict
subset of the host userspace mapping size, e.g. KVM doesn’t support
creating a 1GiB guest mapping unless userspace also has a 1GiB guest
mapping.  Decoupling the mappings sizes would allow userspace to precisely
map only what is needed without impacting guest performance, e.g. to
harden against unintentional accesses to guest memory.

Decoupling guest and userspace mappings may also allow for a cleaner
alternative to high-granularity mappings for HugeTLB, which has reached a
bit of an impasse and is unlikely to ever be merged.

A guest-first memory subsystem also provides clearer line of sight to
things like a dedicated memory pool (for slice-of-hardware VMs) and
elimination of "struct page" (for offload setups where userspace _never_
needs to mmap() guest memory).

More immediately, being able to map memory into KVM guests without mapping
said memory into the host is critical for Confidential VMs (CoCo VMs), the
initial use case for guest_memfd.  While AMD's SEV and Intel's TDX prevent
untrusted software from reading guest private data by encrypting guest
memory with a key that isn't usable by the untrusted host, projects such
as Protected KVM (pKVM) provide confidentiality and integrity *without*
relying on memory encryption.  And with SEV-SNP and TDX, accessing guest
private memory can be fatal to the host, i.e. KVM must be prevent host
userspace from accessing guest memory irrespective of hardware behavior.

Attempt #1 to support CoCo VMs was to add a VMA flag to mark memory as
being mappable only by KVM (or a similarly enlightened kernel subsystem).
That approach was abandoned largely due to it needing to play games with
PROT_NONE to prevent userspace from accessing guest memory.

Attempt #2 to was to usurp PG_hwpoison to prevent the host from mapping
guest private memory into userspace, but that approach failed to meet
several requirements for software-based CoCo VMs, e.g. pKVM, as the kernel
wouldn't easily be able to enforce a 1:1 page:guest association, let alone
a 1:1 pfn:gfn mapping.  And using PG_hwpoison does not work for memory
that isn't backed by 'struct page', e.g. if devices gain support for
exposing encrypted memory regions to guests.

Attempt #3 was to extend the memfd() syscall and wrap shmem to provide
dedicated file-based guest memory.  That approach made it as far as v10
before feedback from Hugh Dickins and Christian Brauner (and others) led
to it demise.

Hugh's objection was that piggybacking shmem made no sense for KVM's use
case as KVM didn't actually *want* the features provided by shmem.  I.e.
KVM was using memfd() and shmem to avoid having to manage memory directly,
not because memfd() and shmem were the optimal solution, e.g. things like
read/write/mmap in shmem were dead weight.

Christian pointed out flaws with implementing a partial overlay (wrapping
only _some_ of shmem), e.g. poking at inode_operations or super_operations
would show shmem stuff, but address_space_operations and file_operations
would show KVM's overlay.  Paraphrashing heavily, Christian suggested KVM
stop being lazy and create a proper API.

Link: https://lore.kernel.org/all/20201020061859.18385-1-kirill.shutemov@linux.intel.com
Link: https://lore.kernel.org/all/20210416154106.23721-1-kirill.shutemov@linux.intel.com
Link: https://lore.kernel.org/all/20210824005248.200037-1-seanjc@google.com
Link: https://lore.kernel.org/all/20211111141352.26311-1-chao.p.peng@linux.intel.com
Link: https://lore.kernel.org/all/20221202061347.1070246-1-chao.p.peng@linux.intel.com
Link: https://lore.kernel.org/all/ff5c5b97-acdf-9745-ebe5-c6609dd6322e@google.com
Link: https://lore.kernel.org/all/20230418-anfallen-irdisch-6993a61be10b@brauner
Link: https://lore.kernel.org/all/ZEM5Zq8oo+xnApW9@google.com
Link: https://lore.kernel.org/linux-mm/20230306191944.GA15773@monkey
Link: https://lore.kernel.org/linux-mm/ZII1p8ZHlHaQ3dDl@casper.infradead.org
Cc: Fuad Tabba <tabba@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerley Tng <ackerleytng@google.com>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Maciej Szmigiero <mail@maciej.szmigiero.name>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Quentin Perret <qperret@google.com>
Cc: Michael Roth <michael.roth@amd.com>
Cc: Wang <wei.w.wang@intel.com>
Cc: Liam Merwick <liam.merwick@oracle.com>
Cc: Isaku Yamahata <isaku.yamahata@gmail.com>
Co-developed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Co-developed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Co-developed-by: Chao Peng <chao.p.peng@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Co-developed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-17-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst |  70 ++++-
 fs/anon_inodes.c               |   1 +
 include/linux/kvm_host.h       |  48 +++
 include/uapi/linux/kvm.h       |  15 +-
 virt/kvm/Kconfig               |   4 +
 virt/kvm/Makefile.kvm          |   1 +
 virt/kvm/guest_memfd.c         | 538 +++++++++++++++++++++++++++++++++
 virt/kvm/kvm_main.c            |  59 +++-
 virt/kvm/kvm_mm.h              |  26 ++
 9 files changed, 754 insertions(+), 8 deletions(-)
 create mode 100644 virt/kvm/guest_memfd.c

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 081ef09d3148f..1e61faf02b2ac 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6201,6 +6201,15 @@ superset of the features supported by the system.
 :Parameters: struct kvm_userspace_memory_region2 (in)
 :Returns: 0 on success, -1 on error
 
+KVM_SET_USER_MEMORY_REGION2 is an extension to KVM_SET_USER_MEMORY_REGION that
+allows mapping guest_memfd memory into a guest.  All fields shared with
+KVM_SET_USER_MEMORY_REGION identically.  Userspace can set KVM_MEM_GUEST_MEMFD
+in flags to have KVM bind the memory region to a given guest_memfd range of
+[guest_memfd_offset, guest_memfd_offset + memory_size].  The target guest_memfd
+must point at a file created via KVM_CREATE_GUEST_MEMFD on the current VM, and
+the target range must not be bound to any other memory region.  All standard
+bounds checks apply (use common sense).
+
 ::
 
   struct kvm_userspace_memory_region2 {
@@ -6209,10 +6218,24 @@ superset of the features supported by the system.
 	__u64 guest_phys_addr;
 	__u64 memory_size; /* bytes */
 	__u64 userspace_addr; /* start of the userspace allocated memory */
-	__u64 pad[16];
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
   };
 
-See KVM_SET_USER_MEMORY_REGION.
+A KVM_MEM_GUEST_MEMFD region _must_ have a valid guest_memfd (private memory) and
+userspace_addr (shared memory).  However, "valid" for userspace_addr simply
+means that the address itself must be a legal userspace address.  The backing
+mapping for userspace_addr is not required to be valid/populated at the time of
+KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated
+on-demand.
+
+When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes
+userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE
+state.  At VM creation time, all memory is shared, i.e. the PRIVATE attribute
+is '0' for all gfns.  Userspace can control whether memory is shared/private by
+toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed.
 
 4.141 KVM_SET_MEMORY_ATTRIBUTES
 -------------------------------
@@ -6250,6 +6273,49 @@ the state of a gfn/page as needed.
 
 The "flags" field is reserved for future extensions and must be '0'.
 
+4.142 KVM_CREATE_GUEST_MEMFD
+----------------------------
+
+:Capability: KVM_CAP_GUEST_MEMFD
+:Architectures: none
+:Type: vm ioctl
+:Parameters: struct kvm_create_guest_memfd(in)
+:Returns: 0 on success, <0 on error
+
+KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor
+that refers to it.  guest_memfd files are roughly analogous to files created
+via memfd_create(), e.g. guest_memfd files live in RAM, have volatile storage,
+and are automatically released when the last reference is dropped.  Unlike
+"regular" memfd_create() files, guest_memfd files are bound to their owning
+virtual machine (see below), cannot be mapped, read, or written by userspace,
+and cannot be resized  (guest_memfd files do however support PUNCH_HOLE).
+
+::
+
+  struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+  };
+
+Conceptually, the inode backing a guest_memfd file represents physical memory,
+i.e. is coupled to the virtual machine as a thing, not to a "struct kvm".  The
+file itself, which is bound to a "struct kvm", is that instance's view of the
+underlying memory, e.g. effectively provides the translation of guest addresses
+to host memory.  This allows for use cases where multiple KVM structures are
+used to manage a single virtual machine, e.g. when performing intrahost
+migration of a virtual machine.
+
+KVM currently only supports mapping guest_memfd via KVM_SET_USER_MEMORY_REGION2,
+and more specifically via the guest_memfd and guest_memfd_offset fields in
+"struct kvm_userspace_memory_region2", where guest_memfd_offset is the offset
+into the guest_memfd instance.  For a given guest_memfd file, there can be at
+most one mapping per page, i.e. binding multiple memory regions to a single
+guest_memfd range is not allowed (any number of memory regions can be bound to
+a single guest_memfd file, but the bound ranges must not overlap).
+
+See KVM_SET_USER_MEMORY_REGION2 for additional details.
+
 5. The kvm_run structure
 ========================
 
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 42b02dc364744..8dd436ee985b3 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -183,6 +183,7 @@ struct file *anon_inode_create_getfile(const char *name,
 	return __anon_inode_getfile(name, fops, priv, flags,
 				    context_inode, true);
 }
+EXPORT_SYMBOL_GPL(anon_inode_create_getfile);
 
 static int __anon_inode_getfd(const char *name,
 			      const struct file_operations *fops,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 68a144cb7dbc6..a6de526c04267 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -589,8 +589,20 @@ struct kvm_memory_slot {
 	u32 flags;
 	short id;
 	u16 as_id;
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	struct {
+		struct file __rcu *file;
+		pgoff_t pgoff;
+	} gmem;
+#endif
 };
 
+static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
+{
+	return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
+}
+
 static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
 {
 	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
@@ -685,6 +697,17 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 }
 #endif
 
+/*
+ * Arch code must define kvm_arch_has_private_mem if support for private memory
+ * is enabled.
+ */
+#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 struct kvm_memslots {
 	u64 generation;
 	atomic_long_t last_used_slot;
@@ -1400,6 +1423,7 @@ void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 void kvm_mmu_invalidate_begin(struct kvm *kvm);
 void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
 void kvm_mmu_invalidate_end(struct kvm *kvm);
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -2355,6 +2379,30 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range);
 bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
 					 struct kvm_gfn_range *range);
+
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) &&
+	       kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+}
+#else
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return false;
+}
 #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
+#else
+static inline int kvm_gmem_get_pfn(struct kvm *kvm,
+				   struct kvm_memory_slot *slot, gfn_t gfn,
+				   kvm_pfn_t *pfn, int *max_order)
+{
+	KVM_BUG_ON(1, kvm);
+	return -EIO;
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e8d167e549804..2802d10aa88c4 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -102,7 +102,10 @@ struct kvm_userspace_memory_region2 {
 	__u64 guest_phys_addr;
 	__u64 memory_size;
 	__u64 userspace_addr;
-	__u64 pad[16];
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
 };
 
 /*
@@ -112,6 +115,7 @@ struct kvm_userspace_memory_region2 {
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
+#define KVM_MEM_GUEST_MEMFD	(1UL << 2)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -1221,6 +1225,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_USER_MEMORY2 231
 #define KVM_CAP_MEMORY_FAULT_INFO 232
 #define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -2301,4 +2306,12 @@ struct kvm_memory_attributes {
 
 #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
 
+#define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 5bd7fcaf9089c..08afef022db9f 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -100,3 +100,7 @@ config KVM_GENERIC_MMU_NOTIFIER
 config KVM_GENERIC_MEMORY_ATTRIBUTES
        select KVM_GENERIC_MMU_NOTIFIER
        bool
+
+config KVM_PRIVATE_MEM
+       select XARRAY_MULTI
+       bool
diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm
index 2c27d5d0c367c..724c89af78af9 100644
--- a/virt/kvm/Makefile.kvm
+++ b/virt/kvm/Makefile.kvm
@@ -12,3 +12,4 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
 kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o
 kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o
 kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o
+kvm-$(CONFIG_KVM_PRIVATE_MEM) += $(KVM)/guest_memfd.o
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
new file mode 100644
index 0000000000000..e65f4170425c4
--- /dev/null
+++ b/virt/kvm/guest_memfd.c
@@ -0,0 +1,538 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/backing-dev.h>
+#include <linux/falloc.h>
+#include <linux/kvm_host.h>
+#include <linux/pagemap.h>
+#include <linux/anon_inodes.h>
+
+#include "kvm_mm.h"
+
+struct kvm_gmem {
+	struct kvm *kvm;
+	struct xarray bindings;
+	struct list_head entry;
+};
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+{
+	struct folio *folio;
+
+	/* TODO: Support huge pages. */
+	folio = filemap_grab_folio(inode->i_mapping, index);
+	if (IS_ERR_OR_NULL(folio))
+		return NULL;
+
+	/*
+	 * Use the up-to-date flag to track whether or not the memory has been
+	 * zeroed before being handed off to the guest.  There is no backing
+	 * storage for the memory, so the folio will remain up-to-date until
+	 * it's removed.
+	 *
+	 * TODO: Skip clearing pages when trusted firmware will do it when
+	 * assigning memory to the guest.
+	 */
+	if (!folio_test_uptodate(folio)) {
+		unsigned long nr_pages = folio_nr_pages(folio);
+		unsigned long i;
+
+		for (i = 0; i < nr_pages; i++)
+			clear_highpage(folio_page(folio, i));
+
+		folio_mark_uptodate(folio);
+	}
+
+	/*
+	 * Ignore accessed, referenced, and dirty flags.  The memory is
+	 * unevictable and there is no storage to write back to.
+	 */
+	return folio;
+}
+
+static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
+				      pgoff_t end)
+{
+	bool flush = false, found_memslot = false;
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = gmem->kvm;
+	unsigned long index;
+
+	xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) {
+		pgoff_t pgoff = slot->gmem.pgoff;
+
+		struct kvm_gfn_range gfn_range = {
+			.start = slot->base_gfn + max(pgoff, start) - pgoff,
+			.end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff,
+			.slot = slot,
+			.may_block = true,
+		};
+
+		if (!found_memslot) {
+			found_memslot = true;
+
+			KVM_MMU_LOCK(kvm);
+			kvm_mmu_invalidate_begin(kvm);
+		}
+
+		flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range);
+	}
+
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	if (found_memslot)
+		KVM_MMU_UNLOCK(kvm);
+}
+
+static void kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start,
+				    pgoff_t end)
+{
+	struct kvm *kvm = gmem->kvm;
+
+	if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+		KVM_MMU_LOCK(kvm);
+		kvm_mmu_invalidate_end(kvm);
+		KVM_MMU_UNLOCK(kvm);
+	}
+}
+
+static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct list_head *gmem_list = &inode->i_mapping->private_list;
+	pgoff_t start = offset >> PAGE_SHIFT;
+	pgoff_t end = (offset + len) >> PAGE_SHIFT;
+	struct kvm_gmem *gmem;
+
+	/*
+	 * Bindings must be stable across invalidation to ensure the start+end
+	 * are balanced.
+	 */
+	filemap_invalidate_lock(inode->i_mapping);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_begin(gmem, start, end);
+
+	truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_end(gmem, start, end);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	return 0;
+}
+
+static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t start, index, end;
+	int r;
+
+	/* Dedicated guest is immutable by default. */
+	if (offset + len > i_size_read(inode))
+		return -EINVAL;
+
+	filemap_invalidate_lock_shared(mapping);
+
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len) >> PAGE_SHIFT;
+
+	r = 0;
+	for (index = start; index < end; ) {
+		struct folio *folio;
+
+		if (signal_pending(current)) {
+			r = -EINTR;
+			break;
+		}
+
+		folio = kvm_gmem_get_folio(inode, index);
+		if (!folio) {
+			r = -ENOMEM;
+			break;
+		}
+
+		index = folio_next_index(folio);
+
+		folio_unlock(folio);
+		folio_put(folio);
+
+		/* 64-bit only, wrapping the index should be impossible. */
+		if (WARN_ON_ONCE(!index))
+			break;
+
+		cond_resched();
+	}
+
+	filemap_invalidate_unlock_shared(mapping);
+
+	return r;
+}
+
+static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset,
+			       loff_t len)
+{
+	int ret;
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE))
+		return -EOPNOTSUPP;
+
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))
+		return -EINVAL;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		ret = kvm_gmem_punch_hole(file_inode(file), offset, len);
+	else
+		ret = kvm_gmem_allocate(file_inode(file), offset, len);
+
+	if (!ret)
+		file_modified(file);
+	return ret;
+}
+
+static int kvm_gmem_release(struct inode *inode, struct file *file)
+{
+	struct kvm_gmem *gmem = file->private_data;
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = gmem->kvm;
+	unsigned long index;
+
+	/*
+	 * Prevent concurrent attempts to *unbind* a memslot.  This is the last
+	 * reference to the file and thus no new bindings can be created, but
+	 * dereferencing the slot for existing bindings needs to be protected
+	 * against memslot updates, specifically so that unbind doesn't race
+	 * and free the memslot (kvm_gmem_get_file() will return NULL).
+	 */
+	mutex_lock(&kvm->slots_lock);
+
+	filemap_invalidate_lock(inode->i_mapping);
+
+	xa_for_each(&gmem->bindings, index, slot)
+		rcu_assign_pointer(slot->gmem.file, NULL);
+
+	synchronize_rcu();
+
+	/*
+	 * All in-flight operations are gone and new bindings can be created.
+	 * Zap all SPTEs pointed at by this file.  Do not free the backing
+	 * memory, as its lifetime is associated with the inode, not the file.
+	 */
+	kvm_gmem_invalidate_begin(gmem, 0, -1ul);
+	kvm_gmem_invalidate_end(gmem, 0, -1ul);
+
+	list_del(&gmem->entry);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	mutex_unlock(&kvm->slots_lock);
+
+	xa_destroy(&gmem->bindings);
+	kfree(gmem);
+
+	kvm_put_kvm(kvm);
+
+	return 0;
+}
+
+static struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot)
+{
+	struct file *file;
+
+	rcu_read_lock();
+
+	file = rcu_dereference(slot->gmem.file);
+	if (file && !get_file_rcu(file))
+		file = NULL;
+
+	rcu_read_unlock();
+
+	return file;
+}
+
+static struct file_operations kvm_gmem_fops = {
+	.open		= generic_file_open,
+	.release	= kvm_gmem_release,
+	.fallocate	= kvm_gmem_fallocate,
+};
+
+void kvm_gmem_init(struct module *module)
+{
+	kvm_gmem_fops.owner = module;
+}
+
+static int kvm_gmem_migrate_folio(struct address_space *mapping,
+				  struct folio *dst, struct folio *src,
+				  enum migrate_mode mode)
+{
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
+static int kvm_gmem_error_page(struct address_space *mapping, struct page *page)
+{
+	struct list_head *gmem_list = &mapping->private_list;
+	struct kvm_gmem *gmem;
+	pgoff_t start, end;
+
+	filemap_invalidate_lock_shared(mapping);
+
+	start = page->index;
+	end = start + thp_nr_pages(page);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_begin(gmem, start, end);
+
+	/*
+	 * Do not truncate the range, what action is taken in response to the
+	 * error is userspace's decision (assuming the architecture supports
+	 * gracefully handling memory errors).  If/when the guest attempts to
+	 * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON,
+	 * at which point KVM can either terminate the VM or propagate the
+	 * error to userspace.
+	 */
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_end(gmem, start, end);
+
+	filemap_invalidate_unlock_shared(mapping);
+
+	return MF_DELAYED;
+}
+
+static const struct address_space_operations kvm_gmem_aops = {
+	.dirty_folio = noop_dirty_folio,
+#ifdef CONFIG_MIGRATION
+	.migrate_folio	= kvm_gmem_migrate_folio,
+#endif
+	.error_remove_page = kvm_gmem_error_page,
+};
+
+static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,
+			    struct kstat *stat, u32 request_mask,
+			    unsigned int query_flags)
+{
+	struct inode *inode = path->dentry->d_inode;
+
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			    struct iattr *attr)
+{
+	return -EINVAL;
+}
+static const struct inode_operations kvm_gmem_iops = {
+	.getattr	= kvm_gmem_getattr,
+	.setattr	= kvm_gmem_setattr,
+};
+
+static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
+{
+	const char *anon_name = "[kvm-gmem]";
+	struct kvm_gmem *gmem;
+	struct inode *inode;
+	struct file *file;
+	int fd, err;
+
+	fd = get_unused_fd_flags(0);
+	if (fd < 0)
+		return fd;
+
+	gmem = kzalloc(sizeof(*gmem), GFP_KERNEL);
+	if (!gmem) {
+		err = -ENOMEM;
+		goto err_fd;
+	}
+
+	file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem,
+					 O_RDWR, NULL);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_gmem;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+
+	inode = file->f_inode;
+	WARN_ON(file->f_mapping != inode->i_mapping);
+
+	inode->i_private = (void *)(unsigned long)flags;
+	inode->i_op = &kvm_gmem_iops;
+	inode->i_mapping->a_ops = &kvm_gmem_aops;
+	inode->i_mode |= S_IFREG;
+	inode->i_size = size;
+	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+	mapping_set_unmovable(inode->i_mapping);
+	/* Unmovable mappings are supposed to be marked unevictable as well. */
+	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
+
+	kvm_get_kvm(kvm);
+	gmem->kvm = kvm;
+	xa_init(&gmem->bindings);
+	list_add(&gmem->entry, &inode->i_mapping->private_list);
+
+	fd_install(fd, file);
+	return fd;
+
+err_gmem:
+	kfree(gmem);
+err_fd:
+	put_unused_fd(fd);
+	return err;
+}
+
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
+{
+	loff_t size = args->size;
+	u64 flags = args->flags;
+	u64 valid_flags = 0;
+
+	if (flags & ~valid_flags)
+		return -EINVAL;
+
+	if (size <= 0 || !PAGE_ALIGNED(size))
+		return -EINVAL;
+
+	return __kvm_gmem_create(kvm, size, flags);
+}
+
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+		  unsigned int fd, loff_t offset)
+{
+	loff_t size = slot->npages << PAGE_SHIFT;
+	unsigned long start, end;
+	struct kvm_gmem *gmem;
+	struct inode *inode;
+	struct file *file;
+	int r = -EINVAL;
+
+	BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff));
+
+	file = fget(fd);
+	if (!file)
+		return -EBADF;
+
+	if (file->f_op != &kvm_gmem_fops)
+		goto err;
+
+	gmem = file->private_data;
+	if (gmem->kvm != kvm)
+		goto err;
+
+	inode = file_inode(file);
+
+	if (offset < 0 || !PAGE_ALIGNED(offset) ||
+	    offset + size > i_size_read(inode))
+		goto err;
+
+	filemap_invalidate_lock(inode->i_mapping);
+
+	start = offset >> PAGE_SHIFT;
+	end = start + slot->npages;
+
+	if (!xa_empty(&gmem->bindings) &&
+	    xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+		filemap_invalidate_unlock(inode->i_mapping);
+		goto err;
+	}
+
+	/*
+	 * No synchronize_rcu() needed, any in-flight readers are guaranteed to
+	 * be see either a NULL file or this new file, no need for them to go
+	 * away.
+	 */
+	rcu_assign_pointer(slot->gmem.file, file);
+	slot->gmem.pgoff = start;
+
+	xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL);
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	/*
+	 * Drop the reference to the file, even on success.  The file pins KVM,
+	 * not the other way 'round.  Active bindings are invalidated if the
+	 * file is closed before memslots are destroyed.
+	 */
+	r = 0;
+err:
+	fput(file);
+	return r;
+}
+
+void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	unsigned long start = slot->gmem.pgoff;
+	unsigned long end = start + slot->npages;
+	struct kvm_gmem *gmem;
+	struct file *file;
+
+	/*
+	 * Nothing to do if the underlying file was already closed (or is being
+	 * closed right now), kvm_gmem_release() invalidates all bindings.
+	 */
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return;
+
+	gmem = file->private_data;
+
+	filemap_invalidate_lock(file->f_mapping);
+	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
+	rcu_assign_pointer(slot->gmem.file, NULL);
+	synchronize_rcu();
+	filemap_invalidate_unlock(file->f_mapping);
+
+	fput(file);
+}
+
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+{
+	pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
+	struct kvm_gmem *gmem;
+	struct folio *folio;
+	struct page *page;
+	struct file *file;
+	int r;
+
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return -EFAULT;
+
+	gmem = file->private_data;
+
+	if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) {
+		r = -EIO;
+		goto out_fput;
+	}
+
+	folio = kvm_gmem_get_folio(file_inode(file), index);
+	if (!folio) {
+		r = -ENOMEM;
+		goto out_fput;
+	}
+
+	if (folio_test_hwpoison(folio)) {
+		r = -EHWPOISON;
+		goto out_unlock;
+	}
+
+	page = folio_file_page(folio, index);
+
+	*pfn = page_to_pfn(page);
+	if (max_order)
+		*max_order = 0;
+
+	r = 0;
+
+out_unlock:
+	folio_unlock(folio);
+out_fput:
+	fput(file);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f1a575d39b3bb..8f46d757a2c5d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -791,7 +791,7 @@ void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
 	}
 }
 
-static bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
 	return kvm_unmap_gfn_range(kvm, range);
@@ -1027,6 +1027,9 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /* This does not remove the slot from struct kvm_memslots data structures */
 static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
+	if (slot->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(slot);
+
 	kvm_destroy_dirty_bitmap(slot);
 
 	kvm_arch_free_memslot(kvm, slot);
@@ -1606,10 +1609,18 @@ static void kvm_replace_memslot(struct kvm *kvm,
 #define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
 	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem)
+static int check_memory_region_flags(struct kvm *kvm,
+				     const struct kvm_userspace_memory_region2 *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
+	if (kvm_arch_has_private_mem(kvm))
+		valid_flags |= KVM_MEM_GUEST_MEMFD;
+
+	/* Dirty logging private memory is not currently supported. */
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
+
 #ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
@@ -2018,7 +2029,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int as_id, id;
 	int r;
 
-	r = check_memory_region_flags(mem);
+	r = check_memory_region_flags(kvm, mem);
 	if (r)
 		return r;
 
@@ -2037,6 +2048,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;
+	if (mem->flags & KVM_MEM_GUEST_MEMFD &&
+	    (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
+	     mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
+		return -EINVAL;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
@@ -2075,6 +2090,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
 			return -EINVAL;
 	} else { /* Modify an existing slot. */
+		/* Private memslots are immutable, they can only be deleted. */
+		if (mem->flags & KVM_MEM_GUEST_MEMFD)
+			return -EINVAL;
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
 		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -2103,10 +2121,23 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new->npages = npages;
 	new->flags = mem->flags;
 	new->userspace_addr = mem->userspace_addr;
+	if (mem->flags & KVM_MEM_GUEST_MEMFD) {
+		r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset);
+		if (r)
+			goto out;
+	}
 
 	r = kvm_set_memslot(kvm, old, new, change);
 	if (r)
-		kfree(new);
+		goto out_unbind;
+
+	return 0;
+
+out_unbind:
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(new);
+out:
+	kfree(new);
 	return r;
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
@@ -2442,7 +2473,7 @@ out:
 
 static u64 kvm_supported_mem_attributes(struct kvm *kvm)
 {
-	if (!kvm)
+	if (!kvm || kvm_arch_has_private_mem(kvm))
 		return KVM_MEMORY_ATTRIBUTE_PRIVATE;
 
 	return 0;
@@ -4844,6 +4875,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 	case KVM_CAP_MEMORY_ATTRIBUTES:
 		return kvm_supported_mem_attributes(kvm);
+#endif
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CAP_GUEST_MEMFD:
+		return !kvm || kvm_arch_has_private_mem(kvm);
 #endif
 	default:
 		break;
@@ -5277,6 +5312,18 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_GET_STATS_FD:
 		r = kvm_vm_ioctl_get_stats_fd(kvm);
 		break;
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CREATE_GUEST_MEMFD: {
+		struct kvm_create_guest_memfd guest_memfd;
+
+		r = -EFAULT;
+		if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd)))
+			goto out;
+
+		r = kvm_gmem_create(kvm, &guest_memfd);
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -6409,6 +6456,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (WARN_ON_ONCE(r))
 		goto err_vfio;
 
+	kvm_gmem_init(module);
+
 	/*
 	 * Registration _must_ be the very last thing done, as this exposes
 	 * /dev/kvm to userspace, i.e. all infrastructure must be setup!
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index 180f1a09e6ba7..ecefc7ec51af8 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -37,4 +37,30 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 }
 #endif /* HAVE_KVM_PFNCACHE */
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+void kvm_gmem_init(struct module *module);
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args);
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+		  unsigned int fd, loff_t offset);
+void kvm_gmem_unbind(struct kvm_memory_slot *slot);
+#else
+static inline void kvm_gmem_init(struct module *module)
+{
+
+}
+
+static inline int kvm_gmem_bind(struct kvm *kvm,
+					 struct kvm_memory_slot *slot,
+					 unsigned int fd, loff_t offset)
+{
+	WARN_ON_ONCE(1);
+	return -EIO;
+}
+
+static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	WARN_ON_ONCE(1);
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif /* __KVM_MM_H__ */
-- 
GitLab


From ee605e31563348f44d2ff0b6b74d33df69dd535c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:00 -0700
Subject: [PATCH 0083/4076] KVM: x86: "Reset" vcpu->run->exit_reason early in
 KVM_RUN

Initialize run->exit_reason to KVM_EXIT_UNKNOWN early in KVM_RUN to reduce
the probability of exiting to userspace with a stale run->exit_reason that
*appears* to be valid.

To support fd-based guest memory (guest memory without a corresponding
userspace virtual address), KVM will exit to userspace for various memory
related errors, which userspace *may* be able to resolve, instead of using
e.g. BUS_MCEERR_AR.  And in the more distant future, KVM will also likely
utilize the same functionality to let userspace "intercept" and handle
memory faults when the userspace mapping is missing, i.e. when fast gup()
fails.

Because many of KVM's internal APIs related to guest memory use '0' to
indicate "success, continue on" and not "exit to userspace", reporting
memory faults/errors to userspace will set run->exit_reason and
corresponding fields in the run structure fields in conjunction with a
a non-zero, negative return code, e.g. -EFAULT or -EHWPOISON.  And because
KVM already returns  -EFAULT in many paths, there's a relatively high
probability that KVM could return -EFAULT without setting run->exit_reason,
in which case reporting KVM_EXIT_UNKNOWN is much better than reporting
whatever exit reason happened to be in the run structure.

Note, KVM must wait until after run->immediate_exit is serviced to
sanitize run->exit_reason as KVM's ABI is that run->exit_reason is
preserved across KVM_RUN when run->immediate_exit is true.

Link: https://lore.kernel.org/all/20230908222905.1321305-1-amoorthy@google.com
Link: https://lore.kernel.org/all/ZFFbwOXZ5uI%2Fgdaf@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-19-seanjc@google.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8f9d8939b63bb..f661acb01c585 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11082,6 +11082,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int r;
 
+	vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
 	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
-- 
GitLab


From 90b4fe17981e155432c4dbc490606d0c2e9c2199 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:22:01 -0700
Subject: [PATCH 0084/4076] KVM: x86: Disallow hugepages when memory attributes
 are mixed

Disallow creating hugepages with mixed memory attributes, e.g. shared
versus private, as mapping a hugepage in this case would allow the guest
to access memory with the wrong attributes, e.g. overlaying private memory
with a shared hugepage.

Tracking whether or not attributes are mixed via the existing
disallow_lpage field, but use the most significant bit in 'disallow_lpage'
to indicate a hugepage has mixed attributes instead using the normal
refcounting.  Whether or not attributes are mixed is binary; either they
are or they aren't.  Attempting to squeeze that info into the refcount is
unnecessarily complex as it would require knowing the previous state of
the mixed count when updating attributes.  Using a flag means KVM just
needs to ensure the current status is reflected in the memslots.

Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-20-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |   3 +
 arch/x86/kvm/mmu/mmu.c          | 154 +++++++++++++++++++++++++++++++-
 arch/x86/kvm/x86.c              |   4 +
 3 files changed, 159 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6f559fb75e6dd..fa0d422024058 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1848,6 +1848,9 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu);
 void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 
+void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
+					    struct kvm_memory_slot *slot);
+
 void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b2d916f786ca1..f5c6b0643645c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -795,16 +795,26 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
 	return &slot->arch.lpage_info[level - 2][idx];
 }
 
+/*
+ * The most significant bit in disallow_lpage tracks whether or not memory
+ * attributes are mixed, i.e. not identical for all gfns at the current level.
+ * The lower order bits are used to refcount other cases where a hugepage is
+ * disallowed, e.g. if KVM has shadow a page table at the gfn.
+ */
+#define KVM_LPAGE_MIXED_FLAG	BIT(31)
+
 static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
 					    gfn_t gfn, int count)
 {
 	struct kvm_lpage_info *linfo;
-	int i;
+	int old, i;
 
 	for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
 		linfo = lpage_info_slot(gfn, slot, i);
+
+		old = linfo->disallow_lpage;
 		linfo->disallow_lpage += count;
-		WARN_ON_ONCE(linfo->disallow_lpage < 0);
+		WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG);
 	}
 }
 
@@ -7176,3 +7186,143 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 	if (kvm->arch.nx_huge_page_recovery_thread)
 		kthread_stop(kvm->arch.nx_huge_page_recovery_thread);
 }
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				int level)
+{
+	return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				 int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+			       int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
+static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       gfn_t gfn, int level, unsigned long attrs)
+{
+	const unsigned long start = gfn;
+	const unsigned long end = start + KVM_PAGES_PER_HPAGE(level);
+
+	if (level == PG_LEVEL_2M)
+		return kvm_range_has_memory_attributes(kvm, start, end, attrs);
+
+	for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) {
+		if (hugepage_test_mixed(slot, gfn, level - 1) ||
+		    attrs != kvm_get_memory_attributes(kvm, gfn))
+			return false;
+	}
+	return true;
+}
+
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range)
+{
+	unsigned long attrs = range->arg.attributes;
+	struct kvm_memory_slot *slot = range->slot;
+	int level;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	lockdep_assert_held(&kvm->slots_lock);
+
+	/*
+	 * Calculate which ranges can be mapped with hugepages even if the slot
+	 * can't map memory PRIVATE.  KVM mustn't create a SHARED hugepage over
+	 * a range that has PRIVATE GFNs, and conversely converting a range to
+	 * SHARED may now allow hugepages.
+	 */
+	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+		return false;
+
+	/*
+	 * The sequence matters here: upper levels consume the result of lower
+	 * level's scanning.
+	 */
+	for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+		gfn_t gfn = gfn_round_for_level(range->start, level);
+
+		/* Process the head page if it straddles the range. */
+		if (gfn != range->start || gfn + nr_pages > range->end) {
+			/*
+			 * Skip mixed tracking if the aligned gfn isn't covered
+			 * by the memslot, KVM can't use a hugepage due to the
+			 * misaligned address regardless of memory attributes.
+			 */
+			if (gfn >= slot->base_gfn) {
+				if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+					hugepage_clear_mixed(slot, gfn, level);
+				else
+					hugepage_set_mixed(slot, gfn, level);
+			}
+			gfn += nr_pages;
+		}
+
+		/*
+		 * Pages entirely covered by the range are guaranteed to have
+		 * only the attributes which were just set.
+		 */
+		for ( ; gfn + nr_pages <= range->end; gfn += nr_pages)
+			hugepage_clear_mixed(slot, gfn, level);
+
+		/*
+		 * Process the last tail page if it straddles the range and is
+		 * contained by the memslot.  Like the head page, KVM can't
+		 * create a hugepage if the slot size is misaligned.
+		 */
+		if (gfn < range->end &&
+		    (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) {
+			if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+				hugepage_clear_mixed(slot, gfn, level);
+			else
+				hugepage_set_mixed(slot, gfn, level);
+		}
+	}
+	return false;
+}
+
+void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
+					    struct kvm_memory_slot *slot)
+{
+	int level;
+
+	if (!kvm_arch_has_private_mem(kvm))
+		return;
+
+	for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		/*
+		 * Don't bother tracking mixed attributes for pages that can't
+		 * be huge due to alignment, i.e. process only pages that are
+		 * entirely contained by the memslot.
+		 */
+		gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level);
+		gfn_t start = gfn_round_for_level(slot->base_gfn, level);
+		gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+		gfn_t gfn;
+
+		if (start < slot->base_gfn)
+			start += nr_pages;
+
+		/*
+		 * Unlike setting attributes, every potential hugepage needs to
+		 * be manually checked as the attributes may already be mixed.
+		 */
+		for (gfn = start; gfn < end; gfn += nr_pages) {
+			unsigned long attrs = kvm_get_memory_attributes(kvm, gfn);
+
+			if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
+				hugepage_clear_mixed(slot, gfn, level);
+			else
+				hugepage_set_mixed(slot, gfn, level);
+		}
+	}
+}
+#endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f661acb01c585..e1aad0c81f6f2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12728,6 +12728,10 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm,
 		}
 	}
 
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	kvm_mmu_init_memslot_memory_attributes(kvm, slot);
+#endif
+
 	if (kvm_page_track_create_memslot(kvm, slot, npages))
 		goto out_free;
 
-- 
GitLab


From 8dd2eee9d526c30fccfe75da7ec5365c6476e510 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:22:02 -0700
Subject: [PATCH 0085/4076] KVM: x86/mmu: Handle page fault for private memory

Add support for resolving page faults on guest private memory for VMs
that differentiate between "shared" and "private" memory.  For such VMs,
KVM_MEM_GUEST_MEMFD memslots can include both fd-based private memory and
hva-based shared memory, and KVM needs to map in the "correct" variant,
i.e. KVM needs to map the gfn shared/private as appropriate based on the
current state of the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE flag.

For AMD's SEV-SNP and Intel's TDX, the guest effectively gets to request
shared vs. private via a bit in the guest page tables, i.e. what the guest
wants may conflict with the current memory attributes.  To support such
"implicit" conversion requests, exit to user with KVM_EXIT_MEMORY_FAULT
to forward the request to userspace.  Add a new flag for memory faults,
KVM_MEMORY_EXIT_FLAG_PRIVATE, to communicate whether the guest wants to
map memory as shared vs. private.

Like KVM_MEMORY_ATTRIBUTE_PRIVATE, use bit 3 for flagging private memory
so that KVM can use bits 0-2 for capturing RWX behavior if/when userspace
needs such information, e.g. a likely user of KVM_EXIT_MEMORY_FAULT is to
exit on missing mappings when handling guest page fault VM-Exits.  In
that case, userspace will want to know RWX information in order to
correctly/precisely resolve the fault.

Note, private memory *must* be backed by guest_memfd, i.e. shared mappings
always come from the host userspace page tables, and private mappings
always come from a guest_memfd instance.

Co-developed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-21-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  |   8 ++-
 arch/x86/kvm/mmu/mmu.c          | 101 ++++++++++++++++++++++++++++++--
 arch/x86/kvm/mmu/mmu_internal.h |   1 +
 include/linux/kvm_host.h        |   8 ++-
 include/uapi/linux/kvm.h        |   1 +
 5 files changed, 110 insertions(+), 9 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1e61faf02b2ac..726c87c35d57c 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6952,6 +6952,7 @@ spec refer, https://github.com/riscv/riscv-sbi-doc.
 
 		/* KVM_EXIT_MEMORY_FAULT */
 		struct {
+  #define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
 			__u64 flags;
 			__u64 gpa;
 			__u64 size;
@@ -6960,8 +6961,11 @@ spec refer, https://github.com/riscv/riscv-sbi-doc.
 KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that
 could not be resolved by KVM.  The 'gpa' and 'size' (in bytes) describe the
 guest physical address range [gpa, gpa + size) of the fault.  The 'flags' field
-describes properties of the faulting access that are likely pertinent.
-Currently, no flags are defined.
+describes properties of the faulting access that are likely pertinent:
+
+ - KVM_MEMORY_EXIT_FLAG_PRIVATE - When set, indicates the memory fault occurred
+   on a private memory access.  When clear, indicates the fault occurred on a
+   shared access.
 
 Note!  KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it
 accompanies a return code of '-1', not '0'!  errno will always be set to EFAULT
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f5c6b0643645c..754a5aaebee5e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3147,9 +3147,9 @@ out:
 	return level;
 }
 
-int kvm_mmu_max_mapping_level(struct kvm *kvm,
-			      const struct kvm_memory_slot *slot, gfn_t gfn,
-			      int max_level)
+static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot,
+				       gfn_t gfn, int max_level, bool is_private)
 {
 	struct kvm_lpage_info *linfo;
 	int host_level;
@@ -3161,6 +3161,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 			break;
 	}
 
+	if (is_private)
+		return max_level;
+
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
@@ -3168,6 +3171,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 	return min(host_level, max_level);
 }
 
+int kvm_mmu_max_mapping_level(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn,
+			      int max_level)
+{
+	bool is_private = kvm_slot_can_be_private(slot) &&
+			  kvm_mem_is_private(kvm, gfn);
+
+	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private);
+}
+
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -3188,8 +3201,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * Enforce the iTLB multihit workaround after capturing the requested
 	 * level, which will be used to do precise, accurate accounting.
 	 */
-	fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
-						     fault->gfn, fault->max_level);
+	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
+						       fault->gfn, fault->max_level,
+						       fault->is_private);
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
@@ -4269,6 +4283,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
 }
 
+static inline u8 kvm_max_level_for_order(int order)
+{
+	BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
+
+	KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K));
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
+		return PG_LEVEL_1G;
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+		return PG_LEVEL_2M;
+
+	return PG_LEVEL_4K;
+}
+
+static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+					      struct kvm_page_fault *fault)
+{
+	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+				      PAGE_SIZE, fault->write, fault->exec,
+				      fault->is_private);
+}
+
+static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
+				   struct kvm_page_fault *fault)
+{
+	int max_order, r;
+
+	if (!kvm_slot_can_be_private(fault->slot)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn,
+			     &max_order);
+	if (r) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return r;
+	}
+
+	fault->max_level = min(kvm_max_level_for_order(max_order),
+			       fault->max_level);
+	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+
+	return RET_PF_CONTINUE;
+}
+
 static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -4301,6 +4364,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			return RET_PF_EMULATE;
 	}
 
+	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	if (fault->is_private)
+		return kvm_faultin_pfn_private(vcpu, fault);
+
 	async = false;
 	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
 					  fault->write, &fault->map_writable,
@@ -7188,6 +7259,26 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range)
+{
+	/*
+	 * Zap SPTEs even if the slot can't be mapped PRIVATE.  KVM x86 only
+	 * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
+	 * can simply ignore such slots.  But if userspace is making memory
+	 * PRIVATE, then KVM must prevent the guest from accessing the memory
+	 * as shared.  And if userspace is making memory SHARED and this point
+	 * is reached, then at least one page within the range was previously
+	 * PRIVATE, i.e. the slot's possible hugepage ranges are changing.
+	 * Zapping SPTEs in this case ensures KVM will reassess whether or not
+	 * a hugepage can be used for affected ranges.
+	 */
+	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+		return false;
+
+	return kvm_unmap_gfn_range(kvm, range);
+}
+
 static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
 				int level)
 {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index decc1f1536694..86c7cb6927867 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -201,6 +201,7 @@ struct kvm_page_fault {
 
 	/* Derived from mmu and global state.  */
 	const bool is_tdp;
+	const bool is_private;
 	const bool nx_huge_page_workaround_enabled;
 
 	/*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a6de526c04267..67dfd4d79529f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2357,14 +2357,18 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
 #define  KVM_DIRTY_RING_MAX_ENTRIES  65536
 
 static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
-						 gpa_t gpa, gpa_t size)
+						 gpa_t gpa, gpa_t size,
+						 bool is_write, bool is_exec,
+						 bool is_private)
 {
 	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
 	vcpu->run->memory_fault.gpa = gpa;
 	vcpu->run->memory_fault.size = size;
 
-	/* Flags are not (yet) defined or communicated to userspace. */
+	/* RWX flags are not (yet) defined or communicated to userspace. */
 	vcpu->run->memory_fault.flags = 0;
+	if (is_private)
+		vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 2802d10aa88c4..8eb10f560c69e 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -535,6 +535,7 @@ struct kvm_run {
 		} notify;
 		/* KVM_EXIT_MEMORY_FAULT */
 		struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
 			__u64 flags;
 			__u64 gpa;
 			__u64 size;
-- 
GitLab


From 2333afa17af0f4b6651214ee17cfd5ae5f47787a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:03 -0700
Subject: [PATCH 0086/4076] KVM: Drop superfluous
 __KVM_VCPU_MULTIPLE_ADDRESS_SPACE macro

Drop __KVM_VCPU_MULTIPLE_ADDRESS_SPACE and instead check the value of
KVM_ADDRESS_SPACE_NUM.

No functional change intended.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-22-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 1 -
 include/linux/kvm_host.h        | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index fa0d422024058..061eec2312993 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2136,7 +2136,6 @@ enum {
 #define HF_SMM_MASK		(1 << 1)
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 2)
 
-# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
 # define KVM_ADDRESS_SPACE_NUM 2
 # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 67dfd4d79529f..db423ea9e3a44 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -690,7 +690,7 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
 #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
-#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#if KVM_ADDRESS_SPACE_NUM == 1
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 {
 	return 0;
-- 
GitLab


From eed52e434bc33603ddb0af62b6c4ef818948489d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:04 -0700
Subject: [PATCH 0087/4076] KVM: Allow arch code to track number of memslot
 address spaces per VM

Let x86 track the number of address spaces on a per-VM basis so that KVM
can disallow SMM memslots for confidential VMs.  Confidentials VMs are
fundamentally incompatible with emulating SMM, which as the name suggests
requires being able to read and write guest memory and register state.

Disallowing SMM will simplify support for guest private memory, as KVM
will not need to worry about tracking memory attributes for multiple
address spaces (SMM is the only "non-default" address space across all
architectures).

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-23-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/book3s_hv.c    |  2 +-
 arch/x86/include/asm/kvm_host.h |  8 +++++++-
 arch/x86/kvm/debugfs.c          |  2 +-
 arch/x86/kvm/mmu/mmu.c          |  6 +++---
 arch/x86/kvm/x86.c              |  2 +-
 include/linux/kvm_host.h        | 17 +++++++++++------
 virt/kvm/dirty_ring.c           |  2 +-
 virt/kvm/kvm_main.c             | 26 ++++++++++++++------------
 8 files changed, 39 insertions(+), 26 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 130bafdb14308..9b0eaa17275a3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -6084,7 +6084,7 @@ static int kvmhv_svm_off(struct kvm *kvm)
 	}
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct kvm_memory_slot *memslot;
 		struct kvm_memslots *slots = __kvm_memslots(kvm, i);
 		int bkt;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 061eec2312993..75ab0da06e644 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2136,9 +2136,15 @@ enum {
 #define HF_SMM_MASK		(1 << 1)
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 2)
 
-# define KVM_ADDRESS_SPACE_NUM 2
+# define KVM_MAX_NR_ADDRESS_SPACES	2
 # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
+
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+	return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
 #else
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
 #endif
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index ee8c4c3496edd..42026b3f3ff34 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -111,7 +111,7 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v)
 	mutex_lock(&kvm->slots_lock);
 	write_lock(&kvm->mmu_lock);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		int bkt;
 
 		slots = __kvm_memslots(kvm, i);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 754a5aaebee5e..4de7670d59760 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3763,7 +3763,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
 	    kvm_page_track_write_tracking_enabled(kvm))
 		goto out_success;
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		slots = __kvm_memslots(kvm, i);
 		kvm_for_each_memslot(slot, bkt, slots) {
 			/*
@@ -6309,7 +6309,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e
 	if (!kvm_memslots_have_rmaps(kvm))
 		return flush;
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		slots = __kvm_memslots(kvm, i);
 
 		kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) {
@@ -6806,7 +6806,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 	 * modifier prior to checking for a wrap of the MMIO generation so
 	 * that a wrap in any address space is detected.
 	 */
-	gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1);
+	gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1);
 
 	/*
 	 * The very rare case: if the MMIO generation number has wrapped,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e1aad0c81f6f2..f521c97f5c64c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12577,7 +12577,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 		hva = slot->userspace_addr;
 	}
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct kvm_userspace_memory_region2 m;
 
 		m.slot = id | (i << 16);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index db423ea9e3a44..3ebc6912c54a1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -80,8 +80,8 @@
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
 
-#ifndef KVM_ADDRESS_SPACE_NUM
-#define KVM_ADDRESS_SPACE_NUM	1
+#ifndef KVM_MAX_NR_ADDRESS_SPACES
+#define KVM_MAX_NR_ADDRESS_SPACES	1
 #endif
 
 /*
@@ -690,7 +690,12 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
 #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
-#if KVM_ADDRESS_SPACE_NUM == 1
+#if KVM_MAX_NR_ADDRESS_SPACES == 1
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+	return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 {
 	return 0;
@@ -745,9 +750,9 @@ struct kvm {
 	struct mm_struct *mm; /* userspace tied to this vm */
 	unsigned long nr_memslot_pages;
 	/* The two memslot sets - active and inactive (per address space) */
-	struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2];
+	struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2];
 	/* The current active memslot set for each address space */
-	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
+	struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES];
 	struct xarray vcpu_array;
 	/*
 	 * Protected by slots_lock, but can be read outside if an
@@ -1017,7 +1022,7 @@ void kvm_put_kvm_no_destroy(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
+	as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES);
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
 			lockdep_is_held(&kvm->slots_lock) ||
 			!refcount_read(&kvm->users_count));
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index c1cd7dfe4a908..86d267db87bb1 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -58,7 +58,7 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
 	as_id = slot >> 16;
 	id = (u16)slot;
 
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return;
 
 	memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8f46d757a2c5d..8758cb799e183 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -615,7 +615,7 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
 
 	idx = srcu_read_lock(&kvm->srcu);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct interval_tree_node *node;
 
 		slots = __kvm_memslots(kvm, i);
@@ -1241,7 +1241,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 		goto out_err_no_irq_srcu;
 
 	refcount_set(&kvm->users_count, 1);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		for (j = 0; j < 2; j++) {
 			slots = &kvm->__memslots[i][j];
 
@@ -1391,7 +1391,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		kvm_free_memslots(kvm, &kvm->__memslots[i][0]);
 		kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
 	}
@@ -1682,7 +1682,7 @@ static void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
 	 * space 0 will use generations 0, 2, 4, ... while address space 1 will
 	 * use generations 1, 3, 5, ...
 	 */
-	gen += KVM_ADDRESS_SPACE_NUM;
+	gen += kvm_arch_nr_memslot_as_ids(kvm);
 
 	kvm_arch_memslots_updated(kvm, gen);
 
@@ -2052,7 +2052,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	    (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
 	     mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
 		return -EINVAL;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		return -EINVAL;
@@ -2188,7 +2188,7 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -2250,7 +2250,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -2362,7 +2362,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	if (log->first_page & 63)
@@ -2493,7 +2493,7 @@ static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
 	gfn_range.arg = range->arg;
 	gfn_range.may_block = range->may_block;
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		slots = __kvm_memslots(kvm, i);
 
 		kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) {
@@ -4848,9 +4848,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
 #endif
-#if KVM_ADDRESS_SPACE_NUM > 1
+#if KVM_MAX_NR_ADDRESS_SPACES > 1
 	case KVM_CAP_MULTI_ADDRESS_SPACE:
-		return KVM_ADDRESS_SPACE_NUM;
+		if (kvm)
+			return kvm_arch_nr_memslot_as_ids(kvm);
+		return KVM_MAX_NR_ADDRESS_SPACES;
 #endif
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
@@ -4958,7 +4960,7 @@ bool kvm_are_all_memslots_empty(struct kvm *kvm)
 
 	lockdep_assert_held(&kvm->slots_lock);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
 			return false;
 	}
-- 
GitLab


From 89ea60c2c7b5838bf192c50062d5720cd6ab8662 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:05 -0700
Subject: [PATCH 0088/4076] KVM: x86: Add support for "protected VMs" that can
 utilize private memory

Add a new x86 VM type, KVM_X86_SW_PROTECTED_VM, to serve as a development
and testing vehicle for Confidential (CoCo) VMs, and potentially to even
become a "real" product in the distant future, e.g. a la pKVM.

The private memory support in KVM x86 is aimed at AMD's SEV-SNP and
Intel's TDX, but those technologies are extremely complex (understatement),
difficult to debug, don't support running as nested guests, and require
hardware that's isn't universally accessible.  I.e. relying SEV-SNP or TDX
for maintaining guest private memory isn't a realistic option.

At the very least, KVM_X86_SW_PROTECTED_VM will enable a variety of
selftests for guest_memfd and private memory support without requiring
unique hardware.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20231027182217.3615211-24-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  | 32 ++++++++++++++++++++++++++++++++
 arch/x86/include/asm/kvm_host.h | 15 +++++++++------
 arch/x86/include/uapi/asm/kvm.h |  3 +++
 arch/x86/kvm/Kconfig            | 12 ++++++++++++
 arch/x86/kvm/mmu/mmu_internal.h |  1 +
 arch/x86/kvm/x86.c              | 16 +++++++++++++++-
 include/uapi/linux/kvm.h        |  1 +
 virt/kvm/Kconfig                |  5 +++++
 8 files changed, 78 insertions(+), 7 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 726c87c35d57c..926241e23aebb 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -147,10 +147,29 @@ described as 'basic' will be available.
 The new VM has no virtual cpus and no memory.
 You probably want to use 0 as machine type.
 
+X86:
+^^^^
+
+Supported X86 VM types can be queried via KVM_CAP_VM_TYPES.
+
+S390:
+^^^^^
+
 In order to create user controlled virtual machines on S390, check
 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
 privileged user (CAP_SYS_ADMIN).
 
+MIPS:
+^^^^^
+
+To use hardware assisted virtualization on MIPS (VZ ASE) rather than
+the default trap & emulate implementation (which changes the virtual
+memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
+flag KVM_VM_MIPS_VZ.
+
+ARM64:
+^^^^^^
+
 On arm64, the physical address size for a VM (IPA Size limit) is limited
 to 40bits by default. The limit can be configured if the host supports the
 extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
@@ -8765,6 +8784,19 @@ block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a
 64-bit bitmap (each bit describing a block size). The default value is
 0, to disable the eager page splitting.
 
+8.41 KVM_CAP_VM_TYPES
+---------------------
+
+:Capability: KVM_CAP_MEMORY_ATTRIBUTES
+:Architectures: x86
+:Type: system ioctl
+
+This capability returns a bitmap of support VM types.  The 1-setting of bit @n
+means the VM type with value @n is supported.  Possible values of @n are::
+
+  #define KVM_X86_DEFAULT_VM	0
+  #define KVM_X86_SW_PROTECTED_VM	1
+
 9. Known KVM API problems
 =========================
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 75ab0da06e644..a565a2e70f30f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1255,6 +1255,7 @@ enum kvm_apicv_inhibit {
 };
 
 struct kvm_arch {
+	unsigned long vm_type;
 	unsigned long n_used_mmu_pages;
 	unsigned long n_requested_mmu_pages;
 	unsigned long n_max_mmu_pages;
@@ -2089,6 +2090,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
 void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
 		       int tdp_max_root_level, int tdp_huge_page_level);
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM)
+#else
+#define kvm_arch_has_private_mem(kvm) false
+#endif
+
 static inline u16 kvm_read_ldt(void)
 {
 	u16 ldt;
@@ -2137,14 +2144,10 @@ enum {
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 2)
 
 # define KVM_MAX_NR_ADDRESS_SPACES	2
+/* SMM is currently unsupported for guests with private memory. */
+# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2)
 # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
-
-static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
-{
-	return KVM_MAX_NR_ADDRESS_SPACES;
-}
-
 #else
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
 #endif
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 1a6a1f9879496..a448d0964fc06 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -562,4 +562,7 @@ struct kvm_pmu_event_filter {
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
 #define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
 
+#define KVM_X86_DEFAULT_VM	0
+#define KVM_X86_SW_PROTECTED_VM	1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index e61383674c756..c1716e83d1761 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -77,6 +77,18 @@ config KVM_WERROR
 
 	  If in doubt, say "N".
 
+config KVM_SW_PROTECTED_VM
+	bool "Enable support for KVM software-protected VMs"
+	depends on EXPERT
+	depends on X86_64
+	select KVM_GENERIC_PRIVATE_MEM
+	help
+	  Enable support for KVM software-protected VMs.  Currently "protected"
+	  means the VM can be backed with memory provided by
+	  KVM_CREATE_GUEST_MEMFD.
+
+	  If unsure, say "N".
+
 config KVM_INTEL
 	tristate "KVM for Intel (and compatible) processors support"
 	depends on KVM && IA32_FEAT_CTL
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 86c7cb6927867..b66a7d47e0e4e 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -297,6 +297,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		.max_level = KVM_MAX_HUGEPAGE_LEVEL,
 		.req_level = PG_LEVEL_4K,
 		.goal_level = PG_LEVEL_4K,
+		.is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT),
 	};
 	int r;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f521c97f5c64c..6d0772b470413 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4548,6 +4548,13 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static bool kvm_is_vm_type_supported(unsigned long type)
+{
+	return type == KVM_X86_DEFAULT_VM ||
+	       (type == KVM_X86_SW_PROTECTED_VM &&
+		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled);
+}
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r = 0;
@@ -4739,6 +4746,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_X86_NOTIFY_VMEXIT:
 		r = kvm_caps.has_notify_vmexit;
 		break;
+	case KVM_CAP_VM_TYPES:
+		r = BIT(KVM_X86_DEFAULT_VM);
+		if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM))
+			r |= BIT(KVM_X86_SW_PROTECTED_VM);
+		break;
 	default:
 		break;
 	}
@@ -12436,9 +12448,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	int ret;
 	unsigned long flags;
 
-	if (type)
+	if (!kvm_is_vm_type_supported(type))
 		return -EINVAL;
 
+	kvm->arch.vm_type = type;
+
 	ret = kvm_page_track_init(kvm);
 	if (ret)
 		goto out;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 8eb10f560c69e..e9cb2df67a1db 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1227,6 +1227,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_MEMORY_FAULT_INFO 232
 #define KVM_CAP_MEMORY_ATTRIBUTES 233
 #define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 08afef022db9f..2c964586aa14e 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -104,3 +104,8 @@ config KVM_GENERIC_MEMORY_ATTRIBUTES
 config KVM_PRIVATE_MEM
        select XARRAY_MULTI
        bool
+
+config KVM_GENERIC_PRIVATE_MEM
+       select KVM_GENERIC_MEMORY_ATTRIBUTES
+       select KVM_PRIVATE_MEM
+       bool
-- 
GitLab


From 335869c3f2b881bda6eeeb2df342841a1db3310b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:06 -0700
Subject: [PATCH 0089/4076] KVM: selftests: Drop unused
 kvm_userspace_memory_region_find() helper

Drop kvm_userspace_memory_region_find(), it's unused and a terrible API
(probably why it's unused).  If anything outside of kvm_util.c needs to
get at the memslot, userspace_mem_region_find() can be exposed to give
others full access to all memory region/slot information.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-25-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/kvm_util_base.h     |  4 ---
 tools/testing/selftests/kvm/lib/kvm_util.c    | 29 -------------------
 2 files changed, 33 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index a18db6a7b3cf4..967eaaeacd756 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -776,10 +776,6 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
 	return n;
 }
 
-struct kvm_userspace_memory_region *
-kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
-				 uint64_t end);
-
 #define sync_global_to_guest(vm, g) ({				\
 	typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g));	\
 	memcpy(_p, &(g), sizeof(g));				\
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 7a8af1821f5da..f09295d56c236 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -590,35 +590,6 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 	return NULL;
 }
 
-/*
- * KVM Userspace Memory Region Find
- *
- * Input Args:
- *   vm - Virtual Machine
- *   start - Starting VM physical address
- *   end - Ending VM physical address, inclusive.
- *
- * Output Args: None
- *
- * Return:
- *   Pointer to overlapping region, NULL if no such region.
- *
- * Public interface to userspace_mem_region_find. Allows tests to look up
- * the memslot datastructure for a given range of guest physical memory.
- */
-struct kvm_userspace_memory_region *
-kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
-				 uint64_t end)
-{
-	struct userspace_mem_region *region;
-
-	region = userspace_mem_region_find(vm, start, end);
-	if (!region)
-		return NULL;
-
-	return &region->region;
-}
-
 __weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
 {
 
-- 
GitLab


From 8d99e347c097ab3f9fb93d0f88dddf20051d7c88 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:07 -0700
Subject: [PATCH 0090/4076] KVM: selftests: Convert lib's mem regions to
 KVM_SET_USER_MEMORY_REGION2

Use KVM_SET_USER_MEMORY_REGION2 throughout KVM's selftests library so that
support for guest private memory can be added without needing an entirely
separate set of helpers.

Note, this obviously makes selftests backwards-incompatible with older KVM
versions from this point forward.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-26-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/kvm_util_base.h     |  2 +-
 tools/testing/selftests/kvm/lib/kvm_util.c    | 19 ++++++++++---------
 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 967eaaeacd756..9f144841c2ee8 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -44,7 +44,7 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
 typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 
 struct userspace_mem_region {
-	struct kvm_userspace_memory_region region;
+	struct kvm_userspace_memory_region2 region;
 	struct sparsebit *unused_phy_pages;
 	int fd;
 	off_t offset;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index f09295d56c236..3676b37bea38d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -453,8 +453,9 @@ void kvm_vm_restart(struct kvm_vm *vmp)
 		vm_create_irqchip(vmp);
 
 	hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) {
-		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
-		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION2, &region->region);
+
+		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 			    "  rc: %i errno: %i\n"
 			    "  slot: %u flags: 0x%x\n"
 			    "  guest_phys_addr: 0x%llx size: 0x%llx",
@@ -657,7 +658,7 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 	}
 
 	region->region.memory_size = 0;
-	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 
 	sparsebit_free(&region->unused_phy_pages);
 	ret = munmap(region->mmap_start, region->mmap_size);
@@ -1014,8 +1015,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	region->region.guest_phys_addr = guest_paddr;
 	region->region.memory_size = npages * vm->page_size;
 	region->region.userspace_addr = (uintptr_t) region->host_mem;
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
-	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
+	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 		"  rc: %i errno: %i\n"
 		"  slot: %u flags: 0x%x\n"
 		"  guest_phys_addr: 0x%lx size: 0x%lx",
@@ -1097,9 +1098,9 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 
 	region->region.flags = flags;
 
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 
-	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 		"  rc: %i errno: %i slot: %u flags: 0x%x",
 		ret, errno, slot, flags);
 }
@@ -1127,9 +1128,9 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
 
 	region->region.guest_phys_addr = new_gpa;
 
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 
-	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n"
+	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed\n"
 		    "ret: %i errno: %i slot: %u new_gpa: 0x%lx",
 		    ret, errno, slot, new_gpa);
 }
-- 
GitLab


From bb2968ad6c33c0902dce48ea57d58c5bb4f3c617 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:08 -0700
Subject: [PATCH 0091/4076] KVM: selftests: Add support for creating private
 memslots

Add support for creating "private" memslots via KVM_CREATE_GUEST_MEMFD and
KVM_SET_USER_MEMORY_REGION2.  Make vm_userspace_mem_region_add() a wrapper
to its effective replacement, vm_mem_add(), so that private memslots are
fully opt-in, i.e. don't require update all tests that add memory regions.

Pivot on the KVM_MEM_PRIVATE flag instead of the validity of the "gmem"
file descriptor so that simple tests can let vm_mem_add() do the heavy
lifting of creating the guest memfd, but also allow the caller to pass in
an explicit fd+offset so that fancier tests can do things like back
multiple memslots with a single file.  If the caller passes in a fd, dup()
the fd so that (a) __vm_mem_region_delete() can close the fd associated
with the memory region without needing yet another flag, and (b) so that
the caller can safely close its copy of the fd without having to first
destroy memslots.

Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-27-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/kvm_util_base.h     | 23 ++++++
 .../testing/selftests/kvm/include/test_util.h |  5 ++
 tools/testing/selftests/kvm/lib/kvm_util.c    | 76 +++++++++++--------
 3 files changed, 73 insertions(+), 31 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 9f144841c2ee8..9f861182c02a8 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -431,6 +431,26 @@ static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name)
 
 void vm_create_irqchip(struct kvm_vm *vm);
 
+static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size,
+					uint64_t flags)
+{
+	struct kvm_create_guest_memfd guest_memfd = {
+		.size = size,
+		.flags = flags,
+	};
+
+	return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd);
+}
+
+static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size,
+					uint64_t flags)
+{
+	int fd = __vm_create_guest_memfd(vm, size, flags);
+
+	TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd));
+	return fd;
+}
+
 void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 			       uint64_t gpa, uint64_t size, void *hva);
 int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
@@ -439,6 +459,9 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	enum vm_mem_backing_src_type src_type,
 	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
 	uint32_t flags);
+void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
+		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+		uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset);
 
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
 void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 7e614adc6cf47..7257f2243ab9f 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -142,6 +142,11 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
 	return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
 }
 
+static inline bool backing_src_can_be_huge(enum vm_mem_backing_src_type t)
+{
+	return t != VM_MEM_SRC_ANONYMOUS && t != VM_MEM_SRC_SHMEM;
+}
+
 /* Aligns x up to the next multiple of size. Size must be a power of 2. */
 static inline uint64_t align_up(uint64_t x, uint64_t size)
 {
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 3676b37bea38d..b63500fca6272 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -669,6 +669,8 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 		TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
 		close(region->fd);
 	}
+	if (region->region.guest_memfd >= 0)
+		close(region->region.guest_memfd);
 
 	free(region);
 }
@@ -870,36 +872,15 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 		    errno, strerror(errno));
 }
 
-/*
- * VM Userspace Memory Region Add
- *
- * Input Args:
- *   vm - Virtual Machine
- *   src_type - Storage source for this region.
- *              NULL to use anonymous memory.
- *   guest_paddr - Starting guest physical address
- *   slot - KVM region slot
- *   npages - Number of physical pages
- *   flags - KVM memory region flags (e.g. KVM_MEM_LOG_DIRTY_PAGES)
- *
- * Output Args: None
- *
- * Return: None
- *
- * Allocates a memory area of the number of pages specified by npages
- * and maps it to the VM specified by vm, at a starting physical address
- * given by guest_paddr.  The region is created with a KVM region slot
- * given by slot, which must be unique and < KVM_MEM_SLOTS_NUM.  The
- * region is created with the flags given by flags.
- */
-void vm_userspace_mem_region_add(struct kvm_vm *vm,
-	enum vm_mem_backing_src_type src_type,
-	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-	uint32_t flags)
+/* FIXME: This thing needs to be ripped apart and rewritten. */
+void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
+		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+		uint32_t flags, int guest_memfd, uint64_t guest_memfd_offset)
 {
 	int ret;
 	struct userspace_mem_region *region;
 	size_t backing_src_pagesz = get_backing_src_pagesz(src_type);
+	size_t mem_size = npages * vm->page_size;
 	size_t alignment;
 
 	TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
@@ -952,7 +933,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	/* Allocate and initialize new mem region structure. */
 	region = calloc(1, sizeof(*region));
 	TEST_ASSERT(region != NULL, "Insufficient Memory");
-	region->mmap_size = npages * vm->page_size;
+	region->mmap_size = mem_size;
 
 #ifdef __s390x__
 	/* On s390x, the host address must be aligned to 1M (due to PGSTEs) */
@@ -999,14 +980,38 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	/* As needed perform madvise */
 	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
 	     src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) {
-		ret = madvise(region->host_mem, npages * vm->page_size,
+		ret = madvise(region->host_mem, mem_size,
 			      src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
 		TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s",
-			    region->host_mem, npages * vm->page_size,
+			    region->host_mem, mem_size,
 			    vm_mem_backing_src_alias(src_type)->name);
 	}
 
 	region->backing_src_type = src_type;
+
+	if (flags & KVM_MEM_GUEST_MEMFD) {
+		if (guest_memfd < 0) {
+			uint32_t guest_memfd_flags = 0;
+			TEST_ASSERT(!guest_memfd_offset,
+				    "Offset must be zero when creating new guest_memfd");
+			guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags);
+		} else {
+			/*
+			 * Install a unique fd for each memslot so that the fd
+			 * can be closed when the region is deleted without
+			 * needing to track if the fd is owned by the framework
+			 * or by the caller.
+			 */
+			guest_memfd = dup(guest_memfd);
+			TEST_ASSERT(guest_memfd >= 0, __KVM_SYSCALL_ERROR("dup()", guest_memfd));
+		}
+
+		region->region.guest_memfd = guest_memfd;
+		region->region.guest_memfd_offset = guest_memfd_offset;
+	} else {
+		region->region.guest_memfd = -1;
+	}
+
 	region->unused_phy_pages = sparsebit_alloc();
 	sparsebit_set_num(region->unused_phy_pages,
 		guest_paddr >> vm->page_shift, npages);
@@ -1019,9 +1024,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 		"  rc: %i errno: %i\n"
 		"  slot: %u flags: 0x%x\n"
-		"  guest_phys_addr: 0x%lx size: 0x%lx",
+		"  guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d\n",
 		ret, errno, slot, flags,
-		guest_paddr, (uint64_t) region->region.memory_size);
+		guest_paddr, (uint64_t) region->region.memory_size,
+		region->region.guest_memfd);
 
 	/* Add to quick lookup data structures */
 	vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region);
@@ -1042,6 +1048,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	}
 }
 
+void vm_userspace_mem_region_add(struct kvm_vm *vm,
+				 enum vm_mem_backing_src_type src_type,
+				 uint64_t guest_paddr, uint32_t slot,
+				 uint64_t npages, uint32_t flags)
+{
+	vm_mem_add(vm, src_type, guest_paddr, slot, npages, flags, -1, 0);
+}
+
 /*
  * Memslot to region
  *
-- 
GitLab


From f7fa67495d118f734f98b406fd46888616b4a3c3 Mon Sep 17 00:00:00 2001
From: Vishal Annapurve <vannapurve@google.com>
Date: Fri, 27 Oct 2023 11:22:09 -0700
Subject: [PATCH 0092/4076] KVM: selftests: Add helpers to convert guest memory
 b/w private and shared

Add helpers to convert memory between private and shared via KVM's
memory attributes, as well as helpers to free/allocate guest_memfd memory
via fallocate().  Userspace, i.e. tests, is NOT required to do fallocate()
when converting memory, as the attributes are the single source of truth.
Provide allocate() helpers so that tests can mimic a userspace that frees
private memory on conversion, e.g. to prioritize memory usage over
performance.

Signed-off-by: Vishal Annapurve <vannapurve@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-28-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/kvm_util_base.h     | 48 +++++++++++++++++++
 tools/testing/selftests/kvm/lib/kvm_util.c    | 28 +++++++++++
 2 files changed, 76 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 9f861182c02a8..1441fca6c273d 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -333,6 +333,54 @@ static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0)
 	vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap);
 }
 
+static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
+					    uint64_t size, uint64_t attributes)
+{
+	struct kvm_memory_attributes attr = {
+		.attributes = attributes,
+		.address = gpa,
+		.size = size,
+		.flags = 0,
+	};
+
+	/*
+	 * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes.  These flows
+	 * need significant enhancements to support multiple attributes.
+	 */
+	TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE,
+		    "Update me to support multiple attributes!");
+
+	vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr);
+}
+
+
+static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa,
+				      uint64_t size)
+{
+	vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE);
+}
+
+static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa,
+				     uint64_t size)
+{
+	vm_set_memory_attributes(vm, gpa, size, 0);
+}
+
+void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size,
+			    bool punch_hole);
+
+static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa,
+					   uint64_t size)
+{
+	vm_guest_mem_fallocate(vm, gpa, size, true);
+}
+
+static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa,
+					 uint64_t size)
+{
+	vm_guest_mem_fallocate(vm, gpa, size, false);
+}
+
 void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
 const char *vm_guest_mode_string(uint32_t i);
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b63500fca6272..cc6007abc4b1e 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1167,6 +1167,34 @@ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
 	__vm_mem_region_delete(vm, memslot2region(vm, slot), true);
 }
 
+void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
+			    bool punch_hole)
+{
+	const int mode = FALLOC_FL_KEEP_SIZE | (punch_hole ? FALLOC_FL_PUNCH_HOLE : 0);
+	struct userspace_mem_region *region;
+	uint64_t end = base + size;
+	uint64_t gpa, len;
+	off_t fd_offset;
+	int ret;
+
+	for (gpa = base; gpa < end; gpa += len) {
+		uint64_t offset;
+
+		region = userspace_mem_region_find(vm, gpa, gpa);
+		TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD,
+			    "Private memory region not found for GPA 0x%lx", gpa);
+
+		offset = gpa - region->region.guest_phys_addr;
+		fd_offset = region->region.guest_memfd_offset + offset;
+		len = min_t(uint64_t, end - gpa, region->region.memory_size - offset);
+
+		ret = fallocate(region->region.guest_memfd, mode, fd_offset, len);
+		TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx\n",
+			    punch_hole ? "punch hole" : "allocate", gpa, len,
+			    region->region.guest_memfd, mode, fd_offset);
+	}
+}
+
 /* Returns the size of a vCPU's kvm_run structure. */
 static int vcpu_mmap_sz(void)
 {
-- 
GitLab


From 01244fce2fa22176e46609c051f6fe15cf81e188 Mon Sep 17 00:00:00 2001
From: Vishal Annapurve <vannapurve@google.com>
Date: Fri, 27 Oct 2023 11:22:10 -0700
Subject: [PATCH 0093/4076] KVM: selftests: Add helpers to do
 KVM_HC_MAP_GPA_RANGE hypercalls (x86)

Add helpers for x86 guests to invoke the KVM_HC_MAP_GPA_RANGE hypercall,
which KVM will forward to userspace and thus can be used by tests to
coordinate private<=>shared conversions between host userspace code and
guest code.

Signed-off-by: Vishal Annapurve <vannapurve@google.com>
[sean: drop shared/private helpers (let tests specify flags)]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-29-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/x86_64/processor.h      | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 25bc61dac5fbe..a84863503fcb4 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -15,6 +15,7 @@
 #include <asm/msr-index.h>
 #include <asm/prctl.h>
 
+#include <linux/kvm_para.h>
 #include <linux/stringify.h>
 
 #include "../kvm_util.h"
@@ -1194,6 +1195,20 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1);
 void xen_hypercall(uint64_t nr, uint64_t a0, void *a1);
 
+static inline uint64_t __kvm_hypercall_map_gpa_range(uint64_t gpa,
+						     uint64_t size, uint64_t flags)
+{
+	return kvm_hypercall(KVM_HC_MAP_GPA_RANGE, gpa, size >> PAGE_SHIFT, flags, 0);
+}
+
+static inline void kvm_hypercall_map_gpa_range(uint64_t gpa, uint64_t size,
+					       uint64_t flags)
+{
+	uint64_t ret = __kvm_hypercall_map_gpa_range(gpa, size, flags);
+
+	GUEST_ASSERT(!ret);
+}
+
 void __vm_xsave_require_permission(uint64_t xfeature, const char *name);
 
 #define vm_xsave_require_permission(xfeature)	\
-- 
GitLab


From 672eaa351015d8165c41fff644ee7d2b369cea12 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:11 -0700
Subject: [PATCH 0094/4076] KVM: selftests: Introduce VM "shape" to allow tests
 to specify the VM type

Add a "vm_shape" structure to encapsulate the selftests-defined "mode",
along with the KVM-defined "type" for use when creating a new VM.  "mode"
tracks physical and virtual address properties, as well as the preferred
backing memory type, while "type" corresponds to the VM type.

Taking the VM type will allow adding tests for KVM_CREATE_GUEST_MEMFD
without needing an entirely separate set of helpers.  At this time,
guest_memfd is effectively usable only by confidential VM types in the
form of guest private memory, and it's expected that x86 will double down
and require unique VM types for TDX and SNP guests.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-30-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/aarch64/page_fault_test.c   |  2 +-
 tools/testing/selftests/kvm/dirty_log_test.c  |  2 +-
 .../selftests/kvm/include/kvm_util_base.h     | 54 +++++++++++++++----
 .../selftests/kvm/kvm_page_table_test.c       |  2 +-
 tools/testing/selftests/kvm/lib/kvm_util.c    | 43 +++++++--------
 tools/testing/selftests/kvm/lib/memstress.c   |  3 +-
 .../kvm/x86_64/ucna_injection_test.c          |  2 +-
 7 files changed, 73 insertions(+), 35 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index eb4217b7c7687..08a5ca5bed56a 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -705,7 +705,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	print_test_banner(mode, p);
 
-	vm = ____vm_create(mode);
+	vm = ____vm_create(VM_SHAPE(mode));
 	setup_memslots(vm, p);
 	kvm_vm_elf_load(vm, program_invocation_name);
 	setup_ucall(vm);
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 936f3a8d1b83e..6cbecf4997676 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -699,7 +699,7 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	vm = __vm_create(mode, 1, extra_mem_pages);
+	vm = __vm_create(VM_SHAPE(mode), 1, extra_mem_pages);
 
 	log_mode_create_vm_done(vm);
 	*vcpu = vm_vcpu_add(vm, 0, guest_code);
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 1441fca6c273d..157508c071f3c 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -188,6 +188,23 @@ enum vm_guest_mode {
 	NUM_VM_MODES,
 };
 
+struct vm_shape {
+	enum vm_guest_mode mode;
+	unsigned int type;
+};
+
+#define VM_TYPE_DEFAULT			0
+
+#define VM_SHAPE(__mode)			\
+({						\
+	struct vm_shape shape = {		\
+		.mode = (__mode),		\
+		.type = VM_TYPE_DEFAULT		\
+	};					\
+						\
+	shape;					\
+})
+
 #if defined(__aarch64__)
 
 extern enum vm_guest_mode vm_mode_default;
@@ -220,6 +237,8 @@ extern enum vm_guest_mode vm_mode_default;
 
 #endif
 
+#define VM_SHAPE_DEFAULT	VM_SHAPE(VM_MODE_DEFAULT)
+
 #define MIN_PAGE_SIZE		(1U << MIN_PAGE_SHIFT)
 #define PTES_PER_MIN_PAGE	ptes_per_page(MIN_PAGE_SIZE)
 
@@ -784,21 +803,21 @@ vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
  * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to
  * calculate the amount of memory needed for per-vCPU data, e.g. stacks.
  */
-struct kvm_vm *____vm_create(enum vm_guest_mode mode);
-struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+struct kvm_vm *____vm_create(struct vm_shape shape);
+struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 			   uint64_t nr_extra_pages);
 
 static inline struct kvm_vm *vm_create_barebones(void)
 {
-	return ____vm_create(VM_MODE_DEFAULT);
+	return ____vm_create(VM_SHAPE_DEFAULT);
 }
 
 static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus)
 {
-	return __vm_create(VM_MODE_DEFAULT, nr_runnable_vcpus, 0);
+	return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0);
 }
 
-struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus,
 				      uint64_t extra_mem_pages,
 				      void *guest_code, struct kvm_vcpu *vcpus[]);
 
@@ -806,17 +825,27 @@ static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus,
 						  void *guest_code,
 						  struct kvm_vcpu *vcpus[])
 {
-	return __vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, 0,
+	return __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, 0,
 				      guest_code, vcpus);
 }
 
+
+struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape,
+					       struct kvm_vcpu **vcpu,
+					       uint64_t extra_mem_pages,
+					       void *guest_code);
+
 /*
  * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages
  * additional pages of guest memory.  Returns the VM and vCPU (via out param).
  */
-struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
-					 uint64_t extra_mem_pages,
-					 void *guest_code);
+static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
+						       uint64_t extra_mem_pages,
+						       void *guest_code)
+{
+	return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu,
+					       extra_mem_pages, guest_code);
+}
 
 static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
 						     void *guest_code)
@@ -824,6 +853,13 @@ static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
 	return __vm_create_with_one_vcpu(vcpu, 0, guest_code);
 }
 
+static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape,
+							   struct kvm_vcpu **vcpu,
+							   void *guest_code)
+{
+	return __vm_create_shape_with_one_vcpu(shape, vcpu, 0, guest_code);
+}
+
 struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm);
 
 void kvm_pin_this_task_to_pcpu(uint32_t pcpu);
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 69f26d80c8216..e37dc9c21888f 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -254,7 +254,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 
 	/* Create a VM with enough guest pages */
 	guest_num_pages = test_mem_size / guest_page_size;
-	vm = __vm_create_with_vcpus(mode, nr_vcpus, guest_num_pages,
+	vm = __vm_create_with_vcpus(VM_SHAPE(mode), nr_vcpus, guest_num_pages,
 				    guest_code, test_args.vcpus);
 
 	/* Align down GPA of the testing memslot */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index cc6007abc4b1e..bf15635eda11b 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -209,7 +209,7 @@ __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm)
 		(1ULL << (vm->va_bits - 1)) >> vm->page_shift);
 }
 
-struct kvm_vm *____vm_create(enum vm_guest_mode mode)
+struct kvm_vm *____vm_create(struct vm_shape shape)
 {
 	struct kvm_vm *vm;
 
@@ -221,13 +221,13 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 	vm->regions.hva_tree = RB_ROOT;
 	hash_init(vm->regions.slot_hash);
 
-	vm->mode = mode;
-	vm->type = 0;
+	vm->mode = shape.mode;
+	vm->type = shape.type;
 
-	vm->pa_bits = vm_guest_mode_params[mode].pa_bits;
-	vm->va_bits = vm_guest_mode_params[mode].va_bits;
-	vm->page_size = vm_guest_mode_params[mode].page_size;
-	vm->page_shift = vm_guest_mode_params[mode].page_shift;
+	vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits;
+	vm->va_bits = vm_guest_mode_params[vm->mode].va_bits;
+	vm->page_size = vm_guest_mode_params[vm->mode].page_size;
+	vm->page_shift = vm_guest_mode_params[vm->mode].page_shift;
 
 	/* Setup mode specific traits. */
 	switch (vm->mode) {
@@ -265,7 +265,7 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 		/*
 		 * Ignore KVM support for 5-level paging (vm->va_bits == 57),
 		 * it doesn't take effect unless a CR4.LA57 is set, which it
-		 * isn't for this VM_MODE.
+		 * isn't for this mode (48-bit virtual address space).
 		 */
 		TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57,
 			    "Linear address width (%d bits) not supported",
@@ -285,10 +285,11 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 		vm->pgtable_levels = 5;
 		break;
 	default:
-		TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
+		TEST_FAIL("Unknown guest mode: 0x%x", vm->mode);
 	}
 
 #ifdef __aarch64__
+	TEST_ASSERT(!vm->type, "ARM doesn't support test-provided types");
 	if (vm->pa_bits != 40)
 		vm->type = KVM_VM_TYPE_ARM_IPA_SIZE(vm->pa_bits);
 #endif
@@ -347,19 +348,19 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	return vm_adjust_num_guest_pages(mode, nr_pages);
 }
 
-struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 			   uint64_t nr_extra_pages)
 {
-	uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus,
+	uint64_t nr_pages = vm_nr_pages_required(shape.mode, nr_runnable_vcpus,
 						 nr_extra_pages);
 	struct userspace_mem_region *slot0;
 	struct kvm_vm *vm;
 	int i;
 
-	pr_debug("%s: mode='%s' pages='%ld'\n", __func__,
-		 vm_guest_mode_string(mode), nr_pages);
+	pr_debug("%s: mode='%s' type='%d', pages='%ld'\n", __func__,
+		 vm_guest_mode_string(shape.mode), shape.type, nr_pages);
 
-	vm = ____vm_create(mode);
+	vm = ____vm_create(shape);
 
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0);
 	for (i = 0; i < NR_MEM_REGIONS; i++)
@@ -400,7 +401,7 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
  * extra_mem_pages is only used to calculate the maximum page table size,
  * no real memory allocation for non-slot0 memory in this function.
  */
-struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus,
 				      uint64_t extra_mem_pages,
 				      void *guest_code, struct kvm_vcpu *vcpus[])
 {
@@ -409,7 +410,7 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus
 
 	TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array");
 
-	vm = __vm_create(mode, nr_vcpus, extra_mem_pages);
+	vm = __vm_create(shape, nr_vcpus, extra_mem_pages);
 
 	for (i = 0; i < nr_vcpus; ++i)
 		vcpus[i] = vm_vcpu_add(vm, i, guest_code);
@@ -417,15 +418,15 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus
 	return vm;
 }
 
-struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
-					 uint64_t extra_mem_pages,
-					 void *guest_code)
+struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape,
+					       struct kvm_vcpu **vcpu,
+					       uint64_t extra_mem_pages,
+					       void *guest_code)
 {
 	struct kvm_vcpu *vcpus[1];
 	struct kvm_vm *vm;
 
-	vm = __vm_create_with_vcpus(VM_MODE_DEFAULT, 1, extra_mem_pages,
-				    guest_code, vcpus);
+	vm = __vm_create_with_vcpus(shape, 1, extra_mem_pages, guest_code, vcpus);
 
 	*vcpu = vcpus[0];
 	return vm;
diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c
index df457452d1464..d05487e5a371d 100644
--- a/tools/testing/selftests/kvm/lib/memstress.c
+++ b/tools/testing/selftests/kvm/lib/memstress.c
@@ -168,7 +168,8 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus,
 	 * The memory is also added to memslot 0, but that's a benign side
 	 * effect as KVM allows aliasing HVAs in meslots.
 	 */
-	vm = __vm_create_with_vcpus(mode, nr_vcpus, slot0_pages + guest_num_pages,
+	vm = __vm_create_with_vcpus(VM_SHAPE(mode), nr_vcpus,
+				    slot0_pages + guest_num_pages,
 				    memstress_guest_code, vcpus);
 
 	args->vm = vm;
diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
index 85f34ca7e49e5..0ed32ec903d03 100644
--- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
+++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
@@ -271,7 +271,7 @@ int main(int argc, char *argv[])
 
 	kvm_check_cap(KVM_CAP_MCE);
 
-	vm = __vm_create(VM_MODE_DEFAULT, 3, 0);
+	vm = __vm_create(VM_SHAPE_DEFAULT, 3, 0);
 
 	kvm_ioctl(vm->kvm_fd, KVM_X86_GET_MCE_CAP_SUPPORTED,
 		  &supported_mcg_caps);
-- 
GitLab


From 242331dfc4959f44e706c9b09b768f312aa5e117 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:12 -0700
Subject: [PATCH 0095/4076] KVM: selftests: Add GUEST_SYNC[1-6] macros for
 synchronizing more data

Add GUEST_SYNC[1-6]() so that tests can pass the maximum amount of
information supported via ucall(), without needing to resort to shared
memory.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-31-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/ucall_common.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index ce33d306c2cba..0fb472a5a0585 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -52,6 +52,17 @@ int ucall_nr_pages_required(uint64_t page_size);
 #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4)	\
 				ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
 #define GUEST_SYNC(stage)	ucall(UCALL_SYNC, 2, "hello", stage)
+#define GUEST_SYNC1(arg0)	ucall(UCALL_SYNC, 1, arg0)
+#define GUEST_SYNC2(arg0, arg1)	ucall(UCALL_SYNC, 2, arg0, arg1)
+#define GUEST_SYNC3(arg0, arg1, arg2) \
+				ucall(UCALL_SYNC, 3, arg0, arg1, arg2)
+#define GUEST_SYNC4(arg0, arg1, arg2, arg3) \
+				ucall(UCALL_SYNC, 4, arg0, arg1, arg2, arg3)
+#define GUEST_SYNC5(arg0, arg1, arg2, arg3, arg4) \
+				ucall(UCALL_SYNC, 5, arg0, arg1, arg2, arg3, arg4)
+#define GUEST_SYNC6(arg0, arg1, arg2, arg3, arg4, arg5) \
+				ucall(UCALL_SYNC, 6, arg0, arg1, arg2, arg3, arg4, arg5)
+
 #define GUEST_PRINTF(_fmt, _args...) ucall_fmt(UCALL_PRINTF, _fmt, ##_args)
 #define GUEST_DONE()		ucall(UCALL_DONE, 0)
 
-- 
GitLab


From 43f623f350ce1c46c53b6b77f4dbe741af8c44f3 Mon Sep 17 00:00:00 2001
From: Vishal Annapurve <vannapurve@google.com>
Date: Fri, 27 Oct 2023 11:22:13 -0700
Subject: [PATCH 0096/4076] KVM: selftests: Add x86-only selftest for private
 memory conversions

Add a selftest to exercise implicit/explicit conversion functionality
within KVM and verify:

 - Shared memory is visible to host userspace
 - Private memory is not visible to host userspace
 - Host userspace and guest can communicate over shared memory
 - Data in shared backing is preserved across conversions (test's
   host userspace doesn't free the data)
 - Private memory is bound to the lifetime of the VM

Ideally, KVM's selftests infrastructure would be reworked to allow backing
a single region of guest memory with multiple memslots for _all_ backing
types and shapes, i.e. ideally the code for using a single backing fd
across multiple memslots would work for "regular" memory as well.  But
sadly, support for KVM_CREATE_GUEST_MEMFD has languished for far too long,
and overhauling selftests' memslots infrastructure would likely open a can
of worms, i.e. delay things even further.

In addition to the more obvious tests, verify that PUNCH_HOLE actually
frees memory.  Directly verifying that KVM frees memory is impractical, if
it's even possible, so instead indirectly verify memory is freed by
asserting that the guest reads zeroes after a PUNCH_HOLE.  E.g. if KVM
zaps SPTEs but doesn't actually punch a hole in the inode, the subsequent
read will still see the previous value.  And obviously punching a hole
shouldn't cause explosions.

Let the user specify the number of memslots in the private mem conversion
test, i.e. don't require the number of memslots to be '1' or "nr_vcpus".
Creating more memslots than vCPUs is particularly interesting, e.g. it can
result in a single KVM_SET_MEMORY_ATTRIBUTES spanning multiple memslots.
To keep the math reasonable, align each vCPU's chunk to at least 2MiB (the
size is 2MiB+4KiB), and require the total size to be cleanly divisible by
the number of memslots.  The goal is to be able to validate that KVM plays
nice with multiple memslots, being able to create a truly arbitrary number
of memslots doesn't add meaningful value, i.e. isn't worth the cost.

Intentionally don't take a requirement on KVM_CAP_GUEST_MEMFD,
KVM_CAP_MEMORY_FAULT_INFO, KVM_MEMORY_ATTRIBUTE_PRIVATE, etc., as it's a
KVM bug to advertise KVM_X86_SW_PROTECTED_VM without its prerequisites.

Signed-off-by: Vishal Annapurve <vannapurve@google.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-32-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../kvm/x86_64/private_mem_conversions_test.c | 482 ++++++++++++++++++
 2 files changed, 483 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index a5963ab9215b9..ecdea5e7afa8a 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -91,6 +91,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test
 TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
 TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
+TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
 TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test
diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
new file mode 100644
index 0000000000000..4d6a37a5d8965
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
@@ -0,0 +1,482 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022, Google LLC.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/kvm_para.h>
+#include <linux/memfd.h>
+#include <linux/sizes.h>
+
+#include <test_util.h>
+#include <kvm_util.h>
+#include <processor.h>
+
+#define BASE_DATA_SLOT		10
+#define BASE_DATA_GPA		((uint64_t)(1ull << 32))
+#define PER_CPU_DATA_SIZE	((uint64_t)(SZ_2M + PAGE_SIZE))
+
+/* Horrific macro so that the line info is captured accurately :-( */
+#define memcmp_g(gpa, pattern,  size)								\
+do {												\
+	uint8_t *mem = (uint8_t *)gpa;								\
+	size_t i;										\
+												\
+	for (i = 0; i < size; i++)								\
+		__GUEST_ASSERT(mem[i] == pattern,						\
+			       "Guest expected 0x%x at offset %lu (gpa 0x%llx), got 0x%x",	\
+			       pattern, i, gpa + i, mem[i]);					\
+} while (0)
+
+static void memcmp_h(uint8_t *mem, uint64_t gpa, uint8_t pattern, size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		TEST_ASSERT(mem[i] == pattern,
+			    "Host expected 0x%x at gpa 0x%lx, got 0x%x",
+			    pattern, gpa + i, mem[i]);
+}
+
+/*
+ * Run memory conversion tests with explicit conversion:
+ * Execute KVM hypercall to map/unmap gpa range which will cause userspace exit
+ * to back/unback private memory. Subsequent accesses by guest to the gpa range
+ * will not cause exit to userspace.
+ *
+ * Test memory conversion scenarios with following steps:
+ * 1) Access private memory using private access and verify that memory contents
+ *   are not visible to userspace.
+ * 2) Convert memory to shared using explicit conversions and ensure that
+ *   userspace is able to access the shared regions.
+ * 3) Convert memory back to private using explicit conversions and ensure that
+ *   userspace is again not able to access converted private regions.
+ */
+
+#define GUEST_STAGE(o, s) { .offset = o, .size = s }
+
+enum ucall_syncs {
+	SYNC_SHARED,
+	SYNC_PRIVATE,
+};
+
+static void guest_sync_shared(uint64_t gpa, uint64_t size,
+			      uint8_t current_pattern, uint8_t new_pattern)
+{
+	GUEST_SYNC5(SYNC_SHARED, gpa, size, current_pattern, new_pattern);
+}
+
+static void guest_sync_private(uint64_t gpa, uint64_t size, uint8_t pattern)
+{
+	GUEST_SYNC4(SYNC_PRIVATE, gpa, size, pattern);
+}
+
+/* Arbitrary values, KVM doesn't care about the attribute flags. */
+#define MAP_GPA_SET_ATTRIBUTES	BIT(0)
+#define MAP_GPA_SHARED		BIT(1)
+#define MAP_GPA_DO_FALLOCATE	BIT(2)
+
+static void guest_map_mem(uint64_t gpa, uint64_t size, bool map_shared,
+			  bool do_fallocate)
+{
+	uint64_t flags = MAP_GPA_SET_ATTRIBUTES;
+
+	if (map_shared)
+		flags |= MAP_GPA_SHARED;
+	if (do_fallocate)
+		flags |= MAP_GPA_DO_FALLOCATE;
+	kvm_hypercall_map_gpa_range(gpa, size, flags);
+}
+
+static void guest_map_shared(uint64_t gpa, uint64_t size, bool do_fallocate)
+{
+	guest_map_mem(gpa, size, true, do_fallocate);
+}
+
+static void guest_map_private(uint64_t gpa, uint64_t size, bool do_fallocate)
+{
+	guest_map_mem(gpa, size, false, do_fallocate);
+}
+
+struct {
+	uint64_t offset;
+	uint64_t size;
+} static const test_ranges[] = {
+	GUEST_STAGE(0, PAGE_SIZE),
+	GUEST_STAGE(0, SZ_2M),
+	GUEST_STAGE(PAGE_SIZE, PAGE_SIZE),
+	GUEST_STAGE(PAGE_SIZE, SZ_2M),
+	GUEST_STAGE(SZ_2M, PAGE_SIZE),
+};
+
+static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate)
+{
+	const uint8_t def_p = 0xaa;
+	const uint8_t init_p = 0xcc;
+	uint64_t j;
+	int i;
+
+	/* Memory should be shared by default. */
+	memset((void *)base_gpa, def_p, PER_CPU_DATA_SIZE);
+	memcmp_g(base_gpa, def_p, PER_CPU_DATA_SIZE);
+	guest_sync_shared(base_gpa, PER_CPU_DATA_SIZE, def_p, init_p);
+
+	memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE);
+
+	for (i = 0; i < ARRAY_SIZE(test_ranges); i++) {
+		uint64_t gpa = base_gpa + test_ranges[i].offset;
+		uint64_t size = test_ranges[i].size;
+		uint8_t p1 = 0x11;
+		uint8_t p2 = 0x22;
+		uint8_t p3 = 0x33;
+		uint8_t p4 = 0x44;
+
+		/*
+		 * Set the test region to pattern one to differentiate it from
+		 * the data range as a whole (contains the initial pattern).
+		 */
+		memset((void *)gpa, p1, size);
+
+		/*
+		 * Convert to private, set and verify the private data, and
+		 * then verify that the rest of the data (map shared) still
+		 * holds the initial pattern, and that the host always sees the
+		 * shared memory (initial pattern).  Unlike shared memory,
+		 * punching a hole in private memory is destructive, i.e.
+		 * previous values aren't guaranteed to be preserved.
+		 */
+		guest_map_private(gpa, size, do_fallocate);
+
+		if (size > PAGE_SIZE) {
+			memset((void *)gpa, p2, PAGE_SIZE);
+			goto skip;
+		}
+
+		memset((void *)gpa, p2, size);
+		guest_sync_private(gpa, size, p1);
+
+		/*
+		 * Verify that the private memory was set to pattern two, and
+		 * that shared memory still holds the initial pattern.
+		 */
+		memcmp_g(gpa, p2, size);
+		if (gpa > base_gpa)
+			memcmp_g(base_gpa, init_p, gpa - base_gpa);
+		if (gpa + size < base_gpa + PER_CPU_DATA_SIZE)
+			memcmp_g(gpa + size, init_p,
+				 (base_gpa + PER_CPU_DATA_SIZE) - (gpa + size));
+
+		/*
+		 * Convert odd-number page frames back to shared to verify KVM
+		 * also correctly handles holes in private ranges.
+		 */
+		for (j = 0; j < size; j += PAGE_SIZE) {
+			if ((j >> PAGE_SHIFT) & 1) {
+				guest_map_shared(gpa + j, PAGE_SIZE, do_fallocate);
+				guest_sync_shared(gpa + j, PAGE_SIZE, p1, p3);
+
+				memcmp_g(gpa + j, p3, PAGE_SIZE);
+			} else {
+				guest_sync_private(gpa + j, PAGE_SIZE, p1);
+			}
+		}
+
+skip:
+		/*
+		 * Convert the entire region back to shared, explicitly write
+		 * pattern three to fill in the even-number frames before
+		 * asking the host to verify (and write pattern four).
+		 */
+		guest_map_shared(gpa, size, do_fallocate);
+		memset((void *)gpa, p3, size);
+		guest_sync_shared(gpa, size, p3, p4);
+		memcmp_g(gpa, p4, size);
+
+		/* Reset the shared memory back to the initial pattern. */
+		memset((void *)gpa, init_p, size);
+
+		/*
+		 * Free (via PUNCH_HOLE) *all* private memory so that the next
+		 * iteration starts from a clean slate, e.g. with respect to
+		 * whether or not there are pages/folios in guest_mem.
+		 */
+		guest_map_shared(base_gpa, PER_CPU_DATA_SIZE, true);
+	}
+}
+
+static void guest_punch_hole(uint64_t gpa, uint64_t size)
+{
+	/* "Mapping" memory shared via fallocate() is done via PUNCH_HOLE. */
+	uint64_t flags = MAP_GPA_SHARED | MAP_GPA_DO_FALLOCATE;
+
+	kvm_hypercall_map_gpa_range(gpa, size, flags);
+}
+
+/*
+ * Test that PUNCH_HOLE actually frees memory by punching holes without doing a
+ * proper conversion.  Freeing (PUNCH_HOLE) should zap SPTEs, and reallocating
+ * (subsequent fault) should zero memory.
+ */
+static void guest_test_punch_hole(uint64_t base_gpa, bool precise)
+{
+	const uint8_t init_p = 0xcc;
+	int i;
+
+	/*
+	 * Convert the entire range to private, this testcase is all about
+	 * punching holes in guest_memfd, i.e. shared mappings aren't needed.
+	 */
+	guest_map_private(base_gpa, PER_CPU_DATA_SIZE, false);
+
+	for (i = 0; i < ARRAY_SIZE(test_ranges); i++) {
+		uint64_t gpa = base_gpa + test_ranges[i].offset;
+		uint64_t size = test_ranges[i].size;
+
+		/*
+		 * Free all memory before each iteration, even for the !precise
+		 * case where the memory will be faulted back in.  Freeing and
+		 * reallocating should obviously work, and freeing all memory
+		 * minimizes the probability of cross-testcase influence.
+		 */
+		guest_punch_hole(base_gpa, PER_CPU_DATA_SIZE);
+
+		/* Fault-in and initialize memory, and verify the pattern. */
+		if (precise) {
+			memset((void *)gpa, init_p, size);
+			memcmp_g(gpa, init_p, size);
+		} else {
+			memset((void *)base_gpa, init_p, PER_CPU_DATA_SIZE);
+			memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE);
+		}
+
+		/*
+		 * Punch a hole at the target range and verify that reads from
+		 * the guest succeed and return zeroes.
+		 */
+		guest_punch_hole(gpa, size);
+		memcmp_g(gpa, 0, size);
+	}
+}
+
+static void guest_code(uint64_t base_gpa)
+{
+	/*
+	 * Run the conversion test twice, with and without doing fallocate() on
+	 * the guest_memfd backing when converting between shared and private.
+	 */
+	guest_test_explicit_conversion(base_gpa, false);
+	guest_test_explicit_conversion(base_gpa, true);
+
+	/*
+	 * Run the PUNCH_HOLE test twice too, once with the entire guest_memfd
+	 * faulted in, once with only the target range faulted in.
+	 */
+	guest_test_punch_hole(base_gpa, false);
+	guest_test_punch_hole(base_gpa, true);
+	GUEST_DONE();
+}
+
+static void handle_exit_hypercall(struct kvm_vcpu *vcpu)
+{
+	struct kvm_run *run = vcpu->run;
+	uint64_t gpa = run->hypercall.args[0];
+	uint64_t size = run->hypercall.args[1] * PAGE_SIZE;
+	bool set_attributes = run->hypercall.args[2] & MAP_GPA_SET_ATTRIBUTES;
+	bool map_shared = run->hypercall.args[2] & MAP_GPA_SHARED;
+	bool do_fallocate = run->hypercall.args[2] & MAP_GPA_DO_FALLOCATE;
+	struct kvm_vm *vm = vcpu->vm;
+
+	TEST_ASSERT(run->hypercall.nr == KVM_HC_MAP_GPA_RANGE,
+		    "Wanted MAP_GPA_RANGE (%u), got '%llu'",
+		    KVM_HC_MAP_GPA_RANGE, run->hypercall.nr);
+
+	if (do_fallocate)
+		vm_guest_mem_fallocate(vm, gpa, size, map_shared);
+
+	if (set_attributes)
+		vm_set_memory_attributes(vm, gpa, size,
+					 map_shared ? 0 : KVM_MEMORY_ATTRIBUTE_PRIVATE);
+	run->hypercall.ret = 0;
+}
+
+static bool run_vcpus;
+
+static void *__test_mem_conversions(void *__vcpu)
+{
+	struct kvm_vcpu *vcpu = __vcpu;
+	struct kvm_run *run = vcpu->run;
+	struct kvm_vm *vm = vcpu->vm;
+	struct ucall uc;
+
+	while (!READ_ONCE(run_vcpus))
+		;
+
+	for ( ;; ) {
+		vcpu_run(vcpu);
+
+		if (run->exit_reason == KVM_EXIT_HYPERCALL) {
+			handle_exit_hypercall(vcpu);
+			continue;
+		}
+
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Wanted KVM_EXIT_IO, got exit reason: %u (%s)",
+			    run->exit_reason, exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+		case UCALL_SYNC: {
+			uint64_t gpa  = uc.args[1];
+			size_t size = uc.args[2];
+			size_t i;
+
+			TEST_ASSERT(uc.args[0] == SYNC_SHARED ||
+				    uc.args[0] == SYNC_PRIVATE,
+				    "Unknown sync command '%ld'", uc.args[0]);
+
+			for (i = 0; i < size; i += vm->page_size) {
+				size_t nr_bytes = min_t(size_t, vm->page_size, size - i);
+				uint8_t *hva = addr_gpa2hva(vm, gpa + i);
+
+				/* In all cases, the host should observe the shared data. */
+				memcmp_h(hva, gpa + i, uc.args[3], nr_bytes);
+
+				/* For shared, write the new pattern to guest memory. */
+				if (uc.args[0] == SYNC_SHARED)
+					memset(hva, uc.args[4], nr_bytes);
+			}
+			break;
+		}
+		case UCALL_DONE:
+			return NULL;
+		default:
+			TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
+		}
+	}
+}
+
+static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t nr_vcpus,
+				 uint32_t nr_memslots)
+{
+	/*
+	 * Allocate enough memory so that each vCPU's chunk of memory can be
+	 * naturally aligned with respect to the size of the backing store.
+	 */
+	const size_t alignment = max_t(size_t, SZ_2M, get_backing_src_pagesz(src_type));
+	const size_t per_cpu_size = align_up(PER_CPU_DATA_SIZE, alignment);
+	const size_t memfd_size = per_cpu_size * nr_vcpus;
+	const size_t slot_size = memfd_size / nr_memslots;
+	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
+	pthread_t threads[KVM_MAX_VCPUS];
+	struct kvm_vm *vm;
+	int memfd, i, r;
+
+	const struct vm_shape shape = {
+		.mode = VM_MODE_DEFAULT,
+		.type = KVM_X86_SW_PROTECTED_VM,
+	};
+
+	TEST_ASSERT(slot_size * nr_memslots == memfd_size,
+		    "The memfd size (0x%lx) needs to be cleanly divisible by the number of memslots (%u)",
+		    memfd_size, nr_memslots);
+	vm = __vm_create_with_vcpus(shape, nr_vcpus, 0, guest_code, vcpus);
+
+	vm_enable_cap(vm, KVM_CAP_EXIT_HYPERCALL, (1 << KVM_HC_MAP_GPA_RANGE));
+
+	memfd = vm_create_guest_memfd(vm, memfd_size, 0);
+
+	for (i = 0; i < nr_memslots; i++)
+		vm_mem_add(vm, src_type, BASE_DATA_GPA + slot_size * i,
+			   BASE_DATA_SLOT + i, slot_size / vm->page_size,
+			   KVM_MEM_GUEST_MEMFD, memfd, slot_size * i);
+
+	for (i = 0; i < nr_vcpus; i++) {
+		uint64_t gpa =  BASE_DATA_GPA + i * per_cpu_size;
+
+		vcpu_args_set(vcpus[i], 1, gpa);
+
+		/*
+		 * Map only what is needed so that an out-of-bounds access
+		 * results #PF => SHUTDOWN instead of data corruption.
+		 */
+		virt_map(vm, gpa, gpa, PER_CPU_DATA_SIZE / vm->page_size);
+
+		pthread_create(&threads[i], NULL, __test_mem_conversions, vcpus[i]);
+	}
+
+	WRITE_ONCE(run_vcpus, true);
+
+	for (i = 0; i < nr_vcpus; i++)
+		pthread_join(threads[i], NULL);
+
+	kvm_vm_free(vm);
+
+	/*
+	 * Allocate and free memory from the guest_memfd after closing the VM
+	 * fd.  The guest_memfd is gifted a reference to its owning VM, i.e.
+	 * should prevent the VM from being fully destroyed until the last
+	 * reference to the guest_memfd is also put.
+	 */
+	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size);
+	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+
+	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size);
+	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+}
+
+static void usage(const char *cmd)
+{
+	puts("");
+	printf("usage: %s [-h] [-m nr_memslots] [-s mem_type] [-n nr_vcpus]\n", cmd);
+	puts("");
+	backing_src_help("-s");
+	puts("");
+	puts(" -n: specify the number of vcpus (default: 1)");
+	puts("");
+	puts(" -m: specify the number of memslots (default: 1)");
+	puts("");
+}
+
+int main(int argc, char *argv[])
+{
+	enum vm_mem_backing_src_type src_type = DEFAULT_VM_MEM_SRC;
+	uint32_t nr_memslots = 1;
+	uint32_t nr_vcpus = 1;
+	int opt;
+
+	TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
+
+	while ((opt = getopt(argc, argv, "hm:s:n:")) != -1) {
+		switch (opt) {
+		case 's':
+			src_type = parse_backing_src_type(optarg);
+			break;
+		case 'n':
+			nr_vcpus = atoi_positive("nr_vcpus", optarg);
+			break;
+		case 'm':
+			nr_memslots = atoi_positive("nr_memslots", optarg);
+			break;
+		case 'h':
+		default:
+			usage(argv[0]);
+			exit(0);
+		}
+	}
+
+	test_mem_conversions(src_type, nr_vcpus, nr_memslots);
+
+	return 0;
+}
-- 
GitLab


From e6f4f345b259cad178bad7e40a9d4b65cf195067 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:22:14 -0700
Subject: [PATCH 0097/4076] KVM: selftests: Add KVM_SET_USER_MEMORY_REGION2
 helper

Add helpers to invoke KVM_SET_USER_MEMORY_REGION2 directly so that tests
can validate of features that are unique to "version 2" of "set user
memory region", e.g. do negative testing on gmem_fd and gmem_offset.

Provide a raw version as well as an assert-success version to reduce
the amount of boilerplate code need for basic usage.

Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-33-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/kvm_util_base.h     |  7 +++++
 tools/testing/selftests/kvm/lib/kvm_util.c    | 29 +++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 157508c071f3c..8ec122f5fcc88 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -522,6 +522,13 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 			       uint64_t gpa, uint64_t size, void *hva);
 int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 				uint64_t gpa, uint64_t size, void *hva);
+void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				uint64_t gpa, uint64_t size, void *hva,
+				uint32_t guest_memfd, uint64_t guest_memfd_offset);
+int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				 uint64_t gpa, uint64_t size, void *hva,
+				 uint32_t guest_memfd, uint64_t guest_memfd_offset);
+
 void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	enum vm_mem_backing_src_type src_type,
 	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index bf15635eda11b..9b29cbf49476d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -873,6 +873,35 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 		    errno, strerror(errno));
 }
 
+int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				 uint64_t gpa, uint64_t size, void *hva,
+				 uint32_t guest_memfd, uint64_t guest_memfd_offset)
+{
+	struct kvm_userspace_memory_region2 region = {
+		.slot = slot,
+		.flags = flags,
+		.guest_phys_addr = gpa,
+		.memory_size = size,
+		.userspace_addr = (uintptr_t)hva,
+		.guest_memfd = guest_memfd,
+		.guest_memfd_offset = guest_memfd_offset,
+	};
+
+	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, &region);
+}
+
+void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				uint64_t gpa, uint64_t size, void *hva,
+				uint32_t guest_memfd, uint64_t guest_memfd_offset)
+{
+	int ret = __vm_set_user_memory_region2(vm, slot, flags, gpa, size, hva,
+					       guest_memfd, guest_memfd_offset);
+
+	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed, errno = %d (%s)",
+		    errno, strerror(errno));
+}
+
+
 /* FIXME: This thing needs to be ripped apart and rewritten. */
 void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-- 
GitLab


From 2feabb855df8f0889146c2e951307ba477d1f37b Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:22:15 -0700
Subject: [PATCH 0098/4076] KVM: selftests: Expand set_memory_region_test to
 validate guest_memfd()

Expand set_memory_region_test to exercise various positive and negative
testcases for private memory.

 - Non-guest_memfd() file descriptor for private memory
 - guest_memfd() from different VM
 - Overlapping bindings
 - Unaligned bindings

Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
[sean: trim the testcases to remove duplicate coverage]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-34-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/kvm_util_base.h     |  12 ++
 .../selftests/kvm/set_memory_region_test.c    | 104 +++++++++++++++++-
 2 files changed, 114 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 8ec122f5fcc88..1b58f943562f8 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -819,6 +819,18 @@ static inline struct kvm_vm *vm_create_barebones(void)
 	return ____vm_create(VM_SHAPE_DEFAULT);
 }
 
+#ifdef __x86_64__
+static inline struct kvm_vm *vm_create_barebones_protected_vm(void)
+{
+	const struct vm_shape shape = {
+		.mode = VM_MODE_DEFAULT,
+		.type = KVM_X86_SW_PROTECTED_VM,
+	};
+
+	return ____vm_create(shape);
+}
+#endif
+
 static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus)
 {
 	return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0);
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index b32960189f5f1..a78394faee7c6 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -385,13 +385,105 @@ static void test_add_max_memory_regions(void)
 	kvm_vm_free(vm);
 }
 
+
+#ifdef __x86_64__
+static void test_invalid_guest_memfd(struct kvm_vm *vm, int memfd,
+				     size_t offset, const char *msg)
+{
+	int r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+					     MEM_REGION_GPA, MEM_REGION_SIZE,
+					     0, memfd, offset);
+	TEST_ASSERT(r == -1 && errno == EINVAL, "%s", msg);
+}
+
+static void test_add_private_memory_region(void)
+{
+	struct kvm_vm *vm, *vm2;
+	int memfd, i;
+
+	pr_info("Testing ADD of KVM_MEM_GUEST_MEMFD memory regions\n");
+
+	vm = vm_create_barebones_protected_vm();
+
+	test_invalid_guest_memfd(vm, vm->kvm_fd, 0, "KVM fd should fail");
+	test_invalid_guest_memfd(vm, vm->fd, 0, "VM's fd should fail");
+
+	memfd = kvm_memfd_alloc(MEM_REGION_SIZE, false);
+	test_invalid_guest_memfd(vm, memfd, 0, "Regular memfd() should fail");
+	close(memfd);
+
+	vm2 = vm_create_barebones_protected_vm();
+	memfd = vm_create_guest_memfd(vm2, MEM_REGION_SIZE, 0);
+	test_invalid_guest_memfd(vm, memfd, 0, "Other VM's guest_memfd() should fail");
+
+	vm_set_user_memory_region2(vm2, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0);
+	close(memfd);
+	kvm_vm_free(vm2);
+
+	memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0);
+	for (i = 1; i < PAGE_SIZE; i++)
+		test_invalid_guest_memfd(vm, memfd, i, "Unaligned offset should fail");
+
+	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0);
+	close(memfd);
+
+	kvm_vm_free(vm);
+}
+
+static void test_add_overlapping_private_memory_regions(void)
+{
+	struct kvm_vm *vm;
+	int memfd;
+	int r;
+
+	pr_info("Testing ADD of overlapping KVM_MEM_GUEST_MEMFD memory regions\n");
+
+	vm = vm_create_barebones_protected_vm();
+
+	memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE * 4, 0);
+
+	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA, MEM_REGION_SIZE * 2, 0, memfd, 0);
+
+	vm_set_user_memory_region2(vm, MEM_REGION_SLOT + 1, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA * 2, MEM_REGION_SIZE * 2,
+				   0, memfd, MEM_REGION_SIZE * 2);
+
+	/*
+	 * Delete the first memslot, and then attempt to recreate it except
+	 * with a "bad" offset that results in overlap in the guest_memfd().
+	 */
+	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+				   MEM_REGION_GPA, 0, NULL, -1, 0);
+
+	/* Overlap the front half of the other slot. */
+	r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+					 MEM_REGION_GPA * 2 - MEM_REGION_SIZE,
+					 MEM_REGION_SIZE * 2,
+					 0, memfd, 0);
+	TEST_ASSERT(r == -1 && errno == EEXIST, "%s",
+		    "Overlapping guest_memfd() bindings should fail with EEXIST");
+
+	/* And now the back half of the other slot. */
+	r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
+					 MEM_REGION_GPA * 2 + MEM_REGION_SIZE,
+					 MEM_REGION_SIZE * 2,
+					 0, memfd, 0);
+	TEST_ASSERT(r == -1 && errno == EEXIST, "%s",
+		    "Overlapping guest_memfd() bindings should fail with EEXIST");
+
+	close(memfd);
+	kvm_vm_free(vm);
+}
+#endif
+
 int main(int argc, char *argv[])
 {
 #ifdef __x86_64__
 	int i, loops;
-#endif
 
-#ifdef __x86_64__
 	/*
 	 * FIXME: the zero-memslot test fails on aarch64 and s390x because
 	 * KVM_RUN fails with ENOEXEC or EFAULT.
@@ -402,6 +494,14 @@ int main(int argc, char *argv[])
 	test_add_max_memory_regions();
 
 #ifdef __x86_64__
+	if (kvm_has_cap(KVM_CAP_GUEST_MEMFD) &&
+	    (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))) {
+		test_add_private_memory_region();
+		test_add_overlapping_private_memory_regions();
+	} else {
+		pr_info("Skipping tests for KVM_MEM_GUEST_MEMFD memory regions\n");
+	}
+
 	if (argc > 1)
 		loops = atoi_positive("Number of iterations", argv[1]);
 	else
-- 
GitLab


From 8a89efd43423cb3005c5e641e846184e292c1465 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:22:16 -0700
Subject: [PATCH 0099/4076] KVM: selftests: Add basic selftest for
 guest_memfd()

Add a selftest to verify the basic functionality of guest_memfd():

+ file descriptor created with the guest_memfd() ioctl does not allow
  read/write/mmap operations
+ file size and block size as returned from fstat are as expected
+ fallocate on the fd checks that offset/length on
  fallocate(FALLOC_FL_PUNCH_HOLE) should be page aligned
+ invalid inputs (misaligned size, invalid flags) are rejected
+ file size and inode are unique (the innocuous-sounding
  anon_inode_getfile() backs all files with a single inode...)

Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-35-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../testing/selftests/kvm/guest_memfd_test.c  | 207 ++++++++++++++++++
 2 files changed, 208 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/guest_memfd_test.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index ecdea5e7afa8a..fd3b30a4ca7bb 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -134,6 +134,7 @@ TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
+TEST_GEN_PROGS_x86_64 += guest_memfd_test
 TEST_GEN_PROGS_x86_64 += guest_print_test
 TEST_GEN_PROGS_x86_64 += hardware_disable_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
new file mode 100644
index 0000000000000..fd389663c49b4
--- /dev/null
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -0,0 +1,207 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright Intel Corporation, 2023
+ *
+ * Author: Chao Peng <chao.p.peng@linux.intel.com>
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdio.h>
+#include <fcntl.h>
+
+#include <linux/bitmap.h>
+#include <linux/falloc.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include "test_util.h"
+#include "kvm_util_base.h"
+
+static void test_file_read_write(int fd)
+{
+	char buf[64];
+
+	TEST_ASSERT(read(fd, buf, sizeof(buf)) < 0,
+		    "read on a guest_mem fd should fail");
+	TEST_ASSERT(write(fd, buf, sizeof(buf)) < 0,
+		    "write on a guest_mem fd should fail");
+	TEST_ASSERT(pread(fd, buf, sizeof(buf), 0) < 0,
+		    "pread on a guest_mem fd should fail");
+	TEST_ASSERT(pwrite(fd, buf, sizeof(buf), 0) < 0,
+		    "pwrite on a guest_mem fd should fail");
+}
+
+static void test_mmap(int fd, size_t page_size)
+{
+	char *mem;
+
+	mem = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	TEST_ASSERT_EQ(mem, MAP_FAILED);
+}
+
+static void test_file_size(int fd, size_t page_size, size_t total_size)
+{
+	struct stat sb;
+	int ret;
+
+	ret = fstat(fd, &sb);
+	TEST_ASSERT(!ret, "fstat should succeed");
+	TEST_ASSERT_EQ(sb.st_size, total_size);
+	TEST_ASSERT_EQ(sb.st_blksize, page_size);
+}
+
+static void test_fallocate(int fd, size_t page_size, size_t total_size)
+{
+	int ret;
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, total_size);
+	TEST_ASSERT(!ret, "fallocate with aligned offset and size should succeed");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			page_size - 1, page_size);
+	TEST_ASSERT(ret, "fallocate with unaligned offset should fail");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, total_size, page_size);
+	TEST_ASSERT(ret, "fallocate beginning at total_size should fail");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, total_size + page_size, page_size);
+	TEST_ASSERT(ret, "fallocate beginning after total_size should fail");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			total_size, page_size);
+	TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) at total_size should succeed");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			total_size + page_size, page_size);
+	TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) after total_size should succeed");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			page_size, page_size - 1);
+	TEST_ASSERT(ret, "fallocate with unaligned size should fail");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+			page_size, page_size);
+	TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) with aligned offset and size should succeed");
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, page_size, page_size);
+	TEST_ASSERT(!ret, "fallocate to restore punched hole should succeed");
+}
+
+static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size)
+{
+	struct {
+		off_t offset;
+		off_t len;
+	} testcases[] = {
+		{0, 1},
+		{0, page_size - 1},
+		{0, page_size + 1},
+
+		{1, 1},
+		{1, page_size - 1},
+		{1, page_size},
+		{1, page_size + 1},
+
+		{page_size, 1},
+		{page_size, page_size - 1},
+		{page_size, page_size + 1},
+	};
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+				testcases[i].offset, testcases[i].len);
+		TEST_ASSERT(ret == -1 && errno == EINVAL,
+			    "PUNCH_HOLE with !PAGE_SIZE offset (%lx) and/or length (%lx) should fail",
+			    testcases[i].offset, testcases[i].len);
+	}
+}
+
+static void test_create_guest_memfd_invalid(struct kvm_vm *vm)
+{
+	size_t page_size = getpagesize();
+	uint64_t flag;
+	size_t size;
+	int fd;
+
+	for (size = 1; size < page_size; size++) {
+		fd = __vm_create_guest_memfd(vm, size, 0);
+		TEST_ASSERT(fd == -1 && errno == EINVAL,
+			    "guest_memfd() with non-page-aligned page size '0x%lx' should fail with EINVAL",
+			    size);
+	}
+
+	for (flag = 1; flag; flag <<= 1) {
+		uint64_t bit;
+
+		fd = __vm_create_guest_memfd(vm, page_size, flag);
+		TEST_ASSERT(fd == -1 && errno == EINVAL,
+			    "guest_memfd() with flag '0x%lx' should fail with EINVAL",
+			    flag);
+
+		for_each_set_bit(bit, &valid_flags, 64) {
+			fd = __vm_create_guest_memfd(vm, page_size, flag | BIT_ULL(bit));
+			TEST_ASSERT(fd == -1 && errno == EINVAL,
+				    "guest_memfd() with flags '0x%llx' should fail with EINVAL",
+				    flag | BIT_ULL(bit));
+		}
+	}
+}
+
+static void test_create_guest_memfd_multiple(struct kvm_vm *vm)
+{
+	int fd1, fd2, ret;
+	struct stat st1, st2;
+
+	fd1 = __vm_create_guest_memfd(vm, 4096, 0);
+	TEST_ASSERT(fd1 != -1, "memfd creation should succeed");
+
+	ret = fstat(fd1, &st1);
+	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
+	TEST_ASSERT(st1.st_size == 4096, "memfd st_size should match requested size");
+
+	fd2 = __vm_create_guest_memfd(vm, 8192, 0);
+	TEST_ASSERT(fd2 != -1, "memfd creation should succeed");
+
+	ret = fstat(fd2, &st2);
+	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
+	TEST_ASSERT(st2.st_size == 8192, "second memfd st_size should match requested size");
+
+	ret = fstat(fd1, &st1);
+	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
+	TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size");
+	TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers");
+}
+
+int main(int argc, char *argv[])
+{
+	size_t page_size;
+	size_t total_size;
+	int fd;
+	struct kvm_vm *vm;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD));
+
+	page_size = getpagesize();
+	total_size = page_size * 4;
+
+	vm = vm_create_barebones();
+
+	test_create_guest_memfd_invalid(vm);
+	test_create_guest_memfd_multiple(vm);
+
+	fd = vm_create_guest_memfd(vm, total_size, 0);
+
+	test_file_read_write(fd);
+	test_mmap(fd, page_size);
+	test_file_size(fd, page_size, total_size);
+	test_fallocate(fd, page_size, total_size);
+	test_invalid_punch_hole(fd, page_size, total_size);
+
+	close(fd);
+}
-- 
GitLab


From e3577788de64139202d89224fe31613c0f02b790 Mon Sep 17 00:00:00 2001
From: Ackerley Tng <ackerleytng@google.com>
Date: Fri, 27 Oct 2023 11:22:17 -0700
Subject: [PATCH 0100/4076] KVM: selftests: Test KVM exit behavior for private
 memory/access

"Testing private access when memslot gets deleted" tests the behavior
of KVM when a private memslot gets deleted while the VM is using the
private memslot. When KVM looks up the deleted (slot = NULL) memslot,
KVM should exit to userspace with KVM_EXIT_MEMORY_FAULT.

In the second test, upon a private access to non-private memslot, KVM
should also exit to userspace with KVM_EXIT_MEMORY_FAULT.

Intentionally don't take a requirement on KVM_CAP_GUEST_MEMFD,
KVM_CAP_MEMORY_FAULT_INFO, KVM_MEMORY_ATTRIBUTE_PRIVATE, etc., as it's a
KVM bug to advertise KVM_X86_SW_PROTECTED_VM without its prerequisites.

Signed-off-by: Ackerley Tng <ackerleytng@google.com>
[sean: call out the similarities with set_memory_region_test]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-36-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../kvm/x86_64/private_mem_kvm_exits_test.c   | 120 ++++++++++++++++++
 2 files changed, 121 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index fd3b30a4ca7bb..69ce8e06b3a34 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -92,6 +92,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
 TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
 TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test
+TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
 TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test
diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c
new file mode 100644
index 0000000000000..13e72fcec8dd2
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023, Google LLC.
+ */
+#include <linux/kvm.h>
+#include <pthread.h>
+#include <stdint.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+/* Arbitrarily selected to avoid overlaps with anything else */
+#define EXITS_TEST_GVA 0xc0000000
+#define EXITS_TEST_GPA EXITS_TEST_GVA
+#define EXITS_TEST_NPAGES 1
+#define EXITS_TEST_SIZE (EXITS_TEST_NPAGES * PAGE_SIZE)
+#define EXITS_TEST_SLOT 10
+
+static uint64_t guest_repeatedly_read(void)
+{
+	volatile uint64_t value;
+
+	while (true)
+		value = *((uint64_t *) EXITS_TEST_GVA);
+
+	return value;
+}
+
+static uint32_t run_vcpu_get_exit_reason(struct kvm_vcpu *vcpu)
+{
+	int r;
+
+	r = _vcpu_run(vcpu);
+	if (r) {
+		TEST_ASSERT(errno == EFAULT, KVM_IOCTL_ERROR(KVM_RUN, r));
+		TEST_ASSERT_EQ(vcpu->run->exit_reason, KVM_EXIT_MEMORY_FAULT);
+	}
+	return vcpu->run->exit_reason;
+}
+
+const struct vm_shape protected_vm_shape = {
+	.mode = VM_MODE_DEFAULT,
+	.type = KVM_X86_SW_PROTECTED_VM,
+};
+
+static void test_private_access_memslot_deleted(void)
+{
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	pthread_t vm_thread;
+	void *thread_return;
+	uint32_t exit_reason;
+
+	vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu,
+					   guest_repeatedly_read);
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    EXITS_TEST_GPA, EXITS_TEST_SLOT,
+				    EXITS_TEST_NPAGES,
+				    KVM_MEM_GUEST_MEMFD);
+
+	virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES);
+
+	/* Request to access page privately */
+	vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE);
+
+	pthread_create(&vm_thread, NULL,
+		       (void *(*)(void *))run_vcpu_get_exit_reason,
+		       (void *)vcpu);
+
+	vm_mem_region_delete(vm, EXITS_TEST_SLOT);
+
+	pthread_join(vm_thread, &thread_return);
+	exit_reason = (uint32_t)(uint64_t)thread_return;
+
+	TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE);
+
+	kvm_vm_free(vm);
+}
+
+static void test_private_access_memslot_not_private(void)
+{
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	uint32_t exit_reason;
+
+	vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu,
+					   guest_repeatedly_read);
+
+	/* Add a non-private memslot (flags = 0) */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    EXITS_TEST_GPA, EXITS_TEST_SLOT,
+				    EXITS_TEST_NPAGES, 0);
+
+	virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES);
+
+	/* Request to access page privately */
+	vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE);
+
+	exit_reason = run_vcpu_get_exit_reason(vcpu);
+
+	TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA);
+	TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE);
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM));
+
+	test_private_access_memslot_deleted();
+	test_private_access_memslot_not_private();
+}
-- 
GitLab


From 5d74316466f4aabdd2ee1e33b45e4933c9bc3ea1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 30 Oct 2023 17:20:49 -0700
Subject: [PATCH 0101/4076] KVM: selftests: Add a memory region subtest to
 validate invalid flags

Add a subtest to set_memory_region_test to verify that KVM rejects invalid
flags and combinations with -EINVAL.  KVM might or might not fail with
EINVAL anyways, but we can at least try.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231031002049.3915752-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/guest_memfd_test.c  |  9 +---
 .../selftests/kvm/set_memory_region_test.c    | 49 +++++++++++++++++++
 2 files changed, 50 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index fd389663c49b4..318ba6ba8bd31 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -136,20 +136,13 @@ static void test_create_guest_memfd_invalid(struct kvm_vm *vm)
 			    size);
 	}
 
-	for (flag = 1; flag; flag <<= 1) {
+	for (flag = 0; flag; flag <<= 1) {
 		uint64_t bit;
 
 		fd = __vm_create_guest_memfd(vm, page_size, flag);
 		TEST_ASSERT(fd == -1 && errno == EINVAL,
 			    "guest_memfd() with flag '0x%lx' should fail with EINVAL",
 			    flag);
-
-		for_each_set_bit(bit, &valid_flags, 64) {
-			fd = __vm_create_guest_memfd(vm, page_size, flag | BIT_ULL(bit));
-			TEST_ASSERT(fd == -1 && errno == EINVAL,
-				    "guest_memfd() with flags '0x%llx' should fail with EINVAL",
-				    flag | BIT_ULL(bit));
-		}
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index a78394faee7c6..1efee1cfcff06 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -326,6 +326,53 @@ static void test_zero_memory_regions(void)
 }
 #endif /* __x86_64__ */
 
+static void test_invalid_memory_region_flags(void)
+{
+	uint32_t supported_flags = KVM_MEM_LOG_DIRTY_PAGES;
+	const uint32_t v2_only_flags = KVM_MEM_GUEST_MEMFD;
+	struct kvm_vm *vm;
+	int r, i;
+
+#ifdef __x86_64__
+	supported_flags |= KVM_MEM_READONLY;
+
+	if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))
+		vm = vm_create_barebones_protected_vm();
+	else
+#endif
+		vm = vm_create_barebones();
+
+	if (kvm_check_cap(KVM_CAP_MEMORY_ATTRIBUTES) & KVM_MEMORY_ATTRIBUTE_PRIVATE)
+		supported_flags |= KVM_MEM_GUEST_MEMFD;
+
+	for (i = 0; i < 32; i++) {
+		if ((supported_flags & BIT(i)) && !(v2_only_flags & BIT(i)))
+			continue;
+
+		r = __vm_set_user_memory_region(vm, MEM_REGION_SLOT, BIT(i),
+						MEM_REGION_GPA, MEM_REGION_SIZE, NULL);
+
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION should have failed on v2 only flag 0x%lx", BIT(i));
+
+		if (supported_flags & BIT(i))
+			continue;
+
+		r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, BIT(i),
+						 MEM_REGION_GPA, MEM_REGION_SIZE, NULL, 0, 0);
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION2 should have failed on unsupported flag 0x%lx", BIT(i));
+	}
+
+	if (supported_flags & KVM_MEM_GUEST_MEMFD) {
+		r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT,
+						 KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD,
+						 MEM_REGION_GPA, MEM_REGION_SIZE, NULL, 0, 0);
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported");
+	}
+}
+
 /*
  * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any
  * tentative to add further slots should fail.
@@ -491,6 +538,8 @@ int main(int argc, char *argv[])
 	test_zero_memory_regions();
 #endif
 
+	test_invalid_memory_region_flags();
+
 	test_add_max_memory_regions();
 
 #ifdef __x86_64__
-- 
GitLab


From 901b277eafbd98ad327525de6c9bf3cc6abd6370 Mon Sep 17 00:00:00 2001
From: Esteban Blanc <eblanc@baylibre.com>
Date: Wed, 8 Nov 2023 11:41:24 +0100
Subject: [PATCH 0102/4076] pinctrl: tps6594: Add driver for TPS6594 pinctrl
 and GPIOs

TI TPS6594 PMIC has 11 GPIOs which can be used
for different functions.

This patch adds a pinctrl and GPIO drivers in
order to use those functions.

Signed-off-by: Esteban Blanc <eblanc@baylibre.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20231108104124.2818275-1-eblanc@baylibre.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig           |  16 ++
 drivers/pinctrl/Makefile          |   1 +
 drivers/pinctrl/pinctrl-tps6594.c | 373 ++++++++++++++++++++++++++++++
 3 files changed, 390 insertions(+)
 create mode 100644 drivers/pinctrl/pinctrl-tps6594.c

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 1de4e1edede01..02133fd9d924e 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -469,6 +469,22 @@ config PINCTRL_TB10X
 	depends on OF && ARC_PLAT_TB10X
 	select GPIOLIB
 
+config PINCTRL_TPS6594
+	tristate "Pinctrl and GPIO driver for TI TPS6594 PMIC"
+	depends on OF && MFD_TPS6594
+	default MFD_TPS6594
+	select PINMUX
+	select GPIOLIB
+	select REGMAP
+	select GPIO_REGMAP
+	select GENERIC_PINCONF
+	help
+	  Say Y to select the pinmuxing and GPIOs driver for the TPS6594
+	  PMICs chip family.
+
+	  This driver can also be built as a module
+	  called tps6594-pinctrl.
+
 config PINCTRL_ZYNQ
 	bool "Pinctrl driver for Xilinx Zynq"
 	depends on ARCH_ZYNQ
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 37575deb7a690..6e8f3416995ca 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_PINCTRL_ST) 	+= pinctrl-st.o
 obj-$(CONFIG_PINCTRL_STMFX) 	+= pinctrl-stmfx.o
 obj-$(CONFIG_PINCTRL_SX150X)	+= pinctrl-sx150x.o
 obj-$(CONFIG_PINCTRL_TB10X)	+= pinctrl-tb10x.o
+obj-$(CONFIG_PINCTRL_TPS6594)	+= pinctrl-tps6594.o
 obj-$(CONFIG_PINCTRL_ZYNQMP)	+= pinctrl-zynqmp.o
 obj-$(CONFIG_PINCTRL_ZYNQ)	+= pinctrl-zynq.o
 
diff --git a/drivers/pinctrl/pinctrl-tps6594.c b/drivers/pinctrl/pinctrl-tps6594.c
new file mode 100644
index 0000000000000..66985e54b74a1
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-tps6594.c
@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Pinmux and GPIO driver for tps6594 PMIC
+ *
+ * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/
+ */
+
+#include <linux/gpio/driver.h>
+#include <linux/gpio/regmap.h>
+#include <linux/module.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/platform_device.h>
+#include <linux/mod_devicetable.h>
+
+#include <linux/mfd/tps6594.h>
+
+#define TPS6594_PINCTRL_PINS_NB 11
+
+#define TPS6594_PINCTRL_GPIO_FUNCTION 0
+#define TPS6594_PINCTRL_SCL_I2C2_CS_SPI_FUNCTION 1
+#define TPS6594_PINCTRL_TRIG_WDOG_FUNCTION 1
+#define TPS6594_PINCTRL_CLK32KOUT_FUNCTION 1
+#define TPS6594_PINCTRL_SCLK_SPMI_FUNCTION 1
+#define TPS6594_PINCTRL_SDATA_SPMI_FUNCTION 1
+#define TPS6594_PINCTRL_NERR_MCU_FUNCTION 1
+#define TPS6594_PINCTRL_PDOG_FUNCTION 1
+#define TPS6594_PINCTRL_SYNCCLKIN_FUNCTION 1
+#define TPS6594_PINCTRL_NRSTOUT_SOC_FUNCTION 2
+#define TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION 2
+#define TPS6594_PINCTRL_SDA_I2C2_SDO_SPI_FUNCTION 2
+#define TPS6594_PINCTRL_NERR_SOC_FUNCTION 2
+#define TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION 3
+#define TPS6594_PINCTRL_NSLEEP1_FUNCTION 4
+#define TPS6594_PINCTRL_NSLEEP2_FUNCTION 5
+#define TPS6594_PINCTRL_WKUP1_FUNCTION 6
+#define TPS6594_PINCTRL_WKUP2_FUNCTION 7
+
+/* Special muxval for recalcitrant pins */
+#define TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION_GPIO8 2
+#define TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION_GPIO8 3
+#define TPS6594_PINCTRL_CLK32KOUT_FUNCTION_GPIO9 3
+
+#define TPS6594_OFFSET_GPIO_SEL 5
+
+#define FUNCTION(fname, v)									\
+{											\
+	.pinfunction = PINCTRL_PINFUNCTION(#fname,					\
+					tps6594_##fname##_func_group_names,		\
+					ARRAY_SIZE(tps6594_##fname##_func_group_names)),\
+	.muxval = v,									\
+}
+
+static const struct pinctrl_pin_desc tps6594_pins[TPS6594_PINCTRL_PINS_NB] = {
+	PINCTRL_PIN(0, "GPIO0"),   PINCTRL_PIN(1, "GPIO1"),
+	PINCTRL_PIN(2, "GPIO2"),   PINCTRL_PIN(3, "GPIO3"),
+	PINCTRL_PIN(4, "GPIO4"),   PINCTRL_PIN(5, "GPIO5"),
+	PINCTRL_PIN(6, "GPIO6"),   PINCTRL_PIN(7, "GPIO7"),
+	PINCTRL_PIN(8, "GPIO8"),   PINCTRL_PIN(9, "GPIO9"),
+	PINCTRL_PIN(10, "GPIO10"),
+};
+
+static const char *const tps6594_gpio_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_nsleep1_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_nsleep2_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_wkup1_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_wkup2_func_group_names[] = {
+	"GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5",
+	"GPIO6", "GPIO7", "GPIO8", "GPIO9", "GPIO10",
+};
+
+static const char *const tps6594_scl_i2c2_cs_spi_func_group_names[] = {
+	"GPIO0",
+	"GPIO1",
+};
+
+static const char *const tps6594_nrstout_soc_func_group_names[] = {
+	"GPIO0",
+	"GPIO10",
+};
+
+static const char *const tps6594_trig_wdog_func_group_names[] = {
+	"GPIO1",
+	"GPIO10",
+};
+
+static const char *const tps6594_sda_i2c2_sdo_spi_func_group_names[] = {
+	"GPIO1",
+};
+
+static const char *const tps6594_clk32kout_func_group_names[] = {
+	"GPIO2",
+	"GPIO3",
+	"GPIO7",
+};
+
+static const char *const tps6594_nerr_soc_func_group_names[] = {
+	"GPIO2",
+};
+
+static const char *const tps6594_sclk_spmi_func_group_names[] = {
+	"GPIO4",
+};
+
+static const char *const tps6594_sdata_spmi_func_group_names[] = {
+	"GPIO5",
+};
+
+static const char *const tps6594_nerr_mcu_func_group_names[] = {
+	"GPIO6",
+};
+
+static const char *const tps6594_syncclkout_func_group_names[] = {
+	"GPIO7",
+	"GPIO9",
+};
+
+static const char *const tps6594_disable_wdog_func_group_names[] = {
+	"GPIO7",
+	"GPIO8",
+};
+
+static const char *const tps6594_pdog_func_group_names[] = {
+	"GPIO8",
+};
+
+static const char *const tps6594_syncclkin_func_group_names[] = {
+	"GPIO9",
+};
+
+struct tps6594_pinctrl_function {
+	struct pinfunction pinfunction;
+	u8 muxval;
+};
+
+static const struct tps6594_pinctrl_function pinctrl_functions[] = {
+	FUNCTION(gpio, TPS6594_PINCTRL_GPIO_FUNCTION),
+	FUNCTION(nsleep1, TPS6594_PINCTRL_NSLEEP1_FUNCTION),
+	FUNCTION(nsleep2, TPS6594_PINCTRL_NSLEEP2_FUNCTION),
+	FUNCTION(wkup1, TPS6594_PINCTRL_WKUP1_FUNCTION),
+	FUNCTION(wkup2, TPS6594_PINCTRL_WKUP2_FUNCTION),
+	FUNCTION(scl_i2c2_cs_spi, TPS6594_PINCTRL_SCL_I2C2_CS_SPI_FUNCTION),
+	FUNCTION(nrstout_soc, TPS6594_PINCTRL_NRSTOUT_SOC_FUNCTION),
+	FUNCTION(trig_wdog, TPS6594_PINCTRL_TRIG_WDOG_FUNCTION),
+	FUNCTION(sda_i2c2_sdo_spi, TPS6594_PINCTRL_SDA_I2C2_SDO_SPI_FUNCTION),
+	FUNCTION(clk32kout, TPS6594_PINCTRL_CLK32KOUT_FUNCTION),
+	FUNCTION(nerr_soc, TPS6594_PINCTRL_NERR_SOC_FUNCTION),
+	FUNCTION(sclk_spmi, TPS6594_PINCTRL_SCLK_SPMI_FUNCTION),
+	FUNCTION(sdata_spmi, TPS6594_PINCTRL_SDATA_SPMI_FUNCTION),
+	FUNCTION(nerr_mcu, TPS6594_PINCTRL_NERR_MCU_FUNCTION),
+	FUNCTION(syncclkout, TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION),
+	FUNCTION(disable_wdog, TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION),
+	FUNCTION(pdog, TPS6594_PINCTRL_PDOG_FUNCTION),
+	FUNCTION(syncclkin, TPS6594_PINCTRL_SYNCCLKIN_FUNCTION),
+};
+
+struct tps6594_pinctrl {
+	struct tps6594 *tps;
+	struct gpio_regmap *gpio_regmap;
+	struct pinctrl_dev *pctl_dev;
+	const struct tps6594_pinctrl_function *funcs;
+	const struct pinctrl_pin_desc *pins;
+};
+
+static int tps6594_gpio_regmap_xlate(struct gpio_regmap *gpio,
+				     unsigned int base, unsigned int offset,
+				     unsigned int *reg, unsigned int *mask)
+{
+	unsigned int line = offset % 8;
+	unsigned int stride = offset / 8;
+
+	switch (base) {
+	case TPS6594_REG_GPIOX_CONF(0):
+		*reg = TPS6594_REG_GPIOX_CONF(offset);
+		*mask = TPS6594_BIT_GPIO_DIR;
+		return 0;
+	case TPS6594_REG_GPIO_IN_1:
+	case TPS6594_REG_GPIO_OUT_1:
+		*reg = base + stride;
+		*mask = BIT(line);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tps6594_pmx_func_cnt(struct pinctrl_dev *pctldev)
+{
+	return ARRAY_SIZE(pinctrl_functions);
+}
+
+static const char *tps6594_pmx_func_name(struct pinctrl_dev *pctldev,
+					 unsigned int selector)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pinctrl->funcs[selector].pinfunction.name;
+}
+
+static int tps6594_pmx_func_groups(struct pinctrl_dev *pctldev,
+				   unsigned int selector,
+				   const char *const **groups,
+				   unsigned int *num_groups)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	*groups = pinctrl->funcs[selector].pinfunction.groups;
+	*num_groups = pinctrl->funcs[selector].pinfunction.ngroups;
+
+	return 0;
+}
+
+static int tps6594_pmx_set(struct tps6594_pinctrl *pinctrl, unsigned int pin,
+			   u8 muxval)
+{
+	u8 mux_sel_val = muxval << TPS6594_OFFSET_GPIO_SEL;
+
+	return regmap_update_bits(pinctrl->tps->regmap,
+				  TPS6594_REG_GPIOX_CONF(pin),
+				  TPS6594_MASK_GPIO_SEL, mux_sel_val);
+}
+
+static int tps6594_pmx_set_mux(struct pinctrl_dev *pctldev,
+			       unsigned int function, unsigned int group)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+	u8 muxval = pinctrl->funcs[function].muxval;
+
+	/* Some pins don't have the same muxval for the same function... */
+	if (group == 8) {
+		if (muxval == TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION)
+			muxval = TPS6594_PINCTRL_DISABLE_WDOG_FUNCTION_GPIO8;
+		else if (muxval == TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION)
+			muxval = TPS6594_PINCTRL_SYNCCLKOUT_FUNCTION_GPIO8;
+	} else if (group == 9) {
+		if (muxval == TPS6594_PINCTRL_CLK32KOUT_FUNCTION)
+			muxval = TPS6594_PINCTRL_CLK32KOUT_FUNCTION_GPIO9;
+	}
+
+	return tps6594_pmx_set(pinctrl, group, muxval);
+}
+
+static int tps6594_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
+					  struct pinctrl_gpio_range *range,
+					  unsigned int offset, bool input)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+	u8 muxval = pinctrl->funcs[TPS6594_PINCTRL_GPIO_FUNCTION].muxval;
+
+	return tps6594_pmx_set(pinctrl, offset, muxval);
+}
+
+static const struct pinmux_ops tps6594_pmx_ops = {
+	.get_functions_count = tps6594_pmx_func_cnt,
+	.get_function_name = tps6594_pmx_func_name,
+	.get_function_groups = tps6594_pmx_func_groups,
+	.set_mux = tps6594_pmx_set_mux,
+	.gpio_set_direction = tps6594_pmx_gpio_set_direction,
+	.strict = true,
+};
+
+static int tps6594_groups_cnt(struct pinctrl_dev *pctldev)
+{
+	return ARRAY_SIZE(tps6594_pins);
+}
+
+static int tps6594_group_pins(struct pinctrl_dev *pctldev,
+			      unsigned int selector, const unsigned int **pins,
+			      unsigned int *num_pins)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	*pins = &pinctrl->pins[selector].number;
+	*num_pins = 1;
+
+	return 0;
+}
+
+static const char *tps6594_group_name(struct pinctrl_dev *pctldev,
+				      unsigned int selector)
+{
+	struct tps6594_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pinctrl->pins[selector].name;
+}
+
+static const struct pinctrl_ops tps6594_pctrl_ops = {
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_group,
+	.dt_free_map = pinconf_generic_dt_free_map,
+	.get_groups_count = tps6594_groups_cnt,
+	.get_group_name = tps6594_group_name,
+	.get_group_pins = tps6594_group_pins,
+};
+
+static int tps6594_pinctrl_probe(struct platform_device *pdev)
+{
+	struct tps6594 *tps = dev_get_drvdata(pdev->dev.parent);
+	struct device *dev = &pdev->dev;
+	struct tps6594_pinctrl *pinctrl;
+	struct pinctrl_desc *pctrl_desc;
+	struct gpio_regmap_config config = {};
+
+	pctrl_desc = devm_kzalloc(dev, sizeof(*pctrl_desc), GFP_KERNEL);
+	if (!pctrl_desc)
+		return -ENOMEM;
+	pctrl_desc->name = dev_name(dev);
+	pctrl_desc->owner = THIS_MODULE;
+	pctrl_desc->pins = tps6594_pins;
+	pctrl_desc->npins = ARRAY_SIZE(tps6594_pins);
+	pctrl_desc->pctlops = &tps6594_pctrl_ops;
+	pctrl_desc->pmxops = &tps6594_pmx_ops;
+
+	pinctrl = devm_kzalloc(dev, sizeof(*pinctrl), GFP_KERNEL);
+	if (!pinctrl)
+		return -ENOMEM;
+	pinctrl->tps = dev_get_drvdata(dev->parent);
+	pinctrl->funcs = pinctrl_functions;
+	pinctrl->pins = tps6594_pins;
+	pinctrl->pctl_dev = devm_pinctrl_register(dev, pctrl_desc, pinctrl);
+	if (IS_ERR(pinctrl->pctl_dev))
+		return dev_err_probe(dev, PTR_ERR(pinctrl->pctl_dev),
+				     "Couldn't register pinctrl driver\n");
+
+	config.parent = tps->dev;
+	config.regmap = tps->regmap;
+	config.ngpio = TPS6594_PINCTRL_PINS_NB;
+	config.ngpio_per_reg = 8;
+	config.reg_dat_base = TPS6594_REG_GPIO_IN_1;
+	config.reg_set_base = TPS6594_REG_GPIO_OUT_1;
+	config.reg_dir_out_base = TPS6594_REG_GPIOX_CONF(0);
+	config.reg_mask_xlate = tps6594_gpio_regmap_xlate;
+
+	pinctrl->gpio_regmap = devm_gpio_regmap_register(dev, &config);
+	if (IS_ERR(pinctrl->gpio_regmap))
+		return dev_err_probe(dev, PTR_ERR(pinctrl->gpio_regmap),
+				     "Couldn't register gpio_regmap driver\n");
+
+	return 0;
+}
+
+static const struct platform_device_id tps6594_pinctrl_id_table[] = {
+	{ "tps6594-pinctrl", },
+	{}
+};
+MODULE_DEVICE_TABLE(platform, tps6594_pinctrl_id_table);
+
+static struct platform_driver tps6594_pinctrl_driver = {
+	.probe = tps6594_pinctrl_probe,
+	.driver = {
+		.name = "tps6594-pinctrl",
+	},
+	.id_table = tps6594_pinctrl_id_table,
+};
+module_platform_driver(tps6594_pinctrl_driver);
+
+MODULE_AUTHOR("Esteban Blanc <eblanc@baylibre.com>");
+MODULE_DESCRIPTION("TPS6594 pinctrl and GPIO driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From b833eb26b628df899f110ebc17d0767e2544c406 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 8 Nov 2023 11:43:31 +0100
Subject: [PATCH 0103/4076] dt-bindings: pinctrl: samsung: add specific
 compatibles for existing SoC

Samsung Exynos SoC reuses several devices from older designs, thus
historically we kept the old (block's) compatible only.  This works fine
and there is no bug here, however guidelines expressed in
Documentation/devicetree/bindings/writing-bindings.rst state that:
1. Compatibles should be specific.
2. We should add new compatibles in case of bugs or features.

Add compatibles specific to each SoC in front of all old-SoC-like
compatibles.

Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com>
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231108104343.24192-6-krzysztof.kozlowski@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../samsung,pinctrl-wakeup-interrupt.yaml     | 24 ++++++++++++-------
 .../bindings/pinctrl/samsung,pinctrl.yaml     |  3 ++-
 2 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 1de91a51234df..1c07af24d6cfa 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -28,15 +28,21 @@ description: |
 
 properties:
   compatible:
-    enum:
-      - samsung,s3c2410-wakeup-eint
-      - samsung,s3c2412-wakeup-eint
-      - samsung,s3c64xx-wakeup-eint
-      - samsung,s5pv210-wakeup-eint
-      - samsung,exynos4210-wakeup-eint
-      - samsung,exynos7-wakeup-eint
-      - samsung,exynos850-wakeup-eint
-      - samsung,exynosautov9-wakeup-eint
+    oneOf:
+      - enum:
+          - samsung,s3c2410-wakeup-eint
+          - samsung,s3c2412-wakeup-eint
+          - samsung,s3c64xx-wakeup-eint
+          - samsung,s5pv210-wakeup-eint
+          - samsung,exynos4210-wakeup-eint
+          - samsung,exynos7-wakeup-eint
+          - samsung,exynos850-wakeup-eint
+          - samsung,exynosautov9-wakeup-eint
+      - items:
+          - enum:
+              - samsung,exynos5433-wakeup-eint
+              - samsung,exynos7885-wakeup-eint
+          - const: samsung,exynos7-wakeup-eint
 
   interrupts:
     description:
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
index 26614621774a5..7509dc36af938 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
@@ -313,7 +313,8 @@ examples:
         pinctrl-0 = <&initial_alive>;
 
         wakeup-interrupt-controller {
-            compatible = "samsung,exynos7-wakeup-eint";
+            compatible = "samsung,exynos5433-wakeup-eint",
+                         "samsung,exynos7-wakeup-eint";
             interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
         };
 
-- 
GitLab


From 4f2ffb1c3ffec70fc2c84accb1bf18831cbfce39 Mon Sep 17 00:00:00 2001
From: Jaewon Kim <jaewon02.kim@samsung.com>
Date: Wed, 15 Nov 2023 18:56:02 +0900
Subject: [PATCH 0104/4076] dt-bindings: pinctrl: samsung: add exynosautov920

Add compatible string for exynosautov920 pin controller.

Signed-off-by: Jaewon Kim <jaewon02.kim@samsung.com>
Link: https://lore.kernel.org/r/20231115095609.39883-7-jaewon02.kim@samsung.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml      | 2 ++
 Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml  | 1 +
 2 files changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 1c07af24d6cfa..1b75abebb9530 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -38,6 +38,7 @@ properties:
           - samsung,exynos7-wakeup-eint
           - samsung,exynos850-wakeup-eint
           - samsung,exynosautov9-wakeup-eint
+          - samsung,exynosautov920-wakeup-eint
       - items:
           - enum:
               - samsung,exynos5433-wakeup-eint
@@ -105,6 +106,7 @@ allOf:
             enum:
               - samsung,exynos850-wakeup-eint
               - samsung,exynosautov9-wakeup-eint
+              - samsung,exynosautov920-wakeup-eint
     then:
       properties:
         interrupts: false
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
index 7509dc36af938..9f04a0c764036 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
@@ -53,6 +53,7 @@ properties:
       - samsung,exynos7885-pinctrl
       - samsung,exynos850-pinctrl
       - samsung,exynosautov9-pinctrl
+      - samsung,exynosautov920-pinctrl
       - tesla,fsd-pinctrl
 
   interrupts:
-- 
GitLab


From a4d511aa24cab1a3175f0421f60fd81ea4721fd1 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Tue, 24 Oct 2023 15:46:46 +0200
Subject: [PATCH 0105/4076] microblaze: Align defconfig with latest Kconfig
 layout

Sync up patch.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/4414109ba26433f00b4c07f600162462ab6c7a93.1698155190.git.michal.simek@amd.com
---
 arch/microblaze/configs/mmu_defconfig | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig
index 7b2d7f6f23c0d..88fce95f6401f 100644
--- a/arch/microblaze/configs/mmu_defconfig
+++ b/arch/microblaze/configs/mmu_defconfig
@@ -3,11 +3,9 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_EXPERT=y
 # CONFIG_BASE_FULL is not set
 CONFIG_KALLSYMS_ALL=y
-CONFIG_EXPERT=y
 CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR=1
 CONFIG_XILINX_MICROBLAZE0_USE_PCMP_INSTR=1
 CONFIG_XILINX_MICROBLAZE0_USE_BARREL=1
@@ -20,7 +18,6 @@ CONFIG_CMDLINE_FORCE=y
 CONFIG_HIGHMEM=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_CMA=y
@@ -78,13 +75,11 @@ CONFIG_CRAMFS=y
 CONFIG_ROMFS_FS=y
 CONFIG_NFS_FS=y
 CONFIG_CIFS=y
-CONFIG_CIFS_STATS2=y
 CONFIG_ENCRYPTED_KEYS=y
 CONFIG_DMA_CMA=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_KGDB=y
 CONFIG_KGDB_TESTS=y
 CONFIG_KGDB_KDB=y
-CONFIG_DEBUG_SLAB=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_SPINLOCK=y
-- 
GitLab


From 873b074050a8028634fb3d4fc95cc9a3a70d10bb Mon Sep 17 00:00:00 2001
From: Raju Kumar Pothuraju <rajukumar.pothuraju@amd.com>
Date: Tue, 24 Oct 2023 15:46:47 +0200
Subject: [PATCH 0106/4076] microblaze: Enable options to mount a rootfs via
 NFS

Enable the options to mount a rootfs over NFS for microblaze
platforms and also support for automatic configuration of IP addresses
during boot as needed by NFS.

Signed-off-by: Raju Kumar Pothuraju <rajukumar.pothuraju@amd.com>
Reviewed-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Signed-off-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/d7bc1c93e485e0a6ab2c234a144402b7bd5f77bb.1698155190.git.michal.simek@amd.com
---
 arch/microblaze/configs/mmu_defconfig | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig
index 88fce95f6401f..85afdb377f739 100644
--- a/arch/microblaze/configs/mmu_defconfig
+++ b/arch/microblaze/configs/mmu_defconfig
@@ -25,6 +25,10 @@ CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
 # CONFIG_IPV6 is not set
 CONFIG_BRIDGE=m
 CONFIG_PCI=y
@@ -74,6 +78,7 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_ROMFS_FS=y
 CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
 CONFIG_CIFS=y
 CONFIG_ENCRYPTED_KEYS=y
 CONFIG_DMA_CMA=y
-- 
GitLab


From ffb0399437ef582b035089d1617bbb0ea174cd0c Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Date: Tue, 24 Oct 2023 15:46:48 +0200
Subject: [PATCH 0107/4076] microblaze: defconfig: Enable the Marvell phy
 driver

Enable the marvell phy driver by default as it is commonly
used PHY on multiple microblaze based evaluation boards.

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/3912fb168671dd5b418da8947ea1c463b554fa86.1698155190.git.michal.simek@amd.com
---
 arch/microblaze/configs/mmu_defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig
index 85afdb377f739..4da7bc4ac4a37 100644
--- a/arch/microblaze/configs/mmu_defconfig
+++ b/arch/microblaze/configs/mmu_defconfig
@@ -44,6 +44,7 @@ CONFIG_NETDEVICES=y
 CONFIG_XILINX_EMACLITE=y
 CONFIG_XILINX_AXI_EMAC=y
 CONFIG_XILINX_LL_TEMAC=y
+CONFIG_MARVELL_PHY=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-- 
GitLab


From ccb9e9dd2a996f5814d7072b968b3d2f4b094188 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 11 Nov 2023 15:32:21 +0100
Subject: [PATCH 0108/4076] dt-bindings: input: samsung,s6sy761: convert to DT
 schema

Convert Samsung  S6SY761 touchscreen controller bindings to DT schema.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231111143221.55452-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../input/touchscreen/samsung,s6sy761.txt     | 32 -----------
 .../input/touchscreen/samsung,s6sy761.yaml    | 54 +++++++++++++++++++
 2 files changed, 54 insertions(+), 32 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
 create mode 100644 Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml

diff --git a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
deleted file mode 100644
index 6805d10d226d3..0000000000000
--- a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-* Samsung S6SY761 touchscreen controller
-
-Required properties:
-- compatible		: must be "samsung,s6sy761"
-- reg			: I2C slave address, (e.g. 0x48)
-- interrupts		: interrupt specification
-- avdd-supply		: analogic power supply
-- vdd-supply		: power supply
-
-Optional properties:
-- touchscreen-size-x	: see touchscreen.txt. This property is embedded in the
-			  device. If defined it forces a different x resolution.
-- touchscreen-size-y	: see touchscreen.txt. This property is embedded in the
-			  device. If defined it forces a different y resolution.
-
-Example:
-
-i2c@00000000 {
-
-	/* ... */
-
-	touchscreen@48 {
-		compatible = "samsung,s6sy761";
-		reg = <0x48>;
-		interrupt-parent = <&gpa1>;
-		interrupts = <1 IRQ_TYPE_NONE>;
-		avdd-supply = <&ldo30_reg>;
-		vdd-supply = <&ldo31_reg>;
-		touchscreen-size-x = <4096>;
-		touchscreen-size-y = <4096>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml
new file mode 100644
index 0000000000000..1ffd17af3c53f
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.yaml
@@ -0,0 +1,54 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/samsung,s6sy761.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Samsung S6SY761 touchscreen controller
+
+maintainers:
+  - Andi Shyti <andi.shyti@kernel.org>
+
+allOf:
+  - $ref: touchscreen.yaml#
+
+properties:
+  compatible:
+    const: samsung,s6sy761
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  avdd-supply: true
+  vdd-supply: true
+
+unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - avdd-supply
+  - vdd-supply
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        touchscreen@48 {
+            compatible = "samsung,s6sy761";
+            reg = <0x48>;
+            interrupt-parent = <&gpa1>;
+            interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+            avdd-supply = <&ldo30_reg>;
+            vdd-supply = <&ldo31_reg>;
+            touchscreen-size-x = <4096>;
+            touchscreen-size-y = <4096>;
+        };
+    };
-- 
GitLab


From 6767b6f4b461149c2f5320daf6a2ac25e36dff9e Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Fri, 3 Nov 2023 15:43:03 -0700
Subject: [PATCH 0109/4076] dt-bindings: qcom,pdc: Add compatible for SM8550

Document the compatible for SM8550 PDC.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
Link: https://lore.kernel.org/r/20231103224304.764730-1-quic_eberman@quicinc.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/interrupt-controller/qcom,pdc.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
index 86d61896f5913..8473afffce63b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
@@ -41,6 +41,7 @@ properties:
           - qcom,sm8250-pdc
           - qcom,sm8350-pdc
           - qcom,sm8450-pdc
+          - qcom,sm8550-pdc
       - const: qcom,pdc
 
   reg:
-- 
GitLab


From 8a5236acacb98f8d8dce1e440aa80caa9ffee29c Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca.ceresoli@bootlin.com>
Date: Mon, 6 Nov 2023 14:03:24 +0100
Subject: [PATCH 0110/4076] of: overlay: enable of_overlay_fdt_apply()
 kerneldoc

of_overlay_fdt_apply() already has a kerneldoc-formatted documentation,
except it is nor marked as such. Adding the second asterisk is enough for
the documentation to take it into account correctly.

Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231106-of_overlay_fdt_apply-kerneldoc-v1-1-9a2d132bc6c1@bootlin.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/overlay.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index a9a292d6d59b2..2ae7e9d24a645 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -964,7 +964,7 @@ out:
 	return ret;
 }
 
-/*
+/**
  * of_overlay_fdt_apply() - Create and apply an overlay changeset
  * @overlay_fdt:	pointer to overlay FDT
  * @overlay_fdt_size:	number of bytes in @overlay_fdt
-- 
GitLab


From 7d646d5c50c60580530a5779bb250c3f277e8f77 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Mon, 13 Nov 2023 15:42:30 -0300
Subject: [PATCH 0111/4076] dt-bindings: power: fsl,scu-pd: Document imx8dl

imx8dxl also contains the SCU PD block.

Add an entry for 'fsl,imx8dl-scu-pd'.

Signed-off-by: Fabio Estevam <festevam@denx.de>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231113184230.14413-1-festevam@gmail.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/power/fsl,scu-pd.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/power/fsl,scu-pd.yaml b/Documentation/devicetree/bindings/power/fsl,scu-pd.yaml
index 407b7cfec783c..7a0f1a4008681 100644
--- a/Documentation/devicetree/bindings/power/fsl,scu-pd.yaml
+++ b/Documentation/devicetree/bindings/power/fsl,scu-pd.yaml
@@ -20,6 +20,7 @@ properties:
   compatible:
     items:
       - enum:
+          - fsl,imx8dl-scu-pd
           - fsl,imx8qm-scu-pd
           - fsl,imx8qxp-scu-pd
       - const: fsl,scu-pd
-- 
GitLab


From b539deafbadb2fc6ba79307a797196454b14f501 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 10 Nov 2023 12:09:08 +0100
Subject: [PATCH 0112/4076] perf report: Add s390 raw data interpretation for
 PAI counters

Commit 39d62336f5c126ad ("s390/pai: add support for cryptography
counters") added support for Processor Activity Instrumentation Facility
(PAI) counters.  These counters values are added as raw data with the
perf sample during 'perf record'.

Now add support to display these counters in the 'perf report' command.

The counter number, its assigned name and value is now printed in
addition to the hexadecimal output.

Output before:

  # perf report -D

  6 514766399626050 0x7b058 [0x48]: PERF_RECORD_SAMPLE(IP, 0x1):
 				303977/303977: 0 period: 1 addr: 0
  ... thread: paitest:303977
  ...... dso: <not found>

  0x7b0a0@/root/perf.data.paicrypto [0x48]: event: 9
  .
  . ... raw event: size 72 bytes
  . 0000:  00 00 00 09 00 01 00 48 00 00 00 00 00 00 00 00  .......H........
  . 0010:  00 04 a3 69 00 04 a3 69 00 01 d4 2d 76 de a0 bb  ...i...i...-v...
  . 0020:  00 00 00 00 00 01 5c 53 00 00 00 06 00 00 00 00  ......\S........
  . 0030:  00 00 00 00 00 00 00 01 00 00 00 0c 00 07 00 00  ................
  . 0040:  00 00 00 53 96 af 00 00                          ...S....

Output after:

  # perf report -D

  6 514766399626050 0x7b058 [0x48]: PERF_RECORD_SAMPLE(IP, 0x1):
 				303977/303977: 0 period: 1 addr: 0
  ... thread: paitest:303977
  ...... dso: <not found>

  0x7b0a0@/root/perf.data.paicrypto [0x48]: event: 9
  .
  . ... raw event: size 72 bytes
  . 0000:  00 00 00 09 00 01 00 48 00 00 00 00 00 00 00 00  .......H........
  . 0010:  00 04 a3 69 00 04 a3 69 00 01 d4 2d 76 de a0 bb  ...i...i...-v...
  . 0020:  00 00 00 00 00 01 5c 53 00 00 00 06 00 00 00 00  ......\S........
  . 0030:  00 00 00 00 00 00 00 01 00 00 00 0c 00 07 00 00  ................
  . 0040:  00 00 00 53 96 af 00 00                          ...S....

        Counter:007 km_aes_128 Value:0x00000000005396af     <--- new

Committer notes:

Had to add ignore pragmas for that __packed function:

  +#pragma GCC diagnostic ignored "-Wpacked"
  +#pragma GCC diagnostic ignored "-Wattributes"

Otherwise this doesn't build in things like debian experimentao cross
building to mips64, etc.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Tested-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Acked-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20231110110908.2312308-1-tmricht@linux.ibm.com
[ Corrected non-existent commit referred to the right one: 39d62336f5c126ad ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/s390-cpumcf-kernel.h |   2 +
 tools/perf/util/s390-sample-raw.c    | 109 +++++++++++++++++++++++++--
 2 files changed, 103 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h
index f55ca07f3ca12..74b36644e3849 100644
--- a/tools/perf/util/s390-cpumcf-kernel.h
+++ b/tools/perf/util/s390-cpumcf-kernel.h
@@ -12,6 +12,8 @@
 #define	S390_CPUMCF_DIAG_DEF	0xfeef	/* Counter diagnostic entry ID */
 #define	PERF_EVENT_CPUM_CF_DIAG	0xBC000	/* Event: Counter sets */
 #define PERF_EVENT_CPUM_SF_DIAG	0xBD000 /* Event: Combined-sampling */
+#define PERF_EVENT_PAI_CRYPTO_ALL	0x1000 /* Event: CRYPTO_ALL */
+#define PERF_EVENT_PAI_NNPA_ALL	0x1800 /* Event: NNPA_ALL */
 
 struct cf_ctrset_entry {	/* CPU-M CF counter set entry (8 byte) */
 	unsigned int def:16;	/* 0-15  Data Entry Format */
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index 115b16edb4513..29a744eeb71eb 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -125,6 +125,9 @@ static int get_counterset_start(int setnr)
 		return 128;
 	case CPUMF_CTR_SET_MT_DIAG:		/* Diagnostic counter set */
 		return 448;
+	case PERF_EVENT_PAI_NNPA_ALL:		/* PAI NNPA counter set */
+	case PERF_EVENT_PAI_CRYPTO_ALL:		/* PAI CRYPTO counter set */
+		return setnr;
 	default:
 		return -1;
 	}
@@ -212,27 +215,117 @@ static void s390_cpumcfdg_dump(struct perf_pmu *pmu, struct perf_sample *sample)
 	}
 }
 
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
+/*
+ * Check for consistency of PAI_CRYPTO/PAI_NNPA raw data.
+ */
+struct pai_data {		/* Event number and value */
+	u16 event_nr;
+	u64 event_val;
+} __packed;
+
+#pragma GCC diagnostic pop
+
+/*
+ * Test for valid raw data. At least one PAI event should be in the raw
+ * data section.
+ */
+static bool s390_pai_all_test(struct perf_sample *sample)
+{
+	unsigned char *buf = sample->raw_data;
+	size_t len = sample->raw_size;
+
+	if (len < 0xa || !buf)
+		return false;
+	return true;
+}
+
+static void s390_pai_all_dump(struct evsel *evsel, struct perf_sample *sample)
+{
+	size_t len = sample->raw_size, offset = 0;
+	unsigned char *p = sample->raw_data;
+	const char *color = PERF_COLOR_BLUE;
+	struct pai_data pai_data;
+	char *ev_name;
+
+	while (offset < len) {
+		memcpy(&pai_data.event_nr, p, sizeof(pai_data.event_nr));
+		pai_data.event_nr = be16_to_cpu(pai_data.event_nr);
+		p += sizeof(pai_data.event_nr);
+		offset += sizeof(pai_data.event_nr);
+
+		memcpy(&pai_data.event_val, p, sizeof(pai_data.event_val));
+		pai_data.event_val = be64_to_cpu(pai_data.event_val);
+		p += sizeof(pai_data.event_val);
+		offset += sizeof(pai_data.event_val);
+
+		ev_name = get_counter_name(evsel->core.attr.config,
+					   pai_data.event_nr, evsel->pmu);
+		color_fprintf(stdout, color, "\tCounter:%03d %s Value:%#018lx\n",
+			      pai_data.event_nr, ev_name ?: "<unknown>",
+			      pai_data.event_val);
+		free(ev_name);
+
+		if (offset + 0xa > len)
+			break;
+	}
+	color_fprintf(stdout, color, "\n");
+}
+
 /* S390 specific trace event function. Check for PERF_RECORD_SAMPLE events
- * and if the event was triggered by a counter set diagnostic event display
- * its raw data.
+ * and if the event was triggered by a
+ * - counter set diagnostic event
+ * - processor activity assist (PAI) crypto counter event
+ * - processor activity assist (PAI) neural network processor assist (NNPA)
+ *   counter event
+ * display its raw data.
  * The function is only invoked when the dump flag -D is set.
+ *
+ * Function evlist__s390_sample_raw() is defined as call back after it has
+ * been verified that the perf.data file was created on s390 platform.
  */
-void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
+void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event,
+			     struct perf_sample *sample)
 {
+	const char *pai_name;
 	struct evsel *evsel;
 
 	if (event->header.type != PERF_RECORD_SAMPLE)
 		return;
 
 	evsel = evlist__event2evsel(evlist, event);
-	if (evsel == NULL ||
-	    evsel->core.attr.config != PERF_EVENT_CPUM_CF_DIAG)
+	if (!evsel)
 		return;
 
 	/* Display raw data on screen */
-	if (!s390_cpumcfdg_testctr(sample)) {
-		pr_err("Invalid counter set data encountered\n");
+	if (evsel->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) {
+		if (!evsel->pmu)
+			evsel->pmu = perf_pmus__find("cpum_cf");
+		if (!s390_cpumcfdg_testctr(sample))
+			pr_err("Invalid counter set data encountered\n");
+		else
+			s390_cpumcfdg_dump(evsel->pmu, sample);
 		return;
 	}
-	s390_cpumcfdg_dump(evsel->pmu, sample);
+
+	switch (evsel->core.attr.config) {
+	case PERF_EVENT_PAI_NNPA_ALL:
+		pai_name = "NNPA_ALL";
+		break;
+	case PERF_EVENT_PAI_CRYPTO_ALL:
+		pai_name = "CRYPTO_ALL";
+		break;
+	default:
+		return;
+	}
+
+	if (!s390_pai_all_test(sample)) {
+		pr_err("Invalid %s raw data encountered\n", pai_name);
+	} else {
+		if (!evsel->pmu)
+			evsel->pmu = perf_pmus__find_by_type(evsel->core.attr.type);
+		s390_pai_all_dump(evsel, sample);
+	}
 }
-- 
GitLab


From acbf6de674ef7b1b5870b25e7b3c695bf84273d0 Mon Sep 17 00:00:00 2001
From: Ji Sheng Teoh <jisheng.teoh@starfivetech.com>
Date: Fri, 3 Nov 2023 16:24:41 +0800
Subject: [PATCH 0113/4076] perf vendor events riscv: Add StarFive Dubhe-80
 JSON file

StarFive's Dubhe-80 supports raw event id 0x00 - 0x22.  The raw events
are enabled through PMU node of DT binding.  Besides raw event, add
standard RISC-V firmware events to support monitoring of firmware event.

Example of PMU DT node:

  pmu {
  	compatible = "riscv,pmu";
  	riscv,raw-event-to-mhpmcounters =
  		/* Event ID 1-31 */
  		<0x00 0x00 0xFFFFFFFF 0xFFFFFFE0 0x00007FF8>,
  		/* Event ID 32-33 */
  		<0x00 0x20 0xFFFFFFFF 0xFFFFFFFE 0x00007FF8>,
  		/* Event ID 34 */
  		<0x00 0x22 0xFFFFFFFF 0xFFFFFF22 0x00007FF8>;
  };

Example of 'perf stat' output:

  [root@user]# perf stat -a \
  	-e access_mmu_stlb \
  	-e miss_mmu_stlb \
  	-e access_mmu_pte_c \
  	-e rob_flush \
  	-e btb_prediction_miss \
  	-e itlb_miss \
  	-e sync_del_fetch_g \
  	-e icache_miss \
  	-e bpu_br_retire \
  	-e bpu_br_miss \
  	-e ret_ins_retire \
  	-e ret_ins_miss \
  	-- openssl speed rsa2048

  Doing 2048 bits private rsa's for 10s: 39 2048 bits private RSA's in
  10.14s
  Doing 2048 bits public rsa's for 10s: 1563 2048 bits public RSA's in
  10.00s
  version: 3.0.11
  built on: Tue Sep 19 13:02:31 2023 UTC
  options: bn(64,64)
  CPUINFO: N/A
                    sign    verify    sign/s verify/s
  rsa 2048 bits 0.260000s 0.006398s      3.8    156.3

   Performance counter stats for 'system wide':

             1338350      access_mmu_stlb
             1154025      miss_mmu_stlb
             1162691      access_mmu_pte_c
               34067      rob_flush
            11212384      btb_prediction_miss
             1256242      itlb_miss
           652523491      sync_del_fetch_g
              384465      icache_miss
            64635789      bpu_br_retire
              323440      bpu_br_miss
             8785143      ret_ins_retire
               31236      ret_ins_miss

        20.760822480 seconds time elapsed

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Ji Sheng Teoh <jisheng.teoh@starfivetech.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Ley Foon Tan <leyfoon.tan@starfivetech.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nikita Shubin <n.shubin@yadro.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20231103082441.1389842-1-jisheng.teoh@starfivetech.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/riscv/mapfile.csv  |   1 +
 .../arch/riscv/starfive/dubhe-80/common.json  | 172 ++++++++++++++++++
 .../riscv/starfive/dubhe-80/firmware.json     |  68 +++++++
 3 files changed, 241 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json
 create mode 100644 tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json

diff --git a/tools/perf/pmu-events/arch/riscv/mapfile.csv b/tools/perf/pmu-events/arch/riscv/mapfile.csv
index c61b3d6ef6166..ee61e26f90cd3 100644
--- a/tools/perf/pmu-events/arch/riscv/mapfile.csv
+++ b/tools/perf/pmu-events/arch/riscv/mapfile.csv
@@ -15,3 +15,4 @@
 #
 #MVENDORID-MARCHID-MIMPID,Version,Filename,EventType
 0x489-0x8000000000000007-0x[[:xdigit:]]+,v1,sifive/u74,core
+0x67e-0x80000000db000080-0x[[:xdigit:]]+,v1,starfive/dubhe-80,core
diff --git a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json
new file mode 100644
index 0000000000000..fbffcacb2aceb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json
@@ -0,0 +1,172 @@
+[
+  {
+    "EventName": "ACCESS_MMU_STLB",
+    "EventCode": "0x1",
+    "BriefDescription": "access MMU STLB"
+  },
+  {
+    "EventName": "MISS_MMU_STLB",
+    "EventCode": "0x2",
+    "BriefDescription": "miss MMU STLB"
+  },
+  {
+    "EventName": "ACCESS_MMU_PTE_C",
+    "EventCode": "0x3",
+    "BriefDescription": "access MMU PTE-Cache"
+  },
+  {
+    "EventName": "MISS_MMU_PTE_C",
+    "EventCode": "0x4",
+    "BriefDescription": "miss MMU PTE-Cache"
+  },
+  {
+    "EventName": "ROB_FLUSH",
+    "EventCode": "0x5",
+    "BriefDescription": "ROB flush (all kinds of exceptions)"
+  },
+  {
+    "EventName": "BTB_PREDICTION_MISS",
+    "EventCode": "0x6",
+    "BriefDescription": "BTB prediction miss"
+  },
+  {
+    "EventName": "ITLB_MISS",
+    "EventCode": "0x7",
+    "BriefDescription": "ITLB miss"
+  },
+  {
+    "EventName": "SYNC_DEL_FETCH_G",
+    "EventCode": "0x8",
+    "BriefDescription": "SYNC delivery a fetch-group"
+  },
+  {
+    "EventName": "ICACHE_MISS",
+    "EventCode": "0x9",
+    "BriefDescription": "ICache miss"
+  },
+  {
+    "EventName": "BPU_BR_RETIRE",
+    "EventCode": "0xA",
+    "BriefDescription": "condition branch instruction retire"
+  },
+  {
+    "EventName": "BPU_BR_MISS",
+    "EventCode": "0xB",
+    "BriefDescription": "condition branch instruction miss"
+  },
+  {
+    "EventName": "RET_INS_RETIRE",
+    "EventCode": "0xC",
+    "BriefDescription": "return instruction retire"
+  },
+  {
+    "EventName": "RET_INS_MISS",
+    "EventCode": "0xD",
+    "BriefDescription": "return instruction miss"
+  },
+  {
+    "EventName": "INDIRECT_JR_MISS",
+    "EventCode": "0xE",
+    "BriefDescription": "indirect JR instruction miss (inlcude without target)"
+  },
+  {
+    "EventName": "IBUF_VAL_ID_NORDY",
+    "EventCode": "0xF",
+    "BriefDescription": "IBUF valid while ID not ready"
+  },
+  {
+    "EventName": "IBUF_NOVAL_ID_RDY",
+    "EventCode": "0x10",
+    "BriefDescription": "IBUF not valid while ID ready"
+  },
+  {
+    "EventName": "REN_INT_PHY_REG_NORDY",
+    "EventCode": "0x11",
+    "BriefDescription": "REN integer physical register file is not ready"
+  },
+  {
+    "EventName": "REN_FP_PHY_REG_NORDY",
+    "EventCode": "0x12",
+    "BriefDescription": "REN floating point physical register file is not ready"
+  },
+  {
+    "EventName": "REN_CP_NORDY",
+    "EventCode": "0x13",
+    "BriefDescription": "REN checkpoint is not ready"
+  },
+  {
+    "EventName": "DEC_VAL_ROB_NORDY",
+    "EventCode": "0x14",
+    "BriefDescription": "DEC is valid and ROB is not ready"
+  },
+  {
+    "EventName": "OOD_FLUSH_LS_DEP",
+    "EventCode": "0x15",
+    "BriefDescription": "out of order flush due to load/store dependency"
+  },
+  {
+    "EventName": "BRU_RET_IJR_INS",
+    "EventCode": "0x16",
+    "BriefDescription": "BRU retire an IJR instruction"
+  },
+  {
+    "EventName": "ACCESS_DTLB",
+    "EventCode": "0x17",
+    "BriefDescription": "access DTLB"
+  },
+  {
+    "EventName": "MISS_DTLB",
+    "EventCode": "0x18",
+    "BriefDescription": "miss DTLB"
+  },
+  {
+    "EventName": "LOAD_INS_DCACHE",
+    "EventCode": "0x19",
+    "BriefDescription": "load instruction access DCache"
+  },
+  {
+    "EventName": "LOAD_INS_MISS_DCACHE",
+    "EventCode": "0x1A",
+    "BriefDescription": "load instruction miss DCache"
+  },
+  {
+    "EventName": "STORE_INS_DCACHE",
+    "EventCode": "0x1B",
+    "BriefDescription": "store/amo instruction access DCache"
+  },
+  {
+    "EventName": "STORE_INS_MISS_DCACHE",
+    "EventCode": "0x1C",
+    "BriefDescription": "store/amo instruction miss DCache"
+  },
+  {
+    "EventName": "LOAD_SCACHE",
+    "EventCode": "0x1D",
+    "BriefDescription": "load access SCache"
+  },
+  {
+    "EventName": "STORE_SCACHE",
+    "EventCode": "0x1E",
+    "BriefDescription": "store access SCache"
+  },
+  {
+    "EventName": "LOAD_MISS_SCACHE",
+    "EventCode": "0x1F",
+    "BriefDescription": "load miss SCache"
+  },
+  {
+    "EventName": "STORE_MISS_SCACHE",
+    "EventCode": "0x20",
+    "BriefDescription": "store miss SCache"
+  },
+  {
+    "EventName": "L2C_PF_REQ",
+    "EventCode": "0x21",
+    "BriefDescription": "L2C data-prefetcher request"
+  },
+  {
+    "EventName": "L2C_PF_HIT",
+    "EventCode": "0x22",
+    "BriefDescription": "L2C data-prefetcher hit"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json
new file mode 100644
index 0000000000000..9b4a032186a7b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json
@@ -0,0 +1,68 @@
+[
+  {
+    "ArchStdEvent": "FW_MISALIGNED_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_MISALIGNED_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ILLEGAL_INSN"
+  },
+  {
+    "ArchStdEvent": "FW_SET_TIMER"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_RECEIVED"
+  }
+]
-- 
GitLab


From 3427fa5b32bbf54e51a2fde347a88161ff16a641 Mon Sep 17 00:00:00 2001
From: Kris Chaplin <kris.chaplin@amd.com>
Date: Tue, 7 Nov 2023 10:06:51 -0800
Subject: [PATCH 0114/4076] dt-bindings: w1: Add AMD AXI w1 host and
 MAINTAINERS entry

Add YAML DT schema for the AMD AXI w1 host IP.

This hardware guarantees protocol timing for driving off-board devices
such as thermal sensors, proms, etc using the 1wire protocol.  The IP
has a register to detect hardware version and so the binding does not
have an explicit version number.

Add MAINTAINERS entry for DT schema.

Co-developed-by: Thomas Delev <thomas.delev@amd.com>
Signed-off-by: Thomas Delev <thomas.delev@amd.com>
Signed-off-by: Kris Chaplin <kris.chaplin@amd.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231107180814.615933-2-kris.chaplin@amd.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/w1/amd,axi-1wire-host.yaml       | 44 +++++++++++++++++++
 MAINTAINERS                                   |  7 +++
 2 files changed, 51 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml

diff --git a/Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml b/Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml
new file mode 100644
index 0000000000000..ef70fa2c0c5da
--- /dev/null
+++ b/Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/w1/amd,axi-1wire-host.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: AMD AXI 1-wire bus host for programmable logic
+
+maintainers:
+  - Kris Chaplin <kris.chaplin@amd.com>
+
+properties:
+  compatible:
+    const: amd,axi-1wire-host
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    onewire@a0000000 {
+        compatible = "amd,axi-1wire-host";
+        reg = <0xa0000000 0x10000>;
+        clocks = <&zynqmp_clk 0x47>;
+        interrupts = <GIC_SPI 0x59 IRQ_TYPE_LEVEL_HIGH>;
+    };
+
+...
diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cfd..cecf289e4ddc1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -893,6 +893,13 @@ Q:	https://patchwork.kernel.org/project/linux-rdma/list/
 F:	drivers/infiniband/hw/efa/
 F:	include/uapi/rdma/efa-abi.h
 
+AMD AXI W1 DRIVER
+M:	Kris Chaplin <kris.chaplin@amd.com>
+R:	Thomas Delev <thomas.delev@amd.com>
+R:	Michal Simek <michal.simek@amd.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml
+
 AMD CDX BUS DRIVER
 M:	Nipun Gupta <nipun.gupta@amd.com>
 M:	Nikhil Agarwal <nikhil.agarwal@amd.com>
-- 
GitLab


From 271c81935801d6449bb7bab5ccfc6cd38238c62b Mon Sep 17 00:00:00 2001
From: Kris Chaplin <kris.chaplin@amd.com>
Date: Tue, 7 Nov 2023 10:06:52 -0800
Subject: [PATCH 0115/4076] w1: Add AXI 1-wire host driver for AMD programmable
 logic IP core

Add a host driver to support the AMD 1-Wire programmable logic IP block.
This block guarantees protocol timing for driving off-board devices such
as thermal sensors, proms, etc.

Add file to MAINTAINERS

Co-developed-by: Thomas Delev <thomas.delev@amd.com>
Signed-off-by: Thomas Delev <thomas.delev@amd.com>
Signed-off-by: Kris Chaplin <kris.chaplin@amd.com>
Link: https://lore.kernel.org/r/20231107180814.615933-3-kris.chaplin@amd.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 MAINTAINERS                     |   1 +
 drivers/w1/masters/Kconfig      |  11 +
 drivers/w1/masters/Makefile     |   1 +
 drivers/w1/masters/amd_axi_w1.c | 395 ++++++++++++++++++++++++++++++++
 4 files changed, 408 insertions(+)
 create mode 100644 drivers/w1/masters/amd_axi_w1.c

diff --git a/MAINTAINERS b/MAINTAINERS
index cecf289e4ddc1..dbe8b0435aafe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -899,6 +899,7 @@ R:	Thomas Delev <thomas.delev@amd.com>
 R:	Michal Simek <michal.simek@amd.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/w1/amd,axi-1wire-host.yaml
+F:	drivers/w1/masters/amd_axi_w1.c
 
 AMD CDX BUS DRIVER
 M:	Nipun Gupta <nipun.gupta@amd.com>
diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig
index ad316573288a8..513c0b114337c 100644
--- a/drivers/w1/masters/Kconfig
+++ b/drivers/w1/masters/Kconfig
@@ -5,6 +5,17 @@
 
 menu "1-wire Bus Masters"
 
+config W1_MASTER_AMD_AXI
+	tristate "AMD AXI 1-wire bus host"
+	help
+	  Say Y here is you want to support the AMD AXI 1-wire IP core.
+	  This driver makes use of the programmable logic IP to perform
+	  correctly timed 1 wire transactions without relying on GPIO timing
+	  through the kernel.
+
+	  This driver can also be built as a module.  If so, the module will be
+	  called amd_w1_axi.
+
 config W1_MASTER_MATROX
 	tristate "Matrox G400 transport layer for 1-wire"
 	depends on PCI
diff --git a/drivers/w1/masters/Makefile b/drivers/w1/masters/Makefile
index c5d85a827e520..6c5a21f9b88ce 100644
--- a/drivers/w1/masters/Makefile
+++ b/drivers/w1/masters/Makefile
@@ -3,6 +3,7 @@
 # Makefile for 1-wire bus master drivers.
 #
 
+obj-$(CONFIG_W1_MASTER_AMD_AXI)		+= amd_axi_w1.o
 obj-$(CONFIG_W1_MASTER_MATROX)		+= matrox_w1.o
 obj-$(CONFIG_W1_MASTER_DS2490)		+= ds2490.o
 obj-$(CONFIG_W1_MASTER_DS2482)		+= ds2482.o
diff --git a/drivers/w1/masters/amd_axi_w1.c b/drivers/w1/masters/amd_axi_w1.c
new file mode 100644
index 0000000000000..24a05c2de5f16
--- /dev/null
+++ b/drivers/w1/masters/amd_axi_w1.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * amd_axi_w1 - AMD 1Wire programmable logic bus host driver
+ *
+ * Copyright (C) 2022-2023 Advanced Micro Devices, Inc. All Rights Reserved.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include <linux/w1.h>
+
+/* 1-wire AMD IP definition */
+#define AXIW1_IPID	0x10ee4453
+/* Registers offset */
+#define AXIW1_INST_REG	0x0
+#define AXIW1_CTRL_REG	0x4
+#define AXIW1_IRQE_REG	0x8
+#define AXIW1_STAT_REG	0xC
+#define AXIW1_DATA_REG	0x10
+#define AXIW1_IPVER_REG	0x18
+#define AXIW1_IPID_REG	0x1C
+/* Instructions */
+#define AXIW1_INITPRES	0x0800
+#define AXIW1_READBIT	0x0C00
+#define AXIW1_WRITEBIT	0x0E00
+#define AXIW1_READBYTE	0x0D00
+#define AXIW1_WRITEBYTE	0x0F00
+/* Status flag masks */
+#define AXIW1_DONE	BIT(0)
+#define AXIW1_READY	BIT(4)
+#define AXIW1_PRESENCE	BIT(31)
+#define AXIW1_MAJORVER_MASK	GENMASK(23, 8)
+#define AXIW1_MINORVER_MASK	GENMASK(7, 0)
+/* Control flag */
+#define AXIW1_GO	BIT(0)
+#define AXI_CLEAR	0
+#define AXI_RESET	BIT(31)
+#define AXIW1_READDATA	BIT(0)
+/* Interrupt Enable */
+#define AXIW1_READY_IRQ_EN	BIT(4)
+#define AXIW1_DONE_IRQ_EN	BIT(0)
+
+#define AXIW1_TIMEOUT	msecs_to_jiffies(100)
+
+#define DRIVER_NAME	"amd_axi_w1"
+
+struct amd_axi_w1_local {
+	struct device *dev;
+	void __iomem *base_addr;
+	int irq;
+	atomic_t flag;			/* Set on IRQ, cleared once serviced */
+	wait_queue_head_t wait_queue;
+	struct w1_bus_master bus_host;
+};
+
+/**
+ * amd_axi_w1_wait_irq_interruptible_timeout() - Wait for IRQ with timeout.
+ *
+ * @amd_axi_w1_local:	Pointer to device structure
+ * @IRQ:		IRQ channel to wait on
+ *
+ * Return:		%0 - OK, %-EINTR - Interrupted, %-EBUSY - Timed out
+ */
+static int amd_axi_w1_wait_irq_interruptible_timeout(struct amd_axi_w1_local *amd_axi_w1_local,
+						     u32 IRQ)
+{
+	int ret;
+
+	/* Enable the IRQ requested and wait for flag to indicate it's been triggered */
+	iowrite32(IRQ, amd_axi_w1_local->base_addr + AXIW1_IRQE_REG);
+	ret = wait_event_interruptible_timeout(amd_axi_w1_local->wait_queue,
+					       atomic_read(&amd_axi_w1_local->flag) != 0,
+					       AXIW1_TIMEOUT);
+	if (ret < 0) {
+		dev_err(amd_axi_w1_local->dev, "Wait IRQ Interrupted\n");
+		return -EINTR;
+	}
+
+	if (!ret) {
+		dev_err(amd_axi_w1_local->dev, "Wait IRQ Timeout\n");
+		return -EBUSY;
+	}
+
+	atomic_set(&amd_axi_w1_local->flag, 0);
+	return 0;
+}
+
+/**
+ * amd_axi_w1_touch_bit() - Performs the touch-bit function - write a 0 or 1 and reads the level.
+ *
+ * @data:	Pointer to device structure
+ * @bit:	The level to write
+ *
+ * Return:	The level read
+ */
+static u8 amd_axi_w1_touch_bit(void *data, u8 bit)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = data;
+	u8 val = 0;
+	int rc;
+
+	/* Wait for READY signal to be 1 to ensure 1-wire IP is ready */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_READY) == 0) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_READY_IRQ_EN);
+		if (rc < 0)
+			return 1; /* Callee doesn't test for error. Return inactive bus state */
+	}
+
+	if (bit)
+		/* Read. Write read Bit command in register 0 */
+		iowrite32(AXIW1_READBIT, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+	else
+		/* Write. Write tx Bit command in instruction register with bit to transmit */
+		iowrite32(AXIW1_WRITEBIT + (bit & 0x01),
+			  amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+
+	/* Write Go signal and clear control reset signal in control register */
+	iowrite32(AXIW1_GO, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for done signal to be 1 */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_DONE) != 1) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local, AXIW1_DONE_IRQ_EN);
+		if (rc < 0)
+			return 1; /* Callee doesn't test for error. Return inactive bus state */
+	}
+
+	/* If read, Retrieve data from register */
+	if (bit)
+		val = (u8)(ioread32(amd_axi_w1_local->base_addr + AXIW1_DATA_REG) & AXIW1_READDATA);
+
+	/* Clear Go signal in register 1 */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	return val;
+}
+
+/**
+ * amd_axi_w1_read_byte - Performs the read byte function.
+ *
+ * @data:	Pointer to device structure
+ * Return:	The value read
+ */
+static u8 amd_axi_w1_read_byte(void *data)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = data;
+	u8 val = 0;
+	int rc;
+
+	/* Wait for READY signal to be 1 to ensure 1-wire IP is ready */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_READY) == 0) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_READY_IRQ_EN);
+		if (rc < 0)
+			return 0xFF; /* Return inactive bus state */
+	}
+
+	/* Write read Byte command in instruction register*/
+	iowrite32(AXIW1_READBYTE, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+
+	/* Write Go signal and clear control reset signal in control register */
+	iowrite32(AXIW1_GO, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for done signal to be 1 */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_DONE) != 1) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local, AXIW1_DONE_IRQ_EN);
+		if (rc < 0)
+			return 0xFF; /* Return inactive bus state */
+	}
+
+	/* Retrieve LSB bit in data register to get RX byte */
+	val = (u8)(ioread32(amd_axi_w1_local->base_addr + AXIW1_DATA_REG) & 0x000000FF);
+
+	/* Clear Go signal in control register */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	return val;
+}
+
+/**
+ * amd_axi_w1_write_byte - Performs the write byte function.
+ *
+ * @data:	The ds2482 channel pointer
+ * @val:	The value to write
+ */
+static void amd_axi_w1_write_byte(void *data, u8 val)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = data;
+	int rc;
+
+	/* Wait for READY signal to be 1 to ensure 1-wire IP is ready */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_READY) == 0) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_READY_IRQ_EN);
+		if (rc < 0)
+			return;
+	}
+
+	/* Write tx Byte command in instruction register with bit to transmit */
+	iowrite32(AXIW1_WRITEBYTE + val, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+
+	/* Write Go signal and clear control reset signal in register 1 */
+	iowrite32(AXIW1_GO, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for done signal to be 1 */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_DONE) != 1) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_DONE_IRQ_EN);
+		if (rc < 0)
+			return;
+	}
+
+	/* Clear Go signal in control register */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+}
+
+/**
+ * amd_axi_w1_reset_bus() - Issues a reset bus sequence.
+ *
+ * @data:	the bus host data struct
+ * Return:	0=Device present, 1=No device present or error
+ */
+static u8 amd_axi_w1_reset_bus(void *data)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = data;
+	u8 val = 0;
+	int rc;
+
+	/* Reset 1-wire Axi IP */
+	iowrite32(AXI_RESET, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for READY signal to be 1 to ensure 1-wire IP is ready */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_READY) == 0) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local,
+							       AXIW1_READY_IRQ_EN);
+		if (rc < 0)
+			return 1; /* Something went wrong with the hardware */
+	}
+	/* Write Initialization command in instruction register */
+	iowrite32(AXIW1_INITPRES, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+
+	/* Write Go signal and clear control reset signal in register 1 */
+	iowrite32(AXIW1_GO, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	/* Wait for done signal to be 1 */
+	while ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_DONE) != 1) {
+		rc = amd_axi_w1_wait_irq_interruptible_timeout(amd_axi_w1_local, AXIW1_DONE_IRQ_EN);
+		if (rc < 0)
+			return 1; /* Something went wrong with the hardware */
+	}
+	/* Retrieve MSB bit in status register to get failure bit */
+	if ((ioread32(amd_axi_w1_local->base_addr + AXIW1_STAT_REG) & AXIW1_PRESENCE) != 0)
+		val = 1;
+
+	/* Clear Go signal in control register */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+
+	return val;
+}
+
+/* Reset the 1-wire AXI IP. Put the IP in reset state and clear registers */
+static void amd_axi_w1_reset(struct amd_axi_w1_local *amd_axi_w1_local)
+{
+	iowrite32(AXI_RESET, amd_axi_w1_local->base_addr + AXIW1_CTRL_REG);
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_INST_REG);
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_IRQE_REG);
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_STAT_REG);
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_DATA_REG);
+}
+
+static irqreturn_t amd_axi_w1_irq(int irq, void *lp)
+{
+	struct amd_axi_w1_local *amd_axi_w1_local = lp;
+
+	/* Reset interrupt trigger */
+	iowrite32(AXI_CLEAR, amd_axi_w1_local->base_addr + AXIW1_IRQE_REG);
+
+	atomic_set(&amd_axi_w1_local->flag, 1);
+	wake_up_interruptible(&amd_axi_w1_local->wait_queue);
+
+	return IRQ_HANDLED;
+}
+
+static int amd_axi_w1_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct amd_axi_w1_local *lp;
+	struct clk *clk;
+	u32 ver_major, ver_minor;
+	int val, rc = 0;
+
+	lp = devm_kzalloc(dev, sizeof(*lp), GFP_KERNEL);
+	if (!lp)
+		return -ENOMEM;
+
+	lp->dev = dev;
+	lp->base_addr = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(lp->base_addr))
+		return PTR_ERR(lp->base_addr);
+
+	lp->irq = platform_get_irq(pdev, 0);
+	if (lp->irq < 0)
+		return lp->irq;
+
+	rc = devm_request_irq(dev, lp->irq, &amd_axi_w1_irq, IRQF_TRIGGER_HIGH, DRIVER_NAME, lp);
+	if (rc)
+		return rc;
+
+	/* Initialize wait queue and flag */
+	init_waitqueue_head(&lp->wait_queue);
+
+	clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	/* Verify IP presence in HW */
+	if (ioread32(lp->base_addr + AXIW1_IPID_REG) != AXIW1_IPID) {
+		dev_err(dev, "AMD 1-wire IP not detected in hardware\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * Allow for future driver expansion supporting new hardware features
+	 * This driver currently only supports hardware 1.x, but include logic
+	 * to detect if a potentially incompatible future version is used
+	 * by reading major version ID. It is highly undesirable for new IP versions
+	 * to break the API, but this code will at least allow for graceful failure
+	 * should that happen. Future new features can be enabled by hardware
+	 * incrementing the minor version and augmenting the driver to detect capability
+	 * using the minor version number
+	 */
+	val = ioread32(lp->base_addr + AXIW1_IPVER_REG);
+	ver_major = FIELD_GET(AXIW1_MAJORVER_MASK, val);
+	ver_minor = FIELD_GET(AXIW1_MINORVER_MASK, val);
+
+	if (ver_major != 1) {
+		dev_err(dev, "AMD AXI W1 host version %u.%u is not supported by this driver",
+			ver_major, ver_minor);
+		return -ENODEV;
+	}
+
+	lp->bus_host.data = lp;
+	lp->bus_host.touch_bit = amd_axi_w1_touch_bit;
+	lp->bus_host.read_byte = amd_axi_w1_read_byte;
+	lp->bus_host.write_byte = amd_axi_w1_write_byte;
+	lp->bus_host.reset_bus = amd_axi_w1_reset_bus;
+
+	amd_axi_w1_reset(lp);
+
+	platform_set_drvdata(pdev, lp);
+	rc = w1_add_master_device(&lp->bus_host);
+	if (rc) {
+		dev_err(dev, "Could not add host device\n");
+		return rc;
+	}
+
+	return 0;
+}
+
+static void amd_axi_w1_remove(struct platform_device *pdev)
+{
+	struct amd_axi_w1_local *lp = platform_get_drvdata(pdev);
+
+	w1_remove_master_device(&lp->bus_host);
+}
+
+static const struct of_device_id amd_axi_w1_of_match[] = {
+	{ .compatible = "amd,axi-1wire-host" },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, amd_axi_w1_of_match);
+
+static struct platform_driver amd_axi_w1_driver = {
+	.probe = amd_axi_w1_probe,
+	.remove_new = amd_axi_w1_remove,
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = amd_axi_w1_of_match,
+	},
+};
+module_platform_driver(amd_axi_w1_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Kris Chaplin <kris.chaplin@amd.com>");
+MODULE_DESCRIPTION("Driver for AMD AXI 1 Wire IP core");
-- 
GitLab


From b9afaa069e58939d95923c27c2fd76a0523119a7 Mon Sep 17 00:00:00 2001
From: Asmaa Mnebhi <asmaa@nvidia.com>
Date: Mon, 30 Oct 2023 16:30:58 -0400
Subject: [PATCH 0116/4076] power: reset: pwr-mlxbf: support graceful reboot
 instead of emergency reset

Replace the soft reset with a graceful reboot.
An acpi event will be triggered by the irq in the pwr-mlxbf.c
to trigger the graceful reboot.

Signed-off-by: Asmaa Mnebhi <asmaa@nvidia.com>
Link: https://lore.kernel.org/r/20231030203058.8056-1-asmaa@nvidia.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/pwr-mlxbf.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/power/reset/pwr-mlxbf.c b/drivers/power/reset/pwr-mlxbf.c
index de35d24bb7ef3..1775b318d0ef4 100644
--- a/drivers/power/reset/pwr-mlxbf.c
+++ b/drivers/power/reset/pwr-mlxbf.c
@@ -17,11 +17,17 @@
 #include <linux/types.h>
 
 struct pwr_mlxbf {
-	struct work_struct send_work;
+	struct work_struct reboot_work;
+	struct work_struct shutdown_work;
 	const char *hid;
 };
 
-static void pwr_mlxbf_send_work(struct work_struct *work)
+static void pwr_mlxbf_reboot_work(struct work_struct *work)
+{
+	acpi_bus_generate_netlink_event("button/reboot.*", "Reboot Button", 0x80, 1);
+}
+
+static void pwr_mlxbf_shutdown_work(struct work_struct *work)
 {
 	acpi_bus_generate_netlink_event("button/power.*", "Power Button", 0x80, 1);
 }
@@ -33,10 +39,10 @@ static irqreturn_t pwr_mlxbf_irq(int irq, void *ptr)
 	struct pwr_mlxbf *priv = ptr;
 
 	if (!strncmp(priv->hid, rst_pwr_hid, 8))
-		emergency_restart();
+		schedule_work(&priv->reboot_work);
 
 	if (!strncmp(priv->hid, low_pwr_hid, 8))
-		schedule_work(&priv->send_work);
+		schedule_work(&priv->shutdown_work);
 
 	return IRQ_HANDLED;
 }
@@ -64,7 +70,11 @@ static int pwr_mlxbf_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return dev_err_probe(dev, irq, "Error getting %s irq.\n", priv->hid);
 
-	err = devm_work_autocancel(dev, &priv->send_work, pwr_mlxbf_send_work);
+	err = devm_work_autocancel(dev, &priv->shutdown_work, pwr_mlxbf_shutdown_work);
+	if (err)
+		return err;
+
+	err = devm_work_autocancel(dev, &priv->reboot_work, pwr_mlxbf_reboot_work);
 	if (err)
 		return err;
 
-- 
GitLab


From 160dff476f81b928ee4a4d2be95066fa32513483 Mon Sep 17 00:00:00 2001
From: Elliot Berman <quic_eberman@quicinc.com>
Date: Tue, 31 Oct 2023 11:27:00 -0700
Subject: [PATCH 0117/4076] dt-bindings: power: reset: $ref reboot-mode in
 syscon-reboot-mode

syscon-reboot-mode.yaml should $ref: reboot-mode.yaml, but instead
rewrites the properties. Update so it $refs instead.

Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231031-ref-reboot-mode-v1-1-18dde4faf7e8@quicinc.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../bindings/power/reset/syscon-reboot-mode.yaml          | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
index 9b1ffceefe3de..b6acff199cdec 100644
--- a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.yaml
@@ -29,12 +29,10 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     description: Offset in the register map for the mode register (in bytes)
 
-patternProperties:
-  "^mode-.+":
-    $ref: /schemas/types.yaml#/definitions/uint32
-    description: Vendor-specific mode value written to the mode register
+allOf:
+  - $ref: reboot-mode.yaml#
 
-additionalProperties: false
+unevaluatedProperties: false
 
 required:
   - compatible
-- 
GitLab


From 5739da3e16ad0ebe99c31cabe960856b53eaaabe Mon Sep 17 00:00:00 2001
From: Elliot Berman <quic_eberman@quicinc.com>
Date: Tue, 31 Oct 2023 11:28:22 -0700
Subject: [PATCH 0118/4076] dt-bindings: power: reset: $ref reboot-mode in
 nvmem-reboot-mode

nvmem-reboot-mode.yaml should $ref: reboot-mode.yaml, but instead
rewrites the properties. Update so it $refs instead.

Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Mukesh Ojha <quic_mojha@quicinc.com>
Link: https://lore.kernel.org/r/20231031-ref-nvmem-reboot-mode-v1-1-c1af9070ce52@quicinc.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../bindings/power/reset/nvmem-reboot-mode.yaml           | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
index 14a262bcbf7cd..627f8a6078c29 100644
--- a/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/nvmem-reboot-mode.yaml
@@ -28,17 +28,15 @@ properties:
     items:
       - const: reboot-mode
 
-patternProperties:
-  "^mode-.+":
-    $ref: /schemas/types.yaml#/definitions/uint32
-    description: Vendor-specific mode value written to the mode register
+allOf:
+  - $ref: reboot-mode.yaml#
 
 required:
   - compatible
   - nvmem-cells
   - nvmem-cell-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
-- 
GitLab


From dfcb264a01a9199e8338a548731baf5bbe77ef19 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Sat, 4 Nov 2023 16:49:06 +0100
Subject: [PATCH 0119/4076] power: supply: bq27xxx: Stop and start delayed work
 in suspend and resume

This driver uses delayed work to perform periodic battery state read out.
This delayed work is not stopped across suspend and resume cycle. The
read out can occur early in the resume cycle. In case of an I2C variant
of this hardware, that read out triggers I2C transfer. That I2C transfer
may happen while the I2C controller is still suspended, which produces a
WARNING in the kernel log.

Fix this by introducing trivial PM ops, which stop the delayed work before
the system enters suspend, and schedule the delayed work right after the
system resumes.

Signed-off-by: Marek Vasut <marex@denx.de>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20231104154920.68585-1-marex@denx.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq27xxx_battery.c     | 22 ++++++++++++++++++++++
 drivers/power/supply/bq27xxx_battery_i2c.c |  1 +
 include/linux/power/bq27xxx_battery.h      |  1 +
 3 files changed, 24 insertions(+)

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 4296600e8912a..1c4a9d1377442 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -2162,6 +2162,28 @@ void bq27xxx_battery_teardown(struct bq27xxx_device_info *di)
 }
 EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown);
 
+#ifdef CONFIG_PM_SLEEP
+static int bq27xxx_battery_suspend(struct device *dev)
+{
+	struct bq27xxx_device_info *di = dev_get_drvdata(dev);
+
+	cancel_delayed_work(&di->work);
+	return 0;
+}
+
+static int bq27xxx_battery_resume(struct device *dev)
+{
+	struct bq27xxx_device_info *di = dev_get_drvdata(dev);
+
+	schedule_delayed_work(&di->work, 0);
+	return 0;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+SIMPLE_DEV_PM_OPS(bq27xxx_battery_battery_pm_ops,
+		  bq27xxx_battery_suspend, bq27xxx_battery_resume);
+EXPORT_SYMBOL_GPL(bq27xxx_battery_battery_pm_ops);
+
 MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
 MODULE_DESCRIPTION("BQ27xxx battery monitor driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 9b5475590518f..3a1798b0c1a79 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -295,6 +295,7 @@ static struct i2c_driver bq27xxx_battery_i2c_driver = {
 	.driver = {
 		.name = "bq27xxx-battery",
 		.of_match_table = of_match_ptr(bq27xxx_battery_i2c_of_match_table),
+		.pm = &bq27xxx_battery_battery_pm_ops,
 	},
 	.probe = bq27xxx_battery_i2c_probe,
 	.remove = bq27xxx_battery_i2c_remove,
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 7c8d65414a70a..7d8025fb74b70 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -83,5 +83,6 @@ struct bq27xxx_device_info {
 void bq27xxx_battery_update(struct bq27xxx_device_info *di);
 int bq27xxx_battery_setup(struct bq27xxx_device_info *di);
 void bq27xxx_battery_teardown(struct bq27xxx_device_info *di);
+extern const struct dev_pm_ops bq27xxx_battery_battery_pm_ops;
 
 #endif
-- 
GitLab


From 099806de68b75a0fe114376b1ee162fdff572ecc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:03 +0100
Subject: [PATCH 0120/4076] power: reset: at91-poweroff: Stop using
 module_platform_driver_probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On today's platforms the benefit of platform_driver_probe() isn't that
relevant any more. It allows to drop some code after booting (or module
loading) for .probe() and discard the .remove() function completely if
the driver is built-in. This typically saves a few 100k.

The downside of platform_driver_probe() is that the driver cannot be
bound and unbound at runtime which is ancient and so slightly
complicates testing. There are also thoughts to deprecate
platform_driver_probe() because it adds some complexity in the driver
core for little gain. Also many drivers don't use it correctly. This
driver for example misses to mark the driver struct with __ref which is
needed to suppress a (W=1) modpost warning.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Link: https://lore.kernel.org/r/20231104211501.3676352-17-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/at91-poweroff.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c
index dd5399785b691..83567428ab432 100644
--- a/drivers/power/reset/at91-poweroff.c
+++ b/drivers/power/reset/at91-poweroff.c
@@ -149,7 +149,7 @@ static void at91_poweroff_dt_set_wakeup_mode(struct platform_device *pdev)
 	writel(wakeup_mode | mode, at91_shdwc.shdwc_base + AT91_SHDW_MR);
 }
 
-static int __init at91_poweroff_probe(struct platform_device *pdev)
+static int at91_poweroff_probe(struct platform_device *pdev)
 {
 	struct device_node *np;
 	u32 ddr_type;
@@ -202,7 +202,7 @@ clk_disable:
 	return ret;
 }
 
-static int __exit at91_poweroff_remove(struct platform_device *pdev)
+static int at91_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == at91_poweroff)
 		pm_power_off = NULL;
@@ -224,13 +224,14 @@ static const struct of_device_id at91_poweroff_of_match[] = {
 MODULE_DEVICE_TABLE(of, at91_poweroff_of_match);
 
 static struct platform_driver at91_poweroff_driver = {
-	.remove = __exit_p(at91_poweroff_remove),
+	.probe = at91_poweroff_probe,
+	.remove = at91_poweroff_remove,
 	.driver = {
 		.name = "at91-poweroff",
 		.of_match_table = at91_poweroff_of_match,
 	},
 };
-module_platform_driver_probe(at91_poweroff_driver, at91_poweroff_probe);
+module_platform_driver(at91_poweroff_driver);
 
 MODULE_AUTHOR("Atmel Corporation");
 MODULE_DESCRIPTION("Shutdown driver for Atmel SoCs");
-- 
GitLab


From 12389c657b623da34ba9b30306e13919d0b42f3a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:04 +0100
Subject: [PATCH 0121/4076] power: reset: at91-reset: Stop using
 module_platform_driver_probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On today's platforms the benefit of platform_driver_probe() isn't that
relevant any more. It allows to drop some code after booting (or module
loading) for .probe() and discard the .remove() function completely if
the driver is built-in. This typically saves a few 100k.

The downside of platform_driver_probe() is that the driver cannot be
bound and unbound at runtime which is ancient and so slightly
complicates testing. There are also thoughts to deprecate
platform_driver_probe() because it adds some complexity in the driver
core for little gain. Also many drivers don't use it correctly. This
driver for example misses to mark the driver struct with __ref which is
needed to suppress a (W=1) modpost warning.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Link: https://lore.kernel.org/r/20231104211501.3676352-18-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/at91-reset.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index aa9b012d3d00b..af85f2f929ba7 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -337,7 +337,7 @@ static int at91_rcdev_init(struct at91_reset *reset,
 	return devm_reset_controller_register(&pdev->dev, &reset->rcdev);
 }
 
-static int __init at91_reset_probe(struct platform_device *pdev)
+static int at91_reset_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
 	struct at91_reset *reset;
@@ -417,7 +417,7 @@ disable_clk:
 	return ret;
 }
 
-static int __exit at91_reset_remove(struct platform_device *pdev)
+static int at91_reset_remove(struct platform_device *pdev)
 {
 	struct at91_reset *reset = platform_get_drvdata(pdev);
 
@@ -428,13 +428,14 @@ static int __exit at91_reset_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver at91_reset_driver = {
-	.remove = __exit_p(at91_reset_remove),
+	.probe = at91_reset_probe,
+	.remove = at91_reset_remove,
 	.driver = {
 		.name = "at91-reset",
 		.of_match_table = at91_reset_of_match,
 	},
 };
-module_platform_driver_probe(at91_reset_driver, at91_reset_probe);
+module_platform_driver(at91_reset_driver);
 
 MODULE_AUTHOR("Atmel Corporation");
 MODULE_DESCRIPTION("Reset driver for Atmel SoCs");
-- 
GitLab


From dde74a5de817e0a011e4783cf26295d7f6fdca26 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:05 +0100
Subject: [PATCH 0122/4076] power: reset: at91-sama5d2_shdwc: Stop using
 module_platform_driver_probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On today's platforms the benefit of platform_driver_probe() isn't that
relevant any more. It allows to drop some code after booting (or module
loading) for .probe() and discard the .remove() function completely if
the driver is built-in. This typically saves a few 100k.

The downside of platform_driver_probe() is that the driver cannot be
bound and unbound at runtime which is ancient and so slightly
complicates testing. There are also thoughts to deprecate
platform_driver_probe() because it adds some complexity in the driver
core for little gain. Also many drivers don't use it correctly. This
driver for example misses to mark the driver struct with __ref which is
needed to suppress a (W=1) modpost warning.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Link: https://lore.kernel.org/r/20231104211501.3676352-19-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/at91-sama5d2_shdwc.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index e76b102b57b1f..ef8add623363a 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -329,7 +329,7 @@ static const struct of_device_id at91_pmc_ids[] = {
 	{ /* Sentinel. */ }
 };
 
-static int __init at91_shdwc_probe(struct platform_device *pdev)
+static int at91_shdwc_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
 	struct device_node *np;
@@ -421,7 +421,7 @@ clk_disable:
 	return ret;
 }
 
-static int __exit at91_shdwc_remove(struct platform_device *pdev)
+static int at91_shdwc_remove(struct platform_device *pdev)
 {
 	struct shdwc *shdw = platform_get_drvdata(pdev);
 
@@ -442,13 +442,14 @@ static int __exit at91_shdwc_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver at91_shdwc_driver = {
-	.remove = __exit_p(at91_shdwc_remove),
+	.probe = at91_shdwc_probe,
+	.remove = at91_shdwc_remove,
 	.driver = {
 		.name = "at91-shdwc",
 		.of_match_table = at91_shdwc_of_match,
 	},
 };
-module_platform_driver_probe(at91_shdwc_driver, at91_shdwc_probe);
+module_platform_driver(at91_shdwc_driver);
 
 MODULE_AUTHOR("Nicolas Ferre <nicolas.ferre@atmel.com>");
 MODULE_DESCRIPTION("Atmel shutdown controller driver");
-- 
GitLab


From 904e582f0c7282b3d7c76c73c06f3ad3b0910335 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:06 +0100
Subject: [PATCH 0123/4076] power: reset: as3722-poweroff: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-20-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/as3722-poweroff.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/as3722-poweroff.c b/drivers/power/reset/as3722-poweroff.c
index 829e0dba2fda3..ab3350ce2d621 100644
--- a/drivers/power/reset/as3722-poweroff.c
+++ b/drivers/power/reset/as3722-poweroff.c
@@ -61,13 +61,11 @@ static int as3722_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int as3722_poweroff_remove(struct platform_device *pdev)
+static void as3722_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == as3722_pm_power_off)
 		pm_power_off = NULL;
 	as3722_pm_poweroff = NULL;
-
-	return 0;
 }
 
 static struct platform_driver as3722_poweroff_driver = {
@@ -75,7 +73,7 @@ static struct platform_driver as3722_poweroff_driver = {
 		.name = "as3722-power-off",
 	},
 	.probe = as3722_poweroff_probe,
-	.remove = as3722_poweroff_remove,
+	.remove_new = as3722_poweroff_remove,
 };
 
 module_platform_driver(as3722_poweroff_driver);
-- 
GitLab


From a31438ece3ec27057c77822b0b0bc0614798c425 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:07 +0100
Subject: [PATCH 0124/4076] power: reset: at91-poweroff: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Link: https://lore.kernel.org/r/20231104211501.3676352-21-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/at91-poweroff.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c
index 83567428ab432..126e774e210c0 100644
--- a/drivers/power/reset/at91-poweroff.c
+++ b/drivers/power/reset/at91-poweroff.c
@@ -202,7 +202,7 @@ clk_disable:
 	return ret;
 }
 
-static int at91_poweroff_remove(struct platform_device *pdev)
+static void at91_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == at91_poweroff)
 		pm_power_off = NULL;
@@ -211,8 +211,6 @@ static int at91_poweroff_remove(struct platform_device *pdev)
 		iounmap(at91_shdwc.mpddrc_base);
 
 	clk_disable_unprepare(at91_shdwc.sclk);
-
-	return 0;
 }
 
 static const struct of_device_id at91_poweroff_of_match[] = {
@@ -225,7 +223,7 @@ MODULE_DEVICE_TABLE(of, at91_poweroff_of_match);
 
 static struct platform_driver at91_poweroff_driver = {
 	.probe = at91_poweroff_probe,
-	.remove = at91_poweroff_remove,
+	.remove_new = at91_poweroff_remove,
 	.driver = {
 		.name = "at91-poweroff",
 		.of_match_table = at91_poweroff_of_match,
-- 
GitLab


From 6f539f3151721f1c90fcdafa2962c19a8efc1afc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:08 +0100
Subject: [PATCH 0125/4076] power: reset: atc260x-poweroff: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-22-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/atc260x-poweroff.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/atc260x-poweroff.c b/drivers/power/reset/atc260x-poweroff.c
index 98f20251a6d18..b4aa50e9685e1 100644
--- a/drivers/power/reset/atc260x-poweroff.c
+++ b/drivers/power/reset/atc260x-poweroff.c
@@ -233,7 +233,7 @@ static int atc260x_pwrc_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int atc260x_pwrc_remove(struct platform_device *pdev)
+static void atc260x_pwrc_remove(struct platform_device *pdev)
 {
 	struct atc260x_pwrc *priv = platform_get_drvdata(pdev);
 
@@ -243,13 +243,11 @@ static int atc260x_pwrc_remove(struct platform_device *pdev)
 	}
 
 	unregister_restart_handler(&priv->restart_nb);
-
-	return 0;
 }
 
 static struct platform_driver atc260x_pwrc_driver = {
 	.probe = atc260x_pwrc_probe,
-	.remove = atc260x_pwrc_remove,
+	.remove_new = atc260x_pwrc_remove,
 	.driver = {
 		.name = "atc260x-pwrc",
 	},
-- 
GitLab


From 6642b13206b2225b0d75451f5dd763574a2c8bb0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:09 +0100
Subject: [PATCH 0126/4076] power: reset: ltc2952-poweroff: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-23-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/ltc2952-poweroff.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c
index eea05921a054b..fa25fbd539343 100644
--- a/drivers/power/reset/ltc2952-poweroff.c
+++ b/drivers/power/reset/ltc2952-poweroff.c
@@ -286,7 +286,7 @@ static int ltc2952_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ltc2952_poweroff_remove(struct platform_device *pdev)
+static void ltc2952_poweroff_remove(struct platform_device *pdev)
 {
 	struct ltc2952_poweroff *data = platform_get_drvdata(pdev);
 
@@ -295,7 +295,6 @@ static int ltc2952_poweroff_remove(struct platform_device *pdev)
 	hrtimer_cancel(&data->timer_wde);
 	atomic_notifier_chain_unregister(&panic_notifier_list,
 					 &data->panic_notifier);
-	return 0;
 }
 
 static const struct of_device_id of_ltc2952_poweroff_match[] = {
@@ -306,7 +305,7 @@ MODULE_DEVICE_TABLE(of, of_ltc2952_poweroff_match);
 
 static struct platform_driver ltc2952_poweroff_driver = {
 	.probe = ltc2952_poweroff_probe,
-	.remove = ltc2952_poweroff_remove,
+	.remove_new = ltc2952_poweroff_remove,
 	.driver = {
 		.name = "ltc2952-poweroff",
 		.of_match_table = of_ltc2952_poweroff_match,
-- 
GitLab


From 99f7fa6c7cc573ebe2529959723b71b4d12ec2f5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:10 +0100
Subject: [PATCH 0127/4076] power: reset: mt6323-poweroff: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/r/20231104211501.3676352-24-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/mt6323-poweroff.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/mt6323-poweroff.c b/drivers/power/reset/mt6323-poweroff.c
index 108167f7738bb..57a63c0ab7fb7 100644
--- a/drivers/power/reset/mt6323-poweroff.c
+++ b/drivers/power/reset/mt6323-poweroff.c
@@ -70,12 +70,10 @@ static int mt6323_pwrc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mt6323_pwrc_remove(struct platform_device *pdev)
+static void mt6323_pwrc_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == &mt6323_do_pwroff)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id mt6323_pwrc_dt_match[] = {
@@ -86,7 +84,7 @@ MODULE_DEVICE_TABLE(of, mt6323_pwrc_dt_match);
 
 static struct platform_driver mt6323_pwrc_driver = {
 	.probe          = mt6323_pwrc_probe,
-	.remove         = mt6323_pwrc_remove,
+	.remove_new     = mt6323_pwrc_remove,
 	.driver         = {
 		.name   = "mt6323-pwrc",
 		.of_match_table = mt6323_pwrc_dt_match,
-- 
GitLab


From 1a0457ab2ce81d92c2077a79080141d924884c5f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:11 +0100
Subject: [PATCH 0128/4076] power: reset: qnap-poweroff: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-25-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/qnap-poweroff.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/power/reset/qnap-poweroff.c b/drivers/power/reset/qnap-poweroff.c
index 0ddf7f25f7b87..e0f2ff6b147c1 100644
--- a/drivers/power/reset/qnap-poweroff.c
+++ b/drivers/power/reset/qnap-poweroff.c
@@ -111,15 +111,14 @@ static int qnap_power_off_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qnap_power_off_remove(struct platform_device *pdev)
+static void qnap_power_off_remove(struct platform_device *pdev)
 {
 	pm_power_off = NULL;
-	return 0;
 }
 
 static struct platform_driver qnap_power_off_driver = {
 	.probe	= qnap_power_off_probe,
-	.remove	= qnap_power_off_remove,
+	.remove_new = qnap_power_off_remove,
 	.driver	= {
 		.name	= "qnap_power_off",
 		.of_match_table = of_match_ptr(qnap_power_off_of_match_table),
-- 
GitLab


From 6f7be7b2f15a654a5f08b7d37df282c171b9380b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:12 +0100
Subject: [PATCH 0129/4076] power: reset: regulator-poweroff: Convert to
 platform remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-26-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/regulator-poweroff.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/regulator-poweroff.c b/drivers/power/reset/regulator-poweroff.c
index 7f87fbb8b051e..15160809c423a 100644
--- a/drivers/power/reset/regulator-poweroff.c
+++ b/drivers/power/reset/regulator-poweroff.c
@@ -52,12 +52,10 @@ static int regulator_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int regulator_poweroff_remove(__maybe_unused struct platform_device *pdev)
+static void regulator_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == &regulator_poweroff_do_poweroff)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id of_regulator_poweroff_match[] = {
@@ -68,7 +66,7 @@ MODULE_DEVICE_TABLE(of, of_regulator_poweroff_match);
 
 static struct platform_driver regulator_poweroff_driver = {
 	.probe = regulator_poweroff_probe,
-	.remove = regulator_poweroff_remove,
+	.remove_new = regulator_poweroff_remove,
 	.driver = {
 		.name = "poweroff-regulator",
 		.of_match_table = of_regulator_poweroff_match,
-- 
GitLab


From aedd4da0aa27fe9d0b03b3fbf62376aebbfc385b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:13 +0100
Subject: [PATCH 0130/4076] power: reset: restart-poweroff: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-27-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/restart-poweroff.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/restart-poweroff.c b/drivers/power/reset/restart-poweroff.c
index 28f1822db1626..f4d6004793d3a 100644
--- a/drivers/power/reset/restart-poweroff.c
+++ b/drivers/power/reset/restart-poweroff.c
@@ -33,12 +33,10 @@ static int restart_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int restart_poweroff_remove(struct platform_device *pdev)
+static void restart_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == &restart_poweroff_do_poweroff)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id of_restart_poweroff_match[] = {
@@ -49,7 +47,7 @@ MODULE_DEVICE_TABLE(of, of_restart_poweroff_match);
 
 static struct platform_driver restart_poweroff_driver = {
 	.probe = restart_poweroff_probe,
-	.remove = restart_poweroff_remove,
+	.remove_new = restart_poweroff_remove,
 	.driver = {
 		.name = "poweroff-restart",
 		.of_match_table = of_restart_poweroff_match,
-- 
GitLab


From 30d26d2be83de0d036f59f384b805dd3bf4bf5ef Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:14 +0100
Subject: [PATCH 0131/4076] power: reset: rmobile-reset: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-28-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/rmobile-reset.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/power/reset/rmobile-reset.c b/drivers/power/reset/rmobile-reset.c
index bd3b396558e0d..5df9b41c68c79 100644
--- a/drivers/power/reset/rmobile-reset.c
+++ b/drivers/power/reset/rmobile-reset.c
@@ -59,11 +59,10 @@ fail_unmap:
 	return error;
 }
 
-static int rmobile_reset_remove(struct platform_device *pdev)
+static void rmobile_reset_remove(struct platform_device *pdev)
 {
 	unregister_restart_handler(&rmobile_reset_nb);
 	iounmap(sysc_base2);
-	return 0;
 }
 
 static const struct of_device_id rmobile_reset_of_match[] = {
@@ -74,7 +73,7 @@ MODULE_DEVICE_TABLE(of, rmobile_reset_of_match);
 
 static struct platform_driver rmobile_reset_driver = {
 	.probe = rmobile_reset_probe,
-	.remove = rmobile_reset_remove,
+	.remove_new = rmobile_reset_remove,
 	.driver = {
 		.name = "rmobile_reset",
 		.of_match_table = rmobile_reset_of_match,
-- 
GitLab


From 2973706c4160ed8c1e695b4dfef4bdb3124c5753 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:15 +0100
Subject: [PATCH 0132/4076] power: reset: syscon-poweroff: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-29-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/syscon-poweroff.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/syscon-poweroff.c b/drivers/power/reset/syscon-poweroff.c
index c3aab7f59345a..1b2ce7734260c 100644
--- a/drivers/power/reset/syscon-poweroff.c
+++ b/drivers/power/reset/syscon-poweroff.c
@@ -76,12 +76,10 @@ static int syscon_poweroff_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int syscon_poweroff_remove(struct platform_device *pdev)
+static void syscon_poweroff_remove(struct platform_device *pdev)
 {
 	if (pm_power_off == syscon_poweroff)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id syscon_poweroff_of_match[] = {
@@ -91,7 +89,7 @@ static const struct of_device_id syscon_poweroff_of_match[] = {
 
 static struct platform_driver syscon_poweroff_driver = {
 	.probe = syscon_poweroff_probe,
-	.remove = syscon_poweroff_remove,
+	.remove_new = syscon_poweroff_remove,
 	.driver = {
 		.name = "syscon-poweroff",
 		.of_match_table = syscon_poweroff_of_match,
-- 
GitLab


From 0bf7207e09673144df6425b2cad8bcb015e3501a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 4 Nov 2023 22:15:16 +0100
Subject: [PATCH 0133/4076] power: reset: tps65086-restart: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Returning an error if unregister_restart_handler() failed has no effect
but triggering another error message. So converting this driver to
.remove_new() has no effect but to suppress the duplicated error message.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231104211501.3676352-30-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/tps65086-restart.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/power/reset/tps65086-restart.c b/drivers/power/reset/tps65086-restart.c
index 5ec819eac7da4..ee8e9f4b837ea 100644
--- a/drivers/power/reset/tps65086-restart.c
+++ b/drivers/power/reset/tps65086-restart.c
@@ -62,19 +62,21 @@ static int tps65086_restart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int tps65086_restart_remove(struct platform_device *pdev)
+static void tps65086_restart_remove(struct platform_device *pdev)
 {
 	struct tps65086_restart *tps65086_restart = platform_get_drvdata(pdev);
 	int ret;
 
 	ret = unregister_restart_handler(&tps65086_restart->handler);
 	if (ret) {
+		/*
+		 * tps65086_restart_probe() registered the restart handler. So
+		 * unregistering should work fine. Checking the error code
+		 * shouldn't be needed, still doing it for completeness.
+		 */
 		dev_err(&pdev->dev, "%s: cannot unregister restart handler: %d\n",
 			__func__, ret);
-		return -ENODEV;
 	}
-
-	return 0;
 }
 
 static const struct platform_device_id tps65086_restart_id_table[] = {
@@ -88,7 +90,7 @@ static struct platform_driver tps65086_restart_driver = {
 		.name = "tps65086-restart",
 	},
 	.probe = tps65086_restart_probe,
-	.remove = tps65086_restart_remove,
+	.remove_new = tps65086_restart_remove,
 	.id_table = tps65086_restart_id_table,
 };
 module_platform_driver(tps65086_restart_driver);
-- 
GitLab


From 20cea2b59abe33b80536b936b6729c88d1de2624 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 5 Nov 2023 10:47:13 +0100
Subject: [PATCH 0134/4076] power: reset: at91-reset: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Link: https://lore.kernel.org/r/20231105094712.3706799-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/at91-reset.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index af85f2f929ba7..16512654295f5 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -417,19 +417,17 @@ disable_clk:
 	return ret;
 }
 
-static int at91_reset_remove(struct platform_device *pdev)
+static void at91_reset_remove(struct platform_device *pdev)
 {
 	struct at91_reset *reset = platform_get_drvdata(pdev);
 
 	unregister_restart_handler(&reset->nb);
 	clk_disable_unprepare(reset->sclk);
-
-	return 0;
 }
 
 static struct platform_driver at91_reset_driver = {
 	.probe = at91_reset_probe,
-	.remove = at91_reset_remove,
+	.remove_new = at91_reset_remove,
 	.driver = {
 		.name = "at91-reset",
 		.of_match_table = at91_reset_of_match,
-- 
GitLab


From 054eb2377523530404fb64c24c8747feb022c5b4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 5 Nov 2023 10:47:14 +0100
Subject: [PATCH 0135/4076] power: reset: at91-sama5d2_shdwc: Convert to
 platform remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Link: https://lore.kernel.org/r/20231105094712.3706799-4-u.kleine-koenig@pengutronix.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/at91-sama5d2_shdwc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index ef8add623363a..af95c7b39cb3c 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -421,7 +421,7 @@ clk_disable:
 	return ret;
 }
 
-static int at91_shdwc_remove(struct platform_device *pdev)
+static void at91_shdwc_remove(struct platform_device *pdev)
 {
 	struct shdwc *shdw = platform_get_drvdata(pdev);
 
@@ -437,13 +437,11 @@ static int at91_shdwc_remove(struct platform_device *pdev)
 	iounmap(shdw->pmc_base);
 
 	clk_disable_unprepare(shdw->sclk);
-
-	return 0;
 }
 
 static struct platform_driver at91_shdwc_driver = {
 	.probe = at91_shdwc_probe,
-	.remove = at91_shdwc_remove,
+	.remove_new = at91_shdwc_remove,
 	.driver = {
 		.name = "at91-shdwc",
 		.of_match_table = at91_shdwc_of_match,
-- 
GitLab


From f37669119423ca852ca855b24732f25c0737aa57 Mon Sep 17 00:00:00 2001
From: Jan Palus <jpalus@fastmail.com>
Date: Sat, 11 Nov 2023 23:17:04 +0100
Subject: [PATCH 0136/4076] power: supply: cw2015: correct time_to_empty units
 in sysfs

RRT_ALRT register holds remaining battery time in minutes therefore it
needs to be scaled accordingly when exposing TIME_TO_EMPTY via sysfs
expressed in seconds

Fixes: b4c7715c10c1 ("power: supply: add CellWise cw2015 fuel gauge driver")
Signed-off-by: Jan Palus <jpalus@fastmail.com>
Link: https://lore.kernel.org/r/20231111221704.5579-1-jpalus@fastmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/cw2015_battery.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/supply/cw2015_battery.c b/drivers/power/supply/cw2015_battery.c
index bb29e9ebd24a8..99f3ccdc30a6a 100644
--- a/drivers/power/supply/cw2015_battery.c
+++ b/drivers/power/supply/cw2015_battery.c
@@ -491,7 +491,7 @@ static int cw_battery_get_property(struct power_supply *psy,
 
 	case POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW:
 		if (cw_battery_valid_time_to_empty(cw_bat))
-			val->intval = cw_bat->time_to_empty;
+			val->intval = cw_bat->time_to_empty * 60;
 		else
 			val->intval = 0;
 		break;
-- 
GitLab


From 74d016ecc1a7974664e98d1afbf649cd4e0e0423 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 15 Nov 2023 22:41:27 -0500
Subject: [PATCH 0137/4076] new helper: user_path_locked_at()

Equivalent of kern_path_locked() taking dfd/userland name.
User introduced in the next commit.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 16 +++++++++++++---
 include/linux/namei.h |  1 +
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 71c13b2990b44..3ffbe268d52c2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2573,13 +2573,13 @@ static int filename_parentat(int dfd, struct filename *name,
 }
 
 /* does lookup, returns the object with parent locked */
-static struct dentry *__kern_path_locked(struct filename *name, struct path *path)
+static struct dentry *__kern_path_locked(int dfd, struct filename *name, struct path *path)
 {
 	struct dentry *d;
 	struct qstr last;
 	int type, error;
 
-	error = filename_parentat(AT_FDCWD, name, 0, path, &last, &type);
+	error = filename_parentat(dfd, name, 0, path, &last, &type);
 	if (error)
 		return ERR_PTR(error);
 	if (unlikely(type != LAST_NORM)) {
@@ -2598,12 +2598,22 @@ static struct dentry *__kern_path_locked(struct filename *name, struct path *pat
 struct dentry *kern_path_locked(const char *name, struct path *path)
 {
 	struct filename *filename = getname_kernel(name);
-	struct dentry *res = __kern_path_locked(filename, path);
+	struct dentry *res = __kern_path_locked(AT_FDCWD, filename, path);
 
 	putname(filename);
 	return res;
 }
 
+struct dentry *user_path_locked_at(int dfd, const char __user *name, struct path *path)
+{
+	struct filename *filename = getname(name);
+	struct dentry *res = __kern_path_locked(dfd, filename, path);
+
+	putname(filename);
+	return res;
+}
+EXPORT_SYMBOL(user_path_locked_at);
+
 int kern_path(const char *name, unsigned int flags, struct path *path)
 {
 	struct filename *filename = getname_kernel(name);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 3100371b5e321..74e0cc14ebf86 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -66,6 +66,7 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne
 extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int);
 extern void done_path_create(struct path *, struct dentry *);
 extern struct dentry *kern_path_locked(const char *, struct path *);
+extern struct dentry *user_path_locked_at(int , const char __user *, struct path *);
 int vfs_path_parent_lookup(struct filename *filename, unsigned int flags,
 			   struct path *parent, struct qstr *last, int *type,
 			   const struct path *root);
-- 
GitLab


From bbe6a7c899e7f265c5a6d01a178336a405e98ed6 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 14 Nov 2023 18:52:42 -0500
Subject: [PATCH 0138/4076] bch2_ioctl_subvolume_destroy(): fix locking

make it use user_path_locked_at() to get the normal directory protection
for modifications, as well as stable ->d_parent and ->d_name in victim

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/bcachefs/fs-ioctl.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 5a39bcb597a33..c5ab5a2dc9bed 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -453,33 +453,36 @@ static long bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp,
 static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
 				struct bch_ioctl_subvolume arg)
 {
+	const char __user *name = (void __user *)(unsigned long)arg.dst_ptr;
 	struct path path;
 	struct inode *dir;
+	struct dentry *victim;
 	int ret = 0;
 
 	if (arg.flags)
 		return -EINVAL;
 
-	ret = user_path_at(arg.dirfd,
-			(const char __user *)(unsigned long)arg.dst_ptr,
-			LOOKUP_FOLLOW, &path);
-	if (ret)
-		return ret;
+	victim = user_path_locked_at(arg.dirfd, name, &path);
+	if (IS_ERR(victim))
+		return PTR_ERR(victim);
 
-	if (path.dentry->d_sb->s_fs_info != c) {
+	if (victim->d_sb->s_fs_info != c) {
 		ret = -EXDEV;
 		goto err;
 	}
-
-	dir = path.dentry->d_parent->d_inode;
-
-	ret = __bch2_unlink(dir, path.dentry, true);
-	if (ret)
+	if (!d_is_positive(victim)) {
+		ret = -ENOENT;
 		goto err;
-
-	fsnotify_rmdir(dir, path.dentry);
-	d_delete(path.dentry);
+	}
+	dir = d_inode(path.dentry);
+	ret = __bch2_unlink(dir, victim, true);
+	if (!ret) {
+		fsnotify_rmdir(dir, victim);
+		d_delete(victim);
+	}
+	inode_unlock(dir);
 err:
+	dput(victim);
 	path_put(&path);
 	return ret;
 }
-- 
GitLab


From 8c91ef9883bfb5a6315917a7104dd1e06c85b278 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:48:17 +0100
Subject: [PATCH 0139/4076] dt-bindings: phy: qcom,sc8280xp-qmp-ufs-phy:
 document the SM8650 QMP UFS PHY

Document the QMP UFS PHY on the SM8650 Platform.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-phy-v2-1-a543a4c4b491@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml      | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
index f3a3296c811cb..8474eef8d0ff5 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml
@@ -32,6 +32,7 @@ properties:
       - qcom,sm8350-qmp-ufs-phy
       - qcom,sm8450-qmp-ufs-phy
       - qcom,sm8550-qmp-ufs-phy
+      - qcom,sm8650-qmp-ufs-phy
 
   reg:
     maxItems: 1
@@ -112,6 +113,7 @@ allOf:
               - qcom,sm8250-qmp-ufs-phy
               - qcom,sm8350-qmp-ufs-phy
               - qcom,sm8550-qmp-ufs-phy
+              - qcom,sm8650-qmp-ufs-phy
     then:
       properties:
         clocks:
-- 
GitLab


From 9e3f381986f6be1a7199587f8921cbb7e89a733e Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:48:18 +0100
Subject: [PATCH 0140/4076] dt-bindings: phy: qcom,sc8280xp-qmp-pcie-phy:
 document the SM8650 QMP PCIe PHYs

Document the QMP PCIe PHYs on the SM8650 Platform.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-phy-v2-2-a543a4c4b491@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml  | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
index 2c3d6553a7bac..6c03f2d5fca3c 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
@@ -36,6 +36,8 @@ properties:
       - qcom,sm8450-qmp-gen4x2-pcie-phy
       - qcom,sm8550-qmp-gen3x2-pcie-phy
       - qcom,sm8550-qmp-gen4x2-pcie-phy
+      - qcom,sm8650-qmp-gen3x2-pcie-phy
+      - qcom,sm8650-qmp-gen4x2-pcie-phy
 
   reg:
     minItems: 1
@@ -147,6 +149,8 @@ allOf:
               - qcom,sm8450-qmp-gen3x2-pcie-phy
               - qcom,sm8550-qmp-gen3x2-pcie-phy
               - qcom,sm8550-qmp-gen4x2-pcie-phy
+              - qcom,sm8650-qmp-gen3x2-pcie-phy
+              - qcom,sm8650-qmp-gen4x2-pcie-phy
     then:
       properties:
         clocks:
@@ -189,6 +193,7 @@ allOf:
           contains:
             enum:
               - qcom,sm8550-qmp-gen4x2-pcie-phy
+              - qcom,sm8650-qmp-gen4x2-pcie-phy
     then:
       properties:
         resets:
-- 
GitLab


From 685c00ac4240c1205005f617916f68b76da78908 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:48:19 +0100
Subject: [PATCH 0141/4076] dt-bindings: phy: qcom,sc8280xp-qmp-usb43dp-phy:
 document the SM8650 QMP USB/DP Combo PHY

Document the QMP USB/DP Combo PHY on the SM8650 Platform.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-phy-v2-3-a543a4c4b491@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml  | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
index 9af203dc8793f..ae83cb8cb21f8 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
@@ -27,6 +27,7 @@ properties:
       - qcom,sm8350-qmp-usb3-dp-phy
       - qcom,sm8450-qmp-usb3-dp-phy
       - qcom,sm8550-qmp-usb3-dp-phy
+      - qcom,sm8650-qmp-usb3-dp-phy
 
   reg:
     maxItems: 1
@@ -128,6 +129,7 @@ allOf:
             - qcom,sc8280xp-qmp-usb43dp-phy
             - qcom,sm6350-qmp-usb3-dp-phy
             - qcom,sm8550-qmp-usb3-dp-phy
+            - qcom,sm8650-qmp-usb3-dp-phy
     then:
       required:
         - power-domains
-- 
GitLab


From 330df15dab25931c9214bfa279319755d2201d7f Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:48:20 +0100
Subject: [PATCH 0142/4076] dt-bindings: phy: qcom,snps-eusb2: document the
 SM8650 Synopsys eUSB2 PHY

Document the Synopsys eUSB2 PHY on the SM8650 Platform by using
the SM8550 as fallback.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-phy-v2-4-a543a4c4b491@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
index c95828607ab6b..8f5d7362046c9 100644
--- a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
@@ -18,6 +18,7 @@ properties:
       - items:
           - enum:
               - qcom,sdx75-snps-eusb2-phy
+              - qcom,sm8650-snps-eusb2-phy
           - const: qcom,sm8550-snps-eusb2-phy
       - const: qcom,sm8550-snps-eusb2-phy
 
-- 
GitLab


From 7c4bf8cb9d40a7222bb5d641979952b196707985 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:48:21 +0100
Subject: [PATCH 0143/4076] phy: qcom: qmp-ufs: add QMP UFS PHY tables for
 SM8650

Add QMP UFS PHY support for the SM8650 platform.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-phy-v2-5-a543a4c4b491@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h    |  1 +
 .../phy-qcom-qmp-qserdes-txrx-ufs-v6.h        |  7 ++
 drivers/phy/qualcomm/phy-qcom-qmp-ufs.c       | 86 +++++++++++++++++++
 3 files changed, 94 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h
index c23d5e41e25b5..fe6c450f61238 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-ufs-v6.h
@@ -12,6 +12,7 @@
 #define QPHY_V6_PCS_UFS_SW_RESET			0x008
 #define QPHY_V6_PCS_UFS_TIMER_20US_CORECLK_STEPS_MSB	0x00c
 #define QPHY_V6_PCS_UFS_TIMER_20US_CORECLK_STEPS_LSB	0x010
+#define QPHY_V6_PCS_UFS_PCS_CTRL1			0x020
 #define QPHY_V6_PCS_UFS_PLL_CNTL			0x02c
 #define QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL		0x030
 #define QPHY_V6_PCS_UFS_TX_SMALL_AMP_DRV_LVL		0x038
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
index 15bcb4ba91399..ae220fd04d10d 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
@@ -10,10 +10,17 @@
 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_RX			0x2c
 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX		0x30
 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_RX		0x34
+#define QSERDES_UFS_V6_TX_LANE_MODE_1				0x7c
 
 #define QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE2		0x08
 #define QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE4		0x10
+#define QSERDES_UFS_V6_RX_UCDR_SO_SATURATION			0x28
+#define QSERDES_UFS_V6_RX_UCDR_PI_CTRL1				0x58
+#define QSERDES_UFS_V6_RX_RX_TERM_BW_CTRL0			0xc4
+#define QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2			0xd4
+#define QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE4			0xdc
 #define QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL			0x178
+#define QSERDES_UFS_V6_RX_INTERFACE_MODE			0x1e0
 #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0			0x208
 #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B1			0x20c
 #define QSERDES_UFS_V6_RX_MODE_RATE_0_1_B3			0x214
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
index 514fa14df6345..5f79d188b435e 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
@@ -803,6 +803,67 @@ static const struct qmp_phy_init_tbl sm8550_ufsphy_pcs[] = {
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02),
 };
 
+static const struct qmp_phy_init_tbl sm8650_ufsphy_serdes[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0xd9),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x11),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_HS_SWITCH_SEL_1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x44),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_INITVAL2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x7f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x4c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x07),
+};
+
+static const struct qmp_phy_init_tbl sm8650_ufsphy_tx[] = {
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_LANE_MODE_1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x07),
+};
+
+static const struct qmp_phy_init_tbl sm8650_ufsphy_rx[] = {
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE4, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0, 0xc2),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B1, 0xc2),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B3, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B6, 0x60),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE2_B3, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE2_B6, 0x60),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B3, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B4, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B5, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE3_B8, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE4_B3, 0xb9),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE4_B6, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_SO_SATURATION, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_PI_CTRL1, 0x94),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_RX_TERM_BW_CTRL0, 0xfa),
+};
+
+static const struct qmp_phy_init_tbl sm8650_ufsphy_pcs[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PCS_CTRL1, 0xc1),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL, 0x0f),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_SIGDET_CTRL2, 0x69),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02),
+};
+
 struct qmp_ufs_offsets {
 	u16 serdes;
 	u16 pcs;
@@ -1303,6 +1364,28 @@ static const struct qmp_phy_cfg sm8550_ufsphy_cfg = {
 	.regs			= ufsphy_v6_regs_layout,
 };
 
+static const struct qmp_phy_cfg sm8650_ufsphy_cfg = {
+	.lanes			= 2,
+
+	.offsets		= &qmp_ufs_offsets_v6,
+
+	.tbls = {
+		.serdes		= sm8650_ufsphy_serdes,
+		.serdes_num	= ARRAY_SIZE(sm8650_ufsphy_serdes),
+		.tx		= sm8650_ufsphy_tx,
+		.tx_num		= ARRAY_SIZE(sm8650_ufsphy_tx),
+		.rx		= sm8650_ufsphy_rx,
+		.rx_num		= ARRAY_SIZE(sm8650_ufsphy_rx),
+		.pcs		= sm8650_ufsphy_pcs,
+		.pcs_num	= ARRAY_SIZE(sm8650_ufsphy_pcs),
+	},
+	.clk_list		= sdm845_ufs_phy_clk_l,
+	.num_clks		= ARRAY_SIZE(sdm845_ufs_phy_clk_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= ufsphy_v6_regs_layout,
+};
+
 static void qmp_ufs_configure_lane(void __iomem *base,
 					const struct qmp_phy_init_tbl tbl[],
 					int num,
@@ -1826,6 +1909,9 @@ static const struct of_device_id qmp_ufs_of_match_table[] = {
 	}, {
 		.compatible = "qcom,sm8550-qmp-ufs-phy",
 		.data = &sm8550_ufsphy_cfg,
+	}, {
+		.compatible = "qcom,sm8650-qmp-ufs-phy",
+		.data = &sm8650_ufsphy_cfg,
 	},
 	{ },
 };
-- 
GitLab


From c954b6d347e78690f053342b2d2759c650e61a43 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:48:22 +0100
Subject: [PATCH 0144/4076] phy: qcom: qmp-pcie: add QMP PCIe PHY tables for
 SM8650

Add QMP PCIe PHY support for the SM8650 platform.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-phy-v2-6-a543a4c4b491@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 65 ++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index b64598ac59f4d..2af7115ef9689 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -1909,6 +1909,35 @@ static const struct qmp_phy_init_tbl sm8550_qmp_gen4x2_pcie_pcs_misc_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_FOM_EQ_CONFIG5, 0xf2),
 };
 
+static const struct qmp_phy_init_tbl sm8650_qmp_gen4x2_pcie_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_2, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_3, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_PI_CONTROLS, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_UCDR_SO_ACC_DEFAULT_VAL_RATE3, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_IVCM_CAL_CTRL2, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_3, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_GM_CAL, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_EQU_ADAPTOR_CNTRL4, 0x0b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_SIGDET_ENABLES, 0x1c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_PHPRE_CTRL, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B0, 0xd3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B1, 0xd3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B3, 0x9a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B4, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B5, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B6, 0xee),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B0, 0x23),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B1, 0x9b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B2, 0x60),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B3, 0xdf),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B4, 0x43),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B5, 0x76),
+	QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B6, 0xff),
+};
+
 static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_serdes_alt_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_COM_BIAS_EN_CLKBUFLR_EN, 0x14),
 	QMP_PHY_INIT_CFG(QSERDES_V5_COM_PLL_IVCO, 0x0f),
@@ -3047,6 +3076,36 @@ static const struct qmp_phy_cfg sm8550_qmp_gen4x2_pciephy_cfg = {
 	.has_nocsr_reset	= true,
 };
 
+static const struct qmp_phy_cfg sm8650_qmp_gen4x2_pciephy_cfg = {
+	.lanes = 2,
+
+	.offsets		= &qmp_pcie_offsets_v6_20,
+
+	.tbls = {
+		.serdes			= sm8550_qmp_gen4x2_pcie_serdes_tbl,
+		.serdes_num		= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_serdes_tbl),
+		.tx			= sm8550_qmp_gen4x2_pcie_tx_tbl,
+		.tx_num			= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_tx_tbl),
+		.rx			= sm8650_qmp_gen4x2_pcie_rx_tbl,
+		.rx_num			= ARRAY_SIZE(sm8650_qmp_gen4x2_pcie_rx_tbl),
+		.pcs			= sm8550_qmp_gen4x2_pcie_pcs_tbl,
+		.pcs_num		= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_pcs_tbl),
+		.pcs_misc		= sm8550_qmp_gen4x2_pcie_pcs_misc_tbl,
+		.pcs_misc_num		= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_pcs_misc_tbl),
+		.ln_shrd		= sm8550_qmp_gen4x2_pcie_ln_shrd_tbl,
+		.ln_shrd_num		= ARRAY_SIZE(sm8550_qmp_gen4x2_pcie_ln_shrd_tbl),
+	},
+	.reset_list		= sdm845_pciephy_reset_l,
+	.num_resets		= ARRAY_SIZE(sdm845_pciephy_reset_l),
+	.vreg_list		= sm8550_qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(sm8550_qmp_phy_vreg_l),
+	.regs			= pciephy_v5_regs_layout,
+
+	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
+	.phy_status		= PHYSTATUS_4_20,
+	.has_nocsr_reset	= true,
+};
+
 static const struct qmp_phy_cfg sa8775p_qmp_gen4x2_pciephy_cfg = {
 	.lanes			= 2,
 	.offsets		= &qmp_pcie_offsets_v5_20,
@@ -3820,6 +3879,12 @@ static const struct of_device_id qmp_pcie_of_match_table[] = {
 	}, {
 		.compatible = "qcom,sm8550-qmp-gen4x2-pcie-phy",
 		.data = &sm8550_qmp_gen4x2_pciephy_cfg,
+	}, {
+		.compatible = "qcom,sm8650-qmp-gen3x2-pcie-phy",
+		.data = &sm8550_qmp_gen3x2_pciephy_cfg,
+	}, {
+		.compatible = "qcom,sm8650-qmp-gen4x2-pcie-phy",
+		.data = &sm8650_qmp_gen4x2_pciephy_cfg,
 	},
 	{ },
 };
-- 
GitLab


From 80c1afe8c5fec68d9467c543551a0b2fddd463ff Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:48:23 +0100
Subject: [PATCH 0145/4076] phy: qcom: qmp-combo: add QMP USB3/DP PHY tables
 for SM8650

Add QMP USB3/DP Combo PHY support for the SM8650 platform.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-phy-v2-7-a543a4c4b491@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-combo.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
index 9c87845c78ec2..0417856b8e7bc 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
@@ -3558,6 +3558,10 @@ static const struct of_device_id qmp_combo_of_match_table[] = {
 		.compatible = "qcom,sm8550-qmp-usb3-dp-phy",
 		.data = &sm8550_usb3dpphy_cfg,
 	},
+	{
+		.compatible = "qcom,sm8650-qmp-usb3-dp-phy",
+		.data = &sm8550_usb3dpphy_cfg,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, qmp_combo_of_match_table);
-- 
GitLab


From 772dd70a5ed6845d87738f82c788c9ff4e37fd7f Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 1 Nov 2023 16:57:57 +0100
Subject: [PATCH 0146/4076] phy: core: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/d2323636c6cd2ec22f73a0ae6c2d34ac99b4abd5.1698854255.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/phy-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 96a0b1e111f34..d9be6a4d53838 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -959,7 +959,7 @@ struct phy *phy_create(struct device *dev, struct device_node *node,
 	if (!phy)
 		return ERR_PTR(-ENOMEM);
 
-	id = ida_simple_get(&phy_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&phy_ida, GFP_KERNEL);
 	if (id < 0) {
 		dev_err(dev, "unable to get id\n");
 		ret = id;
@@ -1232,7 +1232,7 @@ static void phy_release(struct device *dev)
 	dev_vdbg(dev, "releasing '%s'\n", dev_name(dev));
 	debugfs_remove_recursive(phy->debugfs);
 	regulator_put(phy->pwr);
-	ida_simple_remove(&phy_ida, phy->id);
+	ida_free(&phy_ida, phy->id);
 	kfree(phy);
 }
 
-- 
GitLab


From 182d44f9ce2d44a554432139c2d8026faddbe635 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Mon, 4 Sep 2023 17:23:11 +0800
Subject: [PATCH 0147/4076] MAINTAINERS: Remove myself as a Arm CoreSight
 reviewer

I haven't done any meaningful work for a long while on Arm CoreSight and
it's unlikely I'll be able to do related work in the future.

Remove myself from the Arm CoreSight "Reviewers" list.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20230904092311.389112-1-leo.yan@linaro.org
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cfd..485692a6ff4f1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2063,7 +2063,6 @@ ARM/CORESIGHT FRAMEWORK AND DRIVERS
 M:	Suzuki K Poulose <suzuki.poulose@arm.com>
 R:	Mike Leach <mike.leach@linaro.org>
 R:	James Clark <james.clark@arm.com>
-R:	Leo Yan <leo.yan@linaro.org>
 L:	coresight@lists.linaro.org (moderated for non-subscribers)
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-- 
GitLab


From 4277f035d227e829133df284be7e35b7236a5b0f Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Tue, 29 Aug 2023 19:24:04 +0530
Subject: [PATCH 0148/4076] coresight: trbe: Add a representative
 coresight_platform_data for TRBE

TRBE coresight devices do not need regular connections information, as the
paths get built between all percpu source and their respective percpu sink
devices. Please refer 'commit 2cd87a7b293d ("coresight: core: Add support
for dedicated percpu sinks")' which added support for percpu sink devices.

coresight_register() expect device connections via the platform_data. TRBE
devices do not have any graph connections and thus is empty. With upcoming
ACPI support for TRBE, we do not get a real acpi_device and thus
coresight_get_platform_dat() will end up in failures. Hence this allocates
a zeroed coresight_platform_data structure and assigns that back into the
device.

Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20230829135405.1159449-2-anshuman.khandual@arm.com
---
 drivers/hwtracing/coresight/coresight-trbe.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c
index e20c1c6acc731..97b9e72965e66 100644
--- a/drivers/hwtracing/coresight/coresight-trbe.c
+++ b/drivers/hwtracing/coresight/coresight-trbe.c
@@ -1253,8 +1253,18 @@ static void arm_trbe_register_coresight_cpu(struct trbe_drvdata *drvdata, int cp
 	desc.name = devm_kasprintf(dev, GFP_KERNEL, "trbe%d", cpu);
 	if (!desc.name)
 		goto cpu_clear;
-
-	desc.pdata = coresight_get_platform_data(dev);
+	/*
+	 * TRBE coresight devices do not need regular connections
+	 * information, as the paths get built between all percpu
+	 * source and their respective percpu sink devices. Though
+	 * coresight_register() expect device connections via the
+	 * platform_data, which TRBE devices do not have. As they
+	 * are not real ACPI devices, coresight_get_platform_data()
+	 * ends up failing. Instead let's allocate a dummy zeroed
+	 * coresight_platform_data structure and assign that back
+	 * into the device for that purpose.
+	 */
+	desc.pdata = devm_kzalloc(dev, sizeof(*desc.pdata), GFP_KERNEL);
 	if (IS_ERR(desc.pdata))
 		goto cpu_clear;
 
-- 
GitLab


From 17f8b216e02654a0b37127736ce78b32ccaa867b Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Tue, 29 Aug 2023 19:24:05 +0530
Subject: [PATCH 0149/4076] coresight: trbe: Enable ACPI based TRBE devices

This detects and enables ACPI based TRBE devices via the dummy platform
device created earlier for this purpose.

Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20230829135405.1159449-3-anshuman.khandual@arm.com
---
 drivers/hwtracing/coresight/coresight-trbe.c | 9 +++++++++
 drivers/hwtracing/coresight/coresight-trbe.h | 2 ++
 2 files changed, 11 insertions(+)

diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c
index 97b9e72965e66..a3954be7b1f3b 100644
--- a/drivers/hwtracing/coresight/coresight-trbe.c
+++ b/drivers/hwtracing/coresight/coresight-trbe.c
@@ -1546,7 +1546,16 @@ static const struct of_device_id arm_trbe_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, arm_trbe_of_match);
 
+#ifdef CONFIG_ACPI
+static const struct platform_device_id arm_trbe_acpi_match[] = {
+	{ ARMV8_TRBE_PDEV_NAME, 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, arm_trbe_acpi_match);
+#endif
+
 static struct platform_driver arm_trbe_driver = {
+	.id_table = ACPI_PTR(arm_trbe_acpi_match),
 	.driver	= {
 		.name = DRVNAME,
 		.of_match_table = of_match_ptr(arm_trbe_of_match),
diff --git a/drivers/hwtracing/coresight/coresight-trbe.h b/drivers/hwtracing/coresight/coresight-trbe.h
index e915e749be551..45202c48accec 100644
--- a/drivers/hwtracing/coresight/coresight-trbe.h
+++ b/drivers/hwtracing/coresight/coresight-trbe.h
@@ -7,11 +7,13 @@
  *
  * Author: Anshuman Khandual <anshuman.khandual@arm.com>
  */
+#include <linux/acpi.h>
 #include <linux/coresight.h>
 #include <linux/device.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 #include <linux/smp.h>
 
-- 
GitLab


From 4aff040bcc8de28bead01194cbca1dc9471a5a85 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Thu, 21 Sep 2023 09:06:29 +0530
Subject: [PATCH 0150/4076] coresight: etm: Override TRCIDR3.CCITMIN on errata
 affected cpus

This work arounds errata 1490853 on Cortex-A76, and Neoverse-N1, errata
1491015 on Cortex-A77, errata 1502854 on Cortex-X1, and errata 1619801 on
Neoverse-V1, based affected cpus, where software read for TRCIDR3.CCITMIN
field in ETM gets an wrong value.

If software uses the value returned by the TRCIDR3.CCITMIN register field,
then it will limit the range which could be used for programming the ETM.
In reality, the ETM could be programmed with a much smaller value than what
is indicated by the TRCIDR3.CCITMIN field and still function correctly.

If software reads the TRCIDR3.CCITMIN register field, corresponding to the
instruction trace counting minimum threshold, observe the value 0x100 or a
minimum cycle count threshold of 256. The correct value should be 0x4 or a
minimum cycle count threshold of 4.

This work arounds the problem via storing 4 in drvdata->ccitmin on affected
systems where the TRCIDR3.CCITMIN has been 256, thus preserving cycle count
threshold granularity.

These errata information has been updated in Documentation/arch/arm64/silicon-errata.rst,
but without their corresponding configs because these have been implemented
directly in the driver.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: James Clark <james.clark@arm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: linux-doc@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
[ Fixed location of silicon-errata.rst in commit description ]
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20230921033631.1298723-2-anshuman.khandual@arm.com
---
 Documentation/arch/arm64/silicon-errata.rst   | 10 +++++
 .../coresight/coresight-etm4x-core.c          | 37 +++++++++++++++++++
 2 files changed, 47 insertions(+)

diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index f47f63bcf67c9..bfdf236e2af3d 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -117,6 +117,10 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A76      | #1463225        | ARM64_ERRATUM_1463225       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A76      | #1490853        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A77      | #1491015        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A77      | #1508412        | ARM64_ERRATUM_1508412       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2119858        | ARM64_ERRATUM_2119858       |
@@ -127,6 +131,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A715     | #2645198        | ARM64_ERRATUM_2645198       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-X1       | #1502854        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2119858        | ARM64_ERRATUM_2119858       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2224489        | ARM64_ERRATUM_2224489       |
@@ -135,6 +141,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N1     | #1490853        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N2     | #2139208        | ARM64_ERRATUM_2139208       |
@@ -143,6 +151,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N2     | #2253138        | ARM64_ERRATUM_2253138       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-V1     | #1619801        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-600         | #1076982,1209401| N/A                         |
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c
index 34aee59dd1473..5feb2bd41ee59 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-core.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c
@@ -1150,6 +1150,41 @@ static void cpu_detect_trace_filtering(struct etmv4_drvdata *drvdata)
 	drvdata->trfcr = trfcr;
 }
 
+/*
+ * The following errata on applicable cpu ranges, affect the CCITMIN filed
+ * in TCRIDR3 register. Software read for the field returns 0x100 limiting
+ * the cycle threshold granularity, whereas the right value should have
+ * been 0x4, which is well supported in the hardware.
+ */
+static struct midr_range etm_wrong_ccitmin_cpus[] = {
+	/* Erratum #1490853 - Cortex-A76 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 4, 0),
+	/* Erratum #1490853 - Neoverse-N1 */
+	MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 4, 0),
+	/* Erratum #1491015 - Cortex-A77 */
+	MIDR_RANGE(MIDR_CORTEX_A77, 0, 0, 1, 0),
+	/* Erratum #1502854 - Cortex-X1 */
+	MIDR_REV(MIDR_CORTEX_X1, 0, 0),
+	/* Erratum #1619801 - Neoverse-V1 */
+	MIDR_REV(MIDR_NEOVERSE_V1, 0, 0),
+	{},
+};
+
+static void etm4_fixup_wrong_ccitmin(struct etmv4_drvdata *drvdata)
+{
+	/*
+	 * Erratum affected cpus will read 256 as the minimum
+	 * instruction trace cycle counting threshold whereas
+	 * the correct value should be 4 instead. Override the
+	 * recorded value for 'drvdata->ccitmin' to workaround
+	 * this problem.
+	 */
+	if (is_midr_in_range_list(read_cpuid_id(), etm_wrong_ccitmin_cpus)) {
+		if (drvdata->ccitmin == 256)
+			drvdata->ccitmin = 4;
+	}
+}
+
 static void etm4_init_arch_data(void *info)
 {
 	u32 etmidr0;
@@ -1214,6 +1249,8 @@ static void etm4_init_arch_data(void *info)
 	etmidr3 = etm4x_relaxed_read32(csa, TRCIDR3);
 	/* CCITMIN, bits[11:0] minimum threshold value that can be programmed */
 	drvdata->ccitmin = FIELD_GET(TRCIDR3_CCITMIN_MASK, etmidr3);
+	etm4_fixup_wrong_ccitmin(drvdata);
+
 	/* EXLEVEL_S, bits[19:16] Secure state instruction tracing */
 	drvdata->s_ex_level = FIELD_GET(TRCIDR3_EXLEVEL_S_MASK, etmidr3);
 	drvdata->config.s_ex_level = drvdata->s_ex_level;
-- 
GitLab


From 94566c5b07744c7cf5c7cc0ad42b15996ba0b054 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Thu, 21 Sep 2023 09:06:30 +0530
Subject: [PATCH 0151/4076] coresight: etm: Make cycle count threshold user
 configurable

When cycle counting is enabled, we use a default threshold value i.e 0x100
for the instruction trace cycle counting.

This patch makes the cycle threshold user configurable via perf event
attributes( 'cc_threshold' => event->attr.config3[11:0] ), falling back
to the current default if unspecified.

Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: James Clark <james.clark@arm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20230921033631.1298723-3-anshuman.khandual@arm.com
---
 drivers/hwtracing/coresight/coresight-etm-perf.c   | 2 ++
 drivers/hwtracing/coresight/coresight-etm4x-core.c | 9 +++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 89e8ed214ea49..a52cfcce25d6d 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -68,6 +68,7 @@ PMU_FORMAT_ATTR(preset,		"config:0-3");
 PMU_FORMAT_ATTR(sinkid,		"config2:0-31");
 /* config ID - set if a system configuration is selected */
 PMU_FORMAT_ATTR(configid,	"config2:32-63");
+PMU_FORMAT_ATTR(cc_threshold,	"config3:0-11");
 
 
 /*
@@ -101,6 +102,7 @@ static struct attribute *etm_config_formats_attr[] = {
 	&format_attr_preset.attr,
 	&format_attr_configid.attr,
 	&format_attr_branch_broadcast.attr,
+	&format_attr_cc_threshold.attr,
 	NULL,
 };
 
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c
index 5feb2bd41ee59..285539104bcc4 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-core.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c
@@ -644,7 +644,7 @@ static int etm4_parse_event_config(struct coresight_device *csdev,
 	struct etmv4_config *config = &drvdata->config;
 	struct perf_event_attr *attr = &event->attr;
 	unsigned long cfg_hash;
-	int preset;
+	int preset, cc_threshold;
 
 	/* Clear configuration from previous run */
 	memset(config, 0, sizeof(struct etmv4_config));
@@ -667,7 +667,12 @@ static int etm4_parse_event_config(struct coresight_device *csdev,
 	if (attr->config & BIT(ETM_OPT_CYCACC)) {
 		config->cfg |= TRCCONFIGR_CCI;
 		/* TRM: Must program this for cycacc to work */
-		config->ccctlr = ETM_CYC_THRESHOLD_DEFAULT;
+		cc_threshold = attr->config3 & ETM_CYC_THRESHOLD_MASK;
+		if (!cc_threshold)
+			cc_threshold = ETM_CYC_THRESHOLD_DEFAULT;
+		if (cc_threshold < drvdata->ccitmin)
+			cc_threshold = drvdata->ccitmin;
+		config->ccctlr = cc_threshold;
 	}
 	if (attr->config & BIT(ETM_OPT_TS)) {
 		/*
-- 
GitLab


From e5d207b24c54af25fb763af44e2db35347a0f7ee Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Thu, 21 Sep 2023 09:06:31 +0530
Subject: [PATCH 0152/4076] Documentation: coresight: Add cc_threshold tunable

This updates config option to include 'cc_threshold' tunable value.

Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: James Clark <james.clark@arm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20230921033631.1298723-4-anshuman.khandual@arm.com
---
 Documentation/trace/coresight/coresight.rst | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/trace/coresight/coresight.rst b/Documentation/trace/coresight/coresight.rst
index 826e59a698da1..d4f93d6a2d633 100644
--- a/Documentation/trace/coresight/coresight.rst
+++ b/Documentation/trace/coresight/coresight.rst
@@ -624,6 +624,10 @@ They are also listed in the folder /sys/bus/event_source/devices/cs_etm/format/
    * - timestamp
      - Session local version of the system wide setting: :ref:`ETMv4_MODE_TIMESTAMP
        <coresight-timestamp>`
+   * - cc_threshold
+     - Cycle count threshold value. If nothing is provided here or the provided value is 0, then the
+       default value i.e 0x100 will be used. If provided value is less than minimum cycles threshold
+       value, as indicated via TRCIDR3.CCITMIN, then the minimum value will be used instead.
 
 How to use the STM module
 -------------------------
-- 
GitLab


From 2373699a3505061cd21625c3f3b70dc3d03a3d8c Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Fri, 18 Aug 2023 13:51:12 +0530
Subject: [PATCH 0153/4076] coresight: tmc: Make etr buffer mode user
 configurable from sysfs

Currently TMC-ETR automatically selects the buffer mode from all available
methods in the following sequentially fallback manner - also in that order.

1. FLAT mode with or without IOMMU
2. TMC-ETR-SG (scatter gather) mode when available
3. CATU mode when available

But this order might not be ideal for all situations. For example if there
is a CATU connected to ETR, it may be better to use TMC-ETR scatter gather
method, rather than CATU. But hard coding such order changes will prevent
us from testing or using a particular mode. This change provides following
new sysfs tunables for the user to control TMC-ETR buffer mode explicitly,
if required. This adds following new sysfs files for buffer mode selection
purpose explicitly in the user space.

/sys/bus/coresight/devices/tmc_etr<N>/buf_modes_available
/sys/bus/coresight/devices/tmc_etr<N>/buf_mode_preferred

$ cat buf_modes_available
auto flat tmc-sg catu	------------------> Supported TMC-ETR buffer modes

$ echo catu > buf_mode_preferred   -------> Explicit buffer mode request

But explicit user request has to be within supported ETR buffer modes only.
These sysfs interface files are exclussive to ETR, and hence these are not
available for other TMC devices such as ETB or ETF etc.

A new auto' mode (i.e ETR_MODE_AUTO) has been added to help fallback to the
existing default behaviour, when user provided preferred buffer mode fails.
ETR_MODE_FLAT and ETR_MODE_AUTO are always available as preferred modes.

Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: James Clark <james.clark@arm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
[Fixup year in sysfs ABI documentation]
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20230818082112.554638-1-anshuman.khandual@arm.com
---
 .../testing/sysfs-bus-coresight-devices-tmc   |  16 +++
 .../hwtracing/coresight/coresight-tmc-core.c  |  15 ++-
 .../hwtracing/coresight/coresight-tmc-etr.c   | 111 ++++++++++++++++--
 drivers/hwtracing/coresight/coresight-tmc.h   |   3 +
 4 files changed, 131 insertions(+), 14 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
index 6aa527296c710..96aafa66b4a58 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
@@ -91,3 +91,19 @@ Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
 Description:	(RW) Size of the trace buffer for TMC-ETR when used in SYSFS
 		mode. Writable only for TMC-ETR configurations. The value
 		should be aligned to the kernel pagesize.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/buf_modes_available
+Date:		August 2023
+KernelVersion:	6.7
+Contact:	Anshuman Khandual <anshuman.khandual@arm.com>
+Description:	(Read) Shows all supported Coresight TMC-ETR buffer modes available
+		for the users to configure explicitly. This file is avaialble only
+		for TMC ETR devices.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/buf_mode_preferred
+Date:		August 2023
+KernelVersion:	6.7
+Contact:	Anshuman Khandual <anshuman.khandual@arm.com>
+Description:	(RW) Current Coresight TMC-ETR buffer mode selected. But user could
+		only provide a mode which is supported for a given ETR device. This
+		file is available only for TMC ETR devices.
diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c
index c106d142e6322..7ec5365e2b642 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-core.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-core.c
@@ -10,6 +10,7 @@
 #include <linux/device.h>
 #include <linux/idr.h>
 #include <linux/io.h>
+#include <linux/iommu.h>
 #include <linux/err.h>
 #include <linux/fs.h>
 #include <linux/miscdevice.h>
@@ -344,7 +345,14 @@ static const struct attribute_group coresight_tmc_mgmt_group = {
 	.name = "mgmt",
 };
 
-static const struct attribute_group *coresight_tmc_groups[] = {
+static const struct attribute_group *coresight_etf_groups[] = {
+	&coresight_tmc_group,
+	&coresight_tmc_mgmt_group,
+	NULL,
+};
+
+static const struct attribute_group *coresight_etr_groups[] = {
+	&coresight_etr_group,
 	&coresight_tmc_group,
 	&coresight_tmc_mgmt_group,
 	NULL,
@@ -465,6 +473,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	drvdata->memwidth = tmc_get_memwidth(devid);
 	/* This device is not associated with a session */
 	drvdata->pid = -1;
+	drvdata->etr_mode = ETR_MODE_AUTO;
 
 	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
 		drvdata->size = tmc_etr_get_default_buffer_size(dev);
@@ -474,16 +483,17 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	}
 
 	desc.dev = dev;
-	desc.groups = coresight_tmc_groups;
 
 	switch (drvdata->config_type) {
 	case TMC_CONFIG_TYPE_ETB:
+		desc.groups = coresight_etf_groups;
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.ops = &tmc_etb_cs_ops;
 		dev_list = &etb_devs;
 		break;
 	case TMC_CONFIG_TYPE_ETR:
+		desc.groups = coresight_etr_groups;
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM;
 		desc.ops = &tmc_etr_cs_ops;
@@ -496,6 +506,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_list = &etr_devs;
 		break;
 	case TMC_CONFIG_TYPE_ETF:
+		desc.groups = coresight_etf_groups;
 		desc.type = CORESIGHT_DEV_TYPE_LINKSINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO;
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 8311e1028ddb0..af02ba5d5f15d 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -26,6 +26,12 @@ struct etr_flat_buf {
 	size_t		size;
 };
 
+struct etr_buf_hw {
+	bool	has_iommu;
+	bool	has_etr_sg;
+	bool	has_catu;
+};
+
 /*
  * etr_perf_buffer - Perf buffer used for ETR
  * @drvdata		- The ETR drvdaga this buffer has been allocated for.
@@ -830,6 +836,22 @@ static inline int tmc_etr_mode_alloc_buf(int mode,
 	}
 }
 
+static void get_etr_buf_hw(struct device *dev, struct etr_buf_hw *buf_hw)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	buf_hw->has_iommu = iommu_get_domain_for_dev(dev->parent);
+	buf_hw->has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG);
+	buf_hw->has_catu = !!tmc_etr_get_catu_device(drvdata);
+}
+
+static bool etr_can_use_flat_mode(struct etr_buf_hw *buf_hw, ssize_t etr_buf_size)
+{
+	bool has_sg = buf_hw->has_catu || buf_hw->has_etr_sg;
+
+	return !has_sg || buf_hw->has_iommu || etr_buf_size < SZ_1M;
+}
+
 /*
  * tmc_alloc_etr_buf: Allocate a buffer use by ETR.
  * @drvdata	: ETR device details.
@@ -843,23 +865,22 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
 					 int node, void **pages)
 {
 	int rc = -ENOMEM;
-	bool has_etr_sg, has_iommu;
-	bool has_sg, has_catu;
 	struct etr_buf *etr_buf;
+	struct etr_buf_hw buf_hw;
 	struct device *dev = &drvdata->csdev->dev;
 
-	has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG);
-	has_iommu = iommu_get_domain_for_dev(dev->parent);
-	has_catu = !!tmc_etr_get_catu_device(drvdata);
-
-	has_sg = has_catu || has_etr_sg;
-
+	get_etr_buf_hw(dev, &buf_hw);
 	etr_buf = kzalloc(sizeof(*etr_buf), GFP_KERNEL);
 	if (!etr_buf)
 		return ERR_PTR(-ENOMEM);
 
 	etr_buf->size = size;
 
+	/* If there is user directive for buffer mode, try that first */
+	if (drvdata->etr_mode != ETR_MODE_AUTO)
+		rc = tmc_etr_mode_alloc_buf(drvdata->etr_mode, drvdata,
+					    etr_buf, node, pages);
+
 	/*
 	 * If we have to use an existing list of pages, we cannot reliably
 	 * use a contiguous DMA memory (even if we have an IOMMU). Otherwise,
@@ -872,14 +893,13 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
 	 * Fallback to available mechanisms.
 	 *
 	 */
-	if (!pages &&
-	    (!has_sg || has_iommu || size < SZ_1M))
+	if (rc && !pages && etr_can_use_flat_mode(&buf_hw, size))
 		rc = tmc_etr_mode_alloc_buf(ETR_MODE_FLAT, drvdata,
 					    etr_buf, node, pages);
-	if (rc && has_etr_sg)
+	if (rc && buf_hw.has_etr_sg)
 		rc = tmc_etr_mode_alloc_buf(ETR_MODE_ETR_SG, drvdata,
 					    etr_buf, node, pages);
-	if (rc && has_catu)
+	if (rc && buf_hw.has_catu)
 		rc = tmc_etr_mode_alloc_buf(ETR_MODE_CATU, drvdata,
 					    etr_buf, node, pages);
 	if (rc) {
@@ -1804,3 +1824,70 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
 
 	return 0;
 }
+
+static const char *const buf_modes_str[] = {
+	[ETR_MODE_FLAT]		= "flat",
+	[ETR_MODE_ETR_SG]	= "tmc-sg",
+	[ETR_MODE_CATU]		= "catu",
+	[ETR_MODE_AUTO]		= "auto",
+};
+
+static ssize_t buf_modes_available_show(struct device *dev,
+					    struct device_attribute *attr, char *buf)
+{
+	struct etr_buf_hw buf_hw;
+	ssize_t size = 0;
+
+	get_etr_buf_hw(dev, &buf_hw);
+	size += sysfs_emit(buf, "%s ", buf_modes_str[ETR_MODE_AUTO]);
+	size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_FLAT]);
+	if (buf_hw.has_etr_sg)
+		size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_ETR_SG]);
+
+	if (buf_hw.has_catu)
+		size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_CATU]);
+
+	size += sysfs_emit_at(buf, size, "\n");
+	return size;
+}
+static DEVICE_ATTR_RO(buf_modes_available);
+
+static ssize_t buf_mode_preferred_show(struct device *dev,
+					 struct device_attribute *attr, char *buf)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%s\n", buf_modes_str[drvdata->etr_mode]);
+}
+
+static ssize_t buf_mode_preferred_store(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t size)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etr_buf_hw buf_hw;
+
+	get_etr_buf_hw(dev, &buf_hw);
+	if (sysfs_streq(buf, buf_modes_str[ETR_MODE_FLAT]))
+		drvdata->etr_mode = ETR_MODE_FLAT;
+	else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_ETR_SG]) && buf_hw.has_etr_sg)
+		drvdata->etr_mode = ETR_MODE_ETR_SG;
+	else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_CATU]) && buf_hw.has_catu)
+		drvdata->etr_mode = ETR_MODE_CATU;
+	else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_AUTO]))
+		drvdata->etr_mode = ETR_MODE_AUTO;
+	else
+		return -EINVAL;
+	return size;
+}
+static DEVICE_ATTR_RW(buf_mode_preferred);
+
+static struct attribute *coresight_etr_attrs[] = {
+	&dev_attr_buf_modes_available.attr,
+	&dev_attr_buf_mode_preferred.attr,
+	NULL,
+};
+
+const struct attribute_group coresight_etr_group = {
+	.attrs = coresight_etr_attrs,
+};
diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h
index 0ee48c5ba764d..8dcb426ac3e7a 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.h
+++ b/drivers/hwtracing/coresight/coresight-tmc.h
@@ -135,6 +135,7 @@ enum etr_mode {
 	ETR_MODE_FLAT,		/* Uses contiguous flat buffer */
 	ETR_MODE_ETR_SG,	/* Uses in-built TMC ETR SG mechanism */
 	ETR_MODE_CATU,		/* Use SG mechanism in CATU */
+	ETR_MODE_AUTO,		/* Use the default mechanism */
 };
 
 struct etr_buf_operations;
@@ -207,6 +208,7 @@ struct tmc_drvdata {
 	enum tmc_mem_intf_width	memwidth;
 	u32			trigger_cntr;
 	u32			etr_caps;
+	enum etr_mode		etr_mode;
 	struct idr		idr;
 	struct mutex		idr_mutex;
 	struct etr_buf		*sysfs_buf;
@@ -334,5 +336,6 @@ void tmc_etr_set_catu_ops(const struct etr_buf_operations *catu);
 void tmc_etr_remove_catu_ops(void);
 struct etr_buf *tmc_etr_get_buffer(struct coresight_device *csdev,
 				   enum cs_mode mode, void *data);
+extern const struct attribute_group coresight_etr_group;
 
 #endif
-- 
GitLab


From f4443ee5a38cb84bdd0515f8832117b2be0684d6 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:34 +0800
Subject: [PATCH 0154/4076] coresight-tpdm: Remove the unnecessary lock

Remove the unnecessary lock "CS_{UN,}LOCK" in TPDM driver. This
lock is only needed while writing the data to Coresight registers.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-2-git-send-email-quic_taozha@quicinc.com
---
 drivers/hwtracing/coresight/coresight-tpdm.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index f4854af0431e1..b6456120b76a1 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -114,11 +114,9 @@ static void tpdm_init_default_data(struct tpdm_drvdata *drvdata)
 {
 	u32 pidr;
 
-	CS_UNLOCK(drvdata->base);
 	/*  Get the datasets present on the TPDM. */
 	pidr = readl_relaxed(drvdata->base + CORESIGHT_PERIPHIDR0);
 	drvdata->datasets |= pidr & GENMASK(TPDM_DATASETS - 1, 0);
-	CS_LOCK(drvdata->base);
 }
 
 /*
-- 
GitLab


From 2a8d9b371566e798421ef877c5757e2c4a11ad6f Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:35 +0800
Subject: [PATCH 0155/4076] dt-bindings: arm: Add support for DSB element size

Add property "qcom,dsb-elem-size" to support DSB(Discrete Single
Bit) element for TPDM. The associated aggregator will read this
size before it is enabled. DSB element size currently only
supports 32-bit and 64-bit.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-3-git-send-email-quic_taozha@quicinc.com
---
 .../devicetree/bindings/arm/qcom,coresight-tpdm.yaml   | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml b/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
index 3bad47b7b02bb..e19fc375d494e 100644
--- a/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
@@ -44,6 +44,14 @@ properties:
     minItems: 1
     maxItems: 2
 
+  qcom,dsb-element-size:
+    description:
+      Specifies the DSB(Discrete Single Bit) element size supported by
+      the monitor. The associated aggregator will read this size before it
+      is enabled. DSB element size currently only supports 32-bit and 64-bit.
+    $ref: /schemas/types.yaml#/definitions/uint8
+    enum: [32, 64]
+
   clocks:
     maxItems: 1
 
@@ -77,6 +85,8 @@ examples:
       compatible = "qcom,coresight-tpdm", "arm,primecell";
       reg = <0x0684c000 0x1000>;
 
+      qcom,dsb-element-size = /bits/ 8 <32>;
+
       clocks = <&aoss_qmp>;
       clock-names = "apb_pclk";
 
-- 
GitLab


From f7f965c982f7954b46db910146a7ffe0fe1eb5e1 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:36 +0800
Subject: [PATCH 0156/4076] coresight-tpdm: Introduce TPDM subtype to TPDM
 driver

Introduce the new subtype of "CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM"
for TPDM components in driver.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-4-git-send-email-quic_taozha@quicinc.com
---
 drivers/hwtracing/coresight/coresight-core.c | 3 +++
 drivers/hwtracing/coresight/coresight-tpdm.c | 2 +-
 include/linux/coresight.h                    | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index 9fabe00a40d6a..d7f0e231feb99 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -1093,6 +1093,7 @@ static int coresight_validate_source(struct coresight_device *csdev,
 
 	if (subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_PROC &&
 	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE &&
+	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM &&
 	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS) {
 		dev_err(&csdev->dev, "wrong device subtype in %s\n", function);
 		return -EINVAL;
@@ -1162,6 +1163,7 @@ int coresight_enable(struct coresight_device *csdev)
 		per_cpu(tracer_path, cpu) = path;
 		break;
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE:
+	case CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM:
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS:
 		/*
 		 * Use the hash of source's device name as ID
@@ -1212,6 +1214,7 @@ void coresight_disable(struct coresight_device *csdev)
 		per_cpu(tracer_path, cpu) = NULL;
 		break;
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE:
+	case CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM:
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS:
 		hash = hashlen_hash(hashlen_string(NULL, dev_name(&csdev->dev)));
 		/* Find the path by the hash. */
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index b6456120b76a1..abaff0b934dbd 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -203,7 +203,7 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 	if (!desc.name)
 		return -ENOMEM;
 	desc.type = CORESIGHT_DEV_TYPE_SOURCE;
-	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS;
+	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM;
 	desc.ops = &tpdm_cs_ops;
 	desc.pdata = adev->dev.platform_data;
 	desc.dev = &adev->dev;
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index a269fffaf991c..a4cb7dd6ca237 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -64,6 +64,7 @@ enum coresight_dev_subtype_source {
 	CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS,
 };
 
-- 
GitLab


From 57e7235aa1d11d4ea8a25dfdc009b3ee463763af Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:37 +0800
Subject: [PATCH 0157/4076] coresight-tpda: Add DSB dataset support

Read the DSB element size from the device tree. Set the register
bit that controls the DSB element size of the corresponding port.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-5-git-send-email-quic_taozha@quicinc.com
---
 drivers/hwtracing/coresight/coresight-tpda.c | 126 +++++++++++++++++--
 drivers/hwtracing/coresight/coresight-tpda.h |   2 +
 2 files changed, 118 insertions(+), 10 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-tpda.c b/drivers/hwtracing/coresight/coresight-tpda.c
index 8d2b9d29237d4..5f82737c37bba 100644
--- a/drivers/hwtracing/coresight/coresight-tpda.c
+++ b/drivers/hwtracing/coresight/coresight-tpda.c
@@ -21,6 +21,80 @@
 
 DEFINE_CORESIGHT_DEVLIST(tpda_devs, "tpda");
 
+static bool coresight_device_is_tpdm(struct coresight_device *csdev)
+{
+	return (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) &&
+	       (csdev->subtype.source_subtype ==
+			CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM);
+}
+
+/*
+ * Read the DSB element size from the TPDM device
+ * Returns
+ *    The dsb element size read from the devicetree if available.
+ *    0 - Otherwise, with a warning once.
+ */
+static int tpdm_read_dsb_element_size(struct coresight_device *csdev)
+{
+	int rc = 0;
+	u8 size = 0;
+
+	rc = fwnode_property_read_u8(dev_fwnode(csdev->dev.parent),
+			"qcom,dsb-element-size", &size);
+	if (rc)
+		dev_warn_once(&csdev->dev,
+			"Failed to read TPDM DSB Element size: %d\n", rc);
+
+	return size;
+}
+
+/*
+ * Search and read element data size from the TPDM node in
+ * the devicetree. Each input port of TPDA is connected to
+ * a TPDM. Different TPDM supports different types of dataset,
+ * and some may support more than one type of dataset.
+ * Parameter "inport" is used to pass in the input port number
+ * of TPDA, and it is set to -1 in the recursize call.
+ */
+static int tpda_get_element_size(struct coresight_device *csdev,
+				 int inport)
+{
+	int dsb_size = -ENOENT;
+	int i, size;
+	struct coresight_device *in;
+
+	for (i = 0; i < csdev->pdata->nr_inconns; i++) {
+		in = csdev->pdata->in_conns[i]->src_dev;
+		if (!in)
+			continue;
+
+		/* Ignore the paths that do not match port */
+		if (inport > 0 &&
+		    csdev->pdata->in_conns[i]->dest_port != inport)
+			continue;
+
+		if (coresight_device_is_tpdm(in)) {
+			size = tpdm_read_dsb_element_size(in);
+		} else {
+			/* Recurse down the path */
+			size = tpda_get_element_size(in, -1);
+		}
+
+		if (size < 0)
+			return size;
+
+		if (dsb_size < 0) {
+			/* Found a size, save it. */
+			dsb_size = size;
+		} else {
+			/* Found duplicate TPDMs */
+			return -EEXIST;
+		}
+	}
+
+	return dsb_size;
+}
+
 /* Settings pre enabling port control register */
 static void tpda_enable_pre_port(struct tpda_drvdata *drvdata)
 {
@@ -32,26 +106,55 @@ static void tpda_enable_pre_port(struct tpda_drvdata *drvdata)
 	writel_relaxed(val, drvdata->base + TPDA_CR);
 }
 
-static void tpda_enable_port(struct tpda_drvdata *drvdata, int port)
+static int tpda_enable_port(struct tpda_drvdata *drvdata, int port)
 {
 	u32 val;
+	int size;
 
 	val = readl_relaxed(drvdata->base + TPDA_Pn_CR(port));
+	/*
+	 * Configure aggregator port n DSB data set element size
+	 * Set the bit to 0 if the size is 32
+	 * Set the bit to 1 if the size is 64
+	 */
+	size = tpda_get_element_size(drvdata->csdev, port);
+	switch (size) {
+	case 32:
+		val &= ~TPDA_Pn_CR_DSBSIZE;
+		break;
+	case 64:
+		val |= TPDA_Pn_CR_DSBSIZE;
+		break;
+	case 0:
+		return -EEXIST;
+	case -EEXIST:
+		dev_warn_once(&drvdata->csdev->dev,
+			"Detected multiple TPDMs on port %d", -EEXIST);
+		return -EEXIST;
+	default:
+		return -EINVAL;
+	}
+
 	/* Enable the port */
 	val |= TPDA_Pn_CR_ENA;
 	writel_relaxed(val, drvdata->base + TPDA_Pn_CR(port));
+
+	return 0;
 }
 
-static void __tpda_enable(struct tpda_drvdata *drvdata, int port)
+static int __tpda_enable(struct tpda_drvdata *drvdata, int port)
 {
+	int ret;
+
 	CS_UNLOCK(drvdata->base);
 
 	if (!drvdata->csdev->enable)
 		tpda_enable_pre_port(drvdata);
 
-	tpda_enable_port(drvdata, port);
-
+	ret = tpda_enable_port(drvdata, port);
 	CS_LOCK(drvdata->base);
+
+	return ret;
 }
 
 static int tpda_enable(struct coresight_device *csdev,
@@ -59,16 +162,19 @@ static int tpda_enable(struct coresight_device *csdev,
 		       struct coresight_connection *out)
 {
 	struct tpda_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret = 0;
 
 	spin_lock(&drvdata->spinlock);
-	if (atomic_read(&in->dest_refcnt) == 0)
-		__tpda_enable(drvdata, in->dest_port);
+	if (atomic_read(&in->dest_refcnt) == 0) {
+		ret = __tpda_enable(drvdata, in->dest_port);
+		if (!ret) {
+			atomic_inc(&in->dest_refcnt);
+			dev_dbg(drvdata->dev, "TPDA inport %d enabled.\n", in->dest_port);
+		}
+	}
 
-	atomic_inc(&in->dest_refcnt);
 	spin_unlock(&drvdata->spinlock);
-
-	dev_dbg(drvdata->dev, "TPDA inport %d enabled.\n", in->dest_port);
-	return 0;
+	return ret;
 }
 
 static void __tpda_disable(struct tpda_drvdata *drvdata, int port)
diff --git a/drivers/hwtracing/coresight/coresight-tpda.h b/drivers/hwtracing/coresight/coresight-tpda.h
index 0399678df312f..b3b38fd41b64b 100644
--- a/drivers/hwtracing/coresight/coresight-tpda.h
+++ b/drivers/hwtracing/coresight/coresight-tpda.h
@@ -10,6 +10,8 @@
 #define TPDA_Pn_CR(n)		(0x004 + (n * 4))
 /* Aggregator port enable bit */
 #define TPDA_Pn_CR_ENA		BIT(0)
+/* Aggregator port DSB data set element size bit */
+#define TPDA_Pn_CR_DSBSIZE		BIT(8)
 
 #define TPDA_MAX_INPORTS	32
 
-- 
GitLab


From f01e4948b516f073c353041328ae7cf709233303 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:38 +0800
Subject: [PATCH 0158/4076] coresight-tpdm: Initialize DSB subunit
 configuration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DSB is used for monitoring “events”. Events are something that
occurs at some point in time. It could be a state decode, the
act of writing/reading a particular address, a FIFO being empty,
etc. This decoding of the event desired is done outside TPDM.
DSB subunit need to be configured in enablement and disablement.
A struct that specifics associated to dsb dataset is needed. It
saves the configuration and parameters of the dsb datasets. This
change is to add this struct and initialize the configuration of
DSB subunit.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-6-git-send-email-quic_taozha@quicinc.com
---
 drivers/hwtracing/coresight/coresight-tpdm.c | 64 +++++++++++++++++---
 drivers/hwtracing/coresight/coresight-tpdm.h | 18 ++++++
 2 files changed, 74 insertions(+), 8 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index abaff0b934dbd..951ad4d9b76fb 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -20,23 +20,57 @@
 
 DEFINE_CORESIGHT_DEVLIST(tpdm_devs, "tpdm");
 
+static bool tpdm_has_dsb_dataset(struct tpdm_drvdata *drvdata)
+{
+	return (drvdata->datasets & TPDM_PIDR0_DS_DSB);
+}
+
+static void tpdm_reset_datasets(struct tpdm_drvdata *drvdata)
+{
+	if (tpdm_has_dsb_dataset(drvdata)) {
+		memset(drvdata->dsb, 0, sizeof(struct dsb_dataset));
+
+		drvdata->dsb->trig_ts = true;
+		drvdata->dsb->trig_type = false;
+	}
+}
+
 static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 {
 	u32 val;
 
-	/* Set the enable bit of DSB control register to 1 */
+	val = readl_relaxed(drvdata->base + TPDM_DSB_TIER);
+	/* Set trigger timestamp */
+	if (drvdata->dsb->trig_ts)
+		val |= TPDM_DSB_TIER_XTRIG_TSENAB;
+	else
+		val &= ~TPDM_DSB_TIER_XTRIG_TSENAB;
+	writel_relaxed(val, drvdata->base + TPDM_DSB_TIER);
+
 	val = readl_relaxed(drvdata->base + TPDM_DSB_CR);
+	/* Set trigger type */
+	if (drvdata->dsb->trig_type)
+		val |= TPDM_DSB_CR_TRIG_TYPE;
+	else
+		val &= ~TPDM_DSB_CR_TRIG_TYPE;
+	/* Set the enable bit of DSB control register to 1 */
 	val |= TPDM_DSB_CR_ENA;
 	writel_relaxed(val, drvdata->base + TPDM_DSB_CR);
 }
 
-/* TPDM enable operations */
+/*
+ * TPDM enable operations
+ * The TPDM or Monitor serves as data collection component for various
+ * dataset types. It covers Basic Counts(BC), Tenure Counts(TC),
+ * Continuous Multi-Bit(CMB), Multi-lane CMB(MCMB) and Discrete Single
+ * Bit(DSB). This function will initialize the configuration according
+ * to the dataset type supported by the TPDM.
+ */
 static void __tpdm_enable(struct tpdm_drvdata *drvdata)
 {
 	CS_UNLOCK(drvdata->base);
 
-	/* Check if DSB datasets is present for TPDM. */
-	if (drvdata->datasets & TPDM_PIDR0_DS_DSB)
+	if (tpdm_has_dsb_dataset(drvdata))
 		tpdm_enable_dsb(drvdata);
 
 	CS_LOCK(drvdata->base);
@@ -76,8 +110,7 @@ static void __tpdm_disable(struct tpdm_drvdata *drvdata)
 {
 	CS_UNLOCK(drvdata->base);
 
-	/* Check if DSB datasets is present for TPDM. */
-	if (drvdata->datasets & TPDM_PIDR0_DS_DSB)
+	if (tpdm_has_dsb_dataset(drvdata))
 		tpdm_disable_dsb(drvdata);
 
 	CS_LOCK(drvdata->base);
@@ -110,13 +143,23 @@ static const struct coresight_ops tpdm_cs_ops = {
 	.source_ops	= &tpdm_source_ops,
 };
 
-static void tpdm_init_default_data(struct tpdm_drvdata *drvdata)
+static int tpdm_datasets_setup(struct tpdm_drvdata *drvdata)
 {
 	u32 pidr;
 
 	/*  Get the datasets present on the TPDM. */
 	pidr = readl_relaxed(drvdata->base + CORESIGHT_PERIPHIDR0);
 	drvdata->datasets |= pidr & GENMASK(TPDM_DATASETS - 1, 0);
+
+	if (tpdm_has_dsb_dataset(drvdata) && (!drvdata->dsb)) {
+		drvdata->dsb = devm_kzalloc(drvdata->dev,
+						sizeof(*drvdata->dsb), GFP_KERNEL);
+		if (!drvdata->dsb)
+			return -ENOMEM;
+	}
+	tpdm_reset_datasets(drvdata);
+
+	return 0;
 }
 
 /*
@@ -179,6 +222,7 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 	struct coresight_platform_data *pdata;
 	struct tpdm_drvdata *drvdata;
 	struct coresight_desc desc = { 0 };
+	int ret;
 
 	pdata = coresight_get_platform_data(dev);
 	if (IS_ERR(pdata))
@@ -198,6 +242,10 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	drvdata->base = base;
 
+	ret = tpdm_datasets_setup(drvdata);
+	if (ret)
+		return ret;
+
 	/* Set up coresight component description */
 	desc.name = coresight_alloc_device_name(&tpdm_devs, dev);
 	if (!desc.name)
@@ -214,7 +262,7 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 		return PTR_ERR(drvdata->csdev);
 
 	spin_lock_init(&drvdata->spinlock);
-	tpdm_init_default_data(drvdata);
+
 	/* Decrease pm refcount when probe is done.*/
 	pm_runtime_put(&adev->dev);
 
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h
index 543854043a2dd..f59e751d35816 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.h
+++ b/drivers/hwtracing/coresight/coresight-tpdm.h
@@ -11,8 +11,14 @@
 
 /* DSB Subunit Registers */
 #define TPDM_DSB_CR		(0x780)
+#define TPDM_DSB_TIER		(0x784)
+
 /* Enable bit for DSB subunit */
 #define TPDM_DSB_CR_ENA		BIT(0)
+/* Enable bit for DSB subunit trigger type */
+#define TPDM_DSB_CR_TRIG_TYPE		BIT(12)
+/* Enable bit for DSB subunit trigger timestamp */
+#define TPDM_DSB_TIER_XTRIG_TSENAB		BIT(1)
 
 /* TPDM integration test registers */
 #define TPDM_ITATBCNTRL		(0xEF0)
@@ -40,6 +46,16 @@
 #define TPDM_PIDR0_DS_IMPDEF	BIT(0)
 #define TPDM_PIDR0_DS_DSB	BIT(1)
 
+/**
+ * struct dsb_dataset - specifics associated to dsb dataset
+ * @trig_ts:          Enable/Disable trigger timestamp.
+ * @trig_type:        Enable/Disable trigger type.
+ */
+struct dsb_dataset {
+	bool			trig_ts;
+	bool			trig_type;
+};
+
 /**
  * struct tpdm_drvdata - specifics associated to an TPDM component
  * @base:       memory mapped base address for this component.
@@ -48,6 +64,7 @@
  * @spinlock:   lock for the drvdata value.
  * @enable:     enable status of the component.
  * @datasets:   The datasets types present of the TPDM.
+ * @dsb         Specifics associated to TPDM DSB.
  */
 
 struct tpdm_drvdata {
@@ -57,6 +74,7 @@ struct tpdm_drvdata {
 	spinlock_t		spinlock;
 	bool			enable;
 	unsigned long		datasets;
+	struct dsb_dataset	*dsb;
 };
 
 #endif  /* _CORESIGHT_CORESIGHT_TPDM_H */
-- 
GitLab


From 8fbbce11a90f345a1ff39e2a08e312ee763a1139 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:39 +0800
Subject: [PATCH 0159/4076] coresight-tpdm: Add reset node to TPDM node

TPDM device need a node to reset the configurations and status of
it. This change provides a node to reset the configurations and
disable the TPDM if it has been enabled.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-7-git-send-email-quic_taozha@quicinc.com
---
 .../testing/sysfs-bus-coresight-devices-tpdm  | 10 +++++++++
 drivers/hwtracing/coresight/coresight-tpdm.c  | 22 +++++++++++++++++++
 2 files changed, 32 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index 4a58e649550d5..ef8b5a6bd4ac4 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -11,3 +11,13 @@ Description:
 		Accepts only one of the 2 values -  1 or 2.
 		1 : Generate 64 bits data
 		2 : Generate 32 bits data
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/reset_dataset
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(Write) Reset the dataset of the tpdm.
+
+		Accepts only one value -  1.
+		1 : Reset the dataset of the tpdm
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index 951ad4d9b76fb..9c65e4c01128c 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -162,6 +162,27 @@ static int tpdm_datasets_setup(struct tpdm_drvdata *drvdata)
 	return 0;
 }
 
+static ssize_t reset_dataset_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf,
+				   size_t size)
+{
+	int ret = 0;
+	unsigned long val;
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret || val != 1)
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	tpdm_reset_datasets(drvdata);
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_WO(reset_dataset);
+
 /*
  * value 1: 64 bits test data
  * value 2: 32 bits test data
@@ -202,6 +223,7 @@ static ssize_t integration_test_store(struct device *dev,
 static DEVICE_ATTR_WO(integration_test);
 
 static struct attribute *tpdm_attrs[] = {
+	&dev_attr_reset_dataset.attr,
 	&dev_attr_integration_test.attr,
 	NULL,
 };
-- 
GitLab


From 851b3f9c9c0838060158e288c1387d44652c54b5 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:40 +0800
Subject: [PATCH 0160/4076] coresight-tpdm: Add nodes to set trigger timestamp
 and type

The nodes are needed to set or show the trigger timestamp and
trigger type. This change is to add these nodes to achieve these
function.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-8-git-send-email-quic_taozha@quicinc.com
---
 .../testing/sysfs-bus-coresight-devices-tpdm  | 22 +++++
 drivers/hwtracing/coresight/coresight-tpdm.c  | 95 +++++++++++++++++++
 2 files changed, 117 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index ef8b5a6bd4ac4..b15bf012a050a 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -21,3 +21,25 @@ Description:
 
 		Accepts only one value -  1.
 		1 : Reset the dataset of the tpdm
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_trig_type
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the trigger type of the DSB for tpdm.
+
+		Accepts only one of the 2 values -  0 or 1.
+		0 : Set the DSB trigger type to false
+		1 : Set the DSB trigger type to true
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_trig_ts
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the trigger timestamp of the DSB for tpdm.
+
+		Accepts only one of the 2 values -  0 or 1.
+		0 : Set the DSB trigger type to false
+		1 : Set the DSB trigger type to true
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index 9c65e4c01128c..e9fc3482d480a 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -25,6 +25,18 @@ static bool tpdm_has_dsb_dataset(struct tpdm_drvdata *drvdata)
 	return (drvdata->datasets & TPDM_PIDR0_DS_DSB);
 }
 
+static umode_t tpdm_dsb_is_visible(struct kobject *kobj,
+				   struct attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (drvdata && tpdm_has_dsb_dataset(drvdata))
+		return attr->mode;
+
+	return 0;
+}
+
 static void tpdm_reset_datasets(struct tpdm_drvdata *drvdata)
 {
 	if (tpdm_has_dsb_dataset(drvdata)) {
@@ -232,8 +244,91 @@ static struct attribute_group tpdm_attr_grp = {
 	.attrs = tpdm_attrs,
 };
 
+static ssize_t dsb_trig_type_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			 (unsigned int)drvdata->dsb->trig_type);
+}
+
+/*
+ * Trigger type (boolean):
+ * false - Disable trigger type.
+ * true  - Enable trigger type.
+ */
+static ssize_t dsb_trig_type_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf,
+				   size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	if (val)
+		drvdata->dsb->trig_type = true;
+	else
+		drvdata->dsb->trig_type = false;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(dsb_trig_type);
+
+static ssize_t dsb_trig_ts_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			 (unsigned int)drvdata->dsb->trig_ts);
+}
+
+/*
+ * Trigger timestamp (boolean):
+ * false - Disable trigger timestamp.
+ * true  - Enable trigger timestamp.
+ */
+static ssize_t dsb_trig_ts_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf,
+				 size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	if (val)
+		drvdata->dsb->trig_ts = true;
+	else
+		drvdata->dsb->trig_ts = false;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(dsb_trig_ts);
+
+static struct attribute *tpdm_dsb_attrs[] = {
+	&dev_attr_dsb_trig_ts.attr,
+	&dev_attr_dsb_trig_type.attr,
+	NULL,
+};
+
+static struct attribute_group tpdm_dsb_attr_grp = {
+	.attrs = tpdm_dsb_attrs,
+	.is_visible = tpdm_dsb_is_visible,
+};
+
 static const struct attribute_group *tpdm_attr_grps[] = {
 	&tpdm_attr_grp,
+	&tpdm_dsb_attr_grp,
 	NULL,
 };
 
-- 
GitLab


From 018e43ad1eeefbb8797e4c933953c50c09e3f4f6 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:41 +0800
Subject: [PATCH 0161/4076] coresight-tpdm: Add node to set dsb programming
 mode

Add node to set and show programming mode for TPDM DSB subunit.
Once the DSB programming mode is set, it will be written to the
register DSB_CR.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-9-git-send-email-quic_taozha@quicinc.com
---
 .../testing/sysfs-bus-coresight-devices-tpdm  | 14 +++++
 drivers/hwtracing/coresight/coresight-tpdm.c  | 53 +++++++++++++++++++
 drivers/hwtracing/coresight/coresight-tpdm.h  | 19 +++++++
 3 files changed, 86 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index b15bf012a050a..8ec7548070b7b 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -43,3 +43,17 @@ Description:
 		Accepts only one of the 2 values -  0 or 1.
 		0 : Set the DSB trigger type to false
 		1 : Set the DSB trigger type to true
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_mode
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the programming mode of the DSB for tpdm.
+
+		Accepts the value needs to be greater than 0. What data
+		bits do is listed below.
+		Bit[0:1] : Test mode control bit for choosing the inputs.
+		Bit[3] : Set to 0 for low performance mode.
+				 Set to 1 for high performance mode.
+		Bit[4:8] : Select byte lane for high performance mode.
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index e9fc3482d480a..6201f12718ca6 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/amba/bus.h>
+#include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/coresight.h>
 #include <linux/coresight-pmu.h>
@@ -47,6 +48,27 @@ static void tpdm_reset_datasets(struct tpdm_drvdata *drvdata)
 	}
 }
 
+static void set_dsb_mode(struct tpdm_drvdata *drvdata, u32 *val)
+{
+	u32 mode;
+
+	/* Set the test accurate mode */
+	mode = TPDM_DSB_MODE_TEST(drvdata->dsb->mode);
+	*val &= ~TPDM_DSB_CR_TEST_MODE;
+	*val |= FIELD_PREP(TPDM_DSB_CR_TEST_MODE, mode);
+
+	/* Set the byte lane for high-performance mode */
+	mode = TPDM_DSB_MODE_HPBYTESEL(drvdata->dsb->mode);
+	*val &= ~TPDM_DSB_CR_HPSEL;
+	*val |= FIELD_PREP(TPDM_DSB_CR_HPSEL, mode);
+
+	/* Set the performance mode */
+	if (drvdata->dsb->mode & TPDM_DSB_MODE_PERF)
+		*val |= TPDM_DSB_CR_MODE;
+	else
+		*val &= ~TPDM_DSB_CR_MODE;
+}
+
 static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 {
 	u32 val;
@@ -60,6 +82,8 @@ static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 	writel_relaxed(val, drvdata->base + TPDM_DSB_TIER);
 
 	val = readl_relaxed(drvdata->base + TPDM_DSB_CR);
+	/* Set the mode of DSB dataset */
+	set_dsb_mode(drvdata, &val);
 	/* Set trigger type */
 	if (drvdata->dsb->trig_type)
 		val |= TPDM_DSB_CR_TRIG_TYPE;
@@ -244,6 +268,34 @@ static struct attribute_group tpdm_attr_grp = {
 	.attrs = tpdm_attrs,
 };
 
+static ssize_t dsb_mode_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%x\n", drvdata->dsb->mode);
+}
+
+static ssize_t dsb_mode_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf,
+			      size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val < 0) ||
+			(val & ~TPDM_DSB_MODE_MASK))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->dsb->mode = val & TPDM_DSB_MODE_MASK;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(dsb_mode);
+
 static ssize_t dsb_trig_type_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
@@ -316,6 +368,7 @@ static ssize_t dsb_trig_ts_store(struct device *dev,
 static DEVICE_ATTR_RW(dsb_trig_ts);
 
 static struct attribute *tpdm_dsb_attrs[] = {
+	&dev_attr_dsb_mode.attr,
 	&dev_attr_dsb_trig_ts.attr,
 	&dev_attr_dsb_trig_type.attr,
 	NULL,
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h
index f59e751d35816..b55d6f5ce8520 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.h
+++ b/drivers/hwtracing/coresight/coresight-tpdm.h
@@ -15,11 +15,28 @@
 
 /* Enable bit for DSB subunit */
 #define TPDM_DSB_CR_ENA		BIT(0)
+/* Enable bit for DSB subunit perfmance mode */
+#define TPDM_DSB_CR_MODE		BIT(1)
 /* Enable bit for DSB subunit trigger type */
 #define TPDM_DSB_CR_TRIG_TYPE		BIT(12)
+/* Data bits for DSB high performace mode */
+#define TPDM_DSB_CR_HPSEL		GENMASK(6, 2)
+/* Data bits for DSB test mode */
+#define TPDM_DSB_CR_TEST_MODE		GENMASK(10, 9)
+
 /* Enable bit for DSB subunit trigger timestamp */
 #define TPDM_DSB_TIER_XTRIG_TSENAB		BIT(1)
 
+/* DSB programming modes */
+/* DSB mode bits mask */
+#define TPDM_DSB_MODE_MASK			GENMASK(8, 0)
+/* Test mode control bit*/
+#define TPDM_DSB_MODE_TEST(val)	(val & GENMASK(1, 0))
+/* Performance mode */
+#define TPDM_DSB_MODE_PERF		BIT(3)
+/* High performance mode */
+#define TPDM_DSB_MODE_HPBYTESEL(val)	(val & GENMASK(8, 4))
+
 /* TPDM integration test registers */
 #define TPDM_ITATBCNTRL		(0xEF0)
 #define TPDM_ITCNTRL		(0xF00)
@@ -48,10 +65,12 @@
 
 /**
  * struct dsb_dataset - specifics associated to dsb dataset
+ * @mode:             DSB programming mode
  * @trig_ts:          Enable/Disable trigger timestamp.
  * @trig_type:        Enable/Disable trigger type.
  */
 struct dsb_dataset {
+	u32			mode;
 	bool			trig_ts;
 	bool			trig_type;
 };
-- 
GitLab


From f376caf25f79965ab140b7a297cb4a5bb0c89523 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:42 +0800
Subject: [PATCH 0162/4076] coresight-tpdm: Add nodes for dsb edge control

Add the nodes to set value for DSB edge control and DSB edge
control mask. Each DSB subunit TPDM has maximum of n(n<16) EDCR
resgisters to configure edge control. DSB edge detection control
00: Rising edge detection
01: Falling edge detection
10: Rising and falling edge detection (toggle detection)
And each DSB subunit TPDM has maximum of m(m<8) ECDMR registers to
configure mask. Eight 32 bit registers providing DSB interface
edge detection mask control.

Add the nodes to configure DSB edge control and DSB edge control
mask. Each DSB subunit TPDM maximum of 256 edge detections can be
configured. The index and value sysfs files need to be paired and
written to order. The index sysfs file is to set the index number
of the edge detection which needs to be configured. And the value
sysfs file is to set the control or mask for the edge detection.
DSB edge detection control should be set as the following values.
00: Rising edge detection
01: Falling edge detection
10: Rising and falling edge detection (toggle detection)
And DSB edge mask should be set as 0 or 1.
Each DSB subunit TPDM has maximum of n(n<16) EDCR resgisters to
configure edge control. And each DSB subunit TPDM has maximum of
m(m<8) ECDMR registers to configure mask.

Add the nodes to read a set of the edge control value and mask
of the DSB in TPDM.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-10-git-send-email-quic_taozha@quicinc.com
---
 .../testing/sysfs-bus-coresight-devices-tpdm  |  51 +++++
 drivers/hwtracing/coresight/coresight-tpdm.c  | 174 +++++++++++++++++-
 drivers/hwtracing/coresight/coresight-tpdm.h  |  60 ++++++
 3 files changed, 284 insertions(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index 8ec7548070b7b..6853bb1295e30 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -57,3 +57,54 @@ Description:
 		Bit[3] : Set to 0 for low performance mode.
 				 Set to 1 for high performance mode.
 		Bit[4:8] : Select byte lane for high performance mode.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/ctrl_idx
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the index number of the edge detection for the DSB
+		subunit TPDM. Since there are at most 256 edge detections, this
+		value ranges from 0 to 255.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/ctrl_val
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		Write a data to control the edge detection corresponding to
+		the index number. Before writing data to this sysfs file,
+		"ctrl_idx" should be written first to configure the index
+		number of the edge detection which needs to be controlled.
+
+		Accepts only one of the following values.
+		0 - Rising edge detection
+		1 - Falling edge detection
+		2 - Rising and falling edge detection (toggle detection)
+
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/ctrl_mask
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		Write a data to mask the edge detection corresponding to the index
+		number. Before writing data to this sysfs file, "ctrl_idx" should
+		be written first to configure the index number of the edge detection
+		which needs to be masked.
+
+		Accepts only one of the 2 values -  0 or 1.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/edcr[0:15]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		Read a set of the edge control value of the DSB in TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/edcmr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		Read a set of the edge control mask of the DSB in TPDM.
\ No newline at end of file
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index 6201f12718ca6..7175e70c2c4e0 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -21,6 +21,30 @@
 
 DEFINE_CORESIGHT_DEVLIST(tpdm_devs, "tpdm");
 
+/* Read dataset array member with the index number */
+static ssize_t tpdm_simple_dataset_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct tpdm_dataset_attribute *tpdm_attr =
+		container_of(attr, struct tpdm_dataset_attribute, attr);
+
+	switch (tpdm_attr->mem) {
+	case DSB_EDGE_CTRL:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_EDCR)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->edge_ctrl[tpdm_attr->idx]);
+	case DSB_EDGE_CTRL_MASK:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_EDCMR)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->edge_ctrl_mask[tpdm_attr->idx]);
+	}
+	return -EINVAL;
+}
+
 static bool tpdm_has_dsb_dataset(struct tpdm_drvdata *drvdata)
 {
 	return (drvdata->datasets & TPDM_PIDR0_DS_DSB);
@@ -71,7 +95,14 @@ static void set_dsb_mode(struct tpdm_drvdata *drvdata, u32 *val)
 
 static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 {
-	u32 val;
+	u32 val, i;
+
+	for (i = 0; i < TPDM_DSB_MAX_EDCR; i++)
+		writel_relaxed(drvdata->dsb->edge_ctrl[i],
+			   drvdata->base + TPDM_DSB_EDCR(i));
+	for (i = 0; i < TPDM_DSB_MAX_EDCMR; i++)
+		writel_relaxed(drvdata->dsb->edge_ctrl_mask[i],
+			   drvdata->base + TPDM_DSB_EDCMR(i));
 
 	val = readl_relaxed(drvdata->base + TPDM_DSB_TIER);
 	/* Set trigger timestamp */
@@ -296,6 +327,109 @@ static ssize_t dsb_mode_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(dsb_mode);
 
+static ssize_t ctrl_idx_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			(unsigned int)drvdata->dsb->edge_ctrl_idx);
+}
+
+/*
+ * The EDCR registers can include up to 16 32-bit registers, and each
+ * one can be configured to control up to 16 edge detections(2 bits
+ * control one edge detection). So a total 256 edge detections can be
+ * configured. This function provides a way to set the index number of
+ * the edge detection which needs to be configured.
+ */
+static ssize_t ctrl_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf,
+			      size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val >= TPDM_DSB_MAX_LINES))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->dsb->edge_ctrl_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctrl_idx);
+
+/*
+ * This function is used to control the edge detection according
+ * to the index number that has been set.
+ * "edge_ctrl" should be one of the following values.
+ * 0 - Rising edge detection
+ * 1 - Falling edge detection
+ * 2 - Rising and falling edge detection (toggle detection)
+ */
+static ssize_t ctrl_val_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf,
+			      size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val, edge_ctrl;
+	int reg;
+
+	if ((kstrtoul(buf, 0, &edge_ctrl)) || (edge_ctrl > 0x2))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	/*
+	 * There are 2 bit per DSB Edge Control line.
+	 * Thus we have 16 lines in a 32bit word.
+	 */
+	reg = EDCR_TO_WORD_IDX(drvdata->dsb->edge_ctrl_idx);
+	val = drvdata->dsb->edge_ctrl[reg];
+	val &= ~EDCR_TO_WORD_MASK(drvdata->dsb->edge_ctrl_idx);
+	val |= EDCR_TO_WORD_VAL(edge_ctrl, drvdata->dsb->edge_ctrl_idx);
+	drvdata->dsb->edge_ctrl[reg] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_WO(ctrl_val);
+
+static ssize_t ctrl_mask_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf,
+			       size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+	u32 set;
+	int reg;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	/*
+	 * There is 1 bit per DSB Edge Control Mark line.
+	 * Thus we have 32 lines in a 32bit word.
+	 */
+	reg = EDCMR_TO_WORD_IDX(drvdata->dsb->edge_ctrl_idx);
+	set = drvdata->dsb->edge_ctrl_mask[reg];
+	if (val)
+		set |= BIT(EDCMR_TO_WORD_SHIFT(drvdata->dsb->edge_ctrl_idx));
+	else
+		set &= ~BIT(EDCMR_TO_WORD_SHIFT(drvdata->dsb->edge_ctrl_idx));
+	drvdata->dsb->edge_ctrl_mask[reg] = set;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_WO(ctrl_mask);
+
 static ssize_t dsb_trig_type_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
@@ -367,6 +501,37 @@ static ssize_t dsb_trig_ts_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(dsb_trig_ts);
 
+static struct attribute *tpdm_dsb_edge_attrs[] = {
+	&dev_attr_ctrl_idx.attr,
+	&dev_attr_ctrl_val.attr,
+	&dev_attr_ctrl_mask.attr,
+	DSB_EDGE_CTRL_ATTR(0),
+	DSB_EDGE_CTRL_ATTR(1),
+	DSB_EDGE_CTRL_ATTR(2),
+	DSB_EDGE_CTRL_ATTR(3),
+	DSB_EDGE_CTRL_ATTR(4),
+	DSB_EDGE_CTRL_ATTR(5),
+	DSB_EDGE_CTRL_ATTR(6),
+	DSB_EDGE_CTRL_ATTR(7),
+	DSB_EDGE_CTRL_ATTR(8),
+	DSB_EDGE_CTRL_ATTR(9),
+	DSB_EDGE_CTRL_ATTR(10),
+	DSB_EDGE_CTRL_ATTR(11),
+	DSB_EDGE_CTRL_ATTR(12),
+	DSB_EDGE_CTRL_ATTR(13),
+	DSB_EDGE_CTRL_ATTR(14),
+	DSB_EDGE_CTRL_ATTR(15),
+	DSB_EDGE_CTRL_MASK_ATTR(0),
+	DSB_EDGE_CTRL_MASK_ATTR(1),
+	DSB_EDGE_CTRL_MASK_ATTR(2),
+	DSB_EDGE_CTRL_MASK_ATTR(3),
+	DSB_EDGE_CTRL_MASK_ATTR(4),
+	DSB_EDGE_CTRL_MASK_ATTR(5),
+	DSB_EDGE_CTRL_MASK_ATTR(6),
+	DSB_EDGE_CTRL_MASK_ATTR(7),
+	NULL,
+};
+
 static struct attribute *tpdm_dsb_attrs[] = {
 	&dev_attr_dsb_mode.attr,
 	&dev_attr_dsb_trig_ts.attr,
@@ -379,9 +544,16 @@ static struct attribute_group tpdm_dsb_attr_grp = {
 	.is_visible = tpdm_dsb_is_visible,
 };
 
+static struct attribute_group tpdm_dsb_edge_grp = {
+	.attrs = tpdm_dsb_edge_attrs,
+	.is_visible = tpdm_dsb_is_visible,
+	.name = "dsb_edge",
+};
+
 static const struct attribute_group *tpdm_attr_grps[] = {
 	&tpdm_attr_grp,
 	&tpdm_dsb_attr_grp,
+	&tpdm_dsb_edge_grp,
 	NULL,
 };
 
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h
index b55d6f5ce8520..a9c65d96316a0 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.h
+++ b/drivers/hwtracing/coresight/coresight-tpdm.h
@@ -12,6 +12,8 @@
 /* DSB Subunit Registers */
 #define TPDM_DSB_CR		(0x780)
 #define TPDM_DSB_TIER		(0x784)
+#define TPDM_DSB_EDCR(n)	(0x808 + (n * 4))
+#define TPDM_DSB_EDCMR(n)	(0x848 + (n * 4))
 
 /* Enable bit for DSB subunit */
 #define TPDM_DSB_CR_ENA		BIT(0)
@@ -37,6 +39,16 @@
 /* High performance mode */
 #define TPDM_DSB_MODE_HPBYTESEL(val)	(val & GENMASK(8, 4))
 
+#define EDCRS_PER_WORD			16
+#define EDCR_TO_WORD_IDX(r)		((r) / EDCRS_PER_WORD)
+#define EDCR_TO_WORD_SHIFT(r)		((r % EDCRS_PER_WORD) * 2)
+#define EDCR_TO_WORD_VAL(val, r)	(val << EDCR_TO_WORD_SHIFT(r))
+#define EDCR_TO_WORD_MASK(r)		EDCR_TO_WORD_VAL(0x3, r)
+
+#define EDCMRS_PER_WORD				32
+#define EDCMR_TO_WORD_IDX(r)		((r) / EDCMRS_PER_WORD)
+#define EDCMR_TO_WORD_SHIFT(r)		((r) % EDCMRS_PER_WORD)
+
 /* TPDM integration test registers */
 #define TPDM_ITATBCNTRL		(0xEF0)
 #define TPDM_ITCNTRL		(0xF00)
@@ -63,14 +75,43 @@
 #define TPDM_PIDR0_DS_IMPDEF	BIT(0)
 #define TPDM_PIDR0_DS_DSB	BIT(1)
 
+#define TPDM_DSB_MAX_LINES	256
+/* MAX number of EDCR registers */
+#define TPDM_DSB_MAX_EDCR	16
+/* MAX number of EDCMR registers */
+#define TPDM_DSB_MAX_EDCMR	8
+
+#define tpdm_simple_dataset_ro(name, mem, idx)			\
+	(&((struct tpdm_dataset_attribute[]) {			\
+	   {								\
+		__ATTR(name, 0444, tpdm_simple_dataset_show, NULL),	\
+		mem,							\
+		idx,							\
+	   }								\
+	})[0].attr.attr)
+
+#define DSB_EDGE_CTRL_ATTR(nr)					\
+		tpdm_simple_dataset_ro(edcr##nr,		\
+		DSB_EDGE_CTRL, nr)
+
+#define DSB_EDGE_CTRL_MASK_ATTR(nr)				\
+		tpdm_simple_dataset_ro(edcmr##nr,		\
+		DSB_EDGE_CTRL_MASK, nr)
+
 /**
  * struct dsb_dataset - specifics associated to dsb dataset
  * @mode:             DSB programming mode
+ * @edge_ctrl_idx     Index number of the edge control
+ * @edge_ctrl:        Save value for edge control
+ * @edge_ctrl_mask:   Save value for edge control mask
  * @trig_ts:          Enable/Disable trigger timestamp.
  * @trig_type:        Enable/Disable trigger type.
  */
 struct dsb_dataset {
 	u32			mode;
+	u32			edge_ctrl_idx;
+	u32			edge_ctrl[TPDM_DSB_MAX_EDCR];
+	u32			edge_ctrl_mask[TPDM_DSB_MAX_EDCMR];
 	bool			trig_ts;
 	bool			trig_type;
 };
@@ -96,4 +137,23 @@ struct tpdm_drvdata {
 	struct dsb_dataset	*dsb;
 };
 
+/* Enumerate members of various datasets */
+enum dataset_mem {
+	DSB_EDGE_CTRL,
+	DSB_EDGE_CTRL_MASK,
+};
+
+/**
+ * struct tpdm_dataset_attribute - Record the member variables and
+ * index number of datasets that need to be operated by sysfs file
+ * @attr:       The device attribute
+ * @mem:        The member in the dataset data structure
+ * @idx:        The index number of the array data
+ */
+struct tpdm_dataset_attribute {
+	struct device_attribute attr;
+	enum dataset_mem mem;
+	u32 idx;
+};
+
 #endif  /* _CORESIGHT_CORESIGHT_TPDM_H */
-- 
GitLab


From a8138a9445e6d159138b7e574dc5ee7cbcc2f06a Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:43 +0800
Subject: [PATCH 0163/4076] coresight-tpdm: Add nodes to configure pattern
 match output

Add nodes to configure trigger pattern and trigger pattern mask.
Each DSB subunit TPDM has maximum of n(n<7) XPR registers to
configure trigger pattern match output. Eight 32 bit registers
providing DSB interface trigger output pattern match comparison.
And each DSB subunit TPDM has maximum of m(m<7) XPMR registers to
configure trigger pattern mask match output. Eight 32 bit
registers providing DSB interface trigger output pattern match
mask.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-11-git-send-email-quic_taozha@quicinc.com
---
 .../testing/sysfs-bus-coresight-devices-tpdm  | 18 +++-
 drivers/hwtracing/coresight/coresight-tpdm.c  | 82 ++++++++++++++++++-
 drivers/hwtracing/coresight/coresight-tpdm.h  | 28 +++++++
 3 files changed, 126 insertions(+), 2 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index 6853bb1295e30..2252e4706a90d 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -107,4 +107,20 @@ Date:		March 2023
 KernelVersion	6.7
 Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
 Description:
-		Read a set of the edge control mask of the DSB in TPDM.
\ No newline at end of file
+		Read a set of the edge control mask of the DSB in TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_trig_patt/xpr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the value of the trigger pattern for the DSB
+		subunit TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_trig_patt/xpmr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the mask of the trigger pattern for the DSB
+		subunit TPDM.
\ No newline at end of file
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index 7175e70c2c4e0..e04c41f832656 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -41,10 +41,58 @@ static ssize_t tpdm_simple_dataset_show(struct device *dev,
 			return -EINVAL;
 		return sysfs_emit(buf, "0x%x\n",
 			drvdata->dsb->edge_ctrl_mask[tpdm_attr->idx]);
+	case DSB_TRIG_PATT:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->trig_patt[tpdm_attr->idx]);
+	case DSB_TRIG_PATT_MASK:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->trig_patt_mask[tpdm_attr->idx]);
 	}
 	return -EINVAL;
 }
 
+/* Write dataset array member with the index number */
+static ssize_t tpdm_simple_dataset_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf,
+					 size_t size)
+{
+	unsigned long val;
+	ssize_t ret = size;
+
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct tpdm_dataset_attribute *tpdm_attr =
+		container_of(attr, struct tpdm_dataset_attribute, attr);
+
+	if (kstrtoul(buf, 0, &val))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	switch (tpdm_attr->mem) {
+	case DSB_TRIG_PATT:
+		if (tpdm_attr->idx < TPDM_DSB_MAX_PATT)
+			drvdata->dsb->trig_patt[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
+	case DSB_TRIG_PATT_MASK:
+		if (tpdm_attr->idx < TPDM_DSB_MAX_PATT)
+			drvdata->dsb->trig_patt_mask[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	spin_unlock(&drvdata->spinlock);
+
+	return ret;
+}
+
 static bool tpdm_has_dsb_dataset(struct tpdm_drvdata *drvdata)
 {
 	return (drvdata->datasets & TPDM_PIDR0_DS_DSB);
@@ -103,7 +151,12 @@ static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 	for (i = 0; i < TPDM_DSB_MAX_EDCMR; i++)
 		writel_relaxed(drvdata->dsb->edge_ctrl_mask[i],
 			   drvdata->base + TPDM_DSB_EDCMR(i));
-
+	for (i = 0; i < TPDM_DSB_MAX_PATT; i++) {
+		writel_relaxed(drvdata->dsb->trig_patt[i],
+			   drvdata->base + TPDM_DSB_XPR(i));
+		writel_relaxed(drvdata->dsb->trig_patt_mask[i],
+			   drvdata->base + TPDM_DSB_XPMR(i));
+	}
 	val = readl_relaxed(drvdata->base + TPDM_DSB_TIER);
 	/* Set trigger timestamp */
 	if (drvdata->dsb->trig_ts)
@@ -532,6 +585,26 @@ static struct attribute *tpdm_dsb_edge_attrs[] = {
 	NULL,
 };
 
+static struct attribute *tpdm_dsb_trig_patt_attrs[] = {
+	DSB_TRIG_PATT_ATTR(0),
+	DSB_TRIG_PATT_ATTR(1),
+	DSB_TRIG_PATT_ATTR(2),
+	DSB_TRIG_PATT_ATTR(3),
+	DSB_TRIG_PATT_ATTR(4),
+	DSB_TRIG_PATT_ATTR(5),
+	DSB_TRIG_PATT_ATTR(6),
+	DSB_TRIG_PATT_ATTR(7),
+	DSB_TRIG_PATT_MASK_ATTR(0),
+	DSB_TRIG_PATT_MASK_ATTR(1),
+	DSB_TRIG_PATT_MASK_ATTR(2),
+	DSB_TRIG_PATT_MASK_ATTR(3),
+	DSB_TRIG_PATT_MASK_ATTR(4),
+	DSB_TRIG_PATT_MASK_ATTR(5),
+	DSB_TRIG_PATT_MASK_ATTR(6),
+	DSB_TRIG_PATT_MASK_ATTR(7),
+	NULL,
+};
+
 static struct attribute *tpdm_dsb_attrs[] = {
 	&dev_attr_dsb_mode.attr,
 	&dev_attr_dsb_trig_ts.attr,
@@ -550,10 +623,17 @@ static struct attribute_group tpdm_dsb_edge_grp = {
 	.name = "dsb_edge",
 };
 
+static struct attribute_group tpdm_dsb_trig_patt_grp = {
+	.attrs = tpdm_dsb_trig_patt_attrs,
+	.is_visible = tpdm_dsb_is_visible,
+	.name = "dsb_trig_patt",
+};
+
 static const struct attribute_group *tpdm_attr_grps[] = {
 	&tpdm_attr_grp,
 	&tpdm_dsb_attr_grp,
 	&tpdm_dsb_edge_grp,
+	&tpdm_dsb_trig_patt_grp,
 	NULL,
 };
 
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h
index a9c65d96316a0..2cf7bdbdbb15b 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.h
+++ b/drivers/hwtracing/coresight/coresight-tpdm.h
@@ -12,6 +12,8 @@
 /* DSB Subunit Registers */
 #define TPDM_DSB_CR		(0x780)
 #define TPDM_DSB_TIER		(0x784)
+#define TPDM_DSB_XPR(n)		(0x7C8 + (n * 4))
+#define TPDM_DSB_XPMR(n)	(0x7E8 + (n * 4))
 #define TPDM_DSB_EDCR(n)	(0x808 + (n * 4))
 #define TPDM_DSB_EDCMR(n)	(0x848 + (n * 4))
 
@@ -80,6 +82,8 @@
 #define TPDM_DSB_MAX_EDCR	16
 /* MAX number of EDCMR registers */
 #define TPDM_DSB_MAX_EDCMR	8
+/* MAX number of DSB pattern */
+#define TPDM_DSB_MAX_PATT	8
 
 #define tpdm_simple_dataset_ro(name, mem, idx)			\
 	(&((struct tpdm_dataset_attribute[]) {			\
@@ -90,6 +94,16 @@
 	   }								\
 	})[0].attr.attr)
 
+#define tpdm_simple_dataset_rw(name, mem, idx)			\
+	(&((struct tpdm_dataset_attribute[]) {			\
+	   {								\
+		__ATTR(name, 0644, tpdm_simple_dataset_show,		\
+		tpdm_simple_dataset_store),		\
+		mem,							\
+		idx,							\
+	   }								\
+	})[0].attr.attr)
+
 #define DSB_EDGE_CTRL_ATTR(nr)					\
 		tpdm_simple_dataset_ro(edcr##nr,		\
 		DSB_EDGE_CTRL, nr)
@@ -98,12 +112,22 @@
 		tpdm_simple_dataset_ro(edcmr##nr,		\
 		DSB_EDGE_CTRL_MASK, nr)
 
+#define DSB_TRIG_PATT_ATTR(nr)					\
+		tpdm_simple_dataset_rw(xpr##nr,			\
+		DSB_TRIG_PATT, nr)
+
+#define DSB_TRIG_PATT_MASK_ATTR(nr)				\
+		tpdm_simple_dataset_rw(xpmr##nr,		\
+		DSB_TRIG_PATT_MASK, nr)
+
 /**
  * struct dsb_dataset - specifics associated to dsb dataset
  * @mode:             DSB programming mode
  * @edge_ctrl_idx     Index number of the edge control
  * @edge_ctrl:        Save value for edge control
  * @edge_ctrl_mask:   Save value for edge control mask
+ * @trig_patt:        Save value for trigger pattern
+ * @trig_patt_mask:   Save value for trigger pattern mask
  * @trig_ts:          Enable/Disable trigger timestamp.
  * @trig_type:        Enable/Disable trigger type.
  */
@@ -112,6 +136,8 @@ struct dsb_dataset {
 	u32			edge_ctrl_idx;
 	u32			edge_ctrl[TPDM_DSB_MAX_EDCR];
 	u32			edge_ctrl_mask[TPDM_DSB_MAX_EDCMR];
+	u32			trig_patt[TPDM_DSB_MAX_PATT];
+	u32			trig_patt_mask[TPDM_DSB_MAX_PATT];
 	bool			trig_ts;
 	bool			trig_type;
 };
@@ -141,6 +167,8 @@ struct tpdm_drvdata {
 enum dataset_mem {
 	DSB_EDGE_CTRL,
 	DSB_EDGE_CTRL_MASK,
+	DSB_TRIG_PATT,
+	DSB_TRIG_PATT_MASK,
 };
 
 /**
-- 
GitLab


From 4c983382a29eaddd8746af23702f657258bb91cc Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:44 +0800
Subject: [PATCH 0164/4076] coresight-tpdm: Add nodes for timestamp request

Add nodes to configure the timestamp request based on input
pattern match. Each TPDM that support DSB subunit has maximum of
n(n<7) TPR registers to configure value for timestamp request
based on input pattern match. Eight 32 bit registers providing
DSB interface timestamp request  pattern match comparison. And
each TPDM that support DSB subunit has maximum of m(m<7) TPMR
registers to configure pattern mask for timestamp request. Eight
32 bit registers providing DSB interface timestamp request
pattern match mask generation. Add nodes to enable/disable
pattern timestamp and set pattern timestamp type.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-12-git-send-email-quic_taozha@quicinc.com
---
 .../testing/sysfs-bus-coresight-devices-tpdm  |  40 ++++-
 drivers/hwtracing/coresight/coresight-tpdm.c  | 155 +++++++++++++++++-
 drivers/hwtracing/coresight/coresight-tpdm.h  |  24 +++
 3 files changed, 211 insertions(+), 8 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index 2252e4706a90d..1f20a3f7df7df 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -123,4 +123,42 @@ KernelVersion	6.7
 Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
 Description:
 		(RW) Set/Get the mask of the trigger pattern for the DSB
-		subunit TPDM.
\ No newline at end of file
+		subunit TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_patt/tpr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the value of the pattern for the DSB subunit TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_patt/tpmr[0:7]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the mask of the pattern for the DSB subunit TPDM.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_patt/enable_ts
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(Write) Set the pattern timestamp of DSB tpdm. Read
+		the pattern timestamp of DSB tpdm.
+
+		Accepts only one of the 2 values -  0 or 1.
+		0 : Disable DSB pattern timestamp.
+		1 : Enable DSB pattern timestamp.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_patt/set_type
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(Write) Set the pattern type of DSB tpdm. Read
+		the pattern type of DSB tpdm.
+
+		Accepts only one of the 2 values -  0 or 1.
+		0 : Set the DSB pattern type to value.
+		1 : Set the DSB pattern type to toggle.
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index e04c41f832656..693b90c82f3a0 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -51,6 +51,16 @@ static ssize_t tpdm_simple_dataset_show(struct device *dev,
 			return -EINVAL;
 		return sysfs_emit(buf, "0x%x\n",
 			drvdata->dsb->trig_patt_mask[tpdm_attr->idx]);
+	case DSB_PATT:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->patt_val[tpdm_attr->idx]);
+	case DSB_PATT_MASK:
+		if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+			drvdata->dsb->patt_mask[tpdm_attr->idx]);
 	}
 	return -EINVAL;
 }
@@ -85,6 +95,18 @@ static ssize_t tpdm_simple_dataset_store(struct device *dev,
 		else
 			ret = -EINVAL;
 		break;
+	case DSB_PATT:
+		if (tpdm_attr->idx < TPDM_DSB_MAX_PATT)
+			drvdata->dsb->patt_val[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
+	case DSB_PATT_MASK:
+		if (tpdm_attr->idx < TPDM_DSB_MAX_PATT)
+			drvdata->dsb->patt_mask[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -141,6 +163,36 @@ static void set_dsb_mode(struct tpdm_drvdata *drvdata, u32 *val)
 		*val &= ~TPDM_DSB_CR_MODE;
 }
 
+static void set_dsb_tier(struct tpdm_drvdata *drvdata)
+{
+	u32 val;
+
+	val = readl_relaxed(drvdata->base + TPDM_DSB_TIER);
+
+	/* Clear all relevant fields */
+	val &= ~(TPDM_DSB_TIER_PATT_TSENAB | TPDM_DSB_TIER_PATT_TYPE |
+		 TPDM_DSB_TIER_XTRIG_TSENAB);
+
+	/* Set pattern timestamp type and enablement */
+	if (drvdata->dsb->patt_ts) {
+		val |= TPDM_DSB_TIER_PATT_TSENAB;
+		if (drvdata->dsb->patt_type)
+			val |= TPDM_DSB_TIER_PATT_TYPE;
+		else
+			val &= ~TPDM_DSB_TIER_PATT_TYPE;
+	} else {
+		val &= ~TPDM_DSB_TIER_PATT_TSENAB;
+	}
+
+	/* Set trigger timestamp */
+	if (drvdata->dsb->trig_ts)
+		val |= TPDM_DSB_TIER_XTRIG_TSENAB;
+	else
+		val &= ~TPDM_DSB_TIER_XTRIG_TSENAB;
+
+	writel_relaxed(val, drvdata->base + TPDM_DSB_TIER);
+}
+
 static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 {
 	u32 val, i;
@@ -152,18 +204,17 @@ static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 		writel_relaxed(drvdata->dsb->edge_ctrl_mask[i],
 			   drvdata->base + TPDM_DSB_EDCMR(i));
 	for (i = 0; i < TPDM_DSB_MAX_PATT; i++) {
+		writel_relaxed(drvdata->dsb->patt_val[i],
+			   drvdata->base + TPDM_DSB_TPR(i));
+		writel_relaxed(drvdata->dsb->patt_mask[i],
+			   drvdata->base + TPDM_DSB_TPMR(i));
 		writel_relaxed(drvdata->dsb->trig_patt[i],
 			   drvdata->base + TPDM_DSB_XPR(i));
 		writel_relaxed(drvdata->dsb->trig_patt_mask[i],
 			   drvdata->base + TPDM_DSB_XPMR(i));
 	}
-	val = readl_relaxed(drvdata->base + TPDM_DSB_TIER);
-	/* Set trigger timestamp */
-	if (drvdata->dsb->trig_ts)
-		val |= TPDM_DSB_TIER_XTRIG_TSENAB;
-	else
-		val &= ~TPDM_DSB_TIER_XTRIG_TSENAB;
-	writel_relaxed(val, drvdata->base + TPDM_DSB_TIER);
+
+	set_dsb_tier(drvdata);
 
 	val = readl_relaxed(drvdata->base + TPDM_DSB_CR);
 	/* Set the mode of DSB dataset */
@@ -483,6 +534,67 @@ static ssize_t ctrl_mask_store(struct device *dev,
 }
 static DEVICE_ATTR_WO(ctrl_mask);
 
+static ssize_t enable_ts_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			 (unsigned int)drvdata->dsb->patt_ts);
+}
+
+/*
+ * value 1: Enable/Disable DSB pattern timestamp
+ */
+static ssize_t enable_ts_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf,
+			       size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->dsb->patt_ts = !!val;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(enable_ts);
+
+static ssize_t set_type_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	return sysfs_emit(buf, "%u\n",
+			 (unsigned int)drvdata->dsb->patt_type);
+}
+
+/*
+ * value 1: Set DSB pattern type
+ */
+static ssize_t set_type_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val;
+
+	if ((kstrtoul(buf, 0, &val)) || (val & ~1UL))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->dsb->patt_type = val;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(set_type);
+
 static ssize_t dsb_trig_type_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
@@ -605,6 +717,28 @@ static struct attribute *tpdm_dsb_trig_patt_attrs[] = {
 	NULL,
 };
 
+static struct attribute *tpdm_dsb_patt_attrs[] = {
+	DSB_PATT_ATTR(0),
+	DSB_PATT_ATTR(1),
+	DSB_PATT_ATTR(2),
+	DSB_PATT_ATTR(3),
+	DSB_PATT_ATTR(4),
+	DSB_PATT_ATTR(5),
+	DSB_PATT_ATTR(6),
+	DSB_PATT_ATTR(7),
+	DSB_PATT_MASK_ATTR(0),
+	DSB_PATT_MASK_ATTR(1),
+	DSB_PATT_MASK_ATTR(2),
+	DSB_PATT_MASK_ATTR(3),
+	DSB_PATT_MASK_ATTR(4),
+	DSB_PATT_MASK_ATTR(5),
+	DSB_PATT_MASK_ATTR(6),
+	DSB_PATT_MASK_ATTR(7),
+	&dev_attr_enable_ts.attr,
+	&dev_attr_set_type.attr,
+	NULL,
+};
+
 static struct attribute *tpdm_dsb_attrs[] = {
 	&dev_attr_dsb_mode.attr,
 	&dev_attr_dsb_trig_ts.attr,
@@ -629,11 +763,18 @@ static struct attribute_group tpdm_dsb_trig_patt_grp = {
 	.name = "dsb_trig_patt",
 };
 
+static struct attribute_group tpdm_dsb_patt_grp = {
+	.attrs = tpdm_dsb_patt_attrs,
+	.is_visible = tpdm_dsb_is_visible,
+	.name = "dsb_patt",
+};
+
 static const struct attribute_group *tpdm_attr_grps[] = {
 	&tpdm_attr_grp,
 	&tpdm_dsb_attr_grp,
 	&tpdm_dsb_edge_grp,
 	&tpdm_dsb_trig_patt_grp,
+	&tpdm_dsb_patt_grp,
 	NULL,
 };
 
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h
index 2cf7bdbdbb15b..891979db111ac 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.h
+++ b/drivers/hwtracing/coresight/coresight-tpdm.h
@@ -12,6 +12,8 @@
 /* DSB Subunit Registers */
 #define TPDM_DSB_CR		(0x780)
 #define TPDM_DSB_TIER		(0x784)
+#define TPDM_DSB_TPR(n)		(0x788 + (n * 4))
+#define TPDM_DSB_TPMR(n)	(0x7A8 + (n * 4))
 #define TPDM_DSB_XPR(n)		(0x7C8 + (n * 4))
 #define TPDM_DSB_XPMR(n)	(0x7E8 + (n * 4))
 #define TPDM_DSB_EDCR(n)	(0x808 + (n * 4))
@@ -28,8 +30,12 @@
 /* Data bits for DSB test mode */
 #define TPDM_DSB_CR_TEST_MODE		GENMASK(10, 9)
 
+/* Enable bit for DSB subunit pattern timestamp */
+#define TPDM_DSB_TIER_PATT_TSENAB		BIT(0)
 /* Enable bit for DSB subunit trigger timestamp */
 #define TPDM_DSB_TIER_XTRIG_TSENAB		BIT(1)
+/* Bit for DSB subunit pattern type */
+#define TPDM_DSB_TIER_PATT_TYPE			BIT(2)
 
 /* DSB programming modes */
 /* DSB mode bits mask */
@@ -120,14 +126,26 @@
 		tpdm_simple_dataset_rw(xpmr##nr,		\
 		DSB_TRIG_PATT_MASK, nr)
 
+#define DSB_PATT_ATTR(nr)					\
+		tpdm_simple_dataset_rw(tpr##nr,			\
+		DSB_PATT, nr)
+
+#define DSB_PATT_MASK_ATTR(nr)					\
+		tpdm_simple_dataset_rw(tpmr##nr,		\
+		DSB_PATT_MASK, nr)
+
 /**
  * struct dsb_dataset - specifics associated to dsb dataset
  * @mode:             DSB programming mode
  * @edge_ctrl_idx     Index number of the edge control
  * @edge_ctrl:        Save value for edge control
  * @edge_ctrl_mask:   Save value for edge control mask
+ * @patt_val:         Save value for pattern
+ * @patt_mask:        Save value for pattern mask
  * @trig_patt:        Save value for trigger pattern
  * @trig_patt_mask:   Save value for trigger pattern mask
+ * @patt_ts:          Enable/Disable pattern timestamp
+ * @patt_type:        Set pattern type
  * @trig_ts:          Enable/Disable trigger timestamp.
  * @trig_type:        Enable/Disable trigger type.
  */
@@ -136,8 +154,12 @@ struct dsb_dataset {
 	u32			edge_ctrl_idx;
 	u32			edge_ctrl[TPDM_DSB_MAX_EDCR];
 	u32			edge_ctrl_mask[TPDM_DSB_MAX_EDCMR];
+	u32			patt_val[TPDM_DSB_MAX_PATT];
+	u32			patt_mask[TPDM_DSB_MAX_PATT];
 	u32			trig_patt[TPDM_DSB_MAX_PATT];
 	u32			trig_patt_mask[TPDM_DSB_MAX_PATT];
+	bool			patt_ts;
+	bool			patt_type;
 	bool			trig_ts;
 	bool			trig_type;
 };
@@ -169,6 +191,8 @@ enum dataset_mem {
 	DSB_EDGE_CTRL_MASK,
 	DSB_TRIG_PATT,
 	DSB_TRIG_PATT_MASK,
+	DSB_PATT,
+	DSB_PATT_MASK,
 };
 
 /**
-- 
GitLab


From 8e05f86f07a0359584ceb2715fedcc4daf29d898 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:45 +0800
Subject: [PATCH 0165/4076] dt-bindings: arm: Add support for DSB MSR register

Add property "qcom,dsb-msrs-num" to support DSB(Discrete Single
Bit) MSR(mux select register) for TPDM. It specifies the number
of MSR registers supported by the DSB TDPM.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-13-git-send-email-quic_taozha@quicinc.com
---
 .../devicetree/bindings/arm/qcom,coresight-tpdm.yaml   | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml b/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
index e19fc375d494e..61ddc3b5b247b 100644
--- a/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom,coresight-tpdm.yaml
@@ -52,6 +52,15 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint8
     enum: [32, 64]
 
+  qcom,dsb-msrs-num:
+    description:
+      Specifies the number of DSB(Discrete Single Bit) MSR(mux select register)
+      registers supported by the monitor. If this property is not configured
+      or set to 0, it means this DSB TPDM doesn't support MSR.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 32
+
   clocks:
     maxItems: 1
 
@@ -86,6 +95,7 @@ examples:
       reg = <0x0684c000 0x1000>;
 
       qcom,dsb-element-size = /bits/ 8 <32>;
+      qcom,dsb-msrs-num = <16>;
 
       clocks = <&aoss_qmp>;
       clock-names = "apb_pclk";
-- 
GitLab


From 350ba15ae187c118979566f1288adb5f69f24230 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:46 +0800
Subject: [PATCH 0166/4076] coresight-tpdm: Add nodes for dsb msr support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the nodes for DSB subunit MSR(mux select register) support.
The TPDM MSR (mux select register) interface is an optional
interface and associated bank of registers per TPDM subunit.
The intent of mux select registers is to control muxing structures
driving the TPDM’s’ various subunit interfaces.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-14-git-send-email-quic_taozha@quicinc.com
---
 .../testing/sysfs-bus-coresight-devices-tpdm  |  8 ++
 drivers/hwtracing/coresight/coresight-tpdm.c  | 85 +++++++++++++++++++
 drivers/hwtracing/coresight/coresight-tpdm.h  | 12 +++
 3 files changed, 105 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index 1f20a3f7df7df..f07218e788439 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -162,3 +162,11 @@ Description:
 		Accepts only one of the 2 values -  0 or 1.
 		0 : Set the DSB pattern type to value.
 		1 : Set the DSB pattern type to toggle.
+
+What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_msr/msr[0:31]
+Date:		March 2023
+KernelVersion	6.7
+Contact:	Jinlong Mao (QUIC) <quic_jinlmao@quicinc.com>, Tao Zhang (QUIC) <quic_taozha@quicinc.com>
+Description:
+		(RW) Set/Get the MSR(mux select register) for the DSB subunit
+		TPDM.
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index 693b90c82f3a0..b25284e06395f 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -61,6 +61,11 @@ static ssize_t tpdm_simple_dataset_show(struct device *dev,
 			return -EINVAL;
 		return sysfs_emit(buf, "0x%x\n",
 			drvdata->dsb->patt_mask[tpdm_attr->idx]);
+	case DSB_MSR:
+		if (tpdm_attr->idx >= drvdata->dsb_msr_num)
+			return -EINVAL;
+		return sysfs_emit(buf, "0x%x\n",
+				drvdata->dsb->msr[tpdm_attr->idx]);
 	}
 	return -EINVAL;
 }
@@ -107,6 +112,12 @@ static ssize_t tpdm_simple_dataset_store(struct device *dev,
 		else
 			ret = -EINVAL;
 		break;
+	case DSB_MSR:
+		if (tpdm_attr->idx < drvdata->dsb_msr_num)
+			drvdata->dsb->msr[tpdm_attr->idx] = val;
+		else
+			ret = -EINVAL;
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -132,6 +143,22 @@ static umode_t tpdm_dsb_is_visible(struct kobject *kobj,
 	return 0;
 }
 
+static umode_t tpdm_dsb_msr_is_visible(struct kobject *kobj,
+				       struct attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct device_attribute *dev_attr =
+		container_of(attr, struct device_attribute, attr);
+	struct tpdm_dataset_attribute *tpdm_attr =
+		container_of(dev_attr, struct tpdm_dataset_attribute, attr);
+
+	if (tpdm_attr->idx < drvdata->dsb_msr_num)
+		return attr->mode;
+
+	return 0;
+}
+
 static void tpdm_reset_datasets(struct tpdm_drvdata *drvdata)
 {
 	if (tpdm_has_dsb_dataset(drvdata)) {
@@ -193,6 +220,15 @@ static void set_dsb_tier(struct tpdm_drvdata *drvdata)
 	writel_relaxed(val, drvdata->base + TPDM_DSB_TIER);
 }
 
+static void set_dsb_msr(struct tpdm_drvdata *drvdata)
+{
+	int i;
+
+	for (i = 0; i < drvdata->dsb_msr_num; i++)
+		writel_relaxed(drvdata->dsb->msr[i],
+			   drvdata->base + TPDM_DSB_MSR(i));
+}
+
 static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 {
 	u32 val, i;
@@ -216,6 +252,8 @@ static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata)
 
 	set_dsb_tier(drvdata);
 
+	set_dsb_msr(drvdata);
+
 	val = readl_relaxed(drvdata->base + TPDM_DSB_CR);
 	/* Set the mode of DSB dataset */
 	set_dsb_mode(drvdata, &val);
@@ -739,6 +777,42 @@ static struct attribute *tpdm_dsb_patt_attrs[] = {
 	NULL,
 };
 
+static struct attribute *tpdm_dsb_msr_attrs[] = {
+	DSB_MSR_ATTR(0),
+	DSB_MSR_ATTR(1),
+	DSB_MSR_ATTR(2),
+	DSB_MSR_ATTR(3),
+	DSB_MSR_ATTR(4),
+	DSB_MSR_ATTR(5),
+	DSB_MSR_ATTR(6),
+	DSB_MSR_ATTR(7),
+	DSB_MSR_ATTR(8),
+	DSB_MSR_ATTR(9),
+	DSB_MSR_ATTR(10),
+	DSB_MSR_ATTR(11),
+	DSB_MSR_ATTR(12),
+	DSB_MSR_ATTR(13),
+	DSB_MSR_ATTR(14),
+	DSB_MSR_ATTR(15),
+	DSB_MSR_ATTR(16),
+	DSB_MSR_ATTR(17),
+	DSB_MSR_ATTR(18),
+	DSB_MSR_ATTR(19),
+	DSB_MSR_ATTR(20),
+	DSB_MSR_ATTR(21),
+	DSB_MSR_ATTR(22),
+	DSB_MSR_ATTR(23),
+	DSB_MSR_ATTR(24),
+	DSB_MSR_ATTR(25),
+	DSB_MSR_ATTR(26),
+	DSB_MSR_ATTR(27),
+	DSB_MSR_ATTR(28),
+	DSB_MSR_ATTR(29),
+	DSB_MSR_ATTR(30),
+	DSB_MSR_ATTR(31),
+	NULL,
+};
+
 static struct attribute *tpdm_dsb_attrs[] = {
 	&dev_attr_dsb_mode.attr,
 	&dev_attr_dsb_trig_ts.attr,
@@ -769,12 +843,19 @@ static struct attribute_group tpdm_dsb_patt_grp = {
 	.name = "dsb_patt",
 };
 
+static struct attribute_group tpdm_dsb_msr_grp = {
+	.attrs = tpdm_dsb_msr_attrs,
+	.is_visible = tpdm_dsb_msr_is_visible,
+	.name = "dsb_msr",
+};
+
 static const struct attribute_group *tpdm_attr_grps[] = {
 	&tpdm_attr_grp,
 	&tpdm_dsb_attr_grp,
 	&tpdm_dsb_edge_grp,
 	&tpdm_dsb_trig_patt_grp,
 	&tpdm_dsb_patt_grp,
+	&tpdm_dsb_msr_grp,
 	NULL,
 };
 
@@ -809,6 +890,10 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 	if (ret)
 		return ret;
 
+	if (drvdata && tpdm_has_dsb_dataset(drvdata))
+		of_property_read_u32(drvdata->dev->of_node,
+			   "qcom,dsb_msr_num", &drvdata->dsb_msr_num);
+
 	/* Set up coresight component description */
 	desc.name = coresight_alloc_device_name(&tpdm_devs, dev);
 	if (!desc.name)
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h
index 891979db111ac..4115b2a17b8d8 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.h
+++ b/drivers/hwtracing/coresight/coresight-tpdm.h
@@ -18,6 +18,7 @@
 #define TPDM_DSB_XPMR(n)	(0x7E8 + (n * 4))
 #define TPDM_DSB_EDCR(n)	(0x808 + (n * 4))
 #define TPDM_DSB_EDCMR(n)	(0x848 + (n * 4))
+#define TPDM_DSB_MSR(n)		(0x980 + (n * 4))
 
 /* Enable bit for DSB subunit */
 #define TPDM_DSB_CR_ENA		BIT(0)
@@ -90,6 +91,8 @@
 #define TPDM_DSB_MAX_EDCMR	8
 /* MAX number of DSB pattern */
 #define TPDM_DSB_MAX_PATT	8
+/* MAX number of DSB MSR */
+#define TPDM_DSB_MAX_MSR 32
 
 #define tpdm_simple_dataset_ro(name, mem, idx)			\
 	(&((struct tpdm_dataset_attribute[]) {			\
@@ -134,6 +137,10 @@
 		tpdm_simple_dataset_rw(tpmr##nr,		\
 		DSB_PATT_MASK, nr)
 
+#define DSB_MSR_ATTR(nr)					\
+		tpdm_simple_dataset_rw(msr##nr,			\
+		DSB_MSR, nr)
+
 /**
  * struct dsb_dataset - specifics associated to dsb dataset
  * @mode:             DSB programming mode
@@ -144,6 +151,7 @@
  * @patt_mask:        Save value for pattern mask
  * @trig_patt:        Save value for trigger pattern
  * @trig_patt_mask:   Save value for trigger pattern mask
+ * @msr               Save value for MSR
  * @patt_ts:          Enable/Disable pattern timestamp
  * @patt_type:        Set pattern type
  * @trig_ts:          Enable/Disable trigger timestamp.
@@ -158,6 +166,7 @@ struct dsb_dataset {
 	u32			patt_mask[TPDM_DSB_MAX_PATT];
 	u32			trig_patt[TPDM_DSB_MAX_PATT];
 	u32			trig_patt_mask[TPDM_DSB_MAX_PATT];
+	u32			msr[TPDM_DSB_MAX_MSR];
 	bool			patt_ts;
 	bool			patt_type;
 	bool			trig_ts;
@@ -173,6 +182,7 @@ struct dsb_dataset {
  * @enable:     enable status of the component.
  * @datasets:   The datasets types present of the TPDM.
  * @dsb         Specifics associated to TPDM DSB.
+ * @dsb_msr_num Number of MSR supported by DSB TPDM
  */
 
 struct tpdm_drvdata {
@@ -183,6 +193,7 @@ struct tpdm_drvdata {
 	bool			enable;
 	unsigned long		datasets;
 	struct dsb_dataset	*dsb;
+	u32			dsb_msr_num;
 };
 
 /* Enumerate members of various datasets */
@@ -193,6 +204,7 @@ enum dataset_mem {
 	DSB_TRIG_PATT_MASK,
 	DSB_PATT,
 	DSB_PATT_MASK,
+	DSB_MSR,
 };
 
 /**
-- 
GitLab


From 9d4408feff89f8d86b8f34339b08ceb5f8400190 Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Tue, 17 Oct 2023 16:56:08 +0700
Subject: [PATCH 0167/4076] Documentation: ABI: coresight-tpdm: Fix Bit[3]
 description indentation

Stephen Rothwell reported htmldocs warnings when merging coresight tree:

Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm:48: ERROR: Unexpected indentation.
Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm:48: WARNING: Block quote ends without a blank line; unexpected unindent.

Fix indentation alignment for Bit[3] list entry in dsb_mode description to
silence above warnings.

Fixes: 018e43ad1eee ("coresight-tpdm: Add node to set dsb programming mode")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/linux-next/20231017143324.75387a21@canb.auug.org.au/
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://lore.kernel.org/r/20231017095608.136277-1-bagasdotme@gmail.com
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
---
 Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
index f07218e788439..4dd49b159543b 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tpdm
@@ -54,8 +54,8 @@ Description:
 		Accepts the value needs to be greater than 0. What data
 		bits do is listed below.
 		Bit[0:1] : Test mode control bit for choosing the inputs.
-		Bit[3] : Set to 0 for low performance mode.
-				 Set to 1 for high performance mode.
+		Bit[3] : Set to 0 for low performance mode. Set to 1 for high
+		performance mode.
 		Bit[4:8] : Select byte lane for high performance mode.
 
 What:		/sys/bus/coresight/devices/<tpdm-name>/dsb_edge/ctrl_idx
-- 
GitLab


From 46f69b197b6cd06c709581f7ad271bc02dbedb7a Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Tue, 10 Oct 2023 16:47:27 +0800
Subject: [PATCH 0168/4076] hwtracing: hisi_ptt: Disable interrupt after trace
 end

On trace end we disable the hardware but leave the interrupt
unmasked. Mask the interrupt to make the process reverse to
the start. No actual issue since hardware should send no
interrupt after disabled.

Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231010084731.30450-2-yangyicong@huawei.com
---
 drivers/hwtracing/ptt/hisi_ptt.c | 4 ++++
 drivers/hwtracing/ptt/hisi_ptt.h | 1 +
 2 files changed, 5 insertions(+)

diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c
index a991ecb7515a3..01a1eb0d49889 100644
--- a/drivers/hwtracing/ptt/hisi_ptt.c
+++ b/drivers/hwtracing/ptt/hisi_ptt.c
@@ -183,6 +183,10 @@ static void hisi_ptt_wait_dma_reset_done(struct hisi_ptt *hisi_ptt)
 static void hisi_ptt_trace_end(struct hisi_ptt *hisi_ptt)
 {
 	writel(0, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL);
+
+	/* Mask the interrupt on the end */
+	writel(HISI_PTT_TRACE_INT_MASK_ALL, hisi_ptt->iobase + HISI_PTT_TRACE_INT_MASK);
+
 	hisi_ptt->trace_ctrl.started = false;
 }
 
diff --git a/drivers/hwtracing/ptt/hisi_ptt.h b/drivers/hwtracing/ptt/hisi_ptt.h
index e17f045d7e725..46030aa880811 100644
--- a/drivers/hwtracing/ptt/hisi_ptt.h
+++ b/drivers/hwtracing/ptt/hisi_ptt.h
@@ -47,6 +47,7 @@
 #define HISI_PTT_TRACE_INT_STAT		0x0890
 #define   HISI_PTT_TRACE_INT_STAT_MASK	GENMASK(3, 0)
 #define HISI_PTT_TRACE_INT_MASK		0x0894
+#define   HISI_PTT_TRACE_INT_MASK_ALL	GENMASK(3, 0)
 #define HISI_PTT_TUNING_INT_STAT	0x0898
 #define   HISI_PTT_TUNING_INT_STAT_MASK	BIT(0)
 #define HISI_PTT_TRACE_WR_STS		0x08a0
-- 
GitLab


From dabf410d8764dbb24832d18bb825fe7ba5e75d30 Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Tue, 10 Oct 2023 16:47:29 +0800
Subject: [PATCH 0169/4076] hwtracing: hisi_ptt: Optimize the trace data
 committing

In the current implementation, there're 4*4MiB trace buffer and hardware
will fill the buffer one by one. The driver will get notified if one
buffer is full and then copy data to the AUX buffer. If there's no
enough room for the next trace buffer, we'll commit the AUX buffer to
the perf core and try to apply a new one. In a typical configuration
the AUX buffer will be 16MiB, so we'll commit the data after the whole
AUX buffer is occupied. Then the driver cannot apply a new AUX buffer
immediately until the committed data is consumed by userspace and then
there's room in the AUX buffer again.

This patch tries to optimize this by commit the data after one single
trace buffer is filled. Since there's still room in the AUX buffer,
driver can apply a new one without failure and don't need to wait for
the userspace to consume the data.

Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231010084731.30450-4-yangyicong@huawei.com
---
 drivers/hwtracing/ptt/hisi_ptt.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c
index 01a1eb0d49889..c1b5fd2b89741 100644
--- a/drivers/hwtracing/ptt/hisi_ptt.c
+++ b/drivers/hwtracing/ptt/hisi_ptt.c
@@ -274,15 +274,14 @@ static int hisi_ptt_update_aux(struct hisi_ptt *hisi_ptt, int index, bool stop)
 	buf->pos += size;
 
 	/*
-	 * Just commit the traced data if we're going to stop. Otherwise if the
-	 * resident AUX buffer cannot contain the data of next trace buffer,
-	 * apply a new one.
+	 * Always commit the data to the AUX buffer in time to make sure
+	 * userspace got enough time to consume the data.
+	 *
+	 * If we're not going to stop, apply a new one and check whether
+	 * there's enough room for the next trace.
 	 */
-	if (stop) {
-		perf_aux_output_end(handle, buf->pos);
-	} else if (buf->length - buf->pos < HISI_PTT_TRACE_BUF_SIZE) {
-		perf_aux_output_end(handle, buf->pos);
-
+	perf_aux_output_end(handle, size);
+	if (!stop) {
 		buf = perf_aux_output_begin(handle, event);
 		if (!buf)
 			return -EINVAL;
-- 
GitLab


From c4137932d11dff5a347e3462cc52383fc333b86b Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Tue, 24 Oct 2023 14:19:13 +0800
Subject: [PATCH 0170/4076] coresight-tpdm: Correct the property name of MSR
 number

Correct the property name of the DSB MSR number that needs to be
read in TPDM driver. The right property name is
"qcom,dsb-msrs-num".

Fixes: 350ba15ae187 ("coresight-tpdm: Add nodes for dsb msr support")
Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
[ Fix checkpatch failure in the commit description ]
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1698128353-31157-1-git-send-email-quic_taozha@quicinc.com
---
 drivers/hwtracing/coresight/coresight-tpdm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index b25284e06395f..97654aa4b772a 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -892,7 +892,7 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	if (drvdata && tpdm_has_dsb_dataset(drvdata))
 		of_property_read_u32(drvdata->dev->of_node,
-			   "qcom,dsb_msr_num", &drvdata->dsb_msr_num);
+			   "qcom,dsb-msrs-num", &drvdata->dsb_msr_num);
 
 	/* Set up coresight component description */
 	desc.name = coresight_alloc_device_name(&tpdm_devs, dev);
-- 
GitLab


From cc0271a339cc70cae914c3ec20edc2a8058407da Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Wed, 1 Nov 2023 11:52:06 +0000
Subject: [PATCH 0171/4076] coresight: etm4x: Fix width of CCITMIN field

CCITMIN is a 12 bit field and doesn't fit in a u8, so extend it to u16.
This probably wasn't an issue previously because values higher than 255
never occurred.

But since commit 4aff040bcc8d ("coresight: etm: Override TRCIDR3.CCITMIN
on errata affected cpus"), a comparison with 256 was done to enable the
errata, generating the following W=1 build error:

  coresight-etm4x-core.c:1188:24: error: result of comparison of
  constant 256 with expression of type 'u8' (aka 'unsigned char') is
  always false [-Werror,-Wtautological-constant-out-of-range-compare]

   if (drvdata->ccitmin == 256)

Cc: stable@vger.kernel.org
Fixes: 2e1cdfe184b5 ("coresight-etm4x: Adding CoreSight ETM4x driver")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202310302043.as36UFED-lkp@intel.com/
Reviewed-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231101115206.70810-1-james.clark@arm.com
---
 drivers/hwtracing/coresight/coresight-etm4x.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h
index 20e2e4cb76146..da17b6c49b0f1 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.h
+++ b/drivers/hwtracing/coresight/coresight-etm4x.h
@@ -1036,7 +1036,7 @@ struct etmv4_drvdata {
 	u8				ctxid_size;
 	u8				vmid_size;
 	u8				ccsize;
-	u8				ccitmin;
+	u16				ccitmin;
 	u8				s_ex_level;
 	u8				ns_ex_level;
 	u8				q_support;
-- 
GitLab


From fc041bd24f39f28f984cb7dea011b3625c298dd9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 16 Nov 2023 18:33:02 +0100
Subject: [PATCH 0172/4076] coresight: dummy: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231116173301.708873-9-u.kleine-koenig@pengutronix.de
---
 drivers/hwtracing/coresight/coresight-dummy.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c
index e4deafae7bc20..ac70c0b491beb 100644
--- a/drivers/hwtracing/coresight/coresight-dummy.c
+++ b/drivers/hwtracing/coresight/coresight-dummy.c
@@ -122,14 +122,13 @@ static int dummy_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int dummy_remove(struct platform_device *pdev)
+static void dummy_remove(struct platform_device *pdev)
 {
 	struct dummy_drvdata *drvdata = platform_get_drvdata(pdev);
 	struct device *dev = &pdev->dev;
 
 	pm_runtime_disable(dev);
 	coresight_unregister(drvdata->csdev);
-	return 0;
 }
 
 static const struct of_device_id dummy_match[] = {
@@ -140,7 +139,7 @@ static const struct of_device_id dummy_match[] = {
 
 static struct platform_driver dummy_driver = {
 	.probe	= dummy_probe,
-	.remove	= dummy_remove,
+	.remove_new = dummy_remove,
 	.driver	= {
 		.name   = "coresight-dummy",
 		.of_match_table = dummy_match,
-- 
GitLab


From 4445e142b4580e8fd43b67a9192a77027e6933cb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 16 Nov 2023 18:33:03 +0100
Subject: [PATCH 0173/4076] coresight: etm4x: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231116173301.708873-10-u.kleine-koenig@pengutronix.de
---
 drivers/hwtracing/coresight/coresight-etm4x-core.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c
index 285539104bcc4..ce1995a2827f0 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-core.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c
@@ -2303,7 +2303,7 @@ static void etm4_remove_amba(struct amba_device *adev)
 		etm4_remove_dev(drvdata);
 }
 
-static int etm4_remove_platform_dev(struct platform_device *pdev)
+static void etm4_remove_platform_dev(struct platform_device *pdev)
 {
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(&pdev->dev);
 
@@ -2313,8 +2313,6 @@ static int etm4_remove_platform_dev(struct platform_device *pdev)
 
 	if (drvdata && !IS_ERR_OR_NULL(drvdata->pclk))
 		clk_put(drvdata->pclk);
-
-	return 0;
 }
 
 static const struct amba_id etm4_ids[] = {
@@ -2400,7 +2398,7 @@ MODULE_DEVICE_TABLE(acpi, etm4x_acpi_ids);
 
 static struct platform_driver etm4_platform_driver = {
 	.probe		= etm4_probe_platform_dev,
-	.remove		= etm4_remove_platform_dev,
+	.remove_new	= etm4_remove_platform_dev,
 	.driver			= {
 		.name			= "coresight-etm4x",
 		.of_match_table		= etm4_sysreg_match,
-- 
GitLab


From 858aebb52cc0f4b3446842fb5169bdf33fc136d4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 16 Nov 2023 18:33:04 +0100
Subject: [PATCH 0174/4076] coresight: funnel: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231116173301.708873-11-u.kleine-koenig@pengutronix.de
---
 drivers/hwtracing/coresight/coresight-funnel.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index b8e150e45b272..a5b1fc787766a 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -335,11 +335,10 @@ static int static_funnel_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int static_funnel_remove(struct platform_device *pdev)
+static void static_funnel_remove(struct platform_device *pdev)
 {
 	funnel_remove(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static const struct of_device_id static_funnel_match[] = {
@@ -360,7 +359,7 @@ MODULE_DEVICE_TABLE(acpi, static_funnel_ids);
 
 static struct platform_driver static_funnel_driver = {
 	.probe          = static_funnel_probe,
-	.remove          = static_funnel_remove,
+	.remove_new      = static_funnel_remove,
 	.driver         = {
 		.name   = "coresight-static-funnel",
 		/* THIS_MODULE is taken care of by platform_driver_register() */
-- 
GitLab


From 3d1e99f73409499742142ca14ff00946a9e442af Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 16 Nov 2023 18:33:05 +0100
Subject: [PATCH 0175/4076] coresight: replicator: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231116173301.708873-12-u.kleine-koenig@pengutronix.de
---
 drivers/hwtracing/coresight/coresight-replicator.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index b6be730349968..91d93060dda53 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -320,11 +320,10 @@ static int static_replicator_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int static_replicator_remove(struct platform_device *pdev)
+static void static_replicator_remove(struct platform_device *pdev)
 {
 	replicator_remove(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -373,7 +372,7 @@ MODULE_DEVICE_TABLE(acpi, static_replicator_acpi_ids);
 
 static struct platform_driver static_replicator_driver = {
 	.probe          = static_replicator_probe,
-	.remove         = static_replicator_remove,
+	.remove_new     = static_replicator_remove,
 	.driver         = {
 		.name   = "coresight-static-replicator",
 		/* THIS_MODULE is taken care of by platform_driver_register() */
-- 
GitLab


From 98881b34ce90c031164597f73603f3219da79658 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 16 Nov 2023 18:33:06 +0100
Subject: [PATCH 0176/4076] coresight: trbe: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231116173301.708873-13-u.kleine-koenig@pengutronix.de
---
 drivers/hwtracing/coresight/coresight-trbe.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c
index a3954be7b1f3b..6136776482e6d 100644
--- a/drivers/hwtracing/coresight/coresight-trbe.c
+++ b/drivers/hwtracing/coresight/coresight-trbe.c
@@ -1530,14 +1530,13 @@ probe_failed:
 	return ret;
 }
 
-static int arm_trbe_device_remove(struct platform_device *pdev)
+static void arm_trbe_device_remove(struct platform_device *pdev)
 {
 	struct trbe_drvdata *drvdata = platform_get_drvdata(pdev);
 
 	arm_trbe_remove_cpuhp(drvdata);
 	arm_trbe_remove_coresight(drvdata);
 	arm_trbe_remove_irq(drvdata);
-	return 0;
 }
 
 static const struct of_device_id arm_trbe_of_match[] = {
@@ -1562,7 +1561,7 @@ static struct platform_driver arm_trbe_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe	= arm_trbe_device_probe,
-	.remove	= arm_trbe_device_remove,
+	.remove_new = arm_trbe_device_remove,
 };
 
 static int __init arm_trbe_init(void)
-- 
GitLab


From 32d9a78bb9ff9da0082ea6fdb038bc1bf81f6992 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 16 Nov 2023 18:33:07 +0100
Subject: [PATCH 0177/4076] coresight: ultrasoc-smb: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231116173301.708873-14-u.kleine-koenig@pengutronix.de
---
 drivers/hwtracing/coresight/ultrasoc-smb.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c
index 6e32d31a95fe0..2092433ff86e5 100644
--- a/drivers/hwtracing/coresight/ultrasoc-smb.c
+++ b/drivers/hwtracing/coresight/ultrasoc-smb.c
@@ -601,15 +601,13 @@ static int smb_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int smb_remove(struct platform_device *pdev)
+static void smb_remove(struct platform_device *pdev)
 {
 	struct smb_drv_data *drvdata = platform_get_drvdata(pdev);
 
 	smb_unregister_sink(drvdata);
 
 	smb_config_inport(&pdev->dev, false);
-
-	return 0;
 }
 
 #ifdef CONFIG_ACPI
@@ -627,7 +625,7 @@ static struct platform_driver smb_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = smb_probe,
-	.remove = smb_remove,
+	.remove_new = smb_remove,
 };
 module_platform_driver(smb_driver);
 
-- 
GitLab


From f0d1a9b7a0927bd074274a184d72c261292d388e Mon Sep 17 00:00:00 2001
From: Ivan Mikhaylov <fr0st61te@gmail.com>
Date: Sun, 15 Oct 2023 00:12:53 +0300
Subject: [PATCH 0178/4076] dt-bindings: adc: provide max34408/9 device tree
 binding document

The hardware binding for i2c current monitoring device with overcurrent
control.

Signed-off-by: Ivan Mikhaylov <fr0st61te@gmail.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231014211254.16719-2-fr0st61te@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/adc/maxim,max34408.yaml      | 139 ++++++++++++++++++
 1 file changed, 139 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/adc/maxim,max34408.yaml

diff --git a/Documentation/devicetree/bindings/iio/adc/maxim,max34408.yaml b/Documentation/devicetree/bindings/iio/adc/maxim,max34408.yaml
new file mode 100644
index 0000000000000..4cba856e8d473
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/maxim,max34408.yaml
@@ -0,0 +1,139 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/adc/maxim,max34408.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Maxim MAX34408/MAX34409 current monitors with overcurrent control
+
+maintainers:
+  - Ivan Mikhaylov <fr0st61te@gmail.com>
+
+description: |
+  The MAX34408/MAX34409 are two- and four-channel current monitors that are
+  configured and monitored with a standard I2C/SMBus serial interface. Each
+  unidirectional current sensor offers precision high-side operation with a
+  low full-scale sense voltage. The devices automatically sequence through
+  two or four channels and collect the current-sense samples and average them
+  to reduce the effect of impulse noise. The raw ADC samples are compared to
+  user-programmable digital thresholds to indicate overcurrent conditions.
+  Overcurrent conditions trigger a hardware output to provide an immediate
+  indication to shut down any necessary external circuitry.
+
+  Specifications about the devices can be found at:
+  https://www.analog.com/media/en/technical-documentation/data-sheets/MAX34408-MAX34409.pdf
+
+properties:
+  compatible:
+    enum:
+      - maxim,max34408
+      - maxim,max34409
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  powerdown-gpios:
+    description:
+      Shutdown Output. Open-drain output. This output transitions to high impedance
+      when any of the digital comparator thresholds are exceeded as long as the ENA
+      pin is high.
+    maxItems: 1
+
+  powerdown-status-gpios:
+    description:
+      SHTDN Enable Input. CMOS digital input. Connect to GND to clear the latch and
+      unconditionally deassert (force low) the SHTDN output and reset the shutdown
+      delay. Connect to VDD to enable normal latch operation of the SHTDN output.
+    maxItems: 1
+
+  vdd-supply: true
+
+patternProperties:
+  "^channel@[0-3]$":
+    $ref: adc.yaml
+    type: object
+    description:
+      Represents the internal channels of the ADC.
+
+    properties:
+      reg:
+        items:
+          - minimum: 0
+            maximum: 3
+
+      maxim,rsense-val-micro-ohms:
+        description:
+          Adjust the Rsense value to monitor higher or lower current levels for
+          input.
+        enum: [250, 500, 1000, 5000, 10000, 50000, 100000, 200000, 500000]
+        default: 1000
+
+    required:
+      - reg
+      - maxim,rsense-val-micro-ohms
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: maxim,max34408
+    then:
+      patternProperties:
+        "^channel@[2-3]$": false
+        "^channel@[0-1]$":
+          properties:
+            reg:
+              maximum: 1
+    else:
+      patternProperties:
+        "^channel@[0-3]$":
+          properties:
+            reg:
+              maximum: 3
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        adc@1e {
+              compatible = "maxim,max34409";
+              reg = <0x1e>;
+              powerdown-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
+              powerdown-status-gpios = <&gpio0 2 GPIO_ACTIVE_HIGH>;
+
+              #address-cells = <1>;
+              #size-cells = <0>;
+
+              channel@0 {
+                  reg = <0x0>;
+                  maxim,rsense-val-micro-ohms = <5000>;
+              };
+
+              channel@1 {
+                  reg = <0x1>;
+                  maxim,rsense-val-micro-ohms = <10000>;
+             };
+        };
+    };
-- 
GitLab


From cf27775838c5b316732c7dcb539580a736f19bc6 Mon Sep 17 00:00:00 2001
From: Ivan Mikhaylov <fr0st61te@gmail.com>
Date: Sun, 15 Oct 2023 00:12:54 +0300
Subject: [PATCH 0179/4076] iio: adc: Add driver support for MAX34408/9

The MAX34408/MAX34409 are two- and four-channel current monitors that are
configured and monitored with a standard I2C/SMBus serial interface. Each
unidirectional current sensor offers precision high-side operation with a
low full-scale sense voltage. The devices automatically sequence through
two or four channels and collect the current-sense samples and average them
to reduce the effect of impulse noise. The raw ADC samples are compared to
user-programmable digital thresholds to indicate overcurrent conditions.
Overcurrent conditions trigger a hardware output to provide an immediate
indication to shut down any necessary external circuitry.

Add as ADC driver which only supports current monitoring for now.

Link: https://www.analog.com/media/en/technical-documentation/data-sheets/MAX34408-MAX34409.pdf

Signed-off-by: Ivan Mikhaylov <fr0st61te@gmail.com>
Link: https://lore.kernel.org/r/20231014211254.16719-3-fr0st61te@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/Kconfig    |  11 ++
 drivers/iio/adc/Makefile   |   1 +
 drivers/iio/adc/max34408.c | 276 +++++++++++++++++++++++++++++++++++++
 3 files changed, 288 insertions(+)
 create mode 100644 drivers/iio/adc/max34408.c

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 35f9867da12c3..1e2b7a2c67c6b 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -745,6 +745,17 @@ config MAX1363
 	  To compile this driver as a module, choose M here: the module will be
 	  called max1363.
 
+config MAX34408
+	tristate "Maxim max34408/max344089 ADC driver"
+	depends on I2C
+	help
+	  Say yes here to build support for Maxim max34408/max34409 current sense
+	  monitor with 8-bits ADC interface with overcurrent delay/threshold and
+	  shutdown delay.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called max34408.
+
 config MAX77541_ADC
 	tristate "Analog Devices MAX77541 ADC driver"
 	depends on MFD_MAX77541
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index bee11d442af45..c0803383a7ccb 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -68,6 +68,7 @@ obj-$(CONFIG_MAX11205) += max11205.o
 obj-$(CONFIG_MAX11410) += max11410.o
 obj-$(CONFIG_MAX1241) += max1241.o
 obj-$(CONFIG_MAX1363) += max1363.o
+obj-$(CONFIG_MAX34408) += max34408.o
 obj-$(CONFIG_MAX77541_ADC) += max77541-adc.o
 obj-$(CONFIG_MAX9611) += max9611.o
 obj-$(CONFIG_MCP320X) += mcp320x.o
diff --git a/drivers/iio/adc/max34408.c b/drivers/iio/adc/max34408.c
new file mode 100644
index 0000000000000..6c2ea2bc52c6f
--- /dev/null
+++ b/drivers/iio/adc/max34408.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IIO driver for Maxim MAX34409/34408 ADC, 4-Channels/2-Channels, 8bits, I2C
+ *
+ * Datasheet: https://www.analog.com/media/en/technical-documentation/data-sheets/MAX34408-MAX34409.pdf
+ *
+ * TODO: ALERT interrupt, Overcurrent delay, Shutdown delay
+ */
+
+#include <linux/bitfield.h>
+#include <linux/init.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/types.h>
+
+#define MAX34408_STATUS_REG		0x0
+#define MAX34408_CONTROL_REG		0x1
+#define MAX34408_OCDELAY_REG		0x2
+#define MAX34408_SDDELAY_REG		0x3
+
+#define MAX34408_ADC1_REG		0x4
+#define MAX34408_ADC2_REG		0x5
+/* ADC3 & ADC4 always returns 0x0 on 34408 */
+#define MAX34409_ADC3_REG		0x6
+#define MAX34409_ADC4_REG		0x7
+
+#define MAX34408_OCT1_REG		0x8
+#define MAX34408_OCT2_REG		0x9
+#define MAX34409_OCT3_REG		0xA
+#define MAX34409_OCT4_REG		0xB
+
+#define MAX34408_DID_REG		0xC
+#define MAX34408_DCYY_REG		0xD
+#define MAX34408_DCWW_REG		0xE
+
+/* Bit masks for status register */
+#define MAX34408_STATUS_OC_MSK		GENMASK(1, 0)
+#define MAX34409_STATUS_OC_MSK		GENMASK(3, 0)
+#define MAX34408_STATUS_SHTDN		BIT(4)
+#define MAX34408_STATUS_ENA		BIT(5)
+
+/* Bit masks for control register */
+#define MAX34408_CONTROL_AVG0		BIT(0)
+#define MAX34408_CONTROL_AVG1		BIT(1)
+#define MAX34408_CONTROL_AVG2		BIT(2)
+#define MAX34408_CONTROL_ALERT		BIT(3)
+
+#define MAX34408_DEFAULT_AVG		0x4
+
+/* Bit masks for over current delay */
+#define MAX34408_OCDELAY_OCD_MSK	GENMASK(6, 0)
+#define MAX34408_OCDELAY_RESET		BIT(7)
+
+/* Bit masks for shutdown delay */
+#define MAX34408_SDDELAY_SHD_MSK	GENMASK(6, 0)
+#define MAX34408_SDDELAY_RESET		BIT(7)
+
+#define MAX34408_DEFAULT_RSENSE		1000
+
+/**
+ * struct max34408_data - max34408/max34409 specific data.
+ * @regmap:	device register map.
+ * @dev:	max34408 device.
+ * @lock:	lock for protecting access to device hardware registers, mostly
+ *		for read modify write cycles for control registers.
+ * @input_rsense:	Rsense values in uOhm, will be overwritten by
+ *			values from channel nodes.
+ */
+struct max34408_data {
+	struct regmap *regmap;
+	struct device *dev;
+	struct mutex lock;
+	u32 input_rsense[4];
+};
+
+static const struct regmap_config max34408_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.max_register	= MAX34408_DCWW_REG,
+};
+
+struct max34408_adc_model_data {
+	const char *model_name;
+	const struct iio_chan_spec *channels;
+	const int num_channels;
+};
+
+#define MAX34008_CHANNEL(_index, _address)			\
+	{							\
+		.type = IIO_CURRENT,				\
+		.info_mask_separate	= BIT(IIO_CHAN_INFO_RAW) | \
+					  BIT(IIO_CHAN_INFO_SCALE) | \
+					  BIT(IIO_CHAN_INFO_OFFSET), \
+		.channel = (_index),				\
+		.address = (_address),				\
+		.indexed = 1,					\
+	}
+
+static const struct iio_chan_spec max34408_channels[] = {
+	MAX34008_CHANNEL(0, MAX34408_ADC1_REG),
+	MAX34008_CHANNEL(1, MAX34408_ADC2_REG),
+};
+
+static const struct iio_chan_spec max34409_channels[] = {
+	MAX34008_CHANNEL(0, MAX34408_ADC1_REG),
+	MAX34008_CHANNEL(1, MAX34408_ADC2_REG),
+	MAX34008_CHANNEL(2, MAX34409_ADC3_REG),
+	MAX34008_CHANNEL(3, MAX34409_ADC4_REG),
+};
+
+static int max34408_read_adc_avg(struct max34408_data *max34408,
+				 const struct iio_chan_spec *chan, int *val)
+{
+	unsigned int ctrl;
+	int rc;
+
+	guard(mutex)(&max34408->lock);
+	rc = regmap_read(max34408->regmap, MAX34408_CONTROL_REG, (u32 *)&ctrl);
+	if (rc)
+		return rc;
+
+	/* set averaging (0b100) default values*/
+	rc = regmap_write(max34408->regmap, MAX34408_CONTROL_REG,
+			  MAX34408_DEFAULT_AVG);
+	if (rc) {
+		dev_err(max34408->dev,
+			"Error (%d) writing control register\n", rc);
+		return rc;
+	}
+
+	rc = regmap_read(max34408->regmap, chan->address, val);
+	if (rc)
+		return rc;
+
+	/* back to old values */
+	rc = regmap_write(max34408->regmap, MAX34408_CONTROL_REG, ctrl);
+	if (rc)
+		dev_err(max34408->dev,
+			"Error (%d) writing control register\n", rc);
+
+	return rc;
+}
+
+static int max34408_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int *val, int *val2, long mask)
+{
+	struct max34408_data *max34408 = iio_priv(indio_dev);
+	int rc;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		rc = max34408_read_adc_avg(max34408, chan, val);
+		if (rc)
+			return rc;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		/*
+		 * calcluate current for 8bit ADC with Rsense
+		 * value.
+		 * 10 mV * 1000 / Rsense uOhm = max current
+		 * (max current * adc val * 1000) / (2^8 - 1) mA
+		 */
+		*val = 10000 / max34408->input_rsense[chan->channel];
+		*val2 = 8;
+		return IIO_VAL_FRACTIONAL_LOG2;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info max34408_info = {
+	.read_raw	= max34408_read_raw,
+};
+
+static const struct max34408_adc_model_data max34408_model_data = {
+	.model_name = "max34408",
+	.channels = max34408_channels,
+	.num_channels = 2,
+};
+
+static const struct max34408_adc_model_data max34409_model_data = {
+	.model_name = "max34409",
+	.channels = max34409_channels,
+	.num_channels = 4,
+};
+
+static int max34408_probe(struct i2c_client *client)
+{
+	const struct max34408_adc_model_data *model_data;
+	struct device *dev = &client->dev;
+	struct max34408_data *max34408;
+	struct fwnode_handle *node;
+	struct iio_dev *indio_dev;
+	struct regmap *regmap;
+	int rc, i = 0;
+
+	model_data = i2c_get_match_data(client);
+	if (!model_data)
+		return -EINVAL;
+
+	regmap = devm_regmap_init_i2c(client, &max34408_regmap_config);
+	if (IS_ERR(regmap)) {
+		dev_err_probe(dev, PTR_ERR(regmap),
+			      "regmap_init failed\n");
+		return PTR_ERR(regmap);
+	}
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*max34408));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	max34408 = iio_priv(indio_dev);
+	max34408->regmap = regmap;
+	max34408->dev = dev;
+	mutex_init(&max34408->lock);
+
+	device_for_each_child_node(dev, node) {
+		fwnode_property_read_u32(node, "maxim,rsense-val-micro-ohms",
+					 &max34408->input_rsense[i]);
+		i++;
+	}
+
+	/* disable ALERT and averaging */
+	rc = regmap_write(max34408->regmap, MAX34408_CONTROL_REG, 0x0);
+	if (rc)
+		return rc;
+
+	indio_dev->channels = model_data->channels;
+	indio_dev->num_channels = model_data->num_channels;
+	indio_dev->name = model_data->model_name;
+
+	indio_dev->info = &max34408_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct of_device_id max34408_of_match[] = {
+	{
+		.compatible = "maxim,max34408",
+		.data = &max34408_model_data,
+	},
+	{
+		.compatible = "maxim,max34409",
+		.data = &max34409_model_data,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, max34408_of_match);
+
+static const struct i2c_device_id max34408_id[] = {
+	{ "max34408", (kernel_ulong_t)&max34408_model_data },
+	{ "max34409", (kernel_ulong_t)&max34409_model_data },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, max34408_id);
+
+static struct i2c_driver max34408_driver = {
+	.driver = {
+		.name   = "max34408",
+		.of_match_table = max34408_of_match,
+	},
+	.probe = max34408_probe,
+	.id_table = max34408_id,
+};
+module_i2c_driver(max34408_driver);
+
+MODULE_AUTHOR("Ivan Mikhaylov <fr0st61te@gmail.com>");
+MODULE_DESCRIPTION("Maxim MAX34408/34409 ADC driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From a0357c08d4dc4edb9e241bd68d687b793dfd0ba5 Mon Sep 17 00:00:00 2001
From: Jagath Jog J <jagathjog1996@gmail.com>
Date: Fri, 13 Oct 2023 09:18:07 +0530
Subject: [PATCH 0180/4076] dt-bindings: iio: imu: Add Bosch BMI323

Add devicetree description document for Bosch BMI323, a 6-Axis IMU.

Signed-off-by: Jagath Jog J <jagathjog1996@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231013034808.8948-2-jagathjog1996@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/imu/bosch,bmi323.yaml        | 77 +++++++++++++++++++
 1 file changed, 77 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml

diff --git a/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml b/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
new file mode 100644
index 0000000000000..64ef26e196696
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/imu/bosch,bmi323.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Bosch BMI323 6-Axis IMU
+
+maintainers:
+  - Jagath Jog J <jagathjog1996@gmail.com>
+
+description:
+  BMI323 is a 6-axis inertial measurement unit that supports acceleration and
+  gyroscopic measurements with hardware fifo buffering. Sensor also provides
+  events information such as motion, steps, orientation, single and double
+  tap detection.
+
+properties:
+  compatible:
+    const: bosch,bmi323
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+  vddio-supply: true
+
+  interrupts:
+    minItems: 1
+    maxItems: 2
+
+  interrupt-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      enum:
+        - INT1
+        - INT2
+
+  drive-open-drain:
+    description:
+      set if the specified interrupt pin should be configured as
+      open drain. If not set, defaults to push-pull.
+
+  mount-matrix:
+    description:
+      an optional 3x3 mounting rotation matrix.
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+  - vddio-supply
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    // Example for I2C
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        imu@68 {
+            compatible = "bosch,bmi323";
+            reg = <0x68>;
+            vddio-supply = <&vddio>;
+            vdd-supply = <&vdd>;
+            interrupt-parent = <&gpio1>;
+            interrupts = <29 IRQ_TYPE_EDGE_RISING>;
+            interrupt-names = "INT1";
+        };
+    };
-- 
GitLab


From 8a636db3aa57ed468b88804ecf27798df6c9c553 Mon Sep 17 00:00:00 2001
From: Jagath Jog J <jagathjog1996@gmail.com>
Date: Fri, 13 Oct 2023 09:18:08 +0530
Subject: [PATCH 0181/4076] iio: imu: Add driver for BMI323 IMU

The Bosch BMI323 is a 6-axis low-power IMU that provide measurements for
acceleration, angular rate, and temperature. This sensor includes
motion-triggered interrupt features, such as a step counter, tap detection,
and activity/inactivity interrupt capabilities.

The driver supports various functionalities, including data ready, FIFO
data handling, and events such as tap detection, step counting, and
activity interrupts.

Signed-off-by: Jagath Jog J <jagathjog1996@gmail.com>
Link: https://lore.kernel.org/r/20231013034808.8948-3-jagathjog1996@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-iio |   18 +
 MAINTAINERS                             |    7 +
 drivers/iio/imu/Kconfig                 |    1 +
 drivers/iio/imu/Makefile                |    1 +
 drivers/iio/imu/bmi323/Kconfig          |   33 +
 drivers/iio/imu/bmi323/Makefile         |    7 +
 drivers/iio/imu/bmi323/bmi323.h         |  209 +++
 drivers/iio/imu/bmi323/bmi323_core.c    | 2139 +++++++++++++++++++++++
 drivers/iio/imu/bmi323/bmi323_i2c.c     |  121 ++
 drivers/iio/imu/bmi323/bmi323_spi.c     |   92 +
 10 files changed, 2628 insertions(+)
 create mode 100644 drivers/iio/imu/bmi323/Kconfig
 create mode 100644 drivers/iio/imu/bmi323/Makefile
 create mode 100644 drivers/iio/imu/bmi323/bmi323.h
 create mode 100644 drivers/iio/imu/bmi323/bmi323_core.c
 create mode 100644 drivers/iio/imu/bmi323/bmi323_i2c.c
 create mode 100644 drivers/iio/imu/bmi323/bmi323_spi.c

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 19cde14f38692..0eadc08c3a139 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -2254,3 +2254,21 @@ Description:
 		If a label is defined for this event add that to the event
 		specific attributes. This is useful for userspace to be able to
 		better identify an individual event.
+
+What:		/sys/.../events/in_accel_gesture_tap_wait_timeout
+KernelVersion:	6.7
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Enable tap gesture confirmation with timeout.
+
+What:		/sys/.../events/in_accel_gesture_tap_wait_dur
+KernelVersion:	6.7
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Timeout value in seconds for tap gesture confirmation.
+
+What:		/sys/.../events/in_accel_gesture_tap_wait_dur_available
+KernelVersion:	6.7
+Contact:	linux-iio@vger.kernel.org
+Description:
+		List of available timeout value for tap gesture confirmation.
diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cfd..8b74fad87d76f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3647,6 +3647,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/iio/accel/bosch,bma400.yaml
 F:	drivers/iio/accel/bma400*
 
+BOSCH SENSORTEC BMI323 IMU IIO DRIVER
+M:	Jagath Jog J <jagathjog1996@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/imu/bosch,bma400.yaml
+F:	drivers/iio/imu/bmi323/
+
 BPF JIT for ARM
 M:	Russell King <linux@armlinux.org.uk>
 M:	Puranjay Mohan <puranjay12@gmail.com>
diff --git a/drivers/iio/imu/Kconfig b/drivers/iio/imu/Kconfig
index c2f97629e9cdb..52a155ff32504 100644
--- a/drivers/iio/imu/Kconfig
+++ b/drivers/iio/imu/Kconfig
@@ -53,6 +53,7 @@ config ADIS16480
 	  ADIS16485, ADIS16488 inertial sensors.
 
 source "drivers/iio/imu/bmi160/Kconfig"
+source "drivers/iio/imu/bmi323/Kconfig"
 source "drivers/iio/imu/bno055/Kconfig"
 
 config FXOS8700
diff --git a/drivers/iio/imu/Makefile b/drivers/iio/imu/Makefile
index 6eb6120347222..7e2d7d5c3b7bc 100644
--- a/drivers/iio/imu/Makefile
+++ b/drivers/iio/imu/Makefile
@@ -15,6 +15,7 @@ adis_lib-$(CONFIG_IIO_ADIS_LIB_BUFFER) += adis_buffer.o
 obj-$(CONFIG_IIO_ADIS_LIB) += adis_lib.o
 
 obj-y += bmi160/
+obj-y += bmi323/
 obj-y += bno055/
 
 obj-$(CONFIG_FXOS8700) += fxos8700_core.o
diff --git a/drivers/iio/imu/bmi323/Kconfig b/drivers/iio/imu/bmi323/Kconfig
new file mode 100644
index 0000000000000..ab37b285393c1
--- /dev/null
+++ b/drivers/iio/imu/bmi323/Kconfig
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# BMI323 IMU driver
+#
+
+config BMI323
+	tristate
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
+
+config BMI323_I2C
+	tristate "Bosch BMI323 I2C driver"
+	depends on I2C
+	select BMI323
+	select REGMAP_I2C
+	help
+	  Enable support for the Bosch BMI323 6-Axis IMU connected to I2C
+	  interface.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called bmi323_i2c.
+
+config BMI323_SPI
+	tristate "Bosch BMI323 SPI driver"
+	depends on SPI
+	select BMI323
+	select REGMAP_SPI
+	help
+	  Enable support for the Bosch BMI323 6-Axis IMU connected to SPI
+	  interface.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called bmi323_spi.
diff --git a/drivers/iio/imu/bmi323/Makefile b/drivers/iio/imu/bmi323/Makefile
new file mode 100644
index 0000000000000..a6a6dc0207c95
--- /dev/null
+++ b/drivers/iio/imu/bmi323/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Bosch BMI323 IMU
+#
+obj-$(CONFIG_BMI323) += bmi323_core.o
+obj-$(CONFIG_BMI323_I2C) += bmi323_i2c.o
+obj-$(CONFIG_BMI323_SPI) += bmi323_spi.o
diff --git a/drivers/iio/imu/bmi323/bmi323.h b/drivers/iio/imu/bmi323/bmi323.h
new file mode 100644
index 0000000000000..dff126d416583
--- /dev/null
+++ b/drivers/iio/imu/bmi323/bmi323.h
@@ -0,0 +1,209 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * IIO driver for Bosch BMI323 6-Axis IMU
+ *
+ * Copyright (C) 2023, Jagath Jog J <jagathjog1996@gmail.com>
+ */
+
+#ifndef _BMI323_H_
+#define _BMI323_H_
+
+#include <linux/bits.h>
+#include <linux/regmap.h>
+#include <linux/units.h>
+
+#define BMI323_I2C_DUMMY			2
+#define BMI323_SPI_DUMMY			1
+
+/* Register map */
+
+#define BMI323_CHIP_ID_REG			0x00
+#define BMI323_CHIP_ID_VAL			0x0043
+#define BMI323_CHIP_ID_MSK			GENMASK(7, 0)
+#define BMI323_ERR_REG				0x01
+#define BMI323_STATUS_REG			0x02
+#define BMI323_STATUS_POR_MSK			BIT(0)
+
+/* Accelero/Gyro/Temp data registers */
+#define BMI323_ACCEL_X_REG			0x03
+#define BMI323_GYRO_X_REG			0x06
+#define BMI323_TEMP_REG				0x09
+#define BMI323_ALL_CHAN_MSK			GENMASK(5, 0)
+
+/* Status registers */
+#define BMI323_STATUS_INT1_REG			0x0D
+#define BMI323_STATUS_INT2_REG			0x0E
+#define BMI323_STATUS_NOMOTION_MSK		BIT(0)
+#define BMI323_STATUS_MOTION_MSK		BIT(1)
+#define BMI323_STATUS_STP_WTR_MSK		BIT(5)
+#define BMI323_STATUS_TAP_MSK			BIT(8)
+#define BMI323_STATUS_ERROR_MSK			BIT(10)
+#define BMI323_STATUS_TMP_DRDY_MSK		BIT(11)
+#define BMI323_STATUS_GYR_DRDY_MSK		BIT(12)
+#define BMI323_STATUS_ACC_DRDY_MSK		BIT(13)
+#define BMI323_STATUS_ACC_GYR_DRDY_MSK		GENMASK(13, 12)
+#define BMI323_STATUS_FIFO_WTRMRK_MSK		BIT(14)
+#define BMI323_STATUS_FIFO_FULL_MSK		BIT(15)
+
+/* Feature registers */
+#define BMI323_FEAT_IO0_REG			0x10
+#define BMI323_FEAT_IO0_XYZ_NOMOTION_MSK	GENMASK(2, 0)
+#define BMI323_FEAT_IO0_XYZ_MOTION_MSK		GENMASK(5, 3)
+#define BMI323_FEAT_XYZ_MSK			GENMASK(2, 0)
+#define BMI323_FEAT_IO0_STP_CNT_MSK		BIT(9)
+#define BMI323_FEAT_IO0_S_TAP_MSK		BIT(12)
+#define BMI323_FEAT_IO0_D_TAP_MSK		BIT(13)
+#define BMI323_FEAT_IO1_REG			0x11
+#define BMI323_FEAT_IO1_ERR_MSK			GENMASK(3, 0)
+#define BMI323_FEAT_IO2_REG			0x12
+#define BMI323_FEAT_IO_STATUS_REG		0x14
+#define BMI323_FEAT_IO_STATUS_MSK		BIT(0)
+#define BMI323_FEAT_ENG_POLL			2000
+#define BMI323_FEAT_ENG_TIMEOUT			10000
+
+/* FIFO registers */
+#define BMI323_FIFO_FILL_LEVEL_REG		0x15
+#define BMI323_FIFO_DATA_REG			0x16
+
+/* Accelero/Gyro config registers */
+#define BMI323_ACC_CONF_REG			0x20
+#define BMI323_GYRO_CONF_REG			0x21
+#define BMI323_ACC_GYRO_CONF_MODE_MSK		GENMASK(14, 12)
+#define BMI323_ACC_GYRO_CONF_ODR_MSK		GENMASK(3, 0)
+#define BMI323_ACC_GYRO_CONF_SCL_MSK		GENMASK(6, 4)
+#define BMI323_ACC_GYRO_CONF_BW_MSK		BIT(7)
+#define BMI323_ACC_GYRO_CONF_AVG_MSK		GENMASK(10, 8)
+
+/* FIFO registers */
+#define BMI323_FIFO_WTRMRK_REG			0x35
+#define BMI323_FIFO_CONF_REG			0x36
+#define BMI323_FIFO_CONF_STP_FUL_MSK		BIT(0)
+#define BMI323_FIFO_CONF_ACC_GYR_EN_MSK		GENMASK(10, 9)
+#define BMI323_FIFO_ACC_GYR_MSK			GENMASK(1, 0)
+#define BMI323_FIFO_CTRL_REG			0x37
+#define BMI323_FIFO_FLUSH_MSK			BIT(0)
+
+/* Interrupt pin config registers */
+#define BMI323_IO_INT_CTR_REG			0x38
+#define BMI323_IO_INT1_LVL_MSK			BIT(0)
+#define BMI323_IO_INT1_OD_MSK			BIT(1)
+#define BMI323_IO_INT1_OP_EN_MSK		BIT(2)
+#define BMI323_IO_INT1_LVL_OD_OP_MSK		GENMASK(2, 0)
+#define BMI323_IO_INT2_LVL_MSK			BIT(8)
+#define BMI323_IO_INT2_OD_MSK			BIT(9)
+#define BMI323_IO_INT2_OP_EN_MSK		BIT(10)
+#define BMI323_IO_INT2_LVL_OD_OP_MSK		GENMASK(10, 8)
+#define BMI323_IO_INT_CONF_REG			0x39
+#define BMI323_IO_INT_LTCH_MSK			BIT(0)
+#define BMI323_INT_MAP1_REG			0x3A
+#define BMI323_INT_MAP2_REG			0x3B
+#define BMI323_NOMOTION_MSK			GENMASK(1, 0)
+#define BMI323_MOTION_MSK			GENMASK(3, 2)
+#define BMI323_STEP_CNT_MSK			GENMASK(11, 10)
+#define BMI323_TAP_MSK				GENMASK(1, 0)
+#define BMI323_TMP_DRDY_MSK			GENMASK(7, 6)
+#define BMI323_GYR_DRDY_MSK			GENMASK(9, 8)
+#define BMI323_ACC_DRDY_MSK			GENMASK(11, 10)
+#define BMI323_FIFO_WTRMRK_MSK			GENMASK(13, 12)
+#define BMI323_FIFO_FULL_MSK			GENMASK(15, 14)
+
+/* Feature registers */
+#define BMI323_FEAT_CTRL_REG			0x40
+#define BMI323_FEAT_ENG_EN_MSK			BIT(0)
+#define BMI323_FEAT_DATA_ADDR			0x41
+#define BMI323_FEAT_DATA_TX			0x42
+#define BMI323_FEAT_DATA_STATUS			0x43
+#define BMI323_FEAT_DATA_TX_RDY_MSK		BIT(1)
+#define BMI323_FEAT_EVNT_EXT_REG		0x47
+#define BMI323_FEAT_EVNT_EXT_S_MSK		BIT(3)
+#define BMI323_FEAT_EVNT_EXT_D_MSK		BIT(4)
+
+#define BMI323_CMD_REG				0x7E
+#define BMI323_RST_VAL				0xDEAF
+#define BMI323_CFG_RES_REG			0x7F
+
+/* Extended registers */
+#define BMI323_GEN_SET1_REG			0x02
+#define BMI323_GEN_SET1_MODE_MSK		BIT(0)
+#define BMI323_GEN_HOLD_DUR_MSK			GENMASK(4, 1)
+
+/* Any Motion/No Motion config registers */
+#define BMI323_ANYMO1_REG			0x05
+#define BMI323_NOMO1_REG			0x08
+#define BMI323_MO2_OFFSET			0x01
+#define BMI323_MO3_OFFSET			0x02
+#define BMI323_MO1_REF_UP_MSK			BIT(12)
+#define BMI323_MO1_SLOPE_TH_MSK			GENMASK(11, 0)
+#define BMI323_MO2_HYSTR_MSK			GENMASK(9, 0)
+#define BMI323_MO3_DURA_MSK			GENMASK(12, 0)
+
+/* Step counter config registers */
+#define BMI323_STEP_SC1_REG			0x10
+#define BMI323_STEP_SC1_WTRMRK_MSK		GENMASK(9, 0)
+#define BMI323_STEP_SC1_RST_CNT_MSK		BIT(10)
+#define BMI323_STEP_SC1_REG			0x10
+#define BMI323_STEP_LEN				2
+
+/* Tap gesture config registers */
+#define BMI323_TAP1_REG				0x1E
+#define BMI323_TAP1_AXIS_SEL_MSK		GENMASK(1, 0)
+#define BMI323_AXIS_XYZ_MSK			GENMASK(1, 0)
+#define BMI323_TAP1_TIMOUT_MSK			BIT(2)
+#define BMI323_TAP1_MAX_PEAKS_MSK		GENMASK(5, 3)
+#define BMI323_TAP1_MODE_MSK			GENMASK(7, 6)
+#define BMI323_TAP2_REG				0x1F
+#define BMI323_TAP2_THRES_MSK			GENMASK(9, 0)
+#define BMI323_TAP2_MAX_DUR_MSK			GENMASK(15, 10)
+#define BMI323_TAP3_REG				0x20
+#define BMI323_TAP3_QUIET_TIM_MSK		GENMASK(15, 12)
+#define BMI323_TAP3_QT_BW_TAP_MSK		GENMASK(11, 8)
+#define BMI323_TAP3_QT_AFT_GES_MSK		GENMASK(15, 12)
+
+#define BMI323_MOTION_THRES_SCALE		512
+#define BMI323_MOTION_HYSTR_SCALE		512
+#define BMI323_MOTION_DURAT_SCALE		50
+#define BMI323_TAP_THRES_SCALE			512
+#define BMI323_DUR_BW_TAP_SCALE			200
+#define BMI323_QUITE_TIM_GES_SCALE		25
+#define BMI323_MAX_GES_DUR_SCALE		25
+
+/*
+ * The formula to calculate temperature in C.
+ * See datasheet section 6.1.1, Register Map Overview
+ *
+ * T_C = (temp_raw / 512) + 23
+ */
+#define BMI323_TEMP_OFFSET			11776
+#define BMI323_TEMP_SCALE			1953125
+
+/*
+ * The BMI323 features a FIFO with a capacity of 2048 bytes. Each frame
+ * consists of accelerometer (X, Y, Z) data and gyroscope (X, Y, Z) data,
+ * totaling 6 words or 12 bytes. The FIFO buffer can hold a total of
+ * 170 frames.
+ *
+ * If a watermark interrupt is configured for 170 frames, the interrupt will
+ * trigger when the FIFO reaches 169 frames, so limit the maximum watermark
+ * level to 169 frames. In terms of data, 169 frames would equal 1014 bytes,
+ * which is approximately 2 frames before the FIFO reaches its full capacity.
+ * See datasheet section 5.7.3 FIFO Buffer Interrupts
+ */
+#define BMI323_BYTES_PER_SAMPLE			2
+#define BMI323_FIFO_LENGTH_IN_BYTES		2048
+#define BMI323_FIFO_FRAME_LENGTH		6
+#define BMI323_FIFO_FULL_IN_FRAMES		\
+	((BMI323_FIFO_LENGTH_IN_BYTES /		\
+	(BMI323_BYTES_PER_SAMPLE * BMI323_FIFO_FRAME_LENGTH)) - 1)
+#define BMI323_FIFO_FULL_IN_WORDS		\
+	(BMI323_FIFO_FULL_IN_FRAMES * BMI323_FIFO_FRAME_LENGTH)
+
+#define BMI323_INT_MICRO_TO_RAW(val, val2, scale) ((val) * (scale) + \
+						  ((val2) * (scale)) / MEGA)
+
+#define BMI323_RAW_TO_MICRO(raw, scale) ((((raw) % (scale)) * MEGA) / scale)
+
+struct device;
+int bmi323_core_probe(struct device *dev);
+extern const struct regmap_config bmi323_regmap_config;
+
+#endif
diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c
new file mode 100644
index 0000000000000..0bd5dedd9a635
--- /dev/null
+++ b/drivers/iio/imu/bmi323/bmi323_core.c
@@ -0,0 +1,2139 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IIO core driver for Bosch BMI323 6-Axis IMU.
+ *
+ * Copyright (C) 2023, Jagath Jog J <jagathjog1996@gmail.com>
+ *
+ * Datasheet: https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmi323-ds000.pdf
+ */
+
+#include <linux/bitfield.h>
+#include <linux/cleanup.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/minmax.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/units.h>
+
+#include <asm/unaligned.h>
+
+#include <linux/iio/buffer.h>
+#include <linux/iio/events.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+
+#include "bmi323.h"
+
+enum bmi323_sensor_type {
+	BMI323_ACCEL,
+	BMI323_GYRO,
+	BMI323_SENSORS_CNT,
+};
+
+enum bmi323_opr_mode {
+	ACC_GYRO_MODE_DISABLE = 0x00,
+	GYRO_DRIVE_MODE_ENABLED = 0x01,
+	ACC_GYRO_MODE_DUTYCYCLE = 0x03,
+	ACC_GYRO_MODE_CONTINOUS = 0x04,
+	ACC_GYRO_MODE_HIGH_PERF = 0x07,
+};
+
+enum bmi323_state {
+	BMI323_IDLE,
+	BMI323_BUFFER_DRDY_TRIGGERED,
+	BMI323_BUFFER_FIFO,
+};
+
+enum bmi323_irq_pin {
+	BMI323_IRQ_DISABLED,
+	BMI323_IRQ_INT1,
+	BMI323_IRQ_INT2,
+};
+
+enum bmi323_3db_bw {
+	BMI323_BW_ODR_BY_2,
+	BMI323_BW_ODR_BY_4,
+};
+
+enum bmi323_scan {
+	BMI323_ACCEL_X,
+	BMI323_ACCEL_Y,
+	BMI323_ACCEL_Z,
+	BMI323_GYRO_X,
+	BMI323_GYRO_Y,
+	BMI323_GYRO_Z,
+	BMI323_CHAN_MAX
+};
+
+struct bmi323_hw {
+	u8 data;
+	u8 config;
+	const int (*scale_table)[2];
+	int scale_table_len;
+};
+
+/*
+ * The accelerometer supports +-2G/4G/8G/16G ranges, and the resolution of
+ * each sample is 16 bits, signed.
+ * At +-8G the scale can calculated by
+ * ((8 + 8) * 9.80665 / (2^16 - 1)) * 10^6 = 2394.23819 scale in micro
+ *
+ */
+static const int bmi323_accel_scale[][2] = {
+	{ 0, 598 },
+	{ 0, 1197 },
+	{ 0, 2394 },
+	{ 0, 4788 },
+};
+
+static const int bmi323_gyro_scale[][2] = {
+	{ 0, 66 },
+	{ 0, 133 },
+	{ 0, 266 },
+	{ 0, 532 },
+	{ 0, 1065 },
+};
+
+static const int bmi323_accel_gyro_avrg[] = {0, 2, 4, 8, 16, 32, 64};
+
+static const struct bmi323_hw bmi323_hw[2] = {
+	[BMI323_ACCEL] = {
+		.data = BMI323_ACCEL_X_REG,
+		.config = BMI323_ACC_CONF_REG,
+		.scale_table = bmi323_accel_scale,
+		.scale_table_len = ARRAY_SIZE(bmi323_accel_scale),
+	},
+	[BMI323_GYRO] = {
+		.data = BMI323_GYRO_X_REG,
+		.config = BMI323_GYRO_CONF_REG,
+		.scale_table = bmi323_gyro_scale,
+		.scale_table_len = ARRAY_SIZE(bmi323_gyro_scale),
+	},
+};
+
+struct bmi323_data {
+	struct device *dev;
+	struct regmap *regmap;
+	struct iio_mount_matrix orientation;
+	enum bmi323_irq_pin irq_pin;
+	struct iio_trigger *trig;
+	bool drdy_trigger_enabled;
+	enum bmi323_state state;
+	s64 fifo_tstamp, old_fifo_tstamp;
+	u32 odrns[BMI323_SENSORS_CNT];
+	u32 odrhz[BMI323_SENSORS_CNT];
+	unsigned int feature_events;
+
+	/*
+	 * Lock to protect the members of device's private data from concurrent
+	 * access and also to serialize the access of extended registers.
+	 * See bmi323_write_ext_reg(..) for more info.
+	 */
+	struct mutex mutex;
+	int watermark;
+	__le16 fifo_buff[BMI323_FIFO_FULL_IN_WORDS] __aligned(IIO_DMA_MINALIGN);
+	struct {
+		__le16 channels[BMI323_CHAN_MAX];
+		s64 ts __aligned(8);
+	} buffer;
+	__le16 steps_count[BMI323_STEP_LEN];
+};
+
+static const struct iio_mount_matrix *
+bmi323_get_mount_matrix(const struct iio_dev *idev,
+			const struct iio_chan_spec *chan)
+{
+	struct bmi323_data *data = iio_priv(idev);
+
+	return &data->orientation;
+}
+
+static const struct iio_chan_spec_ext_info bmi323_ext_info[] = {
+	IIO_MOUNT_MATRIX(IIO_SHARED_BY_TYPE, bmi323_get_mount_matrix),
+	{ }
+};
+
+static const struct iio_event_spec bmi323_step_wtrmrk_event = {
+	.type = IIO_EV_TYPE_CHANGE,
+	.dir = IIO_EV_DIR_NONE,
+	.mask_shared_by_type = BIT(IIO_EV_INFO_ENABLE) |
+			       BIT(IIO_EV_INFO_VALUE),
+};
+
+static const struct iio_event_spec bmi323_accel_event[] = {
+	{
+		.type = IIO_EV_TYPE_MAG,
+		.dir = IIO_EV_DIR_FALLING,
+		.mask_shared_by_type = BIT(IIO_EV_INFO_VALUE) |
+				       BIT(IIO_EV_INFO_PERIOD) |
+				       BIT(IIO_EV_INFO_HYSTERESIS) |
+				       BIT(IIO_EV_INFO_ENABLE),
+	},
+	{
+		.type = IIO_EV_TYPE_MAG,
+		.dir = IIO_EV_DIR_RISING,
+		.mask_shared_by_type = BIT(IIO_EV_INFO_VALUE) |
+				       BIT(IIO_EV_INFO_PERIOD) |
+				       BIT(IIO_EV_INFO_HYSTERESIS) |
+				       BIT(IIO_EV_INFO_ENABLE),
+	},
+	{
+		.type = IIO_EV_TYPE_GESTURE,
+		.dir = IIO_EV_DIR_SINGLETAP,
+		.mask_shared_by_type = BIT(IIO_EV_INFO_ENABLE) |
+				       BIT(IIO_EV_INFO_VALUE) |
+				       BIT(IIO_EV_INFO_RESET_TIMEOUT),
+	},
+	{
+		.type = IIO_EV_TYPE_GESTURE,
+		.dir = IIO_EV_DIR_DOUBLETAP,
+		.mask_shared_by_type = BIT(IIO_EV_INFO_ENABLE) |
+				       BIT(IIO_EV_INFO_VALUE) |
+				       BIT(IIO_EV_INFO_RESET_TIMEOUT) |
+				       BIT(IIO_EV_INFO_TAP2_MIN_DELAY),
+	},
+};
+
+#define BMI323_ACCEL_CHANNEL(_type, _axis, _index) {			\
+	.type = _type,							\
+	.modified = 1,							\
+	.channel2 = IIO_MOD_##_axis,					\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),			\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SAMP_FREQ) |	\
+				    BIT(IIO_CHAN_INFO_SCALE) |		\
+				    BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+	.info_mask_shared_by_type_available =				\
+				    BIT(IIO_CHAN_INFO_SAMP_FREQ) |	\
+				    BIT(IIO_CHAN_INFO_SCALE) |		\
+				    BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+	.scan_index = _index,						\
+	.scan_type = {							\
+		.sign = 's',						\
+		.realbits = 16,						\
+		.storagebits = 16,					\
+		.endianness = IIO_LE,					\
+	},								\
+	.ext_info = bmi323_ext_info,					\
+	.event_spec = bmi323_accel_event,				\
+	.num_event_specs = ARRAY_SIZE(bmi323_accel_event),		\
+}
+
+#define BMI323_GYRO_CHANNEL(_type, _axis, _index) {			\
+	.type = _type,							\
+	.modified = 1,							\
+	.channel2 = IIO_MOD_##_axis,					\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),			\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SAMP_FREQ) |	\
+				    BIT(IIO_CHAN_INFO_SCALE) |		\
+				    BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+	.info_mask_shared_by_type_available =				\
+				    BIT(IIO_CHAN_INFO_SAMP_FREQ) |	\
+				    BIT(IIO_CHAN_INFO_SCALE) |		\
+				    BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+	.scan_index = _index,						\
+	.scan_type = {							\
+		.sign = 's',						\
+		.realbits = 16,						\
+		.storagebits = 16,					\
+		.endianness = IIO_LE,					\
+	},								\
+	.ext_info = bmi323_ext_info,					\
+}
+
+static const struct iio_chan_spec bmi323_channels[] = {
+	BMI323_ACCEL_CHANNEL(IIO_ACCEL, X, BMI323_ACCEL_X),
+	BMI323_ACCEL_CHANNEL(IIO_ACCEL, Y, BMI323_ACCEL_Y),
+	BMI323_ACCEL_CHANNEL(IIO_ACCEL, Z, BMI323_ACCEL_Z),
+	BMI323_GYRO_CHANNEL(IIO_ANGL_VEL, X, BMI323_GYRO_X),
+	BMI323_GYRO_CHANNEL(IIO_ANGL_VEL, Y, BMI323_GYRO_Y),
+	BMI323_GYRO_CHANNEL(IIO_ANGL_VEL, Z, BMI323_GYRO_Z),
+	{
+		.type = IIO_TEMP,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_OFFSET) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+		.scan_index = -1,
+	},
+	{
+		.type = IIO_STEPS,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED) |
+				      BIT(IIO_CHAN_INFO_ENABLE),
+		.scan_index = -1,
+		.event_spec = &bmi323_step_wtrmrk_event,
+		.num_event_specs = 1,
+
+	},
+	IIO_CHAN_SOFT_TIMESTAMP(BMI323_CHAN_MAX),
+};
+
+static const int bmi323_acc_gyro_odr[][2] = {
+	{ 0, 781250 },
+	{ 1, 562500 },
+	{ 3, 125000 },
+	{ 6, 250000 },
+	{ 12, 500000 },
+	{ 25, 0 },
+	{ 50, 0 },
+	{ 100, 0 },
+	{ 200, 0 },
+	{ 400, 0 },
+	{ 800, 0 },
+};
+
+static const int bmi323_acc_gyro_odrns[] = {
+	1280 * MEGA,
+	640 * MEGA,
+	320 * MEGA,
+	160 * MEGA,
+	80 * MEGA,
+	40 * MEGA,
+	20 * MEGA,
+	10 * MEGA,
+	5 * MEGA,
+	2500 * KILO,
+	1250 * KILO,
+};
+
+static enum bmi323_sensor_type bmi323_iio_to_sensor(enum iio_chan_type iio_type)
+{
+	switch (iio_type) {
+	case IIO_ACCEL:
+		return BMI323_ACCEL;
+	case IIO_ANGL_VEL:
+		return BMI323_GYRO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_set_mode(struct bmi323_data *data,
+			   enum bmi323_sensor_type sensor,
+			   enum bmi323_opr_mode mode)
+{
+	guard(mutex)(&data->mutex);
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				  BMI323_ACC_GYRO_CONF_MODE_MSK,
+				  FIELD_PREP(BMI323_ACC_GYRO_CONF_MODE_MSK,
+					     mode));
+}
+
+/*
+ * When writing data to extended register there must be no communication to
+ * any other register before write transaction is complete.
+ * See datasheet section 6.2 Extended Register Map Description.
+ */
+static int bmi323_write_ext_reg(struct bmi323_data *data, unsigned int ext_addr,
+				unsigned int ext_data)
+{
+	int ret, feature_status;
+
+	ret = regmap_read(data->regmap, BMI323_FEAT_DATA_STATUS,
+			  &feature_status);
+	if (ret)
+		return ret;
+
+	if (!FIELD_GET(BMI323_FEAT_DATA_TX_RDY_MSK, feature_status))
+		return -EBUSY;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_DATA_ADDR, ext_addr);
+	if (ret)
+		return ret;
+
+	return regmap_write(data->regmap, BMI323_FEAT_DATA_TX, ext_data);
+}
+
+/*
+ * When reading data from extended register there must be no communication to
+ * any other register before read transaction is complete.
+ * See datasheet section 6.2 Extended Register Map Description.
+ */
+static int bmi323_read_ext_reg(struct bmi323_data *data, unsigned int ext_addr,
+			       unsigned int *ext_data)
+{
+	int ret, feature_status;
+
+	ret = regmap_read(data->regmap, BMI323_FEAT_DATA_STATUS,
+			  &feature_status);
+	if (ret)
+		return ret;
+
+	if (!FIELD_GET(BMI323_FEAT_DATA_TX_RDY_MSK, feature_status))
+		return -EBUSY;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_DATA_ADDR, ext_addr);
+	if (ret)
+		return ret;
+
+	return regmap_read(data->regmap, BMI323_FEAT_DATA_TX, ext_data);
+}
+
+static int bmi323_update_ext_reg(struct bmi323_data *data,
+				 unsigned int ext_addr,
+				 unsigned int mask, unsigned int ext_data)
+{
+	unsigned int value;
+	int ret;
+
+	ret = bmi323_read_ext_reg(data, ext_addr, &value);
+	if (ret)
+		return ret;
+
+	set_mask_bits(&value, mask, ext_data);
+
+	return bmi323_write_ext_reg(data, ext_addr, value);
+}
+
+static int bmi323_get_error_status(struct bmi323_data *data)
+{
+	int error, ret;
+
+	guard(mutex)(&data->mutex);
+	ret = regmap_read(data->regmap, BMI323_ERR_REG, &error);
+	if (ret)
+		return ret;
+
+	if (error)
+		dev_err(data->dev, "Sensor error 0x%x\n", error);
+
+	return error;
+}
+
+static int bmi323_feature_engine_events(struct bmi323_data *data,
+					const unsigned int event_mask,
+					bool state)
+{
+	unsigned int value;
+	int ret;
+
+	ret = regmap_read(data->regmap, BMI323_FEAT_IO0_REG, &value);
+	if (ret)
+		return ret;
+
+	/* Register must be cleared before changing an active config */
+	ret = regmap_write(data->regmap, BMI323_FEAT_IO0_REG, 0);
+	if (ret)
+		return ret;
+
+	if (state)
+		value |= event_mask;
+	else
+		value &= ~event_mask;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_IO0_REG, value);
+	if (ret)
+		return ret;
+
+	return regmap_write(data->regmap, BMI323_FEAT_IO_STATUS_REG,
+			    BMI323_FEAT_IO_STATUS_MSK);
+}
+
+static int bmi323_step_wtrmrk_en(struct bmi323_data *data, int state)
+{
+	enum bmi323_irq_pin step_irq;
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	if (!FIELD_GET(BMI323_FEAT_IO0_STP_CNT_MSK, data->feature_events))
+		return -EINVAL;
+
+	if (state)
+		step_irq = data->irq_pin;
+	else
+		step_irq = BMI323_IRQ_DISABLED;
+
+	ret = bmi323_update_ext_reg(data, BMI323_STEP_SC1_REG,
+				    BMI323_STEP_SC1_WTRMRK_MSK,
+				    FIELD_PREP(BMI323_STEP_SC1_WTRMRK_MSK,
+					       state ? 1 : 0));
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(data->regmap, BMI323_INT_MAP1_REG,
+				  BMI323_STEP_CNT_MSK,
+				  FIELD_PREP(BMI323_STEP_CNT_MSK, step_irq));
+}
+
+static int bmi323_motion_config_reg(enum iio_event_direction dir)
+{
+	switch (dir) {
+	case IIO_EV_DIR_RISING:
+		return BMI323_ANYMO1_REG;
+	case IIO_EV_DIR_FALLING:
+		return BMI323_NOMO1_REG;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_motion_event_en(struct bmi323_data *data,
+				  enum iio_event_direction dir, int state)
+{
+	unsigned int state_value = state ? BMI323_FEAT_XYZ_MSK : 0;
+	int config, ret, msk, raw, field_value;
+	enum bmi323_irq_pin motion_irq;
+	int irq_msk, irq_field_val;
+
+	if (state)
+		motion_irq = data->irq_pin;
+	else
+		motion_irq = BMI323_IRQ_DISABLED;
+
+	switch (dir) {
+	case IIO_EV_DIR_RISING:
+		msk = BMI323_FEAT_IO0_XYZ_MOTION_MSK;
+		raw = 512;
+		config = BMI323_ANYMO1_REG;
+		irq_msk = BMI323_MOTION_MSK;
+		irq_field_val = FIELD_PREP(BMI323_MOTION_MSK, motion_irq);
+		field_value = FIELD_PREP(BMI323_FEAT_IO0_XYZ_MOTION_MSK,
+					 state_value);
+		break;
+	case IIO_EV_DIR_FALLING:
+		msk = BMI323_FEAT_IO0_XYZ_NOMOTION_MSK;
+		raw = 0;
+		config = BMI323_NOMO1_REG;
+		irq_msk = BMI323_NOMOTION_MSK;
+		irq_field_val = FIELD_PREP(BMI323_NOMOTION_MSK, motion_irq);
+		field_value = FIELD_PREP(BMI323_FEAT_IO0_XYZ_NOMOTION_MSK,
+					 state_value);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	guard(mutex)(&data->mutex);
+	ret = bmi323_feature_engine_events(data, msk, state);
+	if (ret)
+		return ret;
+
+	ret = bmi323_update_ext_reg(data, config,
+				    BMI323_MO1_REF_UP_MSK,
+				    FIELD_PREP(BMI323_MO1_REF_UP_MSK, 0));
+	if (ret)
+		return ret;
+
+	/* Set initial value to avoid interrupts while enabling*/
+	ret = bmi323_update_ext_reg(data, config,
+				    BMI323_MO1_SLOPE_TH_MSK,
+				    FIELD_PREP(BMI323_MO1_SLOPE_TH_MSK, raw));
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP1_REG, irq_msk,
+				 irq_field_val);
+	if (ret)
+		return ret;
+
+	set_mask_bits(&data->feature_events, msk, field_value);
+
+	return 0;
+}
+
+static int bmi323_tap_event_en(struct bmi323_data *data,
+			       enum iio_event_direction dir, int state)
+{
+	enum bmi323_irq_pin tap_irq;
+	int ret, tap_enabled;
+
+	guard(mutex)(&data->mutex);
+
+	if (data->odrhz[BMI323_ACCEL] < 200) {
+		dev_err(data->dev, "Invalid accelrometer parameter\n");
+		return -EINVAL;
+	}
+
+	switch (dir) {
+	case IIO_EV_DIR_SINGLETAP:
+		ret = bmi323_feature_engine_events(data,
+						   BMI323_FEAT_IO0_S_TAP_MSK,
+						   state);
+		if (ret)
+			return ret;
+
+		set_mask_bits(&data->feature_events, BMI323_FEAT_IO0_S_TAP_MSK,
+			      FIELD_PREP(BMI323_FEAT_IO0_S_TAP_MSK, state));
+		break;
+	case IIO_EV_DIR_DOUBLETAP:
+		ret = bmi323_feature_engine_events(data,
+						   BMI323_FEAT_IO0_D_TAP_MSK,
+						   state);
+		if (ret)
+			return ret;
+
+		set_mask_bits(&data->feature_events, BMI323_FEAT_IO0_D_TAP_MSK,
+			      FIELD_PREP(BMI323_FEAT_IO0_D_TAP_MSK, state));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	tap_enabled = FIELD_GET(BMI323_FEAT_IO0_S_TAP_MSK |
+				BMI323_FEAT_IO0_D_TAP_MSK,
+				data->feature_events);
+
+	if (tap_enabled)
+		tap_irq = data->irq_pin;
+	else
+		tap_irq = BMI323_IRQ_DISABLED;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				 BMI323_TAP_MSK,
+				 FIELD_PREP(BMI323_TAP_MSK, tap_irq));
+	if (ret)
+		return ret;
+
+	if (!state)
+		return 0;
+
+	ret = bmi323_update_ext_reg(data, BMI323_TAP1_REG,
+				    BMI323_TAP1_MAX_PEAKS_MSK,
+				    FIELD_PREP(BMI323_TAP1_MAX_PEAKS_MSK,
+					       0x04));
+	if (ret)
+		return ret;
+
+	ret = bmi323_update_ext_reg(data, BMI323_TAP1_REG,
+				    BMI323_TAP1_AXIS_SEL_MSK,
+				    FIELD_PREP(BMI323_TAP1_AXIS_SEL_MSK,
+					       BMI323_AXIS_XYZ_MSK));
+	if (ret)
+		return ret;
+
+	return bmi323_update_ext_reg(data, BMI323_TAP1_REG,
+				     BMI323_TAP1_TIMOUT_MSK,
+				     FIELD_PREP(BMI323_TAP1_TIMOUT_MSK,
+						0));
+}
+
+static ssize_t in_accel_gesture_tap_wait_dur_show(struct device *dev,
+						  struct device_attribute *attr,
+						  char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int reg_value, raw;
+	int ret, val[2];
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = bmi323_read_ext_reg(data, BMI323_TAP2_REG, &reg_value);
+		if (ret)
+			return ret;
+	}
+
+	raw = FIELD_GET(BMI323_TAP2_MAX_DUR_MSK, reg_value);
+	val[0] = raw / BMI323_MAX_GES_DUR_SCALE;
+	val[1] = BMI323_RAW_TO_MICRO(raw, BMI323_MAX_GES_DUR_SCALE);
+
+	return iio_format_value(buf, IIO_VAL_INT_PLUS_MICRO, ARRAY_SIZE(val),
+				val);
+}
+
+static ssize_t in_accel_gesture_tap_wait_dur_store(struct device *dev,
+						   struct device_attribute *attr,
+						   const char *buf, size_t len)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret, val_int, val_fract, raw;
+
+	ret = iio_str_to_fixpoint(buf, 100000, &val_int, &val_fract);
+	if (ret)
+		return ret;
+
+	raw = BMI323_INT_MICRO_TO_RAW(val_int, val_fract,
+				      BMI323_MAX_GES_DUR_SCALE);
+	if (!in_range(raw, 0, 64))
+		return -EINVAL;
+
+	guard(mutex)(&data->mutex);
+	ret = bmi323_update_ext_reg(data, BMI323_TAP2_REG,
+				    BMI323_TAP2_MAX_DUR_MSK,
+				    FIELD_PREP(BMI323_TAP2_MAX_DUR_MSK, raw));
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+/*
+ * Maximum duration from first tap within the second tap is expected to happen.
+ * This timeout is applicable only if gesture_tap_wait_timeout is enabled.
+ */
+static IIO_DEVICE_ATTR_RW(in_accel_gesture_tap_wait_dur, 0);
+
+static ssize_t in_accel_gesture_tap_wait_timeout_show(struct device *dev,
+						      struct device_attribute *attr,
+						      char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int reg_value, raw;
+	int ret;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = bmi323_read_ext_reg(data, BMI323_TAP1_REG, &reg_value);
+		if (ret)
+			return ret;
+	}
+
+	raw = FIELD_GET(BMI323_TAP1_TIMOUT_MSK, reg_value);
+
+	return iio_format_value(buf, IIO_VAL_INT, 1, &raw);
+}
+
+static ssize_t in_accel_gesture_tap_wait_timeout_store(struct device *dev,
+						       struct device_attribute *attr,
+						       const char *buf,
+						       size_t len)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	bool val;
+	int ret;
+
+	ret = kstrtobool(buf, &val);
+	if (ret)
+		return ret;
+
+	guard(mutex)(&data->mutex);
+	ret = bmi323_update_ext_reg(data, BMI323_TAP1_REG,
+				    BMI323_TAP1_TIMOUT_MSK,
+				    FIELD_PREP(BMI323_TAP1_TIMOUT_MSK, val));
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+/* Enable/disable gesture confirmation with wait time */
+static IIO_DEVICE_ATTR_RW(in_accel_gesture_tap_wait_timeout, 0);
+
+static IIO_CONST_ATTR(in_accel_gesture_tap_wait_dur_available,
+		      "[0.0 0.04 2.52]");
+
+static IIO_CONST_ATTR(in_accel_gesture_doubletap_tap2_min_delay_available,
+		      "[0.005 0.005 0.075]");
+
+static IIO_CONST_ATTR(in_accel_gesture_tap_reset_timeout_available,
+		      "[0.04 0.04 0.6]");
+
+static IIO_CONST_ATTR(in_accel_gesture_tap_value_available, "[0.0 0.002 1.99]");
+
+static IIO_CONST_ATTR(in_accel_mag_value_available, "[0.0 0.002 7.99]");
+
+static IIO_CONST_ATTR(in_accel_mag_period_available, "[0.0 0.02 162.0]");
+
+static IIO_CONST_ATTR(in_accel_mag_hysteresis_available, "[0.0 0.002 1.99]");
+
+static struct attribute *bmi323_event_attributes[] = {
+	&iio_const_attr_in_accel_gesture_tap_value_available.dev_attr.attr,
+	&iio_const_attr_in_accel_gesture_tap_reset_timeout_available.dev_attr.attr,
+	&iio_const_attr_in_accel_gesture_doubletap_tap2_min_delay_available.dev_attr.attr,
+	&iio_const_attr_in_accel_gesture_tap_wait_dur_available.dev_attr.attr,
+	&iio_dev_attr_in_accel_gesture_tap_wait_timeout.dev_attr.attr,
+	&iio_dev_attr_in_accel_gesture_tap_wait_dur.dev_attr.attr,
+	&iio_const_attr_in_accel_mag_value_available.dev_attr.attr,
+	&iio_const_attr_in_accel_mag_period_available.dev_attr.attr,
+	&iio_const_attr_in_accel_mag_hysteresis_available.dev_attr.attr,
+	NULL
+};
+
+static const struct attribute_group bmi323_event_attribute_group = {
+	.attrs = bmi323_event_attributes,
+};
+
+static int bmi323_write_event_config(struct iio_dev *indio_dev,
+				     const struct iio_chan_spec *chan,
+				     enum iio_event_type type,
+				     enum iio_event_direction dir, int state)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	switch (type) {
+	case IIO_EV_TYPE_MAG:
+		return bmi323_motion_event_en(data, dir, state);
+	case IIO_EV_TYPE_GESTURE:
+		return bmi323_tap_event_en(data, dir, state);
+	case IIO_EV_TYPE_CHANGE:
+		return bmi323_step_wtrmrk_en(data, state);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_read_event_config(struct iio_dev *indio_dev,
+				    const struct iio_chan_spec *chan,
+				    enum iio_event_type type,
+				    enum iio_event_direction dir)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret, value, reg_val;
+
+	guard(mutex)(&data->mutex);
+
+	switch (chan->type) {
+	case IIO_ACCEL:
+		switch (dir) {
+		case IIO_EV_DIR_SINGLETAP:
+			ret = FIELD_GET(BMI323_FEAT_IO0_S_TAP_MSK,
+					data->feature_events);
+			break;
+		case IIO_EV_DIR_DOUBLETAP:
+			ret = FIELD_GET(BMI323_FEAT_IO0_D_TAP_MSK,
+					data->feature_events);
+			break;
+		case IIO_EV_DIR_RISING:
+			value = FIELD_GET(BMI323_FEAT_IO0_XYZ_MOTION_MSK,
+					  data->feature_events);
+			ret = value ? 1 : 0;
+			break;
+		case IIO_EV_DIR_FALLING:
+			value = FIELD_GET(BMI323_FEAT_IO0_XYZ_NOMOTION_MSK,
+					  data->feature_events);
+			ret = value ? 1 : 0;
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+		}
+		return ret;
+	case IIO_STEPS:
+		ret = regmap_read(data->regmap, BMI323_INT_MAP1_REG, &reg_val);
+		if (ret)
+			return ret;
+
+		return FIELD_GET(BMI323_STEP_CNT_MSK, reg_val) ? 1 : 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_write_event_value(struct iio_dev *indio_dev,
+				    const struct iio_chan_spec *chan,
+				    enum iio_event_type type,
+				    enum iio_event_direction dir,
+				    enum iio_event_info info,
+				    int val, int val2)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int raw;
+	int reg;
+
+	guard(mutex)(&data->mutex);
+
+	switch (type) {
+	case IIO_EV_TYPE_GESTURE:
+		switch (info) {
+		case IIO_EV_INFO_VALUE:
+			if (!in_range(val, 0, 2))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_TAP_THRES_SCALE);
+
+			return bmi323_update_ext_reg(data, BMI323_TAP2_REG,
+						     BMI323_TAP2_THRES_MSK,
+						     FIELD_PREP(BMI323_TAP2_THRES_MSK,
+								raw));
+		case IIO_EV_INFO_RESET_TIMEOUT:
+			if (val || !in_range(val2, 40000, 560001))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_QUITE_TIM_GES_SCALE);
+
+			return bmi323_update_ext_reg(data, BMI323_TAP3_REG,
+						     BMI323_TAP3_QT_AFT_GES_MSK,
+						     FIELD_PREP(BMI323_TAP3_QT_AFT_GES_MSK,
+								raw));
+		case IIO_EV_INFO_TAP2_MIN_DELAY:
+			if (val || !in_range(val2, 5000, 70001))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_DUR_BW_TAP_SCALE);
+
+			return bmi323_update_ext_reg(data, BMI323_TAP3_REG,
+						     BMI323_TAP3_QT_BW_TAP_MSK,
+						     FIELD_PREP(BMI323_TAP3_QT_BW_TAP_MSK,
+								raw));
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_TYPE_MAG:
+		reg = bmi323_motion_config_reg(dir);
+		if (reg < 0)
+			return -EINVAL;
+
+		switch (info) {
+		case IIO_EV_INFO_VALUE:
+			if (!in_range(val, 0, 8))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_MOTION_THRES_SCALE);
+
+			return bmi323_update_ext_reg(data, reg,
+						     BMI323_MO1_SLOPE_TH_MSK,
+						     FIELD_PREP(BMI323_MO1_SLOPE_TH_MSK,
+								raw));
+		case IIO_EV_INFO_PERIOD:
+			if (!in_range(val, 0, 163))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_MOTION_DURAT_SCALE);
+
+			return bmi323_update_ext_reg(data,
+						     reg + BMI323_MO3_OFFSET,
+						     BMI323_MO3_DURA_MSK,
+						     FIELD_PREP(BMI323_MO3_DURA_MSK,
+								raw));
+		case IIO_EV_INFO_HYSTERESIS:
+			if (!in_range(val, 0, 2))
+				return -EINVAL;
+
+			raw = BMI323_INT_MICRO_TO_RAW(val, val2,
+						      BMI323_MOTION_HYSTR_SCALE);
+
+			return bmi323_update_ext_reg(data,
+						     reg + BMI323_MO2_OFFSET,
+						     BMI323_MO2_HYSTR_MSK,
+						     FIELD_PREP(BMI323_MO2_HYSTR_MSK,
+								raw));
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_TYPE_CHANGE:
+		if (!in_range(val, 0, 20461))
+			return -EINVAL;
+
+		raw = val / 20;
+		return bmi323_update_ext_reg(data, BMI323_STEP_SC1_REG,
+					     BMI323_STEP_SC1_WTRMRK_MSK,
+					     FIELD_PREP(BMI323_STEP_SC1_WTRMRK_MSK,
+							raw));
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_read_event_value(struct iio_dev *indio_dev,
+				   const struct iio_chan_spec *chan,
+				   enum iio_event_type type,
+				   enum iio_event_direction dir,
+				   enum iio_event_info info,
+				   int *val, int *val2)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int raw, reg_value;
+	int ret, reg;
+
+	guard(mutex)(&data->mutex);
+
+	switch (type) {
+	case IIO_EV_TYPE_GESTURE:
+		switch (info) {
+		case IIO_EV_INFO_VALUE:
+			ret = bmi323_read_ext_reg(data, BMI323_TAP2_REG,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_TAP2_THRES_MSK, reg_value);
+			*val = raw / BMI323_TAP_THRES_SCALE;
+			*val2 = BMI323_RAW_TO_MICRO(raw, BMI323_TAP_THRES_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_EV_INFO_RESET_TIMEOUT:
+			ret = bmi323_read_ext_reg(data, BMI323_TAP3_REG,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_TAP3_QT_AFT_GES_MSK, reg_value);
+			*val = 0;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_QUITE_TIM_GES_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_EV_INFO_TAP2_MIN_DELAY:
+			ret = bmi323_read_ext_reg(data, BMI323_TAP3_REG,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_TAP3_QT_BW_TAP_MSK, reg_value);
+			*val = 0;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_DUR_BW_TAP_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_TYPE_MAG:
+		reg = bmi323_motion_config_reg(dir);
+		if (reg < 0)
+			return -EINVAL;
+
+		switch (info) {
+		case IIO_EV_INFO_VALUE:
+			ret = bmi323_read_ext_reg(data, reg, &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_MO1_SLOPE_TH_MSK, reg_value);
+			*val = raw / BMI323_MOTION_THRES_SCALE;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_MOTION_THRES_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_EV_INFO_PERIOD:
+			ret = bmi323_read_ext_reg(data,
+						  reg + BMI323_MO3_OFFSET,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_MO3_DURA_MSK, reg_value);
+			*val = raw / BMI323_MOTION_DURAT_SCALE;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_MOTION_DURAT_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_EV_INFO_HYSTERESIS:
+			ret = bmi323_read_ext_reg(data,
+						  reg + BMI323_MO2_OFFSET,
+						  &reg_value);
+			if (ret)
+				return ret;
+
+			raw = FIELD_GET(BMI323_MO2_HYSTR_MSK, reg_value);
+			*val = raw / BMI323_MOTION_HYSTR_SCALE;
+			*val2 = BMI323_RAW_TO_MICRO(raw,
+						    BMI323_MOTION_HYSTR_SCALE);
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_TYPE_CHANGE:
+		ret = bmi323_read_ext_reg(data, BMI323_STEP_SC1_REG,
+					  &reg_value);
+		if (ret)
+			return ret;
+
+		raw = FIELD_GET(BMI323_STEP_SC1_WTRMRK_MSK, reg_value);
+		*val = raw * 20;
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int __bmi323_fifo_flush(struct iio_dev *indio_dev)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int i, ret, fifo_lvl, frame_count, bit, index;
+	__le16 *frame, *pchannels;
+	u64 sample_period;
+	s64 tstamp;
+
+	guard(mutex)(&data->mutex);
+	ret = regmap_read(data->regmap, BMI323_FIFO_FILL_LEVEL_REG, &fifo_lvl);
+	if (ret)
+		return ret;
+
+	fifo_lvl = min(fifo_lvl, BMI323_FIFO_FULL_IN_WORDS);
+
+	frame_count = fifo_lvl / BMI323_FIFO_FRAME_LENGTH;
+	if (!frame_count)
+		return -EINVAL;
+
+	if (fifo_lvl % BMI323_FIFO_FRAME_LENGTH)
+		dev_warn(data->dev, "Bad FIFO alignment\n");
+
+	/*
+	 * Approximate timestamps for each of the sample based on the sampling
+	 * frequency, timestamp for last sample and number of samples.
+	 */
+	if (data->old_fifo_tstamp) {
+		sample_period = data->fifo_tstamp - data->old_fifo_tstamp;
+		do_div(sample_period, frame_count);
+	} else {
+		sample_period = data->odrns[BMI323_ACCEL];
+	}
+
+	tstamp = data->fifo_tstamp - (frame_count - 1) * sample_period;
+
+	ret = regmap_noinc_read(data->regmap, BMI323_FIFO_DATA_REG,
+				&data->fifo_buff[0],
+				fifo_lvl * BMI323_BYTES_PER_SAMPLE);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < frame_count; i++) {
+		frame = &data->fifo_buff[i * BMI323_FIFO_FRAME_LENGTH];
+		pchannels = &data->buffer.channels[0];
+
+		index = 0;
+		for_each_set_bit(bit, indio_dev->active_scan_mask,
+				 BMI323_CHAN_MAX)
+			pchannels[index++] = frame[bit];
+
+		iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer,
+						   tstamp);
+
+		tstamp += sample_period;
+	}
+
+	return frame_count;
+}
+
+static int bmi323_set_watermark(struct iio_dev *indio_dev, unsigned int val)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	val = min(val, (u32)BMI323_FIFO_FULL_IN_FRAMES);
+
+	guard(mutex)(&data->mutex);
+	data->watermark = val;
+
+	return 0;
+}
+
+static int bmi323_fifo_disable(struct bmi323_data *data)
+{
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	ret = regmap_write(data->regmap, BMI323_FIFO_CONF_REG, 0);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				 BMI323_FIFO_WTRMRK_MSK,
+				 FIELD_PREP(BMI323_FIFO_WTRMRK_MSK, 0));
+	if (ret)
+		return ret;
+
+	data->fifo_tstamp = 0;
+	data->state = BMI323_IDLE;
+
+	return 0;
+}
+
+static int bmi323_buffer_predisable(struct iio_dev *indio_dev)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	if (iio_device_get_current_mode(indio_dev) == INDIO_BUFFER_TRIGGERED)
+		return 0;
+
+	return bmi323_fifo_disable(data);
+}
+
+static int bmi323_update_watermark(struct bmi323_data *data)
+{
+	int wtrmrk;
+
+	wtrmrk = data->watermark * BMI323_FIFO_FRAME_LENGTH;
+
+	return regmap_write(data->regmap, BMI323_FIFO_WTRMRK_REG, wtrmrk);
+}
+
+static int bmi323_fifo_enable(struct bmi323_data *data)
+{
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	ret = regmap_update_bits(data->regmap, BMI323_FIFO_CONF_REG,
+				 BMI323_FIFO_CONF_ACC_GYR_EN_MSK,
+				 FIELD_PREP(BMI323_FIFO_CONF_ACC_GYR_EN_MSK,
+					    BMI323_FIFO_ACC_GYR_MSK));
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				 BMI323_FIFO_WTRMRK_MSK,
+				 FIELD_PREP(BMI323_FIFO_WTRMRK_MSK,
+					    data->irq_pin));
+	if (ret)
+		return ret;
+
+	ret = bmi323_update_watermark(data);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(data->regmap, BMI323_FIFO_CTRL_REG,
+			   BMI323_FIFO_FLUSH_MSK);
+	if (ret)
+		return ret;
+
+	data->state = BMI323_BUFFER_FIFO;
+
+	return 0;
+}
+
+static int bmi323_buffer_preenable(struct iio_dev *indio_dev)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	guard(mutex)(&data->mutex);
+	/*
+	 * When the ODR of the accelerometer and gyroscope do not match, the
+	 * maximum ODR value between the accelerometer and gyroscope is used
+	 * for FIFO and the signal with lower ODR will insert dummy frame.
+	 * So allow buffer read only when ODR's of accelero and gyro are equal.
+	 * See datasheet section 5.7 "FIFO Data Buffering".
+	 */
+	if (data->odrns[BMI323_ACCEL] != data->odrns[BMI323_GYRO]) {
+		dev_err(data->dev, "Accelero and Gyro ODR doesn't match\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int bmi323_buffer_postenable(struct iio_dev *indio_dev)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+
+	if (iio_device_get_current_mode(indio_dev) == INDIO_BUFFER_TRIGGERED)
+		return 0;
+
+	return bmi323_fifo_enable(data);
+}
+
+static ssize_t hwfifo_watermark_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int wm;
+
+	scoped_guard(mutex, &data->mutex)
+		wm = data->watermark;
+
+	return sysfs_emit(buf, "%d\n", wm);
+}
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark, 0);
+
+static ssize_t hwfifo_enabled_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct bmi323_data *data = iio_priv(indio_dev);
+	bool state;
+
+	scoped_guard(mutex, &data->mutex)
+		state = data->state == BMI323_BUFFER_FIFO;
+
+	return sysfs_emit(buf, "%d\n", state);
+}
+static IIO_DEVICE_ATTR_RO(hwfifo_enabled, 0);
+
+static const struct iio_dev_attr *bmi323_fifo_attributes[] = {
+	&iio_dev_attr_hwfifo_watermark,
+	&iio_dev_attr_hwfifo_enabled,
+	NULL
+};
+
+static const struct iio_buffer_setup_ops bmi323_buffer_ops = {
+	.preenable = bmi323_buffer_preenable,
+	.postenable = bmi323_buffer_postenable,
+	.predisable = bmi323_buffer_predisable,
+};
+
+static irqreturn_t bmi323_irq_thread_handler(int irq, void *private)
+{
+	struct iio_dev *indio_dev = private;
+	struct bmi323_data *data = iio_priv(indio_dev);
+	unsigned int status_addr, status, feature_event;
+	s64 timestamp = iio_get_time_ns(indio_dev);
+	int ret;
+
+	if (data->irq_pin == BMI323_IRQ_INT1)
+		status_addr = BMI323_STATUS_INT1_REG;
+	else
+		status_addr = BMI323_STATUS_INT2_REG;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, status_addr, &status);
+		if (ret)
+			return IRQ_NONE;
+	}
+
+	if (!status || FIELD_GET(BMI323_STATUS_ERROR_MSK, status))
+		return IRQ_NONE;
+
+	if (FIELD_GET(BMI323_STATUS_FIFO_WTRMRK_MSK, status)) {
+		data->old_fifo_tstamp = data->fifo_tstamp;
+		data->fifo_tstamp = iio_get_time_ns(indio_dev);
+		ret = __bmi323_fifo_flush(indio_dev);
+		if (ret < 0)
+			return IRQ_NONE;
+	}
+
+	if (FIELD_GET(BMI323_STATUS_ACC_GYR_DRDY_MSK, status))
+		iio_trigger_poll_nested(data->trig);
+
+	if (FIELD_GET(BMI323_STATUS_MOTION_MSK, status))
+		iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_ACCEL, 0,
+							     IIO_MOD_X_OR_Y_OR_Z,
+							     IIO_EV_TYPE_MAG,
+							     IIO_EV_DIR_RISING),
+			       timestamp);
+
+	if (FIELD_GET(BMI323_STATUS_NOMOTION_MSK, status))
+		iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_ACCEL, 0,
+							     IIO_MOD_X_OR_Y_OR_Z,
+							     IIO_EV_TYPE_MAG,
+							     IIO_EV_DIR_FALLING),
+			       timestamp);
+
+	if (FIELD_GET(BMI323_STATUS_STP_WTR_MSK, status))
+		iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_STEPS, 0,
+							     IIO_NO_MOD,
+							     IIO_EV_TYPE_CHANGE,
+							     IIO_EV_DIR_NONE),
+			       timestamp);
+
+	if (FIELD_GET(BMI323_STATUS_TAP_MSK, status)) {
+		scoped_guard(mutex, &data->mutex) {
+			ret = regmap_read(data->regmap,
+					  BMI323_FEAT_EVNT_EXT_REG,
+					  &feature_event);
+			if (ret)
+				return IRQ_NONE;
+		}
+
+		if (FIELD_GET(BMI323_FEAT_EVNT_EXT_S_MSK, feature_event)) {
+			iio_push_event(indio_dev,
+				       IIO_MOD_EVENT_CODE(IIO_ACCEL, 0,
+							  IIO_MOD_X_OR_Y_OR_Z,
+							  IIO_EV_TYPE_GESTURE,
+							  IIO_EV_DIR_SINGLETAP),
+				       timestamp);
+		}
+
+		if (FIELD_GET(BMI323_FEAT_EVNT_EXT_D_MSK, feature_event))
+			iio_push_event(indio_dev,
+				       IIO_MOD_EVENT_CODE(IIO_ACCEL, 0,
+							  IIO_MOD_X_OR_Y_OR_Z,
+							  IIO_EV_TYPE_GESTURE,
+							  IIO_EV_DIR_DOUBLETAP),
+				       timestamp);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int bmi323_set_drdy_irq(struct bmi323_data *data,
+			       enum bmi323_irq_pin irq_pin)
+{
+	int ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				 BMI323_GYR_DRDY_MSK,
+				 FIELD_PREP(BMI323_GYR_DRDY_MSK, irq_pin));
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(data->regmap, BMI323_INT_MAP2_REG,
+				  BMI323_ACC_DRDY_MSK,
+				  FIELD_PREP(BMI323_ACC_DRDY_MSK, irq_pin));
+}
+
+static int bmi323_data_rdy_trigger_set_state(struct iio_trigger *trig,
+					     bool state)
+{
+	struct bmi323_data *data = iio_trigger_get_drvdata(trig);
+	enum bmi323_irq_pin irq_pin;
+
+	guard(mutex)(&data->mutex);
+
+	if (data->state == BMI323_BUFFER_FIFO) {
+		dev_warn(data->dev, "Can't set trigger when FIFO enabled\n");
+		return -EBUSY;
+	}
+
+	if (state) {
+		data->state = BMI323_BUFFER_DRDY_TRIGGERED;
+		irq_pin = data->irq_pin;
+	} else {
+		data->state = BMI323_IDLE;
+		irq_pin = BMI323_IRQ_DISABLED;
+	}
+
+	return bmi323_set_drdy_irq(data, irq_pin);
+}
+
+static const struct iio_trigger_ops bmi323_trigger_ops = {
+	.set_trigger_state = &bmi323_data_rdy_trigger_set_state,
+};
+
+static irqreturn_t bmi323_trigger_handler(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *indio_dev = pf->indio_dev;
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret, bit, index = 0;
+
+	/* Lock to protect the data->buffer */
+	guard(mutex)(&data->mutex);
+
+	if (*indio_dev->active_scan_mask == BMI323_ALL_CHAN_MSK) {
+		ret = regmap_bulk_read(data->regmap, BMI323_ACCEL_X_REG,
+				       &data->buffer.channels,
+				       ARRAY_SIZE(data->buffer.channels));
+		if (ret)
+			return IRQ_NONE;
+	} else {
+		for_each_set_bit(bit, indio_dev->active_scan_mask,
+				 BMI323_CHAN_MAX) {
+			ret = regmap_raw_read(data->regmap,
+					      BMI323_ACCEL_X_REG + bit,
+					      &data->buffer.channels[index++],
+					      BMI323_BYTES_PER_SAMPLE);
+			if (ret)
+				return IRQ_NONE;
+		}
+	}
+
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer,
+					   iio_get_time_ns(indio_dev));
+
+	iio_trigger_notify_done(indio_dev->trig);
+
+	return IRQ_HANDLED;
+}
+
+static int bmi323_set_average(struct bmi323_data *data,
+			      enum bmi323_sensor_type sensor, int avg)
+{
+	int raw = ARRAY_SIZE(bmi323_accel_gyro_avrg);
+
+	while (raw--)
+		if (avg == bmi323_accel_gyro_avrg[raw])
+			break;
+	if (raw < 0)
+		return -EINVAL;
+
+	guard(mutex)(&data->mutex);
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				 BMI323_ACC_GYRO_CONF_AVG_MSK,
+				 FIELD_PREP(BMI323_ACC_GYRO_CONF_AVG_MSK,
+					    raw));
+}
+
+static int bmi323_get_average(struct bmi323_data *data,
+			      enum bmi323_sensor_type sensor, int *avg)
+{
+	int ret, value, raw;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, bmi323_hw[sensor].config, &value);
+		if (ret)
+			return ret;
+	}
+
+	raw = FIELD_GET(BMI323_ACC_GYRO_CONF_AVG_MSK, value);
+	*avg = bmi323_accel_gyro_avrg[raw];
+
+	return IIO_VAL_INT;
+}
+
+static int bmi323_enable_steps(struct bmi323_data *data, int val)
+{
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	if (data->odrhz[BMI323_ACCEL] < 200) {
+		dev_err(data->dev, "Invalid accelrometer parameter\n");
+		return -EINVAL;
+	}
+
+	ret = bmi323_feature_engine_events(data, BMI323_FEAT_IO0_STP_CNT_MSK,
+					   val ? 1 : 0);
+	if (ret)
+		return ret;
+
+	set_mask_bits(&data->feature_events, BMI323_FEAT_IO0_STP_CNT_MSK,
+		      FIELD_PREP(BMI323_FEAT_IO0_STP_CNT_MSK, val ? 1 : 0));
+
+	return 0;
+}
+
+static int bmi323_read_steps(struct bmi323_data *data, int *val)
+{
+	int ret;
+
+	guard(mutex)(&data->mutex);
+	if (!FIELD_GET(BMI323_FEAT_IO0_STP_CNT_MSK, data->feature_events))
+		return -EINVAL;
+
+	ret = regmap_bulk_read(data->regmap, BMI323_FEAT_IO2_REG,
+			       data->steps_count,
+			       ARRAY_SIZE(data->steps_count));
+	if (ret)
+		return ret;
+
+	*val = get_unaligned_le32(data->steps_count);
+
+	return IIO_VAL_INT;
+}
+
+static int bmi323_read_axis(struct bmi323_data *data,
+			    struct iio_chan_spec const *chan, int *val)
+{
+	enum bmi323_sensor_type sensor;
+	unsigned int value;
+	u8 addr;
+	int ret;
+
+	ret = bmi323_get_error_status(data);
+	if (ret)
+		return -EINVAL;
+
+	sensor = bmi323_iio_to_sensor(chan->type);
+	addr = bmi323_hw[sensor].data + (chan->channel2 - IIO_MOD_X);
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, addr, &value);
+		if (ret)
+			return ret;
+	}
+
+	*val = sign_extend32(value, chan->scan_type.realbits - 1);
+
+	return IIO_VAL_INT;
+}
+
+static int bmi323_get_temp_data(struct bmi323_data *data, int *val)
+{
+	unsigned int value;
+	int ret;
+
+	ret = bmi323_get_error_status(data);
+	if (ret)
+		return -EINVAL;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, BMI323_TEMP_REG, &value);
+		if (ret)
+			return ret;
+	}
+
+	*val = sign_extend32(value, 15);
+
+	return IIO_VAL_INT;
+}
+
+static int bmi323_get_odr(struct bmi323_data *data,
+			  enum bmi323_sensor_type sensor, int *odr, int *uodr)
+{
+	int ret, value, odr_raw;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, bmi323_hw[sensor].config, &value);
+		if (ret)
+			return ret;
+	}
+
+	odr_raw = FIELD_GET(BMI323_ACC_GYRO_CONF_ODR_MSK, value);
+	*odr = bmi323_acc_gyro_odr[odr_raw - 1][0];
+	*uodr = bmi323_acc_gyro_odr[odr_raw - 1][1];
+
+	return IIO_VAL_INT_PLUS_MICRO;
+}
+
+static int bmi323_configure_power_mode(struct bmi323_data *data,
+				       enum bmi323_sensor_type sensor,
+				       int odr_index)
+{
+	enum bmi323_opr_mode mode;
+
+	if (bmi323_acc_gyro_odr[odr_index][0] > 25)
+		mode = ACC_GYRO_MODE_CONTINOUS;
+	else
+		mode = ACC_GYRO_MODE_DUTYCYCLE;
+
+	return bmi323_set_mode(data, sensor, mode);
+}
+
+static int bmi323_set_odr(struct bmi323_data *data,
+			  enum bmi323_sensor_type sensor, int odr, int uodr)
+{
+	int odr_raw, ret;
+
+	odr_raw = ARRAY_SIZE(bmi323_acc_gyro_odr);
+
+	while (odr_raw--)
+		if (odr == bmi323_acc_gyro_odr[odr_raw][0] &&
+		    uodr == bmi323_acc_gyro_odr[odr_raw][1])
+			break;
+	if (odr_raw < 0)
+		return -EINVAL;
+
+	ret = bmi323_configure_power_mode(data, sensor, odr_raw);
+	if (ret)
+		return -EINVAL;
+
+	guard(mutex)(&data->mutex);
+	data->odrhz[sensor] = bmi323_acc_gyro_odr[odr_raw][0];
+	data->odrns[sensor] = bmi323_acc_gyro_odrns[odr_raw];
+
+	odr_raw++;
+
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				  BMI323_ACC_GYRO_CONF_ODR_MSK,
+				  FIELD_PREP(BMI323_ACC_GYRO_CONF_ODR_MSK,
+					     odr_raw));
+}
+
+static int bmi323_get_scale(struct bmi323_data *data,
+			    enum bmi323_sensor_type sensor, int *val2)
+{
+	int ret, value, scale_raw;
+
+	scoped_guard(mutex, &data->mutex) {
+		ret = regmap_read(data->regmap, bmi323_hw[sensor].config,
+				  &value);
+		if (ret)
+			return ret;
+	}
+
+	scale_raw = FIELD_GET(BMI323_ACC_GYRO_CONF_SCL_MSK, value);
+	*val2 = bmi323_hw[sensor].scale_table[scale_raw][1];
+
+	return IIO_VAL_INT_PLUS_MICRO;
+}
+
+static int bmi323_set_scale(struct bmi323_data *data,
+			    enum bmi323_sensor_type sensor, int val, int val2)
+{
+	int scale_raw;
+
+	scale_raw = bmi323_hw[sensor].scale_table_len;
+
+	while (scale_raw--)
+		if (val == bmi323_hw[sensor].scale_table[scale_raw][0] &&
+		    val2 == bmi323_hw[sensor].scale_table[scale_raw][1])
+			break;
+	if (scale_raw < 0)
+		return -EINVAL;
+
+	guard(mutex)(&data->mutex);
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				  BMI323_ACC_GYRO_CONF_SCL_MSK,
+				  FIELD_PREP(BMI323_ACC_GYRO_CONF_SCL_MSK,
+					     scale_raw));
+}
+
+static int bmi323_read_avail(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     const int **vals, int *type, int *length,
+			     long mask)
+{
+	enum bmi323_sensor_type sensor;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		*vals = (const int *)bmi323_acc_gyro_odr;
+		*length = ARRAY_SIZE(bmi323_acc_gyro_odr) * 2;
+		return IIO_AVAIL_LIST;
+	case IIO_CHAN_INFO_SCALE:
+		sensor = bmi323_iio_to_sensor(chan->type);
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		*vals = (const int *)bmi323_hw[sensor].scale_table;
+		*length = bmi323_hw[sensor].scale_table_len * 2;
+		return IIO_AVAIL_LIST;
+	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+		*type = IIO_VAL_INT;
+		*vals = (const int *)bmi323_accel_gyro_avrg;
+		*length = ARRAY_SIZE(bmi323_accel_gyro_avrg);
+		return IIO_AVAIL_LIST;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_write_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan, int val,
+			    int val2, long mask)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		ret = iio_device_claim_direct_mode(indio_dev);
+		if (ret)
+			return ret;
+
+		ret = bmi323_set_odr(data, bmi323_iio_to_sensor(chan->type),
+				     val, val2);
+		iio_device_release_direct_mode(indio_dev);
+		return ret;
+	case IIO_CHAN_INFO_SCALE:
+		ret = iio_device_claim_direct_mode(indio_dev);
+		if (ret)
+			return ret;
+
+		ret = bmi323_set_scale(data, bmi323_iio_to_sensor(chan->type),
+				       val, val2);
+		iio_device_release_direct_mode(indio_dev);
+		return ret;
+	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+		ret = iio_device_claim_direct_mode(indio_dev);
+		if (ret)
+			return ret;
+
+		ret = bmi323_set_average(data, bmi323_iio_to_sensor(chan->type),
+					 val);
+
+		iio_device_release_direct_mode(indio_dev);
+		return ret;
+	case IIO_CHAN_INFO_ENABLE:
+		return bmi323_enable_steps(data, val);
+	case IIO_CHAN_INFO_PROCESSED:
+		scoped_guard(mutex, &data->mutex) {
+			if (val || !FIELD_GET(BMI323_FEAT_IO0_STP_CNT_MSK,
+					      data->feature_events))
+				return -EINVAL;
+
+			/* Clear step counter value */
+			ret = bmi323_update_ext_reg(data, BMI323_STEP_SC1_REG,
+						    BMI323_STEP_SC1_RST_CNT_MSK,
+						    FIELD_PREP(BMI323_STEP_SC1_RST_CNT_MSK,
+							       1));
+		}
+		return ret;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int bmi323_read_raw(struct iio_dev *indio_dev,
+			   struct iio_chan_spec const *chan, int *val,
+			   int *val2, long mask)
+{
+	struct bmi323_data *data = iio_priv(indio_dev);
+	int ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_PROCESSED:
+		return bmi323_read_steps(data, val);
+	case IIO_CHAN_INFO_RAW:
+		switch (chan->type) {
+		case IIO_ACCEL:
+		case IIO_ANGL_VEL:
+			ret = iio_device_claim_direct_mode(indio_dev);
+			if (ret)
+				return ret;
+
+			ret = bmi323_read_axis(data, chan, val);
+
+			iio_device_release_direct_mode(indio_dev);
+			return ret;
+		case IIO_TEMP:
+			return bmi323_get_temp_data(data, val);
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		return bmi323_get_odr(data, bmi323_iio_to_sensor(chan->type),
+				      val, val2);
+	case IIO_CHAN_INFO_SCALE:
+		switch (chan->type) {
+		case IIO_ACCEL:
+		case IIO_ANGL_VEL:
+			*val = 0;
+			return bmi323_get_scale(data,
+						bmi323_iio_to_sensor(chan->type),
+						val2);
+		case IIO_TEMP:
+			*val = BMI323_TEMP_SCALE / MEGA;
+			*val2 = BMI323_TEMP_SCALE % MEGA;
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+		return bmi323_get_average(data,
+					  bmi323_iio_to_sensor(chan->type),
+					  val);
+	case IIO_CHAN_INFO_OFFSET:
+		switch (chan->type) {
+		case IIO_TEMP:
+			*val = BMI323_TEMP_OFFSET;
+			return IIO_VAL_INT;
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_ENABLE:
+		scoped_guard(mutex, &data->mutex)
+			*val = FIELD_GET(BMI323_FEAT_IO0_STP_CNT_MSK,
+					 data->feature_events);
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info bmi323_info = {
+	.read_raw = bmi323_read_raw,
+	.write_raw = bmi323_write_raw,
+	.read_avail = bmi323_read_avail,
+	.hwfifo_set_watermark = bmi323_set_watermark,
+	.write_event_config = bmi323_write_event_config,
+	.read_event_config = bmi323_read_event_config,
+	.write_event_value = bmi323_write_event_value,
+	.read_event_value = bmi323_read_event_value,
+	.event_attrs = &bmi323_event_attribute_group,
+};
+
+#define BMI323_SCAN_MASK_ACCEL_3AXIS		\
+	(BIT(BMI323_ACCEL_X) | BIT(BMI323_ACCEL_Y) | BIT(BMI323_ACCEL_Z))
+
+#define BMI323_SCAN_MASK_GYRO_3AXIS		\
+	(BIT(BMI323_GYRO_X) | BIT(BMI323_GYRO_Y) | BIT(BMI323_GYRO_Z))
+
+static const unsigned long bmi323_avail_scan_masks[] = {
+	/* 3-axis accel */
+	BMI323_SCAN_MASK_ACCEL_3AXIS,
+	/* 3-axis gyro */
+	BMI323_SCAN_MASK_GYRO_3AXIS,
+	/* 3-axis accel + 3-axis gyro */
+	BMI323_SCAN_MASK_ACCEL_3AXIS | BMI323_SCAN_MASK_GYRO_3AXIS,
+	0
+};
+
+static int bmi323_int_pin_config(struct bmi323_data *data,
+				 enum bmi323_irq_pin irq_pin,
+				 bool active_high, bool open_drain, bool latch)
+{
+	unsigned int mask, field_value;
+	int ret;
+
+	ret = regmap_update_bits(data->regmap, BMI323_IO_INT_CONF_REG,
+				 BMI323_IO_INT_LTCH_MSK,
+				 FIELD_PREP(BMI323_IO_INT_LTCH_MSK, latch));
+	if (ret)
+		return ret;
+
+	ret = bmi323_update_ext_reg(data, BMI323_GEN_SET1_REG,
+				    BMI323_GEN_HOLD_DUR_MSK,
+				    FIELD_PREP(BMI323_GEN_HOLD_DUR_MSK, 0));
+	if (ret)
+		return ret;
+
+	switch (irq_pin) {
+	case BMI323_IRQ_INT1:
+		mask = BMI323_IO_INT1_LVL_OD_OP_MSK;
+
+		field_value = FIELD_PREP(BMI323_IO_INT1_LVL_MSK, active_high) |
+			      FIELD_PREP(BMI323_IO_INT1_OD_MSK, open_drain) |
+			      FIELD_PREP(BMI323_IO_INT1_OP_EN_MSK, 1);
+		break;
+	case BMI323_IRQ_INT2:
+		mask = BMI323_IO_INT2_LVL_OD_OP_MSK;
+
+		field_value = FIELD_PREP(BMI323_IO_INT2_LVL_MSK, active_high) |
+			      FIELD_PREP(BMI323_IO_INT2_OD_MSK, open_drain) |
+			      FIELD_PREP(BMI323_IO_INT2_OP_EN_MSK, 1);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return regmap_update_bits(data->regmap, BMI323_IO_INT_CTR_REG, mask,
+				  field_value);
+}
+
+static int bmi323_trigger_probe(struct bmi323_data *data,
+				struct iio_dev *indio_dev)
+{
+	bool open_drain, active_high, latch;
+	struct fwnode_handle *fwnode;
+	enum bmi323_irq_pin irq_pin;
+	int ret, irq, irq_type;
+	struct irq_data *desc;
+
+	fwnode = dev_fwnode(data->dev);
+	if (!fwnode)
+		return -ENODEV;
+
+	irq = fwnode_irq_get_byname(fwnode, "INT1");
+	if (irq > 0) {
+		irq_pin = BMI323_IRQ_INT1;
+	} else {
+		irq = fwnode_irq_get_byname(fwnode, "INT2");
+		if (irq < 0)
+			return 0;
+
+		irq_pin = BMI323_IRQ_INT2;
+	}
+
+	desc = irq_get_irq_data(irq);
+	if (!desc)
+		return dev_err_probe(data->dev, -EINVAL,
+				     "Could not find IRQ %d\n", irq);
+
+	irq_type = irqd_get_trigger_type(desc);
+	switch (irq_type) {
+	case IRQF_TRIGGER_RISING:
+		latch = false;
+		active_high = true;
+		break;
+	case IRQF_TRIGGER_HIGH:
+		latch = true;
+		active_high = true;
+		break;
+	case IRQF_TRIGGER_FALLING:
+		latch = false;
+		active_high = false;
+		break;
+	case IRQF_TRIGGER_LOW:
+		latch = true;
+		active_high = false;
+		break;
+	default:
+		return dev_err_probe(data->dev, -EINVAL,
+				     "Invalid interrupt type 0x%x specified\n",
+				     irq_type);
+	}
+
+	open_drain = fwnode_property_read_bool(fwnode, "drive-open-drain");
+
+	ret = bmi323_int_pin_config(data, irq_pin, active_high, open_drain,
+				    latch);
+	if (ret)
+		return dev_err_probe(data->dev, ret,
+				     "Failed to configure irq line\n");
+
+	data->trig = devm_iio_trigger_alloc(data->dev, "%s-trig-%d",
+					    indio_dev->name, irq_pin);
+	if (!data->trig)
+		return -ENOMEM;
+
+	data->trig->ops = &bmi323_trigger_ops;
+	iio_trigger_set_drvdata(data->trig, data);
+
+	ret = devm_request_threaded_irq(data->dev, irq, NULL,
+					bmi323_irq_thread_handler,
+					IRQF_ONESHOT, "bmi323-int", indio_dev);
+	if (ret)
+		return dev_err_probe(data->dev, ret, "Failed to request IRQ\n");
+
+	ret = devm_iio_trigger_register(data->dev, data->trig);
+	if (ret)
+		return dev_err_probe(data->dev, ret,
+				     "Trigger registration failed\n");
+
+	data->irq_pin = irq_pin;
+
+	return 0;
+}
+
+static int bmi323_feature_engine_enable(struct bmi323_data *data, bool en)
+{
+	unsigned int feature_status;
+	int ret;
+
+	if (!en)
+		return regmap_write(data->regmap, BMI323_FEAT_CTRL_REG, 0);
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_IO2_REG, 0x012c);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_IO_STATUS_REG,
+			   BMI323_FEAT_IO_STATUS_MSK);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(data->regmap, BMI323_FEAT_CTRL_REG,
+			   BMI323_FEAT_ENG_EN_MSK);
+	if (ret)
+		return ret;
+
+	/*
+	 * It takes around 4 msec to enable the Feature engine, so check
+	 * the status of the feature engine every 2 msec for a maximum
+	 * of 5 trials.
+	 */
+	ret = regmap_read_poll_timeout(data->regmap, BMI323_FEAT_IO1_REG,
+				       feature_status,
+				       FIELD_GET(BMI323_FEAT_IO1_ERR_MSK,
+						 feature_status) == 1,
+				       BMI323_FEAT_ENG_POLL,
+				       BMI323_FEAT_ENG_TIMEOUT);
+	if (ret)
+		return dev_err_probe(data->dev, -EINVAL,
+				"Failed to enable feature engine\n");
+
+	return 0;
+}
+
+static void bmi323_disable(void *data_ptr)
+{
+	struct bmi323_data *data = data_ptr;
+
+	bmi323_set_mode(data, BMI323_ACCEL, ACC_GYRO_MODE_DISABLE);
+	bmi323_set_mode(data, BMI323_GYRO, ACC_GYRO_MODE_DISABLE);
+}
+
+static int bmi323_set_bw(struct bmi323_data *data,
+			 enum bmi323_sensor_type sensor, enum bmi323_3db_bw bw)
+{
+	return regmap_update_bits(data->regmap, bmi323_hw[sensor].config,
+				  BMI323_ACC_GYRO_CONF_BW_MSK,
+				  FIELD_PREP(BMI323_ACC_GYRO_CONF_BW_MSK, bw));
+}
+
+static int bmi323_init(struct bmi323_data *data)
+{
+	int ret, val;
+
+	/*
+	 * Perform soft reset to make sure the device is in a known state after
+	 * start up. A delay of 1.5 ms is required after reset.
+	 * See datasheet section 5.17 "Soft Reset".
+	 */
+	ret = regmap_write(data->regmap, BMI323_CMD_REG, BMI323_RST_VAL);
+	if (ret)
+		return ret;
+
+	usleep_range(1500, 2000);
+
+	/*
+	 * Dummy read is required to enable SPI interface after reset.
+	 * See datasheet section 7.2.1 "Protocol Selection".
+	 */
+	regmap_read(data->regmap, BMI323_CHIP_ID_REG, &val);
+
+	ret = regmap_read(data->regmap, BMI323_STATUS_REG, &val);
+	if (ret)
+		return ret;
+
+	if (!FIELD_GET(BMI323_STATUS_POR_MSK, val))
+		return dev_err_probe(data->dev, -EINVAL,
+				     "Sensor initialization error\n");
+
+	ret = regmap_read(data->regmap, BMI323_CHIP_ID_REG, &val);
+	if (ret)
+		return ret;
+
+	if (FIELD_GET(BMI323_CHIP_ID_MSK, val) != BMI323_CHIP_ID_VAL)
+		return dev_err_probe(data->dev, -EINVAL, "Chip ID mismatch\n");
+
+	ret = bmi323_feature_engine_enable(data, true);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(data->regmap, BMI323_ERR_REG, &val);
+	if (ret)
+		return ret;
+
+	if (val)
+		return dev_err_probe(data->dev, -EINVAL,
+				     "Sensor power error = 0x%x\n", val);
+
+	/*
+	 * Set the Bandwidth coefficient which defines the 3 dB cutoff
+	 * frequency in relation to the ODR.
+	 */
+	ret = bmi323_set_bw(data, BMI323_ACCEL, BMI323_BW_ODR_BY_2);
+	if (ret)
+		return ret;
+
+	ret = bmi323_set_bw(data, BMI323_GYRO, BMI323_BW_ODR_BY_2);
+	if (ret)
+		return ret;
+
+	ret = bmi323_set_odr(data, BMI323_ACCEL, 25, 0);
+	if (ret)
+		return ret;
+
+	ret = bmi323_set_odr(data, BMI323_GYRO, 25, 0);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(data->dev, bmi323_disable, data);
+}
+
+int bmi323_core_probe(struct device *dev)
+{
+	static const char * const regulator_names[] = { "vdd", "vddio" };
+	struct iio_dev *indio_dev;
+	struct bmi323_data *data;
+	struct regmap *regmap;
+	int ret;
+
+	regmap = dev_get_regmap(dev, NULL);
+	if (!regmap)
+		return dev_err_probe(dev, -ENODEV, "Failed to get regmap\n");
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
+	if (!indio_dev)
+		return dev_err_probe(dev, -ENOMEM,
+				     "Failed to allocate device\n");
+
+	ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(regulator_names),
+					     regulator_names);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to enable regulators\n");
+
+	data = iio_priv(indio_dev);
+	data->dev = dev;
+	data->regmap = regmap;
+	mutex_init(&data->mutex);
+
+	ret = bmi323_init(data);
+	if (ret)
+		return -EINVAL;
+
+	ret = iio_read_mount_matrix(dev, &data->orientation);
+	if (ret)
+		return ret;
+
+	indio_dev->name = "bmi323-imu";
+	indio_dev->info = &bmi323_info;
+	indio_dev->channels = bmi323_channels;
+	indio_dev->num_channels = ARRAY_SIZE(bmi323_channels);
+	indio_dev->available_scan_masks = bmi323_avail_scan_masks;
+	indio_dev->modes = INDIO_DIRECT_MODE | INDIO_BUFFER_SOFTWARE;
+	dev_set_drvdata(data->dev, indio_dev);
+
+	ret = bmi323_trigger_probe(data, indio_dev);
+	if (ret)
+		return -EINVAL;
+
+	ret = devm_iio_triggered_buffer_setup_ext(data->dev, indio_dev,
+						  &iio_pollfunc_store_time,
+						  bmi323_trigger_handler,
+						  IIO_BUFFER_DIRECTION_IN,
+						  &bmi323_buffer_ops,
+						  bmi323_fifo_attributes);
+	if (ret)
+		return dev_err_probe(data->dev, ret,
+				     "Failed to setup trigger buffer\n");
+
+	ret = devm_iio_device_register(data->dev, indio_dev);
+	if (ret)
+		return dev_err_probe(data->dev, ret,
+				     "Unable to register iio device\n");
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(bmi323_core_probe, IIO_BMI323);
+
+MODULE_DESCRIPTION("Bosch BMI323 IMU driver");
+MODULE_AUTHOR("Jagath Jog J <jagathjog1996@gmail.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/imu/bmi323/bmi323_i2c.c b/drivers/iio/imu/bmi323/bmi323_i2c.c
new file mode 100644
index 0000000000000..0008e186367d6
--- /dev/null
+++ b/drivers/iio/imu/bmi323/bmi323_i2c.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * I2C driver for Bosch BMI323 6-Axis IMU.
+ *
+ * Copyright (C) 2023, Jagath Jog J <jagathjog1996@gmail.com>
+ */
+
+#include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+#include "bmi323.h"
+
+struct bmi323_i2c_priv {
+	struct i2c_client *i2c;
+	u8 i2c_rx_buffer[BMI323_FIFO_LENGTH_IN_BYTES + BMI323_I2C_DUMMY];
+};
+
+/*
+ * From BMI323 datasheet section 4: Notes on the Serial Interface Support.
+ * Each I2C register read operation requires to read two dummy bytes before
+ * the actual payload.
+ */
+static int bmi323_regmap_i2c_read(void *context, const void *reg_buf,
+				  size_t reg_size, void *val_buf,
+				  size_t val_size)
+{
+	struct bmi323_i2c_priv *priv = context;
+	struct i2c_msg msgs[2];
+	int ret;
+
+	msgs[0].addr = priv->i2c->addr;
+	msgs[0].flags = priv->i2c->flags;
+	msgs[0].len = reg_size;
+	msgs[0].buf = (u8 *)reg_buf;
+
+	msgs[1].addr = priv->i2c->addr;
+	msgs[1].len = val_size + BMI323_I2C_DUMMY;
+	msgs[1].buf = priv->i2c_rx_buffer;
+	msgs[1].flags = priv->i2c->flags | I2C_M_RD;
+
+	ret = i2c_transfer(priv->i2c->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret < 0)
+		return -EIO;
+
+	memcpy(val_buf, priv->i2c_rx_buffer + BMI323_I2C_DUMMY, val_size);
+
+	return 0;
+}
+
+static int bmi323_regmap_i2c_write(void *context, const void *data,
+				   size_t count)
+{
+	struct bmi323_i2c_priv *priv = context;
+	u8 reg;
+
+	reg = *(u8 *)data;
+	return i2c_smbus_write_i2c_block_data(priv->i2c, reg,
+					      count - sizeof(u8),
+					      data + sizeof(u8));
+}
+
+static struct regmap_bus bmi323_regmap_bus = {
+	.read = bmi323_regmap_i2c_read,
+	.write = bmi323_regmap_i2c_write,
+};
+
+const struct regmap_config bmi323_i2c_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+	.max_register = BMI323_CFG_RES_REG,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+};
+
+static int bmi323_i2c_probe(struct i2c_client *i2c)
+{
+	struct device *dev = &i2c->dev;
+	struct bmi323_i2c_priv *priv;
+	struct regmap *regmap;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->i2c = i2c;
+	regmap = devm_regmap_init(dev, &bmi323_regmap_bus, priv,
+				  &bmi323_i2c_regmap_config);
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap),
+				     "Failed to initialize I2C Regmap\n");
+
+	return bmi323_core_probe(dev);
+}
+
+static const struct i2c_device_id bmi323_i2c_ids[] = {
+	{ "bmi323" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, bmi323_i2c_ids);
+
+static const struct of_device_id bmi323_of_i2c_match[] = {
+	{ .compatible = "bosch,bmi323" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, bmi323_of_i2c_match);
+
+static struct i2c_driver bmi323_i2c_driver = {
+	.driver = {
+		.name = "bmi323",
+		.of_match_table = bmi323_of_i2c_match,
+	},
+	.probe = bmi323_i2c_probe,
+	.id_table = bmi323_i2c_ids,
+};
+module_i2c_driver(bmi323_i2c_driver);
+
+MODULE_DESCRIPTION("Bosch BMI323 IMU driver");
+MODULE_AUTHOR("Jagath Jog J <jagathjog1996@gmail.com>");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_BMI323);
diff --git a/drivers/iio/imu/bmi323/bmi323_spi.c b/drivers/iio/imu/bmi323/bmi323_spi.c
new file mode 100644
index 0000000000000..6dc3352dd7143
--- /dev/null
+++ b/drivers/iio/imu/bmi323/bmi323_spi.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SPI driver for Bosch BMI323 6-Axis IMU.
+ *
+ * Copyright (C) 2023, Jagath Jog J <jagathjog1996@gmail.com>
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+
+#include "bmi323.h"
+
+/*
+ * From BMI323 datasheet section 4: Notes on the Serial Interface Support.
+ * Each SPI register read operation requires to read one dummy byte before
+ * the actual payload.
+ */
+static int bmi323_regmap_spi_read(void *context, const void *reg_buf,
+				  size_t reg_size, void *val_buf,
+				  size_t val_size)
+{
+	struct spi_device *spi = context;
+
+	return spi_write_then_read(spi, reg_buf, reg_size, val_buf, val_size);
+}
+
+static int bmi323_regmap_spi_write(void *context, const void *data,
+				   size_t count)
+{
+	struct spi_device *spi = context;
+	u8 *data_buff = (u8 *)data;
+
+	data_buff[1] = data_buff[0];
+	return spi_write(spi, data_buff + 1, count - 1);
+}
+
+static struct regmap_bus bmi323_regmap_bus = {
+	.read = bmi323_regmap_spi_read,
+	.write = bmi323_regmap_spi_write,
+};
+
+const struct regmap_config bmi323_spi_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+	.pad_bits = 8,
+	.read_flag_mask = BIT(7),
+	.max_register = BMI323_CFG_RES_REG,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+};
+
+static int bmi323_spi_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct regmap *regmap;
+
+	regmap = devm_regmap_init(dev, &bmi323_regmap_bus, dev,
+				  &bmi323_spi_regmap_config);
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap),
+				     "Failed to initialize SPI Regmap\n");
+
+	return bmi323_core_probe(dev);
+}
+
+static const struct spi_device_id bmi323_spi_ids[] = {
+	{ "bmi323" },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, bmi323_spi_ids);
+
+static const struct of_device_id bmi323_of_spi_match[] = {
+	{ .compatible = "bosch,bmi323" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, bmi323_of_spi_match);
+
+static struct spi_driver bmi323_spi_driver = {
+	.driver = {
+		.name = "bmi323",
+		.of_match_table = bmi323_of_spi_match,
+	},
+	.probe = bmi323_spi_probe,
+	.id_table = bmi323_spi_ids,
+};
+module_spi_driver(bmi323_spi_driver);
+
+MODULE_DESCRIPTION("Bosch BMI323 IMU driver");
+MODULE_AUTHOR("Jagath Jog J <jagathjog1996@gmail.com>");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_BMI323);
-- 
GitLab


From f9b9ff95be8ce0e8becfd17b416b68d13915733d Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Mon, 16 Oct 2023 08:54:22 -0500
Subject: [PATCH 0182/4076] iio: resolver: ad2s1210: add support for
 adi,fixed-mode

It is possible to use the AD2S1210 with hardwired mode pins (A0 and A1).
According to the devicetree bindings, in this case the adi,fixed-mode
property will specify which of the 3 possible modes the mode pins are
hardwired for and the gpio-modes property is not allowed.

This adds support for the case where the mode pins are hardwired for
config mode. In this configuration, the position and value must be read
from the config register.

The case of hardwired position or velocity mode is not supported as
there would be no way to configure the device.

Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231016135423.16808-1-dlechner@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/resolver/ad2s1210.c | 150 +++++++++++++++++++++++++-------
 1 file changed, 119 insertions(+), 31 deletions(-)

diff --git a/drivers/iio/resolver/ad2s1210.c b/drivers/iio/resolver/ad2s1210.c
index 1bd1b950e7cc5..8646389ec88de 100644
--- a/drivers/iio/resolver/ad2s1210.c
+++ b/drivers/iio/resolver/ad2s1210.c
@@ -141,7 +141,7 @@ struct ad2s1210_state {
 	struct spi_device *sdev;
 	/** GPIO pin connected to SAMPLE line. */
 	struct gpio_desc *sample_gpio;
-	/** GPIO pins connected to A0 and A1 lines. */
+	/** GPIO pins connected to A0 and A1 lines (optional). */
 	struct gpio_descs *mode_gpios;
 	/** Used to access config registers. */
 	struct regmap *regmap;
@@ -149,6 +149,8 @@ struct ad2s1210_state {
 	unsigned long clkin_hz;
 	/** Available raw hysteresis values based on resolution. */
 	int hysteresis_available[2];
+	/* adi,fixed-mode property - only valid when mode_gpios == NULL. */
+	enum ad2s1210_mode fixed_mode;
 	/** The selected resolution */
 	enum ad2s1210_resolution resolution;
 	/** Copy of fault register from the previous read. */
@@ -175,6 +177,9 @@ static int ad2s1210_set_mode(struct ad2s1210_state *st, enum ad2s1210_mode mode)
 	struct gpio_descs *gpios = st->mode_gpios;
 	DECLARE_BITMAP(bitmap, 2);
 
+	if (!gpios)
+		return mode == st->fixed_mode ? 0 : -EOPNOTSUPP;
+
 	bitmap[0] = mode;
 
 	return gpiod_set_array_value(gpios->ndescs, gpios->desc, gpios->info,
@@ -276,7 +281,8 @@ static int ad2s1210_regmap_reg_read(void *context, unsigned int reg,
 	 * parity error. The fault register is read-only and the D7 bit means
 	 * something else there.
 	 */
-	if (reg != AD2S1210_REG_FAULT && st->rx[1] & AD2S1210_ADDRESS_DATA)
+	if ((reg > AD2S1210_REG_VELOCITY_LSB && reg != AD2S1210_REG_FAULT)
+	     && st->rx[1] & AD2S1210_ADDRESS_DATA)
 		return -EBADMSG;
 
 	*val = st->rx[1];
@@ -450,21 +456,53 @@ static int ad2s1210_single_conversion(struct iio_dev *indio_dev,
 	ad2s1210_toggle_sample_line(st);
 	timestamp = iio_get_time_ns(indio_dev);
 
-	switch (chan->type) {
-	case IIO_ANGL:
-		ret = ad2s1210_set_mode(st, MOD_POS);
-		break;
-	case IIO_ANGL_VEL:
-		ret = ad2s1210_set_mode(st, MOD_VEL);
-		break;
-	default:
-		return -EINVAL;
+	if (st->fixed_mode == MOD_CONFIG) {
+		unsigned int reg_val;
+
+		switch (chan->type) {
+		case IIO_ANGL:
+			ret = regmap_bulk_read(st->regmap,
+					       AD2S1210_REG_POSITION_MSB,
+					       &st->sample.raw, 2);
+			if (ret < 0)
+				return ret;
+
+			break;
+		case IIO_ANGL_VEL:
+			ret = regmap_bulk_read(st->regmap,
+					       AD2S1210_REG_VELOCITY_MSB,
+					       &st->sample.raw, 2);
+			if (ret < 0)
+				return ret;
+
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		ret = regmap_read(st->regmap, AD2S1210_REG_FAULT, &reg_val);
+		if (ret < 0)
+			return ret;
+
+		st->sample.fault = reg_val;
+	} else {
+		switch (chan->type) {
+		case IIO_ANGL:
+			ret = ad2s1210_set_mode(st, MOD_POS);
+			break;
+		case IIO_ANGL_VEL:
+			ret = ad2s1210_set_mode(st, MOD_VEL);
+			break;
+		default:
+			return -EINVAL;
+		}
+		if (ret < 0)
+			return ret;
+
+		ret = spi_read(st->sdev, &st->sample, 3);
+		if (ret < 0)
+			return ret;
 	}
-	if (ret < 0)
-		return ret;
-	ret = spi_read(st->sdev, &st->sample, 3);
-	if (ret < 0)
-		return ret;
 
 	switch (chan->type) {
 	case IIO_ANGL:
@@ -1252,27 +1290,53 @@ static irqreturn_t ad2s1210_trigger_handler(int irq, void *p)
 	ad2s1210_toggle_sample_line(st);
 
 	if (test_bit(0, indio_dev->active_scan_mask)) {
-		ret = ad2s1210_set_mode(st, MOD_POS);
-		if (ret < 0)
-			goto error_ret;
-
-		ret = spi_read(st->sdev, &st->sample, 3);
-		if (ret < 0)
-			goto error_ret;
+		if (st->fixed_mode == MOD_CONFIG) {
+			ret = regmap_bulk_read(st->regmap,
+					       AD2S1210_REG_POSITION_MSB,
+					       &st->sample.raw, 2);
+			if (ret < 0)
+				goto error_ret;
+		} else {
+			ret = ad2s1210_set_mode(st, MOD_POS);
+			if (ret < 0)
+				goto error_ret;
+
+			ret = spi_read(st->sdev, &st->sample, 3);
+			if (ret < 0)
+				goto error_ret;
+		}
 
 		memcpy(&st->scan.chan[chan++], &st->sample.raw, 2);
 	}
 
 	if (test_bit(1, indio_dev->active_scan_mask)) {
-		ret = ad2s1210_set_mode(st, MOD_VEL);
-		if (ret < 0)
-			goto error_ret;
+		if (st->fixed_mode == MOD_CONFIG) {
+			ret = regmap_bulk_read(st->regmap,
+					       AD2S1210_REG_VELOCITY_MSB,
+					       &st->sample.raw, 2);
+			if (ret < 0)
+				goto error_ret;
+		} else {
+			ret = ad2s1210_set_mode(st, MOD_VEL);
+			if (ret < 0)
+				goto error_ret;
+
+			ret = spi_read(st->sdev, &st->sample, 3);
+			if (ret < 0)
+				goto error_ret;
+		}
 
-		ret = spi_read(st->sdev, &st->sample, 3);
+		memcpy(&st->scan.chan[chan++], &st->sample.raw, 2);
+	}
+
+	if (st->fixed_mode == MOD_CONFIG) {
+		unsigned int reg_val;
+
+		ret = regmap_read(st->regmap, AD2S1210_REG_FAULT, &reg_val);
 		if (ret < 0)
-			goto error_ret;
+			return ret;
 
-		memcpy(&st->scan.chan[chan++], &st->sample.raw, 2);
+		st->sample.fault = reg_val;
 	}
 
 	ad2s1210_push_events(indio_dev, st->sample.fault, pf->timestamp);
@@ -1299,9 +1363,24 @@ static const struct iio_info ad2s1210_info = {
 static int ad2s1210_setup_properties(struct ad2s1210_state *st)
 {
 	struct device *dev = &st->sdev->dev;
+	const char *str_val;
 	u32 val;
 	int ret;
 
+	ret = device_property_read_string(dev, "adi,fixed-mode", &str_val);
+	if (ret == -EINVAL)
+		st->fixed_mode = -1;
+	else if (ret < 0)
+		return dev_err_probe(dev, ret,
+			"failed to read adi,fixed-mode property\n");
+	else {
+		if (strcmp(str_val, "config"))
+			return dev_err_probe(dev, -EINVAL,
+				"only adi,fixed-mode=\"config\" is supported\n");
+
+		st->fixed_mode = MOD_CONFIG;
+	}
+
 	ret = device_property_read_u32(dev, "assigned-resolution-bits", &val);
 	if (ret < 0)
 		return dev_err_probe(dev, ret,
@@ -1357,12 +1436,21 @@ static int ad2s1210_setup_gpios(struct ad2s1210_state *st)
 				     "failed to request sample GPIO\n");
 
 	/* both pins high means that we start in config mode */
-	st->mode_gpios = devm_gpiod_get_array(dev, "mode", GPIOD_OUT_HIGH);
+	st->mode_gpios = devm_gpiod_get_array_optional(dev, "mode",
+						       GPIOD_OUT_HIGH);
 	if (IS_ERR(st->mode_gpios))
 		return dev_err_probe(dev, PTR_ERR(st->mode_gpios),
 				     "failed to request mode GPIOs\n");
 
-	if (st->mode_gpios->ndescs != 2)
+	if (!st->mode_gpios && st->fixed_mode == -1)
+		return dev_err_probe(dev, -EINVAL,
+			"must specify either adi,fixed-mode or mode-gpios\n");
+
+	if (st->mode_gpios && st->fixed_mode != -1)
+		return dev_err_probe(dev, -EINVAL,
+			"must specify only one of adi,fixed-mode or mode-gpios\n");
+
+	if (st->mode_gpios && st->mode_gpios->ndescs != 2)
 		return dev_err_probe(dev, -EINVAL,
 				     "requires exactly 2 mode-gpios\n");
 
-- 
GitLab


From 0300fa851f38864495e6cb107d9a24d30dcb5e19 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Mon, 16 Oct 2023 10:43:09 -0500
Subject: [PATCH 0183/4076] iio: resolver: ad2s1210: add reset gpio support

This adds support for the optional reset gpio to the ad2s1210 resolver
driver. If the gpio is present in the device tree, it is toggled during
driver probe before the reset of the device initialization. As per the
devicetree bindings, it is expected for the gpio to configured as active
low.

Suggested-by: Michael Hennerich <Michael.Hennerich@analog.com>
Signed-off-by: David Lechner <dlechner@baylibre.com>
Acked-by: Michael Hennerich <michael.hennerich@analog.com>
Link: https://lore.kernel.org/r/20231016154311.38547-1-dlechner@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/resolver/ad2s1210.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/iio/resolver/ad2s1210.c b/drivers/iio/resolver/ad2s1210.c
index 8646389ec88de..a414eef12e5e3 100644
--- a/drivers/iio/resolver/ad2s1210.c
+++ b/drivers/iio/resolver/ad2s1210.c
@@ -1426,6 +1426,7 @@ static int ad2s1210_setup_gpios(struct ad2s1210_state *st)
 {
 	struct device *dev = &st->sdev->dev;
 	struct gpio_descs *resolution_gpios;
+	struct gpio_desc *reset_gpio;
 	DECLARE_BITMAP(bitmap, 2);
 	int ret;
 
@@ -1481,6 +1482,17 @@ static int ad2s1210_setup_gpios(struct ad2s1210_state *st)
 					     "failed to set resolution gpios\n");
 	}
 
+	/* If the optional reset GPIO is present, toggle it to do a hard reset. */
+	reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(reset_gpio))
+		return dev_err_probe(dev, PTR_ERR(reset_gpio),
+				     "failed to request reset GPIO\n");
+
+	if (reset_gpio) {
+		udelay(10);
+		gpiod_set_value(reset_gpio, 0);
+	}
+
 	return 0;
 }
 
-- 
GitLab


From 086386311b3620059d0253eda511f88ca4cdeceb Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 8 Aug 2023 19:27:55 +0300
Subject: [PATCH 0184/4076] device property: Use
 fwnode_property_string_array_count()

Use fwnode_property_string_array_count() instead of open coded variant.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/20230808162800.61651-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/base/property.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 8c40abed78524..3bb9505f1631a 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -473,7 +473,7 @@ int fwnode_property_match_string(const struct fwnode_handle *fwnode,
 	const char **values;
 	int nval, ret;
 
-	nval = fwnode_property_read_string_array(fwnode, propname, NULL, 0);
+	nval = fwnode_property_string_array_count(fwnode, propname);
 	if (nval < 0)
 		return nval;
 
-- 
GitLab


From fac4a535758851215d23d7d92879aeee5035f51d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 8 Aug 2023 19:27:56 +0300
Subject: [PATCH 0185/4076] device property: Add
 fwnode_property_match_property_string()

Sometimes the users want to match the single value string property
against an array of predefined strings. Create a helper for them.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/20230808162800.61651-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/base/property.c  | 35 +++++++++++++++++++++++++++++++++++
 include/linux/property.h | 12 ++++++++++++
 2 files changed, 47 insertions(+)

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 3bb9505f1631a..8f8e2a6816bc0 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -498,6 +498,41 @@ out_free:
 }
 EXPORT_SYMBOL_GPL(fwnode_property_match_string);
 
+/**
+ * fwnode_property_match_property_string - find a property string value in an array and return index
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property holding the string value
+ * @array: String array to search in
+ * @n: Size of the @array
+ *
+ * Find a property string value in a given @array and if it is found return
+ * the index back.
+ *
+ * Return: index, starting from %0, if the string value was found in the @array (success),
+ *	   %-ENOENT when the string value was not found in the @array,
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO or %-EILSEQ if the property is not a string,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_match_property_string(const struct fwnode_handle *fwnode,
+	const char *propname, const char * const *array, size_t n)
+{
+	const char *string;
+	int ret;
+
+	ret = fwnode_property_read_string(fwnode, propname, &string);
+	if (ret)
+		return ret;
+
+	ret = match_string(array, n, string);
+	if (ret < 0)
+		ret = -ENOENT;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(fwnode_property_match_property_string);
+
 /**
  * fwnode_property_get_reference_args() - Find a reference with arguments
  * @fwnode:	Firmware node where to look for the reference
diff --git a/include/linux/property.h b/include/linux/property.h
index 9f2585d705a86..2b8f07fc68a97 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -98,6 +98,18 @@ static inline bool device_is_compatible(const struct device *dev, const char *co
 	return fwnode_device_is_compatible(dev_fwnode(dev), compat);
 }
 
+int fwnode_property_match_property_string(const struct fwnode_handle *fwnode,
+					  const char *propname,
+					  const char * const *array, size_t n);
+
+static inline
+int device_property_match_property_string(const struct device *dev,
+					  const char *propname,
+					  const char * const *array, size_t n)
+{
+	return fwnode_property_match_property_string(dev_fwnode(dev), propname, array, n);
+}
+
 int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode,
 				       const char *prop, const char *nargs_prop,
 				       unsigned int nargs, unsigned int index,
-- 
GitLab


From 7829a9d75989260744514c1d6ce598ece7804200 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 8 Aug 2023 19:27:57 +0300
Subject: [PATCH 0186/4076] iio: frequency: adf4377: Switch to
 device_property_match_property_string()

Replace open coded device_property_match_property_string().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20230808162800.61651-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/frequency/adf4377.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c
index 26abecbd51e06..9284c13f1abb3 100644
--- a/drivers/iio/frequency/adf4377.c
+++ b/drivers/iio/frequency/adf4377.c
@@ -870,7 +870,6 @@ static const struct iio_chan_spec adf4377_channels[] = {
 static int adf4377_properties_parse(struct adf4377_state *st)
 {
 	struct spi_device *spi = st->spi;
-	const char *str;
 	int ret;
 
 	st->clkin = devm_clk_get_enabled(&spi->dev, "ref_in");
@@ -896,16 +895,13 @@ static int adf4377_properties_parse(struct adf4377_state *st)
 		return dev_err_probe(&spi->dev, PTR_ERR(st->gpio_enclk2),
 				     "failed to get the CE GPIO\n");
 
-	ret = device_property_read_string(&spi->dev, "adi,muxout-select", &str);
-	if (ret) {
-		st->muxout_select = ADF4377_MUXOUT_HIGH_Z;
-	} else {
-		ret = match_string(adf4377_muxout_modes, ARRAY_SIZE(adf4377_muxout_modes), str);
-		if (ret < 0)
-			return ret;
-
+	ret = device_property_match_property_string(&spi->dev, "adi,muxout-select",
+						    adf4377_muxout_modes,
+						    ARRAY_SIZE(adf4377_muxout_modes));
+	if (ret >= 0)
 		st->muxout_select = ret;
-	}
+	else
+		st->muxout_select = ADF4377_MUXOUT_HIGH_Z;
 
 	return 0;
 }
-- 
GitLab


From f993267a723f75df0f2996c4b94e76f2db1598be Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 8 Aug 2023 19:27:58 +0300
Subject: [PATCH 0187/4076] iio: frequency: admv1014: Switch to
 device_property_match_property_string()

Replace open coded device_property_match_property_string().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20230808162800.61651-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/frequency/admv1014.c | 31 ++++++++++++-------------------
 1 file changed, 12 insertions(+), 19 deletions(-)

diff --git a/drivers/iio/frequency/admv1014.c b/drivers/iio/frequency/admv1014.c
index bb5e1feef42bf..b46b73b89eb71 100644
--- a/drivers/iio/frequency/admv1014.c
+++ b/drivers/iio/frequency/admv1014.c
@@ -710,7 +710,6 @@ static int admv1014_init(struct admv1014_state *st)
 
 static int admv1014_properties_parse(struct admv1014_state *st)
 {
-	const char *str;
 	unsigned int i;
 	struct spi_device *spi = st->spi;
 	int ret;
@@ -719,27 +718,21 @@ static int admv1014_properties_parse(struct admv1014_state *st)
 
 	st->p1db_comp = device_property_read_bool(&spi->dev, "adi,p1db-compensation-enable");
 
-	ret = device_property_read_string(&spi->dev, "adi,input-mode", &str);
-	if (ret) {
-		st->input_mode = ADMV1014_IQ_MODE;
-	} else {
-		ret = match_string(input_mode_names, ARRAY_SIZE(input_mode_names), str);
-		if (ret < 0)
-			return ret;
-
+	ret = device_property_match_property_string(&spi->dev, "adi,input-mode",
+						    input_mode_names,
+						    ARRAY_SIZE(input_mode_names));
+	if (ret >= 0)
 		st->input_mode = ret;
-	}
-
-	ret = device_property_read_string(&spi->dev, "adi,quad-se-mode", &str);
-	if (ret) {
-		st->quad_se_mode = ADMV1014_SE_MODE_POS;
-	} else {
-		ret = match_string(quad_se_mode_names, ARRAY_SIZE(quad_se_mode_names), str);
-		if (ret < 0)
-			return ret;
+	else
+		st->input_mode = ADMV1014_IQ_MODE;
 
+	ret = device_property_match_property_string(&spi->dev, "adi,quad-se-mode",
+						    quad_se_mode_names,
+						    ARRAY_SIZE(quad_se_mode_names));
+	if (ret >= 0)
 		st->quad_se_mode = ADMV1014_SE_MODE_POS + (ret * 3);
-	}
+	else
+		st->quad_se_mode = ADMV1014_SE_MODE_POS;
 
 	for (i = 0; i < ADMV1014_NUM_REGULATORS; ++i)
 		st->regulators[i].supply = admv1014_reg_name[i];
-- 
GitLab


From 2a5239b6ab8ced2ee9dce34c2d274c98b118be15 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 8 Aug 2023 19:27:59 +0300
Subject: [PATCH 0188/4076] iio: magnetometer: tmag5273: Switch to
 device_property_match_property_string()

Replace open coded device_property_match_property_string().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20230808162800.61651-6-andriy.shevchenko@linux.intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/magnetometer/tmag5273.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/iio/magnetometer/tmag5273.c b/drivers/iio/magnetometer/tmag5273.c
index c5e5c4ad681e6..bcd989d650591 100644
--- a/drivers/iio/magnetometer/tmag5273.c
+++ b/drivers/iio/magnetometer/tmag5273.c
@@ -497,17 +497,13 @@ static int tmag5273_set_operating_mode(struct tmag5273_data *data,
 static void tmag5273_read_device_property(struct tmag5273_data *data)
 {
 	struct device *dev = data->dev;
-	const char *str;
 	int ret;
 
 	data->angle_measurement = TMAG5273_ANGLE_EN_X_Y;
 
-	ret = device_property_read_string(dev, "ti,angle-measurement", &str);
-	if (ret)
-		return;
-
-	ret = match_string(tmag5273_angle_names,
-			   ARRAY_SIZE(tmag5273_angle_names), str);
+	ret = device_property_match_property_string(dev, "ti,angle-measurement",
+						    tmag5273_angle_names,
+						    ARRAY_SIZE(tmag5273_angle_names));
 	if (ret >= 0)
 		data->angle_measurement = ret;
 }
-- 
GitLab


From 7cd11203d9007d604316ef49d6b33a97500fcef7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 8 Aug 2023 19:28:00 +0300
Subject: [PATCH 0189/4076] iio: proximity: sx9324: Switch to
 device_property_match_property_string()

Replace open coded device_property_match_property_string().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20230808162800.61651-7-andriy.shevchenko@linux.intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/sx9324.c | 24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/drivers/iio/proximity/sx9324.c b/drivers/iio/proximity/sx9324.c
index 438f9c9aba6ea..ac2ed2da21ccc 100644
--- a/drivers/iio/proximity/sx9324.c
+++ b/drivers/iio/proximity/sx9324.c
@@ -888,7 +888,6 @@ sx9324_get_default_reg(struct device *dev, int idx,
 	char prop[] = SX9324_PROXRAW_DEF;
 	u32 start = 0, raw = 0, pos = 0;
 	int ret, count, ph, pin;
-	const char *res;
 
 	memcpy(reg_def, &sx9324_default_regs[idx], sizeof(*reg_def));
 
@@ -915,24 +914,21 @@ sx9324_get_default_reg(struct device *dev, int idx,
 		reg_def->def = raw;
 		break;
 	case SX9324_REG_AFE_CTRL0:
-		ret = device_property_read_string(dev,
-				"semtech,cs-idle-sleep", &res);
-		if (!ret)
-			ret = match_string(sx9324_csidle, ARRAY_SIZE(sx9324_csidle), res);
+		ret = device_property_match_property_string(dev, "semtech,cs-idle-sleep",
+							    sx9324_csidle,
+							    ARRAY_SIZE(sx9324_csidle));
 		if (ret >= 0) {
 			reg_def->def &= ~SX9324_REG_AFE_CTRL0_CSIDLE_MASK;
 			reg_def->def |= ret << SX9324_REG_AFE_CTRL0_CSIDLE_SHIFT;
 		}
 
-		ret = device_property_read_string(dev,
-				"semtech,int-comp-resistor", &res);
-		if (ret)
-			break;
-		ret = match_string(sx9324_rints, ARRAY_SIZE(sx9324_rints), res);
-		if (ret < 0)
-			break;
-		reg_def->def &= ~SX9324_REG_AFE_CTRL0_RINT_MASK;
-		reg_def->def |= ret << SX9324_REG_AFE_CTRL0_RINT_SHIFT;
+		ret = device_property_match_property_string(dev, "semtech,int-comp-resistor",
+							    sx9324_rints,
+							    ARRAY_SIZE(sx9324_rints));
+		if (ret >= 0) {
+			reg_def->def &= ~SX9324_REG_AFE_CTRL0_RINT_MASK;
+			reg_def->def |= ret << SX9324_REG_AFE_CTRL0_RINT_SHIFT;
+		}
 		break;
 	case SX9324_REG_AFE_CTRL4:
 	case SX9324_REG_AFE_CTRL7:
-- 
GitLab


From 4f7901bb4dea11f758bf610802216296fdf29b97 Mon Sep 17 00:00:00 2001
From: Matt Ranostay <matt@ranostay.sg>
Date: Sat, 21 Oct 2023 08:53:17 +0000
Subject: [PATCH 0190/4076] mailmap: Change email mapping from previous
 employers

Signed-off-by: Matt Ranostay <matt@ranostay.sg>
Link: https://lore.kernel.org/r/20231021085250.21431-1-matt@ranostay.sg
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .mailmap | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/.mailmap b/.mailmap
index 43031441b2d92..2bff2902bfed4 100644
--- a/.mailmap
+++ b/.mailmap
@@ -383,9 +383,10 @@ Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu>
 Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net>
 Matthieu CASTET <castet.matthieu@free.fr>
 Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com>
-Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting>
-Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com>
-Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com>
+Matt Ranostay <matt@ranostay.sg> <matt.ranostay@konsulko.com>
+Matt Ranostay <matt@ranostay.sg> <matt@ranostay.consulting>
+Matt Ranostay <matt@ranostay.sg> Matthew Ranostay <mranostay@embeddedalley.com>
+Matt Ranostay <matt@ranostay.sg> <matt.ranostay@intel.com>
 Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com>
 Maulik Shah <quic_mkshah@quicinc.com> <mkshah@codeaurora.org>
 Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com>
-- 
GitLab


From a2d43f44628fe4fa9c17f0e09548cb385e772f7e Mon Sep 17 00:00:00 2001
From: Li peiyu <579lpy@gmail.com>
Date: Sat, 21 Oct 2023 15:09:03 +0800
Subject: [PATCH 0191/4076] iio: pressure: fix some word spelling errors

They are appear to be spelling mistakes,
drivers/iio/pressure/bmp280.h:413        endianess->endianness
drivers/iio/pressure/bmp280-core.c:923   dregrees->degrees
drivers/iio/pressure/bmp280-core.c:1388  reescale->rescale
drivers/iio/pressure/bmp280-core.c:1415  reescale->rescale

Signed-off-by: Li peiyu <579lpy@gmail.com>
Link: https://lore.kernel.org/r/20231021070903.6051-1-579lpy@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/pressure/bmp280-core.c | 6 +++---
 drivers/iio/pressure/bmp280.h      | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index a2ef1373a274e..4c493db7db965 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -920,7 +920,7 @@ static int bmp380_cmd(struct bmp280_data *data, u8 cmd)
 }
 
 /*
- * Returns temperature in Celsius dregrees, resolution is 0.01º C. Output value of
+ * Returns temperature in Celsius degrees, resolution is 0.01º C. Output value of
  * "5123" equals 51.2º C. t_fine carries fine temperature as global value.
  *
  * Taken from datasheet, Section Appendix 9, "Compensation formula" and repo
@@ -1385,7 +1385,7 @@ static int bmp580_read_temp(struct bmp280_data *data, int *val, int *val2)
 
 	/*
 	 * Temperature is returned in Celsius degrees in fractional
-	 * form down 2^16. We reescale by x1000 to return milli Celsius
+	 * form down 2^16. We rescale by x1000 to return milli Celsius
 	 * to respect IIO ABI.
 	 */
 	*val = raw_temp * 1000;
@@ -1412,7 +1412,7 @@ static int bmp580_read_press(struct bmp280_data *data, int *val, int *val2)
 	}
 	/*
 	 * Pressure is returned in Pascals in fractional form down 2^16.
-	 * We reescale /1000 to convert to kilopascal to respect IIO ABI.
+	 * We rescale /1000 to convert to kilopascal to respect IIO ABI.
 	 */
 	*val = raw_press;
 	*val2 = 64000; /* 2^6 * 1000 */
diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h
index 5c0563ce75725..9d9f4ce2baa6e 100644
--- a/drivers/iio/pressure/bmp280.h
+++ b/drivers/iio/pressure/bmp280.h
@@ -410,7 +410,7 @@ struct bmp280_data {
 		__le16 bmp280_cal_buf[BMP280_CONTIGUOUS_CALIB_REGS / 2];
 		__be16 bmp180_cal_buf[BMP180_REG_CALIB_COUNT / 2];
 		u8 bmp380_cal_buf[BMP380_CALIB_REG_COUNT];
-		/* Miscellaneous, endianess-aware data buffers */
+		/* Miscellaneous, endianness-aware data buffers */
 		__le16 le16;
 		__be16 be16;
 	} __aligned(IIO_DMA_MINALIGN);
-- 
GitLab


From a6d160b21fe6f9e3ac868ab1d79194d3e7977cd5 Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <mazziesaccount@gmail.com>
Date: Fri, 20 Oct 2023 13:53:47 +0300
Subject: [PATCH 0192/4076] iio: bu27008: Add illuminance channel

The RGB + IR data can be used to calculate the illuminance value (luxes).
Implement the equation obtained from the ROHM HW colleagues and add a
raw light data channel outputting illuminance values in (nano) Luxes.

Both the read_raw and buffering values are supported, with the limitation
that buffering is only allowed when a suitable scan-mask is used. (RGB+IR,
no clear).

The equation has been developed by ROHM HW colleagues for open air sensor.
Adding any lens to the sensor is likely to impact to used c1, c2, c3
coefficients. Also, the output values have only been tested on BU27008.

According to the HW colleagues, the very same equation should work on
BU27010 as well.

Calculate and output illuminance values from BU27008 and BU27010.

Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Link: https://lore.kernel.org/r/ZTJcOxSb/WHzdN8h@dc78bmyyyyyyyyyyyyydt-3.rev.dnainternet.fi
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/rohm-bu27008.c | 201 ++++++++++++++++++++++++++++++-
 1 file changed, 196 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/light/rohm-bu27008.c b/drivers/iio/light/rohm-bu27008.c
index 6a6d778050911..0f010eff1981f 100644
--- a/drivers/iio/light/rohm-bu27008.c
+++ b/drivers/iio/light/rohm-bu27008.c
@@ -130,6 +130,7 @@
  * @BU27008_BLUE:	Blue channel. Via data2 (when used).
  * @BU27008_CLEAR:	Clear channel. Via data2 or data3 (when used).
  * @BU27008_IR:		IR channel. Via data3 (when used).
+ * @BU27008_LUX:	Illuminance channel, computed using RGB and IR.
  * @BU27008_NUM_CHANS:	Number of channel types.
  */
 enum bu27008_chan_type {
@@ -138,6 +139,7 @@ enum bu27008_chan_type {
 	BU27008_BLUE,
 	BU27008_CLEAR,
 	BU27008_IR,
+	BU27008_LUX,
 	BU27008_NUM_CHANS
 };
 
@@ -172,6 +174,8 @@ static const unsigned long bu27008_scan_masks[] = {
 	ALWAYS_SCANNABLE | BIT(BU27008_CLEAR) | BIT(BU27008_IR),
 	/* buffer is R, G, B, IR */
 	ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_IR),
+	/* buffer is R, G, B, IR, LUX */
+	ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_IR) | BIT(BU27008_LUX),
 	0
 };
 
@@ -331,6 +335,19 @@ static const struct iio_chan_spec bu27008_channels[] = {
 	 * Hence we don't advertise available ones either.
 	 */
 	BU27008_CHAN(IR, DATA3, 0),
+	{
+		.type = IIO_LIGHT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+		.channel = BU27008_LUX,
+		.scan_index = BU27008_LUX,
+		.scan_type = {
+			.sign = 'u',
+			.realbits = 64,
+			.storagebits = 64,
+			.endianness = IIO_CPU,
+		},
+	},
 	IIO_CHAN_SOFT_TIMESTAMP(BU27008_NUM_CHANS),
 };
 
@@ -1004,6 +1021,169 @@ static int bu27008_read_one(struct bu27008_data *data, struct iio_dev *idev,
 	return ret;
 }
 
+#define BU27008_LUX_DATA_RED	0
+#define BU27008_LUX_DATA_GREEN	1
+#define BU27008_LUX_DATA_BLUE	2
+#define BU27008_LUX_DATA_IR	3
+#define LUX_DATA_SIZE (BU27008_NUM_HW_CHANS * sizeof(__le16))
+
+static int bu27008_read_lux_chans(struct bu27008_data *data, unsigned int time,
+				  __le16 *chan_data)
+{
+	int ret, chan_sel, tmpret, valid;
+
+	chan_sel = BU27008_BLUE2_IR3 << (ffs(data->cd->chan_sel_mask) - 1);
+
+	ret = regmap_update_bits(data->regmap, data->cd->chan_sel_reg,
+				 data->cd->chan_sel_mask, chan_sel);
+	if (ret)
+		return ret;
+
+	ret = bu27008_meas_set(data, true);
+	if (ret)
+		return ret;
+
+	msleep(time / USEC_PER_MSEC);
+
+	ret = regmap_read_poll_timeout(data->regmap, data->cd->valid_reg,
+				       valid, (valid & BU27008_MASK_VALID),
+				       BU27008_VALID_RESULT_WAIT_QUANTA_US,
+				       BU27008_MAX_VALID_RESULT_WAIT_US);
+	if (ret)
+		goto out;
+
+	ret = regmap_bulk_read(data->regmap, BU27008_REG_DATA0_LO, chan_data,
+			       LUX_DATA_SIZE);
+	if (ret)
+		goto out;
+out:
+	tmpret = bu27008_meas_set(data, false);
+	if (tmpret)
+		dev_warn(data->dev, "Stopping measurement failed\n");
+
+	return ret;
+}
+
+/*
+ * Following equation for computing lux out of register values was given by
+ * ROHM HW colleagues;
+ *
+ * Red = RedData*1024 / Gain * 20 / meas_mode
+ * Green = GreenData* 1024 / Gain * 20 / meas_mode
+ * Blue = BlueData* 1024 / Gain * 20 / meas_mode
+ * IR = IrData* 1024 / Gain * 20 / meas_mode
+ *
+ * where meas_mode is the integration time in mS / 10
+ *
+ * IRratio = (IR > 0.18 * Green) ? 0 : 1
+ *
+ * Lx = max(c1*Red + c2*Green + c3*Blue,0)
+ *
+ * for
+ * IRratio 0: c1 = -0.00002237, c2 = 0.0003219, c3 = -0.000120371
+ * IRratio 1: c1 = -0.00001074, c2 = 0.000305415, c3 = -0.000129367
+ */
+
+/*
+ * The max chan data is 0xffff. When we multiply it by 1024 * 20, we'll get
+ * 0x4FFFB000 which still fits in 32-bit integer. This won't overflow.
+ */
+#define NORM_CHAN_DATA_FOR_LX_CALC(chan, gain, time) (le16_to_cpu(chan) * \
+				   1024 * 20 / (gain) / (time))
+static u64 bu27008_calc_nlux(struct bu27008_data *data, __le16 *lux_data,
+		unsigned int gain, unsigned int gain_ir, unsigned int time)
+{
+	unsigned int red, green, blue, ir;
+	s64 c1, c2, c3, nlux;
+
+	time /= 10000;
+	ir = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_IR], gain_ir, time);
+	red = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_RED], gain, time);
+	green = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_GREEN], gain, time);
+	blue = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_BLUE], gain, time);
+
+	if ((u64)ir * 100LLU > (u64)green * 18LLU) {
+		c1 = -22370;
+		c2 = 321900;
+		c3 = -120371;
+	} else {
+		c1 = -10740;
+		c2 = 305415;
+		c3 = -129367;
+	}
+	nlux = c1 * red + c2 * green + c3 * blue;
+
+	return max_t(s64, 0, nlux);
+}
+
+static int bu27008_get_time_n_gains(struct bu27008_data *data,
+		unsigned int *gain, unsigned int *gain_ir, unsigned int *time)
+{
+	int ret;
+
+	ret = bu27008_get_gain(data, &data->gts, gain);
+	if (ret < 0)
+		return ret;
+
+	ret = bu27008_get_gain(data, &data->gts_ir, gain_ir);
+	if (ret < 0)
+		return ret;
+
+	ret = bu27008_get_int_time_us(data);
+	if (ret < 0)
+		return ret;
+
+	/* Max integration time is 400000. Fits in signed int. */
+	*time = ret;
+
+	return 0;
+}
+
+struct bu27008_buf {
+	__le16 chan[BU27008_NUM_HW_CHANS];
+	u64 lux __aligned(8);
+	s64 ts __aligned(8);
+};
+
+static int bu27008_buffer_fill_lux(struct bu27008_data *data,
+				   struct bu27008_buf *raw)
+{
+	unsigned int gain, gain_ir, time;
+	int ret;
+
+	ret = bu27008_get_time_n_gains(data, &gain, &gain_ir, &time);
+	if (ret)
+		return ret;
+
+	raw->lux = bu27008_calc_nlux(data, raw->chan, gain, gain_ir, time);
+
+	return 0;
+}
+
+static int bu27008_read_lux(struct bu27008_data *data, struct iio_dev *idev,
+			    struct iio_chan_spec const *chan,
+			    int *val, int *val2)
+{
+	__le16 lux_data[BU27008_NUM_HW_CHANS];
+	unsigned int gain, gain_ir, time;
+	u64 nlux;
+	int ret;
+
+	ret = bu27008_get_time_n_gains(data, &gain, &gain_ir, &time);
+	if (ret)
+		return ret;
+
+	ret = bu27008_read_lux_chans(data, time, lux_data);
+	if (ret)
+		return ret;
+
+	nlux = bu27008_calc_nlux(data, lux_data, gain, gain_ir, time);
+	*val = (int)nlux;
+	*val2 = nlux >> 32LLU;
+
+	return IIO_VAL_INT_64;
+}
+
 static int bu27008_read_raw(struct iio_dev *idev,
 			   struct iio_chan_spec const *chan,
 			   int *val, int *val2, long mask)
@@ -1018,7 +1198,10 @@ static int bu27008_read_raw(struct iio_dev *idev,
 			return -EBUSY;
 
 		mutex_lock(&data->mutex);
-		ret = bu27008_read_one(data, idev, chan, val, val2);
+		if (chan->type == IIO_LIGHT)
+			ret = bu27008_read_lux(data, idev, chan, val, val2);
+		else
+			ret = bu27008_read_one(data, idev, chan, val, val2);
 		mutex_unlock(&data->mutex);
 
 		iio_device_release_direct_mode(idev);
@@ -1026,6 +1209,11 @@ static int bu27008_read_raw(struct iio_dev *idev,
 		return ret;
 
 	case IIO_CHAN_INFO_SCALE:
+		if (chan->type == IIO_LIGHT) {
+			*val = 0;
+			*val2 = 1;
+			return IIO_VAL_INT_PLUS_NANO;
+		}
 		ret = bu27008_get_scale(data, chan->scan_index == BU27008_IR,
 					val, val2);
 		if (ret)
@@ -1236,10 +1424,7 @@ static irqreturn_t bu27008_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *idev = pf->indio_dev;
 	struct bu27008_data *data = iio_priv(idev);
-	struct {
-		__le16 chan[BU27008_NUM_HW_CHANS];
-		s64 ts __aligned(8);
-	} raw;
+	struct bu27008_buf raw;
 	int ret, dummy;
 
 	memset(&raw, 0, sizeof(raw));
@@ -1257,6 +1442,12 @@ static irqreturn_t bu27008_trigger_handler(int irq, void *p)
 	if (ret < 0)
 		goto err_read;
 
+	if (test_bit(BU27008_LUX, idev->active_scan_mask)) {
+		ret = bu27008_buffer_fill_lux(data, &raw);
+		if (ret)
+			goto err_read;
+	}
+
 	iio_push_to_buffers_with_timestamp(idev, &raw, pf->timestamp);
 err_read:
 	iio_trigger_notify_done(idev->trig);
-- 
GitLab


From 06261c6f5468eadbe1e87dbeeb877bc5c062f514 Mon Sep 17 00:00:00 2001
From: Amit Dhingra <mechanicalamit@gmail.com>
Date: Thu, 26 Oct 2023 04:13:44 -0700
Subject: [PATCH 0193/4076] MAINTAINERS: correct file entry IIO LIGHT SENSOR
 GAIN-TIME_SCALE HELPERS

Commit ca11e4a35154 ("MAINTAINERS: Add IIO gain-time-scale helpers"),
updates the MAINTAINERS file. However the files listed do not exist.
These presumably come from commit 38416c28e168 ("iio: light: Add
gain-time-scale helpers")

Fix the entries.

Found by ./scripts/get_maintainer.pl --self-test=patterns

Fixes: ca11e4a35154 ("MAINTAINERS: Add IIO gain-time-scale helpers")
Signed-off-by: Amit Dhingra <mechanicalamit@gmail.com>
Acked-by: Matti Vaittinen <mazziesaccount@gmail.com>
Link: https://lore.kernel.org/r/CAO=gReFVhp7QK_XZRBO5vbv6fmFb4BdsZeQPSzWvuiz9UeQekA@mail.gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8b74fad87d76f..91f5585b4bb2b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10340,8 +10340,8 @@ IIO LIGHT SENSOR GAIN-TIME-SCALE HELPERS
 M:	Matti Vaittinen <mazziesaccount@gmail.com>
 L:	linux-iio@vger.kernel.org
 S:	Maintained
-F:	drivers/iio/light/gain-time-scale-helper.c
-F:	drivers/iio/light/gain-time-scale-helper.h
+F:	drivers/iio/industrialio-gts-helper.c
+F:	include/linux/iio/iio-gts-helper.h
 
 IIO MULTIPLEXER
 M:	Peter Rosin <peda@axentia.se>
-- 
GitLab


From 1bbc290b21c51f3a06ea66562d7abac0d6ff9995 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Wed, 25 Oct 2023 11:15:50 +0200
Subject: [PATCH 0194/4076] MAINTAINERS: correct file entry in BOSCH SENSORTEC
 BMI323 IMU IIO DRIVER

Commit b512c767e7bc ("iio: imu: Add driver for BMI323 IMU") adds the
MAINTAINERS section BOSCH SENSORTEC BMI323 IMU IIO DRIVER and refers to a
non-existing device-tree file.

Probably, this mistake was introduced by copying from the BOSCH SENSORTEC
BMA400 ACCELEROMETER IIO DRIVER section and missing to adjust the file
entry properly. This is however easily caught, as the script
./scripts/get_maintainer.pl --self-test=patterns complains about a broken
reference.

The related commit 77583938740e ("dt-bindings: iio: imu: Add Bosch BMI323")
adds bosch,bmi323.yaml, so refer to that intended file instead.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Reviewed-by: Jagath Jog J <jagathjog1996@gmail.com>
Link: https://lore.kernel.org/r/20231025091550.21052-1-lukas.bulwahn@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 91f5585b4bb2b..8e0a91dc8251a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3651,7 +3651,7 @@ BOSCH SENSORTEC BMI323 IMU IIO DRIVER
 M:	Jagath Jog J <jagathjog1996@gmail.com>
 L:	linux-iio@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/iio/imu/bosch,bma400.yaml
+F:	Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
 F:	drivers/iio/imu/bmi323/
 
 BPF JIT for ARM
-- 
GitLab


From aace22e375e287ae825b3b0a8a1d70820cfe27b9 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Sun, 22 Oct 2023 19:22:17 +0200
Subject: [PATCH 0195/4076] iio: pressure: bmp280: Use i2c_get_match_data()

Replace device_get_match_data() and id lookup for retrieving match data
by i2c_get_match_data().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/0554ddae62ba04ccacf58c2de04ec598c876665e.1697994521.git.ang.iglesiasg@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/pressure/bmp280-i2c.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/iio/pressure/bmp280-i2c.c b/drivers/iio/pressure/bmp280-i2c.c
index dbe630ad05b5a..b3e069730f972 100644
--- a/drivers/iio/pressure/bmp280-i2c.c
+++ b/drivers/iio/pressure/bmp280-i2c.c
@@ -11,9 +11,7 @@ static int bmp280_i2c_probe(struct i2c_client *client)
 	const struct bmp280_chip_info *chip_info;
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
 
-	chip_info = device_get_match_data(&client->dev);
-	if (!chip_info)
-		chip_info = (const struct bmp280_chip_info *) id->driver_data;
+	chip_info = i2c_get_match_data(client);
 
 	regmap = devm_regmap_init_i2c(client, chip_info->regmap_config);
 	if (IS_ERR(regmap)) {
-- 
GitLab


From faac4dda9a91f94d96cb38676ca4177a54666d75 Mon Sep 17 00:00:00 2001
From: Angel Iglesias <ang.iglesiasg@gmail.com>
Date: Sun, 22 Oct 2023 19:22:18 +0200
Subject: [PATCH 0196/4076] iio: pressure: bmp280: Use
 spi_get_device_match_data()

Use the spi_get_device_match_data() helper instead of
device_get_match_data() and the fallback match_id logic.

Signed-off-by: Angel Iglesias <ang.iglesiasg@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/9ea8ac90b2b8a8cf45803d0435243c0bee009b37.1697994521.git.ang.iglesiasg@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/pressure/bmp280-spi.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c
index 1dff9bb7c4e90..2eed483a8cc4c 100644
--- a/drivers/iio/pressure/bmp280-spi.c
+++ b/drivers/iio/pressure/bmp280-spi.c
@@ -58,9 +58,7 @@ static int bmp280_spi_probe(struct spi_device *spi)
 		return ret;
 	}
 
-	chip_info = device_get_match_data(&spi->dev);
-	if (!chip_info)
-		chip_info = (const struct bmp280_chip_info *) id->driver_data;
+	chip_info = spi_get_device_match_data(spi);
 
 	regmap = devm_regmap_init(&spi->dev,
 				  &bmp280_regmap_bus,
-- 
GitLab


From 48245f4a8c093f0c06f82b235a9e0dd766dc20df Mon Sep 17 00:00:00 2001
From: Angel Iglesias <ang.iglesiasg@gmail.com>
Date: Sun, 22 Oct 2023 19:22:19 +0200
Subject: [PATCH 0197/4076] iio: pressure: bmp280: Rearrange vars in reverse
 xmas tree order

Small cleanup reordering local variable declarations following reverse
christmas tree convention.

Signed-off-by: Angel Iglesias <ang.iglesiasg@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/bb63a996eb9c4555bf83471770f0169d2627e79c.1697994521.git.ang.iglesiasg@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/pressure/bmp280-i2c.c | 4 ++--
 drivers/iio/pressure/bmp280-spi.c | 6 ++----
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/iio/pressure/bmp280-i2c.c b/drivers/iio/pressure/bmp280-i2c.c
index b3e069730f972..34e3bc758493e 100644
--- a/drivers/iio/pressure/bmp280-i2c.c
+++ b/drivers/iio/pressure/bmp280-i2c.c
@@ -7,9 +7,9 @@
 
 static int bmp280_i2c_probe(struct i2c_client *client)
 {
-	struct regmap *regmap;
-	const struct bmp280_chip_info *chip_info;
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
+	const struct bmp280_chip_info *chip_info;
+	struct regmap *regmap;
 
 	chip_info = i2c_get_match_data(client);
 
diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c
index 2eed483a8cc4c..433d6fac83c4c 100644
--- a/drivers/iio/pressure/bmp280-spi.c
+++ b/drivers/iio/pressure/bmp280-spi.c
@@ -14,8 +14,7 @@
 static int bmp280_regmap_spi_write(void *context, const void *data,
                                    size_t count)
 {
-	struct device *dev = context;
-	struct spi_device *spi = to_spi_device(dev);
+	struct spi_device *spi = to_spi_device(context);
 	u8 buf[2];
 
 	memcpy(buf, data, 2);
@@ -31,8 +30,7 @@ static int bmp280_regmap_spi_write(void *context, const void *data,
 static int bmp280_regmap_spi_read(void *context, const void *reg,
                                   size_t reg_size, void *val, size_t val_size)
 {
-	struct device *dev = context;
-	struct spi_device *spi = to_spi_device(dev);
+	struct spi_device *spi = to_spi_device(context);
 
 	return spi_write_then_read(spi, reg, reg_size, val, val_size);
 }
-- 
GitLab


From 33564435c8084ff29837c9ed9bb9574ec957751d Mon Sep 17 00:00:00 2001
From: Angel Iglesias <ang.iglesiasg@gmail.com>
Date: Sun, 22 Oct 2023 19:22:20 +0200
Subject: [PATCH 0198/4076] iio: pressure: bmp280: Allow multiple chips id per
 family of devices

Improve device detection in certain chip families known to have
various chip IDs. When no ID matches, give a warning but follow
along what device said on the firmware side and try to configure
it.

Signed-off-by: Angel Iglesias <ang.iglesiasg@gmail.com>
Link: https://lore.kernel.org/r/eade22d11e9de4405ea19fdaa5a8249143ae94df.1697994521.git.ang.iglesiasg@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/pressure/bmp280-core.c | 35 ++++++++++++++++++++++--------
 drivers/iio/pressure/bmp280.h      |  3 ++-
 2 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index 4c493db7db965..cc24473762d72 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -794,10 +794,12 @@ static int bmp280_chip_config(struct bmp280_data *data)
 }
 
 static const int bmp280_oversampling_avail[] = { 1, 2, 4, 8, 16 };
+static const u8 bmp280_chip_ids[] = { BMP280_CHIP_ID };
 
 const struct bmp280_chip_info bmp280_chip_info = {
 	.id_reg = BMP280_REG_ID,
-	.chip_id = BMP280_CHIP_ID,
+	.chip_id = bmp280_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bmp280_chip_ids),
 	.regmap_config = &bmp280_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp280_channels,
@@ -846,9 +848,12 @@ static int bme280_chip_config(struct bmp280_data *data)
 	return bmp280_chip_config(data);
 }
 
+static const u8 bme280_chip_ids[] = { BME280_CHIP_ID };
+
 const struct bmp280_chip_info bme280_chip_info = {
 	.id_reg = BMP280_REG_ID,
-	.chip_id = BME280_CHIP_ID,
+	.chip_id = bme280_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bme280_chip_ids),
 	.regmap_config = &bmp280_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp280_channels,
@@ -1220,10 +1225,12 @@ static int bmp380_chip_config(struct bmp280_data *data)
 
 static const int bmp380_oversampling_avail[] = { 1, 2, 4, 8, 16, 32 };
 static const int bmp380_iir_filter_coeffs_avail[] = { 1, 2, 4, 8, 16, 32, 64, 128};
+static const u8 bmp380_chip_ids[] = { BMP380_CHIP_ID };
 
 const struct bmp280_chip_info bmp380_chip_info = {
 	.id_reg = BMP380_REG_ID,
-	.chip_id = BMP380_CHIP_ID,
+	.chip_id = bmp380_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bmp380_chip_ids),
 	.regmap_config = &bmp380_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp380_channels,
@@ -1720,10 +1727,12 @@ static int bmp580_chip_config(struct bmp280_data *data)
 }
 
 static const int bmp580_oversampling_avail[] = { 1, 2, 4, 8, 16, 32, 64, 128 };
+static const u8 bmp580_chip_ids[] = { BMP580_CHIP_ID, BMP580_CHIP_ID_ALT };
 
 const struct bmp280_chip_info bmp580_chip_info = {
 	.id_reg = BMP580_REG_CHIP_ID,
-	.chip_id = BMP580_CHIP_ID,
+	.chip_id = bmp580_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bmp580_chip_ids),
 	.regmap_config = &bmp580_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp380_channels,
@@ -1983,10 +1992,12 @@ static int bmp180_chip_config(struct bmp280_data *data)
 
 static const int bmp180_oversampling_temp_avail[] = { 1 };
 static const int bmp180_oversampling_press_avail[] = { 1, 2, 4, 8 };
+static const u8 bmp180_chip_ids[] = { BMP180_CHIP_ID };
 
 const struct bmp280_chip_info bmp180_chip_info = {
 	.id_reg = BMP280_REG_ID,
-	.chip_id = BMP180_CHIP_ID,
+	.chip_id = bmp180_chip_ids,
+	.num_chip_id = ARRAY_SIZE(bmp180_chip_ids),
 	.regmap_config = &bmp180_regmap_config,
 	.start_up_time = 2000,
 	.channels = bmp280_channels,
@@ -2077,6 +2088,7 @@ int bmp280_common_probe(struct device *dev,
 	struct bmp280_data *data;
 	struct gpio_desc *gpiod;
 	unsigned int chip_id;
+	unsigned int i;
 	int ret;
 
 	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
@@ -2142,12 +2154,17 @@ int bmp280_common_probe(struct device *dev,
 	ret = regmap_read(regmap, data->chip_info->id_reg, &chip_id);
 	if (ret < 0)
 		return ret;
-	if (chip_id != data->chip_info->chip_id) {
-		dev_err(dev, "bad chip id: expected %x got %x\n",
-			data->chip_info->chip_id, chip_id);
-		return -EINVAL;
+
+	for (i = 0; i < data->chip_info->num_chip_id; i++) {
+		if (chip_id == data->chip_info->chip_id[i]) {
+			dev_info(dev, "0x%x is a known chip id for %s\n", chip_id, name);
+			break;
+		}
 	}
 
+	if (i == data->chip_info->num_chip_id)
+		dev_warn(dev, "bad chip id: 0x%x is not a known chip id\n", chip_id);
+
 	if (data->chip_info->preinit) {
 		ret = data->chip_info->preinit(data);
 		if (ret)
diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h
index 9d9f4ce2baa6e..a44ea33221635 100644
--- a/drivers/iio/pressure/bmp280.h
+++ b/drivers/iio/pressure/bmp280.h
@@ -418,7 +418,8 @@ struct bmp280_data {
 
 struct bmp280_chip_info {
 	unsigned int id_reg;
-	const unsigned int chip_id;
+	const u8 *chip_id;
+	int num_chip_id;
 
 	const struct regmap_config *regmap_config;
 
-- 
GitLab


From b19ac45bfe503c399fe8e16a20dddeb1f4870997 Mon Sep 17 00:00:00 2001
From: Angel Iglesias <ang.iglesiasg@gmail.com>
Date: Sun, 22 Oct 2023 19:22:21 +0200
Subject: [PATCH 0199/4076] iio: pressure: bmp280: Add support for BMP390

Add BMP390 device ID to the supported IDs on bmp380 sensor family

Signed-off-by: Angel Iglesias <ang.iglesiasg@gmail.com>
Link: https://lore.kernel.org/r/d6a9e9ca4670c7401545d0d086cd3059e29044c8.1697994521.git.ang.iglesiasg@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/pressure/bmp280-core.c | 3 ++-
 drivers/iio/pressure/bmp280.h      | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index cc24473762d72..fe8734468ed35 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -13,6 +13,7 @@
  * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp280-ds001.pdf
  * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bme280-ds002.pdf
  * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp388-ds001.pdf
+ * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp390-ds002.pdf
  * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp581-ds004.pdf
  *
  * Notice:
@@ -1225,7 +1226,7 @@ static int bmp380_chip_config(struct bmp280_data *data)
 
 static const int bmp380_oversampling_avail[] = { 1, 2, 4, 8, 16, 32 };
 static const int bmp380_iir_filter_coeffs_avail[] = { 1, 2, 4, 8, 16, 32, 64, 128};
-static const u8 bmp380_chip_ids[] = { BMP380_CHIP_ID };
+static const u8 bmp380_chip_ids[] = { BMP380_CHIP_ID, BMP390_CHIP_ID };
 
 const struct bmp280_chip_info bmp380_chip_info = {
 	.id_reg = BMP380_REG_ID,
diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h
index a44ea33221635..4012387d79565 100644
--- a/drivers/iio/pressure/bmp280.h
+++ b/drivers/iio/pressure/bmp280.h
@@ -292,6 +292,7 @@
 #define BMP580_CHIP_ID_ALT		0x51
 #define BMP180_CHIP_ID			0x55
 #define BMP280_CHIP_ID			0x58
+#define BMP390_CHIP_ID			0x60
 #define BME280_CHIP_ID			0x60
 #define BMP280_SOFT_RESET_VAL		0xB6
 
-- 
GitLab


From 18cdaaa482121aef942585cfbb02b1a9058e553d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Mon, 23 Oct 2023 09:10:54 +0100
Subject: [PATCH 0200/4076] iio: imu: Fix spelling mistake "accelrometer" ->
 "accelerometer"

There are two spelling mistakes in dev_err messages. Fix them.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Jagath Jog J <jagathjog1996@gmail.com>
Link: https://lore.kernel.org/r/20231023081054.617292-1-colin.i.king@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/bmi323/bmi323_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c
index 0bd5dedd9a635..183af482828f8 100644
--- a/drivers/iio/imu/bmi323/bmi323_core.c
+++ b/drivers/iio/imu/bmi323/bmi323_core.c
@@ -545,7 +545,7 @@ static int bmi323_tap_event_en(struct bmi323_data *data,
 	guard(mutex)(&data->mutex);
 
 	if (data->odrhz[BMI323_ACCEL] < 200) {
-		dev_err(data->dev, "Invalid accelrometer parameter\n");
+		dev_err(data->dev, "Invalid accelerometer parameter\n");
 		return -EINVAL;
 	}
 
@@ -1453,7 +1453,7 @@ static int bmi323_enable_steps(struct bmi323_data *data, int val)
 
 	guard(mutex)(&data->mutex);
 	if (data->odrhz[BMI323_ACCEL] < 200) {
-		dev_err(data->dev, "Invalid accelrometer parameter\n");
+		dev_err(data->dev, "Invalid accelerometer parameter\n");
 		return -EINVAL;
 	}
 
-- 
GitLab


From d6f250b1fe8e5878823a34fa919fc7e03afb7abb Mon Sep 17 00:00:00 2001
From: Andrew Hepp <andrew.hepp@ahepp.dev>
Date: Wed, 25 Oct 2023 16:31:52 -0700
Subject: [PATCH 0201/4076] dt-bindings: iio: Add MCP9600 thermocouple EMF
 converter

Add support for the MCP9600 thermocouple electromotive force converter. The sensor has  integrated cold junction compensation and a typical accuracy of 0.5 degrees Celsius. The driver supports a resolution of 0.0625 degrees Celsius.

Datasheet: https://ww1.microchip.com/downloads/en/DeviceDoc/MCP960X-Data-Sheet-20005426.pdf
Signed-off-by: Andrew Hepp <andrew.hepp@ahepp.dev>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231025233153.5454-1-andrew.hepp@ahepp.dev
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../iio/temperature/microchip,mcp9600.yaml    | 70 +++++++++++++++++++
 1 file changed, 70 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/temperature/microchip,mcp9600.yaml

diff --git a/Documentation/devicetree/bindings/iio/temperature/microchip,mcp9600.yaml b/Documentation/devicetree/bindings/iio/temperature/microchip,mcp9600.yaml
new file mode 100644
index 0000000000000..d2cafa38a5442
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/temperature/microchip,mcp9600.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/temperature/microchip,mcp9600.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip MCP9600 thermocouple EMF converter
+
+maintainers:
+  - Andrew Hepp <andrew.hepp@ahepp.dev>
+
+description:
+  https://ww1.microchip.com/downloads/en/DeviceDoc/MCP960X-Data-Sheet-20005426.pdf
+
+properties:
+  compatible:
+    const: microchip,mcp9600
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    minItems: 1
+    maxItems: 6
+
+  interrupt-names:
+    minItems: 1
+    maxItems: 6
+    items:
+      enum:
+        - open-circuit
+        - short-circuit
+        - alert1
+        - alert2
+        - alert3
+        - alert4
+
+  thermocouple-type:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Type of thermocouple (THERMOCOUPLE_TYPE_K if omitted).
+      Use defines in dt-bindings/iio/temperature/thermocouple.h.
+      Supported types are B, E, J, K, N, R, S, T.
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/iio/temperature/thermocouple.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        temperature-sensor@60 {
+            compatible = "microchip,mcp9600";
+            reg = <0x60>;
+            interrupt-parent = <&gpio>;
+            interrupts = <25 IRQ_TYPE_EDGE_RISING>;
+            interrupt-names = "open-circuit";
+            thermocouple-type = <THERMOCOUPLE_TYPE_K>;
+            vdd-supply = <&vdd>;
+        };
+    };
-- 
GitLab


From 3f6b9598b6df604a7c556873de18fcc97919b81c Mon Sep 17 00:00:00 2001
From: Andrew Hepp <andrew.hepp@ahepp.dev>
Date: Wed, 25 Oct 2023 16:31:53 -0700
Subject: [PATCH 0202/4076] iio: temperature: Add MCP9600 thermocouple EMF
 converter

Add support for the MCP9600 thermocouple electromotive force converter. The sensor has  integrated cold junction compensation and a typical accuracy of 0.5 degrees Celsius. The driver supports a resolution of 0.0625 degrees Celsius.

Datasheet: https://ww1.microchip.com/downloads/en/DeviceDoc/MCP960X-Data-Sheet-20005426.pdf
Signed-off-by: Andrew Hepp <andrew.hepp@ahepp.dev>
Link: https://lore.kernel.org/r/20231025233153.5454-2-andrew.hepp@ahepp.dev
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/temperature/Kconfig   |  10 +++
 drivers/iio/temperature/Makefile  |   1 +
 drivers/iio/temperature/mcp9600.c | 139 ++++++++++++++++++++++++++++++
 3 files changed, 150 insertions(+)
 create mode 100644 drivers/iio/temperature/mcp9600.c

diff --git a/drivers/iio/temperature/Kconfig b/drivers/iio/temperature/Kconfig
index ed384f33e0c76..ea2ce364b2e91 100644
--- a/drivers/iio/temperature/Kconfig
+++ b/drivers/iio/temperature/Kconfig
@@ -158,4 +158,14 @@ config MAX31865
 	  This driver can also be build as a module. If so, the module
 	  will be called max31865.
 
+config MCP9600
+	tristate "MCP9600 thermocouple EMF converter"
+	depends on I2C
+	help
+	  If you say yes here you get support for MCP9600
+	  thermocouple EMF converter connected via I2C.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called mcp9600.
+
 endmenu
diff --git a/drivers/iio/temperature/Makefile b/drivers/iio/temperature/Makefile
index dfec8c6d30193..9330d4a39598d 100644
--- a/drivers/iio/temperature/Makefile
+++ b/drivers/iio/temperature/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_MAXIM_THERMOCOUPLE) += maxim_thermocouple.o
 obj-$(CONFIG_MAX30208) += max30208.o
 obj-$(CONFIG_MAX31856) += max31856.o
 obj-$(CONFIG_MAX31865) += max31865.o
+obj-$(CONFIG_MCP9600) += mcp9600.o
 obj-$(CONFIG_MLX90614) += mlx90614.o
 obj-$(CONFIG_MLX90632) += mlx90632.o
 obj-$(CONFIG_TMP006) += tmp006.o
diff --git a/drivers/iio/temperature/mcp9600.c b/drivers/iio/temperature/mcp9600.c
new file mode 100644
index 0000000000000..46845804292bf
--- /dev/null
+++ b/drivers/iio/temperature/mcp9600.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * mcp9600.c - Support for Microchip MCP9600 thermocouple EMF converter
+ *
+ * Copyright (c) 2022 Andrew Hepp
+ * Author: <andrew.hepp@ahepp.dev>
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+
+#include <linux/iio/iio.h>
+
+/* MCP9600 registers */
+#define MCP9600_HOT_JUNCTION 0x0
+#define MCP9600_COLD_JUNCTION 0x2
+#define MCP9600_DEVICE_ID 0x20
+
+/* MCP9600 device id value */
+#define MCP9600_DEVICE_ID_MCP9600 0x40
+
+static const struct iio_chan_spec mcp9600_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.address = MCP9600_HOT_JUNCTION,
+		.info_mask_separate =
+			BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE),
+	},
+	{
+		.type = IIO_TEMP,
+		.address = MCP9600_COLD_JUNCTION,
+		.channel2 = IIO_MOD_TEMP_AMBIENT,
+		.modified = 1,
+		.info_mask_separate =
+			BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE),
+	},
+};
+
+struct mcp9600_data {
+	struct i2c_client *client;
+};
+
+static int mcp9600_read(struct mcp9600_data *data,
+			struct iio_chan_spec const *chan, int *val)
+{
+	int ret;
+
+	ret = i2c_smbus_read_word_swapped(data->client, chan->address);
+
+	if (ret < 0)
+		return ret;
+	*val = ret;
+
+	return 0;
+}
+
+static int mcp9600_read_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	struct mcp9600_data *data = iio_priv(indio_dev);
+	int ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = mcp9600_read(data, chan, val);
+		if (ret)
+			return ret;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		*val = 62;
+		*val2 = 500000;
+		return IIO_VAL_INT_PLUS_MICRO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info mcp9600_info = {
+	.read_raw = mcp9600_read_raw,
+};
+
+static int mcp9600_probe(struct i2c_client *client)
+{
+	struct iio_dev *indio_dev;
+	struct mcp9600_data *data;
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(client, MCP9600_DEVICE_ID);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret, "Failed to read device ID\n");
+	if (ret != MCP9600_DEVICE_ID_MCP9600)
+		dev_warn(&client->dev, "Expected ID %x, got %x\n",
+				MCP9600_DEVICE_ID_MCP9600, ret);
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+
+	indio_dev->info = &mcp9600_info;
+	indio_dev->name = "mcp9600";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = mcp9600_channels;
+	indio_dev->num_channels = ARRAY_SIZE(mcp9600_channels);
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct i2c_device_id mcp9600_id[] = {
+	{ "mcp9600" },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, mcp9600_id);
+
+static const struct of_device_id mcp9600_of_match[] = {
+	{ .compatible = "microchip,mcp9600" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mcp9600_of_match);
+
+static struct i2c_driver mcp9600_driver = {
+	.driver = {
+		.name = "mcp9600",
+		.of_match_table = mcp9600_of_match,
+	},
+	.probe = mcp9600_probe,
+	.id_table = mcp9600_id
+};
+module_i2c_driver(mcp9600_driver);
+
+MODULE_AUTHOR("Andrew Hepp <andrew.hepp@ahepp.dev>");
+MODULE_DESCRIPTION("Microchip MCP9600 thermocouple EMF converter driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From c788b9e56acd46f3a07d0fad6fc3f543c3557d2c Mon Sep 17 00:00:00 2001
From: Bragatheswaran Manickavel <bragathemanick0908@gmail.com>
Date: Fri, 27 Oct 2023 15:14:10 +0530
Subject: [PATCH 0203/4076] iio/imu: inv_icm42600: Use max() helper macros

Use the standard max() helper macros instead of direct variable comparison
using if/else blocks or ternary operator. Change identified using
minmax.cocci Coccinelle semantic patch.

Signed-off-by: Bragatheswaran Manickavel <bragathemanick0908@gmail.com>
Acked-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Link: https://lore.kernel.org/r/20231027094410.3706-1-bragathemanick0908@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c  | 5 +----
 drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c | 5 +----
 drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c   | 5 +----
 3 files changed, 3 insertions(+), 12 deletions(-)

diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
index b1e4fde27d256..f67bd5a39beb3 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
@@ -137,10 +137,7 @@ static int inv_icm42600_accel_update_scan_mode(struct iio_dev *indio_dev,
 out_unlock:
 	mutex_unlock(&st->lock);
 	/* sleep maximum required time */
-	if (sleep_accel > sleep_temp)
-		sleep = sleep_accel;
-	else
-		sleep = sleep_temp;
+	sleep = max(sleep_accel, sleep_temp);
 	if (sleep)
 		msleep(sleep);
 	return ret;
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
index 6ef1df9d60b77..b52f328fd26ce 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
@@ -424,10 +424,7 @@ out_unlock:
 	mutex_unlock(&st->lock);
 
 	/* sleep maximum required time */
-	if (sleep_sensor > sleep_temp)
-		sleep = sleep_sensor;
-	else
-		sleep = sleep_temp;
+	sleep = max(sleep_sensor, sleep_temp);
 	if (sleep)
 		msleep(sleep);
 
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
index 3bf946e56e1df..3df0a715e8856 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
@@ -137,10 +137,7 @@ static int inv_icm42600_gyro_update_scan_mode(struct iio_dev *indio_dev,
 out_unlock:
 	mutex_unlock(&st->lock);
 	/* sleep maximum required time */
-	if (sleep_gyro > sleep_temp)
-		sleep = sleep_gyro;
-	else
-		sleep = sleep_temp;
+	sleep = max(sleep_gyro, sleep_temp);
 	if (sleep)
 		msleep(sleep);
 	return ret;
-- 
GitLab


From 9405e968cfde48aecc90ff04611dab620167e1ed Mon Sep 17 00:00:00 2001
From: Ramona Gradinariu <ramona.gradinariu@analog.com>
Date: Fri, 27 Oct 2023 17:03:56 +0300
Subject: [PATCH 0204/4076] iio: imu: adis: Use spi cs inactive delay

A delay is needed each time the chip selected becomes inactive,
even after burst data readings are performed.
Currently, there is no delay added after a burst reading
and in case a new SPI transfer is performed before
the needed delay, the adis device becomes unresponsive until
reset.

This commit is adding the needed delay directly to the spi driver,
using the cs_inactive parameter, in case it is not set and is
removing the additional chip select change delay present in adis
APIs to remove the double delay.

Signed-off-by: Ramona Gradinariu <ramona.gradinariu@analog.com>
Link: https://lore.kernel.org/r/20231027140358.328699-2-ramona.gradinariu@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index bc40240b29e26..495caf4ce87a2 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -44,8 +44,6 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int value,
 			.cs_change = 1,
 			.delay.value = adis->data->write_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 2,
 			.bits_per_word = 8,
@@ -53,8 +51,6 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int value,
 			.cs_change = 1,
 			.delay.value = adis->data->write_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 4,
 			.bits_per_word = 8,
@@ -62,8 +58,6 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int value,
 			.cs_change = 1,
 			.delay.value = adis->data->write_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 6,
 			.bits_per_word = 8,
@@ -144,8 +138,6 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val,
 			.cs_change = 1,
 			.delay.value = adis->data->write_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 2,
 			.bits_per_word = 8,
@@ -153,8 +145,6 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val,
 			.cs_change = 1,
 			.delay.value = adis->data->read_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.tx_buf = adis->tx + 4,
 			.rx_buf = adis->rx,
@@ -163,8 +153,6 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val,
 			.cs_change = 1,
 			.delay.value = adis->data->read_delay,
 			.delay.unit = SPI_DELAY_UNIT_USECS,
-			.cs_change_delay.value = adis->data->cs_change_delay,
-			.cs_change_delay.unit = SPI_DELAY_UNIT_USECS,
 		}, {
 			.rx_buf = adis->rx + 2,
 			.bits_per_word = 8,
@@ -524,6 +512,12 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev,
 	}
 
 	mutex_init(&adis->state_lock);
+
+	if (!spi->cs_inactive.value) {
+		spi->cs_inactive.value = data->cs_change_delay;
+		spi->cs_inactive.unit = SPI_DELAY_UNIT_USECS;
+	}
+
 	adis->spi = spi;
 	adis->data = data;
 	iio_device_set_drvdata(indio_dev, adis);
-- 
GitLab


From 215960408d7fa241f980bcc9e31e8b5caf8ec268 Mon Sep 17 00:00:00 2001
From: Ramona Gradinariu <ramona.gradinariu@analog.com>
Date: Fri, 27 Oct 2023 17:03:57 +0300
Subject: [PATCH 0205/4076] dt-bindings: adis16475: Add
 'spi-cs-inactive-delay-ns' property

The devices supported by adis16475 driver require a stall period
between SPI transactions (during which the chip select is
inactive), with a minimum value equal to 16 microseconds, thus
adding 'spi-cs-inactive-delay-ns' property, which should indicate
the stall time between consecutive SPI transactions.
The specified minimum time may not be sufficient for all
configurations.

Signed-off-by: Ramona Gradinariu <ramona.gradinariu@analog.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231027140358.328699-3-ramona.gradinariu@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml b/Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml
index c73533c54588b..9b7ad609f7dbe 100644
--- a/Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml
@@ -47,6 +47,10 @@ properties:
   spi-max-frequency:
     maximum: 2000000
 
+  spi-cs-inactive-delay-ns:
+    minimum: 16000
+    default: 16000
+
   interrupts:
     maxItems: 1
 
-- 
GitLab


From e4cfeca8f8cb36e13a8764fc7605bb2f338be10b Mon Sep 17 00:00:00 2001
From: Ramona Gradinariu <ramona.gradinariu@analog.com>
Date: Fri, 27 Oct 2023 17:03:58 +0300
Subject: [PATCH 0206/4076] dt-bindings: adis16460: Add
 'spi-cs-inactive-delay-ns' property

The adis16460 device requires a stall time between SPI
transactions (during which the chip select is inactive),
with a minimum value equal to 16 microseconds.
This commit adds 'spi-cs-inactive-delay-ns' property, which should
indicate the stall time between consecutive SPI transactions.
The specified minimum time may not be sufficient for all
configurations.

Signed-off-by: Ramona Gradinariu <ramona.gradinariu@analog.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231027140358.328699-4-ramona.gradinariu@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml b/Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml
index 4e43c80e5119f..4cacc9948726f 100644
--- a/Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/adi,adis16460.yaml
@@ -25,6 +25,10 @@ properties:
 
   spi-cpol: true
 
+  spi-cs-inactive-delay-ns:
+    minimum: 16000
+    default: 16000
+
   interrupts:
     maxItems: 1
 
-- 
GitLab


From 2718f15403fbbff4c4116824e02537e39342986a Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <mazziesaccount@gmail.com>
Date: Mon, 16 Oct 2023 14:04:39 +0300
Subject: [PATCH 0207/4076] iio: sanity check available_scan_masks array

When IIO goes through the available scan masks in order to select the
best suiting one, it will just accept the first listed subset of channels
which meets the user's requirements. If driver lists a mask which is a
subset of some of the masks previously in the array of
avaliable_scan_masks, then the latter one will never be selected.

Add a warning if driver registers masks which can't be used due to the
available_scan_masks-array ordering.

Suggested-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Link: https://lore.kernel.org/r/e55ef0b26a6d3b323bab24920c131c79a01ba08e.1697452986.git.mazziesaccount@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 63 +++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index c77745b594bd6..34e1f8d0071cb 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -1896,6 +1896,66 @@ static int iio_check_extended_name(const struct iio_dev *indio_dev)
 
 static const struct iio_buffer_setup_ops noop_ring_setup_ops;
 
+static void iio_sanity_check_avail_scan_masks(struct iio_dev *indio_dev)
+{
+	unsigned int num_masks, masklength, longs_per_mask;
+	const unsigned long *av_masks;
+	int i;
+
+	av_masks = indio_dev->available_scan_masks;
+	masklength = indio_dev->masklength;
+	longs_per_mask = BITS_TO_LONGS(masklength);
+
+	/*
+	 * The code determining how many available_scan_masks is in the array
+	 * will be assuming the end of masks when first long with all bits
+	 * zeroed is encountered. This is incorrect for masks where mask
+	 * consists of more than one long, and where some of the available masks
+	 * has long worth of bits zeroed (but has subsequent bit(s) set). This
+	 * is a safety measure against bug where array of masks is terminated by
+	 * a single zero while mask width is greater than width of a long.
+	 */
+	if (longs_per_mask > 1)
+		dev_warn(indio_dev->dev.parent,
+			 "multi long available scan masks not fully supported\n");
+
+	if (bitmap_empty(av_masks, masklength))
+		dev_warn(indio_dev->dev.parent, "empty scan mask\n");
+
+	for (num_masks = 0; *av_masks; num_masks++)
+		av_masks += longs_per_mask;
+
+	if (num_masks < 2)
+		return;
+
+	av_masks = indio_dev->available_scan_masks;
+
+	/*
+	 * Go through all the masks from first to one before the last, and see
+	 * that no mask found later from the available_scan_masks array is a
+	 * subset of mask found earlier. If this happens, then the mask found
+	 * later will never get used because scanning the array is stopped when
+	 * the first suitable mask is found. Drivers should order the array of
+	 * available masks in the order of preference (presumably the least
+	 * costy to access masks first).
+	 */
+	for (i = 0; i < num_masks - 1; i++) {
+		const unsigned long *mask1;
+		int j;
+
+		mask1 = av_masks + i * longs_per_mask;
+		for (j = i + 1; j < num_masks; j++) {
+			const unsigned long *mask2;
+
+			mask2 = av_masks + j * longs_per_mask;
+			if (bitmap_subset(mask2, mask1, masklength))
+				dev_warn(indio_dev->dev.parent,
+					 "available_scan_mask %d subset of %d. Never used\n",
+					 j, i);
+		}
+	}
+}
+
 int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod)
 {
 	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
@@ -1934,6 +1994,9 @@ int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod)
 		goto error_unreg_debugfs;
 	}
 
+	if (indio_dev->available_scan_masks)
+		iio_sanity_check_avail_scan_masks(indio_dev);
+
 	ret = iio_device_register_sysfs(indio_dev);
 	if (ret) {
 		dev_err(indio_dev->dev.parent,
-- 
GitLab


From 6543f376ec8aa90a6c1ed44b765f4f0d6c3eb1db Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <mazziesaccount@gmail.com>
Date: Mon, 16 Oct 2023 14:04:55 +0300
Subject: [PATCH 0208/4076] iio: buffer: document known issue

Add documentation explaining why the code which scans all available scan
masks is checking only a single long worth of bits even though the code
was intended to be supporting masks wider than single long.

Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Link: https://lore.kernel.org/r/ef61c2c1e9a1c5e9f713f656871fdcb1652afdc2.1697452986.git.mazziesaccount@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-buffer.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 176d31d9f9d80..09c41e9ccf874 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -413,6 +413,22 @@ static const unsigned long *iio_scan_mask_match(const unsigned long *av_masks,
 {
 	if (bitmap_empty(mask, masklength))
 		return NULL;
+	/*
+	 * The condition here do not handle multi-long masks correctly.
+	 * It only checks the first long to be zero, and will use such mask
+	 * as a terminator even if there was bits set after the first long.
+	 *
+	 * Correct check would require using:
+	 * while (!bitmap_empty(av_masks, masklength))
+	 * instead. This is potentially hazardous because the
+	 * avaliable_scan_masks is a zero terminated array of longs - and
+	 * using the proper bitmap_empty() check for multi-long wide masks
+	 * would require the array to be terminated with multiple zero longs -
+	 * which is not such an usual pattern.
+	 *
+	 * As writing of this no multi-long wide masks were found in-tree, so
+	 * the simple while (*av_masks) check is working.
+	 */
 	while (*av_masks) {
 		if (strict) {
 			if (bitmap_equal(mask, av_masks, masklength))
-- 
GitLab


From b55d073e6501dc6077edaa945a6dad8ac5c8bbab Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Thu, 16 Nov 2023 12:18:23 +0800
Subject: [PATCH 0209/4076] power: supply: bq256xx: fix some problem in
 bq256xx_hw_init

smatch complains that there is a buffer overflow and clang complains
'ret' is never read.

Smatch error:
drivers/power/supply/bq256xx_charger.c:1578 bq256xx_hw_init() error:
buffer overflow 'bq256xx_watchdog_time' 4 <= 4

Clang static checker:
Value stored to 'ret' is never read.

Add check for buffer overflow and error code from regmap_update_bits().

Fixes: 32e4978bb920 ("power: supply: bq256xx: Introduce the BQ256XX charger driver")
Signed-off-by: Su Hui <suhui@nfschina.com>
Link: https://lore.kernel.org/r/20231116041822.1378758-1-suhui@nfschina.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq256xx_charger.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c
index 789a31bd70c39..1a935bc885108 100644
--- a/drivers/power/supply/bq256xx_charger.c
+++ b/drivers/power/supply/bq256xx_charger.c
@@ -1574,13 +1574,16 @@ static int bq256xx_hw_init(struct bq256xx_device *bq)
 			wd_reg_val = i;
 			break;
 		}
-		if (bq->watchdog_timer > bq256xx_watchdog_time[i] &&
+		if (i + 1 < BQ256XX_NUM_WD_VAL &&
+		    bq->watchdog_timer > bq256xx_watchdog_time[i] &&
 		    bq->watchdog_timer < bq256xx_watchdog_time[i + 1])
 			wd_reg_val = i;
 	}
 	ret = regmap_update_bits(bq->regmap, BQ256XX_CHARGER_CONTROL_1,
 				 BQ256XX_WATCHDOG_MASK, wd_reg_val <<
 						BQ256XX_WDT_BIT_SHIFT);
+	if (ret)
+		return ret;
 
 	ret = power_supply_get_battery_info(bq->charger, &bat_info);
 	if (ret == -ENOMEM)
-- 
GitLab


From e4e2fbe7d7d70ce52adeca7ef933488ebfe78f03 Mon Sep 17 00:00:00 2001
From: Petr Vorel <pvorel@suse.cz>
Date: Wed, 8 Nov 2023 09:56:30 +0100
Subject: [PATCH 0210/4076] MAINTAINERS: Remove snawrocki's git tree

There is already krzk/linux.git listed, which is currently used.

Signed-off-by: Petr Vorel <pvorel@suse.cz>
Acked-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Link: https://lore.kernel.org/r/20231108085630.7767-1-pvorel@suse.cz
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cfd..fcd734e1e0455 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19219,7 +19219,6 @@ R:	Alim Akhtar <alim.akhtar@samsung.com>
 L:	linux-samsung-soc@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux.git
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/snawrocki/clk.git
 F:	Documentation/devicetree/bindings/clock/samsung,*.yaml
 F:	Documentation/devicetree/bindings/clock/samsung,s3c*
 F:	drivers/clk/samsung/
-- 
GitLab


From 9e0e9e85e74e4893dc5a2c5a6da54f64cf45290e Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 9 Nov 2023 15:37:05 +0200
Subject: [PATCH 0211/4076] i3c: mipi-i3c-hci: Report NACK response from CCC
 command to core

Currently probe of mipi-i3c-hci will fail if bus doesn't have any I3C
devices connected. This happens when CCC commands that are sent during
i3c_master_bus_init() are not ACKed by any device and controller responds
with an error status set.

The controller can detect NACK both during I3C address header
transmission (broadcast address 0x7e is not ACKed) and when target
device address or dynamic address assignment is NACKed. Former as error
status 0x4: Address Header Error and latter as 0x5: NACK.

Difference between those two NACK statuses were not described explicitly
until MIPI I3C HCI Specification v1.1. Earlier versions share the same
error status code though.

Report both of those as I3C_ERROR_M2 to I3C core code.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Link: https://lore.kernel.org/r/20231109133708.653950-2-jarkko.nikula@linux.intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 1ae56a5699c6b..8471a1fe1dad9 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -245,7 +245,14 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m,
 		if (ccc->rnw)
 			ccc->dests[i - prefixed].payload.len =
 				RESP_DATA_LENGTH(xfer[i].response);
-		if (RESP_STATUS(xfer[i].response) != RESP_SUCCESS) {
+		switch (RESP_STATUS(xfer[i].response)) {
+		case RESP_SUCCESS:
+			continue;
+		case RESP_ERR_ADDR_HEADER:
+		case RESP_ERR_NACK:
+			ccc->err = I3C_ERROR_M2;
+			fallthrough;
+		default:
 			ret = -EIO;
 			goto out;
 		}
-- 
GitLab


From 0be1a06c66c9522abc264bd9cb4df7e676b13ae3 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 9 Nov 2023 15:37:06 +0200
Subject: [PATCH 0212/4076] i3c: mipi-i3c-hci: Do not overallocate transfers in
 hci_cmd_v1_daa()

Function hci_cmd_v1_daa() uses only single transfer at a time so no need
to allocate two transfers and access can be simplified.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Link: https://lore.kernel.org/r/20231109133708.653950-3-jarkko.nikula@linux.intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd_v1.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
index 2b2323aa67141..31f03cb22489a 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
@@ -298,7 +298,7 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 	unsigned int dcr, bcr;
 	DECLARE_COMPLETION_ONSTACK(done);
 
-	xfer = hci_alloc_xfer(2);
+	xfer = hci_alloc_xfer(1);
 	if (!xfer)
 		return -ENOMEM;
 
@@ -339,12 +339,12 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 			ret = -ETIME;
 			break;
 		}
-		if (RESP_STATUS(xfer[0].response) == RESP_ERR_NACK &&
+		if (RESP_STATUS(xfer->response) == RESP_ERR_NACK &&
 		    RESP_DATA_LENGTH(xfer->response) == 1) {
 			ret = 0;  /* no more devices to be assigned */
 			break;
 		}
-		if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) {
+		if (RESP_STATUS(xfer->response) != RESP_SUCCESS) {
 			ret = -EIO;
 			break;
 		}
-- 
GitLab


From f83f86e506e6b776ba5dd70f919f7e2856f9e061 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 9 Nov 2023 15:37:07 +0200
Subject: [PATCH 0213/4076] i3c: mipi-i3c-hci: Handle I3C address header error
 in hci_cmd_v1_daa()

Handle also I3C address header error response status as the end of DAA
process in hci_cmd_v1_daa().

According to MIPI I3C HCI Specification v1.1 the NACK error during DAA
process comes when the device does not accept the dynamic address.
Currently code uses it for successful exit from the process and fails
with any other error response.

I'm unsure is this MIPI I3C HCI version specific difference or
specification misunderstanding but on an early MIPI I3C HCI version
compatible controller responds always with I3C address header error and
not with NACK error when there is no device on the bus or no more devices
participating to DAA process.

Handle now both response statuses as the end of DAA.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Link: https://lore.kernel.org/r/20231109133708.653950-4-jarkko.nikula@linux.intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd_v1.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
index 31f03cb22489a..638b054d6c927 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
@@ -339,7 +339,8 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 			ret = -ETIME;
 			break;
 		}
-		if (RESP_STATUS(xfer->response) == RESP_ERR_NACK &&
+		if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER ||
+		     RESP_STATUS(xfer->response) == RESP_ERR_NACK) &&
 		    RESP_DATA_LENGTH(xfer->response) == 1) {
 			ret = 0;  /* no more devices to be assigned */
 			break;
-- 
GitLab


From 4afd72876942f2ab1e97e79082464a46ab40a485 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 9 Nov 2023 15:37:08 +0200
Subject: [PATCH 0214/4076] i3c: mipi-i3c-hci: Add DMA bounce buffer for
 private transfers

Implement a local bounce buffer for private I3C SDR and I2C transfers
when using DMA and the buffer attached to the transfer is not DMA safe.

Otherwise the DMA transfer will fail and with following warning:

[   11.411059] i3c mipi-i3c-hci.0: rejecting DMA map of vmalloc memory
[   11.417313] WARNING: CPU: 3 PID: 357 at include/linux/dma-mapping.h:332 hci_dma_queue_xfer+0x2e2/0x300 [mipi_i3c_hci]

Strictly speaking private I3C SDR transfers are expected to pass a
DMA-able buffer. However I fear this requirement may easily be slipped
or go unnoticed when I3C interface support is added into a existing
device driver that use regmap API to read/write stack variables.

For example this is the case with the commit 2660b0080bb2 ("iio: imu:
st_lsm6dsx: add i3c basic support for LSM6DSO and LSM6DSR").

Buffer of an I2C message is not required to be DMA safe and the I2C core
provides i2c_(get|put)_dma_safe_msg_buf() helpers for the host
controllers that do DMA and that is also recommendation for the
i2c_xfers() callback from the I3C core.

However due to above I3C private transfers reason I decided to implement
a bounce buffer for them and reuse the same code for the I2C transfers
too. Since this driver is currently the only I3C host controller driver
that can do DMA the implementation is done here and not in I3C core.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Link: https://lore.kernel.org/r/20231109133708.653950-5-jarkko.nikula@linux.intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 40 ++++++++++++++++++++++++++
 drivers/i3c/master/mipi-i3c-hci/dma.c  |  4 ++-
 drivers/i3c/master/mipi-i3c-hci/hci.h  |  1 +
 3 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 8471a1fe1dad9..d7e966a255833 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -276,6 +276,34 @@ static int i3c_hci_daa(struct i3c_master_controller *m)
 	return hci->cmd->perform_daa(hci);
 }
 
+static int i3c_hci_alloc_safe_xfer_buf(struct i3c_hci *hci,
+				       struct hci_xfer *xfer)
+{
+	if (hci->io != &mipi_i3c_hci_dma ||
+	    xfer->data == NULL || !is_vmalloc_addr(xfer->data))
+		return 0;
+
+	if (xfer->rnw)
+		xfer->bounce_buf = kzalloc(xfer->data_len, GFP_KERNEL);
+	else
+		xfer->bounce_buf = kmemdup(xfer->data,
+					   xfer->data_len, GFP_KERNEL);
+
+	return xfer->bounce_buf == NULL ? -ENOMEM : 0;
+}
+
+static void i3c_hci_free_safe_xfer_buf(struct i3c_hci *hci,
+				       struct hci_xfer *xfer)
+{
+	if (hci->io != &mipi_i3c_hci_dma || xfer->bounce_buf == NULL)
+		return;
+
+	if (xfer->rnw)
+		memcpy(xfer->data, xfer->bounce_buf, xfer->data_len);
+
+	kfree(xfer->bounce_buf);
+}
+
 static int i3c_hci_priv_xfers(struct i3c_dev_desc *dev,
 			      struct i3c_priv_xfer *i3c_xfers,
 			      int nxfers)
@@ -309,6 +337,9 @@ static int i3c_hci_priv_xfers(struct i3c_dev_desc *dev,
 		}
 		hci->cmd->prep_i3c_xfer(hci, dev, &xfer[i]);
 		xfer[i].cmd_desc[0] |= CMD_0_ROC;
+		ret = i3c_hci_alloc_safe_xfer_buf(hci, &xfer[i]);
+		if (ret)
+			goto out;
 	}
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
@@ -332,6 +363,9 @@ static int i3c_hci_priv_xfers(struct i3c_dev_desc *dev,
 	}
 
 out:
+	for (i = 0; i < nxfers; i++)
+		i3c_hci_free_safe_xfer_buf(hci, &xfer[i]);
+
 	hci_free_xfer(xfer, nxfers);
 	return ret;
 }
@@ -357,6 +391,9 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev,
 		xfer[i].rnw = i2c_xfers[i].flags & I2C_M_RD;
 		hci->cmd->prep_i2c_xfer(hci, dev, &xfer[i]);
 		xfer[i].cmd_desc[0] |= CMD_0_ROC;
+		ret = i3c_hci_alloc_safe_xfer_buf(hci, &xfer[i]);
+		if (ret)
+			goto out;
 	}
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
@@ -378,6 +415,9 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev,
 	}
 
 out:
+	for (i = 0; i < nxfers; i++)
+		i3c_hci_free_safe_xfer_buf(hci, &xfer[i]);
+
 	hci_free_xfer(xfer, nxfers);
 	return ret;
 }
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index c805a8497319d..4e01a95cc4d0a 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -362,6 +362,7 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	struct hci_rh_data *rh;
 	unsigned int i, ring, enqueue_ptr;
 	u32 op1_val, op2_val;
+	void *buf;
 
 	/* For now we only use ring 0 */
 	ring = 0;
@@ -390,9 +391,10 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 
 		/* 2nd and 3rd words of Data Buffer Descriptor Structure */
 		if (xfer->data) {
+			buf = xfer->bounce_buf ? xfer->bounce_buf : xfer->data;
 			xfer->data_dma =
 				dma_map_single(&hci->master.dev,
-					       xfer->data,
+					       buf,
 					       xfer->data_len,
 					       xfer->rnw ?
 						  DMA_FROM_DEVICE :
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index f109923f6c3f3..f94d95e024bec 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -90,6 +90,7 @@ struct hci_xfer {
 		struct {
 			/* DMA specific */
 			dma_addr_t data_dma;
+			void *bounce_buf;
 			int ring_number;
 			int ring_entry;
 		};
-- 
GitLab


From 2aac0bf4ebc8e09941bb2a40c0ce725437d9a82c Mon Sep 17 00:00:00 2001
From: Joshua Yeong <joshua.yeong@starfivetech.com>
Date: Tue, 14 Nov 2023 16:55:25 +0800
Subject: [PATCH 0215/4076] i3c: Add fallback method for GETMXDS CCC

Some I3C hardware will report error when an incorrect length is received from
device. GETMXDS CCC are available in 2 formats: without turnaround time (format
1) and with turnaround time (format 2). There is no mechanics to determine which
format is supported by device. So in case sending GETMXDS CCC format 2 resulted
in a failure, try sending GETMXDS CCC format 1 instead.

Signed-off-by: Joshua Yeong <joshua.yeong@starfivetech.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231114085525.6271-2-joshua.yeong@starfivetech.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 95caa162706f5..718b643cb54dd 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -1130,8 +1130,16 @@ static int i3c_master_getmxds_locked(struct i3c_master_controller *master,
 
 	i3c_ccc_cmd_init(&cmd, true, I3C_CCC_GETMXDS, &dest, 1);
 	ret = i3c_master_send_ccc_cmd_locked(master, &cmd);
-	if (ret)
-		goto out;
+	if (ret) {
+		/*
+		 * Retry when the device does not support max read turnaround
+		 * while expecting shorter length from this CCC command.
+		 */
+		dest->payload.len -= 3;
+		ret = i3c_master_send_ccc_cmd_locked(master, &cmd);
+		if (ret)
+			goto out;
+	}
 
 	if (dest.payload.len != 2 && dest.payload.len != 5) {
 		ret = -EIO;
-- 
GitLab


From fedfa36d045ab78ea9a0aa2c5a3d5d74c27207d3 Mon Sep 17 00:00:00 2001
From: Jiri Valek - 2N <jiriv@axis.com>
Date: Fri, 17 Nov 2023 02:41:52 +0000
Subject: [PATCH 0216/4076] Input: cap11xx - remove unnecessary IRQ parsing

Separate IRQ parsing is not necessary, I2C core do the job.

Signed-off-by: Jiri Valek - 2N <jiriv@axis.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/cap11xx.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 1b4937dce6725..01e7ead68fead 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -10,7 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/input.h>
 #include <linux/leds.h>
-#include <linux/of_irq.h>
+#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/i2c.h>
 #include <linux/gpio/consumer.h>
@@ -334,7 +334,7 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	struct cap11xx_priv *priv;
 	struct device_node *node;
 	const struct cap11xx_hw_model *cap;
-	int i, error, irq, gain = 0;
+	int i, error, gain = 0;
 	unsigned int val, rev;
 	u32 gain32;
 
@@ -474,13 +474,8 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	if (error)
 		return error;
 
-	irq = irq_of_parse_and_map(node, 0);
-	if (!irq) {
-		dev_err(dev, "Unable to parse or map IRQ\n");
-		return -ENXIO;
-	}
-
-	error = devm_request_threaded_irq(dev, irq, NULL, cap11xx_thread_func,
+	error = devm_request_threaded_irq(dev, i2c_client->irq,
+					  NULL, cap11xx_thread_func,
 					  IRQF_ONESHOT, dev_name(dev), priv);
 	if (error)
 		return error;
-- 
GitLab


From 5496fb8eedd637e1e9d87655f86dc816afd5ad68 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Tue, 14 Nov 2023 12:19:02 +0100
Subject: [PATCH 0217/4076] drivers/fpga: use standard array-copy function

dfl.c utilizes memdup_user() and array_size() to copy a userspace array.
array_size() will likely never trigger thanks to the preceding check.
Nevertheless, in the theoretical event that it would, it would return
SIZE_MAX to memdup_user(), resulting in an attempt to allocate huge
amounts of memory.

string.h from the core-api now provides memdup_array_user() which also
performs an overflow check and returns an error-pointer with -EOVERFLOW
to the caller.
As an additional advantage it standardizes how userspace-arrays are
being copied and, thus, makes it more obvious to readers that an array
is being copied.

Replace memdup_user() with memdup_array_user().

Suggested-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/20231114111901.19380-2-pstanner@redhat.com
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/dfl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c
index dd7a783d53b5f..e69b9f1f2a50c 100644
--- a/drivers/fpga/dfl.c
+++ b/drivers/fpga/dfl.c
@@ -2008,8 +2008,8 @@ long dfl_feature_ioctl_set_irq(struct platform_device *pdev,
 	    (hdr.start + hdr.count < hdr.start))
 		return -EINVAL;
 
-	fds = memdup_user((void __user *)(arg + sizeof(hdr)),
-			  array_size(hdr.count, sizeof(s32)));
+	fds = memdup_array_user((void __user *)(arg + sizeof(hdr)),
+				hdr.count, sizeof(s32));
 	if (IS_ERR(fds))
 		return PTR_ERR(fds);
 
-- 
GitLab


From b4da37db3e2cfc1c60875b0c10cfc556d5342a3a Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Fri, 17 Nov 2023 13:09:24 +0200
Subject: [PATCH 0218/4076] i3c: master: Fix build error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix build error caused by commit 2aac0bf4ebc8 ("i3c: Add fallback method
for GETMXDS CCC") which incorrectly access the "struct i3c_ccc_cmd_dest
dest" as pointer.

drivers/i3c/master.c: In function ‘i3c_master_getmxds_locked’:
drivers/i3c/master.c:1140:21: error: invalid type argument of ‘->’ (have ‘struct i3c_ccc_cmd_dest’)
 1140 |                 dest->payload.len -= 3;
      |                     ^~

Fixes: 2aac0bf4ebc8 ("i3c: Add fallback method for GETMXDS CCC")
Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231117110924.634280-1-jarkko.nikula@linux.intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 718b643cb54dd..8b729ebae2a6e 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -1135,7 +1135,7 @@ static int i3c_master_getmxds_locked(struct i3c_master_controller *master,
 		 * Retry when the device does not support max read turnaround
 		 * while expecting shorter length from this CCC command.
 		 */
-		dest->payload.len -= 3;
+		dest.payload.len -= 3;
 		ret = i3c_master_send_ccc_cmd_locked(master, &cmd);
 		if (ret)
 			goto out;
-- 
GitLab


From 3d762e21d56370a43478b55e604b4a83dd85aafc Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 6 Nov 2023 10:23:10 -0600
Subject: [PATCH 0219/4076] rtc: cmos: Use ACPI alarm for non-Intel x86 systems
 too

Intel systems > 2015 have been configured to use ACPI alarm instead
of HPET to avoid s2idle issues.

Having HPET programmed for wakeup causes problems on AMD systems with
s2idle as well.

One particular case is that the systemd "SuspendThenHibernate" feature
doesn't work properly on the Framework 13" AMD model. Switching to
using ACPI alarm fixes the issue.

Adjust the quirk to apply to AMD/Hygon systems from 2021 onwards.
This matches what has been tested and is specifically to avoid potential
risk to older systems.

Cc:  <stable@vger.kernel.org> # 6.1+
Reported-by:  <alvin.zhuge@gmail.com>
Reported-by:  <renzhamin@gmail.com>
Closes: https://github.com/systemd/systemd/issues/24279
Reported-by: Kelvie Wong <kelvie@kelvie.ca>
Closes: https://community.frame.work/t/systemd-suspend-then-hibernate-wakes-up-after-5-minutes/39392
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20231106162310.85711-1-mario.limonciello@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-cmos.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 228fb2d11c709..696cfa7025ded 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -818,18 +818,24 @@ static void rtc_wake_off(struct device *dev)
 }
 
 #ifdef CONFIG_X86
-/* Enable use_acpi_alarm mode for Intel platforms no earlier than 2015 */
 static void use_acpi_alarm_quirks(void)
 {
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		if (dmi_get_bios_year() < 2015)
+			return;
+		break;
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_HYGON:
+		if (dmi_get_bios_year() < 2021)
+			return;
+		break;
+	default:
 		return;
-
+	}
 	if (!is_hpet_enabled())
 		return;
 
-	if (dmi_get_bios_year() < 2015)
-		return;
-
 	use_acpi_alarm = true;
 }
 #else
-- 
GitLab


From e44a4dc4b36cc087878596b937d52caca35e9b19 Mon Sep 17 00:00:00 2001
From: Dimitri John Ledkov <dimitri.ledkov@canonical.com>
Date: Sun, 22 Oct 2023 20:40:26 +0100
Subject: [PATCH 0220/4076] apparmor: switch SECURITY_APPARMOR_HASH from sha1
 to sha256

sha1 is insecure and has colisions, thus it is not useful for even
lightweight policy hash checks. Switch to sha256, which on modern
hardware is fast enough.

Separately as per NIST Policy on Hash Functions, sha1 usage must be
withdrawn by 2030. This config option currently is one of many that
holds up sha1 usage.

Signed-off-by: Dimitri John Ledkov <dimitri.ledkov@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/Kconfig      | 12 ++++++------
 security/apparmor/apparmorfs.c | 16 ++++++++--------
 security/apparmor/crypto.c     |  6 +++---
 3 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/security/apparmor/Kconfig b/security/apparmor/Kconfig
index e0d1dd0a192a9..64cc3044a42ce 100644
--- a/security/apparmor/Kconfig
+++ b/security/apparmor/Kconfig
@@ -57,10 +57,10 @@ config SECURITY_APPARMOR_INTROSPECT_POLICY
 	  cpu is paramount.
 
 config SECURITY_APPARMOR_HASH
-	bool "Enable introspection of sha1 hashes for loaded profiles"
+	bool "Enable introspection of sha256 hashes for loaded profiles"
 	depends on SECURITY_APPARMOR_INTROSPECT_POLICY
 	select CRYPTO
-	select CRYPTO_SHA1
+	select CRYPTO_SHA256
 	default y
 	help
 	  This option selects whether introspection of loaded policy
@@ -74,10 +74,10 @@ config SECURITY_APPARMOR_HASH_DEFAULT
        depends on SECURITY_APPARMOR_HASH
        default y
        help
-         This option selects whether sha1 hashing of loaded policy
-	 is enabled by default. The generation of sha1 hashes for
-	 loaded policy provide system administrators a quick way
-	 to verify that policy in the kernel matches what is expected,
+	 This option selects whether sha256 hashing of loaded policy
+	 is enabled by default. The generation of sha256 hashes for
+	 loaded policy provide system administrators a quick way to
+	 verify that policy in the kernel matches what is expected,
 	 however it can slow down policy load on some devices. In
 	 these cases policy hashing can be disabled by default and
 	 enabled only if needed.
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 38650e52ef578..21a6413b84726 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -1474,7 +1474,7 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 	rawdata->dents[AAFS_LOADDATA_REVISION] = dent;
 
 	if (aa_g_hash_policy) {
-		dent = aafs_create_file("sha1", S_IFREG | 0444, dir,
+		dent = aafs_create_file("sha256", S_IFREG | 0444, dir,
 					      rawdata, &seq_rawdata_hash_fops);
 		if (IS_ERR(dent))
 			goto fail;
@@ -1648,11 +1648,11 @@ static const char *rawdata_get_link_base(struct dentry *dentry,
 	return target;
 }
 
-static const char *rawdata_get_link_sha1(struct dentry *dentry,
+static const char *rawdata_get_link_sha256(struct dentry *dentry,
 					 struct inode *inode,
 					 struct delayed_call *done)
 {
-	return rawdata_get_link_base(dentry, inode, done, "sha1");
+	return rawdata_get_link_base(dentry, inode, done, "sha256");
 }
 
 static const char *rawdata_get_link_abi(struct dentry *dentry,
@@ -1669,8 +1669,8 @@ static const char *rawdata_get_link_data(struct dentry *dentry,
 	return rawdata_get_link_base(dentry, inode, done, "raw_data");
 }
 
-static const struct inode_operations rawdata_link_sha1_iops = {
-	.get_link	= rawdata_get_link_sha1,
+static const struct inode_operations rawdata_link_sha256_iops = {
+	.get_link	= rawdata_get_link_sha256,
 };
 
 static const struct inode_operations rawdata_link_abi_iops = {
@@ -1743,7 +1743,7 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
 	profile->dents[AAFS_PROF_ATTACH] = dent;
 
 	if (profile->hash) {
-		dent = create_profile_file(dir, "sha1", profile,
+		dent = create_profile_file(dir, "sha256", profile,
 					   &seq_profile_hash_fops);
 		if (IS_ERR(dent))
 			goto fail;
@@ -1753,9 +1753,9 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
 #ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
 	if (profile->rawdata) {
 		if (aa_g_hash_policy) {
-			dent = aafs_create("raw_sha1", S_IFLNK | 0444, dir,
+			dent = aafs_create("raw_sha256", S_IFLNK | 0444, dir,
 					   profile->label.proxy, NULL, NULL,
-					   &rawdata_link_sha1_iops);
+					   &rawdata_link_sha256_iops);
 			if (IS_ERR(dent))
 				goto fail;
 			aa_get_proxy(profile->label.proxy);
diff --git a/security/apparmor/crypto.c b/security/apparmor/crypto.c
index 6724e2ff6da89..aad486b2fca65 100644
--- a/security/apparmor/crypto.c
+++ b/security/apparmor/crypto.c
@@ -106,16 +106,16 @@ static int __init init_profile_hash(void)
 	if (!apparmor_initialized)
 		return 0;
 
-	tfm = crypto_alloc_shash("sha1", 0, 0);
+	tfm = crypto_alloc_shash("sha256", 0, 0);
 	if (IS_ERR(tfm)) {
 		int error = PTR_ERR(tfm);
-		AA_ERROR("failed to setup profile sha1 hashing: %d\n", error);
+		AA_ERROR("failed to setup profile sha256 hashing: %d\n", error);
 		return error;
 	}
 	apparmor_tfm = tfm;
 	apparmor_hash_size = crypto_shash_digestsize(apparmor_tfm);
 
-	aa_info_message("AppArmor sha1 policy hashing enabled");
+	aa_info_message("AppArmor sha256 policy hashing enabled");
 
 	return 0;
 }
-- 
GitLab


From 3c49ce0e220912406a478ac128657672608200a0 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Thu, 9 Nov 2023 06:32:28 -0800
Subject: [PATCH 0221/4076] apparmor: declare stack_msg as static

stack_msg in upstream code is only used in securit/apparmor/domain.c
so declare it as static.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311092251.TwKSNZ0u-lkp@intel.com/
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/domain.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 89fbeab4b33bd..571158ec6188f 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -1311,7 +1311,7 @@ static int change_profile_perms_wrapper(const char *op, const char *name,
 	return error;
 }
 
-const char *stack_msg = "change_profile unprivileged unconfined converted to stacking";
+static const char *stack_msg = "change_profile unprivileged unconfined converted to stacking";
 
 /**
  * aa_change_profile - perform a one-way profile transition
-- 
GitLab


From 735ad5d1532a811d068a731dff46fa02c2185981 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Sun, 19 Nov 2023 01:14:10 -0800
Subject: [PATCH 0222/4076] apparmor: declare nulldfa as static

With the conversion to a refcounted pdb the nulldfa is now only used
in security/apparmor/lsm.c so declar it as static.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311092038.lqfYnvmf-lkp@intel.com/
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/lsm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 4981bdf029931..d3d2fc13c6e7c 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -2106,7 +2106,7 @@ __initcall(apparmor_nf_ip_init);
 static char nulldfa_src[] = {
 	#include "nulldfa.in"
 };
-struct aa_dfa *nulldfa;
+static struct aa_dfa *nulldfa;
 
 static char stacksplitdfa_src[] = {
 	#include "stacksplitdfa.in"
-- 
GitLab


From a7e405a2de69fe5e6657046e978a81683b140051 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Sun, 19 Nov 2023 01:19:41 -0800
Subject: [PATCH 0223/4076] apparmor: add missing params to aa_may_ptrace
 kernel-doc comments

When the cred was explicit passed through to aa_may_ptrace() the
kernel-doc comment was not properly updated.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311040508.AUhi04RY-lkp@intel.com/
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/task.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/security/apparmor/task.c b/security/apparmor/task.c
index f29a2e80e6bf6..c87fb9f4ac18a 100644
--- a/security/apparmor/task.c
+++ b/security/apparmor/task.c
@@ -278,7 +278,9 @@ static int profile_tracer_perm(const struct cred *cred,
 
 /**
  * aa_may_ptrace - test if tracer task can trace the tracee
+ * @tracer_cred: cred of task doing the tracing  (NOT NULL)
  * @tracer: label of the task doing the tracing  (NOT NULL)
+ * @tracee_cred: cred of task to be traced
  * @tracee: task label to be traced
  * @request: permission request
  *
-- 
GitLab


From fb49b6f65a699b3463f5b2f16815340bbd3dabeb Mon Sep 17 00:00:00 2001
From: Iuliana Prodan <iuliana.prodan@nxp.com>
Date: Fri, 13 Oct 2023 18:27:30 +0300
Subject: [PATCH 0224/4076] remoteproc: imx_dsp_rproc: Add mandatory
 find_loaded_rsc_table op

Add the .find_loaded_rsc_table operation for i.MX DSP.
We need it for inter-process communication between DSP
and main core.

This callback is used to find the resource table (defined
in remote processor linker script) where the address of the
vrings along with the other allocated resources (carveouts etc)
are stored.
If this is not found, the vrings are not allocated and
the IPC between cores will not work.

Signed-off-by: Iuliana Prodan <iuliana.prodan@nxp.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://lore.kernel.org/r/20231013152731.23471-2-iuliana.prodan@oss.nxp.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/imx_dsp_rproc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/remoteproc/imx_dsp_rproc.c b/drivers/remoteproc/imx_dsp_rproc.c
index 8fcda9b745459..a1c62d15f16c6 100644
--- a/drivers/remoteproc/imx_dsp_rproc.c
+++ b/drivers/remoteproc/imx_dsp_rproc.c
@@ -940,6 +940,7 @@ static const struct rproc_ops imx_dsp_rproc_ops = {
 	.kick		= imx_dsp_rproc_kick,
 	.load		= imx_dsp_rproc_elf_load_segments,
 	.parse_fw	= imx_dsp_rproc_parse_fw,
+	.find_loaded_rsc_table = rproc_elf_find_loaded_rsc_table,
 	.sanity_check	= rproc_elf_sanity_check,
 	.get_boot_addr	= rproc_elf_get_boot_addr,
 };
-- 
GitLab


From cae0e61beb7acb1c54a17e5418978f096d66def6 Mon Sep 17 00:00:00 2001
From: Iuliana Prodan <iuliana.prodan@nxp.com>
Date: Fri, 13 Oct 2023 18:27:31 +0300
Subject: [PATCH 0225/4076] arm64: dts: imx8mp: Add reserve-memory nodes for
 DSP

Add the reserve-memory nodes used by DSP when the rpmsg
feature is enabled.

Signed-off-by: Iuliana Prodan <iuliana.prodan@nxp.com>
Acked-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Link: https://lore.kernel.org/r/20231013152731.23471-3-iuliana.prodan@oss.nxp.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 arch/arm64/boot/dts/freescale/imx8mp-evk.dts | 22 ++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
index cc9d468b43ab8..f87fa5a948ccc 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
@@ -137,6 +137,28 @@
 		};
 
 	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		dsp_vdev0vring0: vdev0vring0@942f0000 {
+			reg = <0 0x942f0000 0 0x8000>;
+			no-map;
+		};
+
+		dsp_vdev0vring1: vdev0vring1@942f8000 {
+			reg = <0 0x942f8000 0 0x8000>;
+			no-map;
+		};
+
+		dsp_vdev0buffer: vdev0buffer@94300000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x94300000 0 0x100000>;
+			no-map;
+		};
+	};
 };
 
 &flexspi {
-- 
GitLab


From d9dcdb4531fe39ce48919ef8c2c9369ee49f3ad2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 20 Oct 2023 11:21:07 +0200
Subject: [PATCH 0226/4076] PCI: host-generic: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code.  However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

pci_host_common_remove() returned zero unconditionally. With that converted
to return void instead, the generic pci host driver can be switched to
.remove_new() trivially.

Link: https://lore.kernel.org/r/20231020092107.2148311-1-u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Will Deacon <will@kernel.org>
---
 drivers/pci/controller/pci-host-common.c  | 4 +---
 drivers/pci/controller/pci-host-generic.c | 2 +-
 include/linux/pci-ecam.h                  | 2 +-
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c
index 6be3266cd7b5b..45b71806182d2 100644
--- a/drivers/pci/controller/pci-host-common.c
+++ b/drivers/pci/controller/pci-host-common.c
@@ -85,7 +85,7 @@ int pci_host_common_probe(struct platform_device *pdev)
 }
 EXPORT_SYMBOL_GPL(pci_host_common_probe);
 
-int pci_host_common_remove(struct platform_device *pdev)
+void pci_host_common_remove(struct platform_device *pdev)
 {
 	struct pci_host_bridge *bridge = platform_get_drvdata(pdev);
 
@@ -93,8 +93,6 @@ int pci_host_common_remove(struct platform_device *pdev)
 	pci_stop_root_bus(bridge->bus);
 	pci_remove_root_bus(bridge->bus);
 	pci_unlock_rescan_remove();
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_host_common_remove);
 
diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c
index 63865aeb636b8..41cb6a057f6e4 100644
--- a/drivers/pci/controller/pci-host-generic.c
+++ b/drivers/pci/controller/pci-host-generic.c
@@ -82,7 +82,7 @@ static struct platform_driver gen_pci_driver = {
 		.of_match_table = gen_pci_of_match,
 	},
 	.probe = pci_host_common_probe,
-	.remove = pci_host_common_remove,
+	.remove_new = pci_host_common_remove,
 };
 module_platform_driver(gen_pci_driver);
 
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
index 6b1301e2498e9..3a4860bd27586 100644
--- a/include/linux/pci-ecam.h
+++ b/include/linux/pci-ecam.h
@@ -93,6 +93,6 @@ extern const struct pci_ecam_ops loongson_pci_ecam_ops; /* Loongson PCIe */
 #if IS_ENABLED(CONFIG_PCI_HOST_COMMON)
 /* for DT-based PCI controllers that support ECAM */
 int pci_host_common_probe(struct platform_device *pdev);
-int pci_host_common_remove(struct platform_device *pdev);
+void pci_host_common_remove(struct platform_device *pdev);
 #endif
 #endif
-- 
GitLab


From 9a000a72af75886e5de13f4edef7f0d788622e7d Mon Sep 17 00:00:00 2001
From: Tadeusz Struk <tstruk@gigaio.com>
Date: Mon, 13 Nov 2023 19:03:25 +0100
Subject: [PATCH 0227/4076] PCI/P2PDMA: Remove reference to pci_p2pdma_map_sg()

Update Documentation/driver-api/pci/p2pdma.rst doc and remove references to
obsolete p2pdma mapping functions.

Fixes: 0d06132fc84b ("PCI/P2PDMA: Remove pci_p2pdma_[un]map_sg()")
Link: https://lore.kernel.org/r/20231113180325.444692-1-tstruk@gmail.com
Signed-off-by: Tadeusz Struk <tstruk@gigaio.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Cc: stable@kernel.org
---
 Documentation/driver-api/pci/p2pdma.rst | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/Documentation/driver-api/pci/p2pdma.rst b/Documentation/driver-api/pci/p2pdma.rst
index 44deb52beeb47..d0b241628cf13 100644
--- a/Documentation/driver-api/pci/p2pdma.rst
+++ b/Documentation/driver-api/pci/p2pdma.rst
@@ -83,19 +83,9 @@ this to include other types of resources like doorbells.
 Client Drivers
 --------------
 
-A client driver typically only has to conditionally change its DMA map
-routine to use the mapping function :c:func:`pci_p2pdma_map_sg()` instead
-of the usual :c:func:`dma_map_sg()` function. Memory mapped in this
-way does not need to be unmapped.
-
-The client may also, optionally, make use of
-:c:func:`is_pci_p2pdma_page()` to determine when to use the P2P mapping
-functions and when to use the regular mapping functions. In some
-situations, it may be more appropriate to use a flag to indicate a
-given request is P2P memory and map appropriately. It is important to
-ensure that struct pages that back P2P memory stay out of code that
-does not have support for them as other code may treat the pages as
-regular memory which may not be appropriate.
+A client driver only has to use the mapping API :c:func:`dma_map_sg()`
+and :c:func:`dma_unmap_sg()` functions as usual, and the implementation
+will do the right thing for the P2P capable memory.
 
 
 Orchestrator Drivers
-- 
GitLab


From e585a37e5061f6d5060517aed1ca4ccb2e56a34c Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@igalia.com>
Date: Mon, 20 Nov 2023 13:04:36 -0300
Subject: [PATCH 0228/4076] PCI: Only override AMD USB controller if required

By running a Van Gogh device (Steam Deck), the following message
was noticed in the kernel log:

  pci 0000:04:00.3: PCI class overridden (0x0c03fe -> 0x0c03fe) so dwc3 driver can claim this instead of xhci

Effectively this means the quirk executed but changed nothing, since the
class of this device was already the proper one (likely adjusted by newer
firmware versions).

Check and perform the override only if necessary.

Link: https://lore.kernel.org/r/20231120160531.361552-1-gpiccoli@igalia.com
Signed-off-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Huang Rui <ray.huang@amd.com>
Cc: Vicki Pfau <vi@endrift.com>
---
 drivers/pci/quirks.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index ea476252280ab..4e3bb1643b093 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -702,10 +702,13 @@ static void quirk_amd_dwc_class(struct pci_dev *pdev)
 {
 	u32 class = pdev->class;
 
-	/* Use "USB Device (not host controller)" class */
-	pdev->class = PCI_CLASS_SERIAL_USB_DEVICE;
-	pci_info(pdev, "PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n",
-		 class, pdev->class);
+	if (class != PCI_CLASS_SERIAL_USB_DEVICE) {
+		/* Use "USB Device (not host controller)" class */
+		pdev->class = PCI_CLASS_SERIAL_USB_DEVICE;
+		pci_info(pdev,
+			"PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n",
+			class, pdev->class);
+	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB,
 		quirk_amd_dwc_class);
-- 
GitLab


From 3171e46d677a668eed3086da78671f1e4f5b8405 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 13:42:18 +0200
Subject: [PATCH 0229/4076] PCI: Avoid potential out-of-bounds read in
 pci_dev_for_each_resource()

Coverity complains that pointer in the pci_dev_for_each_resource() may be
wrong, i.e., might be used for the out-of-bounds read.

There is no actual issue right now because we have another check afterwards
and the out-of-bounds read is not being performed. In any case it's better
code with this fixed, hence the proposed change.

As Jonas pointed out "It probably makes the code slightly less performant
as res will now be checked for being not NULL (which will always be true),
but I doubt it will be significant (or in any hot paths)."

Fixes: 09cc90063240 ("PCI: Introduce pci_dev_for_each_resource()")
Reported-by: Bjorn Helgaas <bhelgaas@google.com>
Closes: https://lore.kernel.org/r/20230509182122.GA1259567@bhelgaas
Suggested-by: Jonas Gorski <jonas.gorski@gmail.com>
Link: https://lore.kernel.org/r/20231030114218.2752236-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc8679..4ebecc7896ef9 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2127,14 +2127,14 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma);
 	(pci_resource_end((dev), (bar)) ? 				\
 	 resource_size(pci_resource_n((dev), (bar))) : 0)
 
-#define __pci_dev_for_each_res0(dev, res, ...)				\
-	for (unsigned int __b = 0;					\
-	     res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES;	\
+#define __pci_dev_for_each_res0(dev, res, ...)				  \
+	for (unsigned int __b = 0;					  \
+	     __b < PCI_NUM_RESOURCES && (res = pci_resource_n(dev, __b)); \
 	     __b++)
 
-#define __pci_dev_for_each_res1(dev, res, __b)				\
-	for (__b = 0;							\
-	     res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES;	\
+#define __pci_dev_for_each_res1(dev, res, __b)				  \
+	for (__b = 0;							  \
+	     __b < PCI_NUM_RESOURCES && (res = pci_resource_n(dev, __b)); \
 	     __b++)
 
 #define pci_dev_for_each_resource(dev, res, ...)			\
-- 
GitLab


From 60e5f23dc5d68ec01e6dae8f4311230c7d2ccb8a Mon Sep 17 00:00:00 2001
From: Junhao He <hejunhao3@huawei.com>
Date: Tue, 14 Nov 2023 21:33:46 +0800
Subject: [PATCH 0230/4076] coresight: ultrasoc-smb: Use guards to cleanup

Use guards to reduce gotos and simplify control flow.

Signed-off-by: Junhao He <hejunhao3@huawei.com>
Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231114133346.30489-5-hejunhao3@huawei.com
---
 drivers/hwtracing/coresight/ultrasoc-smb.c | 70 +++++++---------------
 1 file changed, 22 insertions(+), 48 deletions(-)

diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c
index 2092433ff86e5..10e886455b8b7 100644
--- a/drivers/hwtracing/coresight/ultrasoc-smb.c
+++ b/drivers/hwtracing/coresight/ultrasoc-smb.c
@@ -97,27 +97,19 @@ static int smb_open(struct inode *inode, struct file *file)
 {
 	struct smb_drv_data *drvdata = container_of(file->private_data,
 					struct smb_drv_data, miscdev);
-	int ret = 0;
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 
-	if (drvdata->reading) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (drvdata->reading)
+		return -EBUSY;
 
-	if (atomic_read(&drvdata->csdev->refcnt)) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (atomic_read(&drvdata->csdev->refcnt))
+		return -EBUSY;
 
 	smb_update_data_size(drvdata);
-
 	drvdata->reading = true;
-out:
-	spin_unlock(&drvdata->spinlock);
 
-	return ret;
+	return 0;
 }
 
 static ssize_t smb_read(struct file *file, char __user *data, size_t len,
@@ -160,9 +152,8 @@ static int smb_release(struct inode *inode, struct file *file)
 	struct smb_drv_data *drvdata = container_of(file->private_data,
 					struct smb_drv_data, miscdev);
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 	drvdata->reading = false;
-	spin_unlock(&drvdata->spinlock);
 
 	return 0;
 }
@@ -255,19 +246,15 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode,
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
 	int ret = 0;
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 
 	/* Do nothing, the trace data is reading by other interface now */
-	if (drvdata->reading) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (drvdata->reading)
+		return -EBUSY;
 
 	/* Do nothing, the SMB is already enabled as other mode */
-	if (drvdata->mode != CS_MODE_DISABLED && drvdata->mode != mode) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (drvdata->mode != CS_MODE_DISABLED && drvdata->mode != mode)
+		return -EBUSY;
 
 	switch (mode) {
 	case CS_MODE_SYSFS:
@@ -281,13 +268,10 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode,
 	}
 
 	if (ret)
-		goto out;
+		return ret;
 
 	atomic_inc(&csdev->refcnt);
-
 	dev_dbg(&csdev->dev, "Ultrasoc SMB enabled\n");
-out:
-	spin_unlock(&drvdata->spinlock);
 
 	return ret;
 }
@@ -295,19 +279,14 @@ out:
 static int smb_disable(struct coresight_device *csdev)
 {
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
-	int ret = 0;
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 
-	if (drvdata->reading) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (drvdata->reading)
+		return -EBUSY;
 
-	if (atomic_dec_return(&csdev->refcnt)) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (atomic_dec_return(&csdev->refcnt))
+		return -EBUSY;
 
 	/* Complain if we (somehow) got out of sync */
 	WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED);
@@ -317,12 +296,9 @@ static int smb_disable(struct coresight_device *csdev)
 	/* Dissociate from the target process. */
 	drvdata->pid = -1;
 	drvdata->mode = CS_MODE_DISABLED;
-
 	dev_dbg(&csdev->dev, "Ultrasoc SMB disabled\n");
-out:
-	spin_unlock(&drvdata->spinlock);
 
-	return ret;
+	return 0;
 }
 
 static void *smb_alloc_buffer(struct coresight_device *csdev,
@@ -395,17 +371,17 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev,
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
 	struct smb_data_buffer *sdb = &drvdata->sdb;
 	struct cs_buffers *buf = sink_config;
-	unsigned long data_size = 0;
+	unsigned long data_size;
 	bool lost = false;
 
 	if (!buf)
 		return 0;
 
-	spin_lock(&drvdata->spinlock);
+	guard(spinlock)(&drvdata->spinlock);
 
 	/* Don't do anything if another tracer is using this sink. */
 	if (atomic_read(&csdev->refcnt) != 1)
-		goto out;
+		return 0;
 
 	smb_disable_hw(drvdata);
 	smb_update_data_size(drvdata);
@@ -424,8 +400,6 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev,
 	smb_sync_perf_buffer(drvdata, buf, handle->head);
 	if (!buf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
-out:
-	spin_unlock(&drvdata->spinlock);
 
 	return data_size;
 }
-- 
GitLab


From e9e60c82fe391d04db55a91c733df4a017c28b2f Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 21 Nov 2023 11:24:08 -0500
Subject: [PATCH 0231/4076] selftests/kvm: fix compilation on non-x86_64
 platforms

MEM_REGION_SLOT and MEM_REGION_GPA are not really needed in
test_invalid_memory_region_flags; the VM never runs and there are no
other slots, so it is okay to use slot 0 and place it at address
zero.  This fixes compilation on architectures that do not
define them.

Fixes: 5d74316466f4 ("KVM: selftests: Add a memory region subtest to validate invalid flags")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/guest_memfd_test.c       |  2 --
 tools/testing/selftests/kvm/set_memory_region_test.c | 12 ++++++------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index 318ba6ba8bd31..c78a98c1a915c 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -137,8 +137,6 @@ static void test_create_guest_memfd_invalid(struct kvm_vm *vm)
 	}
 
 	for (flag = 0; flag; flag <<= 1) {
-		uint64_t bit;
-
 		fd = __vm_create_guest_memfd(vm, page_size, flag);
 		TEST_ASSERT(fd == -1 && errno == EINVAL,
 			    "guest_memfd() with flag '0x%lx' should fail with EINVAL",
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 1efee1cfcff06..6637a0845acf0 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -349,8 +349,8 @@ static void test_invalid_memory_region_flags(void)
 		if ((supported_flags & BIT(i)) && !(v2_only_flags & BIT(i)))
 			continue;
 
-		r = __vm_set_user_memory_region(vm, MEM_REGION_SLOT, BIT(i),
-						MEM_REGION_GPA, MEM_REGION_SIZE, NULL);
+		r = __vm_set_user_memory_region(vm, 0, BIT(i),
+						0, MEM_REGION_SIZE, NULL);
 
 		TEST_ASSERT(r && errno == EINVAL,
 			    "KVM_SET_USER_MEMORY_REGION should have failed on v2 only flag 0x%lx", BIT(i));
@@ -358,16 +358,16 @@ static void test_invalid_memory_region_flags(void)
 		if (supported_flags & BIT(i))
 			continue;
 
-		r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, BIT(i),
-						 MEM_REGION_GPA, MEM_REGION_SIZE, NULL, 0, 0);
+		r = __vm_set_user_memory_region2(vm, 0, BIT(i),
+						 0, MEM_REGION_SIZE, NULL, 0, 0);
 		TEST_ASSERT(r && errno == EINVAL,
 			    "KVM_SET_USER_MEMORY_REGION2 should have failed on unsupported flag 0x%lx", BIT(i));
 	}
 
 	if (supported_flags & KVM_MEM_GUEST_MEMFD) {
-		r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT,
+		r = __vm_set_user_memory_region2(vm, 0,
 						 KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD,
-						 MEM_REGION_GPA, MEM_REGION_SIZE, NULL, 0, 0);
+						 0, MEM_REGION_SIZE, NULL, 0, 0);
 		TEST_ASSERT(r && errno == EINVAL,
 			    "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported");
 	}
-- 
GitLab


From f9cdf40ed66b7abc4fc03c5b47725583e5dc1072 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Sat, 11 Nov 2023 20:26:56 +0000
Subject: [PATCH 0232/4076] USB: misc: iowarrior: remove redundant assignment
 to variable io_res

The variable io_res is being assigned a value that is never read, it is
either being re-assigned a new value that is read later or it's not used
depending on the cases in the following switch statement. The assignment
is redundant and can be removed. Cleans up clang scan build warning:

drivers/usb/misc/iowarrior.c:504:2: warning: Value stored to 'io_res'
is never read [deadcode.DeadStores]

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://lore.kernel.org/r/20231111202656.339103-1-colin.i.king@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 1e3df27bab58f..6d28467ce3522 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -501,7 +501,6 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd,
 		dev->minor, cmd, arg);
 
 	retval = 0;
-	io_res = 0;
 	switch (cmd) {
 	case IOW_WRITE:
 		if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24 ||
-- 
GitLab


From b9a24821c7f7f8f8fbc9fc8539de96b60422d817 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 3 Nov 2023 18:14:29 +0100
Subject: [PATCH 0233/4076] USB: usbip: vudc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231103171428.3636570-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vudc.h      | 2 +-
 drivers/usb/usbip/vudc_dev.c  | 3 +--
 drivers/usb/usbip/vudc_main.c | 2 +-
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/usbip/vudc.h b/drivers/usb/usbip/vudc.h
index 1bd4bc005829b..faf61c9c6a989 100644
--- a/drivers/usb/usbip/vudc.h
+++ b/drivers/usb/usbip/vudc.h
@@ -173,6 +173,6 @@ struct vudc_device *alloc_vudc_device(int devid);
 void put_vudc_device(struct vudc_device *udc_dev);
 
 int vudc_probe(struct platform_device *pdev);
-int vudc_remove(struct platform_device *pdev);
+void vudc_remove(struct platform_device *pdev);
 
 #endif /* __USBIP_VUDC_H */
diff --git a/drivers/usb/usbip/vudc_dev.c b/drivers/usb/usbip/vudc_dev.c
index 44b04c54c0867..f11535020e35a 100644
--- a/drivers/usb/usbip/vudc_dev.c
+++ b/drivers/usb/usbip/vudc_dev.c
@@ -628,12 +628,11 @@ out:
 	return ret;
 }
 
-int vudc_remove(struct platform_device *pdev)
+void vudc_remove(struct platform_device *pdev)
 {
 	struct vudc *udc = platform_get_drvdata(pdev);
 
 	usb_del_gadget_udc(&udc->gadget);
 	cleanup_vudc_hw(udc);
 	kfree(udc);
-	return 0;
 }
diff --git a/drivers/usb/usbip/vudc_main.c b/drivers/usb/usbip/vudc_main.c
index 993e721cb840d..8bee553e48945 100644
--- a/drivers/usb/usbip/vudc_main.c
+++ b/drivers/usb/usbip/vudc_main.c
@@ -19,7 +19,7 @@ MODULE_PARM_DESC(num, "number of emulated controllers");
 
 static struct platform_driver vudc_driver = {
 	.probe		= vudc_probe,
-	.remove		= vudc_remove,
+	.remove_new	= vudc_remove,
 	.driver		= {
 		.name	= GADGET_NAME,
 		.dev_groups = vudc_groups,
-- 
GitLab


From cbd1b152519a581bfe14fb6b14ea6e57cca426c1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 20 Nov 2023 22:58:32 +0100
Subject: [PATCH 0234/4076] usb: gadget: at91_udc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

In the error path emit an error message replacing the (less useful)
message by the core. Apart from the improved error message there is no
change in behaviour.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231120215830.71071-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/at91_udc.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c
index 30ea4a9d5301f..e3bf17a98b380 100644
--- a/drivers/usb/gadget/udc/at91_udc.c
+++ b/drivers/usb/gadget/udc/at91_udc.c
@@ -1924,7 +1924,7 @@ err_unprepare_fclk:
 	return retval;
 }
 
-static int at91udc_remove(struct platform_device *pdev)
+static void at91udc_remove(struct platform_device *pdev)
 {
 	struct at91_udc *udc = platform_get_drvdata(pdev);
 	unsigned long	flags;
@@ -1932,8 +1932,11 @@ static int at91udc_remove(struct platform_device *pdev)
 	DBG("remove\n");
 
 	usb_del_gadget_udc(&udc->gadget);
-	if (udc->driver)
-		return -EBUSY;
+	if (udc->driver) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	spin_lock_irqsave(&udc->lock, flags);
 	pullup(udc, 0);
@@ -1943,8 +1946,6 @@ static int at91udc_remove(struct platform_device *pdev)
 	remove_debug_file(udc);
 	clk_unprepare(udc->fclk);
 	clk_unprepare(udc->iclk);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -2001,7 +2002,7 @@ static int at91udc_resume(struct platform_device *pdev)
 
 static struct platform_driver at91_udc_driver = {
 	.probe		= at91udc_probe,
-	.remove		= at91udc_remove,
+	.remove_new	= at91udc_remove,
 	.shutdown	= at91udc_shutdown,
 	.suspend	= at91udc_suspend,
 	.resume		= at91udc_resume,
-- 
GitLab


From 103081ef40b6738d3052a41f419705517a0f9436 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 20 Nov 2023 22:58:33 +0100
Subject: [PATCH 0235/4076] usb: gadget: fsl_udc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

In the error path emit an error message replacing the (less useful)
message by the core. Apart from the improved error message there is no
change in behaviour.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231120215830.71071-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/fsl_udc_core.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index 2693a10eb0c7c..535b6e79a198e 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -2532,15 +2532,18 @@ err_kfree:
 /* Driver removal function
  * Free resources and finish pending transactions
  */
-static int fsl_udc_remove(struct platform_device *pdev)
+static void fsl_udc_remove(struct platform_device *pdev)
 {
 	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev);
 
 	DECLARE_COMPLETION_ONSTACK(done);
 
-	if (!udc_controller)
-		return -ENODEV;
+	if (!udc_controller) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	udc_controller->done = &done;
 	usb_del_gadget_udc(&udc_controller->gadget);
@@ -2568,8 +2571,6 @@ static int fsl_udc_remove(struct platform_device *pdev)
 	 */
 	if (pdata->exit)
 		pdata->exit(pdev);
-
-	return 0;
 }
 
 /*-----------------------------------------------------------------
@@ -2667,7 +2668,7 @@ static const struct platform_device_id fsl_udc_devtype[] = {
 MODULE_DEVICE_TABLE(platform, fsl_udc_devtype);
 static struct platform_driver udc_driver = {
 	.probe		= fsl_udc_probe,
-	.remove		= fsl_udc_remove,
+	.remove_new	= fsl_udc_remove,
 	.id_table	= fsl_udc_devtype,
 	/* these suspend and resume are not usb suspend and resume */
 	.suspend	= fsl_udc_suspend,
-- 
GitLab


From c45b52f71c4b3b826c18d7a5c7a40c139e8312fb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 20 Nov 2023 22:58:34 +0100
Subject: [PATCH 0236/4076] usb: gadget: gr_udc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

In the error path emit an error message replacing the (less useful)
message by the core. Apart from the improved error message there is no
change in behaviour.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231120215830.71071-4-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/gr_udc.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index c6dfa7cccc11d..fb901be5dac1b 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -2089,15 +2089,18 @@ static void gr_ep_remove(struct gr_udc *dev, int num, int is_in)
 				  ep->tailbuf, ep->tailbuf_paddr);
 }
 
-static int gr_remove(struct platform_device *pdev)
+static void gr_remove(struct platform_device *pdev)
 {
 	struct gr_udc *dev = platform_get_drvdata(pdev);
 	int i;
 
 	if (dev->added)
 		usb_del_gadget_udc(&dev->gadget); /* Shuts everything down */
-	if (dev->driver)
-		return -EBUSY;
+	if (dev->driver) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	gr_dfs_delete(dev);
 	dma_pool_destroy(dev->desc_pool);
@@ -2110,8 +2113,6 @@ static int gr_remove(struct platform_device *pdev)
 		gr_ep_remove(dev, i, 0);
 	for (i = 0; i < dev->nepi; i++)
 		gr_ep_remove(dev, i, 1);
-
-	return 0;
 }
 static int gr_request_irq(struct gr_udc *dev, int irq)
 {
@@ -2248,7 +2249,7 @@ static struct platform_driver gr_driver = {
 		.of_match_table = gr_match,
 	},
 	.probe = gr_probe,
-	.remove = gr_remove,
+	.remove_new = gr_remove,
 };
 module_platform_driver(gr_driver);
 
-- 
GitLab


From 5d888fee4adefbc24bad8eb1091238090ac35e26 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 20 Nov 2023 22:58:35 +0100
Subject: [PATCH 0237/4076] usb: gadget: lpc32xx_udc: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

In the error path emit an error message replacing the (less useful)
message by the core. Apart from the improved error message there is no
change in behaviour.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231120215830.71071-5-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/lpc32xx_udc.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c
index a917cc9a32aba..d5f29f8fe4813 100644
--- a/drivers/usb/gadget/udc/lpc32xx_udc.c
+++ b/drivers/usb/gadget/udc/lpc32xx_udc.c
@@ -3174,13 +3174,16 @@ i2c_fail:
 	return retval;
 }
 
-static int lpc32xx_udc_remove(struct platform_device *pdev)
+static void lpc32xx_udc_remove(struct platform_device *pdev)
 {
 	struct lpc32xx_udc *udc = platform_get_drvdata(pdev);
 
 	usb_del_gadget_udc(&udc->gadget);
-	if (udc->driver)
-		return -EBUSY;
+	if (udc->driver) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	udc_clk_set(udc, 1);
 	udc_disable(udc);
@@ -3194,8 +3197,6 @@ static int lpc32xx_udc_remove(struct platform_device *pdev)
 			  udc->udca_v_base, udc->udca_p_base);
 
 	clk_disable_unprepare(udc->usb_slv_clk);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -3255,7 +3256,7 @@ MODULE_DEVICE_TABLE(of, lpc32xx_udc_of_match);
 
 static struct platform_driver lpc32xx_udc_driver = {
 	.probe		= lpc32xx_udc_probe,
-	.remove		= lpc32xx_udc_remove,
+	.remove_new	= lpc32xx_udc_remove,
 	.shutdown	= lpc32xx_udc_shutdown,
 	.suspend	= lpc32xx_udc_suspend,
 	.resume		= lpc32xx_udc_resume,
-- 
GitLab


From 725d1f1e338bfa0c133e38989d795484534fb9ac Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 20 Nov 2023 22:58:36 +0100
Subject: [PATCH 0238/4076] usb: gadget: pxa25x_udc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

In the error path emit an error message replacing the (less useful)
message by the core. Apart from the improved error message there is no
change in behaviour.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231120215830.71071-6-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/pxa25x_udc.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/gadget/udc/pxa25x_udc.c b/drivers/usb/gadget/udc/pxa25x_udc.c
index df0551ecc810c..1ac26cb49ecf9 100644
--- a/drivers/usb/gadget/udc/pxa25x_udc.c
+++ b/drivers/usb/gadget/udc/pxa25x_udc.c
@@ -2397,12 +2397,15 @@ static void pxa25x_udc_shutdown(struct platform_device *_dev)
 	pullup_off();
 }
 
-static int pxa25x_udc_remove(struct platform_device *pdev)
+static void pxa25x_udc_remove(struct platform_device *pdev)
 {
 	struct pxa25x_udc *dev = platform_get_drvdata(pdev);
 
-	if (dev->driver)
-		return -EBUSY;
+	if (dev->driver) {
+		dev_err(&pdev->dev,
+			"Driver still in use but removing anyhow\n");
+		return;
+	}
 
 	usb_del_gadget_udc(&dev->gadget);
 	dev->pullup = 0;
@@ -2414,7 +2417,6 @@ static int pxa25x_udc_remove(struct platform_device *pdev)
 		dev->transceiver = NULL;
 
 	the_controller = NULL;
-	return 0;
 }
 
 /*-------------------------------------------------------------------------*/
@@ -2472,7 +2474,7 @@ static int pxa25x_udc_resume(struct platform_device *dev)
 static struct platform_driver udc_driver = {
 	.shutdown	= pxa25x_udc_shutdown,
 	.probe		= pxa25x_udc_probe,
-	.remove		= pxa25x_udc_remove,
+	.remove_new	= pxa25x_udc_remove,
 	.suspend	= pxa25x_udc_suspend,
 	.resume		= pxa25x_udc_resume,
 	.driver		= {
-- 
GitLab


From 2d1803ada2e021b9333b8a784c55fe828ab2b985 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 16 Nov 2023 11:14:52 -0800
Subject: [PATCH 0239/4076] usb: gadget: f_midi: Replace strlcpy() with
 strscpy()

strlcpy() reads the entire source buffer first. This read may exceed
the destination size limit. This is both inefficient and can lead
to linear read overflows if a source string is not NUL-terminated[1].
Additionally, it returns the size of the source string, not the
resulting size of the destination string. In an effort to remove strlcpy()
completely[2], replace strlcpy() here with strscpy().

In the unlikely (impossible?) case where opts->id was larger than
PAGE_SIZE, this will now correctly report truncation errors.

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [1]
Link: https://github.com/KSPP/linux/issues/89 [2]
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Will McVicker <willmcvicker@google.com>
Cc: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Cc: Peter Chen <peter.chen@nxp.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Zhang Qilong <zhangqilong3@huawei.com>
Cc: Linyu Yuan <quic_linyyuan@quicinc.com>
Cc: John Keeping <john@keeping.me.uk>
Cc: Azeem Shaikh <azeemshaikh38@gmail.com>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20231116191452.work.902-kees@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_midi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index 5335845d697b5..20c6fbd94f32d 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -1177,11 +1177,11 @@ F_MIDI_OPT(out_ports, true, MAX_PORTS);
 static ssize_t f_midi_opts_id_show(struct config_item *item, char *page)
 {
 	struct f_midi_opts *opts = to_f_midi_opts(item);
-	int result;
+	ssize_t result;
 
 	mutex_lock(&opts->lock);
 	if (opts->id) {
-		result = strlcpy(page, opts->id, PAGE_SIZE);
+		result = strscpy(page, opts->id, PAGE_SIZE);
 	} else {
 		page[0] = 0;
 		result = 0;
-- 
GitLab


From d990e227741692079872a8336d961ef4ab9e8aaf Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Wed, 15 Nov 2023 21:14:07 +0000
Subject: [PATCH 0240/4076] dt-bindings: usb: renesas,usbhs: Document RZ/Five
 SoC

The USBHS IP block on the RZ/Five SoC is identical to one found on the
RZ/G2UL SoC. "renesas,usbhs-r9a07g043" compatible string will be used on
the RZ/Five SoC so to make this clear and to keep this file consistent,
update the comment to include RZ/Five SoC.

No driver changes are required as generic compatible string
"renesas,rza2-usbhs" will be used as a fallback on RZ/Five SoC.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/20231115211407.32067-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/renesas,usbhs.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
index bad55dfb2fa03..40ada78f23288 100644
--- a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
@@ -19,7 +19,7 @@ properties:
       - items:
           - enum:
               - renesas,usbhs-r7s9210   # RZ/A2
-              - renesas,usbhs-r9a07g043 # RZ/G2UL
+              - renesas,usbhs-r9a07g043 # RZ/G2UL and RZ/Five
               - renesas,usbhs-r9a07g044 # RZ/G2{L,LC}
               - renesas,usbhs-r9a07g054 # RZ/V2L
           - const: renesas,rza2-usbhs
-- 
GitLab


From 6437760accfbaf1160342adeaea1a73dcd278799 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Thu, 2 Nov 2023 07:51:13 +0000
Subject: [PATCH 0241/4076] usb: misc: eud: Add IRQ check for
 platform_get_irq()

The function eud_probe() should check the return value of
platform_get_irq() for errors so as to not pass a negative value to
the devm_request_threaded_irq().

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Caleb Connolly <caleb.connolly@linaro.org>
Link: https://lore.kernel.org/r/20231102075113.1043358-1-nichen@iscas.ac.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/qcom_eud.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/misc/qcom_eud.c b/drivers/usb/misc/qcom_eud.c
index 7f371ea1248c3..26e9b8749d8ab 100644
--- a/drivers/usb/misc/qcom_eud.c
+++ b/drivers/usb/misc/qcom_eud.c
@@ -205,6 +205,9 @@ static int eud_probe(struct platform_device *pdev)
 		return PTR_ERR(chip->mode_mgr);
 
 	chip->irq = platform_get_irq(pdev, 0);
+	if (chip->irq < 0)
+		return chip->irq;
+
 	ret = devm_request_threaded_irq(&pdev->dev, chip->irq, handle_eud_irq,
 			handle_eud_irq_thread, IRQF_ONESHOT, NULL, chip);
 	if (ret)
-- 
GitLab


From a776452debdcad6d6e6f8f89fb26496038c86074 Mon Sep 17 00:00:00 2001
From: Piyush Mehta <piyush.mehta@amd.com>
Date: Thu, 2 Nov 2023 12:36:03 +0530
Subject: [PATCH 0242/4076] usb: chipidea: udc: Add revision check of
 2.20[CI_REVISION_22]

Issue: Adding a dTD to a Primed Endpoint May Not Get Recognized with
revision 2.20a.

There is an issue with the add dTD tripwire semaphore (ATDTW bit in
USBCMD register) that can cause the controller to ignore a dTD that is
added to a primed endpoint. When this happens, the software can read
the tripwire bit and the status bit at '1' even though the endpoint is
unprimed.
This issue observed with the Windows host machine.

Workaround:
The software must implement a periodic cycle, and check for each dTD
pending on execution (Active = 1), if the endpoint is primed. It can do
this by reading the corresponding bits in the ENDPTPRIME and ENDPTSTAT
registers. If these bits are read at 0, the software needs to re-prime
the endpoint by writing 1 to the corresponding bit in the ENDPTPRIME
register.

Added conditional revision check of 2.20[CI_REVISION_22] along with 2.40.

Signed-off-by: Piyush Mehta <piyush.mehta@amd.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/20231102070603.777313-1-piyush.mehta@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/udc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 0b7bd3c643c3a..2d7f616270c17 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -688,7 +688,8 @@ static int _hardware_dequeue(struct ci_hw_ep *hwep, struct ci_hw_req *hwreq)
 		if ((TD_STATUS_ACTIVE & tmptoken) != 0) {
 			int n = hw_ep_bit(hwep->num, hwep->dir);
 
-			if (ci->rev == CI_REVISION_24)
+			if (ci->rev == CI_REVISION_24 ||
+			    ci->rev == CI_REVISION_22)
 				if (!hw_read(ci, OP_ENDPTSTAT, BIT(n)))
 					reprime_dtd(ci, hwep, node);
 			hwreq->req.status = -EALREADY;
-- 
GitLab


From 7836be3b100cfc6db3db7ddeb985254bfe1775e4 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 27 Oct 2023 14:39:19 -0400
Subject: [PATCH 0243/4076] usb: cdns3: skip set TRB_IOC when usb_request:
 no_interrupt is true

No completion irq is needed if no_interrupt is true. Needn't set TRB_IOC
at this case.

Check usb_request: no_interrupt and set/skip TRB_IOC in
cdns3_ep_run_transfer().

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/20231027183919.664271-1-Frank.Li@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-gadget.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 11a5b3437c32d..15463b7cddd23 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -1126,6 +1126,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	u16 total_tdl = 0;
 	struct scatterlist *s = NULL;
 	bool sg_supported = !!(request->num_mapped_sgs);
+	u32 ioc = request->no_interrupt ? 0 : TRB_IOC;
 
 	if (priv_ep->type == USB_ENDPOINT_XFER_ISOC)
 		num_trb = priv_ep->interval;
@@ -1235,11 +1236,11 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 			control |= pcs;
 
 		if (priv_ep->type == USB_ENDPOINT_XFER_ISOC  && !priv_ep->dir) {
-			control |= TRB_IOC | TRB_ISP;
+			control |= ioc | TRB_ISP;
 		} else {
 			/* for last element in TD or in SG list */
 			if (sg_iter == (num_trb - 1) && sg_iter != 0)
-				control |= pcs | TRB_IOC | TRB_ISP;
+				control |= pcs | ioc | TRB_ISP;
 		}
 
 		if (sg_iter)
@@ -1270,7 +1271,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	priv_req->num_of_trb = num_trb;
 
 	if (sg_iter == 1)
-		trb->control |= cpu_to_le32(TRB_IOC | TRB_ISP);
+		trb->control |= cpu_to_le32(ioc | TRB_ISP);
 
 	if (priv_dev->dev_ver < DEV_VER_V2 &&
 	    (priv_ep->flags & EP_TDLCHK_EN)) {
-- 
GitLab


From 68a1317412e19cdbc0cbbb9474013adfa1aa986f Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@gmail.com>
Date: Mon, 30 Oct 2023 23:31:58 +0100
Subject: [PATCH 0244/4076] usb: raw-gadget: update documentation

A recent patch added reporting of more event types to Raw Gadget.

Update the documentation to reflect that this feature has been
implemented.

Signed-off-by: Andrey Konovalov <andreyknvl@gmail.com>
Link: https://lore.kernel.org/r/20231030223158.36636-1-andrey.konovalov@linux.dev
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/usb/raw-gadget.rst | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/Documentation/usb/raw-gadget.rst b/Documentation/usb/raw-gadget.rst
index 818a1648b3872..59b2132b584d7 100644
--- a/Documentation/usb/raw-gadget.rst
+++ b/Documentation/usb/raw-gadget.rst
@@ -81,9 +81,6 @@ feature must be kept in the implementation.
 Potential future improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-- Report more events (suspend, resume, etc.) through
-  ``USB_RAW_IOCTL_EVENT_FETCH``.
-
 - Support ``O_NONBLOCK`` I/O. This would be another mode of operation, where
   Raw Gadget would not wait until the completion of each USB request.
 
-- 
GitLab


From 5389b5d74efb6da22b01cdd91105bffc5f71dbdc Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:41:59 +0100
Subject: [PATCH 0245/4076] dt-bindings: usb: qcom,dwc3: document the SM8560
 SuperSpeed DWC3 USB controller

Document the SuperSpeed DWC3 USB controller on the SM8650 Platform.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-bindings-dwc3-v2-1-60c0824fb835@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/qcom,dwc3.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index e889158ca2057..ccce57e4290d4 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -46,6 +46,7 @@ properties:
           - qcom,sm8350-dwc3
           - qcom,sm8450-dwc3
           - qcom,sm8550-dwc3
+          - qcom,sm8650-dwc3
       - const: qcom,dwc3
 
   reg:
@@ -318,6 +319,7 @@ allOf:
               - qcom,sm8250-dwc3
               - qcom,sm8450-dwc3
               - qcom,sm8550-dwc3
+              - qcom,sm8650-dwc3
     then:
       properties:
         clocks:
@@ -377,6 +379,7 @@ allOf:
               - qcom,sm8350-dwc3
               - qcom,sm8450-dwc3
               - qcom,sm8550-dwc3
+              - qcom,sm8650-dwc3
     then:
       properties:
         interrupts:
-- 
GitLab


From 772f88907d92484232f60c51c5c5e792a86d37ac Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:28:53 +0100
Subject: [PATCH 0246/4076] interconnect: qcom: Make qnoc_remove return void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Several interconnect/qcom drivers use qnoc_remove() as remove callback.
Make this function return void (instead of unconditionally zero) and
adapt the drivers using this function accordingly.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231031222851.3126434-12-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/icc-rpm.c | 4 +---
 drivers/interconnect/qcom/icc-rpm.h | 2 +-
 drivers/interconnect/qcom/msm8916.c | 2 +-
 drivers/interconnect/qcom/msm8939.c | 2 +-
 drivers/interconnect/qcom/msm8996.c | 2 +-
 drivers/interconnect/qcom/qcm2290.c | 2 +-
 drivers/interconnect/qcom/qcs404.c  | 2 +-
 drivers/interconnect/qcom/sdm660.c  | 2 +-
 8 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c
index 628e651c555cb..fb54e78f8fd74 100644
--- a/drivers/interconnect/qcom/icc-rpm.c
+++ b/drivers/interconnect/qcom/icc-rpm.c
@@ -627,14 +627,12 @@ err_disable_unprepare_clk:
 }
 EXPORT_SYMBOL(qnoc_probe);
 
-int qnoc_remove(struct platform_device *pdev)
+void qnoc_remove(struct platform_device *pdev)
 {
 	struct qcom_icc_provider *qp = platform_get_drvdata(pdev);
 
 	icc_provider_deregister(&qp->provider);
 	icc_nodes_remove(&qp->provider);
 	clk_disable_unprepare(qp->bus_clk);
-
-	return 0;
 }
 EXPORT_SYMBOL(qnoc_remove);
diff --git a/drivers/interconnect/qcom/icc-rpm.h b/drivers/interconnect/qcom/icc-rpm.h
index a13768cfd2311..f4883d43eae4d 100644
--- a/drivers/interconnect/qcom/icc-rpm.h
+++ b/drivers/interconnect/qcom/icc-rpm.h
@@ -161,7 +161,7 @@ extern const struct rpm_clk_resource aggre1_branch_clk;
 extern const struct rpm_clk_resource aggre2_branch_clk;
 
 int qnoc_probe(struct platform_device *pdev);
-int qnoc_remove(struct platform_device *pdev);
+void qnoc_remove(struct platform_device *pdev);
 
 bool qcom_icc_rpm_smd_available(void);
 int qcom_icc_rpm_smd_send(int ctx, int rsc_type, int id, u32 val);
diff --git a/drivers/interconnect/qcom/msm8916.c b/drivers/interconnect/qcom/msm8916.c
index 35148880b3e87..499b1a9ac413b 100644
--- a/drivers/interconnect/qcom/msm8916.c
+++ b/drivers/interconnect/qcom/msm8916.c
@@ -1344,7 +1344,7 @@ MODULE_DEVICE_TABLE(of, msm8916_noc_of_match);
 
 static struct platform_driver msm8916_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-msm8916",
 		.of_match_table = msm8916_noc_of_match,
diff --git a/drivers/interconnect/qcom/msm8939.c b/drivers/interconnect/qcom/msm8939.c
index b52c5ac1175c3..8ff2c23b1ca0d 100644
--- a/drivers/interconnect/qcom/msm8939.c
+++ b/drivers/interconnect/qcom/msm8939.c
@@ -1421,7 +1421,7 @@ MODULE_DEVICE_TABLE(of, msm8939_noc_of_match);
 
 static struct platform_driver msm8939_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-msm8939",
 		.of_match_table = msm8939_noc_of_match,
diff --git a/drivers/interconnect/qcom/msm8996.c b/drivers/interconnect/qcom/msm8996.c
index b73566c9b21f9..788131400cd13 100644
--- a/drivers/interconnect/qcom/msm8996.c
+++ b/drivers/interconnect/qcom/msm8996.c
@@ -2108,7 +2108,7 @@ MODULE_DEVICE_TABLE(of, qnoc_of_match);
 
 static struct platform_driver qnoc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-msm8996",
 		.of_match_table = qnoc_of_match,
diff --git a/drivers/interconnect/qcom/qcm2290.c b/drivers/interconnect/qcom/qcm2290.c
index b88cf9a022e03..96735800b13c0 100644
--- a/drivers/interconnect/qcom/qcm2290.c
+++ b/drivers/interconnect/qcom/qcm2290.c
@@ -1367,7 +1367,7 @@ MODULE_DEVICE_TABLE(of, qcm2290_noc_of_match);
 
 static struct platform_driver qcm2290_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-qcm2290",
 		.of_match_table = qcm2290_noc_of_match,
diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c
index 9fa1da70c843a..11b49a89c03d1 100644
--- a/drivers/interconnect/qcom/qcs404.c
+++ b/drivers/interconnect/qcom/qcs404.c
@@ -1083,7 +1083,7 @@ MODULE_DEVICE_TABLE(of, qcs404_noc_of_match);
 
 static struct platform_driver qcs404_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-qcs404",
 		.of_match_table = qcs404_noc_of_match,
diff --git a/drivers/interconnect/qcom/sdm660.c b/drivers/interconnect/qcom/sdm660.c
index 7392bebba3344..ab91de446da88 100644
--- a/drivers/interconnect/qcom/sdm660.c
+++ b/drivers/interconnect/qcom/sdm660.c
@@ -1714,7 +1714,7 @@ MODULE_DEVICE_TABLE(of, sdm660_noc_of_match);
 
 static struct platform_driver sdm660_noc_driver = {
 	.probe = qnoc_probe,
-	.remove = qnoc_remove,
+	.remove_new = qnoc_remove,
 	.driver = {
 		.name = "qnoc-sdm660",
 		.of_match_table = sdm660_noc_of_match,
-- 
GitLab


From 57f6b2caf1c610565067dc47d8519b68bd1f2ce6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:28:54 +0100
Subject: [PATCH 0247/4076] interconnect: imx8mm: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231031222851.3126434-13-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/imx/imx8mm.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/interconnect/imx/imx8mm.c b/drivers/interconnect/imx/imx8mm.c
index b43325364aa31..8c40f41822634 100644
--- a/drivers/interconnect/imx/imx8mm.c
+++ b/drivers/interconnect/imx/imx8mm.c
@@ -86,16 +86,9 @@ static int imx8mm_icc_probe(struct platform_device *pdev)
 	return imx_icc_register(pdev, nodes, ARRAY_SIZE(nodes), NULL);
 }
 
-static int imx8mm_icc_remove(struct platform_device *pdev)
-{
-	imx_icc_unregister(pdev);
-
-	return 0;
-}
-
 static struct platform_driver imx8mm_icc_driver = {
 	.probe = imx8mm_icc_probe,
-	.remove = imx8mm_icc_remove,
+	.remove_new = imx_icc_unregister,
 	.driver = {
 		.name = "imx8mm-interconnect",
 	},
-- 
GitLab


From 1841d085e3939625f62c7212540cad99ef38e7d4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:28:55 +0100
Subject: [PATCH 0248/4076] interconnect: imx8mn: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231031222851.3126434-14-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/imx/imx8mn.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/interconnect/imx/imx8mn.c b/drivers/interconnect/imx/imx8mn.c
index 8ce6d8e4bf5e9..fa3d4f97dfa4a 100644
--- a/drivers/interconnect/imx/imx8mn.c
+++ b/drivers/interconnect/imx/imx8mn.c
@@ -75,16 +75,9 @@ static int imx8mn_icc_probe(struct platform_device *pdev)
 	return imx_icc_register(pdev, nodes, ARRAY_SIZE(nodes), NULL);
 }
 
-static int imx8mn_icc_remove(struct platform_device *pdev)
-{
-	imx_icc_unregister(pdev);
-
-	return 0;
-}
-
 static struct platform_driver imx8mn_icc_driver = {
 	.probe = imx8mn_icc_probe,
-	.remove = imx8mn_icc_remove,
+	.remove_new = imx_icc_unregister,
 	.driver = {
 		.name = "imx8mn-interconnect",
 	},
-- 
GitLab


From 12384b76f0c247c6916060b31ec462802e99e9cb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:28:56 +0100
Subject: [PATCH 0249/4076] interconnect: imx8mp: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231031222851.3126434-15-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/imx/imx8mp.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/interconnect/imx/imx8mp.c b/drivers/interconnect/imx/imx8mp.c
index a66ae3638b18a..d218bb47757a2 100644
--- a/drivers/interconnect/imx/imx8mp.c
+++ b/drivers/interconnect/imx/imx8mp.c
@@ -239,16 +239,9 @@ static int imx8mp_icc_probe(struct platform_device *pdev)
 	return imx_icc_register(pdev, nodes, ARRAY_SIZE(nodes), noc_setting_nodes);
 }
 
-static int imx8mp_icc_remove(struct platform_device *pdev)
-{
-	imx_icc_unregister(pdev);
-
-	return 0;
-}
-
 static struct platform_driver imx8mp_icc_driver = {
 	.probe = imx8mp_icc_probe,
-	.remove = imx8mp_icc_remove,
+	.remove_new = imx_icc_unregister,
 	.driver = {
 		.name = "imx8mp-interconnect",
 	},
-- 
GitLab


From 653959e373610817475519f6b519a80547f6381e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:28:57 +0100
Subject: [PATCH 0250/4076] interconnect: imx8mq: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231031222851.3126434-16-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/imx/imx8mq.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/interconnect/imx/imx8mq.c b/drivers/interconnect/imx/imx8mq.c
index b6fb71305c99b..8bbd672b346e1 100644
--- a/drivers/interconnect/imx/imx8mq.c
+++ b/drivers/interconnect/imx/imx8mq.c
@@ -85,16 +85,9 @@ static int imx8mq_icc_probe(struct platform_device *pdev)
 	return imx_icc_register(pdev, nodes, ARRAY_SIZE(nodes), NULL);
 }
 
-static int imx8mq_icc_remove(struct platform_device *pdev)
-{
-	imx_icc_unregister(pdev);
-
-	return 0;
-}
-
 static struct platform_driver imx8mq_icc_driver = {
 	.probe = imx8mq_icc_probe,
-	.remove = imx8mq_icc_remove,
+	.remove_new = imx_icc_unregister,
 	.driver = {
 		.name = "imx8mq-interconnect",
 		.sync_state = icc_sync_state,
-- 
GitLab


From 9d960441db354033c944345efaf33765e3122c31 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:28:58 +0100
Subject: [PATCH 0251/4076] interconnect: qcom/msm8974: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231031222851.3126434-17-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/msm8974.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/interconnect/qcom/msm8974.c b/drivers/interconnect/qcom/msm8974.c
index 21f6c852141e3..241076b5f36b4 100644
--- a/drivers/interconnect/qcom/msm8974.c
+++ b/drivers/interconnect/qcom/msm8974.c
@@ -740,15 +740,13 @@ err_remove_nodes:
 	return ret;
 }
 
-static int msm8974_icc_remove(struct platform_device *pdev)
+static void msm8974_icc_remove(struct platform_device *pdev)
 {
 	struct msm8974_icc_provider *qp = platform_get_drvdata(pdev);
 
 	icc_provider_deregister(&qp->provider);
 	icc_nodes_remove(&qp->provider);
 	clk_bulk_disable_unprepare(qp->num_clks, qp->bus_clks);
-
-	return 0;
 }
 
 static const struct of_device_id msm8974_noc_of_match[] = {
@@ -764,7 +762,7 @@ MODULE_DEVICE_TABLE(of, msm8974_noc_of_match);
 
 static struct platform_driver msm8974_noc_driver = {
 	.probe = msm8974_icc_probe,
-	.remove = msm8974_icc_remove,
+	.remove_new = msm8974_icc_remove,
 	.driver = {
 		.name = "qnoc-msm8974",
 		.of_match_table = msm8974_noc_of_match,
-- 
GitLab


From 237e1edaec6b4ba9c63f23aa2d7b6a4fa146cd0a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:28:59 +0100
Subject: [PATCH 0252/4076] interconnect: qcom/osm-l3: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231031222851.3126434-18-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/osm-l3.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c
index e97478bbc2825..61a8695a9adc7 100644
--- a/drivers/interconnect/qcom/osm-l3.c
+++ b/drivers/interconnect/qcom/osm-l3.c
@@ -148,14 +148,12 @@ static int qcom_osm_l3_set(struct icc_node *src, struct icc_node *dst)
 	return 0;
 }
 
-static int qcom_osm_l3_remove(struct platform_device *pdev)
+static void qcom_osm_l3_remove(struct platform_device *pdev)
 {
 	struct qcom_osm_l3_icc_provider *qp = platform_get_drvdata(pdev);
 
 	icc_provider_deregister(&qp->provider);
 	icc_nodes_remove(&qp->provider);
-
-	return 0;
 }
 
 static int qcom_osm_l3_probe(struct platform_device *pdev)
@@ -292,7 +290,7 @@ MODULE_DEVICE_TABLE(of, osm_l3_of_match);
 
 static struct platform_driver osm_l3_driver = {
 	.probe = qcom_osm_l3_probe,
-	.remove = qcom_osm_l3_remove,
+	.remove_new = qcom_osm_l3_remove,
 	.driver = {
 		.name = "osm-l3",
 		.of_match_table = osm_l3_of_match,
-- 
GitLab


From c9ead908d72f32e026253fae648d0d94a713047d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:29:00 +0100
Subject: [PATCH 0253/4076] interconnect: qcom/smd-rpm: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231031222851.3126434-19-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/smd-rpm.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/interconnect/qcom/smd-rpm.c b/drivers/interconnect/qcom/smd-rpm.c
index 16a145a3c9144..3816bfb4e2f39 100644
--- a/drivers/interconnect/qcom/smd-rpm.c
+++ b/drivers/interconnect/qcom/smd-rpm.c
@@ -63,11 +63,9 @@ int qcom_icc_rpm_set_bus_rate(const struct rpm_clk_resource *clk, int ctx, u32 r
 }
 EXPORT_SYMBOL_GPL(qcom_icc_rpm_set_bus_rate);
 
-static int qcom_icc_rpm_smd_remove(struct platform_device *pdev)
+static void qcom_icc_rpm_smd_remove(struct platform_device *pdev)
 {
 	icc_smd_rpm = NULL;
-
-	return 0;
 }
 
 static int qcom_icc_rpm_smd_probe(struct platform_device *pdev)
@@ -87,7 +85,7 @@ static struct platform_driver qcom_interconnect_rpm_smd_driver = {
 		.name		= "icc_smd_rpm",
 	},
 	.probe = qcom_icc_rpm_smd_probe,
-	.remove = qcom_icc_rpm_smd_remove,
+	.remove_new = qcom_icc_rpm_smd_remove,
 };
 module_platform_driver(qcom_interconnect_rpm_smd_driver);
 MODULE_AUTHOR("Georgi Djakov <georgi.djakov@linaro.org>");
-- 
GitLab


From b73326b60fddf2ea134c2d9d621f441fa2cee532 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 31 Oct 2023 23:29:01 +0100
Subject: [PATCH 0254/4076] interconnect: exynos: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231031222851.3126434-20-u.kleine-koenig@pengutronix.de
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/samsung/exynos.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/interconnect/samsung/exynos.c b/drivers/interconnect/samsung/exynos.c
index ebf09bbf725bd..1ba14cb45d5a2 100644
--- a/drivers/interconnect/samsung/exynos.c
+++ b/drivers/interconnect/samsung/exynos.c
@@ -93,14 +93,12 @@ static struct icc_node *exynos_generic_icc_xlate(struct of_phandle_args *spec,
 	return priv->node;
 }
 
-static int exynos_generic_icc_remove(struct platform_device *pdev)
+static void exynos_generic_icc_remove(struct platform_device *pdev)
 {
 	struct exynos_icc_priv *priv = platform_get_drvdata(pdev);
 
 	icc_provider_deregister(&priv->provider);
 	icc_nodes_remove(&priv->provider);
-
-	return 0;
 }
 
 static int exynos_generic_icc_probe(struct platform_device *pdev)
@@ -182,7 +180,7 @@ static struct platform_driver exynos_generic_icc_driver = {
 		.sync_state = icc_sync_state,
 	},
 	.probe = exynos_generic_icc_probe,
-	.remove = exynos_generic_icc_remove,
+	.remove_new = exynos_generic_icc_remove,
 };
 module_platform_driver(exynos_generic_icc_driver);
 
-- 
GitLab


From e58e519b80ba79cd73abb1d631d429b7322ac9cb Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Wed, 22 Nov 2023 16:24:01 +0530
Subject: [PATCH 0255/4076] pinctrl: intel: use the correct _PM_OPS() export
 macro

Since we don't have runtime PM handles here, we should be using
EXPORT_NS_GPL_DEV_SLEEP_PM_OPS() macro, so that the compiler can
discard it in case CONFIG_PM_SLEEP=n.

Fixes: b10a74b5c0c1 ("pinctrl: intel: Provide Intel pin control wide PM ops structure")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 2367c2747a83f..d6f29e6faab79 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1879,7 +1879,7 @@ static int intel_pinctrl_resume_noirq(struct device *dev)
 	return 0;
 }
 
-EXPORT_NS_GPL_DEV_PM_OPS(intel_pinctrl_pm_ops, PINCTRL_INTEL) = {
+EXPORT_NS_GPL_DEV_SLEEP_PM_OPS(intel_pinctrl_pm_ops, PINCTRL_INTEL) = {
 	NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend_noirq, intel_pinctrl_resume_noirq)
 };
 
-- 
GitLab


From df25461119d987b8c81d232cfe4411e91dcabe66 Mon Sep 17 00:00:00 2001
From: Daniel Stodden <dns@arista.com>
Date: Tue, 21 Nov 2023 20:23:16 -0800
Subject: [PATCH 0256/4076] PCI: switchtec: Fix stdev_release() crash after
 surprise hot remove

A PCI device hot removal may occur while stdev->cdev is held open. The call
to stdev_release() then happens during close or exit, at a point way past
switchtec_pci_remove(). Otherwise the last ref would vanish with the
trailing put_device(), just before return.

At that later point in time, the devm cleanup has already removed the
stdev->mmio_mrpc mapping. Also, the stdev->pdev reference was not a counted
one. Therefore, in DMA mode, the iowrite32() in stdev_release() will cause
a fatal page fault, and the subsequent dma_free_coherent(), if reached,
would pass a stale &stdev->pdev->dev pointer.

Fix by moving MRPC DMA shutdown into switchtec_pci_remove(), after
stdev_kill(). Counting the stdev->pdev ref is now optional, but may prevent
future accidents.

Reproducible via the script at
https://lore.kernel.org/r/20231113212150.96410-1-dns@arista.com

Link: https://lore.kernel.org/r/20231122042316.91208-2-dns@arista.com
Signed-off-by: Daniel Stodden <dns@arista.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Dmitry Safonov <dima@arista.com>
---
 drivers/pci/switch/switchtec.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 5b921387eca61..1804794d0e686 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -1308,13 +1308,6 @@ static void stdev_release(struct device *dev)
 {
 	struct switchtec_dev *stdev = to_stdev(dev);
 
-	if (stdev->dma_mrpc) {
-		iowrite32(0, &stdev->mmio_mrpc->dma_en);
-		flush_wc_buf(stdev);
-		writeq(0, &stdev->mmio_mrpc->dma_addr);
-		dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc),
-				stdev->dma_mrpc, stdev->dma_mrpc_dma_addr);
-	}
 	kfree(stdev);
 }
 
@@ -1358,7 +1351,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev)
 		return ERR_PTR(-ENOMEM);
 
 	stdev->alive = true;
-	stdev->pdev = pdev;
+	stdev->pdev = pci_dev_get(pdev);
 	INIT_LIST_HEAD(&stdev->mrpc_queue);
 	mutex_init(&stdev->mrpc_mutex);
 	stdev->mrpc_busy = 0;
@@ -1391,6 +1384,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev)
 	return stdev;
 
 err_put:
+	pci_dev_put(stdev->pdev);
 	put_device(&stdev->dev);
 	return ERR_PTR(rc);
 }
@@ -1644,6 +1638,18 @@ static int switchtec_init_pci(struct switchtec_dev *stdev,
 	return 0;
 }
 
+static void switchtec_exit_pci(struct switchtec_dev *stdev)
+{
+	if (stdev->dma_mrpc) {
+		iowrite32(0, &stdev->mmio_mrpc->dma_en);
+		flush_wc_buf(stdev);
+		writeq(0, &stdev->mmio_mrpc->dma_addr);
+		dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc),
+				  stdev->dma_mrpc, stdev->dma_mrpc_dma_addr);
+		stdev->dma_mrpc = NULL;
+	}
+}
+
 static int switchtec_pci_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
@@ -1703,6 +1709,9 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 	ida_free(&switchtec_minor_ida, MINOR(stdev->dev.devt));
 	dev_info(&stdev->dev, "unregistered.\n");
 	stdev_kill(stdev);
+	switchtec_exit_pci(stdev);
+	pci_dev_put(stdev->pdev);
+	stdev->pdev = NULL;
 	put_device(&stdev->dev);
 }
 
-- 
GitLab


From 1080b5c0c1a62a36dc29eb6e4dfedf7c9eaf8679 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Fri, 17 Nov 2023 18:16:28 +0100
Subject: [PATCH 0257/4076] of: fix recursion typo in kernel doc

Fix a typo in the kernel doc for the of_platform_depopulate() functions,
which remove children "recursively".

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20231117171628.20139-1-johan+linaro@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/platform.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 126d265aa7d86..2293059758d1d 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -668,7 +668,7 @@ EXPORT_SYMBOL_GPL(of_platform_device_destroy);
  * @parent: device which children will be removed
  *
  * Complementary to of_platform_populate(), this function removes children
- * of the given device (and, recurrently, their children) that have been
+ * of the given device (and, recursively, their children) that have been
  * created from their respective device tree nodes (and only those,
  * leaving others - eg. manually created - unharmed).
  */
@@ -737,7 +737,7 @@ static int devm_of_platform_match(struct device *dev, void *res, void *data)
  * @dev: device that requested to depopulate from device tree data
  *
  * Complementary to devm_of_platform_populate(), this function removes children
- * of the given device (and, recurrently, their children) that have been
+ * of the given device (and, recursively, their children) that have been
  * created from their respective device tree nodes (and only those,
  * leaving others - eg. manually created - unharmed).
  */
-- 
GitLab


From 69dcbbd80421a5d8230c178e01869f8e2edb2317 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 10 Oct 2023 09:52:19 -0700
Subject: [PATCH 0258/4076] locktorture: Increase Hamming distance between
 call_rcu_chain and rcu_call_chains

One letter difference is really not enough, so this commit changes
call_rcu_chain to call_rcu_chain_list.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 kernel/locking/locktorture.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 69d3cd2cfc3ba..415d81e6ce707 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -124,7 +124,7 @@ struct call_rcu_chain {
 	struct rcu_head crc_rh;
 	bool crc_stop;
 };
-struct call_rcu_chain *call_rcu_chain;
+struct call_rcu_chain *call_rcu_chain_list;
 
 /* Forward reference. */
 static void lock_torture_cleanup(void);
@@ -1074,12 +1074,12 @@ static int call_rcu_chain_init(void)
 
 	if (call_rcu_chains <= 0)
 		return 0;
-	call_rcu_chain = kcalloc(call_rcu_chains, sizeof(*call_rcu_chain), GFP_KERNEL);
-	if (!call_rcu_chain)
+	call_rcu_chain_list = kcalloc(call_rcu_chains, sizeof(*call_rcu_chain_list), GFP_KERNEL);
+	if (!call_rcu_chain_list)
 		return -ENOMEM;
 	for (i = 0; i < call_rcu_chains; i++) {
-		call_rcu_chain[i].crc_stop = false;
-		call_rcu(&call_rcu_chain[i].crc_rh, call_rcu_chain_cb);
+		call_rcu_chain_list[i].crc_stop = false;
+		call_rcu(&call_rcu_chain_list[i].crc_rh, call_rcu_chain_cb);
 	}
 	return 0;
 }
@@ -1089,13 +1089,13 @@ static void call_rcu_chain_cleanup(void)
 {
 	int i;
 
-	if (!call_rcu_chain)
+	if (!call_rcu_chain_list)
 		return;
 	for (i = 0; i < call_rcu_chains; i++)
-		smp_store_release(&call_rcu_chain[i].crc_stop, true);
+		smp_store_release(&call_rcu_chain_list[i].crc_stop, true);
 	rcu_barrier();
-	kfree(call_rcu_chain);
-	call_rcu_chain = NULL;
+	kfree(call_rcu_chain_list);
+	call_rcu_chain_list = NULL;
 }
 
 static void lock_torture_cleanup(void)
-- 
GitLab


From 454723b1615f7423fcba0b8f722cef4992a1846f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Mon, 16 Oct 2023 00:25:14 +0200
Subject: [PATCH 0259/4076] rcutorture: add nolibc init support for mips, ppc
 and rv64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use nolibc for all support architectures.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 tools/testing/selftests/rcutorture/bin/mkinitrd.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
index 212c52ca90b55..f3f8671295602 100755
--- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
+++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
@@ -67,7 +67,10 @@ ___EOF___
 # build using nolibc on supported archs (smaller executable) and fall
 # back to regular glibc on other ones.
 if echo -e "#if __x86_64__||__i386__||__i486__||__i586__||__i686__" \
-	   "||__ARM_EABI__||__aarch64__||__s390x__||__loongarch__\nyes\n#endif" \
+	   "||__ARM_EABI__||__aarch64__||(__mips__ && _ABIO32)" \
+	   "||__powerpc__||(__riscv && __riscv_xlen == 64)" \
+	   "||__s390x__||__loongarch__" \
+	   "\nyes\n#endif" \
    | ${CROSS_COMPILE}gcc -E -nostdlib -xc - \
    | grep -q '^yes'; then
 	# architecture supported by nolibc
-- 
GitLab


From af19a2526cba92082723b98fcf191a595054a952 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 1 Nov 2023 10:30:56 -0700
Subject: [PATCH 0260/4076] rcutorture: Add mid-sized stall to TREE07

There is code in rcu_implicit_dynticks_qs() that checks for the current
grace period being halfway to the RCU CPU stall timeout, but rcutorture
currently does not test this code.  This commit therefore adds a 14-second
stall to the TREE07 scenario in order to test this code given the default
RCU CPU stall warning timeout of 21 seconds.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot
index d446099375038..979edbf4c8205 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot
@@ -1 +1,4 @@
 nohz_full=2-9
+rcutorture.stall_cpu=14
+rcutorture.stall_cpu_holdoff=90
+rcutorture.fwd_progress=0
-- 
GitLab


From 90f1015dfee3d33f8ca7bfe03296d100d465e385 Mon Sep 17 00:00:00 2001
From: Zqiang <qiang.zhang1211@gmail.com>
Date: Fri, 3 Nov 2023 15:26:39 +0800
Subject: [PATCH 0261/4076] rcutorture: Add fqs_holdoff check before fqs_task
 is created

For rcutorture tests on RCU implementations that support
force-quiescent-state operations and that set the fqs_duration module
parameter greater than zero, the fqs_task kthread will be created.
However, if the fqs_holdoff module parameter is not set, then its default
value of zero will cause fqs_task enter a long-term busy loop until
stopped by kthread_stop().  This commit therefore adds a fqs_holdoff
check before the fqs_task is created, making sure that whenever the
fqs_task is created, the fqs_holdoff will be greater than zero.

Signed-off-by: Zqiang <qiang.zhang1211@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 kernel/rcu/rcutorture.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 30fc9d34e3297..a0b2520bd32b6 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -3872,7 +3872,9 @@ rcu_torture_init(void)
 	}
 	if (fqs_duration < 0)
 		fqs_duration = 0;
-	if (fqs_duration) {
+	if (fqs_holdoff < 0)
+		fqs_holdoff = 0;
+	if (fqs_duration && fqs_holdoff) {
 		/* Create the fqs thread */
 		firsterr = torture_create_kthread(rcu_torture_fqs, NULL,
 						  fqs_task);
-- 
GitLab


From 5c68b66d4d7eff8cdb6f508f8537faa30c5faa6d Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 20 Nov 2023 20:07:39 +0100
Subject: [PATCH 0262/4076] soundwire: qcom: drop unneeded
 qcom_swrm_stream_alloc_ports() cleanup

The cleanup in "err" goto label clears bits from pconfig array which is
a local variable.  This does not have any effect outside of this
function, so drop this useless code.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231120190740.339350-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/qcom.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index a1e2d6c981862..754870a4a047c 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -1157,7 +1157,7 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 	struct sdw_port_runtime *p_rt;
 	struct sdw_slave *slave;
 	unsigned long *port_mask;
-	int i, maxport, pn, nports = 0, ret = 0;
+	int maxport, pn, nports = 0, ret = 0;
 	unsigned int m_port;
 
 	mutex_lock(&ctrl->port_lock);
@@ -1183,7 +1183,7 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 				if (pn > maxport) {
 					dev_err(ctrl->dev, "All ports busy\n");
 					ret = -EBUSY;
-					goto err;
+					goto out;
 				}
 				set_bit(pn, port_mask);
 				pconfig[nports].num = pn;
@@ -1205,12 +1205,7 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 	sconfig.bps = 1;
 	sdw_stream_add_master(&ctrl->bus, &sconfig, pconfig,
 			      nports, stream);
-err:
-	if (ret) {
-		for (i = 0; i < nports; i++)
-			clear_bit(pconfig[i].num, port_mask);
-	}
-
+out:
 	mutex_unlock(&ctrl->port_lock);
 
 	return ret;
-- 
GitLab


From 5bdc61ef45007908df9d8587111c7a5a552bdd46 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 20 Nov 2023 20:07:40 +0100
Subject: [PATCH 0263/4076] soundwire: qcom: move sconfig in
 qcom_swrm_stream_alloc_ports() out of critical section

Setting members of local variable "sconfig" in
qcom_swrm_stream_alloc_ports() does not depend on any earlier code in
this function, so can be moved up before the critical section.  This
makes the code a bit easier to follow because critical section is
smaller.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231120190740.339350-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/qcom.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index 754870a4a047c..e9a52c1bd3594 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -1160,6 +1160,17 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 	int maxport, pn, nports = 0, ret = 0;
 	unsigned int m_port;
 
+	if (direction == SNDRV_PCM_STREAM_CAPTURE)
+		sconfig.direction = SDW_DATA_DIR_TX;
+	else
+		sconfig.direction = SDW_DATA_DIR_RX;
+
+	/* hw parameters wil be ignored as we only support PDM */
+	sconfig.ch_count = 1;
+	sconfig.frame_rate = params_rate(params);
+	sconfig.type = stream->type;
+	sconfig.bps = 1;
+
 	mutex_lock(&ctrl->port_lock);
 	list_for_each_entry(m_rt, &stream->master_list, stream_node) {
 		if (m_rt->direction == SDW_DATA_DIR_RX) {
@@ -1193,16 +1204,6 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 		}
 	}
 
-	if (direction == SNDRV_PCM_STREAM_CAPTURE)
-		sconfig.direction = SDW_DATA_DIR_TX;
-	else
-		sconfig.direction = SDW_DATA_DIR_RX;
-
-	/* hw parameters wil be ignored as we only support PDM */
-	sconfig.ch_count = 1;
-	sconfig.frame_rate = params_rate(params);
-	sconfig.type = stream->type;
-	sconfig.bps = 1;
 	sdw_stream_add_master(&ctrl->bus, &sconfig, pconfig,
 			      nports, stream);
 out:
-- 
GitLab


From 21f4c443731fdb064c0dd31a743aafd0b075156c Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 20 Nov 2023 18:47:20 +0100
Subject: [PATCH 0264/4076] soundwire: stream: constify sdw_port_config when
 adding devices

sdw_stream_add_master() and sdw_stream_add_slave() do not modify
contents of passed sdw_port_config, so it can be made const for code
safety and as documentation of expected usage.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20231120174720.239610-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/stream.c    | 10 +++++-----
 include/linux/soundwire/sdw.h |  6 +++---
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 69719b335bcb1..9dc6399f206af 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -897,7 +897,7 @@ static struct sdw_port_runtime *sdw_port_alloc(struct list_head *port_list)
 }
 
 static int sdw_port_config(struct sdw_port_runtime *p_rt,
-			   struct sdw_port_config *port_config,
+			   const struct sdw_port_config *port_config,
 			   int port_index)
 {
 	p_rt->ch_mask = port_config[port_index].ch_mask;
@@ -970,7 +970,7 @@ static int sdw_slave_port_is_valid_range(struct device *dev, int num)
 
 static int sdw_slave_port_config(struct sdw_slave *slave,
 				 struct sdw_slave_runtime *s_rt,
-				 struct sdw_port_config *port_config)
+				 const struct sdw_port_config *port_config)
 {
 	struct sdw_port_runtime *p_rt;
 	int ret;
@@ -1026,7 +1026,7 @@ static int sdw_master_port_alloc(struct sdw_master_runtime *m_rt,
 }
 
 static int sdw_master_port_config(struct sdw_master_runtime *m_rt,
-				  struct sdw_port_config *port_config)
+				  const struct sdw_port_config *port_config)
 {
 	struct sdw_port_runtime *p_rt;
 	int ret;
@@ -1861,7 +1861,7 @@ EXPORT_SYMBOL(sdw_release_stream);
  */
 int sdw_stream_add_master(struct sdw_bus *bus,
 			  struct sdw_stream_config *stream_config,
-			  struct sdw_port_config *port_config,
+			  const struct sdw_port_config *port_config,
 			  unsigned int num_ports,
 			  struct sdw_stream_runtime *stream)
 {
@@ -1981,7 +1981,7 @@ EXPORT_SYMBOL(sdw_stream_remove_master);
  */
 int sdw_stream_add_slave(struct sdw_slave *slave,
 			 struct sdw_stream_config *stream_config,
-			 struct sdw_port_config *port_config,
+			 const struct sdw_port_config *port_config,
 			 unsigned int num_ports,
 			 struct sdw_stream_runtime *stream)
 {
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 4f3d14bb15385..904004d8b5622 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -1040,7 +1040,7 @@ int sdw_compute_params(struct sdw_bus *bus);
 
 int sdw_stream_add_master(struct sdw_bus *bus,
 		struct sdw_stream_config *stream_config,
-		struct sdw_port_config *port_config,
+		const struct sdw_port_config *port_config,
 		unsigned int num_ports,
 		struct sdw_stream_runtime *stream);
 int sdw_stream_remove_master(struct sdw_bus *bus,
@@ -1062,7 +1062,7 @@ void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id
 
 int sdw_stream_add_slave(struct sdw_slave *slave,
 			 struct sdw_stream_config *stream_config,
-			 struct sdw_port_config *port_config,
+			 const struct sdw_port_config *port_config,
 			 unsigned int num_ports,
 			 struct sdw_stream_runtime *stream);
 int sdw_stream_remove_slave(struct sdw_slave *slave,
@@ -1084,7 +1084,7 @@ int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val);
 
 static inline int sdw_stream_add_slave(struct sdw_slave *slave,
 				       struct sdw_stream_config *stream_config,
-				       struct sdw_port_config *port_config,
+				       const struct sdw_port_config *port_config,
 				       unsigned int num_ports,
 				       struct sdw_stream_runtime *stream)
 {
-- 
GitLab


From 26fb87ffa9d90fb16ca1b2b262f38d93bdcee934 Mon Sep 17 00:00:00 2001
From: Steffen Eiden <seiden@linux.ibm.com>
Date: Mon, 6 Nov 2023 13:49:22 +0100
Subject: [PATCH 0265/4076] s390/uvdevice: Report additional-data length for
 attestation

Additional data length in the attestation request is an in/out variable.
Software provides the capacity of the buffer. Upon successful request,
firmware reports the actual bytes written to the additional data in that
field. This information is lost, as the length field was not copied back
to userspace before. Attestation might fail, if user space did not
specify the exact amount of needed bytes required, as this length is
part of the attestation measurement.

Signed-off-by: Steffen Eiden <seiden@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Link: https://lore.kernel.org/r/20231106124922.3032370-1-seiden@linux.ibm.com
Message-Id: <20231106124922.3032370-1-seiden@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 drivers/s390/char/uvdevice.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/s390/char/uvdevice.c b/drivers/s390/char/uvdevice.c
index 144cd2e035909..42c9f77f8da0a 100644
--- a/drivers/s390/char/uvdevice.c
+++ b/drivers/s390/char/uvdevice.c
@@ -109,6 +109,7 @@ static int uvio_copy_attest_result_to_user(struct uv_cb_attest *uvcb_attest,
 					   struct uvio_attest *uvio_attest)
 {
 	struct uvio_attest __user *user_uvio_attest = (void __user *)uv_ioctl->argument_addr;
+	u32 __user *user_buf_add_len = (u32 __user *)&user_uvio_attest->add_data_len;
 	void __user *user_buf_add = (void __user *)uvio_attest->add_data_addr;
 	void __user *user_buf_meas = (void __user *)uvio_attest->meas_addr;
 	void __user *user_buf_uid = &user_uvio_attest->config_uid;
@@ -117,6 +118,8 @@ static int uvio_copy_attest_result_to_user(struct uv_cb_attest *uvcb_attest,
 		return -EFAULT;
 	if (add_data && copy_to_user(user_buf_add, add_data, uvio_attest->add_data_len))
 		return -EFAULT;
+	if (put_user(uvio_attest->add_data_len, user_buf_add_len))
+		return -EFAULT;
 	if (copy_to_user(user_buf_uid, uvcb_attest->config_uid, sizeof(uvcb_attest->config_uid)))
 		return -EFAULT;
 	return 0;
-- 
GitLab


From 9768af12edb3b23cfa1f7c05e019115b73f9490c Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Date: Fri, 27 Oct 2023 14:29:55 +0200
Subject: [PATCH 0266/4076] usb: phy: generic: add suspend support for
 regulator

Disable the vcc regulator on suspend and enable it on resume.

Signed-off-by: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Signed-off-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://lore.kernel.org/r/20231027122955.22123-1-francesco@dolcini.it
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/phy/phy-generic.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index 770081b828a42..9ab50f26db607 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -46,15 +46,21 @@ EXPORT_SYMBOL_GPL(usb_phy_generic_unregister);
 static int nop_set_suspend(struct usb_phy *x, int suspend)
 {
 	struct usb_phy_generic *nop = dev_get_drvdata(x->dev);
+	int ret = 0;
 
-	if (!IS_ERR(nop->clk)) {
-		if (suspend)
+	if (suspend) {
+		if (!IS_ERR(nop->clk))
 			clk_disable_unprepare(nop->clk);
-		else
+		if (!IS_ERR(nop->vcc) && !device_may_wakeup(x->dev))
+			ret = regulator_disable(nop->vcc);
+	} else {
+		if (!IS_ERR(nop->vcc) && !device_may_wakeup(x->dev))
+			ret = regulator_enable(nop->vcc);
+		if (!IS_ERR(nop->clk))
 			clk_prepare_enable(nop->clk);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void nop_reset(struct usb_phy_generic *nop)
-- 
GitLab


From e0cc05d52ad310cced029449bcda0f9fc847097c Mon Sep 17 00:00:00 2001
From: Guan-Yu Lin <guanyulin@google.com>
Date: Thu, 16 Nov 2023 16:32:16 +0800
Subject: [PATCH 0267/4076] usb: typec: tcpm: skip checking port->send_discover
 in PD3.0

The original Collison Avoidance mechanism, port->send_discover, avoids
the conflict when port partners start AMS almost the same time. However,
this mechanism is replaced by SINK_TX_OK and SINK_TX_NG. Skip the check
in PD3.0 to avoid the deadlock when source is requesting DR_SWAP where
sink is requesting DISCOVER_IDENTITY.

Signed-off-by: Guan-Yu Lin <guanyulin@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20231116083221.1201892-1-guanyulin@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 058d5b853b574..ff3c171a3a75e 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -2847,7 +2847,7 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 					   PD_MSG_CTRL_NOT_SUPP,
 					   NONE_AMS);
 		} else {
-			if (port->send_discover) {
+			if (port->send_discover && port->negotiated_rev < PD_REV30) {
 				tcpm_queue_message(port, PD_MSG_CTRL_WAIT);
 				break;
 			}
@@ -2863,7 +2863,7 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 					   PD_MSG_CTRL_NOT_SUPP,
 					   NONE_AMS);
 		} else {
-			if (port->send_discover) {
+			if (port->send_discover && port->negotiated_rev < PD_REV30) {
 				tcpm_queue_message(port, PD_MSG_CTRL_WAIT);
 				break;
 			}
@@ -2872,7 +2872,7 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 		}
 		break;
 	case PD_CTRL_VCONN_SWAP:
-		if (port->send_discover) {
+		if (port->send_discover && port->negotiated_rev < PD_REV30) {
 			tcpm_queue_message(port, PD_MSG_CTRL_WAIT);
 			break;
 		}
-- 
GitLab


From d1dbd6987ee10f44a06c46bcfade69cdbb56a5cd Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 11 Nov 2023 15:19:53 +0100
Subject: [PATCH 0268/4076] dt-bindings: usb: qcom,dwc3: adjust number of
 interrupts on SM6125

Qualcomm SM6125 DWC3 USB controller comes with two interrupts (verified
with downstream/vendor code of Trinket DTSI from Xiaomi Laurel device).
Move the qcom,sm6125-dwc3 to appropriate place in allOf:if:then blocks
constraining interrupts.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Marijn Suijten <marijn.suijten@somainline.org>
Link: https://lore.kernel.org/r/20231111141953.51841-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/qcom,dwc3.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index ccce57e4290d4..f6339e8e92d93 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -372,7 +372,6 @@ allOf:
               - qcom,sdx65-dwc3
               - qcom,sdx75-dwc3
               - qcom,sm4250-dwc3
-              - qcom,sm6125-dwc3
               - qcom,sm6350-dwc3
               - qcom,sm8150-dwc3
               - qcom,sm8250-dwc3
@@ -406,6 +405,7 @@ allOf:
               - qcom,msm8996-dwc3
               - qcom,msm8998-dwc3
               - qcom,sm6115-dwc3
+              - qcom,sm6125-dwc3
     then:
       properties:
         interrupts:
-- 
GitLab


From a769154c7cac037914ba375ae88aae55b2c853e0 Mon Sep 17 00:00:00 2001
From: Hardik Gajjar <hgajjar@de.adit-jv.com>
Date: Fri, 27 Oct 2023 17:20:28 +0200
Subject: [PATCH 0269/4076] usb: xhci: Add timeout argument in address_device
 USB HCD callback

- The HCD address_device callback now accepts a user-defined timeout value
  in milliseconds, providing better control over command execution times.
- The default timeout value for the address_device command has been set
  to 5000 ms, aligning with the USB 3.2 specification. However, this
  timeout can be adjusted as needed.
- The xhci_setup_device function has been updated to accept the timeout
  value, allowing it to specify the maximum wait time for the command
  operation to complete.
- The hub driver has also been updated to accommodate the newly added
  timeout parameter during the SET_ADDRESS request.

Signed-off-by: Hardik Gajjar <hgajjar@de.adit-jv.com>
Reviewed-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231027152029.104363-1-hgajjar@de.adit-jv.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c       |  2 +-
 drivers/usb/host/xhci-mem.c  |  2 ++
 drivers/usb/host/xhci-ring.c | 11 ++++++-----
 drivers/usb/host/xhci.c      | 23 ++++++++++++++++-------
 drivers/usb/host/xhci.h      |  9 +++++++--
 include/linux/usb/hcd.h      |  5 +++--
 6 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index b4584a0cd4845..0490582643678 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4662,7 +4662,7 @@ static int hub_set_address(struct usb_device *udev, int devnum)
 	if (udev->state != USB_STATE_DEFAULT)
 		return -EINVAL;
 	if (hcd->driver->address_device)
-		retval = hcd->driver->address_device(hcd, udev);
+		retval = hcd->driver->address_device(hcd, udev, USB_CTRL_SET_TIMEOUT);
 	else
 		retval = usb_control_msg(udev, usb_sndaddr0pipe(),
 				USB_REQ_SET_ADDRESS, 0, devnum, 0,
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 62116586848b8..6faa854152ef1 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1739,6 +1739,8 @@ struct xhci_command *xhci_alloc_command(struct xhci_hcd *xhci,
 	}
 
 	command->status = 0;
+	/* set default timeout to 5000 ms */
+	command->timeout_ms = XHCI_CMD_DEFAULT_TIMEOUT;
 	INIT_LIST_HEAD(&command->cmd_list);
 	return command;
 }
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index f3b5e6345858c..2c1d614b3b0fb 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -366,9 +366,10 @@ void xhci_ring_cmd_db(struct xhci_hcd *xhci)
 	readl(&xhci->dba->doorbell[0]);
 }
 
-static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci, unsigned long delay)
+static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci)
 {
-	return mod_delayed_work(system_wq, &xhci->cmd_timer, delay);
+	return mod_delayed_work(system_wq, &xhci->cmd_timer,
+			msecs_to_jiffies(xhci->current_cmd->timeout_ms));
 }
 
 static struct xhci_command *xhci_next_queued_cmd(struct xhci_hcd *xhci)
@@ -412,7 +413,7 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
 	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
 	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
 		xhci->current_cmd = cur_cmd;
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 		xhci_ring_cmd_db(xhci);
 	}
 }
@@ -1787,7 +1788,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 	if (!list_is_singular(&xhci->cmd_list)) {
 		xhci->current_cmd = list_first_entry(&cmd->cmd_list,
 						struct xhci_command, cmd_list);
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 	} else if (xhci->current_cmd == cmd) {
 		xhci->current_cmd = NULL;
 	}
@@ -4287,7 +4288,7 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
 	/* if there are no other commands queued we start the timeout timer */
 	if (list_empty(&xhci->cmd_list)) {
 		xhci->current_cmd = cmd;
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 	}
 
 	list_add_tail(&cmd->cmd_list, &xhci->cmd_list);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 884b0898d9c95..cb885ddc20326 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4029,12 +4029,18 @@ disable_slot:
 	return 0;
 }
 
-/*
- * Issue an Address Device command and optionally send a corresponding
- * SetAddress request to the device.
+/**
+ * xhci_setup_device - issues an Address Device command to assign a unique
+ *			USB bus address.
+ * @hcd: USB host controller data structure.
+ * @udev: USB dev structure representing the connected device.
+ * @setup: Enum specifying setup mode: address only or with context.
+ * @timeout_ms: Max wait time (ms) for the command operation to complete.
+ *
+ * Return: 0 if successful; otherwise, negative error code.
  */
 static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
-			     enum xhci_setup_dev setup)
+			     enum xhci_setup_dev setup, unsigned int timeout_ms)
 {
 	const char *act = setup == SETUP_CONTEXT_ONLY ? "context" : "address";
 	unsigned long flags;
@@ -4091,6 +4097,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 	}
 
 	command->in_ctx = virt_dev->in_ctx;
+	command->timeout_ms = timeout_ms;
 
 	slot_ctx = xhci_get_slot_ctx(xhci, virt_dev->in_ctx);
 	ctrl_ctx = xhci_get_input_control_ctx(virt_dev->in_ctx);
@@ -4217,14 +4224,16 @@ out:
 	return ret;
 }
 
-static int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
+static int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev,
+			       unsigned int timeout_ms)
 {
-	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ADDRESS);
+	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ADDRESS, timeout_ms);
 }
 
 static int xhci_enable_device(struct usb_hcd *hcd, struct usb_device *udev)
 {
-	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ONLY);
+	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ONLY,
+				 XHCI_CMD_DEFAULT_TIMEOUT);
 }
 
 /*
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 3ea5c092bba71..62b610f007544 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -791,6 +791,8 @@ struct xhci_command {
 	struct completion		*completion;
 	union xhci_trb			*command_trb;
 	struct list_head		cmd_list;
+	/* xHCI command response timeout in milliseconds */
+	unsigned int			timeout_ms;
 };
 
 /* drop context bitmasks */
@@ -1550,8 +1552,11 @@ struct xhci_td {
 	unsigned int		num_trbs;
 };
 
-/* xHCI command default timeout value */
-#define XHCI_CMD_DEFAULT_TIMEOUT	(5 * HZ)
+/*
+ * xHCI command default timeout value in milliseconds.
+ * USB 3.2 spec, section 9.2.6.1
+ */
+#define XHCI_CMD_DEFAULT_TIMEOUT	5000
 
 /* command descriptor */
 struct xhci_cd {
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 00724b4f6e122..cd77fc6095a15 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -372,8 +372,9 @@ struct hc_driver {
 		 * or bandwidth constraints.
 		 */
 	void	(*reset_bandwidth)(struct usb_hcd *, struct usb_device *);
-		/* Returns the hardware-chosen device address */
-	int	(*address_device)(struct usb_hcd *, struct usb_device *udev);
+		/* Set the hardware-chosen device address */
+	int	(*address_device)(struct usb_hcd *, struct usb_device *udev,
+				  unsigned int timeout_ms);
 		/* prepares the hardware to send commands to the device */
 	int	(*enable_device)(struct usb_hcd *, struct usb_device *udev);
 		/* Notifies the HCD after a hub descriptor is fetched.
-- 
GitLab


From 5a1ccf0c72cf917ff3ccc131d1bb8d19338ffe52 Mon Sep 17 00:00:00 2001
From: Hardik Gajjar <hgajjar@de.adit-jv.com>
Date: Fri, 27 Oct 2023 17:20:29 +0200
Subject: [PATCH 0270/4076] usb: new quirk to reduce the SET_ADDRESS request
 timeout

This patch introduces a new USB quirk,
USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT, which modifies the timeout value
for the SET_ADDRESS request. The standard timeout for USB request/command
is 5000 ms, as recommended in the USB 3.2 specification (section 9.2.6.1).

However, certain scenarios, such as connecting devices through an APTIV
hub, can lead to timeout errors when the device enumerates as full speed
initially and later switches to high speed during chirp negotiation.

In such cases, USB analyzer logs reveal that the bus suspends for
5 seconds due to incorrect chirp parsing and resumes only after two
consecutive timeout errors trigger a hub driver reset.

Packet(54) Dir(?) Full Speed J(997.100 us) Idle(  2.850 us)
_______| Time Stamp(28 . 105 910 682)
_______|_____________________________________________________________Ch0
Packet(55) Dir(?) Full Speed J(997.118 us) Idle(  2.850 us)
_______| Time Stamp(28 . 106 910 632)
_______|_____________________________________________________________Ch0
Packet(56) Dir(?) Full Speed J(399.650 us) Idle(222.582 us)
_______| Time Stamp(28 . 107 910 600)
_______|_____________________________________________________________Ch0
Packet(57) Dir Chirp J( 23.955 ms) Idle(115.169 ms)
_______| Time Stamp(28 . 108 532 832)
_______|_____________________________________________________________Ch0
Packet(58) Dir(?) Full Speed J (Suspend)( 5.347 sec) Idle(  5.366 us)
_______| Time Stamp(28 . 247 657 600)
_______|_____________________________________________________________Ch0

This 5-second delay in device enumeration is undesirable, particularly
in automotive applications where quick enumeration is crucial
(ideally within 3 seconds).

The newly introduced quirks provide the flexibility to align with a
3-second time limit, as required in specific contexts like automotive
applications.

By reducing the SET_ADDRESS request timeout to 500 ms, the
system can respond more swiftly to errors, initiate rapid recovery, and
ensure efficient device enumeration. This change is vital for scenarios
where rapid smartphone enumeration and screen projection are essential.

To use the quirk, please write "vendor_id:product_id:p" to
/sys/bus/usb/drivers/hub/module/parameter/quirks

For example,
echo "0x2c48:0x0132:p" > /sys/bus/usb/drivers/hub/module/parameters/quirks"

Signed-off-by: Hardik Gajjar <hgajjar@de.adit-jv.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231027152029.104363-2-hgajjar@de.adit-jv.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  3 +++
 drivers/usb/core/hub.c                          | 15 +++++++++++++--
 drivers/usb/core/quirks.c                       |  7 +++++++
 include/linux/usb/quirks.h                      |  3 +++
 4 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 65731b060e3fe..0a6a4b7f7a3b9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6908,6 +6908,9 @@
 					pause after every control message);
 				o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
 					delay after resetting its port);
+				p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT
+					(Reduce timeout of the SET_ADDRESS
+					request from 5000 ms to 500 ms);
 			Example: quirks=0781:5580:bk,0a5c:5834:gij
 
 	usbhid.mousepoll=
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 0490582643678..756fbd7cac435 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -54,6 +54,12 @@
 #define USB_TP_TRANSMISSION_DELAY_MAX	65535	/* ns */
 #define USB_PING_RESPONSE_TIME		400	/* ns */
 
+/*
+ * The SET_ADDRESS request timeout will be 500 ms when
+ * USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT quirk flag is set.
+ */
+#define USB_SHORT_SET_ADDRESS_REQ_TIMEOUT	500  /* ms */
+
 /* Protect struct usb_device->state and ->children members
  * Note: Both are also protected by ->dev.sem, except that ->state can
  * change to USB_STATE_NOTATTACHED even when the semaphore isn't held. */
@@ -4649,7 +4655,12 @@ EXPORT_SYMBOL_GPL(usb_ep0_reinit);
 static int hub_set_address(struct usb_device *udev, int devnum)
 {
 	int retval;
+	unsigned int timeout_ms = USB_CTRL_SET_TIMEOUT;
 	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
+	struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent);
+
+	if (hub->hdev->quirks & USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT)
+		timeout_ms = USB_SHORT_SET_ADDRESS_REQ_TIMEOUT;
 
 	/*
 	 * The host controller will choose the device address,
@@ -4662,11 +4673,11 @@ static int hub_set_address(struct usb_device *udev, int devnum)
 	if (udev->state != USB_STATE_DEFAULT)
 		return -EINVAL;
 	if (hcd->driver->address_device)
-		retval = hcd->driver->address_device(hcd, udev, USB_CTRL_SET_TIMEOUT);
+		retval = hcd->driver->address_device(hcd, udev, timeout_ms);
 	else
 		retval = usb_control_msg(udev, usb_sndaddr0pipe(),
 				USB_REQ_SET_ADDRESS, 0, devnum, 0,
-				NULL, 0, USB_CTRL_SET_TIMEOUT);
+				NULL, 0, timeout_ms);
 	if (retval == 0) {
 		update_devnum(udev, devnum);
 		/* Device now using proper address. */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 15e9bd180a1d2..b4783574b8e66 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -138,6 +138,9 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp)
 			case 'o':
 				flags |= USB_QUIRK_HUB_SLOW_RESET;
 				break;
+			case 'p':
+				flags |= USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT;
+				break;
 			/* Ignore unrecognized flag characters */
 			}
 		}
@@ -527,6 +530,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	{ USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* APTIV AUTOMOTIVE HUB */
+	{ USB_DEVICE(0x2c48, 0x0132), .driver_info =
+			USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT },
+
 	/* DJI CineSSD */
 	{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
 
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index eeb7c2157c72f..59409c1fc3dee 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -72,4 +72,7 @@
 /* device has endpoints that should be ignored */
 #define USB_QUIRK_ENDPOINT_IGNORE		BIT(15)
 
+/* short SET_ADDRESS request timeout */
+#define USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT	BIT(16)
+
 #endif /* __LINUX_USB_QUIRKS_H */
-- 
GitLab


From 991544dc579b636e69defa3eec486fd6f6191e59 Mon Sep 17 00:00:00 2001
From: Avichal Rakesh <arakesh@google.com>
Date: Wed, 8 Nov 2023 16:41:01 -0800
Subject: [PATCH 0271/4076] usb: gadget: uvc: prevent use of disabled endpoint

Currently the set_alt callback immediately disables the endpoint and queues
the v4l2 streamoff event. However, as the streamoff event is processed
asynchronously, it is possible that the video_pump thread attempts to queue
requests to an already disabled endpoint.

This change moves disabling usb endpoint to the end of streamoff event
callback. As the endpoint's state can no longer be used, video_pump is
now guarded by uvc->state as well. To be consistent with the actual
streaming state, uvc->state is now toggled between CONNECTED and STREAMING
from the v4l2 event callback only.

Link: https://lore.kernel.org/20230615171558.GK741@pendragon.ideasonboard.com/
Link: https://lore.kernel.org/20230531085544.253363-1-dan.scally@ideasonboard.com/
Reviewed-by: Daniel Scally <dan.scally@ideasonboard.com>
Reviewed-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Tested-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Avichal Rakesh <arakesh@google.com>
Link: https://lore.kernel.org/r/20231109004104.3467968-1-arakesh@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uvc.c     | 11 +++++------
 drivers/usb/gadget/function/f_uvc.h     |  2 +-
 drivers/usb/gadget/function/uvc.h       |  2 +-
 drivers/usb/gadget/function/uvc_v4l2.c  | 20 +++++++++++++++++---
 drivers/usb/gadget/function/uvc_video.c |  3 ++-
 5 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index 786379f1b7b72..77999ed53d33e 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -263,10 +263,13 @@ uvc_function_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
 	return 0;
 }
 
-void uvc_function_setup_continue(struct uvc_device *uvc)
+void uvc_function_setup_continue(struct uvc_device *uvc, int disable_ep)
 {
 	struct usb_composite_dev *cdev = uvc->func.config->cdev;
 
+	if (disable_ep && uvc->video.ep)
+		usb_ep_disable(uvc->video.ep);
+
 	usb_composite_setup_continue(cdev);
 }
 
@@ -337,15 +340,11 @@ uvc_function_set_alt(struct usb_function *f, unsigned interface, unsigned alt)
 		if (uvc->state != UVC_STATE_STREAMING)
 			return 0;
 
-		if (uvc->video.ep)
-			usb_ep_disable(uvc->video.ep);
-
 		memset(&v4l2_event, 0, sizeof(v4l2_event));
 		v4l2_event.type = UVC_EVENT_STREAMOFF;
 		v4l2_event_queue(&uvc->vdev, &v4l2_event);
 
-		uvc->state = UVC_STATE_CONNECTED;
-		return 0;
+		return USB_GADGET_DELAYED_STATUS;
 
 	case 1:
 		if (uvc->state != UVC_STATE_CONNECTED)
diff --git a/drivers/usb/gadget/function/f_uvc.h b/drivers/usb/gadget/function/f_uvc.h
index 1db972d4beebe..083aef0c65c6a 100644
--- a/drivers/usb/gadget/function/f_uvc.h
+++ b/drivers/usb/gadget/function/f_uvc.h
@@ -11,7 +11,7 @@
 
 struct uvc_device;
 
-void uvc_function_setup_continue(struct uvc_device *uvc);
+void uvc_function_setup_continue(struct uvc_device *uvc, int disable_ep);
 
 void uvc_function_connect(struct uvc_device *uvc);
 
diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h
index 6751de8b63ad9..989bc6b4e93d3 100644
--- a/drivers/usb/gadget/function/uvc.h
+++ b/drivers/usb/gadget/function/uvc.h
@@ -177,7 +177,7 @@ struct uvc_file_handle {
  * Functions
  */
 
-extern void uvc_function_setup_continue(struct uvc_device *uvc);
+extern void uvc_function_setup_continue(struct uvc_device *uvc, int disable_ep);
 extern void uvc_function_connect(struct uvc_device *uvc);
 extern void uvc_function_disconnect(struct uvc_device *uvc);
 
diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c
index 3f0a9795c0d45..7cb8d027ff0c3 100644
--- a/drivers/usb/gadget/function/uvc_v4l2.c
+++ b/drivers/usb/gadget/function/uvc_v4l2.c
@@ -451,7 +451,7 @@ uvc_v4l2_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	 * Complete the alternate setting selection setup phase now that
 	 * userspace is ready to provide video frames.
 	 */
-	uvc_function_setup_continue(uvc);
+	uvc_function_setup_continue(uvc, 0);
 	uvc->state = UVC_STATE_STREAMING;
 
 	return 0;
@@ -463,11 +463,18 @@ uvc_v4l2_streamoff(struct file *file, void *fh, enum v4l2_buf_type type)
 	struct video_device *vdev = video_devdata(file);
 	struct uvc_device *uvc = video_get_drvdata(vdev);
 	struct uvc_video *video = &uvc->video;
+	int ret = 0;
 
 	if (type != video->queue.queue.type)
 		return -EINVAL;
 
-	return uvcg_video_enable(video, 0);
+	uvc->state = UVC_STATE_CONNECTED;
+	ret = uvcg_video_enable(video, 0);
+	if (ret < 0)
+		return ret;
+
+	uvc_function_setup_continue(uvc, 1);
+	return 0;
 }
 
 static int
@@ -500,6 +507,14 @@ uvc_v4l2_subscribe_event(struct v4l2_fh *fh,
 static void uvc_v4l2_disable(struct uvc_device *uvc)
 {
 	uvc_function_disconnect(uvc);
+	/*
+	 * Drop uvc->state to CONNECTED if it was streaming before.
+	 * This ensures that the usb_requests are no longer queued
+	 * to the controller.
+	 */
+	if (uvc->state == UVC_STATE_STREAMING)
+		uvc->state = UVC_STATE_CONNECTED;
+
 	uvcg_video_enable(&uvc->video, 0);
 	uvcg_free_buffers(&uvc->video.queue);
 	uvc->func_connected = false;
@@ -647,4 +662,3 @@ const struct v4l2_file_operations uvc_v4l2_fops = {
 	.get_unmapped_area = uvcg_v4l2_get_unmapped_area,
 #endif
 };
-
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 91af3b1ef0d41..c334802ac0a43 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -384,13 +384,14 @@ static void uvcg_video_pump(struct work_struct *work)
 	struct uvc_video_queue *queue = &video->queue;
 	/* video->max_payload_size is only set when using bulk transfer */
 	bool is_bulk = video->max_payload_size;
+	struct uvc_device *uvc = video->uvc;
 	struct usb_request *req = NULL;
 	struct uvc_buffer *buf;
 	unsigned long flags;
 	bool buf_done;
 	int ret;
 
-	while (video->ep->enabled) {
+	while (uvc->state == UVC_STATE_STREAMING && video->ep->enabled) {
 		/*
 		 * Retrieve the first available USB request, protected by the
 		 * request lock.
-- 
GitLab


From aeb686a98a9e9743c4c0338957e59643a2708146 Mon Sep 17 00:00:00 2001
From: Avichal Rakesh <arakesh@google.com>
Date: Wed, 8 Nov 2023 16:41:02 -0800
Subject: [PATCH 0272/4076] usb: gadget: uvc: Allocate uvc_requests one at a
 time

Currently, the uvc gadget driver allocates all uvc_requests as one array
and deallocates them all when the video stream stops. This includes
de-allocating all the usb_requests associated with those uvc_requests.
This can lead to use-after-free issues if any of those de-allocated
usb_requests were still owned by the usb controller.

This patch is 1 of 2 patches addressing the use-after-free issue.
Instead of bulk allocating all uvc_requests as an array, this patch
allocates uvc_requests one at a time, which should allows for similar
granularity when deallocating the uvc_requests. This patch has no
functional changes other than allocating each uvc_request separately,
and similarly freeing each of them separately.

Link: https://lore.kernel.org/7cd81649-2795-45b6-8c10-b7df1055020d@google.com
Reviewed-by: Daniel Scally <dan.scally@ideasonboard.com>
Reviewed-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Suggested-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Tested-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Avichal Rakesh <arakesh@google.com>
Link: https://lore.kernel.org/r/20231109004104.3467968-2-arakesh@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc.h       |  3 +-
 drivers/usb/gadget/function/uvc_video.c | 88 ++++++++++++++-----------
 2 files changed, 51 insertions(+), 40 deletions(-)

diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h
index 989bc6b4e93d3..993694da0bbcd 100644
--- a/drivers/usb/gadget/function/uvc.h
+++ b/drivers/usb/gadget/function/uvc.h
@@ -81,6 +81,7 @@ struct uvc_request {
 	struct sg_table sgt;
 	u8 header[UVCG_REQUEST_HEADER_LEN];
 	struct uvc_buffer *last_buf;
+	struct list_head list;
 };
 
 struct uvc_video {
@@ -102,7 +103,7 @@ struct uvc_video {
 
 	/* Requests */
 	unsigned int req_size;
-	struct uvc_request *ureq;
+	struct list_head ureqs; /* all uvc_requests allocated by uvc_video */
 	struct list_head req_free;
 	spinlock_t req_lock;
 
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index c334802ac0a43..1619f9664748d 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -227,6 +227,24 @@ uvc_video_encode_isoc(struct usb_request *req, struct uvc_video *video,
  * Request handling
  */
 
+static void
+uvc_video_free_request(struct uvc_request *ureq, struct usb_ep *ep)
+{
+	sg_free_table(&ureq->sgt);
+	if (ureq->req && ep) {
+		usb_ep_free_request(ep, ureq->req);
+		ureq->req = NULL;
+	}
+
+	kfree(ureq->req_buffer);
+	ureq->req_buffer = NULL;
+
+	if (!list_empty(&ureq->list))
+		list_del_init(&ureq->list);
+
+	kfree(ureq);
+}
+
 static int uvcg_video_ep_queue(struct uvc_video *video, struct usb_request *req)
 {
 	int ret;
@@ -293,27 +311,12 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 static int
 uvc_video_free_requests(struct uvc_video *video)
 {
-	unsigned int i;
-
-	if (video->ureq) {
-		for (i = 0; i < video->uvc_num_requests; ++i) {
-			sg_free_table(&video->ureq[i].sgt);
+	struct uvc_request *ureq, *temp;
 
-			if (video->ureq[i].req) {
-				usb_ep_free_request(video->ep, video->ureq[i].req);
-				video->ureq[i].req = NULL;
-			}
-
-			if (video->ureq[i].req_buffer) {
-				kfree(video->ureq[i].req_buffer);
-				video->ureq[i].req_buffer = NULL;
-			}
-		}
-
-		kfree(video->ureq);
-		video->ureq = NULL;
-	}
+	list_for_each_entry_safe(ureq, temp, &video->ureqs, list)
+		uvc_video_free_request(ureq, video->ep);
 
+	INIT_LIST_HEAD(&video->ureqs);
 	INIT_LIST_HEAD(&video->req_free);
 	video->req_size = 0;
 	return 0;
@@ -322,6 +325,7 @@ uvc_video_free_requests(struct uvc_video *video)
 static int
 uvc_video_alloc_requests(struct uvc_video *video)
 {
+	struct uvc_request *ureq;
 	unsigned int req_size;
 	unsigned int i;
 	int ret = -ENOMEM;
@@ -332,29 +336,33 @@ uvc_video_alloc_requests(struct uvc_video *video)
 		 * max_t(unsigned int, video->ep->maxburst, 1)
 		 * (video->ep->mult);
 
-	video->ureq = kcalloc(video->uvc_num_requests, sizeof(struct uvc_request), GFP_KERNEL);
-	if (video->ureq == NULL)
-		return -ENOMEM;
+	for (i = 0; i < video->uvc_num_requests; i++) {
+		ureq = kzalloc(sizeof(struct uvc_request), GFP_KERNEL);
+		if (ureq == NULL)
+			goto error;
+
+		INIT_LIST_HEAD(&ureq->list);
+
+		list_add_tail(&ureq->list, &video->ureqs);
 
-	for (i = 0; i < video->uvc_num_requests; ++i) {
-		video->ureq[i].req_buffer = kmalloc(req_size, GFP_KERNEL);
-		if (video->ureq[i].req_buffer == NULL)
+		ureq->req_buffer = kmalloc(req_size, GFP_KERNEL);
+		if (ureq->req_buffer == NULL)
 			goto error;
 
-		video->ureq[i].req = usb_ep_alloc_request(video->ep, GFP_KERNEL);
-		if (video->ureq[i].req == NULL)
+		ureq->req = usb_ep_alloc_request(video->ep, GFP_KERNEL);
+		if (ureq->req == NULL)
 			goto error;
 
-		video->ureq[i].req->buf = video->ureq[i].req_buffer;
-		video->ureq[i].req->length = 0;
-		video->ureq[i].req->complete = uvc_video_complete;
-		video->ureq[i].req->context = &video->ureq[i];
-		video->ureq[i].video = video;
-		video->ureq[i].last_buf = NULL;
+		ureq->req->buf = ureq->req_buffer;
+		ureq->req->length = 0;
+		ureq->req->complete = uvc_video_complete;
+		ureq->req->context = ureq;
+		ureq->video = video;
+		ureq->last_buf = NULL;
 
-		list_add_tail(&video->ureq[i].req->list, &video->req_free);
+		list_add_tail(&ureq->req->list, &video->req_free);
 		/* req_size/PAGE_SIZE + 1 for overruns and + 1 for header */
-		sg_alloc_table(&video->ureq[i].sgt,
+		sg_alloc_table(&ureq->sgt,
 			       DIV_ROUND_UP(req_size - UVCG_REQUEST_HEADER_LEN,
 					    PAGE_SIZE) + 2, GFP_KERNEL);
 	}
@@ -489,8 +497,8 @@ static void uvcg_video_pump(struct work_struct *work)
  */
 int uvcg_video_enable(struct uvc_video *video, int enable)
 {
-	unsigned int i;
 	int ret;
+	struct uvc_request *ureq;
 
 	if (video->ep == NULL) {
 		uvcg_info(&video->uvc->func,
@@ -502,9 +510,10 @@ int uvcg_video_enable(struct uvc_video *video, int enable)
 		cancel_work_sync(&video->pump);
 		uvcg_queue_cancel(&video->queue, 0);
 
-		for (i = 0; i < video->uvc_num_requests; ++i)
-			if (video->ureq && video->ureq[i].req)
-				usb_ep_dequeue(video->ep, video->ureq[i].req);
+		list_for_each_entry(ureq, &video->ureqs, list) {
+			if (ureq->req)
+				usb_ep_dequeue(video->ep, ureq->req);
+		}
 
 		uvc_video_free_requests(video);
 		uvcg_queue_enable(&video->queue, 0);
@@ -536,6 +545,7 @@ int uvcg_video_enable(struct uvc_video *video, int enable)
  */
 int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc)
 {
+	INIT_LIST_HEAD(&video->ureqs);
 	INIT_LIST_HEAD(&video->req_free);
 	spin_lock_init(&video->req_lock);
 	INIT_WORK(&video->pump, uvcg_video_pump);
-- 
GitLab


From 2079b60bda3257146a4e8ed7525513865f7e6b3e Mon Sep 17 00:00:00 2001
From: Avichal Rakesh <arakesh@google.com>
Date: Wed, 8 Nov 2023 16:41:03 -0800
Subject: [PATCH 0273/4076] usb: gadget: uvc: move video disable logic to its
 own function

This patch refactors the video disable logic in uvcg_video_enable
into its own separate function 'uvcg_video_disable'. This function
is now used anywhere uvcg_video_enable(video, 0) was used.

Reviewed-by: Daniel Scally <dan.scally@ideasonboard.com>
Suggested-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Avichal Rakesh <arakesh@google.com>
Link: https://lore.kernel.org/r/20231109004104.3467968-3-arakesh@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc_v4l2.c  |  6 ++--
 drivers/usb/gadget/function/uvc_video.c | 40 ++++++++++++++++---------
 drivers/usb/gadget/function/uvc_video.h |  3 +-
 3 files changed, 31 insertions(+), 18 deletions(-)

diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c
index 7cb8d027ff0c3..904dd283cbf72 100644
--- a/drivers/usb/gadget/function/uvc_v4l2.c
+++ b/drivers/usb/gadget/function/uvc_v4l2.c
@@ -443,7 +443,7 @@ uvc_v4l2_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 		return -EINVAL;
 
 	/* Enable UVC video. */
-	ret = uvcg_video_enable(video, 1);
+	ret = uvcg_video_enable(video);
 	if (ret < 0)
 		return ret;
 
@@ -469,7 +469,7 @@ uvc_v4l2_streamoff(struct file *file, void *fh, enum v4l2_buf_type type)
 		return -EINVAL;
 
 	uvc->state = UVC_STATE_CONNECTED;
-	ret = uvcg_video_enable(video, 0);
+	ret = uvcg_video_disable(video);
 	if (ret < 0)
 		return ret;
 
@@ -515,7 +515,7 @@ static void uvc_v4l2_disable(struct uvc_device *uvc)
 	if (uvc->state == UVC_STATE_STREAMING)
 		uvc->state = UVC_STATE_CONNECTED;
 
-	uvcg_video_enable(&uvc->video, 0);
+	uvcg_video_disable(&uvc->video);
 	uvcg_free_buffers(&uvc->video.queue);
 	uvc->func_connected = false;
 	wake_up_interruptible(&uvc->func_connected_queue);
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 1619f9664748d..c3e8c48f46a95 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -493,31 +493,43 @@ static void uvcg_video_pump(struct work_struct *work)
 }
 
 /*
- * Enable or disable the video stream.
+ * Disable the video stream
  */
-int uvcg_video_enable(struct uvc_video *video, int enable)
+int
+uvcg_video_disable(struct uvc_video *video)
 {
-	int ret;
 	struct uvc_request *ureq;
 
 	if (video->ep == NULL) {
 		uvcg_info(&video->uvc->func,
-			  "Video enable failed, device is uninitialized.\n");
+			  "Video disable failed, device is uninitialized.\n");
 		return -ENODEV;
 	}
 
-	if (!enable) {
-		cancel_work_sync(&video->pump);
-		uvcg_queue_cancel(&video->queue, 0);
+	cancel_work_sync(&video->pump);
+	uvcg_queue_cancel(&video->queue, 0);
 
-		list_for_each_entry(ureq, &video->ureqs, list) {
-			if (ureq->req)
-				usb_ep_dequeue(video->ep, ureq->req);
-		}
+	list_for_each_entry(ureq, &video->ureqs, list) {
+		if (ureq->req)
+			usb_ep_dequeue(video->ep, ureq->req);
+	}
 
-		uvc_video_free_requests(video);
-		uvcg_queue_enable(&video->queue, 0);
-		return 0;
+	uvc_video_free_requests(video);
+	uvcg_queue_enable(&video->queue, 0);
+	return 0;
+}
+
+/*
+ * Enable the video stream.
+ */
+int uvcg_video_enable(struct uvc_video *video)
+{
+	int ret;
+
+	if (video->ep == NULL) {
+		uvcg_info(&video->uvc->func,
+			  "Video enable failed, device is uninitialized.\n");
+		return -ENODEV;
 	}
 
 	if ((ret = uvcg_queue_enable(&video->queue, 1)) < 0)
diff --git a/drivers/usb/gadget/function/uvc_video.h b/drivers/usb/gadget/function/uvc_video.h
index 03adeefa343b7..8ef6259741f13 100644
--- a/drivers/usb/gadget/function/uvc_video.h
+++ b/drivers/usb/gadget/function/uvc_video.h
@@ -14,7 +14,8 @@
 
 struct uvc_video;
 
-int uvcg_video_enable(struct uvc_video *video, int enable);
+int uvcg_video_enable(struct uvc_video *video);
+int uvcg_video_disable(struct uvc_video *video);
 
 int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc);
 
-- 
GitLab


From da324ffce34c521b239f319d4051260444a3eb4a Mon Sep 17 00:00:00 2001
From: Avichal Rakesh <arakesh@google.com>
Date: Wed, 8 Nov 2023 16:41:04 -0800
Subject: [PATCH 0274/4076] usb: gadget: uvc: Fix use-after-free for inflight
 usb_requests

Currently, the uvc gadget driver allocates all uvc_requests as one array
and deallocates them all when the video stream stops. This includes
de-allocating all the usb_requests associated with those uvc_requests.
This can lead to use-after-free issues if any of those de-allocated
usb_requests were still owned by the usb controller.

This is patch 2 of 2 in fixing the use-after-free issue. It adds a new
flag to uvc_video to track when frames and requests should be flowing.
When disabling the video stream, the flag is tripped and, instead
of de-allocating all uvc_requests and usb_requests, the gadget
driver only de-allocates those usb_requests that are currently
owned by it (as present in req_free). Other usb_requests are left
untouched until their completion handler is called which takes care
of freeing the usb_request and its corresponding uvc_request.

Now that uvc_video does not depends on uvc->state, this patch removes
unnecessary upates to uvc->state that were made to accommodate uvc_video
logic. This should ensure that uvc gadget driver never accidentally
de-allocates a usb_request that it doesn't own.

Link: https://lore.kernel.org/7cd81649-2795-45b6-8c10-b7df1055020d@google.com
Reviewed-by: Daniel Scally <dan.scally@ideasonboard.com>
Reviewed-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Suggested-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Tested-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Avichal Rakesh <arakesh@google.com>
Link: https://lore.kernel.org/r/20231109004104.3467968-4-arakesh@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc.h       |   1 +
 drivers/usb/gadget/function/uvc_v4l2.c  |  10 +-
 drivers/usb/gadget/function/uvc_video.c | 130 ++++++++++++++++++++----
 3 files changed, 112 insertions(+), 29 deletions(-)

diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h
index 993694da0bbcd..be0d012aa2444 100644
--- a/drivers/usb/gadget/function/uvc.h
+++ b/drivers/usb/gadget/function/uvc.h
@@ -102,6 +102,7 @@ struct uvc_video {
 	unsigned int uvc_num_requests;
 
 	/* Requests */
+	bool is_enabled; /* tracks whether video stream is enabled */
 	unsigned int req_size;
 	struct list_head ureqs; /* all uvc_requests allocated by uvc_video */
 	struct list_head req_free;
diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c
index 904dd283cbf72..c7e5fa4f29e03 100644
--- a/drivers/usb/gadget/function/uvc_v4l2.c
+++ b/drivers/usb/gadget/function/uvc_v4l2.c
@@ -468,11 +468,11 @@ uvc_v4l2_streamoff(struct file *file, void *fh, enum v4l2_buf_type type)
 	if (type != video->queue.queue.type)
 		return -EINVAL;
 
-	uvc->state = UVC_STATE_CONNECTED;
 	ret = uvcg_video_disable(video);
 	if (ret < 0)
 		return ret;
 
+	uvc->state = UVC_STATE_CONNECTED;
 	uvc_function_setup_continue(uvc, 1);
 	return 0;
 }
@@ -507,14 +507,6 @@ uvc_v4l2_subscribe_event(struct v4l2_fh *fh,
 static void uvc_v4l2_disable(struct uvc_device *uvc)
 {
 	uvc_function_disconnect(uvc);
-	/*
-	 * Drop uvc->state to CONNECTED if it was streaming before.
-	 * This ensures that the usb_requests are no longer queued
-	 * to the controller.
-	 */
-	if (uvc->state == UVC_STATE_STREAMING)
-		uvc->state = UVC_STATE_CONNECTED;
-
 	uvcg_video_disable(&uvc->video);
 	uvcg_free_buffers(&uvc->video.queue);
 	uvc->func_connected = false;
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index c3e8c48f46a95..164bdeb7f2a93 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -227,6 +227,10 @@ uvc_video_encode_isoc(struct usb_request *req, struct uvc_video *video,
  * Request handling
  */
 
+/*
+ * Callers must take care to hold req_lock when this function may be called
+ * from multiple threads. For example, when frames are streaming to the host.
+ */
 static void
 uvc_video_free_request(struct uvc_request *ureq, struct usb_ep *ep)
 {
@@ -271,9 +275,26 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 	struct uvc_request *ureq = req->context;
 	struct uvc_video *video = ureq->video;
 	struct uvc_video_queue *queue = &video->queue;
-	struct uvc_device *uvc = video->uvc;
+	struct uvc_buffer *last_buf;
 	unsigned long flags;
 
+	spin_lock_irqsave(&video->req_lock, flags);
+	if (!video->is_enabled) {
+		/*
+		 * When is_enabled is false, uvcg_video_disable() ensures
+		 * that in-flight uvc_buffers are returned, so we can
+		 * safely call free_request without worrying about
+		 * last_buf.
+		 */
+		uvc_video_free_request(ureq, ep);
+		spin_unlock_irqrestore(&video->req_lock, flags);
+		return;
+	}
+
+	last_buf = ureq->last_buf;
+	ureq->last_buf = NULL;
+	spin_unlock_irqrestore(&video->req_lock, flags);
+
 	switch (req->status) {
 	case 0:
 		break;
@@ -295,17 +316,26 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 		uvcg_queue_cancel(queue, 0);
 	}
 
-	if (ureq->last_buf) {
-		uvcg_complete_buffer(&video->queue, ureq->last_buf);
-		ureq->last_buf = NULL;
+	if (last_buf) {
+		spin_lock_irqsave(&queue->irqlock, flags);
+		uvcg_complete_buffer(queue, last_buf);
+		spin_unlock_irqrestore(&queue->irqlock, flags);
 	}
 
 	spin_lock_irqsave(&video->req_lock, flags);
-	list_add_tail(&req->list, &video->req_free);
-	spin_unlock_irqrestore(&video->req_lock, flags);
-
-	if (uvc->state == UVC_STATE_STREAMING)
+	/*
+	 * Video stream might have been disabled while we were
+	 * processing the current usb_request. So make sure
+	 * we're still streaming before queueing the usb_request
+	 * back to req_free
+	 */
+	if (video->is_enabled) {
+		list_add_tail(&req->list, &video->req_free);
 		queue_work(video->async_wq, &video->pump);
+	} else {
+		uvc_video_free_request(ureq, ep);
+	}
+	spin_unlock_irqrestore(&video->req_lock, flags);
 }
 
 static int
@@ -392,20 +422,22 @@ static void uvcg_video_pump(struct work_struct *work)
 	struct uvc_video_queue *queue = &video->queue;
 	/* video->max_payload_size is only set when using bulk transfer */
 	bool is_bulk = video->max_payload_size;
-	struct uvc_device *uvc = video->uvc;
 	struct usb_request *req = NULL;
 	struct uvc_buffer *buf;
 	unsigned long flags;
 	bool buf_done;
 	int ret;
 
-	while (uvc->state == UVC_STATE_STREAMING && video->ep->enabled) {
+	while (true) {
+		if (!video->ep->enabled)
+			return;
+
 		/*
-		 * Retrieve the first available USB request, protected by the
-		 * request lock.
+		 * Check is_enabled and retrieve the first available USB
+		 * request, protected by the request lock.
 		 */
 		spin_lock_irqsave(&video->req_lock, flags);
-		if (list_empty(&video->req_free)) {
+		if (!video->is_enabled || list_empty(&video->req_free)) {
 			spin_unlock_irqrestore(&video->req_lock, flags);
 			return;
 		}
@@ -487,9 +519,11 @@ static void uvcg_video_pump(struct work_struct *work)
 		return;
 
 	spin_lock_irqsave(&video->req_lock, flags);
-	list_add_tail(&req->list, &video->req_free);
+	if (video->is_enabled)
+		list_add_tail(&req->list, &video->req_free);
+	else
+		uvc_video_free_request(req->context, video->ep);
 	spin_unlock_irqrestore(&video->req_lock, flags);
-	return;
 }
 
 /*
@@ -498,7 +532,11 @@ static void uvcg_video_pump(struct work_struct *work)
 int
 uvcg_video_disable(struct uvc_video *video)
 {
-	struct uvc_request *ureq;
+	unsigned long flags;
+	struct list_head inflight_bufs;
+	struct usb_request *req, *temp;
+	struct uvc_buffer *buf, *btemp;
+	struct uvc_request *ureq, *utemp;
 
 	if (video->ep == NULL) {
 		uvcg_info(&video->uvc->func,
@@ -506,15 +544,58 @@ uvcg_video_disable(struct uvc_video *video)
 		return -ENODEV;
 	}
 
+	INIT_LIST_HEAD(&inflight_bufs);
+	spin_lock_irqsave(&video->req_lock, flags);
+	video->is_enabled = false;
+
+	/*
+	 * Remove any in-flight buffers from the uvc_requests
+	 * because we want to return them before cancelling the
+	 * queue. This ensures that we aren't stuck waiting for
+	 * all complete callbacks to come through before disabling
+	 * vb2 queue.
+	 */
+	list_for_each_entry(ureq, &video->ureqs, list) {
+		if (ureq->last_buf) {
+			list_add_tail(&ureq->last_buf->queue, &inflight_bufs);
+			ureq->last_buf = NULL;
+		}
+	}
+	spin_unlock_irqrestore(&video->req_lock, flags);
+
 	cancel_work_sync(&video->pump);
 	uvcg_queue_cancel(&video->queue, 0);
 
-	list_for_each_entry(ureq, &video->ureqs, list) {
-		if (ureq->req)
-			usb_ep_dequeue(video->ep, ureq->req);
+	spin_lock_irqsave(&video->req_lock, flags);
+	/*
+	 * Remove all uvc_requests from ureqs with list_del_init
+	 * This lets uvc_video_free_request correctly identify
+	 * if the uvc_request is attached to a list or not when freeing
+	 * memory.
+	 */
+	list_for_each_entry_safe(ureq, utemp, &video->ureqs, list)
+		list_del_init(&ureq->list);
+
+	list_for_each_entry_safe(req, temp, &video->req_free, list) {
+		list_del(&req->list);
+		uvc_video_free_request(req->context, video->ep);
 	}
 
-	uvc_video_free_requests(video);
+	INIT_LIST_HEAD(&video->ureqs);
+	INIT_LIST_HEAD(&video->req_free);
+	video->req_size = 0;
+	spin_unlock_irqrestore(&video->req_lock, flags);
+
+	/*
+	 * Return all the video buffers before disabling the queue.
+	 */
+	spin_lock_irqsave(&video->queue.irqlock, flags);
+	list_for_each_entry_safe(buf, btemp, &inflight_bufs, queue) {
+		list_del(&buf->queue);
+		uvcg_complete_buffer(&video->queue, buf);
+	}
+	spin_unlock_irqrestore(&video->queue.irqlock, flags);
+
 	uvcg_queue_enable(&video->queue, 0);
 	return 0;
 }
@@ -532,6 +613,14 @@ int uvcg_video_enable(struct uvc_video *video)
 		return -ENODEV;
 	}
 
+	/*
+	 * Safe to access request related fields without req_lock because
+	 * this is the only thread currently active, and no other
+	 * request handling thread will become active until this function
+	 * returns.
+	 */
+	video->is_enabled = true;
+
 	if ((ret = uvcg_queue_enable(&video->queue, 1)) < 0)
 		return ret;
 
@@ -557,6 +646,7 @@ int uvcg_video_enable(struct uvc_video *video)
  */
 int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc)
 {
+	video->is_enabled = false;
 	INIT_LIST_HEAD(&video->ureqs);
 	INIT_LIST_HEAD(&video->req_free);
 	spin_lock_init(&video->req_lock);
-- 
GitLab


From 6acba0345b68772830582ca1ca369a2f45631275 Mon Sep 17 00:00:00 2001
From: Jayant Chowdhary <jchowdhary@google.com>
Date: Mon, 20 Nov 2023 06:20:25 +0000
Subject: [PATCH 0275/4076] usb:gadget:uvc Do not use worker thread to pump
 isoc usb requests

When we use an async work queue to perform the function of pumping
usb requests to the usb controller, it is possible that amongst other
factors, thread scheduling affects at what cadence we're able to pump
requests. This could mean isoc usb requests miss their uframes - resulting
in video stream flickers on the host device.

To avoid this, we make the async_wq thread only produce isoc usb_requests
with uvc buffers encoded into them. The process of queueing to the
endpoint is done by the uvc_video_complete() handler. In case no
usb_requests are ready with encoded information, we just queue a zero
length request to the endpoint from the complete handler.

For bulk endpoints the async_wq thread still queues usb requests to the
endpoint.

Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Jayant Chowdhary <jchowdhary@google.com>
Suggested-by: Avichal Rakesh <arakesh@google.com>
Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231120062026.3759463-1-jchowdhary@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc.h       |   8 +
 drivers/usb/gadget/function/uvc_video.c | 202 ++++++++++++++++++------
 2 files changed, 165 insertions(+), 45 deletions(-)

diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h
index be0d012aa2444..cb35687b11e7e 100644
--- a/drivers/usb/gadget/function/uvc.h
+++ b/drivers/usb/gadget/function/uvc.h
@@ -105,7 +105,15 @@ struct uvc_video {
 	bool is_enabled; /* tracks whether video stream is enabled */
 	unsigned int req_size;
 	struct list_head ureqs; /* all uvc_requests allocated by uvc_video */
+
+	/* USB requests that the video pump thread can encode into */
 	struct list_head req_free;
+
+	/*
+	 * USB requests video pump thread has already encoded into. These are
+	 * ready to be queued to the endpoint.
+	 */
+	struct list_head req_ready;
 	spinlock_t req_lock;
 
 	unsigned int req_int_count;
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 164bdeb7f2a93..98ba524c27f50 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -269,6 +269,101 @@ static int uvcg_video_ep_queue(struct uvc_video *video, struct usb_request *req)
 	return ret;
 }
 
+/* This function must be called with video->req_lock held. */
+static int uvcg_video_usb_req_queue(struct uvc_video *video,
+	struct usb_request *req, bool queue_to_ep)
+{
+	bool is_bulk = video->max_payload_size;
+	struct list_head *list = NULL;
+
+	if (!video->is_enabled) {
+		uvc_video_free_request(req->context, video->ep);
+		return -ENODEV;
+	}
+	if (queue_to_ep) {
+		struct uvc_request *ureq = req->context;
+		/*
+		 * With USB3 handling more requests at a higher speed, we can't
+		 * afford to generate an interrupt for every request. Decide to
+		 * interrupt:
+		 *
+		 * - When no more requests are available in the free queue, as
+		 *   this may be our last chance to refill the endpoint's
+		 *   request queue.
+		 *
+		 * - When this is request is the last request for the video
+		 *   buffer, as we want to start sending the next video buffer
+		 *   ASAP in case it doesn't get started already in the next
+		 *   iteration of this loop.
+		 *
+		 * - Four times over the length of the requests queue (as
+		 *   indicated by video->uvc_num_requests), as a trade-off
+		 *   between latency and interrupt load.
+		 */
+		if (list_empty(&video->req_free) || ureq->last_buf ||
+			!(video->req_int_count %
+			DIV_ROUND_UP(video->uvc_num_requests, 4))) {
+			video->req_int_count = 0;
+			req->no_interrupt = 0;
+		} else {
+			req->no_interrupt = 1;
+		}
+		video->req_int_count++;
+		return uvcg_video_ep_queue(video, req);
+	}
+	/*
+	 * If we're not queuing to the ep, for isoc we're queuing
+	 * to the req_ready list, otherwise req_free.
+	 */
+	list = is_bulk ? &video->req_free : &video->req_ready;
+	list_add_tail(&req->list, list);
+	return 0;
+}
+
+/*
+ * Must only be called from uvcg_video_enable - since after that we only want to
+ * queue requests to the endpoint from the uvc_video_complete complete handler.
+ * This function is needed in order to 'kick start' the flow of requests from
+ * gadget driver to the usb controller.
+ */
+static void uvc_video_ep_queue_initial_requests(struct uvc_video *video)
+{
+	struct usb_request *req = NULL;
+	unsigned long flags = 0;
+	unsigned int count = 0;
+	int ret = 0;
+
+	/*
+	 * We only queue half of the free list since we still want to have
+	 * some free usb_requests in the free list for the video_pump async_wq
+	 * thread to encode uvc buffers into. Otherwise we could get into a
+	 * situation where the free list does not have any usb requests to
+	 * encode into - we always end up queueing 0 length requests to the
+	 * end point.
+	 */
+	unsigned int half_list_size = video->uvc_num_requests / 2;
+
+	spin_lock_irqsave(&video->req_lock, flags);
+	/*
+	 * Take these requests off the free list and queue them all to the
+	 * endpoint. Since we queue 0 length requests with the req_lock held,
+	 * there isn't any 'data' race involved here with the complete handler.
+	 */
+	while (count < half_list_size) {
+		req = list_first_entry(&video->req_free, struct usb_request,
+					list);
+		list_del(&req->list);
+		req->length = 0;
+		ret = uvcg_video_ep_queue(video, req);
+		if (ret < 0) {
+			uvcg_queue_cancel(&video->queue, 0);
+			break;
+		}
+		count++;
+	}
+	spin_unlock_irqrestore(&video->req_lock, flags);
+}
+
 static void
 uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 {
@@ -277,6 +372,8 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 	struct uvc_video_queue *queue = &video->queue;
 	struct uvc_buffer *last_buf;
 	unsigned long flags;
+	bool is_bulk = video->max_payload_size;
+	int ret = 0;
 
 	spin_lock_irqsave(&video->req_lock, flags);
 	if (!video->is_enabled) {
@@ -330,8 +427,45 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 	 * back to req_free
 	 */
 	if (video->is_enabled) {
-		list_add_tail(&req->list, &video->req_free);
-		queue_work(video->async_wq, &video->pump);
+		/*
+		 * Here we check whether any request is available in the ready
+		 * list. If it is, queue it to the ep and add the current
+		 * usb_request to the req_free list - for video_pump to fill in.
+		 * Otherwise, just use the current usb_request to queue a 0
+		 * length request to the ep. Since we always add to the req_free
+		 * list if we dequeue from the ready list, there will never
+		 * be a situation where the req_free list is completely out of
+		 * requests and cannot recover.
+		 */
+		struct usb_request *to_queue = req;
+
+		to_queue->length = 0;
+		if (!list_empty(&video->req_ready)) {
+			to_queue = list_first_entry(&video->req_ready,
+				struct usb_request, list);
+			list_del(&to_queue->list);
+			list_add_tail(&req->list, &video->req_free);
+			/*
+			 * Queue work to the wq as well since it is possible that a
+			 * buffer may not have been completely encoded with the set of
+			 * in-flight usb requests for whih the complete callbacks are
+			 * firing.
+			 * In that case, if we do not queue work to the worker thread,
+			 * the buffer will never be marked as complete - and therefore
+			 * not be returned to userpsace. As a result,
+			 * dequeue -> queue -> dequeue flow of uvc buffers will not
+			 * happen.
+			 */
+			queue_work(video->async_wq, &video->pump);
+		}
+		/*
+		 * Queue to the endpoint. The actual queueing to ep will
+		 * only happen on one thread - the async_wq for bulk endpoints
+		 * and this thread for isoc endpoints.
+		 */
+		ret = uvcg_video_usb_req_queue(video, to_queue, !is_bulk);
+		if (ret < 0)
+			uvcg_queue_cancel(queue, 0);
 	} else {
 		uvc_video_free_request(ureq, ep);
 	}
@@ -348,6 +482,7 @@ uvc_video_free_requests(struct uvc_video *video)
 
 	INIT_LIST_HEAD(&video->ureqs);
 	INIT_LIST_HEAD(&video->req_free);
+	INIT_LIST_HEAD(&video->req_ready);
 	video->req_size = 0;
 	return 0;
 }
@@ -425,8 +560,7 @@ static void uvcg_video_pump(struct work_struct *work)
 	struct usb_request *req = NULL;
 	struct uvc_buffer *buf;
 	unsigned long flags;
-	bool buf_done;
-	int ret;
+	int ret = 0;
 
 	while (true) {
 		if (!video->ep->enabled)
@@ -455,15 +589,6 @@ static void uvcg_video_pump(struct work_struct *work)
 
 		if (buf != NULL) {
 			video->encode(req, video, buf);
-			buf_done = buf->state == UVC_BUF_STATE_DONE;
-		} else if (!(queue->flags & UVC_QUEUE_DISCONNECTED) && !is_bulk) {
-			/*
-			 * No video buffer available; the queue is still connected and
-			 * we're transferring over ISOC. Queue a 0 length request to
-			 * prevent missed ISOC transfers.
-			 */
-			req->length = 0;
-			buf_done = false;
 		} else {
 			/*
 			 * Either the queue has been disconnected or no video buffer
@@ -474,45 +599,25 @@ static void uvcg_video_pump(struct work_struct *work)
 			break;
 		}
 
-		/*
-		 * With USB3 handling more requests at a higher speed, we can't
-		 * afford to generate an interrupt for every request. Decide to
-		 * interrupt:
-		 *
-		 * - When no more requests are available in the free queue, as
-		 *   this may be our last chance to refill the endpoint's
-		 *   request queue.
-		 *
-		 * - When this is request is the last request for the video
-		 *   buffer, as we want to start sending the next video buffer
-		 *   ASAP in case it doesn't get started already in the next
-		 *   iteration of this loop.
-		 *
-		 * - Four times over the length of the requests queue (as
-		 *   indicated by video->uvc_num_requests), as a trade-off
-		 *   between latency and interrupt load.
-		 */
-		if (list_empty(&video->req_free) || buf_done ||
-		    !(video->req_int_count %
-		       DIV_ROUND_UP(video->uvc_num_requests, 4))) {
-			video->req_int_count = 0;
-			req->no_interrupt = 0;
-		} else {
-			req->no_interrupt = 1;
-		}
-
-		/* Queue the USB request */
-		ret = uvcg_video_ep_queue(video, req);
 		spin_unlock_irqrestore(&queue->irqlock, flags);
 
+		spin_lock_irqsave(&video->req_lock, flags);
+		/* For bulk end points we queue from the worker thread
+		 * since we would preferably not want to wait on requests
+		 * to be ready, in the uvcg_video_complete() handler.
+		 * For isoc endpoints we add the request to the ready list
+		 * and only queue it to the endpoint from the complete handler.
+		 */
+		ret = uvcg_video_usb_req_queue(video, req, is_bulk);
+		spin_unlock_irqrestore(&video->req_lock, flags);
+
 		if (ret < 0) {
 			uvcg_queue_cancel(queue, 0);
 			break;
 		}
 
-		/* Endpoint now owns the request */
+		/* The request is owned by  the endpoint / ready list. */
 		req = NULL;
-		video->req_int_count++;
 	}
 
 	if (!req)
@@ -581,8 +686,14 @@ uvcg_video_disable(struct uvc_video *video)
 		uvc_video_free_request(req->context, video->ep);
 	}
 
+	list_for_each_entry_safe(req, temp, &video->req_ready, list) {
+		list_del(&req->list);
+		uvc_video_free_request(req->context, video->ep);
+	}
+
 	INIT_LIST_HEAD(&video->ureqs);
 	INIT_LIST_HEAD(&video->req_free);
+	INIT_LIST_HEAD(&video->req_ready);
 	video->req_size = 0;
 	spin_unlock_irqrestore(&video->req_lock, flags);
 
@@ -636,7 +747,7 @@ int uvcg_video_enable(struct uvc_video *video)
 
 	video->req_int_count = 0;
 
-	queue_work(video->async_wq, &video->pump);
+	uvc_video_ep_queue_initial_requests(video);
 
 	return ret;
 }
@@ -649,6 +760,7 @@ int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc)
 	video->is_enabled = false;
 	INIT_LIST_HEAD(&video->ureqs);
 	INIT_LIST_HEAD(&video->req_free);
+	INIT_LIST_HEAD(&video->req_ready);
 	spin_lock_init(&video->req_lock);
 	INIT_WORK(&video->pump, uvcg_video_pump);
 
-- 
GitLab


From 984f20a0217df3b570a67bf2c0a457f5a128b884 Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Thu, 23 Nov 2023 15:34:03 +0700
Subject: [PATCH 0276/4076] MAINTAINERS: Mark VME subsystem as orphan

Martyn Welch lost his access to VME hardware [1]; and Manohar Vanga has been
MIA since early January 2014 (his last message was [2]). Martyn admitted
that the subsystem is basically orphan, so mark it as such. As a bonus,
add CREDITS entries for the former subsystem maintainers.

Link: https://lore.kernel.org/r/fe8ac0db-d6cc-41bc-b926-484b418e1720@collabora.com/ [1]
Link: https://lore.kernel.org/r/CAEktxaFL=3cmU4vZS2akiAR2vG-3d+9HwTZvBvf5JXuThHoOKg@mail.gmail.com/ [2]
Cc: Martyn Welch <martyn.welch@collabora.com>
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Acked-by: Martyn Welch <martyn@welchs.me.uk>
Link: https://lore.kernel.org/r/20231123083406.12129-2-bagasdotme@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 CREDITS     | 8 ++++++++
 MAINTAINERS | 5 +----
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/CREDITS b/CREDITS
index f33a33fd23717..ba6eb6274f8be 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3916,6 +3916,10 @@ S: 21513 Conradia Ct
 S: Cupertino, CA 95014
 S: USA
 
+N: Manohar Vanga
+E: manohar.vanga@gmail.com
+D: VME subsystem maintainer
+
 N: Thibaut Varène
 E: hacks+kernel@slashdirt.org
 W: http://hacks.slashdirt.org/
@@ -4016,6 +4020,10 @@ D: Fixes for the NE/2-driver
 D: Miscellaneous MCA-support
 D: Cleanup of the Config-files
 
+N: Martyn Welch
+E: martyn@welchs.me.uk
+D: VME subsystem maintainer
+
 N: Matt Welsh
 E: mdw@metalab.unc.edu
 W: http://www.cs.berkeley.edu/~mdw
diff --git a/MAINTAINERS b/MAINTAINERS
index ea790149af795..ff083d1200148 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23234,11 +23234,8 @@ F:	include/linux/vmalloc.h
 F:	mm/vmalloc.c
 
 VME SUBSYSTEM
-M:	Martyn Welch <martyn@welchs.me.uk>
-M:	Manohar Vanga <manohar.vanga@gmail.com>
-M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	linux-kernel@vger.kernel.org
-S:	Odd fixes
+S:	Orphan
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 F:	Documentation/driver-api/vme.rst
 F:	drivers/staging/vme_user/
-- 
GitLab


From 0428f6bda29d86fc49881bf8de80e806df045811 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 13 Nov 2023 11:59:04 -0800
Subject: [PATCH 0277/4076] Staging: rtl8192e: Rename variable bSendDELBA

Rename variable bSendDELBA to send_del_ba to fix checkpatch warning
Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231113195910.8423-2-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 4af8055d24895..c0058d2be6d1c 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -27,31 +27,31 @@ static u8 tx_ts_delete_ba(struct rtllib_device *ieee, struct tx_ts_record *pTxTs
 {
 	struct ba_record *admitted_ba = &pTxTs->TxAdmittedBARecord;
 	struct ba_record *pending_ba = &pTxTs->TxPendingBARecord;
-	u8 bSendDELBA = false;
+	u8 send_del_ba = false;
 
 	if (pending_ba->b_valid) {
 		deactivate_ba_entry(ieee, pending_ba);
-		bSendDELBA = true;
+		send_del_ba = true;
 	}
 
 	if (admitted_ba->b_valid) {
 		deactivate_ba_entry(ieee, admitted_ba);
-		bSendDELBA = true;
+		send_del_ba = true;
 	}
-	return bSendDELBA;
+	return send_del_ba;
 }
 
 static u8 rx_ts_delete_ba(struct rtllib_device *ieee, struct rx_ts_record *ts)
 {
 	struct ba_record *ba = &ts->rx_admitted_ba_record;
-	u8			bSendDELBA = false;
+	u8			send_del_ba = false;
 
 	if (ba->b_valid) {
 		deactivate_ba_entry(ieee, ba);
-		bSendDELBA = true;
+		send_del_ba = true;
 	}
 
-	return bSendDELBA;
+	return send_del_ba;
 }
 
 void rtllib_reset_ba_entry(struct ba_record *ba)
-- 
GitLab


From c1d2dc030365c7ce6641420a604f6fe734138da6 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 13 Nov 2023 11:59:05 -0800
Subject: [PATCH 0278/4076] Staging: rtl8192e: Rename variable
 bCurrentAMPDUEnable

Rename variable bCurrentAMPDUEnable to current_ampdu_enable to fix
checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231113195910.8423-3-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 4 ++--
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 6 +++---
 drivers/staging/rtl8192e/rtllib_tx.c      | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index c0058d2be6d1c..404f873455fc1 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -327,12 +327,12 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 
 	if (!ieee->current_network.qos_data.active ||
 	    !ieee->ht_info->current_ht_support ||
-	    !ieee->ht_info->bCurrentAMPDUEnable) {
+	    !ieee->ht_info->current_ampdu_enable) {
 		netdev_warn(ieee->dev,
 			    "reject to ADDBA_RSP as some capability is not ready(%d, %d, %d)\n",
 			    ieee->current_network.qos_data.active,
 			    ieee->ht_info->current_ht_support,
-			    ieee->ht_info->bCurrentAMPDUEnable);
+			    ieee->ht_info->current_ampdu_enable);
 		reason_code = DELBA_REASON_UNKNOWN_BA;
 		goto OnADDBARsp_Reject;
 	}
diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index f8eb4d553fe02..a4fe72943b367 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -112,7 +112,7 @@ struct rt_hi_throughput {
 	u8 bCurrent_AMSDU_Support;
 	u16 nCurrent_AMSDU_MaxSize;
 	u8 bAMPDUEnable;
-	u8 bCurrentAMPDUEnable;
+	u8 current_ampdu_enable;
 	u8 AMPDU_Factor;
 	u8 CurrentAMPDUFactor;
 	u8 MPDU_Density;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index e607bccc079a5..d5520cc82d229 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -514,12 +514,12 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	else
 		ht_info->nCurrent_AMSDU_MaxSize = ht_info->nAMSDU_MaxSize;
 
-	ht_info->bCurrentAMPDUEnable = ht_info->bAMPDUEnable;
+	ht_info->current_ampdu_enable = ht_info->bAMPDUEnable;
 	if (ieee->rtllib_ap_sec_type &&
 	    (ieee->rtllib_ap_sec_type(ieee) & (SEC_ALG_WEP | SEC_ALG_TKIP))) {
 		if ((ht_info->IOTPeer == HT_IOT_PEER_ATHEROS) ||
 		    (ht_info->IOTPeer == HT_IOT_PEER_UNKNOWN))
-			ht_info->bCurrentAMPDUEnable = false;
+			ht_info->current_ampdu_enable = false;
 	}
 
 	if (!ht_info->reg_rt2rt_aggregation) {
@@ -544,7 +544,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->current_mpdu_density = max_t(u8, ht_info->MPDU_Density,
 					      pPeerHTCap->MPDUDensity);
 	if (ht_info->iot_action & HT_IOT_ACT_TX_USE_AMSDU_8K) {
-		ht_info->bCurrentAMPDUEnable = false;
+		ht_info->current_ampdu_enable = false;
 		ht_info->ForcedAMSDUMode = HT_AGG_FORCE_ENABLE;
 	}
 	ht_info->cur_rx_reorder_enable = ht_info->reg_rx_reorder_enable;
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 9bf679438ad11..a99c3b3f867cc 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -288,7 +288,7 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 
 	if (!ieee->GetNmodeSupportBySecCfg(ieee->dev))
 		return;
-	if (ht_info->bCurrentAMPDUEnable) {
+	if (ht_info->current_ampdu_enable) {
 		if (!rtllib_get_ts(ieee, (struct ts_common_info **)(&pTxTs), hdr->addr1,
 			   skb->priority, TX_DIR, true)) {
 			netdev_info(ieee->dev, "%s: can't get TS\n", __func__);
-- 
GitLab


From 5989b863c682ac14f7c49e56a7031b1f12825ab6 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 13 Nov 2023 11:59:06 -0800
Subject: [PATCH 0279/4076] Staging: rtl8192e: Rename variable
 bAddBaReqInProgress

Rename variable bAddBaReqInProgress to add_ba_req_in_progress to fix
checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231113195910.8423-4-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 6 +++---
 drivers/staging/rtl8192e/rtl819x_TS.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 404f873455fc1..4d51c745e7f2a 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -344,7 +344,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 		goto OnADDBARsp_Reject;
 	}
 
-	ts->bAddBaReqInProgress = false;
+	ts->add_ba_req_in_progress = false;
 	pending_ba = &ts->TxPendingBARecord;
 	pAdmittedBA = &ts->TxAdmittedBARecord;
 
@@ -453,7 +453,7 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 		}
 
 		pTxTs->bUsingBa = false;
-		pTxTs->bAddBaReqInProgress = false;
+		pTxTs->add_ba_req_in_progress = false;
 		pTxTs->bAddBaReqDelayed = false;
 		del_timer_sync(&pTxTs->TsAddBaTimer);
 		tx_ts_delete_ba(ieee, pTxTs);
@@ -513,7 +513,7 @@ void rtllib_ba_setup_timeout(struct timer_list *t)
 	struct tx_ts_record *pTxTs = from_timer(pTxTs, t,
 					      TxPendingBARecord.timer);
 
-	pTxTs->bAddBaReqInProgress = false;
+	pTxTs->add_ba_req_in_progress = false;
 	pTxTs->bAddBaReqDelayed = true;
 	pTxTs->TxPendingBARecord.b_valid = false;
 }
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index fff36315f1744..276a50f987810 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -27,7 +27,7 @@ struct tx_ts_record {
 	u16				TxCurSeq;
 	struct ba_record TxPendingBARecord;
 	struct ba_record TxAdmittedBARecord;
-	u8				bAddBaReqInProgress;
+	u8				add_ba_req_in_progress;
 	u8				bAddBaReqDelayed;
 	u8				bUsingBa;
 	u8				bDisable_AddBa;
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 3206fdb3e65ab..62414e7b88797 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -101,7 +101,7 @@ static void ResetTxTsEntry(struct tx_ts_record *ts)
 {
 	ResetTsCommonInfo(&ts->TsCommonInfo);
 	ts->TxCurSeq = 0;
-	ts->bAddBaReqInProgress = false;
+	ts->add_ba_req_in_progress = false;
 	ts->bAddBaReqDelayed = false;
 	ts->bUsingBa = false;
 	ts->bDisable_AddBa = false;
@@ -433,8 +433,8 @@ void RemoveAllTS(struct rtllib_device *ieee)
 
 void TsStartAddBaProcess(struct rtllib_device *ieee, struct tx_ts_record *pTxTS)
 {
-	if (pTxTS->bAddBaReqInProgress == false) {
-		pTxTS->bAddBaReqInProgress = true;
+	if (pTxTS->add_ba_req_in_progress == false) {
+		pTxTS->add_ba_req_in_progress = true;
 
 		if (pTxTS->bAddBaReqDelayed) {
 			netdev_dbg(ieee->dev, "Start ADDBA after 60 sec!!\n");
-- 
GitLab


From 88b1b5ef720f397e5836157dfd38510d10682f08 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 13 Nov 2023 11:59:07 -0800
Subject: [PATCH 0280/4076] Staging: rtl8192e: Rename variable bAddBaReqDelayed

Rename variable bAddBaReqDelayed to add_ba_req_delayed to fix
checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231113195910.8423-5-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 8 ++++----
 drivers/staging/rtl8192e/rtl819x_TS.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 4d51c745e7f2a..631c857c508fe 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -368,7 +368,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 
 	if (*status_code == ADDBA_STATUS_SUCCESS) {
 		if (pBaParamSet->field.ba_policy == BA_POLICY_DELAYED) {
-			ts->bAddBaReqDelayed = true;
+			ts->add_ba_req_delayed = true;
 			deactivate_ba_entry(ieee, pAdmittedBA);
 			reason_code = DELBA_REASON_END_BA;
 			goto OnADDBARsp_Reject;
@@ -381,7 +381,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 		deactivate_ba_entry(ieee, pAdmittedBA);
 		activate_ba_entry(pAdmittedBA, *pBaTimeoutVal);
 	} else {
-		ts->bAddBaReqDelayed = true;
+		ts->add_ba_req_delayed = true;
 		ts->bDisable_AddBa = true;
 		reason_code = DELBA_REASON_END_BA;
 		goto OnADDBARsp_Reject;
@@ -454,7 +454,7 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 
 		pTxTs->bUsingBa = false;
 		pTxTs->add_ba_req_in_progress = false;
-		pTxTs->bAddBaReqDelayed = false;
+		pTxTs->add_ba_req_delayed = false;
 		del_timer_sync(&pTxTs->TsAddBaTimer);
 		tx_ts_delete_ba(ieee, pTxTs);
 	}
@@ -514,7 +514,7 @@ void rtllib_ba_setup_timeout(struct timer_list *t)
 					      TxPendingBARecord.timer);
 
 	pTxTs->add_ba_req_in_progress = false;
-	pTxTs->bAddBaReqDelayed = true;
+	pTxTs->add_ba_req_delayed = true;
 	pTxTs->TxPendingBARecord.b_valid = false;
 }
 
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index 276a50f987810..0bf73b6257080 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -28,7 +28,7 @@ struct tx_ts_record {
 	struct ba_record TxPendingBARecord;
 	struct ba_record TxAdmittedBARecord;
 	u8				add_ba_req_in_progress;
-	u8				bAddBaReqDelayed;
+	u8				add_ba_req_delayed;
 	u8				bUsingBa;
 	u8				bDisable_AddBa;
 	struct timer_list		TsAddBaTimer;
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 62414e7b88797..3a1bb512ca69c 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -102,7 +102,7 @@ static void ResetTxTsEntry(struct tx_ts_record *ts)
 	ResetTsCommonInfo(&ts->TsCommonInfo);
 	ts->TxCurSeq = 0;
 	ts->add_ba_req_in_progress = false;
-	ts->bAddBaReqDelayed = false;
+	ts->add_ba_req_delayed = false;
 	ts->bUsingBa = false;
 	ts->bDisable_AddBa = false;
 	rtllib_reset_ba_entry(&ts->TxAdmittedBARecord);
@@ -436,7 +436,7 @@ void TsStartAddBaProcess(struct rtllib_device *ieee, struct tx_ts_record *pTxTS)
 	if (pTxTS->add_ba_req_in_progress == false) {
 		pTxTS->add_ba_req_in_progress = true;
 
-		if (pTxTS->bAddBaReqDelayed) {
+		if (pTxTS->add_ba_req_delayed) {
 			netdev_dbg(ieee->dev, "Start ADDBA after 60 sec!!\n");
 			mod_timer(&pTxTS->TsAddBaTimer, jiffies +
 				  msecs_to_jiffies(TS_ADDBA_DELAY));
-- 
GitLab


From 5ed1ffa35545b437fdfb4b9118dd94f95c252c5c Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 13 Nov 2023 11:59:08 -0800
Subject: [PATCH 0281/4076] Staging: rtl8192e: Rename variable bUsingBa

Rename variable bUsingBa to using_ba to fix
checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231113195910.8423-6-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 2 +-
 drivers/staging/rtl8192e/rtl819x_TS.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib_tx.c      | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 631c857c508fe..cbf74cac0599f 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -452,7 +452,7 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 			return -1;
 		}
 
-		pTxTs->bUsingBa = false;
+		pTxTs->using_ba = false;
 		pTxTs->add_ba_req_in_progress = false;
 		pTxTs->add_ba_req_delayed = false;
 		del_timer_sync(&pTxTs->TsAddBaTimer);
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index 0bf73b6257080..289314de1193f 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -29,7 +29,7 @@ struct tx_ts_record {
 	struct ba_record TxAdmittedBARecord;
 	u8				add_ba_req_in_progress;
 	u8				add_ba_req_delayed;
-	u8				bUsingBa;
+	u8				using_ba;
 	u8				bDisable_AddBa;
 	struct timer_list		TsAddBaTimer;
 	u8				num;
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 3a1bb512ca69c..867889dc4fb6a 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -103,7 +103,7 @@ static void ResetTxTsEntry(struct tx_ts_record *ts)
 	ts->TxCurSeq = 0;
 	ts->add_ba_req_in_progress = false;
 	ts->add_ba_req_delayed = false;
-	ts->bUsingBa = false;
+	ts->using_ba = false;
 	ts->bDisable_AddBa = false;
 	rtllib_reset_ba_entry(&ts->TxAdmittedBARecord);
 	rtllib_reset_ba_entry(&ts->TxPendingBARecord);
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index a99c3b3f867cc..cee3b8855c0e1 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -304,10 +304,10 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 				TsStartAddBaProcess(ieee, pTxTs);
 			}
 			goto FORCED_AGG_SETTING;
-		} else if (!pTxTs->bUsingBa) {
+		} else if (!pTxTs->using_ba) {
 			if (SN_LESS(pTxTs->TxAdmittedBARecord.ba_start_seq_ctrl.field.seq_num,
 				    (pTxTs->TxCurSeq + 1) % 4096))
-				pTxTs->bUsingBa = true;
+				pTxTs->using_ba = true;
 			else
 				goto FORCED_AGG_SETTING;
 		}
-- 
GitLab


From 4c4fdf26594a5eaf752832ef2150861c17f3b7db Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 13 Nov 2023 11:59:09 -0800
Subject: [PATCH 0282/4076] Staging: rtl8192e: Rename variable
 bOverwritePending

Rename variable bOverwritePending to overwrite_pending to fix
checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231113195910.8423-7-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 4 ++--
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index cbf74cac0599f..3502f27342e3f 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -462,11 +462,11 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 }
 
 void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
-			   u8 policy, u8	bOverwritePending)
+			   u8 policy, u8	overwrite_pending)
 {
 	struct ba_record *ba = &ts->TxPendingBARecord;
 
-	if (ba->b_valid && !bOverwritePending)
+	if (ba->b_valid && !overwrite_pending)
 		return;
 
 	deactivate_ba_entry(ieee, ba);
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index d2cf3cfaaaba3..adaab56a9fb17 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1788,7 +1788,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb);
 int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb);
 int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb);
 void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
-			   u8 policy, u8 bOverwritePending);
+			   u8 policy, u8 overwrite_pending);
 void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
 			   struct ts_common_info *pTsCommonInfo,
 			   enum tr_select TxRxSelect);
-- 
GitLab


From 23c2c8cf4f90fa1709febe4d543be000ff69f4e8 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 13 Nov 2023 11:59:10 -0800
Subject: [PATCH 0283/4076] Staging: rtl8192e: Rename variable bDisable_AddBa

Rename variable bDisable_AddBa to disable_add_ba to fix
checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231113195910.8423-8-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 2 +-
 drivers/staging/rtl8192e/rtl819x_TS.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib_tx.c      | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 3502f27342e3f..b52b42ac0fc4f 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -382,7 +382,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 		activate_ba_entry(pAdmittedBA, *pBaTimeoutVal);
 	} else {
 		ts->add_ba_req_delayed = true;
-		ts->bDisable_AddBa = true;
+		ts->disable_add_ba = true;
 		reason_code = DELBA_REASON_END_BA;
 		goto OnADDBARsp_Reject;
 	}
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index 289314de1193f..742f575ea6378 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -30,7 +30,7 @@ struct tx_ts_record {
 	u8				add_ba_req_in_progress;
 	u8				add_ba_req_delayed;
 	u8				using_ba;
-	u8				bDisable_AddBa;
+	u8				disable_add_ba;
 	struct timer_list		TsAddBaTimer;
 	u8				num;
 };
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 867889dc4fb6a..41c1e768348a5 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -104,7 +104,7 @@ static void ResetTxTsEntry(struct tx_ts_record *ts)
 	ts->add_ba_req_in_progress = false;
 	ts->add_ba_req_delayed = false;
 	ts->using_ba = false;
-	ts->bDisable_AddBa = false;
+	ts->disable_add_ba = false;
 	rtllib_reset_ba_entry(&ts->TxAdmittedBARecord);
 	rtllib_reset_ba_entry(&ts->TxPendingBARecord);
 }
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index cee3b8855c0e1..1da098f5b84ca 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -300,7 +300,7 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 				;
 			} else if (tcb_desc->bdhcp == 1) {
 				;
-			} else if (!pTxTs->bDisable_AddBa) {
+			} else if (!pTxTs->disable_add_ba) {
 				TsStartAddBaProcess(ieee, pTxTs);
 			}
 			goto FORCED_AGG_SETTING;
-- 
GitLab


From 0d1bf38752afef6e46f73eef1ad32d47e8019962 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:51:05 +0100
Subject: [PATCH 0284/4076] staging: rtl8192e: Remove unused return value of
 rtl92e_set_channel()

Remove unused return value of rtl92e_set_channel().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/0c0e7c72a10731ae7ed49c8161136b0f0b63d7a0.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 12 ++++++------
 drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h |  2 +-
 drivers/staging/rtl8192e/rtl8192e/rtl_core.h   |  2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c
index 4d12d73850415..e1bd4d67e862b 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c
@@ -671,16 +671,16 @@ static void _rtl92e_phy_switch_channel_work_item(struct net_device *dev)
 	_rtl92e_phy_switch_channel(dev, priv->chan);
 }
 
-u8 rtl92e_set_channel(struct net_device *dev, u8 channel)
+void rtl92e_set_channel(struct net_device *dev, u8 channel)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
 
 	if (!priv->up) {
 		netdev_err(dev, "%s(): Driver is not initialized\n", __func__);
-		return false;
+		return;
 	}
 	if (priv->sw_chnl_in_progress)
-		return false;
+		return;
 
 	switch (priv->rtllib->mode) {
 	case WIRELESS_MODE_B:
@@ -688,7 +688,7 @@ u8 rtl92e_set_channel(struct net_device *dev, u8 channel)
 			netdev_warn(dev,
 				    "Channel %d not available in 802.11b.\n",
 				    channel);
-			return false;
+			return;
 		}
 		break;
 	case WIRELESS_MODE_G:
@@ -697,7 +697,7 @@ u8 rtl92e_set_channel(struct net_device *dev, u8 channel)
 			netdev_warn(dev,
 				    "Channel %d not available in 802.11g.\n",
 				    channel);
-			return false;
+			return;
 		}
 		break;
 	}
@@ -714,7 +714,7 @@ u8 rtl92e_set_channel(struct net_device *dev, u8 channel)
 	if (priv->up)
 		_rtl92e_phy_switch_channel_work_item(dev);
 	priv->sw_chnl_in_progress = false;
-	return true;
+	return;
 }
 
 static void _rtl92e_cck_tx_power_track_bw_switch_tssi(struct net_device *dev)
diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h
index 6c4c33ded6a94..ff4b4004b0d00 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h
@@ -41,7 +41,7 @@ void rtl92e_get_tx_power(struct net_device *dev);
 void rtl92e_set_tx_power(struct net_device *dev, u8 channel);
 u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath);
 
-u8 rtl92e_set_channel(struct net_device *dev, u8 channel);
+void rtl92e_set_channel(struct net_device *dev, u8 channel);
 void rtl92e_set_bw_mode(struct net_device *dev,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset);
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
index a4afbf3e934d5..9b0be6dff6279 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
@@ -228,7 +228,7 @@ struct r8192_priv {
 	struct rt_stats stats;
 	struct iw_statistics			wstats;
 
-	u8 (*rf_set_chan)(struct net_device *dev, u8 ch);
+	void (*rf_set_chan)(struct net_device *dev, u8 ch);
 
 	struct rx_desc *rx_ring;
 	struct sk_buff	*rx_buf[MAX_RX_COUNT];
-- 
GitLab


From 468403351369de2615a7690b378aff2fc7aa4350 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:51:11 +0100
Subject: [PATCH 0285/4076] staging: rtl8192e: Change parameter "ch" of
 set_chan() to u8

Change parameter "ch" of set_chan() to u8 to combine functions in the
following patch.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/4a76c0e2384d67410d383fdf860d0e0859555d1e.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h            | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 995daab906c93..98b25768f6141 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -226,7 +226,7 @@ static void _rtl92e_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	netdev_info(dev, "TXTIMEOUT");
 }
 
-static void _rtl92e_set_chan(struct net_device *dev, short ch)
+static void _rtl92e_set_chan(struct net_device *dev, u8 ch)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
 
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index adaab56a9fb17..1d0878d1f6965 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1469,7 +1469,7 @@ struct rtllib_device {
 	 * This function can sleep. the driver should ensure
 	 * the radio has been switched before return.
 	 */
-	void (*set_chan)(struct net_device *dev, short ch);
+	void (*set_chan)(struct net_device *dev, u8 ch);
 
 	/* indicate the driver that the link state is changed
 	 * for example it may indicate the card is associated now.
-- 
GitLab


From 7260ce3cee8cf13ffa0f526e7e4e6a7c2db8ec1e Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:51:18 +0100
Subject: [PATCH 0286/4076] staging: rtl8192e: Unwind pointer to pointer to
 rtl92e_set_channel()

Replace pointer to function to pointer to rtl92e_set_channel() with
pointer to rtl92e_set_channel(). This increases readability of the code.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/a96bac1f34e669a3b2fc4940a0a2d850564a5975.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 13 +------------
 drivers/staging/rtl8192e/rtl8192e/rtl_core.h |  2 --
 2 files changed, 1 insertion(+), 14 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 98b25768f6141..2789f428e4f94 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -226,16 +226,6 @@ static void _rtl92e_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	netdev_info(dev, "TXTIMEOUT");
 }
 
-static void _rtl92e_set_chan(struct net_device *dev, u8 ch)
-{
-	struct r8192_priv *priv = rtllib_priv(dev);
-
-	priv->chan = ch;
-
-	if (priv->rf_set_chan)
-		priv->rf_set_chan(dev, priv->chan);
-}
-
 static void _rtl92e_update_cap(struct net_device *dev, u16 cap)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
@@ -685,7 +675,7 @@ static void _rtl92e_init_priv_handler(struct net_device *dev)
 	struct r8192_priv *priv = rtllib_priv(dev);
 
 	priv->rtllib->softmac_hard_start_xmit	= _rtl92e_hard_start_xmit;
-	priv->rtllib->set_chan			= _rtl92e_set_chan;
+	priv->rtllib->set_chan			= rtl92e_set_channel;
 	priv->rtllib->link_change		= rtl92e_link_change;
 	priv->rtllib->softmac_data_hard_start_xmit = _rtl92e_hard_data_xmit;
 	priv->rtllib->check_nic_enough_desc	= _rtl92e_check_nic_enough_desc;
@@ -694,7 +684,6 @@ static void _rtl92e_init_priv_handler(struct net_device *dev)
 	priv->rtllib->set_wireless_mode		= rtl92e_set_wireless_mode;
 	priv->rtllib->leisure_ps_leave		= rtl92e_leisure_ps_leave;
 	priv->rtllib->set_bw_mode_handler	= rtl92e_set_bw_mode;
-	priv->rf_set_chan			= rtl92e_set_channel;
 
 	priv->rtllib->sta_wake_up = rtl92e_hw_wakeup;
 	priv->rtllib->enter_sleep_state = rtl92e_enter_sleep;
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
index 9b0be6dff6279..348df71e122e9 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
@@ -228,8 +228,6 @@ struct r8192_priv {
 	struct rt_stats stats;
 	struct iw_statistics			wstats;
 
-	void (*rf_set_chan)(struct net_device *dev, u8 ch);
-
 	struct rx_desc *rx_ring;
 	struct sk_buff	*rx_buf[MAX_RX_COUNT];
 	dma_addr_t	rx_ring_dma;
-- 
GitLab


From 589599d4e91763cff1e58b2526c3e1aa05895bde Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:51:25 +0100
Subject: [PATCH 0287/4076] staging: rtl8192e: Remove equation that results in
 constant for chnl_plan

Remove equation for chnl_plan as the last line sets chnl_plan to a
constant.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/d6fbe3d2297d1d5502b183785f14df51a81e3331.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index e93394c51264b..44898e0be21c5 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -387,23 +387,15 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev)
 
 	rtl92e_init_adaptive_rate(dev);
 
-	priv->chnl_plan = priv->eeprom_chnl_plan;
-
 	switch (priv->eeprom_customer_id) {
 	case EEPROM_CID_NetCore:
 		priv->customer_id = RT_CID_819X_NETCORE;
 		break;
 	case EEPROM_CID_TOSHIBA:
 		priv->customer_id = RT_CID_TOSHIBA;
-		if (priv->eeprom_chnl_plan & 0x80)
-			priv->chnl_plan = priv->eeprom_chnl_plan & 0x7f;
-		else
-			priv->chnl_plan = 0x0;
 		break;
 	}
 
-	if (priv->chnl_plan > CHANNEL_PLAN_LEN - 1)
-		priv->chnl_plan = 0;
 	priv->chnl_plan = COUNTRY_CODE_WORLD_WIDE_13;
 
 	if (priv->eeprom_vid == 0x1186 &&  priv->eeprom_did == 0x3304)
-- 
GitLab


From b6806a4b17a1bd77626c24ab050dfabe82ed170d Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:51:34 +0100
Subject: [PATCH 0288/4076] staging: rtl8192e: Remove constant variable
 chnl_plan

Remove constant variable chnl_plan and replace it with its constant.
Remove equation that limits maximum value of chnl_plan as it is always
false.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/e46f16227877fe9853c9d15992e7fd27a0ceeae6.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 --
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c   | 7 +------
 drivers/staging/rtl8192e/rtl8192e/rtl_core.h   | 1 -
 3 files changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index 44898e0be21c5..9b51deba149b8 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -396,8 +396,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev)
 		break;
 	}
 
-	priv->chnl_plan = COUNTRY_CODE_WORLD_WIDE_13;
-
 	if (priv->eeprom_vid == 0x1186 &&  priv->eeprom_did == 0x3304)
 		priv->rtllib->bSupportRemoteWakeUp = true;
 	else
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 2789f428e4f94..68bd035002675 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -795,13 +795,8 @@ static short _rtl92e_get_channel_map(struct net_device *dev)
 
 	struct r8192_priv *priv = rtllib_priv(dev);
 
-	if (priv->chnl_plan >= COUNTRY_CODE_MAX) {
-		netdev_info(dev,
-			    "rtl819x_init:Error channel plan! Set to default.\n");
-		priv->chnl_plan = COUNTRY_CODE_FCC;
-	}
 	dot11d_init(priv->rtllib);
-	dot11d_channel_map(priv->chnl_plan, priv->rtllib);
+	dot11d_channel_map(COUNTRY_CODE_WORLD_WIDE_13, priv->rtllib);
 	for (i = 1; i <= 11; i++)
 		(priv->rtllib->active_channel_map)[i] = 1;
 	(priv->rtllib->active_channel_map)[12] = 2;
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
index 348df71e122e9..addaa1eb39eef 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
@@ -310,7 +310,6 @@ struct r8192_priv {
 
 	bool tx_pwr_data_read_from_eeprom;
 
-	u16 chnl_plan;
 	u8 hw_rf_off_action;
 
 	bool rf_change_in_progress;
-- 
GitLab


From d77ceba0a411e52b18c5b28b3783d11683753365 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:51:42 +0100
Subject: [PATCH 0289/4076] staging: rtl8192e: Remove unused variable
 eeprom_chnl_plan

Remove unused variable eeprom_chnl_plan.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/ffc592edd61332d2d8f9b0da68fc956d76e68fe0.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 --
 drivers/staging/rtl8192e/rtl8192e/rtl_core.h   | 1 -
 2 files changed, 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index 9b51deba149b8..8fe4c03b19c1b 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -261,7 +261,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev)
 		priv->eeprom_customer_id = usValue & 0xff;
 		usValue = rtl92e_eeprom_read(dev,
 					     EEPROM_ICVersion_ChannelPlan >> 1);
-		priv->eeprom_chnl_plan = usValue & 0xff;
 		IC_Version = (usValue & 0xff00) >> 8;
 
 		ICVer8192 = IC_Version & 0xf;
@@ -283,7 +282,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev)
 		priv->eeprom_vid = 0;
 		priv->eeprom_did = 0;
 		priv->eeprom_customer_id = 0;
-		priv->eeprom_chnl_plan = 0;
 	}
 
 	if (!priv->autoload_fail_flag) {
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
index addaa1eb39eef..e7b331c4661c7 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
@@ -284,7 +284,6 @@ struct r8192_priv {
 	u16 eeprom_vid;
 	u16 eeprom_did;
 	u8 eeprom_customer_id;
-	u16 eeprom_chnl_plan;
 
 	u8 eeprom_tx_pwr_level_cck[14];
 	u8 eeprom_tx_pwr_level_ofdm24g[14];
-- 
GitLab


From 89d132c7b0463ee5a704aae787cb66bdd08d03ec Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:51:48 +0100
Subject: [PATCH 0290/4076] staging: rtl8192e: Remove equation to check limits
 of channel

channel_plan is constant COUNTRY_CODE_WORLD_WIDE_13. Remove equation to
check limits of channel as those are always in limit.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/1f91cf8145b304b09b37734a2a504da394833378.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index d0b7332645be3..bb7b5c793b267 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -51,7 +51,7 @@ EXPORT_SYMBOL(dot11d_init);
 
 void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee)
 {
-	int i, max_chan = 14, min_chan = 1;
+	int i;
 
 	ieee->global_domain = false;
 
@@ -59,9 +59,6 @@ void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee)
 		memset(GET_DOT11D_INFO(ieee)->channel_map, 0,
 		       sizeof(GET_DOT11D_INFO(ieee)->channel_map));
 		for (i = 0; i < channel_array[channel_plan].len; i++) {
-			if (channel_array[channel_plan].channel[i] < min_chan ||
-			    channel_array[channel_plan].channel[i] > max_chan)
-				break;
 			GET_DOT11D_INFO(ieee)->channel_map[channel_array
 					[channel_plan].channel[i]] = 1;
 		}
-- 
GitLab


From 7e655d4a801d7bc0eb146c061dc784a8747bf82e Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:51:54 +0100
Subject: [PATCH 0291/4076] staging: rtl8192e: Remove check if
 channel_array[channel_plan].len != 0

channel_plan is constant COUNTRY_CODE_WORLD_WIDE_13. Remove equation to
check length of array as it is always not 0.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/0cfcc32a06033908c469ef0273de2485dbfd6b82.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index bb7b5c793b267..b515008045bd9 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -55,13 +55,11 @@ void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee)
 
 	ieee->global_domain = false;
 
-	if (channel_array[channel_plan].len != 0) {
-		memset(GET_DOT11D_INFO(ieee)->channel_map, 0,
-		       sizeof(GET_DOT11D_INFO(ieee)->channel_map));
-		for (i = 0; i < channel_array[channel_plan].len; i++) {
-			GET_DOT11D_INFO(ieee)->channel_map[channel_array
-					[channel_plan].channel[i]] = 1;
-		}
+	memset(GET_DOT11D_INFO(ieee)->channel_map, 0,
+	       sizeof(GET_DOT11D_INFO(ieee)->channel_map));
+	for (i = 0; i < channel_array[channel_plan].len; i++) {
+		GET_DOT11D_INFO(ieee)->channel_map[channel_array
+				[channel_plan].channel[i]] = 1;
 	}
 
 	switch (channel_plan) {
-- 
GitLab


From 0bdd71630a51b4f230a0df86ad9f76a63f713f59 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:52:01 +0100
Subject: [PATCH 0292/4076] staging: rtl8192e: Remove switch for a constant in
 dot11d_channel_map()

Remove switch for a constant in dot11d_channel_map() as the result will
always be the same.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/d81caa0894bdaaca471010cb3512f3459a2e7df4.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 21 +++------------------
 1 file changed, 3 insertions(+), 18 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index b515008045bd9..37106fd54f000 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -62,24 +62,9 @@ void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee)
 				[channel_plan].channel[i]] = 1;
 	}
 
-	switch (channel_plan) {
-	case COUNTRY_CODE_GLOBAL_DOMAIN:
-		ieee->global_domain = true;
-		for (i = 12; i <= 14; i++)
-			GET_DOT11D_INFO(ieee)->channel_map[i] = 2;
-		ieee->bss_start_channel = 10;
-		break;
-
-	case COUNTRY_CODE_WORLD_WIDE_13:
-		for (i = 12; i <= 13; i++)
-			GET_DOT11D_INFO(ieee)->channel_map[i] = 2;
-		ieee->bss_start_channel = 10;
-		break;
-
-	default:
-		ieee->bss_start_channel = 1;
-		break;
-	}
+	for (i = 12; i <= 13; i++)
+		GET_DOT11D_INFO(ieee)->channel_map[i] = 2;
+	ieee->bss_start_channel = 10;
 }
 EXPORT_SYMBOL(dot11d_channel_map);
 
-- 
GitLab


From bcccdf447e7edc373e48426518cf6ad65a48d234 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sat, 18 Nov 2023 09:52:08 +0100
Subject: [PATCH 0293/4076] staging: rtl8192e: Remove constant index from
 channel_array[]

Used index of channel_array[] is always COUNTRY_CODE_WORLD_WIDE_13. Remove
index and store only used entry in channel_array. This shortens the code
and increases readability.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/379293f2b48d176aaafb023d36aac9bb057f67c7.1700296319.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c            | 31 +++-----------------
 drivers/staging/rtl8192e/dot11d.h            |  2 +-
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c |  2 +-
 3 files changed, 6 insertions(+), 29 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index 37106fd54f000..fdc39e6e7abbe 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -12,28 +12,7 @@ struct channel_list {
 	u8      len;
 };
 
-static struct channel_list channel_array[] = {
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 36, 40, 44, 48, 52, 56, 60, 64,
-	  149, 153, 157, 161, 165}, 24},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11}, 11},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 36, 40, 44, 48, 52, 56,
-	  60, 64}, 21},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 36, 40, 44, 48, 52,
-	  56, 60, 64}, 22},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 36, 40, 44, 48, 52,
-	  56, 60, 64}, 22},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 36, 40, 44, 48, 52,
-	  56, 60, 64}, 22},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 36, 40, 44, 48, 52,
-	 56, 60, 64}, 22},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14}, 14},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13},
-	{{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 36, 40, 44, 48, 52,
-	  56, 60, 64}, 21}
-};
+static struct channel_list channel_array = {{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13};
 
 void dot11d_init(struct rtllib_device *ieee)
 {
@@ -49,7 +28,7 @@ void dot11d_init(struct rtllib_device *ieee)
 }
 EXPORT_SYMBOL(dot11d_init);
 
-void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee)
+void dot11d_channel_map(struct rtllib_device *ieee)
 {
 	int i;
 
@@ -57,10 +36,8 @@ void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee)
 
 	memset(GET_DOT11D_INFO(ieee)->channel_map, 0,
 	       sizeof(GET_DOT11D_INFO(ieee)->channel_map));
-	for (i = 0; i < channel_array[channel_plan].len; i++) {
-		GET_DOT11D_INFO(ieee)->channel_map[channel_array
-				[channel_plan].channel[i]] = 1;
-	}
+	for (i = 0; i < channel_array.len; i++)
+		GET_DOT11D_INFO(ieee)->channel_map[channel_array.channel[i]] = 1;
 
 	for (i = 12; i <= 13; i++)
 		GET_DOT11D_INFO(ieee)->channel_map[i] = 2;
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 6d2b93acfa431..78d1ca1e7743c 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -75,7 +75,7 @@ static inline void RESET_CIE_WATCHDOG(struct rtllib_device *__ieee_dev)
 #define UPDATE_CIE_WATCHDOG(__ieee_dev) (++GET_CIE_WATCHDOG(__ieee_dev))
 
 void dot11d_init(struct rtllib_device *dev);
-void dot11d_channel_map(u8 channel_plan, struct rtllib_device *ieee);
+void dot11d_channel_map(struct rtllib_device *ieee);
 void dot11d_reset(struct rtllib_device *dev);
 void dot11d_update_country(struct rtllib_device *dev, u8 *address,
 			   u16 country_len, u8 *country);
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 68bd035002675..4b842a1789c25 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -796,7 +796,7 @@ static short _rtl92e_get_channel_map(struct net_device *dev)
 	struct r8192_priv *priv = rtllib_priv(dev);
 
 	dot11d_init(priv->rtllib);
-	dot11d_channel_map(COUNTRY_CODE_WORLD_WIDE_13, priv->rtllib);
+	dot11d_channel_map(priv->rtllib);
 	for (i = 1; i <= 11; i++)
 		(priv->rtllib->active_channel_map)[i] = 1;
 	(priv->rtllib->active_channel_map)[12] = 2;
-- 
GitLab


From db295ab87c909a32f416b29194a36f1cab538b38 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:14:36 +0100
Subject: [PATCH 0294/4076] staging: rtl8192e: Remove unexecuted
 rtllib_extract_country_ie()

Variable "enabled" is initialized to false and never changed. Therefore
IS_DOT11D_ENABLE(ieee) returns always false. Because of this all code in
rtllib_extract_country_ie() is never executed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/7b88c62d3cc5c3fb670b5448c7381c7c099b3518.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_rx.c | 31 ----------------------------
 1 file changed, 31 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index ecaa4dec3f944..d9517dbc5593b 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -1663,35 +1663,6 @@ static const char *get_info_element_string(u16 id)
 	}
 }
 
-static inline void rtllib_extract_country_ie(
-	struct rtllib_device *ieee,
-	struct rtllib_info_element *info_element,
-	struct rtllib_network *network,
-	u8 *addr2)
-{
-	if (IS_DOT11D_ENABLE(ieee)) {
-		if (info_element->len != 0) {
-			memcpy(network->CountryIeBuf, info_element->data,
-			       info_element->len);
-			network->CountryIeLen = info_element->len;
-
-			if (!IS_COUNTRY_IE_VALID(ieee)) {
-				if (rtllib_act_scanning(ieee, false) &&
-				    ieee->FirstIe_InScan)
-					netdev_info(ieee->dev,
-						    "Received beacon CountryIE, SSID: <%s>\n",
-						    network->ssid);
-				dot11d_update_country(ieee, addr2,
-						       info_element->len,
-						       info_element->data);
-			}
-		}
-
-		if (IS_EQUAL_CIE_SRC(ieee, addr2))
-			UPDATE_CIE_WATCHDOG(ieee);
-	}
-}
-
 static void rtllib_parse_mife_generic(struct rtllib_device *ieee,
 				      struct rtllib_info_element *info_element,
 				      struct rtllib_network *network,
@@ -2146,8 +2117,6 @@ int rtllib_parse_info_param(struct rtllib_device *ieee,
 		case MFIE_TYPE_COUNTRY:
 			netdev_dbg(ieee->dev, "MFIE_TYPE_COUNTRY: %d bytes\n",
 				   info_element->len);
-			rtllib_extract_country_ie(ieee, info_element, network,
-						  network->bssid);
 			break;
 /* TODO */
 		default:
-- 
GitLab


From f6b64c978890ec0f1951b55f1cbfd9f64fdf79fa Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:14:42 +0100
Subject: [PATCH 0295/4076] staging: rtl8192e: Remove unused function
 dot11d_update_country()

Remove unused function dot11d_update_country().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/364462eae2271f3925b362a439ec27d50dd899ef.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 44 -------------------------------
 drivers/staging/rtl8192e/dot11d.h |  2 --
 2 files changed, 46 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index fdc39e6e7abbe..fc65a63a4de6d 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -61,50 +61,6 @@ void dot11d_reset(struct rtllib_device *ieee)
 	RESET_CIE_WATCHDOG(ieee);
 }
 
-void dot11d_update_country(struct rtllib_device *dev, u8 *address,
-			   u16 country_len, u8 *country)
-{
-	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(dev);
-	u8 i, j, number_of_triples, max_channel_number;
-	struct chnl_txpow_triple *triple;
-
-	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
-	memset(dot11d_info->max_tx_power_list, 0xFF, MAX_CHANNEL_NUMBER + 1);
-	max_channel_number = 0;
-	number_of_triples = (country_len - 3) / 3;
-	triple = (struct chnl_txpow_triple *)(country + 3);
-	for (i = 0; i < number_of_triples; i++) {
-		if (max_channel_number >= triple->first_channel) {
-			netdev_info(dev->dev,
-				    "%s: Invalid country IE, skip it......1\n",
-				    __func__);
-			return;
-		}
-		if (MAX_CHANNEL_NUMBER < (triple->first_channel +
-		    triple->num_channels)) {
-			netdev_info(dev->dev,
-				    "%s: Invalid country IE, skip it......2\n",
-				    __func__);
-			return;
-		}
-
-		for (j = 0; j < triple->num_channels; j++) {
-			dot11d_info->channel_map[triple->first_channel + j] = 1;
-			dot11d_info->max_tx_power_list[triple->first_channel + j] =
-						 triple->max_tx_power;
-			max_channel_number = triple->first_channel + j;
-		}
-
-		triple = (struct chnl_txpow_triple *)((u8 *)triple + 3);
-	}
-
-	UPDATE_CIE_SRC(dev, address);
-
-	dot11d_info->country_len = country_len;
-	memcpy(dot11d_info->country_buffer, country, country_len);
-	dot11d_info->state = DOT11D_STATE_LEARNED;
-}
-
 void dot11d_scan_complete(struct rtllib_device *dev)
 {
 	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(dev);
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 78d1ca1e7743c..39bda2f94eed6 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -77,8 +77,6 @@ static inline void RESET_CIE_WATCHDOG(struct rtllib_device *__ieee_dev)
 void dot11d_init(struct rtllib_device *dev);
 void dot11d_channel_map(struct rtllib_device *ieee);
 void dot11d_reset(struct rtllib_device *dev);
-void dot11d_update_country(struct rtllib_device *dev, u8 *address,
-			   u16 country_len, u8 *country);
 void dot11d_scan_complete(struct rtllib_device *dev);
 
 #endif
-- 
GitLab


From b7bba314def8f4fb6c4ced6f25083e852146a5d3 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:14:51 +0100
Subject: [PATCH 0296/4076] staging: rtl8192e: Remove IS_DOT11D_ENABLE(ieee)

Variable "enabled" is initialized to false and never changed. Therefore
IS_DOT11D_ENABLE(ieee) returns always false. Remove dead code.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/9e737b2246e0b73c3ad84a4ee09f5e94bf778b3c.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c         |  2 --
 drivers/staging/rtl8192e/dot11d.h         |  4 ----
 drivers/staging/rtl8192e/rtllib_softmac.c | 20 --------------------
 3 files changed, 26 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index fc65a63a4de6d..9eb941326bc85 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -18,8 +18,6 @@ void dot11d_init(struct rtllib_device *ieee)
 {
 	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(ieee);
 
-	dot11d_info->enabled = false;
-
 	dot11d_info->state = DOT11D_STATE_NONE;
 	dot11d_info->country_len = 0;
 	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 39bda2f94eed6..c28067510653b 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -33,8 +33,6 @@ enum dot11d_state {
  */
 
 struct rt_dot11d_info {
-	bool enabled;
-
 	u16 country_len;
 	u8  country_buffer[MAX_IE_LEN];
 	u8  country_src_addr[6];
@@ -54,8 +52,6 @@ static inline void copy_mac_addr(unsigned char *des, unsigned char *src)
 #define GET_DOT11D_INFO(__ieee_dev)			\
 	 ((struct rt_dot11d_info *)((__ieee_dev)->dot11d_info))
 
-#define IS_DOT11D_ENABLE(__ieee_dev)			\
-	 (GET_DOT11D_INFO(__ieee_dev)->enabled)
 #define IS_COUNTRY_IE_VALID(__ieee_dev)			\
 	(GET_DOT11D_INFO(__ieee_dev)->country_len > 0)
 
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 42d652fe86013..08349f522c830 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -492,10 +492,6 @@ out:
 	ieee->actscanning = false;
 	ieee->sync_scan_hurryup = 0;
 
-	if (ieee->link_state >= MAC80211_LINKED) {
-		if (IS_DOT11D_ENABLE(ieee))
-			dot11d_scan_complete(ieee);
-	}
 	mutex_unlock(&ieee->scan_mutex);
 
 	ieee->be_scan_inprogress = false;
@@ -552,8 +548,6 @@ static void rtllib_softmac_scan_wq(void *data)
 	return;
 
 out:
-	if (IS_DOT11D_ENABLE(ieee))
-		dot11d_scan_complete(ieee);
 	ieee->current_network.channel = last_channel;
 
 out1:
@@ -609,10 +603,6 @@ static void rtllib_start_scan(struct rtllib_device *ieee)
 {
 	ieee->rtllib_ips_leave_wq(ieee->dev);
 
-	if (IS_DOT11D_ENABLE(ieee)) {
-		if (IS_COUNTRY_IE_VALID(ieee))
-			RESET_CIE_WATCHDOG(ieee);
-	}
 	if (ieee->softmac_features & IEEE_SOFTMAC_SCAN) {
 		if (ieee->scanning_continue == 0) {
 			ieee->actscanning = true;
@@ -625,10 +615,6 @@ static void rtllib_start_scan(struct rtllib_device *ieee)
 /* called with wx_mutex held */
 void rtllib_start_scan_syncro(struct rtllib_device *ieee)
 {
-	if (IS_DOT11D_ENABLE(ieee)) {
-		if (IS_COUNTRY_IE_VALID(ieee))
-			RESET_CIE_WATCHDOG(ieee);
-	}
 	ieee->sync_scan_hurryup = 0;
 	if (ieee->softmac_features & IEEE_SOFTMAC_SCAN)
 		rtllib_softmac_scan_syncro(ieee);
@@ -2090,10 +2076,6 @@ static void rtllib_start_bss(struct rtllib_device *ieee)
 {
 	unsigned long flags;
 
-	if (IS_DOT11D_ENABLE(ieee) && !IS_COUNTRY_IE_VALID(ieee)) {
-		if (!ieee->global_domain)
-			return;
-	}
 	/* check if we have already found the net we
 	 * are interested in (if any).
 	 * if not (we are disassociated and we are not
@@ -2128,8 +2110,6 @@ void rtllib_disassociate(struct rtllib_device *ieee)
 	if (ieee->softmac_features & IEEE_SOFTMAC_TX_QUEUE)
 		rtllib_reset_queue(ieee);
 
-	if (IS_DOT11D_ENABLE(ieee))
-		dot11d_reset(ieee);
 	ieee->link_state = MAC80211_NOLINK;
 	ieee->is_set_key = false;
 	ieee->wap_set = 0;
-- 
GitLab


From 2ce570f8d5dcb5cd6d2e92d14a6dd2182c04c719 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:14:56 +0100
Subject: [PATCH 0297/4076] staging: rtl8192e: Remove unused function
 dot11d_scan_complete()

Remove unused function dot11d_scan_complete().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/065a8223b80730360ee3223067ee612737e777a7.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 15 ---------------
 drivers/staging/rtl8192e/dot11d.h |  1 -
 2 files changed, 16 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index 9eb941326bc85..95fb56cb77fc6 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -59,18 +59,3 @@ void dot11d_reset(struct rtllib_device *ieee)
 	RESET_CIE_WATCHDOG(ieee);
 }
 
-void dot11d_scan_complete(struct rtllib_device *dev)
-{
-	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(dev);
-
-	switch (dot11d_info->state) {
-	case DOT11D_STATE_LEARNED:
-		dot11d_info->state = DOT11D_STATE_DONE;
-		break;
-	case DOT11D_STATE_DONE:
-		dot11d_reset(dev);
-		break;
-	case DOT11D_STATE_NONE:
-		break;
-	}
-}
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index c28067510653b..9e8328af887cc 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -73,6 +73,5 @@ static inline void RESET_CIE_WATCHDOG(struct rtllib_device *__ieee_dev)
 void dot11d_init(struct rtllib_device *dev);
 void dot11d_channel_map(struct rtllib_device *ieee);
 void dot11d_reset(struct rtllib_device *dev);
-void dot11d_scan_complete(struct rtllib_device *dev);
 
 #endif
-- 
GitLab


From ae5bac7425fd7387c1787198d2b9bf8df6de60f4 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:02 +0100
Subject: [PATCH 0298/4076] staging: rtl8192e: Remove unused function
 dot11d_reset()

Remove unused function dot11d_reset().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/09306a7f674e0cf1244c47ef8ddfc5ae147124f8.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 17 -----------------
 drivers/staging/rtl8192e/dot11d.h |  1 -
 2 files changed, 18 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index 95fb56cb77fc6..f0241982c7a86 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -42,20 +42,3 @@ void dot11d_channel_map(struct rtllib_device *ieee)
 	ieee->bss_start_channel = 10;
 }
 EXPORT_SYMBOL(dot11d_channel_map);
-
-void dot11d_reset(struct rtllib_device *ieee)
-{
-	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(ieee);
-	u32 i;
-
-	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
-	memset(dot11d_info->max_tx_power_list, 0xFF, MAX_CHANNEL_NUMBER + 1);
-	for (i = 1; i <= 11; i++)
-		(dot11d_info->channel_map)[i] = 1;
-	for (i = 12; i <= 14; i++)
-		(dot11d_info->channel_map)[i] = 2;
-	dot11d_info->state = DOT11D_STATE_NONE;
-	dot11d_info->country_len = 0;
-	RESET_CIE_WATCHDOG(ieee);
-}
-
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 9e8328af887cc..0ca803be3965a 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -72,6 +72,5 @@ static inline void RESET_CIE_WATCHDOG(struct rtllib_device *__ieee_dev)
 
 void dot11d_init(struct rtllib_device *dev);
 void dot11d_channel_map(struct rtllib_device *ieee);
-void dot11d_reset(struct rtllib_device *dev);
 
 #endif
-- 
GitLab


From 788c6a2e7b39ded3322734284312022e88306f2c Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:10 +0100
Subject: [PATCH 0299/4076] staging: rtl8192e: Remove unused macros
 IS_EQUAL_CIE_SRC and friends

Remove unused macros IS_EQUAL_CIE_SRC, UPDATE_CIE_WATCHDOG,
UPDATE_CIE_SRC and IS_COUNTRY_IE_VALID.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/6d514e946983fb8ef4a3d7d3cb2774261a593d2f.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.h | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 0ca803be3965a..fd0a2df189bf9 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -52,15 +52,6 @@ static inline void copy_mac_addr(unsigned char *des, unsigned char *src)
 #define GET_DOT11D_INFO(__ieee_dev)			\
 	 ((struct rt_dot11d_info *)((__ieee_dev)->dot11d_info))
 
-#define IS_COUNTRY_IE_VALID(__ieee_dev)			\
-	(GET_DOT11D_INFO(__ieee_dev)->country_len > 0)
-
-#define IS_EQUAL_CIE_SRC(__ieee_dev, __address)		\
-	 ether_addr_equal_unaligned( \
-		GET_DOT11D_INFO(__ieee_dev)->country_src_addr, __address)
-#define UPDATE_CIE_SRC(__ieee_dev, __address)		\
-	copy_mac_addr(GET_DOT11D_INFO(__ieee_dev)->country_src_addr, __address)
-
 #define GET_CIE_WATCHDOG(__ieee_dev)				\
 	 (GET_DOT11D_INFO(__ieee_dev)->country_watchdog)
 static inline void RESET_CIE_WATCHDOG(struct rtllib_device *__ieee_dev)
@@ -68,8 +59,6 @@ static inline void RESET_CIE_WATCHDOG(struct rtllib_device *__ieee_dev)
 	GET_CIE_WATCHDOG(__ieee_dev) = 0;
 }
 
-#define UPDATE_CIE_WATCHDOG(__ieee_dev) (++GET_CIE_WATCHDOG(__ieee_dev))
-
 void dot11d_init(struct rtllib_device *dev);
 void dot11d_channel_map(struct rtllib_device *ieee);
 
-- 
GitLab


From 8d0a43cb658de4dfb8f5729419760b6bef9c8358 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:15 +0100
Subject: [PATCH 0300/4076] staging: rtl8192e: Remove unused function
 copy_mac_addr()

Remove unused function copy_mac_addr().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/d157456121388489784ce34e5f3daf91126f80d7.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index fd0a2df189bf9..d3da4af4a16ba 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -44,11 +44,6 @@ struct rt_dot11d_info {
 	enum dot11d_state state;
 };
 
-static inline void copy_mac_addr(unsigned char *des, unsigned char *src)
-{
-	memcpy(des, src, 6);
-}
-
 #define GET_DOT11D_INFO(__ieee_dev)			\
 	 ((struct rt_dot11d_info *)((__ieee_dev)->dot11d_info))
 
-- 
GitLab


From 49dd5a89cc35f2b2e0e3f4f1390cd000819a052a Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:21 +0100
Subject: [PATCH 0301/4076] staging: rtl8192e: Remove unused variable
 dot11d_info->state

Remove unused variable dot11d_info->state. Remove unused enum
dot11d_state as well.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/2f1d4851a7a370c5ef367568c2b098bb9fbf0ce7.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 1 -
 drivers/staging/rtl8192e/dot11d.h | 8 --------
 2 files changed, 9 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index f0241982c7a86..08cf95d269115 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -18,7 +18,6 @@ void dot11d_init(struct rtllib_device *ieee)
 {
 	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(ieee);
 
-	dot11d_info->state = DOT11D_STATE_NONE;
 	dot11d_info->country_len = 0;
 	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
 	memset(dot11d_info->max_tx_power_list, 0xFF, MAX_CHANNEL_NUMBER + 1);
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index d3da4af4a16ba..c7d35ec86aae5 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -16,12 +16,6 @@ struct chnl_txpow_triple {
 	u8  max_tx_power;
 };
 
-enum dot11d_state {
-	DOT11D_STATE_NONE = 0,
-	DOT11D_STATE_LEARNED,
-	DOT11D_STATE_DONE,
-};
-
 /**
  * struct rt_dot11d_info * @country_len: value greater than 0 if
  *		  @country_buffer contains valid country information element.
@@ -40,8 +34,6 @@ struct rt_dot11d_info {
 
 	u8  channel_map[MAX_CHANNEL_NUMBER + 1];
 	u8  max_tx_power_list[MAX_CHANNEL_NUMBER + 1];
-
-	enum dot11d_state state;
 };
 
 #define GET_DOT11D_INFO(__ieee_dev)			\
-- 
GitLab


From cea57157fa7af3eba8f386642937f4964df4ce90 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:26 +0100
Subject: [PATCH 0302/4076] staging: rtl8192e: Remove unused variables from
 struct rt_dot11d_info

Remove unused variables country_len, country_buffer, country_src_addr and
max_tx_power_list. Remove comments about usage as well.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/eeb9915d68c353554973e1056893371d15381f88.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 2 --
 drivers/staging/rtl8192e/dot11d.h | 9 +--------
 2 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index 08cf95d269115..b524ebe318698 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -18,9 +18,7 @@ void dot11d_init(struct rtllib_device *ieee)
 {
 	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(ieee);
 
-	dot11d_info->country_len = 0;
 	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
-	memset(dot11d_info->max_tx_power_list, 0xFF, MAX_CHANNEL_NUMBER + 1);
 	RESET_CIE_WATCHDOG(ieee);
 }
 EXPORT_SYMBOL(dot11d_init);
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index c7d35ec86aae5..64fd39cddc22a 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -17,23 +17,16 @@ struct chnl_txpow_triple {
 };
 
 /**
- * struct rt_dot11d_info * @country_len: value greater than 0 if
- *		  @country_buffer contains valid country information element.
+ * struct rt_dot11d_info
  * @channel_map: holds channel values
  *		0 - invalid,
  *		1 - valid (active scan),
  *		2 - valid (passive scan)
- * @country_src_addr - Source AP of the country IE
  */
 
 struct rt_dot11d_info {
-	u16 country_len;
-	u8  country_buffer[MAX_IE_LEN];
-	u8  country_src_addr[6];
 	u8  country_watchdog;
-
 	u8  channel_map[MAX_CHANNEL_NUMBER + 1];
-	u8  max_tx_power_list[MAX_CHANNEL_NUMBER + 1];
 };
 
 #define GET_DOT11D_INFO(__ieee_dev)			\
-- 
GitLab


From cc0a157ecf3ea5a91a42a0e9e256675e6390d6dd Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:32 +0100
Subject: [PATCH 0303/4076] staging: rtl8192e: Remove unused variable
 country_watchdog

country_watchdog is initialized to 0 and then never changed. Remove
related macros and functions.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/958f2ebbedb51e71e11479f734b4df27484160e1.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 1 -
 drivers/staging/rtl8192e/dot11d.h | 8 --------
 2 files changed, 9 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index b524ebe318698..b8ba95a65f273 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -19,7 +19,6 @@ void dot11d_init(struct rtllib_device *ieee)
 	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(ieee);
 
 	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
-	RESET_CIE_WATCHDOG(ieee);
 }
 EXPORT_SYMBOL(dot11d_init);
 
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 64fd39cddc22a..82748b12bd826 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -25,20 +25,12 @@ struct chnl_txpow_triple {
  */
 
 struct rt_dot11d_info {
-	u8  country_watchdog;
 	u8  channel_map[MAX_CHANNEL_NUMBER + 1];
 };
 
 #define GET_DOT11D_INFO(__ieee_dev)			\
 	 ((struct rt_dot11d_info *)((__ieee_dev)->dot11d_info))
 
-#define GET_CIE_WATCHDOG(__ieee_dev)				\
-	 (GET_DOT11D_INFO(__ieee_dev)->country_watchdog)
-static inline void RESET_CIE_WATCHDOG(struct rtllib_device *__ieee_dev)
-{
-	GET_CIE_WATCHDOG(__ieee_dev) = 0;
-}
-
 void dot11d_init(struct rtllib_device *dev);
 void dot11d_channel_map(struct rtllib_device *ieee);
 
-- 
GitLab


From 1e8d81e8c9ec127a54e21f0370ba40540dcd0ad1 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:39 +0100
Subject: [PATCH 0304/4076] staging: rtl8192e: Remove unused variable
 global_domain

global_domain is initialized to false and then never used.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/5e7a0753ed9d6d934203fe29ab8ecef41090f055.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 2 --
 drivers/staging/rtl8192e/rtllib.h | 1 -
 2 files changed, 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index b8ba95a65f273..fd488e2fa8157 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -26,8 +26,6 @@ void dot11d_channel_map(struct rtllib_device *ieee)
 {
 	int i;
 
-	ieee->global_domain = false;
-
 	memset(GET_DOT11D_INFO(ieee)->channel_map, 0,
 	       sizeof(GET_DOT11D_INFO(ieee)->channel_map));
 	for (i = 0; i < channel_array.len; i++)
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 1d0878d1f6965..820951602fb05 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1322,7 +1322,6 @@ struct rtllib_device {
 
 	/* map of allowed channels. 0 is dummy */
 	void *dot11d_info;
-	bool global_domain;
 	u8 active_channel_map[MAX_CHANNEL_NUMBER+1];
 
 	u8   bss_start_channel;
-- 
GitLab


From 30df513356a70b34ea6c937f8e7b6e413b257214 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:47 +0100
Subject: [PATCH 0305/4076] staging: rtl8192e: Remove unused function
 dot11d_init()

The variable dot11d_info->channel_map is initialized in dot11d_init() and
in dot11d_channel_map(). dot11d_init() is called only once just before
dot11d_channel_map(). Therefore dot11d_init() can be removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/d2e8d81ec9eefc7b7eeb9f6fd6a28b28db6b40f0.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c            | 8 --------
 drivers/staging/rtl8192e/dot11d.h            | 1 -
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 -
 3 files changed, 10 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index fd488e2fa8157..9ec112e00e38c 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -14,14 +14,6 @@ struct channel_list {
 
 static struct channel_list channel_array = {{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13};
 
-void dot11d_init(struct rtllib_device *ieee)
-{
-	struct rt_dot11d_info *dot11d_info = GET_DOT11D_INFO(ieee);
-
-	memset(dot11d_info->channel_map, 0, MAX_CHANNEL_NUMBER + 1);
-}
-EXPORT_SYMBOL(dot11d_init);
-
 void dot11d_channel_map(struct rtllib_device *ieee)
 {
 	int i;
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 82748b12bd826..767bbbc8b01d3 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -31,7 +31,6 @@ struct rt_dot11d_info {
 #define GET_DOT11D_INFO(__ieee_dev)			\
 	 ((struct rt_dot11d_info *)((__ieee_dev)->dot11d_info))
 
-void dot11d_init(struct rtllib_device *dev);
 void dot11d_channel_map(struct rtllib_device *ieee);
 
 #endif
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 4b842a1789c25..c3466291e221d 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -795,7 +795,6 @@ static short _rtl92e_get_channel_map(struct net_device *dev)
 
 	struct r8192_priv *priv = rtllib_priv(dev);
 
-	dot11d_init(priv->rtllib);
 	dot11d_channel_map(priv->rtllib);
 	for (i = 1; i <= 11; i++)
 		(priv->rtllib->active_channel_map)[i] = 1;
-- 
GitLab


From 7c9f0347799f5ceb3fc347f79e1eea30bf2ae145 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:15:53 +0100
Subject: [PATCH 0306/4076] staging: rtl8192e: Remove unused struct
 chnl_txpow_triple

Remove unused struct chnl_txpow_triple.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/f66c7cd95ae460ccb376e9edce11b2b955c908cc.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 767bbbc8b01d3..5c02e51c39cd2 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -10,12 +10,6 @@
 
 #include "rtllib.h"
 
-struct chnl_txpow_triple {
-	u8 first_channel;
-	u8  num_channels;
-	u8  max_tx_power;
-};
-
 /**
  * struct rt_dot11d_info
  * @channel_map: holds channel values
-- 
GitLab


From 6025bef95f6c7426b14a22ca91b18d6dd7833392 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 19 Nov 2023 23:16:05 +0100
Subject: [PATCH 0307/4076] staging: rtl8192e: Remove unused variable
 bss_start_channel

Remove unused variable bss_start_channel.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/a13a8421d43ef1baa2077af1d4955059eba52d79.1700431464.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 1 -
 drivers/staging/rtl8192e/rtllib.h | 2 --
 2 files changed, 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index 9ec112e00e38c..d51d4afff61e8 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -25,6 +25,5 @@ void dot11d_channel_map(struct rtllib_device *ieee)
 
 	for (i = 12; i <= 13; i++)
 		GET_DOT11D_INFO(ieee)->channel_map[i] = 2;
-	ieee->bss_start_channel = 10;
 }
 EXPORT_SYMBOL(dot11d_channel_map);
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 820951602fb05..77ae259eab355 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1324,8 +1324,6 @@ struct rtllib_device {
 	void *dot11d_info;
 	u8 active_channel_map[MAX_CHANNEL_NUMBER+1];
 
-	u8   bss_start_channel;
-
 	int rate;       /* current rate */
 	int basic_rate;
 
-- 
GitLab


From 89abfc0ab58228728c6e3fec9fb5be3064459bd9 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:24 +0530
Subject: [PATCH 0308/4076] staging: vt6655: Type encoding info dropped from
 variable name "qwBSSTimestamp"

variable name "qwBSSTimestamp" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/977e5e538610d28dce6a02a6d475ee336fc0899c.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c | 8 ++++----
 drivers/staging/vt6655/card.h | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index 350ab8f3778a4..59a788b7e2681 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -280,7 +280,7 @@ bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type)
  *  In:
  *      priv            - The adapter to be sync.
  *      rx_rate         - data rate of receive beacon
- *      qwBSSTimestamp  - Rx BCN's TSF
+ *      bss_timestamp   - Rx BCN's TSF
  *      qwLocalTSF      - Local TSF
  *  Out:
  *      none
@@ -288,15 +288,15 @@ bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type)
  * Return Value: none
  */
 bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
-		    u64 qwBSSTimestamp)
+		    u64 bss_timestamp)
 {
 	u64 local_tsf;
 	u64 qwTSFOffset = 0;
 
 	local_tsf = vt6655_get_current_tsf(priv);
 
-	if (qwBSSTimestamp != local_tsf) {
-		qwTSFOffset = CARDqGetTSFOffset(rx_rate, qwBSSTimestamp,
+	if (bss_timestamp != local_tsf) {
+		qwTSFOffset = CARDqGetTSFOffset(rx_rate, bss_timestamp,
 						local_tsf);
 		/* adjust TSF, HW's TSF add TSF Offset reg */
 		qwTSFOffset =  le64_to_cpu(qwTSFOffset);
diff --git a/drivers/staging/vt6655/card.h b/drivers/staging/vt6655/card.h
index 19689a291f5b4..cda969b06fce2 100644
--- a/drivers/staging/vt6655/card.h
+++ b/drivers/staging/vt6655/card.h
@@ -55,7 +55,7 @@ void CARDvSafeResetRx(struct vnt_private *priv);
 void CARDbRadioPowerOff(struct vnt_private *priv);
 bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type);
 bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
-		    u64 qwBSSTimestamp);
+		    u64 bss_timestamp);
 bool CARDbSetBeaconPeriod(struct vnt_private *priv,
 			  unsigned short wBeaconInterval);
 
-- 
GitLab


From efafcb553e9effaa2907378da44839efb166ed92 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:25 +0530
Subject: [PATCH 0309/4076] staging: vt6655: Type encoding info dropped from
 variable name "qwTSFOffset"

variable name "qwTSFOffset" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/035b910c92233a7252a4b312e0cfe5adbcbbae79.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index 59a788b7e2681..e0af14eb7cd49 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -291,17 +291,17 @@ bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
 		    u64 bss_timestamp)
 {
 	u64 local_tsf;
-	u64 qwTSFOffset = 0;
+	u64 tsf_offset = 0;
 
 	local_tsf = vt6655_get_current_tsf(priv);
 
 	if (bss_timestamp != local_tsf) {
-		qwTSFOffset = CARDqGetTSFOffset(rx_rate, bss_timestamp,
+		tsf_offset = CARDqGetTSFOffset(rx_rate, bss_timestamp,
 						local_tsf);
 		/* adjust TSF, HW's TSF add TSF Offset reg */
-		qwTSFOffset =  le64_to_cpu(qwTSFOffset);
-		iowrite32((u32)qwTSFOffset, priv->port_offset + MAC_REG_TSFOFST);
-		iowrite32((u32)(qwTSFOffset >> 32), priv->port_offset + MAC_REG_TSFOFST + 4);
+		tsf_offset =  le64_to_cpu(tsf_offset);
+		iowrite32((u32)tsf_offset, priv->port_offset + MAC_REG_TSFOFST);
+		iowrite32((u32)(tsf_offset >> 32), priv->port_offset + MAC_REG_TSFOFST + 4);
 		vt6655_mac_reg_bits_on(priv->port_offset, MAC_REG_TFTCTL, TFTCTL_TSFSYNCEN);
 	}
 	return true;
-- 
GitLab


From 314b805e699b2b12355b944830b3735bfe92eb5b Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:26 +0530
Subject: [PATCH 0310/4076] staging: vt6655: Type encoding info dropped from
 function name "CARDqGetTSFOffset"

function name "CARDqGetTSFOffset" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/b6b86bd65669cae59ca10171ecee8aa4a13c4a26.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c | 6 +++---
 drivers/staging/vt6655/card.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index e0af14eb7cd49..1edf65e2adcf9 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -10,7 +10,7 @@
  *      CARDvUpdateBasicTopRate - Update BasicTopRate
  *      CARDbAddBasicRate - Add to BasicRateSet
  *      CARDbIsOFDMinBasicRate - Check if any OFDM rate is in BasicRateSet
- *      CARDqGetTSFOffset - Calculate TSFOffset
+ *      card_get_tsf_offset - Calculate TSFOffset
  *      vt6655_get_current_tsf - Read Current NIC TSF counter
  *      CARDqGetNextTBTT - Calculate Next Beacon TSF counter
  *      CARDvSetFirstNextTBTT - Set NIC Beacon time
@@ -296,7 +296,7 @@ bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
 	local_tsf = vt6655_get_current_tsf(priv);
 
 	if (bss_timestamp != local_tsf) {
-		tsf_offset = CARDqGetTSFOffset(rx_rate, bss_timestamp,
+		tsf_offset = card_get_tsf_offset(rx_rate, bss_timestamp,
 						local_tsf);
 		/* adjust TSF, HW's TSF add TSF Offset reg */
 		tsf_offset =  le64_to_cpu(tsf_offset);
@@ -708,7 +708,7 @@ unsigned char card_get_pkt_type(struct vnt_private *priv)
  *
  * Return Value: TSF Offset value
  */
-u64 CARDqGetTSFOffset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2)
+u64 card_get_tsf_offset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2)
 {
 	unsigned short wRxBcnTSFOffst;
 
diff --git a/drivers/staging/vt6655/card.h b/drivers/staging/vt6655/card.h
index cda969b06fce2..df1b9a7c1f212 100644
--- a/drivers/staging/vt6655/card.h
+++ b/drivers/staging/vt6655/card.h
@@ -48,7 +48,7 @@ void CARDvUpdateNextTBTT(struct vnt_private *priv, u64 qwTSF,
 			 unsigned short wBeaconInterval);
 u64 vt6655_get_current_tsf(struct vnt_private *priv);
 u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short wBeaconInterval);
-u64 CARDqGetTSFOffset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2);
+u64 card_get_tsf_offset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2);
 unsigned char card_get_pkt_type(struct vnt_private *priv);
 void CARDvSafeResetTx(struct vnt_private *priv);
 void CARDvSafeResetRx(struct vnt_private *priv);
-- 
GitLab


From b6f0032e047a015e9d7eb9cab652f54664ec7cc8 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:27 +0530
Subject: [PATCH 0311/4076] staging: vt6655: Type encoding info dropped from
 function name "CARDbSetBeaconPeriod"

function name "CARDbSetBeaconPeriod" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/8d4c10ac86f80bb46d5cb1f18079276c3326e5dd.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c        | 2 +-
 drivers/staging/vt6655/card.h        | 2 +-
 drivers/staging/vt6655/device_main.c | 2 +-
 drivers/staging/vt6655/rxtx.c        | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index 1edf65e2adcf9..bfd02a869d646 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -320,7 +320,7 @@ bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
  *
  * Return Value: true if succeed; otherwise false
  */
-bool CARDbSetBeaconPeriod(struct vnt_private *priv,
+bool card_set_beacon_period(struct vnt_private *priv,
 			  unsigned short wBeaconInterval)
 {
 	u64 qwNextTBTT;
diff --git a/drivers/staging/vt6655/card.h b/drivers/staging/vt6655/card.h
index df1b9a7c1f212..f84e4190a2ac4 100644
--- a/drivers/staging/vt6655/card.h
+++ b/drivers/staging/vt6655/card.h
@@ -56,7 +56,7 @@ void CARDbRadioPowerOff(struct vnt_private *priv);
 bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type);
 bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
 		    u64 bss_timestamp);
-bool CARDbSetBeaconPeriod(struct vnt_private *priv,
+bool card_set_beacon_period(struct vnt_private *priv,
 			  unsigned short wBeaconInterval);
 
 #endif /* __CARD_H__ */
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 7d297526e6539..2e2a8da571ab0 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -1537,7 +1537,7 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw,
 			card_update_tsf(priv, conf->beacon_rate->hw_value,
 				       conf->sync_tsf);
 
-			CARDbSetBeaconPeriod(priv, conf->beacon_int);
+			card_set_beacon_period(priv, conf->beacon_int);
 
 			CARDvSetFirstNextTBTT(priv, conf->beacon_int);
 		} else {
diff --git a/drivers/staging/vt6655/rxtx.c b/drivers/staging/vt6655/rxtx.c
index 522d34ca9b0ff..5e5ed582c35e3 100644
--- a/drivers/staging/vt6655/rxtx.c
+++ b/drivers/staging/vt6655/rxtx.c
@@ -1456,7 +1456,7 @@ int vnt_beacon_enable(struct vnt_private *priv, struct ieee80211_vif *vif,
 
 	CARDvSetFirstNextTBTT(priv, conf->beacon_int);
 
-	CARDbSetBeaconPeriod(priv, conf->beacon_int);
+	card_set_beacon_period(priv, conf->beacon_int);
 
 	return vnt_beacon_make(priv, vif);
 }
-- 
GitLab


From 272b281abdf6fc5b86b916e52ce305b783c06c43 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:28 +0530
Subject: [PATCH 0312/4076] staging: vt6655: Type encoding info dropped from
 variable name "wBeaconInterval"

variable name "wBeaconInterval" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/a8aa6227fb8dadfdebb0a6ab74cff9730358c765.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c   | 26 +++++++++++++-------------
 drivers/staging/vt6655/card.h   |  8 ++++----
 drivers/staging/vt6655/device.h |  2 +-
 3 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index bfd02a869d646..c18cbf0aad754 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -314,24 +314,24 @@ bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
  * Parameters:
  *  In:
  *      priv         - The adapter to be set.
- *      wBeaconInterval - Beacon Interval
+ *      beacon_interval - Beacon Interval
  *  Out:
  *      none
  *
  * Return Value: true if succeed; otherwise false
  */
 bool card_set_beacon_period(struct vnt_private *priv,
-			  unsigned short wBeaconInterval)
+			  unsigned short beacon_interval)
 {
 	u64 qwNextTBTT;
 
 	qwNextTBTT = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
 
-	qwNextTBTT = CARDqGetNextTBTT(qwNextTBTT, wBeaconInterval);
+	qwNextTBTT = CARDqGetNextTBTT(qwNextTBTT, beacon_interval);
 
 	/* set HW beacon interval */
-	iowrite16(wBeaconInterval, priv->port_offset + MAC_REG_BI);
-	priv->wBeaconInterval = wBeaconInterval;
+	iowrite16(beacon_interval, priv->port_offset + MAC_REG_BI);
+	priv->beacon_interval = beacon_interval;
 	/* Set NextTBTT */
 	qwNextTBTT =  le64_to_cpu(qwNextTBTT);
 	iowrite32((u32)qwNextTBTT, priv->port_offset + MAC_REG_NEXTTBTT);
@@ -764,11 +764,11 @@ u64 vt6655_get_current_tsf(struct vnt_private *priv)
  *
  * Return Value: TSF value of next Beacon
  */
-u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short wBeaconInterval)
+u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short beacon_interval)
 {
 	u32 beacon_int;
 
-	beacon_int = wBeaconInterval * 1024;
+	beacon_int = beacon_interval * 1024;
 	if (beacon_int) {
 		do_div(qwTSF, beacon_int);
 		qwTSF += 1;
@@ -785,21 +785,21 @@ u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short wBeaconInterval)
  * Parameters:
  *  In:
  *      iobase          - IO Base
- *      wBeaconInterval - Beacon Interval
+ *      beacon_interval - Beacon Interval
  *  Out:
  *      none
  *
  * Return Value: none
  */
 void CARDvSetFirstNextTBTT(struct vnt_private *priv,
-			   unsigned short wBeaconInterval)
+			   unsigned short beacon_interval)
 {
 	void __iomem *iobase = priv->port_offset;
 	u64 qwNextTBTT;
 
 	qwNextTBTT = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
 
-	qwNextTBTT = CARDqGetNextTBTT(qwNextTBTT, wBeaconInterval);
+	qwNextTBTT = CARDqGetNextTBTT(qwNextTBTT, beacon_interval);
 	/* Set NextTBTT */
 	qwNextTBTT =  le64_to_cpu(qwNextTBTT);
 	iowrite32((u32)qwNextTBTT, iobase + MAC_REG_NEXTTBTT);
@@ -815,18 +815,18 @@ void CARDvSetFirstNextTBTT(struct vnt_private *priv,
  *  In:
  *      priv         - The adapter to be set
  *      qwTSF           - Current TSF counter
- *      wBeaconInterval - Beacon Interval
+ *      beacon_interval - Beacon Interval
  *  Out:
  *      none
  *
  * Return Value: none
  */
 void CARDvUpdateNextTBTT(struct vnt_private *priv, u64 qwTSF,
-			 unsigned short wBeaconInterval)
+			 unsigned short beacon_interval)
 {
 	void __iomem *iobase = priv->port_offset;
 
-	qwTSF = CARDqGetNextTBTT(qwTSF, wBeaconInterval);
+	qwTSF = CARDqGetNextTBTT(qwTSF, beacon_interval);
 	/* Set NextTBTT */
 	qwTSF =  le64_to_cpu(qwTSF);
 	iowrite32((u32)qwTSF, iobase + MAC_REG_NEXTTBTT);
diff --git a/drivers/staging/vt6655/card.h b/drivers/staging/vt6655/card.h
index f84e4190a2ac4..1758a95f3ab07 100644
--- a/drivers/staging/vt6655/card.h
+++ b/drivers/staging/vt6655/card.h
@@ -43,11 +43,11 @@ void card_set_rspinf(struct vnt_private *priv, u8 bb_type);
 void CARDvUpdateBasicTopRate(struct vnt_private *priv);
 bool CARDbIsOFDMinBasicRate(struct vnt_private *priv);
 void CARDvSetFirstNextTBTT(struct vnt_private *priv,
-			   unsigned short wBeaconInterval);
+			   unsigned short beacon_interval);
 void CARDvUpdateNextTBTT(struct vnt_private *priv, u64 qwTSF,
-			 unsigned short wBeaconInterval);
+			 unsigned short beacon_interval);
 u64 vt6655_get_current_tsf(struct vnt_private *priv);
-u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short wBeaconInterval);
+u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short beacon_interval);
 u64 card_get_tsf_offset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2);
 unsigned char card_get_pkt_type(struct vnt_private *priv);
 void CARDvSafeResetTx(struct vnt_private *priv);
@@ -57,6 +57,6 @@ bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type);
 bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
 		    u64 bss_timestamp);
 bool card_set_beacon_period(struct vnt_private *priv,
-			  unsigned short wBeaconInterval);
+			  unsigned short beacon_interval);
 
 #endif /* __CARD_H__ */
diff --git a/drivers/staging/vt6655/device.h b/drivers/staging/vt6655/device.h
index d9ee0b7401fe0..fadbfccf42de3 100644
--- a/drivers/staging/vt6655/device.h
+++ b/drivers/staging/vt6655/device.h
@@ -281,7 +281,7 @@ struct vnt_private {
 
 	unsigned char abyEEPROM[EEP_MAX_CONTEXT_SIZE]; /* unsigned long alignment */
 
-	unsigned short wBeaconInterval;
+	unsigned short beacon_interval;
 	u16 wake_up_count;
 
 	struct work_struct interrupt_work;
-- 
GitLab


From 4ef985fa1faf8c7659404d25db950989d33a6097 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:29 +0530
Subject: [PATCH 0313/4076] staging: vt6655: Type encoding info dropped from
 variable name "qwNextTBTT"

variable name "qwTSFOffset" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/6b1fe342f7577c46a980cdc1bee0c7f560f05d87.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index c18cbf0aad754..e4b40125b0942 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -323,19 +323,19 @@ bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
 bool card_set_beacon_period(struct vnt_private *priv,
 			  unsigned short beacon_interval)
 {
-	u64 qwNextTBTT;
+	u64 next_tbtt;
 
-	qwNextTBTT = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
+	next_tbtt = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
 
-	qwNextTBTT = CARDqGetNextTBTT(qwNextTBTT, beacon_interval);
+	next_tbtt = CARDqGetNextTBTT(next_tbtt, beacon_interval);
 
 	/* set HW beacon interval */
 	iowrite16(beacon_interval, priv->port_offset + MAC_REG_BI);
 	priv->beacon_interval = beacon_interval;
 	/* Set NextTBTT */
-	qwNextTBTT =  le64_to_cpu(qwNextTBTT);
-	iowrite32((u32)qwNextTBTT, priv->port_offset + MAC_REG_NEXTTBTT);
-	iowrite32((u32)(qwNextTBTT >> 32), priv->port_offset + MAC_REG_NEXTTBTT + 4);
+	next_tbtt =  le64_to_cpu(next_tbtt);
+	iowrite32((u32)next_tbtt, priv->port_offset + MAC_REG_NEXTTBTT);
+	iowrite32((u32)(next_tbtt >> 32), priv->port_offset + MAC_REG_NEXTTBTT + 4);
 	vt6655_mac_reg_bits_on(priv->port_offset, MAC_REG_TFTCTL, TFTCTL_TBTTSYNCEN);
 
 	return true;
@@ -795,15 +795,15 @@ void CARDvSetFirstNextTBTT(struct vnt_private *priv,
 			   unsigned short beacon_interval)
 {
 	void __iomem *iobase = priv->port_offset;
-	u64 qwNextTBTT;
+	u64 next_tbtt;
 
-	qwNextTBTT = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
+	next_tbtt = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
 
-	qwNextTBTT = CARDqGetNextTBTT(qwNextTBTT, beacon_interval);
+	next_tbtt = CARDqGetNextTBTT(next_tbtt, beacon_interval);
 	/* Set NextTBTT */
-	qwNextTBTT =  le64_to_cpu(qwNextTBTT);
-	iowrite32((u32)qwNextTBTT, iobase + MAC_REG_NEXTTBTT);
-	iowrite32((u32)(qwNextTBTT >> 32), iobase + MAC_REG_NEXTTBTT + 4);
+	next_tbtt =  le64_to_cpu(next_tbtt);
+	iowrite32((u32)next_tbtt, iobase + MAC_REG_NEXTTBTT);
+	iowrite32((u32)(next_tbtt >> 32), iobase + MAC_REG_NEXTTBTT + 4);
 	vt6655_mac_reg_bits_on(iobase, MAC_REG_TFTCTL, TFTCTL_TBTTSYNCEN);
 }
 
-- 
GitLab


From 862aa279cf3d7eb24d95740ea97cfe159bbca0c1 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:30 +0530
Subject: [PATCH 0314/4076] staging: vt6655: Type encoding info dropped from
 function name "CARDqGetNextTBTT"

function name "CARDqGetNextTBTT" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/8e142b33245e6933fb178080b0b14371939a84e6.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c | 10 +++++-----
 drivers/staging/vt6655/card.h |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index e4b40125b0942..716fd36325083 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -12,7 +12,7 @@
  *      CARDbIsOFDMinBasicRate - Check if any OFDM rate is in BasicRateSet
  *      card_get_tsf_offset - Calculate TSFOffset
  *      vt6655_get_current_tsf - Read Current NIC TSF counter
- *      CARDqGetNextTBTT - Calculate Next Beacon TSF counter
+ *      card_get_next_tbtt - Calculate Next Beacon TSF counter
  *      CARDvSetFirstNextTBTT - Set NIC Beacon time
  *      CARDvUpdateNextTBTT - Sync. NIC Beacon time
  *      CARDbRadioPowerOff - Turn Off NIC Radio Power
@@ -327,7 +327,7 @@ bool card_set_beacon_period(struct vnt_private *priv,
 
 	next_tbtt = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
 
-	next_tbtt = CARDqGetNextTBTT(next_tbtt, beacon_interval);
+	next_tbtt = card_get_next_tbtt(next_tbtt, beacon_interval);
 
 	/* set HW beacon interval */
 	iowrite16(beacon_interval, priv->port_offset + MAC_REG_BI);
@@ -764,7 +764,7 @@ u64 vt6655_get_current_tsf(struct vnt_private *priv)
  *
  * Return Value: TSF value of next Beacon
  */
-u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short beacon_interval)
+u64 card_get_next_tbtt(u64 qwTSF, unsigned short beacon_interval)
 {
 	u32 beacon_int;
 
@@ -799,7 +799,7 @@ void CARDvSetFirstNextTBTT(struct vnt_private *priv,
 
 	next_tbtt = vt6655_get_current_tsf(priv); /* Get Local TSF counter */
 
-	next_tbtt = CARDqGetNextTBTT(next_tbtt, beacon_interval);
+	next_tbtt = card_get_next_tbtt(next_tbtt, beacon_interval);
 	/* Set NextTBTT */
 	next_tbtt =  le64_to_cpu(next_tbtt);
 	iowrite32((u32)next_tbtt, iobase + MAC_REG_NEXTTBTT);
@@ -826,7 +826,7 @@ void CARDvUpdateNextTBTT(struct vnt_private *priv, u64 qwTSF,
 {
 	void __iomem *iobase = priv->port_offset;
 
-	qwTSF = CARDqGetNextTBTT(qwTSF, beacon_interval);
+	qwTSF = card_get_next_tbtt(qwTSF, beacon_interval);
 	/* Set NextTBTT */
 	qwTSF =  le64_to_cpu(qwTSF);
 	iowrite32((u32)qwTSF, iobase + MAC_REG_NEXTTBTT);
diff --git a/drivers/staging/vt6655/card.h b/drivers/staging/vt6655/card.h
index 1758a95f3ab07..ab1193799239d 100644
--- a/drivers/staging/vt6655/card.h
+++ b/drivers/staging/vt6655/card.h
@@ -47,7 +47,7 @@ void CARDvSetFirstNextTBTT(struct vnt_private *priv,
 void CARDvUpdateNextTBTT(struct vnt_private *priv, u64 qwTSF,
 			 unsigned short beacon_interval);
 u64 vt6655_get_current_tsf(struct vnt_private *priv);
-u64 CARDqGetNextTBTT(u64 qwTSF, unsigned short beacon_interval);
+u64 card_get_next_tbtt(u64 qwTSF, unsigned short beacon_interval);
 u64 card_get_tsf_offset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2);
 unsigned char card_get_pkt_type(struct vnt_private *priv);
 void CARDvSafeResetTx(struct vnt_private *priv);
-- 
GitLab


From ac491ce137218fe4ebb6333b46658a5bf4bfc2b9 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:31 +0530
Subject: [PATCH 0315/4076] staging: vt6655: Type encoding info dropped from
 function name "CARDbRadioPowerOff"

function name "CARDbRadioPowerOff" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/5b264db5a6d5ac936e02f0a7f465e648504a049e.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c        | 4 ++--
 drivers/staging/vt6655/card.h        | 2 +-
 drivers/staging/vt6655/device_main.c | 6 +++---
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index 716fd36325083..7980b93d2b1e9 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -15,7 +15,7 @@
  *      card_get_next_tbtt - Calculate Next Beacon TSF counter
  *      CARDvSetFirstNextTBTT - Set NIC Beacon time
  *      CARDvUpdateNextTBTT - Sync. NIC Beacon time
- *      CARDbRadioPowerOff - Turn Off NIC Radio Power
+ *      card_radio_power_off - Turn Off NIC Radio Power
  *
  * Revision History:
  *      06-10-2003 Bryan YC Fan:  Re-write codes to support VT3253 spec.
@@ -351,7 +351,7 @@ bool card_set_beacon_period(struct vnt_private *priv,
  *      none
  *
  */
-void CARDbRadioPowerOff(struct vnt_private *priv)
+void card_radio_power_off(struct vnt_private *priv)
 {
 	if (priv->radio_off)
 		return;
diff --git a/drivers/staging/vt6655/card.h b/drivers/staging/vt6655/card.h
index ab1193799239d..5ca715b415e8a 100644
--- a/drivers/staging/vt6655/card.h
+++ b/drivers/staging/vt6655/card.h
@@ -52,7 +52,7 @@ u64 card_get_tsf_offset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2);
 unsigned char card_get_pkt_type(struct vnt_private *priv);
 void CARDvSafeResetTx(struct vnt_private *priv);
 void CARDvSafeResetRx(struct vnt_private *priv);
-void CARDbRadioPowerOff(struct vnt_private *priv);
+void card_radio_power_off(struct vnt_private *priv);
 bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type);
 bool card_update_tsf(struct vnt_private *priv, unsigned char rx_rate,
 		    u64 bss_timestamp);
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 2e2a8da571ab0..210c94312310a 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -454,7 +454,7 @@ static void device_init_registers(struct vnt_private *priv)
 	}
 
 	if (priv->hw_radio_off || priv->bRadioControlOff)
-		CARDbRadioPowerOff(priv);
+		card_radio_power_off(priv);
 
 	/* get Permanent network address */
 	SROMvReadEtherAddress(priv->port_offset, priv->abyCurrentNetAddr);
@@ -1349,7 +1349,7 @@ static void vnt_stop(struct ieee80211_hw *hw)
 
 	MACbShutdown(priv);
 	MACbSoftwareReset(priv);
-	CARDbRadioPowerOff(priv);
+	card_radio_power_off(priv);
 
 	device_free_td0_ring(priv);
 	device_free_td1_ring(priv);
@@ -1712,7 +1712,7 @@ static int vnt_init(struct vnt_private *priv)
 
 	priv->mac_hw = true;
 
-	CARDbRadioPowerOff(priv);
+	card_radio_power_off(priv);
 
 	return 0;
 }
-- 
GitLab


From 157327d09977ea91dfa110b78908596d7b92ae57 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:32 +0530
Subject: [PATCH 0316/4076] staging: vt6655: Type encoding info dropped from
 function name "CARDvSafeResetTx"

function name "CARDvSafeResetTx" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/785a163ab01555bd0a7ed87484d727560d22cd95.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c        | 2 +-
 drivers/staging/vt6655/card.h        | 2 +-
 drivers/staging/vt6655/device_main.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index 7980b93d2b1e9..b249f22246b04 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -382,7 +382,7 @@ void card_radio_power_off(struct vnt_private *priv)
 	vt6655_mac_reg_bits_on(priv->port_offset, MAC_REG_GPIOCTL0, LED_ACTSET);  /* LED issue */
 }
 
-void CARDvSafeResetTx(struct vnt_private *priv)
+void card_safe_reset_tx(struct vnt_private *priv)
 {
 	unsigned int uu;
 	struct vnt_tx_desc *pCurrTD;
diff --git a/drivers/staging/vt6655/card.h b/drivers/staging/vt6655/card.h
index 5ca715b415e8a..f52e42564e81a 100644
--- a/drivers/staging/vt6655/card.h
+++ b/drivers/staging/vt6655/card.h
@@ -50,7 +50,7 @@ u64 vt6655_get_current_tsf(struct vnt_private *priv);
 u64 card_get_next_tbtt(u64 qwTSF, unsigned short beacon_interval);
 u64 card_get_tsf_offset(unsigned char rx_rate, u64 qwTSF1, u64 qwTSF2);
 unsigned char card_get_pkt_type(struct vnt_private *priv);
-void CARDvSafeResetTx(struct vnt_private *priv);
+void card_safe_reset_tx(struct vnt_private *priv);
 void CARDvSafeResetRx(struct vnt_private *priv);
 void card_radio_power_off(struct vnt_private *priv);
 bool card_set_phy_parameter(struct vnt_private *priv, u8 bb_type);
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 210c94312310a..a1f3dc25ad0ed 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -463,7 +463,7 @@ static void device_init_registers(struct vnt_private *priv)
 	/* reset Tx pointer */
 	CARDvSafeResetRx(priv);
 	/* reset Rx pointer */
-	CARDvSafeResetTx(priv);
+	card_safe_reset_tx(priv);
 
 	if (priv->local_id <= REV_ID_VT3253_A1)
 		vt6655_mac_reg_bits_on(priv->port_offset, MAC_REG_RCR, RCR_WPAERR);
-- 
GitLab


From 3ca35c28163a39e38e36386a7cc8889a30f3be53 Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:33 +0530
Subject: [PATCH 0317/4076] staging: vt6655: Type encoding info dropped from
 variable name "pCurrTD"

variable name "pCurrTD" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/06dc61ae807dcaa1dd8fdbf18686f0f4c20be634.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index b249f22246b04..d20afbc1072fd 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -385,7 +385,7 @@ void card_radio_power_off(struct vnt_private *priv)
 void card_safe_reset_tx(struct vnt_private *priv)
 {
 	unsigned int uu;
-	struct vnt_tx_desc *pCurrTD;
+	struct vnt_tx_desc *curr_td;
 
 	/* initialize TD index */
 	priv->apTailTD[0] = &priv->apTD0Rings[0];
@@ -398,13 +398,13 @@ void card_safe_reset_tx(struct vnt_private *priv)
 		priv->iTDUsed[uu] = 0;
 
 	for (uu = 0; uu < priv->opts.tx_descs[0]; uu++) {
-		pCurrTD = &priv->apTD0Rings[uu];
-		pCurrTD->td0.owner = OWNED_BY_HOST;
+		curr_td = &priv->apTD0Rings[uu];
+		curr_td->td0.owner = OWNED_BY_HOST;
 		/* init all Tx Packet pointer to NULL */
 	}
 	for (uu = 0; uu < priv->opts.tx_descs[1]; uu++) {
-		pCurrTD = &priv->apTD1Rings[uu];
-		pCurrTD->td0.owner = OWNED_BY_HOST;
+		curr_td = &priv->apTD1Rings[uu];
+		curr_td->td0.owner = OWNED_BY_HOST;
 		/* init all Tx Packet pointer to NULL */
 	}
 
-- 
GitLab


From 84353aeeb5502fb2f4b2022c5062c09f4936bc4e Mon Sep 17 00:00:00 2001
From: Pavan Bobba <opensource206@gmail.com>
Date: Tue, 31 Oct 2023 11:04:34 +0530
Subject: [PATCH 0318/4076] staging: vt6655: Type encoding info dropped from
 variable name "apTailTD"

variable name "apTailTD" updated like below:

a.type encoding info dropped from name
b.camelcase name replaced by snakecase

Issue found by checkpatch

Signed-off-by: Pavan Bobba <opensource206@gmail.com>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/482553f089fe86dc7ebecd96c9397cfaa9c7bdf9.1698730318.git.opensource206@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/card.c        | 4 ++--
 drivers/staging/vt6655/device.h      | 2 +-
 drivers/staging/vt6655/device_main.c | 8 ++++----
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/vt6655/card.c b/drivers/staging/vt6655/card.c
index d20afbc1072fd..36183f2a64c11 100644
--- a/drivers/staging/vt6655/card.c
+++ b/drivers/staging/vt6655/card.c
@@ -388,10 +388,10 @@ void card_safe_reset_tx(struct vnt_private *priv)
 	struct vnt_tx_desc *curr_td;
 
 	/* initialize TD index */
-	priv->apTailTD[0] = &priv->apTD0Rings[0];
+	priv->tail_td[0] = &priv->apTD0Rings[0];
 	priv->apCurrTD[0] = &priv->apTD0Rings[0];
 
-	priv->apTailTD[1] = &priv->apTD1Rings[0];
+	priv->tail_td[1] = &priv->apTD1Rings[0];
 	priv->apCurrTD[1] = &priv->apTD1Rings[0];
 
 	for (uu = 0; uu < TYPE_MAXTD; uu++)
diff --git a/drivers/staging/vt6655/device.h b/drivers/staging/vt6655/device.h
index fadbfccf42de3..0212240ba23f9 100644
--- a/drivers/staging/vt6655/device.h
+++ b/drivers/staging/vt6655/device.h
@@ -133,7 +133,7 @@ struct vnt_private {
 	volatile int                iTDUsed[TYPE_MAXTD];
 
 	struct vnt_tx_desc *apCurrTD[TYPE_MAXTD];
-	struct vnt_tx_desc *apTailTD[TYPE_MAXTD];
+	struct vnt_tx_desc *tail_td[TYPE_MAXTD];
 
 	struct vnt_tx_desc *apTD0Rings;
 	struct vnt_tx_desc *apTD1Rings;
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index a1f3dc25ad0ed..b0b262de64801 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -737,7 +737,7 @@ static int device_init_td0_ring(struct vnt_private *priv)
 
 	if (i > 0)
 		priv->apTD0Rings[i - 1].next_desc = cpu_to_le32(priv->td0_pool_dma);
-	priv->apTailTD[0] = priv->apCurrTD[0] = &priv->apTD0Rings[0];
+	priv->tail_td[0] = priv->apCurrTD[0] = &priv->apTD0Rings[0];
 
 	return 0;
 
@@ -777,7 +777,7 @@ static int device_init_td1_ring(struct vnt_private *priv)
 
 	if (i > 0)
 		priv->apTD1Rings[i - 1].next_desc = cpu_to_le32(priv->td1_pool_dma);
-	priv->apTailTD[1] = priv->apCurrTD[1] = &priv->apTD1Rings[0];
+	priv->tail_td[1] = priv->apCurrTD[1] = &priv->apTD1Rings[0];
 
 	return 0;
 
@@ -969,7 +969,7 @@ static int device_tx_srv(struct vnt_private *priv, unsigned int idx)
 	unsigned char byTsr0;
 	unsigned char byTsr1;
 
-	for (desc = priv->apTailTD[idx]; priv->iTDUsed[idx] > 0; desc = desc->next) {
+	for (desc = priv->tail_td[idx]; priv->iTDUsed[idx] > 0; desc = desc->next) {
 		if (desc->td0.owner == OWNED_BY_NIC)
 			break;
 		if (works++ > 15)
@@ -1007,7 +1007,7 @@ static int device_tx_srv(struct vnt_private *priv, unsigned int idx)
 		}
 	}
 
-	priv->apTailTD[idx] = desc;
+	priv->tail_td[idx] = desc;
 
 	return works;
 }
-- 
GitLab


From 2a4033b2d4c998d03cabe5799ae7de99f4f3254b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 31 Oct 2023 11:59:34 +0300
Subject: [PATCH 0319/4076] staging: vc04_services: remove unnecessary NULL
 check

We ensured that "service" as non-NULL in the previous if statement so
there is no need to check again here.

Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/1dff4d9b-d067-4525-95e0-ffdc1185cccd@moroto.mountain
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index 39b857da2d429..a0117efa29915 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -2040,8 +2040,7 @@ sync_func(void *v)
 			continue;
 		}
 
-		svc_fourcc = service ? service->base.fourcc
-				     : VCHIQ_MAKE_FOURCC('?', '?', '?', '?');
+		svc_fourcc = service->base.fourcc;
 
 		vchiq_log_trace(state->dev, VCHIQ_SYNC,
 				"Rcvd Msg %s from %p4cc s:%d d:%d len:%d",
-- 
GitLab


From b000ef3ca57a495deac01578f6c328b85090ecb9 Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Mon, 13 Nov 2023 16:38:38 +0700
Subject: [PATCH 0320/4076] drivers: staging: vme_user: Describe VME_BUS and
 VME_TSI148

Help description for both options only tells users to enable them
without description of what VME bridge and TSI148 device are.

Briefly describe them.

Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://lore.kernel.org/r/20231113093839.7687-1-bagasdotme@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vme_user/Kconfig | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/vme_user/Kconfig b/drivers/staging/vme_user/Kconfig
index d65cc5510649e..8e5df6ce36e8f 100644
--- a/drivers/staging/vme_user/Kconfig
+++ b/drivers/staging/vme_user/Kconfig
@@ -3,18 +3,32 @@ menuconfig VME_BUS
 	bool "VME bridge support"
 	depends on PCI
 	help
-	  If you say Y here you get support for the VME bridge Framework.
+	  Enable support for VME (VersaModular Eurocard bus) bridge modules.
+	  The bridge allows connecting VME devices to systems with existing
+	  interfaces (like USB or PCI) by means of translating VME protocol
+	  operations.
+
+	  Note that this only enables the bridge framework. You'll also
+	  likely want to enable driver for specific bridge device you have
+	  to actually use it. If unsure, say N.
 
 if VME_BUS
 
 comment "VME Bridge Drivers"
 
 config VME_TSI148
-	tristate "Tempe"
+	tristate "Tundra TSI148 VME bridge support"
 	depends on HAS_DMA
 	help
-	 If you say Y here you get support for the Tundra TSI148 VME bridge
-	 chip.
+	 If you say Y here you get support for the Tundra TSI148 VME-to-PCI/X
+	 bridge chip (and pin-compatible clones).
+
+	 TSI148 is a high-performant, 2eSST and VME64-compliant VME-to-PCI/X
+	 interconnect bridge with support for PCI and PCI-X bus interface.
+	 It is primarily used in industrial and embedded systems.
+
+	 To compile this driver as a module, say M - the module will be
+	 called vme_tsi148. If unsure, say N.
 
 config VME_FAKE
 	tristate "Fake"
-- 
GitLab


From 9996f0044f344a64377abafec252a753380d3098 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Sun, 29 Oct 2023 13:48:35 +0100
Subject: [PATCH 0321/4076] staging: vchiq_core: Make vchiq_dump_service_state
 static

The function vchiq_dump_service_state() is only used by vchiq_dump_state()
within vchiq_core.c. So move the definition of vchiq_dump_state() below
vchiq_dump_service_state() in order to make it static.

Suggested-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://lore.kernel.org/r/20231029124837.119832-2-wahrenst@gmx.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../interface/vchiq_arm/vchiq_core.c          | 169 +++++++++---------
 .../interface/vchiq_arm/vchiq_core.h          |   3 -
 2 files changed, 85 insertions(+), 87 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index a0117efa29915..0dd177b998071 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -3427,90 +3427,8 @@ vchiq_dump_shared_state(void *dump_context, struct vchiq_state *state,
 	return 0;
 }
 
-int vchiq_dump_state(void *dump_context, struct vchiq_state *state)
-{
-	char buf[80];
-	int len;
-	int i;
-	int err;
-
-	len = scnprintf(buf, sizeof(buf), "State %d: %s", state->id,
-			conn_state_names[state->conn_state]);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	len = scnprintf(buf, sizeof(buf), "  tx_pos=%x(@%pK), rx_pos=%x(@%pK)",
-			state->local->tx_pos,
-			state->tx_data + (state->local_tx_pos & VCHIQ_SLOT_MASK),
-			state->rx_pos,
-			state->rx_data + (state->rx_pos & VCHIQ_SLOT_MASK));
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	len = scnprintf(buf, sizeof(buf), "  Version: %d (min %d)",
-			VCHIQ_VERSION, VCHIQ_VERSION_MIN);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	if (VCHIQ_ENABLE_STATS) {
-		len = scnprintf(buf, sizeof(buf),
-				"  Stats: ctrl_tx_count=%d, ctrl_rx_count=%d, error_count=%d",
-				state->stats.ctrl_tx_count, state->stats.ctrl_rx_count,
-				state->stats.error_count);
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
-	}
-
-	len = scnprintf(buf, sizeof(buf),
-			"  Slots: %d available (%d data), %d recyclable, %d stalls (%d data)",
-			((state->slot_queue_available * VCHIQ_SLOT_SIZE) -
-			state->local_tx_pos) / VCHIQ_SLOT_SIZE,
-			state->data_quota - state->data_use_count,
-			state->local->slot_queue_recycle - state->slot_queue_available,
-			state->stats.slot_stalls, state->stats.data_stalls);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	err = vchiq_dump_platform_state(dump_context);
-	if (err)
-		return err;
-
-	err = vchiq_dump_shared_state(dump_context,
-				      state,
-				      state->local,
-				      "Local");
-	if (err)
-		return err;
-	err = vchiq_dump_shared_state(dump_context,
-				      state,
-				      state->remote,
-				      "Remote");
-	if (err)
-		return err;
-
-	err = vchiq_dump_platform_instances(dump_context);
-	if (err)
-		return err;
-
-	for (i = 0; i < state->unused_service; i++) {
-		struct vchiq_service *service = find_service_by_port(state, i);
-
-		if (service) {
-			err = vchiq_dump_service_state(dump_context, service);
-			vchiq_service_put(service);
-			if (err)
-				return err;
-		}
-	}
-	return 0;
-}
-
-int vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
+static int
+vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
 {
 	char buf[80];
 	int len;
@@ -3605,6 +3523,89 @@ int vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
 	return err;
 }
 
+int vchiq_dump_state(void *dump_context, struct vchiq_state *state)
+{
+	char buf[80];
+	int len;
+	int i;
+	int err;
+
+	len = scnprintf(buf, sizeof(buf), "State %d: %s", state->id,
+			conn_state_names[state->conn_state]);
+	err = vchiq_dump(dump_context, buf, len + 1);
+	if (err)
+		return err;
+
+	len = scnprintf(buf, sizeof(buf), "  tx_pos=%x(@%pK), rx_pos=%x(@%pK)",
+			state->local->tx_pos,
+			state->tx_data + (state->local_tx_pos & VCHIQ_SLOT_MASK),
+			state->rx_pos,
+			state->rx_data + (state->rx_pos & VCHIQ_SLOT_MASK));
+	err = vchiq_dump(dump_context, buf, len + 1);
+	if (err)
+		return err;
+
+	len = scnprintf(buf, sizeof(buf), "  Version: %d (min %d)",
+			VCHIQ_VERSION, VCHIQ_VERSION_MIN);
+	err = vchiq_dump(dump_context, buf, len + 1);
+	if (err)
+		return err;
+
+	if (VCHIQ_ENABLE_STATS) {
+		len = scnprintf(buf, sizeof(buf),
+				"  Stats: ctrl_tx_count=%d, ctrl_rx_count=%d, error_count=%d",
+				state->stats.ctrl_tx_count, state->stats.ctrl_rx_count,
+				state->stats.error_count);
+		err = vchiq_dump(dump_context, buf, len + 1);
+		if (err)
+			return err;
+	}
+
+	len = scnprintf(buf, sizeof(buf),
+			"  Slots: %d available (%d data), %d recyclable, %d stalls (%d data)",
+			((state->slot_queue_available * VCHIQ_SLOT_SIZE) -
+			state->local_tx_pos) / VCHIQ_SLOT_SIZE,
+			state->data_quota - state->data_use_count,
+			state->local->slot_queue_recycle - state->slot_queue_available,
+			state->stats.slot_stalls, state->stats.data_stalls);
+	err = vchiq_dump(dump_context, buf, len + 1);
+	if (err)
+		return err;
+
+	err = vchiq_dump_platform_state(dump_context);
+	if (err)
+		return err;
+
+	err = vchiq_dump_shared_state(dump_context,
+				      state,
+				      state->local,
+				      "Local");
+	if (err)
+		return err;
+	err = vchiq_dump_shared_state(dump_context,
+				      state,
+				      state->remote,
+				      "Remote");
+	if (err)
+		return err;
+
+	err = vchiq_dump_platform_instances(dump_context);
+	if (err)
+		return err;
+
+	for (i = 0; i < state->unused_service; i++) {
+		struct vchiq_service *service = find_service_by_port(state, i);
+
+		if (service) {
+			err = vchiq_dump_service_state(dump_context, service);
+			vchiq_service_put(service);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+
 int vchiq_send_remote_use(struct vchiq_state *state)
 {
 	if (state->conn_state == VCHIQ_CONNSTATE_DISCONNECTED)
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
index 161358db457cd..ea8d588447756 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
@@ -507,9 +507,6 @@ vchiq_bulk_transfer(struct vchiq_instance *instance, unsigned int handle, void *
 extern int
 vchiq_dump_state(void *dump_context, struct vchiq_state *state);
 
-extern int
-vchiq_dump_service_state(void *dump_context, struct vchiq_service *service);
-
 extern void
 vchiq_loud_error_header(void);
 
-- 
GitLab


From 20b68a673a6bd346685f3ae980c457cb6e1794ca Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Sun, 29 Oct 2023 13:48:36 +0100
Subject: [PATCH 0322/4076] staging: vchiq_core: Shorten bulk TX/RX pending
 dump

The calculation for the bulk TX/RX pending is complex and
reaches 99 chars per line. So move the size determination
below the pending calculation and get the rid of the
ternary operator.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://lore.kernel.org/r/20231029124837.119832-3-wahrenst@gmx.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../interface/vchiq_arm/vchiq_core.c          | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index 0dd177b998071..75d82a7b51090 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -3446,7 +3446,7 @@ vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
 		struct vchiq_service_quota *quota =
 			&service->state->service_quotas[service->localport];
 		int fourcc = service->base.fourcc;
-		int tx_pending, rx_pending;
+		int tx_pending, rx_pending, tx_size = 0, rx_size = 0;
 
 		if (service->remoteport != VCHIQ_PORT_FREE) {
 			int len2 = scnprintf(remoteport, sizeof(remoteport),
@@ -3471,18 +3471,23 @@ vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
 
 		tx_pending = service->bulk_tx.local_insert -
 			service->bulk_tx.remote_insert;
+		if (tx_pending) {
+			unsigned int i = BULK_INDEX(service->bulk_tx.remove);
+
+			tx_size = service->bulk_tx.bulks[i].size;
+		}
 
 		rx_pending = service->bulk_rx.local_insert -
 			service->bulk_rx.remote_insert;
+		if (rx_pending) {
+			unsigned int i = BULK_INDEX(service->bulk_rx.remove);
+
+			rx_size = service->bulk_rx.bulks[i].size;
+		}
 
 		len = scnprintf(buf, sizeof(buf),
 				"  Bulk: tx_pending=%d (size %d), rx_pending=%d (size %d)",
-				tx_pending,
-				tx_pending ?
-				service->bulk_tx.bulks[BULK_INDEX(service->bulk_tx.remove)].size :
-				0, rx_pending, rx_pending ?
-				service->bulk_rx.bulks[BULK_INDEX(service->bulk_rx.remove)].size :
-				0);
+				tx_pending, tx_size, rx_pending, rx_size);
 
 		if (VCHIQ_ENABLE_STATS) {
 			err = vchiq_dump(dump_context, buf, len + 1);
-- 
GitLab


From b43d958fbc2359e68d97cc0ce9f05cb4a0b23cbc Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Sun, 29 Oct 2023 13:48:37 +0100
Subject: [PATCH 0323/4076] staging: vchiq_arm: move state dump to debugfs

Besides the IOCTL interface the VCHIQ character device also provides
a state dump of the whole VCHIQ driver via read. Moving the state dump
function to debugfs has a lot advantages:

- following changes on state dump doesn't break userspace ABI
- debug doesn't depend on VCHIQ_CDEV
- dump code simplifies a lot and reduce the chance of buffer overflows

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Tested-by: "Ricardo B. Marliere" <ricardo@marliere.net>
Link: https://lore.kernel.org/r/20231029124837.119832-4-wahrenst@gmx.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../interface/vchiq_arm/vchiq_arm.c           |  94 ++------
 .../interface/vchiq_arm/vchiq_arm.h           |   7 -
 .../interface/vchiq_arm/vchiq_core.c          | 220 ++++++------------
 .../interface/vchiq_arm/vchiq_core.h          |  13 +-
 .../interface/vchiq_arm/vchiq_debugfs.c       |  10 +
 .../interface/vchiq_arm/vchiq_dev.c           |  21 --
 6 files changed, 107 insertions(+), 258 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 9fb8f657cc781..7978fb6dc4fbd 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -659,13 +659,9 @@ vchiq_complete_bulk(struct vchiq_instance *instance, struct vchiq_bulk *bulk)
 			      bulk->actual);
 }
 
-int vchiq_dump_platform_state(void *dump_context)
+void vchiq_dump_platform_state(struct seq_file *f)
 {
-	char buf[80];
-	int len;
-
-	len = snprintf(buf, sizeof(buf), "  Platform: 2835 (VC master)");
-	return vchiq_dump(dump_context, buf, len + 1);
+	seq_puts(f, "  Platform: 2835 (VC master)\n");
 }
 
 #define VCHIQ_INIT_RETRIES 10
@@ -1190,56 +1186,13 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 		bulk_userdata);
 }
 
-int vchiq_dump(void *dump_context, const char *str, int len)
-{
-	struct dump_context *context = (struct dump_context *)dump_context;
-	int copy_bytes;
-
-	if (context->actual >= context->space)
-		return 0;
-
-	if (context->offset > 0) {
-		int skip_bytes = min_t(int, len, context->offset);
-
-		str += skip_bytes;
-		len -= skip_bytes;
-		context->offset -= skip_bytes;
-		if (context->offset > 0)
-			return 0;
-	}
-	copy_bytes = min_t(int, len, context->space - context->actual);
-	if (copy_bytes == 0)
-		return 0;
-	if (copy_to_user(context->buf + context->actual, str,
-			 copy_bytes))
-		return -EFAULT;
-	context->actual += copy_bytes;
-	len -= copy_bytes;
-
-	/*
-	 * If the terminating NUL is included in the length, then it
-	 * marks the end of a line and should be replaced with a
-	 * carriage return.
-	 */
-	if ((len == 0) && (str[copy_bytes - 1] == '\0')) {
-		char cr = '\n';
-
-		if (copy_to_user(context->buf + context->actual - 1,
-				 &cr, 1))
-			return -EFAULT;
-	}
-	return 0;
-}
-
-int vchiq_dump_platform_instances(void *dump_context)
+void vchiq_dump_platform_instances(struct seq_file *f)
 {
 	struct vchiq_state *state = vchiq_get_state();
-	char buf[80];
-	int len;
 	int i;
 
 	if (!state)
-		return -ENOTCONN;
+		return;
 
 	/*
 	 * There is no list of instances, so instead scan all services,
@@ -1264,7 +1217,6 @@ int vchiq_dump_platform_instances(void *dump_context)
 	for (i = 0; i < state->unused_service; i++) {
 		struct vchiq_service *service;
 		struct vchiq_instance *instance;
-		int err;
 
 		rcu_read_lock();
 		service = rcu_dereference(state->services[i]);
@@ -1280,43 +1232,35 @@ int vchiq_dump_platform_instances(void *dump_context)
 		}
 		rcu_read_unlock();
 
-		len = snprintf(buf, sizeof(buf),
-			       "Instance %pK: pid %d,%s completions %d/%d",
-			       instance, instance->pid,
-			       instance->connected ? " connected, " :
-			       "",
-			       instance->completion_insert -
-			       instance->completion_remove,
-			       MAX_COMPLETIONS);
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
+		seq_printf(f, "Instance %pK: pid %d,%s completions %d/%d\n",
+			   instance, instance->pid,
+			   instance->connected ? " connected, " :
+			   "",
+			   instance->completion_insert -
+			   instance->completion_remove,
+			   MAX_COMPLETIONS);
 		instance->mark = 1;
 	}
-	return 0;
 }
 
-int vchiq_dump_platform_service_state(void *dump_context,
-				      struct vchiq_service *service)
+void vchiq_dump_platform_service_state(struct seq_file *f,
+				       struct vchiq_service *service)
 {
 	struct user_service *user_service =
 			(struct user_service *)service->base.userdata;
-	char buf[80];
-	int len;
 
-	len = scnprintf(buf, sizeof(buf), "  instance %pK", service->instance);
+	seq_printf(f, "  instance %pK", service->instance);
 
 	if ((service->base.callback == service_callback) && user_service->is_vchi) {
-		len += scnprintf(buf + len, sizeof(buf) - len, ", %d/%d messages",
-				 user_service->msg_insert - user_service->msg_remove,
-				 MSG_QUEUE_SIZE);
+		seq_printf(f, ", %d/%d messages",
+			   user_service->msg_insert - user_service->msg_remove,
+			   MSG_QUEUE_SIZE);
 
 		if (user_service->dequeue_pending)
-			len += scnprintf(buf + len, sizeof(buf) - len,
-				" (dequeue pending)");
+			seq_puts(f, " (dequeue pending)");
 	}
 
-	return vchiq_dump(dump_context, buf, len + 1);
+	seq_puts(f, "\n");
 }
 
 struct vchiq_state *
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
index 7cdc3d70bd2c1..7844ef765a00e 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
@@ -69,13 +69,6 @@ struct vchiq_instance {
 	struct vchiq_debugfs_node debugfs_node;
 };
 
-struct dump_context {
-	char __user *buf;
-	size_t actual;
-	size_t space;
-	loff_t offset;
-};
-
 extern spinlock_t msg_queue_spinlock;
 extern struct vchiq_state g_state;
 
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index 75d82a7b51090..0468689a6325b 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -3371,8 +3371,8 @@ vchiq_set_service_option(struct vchiq_instance *instance, unsigned int handle,
 	return ret;
 }
 
-static int
-vchiq_dump_shared_state(void *dump_context, struct vchiq_state *state,
+static void
+vchiq_dump_shared_state(struct seq_file *f, struct vchiq_state *state,
 			struct vchiq_shared_state *shared, const char *label)
 {
 	static const char *const debug_names[] = {
@@ -3389,57 +3389,37 @@ vchiq_dump_shared_state(void *dump_context, struct vchiq_state *state,
 		"COMPLETION_QUEUE_FULL_COUNT"
 	};
 	int i;
-	char buf[80];
-	int len;
-	int err;
-
-	len = scnprintf(buf, sizeof(buf), "  %s: slots %d-%d tx_pos=%x recycle=%x",
-			label, shared->slot_first, shared->slot_last,
-			shared->tx_pos, shared->slot_queue_recycle);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	len = scnprintf(buf, sizeof(buf), "    Slots claimed:");
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
+
+	seq_printf(f, "  %s: slots %d-%d tx_pos=%x recycle=%x\n",
+		   label, shared->slot_first, shared->slot_last,
+		   shared->tx_pos, shared->slot_queue_recycle);
+
+	seq_puts(f, "    Slots claimed:\n");
 
 	for (i = shared->slot_first; i <= shared->slot_last; i++) {
 		struct vchiq_slot_info slot_info =
 						*SLOT_INFO_FROM_INDEX(state, i);
 		if (slot_info.use_count != slot_info.release_count) {
-			len = scnprintf(buf, sizeof(buf), "      %d: %d/%d", i, slot_info.use_count,
-					slot_info.release_count);
-			err = vchiq_dump(dump_context, buf, len + 1);
-			if (err)
-				return err;
+			seq_printf(f, "      %d: %d/%d\n", i, slot_info.use_count,
+				   slot_info.release_count);
 		}
 	}
 
 	for (i = 1; i < shared->debug[DEBUG_ENTRIES]; i++) {
-		len = scnprintf(buf, sizeof(buf), "    DEBUG: %s = %d(%x)",
-				debug_names[i], shared->debug[i], shared->debug[i]);
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
+		seq_printf(f, "    DEBUG: %s = %d(%x)\n",
+			   debug_names[i], shared->debug[i], shared->debug[i]);
 	}
-	return 0;
 }
 
-static int
-vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
+static void
+vchiq_dump_service_state(struct seq_file *f, struct vchiq_service *service)
 {
-	char buf[80];
-	int len;
-	int err;
 	unsigned int ref_count;
 
 	/*Don't include the lock just taken*/
 	ref_count = kref_read(&service->ref_count) - 1;
-	len = scnprintf(buf, sizeof(buf), "Service %u: %s (ref %u)",
-			service->localport, srvstate_names[service->srvstate],
-			ref_count);
+	seq_printf(f, "Service %u: %s (ref %u)", service->localport,
+		   srvstate_names[service->srvstate], ref_count);
 
 	if (service->srvstate != VCHIQ_SRVSTATE_FREE) {
 		char remoteport[30];
@@ -3459,15 +3439,10 @@ vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
 			strscpy(remoteport, "n/a", sizeof(remoteport));
 		}
 
-		len += scnprintf(buf + len, sizeof(buf) - len,
-				 " '%p4cc' remote %s (msg use %d/%d, slot use %d/%d)",
-				 &fourcc, remoteport,
-				 quota->message_use_count, quota->message_quota,
-				 quota->slot_use_count, quota->slot_quota);
-
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
+		seq_printf(f, " '%p4cc' remote %s (msg use %d/%d, slot use %d/%d)\n",
+			   &fourcc, remoteport,
+			   quota->message_use_count, quota->message_quota,
+			   quota->slot_use_count, quota->slot_quota);
 
 		tx_pending = service->bulk_tx.local_insert -
 			service->bulk_tx.remote_insert;
@@ -3485,130 +3460,79 @@ vchiq_dump_service_state(void *dump_context, struct vchiq_service *service)
 			rx_size = service->bulk_rx.bulks[i].size;
 		}
 
-		len = scnprintf(buf, sizeof(buf),
-				"  Bulk: tx_pending=%d (size %d), rx_pending=%d (size %d)",
-				tx_pending, tx_size, rx_pending, rx_size);
+		seq_printf(f, "  Bulk: tx_pending=%d (size %d), rx_pending=%d (size %d)\n",
+			   tx_pending, tx_size, rx_pending, rx_size);
 
 		if (VCHIQ_ENABLE_STATS) {
-			err = vchiq_dump(dump_context, buf, len + 1);
-			if (err)
-				return err;
+			seq_printf(f, "  Ctrl: tx_count=%d, tx_bytes=%llu, rx_count=%d, rx_bytes=%llu\n",
+				   service->stats.ctrl_tx_count,
+				   service->stats.ctrl_tx_bytes,
+				   service->stats.ctrl_rx_count,
+				   service->stats.ctrl_rx_bytes);
 
-			len = scnprintf(buf, sizeof(buf),
-					"  Ctrl: tx_count=%d, tx_bytes=%llu, rx_count=%d, rx_bytes=%llu",
-					service->stats.ctrl_tx_count, service->stats.ctrl_tx_bytes,
-					service->stats.ctrl_rx_count, service->stats.ctrl_rx_bytes);
-			err = vchiq_dump(dump_context, buf, len + 1);
-			if (err)
-				return err;
+			seq_printf(f, "  Bulk: tx_count=%d, tx_bytes=%llu, rx_count=%d, rx_bytes=%llu\n",
+				   service->stats.bulk_tx_count,
+				   service->stats.bulk_tx_bytes,
+				   service->stats.bulk_rx_count,
+				   service->stats.bulk_rx_bytes);
 
-			len = scnprintf(buf, sizeof(buf),
-					"  Bulk: tx_count=%d, tx_bytes=%llu, rx_count=%d, rx_bytes=%llu",
-					service->stats.bulk_tx_count, service->stats.bulk_tx_bytes,
-					service->stats.bulk_rx_count, service->stats.bulk_rx_bytes);
-			err = vchiq_dump(dump_context, buf, len + 1);
-			if (err)
-				return err;
-
-			len = scnprintf(buf, sizeof(buf),
-					"  %d quota stalls, %d slot stalls, %d bulk stalls, %d aborted, %d errors",
-					service->stats.quota_stalls, service->stats.slot_stalls,
-					service->stats.bulk_stalls,
-					service->stats.bulk_aborted_count,
-					service->stats.error_count);
+			seq_printf(f, "  %d quota stalls, %d slot stalls, %d bulk stalls, %d aborted, %d errors\n",
+				   service->stats.quota_stalls,
+				   service->stats.slot_stalls,
+				   service->stats.bulk_stalls,
+				   service->stats.bulk_aborted_count,
+				   service->stats.error_count);
 		}
 	}
 
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	if (service->srvstate != VCHIQ_SRVSTATE_FREE)
-		err = vchiq_dump_platform_service_state(dump_context, service);
-	return err;
+	vchiq_dump_platform_service_state(f, service);
 }
 
-int vchiq_dump_state(void *dump_context, struct vchiq_state *state)
+void vchiq_dump_state(struct seq_file *f, struct vchiq_state *state)
 {
-	char buf[80];
-	int len;
 	int i;
-	int err;
-
-	len = scnprintf(buf, sizeof(buf), "State %d: %s", state->id,
-			conn_state_names[state->conn_state]);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	len = scnprintf(buf, sizeof(buf), "  tx_pos=%x(@%pK), rx_pos=%x(@%pK)",
-			state->local->tx_pos,
-			state->tx_data + (state->local_tx_pos & VCHIQ_SLOT_MASK),
-			state->rx_pos,
-			state->rx_data + (state->rx_pos & VCHIQ_SLOT_MASK));
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	len = scnprintf(buf, sizeof(buf), "  Version: %d (min %d)",
-			VCHIQ_VERSION, VCHIQ_VERSION_MIN);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
+
+	seq_printf(f, "State %d: %s\n", state->id,
+		   conn_state_names[state->conn_state]);
+
+	seq_printf(f, "  tx_pos=%x(@%pK), rx_pos=%x(@%pK)\n",
+		   state->local->tx_pos,
+		   state->tx_data + (state->local_tx_pos & VCHIQ_SLOT_MASK),
+		   state->rx_pos,
+		   state->rx_data + (state->rx_pos & VCHIQ_SLOT_MASK));
+
+	seq_printf(f, "  Version: %d (min %d)\n", VCHIQ_VERSION,
+		   VCHIQ_VERSION_MIN);
 
 	if (VCHIQ_ENABLE_STATS) {
-		len = scnprintf(buf, sizeof(buf),
-				"  Stats: ctrl_tx_count=%d, ctrl_rx_count=%d, error_count=%d",
-				state->stats.ctrl_tx_count, state->stats.ctrl_rx_count,
-				state->stats.error_count);
-		err = vchiq_dump(dump_context, buf, len + 1);
-		if (err)
-			return err;
-	}
-
-	len = scnprintf(buf, sizeof(buf),
-			"  Slots: %d available (%d data), %d recyclable, %d stalls (%d data)",
-			((state->slot_queue_available * VCHIQ_SLOT_SIZE) -
-			state->local_tx_pos) / VCHIQ_SLOT_SIZE,
-			state->data_quota - state->data_use_count,
-			state->local->slot_queue_recycle - state->slot_queue_available,
-			state->stats.slot_stalls, state->stats.data_stalls);
-	err = vchiq_dump(dump_context, buf, len + 1);
-	if (err)
-		return err;
-
-	err = vchiq_dump_platform_state(dump_context);
-	if (err)
-		return err;
-
-	err = vchiq_dump_shared_state(dump_context,
-				      state,
-				      state->local,
-				      "Local");
-	if (err)
-		return err;
-	err = vchiq_dump_shared_state(dump_context,
-				      state,
-				      state->remote,
-				      "Remote");
-	if (err)
-		return err;
-
-	err = vchiq_dump_platform_instances(dump_context);
-	if (err)
-		return err;
+		seq_printf(f, "  Stats: ctrl_tx_count=%d, ctrl_rx_count=%d, error_count=%d\n",
+			   state->stats.ctrl_tx_count, state->stats.ctrl_rx_count,
+			   state->stats.error_count);
+	}
+
+	seq_printf(f, "  Slots: %d available (%d data), %d recyclable, %d stalls (%d data)\n",
+		   ((state->slot_queue_available * VCHIQ_SLOT_SIZE) -
+		   state->local_tx_pos) / VCHIQ_SLOT_SIZE,
+		   state->data_quota - state->data_use_count,
+		   state->local->slot_queue_recycle - state->slot_queue_available,
+		   state->stats.slot_stalls, state->stats.data_stalls);
+
+	vchiq_dump_platform_state(f);
+
+	vchiq_dump_shared_state(f, state, state->local, "Local");
+
+	vchiq_dump_shared_state(f, state, state->remote, "Remote");
+
+	vchiq_dump_platform_instances(f);
 
 	for (i = 0; i < state->unused_service; i++) {
 		struct vchiq_service *service = find_service_by_port(state, i);
 
 		if (service) {
-			err = vchiq_dump_service_state(dump_context, service);
+			vchiq_dump_service_state(f, service);
 			vchiq_service_put(service);
-			if (err)
-				return err;
 		}
 	}
-	return 0;
 }
 
 int vchiq_send_remote_use(struct vchiq_state *state)
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
index ea8d588447756..564b5c7072672 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
@@ -6,6 +6,7 @@
 
 #include <linux/mutex.h>
 #include <linux/completion.h>
+#include <linux/debugfs.h>
 #include <linux/dev_printk.h>
 #include <linux/kthread.h>
 #include <linux/kref.h>
@@ -504,8 +505,8 @@ vchiq_bulk_transfer(struct vchiq_instance *instance, unsigned int handle, void *
 		    void __user *uoffset, int size, void *userdata, enum vchiq_bulk_mode mode,
 		    enum vchiq_bulk_dir dir);
 
-extern int
-vchiq_dump_state(void *dump_context, struct vchiq_state *state);
+extern void
+vchiq_dump_state(struct seq_file *f, struct vchiq_state *state);
 
 extern void
 vchiq_loud_error_header(void);
@@ -561,13 +562,11 @@ void vchiq_complete_bulk(struct vchiq_instance *instance, struct vchiq_bulk *bul
 
 void remote_event_signal(struct remote_event *event);
 
-int vchiq_dump(void *dump_context, const char *str, int len);
-
-int vchiq_dump_platform_state(void *dump_context);
+void vchiq_dump_platform_state(struct seq_file *f);
 
-int vchiq_dump_platform_instances(void *dump_context);
+void vchiq_dump_platform_instances(struct seq_file *f);
 
-int vchiq_dump_platform_service_state(void *dump_context, struct vchiq_service *service);
+void vchiq_dump_platform_service_state(struct seq_file *f, struct vchiq_service *service);
 
 int vchiq_use_service_internal(struct vchiq_service *service);
 
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c
index 58db78a9c8d4c..d833e4e2973a7 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c
@@ -40,6 +40,13 @@ static int debugfs_trace_show(struct seq_file *f, void *offset)
 	return 0;
 }
 
+static int vchiq_dump_show(struct seq_file *f, void *offset)
+{
+	vchiq_dump_state(f, &g_state);
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(vchiq_dump);
+
 static int debugfs_trace_open(struct inode *inode, struct file *file)
 {
 	return single_open(file, debugfs_trace_show, inode->i_private);
@@ -115,6 +122,9 @@ void vchiq_debugfs_init(void)
 {
 	vchiq_dbg_dir = debugfs_create_dir("vchiq", NULL);
 	vchiq_dbg_clients = debugfs_create_dir("clients", vchiq_dbg_dir);
+
+	debugfs_create_file("state", S_IFREG | 0444, vchiq_dbg_dir, NULL,
+			    &vchiq_dump_fops);
 }
 
 /* remove all the debugfs entries */
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
index 0bc93f48c14cb..307a2d76cbb74 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
@@ -1306,26 +1306,6 @@ out:
 	return ret;
 }
 
-static ssize_t
-vchiq_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
-{
-	struct dump_context context;
-	int err;
-
-	context.buf = buf;
-	context.actual = 0;
-	context.space = count;
-	context.offset = *ppos;
-
-	err = vchiq_dump_state(&context, &g_state);
-	if (err)
-		return err;
-
-	*ppos += context.actual;
-
-	return context.actual;
-}
-
 static const struct file_operations
 vchiq_fops = {
 	.owner = THIS_MODULE,
@@ -1335,7 +1315,6 @@ vchiq_fops = {
 #endif
 	.open = vchiq_open,
 	.release = vchiq_release,
-	.read = vchiq_read
 };
 
 static struct miscdevice vchiq_miscdev = {
-- 
GitLab


From 280b4e4a9e8009affd8f20ec2d467cb4deb05c1c Mon Sep 17 00:00:00 2001
From: Benjamin Gray <bgray@linux.ibm.com>
Date: Tue, 12 Sep 2023 16:07:59 +1000
Subject: [PATCH 0324/4076] perf tools: Address python 3.6 DeprecationWarning
 for string scapes

Python 3.6 introduced a DeprecationWarning for invalid escape sequences.
This is upgraded to a SyntaxWarning in Python 3.12, and will eventually
be a syntax error.

Fix these now to get ahead of it before it's an error.

Signed-off-by: Benjamin Gray <bgray@linux.ibm.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Hartley Sweeten <hsweeten@visionengravers.com>
Cc: Ian Abbott <abbotti@mev.co.uk>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mykola Lysenko <mykolal@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Todd E Brandt <todd.e.brandt@linux.intel.com>
Cc: Tom Rix <trix@redhat.com>
Cc: linux-doc@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Cc: linux-kselftest@vger.kernel.org
Cc: linux-pm@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230912060801.95533-6-bgray@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.py                 | 2 +-
 tools/perf/scripts/python/arm-cs-trace-disasm.py | 4 ++--
 tools/perf/scripts/python/compaction-times.py    | 2 +-
 tools/perf/scripts/python/exported-sql-viewer.py | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 3c091ab753059..0093c998cb6e6 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -83,7 +83,7 @@ def c_len(s: str) -> int:
   """Return the length of s a C string
 
   This doesn't handle all escape characters properly. It first assumes
-  all \ are for escaping, it then adjusts as it will have over counted
+  all \\ are for escaping, it then adjusts as it will have over counted
   \\. The code uses \000 rather than \0 as a terminator as an adjacent
   number would be folded into a string of \0 (ie. "\0" + "5" doesn't
   equal a terminator followed by the number 5 but the escape of
diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index d59ff53f1d946..de58991c78bb4 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -45,8 +45,8 @@ parser = OptionParser(option_list=option_list)
 # Initialize global dicts and regular expression
 disasm_cache = dict()
 cpu_data = dict()
-disasm_re = re.compile("^\s*([0-9a-fA-F]+):")
-disasm_func_re = re.compile("^\s*([0-9a-fA-F]+)\s.*:")
+disasm_re = re.compile(r"^\s*([0-9a-fA-F]+):")
+disasm_func_re = re.compile(r"^\s*([0-9a-fA-F]+)\s.*:")
 cache_size = 64*1024
 
 glb_source_file_name	= None
diff --git a/tools/perf/scripts/python/compaction-times.py b/tools/perf/scripts/python/compaction-times.py
index 2560a042dc6fa..9401f7c147477 100644
--- a/tools/perf/scripts/python/compaction-times.py
+++ b/tools/perf/scripts/python/compaction-times.py
@@ -260,7 +260,7 @@ def pr_help():
 
 comm_re = None
 pid_re = None
-pid_regex = "^(\d*)-(\d*)$|^(\d*)$"
+pid_regex = r"^(\d*)-(\d*)$|^(\d*)$"
 
 opt_proc = popt.DISP_DFL
 opt_disp = topt.DISP_ALL
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 13f2d8a816109..121cf61ba1b34 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -677,8 +677,8 @@ class CallGraphModelBase(TreeModel):
 			#   sqlite supports GLOB (text only) which uses * and ? and is case sensitive
 			if not self.glb.dbref.is_sqlite3:
 				# Escape % and _
-				s = value.replace("%", "\%")
-				s = s.replace("_", "\_")
+				s = value.replace("%", "\\%")
+				s = s.replace("_", "\\_")
 				# Translate * and ? into SQL LIKE pattern characters % and _
 				trans = string.maketrans("*?", "%_")
 				match = " LIKE '" + str(s).translate(trans) + "'"
-- 
GitLab


From 87f33a1b8f7e3d223fc331fe54fd8ec337dc9cb9 Mon Sep 17 00:00:00 2001
From: Flavio Suligoi <f.suligoi@asem.it>
Date: Thu, 16 Nov 2023 11:53:18 +0100
Subject: [PATCH 0325/4076] dt-bindings: backlight: mp3309c: Remove two
 required properties

The two properties:

- max-brightness
- default brightness

are not really required, so they can be removed from the "required"
section.
The "max-brightness" is no longer used in the current version
of the driver (it was used only in the first version).
The "default-brightness", if omitted in the DT, is managed by the
device driver, using a default value. This value depends on the dimming
mode used:

- for the "analog mode", via I2C commands, this value is fixed by
  hardware (=31)
- while in case of pwm mode the default used is the last value of the
  brightness-levels array.

Also the brightness-levels array is not required:

- in "analog mode", via I2C commands, the brightness-level array is
  fixed by hardware (0..31).;
- in pwm dimming mode, the driver uses a default array of 0..255 and
  the "default-brightness" is the last one, which is "255"

NOTE: there are no compatibility problems with the previous version,
      since the device driver has not yet been included in any kernel.
      Only this dt-binding yaml file is already included in the current
      v6.7.0-rc1 kernel version.
      No developer may have used it.

Other changes:

- improve the backlight working mode description, in the "description"
  section
- update the example, removing the "max-brightness" and introducing the
  "brightess-levels" property

Signed-off-by: Flavio Suligoi <f.suligoi@asem.it>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20231116105319.957600-2-f.suligoi@asem.it
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../bindings/leds/backlight/mps,mp3309c.yaml           | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml b/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
index 4191e33626f51..527a37368ed74 100644
--- a/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
+++ b/Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
@@ -14,8 +14,8 @@ description: |
   programmable switching frequency to optimize efficiency.
   It supports two different dimming modes:
 
-  - analog mode, via I2C commands (default)
-  - PWM controlled mode.
+  - analog mode, via I2C commands, as default mode (32 dimming levels)
+  - PWM controlled mode (optional)
 
   The datasheet is available at:
   https://www.monolithicpower.com/en/mp3309c.html
@@ -50,8 +50,6 @@ properties:
 required:
   - compatible
   - reg
-  - max-brightness
-  - default-brightness
 
 unevaluatedProperties: false
 
@@ -66,8 +64,8 @@ examples:
             compatible = "mps,mp3309c";
             reg = <0x17>;
             pwms = <&pwm1 0 3333333 0>; /* 300 Hz --> (1/f) * 1*10^9 */
-            max-brightness = <100>;
-            default-brightness = <80>;
+            brightness-levels = <0 4 8 16 32 64 128 255>;
+            default-brightness = <6>;
             mps,overvoltage-protection-microvolt = <24000000>;
         };
     };
-- 
GitLab


From 2e914516a58cf86bd0e42c7d3e25c81d44ec2ab8 Mon Sep 17 00:00:00 2001
From: Flavio Suligoi <f.suligoi@asem.it>
Date: Thu, 16 Nov 2023 11:53:19 +0100
Subject: [PATCH 0326/4076] backlight: mp3309c: Add support for MPS MP3309C

The Monolithic Power (MPS) MP3309C is a WLED step-up converter, featuring a
programmable switching frequency to optimize efficiency.
The brightness can be controlled either by I2C commands (called "analog"
mode) or by a PWM input signal (PWM mode).
This driver supports both modes.

For DT configuration details, please refer to:
- Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml

The datasheet is available at:
- https://www.monolithicpower.com/en/mp3309c.html

Signed-off-by: Flavio Suligoi <f.suligoi@asem.it>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20231116105319.957600-3-f.suligoi@asem.it
Signed-off-by: Lee Jones <lee@kernel.org>
---
 MAINTAINERS                       |   7 +
 drivers/video/backlight/Kconfig   |  11 +
 drivers/video/backlight/Makefile  |   1 +
 drivers/video/backlight/mp3309c.c | 443 ++++++++++++++++++++++++++++++
 4 files changed, 462 insertions(+)
 create mode 100644 drivers/video/backlight/mp3309c.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cfd..c00952c462026 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14658,6 +14658,13 @@ S:	Maintained
 F:	Documentation/driver-api/tty/moxa-smartio.rst
 F:	drivers/tty/mxser.*
 
+MP3309C BACKLIGHT DRIVER
+M:	Flavio Suligoi <f.suligoi@asem.it>
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
+F:	drivers/video/backlight/mp3309c.c
+
 MR800 AVERMEDIA USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index 51387b1ef012a..1144a54a35c01 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -402,6 +402,17 @@ config BACKLIGHT_LP8788
 	help
 	  This supports TI LP8788 backlight driver.
 
+config BACKLIGHT_MP3309C
+	tristate "Backlight Driver for MPS MP3309C"
+	depends on I2C && PWM
+	select REGMAP_I2C
+	help
+	  This supports MPS MP3309C backlight WLED driver in both PWM and
+	  analog/I2C dimming modes.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called mp3309c.
+
 config BACKLIGHT_PANDORA
 	tristate "Backlight driver for Pandora console"
 	depends on TWL4030_CORE
diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile
index f72e1c3c59e95..1af583de665bb 100644
--- a/drivers/video/backlight/Makefile
+++ b/drivers/video/backlight/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_BACKLIGHT_LP855X)		+= lp855x_bl.o
 obj-$(CONFIG_BACKLIGHT_LP8788)		+= lp8788_bl.o
 obj-$(CONFIG_BACKLIGHT_LV5207LP)	+= lv5207lp.o
 obj-$(CONFIG_BACKLIGHT_MAX8925)		+= max8925_bl.o
+obj-$(CONFIG_BACKLIGHT_MP3309C)		+= mp3309c.o
 obj-$(CONFIG_BACKLIGHT_MT6370)		+= mt6370-backlight.o
 obj-$(CONFIG_BACKLIGHT_OMAP1)		+= omap1_bl.o
 obj-$(CONFIG_BACKLIGHT_PANDORA)		+= pandora_bl.o
diff --git a/drivers/video/backlight/mp3309c.c b/drivers/video/backlight/mp3309c.c
new file mode 100644
index 0000000000000..3fe4469ef43fd
--- /dev/null
+++ b/drivers/video/backlight/mp3309c.c
@@ -0,0 +1,443 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Driver for MPS MP3309C White LED driver with I2C interface
+ *
+ * This driver support both analog (by I2C commands) and PWM dimming control
+ * modes.
+ *
+ * Copyright (C) 2023 ASEM Srl
+ * Author: Flavio Suligoi <f.suligoi@asem.it>
+ *
+ * Based on pwm_bl.c
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/pwm.h>
+#include <linux/regmap.h>
+
+#define REG_I2C_0	0x00
+#define REG_I2C_1	0x01
+
+#define REG_I2C_0_EN	0x80
+#define REG_I2C_0_D0	0x40
+#define REG_I2C_0_D1	0x20
+#define REG_I2C_0_D2	0x10
+#define REG_I2C_0_D3	0x08
+#define REG_I2C_0_D4	0x04
+#define REG_I2C_0_RSRV1	0x02
+#define REG_I2C_0_RSRV2	0x01
+
+#define REG_I2C_1_RSRV1	0x80
+#define REG_I2C_1_DIMS	0x40
+#define REG_I2C_1_SYNC	0x20
+#define REG_I2C_1_OVP0	0x10
+#define REG_I2C_1_OVP1	0x08
+#define REG_I2C_1_VOS	0x04
+#define REG_I2C_1_LEDO	0x02
+#define REG_I2C_1_OTP	0x01
+
+#define ANALOG_I2C_NUM_LEVELS	32		/* 0..31 */
+#define ANALOG_I2C_REG_MASK	0x7c
+
+#define MP3309C_PWM_DEFAULT_NUM_LEVELS	256	/* 0..255 */
+
+enum mp3309c_status_value {
+	FIRST_POWER_ON,
+	BACKLIGHT_OFF,
+	BACKLIGHT_ON,
+};
+
+enum mp3309c_dimming_mode_value {
+	DIMMING_PWM,
+	DIMMING_ANALOG_I2C,
+};
+
+struct mp3309c_platform_data {
+	unsigned int max_brightness;
+	unsigned int default_brightness;
+	unsigned int *levels;
+	u8  dimming_mode;
+	u8  over_voltage_protection;
+	bool sync_mode;
+	u8 status;
+};
+
+struct mp3309c_chip {
+	struct device *dev;
+	struct mp3309c_platform_data *pdata;
+	struct backlight_device *bl;
+	struct gpio_desc *enable_gpio;
+	struct regmap *regmap;
+	struct pwm_device *pwmd;
+};
+
+static const struct regmap_config mp3309c_regmap = {
+	.name = "mp3309c_regmap",
+	.reg_bits = 8,
+	.reg_stride = 1,
+	.val_bits = 8,
+	.max_register = REG_I2C_1,
+};
+
+static int mp3309c_enable_device(struct mp3309c_chip *chip)
+{
+	u8 reg_val;
+	int ret;
+
+	/* I2C register #0 - Device enable */
+	ret = regmap_update_bits(chip->regmap, REG_I2C_0, REG_I2C_0_EN,
+				 REG_I2C_0_EN);
+	if (ret)
+		return ret;
+
+	/*
+	 * I2C register #1 - Set working mode:
+	 *  - set one of the two dimming mode:
+	 *    - PWM dimming using an external PWM dimming signal
+	 *    - analog dimming using I2C commands
+	 *  - enable/disable synchronous mode
+	 *  - set overvoltage protection (OVP)
+	 */
+	reg_val = 0x00;
+	if (chip->pdata->dimming_mode == DIMMING_PWM)
+		reg_val |= REG_I2C_1_DIMS;
+	if (chip->pdata->sync_mode)
+		reg_val |= REG_I2C_1_SYNC;
+	reg_val |= chip->pdata->over_voltage_protection;
+	ret = regmap_write(chip->regmap, REG_I2C_1, reg_val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mp3309c_bl_update_status(struct backlight_device *bl)
+{
+	struct mp3309c_chip *chip = bl_get_data(bl);
+	int brightness = backlight_get_brightness(bl);
+	struct pwm_state pwmstate;
+	unsigned int analog_val, bits_val;
+	int i, ret;
+
+	if (chip->pdata->dimming_mode == DIMMING_PWM) {
+		/*
+		 * PWM control mode
+		 */
+		pwm_get_state(chip->pwmd, &pwmstate);
+		pwm_set_relative_duty_cycle(&pwmstate,
+					    chip->pdata->levels[brightness],
+					    chip->pdata->levels[chip->pdata->max_brightness]);
+		pwmstate.enabled = true;
+		ret = pwm_apply_state(chip->pwmd, &pwmstate);
+		if (ret)
+			return ret;
+
+		switch (chip->pdata->status) {
+		case FIRST_POWER_ON:
+		case BACKLIGHT_OFF:
+			/*
+			 * After 20ms of low pwm signal level, the chip turns
+			 * off automatically. In this case, before enabling the
+			 * chip again, we must wait about 10ms for pwm signal to
+			 * stabilize.
+			 */
+			if (brightness > 0) {
+				msleep(10);
+				mp3309c_enable_device(chip);
+				chip->pdata->status = BACKLIGHT_ON;
+			} else {
+				chip->pdata->status = BACKLIGHT_OFF;
+			}
+			break;
+		case BACKLIGHT_ON:
+			if (brightness == 0)
+				chip->pdata->status = BACKLIGHT_OFF;
+			break;
+		}
+	} else {
+		/*
+		 * Analog (by I2C command) control mode
+		 *
+		 * The first time, before setting brightness, we must enable the
+		 * device
+		 */
+		if (chip->pdata->status == FIRST_POWER_ON)
+			mp3309c_enable_device(chip);
+
+		/*
+		 * Dimming mode I2C command (fixed dimming range 0..31)
+		 *
+		 * The 5 bits of the dimming analog value D4..D0 is allocated
+		 * in the I2C register #0, in the following way:
+		 *
+		 *     +--+--+--+--+--+--+--+--+
+		 *     |EN|D0|D1|D2|D3|D4|XX|XX|
+		 *     +--+--+--+--+--+--+--+--+
+		 */
+		analog_val = brightness;
+		bits_val = 0;
+		for (i = 0; i <= 5; i++)
+			bits_val += ((analog_val >> i) & 0x01) << (6 - i);
+		ret = regmap_update_bits(chip->regmap, REG_I2C_0,
+					 ANALOG_I2C_REG_MASK, bits_val);
+		if (ret)
+			return ret;
+
+		if (brightness > 0)
+			chip->pdata->status = BACKLIGHT_ON;
+		else
+			chip->pdata->status = BACKLIGHT_OFF;
+	}
+
+	return 0;
+}
+
+static const struct backlight_ops mp3309c_bl_ops = {
+	.update_status = mp3309c_bl_update_status,
+};
+
+static int pm3309c_parse_dt_node(struct mp3309c_chip *chip,
+				 struct mp3309c_platform_data *pdata)
+{
+	struct device_node *node = chip->dev->of_node;
+	struct property *prop_pwms, *prop_levels;
+	int length = 0;
+	int ret, i;
+	unsigned int num_levels, tmp_value;
+
+	if (!node) {
+		dev_err(chip->dev, "failed to get DT node\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * Dimming mode: the MP3309C provides two dimming control mode:
+	 *
+	 * - PWM mode
+	 * - Analog by I2C control mode (default)
+	 *
+	 * I2C control mode is assumed as default but, if the pwms property is
+	 * found in the backlight node, the mode switches to PWM mode.
+	 */
+	pdata->dimming_mode = DIMMING_ANALOG_I2C;
+	prop_pwms = of_find_property(node, "pwms", &length);
+	if (prop_pwms) {
+		chip->pwmd = devm_pwm_get(chip->dev, NULL);
+		if (IS_ERR(chip->pwmd))
+			return dev_err_probe(chip->dev, PTR_ERR(chip->pwmd),
+					     "error getting pwm data\n");
+		pdata->dimming_mode = DIMMING_PWM;
+		pwm_apply_args(chip->pwmd);
+	}
+
+	/*
+	 * In I2C control mode the dimming levels (0..31) are fixed by the
+	 * hardware, while in PWM control mode they can be chosen by the user,
+	 * to allow nonlinear mappings.
+	 */
+	if  (pdata->dimming_mode == DIMMING_ANALOG_I2C) {
+		/*
+		 * Analog (by I2C commands) control mode: fixed 0..31 brightness
+		 * levels
+		 */
+		num_levels = ANALOG_I2C_NUM_LEVELS;
+
+		/* Enable GPIO used in I2C dimming mode only */
+		chip->enable_gpio = devm_gpiod_get(chip->dev, "enable",
+						   GPIOD_OUT_HIGH);
+		if (IS_ERR(chip->enable_gpio))
+			return dev_err_probe(chip->dev,
+					     PTR_ERR(chip->enable_gpio),
+					     "error getting enable gpio\n");
+	} else {
+		/*
+		 * PWM control mode: check for brightness level in DT
+		 */
+		prop_levels = of_find_property(node, "brightness-levels",
+					       &length);
+		if (prop_levels) {
+			/* Read brightness levels from DT */
+			num_levels = length / sizeof(u32);
+			if (num_levels < 2)
+				return -EINVAL;
+		} else {
+			/* Use default brightness levels */
+			num_levels = MP3309C_PWM_DEFAULT_NUM_LEVELS;
+		}
+	}
+
+	/* Fill brightness levels array */
+	pdata->levels = devm_kcalloc(chip->dev, num_levels,
+				     sizeof(*pdata->levels), GFP_KERNEL);
+	if (!pdata->levels)
+		return -ENOMEM;
+	if (prop_levels) {
+		ret = of_property_read_u32_array(node, "brightness-levels",
+						 pdata->levels,
+						 num_levels);
+		if (ret < 0)
+			return ret;
+	} else {
+		for (i = 0; i < num_levels; i++)
+			pdata->levels[i] = i;
+	}
+
+	pdata->max_brightness = num_levels - 1;
+
+	ret = of_property_read_u32(node, "default-brightness",
+				   &pdata->default_brightness);
+	if (ret)
+		pdata->default_brightness = pdata->max_brightness;
+	if (pdata->default_brightness > pdata->max_brightness) {
+		dev_err(chip->dev,
+			"default brightness exceeds max brightness\n");
+		pdata->default_brightness = pdata->max_brightness;
+	}
+
+	/*
+	 * Over-voltage protection (OVP)
+	 *
+	 * This (optional) property values are:
+	 *
+	 *  - 13.5V
+	 *  - 24V
+	 *  - 35.5V (hardware default setting)
+	 *
+	 * If missing, the default value for OVP is 35.5V
+	 */
+	pdata->over_voltage_protection = REG_I2C_1_OVP1;
+	if (!of_property_read_u32(node, "mps,overvoltage-protection-microvolt",
+				  &tmp_value)) {
+		switch (tmp_value) {
+		case 13500000:
+			pdata->over_voltage_protection = 0x00;
+			break;
+		case 24000000:
+			pdata->over_voltage_protection = REG_I2C_1_OVP0;
+			break;
+		case 35500000:
+			pdata->over_voltage_protection = REG_I2C_1_OVP1;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	/* Synchronous (default) and non-synchronous mode */
+	pdata->sync_mode = true;
+	if (of_property_read_bool(node, "mps,no-sync-mode"))
+		pdata->sync_mode = false;
+
+	return 0;
+}
+
+static int mp3309c_probe(struct i2c_client *client)
+{
+	struct mp3309c_platform_data *pdata = dev_get_platdata(&client->dev);
+	struct mp3309c_chip *chip;
+	struct backlight_properties props;
+	struct pwm_state pwmstate;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		dev_err(&client->dev, "failed to check i2c functionality\n");
+		return -EOPNOTSUPP;
+	}
+
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->dev = &client->dev;
+
+	chip->regmap = devm_regmap_init_i2c(client, &mp3309c_regmap);
+	if (IS_ERR(chip->regmap))
+		return dev_err_probe(&client->dev, PTR_ERR(chip->regmap),
+				     "failed to allocate register map\n");
+
+	i2c_set_clientdata(client, chip);
+
+	if (!pdata) {
+		pdata = devm_kzalloc(chip->dev, sizeof(*pdata), GFP_KERNEL);
+		if (!pdata)
+			return -ENOMEM;
+
+		ret = pm3309c_parse_dt_node(chip, pdata);
+		if (ret)
+			return ret;
+	}
+	chip->pdata = pdata;
+
+	/* Backlight properties */
+	props.brightness = pdata->default_brightness;
+	props.max_brightness = pdata->max_brightness;
+	props.scale = BACKLIGHT_SCALE_LINEAR;
+	props.type = BACKLIGHT_RAW;
+	props.power = FB_BLANK_UNBLANK;
+	props.fb_blank = FB_BLANK_UNBLANK;
+	chip->bl = devm_backlight_device_register(chip->dev, "mp3309c",
+						  chip->dev, chip,
+						  &mp3309c_bl_ops, &props);
+	if (IS_ERR(chip->bl))
+		return dev_err_probe(chip->dev, PTR_ERR(chip->bl),
+				     "error registering backlight device\n");
+
+	/* In PWM dimming mode, enable pwm device */
+	if (chip->pdata->dimming_mode == DIMMING_PWM) {
+		pwm_init_state(chip->pwmd, &pwmstate);
+		pwm_set_relative_duty_cycle(&pwmstate,
+					    chip->pdata->default_brightness,
+					    chip->pdata->max_brightness);
+		pwmstate.enabled = true;
+		ret = pwm_apply_state(chip->pwmd, &pwmstate);
+		if (ret)
+			return dev_err_probe(chip->dev, ret,
+					     "error setting pwm device\n");
+	}
+
+	chip->pdata->status = FIRST_POWER_ON;
+	backlight_update_status(chip->bl);
+
+	return 0;
+}
+
+static void mp3309c_remove(struct i2c_client *client)
+{
+	struct mp3309c_chip *chip = i2c_get_clientdata(client);
+	struct backlight_device *bl = chip->bl;
+
+	bl->props.power = FB_BLANK_POWERDOWN;
+	bl->props.brightness = 0;
+	backlight_update_status(chip->bl);
+}
+
+static const struct of_device_id mp3309c_match_table[] = {
+	{ .compatible = "mps,mp3309c", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, mp3309c_match_table);
+
+static const struct i2c_device_id mp3309c_id[] = {
+	{ "mp3309c", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, mp3309c_id);
+
+static struct i2c_driver mp3309c_i2c_driver = {
+	.driver	= {
+			.name		= KBUILD_MODNAME,
+			.of_match_table	= mp3309c_match_table,
+	},
+	.probe		= mp3309c_probe,
+	.remove		= mp3309c_remove,
+	.id_table	= mp3309c_id,
+};
+
+module_i2c_driver(mp3309c_i2c_driver);
+
+MODULE_DESCRIPTION("Backlight Driver for MPS MP3309C");
+MODULE_AUTHOR("Flavio Suligoi <f.suligoi@asem.it>");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 58793f263abc8e5233fabf7466219202db09d048 Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Fri, 17 Nov 2023 13:06:25 +0100
Subject: [PATCH 0327/4076] backlight: pwm_bl: Use dev_err_probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use dev_err_probe to simplify error paths. Also let dev_err_probe handle
the -EPROBE_DEFER case and add an entry to
/sys/kernel/debug/devices_deferred when deferred.

Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20231117120625.2398417-1-alexander.stein@ew.tq-group.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/pwm_bl.c | 34 +++++++++++++++++---------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index 289bd9ce4d36d..5bc9c6c075710 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -461,10 +461,9 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 
 	if (!data) {
 		ret = pwm_backlight_parse_dt(&pdev->dev, &defdata);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "failed to find platform data\n");
-			return ret;
-		}
+		if (ret < 0)
+			return dev_err_probe(&pdev->dev, ret,
+					     "failed to find platform data\n");
 
 		data = &defdata;
 	}
@@ -493,24 +492,27 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	pb->enable_gpio = devm_gpiod_get_optional(&pdev->dev, "enable",
 						  GPIOD_ASIS);
 	if (IS_ERR(pb->enable_gpio)) {
-		ret = PTR_ERR(pb->enable_gpio);
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(pb->enable_gpio),
+				    "failed to acquire enable GPIO\n");
 		goto err_alloc;
 	}
 
 	pb->power_supply = devm_regulator_get_optional(&pdev->dev, "power");
 	if (IS_ERR(pb->power_supply)) {
 		ret = PTR_ERR(pb->power_supply);
-		if (ret == -ENODEV)
+		if (ret == -ENODEV) {
 			pb->power_supply = NULL;
-		else
+		} else {
+			dev_err_probe(&pdev->dev, ret,
+				      "failed to acquire power regulator\n");
 			goto err_alloc;
+		}
 	}
 
 	pb->pwm = devm_pwm_get(&pdev->dev, NULL);
 	if (IS_ERR(pb->pwm)) {
-		ret = PTR_ERR(pb->pwm);
-		if (ret != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "unable to request PWM\n");
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(pb->pwm),
+				    "unable to request PWM\n");
 		goto err_alloc;
 	}
 
@@ -530,8 +532,8 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 
 	ret = pwm_apply_state(pb->pwm, &state);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
-			ret);
+		dev_err_probe(&pdev->dev, ret,
+			      "failed to apply initial PWM state");
 		goto err_alloc;
 	}
 
@@ -568,8 +570,8 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 		ret = pwm_backlight_brightness_default(&pdev->dev, data,
 						       state.period);
 		if (ret < 0) {
-			dev_err(&pdev->dev,
-				"failed to setup default brightness table\n");
+			dev_err_probe(&pdev->dev, ret,
+				      "failed to setup default brightness table\n");
 			goto err_alloc;
 		}
 
@@ -597,8 +599,8 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	bl = backlight_device_register(dev_name(&pdev->dev), &pdev->dev, pb,
 				       &pwm_backlight_ops, &props);
 	if (IS_ERR(bl)) {
-		dev_err(&pdev->dev, "failed to register backlight\n");
-		ret = PTR_ERR(bl);
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(bl),
+				    "failed to register backlight\n");
 		goto err_alloc;
 	}
 
-- 
GitLab


From ad90d0358bd3b4554f243a425168fc7cebe7d04e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:29 +0100
Subject: [PATCH 0328/4076] serial: 8250: omap: Don't skip resource freeing if
 pm_runtime_resume_and_get() failed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Returning an error code from .remove() makes the driver core emit the
little helpful error message:

	remove callback returned a non-zero value. This will be ignored.

and then remove the device anyhow. So all resources that were not freed
are leaked in this case. Skipping serial8250_unregister_port() has the
potential to keep enough of the UART around to trigger a use-after-free.

So replace the error return (and with it the little helpful error
message) by a more useful error message and continue to cleanup.

Fixes: e3f0c638f428 ("serial: 8250: omap: Fix unpaired pm_runtime_put_sync() in omap8250_remove()")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231110152927.70601-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_omap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 2d42f485c9876..661a83dbc11b0 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -1592,7 +1592,7 @@ static int omap8250_remove(struct platform_device *pdev)
 
 	err = pm_runtime_resume_and_get(&pdev->dev);
 	if (err)
-		return err;
+		dev_err(&pdev->dev, "Failed to resume hardware\n");
 
 	up = serial8250_get_port(priv->line);
 	omap_8250_shutdown(&up->port);
-- 
GitLab


From 7635d71e6a4bef6751d85bf3014ed135a83fe352 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:30 +0100
Subject: [PATCH 0329/4076] serial: sccnxp: Improve error message if
 regulator_disable() fails
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Returning an error code from .remove() makes the driver core emit the
little helpful error message:

	remove callback returned a non-zero value. This will be ignored.

and then remove the device anyhow.

So replace the error return (and with it the little helpful error
message) by a more useful error message.

Fixes: 31815c08fc90 ("serial: sccnxp: Replace pdata.init/exit with regulator API")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sccnxp.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c
index 2be2c10980253..8269b0fb30832 100644
--- a/drivers/tty/serial/sccnxp.c
+++ b/drivers/tty/serial/sccnxp.c
@@ -1036,8 +1036,11 @@ static int sccnxp_remove(struct platform_device *pdev)
 
 	uart_unregister_driver(&s->uart);
 
-	if (!IS_ERR(s->regulator))
-		return regulator_disable(s->regulator);
+	if (!IS_ERR(s->regulator)) {
+		int ret = regulator_disable(s->regulator);
+		if (ret)
+			dev_err(&pdev->dev, "Failed to disable regulator\n");
+	}
 
 	return 0;
 }
-- 
GitLab


From 7e1efdf8fce4b09d9d22befaa2c36906eff5dc37 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:31 +0100
Subject: [PATCH 0330/4076] serial: 8250: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com> # 8250_bcm*
Link: https://lore.kernel.org/r/20231110152927.70601-4-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_aspeed_vuart.c | 6 ++----
 drivers/tty/serial/8250/8250_bcm2835aux.c   | 6 ++----
 drivers/tty/serial/8250/8250_bcm7271.c      | 5 ++---
 drivers/tty/serial/8250/8250_core.c         | 5 ++---
 drivers/tty/serial/8250/8250_dw.c           | 6 ++----
 drivers/tty/serial/8250/8250_em.c           | 5 ++---
 drivers/tty/serial/8250/8250_fsl.c          | 5 ++---
 drivers/tty/serial/8250/8250_ingenic.c      | 5 ++---
 drivers/tty/serial/8250/8250_ioc3.c         | 5 ++---
 drivers/tty/serial/8250/8250_lpc18xx.c      | 6 ++----
 drivers/tty/serial/8250/8250_mtk.c          | 6 ++----
 drivers/tty/serial/8250/8250_of.c           | 5 ++---
 drivers/tty/serial/8250/8250_omap.c         | 5 ++---
 drivers/tty/serial/8250/8250_pxa.c          | 6 ++----
 drivers/tty/serial/8250/8250_tegra.c        | 6 ++----
 drivers/tty/serial/8250/8250_uniphier.c     | 6 ++----
 16 files changed, 32 insertions(+), 56 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c
index d7482ae33a1ca..8c2aaf7af7b75 100644
--- a/drivers/tty/serial/8250/8250_aspeed_vuart.c
+++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c
@@ -566,7 +566,7 @@ err_sysfs_remove:
 	return rc;
 }
 
-static int aspeed_vuart_remove(struct platform_device *pdev)
+static void aspeed_vuart_remove(struct platform_device *pdev)
 {
 	struct aspeed_vuart *vuart = platform_get_drvdata(pdev);
 
@@ -574,8 +574,6 @@ static int aspeed_vuart_remove(struct platform_device *pdev)
 	aspeed_vuart_set_enabled(vuart, false);
 	serial8250_unregister_port(vuart->line);
 	sysfs_remove_group(&vuart->dev->kobj, &aspeed_vuart_attr_group);
-
-	return 0;
 }
 
 static const struct of_device_id aspeed_vuart_table[] = {
@@ -590,7 +588,7 @@ static struct platform_driver aspeed_vuart_driver = {
 		.of_match_table = aspeed_vuart_table,
 	},
 	.probe = aspeed_vuart_probe,
-	.remove = aspeed_vuart_remove,
+	.remove_new = aspeed_vuart_remove,
 };
 
 module_platform_driver(aspeed_vuart_driver);
diff --git a/drivers/tty/serial/8250/8250_bcm2835aux.c b/drivers/tty/serial/8250/8250_bcm2835aux.c
index 15a2387a5b258..b5760f914a8cf 100644
--- a/drivers/tty/serial/8250/8250_bcm2835aux.c
+++ b/drivers/tty/serial/8250/8250_bcm2835aux.c
@@ -195,14 +195,12 @@ dis_clk:
 	return ret;
 }
 
-static int bcm2835aux_serial_remove(struct platform_device *pdev)
+static void bcm2835aux_serial_remove(struct platform_device *pdev)
 {
 	struct bcm2835aux_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
 	clk_disable_unprepare(data->clk);
-
-	return 0;
 }
 
 static const struct bcm2835_aux_serial_driver_data bcm2835_acpi_data = {
@@ -228,7 +226,7 @@ static struct platform_driver bcm2835aux_serial_driver = {
 		.acpi_match_table = bcm2835aux_serial_acpi_match,
 	},
 	.probe  = bcm2835aux_serial_probe,
-	.remove = bcm2835aux_serial_remove,
+	.remove_new = bcm2835aux_serial_remove,
 };
 module_platform_driver(bcm2835aux_serial_driver);
 
diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c
index 55dea2539c479..504c4c0208577 100644
--- a/drivers/tty/serial/8250/8250_bcm7271.c
+++ b/drivers/tty/serial/8250/8250_bcm7271.c
@@ -1121,7 +1121,7 @@ release_dma:
 	return ret;
 }
 
-static int brcmuart_remove(struct platform_device *pdev)
+static void brcmuart_remove(struct platform_device *pdev)
 {
 	struct brcmuart_priv *priv = platform_get_drvdata(pdev);
 
@@ -1131,7 +1131,6 @@ static int brcmuart_remove(struct platform_device *pdev)
 	brcmuart_free_bufs(&pdev->dev, priv);
 	if (priv->dma_enabled)
 		brcmuart_arbitration(priv, 0);
-	return 0;
 }
 
 static int __maybe_unused brcmuart_suspend(struct device *dev)
@@ -1207,7 +1206,7 @@ static struct platform_driver brcmuart_platform_driver = {
 		.of_match_table = brcmuart_dt_ids,
 	},
 	.probe		= brcmuart_probe,
-	.remove		= brcmuart_remove,
+	.remove_new	= brcmuart_remove,
 };
 
 static int __init brcmuart_init(void)
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 9127331518587..b62ad9006780c 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -883,7 +883,7 @@ static int serial8250_probe(struct platform_device *dev)
 /*
  * Remove serial ports registered against a platform device.
  */
-static int serial8250_remove(struct platform_device *dev)
+static void serial8250_remove(struct platform_device *dev)
 {
 	int i;
 
@@ -893,7 +893,6 @@ static int serial8250_remove(struct platform_device *dev)
 		if (up->port.dev == &dev->dev)
 			serial8250_unregister_port(i);
 	}
-	return 0;
 }
 
 static int serial8250_suspend(struct platform_device *dev, pm_message_t state)
@@ -926,7 +925,7 @@ static int serial8250_resume(struct platform_device *dev)
 
 static struct platform_driver serial8250_isa_driver = {
 	.probe		= serial8250_probe,
-	.remove		= serial8250_remove,
+	.remove_new	= serial8250_remove,
 	.suspend	= serial8250_suspend,
 	.resume		= serial8250_resume,
 	.driver		= {
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index b94f567647cb6..63b14ce9c009c 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -663,7 +663,7 @@ static int dw8250_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int dw8250_remove(struct platform_device *pdev)
+static void dw8250_remove(struct platform_device *pdev)
 {
 	struct dw8250_data *data = platform_get_drvdata(pdev);
 	struct device *dev = &pdev->dev;
@@ -680,8 +680,6 @@ static int dw8250_remove(struct platform_device *pdev)
 
 	pm_runtime_disable(dev);
 	pm_runtime_put_noidle(dev);
-
-	return 0;
 }
 
 static int dw8250_suspend(struct device *dev)
@@ -789,7 +787,7 @@ static struct platform_driver dw8250_platform_driver = {
 		.acpi_match_table = dw8250_acpi_match,
 	},
 	.probe			= dw8250_probe,
-	.remove			= dw8250_remove,
+	.remove_new		= dw8250_remove,
 };
 
 module_platform_driver(dw8250_platform_driver);
diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c
index ef5019e944eaa..a754755100ffe 100644
--- a/drivers/tty/serial/8250/8250_em.c
+++ b/drivers/tty/serial/8250/8250_em.c
@@ -200,12 +200,11 @@ static int serial8250_em_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int serial8250_em_remove(struct platform_device *pdev)
+static void serial8250_em_remove(struct platform_device *pdev)
 {
 	struct serial8250_em_priv *priv = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(priv->line);
-	return 0;
 }
 
 static const struct of_device_id serial8250_em_dt_ids[] = {
@@ -220,7 +219,7 @@ static struct platform_driver serial8250_em_platform_driver = {
 		.of_match_table = serial8250_em_dt_ids,
 	},
 	.probe			= serial8250_em_probe,
-	.remove			= serial8250_em_remove,
+	.remove_new		= serial8250_em_remove,
 };
 
 module_platform_driver(serial8250_em_platform_driver);
diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c
index f522eb5026c97..5cf675eadefe1 100644
--- a/drivers/tty/serial/8250/8250_fsl.c
+++ b/drivers/tty/serial/8250/8250_fsl.c
@@ -159,12 +159,11 @@ static int fsl8250_acpi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int fsl8250_acpi_remove(struct platform_device *pdev)
+static void fsl8250_acpi_remove(struct platform_device *pdev)
 {
 	struct fsl8250_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
-	return 0;
 }
 
 static const struct acpi_device_id fsl_8250_acpi_id[] = {
@@ -179,7 +178,7 @@ static struct platform_driver fsl8250_platform_driver = {
 		.acpi_match_table	= ACPI_PTR(fsl_8250_acpi_id),
 	},
 	.probe			= fsl8250_acpi_probe,
-	.remove			= fsl8250_acpi_remove,
+	.remove_new		= fsl8250_acpi_remove,
 };
 
 module_platform_driver(fsl8250_platform_driver);
diff --git a/drivers/tty/serial/8250/8250_ingenic.c b/drivers/tty/serial/8250/8250_ingenic.c
index 4c4c4da73ad09..a12f737924c0b 100644
--- a/drivers/tty/serial/8250/8250_ingenic.c
+++ b/drivers/tty/serial/8250/8250_ingenic.c
@@ -320,14 +320,13 @@ out:
 	return err;
 }
 
-static int ingenic_uart_remove(struct platform_device *pdev)
+static void ingenic_uart_remove(struct platform_device *pdev)
 {
 	struct ingenic_uart_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
 	clk_disable_unprepare(data->clk_module);
 	clk_disable_unprepare(data->clk_baud);
-	return 0;
 }
 
 static const struct ingenic_uart_config jz4740_uart_config = {
@@ -368,7 +367,7 @@ static struct platform_driver ingenic_uart_platform_driver = {
 		.of_match_table	= of_match,
 	},
 	.probe			= ingenic_uart_probe,
-	.remove			= ingenic_uart_remove,
+	.remove_new		= ingenic_uart_remove,
 };
 
 module_platform_driver(ingenic_uart_platform_driver);
diff --git a/drivers/tty/serial/8250/8250_ioc3.c b/drivers/tty/serial/8250/8250_ioc3.c
index d5a39e105a76f..50c77c3dacf2c 100644
--- a/drivers/tty/serial/8250/8250_ioc3.c
+++ b/drivers/tty/serial/8250/8250_ioc3.c
@@ -75,17 +75,16 @@ static int serial8250_ioc3_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int serial8250_ioc3_remove(struct platform_device *pdev)
+static void serial8250_ioc3_remove(struct platform_device *pdev)
 {
 	struct ioc3_8250_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
-	return 0;
 }
 
 static struct platform_driver serial8250_ioc3_driver = {
 	.probe  = serial8250_ioc3_probe,
-	.remove = serial8250_ioc3_remove,
+	.remove_new = serial8250_ioc3_remove,
 	.driver = {
 		.name = "ioc3-serial8250",
 	}
diff --git a/drivers/tty/serial/8250/8250_lpc18xx.c b/drivers/tty/serial/8250/8250_lpc18xx.c
index 6dc85aaba5d0b..8d728a6a59914 100644
--- a/drivers/tty/serial/8250/8250_lpc18xx.c
+++ b/drivers/tty/serial/8250/8250_lpc18xx.c
@@ -182,15 +182,13 @@ dis_clk_reg:
 	return ret;
 }
 
-static int lpc18xx_serial_remove(struct platform_device *pdev)
+static void lpc18xx_serial_remove(struct platform_device *pdev)
 {
 	struct lpc18xx_uart_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
 	clk_disable_unprepare(data->clk_uart);
 	clk_disable_unprepare(data->clk_reg);
-
-	return 0;
 }
 
 static const struct of_device_id lpc18xx_serial_match[] = {
@@ -201,7 +199,7 @@ MODULE_DEVICE_TABLE(of, lpc18xx_serial_match);
 
 static struct platform_driver lpc18xx_serial_driver = {
 	.probe  = lpc18xx_serial_probe,
-	.remove = lpc18xx_serial_remove,
+	.remove_new = lpc18xx_serial_remove,
 	.driver = {
 		.name = "lpc18xx-uart",
 		.of_match_table = lpc18xx_serial_match,
diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c
index 23457daae8a14..9ff6bbe9c0863 100644
--- a/drivers/tty/serial/8250/8250_mtk.c
+++ b/drivers/tty/serial/8250/8250_mtk.c
@@ -581,7 +581,7 @@ static int mtk8250_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mtk8250_remove(struct platform_device *pdev)
+static void mtk8250_remove(struct platform_device *pdev)
 {
 	struct mtk8250_data *data = platform_get_drvdata(pdev);
 
@@ -591,8 +591,6 @@ static int mtk8250_remove(struct platform_device *pdev)
 
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
-
-	return 0;
 }
 
 static int __maybe_unused mtk8250_suspend(struct device *dev)
@@ -652,7 +650,7 @@ static struct platform_driver mtk8250_platform_driver = {
 		.of_match_table	= mtk8250_of_match,
 	},
 	.probe			= mtk8250_probe,
-	.remove			= mtk8250_remove,
+	.remove_new		= mtk8250_remove,
 };
 module_platform_driver(mtk8250_platform_driver);
 
diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c
index ef3e745bd09cb..34f17a9785e79 100644
--- a/drivers/tty/serial/8250/8250_of.c
+++ b/drivers/tty/serial/8250/8250_of.c
@@ -251,7 +251,7 @@ err_free:
 /*
  * Release a line
  */
-static int of_platform_serial_remove(struct platform_device *ofdev)
+static void of_platform_serial_remove(struct platform_device *ofdev)
 {
 	struct of_serial_info *info = platform_get_drvdata(ofdev);
 
@@ -261,7 +261,6 @@ static int of_platform_serial_remove(struct platform_device *ofdev)
 	pm_runtime_put_sync(&ofdev->dev);
 	pm_runtime_disable(&ofdev->dev);
 	kfree(info);
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -337,7 +336,7 @@ static struct platform_driver of_platform_serial_driver = {
 		.pm = &of_serial_pm_ops,
 	},
 	.probe = of_platform_serial_probe,
-	.remove = of_platform_serial_remove,
+	.remove_new = of_platform_serial_remove,
 };
 
 module_platform_driver(of_platform_serial_driver);
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 661a83dbc11b0..5a89a8cd7f717 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -1584,7 +1584,7 @@ err:
 	return ret;
 }
 
-static int omap8250_remove(struct platform_device *pdev)
+static void omap8250_remove(struct platform_device *pdev)
 {
 	struct omap8250_priv *priv = platform_get_drvdata(pdev);
 	struct uart_8250_port *up;
@@ -1604,7 +1604,6 @@ static int omap8250_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	cpu_latency_qos_remove_request(&priv->pm_qos_request);
 	device_init_wakeup(&pdev->dev, false);
-	return 0;
 }
 
 static int omap8250_prepare(struct device *dev)
@@ -1863,7 +1862,7 @@ static struct platform_driver omap8250_platform_driver = {
 		.of_match_table = omap8250_dt_ids,
 	},
 	.probe			= omap8250_probe,
-	.remove			= omap8250_remove,
+	.remove_new		= omap8250_remove,
 };
 module_platform_driver(omap8250_platform_driver);
 
diff --git a/drivers/tty/serial/8250/8250_pxa.c b/drivers/tty/serial/8250/8250_pxa.c
index a5b3ea27fc902..77686da42ce8e 100644
--- a/drivers/tty/serial/8250/8250_pxa.c
+++ b/drivers/tty/serial/8250/8250_pxa.c
@@ -146,20 +146,18 @@ static int serial_pxa_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int serial_pxa_remove(struct platform_device *pdev)
+static void serial_pxa_remove(struct platform_device *pdev)
 {
 	struct pxa8250_data *data = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(data->line);
 
 	clk_unprepare(data->clk);
-
-	return 0;
 }
 
 static struct platform_driver serial_pxa_driver = {
 	.probe          = serial_pxa_probe,
-	.remove         = serial_pxa_remove,
+	.remove_new     = serial_pxa_remove,
 
 	.driver		= {
 		.name	= "pxa2xx-uart",
diff --git a/drivers/tty/serial/8250/8250_tegra.c b/drivers/tty/serial/8250/8250_tegra.c
index 89956bbf34d9e..ba352262df75a 100644
--- a/drivers/tty/serial/8250/8250_tegra.c
+++ b/drivers/tty/serial/8250/8250_tegra.c
@@ -128,15 +128,13 @@ err_clkdisable:
 	return ret;
 }
 
-static int tegra_uart_remove(struct platform_device *pdev)
+static void tegra_uart_remove(struct platform_device *pdev)
 {
 	struct tegra_uart *uart = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(uart->line);
 	reset_control_assert(uart->rst);
 	clk_disable_unprepare(uart->clk);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -192,7 +190,7 @@ static struct platform_driver tegra_uart_driver = {
 		.acpi_match_table = ACPI_PTR(tegra_uart_acpi_match),
 	},
 	.probe = tegra_uart_probe,
-	.remove = tegra_uart_remove,
+	.remove_new = tegra_uart_remove,
 };
 
 module_platform_driver(tegra_uart_driver);
diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c
index a405155264b17..6399a38ecce2a 100644
--- a/drivers/tty/serial/8250/8250_uniphier.c
+++ b/drivers/tty/serial/8250/8250_uniphier.c
@@ -241,14 +241,12 @@ static int uniphier_uart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int uniphier_uart_remove(struct platform_device *pdev)
+static void uniphier_uart_remove(struct platform_device *pdev)
 {
 	struct uniphier8250_priv *priv = platform_get_drvdata(pdev);
 
 	serial8250_unregister_port(priv->line);
 	clk_disable_unprepare(priv->clk);
-
-	return 0;
 }
 
 static int __maybe_unused uniphier_uart_suspend(struct device *dev)
@@ -293,7 +291,7 @@ MODULE_DEVICE_TABLE(of, uniphier_uart_match);
 
 static struct platform_driver uniphier_uart_platform_driver = {
 	.probe		= uniphier_uart_probe,
-	.remove		= uniphier_uart_remove,
+	.remove_new	= uniphier_uart_remove,
 	.driver = {
 		.name	= "uniphier-uart",
 		.of_match_table = uniphier_uart_match,
-- 
GitLab


From c1f5edac27fbcaa9c5e4b63d17a2ec39ab648043 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:32 +0100
Subject: [PATCH 0331/4076] serial: altera_jtaguart: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Tobias Klauser <tklauser@distanz.ch>
Link: https://lore.kernel.org/r/20231110152927.70601-5-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/altera_jtaguart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/altera_jtaguart.c b/drivers/tty/serial/altera_jtaguart.c
index 7090b251dd4df..effcba71ea775 100644
--- a/drivers/tty/serial/altera_jtaguart.c
+++ b/drivers/tty/serial/altera_jtaguart.c
@@ -425,7 +425,7 @@ static int altera_jtaguart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int altera_jtaguart_remove(struct platform_device *pdev)
+static void altera_jtaguart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port;
 	int i = pdev->id;
@@ -436,8 +436,6 @@ static int altera_jtaguart_remove(struct platform_device *pdev)
 	port = &altera_jtaguart_ports[i];
 	uart_remove_one_port(&altera_jtaguart_driver, port);
 	iounmap(port->membase);
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -451,7 +449,7 @@ MODULE_DEVICE_TABLE(of, altera_jtaguart_match);
 
 static struct platform_driver altera_jtaguart_platform_driver = {
 	.probe	= altera_jtaguart_probe,
-	.remove	= altera_jtaguart_remove,
+	.remove_new = altera_jtaguart_remove,
 	.driver	= {
 		.name		= DRV_NAME,
 		.of_match_table	= of_match_ptr(altera_jtaguart_match),
-- 
GitLab


From b0f698b80bbc2b6f15e69b16dd7ee2d68ec769f5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:33 +0100
Subject: [PATCH 0332/4076] serial: altera: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Tobias Klauser <tklauser@distanz.ch>
Link: https://lore.kernel.org/r/20231110152927.70601-6-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/altera_uart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 77835ac68df26..081bec31dbd82 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -595,7 +595,7 @@ static int altera_uart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int altera_uart_remove(struct platform_device *pdev)
+static void altera_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
@@ -604,8 +604,6 @@ static int altera_uart_remove(struct platform_device *pdev)
 		port->mapbase = 0;
 		iounmap(port->membase);
 	}
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -619,7 +617,7 @@ MODULE_DEVICE_TABLE(of, altera_uart_match);
 
 static struct platform_driver altera_uart_platform_driver = {
 	.probe	= altera_uart_probe,
-	.remove	= altera_uart_remove,
+	.remove_new = altera_uart_remove,
 	.driver	= {
 		.name		= DRV_NAME,
 		.of_match_table	= of_match_ptr(altera_uart_match),
-- 
GitLab


From 788f501a817a0eb45fe179c4430420fb1516f550 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:34 +0100
Subject: [PATCH 0333/4076] serial: amba-pl011: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-7-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 61cc24cd90e4b..374b4254e39be 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2939,13 +2939,12 @@ static int sbsa_uart_probe(struct platform_device *pdev)
 	return pl011_register_port(uap);
 }
 
-static int sbsa_uart_remove(struct platform_device *pdev)
+static void sbsa_uart_remove(struct platform_device *pdev)
 {
 	struct uart_amba_port *uap = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&amba_reg, &uap->port);
 	pl011_unregister_port(uap);
-	return 0;
 }
 
 static const struct of_device_id sbsa_uart_of_match[] = {
@@ -2963,7 +2962,7 @@ MODULE_DEVICE_TABLE(acpi, sbsa_uart_acpi_match);
 
 static struct platform_driver arm_sbsa_uart_platform_driver = {
 	.probe		= sbsa_uart_probe,
-	.remove		= sbsa_uart_remove,
+	.remove_new	= sbsa_uart_remove,
 	.driver	= {
 		.name	= "sbsa-uart",
 		.pm	= &pl011_dev_pm_ops,
-- 
GitLab


From d3b84c16fde084ff4fc21f0ee0a66865775bf0fb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:35 +0100
Subject: [PATCH 0334/4076] serial: ar933x: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-8-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/ar933x_uart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c
index ffd234673177f..8d09ace062e59 100644
--- a/drivers/tty/serial/ar933x_uart.c
+++ b/drivers/tty/serial/ar933x_uart.c
@@ -818,7 +818,7 @@ err_disable_clk:
 	return ret;
 }
 
-static int ar933x_uart_remove(struct platform_device *pdev)
+static void ar933x_uart_remove(struct platform_device *pdev)
 {
 	struct ar933x_uart_port *up;
 
@@ -828,8 +828,6 @@ static int ar933x_uart_remove(struct platform_device *pdev)
 		uart_remove_one_port(&ar933x_uart_driver, &up->port);
 		clk_disable_unprepare(up->clk);
 	}
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -842,7 +840,7 @@ MODULE_DEVICE_TABLE(of, ar933x_uart_of_ids);
 
 static struct platform_driver ar933x_uart_platform_driver = {
 	.probe		= ar933x_uart_probe,
-	.remove		= ar933x_uart_remove,
+	.remove_new	= ar933x_uart_remove,
 	.driver		= {
 		.name		= DRIVER_NAME,
 		.of_match_table = of_match_ptr(ar933x_uart_of_ids),
-- 
GitLab


From 144b47cd555bc70459962547e6b6079e52f6ba9e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:36 +0100
Subject: [PATCH 0335/4076] serial: atmel: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Acked-by: Richard Genoud <richard.genoud@gmail.com>
Link: https://lore.kernel.org/r/20231110152927.70601-9-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/atmel_serial.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 1946fafc3f3ec..6792680690bd1 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -3001,7 +3001,7 @@ err:
  * protocol that needs bitbanging on IO lines, but use the regular serial
  * port in the normal case.
  */
-static int atmel_serial_remove(struct platform_device *pdev)
+static void atmel_serial_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
@@ -3020,8 +3020,6 @@ static int atmel_serial_remove(struct platform_device *pdev)
 	clear_bit(port->line, atmel_ports_in_use);
 
 	pdev->dev.of_node = NULL;
-
-	return 0;
 }
 
 static SIMPLE_DEV_PM_OPS(atmel_serial_pm_ops, atmel_serial_suspend,
@@ -3029,7 +3027,7 @@ static SIMPLE_DEV_PM_OPS(atmel_serial_pm_ops, atmel_serial_suspend,
 
 static struct platform_driver atmel_serial_driver = {
 	.probe		= atmel_serial_probe,
-	.remove		= atmel_serial_remove,
+	.remove_new	= atmel_serial_remove,
 	.driver		= {
 		.name			= "atmel_usart_serial",
 		.of_match_table		= of_match_ptr(atmel_serial_dt_ids),
-- 
GitLab


From 69b1a03921a49c9a9ea18f21ab3792e1ac1ed2ee Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:37 +0100
Subject: [PATCH 0336/4076] serial: bcm63xx: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20231110152927.70601-10-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/bcm63xx_uart.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index 4a08fd5ee61be..a3cefa153456d 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -868,7 +868,7 @@ static int bcm_uart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int bcm_uart_remove(struct platform_device *pdev)
+static void bcm_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port;
 
@@ -876,7 +876,6 @@ static int bcm_uart_remove(struct platform_device *pdev)
 	uart_remove_one_port(&bcm_uart_driver, port);
 	/* mark port as free */
 	ports[pdev->id].membase = NULL;
-	return 0;
 }
 
 static const struct of_device_id bcm63xx_of_match[] = {
@@ -890,7 +889,7 @@ MODULE_DEVICE_TABLE(of, bcm63xx_of_match);
  */
 static struct platform_driver bcm_uart_platform_driver = {
 	.probe	= bcm_uart_probe,
-	.remove	= bcm_uart_remove,
+	.remove_new = bcm_uart_remove,
 	.driver	= {
 		.name  = "bcm63xx_uart",
 		.of_match_table = bcm63xx_of_match,
-- 
GitLab


From 47cfe5464350b668dec1562a286be132aa1e0aec Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:38 +0100
Subject: [PATCH 0337/4076] serial: clps711x: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-11-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/clps711x.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/clps711x.c b/drivers/tty/serial/clps711x.c
index 55d19937efbd3..7927725b89578 100644
--- a/drivers/tty/serial/clps711x.c
+++ b/drivers/tty/serial/clps711x.c
@@ -510,13 +510,11 @@ static int uart_clps711x_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int uart_clps711x_remove(struct platform_device *pdev)
+static void uart_clps711x_remove(struct platform_device *pdev)
 {
 	struct clps711x_port *s = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&clps711x_uart, &s->port);
-
-	return 0;
 }
 
 static const struct of_device_id __maybe_unused clps711x_uart_dt_ids[] = {
@@ -531,7 +529,7 @@ static struct platform_driver clps711x_uart_platform = {
 		.of_match_table	= of_match_ptr(clps711x_uart_dt_ids),
 	},
 	.probe	= uart_clps711x_probe,
-	.remove	= uart_clps711x_remove,
+	.remove_new = uart_clps711x_remove,
 };
 
 static int __init uart_clps711x_init(void)
-- 
GitLab


From d19993c40ca126889f622e9ec73e329798f41012 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:39 +0100
Subject: [PATCH 0338/4076] serial: cpm: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-12-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/cpm_uart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/cpm_uart.c b/drivers/tty/serial/cpm_uart.c
index be4af6eda4c21..df56c6c5afd0e 100644
--- a/drivers/tty/serial/cpm_uart.c
+++ b/drivers/tty/serial/cpm_uart.c
@@ -1549,13 +1549,11 @@ static int cpm_uart_probe(struct platform_device *ofdev)
 	return ret;
 }
 
-static int cpm_uart_remove(struct platform_device *ofdev)
+static void cpm_uart_remove(struct platform_device *ofdev)
 {
 	struct uart_cpm_port *pinfo = platform_get_drvdata(ofdev);
 
 	uart_remove_one_port(&cpm_reg, &pinfo->port);
-
-	return 0;
 }
 
 static const struct of_device_id cpm_uart_match[] = {
@@ -1581,7 +1579,7 @@ static struct platform_driver cpm_uart_driver = {
 		.of_match_table = cpm_uart_match,
 	},
 	.probe = cpm_uart_probe,
-	.remove = cpm_uart_remove,
+	.remove_new = cpm_uart_remove,
  };
 
 static int __init cpm_uart_init(void)
-- 
GitLab


From e9b09d9c26fed6a5e1a9a829f749496bffb25f71 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:40 +0100
Subject: [PATCH 0339/4076] serial: digicolor: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-13-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/digicolor-usart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/digicolor-usart.c b/drivers/tty/serial/digicolor-usart.c
index 5004125f3045c..e419c4bde8b78 100644
--- a/drivers/tty/serial/digicolor-usart.c
+++ b/drivers/tty/serial/digicolor-usart.c
@@ -503,13 +503,11 @@ static int digicolor_uart_probe(struct platform_device *pdev)
 	return uart_add_one_port(&digicolor_uart, &dp->port);
 }
 
-static int digicolor_uart_remove(struct platform_device *pdev)
+static void digicolor_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&digicolor_uart, port);
-
-	return 0;
 }
 
 static const struct of_device_id digicolor_uart_dt_ids[] = {
@@ -524,7 +522,7 @@ static struct platform_driver digicolor_uart_platform = {
 		.of_match_table	= of_match_ptr(digicolor_uart_dt_ids),
 	},
 	.probe	= digicolor_uart_probe,
-	.remove	= digicolor_uart_remove,
+	.remove_new = digicolor_uart_remove,
 };
 
 static int __init digicolor_uart_init(void)
-- 
GitLab


From 505cc4b418ac209cf0534eeeb370cf9442c364d7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:41 +0100
Subject: [PATCH 0340/4076] serial: esp32_acm: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-14-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/esp32_acm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/esp32_acm.c b/drivers/tty/serial/esp32_acm.c
index cb28a87736aa1..a4cbaedb51702 100644
--- a/drivers/tty/serial/esp32_acm.c
+++ b/drivers/tty/serial/esp32_acm.c
@@ -413,18 +413,17 @@ static int esp32s3_acm_probe(struct platform_device *pdev)
 	return uart_add_one_port(&esp32s3_acm_reg, port);
 }
 
-static int esp32s3_acm_remove(struct platform_device *pdev)
+static void esp32s3_acm_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&esp32s3_acm_reg, port);
-	return 0;
 }
 
 
 static struct platform_driver esp32s3_acm_driver = {
 	.probe		= esp32s3_acm_probe,
-	.remove		= esp32s3_acm_remove,
+	.remove_new	= esp32s3_acm_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.of_match_table	= esp32s3_acm_dt_ids,
-- 
GitLab


From de2f50b74db7f4d476df928f8deca4052160bf81 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:42 +0100
Subject: [PATCH 0341/4076] serial: esp32: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-15-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/esp32_uart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/esp32_uart.c b/drivers/tty/serial/esp32_uart.c
index 85c9c5ad7cc5c..6e12955d13158 100644
--- a/drivers/tty/serial/esp32_uart.c
+++ b/drivers/tty/serial/esp32_uart.c
@@ -737,19 +737,17 @@ static int esp32_uart_probe(struct platform_device *pdev)
 	return uart_add_one_port(&esp32_uart_reg, port);
 }
 
-static int esp32_uart_remove(struct platform_device *pdev)
+static void esp32_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&esp32_uart_reg, port);
-
-	return 0;
 }
 
 
 static struct platform_driver esp32_uart_driver = {
 	.probe		= esp32_uart_probe,
-	.remove		= esp32_uart_remove,
+	.remove_new	= esp32_uart_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.of_match_table	= esp32_uart_dt_ids,
-- 
GitLab


From 77533490f4df4e000be3b2fcadbb1b3fdcfa9257 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:43 +0100
Subject: [PATCH 0342/4076] serial: fsl_linflexuart: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-16-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/fsl_linflexuart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/fsl_linflexuart.c b/drivers/tty/serial/fsl_linflexuart.c
index 3bdaf1ddc3094..52c87876a88de 100644
--- a/drivers/tty/serial/fsl_linflexuart.c
+++ b/drivers/tty/serial/fsl_linflexuart.c
@@ -851,13 +851,11 @@ static int linflex_probe(struct platform_device *pdev)
 	return uart_add_one_port(&linflex_reg, sport);
 }
 
-static int linflex_remove(struct platform_device *pdev)
+static void linflex_remove(struct platform_device *pdev)
 {
 	struct uart_port *sport = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&linflex_reg, sport);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -884,7 +882,7 @@ static SIMPLE_DEV_PM_OPS(linflex_pm_ops, linflex_suspend, linflex_resume);
 
 static struct platform_driver linflex_driver = {
 	.probe		= linflex_probe,
-	.remove		= linflex_remove,
+	.remove_new	= linflex_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.of_match_table	= linflex_dt_ids,
-- 
GitLab


From 6b02503f37e86aca945adc2ece51cda03a497757 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:44 +0100
Subject: [PATCH 0343/4076] serial: fsl_lpuart: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-17-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/fsl_lpuart.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 6d0cfb2e86b45..5ddf110aedbe5 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -2959,7 +2959,7 @@ failed_reset:
 	return ret;
 }
 
-static int lpuart_remove(struct platform_device *pdev)
+static void lpuart_remove(struct platform_device *pdev)
 {
 	struct lpuart_port *sport = platform_get_drvdata(pdev);
 
@@ -2976,7 +2976,6 @@ static int lpuart_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	return 0;
 }
 
 static int lpuart_runtime_suspend(struct device *dev)
@@ -3210,7 +3209,7 @@ static const struct dev_pm_ops lpuart_pm_ops = {
 
 static struct platform_driver lpuart_driver = {
 	.probe		= lpuart_probe,
-	.remove		= lpuart_remove,
+	.remove_new	= lpuart_remove,
 	.driver		= {
 		.name	= "fsl-lpuart",
 		.of_match_table = lpuart_dt_ids,
-- 
GitLab


From c066f87314b7fbbf4d72d38957436a98e7b7e503 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:45 +0100
Subject: [PATCH 0344/4076] serial: imx: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-18-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 708b9852a575d..3ea9466ee5ef0 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -2465,13 +2465,11 @@ static int imx_uart_probe(struct platform_device *pdev)
 	return uart_add_one_port(&imx_uart_uart_driver, &sport->port);
 }
 
-static int imx_uart_remove(struct platform_device *pdev)
+static void imx_uart_remove(struct platform_device *pdev)
 {
 	struct imx_port *sport = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&imx_uart_uart_driver, &sport->port);
-
-	return 0;
 }
 
 static void imx_uart_restore_context(struct imx_port *sport)
@@ -2640,7 +2638,7 @@ static const struct dev_pm_ops imx_uart_pm_ops = {
 
 static struct platform_driver imx_uart_platform_driver = {
 	.probe = imx_uart_probe,
-	.remove = imx_uart_remove,
+	.remove_new = imx_uart_remove,
 
 	.driver = {
 		.name = "imx-uart",
-- 
GitLab


From 04300219c8a826a55f73e5dc7634edfe7ab1128b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:46 +0100
Subject: [PATCH 0345/4076] serial: lantiq: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-19-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/lantiq.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/lantiq.c b/drivers/tty/serial/lantiq.c
index 3adb60c683f70..a0731773ce75c 100644
--- a/drivers/tty/serial/lantiq.c
+++ b/drivers/tty/serial/lantiq.c
@@ -887,13 +887,11 @@ static int lqasc_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int lqasc_remove(struct platform_device *pdev)
+static void lqasc_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&lqasc_reg, port);
-
-	return 0;
 }
 
 static const struct ltq_soc_data soc_data_lantiq = {
@@ -917,7 +915,7 @@ MODULE_DEVICE_TABLE(of, ltq_asc_match);
 
 static struct platform_driver lqasc_driver = {
 	.probe		= lqasc_probe,
-	.remove		= lqasc_remove,
+	.remove_new	= lqasc_remove,
 	.driver		= {
 		.name	= DRVNAME,
 		.of_match_table = ltq_asc_match,
-- 
GitLab


From 2d1c01d4cf26710920c37468ed49d6c41e11944c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:47 +0100
Subject: [PATCH 0346/4076] serial: liteuart: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Gabriel Somlo <gsomlo@gmail.com>
Link: https://lore.kernel.org/r/20231110152927.70601-20-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/liteuart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/liteuart.c b/drivers/tty/serial/liteuart.c
index a25ab1efe38ff..3ce369f763498 100644
--- a/drivers/tty/serial/liteuart.c
+++ b/drivers/tty/serial/liteuart.c
@@ -336,15 +336,13 @@ err_erase_id:
 	return ret;
 }
 
-static int liteuart_remove(struct platform_device *pdev)
+static void liteuart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	unsigned int line = port->line;
 
 	uart_remove_one_port(&liteuart_driver, port);
 	xa_erase(&liteuart_array, line);
-
-	return 0;
 }
 
 static const struct of_device_id liteuart_of_match[] = {
@@ -355,7 +353,7 @@ MODULE_DEVICE_TABLE(of, liteuart_of_match);
 
 static struct platform_driver liteuart_platform_driver = {
 	.probe = liteuart_probe,
-	.remove = liteuart_remove,
+	.remove_new = liteuart_remove,
 	.driver = {
 		.name = KBUILD_MODNAME,
 		.of_match_table = liteuart_of_match,
-- 
GitLab


From 2c1a68b59894f6b18058e0718d58011b28bfa6f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:48 +0100
Subject: [PATCH 0347/4076] serial: lpc32xx_hs: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-21-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/lpc32xx_hs.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/lpc32xx_hs.c b/drivers/tty/serial/lpc32xx_hs.c
index 5149a947b7feb..ec20329f06036 100644
--- a/drivers/tty/serial/lpc32xx_hs.c
+++ b/drivers/tty/serial/lpc32xx_hs.c
@@ -659,13 +659,11 @@ static int serial_hs_lpc32xx_probe(struct platform_device *pdev)
 /*
  * Remove serial ports registered against a platform device.
  */
-static int serial_hs_lpc32xx_remove(struct platform_device *pdev)
+static void serial_hs_lpc32xx_remove(struct platform_device *pdev)
 {
 	struct lpc32xx_hsuart_port *p = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&lpc32xx_hs_reg, &p->port);
-
-	return 0;
 }
 
 
@@ -702,7 +700,7 @@ MODULE_DEVICE_TABLE(of, serial_hs_lpc32xx_dt_ids);
 
 static struct platform_driver serial_hs_lpc32xx_driver = {
 	.probe		= serial_hs_lpc32xx_probe,
-	.remove		= serial_hs_lpc32xx_remove,
+	.remove_new	= serial_hs_lpc32xx_remove,
 	.suspend	= serial_hs_lpc32xx_suspend,
 	.resume		= serial_hs_lpc32xx_resume,
 	.driver		= {
-- 
GitLab


From cec346ec4649bb9d741a52da1632db4e6fd13947 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:49 +0100
Subject: [PATCH 0348/4076] serial: ma35d1: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-22-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/ma35d1_serial.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/ma35d1_serial.c b/drivers/tty/serial/ma35d1_serial.c
index a6a7c405892e8..f9c6c75d9776b 100644
--- a/drivers/tty/serial/ma35d1_serial.c
+++ b/drivers/tty/serial/ma35d1_serial.c
@@ -746,14 +746,13 @@ err_iounmap:
 /*
  * Remove serial ports registered against a platform device.
  */
-static int ma35d1serial_remove(struct platform_device *dev)
+static void ma35d1serial_remove(struct platform_device *dev)
 {
 	struct uart_port *port = platform_get_drvdata(dev);
 	struct uart_ma35d1_port *up = to_ma35d1_uart_port(port);
 
 	uart_remove_one_port(&ma35d1serial_reg, port);
 	clk_disable_unprepare(up->clk);
-	return 0;
 }
 
 static int ma35d1serial_suspend(struct platform_device *dev, pm_message_t state)
@@ -786,7 +785,7 @@ static int ma35d1serial_resume(struct platform_device *dev)
 
 static struct platform_driver ma35d1serial_driver = {
 	.probe      = ma35d1serial_probe,
-	.remove     = ma35d1serial_remove,
+	.remove_new = ma35d1serial_remove,
 	.suspend    = ma35d1serial_suspend,
 	.resume     = ma35d1serial_resume,
 	.driver     = {
-- 
GitLab


From cd1d7071f5c172205fc3a916347aa60a84a16424 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:50 +0100
Subject: [PATCH 0349/4076] serial: mcf: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-23-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/mcf.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/mcf.c b/drivers/tty/serial/mcf.c
index 91b15243f6c65..8690a45239e09 100644
--- a/drivers/tty/serial/mcf.c
+++ b/drivers/tty/serial/mcf.c
@@ -627,7 +627,7 @@ static int mcf_probe(struct platform_device *pdev)
 
 /****************************************************************************/
 
-static int mcf_remove(struct platform_device *pdev)
+static void mcf_remove(struct platform_device *pdev)
 {
 	struct uart_port *port;
 	int i;
@@ -637,15 +637,13 @@ static int mcf_remove(struct platform_device *pdev)
 		if (port)
 			uart_remove_one_port(&mcf_driver, port);
 	}
-
-	return 0;
 }
 
 /****************************************************************************/
 
 static struct platform_driver mcf_platform_driver = {
 	.probe		= mcf_probe,
-	.remove		= mcf_remove,
+	.remove_new	= mcf_remove,
 	.driver		= {
 		.name	= "mcfuart",
 	},
-- 
GitLab


From c4a5b26291710032caf41503ab984431c5e4537b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:51 +0100
Subject: [PATCH 0350/4076] serial: meson: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-24-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/meson_uart.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/meson_uart.c b/drivers/tty/serial/meson_uart.c
index 8dd84617e7158..8395688f5ee92 100644
--- a/drivers/tty/serial/meson_uart.c
+++ b/drivers/tty/serial/meson_uart.c
@@ -795,7 +795,7 @@ static int meson_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int meson_uart_remove(struct platform_device *pdev)
+static void meson_uart_remove(struct platform_device *pdev)
 {
 	struct uart_driver *uart_driver;
 	struct uart_port *port;
@@ -807,12 +807,10 @@ static int meson_uart_remove(struct platform_device *pdev)
 
 	for (int id = 0; id < AML_UART_PORT_NUM; id++)
 		if (meson_ports[id])
-			return 0;
+			return;
 
 	/* No more available uart ports, unregister uart driver */
 	uart_unregister_driver(uart_driver);
-
-	return 0;
 }
 
 static struct meson_uart_data meson_g12a_uart_data = {
@@ -852,7 +850,7 @@ MODULE_DEVICE_TABLE(of, meson_uart_dt_match);
 
 static  struct platform_driver meson_uart_platform_driver = {
 	.probe		= meson_uart_probe,
-	.remove		= meson_uart_remove,
+	.remove_new	= meson_uart_remove,
 	.driver		= {
 		.name		= "meson_uart",
 		.of_match_table	= meson_uart_dt_match,
-- 
GitLab


From abf11a4b4501a09ea1a24f2c9f04459cc24d3ec4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:52 +0100
Subject: [PATCH 0351/4076] serial: milbeaut_usio: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-25-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/milbeaut_usio.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/milbeaut_usio.c b/drivers/tty/serial/milbeaut_usio.c
index db3b81f2aa570..da4c6f7e2a308 100644
--- a/drivers/tty/serial/milbeaut_usio.c
+++ b/drivers/tty/serial/milbeaut_usio.c
@@ -552,15 +552,13 @@ failed:
 	return ret;
 }
 
-static int mlb_usio_remove(struct platform_device *pdev)
+static void mlb_usio_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = &mlb_usio_ports[pdev->id];
 	struct clk *clk = port->private_data;
 
 	uart_remove_one_port(&mlb_usio_uart_driver, port);
 	clk_disable_unprepare(clk);
-
-	return 0;
 }
 
 static const struct of_device_id mlb_usio_dt_ids[] = {
@@ -571,7 +569,7 @@ MODULE_DEVICE_TABLE(of, mlb_usio_dt_ids);
 
 static struct platform_driver mlb_usio_driver = {
 	.probe          = mlb_usio_probe,
-	.remove         = mlb_usio_remove,
+	.remove_new     = mlb_usio_remove,
 	.driver         = {
 		.name   = USIO_NAME,
 		.of_match_table = mlb_usio_dt_ids,
-- 
GitLab


From 4cf1dabec96f8a36e1170954b890bb295de89dbe Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:53 +0100
Subject: [PATCH 0352/4076] serial: mpc52xx: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-26-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/mpc52xx_uart.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/mpc52xx_uart.c b/drivers/tty/serial/mpc52xx_uart.c
index a252465e745f7..95dae5e27b286 100644
--- a/drivers/tty/serial/mpc52xx_uart.c
+++ b/drivers/tty/serial/mpc52xx_uart.c
@@ -1765,15 +1765,12 @@ static int mpc52xx_uart_of_probe(struct platform_device *op)
 	return 0;
 }
 
-static int
-mpc52xx_uart_of_remove(struct platform_device *op)
+static void mpc52xx_uart_of_remove(struct platform_device *op)
 {
 	struct uart_port *port = platform_get_drvdata(op);
 
 	if (port)
 		uart_remove_one_port(&mpc52xx_uart_driver, port);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -1846,7 +1843,7 @@ MODULE_DEVICE_TABLE(of, mpc52xx_uart_of_match);
 
 static struct platform_driver mpc52xx_uart_of_driver = {
 	.probe		= mpc52xx_uart_of_probe,
-	.remove		= mpc52xx_uart_of_remove,
+	.remove_new	= mpc52xx_uart_of_remove,
 #ifdef CONFIG_PM
 	.suspend	= mpc52xx_uart_of_suspend,
 	.resume		= mpc52xx_uart_of_resume,
-- 
GitLab


From a63e5a49d596fab1524ec2fc9b0e683c37901bb4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:54 +0100
Subject: [PATCH 0353/4076] serial: msm: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-27-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/msm_serial.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 597264b546fd7..7fc8f0b16aef6 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -1843,13 +1843,11 @@ static int msm_serial_probe(struct platform_device *pdev)
 	return uart_add_one_port(&msm_uart_driver, port);
 }
 
-static int msm_serial_remove(struct platform_device *pdev)
+static void msm_serial_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&msm_uart_driver, port);
-
-	return 0;
 }
 
 static const struct of_device_id msm_match_table[] = {
@@ -1882,7 +1880,7 @@ static const struct dev_pm_ops msm_serial_dev_pm_ops = {
 };
 
 static struct platform_driver msm_platform_driver = {
-	.remove = msm_serial_remove,
+	.remove_new = msm_serial_remove,
 	.probe = msm_serial_probe,
 	.driver = {
 		.name = "msm_serial",
-- 
GitLab


From 23f6a4d9afc1eddfbe586a6c96b5d9ef87b8138b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:55 +0100
Subject: [PATCH 0354/4076] serial: mxs-auart: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-28-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/mxs-auart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 8eeecf8ad3596..2be9546e0e153 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -1686,7 +1686,7 @@ out_disable_clks:
 	return ret;
 }
 
-static int mxs_auart_remove(struct platform_device *pdev)
+static void mxs_auart_remove(struct platform_device *pdev)
 {
 	struct mxs_auart_port *s = platform_get_drvdata(pdev);
 
@@ -1698,13 +1698,11 @@ static int mxs_auart_remove(struct platform_device *pdev)
 		clk_disable_unprepare(s->clk);
 		clk_disable_unprepare(s->clk_ahb);
 	}
-
-	return 0;
 }
 
 static struct platform_driver mxs_auart_driver = {
 	.probe = mxs_auart_probe,
-	.remove = mxs_auart_remove,
+	.remove_new = mxs_auart_remove,
 	.driver = {
 		.name = "mxs-auart",
 		.of_match_table = mxs_auart_dt_ids,
-- 
GitLab


From 065503963113df1c2d64d37da01490c33e89178c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:56 +0100
Subject: [PATCH 0355/4076] serial: omap: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-29-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/omap-serial.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index ad4c1c5d0a7f0..7307556218797 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1658,7 +1658,7 @@ err_port_line:
 	return ret;
 }
 
-static int serial_omap_remove(struct platform_device *dev)
+static void serial_omap_remove(struct platform_device *dev)
 {
 	struct uart_omap_port *up = platform_get_drvdata(dev);
 
@@ -1670,8 +1670,6 @@ static int serial_omap_remove(struct platform_device *dev)
 	pm_runtime_disable(up->dev);
 	cpu_latency_qos_remove_request(&up->pm_qos_request);
 	device_init_wakeup(&dev->dev, false);
-
-	return 0;
 }
 
 /*
@@ -1808,7 +1806,7 @@ MODULE_DEVICE_TABLE(of, omap_serial_of_match);
 
 static struct platform_driver serial_omap_driver = {
 	.probe          = serial_omap_probe,
-	.remove         = serial_omap_remove,
+	.remove_new     = serial_omap_remove,
 	.driver		= {
 		.name	= OMAP_SERIAL_DRIVER_NAME,
 		.pm	= &serial_omap_dev_pm_ops,
-- 
GitLab


From 8e94fc93762a5999053f35de99306360d9ce5dda Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:57 +0100
Subject: [PATCH 0356/4076] serial: owl: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-30-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/owl-uart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/owl-uart.c b/drivers/tty/serial/owl-uart.c
index 919f5e5aa0f1c..d9fe85397741d 100644
--- a/drivers/tty/serial/owl-uart.c
+++ b/drivers/tty/serial/owl-uart.c
@@ -725,20 +725,18 @@ static int owl_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int owl_uart_remove(struct platform_device *pdev)
+static void owl_uart_remove(struct platform_device *pdev)
 {
 	struct owl_uart_port *owl_port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&owl_uart_driver, &owl_port->port);
 	owl_uart_ports[pdev->id] = NULL;
 	clk_disable_unprepare(owl_port->clk);
-
-	return 0;
 }
 
 static struct platform_driver owl_uart_platform_driver = {
 	.probe = owl_uart_probe,
-	.remove = owl_uart_remove,
+	.remove_new = owl_uart_remove,
 	.driver = {
 		.name = "owl-uart",
 		.of_match_table = owl_uart_dt_matches,
-- 
GitLab


From 915fd7f32d25365a076176af71e9a4787772f2cc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:58 +0100
Subject: [PATCH 0357/4076] serial: pic32: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-31-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/pic32_uart.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/pic32_uart.c b/drivers/tty/serial/pic32_uart.c
index 3a95bf5d55d36..bbb46e6e98a24 100644
--- a/drivers/tty/serial/pic32_uart.c
+++ b/drivers/tty/serial/pic32_uart.c
@@ -938,7 +938,7 @@ err:
 	return ret;
 }
 
-static int pic32_uart_remove(struct platform_device *pdev)
+static void pic32_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct pic32_sport *sport = to_pic32_sport(port);
@@ -947,9 +947,6 @@ static int pic32_uart_remove(struct platform_device *pdev)
 	clk_disable_unprepare(sport->clk);
 	platform_set_drvdata(pdev, NULL);
 	pic32_sports[sport->idx] = NULL;
-
-	/* automatic unroll of sport and gpios */
-	return 0;
 }
 
 static const struct of_device_id pic32_serial_dt_ids[] = {
@@ -960,7 +957,7 @@ MODULE_DEVICE_TABLE(of, pic32_serial_dt_ids);
 
 static struct platform_driver pic32_uart_platform_driver = {
 	.probe		= pic32_uart_probe,
-	.remove		= pic32_uart_remove,
+	.remove_new	= pic32_uart_remove,
 	.driver		= {
 		.name	= PIC32_DEV_NAME,
 		.of_match_table	= of_match_ptr(pic32_serial_dt_ids),
-- 
GitLab


From dd4d4497be8ff2a72e4345c3c1b6450cadfa75d6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:29:59 +0100
Subject: [PATCH 0358/4076] serial: qcom_geni: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-32-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/qcom_geni_serial.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 7e78f97e8f435..e63a8fbe63bdb 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1696,7 +1696,7 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qcom_geni_serial_remove(struct platform_device *pdev)
+static void qcom_geni_serial_remove(struct platform_device *pdev)
 {
 	struct qcom_geni_serial_port *port = platform_get_drvdata(pdev);
 	struct uart_driver *drv = port->private_data.drv;
@@ -1704,8 +1704,6 @@ static int qcom_geni_serial_remove(struct platform_device *pdev)
 	dev_pm_clear_wake_irq(&pdev->dev);
 	device_init_wakeup(&pdev->dev, false);
 	uart_remove_one_port(drv, &port->uport);
-
-	return 0;
 }
 
 static int qcom_geni_serial_sys_suspend(struct device *dev)
@@ -1805,7 +1803,7 @@ static const struct of_device_id qcom_geni_serial_match_table[] = {
 MODULE_DEVICE_TABLE(of, qcom_geni_serial_match_table);
 
 static struct platform_driver qcom_geni_serial_platform_driver = {
-	.remove = qcom_geni_serial_remove,
+	.remove_new = qcom_geni_serial_remove,
 	.probe = qcom_geni_serial_probe,
 	.driver = {
 		.name = "qcom_geni_serial",
-- 
GitLab


From b9fd3145c962d4f37e5e321c0f589d2da74109eb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:00 +0100
Subject: [PATCH 0359/4076] serial: rda: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-33-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/rda-uart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/rda-uart.c b/drivers/tty/serial/rda-uart.c
index d824c8318f330..13deb355cf1bc 100644
--- a/drivers/tty/serial/rda-uart.c
+++ b/drivers/tty/serial/rda-uart.c
@@ -780,19 +780,17 @@ static int rda_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int rda_uart_remove(struct platform_device *pdev)
+static void rda_uart_remove(struct platform_device *pdev)
 {
 	struct rda_uart_port *rda_port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&rda_uart_driver, &rda_port->port);
 	rda_uart_ports[pdev->id] = NULL;
-
-	return 0;
 }
 
 static struct platform_driver rda_uart_platform_driver = {
 	.probe = rda_uart_probe,
-	.remove = rda_uart_remove,
+	.remove_new = rda_uart_remove,
 	.driver = {
 		.name = "rda-uart",
 		.of_match_table = rda_uart_dt_matches,
-- 
GitLab


From 1158e40b26d2fc5f7554c795ec0d8e8a42484f7f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:01 +0100
Subject: [PATCH 0360/4076] serial: sa1100: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-34-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sa1100.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sa1100.c b/drivers/tty/serial/sa1100.c
index be7bcd75d9f49..79c794fa65451 100644
--- a/drivers/tty/serial/sa1100.c
+++ b/drivers/tty/serial/sa1100.c
@@ -870,19 +870,17 @@ static int sa1100_serial_probe(struct platform_device *dev)
 	return 0;
 }
 
-static int sa1100_serial_remove(struct platform_device *pdev)
+static void sa1100_serial_remove(struct platform_device *pdev)
 {
 	struct sa1100_port *sport = platform_get_drvdata(pdev);
 
 	if (sport)
 		uart_remove_one_port(&sa1100_reg, &sport->port);
-
-	return 0;
 }
 
 static struct platform_driver sa11x0_serial_driver = {
 	.probe		= sa1100_serial_probe,
-	.remove		= sa1100_serial_remove,
+	.remove_new	= sa1100_serial_remove,
 	.suspend	= sa1100_serial_suspend,
 	.resume		= sa1100_serial_resume,
 	.driver		= {
-- 
GitLab


From 77772addc1f110a3afc36a8883173f746361edb1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:02 +0100
Subject: [PATCH 0361/4076] serial: samsung: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231110152927.70601-35-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/samsung_tty.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c
index 3bd552841cd28..1b0c2b467a307 100644
--- a/drivers/tty/serial/samsung_tty.c
+++ b/drivers/tty/serial/samsung_tty.c
@@ -2054,7 +2054,7 @@ static int s3c24xx_serial_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int s3c24xx_serial_remove(struct platform_device *dev)
+static void s3c24xx_serial_remove(struct platform_device *dev)
 {
 	struct uart_port *port = s3c24xx_dev_to_port(&dev->dev);
 
@@ -2063,8 +2063,6 @@ static int s3c24xx_serial_remove(struct platform_device *dev)
 	}
 
 	uart_unregister_driver(&s3c24xx_uart_drv);
-
-	return 0;
 }
 
 /* UART power management code */
@@ -2611,7 +2609,7 @@ MODULE_DEVICE_TABLE(of, s3c24xx_uart_dt_match);
 
 static struct platform_driver samsung_serial_driver = {
 	.probe		= s3c24xx_serial_probe,
-	.remove		= s3c24xx_serial_remove,
+	.remove_new	= s3c24xx_serial_remove,
 	.id_table	= s3c24xx_serial_driver_ids,
 	.driver		= {
 		.name	= "samsung-uart",
-- 
GitLab


From 2512ae09b86f93f0278ebcdec766b2b67bbe5686 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:03 +0100
Subject: [PATCH 0362/4076] serial: sccnxp: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-36-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sccnxp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c
index 8269b0fb30832..f24217a560d7a 100644
--- a/drivers/tty/serial/sccnxp.c
+++ b/drivers/tty/serial/sccnxp.c
@@ -1021,7 +1021,7 @@ err_out:
 	return ret;
 }
 
-static int sccnxp_remove(struct platform_device *pdev)
+static void sccnxp_remove(struct platform_device *pdev)
 {
 	int i;
 	struct sccnxp_port *s = platform_get_drvdata(pdev);
@@ -1041,8 +1041,6 @@ static int sccnxp_remove(struct platform_device *pdev)
 		if (ret)
 			dev_err(&pdev->dev, "Failed to disable regulator\n");
 	}
-
-	return 0;
 }
 
 static struct platform_driver sccnxp_uart_driver = {
@@ -1050,7 +1048,7 @@ static struct platform_driver sccnxp_uart_driver = {
 		.name	= SCCNXP_NAME,
 	},
 	.probe		= sccnxp_probe,
-	.remove		= sccnxp_remove,
+	.remove_new	= sccnxp_remove,
 	.id_table	= sccnxp_id_table,
 };
 module_platform_driver(sccnxp_uart_driver);
-- 
GitLab


From d388186258436b3feaffa592fc8c8842ab37f09c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:04 +0100
Subject: [PATCH 0363/4076] serial: tegra: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-37-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial-tegra.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index 6d4006b419754..525f3a2f7bd47 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -1611,13 +1611,12 @@ static int tegra_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int tegra_uart_remove(struct platform_device *pdev)
+static void tegra_uart_remove(struct platform_device *pdev)
 {
 	struct tegra_uart_port *tup = platform_get_drvdata(pdev);
 	struct uart_port *u = &tup->uport;
 
 	uart_remove_one_port(&tegra_uart_driver, u);
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -1644,7 +1643,7 @@ static const struct dev_pm_ops tegra_uart_pm_ops = {
 
 static struct platform_driver tegra_uart_platform_driver = {
 	.probe		= tegra_uart_probe,
-	.remove		= tegra_uart_remove,
+	.remove_new	= tegra_uart_remove,
 	.driver		= {
 		.name	= "serial-tegra",
 		.of_match_table = tegra_uart_of_match,
-- 
GitLab


From f785faa8cdd412b35e9264085f0df4a4fd6cd8f6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:05 +0100
Subject: [PATCH 0364/4076] serial: txx9: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-38-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_txx9.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index eaa9807224555..e1897894a4ef5 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -1052,7 +1052,7 @@ static int serial_txx9_probe(struct platform_device *dev)
 /*
  * Remove serial ports registered against a platform device.
  */
-static int serial_txx9_remove(struct platform_device *dev)
+static void serial_txx9_remove(struct platform_device *dev)
 {
 	int i;
 
@@ -1062,7 +1062,6 @@ static int serial_txx9_remove(struct platform_device *dev)
 		if (up->dev == &dev->dev)
 			serial_txx9_unregister_port(i);
 	}
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -1097,7 +1096,7 @@ static int serial_txx9_resume(struct platform_device *dev)
 
 static struct platform_driver serial_txx9_plat_driver = {
 	.probe		= serial_txx9_probe,
-	.remove		= serial_txx9_remove,
+	.remove_new	= serial_txx9_remove,
 #ifdef CONFIG_PM
 	.suspend	= serial_txx9_suspend,
 	.resume		= serial_txx9_resume,
-- 
GitLab


From 5fc247bf758522258e4cba750e80cc5558ff66e5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:06 +0100
Subject: [PATCH 0365/4076] serial: sh-sci: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231110152927.70601-39-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sh-sci.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 84ab434c94baf..745023001510a 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -3190,7 +3190,7 @@ static struct uart_driver sci_uart_driver = {
 	.cons		= SCI_CONSOLE,
 };
 
-static int sci_remove(struct platform_device *dev)
+static void sci_remove(struct platform_device *dev)
 {
 	struct sci_port *port = platform_get_drvdata(dev);
 	unsigned int type = port->port.type;	/* uart_remove_... clears it */
@@ -3204,8 +3204,6 @@ static int sci_remove(struct platform_device *dev)
 		device_remove_file(&dev->dev, &dev_attr_rx_fifo_trigger);
 	if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF)
 		device_remove_file(&dev->dev, &dev_attr_rx_fifo_timeout);
-
-	return 0;
 }
 
 
@@ -3470,7 +3468,7 @@ static SIMPLE_DEV_PM_OPS(sci_dev_pm_ops, sci_suspend, sci_resume);
 
 static struct platform_driver sci_driver = {
 	.probe		= sci_probe,
-	.remove		= sci_remove,
+	.remove_new	= sci_remove,
 	.driver		= {
 		.name	= "sh-sci",
 		.pm	= &sci_dev_pm_ops,
-- 
GitLab


From 0a208f3d58c76445379eb89cc8660d1ff6d7f988 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:07 +0100
Subject: [PATCH 0366/4076] serial: sifive: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20231110152927.70601-40-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sifive.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index b296e57a9dee4..3541235a3ab69 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -1007,7 +1007,7 @@ probe_out1:
 	return r;
 }
 
-static int sifive_serial_remove(struct platform_device *dev)
+static void sifive_serial_remove(struct platform_device *dev)
 {
 	struct sifive_serial_port *ssp = platform_get_drvdata(dev);
 
@@ -1015,8 +1015,6 @@ static int sifive_serial_remove(struct platform_device *dev)
 	uart_remove_one_port(&sifive_serial_uart_driver, &ssp->port);
 	free_irq(ssp->port.irq, ssp);
 	clk_notifier_unregister(ssp->clk, &ssp->clk_notifier);
-
-	return 0;
 }
 
 static int sifive_serial_suspend(struct device *dev)
@@ -1045,7 +1043,7 @@ MODULE_DEVICE_TABLE(of, sifive_serial_of_match);
 
 static struct platform_driver sifive_serial_platform_driver = {
 	.probe		= sifive_serial_probe,
-	.remove		= sifive_serial_remove,
+	.remove_new	= sifive_serial_remove,
 	.driver		= {
 		.name	= SIFIVE_SERIAL_NAME,
 		.pm = pm_sleep_ptr(&sifive_uart_pm_ops),
-- 
GitLab


From ef2a86440e7d48e09eeb7f6a48359194603d5bdc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:08 +0100
Subject: [PATCH 0367/4076] serial: sprd: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Chunyan Zhang <zhang.lyra@gmail.com>
Link: https://lore.kernel.org/r/20231110152927.70601-41-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sprd_serial.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c
index f257525f92995..15f14fa593da5 100644
--- a/drivers/tty/serial/sprd_serial.c
+++ b/drivers/tty/serial/sprd_serial.c
@@ -1076,7 +1076,7 @@ static struct uart_driver sprd_uart_driver = {
 	.cons = SPRD_CONSOLE,
 };
 
-static int sprd_remove(struct platform_device *dev)
+static void sprd_remove(struct platform_device *dev)
 {
 	struct sprd_uart_port *sup = platform_get_drvdata(dev);
 
@@ -1089,8 +1089,6 @@ static int sprd_remove(struct platform_device *dev)
 
 	if (!sprd_ports_num)
 		uart_unregister_driver(&sprd_uart_driver);
-
-	return 0;
 }
 
 static bool sprd_uart_is_console(struct uart_port *uport)
@@ -1257,7 +1255,7 @@ MODULE_DEVICE_TABLE(of, serial_ids);
 
 static struct platform_driver sprd_platform_driver = {
 	.probe		= sprd_probe,
-	.remove		= sprd_remove,
+	.remove_new	= sprd_remove,
 	.driver		= {
 		.name	= "sprd_serial",
 		.of_match_table = serial_ids,
-- 
GitLab


From 338bc8f964b8b00f1224eebd89f84f59a6fee703 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:09 +0100
Subject: [PATCH 0368/4076] serial: st-asc: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-42-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/st-asc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c
index a821f5d76a26f..bbb5595d7e24c 100644
--- a/drivers/tty/serial/st-asc.c
+++ b/drivers/tty/serial/st-asc.c
@@ -793,13 +793,11 @@ static int asc_serial_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int asc_serial_remove(struct platform_device *pdev)
+static void asc_serial_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&asc_uart_driver, port);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -932,7 +930,7 @@ static const struct dev_pm_ops asc_serial_pm_ops = {
 
 static struct platform_driver asc_serial_driver = {
 	.probe		= asc_serial_probe,
-	.remove		= asc_serial_remove,
+	.remove_new	= asc_serial_remove,
 	.driver	= {
 		.name	= DRIVER_NAME,
 		.pm	= &asc_serial_pm_ops,
-- 
GitLab


From 2cf562441b51bc0dc2cd179d34b83f79293e0fea Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:10 +0100
Subject: [PATCH 0369/4076] serial: stm32: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-43-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/stm32-usart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index 3048620315d60..9781c143def29 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -1822,7 +1822,7 @@ err_dma_rx:
 	return ret;
 }
 
-static int stm32_usart_serial_remove(struct platform_device *pdev)
+static void stm32_usart_serial_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct stm32_port *stm32_port = to_stm32_port(port);
@@ -1861,8 +1861,6 @@ static int stm32_usart_serial_remove(struct platform_device *pdev)
 	}
 
 	stm32_usart_deinit_port(stm32_port);
-
-	return 0;
 }
 
 static void __maybe_unused stm32_usart_console_putchar(struct uart_port *port, unsigned char ch)
@@ -2146,7 +2144,7 @@ static const struct dev_pm_ops stm32_serial_pm_ops = {
 
 static struct platform_driver stm32_serial_driver = {
 	.probe		= stm32_usart_serial_probe,
-	.remove		= stm32_usart_serial_remove,
+	.remove_new	= stm32_usart_serial_remove,
 	.driver	= {
 		.name	= DRIVER_NAME,
 		.pm	= &stm32_serial_pm_ops,
-- 
GitLab


From 3cfff33ae8788b06dd9d4ae1eaa23fc6f1dfb13b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:11 +0100
Subject: [PATCH 0370/4076] serial: sunhv: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-44-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sunhv.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index 5bfc0040f17be..8d612ab80680c 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -595,7 +595,7 @@ out_free_port:
 	return err;
 }
 
-static int hv_remove(struct platform_device *dev)
+static void hv_remove(struct platform_device *dev)
 {
 	struct uart_port *port = platform_get_drvdata(dev);
 
@@ -608,8 +608,6 @@ static int hv_remove(struct platform_device *dev)
 	kfree(con_write_page);
 	kfree(port);
 	sunhv_port = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id hv_match[] = {
@@ -630,7 +628,7 @@ static struct platform_driver hv_driver = {
 		.of_match_table = hv_match,
 	},
 	.probe		= hv_probe,
-	.remove		= hv_remove,
+	.remove_new	= hv_remove,
 };
 
 static int __init sunhv_init(void)
-- 
GitLab


From 3f51b27c9ada772c6888e26586247e6ba1a2c1a1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:12 +0100
Subject: [PATCH 0371/4076] serial: sunplus: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-45-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sunplus-uart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sunplus-uart.c b/drivers/tty/serial/sunplus-uart.c
index 4251f4e1ba997..99f5285819d4b 100644
--- a/drivers/tty/serial/sunplus-uart.c
+++ b/drivers/tty/serial/sunplus-uart.c
@@ -662,13 +662,11 @@ static int sunplus_uart_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int sunplus_uart_remove(struct platform_device *pdev)
+static void sunplus_uart_remove(struct platform_device *pdev)
 {
 	struct sunplus_uart_port *sup = platform_get_drvdata(pdev);
 
 	uart_remove_one_port(&sunplus_uart_driver, &sup->port);
-
-	return 0;
 }
 
 static int __maybe_unused sunplus_uart_suspend(struct device *dev)
@@ -703,7 +701,7 @@ MODULE_DEVICE_TABLE(of, sp_uart_of_match);
 
 static struct platform_driver sunplus_uart_platform_driver = {
 	.probe		= sunplus_uart_probe,
-	.remove		= sunplus_uart_remove,
+	.remove_new	= sunplus_uart_remove,
 	.driver = {
 		.name	= "sunplus_uart",
 		.of_match_table = sp_uart_of_match,
-- 
GitLab


From 78767116e28c536ecbba46e25a278b13106eb34b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:13 +0100
Subject: [PATCH 0372/4076] serial: sunsab: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-46-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sunsab.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 6aa51a6f80630..ff557796b5781 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -1066,7 +1066,7 @@ out:
 	return err;
 }
 
-static int sab_remove(struct platform_device *op)
+static void sab_remove(struct platform_device *op)
 {
 	struct uart_sunsab_port *up = platform_get_drvdata(op);
 
@@ -1078,8 +1078,6 @@ static int sab_remove(struct platform_device *op)
 	of_iounmap(&op->resource[0],
 		   up[0].port.membase,
 		   sizeof(union sab82532_async_regs));
-
-	return 0;
 }
 
 static const struct of_device_id sab_match[] = {
@@ -1100,7 +1098,7 @@ static struct platform_driver sab_driver = {
 		.of_match_table = sab_match,
 	},
 	.probe		= sab_probe,
-	.remove		= sab_remove,
+	.remove_new	= sab_remove,
 };
 
 static int __init sunsab_init(void)
-- 
GitLab


From 499dd0b5b0cbc1cb07b111f36d4bd69b5f050255 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:14 +0100
Subject: [PATCH 0373/4076] serial: sunsu: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-47-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sunsu.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index 1e051cc2591c7..c8b65f4b2710e 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -1515,7 +1515,7 @@ out_unmap:
 	return err;
 }
 
-static int su_remove(struct platform_device *op)
+static void su_remove(struct platform_device *op)
 {
 	struct uart_sunsu_port *up = platform_get_drvdata(op);
 	bool kbdms = false;
@@ -1536,8 +1536,6 @@ static int su_remove(struct platform_device *op)
 
 	if (kbdms)
 		kfree(up);
-
-	return 0;
 }
 
 static const struct of_device_id su_match[] = {
@@ -1565,7 +1563,7 @@ static struct platform_driver su_driver = {
 		.of_match_table = su_match,
 	},
 	.probe		= su_probe,
-	.remove		= su_remove,
+	.remove_new	= su_remove,
 };
 
 static int __init sunsu_init(void)
-- 
GitLab


From 84f74fd3002fb620d46c24694c6d4e320b39ffb2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:15 +0100
Subject: [PATCH 0374/4076] serial: sunzilog: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-48-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sunzilog.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index d3b5e864b727b..c99289c6c8f89 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -1513,7 +1513,7 @@ static void zs_remove_one(struct uart_sunzilog_port *up)
 		uart_remove_one_port(&sunzilog_reg, &up->port);
 }
 
-static int zs_remove(struct platform_device *op)
+static void zs_remove(struct platform_device *op)
 {
 	struct uart_sunzilog_port *up = platform_get_drvdata(op);
 	struct zilog_layout __iomem *regs;
@@ -1523,8 +1523,6 @@ static int zs_remove(struct platform_device *op)
 
 	regs = sunzilog_chip_regs[up[0].port.line / 2];
 	of_iounmap(&op->resource[0], regs, sizeof(struct zilog_layout));
-
-	return 0;
 }
 
 static const struct of_device_id zs_match[] = {
@@ -1541,7 +1539,7 @@ static struct platform_driver zs_driver = {
 		.of_match_table = zs_match,
 	},
 	.probe		= zs_probe,
-	.remove		= zs_remove,
+	.remove_new	= zs_remove,
 };
 
 static int __init sunzilog_init(void)
-- 
GitLab


From 5e29d46f411d3b799182416c8bd939ffd79b87c8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:16 +0100
Subject: [PATCH 0375/4076] serial: tegra-tcu: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-49-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/tegra-tcu.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/tegra-tcu.c b/drivers/tty/serial/tegra-tcu.c
index 65069daf36ec0..d9c78320eb020 100644
--- a/drivers/tty/serial/tegra-tcu.c
+++ b/drivers/tty/serial/tegra-tcu.c
@@ -266,7 +266,7 @@ free_tx:
 	return err;
 }
 
-static int tegra_tcu_remove(struct platform_device *pdev)
+static void tegra_tcu_remove(struct platform_device *pdev)
 {
 	struct tegra_tcu *tcu = platform_get_drvdata(pdev);
 
@@ -277,8 +277,6 @@ static int tegra_tcu_remove(struct platform_device *pdev)
 	uart_remove_one_port(&tcu->driver, &tcu->port);
 	uart_unregister_driver(&tcu->driver);
 	mbox_free_channel(tcu->tx);
-
-	return 0;
 }
 
 static const struct of_device_id tegra_tcu_match[] = {
@@ -293,7 +291,7 @@ static struct platform_driver tegra_tcu_driver = {
 		.of_match_table = tegra_tcu_match,
 	},
 	.probe = tegra_tcu_probe,
-	.remove = tegra_tcu_remove,
+	.remove_new = tegra_tcu_remove,
 };
 module_platform_driver(tegra_tcu_driver);
 
-- 
GitLab


From 7d8ffee1f41dd74f3484417188da1c439d49d840 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:17 +0100
Subject: [PATCH 0376/4076] serial: timbuart: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-50-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/timbuart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/timbuart.c b/drivers/tty/serial/timbuart.c
index 0cc6524f5e8ba..4bc89a9b380a7 100644
--- a/drivers/tty/serial/timbuart.c
+++ b/drivers/tty/serial/timbuart.c
@@ -473,7 +473,7 @@ err_mem:
 	return err;
 }
 
-static int timbuart_remove(struct platform_device *dev)
+static void timbuart_remove(struct platform_device *dev)
 {
 	struct timbuart_port *uart = platform_get_drvdata(dev);
 
@@ -481,8 +481,6 @@ static int timbuart_remove(struct platform_device *dev)
 	uart_remove_one_port(&timbuart_driver, &uart->port);
 	uart_unregister_driver(&timbuart_driver);
 	kfree(uart);
-
-	return 0;
 }
 
 static struct platform_driver timbuart_platform_driver = {
@@ -490,7 +488,7 @@ static struct platform_driver timbuart_platform_driver = {
 		.name	= "timb-uart",
 	},
 	.probe		= timbuart_probe,
-	.remove		= timbuart_remove,
+	.remove_new	= timbuart_remove,
 };
 
 module_platform_driver(timbuart_platform_driver);
-- 
GitLab


From 2a0e8be950b9f945e526c600f9e6f4d265752497 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:18 +0100
Subject: [PATCH 0377/4076] serial: uartlite: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-51-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/uartlite.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index 404c14acafa5f..48c9fca1566b2 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -890,7 +890,7 @@ of_err:
 	return ret;
 }
 
-static int ulite_remove(struct platform_device *pdev)
+static void ulite_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = dev_get_drvdata(&pdev->dev);
 	struct uartlite_data *pdata = port->private_data;
@@ -900,7 +900,6 @@ static int ulite_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	return 0;
 }
 
 /* work with hotplug and coldplug */
@@ -908,7 +907,7 @@ MODULE_ALIAS("platform:uartlite");
 
 static struct platform_driver ulite_platform_driver = {
 	.probe = ulite_probe,
-	.remove = ulite_remove,
+	.remove_new = ulite_remove,
 	.driver = {
 		.name  = "uartlite",
 		.of_match_table = of_match_ptr(ulite_of_match),
-- 
GitLab


From 0e1ff92834b78cc434cd7099680c57f7aa87aff8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:19 +0100
Subject: [PATCH 0378/4076] serial: ucc: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-52-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/ucc_uart.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c
index ed7a6bb5596ab..f9ad942c9aafe 100644
--- a/drivers/tty/serial/ucc_uart.c
+++ b/drivers/tty/serial/ucc_uart.c
@@ -1459,7 +1459,7 @@ out_free:
 	return ret;
 }
 
-static int ucc_uart_remove(struct platform_device *ofdev)
+static void ucc_uart_remove(struct platform_device *ofdev)
 {
 	struct uart_qe_port *qe_port = platform_get_drvdata(ofdev);
 
@@ -1470,8 +1470,6 @@ static int ucc_uart_remove(struct platform_device *ofdev)
 	of_node_put(qe_port->np);
 
 	kfree(qe_port);
-
-	return 0;
 }
 
 static const struct of_device_id ucc_uart_match[] = {
@@ -1492,7 +1490,7 @@ static struct platform_driver ucc_uart_of_driver = {
 		.of_match_table    = ucc_uart_match,
 	},
 	.probe  	= ucc_uart_probe,
-	.remove 	= ucc_uart_remove,
+	.remove_new 	= ucc_uart_remove,
 };
 
 static int __init ucc_uart_init(void)
-- 
GitLab


From 0ea163e23552f51603f9a412812c753cdef1d94d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 10 Nov 2023 16:30:20 +0100
Subject: [PATCH 0379/4076] serial: xilinx_uartps: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231110152927.70601-53-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/xilinx_uartps.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 66a45a634158f..6decf2b13340a 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1666,7 +1666,7 @@ err_out_unregister_driver:
  *
  * Return: 0 on success, negative errno otherwise
  */
-static int cdns_uart_remove(struct platform_device *pdev)
+static void cdns_uart_remove(struct platform_device *pdev)
 {
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct cdns_uart *cdns_uart_data = port->private_data;
@@ -1692,12 +1692,11 @@ static int cdns_uart_remove(struct platform_device *pdev)
 
 	if (!--instances)
 		uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
-	return 0;
 }
 
 static struct platform_driver cdns_uart_platform_driver = {
 	.probe   = cdns_uart_probe,
-	.remove  = cdns_uart_remove,
+	.remove_new = cdns_uart_remove,
 	.driver  = {
 		.name = CDNS_UART_NAME,
 		.of_match_table = cdns_uart_of_match,
-- 
GitLab


From 5592d7e87f239708dc90011d9cf35726657be861 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 11:36:21 +0100
Subject: [PATCH 0380/4076] tty: con3215: drop raw3215_info::ubuffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

clang-struct [1] found raw3215_info::ubuffer unused.

It's actually not used since 2004 when we switched to kernel buffers.

[1] https://github.com/jirislaby/clang-struct

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231121103626.17772-2-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/s390/char/con3215.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index 99361618c31f3..34bc343dcfcca 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -89,7 +89,6 @@ struct raw3215_info {
 	wait_queue_head_t empty_wait; /* wait queue for flushing */
 	struct timer_list timer;      /* timer for delayed output */
 	int line_pos;		      /* position on the line (for tabs) */
-	char ubuffer[80];	      /* copy_from_user buffer */
 };
 
 /* array of 3215 devices structures */
-- 
GitLab


From 5bd8ad372398e64c8a33cb3a0c2a5f823c997ef7 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 11:36:22 +0100
Subject: [PATCH 0381/4076] tty: ipwireless: remove unused
 ipw_dev::attribute_memory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

clang-struct [1] found ipw_dev::attribute_memory unused.

As far as I can see it was never used since the driver merge. Drop it.

[1] https://github.com/jirislaby/clang-struct

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: David Sterba <dsterba@suse.com>
Acked-by: David Sterba <dsterba@suse.com>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231121103626.17772-3-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/ipwireless/main.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/tty/ipwireless/main.h b/drivers/tty/ipwireless/main.h
index 73818bb644167..a5728a5b3f83e 100644
--- a/drivers/tty/ipwireless/main.h
+++ b/drivers/tty/ipwireless/main.h
@@ -49,9 +49,6 @@ struct ipw_dev {
 
 	void __iomem *common_memory;
 
-	/* Reference to attribute memory, containing CIS data */
-	void *attribute_memory;
-
 	/* Hardware context */
 	struct ipw_hardware *hardware;
 	/* Network layer context */
-- 
GitLab


From 79b18e51226e5d99c597a0ed8fee3df1dd595c99 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 11:36:23 +0100
Subject: [PATCH 0382/4076] tty: jsm: remove unused members from struct
 board_ops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

clang-struct [1] found board_ops::get_uart_bytes_left() and
::send_immediate_char() unused.

Both are only set but never called. And it has been like that since the
git history, so drop both the members along with the cls+neo
implementations.

[1] https://github.com/jirislaby/clang-struct

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231121103626.17772-4-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/jsm/jsm.h     |  2 --
 drivers/tty/serial/jsm/jsm_cls.c | 36 ----------------------------
 drivers/tty/serial/jsm/jsm_neo.c | 40 --------------------------------
 3 files changed, 78 deletions(-)

diff --git a/drivers/tty/serial/jsm/jsm.h b/drivers/tty/serial/jsm/jsm.h
index 8489c07f4cd5e..08a42f045ec8c 100644
--- a/drivers/tty/serial/jsm/jsm.h
+++ b/drivers/tty/serial/jsm/jsm.h
@@ -115,8 +115,6 @@ struct board_ops {
 	void (*send_start_character)(struct jsm_channel *ch);
 	void (*send_stop_character)(struct jsm_channel *ch);
 	void (*copy_data_from_queue_to_uart)(struct jsm_channel *ch);
-	u32 (*get_uart_bytes_left)(struct jsm_channel *ch);
-	void (*send_immediate_char)(struct jsm_channel *ch, unsigned char);
 };
 
 
diff --git a/drivers/tty/serial/jsm/jsm_cls.c b/drivers/tty/serial/jsm/jsm_cls.c
index 3fd57ac3ad81c..1eda48964c0b6 100644
--- a/drivers/tty/serial/jsm/jsm_cls.c
+++ b/drivers/tty/serial/jsm/jsm_cls.c
@@ -877,28 +877,6 @@ static void cls_uart_off(struct jsm_channel *ch)
 	writeb(0, &ch->ch_cls_uart->ier);
 }
 
-/*
- * cls_get_uarts_bytes_left.
- * Returns 0 is nothing left in the FIFO, returns 1 otherwise.
- *
- * The channel lock MUST be held by the calling function.
- */
-static u32 cls_get_uart_bytes_left(struct jsm_channel *ch)
-{
-	u8 left = 0;
-	u8 lsr = readb(&ch->ch_cls_uart->lsr);
-
-	/* Determine whether the Transmitter is empty or not */
-	if (!(lsr & UART_LSR_TEMT))
-		left = 1;
-	else {
-		ch->ch_flags |= (CH_TX_FIFO_EMPTY | CH_TX_FIFO_LWM);
-		left = 0;
-	}
-
-	return left;
-}
-
 /*
  * cls_send_break.
  * Starts sending a break thru the UART.
@@ -916,18 +894,6 @@ static void cls_send_break(struct jsm_channel *ch)
 	}
 }
 
-/*
- * cls_send_immediate_char.
- * Sends a specific character as soon as possible to the UART,
- * jumping over any bytes that might be in the write queue.
- *
- * The channel lock MUST be held by the calling function.
- */
-static void cls_send_immediate_char(struct jsm_channel *ch, unsigned char c)
-{
-	writeb(c, &ch->ch_cls_uart->txrx);
-}
-
 struct board_ops jsm_cls_ops = {
 	.intr =				cls_intr,
 	.uart_init =			cls_uart_init,
@@ -943,7 +909,5 @@ struct board_ops jsm_cls_ops = {
 	.send_start_character =		cls_send_start_character,
 	.send_stop_character =		cls_send_stop_character,
 	.copy_data_from_queue_to_uart = cls_copy_data_from_queue_to_uart,
-	.get_uart_bytes_left =		cls_get_uart_bytes_left,
-	.send_immediate_char =		cls_send_immediate_char
 };
 
diff --git a/drivers/tty/serial/jsm/jsm_neo.c b/drivers/tty/serial/jsm/jsm_neo.c
index 2bd6404289708..1fa10f19368f5 100644
--- a/drivers/tty/serial/jsm/jsm_neo.c
+++ b/drivers/tty/serial/jsm/jsm_neo.c
@@ -1309,25 +1309,6 @@ static void neo_uart_off(struct jsm_channel *ch)
 	writeb(0, &ch->ch_neo_uart->ier);
 }
 
-static u32 neo_get_uart_bytes_left(struct jsm_channel *ch)
-{
-	u8 left = 0;
-	u8 lsr = readb(&ch->ch_neo_uart->lsr);
-
-	/* We must cache the LSR as some of the bits get reset once read... */
-	ch->ch_cached_lsr |= lsr;
-
-	/* Determine whether the Transmitter is empty or not */
-	if (!(lsr & UART_LSR_TEMT))
-		left = 1;
-	else {
-		ch->ch_flags |= (CH_TX_FIFO_EMPTY | CH_TX_FIFO_LWM);
-		left = 0;
-	}
-
-	return left;
-}
-
 /* Channel lock MUST be held by the calling function! */
 static void neo_send_break(struct jsm_channel *ch)
 {
@@ -1348,25 +1329,6 @@ static void neo_send_break(struct jsm_channel *ch)
 	}
 }
 
-/*
- * neo_send_immediate_char.
- *
- * Sends a specific character as soon as possible to the UART,
- * jumping over any bytes that might be in the write queue.
- *
- * The channel lock MUST be held by the calling function.
- */
-static void neo_send_immediate_char(struct jsm_channel *ch, unsigned char c)
-{
-	if (!ch)
-		return;
-
-	writeb(c, &ch->ch_neo_uart->txrx);
-
-	/* flush write operation */
-	neo_pci_posting_flush(ch->ch_bd);
-}
-
 struct board_ops jsm_neo_ops = {
 	.intr				= neo_intr,
 	.uart_init			= neo_uart_init,
@@ -1382,6 +1344,4 @@ struct board_ops jsm_neo_ops = {
 	.send_start_character		= neo_send_start_character,
 	.send_stop_character		= neo_send_stop_character,
 	.copy_data_from_queue_to_uart	= neo_copy_data_from_queue_to_uart,
-	.get_uart_bytes_left		= neo_get_uart_bytes_left,
-	.send_immediate_char		= neo_send_immediate_char
 };
-- 
GitLab


From e1d64e153aee72097db1174766ed7adec08724ea Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 11:36:24 +0100
Subject: [PATCH 0383/4076] tty: jsm: remove unused struct jsm_board members
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

clang-struct [1] found jsm_board::type and ::jsm_board_entry unused.

::jsm_board_entry is unused since 614a7d6a76b7 ("fix up newly added jsm driver")
::type was never used as far as I can tell. Even when the driver was
introduced in the pre-git era.

Remove them both.

[1] https://github.com/jirislaby/clang-struct

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231121103626.17772-5-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/jsm/jsm.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/tty/serial/jsm/jsm.h b/drivers/tty/serial/jsm/jsm.h
index 08a42f045ec8c..df55e5dc5afc2 100644
--- a/drivers/tty/serial/jsm/jsm.h
+++ b/drivers/tty/serial/jsm/jsm.h
@@ -125,7 +125,6 @@ struct jsm_board
 {
 	int		boardnum;	/* Board number: 0-32 */
 
-	int		type;		/* Type of board */
 	u8		rev;		/* PCI revision ID */
 	struct pci_dev	*pci_dev;
 	u32		maxports;	/* MAX ports this board can handle */
@@ -153,8 +152,6 @@ struct jsm_board
 	u32		bd_dividend;	/* Board/UARTs specific dividend */
 
 	struct board_ops *bd_ops;
-
-	struct list_head jsm_board_entry;
 };
 
 /************************************************************************
-- 
GitLab


From d0b2b1efbdd29662896591791f1c38477d78d483 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 11:36:25 +0100
Subject: [PATCH 0384/4076] tty: rp2: remove unused rp2_uart_port::ignore_rx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

clang-struct [1] found rp2_uart_port::ignore_rx unused.

It was actually never used. Not even in introductory commit 7d9f49afa451
("serial: rp2: New driver for Comtrol RocketPort 2 cards").

[1] https://github.com/jirislaby/clang-struct

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Kevin Cernekee <cernekee@gmail.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231121103626.17772-6-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/rp2.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/tty/serial/rp2.c b/drivers/tty/serial/rp2.c
index d46a81cddfcd7..4132fcff7d4e2 100644
--- a/drivers/tty/serial/rp2.c
+++ b/drivers/tty/serial/rp2.c
@@ -178,7 +178,6 @@ struct rp2_card;
 struct rp2_uart_port {
 	struct uart_port		port;
 	int				idx;
-	int				ignore_rx;
 	struct rp2_card			*card;
 	void __iomem			*asic_base;
 	void __iomem			*base;
-- 
GitLab


From 50d371a9c5babf54bbcd267a09a2786b6a44a194 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 11:36:26 +0100
Subject: [PATCH 0385/4076] tty: serial_cs: remove unused struct serial_cfg_mem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

clang-struct [1] found struct serial_cfg_mem's members unused.

In fact, the whole structure is unused since commit 6ae3b84d9793
("serial_cs: use pcmcia_loop_config() and pre-determined values"). Drop
it completely.

[1] https://github.com/jirislaby/clang-struct

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231121103626.17772-7-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/serial_cs.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/tty/serial/8250/serial_cs.c b/drivers/tty/serial/8250/serial_cs.c
index dc2ef05a10ebe..2056aed466883 100644
--- a/drivers/tty/serial/8250/serial_cs.c
+++ b/drivers/tty/serial/8250/serial_cs.c
@@ -90,12 +90,6 @@ struct serial_info {
 	const struct serial_quirk *quirk;
 };
 
-struct serial_cfg_mem {
-	tuple_t tuple;
-	cisparse_t parse;
-	u_char buf[256];
-};
-
 /*
  * vers_1 5.0, "Brain Boxes", "2-Port RS232 card", "r6"
  * manfid 0x0160, 0x0104
-- 
GitLab


From dd6ffc9c57f69c2708f7c14dd7da5901b7d24b98 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@seco.com>
Date: Mon, 6 Nov 2023 10:24:28 -0500
Subject: [PATCH 0386/4076] tty: serial: uartlite: Document uartlite_data in
 kernel-doc style

Use @ and - to conform with kernel-doc style.

Reported-by: kernel test robot <yujie.liu@intel.com>
Signed-off-by: Sean Anderson <sean.anderson@seco.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Shubhrajyoti Datta <shubhrajyoti.datta@amd.com>
Link: https://lore.kernel.org/r/20231106152428.3641883-1-sean.anderson@seco.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/uartlite.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index 48c9fca1566b2..f9c69f543a26c 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -62,11 +62,11 @@ static struct uart_port *console_port;
 #endif
 
 /**
- * struct uartlite_data: Driver private data
- * reg_ops: Functions to read/write registers
- * clk: Our parent clock, if present
- * baud: The baud rate configured when this device was synthesized
- * cflags: The cflags for parity and data bits
+ * struct uartlite_data - Driver private data
+ * @reg_ops: Functions to read/write registers
+ * @clk: Our parent clock, if present
+ * @baud: The baud rate configured when this device was synthesized
+ * @cflags: The cflags for parity and data bits
  */
 struct uartlite_data {
 	const struct uartlite_reg_ops *reg_ops;
-- 
GitLab


From 9c8c269b4ae9c1b7f00350cec4777d17154049c0 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Wed, 15 Nov 2023 21:24:31 +0000
Subject: [PATCH 0387/4076] dt-bindings: serial: renesas,sci: Document RZ/Five
 SoC

The SCI block on the RZ/Five SoC is identical to one found on the RZ/G2UL
SoC. "renesas,r9a07g043-sci" compatible string will be used on the RZ/Five
SoC so to make this clear and to keep this file consistent, update the
comment to include RZ/Five SoC.

No driver changes are required as generic compatible string "renesas,sci"
will be used as a fallback on RZ/Five SoC.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231115212431.32872-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/serial/renesas,sci.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/serial/renesas,sci.yaml b/Documentation/devicetree/bindings/serial/renesas,sci.yaml
index 9f7305200c47e..64d3db6e54e5c 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci.yaml
+++ b/Documentation/devicetree/bindings/serial/renesas,sci.yaml
@@ -17,7 +17,7 @@ properties:
     oneOf:
       - items:
           - enum:
-              - renesas,r9a07g043-sci     # RZ/G2UL
+              - renesas,r9a07g043-sci     # RZ/G2UL and RZ/Five
               - renesas,r9a07g044-sci     # RZ/G2{L,LC}
               - renesas,r9a07g054-sci     # RZ/V2L
           - const: renesas,sci            # generic SCI compatible UART
-- 
GitLab


From 7f30c19caf94b98a1f672376e85a6968d756c25e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 5 Nov 2023 22:44:08 +0100
Subject: [PATCH 0388/4076] tty: hvc: Make hvc_remove() return no value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function hvc_remove() returns zero unconditionally. Make it return
void instead to make it obvious that the caller doesn't need to do any
error handling. Accordingly drop the error handling from
hvc_opal_remove().

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Link: https://lore.kernel.org/r/20231105214406.3765906-5-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/hvc/hvc_console.c |  3 +--
 drivers/tty/hvc/hvc_console.h |  2 +-
 drivers/tty/hvc/hvc_opal.c    | 15 +++++++--------
 3 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index 959fae54ca394..57f5c37125e63 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -976,7 +976,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 }
 EXPORT_SYMBOL_GPL(hvc_alloc);
 
-int hvc_remove(struct hvc_struct *hp)
+void hvc_remove(struct hvc_struct *hp)
 {
 	unsigned long flags;
 	struct tty_struct *tty;
@@ -1010,7 +1010,6 @@ int hvc_remove(struct hvc_struct *hp)
 		tty_vhangup(tty);
 		tty_kref_put(tty);
 	}
-	return 0;
 }
 EXPORT_SYMBOL_GPL(hvc_remove);
 
diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h
index 9668f821db01d..78f7543511f10 100644
--- a/drivers/tty/hvc/hvc_console.h
+++ b/drivers/tty/hvc/hvc_console.h
@@ -77,7 +77,7 @@ extern int hvc_instantiate(uint32_t vtermno, int index,
 extern struct hvc_struct * hvc_alloc(uint32_t vtermno, int data,
 				     const struct hv_ops *ops, int outbuf_size);
 /* remove a vterm from hvc tty operation (module_exit or hotplug remove) */
-extern int hvc_remove(struct hvc_struct *hp);
+extern void hvc_remove(struct hvc_struct *hp);
 
 /* data available */
 int hvc_poll(struct hvc_struct *hp);
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 992e199e0ea80..8995b253cf90b 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -235,16 +235,15 @@ static int hvc_opal_probe(struct platform_device *dev)
 static int hvc_opal_remove(struct platform_device *dev)
 {
 	struct hvc_struct *hp = dev_get_drvdata(&dev->dev);
-	int rc, termno;
+	int termno;
 
 	termno = hp->vtermno;
-	rc = hvc_remove(hp);
-	if (rc == 0) {
-		if (hvc_opal_privs[termno] != &hvc_opal_boot_priv)
-			kfree(hvc_opal_privs[termno]);
-		hvc_opal_privs[termno] = NULL;
-	}
-	return rc;
+	hvc_remove(hp);
+	if (hvc_opal_privs[termno] != &hvc_opal_boot_priv)
+		kfree(hvc_opal_privs[termno]);
+	hvc_opal_privs[termno] = NULL;
+
+	return 0;
 }
 
 static struct platform_driver hvc_opal_driver = {
-- 
GitLab


From aa46b225ebbfa7ff96aef431879e8bbc159071e5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 5 Nov 2023 22:44:09 +0100
Subject: [PATCH 0389/4076] tty: hvc: hvc_opal: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Link: https://lore.kernel.org/r/20231105214406.3765906-6-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/hvc/hvc_opal.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 8995b253cf90b..2cdf66e395cc1 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -232,7 +232,7 @@ static int hvc_opal_probe(struct platform_device *dev)
 	return 0;
 }
 
-static int hvc_opal_remove(struct platform_device *dev)
+static void hvc_opal_remove(struct platform_device *dev)
 {
 	struct hvc_struct *hp = dev_get_drvdata(&dev->dev);
 	int termno;
@@ -242,13 +242,11 @@ static int hvc_opal_remove(struct platform_device *dev)
 	if (hvc_opal_privs[termno] != &hvc_opal_boot_priv)
 		kfree(hvc_opal_privs[termno]);
 	hvc_opal_privs[termno] = NULL;
-
-	return 0;
 }
 
 static struct platform_driver hvc_opal_driver = {
 	.probe		= hvc_opal_probe,
-	.remove		= hvc_opal_remove,
+	.remove_new	= hvc_opal_remove,
 	.driver		= {
 		.name	= hvc_opal_name,
 		.of_match_table	= hvc_opal_match,
-- 
GitLab


From 17fabec94d61c27d7efdc66301f1508dc223e291 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Sun, 12 Nov 2023 18:31:19 -0800
Subject: [PATCH 0390/4076] serial: sifive: Declare PM operations as static

They are only used within this file, so they should have static linkage.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20231113023122.1185407-1-samuel.holland@sifive.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sifive.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index 3541235a3ab69..a4cc569a78a25 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -1031,8 +1031,8 @@ static int sifive_serial_resume(struct device *dev)
 	return uart_resume_port(&sifive_serial_uart_driver, &ssp->port);
 }
 
-DEFINE_SIMPLE_DEV_PM_OPS(sifive_uart_pm_ops, sifive_serial_suspend,
-			 sifive_serial_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(sifive_uart_pm_ops, sifive_serial_suspend,
+				sifive_serial_resume);
 
 static const struct of_device_id sifive_serial_of_match[] = {
 	{ .compatible = "sifive,fu540-c000-uart0" },
-- 
GitLab


From 55cb57ac75093e9e19d69ae5754a74805a05ca48 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Mon, 30 Oct 2023 17:22:40 -0400
Subject: [PATCH 0391/4076] serial: sunsab: remove trailing whitespaces

Fix coding style. No functional changes.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231030212240.975885-1-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sunsab.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index ff557796b5781..1ea2f33a07a74 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -443,7 +443,7 @@ static void sunsab_start_tx(struct uart_port *port)
 
 	up->interrupt_mask1 &= ~(SAB82532_IMR1_ALLS|SAB82532_IMR1_XPR);
 	writeb(up->interrupt_mask1, &up->regs->w.imr1);
-	
+
 	if (!test_bit(SAB82532_XPR, &up->irqflags))
 		return;
 
@@ -549,7 +549,7 @@ static int sunsab_startup(struct uart_port *port)
 	(void) readb(&up->regs->r.isr1);
 
 	/*
-	 * Now, initialize the UART 
+	 * Now, initialize the UART
 	 */
 	writeb(0, &up->regs->w.ccr0);				/* power-down */
 	writeb(SAB82532_CCR0_MCE | SAB82532_CCR0_SC_NRZ |
@@ -563,7 +563,7 @@ static int sunsab_startup(struct uart_port *port)
 			   SAB82532_MODE_RAC);
 	writeb(up->cached_mode, &up->regs->w.mode);
 	writeb(SAB82532_RFC_DPS|SAB82532_RFC_RFTH_32, &up->regs->w.rfc);
-	
+
 	tmp = readb(&up->regs->rw.ccr0);
 	tmp |= SAB82532_CCR0_PU;	/* power-up */
 	writeb(tmp, &up->regs->rw.ccr0);
@@ -607,7 +607,7 @@ static void sunsab_shutdown(struct uart_port *port)
 	up->cached_dafo &= ~SAB82532_DAFO_XBRK;
 	writeb(up->cached_dafo, &up->regs->rw.dafo);
 
-	/* Disable Receiver */	
+	/* Disable Receiver */
 	up->cached_mode &= ~SAB82532_MODE_RAC;
 	writeb(up->cached_mode, &up->regs->rw.mode);
 
@@ -622,7 +622,7 @@ static void sunsab_shutdown(struct uart_port *port)
 	 * speed the chip was configured for when the port was open).
 	 */
 #if 0
-	/* Power Down */	
+	/* Power Down */
 	tmp = readb(&up->regs->rw.ccr0);
 	tmp &= ~SAB82532_CCR0_PU;
 	writeb(tmp, &up->regs->rw.ccr0);
@@ -649,7 +649,7 @@ static void calc_ebrg(int baud, int *n_ret, int *m_ret)
 		*m_ret = 0;
 		return;
 	}
-     
+
 	/*
 	 * We scale numbers by 10 so that we get better accuracy
 	 * without having to use floating point.  Here we increment m
@@ -788,7 +788,7 @@ static const char *sunsab_type(struct uart_port *port)
 {
 	struct uart_sunsab_port *up = (void *)port;
 	static char buf[36];
-	
+
 	sprintf(buf, "SAB82532 %s", sab82532_version[up->type]);
 	return buf;
 }
@@ -933,7 +933,7 @@ static int sunsab_console_setup(struct console *con, char *options)
 	sunsab_set_mctrl(&up->port, TIOCM_DTR | TIOCM_RTS);
 
 	uart_port_unlock_irqrestore(&up->port, flags);
-	
+
 	return 0;
 }
 
-- 
GitLab


From 3837a0379533aabb9e4483677077479f7c6aa910 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Mon, 30 Oct 2023 17:14:47 -0400
Subject: [PATCH 0392/4076] serial: sc16is7xx: improve regmap debugfs by using
 one regmap per port

With this current driver regmap implementation, it is hard to make sense
of the register addresses displayed using the regmap debugfs interface,
because they do not correspond to the actual register addresses documented
in the datasheet. For example, register 1 is displayed as registers 04 thru
07:

$ cat /sys/kernel/debug/regmap/spi0.0/registers
  04: 10 -> Port 0, register offset 1
  05: 10 -> Port 1, register offset 1
  06: 00 -> Port 2, register offset 1 -> invalid
  07: 00 -> port 3, register offset 1 -> invalid
  ...

The reason is that bits 0 and 1 of the register address correspond to the
channel (port) bits, so the register address itself starts at bit 2, and we
must 'mentally' shift each register address by 2 bits to get its real
address/offset.

Also, only channels 0 and 1 are supported by the chip, so channel mask
combinations of 10b and 11b are invalid, and the display of these
registers is useless.

This patch adds a separate regmap configuration for each port, similar to
what is done in the max310x driver, so that register addresses displayed
match the register addresses in the chip datasheet. Also, each port now has
its own debugfs entry.

Example with new regmap implementation:

$ cat /sys/kernel/debug/regmap/spi0.0-port0/registers
1: 10
2: 01
3: 00
...

$ cat /sys/kernel/debug/regmap/spi0.0-port1/registers
1: 10
2: 01
3: 00

As an added bonus, this also simplifies some operations (read/write/modify)
because it is no longer necessary to manually shift register addresses.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231030211447.974779-1-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 143 +++++++++++++++++++--------------
 1 file changed, 81 insertions(+), 62 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index db2bb1c0d36c2..4c69c30fbac12 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -300,8 +300,8 @@
 
 
 /* Misc definitions */
+#define SC16IS7XX_SPI_READ_BIT		BIT(7)
 #define SC16IS7XX_FIFO_SIZE		(64)
-#define SC16IS7XX_REG_SHIFT		2
 #define SC16IS7XX_GPIOS_PER_BANK	4
 
 struct sc16is7xx_devtype {
@@ -323,6 +323,7 @@ struct sc16is7xx_one_config {
 struct sc16is7xx_one {
 	struct uart_port		port;
 	u8				line;
+	struct regmap			*regmap;
 	struct kthread_work		tx_work;
 	struct kthread_work		reg_work;
 	struct kthread_delayed_work	ms_work;
@@ -360,48 +361,37 @@ static void sc16is7xx_stop_tx(struct uart_port *port);
 
 #define to_sc16is7xx_one(p,e)	((container_of((p), struct sc16is7xx_one, e)))
 
-static int sc16is7xx_line(struct uart_port *port)
-{
-	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-
-	return one->line;
-}
-
 static u8 sc16is7xx_port_read(struct uart_port *port, u8 reg)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 	unsigned int val = 0;
-	const u8 line = sc16is7xx_line(port);
 
-	regmap_read(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line, &val);
+	regmap_read(one->regmap, reg, &val);
 
 	return val;
 }
 
 static void sc16is7xx_port_write(struct uart_port *port, u8 reg, u8 val)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	const u8 line = sc16is7xx_line(port);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	regmap_write(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line, val);
+	regmap_write(one->regmap, reg, val);
 }
 
 static void sc16is7xx_fifo_read(struct uart_port *port, unsigned int rxlen)
 {
 	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	const u8 line = sc16is7xx_line(port);
-	u8 addr = (SC16IS7XX_RHR_REG << SC16IS7XX_REG_SHIFT) | line;
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	regcache_cache_bypass(s->regmap, true);
-	regmap_raw_read(s->regmap, addr, s->buf, rxlen);
-	regcache_cache_bypass(s->regmap, false);
+	regcache_cache_bypass(one->regmap, true);
+	regmap_raw_read(one->regmap, SC16IS7XX_RHR_REG, s->buf, rxlen);
+	regcache_cache_bypass(one->regmap, false);
 }
 
 static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
 {
 	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	const u8 line = sc16is7xx_line(port);
-	u8 addr = (SC16IS7XX_THR_REG << SC16IS7XX_REG_SHIFT) | line;
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
 	/*
 	 * Don't send zero-length data, at least on SPI it confuses the chip
@@ -410,19 +400,17 @@ static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
 	if (unlikely(!to_send))
 		return;
 
-	regcache_cache_bypass(s->regmap, true);
-	regmap_raw_write(s->regmap, addr, s->buf, to_send);
-	regcache_cache_bypass(s->regmap, false);
+	regcache_cache_bypass(one->regmap, true);
+	regmap_raw_write(one->regmap, SC16IS7XX_THR_REG, s->buf, to_send);
+	regcache_cache_bypass(one->regmap, false);
 }
 
 static void sc16is7xx_port_update(struct uart_port *port, u8 reg,
 				  u8 mask, u8 val)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	const u8 line = sc16is7xx_line(port);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	regmap_update_bits(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line,
-			   mask, val);
+	regmap_update_bits(one->regmap, reg, mask, val);
 }
 
 static int sc16is7xx_alloc_line(void)
@@ -477,7 +465,7 @@ static const struct sc16is7xx_devtype sc16is762_devtype = {
 
 static bool sc16is7xx_regmap_volatile(struct device *dev, unsigned int reg)
 {
-	switch (reg >> SC16IS7XX_REG_SHIFT) {
+	switch (reg) {
 	case SC16IS7XX_RHR_REG:
 	case SC16IS7XX_IIR_REG:
 	case SC16IS7XX_LSR_REG:
@@ -496,7 +484,7 @@ static bool sc16is7xx_regmap_volatile(struct device *dev, unsigned int reg)
 
 static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg)
 {
-	switch (reg >> SC16IS7XX_REG_SHIFT) {
+	switch (reg) {
 	case SC16IS7XX_RHR_REG:
 		return true;
 	default:
@@ -509,6 +497,7 @@ static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg)
 static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 {
 	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 	u8 lcr;
 	u8 prescaler = 0;
 	unsigned long clk = port->uartclk, div = clk / 16 / baud;
@@ -540,12 +529,12 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 			     SC16IS7XX_LCR_CONF_MODE_B);
 
 	/* Enable enhanced features */
-	regcache_cache_bypass(s->regmap, true);
+	regcache_cache_bypass(one->regmap, true);
 	sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
 			      SC16IS7XX_EFR_ENABLE_BIT,
 			      SC16IS7XX_EFR_ENABLE_BIT);
 
-	regcache_cache_bypass(s->regmap, false);
+	regcache_cache_bypass(one->regmap, false);
 
 	/* Put LCR back to the normal mode */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
@@ -561,10 +550,10 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 			     SC16IS7XX_LCR_CONF_MODE_A);
 
 	/* Write the new divisor */
-	regcache_cache_bypass(s->regmap, true);
+	regcache_cache_bypass(one->regmap, true);
 	sc16is7xx_port_write(port, SC16IS7XX_DLH_REG, div / 256);
 	sc16is7xx_port_write(port, SC16IS7XX_DLL_REG, div % 256);
-	regcache_cache_bypass(s->regmap, false);
+	regcache_cache_bypass(one->regmap, false);
 
 	/* Put LCR back to the normal mode */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
@@ -1078,7 +1067,7 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 			     SC16IS7XX_LCR_CONF_MODE_B);
 
 	/* Configure flow control */
-	regcache_cache_bypass(s->regmap, true);
+	regcache_cache_bypass(one->regmap, true);
 	sc16is7xx_port_write(port, SC16IS7XX_XON1_REG, termios->c_cc[VSTART]);
 	sc16is7xx_port_write(port, SC16IS7XX_XOFF1_REG, termios->c_cc[VSTOP]);
 
@@ -1097,7 +1086,7 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 			      SC16IS7XX_EFR_REG,
 			      SC16IS7XX_EFR_FLOWCTRL_BITS,
 			      flow);
-	regcache_cache_bypass(s->regmap, false);
+	regcache_cache_bypass(one->regmap, false);
 
 	/* Update LCR register */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
@@ -1148,7 +1137,6 @@ static int sc16is7xx_config_rs485(struct uart_port *port, struct ktermios *termi
 static int sc16is7xx_startup(struct uart_port *port)
 {
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	unsigned int val;
 	unsigned long flags;
 
@@ -1165,7 +1153,7 @@ static int sc16is7xx_startup(struct uart_port *port)
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
 			     SC16IS7XX_LCR_CONF_MODE_B);
 
-	regcache_cache_bypass(s->regmap, true);
+	regcache_cache_bypass(one->regmap, true);
 
 	/* Enable write access to enhanced features and internal clock div */
 	sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
@@ -1183,7 +1171,7 @@ static int sc16is7xx_startup(struct uart_port *port)
 			     SC16IS7XX_TCR_RX_RESUME(24) |
 			     SC16IS7XX_TCR_RX_HALT(48));
 
-	regcache_cache_bypass(s->regmap, false);
+	regcache_cache_bypass(one->regmap, false);
 
 	/* Now, initialize the UART */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_WORD_LEN_8);
@@ -1464,7 +1452,7 @@ static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s)
 	if (s->mctrl_mask)
 		regmap_update_bits(
 			s->regmap,
-			SC16IS7XX_IOCONTROL_REG << SC16IS7XX_REG_SHIFT,
+			SC16IS7XX_IOCONTROL_REG,
 			SC16IS7XX_IOCONTROL_MODEM_A_BIT |
 			SC16IS7XX_IOCONTROL_MODEM_B_BIT, s->mctrl_mask);
 
@@ -1479,7 +1467,7 @@ static const struct serial_rs485 sc16is7xx_rs485_supported = {
 
 static int sc16is7xx_probe(struct device *dev,
 			   const struct sc16is7xx_devtype *devtype,
-			   struct regmap *regmap, int irq)
+			   struct regmap *regmaps[], int irq)
 {
 	unsigned long freq = 0, *pfreq = dev_get_platdata(dev);
 	unsigned int val;
@@ -1487,16 +1475,16 @@ static int sc16is7xx_probe(struct device *dev,
 	int i, ret;
 	struct sc16is7xx_port *s;
 
-	if (IS_ERR(regmap))
-		return PTR_ERR(regmap);
+	for (i = 0; i < devtype->nr_uart; i++)
+		if (IS_ERR(regmaps[i]))
+			return PTR_ERR(regmaps[i]);
 
 	/*
 	 * This device does not have an identification register that would
 	 * tell us if we are really connected to the correct device.
 	 * The best we can do is to check if communication is at all possible.
 	 */
-	ret = regmap_read(regmap,
-			  SC16IS7XX_LSR_REG << SC16IS7XX_REG_SHIFT, &val);
+	ret = regmap_read(regmaps[0], SC16IS7XX_LSR_REG, &val);
 	if (ret < 0)
 		return -EPROBE_DEFER;
 
@@ -1530,7 +1518,7 @@ static int sc16is7xx_probe(struct device *dev,
 			return -EINVAL;
 	}
 
-	s->regmap = regmap;
+	s->regmap = regmaps[0];
 	s->devtype = devtype;
 	dev_set_drvdata(dev, s);
 	mutex_init(&s->efr_lock);
@@ -1545,8 +1533,8 @@ static int sc16is7xx_probe(struct device *dev,
 	sched_set_fifo(s->kworker_task);
 
 	/* reset device, purging any pending irq / data */
-	regmap_write(s->regmap, SC16IS7XX_IOCONTROL_REG << SC16IS7XX_REG_SHIFT,
-			SC16IS7XX_IOCONTROL_SRESET_BIT);
+	regmap_write(s->regmap, SC16IS7XX_IOCONTROL_REG,
+		     SC16IS7XX_IOCONTROL_SRESET_BIT);
 
 	for (i = 0; i < devtype->nr_uart; ++i) {
 		s->p[i].line		= i;
@@ -1570,6 +1558,7 @@ static int sc16is7xx_probe(struct device *dev,
 		s->p[i].port.ops	= &sc16is7xx_ops;
 		s->p[i].old_mctrl	= 0;
 		s->p[i].port.line	= sc16is7xx_alloc_line();
+		s->p[i].regmap		= regmaps[i];
 
 		if (s->p[i].port.line >= SC16IS7XX_MAX_DEVS) {
 			ret = -ENOMEM;
@@ -1598,13 +1587,13 @@ static int sc16is7xx_probe(struct device *dev,
 		sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_LCR_REG,
 				     SC16IS7XX_LCR_CONF_MODE_B);
 
-		regcache_cache_bypass(s->regmap, true);
+		regcache_cache_bypass(regmaps[i], true);
 
 		/* Enable write access to enhanced features */
 		sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_EFR_REG,
 				     SC16IS7XX_EFR_ENABLE_BIT);
 
-		regcache_cache_bypass(s->regmap, false);
+		regcache_cache_bypass(regmaps[i], false);
 
 		/* Restore access to general registers */
 		sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_LCR_REG, 0x00);
@@ -1698,19 +1687,36 @@ static const struct of_device_id __maybe_unused sc16is7xx_dt_ids[] = {
 MODULE_DEVICE_TABLE(of, sc16is7xx_dt_ids);
 
 static struct regmap_config regcfg = {
-	.reg_bits = 7,
-	.pad_bits = 1,
+	.reg_bits = 5,
+	.pad_bits = 3,
 	.val_bits = 8,
 	.cache_type = REGCACHE_RBTREE,
 	.volatile_reg = sc16is7xx_regmap_volatile,
 	.precious_reg = sc16is7xx_regmap_precious,
+	.max_register = SC16IS7XX_EFCR_REG,
 };
 
+static const char *sc16is7xx_regmap_name(unsigned int port_id)
+{
+	static char buf[6];
+
+	snprintf(buf, sizeof(buf), "port%d", port_id);
+
+	return buf;
+}
+
+static unsigned int sc16is7xx_regmap_port_mask(unsigned int port_id)
+{
+	/* CH1,CH0 are at bits 2:1. */
+	return port_id << 1;
+}
+
 #ifdef CONFIG_SERIAL_SC16IS7XX_SPI
 static int sc16is7xx_spi_probe(struct spi_device *spi)
 {
 	const struct sc16is7xx_devtype *devtype;
-	struct regmap *regmap;
+	struct regmap *regmaps[2];
+	unsigned int i;
 	int ret;
 
 	/* Setup SPI bus */
@@ -1732,11 +1738,20 @@ static int sc16is7xx_spi_probe(struct spi_device *spi)
 		devtype = (struct sc16is7xx_devtype *)id_entry->driver_data;
 	}
 
-	regcfg.max_register = (0xf << SC16IS7XX_REG_SHIFT) |
-			      (devtype->nr_uart - 1);
-	regmap = devm_regmap_init_spi(spi, &regcfg);
+	for (i = 0; i < devtype->nr_uart; i++) {
+		regcfg.name = sc16is7xx_regmap_name(i);
+		/*
+		 * If read_flag_mask is 0, the regmap code sets it to a default
+		 * of 0x80. Since we specify our own mask, we must add the READ
+		 * bit ourselves:
+		 */
+		regcfg.read_flag_mask = sc16is7xx_regmap_port_mask(i) |
+			SC16IS7XX_SPI_READ_BIT;
+		regcfg.write_flag_mask = sc16is7xx_regmap_port_mask(i);
+		regmaps[i] = devm_regmap_init_spi(spi, &regcfg);
+	}
 
-	return sc16is7xx_probe(&spi->dev, devtype, regmap, spi->irq);
+	return sc16is7xx_probe(&spi->dev, devtype, regmaps, spi->irq);
 }
 
 static void sc16is7xx_spi_remove(struct spi_device *spi)
@@ -1775,7 +1790,8 @@ static int sc16is7xx_i2c_probe(struct i2c_client *i2c)
 {
 	const struct i2c_device_id *id = i2c_client_get_device_id(i2c);
 	const struct sc16is7xx_devtype *devtype;
-	struct regmap *regmap;
+	struct regmap *regmaps[2];
+	unsigned int i;
 
 	if (i2c->dev.of_node) {
 		devtype = device_get_match_data(&i2c->dev);
@@ -1785,11 +1801,14 @@ static int sc16is7xx_i2c_probe(struct i2c_client *i2c)
 		devtype = (struct sc16is7xx_devtype *)id->driver_data;
 	}
 
-	regcfg.max_register = (0xf << SC16IS7XX_REG_SHIFT) |
-			      (devtype->nr_uart - 1);
-	regmap = devm_regmap_init_i2c(i2c, &regcfg);
+	for (i = 0; i < devtype->nr_uart; i++) {
+		regcfg.name = sc16is7xx_regmap_name(i);
+		regcfg.read_flag_mask = sc16is7xx_regmap_port_mask(i);
+		regcfg.write_flag_mask = sc16is7xx_regmap_port_mask(i);
+		regmaps[i] = devm_regmap_init_i2c(i2c, &regcfg);
+	}
 
-	return sc16is7xx_probe(&i2c->dev, devtype, regmap, i2c->irq);
+	return sc16is7xx_probe(&i2c->dev, devtype, regmaps, i2c->irq);
 }
 
 static void sc16is7xx_i2c_remove(struct i2c_client *client)
-- 
GitLab


From ec9fc2cffa8d2ff150918baadb07b115c544e8ea Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 19 Nov 2023 16:55:15 +0100
Subject: [PATCH 0393/4076] serial: atmel: convert not to use
 dma_request_slave_channel()

dma_request_slave_channel() is deprecated. dma_request_chan() should
be used directly instead.

Switch to the preferred function and update the error handling accordingly.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/f2e9790d8b49aeba8b43ce018d30a35b837ac1eb.1700409299.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/atmel_serial.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 6792680690bd1..85667f7095154 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1013,14 +1013,18 @@ static int atmel_prepare_tx_dma(struct uart_port *port)
 	struct device *mfd_dev = port->dev->parent;
 	dma_cap_mask_t		mask;
 	struct dma_slave_config config;
+	struct dma_chan *chan;
 	int ret, nent;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
-	atmel_port->chan_tx = dma_request_slave_channel(mfd_dev, "tx");
-	if (atmel_port->chan_tx == NULL)
+	chan = dma_request_chan(mfd_dev, "tx");
+	if (IS_ERR(chan)) {
+		atmel_port->chan_tx = NULL;
 		goto chan_err;
+	}
+	atmel_port->chan_tx = chan;
 	dev_info(port->dev, "using %s for tx DMA transfers\n",
 		dma_chan_name(atmel_port->chan_tx));
 
@@ -1188,6 +1192,7 @@ static int atmel_prepare_rx_dma(struct uart_port *port)
 	dma_cap_mask_t		mask;
 	struct dma_slave_config config;
 	struct circ_buf		*ring;
+	struct dma_chan *chan;
 	int ret, nent;
 
 	ring = &atmel_port->rx_ring;
@@ -1195,9 +1200,12 @@ static int atmel_prepare_rx_dma(struct uart_port *port)
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_CYCLIC, mask);
 
-	atmel_port->chan_rx = dma_request_slave_channel(mfd_dev, "rx");
-	if (atmel_port->chan_rx == NULL)
+	chan = dma_request_chan(mfd_dev, "rx");
+	if (IS_ERR(chan)) {
+		atmel_port->chan_rx = NULL;
 		goto chan_err;
+	}
+	atmel_port->chan_rx = chan;
 	dev_info(port->dev, "using %s for rx DMA transfers\n",
 		dma_chan_name(atmel_port->chan_rx));
 
-- 
GitLab


From 5b05206b05ba98bce4c8f15200b407569fae270e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 19 Nov 2023 17:12:48 +0100
Subject: [PATCH 0394/4076] serial: imx: convert not to use
 dma_request_slave_channel()

dma_request_slave_channel() is deprecated. dma_request_chan() should
be used directly instead.

Switch to the preferred function and update the error handling accordingly.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/a46b493c6b5cfa09417e3e138e304fd01b61e748.1700410346.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 3ea9466ee5ef0..52dd8a6b87603 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -1336,15 +1336,18 @@ static int imx_uart_dma_init(struct imx_port *sport)
 {
 	struct dma_slave_config slave_config = {};
 	struct device *dev = sport->port.dev;
+	struct dma_chan *chan;
 	int ret;
 
 	/* Prepare for RX : */
-	sport->dma_chan_rx = dma_request_slave_channel(dev, "rx");
-	if (!sport->dma_chan_rx) {
+	chan = dma_request_chan(dev, "rx");
+	if (IS_ERR(chan)) {
 		dev_dbg(dev, "cannot get the DMA channel.\n");
-		ret = -EINVAL;
+		sport->dma_chan_rx = NULL;
+		ret = PTR_ERR(chan);
 		goto err;
 	}
+	sport->dma_chan_rx = chan;
 
 	slave_config.direction = DMA_DEV_TO_MEM;
 	slave_config.src_addr = sport->port.mapbase + URXD0;
@@ -1366,12 +1369,14 @@ static int imx_uart_dma_init(struct imx_port *sport)
 	sport->rx_ring.buf = sport->rx_buf;
 
 	/* Prepare for TX : */
-	sport->dma_chan_tx = dma_request_slave_channel(dev, "tx");
-	if (!sport->dma_chan_tx) {
+	chan = dma_request_chan(dev, "tx");
+	if (IS_ERR(chan)) {
 		dev_err(dev, "cannot get the TX DMA channel!\n");
-		ret = -EINVAL;
+		sport->dma_chan_tx = NULL;
+		ret = PTR_ERR(chan);
 		goto err;
 	}
+	sport->dma_chan_tx = chan;
 
 	slave_config.direction = DMA_MEM_TO_DEV;
 	slave_config.dst_addr = sport->port.mapbase + URTX0;
-- 
GitLab


From e6cc39486ae74271673742fe86ee6fb8d1eba16c Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 19 Nov 2023 15:52:39 +0100
Subject: [PATCH 0395/4076] serial: amba-pl011: convert not to use
 dma_request_slave_channel()

dma_request_slave_channel() is deprecated. dma_request_chan() should
be used directly instead.

Switch to the preferred function and update the error handling accordingly.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/6f76e22f77d776d6c1f176d56e7ee341314d8554.1700405529.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 374b4254e39be..bb475c1642fce 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -444,9 +444,9 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 		 dma_chan_name(uap->dmatx.chan));
 
 	/* Optionally make use of an RX channel as well */
-	chan = dma_request_slave_channel(dev, "rx");
+	chan = dma_request_chan(dev, "rx");
 
-	if (!chan && plat && plat->dma_rx_param) {
+	if (IS_ERR(chan) && plat && plat->dma_rx_param) {
 		chan = dma_request_channel(mask, plat->dma_filter, plat->dma_rx_param);
 
 		if (!chan) {
@@ -455,7 +455,7 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 		}
 	}
 
-	if (chan) {
+	if (!IS_ERR(chan)) {
 		struct dma_slave_config rx_conf = {
 			.src_addr = uap->port.mapbase +
 				pl011_reg_to_offset(uap, REG_DR),
-- 
GitLab


From b49c36e4b2ff4d5c8b8a0495f660707ae7dfdda9 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 19 Nov 2023 17:22:20 +0100
Subject: [PATCH 0396/4076] serial: mxs-auart: convert not to use
 dma_request_slave_channel()

dma_request_slave_channel() is deprecated. dma_request_chan() should
be used directly instead.

Switch to the preferred function and update the error handling accordingly.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/94812f7063e4db5590254ec45fe9bb3c6569509e.1700410918.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/mxs-auart.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 2be9546e0e153..3ec725555bcc1 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -904,21 +904,27 @@ static void mxs_auart_dma_exit(struct mxs_auart_port *s)
 
 static int mxs_auart_dma_init(struct mxs_auart_port *s)
 {
+	struct dma_chan *chan;
+
 	if (auart_dma_enabled(s))
 		return 0;
 
 	/* init for RX */
-	s->rx_dma_chan = dma_request_slave_channel(s->dev, "rx");
-	if (!s->rx_dma_chan)
+	chan = dma_request_chan(s->dev, "rx");
+	if (IS_ERR(chan))
 		goto err_out;
+	s->rx_dma_chan = chan;
+
 	s->rx_dma_buf = kzalloc(UART_XMIT_SIZE, GFP_KERNEL | GFP_DMA);
 	if (!s->rx_dma_buf)
 		goto err_out;
 
 	/* init for TX */
-	s->tx_dma_chan = dma_request_slave_channel(s->dev, "tx");
-	if (!s->tx_dma_chan)
+	chan = dma_request_chan(s->dev, "tx");
+	if (IS_ERR(chan))
 		goto err_out;
+	s->tx_dma_chan = chan;
+
 	s->tx_dma_buf = kzalloc(UART_XMIT_SIZE, GFP_KERNEL | GFP_DMA);
 	if (!s->tx_dma_buf)
 		goto err_out;
-- 
GitLab


From f1c7f92ee9ec38aa5e6526257a8a9f1fffc52511 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 19 Nov 2023 19:00:58 +0100
Subject: [PATCH 0397/4076] serial: sh-sci: convert not to use
 dma_request_slave_channel()

dma_request_slave_channel() is deprecated. dma_request_chan() should
be used directly instead.

Switch to the preferred function and update the error handling accordingly.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/d6773b9bd88dbbbea06bc6d5cd59aa117b1ee2ee.1700416841.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sh-sci.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 745023001510a..a85e7b9a2e492 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1558,10 +1558,9 @@ static struct dma_chan *sci_request_dma_chan(struct uart_port *port,
 	struct dma_slave_config cfg;
 	int ret;
 
-	chan = dma_request_slave_channel(port->dev,
-					 dir == DMA_MEM_TO_DEV ? "tx" : "rx");
-	if (!chan) {
-		dev_dbg(port->dev, "dma_request_slave_channel failed\n");
+	chan = dma_request_chan(port->dev, dir == DMA_MEM_TO_DEV ? "tx" : "rx");
+	if (IS_ERR(chan)) {
+		dev_dbg(port->dev, "dma_request_chan failed\n");
 		return NULL;
 	}
 
-- 
GitLab


From abdea7209becf633d96a71ea3b99062ae7012229 Mon Sep 17 00:00:00 2001
From: Chester Lin <clin@suse.com>
Date: Thu, 16 Nov 2023 07:57:32 +0800
Subject: [PATCH 0398/4076] dt-bindings: serial: fsl-linflexuart: change the
 maintainer email address

I am leaving SUSE so the current email address <clin@suse.com> will be
disabled soon. <chester62515@gmail.com> will be my new address for handling
emails, patches and pull requests from upstream and communities.

Cc: Chester Lin <chester62515@gmail.com>
Cc: NXP S32 Linux Team <s32@nxp.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org>
Cc: Conor Dooley <conor+dt@kernel.org>
Signed-off-by: Chester Lin <clin@suse.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231115235732.13633-1-clin@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/serial/fsl,s32-linflexuart.yaml         | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/serial/fsl,s32-linflexuart.yaml b/Documentation/devicetree/bindings/serial/fsl,s32-linflexuart.yaml
index 920539926d7e2..7a105551fa6a8 100644
--- a/Documentation/devicetree/bindings/serial/fsl,s32-linflexuart.yaml
+++ b/Documentation/devicetree/bindings/serial/fsl,s32-linflexuart.yaml
@@ -13,7 +13,7 @@ description: |
   https://www.nxp.com/webapp/Download?colCode=S32V234RM.
 
 maintainers:
-  - Chester Lin <clin@suse.com>
+  - Chester Lin <chester62515@gmail.com>
 
 allOf:
   - $ref: serial.yaml#
-- 
GitLab


From c062bcab592475697d71806edf8cb936b27d4f66 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Thu, 23 Nov 2023 14:32:13 +0100
Subject: [PATCH 0399/4076] interconnect: qcom: introduce RPMh Network-On-Chip
 Interconnect on SM8650 SoC

Add RPMh Network-On-Chip Interconnect support for the SM8650 platform.

Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231123-topic-sm8650-upstream-interconnect-v2-2-7e050874f59b@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/Kconfig  |    9 +
 drivers/interconnect/qcom/Makefile |    2 +
 drivers/interconnect/qcom/sm8650.c | 1674 ++++++++++++++++++++++++++++
 drivers/interconnect/qcom/sm8650.h |  143 +++
 4 files changed, 1828 insertions(+)
 create mode 100644 drivers/interconnect/qcom/sm8650.c
 create mode 100644 drivers/interconnect/qcom/sm8650.h

diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig
index 62b516d38d03f..4c12222e0e8f0 100644
--- a/drivers/interconnect/qcom/Kconfig
+++ b/drivers/interconnect/qcom/Kconfig
@@ -245,5 +245,14 @@ config INTERCONNECT_QCOM_SM8550
 	  This is a driver for the Qualcomm Network-on-Chip on SM8550-based
 	  platforms.
 
+config INTERCONNECT_QCOM_SM8650
+	tristate "Qualcomm SM8650 interconnect driver"
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
+	select INTERCONNECT_QCOM_RPMH
+	select INTERCONNECT_QCOM_BCM_VOTER
+	help
+	  This is a driver for the Qualcomm Network-on-Chip on SM8650-based
+	  platforms.
+
 config INTERCONNECT_QCOM_SMD_RPM
 	tristate
diff --git a/drivers/interconnect/qcom/Makefile b/drivers/interconnect/qcom/Makefile
index c5320e293960a..41e5c5000a3c8 100644
--- a/drivers/interconnect/qcom/Makefile
+++ b/drivers/interconnect/qcom/Makefile
@@ -30,6 +30,7 @@ qnoc-sm8250-objs			:= sm8250.o
 qnoc-sm8350-objs			:= sm8350.o
 qnoc-sm8450-objs			:= sm8450.o
 qnoc-sm8550-objs			:= sm8550.o
+qnoc-sm8650-objs			:= sm8650.o
 icc-smd-rpm-objs			:= smd-rpm.o icc-rpm.o icc-rpm-clocks.o
 
 obj-$(CONFIG_INTERCONNECT_QCOM_BCM_VOTER) += icc-bcm-voter.o
@@ -59,4 +60,5 @@ obj-$(CONFIG_INTERCONNECT_QCOM_SM8250) += qnoc-sm8250.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8350) += qnoc-sm8350.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8450) += qnoc-sm8450.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8550) += qnoc-sm8550.o
+obj-$(CONFIG_INTERCONNECT_QCOM_SM8650) += qnoc-sm8650.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SMD_RPM) += icc-smd-rpm.o
diff --git a/drivers/interconnect/qcom/sm8650.c b/drivers/interconnect/qcom/sm8650.c
new file mode 100644
index 0000000000000..b83de54577b68
--- /dev/null
+++ b/drivers/interconnect/qcom/sm8650.c
@@ -0,0 +1,1674 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#include <linux/device.h>
+#include <linux/interconnect.h>
+#include <linux/interconnect-provider.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <dt-bindings/interconnect/qcom,sm8650-rpmh.h>
+
+#include "bcm-voter.h"
+#include "icc-common.h"
+#include "icc-rpmh.h"
+#include "sm8650.h"
+
+static struct qcom_icc_node qhm_qspi = {
+	.name = "qhm_qspi",
+	.id = SM8650_MASTER_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup1 = {
+	.name = "qhm_qup1",
+	.id = SM8650_MASTER_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_qup02 = {
+	.name = "qxm_qup02",
+	.id = SM8650_MASTER_QUP_3,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc4 = {
+	.name = "xm_sdc4",
+	.id = SM8650_MASTER_SDCC_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_ufs_mem = {
+	.name = "xm_ufs_mem",
+	.id = SM8650_MASTER_UFS_MEM,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_usb3_0 = {
+	.name = "xm_usb3_0",
+	.id = SM8650_MASTER_USB3_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qdss_bam = {
+	.name = "qhm_qdss_bam",
+	.id = SM8650_MASTER_QDSS_BAM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup2 = {
+	.name = "qhm_qup2",
+	.id = SM8650_MASTER_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_crypto = {
+	.name = "qxm_crypto",
+	.id = SM8650_MASTER_CRYPTO,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_ipa = {
+	.name = "qxm_ipa",
+	.id = SM8650_MASTER_IPA,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_sp = {
+	.name = "qxm_sp",
+	.id = SM8650_MASTER_SP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_0 = {
+	.name = "xm_qdss_etr_0",
+	.id = SM8650_MASTER_QDSS_ETR,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_1 = {
+	.name = "xm_qdss_etr_1",
+	.id = SM8650_MASTER_QDSS_ETR_1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc2 = {
+	.name = "xm_sdc2",
+	.id = SM8650_MASTER_SDCC_2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qup0_core_master = {
+	.name = "qup0_core_master",
+	.id = SM8650_MASTER_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_QUP_CORE_0 },
+};
+
+static struct qcom_icc_node qup1_core_master = {
+	.name = "qup1_core_master",
+	.id = SM8650_MASTER_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_QUP_CORE_1 },
+};
+
+static struct qcom_icc_node qup2_core_master = {
+	.name = "qup2_core_master",
+	.id = SM8650_MASTER_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_QUP_CORE_2 },
+};
+
+static struct qcom_icc_node qsm_cfg = {
+	.name = "qsm_cfg",
+	.id = SM8650_MASTER_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 46,
+	.links = { SM8650_SLAVE_AHB2PHY_SOUTH, SM8650_SLAVE_AHB2PHY_NORTH,
+		   SM8650_SLAVE_CAMERA_CFG, SM8650_SLAVE_CLK_CTL,
+		   SM8650_SLAVE_RBCPR_CX_CFG, SM8650_SLAVE_CPR_HMX,
+		   SM8650_SLAVE_RBCPR_MMCX_CFG, SM8650_SLAVE_RBCPR_MXA_CFG,
+		   SM8650_SLAVE_RBCPR_MXC_CFG, SM8650_SLAVE_CPR_NSPCX,
+		   SM8650_SLAVE_CRYPTO_0_CFG, SM8650_SLAVE_CX_RDPM,
+		   SM8650_SLAVE_DISPLAY_CFG, SM8650_SLAVE_GFX3D_CFG,
+		   SM8650_SLAVE_I2C, SM8650_SLAVE_I3C_IBI0_CFG,
+		   SM8650_SLAVE_I3C_IBI1_CFG, SM8650_SLAVE_IMEM_CFG,
+		   SM8650_SLAVE_CNOC_MSS, SM8650_SLAVE_MX_2_RDPM,
+		   SM8650_SLAVE_MX_RDPM, SM8650_SLAVE_PCIE_0_CFG,
+		   SM8650_SLAVE_PCIE_1_CFG, SM8650_SLAVE_PCIE_RSCC,
+		   SM8650_SLAVE_PDM, SM8650_SLAVE_PRNG,
+		   SM8650_SLAVE_QDSS_CFG, SM8650_SLAVE_QSPI_0,
+		   SM8650_SLAVE_QUP_3, SM8650_SLAVE_QUP_1,
+		   SM8650_SLAVE_QUP_2, SM8650_SLAVE_SDCC_2,
+		   SM8650_SLAVE_SDCC_4, SM8650_SLAVE_SPSS_CFG,
+		   SM8650_SLAVE_TCSR, SM8650_SLAVE_TLMM,
+		   SM8650_SLAVE_UFS_MEM_CFG, SM8650_SLAVE_USB3_0,
+		   SM8650_SLAVE_VENUS_CFG, SM8650_SLAVE_VSENSE_CTRL_CFG,
+		   SM8650_SLAVE_CNOC_MNOC_CFG, SM8650_SLAVE_NSP_QTB_CFG,
+		   SM8650_SLAVE_PCIE_ANOC_CFG, SM8650_SLAVE_SERVICE_CNOC_CFG,
+		   SM8650_SLAVE_QDSS_STM, SM8650_SLAVE_TCU },
+};
+
+static struct qcom_icc_node qnm_gemnoc_cnoc = {
+	.name = "qnm_gemnoc_cnoc",
+	.id = SM8650_MASTER_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 9,
+	.links = { SM8650_SLAVE_AOSS, SM8650_SLAVE_IPA_CFG,
+		   SM8650_SLAVE_IPC_ROUTER_CFG, SM8650_SLAVE_TME_CFG,
+		   SM8650_SLAVE_APPSS, SM8650_SLAVE_CNOC_CFG,
+		   SM8650_SLAVE_DDRSS_CFG, SM8650_SLAVE_IMEM,
+		   SM8650_SLAVE_SERVICE_CNOC },
+};
+
+static struct qcom_icc_node qnm_gemnoc_pcie = {
+	.name = "qnm_gemnoc_pcie",
+	.id = SM8650_MASTER_GEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_PCIE_0, SM8650_SLAVE_PCIE_1 },
+};
+
+static struct qcom_icc_node alm_gpu_tcu = {
+	.name = "alm_gpu_tcu",
+	.id = SM8650_MASTER_GPU_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_sys_tcu = {
+	.name = "alm_sys_tcu",
+	.id = SM8650_MASTER_SYS_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_ubwc_p_tcu = {
+	.name = "alm_ubwc_p_tcu",
+	.id = SM8650_MASTER_UBWC_P_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node chm_apps = {
+	.name = "chm_apps",
+	.id = SM8650_MASTER_APPSS_PROC,
+	.channels = 3,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_gpu = {
+	.name = "qnm_gpu",
+	.id = SM8650_MASTER_GFX3D,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpass_gemnoc = {
+	.name = "qnm_lpass_gemnoc",
+	.id = SM8650_MASTER_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_mdsp = {
+	.name = "qnm_mdsp",
+	.id = SM8650_MASTER_MSS_PROC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_mnoc_hf = {
+	.name = "qnm_mnoc_hf",
+	.id = SM8650_MASTER_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_mnoc_sf = {
+	.name = "qnm_mnoc_sf",
+	.id = SM8650_MASTER_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_nsp_gemnoc = {
+	.name = "qnm_nsp_gemnoc",
+	.id = SM8650_MASTER_COMPUTE_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_pcie = {
+	.name = "qnm_pcie",
+	.id = SM8650_MASTER_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 2,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_snoc_sf = {
+	.name = "qnm_snoc_sf",
+	.id = SM8650_MASTER_SNOC_SF_MEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8650_SLAVE_GEM_NOC_CNOC, SM8650_SLAVE_LLCC,
+		   SM8650_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_ubwc_p = {
+	.name = "qnm_ubwc_p",
+	.id = SM8650_MASTER_UBWC_P,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node xm_gic = {
+	.name = "xm_gic",
+	.id = SM8650_MASTER_GIC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpiaon_noc = {
+	.name = "qnm_lpiaon_noc",
+	.id = SM8650_MASTER_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_lpass_lpinoc = {
+	.name = "qnm_lpass_lpinoc",
+	.id = SM8650_MASTER_LPASS_LPINOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LPIAON_NOC_LPASS_AG_NOC },
+};
+
+static struct qcom_icc_node qxm_lpinoc_dsp_axim = {
+	.name = "qxm_lpinoc_dsp_axim",
+	.id = SM8650_MASTER_LPASS_PROC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_LPICX_NOC_LPIAON_NOC },
+};
+
+static struct qcom_icc_node llcc_mc = {
+	.name = "llcc_mc",
+	.id = SM8650_MASTER_LLCC,
+	.channels = 4,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_EBI1 },
+};
+
+static struct qcom_icc_node qnm_camnoc_hf = {
+	.name = "qnm_camnoc_hf",
+	.id = SM8650_MASTER_CAMNOC_HF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_icp = {
+	.name = "qnm_camnoc_icp",
+	.id = SM8650_MASTER_CAMNOC_ICP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_sf = {
+	.name = "qnm_camnoc_sf",
+	.id = SM8650_MASTER_CAMNOC_SF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_mdp = {
+	.name = "qnm_mdp",
+	.id = SM8650_MASTER_MDP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_vapss_hcp = {
+	.name = "qnm_vapss_hcp",
+	.id = SM8650_MASTER_CDSP_HCP,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video = {
+	.name = "qnm_video",
+	.id = SM8650_MASTER_VIDEO,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_cv_cpu = {
+	.name = "qnm_video_cv_cpu",
+	.id = SM8650_MASTER_VIDEO_CV_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_cvp = {
+	.name = "qnm_video_cvp",
+	.id = SM8650_MASTER_VIDEO_PROC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_v_cpu = {
+	.name = "qnm_video_v_cpu",
+	.id = SM8650_MASTER_VIDEO_V_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qsm_mnoc_cfg = {
+	.name = "qsm_mnoc_cfg",
+	.id = SM8650_MASTER_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_SERVICE_MNOC },
+};
+
+static struct qcom_icc_node qnm_nsp = {
+	.name = "qnm_nsp",
+	.id = SM8650_MASTER_CDSP_PROC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_CDSP_MEM_NOC },
+};
+
+static struct qcom_icc_node qsm_pcie_anoc_cfg = {
+	.name = "qsm_pcie_anoc_cfg",
+	.id = SM8650_MASTER_PCIE_ANOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_SERVICE_PCIE_ANOC },
+};
+
+static struct qcom_icc_node xm_pcie3_0 = {
+	.name = "xm_pcie3_0",
+	.id = SM8650_MASTER_PCIE_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node xm_pcie3_1 = {
+	.name = "xm_pcie3_1",
+	.id = SM8650_MASTER_PCIE_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_aggre1_noc = {
+	.name = "qnm_aggre1_noc",
+	.id = SM8650_MASTER_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_aggre2_noc = {
+	.name = "qnm_aggre2_noc",
+	.id = SM8650_MASTER_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qns_a1noc_snoc = {
+	.name = "qns_a1noc_snoc",
+	.id = SM8650_SLAVE_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qns_a2noc_snoc = {
+	.name = "qns_a2noc_snoc",
+	.id = SM8650_SLAVE_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qup0_core_slave = {
+	.name = "qup0_core_slave",
+	.id = SM8650_SLAVE_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup1_core_slave = {
+	.name = "qup1_core_slave",
+	.id = SM8650_SLAVE_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup2_core_slave = {
+	.name = "qup2_core_slave",
+	.id = SM8650_SLAVE_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy0 = {
+	.name = "qhs_ahb2phy0",
+	.id = SM8650_SLAVE_AHB2PHY_SOUTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy1 = {
+	.name = "qhs_ahb2phy1",
+	.id = SM8650_SLAVE_AHB2PHY_NORTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_camera_cfg = {
+	.name = "qhs_camera_cfg",
+	.id = SM8650_SLAVE_CAMERA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_clk_ctl = {
+	.name = "qhs_clk_ctl",
+	.id = SM8650_SLAVE_CLK_CTL,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_cx = {
+	.name = "qhs_cpr_cx",
+	.id = SM8650_SLAVE_RBCPR_CX_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_hmx = {
+	.name = "qhs_cpr_hmx",
+	.id = SM8650_SLAVE_CPR_HMX,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_mmcx = {
+	.name = "qhs_cpr_mmcx",
+	.id = SM8650_SLAVE_RBCPR_MMCX_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_mxa = {
+	.name = "qhs_cpr_mxa",
+	.id = SM8650_SLAVE_RBCPR_MXA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_mxc = {
+	.name = "qhs_cpr_mxc",
+	.id = SM8650_SLAVE_RBCPR_MXC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cpr_nspcx = {
+	.name = "qhs_cpr_nspcx",
+	.id = SM8650_SLAVE_CPR_NSPCX,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_crypto0_cfg = {
+	.name = "qhs_crypto0_cfg",
+	.id = SM8650_SLAVE_CRYPTO_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_cx_rdpm = {
+	.name = "qhs_cx_rdpm",
+	.id = SM8650_SLAVE_CX_RDPM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_display_cfg = {
+	.name = "qhs_display_cfg",
+	.id = SM8650_SLAVE_DISPLAY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_gpuss_cfg = {
+	.name = "qhs_gpuss_cfg",
+	.id = SM8650_SLAVE_GFX3D_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i2c = {
+	.name = "qhs_i2c",
+	.id = SM8650_SLAVE_I2C,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i3c_ibi0_cfg = {
+	.name = "qhs_i3c_ibi0_cfg",
+	.id = SM8650_SLAVE_I3C_IBI0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i3c_ibi1_cfg = {
+	.name = "qhs_i3c_ibi1_cfg",
+	.id = SM8650_SLAVE_I3C_IBI1_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_imem_cfg = {
+	.name = "qhs_imem_cfg",
+	.id = SM8650_SLAVE_IMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_mss_cfg = {
+	.name = "qhs_mss_cfg",
+	.id = SM8650_SLAVE_CNOC_MSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_mx_2_rdpm = {
+	.name = "qhs_mx_2_rdpm",
+	.id = SM8650_SLAVE_MX_2_RDPM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_mx_rdpm = {
+	.name = "qhs_mx_rdpm",
+	.id = SM8650_SLAVE_MX_RDPM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie0_cfg = {
+	.name = "qhs_pcie0_cfg",
+	.id = SM8650_SLAVE_PCIE_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie1_cfg = {
+	.name = "qhs_pcie1_cfg",
+	.id = SM8650_SLAVE_PCIE_1_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie_rscc = {
+	.name = "qhs_pcie_rscc",
+	.id = SM8650_SLAVE_PCIE_RSCC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pdm = {
+	.name = "qhs_pdm",
+	.id = SM8650_SLAVE_PDM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_prng = {
+	.name = "qhs_prng",
+	.id = SM8650_SLAVE_PRNG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qdss_cfg = {
+	.name = "qhs_qdss_cfg",
+	.id = SM8650_SLAVE_QDSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qspi = {
+	.name = "qhs_qspi",
+	.id = SM8650_SLAVE_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup02 = {
+	.name = "qhs_qup02",
+	.id = SM8650_SLAVE_QUP_3,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup1 = {
+	.name = "qhs_qup1",
+	.id = SM8650_SLAVE_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup2 = {
+	.name = "qhs_qup2",
+	.id = SM8650_SLAVE_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc2 = {
+	.name = "qhs_sdc2",
+	.id = SM8650_SLAVE_SDCC_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc4 = {
+	.name = "qhs_sdc4",
+	.id = SM8650_SLAVE_SDCC_4,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_spss_cfg = {
+	.name = "qhs_spss_cfg",
+	.id = SM8650_SLAVE_SPSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tcsr = {
+	.name = "qhs_tcsr",
+	.id = SM8650_SLAVE_TCSR,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tlmm = {
+	.name = "qhs_tlmm",
+	.id = SM8650_SLAVE_TLMM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ufs_mem_cfg = {
+	.name = "qhs_ufs_mem_cfg",
+	.id = SM8650_SLAVE_UFS_MEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_0 = {
+	.name = "qhs_usb3_0",
+	.id = SM8650_SLAVE_USB3_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_venus_cfg = {
+	.name = "qhs_venus_cfg",
+	.id = SM8650_SLAVE_VENUS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_vsense_ctrl_cfg = {
+	.name = "qhs_vsense_ctrl_cfg",
+	.id = SM8650_SLAVE_VSENSE_CTRL_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_mnoc_cfg = {
+	.name = "qss_mnoc_cfg",
+	.id = SM8650_SLAVE_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_MASTER_CNOC_MNOC_CFG },
+};
+
+static struct qcom_icc_node qss_nsp_qtb_cfg = {
+	.name = "qss_nsp_qtb_cfg",
+	.id = SM8650_SLAVE_NSP_QTB_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_pcie_anoc_cfg = {
+	.name = "qss_pcie_anoc_cfg",
+	.id = SM8650_SLAVE_PCIE_ANOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_MASTER_PCIE_ANOC_CFG },
+};
+
+static struct qcom_icc_node srvc_cnoc_cfg = {
+	.name = "srvc_cnoc_cfg",
+	.id = SM8650_SLAVE_SERVICE_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_qdss_stm = {
+	.name = "xs_qdss_stm",
+	.id = SM8650_SLAVE_QDSS_STM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_sys_tcu_cfg = {
+	.name = "xs_sys_tcu_cfg",
+	.id = SM8650_SLAVE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_aoss = {
+	.name = "qhs_aoss",
+	.id = SM8650_SLAVE_AOSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ipa = {
+	.name = "qhs_ipa",
+	.id = SM8650_SLAVE_IPA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ipc_router = {
+	.name = "qhs_ipc_router",
+	.id = SM8650_SLAVE_IPC_ROUTER_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tme_cfg = {
+	.name = "qhs_tme_cfg",
+	.id = SM8650_SLAVE_TME_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_apss = {
+	.name = "qss_apss",
+	.id = SM8650_SLAVE_APPSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_cfg = {
+	.name = "qss_cfg",
+	.id = SM8650_SLAVE_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8650_MASTER_CNOC_CFG },
+};
+
+static struct qcom_icc_node qss_ddrss_cfg = {
+	.name = "qss_ddrss_cfg",
+	.id = SM8650_SLAVE_DDRSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qxs_imem = {
+	.name = "qxs_imem",
+	.id = SM8650_SLAVE_IMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node srvc_cnoc_main = {
+	.name = "srvc_cnoc_main",
+	.id = SM8650_SLAVE_SERVICE_CNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_0 = {
+	.name = "xs_pcie_0",
+	.id = SM8650_SLAVE_PCIE_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_1 = {
+	.name = "xs_pcie_1",
+	.id = SM8650_SLAVE_PCIE_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_gem_noc_cnoc = {
+	.name = "qns_gem_noc_cnoc",
+	.id = SM8650_SLAVE_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_GEM_NOC_CNOC },
+};
+
+static struct qcom_icc_node qns_llcc = {
+	.name = "qns_llcc",
+	.id = SM8650_SLAVE_LLCC,
+	.channels = 4,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_LLCC },
+};
+
+static struct qcom_icc_node qns_pcie = {
+	.name = "qns_pcie",
+	.id = SM8650_SLAVE_MEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8650_MASTER_GEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qns_lpass_ag_noc_gemnoc = {
+	.name = "qns_lpass_ag_noc_gemnoc",
+	.id = SM8650_SLAVE_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qns_lpass_aggnoc = {
+	.name = "qns_lpass_aggnoc",
+	.id = SM8650_SLAVE_LPIAON_NOC_LPASS_AG_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_LPIAON_NOC },
+};
+
+static struct qcom_icc_node qns_lpi_aon_noc = {
+	.name = "qns_lpi_aon_noc",
+	.id = SM8650_SLAVE_LPICX_NOC_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_LPASS_LPINOC },
+};
+
+static struct qcom_icc_node ebi = {
+	.name = "ebi",
+	.id = SM8650_SLAVE_EBI1,
+	.channels = 4,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_mem_noc_hf = {
+	.name = "qns_mem_noc_hf",
+	.id = SM8650_SLAVE_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_MASTER_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qns_mem_noc_sf = {
+	.name = "qns_mem_noc_sf",
+	.id = SM8650_SLAVE_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_MASTER_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node srvc_mnoc = {
+	.name = "srvc_mnoc",
+	.id = SM8650_SLAVE_SERVICE_MNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_nsp_gemnoc = {
+	.name = "qns_nsp_gemnoc",
+	.id = SM8650_SLAVE_CDSP_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8650_MASTER_COMPUTE_NOC },
+};
+
+static struct qcom_icc_node qns_pcie_mem_noc = {
+	.name = "qns_pcie_mem_noc",
+	.id = SM8650_SLAVE_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node srvc_pcie_aggre_noc = {
+	.name = "srvc_pcie_aggre_noc",
+	.id = SM8650_SLAVE_SERVICE_PCIE_ANOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_gemnoc_sf = {
+	.name = "qns_gemnoc_sf",
+	.id = SM8650_SLAVE_SNOC_GEM_NOC_SF,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8650_MASTER_SNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_bcm bcm_acv = {
+	.name = "ACV",
+	.enable_mask = BIT(3),
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_ce0 = {
+	.name = "CE0",
+	.num_nodes = 1,
+	.nodes = { &qxm_crypto },
+};
+
+static struct qcom_icc_bcm bcm_cn0 = {
+	.name = "CN0",
+	.enable_mask = BIT(0),
+	.keepalive = true,
+	.num_nodes = 59,
+	.nodes = { &qsm_cfg, &qhs_ahb2phy0,
+		   &qhs_ahb2phy1, &qhs_camera_cfg,
+		   &qhs_clk_ctl, &qhs_cpr_cx,
+		   &qhs_cpr_hmx, &qhs_cpr_mmcx,
+		   &qhs_cpr_mxa, &qhs_cpr_mxc,
+		   &qhs_cpr_nspcx, &qhs_crypto0_cfg,
+		   &qhs_cx_rdpm, &qhs_display_cfg,
+		   &qhs_gpuss_cfg, &qhs_i2c,
+		   &qhs_i3c_ibi0_cfg, &qhs_i3c_ibi1_cfg,
+		   &qhs_imem_cfg, &qhs_mss_cfg,
+		   &qhs_mx_2_rdpm, &qhs_mx_rdpm,
+		   &qhs_pcie0_cfg, &qhs_pcie1_cfg,
+		   &qhs_pcie_rscc, &qhs_pdm,
+		   &qhs_prng, &qhs_qdss_cfg,
+		   &qhs_qspi, &qhs_qup02,
+		   &qhs_qup1, &qhs_qup2,
+		   &qhs_sdc2, &qhs_sdc4,
+		   &qhs_spss_cfg, &qhs_tcsr,
+		   &qhs_tlmm, &qhs_ufs_mem_cfg,
+		   &qhs_usb3_0, &qhs_venus_cfg,
+		   &qhs_vsense_ctrl_cfg, &qss_mnoc_cfg,
+		   &qss_nsp_qtb_cfg, &qss_pcie_anoc_cfg,
+		   &srvc_cnoc_cfg, &xs_qdss_stm,
+		   &xs_sys_tcu_cfg, &qnm_gemnoc_cnoc,
+		   &qnm_gemnoc_pcie, &qhs_aoss,
+		   &qhs_ipa, &qhs_ipc_router,
+		   &qhs_tme_cfg, &qss_apss,
+		   &qss_cfg, &qss_ddrss_cfg,
+		   &qxs_imem, &srvc_cnoc_main,
+		   &xs_pcie_0, &xs_pcie_1 },
+};
+
+static struct qcom_icc_bcm bcm_co0 = {
+	.name = "CO0",
+	.enable_mask = BIT(0),
+	.num_nodes = 2,
+	.nodes = { &qnm_nsp, &qns_nsp_gemnoc },
+};
+
+static struct qcom_icc_bcm bcm_lp0 = {
+	.name = "LP0",
+	.num_nodes = 2,
+	.nodes = { &qnm_lpass_lpinoc, &qns_lpass_aggnoc },
+};
+
+static struct qcom_icc_bcm bcm_mc0 = {
+	.name = "MC0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_mm0 = {
+	.name = "MM0",
+	.num_nodes = 1,
+	.nodes = { &qns_mem_noc_hf },
+};
+
+static struct qcom_icc_bcm bcm_mm1 = {
+	.name = "MM1",
+	.enable_mask = BIT(0),
+	.num_nodes = 8,
+	.nodes = { &qnm_camnoc_hf, &qnm_camnoc_icp,
+		   &qnm_camnoc_sf, &qnm_vapss_hcp,
+		   &qnm_video_cv_cpu, &qnm_video_cvp,
+		   &qnm_video_v_cpu, &qns_mem_noc_sf },
+};
+
+static struct qcom_icc_bcm bcm_qup0 = {
+	.name = "QUP0",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup0_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup1 = {
+	.name = "QUP1",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup1_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup2 = {
+	.name = "QUP2",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup2_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_sh0 = {
+	.name = "SH0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_llcc },
+};
+
+static struct qcom_icc_bcm bcm_sh1 = {
+	.name = "SH1",
+	.enable_mask = BIT(0),
+	.num_nodes = 15,
+	.nodes = { &alm_gpu_tcu, &alm_sys_tcu,
+		   &alm_ubwc_p_tcu, &chm_apps,
+		   &qnm_gpu, &qnm_mdsp,
+		   &qnm_mnoc_hf, &qnm_mnoc_sf,
+		   &qnm_nsp_gemnoc, &qnm_pcie,
+		   &qnm_snoc_sf, &qnm_ubwc_p,
+		   &xm_gic, &qns_gem_noc_cnoc,
+		   &qns_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sn0 = {
+	.name = "SN0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_gemnoc_sf },
+};
+
+static struct qcom_icc_bcm bcm_sn2 = {
+	.name = "SN2",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre1_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn3 = {
+	.name = "SN3",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre2_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn4 = {
+	.name = "SN4",
+	.num_nodes = 1,
+	.nodes = { &qns_pcie_mem_noc },
+};
+
+static struct qcom_icc_node * const aggre1_noc_nodes[] = {
+	[MASTER_QSPI_0] = &qhm_qspi,
+	[MASTER_QUP_1] = &qhm_qup1,
+	[MASTER_QUP_3] = &qxm_qup02,
+	[MASTER_SDCC_4] = &xm_sdc4,
+	[MASTER_UFS_MEM] = &xm_ufs_mem,
+	[MASTER_USB3_0] = &xm_usb3_0,
+	[SLAVE_A1NOC_SNOC] = &qns_a1noc_snoc,
+};
+
+static const struct qcom_icc_desc sm8650_aggre1_noc = {
+	.nodes = aggre1_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre1_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const aggre2_noc_bcms[] = {
+	&bcm_ce0,
+};
+
+static struct qcom_icc_node * const aggre2_noc_nodes[] = {
+	[MASTER_QDSS_BAM] = &qhm_qdss_bam,
+	[MASTER_QUP_2] = &qhm_qup2,
+	[MASTER_CRYPTO] = &qxm_crypto,
+	[MASTER_IPA] = &qxm_ipa,
+	[MASTER_SP] = &qxm_sp,
+	[MASTER_QDSS_ETR] = &xm_qdss_etr_0,
+	[MASTER_QDSS_ETR_1] = &xm_qdss_etr_1,
+	[MASTER_SDCC_2] = &xm_sdc2,
+	[SLAVE_A2NOC_SNOC] = &qns_a2noc_snoc,
+};
+
+static const struct qcom_icc_desc sm8650_aggre2_noc = {
+	.nodes = aggre2_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre2_noc_nodes),
+	.bcms = aggre2_noc_bcms,
+	.num_bcms = ARRAY_SIZE(aggre2_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const clk_virt_bcms[] = {
+	&bcm_qup0,
+	&bcm_qup1,
+	&bcm_qup2,
+};
+
+static struct qcom_icc_node * const clk_virt_nodes[] = {
+	[MASTER_QUP_CORE_0] = &qup0_core_master,
+	[MASTER_QUP_CORE_1] = &qup1_core_master,
+	[MASTER_QUP_CORE_2] = &qup2_core_master,
+	[SLAVE_QUP_CORE_0] = &qup0_core_slave,
+	[SLAVE_QUP_CORE_1] = &qup1_core_slave,
+	[SLAVE_QUP_CORE_2] = &qup2_core_slave,
+};
+
+static const struct qcom_icc_desc sm8650_clk_virt = {
+	.nodes = clk_virt_nodes,
+	.num_nodes = ARRAY_SIZE(clk_virt_nodes),
+	.bcms = clk_virt_bcms,
+	.num_bcms = ARRAY_SIZE(clk_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const config_noc_bcms[] = {
+	&bcm_cn0,
+};
+
+static struct qcom_icc_node * const config_noc_nodes[] = {
+	[MASTER_CNOC_CFG] = &qsm_cfg,
+	[SLAVE_AHB2PHY_SOUTH] = &qhs_ahb2phy0,
+	[SLAVE_AHB2PHY_NORTH] = &qhs_ahb2phy1,
+	[SLAVE_CAMERA_CFG] = &qhs_camera_cfg,
+	[SLAVE_CLK_CTL] = &qhs_clk_ctl,
+	[SLAVE_RBCPR_CX_CFG] = &qhs_cpr_cx,
+	[SLAVE_CPR_HMX] = &qhs_cpr_hmx,
+	[SLAVE_RBCPR_MMCX_CFG] = &qhs_cpr_mmcx,
+	[SLAVE_RBCPR_MXA_CFG] = &qhs_cpr_mxa,
+	[SLAVE_RBCPR_MXC_CFG] = &qhs_cpr_mxc,
+	[SLAVE_CPR_NSPCX] = &qhs_cpr_nspcx,
+	[SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg,
+	[SLAVE_CX_RDPM] = &qhs_cx_rdpm,
+	[SLAVE_DISPLAY_CFG] = &qhs_display_cfg,
+	[SLAVE_GFX3D_CFG] = &qhs_gpuss_cfg,
+	[SLAVE_I2C] = &qhs_i2c,
+	[SLAVE_I3C_IBI0_CFG] = &qhs_i3c_ibi0_cfg,
+	[SLAVE_I3C_IBI1_CFG] = &qhs_i3c_ibi1_cfg,
+	[SLAVE_IMEM_CFG] = &qhs_imem_cfg,
+	[SLAVE_CNOC_MSS] = &qhs_mss_cfg,
+	[SLAVE_MX_2_RDPM] = &qhs_mx_2_rdpm,
+	[SLAVE_MX_RDPM] = &qhs_mx_rdpm,
+	[SLAVE_PCIE_0_CFG] = &qhs_pcie0_cfg,
+	[SLAVE_PCIE_1_CFG] = &qhs_pcie1_cfg,
+	[SLAVE_PCIE_RSCC] = &qhs_pcie_rscc,
+	[SLAVE_PDM] = &qhs_pdm,
+	[SLAVE_PRNG] = &qhs_prng,
+	[SLAVE_QDSS_CFG] = &qhs_qdss_cfg,
+	[SLAVE_QSPI_0] = &qhs_qspi,
+	[SLAVE_QUP_3] = &qhs_qup02,
+	[SLAVE_QUP_1] = &qhs_qup1,
+	[SLAVE_QUP_2] = &qhs_qup2,
+	[SLAVE_SDCC_2] = &qhs_sdc2,
+	[SLAVE_SDCC_4] = &qhs_sdc4,
+	[SLAVE_SPSS_CFG] = &qhs_spss_cfg,
+	[SLAVE_TCSR] = &qhs_tcsr,
+	[SLAVE_TLMM] = &qhs_tlmm,
+	[SLAVE_UFS_MEM_CFG] = &qhs_ufs_mem_cfg,
+	[SLAVE_USB3_0] = &qhs_usb3_0,
+	[SLAVE_VENUS_CFG] = &qhs_venus_cfg,
+	[SLAVE_VSENSE_CTRL_CFG] = &qhs_vsense_ctrl_cfg,
+	[SLAVE_CNOC_MNOC_CFG] = &qss_mnoc_cfg,
+	[SLAVE_NSP_QTB_CFG] = &qss_nsp_qtb_cfg,
+	[SLAVE_PCIE_ANOC_CFG] = &qss_pcie_anoc_cfg,
+	[SLAVE_SERVICE_CNOC_CFG] = &srvc_cnoc_cfg,
+	[SLAVE_QDSS_STM] = &xs_qdss_stm,
+	[SLAVE_TCU] = &xs_sys_tcu_cfg,
+};
+
+static const struct qcom_icc_desc sm8650_config_noc = {
+	.nodes = config_noc_nodes,
+	.num_nodes = ARRAY_SIZE(config_noc_nodes),
+	.bcms = config_noc_bcms,
+	.num_bcms = ARRAY_SIZE(config_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const cnoc_main_bcms[] = {
+	&bcm_cn0,
+};
+
+static struct qcom_icc_node * const cnoc_main_nodes[] = {
+	[MASTER_GEM_NOC_CNOC] = &qnm_gemnoc_cnoc,
+	[MASTER_GEM_NOC_PCIE_SNOC] = &qnm_gemnoc_pcie,
+	[SLAVE_AOSS] = &qhs_aoss,
+	[SLAVE_IPA_CFG] = &qhs_ipa,
+	[SLAVE_IPC_ROUTER_CFG] = &qhs_ipc_router,
+	[SLAVE_TME_CFG] = &qhs_tme_cfg,
+	[SLAVE_APPSS] = &qss_apss,
+	[SLAVE_CNOC_CFG] = &qss_cfg,
+	[SLAVE_DDRSS_CFG] = &qss_ddrss_cfg,
+	[SLAVE_IMEM] = &qxs_imem,
+	[SLAVE_SERVICE_CNOC] = &srvc_cnoc_main,
+	[SLAVE_PCIE_0] = &xs_pcie_0,
+	[SLAVE_PCIE_1] = &xs_pcie_1,
+};
+
+static const struct qcom_icc_desc sm8650_cnoc_main = {
+	.nodes = cnoc_main_nodes,
+	.num_nodes = ARRAY_SIZE(cnoc_main_nodes),
+	.bcms = cnoc_main_bcms,
+	.num_bcms = ARRAY_SIZE(cnoc_main_bcms),
+};
+
+static struct qcom_icc_bcm * const gem_noc_bcms[] = {
+	&bcm_sh0,
+	&bcm_sh1,
+};
+
+static struct qcom_icc_node * const gem_noc_nodes[] = {
+	[MASTER_GPU_TCU] = &alm_gpu_tcu,
+	[MASTER_SYS_TCU] = &alm_sys_tcu,
+	[MASTER_UBWC_P_TCU] = &alm_ubwc_p_tcu,
+	[MASTER_APPSS_PROC] = &chm_apps,
+	[MASTER_GFX3D] = &qnm_gpu,
+	[MASTER_LPASS_GEM_NOC] = &qnm_lpass_gemnoc,
+	[MASTER_MSS_PROC] = &qnm_mdsp,
+	[MASTER_MNOC_HF_MEM_NOC] = &qnm_mnoc_hf,
+	[MASTER_MNOC_SF_MEM_NOC] = &qnm_mnoc_sf,
+	[MASTER_COMPUTE_NOC] = &qnm_nsp_gemnoc,
+	[MASTER_ANOC_PCIE_GEM_NOC] = &qnm_pcie,
+	[MASTER_SNOC_SF_MEM_NOC] = &qnm_snoc_sf,
+	[MASTER_UBWC_P] = &qnm_ubwc_p,
+	[MASTER_GIC] = &xm_gic,
+	[SLAVE_GEM_NOC_CNOC] = &qns_gem_noc_cnoc,
+	[SLAVE_LLCC] = &qns_llcc,
+	[SLAVE_MEM_NOC_PCIE_SNOC] = &qns_pcie,
+};
+
+static const struct qcom_icc_desc sm8650_gem_noc = {
+	.nodes = gem_noc_nodes,
+	.num_nodes = ARRAY_SIZE(gem_noc_nodes),
+	.bcms = gem_noc_bcms,
+	.num_bcms = ARRAY_SIZE(gem_noc_bcms),
+};
+
+static struct qcom_icc_node * const lpass_ag_noc_nodes[] = {
+	[MASTER_LPIAON_NOC] = &qnm_lpiaon_noc,
+	[SLAVE_LPASS_GEM_NOC] = &qns_lpass_ag_noc_gemnoc,
+};
+
+static const struct qcom_icc_desc sm8650_lpass_ag_noc = {
+	.nodes = lpass_ag_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_ag_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const lpass_lpiaon_noc_bcms[] = {
+	&bcm_lp0,
+};
+
+static struct qcom_icc_node * const lpass_lpiaon_noc_nodes[] = {
+	[MASTER_LPASS_LPINOC] = &qnm_lpass_lpinoc,
+	[SLAVE_LPIAON_NOC_LPASS_AG_NOC] = &qns_lpass_aggnoc,
+};
+
+static const struct qcom_icc_desc sm8650_lpass_lpiaon_noc = {
+	.nodes = lpass_lpiaon_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpiaon_noc_nodes),
+	.bcms = lpass_lpiaon_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_lpiaon_noc_bcms),
+};
+
+static struct qcom_icc_node * const lpass_lpicx_noc_nodes[] = {
+	[MASTER_LPASS_PROC] = &qxm_lpinoc_dsp_axim,
+	[SLAVE_LPICX_NOC_LPIAON_NOC] = &qns_lpi_aon_noc,
+};
+
+static const struct qcom_icc_desc sm8650_lpass_lpicx_noc = {
+	.nodes = lpass_lpicx_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpicx_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const mc_virt_bcms[] = {
+	&bcm_acv,
+	&bcm_mc0,
+};
+
+static struct qcom_icc_node * const mc_virt_nodes[] = {
+	[MASTER_LLCC] = &llcc_mc,
+	[SLAVE_EBI1] = &ebi,
+};
+
+static const struct qcom_icc_desc sm8650_mc_virt = {
+	.nodes = mc_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mc_virt_nodes),
+	.bcms = mc_virt_bcms,
+	.num_bcms = ARRAY_SIZE(mc_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const mmss_noc_bcms[] = {
+	&bcm_mm0,
+	&bcm_mm1,
+};
+
+static struct qcom_icc_node * const mmss_noc_nodes[] = {
+	[MASTER_CAMNOC_HF] = &qnm_camnoc_hf,
+	[MASTER_CAMNOC_ICP] = &qnm_camnoc_icp,
+	[MASTER_CAMNOC_SF] = &qnm_camnoc_sf,
+	[MASTER_MDP] = &qnm_mdp,
+	[MASTER_CDSP_HCP] = &qnm_vapss_hcp,
+	[MASTER_VIDEO] = &qnm_video,
+	[MASTER_VIDEO_CV_PROC] = &qnm_video_cv_cpu,
+	[MASTER_VIDEO_PROC] = &qnm_video_cvp,
+	[MASTER_VIDEO_V_PROC] = &qnm_video_v_cpu,
+	[MASTER_CNOC_MNOC_CFG] = &qsm_mnoc_cfg,
+	[SLAVE_MNOC_HF_MEM_NOC] = &qns_mem_noc_hf,
+	[SLAVE_MNOC_SF_MEM_NOC] = &qns_mem_noc_sf,
+	[SLAVE_SERVICE_MNOC] = &srvc_mnoc,
+};
+
+static const struct qcom_icc_desc sm8650_mmss_noc = {
+	.nodes = mmss_noc_nodes,
+	.num_nodes = ARRAY_SIZE(mmss_noc_nodes),
+	.bcms = mmss_noc_bcms,
+	.num_bcms = ARRAY_SIZE(mmss_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const nsp_noc_bcms[] = {
+	&bcm_co0,
+};
+
+static struct qcom_icc_node * const nsp_noc_nodes[] = {
+	[MASTER_CDSP_PROC] = &qnm_nsp,
+	[SLAVE_CDSP_MEM_NOC] = &qns_nsp_gemnoc,
+};
+
+static const struct qcom_icc_desc sm8650_nsp_noc = {
+	.nodes = nsp_noc_nodes,
+	.num_nodes = ARRAY_SIZE(nsp_noc_nodes),
+	.bcms = nsp_noc_bcms,
+	.num_bcms = ARRAY_SIZE(nsp_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const pcie_anoc_bcms[] = {
+	&bcm_sn4,
+};
+
+static struct qcom_icc_node * const pcie_anoc_nodes[] = {
+	[MASTER_PCIE_ANOC_CFG] = &qsm_pcie_anoc_cfg,
+	[MASTER_PCIE_0] = &xm_pcie3_0,
+	[MASTER_PCIE_1] = &xm_pcie3_1,
+	[SLAVE_ANOC_PCIE_GEM_NOC] = &qns_pcie_mem_noc,
+	[SLAVE_SERVICE_PCIE_ANOC] = &srvc_pcie_aggre_noc,
+};
+
+static const struct qcom_icc_desc sm8650_pcie_anoc = {
+	.nodes = pcie_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_anoc_nodes),
+	.bcms = pcie_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_anoc_bcms),
+};
+
+static struct qcom_icc_bcm * const system_noc_bcms[] = {
+	&bcm_sn0,
+	&bcm_sn2,
+	&bcm_sn3,
+};
+
+static struct qcom_icc_node * const system_noc_nodes[] = {
+	[MASTER_A1NOC_SNOC] = &qnm_aggre1_noc,
+	[MASTER_A2NOC_SNOC] = &qnm_aggre2_noc,
+	[SLAVE_SNOC_GEM_NOC_SF] = &qns_gemnoc_sf,
+};
+
+static const struct qcom_icc_desc sm8650_system_noc = {
+	.nodes = system_noc_nodes,
+	.num_nodes = ARRAY_SIZE(system_noc_nodes),
+	.bcms = system_noc_bcms,
+	.num_bcms = ARRAY_SIZE(system_noc_bcms),
+};
+
+static const struct of_device_id qnoc_of_match[] = {
+	{ .compatible = "qcom,sm8650-aggre1-noc", .data = &sm8650_aggre1_noc },
+	{ .compatible = "qcom,sm8650-aggre2-noc", .data = &sm8650_aggre2_noc },
+	{ .compatible = "qcom,sm8650-clk-virt", .data = &sm8650_clk_virt },
+	{ .compatible = "qcom,sm8650-config-noc", .data = &sm8650_config_noc },
+	{ .compatible = "qcom,sm8650-cnoc-main", .data = &sm8650_cnoc_main },
+	{ .compatible = "qcom,sm8650-gem-noc", .data = &sm8650_gem_noc },
+	{ .compatible = "qcom,sm8650-lpass-ag-noc", .data = &sm8650_lpass_ag_noc },
+	{ .compatible = "qcom,sm8650-lpass-lpiaon-noc", .data = &sm8650_lpass_lpiaon_noc },
+	{ .compatible = "qcom,sm8650-lpass-lpicx-noc", .data = &sm8650_lpass_lpicx_noc },
+	{ .compatible = "qcom,sm8650-mc-virt", .data = &sm8650_mc_virt },
+	{ .compatible = "qcom,sm8650-mmss-noc", .data = &sm8650_mmss_noc },
+	{ .compatible = "qcom,sm8650-nsp-noc", .data = &sm8650_nsp_noc },
+	{ .compatible = "qcom,sm8650-pcie-anoc", .data = &sm8650_pcie_anoc },
+	{ .compatible = "qcom,sm8650-system-noc", .data = &sm8650_system_noc },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qnoc_of_match);
+
+static struct platform_driver qnoc_driver = {
+	.probe = qcom_icc_rpmh_probe,
+	.remove_new = qcom_icc_rpmh_remove,
+	.driver = {
+		.name = "qnoc-sm8650",
+		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
+	},
+};
+
+static int __init qnoc_driver_init(void)
+{
+	return platform_driver_register(&qnoc_driver);
+}
+core_initcall(qnoc_driver_init);
+
+static void __exit qnoc_driver_exit(void)
+{
+	platform_driver_unregister(&qnoc_driver);
+}
+module_exit(qnoc_driver_exit);
+
+MODULE_DESCRIPTION("sm8650 NoC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/interconnect/qcom/sm8650.h b/drivers/interconnect/qcom/sm8650.h
new file mode 100644
index 0000000000000..de35c956fe499
--- /dev/null
+++ b/drivers/interconnect/qcom/sm8650.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * SM8650 interconnect IDs
+ *
+ * Copyright (c) 2020-2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DRIVERS_INTERCONNECT_QCOM_SM8650_H
+#define __DRIVERS_INTERCONNECT_QCOM_SM8650_H
+
+#define SM8650_MASTER_A1NOC_SNOC		0
+#define SM8650_MASTER_A2NOC_SNOC		1
+#define SM8650_MASTER_ANOC_PCIE_GEM_NOC		2
+#define SM8650_MASTER_APPSS_PROC		3
+#define SM8650_MASTER_CAMNOC_HF			4
+#define SM8650_MASTER_CAMNOC_ICP		5
+#define SM8650_MASTER_CAMNOC_SF			6
+#define SM8650_MASTER_CDSP_HCP			7
+#define SM8650_MASTER_CDSP_PROC			8
+#define SM8650_MASTER_CNOC_CFG			9
+#define SM8650_MASTER_CNOC_MNOC_CFG		10
+#define SM8650_MASTER_COMPUTE_NOC		11
+#define SM8650_MASTER_CRYPTO			12
+#define SM8650_MASTER_GEM_NOC_CNOC		13
+#define SM8650_MASTER_GEM_NOC_PCIE_SNOC		14
+#define SM8650_MASTER_GFX3D			15
+#define SM8650_MASTER_GIC			16
+#define SM8650_MASTER_GPU_TCU			17
+#define SM8650_MASTER_IPA			18
+#define SM8650_MASTER_LLCC			19
+#define SM8650_MASTER_LPASS_GEM_NOC		20
+#define SM8650_MASTER_LPASS_LPINOC		21
+#define SM8650_MASTER_LPASS_PROC		22
+#define SM8650_MASTER_LPIAON_NOC		23
+#define SM8650_MASTER_MDP			24
+#define SM8650_MASTER_MNOC_HF_MEM_NOC		25
+#define SM8650_MASTER_MNOC_SF_MEM_NOC		26
+#define SM8650_MASTER_MSS_PROC			27
+#define SM8650_MASTER_PCIE_0			28
+#define SM8650_MASTER_PCIE_1			29
+#define SM8650_MASTER_PCIE_ANOC_CFG		30
+#define SM8650_MASTER_QDSS_BAM			31
+#define SM8650_MASTER_QDSS_ETR			32
+#define SM8650_MASTER_QDSS_ETR_1		33
+#define SM8650_MASTER_QSPI_0			34
+#define SM8650_MASTER_QUP_1			35
+#define SM8650_MASTER_QUP_2			36
+#define SM8650_MASTER_QUP_3			37
+#define SM8650_MASTER_QUP_CORE_0		38
+#define SM8650_MASTER_QUP_CORE_1		39
+#define SM8650_MASTER_QUP_CORE_2		40
+#define SM8650_MASTER_SDCC_2			41
+#define SM8650_MASTER_SDCC_4			42
+#define SM8650_MASTER_SNOC_SF_MEM_NOC		43
+#define SM8650_MASTER_SP			44
+#define SM8650_MASTER_SYS_TCU			45
+#define SM8650_MASTER_UBWC_P			46
+#define SM8650_MASTER_UBWC_P_TCU		47
+#define SM8650_MASTER_UFS_MEM			48
+#define SM8650_MASTER_USB3_0			49
+#define SM8650_MASTER_VIDEO			50
+#define SM8650_MASTER_VIDEO_CV_PROC		51
+#define SM8650_MASTER_VIDEO_PROC		52
+#define SM8650_MASTER_VIDEO_V_PROC		53
+#define SM8650_SLAVE_A1NOC_SNOC			54
+#define SM8650_SLAVE_A2NOC_SNOC			55
+#define SM8650_SLAVE_AHB2PHY_NORTH		56
+#define SM8650_SLAVE_AHB2PHY_SOUTH		57
+#define SM8650_SLAVE_ANOC_PCIE_GEM_NOC		58
+#define SM8650_SLAVE_AOSS			59
+#define SM8650_SLAVE_APPSS			60
+#define SM8650_SLAVE_CAMERA_CFG			61
+#define SM8650_SLAVE_CDSP_MEM_NOC		62
+#define SM8650_SLAVE_CLK_CTL			63
+#define SM8650_SLAVE_CNOC_CFG			64
+#define SM8650_SLAVE_CNOC_MNOC_CFG		65
+#define SM8650_SLAVE_CNOC_MSS			66
+#define SM8650_SLAVE_CPR_HMX			67
+#define SM8650_SLAVE_CPR_NSPCX			68
+#define SM8650_SLAVE_CRYPTO_0_CFG		69
+#define SM8650_SLAVE_CX_RDPM			70
+#define SM8650_SLAVE_DDRSS_CFG			71
+#define SM8650_SLAVE_DISPLAY_CFG		72
+#define SM8650_SLAVE_EBI1			73
+#define SM8650_SLAVE_GEM_NOC_CNOC		74
+#define SM8650_SLAVE_GFX3D_CFG			75
+#define SM8650_SLAVE_I2C			76
+#define SM8650_SLAVE_I3C_IBI0_CFG		77
+#define SM8650_SLAVE_I3C_IBI1_CFG		78
+#define SM8650_SLAVE_IMEM			79
+#define SM8650_SLAVE_IMEM_CFG			80
+#define SM8650_SLAVE_IPA_CFG			81
+#define SM8650_SLAVE_IPC_ROUTER_CFG		82
+#define SM8650_SLAVE_LLCC			83
+#define SM8650_SLAVE_LPASS_GEM_NOC		84
+#define SM8650_SLAVE_LPIAON_NOC_LPASS_AG_NOC	85
+#define SM8650_SLAVE_LPICX_NOC_LPIAON_NOC	86
+#define SM8650_SLAVE_MEM_NOC_PCIE_SNOC		87
+#define SM8650_SLAVE_MNOC_HF_MEM_NOC		88
+#define SM8650_SLAVE_MNOC_SF_MEM_NOC		89
+#define SM8650_SLAVE_MX_2_RDPM			90
+#define SM8650_SLAVE_MX_RDPM			91
+#define SM8650_SLAVE_NSP_QTB_CFG		92
+#define SM8650_SLAVE_PCIE_0			93
+#define SM8650_SLAVE_PCIE_1			94
+#define SM8650_SLAVE_PCIE_0_CFG			95
+#define SM8650_SLAVE_PCIE_1_CFG			96
+#define SM8650_SLAVE_PCIE_ANOC_CFG		97
+#define SM8650_SLAVE_PCIE_RSCC			98
+#define SM8650_SLAVE_PDM			99
+#define SM8650_SLAVE_PRNG			100
+#define SM8650_SLAVE_QDSS_CFG			101
+#define SM8650_SLAVE_QDSS_STM			102
+#define SM8650_SLAVE_QSPI_0			103
+#define SM8650_SLAVE_QUP_1			104
+#define SM8650_SLAVE_QUP_2			105
+#define SM8650_SLAVE_QUP_3			106
+#define SM8650_SLAVE_QUP_CORE_0			107
+#define SM8650_SLAVE_QUP_CORE_1			108
+#define SM8650_SLAVE_QUP_CORE_2			109
+#define SM8650_SLAVE_RBCPR_CX_CFG		110
+#define SM8650_SLAVE_RBCPR_MMCX_CFG		111
+#define SM8650_SLAVE_RBCPR_MXA_CFG		112
+#define SM8650_SLAVE_RBCPR_MXC_CFG		113
+#define SM8650_SLAVE_SDCC_2			114
+#define SM8650_SLAVE_SDCC_4			115
+#define SM8650_SLAVE_SERVICE_CNOC		116
+#define SM8650_SLAVE_SERVICE_CNOC_CFG		117
+#define SM8650_SLAVE_SERVICE_MNOC		118
+#define SM8650_SLAVE_SERVICE_PCIE_ANOC		119
+#define SM8650_SLAVE_SNOC_GEM_NOC_SF		120
+#define SM8650_SLAVE_SPSS_CFG			121
+#define SM8650_SLAVE_TCSR			122
+#define SM8650_SLAVE_TCU			123
+#define SM8650_SLAVE_TLMM			124
+#define SM8650_SLAVE_TME_CFG			125
+#define SM8650_SLAVE_UFS_MEM_CFG		126
+#define SM8650_SLAVE_USB3_0			127
+#define SM8650_SLAVE_VENUS_CFG			128
+#define SM8650_SLAVE_VSENSE_CTRL_CFG		129
+
+#endif
-- 
GitLab


From 0403ae6f165ba51c185f22aa98fa397da4619fc7 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Wed, 25 Oct 2023 09:24:39 +0200
Subject: [PATCH 0400/4076] dt-bindings: interconnect: qcom-bwmon: document
 SM8650 BWMONs

Document SM8650 BWMONs which has - just like SM8550 - a BWMONv4 for
CPU-LLCC and a BWMONv5 for DDR-LLCC paths.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231025-topic-sm8650-upstream-bindings-bwmon-v1-1-11efcdd8799e@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 .../devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml    | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
index 73f809cdb783c..7cb8df757477c 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
@@ -32,6 +32,7 @@ properties:
               - qcom,sm6350-llcc-bwmon
               - qcom,sm8250-cpu-bwmon
               - qcom,sm8550-cpu-bwmon
+              - qcom,sm8650-cpu-bwmon
           - const: qcom,sdm845-bwmon    # BWMON v4, unified register space
       - items:
           - enum:
@@ -40,6 +41,7 @@ properties:
               - qcom,sm6350-cpu-bwmon
               - qcom,sm8250-llcc-bwmon
               - qcom,sm8550-llcc-bwmon
+              - qcom,sm8650-llcc-bwmon
           - const: qcom,sc7280-llcc-bwmon
       - const: qcom,sc7280-llcc-bwmon   # BWMON v5
       - const: qcom,sdm845-llcc-bwmon   # BWMON v5
-- 
GitLab


From 9f196772841e8a344303f42da9b4e596a3554771 Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <quic_rjendra@quicinc.com>
Date: Thu, 23 Nov 2023 19:20:28 +0530
Subject: [PATCH 0401/4076] interconnect: qcom: Add X1E80100 interconnect
 provider driver

Add driver for the Qualcomm interconnect buses found in X1E80100 based
platforms. The topology consists of several NoCs that are controlled by
a remote processor that collects the aggregated bandwidth for each
master-slave pairs.

Co-developed-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Rajendra Nayak <quic_rjendra@quicinc.com>
Co-developed-by: Sibi Sankar <quic_sibis@quicinc.com>
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Link: https://lore.kernel.org/r/20231123135028.29433-3-quic_sibis@quicinc.com
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/Kconfig    |    9 +
 drivers/interconnect/qcom/Makefile   |    2 +
 drivers/interconnect/qcom/x1e80100.c | 2328 ++++++++++++++++++++++++++
 drivers/interconnect/qcom/x1e80100.h |  192 +++
 4 files changed, 2531 insertions(+)
 create mode 100644 drivers/interconnect/qcom/x1e80100.c
 create mode 100644 drivers/interconnect/qcom/x1e80100.h

diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig
index 62b516d38d03f..431f5977afcda 100644
--- a/drivers/interconnect/qcom/Kconfig
+++ b/drivers/interconnect/qcom/Kconfig
@@ -245,5 +245,14 @@ config INTERCONNECT_QCOM_SM8550
 	  This is a driver for the Qualcomm Network-on-Chip on SM8550-based
 	  platforms.
 
+config INTERCONNECT_QCOM_X1E80100
+	tristate "Qualcomm X1E80100 interconnect driver"
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
+	select INTERCONNECT_QCOM_RPMH
+	select INTERCONNECT_QCOM_BCM_VOTER
+	help
+	  This is a driver for the Qualcomm Network-on-Chip on X1E80100-based
+	  platforms.
+
 config INTERCONNECT_QCOM_SMD_RPM
 	tristate
diff --git a/drivers/interconnect/qcom/Makefile b/drivers/interconnect/qcom/Makefile
index c5320e293960a..4d1477e4e5d5e 100644
--- a/drivers/interconnect/qcom/Makefile
+++ b/drivers/interconnect/qcom/Makefile
@@ -30,6 +30,7 @@ qnoc-sm8250-objs			:= sm8250.o
 qnoc-sm8350-objs			:= sm8350.o
 qnoc-sm8450-objs			:= sm8450.o
 qnoc-sm8550-objs			:= sm8550.o
+qnoc-x1e80100-objs			:= x1e80100.o
 icc-smd-rpm-objs			:= smd-rpm.o icc-rpm.o icc-rpm-clocks.o
 
 obj-$(CONFIG_INTERCONNECT_QCOM_BCM_VOTER) += icc-bcm-voter.o
@@ -59,4 +60,5 @@ obj-$(CONFIG_INTERCONNECT_QCOM_SM8250) += qnoc-sm8250.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8350) += qnoc-sm8350.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8450) += qnoc-sm8450.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8550) += qnoc-sm8550.o
+obj-$(CONFIG_INTERCONNECT_QCOM_X1E80100) += qnoc-x1e80100.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SMD_RPM) += icc-smd-rpm.o
diff --git a/drivers/interconnect/qcom/x1e80100.c b/drivers/interconnect/qcom/x1e80100.c
new file mode 100644
index 0000000000000..d19501d913b39
--- /dev/null
+++ b/drivers/interconnect/qcom/x1e80100.c
@@ -0,0 +1,2328 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/interconnect.h>
+#include <linux/interconnect-provider.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <dt-bindings/interconnect/qcom,x1e80100-rpmh.h>
+
+#include "bcm-voter.h"
+#include "icc-common.h"
+#include "icc-rpmh.h"
+#include "x1e80100.h"
+
+static struct qcom_icc_node qhm_qspi = {
+	.name = "qhm_qspi",
+	.id = X1E80100_MASTER_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup1 = {
+	.name = "qhm_qup1",
+	.id = X1E80100_MASTER_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc4 = {
+	.name = "xm_sdc4",
+	.id = X1E80100_MASTER_SDCC_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_ufs_mem = {
+	.name = "xm_ufs_mem",
+	.id = X1E80100_MASTER_UFS_MEM,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup0 = {
+	.name = "qhm_qup0",
+	.id = X1E80100_MASTER_QUP_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup2 = {
+	.name = "qhm_qup2",
+	.id = X1E80100_MASTER_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_crypto = {
+	.name = "qxm_crypto",
+	.id = X1E80100_MASTER_CRYPTO,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_sp = {
+	.name = "qxm_sp",
+	.id = X1E80100_MASTER_SP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_0 = {
+	.name = "xm_qdss_etr_0",
+	.id = X1E80100_MASTER_QDSS_ETR,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_1 = {
+	.name = "xm_qdss_etr_1",
+	.id = X1E80100_MASTER_QDSS_ETR_1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc2 = {
+	.name = "xm_sdc2",
+	.id = X1E80100_MASTER_SDCC_2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node ddr_perf_mode_master = {
+	.name = "ddr_perf_mode_master",
+	.id = X1E80100_MASTER_DDR_PERF_MODE,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_DDR_PERF_MODE },
+};
+
+static struct qcom_icc_node qup0_core_master = {
+	.name = "qup0_core_master",
+	.id = X1E80100_MASTER_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_QUP_CORE_0 },
+};
+
+static struct qcom_icc_node qup1_core_master = {
+	.name = "qup1_core_master",
+	.id = X1E80100_MASTER_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_QUP_CORE_1 },
+};
+
+static struct qcom_icc_node qup2_core_master = {
+	.name = "qup2_core_master",
+	.id = X1E80100_MASTER_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_QUP_CORE_2 },
+};
+
+static struct qcom_icc_node qsm_cfg = {
+	.name = "qsm_cfg",
+	.id = X1E80100_MASTER_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 47,
+	.links = { X1E80100_SLAVE_AHB2PHY_SOUTH, X1E80100_SLAVE_AHB2PHY_NORTH,
+		   X1E80100_SLAVE_AHB2PHY_2, X1E80100_SLAVE_AV1_ENC_CFG,
+		   X1E80100_SLAVE_CAMERA_CFG, X1E80100_SLAVE_CLK_CTL,
+		   X1E80100_SLAVE_CRYPTO_0_CFG, X1E80100_SLAVE_DISPLAY_CFG,
+		   X1E80100_SLAVE_GFX3D_CFG, X1E80100_SLAVE_IMEM_CFG,
+		   X1E80100_SLAVE_IPC_ROUTER_CFG, X1E80100_SLAVE_PCIE_0_CFG,
+		   X1E80100_SLAVE_PCIE_1_CFG, X1E80100_SLAVE_PCIE_2_CFG,
+		   X1E80100_SLAVE_PCIE_3_CFG, X1E80100_SLAVE_PCIE_4_CFG,
+		   X1E80100_SLAVE_PCIE_5_CFG, X1E80100_SLAVE_PCIE_6A_CFG,
+		   X1E80100_SLAVE_PCIE_6B_CFG, X1E80100_SLAVE_PCIE_RSC_CFG,
+		   X1E80100_SLAVE_PDM, X1E80100_SLAVE_PRNG,
+		   X1E80100_SLAVE_QDSS_CFG, X1E80100_SLAVE_QSPI_0,
+		   X1E80100_SLAVE_QUP_0, X1E80100_SLAVE_QUP_1,
+		   X1E80100_SLAVE_QUP_2, X1E80100_SLAVE_SDCC_2,
+		   X1E80100_SLAVE_SDCC_4, X1E80100_SLAVE_SMMUV3_CFG,
+		   X1E80100_SLAVE_TCSR, X1E80100_SLAVE_TLMM,
+		   X1E80100_SLAVE_UFS_MEM_CFG, X1E80100_SLAVE_USB2,
+		   X1E80100_SLAVE_USB3_0, X1E80100_SLAVE_USB3_1,
+		   X1E80100_SLAVE_USB3_2, X1E80100_SLAVE_USB3_MP,
+		   X1E80100_SLAVE_USB4_0, X1E80100_SLAVE_USB4_1,
+		   X1E80100_SLAVE_USB4_2, X1E80100_SLAVE_VENUS_CFG,
+		   X1E80100_SLAVE_LPASS_QTB_CFG, X1E80100_SLAVE_CNOC_MNOC_CFG,
+		   X1E80100_SLAVE_NSP_QTB_CFG, X1E80100_SLAVE_QDSS_STM,
+		   X1E80100_SLAVE_TCU },
+};
+
+static struct qcom_icc_node qnm_gemnoc_cnoc = {
+	.name = "qnm_gemnoc_cnoc",
+	.id = X1E80100_MASTER_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 6,
+	.links = { X1E80100_SLAVE_AOSS, X1E80100_SLAVE_TME_CFG,
+		   X1E80100_SLAVE_APPSS, X1E80100_SLAVE_CNOC_CFG,
+		   X1E80100_SLAVE_BOOT_IMEM, X1E80100_SLAVE_IMEM },
+};
+
+static struct qcom_icc_node qnm_gemnoc_pcie = {
+	.name = "qnm_gemnoc_pcie",
+	.id = X1E80100_MASTER_GEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 8,
+	.links = { X1E80100_SLAVE_PCIE_0, X1E80100_SLAVE_PCIE_1,
+		   X1E80100_SLAVE_PCIE_2, X1E80100_SLAVE_PCIE_3,
+		   X1E80100_SLAVE_PCIE_4, X1E80100_SLAVE_PCIE_5,
+		   X1E80100_SLAVE_PCIE_6A, X1E80100_SLAVE_PCIE_6B },
+};
+
+static struct qcom_icc_node alm_gpu_tcu = {
+	.name = "alm_gpu_tcu",
+	.id = X1E80100_MASTER_GPU_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_pcie_tcu = {
+	.name = "alm_pcie_tcu",
+	.id = X1E80100_MASTER_PCIE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_sys_tcu = {
+	.name = "alm_sys_tcu",
+	.id = X1E80100_MASTER_SYS_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node chm_apps = {
+	.name = "chm_apps",
+	.id = X1E80100_MASTER_APPSS_PROC,
+	.channels = 6,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC,
+		   X1E80100_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_gpu = {
+	.name = "qnm_gpu",
+	.id = X1E80100_MASTER_GFX3D,
+	.channels = 4,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpass = {
+	.name = "qnm_lpass",
+	.id = X1E80100_MASTER_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC,
+		   X1E80100_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_mnoc_hf = {
+	.name = "qnm_mnoc_hf",
+	.id = X1E80100_MASTER_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_mnoc_sf = {
+	.name = "qnm_mnoc_sf",
+	.id = X1E80100_MASTER_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_nsp_noc = {
+	.name = "qnm_nsp_noc",
+	.id = X1E80100_MASTER_COMPUTE_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC,
+		   X1E80100_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_pcie = {
+	.name = "qnm_pcie",
+	.id = X1E80100_MASTER_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 2,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_snoc_sf = {
+	.name = "qnm_snoc_sf",
+	.id = X1E80100_MASTER_SNOC_SF_MEM_NOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 3,
+	.links = { X1E80100_SLAVE_GEM_NOC_CNOC, X1E80100_SLAVE_LLCC,
+		   X1E80100_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node xm_gic = {
+	.name = "xm_gic",
+	.id = X1E80100_MASTER_GIC2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpiaon_noc = {
+	.name = "qnm_lpiaon_noc",
+	.id = X1E80100_MASTER_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_lpass_lpinoc = {
+	.name = "qnm_lpass_lpinoc",
+	.id = X1E80100_MASTER_LPASS_LPINOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LPIAON_NOC_LPASS_AG_NOC },
+};
+
+static struct qcom_icc_node qxm_lpinoc_dsp_axim = {
+	.name = "qxm_lpinoc_dsp_axim",
+	.id = X1E80100_MASTER_LPASS_PROC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LPICX_NOC_LPIAON_NOC },
+};
+
+static struct qcom_icc_node llcc_mc = {
+	.name = "llcc_mc",
+	.id = X1E80100_MASTER_LLCC,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_EBI1 },
+};
+
+static struct qcom_icc_node qnm_av1_enc = {
+	.name = "qnm_av1_enc",
+	.id = X1E80100_MASTER_AV1_ENC,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_hf = {
+	.name = "qnm_camnoc_hf",
+	.id = X1E80100_MASTER_CAMNOC_HF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_icp = {
+	.name = "qnm_camnoc_icp",
+	.id = X1E80100_MASTER_CAMNOC_ICP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_sf = {
+	.name = "qnm_camnoc_sf",
+	.id = X1E80100_MASTER_CAMNOC_SF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_eva = {
+	.name = "qnm_eva",
+	.id = X1E80100_MASTER_EVA,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_mdp = {
+	.name = "qnm_mdp",
+	.id = X1E80100_MASTER_MDP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video = {
+	.name = "qnm_video",
+	.id = X1E80100_MASTER_VIDEO,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_cv_cpu = {
+	.name = "qnm_video_cv_cpu",
+	.id = X1E80100_MASTER_VIDEO_CV_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_v_cpu = {
+	.name = "qnm_video_v_cpu",
+	.id = X1E80100_MASTER_VIDEO_V_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qsm_mnoc_cfg = {
+	.name = "qsm_mnoc_cfg",
+	.id = X1E80100_MASTER_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SERVICE_MNOC },
+};
+
+static struct qcom_icc_node qxm_nsp = {
+	.name = "qxm_nsp",
+	.id = X1E80100_MASTER_CDSP_PROC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_CDSP_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_pcie_north_gem_noc = {
+	.name = "qnm_pcie_north_gem_noc",
+	.id = X1E80100_MASTER_PCIE_NORTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_pcie_south_gem_noc = {
+	.name = "qnm_pcie_south_gem_noc",
+	.id = X1E80100_MASTER_PCIE_SOUTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node xm_pcie_3 = {
+	.name = "xm_pcie_3",
+	.id = X1E80100_MASTER_PCIE_3,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH },
+};
+
+static struct qcom_icc_node xm_pcie_4 = {
+	.name = "xm_pcie_4",
+	.id = X1E80100_MASTER_PCIE_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH },
+};
+
+static struct qcom_icc_node xm_pcie_5 = {
+	.name = "xm_pcie_5",
+	.id = X1E80100_MASTER_PCIE_5,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH },
+};
+
+static struct qcom_icc_node xm_pcie_0 = {
+	.name = "xm_pcie_0",
+	.id = X1E80100_MASTER_PCIE_0,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node xm_pcie_1 = {
+	.name = "xm_pcie_1",
+	.id = X1E80100_MASTER_PCIE_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node xm_pcie_2 = {
+	.name = "xm_pcie_2",
+	.id = X1E80100_MASTER_PCIE_2,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node xm_pcie_6a = {
+	.name = "xm_pcie_6a",
+	.id = X1E80100_MASTER_PCIE_6A,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node xm_pcie_6b = {
+	.name = "xm_pcie_6b",
+	.id = X1E80100_MASTER_PCIE_6B,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node qnm_aggre1_noc = {
+	.name = "qnm_aggre1_noc",
+	.id = X1E80100_MASTER_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_aggre2_noc = {
+	.name = "qnm_aggre2_noc",
+	.id = X1E80100_MASTER_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_gic = {
+	.name = "qnm_gic",
+	.id = X1E80100_MASTER_GIC1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_usb_anoc = {
+	.name = "qnm_usb_anoc",
+	.id = X1E80100_MASTER_USB_NOC_SNOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_aggre_usb_north_snoc = {
+	.name = "qnm_aggre_usb_north_snoc",
+	.id = X1E80100_MASTER_AGGRE_USB_NORTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_USB_NOC_SNOC },
+};
+
+static struct qcom_icc_node qnm_aggre_usb_south_snoc = {
+	.name = "qnm_aggre_usb_south_snoc",
+	.id = X1E80100_MASTER_AGGRE_USB_SOUTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_USB_NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_usb2_0 = {
+	.name = "xm_usb2_0",
+	.id = X1E80100_MASTER_USB2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_NORTH },
+};
+
+static struct qcom_icc_node xm_usb3_mp = {
+	.name = "xm_usb3_mp",
+	.id = X1E80100_MASTER_USB3_MP,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_NORTH },
+};
+
+static struct qcom_icc_node xm_usb3_0 = {
+	.name = "xm_usb3_0",
+	.id = X1E80100_MASTER_USB3_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb3_1 = {
+	.name = "xm_usb3_1",
+	.id = X1E80100_MASTER_USB3_1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb3_2 = {
+	.name = "xm_usb3_2",
+	.id = X1E80100_MASTER_USB3_2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb4_0 = {
+	.name = "xm_usb4_0",
+	.id = X1E80100_MASTER_USB4_0,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb4_1 = {
+	.name = "xm_usb4_1",
+	.id = X1E80100_MASTER_USB4_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node xm_usb4_2 = {
+	.name = "xm_usb4_2",
+	.id = X1E80100_MASTER_USB4_2,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node qnm_mnoc_hf_disp = {
+	.name = "qnm_mnoc_hf_disp",
+	.id = X1E80100_MASTER_MNOC_HF_MEM_NOC_DISP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LLCC_DISP },
+};
+
+static struct qcom_icc_node qnm_pcie_disp = {
+	.name = "qnm_pcie_disp",
+	.id = X1E80100_MASTER_ANOC_PCIE_GEM_NOC_DISP,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LLCC_DISP },
+};
+
+static struct qcom_icc_node llcc_mc_disp = {
+	.name = "llcc_mc_disp",
+	.id = X1E80100_MASTER_LLCC_DISP,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_EBI1_DISP },
+};
+
+static struct qcom_icc_node qnm_mdp_disp = {
+	.name = "qnm_mdp_disp",
+	.id = X1E80100_MASTER_MDP_DISP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_MNOC_HF_MEM_NOC_DISP },
+};
+
+static struct qcom_icc_node qnm_pcie_pcie = {
+	.name = "qnm_pcie_pcie",
+	.id = X1E80100_MASTER_ANOC_PCIE_GEM_NOC_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_LLCC_PCIE },
+};
+
+static struct qcom_icc_node llcc_mc_pcie = {
+	.name = "llcc_mc_pcie",
+	.id = X1E80100_MASTER_LLCC_PCIE,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_EBI1_PCIE },
+};
+
+static struct qcom_icc_node qnm_pcie_north_gem_noc_pcie = {
+	.name = "qnm_pcie_north_gem_noc_pcie",
+	.id = X1E80100_MASTER_PCIE_NORTH_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_ANOC_PCIE_GEM_NOC_PCIE },
+};
+
+static struct qcom_icc_node qnm_pcie_south_gem_noc_pcie = {
+	.name = "qnm_pcie_south_gem_noc_pcie",
+	.id = X1E80100_MASTER_PCIE_SOUTH_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_ANOC_PCIE_GEM_NOC_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_3_pcie = {
+	.name = "xm_pcie_3_pcie",
+	.id = X1E80100_MASTER_PCIE_3_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_4_pcie = {
+	.name = "xm_pcie_4_pcie",
+	.id = X1E80100_MASTER_PCIE_4_PCIE,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_5_pcie = {
+	.name = "xm_pcie_5_pcie",
+	.id = X1E80100_MASTER_PCIE_5_PCIE,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_NORTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_0_pcie = {
+	.name = "xm_pcie_0_pcie",
+	.id = X1E80100_MASTER_PCIE_0_PCIE,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_1_pcie = {
+	.name = "xm_pcie_1_pcie",
+	.id = X1E80100_MASTER_PCIE_1_PCIE,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_2_pcie = {
+	.name = "xm_pcie_2_pcie",
+	.id = X1E80100_MASTER_PCIE_2_PCIE,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_6a_pcie = {
+	.name = "xm_pcie_6a_pcie",
+	.id = X1E80100_MASTER_PCIE_6A_PCIE,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node xm_pcie_6b_pcie = {
+	.name = "xm_pcie_6b_pcie",
+	.id = X1E80100_MASTER_PCIE_6B_PCIE,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_SLAVE_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_node qns_a1noc_snoc = {
+	.name = "qns_a1noc_snoc",
+	.id = X1E80100_SLAVE_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qns_a2noc_snoc = {
+	.name = "qns_a2noc_snoc",
+	.id = X1E80100_SLAVE_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node ddr_perf_mode_slave = {
+	.name = "ddr_perf_mode_slave",
+	.id = X1E80100_SLAVE_DDR_PERF_MODE,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup0_core_slave = {
+	.name = "qup0_core_slave",
+	.id = X1E80100_SLAVE_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup1_core_slave = {
+	.name = "qup1_core_slave",
+	.id = X1E80100_SLAVE_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup2_core_slave = {
+	.name = "qup2_core_slave",
+	.id = X1E80100_SLAVE_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy0 = {
+	.name = "qhs_ahb2phy0",
+	.id = X1E80100_SLAVE_AHB2PHY_SOUTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy1 = {
+	.name = "qhs_ahb2phy1",
+	.id = X1E80100_SLAVE_AHB2PHY_NORTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy2 = {
+	.name = "qhs_ahb2phy2",
+	.id = X1E80100_SLAVE_AHB2PHY_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_av1_enc_cfg = {
+	.name = "qhs_av1_enc_cfg",
+	.id = X1E80100_SLAVE_AV1_ENC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_camera_cfg = {
+	.name = "qhs_camera_cfg",
+	.id = X1E80100_SLAVE_CAMERA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_clk_ctl = {
+	.name = "qhs_clk_ctl",
+	.id = X1E80100_SLAVE_CLK_CTL,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_crypto0_cfg = {
+	.name = "qhs_crypto0_cfg",
+	.id = X1E80100_SLAVE_CRYPTO_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_display_cfg = {
+	.name = "qhs_display_cfg",
+	.id = X1E80100_SLAVE_DISPLAY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_gpuss_cfg = {
+	.name = "qhs_gpuss_cfg",
+	.id = X1E80100_SLAVE_GFX3D_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_imem_cfg = {
+	.name = "qhs_imem_cfg",
+	.id = X1E80100_SLAVE_IMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ipc_router = {
+	.name = "qhs_ipc_router",
+	.id = X1E80100_SLAVE_IPC_ROUTER_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie0_cfg = {
+	.name = "qhs_pcie0_cfg",
+	.id = X1E80100_SLAVE_PCIE_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie1_cfg = {
+	.name = "qhs_pcie1_cfg",
+	.id = X1E80100_SLAVE_PCIE_1_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie2_cfg = {
+	.name = "qhs_pcie2_cfg",
+	.id = X1E80100_SLAVE_PCIE_2_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie3_cfg = {
+	.name = "qhs_pcie3_cfg",
+	.id = X1E80100_SLAVE_PCIE_3_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie4_cfg = {
+	.name = "qhs_pcie4_cfg",
+	.id = X1E80100_SLAVE_PCIE_4_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie5_cfg = {
+	.name = "qhs_pcie5_cfg",
+	.id = X1E80100_SLAVE_PCIE_5_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie6a_cfg = {
+	.name = "qhs_pcie6a_cfg",
+	.id = X1E80100_SLAVE_PCIE_6A_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie6b_cfg = {
+	.name = "qhs_pcie6b_cfg",
+	.id = X1E80100_SLAVE_PCIE_6B_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie_rsc_cfg = {
+	.name = "qhs_pcie_rsc_cfg",
+	.id = X1E80100_SLAVE_PCIE_RSC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pdm = {
+	.name = "qhs_pdm",
+	.id = X1E80100_SLAVE_PDM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_prng = {
+	.name = "qhs_prng",
+	.id = X1E80100_SLAVE_PRNG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qdss_cfg = {
+	.name = "qhs_qdss_cfg",
+	.id = X1E80100_SLAVE_QDSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qspi = {
+	.name = "qhs_qspi",
+	.id = X1E80100_SLAVE_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup0 = {
+	.name = "qhs_qup0",
+	.id = X1E80100_SLAVE_QUP_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup1 = {
+	.name = "qhs_qup1",
+	.id = X1E80100_SLAVE_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup2 = {
+	.name = "qhs_qup2",
+	.id = X1E80100_SLAVE_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc2 = {
+	.name = "qhs_sdc2",
+	.id = X1E80100_SLAVE_SDCC_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc4 = {
+	.name = "qhs_sdc4",
+	.id = X1E80100_SLAVE_SDCC_4,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_smmuv3_cfg = {
+	.name = "qhs_smmuv3_cfg",
+	.id = X1E80100_SLAVE_SMMUV3_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tcsr = {
+	.name = "qhs_tcsr",
+	.id = X1E80100_SLAVE_TCSR,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tlmm = {
+	.name = "qhs_tlmm",
+	.id = X1E80100_SLAVE_TLMM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ufs_mem_cfg = {
+	.name = "qhs_ufs_mem_cfg",
+	.id = X1E80100_SLAVE_UFS_MEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb2_0_cfg = {
+	.name = "qhs_usb2_0_cfg",
+	.id = X1E80100_SLAVE_USB2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_0_cfg = {
+	.name = "qhs_usb3_0_cfg",
+	.id = X1E80100_SLAVE_USB3_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_1_cfg = {
+	.name = "qhs_usb3_1_cfg",
+	.id = X1E80100_SLAVE_USB3_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_2_cfg = {
+	.name = "qhs_usb3_2_cfg",
+	.id = X1E80100_SLAVE_USB3_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_mp_cfg = {
+	.name = "qhs_usb3_mp_cfg",
+	.id = X1E80100_SLAVE_USB3_MP,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb4_0_cfg = {
+	.name = "qhs_usb4_0_cfg",
+	.id = X1E80100_SLAVE_USB4_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb4_1_cfg = {
+	.name = "qhs_usb4_1_cfg",
+	.id = X1E80100_SLAVE_USB4_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb4_2_cfg = {
+	.name = "qhs_usb4_2_cfg",
+	.id = X1E80100_SLAVE_USB4_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_venus_cfg = {
+	.name = "qhs_venus_cfg",
+	.id = X1E80100_SLAVE_VENUS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_lpass_qtb_cfg = {
+	.name = "qss_lpass_qtb_cfg",
+	.id = X1E80100_SLAVE_LPASS_QTB_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_mnoc_cfg = {
+	.name = "qss_mnoc_cfg",
+	.id = X1E80100_SLAVE_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_CNOC_MNOC_CFG },
+};
+
+static struct qcom_icc_node qss_nsp_qtb_cfg = {
+	.name = "qss_nsp_qtb_cfg",
+	.id = X1E80100_SLAVE_NSP_QTB_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_qdss_stm = {
+	.name = "xs_qdss_stm",
+	.id = X1E80100_SLAVE_QDSS_STM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_sys_tcu_cfg = {
+	.name = "xs_sys_tcu_cfg",
+	.id = X1E80100_SLAVE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_aoss = {
+	.name = "qhs_aoss",
+	.id = X1E80100_SLAVE_AOSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tme_cfg = {
+	.name = "qhs_tme_cfg",
+	.id = X1E80100_SLAVE_TME_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_apss = {
+	.name = "qns_apss",
+	.id = X1E80100_SLAVE_APPSS,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_cfg = {
+	.name = "qss_cfg",
+	.id = X1E80100_SLAVE_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_CNOC_CFG },
+};
+
+static struct qcom_icc_node qxs_boot_imem = {
+	.name = "qxs_boot_imem",
+	.id = X1E80100_SLAVE_BOOT_IMEM,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qxs_imem = {
+	.name = "qxs_imem",
+	.id = X1E80100_SLAVE_IMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_0 = {
+	.name = "xs_pcie_0",
+	.id = X1E80100_SLAVE_PCIE_0,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_1 = {
+	.name = "xs_pcie_1",
+	.id = X1E80100_SLAVE_PCIE_1,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_2 = {
+	.name = "xs_pcie_2",
+	.id = X1E80100_SLAVE_PCIE_2,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_3 = {
+	.name = "xs_pcie_3",
+	.id = X1E80100_SLAVE_PCIE_3,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_4 = {
+	.name = "xs_pcie_4",
+	.id = X1E80100_SLAVE_PCIE_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_5 = {
+	.name = "xs_pcie_5",
+	.id = X1E80100_SLAVE_PCIE_5,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_6a = {
+	.name = "xs_pcie_6a",
+	.id = X1E80100_SLAVE_PCIE_6A,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie_6b = {
+	.name = "xs_pcie_6b",
+	.id = X1E80100_SLAVE_PCIE_6B,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_gem_noc_cnoc = {
+	.name = "qns_gem_noc_cnoc",
+	.id = X1E80100_SLAVE_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_GEM_NOC_CNOC },
+};
+
+static struct qcom_icc_node qns_llcc = {
+	.name = "qns_llcc",
+	.id = X1E80100_SLAVE_LLCC,
+	.channels = 8,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LLCC },
+};
+
+static struct qcom_icc_node qns_pcie = {
+	.name = "qns_pcie",
+	.id = X1E80100_SLAVE_MEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_GEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qns_lpass_ag_noc_gemnoc = {
+	.name = "qns_lpass_ag_noc_gemnoc",
+	.id = X1E80100_SLAVE_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qns_lpass_aggnoc = {
+	.name = "qns_lpass_aggnoc",
+	.id = X1E80100_SLAVE_LPIAON_NOC_LPASS_AG_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LPIAON_NOC },
+};
+
+static struct qcom_icc_node qns_lpi_aon_noc = {
+	.name = "qns_lpi_aon_noc",
+	.id = X1E80100_SLAVE_LPICX_NOC_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LPASS_LPINOC },
+};
+
+static struct qcom_icc_node ebi = {
+	.name = "ebi",
+	.id = X1E80100_SLAVE_EBI1,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_mem_noc_hf = {
+	.name = "qns_mem_noc_hf",
+	.id = X1E80100_SLAVE_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qns_mem_noc_sf = {
+	.name = "qns_mem_noc_sf",
+	.id = X1E80100_SLAVE_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node srvc_mnoc = {
+	.name = "srvc_mnoc",
+	.id = X1E80100_SLAVE_SERVICE_MNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_nsp_gemnoc = {
+	.name = "qns_nsp_gemnoc",
+	.id = X1E80100_SLAVE_CDSP_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_COMPUTE_NOC },
+};
+
+static struct qcom_icc_node qns_pcie_mem_noc = {
+	.name = "qns_pcie_mem_noc",
+	.id = X1E80100_SLAVE_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node qns_pcie_north_gem_noc = {
+	.name = "qns_pcie_north_gem_noc",
+	.id = X1E80100_SLAVE_PCIE_NORTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_PCIE_NORTH },
+};
+
+static struct qcom_icc_node qns_pcie_south_gem_noc = {
+	.name = "qns_pcie_south_gem_noc",
+	.id = X1E80100_SLAVE_PCIE_SOUTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_PCIE_SOUTH },
+};
+
+static struct qcom_icc_node qns_gemnoc_sf = {
+	.name = "qns_gemnoc_sf",
+	.id = X1E80100_SLAVE_SNOC_GEM_NOC_SF,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_SNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qns_aggre_usb_snoc = {
+	.name = "qns_aggre_usb_snoc",
+	.id = X1E80100_SLAVE_USB_NOC_SNOC,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_USB_NOC_SNOC },
+};
+
+static struct qcom_icc_node qns_aggre_usb_north_snoc = {
+	.name = "qns_aggre_usb_north_snoc",
+	.id = X1E80100_SLAVE_AGGRE_USB_NORTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_AGGRE_USB_NORTH },
+};
+
+static struct qcom_icc_node qns_aggre_usb_south_snoc = {
+	.name = "qns_aggre_usb_south_snoc",
+	.id = X1E80100_SLAVE_AGGRE_USB_SOUTH,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_AGGRE_USB_SOUTH },
+};
+
+static struct qcom_icc_node qns_llcc_disp = {
+	.name = "qns_llcc_disp",
+	.id = X1E80100_SLAVE_LLCC_DISP,
+	.channels = 8,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LLCC_DISP },
+};
+
+static struct qcom_icc_node ebi_disp = {
+	.name = "ebi_disp",
+	.id = X1E80100_SLAVE_EBI1_DISP,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_mem_noc_hf_disp = {
+	.name = "qns_mem_noc_hf_disp",
+	.id = X1E80100_SLAVE_MNOC_HF_MEM_NOC_DISP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_MNOC_HF_MEM_NOC_DISP },
+};
+
+static struct qcom_icc_node qns_llcc_pcie = {
+	.name = "qns_llcc_pcie",
+	.id = X1E80100_SLAVE_LLCC_PCIE,
+	.channels = 8,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_LLCC_PCIE },
+};
+
+static struct qcom_icc_node ebi_pcie = {
+	.name = "ebi_pcie",
+	.id = X1E80100_SLAVE_EBI1_PCIE,
+	.channels = 8,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_pcie_mem_noc_pcie = {
+	.name = "qns_pcie_mem_noc_pcie",
+	.id = X1E80100_SLAVE_ANOC_PCIE_GEM_NOC_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_ANOC_PCIE_GEM_NOC_PCIE },
+};
+
+static struct qcom_icc_node qns_pcie_north_gem_noc_pcie = {
+	.name = "qns_pcie_north_gem_noc_pcie",
+	.id = X1E80100_SLAVE_PCIE_NORTH_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_PCIE_NORTH_PCIE },
+};
+
+static struct qcom_icc_node qns_pcie_south_gem_noc_pcie = {
+	.name = "qns_pcie_south_gem_noc_pcie",
+	.id = X1E80100_SLAVE_PCIE_SOUTH_PCIE,
+	.channels = 1,
+	.buswidth = 64,
+	.num_links = 1,
+	.links = { X1E80100_MASTER_PCIE_SOUTH_PCIE },
+};
+
+static struct qcom_icc_bcm bcm_acv = {
+	.name = "ACV",
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_acv_perf = {
+	.name = "ACV_PERF",
+	.num_nodes = 1,
+	.nodes = { &ddr_perf_mode_slave },
+};
+
+static struct qcom_icc_bcm bcm_ce0 = {
+	.name = "CE0",
+	.num_nodes = 1,
+	.nodes = { &qxm_crypto },
+};
+
+static struct qcom_icc_bcm bcm_cn0 = {
+	.name = "CN0",
+	.keepalive = true,
+	.num_nodes = 63,
+	.nodes = { &qsm_cfg, &qhs_ahb2phy0,
+		   &qhs_ahb2phy1, &qhs_ahb2phy2,
+		   &qhs_av1_enc_cfg, &qhs_camera_cfg,
+		   &qhs_clk_ctl, &qhs_crypto0_cfg,
+		   &qhs_gpuss_cfg, &qhs_imem_cfg,
+		   &qhs_ipc_router, &qhs_pcie0_cfg,
+		   &qhs_pcie1_cfg, &qhs_pcie2_cfg,
+		   &qhs_pcie3_cfg, &qhs_pcie4_cfg,
+		   &qhs_pcie5_cfg, &qhs_pcie6a_cfg,
+		   &qhs_pcie6b_cfg, &qhs_pcie_rsc_cfg,
+		   &qhs_pdm, &qhs_prng,
+		   &qhs_qdss_cfg, &qhs_qspi,
+		   &qhs_qup0, &qhs_qup1,
+		   &qhs_qup2, &qhs_sdc2,
+		   &qhs_sdc4, &qhs_smmuv3_cfg,
+		   &qhs_tcsr, &qhs_tlmm,
+		   &qhs_ufs_mem_cfg, &qhs_usb2_0_cfg,
+		   &qhs_usb3_0_cfg, &qhs_usb3_1_cfg,
+		   &qhs_usb3_2_cfg, &qhs_usb3_mp_cfg,
+		   &qhs_usb4_0_cfg, &qhs_usb4_1_cfg,
+		   &qhs_usb4_2_cfg, &qhs_venus_cfg,
+		   &qss_lpass_qtb_cfg, &qss_mnoc_cfg,
+		   &qss_nsp_qtb_cfg, &xs_qdss_stm,
+		   &xs_sys_tcu_cfg, &qnm_gemnoc_cnoc,
+		   &qnm_gemnoc_pcie, &qhs_aoss,
+		   &qhs_tme_cfg, &qns_apss,
+		   &qss_cfg, &qxs_boot_imem,
+		   &qxs_imem, &xs_pcie_0,
+		   &xs_pcie_1, &xs_pcie_2,
+		   &xs_pcie_3, &xs_pcie_4,
+		   &xs_pcie_5, &xs_pcie_6a,
+		   &xs_pcie_6b },
+};
+
+static struct qcom_icc_bcm bcm_cn1 = {
+	.name = "CN1",
+	.num_nodes = 1,
+	.nodes = { &qhs_display_cfg },
+};
+
+static struct qcom_icc_bcm bcm_co0 = {
+	.name = "CO0",
+	.num_nodes = 2,
+	.nodes = { &qxm_nsp, &qns_nsp_gemnoc },
+};
+
+static struct qcom_icc_bcm bcm_lp0 = {
+	.name = "LP0",
+	.num_nodes = 2,
+	.nodes = { &qnm_lpass_lpinoc, &qns_lpass_aggnoc },
+};
+
+static struct qcom_icc_bcm bcm_mc0 = {
+	.name = "MC0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_mm0 = {
+	.name = "MM0",
+	.num_nodes = 1,
+	.nodes = { &qns_mem_noc_hf },
+};
+
+static struct qcom_icc_bcm bcm_mm1 = {
+	.name = "MM1",
+	.num_nodes = 10,
+	.nodes = { &qnm_av1_enc, &qnm_camnoc_hf,
+		   &qnm_camnoc_icp, &qnm_camnoc_sf,
+		   &qnm_eva, &qnm_mdp,
+		   &qnm_video, &qnm_video_cv_cpu,
+		   &qnm_video_v_cpu, &qns_mem_noc_sf },
+};
+
+static struct qcom_icc_bcm bcm_pc0 = {
+	.name = "PC0",
+	.num_nodes = 1,
+	.nodes = { &qns_pcie_mem_noc },
+};
+
+static struct qcom_icc_bcm bcm_qup0 = {
+	.name = "QUP0",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup0_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup1 = {
+	.name = "QUP1",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup1_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup2 = {
+	.name = "QUP2",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup2_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_sh0 = {
+	.name = "SH0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_llcc },
+};
+
+static struct qcom_icc_bcm bcm_sh1 = {
+	.name = "SH1",
+	.num_nodes = 13,
+	.nodes = { &alm_gpu_tcu, &alm_pcie_tcu,
+		   &alm_sys_tcu, &chm_apps,
+		   &qnm_gpu, &qnm_lpass,
+		   &qnm_mnoc_hf, &qnm_mnoc_sf,
+		   &qnm_nsp_noc, &qnm_pcie,
+		   &xm_gic, &qns_gem_noc_cnoc,
+		   &qns_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sn0 = {
+	.name = "SN0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_gemnoc_sf },
+};
+
+static struct qcom_icc_bcm bcm_sn2 = {
+	.name = "SN2",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre1_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn3 = {
+	.name = "SN3",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre2_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn4 = {
+	.name = "SN4",
+	.num_nodes = 1,
+	.nodes = { &qnm_usb_anoc },
+};
+
+static struct qcom_icc_bcm bcm_acv_disp = {
+	.name = "ACV",
+	.num_nodes = 1,
+	.nodes = { &ebi_disp },
+};
+
+static struct qcom_icc_bcm bcm_mc0_disp = {
+	.name = "MC0",
+	.num_nodes = 1,
+	.nodes = { &ebi_disp },
+};
+
+static struct qcom_icc_bcm bcm_mm0_disp = {
+	.name = "MM0",
+	.num_nodes = 1,
+	.nodes = { &qns_mem_noc_hf_disp },
+};
+
+static struct qcom_icc_bcm bcm_mm1_disp = {
+	.name = "MM1",
+	.num_nodes = 1,
+	.nodes = { &qnm_mdp_disp },
+};
+
+static struct qcom_icc_bcm bcm_sh0_disp = {
+	.name = "SH0",
+	.num_nodes = 1,
+	.nodes = { &qns_llcc_disp },
+};
+
+static struct qcom_icc_bcm bcm_sh1_disp = {
+	.name = "SH1",
+	.num_nodes = 2,
+	.nodes = { &qnm_mnoc_hf_disp, &qnm_pcie_disp },
+};
+
+static struct qcom_icc_bcm bcm_acv_pcie = {
+	.name = "ACV",
+	.num_nodes = 1,
+	.nodes = { &ebi_pcie },
+};
+
+static struct qcom_icc_bcm bcm_mc0_pcie = {
+	.name = "MC0",
+	.num_nodes = 1,
+	.nodes = { &ebi_pcie },
+};
+
+static struct qcom_icc_bcm bcm_pc0_pcie = {
+	.name = "PC0",
+	.num_nodes = 1,
+	.nodes = { &qns_pcie_mem_noc_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sh0_pcie = {
+	.name = "SH0",
+	.num_nodes = 1,
+	.nodes = { &qns_llcc_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sh1_pcie = {
+	.name = "SH1",
+	.num_nodes = 1,
+	.nodes = { &qnm_pcie_pcie },
+};
+
+static struct qcom_icc_bcm *aggre1_noc_bcms[] = {
+};
+
+static struct qcom_icc_node * const aggre1_noc_nodes[] = {
+	[MASTER_QSPI_0] = &qhm_qspi,
+	[MASTER_QUP_1] = &qhm_qup1,
+	[MASTER_SDCC_4] = &xm_sdc4,
+	[MASTER_UFS_MEM] = &xm_ufs_mem,
+	[SLAVE_A1NOC_SNOC] = &qns_a1noc_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_aggre1_noc = {
+	.nodes = aggre1_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre1_noc_nodes),
+	.bcms = aggre1_noc_bcms,
+	.num_bcms = ARRAY_SIZE(aggre1_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const aggre2_noc_bcms[] = {
+	&bcm_ce0,
+};
+
+static struct qcom_icc_node * const aggre2_noc_nodes[] = {
+	[MASTER_QUP_0] = &qhm_qup0,
+	[MASTER_QUP_2] = &qhm_qup2,
+	[MASTER_CRYPTO] = &qxm_crypto,
+	[MASTER_SP] = &qxm_sp,
+	[MASTER_QDSS_ETR] = &xm_qdss_etr_0,
+	[MASTER_QDSS_ETR_1] = &xm_qdss_etr_1,
+	[MASTER_SDCC_2] = &xm_sdc2,
+	[SLAVE_A2NOC_SNOC] = &qns_a2noc_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_aggre2_noc = {
+	.nodes = aggre2_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre2_noc_nodes),
+	.bcms = aggre2_noc_bcms,
+	.num_bcms = ARRAY_SIZE(aggre2_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const clk_virt_bcms[] = {
+	&bcm_acv_perf,
+	&bcm_qup0,
+	&bcm_qup1,
+	&bcm_qup2,
+};
+
+static struct qcom_icc_node * const clk_virt_nodes[] = {
+	[MASTER_DDR_PERF_MODE] = &ddr_perf_mode_master,
+	[MASTER_QUP_CORE_0] = &qup0_core_master,
+	[MASTER_QUP_CORE_1] = &qup1_core_master,
+	[MASTER_QUP_CORE_2] = &qup2_core_master,
+	[SLAVE_DDR_PERF_MODE] = &ddr_perf_mode_slave,
+	[SLAVE_QUP_CORE_0] = &qup0_core_slave,
+	[SLAVE_QUP_CORE_1] = &qup1_core_slave,
+	[SLAVE_QUP_CORE_2] = &qup2_core_slave,
+};
+
+static const struct qcom_icc_desc x1e80100_clk_virt = {
+	.nodes = clk_virt_nodes,
+	.num_nodes = ARRAY_SIZE(clk_virt_nodes),
+	.bcms = clk_virt_bcms,
+	.num_bcms = ARRAY_SIZE(clk_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const cnoc_cfg_bcms[] = {
+	&bcm_cn0,
+	&bcm_cn1,
+};
+
+static struct qcom_icc_node * const cnoc_cfg_nodes[] = {
+	[MASTER_CNOC_CFG] = &qsm_cfg,
+	[SLAVE_AHB2PHY_SOUTH] = &qhs_ahb2phy0,
+	[SLAVE_AHB2PHY_NORTH] = &qhs_ahb2phy1,
+	[SLAVE_AHB2PHY_2] = &qhs_ahb2phy2,
+	[SLAVE_AV1_ENC_CFG] = &qhs_av1_enc_cfg,
+	[SLAVE_CAMERA_CFG] = &qhs_camera_cfg,
+	[SLAVE_CLK_CTL] = &qhs_clk_ctl,
+	[SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg,
+	[SLAVE_DISPLAY_CFG] = &qhs_display_cfg,
+	[SLAVE_GFX3D_CFG] = &qhs_gpuss_cfg,
+	[SLAVE_IMEM_CFG] = &qhs_imem_cfg,
+	[SLAVE_IPC_ROUTER_CFG] = &qhs_ipc_router,
+	[SLAVE_PCIE_0_CFG] = &qhs_pcie0_cfg,
+	[SLAVE_PCIE_1_CFG] = &qhs_pcie1_cfg,
+	[SLAVE_PCIE_2_CFG] = &qhs_pcie2_cfg,
+	[SLAVE_PCIE_3_CFG] = &qhs_pcie3_cfg,
+	[SLAVE_PCIE_4_CFG] = &qhs_pcie4_cfg,
+	[SLAVE_PCIE_5_CFG] = &qhs_pcie5_cfg,
+	[SLAVE_PCIE_6A_CFG] = &qhs_pcie6a_cfg,
+	[SLAVE_PCIE_6B_CFG] = &qhs_pcie6b_cfg,
+	[SLAVE_PCIE_RSC_CFG] = &qhs_pcie_rsc_cfg,
+	[SLAVE_PDM] = &qhs_pdm,
+	[SLAVE_PRNG] = &qhs_prng,
+	[SLAVE_QDSS_CFG] = &qhs_qdss_cfg,
+	[SLAVE_QSPI_0] = &qhs_qspi,
+	[SLAVE_QUP_0] = &qhs_qup0,
+	[SLAVE_QUP_1] = &qhs_qup1,
+	[SLAVE_QUP_2] = &qhs_qup2,
+	[SLAVE_SDCC_2] = &qhs_sdc2,
+	[SLAVE_SDCC_4] = &qhs_sdc4,
+	[SLAVE_SMMUV3_CFG] = &qhs_smmuv3_cfg,
+	[SLAVE_TCSR] = &qhs_tcsr,
+	[SLAVE_TLMM] = &qhs_tlmm,
+	[SLAVE_UFS_MEM_CFG] = &qhs_ufs_mem_cfg,
+	[SLAVE_USB2] = &qhs_usb2_0_cfg,
+	[SLAVE_USB3_0] = &qhs_usb3_0_cfg,
+	[SLAVE_USB3_1] = &qhs_usb3_1_cfg,
+	[SLAVE_USB3_2] = &qhs_usb3_2_cfg,
+	[SLAVE_USB3_MP] = &qhs_usb3_mp_cfg,
+	[SLAVE_USB4_0] = &qhs_usb4_0_cfg,
+	[SLAVE_USB4_1] = &qhs_usb4_1_cfg,
+	[SLAVE_USB4_2] = &qhs_usb4_2_cfg,
+	[SLAVE_VENUS_CFG] = &qhs_venus_cfg,
+	[SLAVE_LPASS_QTB_CFG] = &qss_lpass_qtb_cfg,
+	[SLAVE_CNOC_MNOC_CFG] = &qss_mnoc_cfg,
+	[SLAVE_NSP_QTB_CFG] = &qss_nsp_qtb_cfg,
+	[SLAVE_QDSS_STM] = &xs_qdss_stm,
+	[SLAVE_TCU] = &xs_sys_tcu_cfg,
+};
+
+static const struct qcom_icc_desc x1e80100_cnoc_cfg = {
+	.nodes = cnoc_cfg_nodes,
+	.num_nodes = ARRAY_SIZE(cnoc_cfg_nodes),
+	.bcms = cnoc_cfg_bcms,
+	.num_bcms = ARRAY_SIZE(cnoc_cfg_bcms),
+};
+
+static struct qcom_icc_bcm * const cnoc_main_bcms[] = {
+	&bcm_cn0,
+};
+
+static struct qcom_icc_node * const cnoc_main_nodes[] = {
+	[MASTER_GEM_NOC_CNOC] = &qnm_gemnoc_cnoc,
+	[MASTER_GEM_NOC_PCIE_SNOC] = &qnm_gemnoc_pcie,
+	[SLAVE_AOSS] = &qhs_aoss,
+	[SLAVE_TME_CFG] = &qhs_tme_cfg,
+	[SLAVE_APPSS] = &qns_apss,
+	[SLAVE_CNOC_CFG] = &qss_cfg,
+	[SLAVE_BOOT_IMEM] = &qxs_boot_imem,
+	[SLAVE_IMEM] = &qxs_imem,
+	[SLAVE_PCIE_0] = &xs_pcie_0,
+	[SLAVE_PCIE_1] = &xs_pcie_1,
+	[SLAVE_PCIE_2] = &xs_pcie_2,
+	[SLAVE_PCIE_3] = &xs_pcie_3,
+	[SLAVE_PCIE_4] = &xs_pcie_4,
+	[SLAVE_PCIE_5] = &xs_pcie_5,
+	[SLAVE_PCIE_6A] = &xs_pcie_6a,
+	[SLAVE_PCIE_6B] = &xs_pcie_6b,
+};
+
+static const struct qcom_icc_desc x1e80100_cnoc_main = {
+	.nodes = cnoc_main_nodes,
+	.num_nodes = ARRAY_SIZE(cnoc_main_nodes),
+	.bcms = cnoc_main_bcms,
+	.num_bcms = ARRAY_SIZE(cnoc_main_bcms),
+};
+
+static struct qcom_icc_bcm * const gem_noc_bcms[] = {
+	&bcm_sh0,
+	&bcm_sh1,
+	&bcm_sh0_disp,
+	&bcm_sh1_disp,
+	&bcm_sh0_pcie,
+	&bcm_sh1_pcie,
+};
+
+static struct qcom_icc_node * const gem_noc_nodes[] = {
+	[MASTER_GPU_TCU] = &alm_gpu_tcu,
+	[MASTER_PCIE_TCU] = &alm_pcie_tcu,
+	[MASTER_SYS_TCU] = &alm_sys_tcu,
+	[MASTER_APPSS_PROC] = &chm_apps,
+	[MASTER_GFX3D] = &qnm_gpu,
+	[MASTER_LPASS_GEM_NOC] = &qnm_lpass,
+	[MASTER_MNOC_HF_MEM_NOC] = &qnm_mnoc_hf,
+	[MASTER_MNOC_SF_MEM_NOC] = &qnm_mnoc_sf,
+	[MASTER_COMPUTE_NOC] = &qnm_nsp_noc,
+	[MASTER_ANOC_PCIE_GEM_NOC] = &qnm_pcie,
+	[MASTER_SNOC_SF_MEM_NOC] = &qnm_snoc_sf,
+	[MASTER_GIC2] = &xm_gic,
+	[SLAVE_GEM_NOC_CNOC] = &qns_gem_noc_cnoc,
+	[SLAVE_LLCC] = &qns_llcc,
+	[SLAVE_MEM_NOC_PCIE_SNOC] = &qns_pcie,
+	[MASTER_MNOC_HF_MEM_NOC_DISP] = &qnm_mnoc_hf_disp,
+	[MASTER_ANOC_PCIE_GEM_NOC_DISP] = &qnm_pcie_disp,
+	[SLAVE_LLCC_DISP] = &qns_llcc_disp,
+	[MASTER_ANOC_PCIE_GEM_NOC_PCIE] = &qnm_pcie_pcie,
+	[SLAVE_LLCC_PCIE] = &qns_llcc_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_gem_noc = {
+	.nodes = gem_noc_nodes,
+	.num_nodes = ARRAY_SIZE(gem_noc_nodes),
+	.bcms = gem_noc_bcms,
+	.num_bcms = ARRAY_SIZE(gem_noc_bcms),
+};
+
+static struct qcom_icc_bcm *lpass_ag_noc_bcms[] = {
+};
+
+static struct qcom_icc_node * const lpass_ag_noc_nodes[] = {
+	[MASTER_LPIAON_NOC] = &qnm_lpiaon_noc,
+	[SLAVE_LPASS_GEM_NOC] = &qns_lpass_ag_noc_gemnoc,
+};
+
+static const struct qcom_icc_desc x1e80100_lpass_ag_noc = {
+	.nodes = lpass_ag_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_ag_noc_nodes),
+	.bcms = lpass_ag_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_ag_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const lpass_lpiaon_noc_bcms[] = {
+	&bcm_lp0,
+};
+
+static struct qcom_icc_node * const lpass_lpiaon_noc_nodes[] = {
+	[MASTER_LPASS_LPINOC] = &qnm_lpass_lpinoc,
+	[SLAVE_LPIAON_NOC_LPASS_AG_NOC] = &qns_lpass_aggnoc,
+};
+
+static const struct qcom_icc_desc x1e80100_lpass_lpiaon_noc = {
+	.nodes = lpass_lpiaon_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpiaon_noc_nodes),
+	.bcms = lpass_lpiaon_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_lpiaon_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const lpass_lpicx_noc_bcms[] = {
+};
+
+static struct qcom_icc_node * const lpass_lpicx_noc_nodes[] = {
+	[MASTER_LPASS_PROC] = &qxm_lpinoc_dsp_axim,
+	[SLAVE_LPICX_NOC_LPIAON_NOC] = &qns_lpi_aon_noc,
+};
+
+static const struct qcom_icc_desc x1e80100_lpass_lpicx_noc = {
+	.nodes = lpass_lpicx_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpicx_noc_nodes),
+	.bcms = lpass_lpicx_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_lpicx_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const mc_virt_bcms[] = {
+	&bcm_acv,
+	&bcm_mc0,
+	&bcm_acv_disp,
+	&bcm_mc0_disp,
+	&bcm_acv_pcie,
+	&bcm_mc0_pcie,
+};
+
+static struct qcom_icc_node * const mc_virt_nodes[] = {
+	[MASTER_LLCC] = &llcc_mc,
+	[SLAVE_EBI1] = &ebi,
+	[MASTER_LLCC_DISP] = &llcc_mc_disp,
+	[SLAVE_EBI1_DISP] = &ebi_disp,
+	[MASTER_LLCC_PCIE] = &llcc_mc_pcie,
+	[SLAVE_EBI1_PCIE] = &ebi_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_mc_virt = {
+	.nodes = mc_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mc_virt_nodes),
+	.bcms = mc_virt_bcms,
+	.num_bcms = ARRAY_SIZE(mc_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const mmss_noc_bcms[] = {
+	&bcm_mm0,
+	&bcm_mm1,
+	&bcm_mm0_disp,
+	&bcm_mm1_disp,
+};
+
+static struct qcom_icc_node * const mmss_noc_nodes[] = {
+	[MASTER_AV1_ENC] = &qnm_av1_enc,
+	[MASTER_CAMNOC_HF] = &qnm_camnoc_hf,
+	[MASTER_CAMNOC_ICP] = &qnm_camnoc_icp,
+	[MASTER_CAMNOC_SF] = &qnm_camnoc_sf,
+	[MASTER_EVA] = &qnm_eva,
+	[MASTER_MDP] = &qnm_mdp,
+	[MASTER_VIDEO] = &qnm_video,
+	[MASTER_VIDEO_CV_PROC] = &qnm_video_cv_cpu,
+	[MASTER_VIDEO_V_PROC] = &qnm_video_v_cpu,
+	[MASTER_CNOC_MNOC_CFG] = &qsm_mnoc_cfg,
+	[SLAVE_MNOC_HF_MEM_NOC] = &qns_mem_noc_hf,
+	[SLAVE_MNOC_SF_MEM_NOC] = &qns_mem_noc_sf,
+	[SLAVE_SERVICE_MNOC] = &srvc_mnoc,
+	[MASTER_MDP_DISP] = &qnm_mdp_disp,
+	[SLAVE_MNOC_HF_MEM_NOC_DISP] = &qns_mem_noc_hf_disp,
+};
+
+static const struct qcom_icc_desc x1e80100_mmss_noc = {
+	.nodes = mmss_noc_nodes,
+	.num_nodes = ARRAY_SIZE(mmss_noc_nodes),
+	.bcms = mmss_noc_bcms,
+	.num_bcms = ARRAY_SIZE(mmss_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const nsp_noc_bcms[] = {
+	&bcm_co0,
+};
+
+static struct qcom_icc_node * const nsp_noc_nodes[] = {
+	[MASTER_CDSP_PROC] = &qxm_nsp,
+	[SLAVE_CDSP_MEM_NOC] = &qns_nsp_gemnoc,
+};
+
+static const struct qcom_icc_desc x1e80100_nsp_noc = {
+	.nodes = nsp_noc_nodes,
+	.num_nodes = ARRAY_SIZE(nsp_noc_nodes),
+	.bcms = nsp_noc_bcms,
+	.num_bcms = ARRAY_SIZE(nsp_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const pcie_center_anoc_bcms[] = {
+	&bcm_pc0,
+	&bcm_pc0_pcie,
+};
+
+static struct qcom_icc_node * const pcie_center_anoc_nodes[] = {
+	[MASTER_PCIE_NORTH] = &qnm_pcie_north_gem_noc,
+	[MASTER_PCIE_SOUTH] = &qnm_pcie_south_gem_noc,
+	[SLAVE_ANOC_PCIE_GEM_NOC] = &qns_pcie_mem_noc,
+	[MASTER_PCIE_NORTH_PCIE] = &qnm_pcie_north_gem_noc_pcie,
+	[MASTER_PCIE_SOUTH_PCIE] = &qnm_pcie_south_gem_noc_pcie,
+	[SLAVE_ANOC_PCIE_GEM_NOC_PCIE] = &qns_pcie_mem_noc_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_pcie_center_anoc = {
+	.nodes = pcie_center_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_center_anoc_nodes),
+	.bcms = pcie_center_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_center_anoc_bcms),
+};
+
+static struct qcom_icc_bcm * const pcie_north_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const pcie_north_anoc_nodes[] = {
+	[MASTER_PCIE_3] = &xm_pcie_3,
+	[MASTER_PCIE_4] = &xm_pcie_4,
+	[MASTER_PCIE_5] = &xm_pcie_5,
+	[SLAVE_PCIE_NORTH] = &qns_pcie_north_gem_noc,
+	[MASTER_PCIE_3_PCIE] = &xm_pcie_3_pcie,
+	[MASTER_PCIE_4_PCIE] = &xm_pcie_4_pcie,
+	[MASTER_PCIE_5_PCIE] = &xm_pcie_5_pcie,
+	[SLAVE_PCIE_NORTH_PCIE] = &qns_pcie_north_gem_noc_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_pcie_north_anoc = {
+	.nodes = pcie_north_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_north_anoc_nodes),
+	.bcms = pcie_north_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_north_anoc_bcms),
+};
+
+static struct qcom_icc_bcm *pcie_south_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const pcie_south_anoc_nodes[] = {
+	[MASTER_PCIE_0] = &xm_pcie_0,
+	[MASTER_PCIE_1] = &xm_pcie_1,
+	[MASTER_PCIE_2] = &xm_pcie_2,
+	[MASTER_PCIE_6A] = &xm_pcie_6a,
+	[MASTER_PCIE_6B] = &xm_pcie_6b,
+	[SLAVE_PCIE_SOUTH] = &qns_pcie_south_gem_noc,
+	[MASTER_PCIE_0_PCIE] = &xm_pcie_0_pcie,
+	[MASTER_PCIE_1_PCIE] = &xm_pcie_1_pcie,
+	[MASTER_PCIE_2_PCIE] = &xm_pcie_2_pcie,
+	[MASTER_PCIE_6A_PCIE] = &xm_pcie_6a_pcie,
+	[MASTER_PCIE_6B_PCIE] = &xm_pcie_6b_pcie,
+	[SLAVE_PCIE_SOUTH_PCIE] = &qns_pcie_south_gem_noc_pcie,
+};
+
+static const struct qcom_icc_desc x1e80100_pcie_south_anoc = {
+	.nodes = pcie_south_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_south_anoc_nodes),
+	.bcms = pcie_south_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_south_anoc_bcms),
+};
+
+static struct qcom_icc_bcm *system_noc_bcms[] = {
+	&bcm_sn0,
+	&bcm_sn2,
+	&bcm_sn3,
+	&bcm_sn4,
+};
+
+static struct qcom_icc_node * const system_noc_nodes[] = {
+	[MASTER_A1NOC_SNOC] = &qnm_aggre1_noc,
+	[MASTER_A2NOC_SNOC] = &qnm_aggre2_noc,
+	[MASTER_GIC1] = &qnm_gic,
+	[MASTER_USB_NOC_SNOC] = &qnm_usb_anoc,
+	[SLAVE_SNOC_GEM_NOC_SF] = &qns_gemnoc_sf,
+};
+
+static const struct qcom_icc_desc x1e80100_system_noc = {
+	.nodes = system_noc_nodes,
+	.num_nodes = ARRAY_SIZE(system_noc_nodes),
+	.bcms = system_noc_bcms,
+	.num_bcms = ARRAY_SIZE(system_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const usb_center_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const usb_center_anoc_nodes[] = {
+	[MASTER_AGGRE_USB_NORTH] = &qnm_aggre_usb_north_snoc,
+	[MASTER_AGGRE_USB_SOUTH] = &qnm_aggre_usb_south_snoc,
+	[SLAVE_USB_NOC_SNOC] = &qns_aggre_usb_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_usb_center_anoc = {
+	.nodes = usb_center_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(usb_center_anoc_nodes),
+	.bcms = usb_center_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(usb_center_anoc_bcms),
+};
+
+static struct qcom_icc_bcm *usb_north_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const usb_north_anoc_nodes[] = {
+	[MASTER_USB2] = &xm_usb2_0,
+	[MASTER_USB3_MP] = &xm_usb3_mp,
+	[SLAVE_AGGRE_USB_NORTH] = &qns_aggre_usb_north_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_usb_north_anoc = {
+	.nodes = usb_north_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(usb_north_anoc_nodes),
+	.bcms = usb_north_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(usb_north_anoc_bcms),
+};
+
+static struct qcom_icc_bcm *usb_south_anoc_bcms[] = {
+};
+
+static struct qcom_icc_node * const usb_south_anoc_nodes[] = {
+	[MASTER_USB3_0] = &xm_usb3_0,
+	[MASTER_USB3_1] = &xm_usb3_1,
+	[MASTER_USB3_2] = &xm_usb3_2,
+	[MASTER_USB4_0] = &xm_usb4_0,
+	[MASTER_USB4_1] = &xm_usb4_1,
+	[MASTER_USB4_2] = &xm_usb4_2,
+	[SLAVE_AGGRE_USB_SOUTH] = &qns_aggre_usb_south_snoc,
+};
+
+static const struct qcom_icc_desc x1e80100_usb_south_anoc = {
+	.nodes = usb_south_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(usb_south_anoc_nodes),
+	.bcms = usb_south_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(usb_south_anoc_bcms),
+};
+
+static const struct of_device_id qnoc_of_match[] = {
+	{ .compatible = "qcom,x1e80100-aggre1-noc", .data = &x1e80100_aggre1_noc},
+	{ .compatible = "qcom,x1e80100-aggre2-noc", .data = &x1e80100_aggre2_noc},
+	{ .compatible = "qcom,x1e80100-clk-virt", .data = &x1e80100_clk_virt},
+	{ .compatible = "qcom,x1e80100-cnoc-cfg", .data = &x1e80100_cnoc_cfg},
+	{ .compatible = "qcom,x1e80100-cnoc-main", .data = &x1e80100_cnoc_main},
+	{ .compatible = "qcom,x1e80100-gem-noc", .data = &x1e80100_gem_noc},
+	{ .compatible = "qcom,x1e80100-lpass-ag-noc", .data = &x1e80100_lpass_ag_noc},
+	{ .compatible = "qcom,x1e80100-lpass-lpiaon-noc", .data = &x1e80100_lpass_lpiaon_noc},
+	{ .compatible = "qcom,x1e80100-lpass-lpicx-noc", .data = &x1e80100_lpass_lpicx_noc},
+	{ .compatible = "qcom,x1e80100-mc-virt", .data = &x1e80100_mc_virt},
+	{ .compatible = "qcom,x1e80100-mmss-noc", .data = &x1e80100_mmss_noc},
+	{ .compatible = "qcom,x1e80100-nsp-noc", .data = &x1e80100_nsp_noc},
+	{ .compatible = "qcom,x1e80100-pcie-center-anoc", .data = &x1e80100_pcie_center_anoc},
+	{ .compatible = "qcom,x1e80100-pcie-north-anoc", .data = &x1e80100_pcie_north_anoc},
+	{ .compatible = "qcom,x1e80100-pcie-south-anoc", .data = &x1e80100_pcie_south_anoc},
+	{ .compatible = "qcom,x1e80100-system-noc", .data = &x1e80100_system_noc},
+	{ .compatible = "qcom,x1e80100-usb-center-anoc", .data = &x1e80100_usb_center_anoc},
+	{ .compatible = "qcom,x1e80100-usb-north-anoc", .data = &x1e80100_usb_north_anoc},
+	{ .compatible = "qcom,x1e80100-usb-south-anoc", .data = &x1e80100_usb_south_anoc},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qnoc_of_match);
+
+static struct platform_driver qnoc_driver = {
+	.probe = qcom_icc_rpmh_probe,
+	.remove_new = qcom_icc_rpmh_remove,
+	.driver = {
+		.name = "qnoc-x1e80100",
+		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
+	},
+};
+
+static int __init qnoc_driver_init(void)
+{
+	return platform_driver_register(&qnoc_driver);
+}
+core_initcall(qnoc_driver_init);
+
+static void __exit qnoc_driver_exit(void)
+{
+	platform_driver_unregister(&qnoc_driver);
+}
+module_exit(qnoc_driver_exit);
+
+MODULE_DESCRIPTION("x1e80100 NoC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/interconnect/qcom/x1e80100.h b/drivers/interconnect/qcom/x1e80100.h
new file mode 100644
index 0000000000000..2e14264f4c2b0
--- /dev/null
+++ b/drivers/interconnect/qcom/x1e80100.h
@@ -0,0 +1,192 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * X1E80100 interconnect IDs
+ *
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DRIVERS_INTERCONNECT_QCOM_X1E80100_H
+#define __DRIVERS_INTERCONNECT_QCOM_X1E80100_H
+
+#define X1E80100_MASTER_A1NOC_SNOC			0
+#define X1E80100_MASTER_A2NOC_SNOC			1
+#define X1E80100_MASTER_ANOC_PCIE_GEM_NOC		2
+#define X1E80100_MASTER_ANOC_PCIE_GEM_NOC_DISP		3
+#define X1E80100_MASTER_APPSS_PROC			4
+#define X1E80100_MASTER_CAMNOC_HF			5
+#define X1E80100_MASTER_CAMNOC_ICP			6
+#define X1E80100_MASTER_CAMNOC_SF			7
+#define X1E80100_MASTER_CDSP_PROC			8
+#define X1E80100_MASTER_CNOC_CFG			9
+#define X1E80100_MASTER_CNOC_MNOC_CFG			10
+#define X1E80100_MASTER_COMPUTE_NOC			11
+#define X1E80100_MASTER_CRYPTO				12
+#define X1E80100_MASTER_GEM_NOC_CNOC			13
+#define X1E80100_MASTER_GEM_NOC_PCIE_SNOC		14
+#define X1E80100_MASTER_GFX3D				15
+#define X1E80100_MASTER_GPU_TCU				16
+#define X1E80100_MASTER_IPA				17
+#define X1E80100_MASTER_LLCC				18
+#define X1E80100_MASTER_LLCC_DISP			19
+#define X1E80100_MASTER_LPASS_GEM_NOC			20
+#define X1E80100_MASTER_LPASS_LPINOC			21
+#define X1E80100_MASTER_LPASS_PROC			22
+#define X1E80100_MASTER_LPIAON_NOC			23
+#define X1E80100_MASTER_MDP				24
+#define X1E80100_MASTER_MDP_DISP			25
+#define X1E80100_MASTER_MNOC_HF_MEM_NOC			26
+#define X1E80100_MASTER_MNOC_HF_MEM_NOC_DISP		27
+#define X1E80100_MASTER_MNOC_SF_MEM_NOC			28
+#define X1E80100_MASTER_PCIE_0				29
+#define X1E80100_MASTER_PCIE_1				30
+#define X1E80100_MASTER_QDSS_ETR			31
+#define X1E80100_MASTER_QDSS_ETR_1			32
+#define X1E80100_MASTER_QSPI_0				33
+#define X1E80100_MASTER_QUP_0				34
+#define X1E80100_MASTER_QUP_1				35
+#define X1E80100_MASTER_QUP_2				36
+#define X1E80100_MASTER_QUP_CORE_0			37
+#define X1E80100_MASTER_QUP_CORE_1			38
+#define X1E80100_MASTER_SDCC_2				39
+#define X1E80100_MASTER_SDCC_4				40
+#define X1E80100_MASTER_SNOC_SF_MEM_NOC			41
+#define X1E80100_MASTER_SP				42
+#define X1E80100_MASTER_SYS_TCU				43
+#define X1E80100_MASTER_UFS_MEM				44
+#define X1E80100_MASTER_USB3_0				45
+#define X1E80100_MASTER_VIDEO				46
+#define X1E80100_MASTER_VIDEO_CV_PROC			47
+#define X1E80100_MASTER_VIDEO_V_PROC			48
+#define X1E80100_SLAVE_A1NOC_SNOC			49
+#define X1E80100_SLAVE_A2NOC_SNOC			50
+#define X1E80100_SLAVE_AHB2PHY_NORTH			51
+#define X1E80100_SLAVE_AHB2PHY_SOUTH			52
+#define X1E80100_SLAVE_ANOC_PCIE_GEM_NOC		53
+#define X1E80100_SLAVE_AOSS				54
+#define X1E80100_SLAVE_APPSS				55
+#define X1E80100_SLAVE_BOOT_IMEM			56
+#define X1E80100_SLAVE_CAMERA_CFG			57
+#define X1E80100_SLAVE_CDSP_MEM_NOC			58
+#define X1E80100_SLAVE_CLK_CTL				59
+#define X1E80100_SLAVE_CNOC_CFG				60
+#define X1E80100_SLAVE_CNOC_MNOC_CFG			61
+#define X1E80100_SLAVE_CRYPTO_0_CFG			62
+#define X1E80100_SLAVE_DISPLAY_CFG			63
+#define X1E80100_SLAVE_EBI1				64
+#define X1E80100_SLAVE_EBI1_DISP			65
+#define X1E80100_SLAVE_GEM_NOC_CNOC			66
+#define X1E80100_SLAVE_GFX3D_CFG			67
+#define X1E80100_SLAVE_IMEM				68
+#define X1E80100_SLAVE_IMEM_CFG				69
+#define X1E80100_SLAVE_IPC_ROUTER_CFG			70
+#define X1E80100_SLAVE_LLCC				71
+#define X1E80100_SLAVE_LLCC_DISP			72
+#define X1E80100_SLAVE_LPASS_GEM_NOC			73
+#define X1E80100_SLAVE_LPASS_QTB_CFG			74
+#define X1E80100_SLAVE_LPIAON_NOC_LPASS_AG_NOC		75
+#define X1E80100_SLAVE_LPICX_NOC_LPIAON_NOC		76
+#define X1E80100_SLAVE_MEM_NOC_PCIE_SNOC		77
+#define X1E80100_SLAVE_MNOC_HF_MEM_NOC			78
+#define X1E80100_SLAVE_MNOC_HF_MEM_NOC_DISP		79
+#define X1E80100_SLAVE_MNOC_SF_MEM_NOC			80
+#define X1E80100_SLAVE_NSP_QTB_CFG			81
+#define X1E80100_SLAVE_PCIE_0				82
+#define X1E80100_SLAVE_PCIE_0_CFG			83
+#define X1E80100_SLAVE_PCIE_1				84
+#define X1E80100_SLAVE_PCIE_1_CFG			85
+#define X1E80100_SLAVE_PDM				86
+#define X1E80100_SLAVE_PRNG				87
+#define X1E80100_SLAVE_QDSS_CFG				88
+#define X1E80100_SLAVE_QDSS_STM				89
+#define X1E80100_SLAVE_QSPI_0				90
+#define X1E80100_SLAVE_QUP_1				91
+#define X1E80100_SLAVE_QUP_2				92
+#define X1E80100_SLAVE_QUP_CORE_0			93
+#define X1E80100_SLAVE_QUP_CORE_1			94
+#define X1E80100_SLAVE_QUP_CORE_2			95
+#define X1E80100_SLAVE_SDCC_2				96
+#define X1E80100_SLAVE_SDCC_4				97
+#define X1E80100_SLAVE_SERVICE_MNOC			98
+#define X1E80100_SLAVE_SNOC_GEM_NOC_SF			99
+#define X1E80100_SLAVE_TCSR				100
+#define X1E80100_SLAVE_TCU				101
+#define X1E80100_SLAVE_TLMM				102
+#define X1E80100_SLAVE_TME_CFG				103
+#define X1E80100_SLAVE_UFS_MEM_CFG			104
+#define X1E80100_SLAVE_USB3_0				105
+#define X1E80100_SLAVE_VENUS_CFG			106
+#define X1E80100_MASTER_DDR_PERF_MODE			107
+#define X1E80100_MASTER_QUP_CORE_2			108
+#define X1E80100_MASTER_PCIE_TCU			109
+#define X1E80100_MASTER_GIC2				110
+#define X1E80100_MASTER_AV1_ENC				111
+#define X1E80100_MASTER_EVA				112
+#define X1E80100_MASTER_PCIE_NORTH			113
+#define X1E80100_MASTER_PCIE_SOUTH			114
+#define X1E80100_MASTER_PCIE_3				115
+#define X1E80100_MASTER_PCIE_4				116
+#define X1E80100_MASTER_PCIE_5				117
+#define X1E80100_MASTER_PCIE_2				118
+#define X1E80100_MASTER_PCIE_6A				119
+#define X1E80100_MASTER_PCIE_6B				120
+#define X1E80100_MASTER_GIC1				121
+#define X1E80100_MASTER_USB_NOC_SNOC			122
+#define X1E80100_MASTER_AGGRE_USB_NORTH			123
+#define X1E80100_MASTER_AGGRE_USB_SOUTH			124
+#define X1E80100_MASTER_USB2				125
+#define X1E80100_MASTER_USB3_MP				126
+#define X1E80100_MASTER_USB3_1				127
+#define X1E80100_MASTER_USB3_2				128
+#define X1E80100_MASTER_USB4_0				129
+#define X1E80100_MASTER_USB4_1				130
+#define X1E80100_MASTER_USB4_2				131
+#define X1E80100_MASTER_ANOC_PCIE_GEM_NOC_PCIE		132
+#define X1E80100_MASTER_LLCC_PCIE			133
+#define X1E80100_MASTER_PCIE_NORTH_PCIE			134
+#define X1E80100_MASTER_PCIE_SOUTH_PCIE			135
+#define X1E80100_MASTER_PCIE_3_PCIE			136
+#define X1E80100_MASTER_PCIE_4_PCIE			137
+#define X1E80100_MASTER_PCIE_5_PCIE			138
+#define X1E80100_MASTER_PCIE_0_PCIE			139
+#define X1E80100_MASTER_PCIE_1_PCIE			140
+#define X1E80100_MASTER_PCIE_2_PCIE			141
+#define X1E80100_MASTER_PCIE_6A_PCIE			142
+#define X1E80100_MASTER_PCIE_6B_PCIE			143
+#define X1E80100_SLAVE_AHB2PHY_2			144
+#define X1E80100_SLAVE_AV1_ENC_CFG			145
+#define X1E80100_SLAVE_PCIE_2_CFG			146
+#define X1E80100_SLAVE_PCIE_3_CFG			147
+#define X1E80100_SLAVE_PCIE_4_CFG			148
+#define X1E80100_SLAVE_PCIE_5_CFG			149
+#define X1E80100_SLAVE_PCIE_6A_CFG			150
+#define X1E80100_SLAVE_PCIE_6B_CFG			151
+#define X1E80100_SLAVE_PCIE_RSC_CFG			152
+#define X1E80100_SLAVE_QUP_0				153
+#define X1E80100_SLAVE_SMMUV3_CFG			154
+#define X1E80100_SLAVE_USB2				155
+#define X1E80100_SLAVE_USB3_1				156
+#define X1E80100_SLAVE_USB3_2				157
+#define X1E80100_SLAVE_USB3_MP				158
+#define X1E80100_SLAVE_USB4_0				159
+#define X1E80100_SLAVE_USB4_1				160
+#define X1E80100_SLAVE_USB4_2				161
+#define X1E80100_SLAVE_PCIE_2				162
+#define X1E80100_SLAVE_PCIE_3				163
+#define X1E80100_SLAVE_PCIE_4				164
+#define X1E80100_SLAVE_PCIE_5				165
+#define X1E80100_SLAVE_PCIE_6A				166
+#define X1E80100_SLAVE_PCIE_6B				167
+#define X1E80100_SLAVE_DDR_PERF_MODE			168
+#define X1E80100_SLAVE_PCIE_NORTH			169
+#define X1E80100_SLAVE_PCIE_SOUTH			170
+#define X1E80100_SLAVE_USB_NOC_SNOC			171
+#define X1E80100_SLAVE_AGGRE_USB_NORTH			172
+#define X1E80100_SLAVE_AGGRE_USB_SOUTH			173
+#define X1E80100_SLAVE_LLCC_PCIE			174
+#define X1E80100_SLAVE_EBI1_PCIE			175
+#define X1E80100_SLAVE_ANOC_PCIE_GEM_NOC_PCIE		176
+#define X1E80100_SLAVE_PCIE_NORTH_PCIE			177
+#define X1E80100_SLAVE_PCIE_SOUTH_PCIE			178
+
+#endif
-- 
GitLab


From 6543ac13c623f906200dfd3f1c407d8d333b6995 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 17 Oct 2023 11:09:32 -0500
Subject: [PATCH 0402/4076] soundwire: bus: introduce controller_id

The existing SoundWire support misses a clear Controller/Manager
hiearchical definition to deal with all variants across SOC vendors.

a) Intel platforms have one controller with 4 or more Managers.
b) AMD platforms have two controllers with one Manager each, but due
to BIOS issues use two different link_id values within the scope of a
single controller.
c) QCOM platforms have one or more controller with one Manager each.

This patch adds a 'controller_id' which can be set by higher
levels. If assigned to -1, the controller_id will be set to the
system-unique IDA-assigned bus->id.

The main change is that the bus->id is no longer used for any device
name, which makes the definition completely predictable and not
dependent on any enumeration order. The bus->id is only used to insert
the Managers in the stream rt context.

Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Tested-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/stable/20231017160933.12624-2-pierre-louis.bossart%40linux.intel.com
Tested-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231017160933.12624-2-pierre-louis.bossart@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/amd_manager.c     | 8 ++++++++
 drivers/soundwire/bus.c             | 4 ++++
 drivers/soundwire/debugfs.c         | 2 +-
 drivers/soundwire/intel_auxdevice.c | 3 +++
 drivers/soundwire/master.c          | 2 +-
 drivers/soundwire/qcom.c            | 3 +++
 include/linux/soundwire/sdw.h       | 4 +++-
 7 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 3a99f6dcdfafa..a3b1f4e6f0f90 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -927,6 +927,14 @@ static int amd_sdw_manager_probe(struct platform_device *pdev)
 	amd_manager->bus.clk_stop_timeout = 200;
 	amd_manager->bus.link_id = amd_manager->instance;
 
+	/*
+	 * Due to BIOS compatibility, the two links are exposed within
+	 * the scope of a single controller. If this changes, the
+	 * controller_id will have to be updated with drv_data
+	 * information.
+	 */
+	amd_manager->bus.controller_id = 0;
+
 	switch (amd_manager->instance) {
 	case ACP_SDW0:
 		amd_manager->num_dout_ports = AMD_SDW0_MAX_TX_PORTS;
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 41b0d9adf68ef..f3fec15c31122 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -22,6 +22,10 @@ static int sdw_get_id(struct sdw_bus *bus)
 		return rc;
 
 	bus->id = rc;
+
+	if (bus->controller_id == -1)
+		bus->controller_id = rc;
+
 	return 0;
 }
 
diff --git a/drivers/soundwire/debugfs.c b/drivers/soundwire/debugfs.c
index d1553cb771874..67abd7e52f092 100644
--- a/drivers/soundwire/debugfs.c
+++ b/drivers/soundwire/debugfs.c
@@ -20,7 +20,7 @@ void sdw_bus_debugfs_init(struct sdw_bus *bus)
 		return;
 
 	/* create the debugfs master-N */
-	snprintf(name, sizeof(name), "master-%d-%d", bus->id, bus->link_id);
+	snprintf(name, sizeof(name), "master-%d-%d", bus->controller_id, bus->link_id);
 	bus->debugfs = debugfs_create_dir(name, sdw_debugfs_root);
 }
 
diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c
index 7f15e3549e539..93698532deac4 100644
--- a/drivers/soundwire/intel_auxdevice.c
+++ b/drivers/soundwire/intel_auxdevice.c
@@ -234,6 +234,9 @@ static int intel_link_probe(struct auxiliary_device *auxdev,
 	cdns->instance = sdw->instance;
 	cdns->msg_count = 0;
 
+	/* single controller for all SoundWire links */
+	bus->controller_id = 0;
+
 	bus->link_id = auxdev->id;
 	bus->clk_stop_timeout = 1;
 
diff --git a/drivers/soundwire/master.c b/drivers/soundwire/master.c
index 9b05c9e25ebe4..51abedbbaa663 100644
--- a/drivers/soundwire/master.c
+++ b/drivers/soundwire/master.c
@@ -145,7 +145,7 @@ int sdw_master_device_add(struct sdw_bus *bus, struct device *parent,
 	md->dev.fwnode = fwnode;
 	md->dev.dma_mask = parent->dma_mask;
 
-	dev_set_name(&md->dev, "sdw-master-%d", bus->id);
+	dev_set_name(&md->dev, "sdw-master-%d-%d", bus->controller_id, bus->link_id);
 
 	ret = device_register(&md->dev);
 	if (ret) {
diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index e9a52c1bd3594..7f8549aab42f3 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -1620,6 +1620,9 @@ static int qcom_swrm_probe(struct platform_device *pdev)
 		}
 	}
 
+	/* FIXME: is there a DT-defined value to use ? */
+	ctrl->bus.controller_id = -1;
+
 	ret = sdw_bus_master_add(&ctrl->bus, dev, dev->fwnode);
 	if (ret) {
 		dev_err(dev, "Failed to register Soundwire controller (%d)\n",
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 904004d8b5622..66f814b63a435 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -886,7 +886,8 @@ struct sdw_master_ops {
  * struct sdw_bus - SoundWire bus
  * @dev: Shortcut to &bus->md->dev to avoid changing the entire code.
  * @md: Master device
- * @link_id: Link id number, can be 0 to N, unique for each Master
+ * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used.
+ * @link_id: Link id number, can be 0 to N, unique for each Controller
  * @id: bus system-wide unique id
  * @slaves: list of Slaves on this bus
  * @assigned: Bitmap for Slave device numbers.
@@ -918,6 +919,7 @@ struct sdw_master_ops {
 struct sdw_bus {
 	struct device *dev;
 	struct sdw_master_device *md;
+	int controller_id;
 	unsigned int link_id;
 	int id;
 	struct list_head slaves;
-- 
GitLab


From 8a8a9ac8a4972ee69d3dd3d1ae43963ae39cee18 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 17 Oct 2023 11:09:33 -0500
Subject: [PATCH 0403/4076] soundwire: fix initializing sysfs for same devices
 on different buses

If same devices with same device IDs are present on different soundwire
buses, the probe fails due to conflicting device names and sysfs
entries:

  sysfs: cannot create duplicate filename '/bus/soundwire/devices/sdw:0:0217:0204:00:0'

The link ID is 0 for both devices, so they should be differentiated by
the controller ID. Add the controller ID so, the device names and sysfs entries look
like:

  sdw:1:0:0217:0204:00:0 -> ../../../devices/platform/soc@0/6ab0000.soundwire-controller/sdw-master-1-0/sdw:1:0:0217:0204:00:0
  sdw:3:0:0217:0204:00:0 -> ../../../devices/platform/soc@0/6b10000.soundwire-controller/sdw-master-3-0/sdw:3:0:0217:0204:00:0

[PLB changes: use bus->controller_id instead of bus->id]

Fixes: 7c3cd189b86d ("soundwire: Add Master registration")
Cc: stable@vger.kernel.org
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Co-developed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Tested-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Mark Brown <broonie@kernel.org>
Tested-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231017160933.12624-3-pierre-louis.bossart@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/slave.c        | 12 ++++++------
 sound/soc/intel/boards/sof_sdw.c |  4 ++--
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index c1c1a2ac293af..060c2982e26b0 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -39,14 +39,14 @@ int sdw_slave_add(struct sdw_bus *bus,
 	slave->dev.fwnode = fwnode;
 
 	if (id->unique_id == SDW_IGNORED_UNIQUE_ID) {
-		/* name shall be sdw:link:mfg:part:class */
-		dev_set_name(&slave->dev, "sdw:%01x:%04x:%04x:%02x",
-			     bus->link_id, id->mfg_id, id->part_id,
+		/* name shall be sdw:ctrl:link:mfg:part:class */
+		dev_set_name(&slave->dev, "sdw:%01x:%01x:%04x:%04x:%02x",
+			     bus->controller_id, bus->link_id, id->mfg_id, id->part_id,
 			     id->class_id);
 	} else {
-		/* name shall be sdw:link:mfg:part:class:unique */
-		dev_set_name(&slave->dev, "sdw:%01x:%04x:%04x:%02x:%01x",
-			     bus->link_id, id->mfg_id, id->part_id,
+		/* name shall be sdw:ctrl:link:mfg:part:class:unique */
+		dev_set_name(&slave->dev, "sdw:%01x:%01x:%04x:%04x:%02x:%01x",
+			     bus->controller_id, bus->link_id, id->mfg_id, id->part_id,
 			     id->class_id, id->unique_id);
 	}
 
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 3312ad8a563b3..690c279bbb886 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -1232,11 +1232,11 @@ static int fill_sdw_codec_dlc(struct device *dev,
 	else if (is_unique_device(adr_link, sdw_version, mfg_id, part_id,
 				  class_id, adr_index))
 		codec->name = devm_kasprintf(dev, GFP_KERNEL,
-					     "sdw:%01x:%04x:%04x:%02x", link_id,
+					     "sdw:0:%01x:%04x:%04x:%02x", link_id,
 					     mfg_id, part_id, class_id);
 	else
 		codec->name = devm_kasprintf(dev, GFP_KERNEL,
-					     "sdw:%01x:%04x:%04x:%02x:%01x", link_id,
+					     "sdw:0:%01x:%04x:%04x:%02x:%01x", link_id,
 					     mfg_id, part_id, class_id, unique_id);
 
 	if (!codec->name)
-- 
GitLab


From a7ae05ef356162c2a7ff108a7ff154d7d0dcd6aa Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Thu, 23 Nov 2023 10:53:32 +0000
Subject: [PATCH 0404/4076] soundwire: qcom: set controller id to hw master id

Qualcomm Soundwire Controllers IP version after 1.3 have a dedicated
master id register which will provide a unique id value for each
controller instance. Use this value instead of artificially generated
value from idr. Versions 1.3 and below only have one instance of
soundwire controller which does no have this register, so let them use
value from idr.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Tested-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231123105332.102167-1-srinivas.kandagatla@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/qcom.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index 7f8549aab42f3..d869e2276815c 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -1620,9 +1620,13 @@ static int qcom_swrm_probe(struct platform_device *pdev)
 		}
 	}
 
-	/* FIXME: is there a DT-defined value to use ? */
 	ctrl->bus.controller_id = -1;
 
+	if (ctrl->version > SWRM_VERSION_1_3_0) {
+		ctrl->reg_read(ctrl, SWRM_COMP_MASTER_ID, &val);
+		ctrl->bus.controller_id = val;
+	}
+
 	ret = sdw_bus_master_add(&ctrl->bus, dev, dev->fwnode);
 	if (ret) {
 		dev_err(dev, "Failed to register Soundwire controller (%d)\n",
-- 
GitLab


From 904140fa45533f6d05071e24492013da16c46b7f Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 22 Nov 2023 21:04:05 +0100
Subject: [PATCH 0405/4076] dt-bindings: pinctrl: samsung: use Exynos7
 fallbacks for newer wake-up controllers

Older ARM8 SoCs like Exynos5433, Exynos7 and Exynos7885 have the pin
controller with wake-up interrupts muxed, thus the wake-up interrupt
controller device node has interrupts property, while its pin banks
might not (because they are muxed by the wake-up controller).

Newer SoCs like Exynos850 and ExynosAutov9 do not used muxed wake-up
interrupts:
1. Wake-up interrupt controller device node has no interrupts,
2. Its pin banks have interrupts (since there is no muxing).

Their programming interface is however still compatible with Exynos7,
thus change the bindings to express this: retain compatibility with
Exynos7 and add new compatibility fallback of Exynos850 in newer
designs.

No driver changes are needed.  This is necessary only to properly
describe DTS.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Jaewon Kim <jaewon02.kim@samsung.com>
Link: https://lore.kernel.org/r/20231122200407.423264-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../samsung,pinctrl-wakeup-interrupt.yaml     | 25 +++++++++++--------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 1b75abebb9530..2bafa867aea24 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -36,13 +36,17 @@ properties:
           - samsung,s5pv210-wakeup-eint
           - samsung,exynos4210-wakeup-eint
           - samsung,exynos7-wakeup-eint
-          - samsung,exynos850-wakeup-eint
-          - samsung,exynosautov9-wakeup-eint
-          - samsung,exynosautov920-wakeup-eint
       - items:
           - enum:
               - samsung,exynos5433-wakeup-eint
               - samsung,exynos7885-wakeup-eint
+              - samsung,exynos850-wakeup-eint
+          - const: samsung,exynos7-wakeup-eint
+      - items:
+          - enum:
+              - samsung,exynosautov9-wakeup-eint
+              - samsung,exynosautov920-wakeup-eint
+          - const: samsung,exynos850-wakeup-eint
           - const: samsung,exynos7-wakeup-eint
 
   interrupts:
@@ -86,11 +90,14 @@ allOf:
   - if:
       properties:
         compatible:
-          contains:
-            enum:
-              - samsung,s5pv210-wakeup-eint
-              - samsung,exynos4210-wakeup-eint
-              - samsung,exynos7-wakeup-eint
+          # Match without "contains", to skip newer variants which are still
+          # compatible with samsung,exynos7-wakeup-eint
+          enum:
+            - samsung,s5pv210-wakeup-eint
+            - samsung,exynos4210-wakeup-eint
+            - samsung,exynos5433-wakeup-eint
+            - samsung,exynos7-wakeup-eint
+            - samsung,exynos7885-wakeup-eint
     then:
       properties:
         interrupts:
@@ -105,8 +112,6 @@ allOf:
           contains:
             enum:
               - samsung,exynos850-wakeup-eint
-              - samsung,exynosautov9-wakeup-eint
-              - samsung,exynosautov920-wakeup-eint
     then:
       properties:
         interrupts: false
-- 
GitLab


From aaf7b392347bc4b32ffcab11c414d983a782e651 Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Fri, 24 Nov 2023 10:27:19 +0530
Subject: [PATCH 0406/4076] dt-bindings: dma: ti: k3-*: Add descriptions for
 register regions

In preparation for introducing more register regions, add description
for existing register regions so that its easier to map reg-names to
that of SoC Documentations/TRMs.

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231124045722.191817-2-vigneshr@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/dma/ti/k3-bcdma.yaml   | 18 +++++++++++++++---
 .../devicetree/bindings/dma/ti/k3-pktdma.yaml  |  6 +++++-
 .../devicetree/bindings/dma/ti/k3-udma.yaml    |  5 ++++-
 3 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index 4ca300a42a99c..11727af9df734 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
@@ -141,7 +141,10 @@ allOf:
         ti,sci-rm-range-tchan: false
 
         reg:
-          maxItems: 3
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: RX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
 
         reg-names:
           items:
@@ -160,7 +163,12 @@ allOf:
     then:
       properties:
         reg:
-          minItems: 5
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: Block Copy Channel Realtime Registers region
+            - description: RX Channel Realtime Registers region
+            - description: TX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
 
         reg-names:
           items:
@@ -184,7 +192,11 @@ allOf:
         ti,sci-rm-range-bchan: false
 
         reg:
-          maxItems: 4
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: RX Channel Realtime Registers region
+            - description: TX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
 
         reg-names:
           items:
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
index a69f62f854d8c..3580b08f65c68 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
@@ -45,7 +45,11 @@ properties:
       The second cell is the ASEL value for the channel
 
   reg:
-    maxItems: 4
+    items:
+      - description: Packet DMA Control /Status Registers region
+      - description: RX Channel Realtime Registers region
+      - description: TX Channel Realtime Registers region
+      - description: Ring Realtime Registers region
 
   reg-names:
     items:
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
index 22f6c5e2f7f4b..ded588bd079a1 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
@@ -69,7 +69,10 @@ properties:
       - ti,j721e-navss-mcu-udmap
 
   reg:
-    maxItems: 3
+    items:
+      - description: UDMA-P Control /Status Registers region
+      - description: RX Channel Realtime Registers region
+      - description: TX Channel Realtime Registers region
 
   reg-names:
     items:
-- 
GitLab


From f04470678132c2d044b92befab39a933ac4d106c Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Fri, 24 Nov 2023 10:27:20 +0530
Subject: [PATCH 0407/4076] dt-bindings: dma: ti: k3-bcdma: Describe cfg
 register regions

Block copy DMA(BCDMA)module on K3 SoCs have ring, BCHAN, TX and RX
channel cfg register regions which are usually configured by a Device
Management firmware. But certain entities such as bootloader (like
U-Boot) may have to access them directly. Describe this region in the
binding documentation for completeness of module description.

Keep the binding compatible with existing DTS files by requiring first
five regions to be present at least.

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231124045722.191817-3-vigneshr@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/dma/ti/k3-bcdma.yaml  | 23 +++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index 11727af9df734..27b8e16365600 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
@@ -37,11 +37,11 @@ properties:
 
   reg:
     minItems: 3
-    maxItems: 5
+    maxItems: 9
 
   reg-names:
     minItems: 3
-    maxItems: 5
+    maxItems: 9
 
   "#dma-cells":
     const: 3
@@ -163,20 +163,30 @@ allOf:
     then:
       properties:
         reg:
+          minItems: 5
           items:
             - description: BCDMA Control /Status Registers region
             - description: Block Copy Channel Realtime Registers region
             - description: RX Channel Realtime Registers region
             - description: TX Channel Realtime Registers region
             - description: Ring Realtime Registers region
+            - description: Ring Configuration Registers region
+            - description: TX Channel Configuration Registers region
+            - description: RX Channel Configuration Registers region
+            - description: Block Copy Channel Configuration Registers region
 
         reg-names:
+          minItems: 5
           items:
             - const: gcfg
             - const: bchanrt
             - const: rchanrt
             - const: tchanrt
             - const: ringrt
+            - const: ring
+            - const: tchan
+            - const: rchan
+            - const: bchan
 
       required:
         - ti,sci-rm-range-bchan
@@ -232,8 +242,13 @@ examples:
                       <0x0 0x4c000000 0x0 0x20000>,
                       <0x0 0x4a820000 0x0 0x20000>,
                       <0x0 0x4aa40000 0x0 0x20000>,
-                      <0x0 0x4bc00000 0x0 0x100000>;
-                reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt";
+                      <0x0 0x4bc00000 0x0 0x100000>,
+                      <0x0 0x48600000 0x0 0x8000>,
+                      <0x0 0x484a4000 0x0 0x2000>,
+                      <0x0 0x484c2000 0x0 0x2000>,
+                      <0x0 0x48420000 0x0 0x2000>;
+                reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt",
+                            "ring", "tchan", "rchan", "bchan";
                 msi-parent = <&inta_main_dmss>;
                 #dma-cells = <3>;
 
-- 
GitLab


From 8d75e0e5eed23e4f8ced5eacae3255e498a1c304 Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Fri, 24 Nov 2023 10:27:21 +0530
Subject: [PATCH 0408/4076] dt-bindings: dma: ti: k3-pktdma: Describe cfg
 register regions

Packet DMA (PKTDMA) module on K3 SoCs have ring cfg, TX and RX channel
cfg and RX flow cfg register regions which are usually configured by a
Device Management firmware. But certain entities such as bootloader
(like U-Boot) may have to access them directly. Describe this region in
the binding documentation for completeness of module description.

Keep the binding compatible with existing DTS files by requiring first
four regions to be present at least.

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231124045722.191817-4-vigneshr@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/dma/ti/k3-pktdma.yaml | 20 +++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
index 3580b08f65c68..11e064c029946 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
@@ -45,18 +45,28 @@ properties:
       The second cell is the ASEL value for the channel
 
   reg:
+    minItems: 4
     items:
       - description: Packet DMA Control /Status Registers region
       - description: RX Channel Realtime Registers region
       - description: TX Channel Realtime Registers region
       - description: Ring Realtime Registers region
+      - description: Ring Configuration Registers region
+      - description: TX Configuration Registers region
+      - description: RX Configuration Registers region
+      - description: RX Flow Configuration Registers region
 
   reg-names:
+    minItems: 4
     items:
       - const: gcfg
       - const: rchanrt
       - const: tchanrt
       - const: ringrt
+      - const: ring
+      - const: tchan
+      - const: rchan
+      - const: rflow
 
   msi-parent: true
 
@@ -140,8 +150,14 @@ examples:
                 reg = <0x0 0x485c0000 0x0 0x100>,
                       <0x0 0x4a800000 0x0 0x20000>,
                       <0x0 0x4aa00000 0x0 0x40000>,
-                      <0x0 0x4b800000 0x0 0x400000>;
-                reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+                      <0x0 0x4b800000 0x0 0x400000>,
+                      <0x0 0x485e0000 0x0 0x20000>,
+                      <0x0 0x484a0000 0x0 0x4000>,
+                      <0x0 0x484c0000 0x0 0x2000>,
+                      <0x0 0x48430000 0x0 0x4000>;
+                reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt",
+                            "ring", "tchan", "rchan", "rflow";
+
                 msi-parent = <&inta_main_dmss>;
                 #dma-cells = <2>;
 
-- 
GitLab


From d7aaccd3beb1ec34b04b13fa236f50efb77c8d6c Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Fri, 24 Nov 2023 10:27:22 +0530
Subject: [PATCH 0409/4076] dt-bindings: dma: ti: k3-udma: Describe cfg
 register regions

Unified DMA (UDMA) module on K3 SoCs have TX and RX channel cfg and RX
flow cfg register regions which are usually configured by a Device
Management firmware. But certain entities such as bootloader (like
U-Boot) may have to access them directly. Describe this region in the
binding documentation for completeness of module description.

Keep the binding compatible with existing DTS files by requiring first
four regions to be present at least.

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231124045722.191817-5-vigneshr@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/dma/ti/k3-udma.yaml       | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
index ded588bd079a1..b18cf2bfdb5b1 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
@@ -69,16 +69,24 @@ properties:
       - ti,j721e-navss-mcu-udmap
 
   reg:
+    minItems: 3
     items:
       - description: UDMA-P Control /Status Registers region
       - description: RX Channel Realtime Registers region
       - description: TX Channel Realtime Registers region
+      - description: TX Configuration Registers region
+      - description: RX Configuration Registers region
+      - description: RX Flow Configuration Registers region
 
   reg-names:
+    minItems: 3
     items:
       - const: gcfg
       - const: rchanrt
       - const: tchanrt
+      - const: tchan
+      - const: rchan
+      - const: rflow
 
   msi-parent: true
 
@@ -161,8 +169,11 @@ examples:
                 compatible = "ti,am654-navss-main-udmap";
                 reg = <0x0 0x31150000 0x0 0x100>,
                       <0x0 0x34000000 0x0 0x100000>,
-                      <0x0 0x35000000 0x0 0x100000>;
-                reg-names = "gcfg", "rchanrt", "tchanrt";
+                      <0x0 0x35000000 0x0 0x100000>,
+                      <0x0 0x30b00000 0x0 0x20000>,
+                      <0x0 0x30c00000 0x0 0x8000>,
+                      <0x0 0x30d00000 0x0 0x4000>;
+                reg-names = "gcfg", "rchanrt", "tchanrt", "tchan", "rchan", "rflow";
                 #dma-cells = <1>;
 
                 ti,ringacc = <&ringacc>;
-- 
GitLab


From 5a002bf206508169dd9d8c002d6326e51f53b42c Mon Sep 17 00:00:00 2001
From: Sergey Shtylyov <s.shtylyov@omp.ru>
Date: Wed, 15 Nov 2023 23:34:53 +0300
Subject: [PATCH 0410/4076] pinctrl: stm32: return errors from
 stm32_gpio_direction_output()

In the STMicroelectronics STM32 driver, stm32_gpio_direction_output()
ignores the result of pinctrl_gpio_direction_output() for no good reason.
Let's propagate errors from pinctrl_gpio_direction_output() upstream...

Found by Linux Verification Center (linuxtesting.org) with the Svace static
analysis tool.

Signed-off-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Link: https://lore.kernel.org/r/5ce023a8-db0c-13a9-be42-09e3348ca44d@omp.ru
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/stm32/pinctrl-stm32.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 64e8201c7eacd..2f2b777fcf4fa 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -240,9 +240,8 @@ static int stm32_gpio_direction_output(struct gpio_chip *chip,
 	struct stm32_gpio_bank *bank = gpiochip_get_data(chip);
 
 	__stm32_gpio_set(bank, offset, value);
-	pinctrl_gpio_direction_output(chip, offset);
 
-	return 0;
+	return pinctrl_gpio_direction_output(chip, offset);
 }
 
 
-- 
GitLab


From a6059c8603bc90746bf0df930ff78013b4c789fe Mon Sep 17 00:00:00 2001
From: Tomer Maimon <tmaimon77@gmail.com>
Date: Wed, 15 Nov 2023 13:12:09 -0800
Subject: [PATCH 0411/4076] pinctrl: npcm7xx: prevent glitch when setting the
 GPIO to output high

Enable GPIO output after setting the output value to prevent a glitch
when pinctrl driver sets gpio pin to output high and the pin is in
the default state (high->low->high).

Signed-off-by: Tomer Maimon <tmaimon77@gmail.com>
Signed-off-by: William A. Kennington III <william@wkennington.com>
Link: https://lore.kernel.org/r/20231115211209.1683449-1-william@wkennington.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
index 1e658721aaba5..62a46d824b465 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
@@ -1790,8 +1790,8 @@ static int npcm7xx_config_set_one(struct npcm7xx_pinctrl *npcm,
 		bank->direction_input(&bank->gc, pin % bank->gc.ngpio);
 		break;
 	case PIN_CONFIG_OUTPUT:
-		iowrite32(gpio, bank->base + NPCM7XX_GP_N_OES);
 		bank->direction_output(&bank->gc, pin % bank->gc.ngpio, arg);
+		iowrite32(gpio, bank->base + NPCM7XX_GP_N_OES);
 		break;
 	case PIN_CONFIG_DRIVE_PUSH_PULL:
 		npcm_gpio_clr(&bank->gc, bank->base + NPCM7XX_GP_N_OTYP, gpio);
-- 
GitLab


From 5180f4fa499eb78f45e2d4ee0883c6483884f4df Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <quic_rjendra@quicinc.com>
Date: Fri, 17 Nov 2023 15:09:20 +0530
Subject: [PATCH 0412/4076] dt-bindings: pinctrl: qcom: Add X1E80100 pinctrl

Add device tree binding Documentation details for Qualcomm X1E80100 TLMM
device.

Signed-off-by: Rajendra Nayak <quic_rjendra@quicinc.com>
Co-developed-by: Sibi Sankar <quic_sibis@quicinc.com>
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231117093921.31968-2-quic_sibis@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,x1e80100-tlmm.yaml  | 143 ++++++++++++++++++
 1 file changed, 143 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
new file mode 100644
index 0000000000000..2bde8845a31ef
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
@@ -0,0 +1,143 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,x1e80100-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. X1E80100 TLMM block
+
+maintainers:
+  - Rajendra Nayak <quic_rjendra@quicinc.com>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm X1E80100 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,x1e80100-tlmm
+
+  reg:
+    maxItems: 1
+
+  interrupts: true
+  interrupt-controller: true
+  "#interrupt-cells": true
+  gpio-controller: true
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 119
+
+  gpio-line-names:
+    maxItems: 238
+
+  "#gpio-cells": true
+  gpio-ranges: true
+  wakeup-parent: true
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-x1e80100-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-x1e80100-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-x1e80100-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-2][0-9]|23[0-7])$"
+            - enum: [ ufs_reset, sdc2_clk, sdc2_cmd, sdc2_data ]
+        minItems: 1
+        maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ aon_cci, aoss_cti, atest_char, atest_char0,
+                atest_char1, atest_char2, atest_char3, atest_usb,
+                audio_ext, audio_ref, cam_aon, cam_mclk, cci_async,
+                cci_i2c, cci_timer0, cci_timer1, cci_timer2, cci_timer3,
+                cci_timer4, cmu_rng0, cmu_rng1, cmu_rng2, cmu_rng3,
+                cri_trng, dbg_out, ddr_bist, ddr_pxi0, ddr_pxi1,
+                ddr_pxi2, ddr_pxi3, ddr_pxi4, ddr_pxi5, ddr_pxi6, ddr_pxi7,
+                edp0_hot, edp0_lcd, edp1_hot, edp1_lcd, eusb0_ac, eusb1_ac,
+                eusb2_ac, eusb3_ac, eusb5_ac, eusb6_ac, gcc_gp1, gcc_gp2,
+                gcc_gp3, gpio, i2s0_data0, i2s0_data1, i2s0_sck, i2s0_ws, i2s1_data0,
+                i2s1_data1, i2s1_sck, i2s1_ws, ibi_i3c, jitter_bist, mdp_vsync0,
+                mdp_vsync1, mdp_vsync2, mdp_vsync3, mdp_vsync4, mdp_vsync5,
+                mdp_vsync6, mdp_vsync7, mdp_vsync8, pcie3_clk, pcie4_clk,
+                pcie5_clk, pcie6a_clk, pcie6b_clk, phase_flag, pll_bist, pll_clk,
+                prng_rosc0, prng_rosc1, prng_rosc2, prng_rosc3, qdss_cti,
+                qdss_gpio, qspi00, qspi01, qspi02, qspi03, qspi0_clk, qspi0_cs0,
+                qspi0_cs1, qup0_se0, qup0_se1, qup0_se2, qup0_se3, qup0_se4,
+                qup0_se5, qup0_se6, qup0_se7, qup1_se0, qup1_se1, qup1_se2, qup1_se3,
+                qup1_se4, qup1_se5, qup1_se6, qup1_se7, qup2_se0, qup2_se1, qup2_se2,
+                qup2_se3, qup2_se4, qup2_se5, qup2_se6, qup2_se7, sd_write, sdc4_clk,
+                sdc4_cmd, sdc4_data0, sdc4_data1, sdc4_data2, sdc4_data3, sys_throttle,
+                tb_trig, tgu_ch0, tgu_ch1, tgu_ch2, tgu_ch3, tgu_ch4, tgu_ch5,
+                tgu_ch6, tgu_ch7, tmess_prng0, tmess_prng1, tmess_prng2, tmess_prng3,
+                tsense_pwm1, tsense_pwm2, sense_pwm3, tsense_pwm4, usb0_dp, usb0_phy,
+                usb0_sbrx, usb0_sbtx, usb1_dp, usb1_phy, usb1_sbrx, usb1_sbtx,
+                usb2_dp, usb2_phy, usb2_sbrx, usb2_sbtx, vsense_trigger ]
+
+    required:
+      - pins
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    tlmm: pinctrl@f100000 {
+        compatible = "qcom,x1e80100-tlmm";
+        reg = <0x0f100000 0xf00000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 239>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-wo-state {
+            pins = "gpio1";
+            function = "gpio";
+        };
+
+        uart-w-state {
+            rx-pins {
+                pins = "gpio26";
+                function = "qup2_se7";
+                bias-pull-up;
+            };
+
+            tx-pins {
+                pins = "gpio27";
+                function = "qup2_se7";
+                bias-disable;
+            };
+        };
+    };
+...
-- 
GitLab


From 05e4941d97ef05ddaa742a57301daab8a2f7db5b Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <quic_rjendra@quicinc.com>
Date: Fri, 17 Nov 2023 15:09:21 +0530
Subject: [PATCH 0413/4076] pinctrl: qcom: Add X1E80100 pinctrl driver

Add initial pinctrl driver to support pin configuration with pinctrl
framework for X1E80100 SoC.

Co-developed-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Rajendra Nayak <quic_rjendra@quicinc.com>
Co-developed-by: Sibi Sankar <quic_sibis@quicinc.com>
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231117093921.31968-3-quic_sibis@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig.msm        |   10 +
 drivers/pinctrl/qcom/Makefile           |    1 +
 drivers/pinctrl/qcom/pinctrl-x1e80100.c | 1876 +++++++++++++++++++++++
 3 files changed, 1887 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-x1e80100.c

diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index 341491de406b4..87b6b70cfcd56 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -374,4 +374,14 @@ config PINCTRL_SM8650
 	  Qualcomm Technologies Inc TLMM block found on the Qualcomm
 	  Technologies Inc SM8650 platform.
 
+config PINCTRL_X1E80100
+	tristate "Qualcomm Technologies Inc X1E80100 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm Technologies Inc Top Level Mode Multiplexer block (TLMM)
+	  block found on the Qualcomm Technologies Inc X1E80100 platform.
+	  Say Y here to compile statically, or M here to compile it as a module.
+	  If unsure, say N.
+
 endif
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index 9bcc1b63e8572..fda23a83cb74f 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -62,3 +62,4 @@ obj-$(CONFIG_PINCTRL_SM8650) += pinctrl-sm8650.o
 obj-$(CONFIG_PINCTRL_SM8650_LPASS_LPI) += pinctrl-sm8650-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SC8280XP_LPASS_LPI) += pinctrl-sc8280xp-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_LPASS_LPI) += pinctrl-lpass-lpi.o
+obj-$(CONFIG_PINCTRL_X1E80100)	+= pinctrl-x1e80100.o
diff --git a/drivers/pinctrl/qcom/pinctrl-x1e80100.c b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
new file mode 100644
index 0000000000000..e30e938403574
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
@@ -0,0 +1,1876 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP("gpio" #id,	\
+			gpio##id##_pins,		\
+			ARRAY_SIZE(gpio##id##_pins)),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9			\
+		},				        \
+		.nfuncs = 10,				\
+		.ctl_reg = REG_SIZE * id,			\
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,		\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.i2c_pull_bit = 13,		\
+		.egpio_enable = 12,		\
+		.egpio_present = 11,		\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define UFS_RESET(pg_name, offset)				\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,	\
+			pg_name##_pins,			\
+			ARRAY_SIZE(pg_name##_pins)),	\
+		.ctl_reg = offset,			\
+		.io_reg = offset + 0x4,			\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+static const struct pinctrl_pin_desc x1e80100_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "GPIO_136"),
+	PINCTRL_PIN(137, "GPIO_137"),
+	PINCTRL_PIN(138, "GPIO_138"),
+	PINCTRL_PIN(139, "GPIO_139"),
+	PINCTRL_PIN(140, "GPIO_140"),
+	PINCTRL_PIN(141, "GPIO_141"),
+	PINCTRL_PIN(142, "GPIO_142"),
+	PINCTRL_PIN(143, "GPIO_143"),
+	PINCTRL_PIN(144, "GPIO_144"),
+	PINCTRL_PIN(145, "GPIO_145"),
+	PINCTRL_PIN(146, "GPIO_146"),
+	PINCTRL_PIN(147, "GPIO_147"),
+	PINCTRL_PIN(148, "GPIO_148"),
+	PINCTRL_PIN(149, "GPIO_149"),
+	PINCTRL_PIN(150, "GPIO_150"),
+	PINCTRL_PIN(151, "GPIO_151"),
+	PINCTRL_PIN(152, "GPIO_152"),
+	PINCTRL_PIN(153, "GPIO_153"),
+	PINCTRL_PIN(154, "GPIO_154"),
+	PINCTRL_PIN(155, "GPIO_155"),
+	PINCTRL_PIN(156, "GPIO_156"),
+	PINCTRL_PIN(157, "GPIO_157"),
+	PINCTRL_PIN(158, "GPIO_158"),
+	PINCTRL_PIN(159, "GPIO_159"),
+	PINCTRL_PIN(160, "GPIO_160"),
+	PINCTRL_PIN(161, "GPIO_161"),
+	PINCTRL_PIN(162, "GPIO_162"),
+	PINCTRL_PIN(163, "GPIO_163"),
+	PINCTRL_PIN(164, "GPIO_164"),
+	PINCTRL_PIN(165, "GPIO_165"),
+	PINCTRL_PIN(166, "GPIO_166"),
+	PINCTRL_PIN(167, "GPIO_167"),
+	PINCTRL_PIN(168, "GPIO_168"),
+	PINCTRL_PIN(169, "GPIO_169"),
+	PINCTRL_PIN(170, "GPIO_170"),
+	PINCTRL_PIN(171, "GPIO_171"),
+	PINCTRL_PIN(172, "GPIO_172"),
+	PINCTRL_PIN(173, "GPIO_173"),
+	PINCTRL_PIN(174, "GPIO_174"),
+	PINCTRL_PIN(175, "GPIO_175"),
+	PINCTRL_PIN(176, "GPIO_176"),
+	PINCTRL_PIN(177, "GPIO_177"),
+	PINCTRL_PIN(178, "GPIO_178"),
+	PINCTRL_PIN(179, "GPIO_179"),
+	PINCTRL_PIN(180, "GPIO_180"),
+	PINCTRL_PIN(181, "GPIO_181"),
+	PINCTRL_PIN(182, "GPIO_182"),
+	PINCTRL_PIN(183, "GPIO_183"),
+	PINCTRL_PIN(184, "GPIO_184"),
+	PINCTRL_PIN(185, "GPIO_185"),
+	PINCTRL_PIN(186, "GPIO_186"),
+	PINCTRL_PIN(187, "GPIO_187"),
+	PINCTRL_PIN(188, "GPIO_188"),
+	PINCTRL_PIN(189, "GPIO_189"),
+	PINCTRL_PIN(190, "GPIO_190"),
+	PINCTRL_PIN(191, "GPIO_191"),
+	PINCTRL_PIN(192, "GPIO_192"),
+	PINCTRL_PIN(193, "GPIO_193"),
+	PINCTRL_PIN(194, "GPIO_194"),
+	PINCTRL_PIN(195, "GPIO_195"),
+	PINCTRL_PIN(196, "GPIO_196"),
+	PINCTRL_PIN(197, "GPIO_197"),
+	PINCTRL_PIN(198, "GPIO_198"),
+	PINCTRL_PIN(199, "GPIO_199"),
+	PINCTRL_PIN(200, "GPIO_200"),
+	PINCTRL_PIN(201, "GPIO_201"),
+	PINCTRL_PIN(202, "GPIO_202"),
+	PINCTRL_PIN(203, "GPIO_203"),
+	PINCTRL_PIN(204, "GPIO_204"),
+	PINCTRL_PIN(205, "GPIO_205"),
+	PINCTRL_PIN(206, "GPIO_206"),
+	PINCTRL_PIN(207, "GPIO_207"),
+	PINCTRL_PIN(208, "GPIO_208"),
+	PINCTRL_PIN(209, "GPIO_209"),
+	PINCTRL_PIN(210, "GPIO_210"),
+	PINCTRL_PIN(211, "GPIO_211"),
+	PINCTRL_PIN(212, "GPIO_212"),
+	PINCTRL_PIN(213, "GPIO_213"),
+	PINCTRL_PIN(214, "GPIO_214"),
+	PINCTRL_PIN(215, "GPIO_215"),
+	PINCTRL_PIN(216, "GPIO_216"),
+	PINCTRL_PIN(217, "GPIO_217"),
+	PINCTRL_PIN(218, "GPIO_218"),
+	PINCTRL_PIN(219, "GPIO_219"),
+	PINCTRL_PIN(220, "GPIO_220"),
+	PINCTRL_PIN(221, "GPIO_221"),
+	PINCTRL_PIN(222, "GPIO_222"),
+	PINCTRL_PIN(223, "GPIO_223"),
+	PINCTRL_PIN(224, "GPIO_224"),
+	PINCTRL_PIN(225, "GPIO_225"),
+	PINCTRL_PIN(226, "GPIO_226"),
+	PINCTRL_PIN(227, "GPIO_227"),
+	PINCTRL_PIN(228, "GPIO_228"),
+	PINCTRL_PIN(229, "GPIO_229"),
+	PINCTRL_PIN(230, "GPIO_230"),
+	PINCTRL_PIN(231, "GPIO_231"),
+	PINCTRL_PIN(232, "GPIO_232"),
+	PINCTRL_PIN(233, "GPIO_233"),
+	PINCTRL_PIN(234, "GPIO_234"),
+	PINCTRL_PIN(235, "GPIO_235"),
+	PINCTRL_PIN(236, "GPIO_236"),
+	PINCTRL_PIN(237, "GPIO_237"),
+	PINCTRL_PIN(238, "UFS_RESET"),
+	PINCTRL_PIN(239, "SDC2_CLK"),
+	PINCTRL_PIN(240, "SDC2_CMD"),
+	PINCTRL_PIN(241, "SDC2_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+DECLARE_MSM_GPIO_PINS(136);
+DECLARE_MSM_GPIO_PINS(137);
+DECLARE_MSM_GPIO_PINS(138);
+DECLARE_MSM_GPIO_PINS(139);
+DECLARE_MSM_GPIO_PINS(140);
+DECLARE_MSM_GPIO_PINS(141);
+DECLARE_MSM_GPIO_PINS(142);
+DECLARE_MSM_GPIO_PINS(143);
+DECLARE_MSM_GPIO_PINS(144);
+DECLARE_MSM_GPIO_PINS(145);
+DECLARE_MSM_GPIO_PINS(146);
+DECLARE_MSM_GPIO_PINS(147);
+DECLARE_MSM_GPIO_PINS(148);
+DECLARE_MSM_GPIO_PINS(149);
+DECLARE_MSM_GPIO_PINS(150);
+DECLARE_MSM_GPIO_PINS(151);
+DECLARE_MSM_GPIO_PINS(152);
+DECLARE_MSM_GPIO_PINS(153);
+DECLARE_MSM_GPIO_PINS(154);
+DECLARE_MSM_GPIO_PINS(155);
+DECLARE_MSM_GPIO_PINS(156);
+DECLARE_MSM_GPIO_PINS(157);
+DECLARE_MSM_GPIO_PINS(158);
+DECLARE_MSM_GPIO_PINS(159);
+DECLARE_MSM_GPIO_PINS(160);
+DECLARE_MSM_GPIO_PINS(161);
+DECLARE_MSM_GPIO_PINS(162);
+DECLARE_MSM_GPIO_PINS(163);
+DECLARE_MSM_GPIO_PINS(164);
+DECLARE_MSM_GPIO_PINS(165);
+DECLARE_MSM_GPIO_PINS(166);
+DECLARE_MSM_GPIO_PINS(167);
+DECLARE_MSM_GPIO_PINS(168);
+DECLARE_MSM_GPIO_PINS(169);
+DECLARE_MSM_GPIO_PINS(170);
+DECLARE_MSM_GPIO_PINS(171);
+DECLARE_MSM_GPIO_PINS(172);
+DECLARE_MSM_GPIO_PINS(173);
+DECLARE_MSM_GPIO_PINS(174);
+DECLARE_MSM_GPIO_PINS(175);
+DECLARE_MSM_GPIO_PINS(176);
+DECLARE_MSM_GPIO_PINS(177);
+DECLARE_MSM_GPIO_PINS(178);
+DECLARE_MSM_GPIO_PINS(179);
+DECLARE_MSM_GPIO_PINS(180);
+DECLARE_MSM_GPIO_PINS(181);
+DECLARE_MSM_GPIO_PINS(182);
+DECLARE_MSM_GPIO_PINS(183);
+DECLARE_MSM_GPIO_PINS(184);
+DECLARE_MSM_GPIO_PINS(185);
+DECLARE_MSM_GPIO_PINS(186);
+DECLARE_MSM_GPIO_PINS(187);
+DECLARE_MSM_GPIO_PINS(188);
+DECLARE_MSM_GPIO_PINS(189);
+DECLARE_MSM_GPIO_PINS(190);
+DECLARE_MSM_GPIO_PINS(191);
+DECLARE_MSM_GPIO_PINS(192);
+DECLARE_MSM_GPIO_PINS(193);
+DECLARE_MSM_GPIO_PINS(194);
+DECLARE_MSM_GPIO_PINS(195);
+DECLARE_MSM_GPIO_PINS(196);
+DECLARE_MSM_GPIO_PINS(197);
+DECLARE_MSM_GPIO_PINS(198);
+DECLARE_MSM_GPIO_PINS(199);
+DECLARE_MSM_GPIO_PINS(200);
+DECLARE_MSM_GPIO_PINS(201);
+DECLARE_MSM_GPIO_PINS(202);
+DECLARE_MSM_GPIO_PINS(203);
+DECLARE_MSM_GPIO_PINS(204);
+DECLARE_MSM_GPIO_PINS(205);
+DECLARE_MSM_GPIO_PINS(206);
+DECLARE_MSM_GPIO_PINS(207);
+DECLARE_MSM_GPIO_PINS(208);
+DECLARE_MSM_GPIO_PINS(209);
+DECLARE_MSM_GPIO_PINS(210);
+DECLARE_MSM_GPIO_PINS(211);
+DECLARE_MSM_GPIO_PINS(212);
+DECLARE_MSM_GPIO_PINS(213);
+DECLARE_MSM_GPIO_PINS(214);
+DECLARE_MSM_GPIO_PINS(215);
+DECLARE_MSM_GPIO_PINS(216);
+DECLARE_MSM_GPIO_PINS(217);
+DECLARE_MSM_GPIO_PINS(218);
+DECLARE_MSM_GPIO_PINS(219);
+DECLARE_MSM_GPIO_PINS(220);
+DECLARE_MSM_GPIO_PINS(221);
+DECLARE_MSM_GPIO_PINS(222);
+DECLARE_MSM_GPIO_PINS(223);
+DECLARE_MSM_GPIO_PINS(224);
+DECLARE_MSM_GPIO_PINS(225);
+DECLARE_MSM_GPIO_PINS(226);
+DECLARE_MSM_GPIO_PINS(227);
+DECLARE_MSM_GPIO_PINS(228);
+DECLARE_MSM_GPIO_PINS(229);
+DECLARE_MSM_GPIO_PINS(230);
+DECLARE_MSM_GPIO_PINS(231);
+DECLARE_MSM_GPIO_PINS(232);
+DECLARE_MSM_GPIO_PINS(233);
+DECLARE_MSM_GPIO_PINS(234);
+DECLARE_MSM_GPIO_PINS(235);
+DECLARE_MSM_GPIO_PINS(236);
+DECLARE_MSM_GPIO_PINS(237);
+
+static const unsigned int ufs_reset_pins[] = { 238 };
+static const unsigned int sdc2_clk_pins[] = { 239 };
+static const unsigned int sdc2_cmd_pins[] = { 240 };
+static const unsigned int sdc2_data_pins[] = { 241 };
+
+enum x1e80100_functions {
+	msm_mux_gpio,
+	msm_mux_RESOUT_GPIO,
+	msm_mux_aon_cci,
+	msm_mux_aoss_cti,
+	msm_mux_atest_char,
+	msm_mux_atest_char0,
+	msm_mux_atest_char1,
+	msm_mux_atest_char2,
+	msm_mux_atest_char3,
+	msm_mux_atest_usb,
+	msm_mux_audio_ext,
+	msm_mux_audio_ref,
+	msm_mux_cam_aon,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async,
+	msm_mux_cci_i2c,
+	msm_mux_cci_timer0,
+	msm_mux_cci_timer1,
+	msm_mux_cci_timer2,
+	msm_mux_cci_timer3,
+	msm_mux_cci_timer4,
+	msm_mux_cmu_rng0,
+	msm_mux_cmu_rng1,
+	msm_mux_cmu_rng2,
+	msm_mux_cmu_rng3,
+	msm_mux_cri_trng,
+	msm_mux_dbg_out,
+	msm_mux_ddr_bist,
+	msm_mux_ddr_pxi0,
+	msm_mux_ddr_pxi1,
+	msm_mux_ddr_pxi2,
+	msm_mux_ddr_pxi3,
+	msm_mux_ddr_pxi4,
+	msm_mux_ddr_pxi5,
+	msm_mux_ddr_pxi6,
+	msm_mux_ddr_pxi7,
+	msm_mux_edp0_hot,
+	msm_mux_edp0_lcd,
+	msm_mux_edp1_hot,
+	msm_mux_edp1_lcd,
+	msm_mux_eusb0_ac,
+	msm_mux_eusb1_ac,
+	msm_mux_eusb2_ac,
+	msm_mux_eusb3_ac,
+	msm_mux_eusb5_ac,
+	msm_mux_eusb6_ac,
+	msm_mux_gcc_gp1,
+	msm_mux_gcc_gp2,
+	msm_mux_gcc_gp3,
+	msm_mux_i2s0_data0,
+	msm_mux_i2s0_data1,
+	msm_mux_i2s0_sck,
+	msm_mux_i2s0_ws,
+	msm_mux_i2s1_data0,
+	msm_mux_i2s1_data1,
+	msm_mux_i2s1_sck,
+	msm_mux_i2s1_ws,
+	msm_mux_ibi_i3c,
+	msm_mux_jitter_bist,
+	msm_mux_mdp_vsync0,
+	msm_mux_mdp_vsync1,
+	msm_mux_mdp_vsync2,
+	msm_mux_mdp_vsync3,
+	msm_mux_mdp_vsync4,
+	msm_mux_mdp_vsync5,
+	msm_mux_mdp_vsync6,
+	msm_mux_mdp_vsync7,
+	msm_mux_mdp_vsync8,
+	msm_mux_pcie3_clk,
+	msm_mux_pcie4_clk,
+	msm_mux_pcie5_clk,
+	msm_mux_pcie6a_clk,
+	msm_mux_pcie6b_clk,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist,
+	msm_mux_pll_clk,
+	msm_mux_prng_rosc0,
+	msm_mux_prng_rosc1,
+	msm_mux_prng_rosc2,
+	msm_mux_prng_rosc3,
+	msm_mux_qdss_cti,
+	msm_mux_qdss_gpio,
+	msm_mux_qspi00,
+	msm_mux_qspi01,
+	msm_mux_qspi02,
+	msm_mux_qspi03,
+	msm_mux_qspi0_clk,
+	msm_mux_qspi0_cs0,
+	msm_mux_qspi0_cs1,
+	msm_mux_qup0_se0,
+	msm_mux_qup0_se1,
+	msm_mux_qup0_se2,
+	msm_mux_qup0_se3,
+	msm_mux_qup0_se4,
+	msm_mux_qup0_se5,
+	msm_mux_qup0_se6,
+	msm_mux_qup0_se7,
+	msm_mux_qup1_se0,
+	msm_mux_qup1_se1,
+	msm_mux_qup1_se2,
+	msm_mux_qup1_se3,
+	msm_mux_qup1_se4,
+	msm_mux_qup1_se5,
+	msm_mux_qup1_se6,
+	msm_mux_qup1_se7,
+	msm_mux_qup2_se0,
+	msm_mux_qup2_se1,
+	msm_mux_qup2_se2,
+	msm_mux_qup2_se3,
+	msm_mux_qup2_se4,
+	msm_mux_qup2_se5,
+	msm_mux_qup2_se6,
+	msm_mux_qup2_se7,
+	msm_mux_sd_write,
+	msm_mux_sdc4_clk,
+	msm_mux_sdc4_cmd,
+	msm_mux_sdc4_data0,
+	msm_mux_sdc4_data1,
+	msm_mux_sdc4_data2,
+	msm_mux_sdc4_data3,
+	msm_mux_sys_throttle,
+	msm_mux_tb_trig,
+	msm_mux_tgu_ch0,
+	msm_mux_tgu_ch1,
+	msm_mux_tgu_ch2,
+	msm_mux_tgu_ch3,
+	msm_mux_tgu_ch4,
+	msm_mux_tgu_ch5,
+	msm_mux_tgu_ch6,
+	msm_mux_tgu_ch7,
+	msm_mux_tmess_prng0,
+	msm_mux_tmess_prng1,
+	msm_mux_tmess_prng2,
+	msm_mux_tmess_prng3,
+	msm_mux_tsense_pwm1,
+	msm_mux_tsense_pwm2,
+	msm_mux_tsense_pwm3,
+	msm_mux_tsense_pwm4,
+	msm_mux_usb0_dp,
+	msm_mux_usb0_phy,
+	msm_mux_usb0_sbrx,
+	msm_mux_usb0_sbtx,
+	msm_mux_usb1_dp,
+	msm_mux_usb1_phy,
+	msm_mux_usb1_sbrx,
+	msm_mux_usb1_sbtx,
+	msm_mux_usb2_dp,
+	msm_mux_usb2_phy,
+	msm_mux_usb2_sbrx,
+	msm_mux_usb2_sbtx,
+	msm_mux_vsense_trigger,
+	msm_mux__,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+	"gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56",
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70",
+	"gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77",
+	"gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84",
+	"gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91",
+	"gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98",
+	"gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104",
+	"gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110",
+	"gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116",
+	"gpio117", "gpio118", "gpio119", "gpio120", "gpio121", "gpio122",
+	"gpio123", "gpio124", "gpio125", "gpio126", "gpio127", "gpio128",
+	"gpio129", "gpio130", "gpio131", "gpio132", "gpio133", "gpio134",
+	"gpio135", "gpio136", "gpio137", "gpio138", "gpio139", "gpio140",
+	"gpio141", "gpio142", "gpio143", "gpio144", "gpio145", "gpio146",
+	"gpio147", "gpio148", "gpio149", "gpio150", "gpio151", "gpio152",
+	"gpio153", "gpio154", "gpio155", "gpio156", "gpio157", "gpio158",
+	"gpio159", "gpio160", "gpio161", "gpio162", "gpio163", "gpio164",
+	"gpio165", "gpio166", "gpio167", "gpio168", "gpio169", "gpio170",
+	"gpio171", "gpio172", "gpio173", "gpio174", "gpio175", "gpio176",
+	"gpio177", "gpio178", "gpio179", "gpio180", "gpio181", "gpio182",
+	"gpio183", "gpio184", "gpio185", "gpio186", "gpio187", "gpio188",
+	"gpio189", "gpio190", "gpio191", "gpio192", "gpio193", "gpio194",
+	"gpio195", "gpio196", "gpio197", "gpio198", "gpio199", "gpio200",
+	"gpio201", "gpio202", "gpio203", "gpio204", "gpio205", "gpio206",
+	"gpio207", "gpio208", "gpio209", "gpio210", "gpio211", "gpio212",
+	"gpio213", "gpio214", "gpio215", "gpio216", "gpio217", "gpio218",
+	"gpio219", "gpio220", "gpio221", "gpio222", "gpio223", "gpio224",
+	"gpio225", "gpio226", "gpio227", "gpio228", "gpio229", "gpio230",
+	"gpio231", "gpio232", "gpio233", "gpio234", "gpio235", "gpio236",
+	"gpio237",
+};
+
+static const char * const RESOUT_GPIO_groups[] = {
+	"gpio160",
+};
+
+static const char * const aon_cci_groups[] = {
+	"gpio235", "gpio236",
+};
+
+static const char * const aoss_cti_groups[] = {
+	"gpio60", "gpio61", "gpio62", "gpio63",
+};
+
+static const char * const atest_char_groups[] = {
+	"gpio181",
+};
+
+static const char * const atest_char0_groups[] = {
+	"gpio185",
+};
+
+static const char * const atest_char1_groups[] = {
+	"gpio184",
+};
+
+static const char * const atest_char2_groups[] = {
+	"gpio188",
+};
+
+static const char * const atest_char3_groups[] = {
+	"gpio182",
+};
+
+static const char * const atest_usb_groups[] = {
+	"gpio9", "gpio10", "gpio35", "gpio38", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48",
+	"gpio49", "gpio50", "gpio51", "gpio52", "gpio53", "gpio54",
+	"gpio58", "gpio59", "gpio65", "gpio66", "gpio67", "gpio72",
+	"gpio73", "gpio74", "gpio75", "gpio80", "gpio81", "gpio83",
+};
+
+static const char * const audio_ext_groups[] = {
+	"gpio134", "gpio142",
+};
+
+static const char * const audio_ref_groups[] = {
+	"gpio142",
+};
+
+static const char * const cam_aon_groups[] = {
+	"gpio100",
+};
+
+static const char * const cam_mclk_groups[] = {
+	"gpio96", "gpio97", "gpio98", "gpio99",
+};
+
+static const char * const cci_async_groups[] = {
+	"gpio111", "gpio112", "gpio113",
+};
+
+static const char * const cci_i2c_groups[] = {
+	"gpio101", "gpio102", "gpio103", "gpio104", "gpio105", "gpio106",
+};
+
+static const char * const cci_timer0_groups[] = {
+	"gpio109",
+};
+
+static const char * const cci_timer1_groups[] = {
+	"gpio110",
+};
+
+static const char * const cci_timer2_groups[] = {
+	"gpio111",
+};
+
+static const char * const cci_timer3_groups[] = {
+	"gpio112",
+};
+
+static const char * const cci_timer4_groups[] = {
+	"gpio113",
+};
+
+static const char * const cmu_rng0_groups[] = {
+	"gpio48",
+};
+
+static const char * const cmu_rng1_groups[] = {
+	"gpio47",
+};
+
+static const char * const cmu_rng2_groups[] = {
+	"gpio46",
+};
+
+static const char * const cmu_rng3_groups[] = {
+	"gpio45",
+};
+
+static const char * const cri_trng_groups[] = {
+	"gpio187",
+};
+
+static const char * const dbg_out_groups[] = {
+	"gpio51",
+};
+
+static const char * const ddr_bist_groups[] = {
+	"gpio54", "gpio55", "gpio56", "gpio57",
+};
+
+static const char * const ddr_pxi0_groups[] = {
+	"gpio9", "gpio38",
+};
+
+static const char * const ddr_pxi1_groups[] = {
+	"gpio10", "gpio41",
+};
+
+static const char * const ddr_pxi2_groups[] = {
+	"gpio42", "gpio43",
+};
+
+static const char * const ddr_pxi3_groups[] = {
+	"gpio44", "gpio45",
+};
+
+static const char * const ddr_pxi4_groups[] = {
+	"gpio46", "gpio47",
+};
+
+static const char * const ddr_pxi5_groups[] = {
+	"gpio48", "gpio49",
+};
+
+static const char * const ddr_pxi6_groups[] = {
+	"gpio50", "gpio51",
+};
+
+static const char * const ddr_pxi7_groups[] = {
+	"gpio52", "gpio53",
+};
+
+static const char * const edp0_hot_groups[] = {
+	"gpio119",
+};
+
+static const char * const edp0_lcd_groups[] = {
+	"gpio120",
+};
+
+static const char * const edp1_hot_groups[] = {
+	"gpio120",
+};
+
+static const char * const edp1_lcd_groups[] = {
+	"gpio115", "gpio119",
+};
+
+static const char * const eusb0_ac_groups[] = {
+	"gpio168",
+};
+
+static const char * const eusb1_ac_groups[] = {
+	"gpio177",
+};
+
+static const char * const eusb2_ac_groups[] = {
+	"gpio186",
+};
+
+static const char * const eusb3_ac_groups[] = {
+	"gpio169",
+};
+
+static const char * const eusb5_ac_groups[] = {
+	"gpio187",
+};
+
+static const char * const eusb6_ac_groups[] = {
+	"gpio178",
+};
+
+static const char * const gcc_gp1_groups[] = {
+	"gpio71", "gpio72",
+};
+
+static const char * const gcc_gp2_groups[] = {
+	"gpio64", "gpio73",
+};
+
+static const char * const gcc_gp3_groups[] = {
+	"gpio74", "gpio82",
+};
+
+static const char * const i2s0_data0_groups[] = {
+	"gpio136",
+};
+
+static const char * const i2s0_data1_groups[] = {
+	"gpio137",
+};
+
+static const char * const i2s0_sck_groups[] = {
+	"gpio135",
+};
+
+static const char * const i2s0_ws_groups[] = {
+	"gpio138",
+};
+
+static const char * const i2s1_data0_groups[] = {
+	"gpio140",
+};
+
+static const char * const i2s1_data1_groups[] = {
+	"gpio142",
+};
+
+static const char * const i2s1_sck_groups[] = {
+	"gpio139",
+};
+
+static const char * const i2s1_ws_groups[] = {
+	"gpio141",
+};
+
+static const char * const ibi_i3c_groups[] = {
+	"gpio0", "gpio1", "gpio32", "gpio33", "gpio36", "gpio37", "gpio68",
+	"gpio69",
+};
+
+static const char * const jitter_bist_groups[] = {
+	"gpio42",
+};
+
+static const char * const mdp_vsync0_groups[] = {
+	"gpio114",
+};
+
+static const char * const mdp_vsync1_groups[] = {
+	"gpio114",
+};
+
+static const char * const mdp_vsync2_groups[] = {
+	"gpio115",
+};
+
+static const char * const mdp_vsync3_groups[] = {
+	"gpio115",
+};
+
+static const char * const mdp_vsync4_groups[] = {
+	"gpio109",
+};
+
+static const char * const mdp_vsync5_groups[] = {
+	"gpio110",
+};
+
+static const char * const mdp_vsync6_groups[] = {
+	"gpio111",
+};
+
+static const char * const mdp_vsync7_groups[] = {
+	"gpio112",
+};
+
+static const char * const mdp_vsync8_groups[] = {
+	"gpio113",
+};
+
+static const char * const pcie3_clk_groups[] = {
+	"gpio144",
+};
+
+static const char * const pcie4_clk_groups[] = {
+	"gpio147",
+};
+
+static const char * const pcie5_clk_groups[] = {
+	"gpio150",
+};
+
+static const char * const pcie6a_clk_groups[] = {
+	"gpio153",
+};
+
+static const char * const pcie6b_clk_groups[] = {
+	"gpio156",
+};
+
+static const char * const phase_flag_groups[] = {
+	"gpio6", "gpio7", "gpio8", "gpio11", "gpio12", "gpio13",
+	"gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19",
+	"gpio20", "gpio21", "gpio22", "gpio23", "gpio24", "gpio25",
+	"gpio26", "gpio27", "gpio39", "gpio40", "gpio76", "gpio77",
+	"gpio78", "gpio181", "gpio182", "gpio184", "gpio185",
+	"gpio186", "gpio187", "gpio188",
+};
+
+static const char * const pll_bist_groups[] = {
+	"gpio28",
+};
+
+static const char * const pll_clk_groups[] = {
+	"gpio35",
+};
+
+static const char * const prng_rosc0_groups[] = {
+	"gpio186",
+};
+
+static const char * const prng_rosc1_groups[] = {
+	"gpio188",
+};
+
+static const char * const prng_rosc2_groups[] = {
+	"gpio182",
+};
+
+static const char * const prng_rosc3_groups[] = {
+	"gpio181",
+};
+
+static const char * const qdss_cti_groups[] = {
+	"gpio18", "gpio19", "gpio23", "gpio27", "gpio161", "gpio162",
+	"gpio215", "gpio217",
+};
+
+static const char * const qdss_gpio_groups[] = {
+	"gpio96", "gpio97", "gpio98", "gpio99", "gpio100", "gpio101",
+	"gpio102", "gpio103", "gpio104", "gpio105", "gpio106", "gpio107",
+	"gpio108", "gpio109", "gpio110", "gpio111", "gpio112", "gpio113",
+	"gpio219", "gpio220", "gpio221", "gpio222", "gpio223", "gpio224",
+	"gpio225", "gpio226", "gpio227", "gpio228", "gpio229", "gpio230",
+	"gpio231", "gpio232", "gpio233", "gpio234", "gpio235", "gpio236",
+};
+
+static const char * const qspi00_groups[] = {
+	"gpio128",
+};
+
+static const char * const qspi01_groups[] = {
+	"gpio129",
+};
+
+static const char * const qspi02_groups[] = {
+	"gpio130",
+};
+
+static const char * const qspi03_groups[] = {
+	"gpio131",
+};
+
+static const char * const qspi0_clk_groups[] = {
+	"gpio127",
+};
+
+static const char * const qspi0_cs0_groups[] = {
+	"gpio132",
+};
+
+static const char * const qspi0_cs1_groups[] = {
+	"gpio133",
+};
+
+static const char * const qup0_se0_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+
+static const char * const qup0_se1_groups[] = {
+	"gpio4", "gpio5", "gpio6", "gpio7",
+};
+
+static const char * const qup0_se2_groups[] = {
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio17", "gpio18", "gpio19",
+};
+
+static const char * const qup0_se3_groups[] = {
+	"gpio12", "gpio13", "gpio14", "gpio15", "gpio21", "gpio22", "gpio23",
+};
+
+static const char * const qup0_se4_groups[] = {
+	"gpio16", "gpio17", "gpio18", "gpio19",
+};
+
+static const char * const qup0_se5_groups[] = {
+	"gpio20", "gpio21", "gpio22", "gpio23",
+};
+
+static const char * const qup0_se6_groups[] = {
+	"gpio24", "gpio25", "gpio26", "gpio27",
+};
+
+static const char * const qup0_se7_groups[] = {
+	"gpio12", "gpio13", "gpio14", "gpio15",
+};
+
+static const char * const qup1_se0_groups[] = {
+	"gpio32", "gpio33", "gpio34", "gpio35",
+};
+
+static const char * const qup1_se1_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+
+static const char * const qup1_se2_groups[] = {
+	"gpio40", "gpio41", "gpio42", "gpio43", "gpio49", "gpio50", "gpio51",
+};
+
+static const char * const qup1_se3_groups[] = {
+	"gpio33", "gpio34", "gpio35", "gpio44", "gpio45", "gpio46", "gpio47",
+};
+
+static const char * const qup1_se4_groups[] = {
+	"gpio48", "gpio49", "gpio50", "gpio51",
+};
+
+static const char * const qup1_se5_groups[] = {
+	"gpio52", "gpio53", "gpio54", "gpio55",
+};
+
+static const char * const qup1_se6_groups[] = {
+	"gpio56", "gpio57", "gpio58", "gpio59",
+};
+
+static const char * const qup1_se7_groups[] = {
+	"gpio52", "gpio53", "gpio54", "gpio55",
+};
+
+static const char * const qup2_se0_groups[] = {
+	"gpio64", "gpio65", "gpio66", "gpio67",
+};
+
+static const char * const qup2_se1_groups[] = {
+	"gpio68", "gpio69", "gpio70", "gpio71",
+};
+
+static const char * const qup2_se2_groups[] = {
+	"gpio72", "gpio73", "gpio74", "gpio75", "gpio81", "gpio82", "gpio83",
+};
+
+static const char * const qup2_se3_groups[] = {
+	"gpio65", "gpio66", "gpio67", "gpio76", "gpio77", "gpio78", "gpio79",
+};
+
+static const char * const qup2_se4_groups[] = {
+	"gpio80", "gpio81", "gpio82", "gpio83",
+};
+
+static const char * const qup2_se5_groups[] = {
+	"gpio84", "gpio85", "gpio86", "gpio87",
+};
+
+static const char * const qup2_se6_groups[] = {
+	"gpio88", "gpio89", "gpio90", "gpio91",
+};
+
+static const char * const qup2_se7_groups[] = {
+	"gpio84", "gpio85", "gpio86", "gpio87",
+};
+
+static const char * const sd_write_groups[] = {
+	"gpio162",
+};
+
+static const char * const sdc4_clk_groups[] = {
+	"gpio127",
+};
+
+static const char * const sdc4_cmd_groups[] = {
+	"gpio132",
+};
+
+static const char * const sdc4_data0_groups[] = {
+	"gpio128",
+};
+
+static const char * const sdc4_data1_groups[] = {
+	"gpio129",
+};
+
+static const char * const sdc4_data2_groups[] = {
+	"gpio130",
+};
+
+static const char * const sdc4_data3_groups[] = {
+	"gpio131",
+};
+
+static const char * const sys_throttle_groups[] = {
+	"gpio39", "gpio94",
+};
+
+static const char * const tb_trig_groups[] = {
+	"gpio133", "gpio137",
+};
+
+static const char * const tgu_ch0_groups[] = {
+	"gpio81",
+};
+
+static const char * const tgu_ch1_groups[] = {
+	"gpio65",
+};
+
+static const char * const tgu_ch2_groups[] = {
+	"gpio66",
+};
+
+static const char * const tgu_ch3_groups[] = {
+	"gpio67",
+};
+
+static const char * const tgu_ch4_groups[] = {
+	"gpio68",
+};
+
+static const char * const tgu_ch5_groups[] = {
+	"gpio69",
+};
+
+static const char * const tgu_ch6_groups[] = {
+	"gpio83",
+};
+
+static const char * const tgu_ch7_groups[] = {
+	"gpio80",
+};
+
+static const char * const tmess_prng0_groups[] = {
+	"gpio92",
+};
+
+static const char * const tmess_prng1_groups[] = {
+	"gpio93",
+};
+
+static const char * const tmess_prng2_groups[] = {
+	"gpio94",
+};
+
+static const char * const tmess_prng3_groups[] = {
+	"gpio95",
+};
+
+static const char * const tsense_pwm1_groups[] = {
+	"gpio34",
+};
+
+static const char * const tsense_pwm2_groups[] = {
+	"gpio34",
+};
+
+static const char * const tsense_pwm3_groups[] = {
+	"gpio34",
+};
+
+static const char * const tsense_pwm4_groups[] = {
+	"gpio34",
+};
+
+static const char * const usb0_dp_groups[] = {
+	"gpio122",
+};
+
+static const char * const usb0_phy_groups[] = {
+	"gpio121",
+};
+
+static const char * const usb0_sbrx_groups[] = {
+	"gpio163",
+};
+
+static const char * const usb0_sbtx_groups[] = {
+	"gpio164", "gpio165",
+};
+
+static const char * const usb1_dp_groups[] = {
+	"gpio124",
+};
+
+static const char * const usb1_phy_groups[] = {
+	"gpio123",
+};
+
+static const char * const usb1_sbrx_groups[] = {
+	"gpio172",
+};
+
+static const char * const usb1_sbtx_groups[] = {
+	"gpio173", "gpio174",
+};
+
+static const char * const usb2_dp_groups[] = {
+	"gpio126",
+};
+
+static const char * const usb2_phy_groups[] = {
+	"gpio125",
+};
+
+static const char * const usb2_sbrx_groups[] = {
+	"gpio181",
+};
+
+static const char * const usb2_sbtx_groups[] = {
+	"gpio182", "gpio183",
+};
+
+static const char * const vsense_trigger_groups[] = {
+	"gpio38",
+};
+
+static const struct pinfunction x1e80100_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(RESOUT_GPIO),
+	MSM_PIN_FUNCTION(aon_cci),
+	MSM_PIN_FUNCTION(aoss_cti),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_char0),
+	MSM_PIN_FUNCTION(atest_char1),
+	MSM_PIN_FUNCTION(atest_char2),
+	MSM_PIN_FUNCTION(atest_char3),
+	MSM_PIN_FUNCTION(atest_usb),
+	MSM_PIN_FUNCTION(audio_ext),
+	MSM_PIN_FUNCTION(audio_ref),
+	MSM_PIN_FUNCTION(cam_aon),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async),
+	MSM_PIN_FUNCTION(cci_i2c),
+	MSM_PIN_FUNCTION(cci_timer0),
+	MSM_PIN_FUNCTION(cci_timer1),
+	MSM_PIN_FUNCTION(cci_timer2),
+	MSM_PIN_FUNCTION(cci_timer3),
+	MSM_PIN_FUNCTION(cci_timer4),
+	MSM_PIN_FUNCTION(cmu_rng0),
+	MSM_PIN_FUNCTION(cmu_rng1),
+	MSM_PIN_FUNCTION(cmu_rng2),
+	MSM_PIN_FUNCTION(cmu_rng3),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(dbg_out),
+	MSM_PIN_FUNCTION(ddr_bist),
+	MSM_PIN_FUNCTION(ddr_pxi0),
+	MSM_PIN_FUNCTION(ddr_pxi1),
+	MSM_PIN_FUNCTION(ddr_pxi2),
+	MSM_PIN_FUNCTION(ddr_pxi3),
+	MSM_PIN_FUNCTION(ddr_pxi4),
+	MSM_PIN_FUNCTION(ddr_pxi5),
+	MSM_PIN_FUNCTION(ddr_pxi6),
+	MSM_PIN_FUNCTION(ddr_pxi7),
+	MSM_PIN_FUNCTION(edp0_hot),
+	MSM_PIN_FUNCTION(edp0_lcd),
+	MSM_PIN_FUNCTION(edp1_hot),
+	MSM_PIN_FUNCTION(edp1_lcd),
+	MSM_PIN_FUNCTION(eusb0_ac),
+	MSM_PIN_FUNCTION(eusb1_ac),
+	MSM_PIN_FUNCTION(eusb2_ac),
+	MSM_PIN_FUNCTION(eusb3_ac),
+	MSM_PIN_FUNCTION(eusb5_ac),
+	MSM_PIN_FUNCTION(eusb6_ac),
+	MSM_PIN_FUNCTION(gcc_gp1),
+	MSM_PIN_FUNCTION(gcc_gp2),
+	MSM_PIN_FUNCTION(gcc_gp3),
+	MSM_PIN_FUNCTION(i2s0_data0),
+	MSM_PIN_FUNCTION(i2s0_data1),
+	MSM_PIN_FUNCTION(i2s0_sck),
+	MSM_PIN_FUNCTION(i2s0_ws),
+	MSM_PIN_FUNCTION(i2s1_data0),
+	MSM_PIN_FUNCTION(i2s1_data1),
+	MSM_PIN_FUNCTION(i2s1_sck),
+	MSM_PIN_FUNCTION(i2s1_ws),
+	MSM_PIN_FUNCTION(ibi_i3c),
+	MSM_PIN_FUNCTION(jitter_bist),
+	MSM_PIN_FUNCTION(mdp_vsync0),
+	MSM_PIN_FUNCTION(mdp_vsync1),
+	MSM_PIN_FUNCTION(mdp_vsync2),
+	MSM_PIN_FUNCTION(mdp_vsync3),
+	MSM_PIN_FUNCTION(mdp_vsync4),
+	MSM_PIN_FUNCTION(mdp_vsync5),
+	MSM_PIN_FUNCTION(mdp_vsync6),
+	MSM_PIN_FUNCTION(mdp_vsync7),
+	MSM_PIN_FUNCTION(mdp_vsync8),
+	MSM_PIN_FUNCTION(pcie3_clk),
+	MSM_PIN_FUNCTION(pcie4_clk),
+	MSM_PIN_FUNCTION(pcie5_clk),
+	MSM_PIN_FUNCTION(pcie6a_clk),
+	MSM_PIN_FUNCTION(pcie6b_clk),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist),
+	MSM_PIN_FUNCTION(pll_clk),
+	MSM_PIN_FUNCTION(prng_rosc0),
+	MSM_PIN_FUNCTION(prng_rosc1),
+	MSM_PIN_FUNCTION(prng_rosc2),
+	MSM_PIN_FUNCTION(prng_rosc3),
+	MSM_PIN_FUNCTION(qdss_cti),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(qspi00),
+	MSM_PIN_FUNCTION(qspi01),
+	MSM_PIN_FUNCTION(qspi02),
+	MSM_PIN_FUNCTION(qspi03),
+	MSM_PIN_FUNCTION(qspi0_clk),
+	MSM_PIN_FUNCTION(qspi0_cs0),
+	MSM_PIN_FUNCTION(qspi0_cs1),
+	MSM_PIN_FUNCTION(qup0_se0),
+	MSM_PIN_FUNCTION(qup0_se1),
+	MSM_PIN_FUNCTION(qup0_se2),
+	MSM_PIN_FUNCTION(qup0_se3),
+	MSM_PIN_FUNCTION(qup0_se4),
+	MSM_PIN_FUNCTION(qup0_se5),
+	MSM_PIN_FUNCTION(qup0_se6),
+	MSM_PIN_FUNCTION(qup0_se7),
+	MSM_PIN_FUNCTION(qup1_se0),
+	MSM_PIN_FUNCTION(qup1_se1),
+	MSM_PIN_FUNCTION(qup1_se2),
+	MSM_PIN_FUNCTION(qup1_se3),
+	MSM_PIN_FUNCTION(qup1_se4),
+	MSM_PIN_FUNCTION(qup1_se5),
+	MSM_PIN_FUNCTION(qup1_se6),
+	MSM_PIN_FUNCTION(qup1_se7),
+	MSM_PIN_FUNCTION(qup2_se0),
+	MSM_PIN_FUNCTION(qup2_se1),
+	MSM_PIN_FUNCTION(qup2_se2),
+	MSM_PIN_FUNCTION(qup2_se3),
+	MSM_PIN_FUNCTION(qup2_se4),
+	MSM_PIN_FUNCTION(qup2_se5),
+	MSM_PIN_FUNCTION(qup2_se6),
+	MSM_PIN_FUNCTION(qup2_se7),
+	MSM_PIN_FUNCTION(sd_write),
+	MSM_PIN_FUNCTION(sdc4_clk),
+	MSM_PIN_FUNCTION(sdc4_cmd),
+	MSM_PIN_FUNCTION(sdc4_data0),
+	MSM_PIN_FUNCTION(sdc4_data1),
+	MSM_PIN_FUNCTION(sdc4_data2),
+	MSM_PIN_FUNCTION(sdc4_data3),
+	MSM_PIN_FUNCTION(sys_throttle),
+	MSM_PIN_FUNCTION(tb_trig),
+	MSM_PIN_FUNCTION(tgu_ch0),
+	MSM_PIN_FUNCTION(tgu_ch1),
+	MSM_PIN_FUNCTION(tgu_ch2),
+	MSM_PIN_FUNCTION(tgu_ch3),
+	MSM_PIN_FUNCTION(tgu_ch4),
+	MSM_PIN_FUNCTION(tgu_ch5),
+	MSM_PIN_FUNCTION(tgu_ch6),
+	MSM_PIN_FUNCTION(tgu_ch7),
+	MSM_PIN_FUNCTION(tmess_prng0),
+	MSM_PIN_FUNCTION(tmess_prng1),
+	MSM_PIN_FUNCTION(tmess_prng2),
+	MSM_PIN_FUNCTION(tmess_prng3),
+	MSM_PIN_FUNCTION(tsense_pwm1),
+	MSM_PIN_FUNCTION(tsense_pwm2),
+	MSM_PIN_FUNCTION(tsense_pwm3),
+	MSM_PIN_FUNCTION(tsense_pwm4),
+	MSM_PIN_FUNCTION(usb0_dp),
+	MSM_PIN_FUNCTION(usb0_phy),
+	MSM_PIN_FUNCTION(usb0_sbrx),
+	MSM_PIN_FUNCTION(usb0_sbtx),
+	MSM_PIN_FUNCTION(usb1_dp),
+	MSM_PIN_FUNCTION(usb1_phy),
+	MSM_PIN_FUNCTION(usb1_sbrx),
+	MSM_PIN_FUNCTION(usb1_sbtx),
+	MSM_PIN_FUNCTION(usb2_dp),
+	MSM_PIN_FUNCTION(usb2_phy),
+	MSM_PIN_FUNCTION(usb2_sbrx),
+	MSM_PIN_FUNCTION(usb2_sbtx),
+	MSM_PIN_FUNCTION(vsense_trigger),
+};
+
+/*
+ * Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup x1e80100_groups[] = {
+	[0] = PINGROUP(0, qup0_se0, ibi_i3c, _, _, _, _, _, _, _),
+	[1] = PINGROUP(1, qup0_se0, ibi_i3c, _, _, _, _, _, _, _),
+	[2] = PINGROUP(2, qup0_se0, _, _, _, _, _, _, _, _),
+	[3] = PINGROUP(3, qup0_se0, _, _, _, _, _, _, _, _),
+	[4] = PINGROUP(4, qup0_se1, _, _, _, _, _, _, _, _),
+	[5] = PINGROUP(5, qup0_se1, _, _, _, _, _, _, _, _),
+	[6] = PINGROUP(6, qup0_se1, phase_flag, _, _, _, _, _, _, _),
+	[7] = PINGROUP(7, qup0_se1, phase_flag, _, _, _, _, _, _, _),
+	[8] = PINGROUP(8, qup0_se2, phase_flag, _, _, _, _, _, _, _),
+	[9] = PINGROUP(9, qup0_se2, _, atest_usb, ddr_pxi0, _, _, _, _, _),
+	[10] = PINGROUP(10, qup0_se2, _, atest_usb, ddr_pxi1, _, _, _, _, _),
+	[11] = PINGROUP(11, qup0_se2, phase_flag, _, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup0_se3, qup0_se7, phase_flag, _, _, _, _, _, _),
+	[13] = PINGROUP(13, qup0_se3, qup0_se7, phase_flag, _, _, _, _, _, _),
+	[14] = PINGROUP(14, qup0_se3, qup0_se7, phase_flag, _, _, _, _, _, _),
+	[15] = PINGROUP(15, qup0_se3, qup0_se7, phase_flag, _, _, _, _, _, _),
+	[16] = PINGROUP(16, qup0_se4, phase_flag, _, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup0_se4, qup0_se2, phase_flag, _, _, _, _, _, _),
+	[18] = PINGROUP(18, qup0_se4, qup0_se2, phase_flag, _, qdss_cti, _, _, _, _),
+	[19] = PINGROUP(19, qup0_se4, qup0_se2, phase_flag, _, qdss_cti, _, _, _, _),
+	[20] = PINGROUP(20, qup0_se5, _, phase_flag, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup0_se5, qup0_se3, _, phase_flag, _, _, _, _, _),
+	[22] = PINGROUP(22, qup0_se5, qup0_se3, _, phase_flag, _, _, _, _, _),
+	[23] = PINGROUP(23, qup0_se5, qup0_se3, phase_flag, _, qdss_cti, _, _, _, _),
+	[24] = PINGROUP(24, qup0_se6, phase_flag, _, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup0_se6, phase_flag, _, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup0_se6, phase_flag, _, _, _, _, _, _, _),
+	[27] = PINGROUP(27, qup0_se6, phase_flag, _, qdss_cti, _, _, _, _, _),
+	[28] = PINGROUP(28, pll_bist, _, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, _, _, _, _, _, _, _, _, _),
+	[30] = PINGROUP(30, _, _, _, _, _, _, _, _, _),
+	[31] = PINGROUP(31, _, _, _, _, _, _, _, _, _),
+	[32] = PINGROUP(32, qup1_se0, ibi_i3c, _, _, _, _, _, _, _),
+	[33] = PINGROUP(33, qup1_se0, ibi_i3c, qup1_se3, _, _, _, _, _, _),
+	[34] = PINGROUP(34, qup1_se0, qup1_se3, tsense_pwm1, tsense_pwm2, tsense_pwm3, tsense_pwm4, _, _, _),
+	[35] = PINGROUP(35, qup1_se0, qup1_se3, pll_clk, atest_usb, _, _, _, _, _),
+	[36] = PINGROUP(36, qup1_se1, ibi_i3c, _, _, _, _, _, _, _),
+	[37] = PINGROUP(37, qup1_se1, ibi_i3c, _, _, _, _, _, _, _),
+	[38] = PINGROUP(38, qup1_se1, vsense_trigger, atest_usb, ddr_pxi0, _, _, _, _, _),
+	[39] = PINGROUP(39, qup1_se1, sys_throttle, phase_flag, _, _, _, _, _, _),
+	[40] = PINGROUP(40, qup1_se2, phase_flag, _, _, _, _, _, _, _),
+	[41] = PINGROUP(41, qup1_se2, atest_usb, ddr_pxi1, _, _, _, _, _, _),
+	[42] = PINGROUP(42, qup1_se2, jitter_bist, atest_usb, ddr_pxi2, _, _, _, _, _),
+	[43] = PINGROUP(43, qup1_se2, _, atest_usb, ddr_pxi2, _, _, _, _, _),
+	[44] = PINGROUP(44, qup1_se3, _, atest_usb, ddr_pxi3, _, _, _, _, _),
+	[45] = PINGROUP(45, qup1_se3, cmu_rng3, _, atest_usb, ddr_pxi3, _, _, _, _),
+	[46] = PINGROUP(46, qup1_se3, cmu_rng2, _, atest_usb, ddr_pxi4, _, _, _, _),
+	[47] = PINGROUP(47, qup1_se3, cmu_rng1, _, atest_usb, ddr_pxi4, _, _, _, _),
+	[48] = PINGROUP(48, qup1_se4, cmu_rng0, _, atest_usb, ddr_pxi5, _, _, _, _),
+	[49] = PINGROUP(49, qup1_se4, qup1_se2, _, atest_usb, ddr_pxi5, _, _, _, _),
+	[50] = PINGROUP(50, qup1_se4, qup1_se2, _, atest_usb, ddr_pxi6, _, _, _, _),
+	[51] = PINGROUP(51, qup1_se4, qup1_se2, dbg_out, atest_usb, ddr_pxi6, _, _, _, _),
+	[52] = PINGROUP(52, qup1_se5, qup1_se7, atest_usb, ddr_pxi7, _, _, _, _, _),
+	[53] = PINGROUP(53, qup1_se5, qup1_se7, _, atest_usb, ddr_pxi7, _, _, _, _),
+	[54] = PINGROUP(54, qup1_se5, qup1_se7, ddr_bist, atest_usb, _, _, _, _, _),
+	[55] = PINGROUP(55, qup1_se5, qup1_se7, ddr_bist, _, _, _, _, _, _),
+	[56] = PINGROUP(56, qup1_se6, ddr_bist, _, _, _, _, _, _, _),
+	[57] = PINGROUP(57, qup1_se6, ddr_bist, _, _, _, _, _, _, _),
+	[58] = PINGROUP(58, qup1_se6, atest_usb, _, _, _, _, _, _, _),
+	[59] = PINGROUP(59, qup1_se6, atest_usb, _, _, _, _, _, _, _),
+	[60] = PINGROUP(60, aoss_cti, _, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, aoss_cti, _, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, aoss_cti, _, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, aoss_cti, _, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, qup2_se0, gcc_gp2, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, qup2_se0, qup2_se3, tgu_ch1, atest_usb, _, _, _, _, _),
+	[66] = PINGROUP(66, qup2_se0, qup2_se3, tgu_ch2, atest_usb, _, _, _, _, _),
+	[67] = PINGROUP(67, qup2_se0, qup2_se3, tgu_ch3, atest_usb, _, _, _, _, _),
+	[68] = PINGROUP(68, qup2_se1, ibi_i3c, tgu_ch4, _, _, _, _, _, _),
+	[69] = PINGROUP(69, qup2_se1, ibi_i3c, tgu_ch5, _, _, _, _, _, _),
+	[70] = PINGROUP(70, qup2_se1, _, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, qup2_se1, gcc_gp1, _, _, _, _, _, _, _),
+	[72] = PINGROUP(72, qup2_se2, gcc_gp1, atest_usb, _, _, _, _, _, _),
+	[73] = PINGROUP(73, qup2_se2, gcc_gp2, atest_usb, _, _, _, _, _, _),
+	[74] = PINGROUP(74, qup2_se2, gcc_gp3, atest_usb, _, _, _, _, _, _),
+	[75] = PINGROUP(75, qup2_se2, atest_usb, _, _, _, _, _, _, _),
+	[76] = PINGROUP(76, qup2_se3, phase_flag, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, qup2_se3, phase_flag, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, qup2_se3, phase_flag, _, _, _, _, _, _, _),
+	[79] = PINGROUP(79, qup2_se3, _, _, _, _, _, _, _, _),
+	[80] = PINGROUP(80, qup2_se4, tgu_ch7, atest_usb, _, _, _, _, _, _),
+	[81] = PINGROUP(81, qup2_se4, qup2_se2, tgu_ch0, atest_usb, _, _, _, _, _),
+	[82] = PINGROUP(82, qup2_se4, qup2_se2, gcc_gp3, _, _, _, _, _, _),
+	[83] = PINGROUP(83, qup2_se4, qup2_se2, tgu_ch6, atest_usb, _, _, _, _, _),
+	[84] = PINGROUP(84, qup2_se5, qup2_se7, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, qup2_se5, qup2_se7, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, qup2_se5, qup2_se7, _, _, _, _, _, _, _),
+	[87] = PINGROUP(87, qup2_se5, qup2_se7, _, _, _, _, _, _, _),
+	[88] = PINGROUP(88, qup2_se6, _, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, qup2_se6, _, _, _, _, _, _, _, _),
+	[90] = PINGROUP(90, qup2_se6, _, _, _, _, _, _, _, _),
+	[91] = PINGROUP(91, qup2_se6, _, _, _, _, _, _, _, _),
+	[92] = PINGROUP(92, tmess_prng0, _, _, _, _, _, _, _, _),
+	[93] = PINGROUP(93, tmess_prng1, _, _, _, _, _, _, _, _),
+	[94] = PINGROUP(94, sys_throttle, tmess_prng2, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, tmess_prng3, _, _, _, _, _, _, _, _),
+	[96] = PINGROUP(96, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[98] = PINGROUP(98, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[99] = PINGROUP(99, cam_mclk, qdss_gpio, _, _, _, _, _, _, _),
+	[100] = PINGROUP(100, cam_aon, qdss_gpio, _, _, _, _, _, _, _),
+	[101] = PINGROUP(101, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[104] = PINGROUP(104, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[106] = PINGROUP(106, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[107] = PINGROUP(107, qdss_gpio, _, _, _, _, _, _, _, _),
+	[108] = PINGROUP(108, qdss_gpio, _, _, _, _, _, _, _, _),
+	[109] = PINGROUP(109, cci_timer0, mdp_vsync4, qdss_gpio, _, _, _, _, _, _),
+	[110] = PINGROUP(110, cci_timer1, mdp_vsync5, qdss_gpio, _, _, _, _, _, _),
+	[111] = PINGROUP(111, cci_timer2, cci_async, mdp_vsync6, qdss_gpio, _, _, _, _, _),
+	[112] = PINGROUP(112, cci_timer3, cci_async, mdp_vsync7, qdss_gpio, _, _, _, _, _),
+	[113] = PINGROUP(113, cci_timer4, cci_async, mdp_vsync8, qdss_gpio, _, _, _, _, _),
+	[114] = PINGROUP(114, mdp_vsync0, mdp_vsync1, _, _, _, _, _, _, _),
+	[115] = PINGROUP(115, mdp_vsync3, mdp_vsync2, edp1_lcd, _, _, _, _, _, _),
+	[116] = PINGROUP(116, _, _, _, _, _, _, _, _, _),
+	[117] = PINGROUP(117, _, _, _, _, _, _, _, _, _),
+	[118] = PINGROUP(118, _, _, _, _, _, _, _, _, _),
+	[119] = PINGROUP(119, edp0_hot, edp1_lcd, _, _, _, _, _, _, _),
+	[120] = PINGROUP(120, edp1_hot, edp0_lcd, _, _, _, _, _, _, _),
+	[121] = PINGROUP(121, usb0_phy, _, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, usb0_dp, _, _, _, _, _, _, _, _),
+	[123] = PINGROUP(123, usb1_phy, _, _, _, _, _, _, _, _),
+	[124] = PINGROUP(124, usb1_dp, _, _, _, _, _, _, _, _),
+	[125] = PINGROUP(125, usb2_phy, _, _, _, _, _, _, _, _),
+	[126] = PINGROUP(126, usb2_dp, _, _, _, _, _, _, _, _),
+	[127] = PINGROUP(127, qspi0_clk, sdc4_clk, _, _, _, _, _, _, _),
+	[128] = PINGROUP(128, qspi00, sdc4_data0, _, _, _, _, _, _, _),
+	[129] = PINGROUP(129, qspi01, sdc4_data1, _, _, _, _, _, _, _),
+	[130] = PINGROUP(130, qspi02, sdc4_data2, _, _, _, _, _, _, _),
+	[131] = PINGROUP(131, qspi03, sdc4_data3, _, _, _, _, _, _, _),
+	[132] = PINGROUP(132, qspi0_cs0, sdc4_cmd, _, _, _, _, _, _, _),
+	[133] = PINGROUP(133, qspi0_cs1, tb_trig, _, _, _, _, _, _, _),
+	[134] = PINGROUP(134, audio_ext, _, _, _, _, _, _, _, _),
+	[135] = PINGROUP(135, i2s0_sck, _, _, _, _, _, _, _, _),
+	[136] = PINGROUP(136, i2s0_data0, _, _, _, _, _, _, _, _),
+	[137] = PINGROUP(137, i2s0_data1, tb_trig, _, _, _, _, _, _, _),
+	[138] = PINGROUP(138, i2s0_ws, _, _, _, _, _, _, _, _),
+	[139] = PINGROUP(139, i2s1_sck, _, _, _, _, _, _, _, _),
+	[140] = PINGROUP(140, i2s1_data0, _, _, _, _, _, _, _, _),
+	[141] = PINGROUP(141, i2s1_ws, _, _, _, _, _, _, _, _),
+	[142] = PINGROUP(142, i2s1_data1, audio_ext, audio_ref, _, _, _, _, _, _),
+	[143] = PINGROUP(143, _, _, _, _, _, _, _, _, _),
+	[144] = PINGROUP(144, pcie3_clk, _, _, _, _, _, _, _, _),
+	[145] = PINGROUP(145, _, _, _, _, _, _, _, _, _),
+	[146] = PINGROUP(146, _, _, _, _, _, _, _, _, _),
+	[147] = PINGROUP(147, pcie4_clk, _, _, _, _, _, _, _, _),
+	[148] = PINGROUP(148, _, _, _, _, _, _, _, _, _),
+	[149] = PINGROUP(149, _, _, _, _, _, _, _, _, _),
+	[150] = PINGROUP(150, pcie5_clk, _, _, _, _, _, _, _, _),
+	[151] = PINGROUP(151, _, _, _, _, _, _, _, _, _),
+	[152] = PINGROUP(152, _, _, _, _, _, _, _, _, _),
+	[153] = PINGROUP(153, pcie6a_clk, _, _, _, _, _, _, _, _),
+	[154] = PINGROUP(154, _, _, _, _, _, _, _, _, _),
+	[155] = PINGROUP(155, _, _, _, _, _, _, _, _, _),
+	[156] = PINGROUP(156, pcie6b_clk, _, _, _, _, _, _, _, _),
+	[157] = PINGROUP(157, _, _, _, _, _, _, _, _, _),
+	[158] = PINGROUP(158, _, _, _, _, _, _, _, _, _),
+	[159] = PINGROUP(159, _, _, _, _, _, _, _, _, _),
+	[160] = PINGROUP(160, RESOUT_GPIO, _, _, _, _, _, _, _, _),
+	[161] = PINGROUP(161, qdss_cti, _, _, _, _, _, _, _, _),
+	[162] = PINGROUP(162, sd_write, qdss_cti, _, _, _, _, _, _, _),
+	[163] = PINGROUP(163, usb0_sbrx, _, _, _, _, _, _, _, _),
+	[164] = PINGROUP(164, usb0_sbtx, _, _, _, _, _, _, _, _),
+	[165] = PINGROUP(165, usb0_sbtx, _, _, _, _, _, _, _, _),
+	[166] = PINGROUP(166, _, _, _, _, _, _, _, _, _),
+	[167] = PINGROUP(167, _, _, _, _, _, _, _, _, _),
+	[168] = PINGROUP(168, eusb0_ac, _, _, _, _, _, _, _, _),
+	[169] = PINGROUP(169, eusb3_ac, _, _, _, _, _, _, _, _),
+	[170] = PINGROUP(170, _, _, _, _, _, _, _, _, _),
+	[171] = PINGROUP(171, _, _, _, _, _, _, _, _, _),
+	[172] = PINGROUP(172, usb1_sbrx, _, _, _, _, _, _, _, _),
+	[173] = PINGROUP(173, usb1_sbtx, _, _, _, _, _, _, _, _),
+	[174] = PINGROUP(174, usb1_sbtx, _, _, _, _, _, _, _, _),
+	[175] = PINGROUP(175, _, _, _, _, _, _, _, _, _),
+	[176] = PINGROUP(176, _, _, _, _, _, _, _, _, _),
+	[177] = PINGROUP(177, eusb1_ac, _, _, _, _, _, _, _, _),
+	[178] = PINGROUP(178, eusb6_ac, _, _, _, _, _, _, _, _),
+	[179] = PINGROUP(179, _, _, _, _, _, _, _, _, _),
+	[180] = PINGROUP(180, _, _, _, _, _, _, _, _, _),
+	[181] = PINGROUP(181, usb2_sbrx, prng_rosc3, phase_flag, _, atest_char, _, _, _, _),
+	[182] = PINGROUP(182, usb2_sbtx, prng_rosc2, phase_flag, _, atest_char3, _, _, _, _),
+	[183] = PINGROUP(183, usb2_sbtx, _, _, _, _, _, _, _, _),
+	[184] = PINGROUP(184, phase_flag, _, atest_char1, _, _, _, _, _, _),
+	[185] = PINGROUP(185, phase_flag, _, atest_char0, _, _, _, _, _, _),
+	[186] = PINGROUP(186, eusb2_ac, prng_rosc0, phase_flag, _, _, _, _, _, _),
+	[187] = PINGROUP(187, eusb5_ac, cri_trng, phase_flag, _, _, _, _, _, _),
+	[188] = PINGROUP(188, prng_rosc1, phase_flag, _, atest_char2, _, _, _, _, _),
+	[189] = PINGROUP(189, _, _, _, _, _, _, _, _, _),
+	[190] = PINGROUP(190, _, _, _, _, _, _, _, _, _),
+	[191] = PINGROUP(191, _, _, _, _, _, _, _, _, _),
+	[192] = PINGROUP(192, _, _, _, _, _, _, _, _, _),
+	[193] = PINGROUP(193, _, _, _, _, _, _, _, _, _),
+	[194] = PINGROUP(194, _, _, _, _, _, _, _, _, _),
+	[195] = PINGROUP(195, _, _, _, _, _, _, _, _, _),
+	[196] = PINGROUP(196, _, _, _, _, _, _, _, _, _),
+	[197] = PINGROUP(197, _, _, _, _, _, _, _, _, _),
+	[198] = PINGROUP(198, _, _, _, _, _, _, _, _, _),
+	[199] = PINGROUP(199, _, _, _, _, _, _, _, _, _),
+	[200] = PINGROUP(200, _, _, _, _, _, _, _, _, _),
+	[201] = PINGROUP(201, _, _, _, _, _, _, _, _, _),
+	[202] = PINGROUP(202, _, _, _, _, _, _, _, _, _),
+	[203] = PINGROUP(203, _, _, _, _, _, _, _, _, _),
+	[204] = PINGROUP(204, _, _, _, _, _, _, _, _, _),
+	[205] = PINGROUP(205, _, _, _, _, _, _, _, _, _),
+	[206] = PINGROUP(206, _, _, _, _, _, _, _, _, _),
+	[207] = PINGROUP(207, _, _, _, _, _, _, _, _, _),
+	[208] = PINGROUP(208, _, _, _, _, _, _, _, _, _),
+	[209] = PINGROUP(209, _, _, _, _, _, _, _, _, _),
+	[210] = PINGROUP(210, _, _, _, _, _, _, _, _, _),
+	[211] = PINGROUP(211, _, _, _, _, _, _, _, _, _),
+	[212] = PINGROUP(212, _, _, _, _, _, _, _, _, _),
+	[213] = PINGROUP(213, _, _, _, _, _, _, _, _, _),
+	[214] = PINGROUP(214, _, _, _, _, _, _, _, _, _),
+	[215] = PINGROUP(215, _, qdss_cti, _, _, _, _, _, _, _),
+	[216] = PINGROUP(216, _, _, _, _, _, _, _, _, _),
+	[217] = PINGROUP(217, _, qdss_cti, _, _, _, _, _, _, _),
+	[218] = PINGROUP(218, _, _, _, _, _, _, _, _, _),
+	[219] = PINGROUP(219, _, qdss_gpio, _, _, _, _, _, _, _),
+	[220] = PINGROUP(220, _, qdss_gpio, _, _, _, _, _, _, _),
+	[221] = PINGROUP(221, _, qdss_gpio, _, _, _, _, _, _, _),
+	[222] = PINGROUP(222, _, qdss_gpio, _, _, _, _, _, _, _),
+	[223] = PINGROUP(223, _, qdss_gpio, _, _, _, _, _, _, _),
+	[224] = PINGROUP(224, _, qdss_gpio, _, _, _, _, _, _, _),
+	[225] = PINGROUP(225, _, qdss_gpio, _, _, _, _, _, _, _),
+	[226] = PINGROUP(226, _, qdss_gpio, _, _, _, _, _, _, _),
+	[227] = PINGROUP(227, _, qdss_gpio, _, _, _, _, _, _, _),
+	[228] = PINGROUP(228, _, qdss_gpio, _, _, _, _, _, _, _),
+	[229] = PINGROUP(229, qdss_gpio, _, _, _, _, _, _, _, _),
+	[230] = PINGROUP(230, qdss_gpio, _, _, _, _, _, _, _, _),
+	[231] = PINGROUP(231, qdss_gpio, _, _, _, _, _, _, _, _),
+	[232] = PINGROUP(232, qdss_gpio, _, _, _, _, _, _, _, _),
+	[233] = PINGROUP(233, qdss_gpio, _, _, _, _, _, _, _, _),
+	[234] = PINGROUP(234, qdss_gpio, _, _, _, _, _, _, _, _),
+	[235] = PINGROUP(235, aon_cci, qdss_gpio, _, _, _, _, _, _, _),
+	[236] = PINGROUP(236, aon_cci, qdss_gpio, _, _, _, _, _, _, _),
+	[237] = PINGROUP(237, _, _, _, _, _, _, _, _, _),
+	[238] = UFS_RESET(ufs_reset, 0x1f9000),
+	[239] = SDC_QDSD_PINGROUP(sdc2_clk, 0x1f2000, 14, 6),
+	[240] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x1f2000, 11, 3),
+	[241] = SDC_QDSD_PINGROUP(sdc2_data, 0x1f2000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map x1e80100_pdc_map[] = {
+	{ 0, 72 }, { 2, 70 }, { 3, 71 }, { 6, 123 }, { 7, 67 }, { 11, 85 },
+	{ 15, 68 }, { 18, 122 }, { 19, 69 }, { 21, 158 }, { 23, 143 }, { 26, 129 },
+	{ 27, 144 }, { 28, 77 }, { 29, 78 }, { 30, 92 }, { 32, 145 }, { 33, 115 },
+	{ 34, 130 }, { 35, 146 }, { 36, 147 }, { 39, 80 }, { 43, 148 }, { 47, 149 },
+	{ 51, 79 }, { 53, 89 }, { 59, 87 }, { 64, 90 }, { 65, 106 }, { 66, 142 },
+	{ 67, 88 }, { 71, 91 }, { 75, 152 }, { 79, 153 }, { 80, 125 }, { 81, 128 },
+	{ 84, 137 }, { 85, 155 }, { 87, 156 }, { 91, 157 }, { 92, 138 }, { 94, 140 },
+	{ 95, 141 }, { 113, 84 }, { 121, 73 }, { 123, 74 }, { 129, 76 }, { 131, 82 },
+	{ 134, 83 }, { 141, 93 }, { 144, 94 }, { 147, 96 }, { 148, 97 }, { 150, 102 },
+	{ 151, 103 }, { 153, 104 }, { 156, 105 }, { 157, 107 }, { 163, 98 }, { 166, 112 },
+	{ 172, 99 }, { 181, 101 }, { 184, 116 }, { 193, 40 }, { 193, 117 }, { 196, 108 },
+	{ 203, 133 }, { 212, 120 }, { 213, 150 }, { 214, 121 }, { 215, 118 }, { 217, 109 },
+	{ 220, 110 }, { 221, 111 }, { 222, 124 }, { 224, 131 }, { 225, 132 },
+};
+
+static const struct msm_pinctrl_soc_data x1e80100_pinctrl = {
+	.pins = x1e80100_pins,
+	.npins = ARRAY_SIZE(x1e80100_pins),
+	.functions = x1e80100_functions,
+	.nfunctions = ARRAY_SIZE(x1e80100_functions),
+	.groups = x1e80100_groups,
+	.ngroups = ARRAY_SIZE(x1e80100_groups),
+	.ngpios = 239,
+	.wakeirq_map = x1e80100_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(x1e80100_pdc_map),
+	.egpio_func = 9,
+};
+
+static int x1e80100_pinctrl_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &x1e80100_pinctrl);
+}
+
+static const struct of_device_id x1e80100_pinctrl_of_match[] = {
+	{ .compatible = "qcom,x1e80100-tlmm", },
+	{ },
+};
+
+static struct platform_driver x1e80100_pinctrl_driver = {
+	.driver = {
+		.name = "x1e80100-tlmm",
+		.of_match_table = x1e80100_pinctrl_of_match,
+	},
+	.probe = x1e80100_pinctrl_probe,
+	.remove_new = msm_pinctrl_remove,
+};
+
+static int __init x1e80100_pinctrl_init(void)
+{
+	return platform_driver_register(&x1e80100_pinctrl_driver);
+}
+arch_initcall(x1e80100_pinctrl_init);
+
+static void __exit x1e80100_pinctrl_exit(void)
+{
+	platform_driver_unregister(&x1e80100_pinctrl_driver);
+}
+module_exit(x1e80100_pinctrl_exit);
+
+MODULE_DESCRIPTION("QTI X1E80100 TLMM pinctrl driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, x1e80100_pinctrl_of_match);
-- 
GitLab


From c3c63e66527c18b598bbf9d77f0849852cd32ff9 Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Thu, 16 Nov 2023 16:30:45 -0600
Subject: [PATCH 0414/4076] pinctrl: as3722: Use devm_gpiochip_add_data() to
 simplify remove path

Use devm version of gpiochip add function to handle removal for us.

Signed-off-by: Andrew Davis <afd@ti.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20231116223045.274211-1-afd@ti.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-as3722.c | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c
index 6a5f23cf7a2a2..0d8c75ce20eda 100644
--- a/drivers/pinctrl/pinctrl-as3722.c
+++ b/drivers/pinctrl/pinctrl-as3722.c
@@ -542,7 +542,6 @@ static int as3722_pinctrl_probe(struct platform_device *pdev)
 
 	as_pci->dev = &pdev->dev;
 	as_pci->as3722 = dev_get_drvdata(pdev->dev.parent);
-	platform_set_drvdata(pdev, as_pci);
 
 	as_pci->pins = as3722_pins_desc;
 	as_pci->num_pins = ARRAY_SIZE(as3722_pins_desc);
@@ -562,7 +561,7 @@ static int as3722_pinctrl_probe(struct platform_device *pdev)
 
 	as_pci->gpio_chip = as3722_gpio_chip;
 	as_pci->gpio_chip.parent = &pdev->dev;
-	ret = gpiochip_add_data(&as_pci->gpio_chip, as_pci);
+	ret = devm_gpiochip_add_data(&pdev->dev, &as_pci->gpio_chip, as_pci);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Couldn't register gpiochip, %d\n", ret);
 		return ret;
@@ -572,21 +571,10 @@ static int as3722_pinctrl_probe(struct platform_device *pdev)
 				0, 0, AS3722_PIN_NUM);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Couldn't add pin range, %d\n", ret);
-		goto fail_range_add;
+		return ret;
 	}
 
 	return 0;
-
-fail_range_add:
-	gpiochip_remove(&as_pci->gpio_chip);
-	return ret;
-}
-
-static void as3722_pinctrl_remove(struct platform_device *pdev)
-{
-	struct as3722_pctrl_info *as_pci = platform_get_drvdata(pdev);
-
-	gpiochip_remove(&as_pci->gpio_chip);
 }
 
 static const struct of_device_id as3722_pinctrl_of_match[] = {
@@ -601,7 +589,6 @@ static struct platform_driver as3722_pinctrl_driver = {
 		.of_match_table = as3722_pinctrl_of_match,
 	},
 	.probe = as3722_pinctrl_probe,
-	.remove_new = as3722_pinctrl_remove,
 };
 module_platform_driver(as3722_pinctrl_driver);
 
-- 
GitLab


From 66fb6eb6fab63ee80fd26cd5bdd9164aead0d207 Mon Sep 17 00:00:00 2001
From: Sibi Sankar <quic_sibis@quicinc.com>
Date: Fri, 24 Nov 2023 15:36:06 +0530
Subject: [PATCH 0415/4076] dt-bindings: dma: qcom: gpi: add compatible for
 X1E80100

The Qualcomm X1E80100 uses GPI DMA for its GENI interface. Add a compatible
string for it in the documentation by using the SM6350 as fallback.

Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231124100608.29964-4-quic_sibis@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/dma/qcom,gpi.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
index 88d0de3d1b46b..d06db2cc931eb 100644
--- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
@@ -32,6 +32,7 @@ properties:
               - qcom,sm8350-gpi-dma
               - qcom,sm8450-gpi-dma
               - qcom,sm8550-gpi-dma
+              - qcom,x1e80100-gpi-dma
           - const: qcom,sm6350-gpi-dma
       - items:
           - enum:
-- 
GitLab


From 228fe713795f5abade1eb0551f47ce6fbb89f4f7 Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Thu, 23 Nov 2023 19:32:12 +0530
Subject: [PATCH 0416/4076] pinctrl: tangier: simplify locking using cleanup
 helpers

Use lock guards from cleanup.h to simplify locking.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-tangier.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-tangier.c b/drivers/pinctrl/intel/pinctrl-tangier.c
index 26e34ec0a9720..2cb0b4758269e 100644
--- a/drivers/pinctrl/intel/pinctrl-tangier.c
+++ b/drivers/pinctrl/intel/pinctrl-tangier.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -220,7 +221,6 @@ static int tng_pinmux_set_mux(struct pinctrl_dev *pctldev,
 	const struct intel_pingroup *grp = &tp->groups[group];
 	u32 bits = grp->mode << BUFCFG_PINMODE_SHIFT;
 	u32 mask = BUFCFG_PINMODE_MASK;
-	unsigned long flags;
 	unsigned int i;
 
 	/*
@@ -232,11 +232,11 @@ static int tng_pinmux_set_mux(struct pinctrl_dev *pctldev,
 			return -EBUSY;
 	}
 
+	guard(raw_spinlock_irqsave)(&tp->lock);
+
 	/* Now enable the mux setting for each pin in the group */
-	raw_spin_lock_irqsave(&tp->lock, flags);
 	for (i = 0; i < grp->grp.npins; i++)
 		tng_update_bufcfg(tp, grp->grp.pins[i], bits, mask);
-	raw_spin_unlock_irqrestore(&tp->lock, flags);
 
 	return 0;
 }
@@ -248,14 +248,13 @@ static int tng_gpio_request_enable(struct pinctrl_dev *pctldev,
 	struct tng_pinctrl *tp = pinctrl_dev_get_drvdata(pctldev);
 	u32 bits = BUFCFG_PINMODE_GPIO << BUFCFG_PINMODE_SHIFT;
 	u32 mask = BUFCFG_PINMODE_MASK;
-	unsigned long flags;
 
 	if (!tng_buf_available(tp, pin))
 		return -EBUSY;
 
-	raw_spin_lock_irqsave(&tp->lock, flags);
+	guard(raw_spinlock_irqsave)(&tp->lock);
+
 	tng_update_bufcfg(tp, pin, bits, mask);
-	raw_spin_unlock_irqrestore(&tp->lock, flags);
 
 	return 0;
 }
@@ -360,7 +359,6 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 	unsigned int param = pinconf_to_config_param(config);
 	unsigned int arg = pinconf_to_config_argument(config);
 	u32 mask, term, value = 0;
-	unsigned long flags;
 
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
@@ -432,9 +430,9 @@ static int tng_config_set_pin(struct tng_pinctrl *tp, unsigned int pin,
 		return -EINVAL;
 	}
 
-	raw_spin_lock_irqsave(&tp->lock, flags);
+	guard(raw_spinlock_irqsave)(&tp->lock);
+
 	tng_update_bufcfg(tp, pin, value, mask);
-	raw_spin_unlock_irqrestore(&tp->lock, flags);
 
 	return 0;
 }
-- 
GitLab


From 9580ba25c5daf49f693ae84dc2e18cd64f210cae Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 Nov 2023 19:54:44 +0200
Subject: [PATCH 0417/4076] pinctrl: lynxpoint: Simplify code with cleanup
 helpers

Use macros defined in linux/cleanup.h to automate resource lifetime
control in the driver.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-lynxpoint.c | 72 +++++++----------------
 1 file changed, 21 insertions(+), 51 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-lynxpoint.c b/drivers/pinctrl/intel/pinctrl-lynxpoint.c
index e6878e4cf20cb..1fb0bba8b386b 100644
--- a/drivers/pinctrl/intel/pinctrl-lynxpoint.c
+++ b/drivers/pinctrl/intel/pinctrl-lynxpoint.c
@@ -10,6 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/array_size.h>
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
 #include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -291,10 +292,9 @@ static int lp_pinmux_set_mux(struct pinctrl_dev *pctldev,
 {
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	const struct intel_pingroup *grp = &lg->soc->groups[group];
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	/* Now enable the mux setting for each pin in the group */
 	for (i = 0; i < grp->grp.npins; i++) {
@@ -312,8 +312,6 @@ static int lp_pinmux_set_mux(struct pinctrl_dev *pctldev,
 		iowrite32(value, reg);
 	}
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
 	return 0;
 }
 
@@ -334,10 +332,9 @@ static int lp_gpio_request_enable(struct pinctrl_dev *pctldev,
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, pin, LP_CONFIG1);
 	void __iomem *conf2 = lp_gpio_reg(&lg->chip, pin, LP_CONFIG2);
-	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	/*
 	 * Reconfigure pin to GPIO mode if needed and issue a warning,
@@ -352,8 +349,6 @@ static int lp_gpio_request_enable(struct pinctrl_dev *pctldev,
 	/* Enable input sensing */
 	lp_gpio_enable_input(conf2);
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
 	return 0;
 }
 
@@ -363,14 +358,11 @@ static void lp_gpio_disable_free(struct pinctrl_dev *pctldev,
 {
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *conf2 = lp_gpio_reg(&lg->chip, pin, LP_CONFIG2);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	/* Disable input sensing */
 	lp_gpio_disable_input(conf2);
-
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
 }
 
 static int lp_gpio_set_direction(struct pinctrl_dev *pctldev,
@@ -379,10 +371,9 @@ static int lp_gpio_set_direction(struct pinctrl_dev *pctldev,
 {
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, pin, LP_CONFIG1);
-	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	value = ioread32(reg);
 	value &= ~DIR_BIT;
@@ -400,8 +391,6 @@ static int lp_gpio_set_direction(struct pinctrl_dev *pctldev,
 	}
 	iowrite32(value, reg);
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
 	return 0;
 }
 
@@ -421,13 +410,11 @@ static int lp_pin_config_get(struct pinctrl_dev *pctldev, unsigned int pin,
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *conf2 = lp_gpio_reg(&lg->chip, pin, LP_CONFIG2);
 	enum pin_config_param param = pinconf_to_config_param(*config);
-	unsigned long flags;
 	u32 value, pull;
 	u16 arg;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
-	value = ioread32(conf2);
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &lg->lock)
+		value = ioread32(conf2);
 
 	pull = value & GPIWP_MASK;
 
@@ -464,11 +451,10 @@ static int lp_pin_config_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	struct intel_pinctrl *lg = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *conf2 = lp_gpio_reg(&lg->chip, pin, LP_CONFIG2);
 	enum pin_config_param param;
-	unsigned long flags;
-	int i, ret = 0;
+	unsigned int i;
 	u32 value;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	value = ioread32(conf2);
 
@@ -489,19 +475,13 @@ static int lp_pin_config_set(struct pinctrl_dev *pctldev, unsigned int pin,
 			value |= GPIWP_UP;
 			break;
 		default:
-			ret = -ENOTSUPP;
+			return -ENOTSUPP;
 		}
-
-		if (ret)
-			break;
 	}
 
-	if (!ret)
-		iowrite32(value, conf2);
+	iowrite32(value, conf2);
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
-	return ret;
+	return 0;
 }
 
 static const struct pinconf_ops lptlp_pinconf_ops = {
@@ -527,16 +507,13 @@ static void lp_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
 {
 	struct intel_pinctrl *lg = gpiochip_get_data(chip);
 	void __iomem *reg = lp_gpio_reg(chip, offset, LP_CONFIG1);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
 
 	if (value)
 		iowrite32(ioread32(reg) | OUT_LVL_BIT, reg);
 	else
 		iowrite32(ioread32(reg) & ~OUT_LVL_BIT, reg);
-
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
 }
 
 static int lp_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
@@ -592,11 +569,10 @@ static void lp_irq_ack(struct irq_data *d)
 	struct intel_pinctrl *lg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, hwirq, LP_INT_STAT);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
+
 	iowrite32(BIT(hwirq % 32), reg);
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
 }
 
 static void lp_irq_unmask(struct irq_data *d)
@@ -613,13 +589,11 @@ static void lp_irq_enable(struct irq_data *d)
 	struct intel_pinctrl *lg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, hwirq, LP_INT_ENABLE);
-	unsigned long flags;
 
 	gpiochip_enable_irq(gc, hwirq);
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
-	iowrite32(ioread32(reg) | BIT(hwirq % 32), reg);
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &lg->lock)
+		iowrite32(ioread32(reg) | BIT(hwirq % 32), reg);
 }
 
 static void lp_irq_disable(struct irq_data *d)
@@ -628,11 +602,9 @@ static void lp_irq_disable(struct irq_data *d)
 	struct intel_pinctrl *lg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	void __iomem *reg = lp_gpio_reg(&lg->chip, hwirq, LP_INT_ENABLE);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
-	iowrite32(ioread32(reg) & ~BIT(hwirq % 32), reg);
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &lg->lock)
+		iowrite32(ioread32(reg) & ~BIT(hwirq % 32), reg);
 
 	gpiochip_disable_irq(gc, hwirq);
 }
@@ -642,7 +614,6 @@ static int lp_irq_set_type(struct irq_data *d, unsigned int type)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct intel_pinctrl *lg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
-	unsigned long flags;
 	void __iomem *reg;
 	u32 value;
 
@@ -656,7 +627,8 @@ static int lp_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EBUSY;
 	}
 
-	raw_spin_lock_irqsave(&lg->lock, flags);
+	guard(raw_spinlock_irqsave)(&lg->lock);
+
 	value = ioread32(reg);
 
 	/* set both TRIG_SEL and INV bits to 0 for rising edge */
@@ -682,8 +654,6 @@ static int lp_irq_set_type(struct irq_data *d, unsigned int type)
 	else if (type & IRQ_TYPE_LEVEL_MASK)
 		irq_set_handler_locked(d, handle_level_irq);
 
-	raw_spin_unlock_irqrestore(&lg->lock, flags);
-
 	return 0;
 }
 
-- 
GitLab


From 1a856a22e6036c5f0d6da7568b4550270f989038 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 Nov 2023 19:50:36 +0200
Subject: [PATCH 0418/4076] pinctrl: baytrail: Fix types of config value in
 byt_pin_config_set()

When unpacked, the config value is split to two of different types.
Fix the types accordingly.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-baytrail.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 3cd0798ee6313..f1af21dbd5fb2 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -918,13 +918,14 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 			      unsigned int num_configs)
 {
 	struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
-	unsigned int param, arg;
 	void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
 	u32 conf, val, db_pulse, debounce;
+	enum pin_config_param param;
 	unsigned long flags;
 	int i, ret = 0;
+	u32 arg;
 
 	raw_spin_lock_irqsave(&byt_lock, flags);
 
-- 
GitLab


From 5398a0e23cf82e2a69088d7080bc588bc07f4284 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 Nov 2023 19:50:37 +0200
Subject: [PATCH 0419/4076] pinctrl: baytrail: Factor out
 byt_gpio_force_input_mode()

There is a piece of code that it being used at least twice.
Factor it out.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-baytrail.c | 42 ++++++++++++------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index f1af21dbd5fb2..291f0454257b1 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -829,6 +829,24 @@ static int byt_set_pull_strength(u32 *reg, u16 strength)
 	return 0;
 }
 
+static void byt_gpio_force_input_mode(struct intel_pinctrl *vg, unsigned int offset)
+{
+	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+	u32 value;
+
+	value = readl(reg);
+	if (!(value & BYT_INPUT_EN))
+		return;
+
+	/*
+	 * Pull assignment is only applicable in input mode. If
+	 * chip is not in input mode, set it and warn about it.
+	 */
+	value &= ~BYT_INPUT_EN;
+	writel(value, reg);
+	dev_warn(vg->dev, "Pin %i: forcibly set to input mode\n", offset);
+}
+
 static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset,
 			      unsigned long *config)
 {
@@ -919,9 +937,8 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 {
 	struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
 	void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
-	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
-	u32 conf, val, db_pulse, debounce;
+	u32 conf, db_pulse, debounce;
 	enum pin_config_param param;
 	unsigned long flags;
 	int i, ret = 0;
@@ -930,7 +947,6 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 	raw_spin_lock_irqsave(&byt_lock, flags);
 
 	conf = readl(conf_reg);
-	val = readl(val_reg);
 
 	for (i = 0; i < num_configs; i++) {
 		param = pinconf_to_config_param(configs[i]);
@@ -945,15 +961,7 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 			if (arg == 1)
 				arg = 2000;
 
-			/*
-			 * Pull assignment is only applicable in input mode. If
-			 * chip is not in input mode, set it and warn about it.
-			 */
-			if (val & BYT_INPUT_EN) {
-				val &= ~BYT_INPUT_EN;
-				writel(val, val_reg);
-				dev_warn(vg->dev, "Pin %i: forcibly set to input mode\n", offset);
-			}
+			byt_gpio_force_input_mode(vg, offset);
 
 			conf &= ~BYT_PULL_ASSIGN_MASK;
 			conf |= BYT_PULL_ASSIGN_DOWN;
@@ -965,15 +973,7 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 			if (arg == 1)
 				arg = 2000;
 
-			/*
-			 * Pull assignment is only applicable in input mode. If
-			 * chip is not in input mode, set it and warn about it.
-			 */
-			if (val & BYT_INPUT_EN) {
-				val &= ~BYT_INPUT_EN;
-				writel(val, val_reg);
-				dev_warn(vg->dev, "Pin %i: forcibly set to input mode\n", offset);
-			}
+			byt_gpio_force_input_mode(vg, offset);
 
 			conf &= ~BYT_PULL_ASSIGN_MASK;
 			conf |= BYT_PULL_ASSIGN_UP;
-- 
GitLab


From 078d83033a76ddbb030e87ed2a56eb28a57a7b34 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 Nov 2023 19:50:38 +0200
Subject: [PATCH 0420/4076] pinctrl: baytrail: Move default strength assignment
 to a switch-case

When ->pin_config_set() is called from the GPIO library (assumed
GpioIo() ACPI resource), the argument can be 1, when, for example,
PullDefault is provided. In such case we supply sane default in
the driver. Move that default assingment to a switch-case, so
it will be consolidated in one place.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-baytrail.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 291f0454257b1..84f21a28fe7e3 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -810,6 +810,7 @@ static int byt_set_pull_strength(u32 *reg, u16 strength)
 	*reg &= ~BYT_PULL_STR_MASK;
 
 	switch (strength) {
+	case 1: /* Set default strength value in case none is given */
 	case 2000:
 		*reg |= BYT_PULL_STR_2K;
 		break;
@@ -957,10 +958,6 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 			conf &= ~BYT_PULL_ASSIGN_MASK;
 			break;
 		case PIN_CONFIG_BIAS_PULL_DOWN:
-			/* Set default strength value in case none is given */
-			if (arg == 1)
-				arg = 2000;
-
 			byt_gpio_force_input_mode(vg, offset);
 
 			conf &= ~BYT_PULL_ASSIGN_MASK;
@@ -969,10 +966,6 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 
 			break;
 		case PIN_CONFIG_BIAS_PULL_UP:
-			/* Set default strength value in case none is given */
-			if (arg == 1)
-				arg = 2000;
-
 			byt_gpio_force_input_mode(vg, offset);
 
 			conf &= ~BYT_PULL_ASSIGN_MASK;
-- 
GitLab


From 6191e49de389f57a2d34fdfe2c5df7fca2a1f246 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 Nov 2023 19:50:39 +0200
Subject: [PATCH 0421/4076] pinctrl: baytrail: Simplify code with cleanup
 helpers

Use macros defined in linux/cleanup.h to automate resource lifetime
control in the driver.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-baytrail.c | 176 +++++++++--------------
 1 file changed, 68 insertions(+), 108 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 84f21a28fe7e3..9b76819e606ad 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -9,6 +9,7 @@
 #include <linux/acpi.h>
 #include <linux/array_size.h>
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
 #include <linux/gpio/driver.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -587,10 +588,9 @@ static void byt_set_group_simple_mux(struct intel_pinctrl *vg,
 				     const struct intel_pingroup group,
 				     unsigned int func)
 {
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	for (i = 0; i < group.grp.npins; i++) {
 		void __iomem *padcfg0;
@@ -608,18 +608,15 @@ static void byt_set_group_simple_mux(struct intel_pinctrl *vg,
 		value |= func;
 		writel(value, padcfg0);
 	}
-
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static void byt_set_group_mixed_mux(struct intel_pinctrl *vg,
 				    const struct intel_pingroup group,
 				    const unsigned int *func)
 {
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	for (i = 0; i < group.grp.npins; i++) {
 		void __iomem *padcfg0;
@@ -637,8 +634,6 @@ static void byt_set_group_mixed_mux(struct intel_pinctrl *vg,
 		value |= func[i];
 		writel(value, padcfg0);
 	}
-
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static int byt_set_mux(struct pinctrl_dev *pctldev, unsigned int func_selector,
@@ -676,10 +671,10 @@ static u32 byt_get_gpio_mux(struct intel_pinctrl *vg, unsigned int offset)
 static void byt_gpio_clear_triggering(struct intel_pinctrl *vg, unsigned int offset)
 {
 	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
-	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
+
 	value = readl(reg);
 
 	/* Do not clear direct-irq enabled IRQs (from gpio_disable_free) */
@@ -687,7 +682,6 @@ static void byt_gpio_clear_triggering(struct intel_pinctrl *vg, unsigned int off
 		value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL);
 
 	writel(value, reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev,
@@ -697,9 +691,8 @@ static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev,
 	struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
 	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
 	u32 value, gpio_mux;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	/*
 	 * In most cases, func pin mux 000 means GPIO function.
@@ -712,15 +705,14 @@ static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev,
 	 */
 	value = readl(reg) & BYT_PIN_MUX;
 	gpio_mux = byt_get_gpio_mux(vg, offset);
-	if (gpio_mux != value) {
-		value = readl(reg) & ~BYT_PIN_MUX;
-		value |= gpio_mux;
-		writel(value, reg);
+	if (gpio_mux == value)
+		return 0;
 
-		dev_warn(vg->dev, FW_BUG "Pin %i: forcibly re-configured as GPIO\n", offset);
-	}
+	value = readl(reg) & ~BYT_PIN_MUX;
+	value |= gpio_mux;
+	writel(value, reg);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
+	dev_warn(vg->dev, FW_BUG "Pin %i: forcibly re-configured as GPIO\n", offset);
 
 	return 0;
 }
@@ -758,10 +750,9 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
 {
 	struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	value = readl(val_reg);
 	value &= ~BYT_DIR_MASK;
@@ -772,8 +763,6 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
 
 	writel(value, val_reg);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
-
 	return 0;
 }
 
@@ -856,15 +845,15 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset,
 	void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
-	unsigned long flags;
 	u32 conf, pull, val, debounce;
 	u16 arg = 0;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
-	conf = readl(conf_reg);
+	scoped_guard(raw_spinlock_irqsave, &byt_lock) {
+		conf = readl(conf_reg);
+		val = readl(val_reg);
+	}
+
 	pull = conf & BYT_PULL_ASSIGN_MASK;
-	val = readl(val_reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
@@ -891,9 +880,8 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset,
 		if (!(conf & BYT_DEBOUNCE_EN))
 			return -EINVAL;
 
-		raw_spin_lock_irqsave(&byt_lock, flags);
-		debounce = readl(db_reg);
-		raw_spin_unlock_irqrestore(&byt_lock, flags);
+		scoped_guard(raw_spinlock_irqsave, &byt_lock)
+			debounce = readl(db_reg);
 
 		switch (debounce & BYT_DEBOUNCE_PULSE_MASK) {
 		case BYT_DEBOUNCE_PULSE_375US:
@@ -941,11 +929,10 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 	void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
 	u32 conf, db_pulse, debounce;
 	enum pin_config_param param;
-	unsigned long flags;
-	int i, ret = 0;
+	int i, ret;
 	u32 arg;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	conf = readl(conf_reg);
 
@@ -963,6 +950,8 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 			conf &= ~BYT_PULL_ASSIGN_MASK;
 			conf |= BYT_PULL_ASSIGN_DOWN;
 			ret = byt_set_pull_strength(&conf, arg);
+			if (ret)
+				return ret;
 
 			break;
 		case PIN_CONFIG_BIAS_PULL_UP:
@@ -971,22 +960,15 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 			conf &= ~BYT_PULL_ASSIGN_MASK;
 			conf |= BYT_PULL_ASSIGN_UP;
 			ret = byt_set_pull_strength(&conf, arg);
+			if (ret)
+				return ret;
 
 			break;
 		case PIN_CONFIG_INPUT_DEBOUNCE:
-			if (arg) {
-				conf |= BYT_DEBOUNCE_EN;
-			} else {
-				conf &= ~BYT_DEBOUNCE_EN;
-
-				/*
-				 * No need to update the pulse value.
-				 * Debounce is going to be disabled.
-				 */
-				break;
-			}
-
 			switch (arg) {
+			case 0:
+				db_pulse = 0;
+				break;
 			case 375:
 				db_pulse = BYT_DEBOUNCE_PULSE_375US;
 				break;
@@ -1009,33 +991,28 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 				db_pulse = BYT_DEBOUNCE_PULSE_24MS;
 				break;
 			default:
-				if (arg)
-					ret = -EINVAL;
-				break;
+				return -EINVAL;
 			}
 
-			if (ret)
-				break;
+			if (db_pulse) {
+				debounce = readl(db_reg);
+				debounce = (debounce & ~BYT_DEBOUNCE_PULSE_MASK) | db_pulse;
+				writel(debounce, db_reg);
 
-			debounce = readl(db_reg);
-			debounce = (debounce & ~BYT_DEBOUNCE_PULSE_MASK) | db_pulse;
-			writel(debounce, db_reg);
+				conf |= BYT_DEBOUNCE_EN;
+			} else {
+				conf &= ~BYT_DEBOUNCE_EN;
+			}
 
 			break;
 		default:
-			ret = -ENOTSUPP;
+			return -ENOTSUPP;
 		}
-
-		if (ret)
-			break;
 	}
 
-	if (!ret)
-		writel(conf, conf_reg);
-
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
+	writel(conf, conf_reg);
 
-	return ret;
+	return 0;
 }
 
 static const struct pinconf_ops byt_pinconf_ops = {
@@ -1055,12 +1032,10 @@ static int byt_gpio_get(struct gpio_chip *chip, unsigned int offset)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
 	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
 	u32 val;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
-	val = readl(reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &byt_lock)
+		val = readl(reg);
 
 	return !!(val & BYT_LEVEL);
 }
@@ -1068,35 +1043,34 @@ static int byt_gpio_get(struct gpio_chip *chip, unsigned int offset)
 static void byt_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
-	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
+	void __iomem *reg;
 	u32 old_val;
 
+	reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	if (!reg)
 		return;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
+
 	old_val = readl(reg);
 	if (value)
 		writel(old_val | BYT_LEVEL, reg);
 	else
 		writel(old_val & ~BYT_LEVEL, reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
-	void __iomem *reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
+	void __iomem *reg;
 	u32 value;
 
+	reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
 	if (!reg)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
-	value = readl(reg);
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &byt_lock)
+		value = readl(reg);
 
 	if (!(value & BYT_OUTPUT_EN))
 		return GPIO_LINE_DIRECTION_OUT;
@@ -1110,17 +1084,15 @@ static int byt_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
 	u32 reg;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	reg = readl(val_reg);
 	reg &= ~BYT_DIR_MASK;
 	reg |= BYT_OUTPUT_EN;
 	writel(reg, val_reg);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 	return 0;
 }
 
@@ -1135,10 +1107,9 @@ static int byt_gpio_direction_output(struct gpio_chip *chip,
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(chip);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
-	unsigned long flags;
 	u32 reg;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	byt_gpio_direct_irq_check(vg, offset);
 
@@ -1151,7 +1122,6 @@ static int byt_gpio_direction_output(struct gpio_chip *chip,
 
 	writel(reg, val_reg);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 	return 0;
 }
 
@@ -1166,7 +1136,6 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 		void __iomem *conf_reg, *val_reg;
 		const char *pull_str = NULL;
 		const char *pull = NULL;
-		unsigned long flags;
 		const char *label;
 		unsigned int pin;
 
@@ -1184,10 +1153,10 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 			continue;
 		}
 
-		raw_spin_lock_irqsave(&byt_lock, flags);
-		conf0 = readl(conf_reg);
-		val = readl(val_reg);
-		raw_spin_unlock_irqrestore(&byt_lock, flags);
+		scoped_guard(raw_spinlock_irqsave, &byt_lock) {
+			conf0 = readl(conf_reg);
+			val = readl(val_reg);
+		}
 
 		comm = intel_get_community(vg, pin);
 		if (!comm) {
@@ -1271,9 +1240,9 @@ static void byt_irq_ack(struct irq_data *d)
 	if (!reg)
 		return;
 
-	raw_spin_lock(&byt_lock);
+	guard(raw_spinlock)(&byt_lock);
+
 	writel(BIT(hwirq % 32), reg);
-	raw_spin_unlock(&byt_lock);
 }
 
 static void byt_irq_mask(struct irq_data *d)
@@ -1291,7 +1260,6 @@ static void byt_irq_unmask(struct irq_data *d)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct intel_pinctrl *vg = gpiochip_get_data(gc);
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
-	unsigned long flags;
 	void __iomem *reg;
 	u32 value;
 
@@ -1301,7 +1269,8 @@ static void byt_irq_unmask(struct irq_data *d)
 	if (!reg)
 		return;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
+
 	value = readl(reg);
 
 	switch (irqd_get_trigger_type(d)) {
@@ -1323,23 +1292,21 @@ static void byt_irq_unmask(struct irq_data *d)
 	}
 
 	writel(value, reg);
-
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
 
 static int byt_irq_type(struct irq_data *d, unsigned int type)
 {
 	struct intel_pinctrl *vg = gpiochip_get_data(irq_data_get_irq_chip_data(d));
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
-	u32 value;
-	unsigned long flags;
 	void __iomem *reg;
+	u32 value;
 
 	reg = byt_gpio_reg(vg, hwirq, BYT_CONF0_REG);
 	if (!reg)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
+
 	value = readl(reg);
 
 	WARN(value & BYT_DIRECT_IRQ_EN,
@@ -1361,8 +1328,6 @@ static int byt_irq_type(struct irq_data *d, unsigned int type)
 	else if (type & IRQ_TYPE_LEVEL_MASK)
 		irq_set_handler_locked(d, handle_level_irq);
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
-
 	return 0;
 }
 
@@ -1394,9 +1359,8 @@ static void byt_gpio_irq_handler(struct irq_desc *desc)
 			continue;
 		}
 
-		raw_spin_lock(&byt_lock);
-		pending = readl(reg);
-		raw_spin_unlock(&byt_lock);
+		scoped_guard(raw_spinlock, &byt_lock)
+			pending = readl(reg);
 		for_each_set_bit(pin, &pending, 32)
 			generic_handle_domain_irq(vg->chip.irq.domain, base + pin);
 	}
@@ -1659,10 +1623,9 @@ static int byt_pinctrl_probe(struct platform_device *pdev)
 static int byt_gpio_suspend(struct device *dev)
 {
 	struct intel_pinctrl *vg = dev_get_drvdata(dev);
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	for (i = 0; i < vg->soc->npins; i++) {
 		void __iomem *reg;
@@ -1686,17 +1649,15 @@ static int byt_gpio_suspend(struct device *dev)
 		vg->context.pads[i].val = value;
 	}
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 	return 0;
 }
 
 static int byt_gpio_resume(struct device *dev)
 {
 	struct intel_pinctrl *vg = dev_get_drvdata(dev);
-	unsigned long flags;
 	int i;
 
-	raw_spin_lock_irqsave(&byt_lock, flags);
+	guard(raw_spinlock_irqsave)(&byt_lock);
 
 	for (i = 0; i < vg->soc->npins; i++) {
 		void __iomem *reg;
@@ -1736,7 +1697,6 @@ static int byt_gpio_resume(struct device *dev)
 		}
 	}
 
-	raw_spin_unlock_irqrestore(&byt_lock, flags);
 	return 0;
 }
 
-- 
GitLab


From 56d02cfa3fbfca7466ccd68f4db78b0297f5c01f Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Thu, 2 Nov 2023 20:39:22 +0000
Subject: [PATCH 0422/4076] dt-bindings: dma: rz-dmac: Document RZ/Five SoC

The DMAC block on the RZ/Five SoC is identical to one found on the RZ/G2UL
SoC. "renesas,r9a07g043-dmac" compatible string will be used on the
RZ/Five SoC so to make this clear, update the comment to include RZ/Five
SoC.

No driver changes are required as generic compatible string
"renesas,rz-dmac" will be used as a fallback on RZ/Five SoC.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231102203922.548353-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
index c284abc6784ae..a42b6a26a6d3f 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
@@ -16,7 +16,7 @@ properties:
   compatible:
     items:
       - enum:
-          - renesas,r9a07g043-dmac # RZ/G2UL
+          - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
           - renesas,r9a07g044-dmac # RZ/G2{L,LC}
           - renesas,r9a07g054-dmac # RZ/V2L
       - const: renesas,rz-dmac
-- 
GitLab


From 0fdd1c4ea99e188dfa8ab7bafbe4004cc72dca30 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 5 Nov 2023 10:34:17 +0100
Subject: [PATCH 0423/4076] dmaengine: milbeaut-hdmac: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

There is an error path that has the above mentioned problem. This patch
only adds a more drastic error message. To properly fix it,
dmaengine_terminate_sync() must be known to have succeeded (or that it's
safe to not call it as other drivers seem to assume).

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231105093415.3704633-7-u.kleine-koenig@pengutronix.de
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/milbeaut-hdmac.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c
index 1b0a95892627d..7b41c670970a6 100644
--- a/drivers/dma/milbeaut-hdmac.c
+++ b/drivers/dma/milbeaut-hdmac.c
@@ -531,7 +531,7 @@ disable_clk:
 	return ret;
 }
 
-static int milbeaut_hdmac_remove(struct platform_device *pdev)
+static void milbeaut_hdmac_remove(struct platform_device *pdev)
 {
 	struct milbeaut_hdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -546,16 +546,21 @@ static int milbeaut_hdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		milbeaut_hdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&mdev->ddev);
 	clk_disable_unprepare(mdev->clk);
-
-	return 0;
 }
 
 static const struct of_device_id milbeaut_hdmac_match[] = {
@@ -566,7 +571,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_hdmac_match);
 
 static struct platform_driver milbeaut_hdmac_driver = {
 	.probe = milbeaut_hdmac_probe,
-	.remove = milbeaut_hdmac_remove,
+	.remove_new = milbeaut_hdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-hdmac",
 		.of_match_table = milbeaut_hdmac_match,
-- 
GitLab


From 47ee210011ddb8b366c7dcf9c1a9c3818573df29 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 5 Nov 2023 10:34:18 +0100
Subject: [PATCH 0424/4076] dmaengine: milbeaut-xdmac: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

There is an error path that has the above mentioned problem. This patch
only adds a more drastic error message. To properly fix it,
dmaengine_terminate_sync() must be known to have succeeded (or that it's
safe to not call it as other drivers seem to assume).

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231105093415.3704633-8-u.kleine-koenig@pengutronix.de
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/milbeaut-xdmac.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c
index d29d01e730aa0..2cce529b448eb 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -368,7 +368,7 @@ disable_xdmac:
 	return ret;
 }
 
-static int milbeaut_xdmac_remove(struct platform_device *pdev)
+static void milbeaut_xdmac_remove(struct platform_device *pdev)
 {
 	struct milbeaut_xdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -383,8 +383,15 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		milbeaut_xdmac_free_chan_resources(chan);
 	}
 
@@ -392,8 +399,6 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&mdev->ddev);
 
 	disable_xdmac(mdev);
-
-	return 0;
 }
 
 static const struct of_device_id milbeaut_xdmac_match[] = {
@@ -404,7 +409,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_xdmac_match);
 
 static struct platform_driver milbeaut_xdmac_driver = {
 	.probe = milbeaut_xdmac_probe,
-	.remove = milbeaut_xdmac_remove,
+	.remove_new = milbeaut_xdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-xdmac",
 		.of_match_table = milbeaut_xdmac_match,
-- 
GitLab


From 5d4304a8d5646c268d73383fbc179db53f85b921 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 5 Nov 2023 10:34:19 +0100
Subject: [PATCH 0425/4076] dmaengine: uniphier-mdmac: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

There is an error path that has the above mentioned problem. This patch
only adds a more drastic error message. To properly fix it,
dmaengine_terminate_sync() must be known to have succeeded (or that it's
safe to not call it as other drivers seem to assume).

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231105093415.3704633-9-u.kleine-koenig@pengutronix.de
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/uniphier-mdmac.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/dma/uniphier-mdmac.c b/drivers/dma/uniphier-mdmac.c
index 618839df07486..ad7125f6e2ca8 100644
--- a/drivers/dma/uniphier-mdmac.c
+++ b/drivers/dma/uniphier-mdmac.c
@@ -453,7 +453,7 @@ disable_clk:
 	return ret;
 }
 
-static int uniphier_mdmac_remove(struct platform_device *pdev)
+static void uniphier_mdmac_remove(struct platform_device *pdev)
 {
 	struct uniphier_mdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -468,16 +468,21 @@ static int uniphier_mdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		uniphier_mdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&mdev->ddev);
 	clk_disable_unprepare(mdev->clk);
-
-	return 0;
 }
 
 static const struct of_device_id uniphier_mdmac_match[] = {
@@ -488,7 +493,7 @@ MODULE_DEVICE_TABLE(of, uniphier_mdmac_match);
 
 static struct platform_driver uniphier_mdmac_driver = {
 	.probe = uniphier_mdmac_probe,
-	.remove = uniphier_mdmac_remove,
+	.remove_new = uniphier_mdmac_remove,
 	.driver = {
 		.name = "uniphier-mio-dmac",
 		.of_match_table = uniphier_mdmac_match,
-- 
GitLab


From ead0e402e50d1101939e4af67891d5b2fa9678b3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 5 Nov 2023 10:34:20 +0100
Subject: [PATCH 0426/4076] dmaengine: uniphier-xdmac: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

There is an error path that has the above mentioned problem. This patch
only adds a more drastic error message. To properly fix it,
dmaengine_terminate_sync() must be known to have succeeded (or that it's
safe to not call it as other drivers seem to assume).

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231105093415.3704633-10-u.kleine-koenig@pengutronix.de
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/uniphier-xdmac.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c
index 3a8ee2b173b52..3ce2dc2ad9de4 100644
--- a/drivers/dma/uniphier-xdmac.c
+++ b/drivers/dma/uniphier-xdmac.c
@@ -563,7 +563,7 @@ out_unregister_dmac:
 	return ret;
 }
 
-static int uniphier_xdmac_remove(struct platform_device *pdev)
+static void uniphier_xdmac_remove(struct platform_device *pdev)
 {
 	struct uniphier_xdmac_device *xdev = platform_get_drvdata(pdev);
 	struct dma_device *ddev = &xdev->ddev;
@@ -579,15 +579,20 @@ static int uniphier_xdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &ddev->channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *xdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		uniphier_xdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(ddev);
-
-	return 0;
 }
 
 static const struct of_device_id uniphier_xdmac_match[] = {
@@ -598,7 +603,7 @@ MODULE_DEVICE_TABLE(of, uniphier_xdmac_match);
 
 static struct platform_driver uniphier_xdmac_driver = {
 	.probe = uniphier_xdmac_probe,
-	.remove = uniphier_xdmac_remove,
+	.remove_new = uniphier_xdmac_remove,
 	.driver = {
 		.name = "uniphier-xdmac",
 		.of_match_table = uniphier_xdmac_match,
-- 
GitLab


From 375ff42c4c9825c19a53b9095ae4b3337cc83442 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Wed, 25 Oct 2023 10:23:04 +0200
Subject: [PATCH 0427/4076] dt-bindings: dma: qcom,gpi: document the SM8650 GPI
 DMA Engine

Document the GPI DMA Engine on the SM8650 Platform.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231025-topic-sm8650-upstream-bindings-gpi-v2-1-4de85293d730@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/dma/qcom,gpi.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
index d06db2cc931eb..deb64cb9ca3ea 100644
--- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
@@ -32,6 +32,7 @@ properties:
               - qcom,sm8350-gpi-dma
               - qcom,sm8450-gpi-dma
               - qcom,sm8550-gpi-dma
+              - qcom,sm8650-gpi-dma
               - qcom,x1e80100-gpi-dma
           - const: qcom,sm6350-gpi-dma
       - items:
-- 
GitLab


From 306f5df81fcc89b462fbeb9dbe26d9a8ad7c7582 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Sun, 29 Oct 2023 18:07:04 +0100
Subject: [PATCH 0428/4076] dmaengine: apple-admac: Keep upper bits of
 REG_BUS_WIDTH
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For RX channels, REG_BUS_WIDTH seems to default to a value of 0xf00, and
macOS preserves the upper bits when setting the configuration in the
lower ones. If we reset the upper bits to 0, this causes framing errors
on suspend/resume (the data stream "tears" and channels get swapped
around). Keeping the upper bits untouched, like the macOS driver does,
fixes this issue.

Signed-off-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Martin Povišer <povik+lin@cutebit.org>
Signed-off-by: Martin Povišer <povik+lin@cutebit.org>
Link: https://lore.kernel.org/r/20231029170704.82238-1-povik+lin@cutebit.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/apple-admac.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c
index 5b63996640d9d..9588773dd2eb6 100644
--- a/drivers/dma/apple-admac.c
+++ b/drivers/dma/apple-admac.c
@@ -57,6 +57,8 @@
 
 #define REG_BUS_WIDTH(ch)	(0x8040 + (ch) * 0x200)
 
+#define BUS_WIDTH_WORD_SIZE	GENMASK(3, 0)
+#define BUS_WIDTH_FRAME_SIZE	GENMASK(7, 4)
 #define BUS_WIDTH_8BIT		0x00
 #define BUS_WIDTH_16BIT		0x01
 #define BUS_WIDTH_32BIT		0x02
@@ -740,7 +742,8 @@ static int admac_device_config(struct dma_chan *chan,
 	struct admac_data *ad = adchan->host;
 	bool is_tx = admac_chan_direction(adchan->no) == DMA_MEM_TO_DEV;
 	int wordsize = 0;
-	u32 bus_width = 0;
+	u32 bus_width = readl_relaxed(ad->base + REG_BUS_WIDTH(adchan->no)) &
+		~(BUS_WIDTH_WORD_SIZE | BUS_WIDTH_FRAME_SIZE);
 
 	switch (is_tx ? config->dst_addr_width : config->src_addr_width) {
 	case DMA_SLAVE_BUSWIDTH_1_BYTE:
-- 
GitLab


From 524fc108b8958683da9fb1c94b445ab9e07819ab Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 15 Nov 2023 17:50:00 +0100
Subject: [PATCH 0429/4076] pinctrl: stop using gpiod_to_chip()

Don't dereference struct gpio_chip directly, use dedicated gpio_device
getters instead.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231115165001.2932350-3-brgl@bgdev.pl
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 1fa89be29b8f9..0b4d07aea3877 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -13,6 +13,7 @@
 #define pr_fmt(fmt) "pinctrl core: " fmt
 
 #include <linux/array_size.h>
+#include <linux/cleanup.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -1649,8 +1650,8 @@ static int pinctrl_pins_show(struct seq_file *s, void *what)
 	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
 	unsigned i, pin;
 #ifdef CONFIG_GPIOLIB
+	struct gpio_device *gdev __free(gpio_device_put) = NULL;
 	struct pinctrl_gpio_range *range;
-	struct gpio_chip *chip;
 	int gpio_num;
 #endif
 
@@ -1685,11 +1686,11 @@ static int pinctrl_pins_show(struct seq_file *s, void *what)
 			 * we need to get rid of the range->base eventually and
 			 * get the descriptor directly from the gpio_chip.
 			 */
-			chip = gpiod_to_chip(gpio_to_desc(gpio_num));
-		else
-			chip = NULL;
-		if (chip)
-			seq_printf(s, "%u:%s ", gpio_num - chip->gpiodev->base, chip->label);
+			gdev = gpiod_to_gpio_device(gpio_to_desc(gpio_num));
+		if (gdev)
+			seq_printf(s, "%u:%s ",
+				   gpio_num - gpio_device_get_base(gdev),
+				   gpio_device_get_label(gdev));
 		else
 			seq_puts(s, "0:? ");
 #endif
-- 
GitLab


From 5f0dedcc9decbe8e8655373a34c87a076502b6db Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 15 Nov 2023 17:50:01 +0100
Subject: [PATCH 0430/4076] pinctrl: don't include GPIOLIB private header

gpio_to_desc() is declared in linux/gpio.h so there's no need to include
gpiolib.h directly.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231115165001.2932350-4-brgl@bgdev.pl
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 0b4d07aea3877..e55959e1af5a5 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -24,6 +24,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 
+#include <linux/gpio.h>
 #include <linux/gpio/driver.h>
 
 #include <linux/pinctrl/consumer.h>
@@ -31,10 +32,6 @@
 #include <linux/pinctrl/machine.h>
 #include <linux/pinctrl/pinctrl.h>
 
-#ifdef CONFIG_GPIOLIB
-#include "../gpio/gpiolib.h"
-#endif
-
 #include "core.h"
 #include "devicetree.h"
 #include "pinconf.h"
-- 
GitLab


From 727e08b1a56a60ee9b68ae5c7539cbcfe2cfe552 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 17 Nov 2023 11:12:37 +0100
Subject: [PATCH 0431/4076] serial: xilinx_uartps: Fix kernel doc about
 .remove()'s return code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the driver was converted to use .remove_new() the return function
doesn't return a value any more. So remove the obsolete documentation
about the return value.

Reported-by: Michal Simek <michal.simek@amd.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/20231117101236.878008-1-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/xilinx_uartps.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 6decf2b13340a..920762d7b4a4b 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1663,8 +1663,6 @@ err_out_unregister_driver:
 /**
  * cdns_uart_remove - called when the platform driver is unregistered
  * @pdev: Pointer to the platform device structure
- *
- * Return: 0 on success, negative errno otherwise
  */
 static void cdns_uart_remove(struct platform_device *pdev)
 {
-- 
GitLab


From e651faa2fba4d387aa00b3c02e9c10232852d2ef Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Fri, 3 Nov 2023 12:12:08 +0100
Subject: [PATCH 0432/4076] drivers/tty/vt: use standard array-copy-functions

tty/vt currently uses memdup_user() and vmemdup_array_user() to copy
userspace arrays.

Whereas there is no danger of overflowing, the call to vmemdup_user()
currently utilizes array_size() to calculate the array size
nevertheless. This is not useful because array_size() would return
SIZE_MAX and pass it to vmemdup_user() in case of (the impossible)
overflow.

string.h from the core-API now provides the wrappers memdup_array_user()
and vmemdup_array_user() to copy userspace arrays in a standardized
manner. Additionally, they also perform generic overflow-checks.

Use these wrappers to make it more obvious and readable that arrays are
being copied.

As we are at it, remove two unnecessary empty lines.

Suggested-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Link: https://lore.kernel.org/r/20231103111207.74621-2-pstanner@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/consolemap.c |  2 +-
 drivers/tty/vt/keyboard.c   | 10 ++++------
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/tty/vt/consolemap.c b/drivers/tty/vt/consolemap.c
index 5e39a4f430ee5..82d70083fead0 100644
--- a/drivers/tty/vt/consolemap.c
+++ b/drivers/tty/vt/consolemap.c
@@ -644,7 +644,7 @@ int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list)
 	if (!ct)
 		return 0;
 
-	unilist = vmemdup_user(list, array_size(sizeof(*unilist), ct));
+	unilist = vmemdup_array_user(list, ct, sizeof(*unilist));
 	if (IS_ERR(unilist))
 		return PTR_ERR(unilist);
 
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 12a192e1196b3..a2116e135a82d 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -1772,12 +1772,10 @@ int vt_do_diacrit(unsigned int cmd, void __user *udp, int perm)
 			return -EINVAL;
 
 		if (ct) {
-
-			dia = memdup_user(a->kbdiacr,
-					sizeof(struct kbdiacr) * ct);
+			dia = memdup_array_user(a->kbdiacr,
+						ct, sizeof(struct kbdiacr));
 			if (IS_ERR(dia))
 				return PTR_ERR(dia);
-
 		}
 
 		spin_lock_irqsave(&kbd_event_lock, flags);
@@ -1811,8 +1809,8 @@ int vt_do_diacrit(unsigned int cmd, void __user *udp, int perm)
 			return -EINVAL;
 
 		if (ct) {
-			buf = memdup_user(a->kbdiacruc,
-					  ct * sizeof(struct kbdiacruc));
+			buf = memdup_array_user(a->kbdiacruc,
+						ct, sizeof(struct kbdiacruc));
 			if (IS_ERR(buf))
 				return PTR_ERR(buf);
 		} 
-- 
GitLab


From 0be916a68c8ada0c98d4c14058717175a367ee87 Mon Sep 17 00:00:00 2001
From: Manikanta Guntupalli <manikanta.guntupalli@amd.com>
Date: Thu, 16 Nov 2023 19:10:02 +0530
Subject: [PATCH 0433/4076] Documentation: devices.txt: Update ttyUL major
 number allocation details

Describe when uartlite driver uses static/dynamic allocation for major
number based on maximum number of uartlite serial ports.

Signed-off-by: Manikanta Guntupalli <manikanta.guntupalli@amd.com>
Link: https://lore.kernel.org/r/20231116134003.3762725-2-manikanta.guntupalli@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/admin-guide/devices.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt
index 8390549235304..94c98be1329a4 100644
--- a/Documentation/admin-guide/devices.txt
+++ b/Documentation/admin-guide/devices.txt
@@ -2704,6 +2704,9 @@
 		    ...
 		 185 = /dev/ttyNX15		Hilscher netX serial port 15
 		 186 = /dev/ttyJ0		JTAG1 DCC protocol based serial port emulation
+
+		 If maximum number of uartlite serial ports is more than 4, then the driver
+		 uses dynamic allocation instead of static allocation for major number.
 		 187 = /dev/ttyUL0		Xilinx uartlite - port 0
 		    ...
 		 190 = /dev/ttyUL3		Xilinx uartlite - port 3
-- 
GitLab


From 01c33b813864ca15a9dec22045ce1a5bb09d5e74 Mon Sep 17 00:00:00 2001
From: Manikanta Guntupalli <manikanta.guntupalli@amd.com>
Date: Thu, 16 Nov 2023 19:10:03 +0530
Subject: [PATCH 0434/4076] serial: uartlite: Use dynamic allocation for major
 number when uart ports > 4

Device number 204 has a range of minors on major number.
uart_register_driver is failing due to lack of minor numbers
when more number of uart ports used. So, to avoid minor number
limitation on 204 major number use dynamic major allocation
when more than 4 uart ports used otherwise use static major
allocation.

https://docs.kernel.org/arch/arm/sa1100/serial_uart.html

Signed-off-by: Manikanta Guntupalli <manikanta.guntupalli@amd.com>
Link: https://lore.kernel.org/r/20231116134003.3762725-3-manikanta.guntupalli@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/Kconfig    | 3 +++
 drivers/tty/serial/uartlite.c | 5 +++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 732c893c8d161..8b1f5756002f8 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -532,6 +532,9 @@ config SERIAL_UARTLITE_NR_UARTS
 	help
 	  Set this to the number of uartlites in your system, or the number
 	  you think you might implement.
+	  If maximum number of uartlite serial ports is more than 4, then the
+	  driver uses dynamic allocation instead of static allocation for major
+	  number.
 
 config SERIAL_SUNCORE
 	bool
diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index f9c69f543a26c..10ba41b7be994 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -24,8 +24,13 @@
 #include <linux/pm_runtime.h>
 
 #define ULITE_NAME		"ttyUL"
+#if CONFIG_SERIAL_UARTLITE_NR_UARTS > 4
+#define ULITE_MAJOR             0       /* use dynamic node allocation */
+#define ULITE_MINOR             0
+#else
 #define ULITE_MAJOR		204
 #define ULITE_MINOR		187
+#endif
 #define ULITE_NR_UARTS		CONFIG_SERIAL_UARTLITE_NR_UARTS
 
 /* ---------------------------------------------------------------------
-- 
GitLab


From 39ff20f5fd4481c9acf3b75c7b705b1ec6604588 Mon Sep 17 00:00:00 2001
From: Tomas Mudrunka <tomas.mudrunka@gmail.com>
Date: Mon, 20 Nov 2023 12:14:51 +0100
Subject: [PATCH 0435/4076] /proc/sysrq-trigger: accept multiple keys at once

This way we can do:
`echo _reisub > /proc/sysrq-trigger`
Instead of:
`for i in r e i s u b; do echo "$i" > /proc/sysrq-trigger; done;`

This can be very useful when trying to execute sysrq combo remotely
or from userspace. When sending keys in multiple separate writes,
userspace (eg. bash or ssh) can be killed before whole combo is completed.
Therefore putting all keys in single write is more robust approach.

Signed-off-by: Tomas Mudrunka <tomas.mudrunka@gmail.com>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231120111451.527952-1-tomas.mudrunka@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/admin-guide/sysrq.rst | 11 ++++++++++-
 drivers/tty/sysrq.c                 | 19 ++++++++++++++++---
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/sysrq.rst b/Documentation/admin-guide/sysrq.rst
index 51906e47327b6..2f2e5bd440f9b 100644
--- a/Documentation/admin-guide/sysrq.rst
+++ b/Documentation/admin-guide/sysrq.rst
@@ -75,10 +75,19 @@ On other
 	submit a patch to be included in this section.
 
 On all
-	Write a character to /proc/sysrq-trigger.  e.g.::
+	Write a single character to /proc/sysrq-trigger.
+	Only the first character is processed, the rest of the string is
+	ignored. However, it is not recommended to write any extra characters
+	as the behavior is undefined and might change in the future versions.
+	E.g.::
 
 		echo t > /proc/sysrq-trigger
 
+	Alternatively, write multiple characters prepended by underscore.
+	This way, all characters will be processed. E.g.::
+
+		echo _reisub > /proc/sysrq-trigger
+
 The :kbd:`<command key>` is case sensitive.
 
 What are the 'command' keys?
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 6b4a28bcf2f5f..02217e3c916b5 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -1150,16 +1150,29 @@ EXPORT_SYMBOL(unregister_sysrq_key);
 #ifdef CONFIG_PROC_FS
 /*
  * writing 'C' to /proc/sysrq-trigger is like sysrq-C
+ * Normally, only the first character written is processed.
+ * However, if the first character is an underscore,
+ * all characters are processed.
  */
 static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf,
 				   size_t count, loff_t *ppos)
 {
-	if (count) {
+	bool bulk = false;
+	size_t i;
+
+	for (i = 0; i < count; i++) {
 		char c;
 
-		if (get_user(c, buf))
+		if (get_user(c, buf + i))
 			return -EFAULT;
-		__handle_sysrq(c, false);
+
+		if (c == '_')
+			bulk = true;
+		else
+			__handle_sysrq(c, false);
+
+		if (!bulk)
+			break;
 	}
 
 	return count;
-- 
GitLab


From b286f4e87e325b76789f30337c98ba72e00532e2 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 13 Nov 2023 10:07:52 +0200
Subject: [PATCH 0436/4076] serial: core: Move tty and serdev to be children of
 serial core port device

Let's move tty and serdev controller to be children of the serial core port
device. This way the runtime PM usage count of a child device propagates
to the serial hardware device.

The tty and serdev devices are associated with a specific serial port of
a serial hardware controller device, and we now have serial core hierarchy
of controllers and ports.

The tty device moves happily with just a change of the parent device and
update of device_find_child() handling. The serdev device init needs some
changes to separate the serial hardware controller device from the parent
device.

With this change the tty devices move under sysfs similar to this x86_64
qemu example of a diff of "find /sys -name ttyS*":

 /sys/class/tty/ttyS0
 /sys/class/tty/ttyS3
 /sys/class/tty/ttyS1
-/sys/devices/pnp0/00:04/tty/ttyS0
-/sys/devices/platform/serial8250/tty/ttyS2
-/sys/devices/platform/serial8250/tty/ttyS3
-/sys/devices/platform/serial8250/tty/ttyS1
+/sys/devices/pnp0/00:04/00:04:0/00:04:0.0/tty/ttyS0
+/sys/devices/platform/serial8250/serial8250:0/serial8250:0.3/tty/ttyS3
+/sys/devices/platform/serial8250/serial8250:0/serial8250:0.1/tty/ttyS1
+/sys/devices/platform/serial8250/serial8250:0/serial8250:0.2/tty/ttyS2

If a serdev device is used instead of a tty, it moves in a similar way.

Suggested-by: Johan Hovold <johan@kernel.org>
Cc: Maximilian Luz <luzmaximilian@gmail.com>
Cc: Rob Herring <robh@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231113080758.30346-1-tony@atomide.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serdev/core.c           | 15 +++++++++------
 drivers/tty/serdev/serdev-ttyport.c |  3 ++-
 drivers/tty/serial/serial_core.c    |  7 ++++---
 drivers/tty/tty_port.c              | 16 +++++++++-------
 include/linux/serdev.h              |  8 +++++++-
 include/linux/tty_port.h            |  4 ++--
 6 files changed, 33 insertions(+), 20 deletions(-)

diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index a5fdaf5e148ef..3090e3454c447 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -468,6 +468,7 @@ EXPORT_SYMBOL_GPL(serdev_device_alloc);
 
 /**
  * serdev_controller_alloc() - Allocate a new serdev controller
+ * @host:	serial port hardware controller device
  * @parent:	parent device
  * @size:	size of private data
  *
@@ -476,8 +477,9 @@ EXPORT_SYMBOL_GPL(serdev_device_alloc);
  * The allocated private data region may be accessed via
  * serdev_controller_get_drvdata()
  */
-struct serdev_controller *serdev_controller_alloc(struct device *parent,
-					      size_t size)
+struct serdev_controller *serdev_controller_alloc(struct device *host,
+						  struct device *parent,
+						  size_t size)
 {
 	struct serdev_controller *ctrl;
 	int id;
@@ -502,7 +504,8 @@ struct serdev_controller *serdev_controller_alloc(struct device *parent,
 	ctrl->dev.type = &serdev_ctrl_type;
 	ctrl->dev.bus = &serdev_bus_type;
 	ctrl->dev.parent = parent;
-	device_set_node(&ctrl->dev, dev_fwnode(parent));
+	ctrl->host = host;
+	device_set_node(&ctrl->dev, dev_fwnode(host));
 	serdev_controller_set_drvdata(ctrl, &ctrl[1]);
 
 	dev_set_name(&ctrl->dev, "serial%d", id);
@@ -665,7 +668,7 @@ static int acpi_serdev_check_resources(struct serdev_controller *ctrl,
 		acpi_get_parent(adev->handle, &lookup.controller_handle);
 
 	/* Make sure controller and ResourceSource handle match */
-	if (!device_match_acpi_handle(ctrl->dev.parent, lookup.controller_handle))
+	if (!device_match_acpi_handle(ctrl->host, lookup.controller_handle))
 		return -ENODEV;
 
 	return 0;
@@ -730,7 +733,7 @@ static int acpi_serdev_register_devices(struct serdev_controller *ctrl)
 	bool skip;
 	int ret;
 
-	if (!has_acpi_companion(ctrl->dev.parent))
+	if (!has_acpi_companion(ctrl->host))
 		return -ENODEV;
 
 	/*
@@ -739,7 +742,7 @@ static int acpi_serdev_register_devices(struct serdev_controller *ctrl)
 	 * succeed in this case, so that the proper serdev devices can be
 	 * added "manually" later.
 	 */
-	ret = acpi_quirk_skip_serdev_enumeration(ctrl->dev.parent, &skip);
+	ret = acpi_quirk_skip_serdev_enumeration(ctrl->host, &skip);
 	if (ret)
 		return ret;
 	if (skip)
diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c
index e3856814ce775..c5381fe15e1c4 100644
--- a/drivers/tty/serdev/serdev-ttyport.c
+++ b/drivers/tty/serdev/serdev-ttyport.c
@@ -274,6 +274,7 @@ static const struct serdev_controller_ops ctrl_ops = {
 };
 
 struct device *serdev_tty_port_register(struct tty_port *port,
+					struct device *host,
 					struct device *parent,
 					struct tty_driver *drv, int idx)
 {
@@ -284,7 +285,7 @@ struct device *serdev_tty_port_register(struct tty_port *port,
 	if (!port || !drv || !parent)
 		return ERR_PTR(-ENODEV);
 
-	ctrl = serdev_controller_alloc(parent, sizeof(struct serport));
+	ctrl = serdev_controller_alloc(host, parent, sizeof(struct serport));
 	if (!ctrl)
 		return ERR_PTR(-ENOMEM);
 	serport = serdev_controller_get_drvdata(ctrl);
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index f1348a5095527..f36ea953e2c9f 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2342,7 +2342,7 @@ int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport)
 
 	mutex_lock(&port->mutex);
 
-	tty_dev = device_find_child(uport->dev, &match, serial_match_port);
+	tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port);
 	if (tty_dev && device_may_wakeup(tty_dev)) {
 		enable_irq_wake(uport->irq);
 		put_device(tty_dev);
@@ -2423,7 +2423,7 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport)
 
 	mutex_lock(&port->mutex);
 
-	tty_dev = device_find_child(uport->dev, &match, serial_match_port);
+	tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port);
 	if (!uport->suspended && device_may_wakeup(tty_dev)) {
 		if (irqd_is_wakeup_set(irq_get_irq_data((uport->irq))))
 			disable_irq_wake(uport->irq);
@@ -3153,7 +3153,8 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 	 * setserial to be used to alter this port's parameters.
 	 */
 	tty_dev = tty_port_register_device_attr_serdev(port, drv->tty_driver,
-			uport->line, uport->dev, port, uport->tty_groups);
+			uport->line, uport->dev, &uport->port_dev->dev, port,
+			uport->tty_groups);
 	if (!IS_ERR(tty_dev)) {
 		device_set_wakeup_capable(tty_dev, 1);
 	} else {
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 63c1252509617..ef72d2e4b928d 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -171,7 +171,8 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr);
  * @port: tty_port of the device
  * @driver: tty_driver for this device
  * @index: index of the tty
- * @device: parent if exists, otherwise NULL
+ * @host: serial port hardware device
+ * @parent: parent if exists, otherwise NULL
  * @drvdata: driver data for the device
  * @attr_grp: attribute group for the device
  *
@@ -180,20 +181,20 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr);
  */
 struct device *tty_port_register_device_attr_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device, void *drvdata,
+		struct device *host, struct device *parent, void *drvdata,
 		const struct attribute_group **attr_grp)
 {
 	struct device *dev;
 
 	tty_port_link_device(port, driver, index);
 
-	dev = serdev_tty_port_register(port, device, driver, index);
+	dev = serdev_tty_port_register(port, host, parent, driver, index);
 	if (PTR_ERR(dev) != -ENODEV) {
 		/* Skip creating cdev if we registered a serdev device */
 		return dev;
 	}
 
-	return tty_register_device_attr(driver, index, device, drvdata,
+	return tty_register_device_attr(driver, index, parent, drvdata,
 			attr_grp);
 }
 EXPORT_SYMBOL_GPL(tty_port_register_device_attr_serdev);
@@ -203,17 +204,18 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr_serdev);
  * @port: tty_port of the device
  * @driver: tty_driver for this device
  * @index: index of the tty
- * @device: parent if exists, otherwise NULL
+ * @host: serial port hardware controller device
+ * @parent: parent if exists, otherwise NULL
  *
  * Register a serdev or tty device depending on if the parent device has any
  * defined serdev clients or not.
  */
 struct device *tty_port_register_device_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device)
+		struct device *host, struct device *parent)
 {
 	return tty_port_register_device_attr_serdev(port, driver, index,
-			device, NULL, NULL);
+			host, parent, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(tty_port_register_device_serdev);
 
diff --git a/include/linux/serdev.h b/include/linux/serdev.h
index f5f97fa25e8ad..0ebf53bb254fa 100644
--- a/include/linux/serdev.h
+++ b/include/linux/serdev.h
@@ -99,12 +99,14 @@ struct serdev_controller_ops {
 /**
  * struct serdev_controller - interface to the serdev controller
  * @dev:	Driver model representation of the device.
+ * @host:	Serial port hardware controller device
  * @nr:		number identifier for this controller/bus.
  * @serdev:	Pointer to slave device for this controller.
  * @ops:	Controller operations.
  */
 struct serdev_controller {
 	struct device		dev;
+	struct device		*host;
 	unsigned int		nr;
 	struct serdev_device	*serdev;
 	const struct serdev_controller_ops *ops;
@@ -167,7 +169,9 @@ struct serdev_device *serdev_device_alloc(struct serdev_controller *);
 int serdev_device_add(struct serdev_device *);
 void serdev_device_remove(struct serdev_device *);
 
-struct serdev_controller *serdev_controller_alloc(struct device *, size_t);
+struct serdev_controller *serdev_controller_alloc(struct device *host,
+						  struct device *parent,
+						  size_t size);
 int serdev_controller_add(struct serdev_controller *);
 void serdev_controller_remove(struct serdev_controller *);
 
@@ -311,11 +315,13 @@ struct tty_driver;
 
 #ifdef CONFIG_SERIAL_DEV_CTRL_TTYPORT
 struct device *serdev_tty_port_register(struct tty_port *port,
+					struct device *host,
 					struct device *parent,
 					struct tty_driver *drv, int idx);
 int serdev_tty_port_unregister(struct tty_port *port);
 #else
 static inline struct device *serdev_tty_port_register(struct tty_port *port,
+					   struct device *host,
 					   struct device *parent,
 					   struct tty_driver *drv, int idx)
 {
diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h
index 6b367eb17979a..3276311a7f384 100644
--- a/include/linux/tty_port.h
+++ b/include/linux/tty_port.h
@@ -149,10 +149,10 @@ struct device *tty_port_register_device_attr(struct tty_port *port,
 		const struct attribute_group **attr_grp);
 struct device *tty_port_register_device_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device);
+		struct device *host, struct device *parent);
 struct device *tty_port_register_device_attr_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device, void *drvdata,
+		struct device *host, struct device *parent, void *drvdata,
 		const struct attribute_group **attr_grp);
 void tty_port_unregister_device(struct tty_port *port,
 		struct tty_driver *driver, unsigned index);
-- 
GitLab


From 45a3a8ef81291b63a2b50a1a145857dd9fc05e89 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 13 Nov 2023 10:07:53 +0200
Subject: [PATCH 0437/4076] serial: core: Revert checks for tx runtime PM state

This reverts commit 81a61051e0ce5fd7e09225c0d5985da08c7954a7.

With tty and serdev controller moved to be children of the serial core
port device, runtime PM usage count of the serdev controller now
propagates to the serial hardware controller parent device as expected.

Cc: Maximilian Luz <luzmaximilian@gmail.com>
Cc: Rob Herring <robh@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231113080758.30346-2-tony@atomide.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index f36ea953e2c9f..0393853b99475 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -156,7 +156,7 @@ static void __uart_start(struct uart_state *state)
 	 * enabled, serial_port_runtime_resume() calls start_tx() again
 	 * after enabling the device.
 	 */
-	if (!pm_runtime_enabled(port->dev) || pm_runtime_active(port->dev))
+	if (pm_runtime_active(&port_dev->dev))
 		port->ops->start_tx(port);
 	pm_runtime_mark_last_busy(&port_dev->dev);
 	pm_runtime_put_autosuspend(&port_dev->dev);
-- 
GitLab


From fffa35a25b4ced5ec89b1c12cf6a4f1d9541d3cb Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Wed, 22 Nov 2023 12:58:59 -0500
Subject: [PATCH 0438/4076] serial: sc16is7xx: change confusing comment about
 Tx FIFO

The comment wording can be confusing, as txlen will return the number of
bytes available in the FIFO, which can be less than the maximum theoretical
Tx FIFO size.

Change the comment so that it is unambiguous.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231122175859.3874753-1-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 4c69c30fbac12..10e90a7774f05 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -664,7 +664,7 @@ static void sc16is7xx_handle_tx(struct uart_port *port)
 	/* Get length of data pending in circular buffer */
 	to_send = uart_circ_chars_pending(xmit);
 	if (likely(to_send)) {
-		/* Limit to size of TX FIFO */
+		/* Limit to space available in TX FIFO */
 		txlen = sc16is7xx_port_read(port, SC16IS7XX_TXLVL_REG);
 		if (txlen > SC16IS7XX_FIFO_SIZE) {
 			dev_err_ratelimited(port->dev,
-- 
GitLab


From 1be5f0819c1adc8308ecdc248314c5f30c994452 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Wed, 22 Nov 2023 12:59:56 -0500
Subject: [PATCH 0439/4076] serial: max310x: change confusing comment about Tx
 FIFO

The comment wording can be confusing, as txlen will return the number of
bytes available in the FIFO, which can be less than the maximum theoretical
Tx FIFO size.

Change the comment so that it is unambiguous.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231122175957.3875102-1-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 97e4965b73d40..f3a99daebdaa0 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -780,7 +780,7 @@ static void max310x_handle_tx(struct uart_port *port)
 	to_send = uart_circ_chars_pending(xmit);
 	until_end = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE);
 	if (likely(to_send)) {
-		/* Limit to size of TX FIFO */
+		/* Limit to space available in TX FIFO */
 		txlen = max310x_port_read(port, MAX310X_TXFIFOLVL_REG);
 		txlen = port->fifosize - txlen;
 		to_send = (to_send > txlen) ? txlen : to_send;
-- 
GitLab


From 358779dd18c1e8531bd6d78c19ed802958d7c677 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:44 +0100
Subject: [PATCH 0440/4076] tty: fix tty_operations types in documentation

Commits 95713967ba52 ("tty: make tty_operations::write()'s count
size_t") and dcaafbe6ee3b ("tty: propagate u8 data to
tty_operations::put_char()") changed types of characters to u8, but
omitted to fix the documentation.

Fix the latter now.

Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-4-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty_driver.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 18beff0cec1ab..f428c1b784a20 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -72,8 +72,7 @@ struct serial_struct;
  *	is closed for the last time freeing up the resources. This is
  *	actually the second part of shutdown for routines that might sleep.
  *
- * @write: ``ssize_t ()(struct tty_struct *tty, const unsigned char *buf,
- *		    size_t count)``
+ * @write: ``ssize_t ()(struct tty_struct *tty, const u8 *buf, size_t count)``
  *
  *	This routine is called by the kernel to write a series (@count) of
  *	characters (@buf) to the @tty device. The characters may come from
@@ -85,7 +84,7 @@ struct serial_struct;
  *
  *	Optional: Required for writable devices. May not sleep.
  *
- * @put_char: ``int ()(struct tty_struct *tty, unsigned char ch)``
+ * @put_char: ``int ()(struct tty_struct *tty, u8 ch)``
  *
  *	This routine is called by the kernel to write a single character @ch to
  *	the @tty device. If the kernel uses this routine, it must call the
-- 
GitLab


From 4c74253b831e5a8eb87d4d8d4a0eae40c331e682 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:42 +0100
Subject: [PATCH 0441/4076] tty: deprecate tty_write_message()

tty_write_message() has only one user: quotas. In particular, there the
use depends on CONFIG_PRINT_QUOTA_WARNING. And that is deprecated and
marked as BROKEN already too.

So make tty_write_message() dependent on that very config option. This
action in fact drops tty_write_message() from the vmlinux binary. Good
riddance.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Jan Kara <jack@suse.com>
Acked-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20231121092258.9334-2-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 06414e43e0b53..ee5a90f9adb54 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1047,6 +1047,7 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_PRINT_QUOTA_WARNING
 /**
  * tty_write_message - write a message to a certain tty, not just the console.
  * @tty: the destination tty_struct
@@ -1057,6 +1058,8 @@ out:
  * needed.
  *
  * We must still hold the BTM and test the CLOSING flag for the moment.
+ *
+ * This function is DEPRECATED, do not use in new code.
  */
 void tty_write_message(struct tty_struct *tty, char *msg)
 {
@@ -1069,6 +1072,7 @@ void tty_write_message(struct tty_struct *tty, char *msg)
 		tty_write_unlock(tty);
 	}
 }
+#endif
 
 static ssize_t file_tty_write(struct file *file, struct kiocb *iocb, struct iov_iter *from)
 {
-- 
GitLab


From d22d53ad8ae8414c547c24de0b828a622fc45ea1 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:43 +0100
Subject: [PATCH 0442/4076] tty: remove unneeded mbz from tiocsti()

'mbz' in tiocsti() is used only to pass TTY_NORMAL to
tty_ldisc_ops::receive_buf(). But that can be achieved easier by simply
passing NULL to ::receive_buf().

So drop this 'mbz'.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-3-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index ee5a90f9adb54..005d91c637072 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2280,7 +2280,7 @@ static bool tty_legacy_tiocsti __read_mostly = IS_ENABLED(CONFIG_LEGACY_TIOCSTI)
  */
 static int tiocsti(struct tty_struct *tty, char __user *p)
 {
-	char ch, mbz = 0;
+	char ch;
 	struct tty_ldisc *ld;
 
 	if (!tty_legacy_tiocsti && !capable(CAP_SYS_ADMIN))
@@ -2296,7 +2296,7 @@ static int tiocsti(struct tty_struct *tty, char __user *p)
 		return -EIO;
 	tty_buffer_lock_exclusive(tty->port);
 	if (ld->ops->receive_buf)
-		ld->ops->receive_buf(tty, &ch, &mbz, 1);
+		ld->ops->receive_buf(tty, &ch, NULL, 1);
 	tty_buffer_unlock_exclusive(tty->port);
 	tty_ldisc_deref(ld);
 	return 0;
-- 
GitLab


From 239123e7e8ec4d35c8591c48f5de44925a88391d Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:45 +0100
Subject: [PATCH 0443/4076] tty: move locking docs out of Returns for functions
 in tty.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Both tty_kref_get() and tty_get_baud_rate() note about locking in their
Return kernel-doc clause. Extract this info into a separate "Locking"
paragraph -- the same as we do for other tty functions.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231121092258.9334-5-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 4b6340ac2af28..7625fc98fef3f 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -393,8 +393,10 @@ extern const struct class tty_class;
  * tty_kref_get - get a tty reference
  * @tty: tty device
  *
- * Returns: a new reference to a tty object. The caller must hold sufficient
- * locks/counts to ensure that their existing reference cannot go away
+ * Returns: a new reference to a tty object
+ *
+ * Locking: The caller must hold sufficient locks/counts to ensure that their
+ * existing reference cannot go away.
  */
 static inline struct tty_struct *tty_kref_get(struct tty_struct *tty)
 {
@@ -436,10 +438,10 @@ void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud,
  * tty_get_baud_rate - get tty bit rates
  * @tty: tty to query
  *
- * Returns: the baud rate as an integer for this terminal. The termios lock
- * must be held by the caller and the terminal bit flags may be updated.
+ * Returns: the baud rate as an integer for this terminal
  *
- * Locking: none
+ * Locking: The termios lock must be held by the caller and the terminal bit
+ * flags may be updated.
  */
 static inline speed_t tty_get_baud_rate(struct tty_struct *tty)
 {
-- 
GitLab


From c35e6ec1f3138c15cfd746f61feb8d789d1e8fb1 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:46 +0100
Subject: [PATCH 0444/4076] tty: amiserial: return from receive_chars() without
 goto

The 'out' label is just before 'return'. So return immediately and drop
both the label and the return. This makes the code more straightforward.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-6-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/amiserial.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index 785558c65ae80..b9580bb9afd3b 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -230,7 +230,7 @@ static void receive_chars(struct serial_state *info)
 	   * should be ignored.
 	   */
 	  if (status & info->ignore_status_mask)
-	    goto out;
+		  return;
 
 	  status &= info->read_status_mask;
 
@@ -258,8 +258,6 @@ static void receive_chars(struct serial_state *info)
 	if (oe == 1)
 		tty_insert_flip_char(&info->tport, 0, TTY_OVERRUN);
 	tty_flip_buffer_push(&info->tport);
-out:
-	return;
 }
 
 static void transmit_chars(struct serial_state *info)
-- 
GitLab


From 73b2ed3675697f1b20d5fa3408397c65a2cbc13e Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:47 +0100
Subject: [PATCH 0445/4076] tty: amiserial: use bool and rename overrun flag in
 receive_chars()

'oe' is a yes-no flag, switch it to boolean. And rename to overrun. All
for the code to be more obvious.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-7-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/amiserial.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index b9580bb9afd3b..a80f059f77bf0 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -180,7 +180,7 @@ static void receive_chars(struct serial_state *info)
 	int serdatr;
 	unsigned char ch, flag;
 	struct	async_icount *icount;
-	int oe = 0;
+	bool overrun = false;
 
 	icount = &info->icount;
 
@@ -251,11 +251,11 @@ static void receive_chars(struct serial_state *info)
 	     * reported immediately, and doesn't
 	     * affect the current character
 	     */
-	     oe = 1;
+	     overrun = true;
 	  }
 	}
 	tty_insert_flip_char(&info->tport, ch, flag);
-	if (oe == 1)
+	if (overrun)
 		tty_insert_flip_char(&info->tport, 0, TTY_OVERRUN);
 	tty_flip_buffer_push(&info->tport);
 }
-- 
GitLab


From 9d3e3301ae9958809b4d96787eaf76221c704ed6 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:48 +0100
Subject: [PATCH 0446/4076] tty: ehv_bytecha: use memcpy_and_pad() in
 local_ev_byte_channel_send()

There is a helper for memcpy(buffer)+memset(the_rest). Use it for
simplicity.

And add a comment why we are doing the copy in the first place.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20231121092258.9334-8-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/ehv_bytechan.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/ehv_bytechan.c b/drivers/tty/ehv_bytechan.c
index a067628e01c81..cc9f4338da601 100644
--- a/drivers/tty/ehv_bytechan.c
+++ b/drivers/tty/ehv_bytechan.c
@@ -143,9 +143,12 @@ static unsigned int local_ev_byte_channel_send(unsigned int handle,
 	char buffer[EV_BYTE_CHANNEL_MAX_BYTES];
 	unsigned int c = *count;
 
+	/*
+	 * ev_byte_channel_send() expects at least EV_BYTE_CHANNEL_MAX_BYTES
+	 * (16 B) in the buffer. Fake it using a local buffer if needed.
+	 */
 	if (c < sizeof(buffer)) {
-		memcpy(buffer, p, c);
-		memset(&buffer[c], 0, sizeof(buffer) - c);
+		memcpy_and_pad(buffer, sizeof(buffer), p, c, 0);
 		p = buffer;
 	}
 	return ev_byte_channel_send(handle, count, p);
-- 
GitLab


From 7cf61de7f748e6f2b6091e3b35a4ddb307193fa8 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:49 +0100
Subject: [PATCH 0447/4076] tty: goldfish: drop unneeded temporary variables

We can pass 'buf' directly to goldfish_tty_rw() using simple (unsigned
long) cast. There is no need to obfuscate the code by another variable
with double casts.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-9-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/goldfish.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c
index 4591f940b7a15..dccf6c6c69c6e 100644
--- a/drivers/tty/goldfish.c
+++ b/drivers/tty/goldfish.c
@@ -128,16 +128,14 @@ static void goldfish_tty_rw(struct goldfish_tty *qtty,
 static void goldfish_tty_do_write(int line, const u8 *buf, unsigned int count)
 {
 	struct goldfish_tty *qtty = &goldfish_ttys[line];
-	unsigned long address = (unsigned long)(void *)buf;
 
-	goldfish_tty_rw(qtty, address, count, 1);
+	goldfish_tty_rw(qtty, (unsigned long)buf, count, 1);
 }
 
 static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 {
 	struct goldfish_tty *qtty = dev_id;
 	void __iomem *base = qtty->base;
-	unsigned long address;
 	unsigned char *buf;
 	u32 count;
 
@@ -147,8 +145,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 
 	count = tty_prepare_flip_string(&qtty->port, &buf, count);
 
-	address = (unsigned long)(void *)buf;
-	goldfish_tty_rw(qtty, address, count, 0);
+	goldfish_tty_rw(qtty, (unsigned long)buf, count, 0);
 
 	tty_flip_buffer_push(&qtty->port);
 	return IRQ_HANDLED;
-- 
GitLab


From e4b3cd3b6a0d79857d561af999451fc958457dee Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:50 +0100
Subject: [PATCH 0448/4076] tty: hso: don't emit load/unload info to the log

It's preferred NOT to emit anything during the module load and unload
(in case the un/load was successful). So drop these prints from hso
along with global 'version'. It even contains no version after all.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-usb@vger.kernel.org
Cc: netdev@vger.kernel.org
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-10-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/usb/hso.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 83b8452220ec1..48450fe861add 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -363,7 +363,6 @@ static int disable_net;
 /* driver info */
 static const char driver_name[] = "hso";
 static const char tty_filename[] = "ttyHS";
-static const char *version = __FILE__ ": " MOD_AUTHOR;
 /* the usb driver itself (registered in hso_init) */
 static struct usb_driver hso_driver;
 /* serial structures */
@@ -3231,9 +3230,6 @@ static int __init hso_init(void)
 	int i;
 	int result;
 
-	/* put it in the log */
-	pr_info("%s\n", version);
-
 	/* Initialise the serial table semaphore and table */
 	for (i = 0; i < HSO_SERIAL_TTY_MINORS; i++)
 		serial_table[i] = NULL;
@@ -3285,8 +3281,6 @@ err_free_tty:
 
 static void __exit hso_exit(void)
 {
-	pr_info("unloaded\n");
-
 	tty_unregister_driver(tty_drv);
 	/* deregister the usb driver */
 	usb_deregister(&hso_driver);
-- 
GitLab


From 4ccef1f142effe765a130c7b020c36eec6bd2a31 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:51 +0100
Subject: [PATCH 0449/4076] tty: hso: don't initialize global serial_table

'serial_table' is global, so there is no need to initialize it to NULLs
at the module load. Drop this unneeded for loop.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-usb@vger.kernel.org
Cc: netdev@vger.kernel.org
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-11-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/usb/hso.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 48450fe861add..f088ea2ba6f39 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -3227,13 +3227,8 @@ static struct usb_driver hso_driver = {
 
 static int __init hso_init(void)
 {
-	int i;
 	int result;
 
-	/* Initialise the serial table semaphore and table */
-	for (i = 0; i < HSO_SERIAL_TTY_MINORS; i++)
-		serial_table[i] = NULL;
-
 	/* allocate our driver using the proper amount of supported minors */
 	tty_drv = tty_alloc_driver(HSO_SERIAL_TTY_MINORS, TTY_DRIVER_REAL_RAW |
 			TTY_DRIVER_DYNAMIC_DEV);
-- 
GitLab


From 7588b0820354694f4e3a2fbadc4d39176ee221aa Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:52 +0100
Subject: [PATCH 0450/4076] tty: hvc_console: use flexible array for outbuf

This means:
* move outbuf to the end of struct hvc_struct and convert from pointer
  to flexible array (the structure is smaller now)
* use struct_size() at the allocation site
* align outbuf in the struct instead of ALIGN() at kzalloc()

And apart from the above, use u8 instead of char (which are the same
thanks to -funsigned-char). The former is now preferred over the latter.

It makes the code easier to understand.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20231121092258.9334-12-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/hvc/hvc_console.c | 4 +---
 drivers/tty/hvc/hvc_console.h | 2 +-
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index 57f5c37125e63..cd1f657f782df 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -922,8 +922,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 			return ERR_PTR(err);
 	}
 
-	hp = kzalloc(ALIGN(sizeof(*hp), sizeof(long)) + outbuf_size,
-			GFP_KERNEL);
+	hp = kzalloc(struct_size(hp, outbuf, outbuf_size), GFP_KERNEL);
 	if (!hp)
 		return ERR_PTR(-ENOMEM);
 
@@ -931,7 +930,6 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 	hp->data = data;
 	hp->ops = ops;
 	hp->outbuf_size = outbuf_size;
-	hp->outbuf = &((char *)hp)[ALIGN(sizeof(*hp), sizeof(long))];
 
 	tty_port_init(&hp->port);
 	hp->port.ops = &hvc_port_ops;
diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h
index 78f7543511f10..4062f8ad84df3 100644
--- a/drivers/tty/hvc/hvc_console.h
+++ b/drivers/tty/hvc/hvc_console.h
@@ -37,7 +37,6 @@ struct hvc_struct {
 	spinlock_t lock;
 	int index;
 	int do_wakeup;
-	char *outbuf;
 	int outbuf_size;
 	int n_outbuf;
 	uint32_t vtermno;
@@ -48,6 +47,7 @@ struct hvc_struct {
 	struct work_struct tty_resize;
 	struct list_head next;
 	unsigned long flags;
+	u8 outbuf[] __aligned(sizeof(long));
 };
 
 /* implemented by a low level driver */
-- 
GitLab


From 2bf93a48ccaace03e29b87cc92e369cade23d15a Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:53 +0100
Subject: [PATCH 0451/4076] tty: nozomi: remove unused debugging DUMP()

DUMP()'s only use is commented out. Remove the macro completely along
with this unused use.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-13-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/nozomi.c | 18 ------------------
 1 file changed, 18 deletions(-)

diff --git a/drivers/tty/nozomi.c b/drivers/tty/nozomi.c
index 02cd40147b3a8..b247341bd12f5 100644
--- a/drivers/tty/nozomi.c
+++ b/drivers/tty/nozomi.c
@@ -65,24 +65,8 @@ do {							\
 #define DBG3(args...) DBG_(0x04, ##args)
 #define DBG4(args...) DBG_(0x08, ##args)
 
-/* TODO: rewrite to optimize macros... */
-
 #define TMP_BUF_MAX 256
 
-#define DUMP(buf__, len__)						\
-	do {								\
-		char tbuf[TMP_BUF_MAX] = {0};				\
-		if (len__ > 1) {					\
-			u32 data_len = min_t(u32, len__, TMP_BUF_MAX);	\
-			strscpy(tbuf, buf__, data_len);			\
-			if (tbuf[data_len - 2] == '\r')			\
-				tbuf[data_len - 2] = 'r';		\
-			DBG1("SENDING: '%s' (%d+n)", tbuf, len__);	\
-		} else {						\
-			DBG1("SENDING: '%s' (%d)", tbuf, len__);	\
-		}							\
-	} while (0)
-
 /*    Defines */
 #define NOZOMI_NAME		"nozomi"
 #define NOZOMI_NAME_TTY		"nozomi_tty"
@@ -754,8 +738,6 @@ static int send_data(enum port_type index, struct nozomi *dc)
 		return 0;
 	}
 
-	/* DUMP(buf, size); */
-
 	/* Write length + data */
 	write_mem32(addr, (u32 *) &size, 4);
 	write_mem32(addr + 4, (u32 *) dc->send_buf, size);
-- 
GitLab


From ab58841ab9fca536e5579312d7b46cbc4822e29c Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:54 +0100
Subject: [PATCH 0452/4076] tty: srmcons: use 'buf' directly in
 srmcons_do_write()

There is no need to have a separate iterator ('cur') through 'buf' in
srmcons_do_write(). 'buf' can be used directly which simplifies the code
a bit.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: linux-alpha@vger.kernel.org
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Link: https://lore.kernel.org/r/20231121092258.9334-14-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/alpha/kernel/srmcons.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index d6139dbae4ac9..b68c5af083cd1 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -94,24 +94,23 @@ srmcons_do_write(struct tty_port *port, const char *buf, int count)
 	static char str_cr[1] = "\r";
 	long c, remaining = count;
 	srmcons_result result;
-	char *cur;
 	int need_cr;
 
-	for (cur = (char *)buf; remaining > 0; ) {
+	while (remaining > 0) {
 		need_cr = 0;
 		/* 
 		 * Break it up into reasonable size chunks to allow a chance
 		 * for input to get in
 		 */
 		for (c = 0; c < min_t(long, 128L, remaining) && !need_cr; c++)
-			if (cur[c] == '\n')
+			if (buf[c] == '\n')
 				need_cr = 1;
 		
 		while (c > 0) {
-			result.as_long = callback_puts(0, cur, c);
+			result.as_long = callback_puts(0, buf, c);
 			c -= result.bits.c;
 			remaining -= result.bits.c;
-			cur += result.bits.c;
+			buf += result.bits.c;
 
 			/*
 			 * Check for pending input iff a tty port was provided
-- 
GitLab


From 6ed18323c7d0748883ad74b3f819fb156753bbc9 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Wed, 22 Nov 2023 08:56:29 +0100
Subject: [PATCH 0453/4076] MAINTAINERS: improve section MICROCHIP MCP3564 ADC
 DRIVER

Commit 33ec3e5fc1ea ("iio: adc: adding support for MCP3564 ADC") adds a new
iio driver and corresponding MAINTAINERS section. It however uses spaces
instead of a single tab for all the entries in that MAINTAINERS section.

Although, the get_maintainer.pl script handles spaces instead of tabs
silently, the MAINTAINERS will quickly get into a messy state with
different indentations throughout the file. So, the checkpatch.pl script
complains when spaces instead of a single tab are used.

Fix this recently added section using tabs instead of spaces.
Further, add the driver's ABI documentation file to this section as well.

Fixes: 33ec3e5fc1ea ("iio: adc: adding support for MCP3564 ADC")
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Link: https://lore.kernel.org/r/20231122075629.21411-1-lukas.bulwahn@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8e0a91dc8251a..cd9591df77d73 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14196,11 +14196,12 @@ F:	Documentation/devicetree/bindings/regulator/mcp16502-regulator.txt
 F:	drivers/regulator/mcp16502.c
 
 MICROCHIP MCP3564 ADC DRIVER
-M:      Marius Cristea <marius.cristea@microchip.com>
-L:      linux-iio@vger.kernel.org
-S:      Supported
-F:      Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
-F:      drivers/iio/adc/mcp3564.c
+M:	Marius Cristea <marius.cristea@microchip.com>
+L:	linux-iio@vger.kernel.org
+S:	Supported
+F:	Documentation/ABI/testing/sysfs-bus-iio-adc-mcp3564
+F:	Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
+F:	drivers/iio/adc/mcp3564.c
 
 MICROCHIP MCP3911 ADC DRIVER
 M:	Marcus Folkesson <marcus.folkesson@gmail.com>
-- 
GitLab


From 1cba275017352ba887058934d23b5c76a3de62ae Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Sun, 26 Nov 2023 01:02:48 -0800
Subject: [PATCH 0454/4076] apparmor: cleanup network hook comments

Drop useless partial kernel doc style comments. Finish/update kerneldoc
comment where there is useful information

Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/lsm.c | 60 +++++++++++------------------------------
 1 file changed, 16 insertions(+), 44 deletions(-)

diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index d3d2fc13c6e7c..3eb992801a7f5 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -987,9 +987,6 @@ static int apparmor_userns_create(const struct cred *cred)
 	return error;
 }
 
-/**
- * apparmor_sk_alloc_security - allocate and attach the sk_security field
- */
 static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags)
 {
 	struct aa_sk_ctx *ctx;
@@ -1003,9 +1000,6 @@ static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags)
 	return 0;
 }
 
-/**
- * apparmor_sk_free_security - free the sk_security field
- */
 static void apparmor_sk_free_security(struct sock *sk)
 {
 	struct aa_sk_ctx *ctx = aa_sock(sk);
@@ -1018,6 +1012,8 @@ static void apparmor_sk_free_security(struct sock *sk)
 
 /**
  * apparmor_sk_clone_security - clone the sk_security field
+ * @sk: sock to have security cloned
+ * @newsk: sock getting clone
  */
 static void apparmor_sk_clone_security(const struct sock *sk,
 				       struct sock *newsk)
@@ -1034,9 +1030,6 @@ static void apparmor_sk_clone_security(const struct sock *sk,
 	new->peer = aa_get_label(ctx->peer);
 }
 
-/**
- * apparmor_socket_create - check perms before creating a new socket
- */
 static int apparmor_socket_create(int family, int type, int protocol, int kern)
 {
 	struct aa_label *label;
@@ -1058,10 +1051,14 @@ static int apparmor_socket_create(int family, int type, int protocol, int kern)
 
 /**
  * apparmor_socket_post_create - setup the per-socket security struct
+ * @sock: socket that is being setup
+ * @family: family of socket being created
+ * @type: type of the socket
+ * @ptotocol: protocol of the socket
+ * @kern: socket is a special kernel socket
  *
  * Note:
- * -   kernel sockets currently labeled unconfined but we may want to
- *     move to a special kernel label
+ * -   kernel sockets labeled kernel_t used to use unconfined
  * -   socket may not have sk here if created with sock_create_lite or
  *     sock_alloc. These should be accept cases which will be handled in
  *     sock_graft.
@@ -1087,9 +1084,6 @@ static int apparmor_socket_post_create(struct socket *sock, int family,
 	return 0;
 }
 
-/**
- * apparmor_socket_bind - check perms before bind addr to socket
- */
 static int apparmor_socket_bind(struct socket *sock,
 				struct sockaddr *address, int addrlen)
 {
@@ -1103,9 +1097,6 @@ static int apparmor_socket_bind(struct socket *sock,
 			 aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk));
 }
 
-/**
- * apparmor_socket_connect - check perms before connecting @sock to @address
- */
 static int apparmor_socket_connect(struct socket *sock,
 				   struct sockaddr *address, int addrlen)
 {
@@ -1119,9 +1110,6 @@ static int apparmor_socket_connect(struct socket *sock,
 			 aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk));
 }
 
-/**
- * apparmor_socket_listen - check perms before allowing listen
- */
 static int apparmor_socket_listen(struct socket *sock, int backlog)
 {
 	AA_BUG(!sock);
@@ -1133,9 +1121,7 @@ static int apparmor_socket_listen(struct socket *sock, int backlog)
 			 aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk));
 }
 
-/**
- * apparmor_socket_accept - check perms before accepting a new connection.
- *
+/*
  * Note: while @newsock is created and has some information, the accept
  *       has not been done.
  */
@@ -1164,18 +1150,12 @@ static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock,
 			 aa_sk_perm(op, request, sock->sk));
 }
 
-/**
- * apparmor_socket_sendmsg - check perms before sending msg to another socket
- */
 static int apparmor_socket_sendmsg(struct socket *sock,
 				   struct msghdr *msg, int size)
 {
 	return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size);
 }
 
-/**
- * apparmor_socket_recvmsg - check perms before receiving a message
- */
 static int apparmor_socket_recvmsg(struct socket *sock,
 				   struct msghdr *msg, int size, int flags)
 {
@@ -1194,17 +1174,11 @@ static int aa_sock_perm(const char *op, u32 request, struct socket *sock)
 			 aa_sk_perm(op, request, sock->sk));
 }
 
-/**
- * apparmor_socket_getsockname - check perms before getting the local address
- */
 static int apparmor_socket_getsockname(struct socket *sock)
 {
 	return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock);
 }
 
-/**
- * apparmor_socket_getpeername - check perms before getting remote address
- */
 static int apparmor_socket_getpeername(struct socket *sock)
 {
 	return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock);
@@ -1223,9 +1197,6 @@ static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock,
 			 aa_sk_perm(op, request, sock->sk));
 }
 
-/**
- * apparmor_socket_getsockopt - check perms before getting socket options
- */
 static int apparmor_socket_getsockopt(struct socket *sock, int level,
 				      int optname)
 {
@@ -1233,9 +1204,6 @@ static int apparmor_socket_getsockopt(struct socket *sock, int level,
 				level, optname);
 }
 
-/**
- * apparmor_socket_setsockopt - check perms before setting socket options
- */
 static int apparmor_socket_setsockopt(struct socket *sock, int level,
 				      int optname)
 {
@@ -1243,9 +1211,6 @@ static int apparmor_socket_setsockopt(struct socket *sock, int level,
 				level, optname);
 }
 
-/**
- * apparmor_socket_shutdown - check perms before shutting down @sock conn
- */
 static int apparmor_socket_shutdown(struct socket *sock, int how)
 {
 	return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock);
@@ -1254,6 +1219,8 @@ static int apparmor_socket_shutdown(struct socket *sock, int how)
 #ifdef CONFIG_NETWORK_SECMARK
 /**
  * apparmor_socket_sock_rcv_skb - check perms before associating skb to sk
+ * @sk: sk to associate @skb with
+ * @skb: skb to check for perms
  *
  * Note: can not sleep may be called with locks held
  *
@@ -1285,6 +1252,11 @@ static struct aa_label *sk_peer_label(struct sock *sk)
 
 /**
  * apparmor_socket_getpeersec_stream - get security context of peer
+ * @sock: socket that we are trying to get the peer context of
+ * @optval: output - buffer to copy peer name to
+ * @optlen: output - size of copied name in @optval
+ * @len: size of @optval buffer
+ * Returns: 0 on success, -errno of failure
  *
  * Note: for tcp only valid if using ipsec or cipso on lan
  */
-- 
GitLab


From f0a8eb60836cd23b72ae83aa7c3b03a5af8e9191 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 23 Nov 2023 09:43:33 -0500
Subject: [PATCH 0455/4076] staging: rtl8192e: renamed variable HTMcsToDataRate

Renamed variable from Pascal/CamelCase to Snake case the variable
HTMcsToDataRate.
HTMcsToDataRate -> ht_mcs_to_data_rate

Linux Kernel coding style (cleanup), checkpatch Avoid CamelCase.
Driver/module rtl8192e compiles.

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231123144337.13112-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index d5520cc82d229..95ed79f346317 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -103,7 +103,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->rx_reorder_pending_time = 30;
 }
 
-static u16 HTMcsToDataRate(struct rtllib_device *ieee, u8 nMcsRate)
+static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 nMcsRate)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
@@ -422,8 +422,8 @@ u8 HTGetHighestMCSRate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 			bitMap = availableMcsRate[i];
 			for (j = 0; j < 8; j++) {
 				if ((bitMap % 2) != 0) {
-					if (HTMcsToDataRate(ieee, (8 * i + j)) >
-					    HTMcsToDataRate(ieee, mcsRate))
+					if (ht_mcs_to_data_rate(ieee, (8 * i + j)) >
+					    ht_mcs_to_data_rate(ieee, mcsRate))
 						mcsRate = 8 * i + j;
 				}
 				bitMap >>= 1;
-- 
GitLab


From 55401b86e04a1b0a5cb89556d58297e9040597a3 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 23 Nov 2023 09:43:34 -0500
Subject: [PATCH 0456/4076] staging: rtl8192e: renamed variable
 TXCountToDataRate

Renamed from Pascal/CamelCase to Snake case the variable
TXCountToDataRate.
TXCountToDataRate -> tx_count_to_data_rate

Linux kernel coding style (cleanup), checkpatch Avoid CamelCase.
Driver/module rtl8192e compiles.

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231123144337.13112-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c    | 2 +-
 drivers/staging/rtl8192e/rtllib.h            | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac_wx.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 95ed79f346317..6bf48543c3390 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -114,7 +114,7 @@ static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 nMcsRate)
 	return MCS_DATA_RATE[is40MHz][isShortGI][(nMcsRate & 0x7f)];
 }
 
-u16  TxCountToDataRate(struct rtllib_device *ieee, u8 nDataRate)
+u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate)
 {
 	u16	CCKOFDMRate[12] = {0x02, 0x04, 0x0b, 0x16, 0x0c, 0x12, 0x18,
 				   0x24, 0x30, 0x48, 0x60, 0x6c};
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 77ae259eab355..f853be8d4d087 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1780,7 +1780,7 @@ extern u16 MCS_DATA_RATE[2][2][77];
 u8 HTCCheck(struct rtllib_device *ieee, u8 *pFrame);
 void HTResetIOTSetting(struct rt_hi_throughput *ht_info);
 bool IsHTHalfNmodeAPs(struct rtllib_device *ieee);
-u16  TxCountToDataRate(struct rtllib_device *ieee, u8 nDataRate);
+u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate);
 int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb);
 int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb);
 int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
index f32584291704e..28aba1d610f7d 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
@@ -208,7 +208,7 @@ int rtllib_wx_get_rate(struct rtllib_device *ieee,
 {
 	u32 tmp_rate;
 
-	tmp_rate = TxCountToDataRate(ieee,
+	tmp_rate = tx_count_to_data_rate(ieee,
 				     ieee->softmac_stats.CurrentShowTxate);
 	wrqu->bitrate.value = tmp_rate * 500000;
 
-- 
GitLab


From ea6df150dd4a30d260df6a583e78ec641e023ce7 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 23 Nov 2023 09:43:35 -0500
Subject: [PATCH 0457/4076] staging: rtl8192e: renamed variable
 IsHTHalfNmodeAPs

Renamed from Pascal/CamelCase to Snake case the variable
IsHTHalfNmodeAPs.
ISHTHalfNmodeAPs -> is_ht_half_nmode_aps

Linux kernel coding style (cleanup), checkpatch Avoid CamelCase.
Driver/module rtl8192e compiles.

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231123144337.13112-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 6bf48543c3390..022b694eeef33 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -139,7 +139,7 @@ u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate)
 	return MCS_DATA_RATE[is40MHz][isShortGI][nDataRate & 0xf];
 }
 
-bool IsHTHalfNmodeAPs(struct rtllib_device *ieee)
+bool is_ht_half_nmode_aps(struct rtllib_device *ieee)
 {
 	bool			retValue = false;
 	struct rtllib_network *net = &ieee->current_network;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index f853be8d4d087..5d6563d12480f 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1779,7 +1779,7 @@ extern u8 MCS_FILTER_ALL[];
 extern u16 MCS_DATA_RATE[2][2][77];
 u8 HTCCheck(struct rtllib_device *ieee, u8 *pFrame);
 void HTResetIOTSetting(struct rt_hi_throughput *ht_info);
-bool IsHTHalfNmodeAPs(struct rtllib_device *ieee);
+bool is_ht_half_nmode_aps(struct rtllib_device *ieee);
 u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate);
 int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb);
 int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 08349f522c830..2ce4f64f88f67 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1858,7 +1858,7 @@ static void rtllib_rx_auth_resp(struct rtllib_device *ieee, struct sk_buff *skb)
 		ieee->softmac_stats.rx_auth_rs_ok++;
 		if (!(ieee->ht_info->iot_action & HT_IOT_ACT_PURE_N_MODE)) {
 			if (!ieee->GetNmodeSupportBySecCfg(ieee->dev)) {
-				if (IsHTHalfNmodeAPs(ieee)) {
+				if (is_ht_half_nmode_aps(ieee)) {
 					bSupportNmode = true;
 					bHalfSupportNmode = true;
 				} else {
-- 
GitLab


From d6171fe96f9507be97d9ec8ec41cce5a1b7deca3 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 23 Nov 2023 09:43:36 -0500
Subject: [PATCH 0458/4076] staging: rtl8192e: renamed variable
 HTIOTPeerDetermine

Renamed from Pascal/CamelCase to Snake case the variable
HTIOTPeerDetermine.
HTIOTPeerDetermine -> ht_iot_peer_determine

Linux kernel coding style (cleanup), checkpatch Avoid CamelCase.
Driver/module rtl8192e compiles.

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231123144337.13112-5-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 022b694eeef33..99721e1a604a5 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -164,7 +164,7 @@ bool is_ht_half_nmode_aps(struct rtllib_device *ieee)
 	return retValue;
 }
 
-static void HTIOTPeerDetermine(struct rtllib_device *ieee)
+static void ht_iot_peer_determine(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 	struct rtllib_network *net = &ieee->current_network;
@@ -672,7 +672,7 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 			ht_info->RT2RT_HT_Mode = (enum rt_ht_capability)0;
 		}
 
-		HTIOTPeerDetermine(ieee);
+		ht_iot_peer_determine(ieee);
 
 		ht_info->iot_action = 0;
 		bIOTAction = HTIOTActIsMgntUseCCK6M(ieee, pNetwork);
-- 
GitLab


From 32992c40e2852afc488cfa6512da69ef49dfab43 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 23 Nov 2023 09:43:37 -0500
Subject: [PATCH 0459/4076] staging: rtl8192e: renamed variable
 HTIOTActIsMgntUseCCK6M

Renamed from Pascal/CamelCase to Snake case the variable
HTIOTActIsMgntUseCCK6M.
HTIOTActIsMgntUseCCK6M -> ht_iot_act_is_mgnt_use_cck_6m

Linux kernel coding style (cleanup), checkpatch Avoid CamelCase.
Driver/module rtl8192e compiles.

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/20231123144337.13112-6-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 99721e1a604a5..da4cf6f257941 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -207,7 +207,7 @@ static void ht_iot_peer_determine(struct rtllib_device *ieee)
 	netdev_dbg(ieee->dev, "IOTPEER: %x\n", ht_info->IOTPeer);
 }
 
-static u8 HTIOTActIsMgntUseCCK6M(struct rtllib_device *ieee,
+static u8 ht_iot_act_is_mgnt_use_cck_6m(struct rtllib_device *ieee,
 				 struct rtllib_network *network)
 {
 	u8	retValue = 0;
@@ -675,7 +675,7 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 		ht_iot_peer_determine(ieee);
 
 		ht_info->iot_action = 0;
-		bIOTAction = HTIOTActIsMgntUseCCK6M(ieee, pNetwork);
+		bIOTAction = ht_iot_act_is_mgnt_use_cck_6m(ieee, pNetwork);
 		if (bIOTAction)
 			ht_info->iot_action |= HT_IOT_ACT_MGNT_USE_CCK_6M;
 		bIOTAction = HTIOTActIsCCDFsync(ieee);
-- 
GitLab


From eca8285c01e1c30e49685bd241bfbb1f7622c927 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 24 Nov 2023 22:30:23 +0100
Subject: [PATCH 0460/4076] staging: rtl8192e: Remove unused interrupt for
 IMR_BcnInt

Driver does not support AP Mode therefore no beacons need to be send.
Remove unused interrupt for IMR_BcnInt.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/64a1f672dbe2ed2c6a660fa1044bd058fe3ba91a.1700860758.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../staging/rtl8192e/rtl8192e/r8192E_dev.c    |  2 +-
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c  | 37 -------------------
 drivers/staging/rtl8192e/rtl8192e/rtl_core.h  |  1 -
 3 files changed, 1 insertion(+), 39 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index 8fe4c03b19c1b..73315a236e769 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -1802,7 +1802,7 @@ rtl92e_init_variables(struct net_device  *dev)
 			    IMR_MGNTDOK | IMR_COMDOK | IMR_HIGHDOK |
 			    IMR_BDOK | IMR_RXCMDOK | IMR_TIMEOUT0 |
 			    IMR_RDU | IMR_RXFOVW | IMR_TXFOVW |
-			    IMR_BcnInt | IMR_TBDOK | IMR_TBDER);
+			    IMR_TBDOK | IMR_TBDER);
 
 	priv->bfirst_after_down = false;
 }
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index c3466291e221d..fc6e8ea039a3b 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -416,38 +416,6 @@ static int _rtl92e_handle_assoc_response(struct net_device *dev,
 	return 0;
 }
 
-static void _rtl92e_prepare_beacon(struct tasklet_struct *t)
-{
-	struct r8192_priv *priv = from_tasklet(priv, t,
-					       irq_prepare_beacon_tasklet);
-	struct net_device *dev = priv->rtllib->dev;
-	struct sk_buff *pskb = NULL, *pnewskb = NULL;
-	struct cb_desc *tcb_desc = NULL;
-	struct rtl8192_tx_ring *ring = NULL;
-	struct tx_desc *pdesc = NULL;
-
-	ring = &priv->tx_ring[BEACON_QUEUE];
-	pskb = __skb_dequeue(&ring->queue);
-	kfree_skb(pskb);
-
-	pnewskb = rtllib_get_beacon(priv->rtllib);
-	if (!pnewskb)
-		return;
-
-	tcb_desc = (struct cb_desc *)(pnewskb->cb + 8);
-	tcb_desc->queue_index = BEACON_QUEUE;
-	tcb_desc->data_rate = 2;
-	tcb_desc->ratr_index = 7;
-	tcb_desc->tx_dis_rate_fallback = 1;
-	tcb_desc->tx_use_drv_assinged_rate = 1;
-	skb_push(pnewskb, priv->rtllib->tx_headroom);
-
-	pdesc = &ring->desc[0];
-	rtl92e_fill_tx_desc(dev, pdesc, tcb_desc, pnewskb);
-	__skb_queue_tail(&ring->queue, pnewskb);
-	pdesc->OWN = 1;
-}
-
 void rtl92e_config_rate(struct net_device *dev, u16 *rate_config)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
@@ -785,8 +753,6 @@ static void _rtl92e_init_priv_task(struct net_device *dev)
 	INIT_DELAYED_WORK(&priv->rtllib->hw_sleep_wq, (void *)rtl92e_hw_sleep_wq);
 	tasklet_setup(&priv->irq_rx_tasklet, _rtl92e_irq_rx_tasklet);
 	tasklet_setup(&priv->irq_tx_tasklet, _rtl92e_irq_tx_tasklet);
-	tasklet_setup(&priv->irq_prepare_beacon_tasklet,
-		      _rtl92e_prepare_beacon);
 }
 
 static short _rtl92e_get_channel_map(struct net_device *dev)
@@ -1810,9 +1776,6 @@ static irqreturn_t _rtl92e_irq(int irq, void *netdev)
 	if (inta & IMR_ROK)
 		tasklet_schedule(&priv->irq_rx_tasklet);
 
-	if (inta & IMR_BcnInt)
-		tasklet_schedule(&priv->irq_prepare_beacon_tasklet);
-
 	if (inta & IMR_RDU) {
 		rtl92e_writel(dev, INTA_MASK,
 			      rtl92e_readl(dev, INTA_MASK) & ~IMR_RDU);
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
index e7b331c4661c7..846f0f7a737ba 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
@@ -219,7 +219,6 @@ struct r8192_priv {
 
 	struct tasklet_struct		irq_rx_tasklet;
 	struct tasklet_struct		irq_tx_tasklet;
-	struct tasklet_struct		irq_prepare_beacon_tasklet;
 
 	struct mutex				wx_mutex;
 	struct mutex				rf_mutex;
-- 
GitLab


From 786b6f5764fffee0da0e8e6d0580278bbb903c11 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 24 Nov 2023 22:30:39 +0100
Subject: [PATCH 0461/4076] staging: rtl8192e: Remove unused function
 rtllib_get_beacon()

Remove unused function rtllib_get_beacon().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/d76eeb7e273f4fcfec4ae8879e56d237363ebde2.1700860758.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h         |  1 -
 drivers/staging/rtl8192e/rtllib_softmac.c | 21 ---------------------
 2 files changed, 22 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 5d6563d12480f..835b407ab1806 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1693,7 +1693,6 @@ void rtllib_softmac_start_protocol(struct rtllib_device *ieee);
 void rtllib_reset_queue(struct rtllib_device *ieee);
 void rtllib_wake_all_queues(struct rtllib_device *ieee);
 void rtllib_stop_all_queues(struct rtllib_device *ieee);
-struct sk_buff *rtllib_get_beacon(struct rtllib_device *ieee);
 
 void notify_wx_assoc_event(struct rtllib_device *ieee);
 void rtllib_ps_tx_ack(struct rtllib_device *ieee, short success);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 2ce4f64f88f67..0ad08165fd852 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2180,27 +2180,6 @@ static struct sk_buff *rtllib_get_beacon_(struct rtllib_device *ieee)
 	return skb;
 }
 
-struct sk_buff *rtllib_get_beacon(struct rtllib_device *ieee)
-{
-	struct sk_buff *skb;
-	struct rtllib_probe_response *b;
-
-	skb = rtllib_get_beacon_(ieee);
-	if (!skb)
-		return NULL;
-
-	b = (struct rtllib_probe_response *)skb->data;
-	b->header.seq_ctrl = cpu_to_le16(ieee->seq_ctrl[0] << 4);
-
-	if (ieee->seq_ctrl[0] == 0xFFF)
-		ieee->seq_ctrl[0] = 0;
-	else
-		ieee->seq_ctrl[0]++;
-
-	return skb;
-}
-EXPORT_SYMBOL(rtllib_get_beacon);
-
 void rtllib_softmac_stop_protocol(struct rtllib_device *ieee)
 {
 	rtllib_stop_scan_syncro(ieee);
-- 
GitLab


From d7f0b9c251fd6de57170ee922f75ea6e88566f7e Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 24 Nov 2023 22:30:47 +0100
Subject: [PATCH 0462/4076] staging: rtl8192e: Remove unused timer beacon_timer

Driver does not support AP Mode therefore no beacons need to be send.
Remove unused timer beacon_timer.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/b16b6b4525ede8e2a218cb39d23f9ef2a3a745a9.1700860759.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h         |  1 -
 drivers/staging/rtl8192e/rtllib_softmac.c | 17 -----------------
 2 files changed, 18 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 835b407ab1806..b7f4d7e2ea263 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1418,7 +1418,6 @@ struct rtllib_device {
 	struct timer_list associate_timer;
 
 	/* used if IEEE_SOFTMAC_BEACONS is set */
-	struct timer_list beacon_timer;
 	u8 need_sw_enc;
 	struct work_struct associate_complete_wq;
 	struct work_struct ips_leave_wq;
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 0ad08165fd852..430951c88123a 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -365,21 +365,6 @@ static void rtllib_send_beacon(struct rtllib_device *ieee)
 		softmac_mgmt_xmit(skb, ieee);
 		ieee->softmac_stats.tx_beacons++;
 	}
-
-	if (ieee->beacon_txing && ieee->ieee_up)
-		mod_timer(&ieee->beacon_timer, jiffies +
-			  (msecs_to_jiffies(ieee->current_network.beacon_interval - 5)));
-}
-
-static void rtllib_send_beacon_cb(struct timer_list *t)
-{
-	struct rtllib_device *ieee =
-		from_timer(ieee, t, beacon_timer);
-	unsigned long flags;
-
-	spin_lock_irqsave(&ieee->beacon_lock, flags);
-	rtllib_send_beacon(ieee);
-	spin_unlock_irqrestore(&ieee->beacon_lock, flags);
 }
 
 /* Enables network monitor mode, all rx packets will be received. */
@@ -2328,8 +2313,6 @@ int rtllib_softmac_init(struct rtllib_device *ieee)
 
 	timer_setup(&ieee->associate_timer, rtllib_associate_abort_cb, 0);
 
-	timer_setup(&ieee->beacon_timer, rtllib_send_beacon_cb, 0);
-
 	INIT_DELAYED_WORK(&ieee->link_change_wq, (void *)rtllib_link_change_wq);
 	INIT_WORK(&ieee->associate_complete_wq, (void *)rtllib_associate_complete_wq);
 	INIT_DELAYED_WORK(&ieee->associate_procedure_wq, (void *)rtllib_associate_procedure_wq);
-- 
GitLab


From 270f40cf35ce8438ffed8b2d3ba6318c50fdf85e Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 24 Nov 2023 22:31:01 +0100
Subject: [PATCH 0463/4076] staging: rtl8192e: Remove unused function
 rtllib_send_beacon()

Remove unused function rtllib_send_beacon().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/fca983a276ae67dc9cd124e236fe9d210fd997d3.1700860759.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 430951c88123a..4e33a453f86e3 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -351,22 +351,6 @@ static inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee)
 	return skb;
 }
 
-static struct sk_buff *rtllib_get_beacon_(struct rtllib_device *ieee);
-
-static void rtllib_send_beacon(struct rtllib_device *ieee)
-{
-	struct sk_buff *skb;
-
-	if (!ieee->ieee_up)
-		return;
-	skb = rtllib_get_beacon_(ieee);
-
-	if (skb) {
-		softmac_mgmt_xmit(skb, ieee);
-		ieee->softmac_stats.tx_beacons++;
-	}
-}
-
 /* Enables network monitor mode, all rx packets will be received. */
 void rtllib_EnableNetMonitorMode(struct net_device *dev,
 		bool bInitState)
-- 
GitLab


From 55003c4d6ac5346bc04e70a96f294a577cfb3fb4 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 24 Nov 2023 22:31:08 +0100
Subject: [PATCH 0464/4076] staging: rtl8192e: Remove unused function
 rtllib_get_beacon_()

Remove unused function rtllib_get_beacon_().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/ed825d5fb1946530c310afca1d3f27e46da35f06.1700860759.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 19 -------------------
 1 file changed, 19 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 4e33a453f86e3..8c7ad56d44022 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2130,25 +2130,6 @@ exit:
 	mutex_unlock(&ieee->wx_mutex);
 }
 
-static struct sk_buff *rtllib_get_beacon_(struct rtllib_device *ieee)
-{
-	static const u8 broadcast_addr[] = {
-		0xff, 0xff, 0xff, 0xff, 0xff, 0xff
-	};
-	struct sk_buff *skb;
-	struct rtllib_probe_response *b;
-
-	skb = rtllib_probe_resp(ieee, broadcast_addr);
-
-	if (!skb)
-		return NULL;
-
-	b = (struct rtllib_probe_response *)skb->data;
-	b->header.frame_control = cpu_to_le16(IEEE80211_STYPE_BEACON);
-
-	return skb;
-}
-
 void rtllib_softmac_stop_protocol(struct rtllib_device *ieee)
 {
 	rtllib_stop_scan_syncro(ieee);
-- 
GitLab


From 7e0ea2ea439fc2876247ea2ac7a6741e9021d1a4 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 24 Nov 2023 22:31:15 +0100
Subject: [PATCH 0465/4076] staging: rtl8192e: Remove unused function
 rtllib_probe_resp()

Remove unused function rtllib_probe_resp().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/be709ffea087df6f960075a51c0eab89f86ef8b2.1700860759.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 146 ----------------------
 1 file changed, 146 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 8c7ad56d44022..d209706524322 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -632,152 +632,6 @@ rtllib_authentication_req(struct rtllib_network *beacon,
 	return skb;
 }
 
-static struct sk_buff *rtllib_probe_resp(struct rtllib_device *ieee,
-					 const u8 *dest)
-{
-	u8 *tag;
-	int beacon_size;
-	struct rtllib_probe_response *beacon_buf;
-	struct sk_buff *skb = NULL;
-	int encrypt;
-	int atim_len, erp_len;
-	struct lib80211_crypt_data *crypt;
-
-	char *ssid = ieee->current_network.ssid;
-	int ssid_len = ieee->current_network.ssid_len;
-	int rate_len = ieee->current_network.rates_len + 2;
-	int rate_ex_len = ieee->current_network.rates_ex_len;
-	int wpa_ie_len = ieee->wpa_ie_len;
-	u8 erpinfo_content = 0;
-
-	u8 *tmp_ht_cap_buf = NULL;
-	u8 tmp_ht_cap_len = 0;
-	u8 *tmp_ht_info_buf = NULL;
-	u8 tmp_ht_info_len = 0;
-	struct rt_hi_throughput *ht_info = ieee->ht_info;
-	u8 *tmp_generic_ie_buf = NULL;
-	u8 tmp_generic_ie_len = 0;
-
-	if (rate_ex_len > 0)
-		rate_ex_len += 2;
-
-	if (ieee->current_network.capability & WLAN_CAPABILITY_IBSS)
-		atim_len = 4;
-	else
-		atim_len = 0;
-
-	if ((ieee->current_network.mode == WIRELESS_MODE_G) ||
-	   (ieee->current_network.mode == WIRELESS_MODE_N_24G &&
-	   ieee->ht_info->bCurSuppCCK)) {
-		erp_len = 3;
-		erpinfo_content = 0;
-		if (ieee->current_network.buseprotection)
-			erpinfo_content |= ERP_UseProtection;
-	} else {
-		erp_len = 0;
-	}
-
-	crypt = ieee->crypt_info.crypt[ieee->crypt_info.tx_keyidx];
-	encrypt = crypt && crypt->ops &&
-		((strcmp(crypt->ops->name, "R-WEP") == 0 || wpa_ie_len));
-	if (ieee->ht_info->current_ht_support) {
-		tmp_ht_cap_buf = (u8 *)&(ieee->ht_info->SelfHTCap);
-		tmp_ht_cap_len = sizeof(ieee->ht_info->SelfHTCap);
-		tmp_ht_info_buf = (u8 *)&(ieee->ht_info->SelfHTInfo);
-		tmp_ht_info_len = sizeof(ieee->ht_info->SelfHTInfo);
-		HTConstructCapabilityElement(ieee, tmp_ht_cap_buf,
-					     &tmp_ht_cap_len, encrypt, false);
-		HTConstructInfoElement(ieee, tmp_ht_info_buf, &tmp_ht_info_len,
-				       encrypt);
-
-		if (ht_info->reg_rt2rt_aggregation) {
-			tmp_generic_ie_buf = ieee->ht_info->sz_rt2rt_agg_buf;
-			tmp_generic_ie_len =
-				 sizeof(ieee->ht_info->sz_rt2rt_agg_buf);
-			HTConstructRT2RTAggElement(ieee, tmp_generic_ie_buf,
-						   &tmp_generic_ie_len);
-		}
-	}
-
-	beacon_size = sizeof(struct rtllib_probe_response) + 2 +
-		ssid_len + 3 + rate_len + rate_ex_len + atim_len + erp_len
-		+ wpa_ie_len + ieee->tx_headroom;
-	skb = dev_alloc_skb(beacon_size);
-	if (!skb)
-		return NULL;
-
-	skb_reserve(skb, ieee->tx_headroom);
-
-	beacon_buf = skb_put(skb, (beacon_size - ieee->tx_headroom));
-	ether_addr_copy(beacon_buf->header.addr1, dest);
-	ether_addr_copy(beacon_buf->header.addr2, ieee->dev->dev_addr);
-	ether_addr_copy(beacon_buf->header.addr3, ieee->current_network.bssid);
-
-	beacon_buf->header.duration_id = 0;
-	beacon_buf->beacon_interval =
-		cpu_to_le16(ieee->current_network.beacon_interval);
-	beacon_buf->capability =
-		cpu_to_le16(ieee->current_network.capability &
-		WLAN_CAPABILITY_IBSS);
-	beacon_buf->capability |=
-		cpu_to_le16(ieee->current_network.capability &
-		WLAN_CAPABILITY_SHORT_PREAMBLE);
-
-	if (ieee->current_network.capability & WLAN_CAPABILITY_SHORT_SLOT_TIME)
-		beacon_buf->capability |=
-			cpu_to_le16(WLAN_CAPABILITY_SHORT_SLOT_TIME);
-
-	crypt = ieee->crypt_info.crypt[ieee->crypt_info.tx_keyidx];
-	if (encrypt)
-		beacon_buf->capability |= cpu_to_le16(WLAN_CAPABILITY_PRIVACY);
-
-	beacon_buf->header.frame_control = cpu_to_le16(IEEE80211_STYPE_PROBE_RESP);
-	beacon_buf->info_element[0].id = MFIE_TYPE_SSID;
-	beacon_buf->info_element[0].len = ssid_len;
-
-	tag = (u8 *)beacon_buf->info_element[0].data;
-
-	memcpy(tag, ssid, ssid_len);
-
-	tag += ssid_len;
-
-	*(tag++) = MFIE_TYPE_RATES;
-	*(tag++) = rate_len - 2;
-	memcpy(tag, ieee->current_network.rates, rate_len - 2);
-	tag += rate_len - 2;
-
-	*(tag++) = MFIE_TYPE_DS_SET;
-	*(tag++) = 1;
-	*(tag++) = ieee->current_network.channel;
-
-	if (atim_len) {
-		u16 val16;
-		*(tag++) = MFIE_TYPE_IBSS_SET;
-		*(tag++) = 2;
-		val16 = ieee->current_network.atim_window;
-		memcpy((u8 *)tag, (u8 *)&val16, 2);
-		tag += 2;
-	}
-
-	if (erp_len) {
-		*(tag++) = MFIE_TYPE_ERP;
-		*(tag++) = 1;
-		*(tag++) = erpinfo_content;
-	}
-	if (rate_ex_len) {
-		*(tag++) = MFIE_TYPE_RATES_EX;
-		*(tag++) = rate_ex_len - 2;
-		memcpy(tag, ieee->current_network.rates_ex, rate_ex_len - 2);
-		tag += rate_ex_len - 2;
-	}
-
-	if (wpa_ie_len) {
-		memcpy(tag, ieee->wpa_ie, ieee->wpa_ie_len);
-		tag += ieee->wpa_ie_len;
-	}
-	return skb;
-}
-
 static struct sk_buff *rtllib_null_func(struct rtllib_device *ieee, short pwr)
 {
 	struct sk_buff *skb;
-- 
GitLab


From 6ae22b8c5f07e31d2b8d48bc4fb2d56e5db13674 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 24 Nov 2023 22:31:21 +0100
Subject: [PATCH 0466/4076] staging: rtl8192e: Remove unused function
 HTConstructInfoElement()

Remove unused function HTConstructInfoElement().

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/ed49162367b03a848895638adcdfe3594d4219b3.1700860759.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 16 ----------------
 drivers/staging/rtl8192e/rtllib.h         |  2 --
 2 files changed, 18 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index da4cf6f257941..00273d709f3c4 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -328,22 +328,6 @@ void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
 	}
 }
 
-void HTConstructInfoElement(struct rtllib_device *ieee, u8 *posHTInfo,
-			    u8 *len, u8 IsEncrypt)
-{
-	struct ht_info_ele *pHTInfoEle = (struct ht_info_ele *)posHTInfo;
-
-	if (!posHTInfo || !pHTInfoEle) {
-		netdev_warn(ieee->dev,
-			    "%s(): posHTInfo and pHTInfoEle are null\n",
-			    __func__);
-		return;
-	}
-
-	memset(posHTInfo, 0, *len);
-	*len = 0;
-}
-
 void HTConstructRT2RTAggElement(struct rtllib_device *ieee, u8 *posRT2RTAgg,
 				u8 *len)
 {
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index b7f4d7e2ea263..04433c79b3a73 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1760,8 +1760,6 @@ void ht_update_default_setting(struct rtllib_device *ieee);
 void HTConstructCapabilityElement(struct rtllib_device *ieee,
 				  u8 *posHTCap, u8 *len,
 				  u8 isEncrypt, bool bAssoc);
-void HTConstructInfoElement(struct rtllib_device *ieee,
-			    u8 *posHTInfo, u8 *len, u8 isEncrypt);
 void HTConstructRT2RTAggElement(struct rtllib_device *ieee,
 				u8 *posRT2RTAgg, u8 *len);
 void HTOnAssocRsp(struct rtllib_device *ieee);
-- 
GitLab


From 956ec671870506c7e05f4acee6f3fc81bf3575d1 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 24 Nov 2023 22:31:27 +0100
Subject: [PATCH 0467/4076] staging: rtl8192e: Remove function
 rtl92e_update_rx_pkt_timestamp()

mac_time and last_rx_desc_tsf are only used in
rtl92e_update_rx_pkt_timestamp(). Depending on a condition one is equal
to the other or vice versa. But since those are not used anywhere else
the function rtl92e_update_rx_pkt_timestamp() is just dead code.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/89a21fa17b32d66e07514bfad5b604d5d4835e25.1700860759.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c |  2 --
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c   | 11 -----------
 drivers/staging/rtl8192e/rtl8192e/rtl_core.h   |  4 ----
 drivers/staging/rtl8192e/rtllib.h              |  1 -
 4 files changed, 18 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index 73315a236e769..13e3f26279aa8 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -1673,8 +1673,6 @@ bool rtl92e_get_rx_stats(struct net_device *dev, struct rtllib_rx_stats *stats,
 	stats->TimeStampLow = pDrvInfo->TSFL;
 	stats->TimeStampHigh = rtl92e_readl(dev, TSFR + 4);
 
-	rtl92e_update_rx_pkt_timestamp(dev, stats);
-
 	if ((stats->RxBufShift + stats->RxDrvInfoSize) > 0)
 		stats->bShift = 1;
 
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index fc6e8ea039a3b..bad34221d8b70 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -1433,17 +1433,6 @@ void rtl92e_reset_desc_ring(struct net_device *dev)
 	spin_unlock_irqrestore(&priv->irq_th_lock, flags);
 }
 
-void rtl92e_update_rx_pkt_timestamp(struct net_device *dev,
-				    struct rtllib_rx_stats *stats)
-{
-	struct r8192_priv *priv = rtllib_priv(dev);
-
-	if (stats->bIsAMPDU && !stats->bFirstMPDU)
-		stats->mac_time = priv->last_rx_desc_tsf;
-	else
-		priv->last_rx_desc_tsf = stats->mac_time;
-}
-
 long rtl92e_translate_to_dbm(struct r8192_priv *priv, u8 signal_strength_index)
 {
 	long	signal_power;
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
index 846f0f7a737ba..546c8a33dae8c 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
@@ -234,8 +234,6 @@ struct r8192_priv {
 	int		rxringcount;
 	u16		rxbuffersize;
 
-	u64 last_rx_desc_tsf;
-
 	u32 receive_config;
 	u8		retry_data;
 	u8		retry_rts;
@@ -391,8 +389,6 @@ void rtl92e_irq_enable(struct net_device *dev);
 void rtl92e_config_rate(struct net_device *dev, u16 *rate_config);
 void rtl92e_irq_disable(struct net_device *dev);
 
-void rtl92e_update_rx_pkt_timestamp(struct net_device *dev,
-				    struct rtllib_rx_stats *stats);
 long rtl92e_translate_to_dbm(struct r8192_priv *priv, u8 signal_strength_index);
 void rtl92e_update_rx_statistics(struct r8192_priv *priv,
 				 struct rtllib_rx_stats *pprevious_stats);
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 04433c79b3a73..47da9b1a86820 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -471,7 +471,6 @@ enum _REG_PREAMBLE_MODE {
  *       any adverse affects.
  */
 struct rtllib_rx_stats {
-	u64 mac_time;
 	s8  rssi;
 	u8  signal;
 	u8  noise;
-- 
GitLab


From 79f2ff6461e7dab9d85051498a32bcbd758fe708 Mon Sep 17 00:00:00 2001
From: Ana-Maria Cusco <ana-maria.cusco@analog.com>
Date: Mon, 13 Nov 2023 12:25:35 +0200
Subject: [PATCH 0468/4076] dt-bindings: iio: hmc425a: add entry for ADRF5740
 Attenuator

The ADRF5740 is a silicon, 4-bit digital attenuator with 22 dB
attenuation control range in 2 dB steps.

Signed-off-by: Ana-Maria Cusco <ana-maria.cusco@analog.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231113102535.51074-3-anamaria.cuscoo@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml       | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml b/Documentation/devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml
index 2ee6080deac7c..67de9d4e3a1df 100644
--- a/Documentation/devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml
+++ b/Documentation/devicetree/bindings/iio/amplifiers/adi,hmc425a.yaml
@@ -12,6 +12,9 @@ maintainers:
 description: |
   Digital Step Attenuator IIO devices with gpio interface.
   Offer various frequency and attenuation ranges.
+  ADRF5750 2 dB LSB, 4-Bit, Silicon Digital Attenuator, 10 MHz to 60 GHz
+    https://www.analog.com/media/en/technical-documentation/data-sheets/adrf5740.pdf
+
   HMC425A 0.5 dB LSB GaAs MMIC 6-BIT DIGITAL POSITIVE CONTROL ATTENUATOR, 2.2 - 8.0 GHz
     https://www.analog.com/media/en/technical-documentation/data-sheets/hmc425A.pdf
 
@@ -22,6 +25,7 @@ description: |
 properties:
   compatible:
     enum:
+      - adi,adrf5740
       - adi,hmc425a
       - adi,hmc540s
 
-- 
GitLab


From ed73c4f13d5b63acce2b6f8c5e73c465479c4940 Mon Sep 17 00:00:00 2001
From: Ana-Maria Cusco <ana-maria.cusco@analog.com>
Date: Mon, 13 Nov 2023 12:25:34 +0200
Subject: [PATCH 0469/4076] iio: amplifiers: hmc425a: add support for ADRF5740
 Attenuator

This adds support for the Analog Devices ADRF5740 2 dB LSB, 4-Bit,
Silicon Digital Attenuator, 10 MHz to 60 GHz.
The default (maximum) gain is also set at probe time, with GPIO lines
driven high to achieve maximum gain, in contrast to other devices
where GPIOs need to be driven low.

Signed-off-by: Ana-Maria Cusco <ana-maria.cusco@analog.com>
Link: https://lore.kernel.org/r/20231113102535.51074-2-anamaria.cuscoo@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/amplifiers/hmc425a.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/iio/amplifiers/hmc425a.c b/drivers/iio/amplifiers/hmc425a.c
index e87d35d50a95c..ed4d729226961 100644
--- a/drivers/iio/amplifiers/hmc425a.c
+++ b/drivers/iio/amplifiers/hmc425a.c
@@ -5,6 +5,7 @@
  * Copyright 2020 Analog Devices Inc.
  */
 
+#include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/gpio/consumer.h>
@@ -22,6 +23,7 @@
 enum hmc425a_type {
 	ID_HMC425A,
 	ID_HMC540S,
+	ID_ADRF5740
 };
 
 struct hmc425a_chip_info {
@@ -74,6 +76,10 @@ static int hmc425a_read_raw(struct iio_dev *indio_dev,
 		case ID_HMC540S:
 			gain = ~code * -1000;
 			break;
+		case ID_ADRF5740:
+			code = code & BIT(3) ? code & ~BIT(2) : code;
+			gain = code * -2000;
+			break;
 		}
 
 		*val = gain / 1000;
@@ -113,6 +119,10 @@ static int hmc425a_write_raw(struct iio_dev *indio_dev,
 	case ID_HMC540S:
 		code = ~((abs(gain) / 1000) & 0xF);
 		break;
+	case ID_ADRF5740:
+		code = (abs(gain) / 2000) & 0xF;
+		code = code & BIT(3) ? code | BIT(2) : code;
+		break;
 	}
 
 	mutex_lock(&st->lock);
@@ -165,6 +175,7 @@ static const struct iio_chan_spec hmc425a_channels[] = {
 static const struct of_device_id hmc425a_of_match[] = {
 	{ .compatible = "adi,hmc425a", .data = (void *)ID_HMC425A },
 	{ .compatible = "adi,hmc540s", .data = (void *)ID_HMC540S },
+	{ .compatible = "adi,adrf5740", .data = (void *)ID_ADRF5740 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, hmc425a_of_match);
@@ -188,6 +199,15 @@ static struct hmc425a_chip_info hmc425a_chip_info_tbl[] = {
 		.gain_max = 0,
 		.default_gain = -0x10, /* set default gain -15.0db*/
 	},
+	[ID_ADRF5740] = {
+		.name = "adrf5740",
+		.channels = hmc425a_channels,
+		.num_channels = ARRAY_SIZE(hmc425a_channels),
+		.num_gpios = 4,
+		.gain_min = -22000,
+		.gain_max = 0,
+		.default_gain = 0xF, /* set default gain -22.0db*/
+	},
 };
 
 static int hmc425a_probe(struct platform_device *pdev)
@@ -229,6 +249,9 @@ static int hmc425a_probe(struct platform_device *pdev)
 	indio_dev->info = &hmc425a_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
+	/* Set default gain */
+	hmc425a_write(indio_dev, st->gain);
+
 	return devm_iio_device_register(&pdev->dev, indio_dev);
 }
 
-- 
GitLab


From 39dac9d0511ff735a4937c5aded7c84aed55f57e Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Mon, 30 Oct 2023 10:07:53 +0800
Subject: [PATCH 0470/4076] iio: imu: inv_mpu6050: return callee's error code
 rather than -EINVAL

regmap_bulk_write()/regmap_bulk_read() return zero or negative error
code, return the callee's error code is better than '-EINVAL'.

Signed-off-by: Su Hui <suhui@nfschina.com>
Link: https://lore.kernel.org/r/20231030020752.67630-1-suhui@nfschina.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_mpu6050/inv_mpu_core.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index 3fbeef1a70186..4713e3bc59e0c 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -567,15 +567,12 @@ static int inv_mpu6050_init_config(struct iio_dev *indio_dev)
 static int inv_mpu6050_sensor_set(struct inv_mpu6050_state  *st, int reg,
 				int axis, int val)
 {
-	int ind, result;
+	int ind;
 	__be16 d = cpu_to_be16(val);
 
 	ind = (axis - IIO_MOD_X) * 2;
-	result = regmap_bulk_write(st->map, reg + ind, &d, sizeof(d));
-	if (result)
-		return -EINVAL;
 
-	return 0;
+	return regmap_bulk_write(st->map, reg + ind, &d, sizeof(d));
 }
 
 static int inv_mpu6050_sensor_show(struct inv_mpu6050_state  *st, int reg,
@@ -587,7 +584,7 @@ static int inv_mpu6050_sensor_show(struct inv_mpu6050_state  *st, int reg,
 	ind = (axis - IIO_MOD_X) * 2;
 	result = regmap_bulk_read(st->map, reg + ind, &d, sizeof(d));
 	if (result)
-		return -EINVAL;
+		return result;
 	*val = (short)be16_to_cpup(&d);
 
 	return IIO_VAL_INT;
-- 
GitLab


From 00799564bafdd73db1bb0482eefbe1aba7d5e15f Mon Sep 17 00:00:00 2001
From: Shreeya Patel <shreeya.patel@collabora.com>
Date: Wed, 8 Nov 2023 00:50:05 +0530
Subject: [PATCH 0471/4076] iio: light: ltrf216a: Return floating point values

For better precision of input light intesity, return floating point
values through sysfs instead of an integer value

Signed-off-by: Shreeya Patel <shreeya.patel@collabora.com>
Link: https://lore.kernel.org/r/20231107192005.285534-1-shreeya.patel@collabora.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/ltrf216a.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/light/ltrf216a.c b/drivers/iio/light/ltrf216a.c
index 8de4dd849936d..68dc48420a886 100644
--- a/drivers/iio/light/ltrf216a.c
+++ b/drivers/iio/light/ltrf216a.c
@@ -234,7 +234,7 @@ static int ltrf216a_read_data(struct ltrf216a_data *data, u8 addr)
 static int ltrf216a_get_lux(struct ltrf216a_data *data)
 {
 	int ret, greendata;
-	u64 lux, div;
+	u64 lux;
 
 	ret = ltrf216a_set_power_state(data, true);
 	if (ret)
@@ -246,10 +246,9 @@ static int ltrf216a_get_lux(struct ltrf216a_data *data)
 
 	ltrf216a_set_power_state(data, false);
 
-	lux = greendata * 45 * LTRF216A_WIN_FAC * 100;
-	div = data->als_gain_fac * data->int_time_fac * 100;
+	lux = greendata * 45 * LTRF216A_WIN_FAC;
 
-	return div_u64(lux, div);
+	return lux;
 }
 
 static int ltrf216a_read_raw(struct iio_dev *indio_dev,
@@ -279,7 +278,8 @@ static int ltrf216a_read_raw(struct iio_dev *indio_dev,
 		if (ret < 0)
 			return ret;
 		*val = ret;
-		return IIO_VAL_INT;
+		*val2 = data->als_gain_fac * data->int_time_fac;
+		return IIO_VAL_FRACTIONAL;
 	case IIO_CHAN_INFO_INT_TIME:
 		mutex_lock(&data->lock);
 		ret = ltrf216a_get_int_time(data, val, val2);
-- 
GitLab


From 44482310b7f8ac4cd8fa7be4cee8c1b260ea5ee9 Mon Sep 17 00:00:00 2001
From: Jagath Jog J <jagathjog1996@gmail.com>
Date: Wed, 8 Nov 2023 09:28:31 +0530
Subject: [PATCH 0472/4076] iio: imu: bmi323: Make the local structures static

Make the local structures static within their respective driver files.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311070530.qKhLTz1Y-lkp@intel.com/
Signed-off-by: Jagath Jog J <jagathjog1996@gmail.com>
Link: https://lore.kernel.org/r/20231108035831.5889-1-jagathjog1996@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/bmi323/bmi323_i2c.c | 2 +-
 drivers/iio/imu/bmi323/bmi323_spi.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/imu/bmi323/bmi323_i2c.c b/drivers/iio/imu/bmi323/bmi323_i2c.c
index 0008e186367d6..20a8001b9956a 100644
--- a/drivers/iio/imu/bmi323/bmi323_i2c.c
+++ b/drivers/iio/imu/bmi323/bmi323_i2c.c
@@ -66,7 +66,7 @@ static struct regmap_bus bmi323_regmap_bus = {
 	.write = bmi323_regmap_i2c_write,
 };
 
-const struct regmap_config bmi323_i2c_regmap_config = {
+static const struct regmap_config bmi323_i2c_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 16,
 	.max_register = BMI323_CFG_RES_REG,
diff --git a/drivers/iio/imu/bmi323/bmi323_spi.c b/drivers/iio/imu/bmi323/bmi323_spi.c
index 6dc3352dd7143..7b1e8127d0dd9 100644
--- a/drivers/iio/imu/bmi323/bmi323_spi.c
+++ b/drivers/iio/imu/bmi323/bmi323_spi.c
@@ -41,7 +41,7 @@ static struct regmap_bus bmi323_regmap_bus = {
 	.write = bmi323_regmap_spi_write,
 };
 
-const struct regmap_config bmi323_spi_regmap_config = {
+static const struct regmap_config bmi323_spi_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 16,
 	.pad_bits = 8,
-- 
GitLab


From f1aad9df93f39267e890836a28d22511f23474e1 Mon Sep 17 00:00:00 2001
From: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Date: Tue, 26 Sep 2023 18:26:00 +0300
Subject: [PATCH 0473/4076] iommu: Map reserved memory as cacheable if device
 is coherent

Check if the device is marked as DMA coherent in the DT and if so,
map its reserved memory as cacheable in the IOMMU.
This fixes the recently added IOMMU reserved memory support which
uses IOMMU_RESV_DIRECT without properly building the PROT for the
mapping.

Fixes: a5bf3cfce8cb ("iommu: Implement of_iommu_get_resv_regions()")
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20230926152600.8749-1-laurentiu.tudor@nxp.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/of_iommu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 157b286e36bf3..5b3631ba5a451 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -254,6 +254,9 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 				phys_addr_t iova;
 				size_t length;
 
+				if (of_dma_is_coherent(dev->of_node))
+					prot |= IOMMU_CACHE;
+
 				maps = of_translate_dma_region(np, maps, &iova, &length);
 				type = iommu_resv_region_get_type(dev, &phys, iova, length);
 
-- 
GitLab


From 9abe6c55354db38f0906fcaf4e1c1644c26cd624 Mon Sep 17 00:00:00 2001
From: Kunwu Chan <chentao@kylinos.cn>
Date: Mon, 20 Nov 2023 17:53:42 +0800
Subject: [PATCH 0474/4076] iommu/amd: Set variable amd_dirty_ops to static

Fix the followng warning:
drivers/iommu/amd/iommu.c:67:30: warning: symbol
 'amd_dirty_ops' was not declared. Should it be static?

This variable is only used in its defining file, so it should be static.

Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231120095342.1102999-1-chentao@kylinos.cn
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index fcc987f5d4edc..9f70643608283 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -64,7 +64,7 @@ LIST_HEAD(hpet_map);
 LIST_HEAD(acpihid_map);
 
 const struct iommu_ops amd_iommu_ops;
-const struct iommu_dirty_ops amd_dirty_ops;
+static const struct iommu_dirty_ops amd_dirty_ops;
 
 int amd_iommu_max_glx_val = -1;
 
@@ -2635,7 +2635,7 @@ static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 	return true;
 }
 
-const struct iommu_dirty_ops amd_dirty_ops = {
+static const struct iommu_dirty_ops amd_dirty_ops = {
 	.set_dirty_tracking = amd_iommu_set_dirty_tracking,
 	.read_and_clear_dirty = amd_iommu_read_and_clear_dirty,
 };
-- 
GitLab


From 00271ca5cbcd36d01f3c58a05378304ba9dd6a2a Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Mon, 20 Nov 2023 15:51:56 +0100
Subject: [PATCH 0475/4076] iommu/virtio: Make use of ops->iotlb_sync_map

Pull out the sync operation from viommu_map_pages() by implementing
ops->iotlb_sync_map. This allows the common IOMMU code to map multiple
elements of an sg with a single sync (see iommu_map_sg()).

Link: https://lore.kernel.org/lkml/20230726111433.1105665-1-schnelle@linux.ibm.com/
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20231120-viommu-sync-map-v3-1-50a57ecf78b5@linux.ibm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/virtio-iommu.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 379ebe03efb6d..3f18f69d70d89 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -843,7 +843,7 @@ static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			.flags		= cpu_to_le32(flags),
 		};
 
-		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
+		ret = viommu_add_req(vdomain->viommu, &map, sizeof(map));
 		if (ret) {
 			viommu_del_mappings(vdomain, iova, end);
 			return ret;
@@ -912,6 +912,20 @@ static void viommu_iotlb_sync(struct iommu_domain *domain,
 	viommu_sync_req(vdomain->viommu);
 }
 
+static int viommu_iotlb_sync_map(struct iommu_domain *domain,
+				 unsigned long iova, size_t size)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/*
+	 * May be called before the viommu is initialized including
+	 * while creating direct mapping
+	 */
+	if (!vdomain->nr_endpoints)
+		return 0;
+	return viommu_sync_req(vdomain->viommu);
+}
+
 static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
 {
 	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
@@ -1058,6 +1072,7 @@ static struct iommu_ops viommu_ops = {
 		.unmap_pages		= viommu_unmap_pages,
 		.iova_to_phys		= viommu_iova_to_phys,
 		.iotlb_sync		= viommu_iotlb_sync,
+		.iotlb_sync_map		= viommu_iotlb_sync_map,
 		.free			= viommu_domain_free,
 	}
 };
-- 
GitLab


From 6f01a732608f294a853f0d1cc963772bac12f1e9 Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Mon, 20 Nov 2023 15:51:57 +0100
Subject: [PATCH 0476/4076] iommu/virtio: Add ops->flush_iotlb_all and enable
 deferred flush

Add ops->flush_iotlb_all operation to enable virtio-iommu for the
dma-iommu deferred flush scheme. This results in a significant increase
in performance in exchange for a window in which devices can still
access previously IOMMU mapped memory when running with
CONFIG_IOMMU_DEFAULT_DMA_LAZY. The previous strict behavior can be
achieved with iommu.strict=1 on the kernel command line or
CONFIG_IOMMU_DEFAULT_DMA_STRICT.

Link: https://lore.kernel.org/lkml/20230802123612.GA6142@myrica/
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20231120-viommu-sync-map-v3-2-50a57ecf78b5@linux.ibm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/virtio-iommu.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 3f18f69d70d89..ef6a874451059 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -926,6 +926,19 @@ static int viommu_iotlb_sync_map(struct iommu_domain *domain,
 	return viommu_sync_req(vdomain->viommu);
 }
 
+static void viommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/*
+	 * May be called before the viommu is initialized including
+	 * while creating direct mapping
+	 */
+	if (!vdomain->nr_endpoints)
+		return;
+	viommu_sync_req(vdomain->viommu);
+}
+
 static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
 {
 	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
@@ -1051,6 +1064,8 @@ static bool viommu_capable(struct device *dev, enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
+	case IOMMU_CAP_DEFERRED_FLUSH:
+		return true;
 	default:
 		return false;
 	}
@@ -1071,6 +1086,7 @@ static struct iommu_ops viommu_ops = {
 		.map_pages		= viommu_map_pages,
 		.unmap_pages		= viommu_unmap_pages,
 		.iova_to_phys		= viommu_iova_to_phys,
+		.flush_iotlb_all	= viommu_flush_iotlb_all,
 		.iotlb_sync		= viommu_iotlb_sync,
 		.iotlb_sync_map		= viommu_iotlb_sync_map,
 		.free			= viommu_domain_free,
-- 
GitLab


From 48ed12788ed8aa099e463c2febcd3f06fb71c68c Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:03:57 +0000
Subject: [PATCH 0477/4076] iommu: Factor out some helpers

The pattern for picking the first device out of the group list is
repeated a few times now, so it's clearly worth factoring out, which
also helps hide the iommu_group_dev detail from places that don't need
to know. Similarly, the safety check for dev_iommu_ops() at certain
public interfaces starts looking a bit repetitive, and might not be
completely obvious at first glance, so let's factor that out for clarity
as well, in preparation for more uses of both.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/566cbd161546caa6aed49662c9b3e8f09dc9c3cf.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 56 ++++++++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 30 deletions(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index f17a1113f3d6a..5c555fc0d54ca 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -368,6 +368,15 @@ static void dev_iommu_free(struct device *dev)
 	kfree(param);
 }
 
+/*
+ * Internal equivalent of device_iommu_mapped() for when we care that a device
+ * actually has API ops, and don't want false positives from VFIO-only groups.
+ */
+static bool dev_has_iommu(struct device *dev)
+{
+	return dev->iommu && dev->iommu->iommu_dev;
+}
+
 static u32 dev_iommu_get_max_pasids(struct device *dev)
 {
 	u32 max_pasids = 0, bits = 0;
@@ -620,7 +629,7 @@ static void __iommu_group_remove_device(struct device *dev)
 
 		list_del(&device->list);
 		__iommu_group_free_device(group, device);
-		if (dev->iommu && dev->iommu->iommu_dev)
+		if (dev_has_iommu(dev))
 			iommu_deinit_device(dev);
 		else
 			dev->iommu_group = NULL;
@@ -819,7 +828,7 @@ int iommu_get_group_resv_regions(struct iommu_group *group,
 		 * Non-API groups still expose reserved_regions in sysfs,
 		 * so filter out calls that get here that way.
 		 */
-		if (!device->dev->iommu)
+		if (!dev_has_iommu(device->dev))
 			break;
 
 		INIT_LIST_HEAD(&dev_resv_regions);
@@ -1225,6 +1234,12 @@ void iommu_group_remove_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_group_remove_device);
 
+static struct device *iommu_group_first_dev(struct iommu_group *group)
+{
+	lockdep_assert_held(&group->mutex);
+	return list_first_entry(&group->devices, struct group_device, list)->dev;
+}
+
 /**
  * iommu_group_for_each_dev - iterate over each device in the group
  * @group: the group
@@ -1752,23 +1767,6 @@ __iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 	return __iommu_group_domain_alloc(group, req_type);
 }
 
-/*
- * Returns the iommu_ops for the devices in an iommu group.
- *
- * It is assumed that all devices in an iommu group are managed by a single
- * IOMMU unit. Therefore, this returns the dev_iommu_ops of the first device
- * in the group.
- */
-static const struct iommu_ops *group_iommu_ops(struct iommu_group *group)
-{
-	struct group_device *device =
-		list_first_entry(&group->devices, struct group_device, list);
-
-	lockdep_assert_held(&group->mutex);
-
-	return dev_iommu_ops(device->dev);
-}
-
 /*
  * req_type of 0 means "auto" which means to select a domain based on
  * iommu_def_domain_type or what the driver actually supports.
@@ -1776,7 +1774,7 @@ static const struct iommu_ops *group_iommu_ops(struct iommu_group *group)
 static struct iommu_domain *
 iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 {
-	const struct iommu_ops *ops = group_iommu_ops(group);
+	const struct iommu_ops *ops = dev_iommu_ops(iommu_group_first_dev(group));
 	struct iommu_domain *dom;
 
 	lockdep_assert_held(&group->mutex);
@@ -1854,7 +1852,7 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 static int iommu_get_def_domain_type(struct iommu_group *group,
 				     struct device *dev, int cur_type)
 {
-	const struct iommu_ops *ops = group_iommu_ops(group);
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	int type;
 
 	if (!ops->def_domain_type)
@@ -2021,7 +2019,7 @@ bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
 {
 	const struct iommu_ops *ops;
 
-	if (!dev->iommu || !dev->iommu->iommu_dev)
+	if (!dev_has_iommu(dev))
 		return false;
 
 	ops = dev_iommu_ops(dev);
@@ -2120,11 +2118,9 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 static struct iommu_domain *
 __iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
 {
-	struct device *dev =
-		list_first_entry(&group->devices, struct group_device, list)
-			->dev;
+	struct device *dev = iommu_group_first_dev(group);
 
-	return __iommu_domain_alloc(group_iommu_ops(group), dev, type);
+	return __iommu_domain_alloc(dev_iommu_ops(dev), dev, type);
 }
 
 struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
@@ -2987,8 +2983,8 @@ EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
  */
 int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
 {
-	if (dev->iommu && dev->iommu->iommu_dev) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+	if (dev_has_iommu(dev)) {
+		const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 		if (ops->dev_enable_feat)
 			return ops->dev_enable_feat(dev, feat);
@@ -3003,8 +2999,8 @@ EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);
  */
 int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 {
-	if (dev->iommu && dev->iommu->iommu_dev) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+	if (dev_has_iommu(dev)) {
+		const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 		if (ops->dev_disable_feat)
 			return ops->dev_disable_feat(dev, feat);
-- 
GitLab


From 1d8d43bb984b9cfa7ff63dbd0e2f6e5775ff1fdb Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:03:58 +0000
Subject: [PATCH 0478/4076] iommu: Decouple iommu_present() from bus ops

Much as I'd like to remove iommu_present(), the final remaining users
are proving stubbornly difficult to clean up, so kick that can down the
road and just rework it to preserve the current behaviour without
depending on bus ops. Since commit 57365a04c921 ("iommu: Move bus setup
to IOMMU device registration"), any registered IOMMU instance is already
considered "present" for every entry in iommu_buses, so it's simply a
case of validating the bus and checking we have at least once IOMMU.

Reviewed-by: Jason Gunthorpe<jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/caa93680bb9d35a8facbcd8ff46267ca67335229.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 5c555fc0d54ca..7fafd073c33e6 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2001,9 +2001,28 @@ int bus_iommu_probe(const struct bus_type *bus)
 	return 0;
 }
 
+/**
+ * iommu_present() - make platform-specific assumptions about an IOMMU
+ * @bus: bus to check
+ *
+ * Do not use this function. You want device_iommu_mapped() instead.
+ *
+ * Return: true if some IOMMU is present and aware of devices on the given bus;
+ * in general it may not be the only IOMMU, and it may not have anything to do
+ * with whatever device you are ultimately interested in.
+ */
 bool iommu_present(const struct bus_type *bus)
 {
-	return bus->iommu_ops != NULL;
+	bool ret = false;
+
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
+		if (iommu_buses[i] == bus) {
+			spin_lock(&iommu_device_lock);
+			ret = !list_empty(&iommu_device_list);
+			spin_unlock(&iommu_device_lock);
+		}
+	}
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
-- 
GitLab


From a9c362db39207c4934c9125e56ed730c5297c37c Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:03:59 +0000
Subject: [PATCH 0479/4076] iommu: Validate that devices match domains

Before we can allow drivers to coexist, we need to make sure that one
driver's domain ops can't misinterpret another driver's dev_iommu_priv
data. To that end, add a token to the domain so we can remember how it
was allocated - for now this may as well be the device ops, since they
still correlate 1:1 with drivers. We can trust ourselves for internal
default domain attachment, so add checks to cover all the public attach
interfaces.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/097c6f30480e4efe12195d00ba0e84ea4837fb4c.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c                | 10 ++++++++++
 drivers/iommu/iommufd/hw_pagetable.c |  2 ++
 include/linux/iommu.h                |  2 +-
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 7fafd073c33e6..8e4436c606d30 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2117,6 +2117,7 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 		return NULL;
 
 	domain->type = type;
+	domain->owner = ops;
 	/*
 	 * If not already set, assume all sizes by default; the driver
 	 * may override this later
@@ -2282,10 +2283,16 @@ struct iommu_domain *iommu_get_dma_domain(struct device *dev)
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group)
 {
+	struct device *dev;
+
 	if (group->domain && group->domain != group->default_domain &&
 	    group->domain != group->blocking_domain)
 		return -EBUSY;
 
+	dev = iommu_group_first_dev(group);
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	return __iommu_group_set_domain(group, domain);
 }
 
@@ -3477,6 +3484,9 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 	if (!group)
 		return -ENODEV;
 
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	mutex_lock(&group->mutex);
 	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
 	if (curr) {
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 2abbeafdbd22d..5be7f513b622d 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -135,6 +135,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			hwpt->domain = NULL;
 			goto out_abort;
 		}
+		hwpt->domain->owner = ops;
 	} else {
 		hwpt->domain = iommu_domain_alloc(idev->dev->bus);
 		if (!hwpt->domain) {
@@ -233,6 +234,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 		hwpt->domain = NULL;
 		goto out_abort;
 	}
+	hwpt->domain->owner = ops;
 
 	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
 		rc = -EINVAL;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ec289c1016f5f..077bf8cae2f7a 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -106,7 +106,7 @@ struct iommu_domain {
 	unsigned type;
 	const struct iommu_domain_ops *ops;
 	const struct iommu_dirty_ops *dirty_ops;
-
+	const struct iommu_ops *owner; /* Whose domain_alloc we came from */
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	struct iommu_domain_geometry geometry;
 	struct iommu_dma_cookie *iova_cookie;
-- 
GitLab


From b4c0497169d54e08346678dbc79ded7809dae5b7 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:04:00 +0000
Subject: [PATCH 0480/4076] iommu: Decouple iommu_domain_alloc() from bus ops

As the final remaining piece of bus-dependent API, iommu_domain_alloc()
can now take responsibility for the "one iommu_ops per bus" rule for
itself. It turns out we can't safely make the internal allocation call
any more group-based or device-based yet - that will have to wait until
the external callers can pass the right thing - but we can at least get
as far as deriving "bus ops" based on which driver is actually managing
devices on the given bus, rather than whichever driver won the race to
register first.

This will then leave us able to convert the last of the core internals
over to the IOMMU-instance model, allow multiple drivers to register and
actually coexist (modulo the above limitation for unmanaged domain users
in the short term), and start trying to solve the long-standing
iommu_probe_device() mess.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/6c7313009aae0e39ae2855920990ebf85af4662f.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 8e4436c606d30..88aeae0acd9b5 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2143,12 +2143,31 @@ __iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
 	return __iommu_domain_alloc(dev_iommu_ops(dev), dev, type);
 }
 
+static int __iommu_domain_alloc_dev(struct device *dev, void *data)
+{
+	const struct iommu_ops **ops = data;
+
+	if (!dev_has_iommu(dev))
+		return 0;
+
+	if (WARN_ONCE(*ops && *ops != dev_iommu_ops(dev),
+		      "Multiple IOMMU drivers present for bus %s, which the public IOMMU API can't fully support yet. You will still need to disable one or more for this to work, sorry!\n",
+		      dev_bus_name(dev)))
+		return -EBUSY;
+
+	*ops = dev_iommu_ops(dev);
+	return 0;
+}
+
 struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
 {
-	if (bus == NULL || bus->iommu_ops == NULL)
+	const struct iommu_ops *ops = NULL;
+	int err = bus_for_each_dev(bus, NULL, &ops, __iommu_domain_alloc_dev);
+
+	if (err || !ops)
 		return NULL;
-	return __iommu_domain_alloc(bus->iommu_ops, NULL,
-				    IOMMU_DOMAIN_UNMANAGED);
+
+	return __iommu_domain_alloc(ops, NULL, IOMMU_DOMAIN_UNMANAGED);
 }
 EXPORT_SYMBOL_GPL(iommu_domain_alloc);
 
-- 
GitLab


From 01bf81af85458c0427a70ae3bf90b375d038c95b Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:04:01 +0000
Subject: [PATCH 0481/4076] iommu/arm-smmu: Don't register fwnode for legacy
 binding

When using the legacy binding we bypass the of_xlate mechanism, so avoid
registering the instance fwnodes which act as keys for that. This will
help __iommu_probe_device() to retrieve the registered ops the same way
as for x86 etc. when no fwspec has previously been set up by of_xlate.

Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/18b0f812a42a74dd6924aea24e68ab409d6e1b52.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index d6d1a2a55cc06..4b83a3adacd6e 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -2161,7 +2161,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev);
+	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops,
+				    using_legacy_binding ? NULL : dev);
 	if (err) {
 		dev_err(dev, "Failed to register iommu\n");
 		iommu_device_sysfs_remove(&smmu->iommu);
-- 
GitLab


From 17de3f5fdd35676b0e3d41c7c9bf4e3032eb3673 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:04:02 +0000
Subject: [PATCH 0482/4076] iommu: Retire bus ops

With the rest of the API internals converted, it's time to finally
tackle probe_device and how we bootstrap the per-device ops association
to begin with. This ends up being disappointingly straightforward, since
fwspec users are already doing it in order to find their of_xlate
callback, and it works out that we can easily do the equivalent for
other drivers too. Then shuffle the remaining awareness of iommu_ops
into the couple of core headers that still need it, and breathe a sigh
of relief.

Ding dong the bus ops are gone!

CC: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/a59011ef65b4b6657cb0b7a388d786b779b61305.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c       | 31 ++++++++++++++++++-------------
 include/acpi/acpi_bus.h     |  2 ++
 include/linux/device.h      |  1 -
 include/linux/device/bus.h  |  5 -----
 include/linux/dma-map-ops.h |  1 +
 5 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 88aeae0acd9b5..254f42b4220b7 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -148,7 +148,7 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 static LIST_HEAD(iommu_device_list);
 static DEFINE_SPINLOCK(iommu_device_lock);
 
-static struct bus_type * const iommu_buses[] = {
+static const struct bus_type * const iommu_buses[] = {
 	&platform_bus_type,
 #ifdef CONFIG_PCI
 	&pci_bus_type,
@@ -257,13 +257,6 @@ int iommu_device_register(struct iommu_device *iommu,
 	/* We need to be able to take module references appropriately */
 	if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner))
 		return -EINVAL;
-	/*
-	 * Temporarily enforce global restriction to a single driver. This was
-	 * already the de-facto behaviour, since any possible combination of
-	 * existing drivers would compete for at least the PCI or platform bus.
-	 */
-	if (iommu_buses[0]->iommu_ops && iommu_buses[0]->iommu_ops != ops)
-		return -EBUSY;
 
 	iommu->ops = ops;
 	if (hwdev)
@@ -273,10 +266,8 @@ int iommu_device_register(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) {
-		iommu_buses[i]->iommu_ops = ops;
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++)
 		err = bus_iommu_probe(iommu_buses[i]);
-	}
 	if (err)
 		iommu_device_unregister(iommu);
 	return err;
@@ -329,7 +320,6 @@ int iommu_device_register_bus(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	bus->iommu_ops = ops;
 	err = bus_iommu_probe(bus);
 	if (err) {
 		iommu_device_unregister_bus(iommu, bus, nb);
@@ -496,12 +486,27 @@ static void iommu_deinit_device(struct device *dev)
 
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops;
+	struct iommu_fwspec *fwspec;
 	struct iommu_group *group;
 	static DEFINE_MUTEX(iommu_probe_device_lock);
 	struct group_device *gdev;
 	int ret;
 
+	/*
+	 * For FDT-based systems and ACPI IORT/VIOT, drivers register IOMMU
+	 * instances with non-NULL fwnodes, and client devices should have been
+	 * identified with a fwspec by this point. Otherwise, we can currently
+	 * assume that only one of Intel, AMD, s390, PAMU or legacy SMMUv2 can
+	 * be present, and that any of their registered instances has suitable
+	 * ops for probing, and thus cheekily co-opt the same mechanism.
+	 */
+	fwspec = dev_iommu_fwspec_get(dev);
+	if (fwspec && fwspec->ops)
+		ops = fwspec->ops;
+	else
+		ops = iommu_ops_from_fwnode(NULL);
+
 	if (!ops)
 		return -ENODEV;
 	/*
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 1216d72c650fa..89079787905d4 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -627,6 +627,8 @@ struct acpi_pci_root {
 
 /* helper */
 
+struct iommu_ops;
+
 bool acpi_dma_supported(const struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,
diff --git a/include/linux/device.h b/include/linux/device.h
index d7a72a8749ea0..0314dbbdb5345 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -42,7 +42,6 @@ struct class;
 struct subsys_private;
 struct device_node;
 struct fwnode_handle;
-struct iommu_ops;
 struct iommu_group;
 struct dev_pin_info;
 struct dev_iommu;
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index ae10c43227543..e25aab08f873d 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -62,9 +62,6 @@ struct fwnode_handle;
  *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
- * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
- *              driver implementations to a bus and allow the driver to do
- *              bus-specific setup
  * @need_parent_lock:	When probing or removing a device on this bus, the
  *			device core should lock the device's parent.
  *
@@ -104,8 +101,6 @@ struct bus_type {
 
 	const struct dev_pm_ops *pm;
 
-	const struct iommu_ops *iommu_ops;
-
 	bool need_parent_lock;
 };
 
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f2fc203fb8a1a..a52e508d1869f 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 
 struct cma;
+struct iommu_ops;
 
 /*
  * Values for struct dma_map_ops.flags:
-- 
GitLab


From e7080665c977ea1aafb8547a9c7bd08b199311d6 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:04:03 +0000
Subject: [PATCH 0483/4076] iommu: Clean up open-coded ownership checks

Some drivers already implement their own defence against the possibility
of being given someone else's device. Since this is now taken care of by
the core code (and via a slightly different path from the original
fwspec-based idea), let's clean them up.

Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/58a9879ce3f03562bb061e6714fe6efb554c3907.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c |  3 ---
 drivers/iommu/arm/arm-smmu/arm-smmu.c       |  9 +--------
 drivers/iommu/arm/arm-smmu/qcom_iommu.c     | 16 +++-------------
 drivers/iommu/mtk_iommu.c                   |  7 +------
 drivers/iommu/mtk_iommu_v1.c                |  3 ---
 drivers/iommu/sprd-iommu.c                  |  8 +-------
 drivers/iommu/virtio-iommu.c                |  3 ---
 7 files changed, 6 insertions(+), 43 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 7445454c2af24..fc4317c25b6d5 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2649,9 +2649,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 	struct arm_smmu_master *master;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops)
-		return ERR_PTR(-ENODEV);
-
 	if (WARN_ON_ONCE(dev_iommu_priv_get(dev)))
 		return ERR_PTR(-EBUSY);
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 4b83a3adacd6e..4d09c00478927 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1116,11 +1116,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_device *smmu;
 	int ret;
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops) {
-		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
-		return -ENXIO;
-	}
-
 	/*
 	 * FIXME: The arch/arm DMA API code tries to attach devices to its own
 	 * domains between of_xlate() and probe_device() - we have no way to cope
@@ -1357,10 +1352,8 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 		fwspec = dev_iommu_fwspec_get(dev);
 		if (ret)
 			goto out_free;
-	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
-		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	} else {
-		return ERR_PTR(-ENODEV);
+		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	}
 
 	ret = -EINVAL;
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index 97b2122032b23..33f3c870086ce 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -79,16 +79,6 @@ static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom)
 
 static const struct iommu_ops qcom_iommu_ops;
 
-static struct qcom_iommu_dev * to_iommu(struct device *dev)
-{
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-
-	if (!fwspec || fwspec->ops != &qcom_iommu_ops)
-		return NULL;
-
-	return dev_iommu_priv_get(dev);
-}
-
 static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid)
 {
 	struct qcom_iommu_dev *qcom_iommu = d->iommu;
@@ -372,7 +362,7 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain)
 
 static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 	int ret;
 
@@ -404,7 +394,7 @@ static int qcom_iommu_identity_attach(struct iommu_domain *identity_domain,
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct qcom_iommu_domain *qcom_domain;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	unsigned int i;
 
 	if (domain == identity_domain || !domain)
@@ -535,7 +525,7 @@ static bool qcom_iommu_capable(struct device *dev, enum iommu_cap cap)
 
 static struct iommu_device *qcom_iommu_probe_device(struct device *dev)
 {
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct device_link *link;
 
 	if (!qcom_iommu)
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 75279500a4a82..7abe9e85a5706 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -863,16 +863,11 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
 	struct device_link *link;
 	struct device *larbdev;
 	unsigned int larbid, larbidx, i;
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
-		return ERR_PTR(-ENODEV); /* Not a iommu client device */
-
-	data = dev_iommu_priv_get(dev);
-
 	if (!MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
 		return &data->iommu;
 
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index 67e044c1a7d93..25b41222abaec 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -481,9 +481,6 @@ static struct iommu_device *mtk_iommu_v1_probe_device(struct device *dev)
 		idx++;
 	}
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
-		return ERR_PTR(-ENODEV); /* Not a iommu client device */
-
 	data = dev_iommu_priv_get(dev);
 
 	/* Link the consumer device with the smi-larb device(supplier) */
diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
index 2eb9fb46703b3..537359f109979 100644
--- a/drivers/iommu/sprd-iommu.c
+++ b/drivers/iommu/sprd-iommu.c
@@ -385,13 +385,7 @@ static phys_addr_t sprd_iommu_iova_to_phys(struct iommu_domain *domain,
 
 static struct iommu_device *sprd_iommu_probe_device(struct device *dev)
 {
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct sprd_iommu_device *sdev;
-
-	if (!fwspec || fwspec->ops != &sprd_iommu_ops)
-		return ERR_PTR(-ENODEV);
-
-	sdev = dev_iommu_priv_get(dev);
+	struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev);
 
 	return &sdev->iommu;
 }
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 379ebe03efb6d..9bcffdde6175d 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -969,9 +969,6 @@ static struct iommu_device *viommu_probe_device(struct device *dev)
 	struct viommu_dev *viommu = NULL;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &viommu_ops)
-		return ERR_PTR(-ENODEV);
-
 	viommu = viommu_get_by_fwnode(fwspec->iommu_fwnode);
 	if (!viommu)
 		return ERR_PTR(-ENODEV);
-- 
GitLab


From 17b226dcf80ce79d02f4f0b08813d8848885b986 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@collabora.com>
Date: Fri, 24 Nov 2023 15:24:33 +0100
Subject: [PATCH 0484/4076] iommu: Allow passing custom allocators to pgtable
 drivers

This will be useful for GPU drivers who want to keep page tables in a
pool so they can:

- keep freed page tables in a free pool and speed-up upcoming page
  table allocations
- batch page table allocation instead of allocating one page at a time
- pre-reserve pages for page tables needed for map/unmap operations,
  to ensure map/unmap operations don't try to allocate memory in paths
  they're allowed to block or fail

It might also be valuable for other aspects of GPU and similar
use-cases, like fine-grained memory accounting and resource limiting.

We will extend the Arm LPAE format to support custom allocators in a
separate commit.

Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20231124142434.1577550-2-boris.brezillon@collabora.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/io-pgtable.c | 23 +++++++++++++++++++++++
 include/linux/io-pgtable.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)

diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index b843fcd365d28..8841c1487f004 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -34,6 +34,26 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 #endif
 };
 
+static int check_custom_allocator(enum io_pgtable_fmt fmt,
+				  struct io_pgtable_cfg *cfg)
+{
+	/* No custom allocator, no need to check the format. */
+	if (!cfg->alloc && !cfg->free)
+		return 0;
+
+	/* When passing a custom allocator, both the alloc and free
+	 * functions should be provided.
+	 */
+	if (!cfg->alloc || !cfg->free)
+		return -EINVAL;
+
+	/* Make sure the format supports custom allocators. */
+	if (io_pgtable_init_table[fmt]->caps & IO_PGTABLE_CAP_CUSTOM_ALLOCATOR)
+		return 0;
+
+	return -EINVAL;
+}
+
 struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 					    struct io_pgtable_cfg *cfg,
 					    void *cookie)
@@ -44,6 +64,9 @@ struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 	if (fmt >= IO_PGTABLE_NUM_FMTS)
 		return NULL;
 
+	if (check_custom_allocator(fmt, cfg))
+		return NULL;
+
 	fns = io_pgtable_init_table[fmt];
 	if (!fns)
 		return NULL;
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 25142a0e2fc2c..86cf1f7ae389a 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -100,6 +100,30 @@ struct io_pgtable_cfg {
 	const struct iommu_flush_ops	*tlb;
 	struct device			*iommu_dev;
 
+	/**
+	 * @alloc: Custom page allocator.
+	 *
+	 * Optional hook used to allocate page tables. If this function is NULL,
+	 * @free must be NULL too.
+	 *
+	 * Memory returned should be zeroed and suitable for dma_map_single() and
+	 * virt_to_phys().
+	 *
+	 * Not all formats support custom page allocators. Before considering
+	 * passing a non-NULL value, make sure the chosen page format supports
+	 * this feature.
+	 */
+	void *(*alloc)(void *cookie, size_t size, gfp_t gfp);
+
+	/**
+	 * @free: Custom page de-allocator.
+	 *
+	 * Optional hook used to free page tables allocated with the @alloc
+	 * hook. Must be non-NULL if @alloc is not NULL, must be NULL
+	 * otherwise.
+	 */
+	void (*free)(void *cookie, void *pages, size_t size);
+
 	/* Low-level data specific to the table format */
 	union {
 		struct {
@@ -241,16 +265,26 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop,
 		iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie);
 }
 
+/**
+ * enum io_pgtable_caps - IO page table backend capabilities.
+ */
+enum io_pgtable_caps {
+	/** @IO_PGTABLE_CAP_CUSTOM_ALLOCATOR: Backend accepts custom page table allocators. */
+	IO_PGTABLE_CAP_CUSTOM_ALLOCATOR = BIT(0),
+};
+
 /**
  * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
  *                              particular format.
  *
  * @alloc: Allocate a set of page tables described by cfg.
  * @free:  Free the page tables associated with iop.
+ * @caps:  Combination of @io_pgtable_caps flags encoding the backend capabilities.
  */
 struct io_pgtable_init_fns {
 	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
 	void (*free)(struct io_pgtable *iop);
+	u32 caps;
 };
 
 extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;
-- 
GitLab


From 87639e01e05c716d8fd5d63846b6d9a8b0a2e79a Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@collabora.com>
Date: Fri, 24 Nov 2023 15:24:34 +0100
Subject: [PATCH 0485/4076] iommu: Extend LPAE page table format to support
 custom allocators

We need that in order to implement the VM_BIND ioctl in the GPU driver
targeting new Mali GPUs.

VM_BIND is about executing MMU map/unmap requests asynchronously,
possibly after waiting for external dependencies encoded as dma_fences.
We intend to use the drm_sched framework to automate the dependency
tracking and VM job dequeuing logic, but this comes with its own set
of constraints, one of them being the fact we are not allowed to
allocate memory in the drm_gpu_scheduler_ops::run_job() to avoid this
sort of deadlocks:

- VM_BIND map job needs to allocate a page table to map some memory
  to the VM. No memory available, so kswapd is kicked
- GPU driver shrinker backend ends up waiting on the fence attached to
  the VM map job or any other job fence depending on this VM operation.

With custom allocators, we will be able to pre-reserve enough pages to
guarantee the map/unmap operations we queued will take place without
going through the system allocator. But we can also optimize
allocation/reservation by not free-ing pages immediately, so any
upcoming page table allocation requests can be serviced by some free
page table pool kept at the driver level.

I might also be valuable for other aspects of GPU and similar
use-cases, like fine-grained memory accounting and resource limiting.

Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20231124142434.1577550-3-boris.brezillon@collabora.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/io-pgtable-arm.c | 55 ++++++++++++++++++++++++----------
 1 file changed, 39 insertions(+), 16 deletions(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 72dcdd468cf30..f7828a7aad410 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -188,20 +188,28 @@ static dma_addr_t __arm_lpae_dma_addr(void *pages)
 }
 
 static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
-				    struct io_pgtable_cfg *cfg)
+				    struct io_pgtable_cfg *cfg,
+				    void *cookie)
 {
 	struct device *dev = cfg->iommu_dev;
 	int order = get_order(size);
-	struct page *p;
 	dma_addr_t dma;
 	void *pages;
 
 	VM_BUG_ON((gfp & __GFP_HIGHMEM));
-	p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
-	if (!p)
+
+	if (cfg->alloc) {
+		pages = cfg->alloc(cookie, size, gfp);
+	} else {
+		struct page *p;
+
+		p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
+		pages = p ? page_address(p) : NULL;
+	}
+
+	if (!pages)
 		return NULL;
 
-	pages = page_address(p);
 	if (!cfg->coherent_walk) {
 		dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
@@ -220,18 +228,28 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 out_unmap:
 	dev_err(dev, "Cannot accommodate DMA translation for IOMMU page tables\n");
 	dma_unmap_single(dev, dma, size, DMA_TO_DEVICE);
+
 out_free:
-	__free_pages(p, order);
+	if (cfg->free)
+		cfg->free(cookie, pages, size);
+	else
+		free_pages((unsigned long)pages, order);
+
 	return NULL;
 }
 
 static void __arm_lpae_free_pages(void *pages, size_t size,
-				  struct io_pgtable_cfg *cfg)
+				  struct io_pgtable_cfg *cfg,
+				  void *cookie)
 {
 	if (!cfg->coherent_walk)
 		dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
 				 size, DMA_TO_DEVICE);
-	free_pages((unsigned long)pages, get_order(size));
+
+	if (cfg->free)
+		cfg->free(cookie, pages, size);
+	else
+		free_pages((unsigned long)pages, get_order(size));
 }
 
 static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries,
@@ -373,13 +391,13 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 	/* Grab a pointer to the next level */
 	pte = READ_ONCE(*ptep);
 	if (!pte) {
-		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg);
+		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg, data->iop.cookie);
 		if (!cptep)
 			return -ENOMEM;
 
 		pte = arm_lpae_install_table(cptep, ptep, 0, data);
 		if (pte)
-			__arm_lpae_free_pages(cptep, tblsz, cfg);
+			__arm_lpae_free_pages(cptep, tblsz, cfg, data->iop.cookie);
 	} else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) {
 		__arm_lpae_sync_pte(ptep, 1, cfg);
 	}
@@ -524,7 +542,7 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
 		__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
 	}
 
-	__arm_lpae_free_pages(start, table_size, &data->iop.cfg);
+	__arm_lpae_free_pages(start, table_size, &data->iop.cfg, data->iop.cookie);
 }
 
 static void arm_lpae_free_pgtable(struct io_pgtable *iop)
@@ -552,7 +570,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
 		return 0;
 
-	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg);
+	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg, data->iop.cookie);
 	if (!tablep)
 		return 0; /* Bytes unmapped */
 
@@ -575,7 +593,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 
 	pte = arm_lpae_install_table(tablep, ptep, blk_pte, data);
 	if (pte != blk_pte) {
-		__arm_lpae_free_pages(tablep, tablesz, cfg);
+		__arm_lpae_free_pages(tablep, tablesz, cfg, data->iop.cookie);
 		/*
 		 * We may race against someone unmapping another part of this
 		 * block, but anything else is invalid. We can't misinterpret
@@ -882,7 +900,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* Looking good; allocate a pgd */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
-					   GFP_KERNEL, cfg);
+					   GFP_KERNEL, cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -984,7 +1002,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* Allocate pgd pages */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
-					   GFP_KERNEL, cfg);
+					   GFP_KERNEL, cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1059,7 +1077,7 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL,
-					   cfg);
+					   cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1080,26 +1098,31 @@ out_free_data:
 }
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_64_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_64_lpae_alloc_pgtable_s2,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_32_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_32_lpae_alloc_pgtable_s2,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_mali_lpae_alloc_pgtable,
 	.free	= arm_lpae_free_pgtable,
 };
-- 
GitLab


From e4c3a81ab88f3230713f4678deb9dd3cb8d0382c Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Wed, 11 Oct 2023 20:59:23 +0100
Subject: [PATCH 0486/4076] pinctrl: renesas: rzg2l: Enhance driver to support
 interrupt affinity setting

Implement irq_set_affinity callback so that we can set affinity
for GPIO IRQs.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231011195923.67404-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 9de350ad7e7d5..aed59c53207c7 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -1576,6 +1576,7 @@ static const struct irq_chip rzg2l_gpio_irqchip = {
 	.irq_set_type = rzg2l_gpio_irq_set_type,
 	.irq_eoi = rzg2l_gpio_irqc_eoi,
 	.irq_print_chip = rzg2l_gpio_irq_print_chip,
+	.irq_set_affinity = irq_chip_set_affinity_parent,
 	.flags = IRQCHIP_IMMUTABLE,
 	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
-- 
GitLab


From dc99d4c8ac46bf533b9519a53795c4cd6ff0fa39 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 22 Nov 2023 15:44:08 -0700
Subject: [PATCH 0487/4076] dt-bindings: pinctrl: renesas: Drop unneeded quotes

Drop unneeded quotes over simple string values to fix a soon to be
enabled yamllint warning:

  [error] string value is redundantly quoted with any quotes (quoted-strings)

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231122224409.2808999-1-robh@kernel.org
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 .../devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml       | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml
index 8271e7b2c162a..8b8e4e1a000f6 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml
@@ -20,7 +20,7 @@ description:
 
 properties:
   compatible:
-    const: "renesas,r7s9210-pinctrl" # RZ/A2M
+    const: renesas,r7s9210-pinctrl # RZ/A2M
 
   reg:
     maxItems: 1
-- 
GitLab


From a08bd8df97b7549fe0edc53d087322314a0c4dfe Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@svenpeter.dev>
Date: Sun, 26 Nov 2023 16:16:59 +0100
Subject: [PATCH 0488/4076] dt-bindings: iommu: dart: Add t8103-usb4-dart
 compatible

This DART variant is found in the t8103 (M1) SoCs and used for the
USB4/Thunderbolt PCIe ports. Unlike the regular t8103 DART these support
up to 64 SIDs and require a slightly different MMIO layout.

Acked-by: Hector Martin <marcan@marcan.st>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Sven Peter <sven@svenpeter.dev>
Link: https://lore.kernel.org/r/20231126151701.16534-2-sven@svenpeter.dev
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 Documentation/devicetree/bindings/iommu/apple,dart.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/iommu/apple,dart.yaml b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
index 903edf85d72e4..7adb1de455a5b 100644
--- a/Documentation/devicetree/bindings/iommu/apple,dart.yaml
+++ b/Documentation/devicetree/bindings/iommu/apple,dart.yaml
@@ -24,6 +24,7 @@ properties:
   compatible:
     enum:
       - apple,t8103-dart
+      - apple,t8103-usb4-dart
       - apple,t8110-dart
       - apple,t6000-dart
 
-- 
GitLab


From c58a17a99753749aabd979bc62babb2243266dcc Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@svenpeter.dev>
Date: Sun, 26 Nov 2023 16:17:00 +0100
Subject: [PATCH 0489/4076] iommu/apple-dart: Write to all
 DART_T8020_STREAM_SELECT

We're about to add support for a DART variant that use more than 16
streams and requires writing to two separate stream select registers
when issuing TLB flushes.

Acked-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Sven Peter <sven@svenpeter.dev>
Link: https://lore.kernel.org/r/20231126151701.16534-3-sven@svenpeter.dev
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/apple-dart.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index ee05f4824bfad..8b6b0cdba9b57 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -368,12 +368,14 @@ apple_dart_t8020_hw_stream_command(struct apple_dart_stream_map *stream_map,
 			     u32 command)
 {
 	unsigned long flags;
-	int ret;
+	int ret, i;
 	u32 command_reg;
 
 	spin_lock_irqsave(&stream_map->dart->lock, flags);
 
-	writel(stream_map->sidmap[0], stream_map->dart->regs + DART_T8020_STREAM_SELECT);
+	for (i = 0; i < BITS_TO_U32(stream_map->dart->num_streams); i++)
+		writel(stream_map->sidmap[i],
+		       stream_map->dart->regs + DART_T8020_STREAM_SELECT + 4 * i);
 	writel(command, stream_map->dart->regs + DART_T8020_STREAM_COMMAND);
 
 	ret = readl_poll_timeout_atomic(
-- 
GitLab


From 863c092323ab17a5bc4b2f3185d4136f9e57bbe3 Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@svenpeter.dev>
Date: Sun, 26 Nov 2023 16:17:01 +0100
Subject: [PATCH 0490/4076] iommu/apple-dart: Add support for t8103 USB4 DART

This variant of the regular t8103 DART is used for the two
USB4/Thunderbolt PCIe controllers. It supports 64 instead of 16 streams
which requires a slightly different MMIO layout.

Acked-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Sven Peter <sven@svenpeter.dev>
Link: https://lore.kernel.org/r/20231126151701.16534-4-sven@svenpeter.dev
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/apple-dart.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index 8b6b0cdba9b57..f47f60c0a4d0d 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -81,6 +81,7 @@
 #define DART_T8020_TCR_BYPASS_DAPF      BIT(12)
 
 #define DART_T8020_TTBR       0x200
+#define DART_T8020_USB4_TTBR  0x400
 #define DART_T8020_TTBR_VALID BIT(31)
 #define DART_T8020_TTBR_ADDR_FIELD_SHIFT 0
 #define DART_T8020_TTBR_SHIFT 12
@@ -1217,6 +1218,33 @@ static const struct apple_dart_hw apple_dart_hw_t8103 = {
 	.ttbr_shift = DART_T8020_TTBR_SHIFT,
 	.ttbr_count = 4,
 };
+
+static const struct apple_dart_hw apple_dart_hw_t8103_usb4 = {
+	.type = DART_T8020,
+	.irq_handler = apple_dart_t8020_irq,
+	.invalidate_tlb = apple_dart_t8020_hw_invalidate_tlb,
+	.oas = 36,
+	.fmt = APPLE_DART,
+	.max_sid_count = 64,
+
+	.enable_streams = DART_T8020_STREAMS_ENABLE,
+	.lock = DART_T8020_CONFIG,
+	.lock_bit = DART_T8020_CONFIG_LOCK,
+
+	.error = DART_T8020_ERROR,
+
+	.tcr = DART_T8020_TCR,
+	.tcr_enabled = DART_T8020_TCR_TRANSLATE_ENABLE,
+	.tcr_disabled = 0,
+	.tcr_bypass = 0,
+
+	.ttbr = DART_T8020_USB4_TTBR,
+	.ttbr_valid = DART_T8020_TTBR_VALID,
+	.ttbr_addr_field_shift = DART_T8020_TTBR_ADDR_FIELD_SHIFT,
+	.ttbr_shift = DART_T8020_TTBR_SHIFT,
+	.ttbr_count = 4,
+};
+
 static const struct apple_dart_hw apple_dart_hw_t6000 = {
 	.type = DART_T6000,
 	.irq_handler = apple_dart_t8020_irq,
@@ -1309,6 +1337,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dar
 
 static const struct of_device_id apple_dart_of_match[] = {
 	{ .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 },
+	{ .compatible = "apple,t8103-usb4-dart", .data = &apple_dart_hw_t8103_usb4 },
 	{ .compatible = "apple,t8110-dart", .data = &apple_dart_hw_t8110 },
 	{ .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 },
 	{},
-- 
GitLab


From 60732292a135e8b8152858f219a563c05e9569e9 Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@svenpeter.dev>
Date: Sun, 26 Nov 2023 17:20:09 +0100
Subject: [PATCH 0491/4076] iommu/apple-dart: Use readl instead of
 readl_relaxed for consistency

While the readl_relaxed in apple_dart_suspend is correct the rest of the
driver uses the non-relaxed variants everywhere and the single
readl_relaxed is inconsistent and possibly confusing.

Signed-off-by: Sven Peter <sven@svenpeter.dev>
Acked-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Neal Gompa <neal@gompa.dev>
Link: https://lore.kernel.org/r/20231126162009.17934-1-sven@svenpeter.dev
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/apple-dart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index f47f60c0a4d0d..7438e9c82ba98 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -1302,7 +1302,7 @@ static __maybe_unused int apple_dart_suspend(struct device *dev)
 	unsigned int sid, idx;
 
 	for (sid = 0; sid < dart->num_streams; sid++) {
-		dart->save_tcr[sid] = readl_relaxed(dart->regs + DART_TCR(dart, sid));
+		dart->save_tcr[sid] = readl(dart->regs + DART_TCR(dart, sid));
 		for (idx = 0; idx < dart->hw->ttbr_count; idx++)
 			dart->save_ttbr[sid][idx] =
 				readl(dart->regs + DART_TTBR(dart, sid, idx));
-- 
GitLab


From 130601d488fa06447283767e447909ce9e975e43 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Fri, 24 Nov 2023 09:41:14 +0100
Subject: [PATCH 0492/4076] dt-bindings: phy:
 amlogic,meson-axg-mipi-pcie-analog: drop text about parent syscon and drop
 example

Since this bindings is referred from amlogic,meson-gx-hhi-sysctrl.yaml, drop the now
useless description about the parent node and also drop the unnecessary example.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231124-amlogic-v6-4-upstream-dsi-ccf-vim3-v9-3-95256ed139e6@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../phy/amlogic,meson-axg-mipi-pcie-analog.yaml | 17 -----------------
 1 file changed, 17 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml
index 009a398083185..70def36e5688d 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml
@@ -9,16 +9,6 @@ title: Amlogic AXG shared MIPI/PCIE analog PHY
 maintainers:
   - Remi Pommarel <repk@triplefau.lt>
 
-description: |+
-  The Everything-Else Power Domains node should be the child of a syscon
-  node with the required property:
-
-  - compatible: Should be the following:
-                "amlogic,meson-gx-hhi-sysctrl", "simple-mfd", "syscon"
-
-  Refer to the bindings described in
-  Documentation/devicetree/bindings/mfd/syscon.yaml
-
 properties:
   compatible:
     const: amlogic,axg-mipi-pcie-analog-phy
@@ -31,10 +21,3 @@ required:
   - "#phy-cells"
 
 additionalProperties: false
-
-examples:
-  - |
-    mpphy: phy {
-          compatible = "amlogic,axg-mipi-pcie-analog-phy";
-          #phy-cells = <0>;
-    };
-- 
GitLab


From 5f4a9a66f8a7582e90311fa8251da33a8d2111d7 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Fri, 24 Nov 2023 09:41:15 +0100
Subject: [PATCH 0493/4076] dt-bindings: phy: amlogic,g12a-mipi-dphy-analog:
 drop unneeded reg property and example

The amlogic,g12a-mipi-dphy-analog is a feature of the simple-mfd
amlogic,meson-axg-hhi-sysctrl system control register zone which is an
intermixed registers zone, thus it's very hard to define clear ranges for
each SoC controlled features even if possible.

The amlogic,g12a-mipi-dphy-analog was wrongly documented as an independent
register range, which is not the reality, thus fix the bindings by dropping
the reg property now it's referred from amlogic,meson-gx-hhi-sysctrl.yaml
and documented as a subnode of amlogic,meson-axg-hhi-sysctrl.

Also drop the unnecessary example, the top level bindings example should
be enough.

Fixes: 76ab79f9726c ("dt-bindings: phy: add Amlogic G12A Analog MIPI D-PHY bindings")
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231124-amlogic-v6-4-upstream-dsi-ccf-vim3-v9-4-95256ed139e6@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml  | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml
index c8c83acfb871d..81c2654b7e57e 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml
@@ -16,20 +16,8 @@ properties:
   "#phy-cells":
     const: 0
 
-  reg:
-    maxItems: 1
-
 required:
   - compatible
-  - reg
   - "#phy-cells"
 
 additionalProperties: false
-
-examples:
-  - |
-    phy@0 {
-          compatible = "amlogic,g12a-mipi-dphy-analog";
-          reg = <0x0 0xc>;
-          #phy-cells = <0>;
-    };
-- 
GitLab


From fa50920b4f82993941e0aac349eb8081ce11e38f Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Thu, 23 Nov 2023 14:37:47 +0100
Subject: [PATCH 0494/4076] dt-bindings: phy: add compatible for Mediatek
 MT8195

Add the compatible string for MediaTek MT8195 SoC, using the same MIPI
D-PHY block as the MT8183.

Signed-off-by: Michael Walle <mwalle@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231123133749.2030661-3-mwalle@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml b/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
index 6703689fcdbe1..f6e494d0d89b8 100644
--- a/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
@@ -31,6 +31,7 @@ properties:
       - items:
           - enum:
               - mediatek,mt8188-mipi-tx
+              - mediatek,mt8195-mipi-tx
               - mediatek,mt8365-mipi-tx
           - const: mediatek,mt8183-mipi-tx
       - const: mediatek,mt2701-mipi-tx
-- 
GitLab


From 2fda59099462ee700e424ba3ac928d13ad6389a8 Mon Sep 17 00:00:00 2001
From: Alex Bee <knaerzche@gmail.com>
Date: Sun, 19 Nov 2023 13:13:36 +0100
Subject: [PATCH 0495/4076] phy: rockchip-inno-usb2: Split ID interrupt phy
 registers

Commit 51a9b2c03dd3 ("phy: rockchip-inno-usb2: Handle ID IRQ") added ID
detection interrupt registers. However the current implementation assumes
that falling and rising edge interrupt are always enabled in registers
spanning over subsequent bits.
That is not the case for RK3128's version of the phy and this
implementation can't be used as-is, since there are bits with different
purpose in between.

This splits up the register definitions for id_det_en, id_det_en and
id_det_clr registers in rising and falling edge variants.
It's required as preparation to support RK3128's Innosilicon usb2 phy as
well in this driver and matches pretty much to what the vendor does, so I'm
not expecting issues for other SoCs with that change.

Signed-off-by: Alex Bee <knaerzche@gmail.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20231119121340.109025-2-knaerzche@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 99 +++++++++++++------
 1 file changed, 70 insertions(+), 29 deletions(-)

diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index a24d2af154df7..b5a1d30df83a1 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -123,9 +123,12 @@ struct rockchip_chg_det_reg {
  * @disrise_en: host disconnect rise edge detection enable.
  * @disrise_st: host disconnect rise edge detection state.
  * @disrise_clr: host disconnect rise edge detection clear.
- * @id_det_en: id detection enable register.
- * @id_det_st: id detection state register.
- * @id_det_clr: id detection clear register.
+ * @idfall_det_en: id detection enable register, falling edge
+ * @idfall_det_st: id detection state register, falling edge
+ * @idfall_det_clr: id detection clear register, falling edge
+ * @idrise_det_en: id detection enable register, rising edge
+ * @idrise_det_st: id detection state register, rising edge
+ * @idrise_det_clr: id detection clear register, rising edge
  * @ls_det_en: linestate detection enable register.
  * @ls_det_st: linestate detection state register.
  * @ls_det_clr: linestate detection clear register.
@@ -146,9 +149,12 @@ struct rockchip_usb2phy_port_cfg {
 	struct usb2phy_reg      disrise_en;
 	struct usb2phy_reg      disrise_st;
 	struct usb2phy_reg      disrise_clr;
-	struct usb2phy_reg	id_det_en;
-	struct usb2phy_reg	id_det_st;
-	struct usb2phy_reg	id_det_clr;
+	struct usb2phy_reg	idfall_det_en;
+	struct usb2phy_reg	idfall_det_st;
+	struct usb2phy_reg	idfall_det_clr;
+	struct usb2phy_reg	idrise_det_en;
+	struct usb2phy_reg	idrise_det_st;
+	struct usb2phy_reg	idrise_det_clr;
 	struct usb2phy_reg	ls_det_en;
 	struct usb2phy_reg	ls_det_st;
 	struct usb2phy_reg	ls_det_clr;
@@ -488,15 +494,27 @@ static int rockchip_usb2phy_init(struct phy *phy)
 			if (ret)
 				goto out;
 
-			/* clear id status and enable id detect irq */
+			/* clear id status and enable id detect irqs */
 			ret = property_enable(rphy->grf,
-					      &rport->port_cfg->id_det_clr,
+					      &rport->port_cfg->idfall_det_clr,
 					      true);
 			if (ret)
 				goto out;
 
 			ret = property_enable(rphy->grf,
-					      &rport->port_cfg->id_det_en,
+					      &rport->port_cfg->idrise_det_clr,
+					      true);
+			if (ret)
+				goto out;
+
+			ret = property_enable(rphy->grf,
+					      &rport->port_cfg->idfall_det_en,
+					      true);
+			if (ret)
+				goto out;
+
+			ret = property_enable(rphy->grf,
+					      &rport->port_cfg->idrise_det_en,
 					      true);
 			if (ret)
 				goto out;
@@ -1030,11 +1048,16 @@ static irqreturn_t rockchip_usb2phy_id_irq(int irq, void *data)
 	struct rockchip_usb2phy *rphy = dev_get_drvdata(rport->phy->dev.parent);
 	bool id;
 
-	if (!property_enabled(rphy->grf, &rport->port_cfg->id_det_st))
+	if (!property_enabled(rphy->grf, &rport->port_cfg->idfall_det_st) &&
+	    !property_enabled(rphy->grf, &rport->port_cfg->idrise_det_st))
 		return IRQ_NONE;
 
 	/* clear id detect irq pending status */
-	property_enable(rphy->grf, &rport->port_cfg->id_det_clr, true);
+	if (property_enabled(rphy->grf, &rport->port_cfg->idfall_det_st))
+		property_enable(rphy->grf, &rport->port_cfg->idfall_det_clr, true);
+
+	if (property_enabled(rphy->grf, &rport->port_cfg->idrise_det_st))
+		property_enable(rphy->grf, &rport->port_cfg->idrise_det_clr, true);
 
 	id = property_enabled(rphy->grf, &rport->port_cfg->utmi_id);
 	extcon_set_state_sync(rphy->edev, EXTCON_USB_HOST, !id);
@@ -1524,9 +1547,12 @@ static const struct rockchip_usb2phy_cfg rk3228_phy_cfgs[] = {
 				.bvalid_det_en	= { 0x0680, 3, 3, 0, 1 },
 				.bvalid_det_st	= { 0x0690, 3, 3, 0, 1 },
 				.bvalid_det_clr	= { 0x06a0, 3, 3, 0, 1 },
-				.id_det_en	= { 0x0680, 6, 5, 0, 3 },
-				.id_det_st	= { 0x0690, 6, 5, 0, 3 },
-				.id_det_clr	= { 0x06a0, 6, 5, 0, 3 },
+				.idfall_det_en	= { 0x0680, 6, 6, 0, 1 },
+				.idfall_det_st	= { 0x0690, 6, 6, 0, 1 },
+				.idfall_det_clr	= { 0x06a0, 6, 6, 0, 1 },
+				.idrise_det_en	= { 0x0680, 5, 5, 0, 1 },
+				.idrise_det_st	= { 0x0690, 5, 5, 0, 1 },
+				.idrise_det_clr	= { 0x06a0, 5, 5, 0, 1 },
 				.ls_det_en	= { 0x0680, 2, 2, 0, 1 },
 				.ls_det_st	= { 0x0690, 2, 2, 0, 1 },
 				.ls_det_clr	= { 0x06a0, 2, 2, 0, 1 },
@@ -1587,9 +1613,12 @@ static const struct rockchip_usb2phy_cfg rk3308_phy_cfgs[] = {
 				.bvalid_det_en	= { 0x3020, 3, 2, 0, 3 },
 				.bvalid_det_st	= { 0x3024, 3, 2, 0, 3 },
 				.bvalid_det_clr = { 0x3028, 3, 2, 0, 3 },
-				.id_det_en	= { 0x3020, 5, 4, 0, 3 },
-				.id_det_st	= { 0x3024, 5, 4, 0, 3 },
-				.id_det_clr	= { 0x3028, 5, 4, 0, 3 },
+				.idfall_det_en	= { 0x3020, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0x3024, 5, 5, 0, 1 },
+				.idfall_det_clr = { 0x3028, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0x3020, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0x3024, 4, 4, 0, 1 },
+				.idrise_det_clr = { 0x3028, 4, 4, 0, 1 },
 				.ls_det_en	= { 0x3020, 0, 0, 0, 1 },
 				.ls_det_st	= { 0x3024, 0, 0, 0, 1 },
 				.ls_det_clr	= { 0x3028, 0, 0, 0, 1 },
@@ -1634,9 +1663,12 @@ static const struct rockchip_usb2phy_cfg rk3328_phy_cfgs[] = {
 				.bvalid_det_en	= { 0x0110, 3, 2, 0, 3 },
 				.bvalid_det_st	= { 0x0114, 3, 2, 0, 3 },
 				.bvalid_det_clr = { 0x0118, 3, 2, 0, 3 },
-				.id_det_en	= { 0x0110, 5, 4, 0, 3 },
-				.id_det_st	= { 0x0114, 5, 4, 0, 3 },
-				.id_det_clr	= { 0x0118, 5, 4, 0, 3 },
+				.idfall_det_en	= { 0x0110, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0x0114, 5, 5, 0, 1 },
+				.idfall_det_clr = { 0x0118, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0x0110, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0x0114, 4, 4, 0, 1 },
+				.idrise_det_clr = { 0x0118, 4, 4, 0, 1 },
 				.ls_det_en	= { 0x0110, 0, 0, 0, 1 },
 				.ls_det_st	= { 0x0114, 0, 0, 0, 1 },
 				.ls_det_clr	= { 0x0118, 0, 0, 0, 1 },
@@ -1700,9 +1732,12 @@ static const struct rockchip_usb2phy_cfg rk3399_phy_cfgs[] = {
 				.bvalid_det_en	= { 0xe3c0, 3, 3, 0, 1 },
 				.bvalid_det_st	= { 0xe3e0, 3, 3, 0, 1 },
 				.bvalid_det_clr	= { 0xe3d0, 3, 3, 0, 1 },
-				.id_det_en	= { 0xe3c0, 5, 4, 0, 3 },
-				.id_det_st	= { 0xe3e0, 5, 4, 0, 3 },
-				.id_det_clr	= { 0xe3d0, 5, 4, 0, 3 },
+				.idfall_det_en	= { 0xe3c0, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0xe3e0, 5, 5, 0, 1 },
+				.idfall_det_clr	= { 0xe3d0, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0xe3c0, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0xe3e0, 4, 4, 0, 1 },
+				.idrise_det_clr	= { 0xe3d0, 4, 4, 0, 1 },
 				.utmi_avalid	= { 0xe2ac, 7, 7, 0, 1 },
 				.utmi_bvalid	= { 0xe2ac, 12, 12, 0, 1 },
 				.utmi_id	= { 0xe2ac, 8, 8, 0, 1 },
@@ -1739,9 +1774,12 @@ static const struct rockchip_usb2phy_cfg rk3399_phy_cfgs[] = {
 				.bvalid_det_en  = { 0xe3c0, 8, 8, 0, 1 },
 				.bvalid_det_st  = { 0xe3e0, 8, 8, 0, 1 },
 				.bvalid_det_clr = { 0xe3d0, 8, 8, 0, 1 },
-				.id_det_en	= { 0xe3c0, 10, 9, 0, 3 },
-				.id_det_st	= { 0xe3e0, 10, 9, 0, 3 },
-				.id_det_clr	= { 0xe3d0, 10, 9, 0, 3 },
+				.idfall_det_en	= { 0xe3c0, 10, 10, 0, 1 },
+				.idfall_det_st	= { 0xe3e0, 10, 10, 0, 1 },
+				.idfall_det_clr	= { 0xe3d0, 10, 10, 0, 1 },
+				.idrise_det_en	= { 0xe3c0, 9, 9, 0, 1 },
+				.idrise_det_st	= { 0xe3e0, 9, 9, 0, 1 },
+				.idrise_det_clr	= { 0xe3d0, 9, 9, 0, 1 },
 				.utmi_avalid	= { 0xe2ac, 10, 10, 0, 1 },
 				.utmi_bvalid    = { 0xe2ac, 16, 16, 0, 1 },
 				.utmi_id	= { 0xe2ac, 11, 11, 0, 1 },
@@ -1770,9 +1808,12 @@ static const struct rockchip_usb2phy_cfg rk3568_phy_cfgs[] = {
 				.bvalid_det_en	= { 0x0080, 3, 2, 0, 3 },
 				.bvalid_det_st	= { 0x0084, 3, 2, 0, 3 },
 				.bvalid_det_clr = { 0x0088, 3, 2, 0, 3 },
-				.id_det_en	= { 0x0080, 5, 4, 0, 3 },
-				.id_det_st	= { 0x0084, 5, 4, 0, 3 },
-				.id_det_clr	= { 0x0088, 5, 4, 0, 3 },
+				.idfall_det_en	= { 0x0080, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0x0084, 5, 5, 0, 1 },
+				.idfall_det_clr	= { 0x0088, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0x0080, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0x0084, 4, 4, 0, 1 },
+				.idrise_det_clr	= { 0x0088, 4, 4, 0, 1 },
 				.utmi_avalid	= { 0x00c0, 10, 10, 0, 1 },
 				.utmi_bvalid	= { 0x00c0, 9, 9, 0, 1 },
 				.utmi_id	= { 0x00c0, 6, 6, 0, 1 },
-- 
GitLab


From 62ff41017e147472b07de6125c3be82ce02a8dd7 Mon Sep 17 00:00:00 2001
From: Alex Bee <knaerzche@gmail.com>
Date: Sun, 19 Nov 2023 13:13:37 +0100
Subject: [PATCH 0496/4076] phy: phy-rockchip-inno-usb2: Add RK3128 support

Add registers to support the 2-port usb2 phy found in RK312x SoC familiy.

Signed-off-by: Alex Bee <knaerzche@gmail.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20231119121340.109025-3-knaerzche@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 57 +++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index b5a1d30df83a1..4f71373ae6e1a 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -1487,6 +1487,14 @@ put_child:
 	return ret;
 }
 
+static int rk3128_usb2phy_tuning(struct rockchip_usb2phy *rphy)
+{
+	/* Turn off differential receiver in suspend mode */
+	return regmap_write_bits(rphy->grf, 0x298,
+				BIT(2) << BIT_WRITEABLE_SHIFT | BIT(2),
+				BIT(2) << BIT_WRITEABLE_SHIFT | 0);
+}
+
 static int rk3588_usb2phy_tuning(struct rockchip_usb2phy *rphy)
 {
 	int ret;
@@ -1536,6 +1544,54 @@ static int rk3588_usb2phy_tuning(struct rockchip_usb2phy *rphy)
 	return ret;
 }
 
+static const struct rockchip_usb2phy_cfg rk3128_phy_cfgs[] = {
+	{
+		.reg = 0x17c,
+		.num_ports	= 2,
+		.phy_tuning	= rk3128_usb2phy_tuning,
+		.clkout_ctl	= { 0x0190, 15, 15, 1, 0 },
+		.port_cfgs	= {
+			[USB2PHY_PORT_OTG] = {
+				.phy_sus	= { 0x017c, 8, 0, 0, 0x1d1 },
+				.bvalid_det_en	= { 0x017c, 14, 14, 0, 1 },
+				.bvalid_det_st	= { 0x017c, 15, 15, 0, 1 },
+				.bvalid_det_clr	= { 0x017c, 15, 15, 0, 1 },
+				.idfall_det_en  = { 0x01a0, 2, 2, 0, 1 },
+				.idfall_det_st  = { 0x01a0, 3, 3, 0, 1 },
+				.idfall_det_clr = { 0x01a0, 3, 3, 0, 1 },
+				.idrise_det_en  = { 0x01a0, 0, 0, 0, 1 },
+				.idrise_det_st  = { 0x01a0, 1, 1, 0, 1 },
+				.idrise_det_clr = { 0x01a0, 1, 1, 0, 1 },
+				.ls_det_en	= { 0x017c, 12, 12, 0, 1 },
+				.ls_det_st	= { 0x017c, 13, 13, 0, 1 },
+				.ls_det_clr	= { 0x017c, 13, 13, 0, 1 },
+				.utmi_bvalid	= { 0x014c, 5, 5, 0, 1 },
+				.utmi_id	= { 0x014c, 8, 8, 0, 1 },
+				.utmi_ls	= { 0x014c, 7, 6, 0, 1 },
+			},
+			[USB2PHY_PORT_HOST] = {
+				.phy_sus	= { 0x0194, 8, 0, 0, 0x1d1 },
+				.ls_det_en	= { 0x0194, 14, 14, 0, 1 },
+				.ls_det_st	= { 0x0194, 15, 15, 0, 1 },
+				.ls_det_clr	= { 0x0194, 15, 15, 0, 1 }
+			}
+		},
+		.chg_det = {
+			.opmode		= { 0x017c, 3, 0, 5, 1 },
+			.cp_det		= { 0x02c0, 6, 6, 0, 1 },
+			.dcp_det	= { 0x02c0, 5, 5, 0, 1 },
+			.dp_det		= { 0x02c0, 7, 7, 0, 1 },
+			.idm_sink_en	= { 0x0184, 8, 8, 0, 1 },
+			.idp_sink_en	= { 0x0184, 7, 7, 0, 1 },
+			.idp_src_en	= { 0x0184, 9, 9, 0, 1 },
+			.rdm_pdwn_en	= { 0x0184, 10, 10, 0, 1 },
+			.vdm_src_en	= { 0x0184, 12, 12, 0, 1 },
+			.vdp_src_en	= { 0x0184, 11, 11, 0, 1 },
+		},
+	},
+	{ /* sentinel */ }
+};
+
 static const struct rockchip_usb2phy_cfg rk3228_phy_cfgs[] = {
 	{
 		.reg = 0x760,
@@ -2031,6 +2087,7 @@ static const struct rockchip_usb2phy_cfg rv1108_phy_cfgs[] = {
 
 static const struct of_device_id rockchip_usb2phy_dt_match[] = {
 	{ .compatible = "rockchip,px30-usb2phy", .data = &rk3328_phy_cfgs },
+	{ .compatible = "rockchip,rk3128-usb2phy", .data = &rk3128_phy_cfgs },
 	{ .compatible = "rockchip,rk3228-usb2phy", .data = &rk3228_phy_cfgs },
 	{ .compatible = "rockchip,rk3308-usb2phy", .data = &rk3308_phy_cfgs },
 	{ .compatible = "rockchip,rk3328-usb2phy", .data = &rk3328_phy_cfgs },
-- 
GitLab


From 7f6f9e0def00cfaeb1d034fd13dbd84470aeccbd Mon Sep 17 00:00:00 2001
From: Rohit Agarwal <quic_rohiagar@quicinc.com>
Date: Fri, 17 Nov 2023 11:45:01 +0530
Subject: [PATCH 0497/4076] phy: qcom-qmp-usb: Add Qualcomm SDX75 USB3 PHY
 support

Add support for USB3 QMP PHY found in SDX75 platform.

Signed-off-by: Rohit Agarwal <quic_rohiagar@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231117061501.537529-1-quic_rohiagar@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-usb.c | 173 ++++++++++++++++++++++++
 1 file changed, 173 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 02f156298e77c..77e91b3eae79e 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -24,6 +24,7 @@
 #include "phy-qcom-qmp-pcs-misc-v4.h"
 #include "phy-qcom-qmp-pcs-usb-v4.h"
 #include "phy-qcom-qmp-pcs-usb-v5.h"
+#include "phy-qcom-qmp-pcs-usb-v6.h"
 
 /* QPHY_SW_RESET bit */
 #define SW_RESET				BIT(0)
@@ -151,6 +152,17 @@ static const unsigned int qmp_v5_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = {
 	[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V5_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR,
 };
 
+static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = {
+	[QPHY_SW_RESET]			= QPHY_V6_PCS_SW_RESET,
+	[QPHY_START_CTRL]		= QPHY_V6_PCS_START_CONTROL,
+	[QPHY_PCS_STATUS]		= QPHY_V6_PCS_PCS_STATUS1,
+	[QPHY_PCS_POWER_DOWN_CONTROL]	= QPHY_V6_PCS_POWER_DOWN_CONTROL,
+
+	/* In PCS_USB */
+	[QPHY_PCS_AUTONOMOUS_MODE_CTRL]	= QPHY_V6_PCS_USB3_AUTONOMOUS_MODE_CTRL,
+	[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V6_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR,
+};
+
 static const struct qmp_phy_init_tbl ipq9574_usb3_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x1a),
 	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x08),
@@ -871,6 +883,134 @@ static const struct qmp_phy_init_tbl sdx65_usb3_uniphy_rx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_RX_SIGDET_ENABLES, 0x00),
 };
 
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x2e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xea),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0xb7),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0xb7),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x34),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xea),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC, 0x0c),
+};
+
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_TX, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_RX, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_OFFSET_RX, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_1, 0xf5),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_3, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_4, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_5, 0x5f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_RCV_DETECT_LVL_2, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V6_TX_PI_QEC_CTRL, 0x21),
+};
+
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FO_GAIN, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SO_GAIN, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x7f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_PI_CONTROLS, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_THRESH1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_THRESH2, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_GAIN1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_GAIN2, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_AUX_DATA_TCOARSE_TFINE, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_VGA_CAL_CNTRL1, 0x54),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_VGA_CAL_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_GM_CAL, 0x13),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_IDAC_TSETTLE_LOW, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_IDAC_TSETTLE_HIGH, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x47),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CNTRL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_DEGLITCH_CNTRL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_LOW, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH, 0xbf),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH2, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH3, 0xdf),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH4, 0xed),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_LOW, 0xdc),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH, 0x5c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH2, 0x9c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH3, 0x1d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH4, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_DFE_EN_TIMER, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_DCC_CTRL1, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_VTH_CODE, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CAL_CTRL1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CAL_TRIM, 0x08),
+};
+
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG1, 0xc4),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG2, 0x89),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG3, 0x20),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG6, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x21),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0xaa),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_CDR_RESET_TIME, 0x0a),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG1, 0x88),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG2, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0c),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG1, 0x4b),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG5, 0x10),
+};
+
+static const struct qmp_phy_init_tbl sdx75_usb3_uniphy_pcs_usb_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RCVR_DTCT_DLY_U3_L, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RCVR_DTCT_DLY_U3_H, 0x00),
+};
+
 static const struct qmp_phy_init_tbl sm8350_usb3_uniphy_tx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_1, 0xa5),
 	QMP_PHY_INIT_CFG(QSERDES_V5_TX_LANE_MODE_2, 0x82),
@@ -1317,6 +1457,14 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v5 = {
 	.rx		= 0x1000,
 };
 
+static const struct qmp_usb_offsets qmp_usb_offsets_v6 = {
+	.serdes		= 0,
+	.pcs		= 0x0200,
+	.pcs_usb	= 0x1200,
+	.tx		= 0x0e00,
+	.rx		= 0x1000,
+};
+
 static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = {
 	.lanes			= 1,
 
@@ -1541,6 +1689,28 @@ static const struct qmp_phy_cfg sdx65_usb3_uniphy_cfg = {
 	.has_pwrdn_delay	= true,
 };
 
+static const struct qmp_phy_cfg sdx75_usb3_uniphy_cfg = {
+	.lanes			= 1,
+	.offsets		= &qmp_usb_offsets_v6,
+
+	.serdes_tbl		= sdx75_usb3_uniphy_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(sdx75_usb3_uniphy_serdes_tbl),
+	.tx_tbl			= sdx75_usb3_uniphy_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(sdx75_usb3_uniphy_tx_tbl),
+	.rx_tbl			= sdx75_usb3_uniphy_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(sdx75_usb3_uniphy_rx_tbl),
+	.pcs_tbl		= sdx75_usb3_uniphy_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(sdx75_usb3_uniphy_pcs_tbl),
+	.pcs_usb_tbl		= sdx75_usb3_uniphy_pcs_usb_tbl,
+	.pcs_usb_tbl_num	= ARRAY_SIZE(sdx75_usb3_uniphy_pcs_usb_tbl),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v6_usb3phy_regs_layout,
+	.pcs_usb_offset		= 0x1000,
+
+	.has_pwrdn_delay	= true,
+};
+
 static const struct qmp_phy_cfg sm8350_usb3_uniphy_cfg = {
 	.lanes			= 1,
 
@@ -2256,6 +2426,9 @@ static const struct of_device_id qmp_usb_of_match_table[] = {
 	}, {
 		.compatible = "qcom,sdx65-qmp-usb3-uni-phy",
 		.data = &sdx65_usb3_uniphy_cfg,
+	}, {
+		.compatible = "qcom,sdx75-qmp-usb3-uni-phy",
+		.data = &sdx75_usb3_uniphy_cfg,
 	}, {
 		.compatible = "qcom,sm6115-qmp-usb3-phy",
 		.data = &qcm2290_usb3phy_cfg,
-- 
GitLab


From 72b4ca7e993e94f09bcf6d19fc385a2e8060c71f Mon Sep 17 00:00:00 2001
From: Nick Forrington <nick.forrington@arm.com>
Date: Thu, 2 Nov 2023 16:22:24 +0000
Subject: [PATCH 0498/4076] perf test: Remove atomics from test_loop to avoid
 test failures

The current use of atomics can lead to test failures, as tests (such as
tests/shell/record.sh) search for samples with "test_loop" as the
top-most stack frame, but find frames related to the atomic operation
(e.g. __aarch64_ldadd4_relax).

This change simply removes the "count" variable, as it is not necessary.

Fixes: 1962ab6f6e0b39e4 ("perf test workload thloop: Make count increments atomic")
Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Nick Forrington <nick.forrington@arm.com>
Acked-by: Leo Yan <leo.yan@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231102162225.50028-1-nick.forrington@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/workloads/thloop.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/perf/tests/workloads/thloop.c b/tools/perf/tests/workloads/thloop.c
index af05269c2eb8a..457b29f91c3ee 100644
--- a/tools/perf/tests/workloads/thloop.c
+++ b/tools/perf/tests/workloads/thloop.c
@@ -7,7 +7,6 @@
 #include "../tests.h"
 
 static volatile sig_atomic_t done;
-static volatile unsigned count;
 
 /* We want to check this symbol in perf report */
 noinline void test_loop(void);
@@ -19,8 +18,7 @@ static void sighandler(int sig __maybe_unused)
 
 noinline void test_loop(void)
 {
-	while (!done)
-		__atomic_fetch_add(&count, 1, __ATOMIC_RELAXED);
+	while (!done);
 }
 
 static void *thfunc(void *arg)
-- 
GitLab


From b457c526072aa8ab312517010837b06d38b9bb66 Mon Sep 17 00:00:00 2001
From: Paran Lee <p4ranlee@gmail.com>
Date: Tue, 21 Nov 2023 07:32:19 +0900
Subject: [PATCH 0499/4076] perf script python: Fail check on dynamic
 allocation

Add PyList_New() Fail check in get_field_numeric_entry()
function and dynamic allocation checking for
set_regs_in_dict(), python_start_script().

Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: MichelleJin <shjy180909@gmail.com>
Signed-off-by: Paran Lee <p4ranlee@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Austin Kim <austindh.kim@gmail.com>
Cc: Honggyu Kim <honggyu.kp@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20231120223218.9036-1-p4ranlee@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../util/scripting-engines/trace-event-python.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 94312741443ab..860e1837ba969 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -353,6 +353,8 @@ static PyObject *get_field_numeric_entry(struct tep_event *event,
 
 	if (is_array) {
 		list = PyList_New(field->arraylen);
+		if (!list)
+			Py_FatalError("couldn't create Python list");
 		item_size = field->size / field->arraylen;
 		n_items = field->arraylen;
 	} else {
@@ -754,7 +756,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, ch
 	}
 }
 
-static void set_regs_in_dict(PyObject *dict,
+static int set_regs_in_dict(PyObject *dict,
 			     struct perf_sample *sample,
 			     struct evsel *evsel)
 {
@@ -770,6 +772,8 @@ static void set_regs_in_dict(PyObject *dict,
 	 */
 	int size = __sw_hweight64(attr->sample_regs_intr) * 28;
 	char *bf = malloc(size);
+	if (!bf)
+		return -1;
 
 	regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, size);
 
@@ -781,6 +785,8 @@ static void set_regs_in_dict(PyObject *dict,
 	pydict_set_item_string_decref(dict, "uregs",
 			_PyUnicode_FromString(bf));
 	free(bf);
+
+	return 0;
 }
 
 static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
@@ -920,7 +926,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 			PyLong_FromUnsignedLongLong(sample->cyc_cnt));
 	}
 
-	set_regs_in_dict(dict, sample, evsel);
+	if (set_regs_in_dict(dict, sample, evsel))
+		Py_FatalError("Failed to setting regs in dict");
 
 	return dict;
 }
@@ -1918,12 +1925,18 @@ static int python_start_script(const char *script, int argc, const char **argv,
 	scripting_context->session = session;
 #if PY_MAJOR_VERSION < 3
 	command_line = malloc((argc + 1) * sizeof(const char *));
+	if (!command_line)
+		return -1;
+
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
 	PyImport_AppendInittab(name, initperf_trace_context);
 #else
 	command_line = malloc((argc + 1) * sizeof(wchar_t *));
+	if (!command_line)
+		return -1;
+
 	command_line[0] = Py_DecodeLocale(script, NULL);
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
-- 
GitLab


From cd38d6b5fa2dfc3beb7311f0b373e3141620c76b Mon Sep 17 00:00:00 2001
From: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Date: Mon, 20 Nov 2023 19:23:56 +0800
Subject: [PATCH 0500/4076] perf script perl: Fail check on dynamic allocation

Return ENOMEM when dynamic allocation failed.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20231120112356.8652-1-zhaimingbing@cmss.chinamobile.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/scripting-engines/trace-event-perl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 603091317bed9..b072ac5d3bc22 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -490,6 +490,9 @@ static int perl_start_script(const char *script, int argc, const char **argv,
 	scripting_context->session = session;
 
 	command_line = malloc((argc + 2) * sizeof(const char *));
+	if (!command_line)
+		return -ENOMEM;
+
 	command_line[0] = "";
 	command_line[1] = script;
 	for (i = 2; i < argc + 2; i++)
-- 
GitLab


From 697579629f850d8f863147351e12e74c50114a8a Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 7 Nov 2023 10:40:20 -0800
Subject: [PATCH 0501/4076] perf test: Basic branch counter support

Add a basic test for the branch counter feature.

The test verifies that
- The new filter can be successfully applied on the supported platforms.
- The counter value can be outputted via the perf report -D

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tinghao Zhang <tinghao.zhang@intel.com>
Link: https://lore.kernel.org/r/20231107184020.1497571-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record.sh | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 29443b8e88765..c74412c68e65a 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -12,6 +12,9 @@ err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 testprog="perf test -w thloop"
 testsym="test_loop"
+cpu_pmu_dir="/sys/bus/event_source/devices/cpu*"
+br_cntr_file="/caps/branch_counter_nr"
+br_cntr_output="branch stack counters"
 
 cleanup() {
   rm -rf "${perfdata}"
@@ -155,10 +158,37 @@ test_workload() {
   echo "Basic target workload test [Success]"
 }
 
+test_branch_counter() {
+  echo "Basic branch counter test"
+  # Check if the branch counter feature is supported
+  for dir in $cpu_pmu_dir
+  do
+    if [ ! -e "$dir$br_cntr_file" ]
+    then
+      echo "branch counter feature not supported on all core PMUs ($dir) [Skipped]"
+      return
+    fi
+  done
+  if ! perf record -o "${perfdata}" -j any,counter ${testprog} 2> /dev/null
+  then
+    echo "Basic branch counter test [Failed record]"
+    err=1
+    return
+  fi
+  if ! perf report -i "${perfdata}" -D -q | grep -q "$br_cntr_output"
+  then
+    echo "Basic branch record test [Failed missing output]"
+    err=1
+    return
+  fi
+  echo "Basic branch counter test [Success]"
+}
+
 test_per_thread
 test_register_capture
 test_system_wide
 test_workload
+test_branch_counter
 
 cleanup
 exit $err
-- 
GitLab


From 2dbba30fd69b604802a9535b74bddb5bcca23793 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Fri, 1 Sep 2023 14:37:15 +0100
Subject: [PATCH 0502/4076] perf cs-etm: Bump minimum OpenCSD version to ensure
 a bugfix is present

Since commit d927ef5004ef ("perf cs-etm: Add exception level consistency
check"), the exception that was added to Perf will be triggered unless
the following bugfix from OpenCSD is present:

 - _Version 1.2.1_:
  - __Bugfix__:
    ETM4x / ETE - output of context elements to client can in some
    circumstances be delayed until after subsequent atoms have been
    processed leading to incorrect memory decode access via the client
    callbacks. Fixed to flush context elements immediately they are
    committed.

Rather than remove the assert and silently fail, just increase the
minimum version requirement to avoid hard to debug issues and
regressions.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: James Clark <james.clark@arm.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230901133716.677499-1-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/feature/test-libopencsd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c
index eb6303ff446ed..4cfcef9da3e43 100644
--- a/tools/build/feature/test-libopencsd.c
+++ b/tools/build/feature/test-libopencsd.c
@@ -4,9 +4,9 @@
 /*
  * Check OpenCSD library version is sufficient to provide required features
  */
-#define OCSD_MIN_VER ((1 << 16) | (1 << 8) | (1))
+#define OCSD_MIN_VER ((1 << 16) | (2 << 8) | (1))
 #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 1.1.1 is required"
+#error "OpenCSD >= 1.2.1 is required"
 #endif
 
 int main(void)
-- 
GitLab


From 26218331f49c858d52e60418cf3cef4c3fa6cf2e Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Sat, 14 Oct 2023 15:45:12 +0800
Subject: [PATCH 0503/4076] perf auxtrace: Add 'T' itrace option for timestamp
 trace

An AUX trace can contain timestamp, but in some situations, the hardware
trace module (e.g. Arm CoreSight) cannot decide the traced timestamp is
the same source with CPU's time, thus the decoder can not use the
timestamp trace for samples.

This patch introduces 'T' itrace option. If users know the platforms
they are working on have the same time counter with CPUs, users can
use this new option to tell a decoder for using timestamp trace as
kernel time.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20231014074513.1668000-2-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/itrace.txt | 1 +
 tools/perf/util/auxtrace.c          | 3 +++
 tools/perf/util/auxtrace.h          | 3 +++
 3 files changed, 7 insertions(+)

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index a97f95825b14e..19cc179be9a78 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -25,6 +25,7 @@
 		q	quicker (less detailed) decoding
 		A	approximate IPC
 		Z	prefer to ignore timestamps (so-called "timeless" decoding)
+		T	use the timestamp trace as kernel time
 
 	The default is all events i.e. the same as --itrace=iybxwpe,
 	except for perf script where it is --itrace=ce
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index a0368202a746a..f528c4364d235 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1638,6 +1638,9 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		case 'Z':
 			synth_opts->timeless_decoding = true;
 			break;
+		case 'T':
+			synth_opts->use_timestamp = true;
+			break;
 		case ' ':
 		case ',':
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 29eb82dff5749..55702215a82d3 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -99,6 +99,7 @@ enum itrace_period_type {
  * @remote_access: whether to synthesize remote access events
  * @mem: whether to synthesize memory events
  * @timeless_decoding: prefer "timeless" decoding i.e. ignore timestamps
+ * @use_timestamp: use the timestamp trace as kernel time
  * @vm_time_correlation: perform VM Time Correlation
  * @vm_tm_corr_dry_run: VM Time Correlation dry-run
  * @vm_tm_corr_args:  VM Time Correlation implementation-specific arguments
@@ -146,6 +147,7 @@ struct itrace_synth_opts {
 	bool			remote_access;
 	bool			mem;
 	bool			timeless_decoding;
+	bool			use_timestamp;
 	bool			vm_time_correlation;
 	bool			vm_tm_corr_dry_run;
 	char			*vm_tm_corr_args;
@@ -678,6 +680,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
 "				q:			quicker (less detailed) decoding\n" \
 "				A:			approximate IPC\n" \
 "				Z:			prefer to ignore timestamps (so-called \"timeless\" decoding)\n" \
+"				T:			use the timestamp trace as kernel time\n" \
 "				PERIOD[ns|us|ms|i|t]:   specify period to sample stream\n" \
 "				concatenate multiple options. Default is iybxwpe or cewp\n"
 
-- 
GitLab


From a4271827e609d30b7255aa7e4c453a8f3fe36a7b Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Sat, 14 Oct 2023 15:45:13 +0800
Subject: [PATCH 0504/4076] perf cs-etm: Enable itrace option 'T'

Prior to Armv8.4, the feature FEAT_TRF is not supported by Arm CPUs.
Consequently, the sysfs node 'ts_source' will not be set as 1 by the
CoreSight ETM driver.  On the other hand, the perf tool relies on the
'ts_source' node to determine whether the kernel timestamp is traced.
Since the 'ts_source' is not set for Arm CPUs prior to Armv8.4,
platforms in this case cannot utilize the traced timestamp as the kernel
time.

This patch enables the 'T' itrace option, which forcibly utilizes the
traced timestamp as the kernel time.  If users are aware that their
working platform's Arm CoreSight shares the same counter with the kernel
time, they can specify 'T' option to decode the traced timestamp as the
kernel time.

An usage example is:

  # perf record -e cs_etm// -- test_program
  # perf script --itrace=i10ibT
  # perf report --itrace=i10ibT

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20231014074513.1668000-3-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index a9873d14c6329..d65d7485886cd 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -3346,12 +3346,27 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 	etm->metadata = metadata;
 	etm->auxtrace_type = auxtrace_info->type;
 
-	/* Use virtual timestamps if all ETMs report ts_source = 1 */
-	etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu);
+	if (etm->synth_opts.use_timestamp)
+		/*
+		 * Prior to Armv8.4, Arm CPUs don't support FEAT_TRF feature,
+		 * therefore the decoder cannot know if the timestamp trace is
+		 * same with the kernel time.
+		 *
+		 * If a user has knowledge for the working platform and can
+		 * specify itrace option 'T' to tell decoder to forcely use the
+		 * traced timestamp as the kernel time.
+		 */
+		etm->has_virtual_ts = true;
+	else
+		/* Use virtual timestamps if all ETMs report ts_source = 1 */
+		etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu);
 
 	if (!etm->has_virtual_ts)
 		ui__warning("Virtual timestamps are not enabled, or not supported by the traced system.\n"
-			    "The time field of the samples will not be set accurately.\n\n");
+			    "The time field of the samples will not be set accurately.\n"
+			    "For Arm CPUs prior to Armv8.4 or without support FEAT_TRF,\n"
+			    "you can specify the itrace option 'T' for timestamp decoding\n"
+			    "if the Coresight timestamp on the platform is same with the kernel time.\n\n");
 
 	etm->auxtrace.process_event = cs_etm__process_event;
 	etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event;
-- 
GitLab


From a24d9d9dc096fc0d0bd85302c9a4fe4fe3b1107b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 22 Nov 2023 20:29:22 -0800
Subject: [PATCH 0505/4076] perf parse-events: Make legacy events lower
 priority than sysfs/JSON

The perf tool has previously made legacy events the priority so with
or without a PMU the legacy event would be opened:

  $ perf stat -e cpu-cycles,cpu/cpu-cycles/ true
  Using CPUID GenuineIntel-6-8D-1
  intel_pt default config: tsc,mtc,mtc_period=3,psb_period=3,pt,branch
  Attempting to add event pmu 'cpu' with 'cpu-cycles,' that may result in non-fatal errors
  After aliases, add event pmu 'cpu' with 'cpu-cycles,' that may result in non-fatal errors
  Control descriptor is not initialized
  ------------------------------------------------------------
  perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    size                             136
    config                           0 (PERF_COUNT_HW_CPU_CYCLES)
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  sys_perf_event_open: pid 833967  cpu -1  group_fd -1  flags 0x8 = 3
  ------------------------------------------------------------
  perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    size                             136
    config                           0 (PERF_COUNT_HW_CPU_CYCLES)
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  ...

Fixes to make hybrid/BIG.little PMUs behave correctly, ie as core PMUs
capable of opening legacy events on each, removing hard coded "cpu_core"
and "cpu_atom" Intel PMU names, etc. caused a behavioral difference on
Apple/ARM due to latent issues in the PMU driver reported in:
https://lore.kernel.org/lkml/08f1f185-e259-4014-9ca4-6411d5c1bc65@marcan.st/

As part of that report Mark Rutland <mark.rutland@arm.com> requested
that legacy events not be higher in priority when a PMU is specified
reversing what has until this change been perf's default behavior. With
this change the above becomes:

  $ perf stat -e cpu-cycles,cpu/cpu-cycles/ true
  Using CPUID GenuineIntel-6-8D-1
  Attempt to add: cpu/cpu-cycles=0/
  ..after resolving event: cpu/event=0x3c/
  Control descriptor is not initialized
  ------------------------------------------------------------
  perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    size                             136
    config                           0 (PERF_COUNT_HW_CPU_CYCLES)
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  sys_perf_event_open: pid 827628  cpu -1  group_fd -1  flags 0x8 = 3
  ------------------------------------------------------------
  perf_event_attr:
    type                             4 (PERF_TYPE_RAW)
    size                             136
    config                           0x3c
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  ...

So the second event has become a raw event as
/sys/devices/cpu/events/cpu-cycles exists.

A fix was necessary to config_term_pmu in parse-events.c as check_alias
expansion needs to happen after config_term_pmu, and config_term_pmu may
need calling a second time because of this.

config_term_pmu is updated to not use the legacy event when the PMU has
such a named event (either from JSON or sysfs).

The bulk of this change is updating all of the parse-events test
expectations so that if a sysfs/JSON event exists for a PMU the test
doesn't fail - a further sign, if it were needed, that the legacy event
priority was a known and tested behavior of the perf tool.

Reported-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Hector Martin <marcan@marcan.st>
Tested-by: Marc Zyngier <maz@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231123042922.834425-1-irogers@google.com
[ Initialize the 'alias_rewrote_terms' variable to false to address a clang warning ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/parse-events.c | 256 +++++++++++++++++++++++---------
 tools/perf/util/parse-events.c  |  52 +++++--
 tools/perf/util/pmu.c           |   8 +-
 tools/perf/util/pmu.h           |   3 +-
 4 files changed, 231 insertions(+), 88 deletions(-)

diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index e52f45c7c3d1a..fbdf710d5eea0 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -162,6 +162,22 @@ static int test__checkevent_numeric(struct evlist *evlist)
 	return TEST_OK;
 }
 
+
+static int assert_hw(struct perf_evsel *evsel, enum perf_hw_id id, const char *name)
+{
+	struct perf_pmu *pmu;
+
+	if (evsel->attr.type == PERF_TYPE_HARDWARE) {
+		TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, id));
+		return 0;
+	}
+	pmu = perf_pmus__find_by_type(evsel->attr.type);
+
+	TEST_ASSERT_VAL("unexpected PMU type", pmu);
+	TEST_ASSERT_VAL("PMU missing event", perf_pmu__have_event(pmu, name));
+	return 0;
+}
+
 static int test__checkevent_symbolic_name(struct evlist *evlist)
 {
 	struct perf_evsel *evsel;
@@ -169,10 +185,12 @@ static int test__checkevent_symbolic_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries);
 
 	perf_evlist__for_each_evsel(&evlist->core, evsel) {
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
-		TEST_ASSERT_VAL("wrong config",
-				test_perf_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		int ret = assert_hw(evsel, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+
+		if (ret)
+			return ret;
 	}
+
 	return TEST_OK;
 }
 
@@ -183,8 +201,10 @@ static int test__checkevent_symbolic_name_config(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries);
 
 	perf_evlist__for_each_evsel(&evlist->core, evsel) {
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
-		TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		int ret = assert_hw(evsel, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+		if (ret)
+			return ret;
 		/*
 		 * The period value gets configured within evlist__config,
 		 * while this test executes only parse events method.
@@ -861,10 +881,14 @@ static int test__group1(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* instructions:k */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -878,8 +902,10 @@ static int test__group1(struct evlist *evlist)
 
 		/* cycles:upp */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -907,6 +933,8 @@ static int test__group2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist));
 
 	evlist__for_each_entry(evlist, evsel) {
+		int ret;
+
 		if (evsel->core.attr.type == PERF_TYPE_SOFTWARE) {
 			/* faults + :ku modifier */
 			leader = evsel;
@@ -939,8 +967,10 @@ static int test__group2(struct evlist *evlist)
 			continue;
 		}
 		/* cycles:k */
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -957,6 +987,7 @@ static int test__group2(struct evlist *evlist)
 static int test__group3(struct evlist *evlist __maybe_unused)
 {
 	struct evsel *evsel, *group1_leader = NULL, *group2_leader = NULL;
+	int ret;
 
 	TEST_ASSERT_VAL("wrong number of entries",
 			evlist->core.nr_entries == (3 * perf_pmus__num_core_pmus() + 2));
@@ -1045,8 +1076,10 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 			continue;
 		}
 		/* instructions:u */
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1070,10 +1103,14 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 			num_core_entries() == evlist__nr_groups(evlist));
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles:u + p */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1089,8 +1126,10 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 
 		/* instructions:kp + p */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1108,6 +1147,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 static int test__group5(struct evlist *evlist __maybe_unused)
 {
 	struct evsel *evsel = NULL, *leader;
+	int ret;
 
 	TEST_ASSERT_VAL("wrong number of entries",
 			evlist->core.nr_entries == (5 * num_core_entries()));
@@ -1117,8 +1157,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	for (int i = 0; i < num_core_entries(); i++) {
 		/* cycles + G */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1133,8 +1175,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 
 		/* instructions + G */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1148,8 +1192,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	for (int i = 0; i < num_core_entries(); i++) {
 		/* cycles:G */
 		evsel = leader = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1164,8 +1210,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 
 		/* instructions:G */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1178,8 +1226,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	for (int i = 0; i < num_core_entries(); i++) {
 		/* cycles */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1201,10 +1251,14 @@ static int test__group_gh1(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles + :H group modifier */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1218,8 +1272,10 @@ static int test__group_gh1(struct evlist *evlist)
 
 		/* cache-misses:G + :H group modifier */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1242,10 +1298,14 @@ static int test__group_gh2(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles + :G group modifier */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1259,8 +1319,10 @@ static int test__group_gh2(struct evlist *evlist)
 
 		/* cache-misses:H + :G group modifier */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1283,10 +1345,14 @@ static int test__group_gh3(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles:G + :u group modifier */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1300,8 +1366,10 @@ static int test__group_gh3(struct evlist *evlist)
 
 		/* cache-misses:H + :u group modifier */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1324,10 +1392,14 @@ static int test__group_gh4(struct evlist *evlist)
 			evlist__nr_groups(evlist) == num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles:G + :uG group modifier */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1341,8 +1413,10 @@ static int test__group_gh4(struct evlist *evlist)
 
 		/* cache-misses:H + :uG group modifier */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1363,10 +1437,14 @@ static int test__leader_sample1(struct evlist *evlist)
 			evlist->core.nr_entries == (3 * num_core_entries()));
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles - sampling group leader */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1379,8 +1457,10 @@ static int test__leader_sample1(struct evlist *evlist)
 
 		/* cache-misses - not sampling */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1392,8 +1472,10 @@ static int test__leader_sample1(struct evlist *evlist)
 
 		/* branch-misses - not sampling */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
@@ -1415,10 +1497,14 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)
 			evlist->core.nr_entries == (2 * num_core_entries()));
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* instructions - sampling group leader */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1431,8 +1517,10 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)
 
 		/* branch-misses - not sampling */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 		TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -1472,10 +1560,14 @@ static int test__pinned_group(struct evlist *evlist)
 			evlist->core.nr_entries == (3 * num_core_entries()));
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles - group leader */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
 		TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
 		/* TODO: The group modifier is not copied to the split group leader. */
@@ -1484,13 +1576,18 @@ static int test__pinned_group(struct evlist *evlist)
 
 		/* cache-misses - can not be pinned, but will go on with the leader */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned);
 
 		/* branch-misses - ditto */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned);
 	}
 	return TEST_OK;
@@ -1517,10 +1614,14 @@ static int test__exclusive_group(struct evlist *evlist)
 			evlist->core.nr_entries == 3 * num_core_entries());
 
 	for (int i = 0; i < num_core_entries(); i++) {
+		int ret;
+
 		/* cycles - group leader */
 		evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
 		TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
 		/* TODO: The group modifier is not copied to the split group leader. */
@@ -1529,13 +1630,18 @@ static int test__exclusive_group(struct evlist *evlist)
 
 		/* cache-misses - can not be pinned, but will go on with the leader */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive);
 
 		/* branch-misses - ditto */
 		evsel = evsel__next(evsel);
-		TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES));
+		ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses");
+		if (ret)
+			return ret;
+
 		TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive);
 	}
 	return TEST_OK;
@@ -1677,9 +1783,11 @@ static int test__checkevent_raw_pmu(struct evlist *evlist)
 static int test__sym_event_slash(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
+	int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+	if (ret)
+		return ret;
 
-	TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE);
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	return TEST_OK;
 }
@@ -1687,9 +1795,11 @@ static int test__sym_event_slash(struct evlist *evlist)
 static int test__sym_event_dc(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
+	int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+	if (ret)
+		return ret;
 
-	TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE);
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
 	return TEST_OK;
 }
@@ -1697,9 +1807,11 @@ static int test__sym_event_dc(struct evlist *evlist)
 static int test__term_equal_term(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
+	int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+	if (ret)
+		return ret;
 
-	TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE);
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
 	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "name") == 0);
 	return TEST_OK;
 }
@@ -1707,9 +1819,11 @@ static int test__term_equal_term(struct evlist *evlist)
 static int test__term_equal_legacy(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
+	int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles");
+
+	if (ret)
+		return ret;
 
-	TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE);
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
 	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "l1d") == 0);
 	return TEST_OK;
 }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index aa2f5c6fc7fc2..66eabcea42427 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -976,7 +976,7 @@ static int config_term_pmu(struct perf_event_attr *attr,
 			   struct parse_events_error *err)
 {
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE) {
-		const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
+		struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 
 		if (!pmu) {
 			char *err_str;
@@ -986,15 +986,23 @@ static int config_term_pmu(struct perf_event_attr *attr,
 							   err_str, /*help=*/NULL);
 			return -EINVAL;
 		}
-		if (perf_pmu__supports_legacy_cache(pmu)) {
+		/*
+		 * Rewrite the PMU event to a legacy cache one unless the PMU
+		 * doesn't support legacy cache events or the event is present
+		 * within the PMU.
+		 */
+		if (perf_pmu__supports_legacy_cache(pmu) &&
+		    !perf_pmu__have_event(pmu, term->config)) {
 			attr->type = PERF_TYPE_HW_CACHE;
 			return parse_events__decode_legacy_cache(term->config, pmu->type,
 								 &attr->config);
-		} else
+		} else {
 			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
+			term->no_value = true;
+		}
 	}
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_HARDWARE) {
-		const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
+		struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 
 		if (!pmu) {
 			char *err_str;
@@ -1004,10 +1012,19 @@ static int config_term_pmu(struct perf_event_attr *attr,
 							   err_str, /*help=*/NULL);
 			return -EINVAL;
 		}
-		attr->type = PERF_TYPE_HARDWARE;
-		attr->config = term->val.num;
-		if (perf_pmus__supports_extended_type())
-			attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+		/*
+		 * If the PMU has a sysfs or json event prefer it over
+		 * legacy. ARM requires this.
+		 */
+		if (perf_pmu__have_event(pmu, term->config)) {
+			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
+			term->no_value = true;
+		} else {
+			attr->type = PERF_TYPE_HARDWARE;
+			attr->config = term->val.num;
+			if (perf_pmus__supports_extended_type())
+				attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+		}
 		return 0;
 	}
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER ||
@@ -1381,6 +1398,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 	YYLTYPE *loc = loc_;
 	LIST_HEAD(config_terms);
 	struct parse_events_terms parsed_terms;
+	bool alias_rewrote_terms = false;
 
 	pmu = parse_state->fake_pmu ?: perf_pmus__find(name);
 
@@ -1433,7 +1451,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return evsel ? 0 : -ENOMEM;
 	}
 
-	if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, &parsed_terms, &info, err)) {
+	/* Configure attr/terms with a known PMU, this will set hardcoded terms. */
+	if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
+		parse_events_terms__exit(&parsed_terms);
+		return -EINVAL;
+	}
+
+	/* Look for event names in the terms and rewrite into format based terms. */
+	if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, &parsed_terms,
+							    &info, &alias_rewrote_terms, err)) {
 		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
 	}
@@ -1447,11 +1473,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		strbuf_release(&sb);
 	}
 
-	/*
-	 * Configure hardcoded terms first, no need to check
-	 * return value when called with fail == 0 ;)
-	 */
-	if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
+	/* Configure attr/terms again if an alias was expanded. */
+	if (alias_rewrote_terms &&
+	    config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
 		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
 	}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d3c9aa4326bee..3c9609944a2f3 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1494,12 +1494,14 @@ static int check_info_data(struct perf_pmu *pmu,
  * defined for the alias
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,
-			  struct perf_pmu_info *info, struct parse_events_error *err)
+			  struct perf_pmu_info *info, bool *rewrote_terms,
+			  struct parse_events_error *err)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	*rewrote_terms = false;
 	info->per_pkg = false;
 
 	/*
@@ -1521,7 +1523,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 						NULL);
 			return ret;
 		}
-
+		*rewrote_terms = true;
 		ret = check_info_data(pmu, alias, info, err, term->err_term);
 		if (ret)
 			return ret;
@@ -1615,6 +1617,8 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
 
 bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 {
+	if (!name)
+		return false;
 	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
 		return true;
 	if (pmu->cpu_aliases_added || !pmu->events_table)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index d2895d415f08f..424c3fee09496 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -201,7 +201,8 @@ int perf_pmu__config_terms(const struct perf_pmu *pmu,
 __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
 int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,
-			  struct perf_pmu_info *info, struct parse_events_error *err);
+			  struct perf_pmu_info *info, bool *rewrote_terms,
+			  struct parse_events_error *err);
 int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb);
 
 int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load);
-- 
GitLab


From 4a18ab467820b75436ea9ddd42ee7cb10efa491c Mon Sep 17 00:00:00 2001
From: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Date: Fri, 24 Nov 2023 17:26:57 +0800
Subject: [PATCH 0506/4076] perf lock: Fix a memory leak on an error path

if a strdup-ed string is NULL,the allocated memory needs freeing.

Signed-off-by: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Acked-by: Ingo Molnar <mingo@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20231124092657.10392-1-zhaimingbing@cmss.chinamobile.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-lock.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index a3ff2f4edbaa5..230461280e452 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -2285,8 +2285,10 @@ setup_args:
 		else
 			ev_name = strdup(contention_tracepoints[j].name);
 
-		if (!ev_name)
+		if (!ev_name) {
+			free(rec_argv);
 			return -ENOMEM;
+		}
 
 		rec_argv[i++] = "-e";
 		rec_argv[i++] = ev_name;
-- 
GitLab


From 62df29a542f9ba8e884fcd470843b620d3f067fc Mon Sep 17 00:00:00 2001
From: Li zeming <zeming@nfschina.com>
Date: Mon, 13 Nov 2023 09:15:43 +0800
Subject: [PATCH 0507/4076] misc: ocxl: context: Remove unnecessary (void*)
 conversions

The ctx pointer does not need to cast the type.

Signed-off-by: Li zeming <zeming@nfschina.com>
Acked-by: Frederic Barrat <fbarrat@linux.ibm.com>
Acked-by: Andrew Donnellan <ajd@linux.ibm.com>
Link: https://lore.kernel.org/r/20231113011543.6940-1-zeming@nfschina.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/ocxl/context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index 7f83116ae11a6..cded7d1caf328 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -55,7 +55,7 @@ EXPORT_SYMBOL_GPL(ocxl_context_alloc);
  */
 static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
 {
-	struct ocxl_context *ctx = (struct ocxl_context *) data;
+	struct ocxl_context *ctx = data;
 
 	mutex_lock(&ctx->xsl_error_lock);
 	ctx->xsl_error.addr = addr;
-- 
GitLab


From 0e425d703c30cddea913e5cc73b2528fba628c90 Mon Sep 17 00:00:00 2001
From: Li zeming <zeming@nfschina.com>
Date: Mon, 13 Nov 2023 09:22:02 +0800
Subject: [PATCH 0508/4076] misc: ocxl: afu_irq: Remove unnecessary (void*)
 conversions

The irq pointer does not need to cast the type.

Signed-off-by: Li zeming <zeming@nfschina.com>
Acked-by: Frederic Barrat <fbarrat@linux.ibm.com>
Acked-by: Andrew Donnellan <ajd@linux.ibm.com>
Link: https://lore.kernel.org/r/20231113012202.7887-1-zeming@nfschina.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/ocxl/afu_irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c
index a06920b7e049a..36f7379b8e2de 100644
--- a/drivers/misc/ocxl/afu_irq.c
+++ b/drivers/misc/ocxl/afu_irq.c
@@ -57,7 +57,7 @@ EXPORT_SYMBOL_GPL(ocxl_irq_set_handler);
 
 static irqreturn_t afu_irq_handler(int virq, void *data)
 {
-	struct afu_irq *irq = (struct afu_irq *) data;
+	struct afu_irq *irq = data;
 
 	trace_ocxl_afu_irq_receive(virq);
 
-- 
GitLab


From 29eb0dc7bd1efe8f35e8d55b0308091ed2f70b86 Mon Sep 17 00:00:00 2001
From: Li zeming <zeming@nfschina.com>
Date: Mon, 13 Nov 2023 09:45:33 +0800
Subject: [PATCH 0509/4076] misc: ocxl: link: Remove unnecessary (void*)
 conversions

The link pointer does not need to cast the type.

Signed-off-by: Li zeming <zeming@nfschina.com>
Acked-by: Frederic Barrat <fbarrat@linux.ibm.com>
Acked-by: Andrew Donnellan <ajd@linux.ibm.com>
Link: https://lore.kernel.org/r/20231113014533.11064-1-zeming@nfschina.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/ocxl/link.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
index c06c699c0e7b1..03402203cacdb 100644
--- a/drivers/misc/ocxl/link.c
+++ b/drivers/misc/ocxl/link.c
@@ -188,7 +188,7 @@ ack:
 
 static irqreturn_t xsl_fault_handler(int irq, void *data)
 {
-	struct ocxl_link *link = (struct ocxl_link *) data;
+	struct ocxl_link *link = data;
 	struct spa *spa = link->spa;
 	u64 dsisr, dar, pe_handle;
 	struct pe_data *pe_data;
@@ -483,7 +483,7 @@ static void release_xsl(struct kref *ref)
 
 void ocxl_link_release(struct pci_dev *dev, void *link_handle)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 
 	mutex_lock(&links_list_lock);
 	kref_put(&link->ref, release_xsl);
@@ -540,7 +540,7 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
 		void (*xsl_err_cb)(void *data, u64 addr, u64 dsisr),
 		void *xsl_err_data)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 	struct spa *spa = link->spa;
 	struct ocxl_process_element *pe;
 	int pe_handle, rc = 0;
@@ -630,7 +630,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_add_pe);
 
 int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 	struct spa *spa = link->spa;
 	struct ocxl_process_element *pe;
 	int pe_handle, rc;
@@ -666,7 +666,7 @@ int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid)
 
 int ocxl_link_remove_pe(void *link_handle, int pasid)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 	struct spa *spa = link->spa;
 	struct ocxl_process_element *pe;
 	struct pe_data *pe_data;
@@ -752,7 +752,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_remove_pe);
 
 int ocxl_link_irq_alloc(void *link_handle, int *hw_irq)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 	int irq;
 
 	if (atomic_dec_if_positive(&link->irq_available) < 0)
@@ -771,7 +771,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_irq_alloc);
 
 void ocxl_link_free_irq(void *link_handle, int hw_irq)
 {
-	struct ocxl_link *link = (struct ocxl_link *) link_handle;
+	struct ocxl_link *link = link_handle;
 
 	xive_native_free_irq(hw_irq);
 	atomic_inc(&link->irq_available);
-- 
GitLab


From bc1183a63057839b18e955b6d68abbb20d37b0f1 Mon Sep 17 00:00:00 2001
From: Li kunyu <kunyu@nfschina.com>
Date: Mon, 13 Nov 2023 09:52:29 +0800
Subject: [PATCH 0510/4076] =?UTF-8?q?misc:=20ocxl:=20main:=20Remove=20unne?=
 =?UTF-8?q?cessary=20=E2=80=980=E2=80=99=20values=20from=20rc?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

rc is assigned first, so it does not need to initialize the assignment.

Signed-off-by: Li kunyu <kunyu@nfschina.com>
Acked-by: Andrew Donnellan <ajd@linux.ibm.com>
Link: https://lore.kernel.org/r/20231113015229.12074-1-kunyu@nfschina.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/ocxl/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/ocxl/main.c b/drivers/misc/ocxl/main.c
index ef73cf35dda2b..658974143c3cc 100644
--- a/drivers/misc/ocxl/main.c
+++ b/drivers/misc/ocxl/main.c
@@ -7,7 +7,7 @@
 
 static int __init init_ocxl(void)
 {
-	int rc = 0;
+	int rc;
 
 	if (!tlbie_capable)
 		return -EINVAL;
-- 
GitLab


From c2535e954f502c3d2c46094dce2894c0fbe9f3a1 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:51 -0800
Subject: [PATCH 0511/4076] Staging: rtl8192e: Rename variable pTxTs

Rename variable pTxTs to ts to fix checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-2-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 50 +++++++++++------------
 drivers/staging/rtl8192e/rtl819x_TSProc.c |  8 ++--
 drivers/staging/rtl8192e/rtllib_tx.c      | 18 ++++----
 3 files changed, 38 insertions(+), 38 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index b52b42ac0fc4f..497791a980ba6 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -23,10 +23,10 @@ static void deactivate_ba_entry(struct rtllib_device *ieee, struct ba_record *ba
 	del_timer_sync(&ba->timer);
 }
 
-static u8 tx_ts_delete_ba(struct rtllib_device *ieee, struct tx_ts_record *pTxTs)
+static u8 tx_ts_delete_ba(struct rtllib_device *ieee, struct tx_ts_record *ts)
 {
-	struct ba_record *admitted_ba = &pTxTs->TxAdmittedBARecord;
-	struct ba_record *pending_ba = &pTxTs->TxPendingBARecord;
+	struct ba_record *admitted_ba = &ts->TxAdmittedBARecord;
+	struct ba_record *pending_ba = &ts->TxPendingBARecord;
 	u8 send_del_ba = false;
 
 	if (pending_ba->b_valid) {
@@ -443,20 +443,20 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 
 		rx_ts_delete_ba(ieee, ts);
 	} else {
-		struct tx_ts_record *pTxTs;
+		struct tx_ts_record *ts;
 
-		if (!rtllib_get_ts(ieee, (struct ts_common_info **)&pTxTs, dst,
+		if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
 			   (u8)pDelBaParamSet->field.tid, TX_DIR, false)) {
 			netdev_warn(ieee->dev, "%s(): can't get TS for TXTS\n",
 				    __func__);
 			return -1;
 		}
 
-		pTxTs->using_ba = false;
-		pTxTs->add_ba_req_in_progress = false;
-		pTxTs->add_ba_req_delayed = false;
-		del_timer_sync(&pTxTs->TsAddBaTimer);
-		tx_ts_delete_ba(ieee, pTxTs);
+		ts->using_ba = false;
+		ts->add_ba_req_in_progress = false;
+		ts->add_ba_req_delayed = false;
+		del_timer_sync(&ts->TsAddBaTimer);
+		tx_ts_delete_ba(ieee, ts);
 	}
 	return 0;
 }
@@ -489,14 +489,14 @@ void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
 			   enum tr_select TxRxSelect)
 {
 	if (TxRxSelect == TX_DIR) {
-		struct tx_ts_record *pTxTs =
+		struct tx_ts_record *ts =
 			 (struct tx_ts_record *)pTsCommonInfo;
 
-		if (tx_ts_delete_ba(ieee, pTxTs))
+		if (tx_ts_delete_ba(ieee, ts))
 			rtllib_send_DELBA(ieee, pTsCommonInfo->addr,
-					  (pTxTs->TxAdmittedBARecord.b_valid) ?
-					 (&pTxTs->TxAdmittedBARecord) :
-					(&pTxTs->TxPendingBARecord),
+					  (ts->TxAdmittedBARecord.b_valid) ?
+					 (&ts->TxAdmittedBARecord) :
+					(&ts->TxPendingBARecord),
 					 TxRxSelect, DELBA_REASON_END_BA);
 	} else if (TxRxSelect == RX_DIR) {
 		struct rx_ts_record *ts =
@@ -510,23 +510,23 @@ void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
 
 void rtllib_ba_setup_timeout(struct timer_list *t)
 {
-	struct tx_ts_record *pTxTs = from_timer(pTxTs, t,
+	struct tx_ts_record *ts = from_timer(ts, t,
 					      TxPendingBARecord.timer);
 
-	pTxTs->add_ba_req_in_progress = false;
-	pTxTs->add_ba_req_delayed = true;
-	pTxTs->TxPendingBARecord.b_valid = false;
+	ts->add_ba_req_in_progress = false;
+	ts->add_ba_req_delayed = true;
+	ts->TxPendingBARecord.b_valid = false;
 }
 
 void rtllib_tx_ba_inact_timeout(struct timer_list *t)
 {
-	struct tx_ts_record *pTxTs = from_timer(pTxTs, t,
+	struct tx_ts_record *ts = from_timer(ts, t,
 					      TxAdmittedBARecord.timer);
-	struct rtllib_device *ieee = container_of(pTxTs, struct rtllib_device,
-				     TxTsRecord[pTxTs->num]);
-	tx_ts_delete_ba(ieee, pTxTs);
-	rtllib_send_DELBA(ieee, pTxTs->TsCommonInfo.addr,
-			  &pTxTs->TxAdmittedBARecord, TX_DIR,
+	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
+				     TxTsRecord[ts->num]);
+	tx_ts_delete_ba(ieee, ts);
+	rtllib_send_DELBA(ieee, ts->TsCommonInfo.addr,
+			  &ts->TxAdmittedBARecord, TX_DIR,
 			  DELBA_REASON_TIMEOUT);
 }
 
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 41c1e768348a5..01d077bf01557 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -82,12 +82,12 @@ static void RxPktPendingTimeout(struct timer_list *t)
 
 static void TsAddBaProcess(struct timer_list *t)
 {
-	struct tx_ts_record *pTxTs = from_timer(pTxTs, t, TsAddBaTimer);
-	u8 num = pTxTs->num;
-	struct rtllib_device *ieee = container_of(pTxTs, struct rtllib_device,
+	struct tx_ts_record *ts = from_timer(ts, t, TsAddBaTimer);
+	u8 num = ts->num;
+	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
 				     TxTsRecord[num]);
 
-	rtllib_ts_init_add_ba(ieee, pTxTs, BA_POLICY_IMMEDIATE, false);
+	rtllib_ts_init_add_ba(ieee, ts, BA_POLICY_IMMEDIATE, false);
 	netdev_dbg(ieee->dev, "%s(): ADDBA Req is started\n", __func__);
 }
 
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 1da098f5b84ca..2ef617a55995b 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -267,7 +267,7 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 				    struct cb_desc *tcb_desc)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
-	struct tx_ts_record *pTxTs = NULL;
+	struct tx_ts_record *ts = NULL;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 
 	if (rtllib_act_scanning(ieee, false))
@@ -289,25 +289,25 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 	if (!ieee->GetNmodeSupportBySecCfg(ieee->dev))
 		return;
 	if (ht_info->current_ampdu_enable) {
-		if (!rtllib_get_ts(ieee, (struct ts_common_info **)(&pTxTs), hdr->addr1,
+		if (!rtllib_get_ts(ieee, (struct ts_common_info **)(&ts), hdr->addr1,
 			   skb->priority, TX_DIR, true)) {
 			netdev_info(ieee->dev, "%s: can't get TS\n", __func__);
 			return;
 		}
-		if (!pTxTs->TxAdmittedBARecord.b_valid) {
+		if (!ts->TxAdmittedBARecord.b_valid) {
 			if (ieee->wpa_ie_len && (ieee->pairwise_key_type ==
 			    KEY_TYPE_NA)) {
 				;
 			} else if (tcb_desc->bdhcp == 1) {
 				;
-			} else if (!pTxTs->disable_add_ba) {
-				TsStartAddBaProcess(ieee, pTxTs);
+			} else if (!ts->disable_add_ba) {
+				TsStartAddBaProcess(ieee, ts);
 			}
 			goto FORCED_AGG_SETTING;
-		} else if (!pTxTs->using_ba) {
-			if (SN_LESS(pTxTs->TxAdmittedBARecord.ba_start_seq_ctrl.field.seq_num,
-				    (pTxTs->TxCurSeq + 1) % 4096))
-				pTxTs->using_ba = true;
+		} else if (!ts->using_ba) {
+			if (SN_LESS(ts->TxAdmittedBARecord.ba_start_seq_ctrl.field.seq_num,
+				    (ts->TxCurSeq + 1) % 4096))
+				ts->using_ba = true;
 			else
 				goto FORCED_AGG_SETTING;
 		}
-- 
GitLab


From 896578ae2c51233742baf3becc9e6753a6e9039a Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:52 -0800
Subject: [PATCH 0512/4076] Staging: rtl8192e: Rename variable BAReq

Rename variable BAReq to ba_req to fix checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-3-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 497791a980ba6..f6ba922dc82ec 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -68,7 +68,7 @@ static struct sk_buff *rtllib_ADDBA(struct rtllib_device *ieee, u8 *dst,
 				    u16 status_code, u8 type)
 {
 	struct sk_buff *skb = NULL;
-	struct ieee80211_hdr_3addr *BAReq = NULL;
+	struct ieee80211_hdr_3addr *ba_req = NULL;
 	u8 *tag = NULL;
 	u16 len = ieee->tx_headroom + 9;
 
@@ -87,13 +87,13 @@ static struct sk_buff *rtllib_ADDBA(struct rtllib_device *ieee, u8 *dst,
 
 	skb_reserve(skb, ieee->tx_headroom);
 
-	BAReq = skb_put(skb, sizeof(struct ieee80211_hdr_3addr));
+	ba_req = skb_put(skb, sizeof(struct ieee80211_hdr_3addr));
 
-	ether_addr_copy(BAReq->addr1, dst);
-	ether_addr_copy(BAReq->addr2, ieee->dev->dev_addr);
+	ether_addr_copy(ba_req->addr1, dst);
+	ether_addr_copy(ba_req->addr2, ieee->dev->dev_addr);
 
-	ether_addr_copy(BAReq->addr3, ieee->current_network.bssid);
-	BAReq->frame_control = cpu_to_le16(IEEE80211_STYPE_ACTION);
+	ether_addr_copy(ba_req->addr3, ieee->current_network.bssid);
+	ba_req->frame_control = cpu_to_le16(IEEE80211_STYPE_ACTION);
 
 	tag = skb_put(skb, 9);
 	*tag++ = ACT_CAT_BA;
-- 
GitLab


From 1628dd0f12c699fbd2e306650836c3e2ac63ecfe Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:53 -0800
Subject: [PATCH 0513/4076] Staging: rtl8192e: Rename variable Delba

Rename variable Delba to del_ba to fix checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-4-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index f6ba922dc82ec..06aaae68aa6ac 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -129,7 +129,7 @@ static struct sk_buff *rtllib_DELBA(struct rtllib_device *ieee, u8 *dst,
 {
 	union delba_param_set DelbaParamSet;
 	struct sk_buff *skb = NULL;
-	struct ieee80211_hdr_3addr *Delba = NULL;
+	struct ieee80211_hdr_3addr *del_ba = NULL;
 	u8 *tag = NULL;
 	u16 len = 6 + ieee->tx_headroom;
 
@@ -148,12 +148,12 @@ static struct sk_buff *rtllib_DELBA(struct rtllib_device *ieee, u8 *dst,
 
 	skb_reserve(skb, ieee->tx_headroom);
 
-	Delba = skb_put(skb, sizeof(struct ieee80211_hdr_3addr));
+	del_ba = skb_put(skb, sizeof(struct ieee80211_hdr_3addr));
 
-	ether_addr_copy(Delba->addr1, dst);
-	ether_addr_copy(Delba->addr2, ieee->dev->dev_addr);
-	ether_addr_copy(Delba->addr3, ieee->current_network.bssid);
-	Delba->frame_control = cpu_to_le16(IEEE80211_STYPE_ACTION);
+	ether_addr_copy(del_ba->addr1, dst);
+	ether_addr_copy(del_ba->addr2, ieee->dev->dev_addr);
+	ether_addr_copy(del_ba->addr3, ieee->current_network.bssid);
+	del_ba->frame_control = cpu_to_le16(IEEE80211_STYPE_ACTION);
 
 	tag = skb_put(skb, 6);
 
-- 
GitLab


From b35fe92f84c92b773592da73d95915960baafa75 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:54 -0800
Subject: [PATCH 0514/4076] Staging: rtl8192e: Rename variable TSpec

Rename variable TSpec to tspec to fix checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-5-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c |  2 +-
 drivers/staging/rtl8192e/rtl819x_TS.h     |  2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 14 +++++++-------
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 06aaae68aa6ac..bf8d426689908 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -474,7 +474,7 @@ void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
 	ba->dialog_token++;
 	ba->ba_param_set.field.amsdu_support = 0;
 	ba->ba_param_set.field.ba_policy = policy;
-	ba->ba_param_set.field.tid = ts->TsCommonInfo.TSpec.ucTSID;
+	ba->ba_param_set.field.tid = ts->TsCommonInfo.tspec.ucTSID;
 	ba->ba_param_set.field.buffer_size = 32;
 	ba->ba_timeout_value = 0;
 	ba->ba_start_seq_ctrl.field.seq_num = (ts->TxCurSeq + 3) % 4096;
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index 742f575ea6378..f2bd53268e3af 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -19,7 +19,7 @@ enum tr_select {
 struct ts_common_info {
 	struct list_head		List;
 	u8				addr[ETH_ALEN];
-	struct qos_tsinfo TSpec;
+	struct qos_tsinfo tspec;
 };
 
 struct tx_ts_record {
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 01d077bf01557..039f070aadd16 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -94,7 +94,7 @@ static void TsAddBaProcess(struct timer_list *t)
 static void ResetTsCommonInfo(struct ts_common_info *pTsCommonInfo)
 {
 	eth_zero_addr(pTsCommonInfo->addr);
-	memset(&pTsCommonInfo->TSpec, 0, sizeof(struct qos_tsinfo));
+	memset(&pTsCommonInfo->tspec, 0, sizeof(struct qos_tsinfo));
 }
 
 static void ResetTxTsEntry(struct tx_ts_record *ts)
@@ -198,8 +198,8 @@ static struct ts_common_info *SearchAdmitTRStream(struct rtllib_device *ieee,
 			continue;
 		list_for_each_entry(pRet, psearch_list, List) {
 			if (memcmp(pRet->addr, addr, 6) == 0 &&
-			    pRet->TSpec.ucTSID == TID &&
-			    pRet->TSpec.ucDirection == dir)
+			    pRet->tspec.ucTSID == TID &&
+			    pRet->tspec.ucDirection == dir)
 				break;
 		}
 		if (&pRet->List  != psearch_list)
@@ -220,7 +220,7 @@ static void MakeTSEntry(struct ts_common_info *pTsCommonInfo, u8 *addr,
 	memcpy(pTsCommonInfo->addr, addr, 6);
 
 	if (pTSPEC)
-		memcpy((u8 *)(&(pTsCommonInfo->TSpec)), (u8 *)pTSPEC,
+		memcpy((u8 *)(&(pTsCommonInfo->tspec)), (u8 *)pTSPEC,
 			sizeof(struct qos_tsinfo));
 }
 
@@ -228,8 +228,8 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 	   u8 *addr, u8 TID, enum tr_select TxRxSelect, bool bAddNewTs)
 {
 	u8	UP = 0;
-	struct qos_tsinfo TSpec;
-	struct qos_tsinfo *ts_info = &TSpec;
+	struct qos_tsinfo tspec;
+	struct qos_tsinfo *ts_info = &tspec;
 	struct list_head *pUnusedList;
 	struct list_head *pAddmitList;
 	enum direction_value Dir;
@@ -308,7 +308,7 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 		ts_info->ucTSID = UP;
 		ts_info->ucDirection = Dir;
 
-		MakeTSEntry(*ppTS, addr, &TSpec);
+		MakeTSEntry(*ppTS, addr, &tspec);
 		list_add_tail(&((*ppTS)->List), pAddmitList);
 
 		return true;
-- 
GitLab


From 56c5fa92de764af083ca88d9ff4e9c466b466f09 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:55 -0800
Subject: [PATCH 0515/4076] Staging: rtl8192e: Rename variable
 TxAdmittedBARecord

Rename variable TxAdmittedBARecord to tx_admitted_ba_record to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-6-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 12 ++++++------
 drivers/staging/rtl8192e/rtl819x_TS.h     |  2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c |  4 ++--
 drivers/staging/rtl8192e/rtllib_tx.c      |  4 ++--
 4 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index bf8d426689908..db529559592b4 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -25,7 +25,7 @@ static void deactivate_ba_entry(struct rtllib_device *ieee, struct ba_record *ba
 
 static u8 tx_ts_delete_ba(struct rtllib_device *ieee, struct tx_ts_record *ts)
 {
-	struct ba_record *admitted_ba = &ts->TxAdmittedBARecord;
+	struct ba_record *admitted_ba = &ts->tx_admitted_ba_record;
 	struct ba_record *pending_ba = &ts->TxPendingBARecord;
 	u8 send_del_ba = false;
 
@@ -346,7 +346,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 
 	ts->add_ba_req_in_progress = false;
 	pending_ba = &ts->TxPendingBARecord;
-	pAdmittedBA = &ts->TxAdmittedBARecord;
+	pAdmittedBA = &ts->tx_admitted_ba_record;
 
 	if (pAdmittedBA->b_valid) {
 		netdev_dbg(ieee->dev, "%s(): ADDBA response already admitted\n",
@@ -494,8 +494,8 @@ void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
 
 		if (tx_ts_delete_ba(ieee, ts))
 			rtllib_send_DELBA(ieee, pTsCommonInfo->addr,
-					  (ts->TxAdmittedBARecord.b_valid) ?
-					 (&ts->TxAdmittedBARecord) :
+					  (ts->tx_admitted_ba_record.b_valid) ?
+					 (&ts->tx_admitted_ba_record) :
 					(&ts->TxPendingBARecord),
 					 TxRxSelect, DELBA_REASON_END_BA);
 	} else if (TxRxSelect == RX_DIR) {
@@ -521,12 +521,12 @@ void rtllib_ba_setup_timeout(struct timer_list *t)
 void rtllib_tx_ba_inact_timeout(struct timer_list *t)
 {
 	struct tx_ts_record *ts = from_timer(ts, t,
-					      TxAdmittedBARecord.timer);
+					      tx_admitted_ba_record.timer);
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
 				     TxTsRecord[ts->num]);
 	tx_ts_delete_ba(ieee, ts);
 	rtllib_send_DELBA(ieee, ts->TsCommonInfo.addr,
-			  &ts->TxAdmittedBARecord, TX_DIR,
+			  &ts->tx_admitted_ba_record, TX_DIR,
 			  DELBA_REASON_TIMEOUT);
 }
 
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index f2bd53268e3af..40b0ed4fefaff 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -26,7 +26,7 @@ struct tx_ts_record {
 	struct ts_common_info TsCommonInfo;
 	u16				TxCurSeq;
 	struct ba_record TxPendingBARecord;
-	struct ba_record TxAdmittedBARecord;
+	struct ba_record tx_admitted_ba_record;
 	u8				add_ba_req_in_progress;
 	u8				add_ba_req_delayed;
 	u8				using_ba;
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 039f070aadd16..0e59a3155c4a5 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -105,7 +105,7 @@ static void ResetTxTsEntry(struct tx_ts_record *ts)
 	ts->add_ba_req_delayed = false;
 	ts->using_ba = false;
 	ts->disable_add_ba = false;
-	rtllib_reset_ba_entry(&ts->TxAdmittedBARecord);
+	rtllib_reset_ba_entry(&ts->tx_admitted_ba_record);
 	rtllib_reset_ba_entry(&ts->TxPendingBARecord);
 }
 
@@ -134,7 +134,7 @@ void rtllib_ts_init(struct rtllib_device *ieee)
 
 		timer_setup(&pTxTS->TxPendingBARecord.timer, rtllib_ba_setup_timeout,
 			    0);
-		timer_setup(&pTxTS->TxAdmittedBARecord.timer,
+		timer_setup(&pTxTS->tx_admitted_ba_record.timer,
 			    rtllib_tx_ba_inact_timeout, 0);
 
 		ResetTxTsEntry(pTxTS);
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 2ef617a55995b..51a8286abd186 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -294,7 +294,7 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 			netdev_info(ieee->dev, "%s: can't get TS\n", __func__);
 			return;
 		}
-		if (!ts->TxAdmittedBARecord.b_valid) {
+		if (!ts->tx_admitted_ba_record.b_valid) {
 			if (ieee->wpa_ie_len && (ieee->pairwise_key_type ==
 			    KEY_TYPE_NA)) {
 				;
@@ -305,7 +305,7 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 			}
 			goto FORCED_AGG_SETTING;
 		} else if (!ts->using_ba) {
-			if (SN_LESS(ts->TxAdmittedBARecord.ba_start_seq_ctrl.field.seq_num,
+			if (SN_LESS(ts->tx_admitted_ba_record.ba_start_seq_ctrl.field.seq_num,
 				    (ts->TxCurSeq + 1) % 4096))
 				ts->using_ba = true;
 			else
-- 
GitLab


From 11fe57bef57ad57837b06d2d2404653d73a30a3c Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:56 -0800
Subject: [PATCH 0516/4076] Staging: rtl8192e: Rename variable
 TxPendingBARecord

Rename variable TxPendingBARecord to tx_pending_ba_record to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-7-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 12 ++++++------
 drivers/staging/rtl8192e/rtl819x_TS.h     |  2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index db529559592b4..51deab720e762 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -26,7 +26,7 @@ static void deactivate_ba_entry(struct rtllib_device *ieee, struct ba_record *ba
 static u8 tx_ts_delete_ba(struct rtllib_device *ieee, struct tx_ts_record *ts)
 {
 	struct ba_record *admitted_ba = &ts->tx_admitted_ba_record;
-	struct ba_record *pending_ba = &ts->TxPendingBARecord;
+	struct ba_record *pending_ba = &ts->tx_pending_ba_record;
 	u8 send_del_ba = false;
 
 	if (pending_ba->b_valid) {
@@ -345,7 +345,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	}
 
 	ts->add_ba_req_in_progress = false;
-	pending_ba = &ts->TxPendingBARecord;
+	pending_ba = &ts->tx_pending_ba_record;
 	pAdmittedBA = &ts->tx_admitted_ba_record;
 
 	if (pAdmittedBA->b_valid) {
@@ -464,7 +464,7 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
 			   u8 policy, u8	overwrite_pending)
 {
-	struct ba_record *ba = &ts->TxPendingBARecord;
+	struct ba_record *ba = &ts->tx_pending_ba_record;
 
 	if (ba->b_valid && !overwrite_pending)
 		return;
@@ -496,7 +496,7 @@ void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
 			rtllib_send_DELBA(ieee, pTsCommonInfo->addr,
 					  (ts->tx_admitted_ba_record.b_valid) ?
 					 (&ts->tx_admitted_ba_record) :
-					(&ts->TxPendingBARecord),
+					(&ts->tx_pending_ba_record),
 					 TxRxSelect, DELBA_REASON_END_BA);
 	} else if (TxRxSelect == RX_DIR) {
 		struct rx_ts_record *ts =
@@ -511,11 +511,11 @@ void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
 void rtllib_ba_setup_timeout(struct timer_list *t)
 {
 	struct tx_ts_record *ts = from_timer(ts, t,
-					      TxPendingBARecord.timer);
+					      tx_pending_ba_record.timer);
 
 	ts->add_ba_req_in_progress = false;
 	ts->add_ba_req_delayed = true;
-	ts->TxPendingBARecord.b_valid = false;
+	ts->tx_pending_ba_record.b_valid = false;
 }
 
 void rtllib_tx_ba_inact_timeout(struct timer_list *t)
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index 40b0ed4fefaff..fdd5f1a2e835c 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -25,7 +25,7 @@ struct ts_common_info {
 struct tx_ts_record {
 	struct ts_common_info TsCommonInfo;
 	u16				TxCurSeq;
-	struct ba_record TxPendingBARecord;
+	struct ba_record tx_pending_ba_record;
 	struct ba_record tx_admitted_ba_record;
 	u8				add_ba_req_in_progress;
 	u8				add_ba_req_delayed;
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 0e59a3155c4a5..ed14e8e1ed936 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -106,7 +106,7 @@ static void ResetTxTsEntry(struct tx_ts_record *ts)
 	ts->using_ba = false;
 	ts->disable_add_ba = false;
 	rtllib_reset_ba_entry(&ts->tx_admitted_ba_record);
-	rtllib_reset_ba_entry(&ts->TxPendingBARecord);
+	rtllib_reset_ba_entry(&ts->tx_pending_ba_record);
 }
 
 static void ResetRxTsEntry(struct rx_ts_record *ts)
@@ -132,7 +132,7 @@ void rtllib_ts_init(struct rtllib_device *ieee)
 		pTxTS->num = count;
 		timer_setup(&pTxTS->TsAddBaTimer, TsAddBaProcess, 0);
 
-		timer_setup(&pTxTS->TxPendingBARecord.timer, rtllib_ba_setup_timeout,
+		timer_setup(&pTxTS->tx_pending_ba_record.timer, rtllib_ba_setup_timeout,
 			    0);
 		timer_setup(&pTxTS->tx_admitted_ba_record.timer,
 			    rtllib_tx_ba_inact_timeout, 0);
-- 
GitLab


From c831d3f629fe98adf6c25974851208e123033fed Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:57 -0800
Subject: [PATCH 0517/4076] Staging: rtl8192e: Rename variable pDialogToken

Rename variable pDialogToken to dialog_token to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-8-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 51deab720e762..78da79ebd7758 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -215,7 +215,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 {
 	struct ieee80211_hdr_3addr *req = NULL;
 	u16 rc = 0;
-	u8 *dst = NULL, *pDialogToken = NULL, *tag = NULL;
+	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
 	struct ba_record *ba = NULL;
 	union ba_param_set *pBaParamSet = NULL;
 	u16 *pBaTimeoutVal = NULL;
@@ -238,7 +238,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	tag = (u8 *)req;
 	dst = (u8 *)(&req->addr2[0]);
 	tag += sizeof(struct ieee80211_hdr_3addr);
-	pDialogToken = tag + 2;
+	dialog_token = tag + 2;
 	pBaParamSet = (union ba_param_set *)(tag + 3);
 	pBaTimeoutVal = (u16 *)(tag + 5);
 	pBaStartSeqCtrl = (union sequence_control *)(req + 7);
@@ -271,7 +271,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	rtllib_FlushRxTsPendingPkts(ieee, ts);
 
 	deactivate_ba_entry(ieee, ba);
-	ba->dialog_token = *pDialogToken;
+	ba->dialog_token = *dialog_token;
 	ba->ba_param_set = *pBaParamSet;
 	ba->ba_timeout_value = *pBaTimeoutVal;
 	ba->ba_start_seq_ctrl = *pBaStartSeqCtrl;
@@ -293,7 +293,7 @@ OnADDBAReq_Fail:
 
 		BA.ba_param_set = *pBaParamSet;
 		BA.ba_timeout_value = *pBaTimeoutVal;
-		BA.dialog_token = *pDialogToken;
+		BA.dialog_token = *dialog_token;
 		BA.ba_param_set.field.ba_policy = BA_POLICY_IMMEDIATE;
 		rtllib_send_ADDBARsp(ieee, dst, &BA, rc);
 		return 0;
@@ -305,7 +305,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	struct ieee80211_hdr_3addr *rsp = NULL;
 	struct ba_record *pending_ba, *pAdmittedBA;
 	struct tx_ts_record *ts = NULL;
-	u8 *dst = NULL, *pDialogToken = NULL, *tag = NULL;
+	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
 	u16 *status_code = NULL, *pBaTimeoutVal = NULL;
 	union ba_param_set *pBaParamSet = NULL;
 	u16			reason_code;
@@ -320,7 +320,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	tag = (u8 *)rsp;
 	dst = (u8 *)(&rsp->addr2[0]);
 	tag += sizeof(struct ieee80211_hdr_3addr);
-	pDialogToken = tag + 2;
+	dialog_token = tag + 2;
 	status_code = (u16 *)(tag + 3);
 	pBaParamSet = (union ba_param_set *)(tag + 5);
 	pBaTimeoutVal = (u16 *)(tag + 7);
@@ -353,7 +353,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 			   __func__);
 		return -1;
 	} else if (!pending_ba->b_valid ||
-		   (*pDialogToken != pending_ba->dialog_token)) {
+		   (*dialog_token != pending_ba->dialog_token)) {
 		netdev_warn(ieee->dev,
 			    "%s(): ADDBA Rsp. BA invalid, DELBA!\n",
 			    __func__);
@@ -374,7 +374,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 			goto OnADDBARsp_Reject;
 		}
 
-		pAdmittedBA->dialog_token = *pDialogToken;
+		pAdmittedBA->dialog_token = *dialog_token;
 		pAdmittedBA->ba_timeout_value = *pBaTimeoutVal;
 		pAdmittedBA->ba_start_seq_ctrl = pending_ba->ba_start_seq_ctrl;
 		pAdmittedBA->ba_param_set = *pBaParamSet;
-- 
GitLab


From 5732a2aa5f4bbd7c898c0bc18bdc73696991feff Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:58 -0800
Subject: [PATCH 0518/4076] Staging: rtl8192e: Rename variable pTsCommonInfo

Rename variable pTsCommonInfo to ts_common_info to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-9-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 10 +++++-----
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 14 +++++++-------
 drivers/staging/rtl8192e/rtllib.h         |  2 +-
 3 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 78da79ebd7758..d11cbe3bbb316 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -485,24 +485,24 @@ void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
 }
 
 void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
-			   struct ts_common_info *pTsCommonInfo,
+			   struct ts_common_info *ts_common_info,
 			   enum tr_select TxRxSelect)
 {
 	if (TxRxSelect == TX_DIR) {
 		struct tx_ts_record *ts =
-			 (struct tx_ts_record *)pTsCommonInfo;
+			 (struct tx_ts_record *)ts_common_info;
 
 		if (tx_ts_delete_ba(ieee, ts))
-			rtllib_send_DELBA(ieee, pTsCommonInfo->addr,
+			rtllib_send_DELBA(ieee, ts_common_info->addr,
 					  (ts->tx_admitted_ba_record.b_valid) ?
 					 (&ts->tx_admitted_ba_record) :
 					(&ts->tx_pending_ba_record),
 					 TxRxSelect, DELBA_REASON_END_BA);
 	} else if (TxRxSelect == RX_DIR) {
 		struct rx_ts_record *ts =
-				 (struct rx_ts_record *)pTsCommonInfo;
+				 (struct rx_ts_record *)ts_common_info;
 		if (rx_ts_delete_ba(ieee, ts))
-			rtllib_send_DELBA(ieee, pTsCommonInfo->addr,
+			rtllib_send_DELBA(ieee, ts_common_info->addr,
 					  &ts->rx_admitted_ba_record,
 					  TxRxSelect, DELBA_REASON_END_BA);
 	}
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index ed14e8e1ed936..2e6b705437d9f 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -91,10 +91,10 @@ static void TsAddBaProcess(struct timer_list *t)
 	netdev_dbg(ieee->dev, "%s(): ADDBA Req is started\n", __func__);
 }
 
-static void ResetTsCommonInfo(struct ts_common_info *pTsCommonInfo)
+static void ResetTsCommonInfo(struct ts_common_info *ts_common_info)
 {
-	eth_zero_addr(pTsCommonInfo->addr);
-	memset(&pTsCommonInfo->tspec, 0, sizeof(struct qos_tsinfo));
+	eth_zero_addr(ts_common_info->addr);
+	memset(&ts_common_info->tspec, 0, sizeof(struct qos_tsinfo));
 }
 
 static void ResetTxTsEntry(struct tx_ts_record *ts)
@@ -211,16 +211,16 @@ static struct ts_common_info *SearchAdmitTRStream(struct rtllib_device *ieee,
 	return NULL;
 }
 
-static void MakeTSEntry(struct ts_common_info *pTsCommonInfo, u8 *addr,
+static void MakeTSEntry(struct ts_common_info *ts_common_info, u8 *addr,
 			struct qos_tsinfo *pTSPEC)
 {
-	if (!pTsCommonInfo)
+	if (!ts_common_info)
 		return;
 
-	memcpy(pTsCommonInfo->addr, addr, 6);
+	memcpy(ts_common_info->addr, addr, 6);
 
 	if (pTSPEC)
-		memcpy((u8 *)(&(pTsCommonInfo->tspec)), (u8 *)pTSPEC,
+		memcpy((u8 *)(&(ts_common_info->tspec)), (u8 *)pTSPEC,
 			sizeof(struct qos_tsinfo));
 }
 
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 47da9b1a86820..0a8c44e497f5c 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1782,7 +1782,7 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb);
 void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
 			   u8 policy, u8 overwrite_pending);
 void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
-			   struct ts_common_info *pTsCommonInfo,
+			   struct ts_common_info *ts_common_info,
 			   enum tr_select TxRxSelect);
 void rtllib_ba_setup_timeout(struct timer_list *t);
 void rtllib_tx_ba_inact_timeout(struct timer_list *t);
-- 
GitLab


From 27236dcfed95d9aed6b1f491ccc4cb85a7656c6b Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:42:59 -0800
Subject: [PATCH 0519/4076] Staging: rtl8192e: Rename variable TxCurSeq

Rename variable TxCurSeq to tx_cur_seq to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-10-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 2 +-
 drivers/staging/rtl8192e/rtl819x_TS.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib_tx.c      | 6 +++---
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index d11cbe3bbb316..328947fc058c1 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -477,7 +477,7 @@ void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
 	ba->ba_param_set.field.tid = ts->TsCommonInfo.tspec.ucTSID;
 	ba->ba_param_set.field.buffer_size = 32;
 	ba->ba_timeout_value = 0;
-	ba->ba_start_seq_ctrl.field.seq_num = (ts->TxCurSeq + 3) % 4096;
+	ba->ba_start_seq_ctrl.field.seq_num = (ts->tx_cur_seq + 3) % 4096;
 
 	activate_ba_entry(ba, BA_SETUP_TIMEOUT);
 
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index fdd5f1a2e835c..4ab712634b4b0 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -24,7 +24,7 @@ struct ts_common_info {
 
 struct tx_ts_record {
 	struct ts_common_info TsCommonInfo;
-	u16				TxCurSeq;
+	u16				tx_cur_seq;
 	struct ba_record tx_pending_ba_record;
 	struct ba_record tx_admitted_ba_record;
 	u8				add_ba_req_in_progress;
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 2e6b705437d9f..e06e563ae7186 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -100,7 +100,7 @@ static void ResetTsCommonInfo(struct ts_common_info *ts_common_info)
 static void ResetTxTsEntry(struct tx_ts_record *ts)
 {
 	ResetTsCommonInfo(&ts->TsCommonInfo);
-	ts->TxCurSeq = 0;
+	ts->tx_cur_seq = 0;
 	ts->add_ba_req_in_progress = false;
 	ts->add_ba_req_delayed = false;
 	ts->using_ba = false;
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 51a8286abd186..92e5be85148ee 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -306,7 +306,7 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 			goto FORCED_AGG_SETTING;
 		} else if (!ts->using_ba) {
 			if (SN_LESS(ts->tx_admitted_ba_record.ba_start_seq_ctrl.field.seq_num,
-				    (ts->TxCurSeq + 1) % 4096))
+				    (ts->tx_cur_seq + 1) % 4096))
 				ts->using_ba = true;
 			else
 				goto FORCED_AGG_SETTING;
@@ -500,8 +500,8 @@ static u16 rtllib_query_seqnum(struct rtllib_device *ieee, struct sk_buff *skb,
 		if (!rtllib_get_ts(ieee, (struct ts_common_info **)(&ts), dst,
 			   skb->priority, TX_DIR, true))
 			return 0;
-		seqnum = ts->TxCurSeq;
-		ts->TxCurSeq = (ts->TxCurSeq + 1) % 4096;
+		seqnum = ts->tx_cur_seq;
+		ts->tx_cur_seq = (ts->tx_cur_seq + 1) % 4096;
 		return seqnum;
 	}
 	return 0;
-- 
GitLab


From 536b207c45479e92269e1a112e2bd4125d12be91 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:43:00 -0800
Subject: [PATCH 0520/4076] Staging: rtl8192e: Rename variable TsAddBaTimer

Rename variable TsAddBaTimer to ts_add_ba_timer to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-11-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c |  2 +-
 drivers/staging/rtl8192e/rtl819x_TS.h     |  2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 10 +++++-----
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 328947fc058c1..2053feb51f619 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -455,7 +455,7 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 		ts->using_ba = false;
 		ts->add_ba_req_in_progress = false;
 		ts->add_ba_req_delayed = false;
-		del_timer_sync(&ts->TsAddBaTimer);
+		del_timer_sync(&ts->ts_add_ba_timer);
 		tx_ts_delete_ba(ieee, ts);
 	}
 	return 0;
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index 4ab712634b4b0..8e22c717fb274 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -31,7 +31,7 @@ struct tx_ts_record {
 	u8				add_ba_req_delayed;
 	u8				using_ba;
 	u8				disable_add_ba;
-	struct timer_list		TsAddBaTimer;
+	struct timer_list		ts_add_ba_timer;
 	u8				num;
 };
 
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index e06e563ae7186..f96538f3e4eee 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -82,7 +82,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 
 static void TsAddBaProcess(struct timer_list *t)
 {
-	struct tx_ts_record *ts = from_timer(ts, t, TsAddBaTimer);
+	struct tx_ts_record *ts = from_timer(ts, t, ts_add_ba_timer);
 	u8 num = ts->num;
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
 				     TxTsRecord[num]);
@@ -130,7 +130,7 @@ void rtllib_ts_init(struct rtllib_device *ieee)
 
 	for (count = 0; count < TOTAL_TS_NUM; count++) {
 		pTxTS->num = count;
-		timer_setup(&pTxTS->TsAddBaTimer, TsAddBaProcess, 0);
+		timer_setup(&pTxTS->ts_add_ba_timer, TsAddBaProcess, 0);
 
 		timer_setup(&pTxTS->tx_pending_ba_record.timer, rtllib_ba_setup_timeout,
 			    0);
@@ -356,7 +356,7 @@ static void RemoveTsEntry(struct rtllib_device *ieee,
 	} else {
 		struct tx_ts_record *pTxTS = (struct tx_ts_record *)pTs;
 
-		del_timer_sync(&pTxTS->TsAddBaTimer);
+		del_timer_sync(&pTxTS->ts_add_ba_timer);
 	}
 }
 
@@ -438,11 +438,11 @@ void TsStartAddBaProcess(struct rtllib_device *ieee, struct tx_ts_record *pTxTS)
 
 		if (pTxTS->add_ba_req_delayed) {
 			netdev_dbg(ieee->dev, "Start ADDBA after 60 sec!!\n");
-			mod_timer(&pTxTS->TsAddBaTimer, jiffies +
+			mod_timer(&pTxTS->ts_add_ba_timer, jiffies +
 				  msecs_to_jiffies(TS_ADDBA_DELAY));
 		} else {
 			netdev_dbg(ieee->dev, "Immediately Start ADDBA\n");
-			mod_timer(&pTxTS->TsAddBaTimer, jiffies + 10);
+			mod_timer(&pTxTS->ts_add_ba_timer, jiffies + 10);
 		}
 	} else {
 		netdev_dbg(ieee->dev, "BA timer is already added\n");
-- 
GitLab


From 30b4c01ccc95eff657f4859d7c29b37e848e18c6 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:43:01 -0800
Subject: [PATCH 0521/4076] Staging: rtl8192e: Rename variable DelbaParamSet

Rename variable DelbaParamSet to del_ba_param_set to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-12-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 2053feb51f619..bd037069d4f3d 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -127,7 +127,7 @@ static struct sk_buff *rtllib_DELBA(struct rtllib_device *ieee, u8 *dst,
 				    struct ba_record *ba,
 				    enum tr_select TxRxSelect, u16 reason_code)
 {
-	union delba_param_set DelbaParamSet;
+	union delba_param_set del_ba_param_set;
 	struct sk_buff *skb = NULL;
 	struct ieee80211_hdr_3addr *del_ba = NULL;
 	u8 *tag = NULL;
@@ -137,10 +137,10 @@ static struct sk_buff *rtllib_DELBA(struct rtllib_device *ieee, u8 *dst,
 		netdev_dbg(ieee->dev, "%s(): reason_code(%d) sentd to: %pM\n",
 			   __func__, reason_code, dst);
 
-	memset(&DelbaParamSet, 0, 2);
+	memset(&del_ba_param_set, 0, 2);
 
-	DelbaParamSet.field.initiator = (TxRxSelect == TX_DIR) ? 1 : 0;
-	DelbaParamSet.field.tid	= ba->ba_param_set.field.tid;
+	del_ba_param_set.field.initiator = (TxRxSelect == TX_DIR) ? 1 : 0;
+	del_ba_param_set.field.tid	= ba->ba_param_set.field.tid;
 
 	skb = dev_alloc_skb(len + sizeof(struct ieee80211_hdr_3addr));
 	if (!skb)
@@ -160,7 +160,7 @@ static struct sk_buff *rtllib_DELBA(struct rtllib_device *ieee, u8 *dst,
 	*tag++ = ACT_CAT_BA;
 	*tag++ = ACT_DELBA;
 
-	put_unaligned_le16(DelbaParamSet.short_data, tag);
+	put_unaligned_le16(del_ba_param_set.short_data, tag);
 	tag += 2;
 
 	put_unaligned_le16(reason_code, tag);
-- 
GitLab


From 60b280a3470e1bf6bddd0756e27a7a783c14e5dc Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:43:02 -0800
Subject: [PATCH 0522/4076] Staging: rtl8192e: Rename variable pBaParamSet

Rename variable pBaParamSet to ba_param_set to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-13-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 24 +++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index bd037069d4f3d..7074a01ad2e85 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -217,7 +217,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	u16 rc = 0;
 	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
 	struct ba_record *ba = NULL;
-	union ba_param_set *pBaParamSet = NULL;
+	union ba_param_set *ba_param_set = NULL;
 	u16 *pBaTimeoutVal = NULL;
 	union sequence_control *pBaStartSeqCtrl = NULL;
 	struct rx_ts_record *ts = NULL;
@@ -239,7 +239,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	dst = (u8 *)(&req->addr2[0]);
 	tag += sizeof(struct ieee80211_hdr_3addr);
 	dialog_token = tag + 2;
-	pBaParamSet = (union ba_param_set *)(tag + 3);
+	ba_param_set = (union ba_param_set *)(tag + 3);
 	pBaTimeoutVal = (u16 *)(tag + 5);
 	pBaStartSeqCtrl = (union sequence_control *)(req + 7);
 
@@ -254,14 +254,14 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 		goto OnADDBAReq_Fail;
 	}
 	if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
-		   (u8)(pBaParamSet->field.tid), RX_DIR, true)) {
+		   (u8)(ba_param_set->field.tid), RX_DIR, true)) {
 		rc = ADDBA_STATUS_REFUSED;
 		netdev_warn(ieee->dev, "%s(): can't get TS\n", __func__);
 		goto OnADDBAReq_Fail;
 	}
 	ba = &ts->rx_admitted_ba_record;
 
-	if (pBaParamSet->field.ba_policy == BA_POLICY_DELAYED) {
+	if (ba_param_set->field.ba_policy == BA_POLICY_DELAYED) {
 		rc = ADDBA_STATUS_INVALID_PARAM;
 		netdev_warn(ieee->dev, "%s(): BA Policy is not correct\n",
 			    __func__);
@@ -272,7 +272,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 
 	deactivate_ba_entry(ieee, ba);
 	ba->dialog_token = *dialog_token;
-	ba->ba_param_set = *pBaParamSet;
+	ba->ba_param_set = *ba_param_set;
 	ba->ba_timeout_value = *pBaTimeoutVal;
 	ba->ba_start_seq_ctrl = *pBaStartSeqCtrl;
 
@@ -291,7 +291,7 @@ OnADDBAReq_Fail:
 	{
 		struct ba_record BA;
 
-		BA.ba_param_set = *pBaParamSet;
+		BA.ba_param_set = *ba_param_set;
 		BA.ba_timeout_value = *pBaTimeoutVal;
 		BA.dialog_token = *dialog_token;
 		BA.ba_param_set.field.ba_policy = BA_POLICY_IMMEDIATE;
@@ -307,7 +307,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	struct tx_ts_record *ts = NULL;
 	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
 	u16 *status_code = NULL, *pBaTimeoutVal = NULL;
-	union ba_param_set *pBaParamSet = NULL;
+	union ba_param_set *ba_param_set = NULL;
 	u16			reason_code;
 
 	if (skb->len < sizeof(struct ieee80211_hdr_3addr) + 9) {
@@ -322,7 +322,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	tag += sizeof(struct ieee80211_hdr_3addr);
 	dialog_token = tag + 2;
 	status_code = (u16 *)(tag + 3);
-	pBaParamSet = (union ba_param_set *)(tag + 5);
+	ba_param_set = (union ba_param_set *)(tag + 5);
 	pBaTimeoutVal = (u16 *)(tag + 7);
 
 	if (!ieee->current_network.qos_data.active ||
@@ -338,7 +338,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	}
 
 	if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
-		   (u8)(pBaParamSet->field.tid), TX_DIR, false)) {
+		   (u8)(ba_param_set->field.tid), TX_DIR, false)) {
 		netdev_warn(ieee->dev, "%s(): can't get TS\n", __func__);
 		reason_code = DELBA_REASON_UNKNOWN_BA;
 		goto OnADDBARsp_Reject;
@@ -367,7 +367,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	}
 
 	if (*status_code == ADDBA_STATUS_SUCCESS) {
-		if (pBaParamSet->field.ba_policy == BA_POLICY_DELAYED) {
+		if (ba_param_set->field.ba_policy == BA_POLICY_DELAYED) {
 			ts->add_ba_req_delayed = true;
 			deactivate_ba_entry(ieee, pAdmittedBA);
 			reason_code = DELBA_REASON_END_BA;
@@ -377,7 +377,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 		pAdmittedBA->dialog_token = *dialog_token;
 		pAdmittedBA->ba_timeout_value = *pBaTimeoutVal;
 		pAdmittedBA->ba_start_seq_ctrl = pending_ba->ba_start_seq_ctrl;
-		pAdmittedBA->ba_param_set = *pBaParamSet;
+		pAdmittedBA->ba_param_set = *ba_param_set;
 		deactivate_ba_entry(ieee, pAdmittedBA);
 		activate_ba_entry(pAdmittedBA, *pBaTimeoutVal);
 	} else {
@@ -393,7 +393,7 @@ OnADDBARsp_Reject:
 	{
 		struct ba_record BA;
 
-		BA.ba_param_set = *pBaParamSet;
+		BA.ba_param_set = *ba_param_set;
 		rtllib_send_DELBA(ieee, dst, &BA, TX_DIR, reason_code);
 		return 0;
 	}
-- 
GitLab


From cc6c66a6d41f6b28fbe5f11c3552381f529a9867 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:43:03 -0800
Subject: [PATCH 0523/4076] Staging: rtl8192e: Rename variable pBaTimeoutVal

Rename variable pBaTimeoutVal to ba_timeout_value to fix checkpatch
warning Avoid CamelCase, and make the name consistent with variables
of same name/type.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-14-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 7074a01ad2e85..964029df310ee 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -218,7 +218,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
 	struct ba_record *ba = NULL;
 	union ba_param_set *ba_param_set = NULL;
-	u16 *pBaTimeoutVal = NULL;
+	u16 *ba_timeout_value = NULL;
 	union sequence_control *pBaStartSeqCtrl = NULL;
 	struct rx_ts_record *ts = NULL;
 
@@ -240,7 +240,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	tag += sizeof(struct ieee80211_hdr_3addr);
 	dialog_token = tag + 2;
 	ba_param_set = (union ba_param_set *)(tag + 3);
-	pBaTimeoutVal = (u16 *)(tag + 5);
+	ba_timeout_value = (u16 *)(tag + 5);
 	pBaStartSeqCtrl = (union sequence_control *)(req + 7);
 
 	if (!ieee->current_network.qos_data.active ||
@@ -273,7 +273,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	deactivate_ba_entry(ieee, ba);
 	ba->dialog_token = *dialog_token;
 	ba->ba_param_set = *ba_param_set;
-	ba->ba_timeout_value = *pBaTimeoutVal;
+	ba->ba_timeout_value = *ba_timeout_value;
 	ba->ba_start_seq_ctrl = *pBaStartSeqCtrl;
 
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev) ||
@@ -292,7 +292,7 @@ OnADDBAReq_Fail:
 		struct ba_record BA;
 
 		BA.ba_param_set = *ba_param_set;
-		BA.ba_timeout_value = *pBaTimeoutVal;
+		BA.ba_timeout_value = *ba_timeout_value;
 		BA.dialog_token = *dialog_token;
 		BA.ba_param_set.field.ba_policy = BA_POLICY_IMMEDIATE;
 		rtllib_send_ADDBARsp(ieee, dst, &BA, rc);
@@ -306,7 +306,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	struct ba_record *pending_ba, *pAdmittedBA;
 	struct tx_ts_record *ts = NULL;
 	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
-	u16 *status_code = NULL, *pBaTimeoutVal = NULL;
+	u16 *status_code = NULL, *ba_timeout_value = NULL;
 	union ba_param_set *ba_param_set = NULL;
 	u16			reason_code;
 
@@ -323,7 +323,7 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	dialog_token = tag + 2;
 	status_code = (u16 *)(tag + 3);
 	ba_param_set = (union ba_param_set *)(tag + 5);
-	pBaTimeoutVal = (u16 *)(tag + 7);
+	ba_timeout_value = (u16 *)(tag + 7);
 
 	if (!ieee->current_network.qos_data.active ||
 	    !ieee->ht_info->current_ht_support ||
@@ -375,11 +375,11 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 		}
 
 		pAdmittedBA->dialog_token = *dialog_token;
-		pAdmittedBA->ba_timeout_value = *pBaTimeoutVal;
+		pAdmittedBA->ba_timeout_value = *ba_timeout_value;
 		pAdmittedBA->ba_start_seq_ctrl = pending_ba->ba_start_seq_ctrl;
 		pAdmittedBA->ba_param_set = *ba_param_set;
 		deactivate_ba_entry(ieee, pAdmittedBA);
-		activate_ba_entry(pAdmittedBA, *pBaTimeoutVal);
+		activate_ba_entry(pAdmittedBA, *ba_timeout_value);
 	} else {
 		ts->add_ba_req_delayed = true;
 		ts->disable_add_ba = true;
-- 
GitLab


From db099efcb25ceb7b2d5cae7cffeb9ac1b1a6852d Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:43:04 -0800
Subject: [PATCH 0524/4076] Staging: rtl8192e: Rename variable pAdmittedBA

Rename variable pAdmittedBA to admitted_ba to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-15-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 964029df310ee..b00d0f7c75177 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -303,7 +303,7 @@ OnADDBAReq_Fail:
 int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 {
 	struct ieee80211_hdr_3addr *rsp = NULL;
-	struct ba_record *pending_ba, *pAdmittedBA;
+	struct ba_record *pending_ba, *admitted_ba;
 	struct tx_ts_record *ts = NULL;
 	u8 *dst = NULL, *dialog_token = NULL, *tag = NULL;
 	u16 *status_code = NULL, *ba_timeout_value = NULL;
@@ -346,9 +346,9 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 
 	ts->add_ba_req_in_progress = false;
 	pending_ba = &ts->tx_pending_ba_record;
-	pAdmittedBA = &ts->tx_admitted_ba_record;
+	admitted_ba = &ts->tx_admitted_ba_record;
 
-	if (pAdmittedBA->b_valid) {
+	if (admitted_ba->b_valid) {
 		netdev_dbg(ieee->dev, "%s(): ADDBA response already admitted\n",
 			   __func__);
 		return -1;
@@ -369,17 +369,17 @@ int rtllib_rx_ADDBARsp(struct rtllib_device *ieee, struct sk_buff *skb)
 	if (*status_code == ADDBA_STATUS_SUCCESS) {
 		if (ba_param_set->field.ba_policy == BA_POLICY_DELAYED) {
 			ts->add_ba_req_delayed = true;
-			deactivate_ba_entry(ieee, pAdmittedBA);
+			deactivate_ba_entry(ieee, admitted_ba);
 			reason_code = DELBA_REASON_END_BA;
 			goto OnADDBARsp_Reject;
 		}
 
-		pAdmittedBA->dialog_token = *dialog_token;
-		pAdmittedBA->ba_timeout_value = *ba_timeout_value;
-		pAdmittedBA->ba_start_seq_ctrl = pending_ba->ba_start_seq_ctrl;
-		pAdmittedBA->ba_param_set = *ba_param_set;
-		deactivate_ba_entry(ieee, pAdmittedBA);
-		activate_ba_entry(pAdmittedBA, *ba_timeout_value);
+		admitted_ba->dialog_token = *dialog_token;
+		admitted_ba->ba_timeout_value = *ba_timeout_value;
+		admitted_ba->ba_start_seq_ctrl = pending_ba->ba_start_seq_ctrl;
+		admitted_ba->ba_param_set = *ba_param_set;
+		deactivate_ba_entry(ieee, admitted_ba);
+		activate_ba_entry(admitted_ba, *ba_timeout_value);
 	} else {
 		ts->add_ba_req_delayed = true;
 		ts->disable_add_ba = true;
-- 
GitLab


From d488759416ed3adf542abe15a530243bb74dd882 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 26 Nov 2023 21:43:05 -0800
Subject: [PATCH 0525/4076] Staging: rtl8192e: Rename variable TsCommonInfo

Rename variable TsCommonInfo to ts_common_info to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231127054305.148276-16-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 6 +++---
 drivers/staging/rtl8192e/rtl819x_TS.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index b00d0f7c75177..58a950ef77ce3 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -474,14 +474,14 @@ void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
 	ba->dialog_token++;
 	ba->ba_param_set.field.amsdu_support = 0;
 	ba->ba_param_set.field.ba_policy = policy;
-	ba->ba_param_set.field.tid = ts->TsCommonInfo.tspec.ucTSID;
+	ba->ba_param_set.field.tid = ts->ts_common_info.tspec.ucTSID;
 	ba->ba_param_set.field.buffer_size = 32;
 	ba->ba_timeout_value = 0;
 	ba->ba_start_seq_ctrl.field.seq_num = (ts->tx_cur_seq + 3) % 4096;
 
 	activate_ba_entry(ba, BA_SETUP_TIMEOUT);
 
-	rtllib_send_ADDBAReq(ieee, ts->TsCommonInfo.addr, ba);
+	rtllib_send_ADDBAReq(ieee, ts->ts_common_info.addr, ba);
 }
 
 void rtllib_ts_init_del_ba(struct rtllib_device *ieee,
@@ -525,7 +525,7 @@ void rtllib_tx_ba_inact_timeout(struct timer_list *t)
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
 				     TxTsRecord[ts->num]);
 	tx_ts_delete_ba(ieee, ts);
-	rtllib_send_DELBA(ieee, ts->TsCommonInfo.addr,
+	rtllib_send_DELBA(ieee, ts->ts_common_info.addr,
 			  &ts->tx_admitted_ba_record, TX_DIR,
 			  DELBA_REASON_TIMEOUT);
 }
diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index 8e22c717fb274..31f7cfbb3aa52 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -23,7 +23,7 @@ struct ts_common_info {
 };
 
 struct tx_ts_record {
-	struct ts_common_info TsCommonInfo;
+	struct ts_common_info ts_common_info;
 	u16				tx_cur_seq;
 	struct ba_record tx_pending_ba_record;
 	struct ba_record tx_admitted_ba_record;
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index f96538f3e4eee..bec73bc53dd08 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -99,7 +99,7 @@ static void ResetTsCommonInfo(struct ts_common_info *ts_common_info)
 
 static void ResetTxTsEntry(struct tx_ts_record *ts)
 {
-	ResetTsCommonInfo(&ts->TsCommonInfo);
+	ResetTsCommonInfo(&ts->ts_common_info);
 	ts->tx_cur_seq = 0;
 	ts->add_ba_req_in_progress = false;
 	ts->add_ba_req_delayed = false;
@@ -138,7 +138,7 @@ void rtllib_ts_init(struct rtllib_device *ieee)
 			    rtllib_tx_ba_inact_timeout, 0);
 
 		ResetTxTsEntry(pTxTS);
-		list_add_tail(&pTxTS->TsCommonInfo.List,
+		list_add_tail(&pTxTS->ts_common_info.List,
 				&ieee->Tx_TS_Unused_List);
 		pTxTS++;
 	}
@@ -292,7 +292,7 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 			struct tx_ts_record *tmp =
 				container_of(*ppTS,
 				struct tx_ts_record,
-				TsCommonInfo);
+				ts_common_info);
 			ResetTxTsEntry(tmp);
 		} else {
 			struct rx_ts_record *ts =
-- 
GitLab


From 581ff5b66c94a8133d1c77ed42334623fadc968c Mon Sep 17 00:00:00 2001
From: zhujun2 <zhujun2@cmss.chinamobile.com>
Date: Tue, 14 Nov 2023 22:42:55 -0800
Subject: [PATCH 0526/4076] perf tests coresight: Remove unused variables

These variables are never referenced in the code, just remove them.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: zhujun2 <zhujun2@cmss.chinamobile.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: coresight@lists.linaro.org
Link: https://lore.kernel.org/r/20231115064255.11057-1-zhujun2@cmss.chinamobile.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c   | 1 -
 tools/perf/tests/shell/coresight/thread_loop/thread_loop.c       | 1 -
 .../shell/coresight/unroll_loop_thread/unroll_loop_thread.c      | 1 -
 3 files changed, 3 deletions(-)

diff --git a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
index a7e169d1bf645..5f886cd09e6b3 100644
--- a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
+++ b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
@@ -42,7 +42,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned long i, len, size, thr;
-	pthread_t threads[256];
 	struct args args[256];
 	long long v;
 
diff --git a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
index c0158fac7d0b0..e05a559253ca9 100644
--- a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
+++ b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
@@ -57,7 +57,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned int i, len, thr;
-	pthread_t threads[256];
 	struct args args[256];
 
 	if (argc < 3) {
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
index 8f6d384208ed9..0fc7bf1a25af3 100644
--- a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
@@ -51,7 +51,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned int i, thr;
-	pthread_t threads[256];
 	struct args args[256];
 
 	if (argc < 2) {
-- 
GitLab


From 5ebe2f4bf0a8fe8cceb5664a7dea4c17e2cf8477 Mon Sep 17 00:00:00 2001
From: Ji Sheng Teoh <jisheng.teoh@starfivetech.com>
Date: Wed, 22 Nov 2023 11:09:08 +0800
Subject: [PATCH 0527/4076] perf vendor events riscv: Add StarFive Dubhe-90
 JSON file

Similar to StarFive's Dubhe-80, Dubhe-90 supports raw event id 0x00 -
0x22. Reuse Dubhe-80 firmware and common json file.  The raw events are
enabled through PMU node of DT binding.  Besides raw event, add standard
RISC-V firmware events to support monitoring of firmware event.

Example of PMU DT node:
pmu {
	compatible = "riscv,pmu";
	riscv,raw-event-to-mhpmcounters =
		/* Event ID 1-31 */
		<0x00 0x00 0xFFFFFFFF 0xFFFFFFE0 0x00007FF8>,
		/* Event ID 32-33 */
		<0x00 0x20 0xFFFFFFFF 0xFFFFFFFE 0x00007FF8>,
		/* Event ID 34 */
		<0x00 0x22 0xFFFFFFFF 0xFFFFFF22 0x00007FF8>;
};

'perf stat' output:

  [root@user]# perf stat -a \
  	-e access_mmu_stlb \
  	-e miss_mmu_stlb \
  	-e access_mmu_pte_c \
  	-e rob_flush \
  	-e btb_prediction_miss \
  	-e itlb_miss \
  	-e sync_del_fetch_g \
  	-e icache_miss \
  	-e bpu_br_retire \
  	-e bpu_br_miss \
  	-e ret_ins_retire \
  	-e ret_ins_miss \
  	-- openssl speed rsa2048
  Doing 2048 bits private rsa's for 10s: 39 2048 bits private RSA's in
  10.03s
  Doing 2048 bits public rsa's for 10s: 1469 2048 bits public RSA's in
  9.47s
  version: 3.0.10
  built on: Tue Aug  1 13:47:24 2023 UTC
  options: bn(64,64)
  CPUINFO: N/A
                    sign    verify    sign/s verify/s
  rsa 2048 bits 0.257179s 0.006447s      3.9    155.1

   Performance counter stats for 'system wide':

             3112882      access_mmu_stlb
               10550      miss_mmu_stlb
               18251      access_mmu_pte_c
              274765      rob_flush
            22470560      btb_prediction_miss
             3035839      itlb_miss
           643549060      sync_del_fetch_g
              133013      icache_miss
            62982796      bpu_br_retire
              287548      bpu_br_miss
             8935910      ret_ins_retire
                8308      ret_ins_miss

        20.656182600 seconds time elapsed

Reviewed-by: Ley Foon Tan <leyfoon.tan@starfivetech.com>
Signed-off-by: Ji Sheng Teoh <jisheng.teoh@starfivetech.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nikita Shubin <n.shubin@yadro.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20231122030908.2981502-1-jisheng.teoh@starfivetech.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/riscv/mapfile.csv | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/arch/riscv/mapfile.csv b/tools/perf/pmu-events/arch/riscv/mapfile.csv
index ee61e26f90cd3..56b03138d46aa 100644
--- a/tools/perf/pmu-events/arch/riscv/mapfile.csv
+++ b/tools/perf/pmu-events/arch/riscv/mapfile.csv
@@ -15,4 +15,4 @@
 #
 #MVENDORID-MARCHID-MIMPID,Version,Filename,EventType
 0x489-0x8000000000000007-0x[[:xdigit:]]+,v1,sifive/u74,core
-0x67e-0x80000000db000080-0x[[:xdigit:]]+,v1,starfive/dubhe-80,core
+0x67e-0x80000000db0000[89]0-0x[[:xdigit:]]+,v1,starfive/dubhe-80,core
-- 
GitLab


From 1638b11ef8156c8551f5aaa5799069633593c5fe Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Thu, 23 Nov 2023 21:32:32 +0530
Subject: [PATCH 0528/4076] perf tools: Add perf binary dependent rule for
 shellcheck log in Makefile.perf

Add rule in new Makefile "tests/Makefile.tests" for running shellcheck
on shell test scripts. This automates below shellcheck into the build.

	$ for F in $(find tests/shell/ -perm -o=x -name '*.sh'); do shellcheck -S warning $F; done

Condition for shellcheck is added in Makefile.perf to avoid build
breakage in the absence of shellcheck binary. Update Makefile.perf to
contain new rule for "SHELLCHECK_TEST" which is for making shellcheck
test as a dependency on perf binary.

Added "tests/Makefile.tests" to run shellcheck on shellscripts in
tests/shell. The make rule "SHLLCHECK_RUN" ensures that, every time
during make, shellcheck will be run only on modified files during
subsequent invocations. By this, if any newly added shell scripts or
fixes in existing scripts breaks coding/formatting style, it will get
captured during the perf build.

Example build failure by modifying probe_vfs_getname.sh in tests/shell:

	In tests/shell/probe_vfs_getname.sh line 8:
	. $(dirname $0)/lib/probe.sh
	  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

	For more information:
	  https://www.shellcheck.net/wiki/SC2046 -- Quote this to prevent word splitt...
	make[3]: *** [/root/athira/perf-tools-next/tools/perf/tests/Makefile.tests:18: tests/shell/.probe_vfs_getname.sh.shellcheck_log] Error 1
	make[2]: *** [Makefile.perf:686: SHELLCHECK_TEST] Error 2
	make[2]: *** Waiting for unfinished jobs....
	make[1]: *** [Makefile.perf:244: sub-make] Error 2
	make: *** [Makefile:70: all] Error 2

Here, like other files which gets created during compilation (ex:
.builtin-bench.o.cmd or .perf.o.cmd ), create .shellcheck_log also as a
hidden file.  Example: tests/shell/.probe_vfs_getname.sh.shellcheck_log
shellcheck is re-run if any of the script gets modified based on its
dependency of this log file.

After this, for testing, changed "tests/shell/trace+probe_vfs_getname.sh" to
break shellcheck format. In the next make run, it is also captured:

	In tests/shell/probe_vfs_getname.sh line 8:
	. $(dirname $0)/lib/probe.sh
	  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

	For more information:
	  https://www.shellcheck.net/wiki/SC2046 -- Quote this to prevent word splitt...
	make[3]: *** [/root/athira/perf-tools-next/tools/perf/tests/Makefile.tests:18: tests/shell/.probe_vfs_getname.sh.shellcheck_log] Error 1
	make[3]: *** Waiting for unfinished jobs....

	In tests/shell/trace+probe_vfs_getname.sh line 14:
	. $(dirname $0)/lib/probe.sh
	  ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

	For more information:
	  https://www.shellcheck.net/wiki/SC2046 -- Quote this to prevent word splitt...
	make[3]: *** [/root/athira/perf-tools-next/tools/perf/tests/Makefile.tests:18: tests/shell/.trace+probe_vfs_getname.sh.shellcheck_log] Error 1
	make[2]: *** [Makefile.perf:686: SHELLCHECK_TEST] Error 2
	make[2]: *** Waiting for unfinished jobs....
	make[1]: *** [Makefile.perf:244: sub-make] Error 2
	make: *** [Makefile:70: all] Error 2

Failure log can be found in the stdout of make itself.

This is reported at build time. To be able to go ahead with the build or
disable shellcheck even though it is known that some test is broken, add
a "NO_SHELLCHECK" option. Example:

  make NO_SHELLCHECK=1

	  INSTALL libsubcmd_headers
	  INSTALL libsymbol_headers
	  INSTALL libapi_headers
	  INSTALL libperf_headers
	  INSTALL libbpf_headers
	  LINK    perf

Note:

This is tested on RHEL and also SLES. Use below check:
"$(shell which shellcheck 2> /dev/null)" to look for presence
of shellcheck binary. The approach "shell command -v" is not
used here. In some of the distros(RHEL), command is available
as executable file (/usr/bin/command). But in some distros(SLES),
it is a shell builtin and not available as executable file.

Committer testing:

  $ type shellcheck
  shellcheck is hashed (/usr/bin/shellcheck)
  $ rpm -qf /usr/bin/shellcheck
  ShellCheck-0.9.0-2.fc38.x86_64
  $
  $ alias m
  $ git diff
  diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh
  index 554e12e83c55fd56..dbc14634678e2bf6 100755
  --- a/tools/perf/tests/shell/probe_vfs_getname.sh
  +++ b/tools/perf/tests/shell/probe_vfs_getname.sh
  @@ -5,7 +5,7 @@
   # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017

   # shellcheck source=lib/probe.sh
  -. "$(dirname $0)"/lib/probe.sh
  +. $(dirname $0)/lib/probe.sh

   skip_if_no_perf_probe || exit 2

  alias m='rm -rf ~/libexec/perf-core/ ; make -k CORESIGHT=1 O=/tmp/build/$(basename $PWD) -C tools/perf install-bin && perf test python'
  $ m
  make: Entering directory '/home/acme/git/perf-tools-next/tools/perf'
    BUILD:   Doing 'make -j32' parallel build
<SNIP>
    INSTALL libbpf_headers

  In tests/shell/probe_vfs_getname.sh line 8:
  . $(dirname $0)/lib/probe.sh
    ^-----------^ SC2046 (warning): Quote this to prevent word splitting.

  For more information:
    https://www.shellcheck.net/wiki/SC2046 -- Quote this to prevent word splitt...
  make[3]: *** [/home/acme/git/perf-tools-next/tools/perf/tests/Makefile.tests:18: tests/shell/.probe_vfs_getname.sh.shellcheck_log] Error 1
  make[2]: *** [Makefile.perf:686: SHELLCHECK_TEST] Error 2
  make[2]: *** Waiting for unfinished jobs....
  make[1]: *** [Makefile.perf:244: sub-make] Error 2
  make: *** [Makefile:113: install-bin] Error 2
  make: Leaving directory '/home/acme/git/perf-tools-next/tools/perf'
  $

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20231123160232.94253-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf        | 21 ++++++++++++++++++++-
 tools/perf/tests/Makefile.tests | 22 ++++++++++++++++++++++
 2 files changed, 42 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/tests/Makefile.tests

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index d80dcaa5a1e33..824cbc0af7d7a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -134,6 +134,8 @@ include ../scripts/utilities.mak
 #	x86 instruction decoder - new instructions test
 #
 # Define GEN_VMLINUX_H to generate vmlinux.h from the BTF.
+#
+# Define NO_SHELLCHECK if you do not want to run shellcheck during build
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -671,7 +673,23 @@ $(PERF_IN): prepare FORCE
 $(PMU_EVENTS_IN): FORCE prepare
 	$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=pmu-events obj=pmu-events
 
-$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN)
+# Runs shellcheck on perf test shell scripts
+
+SHELLCHECK := $(shell which shellcheck 2> /dev/null)
+
+ifeq ($(NO_SHELLCHECK),1)
+SHELLCHECK :=
+endif
+
+ifneq ($(SHELLCHECK),)
+SHELLCHECK_TEST: FORCE prepare
+	$(Q)$(MAKE) -f $(srctree)/tools/perf/tests/Makefile.tests
+else
+SHELLCHECK_TEST:
+	@:
+endif
+
+$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) SHELLCHECK_TEST
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \
 		$(PERF_IN) $(PMU_EVENTS_IN) $(LIBS) -o $@
 
@@ -1134,6 +1152,7 @@ bpf-skel-clean:
 	$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS)
 
 clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean tests-coresight-targets-clean
+	$(Q)$(MAKE) -f $(srctree)/tools/perf/tests/Makefile.tests clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-iostat $(LANG_BINDINGS)
 	$(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
diff --git a/tools/perf/tests/Makefile.tests b/tools/perf/tests/Makefile.tests
new file mode 100644
index 0000000000000..fdaca5f7a946d
--- /dev/null
+++ b/tools/perf/tests/Makefile.tests
@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0
+# Athira Rajeev <atrajeev@linux.vnet.ibm.com>, 2023
+
+PROGS := $(shell find tests/shell -perm -o=x -type f -name '*.sh')
+FILE_NAME := $(notdir $(PROGS))
+FILE_NAME := $(FILE_NAME:%=.%)
+LOGS := $(join $(dir $(PROGS)),$(FILE_NAME))
+LOGS := $(LOGS:%=%.shellcheck_log)
+
+.PHONY: all
+all: SHELLCHECK_RUN
+	@:
+
+SHELLCHECK_RUN: $(LOGS)
+
+.%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call frecho-cmd,test)@shellcheck -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+clean:
+	$(eval log_files := $(shell find . -name '.*.shellcheck_log'))
+	@rm -rf $(log_files)
-- 
GitLab


From d4fbbb26da520e00d87c8187dc3de9eacee66c1c Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 27 Nov 2023 11:17:31 +0000
Subject: [PATCH 0529/4076] KVM: arm64: Add new (V)TCR_EL2 field definitions
 for FEAT_LPA2

As per Arm ARM (0487I.a), (V)TCR_EL2.DS fields control whether 52 bit
input and output addresses are supported on 4K and 16K page size
configurations when FEAT_LPA2 is known to have been implemented.

This adds these field definitions which will be used by KVM when
FEAT_LPA2 is enabled.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231127111737.1897081-7-ryan.roberts@arm.com
---
 arch/arm64/include/asm/kvm_arm.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index b85f46a73e21b..312cbc3008313 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -108,6 +108,7 @@
 #define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En)
 
 /* TCR_EL2 Registers bits */
+#define TCR_EL2_DS		(1UL << 32)
 #define TCR_EL2_RES1		((1U << 31) | (1 << 23))
 #define TCR_EL2_TBI		(1 << 20)
 #define TCR_EL2_PS_SHIFT	16
@@ -122,6 +123,7 @@
 			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
 
 /* VTCR_EL2 Registers bits */
+#define VTCR_EL2_DS		TCR_EL2_DS
 #define VTCR_EL2_RES1		(1U << 31)
 #define VTCR_EL2_HD		(1 << 22)
 #define VTCR_EL2_HA		(1 << 21)
-- 
GitLab


From bd412e2a310cbc43b424198b0065086b0f462625 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 27 Nov 2023 11:17:32 +0000
Subject: [PATCH 0530/4076] KVM: arm64: Use LPA2 page-tables for stage2 and hyp
 stage1

Implement a simple policy whereby if the HW supports FEAT_LPA2 for the
page size we are using, always use LPA2-style page-tables for stage 2
and hyp stage 1 (assuming an nvhe hyp), regardless of the VMM-requested
IPA size or HW-implemented PA size. When in use we can now support up to
52-bit IPA and PA sizes.

We use the previously created cpu feature to track whether LPA2 is
supported for deciding whether to use the LPA2 or classic pte format.

Note that FEAT_LPA2 brings support for bigger block mappings (512GB with
4KB, 64GB with 16KB). We explicitly don't enable these in the library
because stage2_apply_range() works on batch sizes of the largest used
block mapping, and increasing the size of the batch would lead to soft
lockups. See commit 5994bc9e05c2 ("KVM: arm64: Limit
stage2_apply_range() batch size to largest block").

With the addition of LPA2 support in the hypervisor, the PA size
supported by the HW must be capped with a runtime decision, rather than
simply using a compile-time decision based on PA_BITS. For example, on a
system that advertises 52 bit PA but does not support FEAT_LPA2, A 4KB
or 16KB kernel compiled with LPA2 support must still limit the PA size
to 48 bits.

Therefore, move the insertion of the PS field into TCR_EL2 out of
__kvm_hyp_init assembly code and instead do it in cpu_prepare_hyp_mode()
where the rest of TCR_EL2 is prepared. This allows us to figure out PS
with kvm_get_parange(), which has the appropriate logic to ensure the
above requirement. (and the PS field of VTCR_EL2 is already populated
this way).

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231127111737.1897081-8-ryan.roberts@arm.com
---
 arch/arm64/include/asm/kvm_pgtable.h | 49 +++++++++++++++++++++-------
 arch/arm64/kvm/arm.c                 |  5 +++
 arch/arm64/kvm/hyp/nvhe/hyp-init.S   |  4 ---
 arch/arm64/kvm/hyp/pgtable.c         | 15 +++++++--
 4 files changed, 54 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 10068500d6019..69a2a87ecaf6b 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -25,14 +25,24 @@
 #define KVM_PGTABLE_MIN_BLOCK_LEVEL	2U
 #endif
 
-#define kvm_lpa2_is_enabled()		false
+#define kvm_lpa2_is_enabled()		system_supports_lpa2()
+
+static inline u64 kvm_get_parange_max(void)
+{
+	if (kvm_lpa2_is_enabled() ||
+	   (IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && PAGE_SHIFT == 16))
+		return ID_AA64MMFR0_EL1_PARANGE_52;
+	else
+		return ID_AA64MMFR0_EL1_PARANGE_48;
+}
 
 static inline u64 kvm_get_parange(u64 mmfr0)
 {
+	u64 parange_max = kvm_get_parange_max();
 	u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
 				ID_AA64MMFR0_EL1_PARANGE_SHIFT);
-	if (parange > ID_AA64MMFR0_EL1_PARANGE_MAX)
-		parange = ID_AA64MMFR0_EL1_PARANGE_MAX;
+	if (parange > parange_max)
+		parange = parange_max;
 
 	return parange;
 }
@@ -43,6 +53,8 @@ typedef u64 kvm_pte_t;
 
 #define KVM_PTE_ADDR_MASK		GENMASK(47, PAGE_SHIFT)
 #define KVM_PTE_ADDR_51_48		GENMASK(15, 12)
+#define KVM_PTE_ADDR_MASK_LPA2		GENMASK(49, PAGE_SHIFT)
+#define KVM_PTE_ADDR_51_50_LPA2		GENMASK(9, 8)
 
 #define KVM_PHYS_INVALID		(-1ULL)
 
@@ -53,21 +65,34 @@ static inline bool kvm_pte_valid(kvm_pte_t pte)
 
 static inline u64 kvm_pte_to_phys(kvm_pte_t pte)
 {
-	u64 pa = pte & KVM_PTE_ADDR_MASK;
-
-	if (PAGE_SHIFT == 16)
-		pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
+	u64 pa;
+
+	if (kvm_lpa2_is_enabled()) {
+		pa = pte & KVM_PTE_ADDR_MASK_LPA2;
+		pa |= FIELD_GET(KVM_PTE_ADDR_51_50_LPA2, pte) << 50;
+	} else {
+		pa = pte & KVM_PTE_ADDR_MASK;
+		if (PAGE_SHIFT == 16)
+			pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
+	}
 
 	return pa;
 }
 
 static inline kvm_pte_t kvm_phys_to_pte(u64 pa)
 {
-	kvm_pte_t pte = pa & KVM_PTE_ADDR_MASK;
-
-	if (PAGE_SHIFT == 16) {
-		pa &= GENMASK(51, 48);
-		pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48);
+	kvm_pte_t pte;
+
+	if (kvm_lpa2_is_enabled()) {
+		pte = pa & KVM_PTE_ADDR_MASK_LPA2;
+		pa &= GENMASK(51, 50);
+		pte |= FIELD_PREP(KVM_PTE_ADDR_51_50_LPA2, pa >> 50);
+	} else {
+		pte = pa & KVM_PTE_ADDR_MASK;
+		if (PAGE_SHIFT == 16) {
+			pa &= GENMASK(51, 48);
+			pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48);
+		}
 	}
 
 	return pte;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e5f75f1f10853..c4bbc224549bf 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1837,6 +1837,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
+	u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 	unsigned long tcr;
 
 	/*
@@ -1859,6 +1860,10 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	}
 	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
+	tcr &= ~TCR_EL2_PS_MASK;
+	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0));
+	if (kvm_lpa2_is_enabled())
+		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 1cc06e6797bda..f62a7d3602857 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -122,11 +122,7 @@ alternative_if ARM64_HAS_CNP
 alternative_else_nop_endif
 	msr	ttbr0_el2, x2
 
-	/*
-	 * Set the PS bits in TCR_EL2.
-	 */
 	ldr	x0, [x0, #NVHE_INIT_TCR_EL2]
-	tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2
 	msr	tcr_el2, x0
 
 	isb
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 1966fdee740eb..ce9a58cb02fd4 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -79,7 +79,10 @@ static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx)
 
 static bool kvm_phys_is_valid(u64 phys)
 {
-	return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX));
+	u64 parange_max = kvm_get_parange_max();
+	u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max);
+
+	return phys < BIT(shift);
 }
 
 static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys)
@@ -408,7 +411,8 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
 	}
 
 	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap);
-	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
+	if (!kvm_lpa2_is_enabled())
+		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
 	attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF;
 	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
 	*ptep = attr;
@@ -654,6 +658,9 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 		vtcr |= VTCR_EL2_HA;
 #endif /* CONFIG_ARM64_HW_AFDBM */
 
+	if (kvm_lpa2_is_enabled())
+		vtcr |= VTCR_EL2_DS;
+
 	/* Set the vmid bits */
 	vtcr |= (get_vmid_bits(mmfr1) == 16) ?
 		VTCR_EL2_VS_16BIT :
@@ -711,7 +718,9 @@ static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot p
 	if (prot & KVM_PGTABLE_PROT_W)
 		attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;
 
-	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
+	if (!kvm_lpa2_is_enabled())
+		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
+
 	attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF;
 	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
 	*ptep = attr;
-- 
GitLab


From 419edf48d79f6fb2cc3fa090131864e95b321d41 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 27 Nov 2023 11:17:33 +0000
Subject: [PATCH 0531/4076] KVM: arm64: Convert translation level parameter to
 s8

With the introduction of FEAT_LPA2, the Arm ARM adds a new level of
translation, level -1, so levels can now be in the range [-1;3]. 3 is
always the last level and the first level is determined based on the
number of VA bits in use.

Convert level variables to use a signed type in preparation for
supporting this new level -1.

Since the last level is always anchored at 3, and the first level varies
to suit the number of VA/IPA bits, take the opportunity to replace
KVM_PGTABLE_MAX_LEVELS with the 2 macros KVM_PGTABLE_FIRST_LEVEL and
KVM_PGTABLE_LAST_LEVEL. This removes the assumption from the code that
levels run from 0 to KVM_PGTABLE_MAX_LEVELS - 1, which will soon no
longer be true.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231127111737.1897081-9-ryan.roberts@arm.com
---
 arch/arm64/include/asm/kvm_emulate.h  |  2 +-
 arch/arm64/include/asm/kvm_pgtable.h  | 31 +++++++------
 arch/arm64/include/asm/kvm_pkvm.h     |  5 +-
 arch/arm64/kvm/hyp/nvhe/mem_protect.c |  6 +--
 arch/arm64/kvm/hyp/nvhe/mm.c          |  4 +-
 arch/arm64/kvm/hyp/nvhe/setup.c       |  2 +-
 arch/arm64/kvm/hyp/pgtable.c          | 66 +++++++++++++++------------
 arch/arm64/kvm/mmu.c                  | 16 ++++---
 8 files changed, 71 insertions(+), 61 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 78a550537b673..13fd9dbf2d1dd 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -409,7 +409,7 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vc
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
-static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
+static __always_inline s8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
 }
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 69a2a87ecaf6b..3253828e453d5 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -11,7 +11,8 @@
 #include <linux/kvm_host.h>
 #include <linux/types.h>
 
-#define KVM_PGTABLE_MAX_LEVELS		4U
+#define KVM_PGTABLE_FIRST_LEVEL		0
+#define KVM_PGTABLE_LAST_LEVEL		3
 
 /*
  * The largest supported block sizes for KVM (no 52-bit PA support):
@@ -20,9 +21,9 @@
  *  - 64K (level 2):	512MB
  */
 #ifdef CONFIG_ARM64_4K_PAGES
-#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1U
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1
 #else
-#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2U
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2
 #endif
 
 #define kvm_lpa2_is_enabled()		system_supports_lpa2()
@@ -103,28 +104,28 @@ static inline kvm_pfn_t kvm_pte_to_pfn(kvm_pte_t pte)
 	return __phys_to_pfn(kvm_pte_to_phys(pte));
 }
 
-static inline u64 kvm_granule_shift(u32 level)
+static inline u64 kvm_granule_shift(s8 level)
 {
-	/* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */
+	/* Assumes KVM_PGTABLE_LAST_LEVEL is 3 */
 	return ARM64_HW_PGTABLE_LEVEL_SHIFT(level);
 }
 
-static inline u64 kvm_granule_size(u32 level)
+static inline u64 kvm_granule_size(s8 level)
 {
 	return BIT(kvm_granule_shift(level));
 }
 
-static inline bool kvm_level_supports_block_mapping(u32 level)
+static inline bool kvm_level_supports_block_mapping(s8 level)
 {
 	return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
 }
 
 static inline u32 kvm_supported_block_sizes(void)
 {
-	u32 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
+	s8 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
 	u32 r = 0;
 
-	for (; level < KVM_PGTABLE_MAX_LEVELS; level++)
+	for (; level <= KVM_PGTABLE_LAST_LEVEL; level++)
 		r |= BIT(kvm_granule_shift(level));
 
 	return r;
@@ -169,7 +170,7 @@ struct kvm_pgtable_mm_ops {
 	void*		(*zalloc_page)(void *arg);
 	void*		(*zalloc_pages_exact)(size_t size);
 	void		(*free_pages_exact)(void *addr, size_t size);
-	void		(*free_unlinked_table)(void *addr, u32 level);
+	void		(*free_unlinked_table)(void *addr, s8 level);
 	void		(*get_page)(void *addr);
 	void		(*put_page)(void *addr);
 	int		(*page_count)(void *addr);
@@ -265,7 +266,7 @@ struct kvm_pgtable_visit_ctx {
 	u64					start;
 	u64					addr;
 	u64					end;
-	u32					level;
+	s8					level;
 	enum kvm_pgtable_walk_flags		flags;
 };
 
@@ -368,7 +369,7 @@ static inline bool kvm_pgtable_walk_lock_held(void)
  */
 struct kvm_pgtable {
 	u32					ia_bits;
-	u32					start_level;
+	s8					start_level;
 	kvm_pteref_t				pgd;
 	struct kvm_pgtable_mm_ops		*mm_ops;
 
@@ -502,7 +503,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  * The page-table is assumed to be unreachable by any hardware walkers prior to
  * freeing and therefore no TLB invalidation is performed.
  */
-void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
 
 /**
  * kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure.
@@ -526,7 +527,7 @@ void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *p
  * an ERR_PTR(error) on failure.
  */
 kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
-					      u64 phys, u32 level,
+					      u64 phys, s8 level,
 					      enum kvm_pgtable_prot prot,
 					      void *mc, bool force_pte);
 
@@ -752,7 +753,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
  * Return: 0 on success, negative error code on failure.
  */
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, u32 *level);
+			 kvm_pte_t *ptep, s8 *level);
 
 /**
  * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index e46250a020172..ad9cfb5c1ff4e 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -56,10 +56,11 @@ static inline unsigned long hyp_vm_table_pages(void)
 
 static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages)
 {
-	unsigned long total = 0, i;
+	unsigned long total = 0;
+	int i;
 
 	/* Provision the worst case scenario */
-	for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) {
+	for (i = KVM_PGTABLE_FIRST_LEVEL; i <= KVM_PGTABLE_LAST_LEVEL; i++) {
 		nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE);
 		total += nr_pages;
 	}
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 8d0a5834e8830..861c76021a250 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -91,7 +91,7 @@ static void host_s2_put_page(void *addr)
 	hyp_put_page(&host_s2_pool, addr);
 }
 
-static void host_s2_free_unlinked_table(void *addr, u32 level)
+static void host_s2_free_unlinked_table(void *addr, s8 level)
 {
 	kvm_pgtable_stage2_free_unlinked(&host_mmu.mm_ops, addr, level);
 }
@@ -443,7 +443,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 {
 	struct kvm_mem_range cur;
 	kvm_pte_t pte;
-	u32 level;
+	s8 level;
 	int ret;
 
 	hyp_assert_lock_held(&host_mmu.lock);
@@ -462,7 +462,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
 		level++;
-	} while ((level < KVM_PGTABLE_MAX_LEVELS) &&
+	} while ((level <= KVM_PGTABLE_LAST_LEVEL) &&
 			!(kvm_level_supports_block_mapping(level) &&
 			  range_included(&cur, range)));
 
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 65a7a186d7b21..b01a3d1078a88 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -260,7 +260,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
 	 * https://lore.kernel.org/kvm/20221017115209.2099-1-will@kernel.org/T/#mf10dfbaf1eaef9274c581b81c53758918c1d0f03
 	 */
 	dsb(ishst);
-	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), (KVM_PGTABLE_MAX_LEVELS - 1));
+	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), KVM_PGTABLE_LAST_LEVEL);
 	dsb(ish);
 	isb();
 }
@@ -275,7 +275,7 @@ static int __create_fixmap_slot_cb(const struct kvm_pgtable_visit_ctx *ctx,
 {
 	struct hyp_fixmap_slot *slot = per_cpu_ptr(&fixmap_slots, (u64)ctx->arg);
 
-	if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_MAX_LEVELS - 1)
+	if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_LAST_LEVEL)
 		return -EINVAL;
 
 	slot->addr = ctx->addr;
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 0d5e0a89ddce5..bc58d1b515af1 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -181,7 +181,7 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	if (!kvm_pte_valid(ctx->old))
 		return 0;
 
-	if (ctx->level != (KVM_PGTABLE_MAX_LEVELS - 1))
+	if (ctx->level != KVM_PGTABLE_LAST_LEVEL)
 		return -EINVAL;
 
 	phys = kvm_pte_to_phys(ctx->old);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index ce9a58cb02fd4..744bded18e993 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -101,7 +101,7 @@ static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx,
 	return IS_ALIGNED(ctx->addr, granule);
 }
 
-static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, u32 level)
+static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level)
 {
 	u64 shift = kvm_granule_shift(level);
 	u64 mask = BIT(PAGE_SHIFT - 3) - 1;
@@ -117,7 +117,7 @@ static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr)
 	return (addr & mask) >> shift;
 }
 
-static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
+static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level)
 {
 	struct kvm_pgtable pgt = {
 		.ia_bits	= ia_bits,
@@ -127,9 +127,9 @@ static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
 	return kvm_pgd_page_idx(&pgt, -1ULL) + 1;
 }
 
-static bool kvm_pte_table(kvm_pte_t pte, u32 level)
+static bool kvm_pte_table(kvm_pte_t pte, s8 level)
 {
-	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+	if (level == KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
 	if (!kvm_pte_valid(pte))
@@ -157,11 +157,11 @@ static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops
 	return pte;
 }
 
-static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level)
+static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level)
 {
 	kvm_pte_t pte = kvm_phys_to_pte(pa);
-	u64 type = (level == KVM_PGTABLE_MAX_LEVELS - 1) ? KVM_PTE_TYPE_PAGE :
-							   KVM_PTE_TYPE_BLOCK;
+	u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE :
+						       KVM_PTE_TYPE_BLOCK;
 
 	pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI);
 	pte |= FIELD_PREP(KVM_PTE_TYPE, type);
@@ -206,11 +206,11 @@ static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker,
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level);
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level);
 
 static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 				      struct kvm_pgtable_mm_ops *mm_ops,
-				      kvm_pteref_t pteref, u32 level)
+				      kvm_pteref_t pteref, s8 level)
 {
 	enum kvm_pgtable_walk_flags flags = data->walker->flags;
 	kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref);
@@ -275,12 +275,13 @@ out:
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level)
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level)
 {
 	u32 idx;
 	int ret = 0;
 
-	if (WARN_ON_ONCE(level >= KVM_PGTABLE_MAX_LEVELS))
+	if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL ||
+			 level > KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) {
@@ -343,7 +344,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 
 struct leaf_walk_data {
 	kvm_pte_t	pte;
-	u32		level;
+	s8		level;
 };
 
 static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
@@ -358,7 +359,7 @@ static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
 }
 
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, u32 *level)
+			 kvm_pte_t *ptep, s8 *level)
 {
 	struct leaf_walk_data data;
 	struct kvm_pgtable_walker walker = {
@@ -471,7 +472,7 @@ static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	if (hyp_map_walker_try_leaf(ctx, data))
 		return 0;
 
-	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL);
@@ -567,14 +568,19 @@ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
 			 struct kvm_pgtable_mm_ops *mm_ops)
 {
-	u64 levels = ARM64_HW_PGTABLE_LEVELS(va_bits);
+	s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 -
+			 ARM64_HW_PGTABLE_LEVELS(va_bits);
+
+	if (start_level < KVM_PGTABLE_FIRST_LEVEL ||
+	    start_level > KVM_PGTABLE_LAST_LEVEL)
+		return -EINVAL;
 
 	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL);
 	if (!pgt->pgd)
 		return -ENOMEM;
 
 	pgt->ia_bits		= va_bits;
-	pgt->start_level	= KVM_PGTABLE_MAX_LEVELS - levels;
+	pgt->start_level	= start_level;
 	pgt->mm_ops		= mm_ops;
 	pgt->mmu		= NULL;
 	pgt->force_pte_cb	= NULL;
@@ -628,7 +634,7 @@ struct stage2_map_data {
 u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 {
 	u64 vtcr = VTCR_EL2_FLAGS;
-	u8 lvls;
+	s8 lvls;
 
 	vtcr |= kvm_get_parange(mmfr0) << VTCR_EL2_PS_SHIFT;
 	vtcr |= VTCR_EL2_T0SZ(phys_shift);
@@ -911,7 +917,7 @@ static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
 {
 	u64 phys = stage2_map_walker_phys_addr(ctx, data);
 
-	if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1)))
+	if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
 	return kvm_block_mapping_supported(ctx, phys);
@@ -990,7 +996,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 	if (ret != -E2BIG)
 		return ret;
 
-	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	if (!data->memcache)
@@ -1160,7 +1166,7 @@ struct stage2_attr_data {
 	kvm_pte_t			attr_set;
 	kvm_pte_t			attr_clr;
 	kvm_pte_t			pte;
-	u32				level;
+	s8				level;
 };
 
 static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
@@ -1203,7 +1209,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
 static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 				    u64 size, kvm_pte_t attr_set,
 				    kvm_pte_t attr_clr, kvm_pte_t *orig_pte,
-				    u32 *level, enum kvm_pgtable_walk_flags flags)
+				    s8 *level, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI;
@@ -1305,7 +1311,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 				   enum kvm_pgtable_prot prot)
 {
 	int ret;
-	u32 level;
+	s8 level;
 	kvm_pte_t set = 0, clr = 0;
 
 	if (prot & KVM_PTE_LEAF_ATTR_HI_SW)
@@ -1358,7 +1364,7 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 }
 
 kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
-					      u64 phys, u32 level,
+					      u64 phys, s8 level,
 					      enum kvm_pgtable_prot prot,
 					      void *mc, bool force_pte)
 {
@@ -1416,7 +1422,7 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
  * fully populated tree up to the PTE entries. Note that @level is
  * interpreted as in "level @level entry".
  */
-static int stage2_block_get_nr_page_tables(u32 level)
+static int stage2_block_get_nr_page_tables(s8 level)
 {
 	switch (level) {
 	case 1:
@@ -1427,7 +1433,7 @@ static int stage2_block_get_nr_page_tables(u32 level)
 		return 0;
 	default:
 		WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL ||
-			     level >= KVM_PGTABLE_MAX_LEVELS);
+			     level > KVM_PGTABLE_LAST_LEVEL);
 		return -EINVAL;
 	};
 }
@@ -1440,13 +1446,13 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	struct kvm_s2_mmu *mmu;
 	kvm_pte_t pte = ctx->old, new, *childp;
 	enum kvm_pgtable_prot prot;
-	u32 level = ctx->level;
+	s8 level = ctx->level;
 	bool force_pte;
 	int nr_pages;
 	u64 phys;
 
 	/* No huge-pages exist at the last level */
-	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+	if (level == KVM_PGTABLE_LAST_LEVEL)
 		return 0;
 
 	/* We only split valid block mappings */
@@ -1523,7 +1529,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 	u64 vtcr = mmu->vtcr;
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
-	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz);
@@ -1546,7 +1552,7 @@ size_t kvm_pgtable_stage2_pgd_size(u64 vtcr)
 {
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
-	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 }
@@ -1582,7 +1588,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
 	pgt->pgd = NULL;
 }
 
-void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
 	struct kvm_pgtable_walker walker = {
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d87c8fcc4c24f..986a2e6fb9004 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -223,12 +223,12 @@ static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
 {
 	struct page *page = container_of(head, struct page, rcu_head);
 	void *pgtable = page_to_virt(page);
-	u32 level = page_private(page);
+	s8 level = page_private(page);
 
 	kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
 }
 
-static void stage2_free_unlinked_table(void *addr, u32 level)
+static void stage2_free_unlinked_table(void *addr, s8 level)
 {
 	struct page *page = virt_to_page(addr);
 
@@ -804,13 +804,13 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 	struct kvm_pgtable pgt = {
 		.pgd		= (kvm_pteref_t)kvm->mm->pgd,
 		.ia_bits	= vabits_actual,
-		.start_level	= (KVM_PGTABLE_MAX_LEVELS -
-				   CONFIG_PGTABLE_LEVELS),
+		.start_level	= (KVM_PGTABLE_LAST_LEVEL -
+				   CONFIG_PGTABLE_LEVELS + 1),
 		.mm_ops		= &kvm_user_mm_ops,
 	};
 	unsigned long flags;
 	kvm_pte_t pte = 0;	/* Keep GCC quiet... */
-	u32 level = ~0;
+	s8 level = S8_MAX;
 	int ret;
 
 	/*
@@ -829,7 +829,9 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 	 * Not seeing an error, but not updating level? Something went
 	 * deeply wrong...
 	 */
-	if (WARN_ON(level >= KVM_PGTABLE_MAX_LEVELS))
+	if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
+		return -EFAULT;
+	if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL))
 		return -EFAULT;
 
 	/* Oops, the userspace PTs are gone... Replay the fault */
@@ -1388,7 +1390,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
+	s8 fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
-- 
GitLab


From 0abc1b11a032199bb134fd25cd7ee0cdb26b7b03 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 27 Nov 2023 11:17:34 +0000
Subject: [PATCH 0532/4076] KVM: arm64: Support up to 5 levels of translation
 in kvm_pgtable

FEAT_LPA2 increases the maximum levels of translation from 4 to 5 for
the 4KB page case, when IA is >48 bits. While we can still use 4 levels
for stage2 translation in this case (due to stage2 allowing concatenated
page tables for first level lookup), the same kvm_pgtable library is
used for the hyp stage1 page tables and stage1 does not support
concatenation.

Therefore, modify the library to support up to 5 levels. Previous
patches already laid the groundwork for this by refactoring code to work
in terms of KVM_PGTABLE_FIRST_LEVEL and KVM_PGTABLE_LAST_LEVEL. So we
just need to change these macros.

The hardware sometimes encodes the new level differently from the
others: One such place is when reading the level from the FSC field in
the ESR_EL2 register. We never expect to see the lowest level (-1) here
since the stage 2 page tables always use concatenated tables for first
level lookup and therefore only use 4 levels of lookup. So we get away
with just adding a comment to explain why we are not being careful about
decoding level -1.

For stage2 VTCR_EL2.SL2 is introduced to encode the new start level.
However, since we always use concatenated page tables for first level
look up at stage2 (and therefore we will never need the new extra level)
we never touch this new field.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231127111737.1897081-10-ryan.roberts@arm.com
---
 arch/arm64/include/asm/kvm_emulate.h | 10 ++++++++++
 arch/arm64/include/asm/kvm_pgtable.h |  2 +-
 arch/arm64/kvm/hyp/pgtable.c         |  9 +++++++++
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 13fd9dbf2d1dd..d4f1e9cdd5546 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -411,6 +411,16 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vc
 
 static __always_inline s8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
 {
+	/*
+	 * Note: With the introduction of FEAT_LPA2 an extra level of
+	 * translation (level -1) is added. This level (obviously) doesn't
+	 * follow the previous convention of encoding the 4 levels in the 2 LSBs
+	 * of the FSC so this function breaks if the fault is for level -1.
+	 *
+	 * However, stage2 tables always use concatenated tables for first level
+	 * lookup and therefore it is guaranteed that the level will be between
+	 * 0 and 3, and this function continues to work.
+	 */
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
 }
 
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 3253828e453d5..cfdf40f734b12 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -11,7 +11,7 @@
 #include <linux/kvm_host.h>
 #include <linux/types.h>
 
-#define KVM_PGTABLE_FIRST_LEVEL		0
+#define KVM_PGTABLE_FIRST_LEVEL		-1
 #define KVM_PGTABLE_LAST_LEVEL		3
 
 /*
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 744bded18e993..c651df904fe3e 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -645,6 +645,15 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 	lvls = stage2_pgtable_levels(phys_shift);
 	if (lvls < 2)
 		lvls = 2;
+
+	/*
+	 * When LPA2 is enabled, the HW supports an extra level of translation
+	 * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2
+	 * to as an addition to SL0 to enable encoding this extra start level.
+	 * However, since we always use concatenated pages for the first level
+	 * lookup, we will never need this extra level and therefore do not need
+	 * to touch SL2.
+	 */
 	vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);
 
 #ifdef CONFIG_ARM64_HW_AFDBM
-- 
GitLab


From d782ac5b2ceebee5d374e13e990655d1a140d3a6 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 27 Nov 2023 11:17:35 +0000
Subject: [PATCH 0533/4076] KVM: arm64: Allow guests with >48-bit IPA size on
 FEAT_LPA2 systems

With all the page-table infrastructure in place, we can finally increase
the maximum permisable IPA size to 52-bits on 4KB and 16KB page systems
that have FEAT_LPA2.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231127111737.1897081-11-ryan.roberts@arm.com
---
 arch/arm64/kvm/reset.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 5bb4de162cab5..68d1d05672bd4 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -280,12 +280,11 @@ int __init kvm_set_ipa_limit(void)
 	parange = cpuid_feature_extract_unsigned_field(mmfr0,
 				ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 	/*
-	 * IPA size beyond 48 bits could not be supported
-	 * on either 4K or 16K page size. Hence let's cap
-	 * it to 48 bits, in case it's reported as larger
-	 * on the system.
+	 * IPA size beyond 48 bits for 4K and 16K page size is only supported
+	 * when LPA2 is available. So if we have LPA2, enable it, else cap to 48
+	 * bits, in case it's reported as larger on the system.
 	 */
-	if (PAGE_SIZE != SZ_64K)
+	if (!kvm_lpa2_is_enabled() && PAGE_SIZE != SZ_64K)
 		parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48);
 
 	/*
-- 
GitLab


From 72324ac52ddddb168d8008e36d6a617b9b74f6c1 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 27 Nov 2023 11:17:36 +0000
Subject: [PATCH 0534/4076] KVM: selftests: arm64: Determine max ipa size
 per-page size

We are about to add 52 bit PA guest modes for 4K and 16K pages when the
system supports LPA2. In preparation beef up the logic that parses mmfr0
to also tell us what the maximum supported PA size is for each page
size. Max PA size = 0 implies the page size is not supported at all.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231127111737.1897081-12-ryan.roberts@arm.com
---
 .../selftests/kvm/include/aarch64/processor.h |  4 +-
 .../selftests/kvm/include/guest_modes.h       |  4 +-
 .../selftests/kvm/lib/aarch64/processor.c     | 30 ++++++++++--
 tools/testing/selftests/kvm/lib/guest_modes.c | 48 ++++++++-----------
 4 files changed, 50 insertions(+), 36 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index c42d683102c7a..cf20e44e86f2f 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -119,8 +119,8 @@ enum {
 /* Access flag update enable/disable */
 #define TCR_EL1_HA		(1ULL << 39)
 
-void aarch64_get_supported_page_sizes(uint32_t ipa,
-				      bool *ps4k, bool *ps16k, bool *ps64k);
+void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
+					uint32_t *ipa16k, uint32_t *ipa64k);
 
 void vm_init_descriptor_tables(struct kvm_vm *vm);
 void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu);
diff --git a/tools/testing/selftests/kvm/include/guest_modes.h b/tools/testing/selftests/kvm/include/guest_modes.h
index b691df33e64e1..63f5167397ccb 100644
--- a/tools/testing/selftests/kvm/include/guest_modes.h
+++ b/tools/testing/selftests/kvm/include/guest_modes.h
@@ -11,8 +11,8 @@ struct guest_mode {
 
 extern struct guest_mode guest_modes[NUM_VM_MODES];
 
-#define guest_mode_append(mode, supported, enabled) ({ \
-	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+#define guest_mode_append(mode, enabled) ({ \
+	guest_modes[mode] = (struct guest_mode){ (enabled), (enabled) }; \
 })
 
 void guest_modes_append_default(void);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 6fe12e985ba56..e6ffd9037c373 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -492,12 +492,24 @@ uint32_t guest_get_vcpuid(void)
 	return read_sysreg(tpidr_el1);
 }
 
-void aarch64_get_supported_page_sizes(uint32_t ipa,
-				      bool *ps4k, bool *ps16k, bool *ps64k)
+static uint32_t max_ipa_for_page_size(uint32_t vm_ipa, uint32_t gran,
+				uint32_t not_sup_val, uint32_t ipa52_min_val)
+{
+	if (gran == not_sup_val)
+		return 0;
+	else if (gran >= ipa52_min_val && vm_ipa >= 52)
+		return 52;
+	else
+		return min(vm_ipa, 48U);
+}
+
+void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
+					uint32_t *ipa16k, uint32_t *ipa64k)
 {
 	struct kvm_vcpu_init preferred_init;
 	int kvm_fd, vm_fd, vcpu_fd, err;
 	uint64_t val;
+	uint32_t gran;
 	struct kvm_one_reg reg = {
 		.id	= KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1),
 		.addr	= (uint64_t)&val,
@@ -518,9 +530,17 @@ void aarch64_get_supported_page_sizes(uint32_t ipa,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	*ps4k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val) != 0xf;
-	*ps64k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val) == 0;
-	*ps16k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val) != 0;
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val);
+	*ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI,
+					ID_AA64MMFR0_EL1_TGRAN4_52_BIT);
+
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val);
+	*ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI,
+					ID_AA64MMFR0_EL1_TGRAN64_IMP);
+
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val);
+	*ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI,
+					ID_AA64MMFR0_EL1_TGRAN16_52_BIT);
 
 	close(vcpu_fd);
 	close(vm_fd);
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index 1df3ce4b16fd8..772a7dd15db48 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -14,37 +14,31 @@ struct guest_mode guest_modes[NUM_VM_MODES];
 void guest_modes_append_default(void)
 {
 #ifndef __aarch64__
-	guest_mode_append(VM_MODE_DEFAULT, true, true);
+	guest_mode_append(VM_MODE_DEFAULT, true);
 #else
 	{
 		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-		bool ps4k, ps16k, ps64k;
+		uint32_t ipa4k, ipa16k, ipa64k;
 		int i;
 
-		aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k);
+		aarch64_get_supported_page_sizes(limit, &ipa4k, &ipa16k, &ipa64k);
 
-		vm_mode_default = NUM_VM_MODES;
+		guest_mode_append(VM_MODE_P52V48_64K, ipa64k >= 52);
 
-		if (limit >= 52)
-			guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k);
-		if (limit >= 48) {
-			guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k);
-		}
-		if (limit >= 40) {
-			guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k);
-			if (ps4k)
-				vm_mode_default = VM_MODE_P40V48_4K;
-		}
-		if (limit >= 36) {
-			guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k);
-			guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k);
-		}
+		guest_mode_append(VM_MODE_P48V48_4K, ipa4k >= 48);
+		guest_mode_append(VM_MODE_P48V48_16K, ipa16k >= 48);
+		guest_mode_append(VM_MODE_P48V48_64K, ipa64k >= 48);
+
+		guest_mode_append(VM_MODE_P40V48_4K, ipa4k >= 40);
+		guest_mode_append(VM_MODE_P40V48_16K, ipa16k >= 40);
+		guest_mode_append(VM_MODE_P40V48_64K, ipa64k >= 40);
+
+		guest_mode_append(VM_MODE_P36V48_4K, ipa4k >= 36);
+		guest_mode_append(VM_MODE_P36V48_16K, ipa16k >= 36);
+		guest_mode_append(VM_MODE_P36V48_64K, ipa64k >= 36);
+		guest_mode_append(VM_MODE_P36V47_16K, ipa16k >= 36);
+
+		vm_mode_default = ipa4k >= 40 ? VM_MODE_P40V48_4K : NUM_VM_MODES;
 
 		/*
 		 * Pick the first supported IPA size if the default
@@ -72,7 +66,7 @@ void guest_modes_append_default(void)
 		close(kvm_fd);
 		/* Starting with z13 we have 47bits of physical address */
 		if (info.ibc >= 0x30)
-			guest_mode_append(VM_MODE_P47V64_4K, true, true);
+			guest_mode_append(VM_MODE_P47V64_4K, true);
 	}
 #endif
 #ifdef __riscv
@@ -80,9 +74,9 @@ void guest_modes_append_default(void)
 		unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS);
 
 		if (sz >= 52)
-			guest_mode_append(VM_MODE_P52V48_4K, true, true);
+			guest_mode_append(VM_MODE_P52V48_4K, true);
 		if (sz >= 48)
-			guest_mode_append(VM_MODE_P48V48_4K, true, true);
+			guest_mode_append(VM_MODE_P48V48_4K, true);
 	}
 #endif
 }
-- 
GitLab


From 10a0cc3b688fcf753ff3f6518bb15e7a6809e908 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 27 Nov 2023 11:17:37 +0000
Subject: [PATCH 0535/4076] KVM: selftests: arm64: Support P52V48 4K and 16K
 guest_modes

Add support for VM_MODE_P52V48_4K and VM_MODE_P52V48_16K guest modes by
using the FEAT_LPA2 pte format for stage1, when FEAT_LPA2 is available.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231127111737.1897081-13-ryan.roberts@arm.com
---
 .../selftests/kvm/include/kvm_util_base.h     |  1 +
 .../selftests/kvm/lib/aarch64/processor.c     | 39 ++++++++++++++-----
 tools/testing/selftests/kvm/lib/guest_modes.c |  2 +
 tools/testing/selftests/kvm/lib/kvm_util.c    |  3 ++
 4 files changed, 36 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index a18db6a7b3cf4..406500fb6e284 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -171,6 +171,7 @@ static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm,
 
 enum vm_guest_mode {
 	VM_MODE_P52V48_4K,
+	VM_MODE_P52V48_16K,
 	VM_MODE_P52V48_64K,
 	VM_MODE_P48V48_4K,
 	VM_MODE_P48V48_16K,
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index e6ffd9037c373..41c776b642c0c 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -12,6 +12,7 @@
 #include "kvm_util.h"
 #include "processor.h"
 #include <linux/bitfield.h>
+#include <linux/sizes.h>
 
 #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
 
@@ -58,13 +59,25 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva)
 	return (gva >> vm->page_shift) & mask;
 }
 
+static inline bool use_lpa2_pte_format(struct kvm_vm *vm)
+{
+	return (vm->page_size == SZ_4K || vm->page_size == SZ_16K) &&
+	    (vm->pa_bits > 48 || vm->va_bits > 48);
+}
+
 static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs)
 {
 	uint64_t pte;
 
-	pte = pa & GENMASK(47, vm->page_shift);
-	if (vm->page_shift == 16)
-		pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+	if (use_lpa2_pte_format(vm)) {
+		pte = pa & GENMASK(49, vm->page_shift);
+		pte |= FIELD_GET(GENMASK(51, 50), pa) << 8;
+		attrs &= ~GENMASK(9, 8);
+	} else {
+		pte = pa & GENMASK(47, vm->page_shift);
+		if (vm->page_shift == 16)
+			pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+	}
 	pte |= attrs;
 
 	return pte;
@@ -74,9 +87,14 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte)
 {
 	uint64_t pa;
 
-	pa = pte & GENMASK(47, vm->page_shift);
-	if (vm->page_shift == 16)
-		pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+	if (use_lpa2_pte_format(vm)) {
+		pa = pte & GENMASK(49, vm->page_shift);
+		pa |= FIELD_GET(GENMASK(9, 8), pte) << 50;
+	} else {
+		pa = pte & GENMASK(47, vm->page_shift);
+		if (vm->page_shift == 16)
+			pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+	}
 
 	return pa;
 }
@@ -266,9 +284,6 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 
 	/* Configure base granule size */
 	switch (vm->mode) {
-	case VM_MODE_P52V48_4K:
-		TEST_FAIL("AArch64 does not support 4K sized pages "
-			  "with 52-bit physical address ranges");
 	case VM_MODE_PXXV48_4K:
 		TEST_FAIL("AArch64 does not support 4K sized pages "
 			  "with ANY-bit physical address ranges");
@@ -278,12 +293,14 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	case VM_MODE_P36V48_64K:
 		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
 		break;
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P36V48_16K:
 	case VM_MODE_P36V47_16K:
 		tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
 		break;
+	case VM_MODE_P52V48_4K:
 	case VM_MODE_P48V48_4K:
 	case VM_MODE_P40V48_4K:
 	case VM_MODE_P36V48_4K:
@@ -297,6 +314,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 
 	/* Configure output size */
 	switch (vm->mode) {
+	case VM_MODE_P52V48_4K:
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P52V48_64K:
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
 		ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2;
@@ -325,6 +344,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	/* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
 	tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
 	tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+	if (use_lpa2_pte_format(vm))
+		tcr_el1 |= (1ul << 59) /* DS */;
 
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1);
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1);
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index 772a7dd15db48..b04901e551387 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -23,6 +23,8 @@ void guest_modes_append_default(void)
 
 		aarch64_get_supported_page_sizes(limit, &ipa4k, &ipa16k, &ipa64k);
 
+		guest_mode_append(VM_MODE_P52V48_4K, ipa4k >= 52);
+		guest_mode_append(VM_MODE_P52V48_16K, ipa16k >= 52);
 		guest_mode_append(VM_MODE_P52V48_64K, ipa64k >= 52);
 
 		guest_mode_append(VM_MODE_P48V48_4K, ipa4k >= 48);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 7a8af1821f5da..aeba7a23105c6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -148,6 +148,7 @@ const char *vm_guest_mode_string(uint32_t i)
 {
 	static const char * const strings[] = {
 		[VM_MODE_P52V48_4K]	= "PA-bits:52,  VA-bits:48,  4K pages",
+		[VM_MODE_P52V48_16K]	= "PA-bits:52,  VA-bits:48, 16K pages",
 		[VM_MODE_P52V48_64K]	= "PA-bits:52,  VA-bits:48, 64K pages",
 		[VM_MODE_P48V48_4K]	= "PA-bits:48,  VA-bits:48,  4K pages",
 		[VM_MODE_P48V48_16K]	= "PA-bits:48,  VA-bits:48, 16K pages",
@@ -173,6 +174,7 @@ const char *vm_guest_mode_string(uint32_t i)
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
+	[VM_MODE_P52V48_16K]	= { 52, 48,  0x4000, 14 },
 	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
 	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
 	[VM_MODE_P48V48_16K]	= { 48, 48,  0x4000, 14 },
@@ -251,6 +253,7 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 	case VM_MODE_P36V48_64K:
 		vm->pgtable_levels = 3;
 		break;
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P36V48_16K:
-- 
GitLab


From 8aa1e6e29a21f6bb99dcaa64d11e97a21f0f9dc1 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Wed, 22 Nov 2023 10:27:03 +0100
Subject: [PATCH 0536/4076] perf report: Remove warning on missing raw data for
 s390

Command

   # ./perf report -i /tmp/111 -D > /dev/null

emits an error message when a sample for event CRYPTO_ALL in the
perf.data file does not contain any raw data. This is ok.  Do not
trigger this warning when the sample in the perf.data files does not
contain any raw data at all.  Check for availability of raw data for all
events and return if none is available.

Output before:

  # ./perf report -i /tmp/111 -D > /dev/null
  Invalid CRYPTO_ALL raw data encountered
  Invalid CRYPTO_ALL raw data encountered
  Invalid CRYPTO_ALL raw data encountered
  #

Output after:

  # ./perf report -i /tmp/111 -D > /dev/null
  #

Fixes: b539deafbadb2fc6 ("perf report: Add s390 raw data interpretation for PAI counters")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20231122092703.3163191-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/s390-sample-raw.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index 29a744eeb71eb..53383e97ec9d5 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -51,8 +51,6 @@ static bool s390_cpumcfdg_testctr(struct perf_sample *sample)
 	struct cf_trailer_entry *te;
 	struct cf_ctrset_entry *cep, ce;
 
-	if (!len)
-		return false;
 	while (offset < len) {
 		cep = (struct cf_ctrset_entry *)(buf + offset);
 		ce.def = be16_to_cpu(cep->def);
@@ -234,10 +232,9 @@ struct pai_data {		/* Event number and value */
  */
 static bool s390_pai_all_test(struct perf_sample *sample)
 {
-	unsigned char *buf = sample->raw_data;
 	size_t len = sample->raw_size;
 
-	if (len < 0xa || !buf)
+	if (len < 0xa)
 		return false;
 	return true;
 }
@@ -299,6 +296,10 @@ void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event,
 	if (!evsel)
 		return;
 
+	/* Check for raw data in sample */
+	if (!sample->raw_size || !sample->raw_data)
+		return;
+
 	/* Display raw data on screen */
 	if (evsel->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) {
 		if (!evsel->pmu)
-- 
GitLab


From 70df07838fc1c0acfab3325ae79014e241a88bdf Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 23 Nov 2023 09:58:41 +0200
Subject: [PATCH 0537/4076] perf header: Fix segfault on build_mem_topology()
 error path

Do not increase the node count unless a node has been successfully read,
because it can lead to a segfault if an error occurs.

For example, if perf exceeds the open file limit in memory_node__read(),
which, on a test system, could be made to happen by setting the file limit
to exactly 32:

 Before:

  $ ulimit -n 32
  $ perf mem record --all-user -- sleep 1
  [ perf record: Woken up 1 times to write data ]
  failed: can't open memory sysfs data
  perf: Segmentation fault
  Obtained 14 stack frames.
  perf(sighandler_dump_stack+0x48) [0x55f4b1f59558]
  /lib/x86_64-linux-gnu/libc.so.6(+0x42520) [0x7f4ba1c42520]
  /lib/x86_64-linux-gnu/libc.so.6(free+0x1e) [0x7f4ba1ca53fe]
  perf(+0x178ff4) [0x55f4b1f48ff4]
  perf(+0x179a70) [0x55f4b1f49a70]
  perf(+0x17ef5d) [0x55f4b1f4ef5d]
  perf(+0x85c0b) [0x55f4b1e55c0b]
  perf(cmd_record+0xe1d) [0x55f4b1e5920d]
  perf(cmd_mem+0xc96) [0x55f4b1e80e56]
  perf(+0x130460) [0x55f4b1f00460]
  perf(main+0x689) [0x55f4b1e427d9]
  /lib/x86_64-linux-gnu/libc.so.6(+0x29d90) [0x7f4ba1c29d90]
  /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80) [0x7f4ba1c29e40]
  perf(_start+0x25) [0x55f4b1e42a25]
  Segmentation fault (core dumped)
  $

After:

  $ ulimit -n 32
  $ perf mem record --all-user -- sleep 1
  [ perf record: Woken up 1 times to write data ]
  failed: can't open memory sysfs data
  [ perf record: Captured and wrote 0.005 MB perf.data (11 samples) ]
  $

Fixes: f8e502b9d1b3b197 ("perf header: Ensure bitmaps are freed")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123075848.9652-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1c687b5789c0f..08cc2febabde2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1444,7 +1444,9 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp)
 			nodes = new_nodes;
 			size += 4;
 		}
-		ret = memory_node__read(&nodes[cnt++], idx);
+		ret = memory_node__read(&nodes[cnt], idx);
+		if (!ret)
+			cnt += 1;
 	}
 out:
 	closedir(dir);
-- 
GitLab


From 96ba5999e8d86138cea90422f8c00309a7eedd3b Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 23 Nov 2023 09:58:42 +0200
Subject: [PATCH 0538/4076] perf tests lib: Add perf_has_symbol.sh

Some shell tests depend on finding symbols for perf itself, and fail if
perf has been stripped and no debug object is available. Add helper
functions to check if perf has a needed symbol. This is preparation for
amending the tests themselves to be skipped if a needed symbol is not
found.

The functions make use of the "Symbols" test which reads and checks symbols
from a dso, perf itself by default. Note the "Symbols" test will find
symbols using the same method as other perf tests, including, for example,
looking in the buildid cache.

An alternative would be to prevent the needed symbols from being stripped,
which seems to work with gcc's externally_visible attribute, but that
attribute is not supported by clang.

Another alternative would be to use option -Wl,-E (which is already used
when perf is built with perl support) which causes the linker to add all
(global) symbols to the dynamic symbol table. Then the required symbols
need only be made global in scope to avoid being strippable. However that
goes beyond what is needed.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123075848.9652-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/lib/perf_has_symbol.sh | 21 +++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 tools/perf/tests/shell/lib/perf_has_symbol.sh

diff --git a/tools/perf/tests/shell/lib/perf_has_symbol.sh b/tools/perf/tests/shell/lib/perf_has_symbol.sh
new file mode 100644
index 0000000000000..5d59c32ae3e7b
--- /dev/null
+++ b/tools/perf/tests/shell/lib/perf_has_symbol.sh
@@ -0,0 +1,21 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+perf_has_symbol()
+{
+	if perf test -vv "Symbols" 2>&1 | grep "[[:space:]]$1$"; then
+		echo "perf does have symbol '$1'"
+		return 0
+	fi
+	echo "perf does not have symbol '$1'"
+	return 1
+}
+
+skip_test_missing_symbol()
+{
+	if ! perf_has_symbol "$1" ; then
+		echo "perf is missing symbols - skipping test"
+		exit 2
+	fi
+	return 0
+}
-- 
GitLab


From c9526a735082bba57da322332cbcef1bbdff5698 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 23 Nov 2023 09:58:43 +0200
Subject: [PATCH 0539/4076] perf tests: Skip pipe test if noploop symbol is
 missing

perf pipe recording and injection test depends on finding symbol noploop in
perf, and fails if perf has been stripped and no debug object is available.
In that case, skip the test instead.

Example:

 Before:

  $ strip tools/perf/perf
  $ tools/perf/perf buildid-cache -p `realpath tools/perf/perf`
  $ tools/perf/perf test -v pipe
   86: perf pipe recording and injection test                          :
  --- start ---
  test child forked, pid 47734
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.000 MB - ]
       47741    47741       -1 |perf
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.000 MB - ]
  cannot find noploop function in pipe #1
  test child finished with -1
  ---- end ----
  perf pipe recording and injection test: FAILED!

After:

  $ tools/perf/perf test -v pipe
   86: perf pipe recording and injection test                          :
  --- start ---
  test child forked, pid 48996
  perf does not have symbol 'noploop'
  perf is missing symbols - skipping test
  test child finished with -2
  ---- end ----
  perf pipe recording and injection test: Skip

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123075848.9652-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/pipe_test.sh | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/pipe_test.sh b/tools/perf/tests/shell/pipe_test.sh
index 8dd115dd35a7e..a78d35d2cff07 100755
--- a/tools/perf/tests/shell/pipe_test.sh
+++ b/tools/perf/tests/shell/pipe_test.sh
@@ -2,10 +2,17 @@
 # perf pipe recording and injection test
 # SPDX-License-Identifier: GPL-2.0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+sym="noploop"
+
+skip_test_missing_symbol ${sym}
+
 data=$(mktemp /tmp/perf.data.XXXXXX)
 prog="perf test -w noploop"
 task="perf"
-sym="noploop"
 
 if ! perf record -e task-clock:u -o - ${prog} | perf report -i - --task | grep ${task}; then
 	echo "cannot find the test file in the perf report"
-- 
GitLab


From 3c489dbe69c155c86c4460491d11520cf8ec3637 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 23 Nov 2023 09:58:44 +0200
Subject: [PATCH 0540/4076] perf tests: Skip record test if test_loop symbol is
 missing

perf record test depends on finding symbol test_loop in perf, and fails if
perf has been stripped and no debug object is available. In that case, skip
the test instead.

Example:

 Note, building with perl support adds option -Wl,-E which causes the
 linker to add all (global) symbols to the dynamic symbol table. So the
 test_loop symbol, being global, does not get stripped unless NO_LIBPERL=1

 Before:

  $ make NO_LIBPERL=1 -C tools/perf >/dev/null 2>&1
  $ strip tools/perf/perf
  $ tools/perf/perf buildid-cache -p `realpath tools/perf/perf`
  $ tools/perf/perf test -v 'record tests'
   91: perf record tests                                               :
  --- start ---
  test child forked, pid 118750
  Basic --per-thread mode test
  Per-thread record [Failed missing output]
  Register capture test
  Register capture test [Success]
  Basic --system-wide mode test
  System-wide record [Skipped not supported]
  Basic target workload test
  Workload record [Failed missing output]
  test child finished with -1
  ---- end ----
  perf record tests: FAILED!

 After:

  $ tools/perf/perf test -v 'record tests'
   91: perf record tests                                               :
  --- start ---
  test child forked, pid 120025
  perf does not have symbol 'test_loop'
  perf is missing symbols - skipping test
  test child finished with -2
  ---- end ----
  perf record tests: Skip

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123075848.9652-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record.sh | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index c74412c68e65a..3d1a7759a7b2d 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -8,10 +8,16 @@ shelldir=$(dirname "$0")
 # shellcheck source=lib/waiting.sh
 . "${shelldir}"/lib/waiting.sh
 
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+testsym="test_loop"
+
+skip_test_missing_symbol ${testsym}
+
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 testprog="perf test -w thloop"
-testsym="test_loop"
 cpu_pmu_dir="/sys/bus/event_source/devices/cpu*"
 br_cntr_file="/caps/branch_counter_nr"
 br_cntr_output="branch stack counters"
-- 
GitLab


From fc1de29a8b8ad46b590b2d389b53b4ecf9758273 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 23 Nov 2023 09:58:45 +0200
Subject: [PATCH 0541/4076] perf tests: Skip Arm64 callgraphs test if leafloop
 symbol is missing

The test "Check Arm64 callgraphs are complete in fp mode" depends on
finding symbol leafloop in perf, and fails if perf has been stripped and no
debug object is available. In that case, skip the test instead.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123075848.9652-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/test_arm_callgraph_fp.sh | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
index 66dfdfdad553f..e342e6c8aa50c 100755
--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -2,8 +2,14 @@
 # Check Arm64 callgraphs are complete in fp mode
 # SPDX-License-Identifier: GPL-2.0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 lscpu | grep -q "aarch64" || exit 2
 
+skip_test_missing_symbol leafloop
+
 PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 TEST_PROGRAM="perf test -w leafloop"
 
-- 
GitLab


From fcfb5a6189f55669c931dce9fec85280655c515f Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 23 Nov 2023 09:58:46 +0200
Subject: [PATCH 0542/4076] perf tests: Skip branch stack sampling test if
 brstack_bench symbol is missing

The test "Check branch stack sampling" depends on finding symbol
brstack_bench (and several others) in perf, and fails if perf has been
stripped and no debug object is available. In that case, skip the test
instead.

Example:

 Before:

  $ strip tools/perf/perf
  $ tools/perf/perf buildid-cache -p `realpath tools/perf/perf`
  $ tools/perf/perf test -v 'branch stack sampling'
  112: Check branch stack sampling                                     :
  --- start ---
  test child forked, pid 123741
  Testing user branch stack sampling
  + grep -E -m1 ^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL/.*$ /tmp/__perf_test.program.5Dz1U/perf.script
  + cleanup
  + rm -rf /tmp/__perf_test.program.5Dz1U
  test child finished with -1
  ---- end ----
  Check branch stack sampling: FAILED!

 After:

  $ tools/perf/perf test -v 'branch stack sampling'
  112: Check branch stack sampling                                     :
  --- start ---
  test child forked, pid 125157
  perf does not have symbol 'brstack_bench'
  perf is missing symbols - skipping test
  test child finished with -2
  ---- end ----
  Check branch stack sampling: Skip

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123075848.9652-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/test_brstack.sh | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index 09908d71c9941..5f14d0cb013f8 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -4,6 +4,10 @@
 # SPDX-License-Identifier: GPL-2.0
 # German Gomez <german.gomez@arm.com>, 2022
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 # skip the test if the hardware doesn't support branch stack sampling
 # and if the architecture doesn't support filter types: any,save_type,u
 if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev/null 2>&1 ; then
@@ -11,6 +15,8 @@ if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev
 	exit 2
 fi
 
+skip_test_missing_symbol brstack_bench
+
 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
 TESTPROG="perf test -w brstack"
 
-- 
GitLab


From 3b24b15cf6fb2dbe1d009a52c9ddcb7721503d8f Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 23 Nov 2023 09:58:47 +0200
Subject: [PATCH 0543/4076] perf tests: Make data symbol test wait for perf to
 start

The perf data symbol test waits 1 second for perf to run and collect data,
which may be too little if perf takes a long time to start up, which has
been noticed on systems with many CPUs. Use existing wait_for_perf_to_start
helper to wait for perf to start.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123075848.9652-8-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/test_data_symbol.sh | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
index 69bb6fe86c507..e50e54e94f6ff 100755
--- a/tools/perf/tests/shell/test_data_symbol.sh
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -4,6 +4,10 @@
 # SPDX-License-Identifier: GPL-2.0
 # Leo Yan <leo.yan@linaro.org>, 2022
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/waiting.sh
+. "${shelldir}"/lib/waiting.sh
+
 skip_if_no_mem_event() {
 	perf mem record -e list 2>&1 | grep -E -q 'available' && return 0
 	return 2
@@ -13,6 +17,7 @@ skip_if_no_mem_event || exit 2
 
 TEST_PROGRAM="perf test -w datasym"
 PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+ERR_FILE=$(mktemp /tmp/__perf_test.stderr.XXXXX)
 
 check_result() {
 	# The memory report format is as below:
@@ -50,13 +55,15 @@ echo "Recording workload..."
 # specific CPU and test in per-CPU mode.
 is_amd=$(grep -E -c 'vendor_id.*AuthenticAMD' /proc/cpuinfo)
 if (($is_amd >= 1)); then
-	perf mem record -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM &
+	perf mem record -vvv -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM 2>"${ERR_FILE}" &
 else
-	perf mem record --all-user -o ${PERF_DATA} -- $TEST_PROGRAM &
+	perf mem record -vvv --all-user -o ${PERF_DATA} -- $TEST_PROGRAM 2>"${ERR_FILE}" &
 fi
 
 PERFPID=$!
 
+wait_for_perf_to_start ${PERFPID} "${ERR_FILE}"
+
 sleep 1
 
 kill $PERFPID
-- 
GitLab


From 124bf6360ad8fe9267017d10b5dd465d4af73247 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 23 Nov 2023 09:58:48 +0200
Subject: [PATCH 0544/4076] perf tests: Skip data symbol test if buf1 symbol is
 missing

perf data symbol test depends on finding symbol buf1 in perf, and fails if
perf has been stripped and no debug object is available. In that case, skip
the test instead.

Example:

 Before:

  $ strip tools/perf/perf
  $ tools/perf/perf buildid-cache -p `realpath tools/perf/perf`
  $ tools/perf/perf test -v 'data symbol'
  113: Test data symbol                                                :
  --- start ---
  test child forked, pid 125646
  Recording workload...
  [ perf record: Woken up 3 times to write data ]
  [ perf record: Captured and wrote 0.577 MB /tmp/__perf_test.perf.data.Jhbdp (7794 samples) ]
  Cleaning up files...
  test child finished with -1
  ---- end ----
  Test data symbol: FAILED!

 After:

  $ tools/perf/perf test -v 'data symbol'
  113: Test data symbol                                                :
  --- start ---
  test child forked, pid 125747
  perf does not have symbol 'buf1'
  perf is missing symbols - skipping test
  test child finished with -2
  ---- end ----
  Test data symbol: Skip

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123075848.9652-9-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/test_data_symbol.sh | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
index e50e54e94f6ff..3dfa91832aa87 100755
--- a/tools/perf/tests/shell/test_data_symbol.sh
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -8,6 +8,9 @@ shelldir=$(dirname "$0")
 # shellcheck source=lib/waiting.sh
 . "${shelldir}"/lib/waiting.sh
 
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 skip_if_no_mem_event() {
 	perf mem record -e list 2>&1 | grep -E -q 'available' && return 0
 	return 2
@@ -15,6 +18,8 @@ skip_if_no_mem_event() {
 
 skip_if_no_mem_event || exit 2
 
+skip_test_missing_symbol buf1
+
 TEST_PROGRAM="perf test -w datasym"
 PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 ERR_FILE=$(mktemp /tmp/__perf_test.stderr.XXXXX)
-- 
GitLab


From 19dd49c9337a482325d4dd7000e328dac11f6b5c Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 9 Nov 2023 15:27:32 -0800
Subject: [PATCH 0545/4076] perf vendor events: Add skx, clx, icx and spr upi
 bandwidth metric

Add upi_data_receive_bw metric for skylakex, cascadelakex, icelakex
and sapphirerapids. The metric was added to perfmon metrics in:
https://github.com/intel/perfmon/pull/119

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231109232732.2973015-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json  | 6 ++++++
 tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json    | 6 ++++++
 .../pmu-events/arch/x86/sapphirerapids/spr-metrics.json     | 6 ++++++
 tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json    | 6 ++++++
 4 files changed, 24 insertions(+)

diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 84c132af3dfa5..8bc6c07078566 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -1862,6 +1862,12 @@
         "MetricName": "uncore_frequency",
         "ScaleUnit": "1GHz"
     },
+    {
+        "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)",
+        "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
+        "MetricName": "upi_data_receive_bw",
+        "ScaleUnit": "1MB/s"
+    },
     {
         "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)",
         "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
index e98602c667072..71d78a7841ea8 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
@@ -1846,6 +1846,12 @@
         "MetricName": "uncore_frequency",
         "ScaleUnit": "1GHz"
     },
+    {
+        "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)",
+        "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
+        "MetricName": "upi_data_receive_bw",
+        "ScaleUnit": "1MB/s"
+    },
     {
         "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)",
         "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index 06c6d67cb76b0..e31a4aac9f205 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -1964,6 +1964,12 @@
         "MetricName": "uncore_frequency",
         "ScaleUnit": "1GHz"
     },
+    {
+        "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)",
+        "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
+        "MetricName": "upi_data_receive_bw",
+        "ScaleUnit": "1MB/s"
+    },
     {
         "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)",
         "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 4a8f8eeb75255..ec3aa5ef00a3c 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -1806,6 +1806,12 @@
         "MetricName": "uncore_frequency",
         "ScaleUnit": "1GHz"
     },
+    {
+        "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)",
+        "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
+        "MetricName": "upi_data_receive_bw",
+        "ScaleUnit": "1MB/s"
+    },
     {
         "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)",
         "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time",
-- 
GitLab


From 7340c6df49df1b261892d287444c255d0a378063 Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@outlook.com>
Date: Wed, 22 Nov 2023 20:41:06 +0800
Subject: [PATCH 0546/4076] perf vendor events riscv: add T-HEAD C9xx JSON file

Add JSON file of T-HEAD C9xx series events.

The event idx (raw value) is summary as following:

event id range   | support cpu
 0x01 - 0x2a     |  c906,c910,c920

The event ids are based on the public document of T-HEAD and cover the
c900 series.

These events are the max that c900 series support.  Since T-HEAD let
manufacturers decide whether events are usable, the final support of the
perf events is determined by the pmu node of the soc dtb.

Signed-off-by: Inochi Amaoto <inochiama@outlook.com>
Tested-by: Guo Ren <guoren@kernel.org>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Chen Wang <unicorn_wang@outlook.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jisheng Zhang <jszhang@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wei Fu <wefu@redhat.com>
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/IA1PR20MB495325FCF603BAA841E29281BBBAA@IA1PR20MB4953.namprd20.prod.outlook.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/riscv/mapfile.csv  |  1 +
 .../arch/riscv/thead/c900-legacy/cache.json   | 67 ++++++++++++++++
 .../riscv/thead/c900-legacy/firmware.json     | 68 ++++++++++++++++
 .../riscv/thead/c900-legacy/instruction.json  | 72 +++++++++++++++++
 .../riscv/thead/c900-legacy/microarch.json    | 80 +++++++++++++++++++
 5 files changed, 288 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json
 create mode 100644 tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json
 create mode 100644 tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json
 create mode 100644 tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json

diff --git a/tools/perf/pmu-events/arch/riscv/mapfile.csv b/tools/perf/pmu-events/arch/riscv/mapfile.csv
index 56b03138d46aa..cfc449b198105 100644
--- a/tools/perf/pmu-events/arch/riscv/mapfile.csv
+++ b/tools/perf/pmu-events/arch/riscv/mapfile.csv
@@ -15,4 +15,5 @@
 #
 #MVENDORID-MARCHID-MIMPID,Version,Filename,EventType
 0x489-0x8000000000000007-0x[[:xdigit:]]+,v1,sifive/u74,core
+0x5b7-0x0-0x0,v1,thead/c900-legacy,core
 0x67e-0x80000000db0000[89]0-0x[[:xdigit:]]+,v1,starfive/dubhe-80,core
diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json
new file mode 100644
index 0000000000000..2b142348d6359
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json
@@ -0,0 +1,67 @@
+[
+  {
+    "EventName": "L1_ICACHE_ACCESS",
+    "EventCode": "0x00000001",
+    "BriefDescription": "L1 instruction cache access"
+  },
+  {
+    "EventName": "L1_ICACHE_MISS",
+    "EventCode": "0x00000002",
+    "BriefDescription": "L1 instruction cache miss"
+  },
+  {
+    "EventName": "ITLB_MISS",
+    "EventCode": "0x00000003",
+    "BriefDescription": "I-UTLB miss"
+  },
+  {
+    "EventName": "DTLB_MISS",
+    "EventCode": "0x00000004",
+    "BriefDescription": "D-UTLB miss"
+  },
+  {
+    "EventName": "JTLB_MISS",
+    "EventCode": "0x00000005",
+    "BriefDescription": "JTLB miss"
+  },
+  {
+    "EventName": "L1_DCACHE_READ_ACCESS",
+    "EventCode": "0x0000000c",
+    "BriefDescription": "L1 data cache read access"
+  },
+  {
+    "EventName": "L1_DCACHE_READ_MISS",
+    "EventCode": "0x0000000d",
+    "BriefDescription": "L1 data cache read miss"
+  },
+  {
+    "EventName": "L1_DCACHE_WRITE_ACCESS",
+    "EventCode": "0x0000000e",
+    "BriefDescription": "L1 data cache write access"
+  },
+  {
+    "EventName": "L1_DCACHE_WRITE_MISS",
+    "EventCode": "0x0000000f",
+    "BriefDescription": "L1 data cache write miss"
+  },
+  {
+    "EventName": "LL_CACHE_READ_ACCESS",
+    "EventCode": "0x00000010",
+    "BriefDescription": "LL Cache read access"
+  },
+  {
+    "EventName": "LL_CACHE_READ_MISS",
+    "EventCode": "0x00000011",
+    "BriefDescription": "LL Cache read miss"
+  },
+  {
+    "EventName": "LL_CACHE_WRITE_ACCESS",
+    "EventCode": "0x00000012",
+    "BriefDescription": "LL Cache write access"
+  },
+  {
+    "EventName": "LL_CACHE_WRITE_MISS",
+    "EventCode": "0x00000013",
+    "BriefDescription": "LL Cache write miss"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json
new file mode 100644
index 0000000000000..9b4a032186a7b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json
@@ -0,0 +1,68 @@
+[
+  {
+    "ArchStdEvent": "FW_MISALIGNED_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_MISALIGNED_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ILLEGAL_INSN"
+  },
+  {
+    "ArchStdEvent": "FW_SET_TIMER"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_RECEIVED"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json
new file mode 100644
index 0000000000000..c822b53733339
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json
@@ -0,0 +1,72 @@
+[
+  {
+    "EventName": "INST_BRANCH_MISPREDICT",
+    "EventCode": "0x00000006",
+    "BriefDescription": "Mispredicted branch instructions"
+  },
+  {
+    "EventName": "INST_BRANCH",
+    "EventCode": "0x00000007",
+    "BriefDescription": "Retired branch instructions"
+  },
+  {
+    "EventName": "INST_JMP_MISPREDICT",
+    "EventCode": "0x00000008",
+    "BriefDescription": "Indirect branch mispredict"
+  },
+  {
+    "EventName": "INST_JMP",
+    "EventCode": "0x00000009",
+    "BriefDescription": "Retired jmp instructions"
+  },
+  {
+    "EventName": "INST_STORE",
+    "EventCode": "0x0000000b",
+    "BriefDescription": "Retired store instructions"
+  },
+  {
+    "EventName": "INST_ALU",
+    "EventCode": "0x0000001d",
+    "BriefDescription": "Retired ALU instructions"
+  },
+  {
+    "EventName": "INST_LDST",
+    "EventCode": "0x0000001e",
+    "BriefDescription": "Retired Load/Store instructions"
+  },
+  {
+    "EventName": "INST_VECTOR",
+    "EventCode": "0x0000001f",
+    "BriefDescription": "Retired Vector instructions"
+  },
+  {
+    "EventName": "INST_CSR",
+    "EventCode": "0x00000020",
+    "BriefDescription": "Retired CSR instructions"
+  },
+  {
+    "EventName": "INST_SYNC",
+    "EventCode": "0x00000021",
+    "BriefDescription": "Retired sync instructions (AMO/LR/SC instructions)"
+  },
+  {
+    "EventName": "INST_UNALIGNED_ACCESS",
+    "EventCode": "0x00000022",
+    "BriefDescription": "Retired Store/Load instructions with unaligned memory access"
+  },
+  {
+    "EventName": "INST_ECALL",
+    "EventCode": "0x00000025",
+    "BriefDescription": "Retired ecall instructions"
+  },
+  {
+    "EventName": "INST_LONG_JP",
+    "EventCode": "0x00000026",
+    "BriefDescription": "Retired long jump instructions"
+  },
+  {
+    "EventName": "INST_FP",
+    "EventCode": "0x0000002a",
+    "BriefDescription": "Retired FPU instructions"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json
new file mode 100644
index 0000000000000..0ab6f288af91d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json
@@ -0,0 +1,80 @@
+[
+  {
+    "EventName": "LSU_SPEC_FAIL",
+    "EventCode": "0x0000000a",
+    "BriefDescription": "LSU speculation fail"
+  },
+  {
+    "EventName": "IDU_RF_PIPE_FAIL",
+    "EventCode": "0x00000014",
+    "BriefDescription": "Instruction decode unit launch pipeline failed in RF state"
+  },
+  {
+    "EventName": "IDU_RF_REG_FAIL",
+    "EventCode": "0x00000015",
+    "BriefDescription": "Instruction decode unit launch register file fail in RF state"
+  },
+  {
+    "EventName": "IDU_RF_INSTRUCTION",
+    "EventCode": "0x00000016",
+    "BriefDescription": "retired instruction count of Instruction decode unit in RF (Register File) stage"
+  },
+  {
+    "EventName": "LSU_4K_STALL",
+    "EventCode": "0x00000017",
+    "BriefDescription": "LSU stall times for long distance data access (Over 4K)",
+    "PublicDescription": "This stall occurs when translate virtual address with page offset over 4k"
+  },
+  {
+    "EventName": "LSU_OTHER_STALL",
+    "EventCode": "0x00000018",
+    "BriefDescription": "LSU stall times for other reasons (except the 4k stall)"
+  },
+  {
+    "EventName": "LSU_SQ_OTHER_DIS",
+    "EventCode": "0x00000019",
+    "BriefDescription": "LSU store queue discard others"
+  },
+  {
+    "EventName": "LSU_SQ_DATA_DISCARD",
+    "EventCode": "0x0000001a",
+    "BriefDescription": "LSU store queue discard data (uops)"
+  },
+  {
+    "EventName": "BRANCH_DIRECTION_MISPREDICTION",
+    "EventCode": "0x0000001b",
+    "BriefDescription": "Branch misprediction in BTB"
+  },
+  {
+    "EventName": "BRANCH_DIRECTION_PREDICTION",
+    "EventCode": "0x0000001c",
+    "BriefDescription": "All branch prediction in BTB",
+    "PublicDescription": "This event including both successful prediction and failed prediction in BTB"
+  },
+  {
+    "EventName": "INTERRUPT_ACK_COUNT",
+    "EventCode": "0x00000023",
+    "BriefDescription": "acknowledged interrupt count"
+  },
+  {
+    "EventName": "INTERRUPT_OFF_CYCLE",
+    "EventCode": "0x00000024",
+    "BriefDescription": "PLIC arbitration time when the interrupt is not responded",
+    "PublicDescription": "The arbitration time is recorded while meeting any of the following:\n- CPU is M-mode and MIE == 0\n- CPU is S-mode and delegation and SIE == 0\n"
+  },
+  {
+    "EventName": "IFU_STALLED_CYCLE",
+    "EventCode": "0x00000027",
+    "BriefDescription": "Number of stall cycles of the instruction fetch unit (IFU)."
+  },
+  {
+    "EventName": "IDU_STALLED_CYCLE",
+    "EventCode": "0x00000028",
+    "BriefDescription": "hpcp_backend_stall Number of stall cycles of the instruction decoding unit (IDU) and next-level pipeline unit."
+  },
+  {
+    "EventName": "SYNC_STALL",
+    "EventCode": "0x00000029",
+    "BriefDescription": "Sync instruction stall cycle fence/fence.i/sync/sfence"
+  }
+]
-- 
GitLab


From ffa96259ca5f02bbcecd2c45831e7632cd6d3485 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 13 Nov 2023 10:23:24 +0000
Subject: [PATCH 0547/4076] perf test: Use existing config value for objdump
 path

There is already an existing config value for changing the objdump path,
so instead of having two values that do the same thing, make 'perf test'
use annotate.objdump as well.

Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/ZU5Cx4LTrB5q0sIG@kernel.org
Link: https://lore.kernel.org/r/20231113102327.695386-1-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-config.txt | 8 ++------
 tools/perf/tests/builtin-test.c          | 2 +-
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 16398babd1ef5..379f9d7a8ab11 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -251,7 +251,8 @@ annotate.*::
 		addr2line binary to use for file names and line numbers.
 
 	annotate.objdump::
-		objdump binary to use for disassembly and annotations.
+		objdump binary to use for disassembly and annotations,
+		including in the 'perf test' command.
 
 	annotate.disassembler_style::
 		Use this to change the default disassembler style to some other value
@@ -722,11 +723,6 @@ session-<NAME>.*::
 		Defines new record session for daemon. The value is record's
 		command line without the 'record' keyword.
 
-test.*::
-
-	test.objdump::
-		objdump binary to use for disassembly and annotations.
-
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 113e92119e1d1..b8c21e81a021b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -518,7 +518,7 @@ static int run_workload(const char *work, int argc, const char **argv)
 static int perf_test__config(const char *var, const char *value,
 			     void *data __maybe_unused)
 {
-	if (!strcmp(var, "test.objdump"))
+	if (!strcmp(var, "annotate.objdump"))
 		test_objdump_path = value;
 
 	return 0;
-- 
GitLab


From 08973307d28311505b85216d724826e2ca21759e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 11 Oct 2023 20:50:25 -0700
Subject: [PATCH 0548/4076] perf annotate: Check if operand has multiple regs

It needs to check all possible information in an instruction.  Let's add
a field indicating if the operand has multiple registers.  I'll be used
to search type information like in an array access on x86 like:

  mov    0x10(%rax,%rbx,8), %rcx
             -------------
                 here

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231012035111.676789-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 36 ++++++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.h |  2 ++
 2 files changed, 38 insertions(+)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 3364edf30f50e..9a828dc601c75 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -85,6 +85,8 @@ struct arch {
 	struct		{
 		char comment_char;
 		char skip_functions_char;
+		char register_char;
+		char memory_ref_char;
 	} objdump;
 };
 
@@ -188,6 +190,8 @@ static struct arch architectures[] = {
 		.insn_suffix = "bwlq",
 		.objdump =  {
 			.comment_char = '#',
+			.register_char = '%',
+			.memory_ref_char = '(',
 		},
 	},
 	{
@@ -566,6 +570,34 @@ static struct ins_ops lock_ops = {
 	.scnprintf = lock__scnprintf,
 };
 
+/*
+ * Check if the operand has more than one registers like x86 SIB addressing:
+ *   0x1234(%rax, %rbx, 8)
+ *
+ * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
+ * the input string after 'memory_ref_char' if exists.
+ */
+static bool check_multi_regs(struct arch *arch, const char *op)
+{
+	int count = 0;
+
+	if (arch->objdump.register_char == 0)
+		return false;
+
+	if (arch->objdump.memory_ref_char) {
+		op = strchr(op, arch->objdump.memory_ref_char);
+		if (op == NULL)
+			return false;
+	}
+
+	while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
+		count++;
+		op++;
+	}
+
+	return count > 1;
+}
+
 static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
@@ -593,6 +625,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy
 	if (ops->source.raw == NULL)
 		return -1;
 
+	ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
+
 	target = skip_spaces(++s);
 	comment = strchr(s, arch->objdump.comment_char);
 
@@ -613,6 +647,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy
 	if (ops->target.raw == NULL)
 		goto out_free_source;
 
+	ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
+
 	if (comment == NULL)
 		return 0;
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index bc8b95e8b1be1..b64a2be287b30 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -39,12 +39,14 @@ struct ins_operands {
 		s64	offset;
 		bool	offset_avail;
 		bool	outside;
+		bool	multi_regs;
 	} target;
 	union {
 		struct {
 			char	*raw;
 			char	*name;
 			u64	addr;
+			bool	multi_regs;
 		} source;
 		struct {
 			struct ins	    ins;
-- 
GitLab


From ea3ba10f2961f08155bb66c0b1b8088652ca5f28 Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@kontron.de>
Date: Mon, 27 Nov 2023 12:22:24 +0100
Subject: [PATCH 0549/4076] usb: misc: onboard_usb_hub: Print symbolic error
 names

Instead of printing the decimal error codes, let's use the more
human-readable symbolic error names provided by the %pe printk
format specifier.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Link: https://lore.kernel.org/r/20231127112234.109073-1-frieder@fris.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/onboard_usb_hub.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index 2b45404e9732c..6d122772a9706 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -7,6 +7,7 @@
 
 #include <linux/device.h>
 #include <linux/export.h>
+#include <linux/err.h>
 #include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -68,7 +69,7 @@ static int onboard_hub_power_on(struct onboard_hub *hub)
 
 	err = regulator_bulk_enable(hub->pdata->num_supplies, hub->supplies);
 	if (err) {
-		dev_err(hub->dev, "failed to enable supplies: %d\n", err);
+		dev_err(hub->dev, "failed to enable supplies: %pe\n", ERR_PTR(err));
 		return err;
 	}
 
@@ -88,7 +89,7 @@ static int onboard_hub_power_off(struct onboard_hub *hub)
 
 	err = regulator_bulk_disable(hub->pdata->num_supplies, hub->supplies);
 	if (err) {
-		dev_err(hub->dev, "failed to disable supplies: %d\n", err);
+		dev_err(hub->dev, "failed to disable supplies: %pe\n", ERR_PTR(err));
 		return err;
 	}
 
@@ -235,7 +236,7 @@ static void onboard_hub_attach_usb_driver(struct work_struct *work)
 
 	err = driver_attach(&onboard_hub_usbdev_driver.drvwrap.driver);
 	if (err)
-		pr_err("Failed to attach USB driver: %d\n", err);
+		pr_err("Failed to attach USB driver: %pe\n", ERR_PTR(err));
 }
 
 static int onboard_hub_probe(struct platform_device *pdev)
@@ -262,7 +263,7 @@ static int onboard_hub_probe(struct platform_device *pdev)
 
 	err = devm_regulator_bulk_get(dev, hub->pdata->num_supplies, hub->supplies);
 	if (err) {
-		dev_err(dev, "Failed to get regulator supplies: %d\n", err);
+		dev_err(dev, "Failed to get regulator supplies: %pe\n", ERR_PTR(err));
 		return err;
 	}
 
-- 
GitLab


From 65e62b8a955adebee8634804d8f72599213c2774 Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@kontron.de>
Date: Mon, 27 Nov 2023 12:22:25 +0100
Subject: [PATCH 0550/4076] usb: misc: onboard_usb_hub: Add support for clock
 input

Most onboard USB hubs have a dedicated crystal oscillator but on some
boards the clock signal for the hub is provided by the SoC.

In order to support this, we add the possibility of specifying a
clock in the devicetree that gets enabled/disabled when the hub
is powered up/down.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Link: https://lore.kernel.org/r/20231127112234.109073-2-frieder@fris.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/onboard_usb_hub.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index 6d122772a9706..3b209104f648f 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2022, Google LLC
  */
 
+#include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/err.h>
@@ -61,12 +62,19 @@ struct onboard_hub {
 	bool going_away;
 	struct list_head udev_list;
 	struct mutex lock;
+	struct clk *clk;
 };
 
 static int onboard_hub_power_on(struct onboard_hub *hub)
 {
 	int err;
 
+	err = clk_prepare_enable(hub->clk);
+	if (err) {
+		dev_err(hub->dev, "failed to enable clock: %pe\n", ERR_PTR(err));
+		return err;
+	}
+
 	err = regulator_bulk_enable(hub->pdata->num_supplies, hub->supplies);
 	if (err) {
 		dev_err(hub->dev, "failed to enable supplies: %pe\n", ERR_PTR(err));
@@ -93,6 +101,8 @@ static int onboard_hub_power_off(struct onboard_hub *hub)
 		return err;
 	}
 
+	clk_disable_unprepare(hub->clk);
+
 	hub->is_powered_on = false;
 
 	return 0;
@@ -267,6 +277,10 @@ static int onboard_hub_probe(struct platform_device *pdev)
 		return err;
 	}
 
+	hub->clk = devm_clk_get_optional(dev, NULL);
+	if (IS_ERR(hub->clk))
+		return dev_err_probe(dev, PTR_ERR(hub->clk), "failed to get clock\n");
+
 	hub->reset_gpio = devm_gpiod_get_optional(dev, "reset",
 						  GPIOD_OUT_HIGH);
 	if (IS_ERR(hub->reset_gpio))
-- 
GitLab


From 24af68a0ed53629bdde7b53ef8c2be72580d293b Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@kontron.de>
Date: Mon, 27 Nov 2023 12:22:26 +0100
Subject: [PATCH 0551/4076] usb: misc: onboard_usb_hub: Add support for Cypress
 CY7C6563x

The Cypress CY7C6563x is a 2/4-port USB 2.0 hub. Add support for
this hub in the driver in order to bring up reset, supply or clock
dependencies.

There is no reset pulse width given in the datasheet so we expect
a minimal value of 1us to be enough. This hasn't been tested though
due to lack of hardware which has the reset connected to a GPIO.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Link: https://lore.kernel.org/r/20231127112234.109073-3-frieder@fris.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/onboard_usb_hub.c | 1 +
 drivers/usb/misc/onboard_usb_hub.h | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index 3b209104f648f..c09fb6bd7d7d7 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -441,6 +441,7 @@ static void onboard_hub_usbdev_disconnect(struct usb_device *udev)
 static const struct usb_device_id onboard_hub_id_table[] = {
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB33{0,1,2}x/CYUSB230x 3.0 */
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB33{0,1,2}x/CYUSB230x 2.0 */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6570) }, /* CY7C6563x 2.0 */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0620) }, /* Genesys Logic GL3523 USB 3.1 */
diff --git a/drivers/usb/misc/onboard_usb_hub.h b/drivers/usb/misc/onboard_usb_hub.h
index 292110e64a1d9..f360d5cf8d8a0 100644
--- a/drivers/usb/misc/onboard_usb_hub.h
+++ b/drivers/usb/misc/onboard_usb_hub.h
@@ -36,6 +36,11 @@ static const struct onboard_hub_pdata cypress_hx3_data = {
 	.num_supplies = 2,
 };
 
+static const struct onboard_hub_pdata cypress_hx2vl_data = {
+	.reset_us = 1,
+	.num_supplies = 1,
+};
+
 static const struct onboard_hub_pdata genesys_gl850g_data = {
 	.reset_us = 3,
 	.num_supplies = 1,
@@ -61,6 +66,7 @@ static const struct of_device_id onboard_hub_match[] = {
 	{ .compatible = "usb451,8142", .data = &ti_tusb8041_data, },
 	{ .compatible = "usb4b4,6504", .data = &cypress_hx3_data, },
 	{ .compatible = "usb4b4,6506", .data = &cypress_hx3_data, },
+	{ .compatible = "usb4b4,6570", .data = &cypress_hx2vl_data, },
 	{ .compatible = "usb5e3,608", .data = &genesys_gl850g_data, },
 	{ .compatible = "usb5e3,610", .data = &genesys_gl852g_data, },
 	{ .compatible = "usb5e3,620", .data = &genesys_gl852g_data, },
-- 
GitLab


From a19937d829fbe3103e4596c8810a3e5cb372c6d4 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 5 Nov 2023 16:52:17 +0900
Subject: [PATCH 0552/4076] genksyms: remove the remnant of the -s option

Commit 74d931716151 ("genksyms: remove symbol prefix support") removed
the -s (--symbol-prefix) option.

Clean up the left-over.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/genksyms/genksyms.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index f5dfdb9d80e9d..6636d5b30eba1 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -719,7 +719,6 @@ static void genksyms_usage(void)
 {
 	fputs("Usage:\n" "genksyms [-adDTwqhVR] > /path/to/.tmp_obj.ver\n" "\n"
 #ifdef __GNU_LIBRARY__
-	      "  -s, --symbol-prefix   Select symbol prefix\n"
 	      "  -d, --debug           Increment the debug level (repeatable)\n"
 	      "  -D, --dump            Dump expanded symbol defs (for debugging only)\n"
 	      "  -r, --reference file  Read reference symbols from a file\n"
@@ -730,7 +729,6 @@ static void genksyms_usage(void)
 	      "  -h, --help            Print this message\n"
 	      "  -V, --version         Print the release version\n"
 #else				/* __GNU_LIBRARY__ */
-	      "  -s                    Select symbol prefix\n"
 	      "  -d                    Increment the debug level (repeatable)\n"
 	      "  -D                    Dump expanded symbol defs (for debugging only)\n"
 	      "  -r file               Read reference symbols from a file\n"
@@ -763,10 +761,10 @@ int main(int argc, char **argv)
 		{0, 0, 0, 0}
 	};
 
-	while ((o = getopt_long(argc, argv, "s:dwqVDr:T:ph",
+	while ((o = getopt_long(argc, argv, "dwqVDr:T:ph",
 				&long_opts[0], NULL)) != EOF)
 #else				/* __GNU_LIBRARY__ */
-	while ((o = getopt(argc, argv, "s:dwqVDr:T:ph")) != EOF)
+	while ((o = getopt(argc, argv, "dwqVDr:T:ph")) != EOF)
 #endif				/* __GNU_LIBRARY__ */
 		switch (o) {
 		case 'd':
-- 
GitLab


From 96a29581e735bcf3b4e5a4f2daad9f445025f510 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 5 Nov 2023 16:52:18 +0900
Subject: [PATCH 0553/4076] genksyms: use getopt_long() unconditionally

getopt_long() is used by various tools in the kernel (e.g. Kconfig).

It should be fine to use it all the time.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/genksyms/genksyms.c | 18 ------------------
 1 file changed, 18 deletions(-)

diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index 6636d5b30eba1..f3901c55df239 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -16,9 +16,7 @@
 #include <unistd.h>
 #include <assert.h>
 #include <stdarg.h>
-#ifdef __GNU_LIBRARY__
 #include <getopt.h>
-#endif				/* __GNU_LIBRARY__ */
 
 #include "genksyms.h"
 /*----------------------------------------------------------------------*/
@@ -718,7 +716,6 @@ void error_with_pos(const char *fmt, ...)
 static void genksyms_usage(void)
 {
 	fputs("Usage:\n" "genksyms [-adDTwqhVR] > /path/to/.tmp_obj.ver\n" "\n"
-#ifdef __GNU_LIBRARY__
 	      "  -d, --debug           Increment the debug level (repeatable)\n"
 	      "  -D, --dump            Dump expanded symbol defs (for debugging only)\n"
 	      "  -r, --reference file  Read reference symbols from a file\n"
@@ -728,17 +725,6 @@ static void genksyms_usage(void)
 	      "  -q, --quiet           Disable warnings (default)\n"
 	      "  -h, --help            Print this message\n"
 	      "  -V, --version         Print the release version\n"
-#else				/* __GNU_LIBRARY__ */
-	      "  -d                    Increment the debug level (repeatable)\n"
-	      "  -D                    Dump expanded symbol defs (for debugging only)\n"
-	      "  -r file               Read reference symbols from a file\n"
-	      "  -T file               Dump expanded types into file\n"
-	      "  -p                    Preserve reference modversions or fail\n"
-	      "  -w                    Enable warnings\n"
-	      "  -q                    Disable warnings (default)\n"
-	      "  -h                    Print this message\n"
-	      "  -V                    Print the release version\n"
-#endif				/* __GNU_LIBRARY__ */
 	      , stderr);
 }
 
@@ -747,7 +733,6 @@ int main(int argc, char **argv)
 	FILE *dumpfile = NULL, *ref_file = NULL;
 	int o;
 
-#ifdef __GNU_LIBRARY__
 	struct option long_opts[] = {
 		{"debug", 0, 0, 'd'},
 		{"warnings", 0, 0, 'w'},
@@ -763,9 +748,6 @@ int main(int argc, char **argv)
 
 	while ((o = getopt_long(argc, argv, "dwqVDr:T:ph",
 				&long_opts[0], NULL)) != EOF)
-#else				/* __GNU_LIBRARY__ */
-	while ((o = getopt(argc, argv, "dwqVDr:T:ph")) != EOF)
-#endif				/* __GNU_LIBRARY__ */
 		switch (o) {
 		case 'd':
 			flag_debug++;
-- 
GitLab


From ce1fc9345a59c55d3a46dd7da872791cae41324e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Mon, 6 Nov 2023 03:10:47 +0900
Subject: [PATCH 0554/4076] kconfig: do not clear SYMBOL_DEF_USER when the
 value is out of range

When a user-supplied value is out of range, (NEW) and an incorrect default
value are shown.

[Test Kconfig]

  config FOO
          int "foo"
          range 10 20

[Test .config]

  CONFIG_FOO=30

[Result without this fix]

  $ make config
  *
  * Main menu
  *
  foo (FOO) [10] (NEW)

[Result with this fix]

  $ make config
  *
  * Main menu
  *
  foo (FOO) [20]

Currently, the SYMBOL_DEF_USER is cleared if the user input does not
reside within the range. Kconfig forgets the initial value 30, and
prints (NEW) and an incorrect default [10].

Kconfig should remember the user's input. The default should be [20]
because the user's input, 30, is closer to the upper limit of the range.

Please note it will not show up in "make oldconfig" because it is no
longer considered as a new symbol. It also fixes the inconsistent
behavior in listnewconfig/helpnewconfig.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 4a6811d77d182..7fca9cc3ae748 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -594,7 +594,7 @@ int conf_read(const char *name)
 				/* Reset a string value if it's out of range */
 				if (sym_string_within_range(sym, sym->def[S_DEF_USER].val))
 					break;
-				sym->flags &= ~(SYMBOL_VALID|SYMBOL_DEF_USER);
+				sym->flags &= ~SYMBOL_VALID;
 				conf_unsaved++;
 				break;
 			default:
-- 
GitLab


From 259b8bd13db5f61fcc60192d4f73eb2eac9c426f Mon Sep 17 00:00:00 2001
From: Dmitrii Bundin <dmitrii.bundin.a@gmail.com>
Date: Mon, 6 Nov 2023 00:56:22 +0300
Subject: [PATCH 0555/4076] kbuild: deb-pkg: apply short -R and -j options

The long version --rules-file and --jobs are available since 1.18.8
while their short analogues -R and -j have been added since 1.14.7.

The option --rules-file the way it works currently was introduced in the
commit 5cd52673aabdf5eaa58181972119a41041fc85f2 of dpkg dated 23.07.18
with the following changelog entry:

* Fix dpkg-buildpackage option --rules-file parsing. It was trying to parse
  it as --rules-target, which due to the ordering was a no-op.

The current behavior of the long version --rules-file is guaranteed to
be in use starting 1.19.1 and might cause build failures for some
versions newer than 1.18.8 even in spite of being documented that way.

Signed-off-by: Dmitrii Bundin <dmitrii.bundin.a@gmail.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/Makefile.package | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/Makefile.package b/scripts/Makefile.package
index 3addd1c0b989a..f30349f46a975 100644
--- a/scripts/Makefile.package
+++ b/scripts/Makefile.package
@@ -146,7 +146,7 @@ deb-pkg srcdeb-pkg bindeb-pkg:
 	$(if $(findstring source, $(build-type)), \
 		--unsigned-source --compression=$(KDEB_SOURCE_COMPRESS)) \
 	$(if $(findstring binary, $(build-type)), \
-		--rules-file='$(MAKE) -f debian/rules' --jobs=1 -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch), \
+		-R'$(MAKE) -f debian/rules' -j1 -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch), \
 		--no-check-builddeps) \
 	$(DPKG_FLAGS))
 
-- 
GitLab


From 61e3e3c21a9599f7f2c6f15f7e4b099cf6ea290e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 18 Nov 2023 15:18:36 +0900
Subject: [PATCH 0556/4076] kconfig: remove error check for xrealloc()

xrealloc() never returns NULL as it is checked in the callee.

This is a left-over of commit d717f24d8c68 ("kconfig: add xrealloc()
helper").

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 7fca9cc3ae748..2ba4dfdd1aeee 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -289,16 +289,12 @@ static int conf_set_sym_val(struct symbol *sym, int def, int def_flags, char *p)
 #define LINE_GROWTH 16
 static int add_byte(int c, char **lineptr, size_t slen, size_t *n)
 {
-	char *nline;
 	size_t new_size = slen + 1;
+
 	if (new_size > *n) {
 		new_size += LINE_GROWTH - 1;
 		new_size *= 2;
-		nline = xrealloc(*lineptr, new_size);
-		if (!nline)
-			return -1;
-
-		*lineptr = nline;
+		*lineptr = xrealloc(*lineptr, new_size);
 		*n = new_size;
 	}
 
-- 
GitLab


From 4d137ab0107ead0f2590fc0314e627431e3b9e3f Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 18 Nov 2023 16:59:07 +0900
Subject: [PATCH 0557/4076] kconfig: require a space after '#' for valid input

Currently, when an input line starts with '#', (line + 2) is passed to
memcmp() without checking line[1].

It means that line[1] can be any arbitrary character. For example,
"#KCONFIG_FOO is not set" is accepted as valid input, functioning the
same as "# CONFIG_FOO is not set".

More importantly, this can potentially lead to a buffer overrun if
line[1] == '\0'. It occurs if the input only contains '#', as
(line + 2) points to an uninitialized buffer.

Check line[1], and skip the line if it is not a space.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 2ba4dfdd1aeee..556b7f087dbb5 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -426,6 +426,8 @@ load:
 		conf_lineno++;
 		sym = NULL;
 		if (line[0] == '#') {
+			if (line[1] != ' ')
+				continue;
 			if (memcmp(line + 2, CONFIG_, strlen(CONFIG_)))
 				continue;
 			p = strchr(line + 2 + strlen(CONFIG_), ' ');
-- 
GitLab


From 92d4fe0a48f1ab6cf20143dd0b376f4fe842854b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 18 Nov 2023 16:59:08 +0900
Subject: [PATCH 0558/4076] kconfig: remove unused code for S_DEF_AUTO in
 conf_read_simple()

The 'else' arm here is unreachable in practical use cases.

include/config/auto.conf does not include "# CONFIG_... is not set"
line unless it is manually hacked.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 556b7f087dbb5..92e8e37aca4d1 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -436,20 +436,15 @@ load:
 			*p++ = 0;
 			if (strncmp(p, "is not set", 10))
 				continue;
-			if (def == S_DEF_USER) {
-				sym = sym_find(line + 2 + strlen(CONFIG_));
-				if (!sym) {
-					if (warn_unknown)
-						conf_warning("unknown symbol: %s",
-							     line + 2 + strlen(CONFIG_));
 
-					conf_set_changed(true);
-					continue;
-				}
-			} else {
-				sym = sym_lookup(line + 2 + strlen(CONFIG_), 0);
-				if (sym->type == S_UNKNOWN)
-					sym->type = S_BOOLEAN;
+			sym = sym_find(line + 2 + strlen(CONFIG_));
+			if (!sym) {
+				if (warn_unknown)
+					conf_warning("unknown symbol: %s",
+						     line + 2 + strlen(CONFIG_));
+
+				conf_set_changed(true);
+				continue;
 			}
 			if (sym->flags & def_flags) {
 				conf_warning("override: reassigning to symbol %s", sym->name);
-- 
GitLab


From d854b4b21de684a16a7d6163c7b0e9c5ff8a09d3 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 18 Nov 2023 16:59:09 +0900
Subject: [PATCH 0559/4076] kconfig: deduplicate code in conf_read_simple()

Kconfig accepts both "# CONFIG_FOO is not set" and "CONFIG_FOO=n" as
a valid input, but conf_read_simple() duplicates similar code to handle
them. Factor out the common code.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 89 +++++++++++++++-----------------------
 1 file changed, 35 insertions(+), 54 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 92e8e37aca4d1..b6a90f6baea14 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -342,11 +342,10 @@ int conf_read_simple(const char *name, int def)
 	FILE *in = NULL;
 	char   *line = NULL;
 	size_t  line_asize = 0;
-	char *p, *p2;
+	char *p, *p2, *val;
 	struct symbol *sym;
 	int i, def_flags;
-	const char *warn_unknown;
-	const char *werror;
+	const char *warn_unknown, *werror, *sym_name;
 
 	warn_unknown = getenv("KCONFIG_WARN_UNKNOWN_SYMBOLS");
 	werror = getenv("KCONFIG_WERROR");
@@ -424,77 +423,34 @@ load:
 
 	while (compat_getline(&line, &line_asize, in) != -1) {
 		conf_lineno++;
-		sym = NULL;
 		if (line[0] == '#') {
 			if (line[1] != ' ')
 				continue;
-			if (memcmp(line + 2, CONFIG_, strlen(CONFIG_)))
+			p = line + 2;
+			if (memcmp(p, CONFIG_, strlen(CONFIG_)))
 				continue;
-			p = strchr(line + 2 + strlen(CONFIG_), ' ');
+			sym_name = p + strlen(CONFIG_);
+			p = strchr(sym_name, ' ');
 			if (!p)
 				continue;
 			*p++ = 0;
 			if (strncmp(p, "is not set", 10))
 				continue;
 
-			sym = sym_find(line + 2 + strlen(CONFIG_));
-			if (!sym) {
-				if (warn_unknown)
-					conf_warning("unknown symbol: %s",
-						     line + 2 + strlen(CONFIG_));
-
-				conf_set_changed(true);
-				continue;
-			}
-			if (sym->flags & def_flags) {
-				conf_warning("override: reassigning to symbol %s", sym->name);
-			}
-			switch (sym->type) {
-			case S_BOOLEAN:
-			case S_TRISTATE:
-				sym->def[def].tri = no;
-				sym->flags |= def_flags;
-				break;
-			default:
-				;
-			}
+			val = "n";
 		} else if (memcmp(line, CONFIG_, strlen(CONFIG_)) == 0) {
-			p = strchr(line + strlen(CONFIG_), '=');
+			sym_name = line + strlen(CONFIG_);
+			p = strchr(sym_name, '=');
 			if (!p)
 				continue;
 			*p++ = 0;
+			val = p;
 			p2 = strchr(p, '\n');
 			if (p2) {
 				*p2-- = 0;
 				if (*p2 == '\r')
 					*p2 = 0;
 			}
-
-			sym = sym_find(line + strlen(CONFIG_));
-			if (!sym) {
-				if (def == S_DEF_AUTO) {
-					/*
-					 * Reading from include/config/auto.conf
-					 * If CONFIG_FOO previously existed in
-					 * auto.conf but it is missing now,
-					 * include/config/FOO must be touched.
-					 */
-					conf_touch_dep(line + strlen(CONFIG_));
-				} else {
-					if (warn_unknown)
-						conf_warning("unknown symbol: %s",
-							     line + strlen(CONFIG_));
-
-					conf_set_changed(true);
-				}
-				continue;
-			}
-
-			if (sym->flags & def_flags) {
-				conf_warning("override: reassigning to symbol %s", sym->name);
-			}
-			if (conf_set_sym_val(sym, def, def_flags, p))
-				continue;
 		} else {
 			if (line[0] != '\r' && line[0] != '\n')
 				conf_warning("unexpected data: %.*s",
@@ -503,6 +459,31 @@ load:
 			continue;
 		}
 
+		sym = sym_find(sym_name);
+		if (!sym) {
+			if (def == S_DEF_AUTO) {
+				/*
+				 * Reading from include/config/auto.conf.
+				 * If CONFIG_FOO previously existed in auto.conf
+				 * but it is missing now, include/config/FOO
+				 * must be touched.
+				 */
+				conf_touch_dep(sym_name);
+			} else {
+				if (warn_unknown)
+					conf_warning("unknown symbol: %s", sym_name);
+
+				conf_set_changed(true);
+			}
+			continue;
+		}
+
+		if (sym->flags & def_flags)
+			conf_warning("override: reassigning to symbol %s", sym->name);
+
+		if (conf_set_sym_val(sym, def, def_flags, val))
+			continue;
+
 		if (sym && sym_is_choice_value(sym)) {
 			struct symbol *cs = prop_get_symbol(sym_get_choice_prop(sym));
 			switch (sym->def[def].tri) {
-- 
GitLab


From 9925d6b7d12f5019d2a6c465ae72093101edbfd4 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 18 Nov 2023 16:59:10 +0900
Subject: [PATCH 0560/4076] kconfig: introduce getline_stripped() helper

Currently, newline characters are stripped away in multiple places
on the caller.

Doing that in the callee is helpful for further cleanups.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 40 +++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 14 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index b6a90f6baea14..795ac6c9378f1 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -337,12 +337,32 @@ e_out:
 	return -1;
 }
 
+/* like getline(), but the newline character is stripped away */
+static ssize_t getline_stripped(char **lineptr, size_t *n, FILE *stream)
+{
+	ssize_t len;
+
+	len = compat_getline(lineptr, n, stream);
+
+	if (len > 0 && (*lineptr)[len - 1] == '\n') {
+		len--;
+		(*lineptr)[len] = '\0';
+
+		if (len > 0 && (*lineptr)[len - 1] == '\r') {
+			len--;
+			(*lineptr)[len] = '\0';
+		}
+	}
+
+	return len;
+}
+
 int conf_read_simple(const char *name, int def)
 {
 	FILE *in = NULL;
 	char   *line = NULL;
 	size_t  line_asize = 0;
-	char *p, *p2, *val;
+	char *p, *val;
 	struct symbol *sym;
 	int i, def_flags;
 	const char *warn_unknown, *werror, *sym_name;
@@ -421,7 +441,7 @@ load:
 		}
 	}
 
-	while (compat_getline(&line, &line_asize, in) != -1) {
+	while (getline_stripped(&line, &line_asize, in) != -1) {
 		conf_lineno++;
 		if (line[0] == '#') {
 			if (line[1] != ' ')
@@ -443,19 +463,11 @@ load:
 			p = strchr(sym_name, '=');
 			if (!p)
 				continue;
-			*p++ = 0;
-			val = p;
-			p2 = strchr(p, '\n');
-			if (p2) {
-				*p2-- = 0;
-				if (*p2 == '\r')
-					*p2 = 0;
-			}
+			*p = 0;
+			val = p + 1;
 		} else {
-			if (line[0] != '\r' && line[0] != '\n')
-				conf_warning("unexpected data: %.*s",
-					     (int)strcspn(line, "\r\n"), line);
-
+			if (line[0] != '\0')
+				conf_warning("unexpected data: %s", line);
 			continue;
 		}
 
-- 
GitLab


From 4aced3ec84a848bd64bfd725e81c54eb31bf8b24 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 18 Nov 2023 16:59:11 +0900
Subject: [PATCH 0561/4076] kconfig: require an exact match for "is not set" to
 disable CONFIG option

Currently, any string starting "is not set" disables a CONFIG option.

For example, "# CONFIG_FOO is not settled down" is accepted as valid
input, functioning the same as "# CONFIG_FOO is not set". It is a
long-standing oddity.

Check the line against the exact pattern "is not set".

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 795ac6c9378f1..958be12cd621a 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -454,7 +454,7 @@ load:
 			if (!p)
 				continue;
 			*p++ = 0;
-			if (strncmp(p, "is not set", 10))
+			if (strcmp(p, "is not set"))
 				continue;
 
 			val = "n";
-- 
GitLab


From 48ab6c9c9256003a4f2d737ccdcba81e01ba4e68 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 18 Nov 2023 16:59:12 +0900
Subject: [PATCH 0562/4076] kconfig: massage the loop in conf_read_simple()

Make the while-loop code a little more readable.

The gain is that "CONFIG_FOO" without '=' is warned as unexpected data.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 958be12cd621a..bd14aae1db582 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -443,6 +443,10 @@ load:
 
 	while (getline_stripped(&line, &line_asize, in) != -1) {
 		conf_lineno++;
+
+		if (!line[0]) /* blank line */
+			continue;
+
 		if (line[0] == '#') {
 			if (line[1] != ' ')
 				continue;
@@ -458,17 +462,20 @@ load:
 				continue;
 
 			val = "n";
-		} else if (memcmp(line, CONFIG_, strlen(CONFIG_)) == 0) {
+		} else {
+			if (memcmp(line, CONFIG_, strlen(CONFIG_))) {
+				conf_warning("unexpected data: %s", line);
+				continue;
+			}
+
 			sym_name = line + strlen(CONFIG_);
 			p = strchr(sym_name, '=');
-			if (!p)
+			if (!p) {
+				conf_warning("unexpected data: %s", line);
 				continue;
+			}
 			*p = 0;
 			val = p + 1;
-		} else {
-			if (line[0] != '\0')
-				conf_warning("unexpected data: %s", line);
-			continue;
 		}
 
 		sym = sym_find(sym_name);
-- 
GitLab


From 884f55f152cb028056bf9efe557a2d7346e932f5 Mon Sep 17 00:00:00 2001
From: Petr Vorel <pvorel@suse.cz>
Date: Tue, 21 Nov 2023 12:58:54 +0100
Subject: [PATCH 0563/4076] kbuild: buildtar: Remove unused $dirs

The shell variable $dirs is not used any more since 1fc9095846cc
("kbuild: tar-pkg: use tar rules in scripts/Makefile.package"),
therefore remove it".

Fixes: 1fc9095846cc ("kbuild: tar-pkg: use tar rules in scripts/Makefile.package")
Signed-off-by: Petr Vorel <pvorel@suse.cz>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/package/buildtar | 2 --
 1 file changed, 2 deletions(-)

diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index 65b4ea5029621..8ac075dd0e9c5 100755
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -23,7 +23,6 @@ tmpdir=$1
 #
 rm -rf -- "${tmpdir}"
 mkdir -p -- "${tmpdir}/boot"
-dirs=boot
 
 
 #
@@ -42,7 +41,6 @@ fi
 #
 if grep -q '^CONFIG_MODULES=y' include/config/auto.conf; then
 	make ARCH="${ARCH}" -f ${srctree}/Makefile INSTALL_MOD_PATH="${tmpdir}" modules_install
-	dirs="$dirs lib"
 fi
 
 
-- 
GitLab


From b28d6ca1c9cbb64b0c8e435c0ff34d8c5d52812c Mon Sep 17 00:00:00 2001
From: Petr Vorel <petr.vorel@gmail.com>
Date: Tue, 21 Nov 2023 12:58:55 +0100
Subject: [PATCH 0564/4076] kbuild: buildtar: always make modules_install

It is done for the same reasons as 4243afdb9326 does it for builddeb:
always runs make modules to install modules.builtin* files, which are
needed for e.g. initramfs-tools or LTP testing tool.

Signed-off-by: Petr Vorel <pvorel@suse.cz>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/package/buildtar | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index 8ac075dd0e9c5..72c91a1b832f9 100755
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -37,11 +37,9 @@ fi
 
 
 #
-# Try to install modules
+# Install modules
 #
-if grep -q '^CONFIG_MODULES=y' include/config/auto.conf; then
-	make ARCH="${ARCH}" -f ${srctree}/Makefile INSTALL_MOD_PATH="${tmpdir}" modules_install
-fi
+make ARCH="${ARCH}" -f ${srctree}/Makefile INSTALL_MOD_PATH="${tmpdir}" modules_install
 
 
 #
-- 
GitLab


From ef6609adf1ecc4c0797a894d4dd365dbbc4903f9 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Thu, 23 Nov 2023 16:18:24 +0900
Subject: [PATCH 0565/4076] kbuild: remove the last use of old cmd_src_tar rule
 in packaging

The rpm-pkg and deb-pkg targets have transitioned to using 'git archive'
for tarball creation.

Although the old cmd_src_tar is still used by snap-pkg, there is no need
to pack and unpack a tarball solely for passing the source to snapcraft.

Instead, you can use 'source-type: local' to tell the source location to
snapcraft.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 Makefile                           |  2 --
 scripts/Makefile.package           | 24 +-----------------------
 scripts/package/snapcraft.template |  2 +-
 3 files changed, 2 insertions(+), 26 deletions(-)

diff --git a/Makefile b/Makefile
index 99db546fbb452..0df7372175294 100644
--- a/Makefile
+++ b/Makefile
@@ -609,8 +609,6 @@ export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL KBUILD_RUSTFLAGS_KERNEL
 export RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o    \
 			  -name CVS -o -name .pc -o -name .hg -o -name .git \) \
 			  -prune -o
-export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \
-			 --exclude CVS --exclude .pc --exclude .hg --exclude .git
 
 # ===========================================================================
 # Rules shared between *config targets and build targets
diff --git a/scripts/Makefile.package b/scripts/Makefile.package
index f30349f46a975..0c3adc48dfe89 100644
--- a/scripts/Makefile.package
+++ b/scripts/Makefile.package
@@ -4,27 +4,6 @@
 include $(srctree)/scripts/Kbuild.include
 include $(srctree)/scripts/Makefile.lib
 
-KERNELPATH := kernel-$(subst -,_,$(KERNELRELEASE))
-# Include only those top-level files that are needed by make, plus the GPL copy
-TAR_CONTENT := Documentation LICENSES arch block certs crypto drivers fs \
-               include init io_uring ipc kernel lib mm net rust \
-               samples scripts security sound tools usr virt \
-               .config Makefile \
-               Kbuild Kconfig COPYING $(wildcard localversion*)
-
-quiet_cmd_src_tar = TAR     $(2).tar.gz
-      cmd_src_tar = \
-if test "$(objtree)" != "$(srctree)"; then \
-	echo >&2; \
-	echo >&2 "  ERROR:"; \
-	echo >&2 "  Building source tarball is not possible outside the"; \
-	echo >&2 "  kernel source tree. Don't set KBUILD_OUTPUT"; \
-	echo >&2; \
-	false; \
-fi ; \
-tar -I $(KGZIP) -c $(RCS_TAR_IGNORE) -f $(2).tar.gz \
-	--transform 's:^:$(2)/:S' $(TAR_CONTENT) $(3)
-
 # Git
 # ---------------------------------------------------------------------------
 
@@ -157,9 +136,8 @@ snap-pkg:
 	rm -rf $(objtree)/snap
 	mkdir $(objtree)/snap
 	$(MAKE) clean
-	$(call cmd,src_tar,$(KERNELPATH))
 	sed "s@KERNELRELEASE@$(KERNELRELEASE)@; \
-		s@SRCTREE@$(shell realpath $(KERNELPATH).tar.gz)@" \
+		s@SRCTREE@$(abs_srctree)@" \
 		$(srctree)/scripts/package/snapcraft.template > \
 		$(objtree)/snap/snapcraft.yaml
 	cd $(objtree)/snap && \
diff --git a/scripts/package/snapcraft.template b/scripts/package/snapcraft.template
index 626d278e4a5a7..85d5e07d1b40b 100644
--- a/scripts/package/snapcraft.template
+++ b/scripts/package/snapcraft.template
@@ -10,5 +10,5 @@ parts:
   kernel:
     plugin: kernel
     source: SRCTREE
-    source-type: tar
+    source-type: local
     kernel-with-firmware: false
-- 
GitLab


From 55d50ace6b88eb273a10963160cadbadccfcdd64 Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Mon, 27 Nov 2023 20:44:05 +0800
Subject: [PATCH 0566/4076] soundwire: generic_bandwidth_allocation use
 bus->params.max_dr_freq

bus->params.max_dr_freq is calculated and set in sdw_bus_master_add().
We can use it directly instead of calculating it again.

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@intel.com>
Link: https://lore.kernel.org/r/20231127124405.2080431-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/generic_bandwidth_allocation.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
index 31162f2b56381..c70a63d009ae4 100644
--- a/drivers/soundwire/generic_bandwidth_allocation.c
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -333,7 +333,7 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq)
  */
 static int sdw_compute_bus_params(struct sdw_bus *bus)
 {
-	unsigned int max_dr_freq, curr_dr_freq = 0;
+	unsigned int curr_dr_freq = 0;
 	struct sdw_master_prop *mstr_prop = &bus->prop;
 	int i, clk_values, ret;
 	bool is_gear = false;
@@ -351,14 +351,12 @@ static int sdw_compute_bus_params(struct sdw_bus *bus)
 		clk_buf = NULL;
 	}
 
-	max_dr_freq = mstr_prop->max_clk_freq * SDW_DOUBLE_RATE_FACTOR;
-
 	for (i = 0; i < clk_values; i++) {
 		if (!clk_buf)
-			curr_dr_freq = max_dr_freq;
+			curr_dr_freq = bus->params.max_dr_freq;
 		else
 			curr_dr_freq = (is_gear) ?
-				(max_dr_freq >>  clk_buf[i]) :
+				(bus->params.max_dr_freq >>  clk_buf[i]) :
 				clk_buf[i] * SDW_DOUBLE_RATE_FACTOR;
 
 		if (curr_dr_freq <= bus->params.bandwidth)
-- 
GitLab


From 72108c0b9c0e004d7dfc2fc88b02c30b12711325 Mon Sep 17 00:00:00 2001
From: Yang Jihong <yangjihong1@huawei.com>
Date: Tue, 31 Oct 2023 10:55:23 +0000
Subject: [PATCH 0567/4076] perf tools: Add --debug-file option to redirect
 debug output

Currently, debug messages is output to stderr, add --debug-file option to
support redirection to a specified file.

Some test scenarios:

  # perf --list-opts
  --help --version --exec-path --html-path --paginate --no-pager --debugfs-dir --buildid-dir --list-cmds --list-opts --debug --debug-file

  # perf --debug-file
  No path given for --debug-file.

   Usage: perf [--version] [--help] [OPTIONS] COMMAND [ARGS]

  # perf --debug-file /sys/perf.log record -v true
  Open debug file '/sys/perf.log' failed: Permission denied

   Usage: perf [--version] [--help] [OPTIONS] COMMAND [ARGS]

  # perf --debug-file /tmp/perf.log record -v true
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.013 MB perf.data (26 samples) ]
  # cat /tmp/perf.log
  DEBUGINFOD_URLS=
  Using CPUID GenuineIntel-6-3E-4
  nr_cblocks: 0
  affinity: SYS
  mmap flush: 1
  comp level: 0
  mmap size 528384B
  Control descriptor is not initialized
  mmap size 528384B
  Looking at the vmlinux_path (8 entries long)
  Using /proc/kcore for kernel data
  Using /proc/kallsyms for symbols
  symbol:unmap_start file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:unmap_complete file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:map_start file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:map_complete file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:reloc_start file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:reloc_complete file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:init_start file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:init_complete file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:lll_lock_wait_private file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:lll_lock_wait file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:setjmp file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:longjmp file:(null) line:0 offset:0 return:0 lazy:(null)
  symbol:longjmp_target file:(null) line:0 offset:0 return:0 lazy:(null)
  failed to write feature HYBRID_TOPOLOGY

Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231031105523.1472558-1-yangjihong1@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf.txt |  3 +++
 tools/perf/perf.c                 | 30 ++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+)

diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index ba3df49c169d3..a7cf7bc2f9689 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -64,6 +64,9 @@ OPTIONS
           perf-event-open  - Print perf_event_open() arguments and
                              return value
 
+--debug-file::
+	Write debug output to a specified file.
+
 DESCRIPTION
 -----------
 Performance counters for Linux are a new kernel-based subsystem
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index d3fc8090413c8..921bee0a64370 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -39,6 +39,7 @@
 #include <linux/zalloc.h>
 
 static int use_pager = -1;
+static FILE *debug_fp = NULL;
 
 struct cmd_struct {
 	const char *cmd;
@@ -162,6 +163,19 @@ static void commit_pager_choice(void)
 	}
 }
 
+static int set_debug_file(const char *path)
+{
+	debug_fp = fopen(path, "w");
+	if (!debug_fp) {
+		fprintf(stderr, "Open debug file '%s' failed: %s\n",
+			path, strerror(errno));
+		return -1;
+	}
+
+	debug_set_file(debug_fp);
+	return 0;
+}
+
 struct option options[] = {
 	OPT_ARGUMENT("help", "help"),
 	OPT_ARGUMENT("version", "version"),
@@ -174,6 +188,7 @@ struct option options[] = {
 	OPT_ARGUMENT("list-cmds", "list-cmds"),
 	OPT_ARGUMENT("list-opts", "list-opts"),
 	OPT_ARGUMENT("debug", "debug"),
+	OPT_ARGUMENT("debug-file", "debug-file"),
 	OPT_END()
 };
 
@@ -287,6 +302,18 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 
 			(*argv)++;
 			(*argc)--;
+		} else if (!strcmp(cmd, "--debug-file")) {
+			if (*argc < 2) {
+				fprintf(stderr, "No path given for --debug-file.\n");
+				usage(perf_usage_string);
+			}
+
+			if (set_debug_file((*argv)[1]))
+				usage(perf_usage_string);
+
+			(*argv)++;
+			(*argc)--;
+
 		} else {
 			fprintf(stderr, "Unknown option: %s\n", cmd);
 			usage(perf_usage_string);
@@ -547,5 +574,8 @@ int main(int argc, const char **argv)
 	fprintf(stderr, "Failed to run command '%s': %s\n",
 		cmd, str_error_r(errno, sbuf, sizeof(sbuf)));
 out:
+	if (debug_fp)
+		fclose(debug_fp);
+
 	return 1;
 }
-- 
GitLab


From d60469d7c0e5c4e8de10699377d2ba79004236a4 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Nov 2023 15:59:51 -0800
Subject: [PATCH 0568/4076] perf dwarf-aux: Add die_find_variable_by_addr()

The die_find_variable_by_addr() is to find a variables in the given DIE
using given (PC-relative) address.  Global variables will have a
location expression with DW_OP_addr which has an address so can simply
compare it with the address.

  <1><143a7>: Abbrev Number: 2 (DW_TAG_variable)
      <143a8>   DW_AT_name        : loops_per_jiffy
      <143ac>   DW_AT_type        : <0x1cca>
      <143b0>   DW_AT_external    : 1
      <143b0>   DW_AT_decl_file   : 193
      <143b1>   DW_AT_decl_line   : 213
      <143b2>   DW_AT_location    : 9 byte block: 3 b0 46 41 82 ff ff ff ff
                                     (DW_OP_addr: ffffffff824146b0)

Note that the type-offset should be calculated from the base address of
the global variable.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231110000012.3538610-33-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dwarf-aux.c | 79 +++++++++++++++++++++++++++++++++++++
 tools/perf/util/dwarf-aux.h | 14 +++++++
 2 files changed, 93 insertions(+)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 652e6e7368a26..edd9e407bc74e 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1250,8 +1250,12 @@ out:
 struct find_var_data {
 	/* Target instruction address */
 	Dwarf_Addr pc;
+	/* Target memory address (for global data) */
+	Dwarf_Addr addr;
 	/* Target register */
 	unsigned reg;
+	/* Access offset, set for global data */
+	int offset;
 };
 
 /* Max number of registers DW_OP_regN supports */
@@ -1312,6 +1316,81 @@ Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
 	};
 	return die_find_child(sc_die, __die_find_var_reg_cb, &data, die_mem);
 }
+
+/* Only checks direct child DIEs in the given scope */
+static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_var_data *data = arg;
+	int tag = dwarf_tag(die_mem);
+	ptrdiff_t off = 0;
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Word size;
+	Dwarf_Die type_die;
+	Dwarf_Op *ops;
+	size_t nops;
+
+	if (tag != DW_TAG_variable)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+		if (ops->atom != DW_OP_addr)
+			continue;
+
+		if (data->addr < ops->number)
+			continue;
+
+		if (data->addr == ops->number) {
+			/* Update offset relative to the start of the variable */
+			data->offset = 0;
+			return DIE_FIND_CB_END;
+		}
+
+		if (die_get_real_type(die_mem, &type_die) == NULL)
+			continue;
+
+		if (dwarf_aggregate_size(&type_die, &size) < 0)
+			continue;
+
+		if (data->addr >= ops->number + size)
+			continue;
+
+		/* Update offset relative to the start of the variable */
+		data->offset = data->addr - ops->number;
+		return DIE_FIND_CB_END;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_variable_by_addr - Find variable located at given address
+ * @sc_die: a scope DIE
+ * @pc: the program address to find
+ * @addr: the data address to find
+ * @die_mem: a buffer to save the resulting DIE
+ * @offset: the offset in the resulting type
+ *
+ * Find the variable DIE located at the given address (in PC-relative mode).
+ * This is usually for global variables.
+ */
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
+				     Dwarf_Addr addr, Dwarf_Die *die_mem,
+				     int *offset)
+{
+	struct find_var_data data = {
+		.pc = pc,
+		.addr = addr,
+	};
+	Dwarf_Die *result;
+
+	result = die_find_child(sc_die, __die_find_var_addr_cb, &data, die_mem);
+	if (result)
+		*offset = data.offset;
+	return result;
+}
 #endif
 
 /*
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index b6f430730bd13..0ddf61fd3f8be 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -141,6 +141,11 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
 Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
 				    Dwarf_Die *die_mem);
 
+/* Find a (global) variable located in the 'addr' */
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
+				     Dwarf_Addr addr, Dwarf_Die *die_mem,
+				     int *offset);
+
 #else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
@@ -158,6 +163,15 @@ static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unus
 	return NULL;
 }
 
+static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unused,
+						   Dwarf_Addr pc __maybe_unused,
+						   Dwarf_Addr addr __maybe_unused,
+						   Dwarf_Die *die_mem __maybe_unused,
+						   int *offset __maybe_unused)
+{
+	return NULL;
+}
+
 #endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 #endif /* _DWARF_AUX_H */
-- 
GitLab


From 5940a20a186bd74efd6d0dc0b2b7c77d891895d9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 2 Nov 2023 10:56:46 -0700
Subject: [PATCH 0569/4076] perf mmap: Lazily initialize zstd streams to save
 memory when not using it

Zstd streams create dictionaries that can require significant RAM,
especially when there is one per-CPU. Tools like 'perf record' won't use
the streams without the -z option, and so the creation of the streams
is pure overhead. Switch to creating the streams on first use.

Committer notes:

ssize_t comes from sys/types.h, size_t from stddef.h. This worked on
glibc as stdlib.h includes both, but not on musl libc. So do what 'man
size_t' says and include sys/types.h and stddef.h instead of stdlib.h

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231102175735.2272696-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 26 ++++++++++-----
 tools/perf/util/compress.h  |  7 +++--
 tools/perf/util/mmap.c      |  5 ++-
 tools/perf/util/mmap.h      |  1 -
 tools/perf/util/zstd.c      | 63 +++++++++++++++++++------------------
 5 files changed, 59 insertions(+), 43 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8ec818568662e..9b4f3805ca92f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -270,7 +270,7 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 
 static int record__aio_enabled(struct record *rec);
 static int record__comp_enabled(struct record *rec);
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size);
 
 #ifdef HAVE_AIO_SUPPORT
@@ -405,9 +405,13 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size
 	 */
 
 	if (record__comp_enabled(aio->rec)) {
-		size = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
-				     mmap__mmap_len(map) - aio->size,
-				     buf, size);
+		ssize_t compressed = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
+						   mmap__mmap_len(map) - aio->size,
+						   buf, size);
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 	} else {
 		memcpy(aio->data + aio->size, buf, size);
 	}
@@ -633,7 +637,13 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
-		size = zstd_compress(rec->session, map, map->data, mmap__mmap_len(map), bf, size);
+		ssize_t compressed = zstd_compress(rec->session, map, map->data,
+						   mmap__mmap_len(map), bf, size);
+
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 		bf   = map->data;
 	}
 
@@ -1527,10 +1537,10 @@ static size_t process_comp_header(void *record, size_t increment)
 	return size;
 }
 
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size)
 {
-	size_t compressed;
+	ssize_t compressed;
 	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
 	struct zstd_data *zstd_data = &session->zstd_data;
 
@@ -1539,6 +1549,8 @@ static size_t zstd_compress(struct perf_session *session, struct mmap *map,
 
 	compressed = zstd_compress_stream_to_records(zstd_data, dst, dst_size, src, src_size,
 						     max_record_size, process_comp_header);
+	if (compressed < 0)
+		return compressed;
 
 	if (map && map->file) {
 		thread->bytes_transferred += src_size;
diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
index 0cd3369af2a4f..b29109cd36095 100644
--- a/tools/perf/util/compress.h
+++ b/tools/perf/util/compress.h
@@ -3,6 +3,8 @@
 #define PERF_COMPRESS_H
 
 #include <stdbool.h>
+#include <stddef.h>
+#include <sys/types.h>
 #ifdef HAVE_ZSTD_SUPPORT
 #include <zstd.h>
 #endif
@@ -21,6 +23,7 @@ struct zstd_data {
 #ifdef HAVE_ZSTD_SUPPORT
 	ZSTD_CStream	*cstream;
 	ZSTD_DStream	*dstream;
+	int comp_level;
 #endif
 };
 
@@ -29,7 +32,7 @@ struct zstd_data {
 int zstd_init(struct zstd_data *data, int level);
 int zstd_fini(struct zstd_data *data);
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment));
 
@@ -48,7 +51,7 @@ static inline int zstd_fini(struct zstd_data *data __maybe_unused)
 }
 
 static inline
-size_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
 				       void *dst __maybe_unused, size_t dst_size __maybe_unused,
 				       void *src __maybe_unused, size_t src_size __maybe_unused,
 				       size_t max_record_size __maybe_unused,
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 49093b21ee2da..122ee198a86e9 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -295,15 +295,14 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu
 
 	map->core.flush = mp->flush;
 
-	map->comp_level = mp->comp_level;
 #ifndef PYTHON_PERF
-	if (zstd_init(&map->zstd_data, map->comp_level)) {
+	if (zstd_init(&map->zstd_data, mp->comp_level)) {
 		pr_debug2("failed to init mmap compressor, error %d\n", errno);
 		return -1;
 	}
 #endif
 
-	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
+	if (mp->comp_level && !perf_mmap__aio_enabled(map)) {
 		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
 				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
 		if (map->data == MAP_FAILED) {
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index f944c3cd5efa0..0df6e1621c7e8 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -39,7 +39,6 @@ struct mmap {
 #endif
 	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
-	int		comp_level;
 	struct perf_data_file *file;
 	struct zstd_data      zstd_data;
 };
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index 48dd2b018c47a..57027e0ac7b65 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -7,35 +7,9 @@
 
 int zstd_init(struct zstd_data *data, int level)
 {
-	size_t ret;
-
-	data->dstream = ZSTD_createDStream();
-	if (data->dstream == NULL) {
-		pr_err("Couldn't create decompression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initDStream(data->dstream);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize decompression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
-	if (!level)
-		return 0;
-
-	data->cstream = ZSTD_createCStream();
-	if (data->cstream == NULL) {
-		pr_err("Couldn't create compression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initCStream(data->cstream, level);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize compression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
+	data->comp_level = level;
+	data->dstream = NULL;
+	data->cstream = NULL;
 	return 0;
 }
 
@@ -54,7 +28,7 @@ int zstd_fini(struct zstd_data *data)
 	return 0;
 }
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment))
 {
@@ -63,6 +37,21 @@ size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t
 	ZSTD_outBuffer output;
 	void *record;
 
+	if (!data->cstream) {
+		data->cstream = ZSTD_createCStream();
+		if (data->cstream == NULL) {
+			pr_err("Couldn't create compression stream.\n");
+			return -1;
+		}
+
+		ret = ZSTD_initCStream(data->cstream, data->comp_level);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize compression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return -1;
+		}
+	}
+
 	while (input.pos < input.size) {
 		record = dst;
 		size = process_header(record, 0);
@@ -96,6 +85,20 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size
 	ZSTD_inBuffer input = { src, src_size, 0 };
 	ZSTD_outBuffer output = { dst, dst_size, 0 };
 
+	if (!data->dstream) {
+		data->dstream = ZSTD_createDStream();
+		if (data->dstream == NULL) {
+			pr_err("Couldn't create decompression stream.\n");
+			return 0;
+		}
+
+		ret = ZSTD_initDStream(data->dstream);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize decompression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return 0;
+		}
+	}
 	while (input.pos < input.size) {
 		ret = ZSTD_decompressStream(data->dstream, &output, &input);
 		if (ZSTD_isError(ret)) {
-- 
GitLab


From 736dfbde3a842422b3e1fe0f881ef2c82b04f269 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 12 Nov 2023 01:00:30 +0100
Subject: [PATCH 0570/4076] platform/goldfish: goldfish_pipe: Convert to
 platform remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231112000029.151117-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/platform/goldfish/goldfish_pipe.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
index 7737d56191d7c..061aa9647c191 100644
--- a/drivers/platform/goldfish/goldfish_pipe.c
+++ b/drivers/platform/goldfish/goldfish_pipe.c
@@ -915,12 +915,11 @@ static int goldfish_pipe_probe(struct platform_device *pdev)
 	return goldfish_pipe_device_init(pdev, dev);
 }
 
-static int goldfish_pipe_remove(struct platform_device *pdev)
+static void goldfish_pipe_remove(struct platform_device *pdev)
 {
 	struct goldfish_pipe_dev *dev = platform_get_drvdata(pdev);
 
 	goldfish_pipe_device_deinit(pdev, dev);
-	return 0;
 }
 
 static const struct acpi_device_id goldfish_pipe_acpi_match[] = {
@@ -937,7 +936,7 @@ MODULE_DEVICE_TABLE(of, goldfish_pipe_of_match);
 
 static struct platform_driver goldfish_pipe_driver = {
 	.probe = goldfish_pipe_probe,
-	.remove = goldfish_pipe_remove,
+	.remove_new = goldfish_pipe_remove,
 	.driver = {
 		.name = "goldfish_pipe",
 		.of_match_table = goldfish_pipe_of_match,
-- 
GitLab


From 110684d58bdb715032bc7fc92ebdb554ae7deeb6 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Fri, 10 Nov 2023 12:44:00 +0100
Subject: [PATCH 0571/4076] vgacon: drop IA64 reference in VGA_CONSOLE
 dependency list

Commit e9e3300b6e77 ("vgacon: rework Kconfig dependencies") turns the
dependencies into a positive list of supported architectures, which
includes the IA64 architecture, but in the meantime, this architecture is
removed in commit cf8e8658100d ("arch: Remove Itanium (IA-64)
architecture").

Drop the reference to IA64 architecture in the dependency list of the
VGA_CONSOLE config definition.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Link: https://lore.kernel.org/r/20231110114400.30882-1-lukas.bulwahn@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/video/console/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index 83c2d7329ca58..bc31db6ef7d26 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -7,7 +7,7 @@ menu "Console display driver support"
 
 config VGA_CONSOLE
 	bool "VGA text console" if EXPERT || !X86
-	depends on ALPHA || IA64 || X86 || \
+	depends on ALPHA || X86 || \
 		(ARM && ARCH_FOOTBRIDGE) || \
 		(MIPS && (MIPS_MALTA || SIBYTE_BCM112X || SIBYTE_SB1250 || SIBYTE_BCM1x80 || SNI_RM))
 	select APERTURE_HELPERS if (DRM || FB || VFIO_PCI_CORE)
-- 
GitLab


From b9873755a6c8ccfce79094c4dce9efa3ecb1a749 Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Wed, 11 Oct 2023 21:35:22 +0000
Subject: [PATCH 0572/4076] misc: Add Nitro Secure Module driver

When running Linux inside a Nitro Enclave, the hypervisor provides a
special virtio device called "Nitro Security Module" (NSM). This device
has 3 main functions:

  1) Provide attestation reports
  2) Modify PCR state
  3) Provide entropy

This patch adds a driver for NSM that exposes a /dev/nsm device node which
user space can issue an ioctl on this device with raw NSM CBOR formatted
commands to request attestation documents, influence PCR states, read
entropy and enumerate status of the device. In addition, the driver
implements a hwrng backend.

Originally-by: Petre Eftime <petre.eftime@gmail.com>
Signed-off-by: Alexander Graf <graf@amazon.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20231011213522.51781-1-graf@amazon.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS              |   9 +
 drivers/misc/Kconfig     |  13 +
 drivers/misc/Makefile    |   1 +
 drivers/misc/nsm.c       | 506 +++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/nsm.h |  31 +++
 5 files changed, 560 insertions(+)
 create mode 100644 drivers/misc/nsm.c
 create mode 100644 include/uapi/linux/nsm.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 012df8ccf34e9..b9bbbd82742a1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15291,6 +15291,15 @@ F:	include/linux/nitro_enclaves.h
 F:	include/uapi/linux/nitro_enclaves.h
 F:	samples/nitro_enclaves/
 
+NITRO SECURE MODULE (NSM)
+M:	Alexander Graf <graf@amazon.com>
+L:	linux-kernel@vger.kernel.org
+L:	The AWS Nitro Enclaves Team <aws-nitro-enclaves-devel@amazon.com>
+S:	Supported
+W:	https://aws.amazon.com/ec2/nitro/nitro-enclaves/
+F:	drivers/misc/nsm.c
+F:	include/uapi/linux/nsm.h
+
 NOHZ, DYNTICKS SUPPORT
 M:	Frederic Weisbecker <frederic@kernel.org>
 M:	Thomas Gleixner <tglx@linutronix.de>
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index f37c4b8380ae6..8932b6cf9595d 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -562,6 +562,19 @@ config TPS6594_PFSM
 	  This driver can also be built as a module.  If so, the module
 	  will be called tps6594-pfsm.
 
+config NSM
+	tristate "Nitro (Enclaves) Security Module support"
+	depends on VIRTIO
+	select HW_RANDOM
+	select CBOR
+	help
+	  This driver provides support for the Nitro Security Module
+	  in AWS EC2 Nitro based Enclaves. The driver exposes a /dev/nsm
+	  device user space can use to communicate with the hypervisor.
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called nsm.
+
 source "drivers/misc/c2port/Kconfig"
 source "drivers/misc/eeprom/Kconfig"
 source "drivers/misc/cb710/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index f2a4d1ff65d46..ea6ea5bbbc9c6 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -67,3 +67,4 @@ obj-$(CONFIG_TMR_MANAGER)      += xilinx_tmr_manager.o
 obj-$(CONFIG_TMR_INJECT)	+= xilinx_tmr_inject.o
 obj-$(CONFIG_TPS6594_ESM)	+= tps6594-esm.o
 obj-$(CONFIG_TPS6594_PFSM)	+= tps6594-pfsm.o
+obj-$(CONFIG_NSM)		+= nsm.o
diff --git a/drivers/misc/nsm.c b/drivers/misc/nsm.c
new file mode 100644
index 0000000000000..0eaa3b4484bda
--- /dev/null
+++ b/drivers/misc/nsm.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Amazon Nitro Secure Module driver.
+ *
+ * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * The Nitro Secure Module implements commands via CBOR over virtio.
+ * This driver exposes a raw message ioctls on /dev/nsm that user
+ * space can use to issue these commands.
+ */
+
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/interrupt.h>
+#include <linux/hw_random.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/uio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio.h>
+#include <linux/wait.h>
+#include <uapi/linux/nsm.h>
+
+/* Timeout for NSM virtqueue respose in milliseconds. */
+#define NSM_DEFAULT_TIMEOUT_MSECS (120000) /* 2 minutes */
+
+/* Maximum length input data */
+struct nsm_data_req {
+	u32 len;
+	u8  data[NSM_REQUEST_MAX_SIZE];
+};
+
+/* Maximum length output data */
+struct nsm_data_resp {
+	u32 len;
+	u8  data[NSM_RESPONSE_MAX_SIZE];
+};
+
+/* Full NSM request/response message */
+struct nsm_msg {
+	struct nsm_data_req req;
+	struct nsm_data_resp resp;
+};
+
+struct nsm {
+	struct virtio_device *vdev;
+	struct virtqueue     *vq;
+	struct mutex          lock;
+	struct completion     cmd_done;
+	struct miscdevice     misc;
+	struct hwrng          hwrng;
+	struct work_struct    misc_init;
+	struct nsm_msg        msg;
+};
+
+/* NSM device ID */
+static const struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_NITRO_SEC_MOD, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static struct nsm *file_to_nsm(struct file *file)
+{
+	return container_of(file->private_data, struct nsm, misc);
+}
+
+static struct nsm *hwrng_to_nsm(struct hwrng *rng)
+{
+	return container_of(rng, struct nsm, hwrng);
+}
+
+#define CBOR_TYPE_MASK  0xE0
+#define CBOR_TYPE_MAP 0xA0
+#define CBOR_TYPE_TEXT 0x60
+#define CBOR_TYPE_ARRAY 0x40
+#define CBOR_HEADER_SIZE_SHORT 1
+
+#define CBOR_SHORT_SIZE_MAX_VALUE 23
+#define CBOR_LONG_SIZE_U8  24
+#define CBOR_LONG_SIZE_U16 25
+#define CBOR_LONG_SIZE_U32 26
+#define CBOR_LONG_SIZE_U64 27
+
+static bool cbor_object_is_array(const u8 *cbor_object, size_t cbor_object_size)
+{
+	if (cbor_object_size == 0 || cbor_object == NULL)
+		return false;
+
+	return (cbor_object[0] & CBOR_TYPE_MASK) == CBOR_TYPE_ARRAY;
+}
+
+static int cbor_object_get_array(u8 *cbor_object, size_t cbor_object_size, u8 **cbor_array)
+{
+	u8 cbor_short_size;
+	void *array_len_p;
+	u64 array_len;
+	u64 array_offset;
+
+	if (!cbor_object_is_array(cbor_object, cbor_object_size))
+		return -EFAULT;
+
+	cbor_short_size = (cbor_object[0] & 0x1F);
+
+	/* Decoding byte array length */
+	array_offset = CBOR_HEADER_SIZE_SHORT;
+	if (cbor_short_size >= CBOR_LONG_SIZE_U8)
+		array_offset += BIT(cbor_short_size - CBOR_LONG_SIZE_U8);
+
+	if (cbor_object_size < array_offset)
+		return -EFAULT;
+
+	array_len_p = &cbor_object[1];
+
+	switch (cbor_short_size) {
+	case CBOR_SHORT_SIZE_MAX_VALUE: /* short encoding */
+		array_len = cbor_short_size;
+		break;
+	case CBOR_LONG_SIZE_U8:
+		array_len = *(u8 *)array_len_p;
+		break;
+	case CBOR_LONG_SIZE_U16:
+		array_len = be16_to_cpup((__be16 *)array_len_p);
+		break;
+	case CBOR_LONG_SIZE_U32:
+		array_len = be32_to_cpup((__be32 *)array_len_p);
+		break;
+	case CBOR_LONG_SIZE_U64:
+		array_len = be64_to_cpup((__be64 *)array_len_p);
+		break;
+	}
+
+	if (cbor_object_size < array_offset)
+		return -EFAULT;
+
+	if (cbor_object_size - array_offset < array_len)
+		return -EFAULT;
+
+	if (array_len > INT_MAX)
+		return -EFAULT;
+
+	*cbor_array = cbor_object + array_offset;
+	return array_len;
+}
+
+/* Copy the request of a raw message to kernel space */
+static int fill_req_raw(struct nsm *nsm, struct nsm_data_req *req,
+			struct nsm_raw *raw)
+{
+	/* Verify the user input size. */
+	if (raw->request.len > sizeof(req->data))
+		return -EMSGSIZE;
+
+	/* Copy the request payload */
+	if (copy_from_user(req->data, u64_to_user_ptr(raw->request.addr),
+			   raw->request.len))
+		return -EFAULT;
+
+	req->len = raw->request.len;
+
+	return 0;
+}
+
+/* Copy the response of a raw message back to user-space */
+static int parse_resp_raw(struct nsm *nsm, struct nsm_data_resp *resp,
+			  struct nsm_raw *raw)
+{
+	/* Truncate any message that does not fit. */
+	raw->response.len = min_t(u64, raw->response.len, resp->len);
+
+	/* Copy the response content to user space */
+	if (copy_to_user(u64_to_user_ptr(raw->response.addr),
+			 resp->data, raw->response.len))
+		return -EFAULT;
+
+	return 0;
+}
+
+/* Virtqueue interrupt handler */
+static void nsm_vq_callback(struct virtqueue *vq)
+{
+	struct nsm *nsm = vq->vdev->priv;
+
+	complete(&nsm->cmd_done);
+}
+
+/* Forward a message to the NSM device and wait for the response from it */
+static int nsm_sendrecv_msg_locked(struct nsm *nsm)
+{
+	struct device *dev = &nsm->vdev->dev;
+	struct scatterlist sg_in, sg_out;
+	struct nsm_msg *msg = &nsm->msg;
+	struct virtqueue *vq = nsm->vq;
+	unsigned int len;
+	void *queue_buf;
+	bool kicked;
+	int rc;
+
+	/* Initialize scatter-gather lists with request and response buffers. */
+	sg_init_one(&sg_out, msg->req.data, msg->req.len);
+	sg_init_one(&sg_in, msg->resp.data, sizeof(msg->resp.data));
+
+	init_completion(&nsm->cmd_done);
+	/* Add the request buffer (read by the device). */
+	rc = virtqueue_add_outbuf(vq, &sg_out, 1, msg->req.data, GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	/* Add the response buffer (written by the device). */
+	rc = virtqueue_add_inbuf(vq, &sg_in, 1, msg->resp.data, GFP_KERNEL);
+	if (rc)
+		goto cleanup;
+
+	kicked = virtqueue_kick(vq);
+	if (!kicked) {
+		/* Cannot kick the virtqueue. */
+		rc = -EIO;
+		goto cleanup;
+	}
+
+	/* If the kick succeeded, wait for the device's response. */
+	if (!wait_for_completion_io_timeout(&nsm->cmd_done,
+		msecs_to_jiffies(NSM_DEFAULT_TIMEOUT_MSECS))) {
+		rc = -ETIMEDOUT;
+		goto cleanup;
+	}
+
+	queue_buf = virtqueue_get_buf(vq, &len);
+	if (!queue_buf || (queue_buf != msg->req.data)) {
+		dev_err(dev, "wrong request buffer.");
+		rc = -ENODATA;
+		goto cleanup;
+	}
+
+	queue_buf = virtqueue_get_buf(vq, &len);
+	if (!queue_buf || (queue_buf != msg->resp.data)) {
+		dev_err(dev, "wrong response buffer.");
+		rc = -ENODATA;
+		goto cleanup;
+	}
+
+	msg->resp.len = len;
+
+	rc = 0;
+
+cleanup:
+	if (rc) {
+		/* Clean the virtqueue. */
+		while (virtqueue_get_buf(vq, &len) != NULL)
+			;
+	}
+
+	return rc;
+}
+
+static int fill_req_get_random(struct nsm *nsm, struct nsm_data_req *req)
+{
+	/*
+	 * 69                          # text(9)
+	 *     47657452616E646F6D      # "GetRandom"
+	 */
+	const u8 request[] = { CBOR_TYPE_TEXT + strlen("GetRandom"),
+			       'G', 'e', 't', 'R', 'a', 'n', 'd', 'o', 'm' };
+
+	memcpy(req->data, request, sizeof(request));
+	req->len = sizeof(request);
+
+	return 0;
+}
+
+static int parse_resp_get_random(struct nsm *nsm, struct nsm_data_resp *resp,
+				 void *out, size_t max)
+{
+	/*
+	 * A1                          # map(1)
+	 *     69                      # text(9) - Name of field
+	 *         47657452616E646F6D  # "GetRandom"
+	 * A1                          # map(1) - The field itself
+	 *     66                      # text(6)
+	 *         72616E646F6D        # "random"
+	 *	# The rest of the response is random data
+	 */
+	const u8 response[] = { CBOR_TYPE_MAP + 1,
+				CBOR_TYPE_TEXT + strlen("GetRandom"),
+				'G', 'e', 't', 'R', 'a', 'n', 'd', 'o', 'm',
+				CBOR_TYPE_MAP + 1,
+				CBOR_TYPE_TEXT + strlen("random"),
+				'r', 'a', 'n', 'd', 'o', 'm' };
+	struct device *dev = &nsm->vdev->dev;
+	u8 *rand_data = NULL;
+	u8 *resp_ptr = resp->data;
+	u64 resp_len = resp->len;
+	int rc;
+
+	if ((resp->len < sizeof(response) + 1) ||
+	    (memcmp(resp_ptr, response, sizeof(response)) != 0)) {
+		dev_err(dev, "Invalid response for GetRandom");
+		return -EFAULT;
+	}
+
+	resp_ptr += sizeof(response);
+	resp_len -= sizeof(response);
+
+	rc = cbor_object_get_array(resp_ptr, resp_len, &rand_data);
+	if (rc < 0) {
+		dev_err(dev, "GetRandom: Invalid CBOR encoding\n");
+		return rc;
+	}
+
+	rc = min_t(size_t, rc, max);
+	memcpy(out, rand_data, rc);
+
+	return rc;
+}
+
+/*
+ * HwRNG implementation
+ */
+static int nsm_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	struct nsm *nsm = hwrng_to_nsm(rng);
+	struct device *dev = &nsm->vdev->dev;
+	int rc = 0;
+
+	/* NSM always needs to wait for a response */
+	if (!wait)
+		return 0;
+
+	mutex_lock(&nsm->lock);
+
+	rc = fill_req_get_random(nsm, &nsm->msg.req);
+	if (rc != 0)
+		goto out;
+
+	rc = nsm_sendrecv_msg_locked(nsm);
+	if (rc != 0)
+		goto out;
+
+	rc = parse_resp_get_random(nsm, &nsm->msg.resp, data, max);
+	if (rc < 0)
+		goto out;
+
+	dev_dbg(dev, "RNG: returning rand bytes = %d", rc);
+out:
+	mutex_unlock(&nsm->lock);
+	return rc;
+}
+
+static long nsm_dev_ioctl(struct file *file, unsigned int cmd,
+	unsigned long arg)
+{
+	void __user *argp = u64_to_user_ptr((u64)arg);
+	struct nsm *nsm = file_to_nsm(file);
+	struct nsm_raw raw;
+	int r = 0;
+
+	if (cmd != NSM_IOCTL_RAW)
+		return -EINVAL;
+
+	if (_IOC_SIZE(cmd) != sizeof(raw))
+		return -EINVAL;
+
+	/* Copy user argument struct to kernel argument struct */
+	r = -EFAULT;
+	if (copy_from_user(&raw, argp, _IOC_SIZE(cmd)))
+		goto out;
+
+	mutex_lock(&nsm->lock);
+
+	/* Convert kernel argument struct to device request */
+	r = fill_req_raw(nsm, &nsm->msg.req, &raw);
+	if (r)
+		goto out;
+
+	/* Send message to NSM and read reply */
+	r = nsm_sendrecv_msg_locked(nsm);
+	if (r)
+		goto out;
+
+	/* Parse device response into kernel argument struct */
+	r = parse_resp_raw(nsm, &nsm->msg.resp, &raw);
+	if (r)
+		goto out;
+
+	/* Copy kernel argument struct back to user argument struct */
+	r = -EFAULT;
+	if (copy_to_user(argp, &raw, sizeof(raw)))
+		goto out;
+
+	r = 0;
+
+out:
+	mutex_unlock(&nsm->lock);
+	return r;
+}
+
+static int nsm_device_init_vq(struct virtio_device *vdev)
+{
+	struct virtqueue *vq = virtio_find_single_vq(vdev,
+		nsm_vq_callback, "nsm.vq.0");
+	struct nsm *nsm = vdev->priv;
+
+	if (IS_ERR(vq))
+		return PTR_ERR(vq);
+
+	nsm->vq = vq;
+
+	return 0;
+}
+
+static const struct file_operations nsm_dev_fops = {
+	.unlocked_ioctl = nsm_dev_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+};
+
+/* Handler for probing the NSM device */
+static int nsm_device_probe(struct virtio_device *vdev)
+{
+	struct device *dev = &vdev->dev;
+	struct nsm *nsm;
+	int rc;
+
+	nsm = devm_kzalloc(&vdev->dev, sizeof(*nsm), GFP_KERNEL);
+	if (!nsm)
+		return -ENOMEM;
+
+	vdev->priv = nsm;
+	nsm->vdev = vdev;
+
+	rc = nsm_device_init_vq(vdev);
+	if (rc) {
+		dev_err(dev, "queue failed to initialize: %d.\n", rc);
+		goto err_init_vq;
+	}
+
+	mutex_init(&nsm->lock);
+
+	/* Register as hwrng provider */
+	nsm->hwrng = (struct hwrng) {
+		.read = nsm_rng_read,
+		.name = "nsm-hwrng",
+		.quality = 1000,
+	};
+
+	rc = hwrng_register(&nsm->hwrng);
+	if (rc) {
+		dev_err(dev, "RNG initialization error: %d.\n", rc);
+		goto err_hwrng;
+	}
+
+	/* Register /dev/nsm device node */
+	nsm->misc = (struct miscdevice) {
+		.minor	= MISC_DYNAMIC_MINOR,
+		.name	= "nsm",
+		.fops	= &nsm_dev_fops,
+		.mode	= 0666,
+	};
+
+	rc = misc_register(&nsm->misc);
+	if (rc) {
+		dev_err(dev, "misc device registration error: %d.\n", rc);
+		goto err_misc;
+	}
+
+	return 0;
+
+err_misc:
+	hwrng_unregister(&nsm->hwrng);
+err_hwrng:
+	vdev->config->del_vqs(vdev);
+err_init_vq:
+	return rc;
+}
+
+/* Handler for removing the NSM device */
+static void nsm_device_remove(struct virtio_device *vdev)
+{
+	struct nsm *nsm = vdev->priv;
+
+	hwrng_unregister(&nsm->hwrng);
+
+	vdev->config->del_vqs(vdev);
+	misc_deregister(&nsm->misc);
+}
+
+/* NSM device configuration structure */
+static struct virtio_driver virtio_nsm_driver = {
+	.feature_table             = 0,
+	.feature_table_size        = 0,
+	.feature_table_legacy      = 0,
+	.feature_table_size_legacy = 0,
+	.driver.name               = KBUILD_MODNAME,
+	.driver.owner              = THIS_MODULE,
+	.id_table                  = id_table,
+	.probe                     = nsm_device_probe,
+	.remove                    = nsm_device_remove,
+};
+
+module_virtio_driver(virtio_nsm_driver);
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_DESCRIPTION("Virtio NSM driver");
+MODULE_LICENSE("GPL");
diff --git a/include/uapi/linux/nsm.h b/include/uapi/linux/nsm.h
new file mode 100644
index 0000000000000..e529f232f6c04
--- /dev/null
+++ b/include/uapi/linux/nsm.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef __UAPI_LINUX_NSM_H
+#define __UAPI_LINUX_NSM_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define NSM_MAGIC		0x0A
+
+#define NSM_REQUEST_MAX_SIZE	0x1000
+#define NSM_RESPONSE_MAX_SIZE	0x3000
+
+struct nsm_iovec {
+	__u64 addr; /* Virtual address of target buffer */
+	__u64 len;  /* Length of target buffer */
+};
+
+/* Raw NSM message. Only available with CAP_SYS_ADMIN. */
+struct nsm_raw {
+	/* Request from user */
+	struct nsm_iovec request;
+	/* Response to user */
+	struct nsm_iovec response;
+};
+#define NSM_IOCTL_RAW		_IOWR(NSM_MAGIC, 0x0, struct nsm_raw)
+
+#endif /* __UAPI_LINUX_NSM_H */
-- 
GitLab


From a3db64c575ca201c9783f100c70b82d52bd78a93 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Mon, 27 Nov 2023 13:37:09 +0100
Subject: [PATCH 0573/4076] tty: make tty const in tty_get_baud_rate()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 87888fb9ac0c ("tty: Remove baudrate dead code & make
ktermios params const"), the 'tty' parameter is only read in
tty_get_baud_rate(). Therefore, we can make 'tty' accepted in the
function 'const' for clarity.

The "the terminal bit flags may be updated." part of the
tty_get_baud_rate()'s kernel-doc is dropped as it is no longer true.
Because of the same commit above. And it was misplaced anyway.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231127123713.14504-1-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 7625fc98fef3f..e96c85f4f91ed 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -440,10 +440,9 @@ void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud,
  *
  * Returns: the baud rate as an integer for this terminal
  *
- * Locking: The termios lock must be held by the caller and the terminal bit
- * flags may be updated.
+ * Locking: The termios lock must be held by the caller.
  */
-static inline speed_t tty_get_baud_rate(struct tty_struct *tty)
+static inline speed_t tty_get_baud_rate(const struct tty_struct *tty)
 {
 	return tty_termios_baud_rate(&tty->termios);
 }
-- 
GitLab


From ff4b8c3a8be98fee16a8ab7751a5834088e60b23 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Mon, 27 Nov 2023 13:37:10 +0100
Subject: [PATCH 0574/4076] tty: srmcons: make srmcons_do_write() return void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The return value of srmcons_do_write() is ignored as all characters are
pushed. So make srmcons_do_write() to return void.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: linux-alpha@vger.kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231127123713.14504-2-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/alpha/kernel/srmcons.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index b68c5af083cd1..de896fa9829ef 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -88,7 +88,7 @@ srmcons_receive_chars(struct timer_list *t)
 }
 
 /* called with callback_lock held */
-static int
+static void
 srmcons_do_write(struct tty_port *port, const char *buf, int count)
 {
 	static char str_cr[1] = "\r";
@@ -125,7 +125,6 @@ srmcons_do_write(struct tty_port *port, const char *buf, int count)
 				need_cr = 0;
 		}
 	}
-	return count;
 }
 
 static ssize_t
-- 
GitLab


From ad1885559249fa2530cb0659b758583873dc906f Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Mon, 27 Nov 2023 13:37:11 +0100
Subject: [PATCH 0575/4076] tty: srmcons: use 'count' directly in
 srmcons_do_write()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Similarly to 'buf' in the previous patch, there is no need to have a
separate counter ('remaining') in srmcons_do_write(). 'count' can be
used directly which simplifies the code a bit.

Note that the type of the current count ('c') is changed from 'long' to
'size_t' so that:
1) it is prepared for the upcoming change of 'count's type, and
2) is unsigned.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: linux-alpha@vger.kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231127123713.14504-3-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/alpha/kernel/srmcons.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index de896fa9829ef..32bc098de7da1 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -92,24 +92,24 @@ static void
 srmcons_do_write(struct tty_port *port, const char *buf, int count)
 {
 	static char str_cr[1] = "\r";
-	long c, remaining = count;
+	size_t c;
 	srmcons_result result;
 	int need_cr;
 
-	while (remaining > 0) {
+	while (count > 0) {
 		need_cr = 0;
 		/* 
 		 * Break it up into reasonable size chunks to allow a chance
 		 * for input to get in
 		 */
-		for (c = 0; c < min_t(long, 128L, remaining) && !need_cr; c++)
+		for (c = 0; c < min_t(size_t, 128U, count) && !need_cr; c++)
 			if (buf[c] == '\n')
 				need_cr = 1;
 		
 		while (c > 0) {
 			result.as_long = callback_puts(0, buf, c);
 			c -= result.bits.c;
-			remaining -= result.bits.c;
+			count -= result.bits.c;
 			buf += result.bits.c;
 
 			/*
-- 
GitLab


From 2ea2ac84ef357dcaf11a80b303d391fb6c2510d8 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Mon, 27 Nov 2023 13:37:12 +0100
Subject: [PATCH 0576/4076] tty: srmcons: switch need_cr to bool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'need_cr' is a flag, so type it properly to be a 'bool'. Move the
declaration into the loop too. That ensures the variable is initialized
properly even if the code was moved somehow.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: linux-alpha@vger.kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231127123713.14504-4-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/alpha/kernel/srmcons.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 32bc098de7da1..c6b821afbfd3a 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -94,17 +94,16 @@ srmcons_do_write(struct tty_port *port, const char *buf, int count)
 	static char str_cr[1] = "\r";
 	size_t c;
 	srmcons_result result;
-	int need_cr;
 
 	while (count > 0) {
-		need_cr = 0;
+		bool need_cr = false;
 		/* 
 		 * Break it up into reasonable size chunks to allow a chance
 		 * for input to get in
 		 */
 		for (c = 0; c < min_t(size_t, 128U, count) && !need_cr; c++)
 			if (buf[c] == '\n')
-				need_cr = 1;
+				need_cr = true;
 		
 		while (c > 0) {
 			result.as_long = callback_puts(0, buf, c);
@@ -122,7 +121,7 @@ srmcons_do_write(struct tty_port *port, const char *buf, int count)
 		while (need_cr) {
 			result.as_long = callback_puts(0, str_cr, 1);
 			if (result.bits.c > 0)
-				need_cr = 0;
+				need_cr = false;
 		}
 	}
 }
-- 
GitLab


From 068ab2135b3fe0d8957f099a5b860117457825ec Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Mon, 27 Nov 2023 13:37:13 +0100
Subject: [PATCH 0577/4076] tty: srmcons: remove 'str_cr' and use string
 directly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'str_cr' contains a single character: \r. There is no need to declare it
as array. Instead, pass the character (as a string) to callback_puts()
directly. This ensures the string is in proper .rodata (const) section
and makes the code more obvious.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: linux-alpha@vger.kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231127123713.14504-5-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/alpha/kernel/srmcons.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index c6b821afbfd3a..42deea53beab2 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -91,7 +91,6 @@ srmcons_receive_chars(struct timer_list *t)
 static void
 srmcons_do_write(struct tty_port *port, const char *buf, int count)
 {
-	static char str_cr[1] = "\r";
 	size_t c;
 	srmcons_result result;
 
@@ -119,7 +118,7 @@ srmcons_do_write(struct tty_port *port, const char *buf, int count)
 		}
 
 		while (need_cr) {
-			result.as_long = callback_puts(0, str_cr, 1);
+			result.as_long = callback_puts(0, "\r", 1);
 			if (result.bits.c > 0)
 				need_cr = false;
 		}
-- 
GitLab


From ca41ae8f445e0bb88fa84584b451bfbf39b2e7f1 Mon Sep 17 00:00:00 2001
From: Rohit Agarwal <quic_rohiagar@quicinc.com>
Date: Fri, 17 Nov 2023 13:58:29 +0530
Subject: [PATCH 0578/4076] dt-bindings: interrupt-controller: Add SDX75 PDC
 compatible

Add device tree bindings for PDC on SDX75 SOC.

Signed-off-by: Rohit Agarwal <quic_rohiagar@quicinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231117082829.609882-1-quic_rohiagar@quicinc.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/interrupt-controller/qcom,pdc.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
index 8473afffce63b..c879f0d2e07f7 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
@@ -35,6 +35,7 @@ properties:
           - qcom,sdm845-pdc
           - qcom,sdx55-pdc
           - qcom,sdx65-pdc
+          - qcom,sdx75-pdc
           - qcom,sm4450-pdc
           - qcom,sm6350-pdc
           - qcom,sm8150-pdc
-- 
GitLab


From c1c647f604a55e73c6980046cc56df574402e362 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Wed, 25 Oct 2023 09:27:36 +0200
Subject: [PATCH 0579/4076] dt-bindings: qcom,pdc: document the SM8650 Power
 Domain Controller

Document the Power Domain Controller on the SM8650 Platform.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231025-topic-sm8650-upstream-bindings-pdc-v1-1-42f62cc9858c@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/interrupt-controller/qcom,pdc.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
index c879f0d2e07f7..7d8592cef1c0b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
@@ -43,6 +43,7 @@ properties:
           - qcom,sm8350-pdc
           - qcom,sm8450-pdc
           - qcom,sm8550-pdc
+          - qcom,sm8650-pdc
       - const: qcom,pdc
 
   reg:
-- 
GitLab


From daa9249408fcb4985351d91f166fc0e27d255014 Mon Sep 17 00:00:00 2001
From: Sibi Sankar <quic_sibis@quicinc.com>
Date: Fri, 24 Nov 2023 15:36:08 +0530
Subject: [PATCH 0580/4076] dt-bindings: interrupt-controller: qcom,pdc:
 document pdc on X1E80100

The X1E80100 SoC includes a PDC, document it.

Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231124100608.29964-6-quic_sibis@quicinc.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/interrupt-controller/qcom,pdc.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
index 7d8592cef1c0b..4bdc8321904bd 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml
@@ -44,6 +44,7 @@ properties:
           - qcom,sm8450-pdc
           - qcom,sm8550-pdc
           - qcom,sm8650-pdc
+          - qcom,x1e80100-pdc
       - const: qcom,pdc
 
   reg:
-- 
GitLab


From 9e7f72d452477819977f047bddfbec7f66489f3b Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 22 Nov 2023 15:44:19 -0700
Subject: [PATCH 0581/4076] dt-bindings: fsl,dpaa2-console: drop unneeded
 quotes

Drop unneeded quotes over simple string values to fix a soon to be
enabled yamllint warning:

  [error] string value is redundantly quoted with any quotes (quoted-strings)

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231122224419.2809361-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml b/Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml
index 8cc951feb7df4..59b83ea5e05ee 100644
--- a/Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml
+++ b/Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml
@@ -12,7 +12,7 @@ maintainers:
 
 properties:
   compatible:
-    const: "fsl,dpaa2-console"
+    const: fsl,dpaa2-console
 
   reg:
     maxItems: 1
-- 
GitLab


From 67f7a63ecc712dbc307c04a1a7fbf32d1aa864df Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 22 Nov 2023 15:44:32 -0700
Subject: [PATCH 0582/4076] dt-bindings: arm/calxeda: drop unneeded quotes

Drop unneeded quotes over simple string values to fix a soon to be
enabled yamllint warning:

  [error] string value is redundantly quoted with any quotes (quoted-strings)

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231122224432.2809781-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/arm/calxeda/l2ecc.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/arm/calxeda/l2ecc.yaml b/Documentation/devicetree/bindings/arm/calxeda/l2ecc.yaml
index a9fe01238a885..76b65ea149b65 100644
--- a/Documentation/devicetree/bindings/arm/calxeda/l2ecc.yaml
+++ b/Documentation/devicetree/bindings/arm/calxeda/l2ecc.yaml
@@ -16,7 +16,7 @@ maintainers:
 
 properties:
   compatible:
-    const: "calxeda,hb-sregs-l2-ecc"
+    const: calxeda,hb-sregs-l2-ecc
 
   reg:
     maxItems: 1
-- 
GitLab


From d804987153e7bedf503f8e4ba649afe52cfd7f6d Mon Sep 17 00:00:00 2001
From: Vamshi Gajjela <vamshigajjela@google.com>
Date: Sun, 26 Nov 2023 21:34:20 +0530
Subject: [PATCH 0583/4076] serial: 8250_dw: Decouple DLF register check from
 UCV

Designware UART has an optional feature to enable Fractional Baud Rate
Divisor (DLF) through the FRACTIONAL_BAUD_DIVISOR_EN configuration
parameter, and it is not dependent on ADDITIONAL_FEATURES.

dw8250_setup_port() checks DLF to determine dlf_size only when UART
Component Version (UCV) is non-zero. As mentioned above DLF and UCV are
independent features. Move the logic corresponding to DLF size
calculation ahead of the UCV check to prevent early return. Otherwise,
dlf_size will be zero and driver will not be able to use the
controller's fractional baud rate divisor (DLF) feature.

Signed-off-by: Vamshi Gajjela <vamshigajjela@google.com>
Link: https://lore.kernel.org/r/20231126160420.2442330-1-vamshigajjela@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_dwlib.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_dwlib.c b/drivers/tty/serial/8250/8250_dwlib.c
index 84843e204a5e8..136ad093c5b60 100644
--- a/drivers/tty/serial/8250/8250_dwlib.c
+++ b/drivers/tty/serial/8250/8250_dwlib.c
@@ -259,17 +259,6 @@ void dw8250_setup_port(struct uart_port *p)
 	}
 	up->capabilities |= UART_CAP_NOTEMT;
 
-	/*
-	 * If the Component Version Register returns zero, we know that
-	 * ADDITIONAL_FEATURES are not enabled. No need to go any further.
-	 */
-	reg = dw8250_readl_ext(p, DW_UART_UCV);
-	if (!reg)
-		return;
-
-	dev_dbg(p->dev, "Designware UART version %c.%c%c\n",
-		(reg >> 24) & 0xff, (reg >> 16) & 0xff, (reg >> 8) & 0xff);
-
 	/* Preserve value written by firmware or bootloader  */
 	old_dlf = dw8250_readl_ext(p, DW_UART_DLF);
 	dw8250_writel_ext(p, DW_UART_DLF, ~0U);
@@ -282,6 +271,17 @@ void dw8250_setup_port(struct uart_port *p)
 		p->set_divisor = dw8250_set_divisor;
 	}
 
+	/*
+	 * If the Component Version Register returns zero, we know that
+	 * ADDITIONAL_FEATURES are not enabled. No need to go any further.
+	 */
+	reg = dw8250_readl_ext(p, DW_UART_UCV);
+	if (!reg)
+		return;
+
+	dev_dbg(p->dev, "Designware UART version %c.%c%c\n",
+		(reg >> 24) & 0xff, (reg >> 16) & 0xff, (reg >> 8) & 0xff);
+
 	reg = dw8250_readl_ext(p, DW_UART_CPR);
 	if (!reg) {
 		reg = data->pdata->cpr_val;
-- 
GitLab


From eec4954b81c3d9a38b99e78afb553c359db40093 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 28 Nov 2023 10:28:15 +0000
Subject: [PATCH 0584/4076] driver core: make device_is_dependent() static

The function device_is_dependent() is only called by the driver core
internally and should not, at this time, be called by anyone else
outside of it, so mark it as static so as not to give driver authors the
wrong idea.

Cc: Saravana Kannan <saravanak@google.com>
Acked-by: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://lore.kernel.org/r/2023112815-faculty-thud-add8@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 2 +-
 include/linux/device.h | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 67ba592afc777..e574671941041 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -298,7 +298,7 @@ static inline bool device_link_flag_is_sync_state_only(u32 flags)
  * Check if @target depends on @dev or any device dependent on it (its child or
  * its consumer etc).  Return 1 if that is the case or 0 otherwise.
  */
-int device_is_dependent(struct device *dev, void *target)
+static int device_is_dependent(struct device *dev, void *target)
 {
 	struct device_link *link;
 	int ret;
diff --git a/include/linux/device.h b/include/linux/device.h
index d7a72a8749ea0..4aa34c8d13610 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1071,7 +1071,6 @@ int device_rename(struct device *dev, const char *new_name);
 int device_move(struct device *dev, struct device *new_parent,
 		enum dpm_order dpm_order);
 int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
-int device_is_dependent(struct device *dev, void *target);
 
 static inline bool device_supports_offline(struct device *dev)
 {
-- 
GitLab


From 3b99d46a1170754a06f379a83be8101c5f6bfc46 Mon Sep 17 00:00:00 2001
From: angquan yu <angquan21@gmail.com>
Date: Tue, 28 Nov 2023 16:11:05 -0600
Subject: [PATCH 0585/4076] KVM: selftests: Actually print out magic token in
 NX hugepages skip message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pass MAGIC_TOKEN to __TEST_REQUIRE() when printing the help message about
needing to pass a magic value to manually run the NX hugepages test,
otherwise the help message will contain garbage.

  In file included from x86_64/nx_huge_pages_test.c:15:
  x86_64/nx_huge_pages_test.c: In function ‘main’:
  include/test_util.h:40:32: error: format ‘%d’ expects a matching ‘int’ argument [-Werror=format=]
     40 |                 ksft_exit_skip("- " fmt "\n", ##__VA_ARGS__);   \
        |                                ^~~~
  x86_64/nx_huge_pages_test.c:259:9: note: in expansion of macro ‘__TEST_REQUIRE’
    259 |         __TEST_REQUIRE(token == MAGIC_TOKEN,
        |         ^~~~~~~~~~~~~~

Signed-off-by: angquan yu <angquan21@gmail.com>
Link: https://lore.kernel.org/r/20231128221105.63093-1-angquan21@gmail.com
[sean: rewrite shortlog+changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index 18ac5c1952a3a..83e25bccc139d 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -259,7 +259,7 @@ int main(int argc, char **argv)
 	__TEST_REQUIRE(token == MAGIC_TOKEN,
 		       "This test must be run with the magic token %d.\n"
 		       "This is done by nx_huge_pages_test.sh, which\n"
-		       "also handles environment setup for the test.");
+		       "also handles environment setup for the test.", MAGIC_TOKEN);
 
 	run_test(reclaim_period_ms, false, reboot_permissions);
 	run_test(reclaim_period_ms, true, reboot_permissions);
-- 
GitLab


From 7b0dd9430cf0c1ae19645d2a6608a5fb57faffe4 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:12 +0800
Subject: [PATCH 0586/4076] KVM: x86: Consolidate flags for __linearize()

Consolidate @write and @fetch of __linearize() into a set of flags so that
additional flags can be added without needing more/new boolean parameters,
to precisely identify the access type.

No functional change intended.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Acked-by: Kai Huang <kai.huang@intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-2-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/emulate.c     | 21 +++++++++++----------
 arch/x86/kvm/kvm_emulate.h |  4 ++++
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2673cd5c46cb4..87ee1802166a2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -687,8 +687,8 @@ static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size)
 static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 				       struct segmented_address addr,
 				       unsigned *max_size, unsigned size,
-				       bool write, bool fetch,
-				       enum x86emul_mode mode, ulong *linear)
+				       enum x86emul_mode mode, ulong *linear,
+				       unsigned int flags)
 {
 	struct desc_struct desc;
 	bool usable;
@@ -717,11 +717,11 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 		if (!usable)
 			goto bad;
 		/* code segment in protected mode or read-only data segment */
-		if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8))
-					|| !(desc.type & 2)) && write)
+		if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) || !(desc.type & 2)) &&
+		    (flags & X86EMUL_F_WRITE))
 			goto bad;
 		/* unreadable code segment */
-		if (!fetch && (desc.type & 8) && !(desc.type & 2))
+		if (!(flags & X86EMUL_F_FETCH) && (desc.type & 8) && !(desc.type & 2))
 			goto bad;
 		lim = desc_limit_scaled(&desc);
 		if (!(desc.type & 8) && (desc.type & 4)) {
@@ -757,8 +757,8 @@ static int linearize(struct x86_emulate_ctxt *ctxt,
 		     ulong *linear)
 {
 	unsigned max_size;
-	return __linearize(ctxt, addr, &max_size, size, write, false,
-			   ctxt->mode, linear);
+	return __linearize(ctxt, addr, &max_size, size, ctxt->mode, linear,
+			   write ? X86EMUL_F_WRITE : 0);
 }
 
 static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
@@ -771,7 +771,8 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
 
 	if (ctxt->op_bytes != sizeof(unsigned long))
 		addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
-	rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear);
+	rc = __linearize(ctxt, addr, &max_size, 1, ctxt->mode, &linear,
+			 X86EMUL_F_FETCH);
 	if (rc == X86EMUL_CONTINUE)
 		ctxt->_eip = addr.ea;
 	return rc;
@@ -907,8 +908,8 @@ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
 	 * boundary check itself.  Instead, we use max_size to check
 	 * against op_size.
 	 */
-	rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode,
-			 &linear);
+	rc = __linearize(ctxt, addr, &max_size, 0, ctxt->mode, &linear,
+			 X86EMUL_F_FETCH);
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return rc;
 
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index be7aeb9b8ea3b..e24c8ac7b9304 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -88,6 +88,10 @@ struct x86_instruction_info {
 #define X86EMUL_IO_NEEDED       5 /* IO is needed to complete emulation */
 #define X86EMUL_INTERCEPTED     6 /* Intercepted by nested VMCB/VMCS */
 
+/* x86-specific emulation flags */
+#define X86EMUL_F_WRITE			BIT(0)
+#define X86EMUL_F_FETCH			BIT(1)
+
 struct x86_emulate_ops {
 	void (*vm_bugged)(struct x86_emulate_ctxt *ctxt);
 	/*
-- 
GitLab


From 3963c52df42231f72277cd138994ac94f1183d2b Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:14 +0800
Subject: [PATCH 0587/4076] KVM: x86: Add an emulation flag for implicit system
 access

Add an emulation flag X86EMUL_F_IMPLICIT to identify implicit system access
in instruction emulation.  Don't bother wiring up any usage at this point,
as Linear Address Space Separation (LASS) will be the first "real" consumer
of the flag and LASS support will require dedicated hooks, i.e. there
aren't any existing calls where passing X86EMUL_F_IMPLICIT is meaningful.

Add the IMPLICIT flag even though there's no imminent usage so that
Linear Address Masking (LAM) support can reference the flag to document
that addresses for implicit accesses aren't untagged.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-4-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/kvm_emulate.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index e24c8ac7b9304..65fc7ef5ca3da 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -91,6 +91,7 @@ struct x86_instruction_info {
 /* x86-specific emulation flags */
 #define X86EMUL_F_WRITE			BIT(0)
 #define X86EMUL_F_FETCH			BIT(1)
+#define X86EMUL_F_IMPLICIT		BIT(2)
 
 struct x86_emulate_ops {
 	void (*vm_bugged)(struct x86_emulate_ctxt *ctxt);
-- 
GitLab


From 538ac9a92d669c4ccfc64739a32efab2793cea1d Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:15 +0800
Subject: [PATCH 0588/4076] KVM: x86: Add X86EMUL_F_INVLPG and pass it in
 em_invlpg()

Add an emulation flag X86EMUL_F_INVLPG, which is used to identify an
instruction that does TLB invalidation without true memory access.

Only invlpg & invlpga implemented in emulator belong to this kind.
invlpga doesn't need additional information for emulation. Just pass
the flag to em_invlpg().

Linear Address Masking (LAM) and Linear Address Space Separation (LASS)
don't apply to addresses that are inputs to TLB invalidation. The flag
will be consumed to support LAM/LASS virtualization.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-5-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/emulate.c     | 4 +++-
 arch/x86/kvm/kvm_emulate.h | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 87ee1802166a2..ceec8c5f96874 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3440,8 +3440,10 @@ static int em_invlpg(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	ulong linear;
+	unsigned int max_size;
 
-	rc = linearize(ctxt, ctxt->src.addr.mem, 1, false, &linear);
+	rc = __linearize(ctxt, ctxt->src.addr.mem, &max_size, 1, ctxt->mode,
+			 &linear, X86EMUL_F_INVLPG);
 	if (rc == X86EMUL_CONTINUE)
 		ctxt->ops->invlpg(ctxt, linear);
 	/* Disable writeback. */
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 65fc7ef5ca3da..8bd9b23543cc7 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -92,6 +92,7 @@ struct x86_instruction_info {
 #define X86EMUL_F_WRITE			BIT(0)
 #define X86EMUL_F_FETCH			BIT(1)
 #define X86EMUL_F_IMPLICIT		BIT(2)
+#define X86EMUL_F_INVLPG		BIT(3)
 
 struct x86_emulate_ops {
 	void (*vm_bugged)(struct x86_emulate_ctxt *ctxt);
-- 
GitLab


From a130066f74008858ac425b7497d231742474a0ea Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:16 +0800
Subject: [PATCH 0589/4076] KVM: x86/mmu: Drop non-PA bits when getting GFN for
 guest's PGD

Drop non-PA bits when getting GFN for guest's PGD with the maximum theoretical
mask for guest MAXPHYADDR.

Do it unconditionally because it's harmless for 32-bit guests, querying 64-bit
mode would be more expensive, and for EPT the mask isn't tied to guest mode.
Using PT_BASE_ADDR_MASK would be technically wrong (PAE paging has 64-bit
elements _except_ for CR3, which has only 32 valid bits), it wouldn't matter
in practice though.

Opportunistically use GENMASK_ULL() to define __PT_BASE_ADDR_MASK.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-6-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c          | 2 +-
 arch/x86/kvm/mmu/mmu_internal.h | 1 +
 arch/x86/kvm/mmu/paging_tmpl.h  | 2 +-
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 59b026b6ad2a2..73070650b1435 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3806,7 +3806,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 	hpa_t root;
 
 	root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu);
-	root_gfn = root_pgd >> PAGE_SHIFT;
+	root_gfn = (root_pgd & __PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
 
 	if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
 		mmu->root.hpa = kvm_mmu_get_dummy_root();
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index b66a7d47e0e4e..0669a8a668cac 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -13,6 +13,7 @@
 #endif
 
 /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */
+#define __PT_BASE_ADDR_MASK GENMASK_ULL(51, 12)
 #define __PT_LEVEL_SHIFT(level, bits_per_level)	\
 	(PAGE_SHIFT + ((level) - 1) * (bits_per_level))
 #define __PT_INDEX(address, level, bits_per_level) \
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index c85255073f672..4d4e98fe4f354 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -62,7 +62,7 @@
 #endif
 
 /* Common logic, but per-type values.  These also need to be undefined. */
-#define PT_BASE_ADDR_MASK	((pt_element_t)(((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)))
+#define PT_BASE_ADDR_MASK	((pt_element_t)__PT_BASE_ADDR_MASK)
 #define PT_LVL_ADDR_MASK(lvl)	__PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
 #define PT_LVL_OFFSET_MASK(lvl)	__PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
 #define PT_INDEX(addr, lvl)	__PT_INDEX(addr, lvl, PT_LEVEL_BITS)
-- 
GitLab


From 2c49db455ee27c72a680c9e4fad1c12433902ee3 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:17 +0800
Subject: [PATCH 0590/4076] KVM: x86: Add & use kvm_vcpu_is_legal_cr3() to
 check CR3's legality

Add and use kvm_vcpu_is_legal_cr3() to check CR3's legality to provide
a clear distinction between CR3 and GPA checks.  This will allow exempting
bits from kvm_vcpu_is_legal_cr3() without affecting general GPA checks,
e.g. for upcoming features that will use high bits in CR3 for feature
enabling.

No functional change intended.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-7-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.h      | 5 +++++
 arch/x86/kvm/svm/nested.c | 4 ++--
 arch/x86/kvm/vmx/nested.c | 4 ++--
 arch/x86/kvm/x86.c        | 4 ++--
 4 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 0b90532b6e261..5fd3f2d1ca148 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -279,4 +279,9 @@ static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu,
 			vcpu->arch.governed_features.enabled);
 }
 
+static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
+{
+	return kvm_vcpu_is_legal_gpa(vcpu, cr3);
+}
+
 #endif
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 3fea8c47679e6..90ca9489aab63 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -311,7 +311,7 @@ static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu,
 	if ((save->efer & EFER_LME) && (save->cr0 & X86_CR0_PG)) {
 		if (CC(!(save->cr4 & X86_CR4_PAE)) ||
 		    CC(!(save->cr0 & X86_CR0_PE)) ||
-		    CC(kvm_vcpu_is_illegal_gpa(vcpu, save->cr3)))
+		    CC(!kvm_vcpu_is_legal_cr3(vcpu, save->cr3)))
 			return false;
 	}
 
@@ -520,7 +520,7 @@ static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
 static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 			       bool nested_npt, bool reload_pdptrs)
 {
-	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3)))
+	if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3)))
 		return -EINVAL;
 
 	if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) &&
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index c5ec0ef51ff78..db61cf8e3128f 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1085,7 +1085,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 			       bool nested_ept, bool reload_pdptrs,
 			       enum vm_entry_failure_code *entry_failure_code)
 {
-	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) {
+	if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) {
 		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
 	}
@@ -2912,7 +2912,7 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 
 	if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) ||
 	    CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) ||
-	    CC(kvm_vcpu_is_illegal_gpa(vcpu, vmcs12->host_cr3)))
+	    CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3)))
 		return -EINVAL;
 
 	if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d0772b470413..3a648b6e632d3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1284,7 +1284,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	 * stuff CR3, e.g. for RSM emulation, and there is no guarantee that
 	 * the current vCPU mode is accurate.
 	 */
-	if (kvm_vcpu_is_illegal_gpa(vcpu, cr3))
+	if (!kvm_vcpu_is_legal_cr3(vcpu, cr3))
 		return 1;
 
 	if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3))
@@ -11612,7 +11612,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		 */
 		if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA))
 			return false;
-		if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3))
+		if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3))
 			return false;
 	} else {
 		/*
-- 
GitLab


From 9c8021d4ae85f1531230fc33653e06e9f1fdb7f1 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:18 +0800
Subject: [PATCH 0591/4076] KVM: x86: Remove kvm_vcpu_is_illegal_gpa()

Remove kvm_vcpu_is_illegal_gpa() and use !kvm_vcpu_is_legal_gpa() instead.
The "illegal" helper actually predates the "legal" helper, the only reason
the "illegal" variant wasn't removed by commit 4bda0e97868a ("KVM: x86:
Add a helper to check for a legal GPA") was to avoid code churn.  Now that
CR3 has a dedicated helper, there are fewer callers, and so the code churn
isn't that much of a deterrent.

No functional change intended.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-8-binbin.wu@linux.intel.com
[sean: provide a bit of history in the changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.h      | 5 -----
 arch/x86/kvm/vmx/nested.c | 2 +-
 arch/x86/kvm/vmx/vmx.c    | 2 +-
 3 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 5fd3f2d1ca148..fa04a00090a26 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -47,11 +47,6 @@ static inline bool kvm_vcpu_is_legal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	return !(gpa & vcpu->arch.reserved_gpa_bits);
 }
 
-static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
-{
-	return !kvm_vcpu_is_legal_gpa(vcpu, gpa);
-}
-
 static inline bool kvm_vcpu_is_legal_aligned_gpa(struct kvm_vcpu *vcpu,
 						 gpa_t gpa, gpa_t alignment)
 {
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index db61cf8e3128f..51622878d6e44 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2717,7 +2717,7 @@ static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp)
 	}
 
 	/* Reserved bits should not be set */
-	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f)))
+	if (CC(!kvm_vcpu_is_legal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f)))
 		return false;
 
 	/* AD, if set, should be supported */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 40e3780d73aeb..69072e418c73d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5782,7 +5782,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	 * would also use advanced VM-exit information for EPT violations to
 	 * reconstruct the page fault error code.
 	 */
-	if (unlikely(allow_smaller_maxphyaddr && kvm_vcpu_is_illegal_gpa(vcpu, gpa)))
+	if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa)))
 		return kvm_emulate_instruction(vcpu, 0);
 
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
-- 
GitLab


From 37a41847b770c722e98ace72f3851fb49b360c08 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:19 +0800
Subject: [PATCH 0592/4076] KVM: x86: Introduce get_untagged_addr() in
 kvm_x86_ops and call it in emulator

Introduce a new interface get_untagged_addr() to kvm_x86_ops to untag
the metadata from linear address.  Call the interface in linearization
of instruction emulator for 64-bit mode.

When enabled feature like Intel Linear Address Masking (LAM) or AMD Upper
Address Ignore (UAI), linear addresses may be tagged with metadata that
needs to be dropped prior to canonicality checks, i.e. the metadata is
ignored.

Introduce get_untagged_addr() to kvm_x86_ops to hide the vendor specific
code, as sadly LAM and UAI have different semantics.  Pass the emulator
flags to allow vendor specific implementation to precisely identify the
access type (LAM doesn't untag certain accesses).

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-9-binbin.wu@linux.intel.com
[sean: massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  2 ++
 arch/x86/kvm/emulate.c             |  2 +-
 arch/x86/kvm/kvm_emulate.h         |  3 +++
 arch/x86/kvm/x86.c                 | 10 ++++++++++
 5 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 26b628d84594b..756791665117b 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -135,6 +135,7 @@ KVM_X86_OP(msr_filter_changed)
 KVM_X86_OP(complete_emulated_msr)
 KVM_X86_OP(vcpu_deliver_sipi_vector)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
+KVM_X86_OP_OPTIONAL(get_untagged_addr)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a565a2e70f30f..8d042f27d6445 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1762,6 +1762,8 @@ struct kvm_x86_ops {
 	 * Returns vCPU specific APICv inhibit reasons
 	 */
 	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
+
+	gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index ceec8c5f96874..e223043ef5b26 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -701,7 +701,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 	*max_size = 0;
 	switch (mode) {
 	case X86EMUL_MODE_PROT64:
-		*linear = la;
+		*linear = la = ctxt->ops->get_untagged_addr(ctxt, la, flags);
 		va_bits = ctxt_virt_addr_bits(ctxt);
 		if (!__is_canonical_address(la, va_bits))
 			goto bad;
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 8bd9b23543cc7..e6d149825169d 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -230,6 +230,9 @@ struct x86_emulate_ops {
 	int (*leave_smm)(struct x86_emulate_ctxt *ctxt);
 	void (*triple_fault)(struct x86_emulate_ctxt *ctxt);
 	int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr);
+
+	gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr,
+				   unsigned int flags);
 };
 
 /* Type, address-of, and value of an instruction's operand. */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3a648b6e632d3..557872c0331a1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8445,6 +8445,15 @@ static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt)
 		kvm_vm_bugged(kvm);
 }
 
+static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt,
+					gva_t addr, unsigned int flags)
+{
+	if (!kvm_x86_ops.get_untagged_addr)
+		return addr;
+
+	return static_call(kvm_x86_get_untagged_addr)(emul_to_vcpu(ctxt), addr, flags);
+}
+
 static const struct x86_emulate_ops emulate_ops = {
 	.vm_bugged           = emulator_vm_bugged,
 	.read_gpr            = emulator_read_gpr,
@@ -8489,6 +8498,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.leave_smm           = emulator_leave_smm,
 	.triple_fault        = emulator_triple_fault,
 	.set_xcr             = emulator_set_xcr,
+	.get_untagged_addr   = emulator_get_untagged_addr,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
-- 
GitLab


From b39bd520a60c667a339e315ce7a3de2f7178f6e3 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:20 +0800
Subject: [PATCH 0593/4076] KVM: x86: Untag addresses for LAM emulation where
 applicable

Stub in vmx_get_untagged_addr() and wire up calls from the emulator (via
get_untagged_addr()) and "direct" calls from various VM-Exit handlers in
VMX where LAM untagging is supposed to be applied.  Defer implementing
the guts of vmx_get_untagged_addr() to future patches purely to make the
changes easier to consume.

LAM is active only for 64-bit linear addresses and several types of
accesses are exempted.

- Cases need to untag address (handled in get_vmx_mem_address())
  Operand(s) of VMX instructions and INVPCID.
  Operand(s) of SGX ENCLS.

- Cases LAM doesn't apply to (no change needed)
  Operand of INVLPG.
  Linear address in INVPCID descriptor.
  Linear address in INVVPID descriptor.
  BASEADDR specified in SECS of ECREATE.

Note:
  - LAM doesn't apply to write to control registers or MSRs
  - LAM masking is applied before walking page tables, i.e. the faulting
    linear address in CR2 doesn't contain the metadata.
  - The guest linear address saved in VMCS doesn't contain metadata.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-10-binbin.wu@linux.intel.com
[sean: massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/nested.c | 5 +++++
 arch/x86/kvm/vmx/sgx.c    | 1 +
 arch/x86/kvm/vmx/vmx.c    | 7 +++++++
 arch/x86/kvm/vmx/vmx.h    | 2 ++
 arch/x86/kvm/x86.c        | 4 ++++
 5 files changed, 19 insertions(+)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 51622878d6e44..4ba46e1b29d2b 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4980,6 +4980,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 		else
 			*ret = off;
 
+		*ret = vmx_get_untagged_addr(vcpu, *ret, 0);
 		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
 		 * non-canonical form. This is the only check on the memory
 		 * destination for long mode!
@@ -5797,6 +5798,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	vpid02 = nested_get_vpid02(vcpu);
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
+		/*
+		 * LAM doesn't apply to addresses that are inputs to TLB
+		 * invalidation.
+		 */
 		if (!operand.vpid ||
 		    is_noncanonical_address(operand.gla, vcpu))
 			return nested_vmx_fail(vcpu,
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index 3e822e5824975..6fef01e0536e5 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -37,6 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset,
 	if (!IS_ALIGNED(*gva, alignment)) {
 		fault = true;
 	} else if (likely(is_64_bit_mode(vcpu))) {
+		*gva = vmx_get_untagged_addr(vcpu, *gva, 0);
 		fault = is_noncanonical_address(*gva, vcpu);
 	} else {
 		*gva &= 0xffffffff;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 69072e418c73d..d7ff06d777202 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -8205,6 +8205,11 @@ static void vmx_vm_destroy(struct kvm *kvm)
 	free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm));
 }
 
+gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags)
+{
+	return gva;
+}
+
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.name = KBUILD_MODNAME,
 
@@ -8345,6 +8350,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.complete_emulated_msr = kvm_complete_insn_gp,
 
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
+
+	.get_untagged_addr = vmx_get_untagged_addr,
 };
 
 static unsigned int vmx_handle_intel_pt_intr(void)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index c2130d2c8e24b..45cee1a8bc0a4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -420,6 +420,8 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type);
 u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu);
 u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu);
 
+gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
+
 static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
 					     int type, bool value)
 {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 557872c0331a1..ecfe97aa35c2a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13563,6 +13563,10 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
 
 	switch (type) {
 	case INVPCID_TYPE_INDIV_ADDR:
+		/*
+		 * LAM doesn't apply to addresses that are inputs to TLB
+		 * invalidation.
+		 */
 		if ((!pcid_enabled && (operand.pcid != 0)) ||
 		    is_noncanonical_address(operand.gla, vcpu)) {
 			kvm_inject_gp(vcpu, 0);
-- 
GitLab


From 93d1c9f498a7505e0e0a0198f3b3d7f97fcc5fa6 Mon Sep 17 00:00:00 2001
From: Robert Hoo <robert.hu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:21 +0800
Subject: [PATCH 0594/4076] KVM: x86: Virtualize LAM for supervisor pointer

Add support to allow guests to set the new CR4 control bit for LAM and add
implementation to get untagged address for supervisor pointers.

LAM modifies the canonicality check applied to 64-bit linear addresses for
data accesses, allowing software to use of the untranslated address bits for
metadata and masks the metadata bits before using them as linear addresses
to access memory. LAM uses CR4.LAM_SUP (bit 28) to configure and enable LAM
for supervisor pointers. It also changes VMENTER to allow the bit to be set
in VMCS's HOST_CR4 and GUEST_CR4 to support virtualization. Note CR4.LAM_SUP
is allowed to be set even not in 64-bit mode, but it will not take effect
since LAM only applies to 64-bit linear addresses.

Move CR4.LAM_SUP out of CR4_RESERVED_BITS, its reservation depends on vcpu
supporting LAM or not. Leave it intercepted to prevent guest from setting
the bit if LAM is not exposed to guest as well as to avoid vmread every time
when KVM fetches its value, with the expectation that guest won't toggle the
bit frequently.

Set CR4.LAM_SUP bit in the emulated IA32_VMX_CR4_FIXED1 MSR for guests to
allow guests to enable LAM for supervisor pointers in nested VMX operation.

Hardware is not required to do TLB flush when CR4.LAM_SUP toggled, KVM
doesn't need to emulate TLB flush based on it.  There's no other features
or vmx_exec_controls connection, and no other code needed in
{kvm,vmx}_set_cr4().

Skip address untag for instruction fetches (which includes branch targets),
operand of INVLPG instructions, and implicit system accesses, all of which
are not subject to untagging.  Note, get_untagged_addr() isn't invoked for
implicit system accesses as there is no reason to do so, but check the
flag anyways for documentation purposes.

Signed-off-by: Robert Hoo <robert.hu@linux.intel.com>
Co-developed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-11-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h |  3 ++-
 arch/x86/kvm/vmx/vmx.c          | 39 ++++++++++++++++++++++++++++++++-
 arch/x86/kvm/x86.h              |  2 ++
 3 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8d042f27d6445..f96988f283d57 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -133,7 +133,8 @@
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
 			  | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
-			  | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
+			  | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \
+			  | X86_CR4_LAM_SUP))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d7ff06d777202..3bbe5a9362a98 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7673,6 +7673,9 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_UMIP,       ecx, feature_bit(UMIP));
 	cr4_fixed1_update(X86_CR4_LA57,       ecx, feature_bit(LA57));
 
+	entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1);
+	cr4_fixed1_update(X86_CR4_LAM_SUP,    eax, feature_bit(LAM));
+
 #undef cr4_fixed1_update
 }
 
@@ -8205,9 +8208,43 @@ static void vmx_vm_destroy(struct kvm *kvm)
 	free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm));
 }
 
+/*
+ * Note, the SDM states that the linear address is masked *after* the modified
+ * canonicality check, whereas KVM masks (untags) the address and then performs
+ * a "normal" canonicality check.  Functionally, the two methods are identical,
+ * and when the masking occurs relative to the canonicality check isn't visible
+ * to software, i.e. KVM's behavior doesn't violate the SDM.
+ */
 gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags)
 {
-	return gva;
+	int lam_bit;
+
+	if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG))
+		return gva;
+
+	if (!is_64_bit_mode(vcpu))
+		return gva;
+
+	/*
+	 * Bit 63 determines if the address should be treated as user address
+	 * or a supervisor address.
+	 */
+	if (!(gva & BIT_ULL(63))) {
+		/* KVM doesn't yet virtualize LAM_U{48,57}. */
+		return gva;
+	} else {
+		if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP))
+			return gva;
+
+		lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47;
+	}
+
+	/*
+	 * Untag the address by sign-extending the lam_bit, but NOT to bit 63.
+	 * Bit 63 is retained from the raw virtual address so that untagging
+	 * doesn't change a user access to a supervisor access, and vice versa.
+	 */
+	return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63));
 }
 
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 5184fde1dc541..2f7e191666580 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -530,6 +530,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
 		__reserved_bits |= X86_CR4_VMXE;        \
 	if (!__cpu_has(__c, X86_FEATURE_PCID))          \
 		__reserved_bits |= X86_CR4_PCIDE;       \
+	if (!__cpu_has(__c, X86_FEATURE_LAM))           \
+		__reserved_bits |= X86_CR4_LAM_SUP;     \
 	__reserved_bits;                                \
 })
 
-- 
GitLab


From 3098e6eca88e543ea0d190d1fa72b1c047bb3e7d Mon Sep 17 00:00:00 2001
From: Robert Hoo <robert.hu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:22 +0800
Subject: [PATCH 0595/4076] KVM: x86: Virtualize LAM for user pointer

Add support to allow guests to set the new CR3 control bits for Linear
Address Masking (LAM) and add implementation to get untagged address for
user pointers.

LAM modifies the canonical check for 64-bit linear addresses, allowing
software to use the masked/ignored address bits for metadata.  Hardware
masks off the metadata bits before using the linear addresses to access
memory.  LAM uses two new CR3 non-address bits, LAM_U48 (bit 62) and
LAM_U57 (bit 61), to configure LAM for user pointers. LAM also changes
VMENTER to allow both bits to be set in VMCS's HOST_CR3 and GUEST_CR3 for
virtualization.

When EPT is on, CR3 is not trapped by KVM and it's up to the guest to set
any of the two LAM control bits. However, when EPT is off, the actual CR3
used by the guest is generated from the shadow MMU root which is different
from the CR3 that is *set* by the guest, and KVM needs to manually apply
any active control bits to VMCS's GUEST_CR3 based on the cached CR3 *seen*
by the guest.

KVM manually checks guest's CR3 to make sure it points to a valid guest
physical address (i.e. to support smaller MAXPHYSADDR in the guest). Extend
this check to allow the two LAM control bits to be set. After check, LAM
bits of guest CR3 will be stripped off to extract guest physical address.

In case of nested, for a guest which supports LAM, both VMCS12's HOST_CR3
and GUEST_CR3 are allowed to have the new LAM control bits set, i.e. when
L0 enters L1 to emulate a VMEXIT from L2 to L1 or when L0 enters L2
directly. KVM also manually checks VMCS12's HOST_CR3 and GUEST_CR3 being
valid physical address. Extend such check to allow the new LAM control bits
too.

Note, LAM doesn't have a global control bit to turn on/off LAM completely,
but purely depends on hardware's CPUID to determine it can be enabled or
not. That means, when EPT is on, even when KVM doesn't expose LAM to guest,
the guest can still set LAM control bits in CR3 w/o causing problem. This
is an unfortunate virtualization hole. KVM could choose to intercept CR3 in
this case and inject fault but this would hurt performance when running a
normal VM w/o LAM support.  This is undesirable. Just choose to let the
guest do such illegal thing as the worst case is guest being killed when
KVM eventually find out such illegal behaviour and that the guest is
misbehaving.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Robert Hoo <robert.hu@linux.intel.com>
Co-developed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-12-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.h   |  4 ++++
 arch/x86/kvm/mmu.h     |  9 +++++++++
 arch/x86/kvm/vmx/vmx.c | 12 +++++++++---
 3 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index fa04a00090a26..e4bd59c15a2ca 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -276,6 +276,10 @@ static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu,
 
 static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
+	if (kvm_cpu_cap_has(X86_FEATURE_LAM) &&
+	    guest_cpuid_has(vcpu, X86_FEATURE_LAM))
+		cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
+
 	return kvm_vcpu_is_legal_gpa(vcpu, cr3);
 }
 
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index bb8c86eefac04..580e2414b88c7 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -146,6 +146,15 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu)
 	return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu));
 }
 
+static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_cpu_cap_has(X86_FEATURE_LAM) ||
+	    !guest_cpuid_has(vcpu, X86_FEATURE_LAM))
+		return 0;
+
+	return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
+}
+
 static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu)
 {
 	u64 root_hpa = vcpu->arch.mmu->root.hpa;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3bbe5a9362a98..3825ab316be9f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3400,7 +3400,8 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
 			update_guest_cr3 = false;
 		vmx_ept_load_pdptrs(vcpu);
 	} else {
-		guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu);
+		guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu) |
+			    kvm_get_active_cr3_lam_bits(vcpu);
 	}
 
 	if (update_guest_cr3)
@@ -8218,6 +8219,7 @@ static void vmx_vm_destroy(struct kvm *kvm)
 gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags)
 {
 	int lam_bit;
+	unsigned long cr3_bits;
 
 	if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG))
 		return gva;
@@ -8230,8 +8232,12 @@ gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags
 	 * or a supervisor address.
 	 */
 	if (!(gva & BIT_ULL(63))) {
-		/* KVM doesn't yet virtualize LAM_U{48,57}. */
-		return gva;
+		cr3_bits = kvm_get_active_cr3_lam_bits(vcpu);
+		if (!(cr3_bits & (X86_CR3_LAM_U57 | X86_CR3_LAM_U48)))
+			return gva;
+
+		/* LAM_U48 is ignored if LAM_U57 is set. */
+		lam_bit = cr3_bits & X86_CR3_LAM_U57 ? 56 : 47;
 	} else {
 		if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP))
 			return gva;
-- 
GitLab


From 703d794cb8cb28c07b22c1c845f5c4d4c419aff7 Mon Sep 17 00:00:00 2001
From: Robert Hoo <robert.hu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:23 +0800
Subject: [PATCH 0596/4076] KVM: x86: Advertise and enable LAM (user and
 supervisor)

LAM is enumerated by CPUID.7.1:EAX.LAM[bit 26]. Advertise the feature to
userspace and enable it as the final step after the LAM virtualization
support for supervisor and user pointers.

SGX LAM support is not advertised yet. SGX LAM support is enumerated in
SGX's own CPUID and there's no hard requirement that it must be supported
when LAM is reported in CPUID leaf 0x7.

Signed-off-by: Robert Hoo <robert.hu@linux.intel.com>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Jingqi Liu <jingqi.liu@intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-13-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index dda6fc4cfae88..40d68fef748a3 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -671,7 +671,7 @@ void kvm_set_cpu_caps(void)
 	kvm_cpu_cap_mask(CPUID_7_1_EAX,
 		F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) |
 		F(FZRM) | F(FSRS) | F(FSRC) |
-		F(AMX_FP16) | F(AVX_IFMA)
+		F(AMX_FP16) | F(AVX_IFMA) | F(LAM)
 	);
 
 	kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX,
-- 
GitLab


From 183bdd161c2b773a62f01d1c030f5a3a5b7c33b5 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 13 Sep 2023 20:42:24 +0800
Subject: [PATCH 0597/4076] KVM: x86: Use KVM-governed feature framework to
 track "LAM enabled"

Use the governed feature framework to track if Linear Address Masking (LAM)
is "enabled", i.e. if LAM can be used by the guest.

Using the framework to avoid the relative expensive call guest_cpuid_has()
during cr3 and vmexit handling paths for LAM.

No functional change intended.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
Link: https://lore.kernel.org/r/20230913124227.12574-14-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.h             | 3 +--
 arch/x86/kvm/governed_features.h | 1 +
 arch/x86/kvm/mmu.h               | 3 +--
 arch/x86/kvm/vmx/vmx.c           | 1 +
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index e4bd59c15a2ca..856e3037e74f3 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -276,8 +276,7 @@ static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu,
 
 static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
-	if (kvm_cpu_cap_has(X86_FEATURE_LAM) &&
-	    guest_cpuid_has(vcpu, X86_FEATURE_LAM))
+	if (guest_can_use(vcpu, X86_FEATURE_LAM))
 		cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
 
 	return kvm_vcpu_is_legal_gpa(vcpu, cr3);
diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 423a73395c102..ad463b1ed4e4a 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -16,6 +16,7 @@ KVM_GOVERNED_X86_FEATURE(PAUSEFILTER)
 KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD)
 KVM_GOVERNED_X86_FEATURE(VGIF)
 KVM_GOVERNED_X86_FEATURE(VNMI)
+KVM_GOVERNED_X86_FEATURE(LAM)
 
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 580e2414b88c7..60f21bb4c27b1 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -148,8 +148,7 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu)
 {
-	if (!kvm_cpu_cap_has(X86_FEATURE_LAM) ||
-	    !guest_cpuid_has(vcpu, X86_FEATURE_LAM))
+	if (!guest_can_use(vcpu, X86_FEATURE_LAM))
 		return 0;
 
 	return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3825ab316be9f..d30df9b3fe3e5 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7763,6 +7763,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES);
 
 	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX);
+	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LAM);
 
 	vmx_setup_uret_msrs(vmx);
 
-- 
GitLab


From 4ea6babbdd49d15c36665013e740f2e604d8841d Mon Sep 17 00:00:00 2001
From: Yujie Liu <yujie.liu@intel.com>
Date: Wed, 29 Nov 2023 17:13:37 +0800
Subject: [PATCH 0598/4076] xtensa: fix variants path in the Kconfig help

The directory in the path should be "variants" instead of "variant".

Fixes: 420ae9518404 ("xtensa: simplify addition of new core variants")
Signed-off-by: Yujie Liu <yujie.liu@intel.com>
Message-Id: <20231129091337.2084747-1-yujie.liu@intel.com>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 7d792077e5fdc..a9ed6ec3a75e9 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -144,7 +144,7 @@ config XTENSA_VARIANT_CUSTOM_NAME
 	depends on XTENSA_VARIANT_CUSTOM
 	help
 	  Provide the name of a custom Xtensa processor variant.
-	  This CORENAME selects arch/xtensa/variant/CORENAME.
+	  This CORENAME selects arch/xtensa/variants/CORENAME.
 	  Don't forget you have to select MMU if you have one.
 
 config XTENSA_VARIANT_NAME
-- 
GitLab


From 6d638ab8c3df7a4674b4cd2e4cc9d4051587c729 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Mon, 27 Nov 2023 00:12:22 +0900
Subject: [PATCH 0599/4076] xtensa: replace <asm-generic/export.h> with
 <linux/export.h>

Commit ddb5cdbafaaa ("kbuild: generate KSYMTAB entries by modpost")
deprecated <asm-generic/export.h>, which is now a wrapper of
<linux/export.h>.

Replace #include <asm-generic/export.h> with #include <linux/export.h>.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Message-Id: <20231126151222.1556761-1-masahiroy@kernel.org>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/include/asm/asmmacro.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/xtensa/include/asm/asmmacro.h b/arch/xtensa/include/asm/asmmacro.h
index 01bf7d9dbb191..a52d49a16ce7d 100644
--- a/arch/xtensa/include/asm/asmmacro.h
+++ b/arch/xtensa/include/asm/asmmacro.h
@@ -11,7 +11,7 @@
 #ifndef _XTENSA_ASMMACRO_H
 #define _XTENSA_ASMMACRO_H
 
-#include <asm-generic/export.h>
+#include <linux/export.h>
 #include <asm/core.h>
 
 /*
-- 
GitLab


From 791beae7335caa8d8579d201d7f9b18b4d8898e1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 24 Nov 2023 11:09:15 +0200
Subject: [PATCH 0600/4076] xtensa: Use PCI_HEADER_TYPE_MFD instead of literal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace literal 0x80 with PCI_HEADER_TYPE_MFD. While at it, convert
found_multi into boolean.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Message-Id: <20231124090919.23687-3-ilpo.jarvinen@linux.intel.com>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/lib/pci-auto.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/xtensa/lib/pci-auto.c b/arch/xtensa/lib/pci-auto.c
index aa6752237985a..05fc02f9e1c78 100644
--- a/arch/xtensa/lib/pci-auto.c
+++ b/arch/xtensa/lib/pci-auto.c
@@ -11,6 +11,7 @@
  * Based on work from Matt Porter <mporter@mvista.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/pci.h>
@@ -222,10 +223,11 @@ pciauto_postscan_setup_bridge(struct pci_dev *dev, int current_bus, int sub_bus,
 
 int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
 {
-	int sub_bus, pci_devfn, pci_class, cmdstat, found_multi=0;
+	int sub_bus, pci_devfn, pci_class, cmdstat;
 	unsigned short vid;
 	unsigned char header_type;
 	struct pci_dev *dev = &pciauto_dev;
+	bool found_multi = false;
 
 	pciauto_dev.bus = &pciauto_bus;
 	pciauto_dev.sysdata = pci_ctrl;
@@ -261,11 +263,11 @@ int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
 			continue;
 
 		if (!PCI_FUNC(pci_devfn))
-			found_multi = header_type & 0x80;
+			found_multi = FIELD_GET(PCI_HEADER_TYPE_MFD, header_type);
 		pci_read_config_word(dev, PCI_VENDOR_ID, &vid);
 
 		if (vid == 0xffff || vid == 0x0000) {
-			found_multi = 0;
+			found_multi = false;
 			continue;
 		}
 
-- 
GitLab


From e185a24eeab3efd667176aef60f88d27ce641cd7 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 24 Nov 2023 10:21:21 +0100
Subject: [PATCH 0601/4076] dt-bindings: correct white-spaces in examples

Use only one and exactly one space around '=' in DTS example.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org> # For MMC
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> #for-iio
Acked-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231124092121.16866-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/auxdisplay/hit,hd44780.yaml       | 2 +-
 .../devicetree/bindings/clock/baikal,bt1-ccu-pll.yaml     | 2 +-
 Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml | 6 +++---
 .../devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml       | 2 +-
 .../devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml      | 2 +-
 .../interrupt-controller/st,stih407-irq-syscfg.yaml       | 4 ++--
 Documentation/devicetree/bindings/mmc/arm,pl18x.yaml      | 2 +-
 Documentation/devicetree/bindings/net/sff,sfp.yaml        | 2 +-
 .../devicetree/bindings/pci/toshiba,visconti-pcie.yaml    | 2 +-
 .../bindings/pinctrl/renesas,rzg2l-pinctrl.yaml           | 6 +++---
 .../devicetree/bindings/power/supply/richtek,rt9455.yaml  | 8 ++++----
 .../devicetree/bindings/regulator/mps,mp5416.yaml         | 4 ++--
 .../devicetree/bindings/regulator/mps,mpq7920.yaml        | 4 ++--
 .../devicetree/bindings/remoteproc/fsl,imx-rproc.yaml     | 8 ++++----
 14 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/Documentation/devicetree/bindings/auxdisplay/hit,hd44780.yaml b/Documentation/devicetree/bindings/auxdisplay/hit,hd44780.yaml
index fde07e4b119df..406a922a714e8 100644
--- a/Documentation/devicetree/bindings/auxdisplay/hit,hd44780.yaml
+++ b/Documentation/devicetree/bindings/auxdisplay/hit,hd44780.yaml
@@ -113,7 +113,7 @@ examples:
     hd44780 {
             compatible = "hit,hd44780";
             display-height-chars = <2>;
-            display-width-chars  = <16>;
+            display-width-chars = <16>;
             data-gpios = <&pcf8574 4 0>,
                          <&pcf8574 5 0>,
                          <&pcf8574 6 0>,
diff --git a/Documentation/devicetree/bindings/clock/baikal,bt1-ccu-pll.yaml b/Documentation/devicetree/bindings/clock/baikal,bt1-ccu-pll.yaml
index 624984d51c106..7f8d98226437e 100644
--- a/Documentation/devicetree/bindings/clock/baikal,bt1-ccu-pll.yaml
+++ b/Documentation/devicetree/bindings/clock/baikal,bt1-ccu-pll.yaml
@@ -125,7 +125,7 @@ examples:
     clk25m: clock-oscillator-25m {
       compatible = "fixed-clock";
       #clock-cells = <0>;
-      clock-frequency  = <25000000>;
+      clock-frequency = <25000000>;
       clock-output-names = "clk25m";
     };
 ...
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml
index 5fcc8dd012f17..be2616ff9af68 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml
@@ -80,9 +80,9 @@ examples:
             compatible = "adi,ad7780";
             reg = <0>;
 
-            avdd-supply      = <&vdd_supply>;
-            powerdown-gpios  = <&gpio0 12 GPIO_ACTIVE_HIGH>;
-            adi,gain-gpios   = <&gpio1  5 GPIO_ACTIVE_LOW>;
+            avdd-supply = <&vdd_supply>;
+            powerdown-gpios = <&gpio0 12 GPIO_ACTIVE_HIGH>;
+            adi,gain-gpios = <&gpio1  5 GPIO_ACTIVE_LOW>;
             adi,filter-gpios = <&gpio2 15 GPIO_ACTIVE_LOW>;
         };
     };
diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
index 73def67fbe015..b6a233cd5f6bc 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
@@ -58,7 +58,7 @@ examples:
             reg = <0x3600>;
             interrupts = <0x0 0x36 0x0 IRQ_TYPE_EDGE_RISING>;
             qcom,external-resistor-micro-ohms = <10000>;
-            #io-channel-cells  = <1>;
+            #io-channel-cells = <1>;
         };
     };
 ...
diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
index b3a626389870f..64abe9a4cd9e1 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
@@ -46,6 +46,6 @@ examples:
         pmic_rradc: adc@4500 {
             compatible = "qcom,pmi8998-rradc";
             reg = <0x4500>;
-            #io-channel-cells  = <1>;
+            #io-channel-cells = <1>;
         };
     };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stih407-irq-syscfg.yaml b/Documentation/devicetree/bindings/interrupt-controller/st,stih407-irq-syscfg.yaml
index 2b153d7c54216..e44e4e5708a72 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,stih407-irq-syscfg.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,stih407-irq-syscfg.yaml
@@ -55,8 +55,8 @@ examples:
   - |
     #include <dt-bindings/interrupt-controller/irq-st.h>
     irq-syscfg {
-        compatible    = "st,stih407-irq-syscfg";
-        st,syscfg     = <&syscfg_cpu>;
+        compatible = "st,stih407-irq-syscfg";
+        st,syscfg = <&syscfg_cpu>;
         st,irq-device = <ST_IRQ_SYSCFG_PMU_0>,
                         <ST_IRQ_SYSCFG_PMU_1>;
         st,fiq-device = <ST_IRQ_SYSCFG_DISABLED>,
diff --git a/Documentation/devicetree/bindings/mmc/arm,pl18x.yaml b/Documentation/devicetree/bindings/mmc/arm,pl18x.yaml
index 2459a55ed540b..940b126881674 100644
--- a/Documentation/devicetree/bindings/mmc/arm,pl18x.yaml
+++ b/Documentation/devicetree/bindings/mmc/arm,pl18x.yaml
@@ -203,7 +203,7 @@ examples:
       bus-width = <4>;
       cap-sd-highspeed;
       cap-mmc-highspeed;
-      cd-gpios  = <&gpio2 31 0x4>;
+      cd-gpios = <&gpio2 31 0x4>;
       st,sig-dir-dat0;
       st,sig-dir-dat2;
       st,sig-dir-cmd;
diff --git a/Documentation/devicetree/bindings/net/sff,sfp.yaml b/Documentation/devicetree/bindings/net/sff,sfp.yaml
index 973e478a399d3..bf6cbc7c2ba3b 100644
--- a/Documentation/devicetree/bindings/net/sff,sfp.yaml
+++ b/Documentation/devicetree/bindings/net/sff,sfp.yaml
@@ -120,7 +120,7 @@ examples:
       pinctrl-names = "default";
       pinctrl-0 = <&cps_sfpp0_pins>;
       tx-disable-gpios = <&cps_gpio1 29 GPIO_ACTIVE_HIGH>;
-      tx-fault-gpios  = <&cps_gpio1 26 GPIO_ACTIVE_HIGH>;
+      tx-fault-gpios = <&cps_gpio1 26 GPIO_ACTIVE_HIGH>;
     };
 
     mdio {
diff --git a/Documentation/devicetree/bindings/pci/toshiba,visconti-pcie.yaml b/Documentation/devicetree/bindings/pci/toshiba,visconti-pcie.yaml
index 53da2edd7c9ab..120e3bb1e5454 100644
--- a/Documentation/devicetree/bindings/pci/toshiba,visconti-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/toshiba,visconti-pcie.yaml
@@ -83,7 +83,7 @@ examples:
                   <0x0 0x28050000 0x0 0x00010000>,
                   <0x0 0x24200000 0x0 0x00002000>,
                   <0x0 0x24162000 0x0 0x00001000>;
-            reg-names  = "dbi", "config", "ulreg", "smu", "mpu";
+            reg-names = "dbi", "config", "ulreg", "smu", "mpu";
             device_type = "pci";
             bus-range = <0x00 0xff>;
             num-lanes = <2>;
diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
index b5ca40d0e251d..d476de82e5c3f 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
@@ -185,17 +185,17 @@ examples:
                     sd1_mux {
                             pinmux = <RZG2L_PORT_PINMUX(19, 0, 1)>, /* CD */
                                      <RZG2L_PORT_PINMUX(19, 1, 1)>; /* WP */
-                            power-source  = <3300>;
+                            power-source = <3300>;
                     };
 
                     sd1_data {
                             pins = "SD1_DATA0", "SD1_DATA1", "SD1_DATA2", "SD1_DATA3";
-                            power-source  = <3300>;
+                            power-source = <3300>;
                     };
 
                     sd1_ctrl {
                             pins = "SD1_CLK", "SD1_CMD";
-                            power-source  = <3300>;
+                            power-source = <3300>;
                     };
             };
     };
diff --git a/Documentation/devicetree/bindings/power/supply/richtek,rt9455.yaml b/Documentation/devicetree/bindings/power/supply/richtek,rt9455.yaml
index 07e38be39f1bc..89f9603499b46 100644
--- a/Documentation/devicetree/bindings/power/supply/richtek,rt9455.yaml
+++ b/Documentation/devicetree/bindings/power/supply/richtek,rt9455.yaml
@@ -79,10 +79,10 @@ examples:
         interrupt-parent = <&gpio1>;
         interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
 
-        richtek,output-charge-current	    = <500000>;
-        richtek,end-of-charge-percentage    = <10>;
-        richtek,battery-regulation-voltage  = <4200000>;
-        richtek,boost-output-voltage	    = <5050000>;
+        richtek,output-charge-current = <500000>;
+        richtek,end-of-charge-percentage = <10>;
+        richtek,battery-regulation-voltage = <4200000>;
+        richtek,boost-output-voltage = <5050000>;
 
         richtek,min-input-voltage-regulation = <4500000>;
         richtek,avg-input-current-regulation = <500000>;
diff --git a/Documentation/devicetree/bindings/regulator/mps,mp5416.yaml b/Documentation/devicetree/bindings/regulator/mps,mp5416.yaml
index 0221397eb51ec..f825ee9efd810 100644
--- a/Documentation/devicetree/bindings/regulator/mps,mp5416.yaml
+++ b/Documentation/devicetree/bindings/regulator/mps,mp5416.yaml
@@ -62,8 +62,8 @@ examples:
              regulator-name = "buck1";
              regulator-min-microvolt = <600000>;
              regulator-max-microvolt = <2187500>;
-             regulator-min-microamp  = <3800000>;
-             regulator-max-microamp  = <6800000>;
+             regulator-min-microamp = <3800000>;
+             regulator-max-microamp = <6800000>;
              regulator-boot-on;
             };
 
diff --git a/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml b/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml
index 6de5b027f9903..0d34af98403f8 100644
--- a/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml
+++ b/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml
@@ -98,8 +98,8 @@ examples:
              regulator-name = "buck1";
              regulator-min-microvolt = <400000>;
              regulator-max-microvolt = <3587500>;
-             regulator-min-microamp  = <460000>;
-             regulator-max-microamp  = <7600000>;
+             regulator-min-microamp = <460000>;
+             regulator-max-microamp = <7600000>;
              regulator-boot-on;
              mps,buck-ovp-disable;
              mps,buck-phase-delay = /bits/ 8 <2>;
diff --git a/Documentation/devicetree/bindings/remoteproc/fsl,imx-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/fsl,imx-rproc.yaml
index 30632efdad8bb..df36e29d974ca 100644
--- a/Documentation/devicetree/bindings/remoteproc/fsl,imx-rproc.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/fsl,imx-rproc.yaml
@@ -113,10 +113,10 @@ examples:
     };
 
     imx7d-cm4 {
-      compatible	= "fsl,imx7d-cm4";
-      memory-region	= <&m4_reserved_sysmem1>, <&m4_reserved_sysmem2>;
-      syscon		= <&src>;
-      clocks		= <&clks IMX7D_ARM_M4_ROOT_CLK>;
+      compatible = "fsl,imx7d-cm4";
+      memory-region = <&m4_reserved_sysmem1>, <&m4_reserved_sysmem2>;
+      syscon = <&src>;
+      clocks = <&clks IMX7D_ARM_M4_ROOT_CLK>;
     };
 
   - |
-- 
GitLab


From a472ee42e6f60c8714e2306385687922afcba8c4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 29 Nov 2023 12:47:17 -0300
Subject: [PATCH 0602/4076] perf test sigtrap: Generalize the BTF routine to
 reuse it in this test

Move the part that loads the BTF info to a "btf__available()" that will
lazy load the BTF info so that if we need it for some other test, which
we will in the following cset, we can reuse it.

At some point this will move from this specific 'perf test' entry to be
used in other parts of perf, do it when needed.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kate Carcia <kcarcia@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20231129154718.326330-2-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/sigtrap.c | 60 +++++++++++++++++++++++++-------------
 1 file changed, 40 insertions(+), 20 deletions(-)

diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c
index 1de7478ec1894..a1bc7c776254e 100644
--- a/tools/perf/tests/sigtrap.c
+++ b/tools/perf/tests/sigtrap.c
@@ -57,36 +57,51 @@ static struct perf_event_attr make_event_attr(void)
 #ifdef HAVE_BPF_SKEL
 #include <bpf/btf.h>
 
-static bool attr_has_sigtrap(void)
+static struct btf *btf;
+
+static bool btf__available(void)
 {
-	bool ret = false;
-	struct btf *btf;
-	const struct btf_type *t;
+	if (btf == NULL)
+		btf = btf__load_vmlinux_btf();
+
+	return btf != NULL;
+}
+
+static void btf__exit(void)
+{
+	btf__free(btf);
+	btf = NULL;
+}
+
+static const struct btf_member *__btf_type__find_member_by_name(int type_id, const char *member_name)
+{
+	const struct btf_type *t = btf__type_by_id(btf, type_id);
 	const struct btf_member *m;
-	const char *name;
-	int i, id;
+	int i;
+
+	for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+		const char *current_member_name = btf__name_by_offset(btf, m->name_off);
+		if (!strcmp(current_member_name, member_name))
+			return m;
+	}
+
+	return NULL;
+}
+
+static bool attr_has_sigtrap(void)
+{
+	int id;
 
-	btf = btf__load_vmlinux_btf();
-	if (btf == NULL) {
+	if (!btf__available()) {
 		/* should be an old kernel */
 		return false;
 	}
 
 	id = btf__find_by_name_kind(btf, "perf_event_attr", BTF_KIND_STRUCT);
 	if (id < 0)
-		goto out;
+		return false;
 
-	t = btf__type_by_id(btf, id);
-	for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
-		name = btf__name_by_offset(btf, m->name_off);
-		if (!strcmp(name, "sigtrap")) {
-			ret = true;
-			break;
-		}
-	}
-out:
-	btf__free(btf);
-	return ret;
+	return __btf_type__find_member_by_name(id, "sigtrap") != NULL;
 }
 #else  /* !HAVE_BPF_SKEL */
 static bool attr_has_sigtrap(void)
@@ -109,6 +124,10 @@ static bool attr_has_sigtrap(void)
 
 	return ret;
 }
+
+static void btf__exit(void)
+{
+}
 #endif  /* HAVE_BPF_SKEL */
 
 static void
@@ -221,6 +240,7 @@ out_restore_sigaction:
 	sigaction(SIGTRAP, &oldact, NULL);
 out:
 	pthread_barrier_destroy(&barrier);
+	btf__exit();
 	return ret;
 }
 
-- 
GitLab


From 650e0bde43f35bb675e87e30f679a57cfa22e0e5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 29 Nov 2023 12:47:18 -0300
Subject: [PATCH 0603/4076] perf tests sigtrap: Skip if running on a kernel
 with sleepable spinlocks

There are issues as reported that need some more investigation on the
RT kernel front, till that is addressed, skip this test.

This test is already skipped for multiple hardware architectures where
the tested kernel feature is not supported.

Acked-by: Marco Elver <elver@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Kate Carcia <kcarcia@redhat.com>
Cc: Marco Elver <elver@google.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/e368f2c848d77fbc8d259f44e2055fe469c219cf.camel@gmx.de/
Link: https://lore.kernel.org/r/20231129154718.326330-3-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/sigtrap.c | 46 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 44 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c
index a1bc7c776254e..e6fd934b027a3 100644
--- a/tools/perf/tests/sigtrap.c
+++ b/tools/perf/tests/sigtrap.c
@@ -103,6 +103,34 @@ static bool attr_has_sigtrap(void)
 
 	return __btf_type__find_member_by_name(id, "sigtrap") != NULL;
 }
+
+static bool kernel_with_sleepable_spinlocks(void)
+{
+	const struct btf_member *member;
+	const struct btf_type *type;
+	const char *type_name;
+	int id;
+
+	if (!btf__available())
+		return false;
+
+	id = btf__find_by_name_kind(btf, "spinlock", BTF_KIND_STRUCT);
+	if (id < 0)
+		return false;
+
+	// Only RT has a "lock" member for "struct spinlock"
+	member = __btf_type__find_member_by_name(id, "lock");
+	if (member == NULL)
+		return false;
+
+	// But check its type as well
+	type = btf__type_by_id(btf, member->type);
+	if (!type || !btf_is_struct(type))
+		return false;
+
+	type_name = btf__name_by_offset(btf, type->name_off);
+	return type_name && !strcmp(type_name, "rt_mutex_base");
+}
 #else  /* !HAVE_BPF_SKEL */
 static bool attr_has_sigtrap(void)
 {
@@ -125,6 +153,11 @@ static bool attr_has_sigtrap(void)
 	return ret;
 }
 
+static bool kernel_with_sleepable_spinlocks(void)
+{
+	return false;
+}
+
 static void btf__exit(void)
 {
 }
@@ -166,7 +199,7 @@ static int run_test_threads(pthread_t *threads, pthread_barrier_t *barrier)
 
 static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrier)
 {
-	int ret;
+	int ret, expected_sigtraps;
 
 	ctx.iterate_on = 3000;
 
@@ -175,7 +208,16 @@ static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrie
 	ret = run_test_threads(threads, barrier);
 	TEST_ASSERT_EQUAL("disable failed", ioctl(fd, PERF_EVENT_IOC_DISABLE, 0), 0);
 
-	TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, NUM_THREADS * ctx.iterate_on);
+	expected_sigtraps = NUM_THREADS * ctx.iterate_on;
+
+	if (ctx.signal_count < expected_sigtraps && kernel_with_sleepable_spinlocks()) {
+		pr_debug("Expected %d sigtraps, got %d, running on a kernel with sleepable spinlocks.\n",
+			 expected_sigtraps, ctx.signal_count);
+		pr_debug("See https://lore.kernel.org/all/e368f2c848d77fbc8d259f44e2055fe469c219cf.camel@gmx.de/\n");
+		return TEST_SKIP;
+	} else
+		TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, expected_sigtraps);
+
 	TEST_ASSERT_EQUAL("missing signals or incorrectly delivered", ctx.tids_want_signal, 0);
 	TEST_ASSERT_VAL("unexpected si_addr", ctx.first_siginfo.si_addr == &ctx.iterate_on);
 #if 0 /* FIXME: enable when libc's signal.h has si_perf_{type,data} */
-- 
GitLab


From 72a2a0a494ec9aefbca4ad64f46b8e3370809993 Mon Sep 17 00:00:00 2001
From: Likhitha Korrapati <likhitha@linux.ibm.com>
Date: Sun, 26 Nov 2023 02:09:14 -0500
Subject: [PATCH 0604/4076] perf test record+probe_libc_inet_pton: Fix call
 chain match on powerpc

The perf test "probe libc's inet_pton & backtrace it with ping" fails on
powerpc as below:

  # perf test -v "probe libc's inet_pton & backtrace it with
  ping"
   85: probe libc's inet_pton & backtrace it with ping                 :
  --- start ---
  test child forked, pid 96028
  ping 96056 [002] 127271.101961: probe_libc:inet_pton: (7fffa1779a60)
  7fffa1779a60 __GI___inet_pton+0x0 (/usr/lib64/glibc-hwcaps/power10/libc.so.6)
  7fffa172a73c getaddrinfo+0x121c (/usr/lib64/glibc-hwcaps/power10/libc.so.6)
  FAIL: expected backtrace entry
  "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\(/usr/lib64/glibc-hwcaps/power10/libc.so.6\)$"
  got "7fffa172a73c getaddrinfo+0x121c (/usr/lib64/glibc-hwcaps/power10/libc.so.6)"
  test child finished with -1
  ---- end ----
  probe libc's inet_pton & backtrace it with ping: FAILED!

This test installs a probe on libc's inet_pton function, which will use
uprobes and then uses perf trace on a ping to localhost. It gets 3
levels deep backtrace and checks whether it is what we expected or not.

The test started failing from RHEL 9.4 where as it works in previous
distro version (RHEL 9.2). Test expects gaih_inet function to be part of
backtrace. But in the glibc version (2.34-86) which is part of distro
where it fails, this function is missing and hence the test is failing.

From nm and ping command output we can confirm that gaih_inet function
is not present in the expected backtrace for glibc version glibc-2.34-86

  [root@xxx perf]# nm /usr/lib64/glibc-hwcaps/power10/libc.so.6 | grep gaih_inet
  00000000001273e0 t gaih_inet_serv
  00000000001cd8d8 r gaih_inet_typeproto

  [root@xxx perf]# perf script -i /tmp/perf.data.6E8
  ping  104048 [000] 128582.508976: probe_libc:inet_pton: (7fff83779a60)
              7fff83779a60 __GI___inet_pton+0x0 (/usr/lib64/glibc-hwcaps/power10/libc.so.6)
              7fff8372a73c getaddrinfo+0x121c (/usr/lib64/glibc-hwcaps/power10/libc.so.6)
                 11dc73534 [unknown] (/usr/bin/ping)
              7fff8362a8c4 __libc_start_call_main+0x84 (/usr/lib64/glibc-hwcaps/power10/libc.so.6)

  FAIL: expected backtrace entry
  "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\(/usr/lib64/glibc-hwcaps/power10/libc.so.6\)$"
  got "7fff9d52a73c getaddrinfo+0x121c (/usr/lib64/glibc-hwcaps/power10/libc.so.6)"

With version glibc-2.34-60 gaih_inet function is present as part of the
expected backtrace. So we cannot just remove the gaih_inet function from
the backtrace.

  [root@xxx perf]# nm /usr/lib64/glibc-hwcaps/power10/libc.so.6 | grep gaih_inet
  0000000000130490 t gaih_inet.constprop.0
  000000000012e830 t gaih_inet_serv
  00000000001d45e4 r gaih_inet_typeproto

  [root@xxx perf]# ./perf script -i /tmp/perf.data.b6S
  ping   67906 [000] 22699.591699: probe_libc:inet_pton_3: (7fffbdd80820) 7fffbdd80820 __GI___inet_pton+0x0
  (/usr/lib64/glibc-hwcaps/power10/libc.so.6) 7fffbdd31160 gaih_inet.constprop.0+0xcd0
  (/usr/lib64/glibc-hwcaps/power10/libc.so.6) 7fffbdd31c7c getaddrinfo+0x14c
  (/usr/lib64/glibc-hwcaps/power10/libc.so.6) 1140d3558 [unknown] (/usr/bin/ping)

This patch solves this issue by doing a conditional skip. If there is a
gaih_inet function present in the libc then it will be added to the
expected backtrace else the function will be skipped from being added
to the expected backtrace.

Output with the patch

  [root@xxx perf]# ./perf test -v "probe libc's inet_pton & backtrace it
  with ping"
   83: probe libc's inet_pton & backtrace it with ping                 :
  --- start ---
  test child forked, pid 102662
  ping 102692 [000] 127935.549973: probe_libc:inet_pton: (7fff93379a60)
  7fff93379a60 __GI___inet_pton+0x0 (/usr/lib64/glibc-hwcaps/power10/libc.so.6)
  7fff9332a73c getaddrinfo+0x121c (/usr/lib64/glibc-hwcaps/power10/libc.so.6)
  11ef03534 [unknown] (/usr/bin/ping)
  test child finished with 0
  ---- end ----
  probe libc's inet_pton & backtrace it with ping: Ok

Reported-by: Disha Goel <disgoel@linux.ibm.com>
Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Likhitha Korrapati <likhitha@linux.ibm.com>
Tested-by: Disha Goel <disgoel@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20231126070914.175332-1-likhitha@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index eebeea6bdc767..72c65570db378 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -45,7 +45,10 @@ trace_libc_inet_pton_backtrace() {
 		;;
 	ppc64|ppc64le)
 		eventattr='max-stack=4'
-		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		# Add gaih_inet to expected backtrace only if it is part of libc.
+		if nm $libc | grep -F -q gaih_inet.; then
+			echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		fi
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
 		echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
-- 
GitLab


From 11baacb2fd9b1c6e759ad54ca13f259fa1769c73 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 28 Nov 2023 15:48:09 -0600
Subject: [PATCH 0605/4076] dt-bindings: input: sprd,sc27xx-vibrator: Drop
 incomplete example

The example for the Spreadtrum SC27xx PMIC vibrator is incomplete as the
binding is the full PMIC, not just the sub-functions. It is preferred
for MFD examples to be complete in the top-level MFD device binding
rather than piecemeal in each sub-function binding.

This also fixes an undocumented (by schema) compatible warning for
"sprd,sc2731".

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231128214809.3975719-1-robh@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../bindings/input/sprd,sc27xx-vibrator.yaml  | 19 +------------------
 1 file changed, 1 insertion(+), 18 deletions(-)

diff --git a/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml b/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml
index a401a0bfcbec2..4c8d303ff93c9 100644
--- a/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml
+++ b/Documentation/devicetree/bindings/input/sprd,sc27xx-vibrator.yaml
@@ -28,21 +28,4 @@ required:
 
 additionalProperties: false
 
-examples:
-  - |
-    #include <dt-bindings/interrupt-controller/arm-gic.h>
-    sc2731_pmic: pmic@0 {
-      compatible = "sprd,sc2731";
-      reg = <0 0>;
-      spi-max-frequency = <26000000>;
-      interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
-      interrupt-controller;
-      #interrupt-cells = <2>;
-      #address-cells = <1>;
-      #size-cells = <0>;
-
-      vibrator@eb4 {
-        compatible = "sprd,sc2731-vibrator";
-        reg = <0xeb4>;
-      };
-    };
+...
-- 
GitLab


From a42b4bd51b2aec77fb38f1ce0f41846055a8d33c Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 28 Nov 2023 15:48:16 -0600
Subject: [PATCH 0606/4076] dt-bindings: input: mediatek,pmic-keys: Drop
 incomplete example

The example for the Mediatek PMIC keys is incomplete as the binding is
the full PMIC, not just the sub-functions. It is preferred for MFD
examples to be complete in the top-level MFD device binding rather than
piecemeal in each sub-function binding.

This also fixes an undocumented (by schema) compatible warning for
"mediatek,mt6397".

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231128214816.3975893-1-robh@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../bindings/input/mediatek,pmic-keys.yaml    | 24 +------------------
 1 file changed, 1 insertion(+), 23 deletions(-)

diff --git a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
index e34c9e78d38d8..70567d92c746e 100644
--- a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
+++ b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml
@@ -90,26 +90,4 @@ required:
 
 unevaluatedProperties: false
 
-examples:
-  - |
-    #include <dt-bindings/input/input.h>
-    #include <dt-bindings/interrupt-controller/arm-gic.h>
-
-    pmic {
-        compatible = "mediatek,mt6397";
-
-        keys {
-          compatible = "mediatek,mt6397-keys";
-          mediatek,long-press-mode = <1>;
-          power-off-time-sec = <0>;
-
-          key-power {
-            linux,keycodes = <KEY_POWER>;
-            wakeup-source;
-          };
-
-          key-home {
-            linux,keycodes = <KEY_VOLUMEDOWN>;
-          };
-        };
-    };
+...
-- 
GitLab


From fc6543bb55d4077c44e577c321bbf158446c8000 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Sat, 28 Oct 2023 20:34:53 +0100
Subject: [PATCH 0607/4076] KVM: selftests: add -MP to CFLAGS

Using -MD without -MP causes build failures when a header file is deleted
or moved. With -MP, the compiler will emit phony targets for the header
files it lists as dependencies, and the Makefiles won't refuse to attempt
to rebuild a C unit which no longer includes the deleted header.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lore.kernel.org/r/9fc8b5395321abbfcaf5d78477a9a7cd350b08e4.camel@infradead.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 69ce8e06b3a34..914987220a629 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -226,7 +226,7 @@ else
 LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-	-Wno-gnu-variable-sized-type-not-at-end -MD\
+	-Wno-gnu-variable-sized-type-not-at-end -MD -MP \
 	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-builtin-strnlen \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
-- 
GitLab


From 0277022a77a56f8251e8cf8d25e9308478e79ea5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 18 Oct 2023 12:23:25 -0700
Subject: [PATCH 0608/4076] KVM: x86/mmu: Declare flush_remote_tlbs{_range}()
 hooks iff HYPERV!=n

Declare the kvm_x86_ops hooks used to wire up paravirt TLB flushes when
running under Hyper-V if and only if CONFIG_HYPERV!=n.  Wrapping yet more
code with IS_ENABLED(CONFIG_HYPERV) eliminates a handful of conditional
branches, and makes it super obvious why the hooks *might* be valid.

Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231018192325.1893896-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  2 ++
 arch/x86/include/asm/kvm_host.h    | 12 ++++++++++++
 arch/x86/kvm/mmu/mmu.c             | 12 ++++--------
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 26b628d84594b..f482216bbdb89 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -55,8 +55,10 @@ KVM_X86_OP(set_rflags)
 KVM_X86_OP(get_if_flag)
 KVM_X86_OP(flush_tlb_all)
 KVM_X86_OP(flush_tlb_current)
+#if IS_ENABLED(CONFIG_HYPERV)
 KVM_X86_OP_OPTIONAL(flush_remote_tlbs)
 KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range)
+#endif
 KVM_X86_OP(flush_tlb_gva)
 KVM_X86_OP(flush_tlb_guest)
 KVM_X86_OP(vcpu_pre_run)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a565a2e70f30f..5e5e9e0abd4a0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1614,9 +1614,11 @@ struct kvm_x86_ops {
 
 	void (*flush_tlb_all)(struct kvm_vcpu *vcpu);
 	void (*flush_tlb_current)(struct kvm_vcpu *vcpu);
+#if IS_ENABLED(CONFIG_HYPERV)
 	int  (*flush_remote_tlbs)(struct kvm *kvm);
 	int  (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn,
 					gfn_t nr_pages);
+#endif
 
 	/*
 	 * Flush any TLB entries associated with the given GVA.
@@ -1825,6 +1827,7 @@ static inline struct kvm *kvm_arch_alloc_vm(void)
 #define __KVM_HAVE_ARCH_VM_FREE
 void kvm_arch_free_vm(struct kvm *kvm);
 
+#if IS_ENABLED(CONFIG_HYPERV)
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
 static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
@@ -1836,6 +1839,15 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 }
 
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
+						   u64 nr_pages)
+{
+	if (!kvm_x86_ops.flush_remote_tlbs_range)
+		return -EOPNOTSUPP;
+
+	return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+}
+#endif /* CONFIG_HYPERV */
 
 #define kvm_arch_pmi_in_guest(vcpu) \
 	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 59b026b6ad2a2..8531480e5da48 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -271,15 +271,11 @@ static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu,
 
 static inline bool kvm_available_flush_remote_tlbs_range(void)
 {
+#if IS_ENABLED(CONFIG_HYPERV)
 	return kvm_x86_ops.flush_remote_tlbs_range;
-}
-
-int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
-{
-	if (!kvm_x86_ops.flush_remote_tlbs_range)
-		return -EOPNOTSUPP;
-
-	return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+#else
+	return false;
+#endif
 }
 
 static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index);
-- 
GitLab


From 6542a00369284c951185be8fa2ed45cf423cce06 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 7 Nov 2023 17:09:52 -0800
Subject: [PATCH 0609/4076] KVM: selftests: Drop the single-underscore ioctl()
 helpers

Drop _kvm_ioctl(), _vm_ioctl(), and _vcpu_ioctl(), as they are no longer
used by anything other than the no-underscores variants (and may have
never been used directly).  The single-underscore variants were never
intended to be a "feature", they were a stopgap of sorts to ease the
conversion to pretty printing ioctl() names when reporting errors.

Opportunistically add a comment explaining when to use __KVM_IOCTL_ERROR()
versus KVM_IOCTL_ERROR().  The single-underscore macros were subtly
ensuring that the name of the ioctl() was printed on error, i.e. it's all
too easy to overlook the fact that using __KVM_IOCTL_ERROR() is
intentional.

Link: https://lore.kernel.org/r/20231108010953.560824-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/include/kvm_util_base.h     | 30 ++++++++-----------
 1 file changed, 13 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 1b58f943562f8..190f9c0ef5840 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -267,6 +267,13 @@ static inline bool kvm_has_cap(long cap)
 #define __KVM_SYSCALL_ERROR(_name, _ret) \
 	"%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno)
 
+/*
+ * Use the "inner", double-underscore macro when reporting errors from within
+ * other macros so that the name of ioctl() and not its literal numeric value
+ * is printed on error.  The "outer" macro is strongly preferred when reporting
+ * errors "directly", i.e. without an additional layer of macros, as it reduces
+ * the probability of passing in the wrong string.
+ */
 #define __KVM_IOCTL_ERROR(_name, _ret)	__KVM_SYSCALL_ERROR(_name, _ret)
 #define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret)
 
@@ -279,17 +286,13 @@ static inline bool kvm_has_cap(long cap)
 #define __kvm_ioctl(kvm_fd, cmd, arg)				\
 	kvm_do_ioctl(kvm_fd, cmd, arg)
 
-
-#define _kvm_ioctl(kvm_fd, cmd, name, arg)			\
+#define kvm_ioctl(kvm_fd, cmd, arg)				\
 ({								\
 	int ret = __kvm_ioctl(kvm_fd, cmd, arg);		\
 								\
-	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret));	\
+	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret));	\
 })
 
-#define kvm_ioctl(kvm_fd, cmd, arg) \
-	_kvm_ioctl(kvm_fd, cmd, #cmd, arg)
-
 static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { }
 
 #define __vm_ioctl(vm, cmd, arg)				\
@@ -298,17 +301,13 @@ static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { }
 	kvm_do_ioctl((vm)->fd, cmd, arg);			\
 })
 
-#define _vm_ioctl(vm, cmd, name, arg)				\
+#define vm_ioctl(vm, cmd, arg)					\
 ({								\
 	int ret = __vm_ioctl(vm, cmd, arg);			\
 								\
-	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret));	\
+	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret));	\
 })
 
-#define vm_ioctl(vm, cmd, arg)					\
-	_vm_ioctl(vm, cmd, #cmd, arg)
-
-
 static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { }
 
 #define __vcpu_ioctl(vcpu, cmd, arg)				\
@@ -317,16 +316,13 @@ static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { }
 	kvm_do_ioctl((vcpu)->fd, cmd, arg);			\
 })
 
-#define _vcpu_ioctl(vcpu, cmd, name, arg)			\
+#define vcpu_ioctl(vcpu, cmd, arg)				\
 ({								\
 	int ret = __vcpu_ioctl(vcpu, cmd, arg);			\
 								\
-	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret));	\
+	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret));	\
 })
 
-#define vcpu_ioctl(vcpu, cmd, arg)				\
-	_vcpu_ioctl(vcpu, cmd, #cmd, arg)
-
 /*
  * Looks up and returns the value corresponding to the capability
  * (KVM_CAP_*) given by cap.
-- 
GitLab


From 1b78d474ce4ecbf15a4a8b08994b8ed8ceec0dab Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 7 Nov 2023 17:09:53 -0800
Subject: [PATCH 0610/4076] KVM: selftests: Add logic to detect if ioctl()
 failed because VM was killed

Add yet another macro to the VM/vCPU ioctl() framework to detect when an
ioctl() failed because KVM killed/bugged the VM, i.e. when there was
nothing wrong with the ioctl() itself.  If KVM kills a VM, e.g. by way of
a failed KVM_BUG_ON(), all subsequent VM and vCPU ioctl()s will fail with
-EIO, which can be quite misleading and ultimately waste user/developer
time.

Use KVM_CHECK_EXTENSION on KVM_CAP_USER_MEMORY to detect if the VM is
dead and/or bug, as KVM doesn't provide a dedicated ioctl().  Using a
heuristic is obviously less than ideal, but practically speaking the logic
is bulletproof barring a KVM change, and any such change would arguably
break userspace, e.g. if KVM returns something other than -EIO.

Without the detection, tearing down a bugged VM yields a cryptic failure
when deleting memslots:

  ==== Test Assertion Failure ====
  lib/kvm_util.c:689: !ret
  pid=45131 tid=45131 errno=5 - Input/output error
     1	0x00000000004036c3: __vm_mem_region_delete at kvm_util.c:689
     2	0x00000000004042f0: kvm_vm_free at kvm_util.c:724 (discriminator 12)
     3	0x0000000000402929: race_sync_regs at sync_regs_test.c:193
     4	0x0000000000401cab: main at sync_regs_test.c:334 (discriminator 6)
     5	0x0000000000416f13: __libc_start_call_main at libc-start.o:?
     6	0x000000000041855f: __libc_start_main_impl at ??:?
     7	0x0000000000401d40: _start at ??:?
  KVM_SET_USER_MEMORY_REGION failed, rc: -1 errno: 5 (Input/output error)

Which morphs into a more pointed error message with the detection:

  ==== Test Assertion Failure ====
  lib/kvm_util.c:689: false
  pid=80347 tid=80347 errno=5 - Input/output error
     1	0x00000000004039ab: __vm_mem_region_delete at kvm_util.c:689 (discriminator 5)
     2	0x0000000000404660: kvm_vm_free at kvm_util.c:724 (discriminator 12)
     3	0x0000000000402ac9: race_sync_regs at sync_regs_test.c:193
     4	0x0000000000401cb7: main at sync_regs_test.c:334 (discriminator 6)
     5	0x0000000000418263: __libc_start_call_main at libc-start.o:?
     6	0x00000000004198af: __libc_start_main_impl at ??:?
     7	0x0000000000401d90: _start at ??:?
  KVM killed/bugged the VM, check the kernel log for clues

Suggested-by: Michal Luczaj <mhal@rbox.co>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Colton Lewis <coltonlewis@google.com>
Link: https://lore.kernel.org/r/20231108010953.560824-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/include/kvm_util_base.h     | 39 ++++++++++++++++---
 tools/testing/selftests/kvm/lib/kvm_util.c    |  2 +-
 2 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 190f9c0ef5840..e0da036a13aef 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -301,11 +301,40 @@ static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { }
 	kvm_do_ioctl((vm)->fd, cmd, arg);			\
 })
 
+/*
+ * Assert that a VM or vCPU ioctl() succeeded, with extra magic to detect if
+ * the ioctl() failed because KVM killed/bugged the VM.  To detect a dead VM,
+ * probe KVM_CAP_USER_MEMORY, which (a) has been supported by KVM since before
+ * selftests existed and (b) should never outright fail, i.e. is supposed to
+ * return 0 or 1.  If KVM kills a VM, KVM returns -EIO for all ioctl()s for the
+ * VM and its vCPUs, including KVM_CHECK_EXTENSION.
+ */
+#define __TEST_ASSERT_VM_VCPU_IOCTL(cond, name, ret, vm)				\
+do {											\
+	int __errno = errno;								\
+											\
+	static_assert_is_vm(vm);							\
+											\
+	if (cond)									\
+		break;									\
+											\
+	if (errno == EIO &&								\
+	    __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY) < 0) {	\
+		TEST_ASSERT(errno == EIO, "KVM killed the VM, should return -EIO");	\
+		TEST_FAIL("KVM killed/bugged the VM, check the kernel log for clues");	\
+	}										\
+	errno = __errno;								\
+	TEST_ASSERT(cond, __KVM_IOCTL_ERROR(name, ret));				\
+} while (0)
+
+#define TEST_ASSERT_VM_VCPU_IOCTL(cond, cmd, ret, vm)		\
+	__TEST_ASSERT_VM_VCPU_IOCTL(cond, #cmd, ret, vm)
+
 #define vm_ioctl(vm, cmd, arg)					\
 ({								\
 	int ret = __vm_ioctl(vm, cmd, arg);			\
 								\
-	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret));	\
+	__TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm);		\
 })
 
 static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { }
@@ -320,7 +349,7 @@ static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { }
 ({								\
 	int ret = __vcpu_ioctl(vcpu, cmd, arg);			\
 								\
-	TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret));	\
+	__TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm);	\
 })
 
 /*
@@ -331,7 +360,7 @@ static inline int vm_check_cap(struct kvm_vm *vm, long cap)
 {
 	int ret =  __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap);
 
-	TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret));
+	TEST_ASSERT_VM_VCPU_IOCTL(ret >= 0, KVM_CHECK_EXTENSION, ret, vm);
 	return ret;
 }
 
@@ -438,7 +467,7 @@ static inline int vm_get_stats_fd(struct kvm_vm *vm)
 {
 	int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL);
 
-	TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd));
+	TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_GET_STATS_FD, fd, vm);
 	return fd;
 }
 
@@ -680,7 +709,7 @@ static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu)
 {
 	int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL);
 
-	TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd));
+	TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_CHECK_EXTENSION, fd, vcpu->vm);
 	return fd;
 }
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 9b29cbf49476d..17a978b8a2c4b 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1271,7 +1271,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	vcpu->vm = vm;
 	vcpu->id = vcpu_id;
 	vcpu->fd = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(unsigned long)vcpu_id);
-	TEST_ASSERT(vcpu->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu->fd));
+	TEST_ASSERT_VM_VCPU_IOCTL(vcpu->fd >= 0, KVM_CREATE_VCPU, vcpu->fd, vm);
 
 	TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size "
 		"smaller than expected, vcpu_mmap_sz: %i expected_min: %zi",
-- 
GitLab


From e29f5d0c3c7c055b36ef55f9e92100450b2506a3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 15:00:30 -0700
Subject: [PATCH 0611/4076] KVM: selftests: Remove x86's so called "MMIO
 warning" test

Remove x86's mmio_warning_test, as it is unnecessarily complex (there's no
reason to fork, spawn threads, initialize srand(), etc..), unnecessarily
restrictive (triggering triple fault is not unique to Intel CPUs without
unrestricted guest), and provides no meaningful coverage beyond what
basic fuzzing can achieve (running a vCPU with garbage is fuzzing's bread
and butter).

That the test has *all* of the above flaws is not coincidental, as the
code was copy+pasted almost verbatim from the syzkaller reproducer that
originally found the KVM bug (which has long since been fixed).

Cc: Michal Luczaj <mhal@rbox.co>
Link: https://groups.google.com/g/syzkaller/c/lHfau8E3SOE
Link: https://lore.kernel.org/r/20230815220030.560372-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile          |   1 -
 .../selftests/kvm/x86_64/mmio_warning_test.c  | 121 ------------------
 2 files changed, 122 deletions(-)
 delete mode 100644 tools/testing/selftests/kvm/x86_64/mmio_warning_test.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 914987220a629..4412b42d95deb 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -86,7 +86,6 @@ TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
-TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
 TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test
 TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
deleted file mode 100644
index ce1ccc4c1503b..0000000000000
--- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
+++ /dev/null
@@ -1,121 +0,0 @@
-/*
- * mmio_warning_test
- *
- * Copyright (C) 2019, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Test that we don't get a kernel warning when we call KVM_RUN after a
- * triple fault occurs.  To get the triple fault to occur we call KVM_RUN
- * on a VCPU that hasn't been properly setup.
- *
- */
-
-#define _GNU_SOURCE
-#include <fcntl.h>
-#include <kvm_util.h>
-#include <linux/kvm.h>
-#include <processor.h>
-#include <pthread.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-#include <sys/mman.h>
-#include <sys/stat.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <test_util.h>
-#include <unistd.h>
-
-#define NTHREAD 4
-#define NPROCESS 5
-
-struct thread_context {
-	int kvmcpu;
-	struct kvm_run *run;
-};
-
-void *thr(void *arg)
-{
-	struct thread_context *tc = (struct thread_context *)arg;
-	int res;
-	int kvmcpu = tc->kvmcpu;
-	struct kvm_run *run = tc->run;
-
-	res = ioctl(kvmcpu, KVM_RUN, 0);
-	pr_info("ret1=%d exit_reason=%d suberror=%d\n",
-		res, run->exit_reason, run->internal.suberror);
-
-	return 0;
-}
-
-void test(void)
-{
-	int i, kvm, kvmvm, kvmcpu;
-	pthread_t th[NTHREAD];
-	struct kvm_run *run;
-	struct thread_context tc;
-
-	kvm = open("/dev/kvm", O_RDWR);
-	TEST_ASSERT(kvm != -1, "failed to open /dev/kvm");
-	kvmvm = __kvm_ioctl(kvm, KVM_CREATE_VM, NULL);
-	TEST_ASSERT(kvmvm > 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, kvmvm));
-	kvmcpu = ioctl(kvmvm, KVM_CREATE_VCPU, 0);
-	TEST_ASSERT(kvmcpu != -1, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, kvmcpu));
-	run = (struct kvm_run *)mmap(0, 4096, PROT_READ|PROT_WRITE, MAP_SHARED,
-				    kvmcpu, 0);
-	tc.kvmcpu = kvmcpu;
-	tc.run = run;
-	srand(getpid());
-	for (i = 0; i < NTHREAD; i++) {
-		pthread_create(&th[i], NULL, thr, (void *)(uintptr_t)&tc);
-		usleep(rand() % 10000);
-	}
-	for (i = 0; i < NTHREAD; i++)
-		pthread_join(th[i], NULL);
-}
-
-int get_warnings_count(void)
-{
-	int warnings;
-	FILE *f;
-
-	f = popen("dmesg | grep \"WARNING:\" | wc -l", "r");
-	if (fscanf(f, "%d", &warnings) < 1)
-		warnings = 0;
-	pclose(f);
-
-	return warnings;
-}
-
-int main(void)
-{
-	int warnings_before, warnings_after;
-
-	TEST_REQUIRE(host_cpu_is_intel);
-
-	TEST_REQUIRE(!vm_is_unrestricted_guest(NULL));
-
-	warnings_before = get_warnings_count();
-
-	for (int i = 0; i < NPROCESS; ++i) {
-		int status;
-		int pid = fork();
-
-		if (pid < 0)
-			exit(1);
-		if (pid == 0) {
-			test();
-			exit(0);
-		}
-		while (waitpid(pid, &status, __WALL) != pid)
-			;
-	}
-
-	warnings_after = get_warnings_count();
-	TEST_ASSERT(warnings_before == warnings_after,
-		   "Warnings found in kernel.  Run 'dmesg' to inspect them.");
-
-	return 0;
-}
-- 
GitLab


From b77f5ef8ebe4d8ee3a712a216415d7f4d4d0acf2 Mon Sep 17 00:00:00 2001
From: Youngmin Nam <youngmin.nam@samsung.com>
Date: Sun, 26 Nov 2023 18:46:18 +0900
Subject: [PATCH 0612/4076] pinctrl: samsung: add irq_set_affinity() for non
 wake up external gpio interrupt

To support affinity setting for non wake up external gpio interrupt, add
irq_set_affinity callback using irq number from pinctrl driver data.

Before this patch, changing the irq affinity of gpio interrupt is not
possible:

    # cat /proc/irq/418/smp_affinity
    3ff
    # echo 00f > /proc/irq/418/smp_affinity
    # cat /proc/irq/418/smp_affinity
    3ff
    # cat /proc/interrupts
               CPU0       CPU1       CPU2       CPU3    ...
    418:       3631          0          0          0    ...

With this patch applied, it's possible to change irq affinity of gpio
interrupt:

    # cat /proc/irq/418/smp_affinity
    3ff
    # echo 00f > /proc/irq/418/smp_affinity
    # cat /proc/irq/418/smp_affinity
    00f
    # cat /proc/interrupts
               CPU0       CPU1       CPU2       CPU3      ...
    418:       3893        201        181        188      ...

Signed-off-by: Youngmin Nam <youngmin.nam@samsung.com>
Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Tested-by: Sam Protsenko <semen.protsenko@linaro.org>
Link: https://lore.kernel.org/r/20231126094618.2545116-1-youngmin.nam@samsung.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/pinctrl/samsung/pinctrl-exynos.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 6b58ec84e34b1..5d7b788282e94 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -147,6 +147,19 @@ static int exynos_irq_set_type(struct irq_data *irqd, unsigned int type)
 	return 0;
 }
 
+static int exynos_irq_set_affinity(struct irq_data *irqd,
+				   const struct cpumask *dest, bool force)
+{
+	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
+	struct samsung_pinctrl_drv_data *d = bank->drvdata;
+	struct irq_data *parent = irq_get_irq_data(d->irq);
+
+	if (parent)
+		return parent->chip->irq_set_affinity(parent, dest, force);
+
+	return -EINVAL;
+}
+
 static int exynos_irq_request_resources(struct irq_data *irqd)
 {
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
@@ -212,6 +225,7 @@ static const struct exynos_irq_chip exynos_gpio_irq_chip __initconst = {
 		.irq_mask = exynos_irq_mask,
 		.irq_ack = exynos_irq_ack,
 		.irq_set_type = exynos_irq_set_type,
+		.irq_set_affinity = exynos_irq_set_affinity,
 		.irq_request_resources = exynos_irq_request_resources,
 		.irq_release_resources = exynos_irq_release_resources,
 	},
-- 
GitLab


From 11e5ea5242e38d44fcede879473566bb6d68f954 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 28 Nov 2023 15:04:01 +0100
Subject: [PATCH 0613/4076] KVM: arm64: Use helpers to classify exception types
 reported via ESR

Currently, we rely on the fact that exceptions can be trivially
classified by applying a mask/value pair to the syndrome value reported
via the ESR register, but this will no longer be true once we enable
support for 5 level paging.

So introduce a couple of helpers that encapsulate this mask/value pair
matching, and wire them up in the code. No functional change intended,
the actual handling of translation level -1 will be added in a
subsequent patch.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
[maz: folded in changes suggested by Mark]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231128140400.3132145-2-ardb@google.com
---
 arch/arm64/include/asm/esr.h            | 15 +++++++++++
 arch/arm64/include/asm/kvm_emulate.h    | 36 +++++++++++--------------
 arch/arm64/kvm/hyp/include/hyp/fault.h  |  2 +-
 arch/arm64/kvm/hyp/include/hyp/switch.h |  2 +-
 arch/arm64/kvm/mmu.c                    | 35 ++++++++++++------------
 5 files changed, 50 insertions(+), 40 deletions(-)

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index ae35939f395bb..353fe08546cf9 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -392,6 +392,21 @@ static inline bool esr_is_data_abort(unsigned long esr)
 	return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
 }
 
+static inline bool esr_fsc_is_translation_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT;
+}
+
+static inline bool esr_fsc_is_permission_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM;
+}
+
+static inline bool esr_fsc_is_access_flag_fault(unsigned long esr)
+{
+	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_ACCESS;
+}
+
 const char *esr_get_class_string(unsigned long esr);
 #endif /* __ASSEMBLY */
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index d4f1e9cdd5546..31f13e7d339b5 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -404,24 +404,25 @@ static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
 }
 
-static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+static inline
+bool kvm_vcpu_trap_is_permission_fault(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
+	return esr_fsc_is_permission_fault(kvm_vcpu_get_esr(vcpu));
 }
 
-static __always_inline s8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
+static inline
+bool kvm_vcpu_trap_is_translation_fault(const struct kvm_vcpu *vcpu)
 {
-	/*
-	 * Note: With the introduction of FEAT_LPA2 an extra level of
-	 * translation (level -1) is added. This level (obviously) doesn't
-	 * follow the previous convention of encoding the 4 levels in the 2 LSBs
-	 * of the FSC so this function breaks if the fault is for level -1.
-	 *
-	 * However, stage2 tables always use concatenated tables for first level
-	 * lookup and therefore it is guaranteed that the level will be between
-	 * 0 and 3, and this function continues to work.
-	 */
-	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
+	return esr_fsc_is_translation_fault(kvm_vcpu_get_esr(vcpu));
+}
+
+static inline
+u64 kvm_vcpu_trap_get_perm_fault_granule(const struct kvm_vcpu *vcpu)
+{
+	unsigned long esr = kvm_vcpu_get_esr(vcpu);
+
+	BUG_ON(!esr_fsc_is_permission_fault(esr));
+	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(esr & ESR_ELx_FSC_LEVEL));
 }
 
 static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
@@ -464,12 +465,7 @@ static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 		 * first), then a permission fault to allow the flags
 		 * to be set.
 		 */
-		switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
-		case ESR_ELx_FSC_PERM:
-			return true;
-		default:
-			return false;
-		}
+		return kvm_vcpu_trap_is_permission_fault(vcpu);
 	}
 
 	if (kvm_vcpu_trap_is_iabt(vcpu))
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 9ddcfe2c3e574..9e13c1bc2ad54 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
 	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
+	     esr_fsc_is_permission_fault(esr))) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
 	} else {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index f99d8af0b9afb..f44fb11307fb2 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -591,7 +591,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
 		bool valid;
 
-		valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
+		valid = kvm_vcpu_trap_is_translation_fault(vcpu) &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
 			!kvm_vcpu_abt_iss1tw(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 986a2e6fb9004..d14504821b794 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1376,7 +1376,7 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
 
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
-			  unsigned long fault_status)
+			  bool fault_is_perm)
 {
 	int ret = 0;
 	bool write_fault, writable, force_pte = false;
@@ -1390,17 +1390,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	s8 fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 
-	fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level);
+	if (fault_is_perm)
+		fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
-	if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
+	if (fault_is_perm && !write_fault && !exec_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
 	}
@@ -1411,8 +1411,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * only exception to this is when dirty logging is enabled at runtime
 	 * and a write fault needs to collapse a block entry into a table.
 	 */
-	if (fault_status != ESR_ELx_FSC_PERM ||
-	    (logging_active && write_fault)) {
+	if (!fault_is_perm || (logging_active && write_fault)) {
 		ret = kvm_mmu_topup_memory_cache(memcache,
 						 kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
 		if (ret)
@@ -1529,8 +1528,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * backed by a THP and thus use block mapping if possible.
 	 */
 	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
-		if (fault_status ==  ESR_ELx_FSC_PERM &&
-		    fault_granule > PAGE_SIZE)
+		if (fault_is_perm && fault_granule > PAGE_SIZE)
 			vma_pagesize = fault_granule;
 		else
 			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
@@ -1543,7 +1541,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		}
 	}
 
-	if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
+	if (!fault_is_perm && !device && kvm_has_mte(kvm)) {
 		/* Check the VMM hasn't introduced a new disallowed VMA */
 		if (mte_allowed) {
 			sanitise_mte_tags(kvm, pfn, vma_pagesize);
@@ -1569,7 +1567,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
+	if (fault_is_perm && vma_pagesize == fault_granule)
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	else
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
@@ -1620,7 +1618,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
  */
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 {
-	unsigned long fault_status;
+	unsigned long esr;
 	phys_addr_t fault_ipa;
 	struct kvm_memory_slot *memslot;
 	unsigned long hva;
@@ -1628,12 +1626,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
-	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
+	esr = kvm_vcpu_get_esr(vcpu);
 
 	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
-	if (fault_status == ESR_ELx_FSC_FAULT) {
+	if (esr_fsc_is_permission_fault(esr)) {
 		/* Beyond sanitised PARange (which is the IPA limit) */
 		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
 			kvm_inject_size_fault(vcpu);
@@ -1668,9 +1666,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
-	if (fault_status != ESR_ELx_FSC_FAULT &&
-	    fault_status != ESR_ELx_FSC_PERM &&
-	    fault_status != ESR_ELx_FSC_ACCESS) {
+	if (!esr_fsc_is_translation_fault(esr) &&
+	    !esr_fsc_is_permission_fault(esr) &&
+	    !esr_fsc_is_access_flag_fault(esr)) {
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1732,13 +1730,14 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	/* Userspace should not be able to register out-of-bounds IPAs */
 	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->arch.hw_mmu));
 
-	if (fault_status == ESR_ELx_FSC_ACCESS) {
+	if (esr_fsc_is_access_flag_fault(esr)) {
 		handle_access_fault(vcpu, fault_ipa);
 		ret = 1;
 		goto out_unlock;
 	}
 
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva,
+			     esr_fsc_is_permission_fault(esr));
 	if (ret == 0)
 		ret = 1;
 out:
-- 
GitLab


From ad6bcdad2b6724e113f191a12f859a9e8456b26d Mon Sep 17 00:00:00 2001
From: Babis Chalios <bchalios@amazon.es>
Date: Wed, 31 May 2023 11:51:19 +0200
Subject: [PATCH 0614/4076] vmgenid: emit uevent when VMGENID updates

We receive an ACPI notification every time the VM Generation ID changes
and use the new ID as fresh randomness added to the entropy pool. This
commits emits a uevent every time we receive the ACPI notification, as a
means to notify the user space that it now is in a new VM.

Signed-off-by: Babis Chalios <bchalios@amazon.es>
Reviewed-by: Alexander Graf <graf@amazon.com>
Reviewed-by: Lennart Poettering <mzxreary@0pointer.de>
Link: https://lore.kernel.org/r/20230531095119.11202-2-bchalios@amazon.es
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/vmgenid.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c
index a1c467a0e9f71..b67a28da47026 100644
--- a/drivers/virt/vmgenid.c
+++ b/drivers/virt/vmgenid.c
@@ -68,6 +68,7 @@ out:
 static void vmgenid_notify(struct acpi_device *device, u32 event)
 {
 	struct vmgenid_state *state = acpi_driver_data(device);
+	char *envp[] = { "NEW_VMGENID=1", NULL };
 	u8 old_id[VMGENID_SIZE];
 
 	memcpy(old_id, state->this_id, sizeof(old_id));
@@ -75,6 +76,7 @@ static void vmgenid_notify(struct acpi_device *device, u32 event)
 	if (!memcmp(old_id, state->this_id, sizeof(old_id)))
 		return;
 	add_vmfork_randomness(state->this_id, sizeof(state->this_id));
+	kobject_uevent_env(&device->dev.kobj, KOBJ_CHANGE, envp);
 }
 
 static const struct acpi_device_id vmgenid_ids[] = {
-- 
GitLab


From bddae3e7ae70586b3805fdbce193760f13b4d73e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 22:16:59 +0100
Subject: [PATCH 0615/4076] remoteproc: k3-dsp: Suppress duplicate error
 message in .remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the remove callback returns non-zero, the driver core emits an
error message about the error value being ignored. As the driver already
emits an error message already, return zero. This has no effect apart
from suppressing the core's message. The platform device gets unbound
irrespective of the return value.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123211657.518181-6-u.kleine-koenig@pengutronix.de
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_dsp_remoteproc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index ef8415a7cd542..40a5fd8763faf 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -835,8 +835,9 @@ static int k3_dsp_rproc_remove(struct platform_device *pdev)
 	if (rproc->state == RPROC_ATTACHED) {
 		ret = rproc_detach(rproc);
 		if (ret) {
+			/* Note this error path leaks resources */
 			dev_err(dev, "failed to detach proc, ret = %d\n", ret);
-			return ret;
+			return 0;
 		}
 	}
 
-- 
GitLab


From cfd0b5c4fd1d23d1c68f704dcd74c1dbdfd7c144 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 22:17:00 +0100
Subject: [PATCH 0616/4076] remoteproc: k3-dsp: Use symbolic error codes in
 error messages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The error message

	failed to send mailbox message (-EINVAL)

is (for a human) more useful than

	failed to send mailbox message, status = -22

Adapt all error messages to use the symbolic names instead of the
numeric constants. The error paths in .probe() make use of
dev_err_probe() which automatically handles EPROBE_DEFER.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123211657.518181-7-u.kleine-koenig@pengutronix.de>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_dsp_remoteproc.c | 78 ++++++++++-------------
 1 file changed, 34 insertions(+), 44 deletions(-)

diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index 40a5fd8763faf..f048ec1bb00f8 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -158,8 +158,8 @@ static void k3_dsp_rproc_kick(struct rproc *rproc, int vqid)
 	/* send the index of the triggered virtqueue in the mailbox payload */
 	ret = mbox_send_message(kproc->mbox, (void *)msg);
 	if (ret < 0)
-		dev_err(dev, "failed to send mailbox message, status = %d\n",
-			ret);
+		dev_err(dev, "failed to send mailbox message (%pe)\n",
+			ERR_PTR(ret));
 }
 
 /* Put the DSP processor into reset */
@@ -170,7 +170,7 @@ static int k3_dsp_rproc_reset(struct k3_dsp_rproc *kproc)
 
 	ret = reset_control_assert(kproc->reset);
 	if (ret) {
-		dev_err(dev, "local-reset assert failed, ret = %d\n", ret);
+		dev_err(dev, "local-reset assert failed (%pe)\n", ERR_PTR(ret));
 		return ret;
 	}
 
@@ -180,7 +180,7 @@ static int k3_dsp_rproc_reset(struct k3_dsp_rproc *kproc)
 	ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
 						    kproc->ti_sci_id);
 	if (ret) {
-		dev_err(dev, "module-reset assert failed, ret = %d\n", ret);
+		dev_err(dev, "module-reset assert failed (%pe)\n", ERR_PTR(ret));
 		if (reset_control_deassert(kproc->reset))
 			dev_warn(dev, "local-reset deassert back failed\n");
 	}
@@ -200,14 +200,14 @@ static int k3_dsp_rproc_release(struct k3_dsp_rproc *kproc)
 	ret = kproc->ti_sci->ops.dev_ops.get_device(kproc->ti_sci,
 						    kproc->ti_sci_id);
 	if (ret) {
-		dev_err(dev, "module-reset deassert failed, ret = %d\n", ret);
+		dev_err(dev, "module-reset deassert failed (%pe)\n", ERR_PTR(ret));
 		return ret;
 	}
 
 lreset:
 	ret = reset_control_deassert(kproc->reset);
 	if (ret) {
-		dev_err(dev, "local-reset deassert failed, ret = %d\n", ret);
+		dev_err(dev, "local-reset deassert failed, (%pe)\n", ERR_PTR(ret));
 		if (kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
 							  kproc->ti_sci_id))
 			dev_warn(dev, "module-reset assert back failed\n");
@@ -246,7 +246,7 @@ static int k3_dsp_rproc_request_mbox(struct rproc *rproc)
 	 */
 	ret = mbox_send_message(kproc->mbox, (void *)RP_MBOX_ECHO_REQUEST);
 	if (ret < 0) {
-		dev_err(dev, "mbox_send_message failed: %d\n", ret);
+		dev_err(dev, "mbox_send_message failed (%pe)\n", ERR_PTR(ret));
 		mbox_free_channel(kproc->mbox);
 		return ret;
 	}
@@ -272,8 +272,8 @@ static int k3_dsp_rproc_prepare(struct rproc *rproc)
 	ret = kproc->ti_sci->ops.dev_ops.get_device(kproc->ti_sci,
 						    kproc->ti_sci_id);
 	if (ret)
-		dev_err(dev, "module-reset deassert failed, cannot enable internal RAM loading, ret = %d\n",
-			ret);
+		dev_err(dev, "module-reset deassert failed, cannot enable internal RAM loading (%pe)\n",
+			ERR_PTR(ret));
 
 	return ret;
 }
@@ -296,7 +296,7 @@ static int k3_dsp_rproc_unprepare(struct rproc *rproc)
 	ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
 						    kproc->ti_sci_id);
 	if (ret)
-		dev_err(dev, "module-reset assert failed, ret = %d\n", ret);
+		dev_err(dev, "module-reset assert failed (%pe)\n", ERR_PTR(ret));
 
 	return ret;
 }
@@ -561,9 +561,9 @@ static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc)
 
 	num_rmems = of_property_count_elems_of_size(np, "memory-region",
 						    sizeof(phandle));
-	if (num_rmems <= 0) {
-		dev_err(dev, "device does not reserved memory regions, ret = %d\n",
-			num_rmems);
+	if (num_rmems < 0) {
+		dev_err(dev, "device does not reserved memory regions (%pe)\n",
+			ERR_PTR(num_rmems));
 		return -EINVAL;
 	}
 	if (num_rmems < 2) {
@@ -575,8 +575,8 @@ static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc)
 	/* use reserved memory region 0 for vring DMA allocations */
 	ret = of_reserved_mem_device_init_by_idx(dev, np, 0);
 	if (ret) {
-		dev_err(dev, "device cannot initialize DMA pool, ret = %d\n",
-			ret);
+		dev_err(dev, "device cannot initialize DMA pool (%pe)\n",
+			ERR_PTR(ret));
 		return ret;
 	}
 
@@ -687,11 +687,8 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	ret = rproc_of_parse_firmware(dev, 0, &fw_name);
-	if (ret) {
-		dev_err(dev, "failed to parse firmware-name property, ret = %d\n",
-			ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to parse firmware-name property\n");
 
 	rproc = rproc_alloc(dev, dev_name(dev), &k3_dsp_rproc_ops, fw_name,
 			    sizeof(*kproc));
@@ -711,39 +708,35 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 
 	kproc->ti_sci = ti_sci_get_by_phandle(np, "ti,sci");
 	if (IS_ERR(kproc->ti_sci)) {
-		ret = PTR_ERR(kproc->ti_sci);
-		if (ret != -EPROBE_DEFER) {
-			dev_err(dev, "failed to get ti-sci handle, ret = %d\n",
-				ret);
-		}
+		ret = dev_err_probe(dev, PTR_ERR(kproc->ti_sci),
+				    "failed to get ti-sci handle\n");
 		kproc->ti_sci = NULL;
 		goto free_rproc;
 	}
 
 	ret = of_property_read_u32(np, "ti,sci-dev-id", &kproc->ti_sci_id);
 	if (ret) {
-		dev_err(dev, "missing 'ti,sci-dev-id' property\n");
+		dev_err_probe(dev, ret, "missing 'ti,sci-dev-id' property\n");
 		goto put_sci;
 	}
 
 	kproc->reset = devm_reset_control_get_exclusive(dev, NULL);
 	if (IS_ERR(kproc->reset)) {
-		ret = PTR_ERR(kproc->reset);
-		dev_err(dev, "failed to get reset, status = %d\n", ret);
+		ret = dev_err_probe(dev, PTR_ERR(kproc->reset),
+				    "failed to get reset\n");
 		goto put_sci;
 	}
 
 	kproc->tsp = k3_dsp_rproc_of_get_tsp(dev, kproc->ti_sci);
 	if (IS_ERR(kproc->tsp)) {
-		dev_err(dev, "failed to construct ti-sci proc control, ret = %d\n",
-			ret);
-		ret = PTR_ERR(kproc->tsp);
+		ret = dev_err_probe(dev, PTR_ERR(kproc->tsp),
+				    "failed to construct ti-sci proc control\n");
 		goto put_sci;
 	}
 
 	ret = ti_sci_proc_request(kproc->tsp);
 	if (ret < 0) {
-		dev_err(dev, "ti_sci_proc_request failed, ret = %d\n", ret);
+		dev_err_probe(dev, ret, "ti_sci_proc_request failed\n");
 		goto free_tsp;
 	}
 
@@ -753,15 +746,14 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 
 	ret = k3_dsp_reserved_mem_init(kproc);
 	if (ret) {
-		dev_err(dev, "reserved memory init failed, ret = %d\n", ret);
+		dev_err_probe(dev, ret, "reserved memory init failed\n");
 		goto release_tsp;
 	}
 
 	ret = kproc->ti_sci->ops.dev_ops.is_on(kproc->ti_sci, kproc->ti_sci_id,
 					       NULL, &p_state);
 	if (ret) {
-		dev_err(dev, "failed to get initial state, mode cannot be determined, ret = %d\n",
-			ret);
+		dev_err_probe(dev, ret, "failed to get initial state, mode cannot be determined\n");
 		goto release_mem;
 	}
 
@@ -787,8 +779,7 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 		if (data->uses_lreset) {
 			ret = reset_control_status(kproc->reset);
 			if (ret < 0) {
-				dev_err(dev, "failed to get reset status, status = %d\n",
-					ret);
+				dev_err_probe(dev, ret, "failed to get reset status\n");
 				goto release_mem;
 			} else if (ret == 0) {
 				dev_warn(dev, "local reset is deasserted for device\n");
@@ -799,8 +790,7 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev)
 
 	ret = rproc_add(rproc);
 	if (ret) {
-		dev_err(dev, "failed to add register device with remoteproc core, status = %d\n",
-			ret);
+		dev_err_probe(dev, ret, "failed to add register device with remoteproc core\n");
 		goto release_mem;
 	}
 
@@ -813,13 +803,13 @@ release_mem:
 release_tsp:
 	ret1 = ti_sci_proc_release(kproc->tsp);
 	if (ret1)
-		dev_err(dev, "failed to release proc, ret = %d\n", ret1);
+		dev_err(dev, "failed to release proc (%pe)\n", ERR_PTR(ret1));
 free_tsp:
 	kfree(kproc->tsp);
 put_sci:
 	ret1 = ti_sci_put_handle(kproc->ti_sci);
 	if (ret1)
-		dev_err(dev, "failed to put ti_sci handle, ret = %d\n", ret1);
+		dev_err(dev, "failed to put ti_sci handle (%pe)\n", ERR_PTR(ret1));
 free_rproc:
 	rproc_free(rproc);
 	return ret;
@@ -836,7 +826,7 @@ static int k3_dsp_rproc_remove(struct platform_device *pdev)
 		ret = rproc_detach(rproc);
 		if (ret) {
 			/* Note this error path leaks resources */
-			dev_err(dev, "failed to detach proc, ret = %d\n", ret);
+			dev_err(dev, "failed to detach proc (%pe)\n", ERR_PTR(ret));
 			return 0;
 		}
 	}
@@ -845,13 +835,13 @@ static int k3_dsp_rproc_remove(struct platform_device *pdev)
 
 	ret = ti_sci_proc_release(kproc->tsp);
 	if (ret)
-		dev_err(dev, "failed to release proc, ret = %d\n", ret);
+		dev_err(dev, "failed to release proc (%pe)\n", ERR_PTR(ret));
 
 	kfree(kproc->tsp);
 
 	ret = ti_sci_put_handle(kproc->ti_sci);
 	if (ret)
-		dev_err(dev, "failed to put ti_sci handle, ret = %d\n", ret);
+		dev_err(dev, "failed to put ti_sci handle (%pe)\n", ERR_PTR(ret));
 
 	k3_dsp_reserved_mem_exit(kproc);
 	rproc_free(kproc->rproc);
-- 
GitLab


From 3f978d9889a2531e48d97cef7f5126f4104ee69c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 22:17:01 +0100
Subject: [PATCH 0617/4076] remoteproc: k3-dsp: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

There is no change in behaviour as .remove() already returned zero
unconditionally.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123211657.518181-8-u.kleine-koenig@pengutronix.de
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/ti_k3_dsp_remoteproc.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index f048ec1bb00f8..ab882e3b7130b 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -815,7 +815,7 @@ free_rproc:
 	return ret;
 }
 
-static int k3_dsp_rproc_remove(struct platform_device *pdev)
+static void k3_dsp_rproc_remove(struct platform_device *pdev)
 {
 	struct k3_dsp_rproc *kproc = platform_get_drvdata(pdev);
 	struct rproc *rproc = kproc->rproc;
@@ -827,7 +827,7 @@ static int k3_dsp_rproc_remove(struct platform_device *pdev)
 		if (ret) {
 			/* Note this error path leaks resources */
 			dev_err(dev, "failed to detach proc (%pe)\n", ERR_PTR(ret));
-			return 0;
+			return;
 		}
 	}
 
@@ -845,8 +845,6 @@ static int k3_dsp_rproc_remove(struct platform_device *pdev)
 
 	k3_dsp_reserved_mem_exit(kproc);
 	rproc_free(kproc->rproc);
-
-	return 0;
 }
 
 static const struct k3_dsp_mem_data c66_mems[] = {
@@ -897,7 +895,7 @@ MODULE_DEVICE_TABLE(of, k3_dsp_of_match);
 
 static struct platform_driver k3_dsp_rproc_driver = {
 	.probe	= k3_dsp_rproc_probe,
-	.remove	= k3_dsp_rproc_remove,
+	.remove_new = k3_dsp_rproc_remove,
 	.driver	= {
 		.name = "k3-dsp-rproc",
 		.of_match_table = k3_dsp_of_match,
-- 
GitLab


From 75bedc1ee90bd54ae8c5ab8be72506f8c5959584 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 18 Oct 2023 08:19:06 -0700
Subject: [PATCH 0618/4076] KVM: x86: Turn off KVM_WERROR by default for all
 configs

Don't enable KVM_WERROR by default for x86-64 builds as KVM's one-off
-Werror enabling is *mostly* superseded by the kernel-wide WERROR, and
enabling KVM_WERROR by default can cause problems for developers working
on other subsystems.  E.g. subsystems that have a "zero W=1 regressions"
rule can inadvertently build KVM with -Werror and W=1, and end up with
build failures that are completely uninteresting to the developer (W=1 is
prone to false positives, especially on older compilers).

Keep KVM_WERROR as there are combinations where enabling WERROR isn't
feasible, e.g. the default FRAME_WARN=1024 on i386 builds generates a
non-zero number of warnings and thus errors, and there are far too many
warnings throughout the kernel to enable WERROR with W=1 (building KVM
with -Werror is desirable (with a sane compiler) as W=1 does generate
useful warnings).

Opportunistically drop the dependency on !COMPILE_TEST as it's completely
meaningless (it was copied from i195's -Werror Kconfig), as the kernel's
WERROR is explicitly *enabled* for COMPILE_TEST=y kernel's, i.e. enabling
-Werror is obviosly not dependent on COMPILE_TEST=n.

Reported-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/all/20231006205415.3501535-1-kuba@kernel.org
Link: https://lore.kernel.org/r/20231018151906.1841689-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/Kconfig | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index c1716e83d1761..4d086fe67a7cd 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -65,13 +65,13 @@ config KVM
 
 config KVM_WERROR
 	bool "Compile KVM with -Werror"
-	# KASAN may cause the build to fail due to larger frames
-	default y if X86_64 && !KASAN
-	# We use the dependency on !COMPILE_TEST to not be enabled
-	# blindly in allmodconfig or allyesconfig configurations
-	depends on KVM
-	depends on (X86_64 && !KASAN) || !COMPILE_TEST
-	depends on EXPERT
+	# Disallow KVM's -Werror if KASAN is enabled, e.g. to guard against
+	# randomized configs from selecting KVM_WERROR=y, which doesn't play
+	# nice with KASAN.  KASAN builds generates warnings for the default
+	# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
+	# Building KVM with -Werror and KASAN is still doable via enabling
+	# the kernel-wide WERROR=y.
+	depends on KVM && EXPERT && !KASAN
 	help
 	  Add -Werror to the build flags for KVM.
 
-- 
GitLab


From eefe5e6682099445f77f2d97d4c525f9ac9d9b07 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Mon, 23 Oct 2023 17:16:35 -0700
Subject: [PATCH 0619/4076] KVM: x86: Advertise CPUID.(EAX=7,ECX=2):EDX[5:0] to
 userspace

The low five bits {INTEL_PSFD, IPRED_CTRL, RRSBA_CTRL, DDPD_U, BHI_CTRL}
advertise the availability of specific bits in IA32_SPEC_CTRL. Since KVM
dynamically determines the legal IA32_SPEC_CTRL bits for the underlying
hardware, the hard work has already been done. Just let userspace know
that a guest can use these IA32_SPEC_CTRL bits.

The sixth bit (MCDT_NO) states that the processor does not exhibit MXCSR
Configuration Dependent Timing (MCDT) behavior. This is an inherent
property of the physical processor that is inherited by the virtual
CPU. Pass that information on to userspace.

Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Link: https://lore.kernel.org/r/20231024001636.890236-1-jmattson@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c         | 21 ++++++++++++++++++---
 arch/x86/kvm/reverse_cpuid.h | 12 ++++++++++++
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index dda6fc4cfae88..1811a9ddfe1d4 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -679,6 +679,11 @@ void kvm_set_cpu_caps(void)
 		F(AMX_COMPLEX)
 	);
 
+	kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX,
+		F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) |
+		F(BHI_CTRL) | F(MCDT_NO)
+	);
+
 	kvm_cpu_cap_mask(CPUID_D_1_EAX,
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd
 	);
@@ -960,13 +965,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		break;
 	/* function 7 has additional index. */
 	case 7:
-		entry->eax = min(entry->eax, 1u);
+		max_idx = entry->eax = min(entry->eax, 2u);
 		cpuid_entry_override(entry, CPUID_7_0_EBX);
 		cpuid_entry_override(entry, CPUID_7_ECX);
 		cpuid_entry_override(entry, CPUID_7_EDX);
 
-		/* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */
-		if (entry->eax == 1) {
+		/* KVM only supports up to 0x7.2, capped above via min(). */
+		if (max_idx >= 1) {
 			entry = do_host_cpuid(array, function, 1);
 			if (!entry)
 				goto out;
@@ -976,6 +981,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			entry->ebx = 0;
 			entry->ecx = 0;
 		}
+		if (max_idx >= 2) {
+			entry = do_host_cpuid(array, function, 2);
+			if (!entry)
+				goto out;
+
+			cpuid_entry_override(entry, CPUID_7_2_EDX);
+			entry->ecx = 0;
+			entry->ebx = 0;
+			entry->eax = 0;
+		}
 		break;
 	case 0xa: { /* Architectural Performance Monitoring */
 		union cpuid10_eax eax;
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index b816506783755..17007016d8b5e 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -16,6 +16,7 @@ enum kvm_only_cpuid_leafs {
 	CPUID_7_1_EDX,
 	CPUID_8000_0007_EDX,
 	CPUID_8000_0022_EAX,
+	CPUID_7_2_EDX,
 	NR_KVM_CPU_CAPS,
 
 	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
@@ -46,6 +47,14 @@ enum kvm_only_cpuid_leafs {
 #define X86_FEATURE_AMX_COMPLEX         KVM_X86_FEATURE(CPUID_7_1_EDX, 8)
 #define X86_FEATURE_PREFETCHITI         KVM_X86_FEATURE(CPUID_7_1_EDX, 14)
 
+/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */
+#define X86_FEATURE_INTEL_PSFD		KVM_X86_FEATURE(CPUID_7_2_EDX, 0)
+#define X86_FEATURE_IPRED_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 1)
+#define KVM_X86_FEATURE_RRSBA_CTRL	KVM_X86_FEATURE(CPUID_7_2_EDX, 2)
+#define X86_FEATURE_DDPD_U		KVM_X86_FEATURE(CPUID_7_2_EDX, 3)
+#define X86_FEATURE_BHI_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
+#define X86_FEATURE_MCDT_NO		KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
+
 /* CPUID level 0x80000007 (EDX). */
 #define KVM_X86_FEATURE_CONSTANT_TSC	KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8)
 
@@ -80,6 +89,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX},
 	[CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX},
 	[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
+	[CPUID_7_2_EDX]       = {         7, 2, CPUID_EDX},
 };
 
 /*
@@ -116,6 +126,8 @@ static __always_inline u32 __feature_translate(int x86_feature)
 		return KVM_X86_FEATURE_CONSTANT_TSC;
 	else if (x86_feature == X86_FEATURE_PERFMON_V2)
 		return KVM_X86_FEATURE_PERFMON_V2;
+	else if (x86_feature == X86_FEATURE_RRSBA_CTRL)
+		return KVM_X86_FEATURE_RRSBA_CTRL;
 
 	return x86_feature;
 }
-- 
GitLab


From d2ff98b7926e0956c0b92f7d5066cd8a65e7dfef Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 29 Nov 2023 13:06:14 +0200
Subject: [PATCH 0620/4076] dt-bindings: input: gpio-keys: Allow optional
 dedicated wakeirq

Allow configuring an optional dedicated wakeirq for gpio-keys that
some SoCs have.

Let's use the common interrupt naming "irq" and "wakeup" that we already
have in use for some drivers and subsystems like i2c framework.

Note that the gpio-keys interrupt property is optional. If only a gpio
property is specified, the driver tries to translate the gpio into an
interrupt.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231129110618.27551-1-tony@atomide.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/gpio-keys.yaml  | 41 ++++++++++++++++++-
 1 file changed, 40 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/input/gpio-keys.yaml b/Documentation/devicetree/bindings/input/gpio-keys.yaml
index 159cd9d9fe573..cc78c21529213 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys.yaml
+++ b/Documentation/devicetree/bindings/input/gpio-keys.yaml
@@ -31,7 +31,23 @@ patternProperties:
         maxItems: 1
 
       interrupts:
-        maxItems: 1
+        oneOf:
+          - items:
+              - description: Optional key interrupt or wakeup interrupt
+          - items:
+              - description: Key interrupt
+              - description: Wakeup interrupt
+
+      interrupt-names:
+        description:
+          Optional interrupt names, can be used to specify a separate dedicated
+          wake-up interrupt in addition to the gpio irq
+        oneOf:
+          - items:
+              - enum: [ irq, wakeup ]
+          - items:
+              - const: irq
+              - const: wakeup
 
       label:
         description: Descriptive name of the key.
@@ -97,6 +113,20 @@ patternProperties:
       - required:
           - gpios
 
+    allOf:
+      - if:
+          properties:
+            interrupts:
+              minItems: 2
+          required:
+            - interrupts
+        then:
+          properties:
+            interrupt-names:
+              minItems: 2
+          required:
+            - interrupt-names
+
     dependencies:
       wakeup-event-action: [ wakeup-source ]
       linux,input-value: [ gpios ]
@@ -137,6 +167,15 @@ examples:
             linux,code = <108>;
             interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
         };
+
+        key-wakeup {
+            label = "GPIO Key WAKEUP";
+            linux,code = <143>;
+            interrupts-extended = <&intc 2 IRQ_TYPE_EDGE_FALLING>,
+                                  <&intc_wakeup 0 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "irq", "wakeup";
+            wakeup-source;
+        };
     };
 
 ...
-- 
GitLab


From 3717194f249227a3dfd8433bd9374cc7e0cf823d Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 29 Nov 2023 13:06:15 +0200
Subject: [PATCH 0621/4076] Input: gpio-keys - add system suspend support for
 dedicated wakeirqs

Some SoCs have a separate dedicated wake-up interrupt controller that can
be used to wake up the system from deeper idle states. We already support
configuring a separate interrupt for a gpio-keys button to be used with a
gpio line. However, we are lacking support system suspend for cases where
a separate interrupt needs to be used in deeper sleep modes.

Because of it's nature, gpio-keys does not know about the runtime PM state
of the button gpios, and may have several gpio buttons configured for each
gpio-keys device instance. Implementing runtime PM support for gpio-keys
does not help, and we cannot use drivers/base/power/wakeirq.c support. We
need to implement custom wakeirq support for gpio-keys.

For handling a dedicated wakeirq for system suspend, we enable and disable
it with gpio_keys_enable_wakeup() and gpio_keys_disable_wakeup() that we
already use based on device_may_wakeup().

Some systems may have a dedicated wakeirq that can also be used as the
main interrupt, this is already working for gpio-keys. Let's add some
wakeirq related comments while at it as the usage with a gpio line and
separate interrupt line may not be obvious.

Tested-by: Dhruva Gole <d-gole@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231129110618.27551-2-tony@atomide.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/gpio_keys.c | 69 ++++++++++++++++++++++++++++--
 include/linux/gpio_keys.h          |  2 +
 2 files changed, 67 insertions(+), 4 deletions(-)

diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index 2e7c2c046e675..06c09b7addf8e 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -45,7 +45,9 @@ struct gpio_button_data {
 	unsigned int software_debounce;	/* in msecs, for GPIO-driven buttons */
 
 	unsigned int irq;
+	unsigned int wakeirq;
 	unsigned int wakeup_trigger_type;
+
 	spinlock_t lock;
 	bool disabled;
 	bool key_pressed;
@@ -511,6 +513,7 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 	struct gpio_button_data *bdata = &ddata->data[idx];
 	irq_handler_t isr;
 	unsigned long irqflags;
+	const char *wakedesc;
 	int irq;
 	int error;
 
@@ -575,6 +578,14 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 					!gpiod_cansleep(bdata->gpiod);
 		}
 
+		/*
+		 * If an interrupt was specified, use it instead of the gpio
+		 * interrupt and use the gpio for reading the state. A separate
+		 * interrupt may be used as the main button interrupt for
+		 * runtime PM to detect events also in deeper idle states. If a
+		 * dedicated wakeirq is used for system suspend only, see below
+		 * for bdata->wakeirq setup.
+		 */
 		if (button->irq) {
 			bdata->irq = button->irq;
 		} else {
@@ -672,6 +683,36 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 		return error;
 	}
 
+	if (!button->wakeirq)
+		return 0;
+
+	/* Use :wakeup suffix like drivers/base/power/wakeirq.c does */
+	wakedesc = devm_kasprintf(dev, GFP_KERNEL, "%s:wakeup", desc);
+	if (!wakedesc)
+		return -ENOMEM;
+
+	bdata->wakeirq = button->wakeirq;
+	irqflags |= IRQF_NO_SUSPEND;
+
+	/*
+	 * Wakeirq shares the handler with the main interrupt, it's only
+	 * active during system suspend. See gpio_keys_button_enable_wakeup()
+	 * and gpio_keys_button_disable_wakeup().
+	 */
+	error = devm_request_any_context_irq(dev, bdata->wakeirq, isr,
+					     irqflags, wakedesc, bdata);
+	if (error < 0) {
+		dev_err(dev, "Unable to claim wakeirq %d; error %d\n",
+			bdata->irq, error);
+		return error;
+	}
+
+	/*
+	 * Disable wakeirq until suspend. IRQF_NO_AUTOEN won't work if
+	 * IRQF_SHARED was set based on !button->can_disable.
+	 */
+	disable_irq(bdata->wakeirq);
+
 	return 0;
 }
 
@@ -728,7 +769,7 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 	struct gpio_keys_platform_data *pdata;
 	struct gpio_keys_button *button;
 	struct fwnode_handle *child;
-	int nbuttons;
+	int nbuttons, irq;
 
 	nbuttons = device_get_child_node_count(dev);
 	if (nbuttons == 0)
@@ -750,9 +791,19 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 	device_property_read_string(dev, "label", &pdata->name);
 
 	device_for_each_child_node(dev, child) {
-		if (is_of_node(child))
-			button->irq =
-				irq_of_parse_and_map(to_of_node(child), 0);
+		if (is_of_node(child)) {
+			irq = of_irq_get_byname(to_of_node(child), "irq");
+			if (irq > 0)
+				button->irq = irq;
+
+			irq = of_irq_get_byname(to_of_node(child), "wakeup");
+			if (irq > 0)
+				button->wakeirq = irq;
+
+			if (!button->irq && !button->wakeirq)
+				button->irq =
+					irq_of_parse_and_map(to_of_node(child), 0);
+		}
 
 		if (fwnode_property_read_u32(child, "linux,code",
 					     &button->code)) {
@@ -921,6 +972,11 @@ gpio_keys_button_enable_wakeup(struct gpio_button_data *bdata)
 		}
 	}
 
+	if (bdata->wakeirq) {
+		enable_irq(bdata->wakeirq);
+		disable_irq(bdata->irq);
+	}
+
 	return 0;
 }
 
@@ -929,6 +985,11 @@ gpio_keys_button_disable_wakeup(struct gpio_button_data *bdata)
 {
 	int error;
 
+	if (bdata->wakeirq) {
+		enable_irq(bdata->irq);
+		disable_irq(bdata->wakeirq);
+	}
+
 	/*
 	 * The trigger type is always both edges for gpio-based keys and we do
 	 * not support changing wakeup trigger for interrupt-based keys.
diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h
index 3f84aeb81e480..80fa930b04c67 100644
--- a/include/linux/gpio_keys.h
+++ b/include/linux/gpio_keys.h
@@ -21,6 +21,7 @@ struct device;
  *			disable button via sysfs
  * @value:		axis value for %EV_ABS
  * @irq:		Irq number in case of interrupt keys
+ * @wakeirq:		Optional dedicated wake-up interrupt
  */
 struct gpio_keys_button {
 	unsigned int code;
@@ -34,6 +35,7 @@ struct gpio_keys_button {
 	bool can_disable;
 	int value;
 	unsigned int irq;
+	unsigned int wakeirq;
 };
 
 /**
-- 
GitLab


From 80c883db87d9ffe2d685e91ba07a087b1c246c78 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Mon, 23 Oct 2023 17:16:36 -0700
Subject: [PATCH 0622/4076] KVM: x86: Use a switch statement and macros in
 __feature_translate()

Use a switch statement with macro-generated case statements to handle
translating feature flags in order to reduce the probability of runtime
errors due to copy+paste goofs, to make compile-time errors easier to
debug, and to make the code more readable.

E.g. the compiler won't directly generate an error for duplicate if
statements

	if (x86_feature == X86_FEATURE_SGX1)
		return KVM_X86_FEATURE_SGX1;
	else if (x86_feature == X86_FEATURE_SGX2)
		return KVM_X86_FEATURE_SGX1;

and so instead reverse_cpuid_check() will fail due to the untranslated
entry pointing at a Linux-defined leaf, which provides practically no
hint as to what is broken

  arch/x86/kvm/reverse_cpuid.h:108:2: error: call to __compiletime_assert_450 declared with 'error' attribute:
                                      BUILD_BUG_ON failed: x86_leaf == CPUID_LNX_4
          BUILD_BUG_ON(x86_leaf == CPUID_LNX_4);
          ^
whereas duplicate case statements very explicitly point at the offending
code:

  arch/x86/kvm/reverse_cpuid.h:125:2: error: duplicate case value '361'
          KVM_X86_TRANSLATE_FEATURE(SGX2);
          ^
  arch/x86/kvm/reverse_cpuid.h:124:2: error: duplicate case value '360'
          KVM_X86_TRANSLATE_FEATURE(SGX1);
          ^

And without macros, the opposite type of copy+paste goof doesn't generate
any error at compile-time, e.g. this yields no complaints:

        case X86_FEATURE_SGX1:
                return KVM_X86_FEATURE_SGX1;
        case X86_FEATURE_SGX2:
                return KVM_X86_FEATURE_SGX1;

Note, __feature_translate() is forcibly inlined and the feature is known
at compile-time, so the code generation between an if-elif sequence and a
switch statement should be identical.

Signed-off-by: Jim Mattson <jmattson@google.com>
Link: https://lore.kernel.org/r/20231024001636.890236-2-jmattson@google.com
[sean: use a macro, rewrite changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/reverse_cpuid.h | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index 17007016d8b5e..aadefcaa9561d 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -116,20 +116,19 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
  */
 static __always_inline u32 __feature_translate(int x86_feature)
 {
-	if (x86_feature == X86_FEATURE_SGX1)
-		return KVM_X86_FEATURE_SGX1;
-	else if (x86_feature == X86_FEATURE_SGX2)
-		return KVM_X86_FEATURE_SGX2;
-	else if (x86_feature == X86_FEATURE_SGX_EDECCSSA)
-		return KVM_X86_FEATURE_SGX_EDECCSSA;
-	else if (x86_feature == X86_FEATURE_CONSTANT_TSC)
-		return KVM_X86_FEATURE_CONSTANT_TSC;
-	else if (x86_feature == X86_FEATURE_PERFMON_V2)
-		return KVM_X86_FEATURE_PERFMON_V2;
-	else if (x86_feature == X86_FEATURE_RRSBA_CTRL)
-		return KVM_X86_FEATURE_RRSBA_CTRL;
-
-	return x86_feature;
+#define KVM_X86_TRANSLATE_FEATURE(f)	\
+	case X86_FEATURE_##f: return KVM_X86_FEATURE_##f
+
+	switch (x86_feature) {
+	KVM_X86_TRANSLATE_FEATURE(SGX1);
+	KVM_X86_TRANSLATE_FEATURE(SGX2);
+	KVM_X86_TRANSLATE_FEATURE(SGX_EDECCSSA);
+	KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC);
+	KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
+	KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
+	default:
+		return x86_feature;
+	}
 }
 
 static __always_inline u32 __feature_leaf(int x86_feature)
-- 
GitLab


From c52ffadc65e28ab461fd055e9991e8d8106a0056 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 18 Oct 2023 12:56:38 -0700
Subject: [PATCH 0623/4076] KVM: x86: Don't unnecessarily force masterclock
 update on vCPU hotplug

Don't force a masterclock update when a vCPU synchronizes to the current
TSC generation, e.g. when userspace hotplugs a pre-created vCPU into the
VM.  Unnecessarily updating the masterclock is undesirable as it can cause
kvmclock's time to jump, which is particularly painful on systems with a
stable TSC as kvmclock _should_ be fully reliable on such systems.

The unexpected time jumps are due to differences in the TSC=>nanoseconds
conversion algorithms between kvmclock and the host's CLOCK_MONOTONIC_RAW
(the pvclock algorithm is inherently lossy).  When updating the
masterclock, KVM refreshes the "base", i.e. moves the elapsed time since
the last update from the kvmclock/pvclock algorithm to the
CLOCK_MONOTONIC_RAW algorithm.  Synchronizing kvmclock with
CLOCK_MONOTONIC_RAW is the lesser of evils when the TSC is unstable, but
adds no real value when the TSC is stable.

Prior to commit 7f187922ddf6 ("KVM: x86: update masterclock values on TSC
writes"), KVM did NOT force an update when synchronizing a vCPU to the
current generation.

  commit 7f187922ddf6b67f2999a76dcb71663097b75497
  Author: Marcelo Tosatti <mtosatti@redhat.com>
  Date:   Tue Nov 4 21:30:44 2014 -0200

    KVM: x86: update masterclock values on TSC writes

    When the guest writes to the TSC, the masterclock TSC copy must be
    updated as well along with the TSC_OFFSET update, otherwise a negative
    tsc_timestamp is calculated at kvm_guest_time_update.

    Once "if (!vcpus_matched && ka->use_master_clock)" is simplified to
    "if (ka->use_master_clock)", the corresponding "if (!ka->use_master_clock)"
    becomes redundant, so remove the do_request boolean and collapse
    everything into a single condition.

Before that, KVM only re-synced the masterclock if the masterclock was
enabled or disabled  Note, at the time of the above commit, VMX
synchronized TSC on *guest* writes to MSR_IA32_TSC:

        case MSR_IA32_TSC:
                kvm_write_tsc(vcpu, msr_info);
                break;

which is why the changelog specifically says "guest writes", but the bug
that was being fixed wasn't unique to guest write, i.e. a TSC write from
the host would suffer the same problem.

So even though KVM stopped synchronizing on guest writes as of commit
0c899c25d754 ("KVM: x86: do not attempt TSC synchronization on guest
writes"), simply reverting commit 7f187922ddf6 is not an option.  Figuring
out how a negative tsc_timestamp could be computed requires a bit more
sleuthing.

In kvm_write_tsc() (at the time), except for KVM's "less than 1 second"
hack, KVM snapshotted the vCPU's current TSC *and* the current time in
nanoseconds, where kvm->arch.cur_tsc_nsec is the current host kernel time
in nanoseconds:

        ns = get_kernel_ns();

        ...

        if (usdiff < USEC_PER_SEC &&
            vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
                ...
        } else {
                /*
                 * We split periods of matched TSC writes into generations.
                 * For each generation, we track the original measured
                 * nanosecond time, offset, and write, so if TSCs are in
                 * sync, we can match exact offset, and if not, we can match
                 * exact software computation in compute_guest_tsc()
                 *
                 * These values are tracked in kvm->arch.cur_xxx variables.
                 */
                kvm->arch.cur_tsc_generation++;
                kvm->arch.cur_tsc_nsec = ns;
                kvm->arch.cur_tsc_write = data;
                kvm->arch.cur_tsc_offset = offset;
                matched = false;
                pr_debug("kvm: new tsc generation %llu, clock %llu\n",
                         kvm->arch.cur_tsc_generation, data);
        }

        ...

        /* Keep track of which generation this VCPU has synchronized to */
        vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation;
        vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
        vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;

Note that the above creates a new generation and sets "matched" to false!
But because kvm_track_tsc_matching() looks for matched+1, i.e. doesn't
require the vCPU that creates the new generation to match itself, KVM
would immediately compute vcpus_matched as true for VMs with a single vCPU.
As a result, KVM would skip the masterlock update, even though a new TSC
generation was created:

        vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
                         atomic_read(&vcpu->kvm->online_vcpus));

        if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC)
                if (!ka->use_master_clock)
                        do_request = 1;

        if (!vcpus_matched && ka->use_master_clock)
                        do_request = 1;

        if (do_request)
                kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);

On hardware without TSC scaling support, vcpu->tsc_catchup is set to true
if the guest TSC frequency is faster than the host TSC frequency, even if
the TSC is otherwise stable.  And for that mode, kvm_guest_time_update(),
by way of compute_guest_tsc(), uses vcpu->arch.this_tsc_nsec, a.k.a. the
kernel time at the last TSC write, to compute the guest TSC relative to
kernel time:

  static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
  {
        u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec,
                                      vcpu->arch.virtual_tsc_mult,
                                      vcpu->arch.virtual_tsc_shift);
        tsc += vcpu->arch.this_tsc_write;
        return tsc;
  }

Except the "kernel_ns" passed to compute_guest_tsc() isn't the current
kernel time, it's the masterclock snapshot!

        spin_lock(&ka->pvclock_gtod_sync_lock);
        use_master_clock = ka->use_master_clock;
        if (use_master_clock) {
                host_tsc = ka->master_cycle_now;
                kernel_ns = ka->master_kernel_ns;
        }
        spin_unlock(&ka->pvclock_gtod_sync_lock);

        if (vcpu->tsc_catchup) {
                u64 tsc = compute_guest_tsc(v, kernel_ns);
                if (tsc > tsc_timestamp) {
                        adjust_tsc_offset_guest(v, tsc - tsc_timestamp);
                        tsc_timestamp = tsc;
                }
        }

And so when KVM skips the masterclock update after a TSC write, i.e. after
a new TSC generation is started, the "kernel_ns-vcpu->arch.this_tsc_nsec"
is *guaranteed* to generate a negative value, because this_tsc_nsec was
captured after ka->master_kernel_ns.

Forcing a masterclock update essentially fudged around that problem, but
in a heavy handed way that introduced undesirable side effects, i.e.
unnecessarily forces a masterclock update when a new vCPU joins the party
via hotplug.

Note, KVM forces masterclock updates in other weird ways that are also
likely unnecessary, e.g. when establishing a new Xen shared info page and
when userspace creates a brand new vCPU.  But the Xen thing is firmly a
separate mess, and there are no known userspace VMMs that utilize kvmclock
*and* create new vCPUs after the VM is up and running.  I.e. the other
issues are future problems.

Reported-by: Dongli Zhang <dongli.zhang@oracle.com>
Closes: https://lore.kernel.org/all/20230926230649.67852-1-dongli.zhang@oracle.com
Fixes: 7f187922ddf6 ("KVM: x86: update masterclock values on TSC writes")
Cc: David Woodhouse <dwmw2@infradead.org>
Reviewed-by: Dongli Zhang <dongli.zhang@oracle.com>
Tested-by: Dongli Zhang <dongli.zhang@oracle.com>
Link: https://lore.kernel.org/r/20231018195638.1898375-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/x86.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d0772b470413..99ec48203667c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2510,26 +2510,29 @@ static inline int gtod_is_based_on_tsc(int mode)
 }
 #endif
 
-static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
+static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation)
 {
 #ifdef CONFIG_X86_64
-	bool vcpus_matched;
 	struct kvm_arch *ka = &vcpu->kvm->arch;
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 
-	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
-			 atomic_read(&vcpu->kvm->online_vcpus));
+	/*
+	 * To use the masterclock, the host clocksource must be based on TSC
+	 * and all vCPUs must have matching TSCs.  Note, the count for matching
+	 * vCPUs doesn't include the reference vCPU, hence "+1".
+	 */
+	bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 ==
+				 atomic_read(&vcpu->kvm->online_vcpus)) &&
+				gtod_is_based_on_tsc(gtod->clock.vclock_mode);
 
 	/*
-	 * Once the masterclock is enabled, always perform request in
-	 * order to update it.
-	 *
-	 * In order to enable masterclock, the host clocksource must be TSC
-	 * and the vcpus need to have matched TSCs.  When that happens,
-	 * perform request to enable masterclock.
+	 * Request a masterclock update if the masterclock needs to be toggled
+	 * on/off, or when starting a new generation and the masterclock is
+	 * enabled (compute_guest_tsc() requires the masterclock snapshot to be
+	 * taken _after_ the new generation is created).
 	 */
-	if (ka->use_master_clock ||
-	    (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
+	if ((ka->use_master_clock && new_generation) ||
+	    (ka->use_master_clock != use_master_clock))
 		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -2706,7 +2709,7 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
 	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
 	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
 
-	kvm_track_tsc_matching(vcpu);
+	kvm_track_tsc_matching(vcpu, !matched);
 }
 
 static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
-- 
GitLab


From a484755ab2526ebdbe042397cdd6e427eb4b1a68 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 18 Oct 2023 12:41:03 -0700
Subject: [PATCH 0624/4076] Revert "nSVM: Check for reserved encodings of
 TLB_CONTROL in nested VMCB"

Revert KVM's made-up consistency check on SVM's TLB control.  The APM says
that unsupported encodings are reserved, but the APM doesn't state that
VMRUN checks for a supported encoding.  Unless something is called out
in "Canonicalization and Consistency Checks" or listed as MBZ (Must Be
Zero), AMD behavior is typically to let software shoot itself in the foot.

This reverts commit 174a921b6975ef959dd82ee9e8844067a62e3ec1.

Fixes: 174a921b6975 ("nSVM: Check for reserved encodings of TLB_CONTROL in nested VMCB")
Reported-by: Stefan Sterz <s.sterz@proxmox.com>
Closes: https://lkml.kernel.org/r/b9915c9c-4cf6-051a-2d91-44cc6380f455%40proxmox.com
Cc: stable@vger.kernel.org
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20231018194104.1896415-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/nested.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 3fea8c47679e6..60891b9ce25f6 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -247,18 +247,6 @@ static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size)
 	    kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1);
 }
 
-static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl)
-{
-	/* Nested FLUSHBYASID is not supported yet.  */
-	switch(tlb_ctl) {
-		case TLB_CONTROL_DO_NOTHING:
-		case TLB_CONTROL_FLUSH_ALL_ASID:
-			return true;
-		default:
-			return false;
-	}
-}
-
 static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
 					 struct vmcb_ctrl_area_cached *control)
 {
@@ -278,9 +266,6 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
 					   IOPM_SIZE)))
 		return false;
 
-	if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl)))
-		return false;
-
 	if (CC((control->int_ctl & V_NMI_ENABLE_MASK) &&
 	       !vmcb12_is_intercept(control, INTERCEPT_NMI))) {
 		return false;
-- 
GitLab


From 176bfc5b17fee327585583a427e2857d9dfd8f68 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 18 Oct 2023 12:41:04 -0700
Subject: [PATCH 0625/4076] KVM: nSVM: Advertise support for flush-by-ASID

Advertise support for FLUSHBYASID when nested SVM is enabled, as KVM can
always emulate flushing TLB entries for a vmcb12 ASID, e.g. by running L2
with a new, fresh ASID in vmcb02.  Some modern hypervisors, e.g. VMWare
Workstation 17, require FLUSHBYASID support and will refuse to run if it's
not present.

Punt on proper support, as "Honor L1's request to flush an ASID on nested
VMRUN" is one of the TODO items in the (incomplete) list of issues that
need to be addressed in order for KVM to NOT do a full TLB flush on every
nested SVM transition (see nested_svm_transition_tlb_flush()).

Reported-by: Stefan Sterz <s.sterz@proxmox.com>
Closes: https://lkml.kernel.org/r/b9915c9c-4cf6-051a-2d91-44cc6380f455%40proxmox.com
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20231018194104.1896415-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7121463123584..30352c42d62ac 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -5076,6 +5076,13 @@ static __init void svm_set_cpu_caps(void)
 		kvm_cpu_cap_set(X86_FEATURE_SVM);
 		kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN);
 
+		/*
+		 * KVM currently flushes TLBs on *every* nested SVM transition,
+		 * and so for all intents and purposes KVM supports flushing by
+		 * ASID, i.e. KVM is guaranteed to honor every L1 ASID flush.
+		 */
+		kvm_cpu_cap_set(X86_FEATURE_FLUSHBYASID);
+
 		if (nrips)
 			kvm_cpu_cap_set(X86_FEATURE_NRIPS);
 
-- 
GitLab


From 770d6aa2e416fd26f0356e258c77a37574ad9b8c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 18 Oct 2023 12:36:17 -0700
Subject: [PATCH 0626/4076] KVM: SVM: Explicitly require FLUSHBYASID to enable
 SEV support

Add a sanity check that FLUSHBYASID is available if SEV is supported in
hardware, as SEV (and beyond) guests are bound to a single ASID, i.e. KVM
can't "flush" by assigning a new, fresh ASID to the guest.  If FLUSHBYASID
isn't supported for some bizarre reason, KVM would completely fail to do
TLB flushes for SEV+ guests (see pre_svm_run() and pre_sev_run()).

Cc: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20231018193617.1895752-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 4900c078045ac..d0c580607f009 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2191,10 +2191,13 @@ void __init sev_hardware_setup(void)
 	/*
 	 * SEV must obviously be supported in hardware.  Sanity check that the
 	 * CPU supports decode assists, which is mandatory for SEV guests to
-	 * support instruction emulation.
+	 * support instruction emulation.  Ditto for flushing by ASID, as SEV
+	 * guests are bound to a single ASID, i.e. KVM can't rotate to a new
+	 * ASID to effect a TLB flush.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_SEV) ||
-	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)))
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) ||
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID)))
 		goto out;
 
 	/* Retrieve SEV CPUID information */
-- 
GitLab


From 72046d0a077a8f70d4d1e5bdeed324c1a310da8c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 18 Oct 2023 12:20:21 -0700
Subject: [PATCH 0627/4076] KVM: SVM: Don't intercept IRET when injecting NMI
 and vNMI is enabled

When vNMI is enabled, rely entirely on hardware to correctly handle NMI
blocking, i.e. don't intercept IRET to detect when NMIs are no longer
blocked.  KVM already correctly ignores svm->nmi_masked when vNMI is
enabled, so the effect of the bug is essentially an unnecessary VM-Exit.

KVM intercepts IRET for two reasons:
 - To track NMI masking to be able to know at any point of time if NMI
   is masked.
 - To track NMI windows (to inject another NMI after the guest executes
   IRET, i.e. unblocks NMIs)

When vNMI is enabled, both cases are handled by hardware:
- NMI masking state resides in int_ctl.V_NMI_BLOCKING and can be read by
  KVM at will.
- Hardware automatically "injects" pending virtual NMIs when virtual NMIs
  become unblocked.

However, even though pending a virtual NMI for hardware to handle is the
most common way to synthesize a guest NMI, KVM may still directly inject
an NMI via when KVM is handling two "simultaneous" NMIs (see comments in
process_nmi() for details on KVM's simultaneous NMI handling).  Per AMD's
APM, hardware sets the BLOCKING flag when software directly injects an NMI
as well, i.e. KVM doesn't need to manually mark vNMIs as blocked:

  If Event Injection is used to inject an NMI when NMI Virtualization is
  enabled, VMRUN sets V_NMI_MASK in the guest state.

Note, it's still possible that KVM could trigger a spurious IRET VM-Exit.
When running a nested guest, KVM disables vNMI for L2 and thus will enable
IRET interception (in both vmcb01 and vmcb02) while running L2 reason.  If
a nested VM-Exit happens before L2 executes IRET, KVM can end up running
L1 with vNMI enable and IRET intercepted.  This is also a benign bug, and
even less likely to happen, i.e. can be safely punted to a future fix.

Fixes: fa4c027a7956 ("KVM: x86: Add support for SVM's Virtual NMI")
Link: https://lore.kernel.org/all/ZOdnuDZUd4mevCqe@google.como
Cc: Santosh Shukla <santosh.shukla@amd.com>
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Santosh Shukla <santosh.shukla@amd.com>
Link: https://lore.kernel.org/r/20231018192021.1893261-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 30352c42d62ac..c46f07b282305 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3560,8 +3560,15 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu)
 	if (svm->nmi_l1_to_l2)
 		return;
 
-	svm->nmi_masked = true;
-	svm_set_iret_intercept(svm);
+	/*
+	 * No need to manually track NMI masking when vNMI is enabled, hardware
+	 * automatically sets V_NMI_BLOCKING_MASK as appropriate, including the
+	 * case where software directly injects an NMI.
+	 */
+	if (!is_vnmi_enabled(svm)) {
+		svm->nmi_masked = true;
+		svm_set_iret_intercept(svm);
+	}
 	++vcpu->stat.nmi_injections;
 }
 
-- 
GitLab


From 15223c4f973a6120665ece9ce1ad17aec0be0e6c Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 31 Oct 2023 08:52:40 +0100
Subject: [PATCH 0628/4076] KVM: SVM,VMX: Use %rip-relative addressing to
 access kvm_rebooting

Instruction with %rip-relative address operand is one byte shorter than
its absolute address counterpart and is also compatible with position
independent executable (-fpie) build.

No functional changes intended.

Cc: Sean Christopherson <seanjc@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Link: https://lore.kernel.org/r/20231031075312.47525-1-ubizjak@gmail.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/vmenter.S | 10 +++++-----
 arch/x86/kvm/vmx/vmenter.S |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index ef2ebabb059c8..9499f9c6b0771 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -270,16 +270,16 @@ SYM_FUNC_START(__svm_vcpu_run)
 	RESTORE_GUEST_SPEC_CTRL_BODY
 	RESTORE_HOST_SPEC_CTRL_BODY
 
-10:	cmpb $0, kvm_rebooting
+10:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
 	ud2
-30:	cmpb $0, kvm_rebooting
+30:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 4b
 	ud2
-50:	cmpb $0, kvm_rebooting
+50:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 6b
 	ud2
-70:	cmpb $0, kvm_rebooting
+70:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 8b
 	ud2
 
@@ -381,7 +381,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	RESTORE_GUEST_SPEC_CTRL_BODY
 	RESTORE_HOST_SPEC_CTRL_BODY
 
-3:	cmpb $0, kvm_rebooting
+3:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
 	ud2
 
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index be275a0410a89..906ecd0015113 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -289,7 +289,7 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL)
 	RET
 
 .Lfixup:
-	cmpb $0, kvm_rebooting
+	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne .Lvmfail
 	ud2
 .Lvmfail:
-- 
GitLab


From cbb359d81a2695bb5e63ec9de06fcbef28518891 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 3 Nov 2023 16:05:36 -0700
Subject: [PATCH 0629/4076] KVM: x86/pmu: Move PMU reset logic to common x86
 code

Move the common (or at least "ignored") aspects of resetting the vPMU to
common x86 code, along with the stop/release helpers that are no used only
by the common pmu.c.

There is no need to manually handle fixed counters as all_valid_pmc_idx
tracks both fixed and general purpose counters, and resetting the vPMU is
far from a hot path, i.e. the extra bit of overhead to the PMC from the
index is a non-issue.

Zero fixed_ctr_ctrl in common code even though it's Intel specific.
Ensuring it's zero doesn't harm AMD/SVM in any way, and stopping the fixed
counters via all_valid_pmc_idx, but not clearing the associated control
bits, would be odd/confusing.

Make the .reset() hook optional as SVM no longer needs vendor specific
handling.

Cc: stable@vger.kernel.org
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20231103230541.352265-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm-x86-pmu-ops.h |  2 +-
 arch/x86/kvm/pmu.c                     | 40 +++++++++++++++++++++++++-
 arch/x86/kvm/pmu.h                     | 18 ------------
 arch/x86/kvm/svm/pmu.c                 | 16 -----------
 arch/x86/kvm/vmx/pmu_intel.c           | 20 -------------
 5 files changed, 40 insertions(+), 56 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index 6c98f4bb4228b..058bc636356a1 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -22,7 +22,7 @@ KVM_X86_PMU_OP(get_msr)
 KVM_X86_PMU_OP(set_msr)
 KVM_X86_PMU_OP(refresh)
 KVM_X86_PMU_OP(init)
-KVM_X86_PMU_OP(reset)
+KVM_X86_PMU_OP_OPTIONAL(reset)
 KVM_X86_PMU_OP_OPTIONAL(deliver_pmi)
 KVM_X86_PMU_OP_OPTIONAL(cleanup)
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 9ae07db6f0f64..027e9c3c2b93e 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -250,6 +250,24 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
 	return true;
 }
 
+static void pmc_release_perf_event(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		perf_event_release_kernel(pmc->perf_event);
+		pmc->perf_event = NULL;
+		pmc->current_config = 0;
+		pmc_to_pmu(pmc)->event_count--;
+	}
+}
+
+static void pmc_stop_counter(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		pmc->counter = pmc_read_counter(pmc);
+		pmc_release_perf_event(pmc);
+	}
+}
+
 static int filter_cmp(const void *pa, const void *pb, u64 mask)
 {
 	u64 a = *(u64 *)pa & mask;
@@ -654,7 +672,27 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 
 void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 {
-	static_call(kvm_x86_pmu_reset)(vcpu);
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+	int i;
+
+	bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX);
+
+	for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) {
+		pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i);
+		if (!pmc)
+			continue;
+
+		pmc_stop_counter(pmc);
+		pmc->counter = 0;
+
+		if (pmc_is_gp(pmc))
+			pmc->eventsel = 0;
+	}
+
+	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
+
+	static_call_cond(kvm_x86_pmu_reset)(vcpu);
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 1d64113de4883..a46aa9b25150f 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -80,24 +80,6 @@ static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
 	pmc->counter &= pmc_bitmask(pmc);
 }
 
-static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
-{
-	if (pmc->perf_event) {
-		perf_event_release_kernel(pmc->perf_event);
-		pmc->perf_event = NULL;
-		pmc->current_config = 0;
-		pmc_to_pmu(pmc)->event_count--;
-	}
-}
-
-static inline void pmc_stop_counter(struct kvm_pmc *pmc)
-{
-	if (pmc->perf_event) {
-		pmc->counter = pmc_read_counter(pmc);
-		pmc_release_perf_event(pmc);
-	}
-}
-
 static inline bool pmc_is_gp(struct kvm_pmc *pmc)
 {
 	return pmc->type == KVM_PMC_GP;
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 373ff6a6687b3..3fd47de14b38a 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -233,21 +233,6 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void amd_pmu_reset(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	int i;
-
-	for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC; i++) {
-		struct kvm_pmc *pmc = &pmu->gp_counters[i];
-
-		pmc_stop_counter(pmc);
-		pmc->counter = pmc->prev_counter = pmc->eventsel = 0;
-	}
-
-	pmu->global_ctrl = pmu->global_status = 0;
-}
-
 struct kvm_pmu_ops amd_pmu_ops __initdata = {
 	.hw_event_available = amd_hw_event_available,
 	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
@@ -259,7 +244,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = {
 	.set_msr = amd_pmu_set_msr,
 	.refresh = amd_pmu_refresh,
 	.init = amd_pmu_init,
-	.reset = amd_pmu_reset,
 	.EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT,
 	.MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC,
 	.MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS,
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 820d3e1f6b4f8..90c1f7f07e53b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -632,26 +632,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 
 static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	struct kvm_pmc *pmc = NULL;
-	int i;
-
-	for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) {
-		pmc = &pmu->gp_counters[i];
-
-		pmc_stop_counter(pmc);
-		pmc->counter = pmc->prev_counter = pmc->eventsel = 0;
-	}
-
-	for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
-		pmc = &pmu->fixed_counters[i];
-
-		pmc_stop_counter(pmc);
-		pmc->counter = pmc->prev_counter = 0;
-	}
-
-	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
-
 	intel_pmu_release_guest_lbr_event(vcpu);
 }
 
-- 
GitLab


From 1647b52757d59131fe30cf73fa36fac834d4367f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 3 Nov 2023 16:05:37 -0700
Subject: [PATCH 0630/4076] KVM: x86/pmu: Reset the PMU, i.e. stop counters,
 before refreshing

Stop all counters and release all perf events before refreshing the vPMU,
i.e. before reconfiguring the vPMU to respond to changes in the vCPU
model.

Clear need_cleanup in kvm_pmu_reset() as well so that KVM doesn't
prematurely stop counters, e.g. if KVM enters the guest and enables
counters before the vCPU is scheduled out.

Cc: stable@vger.kernel.org
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20231103230541.352265-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/pmu.c | 35 ++++++++++++++++++++++-------------
 1 file changed, 22 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 027e9c3c2b93e..dc8e8e907cfbf 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -657,25 +657,14 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	return 0;
 }
 
-/* refresh PMU settings. This function generally is called when underlying
- * settings are changed (such as changes of PMU CPUID by guest VMs), which
- * should rarely happen.
- */
-void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
-{
-	if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm))
-		return;
-
-	bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX);
-	static_call(kvm_x86_pmu_refresh)(vcpu);
-}
-
 void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
 	int i;
 
+	pmu->need_cleanup = false;
+
 	bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX);
 
 	for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) {
@@ -695,6 +684,26 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 	static_call_cond(kvm_x86_pmu_reset)(vcpu);
 }
 
+
+/*
+ * Refresh the PMU configuration for the vCPU, e.g. if userspace changes CPUID
+ * and/or PERF_CAPABILITIES.
+ */
+void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
+{
+	if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm))
+		return;
+
+	/*
+	 * Stop/release all existing counters/events before realizing the new
+	 * vPMU model.
+	 */
+	kvm_pmu_reset(vcpu);
+
+	bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX);
+	static_call(kvm_x86_pmu_refresh)(vcpu);
+}
+
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-- 
GitLab


From f2f63f7ec6fd13d2d5d5c6d90ea438fbb5a36adc Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 3 Nov 2023 16:05:38 -0700
Subject: [PATCH 0631/4076] KVM: x86/pmu: Stop calling kvm_pmu_reset() at RESET
 (it's redundant)

Drop kvm_vcpu_reset()'s call to kvm_pmu_reset(), the call is performed
only for RESET, which is really just the same thing as vCPU creation,
and kvm_arch_vcpu_create() *just* called kvm_pmu_init(), i.e. there can't
possibly be any work to do.

Unlike Intel, AMD's amd_pmu_refresh() does fill all_valid_pmc_idx even if
guest CPUID is empty, but everything that is at all dynamic is guaranteed
to be '0'/NULL, e.g. it should be impossible for KVM to have already
created a perf event.

Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20231103230541.352265-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/pmu.c | 2 +-
 arch/x86/kvm/pmu.h | 1 -
 arch/x86/kvm/x86.c | 1 -
 3 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index dc8e8e907cfbf..458e836c6efee 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -657,7 +657,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	return 0;
 }
 
-void kvm_pmu_reset(struct kvm_vcpu *vcpu)
+static void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index a46aa9b25150f..db9a12c0a2ef2 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -243,7 +243,6 @@ bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
-void kvm_pmu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_init(struct kvm_vcpu *vcpu);
 void kvm_pmu_cleanup(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d0772b470413..33c071cd95b2e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12221,7 +12221,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	}
 
 	if (!init_event) {
-		kvm_pmu_reset(vcpu);
 		vcpu->arch.smbase = 0x30000;
 
 		vcpu->arch.msr_misc_features_enables = 0;
-- 
GitLab


From ec61b2306dfd117ba5db93dfb54808523ea2b5e0 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 3 Nov 2023 16:05:39 -0700
Subject: [PATCH 0632/4076] KVM: x86/pmu: Remove manual clearing of fields in
 kvm_pmu_init()

Remove code that unnecessarily clears event_count and need_cleanup in
kvm_pmu_init(), the entire kvm_pmu is zeroed just a few lines earlier.
Vendor code doesn't set event_count or need_cleanup during .init(), and
if either VMX or SVM did set those fields it would be a flagrant bug.

Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20231103230541.352265-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/pmu.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 458e836c6efee..c06090196b003 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -710,8 +710,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
 
 	memset(pmu, 0, sizeof(*pmu));
 	static_call(kvm_x86_pmu_init)(vcpu);
-	pmu->event_count = 0;
-	pmu->need_cleanup = false;
 	kvm_pmu_refresh(vcpu);
 }
 
-- 
GitLab


From 89acf1237b81802328beaa094b1139dbb2561883 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 3 Nov 2023 16:05:40 -0700
Subject: [PATCH 0633/4076] KVM: x86/pmu: Update sample period in
 pmc_write_counter()

Update a PMC's sample period in pmc_write_counter() to deduplicate code
across all callers of pmc_write_counter().  Opportunistically move
pmc_write_counter() into pmc.c now that it's doing more work.  WRMSR isn't
such a hot path that an extra CALL+RET pair will be problematic, and the
order of function definitions needs to be changed anyways, i.e. now is a
convenient time to eat the churn.

Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20231103230541.352265-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/pmu.c           | 27 +++++++++++++++++++++++++++
 arch/x86/kvm/pmu.h           | 25 +------------------------
 arch/x86/kvm/svm/pmu.c       |  1 -
 arch/x86/kvm/vmx/pmu_intel.c |  2 --
 4 files changed, 28 insertions(+), 27 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index c06090196b003..3725d001239df 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -161,6 +161,15 @@ static u64 pmc_get_pebs_precise_level(struct kvm_pmc *pmc)
 	return 1;
 }
 
+static u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value)
+{
+	u64 sample_period = (-counter_value) & pmc_bitmask(pmc);
+
+	if (!sample_period)
+		sample_period = pmc_bitmask(pmc) + 1;
+	return sample_period;
+}
+
 static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config,
 				 bool exclude_user, bool exclude_kernel,
 				 bool intr)
@@ -268,6 +277,24 @@ static void pmc_stop_counter(struct kvm_pmc *pmc)
 	}
 }
 
+static void pmc_update_sample_period(struct kvm_pmc *pmc)
+{
+	if (!pmc->perf_event || pmc->is_paused ||
+	    !is_sampling_event(pmc->perf_event))
+		return;
+
+	perf_event_period(pmc->perf_event,
+			  get_sample_period(pmc, pmc->counter));
+}
+
+void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
+{
+	pmc->counter += val - pmc_read_counter(pmc);
+	pmc->counter &= pmc_bitmask(pmc);
+	pmc_update_sample_period(pmc);
+}
+EXPORT_SYMBOL_GPL(pmc_write_counter);
+
 static int filter_cmp(const void *pa, const void *pb, u64 mask)
 {
 	u64 a = *(u64 *)pa & mask;
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index db9a12c0a2ef2..cae85e550f600 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -74,11 +74,7 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 	return counter & pmc_bitmask(pmc);
 }
 
-static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
-{
-	pmc->counter += val - pmc_read_counter(pmc);
-	pmc->counter &= pmc_bitmask(pmc);
-}
+void pmc_write_counter(struct kvm_pmc *pmc, u64 val);
 
 static inline bool pmc_is_gp(struct kvm_pmc *pmc)
 {
@@ -128,25 +124,6 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
 	return NULL;
 }
 
-static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value)
-{
-	u64 sample_period = (-counter_value) & pmc_bitmask(pmc);
-
-	if (!sample_period)
-		sample_period = pmc_bitmask(pmc) + 1;
-	return sample_period;
-}
-
-static inline void pmc_update_sample_period(struct kvm_pmc *pmc)
-{
-	if (!pmc->perf_event || pmc->is_paused ||
-	    !is_sampling_event(pmc->perf_event))
-		return;
-
-	perf_event_period(pmc->perf_event,
-			  get_sample_period(pmc, pmc->counter));
-}
-
 static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 3fd47de14b38a..b6a7ad4d69145 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -161,7 +161,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
 	if (pmc) {
 		pmc_write_counter(pmc, data);
-		pmc_update_sample_period(pmc);
 		return 0;
 	}
 	/* MSR_EVNTSELn */
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 90c1f7f07e53b..a6216c8747291 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -437,11 +437,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			    !(msr & MSR_PMC_FULL_WIDTH_BIT))
 				data = (s64)(s32)data;
 			pmc_write_counter(pmc, data);
-			pmc_update_sample_period(pmc);
 			break;
 		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
 			pmc_write_counter(pmc, data);
-			pmc_update_sample_period(pmc);
 			break;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			reserved_bits = pmu->reserved_bits;
-- 
GitLab


From fd89499a5151d197ba30f7b801f6d8f4646cf446 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 3 Nov 2023 16:05:41 -0700
Subject: [PATCH 0634/4076] KVM: x86/pmu: Track emulated counter events instead
 of previous counter

Explicitly track emulated counter events instead of using the common
counter value that's shared with the hardware counter owned by perf.
Bumping the common counter requires snapshotting the pre-increment value
in order to detect overflow from emulation, and the snapshot approach is
inherently flawed.

Snapshotting the previous counter at every increment assumes that there is
at most one emulated counter event per emulated instruction (or rather,
between checks for KVM_REQ_PMU).  That's mostly holds true today because
KVM only emulates (branch) instructions retired, but the approach will
fall apart if KVM ever supports event types that don't have a 1:1
relationship with instructions.

And KVM already has a relevant bug, as handle_invalid_guest_state()
emulates multiple instructions without checking KVM_REQ_PMU, i.e. could
miss an overflow event due to clobbering pmc->prev_counter.  Not checking
KVM_REQ_PMU is problematic in both cases, but at least with the emulated
counter approach, the resulting behavior is delayed overflow detection,
as opposed to completely lost detection.

Tracking the emulated count fixes another bug where the snapshot approach
can signal spurious overflow due to incorporating both the emulated count
and perf's count in the check, i.e. if overflow is detected by perf, then
KVM's emulation will also incorrectly signal overflow.  Add a comment in
the related code to call out the need to process emulated events *after*
pausing the perf event (big kudos to Mingwei for figuring out that
particular wrinkle).

Cc: Mingwei Zhang <mizhang@google.com>
Cc: Roman Kagan <rkagan@amazon.de>
Cc: Jim Mattson <jmattson@google.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Like Xu <like.xu.linux@gmail.com>
Reviewed-by: Mingwei Zhang <mizhang@google.com>
Link: https://lore.kernel.org/r/20231103230541.352265-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h | 17 +++++++++++-
 arch/x86/kvm/pmu.c              | 48 ++++++++++++++++++++++++---------
 arch/x86/kvm/pmu.h              |  3 ++-
 3 files changed, 53 insertions(+), 15 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a565a2e70f30f..562eaa938847e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -500,8 +500,23 @@ struct kvm_pmc {
 	u8 idx;
 	bool is_paused;
 	bool intr;
+	/*
+	 * Base value of the PMC counter, relative to the *consumed* count in
+	 * the associated perf_event.  This value includes counter updates from
+	 * the perf_event and emulated_count since the last time the counter
+	 * was reprogrammed, but it is *not* the current value as seen by the
+	 * guest or userspace.
+	 *
+	 * The count is relative to the associated perf_event so that KVM
+	 * doesn't need to reprogram the perf_event every time the guest writes
+	 * to the counter.
+	 */
 	u64 counter;
-	u64 prev_counter;
+	/*
+	 * PMC events triggered by KVM emulation that haven't been fully
+	 * processed, i.e. haven't undergone overflow detection.
+	 */
+	u64 emulated_counter;
 	u64 eventsel;
 	struct perf_event *perf_event;
 	struct kvm_vcpu *vcpu;
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 3725d001239df..87cc6c8809ad8 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -127,9 +127,9 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 
 	/*
-	 * Ignore overflow events for counters that are scheduled to be
-	 * reprogrammed, e.g. if a PMI for the previous event races with KVM's
-	 * handling of a related guest WRMSR.
+	 * Ignore asynchronous overflow events for counters that are scheduled
+	 * to be reprogrammed, e.g. if a PMI for the previous event races with
+	 * KVM's handling of a related guest WRMSR.
 	 */
 	if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi))
 		return;
@@ -224,17 +224,30 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config,
 	return 0;
 }
 
-static void pmc_pause_counter(struct kvm_pmc *pmc)
+static bool pmc_pause_counter(struct kvm_pmc *pmc)
 {
 	u64 counter = pmc->counter;
-
-	if (!pmc->perf_event || pmc->is_paused)
-		return;
+	u64 prev_counter;
 
 	/* update counter, reset event value to avoid redundant accumulation */
-	counter += perf_event_pause(pmc->perf_event, true);
+	if (pmc->perf_event && !pmc->is_paused)
+		counter += perf_event_pause(pmc->perf_event, true);
+
+	/*
+	 * Snapshot the previous counter *after* accumulating state from perf.
+	 * If overflow already happened, hardware (via perf) is responsible for
+	 * generating a PMI.  KVM just needs to detect overflow on emulated
+	 * counter events that haven't yet been processed.
+	 */
+	prev_counter = counter & pmc_bitmask(pmc);
+
+	counter += pmc->emulated_counter;
 	pmc->counter = counter & pmc_bitmask(pmc);
+
+	pmc->emulated_counter = 0;
 	pmc->is_paused = true;
+
+	return pmc->counter < prev_counter;
 }
 
 static bool pmc_resume_counter(struct kvm_pmc *pmc)
@@ -289,6 +302,15 @@ static void pmc_update_sample_period(struct kvm_pmc *pmc)
 
 void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
 {
+	/*
+	 * Drop any unconsumed accumulated counts, the WRMSR is a write, not a
+	 * read-modify-write.  Adjust the counter value so that its value is
+	 * relative to the current count, as reading the current count from
+	 * perf is faster than pausing and repgrogramming the event in order to
+	 * reset it to '0'.  Note, this very sneakily offsets the accumulated
+	 * emulated count too, by using pmc_read_counter()!
+	 */
+	pmc->emulated_counter = 0;
 	pmc->counter += val - pmc_read_counter(pmc);
 	pmc->counter &= pmc_bitmask(pmc);
 	pmc_update_sample_period(pmc);
@@ -428,14 +450,15 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	u64 eventsel = pmc->eventsel;
 	u64 new_config = eventsel;
+	bool emulate_overflow;
 	u8 fixed_ctr_ctrl;
 
-	pmc_pause_counter(pmc);
+	emulate_overflow = pmc_pause_counter(pmc);
 
 	if (!pmc_event_is_allowed(pmc))
 		goto reprogram_complete;
 
-	if (pmc->counter < pmc->prev_counter)
+	if (emulate_overflow)
 		__kvm_perf_overflow(pmc, false);
 
 	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
@@ -475,7 +498,6 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 
 reprogram_complete:
 	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
-	pmc->prev_counter = 0;
 }
 
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
@@ -701,6 +723,7 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 
 		pmc_stop_counter(pmc);
 		pmc->counter = 0;
+		pmc->emulated_counter = 0;
 
 		if (pmc_is_gp(pmc))
 			pmc->eventsel = 0;
@@ -772,8 +795,7 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 
 static void kvm_pmu_incr_counter(struct kvm_pmc *pmc)
 {
-	pmc->prev_counter = pmc->counter;
-	pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc);
+	pmc->emulated_counter++;
 	kvm_pmu_request_counter_reprogram(pmc);
 }
 
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index cae85e550f600..7caeb3d8d4fd1 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -66,7 +66,8 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 {
 	u64 counter, enabled, running;
 
-	counter = pmc->counter;
+	counter = pmc->counter + pmc->emulated_counter;
+
 	if (pmc->perf_event && !pmc->is_paused)
 		counter += perf_event_read_value(pmc->perf_event,
 						 &enabled, &running);
-- 
GitLab


From 63912245c19d3a4179da44beefd017eb9270f207 Mon Sep 17 00:00:00 2001
From: Wei Wang <wei.w.wang@intel.com>
Date: Wed, 15 Mar 2023 18:16:06 +0800
Subject: [PATCH 0635/4076] KVM: move KVM_CAP_DEVICE_CTRL to the generic check

KVM_CAP_DEVICE_CTRL allows userspace to check if the kvm_device
framework (e.g. KVM_CREATE_DEVICE) is supported by KVM. Move
KVM_CAP_DEVICE_CTRL to the generic check for the two reasons:
1) it already supports arch agnostic usages (i.e. KVM_DEV_TYPE_VFIO).
For example, userspace VFIO implementation may needs to create
KVM_DEV_TYPE_VFIO on x86, riscv, or arm etc. It is simpler to have it
checked at the generic code than at each arch's code.
2) KVM_CREATE_DEVICE has been added to the generic code.

Link: https://lore.kernel.org/all/20221215115207.14784-1-wei.w.wang@intel.com
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Acked-by: Anup Patel <anup@brainfault.org> (riscv)
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Link: https://lore.kernel.org/r/20230315101606.10636-1-wei.w.wang@intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/arm.c       | 1 -
 arch/powerpc/kvm/powerpc.c | 1 -
 arch/riscv/kvm/vm.c        | 1 -
 arch/s390/kvm/kvm-s390.c   | 1 -
 virt/kvm/kvm_main.c        | 1 +
 5 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e5f75f1f10853..9725783745b47 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -221,7 +221,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = vgic_present;
 		break;
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index c39945a7fce36..13d8309c7ba95 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -528,7 +528,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 7e2b50c692c1b..ce58bc48e5b87 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -179,7 +179,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_riscv_aia_available();
 		break;
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7aa0e668488f0..39463d0e4a1c4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -563,7 +563,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_S390_IRQCHIP:
 	case KVM_CAP_VM_ATTRIBUTES:
 	case KVM_CAP_MP_STATE:
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8758cb799e183..b744eddecbc07 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4873,6 +4873,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #endif
 	case KVM_CAP_BINARY_STATS_FD:
 	case KVM_CAP_SYSTEM_EVENT_DATA:
+	case KVM_CAP_DEVICE_CTRL:
 		return 1;
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 	case KVM_CAP_MEMORY_ATTRIBUTES:
-- 
GitLab


From 573cc0e5cf142d9992d2de3502800890fc717bc0 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Thu, 2 Nov 2023 19:15:24 +0100
Subject: [PATCH 0636/4076] KVM: x86: Harden copying of userspace-array against
 overflow

cpuid.c utilizes vmemdup_user() and array_size() to copy two userspace
arrays. This, currently, does not check for an overflow.

Use the new wrapper vmemdup_array_user() to copy the arrays more safely,
as vmemdup_user() doesn't check for overflow.

Note, KVM explicitly checks the number of entries before duplicating the
array, i.e. adding the overflow check should be a glorified nop.

Suggested-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Link: https://lore.kernel.org/r/20231102181526.43279-2-pstanner@redhat.com
[sean: call out that KVM pre-checks the number of entries]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index dda6fc4cfae88..ad441f0d2917a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -469,7 +469,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 		return -E2BIG;
 
 	if (cpuid->nent) {
-		e = vmemdup_user(entries, array_size(sizeof(*e), cpuid->nent));
+		e = vmemdup_array_user(entries, cpuid->nent, sizeof(*e));
 		if (IS_ERR(e))
 			return PTR_ERR(e);
 
@@ -513,7 +513,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
 		return -E2BIG;
 
 	if (cpuid->nent) {
-		e2 = vmemdup_user(entries, array_size(sizeof(*e2), cpuid->nent));
+		e2 = vmemdup_array_user(entries, cpuid->nent, sizeof(*e2));
 		if (IS_ERR(e2))
 			return PTR_ERR(e2);
 	}
-- 
GitLab


From af76b2dec0984a079d8497bfa37d29a9b55932e1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 30 Nov 2023 14:11:45 -0300
Subject: [PATCH 0637/4076] libapi: Add missing linux/types.h header to get the
 __u64 type on io.h

There are functions using __u64, so we need to have the linux/types.h
header otherwise we'll break when its not included before api/io.h.

Fixes: e95770af4c4a280f ("tools api: Add a lightweight buffered reading api")
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZWjDPL+IzPPsuC3X@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/api/io.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index a77b74c5fb655..2a7fe97588131 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -12,6 +12,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <linux/types.h>
 
 struct io {
 	/* File descriptor being read/ */
-- 
GitLab


From 366efbff58092fac48421fa34018bb34c326088e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 27 Nov 2023 14:08:14 -0800
Subject: [PATCH 0638/4076] libperf: Lazily allocate/size mmap event copy

The event copy in the mmap is used to have storage to read an event. Not
all users of mmaps read the events, such as perf record. The amount of
buffer was also statically set to PERF_SAMPLE_MAX_SIZE rather than the
amount necessary from the header's event size.

Switch to a model where the event_copy is reallocated if too small to
the event's size. This adds the potential for the event to move, so if a
copy of the event pointer were stored it could be broken. All the
current users do:

  while(event = perf_mmap__read_event()) { ... }

and so they would be broken due to the event being overwritten if they
had stored the pointer. Manual inspection and address sanitizer testing
also shows the event pointer not being stored.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231127220902.1315692-3-irogers@google.com
[ Replace two lines with equivalent zfree(&map->event_copy) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/include/internal/mmap.h |  3 ++-
 tools/lib/perf/mmap.c                  | 20 +++++++++++++++++---
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index 5a062af8e9d8e..5f08cab61ecec 100644
--- a/tools/lib/perf/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
@@ -33,7 +33,8 @@ struct perf_mmap {
 	bool			 overwrite;
 	u64			 flush;
 	libperf_unmap_cb_t	 unmap_cb;
-	char			 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+	void			*event_copy;
+	size_t			 event_copy_sz;
 	struct perf_mmap	*next;
 };
 
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 2184814b37dd3..0c903c2372c97 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -19,6 +19,7 @@
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
 		     bool overwrite, libperf_unmap_cb_t unmap_cb)
 {
+	/* Assume fields were zero initialized. */
 	map->fd = -1;
 	map->overwrite = overwrite;
 	map->unmap_cb  = unmap_cb;
@@ -51,13 +52,18 @@ int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
 
 void perf_mmap__munmap(struct perf_mmap *map)
 {
-	if (map && map->base != NULL) {
+	if (!map)
+		return;
+
+	zfree(&map->event_copy);
+	map->event_copy_sz = 0;
+	if (map->base) {
 		munmap(map->base, perf_mmap__mmap_len(map));
 		map->base = NULL;
 		map->fd = -1;
 		refcount_set(&map->refcnt, 0);
 	}
-	if (map && map->unmap_cb)
+	if (map->unmap_cb)
 		map->unmap_cb(map);
 }
 
@@ -223,9 +229,17 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
 		 */
 		if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
 			unsigned int offset = *startp;
-			unsigned int len = min(sizeof(*event), size), cpy;
+			unsigned int len = size, cpy;
 			void *dst = map->event_copy;
 
+			if (size > map->event_copy_sz) {
+				dst = realloc(map->event_copy, size);
+				if (!dst)
+					return NULL;
+				map->event_copy = dst;
+				map->event_copy_sz = size;
+			}
+
 			do {
 				cpy = min(map->mask + 1 - (offset & map->mask), len);
 				memcpy(dst, &data[offset & map->mask], cpy);
-- 
GitLab


From b6a15269cee255dc5fe75c249c701e3956d892cb Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 27 Nov 2023 14:08:16 -0800
Subject: [PATCH 0639/4076] tools api fs: Switch filename__read_str to use io.h

filename__read_str() has its own string reading code that allocates
memory before reading into it. The memory allocated is sized at BUFSIZ
that is 8kb. Most strings are short and so most of this 8kb is wasted.

Refactor io__getline(), as io__getdelim(), so that the newline character
can be configurable and ignored in the case of filename__read_str().

Code like build_caches_for_cpu() in perf's header.c will read many strings
and hold them in a data structure, in this case multiple strings per
cache level per CPU.

Using io.h's io__getline() avoids the wasted memory as strings are
temporarily read into a buffer on the stack before being copied to a
buffer that grows 128 bytes at a time and is never sized larger than the
string.

For a 16 hyperthread system the memory consumption of "perf record
true" is reduced by 180kb, primarily through saving memory when
reading the cache information.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231127220902.1315692-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/api/fs/fs.c | 56 +++++++++++--------------------------------
 tools/lib/api/io.h    | 11 ++++++---
 2 files changed, 22 insertions(+), 45 deletions(-)

diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 5cb0eeec2c8a6..004f2af5504b6 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -16,6 +16,7 @@
 #include <sys/mount.h>
 
 #include "fs.h"
+#include "../io.h"
 #include "debug-internal.h"
 
 #define _STR(x) #x
@@ -344,53 +345,24 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 	return filename__read_ull_base(filename, value, 0);
 }
 
-#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
-
 int filename__read_str(const char *filename, char **buf, size_t *sizep)
 {
-	size_t size = 0, alloc_size = 0;
-	void *bf = NULL, *nbf;
-	int fd, n, err = 0;
-	char sbuf[STRERR_BUFSIZE];
+	struct io io;
+	char bf[128];
+	int err;
 
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
+	io.fd = open(filename, O_RDONLY);
+	if (io.fd < 0)
 		return -errno;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (!nbf) {
-				err = -ENOMEM;
-				break;
-			}
-
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0) {
-			if (size) {
-				pr_warn("read failed %d: %s\n", errno,
-					strerror_r(errno, sbuf, sizeof(sbuf)));
-				err = 0;
-			} else
-				err = -errno;
-
-			break;
-		}
-
-		size += n;
-	} while (n > 0);
-
-	if (!err) {
-		*sizep = size;
-		*buf   = bf;
+	io__init(&io, io.fd, bf, sizeof(bf));
+	*buf = NULL;
+	err = io__getdelim(&io, buf, sizep, /*delim=*/-1);
+	if (err < 0) {
+		free(*buf);
+		*buf = NULL;
 	} else
-		free(bf);
-
-	close(fd);
+		err = 0;
+	close(io.fd);
 	return err;
 }
 
diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index 2a7fe97588131..84adf81020185 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -141,8 +141,8 @@ static inline int io__get_dec(struct io *io, __u64 *dec)
 	}
 }
 
-/* Read up to and including the first newline following the pattern of getline. */
-static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
+/* Read up to and including the first delim. */
+static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_len_out, int delim)
 {
 	char buf[128];
 	int buf_pos = 0;
@@ -152,7 +152,7 @@ static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_l
 
 	/* TODO: reuse previously allocated memory. */
 	free(*line_out);
-	while (ch != '\n') {
+	while (ch != delim) {
 		ch = io__get_char(io);
 
 		if (ch < 0)
@@ -185,4 +185,9 @@ err_out:
 	return -ENOMEM;
 }
 
+static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
+{
+	return io__getdelim(io, line_out, line_len_out, /*delim=*/'\n');
+}
+
 #endif /* __API_IO__ */
-- 
GitLab


From f8846a1a3c54a53f1c30836a2b7143cfa5da223d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 27 Nov 2023 14:08:17 -0800
Subject: [PATCH 0640/4076] tools api fs: Avoid reading whole file for a 1 byte
 bool

sysfs__read_bool() used the first byte from a fully read file into a
string. It then looked at the first byte's value. Avoid doing this and
just read the first byte.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231127220902.1315692-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/api/fs/fs.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 004f2af5504b6..337fde770e45f 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -447,15 +447,22 @@ int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
 
 int sysfs__read_bool(const char *entry, bool *value)
 {
-	char *buf;
-	size_t size;
-	int ret;
+	struct io io;
+	char bf[16];
+	int ret = 0;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
 
-	ret = sysfs__read_str(entry, &buf, &size);
-	if (ret < 0)
-		return ret;
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+	io.fd = open(path, O_RDONLY);
+	if (io.fd < 0)
+		return -errno;
 
-	switch (buf[0]) {
+	io__init(&io, io.fd, bf, sizeof(bf));
+	switch (io__get_char(&io)) {
 	case '1':
 	case 'y':
 	case 'Y':
@@ -469,8 +476,7 @@ int sysfs__read_bool(const char *entry, bool *value)
 	default:
 		ret = -1;
 	}
-
-	free(buf);
+	close(io.fd);
 
 	return ret;
 }
-- 
GitLab


From ab47505ce45b869ab649024dc932e981fcdd6e5f Mon Sep 17 00:00:00 2001
From: Flavio Suligoi <f.suligoi@asem.it>
Date: Wed, 29 Nov 2023 17:45:14 +0100
Subject: [PATCH 0641/4076] backlight: mp3309c: Fix uninitialized local
 variable

In the function "pm3309c_parse_dt_node", when the dimming analog control
mode (by I2C messages) is enabled, the local variable "prop_levels" is
tested without any initialization, as indicated by the following smatch
warning:

drivers/video/backlight/mp3309c.c:279 pm3309c_parse_dt_node() error: uninitialized symbol 'prop_levels'.

To avoid any problem in case of undefined behavior, we need to initialize
it to "NULL".

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/dri-devel/af0a1870-693b-442f-9b11-0503cfcd944a@moroto.mountain/
Fixes: 2e914516a58c ("backlight: mp3309c: Add support for MPS MP3309C")
Signed-off-by: Flavio Suligoi <f.suligoi@asem.it>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20231129164514.2772719-1-f.suligoi@asem.it
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/mp3309c.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/video/backlight/mp3309c.c b/drivers/video/backlight/mp3309c.c
index 3fe4469ef43fd..34d71259fac1d 100644
--- a/drivers/video/backlight/mp3309c.c
+++ b/drivers/video/backlight/mp3309c.c
@@ -203,7 +203,8 @@ static int pm3309c_parse_dt_node(struct mp3309c_chip *chip,
 				 struct mp3309c_platform_data *pdata)
 {
 	struct device_node *node = chip->dev->of_node;
-	struct property *prop_pwms, *prop_levels;
+	struct property *prop_pwms;
+	struct property *prop_levels = NULL;
 	int length = 0;
 	int ret, i;
 	unsigned int num_levels, tmp_value;
-- 
GitLab


From 2cd57cbd5671fb54377ece8e5dbd2c948449b06d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 29 Nov 2023 18:06:24 +0200
Subject: [PATCH 0642/4076] pinctrl: qcom: lpass-lpi: Replace kernel.h with
 what is being used

Replace kernel.h with what exactly is being used, i.e. array_size.h.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231129161459.1002323-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-lpass-lpi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
index 206b2c0ca828c..2017bc80314de 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
@@ -6,8 +6,8 @@
 #ifndef __PINCTRL_LPASS_LPI_H__
 #define __PINCTRL_LPASS_LPI_H__
 
+#include <linux/array_size.h>
 #include <linux/bits.h>
-#include <linux/kernel.h>
 
 #include "../core.h"
 
-- 
GitLab


From 9e863d276876e085910f33b1b45d4bc8125e179a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 29 Nov 2023 18:06:25 +0200
Subject: [PATCH 0643/4076] pinctrl: qcom: lpass-lpi: Remove unused member in
 struct lpi_pingroup

The group is not used anywhere, remove it. And if needed, it should be
struct pingroup anyway.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231129161459.1002323-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-lpass-lpi.h      |  4 ----
 .../pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c   | 16 -------------
 .../pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c | 20 ----------------
 .../pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c   | 20 ----------------
 .../pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c   | 15 ------------
 .../pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c   | 16 -------------
 .../pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c   | 24 -------------------
 .../pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c   | 24 -------------------
 .../pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c   | 24 -------------------
 9 files changed, 163 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
index 2017bc80314de..a9b2f65c1ebe0 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.h
@@ -45,11 +45,8 @@ struct pinctrl_pin_desc;
 
 #define LPI_PINGROUP(id, soff, f1, f2, f3, f4)		\
 	{						\
-		.group.name = "gpio" #id,			\
-		.group.pins = gpio##id##_pins,		\
 		.pin = id,				\
 		.slew_offset = soff,			\
-		.group.num_pins = ARRAY_SIZE(gpio##id##_pins),	\
 		.funcs = (int[]){			\
 			LPI_MUX_gpio,			\
 			LPI_MUX_##f1,			\
@@ -67,7 +64,6 @@ struct pinctrl_pin_desc;
 #define LPI_FLAG_SLEW_RATE_SAME_REG			BIT(0)
 
 struct lpi_pingroup {
-	struct group_desc group;
 	unsigned int pin;
 	/* Bit offset in slew register for SoundWire pins only */
 	int slew_offset;
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
index 99156217c6a5a..6bb39812e1d8b 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c
@@ -36,22 +36,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-
 static const struct pinctrl_pin_desc sc7280_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
index b33483056f423..c0369baf33989 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8280xp-lpass-lpi.c
@@ -45,26 +45,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-
 static const struct pinctrl_pin_desc sc8280xp_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
index e8a6f6f6af547..316d6fc69131b 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6115-lpass-lpi.c
@@ -36,26 +36,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-
 static const struct pinctrl_pin_desc sm6115_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
index cb10ce8d5d28f..9791d9ba5087c 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c
@@ -36,21 +36,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-
 static const struct pinctrl_pin_desc sm8250_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
index 297cc95ac3c01..5b9a2cb216bd8 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c
@@ -36,22 +36,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-
 static const struct pinctrl_pin_desc sm8350_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
index 2e7896791fc0c..a028cbb499472 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8450-lpass-lpi.c
@@ -52,30 +52,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-static int gpio19_pins[] = { 19 };
-static int gpio20_pins[] = { 20 };
-static int gpio21_pins[] = { 21 };
-static int gpio22_pins[] = { 22 };
-
 static const struct pinctrl_pin_desc sm8450_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
index 64458c3fbe5e6..852192b044e17 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c
@@ -52,30 +52,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-static int gpio19_pins[] = { 19 };
-static int gpio20_pins[] = { 20 };
-static int gpio21_pins[] = { 21 };
-static int gpio22_pins[] = { 22 };
-
 static const struct pinctrl_pin_desc sm8550_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
index 6e4be91ff085d..04400c832327a 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650-lpass-lpi.c
@@ -54,30 +54,6 @@ enum lpass_lpi_functions {
 	LPI_MUX__,
 };
 
-static int gpio0_pins[] = { 0 };
-static int gpio1_pins[] = { 1 };
-static int gpio2_pins[] = { 2 };
-static int gpio3_pins[] = { 3 };
-static int gpio4_pins[] = { 4 };
-static int gpio5_pins[] = { 5 };
-static int gpio6_pins[] = { 6 };
-static int gpio7_pins[] = { 7 };
-static int gpio8_pins[] = { 8 };
-static int gpio9_pins[] = { 9 };
-static int gpio10_pins[] = { 10 };
-static int gpio11_pins[] = { 11 };
-static int gpio12_pins[] = { 12 };
-static int gpio13_pins[] = { 13 };
-static int gpio14_pins[] = { 14 };
-static int gpio15_pins[] = { 15 };
-static int gpio16_pins[] = { 16 };
-static int gpio17_pins[] = { 17 };
-static int gpio18_pins[] = { 18 };
-static int gpio19_pins[] = { 19 };
-static int gpio20_pins[] = { 20 };
-static int gpio21_pins[] = { 21 };
-static int gpio22_pins[] = { 22 };
-
 static const struct pinctrl_pin_desc sm8650_lpi_pins[] = {
 	PINCTRL_PIN(0, "gpio0"),
 	PINCTRL_PIN(1, "gpio1"),
-- 
GitLab


From c82c03819b92df0e6472d4c3424e9fd614dde8ad Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 29 Nov 2023 18:06:26 +0200
Subject: [PATCH 0644/4076] pinctrl: equilibrium: Unshadow error code of
 of_property_count_u32_elems()

of_property_count_u32_elems() might return an error code in some cases.
It's naturally better to assign what it's returned to the err variable
and supply the real code to the upper layer(s). Besides that, it's a
common practice to avoid assignments for the data in cases when we know
that the error condition happened. Refactor the code accordingly.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231129161459.1002323-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-equilibrium.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index 5b5ddf7e5d0eb..54755b583d3fa 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -715,12 +715,13 @@ static int eqbr_build_groups(struct eqbr_pinctrl_drv_data *drvdata)
 		if (!prop)
 			continue;
 
-		group.num_pins = of_property_count_u32_elems(np, "pins");
-		if (group.num_pins < 0) {
+		err = of_property_count_u32_elems(np, "pins");
+		if (err < 0) {
 			dev_err(dev, "No pins in the group: %s\n", prop->name);
 			of_node_put(np);
-			return -EINVAL;
+			return err;
 		}
+		group.num_pins = err;
 		group.name = prop->value;
 		group.pins = devm_kcalloc(dev, group.num_pins,
 					  sizeof(*(group.pins)), GFP_KERNEL);
-- 
GitLab


From 271e6a04775d867c9d59cb3c493bebc7970b128e Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 29 Nov 2023 18:06:27 +0200
Subject: [PATCH 0645/4076] pinctrl: equilibrium: Use temporary variable to
 hold pins

The pins are allocated from the heap, but in order to pass
them as constant object, we need to use non-constant pointer.
Achieve this by using a temporary variable.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231129161459.1002323-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-equilibrium.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index 54755b583d3fa..fd59cfdeeface 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -704,7 +704,7 @@ static int eqbr_build_groups(struct eqbr_pinctrl_drv_data *drvdata)
 {
 	struct device *dev = drvdata->dev;
 	struct device_node *node = dev->of_node;
-	unsigned int *pinmux, pin_id, pinmux_id;
+	unsigned int *pins, *pinmux, pin_id, pinmux_id;
 	struct group_desc group;
 	struct device_node *np;
 	struct property *prop;
@@ -723,15 +723,14 @@ static int eqbr_build_groups(struct eqbr_pinctrl_drv_data *drvdata)
 		}
 		group.num_pins = err;
 		group.name = prop->value;
-		group.pins = devm_kcalloc(dev, group.num_pins,
-					  sizeof(*(group.pins)), GFP_KERNEL);
-		if (!group.pins) {
+		pins = devm_kcalloc(dev, group.num_pins, sizeof(*pins), GFP_KERNEL);
+		if (!pins) {
 			of_node_put(np);
 			return -ENOMEM;
 		}
+		group.pins = pins;
 
-		pinmux = devm_kcalloc(dev, group.num_pins, sizeof(*pinmux),
-				      GFP_KERNEL);
+		pinmux = devm_kcalloc(dev, group.num_pins, sizeof(*pinmux), GFP_KERNEL);
 		if (!pinmux) {
 			of_node_put(np);
 			return -ENOMEM;
@@ -750,7 +749,7 @@ static int eqbr_build_groups(struct eqbr_pinctrl_drv_data *drvdata)
 				of_node_put(np);
 				return -EINVAL;
 			}
-			group.pins[j] = pin_id;
+			pins[j] = pin_id;
 			if (of_property_read_u32_index(np, "pinmux", j, &pinmux_id)) {
 				dev_err(dev, "Group %s: Read intel pinmux id failed\n",
 					group.name);
-- 
GitLab


From 26ea8229e7adb508133b078790990486c1657cc7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 29 Nov 2023 18:06:28 +0200
Subject: [PATCH 0646/4076] pinctrl: imx: Use temporary variable to hold pins

The pins are allocated from the heap, but in order to pass
them as constant object, we need to use non-constant pointer.
Achieve this by using a temporary variable.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231129161459.1002323-6-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/pinctrl-imx.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 9bc16943014f0..28164b04b1bed 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -511,6 +511,7 @@ static int imx_pinctrl_parse_groups(struct device_node *np,
 {
 	const struct imx_pinctrl_soc_info *info = ipctl->info;
 	struct imx_pin *pin;
+	unsigned int *pins;
 	int size, pin_size;
 	const __be32 *list;
 	int i;
@@ -557,20 +558,20 @@ static int imx_pinctrl_parse_groups(struct device_node *np,
 	grp->data = devm_kcalloc(ipctl->dev,
 				 grp->num_pins, sizeof(struct imx_pin),
 				 GFP_KERNEL);
-	grp->pins = devm_kcalloc(ipctl->dev,
-				 grp->num_pins, sizeof(unsigned int),
-				 GFP_KERNEL);
-	if (!grp->pins || !grp->data)
+	if (!grp->data)
+		return -ENOMEM;
+
+	pins = devm_kcalloc(ipctl->dev, grp->num_pins, sizeof(*pins), GFP_KERNEL);
+	if (!pins)
 		return -ENOMEM;
+	grp->pins = pins;
 
 	for (i = 0; i < grp->num_pins; i++) {
 		pin = &((struct imx_pin *)(grp->data))[i];
 		if (info->flags & IMX_USE_SCU)
-			info->imx_pinctrl_parse_pin(ipctl, &grp->pins[i],
-						  pin, &list);
+			info->imx_pinctrl_parse_pin(ipctl, &pins[i], pin, &list);
 		else
-			imx_pinctrl_parse_pin_mmio(ipctl, &grp->pins[i],
-						   pin, &list, np);
+			imx_pinctrl_parse_pin_mmio(ipctl, &pins[i], pin, &list, np);
 	}
 
 	return 0;
-- 
GitLab


From 1aa4bb916808503bf6fedd00f50f2077f91cebaa Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 27 Oct 2023 10:26:38 -0700
Subject: [PATCH 0647/4076] KVM: x86/mmu: Fix off-by-1 when splitting huge
 pages during CLEAR

Fix an off-by-1 error when passing in the range of pages to
kvm_mmu_try_split_huge_pages() during CLEAR_DIRTY_LOG. Specifically, end
is the last page that needs to be split (inclusive) so pass in `end + 1`
since kvm_mmu_try_split_huge_pages() expects the `end` to be
non-inclusive.

At worst this will cause a huge page to be write-protected instead of
eagerly split, which is purely a performance issue, not a correctness
issue. But even that is unlikely as it would require userspace pass in a
bitmap where the last page is the only 4K page on a huge page that needs
to be split.

Reported-by: Vipin Sharma <vipinsh@google.com>
Fixes: cb00a70bd4b7 ("KVM: x86/mmu: Split huge pages mapped by the TDP MMU during KVM_CLEAR_DIRTY_LOG")
Signed-off-by: David Matlack <dmatlack@google.com>
Link: https://lore.kernel.org/r/20231027172640.2335197-2-dmatlack@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 59b026b6ad2a2..29ac130fcb843 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1392,7 +1392,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		gfn_t end = slot->base_gfn + gfn_offset + __fls(mask);
 
 		if (READ_ONCE(eager_page_split))
-			kvm_mmu_try_split_huge_pages(kvm, slot, start, end, PG_LEVEL_4K);
+			kvm_mmu_try_split_huge_pages(kvm, slot, start, end + 1, PG_LEVEL_4K);
 
 		kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M);
 
-- 
GitLab


From 45a61ebb221117748d3567a86908618f431ac824 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 27 Oct 2023 10:26:39 -0700
Subject: [PATCH 0648/4076] KVM: x86/mmu: Check for leaf SPTE when clearing
 dirty bit in the TDP MMU

Re-check that the given SPTE is still a leaf and present SPTE after a
failed cmpxchg in clear_dirty_gfn_range(). clear_dirty_gfn_range()
intends to only operate on present leaf SPTEs, but that could change
after a failed cmpxchg.

A check for present was added in commit 3354ef5a592d ("KVM: x86/mmu:
Check for present SPTE when clearing dirty bit in TDP MMU") but the
check for leaf is still buried in tdp_root_for_each_leaf_pte() and does
not get rechecked on retry.

Fixes: a6a0b05da9f3 ("kvm: x86/mmu: Support dirty logging for the TDP MMU")
Signed-off-by: David Matlack <dmatlack@google.com>
Link: https://lore.kernel.org/r/20231027172640.2335197-3-dmatlack@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6cd4dd631a2fa..038983b135740 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1522,12 +1522,13 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 
 	rcu_read_lock();
 
-	tdp_root_for_each_leaf_pte(iter, root, start, end) {
+	tdp_root_for_each_pte(iter, root, start, end) {
 retry:
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
+		if (!is_shadow_present_pte(iter.old_spte) ||
+		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
-		if (!is_shadow_present_pte(iter.old_spte))
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
 
 		KVM_MMU_WARN_ON(kvm_ad_enabled() &&
-- 
GitLab


From 5f3c8c9187b6fa8675951f9fad5b99b11fed21f6 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sat, 25 Nov 2023 03:33:57 -0500
Subject: [PATCH 0649/4076] KVM: x86/mmu: remove unnecessary "bool shared"
 argument from functions

Neither tdp_mmu_next_root nor kvm_tdp_mmu_put_root need to know
if the lock is taken for read or write.  Either way, protection
is achieved via RCU and tdp_mmu_pages_lock.  Remove the argument
and just assert that the lock is taken.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20231125083400.1399197-2-pbonzini@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c     |  2 +-
 arch/x86/kvm/mmu/tdp_mmu.c | 34 +++++++++++++++++++++-------------
 arch/x86/kvm/mmu/tdp_mmu.h |  3 +--
 3 files changed, 23 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 29ac130fcb843..ace9f7c131322 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3580,7 +3580,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 		return;
 
 	if (is_tdp_mmu_page(sp))
-		kvm_tdp_mmu_put_root(kvm, sp, false);
+		kvm_tdp_mmu_put_root(kvm, sp);
 	else if (!--sp->root_count && sp->role.invalid)
 		kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 038983b135740..8cd805fa15164 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -73,10 +73,13 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
 	tdp_mmu_free_sp(sp);
 }
 
-void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
-			  bool shared)
+void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
-	kvm_lockdep_assert_mmu_lock_held(kvm, shared);
+	/*
+	 * Either read or write is okay, but mmu_lock must be held because
+	 * writers are not required to take tdp_mmu_pages_lock.
+	 */
+	lockdep_assert_held(&kvm->mmu_lock);
 
 	if (!refcount_dec_and_test(&root->tdp_mmu_root_count))
 		return;
@@ -106,10 +109,16 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
  */
 static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 					      struct kvm_mmu_page *prev_root,
-					      bool shared, bool only_valid)
+					      bool only_valid)
 {
 	struct kvm_mmu_page *next_root;
 
+	/*
+	 * While the roots themselves are RCU-protected, fields such as
+	 * role.invalid are protected by mmu_lock.
+	 */
+	lockdep_assert_held(&kvm->mmu_lock);
+
 	rcu_read_lock();
 
 	if (prev_root)
@@ -132,7 +141,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 	rcu_read_unlock();
 
 	if (prev_root)
-		kvm_tdp_mmu_put_root(kvm, prev_root, shared);
+		kvm_tdp_mmu_put_root(kvm, prev_root);
 
 	return next_root;
 }
@@ -144,13 +153,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
  * recent root. (Unless keeping a live reference is desirable.)
  *
  * If shared is set, this function is operating under the MMU lock in read
- * mode. In the unlikely event that this thread must free a root, the lock
- * will be temporarily dropped and reacquired in write mode.
+ * mode.
  */
 #define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid);	\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid);		\
 	     _root;								\
-	     _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid))	\
+	     _root = tdp_mmu_next_root(_kvm, _root, _only_valid))		\
 		if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) &&		\
 		    kvm_mmu_page_as_id(_root) != _as_id) {			\
 		} else
@@ -159,9 +167,9 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
 
 #define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared)			\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false);		\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, false);			\
 	     _root;								\
-	     _root = tdp_mmu_next_root(_kvm, _root, _shared, false))		\
+	     _root = tdp_mmu_next_root(_kvm, _root, false))			\
 		if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) {		\
 		} else
 
@@ -891,7 +899,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 		 * the root must be reachable by mmu_notifiers while it's being
 		 * zapped
 		 */
-		kvm_tdp_mmu_put_root(kvm, root, true);
+		kvm_tdp_mmu_put_root(kvm, root);
 	}
 
 	read_unlock(&kvm->mmu_lock);
@@ -1500,7 +1508,7 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm,
 	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) {
 		r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared);
 		if (r) {
-			kvm_tdp_mmu_put_root(kvm, root, shared);
+			kvm_tdp_mmu_put_root(kvm, root);
 			break;
 		}
 	}
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 733a3aef3a96e..20d97aa46c490 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -17,8 +17,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
 	return refcount_inc_not_zero(&root->tdp_mmu_root_count);
 }
 
-void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
-			  bool shared);
+void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root);
 
 bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
 bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
-- 
GitLab


From 484dd27c0602e01cb49db362ad42b95e70912d43 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sat, 25 Nov 2023 03:33:58 -0500
Subject: [PATCH 0650/4076] KVM: x86/mmu: remove unnecessary "bool shared"
 argument from iterators

The "bool shared" argument is more or less unnecessary in the
for_each_*_tdp_mmu_root_yield_safe() macros.  Many users check for
the lock before calling it; all of them either call small functions
that do the check, or end up calling tdp_mmu_set_spte_atomic() and
tdp_mmu_iter_set_spte().  Add a few assertions to make up for the
lost check in for_each_*_tdp_mmu_root_yield_safe(), but even this
is probably overkill and mostly for documentation reasons.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20231125083400.1399197-3-pbonzini@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 48 ++++++++++++++++++--------------------
 1 file changed, 23 insertions(+), 25 deletions(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 8cd805fa15164..c6dc09acea12a 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -155,23 +155,20 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
  * If shared is set, this function is operating under the MMU lock in read
  * mode.
  */
-#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid);		\
-	     _root;								\
-	     _root = tdp_mmu_next_root(_kvm, _root, _only_valid))		\
-		if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) &&		\
-		    kvm_mmu_page_as_id(_root) != _as_id) {			\
+#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid);	\
+	     ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root;	\
+	     _root = tdp_mmu_next_root(_kvm, _root, _only_valid))	\
+		if (kvm_mmu_page_as_id(_root) != _as_id) {		\
 		} else
 
-#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared)	\
-	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
+#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id)	\
+	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true)
 
-#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared)			\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, false);			\
-	     _root;								\
-	     _root = tdp_mmu_next_root(_kvm, _root, false))			\
-		if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) {		\
-		} else
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root)			\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, false);		\
+	     ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root;	\
+	     _root = tdp_mmu_next_root(_kvm, _root, false))
 
 /*
  * Iterate over all TDP MMU roots.  Requires that mmu_lock be held for write,
@@ -840,7 +837,8 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush)
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	for_each_tdp_mmu_root_yield_safe(kvm, root)
 		flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush);
 
 	return flush;
@@ -862,7 +860,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 	 * is being destroyed or the userspace VMM has exited.  In both cases,
 	 * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
 	 */
-	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	for_each_tdp_mmu_root_yield_safe(kvm, root)
 		tdp_mmu_zap_root(kvm, root, false);
 }
 
@@ -876,7 +875,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 
 	read_lock(&kvm->mmu_lock);
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		if (!root->tdp_mmu_scheduled_root_to_zap)
 			continue;
 
@@ -1133,7 +1132,7 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 {
 	struct kvm_mmu_page *root;
 
-	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false)
+	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false)
 		flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end,
 					  range->may_block, flush);
 
@@ -1322,7 +1321,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
-	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id)
 		spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
 			     slot->base_gfn + slot->npages, min_level);
 
@@ -1354,6 +1353,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm,
 {
 	struct kvm_mmu_page *sp;
 
+	kvm_lockdep_assert_mmu_lock_held(kvm, shared);
+
 	/*
 	 * Since we are allocating while under the MMU lock we have to be
 	 * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct
@@ -1504,8 +1505,7 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm,
 	int r = 0;
 
 	kvm_lockdep_assert_mmu_lock_held(kvm, shared);
-
-	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) {
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) {
 		r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared);
 		if (r) {
 			kvm_tdp_mmu_put_root(kvm, root);
@@ -1569,8 +1569,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
 	bool spte_set = false;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
-
-	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id)
 		spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
 				slot->base_gfn + slot->npages);
 
@@ -1704,8 +1703,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	struct kvm_mmu_page *root;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
-
-	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id)
 		zap_collapsible_spte_range(kvm, root, slot);
 }
 
-- 
GitLab


From 250ce1b4d21a94f910c3df5141ff6434ea92524e Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sat, 25 Nov 2023 03:33:59 -0500
Subject: [PATCH 0651/4076] KVM: x86/mmu: always take tdp_mmu_pages_lock

It is cheap to take tdp_mmu_pages_lock in all write-side critical sections.
We already do it all the time when zapping with read_lock(), so it is not
a problem to do it from the kvm_tdp_mmu_zap_all() path (aka
kvm_arch_flush_shadow_all(), aka VM destruction and MMU notifier release).

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20231125083400.1399197-4-pbonzini@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 Documentation/virt/kvm/locking.rst |  7 +++----
 arch/x86/include/asm/kvm_host.h    | 11 ++++++-----
 arch/x86/kvm/mmu/tdp_mmu.c         | 24 ++++--------------------
 3 files changed, 13 insertions(+), 29 deletions(-)

diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index 3a034db5e55f8..02880d5552d5f 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -43,10 +43,9 @@ On x86:
 
 - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock
 
-- kvm->arch.mmu_lock is an rwlock.  kvm->arch.tdp_mmu_pages_lock and
-  kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and
-  cannot be taken without already holding kvm->arch.mmu_lock (typically with
-  ``read_lock`` for the TDP MMU, thus the need for additional spinlocks).
+- kvm->arch.mmu_lock is an rwlock; critical sections for
+  kvm->arch.tdp_mmu_pages_lock and kvm->arch.mmu_unsync_pages_lock must
+  also take kvm->arch.mmu_lock
 
 Everything else is a leaf: no other lock is taken inside the critical
 sections.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a565a2e70f30f..414691169a046 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1407,9 +1407,8 @@ struct kvm_arch {
 	 *	the MMU lock in read mode + RCU or
 	 *	the MMU lock in write mode
 	 *
-	 * For writes, this list is protected by:
-	 *	the MMU lock in read mode + the tdp_mmu_pages_lock or
-	 *	the MMU lock in write mode
+	 * For writes, this list is protected by tdp_mmu_pages_lock; see
+	 * below for the details.
 	 *
 	 * Roots will remain in the list until their tdp_mmu_root_count
 	 * drops to zero, at which point the thread that decremented the
@@ -1426,8 +1425,10 @@ struct kvm_arch {
 	 *  - possible_nx_huge_pages;
 	 *  - the possible_nx_huge_page_link field of kvm_mmu_page structs used
 	 *    by the TDP MMU
-	 * It is acceptable, but not necessary, to acquire this lock when
-	 * the thread holds the MMU lock in write mode.
+	 * Because the lock is only taken within the MMU lock, strictly
+	 * speaking it is redundant to acquire this lock when the thread
+	 * holds the MMU lock in write mode.  However it often simplifies
+	 * the code to do so.
 	 */
 	spinlock_t tdp_mmu_pages_lock;
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index c6dc09acea12a..6ae19b4ee5b1c 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -75,12 +75,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
 
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
-	/*
-	 * Either read or write is okay, but mmu_lock must be held because
-	 * writers are not required to take tdp_mmu_pages_lock.
-	 */
-	lockdep_assert_held(&kvm->mmu_lock);
-
 	if (!refcount_dec_and_test(&root->tdp_mmu_root_count))
 		return;
 
@@ -281,28 +275,18 @@ static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
  *
  * @kvm: kvm instance
  * @sp: the page to be removed
- * @shared: This operation may not be running under the exclusive use of
- *	    the MMU lock and the operation must synchronize with other
- *	    threads that might be adding or removing pages.
  */
-static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
-			      bool shared)
+static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	tdp_unaccount_mmu_page(kvm, sp);
 
 	if (!sp->nx_huge_page_disallowed)
 		return;
 
-	if (shared)
-		spin_lock(&kvm->arch.tdp_mmu_pages_lock);
-	else
-		lockdep_assert_held_write(&kvm->mmu_lock);
-
+	spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	sp->nx_huge_page_disallowed = false;
 	untrack_possible_nx_huge_page(kvm, sp);
-
-	if (shared)
-		spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+	spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
 }
 
 /**
@@ -331,7 +315,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
 
 	trace_kvm_mmu_prepare_zap_page(sp);
 
-	tdp_mmu_unlink_sp(kvm, sp, shared);
+	tdp_mmu_unlink_sp(kvm, sp);
 
 	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
 		tdp_ptep_t sptep = pt + i;
-- 
GitLab


From e59f75de4e501e87de7743fec29dd247a6ae6cd3 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sat, 25 Nov 2023 03:34:00 -0500
Subject: [PATCH 0652/4076] KVM: x86/mmu: fix comment about
 mmu_unsync_pages_lock

Fix the comment about what can and cannot happen when mmu_unsync_pages_lock
is not help.  The comment correctly mentions "clearing sp->unsync", but then
it talks about unsync going from 0 to 1.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20231125083400.1399197-5-pbonzini@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ace9f7c131322..3fec3f6cdd53a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2850,9 +2850,9 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 			/*
 			 * Recheck after taking the spinlock, a different vCPU
 			 * may have since marked the page unsync.  A false
-			 * positive on the unprotected check above is not
+			 * negative on the unprotected check above is not
 			 * possible as clearing sp->unsync _must_ hold mmu_lock
-			 * for write, i.e. unsync cannot transition from 0->1
+			 * for write, i.e. unsync cannot transition from 1->0
 			 * while this CPU holds mmu_lock for read (or write).
 			 */
 			if (READ_ONCE(sp->unsync))
-- 
GitLab


From 8c4976772d9b5858b8b456e84783e089c6cfa66e Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Thu, 2 Nov 2023 19:15:25 +0100
Subject: [PATCH 0653/4076] KVM: s390: Harden copying of userspace-array
 against overflow

guestdbg.c utilizes memdup_user() to copy a userspace array. This,
currently, does not check for an overflow.

Use the new wrapper memdup_array_user() to copy the array more safely.

Note, KVM explicitly checks the number of entries before duplicating the
array, i.e. adding the overflow check should be a glorified nop.

Suggested-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Acked-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Link: https://lore.kernel.org/r/20231102181526.43279-3-pstanner@redhat.com
[sean: call out that KVM pre-checks the number of entries]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/s390/kvm/guestdbg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 3765c4223bf94..80879fc73c900 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -213,8 +213,8 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
 	else if (dbg->arch.nr_hw_bp > MAX_BP_COUNT)
 		return -EINVAL;
 
-	bp_data = memdup_user(dbg->arch.hw_bp,
-			      sizeof(*bp_data) * dbg->arch.nr_hw_bp);
+	bp_data = memdup_array_user(dbg->arch.hw_bp, dbg->arch.nr_hw_bp,
+				    sizeof(*bp_data));
 	if (IS_ERR(bp_data))
 		return PTR_ERR(bp_data);
 
-- 
GitLab


From 1f829359c8c37f77a340575957686ca8c4bca317 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Thu, 2 Nov 2023 19:15:26 +0100
Subject: [PATCH 0654/4076] KVM: Harden copying of userspace-array against
 overflow

kvm_main.c utilizes vmemdup_user() and array_size() to copy a userspace
array. Currently, this does not check for an overflow.

Use the new wrapper vmemdup_array_user() to copy the array more safely.

Note, KVM explicitly checks the number of entries before duplicating the
array, i.e. adding the overflow check should be a glorified nop.

Suggested-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Link: https://lore.kernel.org/r/20231102181526.43279-4-pstanner@redhat.com
[sean: call out that KVM pre-checks the number of entries]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 virt/kvm/kvm_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b744eddecbc07..e76d49daa4701 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5262,9 +5262,8 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 		if (routing.nr) {
 			urouting = argp;
-			entries = vmemdup_user(urouting->entries,
-					       array_size(sizeof(*entries),
-							  routing.nr));
+			entries = vmemdup_array_user(urouting->entries,
+						     routing.nr, sizeof(*entries));
 			if (IS_ERR(entries)) {
 				r = PTR_ERR(entries);
 				goto out;
-- 
GitLab


From 1af3bf2befc07c7198100949dd1bece02a7dbded Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 29 Nov 2023 14:49:13 -0800
Subject: [PATCH 0655/4076] KVM: selftests: Fix MWAIT error message when guest
 assertion fails

Print out the test and vector as intended when a guest assert fails an
assertion regarding MONITOR/MWAIT faulting.  Unfortunately, the guest
printf support doesn't detect such issues at compile-time, so the bug
manifests as a confusing error message, e.g. in the most confusing case,
the test complains that it got vector "0" instead of expected vector "0".

Fixes: 0f52e4aaa614 ("KVM: selftests: Convert the MONITOR/MWAIT test to use printf guest asserts")
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20231107182159.404770-1-seanjc@google.com
Link: https://lore.kernel.org/r/20231129224916.532431-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
index 80aa3d8b18f80..853802641e1ea 100644
--- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
@@ -27,10 +27,12 @@ do {									\
 									\
 	if (fault_wanted)						\
 		__GUEST_ASSERT((vector) == UD_VECTOR,			\
-			       "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", vector); \
+			       "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", \
+			       testcase, vector);			\
 	else								\
 		__GUEST_ASSERT(!(vector),				\
-			       "Expected success on " insn " for testcase '0x%x', got '0x%x'", vector); \
+			       "Expected success on " insn " for testcase '0x%x', got '0x%x'", \
+			       testcase, vector);			\
 } while (0)
 
 static void guest_monitor_wait(int testcase)
-- 
GitLab


From 4d53dcc5d0bc2c445e29cb14df6d2cf93091731f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 29 Nov 2023 14:49:14 -0800
Subject: [PATCH 0656/4076] KVM: selftests: Fix benign %llx vs. %lx issues in
 guest asserts

Convert %llx to %lx as appropriate in guest asserts.  The guest printf
implementation treats them the same as KVM selftests are 64-bit only, but
strictly adhering to the correct format will allow annotating the
underlying helpers with __printf() without introducing new warnings in the
build.

Link: https://lore.kernel.org/r/20231129224916.532431-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/set_memory_region_test.c      | 6 +++---
 tools/testing/selftests/kvm/x86_64/hyperv_features.c      | 2 +-
 .../selftests/kvm/x86_64/private_mem_conversions_test.c   | 2 +-
 .../selftests/kvm/x86_64/svm_nested_soft_inject_test.c    | 4 ++--
 tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c    | 2 +-
 tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c      | 8 ++++----
 6 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 6637a0845acf0..03ec7efd19aa8 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -157,17 +157,17 @@ static void guest_code_move_memory_region(void)
 	 */
 	val = guest_spin_on_val(0);
 	__GUEST_ASSERT(val == 1 || val == MMIO_VAL,
-		       "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val);
+		       "Expected '1' or MMIO ('%lx'), got '%lx'", MMIO_VAL, val);
 
 	/* Spin until the misaligning memory region move completes. */
 	val = guest_spin_on_val(MMIO_VAL);
 	__GUEST_ASSERT(val == 1 || val == 0,
-		       "Expected '0' or '1' (no MMIO), got '%llx'", val);
+		       "Expected '0' or '1' (no MMIO), got '%lx'", val);
 
 	/* Spin until the memory region starts to get re-aligned. */
 	val = guest_spin_on_val(0);
 	__GUEST_ASSERT(val == 1 || val == MMIO_VAL,
-		       "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val);
+		       "Expected '1' or MMIO ('%lx'), got '%lx'", MMIO_VAL, val);
 
 	/* Spin until the re-aligning memory region move completes. */
 	val = guest_spin_on_val(MMIO_VAL);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 9f28aa276c4e2..4bb63b6ee4a0c 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -66,7 +66,7 @@ static void guest_msr(struct msr_data *msr)
 
 	if (msr->write)
 		__GUEST_ASSERT(!vector,
-			       "WRMSR(0x%x) to '0x%llx', RDMSR read '0x%llx'",
+			       "WRMSR(0x%x) to '0x%lx', RDMSR read '0x%lx'",
 			       msr->idx, msr->write_val, msr_val);
 
 	/* Invariant TSC bit appears when TSC invariant control MSR is written to */
diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
index 4d6a37a5d8965..65ad38b6be1f1 100644
--- a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
+++ b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
@@ -35,7 +35,7 @@ do {												\
 												\
 	for (i = 0; i < size; i++)								\
 		__GUEST_ASSERT(mem[i] == pattern,						\
-			       "Guest expected 0x%x at offset %lu (gpa 0x%llx), got 0x%x",	\
+			       "Guest expected 0x%x at offset %lu (gpa 0x%lx), got 0x%x",	\
 			       pattern, i, gpa + i, mem[i]);					\
 } while (0)
 
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
index 7ee44496cf97f..0c7ce3d4e83a6 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
@@ -103,7 +103,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 
 	run_guest(vmcb, svm->vmcb_gpa);
 	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL,
-		       "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'",
+		       "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'",
 		       vmcb->control.exit_code,
 		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
 
@@ -133,7 +133,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i
 
 	run_guest(vmcb, svm->vmcb_gpa);
 	__GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_HLT,
-		       "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'",
+		       "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'",
 		       vmcb->control.exit_code,
 		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
 
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
index ebbcb0a3f7438..2a8d4ac2f0204 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
@@ -56,7 +56,7 @@ static void guest_test_perf_capabilities_gp(uint64_t val)
 	uint8_t vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val);
 
 	__GUEST_ASSERT(vector == GP_VECTOR,
-		       "Expected #GP for value '0x%llx', got vector '0x%x'",
+		       "Expected #GP for value '0x%lx', got vector '0x%x'",
 		       val, vector);
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
index 77d04a7bdaddd..dc6217440db3a 100644
--- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
@@ -25,7 +25,7 @@ do {											\
 											\
 	__GUEST_ASSERT((__supported & (xfeatures)) != (xfeatures) ||			\
 		       __supported == ((xfeatures) | (dependencies)),			\
-		       "supported = 0x%llx, xfeatures = 0x%llx, dependencies = 0x%llx",	\
+		       "supported = 0x%lx, xfeatures = 0x%llx, dependencies = 0x%llx",	\
 		       __supported, (xfeatures), (dependencies));			\
 } while (0)
 
@@ -42,7 +42,7 @@ do {									\
 	uint64_t __supported = (supported_xcr0) & (xfeatures);		\
 									\
 	__GUEST_ASSERT(!__supported || __supported == (xfeatures),	\
-		       "supported = 0x%llx, xfeatures = 0x%llx",	\
+		       "supported = 0x%lx, xfeatures = 0x%llx",		\
 		       __supported, (xfeatures));			\
 } while (0)
 
@@ -81,7 +81,7 @@ static void guest_code(void)
 
 	vector = xsetbv_safe(0, supported_xcr0);
 	__GUEST_ASSERT(!vector,
-		       "Expected success on XSETBV(0x%llx), got vector '0x%x'",
+		       "Expected success on XSETBV(0x%lx), got vector '0x%x'",
 		       supported_xcr0, vector);
 
 	for (i = 0; i < 64; i++) {
@@ -90,7 +90,7 @@ static void guest_code(void)
 
 		vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i));
 		__GUEST_ASSERT(vector == GP_VECTOR,
-			       "Expected #GP on XSETBV(0x%llx), supported XCR0 = %llx, got vector '0x%x'",
+			       "Expected #GP on XSETBV(0x%llx), supported XCR0 = %lx, got vector '0x%x'",
 			       BIT_ULL(i), supported_xcr0, vector);
 	}
 
-- 
GitLab


From f813e6d41baf2bbdd1624f9f01ac4f365eb78891 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 29 Nov 2023 14:49:15 -0800
Subject: [PATCH 0657/4076] KVM: selftests: Fix broken assert messages in
 Hyper-V features test

Swap the ordering of parameters to guest asserts related to {RD,WR}MSR
success/failure in the Hyper-V features test.  As is, the output will
be mangled and broken due to passing an integer as a string and vice
versa.

Opportunistically fix a benign %u vs. %lu issue as well.

Link: https://lore.kernel.org/r/20231129224916.532431-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/hyperv_features.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 4bb63b6ee4a0c..29f6bdbce817e 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -55,11 +55,11 @@ static void guest_msr(struct msr_data *msr)
 	if (msr->fault_expected)
 		__GUEST_ASSERT(vector == GP_VECTOR,
 			       "Expected #GP on %sMSR(0x%x), got vector '0x%x'",
-			       msr->idx, msr->write ? "WR" : "RD", vector);
+			       msr->write ? "WR" : "RD", msr->idx, vector);
 	else
 		__GUEST_ASSERT(!vector,
 			       "Expected success on %sMSR(0x%x), got vector '0x%x'",
-			       msr->idx, msr->write ? "WR" : "RD", vector);
+			       msr->write ? "WR" : "RD", msr->idx, vector);
 
 	if (vector || is_write_only_msr(msr->idx))
 		goto done;
@@ -102,11 +102,11 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
 	vector = __hyperv_hypercall(hcall->control, input, output, &res);
 	if (hcall->ud_expected) {
 		__GUEST_ASSERT(vector == UD_VECTOR,
-			       "Expected #UD for control '%u', got vector '0x%x'",
+			       "Expected #UD for control '%lu', got vector '0x%x'",
 			       hcall->control, vector);
 	} else {
 		__GUEST_ASSERT(!vector,
-			       "Expected no exception for control '%u', got vector '0x%x'",
+			       "Expected no exception for control '%lu', got vector '0x%x'",
 			       hcall->control, vector);
 		GUEST_ASSERT_EQ(res, hcall->expect);
 	}
-- 
GitLab


From 1b2658e4c709135fe1910423d3216632f641baf9 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 29 Nov 2023 14:49:16 -0800
Subject: [PATCH 0658/4076] KVM: selftests: Annotate guest ucall, printf, and
 assert helpers with __printf()

Annotate guest printf helpers with __printf() so that the compiler will
warn about incorrect formatting at compile time (see git log for how easy
it is to screw up with the formatting).

Suggested-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20231129224916.532431-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/test_util.h    | 2 +-
 tools/testing/selftests/kvm/include/ucall_common.h | 7 ++++---
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index a0c7dd3a5b300..71a41fa924b7d 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -191,7 +191,7 @@ static inline uint32_t atoi_non_negative(const char *name, const char *num_str)
 }
 
 int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args);
-int guest_snprintf(char *buf, int n, const char *fmt, ...);
+__printf(3, 4) int guest_snprintf(char *buf, int n, const char *fmt, ...);
 
 char *strdup_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2), nonnull(1)));
 
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index 0fb472a5a0585..d9d6581b8d4f2 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -34,9 +34,10 @@ void ucall_arch_do_ucall(vm_vaddr_t uc);
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu);
 
 void ucall(uint64_t cmd, int nargs, ...);
-void ucall_fmt(uint64_t cmd, const char *fmt, ...);
-void ucall_assert(uint64_t cmd, const char *exp, const char *file,
-		  unsigned int line, const char *fmt, ...);
+__printf(2, 3) void ucall_fmt(uint64_t cmd, const char *fmt, ...);
+__printf(5, 6) void ucall_assert(uint64_t cmd, const char *exp,
+				 const char *file, unsigned int line,
+				 const char *fmt, ...);
 uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc);
 void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
 int ucall_nr_pages_required(uint64_t page_size);
-- 
GitLab


From 197e0da1f1a3445b9b266f83d5d037b4709dae2e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 24 Nov 2023 11:09:13 +0200
Subject: [PATCH 0659/4076] x86/pci: Use PCI_HEADER_TYPE_* instead of literals
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace 0x7f and 0x80 literals with PCI_HEADER_TYPE_* defines.

Link: https://lore.kernel.org/r/20231124090919.23687-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/kernel/aperture_64.c  | 3 +--
 arch/x86/kernel/early-quirks.c | 4 ++--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 4feaa670d5783..89c0c8a3fc7e6 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -259,10 +259,9 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 							order);
 				}
 
-				/* No multi-function device? */
 				type = read_pci_config_byte(bus, slot, func,
 							       PCI_HEADER_TYPE);
-				if (!(type & 0x80))
+				if (!(type & PCI_HEADER_TYPE_MFD))
 					break;
 			}
 		}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index a6c1867fc7aa3..59f4aefc6bc16 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -779,13 +779,13 @@ static int __init check_dev_quirk(int num, int slot, int func)
 	type = read_pci_config_byte(num, slot, func,
 				    PCI_HEADER_TYPE);
 
-	if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) {
+	if ((type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) {
 		sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS);
 		if (sec > num)
 			early_pci_scan_bus(sec);
 	}
 
-	if (!(type & 0x80))
+	if (!(type & PCI_HEADER_TYPE_MFD))
 		return -1;
 
 	return 0;
-- 
GitLab


From 3773343dd8906118fa0bbfd4c84051122da49e99 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 24 Nov 2023 11:09:14 +0200
Subject: [PATCH 0660/4076] powerpc/fsl-pci: Use PCI_HEADER_TYPE_MASK instead
 of literal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace 0x7f literals with PCI_HEADER_TYPE_MASK.

Link: https://lore.kernel.org/r/20231124090919.23687-2-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/powerpc/sysdev/fsl_pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 3868483fbe292..ef7707ea0db7b 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -54,7 +54,7 @@ static void quirk_fsl_pcie_early(struct pci_dev *dev)
 
 	/* if we aren't in host mode don't bother */
 	pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type);
-	if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
+	if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE)
 		return;
 
 	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
@@ -581,7 +581,7 @@ static int fsl_add_bridge(struct platform_device *pdev, int is_primary)
 		hose->ops = &fsl_indirect_pcie_ops;
 		/* For PCIE read HEADER_TYPE to identify controller mode */
 		early_read_config_byte(hose, 0, 0, PCI_HEADER_TYPE, &hdr_type);
-		if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
+		if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE)
 			goto no_bridge;
 
 	} else {
-- 
GitLab


From 420ac76610d76b09aebc0bfc722c7af9c6daf36a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 24 Nov 2023 11:09:16 +0200
Subject: [PATCH 0661/4076] scsi: lpfc: Use PCI_HEADER_TYPE_MFD instead of
 literal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace literal 0x80 with PCI_HEADER_TYPE_MFD.

Link: https://lore.kernel.org/r/20231124090919.23687-4-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/scsi/lpfc/lpfc_sli.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 9386e7b447506..4ac6afd3c2fe9 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -4875,7 +4875,7 @@ void lpfc_reset_barrier(struct lpfc_hba *phba)
 	lockdep_assert_held(&phba->hbalock);
 
 	pci_read_config_byte(phba->pcidev, PCI_HEADER_TYPE, &hdrtype);
-	if (hdrtype != 0x80 ||
+	if (hdrtype != PCI_HEADER_TYPE_MFD ||
 	    (FC_JEDEC_ID(phba->vpd.rev.biuRev) != HELIOS_JEDEC_ID &&
 	     FC_JEDEC_ID(phba->vpd.rev.biuRev) != THOR_JEDEC_ID))
 		return;
-- 
GitLab


From 0d481ff35c9a85d775e5544bb2e331e7d5eb6c3c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 24 Nov 2023 10:59:24 +0200
Subject: [PATCH 0662/4076] x86/pci: Clean up open-coded PCIBIOS return code
 mangling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Per PCI Firmware spec r3.3, sec 2.5.2, 2.6.2, and 2.7, the return code for
these PCI BIOS interfaces is in 8 bits of the EAX register.  Previously it
was extracted by open-coded masks and shifting.

Name the return code bits with a #define and add pcibios_get_return_code()
to extract the return code to improve code readability. In addition,
replace zero test with PCIBIOS_SUCCESSFUL.

No functional changes intended.

Link: https://lore.kernel.org/r/20231124085924.13830-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/pcbios.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 4f15280732edb..244c643bb0b5f 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -3,6 +3,8 @@
  * BIOS32 and PCI BIOS handling.
  */
 
+#include <linux/bits.h>
+#include <linux/bitfield.h>
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -29,8 +31,19 @@
 #define PCIBIOS_HW_TYPE1_SPEC		0x10
 #define PCIBIOS_HW_TYPE2_SPEC		0x20
 
+/*
+ * Returned in EAX:
+ * - AH: return code
+ */
+#define PCIBIOS_RETURN_CODE			GENMASK(15, 8)
+
 int pcibios_enabled;
 
+static u8 pcibios_get_return_code(u32 eax)
+{
+	return FIELD_GET(PCIBIOS_RETURN_CODE, eax);
+}
+
 /* According to the BIOS specification at:
  * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could
  * restrict the x zone to some pages and make it ro. But this may be
@@ -154,7 +167,7 @@ static int __init check_pcibios(void)
 			: "memory");
 		local_irq_restore(flags);
 
-		status = (eax >> 8) & 0xff;
+		status = pcibios_get_return_code(eax);
 		hw_mech = eax & 0xff;
 		major_ver = (ebx >> 8) & 0xff;
 		minor_ver = ebx & 0xff;
@@ -227,7 +240,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus,
 
 	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
 
-	return (int)((result & 0xff00) >> 8);
+	return pcibios_get_return_code(result);
 }
 
 static int pci_bios_write(unsigned int seg, unsigned int bus,
@@ -269,7 +282,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus,
 
 	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
 
-	return (int)((result & 0xff00) >> 8);
+	return pcibios_get_return_code(result);
 }
 
 
@@ -385,9 +398,10 @@ struct irq_routing_table * pcibios_get_irq_routing_table(void)
 		  "m" (opt)
 		: "memory");
 	DBG("OK  ret=%d, size=%d, map=%x\n", ret, opt.size, map);
-	if (ret & 0xff00)
-		printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", (ret >> 8) & 0xff);
-	else if (opt.size) {
+	ret = pcibios_get_return_code(ret);
+	if (ret) {
+		printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", ret);
+	} else if (opt.size) {
 		rt = kmalloc(sizeof(struct irq_routing_table) + opt.size, GFP_KERNEL);
 		if (rt) {
 			memset(rt, 0, sizeof(struct irq_routing_table));
@@ -415,7 +429,7 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq)
 		  "b" ((dev->bus->number << 8) | dev->devfn),
 		  "c" ((irq << 8) | (pin + 10)),
 		  "S" (&pci_indirect));
-	return !(ret & 0xff00);
+	return pcibios_get_return_code(ret) == PCIBIOS_SUCCESSFUL;
 }
 EXPORT_SYMBOL(pcibios_set_irq_routing);
 
-- 
GitLab


From 92ef432f027cffe0ff91ff2cbe9258d89ca53968 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Thu, 23 Nov 2023 18:05:40 +0900
Subject: [PATCH 0663/4076] kbuild: support W=c and W=e shorthands for Kconfig

KCONFIG_WARN_UNKNOWN_SYMBOLS=1 and KCONFIG_WERROR=1 are descriptive
and suitable in scripting, but typing them from the command line can
be tedious.

Associate them with KBUILD_EXTRA_WARN (and the W= shorthand).

Support a new letter 'c' to enable extra checks in Kconfig. You can
still manage compiler warnings (W=1) and Kconfig warnings (W=c)
independently.

Reuse the letter 'e' to turn Kconfig warnings into errors.

As usual, you can combine multiple letters in KCONFIG_EXTRA_WARN.

  $ KCONFIG_WARN_UNKNOWN_SYMBOLS=1 KCONFIG_WERROR=1 make defconfig

can be shortened to:

  $ KBUILD_EXTRA_WARN=ce make defconfig

or, even shorter:

  $ make W=ce defconfig

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
---
 Makefile                   | 10 ++++++++++
 scripts/Makefile.extrawarn |  9 ---------
 scripts/kconfig/Makefile   |  8 ++++++++
 3 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/Makefile b/Makefile
index 0df7372175294..5a11804af640a 100644
--- a/Makefile
+++ b/Makefile
@@ -155,6 +155,15 @@ endif
 
 export KBUILD_EXTMOD
 
+# backward compatibility
+KBUILD_EXTRA_WARN ?= $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)
+
+ifeq ("$(origin W)", "command line")
+  KBUILD_EXTRA_WARN := $(W)
+endif
+
+export KBUILD_EXTRA_WARN
+
 # Kbuild will save output files in the current working directory.
 # This does not need to match to the root of the kernel source tree.
 #
@@ -1659,6 +1668,7 @@ help:
 	@echo  '		1: warnings which may be relevant and do not occur too often'
 	@echo  '		2: warnings which occur quite often but may still be relevant'
 	@echo  '		3: more obscure warnings, can most likely be ignored'
+	@echo  '		c: extra checks in the configuration stage (Kconfig)'
 	@echo  '		e: warnings are being treated as errors'
 	@echo  '		Multiple levels can be combined with W=12 or W=123'
 	@$(if $(dtstree), \
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 2fe6f2828d376..3f94915fab372 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -80,15 +80,6 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init)
 # Warn if there is an enum types mismatch
 KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion)
 
-# backward compatibility
-KBUILD_EXTRA_WARN ?= $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)
-
-ifeq ("$(origin W)", "command line")
-  KBUILD_EXTRA_WARN := $(W)
-endif
-
-export KBUILD_EXTRA_WARN
-
 #
 # W=1 - warnings which may be relevant and do not occur too often
 #
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 4eee155121a8b..322c061b464d2 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -27,6 +27,14 @@ KCONFIG_DEFCONFIG_LIST += \
 endif
 KCONFIG_DEFCONFIG_LIST += arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG)
 
+ifneq ($(findstring c, $(KBUILD_EXTRA_WARN)),)
+export KCONFIG_WARN_UNKNOWN_SYMBOLS=1
+endif
+
+ifneq ($(findstring e, $(KBUILD_EXTRA_WARN)),)
+export KCONFIG_WERROR=1
+endif
+
 # We need this, in case the user has it in its environment
 unexport CONFIG_
 
-- 
GitLab


From 0df8e97085946dd79c06720678a845778b6d6bf8 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Fri, 24 Nov 2023 23:09:08 +0900
Subject: [PATCH 0664/4076] scripts: clean up IA-64 code

A little more janitorial work after commit cf8e8658100d ("arch: Remove
Itanium (IA-64) architecture").

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
---
 scripts/checkstack.pl        |  3 ---
 scripts/gdb/linux/tasks.py   | 15 +++------------
 scripts/head-object-list.txt |  1 -
 scripts/kconfig/mconf.c      |  2 +-
 scripts/kconfig/nconf.c      |  2 +-
 scripts/package/kernel.spec  |  6 ------
 scripts/package/mkdebian     |  2 +-
 scripts/recordmcount.c       |  1 -
 scripts/recordmcount.pl      |  7 -------
 scripts/xz_wrap.sh           |  1 -
 10 files changed, 6 insertions(+), 34 deletions(-)

diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl
index d83ba5d8f3f49..5995dd11a5a6e 100755
--- a/scripts/checkstack.pl
+++ b/scripts/checkstack.pl
@@ -68,9 +68,6 @@ my (@stack, $re, $dre, $sub, $x, $xs, $funcre, $min_stack);
 		#    2f60:    48 81 ec e8 05 00 00       sub    $0x5e8,%rsp
 		$re = qr/^.*[as][du][db]    \$(0x$x{1,8}),\%(e|r)sp$/o;
 		$dre = qr/^.*[as][du][db]    (%.*),\%(e|r)sp$/o;
-	} elsif ($arch eq 'ia64') {
-		#e0000000044011fc:       01 0f fc 8c     adds r12=-384,r12
-		$re = qr/.*adds.*r12=-(([0-9]{2}|[3-9])[0-9]{2}),r12/o;
 	} elsif ($arch eq 'm68k') {
 		#    2b6c:       4e56 fb70       linkw %fp,#-1168
 		#  1df770:       defc ffe4       addaw #-28,%sp
diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py
index 17ec19e9b5bf6..5be53b372a693 100644
--- a/scripts/gdb/linux/tasks.py
+++ b/scripts/gdb/linux/tasks.py
@@ -86,21 +86,12 @@ LxPs()
 
 thread_info_type = utils.CachedType("struct thread_info")
 
-ia64_task_size = None
-
 
 def get_thread_info(task):
     thread_info_ptr_type = thread_info_type.get_type().pointer()
-    if utils.is_target_arch("ia64"):
-        global ia64_task_size
-        if ia64_task_size is None:
-            ia64_task_size = gdb.parse_and_eval("sizeof(struct task_struct)")
-        thread_info_addr = task.address + ia64_task_size
-        thread_info = thread_info_addr.cast(thread_info_ptr_type)
-    else:
-        if task.type.fields()[0].type == thread_info_type.get_type():
-            return task['thread_info']
-        thread_info = task['stack'].cast(thread_info_ptr_type)
+    if task.type.fields()[0].type == thread_info_type.get_type():
+        return task['thread_info']
+    thread_info = task['stack'].cast(thread_info_ptr_type)
     return thread_info.dereference()
 
 
diff --git a/scripts/head-object-list.txt b/scripts/head-object-list.txt
index 26359968744ef..890f69005bab4 100644
--- a/scripts/head-object-list.txt
+++ b/scripts/head-object-list.txt
@@ -17,7 +17,6 @@ arch/arm/kernel/head-nommu.o
 arch/arm/kernel/head.o
 arch/csky/kernel/head.o
 arch/hexagon/kernel/head.o
-arch/ia64/kernel/head.o
 arch/loongarch/kernel/head.o
 arch/m68k/68000/head.o
 arch/m68k/coldfire/head.o
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index eccc87a441e71..3795c36a9181a 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -247,7 +247,7 @@ search_help[] =
 	"      -> PCI support (PCI [=y])\n"
 	"(1)     -> PCI access mode (<choice> [=y])\n"
 	"  Defined at drivers/pci/Kconfig:47\n"
-	"  Depends on: X86_LOCAL_APIC && X86_IO_APIC || IA64\n"
+	"  Depends on: X86_LOCAL_APIC && X86_IO_APIC\n"
 	"  Selects: LIBCRC32\n"
 	"  Selected by: BAR [=n]\n"
 	"-----------------------------------------------------------------\n"
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index 143a2c351d576..8cd72fe259740 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -216,7 +216,7 @@ search_help[] =
 "Symbol: FOO [ = m]\n"
 "Prompt: Foo bus is used to drive the bar HW\n"
 "Defined at drivers/pci/Kconfig:47\n"
-"Depends on: X86_LOCAL_APIC && X86_IO_APIC || IA64\n"
+"Depends on: X86_LOCAL_APIC && X86_IO_APIC\n"
 "Location:\n"
 "  -> Bus options (PCI, PCMCIA, EISA, ISA)\n"
 "    -> PCI support (PCI [ = y])\n"
diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
index 3eee0143e0c5c..89298983a1694 100644
--- a/scripts/package/kernel.spec
+++ b/scripts/package/kernel.spec
@@ -56,13 +56,7 @@ patch -p1 < %{SOURCE2}
 
 %install
 mkdir -p %{buildroot}/boot
-%ifarch ia64
-mkdir -p %{buildroot}/boot/efi
-cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/efi/vmlinuz-%{KERNELRELEASE}
-ln -s efi/vmlinuz-%{KERNELRELEASE} %{buildroot}/boot/
-%else
 cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/vmlinuz-%{KERNELRELEASE}
-%endif
 %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} modules_install
 %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
 cp System.map %{buildroot}/boot/System.map-%{KERNELRELEASE}
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 5044224cf6714..c1a36da85e84f 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -26,7 +26,7 @@ set_debarch() {
 
 	# Attempt to find the correct Debian architecture
 	case "$UTS_MACHINE" in
-	i386|ia64|alpha|m68k|riscv*)
+	i386|alpha|m68k|riscv*)
 		debarch="$UTS_MACHINE" ;;
 	x86_64)
 		debarch=amd64 ;;
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 40ae6b2c7a6da..3e4f54799cc0a 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -590,7 +590,6 @@ static int do_file(char const *const fname)
 		ideal_nop = ideal_nop4_arm64;
 		is_fake_mcount64 = arm64_is_fake_mcount;
 		break;
-	case EM_IA_64:	reltype = R_IA64_IMM64; break;
 	case EM_MIPS:	/* reltype: e_class    */ break;
 	case EM_LOONGARCH:	/* reltype: e_class    */ break;
 	case EM_PPC:	reltype = R_PPC_ADDR32; break;
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 6a4645a579760..f84df9e383fd0 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -275,13 +275,6 @@ if ($arch eq "x86_64") {
     $section_type = '%progbits';
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_AARCH64_CALL26\\s+_mcount\$";
     $type = ".quad";
-} elsif ($arch eq "ia64") {
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
-    $type = "data8";
-
-    if ($is_module eq "0") {
-	$cc .= " -mconstant-gp";
-    }
 } elsif ($arch eq "sparc64") {
     # In the objdump output there are giblets like:
     # 0000000000000000 <igmp_net_exit-0x18>:
diff --git a/scripts/xz_wrap.sh b/scripts/xz_wrap.sh
index 76e9cbcfbeab4..d06baf626abe7 100755
--- a/scripts/xz_wrap.sh
+++ b/scripts/xz_wrap.sh
@@ -15,7 +15,6 @@ LZMA2OPTS=
 case $SRCARCH in
 	x86)            BCJ=--x86 ;;
 	powerpc)        BCJ=--powerpc ;;
-	ia64)           BCJ=--ia64; LZMA2OPTS=pb=4 ;;
 	arm)            BCJ=--arm ;;
 	sparc)          BCJ=--sparc ;;
 esac
-- 
GitLab


From 4e244c10eab345a735c5052688e4a55bddce5bf7 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 26 Nov 2023 01:35:58 +0900
Subject: [PATCH 0665/4076] kconfig: remove unneeded symbol_empty variable

This is used only for initializing other variables.

Use the empty string "" directly.

Please note newval.tri is unused for S_INT/HEX/STRING.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/symbol.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index a76925b46ce63..f7075d148ac79 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -29,12 +29,6 @@ struct symbol symbol_no = {
 	.flags = SYMBOL_CONST|SYMBOL_VALID,
 };
 
-static struct symbol symbol_empty = {
-	.name = "",
-	.curr = { "", no },
-	.flags = SYMBOL_VALID,
-};
-
 struct symbol *modules_sym;
 static tristate modules_val;
 
@@ -346,7 +340,7 @@ void sym_calc_value(struct symbol *sym)
 	case S_INT:
 	case S_HEX:
 	case S_STRING:
-		newval = symbol_empty.curr;
+		newval.val = "";
 		break;
 	case S_BOOLEAN:
 	case S_TRISTATE:
@@ -697,13 +691,12 @@ const char *sym_get_string_default(struct symbol *sym)
 {
 	struct property *prop;
 	struct symbol *ds;
-	const char *str;
+	const char *str = "";
 	tristate val;
 
 	sym_calc_visibility(sym);
 	sym_calc_value(modules_sym);
 	val = symbol_no.curr.tri;
-	str = symbol_empty.curr.val;
 
 	/* If symbol has a default value look it up */
 	prop = sym_get_default_prop(sym);
-- 
GitLab


From 6262afa10ef7cc8fdf39b81a36f9546b68810431 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 26 Nov 2023 01:35:59 +0900
Subject: [PATCH 0666/4076] kconfig: default to zero if int/hex symbol lacks
 default property

When a default property is missing in an int or hex symbol, it defaults
to an empty string, which is not a valid symbol value.

It results in an incorrect .config, and can also lead to an infinite
loop in scripting.

Use "0" for int and "0x0" for hex as a default value.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Yoann Congal <yoann.congal@smile.fr>
---
 scripts/kconfig/symbol.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index f7075d148ac79..a5a4f9153eb73 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -338,7 +338,11 @@ void sym_calc_value(struct symbol *sym)
 
 	switch (sym->type) {
 	case S_INT:
+		newval.val = "0";
+		break;
 	case S_HEX:
+		newval.val = "0x0";
+		break;
 	case S_STRING:
 		newval.val = "";
 		break;
@@ -746,14 +750,17 @@ const char *sym_get_string_default(struct symbol *sym)
 		case yes: return "y";
 		}
 	case S_INT:
+		if (!str[0])
+			str = "0";
+		break;
 	case S_HEX:
-		return str;
-	case S_STRING:
-		return str;
-	case S_UNKNOWN:
+		if (!str[0])
+			str = "0x0";
+		break;
+	default:
 		break;
 	}
-	return "";
+	return str;
 }
 
 const char *sym_get_string_value(struct symbol *sym)
-- 
GitLab


From 072b6ad7cac6a868e56dec5f48a2e67d9ab8cb6e Mon Sep 17 00:00:00 2001
From: Nick Forrington <nick.forrington@arm.com>
Date: Thu, 2 Nov 2023 16:11:16 +0000
Subject: [PATCH 0667/4076] perf docs: Fix man page formatting for 'perf lock'

This makes "CONTENTION" a top level section (rather than a subsection of
"INFO").

Fixes: 79079f21f50a501f ("perf lock: Add -k and -F options to 'contention' subcommand")
Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Nick Forrington <nick.forrington@arm.com>
Tested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231102161117.49533-1-nick.forrington@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-lock.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 503abcba14380..f5938d616d751 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -119,7 +119,7 @@ INFO OPTIONS
 
 
 CONTENTION OPTIONS
---------------
+------------------
 
 -k::
 --key=<value>::
-- 
GitLab


From 556bed5c6d4167f9ffb5c8648cdd3c8e39aefec7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 30 Nov 2023 18:46:36 -0300
Subject: [PATCH 0668/4076] perf beauty: Don't use 'find ... -printf' as it
 isn't available in busybox
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Namhyung reported:

  I'm seeing a build error on my Alpine linux image which uses busybox +
  musl libc:

    In file included from trace/beauty/arch_errno_names.c:1,
                     from builtin-trace.c:899:
    /build/trace/beauty/generated/arch_errno_name_array.c: In function 'arch_syscalls__strerrno':
    /build/trace/beauty/generated/arch_errno_name_array.c:142:49: error: unused parameter 'arch' [-Werror=unused-parameter]
      142 | const char *arch_syscalls__strerrno(const char *arch, int err)

  It looks like busybox find command doesn't have -printf option

    find: unrecognized: -printf
    , Yesterday 9:16 PM
    ,
    BusyBox v1.36.1 (2023-07-27 17:12:24 UTC) multi-call binary.

    Usage: find [-HL] [PATH]... [OPTIONS] [ACTIONS]

    Search for files and perform actions on them.
    First failed action stops processing of current file.
    Defaults: PATH is current directory, action is '-print'

So just remove it and pipe find's entry to a basename loop to produce
the same result.

Then use an alternative loop that relies on the shell to avoid needless
forks and execs.

The discussion about it generated the impetus to stop doing strcmps to
find the right table at each errno to string translation but instead do
this just once and then use a function pointer to the right arch
specific table.

Suggested-by: David Laight <David.Laight@ACULAB.COM>
Reported-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/arch_errno_names.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh
index cc09dcaa891e0..b6e0767b4b34e 100755
--- a/tools/perf/trace/beauty/arch_errno_names.sh
+++ b/tools/perf/trace/beauty/arch_errno_names.sh
@@ -76,7 +76,9 @@ EoHEADER
 
 # Create list of architectures that have a specific errno.h.
 archlist=""
-for arch in $(find $toolsdir/arch -maxdepth 1 -mindepth 1 -type d -printf "%f\n" | sort -r); do
+for f in $toolsdir/arch/*/include/uapi/asm/errno.h; do
+	d=${f%/include/uapi/asm/errno.h}
+	arch="${d##*/}"
 	test -f $toolsdir/arch/$arch/include/uapi/asm/errno.h && archlist="$archlist $arch"
 done
 
-- 
GitLab


From 35a1743f4598e09524ae39651bc42733ec9749de Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:29 +0200
Subject: [PATCH 0669/4076] xhci: dbc: Drop duplicate checks for
 dma_free_coherent()

dma_free_coherent() is NULL-aware, not necessary to check for
the parameter twice. Drop duplicate conditionals in the caller.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index b40d9238d4471..9e9ce37118133 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -28,7 +28,7 @@ static void dbc_ring_free(struct device *dev, struct xhci_ring *ring)
 	if (!ring)
 		return;
 
-	if (ring->first_seg && ring->first_seg->trbs) {
+	if (ring->first_seg) {
 		dma_free_coherent(dev, TRB_SEGMENT_SIZE,
 				  ring->first_seg->trbs,
 				  ring->first_seg->dma);
@@ -394,9 +394,8 @@ static int dbc_erst_alloc(struct device *dev, struct xhci_ring *evt_ring,
 
 static void dbc_erst_free(struct device *dev, struct xhci_erst *erst)
 {
-	if (erst->entries)
-		dma_free_coherent(dev, sizeof(struct xhci_erst_entry),
-				  erst->entries, erst->erst_dma_addr);
+	dma_free_coherent(dev, sizeof(struct xhci_erst_entry), erst->entries,
+			  erst->erst_dma_addr);
 	erst->entries = NULL;
 }
 
@@ -543,11 +542,8 @@ static void xhci_dbc_mem_cleanup(struct xhci_dbc *dbc)
 
 	xhci_dbc_eps_exit(dbc);
 
-	if (dbc->string) {
-		dma_free_coherent(dbc->dev, dbc->string_size,
-				  dbc->string, dbc->string_dma);
-		dbc->string = NULL;
-	}
+	dma_free_coherent(dbc->dev, dbc->string_size, dbc->string, dbc->string_dma);
+	dbc->string = NULL;
 
 	dbc_free_ctx(dbc->dev, dbc->ctx);
 	dbc->ctx = NULL;
-- 
GitLab


From 601fbf65b2a0af126268da22500c24e8616ade5a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:30 +0200
Subject: [PATCH 0670/4076] xhci: dbc: Convert to use sysfs_streq()

It's standard approach to parse values from user space by using
sysfs_streq(). Make driver use it.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 9e9ce37118133..f505b79afe531 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -957,9 +957,9 @@ static ssize_t dbc_store(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	if (!strncmp(buf, "enable", 6))
+	if (sysfs_streq(buf, "enable"))
 		xhci_dbc_start(dbc);
-	else if (!strncmp(buf, "disable", 7))
+	else if (sysfs_streq(buf, "disable"))
 		xhci_dbc_stop(dbc);
 	else
 		return -EINVAL;
-- 
GitLab


From a230f1a74866802b9a87ce7aa8dbd81d22831ab3 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:31 +0200
Subject: [PATCH 0671/4076] xhci: dbc: Use sysfs_emit() to instead of
 scnprintf()

Follow the advice of the Documentation/filesystems/sysfs.rst and show()
should only use sysfs_emit() or sysfs_emit_at() when formatting the
value to be returned to user space.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 44 +++++++++++++---------------------
 drivers/usb/host/xhci-dbgcap.h |  1 +
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index f505b79afe531..df14e336370d5 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -910,41 +910,29 @@ static void xhci_dbc_handle_events(struct work_struct *work)
 	mod_delayed_work(system_wq, &dbc->event_work, 1);
 }
 
+static const char * const dbc_state_strings[DS_MAX] = {
+	[DS_DISABLED] = "disabled",
+	[DS_INITIALIZED] = "initialized",
+	[DS_ENABLED] = "enabled",
+	[DS_CONNECTED] = "connected",
+	[DS_CONFIGURED] = "configured",
+	[DS_STALLED] = "stalled",
+};
+
 static ssize_t dbc_show(struct device *dev,
 			struct device_attribute *attr,
 			char *buf)
 {
-	const char		*p;
 	struct xhci_dbc		*dbc;
 	struct xhci_hcd		*xhci;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	switch (dbc->state) {
-	case DS_DISABLED:
-		p = "disabled";
-		break;
-	case DS_INITIALIZED:
-		p = "initialized";
-		break;
-	case DS_ENABLED:
-		p = "enabled";
-		break;
-	case DS_CONNECTED:
-		p = "connected";
-		break;
-	case DS_CONFIGURED:
-		p = "configured";
-		break;
-	case DS_STALLED:
-		p = "stalled";
-		break;
-	default:
-		p = "unknown";
-	}
+	if (dbc->state >= ARRAY_SIZE(dbc_state_strings))
+		return sysfs_emit(buf, "unknown\n");
 
-	return sprintf(buf, "%s\n", p);
+	return sysfs_emit(buf, "%s\n", dbc_state_strings[dbc->state]);
 }
 
 static ssize_t dbc_store(struct device *dev,
@@ -977,7 +965,7 @@ static ssize_t dbc_idVendor_show(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	return sprintf(buf, "%04x\n", dbc->idVendor);
+	return sysfs_emit(buf, "%04x\n", dbc->idVendor);
 }
 
 static ssize_t dbc_idVendor_store(struct device *dev,
@@ -1017,7 +1005,7 @@ static ssize_t dbc_idProduct_show(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	return sprintf(buf, "%04x\n", dbc->idProduct);
+	return sysfs_emit(buf, "%04x\n", dbc->idProduct);
 }
 
 static ssize_t dbc_idProduct_store(struct device *dev,
@@ -1056,7 +1044,7 @@ static ssize_t dbc_bcdDevice_show(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	return sprintf(buf, "%04x\n", dbc->bcdDevice);
+	return sysfs_emit(buf, "%04x\n", dbc->bcdDevice);
 }
 
 static ssize_t dbc_bcdDevice_store(struct device *dev,
@@ -1096,7 +1084,7 @@ static ssize_t dbc_bInterfaceProtocol_show(struct device *dev,
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
 
-	return sprintf(buf, "%02x\n", dbc->bInterfaceProtocol);
+	return sysfs_emit(buf, "%02x\n", dbc->bInterfaceProtocol);
 }
 
 static ssize_t dbc_bInterfaceProtocol_store(struct device *dev,
diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h
index 51a7ab3ba0cac..e39e3ae1677ae 100644
--- a/drivers/usb/host/xhci-dbgcap.h
+++ b/drivers/usb/host/xhci-dbgcap.h
@@ -82,6 +82,7 @@ enum dbc_state {
 	DS_CONNECTED,
 	DS_CONFIGURED,
 	DS_STALLED,
+	DS_MAX
 };
 
 struct dbc_ep {
-- 
GitLab


From e3be8fb7d012d1e9a1d1b753ca50ff057bbb12b2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:32 +0200
Subject: [PATCH 0672/4076] xhci: dbc: Use ATTRIBUTE_GROUPS()

Embrace ATTRIBUTE_GROUPS() to avoid boiler plate code.
This should not introduce any functional changes.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-5-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index df14e336370d5..660e3ee31dc69 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -1123,7 +1123,7 @@ static DEVICE_ATTR_RW(dbc_idProduct);
 static DEVICE_ATTR_RW(dbc_bcdDevice);
 static DEVICE_ATTR_RW(dbc_bInterfaceProtocol);
 
-static struct attribute *dbc_dev_attributes[] = {
+static struct attribute *dbc_dev_attrs[] = {
 	&dev_attr_dbc.attr,
 	&dev_attr_dbc_idVendor.attr,
 	&dev_attr_dbc_idProduct.attr,
@@ -1131,10 +1131,7 @@ static struct attribute *dbc_dev_attributes[] = {
 	&dev_attr_dbc_bInterfaceProtocol.attr,
 	NULL
 };
-
-static const struct attribute_group dbc_dev_attrib_grp = {
-	.attrs = dbc_dev_attributes,
-};
+ATTRIBUTE_GROUPS(dbc_dev);
 
 struct xhci_dbc *
 xhci_alloc_dbc(struct device *dev, void __iomem *base, const struct dbc_driver *driver)
@@ -1160,7 +1157,7 @@ xhci_alloc_dbc(struct device *dev, void __iomem *base, const struct dbc_driver *
 	INIT_DELAYED_WORK(&dbc->event_work, xhci_dbc_handle_events);
 	spin_lock_init(&dbc->lock);
 
-	ret = sysfs_create_group(&dev->kobj, &dbc_dev_attrib_grp);
+	ret = sysfs_create_groups(&dev->kobj, dbc_dev_groups);
 	if (ret)
 		goto err;
 
@@ -1179,7 +1176,7 @@ void xhci_dbc_remove(struct xhci_dbc *dbc)
 	xhci_dbc_stop(dbc);
 
 	/* remove sysfs files */
-	sysfs_remove_group(&dbc->dev->kobj, &dbc_dev_attrib_grp);
+	sysfs_remove_groups(&dbc->dev->kobj, dbc_dev_groups);
 
 	kfree(dbc);
 }
-- 
GitLab


From 24352d170b5fcab1d7724dd20257e0b73cbdb453 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:33 +0200
Subject: [PATCH 0673/4076] xhci: dbc: Check for errors first in
 xhci_dbc_stop()

The usual pattern is to check for errors and then continue if none.
Apply that pattern to xhci_dbc_stop() code.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-6-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 660e3ee31dc69..6b9f4b8392709 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -646,11 +646,11 @@ static void xhci_dbc_stop(struct xhci_dbc *dbc)
 	spin_lock_irqsave(&dbc->lock, flags);
 	ret = xhci_do_dbc_stop(dbc);
 	spin_unlock_irqrestore(&dbc->lock, flags);
+	if (ret)
+		return;
 
-	if (!ret) {
-		xhci_dbc_mem_cleanup(dbc);
-		pm_runtime_put_sync(dbc->dev); /* note, was self.controller */
-	}
+	xhci_dbc_mem_cleanup(dbc);
+	pm_runtime_put_sync(dbc->dev); /* note, was self.controller */
 }
 
 static void
-- 
GitLab


From 89cd6362e6ad4aa8663c41ac960f223a761385b4 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:34 +0200
Subject: [PATCH 0674/4076] xhci: dbc: Don't shadow error codes in store()
 functions

kstrtox() along with regmap API can return different error codes
based on the circumstances. Don't shadow them when returning to
the caller.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-7-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 6b9f4b8392709..c211c69e80410 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -977,9 +977,11 @@ static ssize_t dbc_idVendor_store(struct device *dev,
 	void __iomem		*ptr;
 	u16			value;
 	u32			dev_info;
+	int ret;
 
-	if (kstrtou16(buf, 0, &value))
-		return -EINVAL;
+	ret = kstrtou16(buf, 0, &value);
+	if (ret)
+		return ret;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
@@ -1017,9 +1019,11 @@ static ssize_t dbc_idProduct_store(struct device *dev,
 	void __iomem		*ptr;
 	u32			dev_info;
 	u16			value;
+	int ret;
 
-	if (kstrtou16(buf, 0, &value))
-		return -EINVAL;
+	ret = kstrtou16(buf, 0, &value);
+	if (ret)
+		return ret;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
@@ -1056,9 +1060,11 @@ static ssize_t dbc_bcdDevice_store(struct device *dev,
 	void __iomem *ptr;
 	u32 dev_info;
 	u16 value;
+	int ret;
 
-	if (kstrtou16(buf, 0, &value))
-		return -EINVAL;
+	ret = kstrtou16(buf, 0, &value);
+	if (ret)
+		return ret;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
 	dbc = xhci->dbc;
@@ -1098,9 +1104,13 @@ static ssize_t dbc_bInterfaceProtocol_store(struct device *dev,
 	u8 value;
 	int ret;
 
-	/* bInterfaceProtocol is 8 bit, but xhci only supports values 0 and 1 */
+	/* bInterfaceProtocol is 8 bit, but... */
 	ret = kstrtou8(buf, 0, &value);
-	if (ret || value > 1)
+	if (ret)
+		return ret;
+
+	/* ...xhci only supports values 0 and 1 */
+	if (value > 1)
 		return -EINVAL;
 
 	xhci = hcd_to_xhci(dev_get_drvdata(dev));
-- 
GitLab


From b28718717b10befac6f43eb5a1e075ee4fb4ef02 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:35 +0200
Subject: [PATCH 0675/4076] xhci: dbc: Replace custom return value with proper
 Linux error code

Replace the custom return value with proper Linux error code.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-8-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index c211c69e80410..779a564ad6987 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -593,7 +593,7 @@ static int xhci_do_dbc_start(struct xhci_dbc *dbc)
 static int xhci_do_dbc_stop(struct xhci_dbc *dbc)
 {
 	if (dbc->state == DS_DISABLED)
-		return -1;
+		return -EINVAL;
 
 	writel(0, &dbc->regs->control);
 	dbc->state = DS_DISABLED;
-- 
GitLab


From 84637512e09c51929e36647a151d26cd1efa1b31 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:36 +0200
Subject: [PATCH 0676/4076] xhci: dbc: Use sizeof_field() where it makes sense

Instead of doing custom calculations, use sizeof_field() macro.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-9-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 779a564ad6987..0c9fd61e9c5b2 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -374,7 +374,7 @@ static void xhci_dbc_eps_init(struct xhci_dbc *dbc)
 
 static void xhci_dbc_eps_exit(struct xhci_dbc *dbc)
 {
-	memset(dbc->eps, 0, sizeof(struct dbc_ep) * ARRAY_SIZE(dbc->eps));
+	memset(dbc->eps, 0, sizeof_field(struct xhci_dbc, eps));
 }
 
 static int dbc_erst_alloc(struct device *dev, struct xhci_ring *evt_ring,
-- 
GitLab


From 311902d4cc4c13c0f1b4e79ee7eb9e04642f3d0b Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:37 +0200
Subject: [PATCH 0677/4076] xhci: dbc: Use sizeof(*pointer) instead of
 sizeof(type)

It is preferred to use sizeof(*pointer) instead of sizeof(type).
The type of the variable can change and one needs not change
the former (unlike the latter). No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-10-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 0c9fd61e9c5b2..73494d55b0be1 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -380,7 +380,7 @@ static void xhci_dbc_eps_exit(struct xhci_dbc *dbc)
 static int dbc_erst_alloc(struct device *dev, struct xhci_ring *evt_ring,
 		    struct xhci_erst *erst, gfp_t flags)
 {
-	erst->entries = dma_alloc_coherent(dev, sizeof(struct xhci_erst_entry),
+	erst->entries = dma_alloc_coherent(dev, sizeof(*erst->entries),
 					   &erst->erst_dma_addr, flags);
 	if (!erst->entries)
 		return -ENOMEM;
@@ -394,7 +394,7 @@ static int dbc_erst_alloc(struct device *dev, struct xhci_ring *evt_ring,
 
 static void dbc_erst_free(struct device *dev, struct xhci_erst *erst)
 {
-	dma_free_coherent(dev, sizeof(struct xhci_erst_entry), erst->entries,
+	dma_free_coherent(dev, sizeof(*erst->entries), erst->entries,
 			  erst->erst_dma_addr);
 	erst->entries = NULL;
 }
@@ -494,7 +494,7 @@ static int xhci_dbc_mem_init(struct xhci_dbc *dbc, gfp_t flags)
 		goto ctx_fail;
 
 	/* Allocate the string table: */
-	dbc->string_size = sizeof(struct dbc_str_descs);
+	dbc->string_size = sizeof(*dbc->string);
 	dbc->string = dma_alloc_coherent(dev, dbc->string_size,
 					 &dbc->string_dma, flags);
 	if (!dbc->string)
-- 
GitLab


From cdcaa870c7be7e421de5c33257d1b3cc074dc802 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:38 +0200
Subject: [PATCH 0678/4076] xhci: dbc: Add missing headers

Don't inherit headers "by chances" from asm/bug.h, asm/io.h,
etc... Include the needed headers explicitly.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-11-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 73494d55b0be1..d82935d31126d 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -6,9 +6,24 @@
  *
  * Author: Lu Baolu <baolu.lu@linux.intel.com>
  */
+#include <linux/bug.h>
+#include <linux/device.h>
 #include <linux/dma-mapping.h>
-#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/kstrtox.h>
+#include <linux/list.h>
 #include <linux/nls.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include <linux/io-64-nonatomic-lo-hi.h>
+
+#include <asm/byteorder.h>
 
 #include "xhci.h"
 #include "xhci-trace.h"
-- 
GitLab


From 5080ef2d373ada6fba2e7b86a56a93c8da909a46 Mon Sep 17 00:00:00 2001
From: Niklas Neronin <niklas.neronin@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:39 +0200
Subject: [PATCH 0679/4076] xhci: check if legacy irq is available before using
 it as fallback

Move the error check "No MSI-X/MSI found and no IRQ in BIOS" inside
'goto legacy'. It is better to check if the IRQ interrupt is available,
before trying to add a handler. Additionally the aforementioned error
message is much more clear.

Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-12-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 95ed9404f6f85..7f2b1312e943b 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -228,12 +228,12 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 		return 0;
 	}
 
+legacy_irq:
 	if (!pdev->irq) {
 		xhci_err(xhci, "No msi-x/msi found and no IRQ in BIOS\n");
 		return -EINVAL;
 	}
 
- legacy_irq:
 	if (!strlen(hcd->irq_descr))
 		snprintf(hcd->irq_descr, sizeof(hcd->irq_descr), "%s:usb%d",
 			 hcd->driver->description, hcd->self.busnum);
-- 
GitLab


From f977f4c9301c8a67c367946a08c4ce940b42c299 Mon Sep 17 00:00:00 2001
From: Niklas Neronin <niklas.neronin@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:40 +0200
Subject: [PATCH 0680/4076] xhci: add handler for only one interrupt line

Current xHCI driver only supports one "interrupter", meaning we will
only use one MSI/MSI-X interrupt line. Thus, add handler only to the
first interrupt line.

Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Co-developed-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-13-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c | 35 ++++++++++-------------------------
 1 file changed, 10 insertions(+), 25 deletions(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 7f2b1312e943b..59bbae69f97c8 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -95,10 +95,9 @@ static void xhci_msix_sync_irqs(struct xhci_hcd *xhci)
 
 	if (hcd->msix_enabled) {
 		struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
-		int i;
 
-		for (i = 0; i < xhci->msix_count; i++)
-			synchronize_irq(pci_irq_vector(pdev, i));
+		/* for now, the driver only supports one primary interrupter */
+		synchronize_irq(pci_irq_vector(pdev, 0));
 	}
 }
 
@@ -112,15 +111,7 @@ static void xhci_cleanup_msix(struct xhci_hcd *xhci)
 	if (hcd->irq > 0)
 		return;
 
-	if (hcd->msix_enabled) {
-		int i;
-
-		for (i = 0; i < xhci->msix_count; i++)
-			free_irq(pci_irq_vector(pdev, i), xhci_to_hcd(xhci));
-	} else {
-		free_irq(pci_irq_vector(pdev, 0), xhci_to_hcd(xhci));
-	}
-
+	free_irq(pci_irq_vector(pdev, 0), xhci_to_hcd(xhci));
 	pci_free_irq_vectors(pdev);
 	hcd->msix_enabled = 0;
 }
@@ -159,9 +150,9 @@ static int xhci_setup_msi(struct xhci_hcd *xhci)
  */
 static int xhci_setup_msix(struct xhci_hcd *xhci)
 {
-	int i, ret;
 	struct usb_hcd *hcd = xhci_to_hcd(xhci);
 	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
+	int ret;
 
 	/*
 	 * calculate number of msi-x vectors supported.
@@ -181,22 +172,16 @@ static int xhci_setup_msix(struct xhci_hcd *xhci)
 		return ret;
 	}
 
-	for (i = 0; i < xhci->msix_count; i++) {
-		ret = request_irq(pci_irq_vector(pdev, i), xhci_msi_irq, 0,
-				"xhci_hcd", xhci_to_hcd(xhci));
-		if (ret)
-			goto disable_msix;
+	ret = request_irq(pci_irq_vector(pdev, 0), xhci_msi_irq, 0, "xhci_hcd",
+			  xhci_to_hcd(xhci));
+	if (ret) {
+		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI-X interrupt");
+		pci_free_irq_vectors(pdev);
+		return ret;
 	}
 
 	hcd->msix_enabled = 1;
 	return ret;
-
-disable_msix:
-	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI-X interrupt");
-	while (--i >= 0)
-		free_irq(pci_irq_vector(pdev, i), xhci_to_hcd(xhci));
-	pci_free_irq_vectors(pdev);
-	return ret;
 }
 
 static int xhci_try_enable_msi(struct usb_hcd *hcd)
-- 
GitLab


From 74554e9c227679a6fc5eb4d968d31c2ca4df853e Mon Sep 17 00:00:00 2001
From: Niklas Neronin <niklas.neronin@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:41 +0200
Subject: [PATCH 0681/4076] xhci: refactor static MSI-X function

The current way the xhci driver sets up MSI/MSI-X interrupts is overly
complex and messy. The whole MSI/MSI-X setup can be done in one simple
function.

Start refactoring this by incorporating 'xhci_setup_msix()' into
'xhci_try_enable_msi()'. 'xhci_setup_msix()' is a static function which
is only called by 'xhci_try_enable_msi()'.

Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-14-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c | 68 +++++++++++++++----------------------
 1 file changed, 28 insertions(+), 40 deletions(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 59bbae69f97c8..370943c048815 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -145,31 +145,40 @@ static int xhci_setup_msi(struct xhci_hcd *xhci)
 	return ret;
 }
 
-/*
- * Set up MSI-X
- */
-static int xhci_setup_msix(struct xhci_hcd *xhci)
+static int xhci_try_enable_msi(struct usb_hcd *hcd)
 {
-	struct usb_hcd *hcd = xhci_to_hcd(xhci);
-	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
+	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+	struct pci_dev  *pdev;
 	int ret;
 
+	pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
 	/*
-	 * calculate number of msi-x vectors supported.
+	 * Some Fresco Logic host controllers advertise MSI, but fail to
+	 * generate interrupts.  Don't even try to enable MSI.
+	 */
+	if (xhci->quirks & XHCI_BROKEN_MSI)
+		goto legacy_irq;
+
+	/* unregister the legacy interrupt */
+	if (hcd->irq)
+		free_irq(hcd->irq, hcd);
+	hcd->irq = 0;
+
+	/*
+	 * calculate number of MSI-X vectors supported.
 	 * - HCS_MAX_INTRS: the max number of interrupts the host can handle,
 	 *   with max number of interrupters based on the xhci HCSPARAMS1.
-	 * - num_online_cpus: maximum msi-x vectors per CPUs core.
+	 * - num_online_cpus: maximum MSI-X vectors per CPUs core.
 	 *   Add additional 1 vector to ensure always available interrupt.
 	 */
 	xhci->msix_count = min(num_online_cpus() + 1,
-				HCS_MAX_INTRS(xhci->hcs_params1));
+			       HCS_MAX_INTRS(xhci->hcs_params1));
 
 	ret = pci_alloc_irq_vectors(pdev, xhci->msix_count, xhci->msix_count,
-			PCI_IRQ_MSIX);
+				    PCI_IRQ_MSIX);
 	if (ret < 0) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-				"Failed to enable MSI-X");
-		return ret;
+		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Failed to enable MSI-X");
+		goto setup_msi;
 	}
 
 	ret = request_irq(pci_irq_vector(pdev, 0), xhci_msi_irq, 0, "xhci_hcd",
@@ -177,37 +186,16 @@ static int xhci_setup_msix(struct xhci_hcd *xhci)
 	if (ret) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI-X interrupt");
 		pci_free_irq_vectors(pdev);
-		return ret;
+		goto setup_msi;
 	}
 
+	hcd->msi_enabled = 1;
 	hcd->msix_enabled = 1;
-	return ret;
-}
-
-static int xhci_try_enable_msi(struct usb_hcd *hcd)
-{
-	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	struct pci_dev  *pdev;
-	int ret;
-
-	pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
-	/*
-	 * Some Fresco Logic host controllers advertise MSI, but fail to
-	 * generate interrupts.  Don't even try to enable MSI.
-	 */
-	if (xhci->quirks & XHCI_BROKEN_MSI)
-		goto legacy_irq;
-
-	/* unregister the legacy interrupt */
-	if (hcd->irq)
-		free_irq(hcd->irq, hcd);
-	hcd->irq = 0;
-
-	ret = xhci_setup_msix(xhci);
-	if (ret)
-		/* fall back to msi*/
-		ret = xhci_setup_msi(xhci);
+	return 0;
 
+setup_msi:
+	/* fall back to MSI */
+	ret = xhci_setup_msi(xhci);
 	if (!ret) {
 		hcd->msi_enabled = 1;
 		return 0;
-- 
GitLab


From a795f708b2844054a7d12aae72397bf51d0f87b3 Mon Sep 17 00:00:00 2001
From: Niklas Neronin <niklas.neronin@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:42 +0200
Subject: [PATCH 0682/4076] xhci: refactor static MSI function

The current way the xhci driver sets up MSI interrupts is overly complex
and messy. The whole MSI setup can be done in one simple function.

Continue refactoring MSI/MSI-X setup by incorporating 'xhci_setup_msi()'
into 'xhci_try_enable_msi()'. Now all interrupt enabling is contained in
one function, which should make it easier to rework.

Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-15-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c | 49 ++++++++++++-------------------------
 1 file changed, 15 insertions(+), 34 deletions(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 370943c048815..dbec0a315566d 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -116,35 +116,6 @@ static void xhci_cleanup_msix(struct xhci_hcd *xhci)
 	hcd->msix_enabled = 0;
 }
 
-/*
- * Set up MSI
- */
-static int xhci_setup_msi(struct xhci_hcd *xhci)
-{
-	int ret;
-	/*
-	 * TODO:Check with MSI Soc for sysdev
-	 */
-	struct pci_dev  *pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
-
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
-	if (ret < 0) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-				"failed to allocate MSI entry");
-		return ret;
-	}
-
-	ret = request_irq(pdev->irq, xhci_msi_irq,
-				0, "xhci_hcd", xhci_to_hcd(xhci));
-	if (ret) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-				"disable MSI interrupt");
-		pci_free_irq_vectors(pdev);
-	}
-
-	return ret;
-}
-
 static int xhci_try_enable_msi(struct usb_hcd *hcd)
 {
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
@@ -194,13 +165,23 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 	return 0;
 
 setup_msi:
-	/* fall back to MSI */
-	ret = xhci_setup_msi(xhci);
-	if (!ret) {
-		hcd->msi_enabled = 1;
-		return 0;
+	/* TODO: Check with MSI Soc for sysdev */
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+	if (ret < 0) {
+		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "failed to allocate MSI entry");
+		goto legacy_irq;
 	}
 
+	ret = request_irq(pdev->irq, xhci_msi_irq, 0, "xhci_hcd", xhci_to_hcd(xhci));
+	if (ret) {
+		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI interrupt");
+		pci_free_irq_vectors(pdev);
+		goto legacy_irq;
+	}
+
+	hcd->msi_enabled = 1;
+	return 0;
+
 legacy_irq:
 	if (!pdev->irq) {
 		xhci_err(xhci, "No msi-x/msi found and no IRQ in BIOS\n");
-- 
GitLab


From dfbf4441f2d31d21e0a98c5fcff6dae8b57b79dd Mon Sep 17 00:00:00 2001
From: Niklas Neronin <niklas.neronin@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:43 +0200
Subject: [PATCH 0683/4076] xhci: change 'msix_count' to encompass MSI or MSI-X
 vectors

Instead of variable 'msix_count' containing the number of MSI-X vectors,
now it can contains MSI or MSI-X vector amount. Because both interrupt
methods allow several vectors. Thus, 'msix_count' is renamed to 'nvecs'.

Additionally, instead of storing the maximum possible vector amount,
now it stores the amount of successfully allocated vectors, or negative
integer on allocation failure.

Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-16-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c | 14 +++++++-------
 drivers/usb/host/xhci.h     |  4 ++--
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index dbec0a315566d..2307164a1e816 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -142,12 +142,12 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 	 * - num_online_cpus: maximum MSI-X vectors per CPUs core.
 	 *   Add additional 1 vector to ensure always available interrupt.
 	 */
-	xhci->msix_count = min(num_online_cpus() + 1,
-			       HCS_MAX_INTRS(xhci->hcs_params1));
+	xhci->nvecs = min(num_online_cpus() + 1,
+			  HCS_MAX_INTRS(xhci->hcs_params1));
 
-	ret = pci_alloc_irq_vectors(pdev, xhci->msix_count, xhci->msix_count,
-				    PCI_IRQ_MSIX);
-	if (ret < 0) {
+	xhci->nvecs = pci_alloc_irq_vectors(pdev, xhci->nvecs, xhci->nvecs,
+					    PCI_IRQ_MSIX);
+	if (xhci->nvecs < 0) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Failed to enable MSI-X");
 		goto setup_msi;
 	}
@@ -166,8 +166,8 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 
 setup_msi:
 	/* TODO: Check with MSI Soc for sysdev */
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
-	if (ret < 0) {
+	xhci->nvecs = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+	if (xhci->nvecs < 0) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "failed to allocate MSI entry");
 		goto legacy_irq;
 	}
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 62b610f007544..90e6b6ef7bd20 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1765,8 +1765,8 @@ struct xhci_hcd {
 	int		page_size;
 	/* Valid values are 12 to 20, inclusive */
 	int		page_shift;
-	/* msi-x vectors */
-	int		msix_count;
+	/* MSI-X/MSI vectors */
+	int		nvecs;
 	/* optional clocks */
 	struct clk		*clk;
 	struct clk		*reg_clk;
-- 
GitLab


From 9831960df237855ea3333e08c26cc9405a7ed440 Mon Sep 17 00:00:00 2001
From: Niklas Neronin <niklas.neronin@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:44 +0200
Subject: [PATCH 0684/4076] xhci: rework 'xhci_try_enable_msi()' MSI and MSI-X
 setup code

Simplify 'xhci_try_enable_msi()' and reduce unnecessary function calls.

xHCI driver first tries to allocate 'num_online_cpu()' number of MSI-X
vectors, if that fails it falls back to a single MSI vector. There is no
good reason for this, we currently only support a primary interrupter.
However, we are still interested in knowing if there are more vectors
available, which will be utilized once we get secondary interrupter
support.

Call 'pci_alloc_irq_vectors()' once (with MSI-X and MSI flag), instead
of separately for MSI-X and MSI. And accept any number of MSI-X or MSI
vectors between 1 and 'num_online_cpu()'.

Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-17-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c | 44 +++++++++++++------------------------
 1 file changed, 15 insertions(+), 29 deletions(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 2307164a1e816..398f81b0500be 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -116,13 +116,13 @@ static void xhci_cleanup_msix(struct xhci_hcd *xhci)
 	hcd->msix_enabled = 0;
 }
 
+/* Try enabling MSI-X with MSI and legacy IRQ as fallback */
 static int xhci_try_enable_msi(struct usb_hcd *hcd)
 {
+	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	struct pci_dev  *pdev;
 	int ret;
 
-	pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
 	/*
 	 * Some Fresco Logic host controllers advertise MSI, but fail to
 	 * generate interrupts.  Don't even try to enable MSI.
@@ -145,42 +145,28 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 	xhci->nvecs = min(num_online_cpus() + 1,
 			  HCS_MAX_INTRS(xhci->hcs_params1));
 
-	xhci->nvecs = pci_alloc_irq_vectors(pdev, xhci->nvecs, xhci->nvecs,
-					    PCI_IRQ_MSIX);
+	/* TODO: Check with MSI Soc for sysdev */
+	xhci->nvecs = pci_alloc_irq_vectors(pdev, 1, xhci->nvecs,
+					    PCI_IRQ_MSIX | PCI_IRQ_MSI);
 	if (xhci->nvecs < 0) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Failed to enable MSI-X");
-		goto setup_msi;
+		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
+			       "failed to allocate IRQ vectors");
+		goto legacy_irq;
 	}
 
 	ret = request_irq(pci_irq_vector(pdev, 0), xhci_msi_irq, 0, "xhci_hcd",
 			  xhci_to_hcd(xhci));
-	if (ret) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI-X interrupt");
-		pci_free_irq_vectors(pdev);
-		goto setup_msi;
-	}
+	if (ret)
+		goto free_irq_vectors;
 
 	hcd->msi_enabled = 1;
-	hcd->msix_enabled = 1;
+	hcd->msix_enabled = pdev->msix_enabled;
 	return 0;
 
-setup_msi:
-	/* TODO: Check with MSI Soc for sysdev */
-	xhci->nvecs = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
-	if (xhci->nvecs < 0) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "failed to allocate MSI entry");
-		goto legacy_irq;
-	}
-
-	ret = request_irq(pdev->irq, xhci_msi_irq, 0, "xhci_hcd", xhci_to_hcd(xhci));
-	if (ret) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI interrupt");
-		pci_free_irq_vectors(pdev);
-		goto legacy_irq;
-	}
-
-	hcd->msi_enabled = 1;
-	return 0;
+free_irq_vectors:
+	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable %s interrupt",
+		       pdev->msix_enabled ? "MSI-X" : "MSI");
+	pci_free_irq_vectors(pdev);
 
 legacy_irq:
 	if (!pdev->irq) {
-- 
GitLab


From 36b24ebf9a04f19f1fe47ec0b50e5ca1d30dd1bc Mon Sep 17 00:00:00 2001
From: Niklas Neronin <niklas.neronin@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:45 +0200
Subject: [PATCH 0685/4076] xhci: minor coding style cleanup in
 'xhci_try_enable_msi()'

Remove extra spaces/indentation and add spaces where required.
This commit does not change any functionality.

Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-18-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 398f81b0500be..dfeca3cbac8bb 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -178,12 +178,10 @@ legacy_irq:
 		snprintf(hcd->irq_descr, sizeof(hcd->irq_descr), "%s:usb%d",
 			 hcd->driver->description, hcd->self.busnum);
 
-	/* fall back to legacy interrupt*/
-	ret = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED,
-			hcd->irq_descr, hcd);
+	/* fall back to legacy interrupt */
+	ret = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED, hcd->irq_descr, hcd);
 	if (ret) {
-		xhci_err(xhci, "request interrupt %d failed\n",
-				pdev->irq);
+		xhci_err(xhci, "request interrupt %d failed\n", pdev->irq);
 		return ret;
 	}
 	hcd->irq = pdev->irq;
-- 
GitLab


From e34900f46cd69b2859b9894275415134a0988d9d Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:46 +0200
Subject: [PATCH 0686/4076] xhci: Reconfigure endpoint 0 max packet size only
 during endpoint reset

The max packet size for full speed control endpoint 0 may vary. It is
defined in the device descriptor, which is read using the same endpoint.
Usb core sets a temporary max packet size value until the real value is
read.

xhci driver needs to reconfigure the endpoint context seen by the
controller if the max packet size changes.
It makes more sense to do this reconfiguration in xhci_endpoint_reset()
instead of urb enqueue as usb core will call endpoint reset during
enumeration if the max packet values differ.
Max packet size adjustment for endpoint 0 can only happen once per
device enumeration.

Previously the max packet size was checked during every urb enqueue.
This is an additional check for every enqueued urb, and also turned out
to have locking issues as urbs may be queued in any context while xhci
max packet size reconfiguration requires memory allocation, locking, and
sleeping.

Tested with a full speed device using both old and new scheme enumeration
and an intentionally incorrect preliminary max packet size value.

Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-19-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 85 ++++++++++++++++++++---------------------
 1 file changed, 42 insertions(+), 43 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index cb885ddc20326..71a117db21a7a 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1438,10 +1438,8 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
  * descriptor.  If the usb_device's max packet size changes after that point,
  * we need to issue an evaluate context command and wait on it.
  */
-static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
-		unsigned int ep_index, struct urb *urb, gfp_t mem_flags)
+static int xhci_check_ep0_maxpacket(struct xhci_hcd *xhci, struct xhci_virt_device *vdev)
 {
-	struct xhci_container_ctx *out_ctx;
 	struct xhci_input_control_ctx *ctrl_ctx;
 	struct xhci_ep_ctx *ep_ctx;
 	struct xhci_command *command;
@@ -1449,11 +1447,15 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
 	int hw_max_packet_size;
 	int ret = 0;
 
-	out_ctx = xhci->devs[slot_id]->out_ctx;
-	ep_ctx = xhci_get_ep_ctx(xhci, out_ctx, ep_index);
+	ep_ctx = xhci_get_ep_ctx(xhci, vdev->out_ctx, 0);
 	hw_max_packet_size = MAX_PACKET_DECODED(le32_to_cpu(ep_ctx->ep_info2));
-	max_packet_size = usb_endpoint_maxp(&urb->dev->ep0.desc);
-	if (hw_max_packet_size != max_packet_size) {
+	max_packet_size = usb_endpoint_maxp(&vdev->udev->ep0.desc);
+
+	if (hw_max_packet_size == max_packet_size)
+		return 0;
+
+	switch (max_packet_size) {
+	case 8: case 16: case 32: case 64: case 9:
 		xhci_dbg_trace(xhci,  trace_xhci_dbg_context_change,
 				"Max Packet Size for ep 0 changed.");
 		xhci_dbg_trace(xhci,  trace_xhci_dbg_context_change,
@@ -1465,28 +1467,22 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
 		xhci_dbg_trace(xhci,  trace_xhci_dbg_context_change,
 				"Issuing evaluate context command.");
 
-		/* Set up the input context flags for the command */
-		/* FIXME: This won't work if a non-default control endpoint
-		 * changes max packet sizes.
-		 */
-
-		command = xhci_alloc_command(xhci, true, mem_flags);
+		command = xhci_alloc_command(xhci, true, GFP_KERNEL);
 		if (!command)
 			return -ENOMEM;
 
-		command->in_ctx = xhci->devs[slot_id]->in_ctx;
+		command->in_ctx = vdev->in_ctx;
 		ctrl_ctx = xhci_get_input_control_ctx(command->in_ctx);
 		if (!ctrl_ctx) {
 			xhci_warn(xhci, "%s: Could not get input context, bad type.\n",
 					__func__);
 			ret = -ENOMEM;
-			goto command_cleanup;
+			break;
 		}
 		/* Set up the modified control endpoint 0 */
-		xhci_endpoint_copy(xhci, xhci->devs[slot_id]->in_ctx,
-				xhci->devs[slot_id]->out_ctx, ep_index);
+		xhci_endpoint_copy(xhci, vdev->in_ctx, vdev->out_ctx, 0);
 
-		ep_ctx = xhci_get_ep_ctx(xhci, command->in_ctx, ep_index);
+		ep_ctx = xhci_get_ep_ctx(xhci, command->in_ctx, 0);
 		ep_ctx->ep_info &= cpu_to_le32(~EP_STATE_MASK);/* must clear */
 		ep_ctx->ep_info2 &= cpu_to_le32(~MAX_PACKET_MASK);
 		ep_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(max_packet_size));
@@ -1494,17 +1490,20 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
 		ctrl_ctx->add_flags = cpu_to_le32(EP0_FLAG);
 		ctrl_ctx->drop_flags = 0;
 
-		ret = xhci_configure_endpoint(xhci, urb->dev, command,
-				true, false);
-
-		/* Clean up the input context for later use by bandwidth
-		 * functions.
-		 */
+		ret = xhci_configure_endpoint(xhci, vdev->udev, command,
+					      true, false);
+		/* Clean up the input context for later use by bandwidth functions */
 		ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG);
-command_cleanup:
-		kfree(command->completion);
-		kfree(command);
+		break;
+	default:
+		dev_dbg(&vdev->udev->dev, "incorrect max packet size %d for ep0\n",
+			max_packet_size);
+		return -EINVAL;
 	}
+
+	kfree(command->completion);
+	kfree(command);
+
 	return ret;
 }
 
@@ -1561,21 +1560,6 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
 
 	trace_xhci_urb_enqueue(urb);
 
-	if (usb_endpoint_xfer_control(&urb->ep->desc)) {
-		/* Check to see if the max packet size for the default control
-		 * endpoint changed during FS device enumeration
-		 */
-		if (urb->dev->speed == USB_SPEED_FULL) {
-			ret = xhci_check_maxpacket(xhci, slot_id,
-					ep_index, urb, mem_flags);
-			if (ret < 0) {
-				xhci_urb_free_priv(urb_priv);
-				urb->hcpriv = NULL;
-				return ret;
-			}
-		}
-	}
-
 	spin_lock_irqsave(&xhci->lock, flags);
 
 	if (xhci->xhc_state & XHCI_STATE_DYING) {
@@ -3104,6 +3088,21 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 	int err;
 
 	xhci = hcd_to_xhci(hcd);
+	ep_index = xhci_get_endpoint_index(&host_ep->desc);
+
+	/*
+	 * Usb core assumes a max packet value for ep0 on FS devices until the
+	 * real value is read from the descriptor. Core resets Ep0 if values
+	 * mismatch. Reconfigure the xhci ep0 endpoint context here in that case
+	 */
+	if (usb_endpoint_xfer_control(&host_ep->desc) && ep_index == 0) {
+		udev = container_of(host_ep, struct usb_device, ep0);
+		if (udev->speed == USB_SPEED_FULL)
+			xhci_check_ep0_maxpacket(xhci, xhci->devs[udev->slot_id]);
+		/* Nothing else should be done here for ep0 during ep reset */
+		return;
+	}
+
 	if (!host_ep->hcpriv)
 		return;
 	udev = (struct usb_device *) host_ep->hcpriv;
@@ -3116,7 +3115,7 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 	 */
 	if (!udev->slot_id || !vdev)
 		return;
-	ep_index = xhci_get_endpoint_index(&host_ep->desc);
+
 	ep = &vdev->eps[ep_index];
 
 	/* Bail out if toggle is already being cleared by a endpoint reset */
-- 
GitLab


From e2e2aacf042f52854c92775b7800ba668e0bdfe4 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 1 Dec 2023 17:06:47 +0200
Subject: [PATCH 0687/4076] xhci: fix possible null pointer deref during xhci
 urb enqueue

There is a short gap between urb being submitted and actually added to the
endpoint queue (linked). If the device is disconnected during this time
then usb core is not yet aware of the pending urb, and device may be freed
just before xhci_urq_enqueue() continues, dereferencing the freed device.

Freeing the device is protected by the xhci spinlock, so make sure we take
and keep the lock while checking that device exists, dereference it, and
add the urb to the queue.

Remove the unnecessary URB check, usb core checks it before calling
xhci_urb_enqueue()

Suggested-by: Kuen-Han Tsai <khtsai@google.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231201150647.1307406-20-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 40 +++++++++++++++++++++++-----------------
 1 file changed, 23 insertions(+), 17 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 71a117db21a7a..08fbabff23a05 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1521,24 +1521,7 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
 	struct urb_priv	*urb_priv;
 	int num_tds;
 
-	if (!urb)
-		return -EINVAL;
-	ret = xhci_check_args(hcd, urb->dev, urb->ep,
-					true, true, __func__);
-	if (ret <= 0)
-		return ret ? ret : -EINVAL;
-
-	slot_id = urb->dev->slot_id;
 	ep_index = xhci_get_endpoint_index(&urb->ep->desc);
-	ep_state = &xhci->devs[slot_id]->eps[ep_index].ep_state;
-
-	if (!HCD_HW_ACCESSIBLE(hcd))
-		return -ESHUTDOWN;
-
-	if (xhci->devs[slot_id]->flags & VDEV_PORT_ERROR) {
-		xhci_dbg(xhci, "Can't queue urb, port error, link inactive\n");
-		return -ENODEV;
-	}
 
 	if (usb_endpoint_xfer_isoc(&urb->ep->desc))
 		num_tds = urb->number_of_packets;
@@ -1562,12 +1545,35 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
 
 	spin_lock_irqsave(&xhci->lock, flags);
 
+	ret = xhci_check_args(hcd, urb->dev, urb->ep,
+			      true, true, __func__);
+	if (ret <= 0) {
+		ret = ret ? ret : -EINVAL;
+		goto free_priv;
+	}
+
+	slot_id = urb->dev->slot_id;
+
+	if (!HCD_HW_ACCESSIBLE(hcd)) {
+		ret = -ESHUTDOWN;
+		goto free_priv;
+	}
+
+	if (xhci->devs[slot_id]->flags & VDEV_PORT_ERROR) {
+		xhci_dbg(xhci, "Can't queue urb, port error, link inactive\n");
+		ret = -ENODEV;
+		goto free_priv;
+	}
+
 	if (xhci->xhc_state & XHCI_STATE_DYING) {
 		xhci_dbg(xhci, "Ep 0x%x: URB %p submitted for non-responsive xHCI host.\n",
 			 urb->ep->desc.bEndpointAddress, urb);
 		ret = -ESHUTDOWN;
 		goto free_priv;
 	}
+
+	ep_state = &xhci->devs[slot_id]->eps[ep_index].ep_state;
+
 	if (*ep_state & (EP_GETTING_STREAMS | EP_GETTING_NO_STREAMS)) {
 		xhci_warn(xhci, "WARN: Can't enqueue URB, ep in streams transition state %x\n",
 			  *ep_state);
-- 
GitLab


From d9443ac5e3ba1991863c61a4e89f04f67f104eca Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 28 Nov 2023 13:17:25 -0500
Subject: [PATCH 0688/4076] staging: rtl8192e: renamed variable nMcsRate

Coding style issue, checkpatch Avoid CamelCase,
rename it nMcsRate -> mcs_rate.

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231128181727.19504-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 00273d709f3c4..4ed72936eb4ae 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -103,7 +103,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->rx_reorder_pending_time = 30;
 }
 
-static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 nMcsRate)
+static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 mcs_rate)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
@@ -111,7 +111,7 @@ static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 nMcsRate)
 	u8	isShortGI = (ht_info->bCurBW40MHz) ?
 			    ((ht_info->bCurShortGI40MHz) ? 1 : 0) :
 			    ((ht_info->bCurShortGI20MHz) ? 1 : 0);
-	return MCS_DATA_RATE[is40MHz][isShortGI][(nMcsRate & 0x7f)];
+	return MCS_DATA_RATE[is40MHz][isShortGI][(mcs_rate & 0x7f)];
 }
 
 u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate)
-- 
GitLab


From 213702c8b61bfc37b9a78a977fb1c4871fee938c Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 28 Nov 2023 13:17:26 -0500
Subject: [PATCH 0689/4076] staging: rtl8192e: renamed variable bCurBW40MHz

Coding style issue, checkpatch Avoid CamelCase,
rename it bCurBW40MHz -> cur_bw_40mhz.

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231128181727.19504-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h        |  2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c    | 16 ++++++++--------
 drivers/staging/rtl8192e/rtllib_softmac_wx.c |  4 ++--
 drivers/staging/rtl8192e/rtllib_tx.c         | 10 +++++-----
 4 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index a4fe72943b367..dd86faab6f53f 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -95,7 +95,7 @@ struct rt_hi_throughput {
 	u8 enable_ht;
 	u8 current_ht_support;
 	u8 bRegBW40MHz;
-	u8 bCurBW40MHz;
+	u8 cur_bw_40mhz;
 	u8 bRegShortGI40MHz;
 	u8 bCurShortGI40MHz;
 	u8 bRegShortGI20MHz;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 4ed72936eb4ae..87e96f2abed03 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -107,8 +107,8 @@ static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 mcs_rate)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	u8	is40MHz = (ht_info->bCurBW40MHz) ? 1 : 0;
-	u8	isShortGI = (ht_info->bCurBW40MHz) ?
+	u8	is40MHz = (ht_info->cur_bw_40mhz) ? 1 : 0;
+	u8	isShortGI = (ht_info->cur_bw_40mhz) ?
 			    ((ht_info->bCurShortGI40MHz) ? 1 : 0) :
 			    ((ht_info->bCurShortGI20MHz) ? 1 : 0);
 	return MCS_DATA_RATE[is40MHz][isShortGI][(mcs_rate & 0x7f)];
@@ -559,7 +559,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 
 	ht_info->current_ht_support = false;
 
-	ht_info->bCurBW40MHz = false;
+	ht_info->cur_bw_40mhz = false;
 	ht_info->cur_tx_bw40mhz = false;
 
 	ht_info->bCurShortGI20MHz = false;
@@ -705,7 +705,7 @@ static void HTSetConnectBwModeCallback(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	if (ht_info->bCurBW40MHz) {
+	if (ht_info->cur_bw_40mhz) {
 		if (ht_info->CurSTAExtChnlOffset == HT_EXTCHNL_OFFSET_UPPER)
 			ieee->set_chan(ieee->dev,
 				       ieee->current_network.channel + 2);
@@ -750,19 +750,19 @@ void HTSetConnectBwMode(struct rtllib_device *ieee,
 			Offset = HT_EXTCHNL_OFFSET_NO_EXT;
 		if (Offset == HT_EXTCHNL_OFFSET_UPPER ||
 		    Offset == HT_EXTCHNL_OFFSET_LOWER) {
-			ht_info->bCurBW40MHz = true;
+			ht_info->cur_bw_40mhz = true;
 			ht_info->CurSTAExtChnlOffset = Offset;
 		} else {
-			ht_info->bCurBW40MHz = false;
+			ht_info->cur_bw_40mhz = false;
 			ht_info->CurSTAExtChnlOffset = HT_EXTCHNL_OFFSET_NO_EXT;
 		}
 	} else {
-		ht_info->bCurBW40MHz = false;
+		ht_info->cur_bw_40mhz = false;
 		ht_info->CurSTAExtChnlOffset = HT_EXTCHNL_OFFSET_NO_EXT;
 	}
 
 	netdev_dbg(ieee->dev, "%s():ht_info->bCurBW40MHz:%x\n", __func__,
-		   ht_info->bCurBW40MHz);
+		   ht_info->cur_bw_40mhz);
 
 	ht_info->sw_bw_in_progress = true;
 
diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
index 28aba1d610f7d..b48c89d2e7bf7 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
@@ -318,10 +318,10 @@ void rtllib_wx_sync_scan_wq(void *data)
 	ieee->ScanOperationBackupHandler(ieee->dev, SCAN_OPT_BACKUP);
 
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht &&
-	    ieee->ht_info->bCurBW40MHz) {
+	    ieee->ht_info->cur_bw_40mhz) {
 		b40M = 1;
 		chan_offset = ieee->ht_info->CurSTAExtChnlOffset;
-		bandwidth = (enum ht_channel_width)ieee->ht_info->bCurBW40MHz;
+		bandwidth = (enum ht_channel_width)ieee->ht_info->cur_bw_40mhz;
 		ieee->set_bw_mode_handler(ieee->dev, HT_CHANNEL_WIDTH_20,
 				       HT_EXTCHNL_OFFSET_NO_EXT);
 	}
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 92e5be85148ee..1468bbf1e23af 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -362,9 +362,9 @@ static void rtllib_query_HTCapShortGI(struct rtllib_device *ieee,
 		return;
 	}
 
-	if (ht_info->bCurBW40MHz && ht_info->bCurShortGI40MHz)
+	if (ht_info->cur_bw_40mhz && ht_info->bCurShortGI40MHz)
 		tcb_desc->bUseShortGI = true;
-	else if (!ht_info->bCurBW40MHz && ht_info->bCurShortGI20MHz)
+	else if (!ht_info->cur_bw_40mhz && ht_info->bCurShortGI20MHz)
 		tcb_desc->bUseShortGI = true;
 }
 
@@ -383,7 +383,7 @@ static void rtllib_query_BandwidthMode(struct rtllib_device *ieee,
 
 	if ((tcb_desc->data_rate & 0x80) == 0)
 		return;
-	if (ht_info->bCurBW40MHz && ht_info->cur_tx_bw40mhz &&
+	if (ht_info->cur_bw_40mhz && ht_info->cur_tx_bw40mhz &&
 	    !ieee->bandwidth_auto_switch.bforced_tx20Mhz)
 		tcb_desc->bPacketBW = true;
 }
@@ -441,9 +441,9 @@ static void rtllib_query_protectionmode(struct rtllib_device *ieee,
 		if (ht_info->current_ht_support && ht_info->enable_ht) {
 			u8 HTOpMode = ht_info->current_op_mode;
 
-			if ((ht_info->bCurBW40MHz && (HTOpMode == 2 ||
+			if ((ht_info->cur_bw_40mhz && (HTOpMode == 2 ||
 						      HTOpMode == 3)) ||
-			     (!ht_info->bCurBW40MHz && HTOpMode == 3)) {
+			     (!ht_info->cur_bw_40mhz && HTOpMode == 3)) {
 				tcb_desc->rts_rate = MGN_24M;
 				tcb_desc->bRTSEnable = true;
 				break;
-- 
GitLab


From ad96610acc0eb81f0342fa688e6d42fd530c328b Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 28 Nov 2023 13:17:27 -0500
Subject: [PATCH 0690/4076] staging: rtl8192e: renamed variable nDataRate

Coding style issue, checkpatch Avoid CamelCase,
rename it nDataRate -> data-rate.

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231128181727.19504-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 87e96f2abed03..f263f329db77a 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -114,29 +114,29 @@ static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 mcs_rate)
 	return MCS_DATA_RATE[is40MHz][isShortGI][(mcs_rate & 0x7f)];
 }
 
-u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate)
+u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 data_rate)
 {
 	u16	CCKOFDMRate[12] = {0x02, 0x04, 0x0b, 0x16, 0x0c, 0x12, 0x18,
 				   0x24, 0x30, 0x48, 0x60, 0x6c};
 	u8	is40MHz = 0;
 	u8	isShortGI = 0;
 
-	if (nDataRate < 12)
-		return CCKOFDMRate[nDataRate];
-	if (nDataRate >= 0x10 && nDataRate <= 0x1f) {
+	if (data_rate < 12)
+		return CCKOFDMRate[data_rate];
+	if (data_rate >= 0x10 && data_rate <= 0x1f) {
 		is40MHz = 0;
 		isShortGI = 0;
-	} else if (nDataRate >= 0x20  && nDataRate <= 0x2f) {
+	} else if (data_rate >= 0x20  && data_rate <= 0x2f) {
 		is40MHz = 1;
 		isShortGI = 0;
-	} else if (nDataRate >= 0x30  && nDataRate <= 0x3f) {
+	} else if (data_rate >= 0x30  && data_rate <= 0x3f) {
 		is40MHz = 0;
 		isShortGI = 1;
-	} else if (nDataRate >= 0x40  && nDataRate <= 0x4f) {
+	} else if (data_rate >= 0x40  && data_rate <= 0x4f) {
 		is40MHz = 1;
 		isShortGI = 1;
 	}
-	return MCS_DATA_RATE[is40MHz][isShortGI][nDataRate & 0xf];
+	return MCS_DATA_RATE[is40MHz][isShortGI][data_rate & 0xf];
 }
 
 bool is_ht_half_nmode_aps(struct rtllib_device *ieee)
-- 
GitLab


From f9c42898830383aff4fdc723828fa93a6abec02d Mon Sep 17 00:00:00 2001
From: Umang Jain <umang.jain@ideasonboard.com>
Date: Wed, 29 Nov 2023 01:48:45 +0530
Subject: [PATCH 0691/4076] staging: vc04_services: vchiq_core: Log through
 struct vchiq_instance

The handle_to_service() helper can return NULL, so `service` pointer
can indeed be set to NULL. So, do not log through service pointer
(which can cause NULL-deference), instead, use the vchiq_instance
function argument to get access to the struct device.

Fixes: f67af5940d6d ("staging: vc04: Convert(and rename) vchiq_log_info() to use dynamic debug")
Reviewed-by: Ricardo B. Marliere <ricardo@marliere.net>
Signed-off-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/20231128201845.489237-1-umang.jain@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../staging/vc04_services/interface/vchiq_arm/vchiq_core.c  | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index 0468689a6325b..e0022acb4c585 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -245,7 +245,7 @@ find_service_by_handle(struct vchiq_instance *instance, unsigned int handle)
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE,
+	vchiq_log_debug(instance->state->dev, VCHIQ_CORE,
 			"Invalid service handle 0x%x", handle);
 	return NULL;
 }
@@ -287,7 +287,7 @@ find_service_for_instance(struct vchiq_instance *instance, unsigned int handle)
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE,
+	vchiq_log_debug(instance->state->dev, VCHIQ_CORE,
 			"Invalid service handle 0x%x", handle);
 	return NULL;
 }
@@ -310,7 +310,7 @@ find_closed_service_for_instance(struct vchiq_instance *instance, unsigned int h
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE,
+	vchiq_log_debug(instance->state->dev, VCHIQ_CORE,
 			"Invalid service handle 0x%x", handle);
 	return service;
 }
-- 
GitLab


From 149261d378d0ca441b16de6c1a250a350df66598 Mon Sep 17 00:00:00 2001
From: Umang Jain <umang.jain@ideasonboard.com>
Date: Wed, 29 Nov 2023 01:49:22 +0530
Subject: [PATCH 0692/4076] staging: vc04_services: Do not pass NULL to
 vchiq_log_error()

vchiq_add_connected_callback() logs using vchiq_log_error() macro,
but passes NULL instead of a struct device pointer. Fix it.

vchiq_add_connected_callback() is not used anywhere in the vc04_services
as of now. It will be used when we add new drivers(VC shared memory and
bcm2835-isp), hence it kept as it is for now.

Fixes: 1d8915cf8899 ("staging: vc04: Convert vchiq_log_error() to use dynamic debug")
Signed-off-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/20231128201926.489269-2-umang.jain@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../vc04_services/interface/vchiq_arm/vchiq_connected.c       | 4 ++--
 .../vc04_services/interface/vchiq_arm/vchiq_connected.h       | 4 +++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
index b3928bd8c9c60..21f9fa1a17132 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
@@ -27,7 +27,7 @@ static void connected_init(void)
  * be made immediately, otherwise it will be deferred until
  * vchiq_call_connected_callbacks is called.
  */
-void vchiq_add_connected_callback(void (*callback)(void))
+void vchiq_add_connected_callback(struct vchiq_device *device, void (*callback)(void))
 {
 	connected_init();
 
@@ -39,7 +39,7 @@ void vchiq_add_connected_callback(void (*callback)(void))
 		callback();
 	} else {
 		if (g_num_deferred_callbacks >= MAX_CALLBACKS) {
-			vchiq_log_error(NULL, VCHIQ_CORE,
+			vchiq_log_error(&device->dev, VCHIQ_CORE,
 					"There already %d callback registered - please increase MAX_CALLBACKS",
 					g_num_deferred_callbacks);
 		} else {
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.h
index 4caf5e30099dc..e4ed56446f8ad 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.h
@@ -1,10 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /* Copyright (c) 2010-2012 Broadcom. All rights reserved. */
 
+#include "vchiq_bus.h"
+
 #ifndef VCHIQ_CONNECTED_H
 #define VCHIQ_CONNECTED_H
 
-void vchiq_add_connected_callback(void (*callback)(void));
+void vchiq_add_connected_callback(struct vchiq_device *device, void (*callback)(void));
 void vchiq_call_connected_callbacks(void);
 
 #endif /* VCHIQ_CONNECTED_H */
-- 
GitLab


From f2dd716cb44ad97fcaa757687ebd8d66cced7536 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 29 Nov 2023 12:10:41 +0100
Subject: [PATCH 0693/4076] dt-bindings: iio: honeywell,mprls0025pa: drop ref
 from pressure properties

The dtschema treats now properties with '-pascal' suffix as standard one
and already defines $ref for them, thus the $ref should be dropped from
the bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231129111041.26782-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml | 2 --
 1 file changed, 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml b/Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml
index b31f8120f14ed..d9e903fbfd99e 100644
--- a/Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml
+++ b/Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml
@@ -53,12 +53,10 @@ properties:
   honeywell,pmin-pascal:
     description:
       Minimum pressure value the sensor can measure in pascal.
-    $ref: /schemas/types.yaml#/definitions/uint32
 
   honeywell,pmax-pascal:
     description:
       Maximum pressure value the sensor can measure in pascal.
-    $ref: /schemas/types.yaml#/definitions/uint32
 
   honeywell,transfer-function:
     description: |
-- 
GitLab


From e66523c72c9aae0ff0dae6859eb77b04de1e8e5f Mon Sep 17 00:00:00 2001
From: Yaxiong Tian <tianyaxiong@kylinos.cn>
Date: Fri, 24 Nov 2023 09:49:13 +0800
Subject: [PATCH 0694/4076] extcon: fix possible name leak in
 extcon_dev_register()

In the error path after calling dev_set_name(), the device
name is leaked. To fix this, moving dev_set_name() after the
error path and before device_register.

Link: https://lore.kernel.org/lkml/TYZPR01MB4784ADCD3E951E0863F3DB72D5B8A@TYZPR01MB4784.apcprd01.prod.exchangelabs.com/
Signed-off-by: Yaxiong Tian <tianyaxiong@kylinos.cn>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/extcon/extcon.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 6f7a60d2ed916..e7f55c021e562 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -1280,8 +1280,6 @@ int extcon_dev_register(struct extcon_dev *edev)
 
 	edev->id = ret;
 
-	dev_set_name(&edev->dev, "extcon%d", edev->id);
-
 	ret = extcon_alloc_cables(edev);
 	if (ret < 0)
 		goto err_alloc_cables;
@@ -1310,6 +1308,7 @@ int extcon_dev_register(struct extcon_dev *edev)
 	RAW_INIT_NOTIFIER_HEAD(&edev->nh_all);
 
 	dev_set_drvdata(&edev->dev, edev);
+	dev_set_name(&edev->dev, "extcon%d", edev->id);
 	edev->state = 0;
 
 	ret = device_register(&edev->dev);
-- 
GitLab


From d49f69425d0db21c80c11ee537220658262bb7f4 Mon Sep 17 00:00:00 2001
From: Michael Hennerich <michael.hennerich@analog.com>
Date: Wed, 29 Nov 2023 14:03:52 +0100
Subject: [PATCH 0695/4076] dt-bindings: adi,ad5791: Add support for
 controlling RBUF

Added new property to support an external amplifier to be connected in a
gain of two configuration.

Signed-off-by: Michael Hennerich <michael.hennerich@analog.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231129-ad5791-michael-stuff-v3-1-48e192b00909@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
index 3a84739736f62..c81285d84db7a 100644
--- a/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
@@ -26,6 +26,11 @@ properties:
   vdd-supply: true
   vss-supply: true
 
+  adi,rbuf-gain2-en:
+    description: Specify to allow an external amplifier to be connected in a
+      gain of two configuration.
+    type: boolean
+
 required:
   - compatible
   - reg
-- 
GitLab


From e737d495b207592106b38449cc9f402133456062 Mon Sep 17 00:00:00 2001
From: Michael Hennerich <michael.hennerich@analog.com>
Date: Wed, 29 Nov 2023 14:03:53 +0100
Subject: [PATCH 0696/4076] iio: dac: ad5791: Add support for controlling RBUF
 via devicetree

This patch adds support for an external amplifier to be connected in a
gain of two configuration.

Signed-off-by: Michael Hennerich <michael.hennerich@analog.com>
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231129-ad5791-michael-stuff-v3-2-48e192b00909@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dac/ad5791.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/dac/ad5791.c b/drivers/iio/dac/ad5791.c
index a4167454da818..75b549827e15a 100644
--- a/drivers/iio/dac/ad5791.c
+++ b/drivers/iio/dac/ad5791.c
@@ -345,6 +345,7 @@ static int ad5791_probe(struct spi_device *spi)
 	struct iio_dev *indio_dev;
 	struct ad5791_state *st;
 	int ret, pos_voltage_uv = 0, neg_voltage_uv = 0;
+	bool use_rbuf_gain2;
 
 	indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st));
 	if (!indio_dev)
@@ -379,6 +380,12 @@ static int ad5791_probe(struct spi_device *spi)
 	st->pwr_down = true;
 	st->spi = spi;
 
+	if (pdata)
+		use_rbuf_gain2 = pdata->use_rbuf_gain2;
+	else
+		use_rbuf_gain2 = device_property_read_bool(&spi->dev,
+							   "adi,rbuf-gain2-en");
+
 	if (!IS_ERR(st->reg_vss) && !IS_ERR(st->reg_vdd)) {
 		st->vref_mv = (pos_voltage_uv + neg_voltage_uv) / 1000;
 		st->vref_neg_mv = neg_voltage_uv / 1000;
@@ -398,7 +405,7 @@ static int ad5791_probe(struct spi_device *spi)
 
 
 	st->ctrl = AD5761_CTRL_LINCOMP(st->chip_info->get_lin_comp(st->vref_mv))
-		  | ((pdata && pdata->use_rbuf_gain2) ? 0 : AD5791_CTRL_RBUF) |
+		  | (use_rbuf_gain2 ? 0 : AD5791_CTRL_RBUF) |
 		  AD5791_CTRL_BIN2SC;
 
 	ret = ad5791_spi_write(st, AD5791_ADDR_CTRL, st->ctrl |
-- 
GitLab


From a61b9a40d67cfe7b79525ad3c3cff19938c5416f Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 28 Nov 2023 15:48:02 -0600
Subject: [PATCH 0697/4076] dt-bindings: iio/adc: ti,palmas-gpadc: Drop
 incomplete example

The example for the TI Palmas ADC is incomplete as the binding is the
full PMIC, not just the sub-functions. It is preferred for MFD examples
to be complete in the top-level MFD device binding rather than piecemeal
in each sub-function binding.

This also fixes an undocumented (by schema) compatible warning for
'"ti,twl6035-pmic", "ti,palmas-pmic"'.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231128214803.3975542-1-robh@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/adc/ti,palmas-gpadc.yaml         | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml b/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml
index 720c16a108d4e..f94057d8f6058 100644
--- a/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml
@@ -67,19 +67,4 @@ required:
   - compatible
   - "#io-channel-cells"
 
-examples:
-  - |
-    #include <dt-bindings/clock/mt8183-clk.h>
-    pmic {
-        compatible = "ti,twl6035-pmic", "ti,palmas-pmic";
-        adc {
-            compatible = "ti,palmas-gpadc";
-            interrupts = <18 0>,
-                         <16 0>,
-                         <17 0>;
-            #io-channel-cells = <1>;
-            ti,channel0-current-microamp = <5>;
-            ti,channel3-current-microamp = <10>;
-        };
-    };
 ...
-- 
GitLab


From ad662c6dbd7aee3ecece6d604a93d8e84851ea17 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 28 Nov 2023 23:56:32 +0100
Subject: [PATCH 0698/4076] iio: proximity: irsd200: Drop unused include

The driver includes the legacy GPIO header <linux/gpio.h> but doesn't
use any symbols from it. Drop it.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Waqar Hameed <waqar.hameed@axis.com>
Link: https://lore.kernel.org/r/20231128-descriptors-iio-v1-1-da1e94755db6@linaro.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/irsd200.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/iio/proximity/irsd200.c b/drivers/iio/proximity/irsd200.c
index bdff91f6b1a37..323ac6dac90e1 100644
--- a/drivers/iio/proximity/irsd200.c
+++ b/drivers/iio/proximity/irsd200.c
@@ -7,7 +7,6 @@
 
 #include <asm/unaligned.h>
 #include <linux/bitfield.h>
-#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/regmap.h>
-- 
GitLab


From 36d8aef52d0562b5b1dc2e54d0fad1dee07182c2 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Thu, 30 Nov 2023 10:54:35 +0000
Subject: [PATCH 0699/4076] usb: atm: Remove snprintf() from sysfs call-backs
 and replace with sysfs_emit()

Since snprintf() has the documented, but still rather strange trait of
returning the length of the data that *would have been* written to the
array if space were available, rather than the arguably more useful
length of data *actually* written, it is usually considered wise to use
something else instead in order to avoid confusion.

In the case of sysfs call-backs, new wrappers exist that do just that.

This patch replaces the 2 uses of snprintf() found in the sysfs .show()
call-backs with the new sysfs_emit() helpers.  Whist we're at it, let's
replace the sprintf()s as well.  For no other reason than consistency.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Matthieu CASTET <castet.matthieu@free.fr>
Cc: Stanislaw Gruszka <stf_xl@wp.pl>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Damien Bergamini <damien.bergamini@free.fr>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231130105459.3208986-2-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/atm/ueagle-atm.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c
index 5812f7ea7f902..8d5580d8d20a8 100644
--- a/drivers/usb/atm/ueagle-atm.c
+++ b/drivers/usb/atm/ueagle-atm.c
@@ -2252,7 +2252,7 @@ static ssize_t stat_status_show(struct device *dev, struct device_attribute *att
 	sc = dev_to_uea(dev);
 	if (!sc)
 		goto out;
-	ret = snprintf(buf, 10, "%08x\n", sc->stats.phy.state);
+	ret = sysfs_emit(buf, "%08x\n", sc->stats.phy.state);
 out:
 	mutex_unlock(&uea_mutex);
 	return ret;
@@ -2318,19 +2318,19 @@ static ssize_t stat_human_status_show(struct device *dev,
 
 	switch (modem_state) {
 	case 0:
-		ret = sprintf(buf, "Modem is booting\n");
+		ret = sysfs_emit(buf, "Modem is booting\n");
 		break;
 	case 1:
-		ret = sprintf(buf, "Modem is initializing\n");
+		ret = sysfs_emit(buf, "Modem is initializing\n");
 		break;
 	case 2:
-		ret = sprintf(buf, "Modem is operational\n");
+		ret = sysfs_emit(buf, "Modem is operational\n");
 		break;
 	case 3:
-		ret = sprintf(buf, "Modem synchronization failed\n");
+		ret = sysfs_emit(buf, "Modem synchronization failed\n");
 		break;
 	default:
-		ret = sprintf(buf, "Modem state is unknown\n");
+		ret = sysfs_emit(buf, "Modem state is unknown\n");
 		break;
 	}
 out:
@@ -2364,7 +2364,7 @@ static ssize_t stat_delin_show(struct device *dev, struct device_attribute *attr
 			delin = "LOSS";
 	}
 
-	ret = sprintf(buf, "%s\n", delin);
+	ret = sysfs_emit(buf, "%s\n", delin);
 out:
 	mutex_unlock(&uea_mutex);
 	return ret;
@@ -2384,7 +2384,7 @@ static ssize_t stat_##name##_show(struct device *dev,		\
 	sc = dev_to_uea(dev);					\
 	if (!sc)						\
 		goto out;					\
-	ret = snprintf(buf, 10, "%08x\n", sc->stats.phy.name);	\
+	ret = sysfs_emit(buf, "%08x\n", sc->stats.phy.name);	\
 	if (reset)						\
 		sc->stats.phy.name = 0;				\
 out:								\
-- 
GitLab


From b385ef088c7aab20a2c0dc20d390d69a6620f0f3 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Thu, 30 Nov 2023 10:54:36 +0000
Subject: [PATCH 0700/4076] usb: cdnsp: Replace snprintf() with the safer
 scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

The uses in this file all seem to assume that data *has been* written!

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Pawel Laszczak <pawell@cadence.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231130105459.3208986-3-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdnsp-debug.h | 354 ++++++++++++++++----------------
 1 file changed, 177 insertions(+), 177 deletions(-)

diff --git a/drivers/usb/cdns3/cdnsp-debug.h b/drivers/usb/cdns3/cdnsp-debug.h
index ad617b7455b9c..cd138acdcce16 100644
--- a/drivers/usb/cdns3/cdnsp-debug.h
+++ b/drivers/usb/cdns3/cdnsp-debug.h
@@ -187,202 +187,202 @@ static inline const char *cdnsp_decode_trb(char *str, size_t size, u32 field0,
 
 	switch (type) {
 	case TRB_LINK:
-		ret = snprintf(str, size,
-			       "LINK %08x%08x intr %ld type '%s' flags %c:%c:%c:%c",
-			       field1, field0, GET_INTR_TARGET(field2),
-			       cdnsp_trb_type_string(type),
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CHAIN ? 'C' : 'c',
-			       field3 & TRB_TC ? 'T' : 't',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"LINK %08x%08x intr %ld type '%s' flags %c:%c:%c:%c",
+				field1, field0, GET_INTR_TARGET(field2),
+				cdnsp_trb_type_string(type),
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CHAIN ? 'C' : 'c',
+				field3 & TRB_TC ? 'T' : 't',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_TRANSFER:
 	case TRB_COMPLETION:
 	case TRB_PORT_STATUS:
 	case TRB_HC_EVENT:
-		ret = snprintf(str, size,
-			       "ep%d%s(%d) type '%s' TRB %08x%08x status '%s'"
-			       " len %ld slot %ld flags %c:%c",
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3),
-			       cdnsp_trb_type_string(type), field1, field0,
-			       cdnsp_trb_comp_code_string(GET_COMP_CODE(field2)),
-			       EVENT_TRB_LEN(field2), TRB_TO_SLOT_ID(field3),
-			       field3 & EVENT_DATA ? 'E' : 'e',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"ep%d%s(%d) type '%s' TRB %08x%08x status '%s'"
+				" len %ld slot %ld flags %c:%c",
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3),
+				cdnsp_trb_type_string(type), field1, field0,
+				cdnsp_trb_comp_code_string(GET_COMP_CODE(field2)),
+				EVENT_TRB_LEN(field2), TRB_TO_SLOT_ID(field3),
+				field3 & EVENT_DATA ? 'E' : 'e',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_MFINDEX_WRAP:
-		ret = snprintf(str, size, "%s: flags %c",
-			       cdnsp_trb_type_string(type),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size, "%s: flags %c",
+				cdnsp_trb_type_string(type),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_SETUP:
-		ret = snprintf(str, size,
-			       "type '%s' bRequestType %02x bRequest %02x "
-			       "wValue %02x%02x wIndex %02x%02x wLength %d "
-			       "length %ld TD size %ld intr %ld Setup ID %ld "
-			       "flags %c:%c:%c",
-			       cdnsp_trb_type_string(type),
-			       field0 & 0xff,
-			       (field0 & 0xff00) >> 8,
-			       (field0 & 0xff000000) >> 24,
-			       (field0 & 0xff0000) >> 16,
-			       (field1 & 0xff00) >> 8,
-			       field1 & 0xff,
-			       (field1 & 0xff000000) >> 16 |
-			       (field1 & 0xff0000) >> 16,
-			       TRB_LEN(field2), GET_TD_SIZE(field2),
-			       GET_INTR_TARGET(field2),
-			       TRB_SETUPID_TO_TYPE(field3),
-			       field3 & TRB_IDT ? 'D' : 'd',
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"type '%s' bRequestType %02x bRequest %02x "
+				"wValue %02x%02x wIndex %02x%02x wLength %d "
+				"length %ld TD size %ld intr %ld Setup ID %ld "
+				"flags %c:%c:%c",
+				cdnsp_trb_type_string(type),
+				field0 & 0xff,
+				(field0 & 0xff00) >> 8,
+				(field0 & 0xff000000) >> 24,
+				(field0 & 0xff0000) >> 16,
+				(field1 & 0xff00) >> 8,
+				field1 & 0xff,
+				(field1 & 0xff000000) >> 16 |
+				(field1 & 0xff0000) >> 16,
+				TRB_LEN(field2), GET_TD_SIZE(field2),
+				GET_INTR_TARGET(field2),
+				TRB_SETUPID_TO_TYPE(field3),
+				field3 & TRB_IDT ? 'D' : 'd',
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_DATA:
-		ret = snprintf(str, size,
-			       "type '%s' Buffer %08x%08x length %ld TD size %ld "
-			       "intr %ld flags %c:%c:%c:%c:%c:%c:%c",
-			       cdnsp_trb_type_string(type),
-			       field1, field0, TRB_LEN(field2),
-			       GET_TD_SIZE(field2),
-			       GET_INTR_TARGET(field2),
-			       field3 & TRB_IDT ? 'D' : 'i',
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CHAIN ? 'C' : 'c',
-			       field3 & TRB_NO_SNOOP ? 'S' : 's',
-			       field3 & TRB_ISP ? 'I' : 'i',
-			       field3 & TRB_ENT ? 'E' : 'e',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"type '%s' Buffer %08x%08x length %ld TD size %ld "
+				"intr %ld flags %c:%c:%c:%c:%c:%c:%c",
+				cdnsp_trb_type_string(type),
+				field1, field0, TRB_LEN(field2),
+				GET_TD_SIZE(field2),
+				GET_INTR_TARGET(field2),
+				field3 & TRB_IDT ? 'D' : 'i',
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CHAIN ? 'C' : 'c',
+				field3 & TRB_NO_SNOOP ? 'S' : 's',
+				field3 & TRB_ISP ? 'I' : 'i',
+				field3 & TRB_ENT ? 'E' : 'e',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_STATUS:
-		ret = snprintf(str, size,
-			       "Buffer %08x%08x length %ld TD size %ld intr"
-			       "%ld type '%s' flags %c:%c:%c:%c",
-			       field1, field0, TRB_LEN(field2),
-			       GET_TD_SIZE(field2),
-			       GET_INTR_TARGET(field2),
-			       cdnsp_trb_type_string(type),
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CHAIN ? 'C' : 'c',
-			       field3 & TRB_ENT ? 'E' : 'e',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"Buffer %08x%08x length %ld TD size %ld intr"
+				"%ld type '%s' flags %c:%c:%c:%c",
+				field1, field0, TRB_LEN(field2),
+				GET_TD_SIZE(field2),
+				GET_INTR_TARGET(field2),
+				cdnsp_trb_type_string(type),
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CHAIN ? 'C' : 'c',
+				field3 & TRB_ENT ? 'E' : 'e',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_NORMAL:
 	case TRB_ISOC:
 	case TRB_EVENT_DATA:
 	case TRB_TR_NOOP:
-		ret = snprintf(str, size,
-			       "type '%s' Buffer %08x%08x length %ld "
-			       "TD size %ld intr %ld "
-			       "flags %c:%c:%c:%c:%c:%c:%c:%c:%c",
-			       cdnsp_trb_type_string(type),
-			       field1, field0, TRB_LEN(field2),
-			       GET_TD_SIZE(field2),
-			       GET_INTR_TARGET(field2),
-			       field3 & TRB_BEI ? 'B' : 'b',
-			       field3 & TRB_IDT ? 'T' : 't',
-			       field3 & TRB_IOC ? 'I' : 'i',
-			       field3 & TRB_CHAIN ? 'C' : 'c',
-			       field3 & TRB_NO_SNOOP ? 'S' : 's',
-			       field3 & TRB_ISP ? 'I' : 'i',
-			       field3 & TRB_ENT ? 'E' : 'e',
-			       field3 & TRB_CYCLE ? 'C' : 'c',
-			       !(field3 & TRB_EVENT_INVALIDATE) ? 'V' : 'v');
+		ret = scnprintf(str, size,
+				"type '%s' Buffer %08x%08x length %ld "
+				"TD size %ld intr %ld "
+				"flags %c:%c:%c:%c:%c:%c:%c:%c:%c",
+				cdnsp_trb_type_string(type),
+				field1, field0, TRB_LEN(field2),
+				GET_TD_SIZE(field2),
+				GET_INTR_TARGET(field2),
+				field3 & TRB_BEI ? 'B' : 'b',
+				field3 & TRB_IDT ? 'T' : 't',
+				field3 & TRB_IOC ? 'I' : 'i',
+				field3 & TRB_CHAIN ? 'C' : 'c',
+				field3 & TRB_NO_SNOOP ? 'S' : 's',
+				field3 & TRB_ISP ? 'I' : 'i',
+				field3 & TRB_ENT ? 'E' : 'e',
+				field3 & TRB_CYCLE ? 'C' : 'c',
+				!(field3 & TRB_EVENT_INVALIDATE) ? 'V' : 'v');
 		break;
 	case TRB_CMD_NOOP:
 	case TRB_ENABLE_SLOT:
-		ret = snprintf(str, size, "%s: flags %c",
-			       cdnsp_trb_type_string(type),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size, "%s: flags %c",
+				cdnsp_trb_type_string(type),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_DISABLE_SLOT:
-		ret = snprintf(str, size, "%s: slot %ld flags %c",
-			       cdnsp_trb_type_string(type),
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size, "%s: slot %ld flags %c",
+				cdnsp_trb_type_string(type),
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_ADDR_DEV:
-		ret = snprintf(str, size,
-			       "%s: ctx %08x%08x slot %ld flags %c:%c",
-			       cdnsp_trb_type_string(type), field1, field0,
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_BSR ? 'B' : 'b',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ctx %08x%08x slot %ld flags %c:%c",
+				cdnsp_trb_type_string(type), field1, field0,
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_BSR ? 'B' : 'b',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_CONFIG_EP:
-		ret = snprintf(str, size,
-			       "%s: ctx %08x%08x slot %ld flags %c:%c",
-			       cdnsp_trb_type_string(type), field1, field0,
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_DC ? 'D' : 'd',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ctx %08x%08x slot %ld flags %c:%c",
+				cdnsp_trb_type_string(type), field1, field0,
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_DC ? 'D' : 'd',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_EVAL_CONTEXT:
-		ret = snprintf(str, size,
-			       "%s: ctx %08x%08x slot %ld flags %c",
-			       cdnsp_trb_type_string(type), field1, field0,
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ctx %08x%08x slot %ld flags %c",
+				cdnsp_trb_type_string(type), field1, field0,
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_RESET_EP:
 	case TRB_HALT_ENDPOINT:
-		ret = snprintf(str, size,
-			       "%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c",
-			       cdnsp_trb_type_string(type),
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3), field1, field0,
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c",
+				cdnsp_trb_type_string(type),
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3), field1, field0,
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_STOP_RING:
-		ret = snprintf(str, size,
-			       "%s: ep%d%s(%d) slot %ld sp %d flags %c",
-			       cdnsp_trb_type_string(type),
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3),
-			       TRB_TO_SLOT_ID(field3),
-			       TRB_TO_SUSPEND_PORT(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ep%d%s(%d) slot %ld sp %d flags %c",
+				cdnsp_trb_type_string(type),
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3),
+				TRB_TO_SLOT_ID(field3),
+				TRB_TO_SUSPEND_PORT(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_SET_DEQ:
-		ret = snprintf(str, size,
-			       "%s: ep%d%s(%d) deq %08x%08x stream %ld slot %ld  flags %c",
-			       cdnsp_trb_type_string(type),
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3), field1, field0,
-			       TRB_TO_STREAM_ID(field2),
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ep%d%s(%d) deq %08x%08x stream %ld slot %ld  flags %c",
+				cdnsp_trb_type_string(type),
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3), field1, field0,
+				TRB_TO_STREAM_ID(field2),
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_RESET_DEV:
-		ret = snprintf(str, size, "%s: slot %ld flags %c",
-			       cdnsp_trb_type_string(type),
-			       TRB_TO_SLOT_ID(field3),
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size, "%s: slot %ld flags %c",
+				cdnsp_trb_type_string(type),
+				TRB_TO_SLOT_ID(field3),
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_ENDPOINT_NRDY:
 		temp = TRB_TO_HOST_STREAM(field2);
 
-		ret = snprintf(str, size,
-			       "%s: ep%d%s(%d) H_SID %x%s%s D_SID %lx flags %c:%c",
-			       cdnsp_trb_type_string(type),
-			       ep_num, ep_id % 2 ? "out" : "in",
-			       TRB_TO_EP_INDEX(field3), temp,
-			       temp == STREAM_PRIME_ACK ? "(PRIME)" : "",
-			       temp == STREAM_REJECTED ? "(REJECTED)" : "",
-			       TRB_TO_DEV_STREAM(field0),
-			       field3 & TRB_STAT ? 'S' : 's',
-			       field3 & TRB_CYCLE ? 'C' : 'c');
+		ret = scnprintf(str, size,
+				"%s: ep%d%s(%d) H_SID %x%s%s D_SID %lx flags %c:%c",
+				cdnsp_trb_type_string(type),
+				ep_num, ep_id % 2 ? "out" : "in",
+				TRB_TO_EP_INDEX(field3), temp,
+				temp == STREAM_PRIME_ACK ? "(PRIME)" : "",
+				temp == STREAM_REJECTED ? "(REJECTED)" : "",
+				TRB_TO_DEV_STREAM(field0),
+				field3 & TRB_STAT ? 'S' : 's',
+				field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	default:
-		ret = snprintf(str, size,
-			       "type '%s' -> raw %08x %08x %08x %08x",
-			       cdnsp_trb_type_string(type),
-			       field0, field1, field2, field3);
+		ret = scnprintf(str, size,
+				"type '%s' -> raw %08x %08x %08x %08x",
+				cdnsp_trb_type_string(type),
+				field0, field1, field2, field3);
 	}
 
-	if (ret >= size)
-		pr_info("CDNSP: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNSP: buffer may be truncated.\n");
 
 	return str;
 }
@@ -465,32 +465,32 @@ static inline const char *cdnsp_decode_portsc(char *str, size_t size,
 {
 	int ret;
 
-	ret = snprintf(str, size, "%s %s %s Link:%s PortSpeed:%d ",
-		       portsc & PORT_POWER ? "Powered" : "Powered-off",
-		       portsc & PORT_CONNECT ? "Connected" : "Not-connected",
-		       portsc & PORT_PED ? "Enabled" : "Disabled",
-		       cdnsp_portsc_link_state_string(portsc),
-		       DEV_PORT_SPEED(portsc));
+	ret = scnprintf(str, size, "%s %s %s Link:%s PortSpeed:%d ",
+			portsc & PORT_POWER ? "Powered" : "Powered-off",
+			portsc & PORT_CONNECT ? "Connected" : "Not-connected",
+			portsc & PORT_PED ? "Enabled" : "Disabled",
+			cdnsp_portsc_link_state_string(portsc),
+			DEV_PORT_SPEED(portsc));
 
 	if (portsc & PORT_RESET)
-		ret += snprintf(str + ret, size - ret, "In-Reset ");
+		ret += scnprintf(str + ret, size - ret, "In-Reset ");
 
-	ret += snprintf(str + ret, size - ret, "Change: ");
+	ret += scnprintf(str + ret, size - ret, "Change: ");
 	if (portsc & PORT_CSC)
-		ret += snprintf(str + ret, size - ret, "CSC ");
+		ret += scnprintf(str + ret, size - ret, "CSC ");
 	if (portsc & PORT_WRC)
-		ret += snprintf(str + ret, size - ret, "WRC ");
+		ret += scnprintf(str + ret, size - ret, "WRC ");
 	if (portsc & PORT_RC)
-		ret += snprintf(str + ret, size - ret, "PRC ");
+		ret += scnprintf(str + ret, size - ret, "PRC ");
 	if (portsc & PORT_PLC)
-		ret += snprintf(str + ret, size - ret, "PLC ");
+		ret += scnprintf(str + ret, size - ret, "PLC ");
 	if (portsc & PORT_CEC)
-		ret += snprintf(str + ret, size - ret, "CEC ");
-	ret += snprintf(str + ret, size - ret, "Wake: ");
+		ret += scnprintf(str + ret, size - ret, "CEC ");
+	ret += scnprintf(str + ret, size - ret, "Wake: ");
 	if (portsc & PORT_WKCONN_E)
-		ret += snprintf(str + ret, size - ret, "WCE ");
+		ret += scnprintf(str + ret, size - ret, "WCE ");
 	if (portsc & PORT_WKDISC_E)
-		ret += snprintf(str + ret, size - ret, "WDE ");
+		ret += scnprintf(str + ret, size - ret, "WDE ");
 
 	return str;
 }
@@ -562,20 +562,20 @@ static inline const char *cdnsp_decode_ep_context(char *str, size_t size,
 
 	avg = EP_AVG_TRB_LENGTH(tx_info);
 
-	ret = snprintf(str, size, "State %s mult %d max P. Streams %d %s",
-		       cdnsp_ep_state_string(ep_state), mult,
-		       max_pstr, lsa ? "LSA " : "");
+	ret = scnprintf(str, size, "State %s mult %d max P. Streams %d %s",
+			cdnsp_ep_state_string(ep_state), mult,
+			max_pstr, lsa ? "LSA " : "");
 
-	ret += snprintf(str + ret, size - ret,
-			"interval %d us max ESIT payload %d CErr %d ",
-			(1 << interval) * 125, esit, cerr);
+	ret += scnprintf(str + ret, size - ret,
+			 "interval %d us max ESIT payload %d CErr %d ",
+			 (1 << interval) * 125, esit, cerr);
 
-	ret += snprintf(str + ret, size - ret,
-			"Type %s %sburst %d maxp %d deq %016llx ",
-			cdnsp_ep_type_string(ep_type), hid ? "HID" : "",
-			burst, maxp, deq);
+	ret += scnprintf(str + ret, size - ret,
+			 "Type %s %sburst %d maxp %d deq %016llx ",
+			 cdnsp_ep_type_string(ep_type), hid ? "HID" : "",
+			 burst, maxp, deq);
 
-	ret += snprintf(str + ret, size - ret, "avg trb len %d", avg);
+	ret += scnprintf(str + ret, size - ret, "avg trb len %d", avg);
 
 	return str;
 }
-- 
GitLab


From 7d7f794482b74e39d8c0cd830333eb40fc0234d4 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Thu, 30 Nov 2023 10:54:37 +0000
Subject: [PATCH 0701/4076] usb: fotg210-hcd: Replace snprintf() with the safer
 scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

The uses in this file both seem to assume that data *has been* written!

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Yuan-Hsin Chen <yhchen@faraday-tech.com>
Cc: Feng-Hsin Chiang <john453@faraday-tech.com>
Cc: Po-Yu Chuang <ratbert.chuang@gmail.com>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231130105459.3208986-4-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/fotg210/fotg210-hcd.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c
index 929106c16b29b..b2f8b53cc8ef5 100644
--- a/drivers/usb/fotg210/fotg210-hcd.c
+++ b/drivers/usb/fotg210/fotg210-hcd.c
@@ -404,9 +404,9 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh,
 			else if (td->hw_alt_next != list_end)
 				mark = '/';
 		}
-		temp = snprintf(next, size,
-				"\n\t%p%c%s len=%d %08x urb %p",
-				td, mark, ({ char *tmp;
+		temp = scnprintf(next, size,
+				 "\n\t%p%c%s len=%d %08x urb %p",
+				 td, mark, ({ char *tmp;
 				switch ((scratch>>8)&0x03) {
 				case 0:
 					tmp = "out";
@@ -424,17 +424,13 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh,
 				(scratch >> 16) & 0x7fff,
 				scratch,
 				td->urb);
-		if (size < temp)
-			temp = size;
 		size -= temp;
 		next += temp;
 		if (temp == size)
 			goto done;
 	}
 
-	temp = snprintf(next, size, "\n");
-	if (size < temp)
-		temp = size;
+	temp = scnprintf(next, size, "\n");
 
 	size -= temp;
 	next += temp;
-- 
GitLab


From 38168e2de320b9c12132eb72cf1f1d3d411fe38c Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Thu, 30 Nov 2023 10:54:38 +0000
Subject: [PATCH 0702/4076] usb: gadget: Remove snprintf() from sysfs
 call-backs and replace with sysfs_emit()

Since snprintf() has the documented, but still rather strange trait of
returning the length of the data that *would have been* written to the
array if space were available, rather than the arguably more useful
length of data *actually* written, it is usually considered wise to use
something else instead in order to avoid confusion.

In the case of sysfs call-backs, new wrappers exist that do just that.

This patch replaces just one use of snprintf() found in the sysfs
.show() call-back with the new sysfs_emit() helper.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231130105459.3208986-5-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/configfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 4c639e9ddedc0..b7d2a1313a684 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -812,7 +812,7 @@ static ssize_t gadget_string_s_show(struct config_item *item, char *page)
 	struct gadget_string *string = to_gadget_string(item);
 	int ret;
 
-	ret = snprintf(page, sizeof(string->string), "%s\n", string->string);
+	ret = sysfs_emit(page, "%s\n", string->string);
 	return ret;
 }
 
-- 
GitLab


From dadc0f0f7afc0273ff680b504ed830d0c307dea3 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Thu, 30 Nov 2023 10:54:39 +0000
Subject: [PATCH 0703/4076] usb: gadget: f_tcm: Remove snprintf() from sysfs
 call-backs and replace with sysfs_emit()

Since snprintf() has the documented, but still rather strange trait of
returning the length of the data that *would have been* written to the
array if space were available, rather than the arguably more useful
length of data *actually* written, it is usually considered wise to use
something else instead in order to avoid confusion.

In the case of sysfs call-backs, new wrappers exist that do just that.

This patch replaces just one use of snprintf() found in the sysfs
.show() call-back with the new sysfs_emit() helper.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Dmitry Bogdanov <d.bogdanov@yadro.com>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231130105459.3208986-6-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_tcm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index ff33f31bcdf64..37befd6db001a 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1504,8 +1504,8 @@ static ssize_t tcm_usbg_tpg_nexus_show(struct config_item *item, char *page)
 		ret = -ENODEV;
 		goto out;
 	}
-	ret = snprintf(page, PAGE_SIZE, "%s\n",
-			tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
+	ret = sysfs_emit(page, "%s\n",
+			 tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
 out:
 	mutex_unlock(&tpg->tpg_mutex);
 	return ret;
-- 
GitLab


From c2d95fcff0f01fa00d9683dddeeea6732b74c779 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 1 Dec 2023 10:29:50 -0800
Subject: [PATCH 0704/4076] usb: core: Don't force USB generic_subclass drivers
 to define probe()

There's no real reason that subclassed USB drivers _need_ to define
probe() since they might want to subclass for some other reason. Make
it optional to define probe() if we're a generic_subclass.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Grant Grundler <grundler@chromium.org>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231201102946.v2.1.I7ea0dd55ee2acdb48b0e6d28c1a704ab2c29206f@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/driver.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index f58a0299fb3bd..1dc0c04130438 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -290,7 +290,10 @@ static int usb_probe_device(struct device *dev)
 	 * specialised device drivers prior to setting the
 	 * use_generic_driver bit.
 	 */
-	error = udriver->probe(udev);
+	if (udriver->probe)
+		error = udriver->probe(udev);
+	else if (!udriver->generic_subclass)
+		error = -EINVAL;
 	if (error == -ENODEV && udriver != &usb_generic_driver &&
 	    (udriver->id_table || udriver->match)) {
 		udev->use_generic_driver = 1;
-- 
GitLab


From a87b8e3be926af0fc3b9b1af42b1127bd1ff077c Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 1 Dec 2023 10:29:51 -0800
Subject: [PATCH 0705/4076] usb: core: Allow subclassed USB drivers to override
 usb_choose_configuration()

For some USB devices we might want to do something different for
usb_choose_configuration(). One example here is the r8152 driver where
we want to end up using the vendor driver with the preferred
interface.

The r8152 driver tried to make things work by implementing a USB
generic_subclass driver and then overriding the normal config
selection after it happened. This is less than ideal and also caused
breakage if someone deauthorized and re-authorized the USB device
because the USB core ended up going back to it's default logic for
choosing the best config. I made an attempt to fix this [1] but it was
a bit ugly.

Let's do this better and allow USB generic_subclass drivers to
override usb_choose_configuration().

[1] https://lore.kernel.org/r/20231130154337.1.Ie00e07f07f87149c9ce0b27ae4e26991d307e14b@changeid

Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231201102946.v2.2.Iade5fa31997f1a0ca3e1dec0591633b02471df12@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/generic.c | 7 +++++++
 include/linux/usb.h        | 6 ++++++
 2 files changed, 13 insertions(+)

diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index 740342a2812ac..dcb8971582284 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -59,10 +59,17 @@ int usb_choose_configuration(struct usb_device *udev)
 	int num_configs;
 	int insufficient_power = 0;
 	struct usb_host_config *c, *best;
+	struct usb_device_driver *udriver = to_usb_device_driver(udev->dev.driver);
 
 	if (usb_device_is_owned(udev))
 		return 0;
 
+	if (udriver->choose_configuration) {
+		i = udriver->choose_configuration(udev);
+		if (i >= 0)
+			return i;
+	}
+
 	best = NULL;
 	c = udev->config;
 	num_configs = udev->descriptor.bNumConfigurations;
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 8c61643acd499..618e5a0b1a223 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1264,6 +1264,9 @@ struct usb_driver {
  *	module is being unloaded.
  * @suspend: Called when the device is going to be suspended by the system.
  * @resume: Called when the device is being resumed by the system.
+ * @choose_configuration: If non-NULL, called instead of the default
+ *	usb_choose_configuration(). If this returns an error then we'll go
+ *	on to call the normal usb_choose_configuration().
  * @dev_groups: Attributes attached to the device that will be created once it
  *	is bound to the driver.
  * @drvwrap: Driver-model core structure wrapper.
@@ -1287,6 +1290,9 @@ struct usb_device_driver {
 
 	int (*suspend) (struct usb_device *udev, pm_message_t message);
 	int (*resume) (struct usb_device *udev, pm_message_t message);
+
+	int (*choose_configuration) (struct usb_device *udev);
+
 	const struct attribute_group **dev_groups;
 	struct usbdrv_wrap drvwrap;
 	const struct usb_device_id *id_table;
-- 
GitLab


From aa4f2b3e418e8673e55145de8b8016a7a9920306 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 1 Dec 2023 10:29:52 -0800
Subject: [PATCH 0706/4076] r8152: Choose our USB config with
 choose_configuration() rather than probe()

If you deauthorize the r8152 device (by writing 0 to the "authorized"
field in sysfs) and then reauthorize it (by writing a 1) then it no
longer works. This is because when you do the above we lose the
special configuration that we set in rtl8152_cfgselector_probe().
Deauthorizing causes the config to be set to -1 and then reauthorizing
runs the default logic for choosing the best config.

I made an attempt to fix it so that the config is kept across
deauthorizing / reauthorizing [1] but it was a bit ugly.

Let's instead use the new USB core feature to override
choose_configuration().

This patch relies upon the patches ("usb: core: Don't force USB
generic_subclass drivers to define probe()") and ("usb: core: Allow
subclassed USB drivers to override usb_choose_configuration()")

[1] https://lore.kernel.org/r/20231130154337.1.Ie00e07f07f87149c9ce0b27ae4e26991d307e14b@changeid

Fixes: ec51fbd1b8a2 ("r8152: add USB device driver for config selection")
Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Grant Grundler <grundler@chromium.org>
Link: https://lore.kernel.org/r/20231201102946.v2.3.Ie00e07f07f87149c9ce0b27ae4e26991d307e14b@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/usb/r8152.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2c5c1e91ded61..0da723d113266 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10053,7 +10053,7 @@ static struct usb_driver rtl8152_driver = {
 	.disable_hub_initiated_lpm = 1,
 };
 
-static int rtl8152_cfgselector_probe(struct usb_device *udev)
+static int rtl8152_cfgselector_choose_configuration(struct usb_device *udev)
 {
 	struct usb_host_config *c;
 	int i, num_configs;
@@ -10080,19 +10080,13 @@ static int rtl8152_cfgselector_probe(struct usb_device *udev)
 	if (i == num_configs)
 		return -ENODEV;
 
-	if (usb_set_configuration(udev, c->desc.bConfigurationValue)) {
-		dev_err(&udev->dev, "Failed to set configuration %d\n",
-			c->desc.bConfigurationValue);
-		return -ENODEV;
-	}
-
-	return 0;
+	return c->desc.bConfigurationValue;
 }
 
 static struct usb_device_driver rtl8152_cfgselector_driver = {
-	.name =		MODULENAME "-cfgselector",
-	.probe =	rtl8152_cfgselector_probe,
-	.id_table =	rtl8152_table,
+	.name =	MODULENAME "-cfgselector",
+	.choose_configuration = rtl8152_cfgselector_choose_configuration,
+	.id_table = rtl8152_table,
 	.generic_subclass = 1,
 	.supports_autosuspend = 1,
 };
-- 
GitLab


From 6a4d4a27f986ac19338da8f18d73eed80ce28fca Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco@wolfvision.net>
Date: Thu, 23 Nov 2023 16:37:01 +0100
Subject: [PATCH 0707/4076] usb: typec: tps6598x: add reset gpio support

The TPS6598x PD controller provides an active-high hardware reset input
that reinitializes all device settings. If it is not grounded by
design, the driver must be able to de-assert it in order to initialize
the device.

The PD controller is not ready for registration right after the reset
de-assertion and a delay must be introduced in that case. According to
TI, the delay can reach up to 1000 ms [1], which is in line with the
experimental results obtained with a TPS65987D.

Add a GPIO descriptor for the reset signal and basic reset management
for initialization and suspend/resume.

[1] https://e2e.ti.com/support/power-management-group/power-management/
f/power-management-forum/1269856/tps65987d-tps65987d-reset-de-assert-
to-normal-operation/4809389#4809389

Signed-off-by: Javier Carrasco <javier.carrasco@wolfvision.net>
Reviewed-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20230912-topic-tps6598x_reset-v3-1-0c2873070a77@wolfvision.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tipd/core.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 196535ad996d0..806ef68273ca0 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -8,6 +8,7 @@
 
 #include <linux/i2c.h>
 #include <linux/acpi.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/power_supply.h>
@@ -64,6 +65,9 @@
 #define TPS_PBMC_RC	0 /* Return code */
 #define TPS_PBMC_DPCS	2 /* device patch complete status */
 
+/* reset de-assertion to ready for operation */
+#define TPS_SETUP_MS			1000
+
 enum {
 	TPS_PORTINFO_SINK,
 	TPS_PORTINFO_SINK_ACCESSORY,
@@ -119,6 +123,7 @@ struct tps6598x {
 	struct mutex lock; /* device lock */
 	u8 i2c_protocol:1;
 
+	struct gpio_desc *reset;
 	struct typec_port *port;
 	struct typec_partner *partner;
 	struct usb_pd_identity partner_identity;
@@ -1191,6 +1196,13 @@ static int tps6598x_probe(struct i2c_client *client)
 	mutex_init(&tps->lock);
 	tps->dev = &client->dev;
 
+	tps->reset = devm_gpiod_get_optional(tps->dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(tps->reset))
+		return dev_err_probe(tps->dev, PTR_ERR(tps->reset),
+				     "failed to get reset GPIO\n");
+	if (tps->reset)
+		msleep(TPS_SETUP_MS);
+
 	tps->regmap = devm_regmap_init_i2c(client, &tps6598x_regmap_config);
 	if (IS_ERR(tps->regmap))
 		return PTR_ERR(tps->regmap);
@@ -1348,6 +1360,9 @@ static void tps6598x_remove(struct i2c_client *client)
 	/* Reset PD controller to remove any applied patch */
 	if (device_is_compatible(tps->dev, "ti,tps25750"))
 		tps6598x_exec_cmd_tmo(tps, "GAID", 0, NULL, 0, NULL, 2000, 0);
+
+	if (tps->reset)
+		gpiod_set_value_cansleep(tps->reset, 1);
 }
 
 static int __maybe_unused tps6598x_suspend(struct device *dev)
@@ -1358,6 +1373,8 @@ static int __maybe_unused tps6598x_suspend(struct device *dev)
 	if (tps->wakeup) {
 		disable_irq(client->irq);
 		enable_irq_wake(client->irq);
+	} else if (tps->reset) {
+		gpiod_set_value_cansleep(tps->reset, 1);
 	}
 
 	if (!client->irq)
@@ -1385,6 +1402,9 @@ static int __maybe_unused tps6598x_resume(struct device *dev)
 	if (tps->wakeup) {
 		disable_irq_wake(client->irq);
 		enable_irq(client->irq);
+	} else if (tps->reset) {
+		gpiod_set_value_cansleep(tps->reset, 0);
+		msleep(TPS_SETUP_MS);
 	}
 
 	if (!client->irq)
-- 
GitLab


From 9f802703fde29011aa9003cb1c5a418623a944ca Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco@wolfvision.net>
Date: Thu, 23 Nov 2023 16:37:02 +0100
Subject: [PATCH 0708/4076] dt-bindings: usb: tps6598x: add reset-gpios
 property

The TPS6598x device family provides a high-level reset pin. It can be
either grounded or used to reinitialize all device settings.

Document the reset GPIO as an optional property and add it to the
existing example.

Signed-off-by: Javier Carrasco <javier.carrasco@wolfvision.net>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230912-topic-tps6598x_reset-v3-2-0c2873070a77@wolfvision.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/ti,tps6598x.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml b/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml
index 323d664ae06a4..1745e28b31105 100644
--- a/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml
@@ -38,6 +38,10 @@ properties:
       - const: main
       - const: patch-address
 
+  reset-gpios:
+    description: GPIO used for the HRESET pin.
+    maxItems: 1
+
   wakeup-source: true
 
   interrupts:
@@ -90,6 +94,7 @@ additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/gpio/gpio.h>
     #include <dt-bindings/interrupt-controller/irq.h>
     i2c {
         #address-cells = <1>;
@@ -106,6 +111,7 @@ examples:
 
             pinctrl-names = "default";
             pinctrl-0 = <&typec_pins>;
+            reset-gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>;
 
             typec_con: connector {
                 compatible = "usb-c-connector";
-- 
GitLab


From db9e54709895241dda23f9347f619afb15291353 Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Tue, 21 Nov 2023 20:38:47 +0000
Subject: [PATCH 0709/4076] usb: typec: tcpm: add tcpm_port_error_recovery
 symbol

Add tcpm_port_error_recovery symbol and corresponding event that runs in
tcpm_pd_event handler to set the port to the ERROR_RECOVERY state. tcpci
drivers can use the symbol to reset the port when tcpc faults affect port
functionality.

Signed-off-by: RD Babiera <rdbabiera@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20231121203845.170234-5-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 14 ++++++++++++++
 include/linux/usb/tcpm.h      |  1 +
 2 files changed, 15 insertions(+)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 50cbc52386b38..ff67553b69323 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -251,6 +251,7 @@ enum frs_typec_current {
 #define TCPM_FRS_EVENT		BIT(3)
 #define TCPM_SOURCING_VBUS	BIT(4)
 #define TCPM_PORT_CLEAN		BIT(5)
+#define TCPM_PORT_ERROR		BIT(6)
 
 #define LOG_BUFFER_ENTRIES	1024
 #define LOG_BUFFER_ENTRY_SIZE	128
@@ -5487,6 +5488,10 @@ static void tcpm_pd_event_handler(struct kthread_work *work)
 					tcpm_set_state(port, tcpm_default_state(port), 0);
 			}
 		}
+		if (events & TCPM_PORT_ERROR) {
+			tcpm_log(port, "port triggering error recovery");
+			tcpm_set_state(port, ERROR_RECOVERY, 0);
+		}
 
 		spin_lock(&port->pd_event_lock);
 	}
@@ -5554,6 +5559,15 @@ bool tcpm_port_is_toggling(struct tcpm_port *port)
 }
 EXPORT_SYMBOL_GPL(tcpm_port_is_toggling);
 
+void tcpm_port_error_recovery(struct tcpm_port *port)
+{
+	spin_lock(&port->pd_event_lock);
+	port->pd_events |= TCPM_PORT_ERROR;
+	spin_unlock(&port->pd_event_lock);
+	kthread_queue_work(port->wq, &port->event_work);
+}
+EXPORT_SYMBOL_GPL(tcpm_port_error_recovery);
+
 static void tcpm_enable_frs_work(struct kthread_work *work)
 {
 	struct tcpm_port *port = container_of(work, struct tcpm_port, enable_frs);
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index ab7ca872950bb..65fac5e1f3178 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -173,5 +173,6 @@ void tcpm_pd_hard_reset(struct tcpm_port *port);
 void tcpm_tcpc_reset(struct tcpm_port *port);
 void tcpm_port_clean(struct tcpm_port *port);
 bool tcpm_port_is_toggling(struct tcpm_port *port);
+void tcpm_port_error_recovery(struct tcpm_port *port);
 
 #endif /* __LINUX_USB_TCPM_H */
-- 
GitLab


From 5e4c8814a431d21bfaf20b464134f40f2f81e152 Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Tue, 21 Nov 2023 20:38:48 +0000
Subject: [PATCH 0710/4076] usb: typec: tcpci: add vconn over current fault
 handling to maxim_core

Add TCPC_FAULT_STATUS_VCONN_OC constant and corresponding mask definition.
Maxim TCPC is capable of detecting VConn over current faults, so add
fault to alert mask. When a Vconn over current fault is triggered, put the
port in an error recovery state via tcpm_port_error_recovery.

Signed-off-by: RD Babiera <rdbabiera@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231121203845.170234-6-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpci_maxim_core.c | 20 +++++++++++++++++++-
 include/linux/usb/tcpci.h                 |  5 ++++-
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpci_maxim_core.c b/drivers/usb/typec/tcpm/tcpci_maxim_core.c
index 9454b12a073c9..7fb966fd639b3 100644
--- a/drivers/usb/typec/tcpm/tcpci_maxim_core.c
+++ b/drivers/usb/typec/tcpm/tcpci_maxim_core.c
@@ -92,11 +92,16 @@ static void max_tcpci_init_regs(struct max_tcpci_chip *chip)
 		return;
 	}
 
+	/* Vconn Over Current Protection */
+	ret = max_tcpci_write8(chip, TCPC_FAULT_STATUS_MASK, TCPC_FAULT_STATUS_MASK_VCONN_OC);
+	if (ret < 0)
+		return;
+
 	alert_mask = TCPC_ALERT_TX_SUCCESS | TCPC_ALERT_TX_DISCARDED | TCPC_ALERT_TX_FAILED |
 		TCPC_ALERT_RX_HARD_RST | TCPC_ALERT_RX_STATUS | TCPC_ALERT_CC_STATUS |
 		TCPC_ALERT_VBUS_DISCNCT | TCPC_ALERT_RX_BUF_OVF | TCPC_ALERT_POWER_STATUS |
 		/* Enable Extended alert for detecting Fast Role Swap Signal */
-		TCPC_ALERT_EXTND | TCPC_ALERT_EXTENDED_STATUS;
+		TCPC_ALERT_EXTND | TCPC_ALERT_EXTENDED_STATUS | TCPC_ALERT_FAULT;
 
 	ret = max_tcpci_write16(chip, TCPC_ALERT_MASK, alert_mask);
 	if (ret < 0) {
@@ -295,6 +300,19 @@ static irqreturn_t _max_tcpci_irq(struct max_tcpci_chip *chip, u16 status)
 		}
 	}
 
+	if (status & TCPC_ALERT_FAULT) {
+		ret = max_tcpci_read8(chip, TCPC_FAULT_STATUS, &reg_status);
+		if (ret < 0)
+			return ret;
+
+		ret = max_tcpci_write8(chip, TCPC_FAULT_STATUS, reg_status);
+		if (ret < 0)
+			return ret;
+
+		if (reg_status & TCPC_FAULT_STATUS_VCONN_OC)
+			tcpm_port_error_recovery(chip->port);
+	}
+
 	if (status & TCPC_ALERT_EXTND) {
 		ret = max_tcpci_read8(chip, TCPC_ALERT_EXTENDED, &reg_status);
 		if (ret < 0)
diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h
index 83376473ac765..467e8045e9f86 100644
--- a/include/linux/usb/tcpci.h
+++ b/include/linux/usb/tcpci.h
@@ -36,7 +36,9 @@
 
 #define TCPC_ALERT_MASK			0x12
 #define TCPC_POWER_STATUS_MASK		0x14
-#define TCPC_FAULT_STATUS_MASK		0x15
+
+#define TCPC_FAULT_STATUS_MASK			0x15
+#define TCPC_FAULT_STATUS_MASK_VCONN_OC		BIT(1)
 
 #define TCPC_EXTENDED_STATUS_MASK		0x16
 #define TCPC_EXTENDED_STATUS_MASK_VSAFE0V	BIT(0)
@@ -104,6 +106,7 @@
 
 #define TCPC_FAULT_STATUS		0x1f
 #define TCPC_FAULT_STATUS_ALL_REG_RST_TO_DEFAULT BIT(7)
+#define TCPC_FAULT_STATUS_VCONN_OC	BIT(1)
 
 #define TCPC_ALERT_EXTENDED		0x21
 
-- 
GitLab


From b89710bd215e650f0aaf8ffe7104413d46d44392 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 27 Nov 2023 18:34:28 +0100
Subject: [PATCH 0711/4076] iio: add modifiers for A and B ultraviolet light

Currently there are only two modifiers for ultraviolet light: a generic
one for any ultraviolet light (IIO_MOD_LIGHT_UV) and one for deep
ultraviolet (IIO_MOD_LIGHT_DUV), which is also referred as ultraviolet
C (UV-C) band and covers short-wave ultraviolet.

There are still no modifiers for the long-wave and medium-wave
ultraviolet bands. These two bands are the main components used to
obtain the UV index on the Earth's surface.

Add modifiers for the ultraviolet A (UV-A) and ultraviolet B (UV-B)
bands.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20231110-veml6075-v3-1-6ee46775b422@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-iio | 7 +++++--
 drivers/iio/industrialio-core.c         | 2 ++
 include/uapi/linux/iio/types.h          | 2 ++
 tools/iio/iio_event_monitor.c           | 2 ++
 4 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 0eadc08c3a139..0d3ec5fc45f2f 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -1574,6 +1574,8 @@ What:		/sys/.../iio:deviceX/in_intensityY_raw
 What:		/sys/.../iio:deviceX/in_intensityY_ir_raw
 What:		/sys/.../iio:deviceX/in_intensityY_both_raw
 What:		/sys/.../iio:deviceX/in_intensityY_uv_raw
+What:		/sys/.../iio:deviceX/in_intensityY_uva_raw
+What:		/sys/.../iio:deviceX/in_intensityY_uvb_raw
 What:		/sys/.../iio:deviceX/in_intensityY_duv_raw
 KernelVersion:	3.4
 Contact:	linux-iio@vger.kernel.org
@@ -1582,8 +1584,9 @@ Description:
 		that measurements contain visible and infrared light
 		components or just infrared light, respectively. Modifier
 		uv indicates that measurements contain ultraviolet light
-		components. Modifier duv indicates that measurements
-		contain deep ultraviolet light components.
+		components. Modifiers uva, uvb and duv indicate that
+		measurements contain A, B or deep (C) ultraviolet light
+		components respectively.
 
 What:		/sys/.../iio:deviceX/in_uvindex_input
 KernelVersion:	4.6
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 34e1f8d0071cb..f6a123d397db5 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -117,6 +117,8 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_LIGHT_GREEN] = "green",
 	[IIO_MOD_LIGHT_BLUE] = "blue",
 	[IIO_MOD_LIGHT_UV] = "uv",
+	[IIO_MOD_LIGHT_UVA] = "uva",
+	[IIO_MOD_LIGHT_UVB] = "uvb",
 	[IIO_MOD_LIGHT_DUV] = "duv",
 	[IIO_MOD_QUATERNION] = "quaternion",
 	[IIO_MOD_TEMP_AMBIENT] = "ambient",
diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h
index 9c2ffdcd66230..5060963707b1e 100644
--- a/include/uapi/linux/iio/types.h
+++ b/include/uapi/linux/iio/types.h
@@ -91,6 +91,8 @@ enum iio_modifier {
 	IIO_MOD_CO2,
 	IIO_MOD_VOC,
 	IIO_MOD_LIGHT_UV,
+	IIO_MOD_LIGHT_UVA,
+	IIO_MOD_LIGHT_UVB,
 	IIO_MOD_LIGHT_DUV,
 	IIO_MOD_PM1,
 	IIO_MOD_PM2P5,
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c
index 2eaaa7123b042..8073c9e4fe46a 100644
--- a/tools/iio/iio_event_monitor.c
+++ b/tools/iio/iio_event_monitor.c
@@ -105,6 +105,8 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_LIGHT_GREEN] = "green",
 	[IIO_MOD_LIGHT_BLUE] = "blue",
 	[IIO_MOD_LIGHT_UV] = "uv",
+	[IIO_MOD_LIGHT_UVA] = "uva",
+	[IIO_MOD_LIGHT_UVB] = "uvb",
 	[IIO_MOD_LIGHT_DUV] = "duv",
 	[IIO_MOD_QUATERNION] = "quaternion",
 	[IIO_MOD_TEMP_AMBIENT] = "ambient",
-- 
GitLab


From 249f27ac71f428e5028a20d764e66c663f8e8a52 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 27 Nov 2023 18:34:29 +0100
Subject: [PATCH 0712/4076] dt-bindings: iio: light: add support for Vishay
 VEML6075

The Vishay VEML6075 is a 16-bit digital UVA and UVB sensor with I2C
interface.

Add bindings and an example for the Vishay VEML6075.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231110-veml6075-v3-2-6ee46775b422@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/light/vishay,veml6075.yaml   | 39 +++++++++++++++++++
 1 file changed, 39 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml

diff --git a/Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml b/Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml
new file mode 100644
index 0000000000000..abee04cd126e4
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml
@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/light/vishay,veml6075.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Vishay VEML6075 UVA and UVB sensor
+
+maintainers:
+  - Javier Carrasco <javier.carrasco.cruz@gmail.com>
+
+properties:
+  compatible:
+    const: vishay,veml6075
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        uv-sensor@10 {
+            compatible = "vishay,veml6075";
+            reg = <0x10>;
+            vdd-supply = <&vdd_reg>;
+        };
+    };
+...
-- 
GitLab


From 3b82f43238aecd73464aeacc9c73407079511533 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 27 Nov 2023 18:34:30 +0100
Subject: [PATCH 0713/4076] iio: light: add VEML6075 UVA and UVB light sensor
 driver

The Vishay VEMl6075 is a low power, 16-bit resolution UVA and UVB
light sensor with I2C interface and noise compensation (visible and
infrarred).

Every UV channel generates an output signal measured in counts per
integration period, where the integration time is configurable.

This driver adds support for both UV channels and the ultraviolet
index (UVI) inferred from them according to the device application note
with open-air (no teflon) coefficients.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20231110-veml6075-v3-3-6ee46775b422@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS                  |   6 +
 drivers/iio/light/Kconfig    |  11 +
 drivers/iio/light/Makefile   |   1 +
 drivers/iio/light/veml6075.c | 474 +++++++++++++++++++++++++++++++++++
 4 files changed, 492 insertions(+)
 create mode 100644 drivers/iio/light/veml6075.c

diff --git a/MAINTAINERS b/MAINTAINERS
index cd9591df77d73..1338e1176ea5f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23192,6 +23192,12 @@ S:	Maintained
 F:	drivers/input/serio/userio.c
 F:	include/uapi/linux/userio.h
 
+VISHAY VEML6075 UVA AND UVB LIGHT SENSOR DRIVER
+M:	Javier Carrasco <javier.carrasco.cruz@gmail.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/light/vishay,veml6075.yaml
+F:	drivers/iio/light/veml6075.c
+
 VISL VIRTUAL STATELESS DECODER DRIVER
 M:	Daniel Almeida <daniel.almeida@collabora.com>
 L:	linux-media@vger.kernel.org
diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig
index 45edba797e4c7..f68e62196bc2c 100644
--- a/drivers/iio/light/Kconfig
+++ b/drivers/iio/light/Kconfig
@@ -637,6 +637,17 @@ config VEML6070
 	  To compile this driver as a module, choose M here: the
 	  module will be called veml6070.
 
+config VEML6075
+	tristate "VEML6075 UVA and UVB light sensor"
+	select REGMAP_I2C
+	depends on I2C
+	help
+	  Say Y here if you want to build a driver for the Vishay VEML6075 UVA
+	  and UVB light sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called veml6075.
+
 config VL6180
 	tristate "VL6180 ALS, range and proximity sensor"
 	depends on I2C
diff --git a/drivers/iio/light/Makefile b/drivers/iio/light/Makefile
index c0db4c4c36ec9..c8289e24e3f66 100644
--- a/drivers/iio/light/Makefile
+++ b/drivers/iio/light/Makefile
@@ -60,5 +60,6 @@ obj-$(CONFIG_VCNL4000)		+= vcnl4000.o
 obj-$(CONFIG_VCNL4035)		+= vcnl4035.o
 obj-$(CONFIG_VEML6030)		+= veml6030.o
 obj-$(CONFIG_VEML6070)		+= veml6070.o
+obj-$(CONFIG_VEML6075)		+= veml6075.o
 obj-$(CONFIG_VL6180)		+= vl6180.o
 obj-$(CONFIG_ZOPT2201)		+= zopt2201.o
diff --git a/drivers/iio/light/veml6075.c b/drivers/iio/light/veml6075.c
new file mode 100644
index 0000000000000..05d4c0e9015d6
--- /dev/null
+++ b/drivers/iio/light/veml6075.c
@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Vishay VEML6075 UVA and UVB light sensor
+ *
+ * Copyright 2023 Javier Carrasco <javier.carrasco.cruz@gmail.com>
+ *
+ * 7-bit I2C slave, address 0x10
+ */
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/units.h>
+
+#include <linux/iio/iio.h>
+
+#define VEML6075_CMD_CONF	0x00 /* configuration register */
+#define VEML6075_CMD_UVA	0x07 /* UVA channel */
+#define VEML6075_CMD_UVB	0x09 /* UVB channel */
+#define VEML6075_CMD_COMP1	0x0A /* visible light compensation */
+#define VEML6075_CMD_COMP2	0x0B /* infrarred light compensation */
+#define VEML6075_CMD_ID		0x0C /* device ID */
+
+#define VEML6075_CONF_IT	GENMASK(6, 4) /* intregration time */
+#define VEML6075_CONF_HD	BIT(3) /* dynamic setting */
+#define VEML6075_CONF_TRIG	BIT(2) /* trigger */
+#define VEML6075_CONF_AF	BIT(1) /* active force enable */
+#define VEML6075_CONF_SD	BIT(0) /* shutdown */
+
+#define VEML6075_IT_50_MS	0x00
+#define VEML6075_IT_100_MS	0x01
+#define VEML6075_IT_200_MS	0x02
+#define VEML6075_IT_400_MS	0x03
+#define VEML6075_IT_800_MS	0x04
+
+#define VEML6075_AF_DISABLE	0x00
+#define VEML6075_AF_ENABLE	0x01
+
+#define VEML6075_SD_DISABLE	0x00
+#define VEML6075_SD_ENABLE	0x01
+
+/* Open-air coefficients and responsivity */
+#define VEML6075_A_COEF		2220
+#define VEML6075_B_COEF		1330
+#define VEML6075_C_COEF		2950
+#define VEML6075_D_COEF		1740
+#define VEML6075_UVA_RESP	1461
+#define VEML6075_UVB_RESP	2591
+
+static const int veml6075_it_ms[] = { 50, 100, 200, 400, 800 };
+
+struct veml6075_data {
+	struct i2c_client *client;
+	struct regmap *regmap;
+	/*
+	 * prevent integration time modification and triggering
+	 * measurements while a measurement is underway.
+	 */
+	struct mutex lock;
+};
+
+/* channel number */
+enum veml6075_chan {
+	CH_UVA,
+	CH_UVB,
+};
+
+static const struct iio_chan_spec veml6075_channels[] = {
+	{
+		.type = IIO_INTENSITY,
+		.channel = CH_UVA,
+		.modified = 1,
+		.channel2 = IIO_MOD_LIGHT_UVA,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+			BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),
+	},
+	{
+		.type = IIO_INTENSITY,
+		.channel = CH_UVB,
+		.modified = 1,
+		.channel2 = IIO_MOD_LIGHT_UVB,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+			BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),
+	},
+	{
+		.type = IIO_UVINDEX,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),
+	},
+};
+
+static int veml6075_request_measurement(struct veml6075_data *data)
+{
+	int ret, conf, int_time;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_CONF, &conf);
+	if (ret < 0)
+		return ret;
+
+	/* disable shutdown and trigger measurement */
+	ret = regmap_write(data->regmap, VEML6075_CMD_CONF,
+			   (conf | VEML6075_CONF_TRIG) & ~VEML6075_CONF_SD);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * A measurement requires between 1.30 and 1.40 times the integration
+	 * time for all possible configurations. Using a 1.50 factor simplifies
+	 * operations and ensures reliability under all circumstances.
+	 */
+	int_time = veml6075_it_ms[FIELD_GET(VEML6075_CONF_IT, conf)];
+	msleep(int_time + (int_time / 2));
+
+	/* shutdown again, data registers are still accessible */
+	return regmap_update_bits(data->regmap, VEML6075_CMD_CONF,
+				  VEML6075_CONF_SD, VEML6075_CONF_SD);
+}
+
+static int veml6075_uva_comp(int raw_uva, int comp1, int comp2)
+{
+	int comp1a_c, comp2a_c, uva_comp;
+
+	comp1a_c = (comp1 * VEML6075_A_COEF) / 1000U;
+	comp2a_c = (comp2 * VEML6075_B_COEF) / 1000U;
+	uva_comp = raw_uva - comp1a_c - comp2a_c;
+
+	return clamp_val(uva_comp, 0, U16_MAX);
+}
+
+static int veml6075_uvb_comp(int raw_uvb, int comp1, int comp2)
+{
+	int comp1b_c, comp2b_c, uvb_comp;
+
+	comp1b_c = (comp1 * VEML6075_C_COEF) / 1000U;
+	comp2b_c = (comp2 * VEML6075_D_COEF) / 1000U;
+	uvb_comp = raw_uvb - comp1b_c - comp2b_c;
+
+	return clamp_val(uvb_comp, 0, U16_MAX);
+}
+
+static int veml6075_read_comp(struct veml6075_data *data, int *c1, int *c2)
+{
+	int ret;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_COMP1, c1);
+	if (ret < 0)
+		return ret;
+
+	return regmap_read(data->regmap, VEML6075_CMD_COMP2, c2);
+}
+
+static int veml6075_read_uv_direct(struct veml6075_data *data, int chan,
+				   int *val)
+{
+	int c1, c2, ret;
+
+	guard(mutex)(&data->lock);
+
+	ret = veml6075_request_measurement(data);
+	if (ret < 0)
+		return ret;
+
+	ret = veml6075_read_comp(data, &c1, &c2);
+	if (ret < 0)
+		return ret;
+
+	switch (chan) {
+	case CH_UVA:
+		ret = regmap_read(data->regmap, VEML6075_CMD_UVA, val);
+		if (ret < 0)
+			return ret;
+
+		*val = veml6075_uva_comp(*val, c1, c2);
+		return IIO_VAL_INT;
+	case CH_UVB:
+		ret = regmap_read(data->regmap, VEML6075_CMD_UVB, val);
+		if (ret < 0)
+			return ret;
+
+		*val = veml6075_uvb_comp(*val, c1, c2);
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_read_int_time_index(struct veml6075_data *data)
+{
+	int ret, conf;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_CONF, &conf);
+	if (ret < 0)
+		return ret;
+
+	return FIELD_GET(VEML6075_CONF_IT, conf);
+}
+
+static int veml6075_read_int_time_ms(struct veml6075_data *data, int *val)
+{
+	int int_index;
+
+	guard(mutex)(&data->lock);
+	int_index = veml6075_read_int_time_index(data);
+	if (int_index < 0)
+		return int_index;
+
+	*val = veml6075_it_ms[int_index];
+
+	return IIO_VAL_INT;
+}
+
+static int veml6075_get_uvi_micro(struct veml6075_data *data, int uva_comp,
+				  int uvb_comp)
+{
+	int uvia_micro = uva_comp * VEML6075_UVA_RESP;
+	int uvib_micro = uvb_comp * VEML6075_UVB_RESP;
+	int int_index;
+
+	int_index = veml6075_read_int_time_index(data);
+	if (int_index < 0)
+		return int_index;
+
+	switch (int_index) {
+	case VEML6075_IT_50_MS:
+		return uvia_micro + uvib_micro;
+	case VEML6075_IT_100_MS:
+	case VEML6075_IT_200_MS:
+	case VEML6075_IT_400_MS:
+	case VEML6075_IT_800_MS:
+		return (uvia_micro + uvib_micro) / (2 << int_index);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_read_uvi(struct veml6075_data *data, int *val, int *val2)
+{
+	int ret, c1, c2, uva, uvb, uvi_micro;
+
+	guard(mutex)(&data->lock);
+
+	ret = veml6075_request_measurement(data);
+	if (ret < 0)
+		return ret;
+
+	ret = veml6075_read_comp(data, &c1, &c2);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_UVA, &uva);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read(data->regmap, VEML6075_CMD_UVB, &uvb);
+	if (ret < 0)
+		return ret;
+
+	uvi_micro = veml6075_get_uvi_micro(data, veml6075_uva_comp(uva, c1, c2),
+					   veml6075_uvb_comp(uvb, c1, c2));
+	if (uvi_micro < 0)
+		return uvi_micro;
+
+	*val = uvi_micro / MICRO;
+	*val2 = uvi_micro % MICRO;
+
+	return IIO_VAL_INT_PLUS_MICRO;
+}
+
+static int veml6075_read_responsivity(int chan, int *val, int *val2)
+{
+	/* scale = 1 / resp */
+	switch (chan) {
+	case CH_UVA:
+		/* resp = 0.93 c/uW/cm2: scale = 1.75268817 */
+		*val = 1;
+		*val2 = 75268817;
+		return IIO_VAL_INT_PLUS_NANO;
+	case CH_UVB:
+		/* resp = 2.1 c/uW/cm2: scale = 0.476190476 */
+		*val = 0;
+		*val2 = 476190476;
+		return IIO_VAL_INT_PLUS_NANO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_read_avail(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       const int **vals, int *type, int *length,
+			       long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_INT_TIME:
+		*length = ARRAY_SIZE(veml6075_it_ms);
+		*vals = veml6075_it_ms;
+		*type = IIO_VAL_INT;
+		return IIO_AVAIL_LIST;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int *val, int *val2, long mask)
+{
+	struct veml6075_data *data = iio_priv(indio_dev);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		return veml6075_read_uv_direct(data, chan->channel, val);
+	case IIO_CHAN_INFO_PROCESSED:
+		return veml6075_read_uvi(data, val, val2);
+	case IIO_CHAN_INFO_INT_TIME:
+		return veml6075_read_int_time_ms(data, val);
+	case IIO_CHAN_INFO_SCALE:
+		return veml6075_read_responsivity(chan->channel, val, val2);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml6075_write_int_time_ms(struct veml6075_data *data, int val)
+{
+	int i = ARRAY_SIZE(veml6075_it_ms);
+
+	guard(mutex)(&data->lock);
+
+	while (i-- > 0) {
+		if (val == veml6075_it_ms[i])
+			break;
+	}
+	if (i < 0)
+		return -EINVAL;
+
+	return regmap_update_bits(data->regmap, VEML6075_CMD_CONF,
+				  VEML6075_CONF_IT,
+				  FIELD_PREP(VEML6075_CONF_IT, i));
+}
+
+static int veml6075_write_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *chan,
+			      int val, int val2, long mask)
+{
+	struct veml6075_data *data = iio_priv(indio_dev);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_INT_TIME:
+		return veml6075_write_int_time_ms(data, val);
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info veml6075_info = {
+	.read_avail = veml6075_read_avail,
+	.read_raw = veml6075_read_raw,
+	.write_raw = veml6075_write_raw,
+};
+
+static bool veml6075_readable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case VEML6075_CMD_CONF:
+	case VEML6075_CMD_UVA:
+	case VEML6075_CMD_UVB:
+	case VEML6075_CMD_COMP1:
+	case VEML6075_CMD_COMP2:
+	case VEML6075_CMD_ID:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool veml6075_writable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case VEML6075_CMD_CONF:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config veml6075_regmap_config = {
+	.name = "veml6075",
+	.reg_bits = 8,
+	.val_bits = 16,
+	.max_register = VEML6075_CMD_ID,
+	.readable_reg = veml6075_readable_reg,
+	.writeable_reg = veml6075_writable_reg,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+};
+
+static int veml6075_probe(struct i2c_client *client)
+{
+	struct veml6075_data *data;
+	struct iio_dev *indio_dev;
+	struct regmap *regmap;
+	int config, ret;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	regmap = devm_regmap_init_i2c(client, &veml6075_regmap_config);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+	data->regmap = regmap;
+
+	mutex_init(&data->lock);
+
+	indio_dev->name = "veml6075";
+	indio_dev->info = &veml6075_info;
+	indio_dev->channels = veml6075_channels;
+	indio_dev->num_channels = ARRAY_SIZE(veml6075_channels);
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	ret = devm_regulator_get_enable(&client->dev, "vdd");
+	if (ret < 0)
+		return ret;
+
+	/* default: 100ms integration time, active force enable, shutdown */
+	config = FIELD_PREP(VEML6075_CONF_IT, VEML6075_IT_100_MS) |
+		FIELD_PREP(VEML6075_CONF_AF, VEML6075_AF_ENABLE) |
+		FIELD_PREP(VEML6075_CONF_SD, VEML6075_SD_ENABLE);
+	ret = regmap_write(data->regmap, VEML6075_CMD_CONF, config);
+	if (ret < 0)
+		return ret;
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct i2c_device_id veml6075_id[] = {
+	{ "veml6075" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, veml6075_id);
+
+static const struct of_device_id veml6075_of_match[] = {
+	{ .compatible = "vishay,veml6075" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, veml6075_of_match);
+
+static struct i2c_driver veml6075_driver = {
+	.driver = {
+		.name   = "veml6075",
+		.of_match_table = veml6075_of_match,
+	},
+	.probe = veml6075_probe,
+	.id_table = veml6075_id,
+};
+
+module_i2c_driver(veml6075_driver);
+
+MODULE_AUTHOR("Javier Carrasco <javier.carrasco.cruz@gmail.com>");
+MODULE_DESCRIPTION("Vishay VEML6075 UVA and UVB light sensor driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 7cc4e6b0e4ddf610477fcec8e3d2a9caae7e8a6c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 29 Nov 2023 18:06:46 +0200
Subject: [PATCH 0714/4076] pinctrl: Convert unsigned to unsigned int

Simple type conversion with no functional change implied.
While at it, adjust indentation where it makes sense.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231129161459.1002323-24-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c                  | 28 +++++++++----------
 drivers/pinctrl/core.h                  | 14 +++++-----
 drivers/pinctrl/devicetree.c            |  8 +++---
 drivers/pinctrl/pinconf-generic.c       | 16 +++++------
 drivers/pinctrl/pinconf.c               | 14 +++++-----
 drivers/pinctrl/pinconf.h               | 10 +++----
 drivers/pinctrl/pinctrl-utils.c         | 26 +++++++++---------
 drivers/pinctrl/pinctrl-utils.h         | 18 ++++++-------
 drivers/pinctrl/pinmux.c                | 36 ++++++++++++-------------
 drivers/pinctrl/pinmux.h                | 20 +++++++-------
 include/linux/pinctrl/machine.h         |  6 ++---
 include/linux/pinctrl/pinconf-generic.h | 10 +++----
 include/linux/pinctrl/pinconf.h         | 16 +++++------
 include/linux/pinctrl/pinctrl.h         | 24 ++++++++---------
 include/linux/pinctrl/pinmux.h          | 22 +++++++--------
 15 files changed, 134 insertions(+), 134 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index e55959e1af5a5..6d1e44efb5f39 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -143,7 +143,7 @@ struct pinctrl_dev *get_pinctrl_dev_from_of_node(struct device_node *np)
  */
 int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name)
 {
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	/* The pin number can be retrived from the pin controller descriptor */
 	for (i = 0; i < pctldev->desc->npins; i++) {
@@ -164,7 +164,7 @@ int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name)
  * @pctldev: the pin control device to lookup the pin on
  * @pin: pin number/id to look up
  */
-const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned pin)
+const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned int pin)
 {
 	const struct pin_desc *desc;
 
@@ -182,7 +182,7 @@ EXPORT_SYMBOL_GPL(pin_get_name);
 /* Deletes a range of pin descriptors */
 static void pinctrl_free_pindescs(struct pinctrl_dev *pctldev,
 				  const struct pinctrl_pin_desc *pins,
-				  unsigned num_pins)
+				  unsigned int num_pins)
 {
 	int i;
 
@@ -250,9 +250,9 @@ failed:
 
 static int pinctrl_register_pins(struct pinctrl_dev *pctldev,
 				 const struct pinctrl_pin_desc *pins,
-				 unsigned num_descs)
+				 unsigned int num_descs)
 {
-	unsigned i;
+	unsigned int i;
 	int ret = 0;
 
 	for (i = 0; i < num_descs; i++) {
@@ -426,7 +426,7 @@ EXPORT_SYMBOL_GPL(pinctrl_add_gpio_range);
 
 void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev,
 			     struct pinctrl_gpio_range *ranges,
-			     unsigned nranges)
+			     unsigned int nranges)
 {
 	int i;
 
@@ -457,7 +457,7 @@ struct pinctrl_dev *pinctrl_find_and_add_gpio_range(const char *devname,
 EXPORT_SYMBOL_GPL(pinctrl_find_and_add_gpio_range);
 
 int pinctrl_get_group_pins(struct pinctrl_dev *pctldev, const char *pin_group,
-				const unsigned **pins, unsigned *num_pins)
+			   const unsigned int **pins, unsigned int *num_pins)
 {
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	int gs;
@@ -732,8 +732,8 @@ int pinctrl_get_group_selector(struct pinctrl_dev *pctldev,
 			       const char *pin_group)
 {
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
-	unsigned ngroups = pctlops->get_groups_count(pctldev);
-	unsigned group_selector = 0;
+	unsigned int ngroups = pctlops->get_groups_count(pctldev);
+	unsigned int group_selector = 0;
 
 	while (group_selector < ngroups) {
 		const char *gname = pctlops->get_group_name(pctldev,
@@ -1430,7 +1430,7 @@ EXPORT_SYMBOL_GPL(devm_pinctrl_put);
  * @num_maps: the number of maps in the mapping table
  */
 int pinctrl_register_mappings(const struct pinctrl_map *maps,
-			      unsigned num_maps)
+			      unsigned int num_maps)
 {
 	int i, ret;
 	struct pinctrl_maps *maps_node;
@@ -1645,7 +1645,7 @@ static int pinctrl_pins_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
-	unsigned i, pin;
+	unsigned int i, pin;
 #ifdef CONFIG_GPIOLIB
 	struct gpio_device *gdev __free(gpio_device_put) = NULL;
 	struct pinctrl_gpio_range *range;
@@ -1709,7 +1709,7 @@ static int pinctrl_groups_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
-	unsigned ngroups, selector = 0;
+	unsigned int ngroups, selector = 0;
 
 	mutex_lock(&pctldev->mutex);
 
@@ -1717,8 +1717,8 @@ static int pinctrl_groups_show(struct seq_file *s, void *what)
 
 	seq_puts(s, "registered pin groups:\n");
 	while (selector < ngroups) {
-		const unsigned *pins = NULL;
-		unsigned num_pins = 0;
+		const unsigned int *pins = NULL;
+		unsigned int num_pins = 0;
 		const char *gname = ops->get_group_name(pctldev, selector);
 		const char *pname;
 		int ret = 0;
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 530370443c191..8b59dd72e4ffd 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -111,8 +111,8 @@ struct pinctrl_state {
  * @func: the function selector to program
  */
 struct pinctrl_setting_mux {
-	unsigned group;
-	unsigned func;
+	unsigned int group;
+	unsigned int func;
 };
 
 /**
@@ -124,9 +124,9 @@ struct pinctrl_setting_mux {
  * @num_configs: the number of entries in array @configs
  */
 struct pinctrl_setting_configs {
-	unsigned group_or_pin;
+	unsigned int group_or_pin;
 	unsigned long *configs;
-	unsigned num_configs;
+	unsigned int num_configs;
 };
 
 /**
@@ -173,7 +173,7 @@ struct pin_desc {
 	void *drv_data;
 	/* These fields only added when supporting pinmux drivers */
 #ifdef CONFIG_PINMUX
-	unsigned mux_usecount;
+	unsigned int mux_usecount;
 	const char *mux_owner;
 	const struct pinctrl_setting_mux *mux_setting;
 	const char *gpio_owner;
@@ -189,7 +189,7 @@ struct pin_desc {
 struct pinctrl_maps {
 	struct list_head node;
 	const struct pinctrl_map *maps;
-	unsigned num_maps;
+	unsigned int num_maps;
 };
 
 #ifdef CONFIG_GENERIC_PINCTRL_GROUPS
@@ -232,7 +232,7 @@ int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev,
 struct pinctrl_dev *get_pinctrl_dev_from_devname(const char *dev_name);
 struct pinctrl_dev *get_pinctrl_dev_from_of_node(struct device_node *np);
 int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name);
-const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned pin);
+const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned int pin);
 int pinctrl_get_group_selector(struct pinctrl_dev *pctldev,
 			       const char *pin_group);
 
diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c
index 6e0a40962f384..df1efc2e52025 100644
--- a/drivers/pinctrl/devicetree.c
+++ b/drivers/pinctrl/devicetree.c
@@ -24,11 +24,11 @@ struct pinctrl_dt_map {
 	struct list_head node;
 	struct pinctrl_dev *pctldev;
 	struct pinctrl_map *map;
-	unsigned num_maps;
+	unsigned int num_maps;
 };
 
 static void dt_free_map(struct pinctrl_dev *pctldev,
-		     struct pinctrl_map *map, unsigned num_maps)
+			struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 
@@ -64,7 +64,7 @@ void pinctrl_dt_free_maps(struct pinctrl *p)
 
 static int dt_remember_or_free_map(struct pinctrl *p, const char *statename,
 				   struct pinctrl_dev *pctldev,
-				   struct pinctrl_map *map, unsigned num_maps)
+				   struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 	struct pinctrl_dt_map *dt_map;
@@ -116,7 +116,7 @@ static int dt_to_map_one_config(struct pinctrl *p,
 	const struct pinctrl_ops *ops;
 	int ret;
 	struct pinctrl_map *map;
-	unsigned num_maps;
+	unsigned int num_maps;
 	bool allow_default = false;
 
 	/* Find the pin controller containing np_config */
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 8313cb5f3b3cd..cada5d18ffae1 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -57,7 +57,7 @@ static const struct pin_config_item conf_items[] = {
 
 static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
 				     struct seq_file *s, const char *gname,
-				     unsigned pin,
+				     unsigned int pin,
 				     const struct pin_config_item *items,
 				     int nitems, int *print_sep)
 {
@@ -110,7 +110,7 @@ static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
  * to be specified the other can be NULL/0.
  */
 void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, struct seq_file *s,
-			       const char *gname, unsigned pin)
+			       const char *gname, unsigned int pin)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
 	int print_sep = 0;
@@ -295,15 +295,15 @@ EXPORT_SYMBOL_GPL(pinconf_generic_parse_dt_config);
 
 int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np, struct pinctrl_map **map,
-		unsigned *reserved_maps, unsigned *num_maps,
+		unsigned int *reserved_maps, unsigned int *num_maps,
 		enum pinctrl_map_type type)
 {
 	int ret;
 	const char *function;
 	struct device *dev = pctldev->dev;
 	unsigned long *configs = NULL;
-	unsigned num_configs = 0;
-	unsigned reserve, strings_count;
+	unsigned int num_configs = 0;
+	unsigned int reserve, strings_count;
 	struct property *prop;
 	const char *group;
 	const char *subnode_target_type = "pins";
@@ -379,9 +379,9 @@ EXPORT_SYMBOL_GPL(pinconf_generic_dt_subnode_to_map);
 
 int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps, enum pinctrl_map_type type)
+		unsigned int *num_maps, enum pinctrl_map_type type)
 {
-	unsigned reserved_maps;
+	unsigned int reserved_maps;
 	struct device_node *np;
 	int ret;
 
@@ -412,7 +412,7 @@ EXPORT_SYMBOL_GPL(pinconf_generic_dt_node_to_map);
 
 void pinconf_generic_dt_free_map(struct pinctrl_dev *pctldev,
 				 struct pinctrl_map *map,
-				 unsigned num_maps)
+				 unsigned int num_maps)
 {
 	pinctrl_utils_free_map(pctldev, map, num_maps);
 }
diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c
index 96d853a8f339b..dca963633b5d1 100644
--- a/drivers/pinctrl/pinconf.c
+++ b/drivers/pinctrl/pinconf.c
@@ -55,7 +55,7 @@ int pinconf_validate_map(const struct pinctrl_map *map, int i)
 	return 0;
 }
 
-int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
+int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned int pin,
 			   unsigned long *config)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
@@ -199,7 +199,7 @@ int pinconf_apply_setting(const struct pinctrl_setting *setting)
 	return 0;
 }
 
-int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 		       unsigned long *configs, size_t nconfigs)
 {
 	const struct pinconf_ops *ops;
@@ -214,7 +214,7 @@ int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
 #ifdef CONFIG_DEBUG_FS
 
 static void pinconf_show_config(struct seq_file *s, struct pinctrl_dev *pctldev,
-		      unsigned long *configs, unsigned num_configs)
+				unsigned long *configs, unsigned int num_configs)
 {
 	const struct pinconf_ops *confops;
 	int i;
@@ -304,7 +304,7 @@ static void pinconf_dump_pin(struct pinctrl_dev *pctldev,
 static int pinconf_pins_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	seq_puts(s, "Pin config settings per pin\n");
 	seq_puts(s, "Format: pin (name): configs\n");
@@ -333,7 +333,7 @@ static int pinconf_pins_show(struct seq_file *s, void *what)
 }
 
 static void pinconf_dump_group(struct pinctrl_dev *pctldev,
-			       struct seq_file *s, unsigned selector,
+			       struct seq_file *s, unsigned int selector,
 			       const char *gname)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
@@ -348,8 +348,8 @@ static int pinconf_groups_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
-	unsigned ngroups = pctlops->get_groups_count(pctldev);
-	unsigned selector = 0;
+	unsigned int ngroups = pctlops->get_groups_count(pctldev);
+	unsigned int selector = 0;
 
 	seq_puts(s, "Pin config settings per pin group\n");
 	seq_puts(s, "Format: group (name): configs\n");
diff --git a/drivers/pinctrl/pinconf.h b/drivers/pinctrl/pinconf.h
index 694bfc9961faf..a14c950bc7004 100644
--- a/drivers/pinctrl/pinconf.h
+++ b/drivers/pinctrl/pinconf.h
@@ -29,14 +29,14 @@ int pinconf_map_to_setting(const struct pinctrl_map *map,
 void pinconf_free_setting(const struct pinctrl_setting *setting);
 int pinconf_apply_setting(const struct pinctrl_setting *setting);
 
-int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 		       unsigned long *configs, size_t nconfigs);
 
 /*
  * You will only be interested in these if you're using PINCONF
  * so don't supply any stubs for these.
  */
-int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
+int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned int pin,
 			   unsigned long *config);
 int pin_config_group_get(const char *dev_name, const char *pin_group,
 			 unsigned long *config);
@@ -68,7 +68,7 @@ static inline int pinconf_apply_setting(const struct pinctrl_setting *setting)
 	return 0;
 }
 
-static inline int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+static inline int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 				     unsigned long *configs, size_t nconfigs)
 {
 	return -ENOTSUPP;
@@ -112,7 +112,7 @@ static inline void pinconf_init_device_debugfs(struct dentry *devroot,
 
 void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
 			       struct seq_file *s, const char *gname,
-			       unsigned pin);
+			       unsigned int pin);
 
 void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 				 struct seq_file *s, unsigned long config);
@@ -120,7 +120,7 @@ void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 
 static inline void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
 					     struct seq_file *s,
-					     const char *gname, unsigned pin)
+					     const char *gname, unsigned int pin)
 {
 	return;
 }
diff --git a/drivers/pinctrl/pinctrl-utils.c b/drivers/pinctrl/pinctrl-utils.c
index 40862f7bd6ca0..d81d7b46116cc 100644
--- a/drivers/pinctrl/pinctrl-utils.c
+++ b/drivers/pinctrl/pinctrl-utils.c
@@ -18,11 +18,11 @@
 #include "pinctrl-utils.h"
 
 int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, unsigned reserve)
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, unsigned int reserve)
 {
-	unsigned old_num = *reserved_maps;
-	unsigned new_num = *num_maps + reserve;
+	unsigned int old_num = *reserved_maps;
+	unsigned int new_num = *num_maps + reserve;
 	struct pinctrl_map *new_map;
 
 	if (old_num >= new_num)
@@ -43,8 +43,8 @@ int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_reserve_map);
 
 int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
 		const char *function)
 {
 	if (WARN_ON(*num_maps == *reserved_maps))
@@ -60,9 +60,9 @@ int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_mux);
 
 int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
-		unsigned long *configs, unsigned num_configs,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
+		unsigned long *configs, unsigned int num_configs,
 		enum pinctrl_map_type type)
 {
 	unsigned long *dup_configs;
@@ -86,11 +86,11 @@ int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_configs);
 
 int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
-		unsigned long **configs, unsigned *num_configs,
+		unsigned long **configs, unsigned int *num_configs,
 		unsigned long config)
 {
-	unsigned old_num = *num_configs;
-	unsigned new_num = old_num + 1;
+	unsigned int old_num = *num_configs;
+	unsigned int new_num = old_num + 1;
 	unsigned long *new_configs;
 
 	new_configs = krealloc(*configs, sizeof(*new_configs) * new_num,
@@ -110,7 +110,7 @@ int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_config);
 
 void pinctrl_utils_free_map(struct pinctrl_dev *pctldev,
-	      struct pinctrl_map *map, unsigned num_maps)
+	      struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 
diff --git a/drivers/pinctrl/pinctrl-utils.h b/drivers/pinctrl/pinctrl-utils.h
index 4108ee2dd6d02..203fba257d717 100644
--- a/drivers/pinctrl/pinctrl-utils.h
+++ b/drivers/pinctrl/pinctrl-utils.h
@@ -15,21 +15,21 @@ struct pinctrl_dev;
 struct pinctrl_map;
 
 int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, unsigned reserve);
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, unsigned int reserve);
 int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
 		const char *function);
 int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
-		unsigned long *configs, unsigned num_configs,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
+		unsigned long *configs, unsigned int num_configs,
 		enum pinctrl_map_type type);
 int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
-		unsigned long **configs, unsigned *num_configs,
+		unsigned long **configs, unsigned int *num_configs,
 		unsigned long config);
 void pinctrl_utils_free_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map *map, unsigned num_maps);
+		struct pinctrl_map *map, unsigned int num_maps);
 
 #endif /* __PINCTRL_UTILS_H__ */
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index 23d2da0b99b92..abbb044d6acec 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -35,8 +35,8 @@
 int pinmux_check_ops(struct pinctrl_dev *pctldev)
 {
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
-	unsigned nfuncs;
-	unsigned selector = 0;
+	unsigned int nfuncs;
+	unsigned int selector = 0;
 
 	/* Check that we implement required operations */
 	if (!ops ||
@@ -84,7 +84,7 @@ int pinmux_validate_map(const struct pinctrl_map *map, int i)
  * Controllers not defined as strict will always return true,
  * menaning that the gpio can be used.
  */
-bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned pin)
+bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned int pin)
 {
 	struct pin_desc *desc = pin_desc_get(pctldev, pin);
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
@@ -262,7 +262,7 @@ static const char *pin_free(struct pinctrl_dev *pctldev, int pin,
  */
 int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio)
+			unsigned int pin, unsigned int gpio)
 {
 	const char *owner;
 	int ret;
@@ -285,7 +285,7 @@ int pinmux_request_gpio(struct pinctrl_dev *pctldev,
  * @pin: the affected currently GPIO-muxed in pin
  * @range: applicable GPIO range
  */
-void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
+void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned int pin,
 		      struct pinctrl_gpio_range *range)
 {
 	const char *owner;
@@ -303,7 +303,7 @@ void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
  */
 int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 			  struct pinctrl_gpio_range *range,
-			  unsigned pin, bool input)
+			  unsigned int pin, bool input)
 {
 	const struct pinmux_ops *ops;
 	int ret;
@@ -322,8 +322,8 @@ static int pinmux_func_name_to_selector(struct pinctrl_dev *pctldev,
 					const char *function)
 {
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
-	unsigned nfuncs = ops->get_functions_count(pctldev);
-	unsigned selector = 0;
+	unsigned int nfuncs = ops->get_functions_count(pctldev);
+	unsigned int selector = 0;
 
 	/* See if this pctldev has this function */
 	while (selector < nfuncs) {
@@ -344,7 +344,7 @@ int pinmux_map_to_setting(const struct pinctrl_map *map,
 	struct pinctrl_dev *pctldev = setting->pctldev;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
 	char const * const *groups;
-	unsigned num_groups;
+	unsigned int num_groups;
 	int ret;
 	const char *group;
 
@@ -409,8 +409,8 @@ int pinmux_enable_setting(const struct pinctrl_setting *setting)
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
 	int ret = 0;
-	const unsigned *pins = NULL;
-	unsigned num_pins = 0;
+	const unsigned int *pins = NULL;
+	unsigned int num_pins = 0;
 	int i;
 	struct pin_desc *desc;
 
@@ -489,8 +489,8 @@ void pinmux_disable_setting(const struct pinctrl_setting *setting)
 	struct pinctrl_dev *pctldev = setting->pctldev;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	int ret = 0;
-	const unsigned *pins = NULL;
-	unsigned num_pins = 0;
+	const unsigned int *pins = NULL;
+	unsigned int num_pins = 0;
 	int i;
 	struct pin_desc *desc;
 
@@ -541,8 +541,8 @@ static int pinmux_functions_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
-	unsigned nfuncs;
-	unsigned func_selector = 0;
+	unsigned int nfuncs;
+	unsigned int func_selector = 0;
 
 	if (!pmxops)
 		return 0;
@@ -553,7 +553,7 @@ static int pinmux_functions_show(struct seq_file *s, void *what)
 		const char *func = pmxops->get_function_name(pctldev,
 							  func_selector);
 		const char * const *groups;
-		unsigned num_groups;
+		unsigned int num_groups;
 		int ret;
 		int i;
 
@@ -584,7 +584,7 @@ static int pinmux_pins_show(struct seq_file *s, void *what)
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	if (!pmxops)
 		return 0;
@@ -818,7 +818,7 @@ EXPORT_SYMBOL_GPL(pinmux_generic_get_function_name);
 int pinmux_generic_get_function_groups(struct pinctrl_dev *pctldev,
 				       unsigned int selector,
 				       const char * const **groups,
-				       unsigned * const num_groups)
+				       unsigned int * const num_groups)
 {
 	struct function_desc *function;
 
diff --git a/drivers/pinctrl/pinmux.h b/drivers/pinctrl/pinmux.h
index ea6f99c24aa5e..7c8aa25ccc806 100644
--- a/drivers/pinctrl/pinmux.h
+++ b/drivers/pinctrl/pinmux.h
@@ -26,16 +26,16 @@ int pinmux_check_ops(struct pinctrl_dev *pctldev);
 
 int pinmux_validate_map(const struct pinctrl_map *map, int i);
 
-bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned pin);
+bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned int pin);
 
 int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio);
-void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
+			unsigned int pin, unsigned int gpio);
+void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned int pin,
 		      struct pinctrl_gpio_range *range);
 int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 			  struct pinctrl_gpio_range *range,
-			  unsigned pin, bool input);
+			  unsigned int pin, bool input);
 
 int pinmux_map_to_setting(const struct pinctrl_map *map,
 			  struct pinctrl_setting *setting);
@@ -56,27 +56,27 @@ static inline int pinmux_validate_map(const struct pinctrl_map *map, int i)
 }
 
 static inline bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev,
-					       unsigned pin)
+					       unsigned int pin)
 {
 	return true;
 }
 
 static inline int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio)
+			unsigned int pin, unsigned int gpio)
 {
 	return 0;
 }
 
 static inline void pinmux_free_gpio(struct pinctrl_dev *pctldev,
-				    unsigned pin,
+				    unsigned int pin,
 				    struct pinctrl_gpio_range *range)
 {
 }
 
 static inline int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 					struct pinctrl_gpio_range *range,
-					unsigned pin, bool input)
+					unsigned int pin, bool input)
 {
 	return 0;
 }
@@ -154,7 +154,7 @@ pinmux_generic_get_function_name(struct pinctrl_dev *pctldev,
 int pinmux_generic_get_function_groups(struct pinctrl_dev *pctldev,
 				       unsigned int selector,
 				       const char * const **groups,
-				       unsigned * const num_groups);
+				       unsigned int * const num_groups);
 
 struct function_desc *pinmux_generic_get_function(struct pinctrl_dev *pctldev,
 						  unsigned int selector);
@@ -162,7 +162,7 @@ struct function_desc *pinmux_generic_get_function(struct pinctrl_dev *pctldev,
 int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 				const char *name,
 				const char * const *groups,
-				unsigned const num_groups,
+				unsigned int const num_groups,
 				void *data);
 
 int pinmux_generic_remove_function(struct pinctrl_dev *pctldev,
diff --git a/include/linux/pinctrl/machine.h b/include/linux/pinctrl/machine.h
index ee8803f6ad07c..673e96df453b3 100644
--- a/include/linux/pinctrl/machine.h
+++ b/include/linux/pinctrl/machine.h
@@ -47,7 +47,7 @@ struct pinctrl_map_mux {
 struct pinctrl_map_configs {
 	const char *group_or_pin;
 	unsigned long *configs;
-	unsigned num_configs;
+	unsigned int num_configs;
 };
 
 /**
@@ -154,13 +154,13 @@ struct pinctrl_map;
 #ifdef CONFIG_PINCTRL
 
 extern int pinctrl_register_mappings(const struct pinctrl_map *map,
-				     unsigned num_maps);
+				     unsigned int num_maps);
 extern void pinctrl_unregister_mappings(const struct pinctrl_map *map);
 extern void pinctrl_provide_dummies(void);
 #else
 
 static inline int pinctrl_register_mappings(const struct pinctrl_map *map,
-					    unsigned num_maps)
+					    unsigned int num_maps)
 {
 	return 0;
 }
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index d74b7a4ea154d..a65d3d078e58b 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -193,17 +193,17 @@ struct pinconf_generic_params {
 
 int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np, struct pinctrl_map **map,
-		unsigned *reserved_maps, unsigned *num_maps,
+		unsigned int *reserved_maps, unsigned int *num_maps,
 		enum pinctrl_map_type type);
 int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps, enum pinctrl_map_type type);
+		unsigned int *num_maps, enum pinctrl_map_type type);
 void pinconf_generic_dt_free_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map *map, unsigned num_maps);
+		struct pinctrl_map *map, unsigned int num_maps);
 
 static inline int pinconf_generic_dt_node_to_map_group(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps)
+		unsigned int *num_maps)
 {
 	return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps,
 			PIN_MAP_TYPE_CONFIGS_GROUP);
@@ -211,7 +211,7 @@ static inline int pinconf_generic_dt_node_to_map_group(struct pinctrl_dev *pctld
 
 static inline int pinconf_generic_dt_node_to_map_pin(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps)
+		unsigned int *num_maps)
 {
 	return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps,
 			PIN_MAP_TYPE_CONFIGS_PIN);
diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h
index f8a8215e9021e..770ec2221156c 100644
--- a/include/linux/pinctrl/pinconf.h
+++ b/include/linux/pinctrl/pinconf.h
@@ -40,25 +40,25 @@ struct pinconf_ops {
 	bool is_generic;
 #endif
 	int (*pin_config_get) (struct pinctrl_dev *pctldev,
-			       unsigned pin,
+			       unsigned int pin,
 			       unsigned long *config);
 	int (*pin_config_set) (struct pinctrl_dev *pctldev,
-			       unsigned pin,
+			       unsigned int pin,
 			       unsigned long *configs,
-			       unsigned num_configs);
+			       unsigned int num_configs);
 	int (*pin_config_group_get) (struct pinctrl_dev *pctldev,
-				     unsigned selector,
+				     unsigned int selector,
 				     unsigned long *config);
 	int (*pin_config_group_set) (struct pinctrl_dev *pctldev,
-				     unsigned selector,
+				     unsigned int selector,
 				     unsigned long *configs,
-				     unsigned num_configs);
+				     unsigned int num_configs);
 	void (*pin_config_dbg_show) (struct pinctrl_dev *pctldev,
 				     struct seq_file *s,
-				     unsigned offset);
+				     unsigned int offset);
 	void (*pin_config_group_dbg_show) (struct pinctrl_dev *pctldev,
 					   struct seq_file *s,
-					   unsigned selector);
+					   unsigned int selector);
 	void (*pin_config_config_dbg_show) (struct pinctrl_dev *pctldev,
 					    struct seq_file *s,
 					    unsigned long config);
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 4d252ea00ed1a..9a8189ffd0f2c 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -54,7 +54,7 @@ struct pingroup {
  * @drv_data: driver-defined per-pin data. pinctrl core does not touch this
  */
 struct pinctrl_pin_desc {
-	unsigned number;
+	unsigned int number;
 	const char *name;
 	void *drv_data;
 };
@@ -82,7 +82,7 @@ struct pinctrl_gpio_range {
 	unsigned int base;
 	unsigned int pin_base;
 	unsigned int npins;
-	unsigned const *pins;
+	unsigned int const *pins;
 	struct gpio_chip *gc;
 };
 
@@ -108,18 +108,18 @@ struct pinctrl_gpio_range {
 struct pinctrl_ops {
 	int (*get_groups_count) (struct pinctrl_dev *pctldev);
 	const char *(*get_group_name) (struct pinctrl_dev *pctldev,
-				       unsigned selector);
+				       unsigned int selector);
 	int (*get_group_pins) (struct pinctrl_dev *pctldev,
-			       unsigned selector,
-			       const unsigned **pins,
-			       unsigned *num_pins);
+			       unsigned int selector,
+			       const unsigned int **pins,
+			       unsigned int *num_pins);
 	void (*pin_dbg_show) (struct pinctrl_dev *pctldev, struct seq_file *s,
-			  unsigned offset);
+			      unsigned int offset);
 	int (*dt_node_to_map) (struct pinctrl_dev *pctldev,
 			       struct device_node *np_config,
-			       struct pinctrl_map **map, unsigned *num_maps);
+			       struct pinctrl_map **map, unsigned int *num_maps);
 	void (*dt_free_map) (struct pinctrl_dev *pctldev,
-			     struct pinctrl_map *map, unsigned num_maps);
+			     struct pinctrl_map *map, unsigned int num_maps);
 };
 
 /**
@@ -193,7 +193,7 @@ extern void pinctrl_add_gpio_range(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *range);
 extern void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *ranges,
-				unsigned nranges);
+				unsigned int nranges);
 extern void pinctrl_remove_gpio_range(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *range);
 
@@ -203,8 +203,8 @@ extern struct pinctrl_gpio_range *
 pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev,
 				 unsigned int pin);
 extern int pinctrl_get_group_pins(struct pinctrl_dev *pctldev,
-				const char *pin_group, const unsigned **pins,
-				unsigned *num_pins);
+				  const char *pin_group, const unsigned int **pins,
+				  unsigned int *num_pins);
 
 /**
  * struct pinfunction - Description about a function
diff --git a/include/linux/pinctrl/pinmux.h b/include/linux/pinctrl/pinmux.h
index a7e370965c531..d6f7b58d6ad0c 100644
--- a/include/linux/pinctrl/pinmux.h
+++ b/include/linux/pinctrl/pinmux.h
@@ -57,26 +57,26 @@ struct pinctrl_gpio_range;
  *	the pin request.
  */
 struct pinmux_ops {
-	int (*request) (struct pinctrl_dev *pctldev, unsigned offset);
-	int (*free) (struct pinctrl_dev *pctldev, unsigned offset);
+	int (*request) (struct pinctrl_dev *pctldev, unsigned int offset);
+	int (*free) (struct pinctrl_dev *pctldev, unsigned int offset);
 	int (*get_functions_count) (struct pinctrl_dev *pctldev);
 	const char *(*get_function_name) (struct pinctrl_dev *pctldev,
-					  unsigned selector);
+					  unsigned int selector);
 	int (*get_function_groups) (struct pinctrl_dev *pctldev,
-				  unsigned selector,
-				  const char * const **groups,
-				  unsigned *num_groups);
-	int (*set_mux) (struct pinctrl_dev *pctldev, unsigned func_selector,
-			unsigned group_selector);
+				    unsigned int selector,
+				    const char * const **groups,
+				    unsigned int *num_groups);
+	int (*set_mux) (struct pinctrl_dev *pctldev, unsigned int func_selector,
+			unsigned int group_selector);
 	int (*gpio_request_enable) (struct pinctrl_dev *pctldev,
 				    struct pinctrl_gpio_range *range,
-				    unsigned offset);
+				    unsigned int offset);
 	void (*gpio_disable_free) (struct pinctrl_dev *pctldev,
 				   struct pinctrl_gpio_range *range,
-				   unsigned offset);
+				   unsigned int offset);
 	int (*gpio_set_direction) (struct pinctrl_dev *pctldev,
 				   struct pinctrl_gpio_range *range,
-				   unsigned offset,
+				   unsigned int offset,
 				   bool input);
 	bool strict;
 };
-- 
GitLab


From 142173c4ad5a981ce2c7b97ecc283885e7e778b6 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 Nov 2023 16:46:35 +0200
Subject: [PATCH 0715/4076] pinctrl: mediatek: Switch to use no-IRQ PM helpers

Since pm.h provides a helper for system no-IRQ PM callbacks,
switch the driver to use it instead of open coded variant.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231122144744.2222207-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mediatek/pinctrl-mt2701.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt2712.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt6795.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8167.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8173.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8183.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8186.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8188.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8192.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8195.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8365.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mt8516.c     | 2 +-
 drivers/pinctrl/mediatek/pinctrl-mtk-common.c | 5 ++---
 drivers/pinctrl/mediatek/pinctrl-paris.c      | 5 ++---
 14 files changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/pinctrl/mediatek/pinctrl-mt2701.c b/drivers/pinctrl/mediatek/pinctrl-mt2701.c
index 5fb377c1668bb..6b1c7122b0fb9 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt2701.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt2701.c
@@ -533,7 +533,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt2701-pinctrl",
 		.of_match_table = mt2701_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt2712.c b/drivers/pinctrl/mediatek/pinctrl-mt2712.c
index 8a6daa0db54b0..bb7394ae252b4 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt2712.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt2712.c
@@ -581,7 +581,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt2712-pinctrl",
 		.of_match_table = mt2712_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt6795.c b/drivers/pinctrl/mediatek/pinctrl-mt6795.c
index 01e855ccd4dd9..ee3ae3d2fa7e8 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt6795.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt6795.c
@@ -612,7 +612,7 @@ static struct platform_driver mt6795_pinctrl_driver = {
 	.driver = {
 		.name = "mt6795-pinctrl",
 		.of_match_table = mt6795_pctrl_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8167.c b/drivers/pinctrl/mediatek/pinctrl-mt8167.c
index ba7f30c3296fe..143c266222725 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8167.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8167.c
@@ -334,7 +334,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt8167-pinctrl",
 		.of_match_table = mt8167_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8173.c b/drivers/pinctrl/mediatek/pinctrl-mt8173.c
index 455eec018f93e..b214deeafbf1d 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8173.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8173.c
@@ -347,7 +347,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt8173-pinctrl",
 		.of_match_table = mt8173_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8183.c b/drivers/pinctrl/mediatek/pinctrl-mt8183.c
index ddc48b725c22d..93e482c6b5fda 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8183.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8183.c
@@ -576,7 +576,7 @@ static struct platform_driver mt8183_pinctrl_driver = {
 	.driver = {
 		.name = "mt8183-pinctrl",
 		.of_match_table = mt8183_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8186.c b/drivers/pinctrl/mediatek/pinctrl-mt8186.c
index a02f7c3269707..7be591591cce5 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8186.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8186.c
@@ -1255,7 +1255,7 @@ static struct platform_driver mt8186_pinctrl_driver = {
 	.driver = {
 		.name = "mt8186-pinctrl",
 		.of_match_table = mt8186_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8188.c b/drivers/pinctrl/mediatek/pinctrl-mt8188.c
index c067e043e6192..3975e99d9cf40 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8188.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8188.c
@@ -1658,7 +1658,7 @@ static struct platform_driver mt8188_pinctrl_driver = {
 	.driver = {
 		.name = "mt8188-pinctrl",
 		.of_match_table = mt8188_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops)
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8192.c b/drivers/pinctrl/mediatek/pinctrl-mt8192.c
index dee1b3aefd36e..e3a76381f7f4e 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8192.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8192.c
@@ -1420,7 +1420,7 @@ static struct platform_driver mt8192_pinctrl_driver = {
 	.driver = {
 		.name = "mt8192-pinctrl",
 		.of_match_table = mt8192_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8195.c b/drivers/pinctrl/mediatek/pinctrl-mt8195.c
index 09c4dcef93383..83345c52b2fa2 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8195.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8195.c
@@ -968,7 +968,7 @@ static struct platform_driver mt8195_pinctrl_driver = {
 	.driver = {
 		.name = "mt8195-pinctrl",
 		.of_match_table = mt8195_pinctrl_of_match,
-		.pm = &mtk_paris_pinctrl_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_paris_pinctrl_pm_ops),
 	},
 	.probe = mtk_paris_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8365.c b/drivers/pinctrl/mediatek/pinctrl-mt8365.c
index 1db04bbdb4236..e3e0d66cfbbfc 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8365.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8365.c
@@ -484,7 +484,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt8365-pinctrl",
 		.of_match_table = mt8365_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8516.c b/drivers/pinctrl/mediatek/pinctrl-mt8516.c
index 950275c47122b..abda75d4354e2 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8516.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8516.c
@@ -334,7 +334,7 @@ static struct platform_driver mtk_pinctrl_driver = {
 	.driver = {
 		.name = "mediatek-mt8516-pinctrl",
 		.of_match_table = mt8516_pctrl_match,
-		.pm = &mtk_eint_pm_ops,
+		.pm = pm_sleep_ptr(&mtk_eint_pm_ops),
 	},
 };
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index e79d66a041940..d39afc122516f 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -914,9 +914,8 @@ static int mtk_eint_resume(struct device *device)
 	return mtk_eint_do_resume(pctl->eint);
 }
 
-const struct dev_pm_ops mtk_eint_pm_ops = {
-	.suspend_noirq = mtk_eint_suspend,
-	.resume_noirq = mtk_eint_resume,
+EXPORT_GPL_DEV_SLEEP_PM_OPS(mtk_eint_pm_ops) = {
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_eint_suspend, mtk_eint_resume)
 };
 
 static int mtk_pctrl_build_state(struct platform_device *pdev)
diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c
index 6392f1e05d028..b6bc31abd2b06 100644
--- a/drivers/pinctrl/mediatek/pinctrl-paris.c
+++ b/drivers/pinctrl/mediatek/pinctrl-paris.c
@@ -1131,9 +1131,8 @@ static int mtk_paris_pinctrl_resume(struct device *device)
 	return mtk_eint_do_resume(pctl->eint);
 }
 
-const struct dev_pm_ops mtk_paris_pinctrl_pm_ops = {
-	.suspend_noirq = mtk_paris_pinctrl_suspend,
-	.resume_noirq = mtk_paris_pinctrl_resume,
+EXPORT_GPL_DEV_SLEEP_PM_OPS(mtk_paris_pinctrl_pm_ops) = {
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_paris_pinctrl_suspend, mtk_paris_pinctrl_resume)
 };
 
 MODULE_LICENSE("GPL v2");
-- 
GitLab


From 27030ff7877262b0555a2870b0e401ebbc0e72c3 Mon Sep 17 00:00:00 2001
From: Richard Acayan <mailingradian@gmail.com>
Date: Mon, 27 Nov 2023 21:02:04 -0500
Subject: [PATCH 0716/4076] pinctrl: qcom: fail to retrieve configuration from
 invalid pin groups

The pinconf-groups debugfs file dumps each valid configuration item of
all pin groups. Some platforms and devices may have pin groups which
cannot be accessed, according to commit 691bf5d5a7bf ("pinctrl: qcom:
Don't allow protected pins to be requested"). Fail for each
configuration item of an invalid pin group by checking the GPIO chip's
valid mask.

The validity of the pin group cannot be checked in the generic pinconf
dump (function "pinconf_generic_dump_one"), as it does not directly
interact with the gpiochip or the pinmux callbacks (which would give it
access to the request callback). Instead, an entry contains the ID and
name of the pingroup with no properties when all items fail.

Signed-off-by: Richard Acayan <mailingradian@gmail.com>
Link: https://lore.kernel.org/r/20231128020202.728156-3-mailingradian@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-msm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 207b410185800..aeaf0d1958f56 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -358,6 +358,10 @@ static int msm_config_group_get(struct pinctrl_dev *pctldev,
 	int ret;
 	u32 val;
 
+	/* Pin information can only be requested from valid pin groups */
+	if (!gpiochip_line_is_valid(&pctrl->chip, group))
+		return -EINVAL;
+
 	g = &pctrl->soc->groups[group];
 
 	ret = msm_config_reg(pctrl, g, param, &mask, &bit);
-- 
GitLab


From aa587ff2abdb773db74e4bf5856631d274b73466 Mon Sep 17 00:00:00 2001
From: Thomas Richard <thomas.richard@bootlin.com>
Date: Tue, 28 Nov 2023 16:34:59 +0100
Subject: [PATCH 0717/4076] dt-bindings: pinctrl: pinctrl-single: add
 ti,j7200-padconf compatible

Add the "ti,j7200-padconf" compatible to support suspend to ram on
j7200.

Signed-off-by: Thomas Richard <thomas.richard@bootlin.com>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231128-j7200-pinctrl-s2r-v1-1-704e7dc24460@bootlin.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml b/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
index 45a307d3ce167..c11495524dd26 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-single.yaml
@@ -31,6 +31,7 @@ properties:
               - ti,omap3-padconf
               - ti,omap4-padconf
               - ti,omap5-padconf
+              - ti,j7200-padconf
           - const: pinctrl-single
 
   reg:
-- 
GitLab


From e24b623d95207735226a57dc0a0019b7da12ad6b Mon Sep 17 00:00:00 2001
From: Thomas Richard <thomas.richard@bootlin.com>
Date: Tue, 28 Nov 2023 16:35:00 +0100
Subject: [PATCH 0718/4076] pinctrl: pinctrl-single: add ti,j7200-padconf
 compatible

On j7200, during suspend to ram pinctrl contexts are lost. To save and
restore contexts during suspend/resume, the flag PCS_CONTEXT_LOSS_OFF
shall be set.

Signed-off-by: Thomas Richard <thomas.richard@bootlin.com>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231128-j7200-pinctrl-s2r-v1-2-704e7dc24460@bootlin.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-single.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 8267be7696352..19cc0db771a5a 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1955,6 +1955,10 @@ static const struct pcs_soc_data pinctrl_single_am654 = {
 	.irq_status_mask = (1 << 30),   /* WKUP_EVT */
 };
 
+static const struct pcs_soc_data pinctrl_single_j7200 = {
+	.flags = PCS_CONTEXT_LOSS_OFF,
+};
+
 static const struct pcs_soc_data pinctrl_single = {
 };
 
@@ -1969,6 +1973,7 @@ static const struct of_device_id pcs_of_match[] = {
 	{ .compatible = "ti,omap3-padconf", .data = &pinctrl_single_omap_wkup },
 	{ .compatible = "ti,omap4-padconf", .data = &pinctrl_single_omap_wkup },
 	{ .compatible = "ti,omap5-padconf", .data = &pinctrl_single_omap_wkup },
+	{ .compatible = "ti,j7200-padconf", .data = &pinctrl_single_j7200 },
 	{ .compatible = "pinctrl-single", .data = &pinctrl_single },
 	{ .compatible = "pinconf-single", .data = &pinconf_single },
 	{ },
-- 
GitLab


From 253bad7f0436284ee0413b1c615a1d4be96893de Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 29 Nov 2023 16:57:38 +0100
Subject: [PATCH 0719/4076] dt-bindings: pinctrl: qcom,sm8550-lpass-lpi: add
 X1E80100 LPASS LPI

Document the Qualcomm X1E80100 SoC Low Power Audio SubSystem Low Power
Island (LPASS LPI) pin controller, compatible with earlier SM8550 model.

Cc: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20231129155738.167030-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml     | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
index ef97432468498..ad5e32130fd75 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
@@ -16,7 +16,11 @@ description:
 
 properties:
   compatible:
-    const: qcom,sm8550-lpass-lpi-pinctrl
+    oneOf:
+      - const: qcom,sm8550-lpass-lpi-pinctrl
+      - items:
+          - const: qcom,x1e80100-lpass-lpi-pinctrl
+          - const: qcom,sm8550-lpass-lpi-pinctrl
 
   reg:
     items:
-- 
GitLab


From 8c82e9e3766b8a7e6a4c633dab5b652333ada78f Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Mon, 27 Nov 2023 22:26:52 +0100
Subject: [PATCH 0720/4076] dt-bindings: iio: light: isl76682: Document
 ISL76682

The ISL76682 is very basic ALS which only supports ALS or IR mode
in four ranges, 1k/4k/16k/64k LUX. There is no IRQ support or any
other fancy functionality. Document it as trivial device.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Marek Vasut <marex@denx.de>
Link: https://lore.kernel.org/r/20231127212726.77707-1-marex@denx.de
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/trivial-devices.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index c3190f2a168a2..27164e9219276 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -179,6 +179,8 @@ properties:
           - isil,isl29030
             # Intersil ISL68137 Digital Output Configurable PWM Controller
           - isil,isl68137
+            # Intersil ISL76682 Ambient Light Sensor
+          - isil,isl76682
             # Linear Technology LTC2488
           - lineartechnology,ltc2488
             # 5 Bit Programmable, Pulse-Width Modulator
-- 
GitLab


From 54373b5d53c1f6aa6164ee5bea4761abb16b351c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 1 Dec 2023 14:52:00 -0300
Subject: [PATCH 0721/4076] perf env: Introduce perf_env__arch_strerrno()

That will cache the arch specific function translating error numbers to
strings.

Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20231201203046.486596-2-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c |  6 ++----
 tools/perf/util/env.c      | 12 ++++++++++++
 tools/perf/util/env.h      |  1 +
 3 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e541d0e2777ab..109b8e64fe69a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2470,9 +2470,8 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam
 static const char *errno_to_name(struct evsel *evsel, int err)
 {
 	struct perf_env *env = evsel__env(evsel);
-	const char *arch_name = perf_env__arch(env);
 
-	return arch_syscalls__strerrno(arch_name, err);
+	return perf_env__arch_strerrno(env, err);
 }
 
 static int trace__sys_exit(struct trace *trace, struct evsel *evsel,
@@ -4264,12 +4263,11 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 			printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
 
 			if (trace->errno_summary && stats->nr_failures) {
-				const char *arch_name = perf_env__arch(trace->host->env);
 				int e;
 
 				for (e = 0; e < stats->max_errno; ++e) {
 					if (stats->errnos[e] != 0)
-						fprintf(fp, "\t\t\t\t%s: %d\n", arch_syscalls__strerrno(arch_name, e + 1), stats->errnos[e]);
+						fprintf(fp, "\t\t\t\t%s: %d\n", perf_env__arch_strerrno(trace->host->env, e + 1), stats->errnos[e]);
 				}
 			}
 		}
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index cbc18b22ace52..a632f33646bb3 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -3,6 +3,7 @@
 #include "debug.h"
 #include "env.h"
 #include "util/header.h"
+#include "linux/compiler.h"
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 #include "cgroup.h"
@@ -12,6 +13,7 @@
 #include <string.h>
 #include "pmus.h"
 #include "strbuf.h"
+#include "trace/beauty/beauty.h"
 
 struct perf_env perf_env;
 
@@ -453,6 +455,16 @@ const char *perf_env__arch(struct perf_env *env)
 	return normalize_arch(arch_name);
 }
 
+const char *perf_env__arch_strerrno(struct perf_env *env __maybe_unused, int err __maybe_unused)
+{
+#if defined(HAVE_SYSCALL_TABLE_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
+	const char *arch_name = perf_env__arch(env);
+	return arch_syscalls__strerrno(arch_name, err);
+#else
+	return "!(HAVE_SYSCALL_TABLE_SUPPORT && HAVE_LIBTRACEEVENT)";
+#endif
+}
+
 const char *perf_env__cpuid(struct perf_env *env)
 {
 	int status;
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 94596ff124d54..79f371879f45b 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -164,6 +164,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env);
 void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__arch(struct perf_env *env);
+const char *perf_env__arch_strerrno(struct perf_env *env, int err);
 const char *perf_env__cpuid(struct perf_env *env);
 const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
-- 
GitLab


From 4acef67646f35e14d202d5f534c0fd68d7691b22 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 1 Dec 2023 17:07:34 -0300
Subject: [PATCH 0722/4076] perf env: Cache the arch specific strerrno function
 in perf_env__arch_strerrno()

So that we don't have to go thru the series of strcmp(arch) calls for
each id -> string translation.

Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20231201203046.486596-3-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/arch_errno_names.sh | 6 +++---
 tools/perf/trace/beauty/beauty.h            | 2 --
 tools/perf/util/env.c                       | 6 ++++--
 tools/perf/util/env.h                       | 5 +++++
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh
index b6e0767b4b34e..7df4bf5b55a3c 100755
--- a/tools/perf/trace/beauty/arch_errno_names.sh
+++ b/tools/perf/trace/beauty/arch_errno_names.sh
@@ -57,13 +57,13 @@ create_arch_errno_table_func()
 	archlist="$1"
 	default="$2"
 
-	printf 'const char *arch_syscalls__strerrno(const char *arch, int err)\n'
+	printf 'arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch)\n'
 	printf '{\n'
 	for arch in $archlist; do
 		printf '\tif (!strcmp(arch, "%s"))\n' $(arch_string "$arch")
-		printf '\t\treturn errno_to_name__%s(err);\n' $(arch_string "$arch")
+		printf '\t\treturn errno_to_name__%s;\n' $(arch_string "$arch")
 	done
-	printf '\treturn errno_to_name__%s(err);\n' $(arch_string "$default")
+	printf '\treturn errno_to_name__%s;\n' $(arch_string "$default")
 	printf '}\n'
 }
 
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 788e8f6bd90eb..9feb794f5c6e1 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -251,6 +251,4 @@ size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool sh
 void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
 				    size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg));
 
-const char *arch_syscalls__strerrno(const char *arch, int err);
-
 #endif /* _PERF_TRACE_BEAUTY_H */
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index a632f33646bb3..c68b7a004f294 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -458,8 +458,10 @@ const char *perf_env__arch(struct perf_env *env)
 const char *perf_env__arch_strerrno(struct perf_env *env __maybe_unused, int err __maybe_unused)
 {
 #if defined(HAVE_SYSCALL_TABLE_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
-	const char *arch_name = perf_env__arch(env);
-	return arch_syscalls__strerrno(arch_name, err);
+	if (env->arch_strerrno == NULL)
+		env->arch_strerrno = arch_syscalls__strerrno_function(perf_env__arch(env));
+
+	return env->arch_strerrno ? env->arch_strerrno(err) : "no arch specific strerrno function";
 #else
 	return "!(HAVE_SYSCALL_TABLE_SUPPORT && HAVE_LIBTRACEEVENT)";
 #endif
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 79f371879f45b..bf7e3c4c211f9 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -53,6 +53,10 @@ struct pmu_caps {
 	char            *pmu_name;
 };
 
+typedef const char *(arch_syscalls__strerrno_t)(int err);
+
+arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch);
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -135,6 +139,7 @@ struct perf_env {
 		 */
 		bool	enabled;
 	} clock;
+	arch_syscalls__strerrno_t *arch_strerrno;
 };
 
 enum perf_compress_type {
-- 
GitLab


From 28b01743ca752cea5ab182297d8b912b22f2a2d1 Mon Sep 17 00:00:00 2001
From: Veronika Molnarova <vmolnaro@redhat.com>
Date: Fri, 1 Dec 2023 20:46:17 +0100
Subject: [PATCH 0723/4076] perf test record user-regs: Fix mask for vg
 register

The 'vg' register for arm64 shows up in --user_regs as available when
masking the variable AT_HWCAP with 1 << 22 returns '1' as done in
perf_regs.c.

However, in subtests for support of SVE, the check for the 'vg' register
is done by masking the variable AT_HWCAP with the value 0x200000 which
is equals to 1 << 21 instead of 1 << 22.

This results in inconsistencies on certain systems where the test
expects that the 'vg' register is not operational when it is, and
vice-versa.

During the testing on a machine that the test expected not to have the
'vg' register available, 'perf record' with the option --user-regs
showed records for the 'vg' register together with all of the others,
which means that the mask for the subtest of perf_event_attr is off by
one.

Change the value of the mask from 0x200000 to 0x400000 to correct it.

Fixes: 9440ebdc333dd12e ("perf test arm64: Add attr tests for new VG register")
Reviewed-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Veronika Molnarova <vmolnaro@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Link: https://lore.kernel.org/r/20231201194617.13012-1-vmolnaro@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 | 2 +-
 tools/perf/tests/attr/test-record-user-regs-sve-aarch64    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 b/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64
index fbb065842880f..bed765450ca97 100644
--- a/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64
+++ b/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64
@@ -6,4 +6,4 @@ args    = --no-bpf-event --user-regs=vg kill >/dev/null 2>&1
 ret     = 129
 test_ret = true
 arch    = aarch64
-auxv    = auxv["AT_HWCAP"] & 0x200000 == 0
+auxv    = auxv["AT_HWCAP"] & 0x400000 == 0
diff --git a/tools/perf/tests/attr/test-record-user-regs-sve-aarch64 b/tools/perf/tests/attr/test-record-user-regs-sve-aarch64
index c598c803221da..a65113cd7311b 100644
--- a/tools/perf/tests/attr/test-record-user-regs-sve-aarch64
+++ b/tools/perf/tests/attr/test-record-user-regs-sve-aarch64
@@ -6,7 +6,7 @@ args    = --no-bpf-event --user-regs=vg kill >/dev/null 2>&1
 ret     = 1
 test_ret = true
 arch    = aarch64
-auxv    = auxv["AT_HWCAP"] & 0x200000 == 0x200000
+auxv    = auxv["AT_HWCAP"] & 0x400000 == 0x400000
 kernel_since = 6.1
 
 [event:base-record]
-- 
GitLab


From 2202844e4468c7539dba0c0b06577c93735af952 Mon Sep 17 00:00:00 2001
From: Longfang Liu <liulongfang@huawei.com>
Date: Mon, 6 Nov 2023 15:22:23 +0800
Subject: [PATCH 0724/4076] vfio/migration: Add debugfs to live migration
 driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are multiple devices, software and operational steps involved
in the process of live migration. An error occurred on any node may
cause the live migration operation to fail.
This complex process makes it very difficult to locate and analyze
the cause when the function fails.

In order to quickly locate the cause of the problem when the
live migration fails, I added a set of debugfs to the vfio
live migration driver.

    +-------------------------------------------+
    |                                           |
    |                                           |
    |                  QEMU                     |
    |                                           |
    |                                           |
    +---+----------------------------+----------+
        |      ^                     |      ^
        |      |                     |      |
        |      |                     |      |
        v      |                     v      |
     +---------+--+               +---------+--+
     |src vfio_dev|               |dst vfio_dev|
     +--+---------+               +--+---------+
        |      ^                     |      ^
        |      |                     |      |
        v      |                     |      |
   +-----------+----+           +-----------+----+
   |src dev debugfs |           |dst dev debugfs |
   +----------------+           +----------------+

The entire debugfs directory will be based on the definition of
the CONFIG_DEBUG_FS macro. If this macro is not enabled, the
interfaces in vfio.h will be empty definitions, and the creation
and initialization of the debugfs directory will not be executed.

   vfio
    |
    +---<dev_name1>
    |    +---migration
    |        +--state
    |
    +---<dev_name2>
         +---migration
             +--state

debugfs will create a public root directory "vfio" file.
then create a dev_name() file for each live migration device.
First, create a unified state acquisition file of "migration"
in this device directory.
Then, create a public live migration state lookup file "state".

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/r/20231106072225.28577-2-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/Kconfig      | 10 +++++
 drivers/vfio/Makefile     |  1 +
 drivers/vfio/debugfs.c    | 92 +++++++++++++++++++++++++++++++++++++++
 drivers/vfio/vfio.h       | 14 ++++++
 drivers/vfio/vfio_main.c  |  4 ++
 include/linux/vfio.h      |  7 +++
 include/uapi/linux/vfio.h |  1 +
 7 files changed, 129 insertions(+)
 create mode 100644 drivers/vfio/debugfs.c

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 6bda6dbb48784..ceae52fd7586d 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -80,6 +80,16 @@ config VFIO_VIRQFD
 	select EVENTFD
 	default n
 
+config VFIO_DEBUGFS
+	bool "Export VFIO internals in DebugFS"
+	depends on DEBUG_FS
+	help
+	  Allows exposure of VFIO device internals. This option enables
+	  the use of debugfs by VFIO drivers as required. The device can
+	  cause the VFIO code create a top-level debug/vfio directory
+	  during initialization, and then populate a subdirectory with
+	  entries as required.
+
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "drivers/vfio/mdev/Kconfig"
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index 68c05705200fc..b2fc9fb499d86 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -7,6 +7,7 @@ vfio-$(CONFIG_VFIO_GROUP) += group.o
 vfio-$(CONFIG_IOMMUFD) += iommufd.o
 vfio-$(CONFIG_VFIO_CONTAINER) += container.o
 vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
+vfio-$(CONFIG_VFIO_DEBUGFS) += debugfs.o
 
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
 obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
diff --git a/drivers/vfio/debugfs.c b/drivers/vfio/debugfs.c
new file mode 100644
index 0000000000000..298bd866f1576
--- /dev/null
+++ b/drivers/vfio/debugfs.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, HiSilicon Ltd.
+ */
+
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/vfio.h>
+#include "vfio.h"
+
+static struct dentry *vfio_debugfs_root;
+
+static int vfio_device_state_read(struct seq_file *seq, void *data)
+{
+	struct device *vf_dev = seq->private;
+	struct vfio_device *vdev = container_of(vf_dev,
+						struct vfio_device, device);
+	enum vfio_device_mig_state state;
+	int ret;
+
+	BUILD_BUG_ON(VFIO_DEVICE_STATE_NR !=
+		     VFIO_DEVICE_STATE_PRE_COPY_P2P + 1);
+
+	ret = vdev->mig_ops->migration_get_state(vdev, &state);
+	if (ret)
+		return -EINVAL;
+
+	switch (state) {
+	case VFIO_DEVICE_STATE_ERROR:
+		seq_puts(seq, "ERROR\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP:
+		seq_puts(seq, "STOP\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING:
+		seq_puts(seq, "RUNNING\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP_COPY:
+		seq_puts(seq, "STOP_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_RESUMING:
+		seq_puts(seq, "RESUMING\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING_P2P:
+		seq_puts(seq, "RUNNING_P2P\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY:
+		seq_puts(seq, "PRE_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY_P2P:
+		seq_puts(seq, "PRE_COPY_P2P\n");
+		break;
+	default:
+		seq_puts(seq, "Invalid\n");
+	}
+
+	return 0;
+}
+
+void vfio_device_debugfs_init(struct vfio_device *vdev)
+{
+	struct device *dev = &vdev->device;
+
+	vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev),
+					      vfio_debugfs_root);
+
+	if (vdev->mig_ops) {
+		struct dentry *vfio_dev_migration = NULL;
+
+		vfio_dev_migration = debugfs_create_dir("migration",
+							vdev->debug_root);
+		debugfs_create_devm_seqfile(dev, "state", vfio_dev_migration,
+					    vfio_device_state_read);
+	}
+}
+
+void vfio_device_debugfs_exit(struct vfio_device *vdev)
+{
+	debugfs_remove_recursive(vdev->debug_root);
+}
+
+void vfio_debugfs_create_root(void)
+{
+	vfio_debugfs_root = debugfs_create_dir("vfio", NULL);
+}
+
+void vfio_debugfs_remove_root(void)
+{
+	debugfs_remove_recursive(vfio_debugfs_root);
+	vfio_debugfs_root = NULL;
+}
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index 307e3f29b527f..bde84ad344e50 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -448,4 +448,18 @@ static inline void vfio_device_put_kvm(struct vfio_device *device)
 }
 #endif
 
+#ifdef CONFIG_VFIO_DEBUGFS
+void vfio_debugfs_create_root(void);
+void vfio_debugfs_remove_root(void);
+
+void vfio_device_debugfs_init(struct vfio_device *vdev);
+void vfio_device_debugfs_exit(struct vfio_device *vdev);
+#else
+static inline void vfio_debugfs_create_root(void) { }
+static inline void vfio_debugfs_remove_root(void) { }
+
+static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { }
+static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { }
+#endif /* CONFIG_VFIO_DEBUGFS */
+
 #endif
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 8d4995ada74a0..1cc93aac99a29 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -311,6 +311,7 @@ static int __vfio_register_dev(struct vfio_device *device,
 	refcount_set(&device->refcount, 1);
 
 	vfio_device_group_register(device);
+	vfio_device_debugfs_init(device);
 
 	return 0;
 err_out:
@@ -378,6 +379,7 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 		}
 	}
 
+	vfio_device_debugfs_exit(device);
 	/* Balances vfio_device_set_group in register path */
 	vfio_device_remove_group(device);
 }
@@ -1676,6 +1678,7 @@ static int __init vfio_init(void)
 	if (ret)
 		goto err_alloc_dev_chrdev;
 
+	vfio_debugfs_create_root();
 	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	return 0;
 
@@ -1691,6 +1694,7 @@ err_virqfd:
 
 static void __exit vfio_cleanup(void)
 {
+	vfio_debugfs_remove_root();
 	ida_destroy(&vfio.device_ida);
 	vfio_cdev_cleanup();
 	class_destroy(vfio.device_class);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index a65b2513f8cdc..89b265bc6ec31 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -69,6 +69,13 @@ struct vfio_device {
 	u8 iommufd_attached:1;
 #endif
 	u8 cdev_opened:1;
+#ifdef CONFIG_DEBUG_FS
+	/*
+	 * debug_root is a static property of the vfio_device
+	 * which must be set prior to registering the vfio_device.
+	 */
+	struct dentry *debug_root;
+#endif
 };
 
 /**
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 7f5fb010226d8..2b68e6cdf1902 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1219,6 +1219,7 @@ enum vfio_device_mig_state {
 	VFIO_DEVICE_STATE_RUNNING_P2P = 5,
 	VFIO_DEVICE_STATE_PRE_COPY = 6,
 	VFIO_DEVICE_STATE_PRE_COPY_P2P = 7,
+	VFIO_DEVICE_STATE_NR,
 };
 
 /**
-- 
GitLab


From 7b994177805f4ef05913c3f242840b262ecf2fa1 Mon Sep 17 00:00:00 2001
From: Longfang Liu <liulongfang@huawei.com>
Date: Mon, 6 Nov 2023 15:22:24 +0800
Subject: [PATCH 0725/4076] Documentation: add debugfs description for vfio
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add an debugfs document description file to help users understand
how to use the accelerator live migration driver's debugfs.

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/r/20231106072225.28577-3-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 Documentation/ABI/testing/debugfs-vfio | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)
 create mode 100644 Documentation/ABI/testing/debugfs-vfio

diff --git a/Documentation/ABI/testing/debugfs-vfio b/Documentation/ABI/testing/debugfs-vfio
new file mode 100644
index 0000000000000..90f7c262f5913
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-vfio
@@ -0,0 +1,25 @@
+What:		/sys/kernel/debug/vfio
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	This debugfs file directory is used for debugging
+		of vfio devices, it's a common directory for all vfio devices.
+		Vfio core will create a device subdirectory under this
+		directory.
+
+What:		/sys/kernel/debug/vfio/<device>/migration
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	This debugfs file directory is used for debugging
+		of vfio devices that support live migration.
+		The debugfs of each vfio device that supports live migration
+		could be created under this directory.
+
+What:		/sys/kernel/debug/vfio/<device>/migration/state
+Date:		December 2023
+KernelVersion:	6.8
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Read the live migration status of the vfio device.
+		The contents of the state file reflects the migration state
+		relative to those defined in the vfio_device_mig_state enum
-- 
GitLab


From 0d9bacfa615310e88bae385d64ca065953cb95ac Mon Sep 17 00:00:00 2001
From: Longfang Liu <liulongfang@huawei.com>
Date: Mon, 6 Nov 2023 15:22:25 +0800
Subject: [PATCH 0726/4076] MAINTAINERS: Add vfio debugfs interface doc link

After adding the debugfs function to the vfio driver,
a new debugfs-vfio file was added.

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Link: https://lore.kernel.org/r/20231106072225.28577-4-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 788be9ab5b733..d924ef5f56999 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22837,6 +22837,7 @@ M:	Alex Williamson <alex.williamson@redhat.com>
 L:	kvm@vger.kernel.org
 S:	Maintained
 T:	git https://github.com/awilliam/linux-vfio.git
+F:	Documentation/ABI/testing/debugfs-vfio
 F:	Documentation/ABI/testing/sysfs-devices-vfio-dev
 F:	Documentation/driver-api/vfio.rst
 F:	drivers/vfio/
-- 
GitLab


From 4004497cec3093d7b0087bc70709b45969fa07b6 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Thu, 16 Nov 2023 16:12:02 -0800
Subject: [PATCH 0727/4076] vfio/pds: Fix calculations in pds_vfio_dirty_sync

The incorrect check is being done for comparing the
iova/length being requested to sync. This can cause
the dirty sync operation to fail. Fix this by making
sure the iova offset added to the requested sync
length doesn't exceed the region_size.

Also, the region_start is assumed to always be at 0.
This can cause dirty tracking to fail because the
device/driver bitmap offset always starts at 0,
however, the region_start/iova may not. Fix this by
determining the iova offset from region_start to
determine the bitmap offset.

Fixes: f232836a9152 ("vfio/pds: Add support for dirty page tracking")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20231117001207.2793-2-brett.creeley@amd.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/pds/dirty.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index c937aa6f39546..27607d7b9030a 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -478,8 +478,7 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		pds_vfio->vf_id, iova, length, pds_vfio->dirty.region_page_size,
 		pages, bitmap_size);
 
-	if (!length || ((dirty->region_start + iova + length) >
-			(dirty->region_start + dirty->region_size))) {
+	if (!length || ((iova - dirty->region_start + length) > dirty->region_size)) {
 		dev_err(dev, "Invalid iova 0x%lx and/or length 0x%lx to sync\n",
 			iova, length);
 		return -EINVAL;
@@ -496,7 +495,8 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	bmp_offset = DIV_ROUND_UP(iova / dirty->region_page_size, sizeof(u64));
+	bmp_offset = DIV_ROUND_UP((iova - dirty->region_start) /
+				  dirty->region_page_size, sizeof(u64));
 
 	dev_dbg(dev,
 		"Syncing dirty bitmap, iova 0x%lx length 0x%lx, bmp_offset %llu bmp_bytes %llu\n",
-- 
GitLab


From 3b8f7a24d1fe79cc3fa1da9be5610b9c3aedbc2a Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Thu, 16 Nov 2023 16:12:03 -0800
Subject: [PATCH 0728/4076] vfio/pds: Only use a single SGL for both seq and
 ack

Since the seq/ack operations never happen in parallel there
is no need for multiple scatter gather lists per region.
The current implementation is wasting memory. Fix this by
only using a single scatter-gather list for both the seq
and ack operations.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20231117001207.2793-3-brett.creeley@amd.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/pds/dirty.c | 68 +++++++++++++-----------------------
 drivers/vfio/pci/pds/dirty.h |  6 ++--
 2 files changed, 28 insertions(+), 46 deletions(-)

diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index 27607d7b9030a..4462f6edb0ed4 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -100,35 +100,35 @@ static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
 }
 
 static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_bmp_info *bmp_info)
+				      struct pds_vfio_dirty *dirty)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
 
-	dma_unmap_single(pdsc_dev, bmp_info->sgl_addr,
-			 bmp_info->num_sge * sizeof(struct pds_lm_sg_elem),
+	dma_unmap_single(pdsc_dev, dirty->sgl_addr,
+			 dirty->num_sge * sizeof(struct pds_lm_sg_elem),
 			 DMA_BIDIRECTIONAL);
-	kfree(bmp_info->sgl);
+	kfree(dirty->sgl);
 
-	bmp_info->num_sge = 0;
-	bmp_info->sgl = NULL;
-	bmp_info->sgl_addr = 0;
+	dirty->num_sge = 0;
+	dirty->sgl = NULL;
+	dirty->sgl_addr = 0;
 }
 
 static void pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio)
 {
-	if (pds_vfio->dirty.host_seq.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_seq);
-	if (pds_vfio->dirty.host_ack.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_ack);
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+
+	if (dirty->sgl)
+		__pds_vfio_dirty_free_sgl(pds_vfio, dirty);
 }
 
-static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_bmp_info *bmp_info,
-				      u32 page_count)
+static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
+				    u32 page_count)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
 	struct pds_lm_sg_elem *sgl;
 	dma_addr_t sgl_addr;
 	size_t sgl_size;
@@ -147,30 +147,9 @@ static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
 		return -EIO;
 	}
 
-	bmp_info->sgl = sgl;
-	bmp_info->num_sge = max_sge;
-	bmp_info->sgl_addr = sgl_addr;
-
-	return 0;
-}
-
-static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
-				    u32 page_count)
-{
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
-	int err;
-
-	err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_seq,
-					 page_count);
-	if (err)
-		return err;
-
-	err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_ack,
-					 page_count);
-	if (err) {
-		__pds_vfio_dirty_free_sgl(pds_vfio, &dirty->host_seq);
-		return err;
-	}
+	dirty->sgl = sgl;
+	dirty->num_sge = max_sge;
+	dirty->sgl_addr = sgl_addr;
 
 	return 0;
 }
@@ -328,6 +307,8 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 	u8 dma_dir = read_seq ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	struct pds_lm_sg_elem *sgl;
 	unsigned long long npages;
 	struct sg_table sg_table;
 	struct scatterlist *sg;
@@ -374,8 +355,9 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 	if (err)
 		goto out_free_sg_table;
 
+	sgl = pds_vfio->dirty.sgl;
 	for_each_sgtable_dma_sg(&sg_table, sg, i) {
-		struct pds_lm_sg_elem *sg_elem = &bmp_info->sgl[i];
+		struct pds_lm_sg_elem *sg_elem = &sgl[i];
 
 		sg_elem->addr = cpu_to_le64(sg_dma_address(sg));
 		sg_elem->len = cpu_to_le32(sg_dma_len(sg));
@@ -383,15 +365,15 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 
 	num_sge = sg_table.nents;
 	size = num_sge * sizeof(struct pds_lm_sg_elem);
-	dma_sync_single_for_device(pdsc_dev, bmp_info->sgl_addr, size, dma_dir);
-	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, bmp_info->sgl_addr, num_sge,
+	dma_sync_single_for_device(pdsc_dev, dirty->sgl_addr, size, dma_dir);
+	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, dirty->sgl_addr, num_sge,
 					 offset, bmp_bytes, read_seq);
 	if (err)
 		dev_err(&pdev->dev,
 			"Dirty bitmap %s failed offset %u bmp_bytes %u num_sge %u DMA 0x%llx: %pe\n",
 			bmp_type_str, offset, bmp_bytes,
-			num_sge, bmp_info->sgl_addr, ERR_PTR(err));
-	dma_sync_single_for_cpu(pdsc_dev, bmp_info->sgl_addr, size, dma_dir);
+			num_sge, dirty->sgl_addr, ERR_PTR(err));
+	dma_sync_single_for_cpu(pdsc_dev, dirty->sgl_addr, size, dma_dir);
 
 	dma_unmap_sgtable(pdsc_dev, &sg_table, dma_dir, 0);
 out_free_sg_table:
diff --git a/drivers/vfio/pci/pds/dirty.h b/drivers/vfio/pci/pds/dirty.h
index f78da25d75ca9..9de5aac58190e 100644
--- a/drivers/vfio/pci/pds/dirty.h
+++ b/drivers/vfio/pci/pds/dirty.h
@@ -7,9 +7,6 @@
 struct pds_vfio_bmp_info {
 	unsigned long *bmp;
 	u32 bmp_bytes;
-	struct pds_lm_sg_elem *sgl;
-	dma_addr_t sgl_addr;
-	u16 num_sge;
 };
 
 struct pds_vfio_dirty {
@@ -18,6 +15,9 @@ struct pds_vfio_dirty {
 	u64 region_size;
 	u64 region_start;
 	u64 region_page_size;
+	struct pds_lm_sg_elem *sgl;
+	dma_addr_t sgl_addr;
+	u16 num_sge;
 	bool is_enabled;
 };
 
-- 
GitLab


From 3f5898133a706402180908b671d5e781fc48f548 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Thu, 16 Nov 2023 16:12:04 -0800
Subject: [PATCH 0729/4076] vfio/pds: Move and rename region specific info

An upcoming change in this series will add support
for multiple regions. To prepare for that, move
region specific information into struct pds_vfio_region
and rename the members for readability. This will
reduce the size of the patch that actually implements
multiple region support.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20231117001207.2793-4-brett.creeley@amd.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/pds/dirty.c | 83 ++++++++++++++++++------------------
 drivers/vfio/pci/pds/dirty.h | 12 ++++--
 2 files changed, 50 insertions(+), 45 deletions(-)

diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index 4462f6edb0ed4..8a7f9eed4e598 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -85,18 +85,18 @@ static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty,
 		return -ENOMEM;
 	}
 
-	dirty->host_seq.bmp = host_seq_bmp;
-	dirty->host_ack.bmp = host_ack_bmp;
+	dirty->region.host_seq.bmp = host_seq_bmp;
+	dirty->region.host_ack.bmp = host_ack_bmp;
 
 	return 0;
 }
 
 static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
 {
-	vfree(dirty->host_seq.bmp);
-	vfree(dirty->host_ack.bmp);
-	dirty->host_seq.bmp = NULL;
-	dirty->host_ack.bmp = NULL;
+	vfree(dirty->region.host_seq.bmp);
+	vfree(dirty->region.host_ack.bmp);
+	dirty->region.host_seq.bmp = NULL;
+	dirty->region.host_ack.bmp = NULL;
 }
 
 static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
@@ -105,21 +105,21 @@ static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
 
-	dma_unmap_single(pdsc_dev, dirty->sgl_addr,
-			 dirty->num_sge * sizeof(struct pds_lm_sg_elem),
+	dma_unmap_single(pdsc_dev, dirty->region.sgl_addr,
+			 dirty->region.num_sge * sizeof(struct pds_lm_sg_elem),
 			 DMA_BIDIRECTIONAL);
-	kfree(dirty->sgl);
+	kfree(dirty->region.sgl);
 
-	dirty->num_sge = 0;
-	dirty->sgl = NULL;
-	dirty->sgl_addr = 0;
+	dirty->region.num_sge = 0;
+	dirty->region.sgl = NULL;
+	dirty->region.sgl_addr = 0;
 }
 
 static void pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio)
 {
 	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
 
-	if (dirty->sgl)
+	if (dirty->region.sgl)
 		__pds_vfio_dirty_free_sgl(pds_vfio, dirty);
 }
 
@@ -147,9 +147,9 @@ static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
 		return -EIO;
 	}
 
-	dirty->sgl = sgl;
-	dirty->num_sge = max_sge;
-	dirty->sgl_addr = sgl_addr;
+	dirty->region.sgl = sgl;
+	dirty->region.num_sge = max_sge;
+	dirty->region.sgl_addr = sgl_addr;
 
 	return 0;
 }
@@ -267,9 +267,9 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 		goto out_free_bitmaps;
 	}
 
-	dirty->region_start = region_start;
-	dirty->region_size = region_size;
-	dirty->region_page_size = region_page_size;
+	dirty->region.start = region_start;
+	dirty->region.size = region_size;
+	dirty->region.page_size = region_page_size;
 	pds_vfio_dirty_set_enabled(pds_vfio);
 
 	pds_vfio_print_guest_region_info(pds_vfio, max_regions);
@@ -304,11 +304,10 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 				  u32 offset, u32 bmp_bytes, bool read_seq)
 {
 	const char *bmp_type_str = read_seq ? "read_seq" : "write_ack";
+	struct pds_vfio_region *region = &pds_vfio->dirty.region;
 	u8 dma_dir = read_seq ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
-	struct pds_lm_sg_elem *sgl;
 	unsigned long long npages;
 	struct sg_table sg_table;
 	struct scatterlist *sg;
@@ -355,9 +354,8 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 	if (err)
 		goto out_free_sg_table;
 
-	sgl = pds_vfio->dirty.sgl;
 	for_each_sgtable_dma_sg(&sg_table, sg, i) {
-		struct pds_lm_sg_elem *sg_elem = &sgl[i];
+		struct pds_lm_sg_elem *sg_elem = &region->sgl[i];
 
 		sg_elem->addr = cpu_to_le64(sg_dma_address(sg));
 		sg_elem->len = cpu_to_le32(sg_dma_len(sg));
@@ -365,15 +363,15 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 
 	num_sge = sg_table.nents;
 	size = num_sge * sizeof(struct pds_lm_sg_elem);
-	dma_sync_single_for_device(pdsc_dev, dirty->sgl_addr, size, dma_dir);
-	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, dirty->sgl_addr, num_sge,
+	dma_sync_single_for_device(pdsc_dev, region->sgl_addr, size, dma_dir);
+	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, region->sgl_addr, num_sge,
 					 offset, bmp_bytes, read_seq);
 	if (err)
 		dev_err(&pdev->dev,
 			"Dirty bitmap %s failed offset %u bmp_bytes %u num_sge %u DMA 0x%llx: %pe\n",
 			bmp_type_str, offset, bmp_bytes,
-			num_sge, dirty->sgl_addr, ERR_PTR(err));
-	dma_sync_single_for_cpu(pdsc_dev, dirty->sgl_addr, size, dma_dir);
+			num_sge, region->sgl_addr, ERR_PTR(err));
+	dma_sync_single_for_cpu(pdsc_dev, region->sgl_addr, size, dma_dir);
 
 	dma_unmap_sgtable(pdsc_dev, &sg_table, dma_dir, 0);
 out_free_sg_table:
@@ -387,14 +385,18 @@ out_free_pages:
 static int pds_vfio_dirty_write_ack(struct pds_vfio_pci_device *pds_vfio,
 				    u32 offset, u32 len)
 {
-	return pds_vfio_dirty_seq_ack(pds_vfio, &pds_vfio->dirty.host_ack,
+	struct pds_vfio_region *region = &pds_vfio->dirty.region;
+
+	return pds_vfio_dirty_seq_ack(pds_vfio, &region->host_ack,
 				      offset, len, WRITE_ACK);
 }
 
 static int pds_vfio_dirty_read_seq(struct pds_vfio_pci_device *pds_vfio,
 				   u32 offset, u32 len)
 {
-	return pds_vfio_dirty_seq_ack(pds_vfio, &pds_vfio->dirty.host_seq,
+	struct pds_vfio_region *region = &pds_vfio->dirty.region;
+
+	return pds_vfio_dirty_seq_ack(pds_vfio, &region->host_seq,
 				      offset, len, READ_SEQ);
 }
 
@@ -402,15 +404,15 @@ static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio,
 					  struct iova_bitmap *dirty_bitmap,
 					  u32 bmp_offset, u32 len_bytes)
 {
-	u64 page_size = pds_vfio->dirty.region_page_size;
-	u64 region_start = pds_vfio->dirty.region_start;
+	u64 page_size = pds_vfio->dirty.region.page_size;
+	u64 region_start = pds_vfio->dirty.region.start;
 	u32 bmp_offset_bit;
 	__le64 *seq, *ack;
 	int dword_count;
 
 	dword_count = len_bytes / sizeof(u64);
-	seq = (__le64 *)((u64)pds_vfio->dirty.host_seq.bmp + bmp_offset);
-	ack = (__le64 *)((u64)pds_vfio->dirty.host_ack.bmp + bmp_offset);
+	seq = (__le64 *)((u64)pds_vfio->dirty.region.host_seq.bmp + bmp_offset);
+	ack = (__le64 *)((u64)pds_vfio->dirty.region.host_ack.bmp + bmp_offset);
 	bmp_offset_bit = bmp_offset * 8;
 
 	for (int i = 0; i < dword_count; i++) {
@@ -451,25 +453,24 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	pages = DIV_ROUND_UP(length, pds_vfio->dirty.region_page_size);
+	pages = DIV_ROUND_UP(length, pds_vfio->dirty.region.page_size);
 	bitmap_size =
 		round_up(pages, sizeof(u64) * BITS_PER_BYTE) / BITS_PER_BYTE;
 
 	dev_dbg(dev,
 		"vf%u: iova 0x%lx length %lu page_size %llu pages %llu bitmap_size %llu\n",
-		pds_vfio->vf_id, iova, length, pds_vfio->dirty.region_page_size,
+		pds_vfio->vf_id, iova, length, pds_vfio->dirty.region.page_size,
 		pages, bitmap_size);
 
-	if (!length || ((iova - dirty->region_start + length) > dirty->region_size)) {
+	if (!length || ((iova - dirty->region.start + length) > dirty->region.size)) {
 		dev_err(dev, "Invalid iova 0x%lx and/or length 0x%lx to sync\n",
 			iova, length);
 		return -EINVAL;
 	}
 
 	/* bitmap is modified in 64 bit chunks */
-	bmp_bytes = ALIGN(DIV_ROUND_UP(length / dirty->region_page_size,
-				       sizeof(u64)),
-			  sizeof(u64));
+	bmp_bytes = ALIGN(DIV_ROUND_UP(length / dirty->region.page_size,
+				       sizeof(u64)), sizeof(u64));
 	if (bmp_bytes != bitmap_size) {
 		dev_err(dev,
 			"Calculated bitmap bytes %llu not equal to bitmap size %llu\n",
@@ -477,8 +478,8 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	bmp_offset = DIV_ROUND_UP((iova - dirty->region_start) /
-				  dirty->region_page_size, sizeof(u64));
+	bmp_offset = DIV_ROUND_UP((iova - dirty->region.start) /
+				  dirty->region.page_size, sizeof(u64));
 
 	dev_dbg(dev,
 		"Syncing dirty bitmap, iova 0x%lx length 0x%lx, bmp_offset %llu bmp_bytes %llu\n",
diff --git a/drivers/vfio/pci/pds/dirty.h b/drivers/vfio/pci/pds/dirty.h
index 9de5aac58190e..07662d369e7c6 100644
--- a/drivers/vfio/pci/pds/dirty.h
+++ b/drivers/vfio/pci/pds/dirty.h
@@ -9,15 +9,19 @@ struct pds_vfio_bmp_info {
 	u32 bmp_bytes;
 };
 
-struct pds_vfio_dirty {
+struct pds_vfio_region {
 	struct pds_vfio_bmp_info host_seq;
 	struct pds_vfio_bmp_info host_ack;
-	u64 region_size;
-	u64 region_start;
-	u64 region_page_size;
+	u64 size;
+	u64 start;
+	u64 page_size;
 	struct pds_lm_sg_elem *sgl;
 	dma_addr_t sgl_addr;
 	u16 num_sge;
+};
+
+struct pds_vfio_dirty {
+	struct pds_vfio_region region;
 	bool is_enabled;
 };
 
-- 
GitLab


From 87bdf9807ed70f5d3a0f852f9d04ceb1c99ad9f6 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Thu, 16 Nov 2023 16:12:05 -0800
Subject: [PATCH 0730/4076] vfio/pds: Pass region info to relevant functions

A later patch in the series implements multi-region
support. That will require specific regions to be
passed to relevant functions. Prepare for that change
by passing the region structure to relevant functions.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20231117001207.2793-5-brett.creeley@amd.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/pds/dirty.c | 71 ++++++++++++++++++------------------
 1 file changed, 36 insertions(+), 35 deletions(-)

diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index 8a7f9eed4e598..09fed7c1771a8 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -100,35 +100,35 @@ static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
 }
 
 static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_dirty *dirty)
+				      struct pds_vfio_region *region)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
 
-	dma_unmap_single(pdsc_dev, dirty->region.sgl_addr,
-			 dirty->region.num_sge * sizeof(struct pds_lm_sg_elem),
+	dma_unmap_single(pdsc_dev, region->sgl_addr,
+			 region->num_sge * sizeof(struct pds_lm_sg_elem),
 			 DMA_BIDIRECTIONAL);
-	kfree(dirty->region.sgl);
+	kfree(region->sgl);
 
-	dirty->region.num_sge = 0;
-	dirty->region.sgl = NULL;
-	dirty->region.sgl_addr = 0;
+	region->num_sge = 0;
+	region->sgl = NULL;
+	region->sgl_addr = 0;
 }
 
 static void pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio)
 {
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	struct pds_vfio_region *region = &pds_vfio->dirty.region;
 
-	if (dirty->region.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, dirty);
+	if (region->sgl)
+		__pds_vfio_dirty_free_sgl(pds_vfio, region);
 }
 
 static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
+				    struct pds_vfio_region *region,
 				    u32 page_count)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
 	struct pds_lm_sg_elem *sgl;
 	dma_addr_t sgl_addr;
 	size_t sgl_size;
@@ -147,9 +147,9 @@ static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
 		return -EIO;
 	}
 
-	dirty->region.sgl = sgl;
-	dirty->region.num_sge = max_sge;
-	dirty->region.sgl_addr = sgl_addr;
+	region->sgl = sgl;
+	region->num_sge = max_sge;
+	region->sgl_addr = sgl_addr;
 
 	return 0;
 }
@@ -260,7 +260,7 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 		goto out_free_region_info;
 	}
 
-	err = pds_vfio_dirty_alloc_sgl(pds_vfio, page_count);
+	err = pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->region, page_count);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n",
 			ERR_PTR(err));
@@ -300,11 +300,11 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd)
 }
 
 static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
+				  struct pds_vfio_region *region,
 				  struct pds_vfio_bmp_info *bmp_info,
 				  u32 offset, u32 bmp_bytes, bool read_seq)
 {
 	const char *bmp_type_str = read_seq ? "read_seq" : "write_ack";
-	struct pds_vfio_region *region = &pds_vfio->dirty.region;
 	u8 dma_dir = read_seq ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
@@ -383,36 +383,36 @@ out_free_pages:
 }
 
 static int pds_vfio_dirty_write_ack(struct pds_vfio_pci_device *pds_vfio,
+				   struct pds_vfio_region *region,
 				    u32 offset, u32 len)
 {
-	struct pds_vfio_region *region = &pds_vfio->dirty.region;
 
-	return pds_vfio_dirty_seq_ack(pds_vfio, &region->host_ack,
+	return pds_vfio_dirty_seq_ack(pds_vfio, region, &region->host_ack,
 				      offset, len, WRITE_ACK);
 }
 
 static int pds_vfio_dirty_read_seq(struct pds_vfio_pci_device *pds_vfio,
+				   struct pds_vfio_region *region,
 				   u32 offset, u32 len)
 {
-	struct pds_vfio_region *region = &pds_vfio->dirty.region;
-
-	return pds_vfio_dirty_seq_ack(pds_vfio, &region->host_seq,
+	return pds_vfio_dirty_seq_ack(pds_vfio, region, &region->host_seq,
 				      offset, len, READ_SEQ);
 }
 
 static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio,
+					  struct pds_vfio_region *region,
 					  struct iova_bitmap *dirty_bitmap,
 					  u32 bmp_offset, u32 len_bytes)
 {
-	u64 page_size = pds_vfio->dirty.region.page_size;
-	u64 region_start = pds_vfio->dirty.region.start;
+	u64 page_size = region->page_size;
+	u64 region_start = region->start;
 	u32 bmp_offset_bit;
 	__le64 *seq, *ack;
 	int dword_count;
 
 	dword_count = len_bytes / sizeof(u64);
-	seq = (__le64 *)((u64)pds_vfio->dirty.region.host_seq.bmp + bmp_offset);
-	ack = (__le64 *)((u64)pds_vfio->dirty.region.host_ack.bmp + bmp_offset);
+	seq = (__le64 *)((u64)region->host_seq.bmp + bmp_offset);
+	ack = (__le64 *)((u64)region->host_ack.bmp + bmp_offset);
 	bmp_offset_bit = bmp_offset * 8;
 
 	for (int i = 0; i < dword_count; i++) {
@@ -441,6 +441,7 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 {
 	struct device *dev = &pds_vfio->vfio_coredev.pdev->dev;
 	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	struct pds_vfio_region *region = &dirty->region;
 	u64 bmp_offset, bmp_bytes;
 	u64 bitmap_size, pages;
 	int err;
@@ -453,23 +454,23 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	pages = DIV_ROUND_UP(length, pds_vfio->dirty.region.page_size);
+	pages = DIV_ROUND_UP(length, region->page_size);
 	bitmap_size =
 		round_up(pages, sizeof(u64) * BITS_PER_BYTE) / BITS_PER_BYTE;
 
 	dev_dbg(dev,
 		"vf%u: iova 0x%lx length %lu page_size %llu pages %llu bitmap_size %llu\n",
-		pds_vfio->vf_id, iova, length, pds_vfio->dirty.region.page_size,
+		pds_vfio->vf_id, iova, length, region->page_size,
 		pages, bitmap_size);
 
-	if (!length || ((iova - dirty->region.start + length) > dirty->region.size)) {
+	if (!length || ((iova - region->start + length) > region->size)) {
 		dev_err(dev, "Invalid iova 0x%lx and/or length 0x%lx to sync\n",
 			iova, length);
 		return -EINVAL;
 	}
 
 	/* bitmap is modified in 64 bit chunks */
-	bmp_bytes = ALIGN(DIV_ROUND_UP(length / dirty->region.page_size,
+	bmp_bytes = ALIGN(DIV_ROUND_UP(length / region->page_size,
 				       sizeof(u64)), sizeof(u64));
 	if (bmp_bytes != bitmap_size) {
 		dev_err(dev,
@@ -478,23 +479,23 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	bmp_offset = DIV_ROUND_UP((iova - dirty->region.start) /
-				  dirty->region.page_size, sizeof(u64));
+	bmp_offset = DIV_ROUND_UP((iova - region->start) /
+				  region->page_size, sizeof(u64));
 
 	dev_dbg(dev,
 		"Syncing dirty bitmap, iova 0x%lx length 0x%lx, bmp_offset %llu bmp_bytes %llu\n",
 		iova, length, bmp_offset, bmp_bytes);
 
-	err = pds_vfio_dirty_read_seq(pds_vfio, bmp_offset, bmp_bytes);
+	err = pds_vfio_dirty_read_seq(pds_vfio, region, bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 
-	err = pds_vfio_dirty_process_bitmaps(pds_vfio, dirty_bitmap, bmp_offset,
-					     bmp_bytes);
+	err = pds_vfio_dirty_process_bitmaps(pds_vfio, region, dirty_bitmap,
+					     bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 
-	err = pds_vfio_dirty_write_ack(pds_vfio, bmp_offset, bmp_bytes);
+	err = pds_vfio_dirty_write_ack(pds_vfio, region, bmp_offset, bmp_bytes);
 	if (err)
 		return err;
 
-- 
GitLab


From 0c320f223ee6892a413428051f35bebf85fe83d3 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Thu, 16 Nov 2023 16:12:06 -0800
Subject: [PATCH 0731/4076] vfio/pds: Move seq/ack bitmaps into region struct

Since the host seq/ack bitmaps are part of a region
move them into struct pds_vfio_region. Also, make use
of the bmp_bytes value for validation purposes.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20231117001207.2793-6-brett.creeley@amd.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/pds/dirty.c | 35 ++++++++++++++++++++++-------------
 drivers/vfio/pci/pds/dirty.h | 10 +++-------
 2 files changed, 25 insertions(+), 20 deletions(-)

diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index 09fed7c1771a8..4824cdfe01eda 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -85,18 +85,20 @@ static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty,
 		return -ENOMEM;
 	}
 
-	dirty->region.host_seq.bmp = host_seq_bmp;
-	dirty->region.host_ack.bmp = host_ack_bmp;
+	dirty->region.host_seq = host_seq_bmp;
+	dirty->region.host_ack = host_ack_bmp;
+	dirty->region.bmp_bytes = bytes;
 
 	return 0;
 }
 
 static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
 {
-	vfree(dirty->region.host_seq.bmp);
-	vfree(dirty->region.host_ack.bmp);
-	dirty->region.host_seq.bmp = NULL;
-	dirty->region.host_ack.bmp = NULL;
+	vfree(dirty->region.host_seq);
+	vfree(dirty->region.host_ack);
+	dirty->region.host_seq = NULL;
+	dirty->region.host_ack = NULL;
+	dirty->region.bmp_bytes = 0;
 }
 
 static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
@@ -301,8 +303,8 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd)
 
 static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 				  struct pds_vfio_region *region,
-				  struct pds_vfio_bmp_info *bmp_info,
-				  u32 offset, u32 bmp_bytes, bool read_seq)
+				  unsigned long *seq_ack_bmp, u32 offset,
+				  u32 bmp_bytes, bool read_seq)
 {
 	const char *bmp_type_str = read_seq ? "read_seq" : "write_ack";
 	u8 dma_dir = read_seq ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
@@ -319,7 +321,7 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 	int err;
 	int i;
 
-	bmp = (void *)((u64)bmp_info->bmp + offset);
+	bmp = (void *)((u64)seq_ack_bmp + offset);
 	page_offset = offset_in_page(bmp);
 	bmp -= page_offset;
 
@@ -387,7 +389,7 @@ static int pds_vfio_dirty_write_ack(struct pds_vfio_pci_device *pds_vfio,
 				    u32 offset, u32 len)
 {
 
-	return pds_vfio_dirty_seq_ack(pds_vfio, region, &region->host_ack,
+	return pds_vfio_dirty_seq_ack(pds_vfio, region, region->host_ack,
 				      offset, len, WRITE_ACK);
 }
 
@@ -395,7 +397,7 @@ static int pds_vfio_dirty_read_seq(struct pds_vfio_pci_device *pds_vfio,
 				   struct pds_vfio_region *region,
 				   u32 offset, u32 len)
 {
-	return pds_vfio_dirty_seq_ack(pds_vfio, region, &region->host_seq,
+	return pds_vfio_dirty_seq_ack(pds_vfio, region, region->host_seq,
 				      offset, len, READ_SEQ);
 }
 
@@ -411,8 +413,8 @@ static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio,
 	int dword_count;
 
 	dword_count = len_bytes / sizeof(u64);
-	seq = (__le64 *)((u64)region->host_seq.bmp + bmp_offset);
-	ack = (__le64 *)((u64)region->host_ack.bmp + bmp_offset);
+	seq = (__le64 *)((u64)region->host_seq + bmp_offset);
+	ack = (__le64 *)((u64)region->host_ack + bmp_offset);
 	bmp_offset_bit = bmp_offset * 8;
 
 	for (int i = 0; i < dword_count; i++) {
@@ -479,6 +481,13 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
+	if (bmp_bytes > region->bmp_bytes) {
+		dev_err(dev,
+			"Calculated bitmap bytes %llu larger than region's cached bmp_bytes %llu\n",
+			bmp_bytes, region->bmp_bytes);
+		return -EINVAL;
+	}
+
 	bmp_offset = DIV_ROUND_UP((iova - region->start) /
 				  region->page_size, sizeof(u64));
 
diff --git a/drivers/vfio/pci/pds/dirty.h b/drivers/vfio/pci/pds/dirty.h
index 07662d369e7c6..a1f6d894f913a 100644
--- a/drivers/vfio/pci/pds/dirty.h
+++ b/drivers/vfio/pci/pds/dirty.h
@@ -4,14 +4,10 @@
 #ifndef _DIRTY_H_
 #define _DIRTY_H_
 
-struct pds_vfio_bmp_info {
-	unsigned long *bmp;
-	u32 bmp_bytes;
-};
-
 struct pds_vfio_region {
-	struct pds_vfio_bmp_info host_seq;
-	struct pds_vfio_bmp_info host_ack;
+	unsigned long *host_seq;
+	unsigned long *host_ack;
+	u64 bmp_bytes;
 	u64 size;
 	u64 start;
 	u64 page_size;
-- 
GitLab


From 2e7c6feb4ef5257189819359e754625ccf5a1d6c Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Thu, 16 Nov 2023 16:12:07 -0800
Subject: [PATCH 0732/4076] vfio/pds: Add multi-region support

Only supporting a single region/range is limiting,
wasteful, and in some cases broken (i.e. when there
are large gaps in the iova memory ranges). Fix this
by adding support for multiple regions based on
what the device tells the driver it can support.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20231117001207.2793-7-brett.creeley@amd.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/pds/dirty.c | 220 ++++++++++++++++++++++++-----------
 drivers/vfio/pci/pds/dirty.h |   4 +-
 2 files changed, 156 insertions(+), 68 deletions(-)

diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index 4824cdfe01eda..8ddf4346fcd5d 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -70,7 +70,7 @@ out_free_region_info:
 	kfree(region_info);
 }
 
-static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty,
+static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_region *region,
 					unsigned long bytes)
 {
 	unsigned long *host_seq_bmp, *host_ack_bmp;
@@ -85,20 +85,27 @@ static int pds_vfio_dirty_alloc_bitmaps(struct pds_vfio_dirty *dirty,
 		return -ENOMEM;
 	}
 
-	dirty->region.host_seq = host_seq_bmp;
-	dirty->region.host_ack = host_ack_bmp;
-	dirty->region.bmp_bytes = bytes;
+	region->host_seq = host_seq_bmp;
+	region->host_ack = host_ack_bmp;
+	region->bmp_bytes = bytes;
 
 	return 0;
 }
 
 static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
 {
-	vfree(dirty->region.host_seq);
-	vfree(dirty->region.host_ack);
-	dirty->region.host_seq = NULL;
-	dirty->region.host_ack = NULL;
-	dirty->region.bmp_bytes = 0;
+	if (!dirty->regions)
+		return;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		vfree(region->host_seq);
+		vfree(region->host_ack);
+		region->host_seq = NULL;
+		region->host_ack = NULL;
+		region->bmp_bytes = 0;
+	}
 }
 
 static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
@@ -119,10 +126,17 @@ static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
 
 static void pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio)
 {
-	struct pds_vfio_region *region = &pds_vfio->dirty.region;
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
 
-	if (region->sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, region);
+	if (!dirty->regions)
+		return;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		if (region->sgl)
+			__pds_vfio_dirty_free_sgl(pds_vfio, region);
+	}
 }
 
 static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
@@ -156,22 +170,90 @@ static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
 	return 0;
 }
 
+static void pds_vfio_dirty_free_regions(struct pds_vfio_dirty *dirty)
+{
+	vfree(dirty->regions);
+	dirty->regions = NULL;
+	dirty->num_regions = 0;
+}
+
+static int pds_vfio_dirty_alloc_regions(struct pds_vfio_pci_device *pds_vfio,
+					struct pds_lm_dirty_region_info *region_info,
+					u64 region_page_size, u8 num_regions)
+{
+	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	u32 dev_bmp_offset_byte = 0;
+	int err;
+
+	dirty->regions = vcalloc(num_regions, sizeof(struct pds_vfio_region));
+	if (!dirty->regions)
+		return -ENOMEM;
+	dirty->num_regions = num_regions;
+
+	for (int i = 0; i < num_regions; i++) {
+		struct pds_lm_dirty_region_info *ri = &region_info[i];
+		struct pds_vfio_region *region = &dirty->regions[i];
+		u64 region_size, region_start;
+		u32 page_count;
+
+		/* page_count might be adjusted by the device */
+		page_count = le32_to_cpu(ri->page_count);
+		region_start = le64_to_cpu(ri->dma_base);
+		region_size = page_count * region_page_size;
+
+		err = pds_vfio_dirty_alloc_bitmaps(region,
+						   page_count / BITS_PER_BYTE);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n",
+				ERR_PTR(err));
+			goto out_free_regions;
+		}
+
+		err = pds_vfio_dirty_alloc_sgl(pds_vfio, region, page_count);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n",
+				ERR_PTR(err));
+			goto out_free_regions;
+		}
+
+		region->size = region_size;
+		region->start = region_start;
+		region->page_size = region_page_size;
+		region->dev_bmp_offset_start_byte = dev_bmp_offset_byte;
+
+		dev_bmp_offset_byte += page_count / BITS_PER_BYTE;
+		if (dev_bmp_offset_byte % BITS_PER_BYTE) {
+			dev_err(&pdev->dev, "Device bitmap offset is mis-aligned\n");
+			err = -EINVAL;
+			goto out_free_regions;
+		}
+	}
+
+	return 0;
+
+out_free_regions:
+	pds_vfio_dirty_free_bitmaps(dirty);
+	pds_vfio_dirty_free_sgl(pds_vfio);
+	pds_vfio_dirty_free_regions(dirty);
+
+	return err;
+}
+
 static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 				 struct rb_root_cached *ranges, u32 nnodes,
 				 u64 *page_size)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
-	u64 region_start, region_size, region_page_size;
 	struct pds_lm_dirty_region_info *region_info;
 	struct interval_tree_node *node = NULL;
+	u64 region_page_size = *page_size;
 	u8 max_regions = 0, num_regions;
 	dma_addr_t regions_dma = 0;
 	u32 num_ranges = nnodes;
-	u32 page_count;
-	u16 len;
 	int err;
+	u16 len;
 
 	dev_dbg(&pdev->dev, "vf%u: Start dirty page tracking\n",
 		pds_vfio->vf_id);
@@ -198,39 +280,38 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 		return -EOPNOTSUPP;
 	}
 
-	/*
-	 * Only support 1 region for now. If there are any large gaps in the
-	 * VM's address regions, then this would be a waste of memory as we are
-	 * generating 2 bitmaps (ack/seq) from the min address to the max
-	 * address of the VM's address regions. In the future, if we support
-	 * more than one region in the device/driver we can split the bitmaps
-	 * on the largest address region gaps. We can do this split up to the
-	 * max_regions times returned from the dirty_status command.
-	 */
-	max_regions = 1;
 	if (num_ranges > max_regions) {
 		vfio_combine_iova_ranges(ranges, nnodes, max_regions);
 		num_ranges = max_regions;
 	}
 
+	region_info = kcalloc(num_ranges, sizeof(*region_info), GFP_KERNEL);
+	if (!region_info)
+		return -ENOMEM;
+	len = num_ranges * sizeof(*region_info);
+
 	node = interval_tree_iter_first(ranges, 0, ULONG_MAX);
 	if (!node)
 		return -EINVAL;
+	for (int i = 0; i < num_ranges; i++) {
+		struct pds_lm_dirty_region_info *ri = &region_info[i];
+		u64 region_size = node->last - node->start + 1;
+		u64 region_start = node->start;
+		u32 page_count;
 
-	region_size = node->last - node->start + 1;
-	region_start = node->start;
-	region_page_size = *page_size;
+		page_count = DIV_ROUND_UP(region_size, region_page_size);
 
-	len = sizeof(*region_info);
-	region_info = kzalloc(len, GFP_KERNEL);
-	if (!region_info)
-		return -ENOMEM;
+		ri->dma_base = cpu_to_le64(region_start);
+		ri->page_count = cpu_to_le32(page_count);
+		ri->page_size_log2 = ilog2(region_page_size);
 
-	page_count = DIV_ROUND_UP(region_size, region_page_size);
+		dev_dbg(&pdev->dev,
+			"region_info[%d]: region_start 0x%llx region_end 0x%lx region_size 0x%llx page_count %u page_size %llu\n",
+			i, region_start, node->last, region_size, page_count,
+			region_page_size);
 
-	region_info->dma_base = cpu_to_le64(region_start);
-	region_info->page_count = cpu_to_le32(page_count);
-	region_info->page_size_log2 = ilog2(region_page_size);
+		node = interval_tree_iter_next(node, 0, ULONG_MAX);
+	}
 
 	regions_dma = dma_map_single(pdsc_dev, (void *)region_info, len,
 				     DMA_BIDIRECTIONAL);
@@ -239,39 +320,20 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 		goto out_free_region_info;
 	}
 
-	err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, max_regions);
+	err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, num_ranges);
 	dma_unmap_single(pdsc_dev, regions_dma, len, DMA_BIDIRECTIONAL);
 	if (err)
 		goto out_free_region_info;
 
-	/*
-	 * page_count might be adjusted by the device,
-	 * update it before freeing region_info DMA
-	 */
-	page_count = le32_to_cpu(region_info->page_count);
-
-	dev_dbg(&pdev->dev,
-		"region_info: regions_dma 0x%llx dma_base 0x%llx page_count %u page_size_log2 %u\n",
-		regions_dma, region_start, page_count,
-		(u8)ilog2(region_page_size));
-
-	err = pds_vfio_dirty_alloc_bitmaps(dirty, page_count / BITS_PER_BYTE);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n",
-			ERR_PTR(err));
-		goto out_free_region_info;
-	}
-
-	err = pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->region, page_count);
+	err = pds_vfio_dirty_alloc_regions(pds_vfio, region_info,
+					   region_page_size, num_ranges);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n",
-			ERR_PTR(err));
-		goto out_free_bitmaps;
+		dev_err(&pdev->dev,
+			"Failed to allocate %d regions for tracking dirty regions: %pe\n",
+			num_regions, ERR_PTR(err));
+		goto out_dirty_disable;
 	}
 
-	dirty->region.start = region_start;
-	dirty->region.size = region_size;
-	dirty->region.page_size = region_page_size;
 	pds_vfio_dirty_set_enabled(pds_vfio);
 
 	pds_vfio_print_guest_region_info(pds_vfio, max_regions);
@@ -280,8 +342,8 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
 
 	return 0;
 
-out_free_bitmaps:
-	pds_vfio_dirty_free_bitmaps(dirty);
+out_dirty_disable:
+	pds_vfio_dirty_disable_cmd(pds_vfio);
 out_free_region_info:
 	kfree(region_info);
 	return err;
@@ -295,6 +357,7 @@ void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio, bool send_cmd)
 			pds_vfio_dirty_disable_cmd(pds_vfio);
 		pds_vfio_dirty_free_sgl(pds_vfio);
 		pds_vfio_dirty_free_bitmaps(&pds_vfio->dirty);
+		pds_vfio_dirty_free_regions(&pds_vfio->dirty);
 	}
 
 	if (send_cmd)
@@ -365,6 +428,7 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 
 	num_sge = sg_table.nents;
 	size = num_sge * sizeof(struct pds_lm_sg_elem);
+	offset += region->dev_bmp_offset_start_byte;
 	dma_sync_single_for_device(pdsc_dev, region->sgl_addr, size, dma_dir);
 	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, region->sgl_addr, num_sge,
 					 offset, bmp_bytes, read_seq);
@@ -437,13 +501,28 @@ static int pds_vfio_dirty_process_bitmaps(struct pds_vfio_pci_device *pds_vfio,
 	return 0;
 }
 
+static struct pds_vfio_region *
+pds_vfio_get_region(struct pds_vfio_pci_device *pds_vfio, unsigned long iova)
+{
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+
+	for (int i = 0; i < dirty->num_regions; i++) {
+		struct pds_vfio_region *region = &dirty->regions[i];
+
+		if (iova >= region->start &&
+		    iova < (region->start + region->size))
+			return region;
+	}
+
+	return NULL;
+}
+
 static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 			       struct iova_bitmap *dirty_bitmap,
 			       unsigned long iova, unsigned long length)
 {
 	struct device *dev = &pds_vfio->vfio_coredev.pdev->dev;
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
-	struct pds_vfio_region *region = &dirty->region;
+	struct pds_vfio_region *region;
 	u64 bmp_offset, bmp_bytes;
 	u64 bitmap_size, pages;
 	int err;
@@ -456,6 +535,13 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
+	region = pds_vfio_get_region(pds_vfio, iova);
+	if (!region) {
+		dev_err(dev, "vf%u: Failed to find region that contains iova 0x%lx length 0x%lx\n",
+			pds_vfio->vf_id, iova, length);
+		return -EINVAL;
+	}
+
 	pages = DIV_ROUND_UP(length, region->page_size);
 	bitmap_size =
 		round_up(pages, sizeof(u64) * BITS_PER_BYTE) / BITS_PER_BYTE;
diff --git a/drivers/vfio/pci/pds/dirty.h b/drivers/vfio/pci/pds/dirty.h
index a1f6d894f913a..c8e23018b8018 100644
--- a/drivers/vfio/pci/pds/dirty.h
+++ b/drivers/vfio/pci/pds/dirty.h
@@ -13,11 +13,13 @@ struct pds_vfio_region {
 	u64 page_size;
 	struct pds_lm_sg_elem *sgl;
 	dma_addr_t sgl_addr;
+	u32 dev_bmp_offset_start_byte;
 	u16 num_sge;
 };
 
 struct pds_vfio_dirty {
-	struct pds_vfio_region region;
+	struct pds_vfio_region *regions;
+	u8 num_regions;
 	bool is_enabled;
 };
 
-- 
GitLab


From 160912fc3d4ae492954c25cd78b90083869f0011 Mon Sep 17 00:00:00 2001
From: Pasha Tatashin <pasha.tatashin@soleen.com>
Date: Thu, 30 Nov 2023 20:09:00 +0000
Subject: [PATCH 0733/4076] vfio/type1: account iommu allocations

iommu allocations should be accounted in order to allow admins to
monitor and limit the amount of iommu memory.

Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231130200900.2320829-1-pasha.tatashin@soleen.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index eacd6ec04de5a..b2854d7939ce0 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1436,7 +1436,7 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT,
 				npage << PAGE_SHIFT, prot | IOMMU_CACHE,
-				GFP_KERNEL);
+				GFP_KERNEL_ACCOUNT);
 		if (ret)
 			goto unwind;
 
@@ -1750,7 +1750,8 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			}
 
 			ret = iommu_map(domain->domain, iova, phys, size,
-					dma->prot | IOMMU_CACHE, GFP_KERNEL);
+					dma->prot | IOMMU_CACHE,
+					GFP_KERNEL_ACCOUNT);
 			if (ret) {
 				if (!dma->iommu_mapped) {
 					vfio_unpin_pages_remote(dma, iova,
@@ -1845,7 +1846,8 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head *
 			continue;
 
 		ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2,
-				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE, GFP_KERNEL);
+				IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE,
+				GFP_KERNEL_ACCOUNT);
 		if (!ret) {
 			size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE);
 
-- 
GitLab


From 6ac061db9c58ca5b9270b1b3940d2464fb3ff183 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:30 +0000
Subject: [PATCH 0734/4076] binder: use EPOLLERR from eventpoll.h

Use EPOLLERR instead of POLLERR to make sure it is cast to the correct
__poll_t type. This fixes the following sparse issue:

  drivers/android/binder.c:5030:24: warning: incorrect type in return expression (different base types)
  drivers/android/binder.c:5030:24:    expected restricted __poll_t
  drivers/android/binder.c:5030:24:    got int

Fixes: f88982679f54 ("binder: check for binder_thread allocation failure in binder_poll()")
Cc: stable@vger.kernel.org
Cc: Eric Biggers <ebiggers@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-2-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 92128aae2d060..71a40a4c546f5 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -5030,7 +5030,7 @@ static __poll_t binder_poll(struct file *filp,
 
 	thread = binder_get_thread(proc);
 	if (!thread)
-		return POLLERR;
+		return EPOLLERR;
 
 	binder_inner_proc_lock(thread->proc);
 	thread->looper |= BINDER_LOOPER_STATE_POLL;
-- 
GitLab


From 3f489c2067c5824528212b0fc18b28d51332d906 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:31 +0000
Subject: [PATCH 0735/4076] binder: fix use-after-free in shinker's callback

The mmap read lock is used during the shrinker's callback, which means
that using alloc->vma pointer isn't safe as it can race with munmap().
As of commit dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in
munmap") the mmap lock is downgraded after the vma has been isolated.

I was able to reproduce this issue by manually adding some delays and
triggering page reclaiming through the shrinker's debug sysfs. The
following KASAN report confirms the UAF:

  ==================================================================
  BUG: KASAN: slab-use-after-free in zap_page_range_single+0x470/0x4b8
  Read of size 8 at addr ffff356ed50e50f0 by task bash/478

  CPU: 1 PID: 478 Comm: bash Not tainted 6.6.0-rc5-00055-g1c8b86a3799f-dirty #70
  Hardware name: linux,dummy-virt (DT)
  Call trace:
   zap_page_range_single+0x470/0x4b8
   binder_alloc_free_page+0x608/0xadc
   __list_lru_walk_one+0x130/0x3b0
   list_lru_walk_node+0xc4/0x22c
   binder_shrink_scan+0x108/0x1dc
   shrinker_debugfs_scan_write+0x2b4/0x500
   full_proxy_write+0xd4/0x140
   vfs_write+0x1ac/0x758
   ksys_write+0xf0/0x1dc
   __arm64_sys_write+0x6c/0x9c

  Allocated by task 492:
   kmem_cache_alloc+0x130/0x368
   vm_area_alloc+0x2c/0x190
   mmap_region+0x258/0x18bc
   do_mmap+0x694/0xa60
   vm_mmap_pgoff+0x170/0x29c
   ksys_mmap_pgoff+0x290/0x3a0
   __arm64_sys_mmap+0xcc/0x144

  Freed by task 491:
   kmem_cache_free+0x17c/0x3c8
   vm_area_free_rcu_cb+0x74/0x98
   rcu_core+0xa38/0x26d4
   rcu_core_si+0x10/0x1c
   __do_softirq+0x2fc/0xd24

  Last potentially related work creation:
   __call_rcu_common.constprop.0+0x6c/0xba0
   call_rcu+0x10/0x1c
   vm_area_free+0x18/0x24
   remove_vma+0xe4/0x118
   do_vmi_align_munmap.isra.0+0x718/0xb5c
   do_vmi_munmap+0xdc/0x1fc
   __vm_munmap+0x10c/0x278
   __arm64_sys_munmap+0x58/0x7c

Fix this issue by performing instead a vma_lookup() which will fail to
find the vma that was isolated before the mmap lock downgrade. Note that
this option has better performance than upgrading to a mmap write lock
which would increase contention. Plus, mmap_write_trylock() has been
recently removed anyway.

Fixes: dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in munmap")
Cc: stable@vger.kernel.org
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-3-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 138f6d43d13b2..9d2eff70c3bab 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -1005,7 +1005,9 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 		goto err_mmget;
 	if (!mmap_read_trylock(mm))
 		goto err_mmap_read_lock_failed;
-	vma = binder_alloc_get_vma(alloc);
+	vma = vma_lookup(mm, page_addr);
+	if (vma && vma != binder_alloc_get_vma(alloc))
+		goto err_invalid_vma;
 
 	list_lru_isolate(lru, item);
 	spin_unlock(lock);
@@ -1031,6 +1033,8 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 	mutex_unlock(&alloc->mutex);
 	return LRU_REMOVED_RETRY;
 
+err_invalid_vma:
+	mmap_read_unlock(mm);
 err_mmap_read_lock_failed:
 	mmput_async(mm);
 err_mmget:
-- 
GitLab


From 9a9ab0d963621d9d12199df9817e66982582d5a5 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:32 +0000
Subject: [PATCH 0736/4076] binder: fix race between mmput() and do_exit()

Task A calls binder_update_page_range() to allocate and insert pages on
a remote address space from Task B. For this, Task A pins the remote mm
via mmget_not_zero() first. This can race with Task B do_exit() and the
final mmput() refcount decrement will come from Task A.

  Task A            | Task B
  ------------------+------------------
  mmget_not_zero()  |
                    |  do_exit()
                    |    exit_mm()
                    |      mmput()
  mmput()           |
    exit_mmap()     |
      remove_vma()  |
        fput()      |

In this case, the work of ____fput() from Task B is queued up in Task A
as TWA_RESUME. So in theory, Task A returns to userspace and the cleanup
work gets executed. However, Task A instead sleep, waiting for a reply
from Task B that never comes (it's dead).

This means the binder_deferred_release() is blocked until an unrelated
binder event forces Task A to go back to userspace. All the associated
death notifications will also be delayed until then.

In order to fix this use mmput_async() that will schedule the work in
the corresponding mm->async_put_work WQ instead of Task A.

Fixes: 457b9a6f09f0 ("Staging: android: add binder driver")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-4-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 9d2eff70c3bab..adcec5ec09597 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -271,7 +271,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 	}
 	if (mm) {
 		mmap_write_unlock(mm);
-		mmput(mm);
+		mmput_async(mm);
 	}
 	return 0;
 
@@ -304,7 +304,7 @@ err_page_ptr_cleared:
 err_no_vma:
 	if (mm) {
 		mmap_write_unlock(mm);
-		mmput(mm);
+		mmput_async(mm);
 	}
 	return vma ? -ENOMEM : -ESRCH;
 }
-- 
GitLab


From 3091c21d3e9322428691ce0b7a0cfa9c0b239eeb Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:33 +0000
Subject: [PATCH 0737/4076] binder: fix async space check for 0-sized buffers

Move the padding of 0-sized buffers to an earlier stage to account for
this round up during the alloc->free_async_space check.

Fixes: 74310e06be4d ("android: binder: Move buffer out of area shared with user space")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-5-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index adcec5ec09597..abff1bafcc43d 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -407,6 +407,10 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 				alloc->pid, extra_buffers_size);
 		return ERR_PTR(-EINVAL);
 	}
+
+	/* Pad 0-size buffers so they get assigned unique addresses */
+	size = max(size, sizeof(void *));
+
 	if (is_async &&
 	    alloc->free_async_space < size + sizeof(struct binder_buffer)) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
@@ -415,9 +419,6 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		return ERR_PTR(-ENOSPC);
 	}
 
-	/* Pad 0-size buffers so they get assigned unique addresses */
-	size = max(size, sizeof(void *));
-
 	while (n) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		BUG_ON(!buffer->free);
-- 
GitLab


From c6d05e0762ab276102246d24affd1e116a46aa0c Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:34 +0000
Subject: [PATCH 0738/4076] binder: fix unused alloc->free_async_space

Each transaction is associated with a 'struct binder_buffer' that stores
the metadata about its buffer area. Since commit 74310e06be4d ("android:
binder: Move buffer out of area shared with user space") this struct is
no longer embedded within the buffer itself but is instead allocated on
the heap to prevent userspace access to this driver-exclusive info.

Unfortunately, the space of this struct is still being accounted for in
the total buffer size calculation, specifically for async transactions.
This results in an additional 104 bytes added to every async buffer
request, and this area is never used.

This wasted space can be substantial. If we consider the maximum mmap
buffer space of SZ_4M, the driver will reserve half of it for async
transactions, or 0x200000. This area should, in theory, accommodate up
to 262,144 buffers of the minimum 8-byte size. However, after adding
the extra 'sizeof(struct binder_buffer)', the total number of buffers
drops to only 18,724, which is a sad 7.14% of the actual capacity.

This patch fixes the buffer size calculation to enable the utilization
of the entire async buffer space. This is expected to reduce the number
of -ENOSPC errors that are seen on the field.

Fixes: 74310e06be4d ("android: binder: Move buffer out of area shared with user space")
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-6-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index abff1bafcc43d..9b5c4d446efad 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -344,8 +344,7 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 			continue;
 		if (!buffer->async_transaction)
 			continue;
-		total_alloc_size += binder_alloc_buffer_size(alloc, buffer)
-			+ sizeof(struct binder_buffer);
+		total_alloc_size += binder_alloc_buffer_size(alloc, buffer);
 		num_buffers++;
 	}
 
@@ -411,8 +410,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	/* Pad 0-size buffers so they get assigned unique addresses */
 	size = max(size, sizeof(void *));
 
-	if (is_async &&
-	    alloc->free_async_space < size + sizeof(struct binder_buffer)) {
+	if (is_async && alloc->free_async_space < size) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
 			      alloc->pid, size);
@@ -520,7 +518,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	buffer->pid = pid;
 	buffer->oneway_spam_suspect = false;
 	if (is_async) {
-		alloc->free_async_space -= size + sizeof(struct binder_buffer);
+		alloc->free_async_space -= size;
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_alloc_buf size %zd async free %zd\n",
 			      alloc->pid, size, alloc->free_async_space);
@@ -658,8 +656,7 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size);
 
 	if (buffer->async_transaction) {
-		alloc->free_async_space += buffer_size + sizeof(struct binder_buffer);
-
+		alloc->free_async_space += buffer_size;
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_free_buf size %zd async free %zd\n",
 			      alloc->pid, size, alloc->free_async_space);
-- 
GitLab


From 122a3c1cb0ff304c2b8934584fcfea4edb2fe5e3 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:35 +0000
Subject: [PATCH 0739/4076] binder: fix trivial typo of
 binder_free_buf_locked()

Fix minor misspelling of the function in the comment section.

No functional changes in this patch.

Cc: stable@vger.kernel.org
Fixes: 0f966cba95c7 ("binder: add flag to clear buffer on txn complete")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-7-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 9b5c4d446efad..a124d2743c69b 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -704,7 +704,7 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 	/*
 	 * We could eliminate the call to binder_alloc_clear_buf()
 	 * from binder_alloc_deferred_release() by moving this to
-	 * binder_alloc_free_buf_locked(). However, that could
+	 * binder_free_buf_locked(). However, that could
 	 * increase contention for the alloc mutex if clear_on_free
 	 * is used frequently for large buffers. The mutex is not
 	 * needed for correctness here.
-- 
GitLab


From e1090371e02b601cbfcea175c2a6cc7c955fa830 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:36 +0000
Subject: [PATCH 0740/4076] binder: fix comment on binder_alloc_new_buf()
 return value

Update the comments of binder_alloc_new_buf() to reflect that the return
value of the function is now ERR_PTR(-errno) on failure.

No functional changes in this patch.

Cc: stable@vger.kernel.org
Fixes: 57ada2fb2250 ("binder: add log information for binder transaction failures")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-8-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index a124d2743c69b..a56cbfd9ba44a 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -556,7 +556,7 @@ err_alloc_buf_struct_failed:
  * is the sum of the three given sizes (each rounded up to
  * pointer-sized boundary)
  *
- * Return:	The allocated buffer or %NULL if error
+ * Return:	The allocated buffer or %ERR_PTR(-errno) if error
  */
 struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 					   size_t data_size,
-- 
GitLab


From da483f8b390546fbe36abd72f58d612a8032e2a8 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:37 +0000
Subject: [PATCH 0741/4076] binder: remove extern from function prototypes

The kernel coding style does not require 'extern' in function prototypes
in .h files, so remove them from drivers/android/binder_alloc.h as they
are not needed.

No functional changes in this patch.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-9-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.h | 38 +++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index dc1e2b01dd64d..82380febdd85d 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -121,27 +121,27 @@ static inline void binder_selftest_alloc(struct binder_alloc *alloc) {}
 enum lru_status binder_alloc_free_page(struct list_head *item,
 				       struct list_lru_one *lru,
 				       spinlock_t *lock, void *cb_arg);
-extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
-						  size_t data_size,
-						  size_t offsets_size,
-						  size_t extra_buffers_size,
-						  int is_async,
-						  int pid);
-extern void binder_alloc_init(struct binder_alloc *alloc);
-extern int binder_alloc_shrinker_init(void);
-extern void binder_alloc_shrinker_exit(void);
-extern void binder_alloc_vma_close(struct binder_alloc *alloc);
-extern struct binder_buffer *
+struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
+					   size_t data_size,
+					   size_t offsets_size,
+					   size_t extra_buffers_size,
+					   int is_async,
+					   int pid);
+void binder_alloc_init(struct binder_alloc *alloc);
+int binder_alloc_shrinker_init(void);
+void binder_alloc_shrinker_exit(void);
+void binder_alloc_vma_close(struct binder_alloc *alloc);
+struct binder_buffer *
 binder_alloc_prepare_to_free(struct binder_alloc *alloc,
 			     uintptr_t user_ptr);
-extern void binder_alloc_free_buf(struct binder_alloc *alloc,
-				  struct binder_buffer *buffer);
-extern int binder_alloc_mmap_handler(struct binder_alloc *alloc,
-				     struct vm_area_struct *vma);
-extern void binder_alloc_deferred_release(struct binder_alloc *alloc);
-extern int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
-extern void binder_alloc_print_allocated(struct seq_file *m,
-					 struct binder_alloc *alloc);
+void binder_alloc_free_buf(struct binder_alloc *alloc,
+			   struct binder_buffer *buffer);
+int binder_alloc_mmap_handler(struct binder_alloc *alloc,
+			      struct vm_area_struct *vma);
+void binder_alloc_deferred_release(struct binder_alloc *alloc);
+int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
+void binder_alloc_print_allocated(struct seq_file *m,
+				  struct binder_alloc *alloc);
 void binder_alloc_print_pages(struct seq_file *m,
 			      struct binder_alloc *alloc);
 
-- 
GitLab


From df9aabead791d7a3d59938abe288720f5c1367f7 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:38 +0000
Subject: [PATCH 0742/4076] binder: keep vma addresses type as unsigned long

The vma addresses in binder are currently stored as void __user *. This
requires casting back and forth between the mm/ api which uses unsigned
long. Since we also do internal arithmetic on these addresses we end up
having to cast them _again_ to an integer type.

Lets stop all the unnecessary casting which kills code readability and
store the virtual addresses as the native unsigned long from mm/. Note
that this approach is preferred over uintptr_t as Linus explains in [1].

Opportunistically add a few cosmetic touchups.

Link: https://lore.kernel.org/all/CAHk-=wj2OHy-5e+srG1fy+ZU00TmZ1NFp6kFLbVLMXHe7A1d-g@mail.gmail.com/ [1]
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-10-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder.c                | 21 +++---
 drivers/android/binder_alloc.c          | 91 +++++++++++--------------
 drivers/android/binder_alloc.h          |  6 +-
 drivers/android/binder_alloc_selftest.c |  6 +-
 drivers/android/binder_trace.h          |  2 +-
 5 files changed, 57 insertions(+), 69 deletions(-)

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 71a40a4c546f5..437d1097b118e 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2077,9 +2077,8 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
 			 * Convert the address to an offset relative to
 			 * the base of the transaction buffer.
 			 */
-			fda_offset =
-			    (parent->buffer - (uintptr_t)buffer->user_data) +
-			    fda->parent_offset;
+			fda_offset = parent->buffer - buffer->user_data +
+				fda->parent_offset;
 			for (fd_index = 0; fd_index < fda->num_fds;
 			     fd_index++) {
 				u32 fd;
@@ -2597,7 +2596,7 @@ static int binder_translate_fd_array(struct list_head *pf_head,
 	 * Convert the address to an offset relative to
 	 * the base of the transaction buffer.
 	 */
-	fda_offset = (parent->buffer - (uintptr_t)t->buffer->user_data) +
+	fda_offset = parent->buffer - t->buffer->user_data +
 		fda->parent_offset;
 	sender_ufda_base = (void __user *)(uintptr_t)sender_uparent->buffer +
 				fda->parent_offset;
@@ -2672,8 +2671,9 @@ static int binder_fixup_parent(struct list_head *pf_head,
 				  proc->pid, thread->pid);
 		return -EINVAL;
 	}
-	buffer_offset = bp->parent_offset +
-			(uintptr_t)parent->buffer - (uintptr_t)b->user_data;
+
+	buffer_offset = bp->parent_offset + parent->buffer - b->user_data;
+
 	return binder_add_fixup(pf_head, buffer_offset, bp->buffer, 0);
 }
 
@@ -3250,7 +3250,7 @@ static void binder_transaction(struct binder_proc *proc,
 				    ALIGN(extra_buffers_size, sizeof(void *)) -
 				    ALIGN(secctx_sz, sizeof(u64));
 
-		t->security_ctx = (uintptr_t)t->buffer->user_data + buf_offset;
+		t->security_ctx = t->buffer->user_data + buf_offset;
 		err = binder_alloc_copy_to_buffer(&target_proc->alloc,
 						  t->buffer, buf_offset,
 						  secctx, secctx_sz);
@@ -3527,8 +3527,7 @@ static void binder_transaction(struct binder_proc *proc,
 				goto err_translate_failed;
 			}
 			/* Fixup buffer pointer to target proc address space */
-			bp->buffer = (uintptr_t)
-				t->buffer->user_data + sg_buf_offset;
+			bp->buffer = t->buffer->user_data + sg_buf_offset;
 			sg_buf_offset += ALIGN(bp->length, sizeof(u64));
 
 			num_valid = (buffer_offset - off_start_offset) /
@@ -4698,7 +4697,7 @@ retry:
 		}
 		trd->data_size = t->buffer->data_size;
 		trd->offsets_size = t->buffer->offsets_size;
-		trd->data.ptr.buffer = (uintptr_t)t->buffer->user_data;
+		trd->data.ptr.buffer = t->buffer->user_data;
 		trd->data.ptr.offsets = trd->data.ptr.buffer +
 					ALIGN(t->buffer->data_size,
 					    sizeof(void *));
@@ -5981,7 +5980,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
 	}
 	if (buffer->target_node)
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
-	seq_printf(m, " size %zd:%zd data %pK\n",
+	seq_printf(m, " size %zd:%zd data %lx\n",
 		   buffer->data_size, buffer->offsets_size,
 		   buffer->user_data);
 }
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index a56cbfd9ba44a..179b67a3ef706 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -125,23 +125,20 @@ static void binder_insert_allocated_buffer_locked(
 
 static struct binder_buffer *binder_alloc_prepare_to_free_locked(
 		struct binder_alloc *alloc,
-		uintptr_t user_ptr)
+		unsigned long user_ptr)
 {
 	struct rb_node *n = alloc->allocated_buffers.rb_node;
 	struct binder_buffer *buffer;
-	void __user *uptr;
-
-	uptr = (void __user *)user_ptr;
 
 	while (n) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		BUG_ON(buffer->free);
 
-		if (uptr < buffer->user_data)
+		if (user_ptr < buffer->user_data) {
 			n = n->rb_left;
-		else if (uptr > buffer->user_data)
+		} else if (user_ptr > buffer->user_data) {
 			n = n->rb_right;
-		else {
+		} else {
 			/*
 			 * Guard against user threads attempting to
 			 * free the buffer when in use by kernel or
@@ -168,7 +165,7 @@ static struct binder_buffer *binder_alloc_prepare_to_free_locked(
  * Return:	Pointer to buffer or NULL
  */
 struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
-						   uintptr_t user_ptr)
+						   unsigned long user_ptr)
 {
 	struct binder_buffer *buffer;
 
@@ -179,18 +176,17 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
 }
 
 static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
-				    void __user *start, void __user *end)
+				    unsigned long start, unsigned long end)
 {
-	void __user *page_addr;
-	unsigned long user_page_addr;
-	struct binder_lru_page *page;
 	struct vm_area_struct *vma = NULL;
+	struct binder_lru_page *page;
 	struct mm_struct *mm = NULL;
+	unsigned long page_addr;
 	bool need_mm = false;
 
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: %s pages %pK-%pK\n", alloc->pid,
-		     allocate ? "allocate" : "free", start, end);
+			   "%d: %s allocate pages %lx-%lx\n", alloc->pid,
+			   allocate ? "allocate" : "free", start, end);
 
 	if (end <= start)
 		return 0;
@@ -249,18 +245,17 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 					    __GFP_HIGHMEM |
 					    __GFP_ZERO);
 		if (!page->page_ptr) {
-			pr_err("%d: binder_alloc_buf failed for page at %pK\n",
-				alloc->pid, page_addr);
+			pr_err("%d: binder_alloc_buf failed for page at %lx\n",
+			       alloc->pid, page_addr);
 			goto err_alloc_page_failed;
 		}
 		page->alloc = alloc;
 		INIT_LIST_HEAD(&page->lru);
 
-		user_page_addr = (uintptr_t)page_addr;
-		ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr);
+		ret = vm_insert_page(vma, page_addr, page->page_ptr);
 		if (ret) {
 			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
-			       alloc->pid, user_page_addr);
+			       alloc->pid, page_addr);
 			goto err_vm_insert_page_failed;
 		}
 
@@ -377,9 +372,9 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	struct binder_buffer *buffer;
 	size_t buffer_size;
 	struct rb_node *best_fit = NULL;
-	void __user *has_page_addr;
-	void __user *end_page_addr;
 	size_t size, data_offsets_size;
+	unsigned long has_page_addr;
+	unsigned long end_page_addr;
 	int ret;
 
 	/* Check binder_alloc is fully initialized */
@@ -477,15 +472,13 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		     "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
 		      alloc->pid, size, buffer, buffer_size);
 
-	has_page_addr = (void __user *)
-		(((uintptr_t)buffer->user_data + buffer_size) & PAGE_MASK);
+	has_page_addr = (buffer->user_data + buffer_size) & PAGE_MASK;
 	WARN_ON(n && buffer_size != size);
-	end_page_addr =
-		(void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
+	end_page_addr = PAGE_ALIGN(buffer->user_data + size);
 	if (end_page_addr > has_page_addr)
 		end_page_addr = has_page_addr;
-	ret = binder_update_page_range(alloc, 1, (void __user *)
-		PAGE_ALIGN((uintptr_t)buffer->user_data), end_page_addr);
+	ret = binder_update_page_range(alloc, 1, PAGE_ALIGN(buffer->user_data),
+				       end_page_addr);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -498,7 +491,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 			       __func__, alloc->pid);
 			goto err_alloc_buf_struct_failed;
 		}
-		new_buffer->user_data = (u8 __user *)buffer->user_data + size;
+		new_buffer->user_data = buffer->user_data + size;
 		list_add(&new_buffer->entry, &buffer->entry);
 		new_buffer->free = 1;
 		binder_insert_free_buffer(alloc, new_buffer);
@@ -536,8 +529,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	return buffer;
 
 err_alloc_buf_struct_failed:
-	binder_update_page_range(alloc, 0, (void __user *)
-				 PAGE_ALIGN((uintptr_t)buffer->user_data),
+	binder_update_page_range(alloc, 0, PAGE_ALIGN(buffer->user_data),
 				 end_page_addr);
 	return ERR_PTR(-ENOMEM);
 }
@@ -574,15 +566,14 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	return buffer;
 }
 
-static void __user *buffer_start_page(struct binder_buffer *buffer)
+static unsigned long buffer_start_page(struct binder_buffer *buffer)
 {
-	return (void __user *)((uintptr_t)buffer->user_data & PAGE_MASK);
+	return buffer->user_data & PAGE_MASK;
 }
 
-static void __user *prev_buffer_end_page(struct binder_buffer *buffer)
+static unsigned long prev_buffer_end_page(struct binder_buffer *buffer)
 {
-	return (void __user *)
-		(((uintptr_t)(buffer->user_data) - 1) & PAGE_MASK);
+	return (buffer->user_data - 1) & PAGE_MASK;
 }
 
 static void binder_delete_free_buffer(struct binder_alloc *alloc,
@@ -597,7 +588,7 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc,
 	if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
 		to_free = false;
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer %pK share page with %pK\n",
+				   "%d: merge free, buffer %lx share page with %lx\n",
 				   alloc->pid, buffer->user_data,
 				   prev->user_data);
 	}
@@ -607,7 +598,7 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc,
 		if (buffer_start_page(next) == buffer_start_page(buffer)) {
 			to_free = false;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-					   "%d: merge free, buffer %pK share page with %pK\n",
+					   "%d: merge free, buffer %lx share page with %lx\n",
 					   alloc->pid,
 					   buffer->user_data,
 					   next->user_data);
@@ -616,17 +607,17 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc,
 
 	if (PAGE_ALIGNED(buffer->user_data)) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer start %pK is page aligned\n",
+				   "%d: merge free, buffer start %lx is page aligned\n",
 				   alloc->pid, buffer->user_data);
 		to_free = false;
 	}
 
 	if (to_free) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
+				   "%d: merge free, buffer %lx do not share page with %lx or %lx\n",
 				   alloc->pid, buffer->user_data,
 				   prev->user_data,
-				   next ? next->user_data : NULL);
+				   next ? next->user_data : 0);
 		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
 					 buffer_start_page(buffer) + PAGE_SIZE);
 	}
@@ -662,10 +653,8 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 			      alloc->pid, size, alloc->free_async_space);
 	}
 
-	binder_update_page_range(alloc, 0,
-		(void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data),
-		(void __user *)(((uintptr_t)
-			  buffer->user_data + buffer_size) & PAGE_MASK));
+	binder_update_page_range(alloc, 0, PAGE_ALIGN(buffer->user_data),
+				 (buffer->user_data + buffer_size) & PAGE_MASK);
 
 	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
 	buffer->free = 1;
@@ -754,7 +743,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 				   SZ_4M);
 	mutex_unlock(&binder_alloc_mmap_lock);
 
-	alloc->buffer = (void __user *)vma->vm_start;
+	alloc->buffer = vma->vm_start;
 
 	alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE,
 			       sizeof(alloc->pages[0]),
@@ -787,7 +776,7 @@ err_alloc_buf_struct_failed:
 	kfree(alloc->pages);
 	alloc->pages = NULL;
 err_alloc_pages_failed:
-	alloc->buffer = NULL;
+	alloc->buffer = 0;
 	mutex_lock(&binder_alloc_mmap_lock);
 	alloc->buffer_size = 0;
 err_already_mapped:
@@ -840,7 +829,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		int i;
 
 		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-			void __user *page_addr;
+			unsigned long page_addr;
 			bool on_lru;
 
 			if (!alloc->pages[i].page_ptr)
@@ -850,7 +839,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 					      &alloc->pages[i].lru);
 			page_addr = alloc->buffer + i * PAGE_SIZE;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				     "%s: %d: page %d at %pK %s\n",
+				     "%s: %d: page %d at %lx %s\n",
 				     __func__, alloc->pid, i, page_addr,
 				     on_lru ? "on lru" : "active");
 			__free_page(alloc->pages[i].page_ptr);
@@ -870,7 +859,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 static void print_binder_buffer(struct seq_file *m, const char *prefix,
 				struct binder_buffer *buffer)
 {
-	seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n",
+	seq_printf(m, "%s %d: %lx size %zd:%zd:%zd %s\n",
 		   prefix, buffer->debug_id, buffer->user_data,
 		   buffer->data_size, buffer->offsets_size,
 		   buffer->extra_buffers_size,
@@ -984,7 +973,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 						    struct binder_lru_page,
 						    lru);
 	struct binder_alloc *alloc;
-	uintptr_t page_addr;
+	unsigned long page_addr;
 	size_t index;
 	struct vm_area_struct *vma;
 
@@ -996,7 +985,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 		goto err_page_already_freed;
 
 	index = page - alloc->pages;
-	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
+	page_addr = alloc->buffer + index * PAGE_SIZE;
 
 	mm = alloc->mm;
 	if (!mmget_not_zero(mm))
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index 82380febdd85d..cb19677a5c153 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -56,7 +56,7 @@ struct binder_buffer {
 	size_t data_size;
 	size_t offsets_size;
 	size_t extra_buffers_size;
-	void __user *user_data;
+	unsigned long user_data;
 	int    pid;
 };
 
@@ -101,7 +101,7 @@ struct binder_alloc {
 	struct mutex mutex;
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
-	void __user *buffer;
+	unsigned long buffer;
 	struct list_head buffers;
 	struct rb_root free_buffers;
 	struct rb_root allocated_buffers;
@@ -133,7 +133,7 @@ void binder_alloc_shrinker_exit(void);
 void binder_alloc_vma_close(struct binder_alloc *alloc);
 struct binder_buffer *
 binder_alloc_prepare_to_free(struct binder_alloc *alloc,
-			     uintptr_t user_ptr);
+			     unsigned long user_ptr);
 void binder_alloc_free_buf(struct binder_alloc *alloc,
 			   struct binder_buffer *buffer);
 int binder_alloc_mmap_handler(struct binder_alloc *alloc,
diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
index c2b323bc3b3a5..341c73b4a807a 100644
--- a/drivers/android/binder_alloc_selftest.c
+++ b/drivers/android/binder_alloc_selftest.c
@@ -93,11 +93,11 @@ static bool check_buffer_pages_allocated(struct binder_alloc *alloc,
 					 struct binder_buffer *buffer,
 					 size_t size)
 {
-	void __user *page_addr;
-	void __user *end;
+	unsigned long page_addr;
+	unsigned long end;
 	int page_index;
 
-	end = (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
+	end = PAGE_ALIGN(buffer->user_data + size);
 	page_addr = buffer->user_data;
 	for (; page_addr < end; page_addr += PAGE_SIZE) {
 		page_index = (page_addr - alloc->buffer) / PAGE_SIZE;
diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h
index 8cc07e6a4273e..fe38c6fc65d0f 100644
--- a/drivers/android/binder_trace.h
+++ b/drivers/android/binder_trace.h
@@ -317,7 +317,7 @@ DEFINE_EVENT(binder_buffer_class, binder_transaction_update_buffer_release,
 
 TRACE_EVENT(binder_update_page_range,
 	TP_PROTO(struct binder_alloc *alloc, bool allocate,
-		 void __user *start, void __user *end),
+		 unsigned long start, unsigned long end),
 	TP_ARGS(alloc, allocate, start, end),
 	TP_STRUCT__entry(
 		__field(int, proc)
-- 
GitLab


From 0d35bf3bf2da8d43fd12fea7699dc936999bf96e Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:39 +0000
Subject: [PATCH 0743/4076] binder: split up binder_update_page_range()

The binder_update_page_range() function performs both allocation and
freeing of binder pages. However, these two operations are unrelated and
have no common logic. In fact, when a free operation is requested, the
allocation logic is skipped entirely. This behavior makes the error path
unnecessarily complex. To improve readability of the code, this patch
splits the allocation and freeing operations into separate functions.

No functional changes are introduced by this patch.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-11-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 79 +++++++++++++++++-----------------
 1 file changed, 40 insertions(+), 39 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 179b67a3ef706..3051ea7ca44fd 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -175,8 +175,32 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
 	return buffer;
 }
 
-static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
-				    unsigned long start, unsigned long end)
+static void binder_free_page_range(struct binder_alloc *alloc,
+				   unsigned long start, unsigned long end)
+{
+	struct binder_lru_page *page;
+	unsigned long page_addr;
+
+	trace_binder_update_page_range(alloc, false, start, end);
+
+	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+		size_t index;
+		int ret;
+
+		index = (page_addr - alloc->buffer) / PAGE_SIZE;
+		page = &alloc->pages[index];
+
+		trace_binder_free_lru_start(alloc, index);
+
+		ret = list_lru_add(&binder_alloc_lru, &page->lru);
+		WARN_ON(!ret);
+
+		trace_binder_free_lru_end(alloc, index);
+	}
+}
+
+static int binder_allocate_page_range(struct binder_alloc *alloc,
+				      unsigned long start, unsigned long end)
 {
 	struct vm_area_struct *vma = NULL;
 	struct binder_lru_page *page;
@@ -185,16 +209,13 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 	bool need_mm = false;
 
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-			   "%d: %s allocate pages %lx-%lx\n", alloc->pid,
-			   allocate ? "allocate" : "free", start, end);
+			   "%d: allocate pages %lx-%lx\n",
+			   alloc->pid, start, end);
 
 	if (end <= start)
 		return 0;
 
-	trace_binder_update_page_range(alloc, allocate, start, end);
-
-	if (allocate == 0)
-		goto free_range;
+	trace_binder_update_page_range(alloc, true, start, end);
 
 	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
 		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
@@ -270,32 +291,12 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 	}
 	return 0;
 
-free_range:
-	for (page_addr = end - PAGE_SIZE; 1; page_addr -= PAGE_SIZE) {
-		bool ret;
-		size_t index;
-
-		index = (page_addr - alloc->buffer) / PAGE_SIZE;
-		page = &alloc->pages[index];
-
-		trace_binder_free_lru_start(alloc, index);
-
-		ret = list_lru_add(&binder_alloc_lru, &page->lru);
-		WARN_ON(!ret);
-
-		trace_binder_free_lru_end(alloc, index);
-		if (page_addr == start)
-			break;
-		continue;
-
 err_vm_insert_page_failed:
-		__free_page(page->page_ptr);
-		page->page_ptr = NULL;
+	__free_page(page->page_ptr);
+	page->page_ptr = NULL;
 err_alloc_page_failed:
 err_page_ptr_cleared:
-		if (page_addr == start)
-			break;
-	}
+	binder_free_page_range(alloc, start, page_addr);
 err_no_vma:
 	if (mm) {
 		mmap_write_unlock(mm);
@@ -477,8 +478,8 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	end_page_addr = PAGE_ALIGN(buffer->user_data + size);
 	if (end_page_addr > has_page_addr)
 		end_page_addr = has_page_addr;
-	ret = binder_update_page_range(alloc, 1, PAGE_ALIGN(buffer->user_data),
-				       end_page_addr);
+	ret = binder_allocate_page_range(alloc, PAGE_ALIGN(buffer->user_data),
+					 end_page_addr);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -529,8 +530,8 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	return buffer;
 
 err_alloc_buf_struct_failed:
-	binder_update_page_range(alloc, 0, PAGE_ALIGN(buffer->user_data),
-				 end_page_addr);
+	binder_free_page_range(alloc, PAGE_ALIGN(buffer->user_data),
+			       end_page_addr);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -618,8 +619,8 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc,
 				   alloc->pid, buffer->user_data,
 				   prev->user_data,
 				   next ? next->user_data : 0);
-		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
-					 buffer_start_page(buffer) + PAGE_SIZE);
+		binder_free_page_range(alloc, buffer_start_page(buffer),
+				       buffer_start_page(buffer) + PAGE_SIZE);
 	}
 	list_del(&buffer->entry);
 	kfree(buffer);
@@ -653,8 +654,8 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 			      alloc->pid, size, alloc->free_async_space);
 	}
 
-	binder_update_page_range(alloc, 0, PAGE_ALIGN(buffer->user_data),
-				 (buffer->user_data + buffer_size) & PAGE_MASK);
+	binder_free_page_range(alloc, PAGE_ALIGN(buffer->user_data),
+			       (buffer->user_data + buffer_size) & PAGE_MASK);
 
 	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
 	buffer->free = 1;
-- 
GitLab


From 377e1684db7a1e23261f3c3ebf76523c0554d512 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:40 +0000
Subject: [PATCH 0744/4076] binder: do unlocked work in binder_alloc_new_buf()

Extract non-critical sections from binder_alloc_new_buf_locked() that
don't require holding the alloc->mutex. While we are here, consolidate
the checks for size overflow and zero-sized padding into a separate
sanitized_size() helper function.

Also add a few touchups to follow the coding guidelines.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-12-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 95 ++++++++++++++++++++--------------
 1 file changed, 56 insertions(+), 39 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 3051ea7ca44fd..40a2ca0c0dea8 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -363,9 +363,7 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 
 static struct binder_buffer *binder_alloc_new_buf_locked(
 				struct binder_alloc *alloc,
-				size_t data_size,
-				size_t offsets_size,
-				size_t extra_buffers_size,
+				size_t size,
 				int is_async,
 				int pid)
 {
@@ -373,39 +371,10 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	struct binder_buffer *buffer;
 	size_t buffer_size;
 	struct rb_node *best_fit = NULL;
-	size_t size, data_offsets_size;
 	unsigned long has_page_addr;
 	unsigned long end_page_addr;
 	int ret;
 
-	/* Check binder_alloc is fully initialized */
-	if (!binder_alloc_get_vma(alloc)) {
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "%d: binder_alloc_buf, no vma\n",
-				   alloc->pid);
-		return ERR_PTR(-ESRCH);
-	}
-
-	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
-		ALIGN(offsets_size, sizeof(void *));
-
-	if (data_offsets_size < data_size || data_offsets_size < offsets_size) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				"%d: got transaction with invalid size %zd-%zd\n",
-				alloc->pid, data_size, offsets_size);
-		return ERR_PTR(-EINVAL);
-	}
-	size = data_offsets_size + ALIGN(extra_buffers_size, sizeof(void *));
-	if (size < data_offsets_size || size < extra_buffers_size) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				"%d: got transaction with invalid extra_buffers_size %zd\n",
-				alloc->pid, extra_buffers_size);
-		return ERR_PTR(-EINVAL);
-	}
-
-	/* Pad 0-size buffers so they get assigned unique addresses */
-	size = max(size, sizeof(void *));
-
 	if (is_async && alloc->free_async_space < size) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
@@ -421,13 +390,14 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		if (size < buffer_size) {
 			best_fit = n;
 			n = n->rb_left;
-		} else if (size > buffer_size)
+		} else if (size > buffer_size) {
 			n = n->rb_right;
-		else {
+		} else {
 			best_fit = n;
 			break;
 		}
 	}
+
 	if (best_fit == NULL) {
 		size_t allocated_buffers = 0;
 		size_t largest_alloc_size = 0;
@@ -505,10 +475,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 		     "%d: binder_alloc_buf size %zd got %pK\n",
 		      alloc->pid, size, buffer);
-	buffer->data_size = data_size;
-	buffer->offsets_size = offsets_size;
 	buffer->async_transaction = is_async;
-	buffer->extra_buffers_size = extra_buffers_size;
 	buffer->pid = pid;
 	buffer->oneway_spam_suspect = false;
 	if (is_async) {
@@ -527,6 +494,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 			alloc->oneway_spam_detected = false;
 		}
 	}
+
 	return buffer;
 
 err_alloc_buf_struct_failed:
@@ -535,6 +503,28 @@ err_alloc_buf_struct_failed:
 	return ERR_PTR(-ENOMEM);
 }
 
+/* Calculate the sanitized total size, returns 0 for invalid request */
+static inline size_t sanitized_size(size_t data_size,
+				    size_t offsets_size,
+				    size_t extra_buffers_size)
+{
+	size_t total, tmp;
+
+	/* Align to pointer size and check for overflows */
+	tmp = ALIGN(data_size, sizeof(void *)) +
+		ALIGN(offsets_size, sizeof(void *));
+	if (tmp < data_size || tmp < offsets_size)
+		return 0;
+	total = tmp + ALIGN(extra_buffers_size, sizeof(void *));
+	if (total < tmp || total < extra_buffers_size)
+		return 0;
+
+	/* Pad 0-sized buffers so they get a unique address */
+	total = max(total, sizeof(void *));
+
+	return total;
+}
+
 /**
  * binder_alloc_new_buf() - Allocate a new binder buffer
  * @alloc:              binder_alloc for this proc
@@ -559,11 +549,38 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 					   int pid)
 {
 	struct binder_buffer *buffer;
+	size_t size;
+
+	/* Check binder_alloc is fully initialized */
+	if (!binder_alloc_get_vma(alloc)) {
+		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
+				   "%d: binder_alloc_buf, no vma\n",
+				   alloc->pid);
+		return ERR_PTR(-ESRCH);
+	}
+
+	size = sanitized_size(data_size, offsets_size, extra_buffers_size);
+	if (unlikely(!size)) {
+		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+				   "%d: got transaction with invalid size %zd-%zd-%zd\n",
+				   alloc->pid, data_size, offsets_size,
+				   extra_buffers_size);
+		return ERR_PTR(-EINVAL);
+	}
 
 	mutex_lock(&alloc->mutex);
-	buffer = binder_alloc_new_buf_locked(alloc, data_size, offsets_size,
-					     extra_buffers_size, is_async, pid);
+	buffer = binder_alloc_new_buf_locked(alloc, size, is_async, pid);
+	if (IS_ERR(buffer)) {
+		mutex_unlock(&alloc->mutex);
+		goto out;
+	}
+
+	buffer->data_size = data_size;
+	buffer->offsets_size = offsets_size;
+	buffer->extra_buffers_size = extra_buffers_size;
 	mutex_unlock(&alloc->mutex);
+
+out:
 	return buffer;
 }
 
-- 
GitLab


From 89f71743bf42217dd4092fda703a8e4f6f4e55ac Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:41 +0000
Subject: [PATCH 0745/4076] binder: remove pid param in binder_alloc_new_buf()

Binder attributes the buffer allocation to the current->tgid everytime.
There is no need to pass this as a parameter so drop it.

Also add a few touchups to follow the coding guidelines. No functional
changes are introduced in this patch.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-13-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder.c                |  2 +-
 drivers/android/binder_alloc.c          | 18 ++++++++----------
 drivers/android/binder_alloc.h          |  7 ++-----
 drivers/android/binder_alloc_selftest.c |  2 +-
 4 files changed, 12 insertions(+), 17 deletions(-)

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 437d1097b118e..45674af6310fe 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -3225,7 +3225,7 @@ static void binder_transaction(struct binder_proc *proc,
 
 	t->buffer = binder_alloc_new_buf(&target_proc->alloc, tr->data_size,
 		tr->offsets_size, extra_buffers_size,
-		!reply && (t->flags & TF_ONE_WAY), current->tgid);
+		!reply && (t->flags & TF_ONE_WAY));
 	if (IS_ERR(t->buffer)) {
 		char *s;
 
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 40a2ca0c0dea8..b5c3e56318e14 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -319,7 +319,7 @@ static inline struct vm_area_struct *binder_alloc_get_vma(
 	return smp_load_acquire(&alloc->vma);
 }
 
-static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
+static bool debug_low_async_space_locked(struct binder_alloc *alloc)
 {
 	/*
 	 * Find the amount and size of buffers allocated by the current caller;
@@ -328,10 +328,11 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 	 * and at some point we'll catch them in the act. This is more efficient
 	 * than keeping a map per pid.
 	 */
-	struct rb_node *n;
 	struct binder_buffer *buffer;
 	size_t total_alloc_size = 0;
+	int pid = current->tgid;
 	size_t num_buffers = 0;
+	struct rb_node *n;
 
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL;
 		 n = rb_next(n)) {
@@ -364,8 +365,7 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
 static struct binder_buffer *binder_alloc_new_buf_locked(
 				struct binder_alloc *alloc,
 				size_t size,
-				int is_async,
-				int pid)
+				int is_async)
 {
 	struct rb_node *n = alloc->free_buffers.rb_node;
 	struct binder_buffer *buffer;
@@ -476,7 +476,6 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		     "%d: binder_alloc_buf size %zd got %pK\n",
 		      alloc->pid, size, buffer);
 	buffer->async_transaction = is_async;
-	buffer->pid = pid;
 	buffer->oneway_spam_suspect = false;
 	if (is_async) {
 		alloc->free_async_space -= size;
@@ -489,7 +488,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 			 * of async space left (which is less than 10% of total
 			 * buffer size).
 			 */
-			buffer->oneway_spam_suspect = debug_low_async_space_locked(alloc, pid);
+			buffer->oneway_spam_suspect = debug_low_async_space_locked(alloc);
 		} else {
 			alloc->oneway_spam_detected = false;
 		}
@@ -532,7 +531,6 @@ static inline size_t sanitized_size(size_t data_size,
  * @offsets_size:       user specified buffer offset
  * @extra_buffers_size: size of extra space for meta-data (eg, security context)
  * @is_async:           buffer for async transaction
- * @pid:				pid to attribute allocation to (used for debugging)
  *
  * Allocate a new buffer given the requested sizes. Returns
  * the kernel version of the buffer pointer. The size allocated
@@ -545,8 +543,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 					   size_t data_size,
 					   size_t offsets_size,
 					   size_t extra_buffers_size,
-					   int is_async,
-					   int pid)
+					   int is_async)
 {
 	struct binder_buffer *buffer;
 	size_t size;
@@ -569,7 +566,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	}
 
 	mutex_lock(&alloc->mutex);
-	buffer = binder_alloc_new_buf_locked(alloc, size, is_async, pid);
+	buffer = binder_alloc_new_buf_locked(alloc, size, is_async);
 	if (IS_ERR(buffer)) {
 		mutex_unlock(&alloc->mutex);
 		goto out;
@@ -578,6 +575,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	buffer->data_size = data_size;
 	buffer->offsets_size = offsets_size;
 	buffer->extra_buffers_size = extra_buffers_size;
+	buffer->pid = current->tgid;
 	mutex_unlock(&alloc->mutex);
 
 out:
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index cb19677a5c153..bbc16bc6d5ac9 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -49,15 +49,13 @@ struct binder_buffer {
 	unsigned async_transaction:1;
 	unsigned oneway_spam_suspect:1;
 	unsigned debug_id:27;
-
 	struct binder_transaction *transaction;
-
 	struct binder_node *target_node;
 	size_t data_size;
 	size_t offsets_size;
 	size_t extra_buffers_size;
 	unsigned long user_data;
-	int    pid;
+	int pid;
 };
 
 /**
@@ -125,8 +123,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 					   size_t data_size,
 					   size_t offsets_size,
 					   size_t extra_buffers_size,
-					   int is_async,
-					   int pid);
+					   int is_async);
 void binder_alloc_init(struct binder_alloc *alloc);
 int binder_alloc_shrinker_init(void);
 void binder_alloc_shrinker_exit(void);
diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
index 341c73b4a807a..ed753747e54ce 100644
--- a/drivers/android/binder_alloc_selftest.c
+++ b/drivers/android/binder_alloc_selftest.c
@@ -119,7 +119,7 @@ static void binder_selftest_alloc_buf(struct binder_alloc *alloc,
 	int i;
 
 	for (i = 0; i < BUFFER_NUM; i++) {
-		buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0, 0);
+		buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0);
 		if (IS_ERR(buffers[i]) ||
 		    !check_buffer_pages_allocated(alloc, buffers[i],
 						  sizes[i])) {
-- 
GitLab


From 9409af24e4503d14093b27db9425f7c99e64fef4 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:42 +0000
Subject: [PATCH 0746/4076] binder: separate the no-space debugging logic

Move the no-space debugging logic into a separate function. Lets also
mark this branch as unlikely in binder_alloc_new_buf_locked() as most
requests will fit without issue.

Also add a few cosmetic changes and suggestions from checkpatch.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-14-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 71 +++++++++++++++++++---------------
 1 file changed, 40 insertions(+), 31 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index b5c3e56318e14..3dca7b1992460 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -319,6 +319,43 @@ static inline struct vm_area_struct *binder_alloc_get_vma(
 	return smp_load_acquire(&alloc->vma);
 }
 
+static void debug_no_space_locked(struct binder_alloc *alloc)
+{
+	size_t largest_alloc_size = 0;
+	struct binder_buffer *buffer;
+	size_t allocated_buffers = 0;
+	size_t largest_free_size = 0;
+	size_t total_alloc_size = 0;
+	size_t total_free_size = 0;
+	size_t free_buffers = 0;
+	size_t buffer_size;
+	struct rb_node *n;
+
+	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+		allocated_buffers++;
+		total_alloc_size += buffer_size;
+		if (buffer_size > largest_alloc_size)
+			largest_alloc_size = buffer_size;
+	}
+
+	for (n = rb_first(&alloc->free_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+		free_buffers++;
+		total_free_size += buffer_size;
+		if (buffer_size > largest_free_size)
+			largest_free_size = buffer_size;
+	}
+
+	binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
+			   "allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
+			   total_alloc_size, allocated_buffers,
+			   largest_alloc_size, total_free_size,
+			   free_buffers, largest_free_size);
+}
+
 static bool debug_low_async_space_locked(struct binder_alloc *alloc)
 {
 	/*
@@ -398,42 +435,14 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		}
 	}
 
-	if (best_fit == NULL) {
-		size_t allocated_buffers = 0;
-		size_t largest_alloc_size = 0;
-		size_t total_alloc_size = 0;
-		size_t free_buffers = 0;
-		size_t largest_free_size = 0;
-		size_t total_free_size = 0;
-
-		for (n = rb_first(&alloc->allocated_buffers); n != NULL;
-		     n = rb_next(n)) {
-			buffer = rb_entry(n, struct binder_buffer, rb_node);
-			buffer_size = binder_alloc_buffer_size(alloc, buffer);
-			allocated_buffers++;
-			total_alloc_size += buffer_size;
-			if (buffer_size > largest_alloc_size)
-				largest_alloc_size = buffer_size;
-		}
-		for (n = rb_first(&alloc->free_buffers); n != NULL;
-		     n = rb_next(n)) {
-			buffer = rb_entry(n, struct binder_buffer, rb_node);
-			buffer_size = binder_alloc_buffer_size(alloc, buffer);
-			free_buffers++;
-			total_free_size += buffer_size;
-			if (buffer_size > largest_free_size)
-				largest_free_size = buffer_size;
-		}
+	if (unlikely(!best_fit)) {
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf size %zd failed, no address space\n",
 				   alloc->pid, size);
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
-				   total_alloc_size, allocated_buffers,
-				   largest_alloc_size, total_free_size,
-				   free_buffers, largest_free_size);
+		debug_no_space_locked(alloc);
 		return ERR_PTR(-ENOSPC);
 	}
+
 	if (n == NULL) {
 		buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
 		buffer_size = binder_alloc_buffer_size(alloc, buffer);
-- 
GitLab


From c13500eaabd2343aa4cbb76b54ec624cb0c0ef8d Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:43 +0000
Subject: [PATCH 0747/4076] binder: relocate low space calculation

Move the low async space calculation to debug_low_async_space_locked().
This logic not only fits better here but also offloads some of the many
tasks currently done in binder_alloc_new_buf_locked().

No functional change in this patch.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-15-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 3dca7b1992460..167ee6f871dc1 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -371,6 +371,15 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc)
 	size_t num_buffers = 0;
 	struct rb_node *n;
 
+	/*
+	 * Only start detecting spammers once we have less than 20% of async
+	 * space left (which is less than 10% of total buffer size).
+	 */
+	if (alloc->free_async_space >= alloc->buffer_size / 10) {
+		alloc->oneway_spam_detected = false;
+		return false;
+	}
+
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL;
 		 n = rb_next(n)) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
@@ -491,16 +500,8 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_alloc_buf size %zd async free %zd\n",
 			      alloc->pid, size, alloc->free_async_space);
-		if (alloc->free_async_space < alloc->buffer_size / 10) {
-			/*
-			 * Start detecting spammers once we have less than 20%
-			 * of async space left (which is less than 10% of total
-			 * buffer size).
-			 */
-			buffer->oneway_spam_suspect = debug_low_async_space_locked(alloc);
-		} else {
-			alloc->oneway_spam_detected = false;
-		}
+		if (debug_low_async_space_locked(alloc))
+			buffer->oneway_spam_suspect = true;
 	}
 
 	return buffer;
-- 
GitLab


From cbc174a64b8d0ab542752c167dc1334b52b88624 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:44 +0000
Subject: [PATCH 0748/4076] binder: relocate binder_alloc_clear_buf()

Move this function up along with binder_alloc_get_page() so that their
prototypes aren't necessary.

No functional change in this patch.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-16-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 124 ++++++++++++++++-----------------
 1 file changed, 61 insertions(+), 63 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 167ee6f871dc1..99eacd8782b8a 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -704,8 +704,68 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	binder_insert_free_buffer(alloc, buffer);
 }
 
+/**
+ * binder_alloc_get_page() - get kernel pointer for given buffer offset
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be accessed
+ * @buffer_offset: offset into @buffer data
+ * @pgoffp: address to copy final page offset to
+ *
+ * Lookup the struct page corresponding to the address
+ * at @buffer_offset into @buffer->user_data. If @pgoffp is not
+ * NULL, the byte-offset into the page is written there.
+ *
+ * The caller is responsible to ensure that the offset points
+ * to a valid address within the @buffer and that @buffer is
+ * not freeable by the user. Since it can't be freed, we are
+ * guaranteed that the corresponding elements of @alloc->pages[]
+ * cannot change.
+ *
+ * Return: struct page
+ */
+static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
+					  struct binder_buffer *buffer,
+					  binder_size_t buffer_offset,
+					  pgoff_t *pgoffp)
+{
+	binder_size_t buffer_space_offset = buffer_offset +
+		(buffer->user_data - alloc->buffer);
+	pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
+	size_t index = buffer_space_offset >> PAGE_SHIFT;
+	struct binder_lru_page *lru_page;
+
+	lru_page = &alloc->pages[index];
+	*pgoffp = pgoff;
+	return lru_page->page_ptr;
+}
+
+/**
+ * binder_alloc_clear_buf() - zero out buffer
+ * @alloc: binder_alloc for this proc
+ * @buffer: binder buffer to be cleared
+ *
+ * memset the given buffer to 0
+ */
 static void binder_alloc_clear_buf(struct binder_alloc *alloc,
-				   struct binder_buffer *buffer);
+				   struct binder_buffer *buffer)
+{
+	size_t bytes = binder_alloc_buffer_size(alloc, buffer);
+	binder_size_t buffer_offset = 0;
+
+	while (bytes) {
+		unsigned long size;
+		struct page *page;
+		pgoff_t pgoff;
+
+		page = binder_alloc_get_page(alloc, buffer,
+					     buffer_offset, &pgoff);
+		size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
+		memset_page(page, pgoff, 0, size);
+		bytes -= size;
+		buffer_offset += size;
+	}
+}
+
 /**
  * binder_alloc_free_buf() - free a binder buffer
  * @alloc:	binder_alloc for this proc
@@ -1148,68 +1208,6 @@ static inline bool check_buffer(struct binder_alloc *alloc,
 		(!buffer->allow_user_free || !buffer->transaction);
 }
 
-/**
- * binder_alloc_get_page() - get kernel pointer for given buffer offset
- * @alloc: binder_alloc for this proc
- * @buffer: binder buffer to be accessed
- * @buffer_offset: offset into @buffer data
- * @pgoffp: address to copy final page offset to
- *
- * Lookup the struct page corresponding to the address
- * at @buffer_offset into @buffer->user_data. If @pgoffp is not
- * NULL, the byte-offset into the page is written there.
- *
- * The caller is responsible to ensure that the offset points
- * to a valid address within the @buffer and that @buffer is
- * not freeable by the user. Since it can't be freed, we are
- * guaranteed that the corresponding elements of @alloc->pages[]
- * cannot change.
- *
- * Return: struct page
- */
-static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
-					  struct binder_buffer *buffer,
-					  binder_size_t buffer_offset,
-					  pgoff_t *pgoffp)
-{
-	binder_size_t buffer_space_offset = buffer_offset +
-		(buffer->user_data - alloc->buffer);
-	pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
-	size_t index = buffer_space_offset >> PAGE_SHIFT;
-	struct binder_lru_page *lru_page;
-
-	lru_page = &alloc->pages[index];
-	*pgoffp = pgoff;
-	return lru_page->page_ptr;
-}
-
-/**
- * binder_alloc_clear_buf() - zero out buffer
- * @alloc: binder_alloc for this proc
- * @buffer: binder buffer to be cleared
- *
- * memset the given buffer to 0
- */
-static void binder_alloc_clear_buf(struct binder_alloc *alloc,
-				   struct binder_buffer *buffer)
-{
-	size_t bytes = binder_alloc_buffer_size(alloc, buffer);
-	binder_size_t buffer_offset = 0;
-
-	while (bytes) {
-		unsigned long size;
-		struct page *page;
-		pgoff_t pgoff;
-
-		page = binder_alloc_get_page(alloc, buffer,
-					     buffer_offset, &pgoff);
-		size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
-		memset_page(page, pgoff, 0, size);
-		bytes -= size;
-		buffer_offset += size;
-	}
-}
-
 /**
  * binder_alloc_copy_user_to_buffer() - copy src user to tgt user
  * @alloc: binder_alloc for this proc
-- 
GitLab


From ea2735ce19c1c6ce0f6011f813a1eea0272c231d Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:45 +0000
Subject: [PATCH 0749/4076] binder: refactor page range allocation

Instead of looping through the page range twice to first determine if
the mmap lock is required, simply do it per-page as needed. Split out
all this logic into a separate binder_install_single_page() function.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-17-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 107 +++++++++++++++------------------
 1 file changed, 47 insertions(+), 60 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 99eacd8782b8a..1caf0e3d34518 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -199,14 +199,51 @@ static void binder_free_page_range(struct binder_alloc *alloc,
 	}
 }
 
+static int binder_install_single_page(struct binder_alloc *alloc,
+				      struct binder_lru_page *lru_page,
+				      unsigned long addr)
+{
+	struct page *page;
+	int ret = 0;
+
+	if (!mmget_not_zero(alloc->mm))
+		return -ESRCH;
+
+	mmap_write_lock(alloc->mm);
+	if (!alloc->vma) {
+		pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
+		ret = -ESRCH;
+		goto out;
+	}
+
+	page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+	if (!page) {
+		pr_err("%d: failed to allocate page\n", alloc->pid);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = vm_insert_page(alloc->vma, addr, page);
+	if (ret) {
+		pr_err("%d: %s failed to insert page at %lx with %d\n",
+		       alloc->pid, __func__, addr, ret);
+		__free_page(page);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	lru_page->page_ptr = page;
+out:
+	mmap_write_unlock(alloc->mm);
+	mmput_async(alloc->mm);
+	return ret;
+}
+
 static int binder_allocate_page_range(struct binder_alloc *alloc,
 				      unsigned long start, unsigned long end)
 {
-	struct vm_area_struct *vma = NULL;
 	struct binder_lru_page *page;
-	struct mm_struct *mm = NULL;
 	unsigned long page_addr;
-	bool need_mm = false;
 
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 			   "%d: allocate pages %lx-%lx\n",
@@ -218,32 +255,9 @@ static int binder_allocate_page_range(struct binder_alloc *alloc,
 	trace_binder_update_page_range(alloc, true, start, end);
 
 	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
-		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
-		if (!page->page_ptr) {
-			need_mm = true;
-			break;
-		}
-	}
-
-	if (need_mm && mmget_not_zero(alloc->mm))
-		mm = alloc->mm;
-
-	if (mm) {
-		mmap_write_lock(mm);
-		vma = alloc->vma;
-	}
-
-	if (!vma && need_mm) {
-		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
-				   "%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
-				   alloc->pid);
-		goto err_no_vma;
-	}
-
-	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
-		int ret;
+		unsigned long index;
 		bool on_lru;
-		size_t index;
+		int ret;
 
 		index = (page_addr - alloc->buffer) / PAGE_SIZE;
 		page = &alloc->pages[index];
@@ -258,26 +272,15 @@ static int binder_allocate_page_range(struct binder_alloc *alloc,
 			continue;
 		}
 
-		if (WARN_ON(!vma))
-			goto err_page_ptr_cleared;
-
 		trace_binder_alloc_page_start(alloc, index);
-		page->page_ptr = alloc_page(GFP_KERNEL |
-					    __GFP_HIGHMEM |
-					    __GFP_ZERO);
-		if (!page->page_ptr) {
-			pr_err("%d: binder_alloc_buf failed for page at %lx\n",
-			       alloc->pid, page_addr);
-			goto err_alloc_page_failed;
-		}
+
 		page->alloc = alloc;
 		INIT_LIST_HEAD(&page->lru);
 
-		ret = vm_insert_page(vma, page_addr, page->page_ptr);
+		ret = binder_install_single_page(alloc, page, page_addr);
 		if (ret) {
-			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
-			       alloc->pid, page_addr);
-			goto err_vm_insert_page_failed;
+			binder_free_page_range(alloc, start, page_addr);
+			return ret;
 		}
 
 		if (index + 1 > alloc->pages_high)
@@ -285,24 +288,8 @@ static int binder_allocate_page_range(struct binder_alloc *alloc,
 
 		trace_binder_alloc_page_end(alloc, index);
 	}
-	if (mm) {
-		mmap_write_unlock(mm);
-		mmput_async(mm);
-	}
-	return 0;
 
-err_vm_insert_page_failed:
-	__free_page(page->page_ptr);
-	page->page_ptr = NULL;
-err_alloc_page_failed:
-err_page_ptr_cleared:
-	binder_free_page_range(alloc, start, page_addr);
-err_no_vma:
-	if (mm) {
-		mmap_write_unlock(mm);
-		mmput_async(mm);
-	}
-	return vma ? -ENOMEM : -ESRCH;
+	return 0;
 }
 
 static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
-- 
GitLab


From c7ac30fad18231a1637d38aa8a97d6b4788ed8ad Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:46 +0000
Subject: [PATCH 0750/4076] binder: malloc new_buffer outside of locks

Preallocate new_buffer before acquiring the alloc->mutex and hand it
down to binder_alloc_new_buf_locked(). The new buffer will be used in
the vast majority of requests (measured at 98.2% in field data). The
buffer is discarded otherwise. This change is required in preparation
for transitioning alloc->mutex into a spinlock in subsequent commits.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-18-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 44 ++++++++++++++++++----------------
 1 file changed, 23 insertions(+), 21 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 1caf0e3d34518..86f4929a55d58 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -395,24 +395,27 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc)
 	return false;
 }
 
+/* Callers preallocate @new_buffer, it is freed by this function if unused */
 static struct binder_buffer *binder_alloc_new_buf_locked(
 				struct binder_alloc *alloc,
+				struct binder_buffer *new_buffer,
 				size_t size,
 				int is_async)
 {
 	struct rb_node *n = alloc->free_buffers.rb_node;
-	struct binder_buffer *buffer;
-	size_t buffer_size;
 	struct rb_node *best_fit = NULL;
+	struct binder_buffer *buffer;
 	unsigned long has_page_addr;
 	unsigned long end_page_addr;
+	size_t buffer_size;
 	int ret;
 
 	if (is_async && alloc->free_async_space < size) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
 			      alloc->pid, size);
-		return ERR_PTR(-ENOSPC);
+		buffer = ERR_PTR(-ENOSPC);
+		goto out;
 	}
 
 	while (n) {
@@ -436,7 +439,8 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 				   "%d: binder_alloc_buf size %zd failed, no address space\n",
 				   alloc->pid, size);
 		debug_no_space_locked(alloc);
-		return ERR_PTR(-ENOSPC);
+		buffer = ERR_PTR(-ENOSPC);
+		goto out;
 	}
 
 	if (n == NULL) {
@@ -455,22 +459,17 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		end_page_addr = has_page_addr;
 	ret = binder_allocate_page_range(alloc, PAGE_ALIGN(buffer->user_data),
 					 end_page_addr);
-	if (ret)
-		return ERR_PTR(ret);
+	if (ret) {
+		buffer = ERR_PTR(ret);
+		goto out;
+	}
 
 	if (buffer_size != size) {
-		struct binder_buffer *new_buffer;
-
-		new_buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
-		if (!new_buffer) {
-			pr_err("%s: %d failed to alloc new buffer struct\n",
-			       __func__, alloc->pid);
-			goto err_alloc_buf_struct_failed;
-		}
 		new_buffer->user_data = buffer->user_data + size;
 		list_add(&new_buffer->entry, &buffer->entry);
 		new_buffer->free = 1;
 		binder_insert_free_buffer(alloc, new_buffer);
+		new_buffer = NULL;
 	}
 
 	rb_erase(best_fit, &alloc->free_buffers);
@@ -491,12 +490,10 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 			buffer->oneway_spam_suspect = true;
 	}
 
+out:
+	/* Discard possibly unused new_buffer */
+	kfree(new_buffer);
 	return buffer;
-
-err_alloc_buf_struct_failed:
-	binder_free_page_range(alloc, PAGE_ALIGN(buffer->user_data),
-			       end_page_addr);
-	return ERR_PTR(-ENOMEM);
 }
 
 /* Calculate the sanitized total size, returns 0 for invalid request */
@@ -542,7 +539,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 					   size_t extra_buffers_size,
 					   int is_async)
 {
-	struct binder_buffer *buffer;
+	struct binder_buffer *buffer, *next;
 	size_t size;
 
 	/* Check binder_alloc is fully initialized */
@@ -562,8 +559,13 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 		return ERR_PTR(-EINVAL);
 	}
 
+	/* Preallocate the next buffer */
+	next = kzalloc(sizeof(*next), GFP_KERNEL);
+	if (!next)
+		return ERR_PTR(-ENOMEM);
+
 	mutex_lock(&alloc->mutex);
-	buffer = binder_alloc_new_buf_locked(alloc, size, is_async);
+	buffer = binder_alloc_new_buf_locked(alloc, next, size, is_async);
 	if (IS_ERR(buffer)) {
 		mutex_unlock(&alloc->mutex);
 		goto out;
-- 
GitLab


From 68aef12d094e4c96d972790f1620415460a4f3cf Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:47 +0000
Subject: [PATCH 0751/4076] binder: initialize lru pages in mmap callback

Rather than repeatedly initializing some of the binder_lru_page members
during binder_alloc_new_buf(), perform this initialization just once in
binder_alloc_mmap_handler(), after the pages have been created.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-19-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 86f4929a55d58..25efdbb2ad5d2 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -274,9 +274,6 @@ static int binder_allocate_page_range(struct binder_alloc *alloc,
 
 		trace_binder_alloc_page_start(alloc, index);
 
-		page->alloc = alloc;
-		INIT_LIST_HEAD(&page->lru);
-
 		ret = binder_install_single_page(alloc, page, page_addr);
 		if (ret) {
 			binder_free_page_range(alloc, start, page_addr);
@@ -798,9 +795,9 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 			      struct vm_area_struct *vma)
 {
-	int ret;
-	const char *failure_string;
 	struct binder_buffer *buffer;
+	const char *failure_string;
+	int ret, i;
 
 	if (unlikely(vma->vm_mm != alloc->mm)) {
 		ret = -EINVAL;
@@ -829,6 +826,11 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 		goto err_alloc_pages_failed;
 	}
 
+	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+		alloc->pages[i].alloc = alloc;
+		INIT_LIST_HEAD(&alloc->pages[i].lru);
+	}
+
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer) {
 		ret = -ENOMEM;
-- 
GitLab


From 37ebbb4f73a0d299fa0c7dd043932a2f5fbbb779 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:48 +0000
Subject: [PATCH 0752/4076] binder: perform page installation outside of locks

Split out the insertion of pages to be outside of the alloc->mutex in a
separate binder_install_buffer_pages() routine. Since this is no longer
serialized, we must look at the full range of pages used by the buffers.
The installation is protected with mmap_sem in write mode since multiple
tasks might race to install the same page.

Besides avoiding unnecessary nested locking this helps in preparation of
switching the alloc->mutex into a spinlock_t in subsequent patches.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-20-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 101 ++++++++++++++++++++++++---------
 1 file changed, 73 insertions(+), 28 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 25efdbb2ad5d2..551f08e844089 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -175,6 +175,21 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
 	return buffer;
 }
 
+static inline void
+binder_set_installed_page(struct binder_lru_page *lru_page,
+			  struct page *page)
+{
+	/* Pairs with acquire in binder_get_installed_page() */
+	smp_store_release(&lru_page->page_ptr, page);
+}
+
+static inline struct page *
+binder_get_installed_page(struct binder_lru_page *lru_page)
+{
+	/* Pairs with release in binder_set_installed_page() */
+	return smp_load_acquire(&lru_page->page_ptr);
+}
+
 static void binder_free_page_range(struct binder_alloc *alloc,
 				   unsigned long start, unsigned long end)
 {
@@ -190,6 +205,9 @@ static void binder_free_page_range(struct binder_alloc *alloc,
 		index = (page_addr - alloc->buffer) / PAGE_SIZE;
 		page = &alloc->pages[index];
 
+		if (!binder_get_installed_page(page))
+			continue;
+
 		trace_binder_free_lru_start(alloc, index);
 
 		ret = list_lru_add(&binder_alloc_lru, &page->lru);
@@ -209,7 +227,14 @@ static int binder_install_single_page(struct binder_alloc *alloc,
 	if (!mmget_not_zero(alloc->mm))
 		return -ESRCH;
 
+	/*
+	 * Protected with mmap_sem in write mode as multiple tasks
+	 * might race to install the same page.
+	 */
 	mmap_write_lock(alloc->mm);
+	if (binder_get_installed_page(lru_page))
+		goto out;
+
 	if (!alloc->vma) {
 		pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
 		ret = -ESRCH;
@@ -232,15 +257,50 @@ static int binder_install_single_page(struct binder_alloc *alloc,
 		goto out;
 	}
 
-	lru_page->page_ptr = page;
+	/* Mark page installation complete and safe to use */
+	binder_set_installed_page(lru_page, page);
 out:
 	mmap_write_unlock(alloc->mm);
 	mmput_async(alloc->mm);
 	return ret;
 }
 
-static int binder_allocate_page_range(struct binder_alloc *alloc,
-				      unsigned long start, unsigned long end)
+static int binder_install_buffer_pages(struct binder_alloc *alloc,
+				       struct binder_buffer *buffer,
+				       size_t size)
+{
+	struct binder_lru_page *page;
+	unsigned long start, final;
+	unsigned long page_addr;
+
+	start = buffer->user_data & PAGE_MASK;
+	final = PAGE_ALIGN(buffer->user_data + size);
+
+	for (page_addr = start; page_addr < final; page_addr += PAGE_SIZE) {
+		unsigned long index;
+		int ret;
+
+		index = (page_addr - alloc->buffer) / PAGE_SIZE;
+		page = &alloc->pages[index];
+
+		if (binder_get_installed_page(page))
+			continue;
+
+		trace_binder_alloc_page_start(alloc, index);
+
+		ret = binder_install_single_page(alloc, page, page_addr);
+		if (ret)
+			return ret;
+
+		trace_binder_alloc_page_end(alloc, index);
+	}
+
+	return 0;
+}
+
+/* The range of pages should exclude those shared with other buffers */
+static void binder_allocate_page_range(struct binder_alloc *alloc,
+				       unsigned long start, unsigned long end)
 {
 	struct binder_lru_page *page;
 	unsigned long page_addr;
@@ -249,15 +309,11 @@ static int binder_allocate_page_range(struct binder_alloc *alloc,
 			   "%d: allocate pages %lx-%lx\n",
 			   alloc->pid, start, end);
 
-	if (end <= start)
-		return 0;
-
 	trace_binder_update_page_range(alloc, true, start, end);
 
 	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
 		unsigned long index;
 		bool on_lru;
-		int ret;
 
 		index = (page_addr - alloc->buffer) / PAGE_SIZE;
 		page = &alloc->pages[index];
@@ -272,21 +328,9 @@ static int binder_allocate_page_range(struct binder_alloc *alloc,
 			continue;
 		}
 
-		trace_binder_alloc_page_start(alloc, index);
-
-		ret = binder_install_single_page(alloc, page, page_addr);
-		if (ret) {
-			binder_free_page_range(alloc, start, page_addr);
-			return ret;
-		}
-
 		if (index + 1 > alloc->pages_high)
 			alloc->pages_high = index + 1;
-
-		trace_binder_alloc_page_end(alloc, index);
 	}
-
-	return 0;
 }
 
 static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
@@ -405,7 +449,6 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	unsigned long has_page_addr;
 	unsigned long end_page_addr;
 	size_t buffer_size;
-	int ret;
 
 	if (is_async && alloc->free_async_space < size) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
@@ -449,18 +492,14 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		     "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
 		      alloc->pid, size, buffer, buffer_size);
 
-	has_page_addr = (buffer->user_data + buffer_size) & PAGE_MASK;
 	WARN_ON(n && buffer_size != size);
+
+	has_page_addr = (buffer->user_data + buffer_size) & PAGE_MASK;
 	end_page_addr = PAGE_ALIGN(buffer->user_data + size);
 	if (end_page_addr > has_page_addr)
 		end_page_addr = has_page_addr;
-	ret = binder_allocate_page_range(alloc, PAGE_ALIGN(buffer->user_data),
-					 end_page_addr);
-	if (ret) {
-		buffer = ERR_PTR(ret);
-		goto out;
-	}
-
+	binder_allocate_page_range(alloc, PAGE_ALIGN(buffer->user_data),
+				   end_page_addr);
 	if (buffer_size != size) {
 		new_buffer->user_data = buffer->user_data + size;
 		list_add(&new_buffer->entry, &buffer->entry);
@@ -538,6 +577,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 {
 	struct binder_buffer *buffer, *next;
 	size_t size;
+	int ret;
 
 	/* Check binder_alloc is fully initialized */
 	if (!binder_alloc_get_vma(alloc)) {
@@ -574,6 +614,11 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	buffer->pid = current->tgid;
 	mutex_unlock(&alloc->mutex);
 
+	ret = binder_install_buffer_pages(alloc, buffer, size);
+	if (ret) {
+		binder_alloc_free_buf(alloc, buffer);
+		buffer = ERR_PTR(ret);
+	}
 out:
 	return buffer;
 }
-- 
GitLab


From 258ce20ede33c551002705fa1488864fb287752c Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:49 +0000
Subject: [PATCH 0753/4076] binder: remove redundant debug log

The debug information in this statement is already logged earlier in the
same function. We can get rid of this duplicate log.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-21-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 551f08e844089..c9292eee8fee0 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -512,9 +512,6 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	buffer->free = 0;
 	buffer->allow_user_free = 0;
 	binder_insert_allocated_buffer_locked(alloc, buffer);
-	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: binder_alloc_buf size %zd got %pK\n",
-		      alloc->pid, size, buffer);
 	buffer->async_transaction = is_async;
 	buffer->oneway_spam_suspect = false;
 	if (is_async) {
-- 
GitLab


From de0e6573125f8ea7a01a9b05a45b0c73116c73b2 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:50 +0000
Subject: [PATCH 0754/4076] binder: make oversized buffer code more readable

The sections in binder_alloc_new_buf_locked() dealing with oversized
buffers are scattered which makes them difficult to read. Instead,
consolidate this code into a single block to improve readability.

No functional change here.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-22-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index c9292eee8fee0..ad9b73c6ddb70 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -483,32 +483,31 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		goto out;
 	}
 
-	if (n == NULL) {
+	if (buffer_size != size) {
+		/* Found an oversized buffer and needs to be split */
 		buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
 		buffer_size = binder_alloc_buffer_size(alloc, buffer);
+
+		WARN_ON(n || buffer_size == size);
+		new_buffer->user_data = buffer->user_data + size;
+		list_add(&new_buffer->entry, &buffer->entry);
+		new_buffer->free = 1;
+		binder_insert_free_buffer(alloc, new_buffer);
+		new_buffer = NULL;
 	}
 
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 		     "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
 		      alloc->pid, size, buffer, buffer_size);
 
-	WARN_ON(n && buffer_size != size);
-
 	has_page_addr = (buffer->user_data + buffer_size) & PAGE_MASK;
 	end_page_addr = PAGE_ALIGN(buffer->user_data + size);
 	if (end_page_addr > has_page_addr)
 		end_page_addr = has_page_addr;
 	binder_allocate_page_range(alloc, PAGE_ALIGN(buffer->user_data),
 				   end_page_addr);
-	if (buffer_size != size) {
-		new_buffer->user_data = buffer->user_data + size;
-		list_add(&new_buffer->entry, &buffer->entry);
-		new_buffer->free = 1;
-		binder_insert_free_buffer(alloc, new_buffer);
-		new_buffer = NULL;
-	}
 
-	rb_erase(best_fit, &alloc->free_buffers);
+	rb_erase(&buffer->rb_node, &alloc->free_buffers);
 	buffer->free = 0;
 	buffer->allow_user_free = 0;
 	binder_insert_allocated_buffer_locked(alloc, buffer);
-- 
GitLab


From ea9cdbf0c7273b55e251b2ed8f85794cfadab5d5 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:51 +0000
Subject: [PATCH 0755/4076] binder: rename lru shrinker utilities

Now that the page allocation step is done separately we should rename
the binder_free_page_range() and binder_allocate_page_range() functions
to provide a more accurate description of what they do. Lets borrow the
freelist concept used in other parts of the kernel for this.

No functional change here.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-23-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c          | 40 ++++++++++++-------------
 drivers/android/binder_alloc.h          |  4 +--
 drivers/android/binder_alloc_selftest.c |  6 ++--
 3 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index ad9b73c6ddb70..052a8c3b0ce1a 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -26,7 +26,7 @@
 #include "binder_alloc.h"
 #include "binder_trace.h"
 
-struct list_lru binder_alloc_lru;
+struct list_lru binder_freelist;
 
 static DEFINE_MUTEX(binder_alloc_mmap_lock);
 
@@ -190,8 +190,8 @@ binder_get_installed_page(struct binder_lru_page *lru_page)
 	return smp_load_acquire(&lru_page->page_ptr);
 }
 
-static void binder_free_page_range(struct binder_alloc *alloc,
-				   unsigned long start, unsigned long end)
+static void binder_lru_freelist_add(struct binder_alloc *alloc,
+				    unsigned long start, unsigned long end)
 {
 	struct binder_lru_page *page;
 	unsigned long page_addr;
@@ -210,7 +210,7 @@ static void binder_free_page_range(struct binder_alloc *alloc,
 
 		trace_binder_free_lru_start(alloc, index);
 
-		ret = list_lru_add(&binder_alloc_lru, &page->lru);
+		ret = list_lru_add(&binder_freelist, &page->lru);
 		WARN_ON(!ret);
 
 		trace_binder_free_lru_end(alloc, index);
@@ -299,14 +299,14 @@ static int binder_install_buffer_pages(struct binder_alloc *alloc,
 }
 
 /* The range of pages should exclude those shared with other buffers */
-static void binder_allocate_page_range(struct binder_alloc *alloc,
-				       unsigned long start, unsigned long end)
+static void binder_lru_freelist_del(struct binder_alloc *alloc,
+				    unsigned long start, unsigned long end)
 {
 	struct binder_lru_page *page;
 	unsigned long page_addr;
 
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-			   "%d: allocate pages %lx-%lx\n",
+			   "%d: pages %lx-%lx\n",
 			   alloc->pid, start, end);
 
 	trace_binder_update_page_range(alloc, true, start, end);
@@ -321,7 +321,7 @@ static void binder_allocate_page_range(struct binder_alloc *alloc,
 		if (page->page_ptr) {
 			trace_binder_alloc_lru_start(alloc, index);
 
-			on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
+			on_lru = list_lru_del(&binder_freelist, &page->lru);
 			WARN_ON(!on_lru);
 
 			trace_binder_alloc_lru_end(alloc, index);
@@ -504,8 +504,8 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	end_page_addr = PAGE_ALIGN(buffer->user_data + size);
 	if (end_page_addr > has_page_addr)
 		end_page_addr = has_page_addr;
-	binder_allocate_page_range(alloc, PAGE_ALIGN(buffer->user_data),
-				   end_page_addr);
+	binder_lru_freelist_del(alloc, PAGE_ALIGN(buffer->user_data),
+				end_page_addr);
 
 	rb_erase(&buffer->rb_node, &alloc->free_buffers);
 	buffer->free = 0;
@@ -671,8 +671,8 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc,
 				   alloc->pid, buffer->user_data,
 				   prev->user_data,
 				   next ? next->user_data : 0);
-		binder_free_page_range(alloc, buffer_start_page(buffer),
-				       buffer_start_page(buffer) + PAGE_SIZE);
+		binder_lru_freelist_add(alloc, buffer_start_page(buffer),
+					buffer_start_page(buffer) + PAGE_SIZE);
 	}
 	list_del(&buffer->entry);
 	kfree(buffer);
@@ -706,8 +706,8 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 			      alloc->pid, size, alloc->free_async_space);
 	}
 
-	binder_free_page_range(alloc, PAGE_ALIGN(buffer->user_data),
-			       (buffer->user_data + buffer_size) & PAGE_MASK);
+	binder_lru_freelist_add(alloc, PAGE_ALIGN(buffer->user_data),
+				(buffer->user_data + buffer_size) & PAGE_MASK);
 
 	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
 	buffer->free = 1;
@@ -953,7 +953,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 			if (!alloc->pages[i].page_ptr)
 				continue;
 
-			on_lru = list_lru_del(&binder_alloc_lru,
+			on_lru = list_lru_del(&binder_freelist,
 					      &alloc->pages[i].lru);
 			page_addr = alloc->buffer + i * PAGE_SIZE;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
@@ -1152,13 +1152,13 @@ err_get_alloc_mutex_failed:
 static unsigned long
 binder_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
-	return list_lru_count(&binder_alloc_lru);
+	return list_lru_count(&binder_freelist);
 }
 
 static unsigned long
 binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
-	return list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+	return list_lru_walk(&binder_freelist, binder_alloc_free_page,
 			    NULL, sc->nr_to_scan);
 }
 
@@ -1184,13 +1184,13 @@ int binder_alloc_shrinker_init(void)
 {
 	int ret;
 
-	ret = list_lru_init(&binder_alloc_lru);
+	ret = list_lru_init(&binder_freelist);
 	if (ret)
 		return ret;
 
 	binder_shrinker = shrinker_alloc(0, "android-binder");
 	if (!binder_shrinker) {
-		list_lru_destroy(&binder_alloc_lru);
+		list_lru_destroy(&binder_freelist);
 		return -ENOMEM;
 	}
 
@@ -1205,7 +1205,7 @@ int binder_alloc_shrinker_init(void)
 void binder_alloc_shrinker_exit(void)
 {
 	shrinker_free(binder_shrinker);
-	list_lru_destroy(&binder_alloc_lru);
+	list_lru_destroy(&binder_freelist);
 }
 
 /**
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index bbc16bc6d5ac9..a5181916942e7 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -15,7 +15,7 @@
 #include <linux/list_lru.h>
 #include <uapi/linux/android/binder.h>
 
-extern struct list_lru binder_alloc_lru;
+extern struct list_lru binder_freelist;
 struct binder_transaction;
 
 /**
@@ -61,7 +61,7 @@ struct binder_buffer {
 /**
  * struct binder_lru_page - page object used for binder shrinker
  * @page_ptr: pointer to physical page in mmap'd space
- * @lru:      entry in binder_alloc_lru
+ * @lru:      entry in binder_freelist
  * @alloc:    binder_alloc for a proc
  */
 struct binder_lru_page {
diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
index ed753747e54ce..fba7ab6ca451f 100644
--- a/drivers/android/binder_alloc_selftest.c
+++ b/drivers/android/binder_alloc_selftest.c
@@ -158,8 +158,8 @@ static void binder_selftest_free_page(struct binder_alloc *alloc)
 	int i;
 	unsigned long count;
 
-	while ((count = list_lru_count(&binder_alloc_lru))) {
-		list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+	while ((count = list_lru_count(&binder_freelist))) {
+		list_lru_walk(&binder_freelist, binder_alloc_free_page,
 			      NULL, count);
 	}
 
@@ -183,7 +183,7 @@ static void binder_selftest_alloc_free(struct binder_alloc *alloc,
 
 	/* Allocate from lru. */
 	binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
-	if (list_lru_count(&binder_alloc_lru))
+	if (list_lru_count(&binder_freelist))
 		pr_err("lru list should be empty but is not\n");
 
 	binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
-- 
GitLab


From 67dcc880780569ec40391cae4d8299adc1e7a44e Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:52 +0000
Subject: [PATCH 0756/4076] binder: document the final page calculation

The code to determine the page range for binder_lru_freelist_del() is
quite obscure. It leverages the buffer_size calculated before doing an
oversized buffer split. This is used to figure out if the last page is
being shared with another active buffer. If so, the page gets trimmed
out of the range as it has been previously removed from the freelist.

This would be equivalent to getting the start page of the next in-use
buffer explicitly. However, the code for this is much larger as we can
see in binder_free_buf_locked() routine. Instead, lets settle on
documenting the tricky step and using better names for now.

I believe an ideal solution would be to count the binder_page->users to
determine when a page should be added or removed from the freelist.
However, this is a much bigger change than what I'm willing to risk at
this time.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-24-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 052a8c3b0ce1a..edd9714ec9f56 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -446,8 +446,8 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	struct rb_node *n = alloc->free_buffers.rb_node;
 	struct rb_node *best_fit = NULL;
 	struct binder_buffer *buffer;
-	unsigned long has_page_addr;
-	unsigned long end_page_addr;
+	unsigned long next_used_page;
+	unsigned long curr_last_page;
 	size_t buffer_size;
 
 	if (is_async && alloc->free_async_space < size) {
@@ -500,12 +500,16 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 		     "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
 		      alloc->pid, size, buffer, buffer_size);
 
-	has_page_addr = (buffer->user_data + buffer_size) & PAGE_MASK;
-	end_page_addr = PAGE_ALIGN(buffer->user_data + size);
-	if (end_page_addr > has_page_addr)
-		end_page_addr = has_page_addr;
+	/*
+	 * Now we remove the pages from the freelist. A clever calculation
+	 * with buffer_size determines if the last page is shared with an
+	 * adjacent in-use buffer. In such case, the page has been already
+	 * removed from the freelist so we trim our range short.
+	 */
+	next_used_page = (buffer->user_data + buffer_size) & PAGE_MASK;
+	curr_last_page = PAGE_ALIGN(buffer->user_data + size);
 	binder_lru_freelist_del(alloc, PAGE_ALIGN(buffer->user_data),
-				end_page_addr);
+				min(next_used_page, curr_last_page));
 
 	rb_erase(&buffer->rb_node, &alloc->free_buffers);
 	buffer->free = 0;
-- 
GitLab


From 8e905217c4543af9cf1754809846157a7dbbb261 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:53 +0000
Subject: [PATCH 0757/4076] binder: collapse print_binder_buffer() into caller

The code in print_binder_buffer() is quite small so it can be collapsed
into its single caller binder_alloc_print_allocated().

No functional change in this patch.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-25-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index edd9714ec9f56..60c829506d310 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -978,16 +978,6 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		     __func__, alloc->pid, buffers, page_count);
 }
 
-static void print_binder_buffer(struct seq_file *m, const char *prefix,
-				struct binder_buffer *buffer)
-{
-	seq_printf(m, "%s %d: %lx size %zd:%zd:%zd %s\n",
-		   prefix, buffer->debug_id, buffer->user_data,
-		   buffer->data_size, buffer->offsets_size,
-		   buffer->extra_buffers_size,
-		   buffer->transaction ? "active" : "delivered");
-}
-
 /**
  * binder_alloc_print_allocated() - print buffer info
  * @m:     seq_file for output via seq_printf()
@@ -999,12 +989,18 @@ static void print_binder_buffer(struct seq_file *m, const char *prefix,
 void binder_alloc_print_allocated(struct seq_file *m,
 				  struct binder_alloc *alloc)
 {
+	struct binder_buffer *buffer;
 	struct rb_node *n;
 
 	mutex_lock(&alloc->mutex);
-	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
-		print_binder_buffer(m, "  buffer",
-				    rb_entry(n, struct binder_buffer, rb_node));
+	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		seq_printf(m, "  buffer %d: %lx size %zd:%zd:%zd %s\n",
+			   buffer->debug_id, buffer->user_data,
+			   buffer->data_size, buffer->offsets_size,
+			   buffer->extra_buffers_size,
+			   buffer->transaction ? "active" : "delivered");
+	}
 	mutex_unlock(&alloc->mutex);
 }
 
-- 
GitLab


From f07b83a48e944c8a1cc1e9f6703fae5e34df2ba4 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:54 +0000
Subject: [PATCH 0758/4076] binder: refactor binder_delete_free_buffer()

Skip the freelist call immediately as needed, instead of continuing the
pointless checks. Also, drop the debug logs that we don't really need.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-26-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 44 +++++++++-------------------------
 1 file changed, 11 insertions(+), 33 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 60c829506d310..c3fc909668677 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -636,48 +636,26 @@ static unsigned long prev_buffer_end_page(struct binder_buffer *buffer)
 static void binder_delete_free_buffer(struct binder_alloc *alloc,
 				      struct binder_buffer *buffer)
 {
-	struct binder_buffer *prev, *next = NULL;
-	bool to_free = true;
+	struct binder_buffer *prev, *next;
+
+	if (PAGE_ALIGNED(buffer->user_data))
+		goto skip_freelist;
 
 	BUG_ON(alloc->buffers.next == &buffer->entry);
 	prev = binder_buffer_prev(buffer);
 	BUG_ON(!prev->free);
-	if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
-		to_free = false;
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer %lx share page with %lx\n",
-				   alloc->pid, buffer->user_data,
-				   prev->user_data);
-	}
+	if (prev_buffer_end_page(prev) == buffer_start_page(buffer))
+		goto skip_freelist;
 
 	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
 		next = binder_buffer_next(buffer);
-		if (buffer_start_page(next) == buffer_start_page(buffer)) {
-			to_free = false;
-			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-					   "%d: merge free, buffer %lx share page with %lx\n",
-					   alloc->pid,
-					   buffer->user_data,
-					   next->user_data);
-		}
+		if (buffer_start_page(next) == buffer_start_page(buffer))
+			goto skip_freelist;
 	}
 
-	if (PAGE_ALIGNED(buffer->user_data)) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer start %lx is page aligned\n",
-				   alloc->pid, buffer->user_data);
-		to_free = false;
-	}
-
-	if (to_free) {
-		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				   "%d: merge free, buffer %lx do not share page with %lx or %lx\n",
-				   alloc->pid, buffer->user_data,
-				   prev->user_data,
-				   next ? next->user_data : 0);
-		binder_lru_freelist_add(alloc, buffer_start_page(buffer),
-					buffer_start_page(buffer) + PAGE_SIZE);
-	}
+	binder_lru_freelist_add(alloc, buffer_start_page(buffer),
+				buffer_start_page(buffer) + PAGE_SIZE);
+skip_freelist:
 	list_del(&buffer->entry);
 	kfree(buffer);
 }
-- 
GitLab


From 162c79731448a5a052e93af7753df579dfe0bf7a Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:55 +0000
Subject: [PATCH 0759/4076] binder: avoid user addresses in debug logs

Prefer logging vma offsets instead of addresses or simply drop the debug
log altogether if not useful. Note this covers the instances affected by
the switch to store addresses as unsigned long. However, there are other
sections in the driver that could do the same.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-27-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder.c       |  4 ++--
 drivers/android/binder_alloc.c | 15 ++++++---------
 2 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 45674af6310fe..c4bb18305e77b 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -5980,9 +5980,9 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
 	}
 	if (buffer->target_node)
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
-	seq_printf(m, " size %zd:%zd data %lx\n",
+	seq_printf(m, " size %zd:%zd offset %lx\n",
 		   buffer->data_size, buffer->offsets_size,
-		   buffer->user_data);
+		   proc->alloc.buffer - buffer->user_data);
 }
 
 static void print_binder_work_ilocked(struct seq_file *m,
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index c3fc909668677..5783675f29708 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -250,8 +250,8 @@ static int binder_install_single_page(struct binder_alloc *alloc,
 
 	ret = vm_insert_page(alloc->vma, addr, page);
 	if (ret) {
-		pr_err("%d: %s failed to insert page at %lx with %d\n",
-		       alloc->pid, __func__, addr, ret);
+		pr_err("%d: %s failed to insert page at offset %lx with %d\n",
+		       alloc->pid, __func__, addr - alloc->buffer, ret);
 		__free_page(page);
 		ret = -ENOMEM;
 		goto out;
@@ -305,10 +305,6 @@ static void binder_lru_freelist_del(struct binder_alloc *alloc,
 	struct binder_lru_page *page;
 	unsigned long page_addr;
 
-	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-			   "%d: pages %lx-%lx\n",
-			   alloc->pid, start, end);
-
 	trace_binder_update_page_range(alloc, true, start, end);
 
 	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
@@ -939,8 +935,8 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 					      &alloc->pages[i].lru);
 			page_addr = alloc->buffer + i * PAGE_SIZE;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				     "%s: %d: page %d at %lx %s\n",
-				     __func__, alloc->pid, i, page_addr,
+				     "%s: %d: page %d %s\n",
+				     __func__, alloc->pid, i,
 				     on_lru ? "on lru" : "active");
 			__free_page(alloc->pages[i].page_ptr);
 			page_count++;
@@ -974,7 +970,8 @@ void binder_alloc_print_allocated(struct seq_file *m,
 	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		seq_printf(m, "  buffer %d: %lx size %zd:%zd:%zd %s\n",
-			   buffer->debug_id, buffer->user_data,
+			   buffer->debug_id,
+			   buffer->user_data - alloc->buffer,
 			   buffer->data_size, buffer->offsets_size,
 			   buffer->extra_buffers_size,
 			   buffer->transaction ? "active" : "delivered");
-- 
GitLab


From e50f4e6cc9bfaca655d3b6a3506d27cf2caa1d40 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:56 +0000
Subject: [PATCH 0760/4076] binder: reverse locking order in shrinker callback

The locking order currently requires the alloc->mutex to be acquired
first followed by the mmap lock. However, the alloc->mutex is converted
into a spinlock in subsequent commits so the order needs to be reversed
to avoid nesting the sleeping mmap lock under the spinlock.

The shrinker's callback binder_alloc_free_page() is the only place that
needs to be reordered since other functions have been refactored and no
longer nest these locks.

Some minor cosmetic changes are also included in this patch.

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-28-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 46 ++++++++++++++++------------------
 1 file changed, 22 insertions(+), 24 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 5783675f29708..a3e56637db4f6 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -1061,35 +1061,39 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 				       void *cb_arg)
 	__must_hold(lock)
 {
-	struct mm_struct *mm = NULL;
-	struct binder_lru_page *page = container_of(item,
-						    struct binder_lru_page,
-						    lru);
-	struct binder_alloc *alloc;
+	struct binder_lru_page *page = container_of(item, typeof(*page), lru);
+	struct binder_alloc *alloc = page->alloc;
+	struct mm_struct *mm = alloc->mm;
+	struct vm_area_struct *vma;
+	struct page *page_to_free;
 	unsigned long page_addr;
 	size_t index;
-	struct vm_area_struct *vma;
 
-	alloc = page->alloc;
+	if (!mmget_not_zero(mm))
+		goto err_mmget;
+	if (!mmap_read_trylock(mm))
+		goto err_mmap_read_lock_failed;
 	if (!mutex_trylock(&alloc->mutex))
 		goto err_get_alloc_mutex_failed;
-
 	if (!page->page_ptr)
 		goto err_page_already_freed;
 
 	index = page - alloc->pages;
 	page_addr = alloc->buffer + index * PAGE_SIZE;
 
-	mm = alloc->mm;
-	if (!mmget_not_zero(mm))
-		goto err_mmget;
-	if (!mmap_read_trylock(mm))
-		goto err_mmap_read_lock_failed;
 	vma = vma_lookup(mm, page_addr);
 	if (vma && vma != binder_alloc_get_vma(alloc))
 		goto err_invalid_vma;
 
+	trace_binder_unmap_kernel_start(alloc, index);
+
+	page_to_free = page->page_ptr;
+	page->page_ptr = NULL;
+
+	trace_binder_unmap_kernel_end(alloc, index);
+
 	list_lru_isolate(lru, item);
+	mutex_unlock(&alloc->mutex);
 	spin_unlock(lock);
 
 	if (vma) {
@@ -1099,28 +1103,22 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 
 		trace_binder_unmap_user_end(alloc, index);
 	}
+
 	mmap_read_unlock(mm);
 	mmput_async(mm);
-
-	trace_binder_unmap_kernel_start(alloc, index);
-
-	__free_page(page->page_ptr);
-	page->page_ptr = NULL;
-
-	trace_binder_unmap_kernel_end(alloc, index);
+	__free_page(page_to_free);
 
 	spin_lock(lock);
-	mutex_unlock(&alloc->mutex);
 	return LRU_REMOVED_RETRY;
 
 err_invalid_vma:
+err_page_already_freed:
+	mutex_unlock(&alloc->mutex);
+err_get_alloc_mutex_failed:
 	mmap_read_unlock(mm);
 err_mmap_read_lock_failed:
 	mmput_async(mm);
 err_mmget:
-err_page_already_freed:
-	mutex_unlock(&alloc->mutex);
-err_get_alloc_mutex_failed:
 	return LRU_SKIP;
 }
 
-- 
GitLab


From 7710e2cca32e7f3958480e8bd44f50e29d0c2509 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 1 Dec 2023 17:21:57 +0000
Subject: [PATCH 0761/4076] binder: switch alloc->mutex to spinlock_t

The alloc->mutex is a highly contended lock that causes performance
issues on Android devices. When a low-priority task is given this lock
and it sleeps, it becomes difficult for the task to wake up and complete
its work. This delays other tasks that are also waiting on the mutex.

The problem gets worse when there is memory pressure in the system,
because this increases the contention on the alloc->mutex while the
shrinker reclaims binder pages.

Switching to a spinlock helps to keep the waiters running and avoids the
overhead of waking up tasks. This significantly improves the transaction
latency when the problematic scenario occurs.

The performance impact of this patchset was measured by stress-testing
the binder alloc contention. In this test, several clients of different
priorities send thousands of transactions of different sizes to a single
server. In parallel, pages get reclaimed using the shinker's debugfs.

The test was run on a Pixel 8, Pixel 6 and qemu machine. The results
were similar on all three devices:

after:
  | sched  | prio | average | max       | min     |
  |--------+------+---------+-----------+---------|
  | fifo   |   99 | 0.135ms |   1.197ms | 0.022ms |
  | fifo   |   01 | 0.136ms |   5.232ms | 0.018ms |
  | other  |  -20 | 0.180ms |   7.403ms | 0.019ms |
  | other  |   19 | 0.241ms |  58.094ms | 0.018ms |

before:
  | sched  | prio | average | max       | min     |
  |--------+------+---------+-----------+---------|
  | fifo   |   99 | 0.350ms | 248.730ms | 0.020ms |
  | fifo   |   01 | 0.357ms | 248.817ms | 0.024ms |
  | other  |  -20 | 0.399ms | 249.906ms | 0.020ms |
  | other  |   19 | 0.477ms | 297.756ms | 0.022ms |

The key metrics above are the average and max latencies (wall time).
These improvements should roughly translate to p95-p99 latencies on real
workloads. The response time is up to 200x faster in these scenarios and
there is no penalty in the regular path.

Note that it is only possible to convert this lock after a series of
changes made by previous patches. These mainly include refactoring the
sections that might_sleep() and changing the locking order with the
mmap_lock amongst others.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-29-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 46 +++++++++++++++++-----------------
 drivers/android/binder_alloc.h | 10 ++++----
 2 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index a3e56637db4f6..a4a4dc87ba53a 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -169,9 +169,9 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
 {
 	struct binder_buffer *buffer;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr);
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return buffer;
 }
 
@@ -597,10 +597,10 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	if (!next)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	buffer = binder_alloc_new_buf_locked(alloc, next, size, is_async);
 	if (IS_ERR(buffer)) {
-		mutex_unlock(&alloc->mutex);
+		spin_unlock(&alloc->lock);
 		goto out;
 	}
 
@@ -608,7 +608,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	buffer->offsets_size = offsets_size;
 	buffer->extra_buffers_size = extra_buffers_size;
 	buffer->pid = current->tgid;
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 
 	ret = binder_install_buffer_pages(alloc, buffer, size);
 	if (ret) {
@@ -785,17 +785,17 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 	 * We could eliminate the call to binder_alloc_clear_buf()
 	 * from binder_alloc_deferred_release() by moving this to
 	 * binder_free_buf_locked(). However, that could
-	 * increase contention for the alloc mutex if clear_on_free
-	 * is used frequently for large buffers. The mutex is not
+	 * increase contention for the alloc->lock if clear_on_free
+	 * is used frequently for large buffers. This lock is not
 	 * needed for correctness here.
 	 */
 	if (buffer->clear_on_free) {
 		binder_alloc_clear_buf(alloc, buffer);
 		buffer->clear_on_free = false;
 	}
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	binder_free_buf_locked(alloc, buffer);
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 }
 
 /**
@@ -893,7 +893,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 	struct binder_buffer *buffer;
 
 	buffers = 0;
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	BUG_ON(alloc->vma);
 
 	while ((n = rb_first(&alloc->allocated_buffers))) {
@@ -943,7 +943,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		}
 		kfree(alloc->pages);
 	}
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	if (alloc->mm)
 		mmdrop(alloc->mm);
 
@@ -966,7 +966,7 @@ void binder_alloc_print_allocated(struct seq_file *m,
 	struct binder_buffer *buffer;
 	struct rb_node *n;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		seq_printf(m, "  buffer %d: %lx size %zd:%zd:%zd %s\n",
@@ -976,7 +976,7 @@ void binder_alloc_print_allocated(struct seq_file *m,
 			   buffer->extra_buffers_size,
 			   buffer->transaction ? "active" : "delivered");
 	}
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 }
 
 /**
@@ -993,7 +993,7 @@ void binder_alloc_print_pages(struct seq_file *m,
 	int lru = 0;
 	int free = 0;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	/*
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
@@ -1009,7 +1009,7 @@ void binder_alloc_print_pages(struct seq_file *m,
 				lru++;
 		}
 	}
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
 	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
 }
@@ -1025,10 +1025,10 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
 	struct rb_node *n;
 	int count = 0;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
 		count++;
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return count;
 }
 
@@ -1073,8 +1073,8 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 		goto err_mmget;
 	if (!mmap_read_trylock(mm))
 		goto err_mmap_read_lock_failed;
-	if (!mutex_trylock(&alloc->mutex))
-		goto err_get_alloc_mutex_failed;
+	if (!spin_trylock(&alloc->lock))
+		goto err_get_alloc_lock_failed;
 	if (!page->page_ptr)
 		goto err_page_already_freed;
 
@@ -1093,7 +1093,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 	trace_binder_unmap_kernel_end(alloc, index);
 
 	list_lru_isolate(lru, item);
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	spin_unlock(lock);
 
 	if (vma) {
@@ -1113,8 +1113,8 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 
 err_invalid_vma:
 err_page_already_freed:
-	mutex_unlock(&alloc->mutex);
-err_get_alloc_mutex_failed:
+	spin_unlock(&alloc->lock);
+err_get_alloc_lock_failed:
 	mmap_read_unlock(mm);
 err_mmap_read_lock_failed:
 	mmput_async(mm);
@@ -1149,7 +1149,7 @@ void binder_alloc_init(struct binder_alloc *alloc)
 	alloc->pid = current->group_leader->pid;
 	alloc->mm = current->mm;
 	mmgrab(alloc->mm);
-	mutex_init(&alloc->mutex);
+	spin_lock_init(&alloc->lock);
 	INIT_LIST_HEAD(&alloc->buffers);
 }
 
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index a5181916942e7..70387234477e0 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -9,7 +9,7 @@
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <linux/mm.h>
-#include <linux/rtmutex.h>
+#include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/list_lru.h>
@@ -72,7 +72,7 @@ struct binder_lru_page {
 
 /**
  * struct binder_alloc - per-binder proc state for binder allocator
- * @mutex:              protects binder_alloc fields
+ * @lock:               protects binder_alloc fields
  * @vma:                vm_area_struct passed to mmap_handler
  *                      (invariant after mmap)
  * @mm:                 copy of task->mm (invariant after open)
@@ -96,7 +96,7 @@ struct binder_lru_page {
  * struct binder_buffer objects used to track the user buffers
  */
 struct binder_alloc {
-	struct mutex mutex;
+	spinlock_t lock;
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
 	unsigned long buffer;
@@ -153,9 +153,9 @@ binder_alloc_get_free_async_space(struct binder_alloc *alloc)
 {
 	size_t free_async_space;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	free_async_space = alloc->free_async_space;
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return free_async_space;
 }
 
-- 
GitLab


From d03a7005d9688bed5f20ab1b6ec9601455d98ef5 Mon Sep 17 00:00:00 2001
From: Lukas Funke <Lukas.Funke@weidmueller.com>
Date: Wed, 22 Nov 2023 09:07:48 +0100
Subject: [PATCH 0762/4076] extcon: usbc-tusb320: Set interrupt polarity based
 on device-tree

Remove 'IRQF_TRIGGER_FALLING' request which is not allowed on
every interrupt controller (i.e. arm64 GIC). Replace flag by a
request that depends on the actual device-tree setting.

Link: https://lore.kernel.org/all/02a701da2717$48abf150$da03d3f0$@samsung.com/
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311221355.yxYpTIw3-lkp@intel.com/
Signed-off-by: Lukas Funke <lukas.funke@weidmueller.com>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/extcon/extcon-usbc-tusb320.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/extcon/extcon-usbc-tusb320.c b/drivers/extcon/extcon-usbc-tusb320.c
index 4d08c2123e598..2eab341de6b76 100644
--- a/drivers/extcon/extcon-usbc-tusb320.c
+++ b/drivers/extcon/extcon-usbc-tusb320.c
@@ -17,6 +17,7 @@
 #include <linux/usb/typec.h>
 #include <linux/usb/typec_altmode.h>
 #include <linux/usb/role.h>
+#include <linux/irq.h>
 
 #define TUSB320_REG8				0x8
 #define TUSB320_REG8_CURRENT_MODE_ADVERTISE	GENMASK(7, 6)
@@ -515,6 +516,8 @@ static int tusb320_probe(struct i2c_client *client)
 	const void *match_data;
 	unsigned int revision;
 	int ret;
+	u32 irq_trigger_type = IRQF_TRIGGER_FALLING;
+	struct irq_data *irq_d;
 
 	priv = devm_kzalloc(&client->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -568,9 +571,13 @@ static int tusb320_probe(struct i2c_client *client)
 		 */
 		tusb320_state_update_handler(priv, true);
 
+	irq_d = irq_get_irq_data(client->irq);
+	if (irq_d)
+		irq_trigger_type = irqd_get_trigger_type(irq_d);
+
 	ret = devm_request_threaded_irq(priv->dev, client->irq, NULL,
 					tusb320_irq_handler,
-					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					IRQF_ONESHOT | irq_trigger_type,
 					client->name, priv);
 	if (ret)
 		tusb320_typec_remove(priv);
-- 
GitLab


From fd7c3c3767c38dbbf2f5c993c6fd42a71846e7e0 Mon Sep 17 00:00:00 2001
From: Mark-PK Tsai <mark-pk.tsai@mediatek.com>
Date: Thu, 19 Oct 2023 09:35:22 +0100
Subject: [PATCH 0763/4076] ARM: 9327/1: vfp: Add missing VFP instructions to
 neon_support_hook

Add the missing "Unconditional Advanced SIMD and floating-point
instructions" in [1] to the VFP undef hook.

This commit addresses the issue reported in [2], where
executing the vudot instruction on a platform with FEAT_DotProd
support resulted in an undefined instruction error.

Link: https://developer.arm.com/documentation/ddi0597/2023-06/?lang=en [1]
Link: https://lore.kernel.org/lkml/20230920083907.30479-1-mark-pk.tsai@mediatek.com/ [2]

Signed-off-by: Mark-PK Tsai <mark-pk.tsai@mediatek.com>
Tested-by: Xuewen Yan <xuewen.yan@unisoc.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
 arch/arm/vfp/vfpmodule.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 7e8773a2d99d0..b68efe643a12c 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -800,6 +800,24 @@ static struct undef_hook neon_support_hook[] = {{
 	.cpsr_mask	= PSR_T_BIT,
 	.cpsr_val	= PSR_T_BIT,
 	.fn		= vfp_support_entry,
+}, {
+	.instr_mask	= 0xff000800,
+	.instr_val	= 0xfc000800,
+	.cpsr_mask	= 0,
+	.cpsr_val	= 0,
+	.fn		= vfp_support_entry,
+}, {
+	.instr_mask	= 0xff000800,
+	.instr_val	= 0xfd000800,
+	.cpsr_mask	= 0,
+	.cpsr_val	= 0,
+	.fn		= vfp_support_entry,
+}, {
+	.instr_mask	= 0xff000800,
+	.instr_val	= 0xfe000800,
+	.cpsr_mask	= 0,
+	.cpsr_val	= 0,
+	.fn		= vfp_support_entry,
 }};
 
 static struct undef_hook vfp_support_hook = {
-- 
GitLab


From f54e8634d1366926c807e2af6125b33cff555fa7 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 7 Nov 2023 01:36:03 +0100
Subject: [PATCH 0764/4076] ARM: 9330/1: davinci: also select PINCTRL

kconfig warns when PINCTRL_SINGLE is selected but PINCTRL is not
set, so also set PINCTRL for ARCH_DAVINCI. This prevents a
kconfig/build warning:

   WARNING: unmet direct dependencies detected for PINCTRL_SINGLE
     Depends on [n]: PINCTRL [=n] && OF [=y] && HAS_IOMEM [=y]
     Selected by [y]:
     - ARCH_DAVINCI [=y] && ARCH_MULTI_V5 [=y]

Closes: lore.kernel.org/r/202311070548.0f6XfBrh-lkp@intel.com

Fixes: f962396ce292 ("ARM: davinci: support multiplatform build for ARM v5")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: patches@armlinux.org.uk
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
 arch/arm/mach-davinci/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index 4316e1370627c..1c8bf56982e56 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -10,6 +10,7 @@ menuconfig ARCH_DAVINCI
 	select PM_GENERIC_DOMAINS_OF if PM && OF
 	select REGMAP_MMIO
 	select RESET_CONTROLLER
+	select PINCTRL
 	select PINCTRL_SINGLE
 
 if ARCH_DAVINCI
-- 
GitLab


From c16af1212479570454752671a170a1756e11fdfb Mon Sep 17 00:00:00 2001
From: Wang Kefeng <wangkefeng.wang@huawei.com>
Date: Thu, 19 Oct 2023 12:21:35 +0100
Subject: [PATCH 0765/4076] ARM: 9328/1: mm: try VMA lock-based page fault
 handling first

Attempt VMA lock-based page fault handling first, and fall back to the
existing mmap_lock-based handling if that fails, the ebizzy benchmark
shows 25% improvement on qemu with 2 cpus.

Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
 arch/arm/Kconfig    |  1 +
 arch/arm/mm/fault.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index f8567e95f98be..8f47d6762ea4b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -35,6 +35,7 @@ config ARM
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_HUGETLBFS if ARM_LPAE
+	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_MEMTEST
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index fef62e4a9edde..e96fb40b9cc32 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -278,6 +278,35 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, addr);
+	if (!vma)
+		goto lock_mmap;
+
+	if (!(vma->vm_flags & vm_flags)) {
+		vma_end_read(vma);
+		goto lock_mmap;
+	}
+	fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
+
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
+	}
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto no_context;
+		return 0;
+	}
+lock_mmap:
+
 retry:
 	vma = lock_mm_and_find_vma(mm, addr, regs);
 	if (unlikely(!vma)) {
@@ -316,6 +345,7 @@ retry:
 	}
 
 	mmap_read_unlock(mm);
+done:
 
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR
-- 
GitLab


From 89320c9785e8429155f8dfa44a183b509866e852 Mon Sep 17 00:00:00 2001
From: Mark-PK Tsai <mark-pk.tsai@mediatek.com>
Date: Thu, 19 Oct 2023 14:38:16 +0100
Subject: [PATCH 0766/4076] ARM: 9329/1: kasan: Use memblock_alloc_try_nid_raw
 for shadow page

kasan_pte_populate fill KASAN_SHADOW_INIT in the newly
allocated shadow page, so it's unnecessary to
use memblock_alloc_try_nid, which always zero the
new allocated memory.

Use memblock_alloc_try_nid_raw instead of
memblock_alloc_try_nid like arm64 does which
can make kasan init faster.

Signed-off-by: Mark-PK Tsai <mark-pk.tsai@mediatek.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
 arch/arm/mm/kasan_init.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c
index 24d71b5db62de..111d4f703136e 100644
--- a/arch/arm/mm/kasan_init.c
+++ b/arch/arm/mm/kasan_init.c
@@ -28,6 +28,12 @@ static pgd_t tmp_pgd_table[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
 
 pmd_t tmp_pmd_table[PTRS_PER_PMD] __page_aligned_bss;
 
+static __init void *kasan_alloc_block_raw(size_t size)
+{
+	return memblock_alloc_try_nid_raw(size, size, __pa(MAX_DMA_ADDRESS),
+				      MEMBLOCK_ALLOC_NOLEAKTRACE, NUMA_NO_NODE);
+}
+
 static __init void *kasan_alloc_block(size_t size)
 {
 	return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS),
@@ -50,7 +56,7 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 			if (!pte_none(READ_ONCE(*ptep)))
 				continue;
 
-			p = kasan_alloc_block(PAGE_SIZE);
+			p = kasan_alloc_block_raw(PAGE_SIZE);
 			if (!p) {
 				panic("%s failed to allocate shadow page for address 0x%lx\n",
 				      __func__, addr);
-- 
GitLab


From 070909e56a7d65fd0b4aad6e808966b7c634befe Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:35 -0600
Subject: [PATCH 0767/4076] x86/pci: Reserve ECAM if BIOS didn't include it in
 PNP0C02 _CRS

Tomasz, Sebastian, and some Proxmox users reported problems initializing
ixgbe NICs.

I think the problem is that ECAM space described in the ACPI MCFG table is
not reserved via a PNP0C02 _CRS method as required by the PCI Firmware spec
(r3.3, sec 4.1.2), but it *is* included in the PNP0A03 host bridge _CRS as
part of the MMIO aperture.

If we allocate space for a PCI BAR, we're likely to allocate it from that
ECAM space, which obviously cannot work.

This could happen for any device, but in the ixgbe case it happens because
it's an SR-IOV device and the BIOS didn't allocate space for the VF BARs,
so Linux reallocated the bridge window leading to ixgbe and put it on top
of the ECAM space.  From Tomasz' system:

  PCI: MMCONFIG for domain 0000 [bus 00-ff] at [mem 0x80000000-0x8fffffff] (base 0x80000000)
  PCI: MMCONFIG at [mem 0x80000000-0x8fffffff] not reserved in ACPI motherboard resources
  pci_bus 0000:00: root bus resource [mem 0x80000000-0xfbffffff window]

  pci 0000:00:01.1: PCI bridge to [bus 02-03]
  pci 0000:00:01.1:   bridge window [mem 0xfb900000-0xfbbfffff]
  pci 0000:02:00.0: [8086:10fb] type 00 class 0x020000  # ixgbe
  pci 0000:02:00.0: reg 0x10: [mem 0xfba80000-0xfbafffff 64bit]
  pci 0000:02:00.0: VF(n) BAR0 space: [mem 0x00000000-0x000fffff 64bit] (contains BAR0 for 64 VFs)
  pci 0000:02:00.0: BAR 7: no space for [mem size 0x00100000 64bit]   # VF BAR 0

  pci_bus 0000:00: No. 2 try to assign unassigned res
  pci 0000:00:01.1: resource 14 [mem 0xfb900000-0xfbbfffff] released
  pci 0000:00:01.1: BAR 14: assigned [mem 0x80000000-0x806fffff]
  pci 0000:02:00.0: BAR 0: assigned [mem 0x80000000-0x8007ffff 64bit]
  pci 0000:02:00.0: BAR 7: assigned [mem 0x80204000-0x80303fff 64bit] # VF BAR 0

Fixes: 07eab0901ede ("efi/x86: Remove EfiMemoryMappedIO from E820 map")
Fixes: fd3a8cff4d4a ("x86/pci: Treat EfiMemoryMappedIO as reservation of ECAM space")
Reported-by: Tomasz Pala <gotar@polanet.pl>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218050
Reported-by: Sebastian Manciulea <manciuleas@protonmail.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218107
Link: https://forum.proxmox.com/threads/proxmox-8-kernel-6-2-16-4-pve-ixgbe-driver-fails-to-load-due-to-pci-device-probing-failure.131203/
Link: https://lore.kernel.org/r/20231121183643.249006-2-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org	# v6.2+
---
 arch/x86/pci/mmconfig-shared.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 4b3efaa82ab7c..e9497ee0f8547 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -525,6 +525,8 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 static bool __ref
 pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
 {
+	struct resource *conflict;
+
 	if (!early && !acpi_disabled) {
 		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
 				       "ACPI motherboard resource"))
@@ -542,8 +544,17 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
 			       &cfg->res);
 
 		if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
-				       "EfiMemoryMappedIO"))
+				       "EfiMemoryMappedIO")) {
+			conflict = insert_resource_conflict(&iomem_resource,
+							    &cfg->res);
+			if (conflict)
+				pr_warn("MMCONFIG %pR conflicts with %s %pR\n",
+					&cfg->res, conflict->name, conflict);
+			else
+				pr_info("MMCONFIG %pR reserved to work around lack of ACPI motherboard _CRS\n",
+					&cfg->res);
 			return true;
+		}
 	}
 
 	/*
-- 
GitLab


From e1fad9dd25ea36ae3655c5f4d505d57ab6d4bcc3 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:36 -0600
Subject: [PATCH 0768/4076] x86/pci: Reword ECAM EfiMemoryMappedIO logging to
 avoid 'reserved'

fd3a8cff4d4a ("x86/pci: Treat EfiMemoryMappedIO as reservation of ECAM
space") added the concept of using the EFI memory map to help decide
whether ECAM space mentioned in the MCFG table is valid.

Unfortunately it described that EfiMemoryMappedIO space as "reserved", but
it is actually not *reserved* by the EFI memory map.  EfiMemoryMappedIO
only means the firmware requested that the OS map this space for use by
firmware runtime services.

Change the dmesg logging to describe it as simply "EfiMemoryMappedIO", not
as "reserved as EfiMemoryMappedIO".  A previous commit actually *does*
reserve the space if ACPI PNP0C01/02 devices haven't done so:

  - PCI: ECAM at [mem 0xe0000000-0xefffffff] reserved as EfiMemoryMappedIO
  + PCI: ECAM at [mem 0xe0000000-0xefffffff] is EfiMemoryMappedIO; assuming valid
    PCI: ECAM [mem 0xe0000000-0xefffffff] reserved to work around lack of ACPI motherboard _CRS

Link: https://lore.kernel.org/r/20231121183643.249006-3-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/mmconfig-shared.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index e9497ee0f8547..64c39a23d37af 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -443,9 +443,11 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used)
 	return mcfg_res.flags;
 }
 
-static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+static bool is_efi_mmio(struct resource *res)
 {
 #ifdef CONFIG_EFI
+	u64 start = res->start;
+	u64 end = res->start + resource_size(res);
 	efi_memory_desc_t *md;
 	u64 size, mmio_start, mmio_end;
 
@@ -455,11 +457,6 @@ static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
 			mmio_start = md->phys_addr;
 			mmio_end = mmio_start + size;
 
-			/*
-			 * N.B. Caller supplies (start, start + size),
-			 * so to match, mmio_end is the first address
-			 * *past* the EFI_MEMORY_MAPPED_IO area.
-			 */
 			if (mmio_start <= start && end <= mmio_end)
 				return true;
 		}
@@ -543,8 +540,9 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
 			       "ACPI motherboard resources\n",
 			       &cfg->res);
 
-		if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
-				       "EfiMemoryMappedIO")) {
+		if (is_efi_mmio(&cfg->res)) {
+			pr_info("ECAM %pR is EfiMemoryMappedIO; assuming valid\n",
+				&cfg->res);
 			conflict = insert_resource_conflict(&iomem_resource,
 							    &cfg->res);
 			if (conflict)
-- 
GitLab


From 286ae88c9e40b261d7860b367c36346434ffeaa3 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:37 -0600
Subject: [PATCH 0769/4076] x86/pci: Add MCFG debug logging

MCFG handling is a frequent source of problems.  Add more logging to aid in
debugging.

Enable the logging with CONFIG_DYNAMIC_DEBUG=y and the kernel boot
parameter 'dyndbg="file arch/x86/pci +p"'.

Link: https://lore.kernel.org/r/20231121183643.249006-4-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/acpi.c            |  3 +++
 arch/x86/pci/mmconfig-shared.c | 23 ++++++++++++++++++-----
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index ea2eb2ec90e2b..55c4b07ec1f63 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -283,6 +283,9 @@ static int setup_mcfg_map(struct acpi_pci_root_info *ci)
 	info->mcfg_added = false;
 	seg = info->sd.domain;
 
+	dev_dbg(dev, "%s(%04x %pR ECAM %pa)\n", __func__, seg,
+		&root->secondary, &root->mcfg_addr);
+
 	/* return success if MMCFG is not in use */
 	if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg)
 		return 0;
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 64c39a23d37af..bc1312d920da4 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -579,7 +579,8 @@ static void __init pci_mmcfg_reject_broken(int early)
 
 	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
 		if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) {
-			pr_info(PREFIX "not using MMCONFIG\n");
+			pr_info(PREFIX "not using MMCONFIG (%pR not reserved)\n",
+				&cfg->res);
 			free_all_mmcfg();
 			return;
 		}
@@ -676,6 +677,8 @@ static int pci_mmcfg_for_each_region(int (*func)(__u64 start, __u64 size,
 
 static void __init __pci_mmcfg_init(int early)
 {
+	pr_debug(PREFIX "%s(%s)\n", __func__, early ? "early" : "late");
+
 	pci_mmcfg_reject_broken(early);
 	if (list_empty(&pci_mmcfg_list))
 		return;
@@ -702,6 +705,8 @@ static int __initdata known_bridge;
 
 void __init pci_mmcfg_early_init(void)
 {
+	pr_debug(PREFIX "%s() pci_probe %#x\n", __func__, pci_probe);
+
 	if (pci_probe & PCI_PROBE_MMCONF) {
 		if (pci_mmcfg_check_hostbridge())
 			known_bridge = 1;
@@ -715,6 +720,8 @@ void __init pci_mmcfg_early_init(void)
 
 void __init pci_mmcfg_late_init(void)
 {
+	pr_debug(PREFIX "%s() pci_probe %#x\n", __func__, pci_probe);
+
 	/* MMCONFIG disabled */
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return;
@@ -735,6 +742,8 @@ static int __init pci_mmcfg_late_insert_resources(void)
 
 	pci_mmcfg_running_state = true;
 
+	pr_debug(PREFIX "%s() pci_probe %#x\n", __func__, pci_probe);
+
 	/* If we are not using MMCONFIG, don't insert the resources. */
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return 1;
@@ -744,9 +753,12 @@ static int __init pci_mmcfg_late_insert_resources(void)
 	 * marked so it won't cause request errors when __request_region is
 	 * called.
 	 */
-	list_for_each_entry(cfg, &pci_mmcfg_list, list)
-		if (!cfg->res.parent)
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+		if (!cfg->res.parent) {
+			pr_debug(PREFIX "%s() insert %pR\n", __func__, &cfg->res);
 			insert_resource(&iomem_resource, &cfg->res);
+		}
+	}
 
 	return 0;
 }
@@ -766,6 +778,8 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	struct resource *tmp = NULL;
 	struct pci_mmcfg_region *cfg;
 
+	dev_dbg(dev, "%s(%04x [bus %02x-%02x])\n", __func__, seg, start, end);
+
 	if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed)
 		return -ENODEV;
 
@@ -810,8 +824,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 				 "%s %pR\n",
 				 &cfg->res, tmp->name, tmp);
 		} else if (pci_mmcfg_arch_map(cfg)) {
-			dev_warn(dev, "fail to map MMCONFIG %pR.\n",
-				 &cfg->res);
+			dev_warn(dev, "fail to map MMCONFIG %pR\n", &cfg->res);
 		} else {
 			list_add_sorted(cfg);
 			dev_info(dev, "MMCONFIG at %pR (base %#lx)\n",
-- 
GitLab


From 704891033b9714f4c9813bf9ffd888fc69ae3948 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:38 -0600
Subject: [PATCH 0770/4076] x86/pci: Rename 'MMCONFIG' to 'ECAM', use pr_fmt

The "MMCONFIG" term is not used in PCI/PCIe specs.  Replace it with "ECAM",
the term used in PCIe r6.0, sec 7.2.2.

Define pr_fmt() instead of repeating PREFIX in every log message.

Link: https://lore.kernel.org/r/20231121183643.249006-5-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/mmconfig-shared.c | 111 ++++++++++++++-------------------
 arch/x86/pci/mmconfig_32.c     |   2 +-
 arch/x86/pci/mmconfig_64.c     |   6 +-
 3 files changed, 52 insertions(+), 67 deletions(-)

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index bc1312d920da4..896cc11013bd6 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * mmconfig-shared.c - Low-level direct PCI config space access via
- *                     MMCONFIG - common code between i386 and x86-64.
+ * Low-level direct PCI config space access via ECAM - common code between
+ * i386 and x86-64.
  *
  * This code does:
  * - known chipset handling
@@ -11,6 +11,8 @@
  * themselves.
  */
 
+#define pr_fmt(fmt) "PCI: " fmt
+
 #include <linux/acpi.h>
 #include <linux/efi.h>
 #include <linux/pci.h>
@@ -24,9 +26,7 @@
 #include <asm/pci_x86.h>
 #include <asm/acpi.h>
 
-#define PREFIX "PCI: "
-
-/* Indicate if the mmcfg resources have been placed into the resource table. */
+/* Indicate if the ECAM resources have been placed into the resource table */
 static bool pci_mmcfg_running_state;
 static bool pci_mmcfg_arch_init_failed;
 static DEFINE_MUTEX(pci_mmcfg_lock);
@@ -90,7 +90,7 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start,
 	res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1;
 	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	snprintf(new->name, PCI_MMCFG_RESOURCE_NAME_LEN,
-		 "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end);
+		 "PCI ECAM %04x [bus %02x-%02x]", segment, start, end);
 	res->name = new->name;
 
 	return new;
@@ -107,10 +107,8 @@ struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
 		list_add_sorted(new);
 		mutex_unlock(&pci_mmcfg_lock);
 
-		pr_info(PREFIX
-		       "MMCONFIG for domain %04x [bus %02x-%02x] at %pR "
-		       "(base %#lx)\n",
-		       segment, start, end, &new->res, (unsigned long)addr);
+		pr_info("ECAM %pR (base %#lx) for domain %04x [bus %02x-%02x]\n",
+			&new->res, (unsigned long)addr, segment, start, end);
 	}
 
 	return new;
@@ -205,7 +203,7 @@ static const char *__init pci_mmcfg_amd_fam10h(void)
 	msr <<= 32;
 	msr |= low;
 
-	/* mmconfig is not enable */
+	/* ECAM is not enabled */
 	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
 		return NULL;
 
@@ -367,7 +365,7 @@ static int __init pci_mmcfg_check_hostbridge(void)
 			name = pci_mmcfg_probes[i].probe();
 
 		if (name)
-			pr_info(PREFIX "%s with MMCONFIG support\n", name);
+			pr_info("%s with ECAM support\n", name);
 	}
 
 	/* some end_bus_number is crazy, fix it */
@@ -487,11 +485,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 		return false;
 
 	if (dev)
-		dev_info(dev, "MMCONFIG at %pR reserved as %s\n",
+		dev_info(dev, "ECAM %pR reserved as %s\n",
 			 &cfg->res, method);
 	else
-		pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n",
-		       &cfg->res, method);
+		pr_info("ECAM %pR reserved as %s\n", &cfg->res, method);
 
 	if (old_size != size) {
 		/* update end_bus */
@@ -500,20 +497,16 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 		cfg->res.end = cfg->res.start +
 		    PCI_MMCFG_BUS_OFFSET(num_buses) - 1;
 		snprintf(cfg->name, PCI_MMCFG_RESOURCE_NAME_LEN,
-			 "PCI MMCONFIG %04x [bus %02x-%02x]",
+			 "PCI ECAM %04x [bus %02x-%02x]",
 			 cfg->segment, cfg->start_bus, cfg->end_bus);
 
 		if (dev)
-			dev_info(dev,
-				"MMCONFIG "
-				"at %pR (base %#lx) (size reduced!)\n",
-				&cfg->res, (unsigned long) cfg->address);
+			dev_info(dev, "ECAM %pR (base %#lx) (size reduced!)\n",
+				 &cfg->res, (unsigned long) cfg->address);
 		else
-			pr_info(PREFIX
-				"MMCONFIG for %04x [bus%02x-%02x] "
-				"at %pR (base %#lx) (size reduced!)\n",
-				cfg->segment, cfg->start_bus, cfg->end_bus,
-				&cfg->res, (unsigned long) cfg->address);
+			pr_info("ECAM %pR (base %#lx) for %04x [bus%02x-%02x] (size reduced!)\n",
+				&cfg->res, (unsigned long) cfg->address,
+				cfg->segment, cfg->start_bus, cfg->end_bus);
 	}
 
 	return true;
@@ -530,15 +523,11 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
 			return true;
 
 		if (dev)
-			dev_info(dev, FW_INFO
-				 "MMCONFIG at %pR not reserved in "
-				 "ACPI motherboard resources\n",
+			dev_info(dev, FW_INFO "ECAM %pR not reserved in ACPI motherboard resources\n",
 				 &cfg->res);
 		else
-			pr_info(FW_INFO PREFIX
-			       "MMCONFIG at %pR not reserved in "
-			       "ACPI motherboard resources\n",
-			       &cfg->res);
+			pr_info(FW_INFO "ECAM %pR not reserved in ACPI motherboard resources\n",
+			        &cfg->res);
 
 		if (is_efi_mmio(&cfg->res)) {
 			pr_info("ECAM %pR is EfiMemoryMappedIO; assuming valid\n",
@@ -546,10 +535,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
 			conflict = insert_resource_conflict(&iomem_resource,
 							    &cfg->res);
 			if (conflict)
-				pr_warn("MMCONFIG %pR conflicts with %s %pR\n",
+				pr_warn("ECAM %pR conflicts with %s %pR\n",
 					&cfg->res, conflict->name, conflict);
 			else
-				pr_info("MMCONFIG %pR reserved to work around lack of ACPI motherboard _CRS\n",
+				pr_info("ECAM %pR reserved to work around lack of ACPI motherboard _CRS\n",
 					&cfg->res);
 			return true;
 		}
@@ -579,7 +568,7 @@ static void __init pci_mmcfg_reject_broken(int early)
 
 	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
 		if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) {
-			pr_info(PREFIX "not using MMCONFIG (%pR not reserved)\n",
+			pr_info("not using ECAM (%pR not reserved)\n",
 				&cfg->res);
 			free_all_mmcfg();
 			return;
@@ -599,9 +588,9 @@ static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
 	if ((mcfg->header.revision >= 1) && (dmi_get_bios_year() >= 2010))
 		return 0;
 
-	pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx "
-	       "is above 4GB, ignored\n", cfg->pci_segment,
-	       cfg->start_bus_number, cfg->end_bus_number, cfg->address);
+	pr_err("ECAM at %#llx for %04x [bus %02x-%02x] is above 4GB, ignored\n",
+	       cfg->address, cfg->pci_segment, cfg->start_bus_number,
+	       cfg->end_bus_number);
 	return -EINVAL;
 }
 
@@ -626,7 +615,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
 		i -= sizeof(struct acpi_mcfg_allocation);
 	}
 	if (entries == 0) {
-		pr_err(PREFIX "MMCONFIG has no entries\n");
+		pr_err("MCFG has no entries\n");
 		return -ENODEV;
 	}
 
@@ -640,7 +629,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
 
 		if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number,
 				   cfg->end_bus_number, cfg->address) == NULL) {
-			pr_warn(PREFIX "no memory for MCFG entries\n");
+			pr_warn("no memory for MCFG entries\n");
 			free_all_mmcfg();
 			return -ENOMEM;
 		}
@@ -677,7 +666,7 @@ static int pci_mmcfg_for_each_region(int (*func)(__u64 start, __u64 size,
 
 static void __init __pci_mmcfg_init(int early)
 {
-	pr_debug(PREFIX "%s(%s)\n", __func__, early ? "early" : "late");
+	pr_debug("%s(%s)\n", __func__, early ? "early" : "late");
 
 	pci_mmcfg_reject_broken(early);
 	if (list_empty(&pci_mmcfg_list))
@@ -705,7 +694,7 @@ static int __initdata known_bridge;
 
 void __init pci_mmcfg_early_init(void)
 {
-	pr_debug(PREFIX "%s() pci_probe %#x\n", __func__, pci_probe);
+	pr_debug("%s() pci_probe %#x\n", __func__, pci_probe);
 
 	if (pci_probe & PCI_PROBE_MMCONF) {
 		if (pci_mmcfg_check_hostbridge())
@@ -720,16 +709,16 @@ void __init pci_mmcfg_early_init(void)
 
 void __init pci_mmcfg_late_init(void)
 {
-	pr_debug(PREFIX "%s() pci_probe %#x\n", __func__, pci_probe);
+	pr_debug("%s() pci_probe %#x\n", __func__, pci_probe);
 
-	/* MMCONFIG disabled */
+	/* ECAM disabled */
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return;
 
 	if (known_bridge)
 		return;
 
-	/* MMCONFIG hasn't been enabled yet, try again */
+	/* ECAM hasn't been enabled yet, try again */
 	if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) {
 		acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
 		__pci_mmcfg_init(0);
@@ -742,9 +731,9 @@ static int __init pci_mmcfg_late_insert_resources(void)
 
 	pci_mmcfg_running_state = true;
 
-	pr_debug(PREFIX "%s() pci_probe %#x\n", __func__, pci_probe);
+	pr_debug("%s() pci_probe %#x\n", __func__, pci_probe);
 
-	/* If we are not using MMCONFIG, don't insert the resources. */
+	/* If we are not using ECAM, don't insert the resources. */
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return 1;
 
@@ -755,7 +744,7 @@ static int __init pci_mmcfg_late_insert_resources(void)
 	 */
 	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
 		if (!cfg->res.parent) {
-			pr_debug(PREFIX "%s() insert %pR\n", __func__, &cfg->res);
+			pr_debug("%s() insert %pR\n", __func__, &cfg->res);
 			insert_resource(&iomem_resource, &cfg->res);
 		}
 	}
@@ -764,13 +753,13 @@ static int __init pci_mmcfg_late_insert_resources(void)
 }
 
 /*
- * Perform MMCONFIG resource insertion after PCI initialization to allow for
+ * Perform ECAM resource insertion after PCI initialization to allow for
  * misprogrammed MCFG tables that state larger sizes but actually conflict
  * with other system resources.
  */
 late_initcall(pci_mmcfg_late_insert_resources);
 
-/* Add MMCFG information for host bridges */
+/* Add ECAM information for host bridges */
 int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 			phys_addr_t addr)
 {
@@ -790,11 +779,9 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	cfg = pci_mmconfig_lookup(seg, start);
 	if (cfg) {
 		if (cfg->end_bus < end)
-			dev_info(dev, FW_INFO
-				 "MMCONFIG for "
-				 "domain %04x [bus %02x-%02x] "
-				 "only partially covers this bridge\n",
-				  cfg->segment, cfg->start_bus, cfg->end_bus);
+			dev_info(dev, FW_INFO "ECAM %pR for domain %04x [bus %02x-%02x] only partially covers this bridge\n",
+				 &cfg->res, cfg->segment, cfg->start_bus,
+				 cfg->end_bus);
 		mutex_unlock(&pci_mmcfg_lock);
 		return -EEXIST;
 	}
@@ -807,10 +794,10 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	rc = -EBUSY;
 	cfg = pci_mmconfig_alloc(seg, start, end, addr);
 	if (cfg == NULL) {
-		dev_warn(dev, "fail to add MMCONFIG (out of memory)\n");
+		dev_warn(dev, "fail to add ECAM (out of memory)\n");
 		rc = -ENOMEM;
 	} else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) {
-		dev_warn(dev, FW_BUG "MMCONFIG %pR isn't reserved\n",
+		dev_warn(dev, FW_BUG "ECAM %pR isn't reserved\n",
 			 &cfg->res);
 	} else {
 		/* Insert resource if it's not in boot stage */
@@ -819,15 +806,13 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 						       &cfg->res);
 
 		if (tmp) {
-			dev_warn(dev,
-				 "MMCONFIG %pR conflicts with "
-				 "%s %pR\n",
+			dev_warn(dev, "ECAM %pR conflicts with %s %pR\n",
 				 &cfg->res, tmp->name, tmp);
 		} else if (pci_mmcfg_arch_map(cfg)) {
-			dev_warn(dev, "fail to map MMCONFIG %pR\n", &cfg->res);
+			dev_warn(dev, "fail to map ECAM %pR\n", &cfg->res);
 		} else {
 			list_add_sorted(cfg);
-			dev_info(dev, "MMCONFIG at %pR (base %#lx)\n",
+			dev_info(dev, "ECAM %pR (base %#lx)\n",
 				 &cfg->res, (unsigned long)addr);
 			cfg = NULL;
 			rc = 0;
@@ -845,7 +830,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	return rc;
 }
 
-/* Delete MMCFG information for host bridges */
+/* Delete ECAM information for host bridges */
 int pci_mmconfig_delete(u16 seg, u8 start, u8 end)
 {
 	struct pci_mmcfg_region *cfg;
diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c
index bfa7898753220..f9ef97c593cf1 100644
--- a/arch/x86/pci/mmconfig_32.c
+++ b/arch/x86/pci/mmconfig_32.c
@@ -131,7 +131,7 @@ const struct pci_raw_ops pci_mmcfg = {
 
 int __init pci_mmcfg_arch_init(void)
 {
-	printk(KERN_INFO "PCI: Using MMCONFIG for extended config space\n");
+	printk(KERN_INFO "PCI: Using ECAM for extended config space\n");
 	raw_pci_ext_ops = &pci_mmcfg;
 	return 1;
 }
diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
index 0c7b6e66c6448..dfdeac0a75719 100644
--- a/arch/x86/pci/mmconfig_64.c
+++ b/arch/x86/pci/mmconfig_64.c
@@ -6,6 +6,8 @@
  * space mapped. This allows lockless config space operation.
  */
 
+#define pr_fmt(fmt) "PCI: " fmt
+
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
@@ -14,8 +16,6 @@
 #include <asm/e820/api.h>
 #include <asm/pci_x86.h>
 
-#define PREFIX "PCI: "
-
 static char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
 {
 	struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
@@ -138,7 +138,7 @@ int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
 {
 	cfg->virt = mcfg_ioremap(cfg);
 	if (!cfg->virt) {
-		pr_err(PREFIX "can't map MMCONFIG at %pR\n", &cfg->res);
+		pr_err("can't map ECAM at %pR\n", &cfg->res);
 		return -ENOMEM;
 	}
 
-- 
GitLab


From 9ad67912d0d019791f0ed6bbf46374fce8a3656e Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:39 -0600
Subject: [PATCH 0771/4076] x86/pci: Rename acpi_mcfg_check_entry() to
 acpi_mcfg_valid_entry()

"acpi_mcfg_check_entry()" doesn't give a hint about what the return value
means.  Rename it to "acpi_mcfg_valid_entry()", convert the return value to
bool, and update the return values and callers to match so testing
"if (acpi_mcfg_valid_entry())" makes sense.

Link: https://lore.kernel.org/r/20231121183643.249006-6-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/mmconfig-shared.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 896cc11013bd6..91fd7921d2211 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -576,22 +576,22 @@ static void __init pci_mmcfg_reject_broken(int early)
 	}
 }
 
-static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
-					struct acpi_mcfg_allocation *cfg)
+static bool __init acpi_mcfg_valid_entry(struct acpi_table_mcfg *mcfg,
+					 struct acpi_mcfg_allocation *cfg)
 {
 	if (cfg->address < 0xFFFFFFFF)
-		return 0;
+		return true;
 
 	if (!strncmp(mcfg->header.oem_id, "SGI", 3))
-		return 0;
+		return true;
 
 	if ((mcfg->header.revision >= 1) && (dmi_get_bios_year() >= 2010))
-		return 0;
+		return true;
 
 	pr_err("ECAM at %#llx for %04x [bus %02x-%02x] is above 4GB, ignored\n",
 	       cfg->address, cfg->pci_segment, cfg->start_bus_number,
 	       cfg->end_bus_number);
-	return -EINVAL;
+	return false;
 }
 
 static int __init pci_parse_mcfg(struct acpi_table_header *header)
@@ -622,7 +622,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
 	cfg_table = (struct acpi_mcfg_allocation *) &mcfg[1];
 	for (i = 0; i < entries; i++) {
 		cfg = &cfg_table[i];
-		if (acpi_mcfg_check_entry(mcfg, cfg)) {
+		if (!acpi_mcfg_valid_entry(mcfg, cfg)) {
 			free_all_mmcfg();
 			return -ENODEV;
 		}
-- 
GitLab


From d26e7fc3d907db19f7e25126476cb416f0527592 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:40 -0600
Subject: [PATCH 0772/4076] x86/pci: Rename pci_mmcfg_check_reserved() to
 pci_mmcfg_reserved()

"pci_mmcfg_check_reserved()" doesn't give a hint about what the boolean
return value means.  Rename it to pci_mmcfg_reserved() so testing
"if (pci_mmcfg_reserved())" makes sense.

Update callers to treat the return value as boolean instead of comparing
with 0.

Link: https://lore.kernel.org/r/20231121183643.249006-7-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/mmconfig-shared.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 91fd7921d2211..b36c10e865058 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -512,8 +512,8 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 	return true;
 }
 
-static bool __ref
-pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
+static bool __ref pci_mmcfg_reserved(struct device *dev,
+				     struct pci_mmcfg_region *cfg, int early)
 {
 	struct resource *conflict;
 
@@ -567,7 +567,7 @@ static void __init pci_mmcfg_reject_broken(int early)
 	struct pci_mmcfg_region *cfg;
 
 	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
-		if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) {
+		if (!pci_mmcfg_reserved(NULL, cfg, early)) {
 			pr_info("not using ECAM (%pR not reserved)\n",
 				&cfg->res);
 			free_all_mmcfg();
@@ -796,7 +796,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	if (cfg == NULL) {
 		dev_warn(dev, "fail to add ECAM (out of memory)\n");
 		rc = -ENOMEM;
-	} else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) {
+	} else if (!pci_mmcfg_reserved(dev, cfg, 0)) {
 		dev_warn(dev, FW_BUG "ECAM %pR isn't reserved\n",
 			 &cfg->res);
 	} else {
-- 
GitLab


From f284dff47b6d00efe1f774d25e9d74874e78c600 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:41 -0600
Subject: [PATCH 0773/4076] x86/pci: Comment pci_mmconfig_insert() obscure MCFG
 dependency

In pci_mmconfig_insert(), there's no reference to "addr" between locking
pci_mmcfg_lock and testing "addr", so it *looks* like we should move the
test before the lock.

But 07f9b61c3915 ("x86/PCI: MMCONFIG: Check earlier for MMCONFIG region at
address zero") did that, which broke things by returning -EINVAL when
"addr" is zero instead of -EEXIST.

So 07f9b61c3915 was reverted by 67d470e0e171 ("Revert "x86/PCI: MMCONFIG:
Check earlier for MMCONFIG region at address zero"").

Add a comment about this issue to prevent it from happening again.

Link: https://lore.kernel.org/r/20231121183643.249006-8-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/mmconfig-shared.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index b36c10e865058..459e95782bb15 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -786,6 +786,10 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 		return -EEXIST;
 	}
 
+	/*
+	 * Don't move earlier; we must return -EEXIST, not -EINVAL, if
+	 * pci_mmconfig_lookup() finds something
+	 */
 	if (!addr) {
 		mutex_unlock(&pci_mmcfg_lock);
 		return -EINVAL;
-- 
GitLab


From f12659832612dac746bd57e20956aabb373a00e7 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:42 -0600
Subject: [PATCH 0774/4076] x86/pci: Return pci_mmconfig_add() failure early

If pci_mmconfig_alloc() fails, return the failure early so it's obvious
that the failure is the exception, and the success is the normal case.  No
functional change intended.

Link: https://lore.kernel.org/r/20231121183643.249006-9-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/mmconfig-shared.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 459e95782bb15..0cc9520666efb 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -102,14 +102,15 @@ struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
 	struct pci_mmcfg_region *new;
 
 	new = pci_mmconfig_alloc(segment, start, end, addr);
-	if (new) {
-		mutex_lock(&pci_mmcfg_lock);
-		list_add_sorted(new);
-		mutex_unlock(&pci_mmcfg_lock);
+	if (!new)
+		return NULL;
 
-		pr_info("ECAM %pR (base %#lx) for domain %04x [bus %02x-%02x]\n",
-			&new->res, (unsigned long)addr, segment, start, end);
-	}
+	mutex_lock(&pci_mmcfg_lock);
+	list_add_sorted(new);
+	mutex_unlock(&pci_mmcfg_lock);
+
+	pr_info("ECAM %pR (base %#lx) for domain %04x [bus %02x-%02x]\n",
+		&new->res, (unsigned long)addr, segment, start, end);
 
 	return new;
 }
-- 
GitLab


From 1dfc86af06131d65be5b6ffb749c5dbceafb6d00 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 21 Nov 2023 12:36:43 -0600
Subject: [PATCH 0775/4076] x86/pci: Reorder pci_mmcfg_arch_map() definition
 before calls

The typical style is to define functions before calling them.  Move
pci_mmcfg_arch_map() and pci_mmcfg_arch_unmap() earlier so they're defined
before they're called.  No functional change intended.

Link: https://lore.kernel.org/r/20231121183643.249006-10-helgaas@kernel.org
Tested-by: Tomasz Pala <gotar@polanet.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/x86/pci/mmconfig_64.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
index dfdeac0a75719..cb5aa79a759e1 100644
--- a/arch/x86/pci/mmconfig_64.c
+++ b/arch/x86/pci/mmconfig_64.c
@@ -111,6 +111,25 @@ static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg)
 	return addr;
 }
 
+int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
+{
+	cfg->virt = mcfg_ioremap(cfg);
+	if (!cfg->virt) {
+		pr_err("can't map ECAM at %pR\n", &cfg->res);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg)
+{
+	if (cfg && cfg->virt) {
+		iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus));
+		cfg->virt = NULL;
+	}
+}
+
 int __init pci_mmcfg_arch_init(void)
 {
 	struct pci_mmcfg_region *cfg;
@@ -133,22 +152,3 @@ void __init pci_mmcfg_arch_free(void)
 	list_for_each_entry(cfg, &pci_mmcfg_list, list)
 		pci_mmcfg_arch_unmap(cfg);
 }
-
-int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
-{
-	cfg->virt = mcfg_ioremap(cfg);
-	if (!cfg->virt) {
-		pr_err("can't map ECAM at %pR\n", &cfg->res);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg)
-{
-	if (cfg && cfg->virt) {
-		iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus));
-		cfg->virt = NULL;
-	}
-}
-- 
GitLab


From 10a149e4b4a9187940adbfff0f216ccb5a15aa41 Mon Sep 17 00:00:00 2001
From: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Date: Thu, 30 Nov 2023 18:15:49 -0800
Subject: [PATCH 0776/4076] perf vendor events arm64 AmpereOne: Rename
 BPU_FLUSH_MEM_FAULT to GPC_FLUSH_MEM_FAULT

The documentation wrongly called the event as BPU_FLUSH_MEM_FAULT and now
has been fixed. Correct the name in the perf tool as well.

Fixes: a9650b7f6fc09d16 ("perf vendor events arm64: Add AmpereOne core PMU events")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20231201021550.1109196-3-ilkka@os.amperecomputing.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
index 88b23b85e33cd..879ff21e0b177 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json
@@ -110,7 +110,7 @@
     {
         "PublicDescription": "Flushes due to memory hazards",
         "EventCode": "0x121",
-        "EventName": "BPU_FLUSH_MEM_FAULT",
+        "EventName": "GPC_FLUSH_MEM_FAULT",
         "BriefDescription": "Flushes due to memory hazards"
     },
     {
-- 
GitLab


From 16438b652b464ef7d0a877d31e93ab54338f6b0a Mon Sep 17 00:00:00 2001
From: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Date: Thu, 30 Nov 2023 18:15:50 -0800
Subject: [PATCH 0777/4076] perf vendor events arm64 AmpereOneX: Add core PMU
 events and metrics

Add JSON files for AmpereOneX core PMU events and metrics.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20231201021550.1109196-4-ilkka@os.amperecomputing.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/arm64/ampere/ampereonex/branch.json  | 125 +++++
 .../arch/arm64/ampere/ampereonex/bus.json     |  20 +
 .../arch/arm64/ampere/ampereonex/cache.json   | 206 ++++++++
 .../arm64/ampere/ampereonex/core-imp-def.json | 464 ++++++++++++++++++
 .../arm64/ampere/ampereonex/exception.json    |  47 ++
 .../arm64/ampere/ampereonex/instruction.json  | 128 +++++
 .../arm64/ampere/ampereonex/intrinsic.json    |  14 +
 .../arch/arm64/ampere/ampereonex/memory.json  |  41 ++
 .../arch/arm64/ampere/ampereonex/metrics.json | 442 +++++++++++++++++
 .../arch/arm64/ampere/ampereonex/mmu.json     | 170 +++++++
 .../arm64/ampere/ampereonex/pipeline.json     |  41 ++
 .../arch/arm64/ampere/ampereonex/spe.json     |  14 +
 tools/perf/pmu-events/arch/arm64/mapfile.csv  |   1 +
 13 files changed, 1713 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json

diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json
new file mode 100644
index 0000000000000..a632755fc0869
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json
@@ -0,0 +1,125 @@
+[
+    {
+        "ArchStdEvent": "BR_IMMED_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_INDIRECT_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_MIS_PRED"
+    },
+    {
+        "ArchStdEvent": "BR_PRED"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, branch not taken",
+        "EventCode": "0x8107",
+        "EventName": "BR_SKIP_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, branch not taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, immediate branch taken",
+        "EventCode": "0x8108",
+        "EventName": "BR_IMMED_TAKEN_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, immediate branch taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, indirect branch excluding return retired",
+        "EventCode": "0x810c",
+        "EventName": "BR_INDNR_TAKEN_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, indirect branch excluding return retired"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted immediate branch",
+        "EventCode": "0x8110",
+        "EventName": "BR_IMMED_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted immediate branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted immediate branch",
+        "EventCode": "0x8111",
+        "EventName": "BR_IMMED_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted immediate branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted indirect branch",
+        "EventCode": "0x8112",
+        "EventName": "BR_IND_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted indirect branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted indirect branch",
+        "EventCode": "0x8113",
+        "EventName": "BR_IND_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted indirect branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted procedure return",
+        "EventCode": "0x8114",
+        "EventName": "BR_RETURN_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted procedure return"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted procedure return",
+        "EventCode": "0x8115",
+        "EventName": "BR_RETURN_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted procedure return"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted indirect branch excluding return",
+        "EventCode": "0x8116",
+        "EventName": "BR_INDNR_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted indirect branch excluding return"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted indirect branch excluding return",
+        "EventCode": "0x8117",
+        "EventName": "BR_INDNR_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted indirect branch excluding return"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted branch, taken",
+        "EventCode": "0x8118",
+        "EventName": "BR_TAKEN_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted branch, taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted branch, taken",
+        "EventCode": "0x8119",
+        "EventName": "BR_TAKEN_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted branch, taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted branch, not taken",
+        "EventCode": "0x811a",
+        "EventName": "BR_SKIP_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted branch, not taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted branch, not taken",
+        "EventCode": "0x811b",
+        "EventName": "BR_SKIP_MIS_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, mispredicted branch, not taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, predicted branch",
+        "EventCode": "0x811c",
+        "EventName": "BR_PRED_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, predicted branch"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, indirect branch",
+        "EventCode": "0x811d",
+        "EventName": "BR_IND_RETIRED",
+        "BriefDescription": "Instruction architecturally executed, indirect branch"
+    },
+    {
+        "PublicDescription": "Branch Record captured.",
+        "EventCode": "0x811f",
+        "EventName": "BRB_FILTRATE",
+        "BriefDescription": "Branch Record captured."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json
new file mode 100644
index 0000000000000..2aeb9907831d6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json
@@ -0,0 +1,20 @@
+[
+    {
+        "ArchStdEvent": "CPU_CYCLES"
+    },
+    {
+        "ArchStdEvent": "BUS_CYCLES"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_RD"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_WR"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS"
+    },
+    {
+        "ArchStdEvent": "CNT_CYCLES"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json
new file mode 100644
index 0000000000000..c50d8e930b05e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json
@@ -0,0 +1,206 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL"
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1I_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB"
+    },
+    {
+        "ArchStdEvent": "L1I_TLB"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L2I_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB"
+    },
+    {
+        "ArchStdEvent": "L2I_TLB"
+    },
+    {
+        "ArchStdEvent": "DTLB_WALK"
+    },
+    {
+        "ArchStdEvent": "ITLB_WALK"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_LMISS_RD"
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE_LMISS"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_LMISS_RD"
+    },
+    {
+        "PublicDescription": "Level 1 data or unified cache demand access",
+        "EventCode": "0x8140",
+        "EventName": "L1D_CACHE_RW",
+        "BriefDescription": "Level 1 data or unified cache demand access"
+    },
+    {
+        "PublicDescription": "Level 1 data or unified cache preload or prefetch",
+        "EventCode": "0x8142",
+        "EventName": "L1D_CACHE_PRFM",
+        "BriefDescription": "Level 1 data or unified cache preload or prefetch"
+    },
+    {
+        "PublicDescription": "Level 1 data or unified cache refill, preload or prefetch",
+        "EventCode": "0x8146",
+        "EventName": "L1D_CACHE_REFILL_PRFM",
+        "BriefDescription": "Level 1 data or unified cache refill, preload or prefetch"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR"
+    },
+    {
+        "PublicDescription": "L1D TLB miss",
+        "EventCode": "0xD600",
+        "EventName": "L1D_TLB_MISS",
+        "BriefDescription": "L1D TLB miss"
+    },
+    {
+        "PublicDescription": "Level 1 prefetcher, load prefetch requests generated",
+        "EventCode": "0xd606",
+        "EventName": "L1_PREFETCH_LD_GEN",
+        "BriefDescription": "Level 1 prefetcher, load prefetch requests generated"
+    },
+    {
+        "PublicDescription": "Level 1 prefetcher, load prefetch fills into the level 1 cache",
+        "EventCode": "0xd607",
+        "EventName": "L1_PREFETCH_LD_FILL",
+        "BriefDescription": "Level 1 prefetcher, load prefetch fills into the level 1 cache"
+    },
+    {
+        "PublicDescription": "Level 1 prefetcher, load prefetch to level 2 generated",
+        "EventCode": "0xd608",
+        "EventName": "L1_PREFETCH_L2_REQ",
+        "BriefDescription": "Level 1 prefetcher, load prefetch to level 2 generated"
+    },
+    {
+        "PublicDescription": "L1 prefetcher, distance was reset",
+        "EventCode": "0xd609",
+        "EventName": "L1_PREFETCH_DIST_RST",
+        "BriefDescription": "L1 prefetcher, distance was reset"
+    },
+    {
+        "PublicDescription": "L1 prefetcher, distance was increased",
+        "EventCode": "0xd60a",
+        "EventName": "L1_PREFETCH_DIST_INC",
+        "BriefDescription": "L1 prefetcher, distance was increased"
+    },
+    {
+        "PublicDescription": "Level 1 prefetcher, table entry is trained",
+        "EventCode": "0xd60b",
+        "EventName": "L1_PREFETCH_ENTRY_TRAINED",
+        "BriefDescription": "Level 1 prefetcher, table entry is trained"
+    },
+    {
+        "PublicDescription": "L1 data cache refill - Read or Write",
+        "EventCode": "0xd60e",
+        "EventName": "L1D_CACHE_REFILL_RW",
+        "BriefDescription": "L1 data cache refill - Read or Write"
+    },
+    {
+        "PublicDescription": "Level 2 cache refill from instruction-side miss, including IMMU refills",
+        "EventCode": "0xD701",
+        "EventName": "L2C_INST_REFILL",
+        "BriefDescription": "Level 2 cache refill from instruction-side miss, including IMMU refills"
+    },
+    {
+        "PublicDescription": "Level 2 cache refill from data-side miss, including DMMU refills",
+        "EventCode": "0xD702",
+        "EventName": "L2C_DATA_REFILL",
+        "BriefDescription": "Level 2 cache refill from data-side miss, including DMMU refills"
+    },
+    {
+        "PublicDescription": "Level 2 cache prefetcher, load prefetch requests generated",
+        "EventCode": "0xD703",
+        "EventName": "L2_PREFETCH_REQ",
+        "BriefDescription": "Level 2 cache prefetcher, load prefetch requests generated"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json
new file mode 100644
index 0000000000000..eb5a2208d2604
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json
@@ -0,0 +1,464 @@
+[
+    {
+        "PublicDescription": "Level 2 prefetch requests, refilled to L2 cache",
+        "EventCode": "0x10A",
+        "EventName": "L2_PREFETCH_REFILL",
+        "BriefDescription": "Level 2 prefetch requests, refilled to L2 cache"
+    },
+    {
+        "PublicDescription": "Level 2 prefetch requests, late",
+        "EventCode": "0x10B",
+        "EventName": "L2_PREFETCH_UPGRADE",
+        "BriefDescription": "Level 2 prefetch requests, late"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed that hit any level of BTB",
+        "EventCode": "0x110",
+        "EventName": "BPU_HIT_BTB",
+        "BriefDescription": "Predictable branch speculatively executed that hit any level of BTB"
+    },
+    {
+        "PublicDescription": "Predictable conditional branch speculatively executed that hit any level of BTB",
+        "EventCode": "0x111",
+        "EventName": "BPU_CONDITIONAL_BRANCH_HIT_BTB",
+        "BriefDescription": "Predictable conditional branch speculatively executed that hit any level of BTB"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor",
+        "EventCode": "0x112",
+        "EventName": "BPU_HIT_INDIRECT_PREDICTOR",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor",
+        "EventCode": "0x113",
+        "EventName": "BPU_HIT_RSB",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor"
+    },
+    {
+        "PublicDescription": "Predictable unconditional branch speculatively executed that did not hit any level of BTB",
+        "EventCode": "0x114",
+        "EventName": "BPU_UNCONDITIONAL_BRANCH_MISS_BTB",
+        "BriefDescription": "Predictable unconditional branch speculatively executed that did not hit any level of BTB"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed, unpredicted",
+        "EventCode": "0x115",
+        "EventName": "BPU_BRANCH_NO_HIT",
+        "BriefDescription": "Predictable branch speculatively executed, unpredicted"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed that hit any level of BTB that mispredict",
+        "EventCode": "0x116",
+        "EventName": "BPU_HIT_BTB_AND_MISPREDICT",
+        "BriefDescription": "Predictable branch speculatively executed that hit any level of BTB that mispredict"
+    },
+    {
+        "PublicDescription": "Predictable conditional branch speculatively executed that hit any level of BTB that (direction) mispredict",
+        "EventCode": "0x117",
+        "EventName": "BPU_CONDITIONAL_BRANCH_HIT_BTB_AND_MISPREDICT",
+        "BriefDescription": "Predictable conditional branch speculatively executed that hit any level of BTB that (direction) mispredict"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor that mispredict",
+        "EventCode": "0x118",
+        "EventName": "BPU_INDIRECT_BRANCH_HIT_BTB_AND_MISPREDICT",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor that mispredict"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor that mispredict",
+        "EventCode": "0x119",
+        "EventName": "BPU_HIT_RSB_AND_MISPREDICT",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor that mispredict"
+    },
+    {
+        "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the overflow/underflow return predictor that mispredict",
+        "EventCode": "0x11a",
+        "EventName": "BPU_MISS_RSB_AND_MISPREDICT",
+        "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the overflow/underflow return predictor that mispredict"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed, unpredicted, that mispredict",
+        "EventCode": "0x11b",
+        "EventName": "BPU_NO_PREDICTION_MISPREDICT",
+        "BriefDescription": "Predictable branch speculatively executed, unpredicted, that mispredict"
+    },
+    {
+        "PublicDescription": "Preditable branch update the BTB region buffer entry",
+        "EventCode": "0x11c",
+        "EventName": "BPU_BTB_UPDATE",
+        "BriefDescription": "Preditable branch update the BTB region buffer entry"
+    },
+    {
+        "PublicDescription": "Count predict pipe stalls due to speculative return address predictor full",
+        "EventCode": "0x11d",
+        "EventName": "BPU_RSB_FULL_STALL",
+        "BriefDescription": "Count predict pipe stalls due to speculative return address predictor full"
+    },
+    {
+        "PublicDescription": "Macro-ops speculatively decoded",
+        "EventCode": "0x11f",
+        "EventName": "ICF_INST_SPEC_DECODE",
+        "BriefDescription": "Macro-ops speculatively decoded"
+    },
+    {
+        "PublicDescription": "Flushes",
+        "EventCode": "0x120",
+        "EventName": "GPC_FLUSH",
+        "BriefDescription": "Flushes"
+    },
+    {
+        "PublicDescription": "Flushes due to memory hazards",
+        "EventCode": "0x121",
+        "EventName": "GPC_FLUSH_MEM_FAULT",
+        "BriefDescription": "Flushes due to memory hazards"
+    },
+    {
+        "PublicDescription": "ETM extout bit 0",
+        "EventCode": "0x141",
+        "EventName": "MSC_ETM_EXTOUT0",
+        "BriefDescription": "ETM extout bit 0"
+    },
+    {
+        "PublicDescription": "ETM extout bit 1",
+        "EventCode": "0x142",
+        "EventName": "MSC_ETM_EXTOUT1",
+        "BriefDescription": "ETM extout bit 1"
+    },
+    {
+        "PublicDescription": "ETM extout bit 2",
+        "EventCode": "0x143",
+        "EventName": "MSC_ETM_EXTOUT2",
+        "BriefDescription": "ETM extout bit 2"
+    },
+    {
+        "PublicDescription": "ETM extout bit 3",
+        "EventCode": "0x144",
+        "EventName": "MSC_ETM_EXTOUT3",
+        "BriefDescription": "ETM extout bit 3"
+    },
+    {
+        "PublicDescription": "Bus request sn",
+        "EventCode": "0x156",
+        "EventName": "L2C_SNOOP",
+        "BriefDescription": "Bus request sn"
+    },
+    {
+        "PublicDescription": "L2 TXDAT LCRD blocked",
+        "EventCode": "0x169",
+        "EventName": "L2C_DAT_CRD_STALL",
+        "BriefDescription": "L2 TXDAT LCRD blocked"
+    },
+    {
+        "PublicDescription": "L2 TXRSP LCRD blocked",
+        "EventCode": "0x16a",
+        "EventName": "L2C_RSP_CRD_STALL",
+        "BriefDescription": "L2 TXRSP LCRD blocked"
+    },
+    {
+        "PublicDescription": "L2 TXREQ LCRD blocked",
+        "EventCode": "0x16b",
+        "EventName": "L2C_REQ_CRD_STALL",
+        "BriefDescription": "L2 TXREQ LCRD blocked"
+    },
+    {
+        "PublicDescription": "Early mispredict",
+        "EventCode": "0xD100",
+        "EventName": "ICF_EARLY_MIS_PRED",
+        "BriefDescription": "Early mispredict"
+    },
+    {
+        "PublicDescription": "FEQ full cycles",
+        "EventCode": "0xD101",
+        "EventName": "ICF_FEQ_FULL",
+        "BriefDescription": "FEQ full cycles"
+    },
+    {
+        "PublicDescription": "Instruction FIFO Full",
+        "EventCode": "0xD102",
+        "EventName": "ICF_INST_FIFO_FULL",
+        "BriefDescription": "Instruction FIFO Full"
+    },
+    {
+        "PublicDescription": "L1I TLB miss",
+        "EventCode": "0xD103",
+        "EventName": "L1I_TLB_MISS",
+        "BriefDescription": "L1I TLB miss"
+    },
+    {
+        "PublicDescription": "ICF sent 0 instructions to IDR this cycle",
+        "EventCode": "0xD104",
+        "EventName": "ICF_STALL",
+        "BriefDescription": "ICF sent 0 instructions to IDR this cycle"
+    },
+    {
+        "PublicDescription": "PC FIFO Full",
+        "EventCode": "0xD105",
+        "EventName": "ICF_PC_FIFO_FULL",
+        "BriefDescription": "PC FIFO Full"
+    },
+    {
+        "PublicDescription": "Stall due to BOB ID",
+        "EventCode": "0xD200",
+        "EventName": "IDR_STALL_BOB_ID",
+        "BriefDescription": "Stall due to BOB ID"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to LOB entries",
+        "EventCode": "0xD201",
+        "EventName": "IDR_STALL_LOB_ID",
+        "BriefDescription": "Dispatch stall due to LOB entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to SOB entries",
+        "EventCode": "0xD202",
+        "EventName": "IDR_STALL_SOB_ID",
+        "BriefDescription": "Dispatch stall due to SOB entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to IXU scheduler entries",
+        "EventCode": "0xD203",
+        "EventName": "IDR_STALL_IXU_SCHED",
+        "BriefDescription": "Dispatch stall due to IXU scheduler entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to FSU scheduler entries",
+        "EventCode": "0xD204",
+        "EventName": "IDR_STALL_FSU_SCHED",
+        "BriefDescription": "Dispatch stall due to FSU scheduler entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to ROB entries",
+        "EventCode": "0xD205",
+        "EventName": "IDR_STALL_ROB_ID",
+        "BriefDescription": "Dispatch stall due to ROB entries"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to flush",
+        "EventCode": "0xD206",
+        "EventName": "IDR_STALL_FLUSH",
+        "BriefDescription": "Dispatch stall due to flush"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to WFI",
+        "EventCode": "0xD207",
+        "EventName": "IDR_STALL_WFI",
+        "BriefDescription": "Dispatch stall due to WFI"
+    },
+    {
+        "PublicDescription": "Number of SWOB drains triggered by timeout",
+        "EventCode": "0xD208",
+        "EventName": "IDR_STALL_SWOB_TIMEOUT",
+        "BriefDescription": "Number of SWOB drains triggered by timeout"
+    },
+    {
+        "PublicDescription": "Number of SWOB drains triggered by system register or special-purpose register read-after-write or specific special-purpose register writes that cause SWOB drain",
+        "EventCode": "0xD209",
+        "EventName": "IDR_STALL_SWOB_RAW",
+        "BriefDescription": "Number of SWOB drains triggered by system register or special-purpose register read-after-write or specific special-purpose register writes that cause SWOB drain"
+    },
+    {
+        "PublicDescription": "Number of SWOB drains triggered by system register write when SWOB full",
+        "EventCode": "0xD20A",
+        "EventName": "IDR_STALL_SWOB_FULL",
+        "BriefDescription": "Number of SWOB drains triggered by system register write when SWOB full"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to L1 instruction cache miss",
+        "EventCode": "0xD20B",
+        "EventName": "STALL_FRONTEND_CACHE",
+        "BriefDescription": "Dispatch stall due to L1 instruction cache miss"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to L1 data cache miss",
+        "EventCode": "0xD20D",
+        "EventName": "STALL_BACKEND_CACHE",
+        "BriefDescription": "Dispatch stall due to L1 data cache miss"
+    },
+    {
+        "PublicDescription": "Dispatch stall due to lack of any core resource",
+        "EventCode": "0xD20F",
+        "EventName": "STALL_BACKEND_RESOURCE",
+        "BriefDescription": "Dispatch stall due to lack of any core resource"
+    },
+    {
+        "PublicDescription": "Instructions issued by the scheduler",
+        "EventCode": "0xD300",
+        "EventName": "IXU_NUM_UOPS_ISSUED",
+        "BriefDescription": "Instructions issued by the scheduler"
+    },
+    {
+        "PublicDescription": "Any uop issued was canceled for any reason",
+        "EventCode": "0xD301",
+        "EventName": "IXU_ISSUE_CANCEL",
+        "BriefDescription": "Any uop issued was canceled for any reason"
+    },
+    {
+        "PublicDescription": "A load wakeup to the scheduler has been canceled",
+        "EventCode": "0xD302",
+        "EventName": "IXU_LOAD_CANCEL",
+        "BriefDescription": "A load wakeup to the scheduler has been canceled"
+    },
+    {
+        "PublicDescription": "The scheduler had to cancel one slow Uop due to resource conflict",
+        "EventCode": "0xD303",
+        "EventName": "IXU_SLOW_CANCEL",
+        "BriefDescription": "The scheduler had to cancel one slow Uop due to resource conflict"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXA",
+        "EventCode": "0xD304",
+        "EventName": "IXU_IXA_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXA"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXA Par 0",
+        "EventCode": "0xD305",
+        "EventName": "IXU_IXA_PAR0_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXA Par 0"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXA Par 1",
+        "EventCode": "0xD306",
+        "EventName": "IXU_IXA_PAR1_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXA Par 1"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXB",
+        "EventCode": "0xD307",
+        "EventName": "IXU_IXB_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXB"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXB Par 0",
+        "EventCode": "0xD308",
+        "EventName": "IXU_IXB_PAR0_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXB Par 0"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXB Par 1",
+        "EventCode": "0xD309",
+        "EventName": "IXU_IXB_PAR1_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXB Par 1"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXC",
+        "EventCode": "0xD30A",
+        "EventName": "IXU_IXC_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXC"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXC Par 0",
+        "EventCode": "0xD30B",
+        "EventName": "IXU_IXC_PAR0_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXC Par 0"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXC Par 1",
+        "EventCode": "0xD30C",
+        "EventName": "IXU_IXC_PAR1_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXC Par 1"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXD",
+        "EventCode": "0xD30D",
+        "EventName": "IXU_IXD_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXD"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXD Par 0",
+        "EventCode": "0xD30E",
+        "EventName": "IXU_IXD_PAR0_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXD Par 0"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on IXD Par 1",
+        "EventCode": "0xD30F",
+        "EventName": "IXU_IXD_PAR1_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on IXD Par 1"
+    },
+    {
+        "PublicDescription": "Uops issued by the FSU scheduler",
+        "EventCode": "0xD400",
+        "EventName": "FSU_ISSUED",
+        "BriefDescription": "Uops issued by the FSU scheduler"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on FSX",
+        "EventCode": "0xD401",
+        "EventName": "FSU_FSX_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on FSX"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on FSY",
+        "EventCode": "0xD402",
+        "EventName": "FSU_FSY_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on FSY"
+    },
+    {
+        "PublicDescription": "Uops issued by the scheduler on FSZ",
+        "EventCode": "0xD403",
+        "EventName": "FSU_FSZ_ISSUED",
+        "BriefDescription": "Uops issued by the scheduler on FSZ"
+    },
+    {
+        "PublicDescription": "Uops canceled (load cancels)",
+        "EventCode": "0xD404",
+        "EventName": "FSU_CANCEL",
+        "BriefDescription": "Uops canceled (load cancels)"
+    },
+    {
+        "PublicDescription": "Count scheduler stalls due to divide/sqrt",
+        "EventCode": "0xD405",
+        "EventName": "FSU_DIV_SQRT_STALL",
+        "BriefDescription": "Count scheduler stalls due to divide/sqrt"
+    },
+    {
+        "PublicDescription": "Number of SWOB drains",
+        "EventCode": "0xD500",
+        "EventName": "GPC_SWOB_DRAIN",
+        "BriefDescription": "Number of SWOB drains"
+    },
+    {
+        "PublicDescription": "GPC detected a Breakpoint instruction match",
+        "EventCode": "0xD501",
+        "EventName": "BREAKPOINT_MATCH",
+        "BriefDescription": "GPC detected a Breakpoint instruction match"
+    },
+    {
+        "PublicDescription": "Core progress monitor triggered",
+        "EventCode": "0xd502",
+        "EventName": "GPC_CPM_TRIGGER",
+        "BriefDescription": "Core progress monitor triggered"
+    },
+    {
+        "PublicDescription": "Fill buffer full",
+        "EventCode": "0xD601",
+        "EventName": "OFB_FULL",
+        "BriefDescription": "Fill buffer full"
+    },
+    {
+        "PublicDescription": "Load satisified from store forwarded data",
+        "EventCode": "0xD605",
+        "EventName": "LD_FROM_ST_FWD",
+        "BriefDescription": "Load satisified from store forwarded data"
+    },
+    {
+        "PublicDescription": "Store retirement pipe stall",
+        "EventCode": "0xD60C",
+        "EventName": "LSU_ST_RETIRE_STALL",
+        "BriefDescription": "Store retirement pipe stall"
+    },
+    {
+        "PublicDescription": "LSU detected a Watchpoint data match",
+        "EventCode": "0xD60D",
+        "EventName": "WATCHPOINT_MATCH",
+        "BriefDescription": "LSU detected a Watchpoint data match"
+    },
+    {
+        "PublicDescription": "Counts cycles that MSC is telling GPC to stall commit due to ETM ISTALL feature",
+        "EventCode": "0xda00",
+        "EventName": "MSC_ETM_COMMIT_STALL",
+        "BriefDescription": "Counts cycles that MSC is telling GPC to stall commit due to ETM ISTALL feature"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json
new file mode 100644
index 0000000000000..bd59ba7b74e42
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json
@@ -0,0 +1,47 @@
+[
+    {
+        "ArchStdEvent": "EXC_UNDEF"
+    },
+    {
+        "ArchStdEvent": "EXC_SVC"
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ"
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ"
+    },
+    {
+        "ArchStdEvent": "EXC_HVC"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ"
+    },
+    {
+        "ArchStdEvent": "EXC_TAKEN"
+    },
+    {
+        "ArchStdEvent": "EXC_RETURN"
+    },
+    {
+        "ArchStdEvent": "EXC_SMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json
new file mode 100644
index 0000000000000..a6a20f541e333
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json
@@ -0,0 +1,128 @@
+[
+    {
+        "ArchStdEvent": "SW_INCR"
+    },
+    {
+        "ArchStdEvent": "ST_RETIRED"
+    },
+    {
+        "ArchStdEvent": "LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "LDST_SPEC"
+    },
+    {
+        "ArchStdEvent": "DP_SPEC"
+    },
+    {
+        "ArchStdEvent": "ASE_SPEC"
+    },
+    {
+        "ArchStdEvent": "VFP_SPEC"
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_IMMED_RETIRED"
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_RETIRED"
+    },
+    {
+        "ArchStdEvent": "CRYPTO_SPEC"
+    },
+    {
+        "ArchStdEvent": "ISB_SPEC"
+    },
+    {
+        "ArchStdEvent": "DSB_SPEC"
+    },
+    {
+        "ArchStdEvent": "DMB_SPEC"
+    },
+    {
+        "ArchStdEvent": "RC_LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "RC_ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "INST_RETIRED"
+    },
+    {
+        "ArchStdEvent": "CID_WRITE_RETIRED"
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_RETIRED"
+    },
+    {
+        "ArchStdEvent": "INST_SPEC"
+    },
+    {
+        "ArchStdEvent": "TTBR_WRITE_RETIRED"
+    },
+    {
+        "ArchStdEvent": "BR_RETIRED"
+    },
+    {
+        "ArchStdEvent": "BR_MIS_PRED_RETIRED"
+    },
+    {
+        "ArchStdEvent": "OP_RETIRED"
+    },
+    {
+        "ArchStdEvent": "OP_SPEC"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed - ASE Scalar",
+        "EventCode": "0xd210",
+        "EventName": "ASE_SCALAR_SPEC",
+        "BriefDescription": "Operation speculatively executed - ASE Scalar"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed - ASE Vector",
+        "EventCode": "0xd211",
+        "EventName": "ASE_VECTOR_SPEC",
+        "BriefDescription": "Operation speculatively executed - ASE Vector"
+    },
+    {
+        "PublicDescription": "Barrier speculatively executed, CSDB",
+        "EventCode": "0x7f",
+        "EventName": "CSDB_SPEC",
+        "BriefDescription": "Barrier speculatively executed, CSDB"
+    },
+    {
+        "PublicDescription": "Prefetch sent to L2.",
+        "EventCode": "0xd106",
+        "EventName": "ICF_PREFETCH_DISPATCH",
+        "BriefDescription": "Prefetch sent to L2."
+    },
+    {
+        "PublicDescription": "Prefetch response received but was dropped since we don't support inflight upgrades.",
+        "EventCode": "0xd107",
+        "EventName": "ICF_PREFETCH_DROPPED_NO_UPGRADE",
+        "BriefDescription": "Prefetch response received but was dropped since we don't support inflight upgrades."
+    },
+    {
+        "PublicDescription": "Prefetch request missed TLB.",
+        "EventCode": "0xd108",
+        "EventName": "ICF_PREFETCH_DROPPED_TLB_MISS",
+        "BriefDescription": "Prefetch request missed TLB."
+    },
+    {
+        "PublicDescription": "Prefetch request dropped since duplicate was found in TLB.",
+        "EventCode": "0xd109",
+        "EventName": "ICF_PREFETCH_DROPPED_DUPLICATE",
+        "BriefDescription": "Prefetch request dropped since duplicate was found in TLB."
+    },
+    {
+        "PublicDescription": "Prefetch request dropped since it was found in cache.",
+        "EventCode": "0xd10a",
+        "EventName": "ICF_PREFETCH_DROPPED_CACHE_HIT",
+        "BriefDescription": "Prefetch request dropped since it was found in cache."
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json
new file mode 100644
index 0000000000000..7ecffb989ae04
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "LDREX_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_PASS_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_FAIL_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_SPEC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json
new file mode 100644
index 0000000000000..a211d94aacde6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json
@@ -0,0 +1,41 @@
+[
+    {
+        "ArchStdEvent": "LD_RETIRED"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR"
+    },
+    {
+        "ArchStdEvent": "LD_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "ST_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS"
+    },
+    {
+        "ArchStdEvent": "MEMORY_ERROR"
+    },
+    {
+        "ArchStdEvent": "LDST_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_RD"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_WR"
+    },
+    {
+        "PublicDescription": "Flushes due to memory hazards",
+        "EventCode": "0x121",
+        "EventName": "BPU_FLUSH_MEM_FAULT",
+        "BriefDescription": "Flushes due to memory hazards"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json
new file mode 100644
index 0000000000000..c5d1d22bd034b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json
@@ -0,0 +1,442 @@
+[
+    {
+        "MetricName": "branch_miss_pred_rate",
+        "MetricExpr": "BR_MIS_PRED / BR_PRED",
+        "BriefDescription": "Branch predictor misprediction rate. May not count branches that are never resolved because they are in the misprediction shadow of an earlier branch",
+        "MetricGroup": "branch",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "bus_utilization",
+        "MetricExpr": "BUS_ACCESS / (BUS_CYCLES * 1)",
+        "BriefDescription": "Core-to-uncore bus utilization",
+        "MetricGroup": "Bus",
+        "ScaleUnit": "100percent of bus cycles"
+    },
+    {
+        "MetricName": "l1d_cache_miss_ratio",
+        "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE",
+        "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.",
+        "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "l1i_cache_miss_ratio",
+        "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE",
+        "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.",
+        "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "Miss_Ratio;l1d_cache_read_miss",
+        "MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD",
+        "BriefDescription": "L1D cache read miss rate",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1per cache read access"
+    },
+    {
+        "MetricName": "l2_cache_miss_ratio",
+        "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE",
+        "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.",
+        "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "l1i_cache_read_miss_rate",
+        "MetricExpr": "L1I_CACHE_LMISS / L1I_CACHE",
+        "BriefDescription": "L1I cache read miss rate",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1per cache access"
+    },
+    {
+        "MetricName": "l2d_cache_read_miss_rate",
+        "MetricExpr": "L2D_CACHE_LMISS_RD / L2D_CACHE_RD",
+        "BriefDescription": "L2 cache read miss rate",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1per cache read access"
+    },
+    {
+        "MetricName": "l1d_cache_miss_mpki",
+        "MetricExpr": "(L1D_CACHE_LMISS_RD * 1e3) / INST_RETIRED",
+        "BriefDescription": "Misses per thousand instructions (data)",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "l1i_cache_miss_mpki",
+        "MetricExpr": "(L1I_CACHE_LMISS * 1e3) / INST_RETIRED",
+        "BriefDescription": "Misses per thousand instructions (instruction)",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "1MPKI"
+    },
+    {
+        "MetricName": "simd_percentage",
+        "MetricExpr": "ASE_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "crypto_percentage",
+        "MetricExpr": "CRYPTO_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "gflops",
+        "MetricExpr": "VFP_SPEC / (duration_time * 1e9)",
+        "BriefDescription": "Giga-floating point operations per second",
+        "MetricGroup": "InstructionMix"
+    },
+    {
+        "MetricName": "integer_dp_percentage",
+        "MetricExpr": "DP_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "ipc",
+        "MetricExpr": "INST_RETIRED / CPU_CYCLES",
+        "BriefDescription": "This metric measures the number of instructions retired per cycle.",
+        "MetricGroup": "General",
+        "ScaleUnit": "1per cycle"
+    },
+    {
+        "MetricName": "load_percentage",
+        "MetricExpr": "LD_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "load_store_spec_rate",
+        "MetricExpr": "LDST_SPEC / INST_SPEC",
+        "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speclatively executed",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "retired_mips",
+        "MetricExpr": "INST_RETIRED / (duration_time * 1e6)",
+        "BriefDescription": "Millions of instructions per second",
+        "MetricGroup": "InstructionMix"
+    },
+    {
+        "MetricName": "spec_utilization_mips",
+        "MetricExpr": "INST_SPEC / (duration_time * 1e6)",
+        "BriefDescription": "Millions of instructions per second",
+        "MetricGroup": "PEutilization"
+    },
+    {
+        "MetricName": "pc_write_spec_rate",
+        "MetricExpr": "PC_WRITE_SPEC / INST_SPEC",
+        "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speclatively executed",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "store_percentage",
+        "MetricExpr": "ST_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "scalar_fp_percentage",
+        "MetricExpr": "VFP_SPEC / INST_SPEC",
+        "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.",
+        "MetricGroup": "Operation_Mix",
+        "ScaleUnit": "100percent of operations"
+    },
+    {
+        "MetricName": "retired_rate",
+        "MetricExpr": "OP_RETIRED / OP_SPEC",
+        "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)",
+        "MetricGroup": "General",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "wasted",
+        "MetricExpr": "1 - (OP_RETIRED / (CPU_CYCLES * #slots))",
+        "BriefDescription": "Of all the micro-operations issued, what proportion are lost",
+        "MetricGroup": "General",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "wasted_rate",
+        "MetricExpr": "1 - OP_RETIRED / OP_SPEC",
+        "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)",
+        "MetricGroup": "General",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "stall_backend_cache_rate",
+        "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and cache miss",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_backend_resource_rate",
+        "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and resource full",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_backend_tlb_rate",
+        "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and TLB miss",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_frontend_cache_rate",
+        "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_frontend_tlb_rate",
+        "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss",
+        "MetricGroup": "Stall",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "dtlb_walk_ratio",
+        "MetricExpr": "DTLB_WALK / L1D_TLB",
+        "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.",
+        "MetricGroup": "Miss_Ratio;DTLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
+    },
+    {
+        "MetricName": "itlb_walk_ratio",
+        "MetricExpr": "ITLB_WALK / L1I_TLB",
+        "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.",
+        "MetricGroup": "Miss_Ratio;ITLB_Effectiveness",
+        "ScaleUnit": "1per TLB access"
+    },
+    {
+        "ArchStdEvent": "backend_bound"
+    },
+    {
+        "ArchStdEvent": "frontend_bound",
+        "MetricExpr": "100 - (retired_fraction + slots_lost_misspeculation_fraction + backend_bound)"
+    },
+    {
+        "MetricName": "slots_lost_misspeculation_fraction",
+        "MetricExpr": "(OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)",
+        "BriefDescription": "Fraction of slots lost due to misspeculation",
+        "DefaultMetricgroupName": "TopdownL1",
+        "MetricGroup": "Default;TopdownL1",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "retired_fraction",
+        "MetricExpr": "OP_RETIRED / (CPU_CYCLES * #slots)",
+        "BriefDescription": "Fraction of slots retiring, useful work",
+        "DefaultMetricgroupName": "TopdownL1",
+        "MetricGroup": "Default;TopdownL1",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "backend_core",
+        "MetricExpr": "(backend_bound / 100) - backend_memory",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to backend non-memory subsystem issues",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "backend_memory",
+        "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE) / CPU_CYCLES",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to backend memory subsystem issues (cache/tlb miss)",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "MetricName": "branch_mispredict",
+        "MetricExpr": "(BR_MIS_PRED_RETIRED / GPC_FLUSH) * slots_lost_misspeculation_fraction",
+        "BriefDescription": "Fraction of slots lost due to branch misprediciton",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "1percent of slots"
+    },
+    {
+        "MetricName": "frontend_bandwidth",
+        "MetricExpr": "frontend_bound - frontend_latency",
+        "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "1percent of slots"
+    },
+    {
+        "MetricName": "frontend_latency",
+        "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - ((frontend_bound / 100) * CPU_CYCLES * #slots)) / #slots)) / CPU_CYCLES",
+        "BriefDescription": "Fraction of slots the CPU was stalled due to frontend latency issues (cache/tlb miss); nothing to dispatch",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "other_miss_pred",
+        "MetricExpr": "slots_lost_misspeculation_fraction - branch_mispredict",
+        "BriefDescription": "Fraction of slots lost due to other/non-branch misprediction misspeculation",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "1percent of slots"
+    },
+    {
+        "MetricName": "pipe_utilization",
+        "MetricExpr": "100 * ((IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6))",
+        "BriefDescription": "Fraction of execute slots utilized",
+        "MetricGroup": "TopdownL2",
+        "ScaleUnit": "1percent of slots"
+    },
+    {
+        "MetricName": "d_cache_l2_miss_rate",
+        "MetricExpr": "STALL_BACKEND_MEM / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data L2 cache miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "d_cache_miss_rate",
+        "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data cache miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "d_tlb_miss_rate",
+        "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to data TLB miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "fsu_pipe_utilization",
+        "MetricExpr": "FSU_ISSUED / (CPU_CYCLES * 2)",
+        "BriefDescription": "Fraction of FSU execute slots utilized",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "i_cache_miss_rate",
+        "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction cache miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "i_tlb_miss_rate",
+        "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction TLB miss",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "ixu_pipe_utilization",
+        "MetricExpr": "IXU_NUM_UOPS_ISSUED / (CPU_CYCLES * #slots)",
+        "BriefDescription": "Fraction of IXU execute slots utilized",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "stall_recovery_rate",
+        "MetricExpr": "IDR_STALL_FLUSH / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled due to flush recovery",
+        "MetricGroup": "TopdownL3",
+        "ScaleUnit": "100percent of slots"
+    },
+    {
+        "MetricName": "stall_fsu_sched_rate",
+        "MetricExpr": "IDR_STALL_FSU_SCHED / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and FSU was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_ixu_sched_rate",
+        "MetricExpr": "IDR_STALL_IXU_SCHED / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and IXU was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_lob_id_rate",
+        "MetricExpr": "IDR_STALL_LOB_ID / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and LOB was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_rob_id_rate",
+        "MetricExpr": "IDR_STALL_ROB_ID / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and ROB was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "stall_sob_id_rate",
+        "MetricExpr": "IDR_STALL_SOB_ID / CPU_CYCLES",
+        "BriefDescription": "Fraction of cycles the CPU was stalled and SOB was full",
+        "MetricGroup": "TopdownL4",
+        "ScaleUnit": "100percent of cycles"
+    },
+    {
+        "MetricName": "l1d_cache_access_demand",
+        "MetricExpr": "L1D_CACHE_RW / L1D_CACHE",
+        "BriefDescription": "L1D cache access - demand",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_access_prefetces",
+        "MetricExpr": "L1D_CACHE_PRFM / L1D_CACHE",
+        "BriefDescription": "L1D cache access - prefetch",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_demand_misses",
+        "MetricExpr": "L1D_CACHE_REFILL_RW / L1D_CACHE",
+        "BriefDescription": "L1D cache demand misses",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_demand_misses_read",
+        "MetricExpr": "L1D_CACHE_REFILL_RD / L1D_CACHE",
+        "BriefDescription": "L1D cache demand misses - read",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_demand_misses_write",
+        "MetricExpr": "L1D_CACHE_REFILL_WR / L1D_CACHE",
+        "BriefDescription": "L1D cache demand misses - write",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "l1d_cache_prefetch_misses",
+        "MetricExpr": "L1D_CACHE_REFILL_PRFM / L1D_CACHE",
+        "BriefDescription": "L1D cache prefetch misses",
+        "MetricGroup": "Cache",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "ase_scalar_mix",
+        "MetricExpr": "ASE_SCALAR_SPEC / OP_SPEC",
+        "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) scalar operations",
+        "MetricGroup": "Instructions",
+        "ScaleUnit": "100percent of cache acceses"
+    },
+    {
+        "MetricName": "ase_vector_mix",
+        "MetricExpr": "ASE_VECTOR_SPEC / OP_SPEC",
+        "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) vector operations",
+        "MetricGroup": "Instructions",
+        "ScaleUnit": "100percent of cache acceses"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json
new file mode 100644
index 0000000000000..66d83b680651e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json
@@ -0,0 +1,170 @@
+[
+    {
+        "PublicDescription": "Level 2 data translation buffer allocation",
+        "EventCode": "0xD800",
+        "EventName": "MMU_D_OTB_ALLOC",
+        "BriefDescription": "Level 2 data translation buffer allocation"
+    },
+    {
+        "PublicDescription": "Data TLB translation cache hit on S1L2 walk cache entry",
+        "EventCode": "0xd801",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L2_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S1L2 walk cache entry"
+    },
+    {
+        "PublicDescription": "Data TLB translation cache hit on S1L1 walk cache entry",
+        "EventCode": "0xd802",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L1_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S1L1 walk cache entry"
+    },
+    {
+        "PublicDescription": "Data TLB translation cache hit on S1L0 walk cache entry",
+        "EventCode": "0xd803",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S1L0_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S1L0 walk cache entry"
+    },
+    {
+        "PublicDescription": "Data TLB translation cache hit on S2L2 walk cache entry",
+        "EventCode": "0xd804",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L2_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S2L2 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Data TLB translation cache hit on S2L1 walk cache entry",
+        "EventCode": "0xd805",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L1_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S2L1 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Data TLB translation cache hit on S2L0 walk cache entry",
+        "EventCode": "0xd806",
+        "EventName": "MMU_D_TRANS_CACHE_HIT_S2L0_WALK",
+        "BriefDescription": "Data TLB translation cache hit on S2L0 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Data-side S1 page walk cache lookup",
+        "EventCode": "0xd807",
+        "EventName": "MMU_D_S1_WALK_CACHE_LOOKUP",
+        "BriefDescription": "Data-side S1 page walk cache lookup"
+    },
+    {
+        "PublicDescrition": "Data-side S1 page walk cache refill",
+        "EventCode": "0xd808",
+        "EventName": "MMU_D_S1_WALK_CACHE_REFILL",
+        "BriefDescription": "Data-side S1 page walk cache refill"
+    },
+    {
+        "PublicDescrition": "Data-side S2 page walk cache lookup",
+        "EventCode": "0xd809",
+        "EventName": "MMU_D_S2_WALK_CACHE_LOOKUP",
+        "BriefDescription": "Data-side S2 page walk cache lookup"
+    },
+    {
+        "PublicDescrition": "Data-side S2 page walk cache refill",
+        "EventCode": "0xd80a",
+        "EventName": "MMU_D_S2_WALK_CACHE_REFILL",
+        "BriefDescription": "Data-side S2 page walk cache refill"
+    },
+    {
+        "PublicDescription": "Data-side S1 table walk fault",
+        "EventCode": "0xD80B",
+        "EventName": "MMU_D_S1_WALK_FAULT",
+        "BriefDescription": "Data-side S1 table walk fault"
+    },
+    {
+        "PublicDescription": "Data-side S2 table walk fault",
+        "EventCode": "0xD80C",
+        "EventName": "MMU_D_S2_WALK_FAULT",
+        "BriefDescription": "Data-side S2 table walk fault"
+    },
+    {
+        "PublicDescription": "Data-side table walk steps or descriptor fetches",
+        "EventCode": "0xD80D",
+        "EventName": "MMU_D_WALK_STEPS",
+        "BriefDescription": "Data-side table walk steps or descriptor fetches"
+    },
+    {
+        "PublicDescription": "Level 2 instruction translation buffer allocation",
+        "EventCode": "0xD900",
+        "EventName": "MMU_I_OTB_ALLOC",
+        "BriefDescription": "Level 2 instruction translation buffer allocation"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S1L2 walk cache entry",
+        "EventCode": "0xd901",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L2_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S1L2 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S1L1 walk cache entry",
+        "EventCode": "0xd902",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L1_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S1L1 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S1L0 walk cache entry",
+        "EventCode": "0xd903",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S1L0_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S1L0 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S2L2 walk cache entry",
+        "EventCode": "0xd904",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L2_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S2L2 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S2L1 walk cache entry",
+        "EventCode": "0xd905",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L1_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S2L1 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction TLB translation cache hit on S2L0 walk cache entry",
+        "EventCode": "0xd906",
+        "EventName": "MMU_I_TRANS_CACHE_HIT_S2L0_WALK",
+        "BriefDescription": "Instruction TLB translation cache hit on S2L0 walk cache entry"
+    },
+    {
+        "PublicDescrition": "Instruction-side S1 page walk cache lookup",
+        "EventCode": "0xd907",
+        "EventName": "MMU_I_S1_WALK_CACHE_LOOKUP",
+        "BriefDescription": "Instruction-side S1 page walk cache lookup"
+    },
+    {
+        "PublicDescrition": "Instruction-side S1 page walk cache refill",
+        "EventCode": "0xd908",
+        "EventName": "MMU_I_S1_WALK_CACHE_REFILL",
+        "BriefDescription": "Instruction-side S1 page walk cache refill"
+    },
+    {
+        "PublicDescrition": "Instruction-side S2 page walk cache lookup",
+        "EventCode": "0xd909",
+        "EventName": "MMU_I_S2_WALK_CACHE_LOOKUP",
+        "BriefDescription": "Instruction-side S2 page walk cache lookup"
+    },
+    {
+        "PublicDescrition": "Instruction-side S2 page walk cache refill",
+        "EventCode": "0xd90a",
+        "EventName": "MMU_I_S2_WALK_CACHE_REFILL",
+        "BriefDescription": "Instruction-side S2 page walk cache refill"
+    },
+    {
+        "PublicDescription": "Instruction-side S1 table walk fault",
+        "EventCode": "0xD90B",
+        "EventName": "MMU_I_S1_WALK_FAULT",
+        "BriefDescription": "Instruction-side S1 table walk fault"
+    },
+    {
+        "PublicDescription": "Instruction-side S2 table walk fault",
+        "EventCode": "0xD90C",
+        "EventName": "MMU_I_S2_WALK_FAULT",
+        "BriefDescription": "Instruction-side S2 table walk fault"
+    },
+    {
+        "PublicDescription": "Instruction-side table walk steps or descriptor fetches",
+        "EventCode": "0xD90D",
+        "EventName": "MMU_I_WALK_STEPS",
+        "BriefDescription": "Instruction-side table walk steps or descriptor fetches"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json
new file mode 100644
index 0000000000000..2fb2d1f183fc7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json
@@ -0,0 +1,41 @@
+[
+    {
+        "ArchStdEvent": "STALL_FRONTEND",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
+    },
+    {
+        "ArchStdEvent": "STALL_BACKEND"
+    },
+    {
+        "ArchStdEvent": "STALL",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT_BACKEND"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT_FRONTEND",
+        "Errata": "Errata AC03_CPU_29",
+        "BriefDescription": "Impacted by errata, use metrics instead -"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT"
+    },
+    {
+        "ArchStdEvent": "STALL_BACKEND_MEM"
+    },
+    {
+        "PublicDescription": "Frontend stall cycles, TLB",
+        "EventCode": "0x815c",
+        "EventName": "STALL_FRONTEND_TLB",
+        "BriefDescription": "Frontend stall cycles, TLB"
+    },
+    {
+        "PublicDescription": "Backend stall cycles, TLB",
+        "EventCode": "0x8167",
+        "EventName": "STALL_BACKEND_TLB",
+        "BriefDescription": "Backend stall cycles, TLB"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json
new file mode 100644
index 0000000000000..20f2165c85fec
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "SAMPLE_POP"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_FEED"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_FILTRATE"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_COLLISION"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index 5b58db5032c11..f4d1ca4d1493d 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -42,3 +42,4 @@
 0x00000000480fd010,v1,hisilicon/hip08,core
 0x00000000500f0000,v1,ampere/emag,core
 0x00000000c00fac30,v1,ampere/ampereone,core
+0x00000000c00fac40,v1,ampere/ampereonex,core
-- 
GitLab


From b809fc656e763296f227b9b31e8f225e5977a8af Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 29 Nov 2023 13:34:25 -0800
Subject: [PATCH 0778/4076] perf build: Shellcheck support for OUTPUT directory

Migrate Makefile.tests to Build so that variables like rule_mkdir are
defined via Makefile.build (needed so the output directory can be
created). This requires SHELLCHECK being exported and the clean rule
tweaking to remove the files in find.

Change find "-perm -o=x" as it was failing on my Debian based Linux
kernel tree, switch to using "-executable".

Adding a filename prefix of "." to the shellcheck log files is a pain
and error prone in make, remove this prefix and just add the
shellcheck log files to .gitignore.

Fix the command echo so that running the test is displayed.

Fixes: 1638b11ef8156c85 ("perf tools: Add perf binary dependent rule for shellcheck log in Makefile.perf")
Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231129213428.2227448-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/.gitignore           |  3 +++
 tools/perf/Makefile.perf        | 30 ++++++++++--------------------
 tools/perf/tests/Build          | 14 ++++++++++++++
 tools/perf/tests/Makefile.tests | 22 ----------------------
 4 files changed, 27 insertions(+), 42 deletions(-)
 delete mode 100644 tools/perf/tests/Makefile.tests

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index ee5c14f3b8b19..f5b81d439387a 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -39,6 +39,9 @@ trace/beauty/generated/
 pmu-events/pmu-events.c
 pmu-events/jevents
 pmu-events/metric_test.log
+tests/shell/*.shellcheck_log
+tests/shell/coresight/*.shellcheck_log
+tests/shell/lib/*.shellcheck_log
 feature/
 libapi/
 libbpf/
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 824cbc0af7d7a..1ab2a908f240a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -229,8 +229,15 @@ else
   force_fixdep := $(config)
 endif
 
+# Runs shellcheck on perf test shell scripts
+ifeq ($(NO_SHELLCHECK),1)
+  SHELLCHECK :=
+else
+  SHELLCHECK := $(shell which shellcheck 2> /dev/null)
+endif
+
 export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
-export HOSTCC HOSTLD HOSTAR HOSTCFLAGS
+export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK
 
 include $(srctree)/tools/build/Makefile.include
 
@@ -673,23 +680,7 @@ $(PERF_IN): prepare FORCE
 $(PMU_EVENTS_IN): FORCE prepare
 	$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=pmu-events obj=pmu-events
 
-# Runs shellcheck on perf test shell scripts
-
-SHELLCHECK := $(shell which shellcheck 2> /dev/null)
-
-ifeq ($(NO_SHELLCHECK),1)
-SHELLCHECK :=
-endif
-
-ifneq ($(SHELLCHECK),)
-SHELLCHECK_TEST: FORCE prepare
-	$(Q)$(MAKE) -f $(srctree)/tools/perf/tests/Makefile.tests
-else
-SHELLCHECK_TEST:
-	@:
-endif
-
-$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) SHELLCHECK_TEST
+$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \
 		$(PERF_IN) $(PMU_EVENTS_IN) $(LIBS) -o $@
 
@@ -1152,9 +1143,8 @@ bpf-skel-clean:
 	$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS)
 
 clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean tests-coresight-targets-clean
-	$(Q)$(MAKE) -f $(srctree)/tools/perf/tests/Makefile.tests clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-iostat $(LANG_BINDINGS)
-	$(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+	$(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete -o -name '*.shellcheck_log' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)$(LIBJVMTI).so
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 2b45ffa462a6c..53ba9c3e20e05 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -77,3 +77,17 @@ CFLAGS_python-use.o   += -DPYTHONPATH="BUILD_STR($(OUTPUT)python)" -DPYTHON="BUI
 CFLAGS_dwarf-unwind.o += -fno-optimize-sibling-calls
 
 perf-y += workloads/
+
+ifdef SHELLCHECK
+  SHELL_TESTS := $(shell find tests/shell -executable -type f -name '*.sh')
+  TEST_LOGS := $(SHELL_TESTS:tests/shell/%=shell/%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(TEST_LOGS)
diff --git a/tools/perf/tests/Makefile.tests b/tools/perf/tests/Makefile.tests
deleted file mode 100644
index fdaca5f7a946d..0000000000000
--- a/tools/perf/tests/Makefile.tests
+++ /dev/null
@@ -1,22 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# Athira Rajeev <atrajeev@linux.vnet.ibm.com>, 2023
-
-PROGS := $(shell find tests/shell -perm -o=x -type f -name '*.sh')
-FILE_NAME := $(notdir $(PROGS))
-FILE_NAME := $(FILE_NAME:%=.%)
-LOGS := $(join $(dir $(PROGS)),$(FILE_NAME))
-LOGS := $(LOGS:%=%.shellcheck_log)
-
-.PHONY: all
-all: SHELLCHECK_RUN
-	@:
-
-SHELLCHECK_RUN: $(LOGS)
-
-.%.shellcheck_log: %
-	$(call rule_mkdir)
-	$(Q)$(call frecho-cmd,test)@shellcheck -S warning "$<" > $@ || (cat $@ && rm $@ && false)
-
-clean:
-	$(eval log_files := $(shell find . -name '.*.shellcheck_log'))
-	@rm -rf $(log_files)
-- 
GitLab


From 8226e4a3b35f525d11934484ee5979399ff8b7dc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 29 Nov 2023 13:34:27 -0800
Subject: [PATCH 0779/4076] perf test: Use common python setup library

Avoid replicated logic by having a common library to set the PYTHON
environment variable.

Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231129213428.2227448-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/lib/setup_python.sh       | 16 ++++++++++++++++
 tools/perf/tests/shell/stat+json_output.sh       | 16 +++-------------
 tools/perf/tests/shell/stat_metrics_values.sh    | 14 ++++----------
 .../tests/shell/test_perf_data_converter_json.sh | 13 +++----------
 4 files changed, 26 insertions(+), 33 deletions(-)
 create mode 100644 tools/perf/tests/shell/lib/setup_python.sh

diff --git a/tools/perf/tests/shell/lib/setup_python.sh b/tools/perf/tests/shell/lib/setup_python.sh
new file mode 100644
index 0000000000000..c2fce1793538d
--- /dev/null
+++ b/tools/perf/tests/shell/lib/setup_python.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+if [ "x$PYTHON" = "x" ]
+then
+  python3 --version >/dev/null 2>&1 && PYTHON=python3
+fi
+if [ "x$PYTHON" = "x" ]
+then
+  python --version >/dev/null 2>&1 && PYTHON=python
+fi
+if [ "x$PYTHON" = "x" ]
+then
+  echo Skipping test, python not detected please set environment variable PYTHON.
+  exit 2
+fi
diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh
index 196e22672c50c..3bc900533a5d6 100755
--- a/tools/perf/tests/shell/stat+json_output.sh
+++ b/tools/perf/tests/shell/stat+json_output.sh
@@ -8,20 +8,10 @@ set -e
 
 skip_test=0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py
-if [ "x$PYTHON" == "x" ]
-then
-	if which python3 > /dev/null
-	then
-		PYTHON=python3
-	elif which python > /dev/null
-	then
-		PYTHON=python
-	else
-		echo Skipping test, python not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
 
 stat_output=$(mktemp /tmp/__perf_test.stat_output.json.XXXXX)
 
diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh
index ad94c936de7e8..7ca172599aa6c 100755
--- a/tools/perf/tests/shell/stat_metrics_values.sh
+++ b/tools/perf/tests/shell/stat_metrics_values.sh
@@ -1,16 +1,10 @@
 #!/bin/bash
 # perf metrics value validation
 # SPDX-License-Identifier: GPL-2.0
-if [ "x$PYTHON" == "x" ]
-then
-	if which python3 > /dev/null
-	then
-		PYTHON=python3
-	else
-		echo Skipping test, python3 not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 
 grep -q GenuineIntel /proc/cpuinfo || { echo Skipping non-Intel; exit 2; }
 
diff --git a/tools/perf/tests/shell/test_perf_data_converter_json.sh b/tools/perf/tests/shell/test_perf_data_converter_json.sh
index 6ded58f98f55b..c4f1b59d116f6 100755
--- a/tools/perf/tests/shell/test_perf_data_converter_json.sh
+++ b/tools/perf/tests/shell/test_perf_data_converter_json.sh
@@ -6,16 +6,9 @@ set -e
 
 err=0
 
-if [ "$PYTHON" = "" ] ; then
-	if which python3 > /dev/null ; then
-		PYTHON=python3
-	elif which python > /dev/null ; then
-		PYTHON=python
-	else
-		echo Skipping test, python not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 result=$(mktemp /tmp/__perf_test.output.json.XXXXX)
-- 
GitLab


From 7d723ef83b8070ab2304df22ed952dc627385406 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 29 Nov 2023 13:34:28 -0800
Subject: [PATCH 0780/4076] perf test: Add basic 'perf list --json" test

Test that JSON output produces valid JSON.

Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231129213428.2227448-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/list.sh | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
 create mode 100755 tools/perf/tests/shell/list.sh

diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh
new file mode 100755
index 0000000000000..22b004f2b23ec
--- /dev/null
+++ b/tools/perf/tests/shell/list.sh
@@ -0,0 +1,19 @@
+#!/bin/sh
+# perf list tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+err=0
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
+
+test_list_json() {
+  echo "Json output test"
+  perf list -j | $PYTHON -m json.tool
+  echo "Json output test [Success]"
+}
+
+test_list_json
+exit $err
-- 
GitLab


From 9eef41014fe01287dae79fe208b9b433b13040bb Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Thu, 23 Nov 2023 21:31:10 +0530
Subject: [PATCH 0781/4076] perf vendor events powerpc: Update datasource event
 name to fix duplicate events

Running "perf list" on powerpc fails with segfault as below:

   $ ./perf list
   Segmentation fault (core dumped)
   $

This happens because of duplicate events in the JSON list.  The powerpc
JSON event list contains some event with same event name, but different
event code. They are:

- PM_INST_FROM_L3MISS (Present in datasource and frontend)
- PM_MRK_DATA_FROM_L2MISS (Present in datasource and marked)
- PM_MRK_INST_FROM_L3MISS (Present in datasource and marked)
- PM_MRK_DATA_FROM_L3MISS (Present in datasource and marked)

pmu_events_table__num_events() uses the value from table_pmu->num_entries
which includes duplicate events as well. This causes issue during "perf
list" and results in a segmentation fault.

Since both event codes are valid, append _DSRC to the Data Source events
(datasource.json), so that they would have a unique name.

Also add PM_DATA_FROM_L2MISS_DSRC and PM_DATA_FROM_L3MISS_DSRC events.

With the fix, 'perf list' works as expected.

Fixes: fc143580753348c6 ("perf vendor events power10: Update JSON/events")
Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Disha Goel <disgoel@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231123160110.94090-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/powerpc/power10/datasource.json       | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/tools/perf/pmu-events/arch/powerpc/power10/datasource.json b/tools/perf/pmu-events/arch/powerpc/power10/datasource.json
index 6b0356f2d3013..0eeaaf1a95b86 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/datasource.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/datasource.json
@@ -99,6 +99,11 @@
     "EventName": "PM_INST_FROM_L2MISS",
     "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss."
   },
+  {
+    "EventCode": "0x0003C0000000C040",
+    "EventName": "PM_DATA_FROM_L2MISS_DSRC",
+    "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss."
+  },
   {
     "EventCode": "0x000380000010C040",
     "EventName": "PM_INST_FROM_L2MISS_ALL",
@@ -161,9 +166,14 @@
   },
   {
     "EventCode": "0x000780000000C040",
-    "EventName": "PM_INST_FROM_L3MISS",
+    "EventName": "PM_INST_FROM_L3MISS_DSRC",
     "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss."
   },
+  {
+    "EventCode": "0x0007C0000000C040",
+    "EventName": "PM_DATA_FROM_L3MISS_DSRC",
+    "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss."
+  },
   {
     "EventCode": "0x000780000010C040",
     "EventName": "PM_INST_FROM_L3MISS_ALL",
@@ -981,7 +991,7 @@
   },
   {
     "EventCode": "0x0003C0000000C142",
-    "EventName": "PM_MRK_DATA_FROM_L2MISS",
+    "EventName": "PM_MRK_DATA_FROM_L2MISS_DSRC",
     "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction."
   },
   {
@@ -1046,12 +1056,12 @@
   },
   {
     "EventCode": "0x000780000000C142",
-    "EventName": "PM_MRK_INST_FROM_L3MISS",
+    "EventName": "PM_MRK_INST_FROM_L3MISS_DSRC",
     "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
   },
   {
     "EventCode": "0x0007C0000000C142",
-    "EventName": "PM_MRK_DATA_FROM_L3MISS",
+    "EventName": "PM_MRK_DATA_FROM_L3MISS_DSRC",
     "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
   },
   {
-- 
GitLab


From a4320085a6c694326dd8db46f563d52d1a826f07 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 28 Nov 2023 12:39:40 -0800
Subject: [PATCH 0782/4076] perf mem: Fix error on hybrid related to
 availability of mem event in a PMU

The below error can be triggered on a hybrid machine.

 $ perf mem record -t load sleep 1
 event syntax error: 'breakpoint/mem-loads,ldlat=30/P'
                                \___ Bad event or PMU

 Unable to find PMU or event on a PMU of 'breakpoint'

In the perf_mem_events__record_args(), the current perf never checks the
availability of a mem event on a given PMU. All the PMUs will be added
to the perf mem event list. Perf errors out for the unsupported PMU.

Extend perf_mem_event__supported() and take a PMU into account. Check
the mem event for each PMU before adding it to the perf mem event list.

Optimize the perf_mem_events__init() a little bit. The function is to
check whether the mem events are supported in the system. It doesn't
need to scan all PMUs. Just return with the first supported PMU is good
enough.

Fixes: 5752c20f3787c9bc ("perf mem: Scan all PMUs instead of just core ones")
Reported-by: Ammy Yi <ammy.yi@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Ammy Yi <ammy.yi@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20231128203940.3964287-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/mem-events.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 954b235e12e51..3a2e3687878c1 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -100,11 +100,14 @@ int perf_mem_events__parse(const char *str)
 	return -1;
 }
 
-static bool perf_mem_event__supported(const char *mnt, char *sysfs_name)
+static bool perf_mem_event__supported(const char *mnt, struct perf_pmu *pmu,
+				      struct perf_mem_event *e)
 {
+	char sysfs_name[100];
 	char path[PATH_MAX];
 	struct stat st;
 
+	scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name);
 	scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, sysfs_name);
 	return !stat(path, &st);
 }
@@ -120,7 +123,6 @@ int perf_mem_events__init(void)
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		struct perf_mem_event *e = perf_mem_events__ptr(j);
-		char sysfs_name[100];
 		struct perf_pmu *pmu = NULL;
 
 		/*
@@ -136,12 +138,12 @@ int perf_mem_events__init(void)
 		 * of core PMU.
 		 */
 		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-			scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name);
-			e->supported |= perf_mem_event__supported(mnt, sysfs_name);
+			e->supported |= perf_mem_event__supported(mnt, pmu, e);
+			if (e->supported) {
+				found = true;
+				break;
+			}
 		}
-
-		if (e->supported)
-			found = true;
 	}
 
 	return found ? 0 : -ENOENT;
@@ -167,13 +169,10 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e,
 						    int idx)
 {
 	const char *mnt = sysfs__mount();
-	char sysfs_name[100];
 	struct perf_pmu *pmu = NULL;
 
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name,
-			  pmu->name);
-		if (!perf_mem_event__supported(mnt, sysfs_name)) {
+		if (!perf_mem_event__supported(mnt, pmu, e)) {
 			pr_err("failed: event '%s' not supported\n",
 			       perf_mem_events__name(idx, pmu->name));
 		}
@@ -183,6 +182,7 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e,
 int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 				 char **rec_tmp, int *tmp_nr)
 {
+	const char *mnt = sysfs__mount();
 	int i = *argv_nr, k = 0;
 	struct perf_mem_event *e;
 
@@ -211,6 +211,9 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 			while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 				const char *s = perf_mem_events__name(j, pmu->name);
 
+				if (!perf_mem_event__supported(mnt, pmu, e))
+					continue;
+
 				rec_argv[i++] = "-e";
 				if (s) {
 					char *copy = strdup(s);
-- 
GitLab


From 144081ef78c36e255c08b74da86ef68e6cf0a221 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 20 Nov 2023 11:04:08 -0800
Subject: [PATCH 0783/4076] perf test: Add basic 'perf diff' test

There are some old bug reports on perf diff crashing:

https://rhaas.blogspot.com/2012/06/perf-good-bad-ugly.html

Happening across them I was prompted to add two very basic tests that
will give some 'perf diff' coverage.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231120190408.281826-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/diff.sh | 101 +++++++++++++++++++++++++++++++++
 1 file changed, 101 insertions(+)
 create mode 100755 tools/perf/tests/shell/diff.sh

diff --git a/tools/perf/tests/shell/diff.sh b/tools/perf/tests/shell/diff.sh
new file mode 100755
index 0000000000000..2131857636888
--- /dev/null
+++ b/tools/perf/tests/shell/diff.sh
@@ -0,0 +1,101 @@
+#!/bin/sh
+# perf diff tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+perfdata1=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+perfdata2=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+perfdata3=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+testprog="perf test -w thloop"
+testsym="test_loop"
+
+cleanup() {
+  rm -rf "${perfdata1}"
+  rm -rf "${perfdata1}".old
+  rm -rf "${perfdata2}"
+  rm -rf "${perfdata2}".old
+  rm -rf "${perfdata3}"
+  rm -rf "${perfdata3}".old
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+make_data() {
+  file="$1"
+  if ! perf record -o "${file}" ${testprog} 2> /dev/null
+  then
+    echo "Workload record [Failed record]"
+    echo 1
+    return
+  fi
+  if ! perf report -i "${file}" -q | grep -q "${testsym}"
+  then
+    echo "Workload record [Failed missing output]"
+    echo 1
+    return
+  fi
+  echo 0
+}
+
+test_two_files() {
+  echo "Basic two file diff test"
+  err=$(make_data "${perfdata1}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata2}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+
+  if ! perf diff "${perfdata1}" "${perfdata2}" | grep -q "${testsym}"
+  then
+    echo "Basic two file diff test [Failed diff]"
+    err=1
+    return
+  fi
+  echo "Basic two file diff test [Success]"
+}
+
+test_three_files() {
+  echo "Basic three file diff test"
+  err=$(make_data "${perfdata1}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata2}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata3}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+
+  if ! perf diff "${perfdata1}" "${perfdata2}" "${perfdata3}" | grep -q "${testsym}"
+  then
+    echo "Basic three file diff test [Failed diff]"
+    err=1
+    return
+  fi
+  echo "Basic three file diff test [Success]"
+}
+
+test_two_files
+test_three_files
+
+cleanup
+exit $err
-- 
GitLab


From 018b04248543f49d677011d4615f243a39a155a8 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 30 Jun 2023 09:00:29 +0100
Subject: [PATCH 0784/4076] perf bench sched-seccomp-notify: Fix spelling
 mistake "synchronious" -> "synchronous"

There is a spelling mistake in an option description. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-janitors@vger.kernel.org
Link: https://lore.kernel.org/r/20230630080029.15614-1-colin.i.king@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/sched-seccomp-notify.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/bench/sched-seccomp-notify.c b/tools/perf/bench/sched-seccomp-notify.c
index a01c40131493b..269c1f4a6852c 100644
--- a/tools/perf/bench/sched-seccomp-notify.c
+++ b/tools/perf/bench/sched-seccomp-notify.c
@@ -32,7 +32,7 @@ static bool sync_mode;
 static const struct option options[] = {
 	OPT_U64('l', "loop",	&loops,		"Specify number of loops"),
 	OPT_BOOLEAN('s', "sync-mode", &sync_mode,
-		    "Enable the synchronious mode for seccomp notifications"),
+		    "Enable the synchronous mode for seccomp notifications"),
 	OPT_END()
 };
 
-- 
GitLab


From 96d1d578dec1e69ed086dd67f7e5974875d981b3 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 5 Dec 2023 14:53:18 -0800
Subject: [PATCH 0785/4076] android: binder: fix a kernel-doc enum warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add kernel-doc notation for @LOOP_END to prevent a kernel-doc
warning.

binder_alloc_selftest.c:76: warning: Enum value 'LOOP_END' not described in enum 'buf_end_align_type'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Arve Hjønnevåg <arve@android.com>
Cc: Todd Kjos <tkjos@android.com>
Cc: Martijn Coenen <maco@android.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Christian Brauner <christian@brauner.io>
Cc: Carlos Llamas <cmllamas@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Acked-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231205225324.32362-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc_selftest.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
index fba7ab6ca451f..81442fe20a695 100644
--- a/drivers/android/binder_alloc_selftest.c
+++ b/drivers/android/binder_alloc_selftest.c
@@ -72,6 +72,10 @@ enum buf_end_align_type {
 	 * buf1 ]|[ buf2 | buf2 | buf2 ][ ...
 	 */
 	NEXT_NEXT_UNALIGNED,
+	/**
+	 * @LOOP_END: The number of enum values in &buf_end_align_type.
+	 * It is used for controlling loop termination.
+	 */
 	LOOP_END,
 };
 
-- 
GitLab


From 6666ea93d2c422ebeb8039d11e642552da682070 Mon Sep 17 00:00:00 2001
From: Hardik Gajjar <hgajjar@de.adit-jv.com>
Date: Tue, 5 Dec 2023 19:18:28 +0100
Subject: [PATCH 0786/4076] usb: hub: Replace hardcoded quirk value with BIT()
 macro

This patch replaces the hardcoded quirk value in the macro with
BIT().

Signed-off-by: Hardik Gajjar <hgajjar@de.adit-jv.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231205181829.127353-1-hgajjar@de.adit-jv.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 5a60e3c7d8ef1..7b6bfffbdc558 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -47,8 +47,8 @@
 #define USB_VENDOR_TEXAS_INSTRUMENTS		0x0451
 #define USB_PRODUCT_TUSB8041_USB3		0x8140
 #define USB_PRODUCT_TUSB8041_USB2		0x8142
-#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	0x01
-#define HUB_QUIRK_DISABLE_AUTOSUSPEND		0x02
+#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	BIT(0)
+#define HUB_QUIRK_DISABLE_AUTOSUSPEND		BIT(1)
 
 #define USB_TP_TRANSMISSION_DELAY	40	/* ns */
 #define USB_TP_TRANSMISSION_DELAY_MAX	65535	/* ns */
-- 
GitLab


From 855d75cf8311fee156fabb5639bb53757ca83dd4 Mon Sep 17 00:00:00 2001
From: Hardik Gajjar <hgajjar@de.adit-jv.com>
Date: Tue, 5 Dec 2023 19:18:29 +0100
Subject: [PATCH 0787/4076] usb: hub: Add quirk to decrease IN-ep poll interval
 for Microchip USB491x hub

There is a potential delay in notifying Linux USB drivers of downstream
USB bus activity when connecting a high-speed or superSpeed device via the
Microchip USB491x hub. This delay is due to the fixed bInterval value of
12 in the silicon of the Microchip USB491x hub.

Microchip requested to ignore the device descriptor and decrease that
value to 9 as it was too late to modify that in silicon.

This patch speeds up the USB enummeration process that helps to pass
Apple Carplay certifications and improve the User experience when utilizing
the USB device via Microchip Multihost USB491x Hub.

A new hub quirk HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL speeds up
the notification process for Microchip USB491x hub by limiting
the maximum bInterval value to 9.

Signed-off-by: Hardik Gajjar <hgajjar@de.adit-jv.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231205181829.127353-2-hgajjar@de.adit-jv.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 7b6bfffbdc558..ffd7c99e24a36 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -47,12 +47,18 @@
 #define USB_VENDOR_TEXAS_INSTRUMENTS		0x0451
 #define USB_PRODUCT_TUSB8041_USB3		0x8140
 #define USB_PRODUCT_TUSB8041_USB2		0x8142
+#define USB_VENDOR_MICROCHIP			0x0424
+#define USB_PRODUCT_USB4913			0x4913
+#define USB_PRODUCT_USB4914			0x4914
+#define USB_PRODUCT_USB4915			0x4915
 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	BIT(0)
 #define HUB_QUIRK_DISABLE_AUTOSUSPEND		BIT(1)
+#define HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL	BIT(2)
 
 #define USB_TP_TRANSMISSION_DELAY	40	/* ns */
 #define USB_TP_TRANSMISSION_DELAY_MAX	65535	/* ns */
 #define USB_PING_RESPONSE_TIME		400	/* ns */
+#define USB_REDUCE_FRAME_INTR_BINTERVAL	9
 
 /*
  * The SET_ADDRESS request timeout will be 500 ms when
@@ -1910,6 +1916,14 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 		usb_autopm_get_interface_no_resume(intf);
 	}
 
+	if ((id->driver_info & HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL) &&
+	    desc->endpoint[0].desc.bInterval > USB_REDUCE_FRAME_INTR_BINTERVAL) {
+		desc->endpoint[0].desc.bInterval =
+			USB_REDUCE_FRAME_INTR_BINTERVAL;
+		/* Tell the HCD about the interrupt ep's new bInterval */
+		usb_set_interface(hdev, 0, 0);
+	}
+
 	if (hub_configure(hub, &desc->endpoint[0].desc) >= 0) {
 		onboard_hub_create_pdevs(hdev, &hub->onboard_hub_devs);
 
@@ -5906,6 +5920,21 @@ static const struct usb_device_id hub_id_table[] = {
       .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS,
       .idProduct = USB_PRODUCT_TUSB8041_USB3,
       .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
+	{ .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+			| USB_DEVICE_ID_MATCH_PRODUCT,
+	  .idVendor = USB_VENDOR_MICROCHIP,
+	  .idProduct = USB_PRODUCT_USB4913,
+	  .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL},
+	{ .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+			| USB_DEVICE_ID_MATCH_PRODUCT,
+	  .idVendor = USB_VENDOR_MICROCHIP,
+	  .idProduct = USB_PRODUCT_USB4914,
+	  .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL},
+	{ .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+			| USB_DEVICE_ID_MATCH_PRODUCT,
+	  .idVendor = USB_VENDOR_MICROCHIP,
+	  .idProduct = USB_PRODUCT_USB4915,
+	  .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL},
     { .match_flags = USB_DEVICE_ID_MATCH_DEV_CLASS,
       .bDeviceClass = USB_CLASS_HUB},
     { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS,
-- 
GitLab


From b3f8e6ae30bd7ade3a96c9beb2a17167d55492a5 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Tue, 5 Dec 2023 21:05:29 +0100
Subject: [PATCH 0788/4076] dt-bindings: usb: xhci: Add support for BCM2711

The xHCI IP on the BCM2711 SoC is compatible to "brcm,xhci-brcm-v2",
but also requires a power domain. So introduce a new compatible
and the specific constraints. Since the key allOf can only occur
once, merge the reference below.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20231205200531.8232-2-wahrenst@gmx.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/usb/generic-xhci.yaml | 25 ++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/generic-xhci.yaml b/Documentation/devicetree/bindings/usb/generic-xhci.yaml
index 594ebb3ee4320..6ceafa4af2922 100644
--- a/Documentation/devicetree/bindings/usb/generic-xhci.yaml
+++ b/Documentation/devicetree/bindings/usb/generic-xhci.yaml
@@ -9,9 +9,6 @@ title: USB xHCI Controller
 maintainers:
   - Mathias Nyman <mathias.nyman@intel.com>
 
-allOf:
-  - $ref: usb-xhci.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -25,6 +22,11 @@ properties:
               - marvell,armada-380-xhci
               - marvell,armada-8k-xhci
           - const: generic-xhci
+      - description: Broadcom SoCs with power domains
+        items:
+          - enum:
+              - brcm,bcm2711-xhci
+          - const: brcm,xhci-brcm-v2
       - description: Broadcom STB SoCs with xHCI
         enum:
           - brcm,xhci-brcm-v2
@@ -49,6 +51,9 @@ properties:
       - const: core
       - const: reg
 
+  power-domains:
+    maxItems: 1
+
 unevaluatedProperties: false
 
 required:
@@ -56,6 +61,20 @@ required:
   - reg
   - interrupts
 
+allOf:
+  - $ref: usb-xhci.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: brcm,bcm2711-xhci
+    then:
+      required:
+        - power-domains
+    else:
+      properties:
+        power-domains: false
+
 examples:
   - |
     usb@f0931000 {
-- 
GitLab


From 95e71986fc1b9a2e1de30bca8e7a5fab12817cdd Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Tue, 5 Dec 2023 21:05:30 +0100
Subject: [PATCH 0789/4076] usb: xhci: xhci-plat: Add support for BCM2711

With the introduction of a BCM2711 specific compatible, this also
needs to be added to the xHCI driver.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20231205200531.8232-3-wahrenst@gmx.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-plat.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 732cdeb739202..e46175c38570b 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -130,6 +130,9 @@ static const struct of_device_id usb_xhci_of_match[] = {
 	}, {
 		.compatible = "brcm,xhci-brcm-v2",
 		.data = &xhci_plat_brcm,
+	}, {
+		.compatible = "brcm,bcm2711-xhci",
+		.data = &xhci_plat_brcm,
 	}, {
 		.compatible = "brcm,bcm7445-xhci",
 		.data = &xhci_plat_brcm,
-- 
GitLab


From 522c35e08b53f157ad3e51848caa861b258001e4 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Tue, 5 Dec 2023 21:05:31 +0100
Subject: [PATCH 0790/4076] ARM: dts: bcm2711: Add BCM2711 xHCI support

The BCM2711 SoC also has a mostly generic xHCI. The USB port is
currently only usable on the Compute Module 4 (e.g. via IO board).
Because DWC2 and xHCI share the same PHY, we let the bootloader
enable it on demand.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20231205200531.8232-4-wahrenst@gmx.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi |  5 +++++
 arch/arm/boot/dts/broadcom/bcm2711.dtsi     | 14 ++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
index 98817a6675b9d..d233a191c1393 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "bcm2835-rpi.dtsi"
 
+#include <dt-bindings/power/raspberrypi-power.h>
 #include <dt-bindings/reset/raspberrypi,firmware-reset.h>
 
 / {
@@ -76,3 +77,7 @@
 &vchiq {
 	interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 };
+
+&xhci {
+	power-domains = <&power RPI_POWER_DOMAIN_USB>;
+};
diff --git a/arch/arm/boot/dts/broadcom/bcm2711.dtsi b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
index 4a379a14966d8..22c7f1561344e 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
@@ -604,6 +604,20 @@
 			};
 		};
 
+		xhci: usb@7e9c0000 {
+			compatible = "brcm,bcm2711-xhci", "brcm,xhci-brcm-v2";
+			reg = <0x0 0x7e9c0000 0x100000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
+			/* DWC2 and this IP block share the same USB PHY,
+			 * enabling both at the same time results in lockups.
+			 * So keep this node disabled and let the bootloader
+			 * decide which interface should be enabled.
+			 */
+			status = "disabled";
+		};
+
 		v3d: gpu@7ec00000 {
 			compatible = "brcm,2711-v3d";
 			reg = <0x0 0x7ec00000 0x4000>,
-- 
GitLab


From c72bbf200162a3b4b9e1baedec9008d8d710b427 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:43:54 +0000
Subject: [PATCH 0791/4076] arch_topology: Make register_cpu_capacity_sysctl()
 tolerant to late CPUs

register_cpu_capacity_sysctl() adds a property to sysfs that describes
the CPUs capacity. This is done from a subsys_initcall() that assumes
all possible CPUs are registered.

With CPU hotplug, possible CPUs aren't registered until they become
present, (or for arm64 enabled). This leads to messages during boot:
| register_cpu_capacity_sysctl: too early to get CPU1 device!
and once these CPUs are added to the system, the file is missing.

Move this to a cpuhp callback, so that the file is created once
CPUs are brought online. This covers CPUs that are added late by
mechanisms like hotplug.
One observable difference is the file is now missing for offline CPUs.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R2g-00CsyV-Ss@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/arch_topology.c | 38 ++++++++++++++++++++++++------------
 1 file changed, 26 insertions(+), 12 deletions(-)

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index b741b5ba82bd6..9ccb7daee78eb 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -220,20 +220,34 @@ static DECLARE_WORK(update_topology_flags_work, update_topology_flags_workfn);
 
 static DEVICE_ATTR_RO(cpu_capacity);
 
-static int register_cpu_capacity_sysctl(void)
+static int cpu_capacity_sysctl_add(unsigned int cpu)
 {
-	int i;
-	struct device *cpu;
+	struct device *cpu_dev = get_cpu_device(cpu);
 
-	for_each_possible_cpu(i) {
-		cpu = get_cpu_device(i);
-		if (!cpu) {
-			pr_err("%s: too early to get CPU%d device!\n",
-			       __func__, i);
-			continue;
-		}
-		device_create_file(cpu, &dev_attr_cpu_capacity);
-	}
+	if (!cpu_dev)
+		return -ENOENT;
+
+	device_create_file(cpu_dev, &dev_attr_cpu_capacity);
+
+	return 0;
+}
+
+static int cpu_capacity_sysctl_remove(unsigned int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+
+	if (!cpu_dev)
+		return -ENOENT;
+
+	device_remove_file(cpu_dev, &dev_attr_cpu_capacity);
+
+	return 0;
+}
+
+static int register_cpu_capacity_sysctl(void)
+{
+	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "topology/cpu-capacity",
+			  cpu_capacity_sysctl_add, cpu_capacity_sysctl_remove);
 
 	return 0;
 }
-- 
GitLab


From d87c49377d5bbf3f5e5729c67f3892e1d2e6f661 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:00 +0000
Subject: [PATCH 0792/4076] x86: intel_epb: Don't rely on link order

intel_epb_init() is called as a subsys_initcall() to register cpuhp
callbacks. The callbacks make use of get_cpu_device() which will return
NULL unless register_cpu() has been called. register_cpu() is called
from topology_init(), which is also a subsys_initcall().

This is fragile. Moving the register_cpu() to a different
subsys_initcall()  leads to a NULL dereference during boot.

Make intel_epb_init() a late_initcall(), user-space can't provide a
policy before this point anyway.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Acked-by: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R2m-00Csyb-2S@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/kernel/cpu/intel_epb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index e4c3ba91321c9..f18d35fe27a92 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -237,4 +237,4 @@ err_out_online:
 	cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE);
 	return ret;
 }
-subsys_initcall(intel_epb_init);
+late_initcall(intel_epb_init);
-- 
GitLab


From 9aa9b4fcc311ede18adfe55e721115f7c59e60be Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:44:05 +0000
Subject: [PATCH 0793/4076] x86/topology: remove arch_*register_cpu() exports

arch_register_cpu() and arch_unregister_cpu() are not used by anything
that can be a module - they are used by drivers/base/cpu.c and
drivers/acpi/acpi_processor.c, neither of which can be a module.

Remove the exports.

Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R2r-00Csyh-7B@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/kernel/topology.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 0bab031300336..fcb62cfdf9464 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -45,13 +45,11 @@ int arch_register_cpu(int cpu)
 	xc->cpu.hotpluggable = cpu > 0;
 	return register_cpu(&xc->cpu, cpu);
 }
-EXPORT_SYMBOL(arch_register_cpu);
 
 void arch_unregister_cpu(int num)
 {
 	unregister_cpu(&per_cpu(cpu_devices, num).cpu);
 }
-EXPORT_SYMBOL(arch_unregister_cpu);
 #else /* CONFIG_HOTPLUG_CPU */
 
 int __init arch_register_cpu(int num)
-- 
GitLab


From 29d93102fd1e19024fce90995040fb3a46fd91c1 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:44:10 +0000
Subject: [PATCH 0794/4076] Loongarch: remove arch_*register_cpu() exports

arch_register_cpu() and arch_unregister_cpu() are not used by anything
that can be a module - they are used by drivers/base/cpu.c and
drivers/acpi/acpi_processor.c, neither of which can be a module.

Remove the exports.

Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R2w-00Csyn-E2@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/loongarch/kernel/topology.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c
index 3fd1660066983..ae860fe815368 100644
--- a/arch/loongarch/kernel/topology.c
+++ b/arch/loongarch/kernel/topology.c
@@ -25,7 +25,6 @@ int arch_register_cpu(int cpu)
 
 	return ret;
 }
-EXPORT_SYMBOL(arch_register_cpu);
 
 void arch_unregister_cpu(int cpu)
 {
@@ -34,7 +33,6 @@ void arch_unregister_cpu(int cpu)
 	c->hotpluggable = 0;
 	unregister_cpu(c);
 }
-EXPORT_SYMBOL(arch_unregister_cpu);
 #endif
 
 static int __init topology_init(void)
-- 
GitLab


From a02f66bb3cf475947b58dd3851b987b8ccd998c1 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:15 +0000
Subject: [PATCH 0795/4076] ACPI: Move ACPI_HOTPLUG_CPU to be disabled on arm64
 and riscv

Neither arm64 nor riscv support physical hotadd of CPUs that were not
present at boot. For arm64 much of the platform description is in static
tables which do not have update methods. arm64 does support HOTPLUG_CPU,
which is backed by a firmware interface to turn CPUs on and off.

acpi_processor_hotadd_init() and acpi_processor_remove() are for adding
and removing CPUs that were not present at boot. arm64 systems that do this
are not supported as there is currently insufficient information in the
platform description. (e.g. did the GICR get removed too?)

arm64 currently relies on the MADT enabled flag check in map_gicc_mpidr()
to prevent CPUs that were not described as present at boot from being
added to the system. Similarly, riscv relies on the same check in
map_rintc_hartid(). Both architectures also rely on the weak 'always fails'
definitions of acpi_map_cpu() and arch_register_cpu().

Subsequent changes will redefine ACPI_HOTPLUG_CPU as making possible
CPUs present. Neither arm64 nor riscv support this.

Disable ACPI_HOTPLUG_CPU for arm64 and riscv by removing 'default y' and
selecting it on the other three ACPI architectures. This allows the weak
definitions of some symbols to be removed.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R31-00Csyt-Jq@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/loongarch/Kconfig        |  1 +
 arch/x86/Kconfig              |  1 +
 drivers/acpi/Kconfig          |  1 -
 drivers/acpi/acpi_processor.c | 18 ------------------
 4 files changed, 2 insertions(+), 19 deletions(-)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index ee123820a4760..331becb2cb4f7 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -5,6 +5,7 @@ config LOONGARCH
 	select ACPI
 	select ACPI_GENERIC_GSI if ACPI
 	select ACPI_MCFG if ACPI
+	select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU
 	select ACPI_PPTT if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
 	select ARCH_BINFMT_ELF_STATE
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3762f41bb0929..dbdcfc708369a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -59,6 +59,7 @@ config X86
 	#
 	select ACPI_LEGACY_TABLES_LOOKUP	if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
+	select ACPI_HOTPLUG_CPU			if ACPI_PROCESSOR && HOTPLUG_CPU
 	select ARCH_32BIT_OFF_T			if X86_32
 	select ARCH_CLOCKSOURCE_INIT
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index f819e760ff195..a3acfc750fce0 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -310,7 +310,6 @@ config ACPI_HOTPLUG_CPU
 	bool
 	depends on ACPI_PROCESSOR && HOTPLUG_CPU
 	select ACPI_CONTAINER
-	default y
 
 config ACPI_PROCESSOR_AGGREGATOR
 	tristate "Processor Aggregator"
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 0f5218e361df5..4fe2ef54088c6 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -184,24 +184,6 @@ static void __init acpi_pcc_cpufreq_init(void) {}
 
 /* Initialization */
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
-int __weak acpi_map_cpu(acpi_handle handle,
-		phys_cpuid_t physid, u32 acpi_id, int *pcpu)
-{
-	return -ENODEV;
-}
-
-int __weak acpi_unmap_cpu(int cpu)
-{
-	return -ENODEV;
-}
-
-int __weak arch_register_cpu(int cpu)
-{
-	return -ENODEV;
-}
-
-void __weak arch_unregister_cpu(int cpu) {}
-
 static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 {
 	unsigned long long sta;
-- 
GitLab


From b0c69e1214bc20960c2ca68317b968e2a2057ed5 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:20 +0000
Subject: [PATCH 0796/4076] drivers: base: Use present CPUs in
 GENERIC_CPU_DEVICES

Three of the five ACPI architectures create sysfs entries using
register_cpu() for present CPUs, whereas arm64, riscv and all
GENERIC_CPU_DEVICES do this for possible CPUs.

Registering a CPU is what causes them to show up in sysfs.

It makes very little sense to register all possible CPUs. Registering
a CPU is what triggers the udev notifications allowing user-space to
react to newly added CPUs.

To allow all five ACPI architectures to use GENERIC_CPU_DEVICES, change
it to use for_each_present_cpu().

Making the ACPI architectures use GENERIC_CPU_DEVICES is a pre-requisite
step to centralise their register_cpu() logic, before moving it into the
ACPI processor driver. When we add support for register CPUs from ACPI
in a later patch, we will avoid registering CPUs in this path.

Of the ACPI architectures that register possible CPUs, arm64 and riscv
do not support making possible CPUs present as they use the weak 'always
fails' version of arch_register_cpu().

Only two of the eight architectures that use GENERIC_CPU_DEVICES have a
distinction between present and possible CPUs.

The following architectures use GENERIC_CPU_DEVICES but are not SMP,
so possible == present:
 * m68k
 * microblaze
 * nios2

The following architectures use GENERIC_CPU_DEVICES and consider
possible == present:
 * csky: setup_smp()
 * processor_probe() sets possible for all CPUs and present for all CPUs
   except the boot cpu, which will have been done by
   init/main.c::start_kernel().

um appears to be a subarchitecture of x86.

The remaining architecture using GENERIC_CPU_DEVICES are:
 * openrisc and hexagon:
   where smp_init_cpus() makes all CPUs < NR_CPUS possible,
   whereas smp_prepare_cpus() only makes CPUs < setup_max_cpus present.

After this change, openrisc and hexagon systems that use the max_cpus
command line argument would not see the other CPUs present in sysfs.
This should not be a problem as these CPUs can't be brought online as
_cpu_up() checks cpu_present().

After this change, only CPUs which are present appear in sysfs.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R36-00Csz0-Px@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 9ea22e165acd6..34b48f660b6bf 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -533,7 +533,7 @@ static void __init cpu_dev_register_generic(void)
 #ifdef CONFIG_GENERIC_CPU_DEVICES
 	int i;
 
-	for_each_possible_cpu(i) {
+	for_each_present_cpu(i) {
 		if (register_cpu(&per_cpu(cpu_devices, i), i))
 			panic("Failed to register CPU device");
 	}
-- 
GitLab


From 0949dd96dffec39683c6066cf8d0877cebc321ec Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:25 +0000
Subject: [PATCH 0797/4076] drivers: base: Allow parts of GENERIC_CPU_DEVICES
 to be overridden

Architectures often have extra per-cpu work that needs doing
before a CPU is registered, often to determine if a CPU is
hotpluggable.

To allow the ACPI architectures to use GENERIC_CPU_DEVICES, move
the cpu_register() call into arch_register_cpu(), which is made __weak
so architectures with extra work can override it.
This aligns with the way x86, ia64 and loongarch register hotplug CPUs
when they become present.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3B-00Csz6-Uh@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/cpu.c  | 14 ++++++++++----
 include/linux/cpu.h |  4 ++++
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 34b48f660b6bf..579064fda97b6 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -525,19 +525,25 @@ bool cpu_is_hotpluggable(unsigned int cpu)
 EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);
 
 #ifdef CONFIG_GENERIC_CPU_DEVICES
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+int __weak arch_register_cpu(int cpu)
+{
+	return register_cpu(&per_cpu(cpu_devices, cpu), cpu);
+}
 #endif
 
 static void __init cpu_dev_register_generic(void)
 {
-#ifdef CONFIG_GENERIC_CPU_DEVICES
 	int i;
 
+	if (!IS_ENABLED(CONFIG_GENERIC_CPU_DEVICES))
+		return;
+
 	for_each_present_cpu(i) {
-		if (register_cpu(&per_cpu(cpu_devices, i), i))
+		if (arch_register_cpu(i))
 			panic("Failed to register CPU device");
 	}
-#endif
 }
 
 #ifdef CONFIG_GENERIC_CPU_VULNERABILITIES
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index fc8094419084f..1e982d63eae8c 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -88,6 +88,10 @@ extern ssize_t arch_cpu_probe(const char *, size_t);
 extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 
+#ifdef CONFIG_GENERIC_CPU_DEVICES
+DECLARE_PER_CPU(struct cpu, cpu_devices);
+#endif
+
 /*
  * These states are not related to the core CPU hotplug mechanism. They are
  * used by various (sub)architectures to track internal state
-- 
GitLab


From 866ec3008691ff205b171413c52c5f1f328a2f8b Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:31 +0000
Subject: [PATCH 0798/4076] drivers: base: Implement weak arch_unregister_cpu()

Add arch_unregister_cpu() to allow the ACPI machinery to call
unregister_cpu(). This is enough for arm64, riscv and loongarch, but
needs to be overridden by x86 and ia64 who need to do more work.

CC: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3H-00CszC-2n@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/cpu.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 579064fda97b6..58bb86091b349 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -531,7 +531,14 @@ int __weak arch_register_cpu(int cpu)
 {
 	return register_cpu(&per_cpu(cpu_devices, cpu), cpu);
 }
-#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+void __weak arch_unregister_cpu(int num)
+{
+	unregister_cpu(&per_cpu(cpu_devices, num));
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+#endif /* CONFIG_GENERIC_CPU_DEVICES */
 
 static void __init cpu_dev_register_generic(void)
 {
-- 
GitLab


From bb5e44fb3be685ecb3feb120aca4269a92cc84cf Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:44:36 +0000
Subject: [PATCH 0799/4076] drivers: base: add arch_cpu_is_hotpluggable()

The differences between architecture specific implementations of
arch_register_cpu() are down to whether the CPU is hotpluggable or not.
Rather than overriding the weak version of arch_register_cpu(), provide
a function that can be used to provide this detail instead.

Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3M-00CszH-6r@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/cpu.c  | 11 ++++++++++-
 include/linux/cpu.h |  1 +
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 58bb86091b349..221ffbeb1c9be 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -527,9 +527,18 @@ EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);
 #ifdef CONFIG_GENERIC_CPU_DEVICES
 DEFINE_PER_CPU(struct cpu, cpu_devices);
 
+bool __weak arch_cpu_is_hotpluggable(int cpu)
+{
+	return false;
+}
+
 int __weak arch_register_cpu(int cpu)
 {
-	return register_cpu(&per_cpu(cpu_devices, cpu), cpu);
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+	c->hotpluggable = arch_cpu_is_hotpluggable(cpu);
+
+	return register_cpu(c, cpu);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 1e982d63eae8c..dcb89c9871640 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -80,6 +80,7 @@ extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
 				 const struct attribute_group **groups,
 				 const char *fmt, ...);
+extern bool arch_cpu_is_hotpluggable(int cpu);
 extern int arch_register_cpu(int cpu);
 extern void arch_unregister_cpu(int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
-- 
GitLab


From d631a881f1ab0091de35ae09ba48193a543666b5 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:41 +0000
Subject: [PATCH 0800/4076] drivers: base: Move cpu_dev_init() after
 node_dev_init()

NUMA systems require the node descriptions to be ready before CPUs are
registered. This is so that the node symlinks can be created in sysfs.

Currently no NUMA platform uses GENERIC_CPU_DEVICES, meaning that CPUs
are registered by arch code, instead of cpu_dev_init().

Move cpu_dev_init() after node_dev_init() so that NUMA architectures
can use GENERIC_CPU_DEVICES.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3R-00CszO-C0@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/init.c b/drivers/base/init.c
index 397eb9880cecb..c4954835128cf 100644
--- a/drivers/base/init.c
+++ b/drivers/base/init.c
@@ -35,8 +35,8 @@ void __init driver_init(void)
 	of_core_init();
 	platform_bus_init();
 	auxiliary_bus_init();
-	cpu_dev_init();
 	memory_dev_init();
 	node_dev_init();
+	cpu_dev_init();
 	container_dev_init();
 }
-- 
GitLab


From ca00f7d999a61383c3e5b2c66537a8e769dd7327 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:46 +0000
Subject: [PATCH 0801/4076] drivers: base: Print a warning instead of panic()
 when register_cpu() fails

loongarch, mips, parisc, riscv and sh all print a warning if
register_cpu() returns an error. Architectures that use
GENERIC_CPU_DEVICES call panic() instead.

Errors in this path indicate something is wrong with the firmware
description of the platform, but the kernel is able to keep running.

Downgrade this to a warning to make it easier to debug this issue.

This will allow architectures that switching over to GENERIC_CPU_DEVICES
to drop their warning, but keep the existing behaviour.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3W-00CszU-GM@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/cpu.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 221ffbeb1c9be..82b6a76125f5e 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -551,14 +551,15 @@ void __weak arch_unregister_cpu(int num)
 
 static void __init cpu_dev_register_generic(void)
 {
-	int i;
+	int i, ret;
 
 	if (!IS_ENABLED(CONFIG_GENERIC_CPU_DEVICES))
 		return;
 
 	for_each_present_cpu(i) {
-		if (arch_register_cpu(i))
-			panic("Failed to register CPU device");
+		ret = arch_register_cpu(i);
+		if (ret)
+			pr_warn("register_cpu %d failed (%d)\n", i, ret);
 	}
 }
 
-- 
GitLab


From d127db1a23c94a876557b5bf8ca8bea49e8debb6 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:51 +0000
Subject: [PATCH 0802/4076] arm64: setup: Switch over to GENERIC_CPU_DEVICES
 using arch_register_cpu()

To allow ACPI's _STA value to hide CPUs that are present, but not
available to online right now due to VMM or firmware policy, the
register_cpu() call needs to be made by the ACPI machinery when ACPI
is in use. This allows it to hide CPUs that are unavailable from sysfs.

Switching to GENERIC_CPU_DEVICES is an intermediate step to allow all
five ACPI architectures to be modified at once.

Switch over to GENERIC_CPU_DEVICES, and provide an arch_register_cpu()
that populates the hotpluggable flag. arch_register_cpu() is also the
interface the ACPI machinery expects.

The struct cpu in struct cpuinfo_arm64 is never used directly, remove
it to use the one GENERIC_CPU_DEVICES provides.

This changes the CPUs visible in sysfs from possible to present, but
on arm64 smp_prepare_cpus() ensures these are the same.

This patch also has the effect of moving the registration of CPUs from
subsys to driver core initialisation, prior to any initcalls running.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3b-00Csza-Ku@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/Kconfig           |  1 +
 arch/arm64/include/asm/cpu.h |  1 -
 arch/arm64/kernel/setup.c    | 13 ++++---------
 3 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7b071a00425d2..84bce830e365c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -132,6 +132,7 @@ config ARM64
 	select GENERIC_ARCH_TOPOLOGY
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_DEVICES
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index f3034099fd952..b1e43f56ee461 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -38,7 +38,6 @@ struct cpuinfo_32bit {
 };
 
 struct cpuinfo_arm64 {
-	struct cpu	cpu;
 	struct kobject	kobj;
 	u64		reg_ctr;
 	u64		reg_cntfrq;
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 417a8a86b2db5..165bd2c0dd5a7 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -402,19 +402,14 @@ static inline bool cpu_can_disable(unsigned int cpu)
 	return false;
 }
 
-static int __init topology_init(void)
+int arch_register_cpu(int num)
 {
-	int i;
+	struct cpu *cpu = &per_cpu(cpu_devices, num);
 
-	for_each_possible_cpu(i) {
-		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
-		cpu->hotpluggable = cpu_can_disable(i);
-		register_cpu(cpu, i);
-	}
+	cpu->hotpluggable = cpu_can_disable(num);
 
-	return 0;
+	return register_cpu(cpu, num);
 }
-subsys_initcall(topology_init);
 
 static void dump_kernel_offset(void)
 {
-- 
GitLab


From 092cfbc6b51143fd216bd55f8811f427d2ef0a0f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:44:56 +0000
Subject: [PATCH 0803/4076] arm64: convert to arch_cpu_is_hotpluggable()

Convert arm64 to use the arch_cpu_is_hotpluggable() helper rather than
arch_register_cpu().

Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3g-00Cszg-PP@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/kernel/setup.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 165bd2c0dd5a7..42c690bb2d608 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -402,13 +402,9 @@ static inline bool cpu_can_disable(unsigned int cpu)
 	return false;
 }
 
-int arch_register_cpu(int num)
+bool arch_cpu_is_hotpluggable(int num)
 {
-	struct cpu *cpu = &per_cpu(cpu_devices, num);
-
-	cpu->hotpluggable = cpu_can_disable(num);
-
-	return register_cpu(cpu, num);
+	return cpu_can_disable(num);
 }
 
 static void dump_kernel_offset(void)
-- 
GitLab


From 5b95f94c3b9f12adf27e970d411e8a744e95cabf Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:45:01 +0000
Subject: [PATCH 0804/4076] x86/topology: Switch over to GENERIC_CPU_DEVICES

Now that GENERIC_CPU_DEVICES calls arch_register_cpu(), which can be
overridden by the arch code, switch over to this to allow common code
to choose when the register_cpu() call is made.

x86's struct cpus come from struct x86_cpu, which has no other members
or users. Remove this and use the version defined by common code.

This is an intermediate step to the logic being moved to drivers/acpi,
where GENERIC_CPU_DEVICES will do the work when booting with acpi=off.

This patch also has the effect of moving the registration of CPUs from
subsys to driver core initialisation, prior to any initcalls running.

----
Changes since RFC:
 * Fixed the second copy of arch_register_cpu() used for non-hotplug
Changes since RFC v2:
 * Remove duplicate of the weak generic arch_register_cpu(), spotted
   by Jonathan Cameron. Add note about initialisation order change.
Changes since RFC v3:
 * Adapt to removal of EXPORT_SYMBOL()s

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3l-00Cszm-UA@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/Kconfig           |  1 +
 arch/x86/include/asm/cpu.h |  4 ----
 arch/x86/kernel/topology.c | 27 ++++-----------------------
 3 files changed, 5 insertions(+), 27 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index dbdcfc708369a..8330c4ac26b32 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -148,6 +148,7 @@ config X86
 	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_DEVICES
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_ENTRY
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index fecc4fe1d68af..f8f9a9b793958 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -23,10 +23,6 @@ static inline void prefill_possible_map(void) {}
 
 #endif /* CONFIG_SMP */
 
-struct x86_cpu {
-	struct cpu cpu;
-};
-
 #ifdef CONFIG_HOTPLUG_CPU
 extern void soft_restart_cpu(void);
 #endif
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index fcb62cfdf9464..c2ed3145a93ba 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -35,36 +35,17 @@
 #include <asm/io_apic.h>
 #include <asm/cpu.h>
 
-static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
-
 #ifdef CONFIG_HOTPLUG_CPU
 int arch_register_cpu(int cpu)
 {
-	struct x86_cpu *xc = per_cpu_ptr(&cpu_devices, cpu);
+	struct cpu *c = per_cpu_ptr(&cpu_devices, cpu);
 
-	xc->cpu.hotpluggable = cpu > 0;
-	return register_cpu(&xc->cpu, cpu);
+	c->hotpluggable = cpu > 0;
+	return register_cpu(c, cpu);
 }
 
 void arch_unregister_cpu(int num)
 {
-	unregister_cpu(&per_cpu(cpu_devices, num).cpu);
-}
-#else /* CONFIG_HOTPLUG_CPU */
-
-int __init arch_register_cpu(int num)
-{
-	return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
+	unregister_cpu(&per_cpu(cpu_devices, num));
 }
 #endif /* CONFIG_HOTPLUG_CPU */
-
-static int __init topology_init(void)
-{
-	int i;
-
-	for_each_present_cpu(i)
-		arch_register_cpu(i);
-
-	return 0;
-}
-subsys_initcall(topology_init);
-- 
GitLab


From b0b26bc580de555a504d7eed3866fca607bf1c1f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:45:07 +0000
Subject: [PATCH 0805/4076] x86/topology: use weak version of
 arch_unregister_cpu()

Since the x86 version of arch_unregister_cpu() is the same as the weak
version, drop the x86 specific version.

Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3r-00Cszs-2R@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/kernel/topology.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index c2ed3145a93ba..211863cb5b816 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -43,9 +43,4 @@ int arch_register_cpu(int cpu)
 	c->hotpluggable = cpu > 0;
 	return register_cpu(c, cpu);
 }
-
-void arch_unregister_cpu(int num)
-{
-	unregister_cpu(&per_cpu(cpu_devices, num));
-}
 #endif /* CONFIG_HOTPLUG_CPU */
-- 
GitLab


From e850a5c406450ae040d09c7b4161d6e75eff2a25 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:45:12 +0000
Subject: [PATCH 0806/4076] x86/topology: convert to use
 arch_cpu_is_hotpluggable()

Convert x86 to use the arch_cpu_is_hotpluggable() helper rather than
arch_register_cpu().

Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3w-00Cszy-6k@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/kernel/topology.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 211863cb5b816..d42c28b8bfd80 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -36,11 +36,8 @@
 #include <asm/cpu.h>
 
 #ifdef CONFIG_HOTPLUG_CPU
-int arch_register_cpu(int cpu)
+bool arch_cpu_is_hotpluggable(int cpu)
 {
-	struct cpu *c = per_cpu_ptr(&cpu_devices, cpu);
-
-	c->hotpluggable = cpu > 0;
-	return register_cpu(c, cpu);
+	return cpu > 0;
 }
 #endif /* CONFIG_HOTPLUG_CPU */
-- 
GitLab


From db3ba29a8315d89736b8af5c1ad945c9967d7655 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:45:17 +0000
Subject: [PATCH 0807/4076] LoongArch: Switch over to GENERIC_CPU_DEVICES

Now that GENERIC_CPU_DEVICES calls arch_register_cpu(), which can be
overridden by the arch code, switch over to this to allow common code
to choose when the register_cpu() call is made.

This allows topology_init() to be removed.

This is an intermediate step to the logic being moved to drivers/acpi,
where GENERIC_CPU_DEVICES will do the work when booting with acpi=off.

This is a subtle change. Originally:
- on boot, topology_init() would have marked present CPUs that
  io_master() is true for as hotplug-incapable.
- if a CPU is hotplugged that is an io_master(), it can later be
  hot-unplugged.

The new behaviour is that any CPU that io_master() is true for will
now always be marked as hotplug-incapable, thus even if it was
hotplugged, it can no longer be hot-unplugged.

This patch also has the effect of moving the registration of CPUs from
subsys to driver core initialisation, prior to any initcalls running.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R41-00Ct04-Bg@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/loongarch/Kconfig           |  1 +
 arch/loongarch/kernel/topology.c | 29 ++---------------------------
 2 files changed, 3 insertions(+), 27 deletions(-)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 331becb2cb4f7..15d05dd2b7f3d 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -72,6 +72,7 @@ config LOONGARCH
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_DEVICES
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY
 	select GENERIC_IOREMAP if !ARCH_IOREMAP
diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c
index ae860fe815368..7dfb46c68f582 100644
--- a/arch/loongarch/kernel/topology.c
+++ b/arch/loongarch/kernel/topology.c
@@ -10,20 +10,13 @@
 
 #include <acpi/processor.h>
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
-
 #ifdef CONFIG_HOTPLUG_CPU
 int arch_register_cpu(int cpu)
 {
-	int ret;
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
 
-	c->hotpluggable = 1;
-	ret = register_cpu(c, cpu);
-	if (ret < 0)
-		pr_warn("register_cpu %d failed (%d)\n", cpu, ret);
-
-	return ret;
+	c->hotpluggable = !io_master(cpu);
+	return register_cpu(c, cpu);
 }
 
 void arch_unregister_cpu(int cpu)
@@ -34,21 +27,3 @@ void arch_unregister_cpu(int cpu)
 	unregister_cpu(c);
 }
 #endif
-
-static int __init topology_init(void)
-{
-	int i, ret;
-
-	for_each_present_cpu(i) {
-		struct cpu *c = &per_cpu(cpu_devices, i);
-
-		c->hotpluggable = !io_master(i);
-		ret = register_cpu(c, i);
-		if (ret < 0)
-			pr_warn("topology_init: register_cpu %d failed (%d)\n", i, ret);
-	}
-
-	return 0;
-}
-
-subsys_initcall(topology_init);
-- 
GitLab


From 0d122fb60046cd888877a6029cc23863d4a1b9e3 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:45:22 +0000
Subject: [PATCH 0808/4076] LoongArch: Use the __weak version of
 arch_unregister_cpu()

LoongArch provides its own arch_unregister_cpu(). This clears the
hotpluggable flag, then unregisters the CPU.

It isn't necessary to clear the hotpluggable flag when unregistering
a cpu. unregister_cpu() writes NULL to the percpu cpu_sys_devices
pointer, meaning cpu_is_hotpluggable() will return false, as
get_cpu_device() has returned NULL.

Remove arch_unregister_cpu() and use the __weak version.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R46-00Ct0A-GJ@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/loongarch/kernel/topology.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c
index 7dfb46c68f582..866c2c9ef6ab2 100644
--- a/arch/loongarch/kernel/topology.c
+++ b/arch/loongarch/kernel/topology.c
@@ -18,12 +18,4 @@ int arch_register_cpu(int cpu)
 	c->hotpluggable = !io_master(cpu);
 	return register_cpu(c, cpu);
 }
-
-void arch_unregister_cpu(int cpu)
-{
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
-
-	c->hotpluggable = 0;
-	unregister_cpu(c);
-}
 #endif
-- 
GitLab


From 13f9f0361c2e64f0dadb7964bfad11bf0a6fb7ab Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:45:27 +0000
Subject: [PATCH 0809/4076] LoongArch: convert to use
 arch_cpu_is_hotpluggable()

Convert loongarch to use the arch_cpu_is_hotpluggable() helper rather
than arch_register_cpu(). Also remove the export as nothing should be
using arch_register_cpu() outside of the core kernel/acpi code.

Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R4B-00Ct0G-Kk@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/loongarch/kernel/topology.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c
index 866c2c9ef6ab2..75d5c51a7cd3d 100644
--- a/arch/loongarch/kernel/topology.c
+++ b/arch/loongarch/kernel/topology.c
@@ -11,11 +11,8 @@
 #include <acpi/processor.h>
 
 #ifdef CONFIG_HOTPLUG_CPU
-int arch_register_cpu(int cpu)
+bool arch_cpu_is_hotpluggable(int cpu)
 {
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
-
-	c->hotpluggable = !io_master(cpu);
-	return register_cpu(c, cpu);
+	return !io_master(cpu);
 }
 #endif
-- 
GitLab


From 96cf2036514acec9bee7c25ca61badc64820d734 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:45:32 +0000
Subject: [PATCH 0810/4076] riscv: Switch over to GENERIC_CPU_DEVICES

Now that GENERIC_CPU_DEVICES calls arch_register_cpu(), which can be
overridden by the arch code, switch over to this to allow common code
to choose when the register_cpu() call is made.

This allows topology_init() to be removed.

This is an intermediate step to the logic being moved to drivers/acpi,
where GENERIC_CPU_DEVICES will do the work when booting with acpi=off.

This patch also has the effect of moving the registration of CPUs from
subsys to driver core initialisation, prior to any initcalls running.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R4G-00Ct0M-PS@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/riscv/Kconfig        |  1 +
 arch/riscv/kernel/setup.c | 19 ++++---------------
 2 files changed, 5 insertions(+), 15 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a6..162425cb9739f 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -71,6 +71,7 @@ config RISCV
 	select GENERIC_ARCH_TOPOLOGY
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CPU_DEVICES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 535a837de55d1..b3a0aa2b78d5b 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -51,7 +51,6 @@ atomic_t hart_lottery __section(".sdata")
 #endif
 ;
 unsigned long boot_cpu_hartid;
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 /*
  * Place kernel memory regions on the resource tree so that
@@ -299,23 +298,13 @@ void __init setup_arch(char **cmdline_p)
 	riscv_user_isa_enable();
 }
 
-static int __init topology_init(void)
+int arch_register_cpu(int cpu)
 {
-	int i, ret;
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
 
-	for_each_possible_cpu(i) {
-		struct cpu *cpu = &per_cpu(cpu_devices, i);
-
-		cpu->hotpluggable = cpu_has_hotplug(i);
-		ret = register_cpu(cpu, i);
-		if (unlikely(ret))
-			pr_warn("Warning: %s: register_cpu %d failed (%d)\n",
-			       __func__, i, ret);
-	}
-
-	return 0;
+	c->hotpluggable = cpu_has_hotplug(cpu);
+	return register_cpu(c, cpu);
 }
-subsys_initcall(topology_init);
 
 void free_initmem(void)
 {
-- 
GitLab


From 00bf4641201092fc06aa51f7dcf45d1ea4d3d4f7 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:45:37 +0000
Subject: [PATCH 0811/4076] riscv: convert to use arch_cpu_is_hotpluggable()

Convert riscv to use the arch_cpu_is_hotpluggable() helper rather than
arch_register_cpu().

Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com> # On HiFive Unmatched
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R4L-00Ct0d-To@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/riscv/kernel/setup.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index b3a0aa2b78d5b..7493fafbe4cbb 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -298,12 +298,9 @@ void __init setup_arch(char **cmdline_p)
 	riscv_user_isa_enable();
 }
 
-int arch_register_cpu(int cpu)
+bool arch_cpu_is_hotpluggable(int cpu)
 {
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
-
-	c->hotpluggable = cpu_has_hotplug(cpu);
-	return register_cpu(c, cpu);
+	return cpu_has_hotplug(cpu);
 }
 
 void free_initmem(void)
-- 
GitLab


From eb2eac0c7b6180332ced94d2979f3d3c7d22aaff Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 20 Nov 2023 16:04:20 -0800
Subject: [PATCH 0812/4076] perf evsel: Fallback to "task-clock" when not
 system wide

When the "cycles" event isn't available evsel will fallback to the
"cpu-clock" software event.

"task-clock" is similar to "cpu-clock" but only runs when the process is
running.

Falling back to "cpu-clock" when not system wide leads to confusion, by
falling back to "task-clock" it is hoped the confusion is less.

Pass the target to determine if "task-clock" is more appropriate.

Update a nearby comment and debug string for the change.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ajay Kaher <akaher@vmware.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Makhalov <amakhalov@vmware.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231121000420.368075-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c |  2 +-
 tools/perf/builtin-stat.c   |  2 +-
 tools/perf/builtin-top.c    |  2 +-
 tools/perf/util/evsel.c     | 18 ++++++++++--------
 tools/perf/util/evsel.h     |  3 ++-
 5 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9b4f3805ca92f..db814eadc16b9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1360,7 +1360,7 @@ static int record__open(struct record *rec)
 	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) {
-			if (evsel__fallback(pos, errno, msg, sizeof(msg))) {
+			if (evsel__fallback(pos, &opts->target, errno, msg, sizeof(msg))) {
 				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a3af805a1d572..d8e5d6f7a87a6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -653,7 +653,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 		if ((evsel__leader(counter) != counter) ||
 		    !(counter->core.leader->nr_members > 1))
 			return COUNTER_SKIP;
-	} else if (evsel__fallback(counter, errno, msg, sizeof(msg))) {
+	} else if (evsel__fallback(counter, &target, errno, msg, sizeof(msg))) {
 		if (verbose > 0)
 			ui__warning("%s\n", msg);
 		return COUNTER_RETRY;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ea8c7eca5eeed..1e42bd1c7d5a5 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1044,7 +1044,7 @@ try_again:
 			    perf_top_overwrite_fallback(top, counter))
 				goto try_again;
 
-			if (evsel__fallback(counter, errno, msg, sizeof(msg))) {
+			if (evsel__fallback(counter, &opts->target, errno, msg, sizeof(msg))) {
 				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a5da74e3a517b..532f34d9fcb50 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2853,7 +2853,8 @@ u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const
 
 #endif
 
-bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize)
+bool evsel__fallback(struct evsel *evsel, struct target *target, int err,
+		     char *msg, size_t msgsize)
 {
 	int paranoid;
 
@@ -2861,18 +2862,19 @@ bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize)
 	    evsel->core.attr.type   == PERF_TYPE_HARDWARE &&
 	    evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) {
 		/*
-		 * If it's cycles then fall back to hrtimer based
-		 * cpu-clock-tick sw counter, which is always available even if
-		 * no PMU support.
+		 * If it's cycles then fall back to hrtimer based cpu-clock sw
+		 * counter, which is always available even if no PMU support.
 		 *
 		 * PPC returns ENXIO until 2.6.37 (behavior changed with commit
 		 * b0a873e).
 		 */
-		scnprintf(msg, msgsize, "%s",
-"The cycles event is not supported, trying to fall back to cpu-clock-ticks");
-
 		evsel->core.attr.type   = PERF_TYPE_SOFTWARE;
-		evsel->core.attr.config = PERF_COUNT_SW_CPU_CLOCK;
+		evsel->core.attr.config = target__has_cpu(target)
+			? PERF_COUNT_SW_CPU_CLOCK
+			: PERF_COUNT_SW_TASK_CLOCK;
+		scnprintf(msg, msgsize,
+			"The cycles event is not supported, trying to fall back to %s",
+			target__has_cpu(target) ? "cpu-clock" : "task-clock");
 
 		zfree(&evsel->name);
 		return true;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index f19ac9f027efc..efbb6e848287f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -460,7 +460,8 @@ static inline bool evsel__is_clock(const struct evsel *evsel)
 	       evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
-bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize);
+bool evsel__fallback(struct evsel *evsel, struct target *target, int err,
+		     char *msg, size_t msgsize);
 int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			 int err, char *msg, size_t size);
 
-- 
GitLab


From 030ac3cad28992ae9099a857848861053273cc8f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 27 Nov 2023 14:08:20 -0800
Subject: [PATCH 0813/4076] perf record: Be lazier in allocating lost samples
 buffer

Wait until a lost sample occurs to allocate the lost samples buffer,
often the buffer isn't necessary. This saves a 64kb allocation and
5.3kb of peak memory consumption.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231127220902.1315692-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index db814eadc16b9..eb5a398ddb1d8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1924,21 +1924,13 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
 static void record__read_lost_samples(struct record *rec)
 {
 	struct perf_session *session = rec->session;
-	struct perf_record_lost_samples *lost;
+	struct perf_record_lost_samples *lost = NULL;
 	struct evsel *evsel;
 
 	/* there was an error during record__open */
 	if (session->evlist == NULL)
 		return;
 
-	lost = zalloc(PERF_SAMPLE_MAX_SIZE);
-	if (lost == NULL) {
-		pr_debug("Memory allocation failed\n");
-		return;
-	}
-
-	lost->header.type = PERF_RECORD_LOST_SAMPLES;
-
 	evlist__for_each_entry(session->evlist, evsel) {
 		struct xyarray *xy = evsel->core.sample_id;
 		u64 lost_count;
@@ -1961,6 +1953,14 @@ static void record__read_lost_samples(struct record *rec)
 				}
 
 				if (count.lost) {
+					if (!lost) {
+						lost = zalloc(PERF_SAMPLE_MAX_SIZE);
+						if (!lost) {
+							pr_debug("Memory allocation failed\n");
+							return;
+						}
+						lost->header.type = PERF_RECORD_LOST_SAMPLES;
+					}
 					__record__save_lost_samples(rec, evsel, lost,
 								    x, y, count.lost, 0);
 				}
@@ -1968,9 +1968,18 @@ static void record__read_lost_samples(struct record *rec)
 		}
 
 		lost_count = perf_bpf_filter__lost_count(evsel);
-		if (lost_count)
+		if (lost_count) {
+			if (!lost) {
+				lost = zalloc(PERF_SAMPLE_MAX_SIZE);
+				if (!lost) {
+					pr_debug("Memory allocation failed\n");
+					return;
+				}
+				lost->header.type = PERF_RECORD_LOST_SAMPLES;
+			}
 			__record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count,
 						    PERF_RECORD_MISC_LOST_SAMPLES_BPF);
+		}
 	}
 out:
 	free(lost);
-- 
GitLab


From d0acce68285e8645038a72c6792483160ca36e5a Mon Sep 17 00:00:00 2001
From: Chengen Du <chengen.du@canonical.com>
Date: Thu, 30 Nov 2023 21:57:23 +0800
Subject: [PATCH 0814/4076] perf symbols: Parse NOTE segments until the build
 id is found

In the ELF file, multiple NOTE segments may exist.
To locate the build id, the process shall persist
in parsing NOTE segments until the build id is found.

Signed-off-by: Chengen Du <chengen.du@canonical.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231130135723.17562-1-chengen.du@canonical.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/symbol-minimal.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index a81a14769bd10..1da8b713509c5 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -159,9 +159,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 				goto out_free;
 
 			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0)
+			if (ret == 0) {
 				ret = bid->size;
-			break;
+				break;
+			}
 		}
 	} else {
 		Elf64_Ehdr ehdr;
@@ -210,9 +211,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 				goto out_free;
 
 			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0)
+			if (ret == 0) {
 				ret = bid->size;
-			break;
+				break;
+			}
 		}
 	}
 out_free:
-- 
GitLab


From c39de951282df9a60ef70664e4378d88006b2670 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:04:53 +0300
Subject: [PATCH 0815/4076] fs/ntfs3: Improve alternative boot processing

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/super.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 9153dffde950c..09d61c6c90aaf 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -866,6 +866,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
 	u16 fn, ao;
 	u8 cluster_bits;
 	u32 boot_off = 0;
+	sector_t boot_block = 0;
 	const char *hint = "Primary boot";
 
 	/* Save original dev_size. Used with alternative boot. */
@@ -873,11 +874,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
 
 	sbi->volume.blocks = dev_size >> PAGE_SHIFT;
 
-	bh = ntfs_bread(sb, 0);
+read_boot:
+	bh = ntfs_bread(sb, boot_block);
 	if (!bh)
-		return -EIO;
+		return boot_block ? -EINVAL : -EIO;
 
-check_boot:
 	err = -EINVAL;
 
 	/* Corrupted image; do not read OOB */
@@ -1108,26 +1109,24 @@ check_boot:
 	}
 
 out:
-	if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) {
+	brelse(bh);
+
+	if (err == -EINVAL && !boot_block && dev_size0 > PAGE_SHIFT) {
 		u32 block_size = min_t(u32, sector_size, PAGE_SIZE);
 		u64 lbo = dev_size0 - sizeof(*boot);
 
-		/*
-	 	 * Try alternative boot (last sector)
-		 */
-		brelse(bh);
-
-		sb_set_blocksize(sb, block_size);
-		bh = ntfs_bread(sb, lbo >> blksize_bits(block_size));
-		if (!bh)
-			return -EINVAL;
-
+		boot_block = lbo >> blksize_bits(block_size);
 		boot_off = lbo & (block_size - 1);
-		hint = "Alternative boot";
-		dev_size = dev_size0; /* restore original size. */
-		goto check_boot;
+		if (boot_block && block_size >= boot_off + sizeof(*boot)) {
+			/*
+			 * Try alternative boot (last sector)
+			 */
+			sb_set_blocksize(sb, block_size);
+			hint = "Alternative boot";
+			dev_size = dev_size0; /* restore original size. */
+			goto read_boot;
+		}
 	}
-	brelse(bh);
 
 	return err;
 }
-- 
GitLab


From 22457c047ed971f2f2e33be593ddfabd9639a409 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:17:07 +0300
Subject: [PATCH 0816/4076] fs/ntfs3: Modified fix directory element type
 detection

Unfortunately reparse attribute is used for many purposes (several dozens).
It is not possible here to know is this name symlink or not.
To get exactly the type of name we should to open inode (read mft).
getattr for opened file (fstat) correctly returns symlink.

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/dir.c | 30 +++++++++++++++++++++++++-----
 1 file changed, 25 insertions(+), 5 deletions(-)

diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index ec0566b322d5d..22ede4da04502 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -309,11 +309,31 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 		return 0;
 	}
 
-	/* NTFS: symlinks are "dir + reparse" or "file + reparse" */
-	if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT)
-		dt_type = DT_LNK;
-	else
-		dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+	/*
+	 * NTFS: symlinks are "dir + reparse" or "file + reparse"
+	 * Unfortunately reparse attribute is used for many purposes (several dozens).
+	 * It is not possible here to know is this name symlink or not.
+	 * To get exactly the type of name we should to open inode (read mft).
+	 * getattr for opened file (fstat) correctly returns symlink.
+	 */
+	dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+
+	/*
+	 * It is not reliable to detect the type of name using duplicated information
+	 * stored in parent directory.
+	 * The only correct way to get the type of name - read MFT record and find ATTR_STD.
+	 * The code below is not good idea.
+	 * It does additional locks/reads just to get the type of name.
+	 * Should we use additional mount option to enable branch below?
+	 */
+	if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) &&
+	    ino != ni->mi.rno) {
+		struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL);
+		if (!IS_ERR_OR_NULL(inode)) {
+			dt_type = fs_umode_to_dtype(inode->i_mode);
+			iput(inode);
+		}
+	}
 
 	return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
 }
-- 
GitLab


From 6a799c928b78b14999b7705c4cca0f88e297fe96 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:24:33 +0300
Subject: [PATCH 0817/4076] fs/ntfs3: Improve ntfs_dir_count

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/dir.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 22ede4da04502..726122ecd39b4 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -515,11 +515,9 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 	struct INDEX_HDR *hdr;
 	const struct ATTR_FILE_NAME *fname;
 	u32 e_size, off, end;
-	u64 vbo = 0;
 	size_t drs = 0, fles = 0, bit = 0;
-	loff_t i_size = ni->vfs_inode.i_size;
 	struct indx_node *node = NULL;
-	u8 index_bits = ni->dir.index_bits;
+	size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits;
 
 	if (is_empty)
 		*is_empty = true;
@@ -563,7 +561,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 				fles += 1;
 		}
 
-		if (vbo >= i_size)
+		if (bit >= max_indx)
 			goto out;
 
 		err = indx_used_bit(&ni->dir, ni, &bit);
@@ -573,8 +571,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 		if (bit == MINUS_ONE_T)
 			goto out;
 
-		vbo = (u64)bit << index_bits;
-		if (vbo >= i_size)
+		if (bit >= max_indx)
 			goto out;
 
 		err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits,
@@ -584,7 +581,6 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 
 		hdr = &node->index->ihdr;
 		bit += 1;
-		vbo = (u64)bit << ni->dir.idx2vbn_bits;
 	}
 
 out:
-- 
GitLab


From 1918c10e137eae266b8eb0ab1cc14421dcb0e3e2 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:26:31 +0300
Subject: [PATCH 0818/4076] fs/ntfs3: Correct hard links updating when dealing
 with DOS names

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/record.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index 53629b1f65e99..7b6423584eaee 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -535,8 +535,20 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi,
 		return false;
 
 	if (ni && is_attr_indexed(attr)) {
-		le16_add_cpu(&ni->mi.mrec->hard_links, -1);
-		ni->mi.dirty = true;
+		u16 links = le16_to_cpu(ni->mi.mrec->hard_links);
+		struct ATTR_FILE_NAME *fname =
+			attr->type != ATTR_NAME ?
+				NULL :
+				resident_data_ex(attr,
+						 SIZEOF_ATTRIBUTE_FILENAME);
+		if (fname && fname->type == FILE_NAME_DOS) {
+			/* Do not decrease links count deleting DOS name. */
+		} else if (!links) {
+			/* minor error. Not critical. */
+		} else {
+			ni->mi.mrec->hard_links = cpu_to_le16(links - 1);
+			ni->mi.dirty = true;
+		}
 	}
 
 	used -= asize;
-- 
GitLab


From 85ba2a75faee759809a7e43b4c103ac59bac1026 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:34:24 +0300
Subject: [PATCH 0819/4076] fs/ntfs3: Print warning while fixing hard links
 count

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 5e3d713749185..fa6c7965473c8 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -412,7 +412,6 @@ end_enum:
 		goto out;
 
 	if (!is_match && name) {
-		/* Reuse rec as buffer for ascii name. */
 		err = -ENOENT;
 		goto out;
 	}
@@ -427,6 +426,7 @@ end_enum:
 
 	if (names != le16_to_cpu(rec->hard_links)) {
 		/* Correct minor error on the fly. Do not mark inode as dirty. */
+		ntfs_inode_warn(inode, "Correct links count -> %u.", names);
 		rec->hard_links = cpu_to_le16(names);
 		ni->mi.dirty = true;
 	}
-- 
GitLab


From 865e7a7700d930d34895a70f8af2eb4e778a5b0e Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:42:04 +0300
Subject: [PATCH 0820/4076] fs/ntfs3: Reduce stack usage

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/fslog.c | 218 +++++++++++++++++++++--------------------------
 1 file changed, 98 insertions(+), 120 deletions(-)

diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 98ccb66508583..7dbb000fc6911 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -974,6 +974,16 @@ skip_looking:
 	return e;
 }
 
+struct restart_info {
+	u64 last_lsn;
+	struct RESTART_HDR *r_page;
+	u32 vbo;
+	bool chkdsk_was_run;
+	bool valid_page;
+	bool initialized;
+	bool restart;
+};
+
 #define RESTART_SINGLE_PAGE_IO cpu_to_le16(0x0001)
 
 #define NTFSLOG_WRAPPED 0x00000001
@@ -987,6 +997,7 @@ struct ntfs_log {
 	struct ntfs_inode *ni;
 
 	u32 l_size;
+	u32 orig_file_size;
 	u32 sys_page_size;
 	u32 sys_page_mask;
 	u32 page_size;
@@ -1040,6 +1051,8 @@ struct ntfs_log {
 
 	struct CLIENT_ID client_id;
 	u32 client_undo_commit;
+
+	struct restart_info rst_info, rst_info2;
 };
 
 static inline u32 lsn_to_vbo(struct ntfs_log *log, const u64 lsn)
@@ -1105,16 +1118,6 @@ static inline bool verify_client_lsn(struct ntfs_log *log,
 	       lsn <= le64_to_cpu(log->ra->current_lsn) && lsn;
 }
 
-struct restart_info {
-	u64 last_lsn;
-	struct RESTART_HDR *r_page;
-	u32 vbo;
-	bool chkdsk_was_run;
-	bool valid_page;
-	bool initialized;
-	bool restart;
-};
-
 static int read_log_page(struct ntfs_log *log, u32 vbo,
 			 struct RECORD_PAGE_HDR **buffer, bool *usa_error)
 {
@@ -1176,7 +1179,7 @@ out:
  * restart page header. It will stop the first time we find a
  * valid page header.
  */
-static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
+static int log_read_rst(struct ntfs_log *log, bool first,
 			struct restart_info *info)
 {
 	u32 skip, vbo;
@@ -1192,7 +1195,7 @@ static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
 	}
 
 	/* Loop continuously until we succeed. */
-	for (; vbo < l_size; vbo = 2 * vbo + skip, skip = 0) {
+	for (; vbo < log->l_size; vbo = 2 * vbo + skip, skip = 0) {
 		bool usa_error;
 		bool brst, bchk;
 		struct RESTART_AREA *ra;
@@ -1285,22 +1288,17 @@ check_result:
 /*
  * Ilog_init_pg_hdr - Init @log from restart page header.
  */
-static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
-			    u32 page_size, u16 major_ver, u16 minor_ver)
+static void log_init_pg_hdr(struct ntfs_log *log, u16 major_ver, u16 minor_ver)
 {
-	log->sys_page_size = sys_page_size;
-	log->sys_page_mask = sys_page_size - 1;
-	log->page_size = page_size;
-	log->page_mask = page_size - 1;
-	log->page_bits = blksize_bits(page_size);
+	log->sys_page_size = log->page_size;
+	log->sys_page_mask = log->page_mask;
 
 	log->clst_per_page = log->page_size >> log->ni->mi.sbi->cluster_bits;
 	if (!log->clst_per_page)
 		log->clst_per_page = 1;
 
-	log->first_page = major_ver >= 2 ?
-				  0x22 * page_size :
-				  ((sys_page_size << 1) + (page_size << 1));
+	log->first_page = major_ver >= 2 ? 0x22 * log->page_size :
+					   4 * log->page_size;
 	log->major_ver = major_ver;
 	log->minor_ver = minor_ver;
 }
@@ -1308,12 +1306,11 @@ static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
 /*
  * log_create - Init @log in cases when we don't have a restart area to use.
  */
-static void log_create(struct ntfs_log *log, u32 l_size, const u64 last_lsn,
+static void log_create(struct ntfs_log *log, const u64 last_lsn,
 		       u32 open_log_count, bool wrapped, bool use_multi_page)
 {
-	log->l_size = l_size;
 	/* All file offsets must be quadword aligned. */
-	log->file_data_bits = blksize_bits(l_size) - 3;
+	log->file_data_bits = blksize_bits(log->l_size) - 3;
 	log->seq_num_mask = (8 << log->file_data_bits) - 1;
 	log->seq_num_bits = sizeof(u64) * 8 - log->file_data_bits;
 	log->seq_num = (last_lsn >> log->file_data_bits) + 2;
@@ -3720,10 +3717,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 	struct ntfs_log *log;
 
-	struct restart_info rst_info, rst_info2;
-	u64 rec_lsn, ra_lsn, checkpt_lsn = 0, rlsn = 0;
+	u64 rec_lsn, checkpt_lsn = 0, rlsn = 0;
 	struct ATTR_NAME_ENTRY *attr_names = NULL;
-	struct ATTR_NAME_ENTRY *ane;
 	struct RESTART_TABLE *dptbl = NULL;
 	struct RESTART_TABLE *trtbl = NULL;
 	const struct RESTART_TABLE *rt;
@@ -3741,9 +3736,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	struct TRANSACTION_ENTRY *tr;
 	struct DIR_PAGE_ENTRY *dp;
 	u32 i, bytes_per_attr_entry;
-	u32 l_size = ni->vfs_inode.i_size;
-	u32 orig_file_size = l_size;
-	u32 page_size, vbo, tail, off, dlen;
+	u32 vbo, tail, off, dlen;
 	u32 saved_len, rec_len, transact_id;
 	bool use_second_page;
 	struct RESTART_AREA *ra2, *ra = NULL;
@@ -3758,52 +3751,50 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	u16 t16;
 	u32 t32;
 
-	/* Get the size of page. NOTE: To replay we can use default page. */
-#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2
-	page_size = norm_file_page(PAGE_SIZE, &l_size, true);
-#else
-	page_size = norm_file_page(PAGE_SIZE, &l_size, false);
-#endif
-	if (!page_size)
-		return -EINVAL;
-
 	log = kzalloc(sizeof(struct ntfs_log), GFP_NOFS);
 	if (!log)
 		return -ENOMEM;
 
 	log->ni = ni;
-	log->l_size = l_size;
-	log->one_page_buf = kmalloc(page_size, GFP_NOFS);
+	log->l_size = log->orig_file_size = ni->vfs_inode.i_size;
+
+	/* Get the size of page. NOTE: To replay we can use default page. */
+#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2
+	log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, true);
+#else
+	log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, false);
+#endif
+	if (!log->page_size) {
+		err = -EINVAL;
+		goto out;
+	}
 
+	log->one_page_buf = kmalloc(log->page_size, GFP_NOFS);
 	if (!log->one_page_buf) {
 		err = -ENOMEM;
 		goto out;
 	}
 
-	log->page_size = page_size;
-	log->page_mask = page_size - 1;
-	log->page_bits = blksize_bits(page_size);
+	log->page_mask = log->page_size - 1;
+	log->page_bits = blksize_bits(log->page_size);
 
 	/* Look for a restart area on the disk. */
-	memset(&rst_info, 0, sizeof(struct restart_info));
-	err = log_read_rst(log, l_size, true, &rst_info);
+	err = log_read_rst(log, true, &log->rst_info);
 	if (err)
 		goto out;
 
 	/* remember 'initialized' */
-	*initialized = rst_info.initialized;
+	*initialized = log->rst_info.initialized;
 
-	if (!rst_info.restart) {
-		if (rst_info.initialized) {
+	if (!log->rst_info.restart) {
+		if (log->rst_info.initialized) {
 			/* No restart area but the file is not initialized. */
 			err = -EINVAL;
 			goto out;
 		}
 
-		log_init_pg_hdr(log, page_size, page_size, 1, 1);
-		log_create(log, l_size, 0, get_random_u32(), false, false);
-
-		log->ra = ra;
+		log_init_pg_hdr(log, 1, 1);
+		log_create(log, 0, get_random_u32(), false, false);
 
 		ra = log_create_ra(log);
 		if (!ra) {
@@ -3820,25 +3811,26 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	 * If the restart offset above wasn't zero then we won't
 	 * look for a second restart.
 	 */
-	if (rst_info.vbo)
+	if (log->rst_info.vbo)
 		goto check_restart_area;
 
-	memset(&rst_info2, 0, sizeof(struct restart_info));
-	err = log_read_rst(log, l_size, false, &rst_info2);
+	err = log_read_rst(log, false, &log->rst_info2);
 	if (err)
 		goto out;
 
 	/* Determine which restart area to use. */
-	if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn)
+	if (!log->rst_info2.restart ||
+	    log->rst_info2.last_lsn <= log->rst_info.last_lsn)
 		goto use_first_page;
 
 	use_second_page = true;
 
-	if (rst_info.chkdsk_was_run && page_size != rst_info.vbo) {
+	if (log->rst_info.chkdsk_was_run &&
+	    log->page_size != log->rst_info.vbo) {
 		struct RECORD_PAGE_HDR *sp = NULL;
 		bool usa_error;
 
-		if (!read_log_page(log, page_size, &sp, &usa_error) &&
+		if (!read_log_page(log, log->page_size, &sp, &usa_error) &&
 		    sp->rhdr.sign == NTFS_CHKD_SIGNATURE) {
 			use_second_page = false;
 		}
@@ -3846,52 +3838,43 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	}
 
 	if (use_second_page) {
-		kfree(rst_info.r_page);
-		memcpy(&rst_info, &rst_info2, sizeof(struct restart_info));
-		rst_info2.r_page = NULL;
+		kfree(log->rst_info.r_page);
+		memcpy(&log->rst_info, &log->rst_info2,
+		       sizeof(struct restart_info));
+		log->rst_info2.r_page = NULL;
 	}
 
 use_first_page:
-	kfree(rst_info2.r_page);
+	kfree(log->rst_info2.r_page);
 
 check_restart_area:
 	/*
 	 * If the restart area is at offset 0, we want
 	 * to write the second restart area first.
 	 */
-	log->init_ra = !!rst_info.vbo;
+	log->init_ra = !!log->rst_info.vbo;
 
 	/* If we have a valid page then grab a pointer to the restart area. */
-	ra2 = rst_info.valid_page ?
-		      Add2Ptr(rst_info.r_page,
-			      le16_to_cpu(rst_info.r_page->ra_off)) :
+	ra2 = log->rst_info.valid_page ?
+		      Add2Ptr(log->rst_info.r_page,
+			      le16_to_cpu(log->rst_info.r_page->ra_off)) :
 		      NULL;
 
-	if (rst_info.chkdsk_was_run ||
+	if (log->rst_info.chkdsk_was_run ||
 	    (ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) {
 		bool wrapped = false;
 		bool use_multi_page = false;
 		u32 open_log_count;
 
 		/* Do some checks based on whether we have a valid log page. */
-		if (!rst_info.valid_page) {
-			open_log_count = get_random_u32();
-			goto init_log_instance;
-		}
-		open_log_count = le32_to_cpu(ra2->open_log_count);
-
-		/*
-		 * If the restart page size isn't changing then we want to
-		 * check how much work we need to do.
-		 */
-		if (page_size != le32_to_cpu(rst_info.r_page->sys_page_size))
-			goto init_log_instance;
+		open_log_count = log->rst_info.valid_page ?
+					 le32_to_cpu(ra2->open_log_count) :
+					 get_random_u32();
 
-init_log_instance:
-		log_init_pg_hdr(log, page_size, page_size, 1, 1);
+		log_init_pg_hdr(log, 1, 1);
 
-		log_create(log, l_size, rst_info.last_lsn, open_log_count,
-			   wrapped, use_multi_page);
+		log_create(log, log->rst_info.last_lsn, open_log_count, wrapped,
+			   use_multi_page);
 
 		ra = log_create_ra(log);
 		if (!ra) {
@@ -3916,28 +3899,27 @@ init_log_instance:
 	 * use the log file. We must use the system page size instead of the
 	 * default size if there is not a clean shutdown.
 	 */
-	t32 = le32_to_cpu(rst_info.r_page->sys_page_size);
-	if (page_size != t32) {
-		l_size = orig_file_size;
-		page_size =
-			norm_file_page(t32, &l_size, t32 == DefaultLogPageSize);
+	t32 = le32_to_cpu(log->rst_info.r_page->sys_page_size);
+	if (log->page_size != t32) {
+		log->l_size = log->orig_file_size;
+		log->page_size = norm_file_page(t32, &log->l_size,
+						t32 == DefaultLogPageSize);
 	}
 
-	if (page_size != t32 ||
-	    page_size != le32_to_cpu(rst_info.r_page->page_size)) {
+	if (log->page_size != t32 ||
+	    log->page_size != le32_to_cpu(log->rst_info.r_page->page_size)) {
 		err = -EINVAL;
 		goto out;
 	}
 
 	/* If the file size has shrunk then we won't mount it. */
-	if (l_size < le64_to_cpu(ra2->l_size)) {
+	if (log->l_size < le64_to_cpu(ra2->l_size)) {
 		err = -EINVAL;
 		goto out;
 	}
 
-	log_init_pg_hdr(log, page_size, page_size,
-			le16_to_cpu(rst_info.r_page->major_ver),
-			le16_to_cpu(rst_info.r_page->minor_ver));
+	log_init_pg_hdr(log, le16_to_cpu(log->rst_info.r_page->major_ver),
+			le16_to_cpu(log->rst_info.r_page->minor_ver));
 
 	log->l_size = le64_to_cpu(ra2->l_size);
 	log->seq_num_bits = le32_to_cpu(ra2->seq_num_bits);
@@ -3945,7 +3927,7 @@ init_log_instance:
 	log->seq_num_mask = (8 << log->file_data_bits) - 1;
 	log->last_lsn = le64_to_cpu(ra2->current_lsn);
 	log->seq_num = log->last_lsn >> log->file_data_bits;
-	log->ra_off = le16_to_cpu(rst_info.r_page->ra_off);
+	log->ra_off = le16_to_cpu(log->rst_info.r_page->ra_off);
 	log->restart_size = log->sys_page_size - log->ra_off;
 	log->record_header_len = le16_to_cpu(ra2->rec_hdr_len);
 	log->ra_size = le16_to_cpu(ra2->ra_len);
@@ -4045,7 +4027,7 @@ find_oldest:
 	log->current_avail = current_log_avail(log);
 
 	/* Remember which restart area to write first. */
-	log->init_ra = rst_info.vbo;
+	log->init_ra = log->rst_info.vbo;
 
 process_log:
 	/* 1.0, 1.1, 2.0 log->major_ver/minor_ver - short values. */
@@ -4105,7 +4087,7 @@ process_log:
 	log->client_id.seq_num = cr->seq_num;
 	log->client_id.client_idx = client;
 
-	err = read_rst_area(log, &rst, &ra_lsn);
+	err = read_rst_area(log, &rst, &checkpt_lsn);
 	if (err)
 		goto out;
 
@@ -4114,9 +4096,8 @@ process_log:
 
 	bytes_per_attr_entry = !rst->major_ver ? 0x2C : 0x28;
 
-	checkpt_lsn = le64_to_cpu(rst->check_point_start);
-	if (!checkpt_lsn)
-		checkpt_lsn = ra_lsn;
+	if (rst->check_point_start)
+		checkpt_lsn = le64_to_cpu(rst->check_point_start);
 
 	/* Allocate and Read the Transaction Table. */
 	if (!rst->transact_table_len)
@@ -4330,23 +4311,20 @@ check_attr_table:
 	lcb = NULL;
 
 check_attribute_names2:
-	if (!rst->attr_names_len)
-		goto trace_attribute_table;
-
-	ane = attr_names;
-	if (!oatbl)
-		goto trace_attribute_table;
-	while (ane->off) {
-		/* TODO: Clear table on exit! */
-		oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
-		t16 = le16_to_cpu(ane->name_bytes);
-		oe->name_len = t16 / sizeof(short);
-		oe->ptr = ane->name;
-		oe->is_attr_name = 2;
-		ane = Add2Ptr(ane, sizeof(struct ATTR_NAME_ENTRY) + t16);
-	}
-
-trace_attribute_table:
+	if (rst->attr_names_len && oatbl) {
+		struct ATTR_NAME_ENTRY *ane = attr_names;
+		while (ane->off) {
+			/* TODO: Clear table on exit! */
+			oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
+			t16 = le16_to_cpu(ane->name_bytes);
+			oe->name_len = t16 / sizeof(short);
+			oe->ptr = ane->name;
+			oe->is_attr_name = 2;
+			ane = Add2Ptr(ane,
+				      sizeof(struct ATTR_NAME_ENTRY) + t16);
+		}
+	}
+
 	/*
 	 * If the checkpt_lsn is zero, then this is a freshly
 	 * formatted disk and we have no work to do.
@@ -5189,7 +5167,7 @@ out:
 	kfree(oatbl);
 	kfree(dptbl);
 	kfree(attr_names);
-	kfree(rst_info.r_page);
+	kfree(log->rst_info.r_page);
 
 	kfree(ra);
 	kfree(log->one_page_buf);
-- 
GitLab


From a8b0c9fc3a2dba07f697ef7825e04363ff12f071 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:46:16 +0300
Subject: [PATCH 0821/4076] fs/ntfs3: Fix multithreaded stress test

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/attrib.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 63f70259edc0d..4b78b669a3bdb 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -886,7 +886,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	struct runs_tree *run = &ni->file.run;
 	struct ntfs_sb_info *sbi;
 	u8 cluster_bits;
-	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTRIB *attr, *attr_b;
 	struct ATTR_LIST_ENTRY *le, *le_b;
 	struct mft_inode *mi, *mi_b;
 	CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen;
@@ -904,12 +904,8 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 		*len = 0;
 	up_read(&ni->file.run_lock);
 
-	if (*len) {
-		if (*lcn != SPARSE_LCN || !new)
-			return 0; /* Fast normal way without allocation. */
-		else if (clen > *len)
-			clen = *len;
-	}
+	if (*len && (*lcn != SPARSE_LCN || !new))
+		return 0; /* Fast normal way without allocation. */
 
 	/* No cluster in cache or we need to allocate cluster in hole. */
 	sbi = ni->mi.sbi;
@@ -918,6 +914,17 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	ni_lock(ni);
 	down_write(&ni->file.run_lock);
 
+	/* Repeat the code above (under write lock). */
+	if (!run_lookup_entry(run, vcn, lcn, len, NULL))
+		*len = 0;
+
+	if (*len) {
+		if (*lcn != SPARSE_LCN || !new)
+			goto out; /* normal way without allocation. */
+		if (clen > *len)
+			clen = *len;
+	}
+
 	le_b = NULL;
 	attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
 	if (!attr_b) {
-- 
GitLab


From d155617006ebc172a80d3eb013c4b867f9a8ada4 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:47:30 +0300
Subject: [PATCH 0822/4076] fs/ntfs3: Fix detected field-spanning write (size
 8) of single field "le->name"

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/ntfs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 86aecbb01a92f..13e96fc63dae5 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -523,7 +523,7 @@ struct ATTR_LIST_ENTRY {
 	__le64 vcn;		// 0x08: Starting VCN of this attribute.
 	struct MFT_REF ref;	// 0x10: MFT record number with attribute.
 	__le16 id;		// 0x18: struct ATTRIB ID.
-	__le16 name[3];		// 0x1A: Just to align. To get real name can use bNameOffset.
+	__le16 name[];		// 0x1A: Just to align. To get real name can use name_off.
 
 }; // sizeof(0x20)
 
-- 
GitLab


From a40b73f608e7de2120fdb9ddc8970421b3c50bc9 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:08:36 +0300
Subject: [PATCH 0823/4076] fs/ntfs3: Correct use bh_read

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/file.c  | 19 +++++++++----------
 fs/ntfs3/inode.c |  7 +++----
 2 files changed, 12 insertions(+), 14 deletions(-)

diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index a5a30a24ce5df..5691f04e6751a 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -188,6 +188,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
 	u32 bh_next, bh_off, to;
 	sector_t iblock;
 	struct folio *folio;
+	bool dirty = false;
 
 	for (; idx < idx_end; idx += 1, from = 0) {
 		page_off = (loff_t)idx << PAGE_SHIFT;
@@ -223,29 +224,27 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
 			/* Ok, it's mapped. Make sure it's up-to-date. */
 			if (folio_test_uptodate(folio))
 				set_buffer_uptodate(bh);
-
-			if (!buffer_uptodate(bh)) {
-				err = bh_read(bh, 0);
-				if (err < 0) {
-					folio_unlock(folio);
-					folio_put(folio);
-					goto out;
-				}
+			else if (bh_read(bh, 0) < 0) {
+				err = -EIO;
+				folio_unlock(folio);
+				folio_put(folio);
+				goto out;
 			}
 
 			mark_buffer_dirty(bh);
-
 		} while (bh_off = bh_next, iblock += 1,
 			 head != (bh = bh->b_this_page));
 
 		folio_zero_segment(folio, from, to);
+		dirty = true;
 
 		folio_unlock(folio);
 		folio_put(folio);
 		cond_resched();
 	}
 out:
-	mark_inode_dirty(inode);
+	if (dirty)
+		mark_inode_dirty(inode);
 	return err;
 }
 
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index fa6c7965473c8..bba0208c4afde 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -345,9 +345,7 @@ next_attr:
 			inode->i_size = le16_to_cpu(rp.SymbolicLinkReparseBuffer
 							    .PrintNameLength) /
 					sizeof(u16);
-
 			ni->i_valid = inode->i_size;
-
 			/* Clear directory bit. */
 			if (ni->ni_flags & NI_FLAG_DIR) {
 				indx_clear(&ni->dir);
@@ -653,9 +651,10 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo,
 			off = vbo & (PAGE_SIZE - 1);
 			folio_set_bh(bh, folio, off);
 
-			err = bh_read(bh, 0);
-			if (err < 0)
+			if (bh_read(bh, 0) < 0) {
+				err = -EIO;
 				goto out;
+			}
 			folio_zero_segment(folio, off + voff, off + block_size);
 		}
 	}
-- 
GitLab


From 4dea9cd522424d3002894c20b729c6fbfb6fc22b Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:16:49 +0300
Subject: [PATCH 0824/4076] fs/ntfs3: Add file_modified

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/file.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 5691f04e6751a..bb80ce2eec2f7 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -632,11 +632,17 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 					    &ni->file.run, i_size, &ni->i_valid,
 					    true, NULL);
 			ni_unlock(ni);
+			if (err)
+				goto out;
 		} else if (new_size > i_size) {
 			inode->i_size = new_size;
 		}
 	}
 
+	err = file_modified(file);
+	if (err)
+		goto out;
+
 out:
 	if (map_locked)
 		filemap_invalidate_unlock(mapping);
@@ -1040,6 +1046,7 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	ssize_t ret;
+	int err;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
 	if (is_encrypted(ni)) {
@@ -1067,6 +1074,12 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret <= 0)
 		goto out;
 
+	err = file_modified(iocb->ki_filp);
+	if (err) {
+		ret = err;
+		goto out;
+	}
+
 	if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
 		/* Should never be here, see ntfs_file_open(). */
 		ret = -EOPNOTSUPP;
-- 
GitLab


From e50f9560b8168a625703a3e7fe1fde9fa53f0837 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:17:46 +0300
Subject: [PATCH 0825/4076] fs/ntfs3: Drop suid and sgid bits as a part of
 fpunch

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/file.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index bb80ce2eec2f7..0ff5d3af28897 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -498,10 +498,14 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		ni_lock(ni);
 		err = attr_punch_hole(ni, vbo, len, &frame_size);
 		ni_unlock(ni);
+		if (!err)
+			goto ok;
+
 		if (err != E_NTFS_NOTALIGNED)
 			goto out;
 
 		/* Process not aligned punch. */
+		err = 0;
 		mask = frame_size - 1;
 		vbo_a = (vbo + mask) & ~mask;
 		end_a = end & ~mask;
@@ -524,6 +528,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 			ni_lock(ni);
 			err = attr_punch_hole(ni, vbo_a, end_a - vbo_a, NULL);
 			ni_unlock(ni);
+			if (err)
+				goto out;
 		}
 	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
 		/*
@@ -563,6 +569,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		ni_lock(ni);
 		err = attr_insert_range(ni, vbo, len);
 		ni_unlock(ni);
+		if (err)
+			goto out;
 	} else {
 		/* Check new size. */
 		u8 cluster_bits = sbi->cluster_bits;
@@ -639,6 +647,7 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		}
 	}
 
+ok:
 	err = file_modified(file);
 	if (err)
 		goto out;
-- 
GitLab


From 6c3684e703837d2116b5cf4beb37aa7145a66b60 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:19:37 +0300
Subject: [PATCH 0826/4076] fs/ntfs3: Implement super_operations::shutdown

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/file.c    | 18 ++++++++++++++++++
 fs/ntfs3/frecord.c |  3 +++
 fs/ntfs3/inode.c   | 21 +++++++++++++++++++--
 fs/ntfs3/namei.c   | 12 ++++++++++++
 fs/ntfs3/ntfs_fs.h |  9 ++++++++-
 fs/ntfs3/super.c   | 12 ++++++++++++
 fs/ntfs3/xattr.c   |  3 +++
 7 files changed, 75 insertions(+), 3 deletions(-)

diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 0ff5d3af28897..07ed3d946e7c5 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -260,6 +260,9 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	bool rw = vma->vm_flags & VM_WRITE;
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "mmap encrypted not supported");
 		return -EOPNOTSUPP;
@@ -677,6 +680,9 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	umode_t mode = inode->i_mode;
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	err = setattr_prepare(idmap, dentry, attr);
 	if (err)
 		goto out;
@@ -732,6 +738,9 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = file->f_mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -766,6 +775,9 @@ static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos,
 	struct inode *inode = in->f_mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -1058,6 +1070,9 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	int err;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -1118,6 +1133,9 @@ int ntfs_file_open(struct inode *inode, struct file *file)
 {
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (unlikely((is_compressed(ni) || is_encrypted(ni)) &&
 		     (file->f_flags & O_DIRECT))) {
 		return -EOPNOTSUPP;
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 3df2d9e34b914..8744ba36d4222 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -3259,6 +3259,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 	if (is_bad_inode(inode) || sb_rdonly(sb))
 		return 0;
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	if (!ni_trylock(ni)) {
 		/* 'ni' is under modification, skip for now. */
 		mark_inode_dirty_sync(inode);
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index bba0208c4afde..85452a6b1d40a 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -852,9 +852,13 @@ static int ntfs_resident_writepage(struct folio *folio,
 				   struct writeback_control *wbc, void *data)
 {
 	struct address_space *mapping = data;
-	struct ntfs_inode *ni = ntfs_i(mapping->host);
+	struct inode *inode = mapping->host;
+	struct ntfs_inode *ni = ntfs_i(inode);
 	int ret;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	ni_lock(ni);
 	ret = attr_data_write_resident(ni, &folio->page);
 	ni_unlock(ni);
@@ -868,7 +872,12 @@ static int ntfs_resident_writepage(struct folio *folio,
 static int ntfs_writepages(struct address_space *mapping,
 			   struct writeback_control *wbc)
 {
-	if (is_resident(ntfs_i(mapping->host)))
+	struct inode *inode = mapping->host;
+
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
+	if (is_resident(ntfs_i(inode)))
 		return write_cache_pages(mapping, wbc, ntfs_resident_writepage,
 					 mapping);
 	return mpage_writepages(mapping, wbc, ntfs_get_block);
@@ -888,6 +897,9 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	*pagep = NULL;
 	if (is_resident(ni)) {
 		struct page *page =
@@ -1305,6 +1317,11 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
 		goto out1;
 	}
 
+	if (unlikely(ntfs3_forced_shutdown(sb))) {
+		err = -EIO;
+		goto out2;
+	}
+
 	/* Mark rw ntfs as dirty. it will be cleared at umount. */
 	ntfs_set_state(sbi, NTFS_DIRTY_DIRTY);
 
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index ee3093be51701..cae41db0aaa7d 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -181,6 +181,9 @@ static int ntfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct ntfs_inode *ni = ntfs_i(dir);
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	ni_lock_dir(ni);
 
 	err = ntfs_unlink_inode(dir, dentry);
@@ -199,6 +202,9 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	u32 size = strlen(symname);
 	struct inode *inode;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0,
 				  symname, size, NULL);
 
@@ -227,6 +233,9 @@ static int ntfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct ntfs_inode *ni = ntfs_i(dir);
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	ni_lock_dir(ni);
 
 	err = ntfs_unlink_inode(dir, dentry);
@@ -264,6 +273,9 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *dir,
 		      1024);
 	static_assert(PATH_MAX >= 4 * 1024);
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	if (flags & ~RENAME_NOREPLACE)
 		return -EINVAL;
 
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index f6706143d14bc..d40bc7669ae58 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -61,6 +61,8 @@ enum utf16_endian;
 
 /* sbi->flags */
 #define NTFS_FLAGS_NODISCARD		0x00000001
+/* ntfs in shutdown state. */
+#define NTFS_FLAGS_SHUTDOWN		0x00000002
 /* Set when LogFile is replaying. */
 #define NTFS_FLAGS_LOG_REPLAYING	0x00000008
 /* Set when we changed first MFT's which copy must be updated in $MftMirr. */
@@ -226,7 +228,7 @@ struct ntfs_sb_info {
 	u64 maxbytes; // Maximum size for normal files.
 	u64 maxbytes_sparse; // Maximum size for sparse file.
 
-	u32 flags; // See NTFS_FLAGS_XXX.
+	unsigned long flags; // See NTFS_FLAGS_
 
 	CLST zone_max; // Maximum MFT zone length in clusters
 	CLST bad_clusters; // The count of marked bad clusters.
@@ -999,6 +1001,11 @@ static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
+static inline bool ntfs3_forced_shutdown(struct super_block *sb)
+{
+	return test_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags);
+}
+
 /*
  * ntfs_up_cluster - Align up on cluster boundary.
  */
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 09d61c6c90aaf..af8521a6ed954 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -714,6 +714,14 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+/*
+ * ntfs_shutdown - super_operations::shutdown
+ */
+static void ntfs_shutdown(struct super_block *sb)
+{
+	set_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags);
+}
+
 /*
  * ntfs_sync_fs - super_operations::sync_fs
  */
@@ -724,6 +732,9 @@ static int ntfs_sync_fs(struct super_block *sb, int wait)
 	struct ntfs_inode *ni;
 	struct inode *inode;
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	ni = sbi->security.ni;
 	if (ni) {
 		inode = &ni->vfs_inode;
@@ -763,6 +774,7 @@ static const struct super_operations ntfs_sops = {
 	.put_super = ntfs_put_super,
 	.statfs = ntfs_statfs,
 	.show_options = ntfs_show_options,
+	.shutdown = ntfs_shutdown,
 	.sync_fs = ntfs_sync_fs,
 	.write_inode = ntfs3_write_inode,
 };
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 4274b6f31cfa1..071356d096d83 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -744,6 +744,9 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de,
 	int err;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	/* Dispatch request. */
 	if (!strcmp(name, SYSTEM_DOS_ATTRIB)) {
 		/* system.dos_attrib */
-- 
GitLab


From 97ec56d390a3a0077b36cb38627f671c72dddce6 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:21:12 +0300
Subject: [PATCH 0827/4076] fs/ntfs3: ntfs3_forced_shutdown use int instead of
 bool

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/fsntfs.c  | 3 ++-
 fs/ntfs3/ntfs_fs.h | 6 +++---
 fs/ntfs3/super.c   | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index fbfe21dbb4259..350461d8cece5 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -853,7 +853,8 @@ void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 	/*
 	 * sb can be NULL here. In this case sbi->flags should be 0 too.
 	 */
-	if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR))
+	if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR) ||
+	    unlikely(ntfs3_forced_shutdown(sb)))
 		return;
 
 	blocksize = sb->s_blocksize;
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index d40bc7669ae58..7510875efef6a 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -62,7 +62,7 @@ enum utf16_endian;
 /* sbi->flags */
 #define NTFS_FLAGS_NODISCARD		0x00000001
 /* ntfs in shutdown state. */
-#define NTFS_FLAGS_SHUTDOWN		0x00000002
+#define NTFS_FLAGS_SHUTDOWN_BIT		0x00000002  /* == 4*/
 /* Set when LogFile is replaying. */
 #define NTFS_FLAGS_LOG_REPLAYING	0x00000008
 /* Set when we changed first MFT's which copy must be updated in $MftMirr. */
@@ -1001,9 +1001,9 @@ static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-static inline bool ntfs3_forced_shutdown(struct super_block *sb)
+static inline int ntfs3_forced_shutdown(struct super_block *sb)
 {
-	return test_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags);
+	return test_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
 }
 
 /*
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index af8521a6ed954..65ef4b57411f0 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -719,7 +719,7 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root)
  */
 static void ntfs_shutdown(struct super_block *sb)
 {
-	set_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags);
+	set_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
 }
 
 /*
-- 
GitLab


From d6ca2d253900b9b0a3a1ad77541d606010f5e5eb Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 28 Nov 2023 11:08:00 +0300
Subject: [PATCH 0828/4076] fs/ntfs3: Add and fix comments

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/dir.c     | 4 +++-
 fs/ntfs3/fsntfs.c  | 2 +-
 fs/ntfs3/ntfs.h    | 2 +-
 fs/ntfs3/ntfs_fs.h | 2 +-
 4 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 726122ecd39b4..9f6dd445eb04d 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -536,8 +536,10 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 			e = Add2Ptr(hdr, off);
 			e_size = le16_to_cpu(e->size);
 			if (e_size < sizeof(struct NTFS_DE) ||
-			    off + e_size > end)
+			    off + e_size > end) {
+				/* Looks like corruption. */
 				break;
+			}
 
 			if (de_is_last(e))
 				break;
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 350461d8cece5..321978019407f 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -2129,8 +2129,8 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi,
 			if (le32_to_cpu(d_security->size) == new_sec_size &&
 			    d_security->key.hash == hash_key.hash &&
 			    !memcmp(d_security + 1, sd, size_sd)) {
-				*security_id = d_security->key.sec_id;
 				/* Such security already exists. */
+				*security_id = d_security->key.sec_id;
 				err = 0;
 				goto out;
 			}
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 13e96fc63dae5..c8981429c7213 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -523,7 +523,7 @@ struct ATTR_LIST_ENTRY {
 	__le64 vcn;		// 0x08: Starting VCN of this attribute.
 	struct MFT_REF ref;	// 0x10: MFT record number with attribute.
 	__le16 id;		// 0x18: struct ATTRIB ID.
-	__le16 name[];		// 0x1A: Just to align. To get real name can use name_off.
+	__le16 name[];		// 0x1A: To get real name use name_off.
 
 }; // sizeof(0x20)
 
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 7510875efef6a..abbc7182554aa 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -874,7 +874,7 @@ int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode,
 
 int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry);
 ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-extern const struct xattr_handler * const ntfs_xattr_handlers[];
+extern const struct xattr_handler *const ntfs_xattr_handlers[];
 
 int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size);
 void ntfs_get_wsl_perm(struct inode *inode);
-- 
GitLab


From aaab47f204aaf47838241d57bf8662c8840de60a Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 28 Nov 2023 11:09:34 +0300
Subject: [PATCH 0829/4076] fs/ntfs3: Add NULL ptr dereference checking at the
 end of attr_allocate_frame()

It is preferable to exit through the out: label because
internal debugging functions are located there.

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/attrib.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 4b78b669a3bdb..646e2dad1b757 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -1743,8 +1743,10 @@ repack:
 			le_b = NULL;
 			attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
 					      0, NULL, &mi_b);
-			if (!attr_b)
-				return -ENOENT;
+			if (!attr_b) {
+				err = -ENOENT;
+				goto out;
+			}
 
 			attr = attr_b;
 			le = le_b;
@@ -1825,13 +1827,15 @@ ins_ext:
 ok:
 	run_truncate_around(run, vcn);
 out:
-	if (new_valid > data_size)
-		new_valid = data_size;
+	if (attr_b) {
+		if (new_valid > data_size)
+			new_valid = data_size;
 
-	valid_size = le64_to_cpu(attr_b->nres.valid_size);
-	if (new_valid != valid_size) {
-		attr_b->nres.valid_size = cpu_to_le64(valid_size);
-		mi_b->dirty = true;
+		valid_size = le64_to_cpu(attr_b->nres.valid_size);
+		if (new_valid != valid_size) {
+			attr_b->nres.valid_size = cpu_to_le64(valid_size);
+			mi_b->dirty = true;
+		}
 	}
 
 	return err;
-- 
GitLab


From 652483bfbc45137e8dce556c9ddbd4458dad4452 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 28 Nov 2023 11:17:20 +0300
Subject: [PATCH 0830/4076] fs/ntfs3: Fix c/mtime typo

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/frecord.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 8744ba36d4222..6ff4f70ba0775 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -3291,7 +3291,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 			modified = true;
 		}
 
-		ts = inode_get_mtime(inode);
+		ts = inode_get_ctime(inode);
 		dup.c_time = kernel2nt(&ts);
 		if (std->c_time != dup.c_time) {
 			std->c_time = dup.c_time;
-- 
GitLab


From 2eab57b131bd9ef22377e09de43beb45a650a752 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 29 Nov 2023 15:41:02 +0100
Subject: [PATCH 0831/4076] interconnect: qcom: Add SM6115 interconnect
 provider driver

Add a driver for managing NoC providers on SM6115.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231125-topic-6115icc-v3-2-bd8907b8cfd7@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/Kconfig  |    9 +
 drivers/interconnect/qcom/Makefile |    2 +
 drivers/interconnect/qcom/sm6115.c | 1427 ++++++++++++++++++++++++++++
 3 files changed, 1438 insertions(+)
 create mode 100644 drivers/interconnect/qcom/sm6115.c

diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig
index 62b516d38d03f..d2a54c5ecd067 100644
--- a/drivers/interconnect/qcom/Kconfig
+++ b/drivers/interconnect/qcom/Kconfig
@@ -191,6 +191,15 @@ config INTERCONNECT_QCOM_SDX75
 	  This is a driver for the Qualcomm Network-on-Chip on sdx75-based
 	  platforms.
 
+config INTERCONNECT_QCOM_SM6115
+	tristate "Qualcomm SM6115 interconnect driver"
+	depends on INTERCONNECT_QCOM
+	depends on QCOM_SMD_RPM
+	select INTERCONNECT_QCOM_SMD_RPM
+	help
+	  This is a driver for the Qualcomm Network-on-Chip on sm6115-based
+	  platforms.
+
 config INTERCONNECT_QCOM_SM6350
 	tristate "Qualcomm SM6350 interconnect driver"
 	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
diff --git a/drivers/interconnect/qcom/Makefile b/drivers/interconnect/qcom/Makefile
index c5320e293960a..7564042a30dc8 100644
--- a/drivers/interconnect/qcom/Makefile
+++ b/drivers/interconnect/qcom/Makefile
@@ -24,6 +24,7 @@ qnoc-sdm845-objs			:= sdm845.o
 qnoc-sdx55-objs				:= sdx55.o
 qnoc-sdx65-objs				:= sdx65.o
 qnoc-sdx75-objs				:= sdx75.o
+qnoc-sm6115-objs			:= sm6115.o
 qnoc-sm6350-objs			:= sm6350.o
 qnoc-sm8150-objs			:= sm8150.o
 qnoc-sm8250-objs			:= sm8250.o
@@ -53,6 +54,7 @@ obj-$(CONFIG_INTERCONNECT_QCOM_SDM845) += qnoc-sdm845.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SDX55) += qnoc-sdx55.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SDX65) += qnoc-sdx65.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SDX75) += qnoc-sdx75.o
+obj-$(CONFIG_INTERCONNECT_QCOM_SM6115) += qnoc-sm6115.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM6350) += qnoc-sm6350.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8150) += qnoc-sm8150.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8250) += qnoc-sm8250.o
diff --git a/drivers/interconnect/qcom/sm6115.c b/drivers/interconnect/qcom/sm6115.c
new file mode 100644
index 0000000000000..c49a83c87739d
--- /dev/null
+++ b/drivers/interconnect/qcom/sm6115.c
@@ -0,0 +1,1427 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#include <dt-bindings/interconnect/qcom,sm6115.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/interconnect-provider.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include "icc-rpm.h"
+
+static const char * const snoc_intf_clocks[] = {
+	"cpu_axi",
+	"ufs_axi",
+	"usb_axi",
+	"ipa", /* Required by qxm_ipa */
+};
+
+static const char * const cnoc_intf_clocks[] = {
+	"usb_axi",
+};
+
+enum {
+	SM6115_MASTER_AMPSS_M0,
+	SM6115_MASTER_ANOC_SNOC,
+	SM6115_MASTER_BIMC_SNOC,
+	SM6115_MASTER_CAMNOC_HF,
+	SM6115_MASTER_CAMNOC_SF,
+	SM6115_MASTER_CRYPTO_CORE0,
+	SM6115_MASTER_GRAPHICS_3D,
+	SM6115_MASTER_IPA,
+	SM6115_MASTER_MDP_PORT0,
+	SM6115_MASTER_PIMEM,
+	SM6115_MASTER_QDSS_BAM,
+	SM6115_MASTER_QDSS_DAP,
+	SM6115_MASTER_QDSS_ETR,
+	SM6115_MASTER_QPIC,
+	SM6115_MASTER_QUP_0,
+	SM6115_MASTER_QUP_CORE_0,
+	SM6115_MASTER_SDCC_1,
+	SM6115_MASTER_SDCC_2,
+	SM6115_MASTER_SNOC_BIMC_NRT,
+	SM6115_MASTER_SNOC_BIMC_RT,
+	SM6115_MASTER_SNOC_BIMC,
+	SM6115_MASTER_SNOC_CFG,
+	SM6115_MASTER_SNOC_CNOC,
+	SM6115_MASTER_TCU_0,
+	SM6115_MASTER_TIC,
+	SM6115_MASTER_USB3,
+	SM6115_MASTER_VIDEO_P0,
+	SM6115_MASTER_VIDEO_PROC,
+
+	SM6115_SLAVE_AHB2PHY_USB,
+	SM6115_SLAVE_ANOC_SNOC,
+	SM6115_SLAVE_APPSS,
+	SM6115_SLAVE_APSS_THROTTLE_CFG,
+	SM6115_SLAVE_BIMC_CFG,
+	SM6115_SLAVE_BIMC_SNOC,
+	SM6115_SLAVE_BOOT_ROM,
+	SM6115_SLAVE_CAMERA_CFG,
+	SM6115_SLAVE_CAMERA_NRT_THROTTLE_CFG,
+	SM6115_SLAVE_CAMERA_RT_THROTTLE_CFG,
+	SM6115_SLAVE_CLK_CTL,
+	SM6115_SLAVE_CNOC_MSS,
+	SM6115_SLAVE_CRYPTO_0_CFG,
+	SM6115_SLAVE_DCC_CFG,
+	SM6115_SLAVE_DDR_PHY_CFG,
+	SM6115_SLAVE_DDR_SS_CFG,
+	SM6115_SLAVE_DISPLAY_CFG,
+	SM6115_SLAVE_DISPLAY_THROTTLE_CFG,
+	SM6115_SLAVE_EBI_CH0,
+	SM6115_SLAVE_GPU_CFG,
+	SM6115_SLAVE_GPU_THROTTLE_CFG,
+	SM6115_SLAVE_HWKM_CORE,
+	SM6115_SLAVE_IMEM_CFG,
+	SM6115_SLAVE_IPA_CFG,
+	SM6115_SLAVE_LPASS,
+	SM6115_SLAVE_MAPSS,
+	SM6115_SLAVE_MDSP_MPU_CFG,
+	SM6115_SLAVE_MESSAGE_RAM,
+	SM6115_SLAVE_OCIMEM,
+	SM6115_SLAVE_PDM,
+	SM6115_SLAVE_PIMEM_CFG,
+	SM6115_SLAVE_PIMEM,
+	SM6115_SLAVE_PKA_CORE,
+	SM6115_SLAVE_PMIC_ARB,
+	SM6115_SLAVE_QDSS_CFG,
+	SM6115_SLAVE_QDSS_STM,
+	SM6115_SLAVE_QM_CFG,
+	SM6115_SLAVE_QM_MPU_CFG,
+	SM6115_SLAVE_QPIC,
+	SM6115_SLAVE_QUP_0,
+	SM6115_SLAVE_QUP_CORE_0,
+	SM6115_SLAVE_RBCPR_CX_CFG,
+	SM6115_SLAVE_RBCPR_MX_CFG,
+	SM6115_SLAVE_RPM,
+	SM6115_SLAVE_SDCC_1,
+	SM6115_SLAVE_SDCC_2,
+	SM6115_SLAVE_SECURITY,
+	SM6115_SLAVE_SERVICE_CNOC,
+	SM6115_SLAVE_SERVICE_SNOC,
+	SM6115_SLAVE_SNOC_BIMC_NRT,
+	SM6115_SLAVE_SNOC_BIMC_RT,
+	SM6115_SLAVE_SNOC_BIMC,
+	SM6115_SLAVE_SNOC_CFG,
+	SM6115_SLAVE_SNOC_CNOC,
+	SM6115_SLAVE_TCSR,
+	SM6115_SLAVE_TCU,
+	SM6115_SLAVE_TLMM,
+	SM6115_SLAVE_USB3,
+	SM6115_SLAVE_VENUS_CFG,
+	SM6115_SLAVE_VENUS_THROTTLE_CFG,
+	SM6115_SLAVE_VSENSE_CTRL_CFG,
+};
+
+static const u16 slv_ebi_slv_bimc_snoc_links[] = {
+	SM6115_SLAVE_EBI_CH0,
+	SM6115_SLAVE_BIMC_SNOC,
+};
+
+static struct qcom_icc_node apps_proc = {
+	.name = "apps_proc",
+	.id = SM6115_MASTER_AMPSS_M0,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 0,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.prio_level = 0,
+	.qos.areq_prio = 0,
+	.mas_rpm_id = 0,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_ebi_slv_bimc_snoc_links),
+	.links = slv_ebi_slv_bimc_snoc_links,
+};
+
+static const u16 link_slv_ebi[] = {
+	SM6115_SLAVE_EBI_CH0,
+};
+
+static struct qcom_icc_node mas_snoc_bimc_rt = {
+	.name = "mas_snoc_bimc_rt",
+	.id = SM6115_MASTER_SNOC_BIMC_RT,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 2,
+	.qos.qos_mode = NOC_QOS_MODE_BYPASS,
+	.qos.areq_prio = 0,
+	.qos.prio_level = 0,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_ebi),
+	.links = link_slv_ebi,
+};
+
+static struct qcom_icc_node mas_snoc_bimc_nrt = {
+	.name = "mas_snoc_bimc_nrt",
+	.id = SM6115_MASTER_SNOC_BIMC_NRT,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 3,
+	.qos.qos_mode = NOC_QOS_MODE_BYPASS,
+	.qos.areq_prio = 0,
+	.qos.prio_level = 0,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_ebi),
+	.links = link_slv_ebi,
+};
+
+static struct qcom_icc_node mas_snoc_bimc = {
+	.name = "mas_snoc_bimc",
+	.id = SM6115_MASTER_SNOC_BIMC,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 6,
+	.qos.qos_mode = NOC_QOS_MODE_BYPASS,
+	.qos.areq_prio = 0,
+	.qos.prio_level = 0,
+	.mas_rpm_id = 3,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_ebi),
+	.links = link_slv_ebi,
+};
+
+static struct qcom_icc_node qnm_gpu = {
+	.name = "qnm_gpu",
+	.id = SM6115_MASTER_GRAPHICS_3D,
+	.channels = 1,
+	.buswidth = 32,
+	.qos.qos_port = 1,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.prio_level = 0,
+	.qos.areq_prio = 0,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_ebi_slv_bimc_snoc_links),
+	.links = slv_ebi_slv_bimc_snoc_links,
+};
+
+static struct qcom_icc_node tcu_0 = {
+	.name = "tcu_0",
+	.id = SM6115_MASTER_TCU_0,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 4,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.prio_level = 6,
+	.qos.areq_prio = 6,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_ebi_slv_bimc_snoc_links),
+	.links = slv_ebi_slv_bimc_snoc_links,
+};
+
+static const u16 qup_core_0_links[] = {
+	SM6115_SLAVE_QUP_CORE_0,
+};
+
+static struct qcom_icc_node qup0_core_master = {
+	.name = "qup0_core_master",
+	.id = SM6115_MASTER_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = 170,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(qup_core_0_links),
+	.links = qup_core_0_links,
+};
+
+static const u16 link_slv_anoc_snoc[] = {
+	SM6115_SLAVE_ANOC_SNOC,
+};
+
+static struct qcom_icc_node crypto_c0 = {
+	.name = "crypto_c0",
+	.id = SM6115_MASTER_CRYPTO_CORE0,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 43,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 23,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static const u16 mas_snoc_cnoc_links[] = {
+	SM6115_SLAVE_AHB2PHY_USB,
+	SM6115_SLAVE_APSS_THROTTLE_CFG,
+	SM6115_SLAVE_BIMC_CFG,
+	SM6115_SLAVE_BOOT_ROM,
+	SM6115_SLAVE_CAMERA_CFG,
+	SM6115_SLAVE_CAMERA_NRT_THROTTLE_CFG,
+	SM6115_SLAVE_CAMERA_RT_THROTTLE_CFG,
+	SM6115_SLAVE_CLK_CTL,
+	SM6115_SLAVE_CNOC_MSS,
+	SM6115_SLAVE_CRYPTO_0_CFG,
+	SM6115_SLAVE_DCC_CFG,
+	SM6115_SLAVE_DDR_PHY_CFG,
+	SM6115_SLAVE_DDR_SS_CFG,
+	SM6115_SLAVE_DISPLAY_CFG,
+	SM6115_SLAVE_DISPLAY_THROTTLE_CFG,
+	SM6115_SLAVE_GPU_CFG,
+	SM6115_SLAVE_GPU_THROTTLE_CFG,
+	SM6115_SLAVE_HWKM_CORE,
+	SM6115_SLAVE_IMEM_CFG,
+	SM6115_SLAVE_IPA_CFG,
+	SM6115_SLAVE_LPASS,
+	SM6115_SLAVE_MAPSS,
+	SM6115_SLAVE_MDSP_MPU_CFG,
+	SM6115_SLAVE_MESSAGE_RAM,
+	SM6115_SLAVE_PDM,
+	SM6115_SLAVE_PIMEM_CFG,
+	SM6115_SLAVE_PKA_CORE,
+	SM6115_SLAVE_PMIC_ARB,
+	SM6115_SLAVE_QDSS_CFG,
+	SM6115_SLAVE_QM_CFG,
+	SM6115_SLAVE_QM_MPU_CFG,
+	SM6115_SLAVE_QPIC,
+	SM6115_SLAVE_QUP_0,
+	SM6115_SLAVE_RBCPR_CX_CFG,
+	SM6115_SLAVE_RBCPR_MX_CFG,
+	SM6115_SLAVE_RPM,
+	SM6115_SLAVE_SDCC_1,
+	SM6115_SLAVE_SDCC_2,
+	SM6115_SLAVE_SECURITY,
+	SM6115_SLAVE_SERVICE_CNOC,
+	SM6115_SLAVE_SNOC_CFG,
+	SM6115_SLAVE_TCSR,
+	SM6115_SLAVE_TLMM,
+	SM6115_SLAVE_USB3,
+	SM6115_SLAVE_VENUS_CFG,
+	SM6115_SLAVE_VENUS_THROTTLE_CFG,
+	SM6115_SLAVE_VSENSE_CTRL_CFG,
+};
+
+static struct qcom_icc_node mas_snoc_cnoc = {
+	.name = "mas_snoc_cnoc",
+	.id = SM6115_MASTER_SNOC_CNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_snoc_cnoc_links),
+	.links = mas_snoc_cnoc_links,
+};
+
+static struct qcom_icc_node xm_dap = {
+	.name = "xm_dap",
+	.id = SM6115_MASTER_QDSS_DAP,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_snoc_cnoc_links),
+	.links = mas_snoc_cnoc_links,
+};
+
+static const u16 link_slv_snoc_bimc_nrt[] = {
+	SM6115_SLAVE_SNOC_BIMC_NRT,
+};
+
+static struct qcom_icc_node qnm_camera_nrt = {
+	.name = "qnm_camera_nrt",
+	.id = SM6115_MASTER_CAMNOC_SF,
+	.channels = 1,
+	.buswidth = 32,
+	.qos.qos_port = 25,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 3,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_nrt),
+	.links = link_slv_snoc_bimc_nrt,
+};
+
+static struct qcom_icc_node qxm_venus0 = {
+	.name = "qxm_venus0",
+	.id = SM6115_MASTER_VIDEO_P0,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 30,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 3,
+	.qos.urg_fwd_en = true,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_nrt),
+	.links = link_slv_snoc_bimc_nrt,
+};
+
+static struct qcom_icc_node qxm_venus_cpu = {
+	.name = "qxm_venus_cpu",
+	.id = SM6115_MASTER_VIDEO_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 34,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_nrt),
+	.links = link_slv_snoc_bimc_nrt,
+};
+
+static const u16 link_slv_snoc_bimc_rt[] = {
+	SM6115_SLAVE_SNOC_BIMC_RT,
+};
+
+static struct qcom_icc_node qnm_camera_rt = {
+	.name = "qnm_camera_rt",
+	.id = SM6115_MASTER_CAMNOC_HF,
+	.channels = 1,
+	.buswidth = 32,
+	.qos.qos_port = 31,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 3,
+	.qos.urg_fwd_en = true,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_rt),
+	.links = link_slv_snoc_bimc_rt,
+};
+
+static struct qcom_icc_node qxm_mdp0 = {
+	.name = "qxm_mdp0",
+	.id = SM6115_MASTER_MDP_PORT0,
+	.channels = 1,
+	.buswidth = 16,
+	.qos.qos_port = 26,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 3,
+	.qos.urg_fwd_en = true,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_snoc_bimc_rt),
+	.links = link_slv_snoc_bimc_rt,
+};
+
+static const u16 slv_service_snoc_links[] = {
+	SM6115_SLAVE_SERVICE_SNOC,
+};
+
+static struct qcom_icc_node qhm_snoc_cfg = {
+	.name = "qhm_snoc_cfg",
+	.id = SM6115_MASTER_SNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_service_snoc_links),
+	.links = slv_service_snoc_links,
+};
+
+static const u16 mas_tic_links[] = {
+	SM6115_SLAVE_APPSS,
+	SM6115_SLAVE_OCIMEM,
+	SM6115_SLAVE_PIMEM,
+	SM6115_SLAVE_QDSS_STM,
+	SM6115_SLAVE_TCU,
+	SM6115_SLAVE_SNOC_BIMC,
+	SM6115_SLAVE_SNOC_CNOC,
+};
+
+static struct qcom_icc_node qhm_tic = {
+	.name = "qhm_tic",
+	.id = SM6115_MASTER_TIC,
+	.channels = 1,
+	.buswidth = 4,
+	.qos.qos_port = 29,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_tic_links),
+	.links = mas_tic_links,
+};
+
+static struct qcom_icc_node mas_anoc_snoc = {
+	.name = "mas_anoc_snoc",
+	.id = SM6115_MASTER_ANOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_tic_links),
+	.links = mas_tic_links,
+};
+
+static const u16 mas_bimc_snoc_links[] = {
+	SM6115_SLAVE_APPSS,
+	SM6115_SLAVE_SNOC_CNOC,
+	SM6115_SLAVE_OCIMEM,
+	SM6115_SLAVE_PIMEM,
+	SM6115_SLAVE_QDSS_STM,
+	SM6115_SLAVE_TCU,
+};
+
+static struct qcom_icc_node mas_bimc_snoc = {
+	.name = "mas_bimc_snoc",
+	.id = SM6115_MASTER_BIMC_SNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = 21,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_bimc_snoc_links),
+	.links = mas_bimc_snoc_links,
+};
+
+static const u16 mas_pimem_links[] = {
+	SM6115_SLAVE_OCIMEM,
+	SM6115_SLAVE_SNOC_BIMC,
+};
+
+static struct qcom_icc_node qxm_pimem = {
+	.name = "qxm_pimem",
+	.id = SM6115_MASTER_PIMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 41,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(mas_pimem_links),
+	.links = mas_pimem_links,
+};
+
+static struct qcom_icc_node qhm_qdss_bam = {
+	.name = "qhm_qdss_bam",
+	.id = SM6115_MASTER_QDSS_BAM,
+	.channels = 1,
+	.buswidth = 4,
+	.qos.qos_port = 23,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node qhm_qpic = {
+	.name = "qhm_qpic",
+	.id = SM6115_MASTER_QPIC,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node qhm_qup0 = {
+	.name = "qhm_qup0",
+	.id = SM6115_MASTER_QUP_0,
+	.channels = 1,
+	.buswidth = 4,
+	.qos.qos_port = 21,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 166,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node qxm_ipa = {
+	.name = "qxm_ipa",
+	.id = SM6115_MASTER_IPA,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 24,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 59,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node xm_qdss_etr = {
+	.name = "xm_qdss_etr",
+	.id = SM6115_MASTER_QDSS_ETR,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 33,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node xm_sdc1 = {
+	.name = "xm_sdc1",
+	.id = SM6115_MASTER_SDCC_1,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 38,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 33,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node xm_sdc2 = {
+	.name = "xm_sdc2",
+	.id = SM6115_MASTER_SDCC_2,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 44,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = 35,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node xm_usb3_0 = {
+	.name = "xm_usb3_0",
+	.id = SM6115_MASTER_USB3,
+	.channels = 1,
+	.buswidth = 8,
+	.qos.qos_port = 45,
+	.qos.qos_mode = NOC_QOS_MODE_FIXED,
+	.qos.areq_prio = 2,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(link_slv_anoc_snoc),
+	.links = link_slv_anoc_snoc,
+};
+
+static struct qcom_icc_node ebi = {
+	.name = "ebi",
+	.id = SM6115_SLAVE_EBI_CH0,
+	.channels = 2,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 0,
+};
+
+static const u16 slv_bimc_snoc_links[] = {
+	SM6115_MASTER_BIMC_SNOC,
+};
+
+static struct qcom_icc_node slv_bimc_snoc = {
+	.name = "slv_bimc_snoc",
+	.id = SM6115_SLAVE_BIMC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 2,
+	.num_links = ARRAY_SIZE(slv_bimc_snoc_links),
+	.links = slv_bimc_snoc_links,
+};
+
+static struct qcom_icc_node qup0_core_slave = {
+	.name = "qup0_core_slave",
+	.id = SM6115_SLAVE_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_ahb2phy_usb = {
+	.name = "qhs_ahb2phy_usb",
+	.id = SM6115_SLAVE_AHB2PHY_USB,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_apss_throttle_cfg = {
+	.name = "qhs_apss_throttle_cfg",
+	.id = SM6115_SLAVE_APSS_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_bimc_cfg = {
+	.name = "qhs_bimc_cfg",
+	.id = SM6115_SLAVE_BIMC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_boot_rom = {
+	.name = "qhs_boot_rom",
+	.id = SM6115_SLAVE_BOOT_ROM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_camera_nrt_throttle_cfg = {
+	.name = "qhs_camera_nrt_throttle_cfg",
+	.id = SM6115_SLAVE_CAMERA_NRT_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_camera_rt_throttle_cfg = {
+	.name = "qhs_camera_rt_throttle_cfg",
+	.id = SM6115_SLAVE_CAMERA_RT_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_camera_ss_cfg = {
+	.name = "qhs_camera_ss_cfg",
+	.id = SM6115_SLAVE_CAMERA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_clk_ctl = {
+	.name = "qhs_clk_ctl",
+	.id = SM6115_SLAVE_CLK_CTL,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_cpr_cx = {
+	.name = "qhs_cpr_cx",
+	.id = SM6115_SLAVE_RBCPR_CX_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_cpr_mx = {
+	.name = "qhs_cpr_mx",
+	.id = SM6115_SLAVE_RBCPR_MX_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_crypto0_cfg = {
+	.name = "qhs_crypto0_cfg",
+	.id = SM6115_SLAVE_CRYPTO_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_dcc_cfg = {
+	.name = "qhs_dcc_cfg",
+	.id = SM6115_SLAVE_DCC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_ddr_phy_cfg = {
+	.name = "qhs_ddr_phy_cfg",
+	.id = SM6115_SLAVE_DDR_PHY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_ddr_ss_cfg = {
+	.name = "qhs_ddr_ss_cfg",
+	.id = SM6115_SLAVE_DDR_SS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_disp_ss_cfg = {
+	.name = "qhs_disp_ss_cfg",
+	.id = SM6115_SLAVE_DISPLAY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_display_throttle_cfg = {
+	.name = "qhs_display_throttle_cfg",
+	.id = SM6115_SLAVE_DISPLAY_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_gpu_cfg = {
+	.name = "qhs_gpu_cfg",
+	.id = SM6115_SLAVE_GPU_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_gpu_throttle_cfg = {
+	.name = "qhs_gpu_throttle_cfg",
+	.id = SM6115_SLAVE_GPU_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_hwkm = {
+	.name = "qhs_hwkm",
+	.id = SM6115_SLAVE_HWKM_CORE,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_imem_cfg = {
+	.name = "qhs_imem_cfg",
+	.id = SM6115_SLAVE_IMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_ipa_cfg = {
+	.name = "qhs_ipa_cfg",
+	.id = SM6115_SLAVE_IPA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_lpass = {
+	.name = "qhs_lpass",
+	.id = SM6115_SLAVE_LPASS,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_mapss = {
+	.name = "qhs_mapss",
+	.id = SM6115_SLAVE_MAPSS,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_mdsp_mpu_cfg = {
+	.name = "qhs_mdsp_mpu_cfg",
+	.id = SM6115_SLAVE_MDSP_MPU_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_mesg_ram = {
+	.name = "qhs_mesg_ram",
+	.id = SM6115_SLAVE_MESSAGE_RAM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_mss = {
+	.name = "qhs_mss",
+	.id = SM6115_SLAVE_CNOC_MSS,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_pdm = {
+	.name = "qhs_pdm",
+	.id = SM6115_SLAVE_PDM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_pimem_cfg = {
+	.name = "qhs_pimem_cfg",
+	.id = SM6115_SLAVE_PIMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_pka_wrapper = {
+	.name = "qhs_pka_wrapper",
+	.id = SM6115_SLAVE_PKA_CORE,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_pmic_arb = {
+	.name = "qhs_pmic_arb",
+	.id = SM6115_SLAVE_PMIC_ARB,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qdss_cfg = {
+	.name = "qhs_qdss_cfg",
+	.id = SM6115_SLAVE_QDSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qm_cfg = {
+	.name = "qhs_qm_cfg",
+	.id = SM6115_SLAVE_QM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qm_mpu_cfg = {
+	.name = "qhs_qm_mpu_cfg",
+	.id = SM6115_SLAVE_QM_MPU_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qpic = {
+	.name = "qhs_qpic",
+	.id = SM6115_SLAVE_QPIC,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_qup0 = {
+	.name = "qhs_qup0",
+	.id = SM6115_SLAVE_QUP_0,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_rpm = {
+	.name = "qhs_rpm",
+	.id = SM6115_SLAVE_RPM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_sdc1 = {
+	.name = "qhs_sdc1",
+	.id = SM6115_SLAVE_SDCC_1,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_sdc2 = {
+	.name = "qhs_sdc2",
+	.id = SM6115_SLAVE_SDCC_2,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_security = {
+	.name = "qhs_security",
+	.id = SM6115_SLAVE_SECURITY,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_snoc_cfg_links[] = {
+	SM6115_MASTER_SNOC_CFG,
+};
+
+static struct qcom_icc_node qhs_snoc_cfg = {
+	.name = "qhs_snoc_cfg",
+	.id = SM6115_SLAVE_SNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_snoc_cfg_links),
+	.links = slv_snoc_cfg_links,
+};
+
+static struct qcom_icc_node qhs_tcsr = {
+	.name = "qhs_tcsr",
+	.id = SM6115_SLAVE_TCSR,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_tlmm = {
+	.name = "qhs_tlmm",
+	.id = SM6115_SLAVE_TLMM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_usb3 = {
+	.name = "qhs_usb3",
+	.id = SM6115_SLAVE_USB3,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_venus_cfg = {
+	.name = "qhs_venus_cfg",
+	.id = SM6115_SLAVE_VENUS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_venus_throttle_cfg = {
+	.name = "qhs_venus_throttle_cfg",
+	.id = SM6115_SLAVE_VENUS_THROTTLE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node qhs_vsense_ctrl_cfg = {
+	.name = "qhs_vsense_ctrl_cfg",
+	.id = SM6115_SLAVE_VSENSE_CTRL_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node srvc_cnoc = {
+	.name = "srvc_cnoc",
+	.id = SM6115_SLAVE_SERVICE_CNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_snoc_bimc_nrt_links[] = {
+	SM6115_MASTER_SNOC_BIMC_NRT,
+};
+
+static struct qcom_icc_node slv_snoc_bimc_nrt = {
+	.name = "slv_snoc_bimc_nrt",
+	.id = SM6115_SLAVE_SNOC_BIMC_NRT,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_snoc_bimc_nrt_links),
+	.links = slv_snoc_bimc_nrt_links,
+};
+
+static const u16 slv_snoc_bimc_rt_links[] = {
+	SM6115_MASTER_SNOC_BIMC_RT,
+};
+
+static struct qcom_icc_node slv_snoc_bimc_rt = {
+	.name = "slv_snoc_bimc_rt",
+	.id = SM6115_SLAVE_SNOC_BIMC_RT,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_snoc_bimc_rt_links),
+	.links = slv_snoc_bimc_rt_links,
+};
+
+static struct qcom_icc_node qhs_apss = {
+	.name = "qhs_apss",
+	.id = SM6115_SLAVE_APPSS,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_snoc_cnoc_links[] = {
+	SM6115_MASTER_SNOC_CNOC
+};
+
+static struct qcom_icc_node slv_snoc_cnoc = {
+	.name = "slv_snoc_cnoc",
+	.id = SM6115_SLAVE_SNOC_CNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 25,
+	.num_links = ARRAY_SIZE(slv_snoc_cnoc_links),
+	.links = slv_snoc_cnoc_links,
+};
+
+static struct qcom_icc_node qxs_imem = {
+	.name = "qxs_imem",
+	.id = SM6115_SLAVE_OCIMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 26,
+};
+
+static struct qcom_icc_node qxs_pimem = {
+	.name = "qxs_pimem",
+	.id = SM6115_SLAVE_PIMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_snoc_bimc_links[] = {
+	SM6115_MASTER_SNOC_BIMC,
+};
+
+static struct qcom_icc_node slv_snoc_bimc = {
+	.name = "slv_snoc_bimc",
+	.id = SM6115_SLAVE_SNOC_BIMC,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 24,
+	.num_links = ARRAY_SIZE(slv_snoc_bimc_links),
+	.links = slv_snoc_bimc_links,
+};
+
+static struct qcom_icc_node srvc_snoc = {
+	.name = "srvc_snoc",
+	.id = SM6115_SLAVE_SERVICE_SNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static struct qcom_icc_node xs_qdss_stm = {
+	.name = "xs_qdss_stm",
+	.id = SM6115_SLAVE_QDSS_STM,
+	.channels = 1,
+	.buswidth = 4,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = 30,
+};
+
+static struct qcom_icc_node xs_sys_tcu_cfg = {
+	.name = "xs_sys_tcu_cfg",
+	.id = SM6115_SLAVE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+};
+
+static const u16 slv_anoc_snoc_links[] = {
+	SM6115_MASTER_ANOC_SNOC,
+};
+
+static struct qcom_icc_node slv_anoc_snoc = {
+	.name = "slv_anoc_snoc",
+	.id = SM6115_SLAVE_ANOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.mas_rpm_id = -1,
+	.slv_rpm_id = -1,
+	.num_links = ARRAY_SIZE(slv_anoc_snoc_links),
+	.links = slv_anoc_snoc_links,
+};
+
+static struct qcom_icc_node *bimc_nodes[] = {
+	[MASTER_AMPSS_M0] = &apps_proc,
+	[MASTER_SNOC_BIMC_RT] = &mas_snoc_bimc_rt,
+	[MASTER_SNOC_BIMC_NRT] = &mas_snoc_bimc_nrt,
+	[SNOC_BIMC_MAS] = &mas_snoc_bimc,
+	[MASTER_GRAPHICS_3D] = &qnm_gpu,
+	[MASTER_TCU_0] = &tcu_0,
+	[SLAVE_EBI_CH0] = &ebi,
+	[BIMC_SNOC_SLV] = &slv_bimc_snoc,
+};
+
+static const struct regmap_config bimc_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x80000,
+	.fast_io	= true,
+};
+
+static const struct qcom_icc_desc sm6115_bimc = {
+	.type = QCOM_ICC_BIMC,
+	.nodes = bimc_nodes,
+	.num_nodes = ARRAY_SIZE(bimc_nodes),
+	.regmap_cfg = &bimc_regmap_config,
+	.bus_clk_desc = &bimc_clk,
+	.keep_alive = true,
+	.qos_offset = 0x8000,
+	.ab_coeff = 153,
+};
+
+static struct qcom_icc_node *config_noc_nodes[] = {
+	[SNOC_CNOC_MAS] = &mas_snoc_cnoc,
+	[MASTER_QDSS_DAP] = &xm_dap,
+	[SLAVE_AHB2PHY_USB] = &qhs_ahb2phy_usb,
+	[SLAVE_APSS_THROTTLE_CFG] = &qhs_apss_throttle_cfg,
+	[SLAVE_BIMC_CFG] = &qhs_bimc_cfg,
+	[SLAVE_BOOT_ROM] = &qhs_boot_rom,
+	[SLAVE_CAMERA_NRT_THROTTLE_CFG] = &qhs_camera_nrt_throttle_cfg,
+	[SLAVE_CAMERA_RT_THROTTLE_CFG] = &qhs_camera_rt_throttle_cfg,
+	[SLAVE_CAMERA_CFG] = &qhs_camera_ss_cfg,
+	[SLAVE_CLK_CTL] = &qhs_clk_ctl,
+	[SLAVE_RBCPR_CX_CFG] = &qhs_cpr_cx,
+	[SLAVE_RBCPR_MX_CFG] = &qhs_cpr_mx,
+	[SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg,
+	[SLAVE_DCC_CFG] = &qhs_dcc_cfg,
+	[SLAVE_DDR_PHY_CFG] = &qhs_ddr_phy_cfg,
+	[SLAVE_DDR_SS_CFG] = &qhs_ddr_ss_cfg,
+	[SLAVE_DISPLAY_CFG] = &qhs_disp_ss_cfg,
+	[SLAVE_DISPLAY_THROTTLE_CFG] = &qhs_display_throttle_cfg,
+	[SLAVE_GPU_CFG] = &qhs_gpu_cfg,
+	[SLAVE_GPU_THROTTLE_CFG] = &qhs_gpu_throttle_cfg,
+	[SLAVE_HWKM_CORE] = &qhs_hwkm,
+	[SLAVE_IMEM_CFG] = &qhs_imem_cfg,
+	[SLAVE_IPA_CFG] = &qhs_ipa_cfg,
+	[SLAVE_LPASS] = &qhs_lpass,
+	[SLAVE_MAPSS] = &qhs_mapss,
+	[SLAVE_MDSP_MPU_CFG] = &qhs_mdsp_mpu_cfg,
+	[SLAVE_MESSAGE_RAM] = &qhs_mesg_ram,
+	[SLAVE_CNOC_MSS] = &qhs_mss,
+	[SLAVE_PDM] = &qhs_pdm,
+	[SLAVE_PIMEM_CFG] = &qhs_pimem_cfg,
+	[SLAVE_PKA_CORE] = &qhs_pka_wrapper,
+	[SLAVE_PMIC_ARB] = &qhs_pmic_arb,
+	[SLAVE_QDSS_CFG] = &qhs_qdss_cfg,
+	[SLAVE_QM_CFG] = &qhs_qm_cfg,
+	[SLAVE_QM_MPU_CFG] = &qhs_qm_mpu_cfg,
+	[SLAVE_QPIC] = &qhs_qpic,
+	[SLAVE_QUP_0] = &qhs_qup0,
+	[SLAVE_RPM] = &qhs_rpm,
+	[SLAVE_SDCC_1] = &qhs_sdc1,
+	[SLAVE_SDCC_2] = &qhs_sdc2,
+	[SLAVE_SECURITY] = &qhs_security,
+	[SLAVE_SNOC_CFG] = &qhs_snoc_cfg,
+	[SLAVE_TCSR] = &qhs_tcsr,
+	[SLAVE_TLMM] = &qhs_tlmm,
+	[SLAVE_USB3] = &qhs_usb3,
+	[SLAVE_VENUS_CFG] = &qhs_venus_cfg,
+	[SLAVE_VENUS_THROTTLE_CFG] = &qhs_venus_throttle_cfg,
+	[SLAVE_VSENSE_CTRL_CFG] = &qhs_vsense_ctrl_cfg,
+	[SLAVE_SERVICE_CNOC] = &srvc_cnoc,
+};
+
+static const struct regmap_config cnoc_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x6200,
+	.fast_io	= true,
+};
+
+static const struct qcom_icc_desc sm6115_config_noc = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = config_noc_nodes,
+	.num_nodes = ARRAY_SIZE(config_noc_nodes),
+	.regmap_cfg = &cnoc_regmap_config,
+	.intf_clocks = cnoc_intf_clocks,
+	.num_intf_clocks = ARRAY_SIZE(cnoc_intf_clocks),
+	.bus_clk_desc = &bus_1_clk,
+	.keep_alive = true,
+};
+
+static struct qcom_icc_node *sys_noc_nodes[] = {
+	[MASTER_CRYPTO_CORE0] = &crypto_c0,
+	[MASTER_SNOC_CFG] = &qhm_snoc_cfg,
+	[MASTER_TIC] = &qhm_tic,
+	[MASTER_ANOC_SNOC] = &mas_anoc_snoc,
+	[BIMC_SNOC_MAS] = &mas_bimc_snoc,
+	[MASTER_PIMEM] = &qxm_pimem,
+	[MASTER_QDSS_BAM] = &qhm_qdss_bam,
+	[MASTER_QPIC] = &qhm_qpic,
+	[MASTER_QUP_0] = &qhm_qup0,
+	[MASTER_IPA] = &qxm_ipa,
+	[MASTER_QDSS_ETR] = &xm_qdss_etr,
+	[MASTER_SDCC_1] = &xm_sdc1,
+	[MASTER_SDCC_2] = &xm_sdc2,
+	[MASTER_USB3] = &xm_usb3_0,
+	[SLAVE_APPSS] = &qhs_apss,
+	[SNOC_CNOC_SLV] = &slv_snoc_cnoc,
+	[SLAVE_OCIMEM] = &qxs_imem,
+	[SLAVE_PIMEM] = &qxs_pimem,
+	[SNOC_BIMC_SLV] = &slv_snoc_bimc,
+	[SLAVE_SERVICE_SNOC] = &srvc_snoc,
+	[SLAVE_QDSS_STM] = &xs_qdss_stm,
+	[SLAVE_TCU] = &xs_sys_tcu_cfg,
+	[SLAVE_ANOC_SNOC] = &slv_anoc_snoc,
+};
+
+static const struct regmap_config sys_noc_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x5f080,
+	.fast_io	= true,
+};
+
+static const struct qcom_icc_desc sm6115_sys_noc = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = sys_noc_nodes,
+	.num_nodes = ARRAY_SIZE(sys_noc_nodes),
+	.regmap_cfg = &sys_noc_regmap_config,
+	.intf_clocks = snoc_intf_clocks,
+	.num_intf_clocks = ARRAY_SIZE(snoc_intf_clocks),
+	.bus_clk_desc = &bus_2_clk,
+	.keep_alive = true,
+};
+
+static struct qcom_icc_node *clk_virt_nodes[] = {
+	[MASTER_QUP_CORE_0] = &qup0_core_master,
+	[SLAVE_QUP_CORE_0] = &qup0_core_slave,
+};
+
+static const struct qcom_icc_desc sm6115_clk_virt = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = clk_virt_nodes,
+	.num_nodes = ARRAY_SIZE(clk_virt_nodes),
+	.regmap_cfg = &sys_noc_regmap_config,
+	.bus_clk_desc = &qup_clk,
+	.keep_alive = true,
+};
+
+static struct qcom_icc_node *mmnrt_virt_nodes[] = {
+	[MASTER_CAMNOC_SF] = &qnm_camera_nrt,
+	[MASTER_VIDEO_P0] = &qxm_venus0,
+	[MASTER_VIDEO_PROC] = &qxm_venus_cpu,
+	[SLAVE_SNOC_BIMC_NRT] = &slv_snoc_bimc_nrt,
+};
+
+static const struct qcom_icc_desc sm6115_mmnrt_virt = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = mmnrt_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mmnrt_virt_nodes),
+	.regmap_cfg = &sys_noc_regmap_config,
+	.bus_clk_desc = &mmaxi_0_clk,
+	.keep_alive = true,
+	.ab_coeff = 142,
+};
+
+static struct qcom_icc_node *mmrt_virt_nodes[] = {
+	[MASTER_CAMNOC_HF] = &qnm_camera_rt,
+	[MASTER_MDP_PORT0] = &qxm_mdp0,
+	[SLAVE_SNOC_BIMC_RT] = &slv_snoc_bimc_rt,
+};
+
+static const struct qcom_icc_desc sm6115_mmrt_virt = {
+	.type = QCOM_ICC_QNOC,
+	.nodes = mmrt_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mmrt_virt_nodes),
+	.regmap_cfg = &sys_noc_regmap_config,
+	.bus_clk_desc = &mmaxi_1_clk,
+	.keep_alive = true,
+	.ab_coeff = 139,
+};
+
+static const struct of_device_id qnoc_of_match[] = {
+	{ .compatible = "qcom,sm6115-bimc", .data = &sm6115_bimc },
+	{ .compatible = "qcom,sm6115-clk-virt", .data = &sm6115_clk_virt },
+	{ .compatible = "qcom,sm6115-cnoc", .data = &sm6115_config_noc },
+	{ .compatible = "qcom,sm6115-mmrt-virt", .data = &sm6115_mmrt_virt },
+	{ .compatible = "qcom,sm6115-mmnrt-virt", .data = &sm6115_mmnrt_virt },
+	{ .compatible = "qcom,sm6115-snoc", .data = &sm6115_sys_noc },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qnoc_of_match);
+
+static struct platform_driver qnoc_driver = {
+	.probe = qnoc_probe,
+	.remove_new = qnoc_remove,
+	.driver = {
+		.name = "qnoc-sm6115",
+		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
+	},
+};
+
+static int __init qnoc_driver_init(void)
+{
+	return platform_driver_register(&qnoc_driver);
+}
+core_initcall(qnoc_driver_init);
+
+static void __exit qnoc_driver_exit(void)
+{
+	platform_driver_unregister(&qnoc_driver);
+}
+module_exit(qnoc_driver_exit);
+
+MODULE_DESCRIPTION("SM6115 NoC driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 407a3898d72ee0020b8cc9dd28b88c8eb8d68214 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 5 Dec 2023 08:49:24 -0800
Subject: [PATCH 0832/4076] perf test shell diff: Skip test if test_loop symbol
 is missing in the perf binary

The diff test depends on finding the symbol test_loop in perf and will
fail if perf has been stripped and no debug object is available. In that
case, skip the test instead.

Suggested-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231205164924.835682-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/diff.sh | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/perf/tests/shell/diff.sh b/tools/perf/tests/shell/diff.sh
index 2131857636888..14b87af88703b 100755
--- a/tools/perf/tests/shell/diff.sh
+++ b/tools/perf/tests/shell/diff.sh
@@ -9,8 +9,15 @@ perfdata1=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 perfdata2=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 perfdata3=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 testprog="perf test -w thloop"
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 testsym="test_loop"
 
+skip_test_missing_symbol ${testsym}
+
 cleanup() {
   rm -rf "${perfdata1}"
   rm -rf "${perfdata1}".old
-- 
GitLab


From 9fa688ea341231837915f996b61f6e0a330d3b38 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 27 Nov 2023 14:08:24 -0800
Subject: [PATCH 0833/4076] perf map: Simplify map_ip/unmap_ip and make 'struct
 map' smaller

When mapping an IP it is either an identity mapping or a DSO relative
mapping, so a single bit is required in the struct to identify
this.

The current code uses function pointers, adding 2 pointers per map and
also pushing the size of a map beyond 1 cache line.

Switch to using a byte to identify the mapping type (as well as priv and
erange_warned), to avoid any masking.

Change struct maps's layout to avoid holes.

Before:
```
struct map {
        u64                        start;                /*     0     8 */
        u64                        end;                  /*     8     8 */
        _Bool                      erange_warned:1;      /*    16: 0  1 */
        _Bool                      priv:1;               /*    16: 1  1 */

        /* XXX 6 bits hole, try to pack */
        /* XXX 3 bytes hole, try to pack */

        u32                        prot;                 /*    20     4 */
        u64                        pgoff;                /*    24     8 */
        u64                        reloc;                /*    32     8 */
        u64                        (*map_ip)(const struct map  *, u64); /*    40     8 */
        u64                        (*unmap_ip)(const struct map  *, u64); /*    48     8 */
        struct dso *               dso;                  /*    56     8 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        refcount_t                 refcnt;               /*    64     4 */
        u32                        flags;                /*    68     4 */

        /* size: 72, cachelines: 2, members: 12 */
        /* sum members: 68, holes: 1, sum holes: 3 */
        /* sum bitfield members: 2 bits, bit holes: 1, sum bit holes: 6 bits */
        /* last cacheline: 8 bytes */
};
```

After:
```
struct map {
        u64                        start;                /*     0     8 */
        u64                        end;                  /*     8     8 */
        u64                        pgoff;                /*    16     8 */
        u64                        reloc;                /*    24     8 */
        struct dso *               dso;                  /*    32     8 */
        refcount_t                 refcnt;               /*    40     4 */
        u32                        prot;                 /*    44     4 */
        u32                        flags;                /*    48     4 */
        enum mapping_type          mapping_type:8;       /*    52: 0  4 */

        /* Bitfield combined with next fields */

        _Bool                      erange_warned;        /*    53     1 */
        _Bool                      priv;                 /*    54     1 */

        /* size: 56, cachelines: 1, members: 11 */
        /* padding: 1 */
        /* last cacheline: 56 bytes */
};
```

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231127220902.1315692-13-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c    |  3 +-
 tools/perf/util/map.c        | 20 +--------
 tools/perf/util/map.h        | 83 +++++++++++++++++++-----------------
 tools/perf/util/symbol-elf.c |  6 +--
 tools/perf/util/symbol.c     |  6 +--
 5 files changed, 50 insertions(+), 68 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index a985d004aa8d8..c5de5363b5e75 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1359,8 +1359,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 	if (machine->vmlinux_map == NULL)
 		return -ENOMEM;
 
-	map__set_map_ip(machine->vmlinux_map, identity__map_ip);
-	map__set_unmap_ip(machine->vmlinux_map, identity__map_ip);
+	map__set_mapping_type(machine->vmlinux_map, MAPPING_TYPE__IDENTITY);
 	return maps__insert(machine__kernel_maps(machine), machine->vmlinux_map);
 }
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f64b830044217..54c67cb7ecefa 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -109,8 +109,7 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso)
 	map__set_pgoff(map, pgoff);
 	map__set_reloc(map, 0);
 	map__set_dso(map, dso__get(dso));
-	map__set_map_ip(map, map__dso_map_ip);
-	map__set_unmap_ip(map, map__dso_unmap_ip);
+	map__set_mapping_type(map, MAPPING_TYPE__DSO);
 	map__set_erange_warned(map, false);
 	refcount_set(map__refcnt(map), 1);
 }
@@ -172,7 +171,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		map__init(result, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
-			map->map_ip = map->unmap_ip = identity__map_ip;
+			map->mapping_type = MAPPING_TYPE__IDENTITY;
 
 			/*
 			 * Set memory without DSO as loaded. All map__find_*
@@ -630,18 +629,3 @@ struct maps *map__kmaps(struct map *map)
 	}
 	return kmap->kmaps;
 }
-
-u64 map__dso_map_ip(const struct map *map, u64 ip)
-{
-	return ip - map__start(map) + map__pgoff(map);
-}
-
-u64 map__dso_unmap_ip(const struct map *map, u64 ip)
-{
-	return ip + map__start(map) - map__pgoff(map);
-}
-
-u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip)
-{
-	return ip;
-}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 1b53d53adc866..3a3b7757da5fd 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -16,23 +16,25 @@ struct dso;
 struct maps;
 struct machine;
 
+enum mapping_type {
+	/* map__map_ip/map__unmap_ip are given as offsets in the DSO. */
+	MAPPING_TYPE__DSO,
+	/* map__map_ip/map__unmap_ip are just the given ip value. */
+	MAPPING_TYPE__IDENTITY,
+};
+
 DECLARE_RC_STRUCT(map) {
 	u64			start;
 	u64			end;
-	bool			erange_warned:1;
-	bool			priv:1;
-	u32			prot;
 	u64			pgoff;
 	u64			reloc;
-
-	/* ip -> dso rip */
-	u64			(*map_ip)(const struct map *, u64);
-	/* dso rip -> ip */
-	u64			(*unmap_ip)(const struct map *, u64);
-
 	struct dso		*dso;
 	refcount_t		refcnt;
+	u32			prot;
 	u32			flags;
+	enum mapping_type	mapping_type:8;
+	bool			erange_warned;
+	bool			priv;
 };
 
 struct kmap;
@@ -41,38 +43,11 @@ struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
 struct maps *map__kmaps(struct map *map);
 
-/* ip -> dso rip */
-u64 map__dso_map_ip(const struct map *map, u64 ip);
-/* dso rip -> ip */
-u64 map__dso_unmap_ip(const struct map *map, u64 ip);
-/* Returns ip */
-u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip);
-
 static inline struct dso *map__dso(const struct map *map)
 {
 	return RC_CHK_ACCESS(map)->dso;
 }
 
-static inline u64 map__map_ip(const struct map *map, u64 ip)
-{
-	return RC_CHK_ACCESS(map)->map_ip(map, ip);
-}
-
-static inline u64 map__unmap_ip(const struct map *map, u64 ip)
-{
-	return RC_CHK_ACCESS(map)->unmap_ip(map, ip);
-}
-
-static inline void *map__map_ip_ptr(struct map *map)
-{
-	return RC_CHK_ACCESS(map)->map_ip;
-}
-
-static inline void* map__unmap_ip_ptr(struct map *map)
-{
-	return RC_CHK_ACCESS(map)->unmap_ip;
-}
-
 static inline u64 map__start(const struct map *map)
 {
 	return RC_CHK_ACCESS(map)->start;
@@ -123,6 +98,34 @@ static inline size_t map__size(const struct map *map)
 	return map__end(map) - map__start(map);
 }
 
+/* ip -> dso rip */
+static inline u64 map__dso_map_ip(const struct map *map, u64 ip)
+{
+	return ip - map__start(map) + map__pgoff(map);
+}
+
+/* dso rip -> ip */
+static inline u64 map__dso_unmap_ip(const struct map *map, u64 ip)
+{
+	return ip + map__start(map) - map__pgoff(map);
+}
+
+static inline u64 map__map_ip(const struct map *map, u64 ip)
+{
+	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
+		return map__dso_map_ip(map, ip);
+	else
+		return ip;
+}
+
+static inline u64 map__unmap_ip(const struct map *map, u64 ip)
+{
+	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
+		return map__dso_unmap_ip(map, ip);
+	else
+		return ip;
+}
+
 /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
 u64 map__rip_2objdump(struct map *map, u64 rip);
 
@@ -294,13 +297,13 @@ static inline void map__set_dso(struct map *map, struct dso *dso)
 	RC_CHK_ACCESS(map)->dso = dso;
 }
 
-static inline void map__set_map_ip(struct map *map, u64 (*map_ip)(const struct map *map, u64 ip))
+static inline void map__set_mapping_type(struct map *map, enum mapping_type type)
 {
-	RC_CHK_ACCESS(map)->map_ip = map_ip;
+	RC_CHK_ACCESS(map)->mapping_type = type;
 }
 
-static inline void map__set_unmap_ip(struct map *map, u64 (*unmap_ip)(const struct map *map, u64 rip))
+static inline enum mapping_type map__mapping_type(struct map *map)
 {
-	RC_CHK_ACCESS(map)->unmap_ip = unmap_ip;
+	return RC_CHK_ACCESS(map)->mapping_type;
 }
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 9e7eeaf616b86..4b934ed3bfd13 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1392,8 +1392,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 			map__set_start(map, shdr->sh_addr + ref_reloc(kmap));
 			map__set_end(map, map__start(map) + shdr->sh_size);
 			map__set_pgoff(map, shdr->sh_offset);
-			map__set_map_ip(map, map__dso_map_ip);
-			map__set_unmap_ip(map, map__dso_unmap_ip);
+			map__set_mapping_type(map, MAPPING_TYPE__DSO);
 			/* Ensure maps are correctly ordered */
 			if (kmaps) {
 				int err;
@@ -1455,8 +1454,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 			map__set_end(curr_map, map__start(curr_map) + shdr->sh_size);
 			map__set_pgoff(curr_map, shdr->sh_offset);
 		} else {
-			map__set_map_ip(curr_map, identity__map_ip);
-			map__set_unmap_ip(curr_map, identity__map_ip);
+			map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
 		}
 		curr_dso->symtab_type = dso->symtab_type;
 		if (maps__insert(kmaps, curr_map))
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 82cc74b9358e0..314c0263bf3c0 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -956,8 +956,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 				return -1;
 			}
 
-			map__set_map_ip(curr_map, identity__map_ip);
-			map__set_unmap_ip(curr_map, identity__map_ip);
+			map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
 			if (maps__insert(kmaps, curr_map)) {
 				dso__put(ndso);
 				return -1;
@@ -1475,8 +1474,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			map__set_start(map, map__start(new_map));
 			map__set_end(map, map__end(new_map));
 			map__set_pgoff(map, map__pgoff(new_map));
-			map__set_map_ip(map, map__map_ip_ptr(new_map));
-			map__set_unmap_ip(map, map__unmap_ip_ptr(new_map));
+			map__set_mapping_type(map, map__mapping_type(new_map));
 			/* Ensure maps are correctly ordered */
 			map_ref = map__get(map);
 			maps__remove(kmaps, map_ref);
-- 
GitLab


From 0f6ab6a3fb7e380a1277f8288f315724ed517114 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 27 Nov 2023 14:08:25 -0800
Subject: [PATCH 0834/4076] perf maps: Move symbol maps functions to maps.c

Move the find and certain other symbol maps__* functions to maps.c for
better abstraction.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231127220902.1315692-14-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/maps.c   | 238 +++++++++++++++++++++++++++++++++++++
 tools/perf/util/maps.h   |  12 ++
 tools/perf/util/symbol.c | 248 ---------------------------------------
 tools/perf/util/symbol.h |   1 -
 4 files changed, 250 insertions(+), 249 deletions(-)

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 233438c95b531..9a011aed4b754 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -475,3 +475,241 @@ struct map_rb_node *map_rb_node__next(struct map_rb_node *node)
 
 	return rb_entry(next, struct map_rb_node, rb_node);
 }
+
+static int map__strcmp(const void *a, const void *b)
+{
+	const struct map *map_a = *(const struct map **)a;
+	const struct map *map_b = *(const struct map **)b;
+	const struct dso *dso_a = map__dso(map_a);
+	const struct dso *dso_b = map__dso(map_b);
+	int ret = strcmp(dso_a->short_name, dso_b->short_name);
+
+	if (ret == 0 && map_a != map_b) {
+		/*
+		 * Ensure distinct but name equal maps have an order in part to
+		 * aid reference counting.
+		 */
+		ret = (int)map__start(map_a) - (int)map__start(map_b);
+		if (ret == 0)
+			ret = (int)((intptr_t)map_a - (intptr_t)map_b);
+	}
+
+	return ret;
+}
+
+static int map__strcmp_name(const void *name, const void *b)
+{
+	const struct dso *dso = map__dso(*(const struct map **)b);
+
+	return strcmp(name, dso->short_name);
+}
+
+void __maps__sort_by_name(struct maps *maps)
+{
+	qsort(maps__maps_by_name(maps), maps__nr_maps(maps), sizeof(struct map *), map__strcmp);
+}
+
+static int map__groups__sort_by_name_from_rbtree(struct maps *maps)
+{
+	struct map_rb_node *rb_node;
+	struct map **maps_by_name = realloc(maps__maps_by_name(maps),
+					    maps__nr_maps(maps) * sizeof(struct map *));
+	int i = 0;
+
+	if (maps_by_name == NULL)
+		return -1;
+
+	up_read(maps__lock(maps));
+	down_write(maps__lock(maps));
+
+	RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name;
+	RC_CHK_ACCESS(maps)->nr_maps_allocated = maps__nr_maps(maps);
+
+	maps__for_each_entry(maps, rb_node)
+		maps_by_name[i++] = map__get(rb_node->map);
+
+	__maps__sort_by_name(maps);
+
+	up_write(maps__lock(maps));
+	down_read(maps__lock(maps));
+
+	return 0;
+}
+
+static struct map *__maps__find_by_name(struct maps *maps, const char *name)
+{
+	struct map **mapp;
+
+	if (maps__maps_by_name(maps) == NULL &&
+	    map__groups__sort_by_name_from_rbtree(maps))
+		return NULL;
+
+	mapp = bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps),
+		       sizeof(*mapp), map__strcmp_name);
+	if (mapp)
+		return *mapp;
+	return NULL;
+}
+
+struct map *maps__find_by_name(struct maps *maps, const char *name)
+{
+	struct map_rb_node *rb_node;
+	struct map *map;
+
+	down_read(maps__lock(maps));
+
+
+	if (RC_CHK_ACCESS(maps)->last_search_by_name) {
+		const struct dso *dso = map__dso(RC_CHK_ACCESS(maps)->last_search_by_name);
+
+		if (strcmp(dso->short_name, name) == 0) {
+			map = RC_CHK_ACCESS(maps)->last_search_by_name;
+			goto out_unlock;
+		}
+	}
+	/*
+	 * If we have maps->maps_by_name, then the name isn't in the rbtree,
+	 * as maps->maps_by_name mirrors the rbtree when lookups by name are
+	 * made.
+	 */
+	map = __maps__find_by_name(maps, name);
+	if (map || maps__maps_by_name(maps) != NULL)
+		goto out_unlock;
+
+	/* Fallback to traversing the rbtree... */
+	maps__for_each_entry(maps, rb_node) {
+		struct dso *dso;
+
+		map = rb_node->map;
+		dso = map__dso(map);
+		if (strcmp(dso->short_name, name) == 0) {
+			RC_CHK_ACCESS(maps)->last_search_by_name = map;
+			goto out_unlock;
+		}
+	}
+	map = NULL;
+
+out_unlock:
+	up_read(maps__lock(maps));
+	return map;
+}
+
+void maps__fixup_end(struct maps *maps)
+{
+	struct map_rb_node *prev = NULL, *curr;
+
+	down_write(maps__lock(maps));
+
+	maps__for_each_entry(maps, curr) {
+		if (prev != NULL && !map__end(prev->map))
+			map__set_end(prev->map, map__start(curr->map));
+
+		prev = curr;
+	}
+
+	/*
+	 * We still haven't the actual symbols, so guess the
+	 * last map final address.
+	 */
+	if (curr && !map__end(curr->map))
+		map__set_end(curr->map, ~0ULL);
+
+	up_write(maps__lock(maps));
+}
+
+/*
+ * Merges map into maps by splitting the new map within the existing map
+ * regions.
+ */
+int maps__merge_in(struct maps *kmaps, struct map *new_map)
+{
+	struct map_rb_node *rb_node;
+	LIST_HEAD(merged);
+	int err = 0;
+
+	maps__for_each_entry(kmaps, rb_node) {
+		struct map *old_map = rb_node->map;
+
+		/* no overload with this one */
+		if (map__end(new_map) < map__start(old_map) ||
+		    map__start(new_map) >= map__end(old_map))
+			continue;
+
+		if (map__start(new_map) < map__start(old_map)) {
+			/*
+			 * |new......
+			 *       |old....
+			 */
+			if (map__end(new_map) < map__end(old_map)) {
+				/*
+				 * |new......|     -> |new..|
+				 *       |old....| ->       |old....|
+				 */
+				map__set_end(new_map, map__start(old_map));
+			} else {
+				/*
+				 * |new.............| -> |new..|       |new..|
+				 *       |old....|    ->       |old....|
+				 */
+				struct map_list_node *m = map_list_node__new();
+
+				if (!m) {
+					err = -ENOMEM;
+					goto out;
+				}
+
+				m->map = map__clone(new_map);
+				if (!m->map) {
+					free(m);
+					err = -ENOMEM;
+					goto out;
+				}
+
+				map__set_end(m->map, map__start(old_map));
+				list_add_tail(&m->node, &merged);
+				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
+				map__set_start(new_map, map__end(old_map));
+			}
+		} else {
+			/*
+			 *      |new......
+			 * |old....
+			 */
+			if (map__end(new_map) < map__end(old_map)) {
+				/*
+				 *      |new..|   -> x
+				 * |old.........| -> |old.........|
+				 */
+				map__put(new_map);
+				new_map = NULL;
+				break;
+			} else {
+				/*
+				 *      |new......| ->         |new...|
+				 * |old....|        -> |old....|
+				 */
+				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
+				map__set_start(new_map, map__end(old_map));
+			}
+		}
+	}
+
+out:
+	while (!list_empty(&merged)) {
+		struct map_list_node *old_node;
+
+		old_node = list_entry(merged.next, struct map_list_node, node);
+		list_del_init(&old_node->node);
+		if (!err)
+			err = maps__insert(kmaps, old_node->map);
+		map__put(old_node->map);
+		free(old_node);
+	}
+
+	if (new_map) {
+		if (!err)
+			err = maps__insert(kmaps, new_map);
+		map__put(new_map);
+	}
+	return err;
+}
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 83144e0645ed4..a689149be8c43 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -21,6 +21,16 @@ struct map_rb_node {
 	struct map *map;
 };
 
+struct map_list_node {
+	struct list_head node;
+	struct map *map;
+};
+
+static inline struct map_list_node *map_list_node__new(void)
+{
+	return malloc(sizeof(struct map_list_node));
+}
+
 struct map_rb_node *maps__first(struct maps *maps);
 struct map_rb_node *map_rb_node__next(struct map_rb_node *node);
 struct map_rb_node *maps__find_node(struct maps *maps, struct map *map);
@@ -133,4 +143,6 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map);
 
 void __maps__sort_by_name(struct maps *maps);
 
+void maps__fixup_end(struct maps *maps);
+
 #endif // __PERF_MAPS_H
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 314c0263bf3c0..1cc42b8d8afb7 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -48,11 +48,6 @@ static bool symbol__is_idle(const char *name);
 int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
-struct map_list_node {
-	struct list_head node;
-	struct map *map;
-};
-
 struct symbol_conf symbol_conf = {
 	.nanosecs		= false,
 	.use_modules		= true,
@@ -90,11 +85,6 @@ static enum dso_binary_type binary_type_symtab[] = {
 
 #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
 
-static struct map_list_node *map_list_node__new(void)
-{
-	return malloc(sizeof(struct map_list_node));
-}
-
 static bool symbol_type__filter(char symbol_type)
 {
 	symbol_type = toupper(symbol_type);
@@ -270,29 +260,6 @@ void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
 		curr->end = roundup(curr->start, 4096) + 4096;
 }
 
-void maps__fixup_end(struct maps *maps)
-{
-	struct map_rb_node *prev = NULL, *curr;
-
-	down_write(maps__lock(maps));
-
-	maps__for_each_entry(maps, curr) {
-		if (prev != NULL && !map__end(prev->map))
-			map__set_end(prev->map, map__start(curr->map));
-
-		prev = curr;
-	}
-
-	/*
-	 * We still haven't the actual symbols, so guess the
-	 * last map final address.
-	 */
-	if (curr && !map__end(curr->map))
-		map__set_end(curr->map, ~0ULL);
-
-	up_write(maps__lock(maps));
-}
-
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
@@ -1270,103 +1237,6 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
 	return 0;
 }
 
-/*
- * Merges map into maps by splitting the new map within the existing map
- * regions.
- */
-int maps__merge_in(struct maps *kmaps, struct map *new_map)
-{
-	struct map_rb_node *rb_node;
-	LIST_HEAD(merged);
-	int err = 0;
-
-	maps__for_each_entry(kmaps, rb_node) {
-		struct map *old_map = rb_node->map;
-
-		/* no overload with this one */
-		if (map__end(new_map) < map__start(old_map) ||
-		    map__start(new_map) >= map__end(old_map))
-			continue;
-
-		if (map__start(new_map) < map__start(old_map)) {
-			/*
-			 * |new......
-			 *       |old....
-			 */
-			if (map__end(new_map) < map__end(old_map)) {
-				/*
-				 * |new......|     -> |new..|
-				 *       |old....| ->       |old....|
-				 */
-				map__set_end(new_map, map__start(old_map));
-			} else {
-				/*
-				 * |new.............| -> |new..|       |new..|
-				 *       |old....|    ->       |old....|
-				 */
-				struct map_list_node *m = map_list_node__new();
-
-				if (!m) {
-					err = -ENOMEM;
-					goto out;
-				}
-
-				m->map = map__clone(new_map);
-				if (!m->map) {
-					free(m);
-					err = -ENOMEM;
-					goto out;
-				}
-
-				map__set_end(m->map, map__start(old_map));
-				list_add_tail(&m->node, &merged);
-				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
-				map__set_start(new_map, map__end(old_map));
-			}
-		} else {
-			/*
-			 *      |new......
-			 * |old....
-			 */
-			if (map__end(new_map) < map__end(old_map)) {
-				/*
-				 *      |new..|   -> x
-				 * |old.........| -> |old.........|
-				 */
-				map__put(new_map);
-				new_map = NULL;
-				break;
-			} else {
-				/*
-				 *      |new......| ->         |new...|
-				 * |old....|        -> |old....|
-				 */
-				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
-				map__set_start(new_map, map__end(old_map));
-			}
-		}
-	}
-
-out:
-	while (!list_empty(&merged)) {
-		struct map_list_node *old_node;
-
-		old_node = list_entry(merged.next, struct map_list_node, node);
-		list_del_init(&old_node->node);
-		if (!err)
-			err = maps__insert(kmaps, old_node->map);
-		map__put(old_node->map);
-		free(old_node);
-	}
-
-	if (new_map) {
-		if (!err)
-			err = maps__insert(kmaps, new_map);
-		map__put(new_map);
-	}
-	return err;
-}
-
 static int dso__load_kcore(struct dso *dso, struct map *map,
 			   const char *kallsyms_filename)
 {
@@ -2065,124 +1935,6 @@ out:
 	return ret;
 }
 
-static int map__strcmp(const void *a, const void *b)
-{
-	const struct map *map_a = *(const struct map **)a;
-	const struct map *map_b = *(const struct map **)b;
-	const struct dso *dso_a = map__dso(map_a);
-	const struct dso *dso_b = map__dso(map_b);
-	int ret = strcmp(dso_a->short_name, dso_b->short_name);
-
-	if (ret == 0 && map_a != map_b) {
-		/*
-		 * Ensure distinct but name equal maps have an order in part to
-		 * aid reference counting.
-		 */
-		ret = (int)map__start(map_a) - (int)map__start(map_b);
-		if (ret == 0)
-			ret = (int)((intptr_t)map_a - (intptr_t)map_b);
-	}
-
-	return ret;
-}
-
-static int map__strcmp_name(const void *name, const void *b)
-{
-	const struct dso *dso = map__dso(*(const struct map **)b);
-
-	return strcmp(name, dso->short_name);
-}
-
-void __maps__sort_by_name(struct maps *maps)
-{
-	qsort(maps__maps_by_name(maps), maps__nr_maps(maps), sizeof(struct map *), map__strcmp);
-}
-
-static int map__groups__sort_by_name_from_rbtree(struct maps *maps)
-{
-	struct map_rb_node *rb_node;
-	struct map **maps_by_name = realloc(maps__maps_by_name(maps),
-					    maps__nr_maps(maps) * sizeof(struct map *));
-	int i = 0;
-
-	if (maps_by_name == NULL)
-		return -1;
-
-	up_read(maps__lock(maps));
-	down_write(maps__lock(maps));
-
-	RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name;
-	RC_CHK_ACCESS(maps)->nr_maps_allocated = maps__nr_maps(maps);
-
-	maps__for_each_entry(maps, rb_node)
-		maps_by_name[i++] = map__get(rb_node->map);
-
-	__maps__sort_by_name(maps);
-
-	up_write(maps__lock(maps));
-	down_read(maps__lock(maps));
-
-	return 0;
-}
-
-static struct map *__maps__find_by_name(struct maps *maps, const char *name)
-{
-	struct map **mapp;
-
-	if (maps__maps_by_name(maps) == NULL &&
-	    map__groups__sort_by_name_from_rbtree(maps))
-		return NULL;
-
-	mapp = bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps),
-		       sizeof(*mapp), map__strcmp_name);
-	if (mapp)
-		return *mapp;
-	return NULL;
-}
-
-struct map *maps__find_by_name(struct maps *maps, const char *name)
-{
-	struct map_rb_node *rb_node;
-	struct map *map;
-
-	down_read(maps__lock(maps));
-
-
-	if (RC_CHK_ACCESS(maps)->last_search_by_name) {
-		const struct dso *dso = map__dso(RC_CHK_ACCESS(maps)->last_search_by_name);
-
-		if (strcmp(dso->short_name, name) == 0) {
-			map = RC_CHK_ACCESS(maps)->last_search_by_name;
-			goto out_unlock;
-		}
-	}
-	/*
-	 * If we have maps->maps_by_name, then the name isn't in the rbtree,
-	 * as maps->maps_by_name mirrors the rbtree when lookups by name are
-	 * made.
-	 */
-	map = __maps__find_by_name(maps, name);
-	if (map || maps__maps_by_name(maps) != NULL)
-		goto out_unlock;
-
-	/* Fallback to traversing the rbtree... */
-	maps__for_each_entry(maps, rb_node) {
-		struct dso *dso;
-
-		map = rb_node->map;
-		dso = map__dso(map);
-		if (strcmp(dso->short_name, name) == 0) {
-			RC_CHK_ACCESS(maps)->last_search_by_name = map;
-			goto out_unlock;
-		}
-	}
-	map = NULL;
-
-out_unlock:
-	up_read(maps__lock(maps));
-	return map;
-}
-
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, bool vmlinux_allocated)
 {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index af87c46b3f89e..071837ddce2ac 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -189,7 +189,6 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
 void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root_cached *symbols);
 void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms);
-void maps__fixup_end(struct maps *maps);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
 int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
-- 
GitLab


From 01261d8a0f082b1a926d14ecb3ae05e52c477c74 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 27 Nov 2023 14:08:26 -0800
Subject: [PATCH 0835/4076] perf thread: Add missing RC_CHK_EQUAL

Comparing pointers without RC_CHK_ACCESS means the indirect object
will be compared rather than the underlying maps when REFCNT_CHECKING
is enabled. Fix by adding missing RC_CHK_EQUAL.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231127220902.1315692-15-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index fe5e6991ae4b4..b9c2039c4230c 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -385,7 +385,7 @@ static int thread__clone_maps(struct thread *thread, struct thread *parent, bool
 	if (thread__pid(thread) == thread__pid(parent))
 		return thread__prepare_access(thread);
 
-	if (thread__maps(thread) == thread__maps(parent)) {
+	if (RC_CHK_EQUAL(thread__maps(thread), thread__maps(parent))) {
 		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
 			 thread__pid(thread), thread__tid(thread),
 			 thread__pid(parent), thread__tid(parent));
-- 
GitLab


From 4347f5114ab776c60727f94a7ab19538401c9ee1 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Mon, 27 Nov 2023 22:26:53 +0100
Subject: [PATCH 0836/4076] iio: light: isl76682: Add ISL76682 driver

The ISL76682 is very basic ALS which only supports ALS or IR mode
in four ranges, 1k/4k/16k/64k LUX. There is no IRQ support or any
other fancy functionality.

Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Matti Vaittinen <mazziesaccount@gmail.com>
Signed-off-by: Marek Vasut <marex@denx.de>
Link: https://lore.kernel.org/r/20231127212726.77707-2-marex@denx.de
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/Kconfig    |  15 ++
 drivers/iio/light/Makefile   |   1 +
 drivers/iio/light/isl76682.c | 346 +++++++++++++++++++++++++++++++++++
 3 files changed, 362 insertions(+)
 create mode 100644 drivers/iio/light/isl76682.c

diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig
index f68e62196bc2c..9ac6c737207fc 100644
--- a/drivers/iio/light/Kconfig
+++ b/drivers/iio/light/Kconfig
@@ -252,6 +252,21 @@ config ISL29125
 	  To compile this driver as a module, choose M here: the module will be
 	  called isl29125.
 
+config ISL76682
+	tristate "Intersil ISL76682 Light Sensor"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  Say Y here if you want to build a driver for the Intersil ISL76682
+	  Ambient Light Sensor and IR Intensity sensor. This driver provides
+	  the readouts via standard IIO sysfs and device interface. Both ALS
+	  illuminance and IR illuminance are provided raw with separate scale
+	  setting which can be configured via sysfs, the default scale is 1000
+	  lux, other options are 4000/16000/64000 lux.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called isl76682.
+
 config HID_SENSOR_ALS
 	depends on HID_SENSOR_HUB
 	select IIO_BUFFER
diff --git a/drivers/iio/light/Makefile b/drivers/iio/light/Makefile
index c8289e24e3f66..4aa0835ece5d9 100644
--- a/drivers/iio/light/Makefile
+++ b/drivers/iio/light/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_IQS621_ALS)	+= iqs621-als.o
 obj-$(CONFIG_SENSORS_ISL29018)	+= isl29018.o
 obj-$(CONFIG_SENSORS_ISL29028)	+= isl29028.o
 obj-$(CONFIG_ISL29125)		+= isl29125.o
+obj-$(CONFIG_ISL76682)		+= isl76682.o
 obj-$(CONFIG_JSA1212)		+= jsa1212.o
 obj-$(CONFIG_SENSORS_LM3533)	+= lm3533-als.o
 obj-$(CONFIG_LTR501)		+= ltr501.o
diff --git a/drivers/iio/light/isl76682.c b/drivers/iio/light/isl76682.c
new file mode 100644
index 0000000000000..0a7c3b09c3c05
--- /dev/null
+++ b/drivers/iio/light/isl76682.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IIO driver for the light sensor ISL76682.
+ * ISL76682 is Ambient Light Sensor
+ *
+ * Copyright (c) 2023 Marek Vasut <marex@denx.de>
+ */
+
+#include <linux/array_size.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/types.h>
+
+#include <linux/iio/iio.h>
+
+#define ISL76682_REG_COMMAND			0x00
+
+#define ISL76682_COMMAND_EN			BIT(7)
+#define ISL76682_COMMAND_MODE_CONTINUOUS	BIT(6)
+#define ISL76682_COMMAND_LIGHT_IR		BIT(5)
+
+#define ISL76682_COMMAND_RANGE_LUX_1K		0x0
+#define ISL76682_COMMAND_RANGE_LUX_4K		0x1
+#define ISL76682_COMMAND_RANGE_LUX_16K		0x2
+#define ISL76682_COMMAND_RANGE_LUX_64K		0x3
+#define ISL76682_COMMAND_RANGE_LUX_MASK		GENMASK(1, 0)
+
+#define ISL76682_REG_ALSIR_L			0x01
+
+#define ISL76682_REG_ALSIR_U			0x02
+
+#define ISL76682_NUM_REGS			(ISL76682_REG_ALSIR_U + 1)
+
+#define ISL76682_CONV_TIME_MS			100
+#define ISL76682_INT_TIME_US			90000
+
+#define ISL76682_ADC_MAX			(BIT(16) - 1)
+
+struct isl76682_chip {
+	/*
+	 * Lock to synchronize access to device command register
+	 * and the content of range variable below.
+	 */
+	struct mutex			lock;
+	struct regmap			*regmap;
+	u8				range;
+	u8				command;
+};
+
+struct isl76682_range {
+	u8				range;
+	u32				als;
+	u32				ir;
+};
+
+static struct isl76682_range isl76682_range_table[] = {
+	{ ISL76682_COMMAND_RANGE_LUX_1K, 15000, 10500 },
+	{ ISL76682_COMMAND_RANGE_LUX_4K, 60000, 42000 },
+	{ ISL76682_COMMAND_RANGE_LUX_16K, 240000, 168000 },
+	{ ISL76682_COMMAND_RANGE_LUX_64K, 960000, 673000 }
+};
+
+static int isl76682_get(struct isl76682_chip *chip, bool mode_ir, int *data)
+{
+	u8 command;
+	int ret;
+
+	command = ISL76682_COMMAND_EN | ISL76682_COMMAND_MODE_CONTINUOUS |
+		  chip->range;
+
+	if (mode_ir)
+		command |= ISL76682_COMMAND_LIGHT_IR;
+
+	if (command != chip->command) {
+		ret = regmap_write(chip->regmap, ISL76682_REG_COMMAND, command);
+		if (ret)
+			return ret;
+
+		/* Need to wait for conversion time if ALS/IR mode enabled */
+		msleep(ISL76682_CONV_TIME_MS);
+
+		chip->command = command;
+	}
+
+	ret = regmap_bulk_read(chip->regmap, ISL76682_REG_ALSIR_L, data, 2);
+	*data &= ISL76682_ADC_MAX;
+	return ret;
+}
+
+static int isl76682_write_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *chan,
+			      int val, int val2, long mask)
+{
+	struct isl76682_chip *chip = iio_priv(indio_dev);
+	int i;
+
+	if (mask != IIO_CHAN_INFO_SCALE)
+		return -EINVAL;
+
+	if (val != 0)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(isl76682_range_table); i++) {
+		if (chan->type == IIO_LIGHT && val2 != isl76682_range_table[i].als)
+			continue;
+		if (chan->type == IIO_INTENSITY && val2 != isl76682_range_table[i].ir)
+			continue;
+
+		scoped_guard(mutex, &chip->lock)
+			chip->range = isl76682_range_table[i].range;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int isl76682_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int *val, int *val2, long mask)
+{
+	struct isl76682_chip *chip = iio_priv(indio_dev);
+	int ret;
+	int i;
+
+	guard(mutex)(&chip->lock);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		switch (chan->type) {
+		case IIO_LIGHT:
+			ret = isl76682_get(chip, false, val);
+			return (ret < 0) ? ret : IIO_VAL_INT;
+		case IIO_INTENSITY:
+			ret = isl76682_get(chip, true, val);
+			return (ret < 0) ? ret : IIO_VAL_INT;
+		default:
+			return -EINVAL;
+		}
+		return -EINVAL;
+	case IIO_CHAN_INFO_SCALE:
+		for (i = 0; i < ARRAY_SIZE(isl76682_range_table); i++) {
+			if (chip->range != isl76682_range_table[i].range)
+				continue;
+
+			*val = 0;
+			switch (chan->type) {
+			case IIO_LIGHT:
+				*val2 = isl76682_range_table[i].als;
+				return IIO_VAL_INT_PLUS_MICRO;
+			case IIO_INTENSITY:
+				*val2 = isl76682_range_table[i].ir;
+				return IIO_VAL_INT_PLUS_MICRO;
+			default:
+				return -EINVAL;
+			}
+		}
+		return -EINVAL;
+	case IIO_CHAN_INFO_INT_TIME:
+		*val = 0;
+		*val2 = ISL76682_INT_TIME_US;
+		return IIO_VAL_INT_PLUS_MICRO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int illuminance_scale_available[] = {
+	0, 15000,
+	0, 60000,
+	0, 240000,
+	0, 960000,
+};
+
+static int intensity_scale_available[] = {
+	0, 10500,
+	0, 42000,
+	0, 168000,
+	0, 673000,
+};
+
+static int isl76682_read_avail(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       const int **vals, int *type,
+			       int *length, long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		switch (chan->type) {
+		case IIO_LIGHT:
+			*vals = illuminance_scale_available;
+			*length = ARRAY_SIZE(illuminance_scale_available);
+			*type = IIO_VAL_INT_PLUS_MICRO;
+			return IIO_AVAIL_LIST;
+		case IIO_INTENSITY:
+			*vals = intensity_scale_available;
+			*length = ARRAY_SIZE(intensity_scale_available);
+			*type = IIO_VAL_INT_PLUS_MICRO;
+			return IIO_AVAIL_LIST;
+		default:
+			return -EINVAL;
+		}
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_chan_spec isl76682_channels[] = {
+	{
+		.type = IIO_LIGHT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+	}, {
+		.type = IIO_INTENSITY,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),
+	}
+};
+
+static const struct iio_info isl76682_info = {
+	.read_avail	= isl76682_read_avail,
+	.read_raw	= isl76682_read_raw,
+	.write_raw	= isl76682_write_raw,
+};
+
+static int isl76682_clear_configure_reg(struct isl76682_chip *chip)
+{
+	struct device *dev = regmap_get_device(chip->regmap);
+	int ret;
+
+	ret = regmap_write(chip->regmap, ISL76682_REG_COMMAND, 0x0);
+	if (ret < 0)
+		dev_err(dev, "Error %d clearing the CONFIGURE register\n", ret);
+
+	/*
+	 * In the success case, the command register was zeroed out.
+	 *
+	 * In the error case, we do not know in which state the command
+	 * register is, so we assume it is zeroed out, so that it would
+	 * be reprogrammed at the next data read out, and at that time
+	 * we hope it would be reprogrammed successfully. That is very
+	 * much a best effort approach.
+	 */
+	chip->command = 0;
+
+	return ret;
+}
+
+static void isl76682_reset_action(void *chip)
+{
+	isl76682_clear_configure_reg(chip);
+}
+
+static bool isl76682_is_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ISL76682_REG_ALSIR_L:
+	case ISL76682_REG_ALSIR_U:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config isl76682_regmap_config = {
+	.reg_bits		= 8,
+	.val_bits		= 8,
+	.volatile_reg		= isl76682_is_volatile_reg,
+	.max_register		= ISL76682_NUM_REGS - 1,
+	.num_reg_defaults_raw	= ISL76682_NUM_REGS,
+	.cache_type		= REGCACHE_FLAT,
+};
+
+static int isl76682_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct isl76682_chip *chip;
+	struct iio_dev *indio_dev;
+	int ret;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*chip));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	chip = iio_priv(indio_dev);
+
+	mutex_init(&chip->lock);
+
+	chip->regmap = devm_regmap_init_i2c(client, &isl76682_regmap_config);
+	ret = PTR_ERR_OR_ZERO(chip->regmap);
+	if (ret)
+		return dev_err_probe(dev, ret, "Error initializing regmap\n");
+
+	chip->range = ISL76682_COMMAND_RANGE_LUX_1K;
+
+	ret = isl76682_clear_configure_reg(chip);
+	if (ret < 0)
+		return ret;
+
+	ret = devm_add_action_or_reset(dev, isl76682_reset_action, chip);
+	if (ret)
+		return ret;
+
+	indio_dev->info = &isl76682_info;
+	indio_dev->channels = isl76682_channels;
+	indio_dev->num_channels = ARRAY_SIZE(isl76682_channels);
+	indio_dev->name = "isl76682";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct i2c_device_id isl76682_id[] = {
+	{ "isl76682" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, isl76682_id);
+
+static const struct of_device_id isl76682_of_match[] = {
+	{ .compatible = "isil,isl76682" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, isl76682_of_match);
+
+static struct i2c_driver isl76682_driver = {
+	.driver  = {
+		.name		= "isl76682",
+		.of_match_table	= isl76682_of_match,
+	},
+	.probe		= isl76682_probe,
+	.id_table	= isl76682_id,
+};
+module_i2c_driver(isl76682_driver);
+
+MODULE_DESCRIPTION("ISL76682 Ambient Light Sensor driver");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Marek Vasut <marex@denx.de>");
-- 
GitLab


From a163854af7c3f3351fa8c2a31cfe9f3b0bc1e51a Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:16:23 +0100
Subject: [PATCH 0837/4076] dt-bindings: iio/adc: qcom,spmi-iadc: fix reg
 description

The IADC register is just the base address in the SPMI PMIC and does not
include any length.

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231130171628.12257-2-johan+linaro@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
index 73def67fbe015..e0e0aa9d5d5b5 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
@@ -25,7 +25,7 @@ properties:
       - const: qcom,spmi-iadc
 
   reg:
-    description: IADC base address and length in the SPMI PMIC register map
+    description: IADC base address in the SPMI PMIC register map
     maxItems: 1
 
   qcom,external-resistor-micro-ohms:
-- 
GitLab


From 9751b00dbfc725d7e1f57ed023557449cb10eaa0 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:16:24 +0100
Subject: [PATCH 0838/4076] dt-bindings: iio/adc: qcom,spmi-iadc: fix example
 node name

The IADC is a child of an SPMI PMIC, which in turn sits on an SPMI bus.

Fixes: a4e6bf69418c ("dt-bindings:iio:adc:qcom,spmi-iadc: txt to yaml format conversion.")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231130171628.12257-3-johan+linaro@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
index e0e0aa9d5d5b5..16889d2d35751 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
@@ -50,7 +50,8 @@ additionalProperties: false
 examples:
   - |
     #include <dt-bindings/interrupt-controller/irq.h>
-    spmi {
+
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
         pmic_iadc: adc@3600 {
-- 
GitLab


From 9b2b96a0f91a61d7a40790a795dbbb6d5696de03 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:16:25 +0100
Subject: [PATCH 0839/4076] dt-bindings: iio/adc: qcom,spmi-iadc: clean up
 example

Clean up the IADC example by adding a newline separator, dropping an
unnecessary label and removing stray white space.

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231130171628.12257-4-johan+linaro@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml          | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
index 16889d2d35751..5ed893ef5c189 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-iadc.yaml
@@ -54,12 +54,13 @@ examples:
     pmic {
         #address-cells = <1>;
         #size-cells = <0>;
-        pmic_iadc: adc@3600 {
+
+        adc@3600 {
             compatible = "qcom,pm8941-iadc", "qcom,spmi-iadc";
             reg = <0x3600>;
             interrupts = <0x0 0x36 0x0 IRQ_TYPE_EDGE_RISING>;
             qcom,external-resistor-micro-ohms = <10000>;
-            #io-channel-cells  = <1>;
+            #io-channel-cells = <1>;
         };
     };
 ...
-- 
GitLab


From adb2af792bfb0378791a2cda74aa90f1648daa20 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:16:26 +0100
Subject: [PATCH 0840/4076] dt-bindings: iio/adc: qcom,spmi-rradc: clean up
 example

Clean up the RRADC example by dropping an unnecessary label and removing
stray white space.

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231130171628.12257-5-johan+linaro@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml          | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
index b3a626389870f..f39bc92c2b99b 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-rradc.yaml
@@ -43,9 +43,9 @@ examples:
         #address-cells = <1>;
         #size-cells = <0>;
 
-        pmic_rradc: adc@4500 {
+        adc@4500 {
             compatible = "qcom,pmi8998-rradc";
             reg = <0x4500>;
-            #io-channel-cells  = <1>;
+            #io-channel-cells = <1>;
         };
     };
-- 
GitLab


From 482aa83e3d836461f1b819715217ce4327ea70f7 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:16:27 +0100
Subject: [PATCH 0841/4076] dt-bindings: iio/adc: qcom,spmi-vadc: fix example
 node names

The VADC is a child of an SPMI PMIC, which in turn sits on an SPMI bus.

Fixes: 74e903461b17 ("dt-bindings: iio: adc: qcom,spmi-vadc: extend example")
Fixes: 5a471662b5d9 ("iio: adc: Convert the QCOM SPMI ADC bindings to .yaml format")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231130171628.12257-6-johan+linaro@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
index ad7d6fc49de58..eb02715bf691c 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
@@ -236,7 +236,7 @@ additionalProperties: false
 
 examples:
   - |
-    spmi {
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
         /* VADC node */
@@ -281,7 +281,7 @@ examples:
     #include <dt-bindings/iio/qcom,spmi-adc7-pm8350.h>
     #include <dt-bindings/interrupt-controller/irq.h>
 
-    spmi {
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
         adc@3100 {
-- 
GitLab


From 90ae7ed9bae5d7832adeba0dd574790fac65cbbf Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:16:28 +0100
Subject: [PATCH 0842/4076] dt-bindings: iio/adc: qcom,spmi-vadc: clean up
 examples

Clean up the VADC examples by dropping a comment, dropping unnecessary
labels and adding newline separators.

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231130171628.12257-7-johan+linaro@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml          | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
index eb02715bf691c..40fa0710f1f0f 100644
--- a/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/qcom,spmi-vadc.yaml
@@ -239,8 +239,8 @@ examples:
     pmic {
         #address-cells = <1>;
         #size-cells = <0>;
-        /* VADC node */
-        pmic_vadc: adc@3100 {
+
+        adc@3100 {
             compatible = "qcom,spmi-vadc";
             reg = <0x3100>;
             interrupts = <0x0 0x31 0x0 0x1>;
@@ -284,6 +284,7 @@ examples:
     pmic {
         #address-cells = <1>;
         #size-cells = <0>;
+
         adc@3100 {
             reg = <0x3100>;
             compatible = "qcom,spmi-adc7";
-- 
GitLab


From 9f4e9ffee97414d882889a943e550c53b5fa1d5c Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Thu, 16 Nov 2023 19:27:11 +0000
Subject: [PATCH 0843/4076] iio: light: pa1203001: Drop ACPI_PTR() protection.

The extra cost of always including the acpi_device_id table is trivial
vs the complexity of adding guards or __maybe_unused markings so
just stop using the ACPI_PTR() macro.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311160851.FDA4CDVE-lkp@intel.com/
Link: https://lore.kernel.org/r/20231116192711.366441-1-jic23@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/pa12203001.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/light/pa12203001.c b/drivers/iio/light/pa12203001.c
index ed241598aefbe..636432c45651d 100644
--- a/drivers/iio/light/pa12203001.c
+++ b/drivers/iio/light/pa12203001.c
@@ -472,7 +472,7 @@ static struct i2c_driver pa12203001_driver = {
 	.driver = {
 		.name = PA12203001_DRIVER_NAME,
 		.pm = &pa12203001_pm_ops,
-		.acpi_match_table = ACPI_PTR(pa12203001_acpi_match),
+		.acpi_match_table = pa12203001_acpi_match,
 	},
 	.probe = pa12203001_probe,
 	.remove = pa12203001_remove,
-- 
GitLab


From 0713ab3bd169da82c35eefd012b07b715e4ebcf7 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 10:35:33 -0800
Subject: [PATCH 0844/4076] perf stat: Exit perf stat if parse groups fails

Metrics were added by a callback but commit a4b8cfcabb1d90ec ("perf
stat: Delay metric parsing") postponed this to allow optimizations based
on the CPU configuration.

In doing so it stopped errors in metric parsing from causing 'perf stat'
termination.

This change adds the termination for bad metric names back in.

Fixes: a4b8cfcabb1d90ec ("perf stat: Delay metric parsing")
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Closes: https://lore.kernel.org/lkml/ZXByT1K6enTh2EHT@kernel.org/
Link: https://lore.kernel.org/r/20231206183533.972028-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d8e5d6f7a87a6..d22228eddccbf 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2695,15 +2695,19 @@ int cmd_stat(int argc, const char **argv)
 	 */
 	if (metrics) {
 		const char *pmu = parse_events_option_args.pmu_filter ?: "all";
+		int ret = metricgroup__parse_groups(evsel_list, pmu, metrics,
+						stat_config.metric_no_group,
+						stat_config.metric_no_merge,
+						stat_config.metric_no_threshold,
+						stat_config.user_requested_cpu_list,
+						stat_config.system_wide,
+						&stat_config.metric_events);
 
-		metricgroup__parse_groups(evsel_list, pmu, metrics,
-					stat_config.metric_no_group,
-					stat_config.metric_no_merge,
-					stat_config.metric_no_threshold,
-					stat_config.user_requested_cpu_list,
-					stat_config.system_wide,
-					&stat_config.metric_events);
 		zfree(&metrics);
+		if (ret) {
+			status = ret;
+			goto out;
+		}
 	}
 
 	if (add_default_attributes())
-- 
GitLab


From 21528c69a0d8483f7c6345b1a0bc8d8975e9a172 Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.ibm.com>
Date: Sun, 19 Nov 2023 20:12:48 -0500
Subject: [PATCH 0845/4076] rootfs: Fix support for rootfstype= when root= is
 given

Documentation/filesystems/ramfs-rootfs-initramfs.rst states:

  If CONFIG_TMPFS is enabled, rootfs will use tmpfs instead of ramfs by
  default.  To force ramfs, add "rootfstype=ramfs" to the kernel command
  line.

This currently does not work when root= is provided since then
saved_root_name contains a string and rootfstype= is ignored. Therefore,
ramfs is currently always chosen when root= is provided.

The current behavior for rootfs's filesystem is:

   root=       | rootfstype= | chosen rootfs filesystem
   ------------+-------------+--------------------------
   unspecified | unspecified | tmpfs
   unspecified | tmpfs       | tmpfs
   unspecified | ramfs       | ramfs
    provided   | ignored     | ramfs

rootfstype= should be respected regardless whether root= is given,
as shown below:

   root=       | rootfstype= | chosen rootfs filesystem
   ------------+-------------+--------------------------
   unspecified | unspecified | tmpfs  (as before)
   unspecified | tmpfs       | tmpfs  (as before)
   unspecified | ramfs       | ramfs  (as before)
    provided   | unspecified | ramfs  (compatibility with before)
    provided   | tmpfs       | tmpfs  (new)
    provided   | ramfs       | ramfs  (new)

This table represents the new behavior.

Fixes: 6e19eded3684 ("initmpfs: use initramfs if rootfstype= or root= specified")
Cc: <stable@vger.kernel.org>
Signed-off-by: Rob Landley <rob@landley.net>
Link: https://lore.kernel.org/lkml/8244c75f-445e-b15b-9dbf-266e7ca666e2@landley.net/
Reviewed-and-Tested-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Stefan Berger <stefanb@linux.ibm.com>
Link: https://lore.kernel.org/r/20231120011248.396012-1-stefanb@linux.ibm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 init/do_mounts.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/init/do_mounts.c b/init/do_mounts.c
index 5fdef94f08645..279ad28bf4fb1 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -510,7 +510,10 @@ struct file_system_type rootfs_fs_type = {
 
 void __init init_rootfs(void)
 {
-	if (IS_ENABLED(CONFIG_TMPFS) && !saved_root_name[0] &&
-		(!root_fs_names || strstr(root_fs_names, "tmpfs")))
-		is_tmpfs = true;
+	if (IS_ENABLED(CONFIG_TMPFS)) {
+		if (!saved_root_name[0] && !root_fs_names)
+			is_tmpfs = true;
+		else if (root_fs_names && !!strstr(root_fs_names, "tmpfs"))
+			is_tmpfs = true;
+	}
 }
-- 
GitLab


From 437cd966d3c6fb65add251e6db537c14dd953b8a Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Mon, 30 Oct 2023 11:23:01 +0530
Subject: [PATCH 0846/4076] firmware: xilinx: Use proper indentation in
 kernel-doc

Use tab for zynqmp_pm_load_pdi() arguments doc indentation.
No functional change.

Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Link: https://lore.kernel.org/r/1698645181-2874487-1-git-send-email-radhey.shyam.pandey@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index b0d22d4455d95..7156b4884b411 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -1395,8 +1395,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_requirement);
 
 /**
  * zynqmp_pm_load_pdi - Load and process PDI
- * @src:       Source device where PDI is located
- * @address:   PDI src address
+ * @src:	Source device where PDI is located
+ * @address:	PDI src address
  *
  * This function provides support to load PDI from linux
  *
-- 
GitLab


From a070830096e44ddaa64931d831f07e944d920c79 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Fri, 3 Nov 2023 12:29:33 +0100
Subject: [PATCH 0847/4076] drivers/comedi: use standard array-copy-function

comedi_fops.c utilizes memdup_user() to copy a userspace array.

The new function memdup_array_user() provides a standardized way to copy
userspace-arrays. It makes it easier to see that an array is being
copied and, additionally, performs a generic overflow-check which might
help make the code more robust in case of changes in the future.

Replace memdup_user() with memdup_array_user().

Suggested-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20231103112932.75795-2-pstanner@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/comedi_fops.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c
index 1548dea15df14..1b481731df964 100644
--- a/drivers/comedi/comedi_fops.c
+++ b/drivers/comedi/comedi_fops.c
@@ -1714,8 +1714,8 @@ static int __comedi_get_user_chanlist(struct comedi_device *dev,
 
 	lockdep_assert_held(&dev->mutex);
 	cmd->chanlist = NULL;
-	chanlist = memdup_user(user_chanlist,
-			       cmd->chanlist_len * sizeof(unsigned int));
+	chanlist = memdup_array_user(user_chanlist,
+				     cmd->chanlist_len, sizeof(unsigned int));
 	if (IS_ERR(chanlist))
 		return PTR_ERR(chanlist);
 
-- 
GitLab


From 190015a4bb016e0263297fa5ad20744b8ce98b50 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 1 Nov 2023 10:41:17 +0100
Subject: [PATCH 0848/4076] ipack: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Link: https://lore.kernel.org/r/435bd17b8a5ddb2fc3e42e2796117ee02263d02a.1698831664.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/ipack/ipack.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c
index cc1ecfd499286..b1471ba016a51 100644
--- a/drivers/ipack/ipack.c
+++ b/drivers/ipack/ipack.c
@@ -207,7 +207,7 @@ struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
 	if (!bus)
 		return NULL;
 
-	bus_nr = ida_simple_get(&ipack_ida, 0, 0, GFP_KERNEL);
+	bus_nr = ida_alloc(&ipack_ida, GFP_KERNEL);
 	if (bus_nr < 0) {
 		kfree(bus);
 		return NULL;
@@ -237,7 +237,7 @@ int ipack_bus_unregister(struct ipack_bus_device *bus)
 {
 	bus_for_each_dev(&ipack_bus_type, NULL, bus,
 		ipack_unregister_bus_member);
-	ida_simple_remove(&ipack_ida, bus->bus_nr);
+	ida_free(&ipack_ida, bus->bus_nr);
 	kfree(bus);
 	return 0;
 }
-- 
GitLab


From ad66d503052d51ff9efeab487f41a39816ffc11c Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 24 Nov 2023 22:14:36 +0100
Subject: [PATCH 0849/4076] parport: Save a few bytes of memory

Most of parport_register_dev_model() callers pass a 'name' that is a
constant string.

So kstrdup_const() can be used to save the duplication of this string
when it is not needed. This saves a few bytes of memory.

Use kfree_const() accordingly when this string is freed.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/0eba5f2ddd142ab0f577f67e482d1152b40ee720.1700860416.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/parport/share.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index e21831d93305d..49c74ded8a53c 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -611,7 +611,7 @@ static void free_pardevice(struct device *dev)
 {
 	struct pardevice *par_dev = to_pardevice(dev);
 
-	kfree(par_dev->name);
+	kfree_const(par_dev->name);
 	kfree(par_dev);
 }
 
@@ -682,8 +682,8 @@ parport_register_dev_model(struct parport *port, const char *name,
 			   const struct pardev_cb *par_dev_cb, int id)
 {
 	struct pardevice *par_dev;
+	const char *devname;
 	int ret;
-	char *devname;
 
 	if (port->physport->flags & PARPORT_FLAG_EXCL) {
 		/* An exclusive device is registered. */
@@ -726,7 +726,7 @@ parport_register_dev_model(struct parport *port, const char *name,
 	if (!par_dev->state)
 		goto err_put_par_dev;
 
-	devname = kstrdup(name, GFP_KERNEL);
+	devname = kstrdup_const(name, GFP_KERNEL);
 	if (!devname)
 		goto err_free_par_dev;
 
@@ -804,7 +804,7 @@ parport_register_dev_model(struct parport *port, const char *name,
 	return par_dev;
 
 err_free_devname:
-	kfree(devname);
+	kfree_const(devname);
 err_free_par_dev:
 	kfree(par_dev->state);
 err_put_par_dev:
-- 
GitLab


From 431c03095d6021bc3dae6502678c53093d2f6182 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 16 Nov 2023 15:31:59 +0100
Subject: [PATCH 0850/4076] eeprom: ee1004: Add support for multiple i2c busses

There are systems with more than 8 memory slots where the i2c bus for
SPD is multiplexed. i2c_register_spd() isn't used yet on such systems,
but it's planned. So we need to extend ee1004 accordingly.
With this extension a maximum of 8 i2c busses is supported.

I don't have such a system for testing, therefore I just verified
that the driver still works on a system with a single i2c bus.

For the sake of simplicity the extension uses the existing global
mutex to protect access on all busses. This could be improved,
but we support 8 busses only, and SPD data is small and rarely
accessed, so it shouldn't be a problem.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/f1a216a8-e77c-49f2-8838-561349b30ab8@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/eeprom/ee1004.c | 94 ++++++++++++++++++++++++------------
 1 file changed, 63 insertions(+), 31 deletions(-)

diff --git a/drivers/misc/eeprom/ee1004.c b/drivers/misc/eeprom/ee1004.c
index a1acd77130f26..fd12ce06a4d5e 100644
--- a/drivers/misc/eeprom/ee1004.c
+++ b/drivers/misc/eeprom/ee1004.c
@@ -31,6 +31,7 @@
  * over performance.
  */
 
+#define EE1004_MAX_BUSSES		8
 #define EE1004_ADDR_SET_PAGE		0x36
 #define EE1004_NUM_PAGES		2
 #define EE1004_PAGE_SIZE		256
@@ -42,9 +43,13 @@
  * from page selection to end of read.
  */
 static DEFINE_MUTEX(ee1004_bus_lock);
-static struct i2c_client *ee1004_set_page[EE1004_NUM_PAGES];
-static unsigned int ee1004_dev_count;
-static int ee1004_current_page;
+
+static struct ee1004_bus_data {
+	struct i2c_adapter *adap;
+	struct i2c_client *set_page[EE1004_NUM_PAGES];
+	unsigned int dev_count;
+	int current_page;
+} ee1004_bus_data[EE1004_MAX_BUSSES];
 
 static const struct i2c_device_id ee1004_ids[] = {
 	{ "ee1004", 0 },
@@ -54,11 +59,29 @@ MODULE_DEVICE_TABLE(i2c, ee1004_ids);
 
 /*-------------------------------------------------------------------------*/
 
-static int ee1004_get_current_page(void)
+static struct ee1004_bus_data *ee1004_get_bus_data(struct i2c_adapter *adap)
+{
+	int i;
+
+	for (i = 0; i < EE1004_MAX_BUSSES; i++)
+		if (ee1004_bus_data[i].adap == adap)
+			return ee1004_bus_data + i;
+
+	/* If not existent yet, create new entry */
+	for (i = 0; i < EE1004_MAX_BUSSES; i++)
+		if (!ee1004_bus_data[i].adap) {
+			ee1004_bus_data[i].adap = adap;
+			return ee1004_bus_data + i;
+		}
+
+	return NULL;
+}
+
+static int ee1004_get_current_page(struct ee1004_bus_data *bd)
 {
 	int err;
 
-	err = i2c_smbus_read_byte(ee1004_set_page[0]);
+	err = i2c_smbus_read_byte(bd->set_page[0]);
 	if (err == -ENXIO) {
 		/* Nack means page 1 is selected */
 		return 1;
@@ -72,28 +95,29 @@ static int ee1004_get_current_page(void)
 	return 0;
 }
 
-static int ee1004_set_current_page(struct device *dev, int page)
+static int ee1004_set_current_page(struct i2c_client *client, int page)
 {
+	struct ee1004_bus_data *bd = i2c_get_clientdata(client);
 	int ret;
 
-	if (page == ee1004_current_page)
+	if (page == bd->current_page)
 		return 0;
 
 	/* Data is ignored */
-	ret = i2c_smbus_write_byte(ee1004_set_page[page], 0x00);
+	ret = i2c_smbus_write_byte(bd->set_page[page], 0x00);
 	/*
 	 * Don't give up just yet. Some memory modules will select the page
 	 * but not ack the command. Check which page is selected now.
 	 */
-	if (ret == -ENXIO && ee1004_get_current_page() == page)
+	if (ret == -ENXIO && ee1004_get_current_page(bd) == page)
 		ret = 0;
 	if (ret < 0) {
-		dev_err(dev, "Failed to select page %d (%d)\n", page, ret);
+		dev_err(&client->dev, "Failed to select page %d (%d)\n", page, ret);
 		return ret;
 	}
 
-	dev_dbg(dev, "Selected page %d\n", page);
-	ee1004_current_page = page;
+	dev_dbg(&client->dev, "Selected page %d\n", page);
+	bd->current_page = page;
 
 	return 0;
 }
@@ -106,7 +130,7 @@ static ssize_t ee1004_eeprom_read(struct i2c_client *client, char *buf,
 	page = offset >> EE1004_PAGE_SHIFT;
 	offset &= (1 << EE1004_PAGE_SHIFT) - 1;
 
-	status = ee1004_set_current_page(&client->dev, page);
+	status = ee1004_set_current_page(client, page);
 	if (status)
 		return status;
 
@@ -158,17 +182,18 @@ static struct bin_attribute *ee1004_attrs[] = {
 
 BIN_ATTRIBUTE_GROUPS(ee1004);
 
-static void ee1004_cleanup(int idx)
+static void ee1004_cleanup(int idx, struct ee1004_bus_data *bd)
 {
-	if (--ee1004_dev_count == 0)
-		while (--idx >= 0) {
-			i2c_unregister_device(ee1004_set_page[idx]);
-			ee1004_set_page[idx] = NULL;
-		}
+	if (--bd->dev_count == 0) {
+		while (--idx >= 0)
+			i2c_unregister_device(bd->set_page[idx]);
+		memset(bd, 0, sizeof(struct ee1004_bus_data));
+	}
 }
 
 static int ee1004_probe(struct i2c_client *client)
 {
+	struct ee1004_bus_data *bd;
 	int err, cnr = 0;
 
 	/* Make sure we can operate on this adapter */
@@ -178,9 +203,19 @@ static int ee1004_probe(struct i2c_client *client)
 				     I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_READ_BYTE_DATA))
 		return -EPFNOSUPPORT;
 
-	/* Use 2 dummy devices for page select command */
 	mutex_lock(&ee1004_bus_lock);
-	if (++ee1004_dev_count == 1) {
+
+	bd = ee1004_get_bus_data(client->adapter);
+	if (!bd) {
+		mutex_unlock(&ee1004_bus_lock);
+		return dev_err_probe(&client->dev, -ENOSPC,
+				     "Only %d busses supported", EE1004_MAX_BUSSES);
+	}
+
+	i2c_set_clientdata(client, bd);
+
+	if (++bd->dev_count == 1) {
+		/* Use 2 dummy devices for page select command */
 		for (cnr = 0; cnr < EE1004_NUM_PAGES; cnr++) {
 			struct i2c_client *cl;
 
@@ -189,20 +224,15 @@ static int ee1004_probe(struct i2c_client *client)
 				err = PTR_ERR(cl);
 				goto err_clients;
 			}
-			ee1004_set_page[cnr] = cl;
+			bd->set_page[cnr] = cl;
 		}
 
 		/* Remember current page to avoid unneeded page select */
-		err = ee1004_get_current_page();
+		err = ee1004_get_current_page(bd);
 		if (err < 0)
 			goto err_clients;
 		dev_dbg(&client->dev, "Currently selected page: %d\n", err);
-		ee1004_current_page = err;
-	} else if (client->adapter != ee1004_set_page[0]->adapter) {
-		dev_err(&client->dev,
-			"Driver only supports devices on a single I2C bus\n");
-		err = -EOPNOTSUPP;
-		goto err_clients;
+		bd->current_page = err;
 	}
 	mutex_unlock(&ee1004_bus_lock);
 
@@ -213,7 +243,7 @@ static int ee1004_probe(struct i2c_client *client)
 	return 0;
 
  err_clients:
-	ee1004_cleanup(cnr);
+	ee1004_cleanup(cnr, bd);
 	mutex_unlock(&ee1004_bus_lock);
 
 	return err;
@@ -221,9 +251,11 @@ static int ee1004_probe(struct i2c_client *client)
 
 static void ee1004_remove(struct i2c_client *client)
 {
+	struct ee1004_bus_data *bd = i2c_get_clientdata(client);
+
 	/* Remove page select clients if this is the last device */
 	mutex_lock(&ee1004_bus_lock);
-	ee1004_cleanup(EE1004_NUM_PAGES);
+	ee1004_cleanup(EE1004_NUM_PAGES, bd);
 	mutex_unlock(&ee1004_bus_lock);
 }
 
-- 
GitLab


From f922b16aa5fad7284e2b7fd7c22bab13c0e418b6 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:09 -0800
Subject: [PATCH 0851/4076] firmware: xilinx: Update firmware call interface to
 support additional args

System-level platform management layer (do_fw_call()) has support for
maximum of 5 arguments as of now (1 EEMI API ID + 4 command arguments).
In order to support new EEMI PM_IOCTL IDs (Secure Read/Write), this
support must be extended to support one additional argument, which
results in a configuration of - 1 EEMI API ID + 5 command arguments.

Update zynqmp_pm_invoke_fn() and do_fw_call() with this new definition
containing variable arguments. As a result, update all the references
to pm invoke function with the updated definition.

Co-developed-by: Izhar Ameer Shaikh <izhar.ameer.shaikh@amd.com>
Signed-off-by: Izhar Ameer Shaikh <izhar.ameer.shaikh@amd.com>
Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-2-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c        | 278 +++++++++++-------------
 drivers/soc/xilinx/xlnx_event_manager.c |   2 +-
 drivers/soc/xilinx/zynqmp_power.c       |   2 +-
 include/linux/firmware/xlnx-zynqmp.h    |   3 +-
 4 files changed, 132 insertions(+), 153 deletions(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 7156b4884b411..2a7fd3fbac8c4 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -106,8 +106,7 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 	}
 }
 
-static noinline int do_fw_call_fail(u64 arg0, u64 arg1, u64 arg2,
-				    u32 *ret_payload)
+static noinline int do_fw_call_fail(u32 *ret_payload, u32 num_args, ...)
 {
 	return -ENODEV;
 }
@@ -116,25 +115,35 @@ static noinline int do_fw_call_fail(u64 arg0, u64 arg1, u64 arg2,
  * PM function call wrapper
  * Invoke do_fw_call_smc or do_fw_call_hvc, depending on the configuration
  */
-static int (*do_fw_call)(u64, u64, u64, u32 *ret_payload) = do_fw_call_fail;
+static int (*do_fw_call)(u32 *ret_payload, u32, ...) = do_fw_call_fail;
 
 /**
  * do_fw_call_smc() - Call system-level platform management layer (SMC)
- * @arg0:		Argument 0 to SMC call
- * @arg1:		Argument 1 to SMC call
- * @arg2:		Argument 2 to SMC call
+ * @num_args:		Number of variable arguments should be <= 8
  * @ret_payload:	Returned value array
  *
  * Invoke platform management function via SMC call (no hypervisor present).
  *
  * Return: Returns status, either success or error+reason
  */
-static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
-				   u32 *ret_payload)
+static noinline int do_fw_call_smc(u32 *ret_payload, u32 num_args, ...)
 {
 	struct arm_smccc_res res;
+	u64 args[8] = {0};
+	va_list arg_list;
+	u8 i;
 
-	arm_smccc_smc(arg0, arg1, arg2, 0, 0, 0, 0, 0, &res);
+	if (num_args > 8)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
+
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u64);
+
+	va_end(arg_list);
+
+	arm_smccc_smc(args[0], args[1], args[2], args[3], args[4], args[5], args[6], args[7], &res);
 
 	if (ret_payload) {
 		ret_payload[0] = lower_32_bits(res.a0);
@@ -148,9 +157,7 @@ static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
 
 /**
  * do_fw_call_hvc() - Call system-level platform management layer (HVC)
- * @arg0:		Argument 0 to HVC call
- * @arg1:		Argument 1 to HVC call
- * @arg2:		Argument 2 to HVC call
+ * @num_args:		Number of variable arguments should be <= 8
  * @ret_payload:	Returned value array
  *
  * Invoke platform management function via HVC
@@ -159,12 +166,24 @@ static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
  *
  * Return: Returns status, either success or error+reason
  */
-static noinline int do_fw_call_hvc(u64 arg0, u64 arg1, u64 arg2,
-				   u32 *ret_payload)
+static noinline int do_fw_call_hvc(u32 *ret_payload, u32 num_args, ...)
 {
 	struct arm_smccc_res res;
+	u64 args[8] = {0};
+	va_list arg_list;
+	u8 i;
+
+	if (num_args > 8)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
+
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u64);
 
-	arm_smccc_hvc(arg0, arg1, arg2, 0, 0, 0, 0, 0, &res);
+	va_end(arg_list);
+
+	arm_smccc_hvc(args[0], args[1], args[2], args[3], args[4], args[5], args[6], args[7], &res);
 
 	if (ret_payload) {
 		ret_payload[0] = lower_32_bits(res.a0);
@@ -184,7 +203,7 @@ static int __do_feature_check_call(const u32 api_id, u32 *ret_payload)
 	smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK;
 	smc_arg[1] = api_id;
 
-	ret = do_fw_call(smc_arg[0], smc_arg[1], 0, ret_payload);
+	ret = do_fw_call(ret_payload, 2, smc_arg[0], smc_arg[1]);
 	if (ret)
 		ret = -EOPNOTSUPP;
 	else
@@ -295,11 +314,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_is_function_supported);
  * zynqmp_pm_invoke_fn() - Invoke the system-level platform management layer
  *			   caller function depending on the configuration
  * @pm_api_id:		Requested PM-API call
- * @arg0:		Argument 0 to requested PM-API call
- * @arg1:		Argument 1 to requested PM-API call
- * @arg2:		Argument 2 to requested PM-API call
- * @arg3:		Argument 3 to requested PM-API call
  * @ret_payload:	Returned value array
+ * @num_args:		Number of arguments to requested PM-API call
  *
  * Invoke platform management function for SMC or HVC call, depending on
  * configuration.
@@ -316,26 +332,38 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_is_function_supported);
  *
  * Return: Returns status, either success or error+reason
  */
-int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
-			u32 arg2, u32 arg3, u32 *ret_payload)
+int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...)
 {
 	/*
 	 * Added SIP service call Function Identifier
 	 * Make sure to stay in x0 register
 	 */
-	u64 smc_arg[4];
-	int ret;
+	u64 smc_arg[8];
+	int ret, i;
+	va_list arg_list;
+	u32 args[14] = {0};
+
+	if (num_args > 14)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
 
 	/* Check if feature is supported or not */
 	ret = zynqmp_pm_feature(pm_api_id);
 	if (ret < 0)
 		return ret;
 
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u32);
+
+	va_end(arg_list);
+
 	smc_arg[0] = PM_SIP_SVC | pm_api_id;
-	smc_arg[1] = ((u64)arg1 << 32) | arg0;
-	smc_arg[2] = ((u64)arg3 << 32) | arg2;
+	for (i = 0; i < 7; i++)
+		smc_arg[i + 1] = ((u64)args[(i * 2) + 1] << 32) | args[i * 2];
 
-	return do_fw_call(smc_arg[0], smc_arg[1], smc_arg[2], ret_payload);
+	return do_fw_call(ret_payload, 8, smc_arg[0], smc_arg[1], smc_arg[2], smc_arg[3],
+			  smc_arg[4], smc_arg[5], smc_arg[6], smc_arg[7]);
 }
 
 static u32 pm_api_version;
@@ -347,14 +375,12 @@ int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset)
 {
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(TF_A_PM_REGISTER_SGI, sgi_num, reset, 0, 0,
-				  NULL);
+	ret = zynqmp_pm_invoke_fn(TF_A_PM_REGISTER_SGI, NULL, 2, sgi_num, reset);
 	if (!ret)
 		return ret;
 
 	/* try old implementation as fallback strategy if above fails */
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_REGISTER_SGI, sgi_num,
-				   reset, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, IOCTL_REGISTER_SGI, sgi_num, reset);
 }
 
 /**
@@ -376,7 +402,7 @@ int zynqmp_pm_get_api_version(u32 *version)
 		*version = pm_api_version;
 		return 0;
 	}
-	ret = zynqmp_pm_invoke_fn(PM_GET_API_VERSION, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_API_VERSION, ret_payload, 0);
 	*version = ret_payload[1];
 
 	return ret;
@@ -399,7 +425,7 @@ int zynqmp_pm_get_chipid(u32 *idcode, u32 *version)
 	if (!idcode || !version)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, ret_payload, 0);
 	*idcode = ret_payload[1];
 	*version = ret_payload[2];
 
@@ -427,7 +453,7 @@ static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 		return 0;
 	}
 
-	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, ret_payload, 0);
 	if (ret < 0)
 		return ret;
 
@@ -459,8 +485,7 @@ static int zynqmp_pm_get_trustzone_version(u32 *version)
 		*version = pm_tz_version;
 		return 0;
 	}
-	ret = zynqmp_pm_invoke_fn(PM_GET_TRUSTZONE_VERSION, 0, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_TRUSTZONE_VERSION, ret_payload, 0);
 	*version = ret_payload[1];
 
 	return ret;
@@ -507,8 +532,8 @@ int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out)
 {
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_QUERY_DATA, qdata.qid, qdata.arg1,
-				  qdata.arg2, qdata.arg3, out);
+	ret = zynqmp_pm_invoke_fn(PM_QUERY_DATA, out, 4, qdata.qid, qdata.arg1, qdata.arg2,
+				  qdata.arg3);
 
 	/*
 	 * For clock name query, all bytes in SMC response are clock name
@@ -530,7 +555,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_query_data);
  */
 int zynqmp_pm_clock_enable(u32 clock_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_ENABLE, clock_id, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_ENABLE, NULL, 1, clock_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_enable);
 
@@ -545,7 +570,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_enable);
  */
 int zynqmp_pm_clock_disable(u32 clock_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_DISABLE, clock_id, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_DISABLE, NULL, 1, clock_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_disable);
 
@@ -564,8 +589,7 @@ int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETSTATE, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETSTATE, ret_payload, 1, clock_id);
 	*state = ret_payload[1];
 
 	return ret;
@@ -584,8 +608,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getstate);
  */
 int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETDIVIDER, clock_id, divider,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_SETDIVIDER, NULL, 2, clock_id, divider);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setdivider);
 
@@ -604,8 +627,7 @@ int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETDIVIDER, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETDIVIDER, ret_payload, 1, clock_id);
 	*divider = ret_payload[1];
 
 	return ret;
@@ -623,10 +645,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getdivider);
  */
 int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETRATE, clock_id,
-				   lower_32_bits(rate),
-				   upper_32_bits(rate),
-				   0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_SETRATE, NULL, 3, clock_id, lower_32_bits(rate),
+				   upper_32_bits(rate));
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setrate);
 
@@ -645,8 +665,7 @@ int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETRATE, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETRATE, ret_payload, 1, clock_id);
 	*rate = ((u64)ret_payload[2] << 32) | ret_payload[1];
 
 	return ret;
@@ -664,8 +683,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getrate);
  */
 int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETPARENT, clock_id,
-				   parent_id, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_SETPARENT, NULL, 2, clock_id, parent_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setparent);
 
@@ -684,8 +702,7 @@ int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETPARENT, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETPARENT, ret_payload, 1, clock_id);
 	*parent_id = ret_payload[1];
 
 	return ret;
@@ -704,8 +721,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getparent);
  */
 int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_PLL_FRAC_MODE,
-				   clk_id, mode, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_PLL_FRAC_MODE, clk_id, mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_mode);
 
@@ -721,8 +737,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_mode);
  */
 int zynqmp_pm_get_pll_frac_mode(u32 clk_id, u32 *mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_PLL_FRAC_MODE,
-				   clk_id, 0, mode);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, mode, 3, 0, IOCTL_GET_PLL_FRAC_MODE, clk_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_mode);
 
@@ -739,8 +754,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_mode);
  */
 int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_PLL_FRAC_DATA,
-				   clk_id, data, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_PLL_FRAC_DATA, clk_id, data);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_data);
 
@@ -756,8 +770,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_data);
  */
 int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_PLL_FRAC_DATA,
-				   clk_id, 0, data);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, data, 3, 0, IOCTL_GET_PLL_FRAC_DATA, clk_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_data);
 
@@ -778,9 +791,8 @@ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value)
 	u32 mask = (node_id == NODE_SD_0) ? GENMASK(15, 0) : GENMASK(31, 16);
 
 	if (value) {
-		return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-					   IOCTL_SET_SD_TAPDELAY,
-					   type, value, NULL);
+		return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node_id, IOCTL_SET_SD_TAPDELAY, type,
+					   value);
 	}
 
 	/*
@@ -798,7 +810,7 @@ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value)
 	 * Use PM_MMIO_READ/PM_MMIO_WRITE to re-implement the missing counter
 	 * part of IOCTL_SET_SD_TAPDELAY which clears SDx_ITAPDLYENA bits.
 	 */
-	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, reg, mask, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, NULL, 2, reg, mask);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay);
 
@@ -814,8 +826,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay);
  */
 int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SD_DLL_RESET,
-				   type, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_SD_DLL_RESET, type);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset);
 
@@ -831,8 +842,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset);
  */
 int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, dev_id, IOCTL_OSPI_MUX_SELECT,
-				   select, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, dev_id, IOCTL_OSPI_MUX_SELECT, select);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_ospi_mux_select);
 
@@ -847,8 +857,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_ospi_mux_select);
  */
 int zynqmp_pm_write_ggs(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_WRITE_GGS,
-				   index, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_WRITE_GGS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_write_ggs);
 
@@ -863,8 +872,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_write_ggs);
  */
 int zynqmp_pm_read_ggs(u32 index, u32 *value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_READ_GGS,
-				   index, 0, value);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, value, 3, 0, IOCTL_READ_GGS, index);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_read_ggs);
 
@@ -880,8 +888,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_read_ggs);
  */
 int zynqmp_pm_write_pggs(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_WRITE_PGGS, index, value,
-				   NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_WRITE_PGGS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_write_pggs);
 
@@ -897,15 +904,13 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_write_pggs);
  */
 int zynqmp_pm_read_pggs(u32 index, u32 *value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_READ_PGGS, index, 0,
-				   value);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, value, 3, 0, IOCTL_READ_PGGS, index);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_read_pggs);
 
 int zynqmp_pm_set_tapdelay_bypass(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_TAPDELAY_BYPASS,
-				   index, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_TAPDELAY_BYPASS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_tapdelay_bypass);
 
@@ -920,8 +925,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_tapdelay_bypass);
  */
 int zynqmp_pm_set_boot_health_status(u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_BOOT_HEALTH_STATUS,
-				   value, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, 0, IOCTL_SET_BOOT_HEALTH_STATUS, value);
 }
 
 /**
@@ -935,8 +939,7 @@ int zynqmp_pm_set_boot_health_status(u32 value)
 int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset,
 			   const enum zynqmp_pm_reset_action assert_flag)
 {
-	return zynqmp_pm_invoke_fn(PM_RESET_ASSERT, reset, assert_flag,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_RESET_ASSERT, NULL, 2, reset, assert_flag);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_reset_assert);
 
@@ -955,8 +958,7 @@ int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status)
 	if (!status)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_RESET_GET_STATUS, reset, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_RESET_GET_STATUS, ret_payload, 1, reset);
 	*status = ret_payload[1];
 
 	return ret;
@@ -981,9 +983,8 @@ int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_LOAD, lower_32_bits(address),
-				  upper_32_bits(address), size, flags,
-				  ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_LOAD, ret_payload, 4, lower_32_bits(address),
+				  upper_32_bits(address), size, flags);
 	if (ret_payload[0])
 		return -ret_payload[0];
 
@@ -1008,7 +1009,7 @@ int zynqmp_pm_fpga_get_status(u32 *value)
 	if (!value)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_GET_STATUS, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_GET_STATUS, ret_payload, 0);
 	*value = ret_payload[1];
 
 	return ret;
@@ -1036,11 +1037,9 @@ int zynqmp_pm_fpga_get_config_status(u32 *value)
 	lower_addr = lower_32_bits((u64)&buf);
 	upper_addr = upper_32_bits((u64)&buf);
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_READ,
-				  XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET,
-				  lower_addr, upper_addr,
-				  XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG,
-				  ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_READ, ret_payload, 4,
+				  XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET, lower_addr, upper_addr,
+				  XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG);
 
 	*value = ret_payload[1];
 
@@ -1058,7 +1057,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_fpga_get_config_status);
  */
 int zynqmp_pm_pinctrl_request(const u32 pin)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_REQUEST, pin, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_REQUEST, NULL, 1, pin);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_request);
 
@@ -1072,7 +1071,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_request);
  */
 int zynqmp_pm_pinctrl_release(const u32 pin)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_RELEASE, pin, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_RELEASE, NULL, 1, pin);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_release);
 
@@ -1093,8 +1092,7 @@ int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
 	if (!id)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_GET_FUNCTION, pin, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_GET_FUNCTION, ret_payload, 1, pin);
 	*id = ret_payload[1];
 
 	return ret;
@@ -1112,8 +1110,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_get_function);
  */
 int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_SET_FUNCTION, pin, id,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_SET_FUNCTION, NULL, 2, pin, id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_set_function);
 
@@ -1136,8 +1133,7 @@ int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param,
 	if (!value)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_GET, pin, param,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_GET, ret_payload, 2, pin, param);
 	*value = ret_payload[1];
 
 	return ret;
@@ -1166,8 +1162,7 @@ int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param,
 			return -EOPNOTSUPP;
 	}
 
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_SET, pin,
-				   param, value, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_SET, NULL, 3, pin, param, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_set_config);
 
@@ -1185,8 +1180,7 @@ unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode)
 	unsigned int ret;
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 
-	ret = zynqmp_pm_invoke_fn(PM_MMIO_READ, CRL_APB_BOOT_PIN_CTRL, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_MMIO_READ, ret_payload, 1, CRL_APB_BOOT_PIN_CTRL);
 
 	*ps_mode = ret_payload[1];
 
@@ -1205,8 +1199,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_read);
  */
 int zynqmp_pm_bootmode_write(u32 ps_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, CRL_APB_BOOT_PIN_CTRL,
-				   CRL_APB_BOOTPIN_CTRL_MASK, ps_mode, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, NULL, 3, CRL_APB_BOOT_PIN_CTRL,
+				   CRL_APB_BOOTPIN_CTRL_MASK, ps_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write);
 
@@ -1221,7 +1215,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write);
  */
 int zynqmp_pm_init_finalize(void)
 {
-	return zynqmp_pm_invoke_fn(PM_PM_INIT_FINALIZE, 0, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PM_INIT_FINALIZE, NULL, 0);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_init_finalize);
 
@@ -1235,7 +1229,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_init_finalize);
  */
 int zynqmp_pm_set_suspend_mode(u32 mode)
 {
-	return zynqmp_pm_invoke_fn(PM_SET_SUSPEND_MODE, mode, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_SET_SUSPEND_MODE, NULL, 1, mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_suspend_mode);
 
@@ -1254,8 +1248,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_suspend_mode);
 int zynqmp_pm_request_node(const u32 node, const u32 capabilities,
 			   const u32 qos, const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_REQUEST_NODE, node, capabilities,
-				   qos, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_REQUEST_NODE, NULL, 4, node, capabilities, qos, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_request_node);
 
@@ -1271,7 +1264,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_request_node);
  */
 int zynqmp_pm_release_node(const u32 node)
 {
-	return zynqmp_pm_invoke_fn(PM_RELEASE_NODE, node, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_RELEASE_NODE, NULL, 1, node);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_release_node);
 
@@ -1290,8 +1283,7 @@ int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				  IOCTL_GET_RPU_OPER_MODE, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_IOCTL, ret_payload, 2, node_id, IOCTL_GET_RPU_OPER_MODE);
 
 	/* only set rpu_mode if no error */
 	if (ret == XST_PM_SUCCESS)
@@ -1313,9 +1305,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_rpu_mode);
  */
 int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				   IOCTL_SET_RPU_OPER_MODE, (u32)rpu_mode,
-				   0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_SET_RPU_OPER_MODE,
+				   (u32)rpu_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_rpu_mode);
 
@@ -1331,9 +1322,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_rpu_mode);
  */
 int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				   IOCTL_TCM_COMB_CONFIG, (u32)tcm_mode, 0,
-				   NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_TCM_COMB_CONFIG,
+				   (u32)tcm_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_tcm_config);
 
@@ -1348,7 +1338,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_tcm_config);
 int zynqmp_pm_force_pwrdwn(const u32 node,
 			   const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_FORCE_POWERDOWN, node, ack, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_FORCE_POWERDOWN, NULL, 2, node, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_force_pwrdwn);
 
@@ -1367,8 +1357,8 @@ int zynqmp_pm_request_wake(const u32 node,
 			   const enum zynqmp_pm_request_ack ack)
 {
 	/* set_addr flag is encoded into 1st bit of address */
-	return zynqmp_pm_invoke_fn(PM_REQUEST_WAKEUP, node, address | set_addr,
-				   address >> 32, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_REQUEST_WAKEUP, NULL, 4, node, address | set_addr,
+				   address >> 32, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_request_wake);
 
@@ -1388,8 +1378,7 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities,
 			      const u32 qos,
 			      const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_SET_REQUIREMENT, node, capabilities,
-				   qos, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_SET_REQUIREMENT, NULL, 4, node, capabilities, qos, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_requirement);
 
@@ -1404,9 +1393,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_requirement);
  */
 int zynqmp_pm_load_pdi(const u32 src, const u64 address)
 {
-	return zynqmp_pm_invoke_fn(PM_LOAD_PDI, src,
-				   lower_32_bits(address),
-				   upper_32_bits(address), 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_LOAD_PDI, NULL, 3, src, lower_32_bits(address),
+				   upper_32_bits(address));
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_load_pdi);
 
@@ -1426,9 +1414,8 @@ int zynqmp_pm_aes_engine(const u64 address, u32 *out)
 	if (!out)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_SECURE_AES, upper_32_bits(address),
-				  lower_32_bits(address),
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_SECURE_AES, ret_payload, 2, upper_32_bits(address),
+				  lower_32_bits(address));
 	*out = ret_payload[1];
 
 	return ret;
@@ -1456,8 +1443,7 @@ int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags)
 	u32 lower_addr = lower_32_bits(address);
 	u32 upper_addr = upper_32_bits(address);
 
-	return zynqmp_pm_invoke_fn(PM_SECURE_SHA, upper_addr, lower_addr,
-				   size, flags, NULL);
+	return zynqmp_pm_invoke_fn(PM_SECURE_SHA, NULL, 4, upper_addr, lower_addr, size, flags);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_sha_hash);
 
@@ -1479,8 +1465,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_sha_hash);
 int zynqmp_pm_register_notifier(const u32 node, const u32 event,
 				const u32 wake, const u32 enable)
 {
-	return zynqmp_pm_invoke_fn(PM_REGISTER_NOTIFIER, node, event,
-				   wake, enable, NULL);
+	return zynqmp_pm_invoke_fn(PM_REGISTER_NOTIFIER, NULL, 4, node, event, wake, enable);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_register_notifier);
 
@@ -1493,8 +1478,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_register_notifier);
  */
 int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype)
 {
-	return zynqmp_pm_invoke_fn(PM_SYSTEM_SHUTDOWN, type, subtype,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_SYSTEM_SHUTDOWN, NULL, 2, type, subtype);
 }
 
 /**
@@ -1506,8 +1490,7 @@ int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype)
  */
 int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_FEATURE_CONFIG,
-				   id, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_FEATURE_CONFIG, id, value);
 }
 
 /**
@@ -1520,8 +1503,7 @@ int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value)
 int zynqmp_pm_get_feature_config(enum pm_feature_config_id id,
 				 u32 *payload)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_FEATURE_CONFIG,
-				   id, 0, payload);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, payload, 3, 0, IOCTL_GET_FEATURE_CONFIG, id);
 }
 
 /**
@@ -1534,8 +1516,7 @@ int zynqmp_pm_get_feature_config(enum pm_feature_config_id id,
  */
 int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node, IOCTL_SET_SD_CONFIG,
-				   config, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node, IOCTL_SET_SD_CONFIG, config, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_config);
 
@@ -1550,8 +1531,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_config);
 int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config,
 			     u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node, IOCTL_SET_GEM_CONFIG,
-				   config, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node, IOCTL_SET_GEM_CONFIG, config, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_gem_config);
 
diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index 86a048a10a13f..adb875f898299 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -483,7 +483,7 @@ static void xlnx_call_notify_cb_handler(const u32 *payload)
 
 static void xlnx_get_event_callback_data(u32 *buf)
 {
-	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf);
+	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, buf, 0);
 }
 
 static irqreturn_t xlnx_event_handler(int irq, void *dev_id)
diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c
index c2c819701eec1..0de0acf80ef89 100644
--- a/drivers/soc/xilinx/zynqmp_power.c
+++ b/drivers/soc/xilinx/zynqmp_power.c
@@ -51,7 +51,7 @@ static enum pm_suspend_mode suspend_mode = PM_SUSPEND_MODE_STD;
 
 static void zynqmp_pm_get_callback_data(u32 *buf)
 {
-	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf);
+	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, buf, 0);
 }
 
 static void suspend_event_callback(const u32 *payload, void *data)
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index d1ea3898564ca..41190bbed8edf 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -509,8 +509,7 @@ struct zynqmp_pm_query_data {
 	u32 arg3;
 };
 
-int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
-			u32 arg2, u32 arg3, u32 *ret_payload);
+int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...);
 
 #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE)
 int zynqmp_pm_get_api_version(u32 *version);
-- 
GitLab


From f689a0ca45fcdf4139727a3a02a49efbb1902306 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:10 -0800
Subject: [PATCH 0852/4076] firmware: xilinx: Expand feature check to support
 all PLM modules

To support feature check for all modules, append the module id of the API
that is being checked to the feature check API so it could be routed to
the target module for processing.

There is no need to check compatible string because the board information
is taken via firmware interface.

Co-developed-by: Saeed Nowshadi <saeed.nowshadi@amd.com>
Signed-off-by: Saeed Nowshadi <saeed.nowshadi@amd.com>
Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-3-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 41 ++++++++++++++++------------
 include/linux/firmware/xlnx-zynqmp.h | 11 ++++++++
 2 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 2a7fd3fbac8c4..ec77aefee17e4 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -199,9 +199,29 @@ static int __do_feature_check_call(const u32 api_id, u32 *ret_payload)
 {
 	int ret;
 	u64 smc_arg[2];
+	u32 module_id;
+	u32 feature_check_api_id;
 
-	smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK;
-	smc_arg[1] = api_id;
+	module_id = FIELD_GET(MODULE_ID_MASK, api_id);
+
+	/*
+	 * Feature check of APIs belonging to PM, XSEM, and TF-A are handled by calling
+	 * PM_FEATURE_CHECK API. For other modules, call PM_API_FEATURES API.
+	 */
+	if (module_id == PM_MODULE_ID || module_id == XSEM_MODULE_ID || module_id == TF_A_MODULE_ID)
+		feature_check_api_id = PM_FEATURE_CHECK;
+	else
+		feature_check_api_id = PM_API_FEATURES;
+
+	/*
+	 * Feature check of TF-A APIs is done in the TF-A layer and it expects for
+	 * MODULE_ID_MASK bits of SMC's arg[0] to be the same as PM_MODULE_ID.
+	 */
+	if (module_id == TF_A_MODULE_ID)
+		module_id = PM_MODULE_ID;
+
+	smc_arg[0] = PM_SIP_SVC | FIELD_PREP(MODULE_ID_MASK, module_id) | feature_check_api_id;
+	smc_arg[1] = (api_id & API_ID_MASK);
 
 	ret = do_fw_call(ret_payload, 2, smc_arg[0], smc_arg[1]);
 	if (ret)
@@ -1904,22 +1924,9 @@ static int zynqmp_firmware_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	np = of_find_compatible_node(NULL, NULL, "xlnx,zynqmp");
-	if (!np) {
-		np = of_find_compatible_node(NULL, NULL, "xlnx,versal");
-		if (!np)
-			return 0;
-
+	ret = do_feature_check_call(PM_FEATURE_CHECK);
+	if (ret >= 0 && ((ret & FIRMWARE_VERSION_MASK) >= PM_API_VERSION_1))
 		feature_check_enabled = true;
-	}
-
-	if (!feature_check_enabled) {
-		ret = do_feature_check_call(PM_FEATURE_CHECK);
-		if (ret >= 0)
-			feature_check_enabled = true;
-	}
-
-	of_node_put(np);
 
 	devinfo = devm_kzalloc(dev, sizeof(*devinfo), GFP_KERNEL);
 	if (!devinfo)
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 41190bbed8edf..e9a7fece5efef 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -32,6 +32,7 @@
 #define PM_SIP_SVC			0xC2000000
 
 /* PM API versions */
+#define PM_API_VERSION_1	1
 #define PM_API_VERSION_2	2
 
 #define PM_PINCTRL_PARAM_SET_VERSION	2
@@ -47,6 +48,9 @@
 #define FAMILY_CODE_MASK	GENMASK(27, 21)
 #define SUB_FAMILY_CODE_MASK	GENMASK(20, 19)
 
+#define API_ID_MASK		GENMASK(7, 0)
+#define MODULE_ID_MASK		GENMASK(11, 8)
+
 /* ATF only commands */
 #define TF_A_PM_REGISTER_SGI		0xa04
 #define PM_GET_TRUSTZONE_VERSION	0xa03
@@ -112,6 +116,12 @@
 #define XPM_EVENT_ERROR_MASK_NOC_NCR		BIT(13)
 #define XPM_EVENT_ERROR_MASK_NOC_CR		BIT(12)
 
+enum pm_module_id {
+	PM_MODULE_ID = 0x0,
+	XSEM_MODULE_ID = 0x3,
+	TF_A_MODULE_ID = 0xa,
+};
+
 enum pm_api_cb_id {
 	PM_INIT_SUSPEND_CB = 30,
 	PM_ACKNOWLEDGE_CB = 31,
@@ -119,6 +129,7 @@ enum pm_api_cb_id {
 };
 
 enum pm_api_id {
+	PM_API_FEATURES = 0,
 	PM_GET_API_VERSION = 1,
 	PM_REGISTER_NOTIFIER = 5,
 	PM_FORCE_POWERDOWN = 8,
-- 
GitLab


From a9d061840010df64aad2a3e5b308e663d6a36e2f Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:11 -0800
Subject: [PATCH 0853/4076] firmware: xilinx: Register event manager driver

Use family code in order to register event manager
driver for Versal and Versal NET platforms, instead
of using compatible string.

Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-4-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index ec77aefee17e4..533679a07b575 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -1916,7 +1916,6 @@ ATTRIBUTE_GROUPS(zynqmp_firmware);
 static int zynqmp_firmware_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct device_node *np;
 	struct zynqmp_devinfo *devinfo;
 	int ret;
 
@@ -1979,14 +1978,12 @@ static int zynqmp_firmware_probe(struct platform_device *pdev)
 
 	zynqmp_pm_api_debugfs_init();
 
-	np = of_find_compatible_node(NULL, NULL, "xlnx,versal");
-	if (np) {
+	if (pm_family_code == VERSAL_FAMILY_CODE) {
 		em_dev = platform_device_register_data(&pdev->dev, "xlnx_event_manager",
 						       -1, NULL, 0);
 		if (IS_ERR(em_dev))
 			dev_err_probe(&pdev->dev, PTR_ERR(em_dev), "EM register fail with error\n");
 	}
-	of_node_put(np);
 
 	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
-- 
GitLab


From 8c016c807a90535432543204dbbb032e4a709009 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:12 -0800
Subject: [PATCH 0854/4076] drivers: soc: xilinx: Fix error message on SGI
 registration failure

Failure to register SGI for firmware event notification is non-fatal error
when feature is not supported by other modules such as Xen and TF-A. Add
_info level log message for such special case.

Also add XST_PM_INVALID_VERSION error code and map it to -EOPNOSUPP Linux
kernel error code. If feature is not supported or EEMI API version is
mismatch, firmware can return XST_PM_INVALID_VERSION = 4 or
XST_PM_NO_FEATURE = 19 error code.

Co-developed-by: Tanmay Shah <tanmay.shah@amd.com>
Signed-off-by: Tanmay Shah <tanmay.shah@amd.com>
Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-5-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c        | 4 +++-
 drivers/soc/xilinx/xlnx_event_manager.c | 6 +++++-
 include/linux/firmware/xlnx-zynqmp.h    | 1 +
 3 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 533679a07b575..077b49e440b57 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -92,6 +92,8 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 		return 0;
 	case XST_PM_NO_FEATURE:
 		return -ENOTSUPP;
+	case XST_PM_INVALID_VERSION:
+		return -EOPNOTSUPP;
 	case XST_PM_NO_ACCESS:
 		return -EACCES;
 	case XST_PM_ABORT_SUSPEND:
@@ -396,7 +398,7 @@ int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset)
 	int ret;
 
 	ret = zynqmp_pm_invoke_fn(TF_A_PM_REGISTER_SGI, NULL, 2, sgi_num, reset);
-	if (!ret)
+	if (ret != -EOPNOTSUPP && !ret)
 		return ret;
 
 	/* try old implementation as fallback strategy if above fails */
diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index adb875f898299..27a8d89a0a091 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -653,7 +653,11 @@ static int xlnx_event_manager_probe(struct platform_device *pdev)
 
 	ret = zynqmp_pm_register_sgi(sgi_num, 0);
 	if (ret) {
-		dev_err(&pdev->dev, "SGI %d Registration over TF-A failed with %d\n", sgi_num, ret);
+		if (ret == -EOPNOTSUPP)
+			dev_err(&pdev->dev, "SGI registration not supported by TF-A or Xen\n");
+		else
+			dev_err(&pdev->dev, "SGI %d registration failed, err %d\n", sgi_num, ret);
+
 		xlnx_event_cleanup_sgi(pdev);
 		return ret;
 	}
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index e9a7fece5efef..ec1800c860069 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -172,6 +172,7 @@ enum pm_api_id {
 /* PMU-FW return status codes */
 enum pm_ret_status {
 	XST_PM_SUCCESS = 0,
+	XST_PM_INVALID_VERSION = 4,
 	XST_PM_NO_FEATURE = 19,
 	XST_PM_INTERNAL = 2000,
 	XST_PM_CONFLICT = 2001,
-- 
GitLab


From 5dac2a98f6542ae1ce78b702374ea4be3f5ee07d Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:13 -0800
Subject: [PATCH 0855/4076] firmware: zynqmp: Add support to handle IPI CRC
 failure

Added new PM error code XST_PM_INVALID_CRC to handle CRC validation failure
during IPI communication.

Co-developed-by: Naman Trivedi Manojbhai <naman.trivedimanojbhai@amd.com>
Signed-off-by: Naman Trivedi Manojbhai <naman.trivedimanojbhai@amd.com>
Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-6-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 1 +
 include/linux/firmware/xlnx-zynqmp.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 077b49e440b57..caa0952bfc422 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -103,6 +103,7 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 	case XST_PM_INTERNAL:
 	case XST_PM_CONFLICT:
 	case XST_PM_INVALID_NODE:
+	case XST_PM_INVALID_CRC:
 	default:
 		return -EINVAL;
 	}
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index ec1800c860069..6b48294f3c923 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -174,6 +174,7 @@ enum pm_ret_status {
 	XST_PM_SUCCESS = 0,
 	XST_PM_INVALID_VERSION = 4,
 	XST_PM_NO_FEATURE = 19,
+	XST_PM_INVALID_CRC = 301,
 	XST_PM_INTERNAL = 2000,
 	XST_PM_CONFLICT = 2001,
 	XST_PM_NO_ACCESS = 2002,
-- 
GitLab


From 5bb03d0dd76700a830243776a99275575cbb2ee1 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 1 Nov 2023 10:33:33 +0100
Subject: [PATCH 0856/4076] base: soc: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/f0ef849446c9b3df7d6b16b1a58d089b4c17276c.1698831191.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/soc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/base/soc.c b/drivers/base/soc.c
index 8dec5228fde3d..c741d0845852a 100644
--- a/drivers/base/soc.c
+++ b/drivers/base/soc.c
@@ -106,7 +106,7 @@ static void soc_release(struct device *dev)
 {
 	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
 
-	ida_simple_remove(&soc_ida, soc_dev->soc_dev_num);
+	ida_free(&soc_ida, soc_dev->soc_dev_num);
 	kfree(soc_dev->dev.groups);
 	kfree(soc_dev);
 }
@@ -155,7 +155,7 @@ struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr
 	soc_attr_groups[1] = soc_dev_attr->custom_attr_group;
 
 	/* Fetch a unique (reclaimable) SOC ID. */
-	ret = ida_simple_get(&soc_ida, 0, 0, GFP_KERNEL);
+	ret = ida_alloc(&soc_ida, GFP_KERNEL);
 	if (ret < 0)
 		goto out3;
 	soc_dev->soc_dev_num = ret;
-- 
GitLab


From 48b5928e18dc27e05cab3dc4c78cd8a15baaf1e5 Mon Sep 17 00:00:00 2001
From: Gregory Price <gourry.memverge@gmail.com>
Date: Mon, 30 Oct 2023 00:42:39 -0400
Subject: [PATCH 0857/4076] base/node.c: initialize the accessor list before
 registering

The current code registers the node as available in the node array
before initializing the accessor list.  This makes it so that
anything which might access the accessor list as a result of
allocations will cause an undefined memory access.

In one example, an extension to access hmat data during interleave
caused this undefined access as a result of a bulk allocation
that occurs during node initialization but before the accessor
list is initialized.

Initialize the accessor list before making the node generally
available to the global system.

Fixes: 08d9dbe72b1f ("node: Link memory nodes to their compute nodes")
Signed-off-by: Gregory Price <gregory.price@memverge.com>
Link: https://lore.kernel.org/r/20231030044239.971756-1-gregory.price@memverge.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/node.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 493d533f83755..4d588f4658c85 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -868,11 +868,15 @@ int __register_one_node(int nid)
 {
 	int error;
 	int cpu;
+	struct node *node;
 
-	node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
-	if (!node_devices[nid])
+	node = kzalloc(sizeof(struct node), GFP_KERNEL);
+	if (!node)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&node->access_list);
+	node_devices[nid] = node;
+
 	error = register_node(node_devices[nid], nid);
 
 	/* link cpu under this node */
@@ -881,7 +885,6 @@ int __register_one_node(int nid)
 			register_cpu_under_node(cpu, nid);
 	}
 
-	INIT_LIST_HEAD(&node_devices[nid]->access_list);
 	node_init_caches(nid);
 
 	return error;
-- 
GitLab


From b17b70212dbf3f60ab95eb563dc165d235e75336 Mon Sep 17 00:00:00 2001
From: Mukesh Ojha <quic_mojha@quicinc.com>
Date: Mon, 30 Oct 2023 15:51:14 +0530
Subject: [PATCH 0858/4076] fs/sysfs/dir.c : Fix typo in comment

Typo correction
kboject => kobject

Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com>
Link: https://lore.kernel.org/r/1698661274-32540-1-git-send-email-quic_mojha@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/sysfs/dir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index b6b6796e16160..4df2afa551dc6 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -81,7 +81,7 @@ void sysfs_remove_dir(struct kobject *kobj)
 	struct kernfs_node *kn = kobj->sd;
 
 	/*
-	 * In general, kboject owner is responsible for ensuring removal
+	 * In general, kobject owner is responsible for ensuring removal
 	 * doesn't race with other operations and sysfs doesn't provide any
 	 * protection; however, when @kobj is used as a symlink target, the
 	 * symlinking entity usually doesn't own @kobj and thus has no
-- 
GitLab


From 4c095734d92a46c243eca79b86ff3237fcce9a57 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 1 Nov 2023 10:36:04 +0100
Subject: [PATCH 0859/4076] software node: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/c7cdc3566c783d106138698b1e1923351fabace8.1698831275.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/swnode.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index 1886995a0b3a3..f7c4317b2ccfe 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -747,10 +747,10 @@ static void software_node_release(struct kobject *kobj)
 	struct swnode *swnode = kobj_to_swnode(kobj);
 
 	if (swnode->parent) {
-		ida_simple_remove(&swnode->parent->child_ids, swnode->id);
+		ida_free(&swnode->parent->child_ids, swnode->id);
 		list_del(&swnode->entry);
 	} else {
-		ida_simple_remove(&swnode_root_ids, swnode->id);
+		ida_free(&swnode_root_ids, swnode->id);
 	}
 
 	if (swnode->allocated)
@@ -776,8 +776,8 @@ swnode_register(const struct software_node *node, struct swnode *parent,
 	if (!swnode)
 		return ERR_PTR(-ENOMEM);
 
-	ret = ida_simple_get(parent ? &parent->child_ids : &swnode_root_ids,
-			     0, 0, GFP_KERNEL);
+	ret = ida_alloc(parent ? &parent->child_ids : &swnode_root_ids,
+			GFP_KERNEL);
 	if (ret < 0) {
 		kfree(swnode);
 		return ERR_PTR(ret);
-- 
GitLab


From bef52aa0f3de1b7d8c258c13b16e577361dabf3a Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Thu, 9 Nov 2023 12:10:08 +0200
Subject: [PATCH 0860/4076] acpi: property: Let args be NULL in
 __acpi_node_get_property_reference

fwnode_get_property_reference_args() may not be called with args argument
NULL on ACPI, OF already supports this. Add the missing NULL checks and
document this.

The purpose is to be able to count the references.

Fixes: 977d5ad39f3e ("ACPI: Convert ACPI reference args to generic fwnode reference args")
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231109101010.1329587-2-sakari.ailus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/acpi/property.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 6979a3f9f90a8..4d042673d57bf 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -852,6 +852,7 @@ static int acpi_get_ref_args(struct fwnode_reference_args *args,
  * @index: Index of the reference to return
  * @num_args: Maximum number of arguments after each reference
  * @args: Location to store the returned reference with optional arguments
+ *	  (may be NULL)
  *
  * Find property with @name, verifify that it is a package containing at least
  * one object reference and if so, store the ACPI device object pointer to the
@@ -908,6 +909,9 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		if (!device)
 			return -EINVAL;
 
+		if (!args)
+			return 0;
+
 		args->fwnode = acpi_fwnode_handle(device);
 		args->nargs = 0;
 		return 0;
-- 
GitLab


From 1eaea4b3604eb9ca7d9a1e73d88fc121bb4061f5 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Thu, 9 Nov 2023 12:10:09 +0200
Subject: [PATCH 0861/4076] software node: Let args be NULL in
 software_node_get_reference_args

fwnode_get_property_reference_args() may not be called with args argument
NULL and while OF already supports this. Add the missing NULL check.

The purpose is to be able to count the references.

Fixes: b06184acf751 ("software node: Add software_node_get_reference_args()")
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231109101010.1329587-3-sakari.ailus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/swnode.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index f7c4317b2ccfe..36512fb75a201 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -541,6 +541,9 @@ software_node_get_reference_args(const struct fwnode_handle *fwnode,
 	if (nargs > NR_FWNODE_REFERENCE_ARGS)
 		return -EINVAL;
 
+	if (!args)
+		return 0;
+
 	args->fwnode = software_node_get(refnode);
 	args->nargs = nargs;
 
-- 
GitLab


From 3babbf614ae66018fa4f97865a7e3a3b8a590fb0 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Thu, 9 Nov 2023 12:10:10 +0200
Subject: [PATCH 0862/4076] device property: fwnode_property_get_reference_args
 allows NULL args now

All three fwnode_property_get_reference_args() implemantations now allow
args argument to be NULL. Document this.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231109101010.1329587-4-sakari.ailus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/property.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 8c40abed78524..8667b13639d2b 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -508,6 +508,7 @@ EXPORT_SYMBOL_GPL(fwnode_property_match_string);
  * @nargs:	Number of arguments. Ignored if @nargs_prop is non-NULL.
  * @index:	Index of the reference, from zero onwards.
  * @args:	Result structure with reference and integer arguments.
+ *		May be NULL.
  *
  * Obtain a reference based on a named property in an fwnode, with
  * integer arguments.
-- 
GitLab


From 055467378bf14d6cc6d17e52dcfc76313b531bd7 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Mon, 13 Nov 2023 14:09:47 -0800
Subject: [PATCH 0863/4076] driver core: Enable fw_devlink=rpm by default

fw_devlink=on has stabilized and is working correctly. Let's start using
device links created by fw_devlink to also enforce runtime PM ordering.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20231113220948.80089-1-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index e574671941041..6736c1de3ba43 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1641,7 +1641,7 @@ static void device_links_purge(struct device *dev)
 #define FW_DEVLINK_FLAGS_RPM		(FW_DEVLINK_FLAGS_ON | \
 					 DL_FLAG_PM_RUNTIME)
 
-static u32 fw_devlink_flags = FW_DEVLINK_FLAGS_ON;
+static u32 fw_devlink_flags = FW_DEVLINK_FLAGS_RPM;
 static int __init fw_devlink_setup(char *arg)
 {
 	if (!arg)
-- 
GitLab


From 7c41da586e9f45bf8842b4dca08681df8d586ebb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 22 Nov 2023 10:33:33 +0100
Subject: [PATCH 0864/4076] driver core: Emit reason for pending deferred probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Ending a boot log with

	platform 3f202000.mmc: deferred probe pending

is already a nice hint about the problem. Sometimes there is a more
detailed error indicator available, add that to the output.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231122093332.274145-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/dd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 0c3725c3eefa4..85152537dbf12 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -313,7 +313,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work)
 
 	mutex_lock(&deferred_probe_mutex);
 	list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe)
-		dev_info(p->device, "deferred probe pending\n");
+		dev_info(p->device, "deferred probe pending: %s", p->deferred_probe_reason ?: "(reason unknown)\n");
 	mutex_unlock(&deferred_probe_mutex);
 
 	fw_devlink_probing_done();
-- 
GitLab


From f538d35a782e56d6d7722ea9c1d8b44899de88c8 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 5 Dec 2023 18:16:19 -0500
Subject: [PATCH 0865/4076] staging: rtl8192e: renamed variable
 bRegShortGI20MHz

Coding style issue, checkpatch Avoid CamelCase,
rename it bRegShortGI20MHz -> reg_short_gi_20mhz

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231205231623.23070-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index dd86faab6f53f..411a1d61128cd 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -98,7 +98,7 @@ struct rt_hi_throughput {
 	u8 cur_bw_40mhz;
 	u8 bRegShortGI40MHz;
 	u8 bCurShortGI40MHz;
-	u8 bRegShortGI20MHz;
+	u8 reg_short_gi_20mhz;
 	u8 bCurShortGI20MHz;
 	u8 bRegSuppCCK;
 	u8 bCurSuppCCK;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index f263f329db77a..c8792f6397ed6 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -71,7 +71,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	ht_info->bRegShortGI20MHz = 1;
+	ht_info->reg_short_gi_20mhz = 1;
 	ht_info->bRegShortGI40MHz = 1;
 
 	ht_info->bRegBW40MHz = 1;
@@ -478,7 +478,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->cur_tx_bw40mhz = ((pPeerHTInfo->RecommemdedTxWidth == 1) ?
 				 true : false);
 
-	ht_info->bCurShortGI20MHz = ((ht_info->bRegShortGI20MHz) ?
+	ht_info->bCurShortGI20MHz = ((ht_info->reg_short_gi_20mhz) ?
 				    ((pPeerHTCap->ShortGI20Mhz == 1) ?
 				    true : false) : false);
 	ht_info->bCurShortGI40MHz = ((ht_info->bRegShortGI40MHz) ?
-- 
GitLab


From 0e3a51520632b9b5f38a98b993e05d6b5d783163 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 5 Dec 2023 18:16:20 -0500
Subject: [PATCH 0866/4076] staging: rtl8192e: renamed variable
 bRegShortGI40MHz

Coding style issue, checkpatch Avoid CamelCase,
rename it bRegShortGI40MHz -> reg_short_gi_40mhz

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231205231623.23070-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 411a1d61128cd..825c60cbcacb4 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -96,7 +96,7 @@ struct rt_hi_throughput {
 	u8 current_ht_support;
 	u8 bRegBW40MHz;
 	u8 cur_bw_40mhz;
-	u8 bRegShortGI40MHz;
+	u8 reg_short_gi_40mhz;
 	u8 bCurShortGI40MHz;
 	u8 reg_short_gi_20mhz;
 	u8 bCurShortGI20MHz;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index c8792f6397ed6..580b1423c46be 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -72,7 +72,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
 	ht_info->reg_short_gi_20mhz = 1;
-	ht_info->bRegShortGI40MHz = 1;
+	ht_info->reg_short_gi_40mhz = 1;
 
 	ht_info->bRegBW40MHz = 1;
 
@@ -481,7 +481,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->bCurShortGI20MHz = ((ht_info->reg_short_gi_20mhz) ?
 				    ((pPeerHTCap->ShortGI20Mhz == 1) ?
 				    true : false) : false);
-	ht_info->bCurShortGI40MHz = ((ht_info->bRegShortGI40MHz) ?
+	ht_info->bCurShortGI40MHz = ((ht_info->reg_short_gi_40mhz) ?
 				     ((pPeerHTCap->ShortGI40Mhz == 1) ?
 				     true : false) : false);
 
-- 
GitLab


From c4dc2c60ce94a28008e17819c18a29ad45f18eca Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 5 Dec 2023 18:16:21 -0500
Subject: [PATCH 0867/4076] staging: rtl8192e: renamed variable bRegBW40MHz

Coding style issue, checkpatch Avoid CamelCase,
rename it bRegBW40MHz -> reg_bw_40mhz

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231205231623.23070-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     |  2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 825c60cbcacb4..ef88d7d713fb3 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -94,7 +94,7 @@ enum ht_aggre_mode {
 struct rt_hi_throughput {
 	u8 enable_ht;
 	u8 current_ht_support;
-	u8 bRegBW40MHz;
+	u8 reg_bw_40mhz;
 	u8 cur_bw_40mhz;
 	u8 reg_short_gi_40mhz;
 	u8 bCurShortGI40MHz;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 580b1423c46be..68ad082d41be7 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -74,9 +74,9 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->reg_short_gi_20mhz = 1;
 	ht_info->reg_short_gi_40mhz = 1;
 
-	ht_info->bRegBW40MHz = 1;
+	ht_info->reg_bw_40mhz = 1;
 
-	if (ht_info->bRegBW40MHz)
+	if (ht_info->reg_bw_40mhz)
 		ht_info->bRegSuppCCK = 1;
 	else
 		ht_info->bRegSuppCCK = true;
@@ -275,7 +275,7 @@ void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
 		pCapELE->ChlWidth = 0;
 	else
-		pCapELE->ChlWidth = (pHT->bRegBW40MHz ? 1 : 0);
+		pCapELE->ChlWidth = (pHT->reg_bw_40mhz ? 1 : 0);
 
 	pCapELE->MimoPwrSave		= pHT->self_mimo_ps;
 	pCapELE->GreenField		= 0;
@@ -286,7 +286,7 @@ void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
 	pCapELE->RxSTBC			= 0;
 	pCapELE->DelayBA		= 0;
 	pCapELE->MaxAMSDUSize = (MAX_RECEIVE_BUFFER_SIZE >= 7935) ? 1 : 0;
-	pCapELE->DssCCk = ((pHT->bRegBW40MHz) ? (pHT->bRegSuppCCK ? 1 : 0) : 0);
+	pCapELE->DssCCk = ((pHT->reg_bw_40mhz) ? (pHT->bRegSuppCCK ? 1 : 0) : 0);
 	pCapELE->PSMP = 0;
 	pCapELE->LSigTxopProtect = 0;
 
@@ -734,7 +734,7 @@ void HTSetConnectBwMode(struct rtllib_device *ieee,
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	if (!ht_info->bRegBW40MHz)
+	if (!ht_info->reg_bw_40mhz)
 		return;
 
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
-- 
GitLab


From 41c93322313d9db23d42cf578c9826e55ee16fc6 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 5 Dec 2023 18:16:22 -0500
Subject: [PATCH 0868/4076] staging: rtl8192e: renamed variable bRegSuppCCK

Coding style issue, checkpatch Avoid CamelCase,
rename it bRegSuppCCK -> reg_supp_cck

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231205231623.23070-5-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index ef88d7d713fb3..c3efff2873d42 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -100,7 +100,7 @@ struct rt_hi_throughput {
 	u8 bCurShortGI40MHz;
 	u8 reg_short_gi_20mhz;
 	u8 bCurShortGI20MHz;
-	u8 bRegSuppCCK;
+	u8 reg_supp_cck;
 	u8 bCurSuppCCK;
 	enum ht_spec_ver ePeerHTSpecVer;
 	struct ht_capab_ele SelfHTCap;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 68ad082d41be7..910f8e9c93942 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -77,9 +77,9 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->reg_bw_40mhz = 1;
 
 	if (ht_info->reg_bw_40mhz)
-		ht_info->bRegSuppCCK = 1;
+		ht_info->reg_supp_cck = 1;
 	else
-		ht_info->bRegSuppCCK = true;
+		ht_info->reg_supp_cck = true;
 
 	ht_info->nAMSDU_MaxSize = 7935UL;
 	ht_info->bAMSDU_Support = 0;
@@ -286,7 +286,7 @@ void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
 	pCapELE->RxSTBC			= 0;
 	pCapELE->DelayBA		= 0;
 	pCapELE->MaxAMSDUSize = (MAX_RECEIVE_BUFFER_SIZE >= 7935) ? 1 : 0;
-	pCapELE->DssCCk = ((pHT->reg_bw_40mhz) ? (pHT->bRegSuppCCK ? 1 : 0) : 0);
+	pCapELE->DssCCk = ((pHT->reg_bw_40mhz) ? (pHT->reg_supp_cck ? 1 : 0) : 0);
 	pCapELE->PSMP = 0;
 	pCapELE->LSigTxopProtect = 0;
 
@@ -485,7 +485,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 				     ((pPeerHTCap->ShortGI40Mhz == 1) ?
 				     true : false) : false);
 
-	ht_info->bCurSuppCCK = ((ht_info->bRegSuppCCK) ?
+	ht_info->bCurSuppCCK = ((ht_info->reg_supp_cck) ?
 			       ((pPeerHTCap->DssCCk == 1) ? true :
 			       false) : false);
 
-- 
GitLab


From d0a665b48876867a5cab9d86f28df05f0697c454 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 5 Dec 2023 18:16:23 -0500
Subject: [PATCH 0869/4076] staging: rtl8192e: renamed variable nAMSDU_MaxSize

Coding style issue, checkpatch Avoid CamelCase,
rename it nAMSDU_MaxSize -> amsdu_max_size

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231205231623.23070-6-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index c3efff2873d42..5018c3905be85 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -108,7 +108,7 @@ struct rt_hi_throughput {
 	u8 PeerHTCapBuf[32];
 	u8 PeerHTInfoBuf[32];
 	u8 bAMSDU_Support;
-	u16 nAMSDU_MaxSize;
+	u16 amsdu_max_size;
 	u8 bCurrent_AMSDU_Support;
 	u16 nCurrent_AMSDU_MaxSize;
 	u8 bAMPDUEnable;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 910f8e9c93942..6475832f23f67 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -81,7 +81,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	else
 		ht_info->reg_supp_cck = true;
 
-	ht_info->nAMSDU_MaxSize = 7935UL;
+	ht_info->amsdu_max_size = 7935UL;
 	ht_info->bAMSDU_Support = 0;
 
 	ht_info->bAMPDUEnable = 1;
@@ -493,10 +493,10 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 
 	nMaxAMSDUSize = (pPeerHTCap->MaxAMSDUSize == 0) ? 3839 : 7935;
 
-	if (ht_info->nAMSDU_MaxSize > nMaxAMSDUSize)
+	if (ht_info->amsdu_max_size > nMaxAMSDUSize)
 		ht_info->nCurrent_AMSDU_MaxSize = nMaxAMSDUSize;
 	else
-		ht_info->nCurrent_AMSDU_MaxSize = ht_info->nAMSDU_MaxSize;
+		ht_info->nCurrent_AMSDU_MaxSize = ht_info->amsdu_max_size;
 
 	ht_info->current_ampdu_enable = ht_info->bAMPDUEnable;
 	if (ieee->rtllib_ap_sec_type &&
@@ -569,7 +569,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	ht_info->bCurSuppCCK = true;
 
 	ht_info->bCurrent_AMSDU_Support = false;
-	ht_info->nCurrent_AMSDU_MaxSize = ht_info->nAMSDU_MaxSize;
+	ht_info->nCurrent_AMSDU_MaxSize = ht_info->amsdu_max_size;
 	ht_info->current_mpdu_density = ht_info->MPDU_Density;
 	ht_info->CurrentAMPDUFactor = ht_info->AMPDU_Factor;
 
-- 
GitLab


From e70f17ed997cb7ee6c34089f2cdc2a9edc886503 Mon Sep 17 00:00:00 2001
From: Umang Jain <umang.jain@ideasonboard.com>
Date: Tue, 5 Dec 2023 14:11:54 +0530
Subject: [PATCH 0870/4076] staging: vc04_services: Drop vchiq_log_error() in
 favour of dev_err

Drop vchiq_log_error() macro which wraps dev_dbg(). Introduce the usage
of dev_err() directly.

Signed-off-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/20231205084157.73819-2-umang.jain@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../interface/vchiq_arm/vchiq_arm.c           |  50 ++++----
 .../interface/vchiq_arm/vchiq_connected.c     |   6 +-
 .../interface/vchiq_arm/vchiq_core.c          | 113 +++++++++---------
 .../interface/vchiq_arm/vchiq_core.h          |   4 -
 .../interface/vchiq_arm/vchiq_dev.c           |  45 ++++---
 5 files changed, 101 insertions(+), 117 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 7978fb6dc4fbd..b403400edd8e1 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -683,8 +683,7 @@ int vchiq_initialise(struct vchiq_instance **instance_out)
 		usleep_range(500, 600);
 	}
 	if (i == VCHIQ_INIT_RETRIES) {
-		vchiq_log_error(state->dev, VCHIQ_CORE, "%s: videocore not initialized\n",
-				__func__);
+		dev_err(state->dev, "core: %s: Videocore not initialized\n", __func__);
 		ret = -ENOTCONN;
 		goto failed;
 	} else if (i > 0) {
@@ -694,8 +693,7 @@ int vchiq_initialise(struct vchiq_instance **instance_out)
 
 	instance = kzalloc(sizeof(*instance), GFP_KERNEL);
 	if (!instance) {
-		vchiq_log_error(state->dev, VCHIQ_CORE,
-				"%s: error allocating vchiq instance\n", __func__);
+		dev_err(state->dev, "core: %s: Cannot allocate vchiq instance\n", __func__);
 		ret = -ENOMEM;
 		goto failed;
 	}
@@ -967,8 +965,7 @@ vchiq_blocking_bulk_transfer(struct vchiq_instance *instance, unsigned int handl
 	} else {
 		waiter = kzalloc(sizeof(*waiter), GFP_KERNEL);
 		if (!waiter) {
-			vchiq_log_error(service->state->dev, VCHIQ_CORE,
-					"%s - out of memory", __func__);
+			dev_err(service->state->dev, "core: %s: - Out of memory\n", __func__);
 			return -ENOMEM;
 		}
 	}
@@ -1290,8 +1287,8 @@ vchiq_keepalive_vchiq_callback(struct vchiq_instance *instance,
 			       struct vchiq_header *header,
 			       unsigned int service_user, void *bulk_user)
 {
-	vchiq_log_error(instance->state->dev, VCHIQ_SUSPEND,
-			"%s callback reason %d", __func__, reason);
+	dev_err(instance->state->dev, "suspend: %s: callback reason %d\n",
+		__func__, reason);
 	return 0;
 }
 
@@ -1315,22 +1312,20 @@ vchiq_keepalive_thread_func(void *v)
 
 	ret = vchiq_initialise(&instance);
 	if (ret) {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-				"%s vchiq_initialise failed %d", __func__, ret);
+		dev_err(state->dev, "suspend: %s: vchiq_initialise failed %d\n", __func__, ret);
 		goto exit;
 	}
 
 	status = vchiq_connect(instance);
 	if (status) {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-				"%s vchiq_connect failed %d", __func__, status);
+		dev_err(state->dev, "suspend: %s: vchiq_connect failed %d\n", __func__, status);
 		goto shutdown;
 	}
 
 	status = vchiq_add_service(instance, &params, &ka_handle);
 	if (status) {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-				"%s vchiq_open_service failed %d", __func__, status);
+		dev_err(state->dev, "suspend: %s: vchiq_open_service failed %d\n",
+			__func__, status);
 		goto shutdown;
 	}
 
@@ -1338,8 +1333,7 @@ vchiq_keepalive_thread_func(void *v)
 		long rc = 0, uc = 0;
 
 		if (wait_for_completion_interruptible(&arm_state->ka_evt)) {
-			vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-					"%s interrupted", __func__);
+			dev_err(state->dev, "suspend: %s: interrupted\n", __func__);
 			flush_signals(current);
 			continue;
 		}
@@ -1359,16 +1353,15 @@ vchiq_keepalive_thread_func(void *v)
 			atomic_inc(&arm_state->ka_use_ack_count);
 			status = vchiq_use_service(instance, ka_handle);
 			if (status) {
-				vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-						"%s vchiq_use_service error %d", __func__, status);
+				dev_err(state->dev, "suspend: %s: vchiq_use_service error %d\n",
+					__func__, status);
 			}
 		}
 		while (rc--) {
 			status = vchiq_release_service(instance, ka_handle);
 			if (status) {
-				vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-						"%s vchiq_release_service error %d", __func__,
-						status);
+				dev_err(state->dev, "suspend: %s: vchiq_release_service error %d\n",
+					__func__, status);
 			}
 		}
 	}
@@ -1403,7 +1396,7 @@ vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service,
 			 service->client_id);
 		entity_uc = &service->service_use_count;
 	} else {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND, "%s null service ptr", __func__);
+		dev_err(state->dev, "suspend: %s: null service ptr\n", __func__);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1686,10 +1679,10 @@ vchiq_check_service(struct vchiq_service *service)
 	read_unlock_bh(&arm_state->susp_res_lock);
 
 	if (ret) {
-		vchiq_log_error(service->state->dev, VCHIQ_SUSPEND,
-				"%s ERROR - %p4cc:%d service count %d, state count %d", __func__,
-				&service->base.fourcc, service->client_id,
-				service->service_use_count, arm_state->videocore_use_count);
+		dev_err(service->state->dev,
+			"suspend: %s:  %p4cc:%d service count %d, state count %d\n",
+			__func__, &service->base.fourcc, service->client_id,
+			service->service_use_count, arm_state->videocore_use_count);
 		vchiq_dump_service_use_state(service->state);
 	}
 out:
@@ -1722,9 +1715,8 @@ void vchiq_platform_conn_state_changed(struct vchiq_state *state,
 					      (void *)state,
 					      threadname);
 	if (IS_ERR(arm_state->ka_thread)) {
-		vchiq_log_error(state->dev, VCHIQ_SUSPEND,
-				"vchiq: FATAL: couldn't create thread %s",
-				threadname);
+		dev_err(state->dev, "suspend: Couldn't create thread %s\n",
+			threadname);
 	} else {
 		wake_up_process(arm_state->ka_thread);
 	}
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
index 21f9fa1a17132..3cad13f09e376 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_connected.c
@@ -39,9 +39,9 @@ void vchiq_add_connected_callback(struct vchiq_device *device, void (*callback)(
 		callback();
 	} else {
 		if (g_num_deferred_callbacks >= MAX_CALLBACKS) {
-			vchiq_log_error(&device->dev, VCHIQ_CORE,
-					"There already %d callback registered - please increase MAX_CALLBACKS",
-					g_num_deferred_callbacks);
+			dev_err(&device->dev,
+				"core: There already %d callback registered - please increase MAX_CALLBACKS\n",
+				g_num_deferred_callbacks);
 		} else {
 			g_deferred_callback[g_num_deferred_callbacks] =
 				callback;
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index e0022acb4c585..63f412815a32c 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -741,10 +741,10 @@ process_free_data_message(struct vchiq_state *state, u32 *service_found,
 		 */
 		complete(&quota->quota_event);
 	} else if (count == 0) {
-		vchiq_log_error(state->dev, VCHIQ_CORE,
-				"service %d message_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)",
-				port, quota->message_use_count, header, msgid, header->msgid,
-				header->size);
+		dev_err(state->dev,
+			"core: service %d message_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)\n",
+			port, quota->message_use_count, header, msgid,
+			header->msgid, header->size);
 		WARN(1, "invalid message use count\n");
 	}
 	if (!BITSET_IS_SET(service_found, port)) {
@@ -766,9 +766,9 @@ process_free_data_message(struct vchiq_state *state, u32 *service_found,
 			vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: pfq:%d %x@%pK - slot_use->%d",
 					state->id, port, header->size, header, count - 1);
 		} else {
-			vchiq_log_error(state->dev, VCHIQ_CORE,
-					"service %d slot_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)",
-					port, count, header, msgid, header->msgid, header->size);
+			dev_err(state->dev,
+				"core: service %d slot_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)\n",
+				port, count, header, msgid, header->msgid, header->size);
 			WARN(1, "bad slot use count\n");
 		}
 	}
@@ -831,9 +831,9 @@ process_free_queue(struct vchiq_state *state, u32 *service_found,
 
 			pos += calc_stride(header->size);
 			if (pos > VCHIQ_SLOT_SIZE) {
-				vchiq_log_error(state->dev, VCHIQ_CORE,
-						"pfq - pos %x: header %pK, msgid %x, header->msgid %x, header->size %x",
-						pos, header, msgid, header->msgid, header->size);
+				dev_err(state->dev,
+					"core: pfq - pos %x: header %pK, msgid %x, header->msgid %x, header->size %x\n",
+					pos, header, msgid, header->msgid, header->size);
 				WARN(1, "invalid slot position\n");
 			}
 		}
@@ -1167,8 +1167,8 @@ queue_message_sync(struct vchiq_state *state, struct vchiq_service *service,
 		int oldmsgid = header->msgid;
 
 		if (oldmsgid != VCHIQ_MSGID_PADDING)
-			vchiq_log_error(state->dev, VCHIQ_CORE, "%d: qms - msgid %x, not PADDING",
-					state->id, oldmsgid);
+			dev_err(state->dev, "core: %d: qms - msgid %x, not PADDING\n",
+				state->id, oldmsgid);
 	}
 
 	vchiq_log_debug(state->dev, VCHIQ_SYNC,
@@ -1616,10 +1616,10 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		}
 
 		if (!service) {
-			vchiq_log_error(state->dev, VCHIQ_CORE,
-					"%d: prs %s@%pK (%d->%d) - invalid/closed service %d",
-					state->id, msg_type_str(type), header, remoteport,
-					localport, localport);
+			dev_err(state->dev,
+				"core: %d: prs %s@%pK (%d->%d) - invalid/closed service %d\n",
+				state->id, msg_type_str(type), header, remoteport,
+				localport, localport);
 			goto skip_message;
 		}
 		break;
@@ -1640,9 +1640,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 
 	if (((unsigned long)header & VCHIQ_SLOT_MASK) +
 	    calc_stride(size) > VCHIQ_SLOT_SIZE) {
-		vchiq_log_error(state->dev, VCHIQ_CORE,
-				"header %pK (msgid %x) - size %x too big for slot",
-				header, (unsigned int)msgid, (unsigned int)size);
+		dev_err(state->dev, "core: header %pK (msgid %x) - size %x too big for slot\n",
+			header, (unsigned int)msgid, (unsigned int)size);
 		WARN(1, "oversized for slot\n");
 	}
 
@@ -1668,8 +1667,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 			set_service_state(service, VCHIQ_SRVSTATE_OPEN);
 			complete(&service->remove_event);
 		} else {
-			vchiq_log_error(state->dev, VCHIQ_CORE, "OPENACK received in state %s",
-					srvstate_names[service->srvstate]);
+			dev_err(state->dev, "core: OPENACK received in state %s\n",
+				srvstate_names[service->srvstate]);
 		}
 		break;
 	case VCHIQ_MSG_CLOSE:
@@ -1740,11 +1739,10 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 			}
 			if ((int)(queue->remote_insert -
 				queue->local_insert) >= 0) {
-				vchiq_log_error(state->dev, VCHIQ_CORE,
-						"%d: prs %s@%pK (%d->%d) unexpected (ri=%d,li=%d)",
-						state->id, msg_type_str(type), header, remoteport,
-						localport, queue->remote_insert,
-						queue->local_insert);
+				dev_err(state->dev,
+					"core: %d: prs %s@%pK (%d->%d) unexpected (ri=%d,li=%d)\n",
+					state->id, msg_type_str(type), header, remoteport,
+					localport, queue->remote_insert, queue->local_insert);
 				mutex_unlock(&service->bulk_mutex);
 				break;
 			}
@@ -1790,8 +1788,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs PAUSE@%pK,%x",
 				state->id, header, size);
 		if (state->conn_state == VCHIQ_CONNSTATE_PAUSED) {
-			vchiq_log_error(state->dev, VCHIQ_CORE,
-					"%d: PAUSE received in state PAUSED", state->id);
+			dev_err(state->dev, "core: %d: PAUSE received in state PAUSED\n",
+				state->id);
 			break;
 		}
 		if (state->conn_state != VCHIQ_CONNSTATE_PAUSE_SENT) {
@@ -1821,8 +1819,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		break;
 
 	default:
-		vchiq_log_error(state->dev, VCHIQ_CORE, "%d: prs invalid msgid %x@%pK,%x",
-				state->id, msgid, header, size);
+		dev_err(state->dev, "core: %d: prs invalid msgid %x@%pK,%x\n",
+			state->id, msgid, header, size);
 		WARN(1, "invalid message\n");
 		break;
 	}
@@ -1932,7 +1930,7 @@ handle_poll(struct vchiq_state *state)
 			 * since the PAUSE should have flushed
 			 * through outstanding messages.
 			 */
-			vchiq_log_error(state->dev, VCHIQ_CORE, "Failed to send RESUME message");
+			dev_err(state->dev, "core: Failed to send RESUME message\n");
 		}
 		break;
 	default:
@@ -2032,10 +2030,10 @@ sync_func(void *v)
 		service = find_service_by_port(state, localport);
 
 		if (!service) {
-			vchiq_log_error(state->dev, VCHIQ_SYNC,
-					"%d: sf %s@%pK (%d->%d) - invalid/closed service %d",
-					state->id, msg_type_str(type), header,
-					remoteport, localport, localport);
+			dev_err(state->dev,
+				"sync: %d: sf %s@%pK (%d->%d) - invalid/closed service %d\n",
+				state->id, msg_type_str(type), header, remoteport,
+				localport, localport);
 			release_message_sync(state, header);
 			continue;
 		}
@@ -2077,15 +2075,15 @@ sync_func(void *v)
 			    (service->srvstate == VCHIQ_SRVSTATE_OPENSYNC)) {
 				if (make_service_callback(service, VCHIQ_MESSAGE_AVAILABLE, header,
 							  NULL) == -EAGAIN)
-					vchiq_log_error(state->dev, VCHIQ_SYNC,
-							"synchronous callback to service %d returns -EAGAIN",
-							localport);
+					dev_err(state->dev,
+						"sync: error: synchronous callback to service %d returns -EAGAIN\n",
+						localport);
 			}
 			break;
 
 		default:
-			vchiq_log_error(state->dev, VCHIQ_SYNC, "%d: sf unexpected msgid %x@%pK,%x",
-					state->id, msgid, header, size);
+			dev_err(state->dev, "sync: error: %d: sf unexpected msgid %x@%pK,%x\n",
+				state->id, msgid, header, size);
 			release_message_sync(state, header);
 			break;
 		}
@@ -2118,8 +2116,8 @@ vchiq_init_slots(struct device *dev, void *mem_base, int mem_size)
 	num_slots -= first_data_slot;
 
 	if (num_slots < 4) {
-		vchiq_log_error(dev, VCHIQ_CORE, "%s - insufficient memory %x bytes",
-				__func__, mem_size);
+		dev_err(dev, "core: %s: Insufficient memory %x bytes\n",
+			__func__, mem_size);
 		return NULL;
 	}
 
@@ -2500,11 +2498,10 @@ vchiq_open_service_internal(struct vchiq_service *service, int client_id)
 	} else if ((service->srvstate != VCHIQ_SRVSTATE_OPEN) &&
 		   (service->srvstate != VCHIQ_SRVSTATE_OPENSYNC)) {
 		if (service->srvstate != VCHIQ_SRVSTATE_CLOSEWAIT)
-			vchiq_log_error(service->state->dev, VCHIQ_CORE,
-					"%d: osi - srvstate = %s (ref %u)",
-					service->state->id,
-					srvstate_names[service->srvstate],
-					kref_read(&service->ref_count));
+			dev_err(service->state->dev,
+				"core: %d: osi - srvstate = %s (ref %u)\n",
+				service->state->id, srvstate_names[service->srvstate],
+				kref_read(&service->ref_count));
 		status = -EINVAL;
 		VCHIQ_SERVICE_STATS_INC(service, error_count);
 		vchiq_release_service_internal(service);
@@ -2565,9 +2562,9 @@ release_service_messages(struct vchiq_service *service)
 			}
 			pos += calc_stride(header->size);
 			if (pos > VCHIQ_SLOT_SIZE) {
-				vchiq_log_error(state->dev, VCHIQ_CORE,
-						"fsi - pos %x: header %pK, msgid %x, header->msgid %x, header->size %x",
-						pos, header, msgid, header->msgid, header->size);
+				dev_err(state->dev,
+					"core: fsi - pos %x: header %pK, msgid %x, header->msgid %x, header->size %x\n",
+					pos, header, msgid, header->msgid, header->size);
 				WARN(1, "invalid slot position\n");
 			}
 		}
@@ -2621,8 +2618,8 @@ close_service_complete(struct vchiq_service *service, int failstate)
 	case VCHIQ_SRVSTATE_LISTENING:
 		break;
 	default:
-		vchiq_log_error(service->state->dev, VCHIQ_CORE, "%s(%x) called in state %s",
-				__func__, service->handle, srvstate_names[service->srvstate]);
+		dev_err(service->state->dev, "core: (%x) called in state %s\n",
+			service->handle, srvstate_names[service->srvstate]);
 		WARN(1, "%s in unexpected state\n", __func__);
 		return -EINVAL;
 	}
@@ -2677,8 +2674,8 @@ vchiq_close_service_internal(struct vchiq_service *service, int close_recvd)
 	case VCHIQ_SRVSTATE_LISTENING:
 	case VCHIQ_SRVSTATE_CLOSEWAIT:
 		if (close_recvd) {
-			vchiq_log_error(state->dev, VCHIQ_CORE, "%s(1) called in state %s",
-					__func__, srvstate_names[service->srvstate]);
+			dev_err(state->dev, "core: (1) called in state %s\n",
+				srvstate_names[service->srvstate]);
 		} else if (is_server) {
 			if (service->srvstate == VCHIQ_SRVSTATE_LISTENING) {
 				status = -EINVAL;
@@ -2765,8 +2762,8 @@ vchiq_close_service_internal(struct vchiq_service *service, int close_recvd)
 		break;
 
 	default:
-		vchiq_log_error(state->dev, VCHIQ_CORE, "%s(%d) called in state %s", __func__,
-				close_recvd, srvstate_names[service->srvstate]);
+		dev_err(state->dev, "core: (%d) called in state %s\n",
+			close_recvd, srvstate_names[service->srvstate]);
 		break;
 	}
 
@@ -2805,8 +2802,8 @@ vchiq_free_service_internal(struct vchiq_service *service)
 	case VCHIQ_SRVSTATE_CLOSEWAIT:
 		break;
 	default:
-		vchiq_log_error(state->dev, VCHIQ_CORE, "%d: fsi - (%d) in state %s", state->id,
-				service->localport, srvstate_names[service->srvstate]);
+		dev_err(state->dev, "core: %d: fsi - (%d) in state %s\n",
+			state->id, service->localport, srvstate_names[service->srvstate]);
 		return;
 	}
 
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
index 564b5c7072672..d7dcd17e4bfff 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
@@ -53,10 +53,6 @@ static inline const char *log_category_str(enum vchiq_log_category c)
 	return strings[c];
 };
 
-#ifndef vchiq_log_error
-#define vchiq_log_error(dev, cat, fmt, ...) \
-	do { dev_dbg(dev, "%s error: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-#endif
 #ifndef vchiq_log_warning
 #define vchiq_log_warning(dev, cat, fmt, ...) \
 	do { dev_dbg(dev, "%s warning: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
index 307a2d76cbb74..ba287cb4c87bf 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
@@ -271,9 +271,9 @@ static int vchiq_ioc_dequeue_message(struct vchiq_instance *instance,
 			ret = -EFAULT;
 		}
 	} else {
-		vchiq_log_error(service->state->dev, VCHIQ_ARM,
-				"header %pK: bufsize %x < size %x",
-				header, args->bufsize, header->size);
+		dev_err(service->state->dev,
+			"arm: header %pK: bufsize %x < size %x\n",
+			header, args->bufsize, header->size);
 		WARN(1, "invalid size\n");
 		ret = -EMSGSIZE;
 	}
@@ -318,8 +318,8 @@ static int vchiq_irq_queue_bulk_tx_rx(struct vchiq_instance *instance,
 		}
 		mutex_unlock(&instance->bulk_waiter_list_mutex);
 		if (!waiter) {
-			vchiq_log_error(service->state->dev, VCHIQ_ARM,
-					"no bulk_waiter found for pid %d", current->pid);
+			dev_err(service->state->dev,
+				"arm: no bulk_waiter found for pid %d\n", current->pid);
 			ret = -ESRCH;
 			goto out;
 		}
@@ -501,10 +501,10 @@ static int vchiq_ioc_await_completion(struct vchiq_instance *instance,
 			msglen = header->size + sizeof(struct vchiq_header);
 			/* This must be a VCHIQ-style service */
 			if (args->msgbufsize < msglen) {
-				vchiq_log_error(service->state->dev, VCHIQ_ARM,
-						"header %pK: msgbufsize %x < msglen %x",
-						header, args->msgbufsize, msglen);
-						WARN(1, "invalid message size\n");
+				dev_err(service->state->dev,
+					"arm: header %pK: msgbufsize %x < msglen %x\n",
+					header, args->msgbufsize, msglen);
+				WARN(1, "invalid message size\n");
 				if (ret == 0)
 					ret = -EMSGSIZE;
 				break;
@@ -618,9 +618,9 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		}
 		rc = mutex_lock_killable(&instance->state->mutex);
 		if (rc) {
-			vchiq_log_error(instance->state->dev, VCHIQ_ARM,
-					"vchiq: connect: could not lock mutex for state %d: %d",
-					instance->state->id, rc);
+			dev_err(instance->state->dev,
+				"arm: vchiq: connect: could not lock mutex for state %d: %d\n",
+				instance->state->id, rc);
 			ret = -EINTR;
 			break;
 		}
@@ -630,8 +630,8 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (!status)
 			instance->connected = 1;
 		else
-			vchiq_log_error(instance->state->dev, VCHIQ_ARM,
-					"vchiq: could not connect: %d", status);
+			dev_err(instance->state->dev,
+				"arm: vchiq: could not connect: %d\n", status);
 		break;
 
 	case VCHIQ_IOC_CREATE_SERVICE: {
@@ -700,13 +700,13 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				vchiq_use_service_internal(service) :
 				vchiq_release_service_internal(service);
 			if (ret) {
-				vchiq_log_error(instance->state->dev, VCHIQ_SUSPEND,
-						"%s: cmd %s returned error %ld for service %p4cc:%03d",
-						__func__, (cmd == VCHIQ_IOC_USE_SERVICE) ?
-						"VCHIQ_IOC_USE_SERVICE" :
-						"VCHIQ_IOC_RELEASE_SERVICE",
-						ret, &service->base.fourcc,
-						service->client_id);
+				dev_err(instance->state->dev,
+					"suspend: cmd %s returned error %ld for service %p4cc:%03d\n",
+					(cmd == VCHIQ_IOC_USE_SERVICE) ?
+					"VCHIQ_IOC_USE_SERVICE" :
+					"VCHIQ_IOC_RELEASE_SERVICE",
+					ret, &service->base.fourcc,
+					service->client_id);
 			}
 		} else {
 			ret = -EINVAL;
@@ -1173,8 +1173,7 @@ static int vchiq_open(struct inode *inode, struct file *file)
 	vchiq_log_debug(state->dev, VCHIQ_ARM, "vchiq_open");
 
 	if (!state) {
-		vchiq_log_error(state->dev, VCHIQ_ARM,
-				"vchiq has no connection to VideoCore");
+		dev_err(state->dev, "arm: vchiq has no connection to VideoCore\n");
 		return -ENOTCONN;
 	}
 
-- 
GitLab


From 085bb4131e0f251c9f369273026828f7ad9ef17a Mon Sep 17 00:00:00 2001
From: Umang Jain <umang.jain@ideasonboard.com>
Date: Tue, 5 Dec 2023 14:11:55 +0530
Subject: [PATCH 0871/4076] staging: vc04_services: Drop vchiq_log_warning() in
 favour of dev_warn

Drop vchiq_log_warning() macro which wraps dev_dbg(). Introduce the usage
of dev_warn() directly.

Signed-off-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/20231205084157.73819-3-umang.jain@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../interface/vchiq_arm/vchiq_arm.c           | 30 +++++++++----------
 .../interface/vchiq_arm/vchiq_core.c          | 30 +++++++++----------
 .../interface/vchiq_arm/vchiq_core.h          |  4 ---
 3 files changed, 29 insertions(+), 35 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index b403400edd8e1..56326b59a718a 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -687,8 +687,8 @@ int vchiq_initialise(struct vchiq_instance **instance_out)
 		ret = -ENOTCONN;
 		goto failed;
 	} else if (i > 0) {
-		vchiq_log_warning(state->dev, VCHIQ_CORE,
-				  "%s: videocore initialized after %d retries\n", __func__, i);
+		dev_warn(state->dev, "core: %s: videocore initialized after %d retries\n",
+			 __func__, i);
 	}
 
 	instance = kzalloc(sizeof(*instance), GFP_KERNEL);
@@ -1644,20 +1644,19 @@ vchiq_dump_service_use_state(struct vchiq_state *state)
 	read_unlock_bh(&arm_state->susp_res_lock);
 
 	if (only_nonzero)
-		vchiq_log_warning(state->dev, VCHIQ_SUSPEND,
-				  "Too many active services (%d). Only dumping up to first %d services with non-zero use-count",
-				  active_services, found);
+		dev_warn(state->dev,
+			 "suspend: Too many active services (%d). Only dumping up to first %d services with non-zero use-count\n",
+			 active_services, found);
 
 	for (i = 0; i < found; i++) {
-		vchiq_log_warning(state->dev, VCHIQ_SUSPEND,
-				  "%p4cc:%d service count %d %s",
-				  &service_data[i].fourcc,
-				  service_data[i].clientid, service_data[i].use_count,
-				  service_data[i].use_count ? nz : "");
+		dev_warn(state->dev,
+			 "suspend: %p4cc:%d service count %d %s\n",
+			 &service_data[i].fourcc,
+			 service_data[i].clientid, service_data[i].use_count,
+			 service_data[i].use_count ? nz : "");
 	}
-	vchiq_log_warning(state->dev, VCHIQ_SUSPEND, "VCHIQ use count %d", peer_count);
-	vchiq_log_warning(state->dev, VCHIQ_SUSPEND, "Overall vchiq instance use count %d",
-			  vc_use_count);
+	dev_warn(state->dev, "suspend: VCHIQ use count %d\n", peer_count);
+	dev_warn(state->dev, "suspend: Overall vchiq instance use count %d\n", vc_use_count);
 
 	kfree(service_data);
 }
@@ -1771,8 +1770,7 @@ static int vchiq_probe(struct platform_device *pdev)
 	 */
 	err = vchiq_register_chrdev(&pdev->dev);
 	if (err) {
-		vchiq_log_warning(&pdev->dev, VCHIQ_ARM,
-				  "Failed to initialize vchiq cdev");
+		dev_warn(&pdev->dev, "arm: Failed to initialize vchiq cdev\n");
 		goto error_exit;
 	}
 
@@ -1782,7 +1780,7 @@ static int vchiq_probe(struct platform_device *pdev)
 	return 0;
 
 failed_platform_init:
-	vchiq_log_warning(&pdev->dev, VCHIQ_ARM, "could not initialize vchiq platform");
+	dev_warn(&pdev->dev, "arm: Could not initialize vchiq platform\n");
 error_exit:
 	return err;
 }
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index 63f412815a32c..2fd7939540011 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -465,9 +465,9 @@ make_service_callback(struct vchiq_service *service, enum vchiq_reason reason,
 	status = service->base.callback(service->instance, reason, header, service->handle,
 					bulk_userdata);
 	if (status && (status != -EAGAIN)) {
-		vchiq_log_warning(service->state->dev, VCHIQ_CORE,
-				  "%d: ignoring ERROR from callback to service %x",
-				  service->state->id, service->handle);
+		dev_warn(service->state->dev,
+			 "core: %d: ignoring ERROR from callback to service %x\n",
+			 service->state->id, service->handle);
 		status = 0;
 	}
 
@@ -1609,10 +1609,10 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 				vchiq_service_put(service);
 			service = get_connected_service(state, remoteport);
 			if (service)
-				vchiq_log_warning(state->dev, VCHIQ_CORE,
-						  "%d: prs %s@%pK (%d->%d) - found connected service %d",
-						  state->id, msg_type_str(type), header,
-						  remoteport, localport, service->localport);
+				dev_warn(state->dev,
+					 "core: %d: prs %s@%pK (%d->%d) - found connected service %d\n",
+					 state->id, msg_type_str(type), header,
+					 remoteport, localport, service->localport);
 		}
 
 		if (!service) {
@@ -2903,10 +2903,10 @@ vchiq_close_service(struct vchiq_instance *instance, unsigned int handle)
 		    (service->srvstate == VCHIQ_SRVSTATE_OPEN))
 			break;
 
-		vchiq_log_warning(service->state->dev, VCHIQ_CORE,
-				  "%d: close_service:%d - waiting in state %s",
-				  service->state->id, service->localport,
-				  srvstate_names[service->srvstate]);
+		dev_warn(service->state->dev,
+			 "core: %d: close_service:%d - waiting in state %s\n",
+			 service->state->id, service->localport,
+			 srvstate_names[service->srvstate]);
 	}
 
 	if (!status &&
@@ -2964,10 +2964,10 @@ vchiq_remove_service(struct vchiq_instance *instance, unsigned int handle)
 		    (service->srvstate == VCHIQ_SRVSTATE_OPEN))
 			break;
 
-		vchiq_log_warning(service->state->dev, VCHIQ_CORE,
-				  "%d: remove_service:%d - waiting in state %s",
-				  service->state->id, service->localport,
-				  srvstate_names[service->srvstate]);
+		dev_warn(service->state->dev,
+			 "core: %d: remove_service:%d - waiting in state %s\n",
+			 service->state->id, service->localport,
+			 srvstate_names[service->srvstate]);
 	}
 
 	if (!status && (service->srvstate != VCHIQ_SRVSTATE_FREE))
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
index d7dcd17e4bfff..bc980a0017111 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
@@ -53,10 +53,6 @@ static inline const char *log_category_str(enum vchiq_log_category c)
 	return strings[c];
 };
 
-#ifndef vchiq_log_warning
-#define vchiq_log_warning(dev, cat, fmt, ...) \
-	do { dev_dbg(dev, "%s warning: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-#endif
 #ifndef vchiq_log_debug
 #define vchiq_log_debug(dev, cat, fmt, ...) \
 	do { dev_dbg(dev, "%s debug: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-- 
GitLab


From 078666d7ee6d3cccc1717212b24562649906a30f Mon Sep 17 00:00:00 2001
From: Umang Jain <umang.jain@ideasonboard.com>
Date: Tue, 5 Dec 2023 14:11:56 +0530
Subject: [PATCH 0872/4076] staging: vc04_services: Drop vchiq_log_trace() in
 favour of dev_dbg

Drop vchiq_log_trace() macro which wraps dev_dbg(). Introduce the usage
of dev_dbg() directly.

Meanwhile at it, drop the usage of __func__ from the logs.
Dynamic debug supports this via the 'f'  decorator flag.

Signed-off-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/20231205084157.73819-4-umang.jain@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../interface/vchiq_arm/vchiq_arm.c           |  53 ++++-----
 .../interface/vchiq_arm/vchiq_core.c          | 101 +++++++++---------
 .../interface/vchiq_arm/vchiq_core.h          |   4 -
 .../interface/vchiq_arm/vchiq_dev.c           |  15 ++-
 4 files changed, 78 insertions(+), 95 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 56326b59a718a..e337b83876478 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -255,8 +255,7 @@ create_pagelist(struct vchiq_instance *instance, char *buf, char __user *ubuf,
 	pagelist = dma_alloc_coherent(instance->state->dev, pagelist_size, &dma_addr,
 				      GFP_KERNEL);
 
-	vchiq_log_trace(instance->state->dev, VCHIQ_ARM,
-			"%s - %pK", __func__, pagelist);
+	dev_dbg(instance->state->dev, "arm: %pK\n", pagelist);
 
 	if (!pagelist)
 		return NULL;
@@ -407,8 +406,7 @@ free_pagelist(struct vchiq_instance *instance, struct vchiq_pagelist_info *pagel
 	struct page **pages = pagelistinfo->pages;
 	unsigned int num_pages = pagelistinfo->num_pages;
 
-	vchiq_log_trace(instance->state->dev, VCHIQ_ARM,
-			"%s - %pK, %d", __func__, pagelistinfo->pagelist, actual);
+	dev_dbg(instance->state->dev, "arm: %pK, %d\n", pagelistinfo->pagelist, actual);
 
 	/*
 	 * NOTE: dma_unmap_sg must be called before the
@@ -708,8 +706,7 @@ int vchiq_initialise(struct vchiq_instance **instance_out)
 	ret = 0;
 
 failed:
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, ret);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, ret);
 
 	return ret;
 }
@@ -742,8 +739,7 @@ int vchiq_shutdown(struct vchiq_instance *instance)
 
 	mutex_unlock(&state->mutex);
 
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, status);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, status);
 
 	free_bulk_waiter(instance);
 	kfree(instance);
@@ -763,8 +759,8 @@ int vchiq_connect(struct vchiq_instance *instance)
 	struct vchiq_state *state = instance->state;
 
 	if (mutex_lock_killable(&state->mutex)) {
-		vchiq_log_trace(state->dev, VCHIQ_CORE,
-				"%s: call to mutex_lock failed", __func__);
+		dev_dbg(state->dev,
+			"core: call to mutex_lock failed\n");
 		status = -EAGAIN;
 		goto failed;
 	}
@@ -776,8 +772,7 @@ int vchiq_connect(struct vchiq_instance *instance)
 	mutex_unlock(&state->mutex);
 
 failed:
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, status);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, status);
 
 	return status;
 }
@@ -808,8 +803,7 @@ vchiq_add_service(struct vchiq_instance *instance,
 		status = -EINVAL;
 	}
 
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, status);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, status);
 
 	return status;
 }
@@ -840,8 +834,7 @@ vchiq_open_service(struct vchiq_instance *instance,
 	}
 
 failed:
-	vchiq_log_trace(state->dev, VCHIQ_CORE,
-			"%s(%p): returning %d", __func__, instance, status);
+	dev_dbg(state->dev, "core: (%p): returning %d\n", instance, status);
 
 	return status;
 }
@@ -1010,8 +1003,7 @@ add_completion(struct vchiq_instance *instance, enum vchiq_reason reason,
 	while ((insert - instance->completion_remove) >= MAX_COMPLETIONS) {
 		/* Out of space - wait for the client */
 		DEBUG_TRACE(SERVICE_CALLBACK_LINE);
-		vchiq_log_trace(instance->state->dev, VCHIQ_CORE,
-				"%s - completion queue full", __func__);
+		dev_dbg(instance->state->dev, "core: completion queue full\n");
 		DEBUG_COUNT(COMPLETION_QUEUE_FULL_COUNT);
 		if (wait_for_completion_interruptible(&instance->remove_event)) {
 			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
@@ -1099,11 +1091,11 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 	vchiq_service_get(service);
 	rcu_read_unlock();
 
-	vchiq_log_trace(service->state->dev, VCHIQ_ARM,
-			"%s - service %lx(%d,%p), reason %d, header %lx, instance %lx, bulk_userdata %lx",
-			__func__, (unsigned long)user_service, service->localport,
-			user_service->userdata, reason, (unsigned long)header,
-			(unsigned long)instance, (unsigned long)bulk_userdata);
+	dev_dbg(service->state->dev,
+		"arm: service %lx(%d,%p), reason %d, header %lx, instance %lx, bulk_userdata %lx\n",
+		(unsigned long)user_service, service->localport,
+		user_service->userdata, reason, (unsigned long)header,
+		(unsigned long)instance, (unsigned long)bulk_userdata);
 
 	if (header && user_service->is_vchi) {
 		spin_lock(&msg_queue_spinlock);
@@ -1112,8 +1104,7 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 			spin_unlock(&msg_queue_spinlock);
 			DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 			DEBUG_COUNT(MSG_QUEUE_FULL_COUNT);
-			vchiq_log_trace(service->state->dev, VCHIQ_ARM,
-					"%s - msg queue full", __func__);
+			dev_dbg(service->state->dev, "arm: msg queue full\n");
 			/*
 			 * If there is no MESSAGE_AVAILABLE in the completion
 			 * queue, add one
@@ -1405,8 +1396,8 @@ vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service,
 	local_uc = ++arm_state->videocore_use_count;
 	++(*entity_uc);
 
-	vchiq_log_trace(state->dev, VCHIQ_SUSPEND, "%s %s count %d, state count %d",
-			__func__, entity, *entity_uc, local_uc);
+	dev_dbg(state->dev, "suspend: %s count %d, state count %d\n",
+		entity, *entity_uc, local_uc);
 
 	write_unlock_bh(&arm_state->susp_res_lock);
 
@@ -1425,7 +1416,7 @@ vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service,
 	}
 
 out:
-	vchiq_log_trace(state->dev, VCHIQ_SUSPEND, "%s exit %d", __func__, ret);
+	dev_dbg(state->dev, "suspend: exit %d\n", ret);
 	return ret;
 }
 
@@ -1463,14 +1454,14 @@ vchiq_release_internal(struct vchiq_state *state, struct vchiq_service *service)
 	--arm_state->videocore_use_count;
 	--(*entity_uc);
 
-	vchiq_log_trace(state->dev, VCHIQ_SUSPEND, "%s %s count %d, state count %d",
-			__func__, entity, *entity_uc, arm_state->videocore_use_count);
+	dev_dbg(state->dev, "suspend: %s count %d, state count %d\n",
+		entity, *entity_uc, arm_state->videocore_use_count);
 
 unlock:
 	write_unlock_bh(&arm_state->susp_res_lock);
 
 out:
-	vchiq_log_trace(state->dev, VCHIQ_SUSPEND, "%s exit %d", __func__, ret);
+	dev_dbg(state->dev, "suspend: exit %d\n", ret);
 	return ret;
 }
 
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index 2fd7939540011..d197e4504bd40 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -459,9 +459,9 @@ make_service_callback(struct vchiq_service *service, enum vchiq_reason reason,
 {
 	int status;
 
-	vchiq_log_trace(service->state->dev, VCHIQ_CORE, "%d: callback:%d (%s, %pK, %pK)",
-			service->state->id, service->localport, reason_names[reason],
-			header, bulk_userdata);
+	dev_dbg(service->state->dev, "core: %d: callback:%d (%s, %pK, %pK)\n",
+		service->state->id, service->localport, reason_names[reason],
+		header, bulk_userdata);
 	status = service->base.callback(service->instance, reason, header, service->handle,
 					bulk_userdata);
 	if (status && (status != -EAGAIN)) {
@@ -763,8 +763,8 @@ process_free_data_message(struct vchiq_state *state, u32 *service_found,
 			 * it has dropped below its quota
 			 */
 			complete(&quota->quota_event);
-			vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: pfq:%d %x@%pK - slot_use->%d",
-					state->id, port, header->size, header, count - 1);
+			dev_dbg(state->dev, "core: %d: pfq:%d %x@%pK - slot_use->%d\n",
+				state->id, port, header->size, header, count - 1);
 		} else {
 			dev_err(state->dev,
 				"core: service %d slot_use_count=%d (header %pK, msgid %x, header->msgid %x, header->size %x)\n",
@@ -809,9 +809,9 @@ process_free_queue(struct vchiq_state *state, u32 *service_found,
 		 */
 		rmb();
 
-		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: pfq %d=%pK %x %x",
-				state->id, slot_index, data, local->slot_queue_recycle,
-				slot_queue_available);
+		dev_dbg(state->dev, "core: %d: pfq %d=%pK %x %x\n",
+			state->id, slot_index, data, local->slot_queue_recycle,
+			slot_queue_available);
 
 		/* Initialise the bitmask for services which have used this slot */
 		memset(service_found, 0, length);
@@ -980,10 +980,10 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 		       ((tx_end_index != quota->previous_tx_index) &&
 			(quota->slot_use_count == quota->slot_quota))) {
 			spin_unlock(&quota_spinlock);
-			vchiq_log_trace(state->dev, VCHIQ_CORE,
-					"%d: qm:%d %s,%zx - quota stall (msg %d, slot %d)",
-					state->id, service->localport, msg_type_str(type), size,
-					quota->message_use_count, quota->slot_use_count);
+			dev_dbg(state->dev,
+				"core: %d: qm:%d %s,%zx - quota stall (msg %d, slot %d)\n",
+				state->id, service->localport, msg_type_str(type), size,
+				quota->message_use_count, quota->slot_use_count);
 			VCHIQ_SERVICE_STATS_INC(service, quota_stalls);
 			mutex_unlock(&state->slot_mutex);
 			if (wait_for_completion_interruptible(&quota->quota_event))
@@ -1073,10 +1073,9 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 		spin_unlock(&quota_spinlock);
 
 		if (slot_use_count)
-			vchiq_log_trace(state->dev, VCHIQ_CORE,
-					"%d: qm:%d %s,%zx - slot_use->%d (hdr %p)", state->id,
-					service->localport, msg_type_str(VCHIQ_MSG_TYPE(msgid)),
-					size, slot_use_count, header);
+			dev_dbg(state->dev, "core: %d: qm:%d %s,%zx - slot_use->%d (hdr %p)\n",
+				state->id, service->localport, msg_type_str(VCHIQ_MSG_TYPE(msgid)),
+				size, slot_use_count, header);
 
 		VCHIQ_SERVICE_STATS_INC(service, ctrl_tx_count);
 		VCHIQ_SERVICE_STATS_ADD(service, ctrl_tx_bytes, size);
@@ -1205,11 +1204,11 @@ queue_message_sync(struct vchiq_state *state, struct vchiq_service *service,
 	svc_fourcc = service ? service->base.fourcc
 			     : VCHIQ_MAKE_FOURCC('?', '?', '?', '?');
 
-	vchiq_log_trace(state->dev, VCHIQ_SYNC,
-			"Sent Sync Msg %s(%u) to %p4cc s:%u d:%d len:%d",
-			msg_type_str(VCHIQ_MSG_TYPE(msgid)), VCHIQ_MSG_TYPE(msgid),
-			&svc_fourcc, VCHIQ_MSG_SRCPORT(msgid),
-			VCHIQ_MSG_DSTPORT(msgid), size);
+	dev_dbg(state->dev,
+		"sync: Sent Sync Msg %s(%u) to %p4cc s:%u d:%d len:%d\n",
+		msg_type_str(VCHIQ_MSG_TYPE(msgid)), VCHIQ_MSG_TYPE(msgid),
+		&svc_fourcc, VCHIQ_MSG_SRCPORT(msgid),
+		VCHIQ_MSG_DSTPORT(msgid), size);
 
 	remote_event_signal(&state->remote->sync_trigger);
 
@@ -1298,11 +1297,11 @@ notify_bulks(struct vchiq_service *service, struct vchiq_bulk_queue *queue,
 {
 	int status = 0;
 
-	vchiq_log_trace(service->state->dev, VCHIQ_CORE,
-			"%d: nb:%d %cx - p=%x rn=%x r=%x",
-			service->state->id, service->localport,
-			(queue == &service->bulk_tx) ? 't' : 'r',
-			queue->process, queue->remote_notify, queue->remove);
+	dev_dbg(service->state->dev,
+		"core: %d: nb:%d %cx - p=%x rn=%x r=%x\n",
+		service->state->id, service->localport,
+		(queue == &service->bulk_tx) ? 't' : 'r',
+		queue->process, queue->remote_notify, queue->remove);
 
 	queue->remote_notify = queue->process;
 
@@ -1425,11 +1424,11 @@ abort_outstanding_bulks(struct vchiq_service *service,
 {
 	int is_tx = (queue == &service->bulk_tx);
 
-	vchiq_log_trace(service->state->dev, VCHIQ_CORE,
-			"%d: aob:%d %cx - li=%x ri=%x p=%x",
-			service->state->id, service->localport,
-			is_tx ? 't' : 'r', queue->local_insert,
-			queue->remote_insert, queue->process);
+	dev_dbg(service->state->dev,
+		"core: %d: aob:%d %cx - li=%x ri=%x p=%x\n",
+		service->state->id, service->localport,
+		is_tx ? 't' : 'r', queue->local_insert,
+		queue->remote_insert, queue->process);
 
 	WARN_ON((int)(queue->local_insert - queue->process) < 0);
 	WARN_ON((int)(queue->remote_insert - queue->process) < 0);
@@ -1764,10 +1763,10 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 					state->id, msg_type_str(type), header, remoteport,
 					localport, bulk->actual, &bulk->data);
 
-			vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs:%d %cx li=%x ri=%x p=%x",
-					state->id, localport,
-					(type == VCHIQ_MSG_BULK_RX_DONE) ? 'r' : 't',
-					queue->local_insert, queue->remote_insert, queue->process);
+			dev_dbg(state->dev, "core: %d: prs:%d %cx li=%x ri=%x p=%x\n",
+				state->id, localport,
+				(type == VCHIQ_MSG_BULK_RX_DONE) ? 'r' : 't',
+				queue->local_insert, queue->remote_insert, queue->process);
 
 			DEBUG_TRACE(PARSE_LINE);
 			WARN_ON(queue->process == queue->local_insert);
@@ -1780,13 +1779,13 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		}
 		break;
 	case VCHIQ_MSG_PADDING:
-		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs PADDING@%pK,%x",
-				state->id, header, size);
+		dev_dbg(state->dev, "core: %d: prs PADDING@%pK,%x\n",
+			state->id, header, size);
 		break;
 	case VCHIQ_MSG_PAUSE:
 		/* If initiated, signal the application thread */
-		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs PAUSE@%pK,%x",
-				state->id, header, size);
+		dev_dbg(state->dev, "core: %d: prs PAUSE@%pK,%x\n",
+			state->id, header, size);
 		if (state->conn_state == VCHIQ_CONNSTATE_PAUSED) {
 			dev_err(state->dev, "core: %d: PAUSE received in state PAUSED\n",
 				state->id);
@@ -1802,8 +1801,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		vchiq_set_conn_state(state, VCHIQ_CONNSTATE_PAUSED);
 		break;
 	case VCHIQ_MSG_RESUME:
-		vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: prs RESUME@%pK,%x",
-				state->id, header, size);
+		dev_dbg(state->dev, "core: %d: prs RESUME@%pK,%x\n",
+			state->id, header, size);
 		/* Release the slot mutex */
 		mutex_unlock(&state->slot_mutex);
 		vchiq_set_conn_state(state, VCHIQ_CONNSTATE_CONNECTED);
@@ -2040,10 +2039,8 @@ sync_func(void *v)
 
 		svc_fourcc = service->base.fourcc;
 
-		vchiq_log_trace(state->dev, VCHIQ_SYNC,
-				"Rcvd Msg %s from %p4cc s:%d d:%d len:%d",
-				msg_type_str(type), &svc_fourcc,
-				remoteport, localport, size);
+		dev_dbg(state->dev, "sync: Rcvd Msg %s from %p4cc s:%d d:%d len:%d\n",
+			msg_type_str(type), &svc_fourcc, remoteport, localport, size);
 		if (size > 0)
 			vchiq_log_dump_mem(state->dev, "Rcvd", 0, header->data, min(16, size));
 
@@ -2068,8 +2065,8 @@ sync_func(void *v)
 			break;
 
 		case VCHIQ_MSG_DATA:
-			vchiq_log_trace(state->dev, VCHIQ_SYNC, "%d: sf DATA@%pK,%x (%d->%d)",
-					state->id, header, size, remoteport, localport);
+			dev_dbg(state->dev, "sync: %d: sf DATA@%pK,%x (%d->%d)\n",
+				state->id, header, size, remoteport, localport);
 
 			if ((service->remoteport == remoteport) &&
 			    (service->srvstate == VCHIQ_SRVSTATE_OPENSYNC)) {
@@ -3111,9 +3108,9 @@ int vchiq_bulk_transfer(struct vchiq_instance *instance, unsigned int handle,
 	mutex_unlock(&state->slot_mutex);
 	mutex_unlock(&service->bulk_mutex);
 
-	vchiq_log_trace(state->dev, VCHIQ_CORE, "%d: bt:%d %cx li=%x ri=%x p=%x",
-			state->id, service->localport, dir_char, queue->local_insert,
-			queue->remote_insert, queue->process);
+	dev_dbg(state->dev, "core: %d: bt:%d %cx li=%x ri=%x p=%x\n",
+		state->id, service->localport, dir_char, queue->local_insert,
+		queue->remote_insert, queue->process);
 
 waiting:
 	vchiq_service_put(service);
@@ -3579,9 +3576,9 @@ void vchiq_log_dump_mem(struct device *dev, const char *label, u32 addr,
 		*s++ = '\0';
 
 		if (label && (*label != '\0'))
-			vchiq_log_trace(dev, VCHIQ_CORE, "%s: %08x: %s", label, addr, line_buf);
+			dev_dbg(dev, "core: %s: %08x: %s\n", label, addr, line_buf);
 		else
-			vchiq_log_trace(dev, VCHIQ_CORE, "%s: %08x: %s", label, addr, line_buf);
+			dev_dbg(dev, "core: %s: %08x: %s\n", label, addr, line_buf);
 
 		addr += 16;
 		mem += 16;
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
index bc980a0017111..36e34a7fc6286 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
@@ -57,10 +57,6 @@ static inline const char *log_category_str(enum vchiq_log_category c)
 #define vchiq_log_debug(dev, cat, fmt, ...) \
 	do { dev_dbg(dev, "%s debug: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
 #endif
-#ifndef vchiq_log_trace
-#define vchiq_log_trace(dev, cat, fmt, ...) \
-	do { dev_dbg(dev, "%s trace: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-#endif
 
 #define VCHIQ_SLOT_MASK        (VCHIQ_SLOT_SIZE - 1)
 #define VCHIQ_SLOT_QUEUE_MASK  (VCHIQ_MAX_SLOTS_PER_SIDE - 1)
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
index ba287cb4c87bf..38841c9d8ef9d 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
@@ -582,10 +582,9 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	long ret = 0;
 	int i, rc;
 
-	vchiq_log_trace(instance->state->dev, VCHIQ_ARM,
-			"%s - instance %pK, cmd %s, arg %lx", __func__, instance,
-			((_IOC_TYPE(cmd) == VCHIQ_IOC_MAGIC) && (_IOC_NR(cmd) <= VCHIQ_IOC_MAX)) ?
-			ioctl_names[_IOC_NR(cmd)] : "<invalid>", arg);
+	dev_dbg(instance->state->dev, "arm: instance %pK, cmd %s, arg %lx\n", instance,
+		((_IOC_TYPE(cmd) == VCHIQ_IOC_MAGIC) && (_IOC_NR(cmd) <= VCHIQ_IOC_MAX)) ?
+		ioctl_names[_IOC_NR(cmd)] : "<invalid>", arg);
 
 	switch (cmd) {
 	case VCHIQ_IOC_SHUTDOWN:
@@ -873,10 +872,10 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
 				ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
 	} else {
-		vchiq_log_trace(instance->state->dev, VCHIQ_ARM,
-				"  ioctl instance %pK, cmd %s -> status %d, %ld",
-				instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
-				ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
+		dev_dbg(instance->state->dev,
+			"arm: ioctl instance %pK, cmd %s -> status %d\n, %ld\n",
+			instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
+			ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
 	}
 
 	return ret;
-- 
GitLab


From 55e23aa95b10731c08ab207a42d868aaff3bd2a5 Mon Sep 17 00:00:00 2001
From: Umang Jain <umang.jain@ideasonboard.com>
Date: Tue, 5 Dec 2023 14:11:57 +0530
Subject: [PATCH 0873/4076] staging: vc04_services: Drop vchiq_log_debug() in
 favour of dev_dbg

Drop vchiq_log_debug() macro which wraps dev_dbg(). Introduce the usage
of dev_dbg() directly.

Meanwhile at it, drop the usage of __func__ from the logs.
Dynamic debug supports this via the 'f'  decorator flag.

Remove the entry from TODO regarding custom logging. VC04 is now
aligned according to the standard kernel logging mechanisms.

Signed-off-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/20231205084157.73819-5-umang.jain@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vc04_services/interface/TODO  |   5 -
 .../interface/vchiq_arm/vchiq_arm.c           |  45 +++--
 .../interface/vchiq_arm/vchiq_core.c          | 159 ++++++++----------
 .../interface/vchiq_arm/vchiq_core.h          |  26 ---
 .../interface/vchiq_arm/vchiq_dev.c           |  32 ++--
 5 files changed, 106 insertions(+), 161 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/TODO b/drivers/staging/vc04_services/interface/TODO
index 6d9d4a800aa73..05eb5140d0966 100644
--- a/drivers/staging/vc04_services/interface/TODO
+++ b/drivers/staging/vc04_services/interface/TODO
@@ -23,11 +23,6 @@ should properly handle a module unload. This also includes that all
 resources must be freed (kthreads, debugfs entries, ...) and global
 variables avoided.
 
-* Cleanup logging mechanism
-
-The driver should probably be using the standard kernel logging mechanisms
-such as dev_info, dev_dbg, and friends.
-
 * Documentation
 
 A short top-down description of this driver's architecture (function of
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index e337b83876478..4b4ff469d3a31 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -310,9 +310,8 @@ create_pagelist(struct vchiq_instance *instance, char *buf, char __user *ubuf,
 						   type == PAGELIST_READ, pages);
 
 		if (actual_pages != num_pages) {
-			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-					"%s - only %d/%d pages locked",
-					__func__, actual_pages, num_pages);
+			dev_dbg(instance->state->dev, "arm: Only %d/%d pages locked\n",
+				actual_pages, num_pages);
 
 			/* This is probably due to the process being killed */
 			if (actual_pages > 0)
@@ -554,8 +553,8 @@ static int vchiq_platform_init(struct platform_device *pdev, struct vchiq_state
 		return -ENXIO;
 	}
 
-	vchiq_log_debug(&pdev->dev, VCHIQ_ARM, "vchiq_init - done (slots %pK, phys %pad)",
-			vchiq_slot_zero, &slot_phys);
+	dev_dbg(&pdev->dev, "arm: vchiq_init - done (slots %pK, phys %pad)\n",
+		vchiq_slot_zero, &slot_phys);
 
 	vchiq_call_connected_callbacks();
 
@@ -719,9 +718,9 @@ void free_bulk_waiter(struct vchiq_instance *instance)
 	list_for_each_entry_safe(waiter, next,
 				 &instance->bulk_waiter_list, list) {
 		list_del(&waiter->list);
-		vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-				"bulk_waiter - cleaned up %pK for pid %d",
-				waiter, waiter->pid);
+		dev_dbg(instance->state->dev,
+			"arm: bulk_waiter - cleaned up %pK for pid %d\n",
+			waiter, waiter->pid);
 		kfree(waiter);
 	}
 }
@@ -981,9 +980,8 @@ vchiq_blocking_bulk_transfer(struct vchiq_instance *instance, unsigned int handl
 		mutex_lock(&instance->bulk_waiter_list_mutex);
 		list_add(&waiter->list, &instance->bulk_waiter_list);
 		mutex_unlock(&instance->bulk_waiter_list_mutex);
-		vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-				"saved bulk_waiter %pK for pid %d", waiter,
-				current->pid);
+		dev_dbg(instance->state->dev, "arm: saved bulk_waiter %pK for pid %d\n",
+			waiter, current->pid);
 	}
 
 	return status;
@@ -1006,12 +1004,10 @@ add_completion(struct vchiq_instance *instance, enum vchiq_reason reason,
 		dev_dbg(instance->state->dev, "core: completion queue full\n");
 		DEBUG_COUNT(COMPLETION_QUEUE_FULL_COUNT);
 		if (wait_for_completion_interruptible(&instance->remove_event)) {
-			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-					"service_callback interrupted");
+			dev_dbg(instance->state->dev, "arm: service_callback interrupted\n");
 			return -EAGAIN;
 		} else if (instance->closing) {
-			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-					"service_callback closing");
+			dev_dbg(instance->state->dev, "arm: service_callback closing\n");
 			return 0;
 		}
 		DEBUG_TRACE(SERVICE_CALLBACK_LINE);
@@ -1113,8 +1109,8 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 				instance->completion_remove) < 0) {
 				int status;
 
-				vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-						"Inserting extra MESSAGE_AVAILABLE");
+				dev_dbg(instance->state->dev,
+					"arm: Inserting extra MESSAGE_AVAILABLE\n");
 				DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 				status = add_completion(instance, reason, NULL, user_service,
 							bulk_userdata);
@@ -1127,14 +1123,12 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 
 			DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 			if (wait_for_completion_interruptible(&user_service->remove_event)) {
-				vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-						"%s interrupted", __func__);
+				dev_dbg(instance->state->dev, "arm: interrupted\n");
 				DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 				vchiq_service_put(service);
 				return -EAGAIN;
 			} else if (instance->closing) {
-				vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-						"%s closing", __func__);
+				dev_dbg(instance->state->dev, "arm: closing\n");
 				DEBUG_TRACE(SERVICE_CALLBACK_LINE);
 				vchiq_service_put(service);
 				return -EINVAL;
@@ -1686,8 +1680,8 @@ void vchiq_platform_conn_state_changed(struct vchiq_state *state,
 	struct vchiq_arm_state *arm_state = vchiq_platform_get_arm_state(state);
 	char threadname[16];
 
-	vchiq_log_debug(state->dev, VCHIQ_SUSPEND, "%d: %s->%s", state->id,
-			get_conn_state_name(oldstate), get_conn_state_name(newstate));
+	dev_dbg(state->dev, "suspend: %d: %s->%s\n",
+		state->id, get_conn_state_name(oldstate), get_conn_state_name(newstate));
 	if (state->conn_state != VCHIQ_CONNSTATE_CONNECTED)
 		return;
 
@@ -1751,9 +1745,8 @@ static int vchiq_probe(struct platform_device *pdev)
 
 	vchiq_debugfs_init();
 
-	vchiq_log_debug(&pdev->dev, VCHIQ_ARM,
-			"vchiq: platform initialised - version %d (min %d)",
-			VCHIQ_VERSION, VCHIQ_VERSION_MIN);
+	dev_dbg(&pdev->dev, "arm: platform initialised - version %d (min %d)\n",
+		VCHIQ_VERSION, VCHIQ_VERSION_MIN);
 
 	/*
 	 * Simply exit on error since the function handles cleanup in
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index d197e4504bd40..76c27778154aa 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -217,10 +217,10 @@ static const char *msg_type_str(unsigned int msg_type)
 static inline void
 set_service_state(struct vchiq_service *service, int newstate)
 {
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE, "%d: srv:%d %s->%s",
-			service->state->id, service->localport,
-			srvstate_names[service->srvstate],
-			srvstate_names[newstate]);
+	dev_dbg(service->state->dev, "core: %d: srv:%d %s->%s\n",
+		service->state->id, service->localport,
+		srvstate_names[service->srvstate],
+		srvstate_names[newstate]);
 	service->srvstate = newstate;
 }
 
@@ -245,8 +245,7 @@ find_service_by_handle(struct vchiq_instance *instance, unsigned int handle)
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(instance->state->dev, VCHIQ_CORE,
-			"Invalid service handle 0x%x", handle);
+	dev_dbg(instance->state->dev, "core: Invalid service handle 0x%x\n", handle);
 	return NULL;
 }
 
@@ -266,8 +265,7 @@ find_service_by_port(struct vchiq_state *state, unsigned int localport)
 		}
 		rcu_read_unlock();
 	}
-	vchiq_log_debug(state->dev, VCHIQ_CORE,
-			"Invalid port %u", localport);
+	dev_dbg(state->dev, "core: Invalid port %u\n", localport);
 	return NULL;
 }
 
@@ -287,8 +285,7 @@ find_service_for_instance(struct vchiq_instance *instance, unsigned int handle)
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(instance->state->dev, VCHIQ_CORE,
-			"Invalid service handle 0x%x", handle);
+	dev_dbg(instance->state->dev, "core: Invalid service handle 0x%x\n", handle);
 	return NULL;
 }
 
@@ -310,8 +307,7 @@ find_closed_service_for_instance(struct vchiq_instance *instance, unsigned int h
 		return service;
 	}
 	rcu_read_unlock();
-	vchiq_log_debug(instance->state->dev, VCHIQ_CORE,
-			"Invalid service handle 0x%x", handle);
+	dev_dbg(instance->state->dev, "core: Invalid service handle 0x%x\n", handle);
 	return service;
 }
 
@@ -482,8 +478,8 @@ vchiq_set_conn_state(struct vchiq_state *state, enum vchiq_connstate newstate)
 {
 	enum vchiq_connstate oldstate = state->conn_state;
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: %s->%s", state->id, conn_state_names[oldstate],
-			conn_state_names[newstate]);
+	dev_dbg(state->dev, "core: %d: %s->%s\n",
+		state->id, conn_state_names[oldstate], conn_state_names[newstate]);
 	state->conn_state = newstate;
 	vchiq_platform_conn_state_changed(state, oldstate, newstate);
 }
@@ -1023,9 +1019,9 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 		int tx_end_index;
 		int slot_use_count;
 
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: qm %s@%pK,%zx (%d->%d)", state->id,
-				msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
-				VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
+		dev_dbg(state->dev, "core: %d: qm %s@%pK,%zx (%d->%d)\n",
+			state->id, msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
+			VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
 
 		WARN_ON(flags & (QMFLAGS_NO_MUTEX_LOCK |
 				 QMFLAGS_NO_MUTEX_UNLOCK));
@@ -1080,9 +1076,9 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 		VCHIQ_SERVICE_STATS_INC(service, ctrl_tx_count);
 		VCHIQ_SERVICE_STATS_ADD(service, ctrl_tx_bytes, size);
 	} else {
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: qm %s@%pK,%zx (%d->%d)", state->id,
-				msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
-				VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
+		dev_dbg(state->dev, "core: %d: qm %s@%pK,%zx (%d->%d)\n",
+			state->id, msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
+			VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
 		if (size != 0) {
 			/*
 			 * It is assumed for now that this code path
@@ -1110,11 +1106,9 @@ queue_message(struct vchiq_state *state, struct vchiq_service *service,
 			? service->base.fourcc
 			: VCHIQ_MAKE_FOURCC('?', '?', '?', '?');
 
-		vchiq_log_debug(state->dev, VCHIQ_CORE_MSG,
-				"Sent Msg %s(%u) to %p4cc s:%u d:%d len:%zu",
-				msg_type_str(VCHIQ_MSG_TYPE(msgid)), VCHIQ_MSG_TYPE(msgid),
-				&svc_fourcc, VCHIQ_MSG_SRCPORT(msgid),
-				VCHIQ_MSG_DSTPORT(msgid), size);
+		dev_dbg(state->dev, "core_msg: Sent Msg %s(%u) to %p4cc s:%u d:%d len:%zu\n",
+			msg_type_str(VCHIQ_MSG_TYPE(msgid)), VCHIQ_MSG_TYPE(msgid),
+			&svc_fourcc, VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid), size);
 	}
 
 	/* Make sure the new header is visible to the peer. */
@@ -1170,11 +1164,9 @@ queue_message_sync(struct vchiq_state *state, struct vchiq_service *service,
 				state->id, oldmsgid);
 	}
 
-	vchiq_log_debug(state->dev, VCHIQ_SYNC,
-			"%d: qms %s@%pK,%x (%d->%d)", state->id,
-			msg_type_str(VCHIQ_MSG_TYPE(msgid)),
-			header, size, VCHIQ_MSG_SRCPORT(msgid),
-			VCHIQ_MSG_DSTPORT(msgid));
+	dev_dbg(state->dev, "sync: %d: qms %s@%pK,%x (%d->%d)\n",
+		state->id, msg_type_str(VCHIQ_MSG_TYPE(msgid)), header, size,
+		VCHIQ_MSG_SRCPORT(msgid), VCHIQ_MSG_DSTPORT(msgid));
 
 	callback_result =
 		copy_message_data(copy_callback, context,
@@ -1260,9 +1252,9 @@ release_slot(struct vchiq_state *state, struct vchiq_slot_info *slot_info,
 			VCHIQ_SLOT_QUEUE_MASK] =
 			SLOT_INDEX_FROM_INFO(state, slot_info);
 		state->remote->slot_queue_recycle = slot_queue_recycle + 1;
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: %s %d - recycle->%x",
-				state->id, __func__, SLOT_INDEX_FROM_INFO(state, slot_info),
-				state->remote->slot_queue_recycle);
+		dev_dbg(state->dev, "core: %d: %d - recycle->%x\n",
+			state->id, SLOT_INDEX_FROM_INFO(state, slot_info),
+			state->remote->slot_queue_recycle);
 
 		/*
 		 * A write barrier is necessary, but remote_event_signal
@@ -1381,8 +1373,8 @@ poll_services_of_group(struct vchiq_state *state, int group)
 
 		service_flags = atomic_xchg(&service->poll_flags, 0);
 		if (service_flags & BIT(VCHIQ_POLL_REMOVE)) {
-			vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: ps - remove %d<->%d",
-					state->id, service->localport, service->remoteport);
+			dev_dbg(state->dev, "core: %d: ps - remove %d<->%d\n",
+				state->id, service->localport, service->remoteport);
 
 			/*
 			 * Make it look like a client, because
@@ -1394,8 +1386,8 @@ poll_services_of_group(struct vchiq_state *state, int group)
 			if (vchiq_close_service_internal(service, NO_CLOSE_RECVD))
 				request_poll(state, service, VCHIQ_POLL_REMOVE);
 		} else if (service_flags & BIT(VCHIQ_POLL_TERMINATE)) {
-			vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: ps - terminate %d<->%d",
-					state->id, service->localport, service->remoteport);
+			dev_dbg(state->dev, "core: %d: ps - terminate %d<->%d\n",
+				state->id, service->localport, service->remoteport);
 			if (vchiq_close_service_internal(service, NO_CLOSE_RECVD))
 				request_poll(state, service, VCHIQ_POLL_TERMINATE);
 		}
@@ -1447,11 +1439,11 @@ abort_outstanding_bulks(struct vchiq_service *service,
 		if (queue->process != queue->local_insert) {
 			vchiq_complete_bulk(service->instance, bulk);
 
-			vchiq_log_debug(service->state->dev, VCHIQ_CORE_MSG,
-					"%s %p4cc d:%d ABORTED - tx len:%d, rx len:%d",
-					is_tx ? "Send Bulk to" : "Recv Bulk from",
-					&service->base.fourcc,
-					service->remoteport, bulk->size, bulk->remote_size);
+			dev_dbg(service->state->dev,
+				"core_msg: %s %p4cc d:%d ABORTED - tx len:%d, rx len:%d\n",
+				is_tx ? "Send Bulk to" : "Recv Bulk from",
+				&service->base.fourcc,
+				service->remoteport, bulk->size, bulk->remote_size);
 		} else {
 			/* fabricate a matching dummy bulk */
 			bulk->data = 0;
@@ -1484,8 +1476,8 @@ parse_open(struct vchiq_state *state, struct vchiq_header *header)
 
 	payload = (struct vchiq_open_payload *)header->data;
 	fourcc = payload->fourcc;
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: prs OPEN@%pK (%d->'%p4cc')",
-			state->id, header, localport, &fourcc);
+	dev_dbg(state->dev, "core: %d: prs OPEN@%pK (%d->'%p4cc')\n",
+		state->id, header, localport, &fourcc);
 
 	service = get_listening_service(state, fourcc);
 	if (!service)
@@ -1630,10 +1622,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 	svc_fourcc = service ? service->base.fourcc
 			     : VCHIQ_MAKE_FOURCC('?', '?', '?', '?');
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE_MSG,
-			"Rcvd Msg %s(%u) from %p4cc s:%d d:%d len:%d",
-			msg_type_str(type), type, &svc_fourcc,
-			remoteport, localport, size);
+	dev_dbg(state->dev, "core_msg: Rcvd Msg %s(%u) from %p4cc s:%d d:%d len:%d\n",
+		msg_type_str(type), type, &svc_fourcc, remoteport, localport, size);
 	if (size > 0)
 		vchiq_log_dump_mem(state->dev, "Rcvd", 0, header->data, min(16, size));
 
@@ -1657,10 +1647,10 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 				header->data;
 			service->peer_version = payload->version;
 		}
-		vchiq_log_debug(state->dev, VCHIQ_CORE,
-				"%d: prs OPENACK@%pK,%x (%d->%d) v:%d",
-				state->id, header, size, remoteport, localport,
-				service->peer_version);
+		dev_dbg(state->dev,
+			"core: %d: prs OPENACK@%pK,%x (%d->%d) v:%d\n",
+			state->id, header, size, remoteport, localport,
+			service->peer_version);
 		if (service->srvstate == VCHIQ_SRVSTATE_OPENING) {
 			service->remoteport = remoteport;
 			set_service_state(service, VCHIQ_SRVSTATE_OPEN);
@@ -1673,21 +1663,20 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 	case VCHIQ_MSG_CLOSE:
 		WARN_ON(size); /* There should be no data */
 
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: prs CLOSE@%pK (%d->%d)",
-				state->id, header, remoteport, localport);
+		dev_dbg(state->dev, "core: %d: prs CLOSE@%pK (%d->%d)\n",
+			state->id, header, remoteport, localport);
 
 		mark_service_closing_internal(service, 1);
 
 		if (vchiq_close_service_internal(service, CLOSE_RECVD) == -EAGAIN)
 			goto bail_not_ready;
 
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "Close Service %p4cc s:%u d:%d",
-				&service->base.fourcc,
-				service->localport, service->remoteport);
+		dev_dbg(state->dev, "core: Close Service %p4cc s:%u d:%d\n",
+			&service->base.fourcc, service->localport, service->remoteport);
 		break;
 	case VCHIQ_MSG_DATA:
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: prs DATA@%pK,%x (%d->%d)",
-				state->id, header, size, remoteport, localport);
+		dev_dbg(state->dev, "core: %d: prs DATA@%pK,%x (%d->%d)\n",
+			state->id, header, size, remoteport, localport);
 
 		if ((service->remoteport == remoteport) &&
 		    (service->srvstate == VCHIQ_SRVSTATE_OPEN)) {
@@ -1706,8 +1695,8 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 		}
 		break;
 	case VCHIQ_MSG_CONNECT:
-		vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: prs CONNECT@%pK",
-				state->id, header);
+		dev_dbg(state->dev, "core: %d: prs CONNECT@%pK\n",
+			state->id, header);
 		state->version_common =	((struct vchiq_slot_zero *)
 					 state->slot_data)->version;
 		complete(&state->connect);
@@ -1758,10 +1747,9 @@ parse_message(struct vchiq_state *state, struct vchiq_header *header)
 			bulk->actual = *(int *)header->data;
 			queue->remote_insert++;
 
-			vchiq_log_debug(state->dev, VCHIQ_CORE,
-					"%d: prs %s@%pK (%d->%d) %x@%pad",
-					state->id, msg_type_str(type), header, remoteport,
-					localport, bulk->actual, &bulk->data);
+			dev_dbg(state->dev, "core: %d: prs %s@%pK (%d->%d) %x@%pad\n",
+				state->id, msg_type_str(type), header, remoteport,
+				localport, bulk->actual, &bulk->data);
 
 			dev_dbg(state->dev, "core: %d: prs:%d %cx li=%x ri=%x p=%x\n",
 				state->id, localport,
@@ -2052,9 +2040,9 @@ sync_func(void *v)
 					header->data;
 				service->peer_version = payload->version;
 			}
-			vchiq_log_debug(state->dev, VCHIQ_SYNC, "%d: sf OPENACK@%pK,%x (%d->%d) v:%d",
-					state->id, header, size, remoteport, localport,
-					service->peer_version);
+			dev_err(state->dev, "sync: %d: sf OPENACK@%pK,%x (%d->%d) v:%d\n",
+				state->id, header, size, remoteport, localport,
+				service->peer_version);
 			if (service->srvstate == VCHIQ_SRVSTATE_OPENING) {
 				service->remoteport = remoteport;
 				set_service_state(service, VCHIQ_SRVSTATE_OPENSYNC);
@@ -2456,9 +2444,9 @@ vchiq_add_service_internal(struct vchiq_state *state,
 	/* Bring this service online */
 	set_service_state(service, srvstate);
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE_MSG, "%s Service %p4cc SrcPort:%d",
-			(srvstate == VCHIQ_SRVSTATE_OPENING) ? "Open" : "Add",
-			&params->fourcc, service->localport);
+	dev_dbg(state->dev, "core_msg: %s Service %p4cc SrcPort:%d\n",
+		(srvstate == VCHIQ_SRVSTATE_OPENING) ? "Open" : "Add",
+		&params->fourcc, service->localport);
 
 	/* Don't unlock the service - leave it with a ref_count of 1. */
 
@@ -2553,8 +2541,7 @@ release_service_messages(struct vchiq_service *service)
 			int port = VCHIQ_MSG_DSTPORT(msgid);
 
 			if ((port == service->localport) && (msgid & VCHIQ_MSGID_CLAIMED)) {
-				vchiq_log_debug(state->dev, VCHIQ_CORE,
-						"  fsi - hdr %pK", header);
+				dev_dbg(state->dev, "core:  fsi - hdr %pK\n", header);
 				release_slot(state, slot_info, header, NULL);
 			}
 			pos += calc_stride(header->size);
@@ -2662,8 +2649,9 @@ vchiq_close_service_internal(struct vchiq_service *service, int close_recvd)
 	int close_id = MAKE_CLOSE(service->localport,
 				  VCHIQ_MSG_DSTPORT(service->remoteport));
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: csi:%d,%d (%s)", service->state->id,
-			service->localport, close_recvd, srvstate_names[service->srvstate]);
+	dev_dbg(state->dev, "core: %d: csi:%d,%d (%s)\n",
+		service->state->id, service->localport, close_recvd,
+		srvstate_names[service->srvstate]);
 
 	switch (service->srvstate) {
 	case VCHIQ_SRVSTATE_CLOSED:
@@ -2773,8 +2761,8 @@ vchiq_terminate_service_internal(struct vchiq_service *service)
 {
 	struct vchiq_state *state = service->state;
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: tsi - (%d<->%d)", state->id,
-			service->localport, service->remoteport);
+	dev_dbg(state->dev, "core: %d: tsi - (%d<->%d)\n",
+		state->id, service->localport, service->remoteport);
 
 	mark_service_closing(service);
 
@@ -2788,8 +2776,7 @@ vchiq_free_service_internal(struct vchiq_service *service)
 {
 	struct vchiq_state *state = service->state;
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: fsi - (%d)",
-			state->id, service->localport);
+	dev_dbg(state->dev, "core: %d: fsi - (%d)\n", state->id, service->localport);
 
 	switch (service->srvstate) {
 	case VCHIQ_SRVSTATE_OPENING:
@@ -2869,8 +2856,8 @@ vchiq_close_service(struct vchiq_instance *instance, unsigned int handle)
 	if (!service)
 		return -EINVAL;
 
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE, "%d: close_service:%d",
-			service->state->id, service->localport);
+	dev_dbg(service->state->dev, "core: %d: close_service:%d\n",
+		service->state->id, service->localport);
 
 	if ((service->srvstate == VCHIQ_SRVSTATE_FREE) ||
 	    (service->srvstate == VCHIQ_SRVSTATE_LISTENING) ||
@@ -2927,8 +2914,8 @@ vchiq_remove_service(struct vchiq_instance *instance, unsigned int handle)
 	if (!service)
 		return -EINVAL;
 
-	vchiq_log_debug(service->state->dev, VCHIQ_CORE, "%d: remove_service:%d",
-			service->state->id, service->localport);
+	dev_dbg(service->state->dev, "core: %d: remove_service:%d\n",
+		service->state->id, service->localport);
 
 	if (service->srvstate == VCHIQ_SRVSTATE_FREE) {
 		vchiq_service_put(service);
@@ -3071,9 +3058,9 @@ int vchiq_bulk_transfer(struct vchiq_instance *instance, unsigned int handle,
 	 */
 	wmb();
 
-	vchiq_log_debug(state->dev, VCHIQ_CORE, "%d: bt (%d->%d) %cx %x@%pad %pK",
-			state->id, service->localport, service->remoteport,
-			dir_char, size, &bulk->data, userdata);
+	dev_dbg(state->dev, "core: %d: bt (%d->%d) %cx %x@%pad %pK\n",
+		state->id, service->localport, service->remoteport,
+		dir_char, size, &bulk->data, userdata);
 
 	/*
 	 * The slot mutex must be held when the service is being closed, so
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
index 36e34a7fc6286..c8527551b58cd 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h
@@ -32,32 +32,6 @@
 #define VCHIQ_SLOT_SIZE     4096
 #define VCHIQ_MAX_MSG_SIZE  (VCHIQ_SLOT_SIZE - sizeof(struct vchiq_header))
 
-enum vchiq_log_category {
-	VCHIQ_ARM,
-	VCHIQ_CORE,
-	VCHIQ_CORE_MSG,
-	VCHIQ_SYNC,
-	VCHIQ_SUSPEND,
-};
-
-static inline const char *log_category_str(enum vchiq_log_category c)
-{
-	static const char * const strings[] = {
-		"vchiq_arm",
-		"vchiq_core",
-		"vchiq_core_msg",
-		"vchiq_sync",
-		"vchiq_suspend",
-	};
-
-	return strings[c];
-};
-
-#ifndef vchiq_log_debug
-#define vchiq_log_debug(dev, cat, fmt, ...) \
-	do { dev_dbg(dev, "%s debug: " fmt, log_category_str(cat), ##__VA_ARGS__); } while (0)
-#endif
-
 #define VCHIQ_SLOT_MASK        (VCHIQ_SLOT_SIZE - 1)
 #define VCHIQ_SLOT_QUEUE_MASK  (VCHIQ_MAX_SLOTS_PER_SIDE - 1)
 #define VCHIQ_SLOT_ZERO_SLOTS  DIV_ROUND_UP(sizeof(struct vchiq_slot_zero), \
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
index 38841c9d8ef9d..68c8897c504c3 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
@@ -47,9 +47,8 @@ user_service_free(void *userdata)
 
 static void close_delivered(struct user_service *user_service)
 {
-	vchiq_log_debug(user_service->service->state->dev, VCHIQ_ARM,
-			"%s(handle=%x)",
-			__func__, user_service->service->handle);
+	dev_dbg(user_service->service->state->dev,
+		"arm: (handle=%x)\n", user_service->service->handle);
 
 	if (user_service->close_pending) {
 		/* Allow the underlying service to be culled */
@@ -235,8 +234,7 @@ static int vchiq_ioc_dequeue_message(struct vchiq_instance *instance,
 			spin_unlock(&msg_queue_spinlock);
 			DEBUG_TRACE(DEQUEUE_MESSAGE_LINE);
 			if (wait_for_completion_interruptible(&user_service->insert_event)) {
-				vchiq_log_debug(service->state->dev, VCHIQ_ARM,
-						"DEQUEUE_MESSAGE interrupted");
+				dev_dbg(service->state->dev, "arm: DEQUEUE_MESSAGE interrupted\n");
 				ret = -EINTR;
 				break;
 			}
@@ -323,8 +321,8 @@ static int vchiq_irq_queue_bulk_tx_rx(struct vchiq_instance *instance,
 			ret = -ESRCH;
 			goto out;
 		}
-		vchiq_log_debug(service->state->dev, VCHIQ_ARM,
-				"found bulk_waiter %pK for pid %d", waiter, current->pid);
+		dev_dbg(service->state->dev, "arm: found bulk_waiter %pK for pid %d\n",
+			waiter, current->pid);
 		userdata = &waiter->bulk_waiter;
 	} else {
 		userdata = args->userdata;
@@ -355,8 +353,8 @@ static int vchiq_irq_queue_bulk_tx_rx(struct vchiq_instance *instance,
 		mutex_lock(&instance->bulk_waiter_list_mutex);
 		list_add(&waiter->list, &instance->bulk_waiter_list);
 		mutex_unlock(&instance->bulk_waiter_list_mutex);
-		vchiq_log_debug(service->state->dev, VCHIQ_ARM,
-				"saved bulk_waiter %pK for pid %d", waiter, current->pid);
+		dev_dbg(service->state->dev, "arm: saved bulk_waiter %pK for pid %d\n",
+			waiter, current->pid);
 
 		ret = put_user(mode_waiting, mode);
 	}
@@ -455,8 +453,7 @@ static int vchiq_ioc_await_completion(struct vchiq_instance *instance,
 		mutex_lock(&instance->completion_mutex);
 		if (rc) {
 			DEBUG_TRACE(AWAIT_COMPLETION_LINE);
-			vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-					"AWAIT_COMPLETION interrupted");
+			dev_dbg(instance->state->dev, "arm: AWAIT_COMPLETION interrupted\n");
 			ret = -EINTR;
 			goto out;
 		}
@@ -867,10 +864,10 @@ vchiq_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	}
 
 	if (!status && (ret < 0) && (ret != -EINTR) && (ret != -EWOULDBLOCK)) {
-		vchiq_log_debug(instance->state->dev, VCHIQ_ARM,
-				"  ioctl instance %pK, cmd %s -> status %d, %ld",
-				instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
-				ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
+		dev_dbg(instance->state->dev,
+			"arm: ioctl instance %pK, cmd %s -> status %d, %ld\n",
+			instance, (_IOC_NR(cmd) <= VCHIQ_IOC_MAX) ?
+			ioctl_names[_IOC_NR(cmd)] : "<invalid>", status, ret);
 	} else {
 		dev_dbg(instance->state->dev,
 			"arm: ioctl instance %pK, cmd %s -> status %d\n, %ld\n",
@@ -1169,7 +1166,7 @@ static int vchiq_open(struct inode *inode, struct file *file)
 	struct vchiq_state *state = vchiq_get_state();
 	struct vchiq_instance *instance;
 
-	vchiq_log_debug(state->dev, VCHIQ_ARM, "vchiq_open");
+	dev_dbg(state->dev, "arm: vchiq open\n");
 
 	if (!state) {
 		dev_err(state->dev, "arm: vchiq has no connection to VideoCore\n");
@@ -1204,8 +1201,7 @@ static int vchiq_release(struct inode *inode, struct file *file)
 	int ret = 0;
 	int i;
 
-	vchiq_log_debug(state->dev, VCHIQ_ARM, "%s: instance=%lx", __func__,
-			(unsigned long)instance);
+	dev_dbg(state->dev, "arm: instance=%lx\n", (unsigned long)instance);
 
 	if (!state) {
 		ret = -EPERM;
-- 
GitLab


From 566f5ca9768075e453b7b51a397733968df4287d Mon Sep 17 00:00:00 2001
From: Wentong Wu <wentong.wu@intel.com>
Date: Mon, 4 Dec 2023 08:55:43 +0800
Subject: [PATCH 0874/4076] mei: Add transport driver for IVSC device

The Intel visual sensing controller (IVSC) device is designed to control
the camera sharing between host IPU for media usage and IVSC for context
sensing (face detection).

IVSC is exposed to HOST as an SPI device and the message protocol over
the SPI BUS for communicating with the IVSC device is implemented. This
is the backend of mei framework for IVSC device, which usually handles
the hardware data transfer. The mei_csi and mei_ace are the clients of
IVSC mei framework.

The firmware downloading for the IVSC device is implemented as well.

Signed-off-by: Wentong Wu <wentong.wu@intel.com>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Tested-by: Hao Yao <hao.yao@intel.com>
Acked-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/1701651344-20723-2-git-send-email-wentong.wu@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/Kconfig         |  11 +
 drivers/misc/mei/Makefile        |   4 +
 drivers/misc/mei/vsc-fw-loader.c | 822 +++++++++++++++++++++++++++++++
 drivers/misc/mei/vsc-tp.c        | 555 +++++++++++++++++++++
 drivers/misc/mei/vsc-tp.h        |  50 ++
 5 files changed, 1442 insertions(+)
 create mode 100644 drivers/misc/mei/vsc-fw-loader.c
 create mode 100644 drivers/misc/mei/vsc-tp.c
 create mode 100644 drivers/misc/mei/vsc-tp.h

diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig
index 37db142de413e..470957a694593 100644
--- a/drivers/misc/mei/Kconfig
+++ b/drivers/misc/mei/Kconfig
@@ -60,6 +60,17 @@ config INTEL_MEI_GSC
 	  tasks such as graphics card firmware update and security
 	  tasks.
 
+config INTEL_MEI_VSC_HW
+	tristate "Intel visual sensing controller device transport driver"
+	depends on ACPI && SPI
+	depends on GPIOLIB || COMPILE_TEST
+	help
+	  Intel SPI transport driver between host and Intel visual sensing
+	  controller (IVSC) device.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called mei-vsc-hw.
+
 source "drivers/misc/mei/hdcp/Kconfig"
 source "drivers/misc/mei/pxp/Kconfig"
 source "drivers/misc/mei/gsc_proxy/Kconfig"
diff --git a/drivers/misc/mei/Makefile b/drivers/misc/mei/Makefile
index 14aee253ae482..3d0da19a1501d 100644
--- a/drivers/misc/mei/Makefile
+++ b/drivers/misc/mei/Makefile
@@ -31,3 +31,7 @@ CFLAGS_mei-trace.o = -I$(src)
 obj-$(CONFIG_INTEL_MEI_HDCP) += hdcp/
 obj-$(CONFIG_INTEL_MEI_PXP) += pxp/
 obj-$(CONFIG_INTEL_MEI_GSC_PROXY) += gsc_proxy/
+
+obj-$(CONFIG_INTEL_MEI_VSC_HW) += mei-vsc-hw.o
+mei-vsc-hw-y := vsc-tp.o
+mei-vsc-hw-y += vsc-fw-loader.o
diff --git a/drivers/misc/mei/vsc-fw-loader.c b/drivers/misc/mei/vsc-fw-loader.c
new file mode 100644
index 0000000000000..3e151f06e85b7
--- /dev/null
+++ b/drivers/misc/mei/vsc-fw-loader.c
@@ -0,0 +1,822 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, Intel Corporation.
+ * Intel Visual Sensing Controller Transport Layer Linux driver
+ */
+
+#include <linux/acpi.h>
+#include <linux/align.h>
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/firmware.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/string_helpers.h>
+#include <linux/types.h>
+
+#include <asm-generic/unaligned.h>
+
+#include "vsc-tp.h"
+
+#define VSC_MAGIC_NUM			0x49505343 /* IPSC */
+#define VSC_MAGIC_FW			0x49574653 /* IWFS */
+#define VSC_MAGIC_FILE			0x46564353 /* FVCS */
+
+#define VSC_ADDR_BASE			0xE0030000
+#define VSC_EFUSE_ADDR			(VSC_ADDR_BASE + 0x038)
+#define VSC_STRAP_ADDR			(VSC_ADDR_BASE + 0x100)
+
+#define VSC_STRAP_KEY_SRC_MASK		BIT(0)
+#define VSC_STRAP_KEY_SRC_PRODUCT	1
+
+#define VSC_MAINSTEPPING_VERSION_MASK	GENMASK(7, 4)
+#define VSC_MAINSTEPPING_VERSION_A	0
+
+#define VSC_SUBSTEPPING_VERSION_MASK	GENMASK(3, 0)
+#define VSC_SUBSTEPPING_VERSION_0	0
+#define VSC_SUBSTEPPING_VERSION_1	2
+
+#define VSC_BOOT_IMG_OPTION_MASK	GENMASK(15, 0)
+
+#define VSC_SKU_CFG_LOCATION		0x5001A000
+#define VSC_SKU_MAX_SIZE		4100u
+
+#define VSC_ACE_IMG_CNT			2
+#define VSC_CSI_IMG_CNT			4
+#define VSC_IMG_CNT_MAX			6
+
+#define VSC_ROM_PKG_SIZE		256u
+#define VSC_FW_PKG_SIZE			512u
+
+#define VSC_CSI_IMAGE_NAME_FMT		"ivsc_fw_a1.bin"
+#define VSC_CSI_IMAGE_NAME_FMT_PROD	"ivsc_fw_a1_%s.bin"
+#define VSC_ACE_IMAGE_NAME_FMT		"ivsc_pkg_%s_0_a1.bin"
+#define VSC_ACE_IMAGE_NAME_FMT_PROD	"ivsc_pkg_%s_0_a1_%s.bin"
+#define VSC_CFG_IMAGE_NAME_FMT		"ivsc_skucfg_%s_0_1_a1.bin"
+#define VSC_CFG_IMAGE_NAME_FMT_PROD	"ivsc_skucfg_%s_0_1_a1_%s.bin"
+
+#define VSC_IMAGE_FOLDER_FMT		"vsc/soc_a1"
+#define VSC_IMAGE_FOLDER_FMT_PROD	"vsc/soc_a1_%s"
+
+#define VSC_IMAGE_NAME_MAX_LEN		64
+#define VSC_IMAGE_PATH_MAX_LEN		128
+
+#define VSC_SENSOR_NAME_MAX_LEN		16
+#define VSC_IMAGE_FOLDER_NAME_MAX_LEN	32
+#define VSC_IMAGE_NAME_SUFFIX_MAX_LEN	8
+
+/* command id */
+enum {
+	VSC_CMD_QUERY = 0,
+	VSC_CMD_DL_SET = 1,
+	VSC_CMD_DL_START = 2,
+	VSC_CMD_DL_CONT = 3,
+	VSC_CMD_DUMP_MEM = 4,
+	VSC_CMD_GET_CONT = 8,
+	VSC_CMD_CAM_BOOT = 10,
+};
+
+/* command ack token */
+enum {
+	VSC_TOKEN_BOOTLOADER_REQ = 1,
+	VSC_TOKEN_DUMP_RESP = 4,
+	VSC_TOKEN_ERROR = 7,
+};
+
+/* image type */
+enum {
+	VSC_IMG_BOOTLOADER_TYPE = 1,
+	VSC_IMG_CSI_EM7D_TYPE,
+	VSC_IMG_CSI_SEM_TYPE,
+	VSC_IMG_CSI_RUNTIME_TYPE,
+	VSC_IMG_ACE_VISION_TYPE,
+	VSC_IMG_ACE_CFG_TYPE,
+	VSC_IMG_SKU_CFG_TYPE,
+};
+
+/* image fragments */
+enum {
+	VSC_IMG_BOOTLOADER_FRAG,
+	VSC_IMG_CSI_SEM_FRAG,
+	VSC_IMG_CSI_RUNTIME_FRAG,
+	VSC_IMG_ACE_VISION_FRAG,
+	VSC_IMG_ACE_CFG_FRAG,
+	VSC_IMG_CSI_EM7D_FRAG,
+	VSC_IMG_SKU_CFG_FRAG,
+	VSC_IMG_FRAG_MAX
+};
+
+struct vsc_rom_cmd {
+	__le32 magic;
+	__u8 cmd_id;
+	union {
+		/* download start */
+		struct {
+			__u8 img_type;
+			__le16 option;
+			__le32 img_len;
+			__le32 img_loc;
+			__le32 crc;
+			DECLARE_FLEX_ARRAY(__u8, res);
+		} __packed dl_start;
+		/* download set */
+		struct {
+			__u8 option;
+			__le16 img_cnt;
+			DECLARE_FLEX_ARRAY(__le32, payload);
+		} __packed dl_set;
+		/* download continue */
+		struct {
+			__u8 end_flag;
+			__le16 len;
+			/* 8 is the offset of payload */
+			__u8 payload[VSC_ROM_PKG_SIZE - 8];
+		} __packed dl_cont;
+		/* dump memory */
+		struct {
+			__u8 res;
+			__le16 len;
+			__le32 addr;
+			DECLARE_FLEX_ARRAY(__u8, payload);
+		} __packed dump_mem;
+		/* 5 is the offset of padding */
+		__u8 padding[VSC_ROM_PKG_SIZE - 5];
+	} data;
+};
+
+struct vsc_rom_cmd_ack {
+	__le32 magic;
+	__u8 token;
+	__u8 type;
+	__u8 res[2];
+	__u8 payload[];
+};
+
+struct vsc_fw_cmd {
+	__le32 magic;
+	__u8 cmd_id;
+	union {
+		struct {
+			__le16 option;
+			__u8 img_type;
+			__le32 img_len;
+			__le32 img_loc;
+			__le32 crc;
+			DECLARE_FLEX_ARRAY(__u8, res);
+		} __packed dl_start;
+		struct {
+			__le16 option;
+			__u8 img_cnt;
+			DECLARE_FLEX_ARRAY(__le32, payload);
+		} __packed dl_set;
+		struct {
+			__le32 addr;
+			__u8 len;
+			DECLARE_FLEX_ARRAY(__u8, payload);
+		} __packed dump_mem;
+		struct {
+			__u8 resv[3];
+			__le32 crc;
+			DECLARE_FLEX_ARRAY(__u8, payload);
+		} __packed boot;
+		/* 5 is the offset of padding */
+		__u8 padding[VSC_FW_PKG_SIZE - 5];
+	} data;
+};
+
+struct vsc_img {
+	__le32 magic;
+	__le32 option;
+	__le32 image_count;
+	__le32 image_location[VSC_IMG_CNT_MAX];
+};
+
+struct vsc_fw_sign {
+	__le32 magic;
+	__le32 image_size;
+	__u8 image[];
+};
+
+struct vsc_image_code_data {
+	/* fragment index */
+	u8 frag_index;
+	/* image type */
+	u8 image_type;
+};
+
+struct vsc_img_frag {
+	u8 type;
+	u32 location;
+	const u8 *data;
+	u32 size;
+};
+
+/**
+ * struct vsc_fw_loader - represent vsc firmware loader
+ * @dev: device used to request fimware
+ * @tp: transport layer used with the firmware loader
+ * @csi: CSI image
+ * @ace: ACE image
+ * @cfg: config image
+ * @tx_buf: tx buffer
+ * @rx_buf: rx buffer
+ * @option: command option
+ * @count: total image count
+ * @key_src: key source
+ * @folder: image folder
+ * @sensor_name: camera sensor name
+ * @suffix: image name suffix
+ * @frags: image fragments
+ */
+struct vsc_fw_loader {
+	struct device *dev;
+	struct vsc_tp *tp;
+
+	const struct firmware *csi;
+	const struct firmware *ace;
+	const struct firmware *cfg;
+
+	void *tx_buf;
+	void *rx_buf;
+
+	u16 option;
+	u16 count;
+	u32 key_src;
+
+	char folder[VSC_IMAGE_FOLDER_NAME_MAX_LEN];
+	char sensor_name[VSC_SENSOR_NAME_MAX_LEN];
+	char suffix[VSC_IMAGE_NAME_SUFFIX_MAX_LEN];
+
+	struct vsc_img_frag frags[VSC_IMG_FRAG_MAX];
+};
+
+static inline u32 vsc_sum_crc(void *data, size_t size)
+{
+	u32 crc = 0;
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		crc += *((u8 *)data + i);
+
+	return crc;
+}
+
+/* get sensor name to construct image name */
+static int vsc_get_sensor_name(struct vsc_fw_loader *fw_loader,
+			       struct device *dev)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER };
+	union acpi_object obj = {
+		.type = ACPI_TYPE_INTEGER,
+		.integer.value = 1,
+	};
+	struct acpi_object_list arg_list = {
+		.count = 1,
+		.pointer = &obj,
+	};
+	union acpi_object *ret_obj;
+	acpi_handle handle;
+	acpi_status status;
+	int ret = 0;
+
+	handle = ACPI_HANDLE(dev);
+	if (!handle)
+		return -EINVAL;
+
+	status = acpi_evaluate_object(handle, "SID", &arg_list, &buffer);
+	if (ACPI_FAILURE(status)) {
+		dev_err(dev, "can't evaluate SID method: %d\n", status);
+		return -ENODEV;
+	}
+
+	ret_obj = buffer.pointer;
+	if (!ret_obj) {
+		dev_err(dev, "can't locate ACPI buffer\n");
+		return -ENODEV;
+	}
+
+	if (ret_obj->type != ACPI_TYPE_STRING) {
+		dev_err(dev, "found non-string entry\n");
+		ret = -ENODEV;
+		goto out_free_buff;
+	}
+
+	/* string length excludes trailing NUL */
+	if (ret_obj->string.length >= sizeof(fw_loader->sensor_name)) {
+		dev_err(dev, "sensor name buffer too small\n");
+		ret = -EINVAL;
+		goto out_free_buff;
+	}
+
+	memcpy(fw_loader->sensor_name, ret_obj->string.pointer,
+	       ret_obj->string.length);
+
+	string_lower(fw_loader->sensor_name, fw_loader->sensor_name);
+
+out_free_buff:
+	ACPI_FREE(buffer.pointer);
+
+	return ret;
+}
+
+static int vsc_identify_silicon(struct vsc_fw_loader *fw_loader)
+{
+	struct vsc_rom_cmd_ack *ack = fw_loader->rx_buf;
+	struct vsc_rom_cmd *cmd = fw_loader->tx_buf;
+	u8 version, sub_version;
+	int ret;
+
+	/* identify stepping information */
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_DUMP_MEM;
+	cmd->data.dump_mem.addr = cpu_to_le32(VSC_EFUSE_ADDR);
+	cmd->data.dump_mem.len = cpu_to_le16(sizeof(__le32));
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token == VSC_TOKEN_ERROR)
+		return -EINVAL;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_GET_CONT;
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token != VSC_TOKEN_DUMP_RESP)
+		return -EINVAL;
+
+	version = FIELD_GET(VSC_MAINSTEPPING_VERSION_MASK, ack->payload[0]);
+	sub_version = FIELD_GET(VSC_SUBSTEPPING_VERSION_MASK, ack->payload[0]);
+
+	if (version != VSC_MAINSTEPPING_VERSION_A)
+		return -EINVAL;
+
+	if (sub_version != VSC_SUBSTEPPING_VERSION_0 &&
+	    sub_version != VSC_SUBSTEPPING_VERSION_1)
+		return -EINVAL;
+
+	dev_info(fw_loader->dev, "silicon stepping version is %u:%u\n",
+		 version, sub_version);
+
+	/* identify strap information */
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_DUMP_MEM;
+	cmd->data.dump_mem.addr = cpu_to_le32(VSC_STRAP_ADDR);
+	cmd->data.dump_mem.len = cpu_to_le16(sizeof(__le32));
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token == VSC_TOKEN_ERROR)
+		return -EINVAL;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_GET_CONT;
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token != VSC_TOKEN_DUMP_RESP)
+		return -EINVAL;
+
+	fw_loader->key_src = FIELD_GET(VSC_STRAP_KEY_SRC_MASK, ack->payload[2]);
+
+	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
+		strscpy(fw_loader->suffix, "prod", sizeof(fw_loader->suffix));
+
+	return 0;
+}
+
+static int vsc_identify_csi_image(struct vsc_fw_loader *fw_loader)
+{
+	char path[VSC_IMAGE_PATH_MAX_LEN];
+	char name[VSC_IMAGE_NAME_MAX_LEN];
+	const struct firmware *image;
+	struct vsc_fw_sign *sign;
+	struct vsc_img *img;
+	unsigned int i;
+	int ret;
+
+	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
+		snprintf(name, sizeof(name), VSC_CSI_IMAGE_NAME_FMT_PROD,
+			 fw_loader->suffix);
+	else
+		snprintf(name, sizeof(name), VSC_CSI_IMAGE_NAME_FMT);
+
+	snprintf(path, sizeof(path), "%s/%s", fw_loader->folder, name);
+
+	ret = request_firmware(&image, path, fw_loader->dev);
+	if (ret)
+		return ret;
+
+	img = (struct vsc_img *)image->data;
+	if (!img) {
+		ret = -ENOENT;
+		goto err_release_image;
+	}
+
+	if (le32_to_cpu(img->magic) != VSC_MAGIC_FILE) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+
+	if (le32_to_cpu(img->image_count) != VSC_CSI_IMG_CNT) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+	fw_loader->count += le32_to_cpu(img->image_count) - 1;
+
+	fw_loader->option =
+		FIELD_GET(VSC_BOOT_IMG_OPTION_MASK, le32_to_cpu(img->option));
+
+	sign = (struct vsc_fw_sign *)
+		(img->image_location + le32_to_cpu(img->image_count));
+
+	for (i = 0; i < VSC_CSI_IMG_CNT; i++) {
+		/* mapping from CSI image index to image code data */
+		static const struct vsc_image_code_data csi_image_map[] = {
+			{ VSC_IMG_BOOTLOADER_FRAG, VSC_IMG_BOOTLOADER_TYPE },
+			{ VSC_IMG_CSI_SEM_FRAG, VSC_IMG_CSI_SEM_TYPE },
+			{ VSC_IMG_CSI_RUNTIME_FRAG, VSC_IMG_CSI_RUNTIME_TYPE },
+			{ VSC_IMG_CSI_EM7D_FRAG, VSC_IMG_CSI_EM7D_TYPE },
+		};
+		struct vsc_img_frag *frag;
+
+		if ((u8 *)sign + sizeof(*sign) > image->data + image->size) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		if (le32_to_cpu(sign->magic) != VSC_MAGIC_FW) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		if (!le32_to_cpu(img->image_location[i])) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		frag = &fw_loader->frags[csi_image_map[i].frag_index];
+
+		frag->data = sign->image;
+		frag->size = le32_to_cpu(sign->image_size);
+		frag->location = le32_to_cpu(img->image_location[i]);
+		frag->type = csi_image_map[i].image_type;
+
+		sign = (struct vsc_fw_sign *)
+			(sign->image + le32_to_cpu(sign->image_size));
+	}
+
+	fw_loader->csi = image;
+
+	return 0;
+
+err_release_image:
+	release_firmware(image);
+
+	return ret;
+}
+
+static int vsc_identify_ace_image(struct vsc_fw_loader *fw_loader)
+{
+	char path[VSC_IMAGE_PATH_MAX_LEN];
+	char name[VSC_IMAGE_NAME_MAX_LEN];
+	const struct firmware *image;
+	struct vsc_fw_sign *sign;
+	struct vsc_img *img;
+	unsigned int i;
+	int ret;
+
+	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
+		snprintf(name, sizeof(name), VSC_ACE_IMAGE_NAME_FMT_PROD,
+			 fw_loader->sensor_name, fw_loader->suffix);
+	else
+		snprintf(name, sizeof(name), VSC_ACE_IMAGE_NAME_FMT,
+			 fw_loader->sensor_name);
+
+	snprintf(path, sizeof(path), "%s/%s", fw_loader->folder, name);
+
+	ret = request_firmware(&image, path, fw_loader->dev);
+	if (ret)
+		return ret;
+
+	img = (struct vsc_img *)image->data;
+	if (!img) {
+		ret = -ENOENT;
+		goto err_release_image;
+	}
+
+	if (le32_to_cpu(img->magic) != VSC_MAGIC_FILE) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+
+	if (le32_to_cpu(img->image_count) != VSC_ACE_IMG_CNT) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+	fw_loader->count += le32_to_cpu(img->image_count);
+
+	sign = (struct vsc_fw_sign *)
+		(img->image_location + le32_to_cpu(img->image_count));
+
+	for (i = 0; i < VSC_ACE_IMG_CNT; i++) {
+		/* mapping from ACE image index to image code data */
+		static const struct vsc_image_code_data ace_image_map[] = {
+			{ VSC_IMG_ACE_VISION_FRAG, VSC_IMG_ACE_VISION_TYPE },
+			{ VSC_IMG_ACE_CFG_FRAG, VSC_IMG_ACE_CFG_TYPE },
+		};
+		struct vsc_img_frag *frag, *last_frag;
+		u8 frag_index;
+
+		if ((u8 *)sign + sizeof(*sign) > image->data + image->size) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		if (le32_to_cpu(sign->magic) != VSC_MAGIC_FW) {
+			ret = -EINVAL;
+			goto err_release_image;
+		}
+
+		frag_index = ace_image_map[i].frag_index;
+		frag = &fw_loader->frags[frag_index];
+
+		frag->data = sign->image;
+		frag->size = le32_to_cpu(sign->image_size);
+		frag->location = le32_to_cpu(img->image_location[i]);
+		frag->type = ace_image_map[i].image_type;
+
+		if (!frag->location) {
+			last_frag = &fw_loader->frags[frag_index - 1];
+			frag->location =
+				ALIGN(last_frag->location + last_frag->size, SZ_4K);
+		}
+
+		sign = (struct vsc_fw_sign *)
+			(sign->image + le32_to_cpu(sign->image_size));
+	}
+
+	fw_loader->ace = image;
+
+	return 0;
+
+err_release_image:
+	release_firmware(image);
+
+	return ret;
+}
+
+static int vsc_identify_cfg_image(struct vsc_fw_loader *fw_loader)
+{
+	struct vsc_img_frag *frag = &fw_loader->frags[VSC_IMG_SKU_CFG_FRAG];
+	char path[VSC_IMAGE_PATH_MAX_LEN];
+	char name[VSC_IMAGE_NAME_MAX_LEN];
+	const struct firmware *image;
+	u32 size;
+	int ret;
+
+	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
+		snprintf(name, sizeof(name), VSC_CFG_IMAGE_NAME_FMT_PROD,
+			 fw_loader->sensor_name, fw_loader->suffix);
+	else
+		snprintf(name, sizeof(name), VSC_CFG_IMAGE_NAME_FMT,
+			 fw_loader->sensor_name);
+
+	snprintf(path, sizeof(path), "%s/%s", fw_loader->folder, name);
+
+	ret = request_firmware(&image, path, fw_loader->dev);
+	if (ret)
+		return ret;
+
+	/* identify image size */
+	if (image->size <= sizeof(u32) || image->size > VSC_SKU_MAX_SIZE) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+
+	size = le32_to_cpu(*((__le32 *)image->data)) + sizeof(u32);
+	if (image->size != size) {
+		ret = -EINVAL;
+		goto err_release_image;
+	}
+
+	frag->data = image->data;
+	frag->size = image->size;
+	frag->type = VSC_IMG_SKU_CFG_TYPE;
+	frag->location = VSC_SKU_CFG_LOCATION;
+
+	fw_loader->cfg = image;
+
+	return 0;
+
+err_release_image:
+	release_firmware(image);
+
+	return ret;
+}
+
+static int vsc_download_bootloader(struct vsc_fw_loader *fw_loader)
+{
+	struct vsc_img_frag *frag = &fw_loader->frags[VSC_IMG_BOOTLOADER_FRAG];
+	struct vsc_rom_cmd_ack *ack = fw_loader->rx_buf;
+	struct vsc_rom_cmd *cmd = fw_loader->tx_buf;
+	u32 len, c_len;
+	size_t remain;
+	const u8 *p;
+	int ret;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_QUERY;
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, ack, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+	if (ack->token != VSC_TOKEN_DUMP_RESP &&
+	    ack->token != VSC_TOKEN_BOOTLOADER_REQ)
+		return -EINVAL;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_DL_START;
+	cmd->data.dl_start.option = cpu_to_le16(fw_loader->option);
+	cmd->data.dl_start.img_type = frag->type;
+	cmd->data.dl_start.img_len = cpu_to_le32(frag->size);
+	cmd->data.dl_start.img_loc = cpu_to_le32(frag->location);
+
+	c_len = offsetof(struct vsc_rom_cmd, data.dl_start.crc);
+	cmd->data.dl_start.crc = cpu_to_le32(vsc_sum_crc(cmd, c_len));
+
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_ROM_PKG_SIZE);
+	if (ret)
+		return ret;
+
+	p = frag->data;
+	remain = frag->size;
+
+	/* download image data */
+	while (remain > 0) {
+		len = min(remain, sizeof(cmd->data.dl_cont.payload));
+
+		cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+		cmd->cmd_id = VSC_CMD_DL_CONT;
+		cmd->data.dl_cont.len = cpu_to_le16(len);
+		cmd->data.dl_cont.end_flag = remain == len;
+		memcpy(cmd->data.dl_cont.payload, p, len);
+
+		ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_ROM_PKG_SIZE);
+		if (ret)
+			return ret;
+
+		p += len;
+		remain -= len;
+	}
+
+	return 0;
+}
+
+static int vsc_download_firmware(struct vsc_fw_loader *fw_loader)
+{
+	struct vsc_fw_cmd *cmd = fw_loader->tx_buf;
+	unsigned int i, index = 0;
+	u32 c_len;
+	int ret;
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_DL_SET;
+	cmd->data.dl_set.img_cnt = cpu_to_le16(fw_loader->count);
+	put_unaligned_le16(fw_loader->option, &cmd->data.dl_set.option);
+
+	for (i = VSC_IMG_CSI_SEM_FRAG; i <= VSC_IMG_CSI_EM7D_FRAG; i++) {
+		struct vsc_img_frag *frag = &fw_loader->frags[i];
+
+		cmd->data.dl_set.payload[index++] = cpu_to_le32(frag->location);
+		cmd->data.dl_set.payload[index++] = cpu_to_le32(frag->size);
+	}
+
+	c_len = offsetof(struct vsc_fw_cmd, data.dl_set.payload[index]);
+	cmd->data.dl_set.payload[index] = cpu_to_le32(vsc_sum_crc(cmd, c_len));
+
+	ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_FW_PKG_SIZE);
+	if (ret)
+		return ret;
+
+	for (i = VSC_IMG_CSI_SEM_FRAG; i < VSC_IMG_FRAG_MAX; i++) {
+		struct vsc_img_frag *frag = &fw_loader->frags[i];
+		const u8 *p;
+		u32 remain;
+
+		cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+		cmd->cmd_id = VSC_CMD_DL_START;
+		cmd->data.dl_start.img_type = frag->type;
+		cmd->data.dl_start.img_len = cpu_to_le32(frag->size);
+		cmd->data.dl_start.img_loc = cpu_to_le32(frag->location);
+		put_unaligned_le16(fw_loader->option, &cmd->data.dl_start.option);
+
+		c_len = offsetof(struct vsc_fw_cmd, data.dl_start.crc);
+		cmd->data.dl_start.crc = cpu_to_le32(vsc_sum_crc(cmd, c_len));
+
+		ret = vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_FW_PKG_SIZE);
+		if (ret)
+			return ret;
+
+		p = frag->data;
+		remain = frag->size;
+
+		/* download image data */
+		while (remain > 0) {
+			u32 len = min(remain, VSC_FW_PKG_SIZE);
+
+			memcpy(fw_loader->tx_buf, p, len);
+			memset(fw_loader->tx_buf + len, 0, VSC_FW_PKG_SIZE - len);
+
+			ret = vsc_tp_rom_xfer(fw_loader->tp, fw_loader->tx_buf,
+					      NULL, VSC_FW_PKG_SIZE);
+			if (ret)
+				break;
+
+			p += len;
+			remain -= len;
+		}
+	}
+
+	cmd->magic = cpu_to_le32(VSC_MAGIC_NUM);
+	cmd->cmd_id = VSC_CMD_CAM_BOOT;
+
+	c_len = offsetof(struct vsc_fw_cmd, data.dl_start.crc);
+	cmd->data.boot.crc = cpu_to_le32(vsc_sum_crc(cmd, c_len));
+
+	return vsc_tp_rom_xfer(fw_loader->tp, cmd, NULL, VSC_FW_PKG_SIZE);
+}
+
+/**
+ * vsc_tp_init - init vsc_tp
+ * @tp: vsc_tp device handle
+ * @dev: device node for mei vsc device
+ * Return: 0 in case of success, negative value in case of error
+ */
+int vsc_tp_init(struct vsc_tp *tp, struct device *dev)
+{
+	struct vsc_fw_loader *fw_loader __free(kfree) = NULL;
+	void *tx_buf __free(kfree) = NULL;
+	void *rx_buf __free(kfree) = NULL;
+	int ret;
+
+	fw_loader = kzalloc(sizeof(*fw_loader), GFP_KERNEL);
+	if (!fw_loader)
+		return -ENOMEM;
+
+	tx_buf = kzalloc(VSC_FW_PKG_SIZE, GFP_KERNEL);
+	if (!tx_buf)
+		return -ENOMEM;
+
+	rx_buf = kzalloc(VSC_FW_PKG_SIZE, GFP_KERNEL);
+	if (!rx_buf)
+		return -ENOMEM;
+
+	fw_loader->tx_buf = tx_buf;
+	fw_loader->rx_buf = rx_buf;
+
+	fw_loader->tp = tp;
+	fw_loader->dev = dev;
+
+	ret = vsc_get_sensor_name(fw_loader, dev);
+	if (ret)
+		return ret;
+
+	ret = vsc_identify_silicon(fw_loader);
+	if (ret)
+		return ret;
+
+	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
+		snprintf(fw_loader->folder, sizeof(fw_loader->folder),
+			 VSC_IMAGE_FOLDER_FMT_PROD, fw_loader->suffix);
+	else
+		snprintf(fw_loader->folder, sizeof(fw_loader->folder),
+			 VSC_IMAGE_FOLDER_FMT);
+
+	ret = vsc_identify_csi_image(fw_loader);
+	if (ret)
+		return ret;
+
+	ret = vsc_identify_ace_image(fw_loader);
+	if (ret)
+		goto err_release_csi;
+
+	ret = vsc_identify_cfg_image(fw_loader);
+	if (ret)
+		goto err_release_ace;
+
+	ret = vsc_download_bootloader(fw_loader);
+	if (!ret)
+		ret = vsc_download_firmware(fw_loader);
+
+	release_firmware(fw_loader->cfg);
+
+err_release_ace:
+	release_firmware(fw_loader->ace);
+
+err_release_csi:
+	release_firmware(fw_loader->csi);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_init, VSC_TP);
diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
new file mode 100644
index 0000000000000..6f4a4be6ccb55
--- /dev/null
+++ b/drivers/misc/mei/vsc-tp.c
@@ -0,0 +1,555 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, Intel Corporation.
+ * Intel Visual Sensing Controller Transport Layer Linux driver
+ */
+
+#include <linux/acpi.h>
+#include <linux/cleanup.h>
+#include <linux/crc32.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/types.h>
+
+#include "vsc-tp.h"
+
+#define VSC_TP_RESET_PIN_TOGGLE_INTERVAL_MS	20
+#define VSC_TP_ROM_BOOTUP_DELAY_MS		10
+#define VSC_TP_ROM_XFER_POLL_TIMEOUT_US		(500 * USEC_PER_MSEC)
+#define VSC_TP_ROM_XFER_POLL_DELAY_US		(20 * USEC_PER_MSEC)
+#define VSC_TP_WAIT_FW_ASSERTED_TIMEOUT		(2 * HZ)
+#define VSC_TP_MAX_XFER_COUNT			5
+
+#define VSC_TP_PACKET_SYNC			0x31
+#define VSC_TP_CRC_SIZE				sizeof(u32)
+#define VSC_TP_MAX_MSG_SIZE			2048
+/* SPI xfer timeout size */
+#define VSC_TP_XFER_TIMEOUT_BYTES		700
+#define VSC_TP_PACKET_PADDING_SIZE		1
+#define VSC_TP_PACKET_SIZE(pkt) \
+	(sizeof(struct vsc_tp_packet) + le16_to_cpu((pkt)->len) + VSC_TP_CRC_SIZE)
+#define VSC_TP_MAX_PACKET_SIZE \
+	(sizeof(struct vsc_tp_packet) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
+#define VSC_TP_MAX_XFER_SIZE \
+	(VSC_TP_MAX_PACKET_SIZE + VSC_TP_XFER_TIMEOUT_BYTES)
+#define VSC_TP_NEXT_XFER_LEN(len, offset) \
+	(len + sizeof(struct vsc_tp_packet) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
+
+struct vsc_tp_packet {
+	__u8 sync;
+	__u8 cmd;
+	__le16 len;
+	__le32 seq;
+	__u8 buf[] __counted_by(len);
+};
+
+struct vsc_tp {
+	/* do the actual data transfer */
+	struct spi_device *spi;
+
+	/* bind with mei framework */
+	struct platform_device *pdev;
+
+	struct gpio_desc *wakeuphost;
+	struct gpio_desc *resetfw;
+	struct gpio_desc *wakeupfw;
+
+	/* command sequence number */
+	u32 seq;
+
+	/* command buffer */
+	void *tx_buf;
+	void *rx_buf;
+
+	atomic_t assert_cnt;
+	wait_queue_head_t xfer_wait;
+
+	vsc_tp_event_cb_t event_notify;
+	void *event_notify_context;
+
+	/* used to protect command download */
+	struct mutex mutex;
+};
+
+/* GPIO resources */
+static const struct acpi_gpio_params wakeuphost_gpio = { 0, 0, false };
+static const struct acpi_gpio_params wakeuphostint_gpio = { 1, 0, false };
+static const struct acpi_gpio_params resetfw_gpio = { 2, 0, false };
+static const struct acpi_gpio_params wakeupfw = { 3, 0, false };
+
+static const struct acpi_gpio_mapping vsc_tp_acpi_gpios[] = {
+	{ "wakeuphost-gpios", &wakeuphost_gpio, 1 },
+	{ "wakeuphostint-gpios", &wakeuphostint_gpio, 1 },
+	{ "resetfw-gpios", &resetfw_gpio, 1 },
+	{ "wakeupfw-gpios", &wakeupfw, 1 },
+	{}
+};
+
+/* wakeup firmware and wait for response */
+static int vsc_tp_wakeup_request(struct vsc_tp *tp)
+{
+	int ret;
+
+	gpiod_set_value_cansleep(tp->wakeupfw, 0);
+
+	ret = wait_event_timeout(tp->xfer_wait,
+				 atomic_read(&tp->assert_cnt) &&
+				 gpiod_get_value_cansleep(tp->wakeuphost),
+				 VSC_TP_WAIT_FW_ASSERTED_TIMEOUT);
+	if (!ret)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void vsc_tp_wakeup_release(struct vsc_tp *tp)
+{
+	atomic_dec_if_positive(&tp->assert_cnt);
+
+	gpiod_set_value_cansleep(tp->wakeupfw, 1);
+}
+
+static int vsc_tp_dev_xfer(struct vsc_tp *tp, void *obuf, void *ibuf, size_t len)
+{
+	struct spi_message msg = { 0 };
+	struct spi_transfer xfer = {
+		.tx_buf = obuf,
+		.rx_buf = ibuf,
+		.len = len,
+	};
+
+	spi_message_init_with_transfers(&msg, &xfer, 1);
+
+	return spi_sync_locked(tp->spi, &msg);
+}
+
+static int vsc_tp_xfer_helper(struct vsc_tp *tp, struct vsc_tp_packet *pkt,
+			      void *ibuf, u16 ilen)
+{
+	int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet);
+	int next_xfer_len = VSC_TP_PACKET_SIZE(pkt) + VSC_TP_XFER_TIMEOUT_BYTES;
+	u8 *src, *crc_src, *rx_buf = tp->rx_buf;
+	int count_down = VSC_TP_MAX_XFER_COUNT;
+	u32 recv_crc = 0, crc = ~0;
+	struct vsc_tp_packet ack;
+	u8 *dst = (u8 *)&ack;
+	bool synced = false;
+
+	do {
+		ret = vsc_tp_dev_xfer(tp, pkt, rx_buf, next_xfer_len);
+		if (ret)
+			return ret;
+		memset(pkt, 0, VSC_TP_MAX_XFER_SIZE);
+
+		if (synced) {
+			src = rx_buf;
+			src_len = next_xfer_len;
+		} else {
+			src = memchr(rx_buf, VSC_TP_PACKET_SYNC, next_xfer_len);
+			if (!src)
+				continue;
+			synced = true;
+			src_len = next_xfer_len - (src - rx_buf);
+		}
+
+		/* traverse received data */
+		while (src_len > 0) {
+			cpy_len = min(src_len, dst_len);
+			memcpy(dst, src, cpy_len);
+			crc_src = src;
+			src += cpy_len;
+			src_len -= cpy_len;
+			dst += cpy_len;
+			dst_len -= cpy_len;
+
+			if (offset < sizeof(ack)) {
+				offset += cpy_len;
+				crc = crc32(crc, crc_src, cpy_len);
+
+				if (!src_len)
+					continue;
+
+				if (le16_to_cpu(ack.len)) {
+					dst = ibuf;
+					dst_len = min(ilen, le16_to_cpu(ack.len));
+				} else {
+					dst = (u8 *)&recv_crc;
+					dst_len = sizeof(recv_crc);
+				}
+			} else if (offset < sizeof(ack) + le16_to_cpu(ack.len)) {
+				offset += cpy_len;
+				crc = crc32(crc, crc_src, cpy_len);
+
+				if (src_len) {
+					int remain = sizeof(ack) + le16_to_cpu(ack.len) - offset;
+
+					cpy_len = min(src_len, remain);
+					offset += cpy_len;
+					crc = crc32(crc, src, cpy_len);
+					src += cpy_len;
+					src_len -= cpy_len;
+					if (src_len) {
+						dst = (u8 *)&recv_crc;
+						dst_len = sizeof(recv_crc);
+						continue;
+					}
+				}
+				next_xfer_len = VSC_TP_NEXT_XFER_LEN(le16_to_cpu(ack.len), offset);
+			} else if (offset < sizeof(ack) + le16_to_cpu(ack.len) + VSC_TP_CRC_SIZE) {
+				offset += cpy_len;
+
+				if (src_len) {
+					/* terminate the traverse */
+					next_xfer_len = 0;
+					break;
+				}
+				next_xfer_len = VSC_TP_NEXT_XFER_LEN(le16_to_cpu(ack.len), offset);
+			}
+		}
+	} while (next_xfer_len > 0 && --count_down);
+
+	if (next_xfer_len > 0)
+		return -EAGAIN;
+
+	if (~recv_crc != crc || le32_to_cpu(ack.seq) != tp->seq) {
+		dev_err(&tp->spi->dev, "recv crc or seq error\n");
+		return -EINVAL;
+	}
+
+	if (ack.cmd == VSC_TP_CMD_ACK || ack.cmd == VSC_TP_CMD_NACK ||
+	    ack.cmd == VSC_TP_CMD_BUSY) {
+		dev_err(&tp->spi->dev, "recv cmd ack error\n");
+		return -EAGAIN;
+	}
+
+	return min(le16_to_cpu(ack.len), ilen);
+}
+
+/**
+ * vsc_tp_xfer - transfer data to firmware
+ * @tp: vsc_tp device handle
+ * @cmd: the command to be sent to the device
+ * @obuf: the tx buffer to be sent to the device
+ * @olen: the length of tx buffer
+ * @ibuf: the rx buffer to receive from the device
+ * @ilen: the length of rx buffer
+ * Return: the length of received data in case of success,
+ *	otherwise negative value
+ */
+int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen,
+		void *ibuf, size_t ilen)
+{
+	struct vsc_tp_packet *pkt = tp->tx_buf;
+	u32 crc;
+	int ret;
+
+	if (!obuf || !ibuf || olen > VSC_TP_MAX_MSG_SIZE)
+		return -EINVAL;
+
+	guard(mutex)(&tp->mutex);
+
+	pkt->sync = VSC_TP_PACKET_SYNC;
+	pkt->cmd = cmd;
+	pkt->len = cpu_to_le16(olen);
+	pkt->seq = cpu_to_le32(++tp->seq);
+	memcpy(pkt->buf, obuf, olen);
+
+	crc = ~crc32(~0, (u8 *)pkt, sizeof(pkt) + olen);
+	memcpy(pkt->buf + olen, &crc, sizeof(crc));
+
+	ret = vsc_tp_wakeup_request(tp);
+	if (unlikely(ret))
+		dev_err(&tp->spi->dev, "wakeup firmware failed ret: %d\n", ret);
+	else
+		ret = vsc_tp_xfer_helper(tp, pkt, ibuf, ilen);
+
+	vsc_tp_wakeup_release(tp);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_xfer, VSC_TP);
+
+/**
+ * vsc_tp_rom_xfer - transfer data to rom code
+ * @tp: vsc_tp device handle
+ * @obuf: the data buffer to be sent to the device
+ * @ibuf: the buffer to receive data from the device
+ * @len: the length of tx buffer and rx buffer
+ * Return: 0 in case of success, negative value in case of error
+ */
+int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
+{
+	size_t words = len / sizeof(__be32);
+	int ret;
+
+	if (len % sizeof(__be32) || len > VSC_TP_MAX_MSG_SIZE)
+		return -EINVAL;
+
+	guard(mutex)(&tp->mutex);
+
+	/* rom xfer is big endian */
+	cpu_to_be32_array(tp->tx_buf, obuf, words);
+
+	ret = read_poll_timeout(gpiod_get_value_cansleep, ret,
+				!ret, VSC_TP_ROM_XFER_POLL_DELAY_US,
+				VSC_TP_ROM_XFER_POLL_TIMEOUT_US, false,
+				tp->wakeuphost);
+	if (ret) {
+		dev_err(&tp->spi->dev, "wait rom failed ret: %d\n", ret);
+		return ret;
+	}
+
+	ret = vsc_tp_dev_xfer(tp, tp->tx_buf, tp->rx_buf, len);
+	if (ret)
+		return ret;
+
+	if (ibuf)
+		cpu_to_be32_array(ibuf, tp->rx_buf, words);
+
+	return ret;
+}
+
+/**
+ * vsc_tp_reset - reset vsc transport layer
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_reset(struct vsc_tp *tp)
+{
+	disable_irq(tp->spi->irq);
+
+	/* toggle reset pin */
+	gpiod_set_value_cansleep(tp->resetfw, 0);
+	msleep(VSC_TP_RESET_PIN_TOGGLE_INTERVAL_MS);
+	gpiod_set_value_cansleep(tp->resetfw, 1);
+
+	/* wait for ROM */
+	msleep(VSC_TP_ROM_BOOTUP_DELAY_MS);
+
+	/*
+	 * Set default host wakeup pin to non-active
+	 * to avoid unexpected host irq interrupt.
+	 */
+	gpiod_set_value_cansleep(tp->wakeupfw, 1);
+
+	atomic_set(&tp->assert_cnt, 0);
+
+	enable_irq(tp->spi->irq);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_reset, VSC_TP);
+
+/**
+ * vsc_tp_need_read - check if device has data to sent
+ * @tp: vsc_tp device handle
+ * Return: true if device has data to sent, otherwise false
+ */
+bool vsc_tp_need_read(struct vsc_tp *tp)
+{
+	if (!atomic_read(&tp->assert_cnt))
+		return false;
+	if (!gpiod_get_value_cansleep(tp->wakeuphost))
+		return false;
+	if (!gpiod_get_value_cansleep(tp->wakeupfw))
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_need_read, VSC_TP);
+
+/**
+ * vsc_tp_register_event_cb - register a callback function to receive event
+ * @tp: vsc_tp device handle
+ * @event_cb: callback function
+ * @context: execution context of event callback
+ * Return: 0 in case of success, negative value in case of error
+ */
+int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb,
+			    void *context)
+{
+	tp->event_notify = event_cb;
+	tp->event_notify_context = context;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_register_event_cb, VSC_TP);
+
+/**
+ * vsc_tp_intr_synchronize - synchronize vsc_tp interrupt
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_intr_synchronize(struct vsc_tp *tp)
+{
+	synchronize_irq(tp->spi->irq);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_synchronize, VSC_TP);
+
+/**
+ * vsc_tp_intr_enable - enable vsc_tp interrupt
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_intr_enable(struct vsc_tp *tp)
+{
+	enable_irq(tp->spi->irq);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_enable, VSC_TP);
+
+/**
+ * vsc_tp_intr_disable - disable vsc_tp interrupt
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_intr_disable(struct vsc_tp *tp)
+{
+	disable_irq(tp->spi->irq);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_disable, VSC_TP);
+
+static irqreturn_t vsc_tp_isr(int irq, void *data)
+{
+	struct vsc_tp *tp = data;
+
+	atomic_inc(&tp->assert_cnt);
+
+	wake_up(&tp->xfer_wait);
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t vsc_tp_thread_isr(int irq, void *data)
+{
+	struct vsc_tp *tp = data;
+
+	if (tp->event_notify)
+		tp->event_notify(tp->event_notify_context);
+
+	return IRQ_HANDLED;
+}
+
+static int vsc_tp_match_any(struct acpi_device *adev, void *data)
+{
+	struct acpi_device **__adev = data;
+
+	*__adev = adev;
+
+	return 1;
+}
+
+static int vsc_tp_probe(struct spi_device *spi)
+{
+	struct platform_device_info pinfo = { 0 };
+	struct device *dev = &spi->dev;
+	struct platform_device *pdev;
+	struct acpi_device *adev;
+	struct vsc_tp *tp;
+	int ret;
+
+	tp = devm_kzalloc(dev, sizeof(*tp), GFP_KERNEL);
+	if (!tp)
+		return -ENOMEM;
+
+	tp->tx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	if (!tp->tx_buf)
+		return -ENOMEM;
+
+	tp->rx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	if (!tp->rx_buf)
+		return -ENOMEM;
+
+	ret = devm_acpi_dev_add_driver_gpios(dev, vsc_tp_acpi_gpios);
+	if (ret)
+		return ret;
+
+	tp->wakeuphost = devm_gpiod_get(dev, "wakeuphost", GPIOD_IN);
+	if (IS_ERR(tp->wakeuphost))
+		return PTR_ERR(tp->wakeuphost);
+
+	tp->resetfw = devm_gpiod_get(dev, "resetfw", GPIOD_OUT_HIGH);
+	if (IS_ERR(tp->resetfw))
+		return PTR_ERR(tp->resetfw);
+
+	tp->wakeupfw = devm_gpiod_get(dev, "wakeupfw", GPIOD_OUT_HIGH);
+	if (IS_ERR(tp->wakeupfw))
+		return PTR_ERR(tp->wakeupfw);
+
+	atomic_set(&tp->assert_cnt, 0);
+	init_waitqueue_head(&tp->xfer_wait);
+	tp->spi = spi;
+
+	irq_set_status_flags(spi->irq, IRQ_DISABLE_UNLAZY);
+	ret = devm_request_threaded_irq(dev, spi->irq, vsc_tp_isr,
+					vsc_tp_thread_isr,
+					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					dev_name(dev), tp);
+	if (ret)
+		return ret;
+
+	mutex_init(&tp->mutex);
+
+	/* only one child acpi device */
+	ret = acpi_dev_for_each_child(ACPI_COMPANION(dev),
+				      vsc_tp_match_any, &adev);
+	if (!ret) {
+		ret = -ENODEV;
+		goto err_destroy_lock;
+	}
+	pinfo.fwnode = acpi_fwnode_handle(adev);
+
+	pinfo.name = "intel_vsc";
+	pinfo.data = &tp;
+	pinfo.size_data = sizeof(tp);
+	pinfo.id = PLATFORM_DEVID_NONE;
+
+	pdev = platform_device_register_full(&pinfo);
+	if (IS_ERR(pdev)) {
+		ret = PTR_ERR(pdev);
+		goto err_destroy_lock;
+	}
+
+	tp->pdev = pdev;
+	spi_set_drvdata(spi, tp);
+
+	return 0;
+
+err_destroy_lock:
+	mutex_destroy(&tp->mutex);
+
+	return ret;
+}
+
+static void vsc_tp_remove(struct spi_device *spi)
+{
+	struct vsc_tp *tp = spi_get_drvdata(spi);
+
+	platform_device_unregister(tp->pdev);
+
+	mutex_destroy(&tp->mutex);
+}
+
+static const struct acpi_device_id vsc_tp_acpi_ids[] = {
+	{ "INTC1009" }, /* Raptor Lake */
+	{ "INTC1058" }, /* Tiger Lake */
+	{ "INTC1094" }, /* Alder Lake */
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, vsc_tp_acpi_ids);
+
+static struct spi_driver vsc_tp_driver = {
+	.probe = vsc_tp_probe,
+	.remove = vsc_tp_remove,
+	.driver = {
+		.name = "vsc-tp",
+		.acpi_match_table = vsc_tp_acpi_ids,
+	},
+};
+module_spi_driver(vsc_tp_driver);
+
+MODULE_AUTHOR("Wentong Wu <wentong.wu@intel.com>");
+MODULE_AUTHOR("Zhifeng Wang <zhifeng.wang@intel.com>");
+MODULE_DESCRIPTION("Intel Visual Sensing Controller Transport Layer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/misc/mei/vsc-tp.h b/drivers/misc/mei/vsc-tp.h
new file mode 100644
index 0000000000000..f9513ddc3e409
--- /dev/null
+++ b/drivers/misc/mei/vsc-tp.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023, Intel Corporation.
+ * Intel Visual Sensing Controller Transport Layer Linux driver
+ */
+
+#ifndef _VSC_TP_H_
+#define _VSC_TP_H_
+
+#include <linux/types.h>
+
+#define VSC_TP_CMD_WRITE	0x01
+#define VSC_TP_CMD_READ		0x02
+
+#define VSC_TP_CMD_ACK		0x10
+#define VSC_TP_CMD_NACK		0x11
+#define VSC_TP_CMD_BUSY		0x12
+
+struct vsc_tp;
+
+/**
+ * typedef vsc_event_cb_t - event callback function signature
+ * @context: the execution context of who registered this callback
+ *
+ * The callback function is called in interrupt context and the data
+ * payload is only valid during the call. If the user needs access
+ * the data payload later, it must copy the payload.
+ */
+typedef void (*vsc_tp_event_cb_t)(void *context);
+
+int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf,
+		    size_t len);
+
+int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen,
+		void *ibuf, size_t ilen);
+
+int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb,
+			     void *context);
+
+void vsc_tp_intr_enable(struct vsc_tp *tp);
+void vsc_tp_intr_disable(struct vsc_tp *tp);
+void vsc_tp_intr_synchronize(struct vsc_tp *tp);
+
+void vsc_tp_reset(struct vsc_tp *tp);
+
+bool vsc_tp_need_read(struct vsc_tp *tp);
+
+int vsc_tp_init(struct vsc_tp *tp, struct device *dev);
+
+#endif
-- 
GitLab


From 386a766c4169006d0e9df44823849930b8995e32 Mon Sep 17 00:00:00 2001
From: Wentong Wu <wentong.wu@intel.com>
Date: Mon, 4 Dec 2023 08:55:44 +0800
Subject: [PATCH 0875/4076] mei: Add MEI hardware support for IVSC device

The protocol used for the IVSC device to communicate with HOST is MEI.
The MEI hardware interfaces for the IVSC device are implemented.

The APIs are exposed by MEI framework to mei clients, e.g. mei_csi and
mei_ace.

Signed-off-by: Wentong Wu <wentong.wu@intel.com>
Reviewed-by: Alexander Usyskin <alexander.usyskin@intel.com>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Tested-by: Hao Yao <hao.yao@intel.com>
Acked-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/1701651344-20723-3-git-send-email-wentong.wu@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/Kconfig        |  13 +
 drivers/misc/mei/Makefile       |   3 +
 drivers/misc/mei/platform-vsc.c | 450 ++++++++++++++++++++++++++++++++
 3 files changed, 466 insertions(+)
 create mode 100644 drivers/misc/mei/platform-vsc.c

diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig
index 470957a694593..858bd701d68c3 100644
--- a/drivers/misc/mei/Kconfig
+++ b/drivers/misc/mei/Kconfig
@@ -71,6 +71,19 @@ config INTEL_MEI_VSC_HW
 	  This driver can also be built as a module. If so, the module
 	  will be called mei-vsc-hw.
 
+config INTEL_MEI_VSC
+	tristate "Intel visual sensing controller device with ME interface"
+	depends on INTEL_MEI_VSC_HW
+	depends on INTEL_MEI
+	help
+	  Intel MEI over SPI driver for Intel visual sensing controller
+	  (IVSC) device embedded in IA platform. It supports camera sharing
+	  between IVSC for context sensing and IPU for typical media usage.
+	  Select this config should enable transport layer for IVSC device.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called mei-vsc.
+
 source "drivers/misc/mei/hdcp/Kconfig"
 source "drivers/misc/mei/pxp/Kconfig"
 source "drivers/misc/mei/gsc_proxy/Kconfig"
diff --git a/drivers/misc/mei/Makefile b/drivers/misc/mei/Makefile
index 3d0da19a1501d..6f9fdbf1a4959 100644
--- a/drivers/misc/mei/Makefile
+++ b/drivers/misc/mei/Makefile
@@ -35,3 +35,6 @@ obj-$(CONFIG_INTEL_MEI_GSC_PROXY) += gsc_proxy/
 obj-$(CONFIG_INTEL_MEI_VSC_HW) += mei-vsc-hw.o
 mei-vsc-hw-y := vsc-tp.o
 mei-vsc-hw-y += vsc-fw-loader.o
+
+obj-$(CONFIG_INTEL_MEI_VSC) += mei-vsc.o
+mei-vsc-y := platform-vsc.o
diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c
new file mode 100644
index 0000000000000..8d303c6c00006
--- /dev/null
+++ b/drivers/misc/mei/platform-vsc.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, Intel Corporation.
+ * Intel Visual Sensing Controller Interface Linux driver
+ */
+
+#include <linux/align.h>
+#include <linux/cache.h>
+#include <linux/cleanup.h>
+#include <linux/iopoll.h>
+#include <linux/list.h>
+#include <linux/mei.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/overflow.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/timekeeping.h>
+#include <linux/types.h>
+
+#include <asm-generic/bug.h>
+#include <asm-generic/unaligned.h>
+
+#include "mei_dev.h"
+#include "vsc-tp.h"
+
+#define MEI_VSC_DRV_NAME		"intel_vsc"
+
+#define MEI_VSC_MAX_MSG_SIZE		512
+
+#define MEI_VSC_POLL_DELAY_US		(50 * USEC_PER_MSEC)
+#define MEI_VSC_POLL_TIMEOUT_US		(200 * USEC_PER_MSEC)
+
+#define mei_dev_to_vsc_hw(dev)		((struct mei_vsc_hw *)((dev)->hw))
+
+struct mei_vsc_host_timestamp {
+	u64 realtime;
+	u64 boottime;
+};
+
+struct mei_vsc_hw {
+	struct vsc_tp *tp;
+
+	bool fw_ready;
+	bool host_ready;
+
+	atomic_t write_lock_cnt;
+
+	u32 rx_len;
+	u32 rx_hdr;
+
+	/* buffer for tx */
+	char tx_buf[MEI_VSC_MAX_MSG_SIZE + sizeof(struct mei_msg_hdr)] ____cacheline_aligned;
+	/* buffer for rx */
+	char rx_buf[MEI_VSC_MAX_MSG_SIZE + sizeof(struct mei_msg_hdr)] ____cacheline_aligned;
+};
+
+static int mei_vsc_read_helper(struct mei_vsc_hw *hw, u8 *buf,
+			       u32 max_len)
+{
+	struct mei_vsc_host_timestamp ts = {
+		.realtime = ktime_to_ns(ktime_get_real()),
+		.boottime = ktime_to_ns(ktime_get_boottime()),
+	};
+
+	return vsc_tp_xfer(hw->tp, VSC_TP_CMD_READ, &ts, sizeof(ts),
+			   buf, max_len);
+}
+
+static int mei_vsc_write_helper(struct mei_vsc_hw *hw, u8 *buf, u32 len)
+{
+	u8 status;
+
+	return vsc_tp_xfer(hw->tp, VSC_TP_CMD_WRITE, buf, len, &status,
+			   sizeof(status));
+}
+
+static int mei_vsc_fw_status(struct mei_device *mei_dev,
+			     struct mei_fw_status *fw_status)
+{
+	if (!fw_status)
+		return -EINVAL;
+
+	fw_status->count = 0;
+
+	return 0;
+}
+
+static inline enum mei_pg_state mei_vsc_pg_state(struct mei_device *mei_dev)
+{
+	return MEI_PG_OFF;
+}
+
+static void mei_vsc_intr_enable(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	vsc_tp_intr_enable(hw->tp);
+}
+
+static void mei_vsc_intr_disable(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	vsc_tp_intr_disable(hw->tp);
+}
+
+/* mei framework requires this ops */
+static void mei_vsc_intr_clear(struct mei_device *mei_dev)
+{
+}
+
+/* wait for pending irq handler */
+static void mei_vsc_synchronize_irq(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	vsc_tp_intr_synchronize(hw->tp);
+}
+
+static int mei_vsc_hw_config(struct mei_device *mei_dev)
+{
+	return 0;
+}
+
+static bool mei_vsc_host_is_ready(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	return hw->host_ready;
+}
+
+static bool mei_vsc_hw_is_ready(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	return hw->fw_ready;
+}
+
+static int mei_vsc_hw_start(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	int ret, rlen;
+	u8 buf;
+
+	hw->host_ready = true;
+
+	vsc_tp_intr_enable(hw->tp);
+
+	ret = read_poll_timeout(mei_vsc_read_helper, rlen,
+				rlen >= 0, MEI_VSC_POLL_DELAY_US,
+				MEI_VSC_POLL_TIMEOUT_US, true,
+				hw, &buf, sizeof(buf));
+	if (ret) {
+		dev_err(mei_dev->dev, "wait fw ready failed: %d\n", ret);
+		return ret;
+	}
+
+	hw->fw_ready = true;
+
+	return 0;
+}
+
+static bool mei_vsc_hbuf_is_ready(struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	return atomic_read(&hw->write_lock_cnt) == 0;
+}
+
+static int mei_vsc_hbuf_empty_slots(struct mei_device *mei_dev)
+{
+	return MEI_VSC_MAX_MSG_SIZE / MEI_SLOT_SIZE;
+}
+
+static u32 mei_vsc_hbuf_depth(const struct mei_device *mei_dev)
+{
+	return MEI_VSC_MAX_MSG_SIZE / MEI_SLOT_SIZE;
+}
+
+static int mei_vsc_write(struct mei_device *mei_dev,
+			 const void *hdr, size_t hdr_len,
+			 const void *data, size_t data_len)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	char *buf = hw->tx_buf;
+	int ret;
+
+	if (WARN_ON(!hdr || !IS_ALIGNED(hdr_len, 4)))
+		return -EINVAL;
+
+	if (!data || data_len > MEI_VSC_MAX_MSG_SIZE)
+		return -EINVAL;
+
+	atomic_inc(&hw->write_lock_cnt);
+
+	memcpy(buf, hdr, hdr_len);
+	memcpy(buf + hdr_len, data, data_len);
+
+	ret = mei_vsc_write_helper(hw, buf, hdr_len + data_len);
+
+	atomic_dec_if_positive(&hw->write_lock_cnt);
+
+	return ret < 0 ? ret : 0;
+}
+
+static inline u32 mei_vsc_read(const struct mei_device *mei_dev)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	int ret;
+
+	ret = mei_vsc_read_helper(hw, hw->rx_buf, sizeof(hw->rx_buf));
+	if (ret < 0 || ret < sizeof(u32))
+		return 0;
+	hw->rx_len = ret;
+
+	hw->rx_hdr = get_unaligned_le32(hw->rx_buf);
+
+	return hw->rx_hdr;
+}
+
+static int mei_vsc_count_full_read_slots(struct mei_device *mei_dev)
+{
+	return MEI_VSC_MAX_MSG_SIZE / MEI_SLOT_SIZE;
+}
+
+static int mei_vsc_read_slots(struct mei_device *mei_dev, unsigned char *buf,
+			      unsigned long len)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	struct mei_msg_hdr *hdr;
+
+	hdr = (struct mei_msg_hdr *)&hw->rx_hdr;
+	if (len != hdr->length || hdr->length + sizeof(*hdr) != hw->rx_len)
+		return -EINVAL;
+
+	memcpy(buf, hw->rx_buf + sizeof(*hdr), len);
+
+	return 0;
+}
+
+static bool mei_vsc_pg_in_transition(struct mei_device *mei_dev)
+{
+	return mei_dev->pg_event >= MEI_PG_EVENT_WAIT &&
+	       mei_dev->pg_event <= MEI_PG_EVENT_INTR_WAIT;
+}
+
+static bool mei_vsc_pg_is_enabled(struct mei_device *mei_dev)
+{
+	return false;
+}
+
+static int mei_vsc_hw_reset(struct mei_device *mei_dev, bool intr_enable)
+{
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+
+	vsc_tp_reset(hw->tp);
+
+	vsc_tp_intr_disable(hw->tp);
+
+	return vsc_tp_init(hw->tp, mei_dev->dev);
+}
+
+static const struct mei_hw_ops mei_vsc_hw_ops = {
+	.fw_status = mei_vsc_fw_status,
+	.pg_state = mei_vsc_pg_state,
+
+	.host_is_ready = mei_vsc_host_is_ready,
+	.hw_is_ready = mei_vsc_hw_is_ready,
+	.hw_reset = mei_vsc_hw_reset,
+	.hw_config = mei_vsc_hw_config,
+	.hw_start = mei_vsc_hw_start,
+
+	.pg_in_transition = mei_vsc_pg_in_transition,
+	.pg_is_enabled = mei_vsc_pg_is_enabled,
+
+	.intr_clear = mei_vsc_intr_clear,
+	.intr_enable = mei_vsc_intr_enable,
+	.intr_disable = mei_vsc_intr_disable,
+	.synchronize_irq = mei_vsc_synchronize_irq,
+
+	.hbuf_free_slots = mei_vsc_hbuf_empty_slots,
+	.hbuf_is_ready = mei_vsc_hbuf_is_ready,
+	.hbuf_depth = mei_vsc_hbuf_depth,
+	.write = mei_vsc_write,
+
+	.rdbuf_full_slots = mei_vsc_count_full_read_slots,
+	.read_hdr = mei_vsc_read,
+	.read = mei_vsc_read_slots,
+};
+
+static void mei_vsc_event_cb(void *context)
+{
+	struct mei_device *mei_dev = context;
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
+	struct list_head cmpl_list;
+	s32 slots;
+	int ret;
+
+	if (mei_dev->dev_state == MEI_DEV_RESETTING ||
+	    mei_dev->dev_state == MEI_DEV_INITIALIZING)
+		return;
+
+	INIT_LIST_HEAD(&cmpl_list);
+
+	guard(mutex)(&mei_dev->device_lock);
+
+	while (vsc_tp_need_read(hw->tp)) {
+		/* check slots available for reading */
+		slots = mei_count_full_read_slots(mei_dev);
+
+		ret = mei_irq_read_handler(mei_dev, &cmpl_list, &slots);
+		if (ret) {
+			if (ret != -ENODATA) {
+				if (mei_dev->dev_state != MEI_DEV_RESETTING &&
+				    mei_dev->dev_state != MEI_DEV_POWER_DOWN)
+					schedule_work(&mei_dev->reset_work);
+			}
+
+			return;
+		}
+	}
+
+	mei_dev->hbuf_is_ready = mei_hbuf_is_ready(mei_dev);
+	ret = mei_irq_write_handler(mei_dev, &cmpl_list);
+	if (ret)
+		dev_err(mei_dev->dev, "dispatch write request failed: %d\n", ret);
+
+	mei_dev->hbuf_is_ready = mei_hbuf_is_ready(mei_dev);
+	mei_irq_compl_handler(mei_dev, &cmpl_list);
+}
+
+static int mei_vsc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mei_device *mei_dev;
+	struct mei_vsc_hw *hw;
+	struct vsc_tp *tp;
+	int ret;
+
+	tp = *(struct vsc_tp **)dev_get_platdata(dev);
+	if (!tp)
+		return dev_err_probe(dev, -ENODEV, "no platform data\n");
+
+	mei_dev = devm_kzalloc(dev, size_add(sizeof(*mei_dev), sizeof(*hw)),
+			       GFP_KERNEL);
+	if (!mei_dev)
+		return -ENOMEM;
+
+	mei_device_init(mei_dev, dev, false, &mei_vsc_hw_ops);
+	mei_dev->fw_f_fw_ver_supported = 0;
+	mei_dev->kind = "ivsc";
+
+	hw = mei_dev_to_vsc_hw(mei_dev);
+	atomic_set(&hw->write_lock_cnt, 0);
+	hw->tp = tp;
+
+	platform_set_drvdata(pdev, mei_dev);
+
+	vsc_tp_register_event_cb(tp, mei_vsc_event_cb, mei_dev);
+
+	ret = mei_start(mei_dev);
+	if (ret) {
+		dev_err_probe(dev, ret, "init hw failed\n");
+		goto err_cancel;
+	}
+
+	ret = mei_register(mei_dev, dev);
+	if (ret)
+		goto err_stop;
+
+	pm_runtime_enable(mei_dev->dev);
+
+	return 0;
+
+err_stop:
+	mei_stop(mei_dev);
+
+err_cancel:
+	mei_cancel_work(mei_dev);
+
+	mei_disable_interrupts(mei_dev);
+
+	return ret;
+}
+
+static int mei_vsc_remove(struct platform_device *pdev)
+{
+	struct mei_device *mei_dev = platform_get_drvdata(pdev);
+
+	pm_runtime_disable(mei_dev->dev);
+
+	mei_stop(mei_dev);
+
+	mei_disable_interrupts(mei_dev);
+
+	mei_deregister(mei_dev);
+
+	return 0;
+}
+
+static int mei_vsc_suspend(struct device *dev)
+{
+	struct mei_device *mei_dev = dev_get_drvdata(dev);
+
+	mei_stop(mei_dev);
+
+	return 0;
+}
+
+static int mei_vsc_resume(struct device *dev)
+{
+	struct mei_device *mei_dev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = mei_restart(mei_dev);
+	if (ret)
+		return ret;
+
+	/* start timer if stopped in suspend */
+	schedule_delayed_work(&mei_dev->timer_work, HZ);
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(mei_vsc_pm_ops, mei_vsc_suspend, mei_vsc_resume);
+
+static const struct platform_device_id mei_vsc_id_table[] = {
+	{ MEI_VSC_DRV_NAME },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, mei_vsc_id_table);
+
+static struct platform_driver mei_vsc_drv = {
+	.probe = mei_vsc_probe,
+	.remove = mei_vsc_remove,
+	.id_table = mei_vsc_id_table,
+	.driver = {
+		.name = MEI_VSC_DRV_NAME,
+		.pm = &mei_vsc_pm_ops,
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+	},
+};
+module_platform_driver(mei_vsc_drv);
+
+MODULE_AUTHOR("Wentong Wu <wentong.wu@intel.com>");
+MODULE_AUTHOR("Zhifeng Wang <zhifeng.wang@intel.com>");
+MODULE_DESCRIPTION("Intel Visual Sensing Controller Interface");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(VSC_TP);
-- 
GitLab


From 731b30f6aab7c45bb89372c3c05b711cee362b69 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 4 Dec 2023 17:56:32 +0200
Subject: [PATCH 0876/4076] pinctrl: renesas: Mark local variable with const in
 ->set_mux()

We are not going to change pins in the ->set_mux() callback. Mark
the local variable with a const qualifier. While at it, make it
also unsigned.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231204160033.1872569-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 2 +-
 drivers/pinctrl/renesas/pinctrl-rzv2m.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index aed59c53207c7..68fcc2a4efbc7 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -273,7 +273,7 @@ static int rzg2l_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 	struct function_desc *func;
 	unsigned int i, *psel_val;
 	struct group_desc *group;
-	int *pins;
+	const unsigned int *pins;
 
 	func = pinmux_generic_get_function(pctldev, func_selector);
 	if (!func)
diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
index 21d7d5ac8c4a7..eb304fab17968 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
@@ -165,7 +165,7 @@ static int rzv2m_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 	struct function_desc *func;
 	unsigned int i, *psel_val;
 	struct group_desc *group;
-	int *pins;
+	const unsigned int *pins;
 
 	func = pinmux_generic_get_function(pctldev, func_selector);
 	if (!func)
-- 
GitLab


From d98d73855f48e9f97f8f08d2376fb925ffc58c3f Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 4 Dec 2023 17:56:33 +0200
Subject: [PATCH 0877/4076] pinctrl: core: Make pins const unsigned int pointer
 in struct group_desc

It's unclear why it's not a const unsigned int pointer from day 1.
Make the pins member const unsigned int pointer in struct group_desc.
Update necessary APIs.

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231204160033.1872569-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c | 2 +-
 drivers/pinctrl/core.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 6d1e44efb5f39..d678effcedd88 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -640,7 +640,7 @@ static int pinctrl_generic_group_name_to_selector(struct pinctrl_dev *pctldev,
  * Note that the caller must take care of locking.
  */
 int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
-			      int *pins, int num_pins, void *data)
+			      const unsigned int *pins, int num_pins, void *data)
 {
 	struct group_desc *group;
 	int selector, error;
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 8b59dd72e4ffd..8ef4b536bca50 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -203,7 +203,7 @@ struct pinctrl_maps {
  */
 struct group_desc {
 	const char *name;
-	int *pins;
+	const unsigned int *pins;
 	int num_pins;
 	void *data;
 };
@@ -222,7 +222,7 @@ struct group_desc *pinctrl_generic_get_group(struct pinctrl_dev *pctldev,
 					     unsigned int group_selector);
 
 int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
-			      int *gpins, int ngpins, void *data);
+			      const unsigned int *pins, int num_pins, void *data);
 
 int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev,
 				 unsigned int group_selector);
-- 
GitLab


From be1d5f57366c3181b3df4b818caa2cd8a5c95490 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 4 Dec 2023 17:56:34 +0200
Subject: [PATCH 0878/4076] pinctrl: equilibrium: Convert to use struct
 pingroup

The pin control header provides struct pingroup.
Utilize it instead of open coded variants in the driver.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231204160033.1872569-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-equilibrium.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index fd59cfdeeface..4ebae516d1b1e 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -705,7 +705,7 @@ static int eqbr_build_groups(struct eqbr_pinctrl_drv_data *drvdata)
 	struct device *dev = drvdata->dev;
 	struct device_node *node = dev->of_node;
 	unsigned int *pins, *pinmux, pin_id, pinmux_id;
-	struct group_desc group;
+	struct pingroup group, *grp = &group;
 	struct device_node *np;
 	struct property *prop;
 	int j, err;
@@ -721,49 +721,49 @@ static int eqbr_build_groups(struct eqbr_pinctrl_drv_data *drvdata)
 			of_node_put(np);
 			return err;
 		}
-		group.num_pins = err;
-		group.name = prop->value;
-		pins = devm_kcalloc(dev, group.num_pins, sizeof(*pins), GFP_KERNEL);
+		grp->npins = err;
+		grp->name = prop->value;
+		pins = devm_kcalloc(dev, grp->npins, sizeof(*pins), GFP_KERNEL);
 		if (!pins) {
 			of_node_put(np);
 			return -ENOMEM;
 		}
-		group.pins = pins;
+		grp->pins = pins;
 
-		pinmux = devm_kcalloc(dev, group.num_pins, sizeof(*pinmux), GFP_KERNEL);
+		pinmux = devm_kcalloc(dev, grp->npins, sizeof(*pinmux), GFP_KERNEL);
 		if (!pinmux) {
 			of_node_put(np);
 			return -ENOMEM;
 		}
 
-		for (j = 0; j < group.num_pins; j++) {
+		for (j = 0; j < grp->npins; j++) {
 			if (of_property_read_u32_index(np, "pins", j, &pin_id)) {
 				dev_err(dev, "Group %s: Read intel pins id failed\n",
-					group.name);
+					grp->name);
 				of_node_put(np);
 				return -EINVAL;
 			}
 			if (pin_id >= drvdata->pctl_desc.npins) {
 				dev_err(dev, "Group %s: Invalid pin ID, idx: %d, pin %u\n",
-					group.name, j, pin_id);
+					grp->name, j, pin_id);
 				of_node_put(np);
 				return -EINVAL;
 			}
 			pins[j] = pin_id;
 			if (of_property_read_u32_index(np, "pinmux", j, &pinmux_id)) {
 				dev_err(dev, "Group %s: Read intel pinmux id failed\n",
-					group.name);
+					grp->name);
 				of_node_put(np);
 				return -EINVAL;
 			}
 			pinmux[j] = pinmux_id;
 		}
 
-		err = pinctrl_generic_add_group(drvdata->pctl_dev, group.name,
-						group.pins, group.num_pins,
+		err = pinctrl_generic_add_group(drvdata->pctl_dev,
+						grp->name, grp->pins, grp->npins,
 						pinmux);
 		if (err < 0) {
-			dev_err(dev, "Failed to register group %s\n", group.name);
+			dev_err(dev, "Failed to register group %s\n", grp->name);
 			of_node_put(np);
 			return err;
 		}
-- 
GitLab


From 3859a6fdf0edd54e05d0a35a2b418dbf85d43dc1 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 4 Dec 2023 17:56:35 +0200
Subject: [PATCH 0879/4076] pinctrl: keembay: Convert to use struct pingroup

The pin control header provides struct pingroup.
Utilize it instead of open coded variants in the driver.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231204160033.1872569-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-keembay.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-keembay.c b/drivers/pinctrl/pinctrl-keembay.c
index 152c35bce8ecc..87d328853ae47 100644
--- a/drivers/pinctrl/pinctrl-keembay.c
+++ b/drivers/pinctrl/pinctrl-keembay.c
@@ -1517,7 +1517,7 @@ static int keembay_gpiochip_probe(struct keembay_pinctrl *kpc,
 
 static int keembay_build_groups(struct keembay_pinctrl *kpc)
 {
-	struct group_desc *grp;
+	struct pingroup *grp;
 	unsigned int i;
 
 	kpc->ngroups = kpc->npins;
@@ -1528,7 +1528,7 @@ static int keembay_build_groups(struct keembay_pinctrl *kpc)
 	/* Each pin is categorised as one group */
 	for (i = 0; i < kpc->ngroups; i++) {
 		const struct pinctrl_pin_desc *pdesc = keembay_pins + i;
-		struct group_desc *kmb_grp = grp + i;
+		struct pingroup *kmb_grp = grp + i;
 
 		kmb_grp->name = pdesc->name;
 		kmb_grp->pins = (int *)&pdesc->number;
-- 
GitLab


From 583b5273a624e7d87b7038404cb1524450abdfbc Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 4 Dec 2023 17:56:36 +0200
Subject: [PATCH 0880/4076] pinctrl: nuvoton: Convert to use struct pingroup
 and PINCTRL_PINGROUP()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pin control header provides struct pingroup and PINCTRL_PINGROUP() macro.
Utilize them instead of open coded variants in the driver.

Reviewed-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231204160033.1872569-6-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/nuvoton/pinctrl-wpcm450.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/nuvoton/pinctrl-wpcm450.c b/drivers/pinctrl/nuvoton/pinctrl-wpcm450.c
index 0cff44b07b292..4589900244c79 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-wpcm450.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-wpcm450.c
@@ -474,9 +474,8 @@ enum {
 #undef WPCM450_GRP
 };
 
-static struct group_desc wpcm450_groups[] = {
-#define WPCM450_GRP(x) { .name = #x, .pins = x ## _pins, \
-			.num_pins = ARRAY_SIZE(x ## _pins) }
+static struct pingroup wpcm450_groups[] = {
+#define WPCM450_GRP(x) PINCTRL_PINGROUP(#x, x ## _pins, ARRAY_SIZE(x ## _pins))
 	WPCM450_GRPS
 #undef WPCM450_GRP
 };
@@ -852,7 +851,7 @@ static int wpcm450_get_group_pins(struct pinctrl_dev *pctldev,
 				  const unsigned int **pins,
 				  unsigned int *npins)
 {
-	*npins = wpcm450_groups[selector].num_pins;
+	*npins = wpcm450_groups[selector].npins;
 	*pins  = wpcm450_groups[selector].pins;
 
 	return 0;
@@ -901,7 +900,7 @@ static int wpcm450_pinmux_set_mux(struct pinctrl_dev *pctldev,
 	struct wpcm450_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
 
 	wpcm450_setfunc(pctrl->gcr_regmap, wpcm450_groups[group].pins,
-			wpcm450_groups[group].num_pins, function);
+			wpcm450_groups[group].npins, function);
 
 	return 0;
 }
-- 
GitLab


From 64d9799d6dd04601227f602ae961e3f3d2f1f02b Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 6 Dec 2023 09:45:25 -0800
Subject: [PATCH 0881/4076] backlight: ili922x: Drop kernel-doc for local
 macros

Don't use kernel-doc notation for the local macros START_BYTE() and
CHECK_FREQ_REG(). This prevents these kernel-doc warnings:

ili922x.c:85: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * START_BYTE(id, rs, rw)
ili922x.c:85: warning: missing initial short description on line:
 * START_BYTE(id, rs, rw)
ili922x.c:118: warning: expecting prototype for CHECK_FREQ_REG(spi_device s, spi_transfer x)(). Prototype was for CHECK_FREQ_REG() instead

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20231206174525.14960-1-rdunlap@infradead.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/ili922x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c
index e7b6bd827986f..206e77afc56f2 100644
--- a/drivers/video/backlight/ili922x.c
+++ b/drivers/video/backlight/ili922x.c
@@ -81,7 +81,7 @@
 #define START_RW_WRITE		0
 #define START_RW_READ		1
 
-/**
+/*
  * START_BYTE(id, rs, rw)
  *
  * Set the start byte according to the required operation.
@@ -100,7 +100,7 @@
 #define START_BYTE(id, rs, rw)	\
 	(0x70 | (((id) & 0x01) << 2) | (((rs) & 0x01) << 1) | ((rw) & 0x01))
 
-/**
+/*
  * CHECK_FREQ_REG(spi_device s, spi_transfer x) - Check the frequency
  *	for the SPI transfer. According to the datasheet, the controller
  *	accept higher frequency for the GRAM transfer, but it requires
-- 
GitLab


From 9c0a5b3f9e55cf9a3dc85843666cae28adfdf7e3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 4 Dec 2023 23:05:21 +0100
Subject: [PATCH 0882/4076] w1: gpio: Don't use platform data for driver data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

struct device's .platform_data isn't for drivers to write to. For
driver-specific data there is .driver_data instead.

As there is no in-tree platform that provides w1_gpio_platform_data,
drop the include file and replace it by a local struct w1_gpio_ddata.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/8f7ebe03ddaa5a5c6e2b36fecdf59da7fc373527.1701727212.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/masters/w1-gpio.c | 56 +++++++++++++++++-------------------
 include/linux/w1-gpio.h      | 22 --------------
 2 files changed, 27 insertions(+), 51 deletions(-)
 delete mode 100644 include/linux/w1-gpio.h

diff --git a/drivers/w1/masters/w1-gpio.c b/drivers/w1/masters/w1-gpio.c
index e45acb6d916ee..8d65db65178c9 100644
--- a/drivers/w1/masters/w1-gpio.c
+++ b/drivers/w1/masters/w1-gpio.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/w1-gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of_platform.h>
 #include <linux/err.h>
@@ -18,9 +17,16 @@
 
 #include <linux/w1.h>
 
+struct w1_gpio_ddata {
+	struct gpio_desc *gpiod;
+	struct gpio_desc *pullup_gpiod;
+	void (*enable_external_pullup)(int enable);
+	unsigned int pullup_duration;
+};
+
 static u8 w1_gpio_set_pullup(void *data, int delay)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *pdata = data;
 
 	if (delay) {
 		pdata->pullup_duration = delay;
@@ -46,14 +52,14 @@ static u8 w1_gpio_set_pullup(void *data, int delay)
 
 static void w1_gpio_write_bit(void *data, u8 bit)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *pdata = data;
 
 	gpiod_set_value(pdata->gpiod, bit);
 }
 
 static u8 w1_gpio_read_bit(void *data)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *pdata = data;
 
 	return gpiod_get_value(pdata->gpiod) ? 1 : 0;
 }
@@ -69,35 +75,25 @@ MODULE_DEVICE_TABLE(of, w1_gpio_dt_ids);
 static int w1_gpio_probe(struct platform_device *pdev)
 {
 	struct w1_bus_master *master;
-	struct w1_gpio_platform_data *pdata;
+	struct w1_gpio_ddata *pdata;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	/* Enforce open drain mode by default */
 	enum gpiod_flags gflags = GPIOD_OUT_LOW_OPEN_DRAIN;
 	int err;
 
-	if (of_have_populated_dt()) {
-		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata)
-			return -ENOMEM;
-
-		/*
-		 * This parameter means that something else than the gpiolib has
-		 * already set the line into open drain mode, so we should just
-		 * driver it high/low like we are in full control of the line and
-		 * open drain will happen transparently.
-		 */
-		if (of_property_present(np, "linux,open-drain"))
-			gflags = GPIOD_OUT_LOW;
-
-		pdev->dev.platform_data = pdata;
-	}
-	pdata = dev_get_platdata(dev);
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
 
-	if (!pdata) {
-		dev_err(dev, "No configuration data\n");
-		return -ENXIO;
-	}
+	/*
+	 * This parameter means that something else than the gpiolib has
+	 * already set the line into open drain mode, so we should just
+	 * driver it high/low like we are in full control of the line and
+	 * open drain will happen transparently.
+	 */
+	if (of_property_present(np, "linux,open-drain"))
+		gflags = GPIOD_OUT_LOW;
 
 	master = devm_kzalloc(dev, sizeof(struct w1_bus_master),
 			GFP_KERNEL);
@@ -152,7 +148,7 @@ static int w1_gpio_probe(struct platform_device *pdev)
 static int w1_gpio_remove(struct platform_device *pdev)
 {
 	struct w1_bus_master *master = platform_get_drvdata(pdev);
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct w1_gpio_ddata *pdata = master->data;
 
 	if (pdata->enable_external_pullup)
 		pdata->enable_external_pullup(0);
@@ -167,7 +163,8 @@ static int w1_gpio_remove(struct platform_device *pdev)
 
 static int __maybe_unused w1_gpio_suspend(struct device *dev)
 {
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(dev);
+	struct w1_bus_master *master = dev_get_drvdata(dev);
+	struct w1_gpio_ddata *pdata = master->data;
 
 	if (pdata->enable_external_pullup)
 		pdata->enable_external_pullup(0);
@@ -177,7 +174,8 @@ static int __maybe_unused w1_gpio_suspend(struct device *dev)
 
 static int __maybe_unused w1_gpio_resume(struct device *dev)
 {
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(dev);
+	struct w1_bus_master *master = dev_get_drvdata(dev);
+	struct w1_gpio_ddata *pdata = master->data;
 
 	if (pdata->enable_external_pullup)
 		pdata->enable_external_pullup(1);
diff --git a/include/linux/w1-gpio.h b/include/linux/w1-gpio.h
deleted file mode 100644
index 3495fd0dc7900..0000000000000
--- a/include/linux/w1-gpio.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * w1-gpio interface to platform code
- *
- * Copyright (C) 2007 Ville Syrjala <syrjala@sci.fi>
- */
-#ifndef _LINUX_W1_GPIO_H
-#define _LINUX_W1_GPIO_H
-
-struct gpio_desc;
-
-/**
- * struct w1_gpio_platform_data - Platform-dependent data for w1-gpio
- */
-struct w1_gpio_platform_data {
-	struct gpio_desc *gpiod;
-	struct gpio_desc *pullup_gpiod;
-	void (*enable_external_pullup)(int enable);
-	unsigned int pullup_duration;
-};
-
-#endif /* _LINUX_W1_GPIO_H */
-- 
GitLab


From deaba3d687b7cb1a2868bd514fd665ee5efcaaf3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 4 Dec 2023 23:05:22 +0100
Subject: [PATCH 0883/4076] w1: gpio: Drop unused enable_external_pullup from
 driver data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This member is always NULL, so drop it. That makes the suspend and
resume callbacks empty, so they can be dropped, too.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/7009fc53745c8e0336e9379022ce648a60c519f8.1701727212.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/masters/w1-gpio.c | 32 --------------------------------
 1 file changed, 32 deletions(-)

diff --git a/drivers/w1/masters/w1-gpio.c b/drivers/w1/masters/w1-gpio.c
index 8d65db65178c9..67596428f69b1 100644
--- a/drivers/w1/masters/w1-gpio.c
+++ b/drivers/w1/masters/w1-gpio.c
@@ -20,7 +20,6 @@
 struct w1_gpio_ddata {
 	struct gpio_desc *gpiod;
 	struct gpio_desc *pullup_gpiod;
-	void (*enable_external_pullup)(int enable);
 	unsigned int pullup_duration;
 };
 
@@ -134,9 +133,6 @@ static int w1_gpio_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	if (pdata->enable_external_pullup)
-		pdata->enable_external_pullup(1);
-
 	if (pdata->pullup_gpiod)
 		gpiod_set_value(pdata->pullup_gpiod, 1);
 
@@ -150,9 +146,6 @@ static int w1_gpio_remove(struct platform_device *pdev)
 	struct w1_bus_master *master = platform_get_drvdata(pdev);
 	struct w1_gpio_ddata *pdata = master->data;
 
-	if (pdata->enable_external_pullup)
-		pdata->enable_external_pullup(0);
-
 	if (pdata->pullup_gpiod)
 		gpiod_set_value(pdata->pullup_gpiod, 0);
 
@@ -161,34 +154,9 @@ static int w1_gpio_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int __maybe_unused w1_gpio_suspend(struct device *dev)
-{
-	struct w1_bus_master *master = dev_get_drvdata(dev);
-	struct w1_gpio_ddata *pdata = master->data;
-
-	if (pdata->enable_external_pullup)
-		pdata->enable_external_pullup(0);
-
-	return 0;
-}
-
-static int __maybe_unused w1_gpio_resume(struct device *dev)
-{
-	struct w1_bus_master *master = dev_get_drvdata(dev);
-	struct w1_gpio_ddata *pdata = master->data;
-
-	if (pdata->enable_external_pullup)
-		pdata->enable_external_pullup(1);
-
-	return 0;
-}
-
-static SIMPLE_DEV_PM_OPS(w1_gpio_pm_ops, w1_gpio_suspend, w1_gpio_resume);
-
 static struct platform_driver w1_gpio_driver = {
 	.driver = {
 		.name	= "w1-gpio",
-		.pm	= &w1_gpio_pm_ops,
 		.of_match_table = of_match_ptr(w1_gpio_dt_ids),
 	},
 	.probe = w1_gpio_probe,
-- 
GitLab


From 0ca9223fe9f75dce6e5cd306c685ee687a0bbdeb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 4 Dec 2023 23:05:23 +0100
Subject: [PATCH 0884/4076] w1: gpio: rename pointer to driver data from pdata
 to ddata
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pdata is a relict when this was still platform data.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/f863cacc485a701268164c9734b6d4aef23dae3e.1701727212.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/masters/w1-gpio.c | 54 ++++++++++++++++++------------------
 1 file changed, 27 insertions(+), 27 deletions(-)

diff --git a/drivers/w1/masters/w1-gpio.c b/drivers/w1/masters/w1-gpio.c
index 67596428f69b1..05c67038ed20c 100644
--- a/drivers/w1/masters/w1-gpio.c
+++ b/drivers/w1/masters/w1-gpio.c
@@ -25,25 +25,25 @@ struct w1_gpio_ddata {
 
 static u8 w1_gpio_set_pullup(void *data, int delay)
 {
-	struct w1_gpio_ddata *pdata = data;
+	struct w1_gpio_ddata *ddata = data;
 
 	if (delay) {
-		pdata->pullup_duration = delay;
+		ddata->pullup_duration = delay;
 	} else {
-		if (pdata->pullup_duration) {
+		if (ddata->pullup_duration) {
 			/*
 			 * This will OVERRIDE open drain emulation and force-pull
 			 * the line high for some time.
 			 */
-			gpiod_set_raw_value(pdata->gpiod, 1);
-			msleep(pdata->pullup_duration);
+			gpiod_set_raw_value(ddata->gpiod, 1);
+			msleep(ddata->pullup_duration);
 			/*
 			 * This will simply set the line as input since we are doing
 			 * open drain emulation in the GPIO library.
 			 */
-			gpiod_set_value(pdata->gpiod, 1);
+			gpiod_set_value(ddata->gpiod, 1);
 		}
-		pdata->pullup_duration = 0;
+		ddata->pullup_duration = 0;
 	}
 
 	return 0;
@@ -51,16 +51,16 @@ static u8 w1_gpio_set_pullup(void *data, int delay)
 
 static void w1_gpio_write_bit(void *data, u8 bit)
 {
-	struct w1_gpio_ddata *pdata = data;
+	struct w1_gpio_ddata *ddata = data;
 
-	gpiod_set_value(pdata->gpiod, bit);
+	gpiod_set_value(ddata->gpiod, bit);
 }
 
 static u8 w1_gpio_read_bit(void *data)
 {
-	struct w1_gpio_ddata *pdata = data;
+	struct w1_gpio_ddata *ddata = data;
 
-	return gpiod_get_value(pdata->gpiod) ? 1 : 0;
+	return gpiod_get_value(ddata->gpiod) ? 1 : 0;
 }
 
 #if defined(CONFIG_OF)
@@ -74,15 +74,15 @@ MODULE_DEVICE_TABLE(of, w1_gpio_dt_ids);
 static int w1_gpio_probe(struct platform_device *pdev)
 {
 	struct w1_bus_master *master;
-	struct w1_gpio_ddata *pdata;
+	struct w1_gpio_ddata *ddata;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	/* Enforce open drain mode by default */
 	enum gpiod_flags gflags = GPIOD_OUT_LOW_OPEN_DRAIN;
 	int err;
 
-	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata)
+	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
 		return -ENOMEM;
 
 	/*
@@ -99,23 +99,23 @@ static int w1_gpio_probe(struct platform_device *pdev)
 	if (!master)
 		return -ENOMEM;
 
-	pdata->gpiod = devm_gpiod_get_index(dev, NULL, 0, gflags);
-	if (IS_ERR(pdata->gpiod)) {
+	ddata->gpiod = devm_gpiod_get_index(dev, NULL, 0, gflags);
+	if (IS_ERR(ddata->gpiod)) {
 		dev_err(dev, "gpio_request (pin) failed\n");
-		return PTR_ERR(pdata->gpiod);
+		return PTR_ERR(ddata->gpiod);
 	}
 
-	pdata->pullup_gpiod =
+	ddata->pullup_gpiod =
 		devm_gpiod_get_index_optional(dev, NULL, 1, GPIOD_OUT_LOW);
-	if (IS_ERR(pdata->pullup_gpiod)) {
+	if (IS_ERR(ddata->pullup_gpiod)) {
 		dev_err(dev, "gpio_request_one "
 			"(ext_pullup_enable_pin) failed\n");
-		return PTR_ERR(pdata->pullup_gpiod);
+		return PTR_ERR(ddata->pullup_gpiod);
 	}
 
-	master->data = pdata;
+	master->data = ddata;
 	master->read_bit = w1_gpio_read_bit;
-	gpiod_direction_output(pdata->gpiod, 1);
+	gpiod_direction_output(ddata->gpiod, 1);
 	master->write_bit = w1_gpio_write_bit;
 
 	/*
@@ -133,8 +133,8 @@ static int w1_gpio_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	if (pdata->pullup_gpiod)
-		gpiod_set_value(pdata->pullup_gpiod, 1);
+	if (ddata->pullup_gpiod)
+		gpiod_set_value(ddata->pullup_gpiod, 1);
 
 	platform_set_drvdata(pdev, master);
 
@@ -144,10 +144,10 @@ static int w1_gpio_probe(struct platform_device *pdev)
 static int w1_gpio_remove(struct platform_device *pdev)
 {
 	struct w1_bus_master *master = platform_get_drvdata(pdev);
-	struct w1_gpio_ddata *pdata = master->data;
+	struct w1_gpio_ddata *ddata = master->data;
 
-	if (pdata->pullup_gpiod)
-		gpiod_set_value(pdata->pullup_gpiod, 0);
+	if (ddata->pullup_gpiod)
+		gpiod_set_value(ddata->pullup_gpiod, 0);
 
 	w1_remove_master_device(master);
 
-- 
GitLab


From a89c3d832784cdc900153e4e1db2a4a28fc4cf9a Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 25 Oct 2023 12:02:34 +0200
Subject: [PATCH 0885/4076] dt-bindings: mfd: ams,as3711: Convert to
 json-schema

Convert the Austria MicroSystems AS3711 Quad Buck High Current PMIC with
Charger Device Tree binding documentation to json-schema.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/56a5ebee588696f9022fa29fa8e266c8bdee6fd7.1698228043.git.geert+renesas@glider.be
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../devicetree/bindings/mfd/ams,as3711.yaml   | 223 ++++++++++++++++++
 .../devicetree/bindings/mfd/as3711.txt        |  73 ------
 2 files changed, 223 insertions(+), 73 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/mfd/ams,as3711.yaml
 delete mode 100644 Documentation/devicetree/bindings/mfd/as3711.txt

diff --git a/Documentation/devicetree/bindings/mfd/ams,as3711.yaml b/Documentation/devicetree/bindings/mfd/ams,as3711.yaml
new file mode 100644
index 0000000000000..ad8649cbb2cce
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/ams,as3711.yaml
@@ -0,0 +1,223 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/ams,as3711.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Austria MicroSystems AS3711 Quad Buck High Current PMIC with Charger
+
+maintainers:
+  - Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
+
+description:
+  AS3711 is an I2C PMIC from Austria MicroSystems with multiple DC/DC and LDO
+  power supplies, a battery charger and an RTC.  So far only bindings for the
+  two step-up DC/DC converters are defined.
+
+properties:
+  compatible:
+    const: ams,as3711
+
+  reg:
+    maxItems: 1
+
+  backlight:
+    description:
+      Step-up converter configuration, to be used as a backlight source
+    type: object
+    additionalProperties: false
+    properties:
+      compatible:
+        const: ams,as3711-bl
+
+      su1-dev:
+        description: Framebuffer phandle for the first step-up converter
+        $ref: /schemas/types.yaml#/definitions/phandle
+
+      su1-max-uA:
+        description: Maximum current for the first step-up converter
+        $ref: /schemas/types.yaml#/definitions/uint32
+
+      su2-dev:
+        description: Framebuffer phandle for the second step-up converter
+        $ref: /schemas/types.yaml#/definitions/phandle
+
+      su2-max-uA:
+        description: Maximum current for the second step-up converter
+        $ref: /schemas/types.yaml#/definitions/uint32
+
+      su2-feedback-voltage:
+        description: Second step-up converter uses voltage feedback
+        type: boolean
+
+      su2-feedback-curr1:
+        description:
+          Second step-up converter uses CURR1 input for current feedback
+        type: boolean
+
+      su2-feedback-curr2:
+        description:
+          Second step-up converter uses CURR2 input for current feedback
+        type: boolean
+
+      su2-feedback-curr3:
+        description:
+          Second step-up converter uses CURR3 input for current feedback
+        type: boolean
+
+      su2-feedback-curr-auto:
+        description:
+          Second step-up converter uses automatic current feedback selection
+        type: boolean
+
+      su2-fbprot-lx-sd4:
+        description:
+          Second step-up converter uses LX_SD4 for over-voltage protection
+        type: boolean
+
+      su2-fbprot-gpio2:
+        description:
+          Second step-up converter uses GPIO2 for over-voltage protection
+        type: boolean
+
+      su2-fbprot-gpio3:
+        description:
+          Second step-up converter uses GPIO3 for over-voltage protection
+        type: boolean
+
+      su2-fbprot-gpio4:
+        description:
+          Second step-up converter uses GPIO4 for over-voltage protection
+        type: boolean
+
+      su2-auto-curr1:
+        description:
+          Second step-up converter uses CURR1 input for automatic current
+          feedback
+        type: boolean
+
+      su2-auto-curr2:
+        description:
+          Second step-up converter uses CURR2 input for automatic current
+          feedback
+        type: boolean
+
+      su2-auto-curr3:
+        description:
+          Second step-up converter uses CURR3 input for automatic current
+          feedback
+        type: boolean
+
+    required:
+      - compatible
+
+    dependentRequired:
+      # To use the SU1 converter as a backlight source the following two
+      # properties must be provided:
+      su1-dev: [ su1-max-uA ]
+      su1-max-uA: [ su1-dev ]
+
+      # To use the SU2 converter as a backlight source the following two
+      # properties must be provided:
+      su2-dev: [ su2-max-uA ]
+      su2-max-uA: [ su2-dev ]
+
+      su2-feedback-voltage: [ su2-dev ]
+      su2-feedback-curr1: [ su2-dev ]
+      su2-feedback-curr2: [ su2-dev ]
+      su2-feedback-curr3: [ su2-dev ]
+      su2-feedback-curr-auto: [ su2-dev ]
+      su2-fbprot-lx-sd4: [ su2-dev ]
+      su2-fbprot-gpio2: [ su2-dev ]
+      su2-fbprot-gpio3: [ su2-dev ]
+      su2-fbprot-gpio4: [ su2-dev ]
+      su2-auto-curr1: [ su2-feedback-curr-auto ]
+      su2-auto-curr2: [ su2-feedback-curr-auto ]
+      su2-auto-curr3: [ su2-feedback-curr-auto ]
+
+    dependentSchemas:
+      su2-dev:
+        allOf:
+          - oneOf:
+              - required:
+                  - su2-feedback-voltage
+              - required:
+                  - su2-feedback-curr1
+              - required:
+                  - su2-feedback-curr2
+              - required:
+                  - su2-feedback-curr3
+              - required:
+                  - su2-feedback-curr-auto
+          - oneOf:
+              - required:
+                  - su2-fbprot-lx-sd4
+              - required:
+                  - su2-fbprot-gpio2
+              - required:
+                  - su2-fbprot-gpio3
+              - required:
+                  - su2-fbprot-gpio4
+
+      su2-feedback-curr-auto:
+        anyOf:
+          - required:
+              - su2-auto-curr1
+          - required:
+              - su2-auto-curr2
+          - required:
+              - su2-auto-curr3
+
+  regulators:
+    description: Other DC/DC and LDO supplies
+    type: object
+    unevaluatedProperties: false
+    patternProperties:
+      "^(sd[1-4]|ldo[1-8])$":
+        type: object
+        $ref: /schemas/regulator/regulator.yaml#
+        unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pmic@40 {
+            compatible = "ams,as3711";
+            reg = <0x40>;
+
+            regulators {
+                sd4 {
+                    regulator-name = "1.215V";
+                    regulator-min-microvolt = <1215000>;
+                    regulator-max-microvolt = <1235000>;
+                };
+                ldo2 {
+                    regulator-name = "2.8V CPU";
+                    regulator-min-microvolt = <2800000>;
+                    regulator-max-microvolt = <2800000>;
+                    regulator-always-on;
+                    regulator-boot-on;
+                };
+            };
+
+            backlight {
+                compatible = "ams,as3711-bl";
+                su2-dev = <&lcdc>;
+                su2-max-uA = <36000>;
+                su2-feedback-curr-auto;
+                su2-fbprot-gpio4;
+                su2-auto-curr1;
+                su2-auto-curr2;
+                su2-auto-curr3;
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/mfd/as3711.txt b/Documentation/devicetree/bindings/mfd/as3711.txt
deleted file mode 100644
index d98cf18c721ce..0000000000000
--- a/Documentation/devicetree/bindings/mfd/as3711.txt
+++ /dev/null
@@ -1,73 +0,0 @@
-AS3711 is an I2C PMIC from Austria MicroSystems with multiple DCDC and LDO power
-supplies, a battery charger and an RTC. So far only bindings for the two stepup
-DCDC converters are defined. Other DCDC and LDO supplies are configured, using
-standard regulator properties, they must belong to a sub-node, called
-"regulators" and be called "sd1" to "sd4" and "ldo1" to "ldo8." Stepup converter
-configuration should be placed in a subnode, called "backlight."
-
-Compulsory properties:
-- compatible		: must be "ams,as3711"
-- reg			: specifies the I2C address
-
-To use the SU1 converter as a backlight source the following two properties must
-be provided:
-- su1-dev		: framebuffer phandle
-- su1-max-uA		: maximum current
-
-To use the SU2 converter as a backlight source the following two properties must
-be provided:
-- su2-dev		: framebuffer phandle
-- su1-max-uA		: maximum current
-
-Additionally one of these properties must be provided to select the type of
-feedback used:
-- su2-feedback-voltage	: voltage feedback is used
-- su2-feedback-curr1	: CURR1 input used for current feedback
-- su2-feedback-curr2	: CURR2 input used for current feedback
-- su2-feedback-curr3	: CURR3 input used for current feedback
-- su2-feedback-curr-auto: automatic current feedback selection
-
-and one of these to select the over-voltage protection pin
-- su2-fbprot-lx-sd4	: LX_SD4 is used for over-voltage protection
-- su2-fbprot-gpio2	: GPIO2 is used for over-voltage protection
-- su2-fbprot-gpio3	: GPIO3 is used for over-voltage protection
-- su2-fbprot-gpio4	: GPIO4 is used for over-voltage protection
-
-If "su2-feedback-curr-auto" is selected, one or more of the following properties
-have to be specified:
-- su2-auto-curr1	: use CURR1 input for current feedback
-- su2-auto-curr2	: use CURR2 input for current feedback
-- su2-auto-curr3	: use CURR3 input for current feedback
-
-Example:
-
-as3711@40 {
-	compatible = "ams,as3711";
-	reg = <0x40>;
-
-	regulators {
-		sd4 {
-			regulator-name = "1.215V";
-			regulator-min-microvolt = <1215000>;
-			regulator-max-microvolt = <1235000>;
-		};
-		ldo2 {
-			regulator-name = "2.8V CPU";
-			regulator-min-microvolt = <2800000>;
-			regulator-max-microvolt = <2800000>;
-			regulator-always-on;
-			regulator-boot-on;
-		};
-	};
-
-	backlight {
-		compatible = "ams,as3711-bl";
-		su2-dev = <&lcdc>;
-		su2-max-uA = <36000>;
-		su2-feedback-curr-auto;
-		su2-fbprot-gpio4;
-		su2-auto-curr1;
-		su2-auto-curr2;
-		su2-auto-curr3;
-	};
-};
-- 
GitLab


From 33455f8da1cf4621fc881faf0190e3671a6dc8ff Mon Sep 17 00:00:00 2001
From: Mukesh Ojha <quic_mojha@quicinc.com>
Date: Wed, 25 Oct 2023 22:36:38 +0530
Subject: [PATCH 0886/4076] dt-bindings: mfd: qcom,tcsr: Add compatible for
 sm8250/sm8350

Document the compatible for both sm8250 and sm8350 SoCs.

Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/1698253601-11957-1-git-send-email-quic_mojha@quicinc.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml
index 33c3d023a1068..798705ab6a460 100644
--- a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml
+++ b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml
@@ -29,6 +29,8 @@ properties:
           - qcom,sdx65-tcsr
           - qcom,sm4450-tcsr
           - qcom,sm8150-tcsr
+          - qcom,sm8250-tcsr
+          - qcom,sm8350-tcsr
           - qcom,sm8450-tcsr
           - qcom,tcsr-apq8064
           - qcom,tcsr-apq8084
-- 
GitLab


From 895243c8763e9c81cace2d526d9770fa1ad035a2 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 1 Nov 2023 16:55:38 +0100
Subject: [PATCH 0887/4076] mfd: intel-lpss: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/a63f3da5745187f5a9b1e2ec0492f2fe2e0b0b8d.1698854117.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index 9591b354072ad..9115ba4c768f2 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -405,7 +405,7 @@ int intel_lpss_probe(struct device *dev,
 
 	intel_lpss_init_dev(lpss);
 
-	lpss->devid = ida_simple_get(&intel_lpss_devid_ida, 0, 0, GFP_KERNEL);
+	lpss->devid = ida_alloc(&intel_lpss_devid_ida, GFP_KERNEL);
 	if (lpss->devid < 0)
 		return lpss->devid;
 
@@ -442,7 +442,7 @@ err_remove_ltr:
 	intel_lpss_unregister_clock(lpss);
 
 err_clk_register:
-	ida_simple_remove(&intel_lpss_devid_ida, lpss->devid);
+	ida_free(&intel_lpss_devid_ida, lpss->devid);
 
 	return ret;
 }
@@ -456,7 +456,7 @@ void intel_lpss_remove(struct device *dev)
 	intel_lpss_debugfs_remove(lpss);
 	intel_lpss_ltr_hide(lpss);
 	intel_lpss_unregister_clock(lpss);
-	ida_simple_remove(&intel_lpss_devid_ida, lpss->devid);
+	ida_free(&intel_lpss_devid_ida, lpss->devid);
 }
 EXPORT_SYMBOL_GPL(intel_lpss_remove);
 
-- 
GitLab


From 6978c7d2dd81e0a3f9d30d1fbdb013a5ae5fabaf Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 6 Nov 2023 20:40:51 +0200
Subject: [PATCH 0888/4076] mfd: intel-lpss: Use PCI APIs instead of
 dereferencing

We have a few PCI APIs that may be used instead of direct dereferencing,
Using them will also provide better error codes.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231106184052.1166579-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss-pci.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index ae5759200622c..cf56cd3a40ee1 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -37,13 +37,17 @@ static int intel_lpss_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY);
+	if (ret)
+		return ret;
+
 	info = devm_kmemdup(&pdev->dev, (void *)id->driver_data, sizeof(*info),
 			    GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
-	info->mem = &pdev->resource[0];
-	info->irq = pdev->irq;
+	info->mem = pci_resource_n(pdev, 0);
+	info->irq = pci_irq_vector(pdev, 0);
 
 	if (pci_match_id(ignore_resource_conflicts_ids, pdev))
 		info->ignore_resource_conflicts = true;
-- 
GitLab


From 92827c1020706333f528e1ecd47145d9a426517e Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Mon, 6 Nov 2023 20:40:52 +0200
Subject: [PATCH 0889/4076] mfd: intel-lpss: Return error code received from
 the IRQ API

platform_get_irq() returns a negative error code to indicate an error.
As does pci_alloc_irq_vectors() and pci_irq_vector(). So in
intel_lpss_probe() the erroneous IRQ would be better returned as is.

The pci_alloc_irq_vectors() call and platform_get_irq() guarantee
that IRQs will not be 0, so we'll drop that check as well.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
[andy: updated commit message]
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231106184052.1166579-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index 9115ba4c768f2..bbd65da46db6f 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -378,9 +378,12 @@ int intel_lpss_probe(struct device *dev,
 	struct intel_lpss *lpss;
 	int ret;
 
-	if (!info || !info->mem || info->irq <= 0)
+	if (!info || !info->mem)
 		return -EINVAL;
 
+	if (info->irq < 0)
+		return info->irq;
+
 	lpss = devm_kzalloc(dev, sizeof(*lpss), GFP_KERNEL);
 	if (!lpss)
 		return -ENOMEM;
-- 
GitLab


From 4aedcd4aa61d536ca17e67ecd5bc5d42529164f4 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Thu, 16 Nov 2023 15:05:13 +0100
Subject: [PATCH 0890/4076] mfd: rk8xx: fixup devices registration with
 PLATFORM_DEVID_AUTO

Since commit 210f418f8ace ("mfd: rk8xx: Add rk806 support"), devices are
registered with "0" as id, causing devices to not have an automatic device id
and prevents having multiple RK8xx PMICs on the same system.

Properly pass PLATFORM_DEVID_AUTO to devm_mfd_add_devices() and since
it will ignore the cells .id with this special value, also cleanup
by removing all now ignored cells .id values.

Now we have the same behaviour as before rk806 introduction and rk806
retains the intended behavior.

This fixes a regression while booting the Odroid Go Ultra on v6.6.1:
sysfs: cannot create duplicate filename '/bus/platform/devices/rk808-clkout'
CPU: 3 PID: 97 Comm: kworker/u12:2 Not tainted 6.6.1 #1
Hardware name: Hardkernel ODROID-GO-Ultra (DT)
Workqueue: events_unbound deferred_probe_work_func
Call trace:
dump_backtrace+0x9c/0x11c
show_stack+0x18/0x24
dump_stack_lvl+0x78/0xc4
dump_stack+0x18/0x24
sysfs_warn_dup+0x64/0x80
sysfs_do_create_link_sd+0xf0/0xf8
sysfs_create_link+0x20/0x40
bus_add_device+0x114/0x160
device_add+0x3f0/0x7cc
platform_device_add+0x180/0x270
mfd_add_device+0x390/0x4a8
devm_mfd_add_devices+0xb0/0x150
rk8xx_probe+0x26c/0x410
rk8xx_i2c_probe+0x64/0x98
i2c_device_probe+0x104/0x2e8
really_probe+0x184/0x3c8
__driver_probe_device+0x7c/0x16c
driver_probe_device+0x3c/0x10c
__device_attach_driver+0xbc/0x158
bus_for_each_drv+0x80/0xdc
__device_attach+0x9c/0x1ac
device_initial_probe+0x14/0x20
bus_probe_device+0xac/0xb0
deferred_probe_work_func+0xa0/0xf4
process_one_work+0x1bc/0x378
worker_thread+0x1dc/0x3d4
kthread+0x104/0x118
ret_from_fork+0x10/0x20
rk8xx-i2c 0-001c: error -EEXIST: failed to add MFD devices
rk8xx-i2c: probe of 0-001c failed with error -17

Fixes: 210f418f8ace ("mfd: rk8xx: Add rk806 support")
Reported-by: Adam Green <greena88@gmail.com>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Link: https://lore.kernel.org/r/20231116-topic-amlogic-upstream-fix-rk8xx-devid-auto-v2-1-3f1bad68ab9d@linaro.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/rk8xx-core.c | 34 +++++++++++++---------------------
 1 file changed, 13 insertions(+), 21 deletions(-)

diff --git a/drivers/mfd/rk8xx-core.c b/drivers/mfd/rk8xx-core.c
index c47164a3ec1da..b1ffc3b9e2be7 100644
--- a/drivers/mfd/rk8xx-core.c
+++ b/drivers/mfd/rk8xx-core.c
@@ -53,76 +53,68 @@ static const struct resource rk817_charger_resources[] = {
 };
 
 static const struct mfd_cell rk805s[] = {
-	{ .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk805-pinctrl", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
+	{ .name = "rk805-pinctrl", },
 	{
 		.name = "rk808-rtc",
 		.num_resources = ARRAY_SIZE(rtc_resources),
 		.resources = &rtc_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
 	{	.name = "rk805-pwrkey",
 		.num_resources = ARRAY_SIZE(rk805_key_resources),
 		.resources = &rk805_key_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
 };
 
 static const struct mfd_cell rk806s[] = {
-	{ .name = "rk805-pinctrl", .id = PLATFORM_DEVID_AUTO, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_AUTO, },
+	{ .name = "rk805-pinctrl", },
+	{ .name = "rk808-regulator", },
 	{
 		.name = "rk805-pwrkey",
 		.resources = rk806_pwrkey_resources,
 		.num_resources = ARRAY_SIZE(rk806_pwrkey_resources),
-		.id = PLATFORM_DEVID_AUTO,
 	},
 };
 
 static const struct mfd_cell rk808s[] = {
-	{ .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
 	{
 		.name = "rk808-rtc",
 		.num_resources = ARRAY_SIZE(rtc_resources),
 		.resources = rtc_resources,
-		.id = PLATFORM_DEVID_NONE,
 	},
 };
 
 static const struct mfd_cell rk817s[] = {
-	{ .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
 	{
 		.name = "rk805-pwrkey",
 		.num_resources = ARRAY_SIZE(rk817_pwrkey_resources),
 		.resources = &rk817_pwrkey_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
 	{
 		.name = "rk808-rtc",
 		.num_resources = ARRAY_SIZE(rk817_rtc_resources),
 		.resources = &rk817_rtc_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
-	{ .name = "rk817-codec", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk817-codec", },
 	{
 		.name = "rk817-charger",
 		.num_resources = ARRAY_SIZE(rk817_charger_resources),
 		.resources = &rk817_charger_resources[0],
-		.id = PLATFORM_DEVID_NONE,
 	},
 };
 
 static const struct mfd_cell rk818s[] = {
-	{ .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, },
-	{ .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, },
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
 	{
 		.name = "rk808-rtc",
 		.num_resources = ARRAY_SIZE(rtc_resources),
 		.resources = rtc_resources,
-		.id = PLATFORM_DEVID_NONE,
 	},
 };
 
@@ -684,7 +676,7 @@ int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap
 					     pre_init_reg[i].addr);
 	}
 
-	ret = devm_mfd_add_devices(dev, 0, cells, nr_cells, NULL, 0,
+	ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, cells, nr_cells, NULL, 0,
 			      regmap_irq_get_domain(rk808->irq_data));
 	if (ret)
 		return dev_err_probe(dev, ret, "failed to add MFD devices\n");
-- 
GitLab


From 6d461d3c68fb994d56a41b7280aada742dc71cea Mon Sep 17 00:00:00 2001
From: Andre Werner <andre.werner@systec-electronic.com>
Date: Tue, 21 Nov 2023 07:32:59 +0100
Subject: [PATCH 0891/4076] mfd: tps65086: Enable register view in debugfs

Previously there was no output for the regmap's registers
in debugfs due to missing "max_register" property in regmap
configuration.

Signed-off-by: Andre Werner <andre.werner@systec-electronic.com>
Link: https://lore.kernel.org/r/20231121063259.13991-1-andre.werner@systec-electronic.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/tps65086.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mfd/tps65086.c b/drivers/mfd/tps65086.c
index 152179ee11ca8..fdce81b33f603 100644
--- a/drivers/mfd/tps65086.c
+++ b/drivers/mfd/tps65086.c
@@ -36,6 +36,7 @@ static const struct regmap_config tps65086_regmap_config = {
 	.val_bits = 8,
 	.cache_type = REGCACHE_MAPLE,
 	.volatile_table = &tps65086_volatile_table,
+	.max_register = TPS65086_OC_STATUS,
 };
 
 static const struct regmap_irq tps65086_irqs[] = {
-- 
GitLab


From fc2db185632d310d96f8d61f9f8cd4610bca790a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:29 +0100
Subject: [PATCH 0892/4076] mfd: ab8500-sysctrl: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/ab8500-sysctrl.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
index eeeb62415f538..ce81fcb785d03 100644
--- a/drivers/mfd/ab8500-sysctrl.c
+++ b/drivers/mfd/ab8500-sysctrl.c
@@ -140,14 +140,12 @@ static int ab8500_sysctrl_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ab8500_sysctrl_remove(struct platform_device *pdev)
+static void ab8500_sysctrl_remove(struct platform_device *pdev)
 {
 	sysctrl_dev = NULL;
 
 	if (pm_power_off == ab8500_power_off)
 		pm_power_off = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id ab8500_sysctrl_match[] = {
@@ -161,7 +159,7 @@ static struct platform_driver ab8500_sysctrl_driver = {
 		.of_match_table = ab8500_sysctrl_match,
 	},
 	.probe = ab8500_sysctrl_probe,
-	.remove = ab8500_sysctrl_remove,
+	.remove_new = ab8500_sysctrl_remove,
 };
 
 static int __init ab8500_sysctrl_init(void)
-- 
GitLab


From 13b254c02e9b109f1bc2990b6333d47412f6f955 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:30 +0100
Subject: [PATCH 0893/4076] mfd: cros_ec_dev: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/cros_ec_dev.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c
index 79d393b602bf3..603b1cd527850 100644
--- a/drivers/mfd/cros_ec_dev.c
+++ b/drivers/mfd/cros_ec_dev.c
@@ -288,13 +288,12 @@ failed:
 	return retval;
 }
 
-static int ec_device_remove(struct platform_device *pdev)
+static void ec_device_remove(struct platform_device *pdev)
 {
 	struct cros_ec_dev *ec = dev_get_drvdata(&pdev->dev);
 
 	mfd_remove_devices(ec->dev);
 	device_unregister(&ec->class_dev);
-	return 0;
 }
 
 static const struct platform_device_id cros_ec_id[] = {
@@ -309,7 +308,7 @@ static struct platform_driver cros_ec_dev_driver = {
 	},
 	.id_table = cros_ec_id,
 	.probe = ec_device_probe,
-	.remove = ec_device_remove,
+	.remove_new = ec_device_remove,
 };
 
 static int __init cros_ec_dev_init(void)
-- 
GitLab


From 3b257f28369be3509d2d9b66623a5cbce3f42fcb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:31 +0100
Subject: [PATCH 0894/4076] mfd: exynos-lpass: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-4-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/exynos-lpass.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/exynos-lpass.c b/drivers/mfd/exynos-lpass.c
index 1506d8d352b19..e58990c85ed87 100644
--- a/drivers/mfd/exynos-lpass.c
+++ b/drivers/mfd/exynos-lpass.c
@@ -137,7 +137,7 @@ static int exynos_lpass_probe(struct platform_device *pdev)
 	return devm_of_platform_populate(dev);
 }
 
-static int exynos_lpass_remove(struct platform_device *pdev)
+static void exynos_lpass_remove(struct platform_device *pdev)
 {
 	struct exynos_lpass *lpass = platform_get_drvdata(pdev);
 
@@ -146,8 +146,6 @@ static int exynos_lpass_remove(struct platform_device *pdev)
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		exynos_lpass_disable(lpass);
 	regmap_exit(lpass->top);
-
-	return 0;
 }
 
 static int __maybe_unused exynos_lpass_suspend(struct device *dev)
@@ -187,7 +185,7 @@ static struct platform_driver exynos_lpass_driver = {
 		.of_match_table	= exynos_lpass_of_match,
 	},
 	.probe	= exynos_lpass_probe,
-	.remove	= exynos_lpass_remove,
+	.remove_new = exynos_lpass_remove,
 };
 module_platform_driver(exynos_lpass_driver);
 
-- 
GitLab


From 7127bf6eed433dec79abc08bd98ce2c21a5e22c9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:32 +0100
Subject: [PATCH 0895/4076] mfd: fsl-imx25-tsadc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-5-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/fsl-imx25-tsadc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/fsl-imx25-tsadc.c b/drivers/mfd/fsl-imx25-tsadc.c
index 089c2ce615b6d..74f38bf3778f8 100644
--- a/drivers/mfd/fsl-imx25-tsadc.c
+++ b/drivers/mfd/fsl-imx25-tsadc.c
@@ -194,11 +194,9 @@ err_irq:
 	return ret;
 }
 
-static int mx25_tsadc_remove(struct platform_device *pdev)
+static void mx25_tsadc_remove(struct platform_device *pdev)
 {
 	mx25_tsadc_unset_irq(pdev);
-
-	return 0;
 }
 
 static const struct of_device_id mx25_tsadc_ids[] = {
@@ -213,7 +211,7 @@ static struct platform_driver mx25_tsadc_driver = {
 		.of_match_table = mx25_tsadc_ids,
 	},
 	.probe = mx25_tsadc_probe,
-	.remove = mx25_tsadc_remove,
+	.remove_new = mx25_tsadc_remove,
 };
 module_platform_driver(mx25_tsadc_driver);
 
-- 
GitLab


From 022457cfec84c5ec7a70b5cb9bef587dc7f21681 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:33 +0100
Subject: [PATCH 0896/4076] mfd: hi655x-pmic: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-6-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/hi655x-pmic.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mfd/hi655x-pmic.c b/drivers/mfd/hi655x-pmic.c
index 8feae8d8fd9d4..042109304db41 100644
--- a/drivers/mfd/hi655x-pmic.c
+++ b/drivers/mfd/hi655x-pmic.c
@@ -144,13 +144,12 @@ static int hi655x_pmic_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int hi655x_pmic_remove(struct platform_device *pdev)
+static void hi655x_pmic_remove(struct platform_device *pdev)
 {
 	struct hi655x_pmic *pmic = platform_get_drvdata(pdev);
 
 	regmap_del_irq_chip(gpiod_to_irq(pmic->gpio), pmic->irq_data);
 	mfd_remove_devices(&pdev->dev);
-	return 0;
 }
 
 static const struct of_device_id hi655x_pmic_match[] = {
@@ -165,7 +164,7 @@ static struct platform_driver hi655x_pmic_driver = {
 		.of_match_table = hi655x_pmic_match,
 	},
 	.probe  = hi655x_pmic_probe,
-	.remove = hi655x_pmic_remove,
+	.remove_new = hi655x_pmic_remove,
 };
 module_platform_driver(hi655x_pmic_driver);
 
-- 
GitLab


From dd28e01d39d56ba11bf0ccb08b9b73447ad51189 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:34 +0100
Subject: [PATCH 0897/4076] mfd: intel-lpss-acpi: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-7-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss-acpi.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/intel-lpss-acpi.c b/drivers/mfd/intel-lpss-acpi.c
index 212818aef93e2..5184fd1a5df13 100644
--- a/drivers/mfd/intel-lpss-acpi.c
+++ b/drivers/mfd/intel-lpss-acpi.c
@@ -198,19 +198,17 @@ static int intel_lpss_acpi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int intel_lpss_acpi_remove(struct platform_device *pdev)
+static void intel_lpss_acpi_remove(struct platform_device *pdev)
 {
 	intel_lpss_remove(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 static INTEL_LPSS_PM_OPS(intel_lpss_acpi_pm_ops);
 
 static struct platform_driver intel_lpss_acpi_driver = {
 	.probe = intel_lpss_acpi_probe,
-	.remove = intel_lpss_acpi_remove,
+	.remove_new = intel_lpss_acpi_remove,
 	.driver = {
 		.name = "intel-lpss",
 		.acpi_match_table = intel_lpss_acpi_ids,
-- 
GitLab


From 0c45dd86145067b35009345e2e69a6309a34b7f5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:35 +0100
Subject: [PATCH 0898/4076] mfd: kempld-core: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-8-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/kempld-core.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c
index 33c6cfe9fe42d..67af36a389136 100644
--- a/drivers/mfd/kempld-core.c
+++ b/drivers/mfd/kempld-core.c
@@ -535,7 +535,7 @@ static int kempld_probe(struct platform_device *pdev)
 	return kempld_detect_device(pld);
 }
 
-static int kempld_remove(struct platform_device *pdev)
+static void kempld_remove(struct platform_device *pdev)
 {
 	struct kempld_device_data *pld = platform_get_drvdata(pdev);
 	const struct kempld_platform_data *pdata = dev_get_platdata(pld->dev);
@@ -544,8 +544,6 @@ static int kempld_remove(struct platform_device *pdev)
 
 	mfd_remove_devices(&pdev->dev);
 	pdata->release_hardware_mutex(pld);
-
-	return 0;
 }
 
 #ifdef CONFIG_ACPI
@@ -563,7 +561,7 @@ static struct platform_driver kempld_driver = {
 		.acpi_match_table = ACPI_PTR(kempld_acpi_table),
 	},
 	.probe		= kempld_probe,
-	.remove		= kempld_remove,
+	.remove_new	= kempld_remove,
 };
 
 static const struct dmi_system_id kempld_dmi_table[] __initconst = {
-- 
GitLab


From a861a27a0e3ba6f347ccab2fab0f5c3b52ddfce0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:36 +0100
Subject: [PATCH 0899/4076] mfd: mcp-sa11x0: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-9-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/mcp-sa11x0.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/mcp-sa11x0.c b/drivers/mfd/mcp-sa11x0.c
index 1c9831b78cf9c..3883e472b739d 100644
--- a/drivers/mfd/mcp-sa11x0.c
+++ b/drivers/mfd/mcp-sa11x0.c
@@ -232,7 +232,7 @@ static int mcp_sa11x0_probe(struct platform_device *dev)
 	return ret;
 }
 
-static int mcp_sa11x0_remove(struct platform_device *dev)
+static void mcp_sa11x0_remove(struct platform_device *dev)
 {
 	struct mcp *mcp = platform_get_drvdata(dev);
 	struct mcp_sa11x0 *m = priv(mcp);
@@ -251,8 +251,6 @@ static int mcp_sa11x0_remove(struct platform_device *dev)
 	mcp_host_free(mcp);
 	release_mem_region(mem1->start, resource_size(mem1));
 	release_mem_region(mem0->start, resource_size(mem0));
-
-	return 0;
 }
 
 static int mcp_sa11x0_suspend(struct device *dev)
@@ -288,7 +286,7 @@ static const struct dev_pm_ops mcp_sa11x0_pm_ops = {
 
 static struct platform_driver mcp_sa11x0_driver = {
 	.probe		= mcp_sa11x0_probe,
-	.remove		= mcp_sa11x0_remove,
+	.remove_new	= mcp_sa11x0_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.pm	= pm_sleep_ptr(&mcp_sa11x0_pm_ops),
-- 
GitLab


From 795cf0ac2af2ffe3e4a39da3b8350aeed0e7a80d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:37 +0100
Subject: [PATCH 0900/4076] mfd: mxs-lradc: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-10-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/mxs-lradc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/mxs-lradc.c b/drivers/mfd/mxs-lradc.c
index ec1b356562b9a..73893890b50a0 100644
--- a/drivers/mfd/mxs-lradc.c
+++ b/drivers/mfd/mxs-lradc.c
@@ -230,13 +230,11 @@ err_clk:
 	return ret;
 }
 
-static int mxs_lradc_remove(struct platform_device *pdev)
+static void mxs_lradc_remove(struct platform_device *pdev)
 {
 	struct mxs_lradc *lradc = platform_get_drvdata(pdev);
 
 	clk_disable_unprepare(lradc->clk);
-
-	return 0;
 }
 
 static struct platform_driver mxs_lradc_driver = {
@@ -245,7 +243,7 @@ static struct platform_driver mxs_lradc_driver = {
 		.of_match_table = mxs_lradc_dt_ids,
 	},
 	.probe = mxs_lradc_probe,
-	.remove = mxs_lradc_remove,
+	.remove_new = mxs_lradc_remove,
 };
 module_platform_driver(mxs_lradc_driver);
 
-- 
GitLab


From 418d1e74f8597e0b2d5d0d6e1be8f1f47e68f0a4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:38 +0100
Subject: [PATCH 0901/4076] mfd: omap-usb-host: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-11-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/omap-usb-host.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 78f1bb55dbc0f..ebc62033db169 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -816,13 +816,12 @@ static int usbhs_omap_remove_child(struct device *dev, void *data)
  *
  * Reverses the effect of usbhs_omap_probe().
  */
-static int usbhs_omap_remove(struct platform_device *pdev)
+static void usbhs_omap_remove(struct platform_device *pdev)
 {
 	pm_runtime_disable(&pdev->dev);
 
 	/* remove children */
 	device_for_each_child(&pdev->dev, NULL, usbhs_omap_remove_child);
-	return 0;
 }
 
 static const struct dev_pm_ops usbhsomap_dev_pm_ops = {
@@ -845,7 +844,7 @@ static struct platform_driver usbhs_omap_driver = {
 		.of_match_table = usbhs_omap_dt_ids,
 	},
 	.probe		= usbhs_omap_probe,
-	.remove		= usbhs_omap_remove,
+	.remove_new	= usbhs_omap_remove,
 };
 
 MODULE_AUTHOR("Keshava Munegowda <keshava_mgowda@ti.com>");
-- 
GitLab


From 32c9cd0abc8a37fbcdacc4487c33bf08a0579488 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:39 +0100
Subject: [PATCH 0902/4076] mfd: omap-usb-tll: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-12-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/omap-usb-tll.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
index 906353735c782..b6303ddb013b0 100644
--- a/drivers/mfd/omap-usb-tll.c
+++ b/drivers/mfd/omap-usb-tll.c
@@ -270,7 +270,7 @@ static int usbtll_omap_probe(struct platform_device *pdev)
  *
  * Reverses the effect of usbtll_omap_probe().
  */
-static int usbtll_omap_remove(struct platform_device *pdev)
+static void usbtll_omap_remove(struct platform_device *pdev)
 {
 	struct usbtll_omap *tll = platform_get_drvdata(pdev);
 	int i;
@@ -287,7 +287,6 @@ static int usbtll_omap_remove(struct platform_device *pdev)
 	}
 
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static const struct of_device_id usbtll_omap_dt_ids[] = {
@@ -303,7 +302,7 @@ static struct platform_driver usbtll_omap_driver = {
 		.of_match_table = usbtll_omap_dt_ids,
 	},
 	.probe		= usbtll_omap_probe,
-	.remove		= usbtll_omap_remove,
+	.remove_new	= usbtll_omap_remove,
 };
 
 int omap_tll_init(struct usbhs_omap_platform_data *pdata)
-- 
GitLab


From e999021c53720d393d28f1be4aa844170566e1f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:40 +0100
Subject: [PATCH 0903/4076] mfd: pcf50633-adc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-13-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/pcf50633-adc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/pcf50633-adc.c b/drivers/mfd/pcf50633-adc.c
index 191b1bc6141c2..ab55906f91f98 100644
--- a/drivers/mfd/pcf50633-adc.c
+++ b/drivers/mfd/pcf50633-adc.c
@@ -218,7 +218,7 @@ static int pcf50633_adc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int pcf50633_adc_remove(struct platform_device *pdev)
+static void pcf50633_adc_remove(struct platform_device *pdev)
 {
 	struct pcf50633_adc *adc = platform_get_drvdata(pdev);
 	int i, head;
@@ -236,8 +236,6 @@ static int pcf50633_adc_remove(struct platform_device *pdev)
 		kfree(adc->queue[i]);
 
 	mutex_unlock(&adc->queue_mutex);
-
-	return 0;
 }
 
 static struct platform_driver pcf50633_adc_driver = {
@@ -245,7 +243,7 @@ static struct platform_driver pcf50633_adc_driver = {
 		.name = "pcf50633-adc",
 	},
 	.probe = pcf50633_adc_probe,
-	.remove = pcf50633_adc_remove,
+	.remove_new = pcf50633_adc_remove,
 };
 
 module_platform_driver(pcf50633_adc_driver);
-- 
GitLab


From 19ea1d3953017518d85db35b69b5aea9bc64d630 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:41 +0100
Subject: [PATCH 0904/4076] mfd: qcom-pm8xxx: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-14-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/qcom-pm8xxx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/qcom-pm8xxx.c b/drivers/mfd/qcom-pm8xxx.c
index 07c531bd1236e..8b6285f687da5 100644
--- a/drivers/mfd/qcom-pm8xxx.c
+++ b/drivers/mfd/qcom-pm8xxx.c
@@ -585,19 +585,17 @@ static int pm8xxx_remove_child(struct device *dev, void *unused)
 	return 0;
 }
 
-static int pm8xxx_remove(struct platform_device *pdev)
+static void pm8xxx_remove(struct platform_device *pdev)
 {
 	struct pm_irq_chip *chip = platform_get_drvdata(pdev);
 
 	device_for_each_child(&pdev->dev, NULL, pm8xxx_remove_child);
 	irq_domain_remove(chip->irqdomain);
-
-	return 0;
 }
 
 static struct platform_driver pm8xxx_driver = {
 	.probe		= pm8xxx_probe,
-	.remove		= pm8xxx_remove,
+	.remove_new	= pm8xxx_remove,
 	.driver		= {
 		.name	= "pm8xxx-core",
 		.of_match_table = pm8xxx_id_table,
-- 
GitLab


From c20fddf7acfb54d856c34208926701d32c25eb18 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:42 +0100
Subject: [PATCH 0905/4076] mfd: sm501: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-15-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/sm501.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index 28027982cf693..b3592982a83b5 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -1667,7 +1667,7 @@ static void sm501_pci_remove(struct pci_dev *dev)
 	pci_disable_device(dev);
 }
 
-static int sm501_plat_remove(struct platform_device *dev)
+static void sm501_plat_remove(struct platform_device *dev)
 {
 	struct sm501_devdata *sm = platform_get_drvdata(dev);
 
@@ -1675,8 +1675,6 @@ static int sm501_plat_remove(struct platform_device *dev)
 	iounmap(sm->regs);
 
 	release_mem_region(sm->io_res->start, 0x100);
-
-	return 0;
 }
 
 static const struct pci_device_id sm501_pci_tbl[] = {
@@ -1707,7 +1705,7 @@ static struct platform_driver sm501_plat_driver = {
 		.of_match_table = of_sm501_match_tbl,
 	},
 	.probe		= sm501_plat_probe,
-	.remove		= sm501_plat_remove,
+	.remove_new	= sm501_plat_remove,
 	.suspend	= pm_sleep_ptr(sm501_plat_suspend),
 	.resume		= pm_sleep_ptr(sm501_plat_resume),
 };
-- 
GitLab


From eea669cbcbf9b34755eed3abe842052e700c9908 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:43 +0100
Subject: [PATCH 0906/4076] mfd: stm32-timers: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-16-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/stm32-timers.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/stm32-timers.c b/drivers/mfd/stm32-timers.c
index a656a1c186a89..9fd13d88950c6 100644
--- a/drivers/mfd/stm32-timers.c
+++ b/drivers/mfd/stm32-timers.c
@@ -306,7 +306,7 @@ static int stm32_timers_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int stm32_timers_remove(struct platform_device *pdev)
+static void stm32_timers_remove(struct platform_device *pdev)
 {
 	struct stm32_timers *ddata = platform_get_drvdata(pdev);
 
@@ -316,8 +316,6 @@ static int stm32_timers_remove(struct platform_device *pdev)
 	 */
 	of_platform_depopulate(&pdev->dev);
 	stm32_timers_dma_remove(&pdev->dev, ddata);
-
-	return 0;
 }
 
 static const struct of_device_id stm32_timers_of_match[] = {
@@ -328,7 +326,7 @@ MODULE_DEVICE_TABLE(of, stm32_timers_of_match);
 
 static struct platform_driver stm32_timers_driver = {
 	.probe = stm32_timers_probe,
-	.remove = stm32_timers_remove,
+	.remove_new = stm32_timers_remove,
 	.driver	= {
 		.name = "stm32-timers",
 		.of_match_table = stm32_timers_of_match,
-- 
GitLab


From 740ad6d1b39301960a28a5d47f5d985407bec42a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:44 +0100
Subject: [PATCH 0907/4076] mfd: ti_am335x_tscadc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-17-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/ti_am335x_tscadc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index b88eb70c17b35..4bbd542d753e4 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -298,7 +298,7 @@ err_disable_clk:
 	return err;
 }
 
-static int ti_tscadc_remove(struct platform_device *pdev)
+static void ti_tscadc_remove(struct platform_device *pdev)
 {
 	struct ti_tscadc_dev *tscadc = platform_get_drvdata(pdev);
 
@@ -308,8 +308,6 @@ static int ti_tscadc_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 
 	mfd_remove_devices(tscadc->dev);
-
-	return 0;
 }
 
 static int __maybe_unused ti_tscadc_can_wakeup(struct device *dev, void *data)
@@ -381,7 +379,7 @@ static struct platform_driver ti_tscadc_driver = {
 		.of_match_table = ti_tscadc_dt_ids,
 	},
 	.probe	= ti_tscadc_probe,
-	.remove	= ti_tscadc_remove,
+	.remove_new = ti_tscadc_remove,
 
 };
 
-- 
GitLab


From 66d721ca1c40a12ab4c7dad8cc9ad0f76310d1f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:45 +0100
Subject: [PATCH 0908/4076] mfd: tps65911-comparator: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-18-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/tps65911-comparator.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/tps65911-comparator.c b/drivers/mfd/tps65911-comparator.c
index 8f4210075913c..f206a9c50e9d8 100644
--- a/drivers/mfd/tps65911-comparator.c
+++ b/drivers/mfd/tps65911-comparator.c
@@ -140,15 +140,13 @@ static int tps65911_comparator_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int tps65911_comparator_remove(struct platform_device *pdev)
+static void tps65911_comparator_remove(struct platform_device *pdev)
 {
 	struct tps65910 *tps65910;
 
 	tps65910 = dev_get_drvdata(pdev->dev.parent);
 	device_remove_file(&pdev->dev, &dev_attr_comp2_threshold);
 	device_remove_file(&pdev->dev, &dev_attr_comp1_threshold);
-
-	return 0;
 }
 
 static struct platform_driver tps65911_comparator_driver = {
@@ -156,7 +154,7 @@ static struct platform_driver tps65911_comparator_driver = {
 		.name = "tps65911-comparator",
 	},
 	.probe = tps65911_comparator_probe,
-	.remove = tps65911_comparator_remove,
+	.remove_new = tps65911_comparator_remove,
 };
 
 static int __init tps65911_comparator_init(void)
-- 
GitLab


From e0191f305fb18264fe1178fd4103f0efa2ce4772 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 17:56:46 +0100
Subject: [PATCH 0909/4076] mfd: twl4030-audio: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231123165627.492259-19-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/twl4030-audio.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c
index 88002f8941e5e..d436ddf661dab 100644
--- a/drivers/mfd/twl4030-audio.c
+++ b/drivers/mfd/twl4030-audio.c
@@ -258,12 +258,10 @@ static int twl4030_audio_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int twl4030_audio_remove(struct platform_device *pdev)
+static void twl4030_audio_remove(struct platform_device *pdev)
 {
 	mfd_remove_devices(&pdev->dev);
 	twl4030_audio_dev = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id twl4030_audio_of_match[] = {
@@ -278,7 +276,7 @@ static struct platform_driver twl4030_audio_driver = {
 		.of_match_table = twl4030_audio_of_match,
 	},
 	.probe		= twl4030_audio_probe,
-	.remove		= twl4030_audio_remove,
+	.remove_new	= twl4030_audio_remove,
 };
 
 module_platform_driver(twl4030_audio_driver);
-- 
GitLab


From 4773d2f1a5c73c590c0c83bf42b156532bc69cb2 Mon Sep 17 00:00:00 2001
From: Dang Huynh <danct12@riseup.net>
Date: Tue, 21 Nov 2023 12:34:59 +0700
Subject: [PATCH 0910/4076] mfd: qcom-spmi-pmic: Add support for PM8937

Add the subtype and compatible strings for PM8937.

The PM8937 is found in various SoCs, including MSM8917, MSM8937,
MSM8940 and APQ variants.

Reviewed-by: Caleb Connolly <caleb.connolly@linaro.org>
Signed-off-by: Dang Huynh <danct12@riseup.net>
Link: https://lore.kernel.org/r/20231121-pm8937-v2-1-b0171ab62075@riseup.net
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/qcom-spmi-pmic.c      | 1 +
 include/soc/qcom/qcom-spmi-pmic.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/mfd/qcom-spmi-pmic.c b/drivers/mfd/qcom-spmi-pmic.c
index 4549fa9f7d4bc..eab5bf6cff105 100644
--- a/drivers/mfd/qcom-spmi-pmic.c
+++ b/drivers/mfd/qcom-spmi-pmic.c
@@ -53,6 +53,7 @@ static const struct of_device_id pmic_spmi_id_table[] = {
 	{ .compatible = "qcom,pm8901", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8909", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8916", .data = N_USIDS(2) },
+	{ .compatible = "qcom,pm8937", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8941", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8950", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8994", .data = N_USIDS(2) },
diff --git a/include/soc/qcom/qcom-spmi-pmic.h b/include/soc/qcom/qcom-spmi-pmic.h
index c47cc71a999ec..17a0a8c3d6560 100644
--- a/include/soc/qcom/qcom-spmi-pmic.h
+++ b/include/soc/qcom/qcom-spmi-pmic.h
@@ -31,6 +31,7 @@
 #define PM8998_SUBTYPE		0x14
 #define PMI8998_SUBTYPE		0x15
 #define PM8005_SUBTYPE		0x18
+#define PM8937_SUBTYPE		0x19
 #define PM660L_SUBTYPE		0x1a
 #define PM660_SUBTYPE		0x1b
 #define PM8150_SUBTYPE		0x1e
-- 
GitLab


From 2f7cae55831d6b1b57edadf27979efc97644844c Mon Sep 17 00:00:00 2001
From: Dang Huynh <danct12@riseup.net>
Date: Tue, 21 Nov 2023 12:35:00 +0700
Subject: [PATCH 0911/4076] dt-bindings: mfd: qcom-spmi-pmic: Document PM8937
 PMIC

Add bindings for PM8937 PMIC (qcom,pm8937). This PMIC is found in
boards with MSM8917, MSM8937, MSM8940 and APQ variants.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Dang Huynh <danct12@riseup.net>
Link: https://lore.kernel.org/r/20231121-pm8937-v2-2-b0171ab62075@riseup.net
Signed-off-by: Lee Jones <lee@kernel.org>
---
 Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
index 9fa5686039306..8f728920df9e2 100644
--- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
@@ -66,6 +66,7 @@ properties:
           - qcom,pm8841
           - qcom,pm8909
           - qcom,pm8916
+          - qcom,pm8937
           - qcom,pm8941
           - qcom,pm8950
           - qcom,pm8953
-- 
GitLab


From 7ac5241eaec4c25dd5a78734ae3c33cb25c8bf97 Mon Sep 17 00:00:00 2001
From: Nikita Travkin <nikita@trvn.ru>
Date: Mon, 20 Nov 2023 19:03:03 +0500
Subject: [PATCH 0912/4076] dt-bindings: mfd: qcom,spmi-pmic: Add pm8916 vm-bms
 and lbc

PM8916 (and probably some other similar pmics) have hardware blocks for
battery monitoring and charging. Add patterns for respecive nodes so the
devicetree for those blocks can be validated properly.

Signed-off-by: Nikita Travkin <nikita@trvn.ru>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231120-pm8916-dtsi-bms-lbc-v4-1-4f91056c8252@trvn.ru
Signed-off-by: Lee Jones <lee@kernel.org>
---
 Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
index 8f728920df9e2..8103fb61a16cc 100644
--- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml
@@ -135,9 +135,15 @@ patternProperties:
     type: object
     $ref: /schemas/sound/qcom,pm8916-wcd-analog-codec.yaml#
 
+  "^battery@[0-9a-f]+$":
+    type: object
+    oneOf:
+      - $ref: /schemas/power/supply/qcom,pm8916-bms-vm.yaml#
+
   "^charger@[0-9a-f]+$":
     type: object
     oneOf:
+      - $ref: /schemas/power/supply/qcom,pm8916-lbc.yaml#
       - $ref: /schemas/power/supply/qcom,pm8941-charger.yaml#
       - $ref: /schemas/power/supply/qcom,pm8941-coincell.yaml#
       - $ref: /schemas/power/supply/qcom,pmi8998-charger.yaml#
-- 
GitLab


From d19e5510c84db2cfb60aa187b1cb1a25cb23df52 Mon Sep 17 00:00:00 2001
From: Santhosh Kumar K <s-k6@ti.com>
Date: Fri, 24 Nov 2023 10:20:19 +0530
Subject: [PATCH 0913/4076] dt-bindings: mfd: ti,am3359-tscadc: Allow dmas
 property to be optional

ADC module can function without DMA, so there may not be dma channel
always associated with device. Hence, remove "dmas", "dma-names" from list
of required properties.

Signed-off-by: Santhosh Kumar K <s-k6@ti.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231124045019.21003-1-s-k6@ti.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml | 2 --
 1 file changed, 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml b/Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml
index 23a63265be3c8..70b5dfce07d29 100644
--- a/Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml
+++ b/Documentation/devicetree/bindings/mfd/ti,am3359-tscadc.yaml
@@ -61,8 +61,6 @@ required:
   - interrupts
   - clocks
   - clock-names
-  - dmas
-  - dma-names
 
 additionalProperties: false
 
-- 
GitLab


From 3b6dba220e67eda42f1263403fbbba64992da3ae Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 24 Nov 2023 21:31:24 +0200
Subject: [PATCH 0914/4076] mfd: intel-lpss: Revert "Add missing check for
 platform_get_resource"

This reverts commit d918e0d5824495a75d00b879118b098fcab36fdb.

The commit in question does not fix anything and only introduces
a duplication in the code. The main intel_lpss_probe() performs
all necessary checks.

While at it and in order of avoiding similar patches to come, add
a comment.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231124200258.3682979-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss-acpi.c | 4 +---
 drivers/mfd/intel-lpss-pci.c  | 1 +
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mfd/intel-lpss-acpi.c b/drivers/mfd/intel-lpss-acpi.c
index 5184fd1a5df13..52ffc0d9c23f1 100644
--- a/drivers/mfd/intel-lpss-acpi.c
+++ b/drivers/mfd/intel-lpss-acpi.c
@@ -182,10 +182,8 @@ static int intel_lpss_acpi_probe(struct platform_device *pdev)
 	if (!info)
 		return -ENOMEM;
 
+	/* No need to check mem and irq here as intel_lpss_probe() does it for us */
 	info->mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!info->mem)
-		return -ENODEV;
-
 	info->irq = platform_get_irq(pdev, 0);
 
 	ret = intel_lpss_probe(&pdev->dev, info);
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index cf56cd3a40ee1..709b0fb4419de 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -46,6 +46,7 @@ static int intel_lpss_pci_probe(struct pci_dev *pdev,
 	if (!info)
 		return -ENOMEM;
 
+	/* No need to check mem and irq here as intel_lpss_probe() does it for us */
 	info->mem = pci_resource_n(pdev, 0);
 	info->irq = pci_irq_vector(pdev, 0);
 
-- 
GitLab


From 9ffe4c1089f6c3097cb9184a36e912e2eeb66f4b Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 24 Nov 2023 21:31:25 +0200
Subject: [PATCH 0915/4076] mfd: intel-lpss: Use device_get_match_data()

Use preferred device_get_match_data() instead of acpi_match_device() to
get the driver match data. With this, adjust the includes to explicitly
include the correct headers.

Introduce a temporary variable in PCI glue driver to be consistent with
ACPI one on the same matter.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231124200258.3682979-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss-acpi.c | 11 +++++------
 drivers/mfd/intel-lpss-pci.c  |  4 ++--
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/mfd/intel-lpss-acpi.c b/drivers/mfd/intel-lpss-acpi.c
index 52ffc0d9c23f1..bba208235754e 100644
--- a/drivers/mfd/intel-lpss-acpi.c
+++ b/drivers/mfd/intel-lpss-acpi.c
@@ -8,9 +8,9 @@
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
  */
 
-#include <linux/acpi.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/platform_device.h>
@@ -169,16 +169,15 @@ MODULE_DEVICE_TABLE(acpi, intel_lpss_acpi_ids);
 
 static int intel_lpss_acpi_probe(struct platform_device *pdev)
 {
+	const struct intel_lpss_platform_info *data;
 	struct intel_lpss_platform_info *info;
-	const struct acpi_device_id *id;
 	int ret;
 
-	id = acpi_match_device(intel_lpss_acpi_ids, &pdev->dev);
-	if (!id)
+	data = device_get_match_data(&pdev->dev);
+	if (!data)
 		return -ENODEV;
 
-	info = devm_kmemdup(&pdev->dev, (void *)id->driver_data, sizeof(*info),
-			    GFP_KERNEL);
+	info = devm_kmemdup(&pdev->dev, data, sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index 709b0fb4419de..94042bfe7dbfb 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -30,6 +30,7 @@ static const struct pci_device_id ignore_resource_conflicts_ids[] = {
 static int intel_lpss_pci_probe(struct pci_dev *pdev,
 				const struct pci_device_id *id)
 {
+	const struct intel_lpss_platform_info *data = (void *)id->driver_data;
 	struct intel_lpss_platform_info *info;
 	int ret;
 
@@ -41,8 +42,7 @@ static int intel_lpss_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
-	info = devm_kmemdup(&pdev->dev, (void *)id->driver_data, sizeof(*info),
-			    GFP_KERNEL);
+	info = devm_kmemdup(&pdev->dev, data, sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
-- 
GitLab


From a936a91718fabe9e1c8e2da4265f5088f8e300de Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 24 Nov 2023 21:31:26 +0200
Subject: [PATCH 0916/4076] mfd: intel-lpss: Adjust header inclusions

Adjust header inclusions to avoid "proxy" headers and explicitly
include what we are using.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231124200258.3682979-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss-acpi.c |  6 +++++-
 drivers/mfd/intel-lpss-pci.c  |  8 ++++++--
 drivers/mfd/intel-lpss.c      | 17 ++++++++++++-----
 3 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/drivers/mfd/intel-lpss-acpi.c b/drivers/mfd/intel-lpss-acpi.c
index bba208235754e..e4a62cc02cfce 100644
--- a/drivers/mfd/intel-lpss-acpi.c
+++ b/drivers/mfd/intel-lpss-acpi.c
@@ -8,15 +8,19 @@
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
  */
 
+#include <linux/device.h>
+#include <linux/gfp_types.h>
 #include <linux/ioport.h>
-#include <linux/kernel.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
+
 #include <linux/pxa2xx_ssp.h>
 
+#include <asm/errno.h>
+
 #include "intel-lpss.h"
 
 static const struct property_entry spt_spi_properties[] = {
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index 94042bfe7dbfb..bc15379afe3b0 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -8,14 +8,18 @@
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
  */
 
-#include <linux/ioport.h>
-#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/gfp_types.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
+
 #include <linux/pxa2xx_ssp.h>
 
+#include <asm/errno.h>
+
 #include "intel-lpss.h"
 
 /* Some DSDTs have an unused GEXP ACPI device conflicting with I2C4 resources */
diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index bbd65da46db6f..79ea5e2ad0a6b 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -10,26 +10,33 @@
  *          Jarkko Nikula <jarkko.nikula@linux.intel.com>
  */
 
-#include <linux/clk.h>
+#include <linux/array_size.h>
+#include <linux/bits.h>
 #include <linux/clkdev.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gfp_types.h>
 #include <linux/idr.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/mfd/core.h>
+#include <linux/module.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
-#include <linux/property.h>
-#include <linux/seq_file.h>
+#include <linux/sprintf.h>
+#include <linux/types.h>
+
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include <linux/dma/idma64.h>
 
 #include "intel-lpss.h"
 
+struct dentry;
+
 #define LPSS_DEV_OFFSET		0x000
 #define LPSS_DEV_SIZE		0x200
 #define LPSS_PRIV_OFFSET	0x200
-- 
GitLab


From 24ee97a9e816a333688141eed2fbbb2d5e60b5d1 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 24 Nov 2023 21:31:27 +0200
Subject: [PATCH 0917/4076] mfd: intel-lpss: Move exported symbols to
 INTEL_LPSS namespace

Avoid unnecessary pollution of the global symbol namespace by
moving library functions in to a specific namespace and import
that into the drivers that make use of the functions.

For more info: https://lwn.net/Articles/760045/

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231124200258.3682979-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss-acpi.c |  1 +
 drivers/mfd/intel-lpss-pci.c  |  1 +
 drivers/mfd/intel-lpss.c      | 10 +++++-----
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/mfd/intel-lpss-acpi.c b/drivers/mfd/intel-lpss-acpi.c
index e4a62cc02cfce..a9e2d9308a01c 100644
--- a/drivers/mfd/intel-lpss-acpi.c
+++ b/drivers/mfd/intel-lpss-acpi.c
@@ -223,3 +223,4 @@ MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
 MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
 MODULE_DESCRIPTION("Intel LPSS ACPI driver");
 MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(INTEL_LPSS);
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index bc15379afe3b0..e1d89423daa6a 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -603,3 +603,4 @@ MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
 MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
 MODULE_DESCRIPTION("Intel LPSS PCI driver");
 MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(INTEL_LPSS);
diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index 79ea5e2ad0a6b..4a63703b6da56 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -456,7 +456,7 @@ err_clk_register:
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(intel_lpss_probe);
+EXPORT_SYMBOL_NS_GPL(intel_lpss_probe, INTEL_LPSS);
 
 void intel_lpss_remove(struct device *dev)
 {
@@ -468,7 +468,7 @@ void intel_lpss_remove(struct device *dev)
 	intel_lpss_unregister_clock(lpss);
 	ida_free(&intel_lpss_devid_ida, lpss->devid);
 }
-EXPORT_SYMBOL_GPL(intel_lpss_remove);
+EXPORT_SYMBOL_NS_GPL(intel_lpss_remove, INTEL_LPSS);
 
 #ifdef CONFIG_PM
 static int resume_lpss_device(struct device *dev, void *data)
@@ -488,7 +488,7 @@ int intel_lpss_prepare(struct device *dev)
 	device_for_each_child_reverse(dev, NULL, resume_lpss_device);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_lpss_prepare);
+EXPORT_SYMBOL_NS_GPL(intel_lpss_prepare, INTEL_LPSS);
 
 int intel_lpss_suspend(struct device *dev)
 {
@@ -509,7 +509,7 @@ int intel_lpss_suspend(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_lpss_suspend);
+EXPORT_SYMBOL_NS_GPL(intel_lpss_suspend, INTEL_LPSS);
 
 int intel_lpss_resume(struct device *dev)
 {
@@ -524,7 +524,7 @@ int intel_lpss_resume(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(intel_lpss_resume);
+EXPORT_SYMBOL_NS_GPL(intel_lpss_resume, INTEL_LPSS);
 #endif
 
 static int __init intel_lpss_init(void)
-- 
GitLab


From fd58bb8c7da3c2d4314d7ab76402ca18e9cc0afa Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 24 Nov 2023 21:31:28 +0200
Subject: [PATCH 0918/4076] mfd: intel-lpss: Provide Intel LPSS PM ops
 structure

With the help of EXPORT_NS_GPL_DEV_PM_OPS() and other *_PM_OPS() macros
we may convert PM ops functions to become static. This also takes into
account the PM configuration options such as CONFIG_PM and CONFIG_PM_SLEEP.
This all removes a lot of ugly macros and ifdeffery in the driver.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231124200258.3682979-6-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss-acpi.c |  5 ++---
 drivers/mfd/intel-lpss-pci.c  |  5 ++---
 drivers/mfd/intel-lpss.c      | 18 ++++++++++--------
 drivers/mfd/intel-lpss.h      | 28 +---------------------------
 4 files changed, 15 insertions(+), 41 deletions(-)

diff --git a/drivers/mfd/intel-lpss-acpi.c b/drivers/mfd/intel-lpss-acpi.c
index a9e2d9308a01c..2a83f8678f1d9 100644
--- a/drivers/mfd/intel-lpss-acpi.c
+++ b/drivers/mfd/intel-lpss-acpi.c
@@ -13,6 +13,7 @@
 #include <linux/ioport.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
@@ -205,15 +206,13 @@ static void intel_lpss_acpi_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 }
 
-static INTEL_LPSS_PM_OPS(intel_lpss_acpi_pm_ops);
-
 static struct platform_driver intel_lpss_acpi_driver = {
 	.probe = intel_lpss_acpi_probe,
 	.remove_new = intel_lpss_acpi_remove,
 	.driver = {
 		.name = "intel-lpss",
 		.acpi_match_table = intel_lpss_acpi_ids,
-		.pm = &intel_lpss_acpi_pm_ops,
+		.pm = pm_ptr(&intel_lpss_pm_ops),
 	},
 };
 
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index e1d89423daa6a..8f5e10817a9c5 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -13,6 +13,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
 
@@ -81,8 +82,6 @@ static void intel_lpss_pci_remove(struct pci_dev *pdev)
 	intel_lpss_remove(&pdev->dev);
 }
 
-static INTEL_LPSS_PM_OPS(intel_lpss_pci_pm_ops);
-
 static const struct property_entry spt_spi_properties[] = {
 	PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_SPT_SSP),
 	{ }
@@ -593,7 +592,7 @@ static struct pci_driver intel_lpss_pci_driver = {
 	.probe = intel_lpss_pci_probe,
 	.remove = intel_lpss_pci_remove,
 	.driver = {
-		.pm = &intel_lpss_pci_pm_ops,
+		.pm = pm_ptr(&intel_lpss_pm_ops),
 	},
 };
 
diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index 4a63703b6da56..177915845ba2b 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -24,6 +24,7 @@
 #include <linux/ioport.h>
 #include <linux/mfd/core.h>
 #include <linux/module.h>
+#include <linux/pm.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 #include <linux/sprintf.h>
@@ -470,7 +471,6 @@ void intel_lpss_remove(struct device *dev)
 }
 EXPORT_SYMBOL_NS_GPL(intel_lpss_remove, INTEL_LPSS);
 
-#ifdef CONFIG_PM
 static int resume_lpss_device(struct device *dev, void *data)
 {
 	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
@@ -479,7 +479,7 @@ static int resume_lpss_device(struct device *dev, void *data)
 	return 0;
 }
 
-int intel_lpss_prepare(struct device *dev)
+static int intel_lpss_prepare(struct device *dev)
 {
 	/*
 	 * Resume both child devices before entering system sleep. This
@@ -488,9 +488,8 @@ int intel_lpss_prepare(struct device *dev)
 	device_for_each_child_reverse(dev, NULL, resume_lpss_device);
 	return 0;
 }
-EXPORT_SYMBOL_NS_GPL(intel_lpss_prepare, INTEL_LPSS);
 
-int intel_lpss_suspend(struct device *dev)
+static int intel_lpss_suspend(struct device *dev)
 {
 	struct intel_lpss *lpss = dev_get_drvdata(dev);
 	unsigned int i;
@@ -509,9 +508,8 @@ int intel_lpss_suspend(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_NS_GPL(intel_lpss_suspend, INTEL_LPSS);
 
-int intel_lpss_resume(struct device *dev)
+static int intel_lpss_resume(struct device *dev)
 {
 	struct intel_lpss *lpss = dev_get_drvdata(dev);
 	unsigned int i;
@@ -524,8 +522,12 @@ int intel_lpss_resume(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_NS_GPL(intel_lpss_resume, INTEL_LPSS);
-#endif
+
+EXPORT_NS_GPL_DEV_PM_OPS(intel_lpss_pm_ops, INTEL_LPSS) = {
+	.prepare = pm_sleep_ptr(&intel_lpss_prepare),
+	LATE_SYSTEM_SLEEP_PM_OPS(intel_lpss_suspend, intel_lpss_resume)
+	RUNTIME_PM_OPS(intel_lpss_suspend, intel_lpss_resume, NULL)
+};
 
 static int __init intel_lpss_init(void)
 {
diff --git a/drivers/mfd/intel-lpss.h b/drivers/mfd/intel-lpss.h
index 062ce95b68b9a..c1d72b117ed5e 100644
--- a/drivers/mfd/intel-lpss.h
+++ b/drivers/mfd/intel-lpss.h
@@ -30,32 +30,6 @@ int intel_lpss_probe(struct device *dev,
 		     const struct intel_lpss_platform_info *info);
 void intel_lpss_remove(struct device *dev);
 
-#ifdef CONFIG_PM
-int intel_lpss_prepare(struct device *dev);
-int intel_lpss_suspend(struct device *dev);
-int intel_lpss_resume(struct device *dev);
-
-#ifdef CONFIG_PM_SLEEP
-#define INTEL_LPSS_SLEEP_PM_OPS			\
-	.prepare = intel_lpss_prepare,		\
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(intel_lpss_suspend, intel_lpss_resume)
-#else
-#define INTEL_LPSS_SLEEP_PM_OPS
-#endif
-
-#define INTEL_LPSS_RUNTIME_PM_OPS		\
-	.runtime_suspend = intel_lpss_suspend,	\
-	.runtime_resume = intel_lpss_resume,
-
-#else /* !CONFIG_PM */
-#define INTEL_LPSS_SLEEP_PM_OPS
-#define INTEL_LPSS_RUNTIME_PM_OPS
-#endif /* CONFIG_PM */
-
-#define INTEL_LPSS_PM_OPS(name)			\
-const struct dev_pm_ops name = {		\
-	INTEL_LPSS_SLEEP_PM_OPS			\
-	INTEL_LPSS_RUNTIME_PM_OPS		\
-}
+extern const struct dev_pm_ops intel_lpss_pm_ops;
 
 #endif /* __MFD_INTEL_LPSS_H */
-- 
GitLab


From 1fe13d83e2873b0aedeb5b9a299ca763bd37d75f Mon Sep 17 00:00:00 2001
From: Kaihua Zhong <zhongkaihua@kylinos.cn>
Date: Wed, 29 Nov 2023 09:55:26 +0800
Subject: [PATCH 0919/4076] mfd: Fix a few spelling mistakes in PMIC header
 file comments

Fix four comment typos in MFD PMIC header files.

Reported-by: k2ci <kernel-bot@kylinos.cn>
Signed-off-by: Kaihua Zhong <zhongkaihua@kylinos.cn>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20231129015526.3302865-1-zhongkaihua@kylinos.cn
Signed-off-by: Lee Jones <lee@kernel.org>
---
 include/linux/mfd/max77693-private.h | 2 +-
 include/linux/mfd/max77843-private.h | 2 +-
 include/linux/mfd/si476x-platform.h  | 2 +-
 include/linux/mfd/tps65910.h         | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index 311f7d3d23236..54444ff2a5dea 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -405,7 +405,7 @@ enum max77693_haptic_reg {
 	MAX77693_HAPTIC_REG_END,
 };
 
-/* max77693-pmic LSCNFG configuraton register */
+/* max77693-pmic LSCNFG configuration register */
 #define MAX77693_PMIC_LOW_SYS_MASK      0x80
 #define MAX77693_PMIC_LOW_SYS_SHIFT     7
 
diff --git a/include/linux/mfd/max77843-private.h b/include/linux/mfd/max77843-private.h
index 0bc7454c4dbe3..2fb4db67f1104 100644
--- a/include/linux/mfd/max77843-private.h
+++ b/include/linux/mfd/max77843-private.h
@@ -198,7 +198,7 @@ enum max77843_irq_muic {
 #define MAX77843_MCONFIG_MEN_MASK		BIT(MCONFIG_MEN_SHIFT)
 #define MAX77843_MCONFIG_PDIV_MASK		(0x3 << MCONFIG_PDIV_SHIFT)
 
-/* Max77843 charger insterrupts */
+/* Max77843 charger interrupts */
 #define MAX77843_CHG_BYP_I			BIT(0)
 #define MAX77843_CHG_BATP_I			BIT(2)
 #define MAX77843_CHG_BAT_I			BIT(3)
diff --git a/include/linux/mfd/si476x-platform.h b/include/linux/mfd/si476x-platform.h
index 18363b773d070..cb99e16ca9473 100644
--- a/include/linux/mfd/si476x-platform.h
+++ b/include/linux/mfd/si476x-platform.h
@@ -10,7 +10,7 @@
 #ifndef __SI476X_PLATFORM_H__
 #define __SI476X_PLATFORM_H__
 
-/* It is possible to select one of the four adresses using pins A0
+/* It is possible to select one of the four addresses using pins A0
  * and A1 on SI476x */
 #define SI476X_I2C_ADDR_1	0x60
 #define SI476X_I2C_ADDR_2	0x61
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 701925db75b3f..f67ef0a4e041c 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -749,7 +749,7 @@
 #define VDDCTRL_ST_SHIFT                                 0
 
 
-/*Register VDDCTRL_OP  (0x28) bit definitios */
+/*Register VDDCTRL_OP  (0x28) bit definitions */
 #define VDDCTRL_OP_CMD_MASK                              0x80
 #define VDDCTRL_OP_CMD_SHIFT                             7
 #define VDDCTRL_OP_SEL_MASK                              0x7F
-- 
GitLab


From 47b1b03dc56ebc302620ce43e967aa8f33516f6f Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Thu, 30 Nov 2023 11:57:11 +0000
Subject: [PATCH 0920/4076] mfd: cs42l43: Correct SoundWire port list

Two ports are missing from the port list, and the wrong port is set
to 4 channels. Also the attempt to list them by function is rather
misguided, there is nothing in the hardware that fixes a particular
port to one function. Factor out the port properties to an actual
struct, fixing the missing ports and correcting the port set to 4
channels.

Fixes: ace6d1448138 ("mfd: cs42l43: Add support for cs42l43 core driver")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231130115712.669180-1-ckeepax@opensource.cirrus.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/cs42l43-sdw.c | 74 +++++++++++++++------------------------
 1 file changed, 28 insertions(+), 46 deletions(-)

diff --git a/drivers/mfd/cs42l43-sdw.c b/drivers/mfd/cs42l43-sdw.c
index 7392b3d2e6b96..4be4df9dd8cf1 100644
--- a/drivers/mfd/cs42l43-sdw.c
+++ b/drivers/mfd/cs42l43-sdw.c
@@ -17,13 +17,12 @@
 
 #include "cs42l43.h"
 
-enum cs42l43_sdw_ports {
-	CS42L43_DMIC_DEC_ASP_PORT = 1,
-	CS42L43_SPK_TX_PORT,
-	CS42L43_SPDIF_HP_PORT,
-	CS42L43_SPK_RX_PORT,
-	CS42L43_ASP_PORT,
-};
+#define CS42L43_SDW_PORT(port, chans) { \
+	.num = port, \
+	.max_ch = chans, \
+	.type = SDW_DPN_FULL, \
+	.max_word = 24, \
+}
 
 static const struct regmap_config cs42l43_sdw_regmap = {
 	.reg_bits		= 32,
@@ -42,65 +41,48 @@ static const struct regmap_config cs42l43_sdw_regmap = {
 	.num_reg_defaults	= ARRAY_SIZE(cs42l43_reg_default),
 };
 
+static const struct sdw_dpn_prop cs42l43_src_port_props[] = {
+	CS42L43_SDW_PORT(1, 4),
+	CS42L43_SDW_PORT(2, 2),
+	CS42L43_SDW_PORT(3, 2),
+	CS42L43_SDW_PORT(4, 2),
+};
+
+static const struct sdw_dpn_prop cs42l43_sink_port_props[] = {
+	CS42L43_SDW_PORT(5, 2),
+	CS42L43_SDW_PORT(6, 2),
+	CS42L43_SDW_PORT(7, 2),
+};
+
 static int cs42l43_read_prop(struct sdw_slave *sdw)
 {
 	struct sdw_slave_prop *prop = &sdw->prop;
 	struct device *dev = &sdw->dev;
-	struct sdw_dpn_prop *dpn;
-	unsigned long addr;
-	int nval;
 	int i;
-	u32 bit;
 
 	prop->use_domain_irq = true;
 	prop->paging_support = true;
 	prop->wake_capable = true;
-	prop->source_ports = BIT(CS42L43_DMIC_DEC_ASP_PORT) | BIT(CS42L43_SPK_TX_PORT);
-	prop->sink_ports = BIT(CS42L43_SPDIF_HP_PORT) |
-			   BIT(CS42L43_SPK_RX_PORT) | BIT(CS42L43_ASP_PORT);
 	prop->quirks = SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY;
 	prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY |
 			      SDW_SCP_INT1_IMPL_DEF;
 
-	nval = hweight32(prop->source_ports);
-	prop->src_dpn_prop = devm_kcalloc(dev, nval, sizeof(*prop->src_dpn_prop),
-					  GFP_KERNEL);
+	for (i = 0; i < ARRAY_SIZE(cs42l43_src_port_props); i++)
+		prop->source_ports |= BIT(cs42l43_src_port_props[i].num);
+
+	prop->src_dpn_prop = devm_kmemdup(dev, cs42l43_src_port_props,
+					  sizeof(cs42l43_src_port_props), GFP_KERNEL);
 	if (!prop->src_dpn_prop)
 		return -ENOMEM;
 
-	i = 0;
-	dpn = prop->src_dpn_prop;
-	addr = prop->source_ports;
-	for_each_set_bit(bit, &addr, 32) {
-		dpn[i].num = bit;
-		dpn[i].max_ch = 2;
-		dpn[i].type = SDW_DPN_FULL;
-		dpn[i].max_word = 24;
-		i++;
-	}
-	/*
-	 * All ports are 2 channels max, except the first one,
-	 * CS42L43_DMIC_DEC_ASP_PORT.
-	 */
-	dpn[CS42L43_DMIC_DEC_ASP_PORT].max_ch = 4;
+	for (i = 0; i < ARRAY_SIZE(cs42l43_sink_port_props); i++)
+		prop->sink_ports |= BIT(cs42l43_sink_port_props[i].num);
 
-	nval = hweight32(prop->sink_ports);
-	prop->sink_dpn_prop = devm_kcalloc(dev, nval, sizeof(*prop->sink_dpn_prop),
-					   GFP_KERNEL);
+	prop->sink_dpn_prop = devm_kmemdup(dev, cs42l43_sink_port_props,
+					   sizeof(cs42l43_sink_port_props), GFP_KERNEL);
 	if (!prop->sink_dpn_prop)
 		return -ENOMEM;
 
-	i = 0;
-	dpn = prop->sink_dpn_prop;
-	addr = prop->sink_ports;
-	for_each_set_bit(bit, &addr, 32) {
-		dpn[i].num = bit;
-		dpn[i].max_ch = 2;
-		dpn[i].type = SDW_DPN_FULL;
-		dpn[i].max_word = 24;
-		i++;
-	}
-
 	return 0;
 }
 
-- 
GitLab


From db763745626495d23b0691f3906d3d7c40110db4 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Thu, 30 Nov 2023 11:57:12 +0000
Subject: [PATCH 0921/4076] mfd: cs42l43: Correct order of include files to be
 alphabetical

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231130115712.669180-2-ckeepax@opensource.cirrus.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/cs42l43-sdw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mfd/cs42l43-sdw.c b/drivers/mfd/cs42l43-sdw.c
index 4be4df9dd8cf1..1d85bbf8cdd5d 100644
--- a/drivers/mfd/cs42l43-sdw.c
+++ b/drivers/mfd/cs42l43-sdw.c
@@ -6,11 +6,11 @@
  *                         Cirrus Logic International Semiconductor Ltd.
  */
 
+#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/mfd/cs42l43-regs.h>
 #include <linux/module.h>
-#include <linux/device.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/soundwire/sdw_type.h>
-- 
GitLab


From 7a29fa05aeca2c16193f00a883c56ffc7c25b6c5 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@gmail.com>
Date: Sun, 29 Oct 2023 13:48:43 +0200
Subject: [PATCH 0922/4076] mfd: twl6030-irq: Revert to use of_match_device()

The core twl chip is probed via i2c and the dev->driver->of_match_table is
NULL, causing the driver to fail to probe.

This partially reverts:

  commit 1e0c866887f4 ("mfd: Use device_get_match_data() in a bunch of drivers")

Fixes: 1e0c866887f4 ("mfd: Use device_get_match_data() in a bunch of drivers")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@gmail.com>
Link: https://lore.kernel.org/r/20231029114843.15553-1-peter.ujfalusi@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/twl6030-irq.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/mfd/twl6030-irq.c b/drivers/mfd/twl6030-irq.c
index f9fce8408c2cf..3c03681c124c0 100644
--- a/drivers/mfd/twl6030-irq.c
+++ b/drivers/mfd/twl6030-irq.c
@@ -24,10 +24,10 @@
 #include <linux/kthread.h>
 #include <linux/mfd/twl.h>
 #include <linux/platform_device.h>
-#include <linux/property.h>
 #include <linux/suspend.h>
 #include <linux/of.h>
 #include <linux/irqdomain.h>
+#include <linux/of_device.h>
 
 #include "twl-core.h"
 
@@ -368,10 +368,10 @@ int twl6030_init_irq(struct device *dev, int irq_num)
 	int			nr_irqs;
 	int			status;
 	u8			mask[3];
-	const int		*irq_tbl;
+	const struct of_device_id *of_id;
 
-	irq_tbl = device_get_match_data(dev);
-	if (!irq_tbl) {
+	of_id = of_match_device(twl6030_of_match, dev);
+	if (!of_id || !of_id->data) {
 		dev_err(dev, "Unknown TWL device model\n");
 		return -EINVAL;
 	}
@@ -409,7 +409,7 @@ int twl6030_init_irq(struct device *dev, int irq_num)
 
 	twl6030_irq->pm_nb.notifier_call = twl6030_irq_pm_notifier;
 	atomic_set(&twl6030_irq->wakeirqs, 0);
-	twl6030_irq->irq_mapping_tbl = irq_tbl;
+	twl6030_irq->irq_mapping_tbl = of_id->data;
 
 	twl6030_irq->irq_domain =
 		irq_domain_add_linear(node, nr_irqs,
-- 
GitLab


From 0c679fffd67605a2c10a61a9a09890970eae11a9 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 30 Nov 2023 16:32:06 +0200
Subject: [PATCH 0923/4076] mfd: intel-lpss: Don't fail probe on success of
 pci_alloc_irq_vectors()

The pci_alloc_irq_vectors() returns a positive number on success.
Hence we have to filter the negative numbers for error condition.
Update the check accordingly.

Fixes: e6951fb78787 ("mfd: intel-lpss: Use PCI APIs instead of dereferencing")
Reported-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231130143206.1475831-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss-pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index 8f5e10817a9c5..4621d3950b8f9 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -44,7 +44,7 @@ static int intel_lpss_pci_probe(struct pci_dev *pdev,
 		return ret;
 
 	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	info = devm_kmemdup(&pdev->dev, data, sizeof(*info), GFP_KERNEL);
-- 
GitLab


From 769ff5283f0d7edc819743f183d51af077411107 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Thu, 30 Nov 2023 13:11:56 +0800
Subject: [PATCH 0924/4076] backlight: ili922x: Add an error code check in
 ili922x_write()

Clang static analyzer complains that value stored to 'ret' is never read.
Return the error code when spi_sync() failed.

Signed-off-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20231130051155.1235972-1-suhui@nfschina.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/video/backlight/ili922x.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c
index 206e77afc56f2..c8e0e655dc867 100644
--- a/drivers/video/backlight/ili922x.c
+++ b/drivers/video/backlight/ili922x.c
@@ -269,6 +269,10 @@ static int ili922x_write(struct spi_device *spi, u8 reg, u16 value)
 	spi_message_add_tail(&xfer_regindex, &msg);
 
 	ret = spi_sync(spi, &msg);
+	if (ret < 0) {
+		dev_err(&spi->dev, "Error sending SPI message 0x%x", ret);
+		return ret;
+	}
 
 	spi_message_init(&msg);
 	tbuf[0] = set_tx_byte(START_BYTE(ili922x_id, START_RS_REG,
-- 
GitLab


From 41673c66b3d0c09915698fec5c13b24336f18dd1 Mon Sep 17 00:00:00 2001
From: Kunwu Chan <chentao@kylinos.cn>
Date: Mon, 4 Dec 2023 17:24:43 +0800
Subject: [PATCH 0925/4076] mfd: syscon: Fix null pointer dereference in
 of_syscon_register()

kasprintf() returns a pointer to dynamically allocated memory
which can be NULL upon failure.

Fixes: e15d7f2b81d2 ("mfd: syscon: Use a unique name with regmap_config")
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20231204092443.2462115-1-chentao@kylinos.cn
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/syscon.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c
index 57b29c3251312..c9550368d9ea5 100644
--- a/drivers/mfd/syscon.c
+++ b/drivers/mfd/syscon.c
@@ -105,6 +105,10 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_res)
 	}
 
 	syscon_config.name = kasprintf(GFP_KERNEL, "%pOFn@%pa", np, &res.start);
+	if (!syscon_config.name) {
+		ret = -ENOMEM;
+		goto err_regmap;
+	}
 	syscon_config.reg_stride = reg_io_width;
 	syscon_config.val_bits = reg_io_width * 8;
 	syscon_config.max_register = resource_size(&res) - reg_io_width;
-- 
GitLab


From 9b413e3c07d251191410976d669260079b48e7b1 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 4 Dec 2023 12:45:07 +0000
Subject: [PATCH 0926/4076] mfd: da9062: Simplify obtaining I2C match data

Simplify probe() by replacing of_device_get_match_data() and ID lookup for
retrieving match data by i2c_get_match_data().

Some minor cleanups:
 * Remove the trailing comma in the terminator entry for the ID
   table making code robust against (theoretical) misrebases or other
   similar things where the new entry goes _after_ the termination without
   the compiler noticing.
 * Move OF table near to the user.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231204124507.124758-1-biju.das.jz@bp.renesas.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/da9062-core.c | 22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

diff --git a/drivers/mfd/da9062-core.c b/drivers/mfd/da9062-core.c
index 45da007d3e702..73a22107900c8 100644
--- a/drivers/mfd/da9062-core.c
+++ b/drivers/mfd/da9062-core.c
@@ -588,16 +588,8 @@ static struct regmap_config da9062_regmap_config = {
 	.volatile_table = &da9062_aa_volatile_table,
 };
 
-static const struct of_device_id da9062_dt_ids[] = {
-	{ .compatible = "dlg,da9061", .data = (void *)COMPAT_TYPE_DA9061, },
-	{ .compatible = "dlg,da9062", .data = (void *)COMPAT_TYPE_DA9062, },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, da9062_dt_ids);
-
 static int da9062_i2c_probe(struct i2c_client *i2c)
 {
-	const struct i2c_device_id *id = i2c_client_get_device_id(i2c);
 	struct da9062 *chip;
 	unsigned int irq_base = 0;
 	const struct mfd_cell *cell;
@@ -611,10 +603,7 @@ static int da9062_i2c_probe(struct i2c_client *i2c)
 	if (!chip)
 		return -ENOMEM;
 
-	if (i2c->dev.of_node)
-		chip->chip_type = (uintptr_t)of_device_get_match_data(&i2c->dev);
-	else
-		chip->chip_type = id->driver_data;
+	chip->chip_type = (uintptr_t)i2c_get_match_data(i2c);
 
 	i2c_set_clientdata(i2c, chip);
 	chip->dev = &i2c->dev;
@@ -714,10 +703,17 @@ static void da9062_i2c_remove(struct i2c_client *i2c)
 	regmap_del_irq_chip(i2c->irq, chip->regmap_irq);
 }
 
+static const struct of_device_id da9062_dt_ids[] = {
+	{ .compatible = "dlg,da9061", .data = (void *)COMPAT_TYPE_DA9061 },
+	{ .compatible = "dlg,da9062", .data = (void *)COMPAT_TYPE_DA9062 },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, da9062_dt_ids);
+
 static const struct i2c_device_id da9062_i2c_id[] = {
 	{ "da9061", COMPAT_TYPE_DA9061 },
 	{ "da9062", COMPAT_TYPE_DA9062 },
-	{ },
+	{ }
 };
 MODULE_DEVICE_TABLE(i2c, da9062_i2c_id);
 
-- 
GitLab


From e23f1530eab97e8d9dfbbdd9af3802c9c1e026a4 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Wed, 6 Dec 2023 12:17:51 +0100
Subject: [PATCH 0927/4076] dt-bindings: mfd: hisilicon,hi6421-spmi-pmic: Fix
 up binding reference

Fix up the SPMI PMIC binding document free text reference which
erroneously referred to itself rather than the parent SPMI controller
binding as intended.

Fixes: 9e5917288545 ("dt: document HiSilicon SPMI controller and mfd/regulator properties")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231206111754.7410-2-johan+linaro@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
index bdff5b6534538..e36e5ce58136b 100644
--- a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
@@ -17,7 +17,7 @@ description: |
   node.
 
   The SPMI controller part is provided by
-  Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
+  Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml
 
 properties:
   $nodename:
-- 
GitLab


From d5c005ff9fe33dc7c2c3e13d1bdca698f441ac86 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Wed, 6 Dec 2023 12:17:52 +0100
Subject: [PATCH 0928/4076] dt-bindings: mfd: hisilicon,hi6421-spmi-pmic: Fix
 regulator binding

The regulator child nodes do not have unit addresses so drop the
incorrect '#address-cells' and '#size-cells' properties from the parent
'regulators' node.

Fixes: 352335a6aced ("staging: hikey9xx: hisilicon, hi6421-spmi-pmic.yaml: simplify props")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231206111754.7410-3-johan+linaro@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml       | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
index e36e5ce58136b..45cd6a613a91f 100644
--- a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
@@ -42,13 +42,6 @@ properties:
 
     additionalProperties: false
 
-    properties:
-      '#address-cells':
-        const: 1
-
-      '#size-cells':
-        const: 0
-
     patternProperties:
       '^ldo[0-9]+$':
         type: object
@@ -77,9 +70,6 @@ examples:
       interrupts = <0 0>;
 
       regulators {
-        #address-cells = <1>;
-        #size-cells = <0>;
-
         ldo3: ldo3 {
           regulator-name = "ldo3";
           regulator-min-microvolt = <1500000>;
-- 
GitLab


From 1aa77a7ed020721c6c4a3da16ea3a970f2ce4eea Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Wed, 6 Dec 2023 12:17:53 +0100
Subject: [PATCH 0929/4076] dt-bindings: mfd: hisilicon,hi6421-spmi-pmic: Clean
 up example

The SPMI PMIC sits on an SPMI bus which and has two address cells with
no size.

Clean up the example by adding a parent SPMI bus node with proper
'#address-cells' and '#size-cells' properties, using a define for the
second register value, dropping the unnecessary label and increasing the
indentation to four spaces.

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231206111754.7410-4-johan+linaro@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../mfd/hisilicon,hi6421-spmi-pmic.yaml       | 134 +++++++++---------
 1 file changed, 70 insertions(+), 64 deletions(-)

diff --git a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
index 45cd6a613a91f..6a824351834ee 100644
--- a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml
@@ -59,69 +59,75 @@ additionalProperties: false
 
 examples:
   - |
-
-    pmic: pmic@0 {
-      compatible = "hisilicon,hi6421v600-spmi";
-      reg = <0 0>;
-
-      #interrupt-cells = <2>;
-      interrupt-controller;
-      interrupt-parent = <&gpio28>;
-      interrupts = <0 0>;
-
-      regulators {
-        ldo3: ldo3 {
-          regulator-name = "ldo3";
-          regulator-min-microvolt = <1500000>;
-          regulator-max-microvolt = <2000000>;
-          regulator-boot-on;
-        };
-
-        ldo4: ldo4 {
-          regulator-name = "ldo4";
-          regulator-min-microvolt = <1725000>;
-          regulator-max-microvolt = <1900000>;
-          regulator-boot-on;
-        };
-
-        ldo9: ldo9 {
-          regulator-name = "ldo9";
-          regulator-min-microvolt = <1750000>;
-          regulator-max-microvolt = <3300000>;
-          regulator-boot-on;
-        };
-
-        ldo15: ldo15 {
-          regulator-name = "ldo15";
-          regulator-min-microvolt = <1800000>;
-          regulator-max-microvolt = <3000000>;
-          regulator-always-on;
-        };
-
-        ldo16: ldo16 {
-          regulator-name = "ldo16";
-          regulator-min-microvolt = <1800000>;
-          regulator-max-microvolt = <3000000>;
-          regulator-boot-on;
-        };
-
-        ldo17: ldo17 {
-          regulator-name = "ldo17";
-          regulator-min-microvolt = <2500000>;
-          regulator-max-microvolt = <3300000>;
-        };
-
-        ldo33: ldo33 {
-          regulator-name = "ldo33";
-          regulator-min-microvolt = <2500000>;
-          regulator-max-microvolt = <3300000>;
-          regulator-boot-on;
-        };
-
-        ldo34: ldo34 {
-          regulator-name = "ldo34";
-          regulator-min-microvolt = <2600000>;
-          regulator-max-microvolt = <3300000>;
+    #include <dt-bindings/spmi/spmi.h>
+
+    spmi {
+        #address-cells = <2>;
+        #size-cells = <0>;
+
+        pmic@0 {
+            compatible = "hisilicon,hi6421v600-spmi";
+            reg = <0 SPMI_USID>;
+
+            #interrupt-cells = <2>;
+            interrupt-controller;
+            interrupt-parent = <&gpio28>;
+            interrupts = <0 0>;
+
+            regulators {
+                ldo3 {
+                    regulator-name = "ldo3";
+                    regulator-min-microvolt = <1500000>;
+                    regulator-max-microvolt = <2000000>;
+                    regulator-boot-on;
+                };
+
+                ldo4 {
+                    regulator-name = "ldo4";
+                    regulator-min-microvolt = <1725000>;
+                    regulator-max-microvolt = <1900000>;
+                    regulator-boot-on;
+                };
+
+                ldo9 {
+                    regulator-name = "ldo9";
+                    regulator-min-microvolt = <1750000>;
+                    regulator-max-microvolt = <3300000>;
+                    regulator-boot-on;
+                };
+
+                ldo15 {
+                    regulator-name = "ldo15";
+                    regulator-min-microvolt = <1800000>;
+                    regulator-max-microvolt = <3000000>;
+                    regulator-always-on;
+                };
+
+                ldo16 {
+                    regulator-name = "ldo16";
+                    regulator-min-microvolt = <1800000>;
+                    regulator-max-microvolt = <3000000>;
+                    regulator-boot-on;
+                };
+
+                ldo17 {
+                    regulator-name = "ldo17";
+                    regulator-min-microvolt = <2500000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+
+                ldo33 {
+                    regulator-name = "ldo33";
+                    regulator-min-microvolt = <2500000>;
+                    regulator-max-microvolt = <3300000>;
+                    regulator-boot-on;
+                };
+
+                ldo34 {
+                    regulator-name = "ldo34";
+                    regulator-min-microvolt = <2600000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+            };
         };
-      };
     };
-- 
GitLab


From 3310288f61357b9b54139c93fc7665d60c0288bf Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javierm@redhat.com>
Date: Mon, 13 Nov 2023 09:51:41 +0100
Subject: [PATCH 0930/4076] of/platform: Disable sysfb if a simple-framebuffer
 node is found

Some DT platforms use EFI to boot and in this case the EFI Boot Services
may register a EFI_GRAPHICS_OUTPUT_PROTOCOL handle, that will later be
queried by the Linux EFI stub to fill the global struct screen_info data.

The data is used by the Generic System Framebuffers (sysfb) framework to
add a platform device with platform data about the system framebuffer.

But if there is a "simple-framebuffer" node in the DT, the OF core will
also do the same and add another device for the system framebuffer.

This could lead for example, to two platform devices ("simple-framebuffer"
and "efi-framebuffer") to be added and matched with their corresponding
drivers. So both efifb and simpledrm will be probed, leading to following:

[    0.055752] efifb: framebuffer at 0xbd58dc000, using 16000k, total 16000k
[    0.055755] efifb: mode is 2560x1600x32, linelength=10240, pages=1
[    0.055758] efifb: scrolling: redraw
[    0.055759] efifb: Truecolor: size=2:10:10:10, shift=30:20:10:0
...
[    3.295896] simple-framebuffer bd58dc000.framebuffer: [drm] *ERROR*
could not acquire memory range [??? 0xffff79f30a29ee40-0x2a5000001a7
flags 0x0]: -16
[    3.298018] simple-framebuffer: probe of bd58dc000.framebuffer
failed with error -16

To prevent the issue, make the OF core to disable sysfb if there is a node
with a "simple-framebuffer" compatible. That way only this device will be
registered and sysfb would not attempt to register another one using the
screen_info data even if this has been filled.

This seems the correct thing to do in this case because:

a) On a DT platform, the DTB is the single source of truth since is what
   describes the hardware topology. Even if EFI Boot Services are used to
   boot the machine.

b) The of_platform_default_populate_init() function is called in the
   arch_initcall_sync() initcall level while the sysfb_init() function
   is called later in the subsys_initcall() initcall level.

Reported-by: Andrew Worsley <amworsley@gmail.com>
Closes: https://lore.kernel.org/all/20231111042926.52990-2-amworsley@gmail.com
Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://lore.kernel.org/r/20231113085305.1823455-1-javierm@redhat.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/platform.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 2293059758d1d..af0e1fb2ab688 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -20,6 +20,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/sysfb.h>
 
 #include "of_private.h"
 
@@ -621,8 +622,21 @@ static int __init of_platform_default_populate_init(void)
 		}
 
 		node = of_get_compatible_child(of_chosen, "simple-framebuffer");
-		of_platform_device_create(node, NULL, NULL);
-		of_node_put(node);
+		if (node) {
+			/*
+			 * Since a "simple-framebuffer" device is already added
+			 * here, disable the Generic System Framebuffers (sysfb)
+			 * to prevent it from registering another device for the
+			 * system framebuffer later (e.g: using the screen_info
+			 * data that may had been filled as well).
+			 *
+			 * This can happen for example on DT systems that do EFI
+			 * booting and may provide a GOP handle to the EFI stub.
+			 */
+			sysfb_disable();
+			of_platform_device_create(node, NULL, NULL);
+			of_node_put(node);
+		}
 
 		/* Populate everything else. */
 		of_platform_default_populate(NULL, NULL, NULL);
-- 
GitLab


From 87562052c965ba7de6dc490434e53691fe46c898 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:15 +0100
Subject: [PATCH 0931/4076] KVM: x86/xen: Remove unneeded xen context from
 kvm_arch when !CONFIG_KVM_XEN

Saving a few bytes of memory per KVM VM is certainly great but what's more
important is the ability to see where the code accesses Xen emulation
context while CONFIG_KVM_XEN is not enabled. Currently, kvm_cpu_get_extint()
is the only such place and it is harmless: kvm_xen_has_interrupt() always
returns '0' when !CONFIG_KVM_XEN.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-2-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h | 5 +++++
 arch/x86/kvm/irq.c              | 2 ++
 2 files changed, 7 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5e5e9e0abd4a0..b0ca65632f2ce 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1136,6 +1136,7 @@ struct msr_bitmap_range {
 	unsigned long *bitmap;
 };
 
+#ifdef CONFIG_KVM_XEN
 /* Xen emulation context */
 struct kvm_xen {
 	struct mutex xen_lock;
@@ -1147,6 +1148,7 @@ struct kvm_xen {
 	struct idr evtchn_ports;
 	unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 };
+#endif
 
 enum kvm_irqchip_mode {
 	KVM_IRQCHIP_NONE,
@@ -1349,7 +1351,10 @@ struct kvm_arch {
 	struct hlist_head mask_notifier_list;
 
 	struct kvm_hv hyperv;
+
+#ifdef CONFIG_KVM_XEN
 	struct kvm_xen xen;
+#endif
 
 	bool backwards_tsc_observed;
 	bool boot_vcpu_runs_old_kvmclock;
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index b2c397dd2bc66..ad9ca8a60144c 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -118,8 +118,10 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.nr;
 
+#ifdef CONFIG_KVM_XEN
 	if (kvm_xen_has_interrupt(v))
 		return v->kvm->arch.xen.upcall_vector;
+#endif
 
 	if (irqchip_split(v->kvm)) {
 		int vector = v->arch.pending_external_vector;
-- 
GitLab


From cfef5af3cb0e57501dcac2816ab11a20c074866d Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:16 +0100
Subject: [PATCH 0932/4076] KVM: x86: Move Hyper-V partition assist page out of
 Hyper-V emulation context

Hyper-V partition assist page is used when KVM runs on top of Hyper-V and
is not used for Windows/Hyper-V guests on KVM, this means that 'hv_pa_pg'
placement in 'struct kvm_hv' is unfortunate. As a preparation to making
Hyper-V emulation optional, move 'hv_pa_pg' to 'struct kvm_arch' and put it
under CONFIG_HYPERV.

While on it, introduce hv_get_partition_assist_page() helper to allocate
partition assist page. Move the comment explaining why we use a single page
for all vCPUs from VMX and expand it a bit.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-3-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h |  2 +-
 arch/x86/kvm/kvm_onhyperv.h     | 20 ++++++++++++++++++++
 arch/x86/kvm/svm/svm_onhyperv.c | 10 +++-------
 arch/x86/kvm/vmx/vmx.c          | 14 +++-----------
 arch/x86/kvm/x86.c              |  4 +++-
 5 files changed, 30 insertions(+), 20 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b0ca65632f2ce..86069b985d227 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1125,7 +1125,6 @@ struct kvm_hv {
 	 */
 	unsigned int synic_auto_eoi_used;
 
-	struct hv_partition_assist_pg *hv_pa_pg;
 	struct kvm_hv_syndbg hv_syndbg;
 };
 
@@ -1447,6 +1446,7 @@ struct kvm_arch {
 #if IS_ENABLED(CONFIG_HYPERV)
 	hpa_t	hv_root_tdp;
 	spinlock_t hv_root_tdp_lock;
+	struct hv_partition_assist_pg *hv_pa_pg;
 #endif
 	/*
 	 * VM-scope maximum vCPU ID. Used to determine the size of structures
diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h
index f9ca3e7432b2e..eefab3dc8498b 100644
--- a/arch/x86/kvm/kvm_onhyperv.h
+++ b/arch/x86/kvm/kvm_onhyperv.h
@@ -10,6 +10,26 @@
 int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages);
 int hv_flush_remote_tlbs(struct kvm *kvm);
 void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp);
+static inline hpa_t hv_get_partition_assist_page(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Partition assist page is something which Hyper-V running in L0
+	 * requires from KVM running in L1 before direct TLB flush for L2
+	 * guests can be enabled. KVM doesn't currently use the page but to
+	 * comply with TLFS it still needs to be allocated. For now, this
+	 * is a single page shared among all vCPUs.
+	 */
+	struct hv_partition_assist_pg **p_hv_pa_pg =
+		&vcpu->kvm->arch.hv_pa_pg;
+
+	if (!*p_hv_pa_pg)
+		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
+
+	if (!*p_hv_pa_pg)
+		return INVALID_PAGE;
+
+	return __pa(*p_hv_pa_pg);
+}
 #else /* !CONFIG_HYPERV */
 static inline int hv_flush_remote_tlbs(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c
index 7af8422d33821..3971b3ea5d04b 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.c
+++ b/arch/x86/kvm/svm/svm_onhyperv.c
@@ -18,18 +18,14 @@
 int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
 {
 	struct hv_vmcb_enlightenments *hve;
-	struct hv_partition_assist_pg **p_hv_pa_pg =
-			&to_kvm_hv(vcpu->kvm)->hv_pa_pg;
+	hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu);
 
-	if (!*p_hv_pa_pg)
-		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL);
-
-	if (!*p_hv_pa_pg)
+	if (partition_assist_page == INVALID_PAGE)
 		return -ENOMEM;
 
 	hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments;
 
-	hve->partition_assist_page = __pa(*p_hv_pa_pg);
+	hve->partition_assist_page = partition_assist_page;
 	hve->hv_vm_id = (unsigned long)vcpu->kvm;
 	if (!hve->hv_enlightenments_control.nested_flush_hypercall) {
 		hve->hv_enlightenments_control.nested_flush_hypercall = 1;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 40e3780d73aeb..cf19a33466396 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -523,22 +523,14 @@ module_param(enlightened_vmcs, bool, 0444);
 static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
 {
 	struct hv_enlightened_vmcs *evmcs;
-	struct hv_partition_assist_pg **p_hv_pa_pg =
-			&to_kvm_hv(vcpu->kvm)->hv_pa_pg;
-	/*
-	 * Synthetic VM-Exit is not enabled in current code and so All
-	 * evmcs in singe VM shares same assist page.
-	 */
-	if (!*p_hv_pa_pg)
-		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
+	hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu);
 
-	if (!*p_hv_pa_pg)
+	if (partition_assist_page == INVALID_PAGE)
 		return -ENOMEM;
 
 	evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs;
 
-	evmcs->partition_assist_page =
-		__pa(*p_hv_pa_pg);
+	evmcs->partition_assist_page = partition_assist_page;
 	evmcs->hv_vm_id = (unsigned long)vcpu->kvm;
 	evmcs->hv_enlightenments_control.nested_flush_hypercall = 1;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d0772b470413..81224b9676d99 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12438,7 +12438,9 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 
 void kvm_arch_free_vm(struct kvm *kvm)
 {
-	kfree(to_kvm_hv(kvm)->hv_pa_pg);
+#if IS_ENABLED(CONFIG_HYPERV)
+	kfree(kvm->arch.hv_pa_pg);
+#endif
 	__kvm_arch_free_vm(kvm);
 }
 
-- 
GitLab


From 50a82b0eb88c108d1ebc73a97f5b81df0d5918e0 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:17 +0100
Subject: [PATCH 0933/4076] KVM: VMX: Split off vmx_onhyperv.{ch} from
 hyperv.{ch}

hyperv.{ch} is currently a mix of stuff which is needed by both Hyper-V on
KVM and KVM on Hyper-V. As a preparation to making Hyper-V emulation
optional, put KVM-on-Hyper-V specific code into dedicated files.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-4-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/Makefile           |   4 +
 arch/x86/kvm/vmx/hyperv.c       | 139 --------------------
 arch/x86/kvm/vmx/hyperv.h       | 217 ++++++++++++++++----------------
 arch/x86/kvm/vmx/vmx.c          |   1 +
 arch/x86/kvm/vmx/vmx_onhyperv.c |  36 ++++++
 arch/x86/kvm/vmx/vmx_onhyperv.h | 124 ++++++++++++++++++
 arch/x86/kvm/vmx/vmx_ops.h      |   2 +-
 7 files changed, 271 insertions(+), 252 deletions(-)
 create mode 100644 arch/x86/kvm/vmx/vmx_onhyperv.c
 create mode 100644 arch/x86/kvm/vmx/vmx_onhyperv.h

diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 80e3fe184d17e..a99ffc3f3a3fd 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -26,6 +26,10 @@ kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
 			   vmx/hyperv.o vmx/nested.o vmx/posted_intr.o
 kvm-intel-$(CONFIG_X86_SGX_KVM)	+= vmx/sgx.o
 
+ifdef CONFIG_HYPERV
+kvm-intel-y		+= vmx/vmx_onhyperv.o
+endif
+
 kvm-amd-y		+= svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \
 			   svm/sev.o svm/hyperv.o
 
diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c
index 313b8bb5b8a7c..de13dc14fe1d2 100644
--- a/arch/x86/kvm/vmx/hyperv.c
+++ b/arch/x86/kvm/vmx/hyperv.c
@@ -13,111 +13,6 @@
 
 #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK
 
-/*
- * Enlightened VMCSv1 doesn't support these:
- *
- *	POSTED_INTR_NV                  = 0x00000002,
- *	GUEST_INTR_STATUS               = 0x00000810,
- *	APIC_ACCESS_ADDR		= 0x00002014,
- *	POSTED_INTR_DESC_ADDR           = 0x00002016,
- *	EOI_EXIT_BITMAP0                = 0x0000201c,
- *	EOI_EXIT_BITMAP1                = 0x0000201e,
- *	EOI_EXIT_BITMAP2                = 0x00002020,
- *	EOI_EXIT_BITMAP3                = 0x00002022,
- *	GUEST_PML_INDEX			= 0x00000812,
- *	PML_ADDRESS			= 0x0000200e,
- *	VM_FUNCTION_CONTROL             = 0x00002018,
- *	EPTP_LIST_ADDRESS               = 0x00002024,
- *	VMREAD_BITMAP                   = 0x00002026,
- *	VMWRITE_BITMAP                  = 0x00002028,
- *
- *	TSC_MULTIPLIER                  = 0x00002032,
- *	PLE_GAP                         = 0x00004020,
- *	PLE_WINDOW                      = 0x00004022,
- *	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
- *
- * Currently unsupported in KVM:
- *	GUEST_IA32_RTIT_CTL		= 0x00002814,
- */
-#define EVMCS1_SUPPORTED_PINCTRL					\
-	(PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 PIN_BASED_EXT_INTR_MASK |					\
-	 PIN_BASED_NMI_EXITING |					\
-	 PIN_BASED_VIRTUAL_NMIS)
-
-#define EVMCS1_SUPPORTED_EXEC_CTRL					\
-	(CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 CPU_BASED_HLT_EXITING |					\
-	 CPU_BASED_CR3_LOAD_EXITING |					\
-	 CPU_BASED_CR3_STORE_EXITING |					\
-	 CPU_BASED_UNCOND_IO_EXITING |					\
-	 CPU_BASED_MOV_DR_EXITING |					\
-	 CPU_BASED_USE_TSC_OFFSETTING |					\
-	 CPU_BASED_MWAIT_EXITING |					\
-	 CPU_BASED_MONITOR_EXITING |					\
-	 CPU_BASED_INVLPG_EXITING |					\
-	 CPU_BASED_RDPMC_EXITING |					\
-	 CPU_BASED_INTR_WINDOW_EXITING |				\
-	 CPU_BASED_CR8_LOAD_EXITING |					\
-	 CPU_BASED_CR8_STORE_EXITING |					\
-	 CPU_BASED_RDTSC_EXITING |					\
-	 CPU_BASED_TPR_SHADOW |						\
-	 CPU_BASED_USE_IO_BITMAPS |					\
-	 CPU_BASED_MONITOR_TRAP_FLAG |					\
-	 CPU_BASED_USE_MSR_BITMAPS |					\
-	 CPU_BASED_NMI_WINDOW_EXITING |					\
-	 CPU_BASED_PAUSE_EXITING |					\
-	 CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
-
-#define EVMCS1_SUPPORTED_2NDEXEC					\
-	(SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |			\
-	 SECONDARY_EXEC_WBINVD_EXITING |				\
-	 SECONDARY_EXEC_ENABLE_VPID |					\
-	 SECONDARY_EXEC_ENABLE_EPT |					\
-	 SECONDARY_EXEC_UNRESTRICTED_GUEST |				\
-	 SECONDARY_EXEC_DESC |						\
-	 SECONDARY_EXEC_ENABLE_RDTSCP |					\
-	 SECONDARY_EXEC_ENABLE_INVPCID |				\
-	 SECONDARY_EXEC_ENABLE_XSAVES |					\
-	 SECONDARY_EXEC_RDSEED_EXITING |				\
-	 SECONDARY_EXEC_RDRAND_EXITING |				\
-	 SECONDARY_EXEC_TSC_SCALING |					\
-	 SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |				\
-	 SECONDARY_EXEC_PT_USE_GPA |					\
-	 SECONDARY_EXEC_PT_CONCEAL_VMX |				\
-	 SECONDARY_EXEC_BUS_LOCK_DETECTION |				\
-	 SECONDARY_EXEC_NOTIFY_VM_EXITING |				\
-	 SECONDARY_EXEC_ENCLS_EXITING)
-
-#define EVMCS1_SUPPORTED_3RDEXEC (0ULL)
-
-#define EVMCS1_SUPPORTED_VMEXIT_CTRL					\
-	(VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 VM_EXIT_SAVE_DEBUG_CONTROLS |					\
-	 VM_EXIT_ACK_INTR_ON_EXIT |					\
-	 VM_EXIT_HOST_ADDR_SPACE_SIZE |					\
-	 VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |				\
-	 VM_EXIT_SAVE_IA32_PAT |					\
-	 VM_EXIT_LOAD_IA32_PAT |					\
-	 VM_EXIT_SAVE_IA32_EFER |					\
-	 VM_EXIT_LOAD_IA32_EFER |					\
-	 VM_EXIT_CLEAR_BNDCFGS |					\
-	 VM_EXIT_PT_CONCEAL_PIP |					\
-	 VM_EXIT_CLEAR_IA32_RTIT_CTL)
-
-#define EVMCS1_SUPPORTED_VMENTRY_CTRL					\
-	(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 VM_ENTRY_LOAD_DEBUG_CONTROLS |					\
-	 VM_ENTRY_IA32E_MODE |						\
-	 VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |				\
-	 VM_ENTRY_LOAD_IA32_PAT |					\
-	 VM_ENTRY_LOAD_IA32_EFER |					\
-	 VM_ENTRY_LOAD_BNDCFGS |					\
-	 VM_ENTRY_PT_CONCEAL_PIP |					\
-	 VM_ENTRY_LOAD_IA32_RTIT_CTL)
-
-#define EVMCS1_SUPPORTED_VMFUNC (0)
-
 #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x)
 #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \
 		{EVMCS1_OFFSET(name), clean_field}
@@ -608,40 +503,6 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_HYPERV)
-DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs);
-
-/*
- * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption
- * is: in case a feature has corresponding fields in eVMCS described and it was
- * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a
- * feature which has no corresponding eVMCS field, this likely means that KVM
- * needs to be updated.
- */
-#define evmcs_check_vmcs_conf(field, ctrl)					\
-	do {									\
-		typeof(vmcs_conf->field) unsupported;				\
-										\
-		unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl;	\
-		if (unsupported) {						\
-			pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\
-				     (u64)unsupported);				\
-			vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl;		\
-		}								\
-	}									\
-	while (0)
-
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
-{
-	evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL);
-	evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL);
-	evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC);
-	evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC);
-	evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL);
-	evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL);
-}
-#endif
-
 int nested_enable_evmcs(struct kvm_vcpu *vcpu,
 			uint16_t *vmcs_version)
 {
diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h
index 9623fe1651c48..9401dbfaea7ce 100644
--- a/arch/x86/kvm/vmx/hyperv.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -14,12 +14,113 @@
 #include "vmcs.h"
 #include "vmcs12.h"
 
-struct vmcs_config;
-
-#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs))
-
 #define KVM_EVMCS_VERSION 1
 
+/*
+ * Enlightened VMCSv1 doesn't support these:
+ *
+ *	POSTED_INTR_NV                  = 0x00000002,
+ *	GUEST_INTR_STATUS               = 0x00000810,
+ *	APIC_ACCESS_ADDR		= 0x00002014,
+ *	POSTED_INTR_DESC_ADDR           = 0x00002016,
+ *	EOI_EXIT_BITMAP0                = 0x0000201c,
+ *	EOI_EXIT_BITMAP1                = 0x0000201e,
+ *	EOI_EXIT_BITMAP2                = 0x00002020,
+ *	EOI_EXIT_BITMAP3                = 0x00002022,
+ *	GUEST_PML_INDEX			= 0x00000812,
+ *	PML_ADDRESS			= 0x0000200e,
+ *	VM_FUNCTION_CONTROL             = 0x00002018,
+ *	EPTP_LIST_ADDRESS               = 0x00002024,
+ *	VMREAD_BITMAP                   = 0x00002026,
+ *	VMWRITE_BITMAP                  = 0x00002028,
+ *
+ *	TSC_MULTIPLIER                  = 0x00002032,
+ *	PLE_GAP                         = 0x00004020,
+ *	PLE_WINDOW                      = 0x00004022,
+ *	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
+ *
+ * Currently unsupported in KVM:
+ *	GUEST_IA32_RTIT_CTL		= 0x00002814,
+ */
+#define EVMCS1_SUPPORTED_PINCTRL					\
+	(PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 PIN_BASED_EXT_INTR_MASK |					\
+	 PIN_BASED_NMI_EXITING |					\
+	 PIN_BASED_VIRTUAL_NMIS)
+
+#define EVMCS1_SUPPORTED_EXEC_CTRL					\
+	(CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 CPU_BASED_HLT_EXITING |					\
+	 CPU_BASED_CR3_LOAD_EXITING |					\
+	 CPU_BASED_CR3_STORE_EXITING |					\
+	 CPU_BASED_UNCOND_IO_EXITING |					\
+	 CPU_BASED_MOV_DR_EXITING |					\
+	 CPU_BASED_USE_TSC_OFFSETTING |					\
+	 CPU_BASED_MWAIT_EXITING |					\
+	 CPU_BASED_MONITOR_EXITING |					\
+	 CPU_BASED_INVLPG_EXITING |					\
+	 CPU_BASED_RDPMC_EXITING |					\
+	 CPU_BASED_INTR_WINDOW_EXITING |				\
+	 CPU_BASED_CR8_LOAD_EXITING |					\
+	 CPU_BASED_CR8_STORE_EXITING |					\
+	 CPU_BASED_RDTSC_EXITING |					\
+	 CPU_BASED_TPR_SHADOW |						\
+	 CPU_BASED_USE_IO_BITMAPS |					\
+	 CPU_BASED_MONITOR_TRAP_FLAG |					\
+	 CPU_BASED_USE_MSR_BITMAPS |					\
+	 CPU_BASED_NMI_WINDOW_EXITING |					\
+	 CPU_BASED_PAUSE_EXITING |					\
+	 CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
+
+#define EVMCS1_SUPPORTED_2NDEXEC					\
+	(SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |			\
+	 SECONDARY_EXEC_WBINVD_EXITING |				\
+	 SECONDARY_EXEC_ENABLE_VPID |					\
+	 SECONDARY_EXEC_ENABLE_EPT |					\
+	 SECONDARY_EXEC_UNRESTRICTED_GUEST |				\
+	 SECONDARY_EXEC_DESC |						\
+	 SECONDARY_EXEC_ENABLE_RDTSCP |					\
+	 SECONDARY_EXEC_ENABLE_INVPCID |				\
+	 SECONDARY_EXEC_ENABLE_XSAVES |					\
+	 SECONDARY_EXEC_RDSEED_EXITING |				\
+	 SECONDARY_EXEC_RDRAND_EXITING |				\
+	 SECONDARY_EXEC_TSC_SCALING |					\
+	 SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |				\
+	 SECONDARY_EXEC_PT_USE_GPA |					\
+	 SECONDARY_EXEC_PT_CONCEAL_VMX |				\
+	 SECONDARY_EXEC_BUS_LOCK_DETECTION |				\
+	 SECONDARY_EXEC_NOTIFY_VM_EXITING |				\
+	 SECONDARY_EXEC_ENCLS_EXITING)
+
+#define EVMCS1_SUPPORTED_3RDEXEC (0ULL)
+
+#define EVMCS1_SUPPORTED_VMEXIT_CTRL					\
+	(VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 VM_EXIT_SAVE_DEBUG_CONTROLS |					\
+	 VM_EXIT_ACK_INTR_ON_EXIT |					\
+	 VM_EXIT_HOST_ADDR_SPACE_SIZE |					\
+	 VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |				\
+	 VM_EXIT_SAVE_IA32_PAT |					\
+	 VM_EXIT_LOAD_IA32_PAT |					\
+	 VM_EXIT_SAVE_IA32_EFER |					\
+	 VM_EXIT_LOAD_IA32_EFER |					\
+	 VM_EXIT_CLEAR_BNDCFGS |					\
+	 VM_EXIT_PT_CONCEAL_PIP |					\
+	 VM_EXIT_CLEAR_IA32_RTIT_CTL)
+
+#define EVMCS1_SUPPORTED_VMENTRY_CTRL					\
+	(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 VM_ENTRY_LOAD_DEBUG_CONTROLS |					\
+	 VM_ENTRY_IA32E_MODE |						\
+	 VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |				\
+	 VM_ENTRY_LOAD_IA32_PAT |					\
+	 VM_ENTRY_LOAD_IA32_EFER |					\
+	 VM_ENTRY_LOAD_BNDCFGS |					\
+	 VM_ENTRY_PT_CONCEAL_PIP |					\
+	 VM_ENTRY_LOAD_IA32_RTIT_CTL)
+
+#define EVMCS1_SUPPORTED_VMFUNC (0)
+
 struct evmcs_field {
 	u16 offset;
 	u16 clean_field;
@@ -65,114 +166,6 @@ static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs,
 	return vmcs12_read_any((void *)evmcs, field, offset);
 }
 
-#if IS_ENABLED(CONFIG_HYPERV)
-
-DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs);
-
-static __always_inline bool kvm_is_using_evmcs(void)
-{
-	return static_branch_unlikely(&__kvm_is_using_evmcs);
-}
-
-static __always_inline int get_evmcs_offset(unsigned long field,
-					    u16 *clean_field)
-{
-	int offset = evmcs_field_offset(field, clean_field);
-
-	WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field);
-	return offset;
-}
-
-static __always_inline void evmcs_write64(unsigned long field, u64 value)
-{
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u64 *)((char *)current_evmcs + offset) = value;
-
-	current_evmcs->hv_clean_fields &= ~clean_field;
-}
-
-static __always_inline void evmcs_write32(unsigned long field, u32 value)
-{
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u32 *)((char *)current_evmcs + offset) = value;
-	current_evmcs->hv_clean_fields &= ~clean_field;
-}
-
-static __always_inline void evmcs_write16(unsigned long field, u16 value)
-{
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u16 *)((char *)current_evmcs + offset) = value;
-	current_evmcs->hv_clean_fields &= ~clean_field;
-}
-
-static __always_inline u64 evmcs_read64(unsigned long field)
-{
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u64 *)((char *)current_evmcs + offset);
-}
-
-static __always_inline u32 evmcs_read32(unsigned long field)
-{
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u32 *)((char *)current_evmcs + offset);
-}
-
-static __always_inline u16 evmcs_read16(unsigned long field)
-{
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u16 *)((char *)current_evmcs + offset);
-}
-
-static inline void evmcs_load(u64 phys_addr)
-{
-	struct hv_vp_assist_page *vp_ap =
-		hv_get_vp_assist_page(smp_processor_id());
-
-	if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall)
-		vp_ap->nested_control.features.directhypercall = 1;
-	vp_ap->current_nested_vmcs = phys_addr;
-	vp_ap->enlighten_vmentry = 1;
-}
-
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
-#else /* !IS_ENABLED(CONFIG_HYPERV) */
-static __always_inline bool kvm_is_using_evmcs(void) { return false; }
-static __always_inline void evmcs_write64(unsigned long field, u64 value) {}
-static __always_inline void evmcs_write32(unsigned long field, u32 value) {}
-static __always_inline void evmcs_write16(unsigned long field, u16 value) {}
-static __always_inline u64 evmcs_read64(unsigned long field) { return 0; }
-static __always_inline u32 evmcs_read32(unsigned long field) { return 0; }
-static __always_inline u16 evmcs_read16(unsigned long field) { return 0; }
-static inline void evmcs_load(u64 phys_addr) {}
-#endif /* IS_ENABLED(CONFIG_HYPERV) */
-
 #define EVMPTR_INVALID (-1ULL)
 #define EVMPTR_MAP_PENDING (-2ULL)
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index cf19a33466396..552593a2ac148 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -66,6 +66,7 @@
 #include "vmx.h"
 #include "x86.h"
 #include "smm.h"
+#include "vmx_onhyperv.h"
 
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.c b/arch/x86/kvm/vmx/vmx_onhyperv.c
new file mode 100644
index 0000000000000..b9a8b91166d02
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmx_onhyperv.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "capabilities.h"
+#include "vmx_onhyperv.h"
+
+DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs);
+
+/*
+ * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption
+ * is: in case a feature has corresponding fields in eVMCS described and it was
+ * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a
+ * feature which has no corresponding eVMCS field, this likely means that KVM
+ * needs to be updated.
+ */
+#define evmcs_check_vmcs_conf(field, ctrl)					\
+	do {									\
+		typeof(vmcs_conf->field) unsupported;				\
+										\
+		unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl;	\
+		if (unsupported) {						\
+			pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\
+				     (u64)unsupported);				\
+			vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl;		\
+		}								\
+	}									\
+	while (0)
+
+void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
+{
+	evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL);
+	evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL);
+	evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC);
+	evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC);
+	evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL);
+	evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL);
+}
diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h
new file mode 100644
index 0000000000000..11541d272dbd8
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmx_onhyperv.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__
+#define __ARCH_X86_KVM_VMX_ONHYPERV_H__
+
+#include <asm/hyperv-tlfs.h>
+
+#include <linux/jump_label.h>
+
+#include "capabilities.h"
+#include "hyperv.h"
+#include "vmcs12.h"
+
+#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs))
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs);
+
+static __always_inline bool kvm_is_using_evmcs(void)
+{
+	return static_branch_unlikely(&__kvm_is_using_evmcs);
+}
+
+static __always_inline int get_evmcs_offset(unsigned long field,
+					    u16 *clean_field)
+{
+	int offset = evmcs_field_offset(field, clean_field);
+
+	WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field);
+	return offset;
+}
+
+static __always_inline void evmcs_write64(unsigned long field, u64 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u64 *)((char *)current_evmcs + offset) = value;
+
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static __always_inline void evmcs_write32(unsigned long field, u32 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u32 *)((char *)current_evmcs + offset) = value;
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static __always_inline void evmcs_write16(unsigned long field, u16 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u16 *)((char *)current_evmcs + offset) = value;
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static __always_inline u64 evmcs_read64(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u64 *)((char *)current_evmcs + offset);
+}
+
+static __always_inline u32 evmcs_read32(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u32 *)((char *)current_evmcs + offset);
+}
+
+static __always_inline u16 evmcs_read16(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u16 *)((char *)current_evmcs + offset);
+}
+
+static inline void evmcs_load(u64 phys_addr)
+{
+	struct hv_vp_assist_page *vp_ap =
+		hv_get_vp_assist_page(smp_processor_id());
+
+	if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall)
+		vp_ap->nested_control.features.directhypercall = 1;
+	vp_ap->current_nested_vmcs = phys_addr;
+	vp_ap->enlighten_vmentry = 1;
+}
+
+void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
+#else /* !IS_ENABLED(CONFIG_HYPERV) */
+static __always_inline bool kvm_is_using_evmcs(void) { return false; }
+static __always_inline void evmcs_write64(unsigned long field, u64 value) {}
+static __always_inline void evmcs_write32(unsigned long field, u32 value) {}
+static __always_inline void evmcs_write16(unsigned long field, u16 value) {}
+static __always_inline u64 evmcs_read64(unsigned long field) { return 0; }
+static __always_inline u32 evmcs_read32(unsigned long field) { return 0; }
+static __always_inline u16 evmcs_read16(unsigned long field) { return 0; }
+static inline void evmcs_load(u64 phys_addr) {}
+#endif /* IS_ENABLED(CONFIG_HYPERV) */
+
+#endif /* __ARCH_X86_KVM_VMX_ONHYPERV_H__ */
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index 33af7b4c6eb4a..f41ce3c24123a 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -6,7 +6,7 @@
 
 #include <asm/vmx.h>
 
-#include "hyperv.h"
+#include "vmx_onhyperv.h"
 #include "vmcs.h"
 #include "../x86.h"
 
-- 
GitLab


From 16e880bfa6377871da233c846ecdf23db2bf1d97 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:18 +0100
Subject: [PATCH 0934/4076] KVM: x86: Introduce helper to check if auto-EOI is
 set in Hyper-V SynIC

As a preparation to making Hyper-V emulation optional, create a dedicated
kvm_hv_synic_auto_eoi_set() helper to avoid extra ifdefs in lapic.c

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-5-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/hyperv.h | 6 ++++++
 arch/x86/kvm/lapic.c  | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index f83b8db72b118..286956fe1a2e8 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -105,6 +105,12 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
 void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
 int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
 
+static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector)
+{
+	return to_hv_vcpu(vcpu) &&
+	       test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap);
+}
+
 void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
 
 bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 245b20973caee..f7abc1008cadf 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2905,7 +2905,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	 */
 
 	apic_clear_irr(vector, apic);
-	if (to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap)) {
+	if (kvm_hv_synic_auto_eoi_set(vcpu, vector)) {
 		/*
 		 * For auto-EOI interrupts, there might be another pending
 		 * interrupt above PPR, so check whether to raise another
-- 
GitLab


From 0659262a2625ca3e4061796cd4f4935091220056 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:19 +0100
Subject: [PATCH 0935/4076] KVM: x86: Introduce helper to check if vector is
 set in Hyper-V SynIC

As a preparation to making Hyper-V emulation optional, create a dedicated
kvm_hv_synic_has_vector() helper to avoid extra ifdefs in lapic.c.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-6-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/hyperv.h | 5 +++++
 arch/x86/kvm/lapic.c  | 3 +--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 286956fe1a2e8..9d8fa6ba63413 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -105,6 +105,11 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
 void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
 int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
 
+static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector)
+{
+	return to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->vec_bitmap);
+}
+
 static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector)
 {
 	return to_hv_vcpu(vcpu) &&
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index f7abc1008cadf..3242f3da24576 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1475,8 +1475,7 @@ static int apic_set_eoi(struct kvm_lapic *apic)
 	apic_clear_isr(vector, apic);
 	apic_update_ppr(apic);
 
-	if (to_hv_vcpu(apic->vcpu) &&
-	    test_bit(vector, to_hv_synic(apic->vcpu)->vec_bitmap))
+	if (kvm_hv_synic_has_vector(apic->vcpu, vector))
 		kvm_hv_synic_send_eoi(apic->vcpu, vector);
 
 	kvm_ioapic_send_eoi(apic, vector);
-- 
GitLab


From e7ad84db4d718e18c7a133e941ba4c7d4c6d4cbf Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:20 +0100
Subject: [PATCH 0936/4076] KVM: VMX: Split off hyperv_evmcs.{ch}

Some Enlightened VMCS related code is needed both by Hyper-V on KVM and
KVM on Hyper-V. As a preparation to making Hyper-V emulation optional,
create dedicated 'hyperv_evmcs.{ch}' files which are used by both.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-7-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/Makefile           |   2 +-
 arch/x86/kvm/vmx/hyperv.c       | 308 -------------------------------
 arch/x86/kvm/vmx/hyperv.h       | 163 +----------------
 arch/x86/kvm/vmx/hyperv_evmcs.c | 315 ++++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/hyperv_evmcs.h | 166 +++++++++++++++++
 arch/x86/kvm/vmx/nested.h       |   1 +
 arch/x86/kvm/vmx/vmx_onhyperv.h |   3 +-
 7 files changed, 486 insertions(+), 472 deletions(-)
 create mode 100644 arch/x86/kvm/vmx/hyperv_evmcs.c
 create mode 100644 arch/x86/kvm/vmx/hyperv_evmcs.h

diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index a99ffc3f3a3fd..8ea872401cd67 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -23,7 +23,7 @@ kvm-$(CONFIG_KVM_XEN)	+= xen.o
 kvm-$(CONFIG_KVM_SMM)	+= smm.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
-			   vmx/hyperv.o vmx/nested.o vmx/posted_intr.o
+			   vmx/hyperv.o vmx/hyperv_evmcs.o vmx/nested.o vmx/posted_intr.o
 kvm-intel-$(CONFIG_X86_SGX_KVM)	+= vmx/sgx.o
 
 ifdef CONFIG_HYPERV
diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c
index de13dc14fe1d2..fab6a1ad98dc1 100644
--- a/arch/x86/kvm/vmx/hyperv.c
+++ b/arch/x86/kvm/vmx/hyperv.c
@@ -13,314 +13,6 @@
 
 #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK
 
-#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x)
-#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \
-		{EVMCS1_OFFSET(name), clean_field}
-
-const struct evmcs_field vmcs_field_to_evmcs_1[] = {
-	/* 64 bit rw */
-	EVMCS1_FIELD(GUEST_RIP, guest_rip,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(GUEST_RSP, guest_rsp,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
-	EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
-	EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_CR0, host_cr0,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_CR3, host_cr3,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_CR4, host_cr4,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_RIP, host_rip,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP),
-	EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP),
-	EVMCS1_FIELD(MSR_BITMAP, msr_bitmap,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP),
-	EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(TSC_OFFSET, tsc_offset,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(GUEST_CR0, guest_cr0,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(GUEST_CR3, guest_cr3,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(GUEST_CR4, guest_cr4,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(GUEST_DR7, guest_dr7,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
-	EVMCS1_FIELD(HOST_FS_BASE, host_fs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_GS_BASE, host_gs_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_TR_BASE, host_tr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(HOST_RSP, host_rsp,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
-	EVMCS1_FIELD(EPT_POINTER, ept_pointer,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
-	EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
-	/*
-	 * Not used by KVM:
-	 *
-	 * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	 * EVMCS1_FIELD(0x0000682A, guest_ssp,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
-	 * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	 * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	 * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	 * EVMCS1_FIELD(0x00006C1A, host_ssp,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	 * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr,
-	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	 */
-
-	/* 64 bit read only */
-	EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	/*
-	 * Not defined in KVM:
-	 *
-	 * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx,
-	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
-	 * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi,
-	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
-	 * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi,
-	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
-	 * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip,
-	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
-	 */
-	EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-
-	/*
-	 * No mask defined in the spec as Hyper-V doesn't currently support
-	 * these. Future proof by resetting the whole clean field mask on
-	 * access.
-	 */
-	EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-
-	/* 32 bit rw */
-	EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
-	EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC),
-	EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN),
-	EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY),
-	EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
-	EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE,
-		     vm_entry_exception_error_code,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
-	EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
-	EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
-	EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
-	EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
-	EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-	EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
-
-	/* 32 bit read only */
-	EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-	EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
-
-	/* No mask defined in the spec (not used) */
-	EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-	EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
-
-	/* 16 bit rw */
-	EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
-	EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
-	EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id,
-		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
-};
-const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
-
 u64 nested_get_evmptr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h
index 9401dbfaea7ce..d4ed99008518c 100644
--- a/arch/x86/kvm/vmx/hyperv.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -2,170 +2,9 @@
 #ifndef __KVM_X86_VMX_HYPERV_H
 #define __KVM_X86_VMX_HYPERV_H
 
-#include <linux/jump_label.h>
-
-#include <asm/hyperv-tlfs.h>
-#include <asm/mshyperv.h>
-#include <asm/vmx.h>
-
-#include "../hyperv.h"
-
-#include "capabilities.h"
-#include "vmcs.h"
+#include <linux/kvm_host.h>
 #include "vmcs12.h"
 
-#define KVM_EVMCS_VERSION 1
-
-/*
- * Enlightened VMCSv1 doesn't support these:
- *
- *	POSTED_INTR_NV                  = 0x00000002,
- *	GUEST_INTR_STATUS               = 0x00000810,
- *	APIC_ACCESS_ADDR		= 0x00002014,
- *	POSTED_INTR_DESC_ADDR           = 0x00002016,
- *	EOI_EXIT_BITMAP0                = 0x0000201c,
- *	EOI_EXIT_BITMAP1                = 0x0000201e,
- *	EOI_EXIT_BITMAP2                = 0x00002020,
- *	EOI_EXIT_BITMAP3                = 0x00002022,
- *	GUEST_PML_INDEX			= 0x00000812,
- *	PML_ADDRESS			= 0x0000200e,
- *	VM_FUNCTION_CONTROL             = 0x00002018,
- *	EPTP_LIST_ADDRESS               = 0x00002024,
- *	VMREAD_BITMAP                   = 0x00002026,
- *	VMWRITE_BITMAP                  = 0x00002028,
- *
- *	TSC_MULTIPLIER                  = 0x00002032,
- *	PLE_GAP                         = 0x00004020,
- *	PLE_WINDOW                      = 0x00004022,
- *	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
- *
- * Currently unsupported in KVM:
- *	GUEST_IA32_RTIT_CTL		= 0x00002814,
- */
-#define EVMCS1_SUPPORTED_PINCTRL					\
-	(PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 PIN_BASED_EXT_INTR_MASK |					\
-	 PIN_BASED_NMI_EXITING |					\
-	 PIN_BASED_VIRTUAL_NMIS)
-
-#define EVMCS1_SUPPORTED_EXEC_CTRL					\
-	(CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 CPU_BASED_HLT_EXITING |					\
-	 CPU_BASED_CR3_LOAD_EXITING |					\
-	 CPU_BASED_CR3_STORE_EXITING |					\
-	 CPU_BASED_UNCOND_IO_EXITING |					\
-	 CPU_BASED_MOV_DR_EXITING |					\
-	 CPU_BASED_USE_TSC_OFFSETTING |					\
-	 CPU_BASED_MWAIT_EXITING |					\
-	 CPU_BASED_MONITOR_EXITING |					\
-	 CPU_BASED_INVLPG_EXITING |					\
-	 CPU_BASED_RDPMC_EXITING |					\
-	 CPU_BASED_INTR_WINDOW_EXITING |				\
-	 CPU_BASED_CR8_LOAD_EXITING |					\
-	 CPU_BASED_CR8_STORE_EXITING |					\
-	 CPU_BASED_RDTSC_EXITING |					\
-	 CPU_BASED_TPR_SHADOW |						\
-	 CPU_BASED_USE_IO_BITMAPS |					\
-	 CPU_BASED_MONITOR_TRAP_FLAG |					\
-	 CPU_BASED_USE_MSR_BITMAPS |					\
-	 CPU_BASED_NMI_WINDOW_EXITING |					\
-	 CPU_BASED_PAUSE_EXITING |					\
-	 CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
-
-#define EVMCS1_SUPPORTED_2NDEXEC					\
-	(SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |			\
-	 SECONDARY_EXEC_WBINVD_EXITING |				\
-	 SECONDARY_EXEC_ENABLE_VPID |					\
-	 SECONDARY_EXEC_ENABLE_EPT |					\
-	 SECONDARY_EXEC_UNRESTRICTED_GUEST |				\
-	 SECONDARY_EXEC_DESC |						\
-	 SECONDARY_EXEC_ENABLE_RDTSCP |					\
-	 SECONDARY_EXEC_ENABLE_INVPCID |				\
-	 SECONDARY_EXEC_ENABLE_XSAVES |					\
-	 SECONDARY_EXEC_RDSEED_EXITING |				\
-	 SECONDARY_EXEC_RDRAND_EXITING |				\
-	 SECONDARY_EXEC_TSC_SCALING |					\
-	 SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |				\
-	 SECONDARY_EXEC_PT_USE_GPA |					\
-	 SECONDARY_EXEC_PT_CONCEAL_VMX |				\
-	 SECONDARY_EXEC_BUS_LOCK_DETECTION |				\
-	 SECONDARY_EXEC_NOTIFY_VM_EXITING |				\
-	 SECONDARY_EXEC_ENCLS_EXITING)
-
-#define EVMCS1_SUPPORTED_3RDEXEC (0ULL)
-
-#define EVMCS1_SUPPORTED_VMEXIT_CTRL					\
-	(VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 VM_EXIT_SAVE_DEBUG_CONTROLS |					\
-	 VM_EXIT_ACK_INTR_ON_EXIT |					\
-	 VM_EXIT_HOST_ADDR_SPACE_SIZE |					\
-	 VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |				\
-	 VM_EXIT_SAVE_IA32_PAT |					\
-	 VM_EXIT_LOAD_IA32_PAT |					\
-	 VM_EXIT_SAVE_IA32_EFER |					\
-	 VM_EXIT_LOAD_IA32_EFER |					\
-	 VM_EXIT_CLEAR_BNDCFGS |					\
-	 VM_EXIT_PT_CONCEAL_PIP |					\
-	 VM_EXIT_CLEAR_IA32_RTIT_CTL)
-
-#define EVMCS1_SUPPORTED_VMENTRY_CTRL					\
-	(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |				\
-	 VM_ENTRY_LOAD_DEBUG_CONTROLS |					\
-	 VM_ENTRY_IA32E_MODE |						\
-	 VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |				\
-	 VM_ENTRY_LOAD_IA32_PAT |					\
-	 VM_ENTRY_LOAD_IA32_EFER |					\
-	 VM_ENTRY_LOAD_BNDCFGS |					\
-	 VM_ENTRY_PT_CONCEAL_PIP |					\
-	 VM_ENTRY_LOAD_IA32_RTIT_CTL)
-
-#define EVMCS1_SUPPORTED_VMFUNC (0)
-
-struct evmcs_field {
-	u16 offset;
-	u16 clean_field;
-};
-
-extern const struct evmcs_field vmcs_field_to_evmcs_1[];
-extern const unsigned int nr_evmcs_1_fields;
-
-static __always_inline int evmcs_field_offset(unsigned long field,
-					      u16 *clean_field)
-{
-	unsigned int index = ROL16(field, 6);
-	const struct evmcs_field *evmcs_field;
-
-	if (unlikely(index >= nr_evmcs_1_fields))
-		return -ENOENT;
-
-	evmcs_field = &vmcs_field_to_evmcs_1[index];
-
-	/*
-	 * Use offset=0 to detect holes in eVMCS. This offset belongs to
-	 * 'revision_id' but this field has no encoding and is supposed to
-	 * be accessed directly.
-	 */
-	if (unlikely(!evmcs_field->offset))
-		return -ENOENT;
-
-	if (clean_field)
-		*clean_field = evmcs_field->clean_field;
-
-	return evmcs_field->offset;
-}
-
-static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs,
-				 unsigned long field, u16 offset)
-{
-	/*
-	 * vmcs12_read_any() doesn't care whether the supplied structure
-	 * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes
-	 * the exact offset of the required field, use it for convenience
-	 * here.
-	 */
-	return vmcs12_read_any((void *)evmcs, field, offset);
-}
-
 #define EVMPTR_INVALID (-1ULL)
 #define EVMPTR_MAP_PENDING (-2ULL)
 
diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.c b/arch/x86/kvm/vmx/hyperv_evmcs.c
new file mode 100644
index 0000000000000..904bfcd1519b0
--- /dev/null
+++ b/arch/x86/kvm/vmx/hyperv_evmcs.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains common code for working with Enlightened VMCS which is
+ * used both by Hyper-V on KVM and KVM on Hyper-V.
+ */
+
+#include "hyperv_evmcs.h"
+
+#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x)
+#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \
+		{EVMCS1_OFFSET(name), clean_field}
+
+const struct evmcs_field vmcs_field_to_evmcs_1[] = {
+	/* 64 bit rw */
+	EVMCS1_FIELD(GUEST_RIP, guest_rip,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(GUEST_RSP, guest_rsp,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+	EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+	EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_CR0, host_cr0,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_CR3, host_cr3,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_CR4, host_cr4,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_RIP, host_rip,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP),
+	EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP),
+	EVMCS1_FIELD(MSR_BITMAP, msr_bitmap,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP),
+	EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(TSC_OFFSET, tsc_offset,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(GUEST_CR0, guest_cr0,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(GUEST_CR3, guest_cr3,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(GUEST_CR4, guest_cr4,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(GUEST_DR7, guest_dr7,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR),
+	EVMCS1_FIELD(HOST_FS_BASE, host_fs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_GS_BASE, host_gs_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_TR_BASE, host_tr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(HOST_RSP, host_rsp,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER),
+	EVMCS1_FIELD(EPT_POINTER, ept_pointer,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
+	EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+	/*
+	 * Not used by KVM:
+	 *
+	 * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	 * EVMCS1_FIELD(0x0000682A, guest_ssp,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+	 * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	 * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	 * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	 * EVMCS1_FIELD(0x00006C1A, host_ssp,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	 * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr,
+	 *	     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	 */
+
+	/* 64 bit read only */
+	EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	/*
+	 * Not defined in KVM:
+	 *
+	 * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx,
+	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
+	 * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi,
+	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
+	 * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi,
+	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
+	 * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip,
+	 *		HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE);
+	 */
+	EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+
+	/*
+	 * No mask defined in the spec as Hyper-V doesn't currently support
+	 * these. Future proof by resetting the whole clean field mask on
+	 * access.
+	 */
+	EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+
+	/* 32 bit rw */
+	EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+	EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC),
+	EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN),
+	EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY),
+	EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
+	EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE,
+		     vm_entry_exception_error_code,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
+	EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT),
+	EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
+	EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
+	EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1),
+	EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+	EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+
+	/* 32 bit read only */
+	EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+	EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
+
+	/* No mask defined in the spec (not used) */
+	EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+	EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL),
+
+	/* 16 bit rw */
+	EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+	EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2),
+	EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id,
+		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
+};
+const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h
new file mode 100644
index 0000000000000..a543fccfc5747
--- /dev/null
+++ b/arch/x86/kvm/vmx/hyperv_evmcs.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file contains common definitions for working with Enlightened VMCS which
+ * are used both by Hyper-V on KVM and KVM on Hyper-V.
+ */
+#ifndef __KVM_X86_VMX_HYPERV_EVMCS_H
+#define __KVM_X86_VMX_HYPERV_EVMCS_H
+
+#include <asm/hyperv-tlfs.h>
+
+#include "capabilities.h"
+#include "vmcs12.h"
+
+#define KVM_EVMCS_VERSION 1
+
+/*
+ * Enlightened VMCSv1 doesn't support these:
+ *
+ *	POSTED_INTR_NV                  = 0x00000002,
+ *	GUEST_INTR_STATUS               = 0x00000810,
+ *	APIC_ACCESS_ADDR		= 0x00002014,
+ *	POSTED_INTR_DESC_ADDR           = 0x00002016,
+ *	EOI_EXIT_BITMAP0                = 0x0000201c,
+ *	EOI_EXIT_BITMAP1                = 0x0000201e,
+ *	EOI_EXIT_BITMAP2                = 0x00002020,
+ *	EOI_EXIT_BITMAP3                = 0x00002022,
+ *	GUEST_PML_INDEX			= 0x00000812,
+ *	PML_ADDRESS			= 0x0000200e,
+ *	VM_FUNCTION_CONTROL             = 0x00002018,
+ *	EPTP_LIST_ADDRESS               = 0x00002024,
+ *	VMREAD_BITMAP                   = 0x00002026,
+ *	VMWRITE_BITMAP                  = 0x00002028,
+ *
+ *	TSC_MULTIPLIER                  = 0x00002032,
+ *	PLE_GAP                         = 0x00004020,
+ *	PLE_WINDOW                      = 0x00004022,
+ *	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
+ *
+ * Currently unsupported in KVM:
+ *	GUEST_IA32_RTIT_CTL		= 0x00002814,
+ */
+#define EVMCS1_SUPPORTED_PINCTRL					\
+	(PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 PIN_BASED_EXT_INTR_MASK |					\
+	 PIN_BASED_NMI_EXITING |					\
+	 PIN_BASED_VIRTUAL_NMIS)
+
+#define EVMCS1_SUPPORTED_EXEC_CTRL					\
+	(CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 CPU_BASED_HLT_EXITING |					\
+	 CPU_BASED_CR3_LOAD_EXITING |					\
+	 CPU_BASED_CR3_STORE_EXITING |					\
+	 CPU_BASED_UNCOND_IO_EXITING |					\
+	 CPU_BASED_MOV_DR_EXITING |					\
+	 CPU_BASED_USE_TSC_OFFSETTING |					\
+	 CPU_BASED_MWAIT_EXITING |					\
+	 CPU_BASED_MONITOR_EXITING |					\
+	 CPU_BASED_INVLPG_EXITING |					\
+	 CPU_BASED_RDPMC_EXITING |					\
+	 CPU_BASED_INTR_WINDOW_EXITING |				\
+	 CPU_BASED_CR8_LOAD_EXITING |					\
+	 CPU_BASED_CR8_STORE_EXITING |					\
+	 CPU_BASED_RDTSC_EXITING |					\
+	 CPU_BASED_TPR_SHADOW |						\
+	 CPU_BASED_USE_IO_BITMAPS |					\
+	 CPU_BASED_MONITOR_TRAP_FLAG |					\
+	 CPU_BASED_USE_MSR_BITMAPS |					\
+	 CPU_BASED_NMI_WINDOW_EXITING |					\
+	 CPU_BASED_PAUSE_EXITING |					\
+	 CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
+
+#define EVMCS1_SUPPORTED_2NDEXEC					\
+	(SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |			\
+	 SECONDARY_EXEC_WBINVD_EXITING |				\
+	 SECONDARY_EXEC_ENABLE_VPID |					\
+	 SECONDARY_EXEC_ENABLE_EPT |					\
+	 SECONDARY_EXEC_UNRESTRICTED_GUEST |				\
+	 SECONDARY_EXEC_DESC |						\
+	 SECONDARY_EXEC_ENABLE_RDTSCP |					\
+	 SECONDARY_EXEC_ENABLE_INVPCID |				\
+	 SECONDARY_EXEC_ENABLE_XSAVES |					\
+	 SECONDARY_EXEC_RDSEED_EXITING |				\
+	 SECONDARY_EXEC_RDRAND_EXITING |				\
+	 SECONDARY_EXEC_TSC_SCALING |					\
+	 SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |				\
+	 SECONDARY_EXEC_PT_USE_GPA |					\
+	 SECONDARY_EXEC_PT_CONCEAL_VMX |				\
+	 SECONDARY_EXEC_BUS_LOCK_DETECTION |				\
+	 SECONDARY_EXEC_NOTIFY_VM_EXITING |				\
+	 SECONDARY_EXEC_ENCLS_EXITING)
+
+#define EVMCS1_SUPPORTED_3RDEXEC (0ULL)
+
+#define EVMCS1_SUPPORTED_VMEXIT_CTRL					\
+	(VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 VM_EXIT_SAVE_DEBUG_CONTROLS |					\
+	 VM_EXIT_ACK_INTR_ON_EXIT |					\
+	 VM_EXIT_HOST_ADDR_SPACE_SIZE |					\
+	 VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |				\
+	 VM_EXIT_SAVE_IA32_PAT |					\
+	 VM_EXIT_LOAD_IA32_PAT |					\
+	 VM_EXIT_SAVE_IA32_EFER |					\
+	 VM_EXIT_LOAD_IA32_EFER |					\
+	 VM_EXIT_CLEAR_BNDCFGS |					\
+	 VM_EXIT_PT_CONCEAL_PIP |					\
+	 VM_EXIT_CLEAR_IA32_RTIT_CTL)
+
+#define EVMCS1_SUPPORTED_VMENTRY_CTRL					\
+	(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |				\
+	 VM_ENTRY_LOAD_DEBUG_CONTROLS |					\
+	 VM_ENTRY_IA32E_MODE |						\
+	 VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |				\
+	 VM_ENTRY_LOAD_IA32_PAT |					\
+	 VM_ENTRY_LOAD_IA32_EFER |					\
+	 VM_ENTRY_LOAD_BNDCFGS |					\
+	 VM_ENTRY_PT_CONCEAL_PIP |					\
+	 VM_ENTRY_LOAD_IA32_RTIT_CTL)
+
+#define EVMCS1_SUPPORTED_VMFUNC (0)
+
+struct evmcs_field {
+	u16 offset;
+	u16 clean_field;
+};
+
+extern const struct evmcs_field vmcs_field_to_evmcs_1[];
+extern const unsigned int nr_evmcs_1_fields;
+
+static __always_inline int evmcs_field_offset(unsigned long field,
+					      u16 *clean_field)
+{
+	const struct evmcs_field *evmcs_field;
+	unsigned int index = ROL16(field, 6);
+
+	if (unlikely(index >= nr_evmcs_1_fields))
+		return -ENOENT;
+
+	evmcs_field = &vmcs_field_to_evmcs_1[index];
+
+	/*
+	 * Use offset=0 to detect holes in eVMCS. This offset belongs to
+	 * 'revision_id' but this field has no encoding and is supposed to
+	 * be accessed directly.
+	 */
+	if (unlikely(!evmcs_field->offset))
+		return -ENOENT;
+
+	if (clean_field)
+		*clean_field = evmcs_field->clean_field;
+
+	return evmcs_field->offset;
+}
+
+static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs,
+				 unsigned long field, u16 offset)
+{
+	/*
+	 * vmcs12_read_any() doesn't care whether the supplied structure
+	 * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes
+	 * the exact offset of the required field, use it for convenience
+	 * here.
+	 */
+	return vmcs12_read_any((void *)evmcs, field, offset);
+}
+
+#endif /* __KVM_X86_VMX_HYPERV_H */
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index b4b9d51438c6b..b0f2e26c1aeae 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -3,6 +3,7 @@
 #define __KVM_X86_VMX_NESTED_H
 
 #include "kvm_cache_regs.h"
+#include "hyperv.h"
 #include "vmcs12.h"
 #include "vmx.h"
 
diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h
index 11541d272dbd8..eb48153bfd73c 100644
--- a/arch/x86/kvm/vmx/vmx_onhyperv.h
+++ b/arch/x86/kvm/vmx/vmx_onhyperv.h
@@ -4,11 +4,12 @@
 #define __ARCH_X86_KVM_VMX_ONHYPERV_H__
 
 #include <asm/hyperv-tlfs.h>
+#include <asm/mshyperv.h>
 
 #include <linux/jump_label.h>
 
 #include "capabilities.h"
-#include "hyperv.h"
+#include "hyperv_evmcs.h"
 #include "vmcs12.h"
 
 #define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs))
-- 
GitLab


From af9d544a452114eb54638015544b884e1befd0fb Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:21 +0100
Subject: [PATCH 0937/4076] KVM: x86: Introduce helper to handle Hyper-V
 paravirt TLB flush requests

As a preparation to making Hyper-V emulation optional, introduce a helper
to handle pending KVM_REQ_HV_TLB_FLUSH requests.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-8-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/hyperv.h     | 13 +++++++++++++
 arch/x86/kvm/svm/nested.c | 10 ++--------
 arch/x86/kvm/vmx/nested.c | 10 ++--------
 3 files changed, 17 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 9d8fa6ba63413..77f6549aa5de5 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -247,6 +247,19 @@ static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu)
 	return kvm_hv_get_assist_page(vcpu);
 }
 
+static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu,
+						     bool tdp_enabled)
+{
+	/*
+	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
+	 * L2's VP_ID upon request from the guest. Make sure we check for
+	 * pending entries in the right FIFO upon L1/L2 transition as these
+	 * requests are put by other vCPUs asynchronously.
+	 */
+	if (to_hv_vcpu(vcpu) && tdp_enabled)
+		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+}
+
 int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
 
 #endif
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 3fea8c47679e6..74c04102ef01c 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -487,14 +487,8 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm,
 
 static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
-	 * L2's VP_ID upon request from the guest. Make sure we check for
-	 * pending entries in the right FIFO upon L1/L2 transition as these
-	 * requests are put by other vCPUs asynchronously.
-	 */
-	if (to_hv_vcpu(vcpu) && npt_enabled)
-		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+	/* Handle pending Hyper-V TLB flush requests */
+	kvm_hv_nested_transtion_tlb_flush(vcpu, npt_enabled);
 
 	/*
 	 * TODO: optimize unconditional TLB flush/MMU sync.  A partial list of
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index c5ec0ef51ff78..382c0746d0693 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1139,14 +1139,8 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	/*
-	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
-	 * L2's VP_ID upon request from the guest. Make sure we check for
-	 * pending entries in the right FIFO upon L1/L2 transition as these
-	 * requests are put by other vCPUs asynchronously.
-	 */
-	if (to_hv_vcpu(vcpu) && enable_ept)
-		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+	/* Handle pending Hyper-V TLB flush requests */
+	kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept);
 
 	/*
 	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
-- 
GitLab


From b2e02f82b7f76234305c5a7fba4dbebc47ce4cb5 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:22 +0100
Subject: [PATCH 0938/4076] KVM: nVMX: Split off helper for emulating VMCLEAR
 on Hyper-V eVMCS

To avoid overloading handle_vmclear() with Hyper-V specific details and to
prepare the code to making Hyper-V emulation optional, create a dedicated
nested_evmcs_handle_vmclear() helper.

No functional change intended.

Suggested-by: Sean Christopherson <seanjc@google.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-9-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/nested.c | 38 ++++++++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 382c0746d0693..903b6f9ea2bdf 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -243,6 +243,29 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 	}
 }
 
+static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	/*
+	 * When Enlightened VMEntry is enabled on the calling CPU we treat
+	 * memory area pointer by vmptr as Enlightened VMCS (as there's no good
+	 * way to distinguish it from VMCS12) and we must not corrupt it by
+	 * writing to the non-existent 'launch_state' field. The area doesn't
+	 * have to be the currently active EVMCS on the calling CPU and there's
+	 * nothing KVM has to do to transition it from 'active' to 'non-active'
+	 * state. It is possible that the area will stay mapped as
+	 * vmx->nested.hv_evmcs but this shouldn't be a problem.
+	 */
+	if (!guest_cpuid_has_evmcs(vcpu) ||
+	    !evmptr_is_valid(nested_get_evmptr(vcpu)))
+		return false;
+
+	if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr)
+		nested_release_evmcs(vcpu);
+
+	return true;
+}
+
 static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
 				     struct loaded_vmcs *prev)
 {
@@ -5286,18 +5309,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 	if (vmptr == vmx->nested.vmxon_ptr)
 		return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
 
-	/*
-	 * When Enlightened VMEntry is enabled on the calling CPU we treat
-	 * memory area pointer by vmptr as Enlightened VMCS (as there's no good
-	 * way to distinguish it from VMCS12) and we must not corrupt it by
-	 * writing to the non-existent 'launch_state' field. The area doesn't
-	 * have to be the currently active EVMCS on the calling CPU and there's
-	 * nothing KVM has to do to transition it from 'active' to 'non-active'
-	 * state. It is possible that the area will stay mapped as
-	 * vmx->nested.hv_evmcs but this shouldn't be a problem.
-	 */
-	if (likely(!guest_cpuid_has_evmcs(vcpu) ||
-		   !evmptr_is_valid(nested_get_evmptr(vcpu)))) {
+	if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) {
 		if (vmptr == vmx->nested.current_vmptr)
 			nested_release_vmcs12(vcpu);
 
@@ -5314,8 +5326,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 					   vmptr + offsetof(struct vmcs12,
 							    launch_state),
 					   &zero, sizeof(zero));
-	} else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) {
-		nested_release_evmcs(vcpu);
 	}
 
 	return nested_vmx_succeed(vcpu);
-- 
GitLab


From 6dac1195181cb561a1ac32b92f58c92e87a91c70 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:23 +0100
Subject: [PATCH 0939/4076] KVM: selftests: Make Hyper-V tests explicitly
 require KVM Hyper-V support

In preparation for conditional Hyper-V emulation enablement in KVM, make
Hyper-V specific tests skip gracefully instead of failing when KVM support
for emulating Hyper-V is not there.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-10-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86_64/hyperv_clock.c            | 2 ++
 tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c            | 5 +++--
 .../selftests/kvm/x86_64/hyperv_extended_hypercalls.c        | 2 ++
 tools/testing/selftests/kvm/x86_64/hyperv_features.c         | 2 ++
 tools/testing/selftests/kvm/x86_64/hyperv_ipi.c              | 2 ++
 tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c         | 1 +
 tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c        | 2 ++
 7 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index f25749eaa6a84..f5e1e98f04f9e 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -211,6 +211,8 @@ int main(void)
 	vm_vaddr_t tsc_page_gva;
 	int stage;
 
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TIME));
+
 	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
 
 	vcpu_set_hv_cpuid(vcpu);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
index 7bde0c4dfdbd1..4c7257ecd2a68 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
@@ -240,11 +240,12 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	int stage;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
-
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH));
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
 	hcall_page = vm_vaddr_alloc_pages(vm, 1);
 	memset(addr_gva2hva(vm, hcall_page), 0x0,  getpagesize());
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
index e036db1f32b9b..949e08e98f315 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
@@ -43,6 +43,8 @@ int main(void)
 	uint64_t *outval;
 	struct ucall uc;
 
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID));
+
 	/* Verify if extended hypercalls are supported */
 	if (!kvm_cpuid_has(kvm_get_supported_hv_cpuid(),
 			   HV_ENABLE_EXTENDED_HYPERCALLS)) {
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 9f28aa276c4e2..387c605a30772 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -690,6 +690,8 @@ static void guest_test_hcalls_access(void)
 
 int main(void)
 {
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENFORCE_CPUID));
+
 	pr_info("Testing access to Hyper-V specific MSRs\n");
 	guest_test_msrs_access();
 
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
index 6feb5ddb031da..65e5f4c05068a 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
@@ -248,6 +248,8 @@ int main(int argc, char *argv[])
 	int stage = 1, r;
 	struct ucall uc;
 
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_SEND_IPI));
+
 	vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code);
 
 	/* Hypercall input/output */
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
index 6c12785620906..c9b18707edc03 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
@@ -158,6 +158,7 @@ int main(int argc, char *argv[])
 	int stage;
 
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH));
 
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
index 4758b6ef5618e..c4443f71f8dd0 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
@@ -590,6 +590,8 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	int stage = 1, r, i;
 
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TLBFLUSH));
+
 	vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code);
 
 	/* Test data page */
-- 
GitLab


From 225b7c1117b2f6dadbdb1d40538d37b9685e8b18 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:24 +0100
Subject: [PATCH 0940/4076] KVM: selftests: Fix vmxon_pa == vmcs12_pa == -1ull
 nVMX testcase for !eVMCS

The "vmxon_pa == vmcs12_pa == -1ull" test happens to work by accident: as
Enlightened VMCS is always supported, set_default_vmx_state() adds
'KVM_STATE_NESTED_EVMCS' to 'flags' and the following branch of
vmx_set_nested_state() is executed:

        if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) &&
            (!guest_can_use(vcpu, X86_FEATURE_VMX) ||
             !vmx->nested.enlightened_vmcs_enabled))
                        return -EINVAL;

as 'enlightened_vmcs_enabled' is false. In fact, "vmxon_pa == vmcs12_pa ==
-1ull" is a valid state when not tainted by wrong flags so the test should
aim for this branch:

        if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA)
                return 0;

Test all this properly:
- Without KVM_STATE_NESTED_EVMCS in the flags, the expected return value is
'0'.
- With KVM_STATE_NESTED_EVMCS flag (when supported) set, the expected
return value is '-EINVAL' prior to enabling eVMCS and '0' after.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-11-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../kvm/x86_64/vmx_set_nested_state_test.c       | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
index 41ea7028a1f8d..67a62a5a88951 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -125,21 +125,25 @@ void test_vmx_nested_state(struct kvm_vcpu *vcpu)
 
 	/*
 	 * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without
-	 * setting the nested state but flags other than eVMCS must be clear.
-	 * The eVMCS flag can be set if the enlightened VMCS capability has
-	 * been enabled.
+	 * setting the nested state. When the eVMCS flag is not set, the
+	 * expected return value is '0'.
 	 */
 	set_default_vmx_state(state, state_sz);
+	state->flags = 0;
 	state->hdr.vmx.vmxon_pa = -1ull;
 	state->hdr.vmx.vmcs12_pa = -1ull;
-	test_nested_state_expect_einval(vcpu, state);
+	test_nested_state(vcpu, state);
 
-	state->flags &= KVM_STATE_NESTED_EVMCS;
+	/*
+	 * When eVMCS is supported, the eVMCS flag can only be set if the
+	 * enlightened VMCS capability has been enabled.
+	 */
 	if (have_evmcs) {
+		state->flags = KVM_STATE_NESTED_EVMCS;
 		test_nested_state_expect_einval(vcpu, state);
 		vcpu_enable_evmcs(vcpu);
+		test_nested_state(vcpu, state);
 	}
-	test_nested_state(vcpu, state);
 
 	/* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */
 	state->hdr.vmx.smm.flags = 1;
-- 
GitLab


From f97314626734deaef49564a429c6f8eee3846bd3 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:25 +0100
Subject: [PATCH 0941/4076] KVM: nVMX: Move guest_cpuid_has_evmcs() to hyperv.h

In preparation for making Hyper-V emulation optional, move Hyper-V specific
guest_cpuid_has_evmcs() to hyperv.h.

No functional change intended.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-12-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/hyperv.h | 11 +++++++++++
 arch/x86/kvm/vmx/vmx.h    | 10 ----------
 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h
index d4ed99008518c..6e1ee951e3606 100644
--- a/arch/x86/kvm/vmx/hyperv.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -4,6 +4,7 @@
 
 #include <linux/kvm_host.h>
 #include "vmcs12.h"
+#include "vmx.h"
 
 #define EVMPTR_INVALID (-1ULL)
 #define EVMPTR_MAP_PENDING (-2ULL)
@@ -20,6 +21,16 @@ enum nested_evmptrld_status {
 	EVMPTRLD_ERROR,
 };
 
+static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and
+	 * eVMCS has been explicitly enabled by userspace.
+	 */
+	return vcpu->arch.hyperv_enabled &&
+	       to_vmx(vcpu)->nested.enlightened_vmcs_enabled;
+}
+
 u64 nested_get_evmptr(struct kvm_vcpu *vcpu);
 uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu);
 int nested_enable_evmcs(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index c2130d2c8e24b..959c6d94287fc 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -745,14 +745,4 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu)
 	return  lapic_in_kernel(vcpu) && enable_ipiv;
 }
 
-static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and
-	 * eVMCS has been explicitly enabled by userspace.
-	 */
-	return vcpu->arch.hyperv_enabled &&
-	       to_vmx(vcpu)->nested.enlightened_vmcs_enabled;
-}
-
 #endif /* __KVM_X86_VMX_H */
-- 
GitLab


From b4f69df0f65e97fec439130a0d0a8b9c7cc02df2 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:26 +0100
Subject: [PATCH 0942/4076] KVM: x86: Make Hyper-V emulation optional

Hyper-V emulation in KVM is a fairly big chunk and in some cases it may be
desirable to not compile it in to reduce module sizes as well as the attack
surface. Introduce CONFIG_KVM_HYPERV option to make it possible.

Note, there's room for further nVMX/nSVM code optimizations when
!CONFIG_KVM_HYPERV, this will be done in follow-up patches.

Reorganize Makefile a bit so all CONFIG_HYPERV and CONFIG_KVM_HYPERV files
are grouped together.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-13-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h |  6 ++++
 arch/x86/kvm/Kconfig            | 14 ++++++++
 arch/x86/kvm/Makefile           | 20 +++++------
 arch/x86/kvm/cpuid.c            |  6 ++++
 arch/x86/kvm/hyperv.h           | 61 +++++++++++++++++++++++++++++++-
 arch/x86/kvm/irq_comm.c         |  9 ++++-
 arch/x86/kvm/svm/hyperv.h       |  9 +++++
 arch/x86/kvm/vmx/hyperv.h       | 17 ++++++---
 arch/x86/kvm/vmx/nested.c       | 30 ++++++++++++++++
 arch/x86/kvm/vmx/vmx.c          |  2 ++
 arch/x86/kvm/x86.c              | 62 ++++++++++++++++++++++++---------
 11 files changed, 201 insertions(+), 35 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 86069b985d227..b093c2191cd3f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -937,8 +937,10 @@ struct kvm_vcpu_arch {
 	/* used for guest single stepping over the given code position */
 	unsigned long singlestep_rip;
 
+#ifdef CONFIG_KVM_HYPERV
 	bool hyperv_enabled;
 	struct kvm_vcpu_hv *hyperv;
+#endif
 #ifdef CONFIG_KVM_XEN
 	struct kvm_vcpu_xen xen;
 #endif
@@ -1095,6 +1097,7 @@ enum hv_tsc_page_status {
 	HV_TSC_PAGE_BROKEN,
 };
 
+#ifdef CONFIG_KVM_HYPERV
 /* Hyper-V emulation context */
 struct kvm_hv {
 	struct mutex hv_lock;
@@ -1127,6 +1130,7 @@ struct kvm_hv {
 
 	struct kvm_hv_syndbg hv_syndbg;
 };
+#endif
 
 struct msr_bitmap_range {
 	u32 flags;
@@ -1349,7 +1353,9 @@ struct kvm_arch {
 	/* reads protected by irq_srcu, writes by irq_lock */
 	struct hlist_head mask_notifier_list;
 
+#ifdef CONFIG_KVM_HYPERV
 	struct kvm_hv hyperv;
+#endif
 
 #ifdef CONFIG_KVM_XEN
 	struct kvm_xen xen;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index c1716e83d1761..34f2f47cadf2b 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -141,6 +141,20 @@ config KVM_SMM
 
 	  If unsure, say Y.
 
+config KVM_HYPERV
+	bool "Support for Microsoft Hyper-V emulation"
+	depends on KVM
+	default y
+	help
+	  Provides KVM support for emulating Microsoft Hyper-V.  This allows KVM
+	  to expose a subset of the paravirtualized interfaces defined in the
+	  Hyper-V Hypervisor Top-Level Functional Specification (TLFS):
+	  https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs
+	  These interfaces are required for the correct and performant functioning
+	  of Windows and Hyper-V guests on KVM.
+
+	  If unsure, say "Y".
+
 config KVM_XEN
 	bool "Support for Xen hypercall interface"
 	depends on KVM
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 8ea872401cd67..475b5fa917a62 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -11,29 +11,27 @@ include $(srctree)/virt/kvm/Makefile.kvm
 
 kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
-			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \
+			   debugfs.o mmu/mmu.o mmu/page_track.o \
 			   mmu/spte.o
 
-ifdef CONFIG_HYPERV
-kvm-y			+= kvm_onhyperv.o
-endif
-
 kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
+kvm-$(CONFIG_KVM_HYPERV) += hyperv.o
 kvm-$(CONFIG_KVM_XEN)	+= xen.o
 kvm-$(CONFIG_KVM_SMM)	+= smm.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
-			   vmx/hyperv.o vmx/hyperv_evmcs.o vmx/nested.o vmx/posted_intr.o
-kvm-intel-$(CONFIG_X86_SGX_KVM)	+= vmx/sgx.o
+			   vmx/nested.o vmx/posted_intr.o
 
-ifdef CONFIG_HYPERV
-kvm-intel-y		+= vmx/vmx_onhyperv.o
-endif
+kvm-intel-$(CONFIG_X86_SGX_KVM)	+= vmx/sgx.o
+kvm-intel-$(CONFIG_KVM_HYPERV)	+= vmx/hyperv.o vmx/hyperv_evmcs.o
 
 kvm-amd-y		+= svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \
-			   svm/sev.o svm/hyperv.o
+			   svm/sev.o
+kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o
 
 ifdef CONFIG_HYPERV
+kvm-y			+= kvm_onhyperv.o
+kvm-intel-y		+= vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o
 kvm-amd-y		+= svm/svm_onhyperv.o
 endif
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index dda6fc4cfae88..1b278a3f06895 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -314,11 +314,15 @@ EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
 
 static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct kvm_cpuid_entry2 *entry;
 
 	entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE,
 				  KVM_CPUID_INDEX_NOT_SIGNIFICANT);
 	return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX;
+#else
+	return false;
+#endif
 }
 
 static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
@@ -433,11 +437,13 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
 		return 0;
 	}
 
+#ifdef CONFIG_KVM_HYPERV
 	if (kvm_cpuid_has_hyperv(e2, nent)) {
 		r = kvm_hv_vcpu_init(vcpu);
 		if (r)
 			return r;
 	}
+#endif
 
 	r = kvm_check_cpuid(vcpu, e2, nent);
 	if (r)
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 77f6549aa5de5..1dc0b6604526a 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -24,6 +24,8 @@
 #include <linux/kvm_host.h>
 #include "x86.h"
 
+#ifdef CONFIG_KVM_HYPERV
+
 /* "Hv#1" signature */
 #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648
 
@@ -261,5 +263,62 @@ static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu,
 }
 
 int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
+#else /* CONFIG_KVM_HYPERV */
+static inline void kvm_hv_setup_tsc_page(struct kvm *kvm,
+					 struct pvclock_vcpu_time_info *hv_clock) {}
+static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {}
+static inline void kvm_hv_init_vm(struct kvm *kvm) {}
+static inline void kvm_hv_destroy_vm(struct kvm *kvm) {}
+static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+static inline void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	return HV_STATUS_ACCESS_DENIED;
+}
+static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {}
+static inline void kvm_hv_free_pa_page(struct kvm *kvm) {}
+static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector)
+{
+	return false;
+}
+static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector)
+{
+	return false;
+}
+static inline void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) {}
+static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) {}
+static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu)
+{
+	return vcpu->vcpu_idx;
+}
+static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, bool tdp_enabled) {}
+#endif /* CONFIG_KVM_HYPERV */
 
-#endif
+#endif /* __ARCH_X86_KVM_HYPERV_H__ */
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 16d076a1b91ac..68f3f6c260469 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -144,7 +144,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
 }
 
-
+#ifdef CONFIG_KVM_HYPERV
 static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
 		    struct kvm *kvm, int irq_source_id, int level,
 		    bool line_status)
@@ -154,6 +154,7 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
 
 	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
 }
+#endif
 
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
@@ -163,9 +164,11 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	int r;
 
 	switch (e->type) {
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_IRQ_ROUTING_HV_SINT:
 		return kvm_hv_set_sint(e, kvm, irq_source_id, level,
 				       line_status);
+#endif
 
 	case KVM_IRQ_ROUTING_MSI:
 		if (kvm_msi_route_invalid(kvm, e))
@@ -314,11 +317,13 @@ int kvm_set_routing_entry(struct kvm *kvm,
 		if (kvm_msi_route_invalid(kvm, e))
 			return -EINVAL;
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_IRQ_ROUTING_HV_SINT:
 		e->set = kvm_hv_set_sint;
 		e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
 		e->hv_sint.sint = ue->u.hv_sint.sint;
 		break;
+#endif
 #ifdef CONFIG_KVM_XEN
 	case KVM_IRQ_ROUTING_XEN_EVTCHN:
 		return kvm_xen_setup_evtchn(kvm, e, ue);
@@ -438,5 +443,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 
 void kvm_arch_irq_routing_update(struct kvm *kvm)
 {
+#ifdef CONFIG_KVM_HYPERV
 	kvm_hv_irq_routing_update(kvm);
+#endif
 }
diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h
index 02f4784b5d446..d3f8bfc05832e 100644
--- a/arch/x86/kvm/svm/hyperv.h
+++ b/arch/x86/kvm/svm/hyperv.h
@@ -11,6 +11,7 @@
 #include "../hyperv.h"
 #include "svm.h"
 
+#ifdef CONFIG_KVM_HYPERV
 static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -41,5 +42,13 @@ static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
 }
 
 void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
+#else /* CONFIG_KVM_HYPERV */
+static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) {}
+static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) {}
+#endif /* CONFIG_KVM_HYPERV */
 
 #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */
diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h
index 6e1ee951e3606..0e90ef4efe341 100644
--- a/arch/x86/kvm/vmx/hyperv.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -9,11 +9,6 @@
 #define EVMPTR_INVALID (-1ULL)
 #define EVMPTR_MAP_PENDING (-2ULL)
 
-static inline bool evmptr_is_valid(u64 evmptr)
-{
-	return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING;
-}
-
 enum nested_evmptrld_status {
 	EVMPTRLD_DISABLED,
 	EVMPTRLD_SUCCEEDED,
@@ -21,6 +16,12 @@ enum nested_evmptrld_status {
 	EVMPTRLD_ERROR,
 };
 
+#ifdef CONFIG_KVM_HYPERV
+static inline bool evmptr_is_valid(u64 evmptr)
+{
+	return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING;
+}
+
 static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -39,5 +40,11 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *
 int nested_evmcs_check_controls(struct vmcs12 *vmcs12);
 bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu);
 void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
+#else
+static inline bool evmptr_is_valid(u64 evmptr)
+{
+	return false;
+}
+#endif
 
 #endif /* __KVM_X86_VMX_HYPERV_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 903b6f9ea2bdf..01a94d290c125 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -226,6 +226,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
 
 static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
@@ -241,10 +242,12 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 		hv_vcpu->nested.vm_id = 0;
 		hv_vcpu->nested.vp_id = 0;
 	}
+#endif
 }
 
 static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	/*
 	 * When Enlightened VMEntry is enabled on the calling CPU we treat
@@ -264,6 +267,9 @@ static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr)
 		nested_release_evmcs(vcpu);
 
 	return true;
+#else
+	return false;
+#endif
 }
 
 static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
@@ -1595,6 +1601,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 
 static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
 	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu);
@@ -1835,10 +1842,14 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields
 	 */
 
 	return;
+#else /* CONFIG_KVM_HYPERV */
+	KVM_BUG_ON(1, vmx->vcpu.kvm);
+#endif /* CONFIG_KVM_HYPERV */
 }
 
 static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
 	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
 
@@ -2009,6 +2020,9 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
 	evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs;
 
 	return;
+#else /* CONFIG_KVM_HYPERV */
+	KVM_BUG_ON(1, vmx->vcpu.kvm);
+#endif /* CONFIG_KVM_HYPERV */
 }
 
 /*
@@ -2018,6 +2032,7 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
 static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
 	struct kvm_vcpu *vcpu, bool from_launch)
 {
+#ifdef CONFIG_KVM_HYPERV
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	bool evmcs_gpa_changed = false;
 	u64 evmcs_gpa;
@@ -2099,6 +2114,9 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
 	}
 
 	return EVMPTRLD_SUCCEEDED;
+#else
+	return EVMPTRLD_DISABLED;
+#endif
 }
 
 void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu)
@@ -2905,8 +2923,10 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
 	    nested_check_vm_entry_controls(vcpu, vmcs12))
 		return -EINVAL;
 
+#ifdef CONFIG_KVM_HYPERV
 	if (guest_cpuid_has_evmcs(vcpu))
 		return nested_evmcs_check_controls(vmcs12);
+#endif
 
 	return 0;
 }
@@ -3178,6 +3198,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+#ifdef CONFIG_KVM_HYPERV
 static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -3205,6 +3226,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
 
 	return true;
 }
+#endif
 
 static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 {
@@ -3296,6 +3318,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 
 static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 {
+#ifdef CONFIG_KVM_HYPERV
 	/*
 	 * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy
 	 * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory
@@ -3312,6 +3335,7 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 
 		return false;
 	}
+#endif
 
 	if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu))
 		return false;
@@ -4749,6 +4773,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	/* trying to cancel vmlaunch/vmresume is a bug */
 	WARN_ON_ONCE(vmx->nested.nested_run_pending);
 
+#ifdef CONFIG_KVM_HYPERV
 	if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
 		/*
 		 * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map
@@ -4758,6 +4783,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		 */
 		(void)nested_get_evmcs_page(vcpu);
 	}
+#endif
 
 	/* Service pending TLB flush requests for L2 before switching to L1. */
 	kvm_service_local_tlb_flush_requests(vcpu);
@@ -6212,11 +6238,13 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 		 * Handle L2's bus locks in L0 directly.
 		 */
 		return true;
+#ifdef CONFIG_KVM_HYPERV
 	case EXIT_REASON_VMCALL:
 		/* Hyper-V L2 TLB flush hypercall is handled by L0 */
 		return guest_hv_cpuid_has_l2_tlb_flush(vcpu) &&
 			nested_evmcs_l2_tlb_flush_enabled(vcpu) &&
 			kvm_hv_is_tlb_flush_hcall(vcpu);
+#endif
 	default:
 		break;
 	}
@@ -7100,7 +7128,9 @@ struct kvm_x86_nested_ops vmx_nested_ops = {
 	.set_state = vmx_set_nested_state,
 	.get_nested_state_pages = vmx_get_nested_state_pages,
 	.write_log_dirty = nested_vmx_write_pml_buffer,
+#ifdef CONFIG_KVM_HYPERV
 	.enable_evmcs = nested_enable_evmcs,
 	.get_evmcs_version = nested_get_evmcs_version,
 	.hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush,
+#endif
 };
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 552593a2ac148..3ff5c44dff9d5 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2048,6 +2048,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
 				    &msr_info->data))
 			return 1;
+#ifdef CONFIG_KVM_HYPERV
 		/*
 		 * Enlightened VMCS v1 doesn't have certain VMCS fields but
 		 * instead of just ignoring the features, different Hyper-V
@@ -2058,6 +2059,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu))
 			nested_evmcs_filter_control_msr(vcpu, msr_info->index,
 							&msr_info->data);
+#endif
 		break;
 	case MSR_IA32_RTIT_CTL:
 		if (!vmx_pt_mode_is_host_guest())
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 81224b9676d99..598b057611e02 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1504,6 +1504,8 @@ static unsigned num_msrs_to_save;
 static const u32 emulated_msrs_all[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
+
+#ifdef CONFIG_KVM_HYPERV
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
 	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
 	HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY,
@@ -1521,6 +1523,7 @@ static const u32 emulated_msrs_all[] = {
 	HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS,
 	HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER,
 	HV_X64_MSR_SYNDBG_PENDING_BUFFER,
+#endif
 
 	MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK,
@@ -4020,6 +4023,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 * the need to ignore the workaround.
 		 */
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
 	case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
 	case HV_X64_MSR_SYNDBG_OPTIONS:
@@ -4032,6 +4036,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case HV_X64_MSR_TSC_INVARIANT_CONTROL:
 		return kvm_hv_set_msr_common(vcpu, msr, data,
 					     msr_info->host_initiated);
+#endif
 	case MSR_IA32_BBL_CR_CTL3:
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
@@ -4377,6 +4382,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 */
 		msr_info->data = 0x20000000;
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
 	case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
 	case HV_X64_MSR_SYNDBG_OPTIONS:
@@ -4390,6 +4396,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return kvm_hv_get_msr_common(vcpu,
 					     msr_info->index, &msr_info->data,
 					     msr_info->host_initiated);
+#endif
 	case MSR_IA32_BBL_CR_CTL3:
 		/* This legacy MSR exists but isn't fully documented in current
 		 * silicon.  It is however accessed by winxp in very narrow
@@ -4527,6 +4534,7 @@ static inline bool kvm_can_mwait_in_guest(void)
 		boot_cpu_has(X86_FEATURE_ARAT);
 }
 
+#ifdef CONFIG_KVM_HYPERV
 static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
 					    struct kvm_cpuid2 __user *cpuid_arg)
 {
@@ -4547,6 +4555,7 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
 
 	return 0;
 }
+#endif
 
 static bool kvm_is_vm_type_supported(unsigned long type)
 {
@@ -4580,9 +4589,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_VCPU_EVENTS:
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
 	case KVM_CAP_HYPERV_SPIN:
+	case KVM_CAP_HYPERV_TIME:
 	case KVM_CAP_HYPERV_SYNIC:
 	case KVM_CAP_HYPERV_SYNIC2:
 	case KVM_CAP_HYPERV_VP_INDEX:
@@ -4592,6 +4603,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_CPUID:
 	case KVM_CAP_HYPERV_ENFORCE_CPUID:
 	case KVM_CAP_SYS_HYPERV_CPUID:
+#endif
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -4601,7 +4613,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_KVMCLOCK_CTRL:
 	case KVM_CAP_READONLY_MEM:
-	case KVM_CAP_HYPERV_TIME:
 	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 	case KVM_CAP_TSC_DEADLINE_TIMER:
 	case KVM_CAP_DISABLE_QUIRKS:
@@ -4712,12 +4723,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_x86_ops.nested_ops->get_state ?
 			kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0;
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
 		r = kvm_x86_ops.enable_l2_tlb_flush != NULL;
 		break;
 	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
 		r = kvm_x86_ops.nested_ops->enable_evmcs != NULL;
 		break;
+#endif
 	case KVM_CAP_SMALLER_MAXPHYADDR:
 		r = (int) allow_smaller_maxphyaddr;
 		break;
@@ -4884,9 +4897,11 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	case KVM_GET_MSRS:
 		r = msr_io(NULL, argp, do_get_msr_feature, 1);
 		break;
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_GET_SUPPORTED_HV_CPUID:
 		r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp);
 		break;
+#endif
 	case KVM_GET_DEVICE_ATTR: {
 		struct kvm_device_attr attr;
 		r = -EFAULT;
@@ -5712,14 +5727,11 @@ static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 				     struct kvm_enable_cap *cap)
 {
-	int r;
-	uint16_t vmcs_version;
-	void __user *user_ptr;
-
 	if (cap->flags)
 		return -EINVAL;
 
 	switch (cap->cap) {
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_CAP_HYPERV_SYNIC2:
 		if (cap->args[0])
 			return -EINVAL;
@@ -5731,16 +5743,22 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		return kvm_hv_activate_synic(vcpu, cap->cap ==
 					     KVM_CAP_HYPERV_SYNIC2);
 	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
-		if (!kvm_x86_ops.nested_ops->enable_evmcs)
-			return -ENOTTY;
-		r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version);
-		if (!r) {
-			user_ptr = (void __user *)(uintptr_t)cap->args[0];
-			if (copy_to_user(user_ptr, &vmcs_version,
-					 sizeof(vmcs_version)))
-				r = -EFAULT;
+		{
+			int r;
+			uint16_t vmcs_version;
+			void __user *user_ptr;
+
+			if (!kvm_x86_ops.nested_ops->enable_evmcs)
+				return -ENOTTY;
+			r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version);
+			if (!r) {
+				user_ptr = (void __user *)(uintptr_t)cap->args[0];
+				if (copy_to_user(user_ptr, &vmcs_version,
+						 sizeof(vmcs_version)))
+					r = -EFAULT;
+			}
+			return r;
 		}
-		return r;
 	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
 		if (!kvm_x86_ops.enable_l2_tlb_flush)
 			return -ENOTTY;
@@ -5749,6 +5767,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 
 	case KVM_CAP_HYPERV_ENFORCE_CPUID:
 		return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]);
+#endif
 
 	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
 		vcpu->arch.pv_cpuid.enforce = cap->args[0];
@@ -6141,9 +6160,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_GET_SUPPORTED_HV_CPUID:
 		r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp);
 		break;
+#endif
 #ifdef CONFIG_KVM_XEN
 	case KVM_XEN_VCPU_GET_ATTR: {
 		struct kvm_xen_vcpu_attr xva;
@@ -7201,6 +7222,7 @@ set_pit2_out:
 		r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, &region);
 		break;
 	}
+#ifdef CONFIG_KVM_HYPERV
 	case KVM_HYPERV_EVENTFD: {
 		struct kvm_hyperv_eventfd hvevfd;
 
@@ -7210,6 +7232,7 @@ set_pit2_out:
 		r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd);
 		break;
 	}
+#endif
 	case KVM_SET_PMU_EVENT_FILTER:
 		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
 		break;
@@ -10588,19 +10611,20 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 
 static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 {
-	u64 eoi_exit_bitmap[4];
-
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		return;
 
+#ifdef CONFIG_KVM_HYPERV
 	if (to_hv_vcpu(vcpu)) {
+		u64 eoi_exit_bitmap[4];
+
 		bitmap_or((ulong *)eoi_exit_bitmap,
 			  vcpu->arch.ioapic_handled_vectors,
 			  to_hv_synic(vcpu)->vec_bitmap, 256);
 		static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
 		return;
 	}
-
+#endif
 	static_call_cond(kvm_x86_load_eoi_exitmap)(
 		vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
 }
@@ -10691,9 +10715,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		 * the flushes are considered "remote" and not "local" because
 		 * the requests can be initiated from other vCPUs.
 		 */
+#ifdef CONFIG_KVM_HYPERV
 		if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) &&
 		    kvm_hv_vcpu_flush_tlb(vcpu))
 			kvm_vcpu_flush_tlb_guest(vcpu);
+#endif
 
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -10746,6 +10772,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			vcpu_load_eoi_exitmap(vcpu);
 		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
 			kvm_vcpu_reload_apic_access_page(vcpu);
+#ifdef CONFIG_KVM_HYPERV
 		if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH;
@@ -10776,6 +10803,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		 */
 		if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu))
 			kvm_hv_process_stimers(vcpu);
+#endif
 		if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
 			kvm_vcpu_update_apicv(vcpu);
 		if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
-- 
GitLab


From 453e42b0557148cc7092c72eff6677a5436e3c7c Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:27 +0100
Subject: [PATCH 0943/4076] KVM: nVMX: Introduce helpers to check if Hyper-V
 evmptr12 is valid/set

In order to get rid of raw 'vmx->nested.hv_evmcs_vmptr' accesses when
!CONFIG_KVM_HYPERV, introduce a pair of helpers:

nested_vmx_is_evmptr12_valid() to check that eVMPTR points to a valid
address.

nested_vmx_is_evmptr12_valid() to check that eVMPTR either points to a
valid address or is in 'pending' port-migration state (meaning it is
supposed to be valid but the exact address wasn't acquired from guest's
memory yet).

No functional change intended.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-14-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/hyperv.h | 30 ++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/nested.c | 38 +++++++++++++++++++-------------------
 arch/x86/kvm/vmx/nested.h |  2 +-
 3 files changed, 50 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h
index 0e90ef4efe341..71e90a16f1837 100644
--- a/arch/x86/kvm/vmx/hyperv.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -22,6 +22,21 @@ static inline bool evmptr_is_valid(u64 evmptr)
 	return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING;
 }
 
+static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx)
+{
+	return evmptr_is_valid(vmx->nested.hv_evmcs_vmptr);
+}
+
+static inline bool evmptr_is_set(u64 evmptr)
+{
+	return evmptr != EVMPTR_INVALID;
+}
+
+static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx)
+{
+	return evmptr_is_set(vmx->nested.hv_evmcs_vmptr);
+}
+
 static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -45,6 +60,21 @@ static inline bool evmptr_is_valid(u64 evmptr)
 {
 	return false;
 }
+
+static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx)
+{
+	return false;
+}
+
+static inline bool evmptr_is_set(u64 evmptr)
+{
+	return false;
+}
+
+static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx)
+{
+	return false;
+}
 #endif
 
 #endif /* __KVM_X86_VMX_HYPERV_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 01a94d290c125..0507174750e04 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -179,7 +179,7 @@ static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
 	 * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all
 	 * fields and thus must be synced.
 	 */
-	if (to_vmx(vcpu)->nested.hv_evmcs_vmptr != EVMPTR_INVALID)
+	if (nested_vmx_is_evmptr12_set(to_vmx(vcpu)))
 		to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true;
 
 	return kvm_skip_emulated_instruction(vcpu);
@@ -194,7 +194,7 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error)
 	 * can't be done if there isn't a current VMCS.
 	 */
 	if (vmx->nested.current_vmptr == INVALID_GPA &&
-	    !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	    !nested_vmx_is_evmptr12_valid(vmx))
 		return nested_vmx_failInvalid(vcpu);
 
 	return nested_vmx_failValid(vcpu, vm_instruction_error);
@@ -230,7 +230,7 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+	if (nested_vmx_is_evmptr12_valid(vmx)) {
 		kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
 		vmx->nested.hv_evmcs = NULL;
 	}
@@ -2123,7 +2123,7 @@ void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (nested_vmx_is_evmptr12_valid(vmx))
 		copy_vmcs12_to_enlightened(vmx);
 	else
 		copy_vmcs12_to_shadow(vmx);
@@ -2277,7 +2277,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 	u32 exec_control;
 	u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12);
 
-	if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx))
 		prepare_vmcs02_early_rare(vmx, vmcs12);
 
 	/*
@@ -2572,11 +2572,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	bool load_guest_pdptrs_vmcs12 = false;
 
-	if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+	if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) {
 		prepare_vmcs02_rare(vmx, vmcs12);
 		vmx->nested.dirty_vmcs12 = false;
 
-		load_guest_pdptrs_vmcs12 = !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) ||
+		load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) ||
 			!(vmx->nested.hv_evmcs->hv_clean_fields &
 			  HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1);
 	}
@@ -2699,7 +2699,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * bits when it changes a field in eVMCS. Mark all fields as clean
 	 * here.
 	 */
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (nested_vmx_is_evmptr12_valid(vmx))
 		vmx->nested.hv_evmcs->hv_clean_fields |=
 			HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 
@@ -3579,7 +3579,7 @@ vmentry_fail_vmexit:
 
 	load_vmcs12_host_state(vcpu, vmcs12);
 	vmcs12->vm_exit_reason = exit_reason.full;
-	if (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
 	return NVMX_VMENTRY_VMEXIT;
 }
@@ -3610,7 +3610,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (CC(evmptrld_status == EVMPTRLD_VMFAIL))
 		return nested_vmx_failInvalid(vcpu);
 
-	if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) &&
+	if (CC(!nested_vmx_is_evmptr12_valid(vmx) &&
 	       vmx->nested.current_vmptr == INVALID_GPA))
 		return nested_vmx_failInvalid(vcpu);
 
@@ -3625,7 +3625,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (CC(vmcs12->hdr.shadow_vmcs))
 		return nested_vmx_failInvalid(vcpu);
 
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+	if (nested_vmx_is_evmptr12_valid(vmx)) {
 		copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields);
 		/* Enlightened VMCS doesn't have launch state */
 		vmcs12->launch_state = !launch;
@@ -4370,11 +4370,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (nested_vmx_is_evmptr12_valid(vmx))
 		sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
 
 	vmx->nested.need_sync_vmcs02_to_vmcs12_rare =
-		!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr);
+		!nested_vmx_is_evmptr12_valid(vmx);
 
 	vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
 	vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);
@@ -4897,7 +4897,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	}
 
 	if ((vm_exit_reason != -1) &&
-	    (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)))
+	    (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)))
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
 
 	/* in case we halted in L2 */
@@ -5390,7 +5390,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	/* Decode instruction info and find the field to read */
 	field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf));
 
-	if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+	if (!nested_vmx_is_evmptr12_valid(vmx)) {
 		/*
 		 * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA,
 		 * any VMREAD sets the ALU flags for VMfailInvalid.
@@ -5616,7 +5616,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
 
 	/* Forbid normal VMPTRLD if Enlightened version was used */
-	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+	if (nested_vmx_is_evmptr12_valid(vmx))
 		return 1;
 
 	if (vmx->nested.current_vmptr != vmptr) {
@@ -5679,7 +5679,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (unlikely(evmptr_is_valid(to_vmx(vcpu)->nested.hv_evmcs_vmptr)))
+	if (unlikely(nested_vmx_is_evmptr12_valid(to_vmx(vcpu))))
 		return 1;
 
 	if (get_vmx_mem_address(vcpu, exit_qual, instr_info,
@@ -6467,7 +6467,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 			kvm_state.size += sizeof(user_vmx_nested_state->vmcs12);
 
 			/* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */
-			if (vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID)
+			if (nested_vmx_is_evmptr12_set(vmx))
 				kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
 
 			if (is_guest_mode(vcpu) &&
@@ -6523,7 +6523,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 	} else  {
 		copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));
 		if (!vmx->nested.need_vmcs12_to_shadow_sync) {
-			if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
+			if (nested_vmx_is_evmptr12_valid(vmx))
 				/*
 				 * L1 hypervisor is not obliged to keep eVMCS
 				 * clean fields data always up-to-date while
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index b0f2e26c1aeae..cce4e2aa30fbf 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -58,7 +58,7 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu)
 
 	/* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */
 	return vmx->nested.current_vmptr != -1ull ||
-		vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID;
+		nested_vmx_is_evmptr12_set(vmx);
 }
 
 static inline u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
-- 
GitLab


From c98842b26c233318bb18c77cc6e25859fe76c80e Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:28 +0100
Subject: [PATCH 0944/4076] KVM: nVMX: Introduce accessor to get Hyper-V eVMCS
 pointer

There's a number of 'vmx->nested.hv_evmcs' accesses in nested.c, introduce
'nested_vmx_evmcs()' accessor to hide them all in !CONFIG_KVM_HYPERV case.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-15-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/hyperv.h | 10 ++++++++++
 arch/x86/kvm/vmx/nested.c | 33 ++++++++++++++++++---------------
 2 files changed, 28 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h
index 71e90a16f1837..a87407412615c 100644
--- a/arch/x86/kvm/vmx/hyperv.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -37,6 +37,11 @@ static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx)
 	return evmptr_is_set(vmx->nested.hv_evmcs_vmptr);
 }
 
+static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx)
+{
+	return vmx->nested.hv_evmcs;
+}
+
 static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -75,6 +80,11 @@ static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx)
 {
 	return false;
 }
+
+static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx)
+{
+	return NULL;
+}
 #endif
 
 #endif /* __KVM_X86_VMX_HYPERV_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0507174750e04..4e872863a0c9c 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -263,7 +263,7 @@ static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr)
 	    !evmptr_is_valid(nested_get_evmptr(vcpu)))
 		return false;
 
-	if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr)
+	if (nested_vmx_evmcs(vmx) && vmptr == vmx->nested.hv_evmcs_vmptr)
 		nested_release_evmcs(vcpu);
 
 	return true;
@@ -601,7 +601,6 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	int msr;
 	unsigned long *msr_bitmap_l1;
 	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
-	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
 	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
@@ -617,10 +616,13 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	 * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature
 	 *   and tells KVM (L0) there were no changes in MSR bitmap for L2.
 	 */
-	if (!vmx->nested.force_msr_bitmap_recalc && evmcs &&
-	    evmcs->hv_enlightenments_control.msr_bitmap &&
-	    evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP)
-		return true;
+	if (!vmx->nested.force_msr_bitmap_recalc) {
+		struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
+
+		if (evmcs && evmcs->hv_enlightenments_control.msr_bitmap &&
+		    evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP)
+			return true;
+	}
 
 	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
 		return false;
@@ -1603,7 +1605,7 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields
 {
 #ifdef CONFIG_KVM_HYPERV
 	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
-	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu);
 
 	/* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */
@@ -1851,7 +1853,7 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
 {
 #ifdef CONFIG_KVM_HYPERV
 	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
-	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
 
 	/*
 	 * Should not be changed by KVM:
@@ -2438,7 +2440,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 
 static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 {
-	struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+	struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx);
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
 			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
@@ -2570,6 +2572,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			  enum vm_entry_failure_code *entry_failure_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
 	bool load_guest_pdptrs_vmcs12 = false;
 
 	if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) {
@@ -2577,8 +2580,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		vmx->nested.dirty_vmcs12 = false;
 
 		load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) ||
-			!(vmx->nested.hv_evmcs->hv_clean_fields &
-			  HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1);
+			!(evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1);
 	}
 
 	if (vmx->nested.nested_run_pending &&
@@ -2700,8 +2702,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * here.
 	 */
 	if (nested_vmx_is_evmptr12_valid(vmx))
-		vmx->nested.hv_evmcs->hv_clean_fields |=
-			HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+		evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 
 	return 0;
 }
@@ -3626,7 +3627,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return nested_vmx_failInvalid(vcpu);
 
 	if (nested_vmx_is_evmptr12_valid(vmx)) {
-		copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields);
+		struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx);
+
+		copy_enlightened_to_vmcs12(vmx, evmcs->hv_clean_fields);
 		/* Enlightened VMCS doesn't have launch state */
 		vmcs12->launch_state = !launch;
 	} else if (enable_shadow_vmcs) {
@@ -5428,7 +5431,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 			return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
 
 		/* Read the field, zero-extended to a u64 value */
-		value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset);
+		value = evmcs_read_any(nested_vmx_evmcs(vmx), field, offset);
 	}
 
 	/*
-- 
GitLab


From 5a30f97683af802c0fa24d1cfc339f87cdb6791b Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:29 +0100
Subject: [PATCH 0945/4076] KVM: nVMX: Hide more stuff under CONFIG_KVM_HYPERV

'hv_evmcs_vmptr'/'hv_evmcs_map'/'hv_evmcs' fields in 'struct nested_vmx'
should not be used when !CONFIG_KVM_HYPERV, hide them when
!CONFIG_KVM_HYPERV.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-16-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/vmx/nested.c | 2 ++
 arch/x86/kvm/vmx/vmx.c    | 3 +++
 arch/x86/kvm/vmx/vmx.h    | 2 ++
 3 files changed, 7 insertions(+)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 4e872863a0c9c..cf47b8b7f40f4 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6667,6 +6667,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 			return -EINVAL;
 
 		set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa);
+#ifdef CONFIG_KVM_HYPERV
 	} else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
 		/*
 		 * nested_vmx_handle_enlightened_vmptrld() cannot be called
@@ -6676,6 +6677,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		 */
 		vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING;
 		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+#endif
 	} else {
 		return -EINVAL;
 	}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3ff5c44dff9d5..a26603ddc968f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4828,7 +4828,10 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.vmxon_ptr = INVALID_GPA;
 	vmx->nested.current_vmptr = INVALID_GPA;
+
+#ifdef CONFIG_KVM_HYPERV
 	vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
+#endif
 
 	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 959c6d94287fc..8fe6eb2b4a34c 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -241,9 +241,11 @@ struct nested_vmx {
 		bool guest_mode;
 	} smm;
 
+#ifdef CONFIG_KVM_HYPERV
 	gpa_t hv_evmcs_vmptr;
 	struct kvm_host_map hv_evmcs_map;
 	struct hv_enlightened_vmcs *hv_evmcs;
+#endif
 };
 
 struct vcpu_vmx {
-- 
GitLab


From 017a99a966f1183e611f0b0fa6bec40160c81813 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 5 Dec 2023 11:36:30 +0100
Subject: [PATCH 0946/4076] KVM: nSVM: Hide more stuff under
 CONFIG_KVM_HYPERV/CONFIG_HYPERV

'struct hv_vmcb_enlightenments' in VMCB only make sense when either
CONFIG_KVM_HYPERV or CONFIG_HYPERV is enabled.

No functional change intended.

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20231205103630.1391318-17-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/nested.c | 20 ++++++++++++++------
 arch/x86/kvm/svm/svm.h    |  2 ++
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 74c04102ef01c..20212aac050b8 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -187,7 +187,6 @@ void recalc_intercepts(struct vcpu_svm *svm)
  */
 static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 {
-	struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
 	int i;
 
 	/*
@@ -198,11 +197,16 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	 * - Nested hypervisor (L1) is using Hyper-V emulation interface and
 	 * tells KVM (L0) there were no changes in MSR bitmap for L2.
 	 */
-	if (!svm->nested.force_msr_bitmap_recalc &&
-	    kvm_hv_hypercall_enabled(&svm->vcpu) &&
-	    hve->hv_enlightenments_control.msr_bitmap &&
-	    (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
-		goto set_msrpm_base_pa;
+#ifdef CONFIG_KVM_HYPERV
+	if (!svm->nested.force_msr_bitmap_recalc) {
+		struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
+
+		if (kvm_hv_hypercall_enabled(&svm->vcpu) &&
+		    hve->hv_enlightenments_control.msr_bitmap &&
+		    (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
+			goto set_msrpm_base_pa;
+	}
+#endif
 
 	if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return true;
@@ -230,7 +234,9 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 
 	svm->nested.force_msr_bitmap_recalc = false;
 
+#ifdef CONFIG_KVM_HYPERV
 set_msrpm_base_pa:
+#endif
 	svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm));
 
 	return true;
@@ -378,12 +384,14 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu,
 	to->msrpm_base_pa &= ~0x0fffULL;
 	to->iopm_base_pa  &= ~0x0fffULL;
 
+#ifdef CONFIG_KVM_HYPERV
 	/* Hyper-V extensions (Enlightened VMCB) */
 	if (kvm_hv_hypercall_enabled(vcpu)) {
 		to->clean = from->clean;
 		memcpy(&to->hv_enlightenments, &from->hv_enlightenments,
 		       sizeof(to->hv_enlightenments));
 	}
+#endif
 }
 
 void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index be67ab7fdd104..59adff7bbf554 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -148,7 +148,9 @@ struct vmcb_ctrl_area_cached {
 	u64 virt_ext;
 	u32 clean;
 	union {
+#if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV)
 		struct hv_vmcb_enlightenments hv_enlightenments;
+#endif
 		u8 reserved_sw[32];
 	};
 };
-- 
GitLab


From 9d03194a36345796d4f0f8d6b72eb770a45d614e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 28 Nov 2023 09:54:34 -0800
Subject: [PATCH 0947/4076] perf annotate: Introduce global annotation_options

The annotation options are to control the behavior of objdump and the
output.  It's basically used by 'perf annotate' but 'perf report' and
'perf top' can call it on TUI dynamically.

But it doesn't need to have a copy of annotation options in many places.

As most of the work is done in the util/annotate.c file, add a global
variable and set/use it instead of having their own copies.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231128175441.721579-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c | 43 +++++++++++++++++------------------
 tools/perf/util/annotate.c    |  3 +++
 tools/perf/util/annotate.h    |  2 ++
 3 files changed, 26 insertions(+), 22 deletions(-)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index a9129b51d5118..67b36a7a12e3e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -45,7 +45,6 @@
 struct perf_annotate {
 	struct perf_tool tool;
 	struct perf_session *session;
-	struct annotation_options opts;
 #ifdef HAVE_SLANG_SUPPORT
 	bool	   use_tui;
 #endif
@@ -318,9 +317,9 @@ static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_annotate *ann)
 {
 	if (!ann->use_stdio2)
-		return symbol__tty_annotate(&he->ms, evsel, &ann->opts);
+		return symbol__tty_annotate(&he->ms, evsel, &annotate_opts);
 
-	return symbol__tty_annotate2(&he->ms, evsel, &ann->opts);
+	return symbol__tty_annotate2(&he->ms, evsel, &annotate_opts);
 }
 
 static void hists__find_annotations(struct hists *hists,
@@ -376,14 +375,14 @@ find_next:
 				return;
 			}
 
-			ret = annotate(he, evsel, &ann->opts, NULL);
+			ret = annotate(he, evsel, &annotate_opts, NULL);
 			if (!ret || !ann->skip_missing)
 				return;
 
 			/* skip missing symbols */
 			nd = rb_next(nd);
 		} else if (use_browser == 1) {
-			key = hist_entry__tui_annotate(he, evsel, NULL, &ann->opts);
+			key = hist_entry__tui_annotate(he, evsel, NULL, &annotate_opts);
 
 			switch (key) {
 			case -1:
@@ -425,9 +424,9 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			goto out;
 	}
 
-	if (!ann->opts.objdump_path) {
+	if (!annotate_opts.objdump_path) {
 		ret = perf_env__lookup_objdump(&session->header.env,
-					       &ann->opts.objdump_path);
+					       &annotate_opts.objdump_path);
 		if (ret)
 			goto out;
 	}
@@ -561,9 +560,9 @@ int cmd_annotate(int argc, const char **argv)
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
 		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
-	OPT_BOOLEAN('l', "print-line", &annotate.opts.print_lines,
+	OPT_BOOLEAN('l', "print-line", &annotate_opts.print_lines,
 		    "print matching source lines (may be slow)"),
-	OPT_BOOLEAN('P', "full-paths", &annotate.opts.full_path,
+	OPT_BOOLEAN('P', "full-paths", &annotate_opts.full_path,
 		    "Don't shorten the displayed pathnames"),
 	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
 		    "Skip symbols that cannot be annotated"),
@@ -574,15 +573,15 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK(0, "symfs", NULL, "directory",
 		     "Look for files with symbols relative to this directory",
 		     symbol__config_symfs),
-	OPT_BOOLEAN(0, "source", &annotate.opts.annotate_src,
+	OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src,
 		    "Interleave source code with assembly code (default)"),
-	OPT_BOOLEAN(0, "asm-raw", &annotate.opts.show_asm_raw,
+	OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
-	OPT_STRING(0, "prefix", &annotate.opts.prefix, "prefix",
+	OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix",
 		    "Add prefix to source file path names in programs (with --prefix-strip)"),
-	OPT_STRING(0, "prefix-strip", &annotate.opts.prefix_strip, "N",
+	OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N",
 		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
@@ -601,7 +600,7 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
 			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
 			     stdio__config_color, "always"),
-	OPT_CALLBACK(0, "percent-type", &annotate.opts, "local-period",
+	OPT_CALLBACK(0, "percent-type", &annotate_opts, "local-period",
 		     "Set percent type local/global-period/hits",
 		     annotate_parse_percent_type),
 	OPT_CALLBACK(0, "percent-limit", &annotate, "percent",
@@ -617,13 +616,13 @@ int cmd_annotate(int argc, const char **argv)
 	set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE);
 
-	annotation_options__init(&annotate.opts);
+	annotation_options__init(&annotate_opts);
 
 	ret = hists__init();
 	if (ret < 0)
 		return ret;
 
-	annotation_config__init(&annotate.opts);
+	annotation_config__init(&annotate_opts);
 
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 	if (argc) {
@@ -638,13 +637,13 @@ int cmd_annotate(int argc, const char **argv)
 	}
 
 	if (disassembler_style) {
-		annotate.opts.disassembler_style = strdup(disassembler_style);
-		if (!annotate.opts.disassembler_style)
+		annotate_opts.disassembler_style = strdup(disassembler_style);
+		if (!annotate_opts.disassembler_style)
 			return -ENOMEM;
 	}
 	if (objdump_path) {
-		annotate.opts.objdump_path = strdup(objdump_path);
-		if (!annotate.opts.objdump_path)
+		annotate_opts.objdump_path = strdup(objdump_path);
+		if (!annotate_opts.objdump_path)
 			return -ENOMEM;
 	}
 	if (addr2line_path) {
@@ -653,7 +652,7 @@ int cmd_annotate(int argc, const char **argv)
 			return -ENOMEM;
 	}
 
-	if (annotate_check_args(&annotate.opts) < 0)
+	if (annotate_check_args(&annotate_opts) < 0)
 		return -EINVAL;
 
 #ifdef HAVE_GTK2_SUPPORT
@@ -734,7 +733,7 @@ out_delete:
 #ifndef NDEBUG
 	perf_session__delete(annotate.session);
 #endif
-	annotation_options__exit(&annotate.opts);
+	annotation_options__exit(&annotate_opts);
 
 	return ret;
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 9a828dc601c75..77b78001b94d0 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -57,6 +57,9 @@
 
 #include <linux/ctype.h>
 
+/* global annotation options */
+struct annotation_options annotate_opts;
+
 static regex_t	 file_lineno;
 
 static struct ins_ops *ins__find(struct arch *arch, const char *name);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index b64a2be287b30..8c1a070725faa 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -105,6 +105,8 @@ struct annotation_options {
 	unsigned int percent_type;
 };
 
+extern struct annotation_options annotate_opts;
+
 enum {
 	ANNOTATION__OFFSET_JUMP_TARGETS = 1,
 	ANNOTATION__OFFSET_CALL,
-- 
GitLab


From 14953f038d6b30e3dc9d1aa4d4584ac505e5a8ec Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 28 Nov 2023 09:54:35 -0800
Subject: [PATCH 0948/4076] perf report: Convert to the global
 annotation_options

Use the global option and drop the local copy.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231128175441.721579-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c | 33 ++++++++++++++++-----------------
 1 file changed, 16 insertions(+), 17 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 121a2781323c8..90f98953587c0 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -98,7 +98,6 @@ struct report {
 	bool			skip_empty;
 	int			max_stack;
 	struct perf_read_values	show_threads_values;
-	struct annotation_options annotation_opts;
 	const char		*pretty_printing_style;
 	const char		*cpu_list;
 	const char		*symbol_filter_str;
@@ -542,7 +541,7 @@ static int evlist__tui_block_hists_browse(struct evlist *evlist, struct report *
 		ret = report__browse_block_hists(&rep->block_reports[i++].hist,
 						 rep->min_percent, pos,
 						 &rep->session->header.env,
-						 &rep->annotation_opts);
+						 &annotate_opts);
 		if (ret != 0)
 			return ret;
 	}
@@ -670,7 +669,7 @@ static int report__browse_hists(struct report *rep)
 		}
 
 		ret = evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent,
-					       &session->header.env, true, &rep->annotation_opts);
+					       &session->header.env, true, &annotate_opts);
 		/*
 		 * Usually "ret" is the last pressed key, and we only
 		 * care if the key notifies us to switch data file.
@@ -745,7 +744,7 @@ static int hists__resort_cb(struct hist_entry *he, void *arg)
 	if (rep->symbol_ipc && sym && !sym->annotate2) {
 		struct evsel *evsel = hists_to_evsel(he->hists);
 
-		symbol__annotate2(&he->ms, evsel, &rep->annotation_opts, NULL);
+		symbol__annotate2(&he->ms, evsel, &annotate_opts, NULL);
 	}
 
 	return 0;
@@ -1341,15 +1340,15 @@ int cmd_report(int argc, const char **argv)
 		   "list of cpus to profile"),
 	OPT_BOOLEAN('I', "show-info", &report.show_full_info,
 		    "Display extended information about perf.data file"),
-	OPT_BOOLEAN(0, "source", &report.annotation_opts.annotate_src,
+	OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src,
 		    "Interleave source code with assembly code (default)"),
-	OPT_BOOLEAN(0, "asm-raw", &report.annotation_opts.show_asm_raw,
+	OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
-	OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix",
+	OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix",
 		    "Add prefix to source file path names in programs (with --prefix-strip)"),
-	OPT_STRING(0, "prefix-strip", &report.annotation_opts.prefix_strip, "N",
+	OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N",
 		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
@@ -1401,7 +1400,7 @@ int cmd_report(int argc, const char **argv)
 		   "Time span of interest (start,stop)"),
 	OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
 		    "Show inline function"),
-	OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period",
+	OPT_CALLBACK(0, "percent-type", &annotate_opts, "local-period",
 		     "Set percent type local/global-period/hits",
 		     annotate_parse_percent_type),
 	OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Show times in nanosecs"),
@@ -1433,7 +1432,7 @@ int cmd_report(int argc, const char **argv)
 	 */
 	symbol_conf.keep_exited_threads = true;
 
-	annotation_options__init(&report.annotation_opts);
+	annotation_options__init(&annotate_opts);
 
 	ret = perf_config(report__config, &report);
 	if (ret)
@@ -1452,13 +1451,13 @@ int cmd_report(int argc, const char **argv)
 	}
 
 	if (disassembler_style) {
-		report.annotation_opts.disassembler_style = strdup(disassembler_style);
-		if (!report.annotation_opts.disassembler_style)
+		annotate_opts.disassembler_style = strdup(disassembler_style);
+		if (!annotate_opts.disassembler_style)
 			return -ENOMEM;
 	}
 	if (objdump_path) {
-		report.annotation_opts.objdump_path = strdup(objdump_path);
-		if (!report.annotation_opts.objdump_path)
+		annotate_opts.objdump_path = strdup(objdump_path);
+		if (!annotate_opts.objdump_path)
 			return -ENOMEM;
 	}
 	if (addr2line_path) {
@@ -1467,7 +1466,7 @@ int cmd_report(int argc, const char **argv)
 			return -ENOMEM;
 	}
 
-	if (annotate_check_args(&report.annotation_opts) < 0) {
+	if (annotate_check_args(&annotate_opts) < 0) {
 		ret = -EINVAL;
 		goto exit;
 	}
@@ -1699,7 +1698,7 @@ repeat:
 			 */
 			symbol_conf.priv_size += sizeof(u32);
 		}
-		annotation_config__init(&report.annotation_opts);
+		annotation_config__init(&annotate_opts);
 	}
 
 	if (symbol__init(&session->header.env) < 0)
@@ -1753,7 +1752,7 @@ error:
 	zstd_fini(&(session->zstd_data));
 	perf_session__delete(session);
 exit:
-	annotation_options__exit(&report.annotation_opts);
+	annotation_options__exit(&annotate_opts);
 	free(sort_order_help);
 	free(field_order_help);
 	return ret;
-- 
GitLab


From c9a21a872c69032cb9a94ebc171649c0c28141d7 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 28 Nov 2023 09:54:36 -0800
Subject: [PATCH 0949/4076] perf top: Convert to the global annotation_options

Use the global option and drop the local copy.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231128175441.721579-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c | 44 ++++++++++++++++++++--------------------
 tools/perf/util/top.h    |  1 -
 2 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1e42bd1c7d5a5..a6495aa5898ed 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -147,7 +147,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL);
+	err = symbol__annotate(&he->ms, evsel, &annotate_opts, NULL);
 	if (err == 0) {
 		top->sym_filter_entry = he;
 	} else {
@@ -261,9 +261,9 @@ static void perf_top__show_details(struct perf_top *top)
 		goto out_unlock;
 
 	printf("Showing %s for %s\n", evsel__name(top->sym_evsel), symbol->name);
-	printf("  Events  Pcnt (>=%d%%)\n", top->annotation_opts.min_pcnt);
+	printf("  Events  Pcnt (>=%d%%)\n", annotate_opts.min_pcnt);
 
-	more = symbol__annotate_printf(&he->ms, top->sym_evsel, &top->annotation_opts);
+	more = symbol__annotate_printf(&he->ms, top->sym_evsel, &annotate_opts);
 
 	if (top->evlist->enabled) {
 		if (top->zero)
@@ -450,7 +450,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top)
 
 	fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", top->count_filter);
 
-	fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", top->annotation_opts.min_pcnt);
+	fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", annotate_opts.min_pcnt);
 	fprintf(stdout, "\t[s]     annotate symbol.                   \t(%s)\n", name?: "NULL");
 	fprintf(stdout, "\t[S]     stop annotation.\n");
 
@@ -553,7 +553,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 			prompt_integer(&top->count_filter, "Enter display event count filter");
 			break;
 		case 'F':
-			prompt_percent(&top->annotation_opts.min_pcnt,
+			prompt_percent(&annotate_opts.min_pcnt,
 				       "Enter details display event filter (percent)");
 			break;
 		case 'K':
@@ -647,7 +647,7 @@ repeat:
 
 	ret = evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
 				       &top->session->header.env, !top->record_opts.overwrite,
-				       &top->annotation_opts);
+				       &annotate_opts);
 	if (ret == K_RELOAD) {
 		top->zero = true;
 		goto repeat;
@@ -1241,9 +1241,9 @@ static int __cmd_top(struct perf_top *top)
 	pthread_t thread, thread_process;
 	int ret;
 
-	if (!top->annotation_opts.objdump_path) {
+	if (!annotate_opts.objdump_path) {
 		ret = perf_env__lookup_objdump(&top->session->header.env,
-					       &top->annotation_opts.objdump_path);
+					       &annotate_opts.objdump_path);
 		if (ret)
 			return ret;
 	}
@@ -1536,9 +1536,9 @@ int cmd_top(int argc, const char **argv)
 		   "only consider symbols in these comms"),
 	OPT_STRING(0, "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
-	OPT_BOOLEAN(0, "source", &top.annotation_opts.annotate_src,
+	OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src,
 		    "Interleave source code with assembly code (default)"),
-	OPT_BOOLEAN(0, "asm-raw", &top.annotation_opts.show_asm_raw,
+	OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
@@ -1549,9 +1549,9 @@ int cmd_top(int argc, const char **argv)
 		   "addr2line binary to use for line numbers"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
-	OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix",
+	OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix",
 		    "Add prefix to source file path names in programs (with --prefix-strip)"),
-	OPT_STRING(0, "prefix-strip", &top.annotation_opts.prefix_strip, "N",
+	OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N",
 		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
 	OPT_CALLBACK(0, "percent-limit", &top, "percent",
@@ -1609,10 +1609,10 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		return status;
 
-	annotation_options__init(&top.annotation_opts);
+	annotation_options__init(&annotate_opts);
 
-	top.annotation_opts.min_pcnt = 5;
-	top.annotation_opts.context  = 4;
+	annotate_opts.min_pcnt = 5;
+	annotate_opts.context  = 4;
 
 	top.evlist = evlist__new();
 	if (top.evlist == NULL)
@@ -1642,13 +1642,13 @@ int cmd_top(int argc, const char **argv)
 		usage_with_options(top_usage, options);
 
 	if (disassembler_style) {
-		top.annotation_opts.disassembler_style = strdup(disassembler_style);
-		if (!top.annotation_opts.disassembler_style)
+		annotate_opts.disassembler_style = strdup(disassembler_style);
+		if (!annotate_opts.disassembler_style)
 			return -ENOMEM;
 	}
 	if (objdump_path) {
-		top.annotation_opts.objdump_path = strdup(objdump_path);
-		if (!top.annotation_opts.objdump_path)
+		annotate_opts.objdump_path = strdup(objdump_path);
+		if (!annotate_opts.objdump_path)
 			return -ENOMEM;
 	}
 	if (addr2line_path) {
@@ -1661,7 +1661,7 @@ int cmd_top(int argc, const char **argv)
 	if (status)
 		goto out_delete_evlist;
 
-	if (annotate_check_args(&top.annotation_opts) < 0)
+	if (annotate_check_args(&annotate_opts) < 0)
 		goto out_delete_evlist;
 
 	if (!top.evlist->core.nr_entries) {
@@ -1787,7 +1787,7 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		goto out_delete_evlist;
 
-	annotation_config__init(&top.annotation_opts);
+	annotation_config__init(&annotate_opts);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	status = symbol__init(NULL);
@@ -1840,7 +1840,7 @@ int cmd_top(int argc, const char **argv)
 out_delete_evlist:
 	evlist__delete(top.evlist);
 	perf_session__delete(top.session);
-	annotation_options__exit(&top.annotation_opts);
+	annotation_options__exit(&annotate_opts);
 
 	return status;
 }
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index a8b0d79bd96cf..4c5588dbb1317 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -21,7 +21,6 @@ struct perf_top {
 	struct perf_tool   tool;
 	struct evlist *evlist, *sb_evlist;
 	struct record_opts record_opts;
-	struct annotation_options annotation_opts;
 	struct evswitch	   evswitch;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
-- 
GitLab


From 41fd3cacd29f47f6b9c6474b27c5b0513786c4e9 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 28 Nov 2023 09:54:37 -0800
Subject: [PATCH 0950/4076] perf annotate: Use global annotation_options

Now it can directly use the global options and no need to pass it as an
argument.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231128175441.721579-5-namhyung@kernel.org
[ Fixup build with GTK2=1 ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c     |   7 +-
 tools/perf/builtin-report.c       |   2 +-
 tools/perf/builtin-top.c          |   4 +-
 tools/perf/ui/browsers/annotate.c |   6 +-
 tools/perf/ui/gtk/annotate.c      |   6 +-
 tools/perf/ui/gtk/gtk.h           |   2 -
 tools/perf/util/annotate.c        | 118 ++++++++++++++----------------
 tools/perf/util/annotate.h        |  15 ++--
 8 files changed, 71 insertions(+), 89 deletions(-)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 67b36a7a12e3e..9c1e2b2b5bc0b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -317,9 +317,9 @@ static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_annotate *ann)
 {
 	if (!ann->use_stdio2)
-		return symbol__tty_annotate(&he->ms, evsel, &annotate_opts);
+		return symbol__tty_annotate(&he->ms, evsel);
 
-	return symbol__tty_annotate2(&he->ms, evsel, &annotate_opts);
+	return symbol__tty_annotate2(&he->ms, evsel);
 }
 
 static void hists__find_annotations(struct hists *hists,
@@ -365,7 +365,6 @@ find_next:
 			int ret;
 			int (*annotate)(struct hist_entry *he,
 					struct evsel *evsel,
-					struct annotation_options *options,
 					struct hist_browser_timer *hbt);
 
 			annotate = dlsym(perf_gtk_handle,
@@ -375,7 +374,7 @@ find_next:
 				return;
 			}
 
-			ret = annotate(he, evsel, &annotate_opts, NULL);
+			ret = annotate(he, evsel, NULL);
 			if (!ret || !ann->skip_missing)
 				return;
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 90f98953587c0..2b86651615cd7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -744,7 +744,7 @@ static int hists__resort_cb(struct hist_entry *he, void *arg)
 	if (rep->symbol_ipc && sym && !sym->annotate2) {
 		struct evsel *evsel = hists_to_evsel(he->hists);
 
-		symbol__annotate2(&he->ms, evsel, &annotate_opts, NULL);
+		symbol__annotate2(&he->ms, evsel, NULL);
 	}
 
 	return 0;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a6495aa5898ed..46a61634701b7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -147,7 +147,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(&he->ms, evsel, &annotate_opts, NULL);
+	err = symbol__annotate(&he->ms, evsel, NULL);
 	if (err == 0) {
 		top->sym_filter_entry = he;
 	} else {
@@ -263,7 +263,7 @@ static void perf_top__show_details(struct perf_top *top)
 	printf("Showing %s for %s\n", evsel__name(top->sym_evsel), symbol->name);
 	printf("  Events  Pcnt (>=%d%%)\n", annotate_opts.min_pcnt);
 
-	more = symbol__annotate_printf(&he->ms, top->sym_evsel, &annotate_opts);
+	more = symbol__annotate_printf(&he->ms, top->sym_evsel);
 
 	if (top->evlist->enabled) {
 		if (top->zero)
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 163f916fff68e..ed0e692afdbe9 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -114,7 +114,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	if (!browser->navkeypressed)
 		ops.width += 1;
 
-	annotation_line__write(al, notes, &ops, ab->opts);
+	annotation_line__write(al, notes, &ops);
 
 	if (ops.current_entry)
 		ab->selection = al;
@@ -884,7 +884,7 @@ show_sup_ins:
 			continue;
 		}
 		case 'P':
-			map_symbol__annotation_dump(ms, evsel, browser->opts);
+			map_symbol__annotation_dump(ms, evsel);
 			continue;
 		case 't':
 			if (symbol_conf.show_total_period) {
@@ -979,7 +979,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 		return -1;
 
 	if (not_annotated) {
-		err = symbol__annotate2(ms, evsel, opts, &browser.arch);
+		err = symbol__annotate2(ms, evsel, &browser.arch);
 		if (err) {
 			char msg[BUFSIZ];
 			dso->annotate_warned = true;
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 2effac77ca8c6..394861245fd3e 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -162,7 +162,6 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct map_symbol *ms,
 }
 
 static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
-				struct annotation_options *options,
 				struct hist_browser_timer *hbt)
 {
 	struct dso *dso = map__dso(ms->map);
@@ -176,7 +175,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (dso->annotate_warned)
 		return -1;
 
-	err = symbol__annotate(ms, evsel, options, NULL);
+	err = symbol__annotate(ms, evsel, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		dso->annotate_warned = true;
@@ -244,10 +243,9 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 int hist_entry__gtk_annotate(struct hist_entry *he,
 			     struct evsel *evsel,
-			     struct annotation_options *options,
 			     struct hist_browser_timer *hbt)
 {
-	return symbol__gtk_annotate(&he->ms, evsel, options, hbt);
+	return symbol__gtk_annotate(&he->ms, evsel, hbt);
 }
 
 void perf_gtk__show_annotations(void)
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index 1e84dceb52671..a2b497f03fd6e 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -56,13 +56,11 @@ struct evsel;
 struct evlist;
 struct hist_entry;
 struct hist_browser_timer;
-struct annotation_options;
 
 int evlist__gtk_browse_hists(struct evlist *evlist, const char *help,
 			     struct hist_browser_timer *hbt, float min_pcnt);
 int hist_entry__gtk_annotate(struct hist_entry *he,
 			     struct evsel *evsel,
-			     struct annotation_options *options,
 			     struct hist_browser_timer *hbt);
 void perf_gtk__show_annotations(void);
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 77b78001b94d0..daff9af552f4f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1896,7 +1896,6 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 				   struct annotate_args *args)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	struct annotation_options *opts = args->options;
 	struct bpf_prog_linfo *prog_linfo = NULL;
 	struct bpf_prog_info_node *info_node;
 	int len = sym->end - sym->start;
@@ -2006,7 +2005,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 		prev_buf_size = buf_size;
 		fflush(s);
 
-		if (!opts->hide_src_code && srcline) {
+		if (!annotate_opts.hide_src_code && srcline) {
 			args->offset = -1;
 			args->line = strdup(srcline);
 			args->line_nr = 0;
@@ -2129,7 +2128,7 @@ static char *expand_tabs(char *line, char **storage, size_t *storage_len)
 
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
-	struct annotation_options *opts = args->options;
+	struct annotation_options *opts = &annotate_opts;
 	struct map *map = args->ms.map;
 	struct dso *dso = map__dso(map);
 	char *command;
@@ -2380,13 +2379,13 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 }
 
 int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
-		     struct annotation_options *options, struct arch **parch)
+		     struct arch **parch)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
 	struct annotate_args args = {
 		.evsel		= evsel,
-		.options	= options,
+		.options	= &annotate_opts,
 	};
 	struct perf_env *env = evsel__env(evsel);
 	const char *arch_name = perf_env__arch(env);
@@ -2414,7 +2413,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	}
 
 	args.ms = *ms;
-	if (notes->options && notes->options->full_addr)
+	if (annotate_opts.full_addr)
 		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
 		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
@@ -2422,12 +2421,12 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	return symbol__disassemble(sym, &args);
 }
 
-static void insert_source_line(struct rb_root *root, struct annotation_line *al,
-			       struct annotation_options *opts)
+static void insert_source_line(struct rb_root *root, struct annotation_line *al)
 {
 	struct annotation_line *iter;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
+	unsigned int percent_type = annotate_opts.percent_type;
 	int i, ret;
 
 	while (*p != NULL) {
@@ -2438,7 +2437,7 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al,
 		if (ret == 0) {
 			for (i = 0; i < al->data_nr; i++) {
 				iter->data[i].percent_sum += annotation_data__percent(&al->data[i],
-										      opts->percent_type);
+										      percent_type);
 			}
 			return;
 		}
@@ -2451,7 +2450,7 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al,
 
 	for (i = 0; i < al->data_nr; i++) {
 		al->data[i].percent_sum = annotation_data__percent(&al->data[i],
-								   opts->percent_type);
+								   percent_type);
 	}
 
 	rb_link_node(&al->rb_node, parent, p);
@@ -2573,8 +2572,7 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start)
 	return 0;
 }
 
-int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
-			    struct annotation_options *opts)
+int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct map *map = ms->map;
 	struct symbol *sym = ms->sym;
@@ -2585,6 +2583,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evsel->core.idx);
 	struct annotation_line *pos, *queue = NULL;
+	struct annotation_options *opts = &annotate_opts;
 	u64 start = map__rip_2objdump(map, sym->start);
 	int printed = 2, queue_len = 0, addr_fmt_width;
 	int more = 0;
@@ -2713,8 +2712,7 @@ static void FILE__write_graph(void *fp, int graph)
 	fputs(s, fp);
 }
 
-static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
-				     struct annotation_options *opts)
+static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct annotation_write_ops wops = {
@@ -2731,7 +2729,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
 	list_for_each_entry(al, &notes->src->source, node) {
 		if (annotation_line__filter(al, notes))
 			continue;
-		annotation_line__write(al, notes, &wops, opts);
+		annotation_line__write(al, notes, &wops);
 		fputc('\n', fp);
 		wops.first_line = false;
 	}
@@ -2739,8 +2737,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
 	return 0;
 }
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
-				struct annotation_options *opts)
+int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel)
 {
 	const char *ev_name = evsel__name(evsel);
 	char buf[1024];
@@ -2762,7 +2759,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
 
 	fprintf(fp, "%s() %s\nEvent: %s\n\n",
 		ms->sym->name, map__dso(ms->map)->long_name, ev_name);
-	symbol__annotate_fprintf2(ms->sym, fp, opts);
+	symbol__annotate_fprintf2(ms->sym, fp);
 
 	fclose(fp);
 	err = 0;
@@ -2939,24 +2936,24 @@ void annotation__init_column_widths(struct annotation *notes, struct symbol *sym
 
 void annotation__update_column_widths(struct annotation *notes)
 {
-	if (notes->options->use_offset)
+	if (annotate_opts.use_offset)
 		notes->widths.target = notes->widths.min_addr;
-	else if (notes->options->full_addr)
+	else if (annotate_opts.full_addr)
 		notes->widths.target = BITS_PER_LONG / 4;
 	else
 		notes->widths.target = notes->widths.max_addr;
 
 	notes->widths.addr = notes->widths.target;
 
-	if (notes->options->show_nr_jumps)
+	if (annotate_opts.show_nr_jumps)
 		notes->widths.addr += notes->widths.jumps + 1;
 }
 
 void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms)
 {
-	notes->options->full_addr = !notes->options->full_addr;
+	annotate_opts.full_addr = !annotate_opts.full_addr;
 
-	if (notes->options->full_addr)
+	if (annotate_opts.full_addr)
 		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
 		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
@@ -2965,8 +2962,7 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m
 }
 
 static void annotation__calc_lines(struct annotation *notes, struct map *map,
-				   struct rb_root *root,
-				   struct annotation_options *opts)
+				   struct rb_root *root)
 {
 	struct annotation_line *al;
 	struct rb_root tmp_root = RB_ROOT;
@@ -2979,7 +2975,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 			double percent;
 
 			percent = annotation_data__percent(&al->data[i],
-							   opts->percent_type);
+							   annotate_opts.percent_type);
 
 			if (percent > percent_max)
 				percent_max = percent;
@@ -2990,22 +2986,20 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 
 		al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL,
 				       false, true, notes->start + al->offset);
-		insert_source_line(&tmp_root, al, opts);
+		insert_source_line(&tmp_root, al);
 	}
 
 	resort_source_line(root, &tmp_root);
 }
 
-static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root,
-			       struct annotation_options *opts)
+static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root)
 {
 	struct annotation *notes = symbol__annotation(ms->sym);
 
-	annotation__calc_lines(notes, ms->map, root, opts);
+	annotation__calc_lines(notes, ms->map, root);
 }
 
-int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
-			  struct annotation_options *opts)
+int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct dso *dso = map__dso(ms->map);
 	struct symbol *sym = ms->sym;
@@ -3014,7 +3008,7 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
 	char buf[1024];
 	int err;
 
-	err = symbol__annotate2(ms, evsel, opts, NULL);
+	err = symbol__annotate2(ms, evsel, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 
@@ -3024,31 +3018,31 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
 		return -1;
 	}
 
-	if (opts->print_lines) {
-		srcline_full_filename = opts->full_path;
-		symbol__calc_lines(ms, &source_line, opts);
+	if (annotate_opts.print_lines) {
+		srcline_full_filename = annotate_opts.full_path;
+		symbol__calc_lines(ms, &source_line);
 		print_summary(&source_line, dso->long_name);
 	}
 
 	hists__scnprintf_title(hists, buf, sizeof(buf));
 	fprintf(stdout, "%s, [percent: %s]\n%s() %s\n",
-		buf, percent_type_str(opts->percent_type), sym->name, dso->long_name);
-	symbol__annotate_fprintf2(sym, stdout, opts);
+		buf, percent_type_str(annotate_opts.percent_type), sym->name,
+		dso->long_name);
+	symbol__annotate_fprintf2(sym, stdout);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
 
 	return 0;
 }
 
-int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
-			 struct annotation_options *opts)
+int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct dso *dso = map__dso(ms->map);
 	struct symbol *sym = ms->sym;
 	struct rb_root source_line = RB_ROOT;
 	int err;
 
-	err = symbol__annotate(ms, evsel, opts, NULL);
+	err = symbol__annotate(ms, evsel, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 
@@ -3060,13 +3054,13 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 	symbol__calc_percent(sym, evsel);
 
-	if (opts->print_lines) {
-		srcline_full_filename = opts->full_path;
-		symbol__calc_lines(ms, &source_line, opts);
+	if (annotate_opts.print_lines) {
+		srcline_full_filename = annotate_opts.full_path;
+		symbol__calc_lines(ms, &source_line);
 		print_summary(&source_line, dso->long_name);
 	}
 
-	symbol__annotate_printf(ms, evsel, opts);
+	symbol__annotate_printf(ms, evsel);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
 
@@ -3127,7 +3121,7 @@ call_like:
 		obj__printf(obj, "  ");
 	}
 
-	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset, notes->widths.max_ins_name);
+	disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset, notes->widths.max_ins_name);
 }
 
 static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
@@ -3210,7 +3204,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		else
 			obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
 
-		if (!notes->options->show_minmax_cycle) {
+		if (!annotate_opts.show_minmax_cycle) {
 			if (al->cycles && al->cycles->avg)
 				obj__printf(obj, "%*" PRIu64 " ",
 					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles->avg);
@@ -3254,7 +3248,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	if (!*al->line)
 		obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " ");
 	else if (al->offset == -1) {
-		if (al->line_nr && notes->options->show_linenr)
+		if (al->line_nr && annotate_opts.show_linenr)
 			printed = scnprintf(bf, sizeof(bf), "%-*d ", notes->widths.addr + 1, al->line_nr);
 		else
 			printed = scnprintf(bf, sizeof(bf), "%-*s  ", notes->widths.addr, " ");
@@ -3264,15 +3258,15 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		u64 addr = al->offset;
 		int color = -1;
 
-		if (!notes->options->use_offset)
+		if (!annotate_opts.use_offset)
 			addr += notes->start;
 
-		if (!notes->options->use_offset) {
+		if (!annotate_opts.use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
 		} else {
 			if (al->jump_sources &&
-			    notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
-				if (notes->options->show_nr_jumps) {
+			    annotate_opts.offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
+				if (annotate_opts.show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
 							    notes->widths.jumps,
@@ -3286,9 +3280,9 @@ print_addr:
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
 						    notes->widths.target, addr);
 			} else if (ins__is_call(&disasm_line(al)->ins) &&
-				   notes->options->offset_level >= ANNOTATION__OFFSET_CALL) {
+				   annotate_opts.offset_level >= ANNOTATION__OFFSET_CALL) {
 				goto print_addr;
-			} else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
+			} else if (annotate_opts.offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
 				goto print_addr;
 			} else {
 				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
@@ -3310,19 +3304,18 @@ print_addr:
 }
 
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
-			    struct annotation_write_ops *wops,
-			    struct annotation_options *opts)
+			    struct annotation_write_ops *wops)
 {
 	__annotation_line__write(al, notes, wops->first_line, wops->current_entry,
 				 wops->change_color, wops->width, wops->obj,
-				 opts->percent_type,
+				 annotate_opts.percent_type,
 				 wops->set_color, wops->set_percent_color,
 				 wops->set_jumps_percent_color, wops->printf,
 				 wops->write_graph);
 }
 
 int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
-		      struct annotation_options *options, struct arch **parch)
+		      struct arch **parch)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
@@ -3336,11 +3329,11 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	if (evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
-	err = symbol__annotate(ms, evsel, options, parch);
+	err = symbol__annotate(ms, evsel, parch);
 	if (err)
 		goto out_free_offsets;
 
-	notes->options = options;
+	notes->options = &annotate_opts;
 
 	symbol__calc_percent(sym, evsel);
 
@@ -3468,10 +3461,9 @@ static unsigned int parse_percent_type(char *str1, char *str2)
 	return type;
 }
 
-int annotate_parse_percent_type(const struct option *opt, const char *_str,
+int annotate_parse_percent_type(const struct option *opt __maybe_unused, const char *_str,
 				int unset __maybe_unused)
 {
-	struct annotation_options *opts = opt->value;
 	unsigned int type;
 	char *str1, *str2;
 	int err = -1;
@@ -3490,7 +3482,7 @@ int annotate_parse_percent_type(const struct option *opt, const char *_str,
 	if (type == (unsigned int) -1)
 		type = parse_percent_type(str2, str1);
 	if (type != (unsigned int) -1) {
-		opts->percent_type = type;
+		annotate_opts.percent_type = type;
 		err = 0;
 	}
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 8c1a070725faa..7bf29baa43f54 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -224,8 +224,7 @@ struct annotation_write_ops {
 };
 
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
-			    struct annotation_write_ops *ops,
-			    struct annotation_options *opts);
+			    struct annotation_write_ops *ops);
 
 int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   char *bf, size_t size,
@@ -375,11 +374,9 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct map_symbol *ms,
 		     struct evsel *evsel,
-		     struct annotation_options *options,
 		     struct arch **parch);
 int symbol__annotate2(struct map_symbol *ms,
 		      struct evsel *evsel,
-		      struct annotation_options *options,
 		      struct arch **parch);
 
 enum symbol_disassemble_errno {
@@ -406,20 +403,18 @@ enum symbol_disassemble_errno {
 
 int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen);
 
-int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
-			    struct annotation_options *options);
+int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void annotated_source__purge(struct annotated_source *as);
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
-				struct annotation_options *opts);
+int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel);
 
 bool ui__has_annotation(void);
 
-int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts);
+int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel);
 
-int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts);
+int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel);
 
 #ifdef HAVE_SLANG_SUPPORT
 int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-- 
GitLab


From 22197fb296913f83c7182befd2a8b23bf042f279 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 28 Nov 2023 09:54:38 -0800
Subject: [PATCH 0951/4076] perf ui/browser/annotate: Use global
 annotation_options

Now it can use the global options and no need save local browser
options separately.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231128175441.721579-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c     |  2 +-
 tools/perf/builtin-report.c       |  8 ++--
 tools/perf/builtin-top.c          |  3 +-
 tools/perf/ui/browsers/annotate.c | 65 ++++++++++++++-----------------
 tools/perf/ui/browsers/hists.c    | 34 ++++++----------
 tools/perf/ui/browsers/hists.h    |  2 -
 tools/perf/util/annotate.h        |  6 +--
 tools/perf/util/block-info.c      |  6 +--
 tools/perf/util/block-info.h      |  3 +-
 tools/perf/util/hist.h            | 25 ++++--------
 10 files changed, 59 insertions(+), 95 deletions(-)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 9c1e2b2b5bc0b..d17213bd83327 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -381,7 +381,7 @@ find_next:
 			/* skip missing symbols */
 			nd = rb_next(nd);
 		} else if (use_browser == 1) {
-			key = hist_entry__tui_annotate(he, evsel, NULL, &annotate_opts);
+			key = hist_entry__tui_annotate(he, evsel, NULL);
 
 			switch (key) {
 			case -1:
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2b86651615cd7..bc0d986c1e0c1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -540,8 +540,7 @@ static int evlist__tui_block_hists_browse(struct evlist *evlist, struct report *
 	evlist__for_each_entry(evlist, pos) {
 		ret = report__browse_block_hists(&rep->block_reports[i++].hist,
 						 rep->min_percent, pos,
-						 &rep->session->header.env,
-						 &annotate_opts);
+						 &rep->session->header.env);
 		if (ret != 0)
 			return ret;
 	}
@@ -573,8 +572,7 @@ static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, c
 
 		if (rep->total_cycles_mode) {
 			report__browse_block_hists(&rep->block_reports[i++].hist,
-						   rep->min_percent, pos,
-						   NULL, NULL);
+						   rep->min_percent, pos, NULL);
 			continue;
 		}
 
@@ -669,7 +667,7 @@ static int report__browse_hists(struct report *rep)
 		}
 
 		ret = evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent,
-					       &session->header.env, true, &annotate_opts);
+					       &session->header.env, true);
 		/*
 		 * Usually "ret" is the last pressed key, and we only
 		 * care if the key notifies us to switch data file.
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 46a61634701b7..b5222d2419832 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -646,8 +646,7 @@ repeat:
 	}
 
 	ret = evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
-				       &top->session->header.env, !top->record_opts.overwrite,
-				       &annotate_opts);
+				       &top->session->header.env, !top->record_opts.overwrite);
 	if (ret == K_RELOAD) {
 		top->zero = true;
 		goto repeat;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ed0e692afdbe9..fda17c1f20319 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -27,7 +27,6 @@ struct annotate_browser {
 	struct rb_node		   *curr_hot;
 	struct annotation_line	   *selection;
 	struct arch		   *arch;
-	struct annotation_options  *opts;
 	bool			    searching_backwards;
 	char			    search_bf[128];
 };
@@ -97,7 +96,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	struct annotation_write_ops ops = {
 		.first_line		 = row == 0,
 		.current_entry		 = is_current_entry,
-		.change_color		 = (!notes->options->hide_src_code &&
+		.change_color		 = (!annotate_opts.hide_src_code &&
 					    (!is_current_entry ||
 					     (browser->use_navkeypressed &&
 					      !browser->navkeypressed))),
@@ -128,7 +127,7 @@ static int is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 
 	while (pos && pos->al.offset == -1) {
 		pos = list_prev_entry(pos, al.node);
-		if (!ab->opts->hide_src_code)
+		if (!annotate_opts.hide_src_code)
 			diff++;
 	}
 
@@ -195,7 +194,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		return;
 	}
 
-	if (notes->options->hide_src_code) {
+	if (annotate_opts.hide_src_code) {
 		from = cursor->al.idx_asm;
 		to = target->idx_asm;
 	} else {
@@ -224,7 +223,7 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 	int ret = ui_browser__list_head_refresh(browser);
 	int pcnt_width = annotation__pcnt_width(notes);
 
-	if (notes->options->jump_arrows)
+	if (annotate_opts.jump_arrows)
 		annotate_browser__draw_current_jump(browser);
 
 	ui_browser__set_color(browser, HE_COLORSET_NORMAL);
@@ -258,7 +257,7 @@ static void disasm_rb_tree__insert(struct annotate_browser *browser,
 		parent = *p;
 		l = rb_entry(parent, struct annotation_line, rb_node);
 
-		if (disasm__cmp(al, l, browser->opts->percent_type) < 0)
+		if (disasm__cmp(al, l, annotate_opts.percent_type) < 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -294,11 +293,10 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 static void annotate_browser__set_rb_top(struct annotate_browser *browser,
 					 struct rb_node *nd)
 {
-	struct annotation *notes = browser__annotation(&browser->b);
 	struct annotation_line * pos = rb_entry(nd, struct annotation_line, rb_node);
 	u32 idx = pos->idx;
 
-	if (notes->options->hide_src_code)
+	if (annotate_opts.hide_src_code)
 		idx = pos->idx_asm;
 	annotate_browser__set_top(browser, pos, idx);
 	browser->curr_hot = nd;
@@ -331,7 +329,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 			double percent;
 
 			percent = annotation_data__percent(&pos->al.data[i],
-							   browser->opts->percent_type);
+							   annotate_opts.percent_type);
 
 			if (max_percent < percent)
 				max_percent = percent;
@@ -380,12 +378,12 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 	browser->b.seek(&browser->b, offset, SEEK_CUR);
 	al = list_entry(browser->b.top, struct annotation_line, node);
 
-	if (notes->options->hide_src_code) {
+	if (annotate_opts.hide_src_code) {
 		if (al->idx_asm < offset)
 			offset = al->idx;
 
 		browser->b.nr_entries = notes->src->nr_entries;
-		notes->options->hide_src_code = false;
+		annotate_opts.hide_src_code = false;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
 		browser->b.top_idx = al->idx - offset;
 		browser->b.index = al->idx;
@@ -403,7 +401,7 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 			offset = al->idx_asm;
 
 		browser->b.nr_entries = notes->src->nr_asm_entries;
-		notes->options->hide_src_code = true;
+		annotate_opts.hide_src_code = true;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
 		browser->b.top_idx = al->idx_asm - offset;
 		browser->b.index = al->idx_asm;
@@ -483,8 +481,8 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 	target_ms.map = ms->map;
 	target_ms.sym = dl->ops.target.sym;
 	annotation__unlock(notes);
-	symbol__tui_annotate(&target_ms, evsel, hbt, browser->opts);
-	sym_title(ms->sym, ms->map, title, sizeof(title), browser->opts->percent_type);
+	symbol__tui_annotate(&target_ms, evsel, hbt);
+	sym_title(ms->sym, ms->map, title, sizeof(title), annotate_opts.percent_type);
 	ui_browser__show_title(&browser->b, title);
 	return true;
 }
@@ -659,7 +657,6 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser,
 
 static int annotate_browser__show(struct ui_browser *browser, char *title, const char *help)
 {
-	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
 	struct map_symbol *ms = browser->priv;
 	struct symbol *sym = ms->sym;
 	char symbol_dso[SYM_TITLE_MAX_SIZE];
@@ -667,7 +664,7 @@ static int annotate_browser__show(struct ui_browser *browser, char *title, const
 	if (ui_browser__show(browser, title, help) < 0)
 		return -1;
 
-	sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), ab->opts->percent_type);
+	sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), annotate_opts.percent_type);
 
 	ui_browser__gotorc_title(browser, 0, 0);
 	ui_browser__set_color(browser, HE_COLORSET_ROOT);
@@ -809,7 +806,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 			annotate_browser__show(&browser->b, title, help);
 			continue;
 		case 'k':
-			notes->options->show_linenr = !notes->options->show_linenr;
+			annotate_opts.show_linenr = !annotate_opts.show_linenr;
 			continue;
 		case 'l':
 			annotate_browser__show_full_location (&browser->b);
@@ -822,18 +819,18 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				ui_helpline__puts(help);
 			continue;
 		case 'o':
-			notes->options->use_offset = !notes->options->use_offset;
+			annotate_opts.use_offset = !annotate_opts.use_offset;
 			annotation__update_column_widths(notes);
 			continue;
 		case 'O':
-			if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
-				notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+			if (++annotate_opts.offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+				annotate_opts.offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
 			continue;
 		case 'j':
-			notes->options->jump_arrows = !notes->options->jump_arrows;
+			annotate_opts.jump_arrows = !annotate_opts.jump_arrows;
 			continue;
 		case 'J':
-			notes->options->show_nr_jumps = !notes->options->show_nr_jumps;
+			annotate_opts.show_nr_jumps = !annotate_opts.show_nr_jumps;
 			annotation__update_column_widths(notes);
 			continue;
 		case '/':
@@ -897,15 +894,15 @@ show_sup_ins:
 			annotation__update_column_widths(notes);
 			continue;
 		case 'c':
-			if (notes->options->show_minmax_cycle)
-				notes->options->show_minmax_cycle = false;
+			if (annotate_opts.show_minmax_cycle)
+				annotate_opts.show_minmax_cycle = false;
 			else
-				notes->options->show_minmax_cycle = true;
+				annotate_opts.show_minmax_cycle = true;
 			annotation__update_column_widths(notes);
 			continue;
 		case 'p':
 		case 'b':
-			switch_percent_type(browser->opts, key == 'b');
+			switch_percent_type(&annotate_opts, key == 'b');
 			hists__scnprintf_title(hists, title, sizeof(title));
 			annotate_browser__show(&browser->b, title, help);
 			continue;
@@ -932,26 +929,23 @@ out:
 }
 
 int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *opts)
+			     struct hist_browser_timer *hbt)
 {
-	return symbol__tui_annotate(ms, evsel, hbt, opts);
+	return symbol__tui_annotate(ms, evsel, hbt);
 }
 
 int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *opts)
+			     struct hist_browser_timer *hbt)
 {
 	/* reset abort key so that it can get Ctrl-C as a key */
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
 
-	return map_symbol__tui_annotate(&he->ms, evsel, hbt, opts);
+	return map_symbol__tui_annotate(&he->ms, evsel, hbt);
 }
 
 int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			 struct hist_browser_timer *hbt,
-			 struct annotation_options *opts)
+			 struct hist_browser_timer *hbt)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
@@ -965,7 +959,6 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 			.priv	 = ms,
 			.use_navkeypressed = true,
 		},
-		.opts = opts,
 	};
 	struct dso *dso;
 	int ret = -1, err;
@@ -996,7 +989,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
 
-	if (notes->options->hide_src_code)
+	if (annotate_opts.hide_src_code)
 		ui_browser__init_asm_mode(&browser.b);
 
 	ret = annotate_browser__run(&browser, evsel, hbt);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index f4812b2268181..3061dea29e6b6 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2250,8 +2250,7 @@ struct hist_browser *hist_browser__new(struct hists *hists)
 static struct hist_browser *
 perf_evsel_browser__new(struct evsel *evsel,
 			struct hist_browser_timer *hbt,
-			struct perf_env *env,
-			struct annotation_options *annotation_opts)
+			struct perf_env *env)
 {
 	struct hist_browser *browser = hist_browser__new(evsel__hists(evsel));
 
@@ -2259,7 +2258,6 @@ perf_evsel_browser__new(struct evsel *evsel,
 		browser->hbt   = hbt;
 		browser->env   = env;
 		browser->title = hists_browser__scnprintf_title;
-		browser->annotation_opts = annotation_opts;
 	}
 	return browser;
 }
@@ -2432,8 +2430,8 @@ do_annotate(struct hist_browser *browser, struct popup_action *act)
 	struct hist_entry *he;
 	int err;
 
-	if (!browser->annotation_opts->objdump_path &&
-	    perf_env__lookup_objdump(browser->env, &browser->annotation_opts->objdump_path))
+	if (!annotate_opts.objdump_path &&
+	    perf_env__lookup_objdump(browser->env, &annotate_opts.objdump_path))
 		return 0;
 
 	notes = symbol__annotation(act->ms.sym);
@@ -2445,8 +2443,7 @@ do_annotate(struct hist_browser *browser, struct popup_action *act)
 	else
 		evsel = hists_to_evsel(browser->hists);
 
-	err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt,
-				       browser->annotation_opts);
+	err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt);
 	he = hist_browser__selected_entry(browser);
 	/*
 	 * offer option to annotate the other branch source or target
@@ -2943,11 +2940,10 @@ next:
 
 static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *helpline,
 			       bool left_exits, struct hist_browser_timer *hbt, float min_pcnt,
-			       struct perf_env *env, bool warn_lost_event,
-			       struct annotation_options *annotation_opts)
+			       struct perf_env *env, bool warn_lost_event)
 {
 	struct hists *hists = evsel__hists(evsel);
-	struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts);
+	struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
 	struct branch_info *bi = NULL;
 #define MAX_OPTIONS  16
 	char *options[MAX_OPTIONS];
@@ -3398,7 +3394,6 @@ out:
 struct evsel_menu {
 	struct ui_browser b;
 	struct evsel *selection;
-	struct annotation_options *annotation_opts;
 	bool lost_events, lost_events_warned;
 	float min_pcnt;
 	struct perf_env *env;
@@ -3499,8 +3494,7 @@ browse_hists:
 				hbt->timer(hbt->arg);
 			key = evsel__hists_browse(pos, nr_events, help, true, hbt,
 						  menu->min_pcnt, menu->env,
-						  warn_lost_event,
-						  menu->annotation_opts);
+						  warn_lost_event);
 			ui_browser__show_title(&menu->b, title);
 			switch (key) {
 			case K_TAB:
@@ -3557,7 +3551,7 @@ static bool filter_group_entries(struct ui_browser *browser __maybe_unused,
 
 static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, const char *help,
 				      struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env,
-				      bool warn_lost_event, struct annotation_options *annotation_opts)
+				      bool warn_lost_event)
 {
 	struct evsel *pos;
 	struct evsel_menu menu = {
@@ -3572,7 +3566,6 @@ static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, con
 		},
 		.min_pcnt = min_pcnt,
 		.env = env,
-		.annotation_opts = annotation_opts,
 	};
 
 	ui_helpline__push("Press ESC to exit");
@@ -3607,8 +3600,7 @@ static bool evlist__single_entry(struct evlist *evlist)
 }
 
 int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt,
-			     float min_pcnt, struct perf_env *env, bool warn_lost_event,
-			     struct annotation_options *annotation_opts)
+			     float min_pcnt, struct perf_env *env, bool warn_lost_event)
 {
 	int nr_entries = evlist->core.nr_entries;
 
@@ -3617,7 +3609,7 @@ single_entry: {
 		struct evsel *first = evlist__first(evlist);
 
 		return evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt,
-					   env, warn_lost_event, annotation_opts);
+					   env, warn_lost_event);
 	}
 	}
 
@@ -3635,7 +3627,7 @@ single_entry: {
 	}
 
 	return __evlist__tui_browse_hists(evlist, nr_entries, help, hbt, min_pcnt, env,
-					  warn_lost_event, annotation_opts);
+					  warn_lost_event);
 }
 
 static int block_hists_browser__title(struct hist_browser *browser, char *bf,
@@ -3654,8 +3646,7 @@ static int block_hists_browser__title(struct hist_browser *browser, char *bf,
 }
 
 int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
-			   float min_percent, struct perf_env *env,
-			   struct annotation_options *annotation_opts)
+			   float min_percent, struct perf_env *env)
 {
 	struct hists *hists = &bh->block_hists;
 	struct hist_browser *browser;
@@ -3672,7 +3663,6 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 	browser->title = block_hists_browser__title;
 	browser->min_pcnt = min_percent;
 	browser->env = env;
-	browser->annotation_opts = annotation_opts;
 
 	/* reset abort key so that it can get Ctrl-C as a key */
 	SLang_reset_tty();
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
index 1e938d9ffa5ee..de46f6c56b0ef 100644
--- a/tools/perf/ui/browsers/hists.h
+++ b/tools/perf/ui/browsers/hists.h
@@ -4,7 +4,6 @@
 
 #include "ui/browser.h"
 
-struct annotation_options;
 struct evsel;
 
 struct hist_browser {
@@ -15,7 +14,6 @@ struct hist_browser {
 	struct hist_browser_timer *hbt;
 	struct pstack	    *pstack;
 	struct perf_env	    *env;
-	struct annotation_options *annotation_opts;
 	struct evsel	    *block_evsel;
 	int		     print_seq;
 	bool		     show_dso;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 7bf29baa43f54..857c5fa0e6b16 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -418,13 +418,11 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel);
 
 #ifdef HAVE_SLANG_SUPPORT
 int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			 struct hist_browser_timer *hbt,
-			 struct annotation_options *opts);
+			 struct hist_browser_timer *hbt);
 #else
 static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 				struct evsel *evsel  __maybe_unused,
-				struct hist_browser_timer *hbt __maybe_unused,
-				struct annotation_options *opts __maybe_unused)
+				struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index 08f82c1f166c3..dec910989701e 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -464,8 +464,7 @@ void block_info__free_report(struct block_report *reps, int nr_reps)
 }
 
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
-			       struct evsel *evsel, struct perf_env *env,
-			       struct annotation_options *annotation_opts)
+			       struct evsel *evsel, struct perf_env *env)
 {
 	int ret;
 
@@ -477,8 +476,7 @@ int report__browse_block_hists(struct block_hist *bh, float min_percent,
 		return 0;
 	case 1:
 		symbol_conf.report_individual_block = true;
-		ret = block_hists_tui_browse(bh, evsel, min_percent,
-					     env, annotation_opts);
+		ret = block_hists_tui_browse(bh, evsel, min_percent, env);
 		return ret;
 	default:
 		return -1;
diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h
index 42e9dcc4cf0ab..96f53e89795e2 100644
--- a/tools/perf/util/block-info.h
+++ b/tools/perf/util/block-info.h
@@ -78,8 +78,7 @@ struct block_report *block_info__create_report(struct evlist *evlist,
 void block_info__free_report(struct block_report *reps, int nr_reps);
 
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
-			       struct evsel *evsel, struct perf_env *env,
-			       struct annotation_options *annotation_opts);
+			       struct evsel *evsel, struct perf_env *env);
 
 float block_info__total_cycles_percent(struct hist_entry *he);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index afc9f1c7f4dc2..5d0db96609dff 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -457,7 +457,6 @@ struct hist_browser_timer {
 	int refresh;
 };
 
-struct annotation_options;
 struct res_sample;
 
 enum rstype {
@@ -473,16 +472,13 @@ struct block_hist;
 void attr_to_script(char *buf, struct perf_event_attr *attr);
 
 int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *annotation_opts);
+			     struct hist_browser_timer *hbt);
 
 int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *annotation_opts);
+			     struct hist_browser_timer *hbt);
 
 int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt,
-			     float min_pcnt, struct perf_env *env, bool warn_lost_event,
-			     struct annotation_options *annotation_options);
+			     float min_pcnt, struct perf_env *env, bool warn_lost_event);
 
 int script_browse(const char *script_opt, struct evsel *evsel);
 
@@ -492,8 +488,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res,
 void res_sample_init(void);
 
 int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
-			   float min_percent, struct perf_env *env,
-			   struct annotation_options *annotation_opts);
+			   float min_percent, struct perf_env *env);
 #else
 static inline
 int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
@@ -501,23 +496,20 @@ int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
 			     struct hist_browser_timer *hbt __maybe_unused,
 			     float min_pcnt __maybe_unused,
 			     struct perf_env *env __maybe_unused,
-			     bool warn_lost_event __maybe_unused,
-			     struct annotation_options *annotation_options __maybe_unused)
+			     bool warn_lost_event __maybe_unused)
 {
 	return 0;
 }
 static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 					   struct evsel *evsel __maybe_unused,
-					   struct hist_browser_timer *hbt __maybe_unused,
-					   struct annotation_options *annotation_options __maybe_unused)
+					   struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
 
 static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
 					   struct evsel *evsel __maybe_unused,
-					   struct hist_browser_timer *hbt __maybe_unused,
-					   struct annotation_options *annotation_opts __maybe_unused)
+					   struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
@@ -541,8 +533,7 @@ static inline void res_sample_init(void) {}
 static inline int block_hists_tui_browse(struct block_hist *bh __maybe_unused,
 					 struct evsel *evsel __maybe_unused,
 					 float min_percent __maybe_unused,
-					 struct perf_env *env __maybe_unused,
-					 struct annotation_options *annotation_opts __maybe_unused)
+					 struct perf_env *env __maybe_unused)
 {
 	return 0;
 }
-- 
GitLab


From 7f929aea21fd0be5e0d9ee5827d5b809daa69f29 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 28 Nov 2023 09:54:39 -0800
Subject: [PATCH 0952/4076] perf annotate: Ensure init/exit for global options

Now it only cares about the global options so it can just handle it
without the argument.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231128175441.721579-7-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c |  8 ++++----
 tools/perf/builtin-report.c   |  8 ++++----
 tools/perf/builtin-top.c      |  8 ++++----
 tools/perf/util/annotate.c    | 19 +++++++++++--------
 tools/perf/util/annotate.h    |  8 ++++----
 5 files changed, 27 insertions(+), 24 deletions(-)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index d17213bd83327..d880f1b039fdf 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -615,13 +615,13 @@ int cmd_annotate(int argc, const char **argv)
 	set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE);
 
-	annotation_options__init(&annotate_opts);
+	annotation_options__init();
 
 	ret = hists__init();
 	if (ret < 0)
 		return ret;
 
-	annotation_config__init(&annotate_opts);
+	annotation_config__init();
 
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 	if (argc) {
@@ -651,7 +651,7 @@ int cmd_annotate(int argc, const char **argv)
 			return -ENOMEM;
 	}
 
-	if (annotate_check_args(&annotate_opts) < 0)
+	if (annotate_check_args() < 0)
 		return -EINVAL;
 
 #ifdef HAVE_GTK2_SUPPORT
@@ -732,7 +732,7 @@ out_delete:
 #ifndef NDEBUG
 	perf_session__delete(annotate.session);
 #endif
-	annotation_options__exit(&annotate_opts);
+	annotation_options__exit();
 
 	return ret;
 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bc0d986c1e0c1..17fb171e898b9 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1430,7 +1430,7 @@ int cmd_report(int argc, const char **argv)
 	 */
 	symbol_conf.keep_exited_threads = true;
 
-	annotation_options__init(&annotate_opts);
+	annotation_options__init();
 
 	ret = perf_config(report__config, &report);
 	if (ret)
@@ -1464,7 +1464,7 @@ int cmd_report(int argc, const char **argv)
 			return -ENOMEM;
 	}
 
-	if (annotate_check_args(&annotate_opts) < 0) {
+	if (annotate_check_args() < 0) {
 		ret = -EINVAL;
 		goto exit;
 	}
@@ -1696,7 +1696,7 @@ repeat:
 			 */
 			symbol_conf.priv_size += sizeof(u32);
 		}
-		annotation_config__init(&annotate_opts);
+		annotation_config__init();
 	}
 
 	if (symbol__init(&session->header.env) < 0)
@@ -1750,7 +1750,7 @@ error:
 	zstd_fini(&(session->zstd_data));
 	perf_session__delete(session);
 exit:
-	annotation_options__exit(&annotate_opts);
+	annotation_options__exit();
 	free(sort_order_help);
 	free(field_order_help);
 	return ret;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b5222d2419832..ed83afeeced05 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1608,7 +1608,7 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		return status;
 
-	annotation_options__init(&annotate_opts);
+	annotation_options__init();
 
 	annotate_opts.min_pcnt = 5;
 	annotate_opts.context  = 4;
@@ -1660,7 +1660,7 @@ int cmd_top(int argc, const char **argv)
 	if (status)
 		goto out_delete_evlist;
 
-	if (annotate_check_args(&annotate_opts) < 0)
+	if (annotate_check_args() < 0)
 		goto out_delete_evlist;
 
 	if (!top.evlist->core.nr_entries) {
@@ -1786,7 +1786,7 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		goto out_delete_evlist;
 
-	annotation_config__init(&annotate_opts);
+	annotation_config__init();
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	status = symbol__init(NULL);
@@ -1839,7 +1839,7 @@ int cmd_top(int argc, const char **argv)
 out_delete_evlist:
 	evlist__delete(top.evlist);
 	perf_session__delete(top.session);
-	annotation_options__exit(&annotate_opts);
+	annotation_options__exit();
 
 	return status;
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index daff9af552f4f..626ff3baeb855 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -3416,8 +3416,10 @@ static int annotation__config(const char *var, const char *value, void *data)
 	return 0;
 }
 
-void annotation_options__init(struct annotation_options *opt)
+void annotation_options__init(void)
 {
+	struct annotation_options *opt = &annotate_opts;
+
 	memset(opt, 0, sizeof(*opt));
 
 	/* Default values. */
@@ -3428,16 +3430,15 @@ void annotation_options__init(struct annotation_options *opt)
 	opt->percent_type = PERCENT_PERIOD_LOCAL;
 }
 
-
-void annotation_options__exit(struct annotation_options *opt)
+void annotation_options__exit(void)
 {
-	zfree(&opt->disassembler_style);
-	zfree(&opt->objdump_path);
+	zfree(&annotate_opts.disassembler_style);
+	zfree(&annotate_opts.objdump_path);
 }
 
-void annotation_config__init(struct annotation_options *opt)
+void annotation_config__init(void)
 {
-	perf_config(annotation__config, opt);
+	perf_config(annotation__config, &annotate_opts);
 }
 
 static unsigned int parse_percent_type(char *str1, char *str2)
@@ -3491,8 +3492,10 @@ out:
 	return err;
 }
 
-int annotate_check_args(struct annotation_options *args)
+int annotate_check_args(void)
 {
+	struct annotation_options *args = &annotate_opts;
+
 	if (args->prefix_strip && !args->prefix) {
 		pr_err("--prefix-strip requires --prefix\n");
 		return -1;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 857c5fa0e6b16..4283eb4522b28 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -428,14 +428,14 @@ static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 }
 #endif
 
-void annotation_options__init(struct annotation_options *opt);
-void annotation_options__exit(struct annotation_options *opt);
+void annotation_options__init(void);
+void annotation_options__exit(void);
 
-void annotation_config__init(struct annotation_options *opt);
+void annotation_config__init(void);
 
 int annotate_parse_percent_type(const struct option *opt, const char *_str,
 				int unset);
 
-int annotate_check_args(struct annotation_options *args);
+int annotate_check_args(void);
 
 #endif	/* __PERF_ANNOTATE_H */
-- 
GitLab


From 2fa21d694c63081f26444847c916e5fc83bcefa1 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 28 Nov 2023 09:54:40 -0800
Subject: [PATCH 0953/4076] perf annotate: Remove remaining usages of local
 annotation options

So that it can get rid of the unused data.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231128175441.721579-8-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/browsers/annotate.c | 14 ++++++--------
 tools/perf/util/annotate.c        |  2 +-
 tools/perf/util/annotate.h        |  6 +++---
 3 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index fda17c1f20319..cb2eb6dcb5321 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -37,11 +37,10 @@ static inline struct annotation *browser__annotation(struct ui_browser *browser)
 	return symbol__annotation(ms->sym);
 }
 
-static bool disasm_line__filter(struct ui_browser *browser, void *entry)
+static bool disasm_line__filter(struct ui_browser *browser __maybe_unused, void *entry)
 {
-	struct annotation *notes = browser__annotation(browser);
 	struct annotation_line *al = list_entry(entry, struct annotation_line, node);
-	return annotation_line__filter(al, notes);
+	return annotation_line__filter(al);
 }
 
 static int ui_browser__jumps_percent_color(struct ui_browser *browser, int nr, bool current)
@@ -269,7 +268,6 @@ static void disasm_rb_tree__insert(struct annotate_browser *browser,
 static void annotate_browser__set_top(struct annotate_browser *browser,
 				      struct annotation_line *pos, u32 idx)
 {
-	struct annotation *notes = browser__annotation(&browser->b);
 	unsigned back;
 
 	ui_browser__refresh_dimensions(&browser->b);
@@ -279,7 +277,7 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 	while (browser->b.top_idx != 0 && back != 0) {
 		pos = list_entry(pos->node.prev, struct annotation_line, node);
 
-		if (annotation_line__filter(pos, notes))
+		if (annotation_line__filter(pos))
 			continue;
 
 		--browser->b.top_idx;
@@ -498,7 +496,7 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows
 	list_for_each_entry(pos, &notes->src->source, al.node) {
 		if (pos->al.offset == offset)
 			return pos;
-		if (!annotation_line__filter(&pos->al, notes))
+		if (!annotation_line__filter(&pos->al))
 			++*idx;
 	}
 
@@ -542,7 +540,7 @@ struct annotation_line *annotate_browser__find_string(struct annotate_browser *b
 
 	*idx = browser->b.index;
 	list_for_each_entry_continue(al, &notes->src->source, node) {
-		if (annotation_line__filter(al, notes))
+		if (annotation_line__filter(al))
 			continue;
 
 		++*idx;
@@ -579,7 +577,7 @@ struct annotation_line *annotate_browser__find_string_reverse(struct annotate_br
 
 	*idx = browser->b.index;
 	list_for_each_entry_continue_reverse(al, &notes->src->source, node) {
-		if (annotation_line__filter(al, notes))
+		if (annotation_line__filter(al))
 			continue;
 
 		--*idx;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 626ff3baeb855..09c399ab03843 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2727,7 +2727,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp)
 	struct annotation_line *al;
 
 	list_for_each_entry(al, &notes->src->source, node) {
-		if (annotation_line__filter(al, notes))
+		if (annotation_line__filter(al))
 			continue;
 		annotation_line__write(al, notes, &wops);
 		fputc('\n', fp);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 4283eb4522b28..6d5a6bb49a975 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -320,7 +320,7 @@ bool annotation__trylock(struct annotation *notes) EXCLUSIVE_TRYLOCK_FUNCTION(tr
 
 static inline int annotation__cycles_width(struct annotation *notes)
 {
-	if (notes->branch && notes->options->show_minmax_cycle)
+	if (notes->branch && annotate_opts.show_minmax_cycle)
 		return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH;
 
 	return notes->branch ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
@@ -331,9 +331,9 @@ static inline int annotation__pcnt_width(struct annotation *notes)
 	return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
 }
 
-static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
+static inline bool annotation_line__filter(struct annotation_line *al)
 {
-	return notes->options->hide_src_code && al->offset == -1;
+	return annotate_opts.hide_src_code && al->offset == -1;
 }
 
 void annotation__set_offsets(struct annotation *notes, s64 size);
-- 
GitLab


From 327f7533cc596427b62f431c8852951412b6c0dc Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 28 Nov 2023 09:54:41 -0800
Subject: [PATCH 0954/4076] perf annotate: Get rid of local annotation options

It doesn't need the option in the struct annotation which is allocated
for each symbol.  It can directly use the global options and save 8
bytes per symbol.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231128175441.721579-9-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 2 --
 tools/perf/util/annotate.h | 1 -
 2 files changed, 3 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 09c399ab03843..c81fa0791918e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -3333,8 +3333,6 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	if (err)
 		goto out_free_offsets;
 
-	notes->options = &annotate_opts;
-
 	symbol__calc_percent(sym, evsel);
 
 	annotation__set_offsets(notes, size);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 6d5a6bb49a975..589f8aaf02366 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -294,7 +294,6 @@ struct annotated_branch {
 
 struct LOCKABLE annotation {
 	u64			start;
-	struct annotation_options *options;
 	int			nr_events;
 	int			max_jump_sources;
 	struct {
-- 
GitLab


From cb46fca88d14939da2785567253d0a297f31be27 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Tue, 29 Aug 2023 08:20:14 -0700
Subject: [PATCH 0955/4076] cxl: Add Support for Get Timestamp

Add the call to the UAPI such that userspace may corelate the
timestamps from the device log with system wall time, if, for
example there's any sort of inaccuracy or skew in the device.

Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20230829152014.15452-1-dave@stgolabs.net
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c      | 1 +
 drivers/cxl/cxlmem.h         | 1 +
 include/uapi/linux/cxl_mem.h | 1 +
 3 files changed, 3 insertions(+)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 36270dcfb42ef..b86dbd25740c3 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -63,6 +63,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = {
 	CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0),
 	CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0),
 	CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0),
+	CXL_CMD(GET_TIMESTAMP, 0, 0x8, 0),
 };
 
 /*
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index a2fcbca253f39..6a6becee402b9 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -503,6 +503,7 @@ enum cxl_opcode {
 	CXL_MBOX_OP_GET_FW_INFO		= 0x0200,
 	CXL_MBOX_OP_TRANSFER_FW		= 0x0201,
 	CXL_MBOX_OP_ACTIVATE_FW		= 0x0202,
+	CXL_MBOX_OP_GET_TIMESTAMP	= 0x0300,
 	CXL_MBOX_OP_SET_TIMESTAMP	= 0x0301,
 	CXL_MBOX_OP_GET_SUPPORTED_LOGS	= 0x0400,
 	CXL_MBOX_OP_GET_LOG		= 0x0401,
diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h
index 14bc6e7421483..42066f4eb8903 100644
--- a/include/uapi/linux/cxl_mem.h
+++ b/include/uapi/linux/cxl_mem.h
@@ -46,6 +46,7 @@
 	___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"),         \
 	___DEPRECATED(SCAN_MEDIA, "Scan Media"),                          \
 	___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"),          \
+	___C(GET_TIMESTAMP, "Get Timestamp"),                             \
 	___C(MAX, "invalid / last command")
 
 #define ___C(a, b) CXL_MEM_COMMAND_ID_##a
-- 
GitLab


From 83a368a3fc8ae8538bccb713dc0cae9eacc04790 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 3 Dec 2023 18:46:22 +0100
Subject: [PATCH 0956/4076] docs: dt-bindings: add DTS Coding Style document
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document preferred coding style for Devicetree sources (DTS and DTSI),
to bring consistency among all (sub)architectures and ease in reviews.

Cc: Andrew Davis <afd@ti.com>
cc: Andrew Lunn <andrew@lunn.ch>
Cc: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Bjorn Andersson <andersson@kernel.org>
Cc: Chen-Yu Tsai <wens@kernel.org>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Michal Simek <michal.simek@amd.com>
Cc: Neil Armstrong <neil.armstrong@linaro.org>
Cc: Nishanth Menon <nm@ti.com>
Cc: Olof Johansson <olof@lixom.net>
Cc: Rafał Miłecki <zajec5@gmail.com>
Acked-by: Neil Armstrong <neil.armstrong@linaro.org>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Konrad Dybcio <konradybcio@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/r/20231203174622.18402-1-krzysztof.kozlowski@linaro.org
[robh: quote property names in order of properties section]
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/dts-coding-style.rst  | 196 ++++++++++++++++++
 Documentation/devicetree/bindings/index.rst   |   1 +
 2 files changed, 197 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/dts-coding-style.rst

diff --git a/Documentation/devicetree/bindings/dts-coding-style.rst b/Documentation/devicetree/bindings/dts-coding-style.rst
new file mode 100644
index 0000000000000..a9bdd2b59dcab
--- /dev/null
+++ b/Documentation/devicetree/bindings/dts-coding-style.rst
@@ -0,0 +1,196 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================
+Devicetree Sources (DTS) Coding Style
+=====================================
+
+When writing Devicetree Sources (DTS) please observe below guidelines.  They
+should be considered complementary to any rules expressed already in
+the Devicetree Specification and the dtc compiler (including W=1 and W=2
+builds).
+
+Individual architectures and subarchitectures can define additional rules,
+making the coding style stricter.
+
+Naming and Valid Characters
+---------------------------
+
+The Devicetree Specification allows a broad range of characters in node
+and property names, but this coding style narrows the range down to achieve
+better code readability.
+
+1. Node and property names can use only the following characters:
+
+   * Lowercase characters: [a-z]
+   * Digits: [0-9]
+   * Dash: -
+
+2. Labels can use only the following characters:
+
+   * Lowercase characters: [a-z]
+   * Digits: [0-9]
+   * Underscore: _
+
+3. Unless a bus defines differently, unit addresses shall use lowercase
+   hexadecimal digits, without leading zeros (padding).
+
+4. Hex values in properties, e.g. "reg", shall use lowercase hex.  The address
+   part can be padded with leading zeros.
+
+Example::
+
+	gpi_dma2: dma-controller@a00000 {
+		compatible = "qcom,sm8550-gpi-dma", "qcom,sm6350-gpi-dma";
+		reg = <0x0 0x00a00000 0x0 0x60000>;
+	}
+
+Order of Nodes
+--------------
+
+1. Nodes on any bus, thus using unit addresses for children, shall be
+   ordered by unit address in ascending order.
+   Alternatively for some subarchitectures, nodes of the same type can be
+   grouped together, e.g. all I2C controllers one after another even if this
+   breaks unit address ordering.
+
+2. Nodes without unit addresses shall be ordered alpha-numerically by the node
+   name.  For a few node types, they can be ordered by the main property, e.g.
+   pin configuration states ordered by value of "pins" property.
+
+3. When extending nodes in the board DTS via &label, the entries shall be
+   ordered either alpha-numerically or by keeping the order from DTSI, where
+   the choice depends on the subarchitecture.
+
+The above-described ordering rules are easy to enforce during review, reduce
+chances of conflicts for simultaneous additions of new nodes to a file and help
+in navigating through the DTS source.
+
+Example::
+
+	/* SoC DTSI */
+
+	/ {
+		cpus {
+			/* ... */
+		};
+
+		psci {
+			/* ... */
+		};
+
+		soc@0 {
+			dma: dma-controller@10000 {
+				/* ... */
+			};
+
+			clk: clock-controller@80000 {
+				/* ... */
+			};
+		};
+	};
+
+	/* Board DTS - alphabetical order */
+
+	&clk {
+		/* ... */
+	};
+
+	&dma {
+		/* ... */
+	};
+
+	/* Board DTS - alternative order, keep as DTSI */
+
+	&dma {
+		/* ... */
+	};
+
+	&clk {
+		/* ... */
+	};
+
+Order of Properties in Device Node
+----------------------------------
+
+The following order of properties in device nodes is preferred:
+
+1. "compatible"
+2. "reg"
+3. "ranges"
+4. Standard/common properties (defined by common bindings, e.g. without
+   vendor-prefixes)
+5. Vendor-specific properties
+6. "status" (if applicable)
+7. Child nodes, where each node is preceded with a blank line
+
+The "status" property is by default "okay", thus it can be omitted.
+
+The above-described ordering follows this approach:
+
+1. Most important properties start the node: compatible then bus addressing to
+   match unit address.
+2. Each node will have common properties in similar place.
+3. Status is the last information to annotate that device node is or is not
+   finished (board resources are needed).
+
+Example::
+
+	/* SoC DTSI */
+
+	device_node: device-class@6789abc {
+		compatible = "vendor,device";
+		reg = <0x0 0x06789abc 0x0 0xa123>;
+		ranges = <0x0 0x0 0x06789abc 0x1000>;
+		#dma-cells = <1>;
+		clocks = <&clock_controller 0>, <&clock_controller 1>;
+		clock-names = "bus", "host";
+		vendor,custom-property = <2>;
+		status = "disabled";
+
+		child_node: child-class@100 {
+			reg = <0x100 0x200>;
+			/* ... */
+		};
+	};
+
+	/* Board DTS */
+
+	&device_node {
+		vdd-supply = <&board_vreg1>;
+		status = "okay";
+	}
+
+Indentation
+-----------
+
+1. Use indentation according to Documentation/process/coding-style.rst.
+2. Each entry in arrays with multiple cells, e.g. "reg" with two IO addresses,
+   shall be enclosed in <>.
+3. For arrays spanning across lines, it is preferred to align the continued
+   entries with opening < from the first line.
+
+Example::
+
+	thermal-sensor@c271000 {
+		compatible = "qcom,sm8550-tsens", "qcom,tsens-v2";
+		reg = <0x0 0x0c271000 0x0 0x1000>,
+		      <0x0 0x0c222000 0x0 0x1000>;
+	};
+
+Organizing DTSI and DTS
+-----------------------
+
+The DTSI and DTS files shall be organized in a way representing the common,
+reusable parts of hardware.  Typically, this means organizing DTSI and DTS files
+into several files:
+
+1. DTSI with contents of the entire SoC, without nodes for hardware not present
+   on the SoC.
+2. If applicable: DTSI with common or re-usable parts of the hardware, e.g.
+   entire System-on-Module.
+3. DTS representing the board.
+
+Hardware components that are present on the board shall be placed in the
+board DTS, not in the SoC or SoM DTSI.  A partial exception is a common
+external reference SoC input clock, which could be coded as a fixed-clock in
+the SoC DTSI with its frequency provided by each board DTS.
diff --git a/Documentation/devicetree/bindings/index.rst b/Documentation/devicetree/bindings/index.rst
index d9002a3a0abb3..cc1fbdc056572 100644
--- a/Documentation/devicetree/bindings/index.rst
+++ b/Documentation/devicetree/bindings/index.rst
@@ -4,6 +4,7 @@
    :maxdepth: 1
 
    ABI
+   dts-coding-style
    writing-bindings
    writing-schema
    submitting-patches
-- 
GitLab


From c3dc3d079d191c9149496b3c7fe1ece909386d93 Mon Sep 17 00:00:00 2001
From: Vignesh Viswanathan <quic_viswanat@quicinc.com>
Date: Tue, 5 Sep 2023 15:25:35 +0530
Subject: [PATCH 0957/4076] hwspinlock: qcom: Remove IPQ6018 SOC specific
 compatible

IPQ6018 has 32 tcsr_mutex hwlock registers with stride 0x1000.
The compatible string qcom,ipq6018-tcsr-mutex is mapped to
of_msm8226_tcsr_mutex which has 32 locks configured with stride of 0x80
and doesn't match the HW present in IPQ6018.

Remove IPQ6018 specific compatible string so that it fallsback to
of_tcsr_mutex data which maps to the correct configuration for IPQ6018.

Fixes: 5d4753f741d8 ("hwspinlock: qcom: add support for MMIO on older SoCs")
Signed-off-by: Vignesh Viswanathan <quic_viswanat@quicinc.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230905095535.1263113-3-quic_viswanat@quicinc.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/hwspinlock/qcom_hwspinlock.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c
index a0fd67fd29344..814dfe8697bf3 100644
--- a/drivers/hwspinlock/qcom_hwspinlock.c
+++ b/drivers/hwspinlock/qcom_hwspinlock.c
@@ -115,7 +115,6 @@ static const struct of_device_id qcom_hwspinlock_of_match[] = {
 	{ .compatible = "qcom,sfpb-mutex", .data = &of_sfpb_mutex },
 	{ .compatible = "qcom,tcsr-mutex", .data = &of_tcsr_mutex },
 	{ .compatible = "qcom,apq8084-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
-	{ .compatible = "qcom,ipq6018-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
 	{ .compatible = "qcom,msm8226-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
 	{ .compatible = "qcom,msm8974-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
 	{ .compatible = "qcom,msm8994-tcsr-mutex", .data = &of_msm8226_tcsr_mutex },
-- 
GitLab


From bcd0f5d18b0b1134ccf9ef68e7a0cf637aab380d Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 5 Dec 2023 21:54:39 -0800
Subject: [PATCH 0958/4076] hwspinlock/core: fix kernel-doc warnings

Correct function comments to prevent kernel-doc warnings
found when using "W=1".

hwspinlock_core.c:208: warning: Excess function parameter 'timeout' description in '__hwspin_lock_timeout'
hwspinlock_core.c:318: warning: Excess function parameter 'bank' description in 'of_hwspin_lock_simple_xlate'
hwspinlock_core.c:647: warning: Function parameter or member 'hwlock' not described in '__hwspin_lock_request'

and 17 warnings like:
hwspinlock_core.c:487: warning: No description found for return value of 'hwspin_lock_register'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Ohad Ben-Cohen <ohad@wizery.com>
Cc: Bjorn Andersson <andersson@kernel.org>
Cc: Baolin Wang <baolin.wang7@gmail.com>
Cc: linux-remoteproc@vger.kernel.org
Link: https://lore.kernel.org/r/20231206055439.671-1-rdunlap@infradead.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/hwspinlock/hwspinlock_core.c | 53 +++++++++++++++-------------
 1 file changed, 29 insertions(+), 24 deletions(-)

diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c
index ada694ba9f958..0c0a932c00f35 100644
--- a/drivers/hwspinlock/hwspinlock_core.c
+++ b/drivers/hwspinlock/hwspinlock_core.c
@@ -84,8 +84,9 @@ static DEFINE_MUTEX(hwspinlock_tree_lock);
  * should decide between spin_trylock, spin_trylock_irq and
  * spin_trylock_irqsave.
  *
- * Returns 0 if we successfully locked the hwspinlock or -EBUSY if
+ * Returns: %0 if we successfully locked the hwspinlock or -EBUSY if
  * the hwspinlock was already taken.
+ *
  * This function will never sleep.
  */
 int __hwspin_trylock(struct hwspinlock *hwlock, int mode, unsigned long *flags)
@@ -171,7 +172,7 @@ EXPORT_SYMBOL_GPL(__hwspin_trylock);
 /**
  * __hwspin_lock_timeout() - lock an hwspinlock with timeout limit
  * @hwlock: the hwspinlock to be locked
- * @timeout: timeout value in msecs
+ * @to: timeout value in msecs
  * @mode: mode which controls whether local interrupts are disabled or not
  * @flags: a pointer to where the caller's interrupt state will be saved at (if
  *         requested)
@@ -199,9 +200,11 @@ EXPORT_SYMBOL_GPL(__hwspin_trylock);
  * to choose the appropriate @mode of operation, exactly the same way users
  * should decide between spin_lock, spin_lock_irq and spin_lock_irqsave.
  *
- * Returns 0 when the @hwlock was successfully taken, and an appropriate
+ * Returns: %0 when the @hwlock was successfully taken, and an appropriate
  * error code otherwise (most notably -ETIMEDOUT if the @hwlock is still
- * busy after @timeout msecs). The function will never sleep.
+ * busy after @timeout msecs).
+ *
+ * The function will never sleep.
  */
 int __hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int to,
 					int mode, unsigned long *flags)
@@ -304,13 +307,12 @@ EXPORT_SYMBOL_GPL(__hwspin_unlock);
 
 /**
  * of_hwspin_lock_simple_xlate - translate hwlock_spec to return a lock id
- * @bank: the hwspinlock device bank
  * @hwlock_spec: hwlock specifier as found in the device tree
  *
  * This is a simple translation function, suitable for hwspinlock platform
  * drivers that only has a lock specifier length of 1.
  *
- * Returns a relative index of the lock within a specified bank on success,
+ * Returns: a relative index of the lock within a specified bank on success,
  * or -EINVAL on invalid specifier cell count.
  */
 static inline int
@@ -332,9 +334,10 @@ of_hwspin_lock_simple_xlate(const struct of_phandle_args *hwlock_spec)
  * hwspinlock device, so that it can be requested using the normal
  * hwspin_lock_request_specific() API.
  *
- * Returns the global lock id number on success, -EPROBE_DEFER if the hwspinlock
- * device is not yet registered, -EINVAL on invalid args specifier value or an
- * appropriate error as returned from the OF parsing of the DT client node.
+ * Returns: the global lock id number on success, -EPROBE_DEFER if the
+ * hwspinlock device is not yet registered, -EINVAL on invalid args
+ * specifier value or an appropriate error as returned from the OF parsing
+ * of the DT client node.
  */
 int of_hwspin_lock_get_id(struct device_node *np, int index)
 {
@@ -399,9 +402,10 @@ EXPORT_SYMBOL_GPL(of_hwspin_lock_get_id);
  * the hwspinlock device, so that it can be requested using the normal
  * hwspin_lock_request_specific() API.
  *
- * Returns the global lock id number on success, -EPROBE_DEFER if the hwspinlock
- * device is not yet registered, -EINVAL on invalid args specifier value or an
- * appropriate error as returned from the OF parsing of the DT client node.
+ * Returns: the global lock id number on success, -EPROBE_DEFER if the
+ * hwspinlock device is not yet registered, -EINVAL on invalid args
+ * specifier value or an appropriate error as returned from the OF parsing
+ * of the DT client node.
  */
 int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name)
 {
@@ -481,7 +485,7 @@ out:
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev,
 		const struct hwspinlock_ops *ops, int base_id, int num_locks)
@@ -529,7 +533,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_register);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int hwspin_lock_unregister(struct hwspinlock_device *bank)
 {
@@ -578,7 +582,7 @@ static int devm_hwspin_lock_device_match(struct device *dev, void *res,
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int devm_hwspin_lock_unregister(struct device *dev,
 				struct hwspinlock_device *bank)
@@ -607,7 +611,7 @@ EXPORT_SYMBOL_GPL(devm_hwspin_lock_unregister);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int devm_hwspin_lock_register(struct device *dev,
 			      struct hwspinlock_device *bank,
@@ -635,12 +639,13 @@ EXPORT_SYMBOL_GPL(devm_hwspin_lock_register);
 
 /**
  * __hwspin_lock_request() - tag an hwspinlock as used and power it up
+ * @hwlock: the target hwspinlock
  *
  * This is an internal function that prepares an hwspinlock instance
  * before it is given to the user. The function assumes that
  * hwspinlock_tree_lock is taken.
  *
- * Returns 0 or positive to indicate success, and a negative value to
+ * Returns: %0 or positive to indicate success, and a negative value to
  * indicate an error (with the appropriate error code)
  */
 static int __hwspin_lock_request(struct hwspinlock *hwlock)
@@ -680,7 +685,7 @@ static int __hwspin_lock_request(struct hwspinlock *hwlock)
  * hwspin_lock_get_id() - retrieve id number of a given hwspinlock
  * @hwlock: a valid hwspinlock instance
  *
- * Returns the id number of a given @hwlock, or -EINVAL if @hwlock is invalid.
+ * Returns: the id number of a given @hwlock, or -EINVAL if @hwlock is invalid.
  */
 int hwspin_lock_get_id(struct hwspinlock *hwlock)
 {
@@ -704,7 +709,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_get_id);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns the address of the assigned hwspinlock, or NULL on error
+ * Returns: the address of the assigned hwspinlock, or %NULL on error
  */
 struct hwspinlock *hwspin_lock_request(void)
 {
@@ -747,7 +752,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_request);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns the address of the assigned hwspinlock, or NULL on error
+ * Returns: the address of the assigned hwspinlock, or %NULL on error
  */
 struct hwspinlock *hwspin_lock_request_specific(unsigned int id)
 {
@@ -795,7 +800,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_request_specific);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int hwspin_lock_free(struct hwspinlock *hwlock)
 {
@@ -865,7 +870,7 @@ static void devm_hwspin_lock_release(struct device *dev, void *res)
  *
  * Should be called from a process context (might sleep)
  *
- * Returns 0 on success, or an appropriate error code on failure
+ * Returns: %0 on success, or an appropriate error code on failure
  */
 int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock)
 {
@@ -891,7 +896,7 @@ EXPORT_SYMBOL_GPL(devm_hwspin_lock_free);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns the address of the assigned hwspinlock, or NULL on error
+ * Returns: the address of the assigned hwspinlock, or %NULL on error
  */
 struct hwspinlock *devm_hwspin_lock_request(struct device *dev)
 {
@@ -926,7 +931,7 @@ EXPORT_SYMBOL_GPL(devm_hwspin_lock_request);
  *
  * Should be called from a process context (might sleep)
  *
- * Returns the address of the assigned hwspinlock, or NULL on error
+ * Returns: the address of the assigned hwspinlock, or %NULL on error
  */
 struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev,
 						     unsigned int id)
-- 
GitLab


From 6d72283526090850274d065cd5d60af732cc5fc8 Mon Sep 17 00:00:00 2001
From: Paul Durrant <pdurrant@amazon.com>
Date: Thu, 2 Nov 2023 16:21:28 +0000
Subject: [PATCH 0959/4076] KVM x86/xen: add an override for
 PVCLOCK_TSC_STABLE_BIT

Unless explicitly told to do so (by passing 'clocksource=tsc' and
'tsc=stable:socket', and then jumping through some hoops concerning
potential CPU hotplug) Xen will never use TSC as its clocksource.
Hence, by default, a Xen guest will not see PVCLOCK_TSC_STABLE_BIT set
in either the primary or secondary pvclock memory areas. This has
led to bugs in some guest kernels which only become evident if
PVCLOCK_TSC_STABLE_BIT *is* set in the pvclocks. Hence, to support
such guests, give the VMM a new Xen HVM config flag to tell KVM to
forcibly clear the bit in the Xen pvclocks.

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lore.kernel.org/r/20231102162128.2353459-1-paul@xen.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 Documentation/virt/kvm/api.rst |  6 ++++++
 arch/x86/kvm/x86.c             | 28 +++++++++++++++++++++++-----
 arch/x86/kvm/xen.c             |  9 ++++++++-
 include/uapi/linux/kvm.h       |  1 +
 4 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 926241e23aebb..dca83c65d97f3 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8562,6 +8562,7 @@ PVHVM guests. Valid flags are::
   #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL		(1 << 4)
   #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
   #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+  #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
 ioctl is available, for the guest to set its hypercall page.
@@ -8605,6 +8606,11 @@ behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless
 specifically enabled (by the guest making the hypercall, causing the VMM
 to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute).
 
+The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag indicates that KVM supports
+clearing the PVCLOCK_TSC_STABLE_BIT flag in Xen pvclock sources. This will be
+done when the KVM_CAP_XEN_HVM ioctl sets the
+KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag.
+
 8.31 KVM_CAP_PPC_MULTITCE
 -------------------------
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d0772b470413..aa7cea9600b00 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3104,7 +3104,8 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 
 static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 				    struct gfn_to_pfn_cache *gpc,
-				    unsigned int offset)
+				    unsigned int offset,
+				    bool force_tsc_unstable)
 {
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct pvclock_vcpu_time_info *guest_hv_clock;
@@ -3141,6 +3142,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 	}
 
 	memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock));
+
+	if (force_tsc_unstable)
+		guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT;
+
 	smp_wmb();
 
 	guest_hv_clock->version = ++vcpu->hv_clock.version;
@@ -3161,6 +3166,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	u64 tsc_timestamp, host_tsc;
 	u8 pvclock_flags;
 	bool use_master_clock;
+#ifdef CONFIG_KVM_XEN
+	/*
+	 * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless
+	 * explicitly told to use TSC as its clocksource Xen will not set this bit.
+	 * This default behaviour led to bugs in some guest kernels which cause
+	 * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags.
+	 */
+	bool xen_pvclock_tsc_unstable =
+		ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
+#endif
 
 	kernel_ns = 0;
 	host_tsc = 0;
@@ -3239,13 +3254,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	vcpu->hv_clock.flags = pvclock_flags;
 
 	if (vcpu->pv_time.active)
-		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0);
+		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false);
 #ifdef CONFIG_KVM_XEN
 	if (vcpu->xen.vcpu_info_cache.active)
 		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache,
-					offsetof(struct compat_vcpu_info, time));
+					offsetof(struct compat_vcpu_info, time),
+					xen_pvclock_tsc_unstable);
 	if (vcpu->xen.vcpu_time_info_cache.active)
-		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0);
+		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0,
+					xen_pvclock_tsc_unstable);
 #endif
 	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
@@ -4646,7 +4663,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		    KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
 		    KVM_XEN_HVM_CONFIG_SHARED_INFO |
 		    KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL |
-		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND |
+		    KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
 		if (sched_info_on())
 			r |= KVM_XEN_HVM_CONFIG_RUNSTATE |
 			     KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG;
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index e53fad915a626..e43948b87f94c 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1162,7 +1162,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 {
 	/* Only some feature flags need to be *enabled* by userspace */
 	u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
-		KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+		KVM_XEN_HVM_CONFIG_EVTCHN_SEND |
+		KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
+	u32 old_flags;
 
 	if (xhc->flags & ~permitted_flags)
 		return -EINVAL;
@@ -1183,9 +1185,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 	else if (!xhc->msr && kvm->arch.xen_hvm_config.msr)
 		static_branch_slow_dec_deferred(&kvm_xen_enabled);
 
+	old_flags = kvm->arch.xen_hvm_config.flags;
 	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
 
 	mutex_unlock(&kvm->arch.xen.xen_lock);
+
+	if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE)
+		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
+
 	return 0;
 }
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e9cb2df67a1db..175420b26e363 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1318,6 +1318,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
-- 
GitLab


From efc19c44aa442197ddcbb157c6ca54a56eba8c4e Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 7 Dec 2023 10:33:18 -0600
Subject: [PATCH 0960/4076] w1: amd_axi_w1: Explicitly include correct DT
 includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it was merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231207163318.2727816-1-robh@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/masters/amd_axi_w1.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/w1/masters/amd_axi_w1.c b/drivers/w1/masters/amd_axi_w1.c
index 24a05c2de5f16..4d3a68ca9263a 100644
--- a/drivers/w1/masters/amd_axi_w1.c
+++ b/drivers/w1/masters/amd_axi_w1.c
@@ -12,8 +12,9 @@
 #include <linux/io.h>
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/types.h>
 #include <linux/wait.h>
 
-- 
GitLab


From 2159bd4e905704b1765b6b883ea15e51ad986a6a Mon Sep 17 00:00:00 2001
From: Yuntao Wang <ytcoode@gmail.com>
Date: Thu, 7 Dec 2023 21:10:01 +0800
Subject: [PATCH 0961/4076] memblock: Return NUMA_NO_NODE instead of -1 to
 improve code readability

When no corresponding memory region is found for the given pfn, return
NUMA_NO_NODE instead of -1. This improves code readability and aligns with
the existing logic of the memblock_search_pfn_nid() function's user.

Signed-off-by: Yuntao Wang <ytcoode@gmail.com>
Link: https://lore.kernel.org/r/20231207131001.224914-1-ytcoode@gmail.com
Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
---
 mm/memblock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index 5a88d6d24d793..c1f579c23396a 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1851,7 +1851,7 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
 	int mid = memblock_search(type, PFN_PHYS(pfn));
 
 	if (mid == -1)
-		return -1;
+		return NUMA_NO_NODE;
 
 	*start_pfn = PFN_DOWN(type->regions[mid].base);
 	*end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size);
-- 
GitLab


From 78d60dae9a0c9f09aa3d6477c94047df2fe6f7b0 Mon Sep 17 00:00:00 2001
From: Paul Geurts <paul_geurts@live.nl>
Date: Fri, 24 Nov 2023 14:11:10 +0100
Subject: [PATCH 0962/4076] serial: imx: fix tx statemachine deadlock

When using the serial port as RS485 port, the tx statemachine is used to
control the RTS pin to drive the RS485 transceiver TX_EN pin. When the
TTY port is closed in the middle of a transmission (for instance during
userland application crash), imx_uart_shutdown disables the interface
and disables the Transmission Complete interrupt. afer that,
imx_uart_stop_tx bails on an incomplete transmission, to be retriggered
by the TC interrupt. This interrupt is disabled and therefore the tx
statemachine never transitions out of SEND. The statemachine is in
deadlock now, and the TX_EN remains low, making the interface useless.

imx_uart_stop_tx now checks for incomplete transmission AND whether TC
interrupts are enabled before bailing to be retriggered. This makes sure
the state machine handling is reached, and is properly set to
WAIT_AFTER_SEND.

Fixes: cb1a60923609 ("serial: imx: implement rts delaying for rs485")
Signed-off-by: Paul Geurts <paul_geurts@live.nl>
Tested-by: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Tested-by: Eberhard Stoll <eberhard.stoll@gmx.de>
Link: https://lore.kernel.org/r/AM0PR09MB26758F651BC1B742EB45775995B8A@AM0PR09MB2675.eurprd09.prod.outlook.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 52dd8a6b87603..e7e952bb7bb8a 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -415,13 +415,13 @@ static void imx_uart_stop_tx(struct uart_port *port)
 	ucr1 = imx_uart_readl(sport, UCR1);
 	imx_uart_writel(sport, ucr1 & ~UCR1_TRDYEN, UCR1);
 
+	ucr4 = imx_uart_readl(sport, UCR4);
 	usr2 = imx_uart_readl(sport, USR2);
-	if (!(usr2 & USR2_TXDC)) {
+	if ((!(usr2 & USR2_TXDC)) && (ucr4 & UCR4_TCEN)) {
 		/* The shifter is still busy, so retry once TC triggers */
 		return;
 	}
 
-	ucr4 = imx_uart_readl(sport, UCR4);
 	ucr4 &= ~UCR4_TCEN;
 	imx_uart_writel(sport, ucr4, UCR4);
 
-- 
GitLab


From 675bf8ef209cc8da28ffefd7d8a93c53735cc84a Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Thu, 30 Nov 2023 12:30:01 +0100
Subject: [PATCH 0963/4076] tty: virtio: drop virtio_cons_early_init()

The last user of virtio_cons_early_init() was dropped in commit
7fb2b2d51244 ("s390/virtio: remove the old KVM virtio transport").

So now, drop virtio_cons_early_init() and the logic and headers behind
too.

Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Acked-by: Jason Wang <jasowang@redhat.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Amit Shah <amit@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: linux-alpha@vger.kernel.org
Cc: virtualization@lists.linux.dev
Link: https://lore.kernel.org/r/20231130113001.29154-1-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS                    |  1 -
 drivers/char/virtio_console.c  | 48 ----------------------------------
 include/linux/virtio_console.h | 38 ---------------------------
 3 files changed, 87 deletions(-)
 delete mode 100644 include/linux/virtio_console.h

diff --git a/MAINTAINERS b/MAINTAINERS
index ea790149af795..d60009f3ef9cb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23018,7 +23018,6 @@ M:	Amit Shah <amit@kernel.org>
 L:	virtualization@lists.linux.dev
 S:	Maintained
 F:	drivers/char/virtio_console.c
-F:	include/linux/virtio_console.h
 F:	include/uapi/linux/virtio_console.h
 
 VIRTIO CORE AND NET DRIVERS
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 431e9e5bf9c15..8abe599c1c07e 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -230,9 +230,6 @@ struct port {
 	bool guest_connected;
 };
 
-/* This is the very early arch-specified put chars function. */
-static int (*early_put_chars)(u32, const char *, int);
-
 static struct port *find_port_by_vtermno(u32 vtermno)
 {
 	struct port *port;
@@ -1114,9 +1111,6 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 	void *data;
 	int ret;
 
-	if (unlikely(early_put_chars))
-		return early_put_chars(vtermno, buf, count);
-
 	port = find_port_by_vtermno(vtermno);
 	if (!port)
 		return -EPIPE;
@@ -1142,10 +1136,6 @@ static int get_chars(u32 vtermno, char *buf, int count)
 {
 	struct port *port;
 
-	/* If we've not set up the port yet, we have no input to give. */
-	if (unlikely(early_put_chars))
-		return 0;
-
 	port = find_port_by_vtermno(vtermno);
 	if (!port)
 		return -EPIPE;
@@ -1201,21 +1191,6 @@ static const struct hv_ops hv_ops = {
 	.notifier_hangup = notifier_del_vio,
 };
 
-/*
- * Console drivers are initialized very early so boot messages can go
- * out, so we do things slightly differently from the generic virtio
- * initialization of the net and block drivers.
- *
- * At this stage, the console is output-only.  It's too early to set
- * up a virtqueue, so we let the drivers do some boutique early-output
- * thing.
- */
-int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int))
-{
-	early_put_chars = put_chars;
-	return hvc_instantiate(0, 0, &hv_ops);
-}
-
 static int init_port_console(struct port *port)
 {
 	int ret;
@@ -1256,13 +1231,6 @@ static int init_port_console(struct port *port)
 	spin_unlock_irq(&pdrvdata_lock);
 	port->guest_connected = true;
 
-	/*
-	 * Start using the new console output if this is the first
-	 * console to come up.
-	 */
-	if (early_put_chars)
-		early_put_chars = NULL;
-
 	/* Notify host of port being opened */
 	send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 1);
 
@@ -1999,7 +1967,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 	struct ports_device *portdev;
 	int err;
 	bool multiport;
-	bool early = early_put_chars != NULL;
 
 	/* We only need a config space if features are offered */
 	if (!vdev->config->get &&
@@ -2010,9 +1977,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 		return -EINVAL;
 	}
 
-	/* Ensure to read early_put_chars now */
-	barrier();
-
 	portdev = kmalloc(sizeof(*portdev), GFP_KERNEL);
 	if (!portdev) {
 		err = -ENOMEM;
@@ -2100,18 +2064,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 	__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
 			   VIRTIO_CONSOLE_DEVICE_READY, 1);
 
-	/*
-	 * If there was an early virtio console, assume that there are no
-	 * other consoles. We need to wait until the hvc_alloc matches the
-	 * hvc_instantiate, otherwise tty_open will complain, resulting in
-	 * a "Warning: unable to open an initial console" boot failure.
-	 * Without multiport this is done in add_port above. With multiport
-	 * this might take some host<->guest communication - thus we have to
-	 * wait.
-	 */
-	if (multiport && early)
-		wait_for_completion(&early_console_added);
-
 	return 0;
 
 free_chrdev:
diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h
deleted file mode 100644
index d2e2785af6026..0000000000000
--- a/include/linux/virtio_console.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers:
- *
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the name of IBM nor the names of its contributors
- *    may be used to endorse or promote products derived from this software
- *    without specific prior written permission.
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * Copyright (C) Red Hat, Inc., 2009, 2010, 2011
- * Copyright (C) Amit Shah <amit.shah@redhat.com>, 2009, 2010, 2011
- */
-#ifndef _LINUX_VIRTIO_CONSOLE_H
-#define _LINUX_VIRTIO_CONSOLE_H
-
-#include <uapi/linux/virtio_console.h>
-
-int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int));
-#endif /* _LINUX_VIRTIO_CONSOLE_H */
-- 
GitLab


From 093258a9963bfac043244995bff87dc2c931b9b5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 30 Nov 2023 15:07:13 +0100
Subject: [PATCH 0964/4076] tty: serial: amba: cleanup whitespace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix whitespace in include/linux/amba/serial.h to match current kernel
coding standards. Fixes about:

 - CHECK: spaces preferred around that '|' (ctx:VxV)
 - ERROR: code indent should use tabs where possible
 - WARNING: Unnecessary space before function pointer arguments
 - WARNING: please, no spaces at the start of a line

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231130-mbly-uart-v5-1-6566703a04b5@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/amba/serial.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index a1307b58cc2c6..27003ec52114c 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -75,10 +75,10 @@
 #define UART011_DR_PE		(1 << 9)
 #define UART011_DR_FE		(1 << 8)
 
-#define UART01x_RSR_OE 		0x08
-#define UART01x_RSR_BE 		0x04
-#define UART01x_RSR_PE 		0x02
-#define UART01x_RSR_FE 		0x01
+#define UART01x_RSR_OE		0x08
+#define UART01x_RSR_BE		0x04
+#define UART01x_RSR_PE		0x02
+#define UART01x_RSR_FE		0x01
 
 #define UART011_FR_RI		0x100
 #define UART011_FR_TXFE		0x080
@@ -86,9 +86,9 @@
 #define UART01x_FR_TXFF		0x020
 #define UART01x_FR_RXFE		0x010
 #define UART01x_FR_BUSY		0x008
-#define UART01x_FR_DCD 		0x004
-#define UART01x_FR_DSR 		0x002
-#define UART01x_FR_CTS 		0x001
+#define UART01x_FR_DCD		0x004
+#define UART01x_FR_DSR		0x002
+#define UART01x_FR_CTS		0x001
 #define UART01x_FR_TMSK		(UART01x_FR_TXFF + UART01x_FR_BUSY)
 
 /*
@@ -110,14 +110,14 @@
 #define UART011_CR_TXE		0x0100	/* transmit enable */
 #define UART011_CR_LBE		0x0080	/* loopback enable */
 #define UART010_CR_RTIE		0x0040
-#define UART010_CR_TIE 		0x0020
-#define UART010_CR_RIE 		0x0010
+#define UART010_CR_TIE		0x0020
+#define UART010_CR_RIE		0x0010
 #define UART010_CR_MSIE		0x0008
 #define ST_UART011_CR_OVSFACT	0x0008	/* Oversampling factor */
 #define UART01x_CR_IIRLP	0x0004	/* SIR low power mode */
 #define UART01x_CR_SIREN	0x0002	/* SIR enable */
 #define UART01x_CR_UARTEN	0x0001	/* UART enable */
- 
+
 #define UART011_LCRH_SPS	0x80
 #define UART01x_LCRH_WLEN_8	0x60
 #define UART01x_LCRH_WLEN_7	0x40
@@ -203,8 +203,8 @@
 #define UART011_TXDMAE		(1 << 1)	/* enable transmit dma */
 #define UART011_RXDMAE		(1 << 0)	/* enable receive dma */
 
-#define UART01x_RSR_ANY		(UART01x_RSR_OE|UART01x_RSR_BE|UART01x_RSR_PE|UART01x_RSR_FE)
-#define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD|UART01x_FR_DSR|UART01x_FR_CTS)
+#define UART01x_RSR_ANY		(UART01x_RSR_OE | UART01x_RSR_BE | UART01x_RSR_PE | UART01x_RSR_FE)
+#define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD | UART01x_FR_DSR | UART01x_FR_CTS)
 
 #ifndef __ASSEMBLY__
 struct amba_device; /* in uncompress this is included but amba/bus.h is not */
@@ -220,8 +220,8 @@ struct amba_pl011_data {
 	bool dma_rx_poll_enable;
 	unsigned int dma_rx_poll_rate;
 	unsigned int dma_rx_poll_timeout;
-        void (*init) (void);
-	void (*exit) (void);
+	void (*init)(void);
+	void (*exit)(void);
 };
 #endif
 
-- 
GitLab


From b18fefd230e47f22d2ec014219bc053c5806afb9 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@cherry.de>
Date: Fri, 1 Dec 2023 15:05:42 +0100
Subject: [PATCH 0965/4076] dt-bindings: serial: snps-dw-apb-uart: include
 rs485 schema

The dw-apb-uart also can emulate rs485, so include the rs485
schema to allow validating rs485 properties.

Signed-off-by: Heiko Stuebner <heiko.stuebner@cherry.de>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231201140542.323564-1-heiko@sntech.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml
index 17c553123f96e..1001d2a6ace85 100644
--- a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml
@@ -11,6 +11,7 @@ maintainers:
 
 allOf:
   - $ref: serial.yaml#
+  - $ref: rs485.yaml#
 
 properties:
   compatible:
-- 
GitLab


From 0ec058ece2f933aed66b76bd5cb9b5e6764853c3 Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.kumar.halder@amd.com>
Date: Tue, 5 Dec 2023 12:35:34 +0000
Subject: [PATCH 0966/4076] tty: hvc: dcc: Check for TXfull condition while
 setting up early console

Refer ARM DDI 0487I.a ID081822, D17.3.8, DBGDTRTX_EL0,
"If TXfull is set to 1, set DTRRX and DTRTX to UNKNOWN"

Thus one should always check for TXfull condition before hvc can be
used as an early console. This is similar to what is being done
today in hvc_dcc_console_init() and hvc_dcc_init().

The count 0x4000000 has been obtained from uboot (v2024.01-rc3)
drivers/serial/arm_dcc.c "TIMEOUT_COUNT".
It reads the dcc status and waits for 0x4000000  times for the TX Fifo
to be available before returning an error. Thus, it will prevent DCC
to be used as early console.

Signed-off-by: Ayan Kumar Halder <ayan.kumar.halder@amd.com>
Link: https://lore.kernel.org/r/20231205123534.3376883-1-ayan.kumar.halder@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/hvc/hvc_dcc.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/tty/hvc/hvc_dcc.c b/drivers/tty/hvc/hvc_dcc.c
index 1751108cf763e..136381bec7cd7 100644
--- a/drivers/tty/hvc/hvc_dcc.c
+++ b/drivers/tty/hvc/hvc_dcc.c
@@ -47,6 +47,14 @@ static void dcc_early_write(struct console *con, const char *s, unsigned n)
 static int __init dcc_early_console_setup(struct earlycon_device *device,
 					  const char *opt)
 {
+	unsigned int count = 0x4000000;
+
+	while (--count && (__dcc_getstatus() & DCC_STATUS_TX))
+		cpu_relax();
+
+	if (__dcc_getstatus() & DCC_STATUS_TX)
+		return -ENODEV;
+
 	device->con->write = dcc_early_write;
 
 	return 0;
-- 
GitLab


From 1e7e56160d9ddec12093047e09abb17b0fa1a834 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Tue, 5 Dec 2023 14:16:43 +0100
Subject: [PATCH 0967/4076] serial: ucc_uart: Fix multiple address space type
 errors

sparse reports multiple problems with address space type.

Most problems are linked to missing __iomem qualifier.

Others are caused by dereferencing __iomem addresses.

Fix all this by adding missing __iomem and using ioread32be().

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312050412.zN2PKArS-lkp@intel.com/
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Link: https://lore.kernel.org/r/e49deeb079391ff7273ec32f5563df94cf70bc95.1701781976.git.christophe.leroy@csgroup.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/ucc_uart.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c
index f9ad942c9aafe..397b95dff7eda 100644
--- a/drivers/tty/serial/ucc_uart.c
+++ b/drivers/tty/serial/ucc_uart.c
@@ -189,10 +189,10 @@ struct uart_qe_port {
 	u16 tx_fifosize;
 	int wait_closing;
 	u32 flags;
-	struct qe_bd *rx_bd_base;
-	struct qe_bd *rx_cur;
-	struct qe_bd *tx_bd_base;
-	struct qe_bd *tx_cur;
+	struct qe_bd __iomem *rx_bd_base;
+	struct qe_bd __iomem *rx_cur;
+	struct qe_bd __iomem *tx_bd_base;
+	struct qe_bd __iomem *tx_cur;
 	unsigned char *tx_buf;
 	unsigned char *rx_buf;
 	void *bd_virt;  	/* virtual address of the BD buffers */
@@ -258,7 +258,7 @@ static unsigned int qe_uart_tx_empty(struct uart_port *port)
 {
 	struct uart_qe_port *qe_port =
 		container_of(port, struct uart_qe_port, port);
-	struct qe_bd *bdp = qe_port->tx_bd_base;
+	struct qe_bd __iomem *bdp = qe_port->tx_bd_base;
 
 	while (1) {
 		if (ioread16be(&bdp->status) & BD_SC_READY)
@@ -330,7 +330,7 @@ static void qe_uart_stop_tx(struct uart_port *port)
  */
 static int qe_uart_tx_pump(struct uart_qe_port *qe_port)
 {
-	struct qe_bd *bdp;
+	struct qe_bd __iomem *bdp;
 	unsigned char *p;
 	unsigned int count;
 	struct uart_port *port = &qe_port->port;
@@ -341,7 +341,7 @@ static int qe_uart_tx_pump(struct uart_qe_port *qe_port)
 		/* Pick next descriptor and fill from buffer */
 		bdp = qe_port->tx_cur;
 
-		p = qe2cpu_addr(be32_to_cpu(bdp->buf), qe_port);
+		p = qe2cpu_addr(ioread32be(&bdp->buf), qe_port);
 
 		*p++ = port->x_char;
 		iowrite16be(1, &bdp->length);
@@ -368,7 +368,7 @@ static int qe_uart_tx_pump(struct uart_qe_port *qe_port)
 
 	while (!(ioread16be(&bdp->status) & BD_SC_READY) && !uart_circ_empty(xmit)) {
 		count = 0;
-		p = qe2cpu_addr(be32_to_cpu(bdp->buf), qe_port);
+		p = qe2cpu_addr(ioread32be(&bdp->buf), qe_port);
 		while (count < qe_port->tx_fifosize) {
 			*p++ = xmit->buf[xmit->tail];
 			uart_xmit_advance(port, 1);
@@ -460,7 +460,7 @@ static void qe_uart_int_rx(struct uart_qe_port *qe_port)
 	unsigned char ch, *cp;
 	struct uart_port *port = &qe_port->port;
 	struct tty_port *tport = &port->state->port;
-	struct qe_bd *bdp;
+	struct qe_bd __iomem *bdp;
 	u16 status;
 	unsigned int flg;
 
@@ -487,7 +487,7 @@ static void qe_uart_int_rx(struct uart_qe_port *qe_port)
 		}
 
 		/* get pointer */
-		cp = qe2cpu_addr(be32_to_cpu(bdp->buf), qe_port);
+		cp = qe2cpu_addr(ioread32be(&bdp->buf), qe_port);
 
 		/* loop through the buffer */
 		while (i-- > 0) {
@@ -590,7 +590,7 @@ static void qe_uart_initbd(struct uart_qe_port *qe_port)
 {
 	int i;
 	void *bd_virt;
-	struct qe_bd *bdp;
+	struct qe_bd __iomem *bdp;
 
 	/* Set the physical address of the host memory buffers in the buffer
 	 * descriptors, and the virtual address for us to work with.
@@ -648,7 +648,7 @@ static void qe_uart_init_ucc(struct uart_qe_port *qe_port)
 {
 	u32 cecr_subblock;
 	struct ucc_slow __iomem *uccp = qe_port->uccp;
-	struct ucc_uart_pram *uccup = qe_port->uccup;
+	struct ucc_uart_pram __iomem *uccup = qe_port->uccup;
 
 	unsigned int i;
 
@@ -983,7 +983,7 @@ static int qe_uart_request_port(struct uart_port *port)
 
 	qe_port->us_private = uccs;
 	qe_port->uccp = uccs->us_regs;
-	qe_port->uccup = (struct ucc_uart_pram *) uccs->us_pram;
+	qe_port->uccup = (struct ucc_uart_pram __iomem *)uccs->us_pram;
 	qe_port->rx_bd_base = uccs->rx_bd;
 	qe_port->tx_bd_base = uccs->tx_bd;
 
@@ -1156,7 +1156,7 @@ static void uart_firmware_cont(const struct firmware *fw, void *context)
 
 	firmware = (struct qe_firmware *) fw->data;
 
-	if (firmware->header.length != fw->size) {
+	if (be32_to_cpu(firmware->header.length) != fw->size) {
 		dev_err(dev, "invalid firmware\n");
 		goto out;
 	}
-- 
GitLab


From 692079bda7802fccbf82daeb93d47d3d92972bbf Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan.gerhold@kernkonzept.com>
Date: Tue, 28 Nov 2023 10:43:32 +0100
Subject: [PATCH 0968/4076] dt-bindings: serial: qcom,msm-uartdm: Vote for
 shared resources

Document power-domains, operating-points-v2 and interconnects to allow
making performance state votes for certain clock frequencies of the UART
DM controller. The interconnect path to DRAM is needed when UART DM is
used together with a DMA engine.

Voting for these shared resources is necessary to guarantee performance
with power management enabled. Otherwise these resources might run at
minimal performance state which is not sufficient for certain UART
baud rates.

Signed-off-by: Stephan Gerhold <stephan.gerhold@kernkonzept.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231128-serial-msm-dvfs-v1-1-4f290d20a4be@kernkonzept.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/serial/qcom,msm-uartdm.yaml | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.yaml b/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.yaml
index ee52bf8e8917d..e0fa363ad7e2e 100644
--- a/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.yaml
+++ b/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.yaml
@@ -48,9 +48,17 @@ properties:
       - const: tx
       - const: rx
 
+  interconnects:
+    maxItems: 1
+
   interrupts:
     maxItems: 1
 
+  operating-points-v2: true
+
+  power-domains:
+    maxItems: 1
+
   qcom,rx-crci:
     $ref: /schemas/types.yaml#/definitions/uint32
     description:
@@ -99,7 +107,9 @@ unevaluatedProperties: false
 
 examples:
   - |
+    #include <dt-bindings/interconnect/qcom,msm8996.h>
     #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/qcom-rpmpd.h>
 
     serial@f991e000 {
         compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
@@ -109,4 +119,7 @@ examples:
         clock-names = "core", "iface";
         dmas = <&dma0 0>, <&dma0 1>;
         dma-names = "tx", "rx";
+        power-domains = <&rpmpd MSM8996_VDDCX>;
+        operating-points-v2 = <&uart_opp_table>;
+        interconnects = <&pnoc MASTER_BLSP_1 &bimc SLAVE_EBI_CH0>;
     };
-- 
GitLab


From 173ebdedcd844a39bb884afc1c1f97b74319dda6 Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan.gerhold@kernkonzept.com>
Date: Tue, 28 Nov 2023 10:43:33 +0100
Subject: [PATCH 0969/4076] serial: msm: Use OPP table for DVFS support

Parse the OPP table from the device tree and use dev_pm_opp_set_rate()
instead of clk_set_rate() to allow making performance state votes
specified in the OPP table (e.g. for power domains and interconnects).

Without an OPP table in the device tree this will behave just as before
this patch.

Signed-off-by: Stephan Gerhold <stephan.gerhold@kernkonzept.com>
Link: https://lore.kernel.org/r/20231128-serial-msm-dvfs-v1-2-4f290d20a4be@kernkonzept.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/msm_serial.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 7fc8f0b16aef6..e24204ad35def 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/platform_device.h>
+#include <linux/pm_opp.h>
 #include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -1131,7 +1132,7 @@ static int msm_set_baud_rate(struct uart_port *port, unsigned int baud,
 	uart_port_unlock_irqrestore(port, flags);
 
 	entry = msm_find_best_baud(port, baud, &rate);
-	clk_set_rate(msm_port->clk, rate);
+	dev_pm_opp_set_rate(port->dev, rate);
 	baud = rate / 16 / entry->divisor;
 
 	uart_port_lock_irqsave(port, &flags);
@@ -1186,6 +1187,7 @@ static void msm_init_clock(struct uart_port *port)
 {
 	struct msm_port *msm_port = to_msm_port(port);
 
+	dev_pm_opp_set_rate(port->dev, port->uartclk);
 	clk_prepare_enable(msm_port->clk);
 	clk_prepare_enable(msm_port->pclk);
 	msm_serial_set_mnd_regs(port);
@@ -1239,6 +1241,7 @@ err_irq:
 
 	clk_disable_unprepare(msm_port->pclk);
 	clk_disable_unprepare(msm_port->clk);
+	dev_pm_opp_set_rate(port->dev, 0);
 
 	return ret;
 }
@@ -1254,6 +1257,7 @@ static void msm_shutdown(struct uart_port *port)
 		msm_release_dma(msm_port);
 
 	clk_disable_unprepare(msm_port->clk);
+	dev_pm_opp_set_rate(port->dev, 0);
 
 	free_irq(port->irq, port);
 }
@@ -1419,11 +1423,13 @@ static void msm_power(struct uart_port *port, unsigned int state,
 
 	switch (state) {
 	case 0:
+		dev_pm_opp_set_rate(port->dev, port->uartclk);
 		clk_prepare_enable(msm_port->clk);
 		clk_prepare_enable(msm_port->pclk);
 		break;
 	case 3:
 		clk_disable_unprepare(msm_port->clk);
+		dev_pm_opp_set_rate(port->dev, 0);
 		clk_disable_unprepare(msm_port->pclk);
 		break;
 	default:
@@ -1789,7 +1795,7 @@ static int msm_serial_probe(struct platform_device *pdev)
 	struct resource *resource;
 	struct uart_port *port;
 	const struct of_device_id *id;
-	int irq, line;
+	int irq, line, ret;
 
 	if (pdev->dev.of_node)
 		line = of_alias_get_id(pdev->dev.of_node, "serial");
@@ -1824,6 +1830,15 @@ static int msm_serial_probe(struct platform_device *pdev)
 			return PTR_ERR(msm_port->pclk);
 	}
 
+	ret = devm_pm_opp_set_clkname(&pdev->dev, "core");
+	if (ret)
+		return ret;
+
+	/* OPP table is optional */
+	ret = devm_pm_opp_of_add_table(&pdev->dev);
+	if (ret && ret != -ENODEV)
+		return dev_err_probe(&pdev->dev, ret, "invalid OPP table\n");
+
 	port->uartclk = clk_get_rate(msm_port->clk);
 	dev_info(&pdev->dev, "uartclk = %d\n", port->uartclk);
 
-- 
GitLab


From e01b5712a80d04cdb4699d6a0b3d5f6e838425d5 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:46 +0100
Subject: [PATCH 0970/4076] tty: goldfish: use bool for is_write parameter

do_rw_io()'s is_write parameter is boolean, but typed int. Switch to the
former, so that it's obvious. (And the two users too.)

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-2-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/goldfish.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c
index dccf6c6c69c6e..7ad7fa66cb273 100644
--- a/drivers/tty/goldfish.c
+++ b/drivers/tty/goldfish.c
@@ -53,7 +53,7 @@ static struct goldfish_tty *goldfish_ttys;
 static void do_rw_io(struct goldfish_tty *qtty,
 		     unsigned long address,
 		     unsigned int count,
-		     int is_write)
+		     bool is_write)
 {
 	unsigned long irq_flags;
 	void __iomem *base = qtty->base;
@@ -76,7 +76,7 @@ static void do_rw_io(struct goldfish_tty *qtty,
 static void goldfish_tty_rw(struct goldfish_tty *qtty,
 			    unsigned long addr,
 			    unsigned int count,
-			    int is_write)
+			    bool is_write)
 {
 	dma_addr_t dma_handle;
 	enum dma_data_direction dma_dir;
@@ -129,7 +129,7 @@ static void goldfish_tty_do_write(int line, const u8 *buf, unsigned int count)
 {
 	struct goldfish_tty *qtty = &goldfish_ttys[line];
 
-	goldfish_tty_rw(qtty, (unsigned long)buf, count, 1);
+	goldfish_tty_rw(qtty, (unsigned long)buf, count, true);
 }
 
 static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
@@ -145,7 +145,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 
 	count = tty_prepare_flip_string(&qtty->port, &buf, count);
 
-	goldfish_tty_rw(qtty, (unsigned long)buf, count, 0);
+	goldfish_tty_rw(qtty, (unsigned long)buf, count, false);
 
 	tty_flip_buffer_push(&qtty->port);
 	return IRQ_HANDLED;
-- 
GitLab


From e93102bea4a1935403d2aadce567fbd1b9e853e0 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:47 +0100
Subject: [PATCH 0971/4076] tty: mmc: sdio_uart: switch sdio_in() to return u8

sdio_in() returns a value returned from sdio_readb(). The latter returns
u8. So should the former. Therefore, switch sdio_in() return type to u8
and all its callers too.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: linux-mmc@vger.kernel.org
Link: https://lore.kernel.org/r/20231206073712.17776-3-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/mmc/core/sdio_uart.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c
index ef38dcd3a8872..a05322f157718 100644
--- a/drivers/mmc/core/sdio_uart.c
+++ b/drivers/mmc/core/sdio_uart.c
@@ -178,11 +178,9 @@ static inline void sdio_uart_release_func(struct sdio_uart_port *port)
 		sdio_release_host(port->func);
 }
 
-static inline unsigned int sdio_in(struct sdio_uart_port *port, int offset)
+static inline u8 sdio_in(struct sdio_uart_port *port, int offset)
 {
-	unsigned char c;
-	c = sdio_readb(port->func, port->regs_offset + offset, NULL);
-	return c;
+	return sdio_readb(port->func, port->regs_offset + offset, NULL);
 }
 
 static inline void sdio_out(struct sdio_uart_port *port, int offset, int value)
@@ -192,8 +190,8 @@ static inline void sdio_out(struct sdio_uart_port *port, int offset, int value)
 
 static unsigned int sdio_uart_get_mctrl(struct sdio_uart_port *port)
 {
-	unsigned char status;
 	unsigned int ret;
+	u8 status;
 
 	/* FIXME: What stops this losing the delta bits and breaking
 	   sdio_uart_check_modem_status ? */
@@ -354,14 +352,13 @@ static void sdio_uart_stop_rx(struct sdio_uart_port *port)
 	sdio_out(port, UART_IER, port->ier);
 }
 
-static void sdio_uart_receive_chars(struct sdio_uart_port *port,
-				    unsigned int *status)
+static void sdio_uart_receive_chars(struct sdio_uart_port *port, u8 *status)
 {
-	unsigned int ch, flag;
+	unsigned int flag;
 	int max_count = 256;
 
 	do {
-		ch = sdio_in(port, UART_RX);
+		u8 ch = sdio_in(port, UART_RX);
 		flag = TTY_NORMAL;
 		port->icount.rx++;
 
@@ -449,8 +446,8 @@ static void sdio_uart_transmit_chars(struct sdio_uart_port *port)
 
 static void sdio_uart_check_modem_status(struct sdio_uart_port *port)
 {
-	int status;
 	struct tty_struct *tty;
+	u8 status;
 
 	status = sdio_in(port, UART_MSR);
 
@@ -499,7 +496,7 @@ static void sdio_uart_check_modem_status(struct sdio_uart_port *port)
 static void sdio_uart_irq(struct sdio_func *func)
 {
 	struct sdio_uart_port *port = sdio_get_drvdata(func);
-	unsigned int iir, lsr;
+	u8 iir, lsr;
 
 	/*
 	 * In a few places sdio_uart_irq() is called directly instead of
-- 
GitLab


From 49943393c9f0be61fd494a884851aa117cd72382 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:48 +0100
Subject: [PATCH 0972/4076] tty: switch tty_port::xmit_* to u8

Both xmit_buf and xmit_fifo of struct tty_port should be u8. To conform
to characters in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-4-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_port.c   | 2 +-
 include/linux/tty_port.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index ef72d2e4b928d..14cca33d22693 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -247,7 +247,7 @@ int tty_port_alloc_xmit_buf(struct tty_port *port)
 	/* We may sleep in get_zeroed_page() */
 	mutex_lock(&port->buf_mutex);
 	if (port->xmit_buf == NULL) {
-		port->xmit_buf = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+		port->xmit_buf = (u8 *)get_zeroed_page(GFP_KERNEL);
 		if (port->xmit_buf)
 			kfifo_init(&port->xmit_fifo, port->xmit_buf, PAGE_SIZE);
 	}
diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h
index 3276311a7f384..1b861f2100b69 100644
--- a/include/linux/tty_port.h
+++ b/include/linux/tty_port.h
@@ -114,8 +114,8 @@ struct tty_port {
 	unsigned char		console:1;
 	struct mutex		mutex;
 	struct mutex		buf_mutex;
-	unsigned char		*xmit_buf;
-	DECLARE_KFIFO_PTR(xmit_fifo, unsigned char);
+	u8			*xmit_buf;
+	DECLARE_KFIFO_PTR(xmit_fifo, u8);
 	unsigned int		close_delay;
 	unsigned int		closing_wait;
 	int			drain_delay;
-- 
GitLab


From 3a00da027946cd08db1c1be2de4620950bbdf074 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:49 +0100
Subject: [PATCH 0973/4076] tty: make tty_operations::send_xchar accept u8 char

tty_operations::send_xchar is one of the last users of 'char' type for
characters in the tty layer. Convert it to u8 now.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Marcel Holtmann <marcel@holtmann.org>
Cc: Johan Hedberg <johan.hedberg@gmail.com>
Cc: Luiz Augusto von Dentz <luiz.dentz@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-mmc@vger.kernel.org
Cc: linux-bluetooth@vger.kernel.org
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20231206073712.17776-5-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/isdn/capi/capi.c         | 4 ++--
 drivers/mmc/core/sdio_uart.c     | 2 +-
 drivers/tty/amiserial.c          | 2 +-
 drivers/tty/serial/serial_core.c | 2 +-
 drivers/tty/tty_io.c             | 2 +-
 include/linux/tty.h              | 2 +-
 include/linux/tty_driver.h       | 4 ++--
 net/bluetooth/rfcomm/tty.c       | 2 +-
 8 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 2f37895154455..6e80d7bd3c4dc 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -1231,9 +1231,9 @@ static void capinc_tty_hangup(struct tty_struct *tty)
 	tty_port_hangup(&mp->port);
 }
 
-static void capinc_tty_send_xchar(struct tty_struct *tty, char ch)
+static void capinc_tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
-	pr_debug("capinc_tty_send_xchar(%d)\n", ch);
+	pr_debug("capinc_tty_send_xchar(%u)\n", ch);
 }
 
 static const struct tty_operations capinc_ops = {
diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c
index a05322f157718..370fadf1d6d1c 100644
--- a/drivers/mmc/core/sdio_uart.c
+++ b/drivers/mmc/core/sdio_uart.c
@@ -792,7 +792,7 @@ static unsigned int sdio_uart_chars_in_buffer(struct tty_struct *tty)
 	return kfifo_len(&port->xmit_fifo);
 }
 
-static void sdio_uart_send_xchar(struct tty_struct *tty, char ch)
+static void sdio_uart_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct sdio_uart_port *port = tty->driver_data;
 
diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index a80f059f77bf0..a30dc054ffbf6 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -811,7 +811,7 @@ static void rs_flush_buffer(struct tty_struct *tty)
  * This function is used to send a high-priority XON/XOFF character to
  * the device
  */
-static void rs_send_xchar(struct tty_struct *tty, char ch)
+static void rs_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct serial_state *info = tty->driver_data;
         unsigned long flags;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 0393853b99475..80085b151b34d 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -687,7 +687,7 @@ EXPORT_SYMBOL_GPL(uart_xchar_out);
  * This function is used to send a high-priority XON/XOFF character to
  * the device
  */
-static void uart_send_xchar(struct tty_struct *tty, char ch)
+static void uart_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct uart_state *state = tty->driver_data;
 	struct uart_port *port;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 005d91c637072..6a502110da619 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1149,7 +1149,7 @@ ssize_t redirected_tty_write(struct kiocb *iocb, struct iov_iter *iter)
  *
  * Locking: none for xchar method, write ordering for write method.
  */
-int tty_send_xchar(struct tty_struct *tty, char ch)
+int tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	bool was_stopped = tty->flow.stopped;
 
diff --git a/include/linux/tty.h b/include/linux/tty.h
index e96c85f4f91ed..d3bedcc08738a 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -410,7 +410,7 @@ void tty_wait_until_sent(struct tty_struct *tty, long timeout);
 void stop_tty(struct tty_struct *tty);
 void start_tty(struct tty_struct *tty);
 void tty_write_message(struct tty_struct *tty, char *msg);
-int tty_send_xchar(struct tty_struct *tty, char ch);
+int tty_send_xchar(struct tty_struct *tty, u8 ch);
 int tty_put_char(struct tty_struct *tty, unsigned char c);
 unsigned int tty_chars_in_buffer(struct tty_struct *tty);
 unsigned int tty_write_room(struct tty_struct *tty);
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index f428c1b784a20..7372124fbf90b 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -242,7 +242,7 @@ struct serial_struct;
  *	Optional: If not provided, the device is assumed to have no FIFO.
  *	Usually correct to invoke via tty_wait_until_sent(). May sleep.
  *
- * @send_xchar: ``void ()(struct tty_struct *tty, char ch)``
+ * @send_xchar: ``void ()(struct tty_struct *tty, u8 ch)``
  *
  *	This routine is used to send a high-priority XON/XOFF character (@ch)
  *	to the @tty device.
@@ -374,7 +374,7 @@ struct tty_operations {
 	void (*flush_buffer)(struct tty_struct *tty);
 	void (*set_ldisc)(struct tty_struct *tty);
 	void (*wait_until_sent)(struct tty_struct *tty, int timeout);
-	void (*send_xchar)(struct tty_struct *tty, char ch);
+	void (*send_xchar)(struct tty_struct *tty, u8 ch);
 	int (*tiocmget)(struct tty_struct *tty);
 	int (*tiocmset)(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 94ec913dfb76e..69c75c041fe10 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -1041,7 +1041,7 @@ static void rfcomm_tty_flush_buffer(struct tty_struct *tty)
 	tty_wakeup(tty);
 }
 
-static void rfcomm_tty_send_xchar(struct tty_struct *tty, char ch)
+static void rfcomm_tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	BT_DBG("tty %p ch %c", tty, ch);
 }
-- 
GitLab


From 4e8d8878145f1478886e1630c44113ad2c2eb99d Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:50 +0100
Subject: [PATCH 0974/4076] tty: core: the rest to u8

There are still last minor users in the tty core that still reference
characters by the 'char' type. Switch them to u8.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-6-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c | 10 +++++-----
 include/linux/tty.h  |  4 ++--
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 6a502110da619..f3ca2105b66df 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -852,9 +852,9 @@ static ssize_t iterate_tty_read(struct tty_ldisc *ld, struct tty_struct *tty,
 {
 	void *cookie = NULL;
 	unsigned long offset = 0;
-	char kernel_buf[64];
 	ssize_t retval = 0;
 	size_t copied, count = iov_iter_count(to);
+	u8 kernel_buf[64];
 
 	do {
 		ssize_t size = min(count, sizeof(kernel_buf));
@@ -995,7 +995,7 @@ static ssize_t iterate_tty_write(struct tty_ldisc *ld, struct tty_struct *tty,
 
 	/* write_buf/write_cnt is protected by the atomic_write_lock mutex */
 	if (tty->write_cnt < chunk) {
-		unsigned char *buf_chunk;
+		u8 *buf_chunk;
 
 		if (chunk < 1024)
 			chunk = 1024;
@@ -2278,10 +2278,10 @@ static bool tty_legacy_tiocsti __read_mostly = IS_ENABLED(CONFIG_LEGACY_TIOCSTI)
  *  * Called functions take tty_ldiscs_lock
  *  * current->signal->tty check is safe without locks
  */
-static int tiocsti(struct tty_struct *tty, char __user *p)
+static int tiocsti(struct tty_struct *tty, u8 __user *p)
 {
-	char ch;
 	struct tty_ldisc *ld;
+	u8 ch;
 
 	if (!tty_legacy_tiocsti && !capable(CAP_SYS_ADMIN))
 		return -EIO;
@@ -3142,7 +3142,7 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx)
  *
  * Return: the number of characters successfully output.
  */
-int tty_put_char(struct tty_struct *tty, unsigned char ch)
+int tty_put_char(struct tty_struct *tty, u8 ch)
 {
 	if (tty->ops->put_char)
 		return tty->ops->put_char(tty, ch);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index d3bedcc08738a..cc08f7e1c122b 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -242,7 +242,7 @@ struct tty_struct {
 	void *driver_data;
 	spinlock_t files_lock;
 	int write_cnt;
-	unsigned char *write_buf;
+	u8 *write_buf;
 
 	struct list_head tty_files;
 
@@ -411,7 +411,7 @@ void stop_tty(struct tty_struct *tty);
 void start_tty(struct tty_struct *tty);
 void tty_write_message(struct tty_struct *tty, char *msg);
 int tty_send_xchar(struct tty_struct *tty, u8 ch);
-int tty_put_char(struct tty_struct *tty, unsigned char c);
+int tty_put_char(struct tty_struct *tty, u8 c);
 unsigned int tty_chars_in_buffer(struct tty_struct *tty);
 unsigned int tty_write_room(struct tty_struct *tty);
 void tty_driver_flush_buffer(struct tty_struct *tty);
-- 
GitLab


From fbdeead9598ca202bf30c5c4b14f3768db99ca45 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:51 +0100
Subject: [PATCH 0975/4076] tty: ami: use u8 for characters and flag

Switch character types to u8. To conform to characters in the rest of
the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20231206073712.17776-7-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/amiserial.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index a30dc054ffbf6..7716ce0d35bc2 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -81,7 +81,7 @@ struct serial_state {
 	int			quot;
 	int			IER; 	/* Interrupt Enable Register */
 	int			MCR; 	/* Modem control register */
-	int			x_char;	/* xon/xoff character */
+	u8			x_char;	/* xon/xoff character */
 };
 
 static struct tty_driver *serial_driver;
@@ -178,7 +178,7 @@ static void receive_chars(struct serial_state *info)
 {
         int status;
 	int serdatr;
-	unsigned char ch, flag;
+	u8 ch, flag;
 	struct	async_icount *icount;
 	bool overrun = false;
 
-- 
GitLab


From 03e5af525750d83228f7177dbe9c9ae6ccd961e6 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:52 +0100
Subject: [PATCH 0976/4076] tty: bcm: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Scott Branden <scott.branden@broadcom.com>
Cc: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20231206073712.17776-8-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/bcm-vk/bcm_vk_tty.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/bcm-vk/bcm_vk_tty.c b/drivers/misc/bcm-vk/bcm_vk_tty.c
index 2bce835ca43ef..59bab76ff0a9d 100644
--- a/drivers/misc/bcm-vk/bcm_vk_tty.c
+++ b/drivers/misc/bcm-vk/bcm_vk_tty.c
@@ -64,9 +64,9 @@ static void bcm_vk_tty_wq_handler(struct work_struct *work)
 	struct bcm_vk_tty *vktty;
 	int card_status;
 	int count;
-	unsigned char c;
 	int i;
 	int wr;
+	u8 c;
 
 	card_status = vkread32(vk, BAR_0, BAR_CARD_STATUS);
 	if (BCM_VK_INTF_IS_DOWN(card_status))
@@ -192,7 +192,7 @@ static ssize_t bcm_vk_tty_write(struct tty_struct *tty, const u8 *buffer,
 	int index;
 	struct bcm_vk *vk;
 	struct bcm_vk_tty *vktty;
-	int i;
+	size_t i;
 
 	index = tty->index;
 	vk = dev_get_drvdata(tty->dev);
-- 
GitLab


From 359bbdc0cdfc8504c617f7a00af959a17277d4f4 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:53 +0100
Subject: [PATCH 0977/4076] tty: con3215: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Link: https://lore.kernel.org/r/20231206073712.17776-9-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/s390/char/con3215.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index 34bc343dcfcca..0b0324fe4aff3 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -79,8 +79,8 @@ struct raw3215_info {
 	struct ccw_device *cdev;      /* device for tty driver */
 	spinlock_t *lock;	      /* pointer to irq lock */
 	int flags;		      /* state flags */
-	char *buffer;		      /* pointer to output buffer */
-	char *inbuf;		      /* pointer to input buffer */
+	u8 *buffer;		      /* pointer to output buffer */
+	u8 *inbuf;		      /* pointer to input buffer */
 	int head;		      /* first free byte in output buffer */
 	int count;		      /* number of bytes in output buffer */
 	int written;		      /* number of bytes in write requests */
@@ -522,12 +522,14 @@ static unsigned int raw3215_make_room(struct raw3215_info *raw,
  *	string	without blocking.
  *	Return value is the number of bytes copied.
  */
-static unsigned int raw3215_addtext(const char *str, unsigned int length,
+static unsigned int raw3215_addtext(const u8 *str, size_t length,
 				    struct raw3215_info *raw, int opmode,
 				    unsigned int todrop)
 {
-	unsigned int c, ch, i, blanks, expanded_size = 0;
+	unsigned int i, blanks, expanded_size = 0;
 	unsigned int column = raw->line_pos;
+	size_t c;
+	u8 ch;
 
 	if (opmode == RAW3215_COUNT)
 		todrop = 0;
@@ -558,7 +560,7 @@ static unsigned int raw3215_addtext(const char *str, unsigned int length,
 		if (todrop && expanded_size < todrop)	/* Drop head data */
 			continue;
 		for (i = 0; i < blanks; i++) {
-			raw->buffer[raw->head] = (char)_ascebc[(int)ch];
+			raw->buffer[raw->head] = _ascebc[ch];
 			raw->head = (raw->head + 1) & (RAW3215_BUFFER_SIZE - 1);
 			raw->count++;
 		}
@@ -570,8 +572,8 @@ static unsigned int raw3215_addtext(const char *str, unsigned int length,
 /*
  * String write routine for 3215 devices
  */
-static void raw3215_write(struct raw3215_info *raw, const char *str,
-			  unsigned int length)
+static void raw3215_write(struct raw3215_info *raw, const u8 *str,
+			  size_t length)
 {
 	unsigned int count, avail;
 	unsigned long flags;
@@ -596,7 +598,7 @@ static void raw3215_write(struct raw3215_info *raw, const char *str,
 /*
  * Put character routine for 3215 devices
  */
-static void raw3215_putchar(struct raw3215_info *raw, unsigned char ch)
+static void raw3215_putchar(struct raw3215_info *raw, u8 ch)
 {
 	raw3215_write(raw, &ch, 1);
 }
@@ -823,12 +825,10 @@ static struct ccw_driver raw3215_ccw_driver = {
 	.int_class	= IRQIO_C15,
 };
 
-static void handle_write(struct raw3215_info *raw, const char *str, int count)
+static void handle_write(struct raw3215_info *raw, const u8 *str, size_t count)
 {
-	int i;
-
 	while (count > 0) {
-		i = min_t(int, count, RAW3215_BUFFER_SIZE - 1);
+		size_t i = min_t(size_t, count, RAW3215_BUFFER_SIZE - 1);
 		raw3215_write(raw, str, i);
 		count -= i;
 		str += i;
-- 
GitLab


From e17934c1bcc1aeb6289309f300e2541d688ee0d6 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:54 +0100
Subject: [PATCH 0978/4076] tty: con3270: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Link: https://lore.kernel.org/r/20231206073712.17776-10-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/s390/char/con3270.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index 363315fa1666d..251d2a1c3eef9 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -54,7 +54,7 @@ struct tty3270_attribute {
 };
 
 struct tty3270_cell {
-	unsigned char character;
+	u8 character;
 	struct tty3270_attribute attributes;
 };
 
@@ -123,7 +123,7 @@ struct tty3270 {
 
 	/* Character array for put_char/flush_chars. */
 	unsigned int char_count;
-	char char_buf[TTY3270_CHAR_BUF_SIZE];
+	u8 char_buf[TTY3270_CHAR_BUF_SIZE];
 };
 
 /* tty3270->update_flags. See tty3270_update for details. */
@@ -1255,7 +1255,7 @@ static unsigned int tty3270_write_room(struct tty_struct *tty)
  * Insert character into the screen at the current position with the
  * current color and highlight. This function does NOT do cursor movement.
  */
-static void tty3270_put_character(struct tty3270 *tp, char ch)
+static void tty3270_put_character(struct tty3270 *tp, u8 ch)
 {
 	struct tty3270_line *line;
 	struct tty3270_cell *cell;
@@ -1561,7 +1561,7 @@ static void tty3270_goto_xy(struct tty3270 *tp, int cx, int cy)
  *  Pn is a numeric parameter, a string of zero or more decimal digits.
  *  Ps is a selective parameter.
  */
-static void tty3270_escape_sequence(struct tty3270 *tp, char ch)
+static void tty3270_escape_sequence(struct tty3270 *tp, u8 ch)
 {
 	enum { ES_NORMAL, ES_ESC, ES_SQUARE, ES_PAREN, ES_GETPARS };
 
@@ -1726,7 +1726,7 @@ static void tty3270_escape_sequence(struct tty3270 *tp, char ch)
  * String write routine for 3270 ttys
  */
 static void tty3270_do_write(struct tty3270 *tp, struct tty_struct *tty,
-			     const unsigned char *buf, int count)
+			     const u8 *buf, size_t count)
 {
 	int i_msg, i;
 
@@ -2052,7 +2052,7 @@ con3270_write(struct console *co, const char *str, unsigned int count)
 {
 	struct tty3270 *tp = co->data;
 	unsigned long flags;
-	char c;
+	u8 c;
 
 	spin_lock_irqsave(&tp->view.lock, flags);
 	while (count--) {
-- 
GitLab


From 0d08abb98331a56c4ec84539be7c401321a2eb0c Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:55 +0100
Subject: [PATCH 0979/4076] tty: ehv_bytechan: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20231206073712.17776-11-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/ehv_bytechan.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/tty/ehv_bytechan.c b/drivers/tty/ehv_bytechan.c
index cc9f4338da601..69508d7a4135f 100644
--- a/drivers/tty/ehv_bytechan.c
+++ b/drivers/tty/ehv_bytechan.c
@@ -49,7 +49,7 @@ struct ehv_bc_data {
 	unsigned int tx_irq;
 
 	spinlock_t lock;	/* lock for transmit buffer */
-	unsigned char buf[BUF_SIZE];	/* transmit circular buffer */
+	u8 buf[BUF_SIZE];	/* transmit circular buffer */
 	unsigned int head;	/* circular buffer head */
 	unsigned int tail;	/* circular buffer tail */
 
@@ -138,9 +138,9 @@ static int find_console_handle(void)
 
 static unsigned int local_ev_byte_channel_send(unsigned int handle,
 					       unsigned int *count,
-					       const char *p)
+					       const u8 *p)
 {
-	char buffer[EV_BYTE_CHANNEL_MAX_BYTES];
+	u8 buffer[EV_BYTE_CHANNEL_MAX_BYTES];
 	unsigned int c = *count;
 
 	/*
@@ -166,7 +166,7 @@ static unsigned int local_ev_byte_channel_send(unsigned int handle,
  * has been sent, or if some error has occurred.
  *
  */
-static void byte_channel_spin_send(const char data)
+static void byte_channel_spin_send(const u8 data)
 {
 	int ret, count;
 
@@ -474,8 +474,7 @@ static ssize_t ehv_bc_tty_write(struct tty_struct *ttys, const u8 *s,
 {
 	struct ehv_bc_data *bc = ttys->driver_data;
 	unsigned long flags;
-	unsigned int len;
-	unsigned int written = 0;
+	size_t len, written = 0;
 
 	while (1) {
 		spin_lock_irqsave(&bc->lock, flags);
-- 
GitLab


From f3fb7367af89457a8818bc93e35a274ccb5b9e44 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:56 +0100
Subject: [PATCH 0980/4076] tty: goldfish: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-12-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/goldfish.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c
index 7ad7fa66cb273..d27979eabfdfb 100644
--- a/drivers/tty/goldfish.c
+++ b/drivers/tty/goldfish.c
@@ -50,10 +50,8 @@ static u32 goldfish_tty_line_count = 8;
 static u32 goldfish_tty_current_line_count;
 static struct goldfish_tty *goldfish_ttys;
 
-static void do_rw_io(struct goldfish_tty *qtty,
-		     unsigned long address,
-		     unsigned int count,
-		     bool is_write)
+static void do_rw_io(struct goldfish_tty *qtty, unsigned long address,
+		     size_t count, bool is_write)
 {
 	unsigned long irq_flags;
 	void __iomem *base = qtty->base;
@@ -73,10 +71,8 @@ static void do_rw_io(struct goldfish_tty *qtty,
 	spin_unlock_irqrestore(&qtty->lock, irq_flags);
 }
 
-static void goldfish_tty_rw(struct goldfish_tty *qtty,
-			    unsigned long addr,
-			    unsigned int count,
-			    bool is_write)
+static void goldfish_tty_rw(struct goldfish_tty *qtty, unsigned long addr,
+			    size_t count, bool is_write)
 {
 	dma_addr_t dma_handle;
 	enum dma_data_direction dma_dir;
@@ -125,7 +121,7 @@ static void goldfish_tty_rw(struct goldfish_tty *qtty,
 	}
 }
 
-static void goldfish_tty_do_write(int line, const u8 *buf, unsigned int count)
+static void goldfish_tty_do_write(int line, const u8 *buf, size_t count)
 {
 	struct goldfish_tty *qtty = &goldfish_ttys[line];
 
@@ -136,7 +132,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 {
 	struct goldfish_tty *qtty = dev_id;
 	void __iomem *base = qtty->base;
-	unsigned char *buf;
+	u8 *buf;
 	u32 count;
 
 	count = gf_ioread32(base + GOLDFISH_TTY_REG_BYTES_READY);
-- 
GitLab


From f32fcbedbe9290565e4eac3fd7c4c451d5478787 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:57 +0100
Subject: [PATCH 0981/4076] tty: hvc: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Amit Shah <amit@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: virtualization@lists.linux.dev
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20231206073712.17776-13-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/powerpc/include/asm/hvconsole.h       |  4 ++--
 arch/powerpc/include/asm/hvsi.h            | 18 ++++++++--------
 arch/powerpc/include/asm/opal.h            |  8 +++++---
 arch/powerpc/platforms/powernv/opal.c      | 14 +++++++------
 arch/powerpc/platforms/pseries/hvconsole.c |  4 ++--
 drivers/char/virtio_console.c              | 10 ++++-----
 drivers/tty/hvc/hvc_console.h              |  4 ++--
 drivers/tty/hvc/hvc_dcc.c                  | 24 +++++++++++-----------
 drivers/tty/hvc/hvc_iucv.c                 | 18 ++++++++--------
 drivers/tty/hvc/hvc_opal.c                 |  5 +++--
 drivers/tty/hvc/hvc_riscv_sbi.c            |  9 ++++----
 drivers/tty/hvc/hvc_rtas.c                 | 11 +++++-----
 drivers/tty/hvc/hvc_udbg.c                 |  9 ++++----
 drivers/tty/hvc/hvc_vio.c                  | 18 ++++++++--------
 drivers/tty/hvc/hvc_xen.c                  | 23 +++++++++++----------
 drivers/tty/hvc/hvsi_lib.c                 | 20 ++++++++++--------
 16 files changed, 107 insertions(+), 92 deletions(-)

diff --git a/arch/powerpc/include/asm/hvconsole.h b/arch/powerpc/include/asm/hvconsole.h
index ccb2034506f0f..d841a97010a0f 100644
--- a/arch/powerpc/include/asm/hvconsole.h
+++ b/arch/powerpc/include/asm/hvconsole.h
@@ -21,8 +21,8 @@
  * Vio firmware always attempts to fetch MAX_VIO_GET_CHARS chars.  The 'count'
  * parm is included to conform to put_chars() function pointer template
  */
-extern int hvc_get_chars(uint32_t vtermno, char *buf, int count);
-extern int hvc_put_chars(uint32_t vtermno, const char *buf, int count);
+extern ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count);
+extern ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count);
 
 /* Provided by HVC VIO */
 void hvc_vio_init_early(void);
diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h
index 464a7519ed644..9058edcb632b4 100644
--- a/arch/powerpc/include/asm/hvsi.h
+++ b/arch/powerpc/include/asm/hvsi.h
@@ -64,7 +64,7 @@ struct hvsi_priv {
 	unsigned int	inbuf_len;	/* data in input buffer */
 	unsigned char	inbuf[HVSI_INBUF_SIZE];
 	unsigned int	inbuf_cur;	/* Cursor in input buffer */
-	unsigned int	inbuf_pktlen;	/* packet length from cursor */
+	size_t		inbuf_pktlen;	/* packet length from cursor */
 	atomic_t	seqno;		/* packet sequence number */
 	unsigned int	opened:1;	/* driver opened */
 	unsigned int	established:1;	/* protocol established */
@@ -72,24 +72,26 @@ struct hvsi_priv {
 	unsigned int	mctrl_update:1;	/* modem control updated */
 	unsigned short	mctrl;		/* modem control */
 	struct tty_struct *tty;		/* tty structure */
-	int (*get_chars)(uint32_t termno, char *buf, int count);
-	int (*put_chars)(uint32_t termno, const char *buf, int count);
+	ssize_t (*get_chars)(uint32_t termno, u8 *buf, size_t count);
+	ssize_t (*put_chars)(uint32_t termno, const u8 *buf, size_t count);
 	uint32_t	termno;
 };
 
 /* hvsi lib functions */
 struct hvc_struct;
 extern void hvsilib_init(struct hvsi_priv *pv,
-			 int (*get_chars)(uint32_t termno, char *buf, int count),
-			 int (*put_chars)(uint32_t termno, const char *buf,
-					  int count),
+			 ssize_t (*get_chars)(uint32_t termno, u8 *buf,
+					      size_t count),
+			 ssize_t (*put_chars)(uint32_t termno, const u8 *buf,
+					      size_t count),
 			 int termno, int is_console);
 extern int hvsilib_open(struct hvsi_priv *pv, struct hvc_struct *hp);
 extern void hvsilib_close(struct hvsi_priv *pv, struct hvc_struct *hp);
 extern int hvsilib_read_mctrl(struct hvsi_priv *pv);
 extern int hvsilib_write_mctrl(struct hvsi_priv *pv, int dtr);
 extern void hvsilib_establish(struct hvsi_priv *pv);
-extern int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count);
-extern int hvsilib_put_chars(struct hvsi_priv *pv, const char *buf, int count);
+extern ssize_t hvsilib_get_chars(struct hvsi_priv *pv, u8 *buf, size_t count);
+extern ssize_t hvsilib_put_chars(struct hvsi_priv *pv, const u8 *buf,
+				 size_t count);
 
 #endif /* _HVSI_H */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index b66b0c615f4f1..af304e6cb486c 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -313,9 +313,11 @@ extern int early_init_dt_scan_recoverable_ranges(unsigned long node,
 				 const char *uname, int depth, void *data);
 void __init opal_configure_cores(void);
 
-extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
-extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
-extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len);
+extern ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count);
+extern ssize_t opal_put_chars(uint32_t vtermno, const u8 *buf,
+			      size_t total_len);
+extern ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *buf,
+				     size_t total_len);
 extern int opal_flush_chars(uint32_t vtermno, bool wait);
 extern int opal_flush_console(uint32_t vtermno);
 
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index cdf3838f08d37..45dd77e3ccf6f 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -424,7 +424,7 @@ static int __init opal_message_init(struct device_node *opal_node)
 	return 0;
 }
 
-int opal_get_chars(uint32_t vtermno, char *buf, int count)
+ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	s64 rc;
 	__be64 evt, len;
@@ -441,10 +441,11 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count)
 	return 0;
 }
 
-static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, bool atomic)
+static ssize_t __opal_put_chars(uint32_t vtermno, const u8 *data,
+				size_t total_len, bool atomic)
 {
 	unsigned long flags = 0 /* shut up gcc */;
-	int written;
+	ssize_t written;
 	__be64 olen;
 	s64 rc;
 
@@ -484,7 +485,7 @@ static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, b
 		if (atomic) {
 			/* Should not happen */
 			pr_warn("atomic console write returned partial "
-				"len=%d written=%d\n", total_len, written);
+				"len=%zu written=%zd\n", total_len, written);
 		}
 		if (!written)
 			written = -EAGAIN;
@@ -497,7 +498,7 @@ out:
 	return written;
 }
 
-int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
+ssize_t opal_put_chars(uint32_t vtermno, const u8 *data, size_t total_len)
 {
 	return __opal_put_chars(vtermno, data, total_len, false);
 }
@@ -508,7 +509,8 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
  * true at the moment because console space can race with OPAL's console
  * writes.
  */
-int opal_put_chars_atomic(uint32_t vtermno, const char *data, int total_len)
+ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *data,
+			      size_t total_len)
 {
 	return __opal_put_chars(vtermno, data, total_len, true);
 }
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index 1ac52963e08b4..8803c947998e1 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -25,7 +25,7 @@
  *	firmware.
  * @count: not used?
  */
-int hvc_get_chars(uint32_t vtermno, char *buf, int count)
+ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	long ret;
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(hvc_get_chars);
  *	firmware. Must be at least 16 bytes, even if count is less than 16.
  * @count: Send this number of characters.
  */
-int hvc_put_chars(uint32_t vtermno, const char *buf, int count)
+ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count)
 {
 	unsigned long *lbuf = (unsigned long *) buf;
 	long ret;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 8abe599c1c07e..035f89f1a251e 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -650,7 +650,7 @@ done:
  * Give out the data that's requested from the buffer that we have
  * queued up.
  */
-static ssize_t fill_readbuf(struct port *port, char __user *out_buf,
+static ssize_t fill_readbuf(struct port *port, u8 __user *out_buf,
 			    size_t out_count, bool to_user)
 {
 	struct port_buffer *buf;
@@ -669,7 +669,7 @@ static ssize_t fill_readbuf(struct port *port, char __user *out_buf,
 		if (ret)
 			return -EFAULT;
 	} else {
-		memcpy((__force char *)out_buf, buf->buf + buf->offset,
+		memcpy((__force u8 *)out_buf, buf->buf + buf->offset,
 		       out_count);
 	}
 
@@ -1104,7 +1104,7 @@ static const struct file_operations port_fops = {
  * it to finish: inefficient in theory, but in practice
  * implementations will do it immediately.
  */
-static int put_chars(u32 vtermno, const char *buf, int count)
+static ssize_t put_chars(u32 vtermno, const u8 *buf, size_t count)
 {
 	struct port *port;
 	struct scatterlist sg[1];
@@ -1132,7 +1132,7 @@ static int put_chars(u32 vtermno, const char *buf, int count)
  * We call out to fill_readbuf that gets us the required data from the
  * buffers that are queued up.
  */
-static int get_chars(u32 vtermno, char *buf, int count)
+static ssize_t get_chars(u32 vtermno, u8 *buf, size_t count)
 {
 	struct port *port;
 
@@ -1143,7 +1143,7 @@ static int get_chars(u32 vtermno, char *buf, int count)
 	/* If we don't have an input queue yet, we can't get input. */
 	BUG_ON(!port->in_vq);
 
-	return fill_readbuf(port, (__force char __user *)buf, count, false);
+	return fill_readbuf(port, (__force u8 __user *)buf, count, false);
 }
 
 static void resize_console(struct port *port)
diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h
index 4062f8ad84df3..cf4c1af08a7c9 100644
--- a/drivers/tty/hvc/hvc_console.h
+++ b/drivers/tty/hvc/hvc_console.h
@@ -52,8 +52,8 @@ struct hvc_struct {
 
 /* implemented by a low level driver */
 struct hv_ops {
-	int (*get_chars)(uint32_t vtermno, char *buf, int count);
-	int (*put_chars)(uint32_t vtermno, const char *buf, int count);
+	ssize_t (*get_chars)(uint32_t vtermno, u8 *buf, size_t count);
+	ssize_t (*put_chars)(uint32_t vtermno, const u8 *buf, size_t count);
 	int (*flush)(uint32_t vtermno, bool wait);
 
 	/* Callbacks for notification. Called in open, close and hangup */
diff --git a/drivers/tty/hvc/hvc_dcc.c b/drivers/tty/hvc/hvc_dcc.c
index 136381bec7cd7..dfc5c9c38f074 100644
--- a/drivers/tty/hvc/hvc_dcc.c
+++ b/drivers/tty/hvc/hvc_dcc.c
@@ -26,10 +26,10 @@
 /* Lock to serialize access to DCC fifo */
 static DEFINE_SPINLOCK(dcc_lock);
 
-static DEFINE_KFIFO(inbuf, unsigned char, DCC_INBUF_SIZE);
-static DEFINE_KFIFO(outbuf, unsigned char, DCC_OUTBUF_SIZE);
+static DEFINE_KFIFO(inbuf, u8, DCC_INBUF_SIZE);
+static DEFINE_KFIFO(outbuf, u8, DCC_OUTBUF_SIZE);
 
-static void dcc_uart_console_putchar(struct uart_port *port, unsigned char ch)
+static void dcc_uart_console_putchar(struct uart_port *port, u8 ch)
 {
 	while (__dcc_getstatus() & DCC_STATUS_TX)
 		cpu_relax();
@@ -62,9 +62,9 @@ static int __init dcc_early_console_setup(struct earlycon_device *device,
 
 EARLYCON_DECLARE(dcc, dcc_early_console_setup);
 
-static int hvc_dcc_put_chars(uint32_t vt, const char *buf, int count)
+static ssize_t hvc_dcc_put_chars(uint32_t vt, const u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; i++) {
 		while (__dcc_getstatus() & DCC_STATUS_TX)
@@ -76,9 +76,9 @@ static int hvc_dcc_put_chars(uint32_t vt, const char *buf, int count)
 	return count;
 }
 
-static int hvc_dcc_get_chars(uint32_t vt, char *buf, int count)
+static ssize_t hvc_dcc_get_chars(uint32_t vt, u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; ++i)
 		if (__dcc_getstatus() & DCC_STATUS_RX)
@@ -157,8 +157,8 @@ static DECLARE_WORK(dcc_pwork, dcc_put_work);
  */
 static void dcc_get_work(struct work_struct *work)
 {
-	unsigned char ch;
 	unsigned long irqflags;
+	u8 ch;
 
 	/*
 	 * Read characters from DCC and put them into the input FIFO, as
@@ -180,10 +180,10 @@ static DECLARE_WORK(dcc_gwork, dcc_get_work);
  * Write characters directly to the DCC if we're on core 0 and the FIFO
  * is empty, or write them to the FIFO if we're not.
  */
-static int hvc_dcc0_put_chars(u32 vt, const char *buf, int count)
+static ssize_t hvc_dcc0_put_chars(u32 vt, const u8 *buf, size_t count)
 {
-	int len;
 	unsigned long irqflags;
+	ssize_t len;
 
 	if (!IS_ENABLED(CONFIG_HVC_DCC_SERIALIZE_SMP))
 		return hvc_dcc_put_chars(vt, buf, count);
@@ -219,10 +219,10 @@ static int hvc_dcc0_put_chars(u32 vt, const char *buf, int count)
  * Read characters directly from the DCC if we're on core 0 and the FIFO
  * is empty, or read them from the FIFO if we're not.
  */
-static int hvc_dcc0_get_chars(u32 vt, char *buf, int count)
+static ssize_t hvc_dcc0_get_chars(u32 vt, u8 *buf, size_t count)
 {
-	int len;
 	unsigned long irqflags;
+	ssize_t len;
 
 	if (!IS_ENABLED(CONFIG_HVC_DCC_SERIALIZE_SMP))
 		return hvc_dcc_get_chars(vt, buf, count);
diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c
index 543f35ddf523c..fdecc0d63731a 100644
--- a/drivers/tty/hvc/hvc_iucv.c
+++ b/drivers/tty/hvc/hvc_iucv.c
@@ -215,11 +215,11 @@ static void destroy_tty_buffer_list(struct list_head *list)
  * If the IUCV path has been severed, then -EPIPE is returned to cause a
  * hang up (that is issued by the HVC layer).
  */
-static int hvc_iucv_write(struct hvc_iucv_private *priv,
-			  char *buf, int count, int *has_more_data)
+static ssize_t hvc_iucv_write(struct hvc_iucv_private *priv,
+			      u8 *buf, size_t count, int *has_more_data)
 {
 	struct iucv_tty_buffer *rb;
-	int written;
+	ssize_t written;
 	int rc;
 
 	/* immediately return if there is no IUCV connection */
@@ -312,10 +312,10 @@ out_written:
  *		the routine locks the struct hvc_iucv_private->lock to call
  *		helper functions.
  */
-static int hvc_iucv_get_chars(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_iucv_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	struct hvc_iucv_private *priv = hvc_iucv_get_private(vtermno);
-	int written;
+	ssize_t written;
 	int has_more_data;
 
 	if (count <= 0)
@@ -352,8 +352,8 @@ static int hvc_iucv_get_chars(uint32_t vtermno, char *buf, int count)
  * If an existing IUCV communicaton path has been severed, -EPIPE is returned
  * (that can be passed to HVC layer to cause a tty hangup).
  */
-static int hvc_iucv_queue(struct hvc_iucv_private *priv, const char *buf,
-			  int count)
+static ssize_t hvc_iucv_queue(struct hvc_iucv_private *priv, const u8 *buf,
+			      size_t count)
 {
 	size_t len;
 
@@ -455,12 +455,12 @@ static void hvc_iucv_sndbuf_work(struct work_struct *work)
  * Locking:	The method gets called under an irqsave() spinlock; and
  *		locks struct hvc_iucv_private->lock.
  */
-static int hvc_iucv_put_chars(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvc_iucv_put_chars(uint32_t vtermno, const u8 *buf, size_t count)
 {
 	struct hvc_iucv_private *priv = hvc_iucv_get_private(vtermno);
 	int queued;
 
-	if (count <= 0)
+	if (!count)
 		return 0;
 
 	if (!priv)
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 2cdf66e395cc1..095c33ad10f83 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -58,7 +58,7 @@ static const struct hv_ops hvc_opal_raw_ops = {
 	.notifier_hangup = notifier_hangup_irq,
 };
 
-static int hvc_opal_hvsi_get_chars(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_opal_hvsi_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	struct hvc_opal_priv *pv = hvc_opal_privs[vtermno];
 
@@ -68,7 +68,8 @@ static int hvc_opal_hvsi_get_chars(uint32_t vtermno, char *buf, int count)
 	return hvsilib_get_chars(&pv->hvsi, buf, count);
 }
 
-static int hvc_opal_hvsi_put_chars(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvc_opal_hvsi_put_chars(uint32_t vtermno, const u8 *buf,
+				       size_t count)
 {
 	struct hvc_opal_priv *pv = hvc_opal_privs[vtermno];
 
diff --git a/drivers/tty/hvc/hvc_riscv_sbi.c b/drivers/tty/hvc/hvc_riscv_sbi.c
index 31f53fa77e4af..a72591279f865 100644
--- a/drivers/tty/hvc/hvc_riscv_sbi.c
+++ b/drivers/tty/hvc/hvc_riscv_sbi.c
@@ -15,9 +15,9 @@
 
 #include "hvc_console.h"
 
-static int hvc_sbi_tty_put(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvc_sbi_tty_put(uint32_t vtermno, const u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; i++)
 		sbi_console_putchar(buf[i]);
@@ -25,9 +25,10 @@ static int hvc_sbi_tty_put(uint32_t vtermno, const char *buf, int count)
 	return i;
 }
 
-static int hvc_sbi_tty_get(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_sbi_tty_get(uint32_t vtermno, u8 *buf, size_t count)
 {
-	int i, c;
+	size_t i;
+	int c;
 
 	for (i = 0; i < count; i++) {
 		c = sbi_console_getchar();
diff --git a/drivers/tty/hvc/hvc_rtas.c b/drivers/tty/hvc/hvc_rtas.c
index 184d325abeeda..a0b90275b37f6 100644
--- a/drivers/tty/hvc/hvc_rtas.c
+++ b/drivers/tty/hvc/hvc_rtas.c
@@ -31,10 +31,10 @@ static struct hvc_struct *hvc_rtas_dev;
 static int rtascons_put_char_token = RTAS_UNKNOWN_SERVICE;
 static int rtascons_get_char_token = RTAS_UNKNOWN_SERVICE;
 
-static inline int hvc_rtas_write_console(uint32_t vtermno, const char *buf,
-		int count)
+static ssize_t hvc_rtas_write_console(uint32_t vtermno, const u8 *buf,
+				      size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; i++) {
 		if (rtas_call(rtascons_put_char_token, 1, 1, NULL, buf[i]))
@@ -44,9 +44,10 @@ static inline int hvc_rtas_write_console(uint32_t vtermno, const char *buf,
 	return i;
 }
 
-static int hvc_rtas_read_console(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_rtas_read_console(uint32_t vtermno, u8 *buf, size_t count)
 {
-	int i, c;
+	size_t i;
+	int c;
 
 	for (i = 0; i < count; i++) {
 		if (rtas_call(rtascons_get_char_token, 0, 2, &c))
diff --git a/drivers/tty/hvc/hvc_udbg.c b/drivers/tty/hvc/hvc_udbg.c
index ff0dcc56413c4..fdc2699b78dc4 100644
--- a/drivers/tty/hvc/hvc_udbg.c
+++ b/drivers/tty/hvc/hvc_udbg.c
@@ -19,9 +19,9 @@
 
 static struct hvc_struct *hvc_udbg_dev;
 
-static int hvc_udbg_put(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvc_udbg_put(uint32_t vtermno, const u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count && udbg_putc; i++)
 		udbg_putc(buf[i]);
@@ -29,9 +29,10 @@ static int hvc_udbg_put(uint32_t vtermno, const char *buf, int count)
 	return i;
 }
 
-static int hvc_udbg_get(uint32_t vtermno, char *buf, int count)
+static ssize_t hvc_udbg_get(uint32_t vtermno, u8 *buf, size_t count)
 {
-	int i, c;
+	size_t i;
+	int c;
 
 	if (!udbg_getc_poll)
 		return 0;
diff --git a/drivers/tty/hvc/hvc_vio.c b/drivers/tty/hvc/hvc_vio.c
index 736b230f5ec04..47930601a26a8 100644
--- a/drivers/tty/hvc/hvc_vio.c
+++ b/drivers/tty/hvc/hvc_vio.c
@@ -58,20 +58,20 @@ struct hvterm_priv {
 	hv_protocol_t		proto;	/* Raw data or HVSI packets */
 	struct hvsi_priv	hvsi;	/* HVSI specific data */
 	spinlock_t		buf_lock;
-	char			buf[SIZE_VIO_GET_CHARS];
-	int			left;
-	int			offset;
+	u8			buf[SIZE_VIO_GET_CHARS];
+	size_t			left;
+	size_t			offset;
 };
 static struct hvterm_priv *hvterm_privs[MAX_NR_HVC_CONSOLES];
 /* For early boot console */
 static struct hvterm_priv hvterm_priv0;
 
-static int hvterm_raw_get_chars(uint32_t vtermno, char *buf, int count)
+static ssize_t hvterm_raw_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
 	unsigned long i;
 	unsigned long flags;
-	int got;
+	size_t got;
 
 	if (WARN_ON(!pv))
 		return 0;
@@ -115,7 +115,8 @@ static int hvterm_raw_get_chars(uint32_t vtermno, char *buf, int count)
  *       you are sending fewer chars.
  * @count: number of chars to send.
  */
-static int hvterm_raw_put_chars(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvterm_raw_put_chars(uint32_t vtermno, const u8 *buf,
+				    size_t count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
 
@@ -133,7 +134,7 @@ static const struct hv_ops hvterm_raw_ops = {
 	.notifier_hangup = notifier_hangup_irq,
 };
 
-static int hvterm_hvsi_get_chars(uint32_t vtermno, char *buf, int count)
+static ssize_t hvterm_hvsi_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
 
@@ -143,7 +144,8 @@ static int hvterm_hvsi_get_chars(uint32_t vtermno, char *buf, int count)
 	return hvsilib_get_chars(&pv->hvsi, buf, count);
 }
 
-static int hvterm_hvsi_put_chars(uint32_t vtermno, const char *buf, int count)
+static ssize_t hvterm_hvsi_put_chars(uint32_t vtermno, const u8 *buf,
+				     size_t count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
 
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 34c01874f45be..0e497501f8e31 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -84,13 +84,13 @@ static inline void notify_daemon(struct xencons_info *cons)
 	notify_remote_via_evtchn(cons->evtchn);
 }
 
-static int __write_console(struct xencons_info *xencons,
-		const char *data, int len)
+static ssize_t __write_console(struct xencons_info *xencons,
+			       const u8 *data, size_t len)
 {
 	XENCONS_RING_IDX cons, prod;
 	struct xencons_interface *intf = xencons->intf;
-	int sent = 0;
 	unsigned long flags;
+	size_t sent = 0;
 
 	spin_lock_irqsave(&xencons->ring_lock, flags);
 	cons = intf->out_cons;
@@ -115,10 +115,11 @@ static int __write_console(struct xencons_info *xencons,
 	return sent;
 }
 
-static int domU_write_console(uint32_t vtermno, const char *data, int len)
+static ssize_t domU_write_console(uint32_t vtermno, const u8 *data, size_t len)
 {
-	int ret = len;
 	struct xencons_info *cons = vtermno_to_xencons(vtermno);
+	size_t ret = len;
+
 	if (cons == NULL)
 		return -EINVAL;
 
@@ -129,7 +130,7 @@ static int domU_write_console(uint32_t vtermno, const char *data, int len)
 	 * kernel is crippled.
 	 */
 	while (len) {
-		int sent = __write_console(cons, data, len);
+		ssize_t sent = __write_console(cons, data, len);
 
 		if (sent < 0)
 			return sent;
@@ -144,14 +145,14 @@ static int domU_write_console(uint32_t vtermno, const char *data, int len)
 	return ret;
 }
 
-static int domU_read_console(uint32_t vtermno, char *buf, int len)
+static ssize_t domU_read_console(uint32_t vtermno, u8 *buf, size_t len)
 {
 	struct xencons_interface *intf;
 	XENCONS_RING_IDX cons, prod;
-	int recv = 0;
 	struct xencons_info *xencons = vtermno_to_xencons(vtermno);
 	unsigned int eoiflag = 0;
 	unsigned long flags;
+	size_t recv = 0;
 
 	if (xencons == NULL)
 		return -EINVAL;
@@ -209,7 +210,7 @@ static const struct hv_ops domU_hvc_ops = {
 	.notifier_hangup = notifier_hangup_irq,
 };
 
-static int dom0_read_console(uint32_t vtermno, char *buf, int len)
+static ssize_t dom0_read_console(uint32_t vtermno, u8 *buf, size_t len)
 {
 	return HYPERVISOR_console_io(CONSOLEIO_read, len, buf);
 }
@@ -218,9 +219,9 @@ static int dom0_read_console(uint32_t vtermno, char *buf, int len)
  * Either for a dom0 to write to the system console, or a domU with a
  * debug version of Xen
  */
-static int dom0_write_console(uint32_t vtermno, const char *str, int len)
+static ssize_t dom0_write_console(uint32_t vtermno, const u8 *str, size_t len)
 {
-	int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (char *)str);
+	int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (u8 *)str);
 	if (rc < 0)
 		return rc;
 
diff --git a/drivers/tty/hvc/hvsi_lib.c b/drivers/tty/hvc/hvsi_lib.c
index 09289c8154aec..22e1bc4d8a668 100644
--- a/drivers/tty/hvc/hvsi_lib.c
+++ b/drivers/tty/hvc/hvsi_lib.c
@@ -12,7 +12,7 @@ static int hvsi_send_packet(struct hvsi_priv *pv, struct hvsi_header *packet)
 	packet->seqno = cpu_to_be16(atomic_inc_return(&pv->seqno));
 
 	/* Assumes that always succeeds, works in practice */
-	return pv->put_chars(pv->termno, (char *)packet, packet->len);
+	return pv->put_chars(pv->termno, (u8 *)packet, packet->len);
 }
 
 static void hvsi_start_handshake(struct hvsi_priv *pv)
@@ -178,9 +178,10 @@ static int hvsi_get_packet(struct hvsi_priv *pv)
 	return 0;
 }
 
-int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count)
+ssize_t hvsilib_get_chars(struct hvsi_priv *pv, u8 *buf, size_t count)
 {
-	unsigned int tries, read = 0;
+	unsigned int tries;
+	size_t read = 0;
 
 	if (WARN_ON(!pv))
 		return -ENXIO;
@@ -199,7 +200,7 @@ int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count)
 	for (tries = 1; count && tries < 2; tries++) {
 		/* Consume existing data packet */
 		if (pv->inbuf_pktlen) {
-			unsigned int l = min(count, (int)pv->inbuf_pktlen);
+			size_t l = min(count, pv->inbuf_pktlen);
 			memcpy(&buf[read], &pv->inbuf[pv->inbuf_cur], l);
 			pv->inbuf_cur += l;
 			pv->inbuf_pktlen -= l;
@@ -228,10 +229,11 @@ int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count)
 	return read;
 }
 
-int hvsilib_put_chars(struct hvsi_priv *pv, const char *buf, int count)
+ssize_t hvsilib_put_chars(struct hvsi_priv *pv, const u8 *buf, size_t count)
 {
 	struct hvsi_data dp;
-	int rc, adjcount = min(count, HVSI_MAX_OUTGOING_DATA);
+	size_t adjcount = min_t(size_t, count, HVSI_MAX_OUTGOING_DATA);
+	int rc;
 
 	if (WARN_ON(!pv))
 		return -ENODEV;
@@ -411,9 +413,9 @@ void hvsilib_close(struct hvsi_priv *pv, struct hvc_struct *hp)
 }
 
 void hvsilib_init(struct hvsi_priv *pv,
-		  int (*get_chars)(uint32_t termno, char *buf, int count),
-		  int (*put_chars)(uint32_t termno, const char *buf,
-				   int count),
+		  ssize_t (*get_chars)(uint32_t termno, u8 *buf, size_t count),
+		  ssize_t (*put_chars)(uint32_t termno, const u8 *buf,
+				       size_t count),
 		  int termno, int is_console)
 {
 	memset(pv, 0, sizeof(*pv));
-- 
GitLab


From 2f982313279baa066f03f4816f3fa3521a4d41cb Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:58 +0100
Subject: [PATCH 0982/4076] tty: ipoctal: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Cc: Jens Taprogge <jens.taprogge@taprogge.org>
Cc: industrypack-devel@lists.sourceforge.net
Link: https://lore.kernel.org/r/20231206073712.17776-14-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/ipack/devices/ipoctal.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c
index da308be6c4877..ba2e9e52d72bf 100644
--- a/drivers/ipack/devices/ipoctal.c
+++ b/drivers/ipack/devices/ipoctal.c
@@ -158,9 +158,7 @@ static int ipoctal_get_icount(struct tty_struct *tty,
 static void ipoctal_irq_rx(struct ipoctal_channel *channel, u8 sr)
 {
 	struct tty_port *port = &channel->tty_port;
-	unsigned char value;
-	unsigned char flag;
-	u8 isr;
+	u8 isr, value, flag;
 
 	do {
 		value = ioread8(&channel->regs->r.rhr);
@@ -202,8 +200,8 @@ static void ipoctal_irq_rx(struct ipoctal_channel *channel, u8 sr)
 
 static void ipoctal_irq_tx(struct ipoctal_channel *channel)
 {
-	unsigned char value;
 	unsigned int *pointer_write = &channel->pointer_write;
+	u8 value;
 
 	if (channel->nb_bytes == 0)
 		return;
@@ -436,11 +434,11 @@ err_put_driver:
 	return res;
 }
 
-static inline int ipoctal_copy_write_buffer(struct ipoctal_channel *channel,
-					    const u8 *buf, int count)
+static inline size_t ipoctal_copy_write_buffer(struct ipoctal_channel *channel,
+					       const u8 *buf, size_t count)
 {
 	unsigned long flags;
-	int i;
+	size_t i;
 	unsigned int *pointer_read = &channel->pointer_read;
 
 	/* Copy the bytes from the user buffer to the internal one */
@@ -462,7 +460,7 @@ static ssize_t ipoctal_write_tty(struct tty_struct *tty, const u8 *buf,
 				 size_t count)
 {
 	struct ipoctal_channel *channel = tty->driver_data;
-	unsigned int char_copied;
+	size_t char_copied;
 
 	char_copied = ipoctal_copy_write_buffer(channel, buf, count);
 
-- 
GitLab


From b7a43d0c878169037c7a08985b1d444f1e4b0629 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:59 +0100
Subject: [PATCH 0983/4076] tty: m68k: nfcon: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: linux-m68k@lists.linux-m68k.org
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20231206073712.17776-15-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/m68k/emu/nfcon.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/m68k/emu/nfcon.c b/arch/m68k/emu/nfcon.c
index 3a74d493eb3e6..17b2987c2bf54 100644
--- a/arch/m68k/emu/nfcon.c
+++ b/arch/m68k/emu/nfcon.c
@@ -23,9 +23,9 @@ static int stderr_id;
 static struct tty_port nfcon_tty_port;
 static struct tty_driver *nfcon_tty_driver;
 
-static void nfputs(const char *str, unsigned int count)
+static void nfputs(const u8 *str, size_t count)
 {
-	char buf[68];
+	u8 buf[68];
 	unsigned long phys = virt_to_phys(buf);
 
 	buf[64] = 0;
-- 
GitLab


From ce7cbd9a6c81b5fc899bbc730072a1bddeae5d0d Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:00 +0100
Subject: [PATCH 0984/4076] tty: mips_ejtag_fdc: use u8 for character pointers

mips_ejtag_fdc_encode() and mips_ejtag_fdc_put_chan() declare arrays of
pointers to characters. Switch their types from char to u8 to conform
to the current tty layer types for characters.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-16-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/mips_ejtag_fdc.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c
index 369ec71c24ef0..aac80b69a069c 100644
--- a/drivers/tty/mips_ejtag_fdc.c
+++ b/drivers/tty/mips_ejtag_fdc.c
@@ -213,16 +213,16 @@ struct fdc_word {
  */
 
 /* ranges >= 1 && sizes[0] >= 1 */
-static struct fdc_word mips_ejtag_fdc_encode(const char **ptrs,
+static struct fdc_word mips_ejtag_fdc_encode(const u8 **ptrs,
 					     unsigned int *sizes,
 					     unsigned int ranges)
 {
 	struct fdc_word word = { 0, 0 };
-	const char **ptrs_end = ptrs + ranges;
+	const u8 **ptrs_end = ptrs + ranges;
 
 	for (; ptrs < ptrs_end; ++ptrs) {
-		const char *ptr = *(ptrs++);
-		const char *end = ptr + *(sizes++);
+		const u8 *ptr = *(ptrs++);
+		const u8 *end = ptr + *(sizes++);
 
 		for (; ptr < end; ++ptr) {
 			word.word |= (u8)*ptr << (8*word.bytes);
@@ -417,7 +417,7 @@ static unsigned int mips_ejtag_fdc_put_chan(struct mips_ejtag_fdc_tty *priv,
 {
 	struct mips_ejtag_fdc_tty_port *dport;
 	struct tty_struct *tty;
-	const char *ptrs[2];
+	const u8 *ptrs[2];
 	unsigned int sizes[2] = { 0 };
 	struct fdc_word word = { .bytes = 0 };
 	unsigned long flags;
-- 
GitLab


From 2573f7eac04dbcdd4f24957e3a3bc891ed2dc88f Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:01 +0100
Subject: [PATCH 0985/4076] tty: mmc: sdio: use u8 for flag

Switch character types to u8. To conform to characters in the rest of
the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: linux-mmc@vger.kernel.org
Link: https://lore.kernel.org/r/20231206073712.17776-17-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/mmc/core/sdio_uart.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c
index 370fadf1d6d1c..575ebbce378e0 100644
--- a/drivers/mmc/core/sdio_uart.c
+++ b/drivers/mmc/core/sdio_uart.c
@@ -354,12 +354,11 @@ static void sdio_uart_stop_rx(struct sdio_uart_port *port)
 
 static void sdio_uart_receive_chars(struct sdio_uart_port *port, u8 *status)
 {
-	unsigned int flag;
 	int max_count = 256;
 
 	do {
 		u8 ch = sdio_in(port, UART_RX);
-		flag = TTY_NORMAL;
+		u8 flag = TTY_NORMAL;
 		port->icount.rx++;
 
 		if (unlikely(*status & (UART_LSR_BI | UART_LSR_PE |
-- 
GitLab


From cb8566b9b3b18b0476f48c567275a2da4501cb2c Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:02 +0100
Subject: [PATCH 0986/4076] tty: moxa: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-18-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/moxa.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c
index bf3f87ba3a92c..ebaada8db9294 100644
--- a/drivers/tty/moxa.c
+++ b/drivers/tty/moxa.c
@@ -514,7 +514,7 @@ static void MoxaPortLineCtrl(struct moxa_port *, bool, bool);
 static void MoxaPortFlowCtrl(struct moxa_port *, int, int, int, int, int);
 static int MoxaPortLineStatus(struct moxa_port *);
 static void MoxaPortFlushData(struct moxa_port *, int);
-static int MoxaPortWriteData(struct tty_struct *, const unsigned char *, int);
+static ssize_t MoxaPortWriteData(struct tty_struct *, const u8 *, size_t);
 static int MoxaPortReadData(struct moxa_port *);
 static unsigned int MoxaPortTxQueue(struct moxa_port *);
 static int MoxaPortRxQueue(struct moxa_port *);
@@ -1933,10 +1933,10 @@ static void MoxaPortFlushData(struct moxa_port *port, int mode)
  *
  *      Function 20:    Write data.
  *      Syntax:
- *      int  MoxaPortWriteData(int port, unsigned char * buffer, int length);
+ *      ssize_t  MoxaPortWriteData(int port, u8 *buffer, size_t length);
  *           int port           : port number (0 - 127)
- *           unsigned char * buffer     : pointer to write data buffer.
- *           int length         : write data length
+ *           u8 *buffer         : pointer to write data buffer.
+ *           size_t length      : write data length
  *
  *           return:    0 - length      : real write data length
  *
@@ -2163,11 +2163,12 @@ static int MoxaPortLineStatus(struct moxa_port *port)
 	return val;
 }
 
-static int MoxaPortWriteData(struct tty_struct *tty, const u8 *buffer, int len)
+static ssize_t MoxaPortWriteData(struct tty_struct *tty, const u8 *buffer,
+				 size_t len)
 {
 	struct moxa_port *port = tty->driver_data;
 	void __iomem *baseAddr, *ofsAddr, *ofs;
-	unsigned int c, total;
+	size_t c, total;
 	u16 head, tail, tx_mask, spage, epage;
 	u16 pageno, pageofs, bufhead;
 
@@ -2224,8 +2225,8 @@ static int MoxaPortWriteData(struct tty_struct *tty, const u8 *buffer, int len)
 static int MoxaPortReadData(struct moxa_port *port)
 {
 	struct tty_struct *tty = port->port.tty;
-	unsigned char *dst;
 	void __iomem *baseAddr, *ofsAddr, *ofs;
+	u8 *dst;
 	unsigned int count, len, total;
 	u16 tail, rx_mask, spage, epage;
 	u16 pageno, pageofs, bufhead, head;
-- 
GitLab


From 59b943356b53312c02ec5cdb0b8dfc23e41c08fa Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:03 +0100
Subject: [PATCH 0987/4076] tty: mxser: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-19-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/mxser.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c
index 6ce7f259968fa..458bb1280ebf9 100644
--- a/drivers/tty/mxser.c
+++ b/drivers/tty/mxser.c
@@ -264,7 +264,7 @@ struct mxser_port {
 	u8 rx_low_water;
 	int type;		/* UART type */
 
-	unsigned char x_char;	/* xon/xoff character */
+	u8 x_char;		/* xon/xoff character */
 	u8 IER;			/* Interrupt Enable Register */
 	u8 MCR;			/* Modem control register */
 	u8 FCR;			/* FIFO control register */
@@ -905,7 +905,7 @@ static ssize_t mxser_write(struct tty_struct *tty, const u8 *buf, size_t count)
 {
 	struct mxser_port *info = tty->driver_data;
 	unsigned long flags;
-	int written;
+	size_t written;
 	bool is_empty;
 
 	spin_lock_irqsave(&info->slock, flags);
@@ -1521,7 +1521,7 @@ static u8 mxser_receive_chars_old(struct tty_struct *tty,
 			if (++ignored > 100)
 				break;
 		} else {
-			char flag = 0;
+			u8 flag = 0;
 			if (status & UART_LSR_BRK_ERROR_BITS) {
 				if (status & UART_LSR_BI) {
 					flag = TTY_BREAK;
@@ -1585,7 +1585,7 @@ static void mxser_transmit_chars(struct tty_struct *tty, struct mxser_port *port
 
 	count = port->xmit_fifo_size;
 	do {
-		unsigned char c;
+		u8 c;
 
 		if (!kfifo_get(&port->port.xmit_fifo, &c))
 			break;
-- 
GitLab


From eb7e45db2e0af233cb1dede0b16413e902068a03 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:04 +0100
Subject: [PATCH 0988/4076] tty: n_gsm: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-20-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_gsm.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index a3ab3946e4add..4036566febcba 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -124,8 +124,8 @@ struct gsm_msg {
 	u8 addr;		/* DLCI address + flags */
 	u8 ctrl;		/* Control byte + flags */
 	unsigned int len;	/* Length of data block (can be zero) */
-	unsigned char *data;	/* Points into buffer but not at the start */
-	unsigned char buffer[];
+	u8 *data;	/* Points into buffer but not at the start */
+	u8 buffer[];
 };
 
 enum gsm_dlci_state {
@@ -283,7 +283,7 @@ struct gsm_mux {
 	/* Bits for GSM mode decoding */
 
 	/* Framing Layer */
-	unsigned char *buf;
+	u8 *buf;
 	enum gsm_mux_state state;
 	unsigned int len;
 	unsigned int address;
@@ -2856,7 +2856,7 @@ invalid:
  *	Receive bytes in gsm mode 0
  */
 
-static void gsm0_receive(struct gsm_mux *gsm, unsigned char c)
+static void gsm0_receive(struct gsm_mux *gsm, u8 c)
 {
 	unsigned int len;
 
@@ -2947,7 +2947,7 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c)
  *	Receive bytes in mode 1 (Advanced option)
  */
 
-static void gsm1_receive(struct gsm_mux *gsm, unsigned char c)
+static void gsm1_receive(struct gsm_mux *gsm, u8 c)
 {
 	/* handle XON/XOFF */
 	if ((c & ISO_IEC_646_MASK) == XON) {
@@ -3541,7 +3541,7 @@ static void gsmld_receive_buf(struct tty_struct *tty, const u8 *cp,
 			      const u8 *fp, size_t count)
 {
 	struct gsm_mux *gsm = tty->disc_data;
-	char flags = TTY_NORMAL;
+	u8 flags = TTY_NORMAL;
 
 	if (debug & DBG_DATA)
 		gsm_hex_dump_bytes(__func__, cp, count);
@@ -3711,7 +3711,7 @@ static ssize_t gsmld_write(struct tty_struct *tty, struct file *file,
 {
 	struct gsm_mux *gsm = tty->disc_data;
 	unsigned long flags;
-	int space;
+	size_t space;
 	int ret;
 
 	if (!gsm)
@@ -3909,8 +3909,7 @@ static void gsm_mux_net_tx_timeout(struct net_device *net, unsigned int txqueue)
 	net->stats.tx_errors++;
 }
 
-static void gsm_mux_rx_netchar(struct gsm_dlci *dlci,
-				const unsigned char *in_buf, int size)
+static void gsm_mux_rx_netchar(struct gsm_dlci *dlci, const u8 *in_buf, int size)
 {
 	struct net_device *net = dlci->net;
 	struct sk_buff *skb;
-- 
GitLab


From 5655b16ea5cf00465b13942dd045cf38f1414d46 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:05 +0100
Subject: [PATCH 0989/4076] tty: n_hdlc: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Note u8 is already both passed in and expected on output.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-21-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_hdlc.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index a670419efe796..1615f074ab86c 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -109,8 +109,8 @@
 
 struct n_hdlc_buf {
 	struct list_head  list_item;
-	int		  count;
-	char		  buf[];
+	size_t		  count;
+	u8		  buf[];
 };
 
 struct n_hdlc_buf_list {
@@ -263,9 +263,9 @@ static int n_hdlc_tty_open(struct tty_struct *tty)
  */
 static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 {
-	register int actual;
 	unsigned long flags;
 	struct n_hdlc_buf *tbuf;
+	ssize_t actual;
 
 check_again:
 
@@ -281,7 +281,7 @@ check_again:
 
 	tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
 	while (tbuf) {
-		pr_debug("sending frame %p, count=%d\n", tbuf, tbuf->count);
+		pr_debug("sending frame %p, count=%zu\n", tbuf, tbuf->count);
 
 		/* Send the next block of data to device */
 		set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
@@ -521,9 +521,9 @@ static ssize_t n_hdlc_tty_write(struct tty_struct *tty, struct file *file,
 				const u8 *data, size_t count)
 {
 	struct n_hdlc *n_hdlc = tty->disc_data;
-	int error = 0;
 	DECLARE_WAITQUEUE(wait, current);
 	struct n_hdlc_buf *tbuf;
+	ssize_t error = 0;
 
 	pr_debug("%s() called count=%zd\n", __func__, count);
 
-- 
GitLab


From 5c99e2977f137cbedbd535a8884c5f3be32e738a Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:06 +0100
Subject: [PATCH 0990/4076] tty: nozomi: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-22-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/nozomi.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/nozomi.c b/drivers/tty/nozomi.c
index b247341bd12f5..e28a921c16374 100644
--- a/drivers/tty/nozomi.c
+++ b/drivers/tty/nozomi.c
@@ -783,11 +783,10 @@ static int receive_data(enum port_type index, struct nozomi *dc)
 			tty_insert_flip_char(&port->port, buf[0], TTY_NORMAL);
 			size = 0;
 		} else if (size < RECEIVE_BUF_MAX) {
-			size -= tty_insert_flip_string(&port->port,
-					(char *)buf, size);
+			size -= tty_insert_flip_string(&port->port, buf, size);
 		} else {
-			i = tty_insert_flip_string(&port->port,
-					(char *)buf, RECEIVE_BUF_MAX);
+			i = tty_insert_flip_string(&port->port, buf,
+						   RECEIVE_BUF_MAX);
 			size -= i;
 			offset += i;
 		}
@@ -1584,10 +1583,10 @@ static void ntty_hangup(struct tty_struct *tty)
 static ssize_t ntty_write(struct tty_struct *tty, const u8 *buffer,
 			  size_t count)
 {
-	int rval = -EINVAL;
 	struct nozomi *dc = get_dc_by_tty(tty);
 	struct port *port = tty->driver_data;
 	unsigned long flags;
+	size_t rval;
 
 	if (!dc || !port)
 		return -ENODEV;
-- 
GitLab


From f2470d2bc4327c2c1a604c6e247442dbb14c90c5 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:07 +0100
Subject: [PATCH 0991/4076] tty: serdev: convert to u8 and size_t in
 serdev_controller_ops

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

In this patch, only struct serdev_controller_ops hooks. The rest will
follow.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-23-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serdev/serdev-ttyport.c | 2 +-
 include/linux/serdev.h              | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c
index c5381fe15e1c4..e94e090cf0a1a 100644
--- a/drivers/tty/serdev/serdev-ttyport.c
+++ b/drivers/tty/serdev/serdev-ttyport.c
@@ -74,7 +74,7 @@ static const struct tty_port_client_operations client_ops = {
  * Callback functions from the serdev core.
  */
 
-static int ttyport_write_buf(struct serdev_controller *ctrl, const unsigned char *data, size_t len)
+static ssize_t ttyport_write_buf(struct serdev_controller *ctrl, const u8 *data, size_t len)
 {
 	struct serport *serport = serdev_controller_get_drvdata(ctrl);
 	struct tty_struct *tty = serport->tty;
diff --git a/include/linux/serdev.h b/include/linux/serdev.h
index 0ebf53bb254fa..8cdab2c3b6d58 100644
--- a/include/linux/serdev.h
+++ b/include/linux/serdev.h
@@ -82,7 +82,7 @@ enum serdev_parity {
  * serdev controller structures
  */
 struct serdev_controller_ops {
-	int (*write_buf)(struct serdev_controller *, const unsigned char *, size_t);
+	ssize_t (*write_buf)(struct serdev_controller *, const u8 *, size_t);
 	void (*write_flush)(struct serdev_controller *);
 	int (*write_room)(struct serdev_controller *);
 	int (*open)(struct serdev_controller *);
@@ -185,9 +185,9 @@ static inline void serdev_controller_write_wakeup(struct serdev_controller *ctrl
 	serdev->ops->write_wakeup(serdev);
 }
 
-static inline int serdev_controller_receive_buf(struct serdev_controller *ctrl,
-					      const unsigned char *data,
-					      size_t count)
+static inline ssize_t serdev_controller_receive_buf(struct serdev_controller *ctrl,
+						    const u8 *data,
+						    size_t count)
 {
 	struct serdev_device *serdev = ctrl->serdev;
 
-- 
GitLab


From 475fc6e2de6fec0ff3c9a74ddcfd2b52c90adc0d Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:08 +0100
Subject: [PATCH 0992/4076] tty: serdev: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

This patch converts struct serdev_device_ops hooks and its
instantiations.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Rob Herring <robh@kernel.org>
Acked-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-24-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bluetooth/btmtkuart.c                  |  4 ++--
 drivers/bluetooth/btnxpuart.c                  |  4 ++--
 drivers/bluetooth/hci_serdev.c                 |  4 ++--
 drivers/gnss/serial.c                          |  4 ++--
 drivers/gnss/sirf.c                            |  4 ++--
 drivers/greybus/gb-beagleplay.c                |  5 +++--
 drivers/iio/chemical/pms7003.c                 |  6 +++---
 drivers/iio/chemical/scd30_serial.c            |  6 +++---
 drivers/iio/chemical/sps30_serial.c            | 18 +++++++++---------
 drivers/iio/imu/bno055/bno055_ser_core.c       |  6 +++---
 drivers/mfd/rave-sp.c                          | 10 +++++-----
 drivers/net/ethernet/qualcomm/qca_uart.c       |  5 ++---
 drivers/nfc/pn533/uart.c                       |  4 ++--
 drivers/nfc/s3fwrn5/uart.c                     |  5 ++---
 drivers/platform/chrome/cros_ec_uart.c         |  5 ++---
 .../platform/surface/aggregator/controller.h   |  4 ++--
 drivers/platform/surface/aggregator/core.c     |  4 ++--
 .../surface/aggregator/ssh_packet_layer.c      |  4 ++--
 .../surface/aggregator/ssh_packet_layer.h      |  2 +-
 drivers/tty/serdev/core.c                      | 12 +++++-------
 include/linux/serdev.h                         | 13 +++++++------
 sound/drivers/serial-generic.c                 |  4 ++--
 22 files changed, 65 insertions(+), 68 deletions(-)

diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c
index 935feab815d97..d4f4e40ac5d2b 100644
--- a/drivers/bluetooth/btmtkuart.c
+++ b/drivers/bluetooth/btmtkuart.c
@@ -385,8 +385,8 @@ static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
 	return 0;
 }
 
-static int btmtkuart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				 size_t count)
+static ssize_t btmtkuart_receive_buf(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
 	int err;
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index b7e66b7ac5702..d75487a90bbac 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -1264,8 +1264,8 @@ static const struct h4_recv_pkt nxp_recv_pkts[] = {
 	{ NXP_RECV_FW_REQ_V3,   .recv = nxp_recv_fw_req_v3 },
 };
 
-static int btnxpuart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				 size_t count)
+static ssize_t btnxpuart_receive_buf(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct btnxpuart_dev *nxpdev = serdev_device_get_drvdata(serdev);
 
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index f16fd79bc02b8..39c8b567da3c0 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -271,8 +271,8 @@ static void hci_uart_write_wakeup(struct serdev_device *serdev)
  *
  * Return: number of processed bytes
  */
-static int hci_uart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				   size_t count)
+static ssize_t hci_uart_receive_buf(struct serdev_device *serdev,
+				    const u8 *data, size_t count)
 {
 	struct hci_uart *hu = serdev_device_get_drvdata(serdev);
 
diff --git a/drivers/gnss/serial.c b/drivers/gnss/serial.c
index 5d8e9bfb24d02..baa956494e79f 100644
--- a/drivers/gnss/serial.c
+++ b/drivers/gnss/serial.c
@@ -80,8 +80,8 @@ static const struct gnss_operations gnss_serial_gnss_ops = {
 	.write_raw	= gnss_serial_write_raw,
 };
 
-static int gnss_serial_receive_buf(struct serdev_device *serdev,
-					const unsigned char *buf, size_t count)
+static ssize_t gnss_serial_receive_buf(struct serdev_device *serdev,
+				       const u8 *buf, size_t count)
 {
 	struct gnss_serial *gserial = serdev_device_get_drvdata(serdev);
 	struct gnss_device *gdev = gserial->gdev;
diff --git a/drivers/gnss/sirf.c b/drivers/gnss/sirf.c
index bcb53ccfee4d5..6801a8fb20401 100644
--- a/drivers/gnss/sirf.c
+++ b/drivers/gnss/sirf.c
@@ -160,8 +160,8 @@ static const struct gnss_operations sirf_gnss_ops = {
 	.write_raw	= sirf_write_raw,
 };
 
-static int sirf_receive_buf(struct serdev_device *serdev,
-				const unsigned char *buf, size_t count)
+static ssize_t sirf_receive_buf(struct serdev_device *serdev,
+				const u8 *buf, size_t count)
 {
 	struct sirf_data *data = serdev_device_get_drvdata(serdev);
 	struct gnss_device *gdev = data->gdev;
diff --git a/drivers/greybus/gb-beagleplay.c b/drivers/greybus/gb-beagleplay.c
index 43318c1993ba9..2da37ff92cf1c 100644
--- a/drivers/greybus/gb-beagleplay.c
+++ b/drivers/greybus/gb-beagleplay.c
@@ -257,7 +257,7 @@ static void hdlc_rx_frame(struct gb_beagleplay *bg)
 	}
 }
 
-static int hdlc_rx(struct gb_beagleplay *bg, const u8 *data, size_t count)
+static ssize_t hdlc_rx(struct gb_beagleplay *bg, const u8 *data, size_t count)
 {
 	size_t i;
 	u8 c;
@@ -317,7 +317,8 @@ static void hdlc_deinit(struct gb_beagleplay *bg)
 	flush_work(&bg->tx_work);
 }
 
-static int gb_tty_receive(struct serdev_device *sd, const unsigned char *data, size_t count)
+static ssize_t gb_tty_receive(struct serdev_device *sd, const u8 *data,
+			      size_t count)
 {
 	struct gb_beagleplay *bg = serdev_device_get_drvdata(sd);
 
diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c
index e9857d93b307e..b5cf15a515d25 100644
--- a/drivers/iio/chemical/pms7003.c
+++ b/drivers/iio/chemical/pms7003.c
@@ -211,13 +211,13 @@ static bool pms7003_frame_is_okay(struct pms7003_frame *frame)
 	return checksum == pms7003_calc_checksum(frame);
 }
 
-static int pms7003_receive_buf(struct serdev_device *serdev,
-			       const unsigned char *buf, size_t size)
+static ssize_t pms7003_receive_buf(struct serdev_device *serdev, const u8 *buf,
+				   size_t size)
 {
 	struct iio_dev *indio_dev = serdev_device_get_drvdata(serdev);
 	struct pms7003_state *state = iio_priv(indio_dev);
 	struct pms7003_frame *frame = &state->frame;
-	int num;
+	size_t num;
 
 	if (!frame->expected_length) {
 		u16 magic;
diff --git a/drivers/iio/chemical/scd30_serial.c b/drivers/iio/chemical/scd30_serial.c
index 3c519103d30b5..a47654591e555 100644
--- a/drivers/iio/chemical/scd30_serial.c
+++ b/drivers/iio/chemical/scd30_serial.c
@@ -174,13 +174,13 @@ static int scd30_serdev_command(struct scd30_state *state, enum scd30_cmd cmd, u
 	return 0;
 }
 
-static int scd30_serdev_receive_buf(struct serdev_device *serdev,
-				    const unsigned char *buf, size_t size)
+static ssize_t scd30_serdev_receive_buf(struct serdev_device *serdev,
+					const u8 *buf, size_t size)
 {
 	struct iio_dev *indio_dev = serdev_device_get_drvdata(serdev);
 	struct scd30_serdev_priv *priv;
 	struct scd30_state *state;
-	int num;
+	size_t num;
 
 	if (!indio_dev)
 		return 0;
diff --git a/drivers/iio/chemical/sps30_serial.c b/drivers/iio/chemical/sps30_serial.c
index 164f4b3e025c9..3afa89f8acc32 100644
--- a/drivers/iio/chemical/sps30_serial.c
+++ b/drivers/iio/chemical/sps30_serial.c
@@ -74,8 +74,8 @@ static int sps30_serial_xfer(struct sps30_state *state, const unsigned char *buf
 }
 
 static const struct {
-	unsigned char byte;
-	unsigned char byte2;
+	u8 byte;
+	u8 byte2;
 } sps30_serial_bytes[] = {
 	{ 0x11, 0x31 },
 	{ 0x13, 0x33 },
@@ -83,7 +83,7 @@ static const struct {
 	{ 0x7d, 0x5d },
 };
 
-static int sps30_serial_put_byte(unsigned char *buf, unsigned char byte)
+static int sps30_serial_put_byte(u8 *buf, u8 byte)
 {
 	int i;
 
@@ -102,7 +102,7 @@ static int sps30_serial_put_byte(unsigned char *buf, unsigned char byte)
 	return 1;
 }
 
-static char sps30_serial_get_byte(bool escaped, unsigned char byte2)
+static u8 sps30_serial_get_byte(bool escaped, u8 byte2)
 {
 	int i;
 
@@ -130,8 +130,8 @@ static unsigned char sps30_serial_calc_chksum(const unsigned char *buf, size_t n
 	return ~chksum;
 }
 
-static int sps30_serial_prep_frame(unsigned char *buf, unsigned char cmd,
-				   const unsigned char *arg, size_t arg_size)
+static int sps30_serial_prep_frame(u8 *buf, u8 cmd, const u8 *arg,
+				   size_t arg_size)
 {
 	unsigned char chksum;
 	int num = 0;
@@ -210,14 +210,14 @@ static int sps30_serial_command(struct sps30_state *state, unsigned char cmd,
 	return rsp_size;
 }
 
-static int sps30_serial_receive_buf(struct serdev_device *serdev,
-				    const unsigned char *buf, size_t size)
+static ssize_t sps30_serial_receive_buf(struct serdev_device *serdev,
+					const u8 *buf, size_t size)
 {
 	struct iio_dev *indio_dev = dev_get_drvdata(&serdev->dev);
 	struct sps30_serial_priv *priv;
 	struct sps30_state *state;
-	unsigned char byte;
 	size_t i;
+	u8 byte;
 
 	if (!indio_dev)
 		return 0;
diff --git a/drivers/iio/imu/bno055/bno055_ser_core.c b/drivers/iio/imu/bno055/bno055_ser_core.c
index 57728a5684715..5677bdf4f846e 100644
--- a/drivers/iio/imu/bno055/bno055_ser_core.c
+++ b/drivers/iio/imu/bno055/bno055_ser_core.c
@@ -378,12 +378,12 @@ static void bno055_ser_handle_rx(struct bno055_ser_priv *priv, int status)
  * Also, we assume to RX one pkt per time (i.e. the HW doesn't send anything
  * unless we require to AND we don't queue more than one request per time).
  */
-static int bno055_ser_receive_buf(struct serdev_device *serdev,
-				  const unsigned char *buf, size_t size)
+static ssize_t bno055_ser_receive_buf(struct serdev_device *serdev,
+				      const u8 *buf, size_t size)
 {
 	int status;
 	struct bno055_ser_priv *priv = serdev_device_get_drvdata(serdev);
-	int remaining = size;
+	size_t remaining = size;
 
 	if (size == 0)
 		return 0;
diff --git a/drivers/mfd/rave-sp.c b/drivers/mfd/rave-sp.c
index da50eba100149..b1229bb143ee7 100644
--- a/drivers/mfd/rave-sp.c
+++ b/drivers/mfd/rave-sp.c
@@ -471,17 +471,17 @@ static void rave_sp_receive_frame(struct rave_sp *sp,
 		rave_sp_receive_reply(sp, data, length);
 }
 
-static int rave_sp_receive_buf(struct serdev_device *serdev,
-			       const unsigned char *buf, size_t size)
+static ssize_t rave_sp_receive_buf(struct serdev_device *serdev,
+				   const u8 *buf, size_t size)
 {
 	struct device *dev = &serdev->dev;
 	struct rave_sp *sp = dev_get_drvdata(dev);
 	struct rave_sp_deframer *deframer = &sp->deframer;
-	const unsigned char *src = buf;
-	const unsigned char *end = buf + size;
+	const u8 *src = buf;
+	const u8 *end = buf + size;
 
 	while (src < end) {
-		const unsigned char byte = *src++;
+		const u8 byte = *src++;
 
 		switch (deframer->state) {
 		case RAVE_SP_EXPECT_SOF:
diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c
index 9adec91f35e94..223321897b961 100644
--- a/drivers/net/ethernet/qualcomm/qca_uart.c
+++ b/drivers/net/ethernet/qualcomm/qca_uart.c
@@ -58,9 +58,8 @@ struct qcauart {
 	unsigned char *tx_buffer;
 };
 
-static int
-qca_tty_receive(struct serdev_device *serdev, const unsigned char *data,
-		size_t count)
+static ssize_t
+qca_tty_receive(struct serdev_device *serdev, const u8 *data, size_t count)
 {
 	struct qcauart *qca = serdev_device_get_drvdata(serdev);
 	struct net_device *netdev = qca->net_dev;
diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c
index a556acdb947bb..2eb5978bd79e1 100644
--- a/drivers/nfc/pn533/uart.c
+++ b/drivers/nfc/pn533/uart.c
@@ -203,8 +203,8 @@ static int pn532_uart_rx_is_frame(struct sk_buff *skb)
 	return 0;
 }
 
-static int pn532_receive_buf(struct serdev_device *serdev,
-		const unsigned char *data, size_t count)
+static ssize_t pn532_receive_buf(struct serdev_device *serdev,
+				 const u8 *data, size_t count)
 {
 	struct pn532_uart_phy *dev = serdev_device_get_drvdata(serdev);
 	size_t i;
diff --git a/drivers/nfc/s3fwrn5/uart.c b/drivers/nfc/s3fwrn5/uart.c
index 82ea35d748a5d..456d3947116c1 100644
--- a/drivers/nfc/s3fwrn5/uart.c
+++ b/drivers/nfc/s3fwrn5/uart.c
@@ -51,9 +51,8 @@ static const struct s3fwrn5_phy_ops uart_phy_ops = {
 	.write = s3fwrn82_uart_write,
 };
 
-static int s3fwrn82_uart_read(struct serdev_device *serdev,
-			      const unsigned char *data,
-			      size_t count)
+static ssize_t s3fwrn82_uart_read(struct serdev_device *serdev,
+				  const u8 *data, size_t count)
 {
 	struct s3fwrn82_uart_phy *phy = serdev_device_get_drvdata(serdev);
 	size_t i;
diff --git a/drivers/platform/chrome/cros_ec_uart.c b/drivers/platform/chrome/cros_ec_uart.c
index 788246559bbba..68d80559fddc2 100644
--- a/drivers/platform/chrome/cros_ec_uart.c
+++ b/drivers/platform/chrome/cros_ec_uart.c
@@ -81,9 +81,8 @@ struct cros_ec_uart {
 	struct response_info response;
 };
 
-static int cros_ec_uart_rx_bytes(struct serdev_device *serdev,
-				 const u8 *data,
-				 size_t count)
+static ssize_t cros_ec_uart_rx_bytes(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct ec_host_response *host_response;
 	struct cros_ec_device *ec_dev = serdev_device_get_drvdata(serdev);
diff --git a/drivers/platform/surface/aggregator/controller.h b/drivers/platform/surface/aggregator/controller.h
index f0d987abc51e3..f1638c2081e8b 100644
--- a/drivers/platform/surface/aggregator/controller.h
+++ b/drivers/platform/surface/aggregator/controller.h
@@ -238,8 +238,8 @@ struct ssam_controller {
  * layer of the controller has been shut down, %-ESHUTDOWN.
  */
 static inline
-int ssam_controller_receive_buf(struct ssam_controller *ctrl,
-				const unsigned char *buf, size_t n)
+ssize_t ssam_controller_receive_buf(struct ssam_controller *ctrl, const u8 *buf,
+				    size_t n)
 {
 	return ssh_ptl_rx_rcvbuf(&ctrl->rtl.ptl, buf, n);
 }
diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c
index 1a6373dea109c..72d7314a4efd7 100644
--- a/drivers/platform/surface/aggregator/core.c
+++ b/drivers/platform/surface/aggregator/core.c
@@ -227,8 +227,8 @@ EXPORT_SYMBOL_GPL(ssam_client_bind);
 
 /* -- Glue layer (serdev_device -> ssam_controller). ------------------------ */
 
-static int ssam_receive_buf(struct serdev_device *dev, const unsigned char *buf,
-			    size_t n)
+static ssize_t ssam_receive_buf(struct serdev_device *dev, const u8 *buf,
+				size_t n)
 {
 	struct ssam_controller *ctrl;
 
diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.c b/drivers/platform/surface/aggregator/ssh_packet_layer.c
index def8d7ac541f7..d726b1a863199 100644
--- a/drivers/platform/surface/aggregator/ssh_packet_layer.c
+++ b/drivers/platform/surface/aggregator/ssh_packet_layer.c
@@ -1887,9 +1887,9 @@ int ssh_ptl_rx_stop(struct ssh_ptl *ptl)
  * Return: Returns the number of bytes transferred (positive or zero) on
  * success. Returns %-ESHUTDOWN if the packet layer has been shut down.
  */
-int ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n)
+ssize_t ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n)
 {
-	int used;
+	size_t used;
 
 	if (test_bit(SSH_PTL_SF_SHUTDOWN_BIT, &ptl->state))
 		return -ESHUTDOWN;
diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.h b/drivers/platform/surface/aggregator/ssh_packet_layer.h
index 64633522f9716..c80e822070dfd 100644
--- a/drivers/platform/surface/aggregator/ssh_packet_layer.h
+++ b/drivers/platform/surface/aggregator/ssh_packet_layer.h
@@ -162,7 +162,7 @@ void ssh_ptl_shutdown(struct ssh_ptl *ptl);
 int ssh_ptl_submit(struct ssh_ptl *ptl, struct ssh_packet *p);
 void ssh_ptl_cancel(struct ssh_packet *p);
 
-int ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n);
+ssize_t ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n);
 
 /**
  * ssh_ptl_tx_wakeup_transfer() - Wake up packet transmitter thread for
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index 3090e3454c447..de8d87d4858d4 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -225,8 +225,7 @@ EXPORT_SYMBOL_GPL(serdev_device_write_wakeup);
  * Return: The number of bytes written (less than count if not enough room in
  * the write buffer), or a negative errno on errors.
  */
-int serdev_device_write_buf(struct serdev_device *serdev,
-			    const unsigned char *buf, size_t count)
+int serdev_device_write_buf(struct serdev_device *serdev, const u8 *buf, size_t count)
 {
 	struct serdev_controller *ctrl = serdev->ctrl;
 
@@ -259,13 +258,12 @@ EXPORT_SYMBOL_GPL(serdev_device_write_buf);
  * -ETIMEDOUT or -ERESTARTSYS if interrupted before any bytes were written, or
  * a negative errno on errors.
  */
-int serdev_device_write(struct serdev_device *serdev,
-			const unsigned char *buf, size_t count,
-			long timeout)
+ssize_t serdev_device_write(struct serdev_device *serdev, const u8 *buf,
+			    size_t count, long timeout)
 {
 	struct serdev_controller *ctrl = serdev->ctrl;
-	int written = 0;
-	int ret;
+	size_t written = 0;
+	ssize_t ret;
 
 	if (!ctrl || !ctrl->ops->write_buf || !serdev->ops->write_wakeup)
 		return -EINVAL;
diff --git a/include/linux/serdev.h b/include/linux/serdev.h
index 8cdab2c3b6d58..3fab88ba265ee 100644
--- a/include/linux/serdev.h
+++ b/include/linux/serdev.h
@@ -27,7 +27,7 @@ struct serdev_device;
  *			not sleep.
  */
 struct serdev_device_ops {
-	int (*receive_buf)(struct serdev_device *, const unsigned char *, size_t);
+	ssize_t (*receive_buf)(struct serdev_device *, const u8 *, size_t);
 	void (*write_wakeup)(struct serdev_device *);
 };
 
@@ -204,13 +204,13 @@ void serdev_device_close(struct serdev_device *);
 int devm_serdev_device_open(struct device *, struct serdev_device *);
 unsigned int serdev_device_set_baudrate(struct serdev_device *, unsigned int);
 void serdev_device_set_flow_control(struct serdev_device *, bool);
-int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_t);
+int serdev_device_write_buf(struct serdev_device *, const u8 *, size_t);
 void serdev_device_wait_until_sent(struct serdev_device *, long);
 int serdev_device_get_tiocm(struct serdev_device *);
 int serdev_device_set_tiocm(struct serdev_device *, int, int);
 int serdev_device_break_ctl(struct serdev_device *serdev, int break_state);
 void serdev_device_write_wakeup(struct serdev_device *);
-int serdev_device_write(struct serdev_device *, const unsigned char *, size_t, long);
+ssize_t serdev_device_write(struct serdev_device *, const u8 *, size_t, long);
 void serdev_device_write_flush(struct serdev_device *);
 int serdev_device_write_room(struct serdev_device *);
 
@@ -248,7 +248,7 @@ static inline unsigned int serdev_device_set_baudrate(struct serdev_device *sdev
 }
 static inline void serdev_device_set_flow_control(struct serdev_device *sdev, bool enable) {}
 static inline int serdev_device_write_buf(struct serdev_device *serdev,
-					  const unsigned char *buf,
+					  const u8 *buf,
 					  size_t count)
 {
 	return -ENODEV;
@@ -266,8 +266,9 @@ static inline int serdev_device_break_ctl(struct serdev_device *serdev, int brea
 {
 	return -EOPNOTSUPP;
 }
-static inline int serdev_device_write(struct serdev_device *sdev, const unsigned char *buf,
-				      size_t count, unsigned long timeout)
+static inline ssize_t serdev_device_write(struct serdev_device *sdev,
+					  const u8 *buf, size_t count,
+					  unsigned long timeout)
 {
 	return -ENODEV;
 }
diff --git a/sound/drivers/serial-generic.c b/sound/drivers/serial-generic.c
index c8db6c75d133d..d6e5aafd697c7 100644
--- a/sound/drivers/serial-generic.c
+++ b/sound/drivers/serial-generic.c
@@ -100,8 +100,8 @@ static void snd_serial_generic_write_wakeup(struct serdev_device *serdev)
 	snd_serial_generic_tx_wakeup(drvdata);
 }
 
-static int snd_serial_generic_receive_buf(struct serdev_device *serdev,
-				const unsigned char *buf, size_t count)
+static ssize_t snd_serial_generic_receive_buf(struct serdev_device *serdev,
+					      const u8 *buf, size_t count)
 {
 	int ret;
 	struct snd_serial_generic *drvdata = serdev_device_get_drvdata(serdev);
-- 
GitLab


From 14abfd0cb52f21256f4353196ddfb8e6f3c4e8b4 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:09 +0100
Subject: [PATCH 0993/4076] tty: srmcons: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: linux-alpha@vger.kernel.org
Link: https://lore.kernel.org/r/20231206073712.17776-25-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/alpha/kernel/srmcons.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 42deea53beab2..feaf89f6936bc 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -53,7 +53,7 @@ srmcons_do_receive_chars(struct tty_port *port)
 	do {
 		result.as_long = callback_getc(0);
 		if (result.bits.status < 2) {
-			tty_insert_flip_char(port, (char)result.bits.c, 0);
+			tty_insert_flip_char(port, (u8)result.bits.c, 0);
 			count++;
 		}
 	} while((result.bits.status & 1) && (++loops < 10));
@@ -89,7 +89,7 @@ srmcons_receive_chars(struct timer_list *t)
 
 /* called with callback_lock held */
 static void
-srmcons_do_write(struct tty_port *port, const char *buf, int count)
+srmcons_do_write(struct tty_port *port, const u8 *buf, size_t count)
 {
 	size_t c;
 	srmcons_result result;
@@ -131,7 +131,7 @@ srmcons_write(struct tty_struct *tty, const u8 *buf, size_t count)
 	unsigned long flags;
 
 	spin_lock_irqsave(&srmcons_callback_lock, flags);
-	srmcons_do_write(tty->port, (const char *) buf, count);
+	srmcons_do_write(tty->port, buf, count);
 	spin_unlock_irqrestore(&srmcons_callback_lock, flags);
 
 	return count;
-- 
GitLab


From 18977909bfba2a866f5e2cd0ce540919de5aa394 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:10 +0100
Subject: [PATCH 0994/4076] tty: ttyprintk: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20231206073712.17776-26-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/char/ttyprintk.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c
index 5af804c17a753..4c806a189ee53 100644
--- a/drivers/char/ttyprintk.c
+++ b/drivers/char/ttyprintk.c
@@ -40,7 +40,7 @@ static struct ttyprintk_port tpk_port;
 
 static int tpk_curr;
 
-static char tpk_buffer[TPK_STR_SIZE + 4];
+static u8 tpk_buffer[TPK_STR_SIZE + 4];
 
 static void tpk_flush(void)
 {
@@ -51,9 +51,9 @@ static void tpk_flush(void)
 	}
 }
 
-static int tpk_printk(const u8 *buf, int count)
+static int tpk_printk(const u8 *buf, size_t count)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < count; i++) {
 		if (tpk_curr >= TPK_STR_SIZE) {
-- 
GitLab


From b49d18493a0b9bb79289c5bec31acf073c34edd2 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:11 +0100
Subject: [PATCH 0995/4076] tty: um: convert to u8/__u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

Note we use __u8 in the userspace files.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: linux-um@lists.infradead.org
Link: https://lore.kernel.org/r/20231206073712.17776-27-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/um/drivers/chan.h      | 2 +-
 arch/um/drivers/chan_kern.c | 9 ++++-----
 arch/um/drivers/chan_user.c | 4 ++--
 arch/um/drivers/chan_user.h | 9 +++++----
 arch/um/drivers/line.c      | 2 +-
 arch/um/drivers/line.h      | 6 +++---
 arch/um/drivers/null.c      | 2 +-
 7 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/arch/um/drivers/chan.h b/arch/um/drivers/chan.h
index 3fec3b8406e98..e14b9cdf7a33d 100644
--- a/arch/um/drivers/chan.h
+++ b/arch/um/drivers/chan.h
@@ -30,7 +30,7 @@ struct chan {
 extern void chan_interrupt(struct line *line, int irq);
 extern int parse_chan_pair(char *str, struct line *line, int device,
 			   const struct chan_opts *opts, char **error_out);
-extern int write_chan(struct chan *chan, const char *buf, int len,
+extern int write_chan(struct chan *chan, const u8 *buf, size_t len,
 			     int write_irq);
 extern int console_write_chan(struct chan *chan, const char *buf, 
 			      int len);
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index 26a702a065154..37538b4168da6 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -33,14 +33,14 @@ static void not_configged_close(int fd, void *data)
 	       "UML\n");
 }
 
-static int not_configged_read(int fd, char *c_out, void *data)
+static int not_configged_read(int fd, u8 *c_out, void *data)
 {
 	printk(KERN_ERR "Using a channel type which is configured out of "
 	       "UML\n");
 	return -EIO;
 }
 
-static int not_configged_write(int fd, const char *buf, int len, void *data)
+static int not_configged_write(int fd, const u8 *buf, size_t len, void *data)
 {
 	printk(KERN_ERR "Using a channel type which is configured out of "
 	       "UML\n");
@@ -247,8 +247,7 @@ void deactivate_chan(struct chan *chan, int irq)
 		deactivate_fd(chan->fd, irq);
 }
 
-int write_chan(struct chan *chan, const char *buf, int len,
-	       int write_irq)
+int write_chan(struct chan *chan, const u8 *buf, size_t len, int write_irq)
 {
 	int n, ret = 0;
 
@@ -540,7 +539,7 @@ void chan_interrupt(struct line *line, int irq)
 	struct tty_port *port = &line->port;
 	struct chan *chan = line->chan_in;
 	int err;
-	char c;
+	u8 c;
 
 	if (!chan || !chan->ops->read)
 		goto out;
diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index 25727ed648b72..40d98dd23c8a8 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -19,7 +19,7 @@ void generic_close(int fd, void *unused)
 	close(fd);
 }
 
-int generic_read(int fd, char *c_out, void *unused)
+int generic_read(int fd, __u8 *c_out, void *unused)
 {
 	int n;
 
@@ -35,7 +35,7 @@ int generic_read(int fd, char *c_out, void *unused)
 
 /* XXX Trivial wrapper around write */
 
-int generic_write(int fd, const char *buf, int n, void *unused)
+int generic_write(int fd, const __u8 *buf, size_t n, void *unused)
 {
 	int err;
 
diff --git a/arch/um/drivers/chan_user.h b/arch/um/drivers/chan_user.h
index 4e51b85e2a23a..e158e16fb3cc9 100644
--- a/arch/um/drivers/chan_user.h
+++ b/arch/um/drivers/chan_user.h
@@ -7,6 +7,7 @@
 #define __CHAN_USER_H__
 
 #include <init.h>
+#include <linux/types.h>
 
 struct chan_opts {
 	void (*const announce)(char *dev_name, int dev);
@@ -19,8 +20,8 @@ struct chan_ops {
 	void *(*init)(char *, int, const struct chan_opts *);
 	int (*open)(int, int, int, void *, char **);
 	void (*close)(int, void *);
-	int (*read)(int, char *, void *);
-	int (*write)(int, const char *, int, void *);
+	int (*read)(int, __u8 *, void *);
+	int (*write)(int, const __u8 *, size_t, void *);
 	int (*console_write)(int, const char *, int);
 	int (*window_size)(int, void *, unsigned short *, unsigned short *);
 	void (*free)(void *);
@@ -31,8 +32,8 @@ extern const struct chan_ops fd_ops, null_ops, port_ops, pts_ops, pty_ops,
 	tty_ops, xterm_ops;
 
 extern void generic_close(int fd, void *unused);
-extern int generic_read(int fd, char *c_out, void *unused);
-extern int generic_write(int fd, const char *buf, int n, void *unused);
+extern int generic_read(int fd, __u8 *c_out, void *unused);
+extern int generic_write(int fd, const __u8 *buf, size_t n, void *unused);
 extern int generic_console_write(int fd, const char *buf, int n);
 extern int generic_window_size(int fd, void *unused, unsigned short *rows_out,
 			       unsigned short *cols_out);
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index b98545f3edb50..c9403629cc56c 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -83,7 +83,7 @@ unsigned int line_chars_in_buffer(struct tty_struct *tty)
  *
  * Must be called while holding line->lock!
  */
-static int buffer_data(struct line *line, const char *buf, int len)
+static int buffer_data(struct line *line, const u8 *buf, size_t len)
 {
 	int end, room;
 
diff --git a/arch/um/drivers/line.h b/arch/um/drivers/line.h
index e84fb9b4165e8..e8bd6f3dfb507 100644
--- a/arch/um/drivers/line.h
+++ b/arch/um/drivers/line.h
@@ -47,9 +47,9 @@ struct line {
 	 *
 	 * buffer points to a buffer allocated on demand, of length
 	 * LINE_BUFSIZE, head to the start of the ring, tail to the end.*/
-	char *buffer;
-	char *head;
-	char *tail;
+	u8 *buffer;
+	u8 *head;
+	u8 *tail;
 
 	int sigio;
 	struct delayed_work task;
diff --git a/arch/um/drivers/null.c b/arch/um/drivers/null.c
index 87087763a417f..30d59b8481b40 100644
--- a/arch/um/drivers/null.c
+++ b/arch/um/drivers/null.c
@@ -28,7 +28,7 @@ static int null_open(int input, int output, int primary, void *d,
 	return (fd < 0) ? -errno : fd;
 }
 
-static int null_read(int fd, char *c_out, void *unused)
+static int null_read(int fd, __u8 *c_out, void *unused)
 {
 	return -ENODEV;
 }
-- 
GitLab


From ae5af710f369a4d88792bf1d9da317884156cd87 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:12 +0100
Subject: [PATCH 0996/4076] tty: xtensa/iss: use u8

Switch character types to u8. To conform to characters in the rest of
the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Chris Zankel <chris@zankel.net>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Link: https://lore.kernel.org/r/20231206073712.17776-28-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/xtensa/platforms/iss/console.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 7d1f8b398a464..8896e691c051e 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -65,7 +65,7 @@ static void rs_poll(struct timer_list *unused)
 	struct tty_port *port = &serial_port;
 	int i = 0;
 	int rd = 1;
-	unsigned char c;
+	u8 c;
 
 	while (simc_poll(0)) {
 		rd = simc_read(0, &c, 1);
-- 
GitLab


From 644977738c445c11c48152e11a1cb50c2fc4bc20 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 12 Nov 2023 19:43:59 +0100
Subject: [PATCH 0997/4076] dt-bindings: gpu: samsung-rotator: drop redundant
 quotes

Compatibles should not use quotes in the bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231112184403.3449-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/gpu/samsung-rotator.yaml         | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/gpu/samsung-rotator.yaml b/Documentation/devicetree/bindings/gpu/samsung-rotator.yaml
index d60626ffb28e2..18bf44e06e8f3 100644
--- a/Documentation/devicetree/bindings/gpu/samsung-rotator.yaml
+++ b/Documentation/devicetree/bindings/gpu/samsung-rotator.yaml
@@ -12,10 +12,11 @@ maintainers:
 properties:
   compatible:
     enum:
-      - "samsung,s5pv210-rotator"
-      - "samsung,exynos4210-rotator"
-      - "samsung,exynos4212-rotator"
-      - "samsung,exynos5250-rotator"
+      - samsung,s5pv210-rotator
+      - samsung,exynos4210-rotator
+      - samsung,exynos4212-rotator
+      - samsung,exynos5250-rotator
+
   reg:
     maxItems: 1
 
-- 
GitLab


From 6b91e0ee7fc9e5b0ec0a8150ddc5fea15786ec7e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 12 Nov 2023 19:44:00 +0100
Subject: [PATCH 0998/4076] dt-bindings: gpu: samsung: re-order entries to
 match coding convention

The Devicetree bindings coding convention, as used in most of the files
and expressed in Documentation/devicetree/bindings/example-schema.yaml,
expects "allOf:" block with if-statements after "required:" block.

Re-order few schemas to match the convention to avoid repeating review
comments for new patches using existing code as template.  No functional
changes.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231112184403.3449-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/gpu/samsung-g2d.yaml  | 53 +++++++++--------
 .../bindings/gpu/samsung-scaler.yaml          | 59 +++++++++----------
 2 files changed, 56 insertions(+), 56 deletions(-)

diff --git a/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml b/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
index e7daae8625789..b6951acc76436 100644
--- a/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
+++ b/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
@@ -27,32 +27,6 @@ properties:
   iommus: {}
   power-domains: {}
 
-if:
-  properties:
-    compatible:
-      contains:
-        const: samsung,exynos5250-g2d
-
-then:
-  properties:
-    clocks:
-      items:
-        - description: fimg2d clock
-    clock-names:
-      items:
-        - const: fimg2d
-
-else:
-  properties:
-    clocks:
-      items:
-        - description: sclk_fimg2d clock
-        - description: fimg2d clock
-    clock-names:
-      items:
-        - const: sclk_fimg2d
-        - const: fimg2d
-
 required:
   - compatible
   - reg
@@ -60,6 +34,33 @@ required:
   - clocks
   - clock-names
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: samsung,exynos5250-g2d
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: fimg2d clock
+        clock-names:
+          items:
+            - const: fimg2d
+
+    else:
+      properties:
+        clocks:
+          items:
+            - description: sclk_fimg2d clock
+            - description: fimg2d clock
+        clock-names:
+          items:
+            - const: sclk_fimg2d
+            - const: fimg2d
+
 additionalProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml b/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
index 5317ac64426af..97d86a002a90e 100644
--- a/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
+++ b/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
@@ -26,36 +26,6 @@ properties:
   iommus: {}
   power-domains: {}
 
-if:
-  properties:
-    compatible:
-      contains:
-        const: samsung,exynos5420-scaler
-
-then:
-  properties:
-    clocks:
-      items:
-        - description: mscl clock
-
-    clock-names:
-      items:
-        - const: mscl
-
-else:
-  properties:
-    clocks:
-      items:
-        - description: pclk clock
-        - description: aclk clock
-        - description: aclk_xiu clock
-
-    clock-names:
-      items:
-        - const: pclk
-        - const: aclk
-        - const: aclk_xiu
-
 required:
   - compatible
   - reg
@@ -63,6 +33,35 @@ required:
   - clocks
   - clock-names
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: samsung,exynos5420-scaler
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: mscl clock
+        clock-names:
+          items:
+            - const: mscl
+
+    else:
+      properties:
+        clocks:
+          items:
+            - description: pclk clock
+            - description: aclk clock
+            - description: aclk_xiu clock
+        clock-names:
+          items:
+            - const: pclk
+            - const: aclk
+            - const: aclk_xiu
+
 additionalProperties: false
 
 examples:
-- 
GitLab


From f1d797b6da5e4a7cacc04eb9a49fe1a421169ff3 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 12 Nov 2023 19:44:01 +0100
Subject: [PATCH 0999/4076] dt-bindings: gpu: samsung: constrain clocks in
 top-level properties

When number of clock varies between variants, the Devicetree bindings
coding convention expects to have widest constraints in top-level
definition of the properties and narrow them in allOf:if:then block.

This is more readable and sometimes allows to spot some errors in the
bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231112184403.3449-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/gpu/samsung-g2d.yaml | 10 ++++++++--
 .../devicetree/bindings/gpu/samsung-scaler.yaml        | 10 ++++++++--
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml b/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
index b6951acc76436..f368966cf83ab 100644
--- a/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
+++ b/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
@@ -22,8 +22,14 @@ properties:
   interrupts:
     maxItems: 1
 
-  clocks: {}
-  clock-names: {}
+  clocks:
+    minItems: 1
+    maxItems: 2
+
+  clock-names:
+    minItems: 1
+    maxItems: 2
+
   iommus: {}
   power-domains: {}
 
diff --git a/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml b/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
index 97d86a002a90e..e08fc1e4115f1 100644
--- a/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
+++ b/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
@@ -21,8 +21,14 @@ properties:
   interrupts:
     maxItems: 1
 
-  clocks: {}
-  clock-names: {}
+  clocks:
+    minItems: 1
+    maxItems: 3
+
+  clock-names:
+    minItems: 1
+    maxItems: 3
+
   iommus: {}
   power-domains: {}
 
-- 
GitLab


From 6ff067f3d56689aa67bf9885f4a63b5160111ae0 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 12 Nov 2023 19:44:02 +0100
Subject: [PATCH 1000/4076] dt-bindings: gpu: samsung-g2d: constrain iommus and
 power-domains

Provide specific constraints for iommus and power-domains, based on
current DTS.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231112184403.3449-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/gpu/samsung-g2d.yaml | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml b/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
index f368966cf83ab..132aaa49597b6 100644
--- a/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
+++ b/Documentation/devicetree/bindings/gpu/samsung-g2d.yaml
@@ -30,8 +30,12 @@ properties:
     minItems: 1
     maxItems: 2
 
-  iommus: {}
-  power-domains: {}
+  iommus:
+    minItems: 1
+    maxItems: 2
+
+  power-domains:
+    maxItems: 1
 
 required:
   - compatible
-- 
GitLab


From 6a4ff5eab84323f0275b8bde36cf4cea5ff7dcb1 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 12 Nov 2023 19:44:03 +0100
Subject: [PATCH 1001/4076] dt-bindings: gpu: samsung-scaler: constrain iommus
 and power-domains

Provide specific constraints for iommus and power-domains, based on
current DTS.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231112184403.3449-5-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/gpu/samsung-scaler.yaml      | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml b/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
index e08fc1e4115f1..9fb530e65d0e8 100644
--- a/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
+++ b/Documentation/devicetree/bindings/gpu/samsung-scaler.yaml
@@ -29,8 +29,12 @@ properties:
     minItems: 1
     maxItems: 3
 
-  iommus: {}
-  power-domains: {}
+  iommus:
+    minItems: 1
+    maxItems: 2
+
+  power-domains:
+    maxItems: 1
 
 required:
   - compatible
@@ -54,6 +58,8 @@ allOf:
         clock-names:
           items:
             - const: mscl
+        iommus:
+          minItems: 2
 
     else:
       properties:
@@ -67,6 +73,8 @@ allOf:
             - const: pclk
             - const: aclk
             - const: aclk_xiu
+        iommus:
+          maxItems: 1
 
 additionalProperties: false
 
-- 
GitLab


From f0f99f371822c48847e02e56d6e7de507e18f186 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 7 Nov 2023 09:04:36 +0100
Subject: [PATCH 1002/4076] dt-bindings: cache: qcom,llcc: correct QDU1000 reg
 entries

Qualcomm QDU1000 DTSI comes with one LLCC0 base address as pointed by
dtbs_check:

  qdu1000-idp.dtb: system-cache-controller@19200000: reg-names:2: 'llcc2_base' was expected

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Mukesh Ojha <quic_mojha@quicinc.com>
Link: https://lore.kernel.org/r/20231107080436.16747-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/cache/qcom,llcc.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/cache/qcom,llcc.yaml b/Documentation/devicetree/bindings/cache/qcom,llcc.yaml
index 580f9a97ddf78..d610b0be262cf 100644
--- a/Documentation/devicetree/bindings/cache/qcom,llcc.yaml
+++ b/Documentation/devicetree/bindings/cache/qcom,llcc.yaml
@@ -64,6 +64,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,qdu1000-llcc
               - qcom,sc7180-llcc
               - qcom,sm6350-llcc
     then:
@@ -101,7 +102,6 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,qdu1000-llcc
               - qcom,sc8180x-llcc
               - qcom,sc8280xp-llcc
     then:
-- 
GitLab


From 765a0542fdc7aad7cbc1da3bd19bed6297b54e2c Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:21 -0800
Subject: [PATCH 1003/4076] x86/virt/tdx: Detect TDX during kernel boot

Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
host and certain physical attacks.  A CPU-attested software module
called 'the TDX module' runs inside a new isolated memory range as a
trusted hypervisor to manage and run protected VMs.

Pre-TDX Intel hardware has support for a memory encryption architecture
called MKTME.  The memory encryption hardware underpinning MKTME is also
used for Intel TDX.  TDX ends up "stealing" some of the physical address
space from the MKTME architecture for crypto-protection to VMs.  The
BIOS is responsible for partitioning the "KeyID" space between legacy
MKTME and TDX.  The KeyIDs reserved for TDX are called 'TDX private
KeyIDs' or 'TDX KeyIDs' for short.

During machine boot, TDX microcode verifies that the BIOS programmed TDX
private KeyIDs consistently and correctly programmed across all CPU
packages.  The MSRs are locked in this state after verification.  This
is why MSR_IA32_MKTME_KEYID_PARTITIONING gets used for TDX enumeration:
it indicates not just that the hardware supports TDX, but that all the
boot-time security checks passed.

The TDX module is expected to be loaded by the BIOS when it enables TDX,
but the kernel needs to properly initialize it before it can be used to
create and run any TDX guests.  The TDX module will be initialized by
the KVM subsystem when KVM wants to use TDX.

Detect platform TDX support by detecting TDX private KeyIDs.

The TDX module itself requires one TDX KeyID as the 'TDX global KeyID'
to protect its metadata.  Each TDX guest also needs a TDX KeyID for its
own protection.  Just use the first TDX KeyID as the global KeyID and
leave the rest for TDX guests.  If no TDX KeyID is left for TDX guests,
disable TDX as initializing the TDX module alone is useless.

[ dhansen: add X86_FEATURE, replace helper function ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-1-dave.hansen%40intel.com
---
 arch/x86/include/asm/cpufeatures.h |  1 +
 arch/x86/include/asm/msr-index.h   |  3 ++
 arch/x86/include/asm/tdx.h         |  3 ++
 arch/x86/kernel/cpu/common.c       |  2 +
 arch/x86/virt/vmx/tdx/Makefile     |  2 +-
 arch/x86/virt/vmx/tdx/tdx.c        | 81 ++++++++++++++++++++++++++++++
 6 files changed, 91 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/virt/vmx/tdx/tdx.c

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4af140cf5719e..45ddc6b6baaa1 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -198,6 +198,7 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM	( 7*32+ 7) /* Platform supports being a TDX host */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1d51e1850ed03..66c12d4efa31a 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -536,6 +536,9 @@
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
 
+/* KeyID partitioning between MKTME and TDX */
+#define MSR_IA32_MKTME_KEYID_PARTITIONING	0x00000087
+
 /*
  * AMD64 MSRs. Not complete. See the architecture manual for a more
  * complete list.
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index f3d5305a60fc5..e5dd1cb0e1a10 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -83,6 +83,9 @@ static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1,
 u64 __seamcall(u64 fn, struct tdx_module_args *args);
 u64 __seamcall_ret(u64 fn, struct tdx_module_args *args);
 u64 __seamcall_saved_ret(u64 fn, struct tdx_module_args *args);
+void tdx_init(void);
+#else
+static inline void tdx_init(void) { }
 #endif	/* CONFIG_INTEL_TDX_HOST */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b14fc8c1c9538..b968a2496e80b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -66,6 +66,7 @@
 #include <asm/set_memory.h>
 #include <asm/traps.h>
 #include <asm/sev.h>
+#include <asm/tdx.h>
 
 #include "cpu.h"
 
@@ -1987,6 +1988,7 @@ static __init void identify_boot_cpu(void)
 	setup_cr_pinning();
 
 	tsx_init();
+	tdx_init();
 	lkgs_init();
 }
 
diff --git a/arch/x86/virt/vmx/tdx/Makefile b/arch/x86/virt/vmx/tdx/Makefile
index 46ef8f73aebbb..90da47eb85eec 100644
--- a/arch/x86/virt/vmx/tdx/Makefile
+++ b/arch/x86/virt/vmx/tdx/Makefile
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y += seamcall.o
+obj-y += seamcall.o tdx.o
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
new file mode 100644
index 0000000000000..94689aef44a65
--- /dev/null
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(c) 2023 Intel Corporation.
+ *
+ * Intel Trusted Domain Extensions (TDX) support
+ */
+
+#define pr_fmt(fmt)	"virt/tdx: " fmt
+
+#include <linux/types.h>
+#include <linux/cache.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/printk.h>
+#include <asm/msr-index.h>
+#include <asm/msr.h>
+#include <asm/cpufeature.h>
+#include <asm/tdx.h>
+
+static u32 tdx_global_keyid __ro_after_init;
+static u32 tdx_guest_keyid_start __ro_after_init;
+static u32 tdx_nr_guest_keyids __ro_after_init;
+
+static __init int record_keyid_partitioning(u32 *tdx_keyid_start,
+					    u32 *nr_tdx_keyids)
+{
+	u32 _nr_mktme_keyids, _tdx_keyid_start, _nr_tdx_keyids;
+	int ret;
+
+	/*
+	 * IA32_MKTME_KEYID_PARTIONING:
+	 *   Bit [31:0]:	Number of MKTME KeyIDs.
+	 *   Bit [63:32]:	Number of TDX private KeyIDs.
+	 */
+	ret = rdmsr_safe(MSR_IA32_MKTME_KEYID_PARTITIONING, &_nr_mktme_keyids,
+			&_nr_tdx_keyids);
+	if (ret || !_nr_tdx_keyids)
+		return -EINVAL;
+
+	/* TDX KeyIDs start after the last MKTME KeyID. */
+	_tdx_keyid_start = _nr_mktme_keyids + 1;
+
+	*tdx_keyid_start = _tdx_keyid_start;
+	*nr_tdx_keyids = _nr_tdx_keyids;
+
+	return 0;
+}
+
+void __init tdx_init(void)
+{
+	u32 tdx_keyid_start, nr_tdx_keyids;
+	int err;
+
+	err = record_keyid_partitioning(&tdx_keyid_start, &nr_tdx_keyids);
+	if (err)
+		return;
+
+	pr_info("BIOS enabled: private KeyID range [%u, %u)\n",
+			tdx_keyid_start, tdx_keyid_start + nr_tdx_keyids);
+
+	/*
+	 * The TDX module itself requires one 'global KeyID' to protect
+	 * its metadata.  If there's only one TDX KeyID, there won't be
+	 * any left for TDX guests thus there's no point to enable TDX
+	 * at all.
+	 */
+	if (nr_tdx_keyids < 2) {
+		pr_err("initialization failed: too few private KeyIDs available.\n");
+		return;
+	}
+
+	/*
+	 * Just use the first TDX KeyID as the 'global KeyID' and
+	 * leave the rest for TDX guests.
+	 */
+	tdx_global_keyid = tdx_keyid_start;
+	tdx_guest_keyid_start = tdx_keyid_start + 1;
+	tdx_nr_guest_keyids = nr_tdx_keyids - 1;
+
+	setup_force_cpu_cap(X86_FEATURE_TDX_HOST_PLATFORM);
+}
-- 
GitLab


From d623704bb23901a25bf6d6a40aa16b43a17622eb Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:22 -0800
Subject: [PATCH 1004/4076] x86/virt/tdx: Define TDX supported page sizes as
 macros

TDX supports 4K, 2M and 1G page sizes.  The corresponding values are
defined by the TDX module spec and used as TDX module ABI.  Currently,
they are used in try_accept_one() when the TDX guest tries to accept a
page.  However currently try_accept_one() uses hard-coded magic values.

Define TDX supported page sizes as macros and get rid of the hard-coded
values in try_accept_one().  TDX host support will need to use them too.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/all/20231208170740.53979-2-dave.hansen%40intel.com
---
 arch/x86/coco/tdx/tdx-shared.c    | 6 +++---
 arch/x86/include/asm/shared/tdx.h | 5 +++++
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/coco/tdx/tdx-shared.c b/arch/x86/coco/tdx/tdx-shared.c
index 78e413269791e..1655aa56a0a51 100644
--- a/arch/x86/coco/tdx/tdx-shared.c
+++ b/arch/x86/coco/tdx/tdx-shared.c
@@ -22,13 +22,13 @@ static unsigned long try_accept_one(phys_addr_t start, unsigned long len,
 	 */
 	switch (pg_level) {
 	case PG_LEVEL_4K:
-		page_size = 0;
+		page_size = TDX_PS_4K;
 		break;
 	case PG_LEVEL_2M:
-		page_size = 1;
+		page_size = TDX_PS_2M;
 		break;
 	case PG_LEVEL_1G:
-		page_size = 2;
+		page_size = TDX_PS_1G;
 		break;
 	default:
 		return 0;
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index ccce7ebd86772..a4036149c4847 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -55,6 +55,11 @@
 	(TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8  | TDX_R9  | \
 	 TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15)
 
+/* TDX supported page sizes from the TDX module ABI. */
+#define TDX_PS_4K	0
+#define TDX_PS_2M	1
+#define TDX_PS_1G	2
+
 #ifndef __ASSEMBLY__
 
 #include <linux/compiler_attributes.h>
-- 
GitLab


From 3115cabd935ade76fbe61154d1e405158e548272 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:23 -0800
Subject: [PATCH 1005/4076] x86/virt/tdx: Make INTEL_TDX_HOST depend on
 X86_X2APIC

TDX capable platforms are locked to X2APIC mode and cannot fall back to
the legacy xAPIC mode when TDX is enabled by the BIOS.  TDX host support
requires x2APIC.  Make INTEL_TDX_HOST depend on X86_X2APIC.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lore.kernel.org/lkml/ba80b303-31bf-d44a-b05d-5c0f83038798@intel.com/
Link: https://lore.kernel.org/all/20231208170740.53979-3-dave.hansen%40intel.com
---
 arch/x86/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3762f41bb0929..eb6e63956d51e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1970,6 +1970,7 @@ config INTEL_TDX_HOST
 	depends on CPU_SUP_INTEL
 	depends on X86_64
 	depends on KVM_INTEL
+	depends on X86_X2APIC
 	help
 	  Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
 	  host and certain physical attacks.  This option enables necessary TDX
-- 
GitLab


From 1e66a7e275393055d98d2306771fe1feadeb1cd6 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:24 -0800
Subject: [PATCH 1006/4076] x86/virt/tdx: Handle SEAMCALL no entropy error in
 common code

Some SEAMCALLs use the RDRAND hardware and can fail for the same reasons
as RDRAND.  Use the kernel RDRAND retry logic for them.

There are three __seamcall*() variants.  Do the SEAMCALL retry in common
code and add a wrapper for each of them.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirll.shutemov@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-4-dave.hansen%40intel.com
---
 arch/x86/include/asm/tdx.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index e5dd1cb0e1a10..24c0357081bdf 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -24,6 +24,11 @@
 #define TDX_SEAMCALL_GP			(TDX_SW_ERROR | X86_TRAP_GP)
 #define TDX_SEAMCALL_UD			(TDX_SW_ERROR | X86_TRAP_UD)
 
+/*
+ * TDX module SEAMCALL leaf function error codes
+ */
+#define TDX_RND_NO_ENTROPY	0x8000020300000000ULL
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -84,6 +89,27 @@ u64 __seamcall(u64 fn, struct tdx_module_args *args);
 u64 __seamcall_ret(u64 fn, struct tdx_module_args *args);
 u64 __seamcall_saved_ret(u64 fn, struct tdx_module_args *args);
 void tdx_init(void);
+
+#include <asm/archrandom.h>
+
+typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args);
+
+static inline u64 sc_retry(sc_func_t func, u64 fn,
+			   struct tdx_module_args *args)
+{
+	int retry = RDRAND_RETRY_LOOPS;
+	u64 ret;
+
+	do {
+		ret = func(fn, args);
+	} while (ret == TDX_RND_NO_ENTROPY && --retry);
+
+	return ret;
+}
+
+#define seamcall(_fn, _args)		sc_retry(__seamcall, (_fn), (_args))
+#define seamcall_ret(_fn, _args)	sc_retry(__seamcall_ret, (_fn), (_args))
+#define seamcall_saved_ret(_fn, _args)	sc_retry(__seamcall_saved_ret, (_fn), (_args))
 #else
 static inline void tdx_init(void) { }
 #endif	/* CONFIG_INTEL_TDX_HOST */
-- 
GitLab


From df01f5ae07dd9ca0c755943a5cfcc4e78e480f99 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:25 -0800
Subject: [PATCH 1007/4076] x86/virt/tdx: Add SEAMCALL error printing for
 module initialization

The SEAMCALLs involved during the TDX module initialization are not
expected to fail.  In fact, they are not expected to return any non-zero
code (except the "running out of entropy error", which can be handled
internally already).

Add yet another set of SEAMCALL wrappers, which treats all non-zero
return code as error, to support printing SEAMCALL error upon failure
for module initialization.  Note the TDX module initialization doesn't
use the _saved_ret() variant thus no wrapper is added for it.

SEAMCALL assembly can also return kernel-defined error codes for three
special cases: 1) TDX isn't enabled by the BIOS; 2) TDX module isn't
loaded; 3) CPU isn't in VMX operation.  Whether they can legally happen
depends on the caller, so leave to the caller to print error message
when desired.

Also convert the SEAMCALL error codes to the kernel error codes in the
new wrappers so that each SEAMCALL caller doesn't have to repeat the
conversion.

[ dhansen: Align the register dump with show_regs().  Zero-pad the
	   contents, split on two lines and use consistent spacing. ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-5-dave.hansen%40intel.com
---
 arch/x86/include/asm/tdx.h  |  1 +
 arch/x86/virt/vmx/tdx/tdx.c | 44 +++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 24c0357081bdf..2c0f4162fe99d 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -27,6 +27,7 @@
 /*
  * TDX module SEAMCALL leaf function error codes
  */
+#define TDX_SUCCESS		0ULL
 #define TDX_RND_NO_ENTROPY	0x8000020300000000ULL
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 94689aef44a65..262b9b64a50ba 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -21,6 +21,50 @@ static u32 tdx_global_keyid __ro_after_init;
 static u32 tdx_guest_keyid_start __ro_after_init;
 static u32 tdx_nr_guest_keyids __ro_after_init;
 
+typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args);
+
+static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args)
+{
+	pr_err("SEAMCALL (0x%016llx) failed: 0x%016llx\n", fn, err);
+}
+
+static inline void seamcall_err_ret(u64 fn, u64 err,
+				    struct tdx_module_args *args)
+{
+	seamcall_err(fn, err, args);
+	pr_err("RCX 0x%016llx RDX 0x%016llx R08 0x%016llx\n",
+			args->rcx, args->rdx, args->r8);
+	pr_err("R09 0x%016llx R10 0x%016llx R11 0x%016llx\n",
+			args->r9, args->r10, args->r11);
+}
+
+static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func,
+				 u64 fn, struct tdx_module_args *args)
+{
+	u64 sret = sc_retry(func, fn, args);
+
+	if (sret == TDX_SUCCESS)
+		return 0;
+
+	if (sret == TDX_SEAMCALL_VMFAILINVALID)
+		return -ENODEV;
+
+	if (sret == TDX_SEAMCALL_GP)
+		return -EOPNOTSUPP;
+
+	if (sret == TDX_SEAMCALL_UD)
+		return -EACCES;
+
+	err_func(fn, sret, args);
+	return -EIO;
+}
+
+#define seamcall_prerr(__fn, __args)						\
+	sc_retry_prerr(__seamcall, seamcall_err, (__fn), (__args))
+
+#define seamcall_prerr_ret(__fn, __args)					\
+	sc_retry_prerr(__seamcall_ret, seamcall_err_ret, (__fn), (__args))
+
 static __init int record_keyid_partitioning(u32 *tdx_keyid_start,
 					    u32 *nr_tdx_keyids)
 {
-- 
GitLab


From 6162b310bc219d18bac970dbd441d7743097d1b9 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:26 -0800
Subject: [PATCH 1008/4076] x86/virt/tdx: Add skeleton to enable TDX on demand

There are essentially two steps to get the TDX module ready:
1) Get each CPU ready to run TDX
2) Set up the shared TDX module data structures

Introduce and export (to KVM) the infrastructure to do both of these
pieces at runtime.

== Per-CPU TDX Initialization ==

Track the initialization status of each CPU with a per-cpu variable.
This avoids failures in the case of KVM module reloads and handles cases
where CPUs come online later.

Generally, the per-cpu SEAMCALLs happen first.  But there's actually one
global call that has to happen before _any_ others (TDH_SYS_INIT).  It's
analogous to the boot CPU having to do a bit of extra work just because
it happens to be the first one.  Track if _any_ CPU has done this call
and then only actually do it during the first per-cpu init.

== Shared TDX Initialization ==

Create the global state function (tdx_enable()) as a simple placeholder.
The TODO list will be pared down as functionality is added.

Use a state machine protected by mutex to make sure the work in
tdx_enable() will only be done once.  This avoids failures if the KVM
module is reloaded.

A CPU must be made ready to run TDX before it can participate in
initializing the shared parts of the module.  Any caller of tdx_enable()
need to ensure that it can never run on a CPU which is not ready to
run TDX.  It needs to be wary of CPU hotplug, preemption and the
VMX enabling state of any CPU on which it might run.

== Why runtime instead of boot time? ==

The TDX module can be initialized only once in its lifetime.  Instead
of always initializing it at boot time, this implementation chooses an
"on demand" approach to initialize TDX until there is a real need (e.g
when requested by KVM).  This approach has below pros:

1) It avoids consuming the memory that must be allocated by kernel and
given to the TDX module as metadata (~1/256th of the TDX-usable memory),
and also saves the CPU cycles of initializing the TDX module (and the
metadata) when TDX is not used at all.

2) The TDX module design allows it to be updated while the system is
running.  The update procedure shares quite a few steps with this "on
demand" initialization mechanism.  The hope is that much of "on demand"
mechanism can be shared with a future "update" mechanism.  A boot-time
TDX module implementation would not be able to share much code with the
update mechanism.

3) Making SEAMCALL requires VMX to be enabled.  Currently, only the KVM
code mucks with VMX enabling.  If the TDX module were to be initialized
separately from KVM (like at boot), the boot code would need to be
taught how to muck with VMX enabling and KVM would need to be taught how
to cope with that.  Making KVM itself responsible for TDX initialization
lets the rest of the kernel stay blissfully unaware of VMX.

[ dhansen: completely reorder/rewrite changelog ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Nikolay Borisov <nik.borisov@suse.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-6-dave.hansen%40intel.com
---
 arch/x86/include/asm/tdx.h  |   4 +
 arch/x86/virt/vmx/tdx/tdx.c | 167 ++++++++++++++++++++++++++++++++++++
 arch/x86/virt/vmx/tdx/tdx.h |  30 +++++++
 3 files changed, 201 insertions(+)
 create mode 100644 arch/x86/virt/vmx/tdx/tdx.h

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 2c0f4162fe99d..c54948e1999c0 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -111,8 +111,12 @@ static inline u64 sc_retry(sc_func_t func, u64 fn,
 #define seamcall(_fn, _args)		sc_retry(__seamcall, (_fn), (_args))
 #define seamcall_ret(_fn, _args)	sc_retry(__seamcall_ret, (_fn), (_args))
 #define seamcall_saved_ret(_fn, _args)	sc_retry(__seamcall_saved_ret, (_fn), (_args))
+int tdx_cpu_enable(void);
+int tdx_enable(void);
 #else
 static inline void tdx_init(void) { }
+static inline int tdx_cpu_enable(void) { return -ENODEV; }
+static inline int tdx_enable(void)  { return -ENODEV; }
 #endif	/* CONFIG_INTEL_TDX_HOST */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 262b9b64a50ba..ecb0df8ff8b8f 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -12,15 +12,25 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/printk.h>
+#include <linux/cpu.h>
+#include <linux/spinlock.h>
+#include <linux/percpu-defs.h>
+#include <linux/mutex.h>
 #include <asm/msr-index.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
 #include <asm/tdx.h>
+#include "tdx.h"
 
 static u32 tdx_global_keyid __ro_after_init;
 static u32 tdx_guest_keyid_start __ro_after_init;
 static u32 tdx_nr_guest_keyids __ro_after_init;
 
+static DEFINE_PER_CPU(bool, tdx_lp_initialized);
+
+static enum tdx_module_status_t tdx_module_status;
+static DEFINE_MUTEX(tdx_module_lock);
+
 typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args);
 
 static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args)
@@ -65,6 +75,163 @@ static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func,
 #define seamcall_prerr_ret(__fn, __args)					\
 	sc_retry_prerr(__seamcall_ret, seamcall_err_ret, (__fn), (__args))
 
+/*
+ * Do the module global initialization once and return its result.
+ * It can be done on any cpu.  It's always called with interrupts
+ * disabled.
+ */
+static int try_init_module_global(void)
+{
+	struct tdx_module_args args = {};
+	static DEFINE_RAW_SPINLOCK(sysinit_lock);
+	static bool sysinit_done;
+	static int sysinit_ret;
+
+	lockdep_assert_irqs_disabled();
+
+	raw_spin_lock(&sysinit_lock);
+
+	if (sysinit_done)
+		goto out;
+
+	/* RCX is module attributes and all bits are reserved */
+	args.rcx = 0;
+	sysinit_ret = seamcall_prerr(TDH_SYS_INIT, &args);
+
+	/*
+	 * The first SEAMCALL also detects the TDX module, thus
+	 * it can fail due to the TDX module is not loaded.
+	 * Dump message to let the user know.
+	 */
+	if (sysinit_ret == -ENODEV)
+		pr_err("module not loaded\n");
+
+	sysinit_done = true;
+out:
+	raw_spin_unlock(&sysinit_lock);
+	return sysinit_ret;
+}
+
+/**
+ * tdx_cpu_enable - Enable TDX on local cpu
+ *
+ * Do one-time TDX module per-cpu initialization SEAMCALL (and TDX module
+ * global initialization SEAMCALL if not done) on local cpu to make this
+ * cpu be ready to run any other SEAMCALLs.
+ *
+ * Always call this function via IPI function calls.
+ *
+ * Return 0 on success, otherwise errors.
+ */
+int tdx_cpu_enable(void)
+{
+	struct tdx_module_args args = {};
+	int ret;
+
+	if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM))
+		return -ENODEV;
+
+	lockdep_assert_irqs_disabled();
+
+	if (__this_cpu_read(tdx_lp_initialized))
+		return 0;
+
+	/*
+	 * The TDX module global initialization is the very first step
+	 * to enable TDX.  Need to do it first (if hasn't been done)
+	 * before the per-cpu initialization.
+	 */
+	ret = try_init_module_global();
+	if (ret)
+		return ret;
+
+	ret = seamcall_prerr(TDH_SYS_LP_INIT, &args);
+	if (ret)
+		return ret;
+
+	__this_cpu_write(tdx_lp_initialized, true);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tdx_cpu_enable);
+
+static int init_tdx_module(void)
+{
+	/*
+	 * TODO:
+	 *
+	 *  - Build the list of TDX-usable memory regions.
+	 *  - Get TDX module "TD Memory Region" (TDMR) global metadata.
+	 *  - Construct a list of TDMRs to cover all TDX-usable memory
+	 *    regions.
+	 *  - Configure the TDMRs and the global KeyID to the TDX module.
+	 *  - Configure the global KeyID on all packages.
+	 *  - Initialize all TDMRs.
+	 *
+	 *  Return error before all steps are done.
+	 */
+	return -EINVAL;
+}
+
+static int __tdx_enable(void)
+{
+	int ret;
+
+	ret = init_tdx_module();
+	if (ret) {
+		pr_err("module initialization failed (%d)\n", ret);
+		tdx_module_status = TDX_MODULE_ERROR;
+		return ret;
+	}
+
+	pr_info("module initialized\n");
+	tdx_module_status = TDX_MODULE_INITIALIZED;
+
+	return 0;
+}
+
+/**
+ * tdx_enable - Enable TDX module to make it ready to run TDX guests
+ *
+ * This function assumes the caller has: 1) held read lock of CPU hotplug
+ * lock to prevent any new cpu from becoming online; 2) done both VMXON
+ * and tdx_cpu_enable() on all online cpus.
+ *
+ * This function can be called in parallel by multiple callers.
+ *
+ * Return 0 if TDX is enabled successfully, otherwise error.
+ */
+int tdx_enable(void)
+{
+	int ret;
+
+	if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM))
+		return -ENODEV;
+
+	lockdep_assert_cpus_held();
+
+	mutex_lock(&tdx_module_lock);
+
+	switch (tdx_module_status) {
+	case TDX_MODULE_UNINITIALIZED:
+		ret = __tdx_enable();
+		break;
+	case TDX_MODULE_INITIALIZED:
+		/* Already initialized, great, tell the caller. */
+		ret = 0;
+		break;
+	default:
+		/* Failed to initialize in the previous attempts */
+		ret = -EINVAL;
+		break;
+	}
+
+	mutex_unlock(&tdx_module_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdx_enable);
+
 static __init int record_keyid_partitioning(u32 *tdx_keyid_start,
 					    u32 *nr_tdx_keyids)
 {
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
new file mode 100644
index 0000000000000..a3c52270df5b7
--- /dev/null
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_VIRT_TDX_H
+#define _X86_VIRT_TDX_H
+
+/*
+ * This file contains both macros and data structures defined by the TDX
+ * architecture and Linux defined software data structures and functions.
+ * The two should not be mixed together for better readability.  The
+ * architectural definitions come first.
+ */
+
+/*
+ * TDX module SEAMCALL leaf functions
+ */
+#define TDH_SYS_INIT		33
+#define TDH_SYS_LP_INIT		35
+
+/*
+ * Do not put any hardware-defined TDX structure representations below
+ * this comment!
+ */
+
+/* Kernel defined TDX module status during module initialization. */
+enum tdx_module_status_t {
+	TDX_MODULE_UNINITIALIZED,
+	TDX_MODULE_INITIALIZED,
+	TDX_MODULE_ERROR
+};
+
+#endif
-- 
GitLab


From abe8dbab8f9f8370c26e7b79b49ed795c1b6b70f Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:27 -0800
Subject: [PATCH 1009/4076] x86/virt/tdx: Use all system memory when
 initializing TDX module as TDX memory

Start to transit out the "multi-steps" to initialize the TDX module.

TDX provides increased levels of memory confidentiality and integrity.
This requires special hardware support for features like memory
encryption and storage of memory integrity checksums.  Not all memory
satisfies these requirements.

As a result, TDX introduced the concept of a "Convertible Memory Region"
(CMR).  During boot, the firmware builds a list of all of the memory
ranges which can provide the TDX security guarantees.  The list of these
ranges is available to the kernel by querying the TDX module.

CMRs tell the kernel which memory is TDX compatible.  The kernel needs
to build a list of memory regions (out of CMRs) as "TDX-usable" memory
and pass them to the TDX module.  Once this is done, those "TDX-usable"
memory regions are fixed during module's lifetime.

To keep things simple, assume that all TDX-protected memory will come
from the page allocator.  Make sure all pages in the page allocator
*are* TDX-usable memory.

As TDX-usable memory is a fixed configuration, take a snapshot of the
memory configuration from memblocks at the time of module initialization
(memblocks are modified on memory hotplug).  This snapshot is used to
enable TDX support for *this* memory configuration only.  Use a memory
hotplug notifier to ensure that no other RAM can be added outside of
this configuration.

This approach requires all memblock memory regions at the time of module
initialization to be TDX convertible memory to work, otherwise module
initialization will fail in a later SEAMCALL when passing those regions
to the module.  This approach works when all boot-time "system RAM" is
TDX convertible memory and no non-TDX-convertible memory is hot-added
to the core-mm before module initialization.

For instance, on the first generation of TDX machines, both CXL memory
and NVDIMM are not TDX convertible memory.  Using kmem driver to hot-add
any CXL memory or NVDIMM to the core-mm before module initialization
will result in failure to initialize the module.  The SEAMCALL error
code will be available in the dmesg to help user to understand the
failure.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-7-dave.hansen%40intel.com
---
 arch/x86/Kconfig            |   1 +
 arch/x86/kernel/setup.c     |   2 +
 arch/x86/virt/vmx/tdx/tdx.c | 167 +++++++++++++++++++++++++++++++++++-
 arch/x86/virt/vmx/tdx/tdx.h |   6 ++
 4 files changed, 174 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index eb6e63956d51e..2c69ef8448059 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1971,6 +1971,7 @@ config INTEL_TDX_HOST
 	depends on X86_64
 	depends on KVM_INTEL
 	depends on X86_X2APIC
+	select ARCH_KEEP_MEMBLOCK
 	help
 	  Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
 	  host and certain physical attacks.  This option enables necessary TDX
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1526747bedf2f..9597c002b3c49 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1033,6 +1033,8 @@ void __init setup_arch(char **cmdline_p)
 	 *
 	 * Moreover, on machines with SandyBridge graphics or in setups that use
 	 * crashkernel the entire 1M is reserved anyway.
+	 *
+	 * Note the host kernel TDX also requires the first 1MB being reserved.
 	 */
 	x86_platform.realmode_reserve();
 
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index ecb0df8ff8b8f..6a3585bc8aa48 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -16,6 +16,12 @@
 #include <linux/spinlock.h>
 #include <linux/percpu-defs.h>
 #include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/memblock.h>
+#include <linux/memory.h>
+#include <linux/minmax.h>
+#include <linux/sizes.h>
+#include <linux/pfn.h>
 #include <asm/msr-index.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
@@ -31,6 +37,9 @@ static DEFINE_PER_CPU(bool, tdx_lp_initialized);
 static enum tdx_module_status_t tdx_module_status;
 static DEFINE_MUTEX(tdx_module_lock);
 
+/* All TDX-usable memory regions.  Protected by mem_hotplug_lock. */
+static LIST_HEAD(tdx_memlist);
+
 typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args);
 
 static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args)
@@ -155,12 +164,102 @@ int tdx_cpu_enable(void)
 }
 EXPORT_SYMBOL_GPL(tdx_cpu_enable);
 
+/*
+ * Add a memory region as a TDX memory block.  The caller must make sure
+ * all memory regions are added in address ascending order and don't
+ * overlap.
+ */
+static int add_tdx_memblock(struct list_head *tmb_list, unsigned long start_pfn,
+			    unsigned long end_pfn)
+{
+	struct tdx_memblock *tmb;
+
+	tmb = kmalloc(sizeof(*tmb), GFP_KERNEL);
+	if (!tmb)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&tmb->list);
+	tmb->start_pfn = start_pfn;
+	tmb->end_pfn = end_pfn;
+
+	/* @tmb_list is protected by mem_hotplug_lock */
+	list_add_tail(&tmb->list, tmb_list);
+	return 0;
+}
+
+static void free_tdx_memlist(struct list_head *tmb_list)
+{
+	/* @tmb_list is protected by mem_hotplug_lock */
+	while (!list_empty(tmb_list)) {
+		struct tdx_memblock *tmb = list_first_entry(tmb_list,
+				struct tdx_memblock, list);
+
+		list_del(&tmb->list);
+		kfree(tmb);
+	}
+}
+
+/*
+ * Ensure that all memblock memory regions are convertible to TDX
+ * memory.  Once this has been established, stash the memblock
+ * ranges off in a secondary structure because memblock is modified
+ * in memory hotplug while TDX memory regions are fixed.
+ */
+static int build_tdx_memlist(struct list_head *tmb_list)
+{
+	unsigned long start_pfn, end_pfn;
+	int i, ret;
+
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+		/*
+		 * The first 1MB is not reported as TDX convertible memory.
+		 * Although the first 1MB is always reserved and won't end up
+		 * to the page allocator, it is still in memblock's memory
+		 * regions.  Skip them manually to exclude them as TDX memory.
+		 */
+		start_pfn = max(start_pfn, PHYS_PFN(SZ_1M));
+		if (start_pfn >= end_pfn)
+			continue;
+
+		/*
+		 * Add the memory regions as TDX memory.  The regions in
+		 * memblock has already guaranteed they are in address
+		 * ascending order and don't overlap.
+		 */
+		ret = add_tdx_memblock(tmb_list, start_pfn, end_pfn);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	free_tdx_memlist(tmb_list);
+	return ret;
+}
+
 static int init_tdx_module(void)
 {
+	int ret;
+
+	/*
+	 * To keep things simple, assume that all TDX-protected memory
+	 * will come from the page allocator.  Make sure all pages in the
+	 * page allocator are TDX-usable memory.
+	 *
+	 * Build the list of "TDX-usable" memory regions which cover all
+	 * pages in the page allocator to guarantee that.  Do it while
+	 * holding mem_hotplug_lock read-lock as the memory hotplug code
+	 * path reads the @tdx_memlist to reject any new memory.
+	 */
+	get_online_mems();
+
+	ret = build_tdx_memlist(&tdx_memlist);
+	if (ret)
+		goto out_put_tdxmem;
+
 	/*
 	 * TODO:
 	 *
-	 *  - Build the list of TDX-usable memory regions.
 	 *  - Get TDX module "TD Memory Region" (TDMR) global metadata.
 	 *  - Construct a list of TDMRs to cover all TDX-usable memory
 	 *    regions.
@@ -170,7 +269,14 @@ static int init_tdx_module(void)
 	 *
 	 *  Return error before all steps are done.
 	 */
-	return -EINVAL;
+	ret = -EINVAL;
+out_put_tdxmem:
+	/*
+	 * @tdx_memlist is written here and read at memory hotplug time.
+	 * Lock out memory hotplug code while building it.
+	 */
+	put_online_mems();
+	return ret;
 }
 
 static int __tdx_enable(void)
@@ -257,6 +363,56 @@ static __init int record_keyid_partitioning(u32 *tdx_keyid_start,
 	return 0;
 }
 
+static bool is_tdx_memory(unsigned long start_pfn, unsigned long end_pfn)
+{
+	struct tdx_memblock *tmb;
+
+	/*
+	 * This check assumes that the start_pfn<->end_pfn range does not
+	 * cross multiple @tdx_memlist entries.  A single memory online
+	 * event across multiple memblocks (from which @tdx_memlist
+	 * entries are derived at the time of module initialization) is
+	 * not possible.  This is because memory offline/online is done
+	 * on granularity of 'struct memory_block', and the hotpluggable
+	 * memory region (one memblock) must be multiple of memory_block.
+	 */
+	list_for_each_entry(tmb, &tdx_memlist, list) {
+		if (start_pfn >= tmb->start_pfn && end_pfn <= tmb->end_pfn)
+			return true;
+	}
+	return false;
+}
+
+static int tdx_memory_notifier(struct notifier_block *nb, unsigned long action,
+			       void *v)
+{
+	struct memory_notify *mn = v;
+
+	if (action != MEM_GOING_ONLINE)
+		return NOTIFY_OK;
+
+	/*
+	 * Empty list means TDX isn't enabled.  Allow any memory
+	 * to go online.
+	 */
+	if (list_empty(&tdx_memlist))
+		return NOTIFY_OK;
+
+	/*
+	 * The TDX memory configuration is static and can not be
+	 * changed.  Reject onlining any memory which is outside of
+	 * the static configuration whether it supports TDX or not.
+	 */
+	if (is_tdx_memory(mn->start_pfn, mn->start_pfn + mn->nr_pages))
+		return NOTIFY_OK;
+
+	return NOTIFY_BAD;
+}
+
+static struct notifier_block tdx_memory_nb = {
+	.notifier_call = tdx_memory_notifier,
+};
+
 void __init tdx_init(void)
 {
 	u32 tdx_keyid_start, nr_tdx_keyids;
@@ -280,6 +436,13 @@ void __init tdx_init(void)
 		return;
 	}
 
+	err = register_memory_notifier(&tdx_memory_nb);
+	if (err) {
+		pr_err("initialization failed: register_memory_notifier() failed (%d)\n",
+				err);
+		return;
+	}
+
 	/*
 	 * Just use the first TDX KeyID as the 'global KeyID' and
 	 * leave the rest for TDX guests.
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index a3c52270df5b7..c11e0a7ca664b 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -27,4 +27,10 @@ enum tdx_module_status_t {
 	TDX_MODULE_ERROR
 };
 
+struct tdx_memblock {
+	struct list_head list;
+	unsigned long start_pfn;
+	unsigned long end_pfn;
+};
+
 #endif
-- 
GitLab


From cf72bc481634b7c4cd780b6338f222e2892b0232 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:28 -0800
Subject: [PATCH 1010/4076] x86/virt/tdx: Get module global metadata for module
 initialization

The TDX module global metadata provides system-wide information about
the module.

TL;DR:

Use the TDH.SYS.RD SEAMCALL to tell if the module is good or not.

Long Version:

1) Only initialize TDX module with version 1.5 and later

TDX module 1.0 has some compatibility issues with the later versions of
module, as documented in the "Intel TDX module ABI incompatibilities
between TDX1.0 and TDX1.5" spec.  Don't bother with module versions that
do not have a stable ABI.

2) Get the essential global metadata for module initialization

TDX reports a list of "Convertible Memory Region" (CMR) to tell the
kernel which memory is TDX compatible.  The kernel needs to build a list
of memory regions (out of CMRs) as "TDX-usable" memory and pass them to
the TDX module.  The kernel does this by constructing a list of "TD
Memory Regions" (TDMRs) to cover all these memory regions and passing
them to the TDX module.

Each TDMR is a TDX architectural data structure containing the memory
region that the TDMR covers, plus the information to track (within this
TDMR):
  a) the "Physical Address Metadata Table" (PAMT) to track each TDX
     memory page's status (such as which TDX guest "owns" a given page,
     and
  b) the "reserved areas" to tell memory holes that cannot be used as
     TDX memory.

The kernel needs to get below metadata from the TDX module to build the
list of TDMRs:
  a) the maximum number of supported TDMRs
  b) the maximum number of supported reserved areas per TDMR and,
  c) the PAMT entry size for each TDX-supported page size.

== Implementation ==

The TDX module has two modes of fetching the metadata: a one field at
a time, or all in one blob.  Use the field at a time for now.  It is
slower, but there just are not enough fields now to justify the
complexity of extra unpacking.

The err_free_tdxmem=>out_put_tdxmem goto looks wonky by itself.  But
it is the first of a bunch of error handling that will get stuck at
its site.

[ dhansen: clean up changelog and add a struct to map between
	   the TDX module fields and 'struct tdx_tdmr_sysinfo' ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-8-dave.hansen%40intel.com
---
 arch/x86/include/asm/shared/tdx.h |  1 +
 arch/x86/virt/vmx/tdx/tdx.c       | 88 ++++++++++++++++++++++++++++++-
 arch/x86/virt/vmx/tdx/tdx.h       | 39 ++++++++++++++
 3 files changed, 127 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index a4036149c4847..fdfd41511b021 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -59,6 +59,7 @@
 #define TDX_PS_4K	0
 #define TDX_PS_2M	1
 #define TDX_PS_1G	2
+#define TDX_PS_NR	(TDX_PS_1G + 1)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 6a3585bc8aa48..e76ad7c2e53b2 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -237,8 +237,85 @@ err:
 	return ret;
 }
 
+static int read_sys_metadata_field(u64 field_id, u64 *data)
+{
+	struct tdx_module_args args = {};
+	int ret;
+
+	/*
+	 * TDH.SYS.RD -- reads one global metadata field
+	 *  - RDX (in): the field to read
+	 *  - R8 (out): the field data
+	 */
+	args.rdx = field_id;
+	ret = seamcall_prerr_ret(TDH_SYS_RD, &args);
+	if (ret)
+		return ret;
+
+	*data = args.r8;
+
+	return 0;
+}
+
+static int read_sys_metadata_field16(u64 field_id,
+				     int offset,
+				     struct tdx_tdmr_sysinfo *ts)
+{
+	u16 *ts_member = ((void *)ts) + offset;
+	u64 tmp;
+	int ret;
+
+	if (WARN_ON_ONCE(MD_FIELD_ID_ELE_SIZE_CODE(field_id) !=
+			MD_FIELD_ID_ELE_SIZE_16BIT))
+		return -EINVAL;
+
+	ret = read_sys_metadata_field(field_id, &tmp);
+	if (ret)
+		return ret;
+
+	*ts_member = tmp;
+
+	return 0;
+}
+
+struct field_mapping {
+	u64 field_id;
+	int offset;
+};
+
+#define TD_SYSINFO_MAP(_field_id, _offset) \
+	{ .field_id = MD_FIELD_ID_##_field_id,	   \
+	  .offset   = offsetof(struct tdx_tdmr_sysinfo, _offset) }
+
+/* Map TD_SYSINFO fields into 'struct tdx_tdmr_sysinfo': */
+static const struct field_mapping fields[] = {
+	TD_SYSINFO_MAP(MAX_TDMRS,	      max_tdmrs),
+	TD_SYSINFO_MAP(MAX_RESERVED_PER_TDMR, max_reserved_per_tdmr),
+	TD_SYSINFO_MAP(PAMT_4K_ENTRY_SIZE,    pamt_entry_size[TDX_PS_4K]),
+	TD_SYSINFO_MAP(PAMT_2M_ENTRY_SIZE,    pamt_entry_size[TDX_PS_2M]),
+	TD_SYSINFO_MAP(PAMT_1G_ENTRY_SIZE,    pamt_entry_size[TDX_PS_1G]),
+};
+
+static int get_tdx_tdmr_sysinfo(struct tdx_tdmr_sysinfo *tdmr_sysinfo)
+{
+	int ret;
+	int i;
+
+	/* Populate 'tdmr_sysinfo' fields using the mapping structure above: */
+	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		ret = read_sys_metadata_field16(fields[i].field_id,
+						fields[i].offset,
+						tdmr_sysinfo);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int init_tdx_module(void)
 {
+	struct tdx_tdmr_sysinfo tdmr_sysinfo;
 	int ret;
 
 	/*
@@ -257,10 +334,13 @@ static int init_tdx_module(void)
 	if (ret)
 		goto out_put_tdxmem;
 
+	ret = get_tdx_tdmr_sysinfo(&tdmr_sysinfo);
+	if (ret)
+		goto err_free_tdxmem;
+
 	/*
 	 * TODO:
 	 *
-	 *  - Get TDX module "TD Memory Region" (TDMR) global metadata.
 	 *  - Construct a list of TDMRs to cover all TDX-usable memory
 	 *    regions.
 	 *  - Configure the TDMRs and the global KeyID to the TDX module.
@@ -270,6 +350,8 @@ static int init_tdx_module(void)
 	 *  Return error before all steps are done.
 	 */
 	ret = -EINVAL;
+	if (ret)
+		goto err_free_tdxmem;
 out_put_tdxmem:
 	/*
 	 * @tdx_memlist is written here and read at memory hotplug time.
@@ -277,6 +359,10 @@ out_put_tdxmem:
 	 */
 	put_online_mems();
 	return ret;
+
+err_free_tdxmem:
+	free_tdx_memlist(&tdx_memlist);
+	goto out_put_tdxmem;
 }
 
 static int __tdx_enable(void)
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index c11e0a7ca664b..29cdf5ea5544a 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -2,6 +2,8 @@
 #ifndef _X86_VIRT_TDX_H
 #define _X86_VIRT_TDX_H
 
+#include <linux/bits.h>
+
 /*
  * This file contains both macros and data structures defined by the TDX
  * architecture and Linux defined software data structures and functions.
@@ -13,8 +15,38 @@
  * TDX module SEAMCALL leaf functions
  */
 #define TDH_SYS_INIT		33
+#define TDH_SYS_RD		34
 #define TDH_SYS_LP_INIT		35
 
+/*
+ * Global scope metadata field ID.
+ *
+ * See Table "Global Scope Metadata", TDX module 1.5 ABI spec.
+ */
+#define MD_FIELD_ID_MAX_TDMRS			0x9100000100000008ULL
+#define MD_FIELD_ID_MAX_RESERVED_PER_TDMR	0x9100000100000009ULL
+#define MD_FIELD_ID_PAMT_4K_ENTRY_SIZE		0x9100000100000010ULL
+#define MD_FIELD_ID_PAMT_2M_ENTRY_SIZE		0x9100000100000011ULL
+#define MD_FIELD_ID_PAMT_1G_ENTRY_SIZE		0x9100000100000012ULL
+
+/*
+ * Sub-field definition of metadata field ID.
+ *
+ * See Table "MD_FIELD_ID (Metadata Field Identifier / Sequence Header)
+ * Definition", TDX module 1.5 ABI spec.
+ *
+ *  - Bit 33:32: ELEMENT_SIZE_CODE -- size of a single element of metadata
+ *
+ *	0: 8 bits
+ *	1: 16 bits
+ *	2: 32 bits
+ *	3: 64 bits
+ */
+#define MD_FIELD_ID_ELE_SIZE_CODE(_field_id)	\
+		(((_field_id) & GENMASK_ULL(33, 32)) >> 32)
+
+#define MD_FIELD_ID_ELE_SIZE_16BIT	1
+
 /*
  * Do not put any hardware-defined TDX structure representations below
  * this comment!
@@ -33,4 +65,11 @@ struct tdx_memblock {
 	unsigned long end_pfn;
 };
 
+/* "TDMR info" part of "Global Scope Metadata" for constructing TDMRs */
+struct tdx_tdmr_sysinfo {
+	u16 max_tdmrs;
+	u16 max_reserved_per_tdmr;
+	u16 pamt_entry_size[TDX_PS_NR];
+};
+
 #endif
-- 
GitLab


From 5173d3c5d018161aca17d4ac95367cf832c7fff1 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:29 -0800
Subject: [PATCH 1011/4076] x86/virt/tdx: Add placeholder to construct TDMRs to
 cover all TDX memory regions

After the kernel selects all TDX-usable memory regions, the kernel needs
to pass those regions to the TDX module via data structure "TD Memory
Region" (TDMR).

Add a placeholder to construct a list of TDMRs (in multiple steps) to
cover all TDX-usable memory regions.

=== Long Version ===

TDX provides increased levels of memory confidentiality and integrity.
This requires special hardware support for features like memory
encryption and storage of memory integrity checksums.  Not all memory
satisfies these requirements.

As a result, TDX introduced the concept of a "Convertible Memory Region"
(CMR).  During boot, the firmware builds a list of all of the memory
ranges which can provide the TDX security guarantees.  The list of these
ranges is available to the kernel by querying the TDX module.

The TDX architecture needs additional metadata to record things like
which TD guest "owns" a given page of memory.  This metadata essentially
serves as the 'struct page' for the TDX module.  The space for this
metadata is not reserved by the hardware up front and must be allocated
by the kernel and given to the TDX module.

Since this metadata consumes space, the VMM can choose whether or not to
allocate it for a given area of convertible memory.  If it chooses not
to, the memory cannot receive TDX protections and can not be used by TDX
guests as private memory.

For every memory region that the VMM wants to use as TDX memory, it sets
up a "TD Memory Region" (TDMR).  Each TDMR represents a physically
contiguous convertible range and must also have its own physically
contiguous metadata table, referred to as a Physical Address Metadata
Table (PAMT), to track status for each page in the TDMR range.

Unlike a CMR, each TDMR requires 1G granularity and alignment.  To
support physical RAM areas that don't meet those strict requirements,
each TDMR permits a number of internal "reserved areas" which can be
placed over memory holes.  If PAMT metadata is placed within a TDMR it
must be covered by one of these reserved areas.

Let's summarize the concepts:

 CMR - Firmware-enumerated physical ranges that support TDX.  CMRs are
       4K aligned.
TDMR - Physical address range which is chosen by the kernel to support
       TDX.  1G granularity and alignment required.  Each TDMR has
       reserved areas where TDX memory holes and overlapping PAMTs can
       be represented.
PAMT - Physically contiguous TDX metadata.  One table for each page size
       per TDMR.  Roughly 1/256th of TDMR in size.  256G TDMR = ~1G
       PAMT.

As one step of initializing the TDX module, the kernel configures
TDX-usable memory regions by passing a list of TDMRs to the TDX module.

Constructing the list of TDMRs consists below steps:

1) Fill out TDMRs to cover all memory regions that the TDX module will
   use for TD memory.
2) Allocate and set up PAMT for each TDMR.
3) Designate reserved areas for each TDMR.

Add a placeholder to construct TDMRs to do the above steps.  To keep
things simple, just allocate enough space to hold maximum number of
TDMRs up front.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-9-dave.hansen%40intel.com
---
 arch/x86/virt/vmx/tdx/tdx.c | 93 +++++++++++++++++++++++++++++++++++--
 arch/x86/virt/vmx/tdx/tdx.h | 33 +++++++++++++
 2 files changed, 123 insertions(+), 3 deletions(-)

diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index e76ad7c2e53b2..eeb7bf8c37427 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -22,6 +22,7 @@
 #include <linux/minmax.h>
 #include <linux/sizes.h>
 #include <linux/pfn.h>
+#include <linux/align.h>
 #include <asm/msr-index.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
@@ -34,6 +35,8 @@ static u32 tdx_nr_guest_keyids __ro_after_init;
 
 static DEFINE_PER_CPU(bool, tdx_lp_initialized);
 
+static struct tdmr_info_list tdx_tdmr_list;
+
 static enum tdx_module_status_t tdx_module_status;
 static DEFINE_MUTEX(tdx_module_lock);
 
@@ -313,6 +316,80 @@ static int get_tdx_tdmr_sysinfo(struct tdx_tdmr_sysinfo *tdmr_sysinfo)
 	return 0;
 }
 
+/* Calculate the actual TDMR size */
+static int tdmr_size_single(u16 max_reserved_per_tdmr)
+{
+	int tdmr_sz;
+
+	/*
+	 * The actual size of TDMR depends on the maximum
+	 * number of reserved areas.
+	 */
+	tdmr_sz = sizeof(struct tdmr_info);
+	tdmr_sz += sizeof(struct tdmr_reserved_area) * max_reserved_per_tdmr;
+
+	return ALIGN(tdmr_sz, TDMR_INFO_ALIGNMENT);
+}
+
+static int alloc_tdmr_list(struct tdmr_info_list *tdmr_list,
+			   struct tdx_tdmr_sysinfo *tdmr_sysinfo)
+{
+	size_t tdmr_sz, tdmr_array_sz;
+	void *tdmr_array;
+
+	tdmr_sz = tdmr_size_single(tdmr_sysinfo->max_reserved_per_tdmr);
+	tdmr_array_sz = tdmr_sz * tdmr_sysinfo->max_tdmrs;
+
+	/*
+	 * To keep things simple, allocate all TDMRs together.
+	 * The buffer needs to be physically contiguous to make
+	 * sure each TDMR is physically contiguous.
+	 */
+	tdmr_array = alloc_pages_exact(tdmr_array_sz,
+			GFP_KERNEL | __GFP_ZERO);
+	if (!tdmr_array)
+		return -ENOMEM;
+
+	tdmr_list->tdmrs = tdmr_array;
+
+	/*
+	 * Keep the size of TDMR to find the target TDMR
+	 * at a given index in the TDMR list.
+	 */
+	tdmr_list->tdmr_sz = tdmr_sz;
+	tdmr_list->max_tdmrs = tdmr_sysinfo->max_tdmrs;
+	tdmr_list->nr_consumed_tdmrs = 0;
+
+	return 0;
+}
+
+static void free_tdmr_list(struct tdmr_info_list *tdmr_list)
+{
+	free_pages_exact(tdmr_list->tdmrs,
+			tdmr_list->max_tdmrs * tdmr_list->tdmr_sz);
+}
+
+/*
+ * Construct a list of TDMRs on the preallocated space in @tdmr_list
+ * to cover all TDX memory regions in @tmb_list based on the TDX module
+ * TDMR global information in @tdmr_sysinfo.
+ */
+static int construct_tdmrs(struct list_head *tmb_list,
+			   struct tdmr_info_list *tdmr_list,
+			   struct tdx_tdmr_sysinfo *tdmr_sysinfo)
+{
+	/*
+	 * TODO:
+	 *
+	 *  - Fill out TDMRs to cover all TDX memory regions.
+	 *  - Allocate and set up PAMTs for each TDMR.
+	 *  - Designate reserved areas for each TDMR.
+	 *
+	 * Return -EINVAL until constructing TDMRs is done
+	 */
+	return -EINVAL;
+}
+
 static int init_tdx_module(void)
 {
 	struct tdx_tdmr_sysinfo tdmr_sysinfo;
@@ -338,11 +415,19 @@ static int init_tdx_module(void)
 	if (ret)
 		goto err_free_tdxmem;
 
+	/* Allocate enough space for constructing TDMRs */
+	ret = alloc_tdmr_list(&tdx_tdmr_list, &tdmr_sysinfo);
+	if (ret)
+		goto err_free_tdxmem;
+
+	/* Cover all TDX-usable memory regions in TDMRs */
+	ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &tdmr_sysinfo);
+	if (ret)
+		goto err_free_tdmrs;
+
 	/*
 	 * TODO:
 	 *
-	 *  - Construct a list of TDMRs to cover all TDX-usable memory
-	 *    regions.
 	 *  - Configure the TDMRs and the global KeyID to the TDX module.
 	 *  - Configure the global KeyID on all packages.
 	 *  - Initialize all TDMRs.
@@ -351,7 +436,7 @@ static int init_tdx_module(void)
 	 */
 	ret = -EINVAL;
 	if (ret)
-		goto err_free_tdxmem;
+		goto err_free_tdmrs;
 out_put_tdxmem:
 	/*
 	 * @tdx_memlist is written here and read at memory hotplug time.
@@ -360,6 +445,8 @@ out_put_tdxmem:
 	put_online_mems();
 	return ret;
 
+err_free_tdmrs:
+	free_tdmr_list(&tdx_tdmr_list);
 err_free_tdxmem:
 	free_tdx_memlist(&tdx_memlist);
 	goto out_put_tdxmem;
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index 29cdf5ea5544a..9b6b5d70804f4 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -47,6 +47,30 @@
 
 #define MD_FIELD_ID_ELE_SIZE_16BIT	1
 
+struct tdmr_reserved_area {
+	u64 offset;
+	u64 size;
+} __packed;
+
+#define TDMR_INFO_ALIGNMENT	512
+
+struct tdmr_info {
+	u64 base;
+	u64 size;
+	u64 pamt_1g_base;
+	u64 pamt_1g_size;
+	u64 pamt_2m_base;
+	u64 pamt_2m_size;
+	u64 pamt_4k_base;
+	u64 pamt_4k_size;
+	/*
+	 * The actual number of reserved areas depends on the value of
+	 * field MD_FIELD_ID_MAX_RESERVED_PER_TDMR in the TDX module
+	 * global metadata.
+	 */
+	DECLARE_FLEX_ARRAY(struct tdmr_reserved_area, reserved_areas);
+} __packed __aligned(TDMR_INFO_ALIGNMENT);
+
 /*
  * Do not put any hardware-defined TDX structure representations below
  * this comment!
@@ -72,4 +96,13 @@ struct tdx_tdmr_sysinfo {
 	u16 pamt_entry_size[TDX_PS_NR];
 };
 
+struct tdmr_info_list {
+	void *tdmrs;	/* Flexible array to hold 'tdmr_info's */
+	int nr_consumed_tdmrs;	/* How many 'tdmr_info's are in use */
+
+	/* Metadata for finding target 'tdmr_info' and freeing @tdmrs */
+	int tdmr_sz;	/* Size of one 'tdmr_info' */
+	int max_tdmrs;	/* How many 'tdmr_info's are allocated */
+};
+
 #endif
-- 
GitLab


From f3338ac15931075ef8b81145f5de128158a8dc8e Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:30 -0800
Subject: [PATCH 1012/4076] x86/virt/tdx: Fill out TDMRs to cover all TDX
 memory regions

Start to transit out the "multi-steps" to construct a list of "TD Memory
Regions" (TDMRs) to cover all TDX-usable memory regions.

The kernel configures TDX-usable memory regions by passing a list of
TDMRs "TD Memory Regions" (TDMRs) to the TDX module.  Each TDMR contains
the information of the base/size of a memory region, the base/size of the
associated Physical Address Metadata Table (PAMT) and a list of reserved
areas in the region.

Do the first step to fill out a number of TDMRs to cover all TDX memory
regions.  To keep it simple, always try to use one TDMR for each memory
region.  As the first step only set up the base/size for each TDMR.

Each TDMR must be 1G aligned and the size must be in 1G granularity.
This implies that one TDMR could cover multiple memory regions.  If a
memory region spans the 1GB boundary and the former part is already
covered by the previous TDMR, just use a new TDMR for the remaining
part.

TDX only supports a limited number of TDMRs.  Disable TDX if all TDMRs
are consumed but there is more memory region to cover.

There are fancier things that could be done like trying to merge
adjacent TDMRs.  This would allow more pathological memory layouts to be
supported.  But, current systems are not even close to exhausting the
existing TDMR resources in practice.  For now, keep it simple.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-10-dave.hansen%40intel.com
---
 arch/x86/virt/vmx/tdx/tdx.c | 103 +++++++++++++++++++++++++++++++++++-
 arch/x86/virt/vmx/tdx/tdx.h |   3 ++
 2 files changed, 105 insertions(+), 1 deletion(-)

diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index eeb7bf8c37427..d7f928713b6c9 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -369,6 +369,102 @@ static void free_tdmr_list(struct tdmr_info_list *tdmr_list)
 			tdmr_list->max_tdmrs * tdmr_list->tdmr_sz);
 }
 
+/* Get the TDMR from the list at the given index. */
+static struct tdmr_info *tdmr_entry(struct tdmr_info_list *tdmr_list,
+				    int idx)
+{
+	int tdmr_info_offset = tdmr_list->tdmr_sz * idx;
+
+	return (void *)tdmr_list->tdmrs + tdmr_info_offset;
+}
+
+#define TDMR_ALIGNMENT		SZ_1G
+#define TDMR_ALIGN_DOWN(_addr)	ALIGN_DOWN((_addr), TDMR_ALIGNMENT)
+#define TDMR_ALIGN_UP(_addr)	ALIGN((_addr), TDMR_ALIGNMENT)
+
+static inline u64 tdmr_end(struct tdmr_info *tdmr)
+{
+	return tdmr->base + tdmr->size;
+}
+
+/*
+ * Take the memory referenced in @tmb_list and populate the
+ * preallocated @tdmr_list, following all the special alignment
+ * and size rules for TDMR.
+ */
+static int fill_out_tdmrs(struct list_head *tmb_list,
+			  struct tdmr_info_list *tdmr_list)
+{
+	struct tdx_memblock *tmb;
+	int tdmr_idx = 0;
+
+	/*
+	 * Loop over TDX memory regions and fill out TDMRs to cover them.
+	 * To keep it simple, always try to use one TDMR to cover one
+	 * memory region.
+	 *
+	 * In practice TDX supports at least 64 TDMRs.  A 2-socket system
+	 * typically only consumes less than 10 of those.  This code is
+	 * dumb and simple and may use more TMDRs than is strictly
+	 * required.
+	 */
+	list_for_each_entry(tmb, tmb_list, list) {
+		struct tdmr_info *tdmr = tdmr_entry(tdmr_list, tdmr_idx);
+		u64 start, end;
+
+		start = TDMR_ALIGN_DOWN(PFN_PHYS(tmb->start_pfn));
+		end   = TDMR_ALIGN_UP(PFN_PHYS(tmb->end_pfn));
+
+		/*
+		 * A valid size indicates the current TDMR has already
+		 * been filled out to cover the previous memory region(s).
+		 */
+		if (tdmr->size) {
+			/*
+			 * Loop to the next if the current memory region
+			 * has already been fully covered.
+			 */
+			if (end <= tdmr_end(tdmr))
+				continue;
+
+			/* Otherwise, skip the already covered part. */
+			if (start < tdmr_end(tdmr))
+				start = tdmr_end(tdmr);
+
+			/*
+			 * Create a new TDMR to cover the current memory
+			 * region, or the remaining part of it.
+			 */
+			tdmr_idx++;
+			if (tdmr_idx >= tdmr_list->max_tdmrs) {
+				pr_warn("initialization failed: TDMRs exhausted.\n");
+				return -ENOSPC;
+			}
+
+			tdmr = tdmr_entry(tdmr_list, tdmr_idx);
+		}
+
+		tdmr->base = start;
+		tdmr->size = end - start;
+	}
+
+	/* @tdmr_idx is always the index of the last valid TDMR. */
+	tdmr_list->nr_consumed_tdmrs = tdmr_idx + 1;
+
+	/*
+	 * Warn early that kernel is about to run out of TDMRs.
+	 *
+	 * This is an indication that TDMR allocation has to be
+	 * reworked to be smarter to not run into an issue.
+	 */
+	if (tdmr_list->max_tdmrs - tdmr_list->nr_consumed_tdmrs < TDMR_NR_WARN)
+		pr_warn("consumed TDMRs reaching limit: %d used out of %d\n",
+				tdmr_list->nr_consumed_tdmrs,
+				tdmr_list->max_tdmrs);
+
+	return 0;
+}
+
 /*
  * Construct a list of TDMRs on the preallocated space in @tdmr_list
  * to cover all TDX memory regions in @tmb_list based on the TDX module
@@ -378,10 +474,15 @@ static int construct_tdmrs(struct list_head *tmb_list,
 			   struct tdmr_info_list *tdmr_list,
 			   struct tdx_tdmr_sysinfo *tdmr_sysinfo)
 {
+	int ret;
+
+	ret = fill_out_tdmrs(tmb_list, tdmr_list);
+	if (ret)
+		return ret;
+
 	/*
 	 * TODO:
 	 *
-	 *  - Fill out TDMRs to cover all TDX memory regions.
 	 *  - Allocate and set up PAMTs for each TDMR.
 	 *  - Designate reserved areas for each TDMR.
 	 *
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index 9b6b5d70804f4..f18ce1b88b0af 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -96,6 +96,9 @@ struct tdx_tdmr_sysinfo {
 	u16 pamt_entry_size[TDX_PS_NR];
 };
 
+/* Warn if kernel has less than TDMR_NR_WARN TDMRs after allocation */
+#define TDMR_NR_WARN 4
+
 struct tdmr_info_list {
 	void *tdmrs;	/* Flexible array to hold 'tdmr_info's */
 	int nr_consumed_tdmrs;	/* How many 'tdmr_info's are in use */
-- 
GitLab


From ac3a22088434e31dddda82aa473bee008df99b97 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:31 -0800
Subject: [PATCH 1013/4076] x86/virt/tdx: Allocate and set up PAMTs for TDMRs

The TDX module uses additional metadata to record things like which
guest "owns" a given page of memory.  This metadata, referred as
Physical Address Metadata Table (PAMT), essentially serves as the
'struct page' for the TDX module.  PAMTs are not reserved by hardware
up front.  They must be allocated by the kernel and then given to the
TDX module during module initialization.

TDX supports 3 page sizes: 4K, 2M, and 1G.  Each "TD Memory Region"
(TDMR) has 3 PAMTs to track the 3 supported page sizes.  Each PAMT must
be a physically contiguous area from a Convertible Memory Region (CMR).
However, the PAMTs which track pages in one TDMR do not need to reside
within that TDMR but can be anywhere in CMRs.  If one PAMT overlaps with
any TDMR, the overlapping part must be reported as a reserved area in
that particular TDMR.

Use alloc_contig_pages() since PAMT must be a physically contiguous area
and it may be potentially large (~1/256th of the size of the given TDMR).
The downside is alloc_contig_pages() may fail at runtime.  One (bad)
mitigation is to launch a TDX guest early during system boot to get
those PAMTs allocated at early time, but the only way to fix is to add a
boot option to allocate or reserve PAMTs during kernel boot.

It is imperfect but will be improved on later.

TDX only supports a limited number of reserved areas per TDMR to cover
both PAMTs and memory holes within the given TDMR.  If many PAMTs are
allocated within a single TDMR, the reserved areas may not be sufficient
to cover all of them.

Adopt the following policies when allocating PAMTs for a given TDMR:

  - Allocate three PAMTs of the TDMR in one contiguous chunk to minimize
    the total number of reserved areas consumed for PAMTs.
  - Try to first allocate PAMT from the local node of the TDMR for better
    NUMA locality.

Also dump out how many pages are allocated for PAMTs when the TDX module
is initialized successfully.  This helps answer the eternal "where did
all my memory go?" questions.

[ dhansen: merge in error handling cleanup ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-11-dave.hansen%40intel.com
---
 arch/x86/Kconfig            |   1 +
 arch/x86/virt/vmx/tdx/tdx.c | 217 +++++++++++++++++++++++++++++++++++-
 arch/x86/virt/vmx/tdx/tdx.h |   1 +
 3 files changed, 213 insertions(+), 6 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2c69ef8448059..e255d8ae5e77e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1972,6 +1972,7 @@ config INTEL_TDX_HOST
 	depends on KVM_INTEL
 	depends on X86_X2APIC
 	select ARCH_KEEP_MEMBLOCK
+	depends on CONTIG_ALLOC
 	help
 	  Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
 	  host and certain physical attacks.  This option enables necessary TDX
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index d7f928713b6c9..c2bff81245986 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -173,7 +173,7 @@ EXPORT_SYMBOL_GPL(tdx_cpu_enable);
  * overlap.
  */
 static int add_tdx_memblock(struct list_head *tmb_list, unsigned long start_pfn,
-			    unsigned long end_pfn)
+			    unsigned long end_pfn, int nid)
 {
 	struct tdx_memblock *tmb;
 
@@ -184,6 +184,7 @@ static int add_tdx_memblock(struct list_head *tmb_list, unsigned long start_pfn,
 	INIT_LIST_HEAD(&tmb->list);
 	tmb->start_pfn = start_pfn;
 	tmb->end_pfn = end_pfn;
+	tmb->nid = nid;
 
 	/* @tmb_list is protected by mem_hotplug_lock */
 	list_add_tail(&tmb->list, tmb_list);
@@ -211,9 +212,9 @@ static void free_tdx_memlist(struct list_head *tmb_list)
 static int build_tdx_memlist(struct list_head *tmb_list)
 {
 	unsigned long start_pfn, end_pfn;
-	int i, ret;
+	int i, nid, ret;
 
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
 		/*
 		 * The first 1MB is not reported as TDX convertible memory.
 		 * Although the first 1MB is always reserved and won't end up
@@ -229,7 +230,7 @@ static int build_tdx_memlist(struct list_head *tmb_list)
 		 * memblock has already guaranteed they are in address
 		 * ascending order and don't overlap.
 		 */
-		ret = add_tdx_memblock(tmb_list, start_pfn, end_pfn);
+		ret = add_tdx_memblock(tmb_list, start_pfn, end_pfn, nid);
 		if (ret)
 			goto err;
 	}
@@ -465,6 +466,202 @@ static int fill_out_tdmrs(struct list_head *tmb_list,
 	return 0;
 }
 
+/*
+ * Calculate PAMT size given a TDMR and a page size.  The returned
+ * PAMT size is always aligned up to 4K page boundary.
+ */
+static unsigned long tdmr_get_pamt_sz(struct tdmr_info *tdmr, int pgsz,
+				      u16 pamt_entry_size)
+{
+	unsigned long pamt_sz, nr_pamt_entries;
+
+	switch (pgsz) {
+	case TDX_PS_4K:
+		nr_pamt_entries = tdmr->size >> PAGE_SHIFT;
+		break;
+	case TDX_PS_2M:
+		nr_pamt_entries = tdmr->size >> PMD_SHIFT;
+		break;
+	case TDX_PS_1G:
+		nr_pamt_entries = tdmr->size >> PUD_SHIFT;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	pamt_sz = nr_pamt_entries * pamt_entry_size;
+	/* TDX requires PAMT size must be 4K aligned */
+	pamt_sz = ALIGN(pamt_sz, PAGE_SIZE);
+
+	return pamt_sz;
+}
+
+/*
+ * Locate a NUMA node which should hold the allocation of the @tdmr
+ * PAMT.  This node will have some memory covered by the TDMR.  The
+ * relative amount of memory covered is not considered.
+ */
+static int tdmr_get_nid(struct tdmr_info *tdmr, struct list_head *tmb_list)
+{
+	struct tdx_memblock *tmb;
+
+	/*
+	 * A TDMR must cover at least part of one TMB.  That TMB will end
+	 * after the TDMR begins.  But, that TMB may have started before
+	 * the TDMR.  Find the next 'tmb' that _ends_ after this TDMR
+	 * begins.  Ignore 'tmb' start addresses.  They are irrelevant.
+	 */
+	list_for_each_entry(tmb, tmb_list, list) {
+		if (tmb->end_pfn > PHYS_PFN(tdmr->base))
+			return tmb->nid;
+	}
+
+	/*
+	 * Fall back to allocating the TDMR's metadata from node 0 when
+	 * no TDX memory block can be found.  This should never happen
+	 * since TDMRs originate from TDX memory blocks.
+	 */
+	pr_warn("TDMR [0x%llx, 0x%llx): unable to find local NUMA node for PAMT allocation, fallback to use node 0.\n",
+			tdmr->base, tdmr_end(tdmr));
+	return 0;
+}
+
+/*
+ * Allocate PAMTs from the local NUMA node of some memory in @tmb_list
+ * within @tdmr, and set up PAMTs for @tdmr.
+ */
+static int tdmr_set_up_pamt(struct tdmr_info *tdmr,
+			    struct list_head *tmb_list,
+			    u16 pamt_entry_size[])
+{
+	unsigned long pamt_base[TDX_PS_NR];
+	unsigned long pamt_size[TDX_PS_NR];
+	unsigned long tdmr_pamt_base;
+	unsigned long tdmr_pamt_size;
+	struct page *pamt;
+	int pgsz, nid;
+
+	nid = tdmr_get_nid(tdmr, tmb_list);
+
+	/*
+	 * Calculate the PAMT size for each TDX supported page size
+	 * and the total PAMT size.
+	 */
+	tdmr_pamt_size = 0;
+	for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) {
+		pamt_size[pgsz] = tdmr_get_pamt_sz(tdmr, pgsz,
+					pamt_entry_size[pgsz]);
+		tdmr_pamt_size += pamt_size[pgsz];
+	}
+
+	/*
+	 * Allocate one chunk of physically contiguous memory for all
+	 * PAMTs.  This helps minimize the PAMT's use of reserved areas
+	 * in overlapped TDMRs.
+	 */
+	pamt = alloc_contig_pages(tdmr_pamt_size >> PAGE_SHIFT, GFP_KERNEL,
+			nid, &node_online_map);
+	if (!pamt)
+		return -ENOMEM;
+
+	/*
+	 * Break the contiguous allocation back up into the
+	 * individual PAMTs for each page size.
+	 */
+	tdmr_pamt_base = page_to_pfn(pamt) << PAGE_SHIFT;
+	for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) {
+		pamt_base[pgsz] = tdmr_pamt_base;
+		tdmr_pamt_base += pamt_size[pgsz];
+	}
+
+	tdmr->pamt_4k_base = pamt_base[TDX_PS_4K];
+	tdmr->pamt_4k_size = pamt_size[TDX_PS_4K];
+	tdmr->pamt_2m_base = pamt_base[TDX_PS_2M];
+	tdmr->pamt_2m_size = pamt_size[TDX_PS_2M];
+	tdmr->pamt_1g_base = pamt_base[TDX_PS_1G];
+	tdmr->pamt_1g_size = pamt_size[TDX_PS_1G];
+
+	return 0;
+}
+
+static void tdmr_get_pamt(struct tdmr_info *tdmr, unsigned long *pamt_base,
+			  unsigned long *pamt_size)
+{
+	unsigned long pamt_bs, pamt_sz;
+
+	/*
+	 * The PAMT was allocated in one contiguous unit.  The 4K PAMT
+	 * should always point to the beginning of that allocation.
+	 */
+	pamt_bs = tdmr->pamt_4k_base;
+	pamt_sz = tdmr->pamt_4k_size + tdmr->pamt_2m_size + tdmr->pamt_1g_size;
+
+	WARN_ON_ONCE((pamt_bs & ~PAGE_MASK) || (pamt_sz & ~PAGE_MASK));
+
+	*pamt_base = pamt_bs;
+	*pamt_size = pamt_sz;
+}
+
+static void tdmr_free_pamt(struct tdmr_info *tdmr)
+{
+	unsigned long pamt_base, pamt_size;
+
+	tdmr_get_pamt(tdmr, &pamt_base, &pamt_size);
+
+	/* Do nothing if PAMT hasn't been allocated for this TDMR */
+	if (!pamt_size)
+		return;
+
+	if (WARN_ON_ONCE(!pamt_base))
+		return;
+
+	free_contig_range(pamt_base >> PAGE_SHIFT, pamt_size >> PAGE_SHIFT);
+}
+
+static void tdmrs_free_pamt_all(struct tdmr_info_list *tdmr_list)
+{
+	int i;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++)
+		tdmr_free_pamt(tdmr_entry(tdmr_list, i));
+}
+
+/* Allocate and set up PAMTs for all TDMRs */
+static int tdmrs_set_up_pamt_all(struct tdmr_info_list *tdmr_list,
+				 struct list_head *tmb_list,
+				 u16 pamt_entry_size[])
+{
+	int i, ret = 0;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		ret = tdmr_set_up_pamt(tdmr_entry(tdmr_list, i), tmb_list,
+				pamt_entry_size);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	tdmrs_free_pamt_all(tdmr_list);
+	return ret;
+}
+
+static unsigned long tdmrs_count_pamt_kb(struct tdmr_info_list *tdmr_list)
+{
+	unsigned long pamt_size = 0;
+	int i;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		unsigned long base, size;
+
+		tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size);
+		pamt_size += size;
+	}
+
+	return pamt_size / 1024;
+}
+
 /*
  * Construct a list of TDMRs on the preallocated space in @tdmr_list
  * to cover all TDX memory regions in @tmb_list based on the TDX module
@@ -480,10 +677,13 @@ static int construct_tdmrs(struct list_head *tmb_list,
 	if (ret)
 		return ret;
 
+	ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list,
+			tdmr_sysinfo->pamt_entry_size);
+	if (ret)
+		return ret;
 	/*
 	 * TODO:
 	 *
-	 *  - Allocate and set up PAMTs for each TDMR.
 	 *  - Designate reserved areas for each TDMR.
 	 *
 	 * Return -EINVAL until constructing TDMRs is done
@@ -537,7 +737,10 @@ static int init_tdx_module(void)
 	 */
 	ret = -EINVAL;
 	if (ret)
-		goto err_free_tdmrs;
+		goto err_free_pamts;
+
+	pr_info("%lu KB allocated for PAMT\n", tdmrs_count_pamt_kb(&tdx_tdmr_list));
+
 out_put_tdxmem:
 	/*
 	 * @tdx_memlist is written here and read at memory hotplug time.
@@ -546,6 +749,8 @@ out_put_tdxmem:
 	put_online_mems();
 	return ret;
 
+err_free_pamts:
+	tdmrs_free_pamt_all(&tdx_tdmr_list);
 err_free_tdmrs:
 	free_tdmr_list(&tdx_tdmr_list);
 err_free_tdxmem:
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index f18ce1b88b0af..1b04efece9dbd 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -87,6 +87,7 @@ struct tdx_memblock {
 	struct list_head list;
 	unsigned long start_pfn;
 	unsigned long end_pfn;
+	int nid;
 };
 
 /* "TDMR info" part of "Global Scope Metadata" for constructing TDMRs */
-- 
GitLab


From dde3b60d572c941e2c72d22c18a08586fb67bb50 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:32 -0800
Subject: [PATCH 1014/4076] x86/virt/tdx: Designate reserved areas for all
 TDMRs

As the last step of constructing TDMRs, populate reserved areas for all
TDMRs.  Cover all memory holes and PAMTs with a TMDR reserved area.

[ dhansen: trim down chagnelog ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-12-dave.hansen%40intel.com
---
 arch/x86/virt/vmx/tdx/tdx.c | 217 ++++++++++++++++++++++++++++++++++--
 1 file changed, 209 insertions(+), 8 deletions(-)

diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index c2bff81245986..98283f728a816 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -23,6 +23,7 @@
 #include <linux/sizes.h>
 #include <linux/pfn.h>
 #include <linux/align.h>
+#include <linux/sort.h>
 #include <asm/msr-index.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
@@ -662,6 +663,207 @@ static unsigned long tdmrs_count_pamt_kb(struct tdmr_info_list *tdmr_list)
 	return pamt_size / 1024;
 }
 
+static int tdmr_add_rsvd_area(struct tdmr_info *tdmr, int *p_idx, u64 addr,
+			      u64 size, u16 max_reserved_per_tdmr)
+{
+	struct tdmr_reserved_area *rsvd_areas = tdmr->reserved_areas;
+	int idx = *p_idx;
+
+	/* Reserved area must be 4K aligned in offset and size */
+	if (WARN_ON(addr & ~PAGE_MASK || size & ~PAGE_MASK))
+		return -EINVAL;
+
+	if (idx >= max_reserved_per_tdmr) {
+		pr_warn("initialization failed: TDMR [0x%llx, 0x%llx): reserved areas exhausted.\n",
+				tdmr->base, tdmr_end(tdmr));
+		return -ENOSPC;
+	}
+
+	/*
+	 * Consume one reserved area per call.  Make no effort to
+	 * optimize or reduce the number of reserved areas which are
+	 * consumed by contiguous reserved areas, for instance.
+	 */
+	rsvd_areas[idx].offset = addr - tdmr->base;
+	rsvd_areas[idx].size = size;
+
+	*p_idx = idx + 1;
+
+	return 0;
+}
+
+/*
+ * Go through @tmb_list to find holes between memory areas.  If any of
+ * those holes fall within @tdmr, set up a TDMR reserved area to cover
+ * the hole.
+ */
+static int tdmr_populate_rsvd_holes(struct list_head *tmb_list,
+				    struct tdmr_info *tdmr,
+				    int *rsvd_idx,
+				    u16 max_reserved_per_tdmr)
+{
+	struct tdx_memblock *tmb;
+	u64 prev_end;
+	int ret;
+
+	/*
+	 * Start looking for reserved blocks at the
+	 * beginning of the TDMR.
+	 */
+	prev_end = tdmr->base;
+	list_for_each_entry(tmb, tmb_list, list) {
+		u64 start, end;
+
+		start = PFN_PHYS(tmb->start_pfn);
+		end   = PFN_PHYS(tmb->end_pfn);
+
+		/* Break if this region is after the TDMR */
+		if (start >= tdmr_end(tdmr))
+			break;
+
+		/* Exclude regions before this TDMR */
+		if (end < tdmr->base)
+			continue;
+
+		/*
+		 * Skip over memory areas that
+		 * have already been dealt with.
+		 */
+		if (start <= prev_end) {
+			prev_end = end;
+			continue;
+		}
+
+		/* Add the hole before this region */
+		ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end,
+				start - prev_end,
+				max_reserved_per_tdmr);
+		if (ret)
+			return ret;
+
+		prev_end = end;
+	}
+
+	/* Add the hole after the last region if it exists. */
+	if (prev_end < tdmr_end(tdmr)) {
+		ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end,
+				tdmr_end(tdmr) - prev_end,
+				max_reserved_per_tdmr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Go through @tdmr_list to find all PAMTs.  If any of those PAMTs
+ * overlaps with @tdmr, set up a TDMR reserved area to cover the
+ * overlapping part.
+ */
+static int tdmr_populate_rsvd_pamts(struct tdmr_info_list *tdmr_list,
+				    struct tdmr_info *tdmr,
+				    int *rsvd_idx,
+				    u16 max_reserved_per_tdmr)
+{
+	int i, ret;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		struct tdmr_info *tmp = tdmr_entry(tdmr_list, i);
+		unsigned long pamt_base, pamt_size, pamt_end;
+
+		tdmr_get_pamt(tmp, &pamt_base, &pamt_size);
+		/* Each TDMR must already have PAMT allocated */
+		WARN_ON_ONCE(!pamt_size || !pamt_base);
+
+		pamt_end = pamt_base + pamt_size;
+		/* Skip PAMTs outside of the given TDMR */
+		if ((pamt_end <= tdmr->base) ||
+				(pamt_base >= tdmr_end(tdmr)))
+			continue;
+
+		/* Only mark the part within the TDMR as reserved */
+		if (pamt_base < tdmr->base)
+			pamt_base = tdmr->base;
+		if (pamt_end > tdmr_end(tdmr))
+			pamt_end = tdmr_end(tdmr);
+
+		ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, pamt_base,
+				pamt_end - pamt_base,
+				max_reserved_per_tdmr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* Compare function called by sort() for TDMR reserved areas */
+static int rsvd_area_cmp_func(const void *a, const void *b)
+{
+	struct tdmr_reserved_area *r1 = (struct tdmr_reserved_area *)a;
+	struct tdmr_reserved_area *r2 = (struct tdmr_reserved_area *)b;
+
+	if (r1->offset + r1->size <= r2->offset)
+		return -1;
+	if (r1->offset >= r2->offset + r2->size)
+		return 1;
+
+	/* Reserved areas cannot overlap.  The caller must guarantee. */
+	WARN_ON_ONCE(1);
+	return -1;
+}
+
+/*
+ * Populate reserved areas for the given @tdmr, including memory holes
+ * (via @tmb_list) and PAMTs (via @tdmr_list).
+ */
+static int tdmr_populate_rsvd_areas(struct tdmr_info *tdmr,
+				    struct list_head *tmb_list,
+				    struct tdmr_info_list *tdmr_list,
+				    u16 max_reserved_per_tdmr)
+{
+	int ret, rsvd_idx = 0;
+
+	ret = tdmr_populate_rsvd_holes(tmb_list, tdmr, &rsvd_idx,
+			max_reserved_per_tdmr);
+	if (ret)
+		return ret;
+
+	ret = tdmr_populate_rsvd_pamts(tdmr_list, tdmr, &rsvd_idx,
+			max_reserved_per_tdmr);
+	if (ret)
+		return ret;
+
+	/* TDX requires reserved areas listed in address ascending order */
+	sort(tdmr->reserved_areas, rsvd_idx, sizeof(struct tdmr_reserved_area),
+			rsvd_area_cmp_func, NULL);
+
+	return 0;
+}
+
+/*
+ * Populate reserved areas for all TDMRs in @tdmr_list, including memory
+ * holes (via @tmb_list) and PAMTs.
+ */
+static int tdmrs_populate_rsvd_areas_all(struct tdmr_info_list *tdmr_list,
+					 struct list_head *tmb_list,
+					 u16 max_reserved_per_tdmr)
+{
+	int i;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		int ret;
+
+		ret = tdmr_populate_rsvd_areas(tdmr_entry(tdmr_list, i),
+				tmb_list, tdmr_list, max_reserved_per_tdmr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /*
  * Construct a list of TDMRs on the preallocated space in @tdmr_list
  * to cover all TDX memory regions in @tmb_list based on the TDX module
@@ -681,14 +883,13 @@ static int construct_tdmrs(struct list_head *tmb_list,
 			tdmr_sysinfo->pamt_entry_size);
 	if (ret)
 		return ret;
-	/*
-	 * TODO:
-	 *
-	 *  - Designate reserved areas for each TDMR.
-	 *
-	 * Return -EINVAL until constructing TDMRs is done
-	 */
-	return -EINVAL;
+
+	ret = tdmrs_populate_rsvd_areas_all(tdmr_list, tmb_list,
+			tdmr_sysinfo->max_reserved_per_tdmr);
+	if (ret)
+		tdmrs_free_pamt_all(tdmr_list);
+
+	return ret;
 }
 
 static int init_tdx_module(void)
-- 
GitLab


From 554ce1c36d1bbeaec42ba870bad75e200af204be Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:33 -0800
Subject: [PATCH 1015/4076] x86/virt/tdx: Configure TDX module with the TDMRs
 and global KeyID

The TDX module uses a private KeyID as the "global KeyID" for mapping
things like the PAMT and other TDX metadata.  This KeyID has already
been reserved when detecting TDX during the kernel early boot.

Now that the "TD Memory Regions" (TDMRs) are fully built, pass them to
the TDX module together with the global KeyID.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-13-dave.hansen%40intel.com
---
 arch/x86/virt/vmx/tdx/tdx.c | 43 ++++++++++++++++++++++++++++++++++++-
 arch/x86/virt/vmx/tdx/tdx.h |  2 ++
 2 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 98283f728a816..5146503233c07 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -24,6 +24,8 @@
 #include <linux/pfn.h>
 #include <linux/align.h>
 #include <linux/sort.h>
+#include <linux/log2.h>
+#include <asm/page.h>
 #include <asm/msr-index.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
@@ -892,6 +894,41 @@ static int construct_tdmrs(struct list_head *tmb_list,
 	return ret;
 }
 
+static int config_tdx_module(struct tdmr_info_list *tdmr_list, u64 global_keyid)
+{
+	struct tdx_module_args args = {};
+	u64 *tdmr_pa_array;
+	size_t array_sz;
+	int i, ret;
+
+	/*
+	 * TDMRs are passed to the TDX module via an array of physical
+	 * addresses of each TDMR.  The array itself also has certain
+	 * alignment requirement.
+	 */
+	array_sz = tdmr_list->nr_consumed_tdmrs * sizeof(u64);
+	array_sz = roundup_pow_of_two(array_sz);
+	if (array_sz < TDMR_INFO_PA_ARRAY_ALIGNMENT)
+		array_sz = TDMR_INFO_PA_ARRAY_ALIGNMENT;
+
+	tdmr_pa_array = kzalloc(array_sz, GFP_KERNEL);
+	if (!tdmr_pa_array)
+		return -ENOMEM;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++)
+		tdmr_pa_array[i] = __pa(tdmr_entry(tdmr_list, i));
+
+	args.rcx = __pa(tdmr_pa_array);
+	args.rdx = tdmr_list->nr_consumed_tdmrs;
+	args.r8 = global_keyid;
+	ret = seamcall_prerr(TDH_SYS_CONFIG, &args);
+
+	/* Free the array as it is not required anymore. */
+	kfree(tdmr_pa_array);
+
+	return ret;
+}
+
 static int init_tdx_module(void)
 {
 	struct tdx_tdmr_sysinfo tdmr_sysinfo;
@@ -927,10 +964,14 @@ static int init_tdx_module(void)
 	if (ret)
 		goto err_free_tdmrs;
 
+	/* Pass the TDMRs and the global KeyID to the TDX module */
+	ret = config_tdx_module(&tdx_tdmr_list, tdx_global_keyid);
+	if (ret)
+		goto err_free_pamts;
+
 	/*
 	 * TODO:
 	 *
-	 *  - Configure the TDMRs and the global KeyID to the TDX module.
 	 *  - Configure the global KeyID on all packages.
 	 *  - Initialize all TDMRs.
 	 *
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index 1b04efece9dbd..fa5bcf8b5a9ca 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -17,6 +17,7 @@
 #define TDH_SYS_INIT		33
 #define TDH_SYS_RD		34
 #define TDH_SYS_LP_INIT		35
+#define TDH_SYS_CONFIG		45
 
 /*
  * Global scope metadata field ID.
@@ -53,6 +54,7 @@ struct tdmr_reserved_area {
 } __packed;
 
 #define TDMR_INFO_ALIGNMENT	512
+#define TDMR_INFO_PA_ARRAY_ALIGNMENT	512
 
 struct tdmr_info {
 	u64 base;
-- 
GitLab


From e56d28df2f666af9ce0c27d8d204ad813d3766f4 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:34 -0800
Subject: [PATCH 1016/4076] x86/virt/tdx: Configure global KeyID on all
 packages

After the list of TDMRs and the global KeyID are configured to the TDX
module, the kernel needs to configure the key of the global KeyID on all
packages using TDH.SYS.KEY.CONFIG.

This SEAMCALL cannot run parallel on different cpus.  Loop all online
cpus and use smp_call_on_cpu() to call this SEAMCALL on the first cpu of
each package.

To keep things simple, this implementation takes no affirmative steps to
online cpus to make sure there's at least one cpu for each package.  The
callers (aka. KVM) can ensure success by ensuring sufficient CPUs are
online for this to succeed.

Intel hardware doesn't guarantee cache coherency across different
KeyIDs.  The PAMTs are transitioning from being used by the kernel
mapping (KeyId 0) to the TDX module's "global KeyID" mapping.

This means that the kernel must flush any dirty KeyID-0 PAMT cachelines
before the TDX module uses the global KeyID to access the PAMTs.
Otherwise, if those dirty cachelines were written back, they would
corrupt the TDX module's metadata.  Aside: This corruption would be
detected by the memory integrity hardware on the next read of the memory
with the global KeyID.  The result would likely be fatal to the system
but would not impact TDX security.

Following the TDX module specification, flush cache before configuring
the global KeyID on all packages.  Given the PAMT size can be large
(~1/256th of system RAM), just use WBINVD on all CPUs to flush.

If TDH.SYS.KEY.CONFIG fails, the TDX module may already have "converted"
some memory for TDX module use.  Convert the memory back so that it can
be safely used by the kernel again.  Note that this is slower than it
should be because of the "partial write machine check" erratum which
affects TDX-capable hardware.

Also refactor and introduce a new helper: tdmr_do_pamt_func().  This
takes a TDMR and runs a function on its PAMT.  It looks a _bit_ odd to
pass a function pointer around like this, but its use is pretty narrow
and it does eliminate what would otherwise be some copying and pasting.

[ dhansen: * munge changelog as usual
	   * remove weird (*pamd_func)() syntax ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-14-dave.hansen%40intel.com
---
 arch/x86/virt/vmx/tdx/tdx.c | 133 +++++++++++++++++++++++++++++++++++-
 arch/x86/virt/vmx/tdx/tdx.h |   1 +
 2 files changed, 132 insertions(+), 2 deletions(-)

diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 5146503233c07..d2e4180b8bd0f 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -26,6 +26,7 @@
 #include <linux/sort.h>
 #include <linux/log2.h>
 #include <asm/page.h>
+#include <asm/special_insns.h>
 #include <asm/msr-index.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
@@ -606,7 +607,8 @@ static void tdmr_get_pamt(struct tdmr_info *tdmr, unsigned long *pamt_base,
 	*pamt_size = pamt_sz;
 }
 
-static void tdmr_free_pamt(struct tdmr_info *tdmr)
+static void tdmr_do_pamt_func(struct tdmr_info *tdmr,
+		void (*pamt_func)(unsigned long base, unsigned long size))
 {
 	unsigned long pamt_base, pamt_size;
 
@@ -619,9 +621,19 @@ static void tdmr_free_pamt(struct tdmr_info *tdmr)
 	if (WARN_ON_ONCE(!pamt_base))
 		return;
 
+	pamt_func(pamt_base, pamt_size);
+}
+
+static void free_pamt(unsigned long pamt_base, unsigned long pamt_size)
+{
 	free_contig_range(pamt_base >> PAGE_SHIFT, pamt_size >> PAGE_SHIFT);
 }
 
+static void tdmr_free_pamt(struct tdmr_info *tdmr)
+{
+	tdmr_do_pamt_func(tdmr, free_pamt);
+}
+
 static void tdmrs_free_pamt_all(struct tdmr_info_list *tdmr_list)
 {
 	int i;
@@ -650,6 +662,41 @@ err:
 	return ret;
 }
 
+/*
+ * Convert TDX private pages back to normal by using MOVDIR64B to
+ * clear these pages.  Note this function doesn't flush cache of
+ * these TDX private pages.  The caller should make sure of that.
+ */
+static void reset_tdx_pages(unsigned long base, unsigned long size)
+{
+	const void *zero_page = (const void *)page_address(ZERO_PAGE(0));
+	unsigned long phys, end;
+
+	end = base + size;
+	for (phys = base; phys < end; phys += 64)
+		movdir64b(__va(phys), zero_page);
+
+	/*
+	 * MOVDIR64B uses WC protocol.  Use memory barrier to
+	 * make sure any later user of these pages sees the
+	 * updated data.
+	 */
+	mb();
+}
+
+static void tdmr_reset_pamt(struct tdmr_info *tdmr)
+{
+	tdmr_do_pamt_func(tdmr, reset_tdx_pages);
+}
+
+static void tdmrs_reset_pamt_all(struct tdmr_info_list *tdmr_list)
+{
+	int i;
+
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++)
+		tdmr_reset_pamt(tdmr_entry(tdmr_list, i));
+}
+
 static unsigned long tdmrs_count_pamt_kb(struct tdmr_info_list *tdmr_list)
 {
 	unsigned long pamt_size = 0;
@@ -929,6 +976,64 @@ static int config_tdx_module(struct tdmr_info_list *tdmr_list, u64 global_keyid)
 	return ret;
 }
 
+static int do_global_key_config(void *unused)
+{
+	struct tdx_module_args args = {};
+
+	return seamcall_prerr(TDH_SYS_KEY_CONFIG, &args);
+}
+
+/*
+ * Attempt to configure the global KeyID on all physical packages.
+ *
+ * This requires running code on at least one CPU in each package.
+ * TDMR initialization) will fail will fail if any package in the
+ * system has no online CPUs.
+ *
+ * This code takes no affirmative steps to online CPUs.  Callers (aka.
+ * KVM) can ensure success by ensuring sufficient CPUs are online and
+ * can run SEAMCALLs.
+ */
+static int config_global_keyid(void)
+{
+	cpumask_var_t packages;
+	int cpu, ret = -EINVAL;
+
+	if (!zalloc_cpumask_var(&packages, GFP_KERNEL))
+		return -ENOMEM;
+
+	/*
+	 * Hardware doesn't guarantee cache coherency across different
+	 * KeyIDs.  The kernel needs to flush PAMT's dirty cachelines
+	 * (associated with KeyID 0) before the TDX module can use the
+	 * global KeyID to access the PAMT.  Given PAMTs are potentially
+	 * large (~1/256th of system RAM), just use WBINVD.
+	 */
+	wbinvd_on_all_cpus();
+
+	for_each_online_cpu(cpu) {
+		/*
+		 * The key configuration only needs to be done once per
+		 * package and will return an error if configured more
+		 * than once.  Avoid doing it multiple times per package.
+		 */
+		if (cpumask_test_and_set_cpu(topology_physical_package_id(cpu),
+					packages))
+			continue;
+
+		/*
+		 * TDH.SYS.KEY.CONFIG cannot run concurrently on
+		 * different cpus.  Do it one by one.
+		 */
+		ret = smp_call_on_cpu(cpu, do_global_key_config, NULL, true);
+		if (ret)
+			break;
+	}
+
+	free_cpumask_var(packages);
+	return ret;
+}
+
 static int init_tdx_module(void)
 {
 	struct tdx_tdmr_sysinfo tdmr_sysinfo;
@@ -969,6 +1074,11 @@ static int init_tdx_module(void)
 	if (ret)
 		goto err_free_pamts;
 
+	/* Config the key of global KeyID on all packages */
+	ret = config_global_keyid();
+	if (ret)
+		goto err_reset_pamts;
+
 	/*
 	 * TODO:
 	 *
@@ -979,7 +1089,7 @@ static int init_tdx_module(void)
 	 */
 	ret = -EINVAL;
 	if (ret)
-		goto err_free_pamts;
+		goto err_reset_pamts;
 
 	pr_info("%lu KB allocated for PAMT\n", tdmrs_count_pamt_kb(&tdx_tdmr_list));
 
@@ -991,6 +1101,22 @@ out_put_tdxmem:
 	put_online_mems();
 	return ret;
 
+err_reset_pamts:
+	/*
+	 * Part of PAMTs may already have been initialized by the
+	 * TDX module.  Flush cache before returning PAMTs back
+	 * to the kernel.
+	 */
+	wbinvd_on_all_cpus();
+	/*
+	 * According to the TDX hardware spec, if the platform
+	 * doesn't have the "partial write machine check"
+	 * erratum, any kernel read/write will never cause #MC
+	 * in kernel space, thus it's OK to not convert PAMTs
+	 * back to normal.  But do the conversion anyway here
+	 * as suggested by the TDX spec.
+	 */
+	tdmrs_reset_pamt_all(&tdx_tdmr_list);
 err_free_pamts:
 	tdmrs_free_pamt_all(&tdx_tdmr_list);
 err_free_tdmrs:
@@ -1024,6 +1150,9 @@ static int __tdx_enable(void)
  * lock to prevent any new cpu from becoming online; 2) done both VMXON
  * and tdx_cpu_enable() on all online cpus.
  *
+ * This function requires there's at least one online cpu for each CPU
+ * package to succeed.
+ *
  * This function can be called in parallel by multiple callers.
  *
  * Return 0 if TDX is enabled successfully, otherwise error.
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index fa5bcf8b5a9ca..dd35baf756b86 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -14,6 +14,7 @@
 /*
  * TDX module SEAMCALL leaf functions
  */
+#define TDH_SYS_KEY_CONFIG	31
 #define TDH_SYS_INIT		33
 #define TDH_SYS_RD		34
 #define TDH_SYS_LP_INIT		35
-- 
GitLab


From 0b2bc38131f02d6fd38695f191bbd8c6109ecffc Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:35 -0800
Subject: [PATCH 1017/4076] x86/virt/tdx: Initialize all TDMRs

After the global KeyID has been configured on all packages, initialize
all TDMRs to make all TDX-usable memory regions that are passed to the
TDX module become usable.

This is the last step of initializing the TDX module.

Initializing TDMRs can be time consuming on large memory systems as it
involves initializing all metadata entries for all pages that can be
used by TDX guests.  Initializing different TDMRs can be parallelized.
For now to keep it simple, just initialize all TDMRs one by one.  It can
be enhanced in the future.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-15-dave.hansen%40intel.com
---
 arch/x86/virt/vmx/tdx/tdx.c | 61 +++++++++++++++++++++++++++++++------
 arch/x86/virt/vmx/tdx/tdx.h |  1 +
 2 files changed, 53 insertions(+), 9 deletions(-)

diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index d2e4180b8bd0f..48fb1b3101c04 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1034,6 +1034,56 @@ static int config_global_keyid(void)
 	return ret;
 }
 
+static int init_tdmr(struct tdmr_info *tdmr)
+{
+	u64 next;
+
+	/*
+	 * Initializing a TDMR can be time consuming.  To avoid long
+	 * SEAMCALLs, the TDX module may only initialize a part of the
+	 * TDMR in each call.
+	 */
+	do {
+		struct tdx_module_args args = {
+			.rcx = tdmr->base,
+		};
+		int ret;
+
+		ret = seamcall_prerr_ret(TDH_SYS_TDMR_INIT, &args);
+		if (ret)
+			return ret;
+		/*
+		 * RDX contains 'next-to-initialize' address if
+		 * TDH.SYS.TDMR.INIT did not fully complete and
+		 * should be retried.
+		 */
+		next = args.rdx;
+		cond_resched();
+		/* Keep making SEAMCALLs until the TDMR is done */
+	} while (next < tdmr->base + tdmr->size);
+
+	return 0;
+}
+
+static int init_tdmrs(struct tdmr_info_list *tdmr_list)
+{
+	int i;
+
+	/*
+	 * This operation is costly.  It can be parallelized,
+	 * but keep it simple for now.
+	 */
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		int ret;
+
+		ret = init_tdmr(tdmr_entry(tdmr_list, i));
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int init_tdx_module(void)
 {
 	struct tdx_tdmr_sysinfo tdmr_sysinfo;
@@ -1079,15 +1129,8 @@ static int init_tdx_module(void)
 	if (ret)
 		goto err_reset_pamts;
 
-	/*
-	 * TODO:
-	 *
-	 *  - Configure the global KeyID on all packages.
-	 *  - Initialize all TDMRs.
-	 *
-	 *  Return error before all steps are done.
-	 */
-	ret = -EINVAL;
+	/* Initialize TDMRs to complete the TDX module initialization */
+	ret = init_tdmrs(&tdx_tdmr_list);
 	if (ret)
 		goto err_reset_pamts;
 
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index dd35baf756b86..c0610f0bb88ce 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -18,6 +18,7 @@
 #define TDH_SYS_INIT		33
 #define TDH_SYS_RD		34
 #define TDH_SYS_LP_INIT		35
+#define TDH_SYS_TDMR_INIT	36
 #define TDH_SYS_CONFIG		45
 
 /*
-- 
GitLab


From f3f6aa68640298fb966811b991c7b8efee67e181 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:36 -0800
Subject: [PATCH 1018/4076] x86/virt/tdx: Handle TDX interaction with sleep and
 hibernation

TDX is incompatible with hibernation and some ACPI sleep states.
Users must disable hibernation to use TDX.  Users must also disable
TDX if they want to use ACPI S3 sleep.

This feels a bit wonky and asymmetric, but it avoids adding any new
command-line parameters for now.  It can be improved if users hate it
too much.

Long version:

TDX cannot survive from S3 and deeper states.  The hardware resets and
disables TDX completely when platform goes to S3 and deeper.  Both TDX
guests and the TDX module get destroyed permanently.

The kernel uses S3 to support suspend-to-ram, and S4 or deeper states to
support hibernation.  The kernel also maintains TDX states to track
whether it has been initialized and its metadata resource, etc.  After
resuming from S3 or hibernation, these TDX states won't be correct
anymore.

Theoretically, the kernel can do more complicated things like resetting
TDX internal states and TDX module metadata before going to S3 or
deeper, and re-initialize TDX module after resuming, etc, but there is
no way to save/restore TDX guests for now.

Until TDX supports full save and restore of TDX guests, there is no big
value to handle TDX module in suspend and hibernation alone.  To make
things simple, just choose to make TDX mutually exclusive with S3 and
hibernation.

Note the TDX module is initialized at runtime.  To avoid having to deal
with the fuss of determining TDX state at runtime, just choose TDX vs S3
and hibernation at kernel early boot.  It's a bad user experience if the
choice of TDX and S3/hibernation is done at runtime anyway, i.e., the
user can experience being able to do S3/hibernation but later becoming
unable to due to TDX being enabled.

Disable TDX in kernel early boot when hibernation support is available.
Currently there's no mechanism exposed by the hibernation code to allow
other kernel code to disable hibernation once for all.  Users that want
TDX must disable hibernation, like using hibername=no on the command
line.

Disable ACPI S3 when TDX is enabled by the BIOS.  For now the user needs
to disable TDX in the BIOS to use ACPI S3.  A new kernel command line
can be added in the future if there's a need to let user disable TDX
host via kernel command line.

Alternatively, the kernel could disable TDX when ACPI S3 is supported
and request the user to disable S3 to use TDX.  But there's no existing
kernel command line to do that, and BIOS doesn't always have an option
to disable S3.

[ dhansen: subject / changelog tweaks ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-16-dave.hansen%40intel.com
---
 arch/x86/virt/vmx/tdx/tdx.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 48fb1b3101c04..6d030f64720ba 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -25,6 +25,8 @@
 #include <linux/align.h>
 #include <linux/sort.h>
 #include <linux/log2.h>
+#include <linux/acpi.h>
+#include <linux/suspend.h>
 #include <asm/page.h>
 #include <asm/special_insns.h>
 #include <asm/msr-index.h>
@@ -1329,6 +1331,15 @@ void __init tdx_init(void)
 		return;
 	}
 
+	/*
+	 * At this point, hibernation_available() indicates whether or
+	 * not hibernation support has been permanently disabled.
+	 */
+	if (hibernation_available()) {
+		pr_err("initialization failed: Hibernation support is enabled\n");
+		return;
+	}
+
 	err = register_memory_notifier(&tdx_memory_nb);
 	if (err) {
 		pr_err("initialization failed: register_memory_notifier() failed (%d)\n",
@@ -1336,6 +1347,11 @@ void __init tdx_init(void)
 		return;
 	}
 
+#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
+	pr_info("Disable ACPI S3. Turn off TDX in the BIOS to use ACPI S3.\n");
+	acpi_suspend_lowlevel = NULL;
+#endif
+
 	/*
 	 * Just use the first TDX KeyID as the 'global KeyID' and
 	 * leave the rest for TDX guests.
-- 
GitLab


From 79eba8c924f7decfa71ddf187d38cb9f5f2cd7b3 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:42 +0200
Subject: [PATCH 1019/4076] selftests/sgx: Fix uninitialized pointer
 dereference in error path

Ensure ctx is zero-initialized, such that the encl_measure function will
not call EVP_MD_CTX_destroy with an uninitialized ctx pointer in case of an
early error during key generation.

Fixes: 2adcba79e69d ("selftests/x86: Add a selftest for SGX")
Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/20231005153854.25566-2-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/sigstruct.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c
index a07896a463643..d73b29becf5b0 100644
--- a/tools/testing/selftests/sgx/sigstruct.c
+++ b/tools/testing/selftests/sgx/sigstruct.c
@@ -318,9 +318,9 @@ bool encl_measure(struct encl *encl)
 	struct sgx_sigstruct *sigstruct = &encl->sigstruct;
 	struct sgx_sigstruct_payload payload;
 	uint8_t digest[SHA256_DIGEST_LENGTH];
+	EVP_MD_CTX *ctx = NULL;
 	unsigned int siglen;
 	RSA *key = NULL;
-	EVP_MD_CTX *ctx;
 	int i;
 
 	memset(sigstruct, 0, sizeof(*sigstruct));
@@ -384,7 +384,8 @@ bool encl_measure(struct encl *encl)
 	return true;
 
 err:
-	EVP_MD_CTX_destroy(ctx);
+	if (ctx)
+		EVP_MD_CTX_destroy(ctx);
 	RSA_free(key);
 	return false;
 }
-- 
GitLab


From b84fc2e0139ba4b23b8039bd7cfd242894fe8f8b Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:43 +0200
Subject: [PATCH 1020/4076] selftests/sgx: Fix uninitialized pointer
 dereferences in encl_get_entry

Ensure sym_tab and sym_names are zero-initialized and add an early-out
condition in the unlikely (erroneous) case that the enclave ELF file would
not contain a symbol table.

This addresses -Werror=maybe-uninitialized compiler warnings for gcc -O2.

Fixes: 33c5aac3bf32 ("selftests/sgx: Test complete changing of page type flow")
Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lore.kernel.org/all/20231005153854.25566-3-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/load.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c
index 94bdeac1cf041..c9f658e44de6c 100644
--- a/tools/testing/selftests/sgx/load.c
+++ b/tools/testing/selftests/sgx/load.c
@@ -136,11 +136,11 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg)
  */
 uint64_t encl_get_entry(struct encl *encl, const char *symbol)
 {
+	Elf64_Sym *symtab = NULL;
+	char *sym_names = NULL;
 	Elf64_Shdr *sections;
-	Elf64_Sym *symtab;
 	Elf64_Ehdr *ehdr;
-	char *sym_names;
-	int num_sym;
+	int num_sym = 0;
 	int i;
 
 	ehdr = encl->bin;
@@ -161,6 +161,9 @@ uint64_t encl_get_entry(struct encl *encl, const char *symbol)
 		}
 	}
 
+	if (!symtab || !sym_names)
+		return 0;
+
 	for (i = 0; i < num_sym; i++) {
 		Elf64_Sym *sym = &symtab[i];
 
-- 
GitLab


From 853a57a43ebdb8c024160c1a0990bae85f4bcc2f Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:44 +0200
Subject: [PATCH 1021/4076] selftests/sgx: Include memory clobber for inline
 asm in test enclave

Add the "memory" clobber to the EMODPE and EACCEPT asm blocks to tell the
compiler the assembly code accesses to the secinfo struct. This ensures
the compiler treats the asm block as a memory barrier and the write to
secinfo will be visible to ENCLU.

Fixes: 20404a808593 ("selftests/sgx: Add test for EPCM permission changes")
Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lore.kernel.org/all/20231005153854.25566-4-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/test_encl.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c
index c0d6397295e31..ae791df3e5a57 100644
--- a/tools/testing/selftests/sgx/test_encl.c
+++ b/tools/testing/selftests/sgx/test_encl.c
@@ -24,10 +24,11 @@ static void do_encl_emodpe(void *_op)
 	secinfo.flags = op->flags;
 
 	asm volatile(".byte 0x0f, 0x01, 0xd7"
-				:
+				: /* no outputs */
 				: "a" (EMODPE),
 				  "b" (&secinfo),
-				  "c" (op->epc_addr));
+				  "c" (op->epc_addr)
+				: "memory" /* read from secinfo pointer */);
 }
 
 static void do_encl_eaccept(void *_op)
@@ -42,7 +43,8 @@ static void do_encl_eaccept(void *_op)
 				: "=a" (rax)
 				: "a" (EACCEPT),
 				  "b" (&secinfo),
-				  "c" (op->epc_addr));
+				  "c" (op->epc_addr)
+				: "memory" /* read from secinfo pointer */);
 
 	op->ret = rax;
 }
-- 
GitLab


From f79464658d858e07af0c4c9b30f5baedeeae0c04 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:45 +0200
Subject: [PATCH 1022/4076] selftests/sgx: Separate linker options

Fixes "'linker' input unused [-Wunused-command-line-argument]" errors when
compiling with clang.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lore.kernel.org/all/20231005153854.25566-5-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/Makefile | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
index 50aab6b57da34..dcdd04b322f83 100644
--- a/tools/testing/selftests/sgx/Makefile
+++ b/tools/testing/selftests/sgx/Makefile
@@ -12,9 +12,11 @@ OBJCOPY := $(CROSS_COMPILE)objcopy
 endif
 
 INCLUDES := -I$(top_srcdir)/tools/include
-HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack
-ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \
+HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC
+HOST_LDFLAGS := -z noexecstack -lcrypto
+ENCL_CFLAGS += -Wall -Werror -static -nostdlib -nostartfiles -fPIC \
 	       -fno-stack-protector -mrdrnd $(INCLUDES)
+ENCL_LDFLAGS := -Wl,-T,test_encl.lds,--build-id=none
 
 TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx
 TEST_FILES := $(OUTPUT)/test_encl.elf
@@ -28,7 +30,7 @@ $(OUTPUT)/test_sgx: $(OUTPUT)/main.o \
 		    $(OUTPUT)/sigstruct.o \
 		    $(OUTPUT)/call.o \
 		    $(OUTPUT)/sign_key.o
-	$(CC) $(HOST_CFLAGS) -o $@ $^ -lcrypto
+	$(CC) $(HOST_CFLAGS) -o $@ $^ $(HOST_LDFLAGS)
 
 $(OUTPUT)/main.o: main.c
 	$(CC) $(HOST_CFLAGS) -c $< -o $@
@@ -45,8 +47,8 @@ $(OUTPUT)/call.o: call.S
 $(OUTPUT)/sign_key.o: sign_key.S
 	$(CC) $(HOST_CFLAGS) -c $< -o $@
 
-$(OUTPUT)/test_encl.elf: test_encl.lds test_encl.c test_encl_bootstrap.S
-	$(CC) $(ENCL_CFLAGS) -T $^ -o $@ -Wl,--build-id=none
+$(OUTPUT)/test_encl.elf: test_encl.c test_encl_bootstrap.S
+	$(CC) $(ENCL_CFLAGS) $^ -o $@ $(ENCL_LDFLAGS)
 
 EXTRA_CLEAN := \
 	$(OUTPUT)/test_encl.elf \
-- 
GitLab


From 304b259e63b94c4f825e0648b33b15f8962955c7 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:46 +0200
Subject: [PATCH 1023/4076] selftests/sgx: Specify freestanding environment for
 enclave compilation

Use -ffreestanding to assert the enclave compilation targets a
freestanding environment (i.e., without "main" or standard libraries).
This fixes clang reporting "undefined reference to `memset'" after
erroneously optimizing away the provided memset/memcpy implementations.

Still need to instruct the linker from using standard system startup
functions, but drop -nostartfiles as it is implied by -nostdlib.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/20231005153854.25566-6-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
index dcdd04b322f83..7eb890bdd3f0c 100644
--- a/tools/testing/selftests/sgx/Makefile
+++ b/tools/testing/selftests/sgx/Makefile
@@ -14,7 +14,7 @@ endif
 INCLUDES := -I$(top_srcdir)/tools/include
 HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC
 HOST_LDFLAGS := -z noexecstack -lcrypto
-ENCL_CFLAGS += -Wall -Werror -static -nostdlib -nostartfiles -fPIC \
+ENCL_CFLAGS += -Wall -Werror -static -nostdlib -ffreestanding -fPIC \
 	       -fno-stack-protector -mrdrnd $(INCLUDES)
 ENCL_LDFLAGS := -Wl,-T,test_encl.lds,--build-id=none
 
-- 
GitLab


From 4f812df8f37463767c2a74c2bd77de94acdb2be6 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:47 +0200
Subject: [PATCH 1024/4076] selftests/sgx: Remove redundant enclave base
 address save/restore

Remove redundant push/pop pair that stores and restores the enclave base
address in the test enclave, as it is never used after the pop and can
anyway be easily retrieved via the __encl_base symbol.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/20231005153854.25566-7-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/test_encl_bootstrap.S | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S
index 03ae0f57e29d0..e0ce993d3f2cb 100644
--- a/tools/testing/selftests/sgx/test_encl_bootstrap.S
+++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S
@@ -55,12 +55,9 @@ encl_entry_core:
 	push	%rax
 
 	push	%rcx # push the address after EENTER
-	push	%rbx # push the enclave base address
 
 	call	encl_body
 
-	pop	%rbx # pop the enclave base address
-
 	/* Clear volatile GPRs, except RAX (EEXIT function). */
 	xor     %rcx, %rcx
 	xor     %rdx, %rdx
-- 
GitLab


From f7884e732841450de36c2b1ed49b91e8e854a7d1 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:48 +0200
Subject: [PATCH 1025/4076] selftests/sgx: Produce static-pie executable for
 test enclave

The current combination of -static and -fPIC creates a static executable
with position-dependent addresses for global variables. Use -static-pie
and -fPIE to create a proper static position independent executable that
can be loaded at any address without a dynamic linker.

When building the original "lea (encl_stack)(%rbx), %rax" assembly code
with -static-pie -fPIE, the linker complains about a relocation it cannot
resolve:

/usr/local/bin/ld: /tmp/cchIWyfG.o: relocation R_X86_64_32S against
`.data' can not be used when making a PIE object; recompile with -fPIE
collect2: error: ld returned 1 exit status

Thus, since only RIP-relative addressing is legit for local symbols, use
"encl_stack(%rip)" and declare an explicit "__encl_base" symbol at the
start of the linker script to be able to calculate the stack address
relative to the current TCS in the enclave assembly entry code.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/f9c24d89-ed72-7d9e-c650-050d722c6b04@cs.kuleuven.be/
Link: https://lore.kernel.org/all/20231005153854.25566-8-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/Makefile              | 2 +-
 tools/testing/selftests/sgx/test_encl.lds         | 1 +
 tools/testing/selftests/sgx/test_encl_bootstrap.S | 9 ++++++---
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
index 7eb890bdd3f0c..8d2ba6adc92bd 100644
--- a/tools/testing/selftests/sgx/Makefile
+++ b/tools/testing/selftests/sgx/Makefile
@@ -14,7 +14,7 @@ endif
 INCLUDES := -I$(top_srcdir)/tools/include
 HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC
 HOST_LDFLAGS := -z noexecstack -lcrypto
-ENCL_CFLAGS += -Wall -Werror -static -nostdlib -ffreestanding -fPIC \
+ENCL_CFLAGS += -Wall -Werror -static-pie -nostdlib -ffreestanding -fPIE \
 	       -fno-stack-protector -mrdrnd $(INCLUDES)
 ENCL_LDFLAGS := -Wl,-T,test_encl.lds,--build-id=none
 
diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds
index a1ec64f7d91fc..62d37160f59b2 100644
--- a/tools/testing/selftests/sgx/test_encl.lds
+++ b/tools/testing/selftests/sgx/test_encl.lds
@@ -10,6 +10,7 @@ PHDRS
 SECTIONS
 {
 	. = 0;
+        __encl_base = .;
 	.tcs : {
 		*(.tcs*)
 	} : tcs
diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S
index e0ce993d3f2cb..28fe5d2ac0afd 100644
--- a/tools/testing/selftests/sgx/test_encl_bootstrap.S
+++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S
@@ -42,9 +42,12 @@
 encl_entry:
 	# RBX contains the base address for TCS, which is the first address
 	# inside the enclave for TCS #1 and one page into the enclave for
-	# TCS #2. By adding the value of encl_stack to it, we get
-	# the absolute address for the stack.
-	lea	(encl_stack)(%rbx), %rax
+	# TCS #2. First make it relative by substracting __encl_base and
+	# then add the address of encl_stack to get the address for the stack.
+	lea __encl_base(%rip), %rax
+	sub %rax, %rbx
+	lea encl_stack(%rip), %rax
+	add %rbx, %rax
 	jmp encl_entry_core
 encl_dyn_entry:
 	# Entry point for dynamically created TCS page expected to follow
-- 
GitLab


From d06978e8e47a348c0d33462a8c2bf8f46d2b7df5 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:49 +0200
Subject: [PATCH 1026/4076] selftests/sgx: Handle relocations in test enclave

Static-pie binaries normally include a startup routine to perform any ELF
relocations from .rela.dyn. Since the enclave loading process is different
and glibc is not included, do the necessary relocation for encl_op_array
entries manually at runtime relative to the enclave base to ensure correct
function pointers.

When keeping encl_op_array as a local variable on the stack, gcc without
optimizations generates code that explicitly gets the right function
addresses and stores them to create the array on the stack:

encl_body:
    /* snipped */
    lea    do_encl_op_put_to_buf(%rip), %rax
    mov    %rax, -0x50(%rbp)
    lea    do_encl_op_get_from_buf(%rip), %rax
    mov    %rax,-0x48(%rbp)
    lea    do_encl_op_put_to_addr(%rip), %rax
    /* snipped */

However, gcc -Os or clang generate more efficient code that initializes
encl_op_array by copying a "prepared copy" containing the absolute
addresses of the functions (i.e., relative to the image base starting from
0) generated by the compiler/linker:

encl_body:
    /* snipped */
    lea    prepared_copy(%rip), %rsi
    lea    -0x48(%rsp), %rdi
    mov    $0x10,%ecx
    rep movsl %ds:(%rsi),%es:(%rdi)
    /* snipped */

When building the enclave with -static-pie, the compiler/linker includes
relocation entries for the function symbols in the "prepared copy":

Relocation section '.rela.dyn' at offset 0x4000 contains 12 entries:
  Offset          Info           Type         Symbol
/* snipped; "prepared_copy" starts at 0x6000 */
000000006000  000000000008 R_X86_64_RELATIVE  <do_encl_emodpe>
000000006008  000000000008 R_X86_64_RELATIVE  <do_encl_eaccept>
000000006010  000000000008 R_X86_64_RELATIVE  <do_encl_op_put_to_buf>
000000006018  000000000008 R_X86_64_RELATIVE  <do_encl_op_get_from_buf>
000000006020  000000000008 R_X86_64_RELATIVE  <do_encl_op_put_to_addr>
000000006028  000000000008 R_X86_64_RELATIVE  <do_encl_op_get_from_addr>
000000006030  000000000008 R_X86_64_RELATIVE  <do_encl_op_nop>
000000006038  000000000008 R_X86_64_RELATIVE  <do_encl_init_tcs_page>

Static-pie binaries normally include a glibc "_dl_relocate_static_pie"
routine that will perform these relocations as part of the startup.
However, since the enclave loading process is different and glibc is not
included, we cannot rely on these relocations to be performed. Without
relocations, the code would erroneously jump to the _absolute_ function
address loaded from the local copy.

Thus, declare "encl_op_array" as global and manually relocate the loaded
function-pointer entries relative to the enclave base at runtime. This
generates the following code:

encl_body:
    /* snipped */
    lea    encl_op_array(%rip), %rcx
    lea    __encl_base(%rip), %rax
    add    (%rcx,%rdx,8),%rax
    jmp    *%rax

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/150d8ca8-2c66-60d1-f9fc-8e6279824e94@cs.kuleuven.be/
Link: https://lore.kernel.org/all/5c22de5a-4b3b-1f38-9771-409b4ec7f96d@cs.kuleuven.be/#r
Link: https://lore.kernel.org/all/20231005153854.25566-9-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/test_encl.c | 50 +++++++++++++++++--------
 1 file changed, 35 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c
index ae791df3e5a57..649604c526e77 100644
--- a/tools/testing/selftests/sgx/test_encl.c
+++ b/tools/testing/selftests/sgx/test_encl.c
@@ -121,21 +121,41 @@ static void do_encl_op_nop(void *_op)
 
 }
 
+/*
+ * Symbol placed at the start of the enclave image by the linker script.
+ * Declare this extern symbol with visibility "hidden" to ensure the compiler
+ * does not access it through the GOT and generates position-independent
+ * addressing as __encl_base(%rip), so we can get the actual enclave base
+ * during runtime.
+ */
+extern const uint8_t __attribute__((visibility("hidden"))) __encl_base;
+
+typedef void (*encl_op_t)(void *);
+static const encl_op_t encl_op_array[ENCL_OP_MAX] = {
+	do_encl_op_put_to_buf,
+	do_encl_op_get_from_buf,
+	do_encl_op_put_to_addr,
+	do_encl_op_get_from_addr,
+	do_encl_op_nop,
+	do_encl_eaccept,
+	do_encl_emodpe,
+	do_encl_init_tcs_page,
+};
+
 void encl_body(void *rdi,  void *rsi)
 {
-	const void (*encl_op_array[ENCL_OP_MAX])(void *) = {
-		do_encl_op_put_to_buf,
-		do_encl_op_get_from_buf,
-		do_encl_op_put_to_addr,
-		do_encl_op_get_from_addr,
-		do_encl_op_nop,
-		do_encl_eaccept,
-		do_encl_emodpe,
-		do_encl_init_tcs_page,
-	};
-
-	struct encl_op_header *op = (struct encl_op_header *)rdi;
-
-	if (op->type < ENCL_OP_MAX)
-		(*encl_op_array[op->type])(op);
+	struct encl_op_header *header = (struct encl_op_header *)rdi;
+	encl_op_t op;
+
+	if (header->type >= ENCL_OP_MAX)
+		return;
+
+	/*
+	 * The enclave base address needs to be added, as this call site
+	 * *cannot be* made rip-relative by the compiler, or fixed up by
+	 * any other possible means.
+	 */
+	op = ((uint64_t)&__encl_base) + encl_op_array[header->type];
+
+	(*op)(header);
 }
-- 
GitLab


From 9fd552ee32c6c1e27c125016b87d295bea6faea7 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:50 +0200
Subject: [PATCH 1027/4076] selftests/sgx: Fix linker script asserts

DEFINED only considers symbols, not section names. Hence, replace the
check for .got.plt with the _GLOBAL_OFFSET_TABLE_ symbol and remove other
(non-essential) asserts.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lore.kernel.org/all/20231005153854.25566-10-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/test_encl.lds | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds
index 62d37160f59b2..6ffdfc9fb4cfb 100644
--- a/tools/testing/selftests/sgx/test_encl.lds
+++ b/tools/testing/selftests/sgx/test_encl.lds
@@ -35,8 +35,4 @@ SECTIONS
 	}
 }
 
-ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves")
-ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves")
-ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves")
-ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves")
-ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves")
+ASSERT(!DEFINED(_GLOBAL_OFFSET_TABLE_), "Libcalls through GOT are not supported in enclaves")
-- 
GitLab


From a4c39ef4ed43103caef80029cd30427a9ff342d8 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:51 +0200
Subject: [PATCH 1028/4076] selftests/sgx: Ensure test enclave buffer is
 entirely preserved

Attach the "used" attribute to instruct the compiler to preserve the static
encl_buffer, even if it appears it is not entirely referenced in the enclave
code, as expected by the external tests manipulating page permissions.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/a2732938-f3db-a0af-3d68-a18060f66e79@cs.kuleuven.be/
Link: https://lore.kernel.org/all/20231005153854.25566-11-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/defines.h   | 1 +
 tools/testing/selftests/sgx/test_encl.c | 9 +++++----
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h
index d8587c971941a..b8f482667ce14 100644
--- a/tools/testing/selftests/sgx/defines.h
+++ b/tools/testing/selftests/sgx/defines.h
@@ -13,6 +13,7 @@
 
 #define __aligned(x) __attribute__((__aligned__(x)))
 #define __packed __attribute__((packed))
+#define __used __attribute__((used))
 
 #include "../../../../arch/x86/include/asm/sgx.h"
 #include "../../../../arch/x86/include/asm/enclu.h"
diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c
index 649604c526e77..7465f121fb746 100644
--- a/tools/testing/selftests/sgx/test_encl.c
+++ b/tools/testing/selftests/sgx/test_encl.c
@@ -5,11 +5,12 @@
 #include "defines.h"
 
 /*
- * Data buffer spanning two pages that will be placed first in .data
- * segment. Even if not used internally the second page is needed by
- * external test manipulating page permissions.
+ * Data buffer spanning two pages that will be placed first in the .data
+ * segment. Even if not used internally the second page is needed by external
+ * test manipulating page permissions, so mark encl_buffer as "used" to make
+ * sure it is entirely preserved by the compiler.
  */
-static uint8_t encl_buffer[8192] = { 1 };
+static uint8_t __used encl_buffer[8192] = { 1 };
 
 enum sgx_enclu_function {
 	EACCEPT = 0x5,
-- 
GitLab


From 022416496008bd51cb7b33975cc0008749329a86 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:52 +0200
Subject: [PATCH 1029/4076] selftests/sgx: Ensure expected location of test
 enclave buffer

The external tests manipulating page permissions expect encl_buffer to be
placed at the start of the test enclave's .data section. As this is not
guaranteed per the C standard, explicitly place encl_buffer in a separate
section that is explicitly placed at the start of the .data segment in the
linker script to avoid the compiler placing it somewhere else in .data.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/20231005153854.25566-12-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/defines.h     | 1 +
 tools/testing/selftests/sgx/test_encl.c   | 8 ++++----
 tools/testing/selftests/sgx/test_encl.lds | 1 +
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h
index b8f482667ce14..402f8787a71cc 100644
--- a/tools/testing/selftests/sgx/defines.h
+++ b/tools/testing/selftests/sgx/defines.h
@@ -14,6 +14,7 @@
 #define __aligned(x) __attribute__((__aligned__(x)))
 #define __packed __attribute__((packed))
 #define __used __attribute__((used))
+#define __section(x)__attribute__((__section__(x)))
 
 #include "../../../../arch/x86/include/asm/sgx.h"
 #include "../../../../arch/x86/include/asm/enclu.h"
diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c
index 7465f121fb746..2c4d709cce2d9 100644
--- a/tools/testing/selftests/sgx/test_encl.c
+++ b/tools/testing/selftests/sgx/test_encl.c
@@ -6,11 +6,11 @@
 
 /*
  * Data buffer spanning two pages that will be placed first in the .data
- * segment. Even if not used internally the second page is needed by external
- * test manipulating page permissions, so mark encl_buffer as "used" to make
- * sure it is entirely preserved by the compiler.
+ * segment via the linker script. Even if not used internally the second page
+ * is needed by external test manipulating page permissions, so mark
+ * encl_buffer as "used" to make sure it is entirely preserved by the compiler.
  */
-static uint8_t __used encl_buffer[8192] = { 1 };
+static uint8_t __used __section(".data.encl_buffer") encl_buffer[8192] = { 1 };
 
 enum sgx_enclu_function {
 	EACCEPT = 0x5,
diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds
index 6ffdfc9fb4cfb..333a3e78fdc97 100644
--- a/tools/testing/selftests/sgx/test_encl.lds
+++ b/tools/testing/selftests/sgx/test_encl.lds
@@ -24,6 +24,7 @@ SECTIONS
 	} : text
 
 	.data : {
+		*(.data.encl_buffer)
 		*(.data*)
 	} : data
 
-- 
GitLab


From ec44ca1e34bc3a9864a8c1bf8636066ec6d5d2e5 Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:53 +0200
Subject: [PATCH 1030/4076] selftests/sgx: Discard unsupported ELF sections

Building the test enclave with -static-pie may produce a dynamic symbol
table, but this is not supported for enclaves and any relocations need to
happen manually (e.g., as for "encl_op_array"). Thus, opportunistically
discard ".dyn*" and ".gnu.hash" which the enclave loader cannot handle.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lore.kernel.org/all/20231005153854.25566-13-jo.vanbulck%40cs.kuleuven.be
---
 tools/testing/selftests/sgx/test_encl.lds | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds
index 333a3e78fdc97..ffe851a1cac40 100644
--- a/tools/testing/selftests/sgx/test_encl.lds
+++ b/tools/testing/selftests/sgx/test_encl.lds
@@ -33,6 +33,8 @@ SECTIONS
 		*(.note*)
 		*(.debug*)
 		*(.eh_frame*)
+		*(.dyn*)
+		*(.gnu.hash)
 	}
 }
 
-- 
GitLab


From 886c5be0b12e89b2905c26c4f24d50ae91f261da Mon Sep 17 00:00:00 2001
From: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Date: Thu, 5 Oct 2023 17:38:54 +0200
Subject: [PATCH 1031/4076] selftests/sgx: Remove incomplete ABI sanitization
 code in test enclave

As the selftest enclave is *not* intended for production, simplify the
code by not initializing CPU configuration registers as expected by the
ABI on enclave entry or cleansing caller-save registers on enclave exit.

Signed-off-by: Jo Van Bulck <jo.vanbulck@cs.kuleuven.be>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lore.kernel.org/all/da0cfb1e-e347-f7f2-ac72-aec0ee0d867d@intel.com/
Link: https://lore.kernel.org/all/20231005153854.25566-14-jo.vanbulck%40cs.kuleuven.be
---
 .../testing/selftests/sgx/test_encl_bootstrap.S  | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S
index 28fe5d2ac0afd..d8c4ac94e032c 100644
--- a/tools/testing/selftests/sgx/test_encl_bootstrap.S
+++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S
@@ -59,21 +59,11 @@ encl_entry_core:
 
 	push	%rcx # push the address after EENTER
 
+	# NOTE: as the selftest enclave is *not* intended for production,
+	# simplify the code by not initializing ABI registers on entry or
+	# cleansing caller-save registers on exit.
 	call	encl_body
 
-	/* Clear volatile GPRs, except RAX (EEXIT function). */
-	xor     %rcx, %rcx
-	xor     %rdx, %rdx
-	xor     %rdi, %rdi
-	xor     %rsi, %rsi
-	xor     %r8, %r8
-	xor     %r9, %r9
-	xor     %r10, %r10
-	xor     %r11, %r11
-
-	# Reset status flags.
-	add     %rdx, %rdx # OF = SF = AF = CF = 0; ZF = PF = 1
-
 	# Prepare EEXIT target by popping the address of the instruction after
 	# EENTER to RBX.
 	pop	%rbx
-- 
GitLab


From 981cf568a8644161c2f15c02278ebc2834b51ba6 Mon Sep 17 00:00:00 2001
From: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Date: Tue, 5 Dec 2023 21:56:05 -0500
Subject: [PATCH 1032/4076] selftests/sgx: Skip non X86_64 platform

When building whole selftests on arm64, rsync gives an erorr about sgx:

rsync: [sender] link_stat "/root/linux-next/tools/testing/selftests/sgx/test_encl.elf" failed: No such file or directory (2)
rsync error: some files/attrs were not transferred (see previous errors) (code 23) at main.c(1327) [sender=3.2.5]

The root casue is sgx only used on X86_64, and shall be skipped on other
platforms.

Fix this by moving TEST_CUSTOM_PROGS and TEST_FILES inside the if check,
then the build result will be "Skipping non-existent dir: sgx".

Fixes: 2adcba79e69d ("selftests/x86: Add a selftest for SGX")
Signed-off-by: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lore.kernel.org/all/20231206025605.3965302-1-zhaomzhao%40126.com
---
 tools/testing/selftests/sgx/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
index 8d2ba6adc92bd..867f88ce2570a 100644
--- a/tools/testing/selftests/sgx/Makefile
+++ b/tools/testing/selftests/sgx/Makefile
@@ -18,10 +18,10 @@ ENCL_CFLAGS += -Wall -Werror -static-pie -nostdlib -ffreestanding -fPIE \
 	       -fno-stack-protector -mrdrnd $(INCLUDES)
 ENCL_LDFLAGS := -Wl,-T,test_encl.lds,--build-id=none
 
+ifeq ($(CAN_BUILD_X86_64), 1)
 TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx
 TEST_FILES := $(OUTPUT)/test_encl.elf
 
-ifeq ($(CAN_BUILD_X86_64), 1)
 all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf
 endif
 
-- 
GitLab


From 849c1816436fe359e85587fba5b69ddd3a957b31 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 8 Dec 2023 13:46:22 -0500
Subject: [PATCH 1033/4076] KVM: selftests: fix supported_flags for aarch64

KVM/Arm supports readonly memslots; fix the calculation of
supported_flags in set_memory_region_test.c, otherwise the
test fails.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/set_memory_region_test.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 6637a0845acf0..dfd1d1e22da32 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -333,9 +333,11 @@ static void test_invalid_memory_region_flags(void)
 	struct kvm_vm *vm;
 	int r, i;
 
-#ifdef __x86_64__
+#if defined __aarch64__ || defined __x86_64__
 	supported_flags |= KVM_MEM_READONLY;
+#endif
 
+#ifdef __x86_64__
 	if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))
 		vm = vm_create_barebones_protected_vm();
 	else
-- 
GitLab


From 80583d0cfd8ff44d60a5fa76a6bf3c08eb67c328 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 8 Dec 2023 13:46:48 -0500
Subject: [PATCH 1034/4076] KVM: guest-memfd: fix unused-function warning

With migration disabled, one function becomes unused:

virt/kvm/guest_memfd.c:262:12: error: 'kvm_gmem_migrate_folio' defined but not used [-Werror=unused-function]
  262 | static int kvm_gmem_migrate_folio(struct address_space *mapping,
      |            ^~~~~~~~~~~~~~~~~~~~~~

Remove the #ifdef around the reference so that fallback_migrate_folio()
is never used.  The gmem implementation of the hook is trivial; since
the gmem mapping is unmovable, the pages should not be migrated anyway.

Fixes: a7800aa80ea4 ("KVM: Add KVM_CREATE_GUEST_MEMFD ioctl() for guest-specific backing memory")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/guest_memfd.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index b992723961195..c2e2371720a9c 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -300,9 +300,7 @@ static int kvm_gmem_error_page(struct address_space *mapping, struct page *page)
 
 static const struct address_space_operations kvm_gmem_aops = {
 	.dirty_folio = noop_dirty_folio,
-#ifdef CONFIG_MIGRATION
 	.migrate_folio	= kvm_gmem_migrate_folio,
-#endif
 	.error_remove_page = kvm_gmem_error_page,
 };
 
-- 
GitLab


From 75d6872907cc8827248f4d5f803c03e1175c3158 Mon Sep 17 00:00:00 2001
From: Adrien Leravat <adrien.leravat@gmail.com>
Date: Sun, 3 Dec 2023 12:06:04 -0800
Subject: [PATCH 1035/4076] doc: rmpsg: Update with rpmsg_endpoint

It seems the documentation was not updated when `rpmsg_sendto`
and related switched from `rpmsg_channel` to `rpmsg_endpoint`.
This change updates the proper calls, text, and the sample.

Signed-off-by: Adrien Leravat <adrien.leravat@gmail.com>
Link: https://lore.kernel.org/r/20231203200606.255302-1-adrien.leravat@gmail.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 Documentation/staging/rpmsg.rst | 50 ++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 23 deletions(-)

diff --git a/Documentation/staging/rpmsg.rst b/Documentation/staging/rpmsg.rst
index 1ce353cb232a3..dba3e5f656129 100644
--- a/Documentation/staging/rpmsg.rst
+++ b/Documentation/staging/rpmsg.rst
@@ -68,13 +68,14 @@ User API
 
 ::
 
-  int rpmsg_send(struct rpmsg_channel *rpdev, void *data, int len);
+  int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len);
 
-sends a message across to the remote processor on a given channel.
-The caller should specify the channel, the data it wants to send,
+sends a message across to the remote processor from the given endpoint.
+The caller should specify the endpoint, the data it wants to send,
 and its length (in bytes). The message will be sent on the specified
-channel, i.e. its source and destination address fields will be
-set to the channel's src and dst addresses.
+endpoint's channel, i.e. its source and destination address fields will be
+respectively set to the endpoint's src address and its parent channel
+dst addresses.
 
 In case there are no TX buffers available, the function will block until
 one becomes available (i.e. until the remote processor consumes
@@ -87,17 +88,18 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_sendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst);
+  int rpmsg_sendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst);
 
-sends a message across to the remote processor on a given channel,
+sends a message across to the remote processor from a given endpoint,
 to a destination address provided by the caller.
 
-The caller should specify the channel, the data it wants to send,
+The caller should specify the endpoint, the data it wants to send,
 its length (in bytes), and an explicit destination address.
 
 The message will then be sent to the remote processor to which the
-channel belongs, using the channel's src address, and the user-provided
-dst address (thus the channel's dst address will be ignored).
+endpoints's channel belongs, using the endpoints's src address,
+and the user-provided dst address (thus the channel's dst address
+will be ignored).
 
 In case there are no TX buffers available, the function will block until
 one becomes available (i.e. until the remote processor consumes
@@ -110,18 +112,19 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_send_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
+  int rpmsg_send_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst,
 							void *data, int len);
 
 
 sends a message across to the remote processor, using the src and dst
 addresses provided by the user.
 
-The caller should specify the channel, the data it wants to send,
+The caller should specify the endpoint, the data it wants to send,
 its length (in bytes), and explicit source and destination addresses.
 The message will then be sent to the remote processor to which the
-channel belongs, but the channel's src and dst addresses will be
-ignored (and the user-provided addresses will be used instead).
+endpoint's channel belongs, but the endpoint's src and channel dst
+addresses will be ignored (and the user-provided addresses will
+be used instead).
 
 In case there are no TX buffers available, the function will block until
 one becomes available (i.e. until the remote processor consumes
@@ -134,13 +137,14 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_trysend(struct rpmsg_channel *rpdev, void *data, int len);
+  int rpmsg_trysend(struct rpmsg_endpoint *ept, void *data, int len);
 
-sends a message across to the remote processor on a given channel.
-The caller should specify the channel, the data it wants to send,
+sends a message across to the remote processor from a given endpoint.
+The caller should specify the endpoint, the data it wants to send,
 and its length (in bytes). The message will be sent on the specified
-channel, i.e. its source and destination address fields will be
-set to the channel's src and dst addresses.
+endpoint's channel, i.e. its source and destination address fields will be
+respectively set to the endpoint's src address and its parent channel
+dst addresses.
 
 In case there are no TX buffers available, the function will immediately
 return -ENOMEM without waiting until one becomes available.
@@ -150,10 +154,10 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_trysendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst)
+  int rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst)
 
 
-sends a message across to the remote processor on a given channel,
+sends a message across to the remote processor from a given endoint,
 to a destination address provided by the user.
 
 The user should specify the channel, the data it wants to send,
@@ -171,7 +175,7 @@ Returns 0 on success and an appropriate error value on failure.
 
 ::
 
-  int rpmsg_trysend_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
+  int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst,
 							void *data, int len);
 
 
@@ -284,7 +288,7 @@ content to the console.
 	dev_info(&rpdev->dev, "chnl: 0x%x -> 0x%x\n", rpdev->src, rpdev->dst);
 
 	/* send a message on our channel */
-	err = rpmsg_send(rpdev, "hello!", 6);
+	err = rpmsg_send(rpdev->ept, "hello!", 6);
 	if (err) {
 		pr_err("rpmsg_send failed: %d\n", err);
 		return err;
-- 
GitLab


From 8132d887a7023b212f242a51ae89281c69fde996 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 18 Oct 2023 12:11:56 -0400
Subject: [PATCH 1036/4076] KVM: remove CONFIG_HAVE_KVM_EVENTFD

virt/kvm/eventfd.c is compiled unconditionally, meaning that the ioeventfds
member of struct kvm is accessed unconditionally.  CONFIG_HAVE_KVM_EVENTFD
therefore must be defined for KVM common code to compile successfully,
remove it.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/Kconfig     |  1 -
 arch/loongarch/kvm/Kconfig |  1 -
 arch/mips/kvm/Kconfig      |  1 -
 arch/powerpc/kvm/Kconfig   |  1 -
 arch/riscv/kvm/Kconfig     |  1 -
 arch/s390/kvm/Kconfig      |  1 -
 arch/x86/kvm/Kconfig       |  1 -
 include/linux/kvm_host.h   | 30 +-----------------------------
 virt/kvm/Kconfig           |  5 +----
 9 files changed, 2 insertions(+), 40 deletions(-)

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 1a777715199fa..87bd96c1254f4 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -29,7 +29,6 @@ menuconfig KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_VFIO
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select NEED_KVM_DIRTY_RING_WITH_BITMAP
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index f22bae89b07d3..daba4cd5e87d1 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -22,7 +22,6 @@ config KVM
 	depends on AS_HAS_LVZ_EXTENSION
 	depends on HAVE_KVM
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index c04987d2ed2e3..428141b0b48f5 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -22,7 +22,6 @@ config KVM
 	select EXPORT_UASM
 	select PREEMPT_NOTIFIERS
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_MMIO
 	select KVM_GENERIC_MMU_NOTIFIER
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index b33358ee64244..0f4e6e7ba35d7 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -20,7 +20,6 @@ if VIRTUALIZATION
 config KVM
 	bool
 	select PREEMPT_NOTIFIERS
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_VFIO
 	select IRQ_BYPASS_MANAGER
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index ae2e05f050ece..be264b78487d4 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -20,7 +20,6 @@ if VIRTUALIZATION
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
 	depends on RISCV_SBI && MMU
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 45fdf2a9b2e32..ed567b858535b 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -23,7 +23,6 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
-	select HAVE_KVM_EVENTFD
 	select KVM_ASYNC_PF
 	select KVM_ASYNC_PF_SYNC
 	select HAVE_KVM_IRQCHIP
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index c1716e83d1761..088c66bee98fb 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -33,7 +33,6 @@ config KVM
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_IRQ_ROUTING
-	select HAVE_KVM_EVENTFD
 	select KVM_ASYNC_PF
 	select USER_RETURN_NOTIFIER
 	select KVM_MMIO
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ea1523a7b83ad..3fe5a6be77688 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -782,7 +782,6 @@ struct kvm {
 	struct list_head vm_list;
 	struct mutex lock;
 	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
-#ifdef CONFIG_HAVE_KVM_EVENTFD
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
@@ -791,7 +790,6 @@ struct kvm {
 		struct mutex      resampler_lock;
 	} irqfds;
 	struct list_head ioeventfds;
-#endif
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	refcount_t users_count;
@@ -2056,8 +2054,6 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
 
-#ifdef CONFIG_HAVE_KVM_EVENTFD
-
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
@@ -2082,31 +2078,7 @@ static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
 {
 	return false;
 }
-#endif
-
-#else
-
-static inline void kvm_eventfd_init(struct kvm *kvm) {}
-
-static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
-{
-	return -EINVAL;
-}
-
-static inline void kvm_irqfd_release(struct kvm *kvm) {}
-
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm)
-{
-}
-#endif
-
-static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
-{
-	return -ENOSYS;
-}
-
-#endif /* CONFIG_HAVE_KVM_EVENTFD */
+#endif /* CONFIG_HAVE_KVM_IRQFD */
 
 void kvm_arch_irq_routing_update(struct kvm *kvm);
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 2c964586aa14e..72e0cac864f94 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -3,6 +3,7 @@
 
 config HAVE_KVM
        bool
+       select EVENTFD
 
 config HAVE_KVM_PFNCACHE
        bool
@@ -39,10 +40,6 @@ config NEED_KVM_DIRTY_RING_WITH_BITMAP
 	bool
 	depends on HAVE_KVM_DIRTY_RING
 
-config HAVE_KVM_EVENTFD
-       bool
-       select EVENTFD
-
 config KVM_MMIO
        bool
 
-- 
GitLab


From c5b31cc2371728ddefe9baf1d036aeb630a25d96 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 18 Oct 2023 12:07:32 -0400
Subject: [PATCH 1037/4076] KVM: remove CONFIG_HAVE_KVM_IRQFD

All platforms with a kernel irqchip have support for irqfd.  Unify the
two configuration items so that userspace can expect to use irqfd to
inject interrupts into the irqchip.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/Kconfig     | 1 -
 arch/powerpc/kvm/Kconfig   | 2 --
 arch/powerpc/kvm/powerpc.c | 2 +-
 arch/riscv/kvm/Kconfig     | 1 -
 arch/s390/kvm/Kconfig      | 1 -
 arch/x86/kvm/Kconfig       | 1 -
 include/linux/kvm_host.h   | 9 ++++-----
 include/trace/events/kvm.h | 8 ++++----
 virt/kvm/Kconfig           | 3 ---
 virt/kvm/eventfd.c         | 6 +++---
 virt/kvm/kvm_main.c        | 4 ++--
 11 files changed, 14 insertions(+), 24 deletions(-)

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 87bd96c1254f4..b07c60c9737dc 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -29,7 +29,6 @@ menuconfig KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_VFIO
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select NEED_KVM_DIRTY_RING_WITH_BITMAP
 	select HAVE_KVM_MSI
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 0f4e6e7ba35d7..b47196085a42d 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -224,7 +224,6 @@ config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && PPC_E500
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	help
@@ -237,7 +236,6 @@ config KVM_XICS
 	bool "KVM in-kernel XICS emulation"
 	depends on KVM_BOOK3S_64 && !KVM_MPIC
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	default y
 	help
 	  Include support for the XICS (eXternal Interrupt Controller
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index c39945a7fce36..c3f82e238b703 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -578,7 +578,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD_RESAMPLE:
 		r = !xive_enabled();
 		break;
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index be264b78487d4..2b0b510353020 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -21,7 +21,6 @@ config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
 	depends on RISCV_SBI && MMU
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index ed567b858535b..bb6d903511194 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -26,7 +26,6 @@ config KVM
 	select KVM_ASYNC_PF
 	select KVM_ASYNC_PF_SYNC
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_INVALID_WAKEUPS
 	select HAVE_KVM_NO_POLL
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 088c66bee98fb..b07247b0b958e 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -27,7 +27,6 @@ config KVM
 	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_TSO
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select IRQ_BYPASS_MANAGER
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3fe5a6be77688..1bba24a13ec93 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -805,8 +805,7 @@ struct kvm {
 	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
-#endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
@@ -996,7 +995,7 @@ static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
 }
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd_init(void);
 void kvm_irqfd_exit(void);
 #else
@@ -2057,7 +2056,7 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
 bool kvm_notify_irqfd_resampler(struct kvm *kvm,
@@ -2078,7 +2077,7 @@ static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
 {
 	return false;
 }
-#endif /* CONFIG_HAVE_KVM_IRQFD */
+#endif /* CONFIG_HAVE_KVM_IRQCHIP */
 
 void kvm_arch_irq_routing_update(struct kvm *kvm);
 
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 3bd31ea23fee9..011fba6b55522 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -62,7 +62,7 @@ TRACE_EVENT(kvm_vcpu_wakeup,
 		  __entry->valid ? "valid" : "invalid")
 );
 
-#if defined(CONFIG_HAVE_KVM_IRQFD)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
 	TP_ARGS(gsi, level, irq_source_id),
@@ -82,7 +82,7 @@ TRACE_EVENT(kvm_set_irq,
 	TP_printk("gsi %u level %d source %d",
 		  __entry->gsi, __entry->level, __entry->irq_source_id)
 );
-#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 #if defined(__KVM_HAVE_IOAPIC)
 #define kvm_deliver_mode		\
@@ -170,7 +170,7 @@ TRACE_EVENT(kvm_msi_set_irq,
 
 #endif /* defined(__KVM_HAVE_IOAPIC) */
 
-#if defined(CONFIG_HAVE_KVM_IRQFD)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 
 #ifdef kvm_irqchips
 #define kvm_ack_irq_string "irqchip %s pin %u"
@@ -197,7 +197,7 @@ TRACE_EVENT(kvm_ack_irq,
 	TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm)
 );
 
-#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 72e0cac864f94..6793211a0b642 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -11,9 +11,6 @@ config HAVE_KVM_PFNCACHE
 config HAVE_KVM_IRQCHIP
        bool
 
-config HAVE_KVM_IRQFD
-       bool
-
 config HAVE_KVM_IRQ_ROUTING
        bool
 
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 89912a17f5d57..19534156d48c5 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -28,7 +28,7 @@
 
 #include <kvm/iodev.h>
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 
 static struct workqueue_struct *irqfd_cleanup_wq;
 
@@ -531,7 +531,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
 	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
@@ -540,7 +540,7 @@ kvm_eventfd_init(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 /*
  * shutdown any irqfd's that match fd+gsi
  */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8758cb799e183..a20cf1f9ad290 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1273,7 +1273,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_disable;
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
@@ -4826,7 +4826,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #ifdef CONFIG_HAVE_KVM_MSI
 	case KVM_CAP_SIGNAL_MSI:
 #endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD:
 #endif
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
-- 
GitLab


From a5d3df8ae13fada772fbce952e9ee7b3433dba16 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 8 Nov 2023 10:34:03 +0100
Subject: [PATCH 1038/4076] KVM: remove deprecated UAPIs

The deprecated interfaces were removed 15 years ago.  KVM's
device assignment was deprecated in 4.2 and removed 6.5 years
ago; the only interest might be in compiling ancient versions
of QEMU, but QEMU has been using its own imported copy of the
kernel headers since June 2011.  So again we go into archaeology
territory; just remove the cruft.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 12 -----
 include/uapi/linux/kvm.h       | 90 ----------------------------------
 virt/kvm/kvm_main.c            |  5 --
 3 files changed, 107 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 926241e23aebb..9326af2a48696 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -627,18 +627,6 @@ interrupt number dequeues the interrupt.
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 
-4.17 KVM_DEBUG_GUEST
---------------------
-
-:Capability: basic
-:Architectures: none
-:Type: vcpu ioctl
-:Parameters: none)
-:Returns: -1 on error
-
-Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.
-
-
 4.18 KVM_GET_MSRS
 -----------------
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e9cb2df67a1db..b1f92a0edc356 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -16,76 +16,6 @@
 
 #define KVM_API_VERSION 12
 
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT           16
-
-#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE       12
-#define KVM_TRC_CYCLE_SIZE      8
-#define KVM_TRC_EXTRA_MAX       7
-
-#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
-	__u32 buf_size;
-	__u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
-	_IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-struct kvm_debug_guest {
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
@@ -967,9 +897,6 @@ struct kvm_ppc_resize_hpt {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 #define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
@@ -1536,20 +1463,8 @@ struct kvm_s390_ucas_mapping {
 			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
 #define KVM_UNREGISTER_COALESCED_MMIO \
 			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
-				       struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
-#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
-				       struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
-				       struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
-				       struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
 #define KVM_CREATE_PIT2		  _IOW(KVMIO,  0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
@@ -1566,9 +1481,6 @@ struct kvm_s390_ucas_mapping {
 *  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
-				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 /* Available with KVM_CAP_PPC_GET_SMMU_INFO */
@@ -1621,8 +1533,6 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a20cf1f9ad290..acd67fb401833 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5497,11 +5497,6 @@ static long kvm_dev_ioctl(struct file *filp,
 		r += PAGE_SIZE;    /* coalesced mmio ring page */
 #endif
 		break;
-	case KVM_TRACE_ENABLE:
-	case KVM_TRACE_PAUSE:
-	case KVM_TRACE_DISABLE:
-		r = -EOPNOTSUPP;
-		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);
 	}
-- 
GitLab


From 8ed26ab8d59111c2f7b86d200d1eb97d2a458fd1 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 18 Oct 2023 12:18:00 -0400
Subject: [PATCH 1039/4076] KVM: clean up directives to compile out irqfds

Keep all #ifdef CONFIG_HAVE_KVM_IRQCHIP parts of eventfd.c together, and
compile out the irqfds field of struct kvm if the symbol is not defined.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  2 ++
 virt/kvm/eventfd.c       | 26 ++++++++++++--------------
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1bba24a13ec93..7e7fd25b09b3e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -782,6 +782,7 @@ struct kvm {
 	struct list_head vm_list;
 	struct mutex lock;
 	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
@@ -789,6 +790,7 @@ struct kvm {
 		struct list_head  resampler_list;
 		struct mutex      resampler_lock;
 	} irqfds;
+#endif
 	struct list_head ioeventfds;
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 19534156d48c5..d516e6d33f56f 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -526,21 +526,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 	synchronize_srcu(&kvm->irq_srcu);
 	kvm_arch_post_irq_ack_notifier_list_update(kvm);
 }
-#endif
-
-void
-kvm_eventfd_init(struct kvm *kvm)
-{
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
-	spin_lock_init(&kvm->irqfds.lock);
-	INIT_LIST_HEAD(&kvm->irqfds.items);
-	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
-	mutex_init(&kvm->irqfds.resampler_lock);
-#endif
-	INIT_LIST_HEAD(&kvm->ioeventfds);
-}
 
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -1012,3 +998,15 @@ kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	return kvm_assign_ioeventfd(kvm, args);
 }
+
+void
+kvm_eventfd_init(struct kvm *kvm)
+{
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+	spin_lock_init(&kvm->irqfds.lock);
+	INIT_LIST_HEAD(&kvm->irqfds.items);
+	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
+	mutex_init(&kvm->irqfds.resampler_lock);
+#endif
+	INIT_LIST_HEAD(&kvm->ioeventfds);
+}
-- 
GitLab


From 7048708fec3a401f9a70e4a74e2e12aa7f88c132 Mon Sep 17 00:00:00 2001
From: Johan Jonker <jbx6244@gmail.com>
Date: Mon, 4 Dec 2023 18:39:03 +0100
Subject: [PATCH 1040/4076] dt-bindings: drm: rockchip: convert
 inno_hdmi-rockchip.txt to yaml

Convert inno_hdmi-rockchip.txt to yaml.

Signed-off-by: Johan Jonker <jbx6244@gmail.com>
Link: https://lore.kernel.org/r/49c6afec-022f-02de-99a0-d409b64da198@gmail.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../display/rockchip/inno_hdmi-rockchip.txt   |  49 ---------
 .../display/rockchip/rockchip,inno-hdmi.yaml  | 103 ++++++++++++++++++
 2 files changed, 103 insertions(+), 49 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/display/rockchip/inno_hdmi-rockchip.txt
 create mode 100644 Documentation/devicetree/bindings/display/rockchip/rockchip,inno-hdmi.yaml

diff --git a/Documentation/devicetree/bindings/display/rockchip/inno_hdmi-rockchip.txt b/Documentation/devicetree/bindings/display/rockchip/inno_hdmi-rockchip.txt
deleted file mode 100644
index cec21714f0e0a..0000000000000
--- a/Documentation/devicetree/bindings/display/rockchip/inno_hdmi-rockchip.txt
+++ /dev/null
@@ -1,49 +0,0 @@
-Rockchip specific extensions to the Innosilicon HDMI
-================================
-
-Required properties:
-- compatible:
-	"rockchip,rk3036-inno-hdmi";
-- reg:
-	Physical base address and length of the controller's registers.
-- clocks, clock-names:
-	Phandle to hdmi controller clock, name should be "pclk"
-- interrupts:
-	HDMI interrupt number
-- ports:
-	Contain one port node with endpoint definitions as defined in
-	Documentation/devicetree/bindings/graph.txt.
-- pinctrl-0, pinctrl-name:
-	Switch the iomux of HPD/CEC pins to HDMI function.
-
-Example:
-hdmi: hdmi@20034000 {
-	compatible = "rockchip,rk3036-inno-hdmi";
-	reg = <0x20034000 0x4000>;
-	interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
-	clocks = <&cru  PCLK_HDMI>;
-	clock-names = "pclk";
-	pinctrl-names = "default";
-	pinctrl-0 = <&hdmi_ctl>;
-
-	hdmi_in: port {
-		#address-cells = <1>;
-		#size-cells = <0>;
-		hdmi_in_lcdc: endpoint@0 {
-			reg = <0>;
-			remote-endpoint = <&lcdc_out_hdmi>;
-		};
-	};
-};
-
-&pinctrl {
-	hdmi {
-		hdmi_ctl: hdmi-ctl {
-			rockchip,pins = <1 8  RK_FUNC_1 &pcfg_pull_none>,
-					<1 9  RK_FUNC_1 &pcfg_pull_none>,
-					<1 10 RK_FUNC_1 &pcfg_pull_none>,
-					<1 11 RK_FUNC_1 &pcfg_pull_none>;
-		};
-	};
-
-};
diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip,inno-hdmi.yaml b/Documentation/devicetree/bindings/display/rockchip/rockchip,inno-hdmi.yaml
new file mode 100644
index 0000000000000..96889c86849ab
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/rockchip/rockchip,inno-hdmi.yaml
@@ -0,0 +1,103 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/rockchip/rockchip,inno-hdmi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip Innosilicon HDMI controller
+
+maintainers:
+  - Sandy Huang <hjc@rock-chips.com>
+  - Heiko Stuebner <heiko@sntech.de>
+
+properties:
+  compatible:
+    enum:
+      - rockchip,rk3036-inno-hdmi
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: pclk
+
+  ports:
+    $ref: /schemas/graph.yaml#/properties/ports
+
+    properties:
+      port@0:
+        $ref: /schemas/graph.yaml#/properties/port
+        description:
+          Port node with one endpoint connected to a vop node.
+
+      port@1:
+        $ref: /schemas/graph.yaml#/properties/port
+        description:
+          Port node with one endpoint connected to a hdmi-connector node.
+
+    required:
+      - port@0
+      - port@1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - pinctrl-0
+  - pinctrl-names
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/rk3036-cru.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/pinctrl/rockchip.h>
+    hdmi: hdmi@20034000 {
+      compatible = "rockchip,rk3036-inno-hdmi";
+      reg = <0x20034000 0x4000>;
+      interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
+      clocks = <&cru  PCLK_HDMI>;
+      clock-names = "pclk";
+      pinctrl-names = "default";
+      pinctrl-0 = <&hdmi_ctl>;
+
+      ports {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        hdmi_in: port@0 {
+          reg = <0>;
+          hdmi_in_vop: endpoint {
+            remote-endpoint = <&vop_out_hdmi>;
+          };
+        };
+
+        hdmi_out: port@1 {
+          reg = <1>;
+          hdmi_out_con: endpoint {
+            remote-endpoint = <&hdmi_con_in>;
+          };
+        };
+      };
+    };
+
+    pinctrl {
+      hdmi {
+        hdmi_ctl: hdmi-ctl {
+          rockchip,pins = <1 RK_PB0 1 &pcfg_pull_none>,
+                          <1 RK_PB1 1 &pcfg_pull_none>,
+                          <1 RK_PB2 1 &pcfg_pull_none>,
+                          <1 RK_PB3 1 &pcfg_pull_none>;
+        };
+      };
+    };
-- 
GitLab


From d3e09f57345f86cf5c47a89fc216f6c98f9a4a7a Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Fri, 8 Dec 2023 13:20:35 +0530
Subject: [PATCH 1041/4076] dt-bindings: input: gpio-mouse: Convert to
 json-schema

Convert device tree binding documentation for GPIO attached mouse to
json-schema.

Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231208075037.114598-1-anshulusr@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/gpio-mouse.txt  | 32 ---------
 .../devicetree/bindings/input/gpio-mouse.yaml | 68 +++++++++++++++++++
 2 files changed, 68 insertions(+), 32 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/input/gpio-mouse.txt
 create mode 100644 Documentation/devicetree/bindings/input/gpio-mouse.yaml

diff --git a/Documentation/devicetree/bindings/input/gpio-mouse.txt b/Documentation/devicetree/bindings/input/gpio-mouse.txt
deleted file mode 100644
index 519510a11af98..0000000000000
--- a/Documentation/devicetree/bindings/input/gpio-mouse.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-Device-Tree bindings for GPIO attached mice
-
-This simply uses standard GPIO handles to define a simple mouse connected
-to 5-7 GPIO lines.
-
-Required properties:
-	- compatible: must be "gpio-mouse"
-	- scan-interval-ms: The scanning interval in milliseconds
-	- up-gpios: GPIO line phandle to the line indicating "up"
-	- down-gpios: GPIO line phandle to the line indicating "down"
-	- left-gpios: GPIO line phandle to the line indicating "left"
-	- right-gpios: GPIO line phandle to the line indicating "right"
-
-Optional properties:
-	- button-left-gpios: GPIO line handle to the left mouse button
-	- button-middle-gpios: GPIO line handle to the middle mouse button
-	- button-right-gpios: GPIO line handle to the right mouse button
-Example:
-
-#include <dt-bindings/gpio/gpio.h>
-
-gpio-mouse {
-	compatible = "gpio-mouse";
-	scan-interval-ms = <50>;
-	up-gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
-	down-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
-	left-gpios = <&gpio0 2 GPIO_ACTIVE_LOW>;
-	right-gpios = <&gpio0 3 GPIO_ACTIVE_LOW>;
-	button-left-gpios = <&gpio0 4 GPIO_ACTIVE_LOW>;
-	button-middle-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
-	button-right-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>;
-};
diff --git a/Documentation/devicetree/bindings/input/gpio-mouse.yaml b/Documentation/devicetree/bindings/input/gpio-mouse.yaml
new file mode 100644
index 0000000000000..3928ec6aff1dc
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/gpio-mouse.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/gpio-mouse.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: GPIO attached mouse
+
+description: |
+  This simply uses standard GPIO handles to define a simple mouse connected
+  to 5-7 GPIO lines.
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+properties:
+  compatible:
+    const: gpio-mouse
+
+  scan-interval-ms:
+    maxItems: 1
+
+  up-gpios:
+    maxItems: 1
+
+  down-gpios:
+    maxItems: 1
+
+  left-gpios:
+    maxItems: 1
+
+  right-gpios:
+    maxItems: 1
+
+  button-left-gpios:
+    maxItems: 1
+
+  button-middle-gpios:
+    maxItems: 1
+
+  button-right-gpios:
+    maxItems: 1
+
+required:
+  - compatible
+  - scan-interval-ms
+  - up-gpios
+  - down-gpios
+  - left-gpios
+  - right-gpios
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    gpio-mouse {
+        compatible = "gpio-mouse";
+        scan-interval-ms = <50>;
+        up-gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+        down-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
+        left-gpios = <&gpio0 2 GPIO_ACTIVE_LOW>;
+        right-gpios = <&gpio0 3 GPIO_ACTIVE_LOW>;
+        button-left-gpios = <&gpio0 4 GPIO_ACTIVE_LOW>;
+        button-middle-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
+        button-right-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>;
+    };
-- 
GitLab


From 93596ac342c501db98dbd7b94bc60c12daad7569 Mon Sep 17 00:00:00 2001
From: Umang Jain <umang.jain@ideasonboard.com>
Date: Thu, 7 Dec 2023 14:08:36 +0530
Subject: [PATCH 1042/4076] staging: vc04_services: vchiq_arm: Use %p to log
 pointer address

Solves the following Smatch warnings:
service_callback() warn: argument 7 to %lx specifier is cast from pointer
service_callback() warn: argument 11 to %lx specifier is cast from pointer
service_callback() warn: argument 12 to %lx specifier is cast from pointer
service_callback() warn: argument 13 to %lx specifier is cast from pointer

%p will print the hashed pointer to dynamic debug.
In order to print the unmodified pointer address, one can use the
`no_hash_pointers` via kernel parameters.

Signed-off-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/20231207083837.153843-2-umang.jain@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../staging/vc04_services/interface/vchiq_arm/vchiq_arm.c  | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 4b4ff469d3a31..1579bd4e5263c 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -1088,10 +1088,9 @@ service_callback(struct vchiq_instance *instance, enum vchiq_reason reason,
 	rcu_read_unlock();
 
 	dev_dbg(service->state->dev,
-		"arm: service %lx(%d,%p), reason %d, header %lx, instance %lx, bulk_userdata %lx\n",
-		(unsigned long)user_service, service->localport,
-		user_service->userdata, reason, (unsigned long)header,
-		(unsigned long)instance, (unsigned long)bulk_userdata);
+		"arm: service %p(%d,%p), reason %d, header %p, instance %p, bulk_userdata %p\n",
+		user_service, service->localport, user_service->userdata,
+		reason, header, instance, bulk_userdata);
 
 	if (header && user_service->is_vchi) {
 		spin_lock(&msg_queue_spinlock);
-- 
GitLab


From 6cb3158903c6402d7be26677becde5dc1862a48b Mon Sep 17 00:00:00 2001
From: Umang Jain <umang.jain@ideasonboard.com>
Date: Thu, 7 Dec 2023 14:08:37 +0530
Subject: [PATCH 1043/4076] staging: vc04_services: vchiq_dev: Use %p to log
 pointer address

Solves the following Smatch warnings:
vchiq_release() warn: argument 7 to %lx specifier is cast from pointer

%p will print the hashed pointer to dynamic debug.
In order to print the unmodified pointer address, one can use the
`no_hash_pointers` via kernel parameters.

Signed-off-by: Umang Jain <umang.jain@ideasonboard.com>
Link: https://lore.kernel.org/r/20231207083837.153843-3-umang.jain@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
index 68c8897c504c3..4d9deeeb637aa 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_dev.c
@@ -1201,7 +1201,7 @@ static int vchiq_release(struct inode *inode, struct file *file)
 	int ret = 0;
 	int i;
 
-	dev_dbg(state->dev, "arm: instance=%lx\n", (unsigned long)instance);
+	dev_dbg(state->dev, "arm: instance=%p\n", instance);
 
 	if (!state) {
 		ret = -EPERM;
-- 
GitLab


From cbf028b29d17ebc1ab35cc1baf0d29c6b9b693d8 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Wed, 6 Dec 2023 18:04:00 -0500
Subject: [PATCH 1044/4076] staging: rtl8192e: renamed variable bAMSDU_Support

Coding style issue, checkpatch Avoid CamelCase,
rename it. bAMSDU_Suppport -> amsdu_support

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231206230404.1721-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 5018c3905be85..e02fa40262bd6 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -107,7 +107,7 @@ struct rt_hi_throughput {
 	struct ht_info_ele SelfHTInfo;
 	u8 PeerHTCapBuf[32];
 	u8 PeerHTInfoBuf[32];
-	u8 bAMSDU_Support;
+	u8 amsdu_support;
 	u16 amsdu_max_size;
 	u8 bCurrent_AMSDU_Support;
 	u16 nCurrent_AMSDU_MaxSize;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 6475832f23f67..b2f2e1c0cf6b8 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -82,7 +82,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 		ht_info->reg_supp_cck = true;
 
 	ht_info->amsdu_max_size = 7935UL;
-	ht_info->bAMSDU_Support = 0;
+	ht_info->amsdu_support = 0;
 
 	ht_info->bAMPDUEnable = 1;
 	ht_info->AMPDU_Factor = 2;
@@ -489,7 +489,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 			       ((pPeerHTCap->DssCCk == 1) ? true :
 			       false) : false);
 
-	ht_info->bCurrent_AMSDU_Support = ht_info->bAMSDU_Support;
+	ht_info->bCurrent_AMSDU_Support = ht_info->amsdu_support;
 
 	nMaxAMSDUSize = (pPeerHTCap->MaxAMSDUSize == 0) ? 3839 : 7935;
 
-- 
GitLab


From e97f14e92dd422cd1dd265dc086b73354293080f Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Wed, 6 Dec 2023 18:04:01 -0500
Subject: [PATCH 1045/4076] staging: rtl8192e: renamed variable bAMPDUEnable

Coding style issue, checkpatch Avoid CamelCase,
rename it. bAMPDUEnable -> ampdu_enable

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231206230404.1721-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 +-
 drivers/staging/rtl8192e/rtl819x_HT.h          | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c      | 4 ++--
 drivers/staging/rtl8192e/rtllib.h              | 2 +-
 drivers/staging/rtl8192e/rtllib_tx.c           | 8 ++++----
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index 13e3f26279aa8..fe48cc6b7132a 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -883,7 +883,7 @@ void  rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc,
 	pTxFwInfo->Short = _rtl92e_query_is_short(pTxFwInfo->TxHT,
 						  pTxFwInfo->TxRate, cb_desc);
 
-	if (cb_desc->bAMPDUEnable) {
+	if (cb_desc->ampdu_enable) {
 		pTxFwInfo->AllowAggregation = 1;
 		pTxFwInfo->RxMF = cb_desc->ampdu_factor;
 		pTxFwInfo->RxAMD = cb_desc->ampdu_density;
diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index e02fa40262bd6..7a3e36db849c3 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -111,7 +111,7 @@ struct rt_hi_throughput {
 	u16 amsdu_max_size;
 	u8 bCurrent_AMSDU_Support;
 	u16 nCurrent_AMSDU_MaxSize;
-	u8 bAMPDUEnable;
+	u8 ampdu_enable;
 	u8 current_ampdu_enable;
 	u8 AMPDU_Factor;
 	u8 CurrentAMPDUFactor;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index b2f2e1c0cf6b8..9841af15089fc 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -84,7 +84,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->amsdu_max_size = 7935UL;
 	ht_info->amsdu_support = 0;
 
-	ht_info->bAMPDUEnable = 1;
+	ht_info->ampdu_enable = 1;
 	ht_info->AMPDU_Factor = 2;
 	ht_info->MPDU_Density = 0;
 
@@ -498,7 +498,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	else
 		ht_info->nCurrent_AMSDU_MaxSize = ht_info->amsdu_max_size;
 
-	ht_info->current_ampdu_enable = ht_info->bAMPDUEnable;
+	ht_info->current_ampdu_enable = ht_info->ampdu_enable;
 	if (ieee->rtllib_ap_sec_type &&
 	    (ieee->rtllib_ap_sec_type(ieee) & (SEC_ALG_WEP | SEC_ALG_TKIP))) {
 		if ((ht_info->IOTPeer == HT_IOT_PEER_ATHEROS) ||
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 0a8c44e497f5c..eb6e02f3d6b26 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -118,7 +118,7 @@ struct cb_desc {
 	u8 bUseShortGI:1;
 	u8 bUseShortPreamble:1;
 	u8 bTxEnableFwCalcDur:1;
-	u8 bAMPDUEnable:1;
+	u8 ampdu_enable:1;
 	u8 bRTSSTBC:1;
 	u8 RTSSC:1;
 
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 1468bbf1e23af..9981bf4eabff8 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -312,7 +312,7 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 				goto FORCED_AGG_SETTING;
 		}
 		if (ieee->iw_mode == IW_MODE_INFRA) {
-			tcb_desc->bAMPDUEnable = true;
+			tcb_desc->ampdu_enable = true;
 			tcb_desc->ampdu_factor = ht_info->CurrentAMPDUFactor;
 			tcb_desc->ampdu_density = ht_info->current_mpdu_density;
 		}
@@ -323,13 +323,13 @@ FORCED_AGG_SETTING:
 		break;
 
 	case HT_AGG_FORCE_ENABLE:
-		tcb_desc->bAMPDUEnable = true;
+		tcb_desc->ampdu_enable = true;
 		tcb_desc->ampdu_density = ht_info->forced_mpdu_density;
 		tcb_desc->ampdu_factor = ht_info->forced_ampdu_factor;
 		break;
 
 	case HT_AGG_FORCE_DISABLE:
-		tcb_desc->bAMPDUEnable = false;
+		tcb_desc->ampdu_enable = false;
 		tcb_desc->ampdu_density = 0;
 		tcb_desc->ampdu_factor = 0;
 		break;
@@ -454,7 +454,7 @@ static void rtllib_query_protectionmode(struct rtllib_device *ieee,
 			tcb_desc->bRTSEnable = true;
 			break;
 		}
-		if (tcb_desc->bAMPDUEnable) {
+		if (tcb_desc->ampdu_enable) {
 			tcb_desc->rts_rate = MGN_24M;
 			tcb_desc->bRTSEnable = false;
 			break;
-- 
GitLab


From 1d7ce9861b53ab4a548f178ebf5ad8f2afbd65fa Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Wed, 6 Dec 2023 18:04:02 -0500
Subject: [PATCH 1046/4076] staging: rtl8192e: renamed variable AMPDU_Factor

Coding style issue, checkpatch Avoid CamelCase,
rename it. AMPDU_Factor -> ampdu_factor

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231206230404.1721-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 7a3e36db849c3..c01ccf2529249 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -113,7 +113,7 @@ struct rt_hi_throughput {
 	u16 nCurrent_AMSDU_MaxSize;
 	u8 ampdu_enable;
 	u8 current_ampdu_enable;
-	u8 AMPDU_Factor;
+	u8 ampdu_factor;
 	u8 CurrentAMPDUFactor;
 	u8 MPDU_Density;
 	u8 current_mpdu_density;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 9841af15089fc..0f044356e4281 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -85,7 +85,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->amsdu_support = 0;
 
 	ht_info->ampdu_enable = 1;
-	ht_info->AMPDU_Factor = 2;
+	ht_info->ampdu_factor = 2;
 	ht_info->MPDU_Density = 0;
 
 	ht_info->self_mimo_ps = 3;
@@ -507,11 +507,11 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	}
 
 	if (!ht_info->reg_rt2rt_aggregation) {
-		if (ht_info->AMPDU_Factor > pPeerHTCap->MaxRxAMPDUFactor)
+		if (ht_info->ampdu_factor > pPeerHTCap->MaxRxAMPDUFactor)
 			ht_info->CurrentAMPDUFactor =
 						 pPeerHTCap->MaxRxAMPDUFactor;
 		else
-			ht_info->CurrentAMPDUFactor = ht_info->AMPDU_Factor;
+			ht_info->CurrentAMPDUFactor = ht_info->ampdu_factor;
 
 	} else {
 		if (ieee->current_network.bssht.bd_rt2rt_aggregation) {
@@ -571,7 +571,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	ht_info->bCurrent_AMSDU_Support = false;
 	ht_info->nCurrent_AMSDU_MaxSize = ht_info->amsdu_max_size;
 	ht_info->current_mpdu_density = ht_info->MPDU_Density;
-	ht_info->CurrentAMPDUFactor = ht_info->AMPDU_Factor;
+	ht_info->CurrentAMPDUFactor = ht_info->ampdu_factor;
 
 	memset((void *)(&ht_info->SelfHTCap), 0,
 	       sizeof(ht_info->SelfHTCap));
-- 
GitLab


From bc36fa00acfac1c3cc35fc03a9bd503beb91a3ad Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Wed, 6 Dec 2023 18:04:03 -0500
Subject: [PATCH 1047/4076] staging: rtl8192e: renamed variable MPDU_Density

Coding style issue, checkpatch Avoid CamelCase,
rename it. MPDU_Density -> mpdu_density

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231206230404.1721-5-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index c01ccf2529249..98c1e5840e31b 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -115,7 +115,7 @@ struct rt_hi_throughput {
 	u8 current_ampdu_enable;
 	u8 ampdu_factor;
 	u8 CurrentAMPDUFactor;
-	u8 MPDU_Density;
+	u8 mpdu_density;
 	u8 current_mpdu_density;
 	enum ht_aggre_mode ForcedAMPDUMode;
 	u8 forced_ampdu_factor;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 0f044356e4281..72b30d4df5f7d 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -86,7 +86,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 
 	ht_info->ampdu_enable = 1;
 	ht_info->ampdu_factor = 2;
-	ht_info->MPDU_Density = 0;
+	ht_info->mpdu_density = 0;
 
 	ht_info->self_mimo_ps = 3;
 	if (ht_info->self_mimo_ps == 2)
@@ -525,7 +525,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 							    HT_AGG_SIZE_32K);
 		}
 	}
-	ht_info->current_mpdu_density = max_t(u8, ht_info->MPDU_Density,
+	ht_info->current_mpdu_density = max_t(u8, ht_info->mpdu_density,
 					      pPeerHTCap->MPDUDensity);
 	if (ht_info->iot_action & HT_IOT_ACT_TX_USE_AMSDU_8K) {
 		ht_info->current_ampdu_enable = false;
@@ -570,7 +570,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 
 	ht_info->bCurrent_AMSDU_Support = false;
 	ht_info->nCurrent_AMSDU_MaxSize = ht_info->amsdu_max_size;
-	ht_info->current_mpdu_density = ht_info->MPDU_Density;
+	ht_info->current_mpdu_density = ht_info->mpdu_density;
 	ht_info->CurrentAMPDUFactor = ht_info->ampdu_factor;
 
 	memset((void *)(&ht_info->SelfHTCap), 0,
-- 
GitLab


From 445bdee3ee88db62a0aca176724de9fcd3381a14 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Wed, 6 Dec 2023 18:04:04 -0500
Subject: [PATCH 1048/4076] staging: rtl8192e: renamed variable
 bTxEnableFwCalcDur

Coding style issue, checkpatch Avoid CamelCase,
rename it. bTxEnableFwCalcDur -> tx_enable_fw_calc_dur

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231206230404.1721-6-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 +-
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c   | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c      | 2 +-
 drivers/staging/rtl8192e/rtllib.h              | 4 ++--
 drivers/staging/rtl8192e/rtllib_tx.c           | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index fe48cc6b7132a..39fa5f60db457 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -879,7 +879,7 @@ void  rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc,
 	memset(pTxFwInfo, 0, sizeof(struct tx_fwinfo_8190pci));
 	pTxFwInfo->TxHT = (cb_desc->data_rate & 0x80) ? 1 : 0;
 	pTxFwInfo->TxRate = _rtl92e_rate_mgn_to_hw(cb_desc->data_rate);
-	pTxFwInfo->EnableCPUDur = cb_desc->bTxEnableFwCalcDur;
+	pTxFwInfo->EnableCPUDur = cb_desc->tx_enable_fw_calc_dur;
 	pTxFwInfo->Short = _rtl92e_query_is_short(pTxFwInfo->TxHT,
 						  pTxFwInfo->TxRate, cb_desc);
 
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index bad34221d8b70..1f45b6b00d1b2 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -1189,7 +1189,7 @@ static int _rtl92e_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	tcb_desc->ratr_index = 7;
 	tcb_desc->tx_dis_rate_fallback = 1;
 	tcb_desc->tx_use_drv_assinged_rate = 1;
-	tcb_desc->bTxEnableFwCalcDur = 1;
+	tcb_desc->tx_enable_fw_calc_dur = 1;
 	skb_push(skb, priv->rtllib->tx_headroom);
 	ret = _rtl92e_tx(dev, skb);
 	if (ret != 0)
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 72b30d4df5f7d..a421c56af9e24 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -94,7 +94,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ieee->tx_dis_rate_fallback = 0;
 	ieee->tx_use_drv_assinged_rate = 0;
 
-	ieee->bTxEnableFwCalcDur = 1;
+	ieee->tx_enable_fw_calc_dur = 1;
 
 	ht_info->reg_rt2rt_aggregation = 1;
 
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index eb6e02f3d6b26..ec720f7766390 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -117,7 +117,7 @@ struct cb_desc {
 	u8 bRTSEnable:1;
 	u8 bUseShortGI:1;
 	u8 bUseShortPreamble:1;
-	u8 bTxEnableFwCalcDur:1;
+	u8 tx_enable_fw_calc_dur:1;
 	u8 ampdu_enable:1;
 	u8 bRTSSTBC:1;
 	u8 RTSSC:1;
@@ -1223,7 +1223,7 @@ struct rtllib_device {
 	u8	HTHighestOperaRate;
 	u8	tx_dis_rate_fallback;
 	u8	tx_use_drv_assinged_rate;
-	u8	bTxEnableFwCalcDur;
+	u8	tx_enable_fw_calc_dur;
 	atomic_t	atm_swbw;
 
 	struct list_head		Tx_TS_Admit_List;
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 9981bf4eabff8..b8f8c9039e01f 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -847,7 +847,7 @@ static int rtllib_xmit_inter(struct sk_buff *skb, struct net_device *dev)
 	if (txb) {
 		tcb_desc = (struct cb_desc *)
 				(txb->fragments[0]->cb + MAX_DEV_ADDR_SIZE);
-		tcb_desc->bTxEnableFwCalcDur = 1;
+		tcb_desc->tx_enable_fw_calc_dur = 1;
 		tcb_desc->priority = skb->priority;
 
 		if (ether_type == ETH_P_PAE) {
-- 
GitLab


From 97cb8afde7eef551cb6a546f5d77c86f05e34107 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 8 Dec 2023 19:19:32 +0100
Subject: [PATCH 1049/4076] staging: rtl8192e: Remove function
 rtllib_update_active_chan_map()

Remove function rtllib_update_active_chan_map() as "active_channel_map"
and "channel_map" have the same content.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/bae3ddeffe96e4ac7d929127ce3a72cd23fae8dd.1701989555.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index d209706524322..fdb0e76d20b09 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -394,12 +394,6 @@ static void rtllib_send_probe_requests(struct rtllib_device *ieee)
 	}
 }
 
-static void rtllib_update_active_chan_map(struct rtllib_device *ieee)
-{
-	memcpy(ieee->active_channel_map, GET_DOT11D_INFO(ieee)->channel_map,
-	       MAX_CHANNEL_NUMBER + 1);
-}
-
 /* this performs syncro scan blocking the caller until all channels
  * in the allowed channel map has been checked.
  */
@@ -408,8 +402,6 @@ static void rtllib_softmac_scan_syncro(struct rtllib_device *ieee)
 	union iwreq_data wrqu;
 	short ch = 0;
 
-	rtllib_update_active_chan_map(ieee);
-
 	ieee->be_scan_inprogress = true;
 
 	mutex_lock(&ieee->scan_mutex);
@@ -475,8 +467,6 @@ static void rtllib_softmac_scan_wq(void *data)
 				     struct rtllib_device, softmac_scan_wq);
 	u8 last_channel = ieee->current_network.channel;
 
-	rtllib_update_active_chan_map(ieee);
-
 	if (!ieee->ieee_up)
 		return;
 	if (rtllib_act_scanning(ieee, true))
@@ -2042,8 +2032,6 @@ void rtllib_start_protocol(struct rtllib_device *ieee)
 	short ch = 0;
 	int i = 0;
 
-	rtllib_update_active_chan_map(ieee);
-
 	if (ieee->proto_started)
 		return;
 
-- 
GitLab


From 5c983f61875f8372997bc678a53c8c6a734e408c Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 8 Dec 2023 19:19:45 +0100
Subject: [PATCH 1050/4076] staging: rtl8192e: Remove variable channel_map

Remove variable channel_map as it is initialized but not used. Remove
channel_array as well as it is without channel_map unused.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/19ca762b4b9d5a3e857b31c22f0688324ca3bd9d.1701989555.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c | 10 ----------
 drivers/staging/rtl8192e/dot11d.h |  1 -
 2 files changed, 11 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index d51d4afff61e8..c44ff26e8d619 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -12,18 +12,8 @@ struct channel_list {
 	u8      len;
 };
 
-static struct channel_list channel_array = {{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, 13};
-
 void dot11d_channel_map(struct rtllib_device *ieee)
 {
-	int i;
-
-	memset(GET_DOT11D_INFO(ieee)->channel_map, 0,
-	       sizeof(GET_DOT11D_INFO(ieee)->channel_map));
-	for (i = 0; i < channel_array.len; i++)
-		GET_DOT11D_INFO(ieee)->channel_map[channel_array.channel[i]] = 1;
 
-	for (i = 12; i <= 13; i++)
-		GET_DOT11D_INFO(ieee)->channel_map[i] = 2;
 }
 EXPORT_SYMBOL(dot11d_channel_map);
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 5c02e51c39cd2..d047283f2cebb 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -19,7 +19,6 @@
  */
 
 struct rt_dot11d_info {
-	u8  channel_map[MAX_CHANNEL_NUMBER + 1];
 };
 
 #define GET_DOT11D_INFO(__ieee_dev)			\
-- 
GitLab


From 0c2d3ca5608402c04c673538139578f52193d7a7 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 8 Dec 2023 19:19:51 +0100
Subject: [PATCH 1051/4076] staging: rtl8192e: Remove variable dot11d_info

Remove variable dot11d_info as it is unused. Remove unused struct
channel_list and empty struct rt_dot11d_info.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/2438971feb0c02c5c72776f57201a4011f249190.1701989555.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c         | 5 -----
 drivers/staging/rtl8192e/dot11d.h         | 6 ------
 drivers/staging/rtl8192e/rtllib.h         | 1 -
 drivers/staging/rtl8192e/rtllib_softmac.c | 6 ------
 4 files changed, 18 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index c44ff26e8d619..8d89f962b3bf4 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -7,11 +7,6 @@
  ******************************************************************************/
 #include "dot11d.h"
 
-struct channel_list {
-	u8      channel[32];
-	u8      len;
-};
-
 void dot11d_channel_map(struct rtllib_device *ieee)
 {
 
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index d047283f2cebb..98aa28d0cf721 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -18,12 +18,6 @@
  *		2 - valid (passive scan)
  */
 
-struct rt_dot11d_info {
-};
-
-#define GET_DOT11D_INFO(__ieee_dev)			\
-	 ((struct rt_dot11d_info *)((__ieee_dev)->dot11d_info))
-
 void dot11d_channel_map(struct rtllib_device *ieee);
 
 #endif
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index ec720f7766390..51dcea57a3292 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1320,7 +1320,6 @@ struct rtllib_device {
 	u16 scan_watch_dog;
 
 	/* map of allowed channels. 0 is dummy */
-	void *dot11d_info;
 	u8 active_channel_map[MAX_CHANNEL_NUMBER+1];
 
 	int rate;       /* current rate */
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index fdb0e76d20b09..3c92eb401e8cc 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2077,9 +2077,6 @@ int rtllib_softmac_init(struct rtllib_device *ieee)
 	ieee->link_state = MAC80211_NOLINK;
 	for (i = 0; i < 5; i++)
 		ieee->seq_ctrl[i] = 0;
-	ieee->dot11d_info = kzalloc(sizeof(struct rt_dot11d_info), GFP_ATOMIC);
-	if (!ieee->dot11d_info)
-		return -ENOMEM;
 
 	ieee->link_detect_info.SlotIndex = 0;
 	ieee->link_detect_info.SlotNum = 2;
@@ -2153,9 +2150,6 @@ void rtllib_softmac_free(struct rtllib_device *ieee)
 	cancel_work_sync(&ieee->ips_leave_wq);
 	cancel_work_sync(&ieee->wx_sync_scan_wq);
 	cancel_work_sync(&ieee->ps_task);
-
-	kfree(ieee->dot11d_info);
-	ieee->dot11d_info = NULL;
 }
 
 static inline struct sk_buff *
-- 
GitLab


From 2cdfd6dc0f44617652d9f58ea58b352a0c095070 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 8 Dec 2023 19:19:57 +0100
Subject: [PATCH 1052/4076] staging: rtl8192e: Remove function
 dot11d_channel_map()

Remove function dot11d_channel_map() as it is empty.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/877c0efcf56977cbf0943b34beda4ff2ca514714.1701989555.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/dot11d.c            | 6 ------
 drivers/staging/rtl8192e/dot11d.h            | 2 --
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 -
 3 files changed, 9 deletions(-)

diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
index 8d89f962b3bf4..ec71bae05c1f0 100644
--- a/drivers/staging/rtl8192e/dot11d.c
+++ b/drivers/staging/rtl8192e/dot11d.c
@@ -6,9 +6,3 @@
  * wlanfae <wlanfae@realtek.com>
  ******************************************************************************/
 #include "dot11d.h"
-
-void dot11d_channel_map(struct rtllib_device *ieee)
-{
-
-}
-EXPORT_SYMBOL(dot11d_channel_map);
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
index 98aa28d0cf721..eeefbfa96938e 100644
--- a/drivers/staging/rtl8192e/dot11d.h
+++ b/drivers/staging/rtl8192e/dot11d.h
@@ -18,6 +18,4 @@
  *		2 - valid (passive scan)
  */
 
-void dot11d_channel_map(struct rtllib_device *ieee);
-
 #endif
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 1f45b6b00d1b2..72e89ccfb1840 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -761,7 +761,6 @@ static short _rtl92e_get_channel_map(struct net_device *dev)
 
 	struct r8192_priv *priv = rtllib_priv(dev);
 
-	dot11d_channel_map(priv->rtllib);
 	for (i = 1; i <= 11; i++)
 		(priv->rtllib->active_channel_map)[i] = 1;
 	(priv->rtllib->active_channel_map)[12] = 2;
-- 
GitLab


From 13afc9bd5349925b104cd751ea67d07d5cff9433 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Fri, 8 Dec 2023 19:20:04 +0100
Subject: [PATCH 1053/4076] staging: rtl8192e: Remove files dot11d.c and
 dot11d.h

Remove files dot11d.c and dot11d.h as they are empty.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/ed7de82ade0fde1835bbd88aafba74aeb128beed.1701989555.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/Makefile            |  1 -
 drivers/staging/rtl8192e/dot11d.c            |  8 --------
 drivers/staging/rtl8192e/dot11d.h            | 21 --------------------
 drivers/staging/rtl8192e/rtl8192e/rtl_core.h |  2 --
 drivers/staging/rtl8192e/rtllib_rx.c         |  1 -
 drivers/staging/rtl8192e/rtllib_softmac.c    |  1 -
 drivers/staging/rtl8192e/rtllib_softmac_wx.c |  1 -
 7 files changed, 35 deletions(-)
 delete mode 100644 drivers/staging/rtl8192e/dot11d.c
 delete mode 100644 drivers/staging/rtl8192e/dot11d.h

diff --git a/drivers/staging/rtl8192e/Makefile b/drivers/staging/rtl8192e/Makefile
index 6af519938868e..a1492215dab10 100644
--- a/drivers/staging/rtl8192e/Makefile
+++ b/drivers/staging/rtl8192e/Makefile
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 rtllib-objs :=			\
-	dot11d.o		\
 	rtllib_module.o		\
 	rtllib_rx.o		\
 	rtllib_tx.o		\
diff --git a/drivers/staging/rtl8192e/dot11d.c b/drivers/staging/rtl8192e/dot11d.c
deleted file mode 100644
index ec71bae05c1f0..0000000000000
--- a/drivers/staging/rtl8192e/dot11d.c
+++ /dev/null
@@ -1,8 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/******************************************************************************
- * Copyright(c) 2008 - 2010 Realtek Corporation. All rights reserved.
- *
- * Contact Information:
- * wlanfae <wlanfae@realtek.com>
- ******************************************************************************/
-#include "dot11d.h"
diff --git a/drivers/staging/rtl8192e/dot11d.h b/drivers/staging/rtl8192e/dot11d.h
deleted file mode 100644
index eeefbfa96938e..0000000000000
--- a/drivers/staging/rtl8192e/dot11d.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/******************************************************************************
- * Copyright(c) 2008 - 2010 Realtek Corporation. All rights reserved.
- *
- * Contact Information:
- * wlanfae <wlanfae@realtek.com>
- ******************************************************************************/
-#ifndef __INC_DOT11D_H
-#define __INC_DOT11D_H
-
-#include "rtllib.h"
-
-/**
- * struct rt_dot11d_info
- * @channel_map: holds channel values
- *		0 - invalid,
- *		1 - valid (active scan),
- *		2 - valid (passive scan)
- */
-
-#endif
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
index 546c8a33dae8c..1d6d31292f411 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h
@@ -34,8 +34,6 @@
 
 #include "../rtllib.h"
 
-#include "../dot11d.h"
-
 #include "r8192E_firmware.h"
 #include "r8192E_hw.h"
 
diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index d9517dbc5593b..62d02576b4418 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -34,7 +34,6 @@
 #include <linux/ctype.h>
 
 #include "rtllib.h"
-#include "dot11d.h"
 
 static void rtllib_rx_mgt(struct rtllib_device *ieee, struct sk_buff *skb,
 			  struct rtllib_rx_stats *stats);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 3c92eb401e8cc..5c89744b2bbe3 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -18,7 +18,6 @@
 #include <linux/uaccess.h>
 #include <linux/etherdevice.h>
 #include <linux/ieee80211.h>
-#include "dot11d.h"
 
 static void rtllib_sta_wakeup(struct rtllib_device *ieee, short nl);
 
diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
index b48c89d2e7bf7..5d165d0b134d1 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
@@ -14,7 +14,6 @@
 #include <linux/etherdevice.h>
 
 #include "rtllib.h"
-#include "dot11d.h"
 
 int rtllib_wx_set_freq(struct rtllib_device *ieee, struct iw_request_info *a,
 			     union iwreq_data *wrqu, char *b)
-- 
GitLab


From da811655dddb71332905a7c7f4abfa4f9ecd38c1 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 7 Dec 2023 20:55:32 -0500
Subject: [PATCH 1054/4076] staging: rtl8192e: renamed variable
 bCurShortGI40MHz

Coding style issue, checkpatch Avoid CamelCase,
rename it. bCurShortGI40MHz -> cur_short_gi_40mhz

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231208015536.21013-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 +-
 drivers/staging/rtl8192e/rtl8192e/rtl_dm.c     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HT.h          | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c      | 6 +++---
 drivers/staging/rtl8192e/rtllib_tx.c           | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index 39fa5f60db457..f01240f7e514f 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -1763,7 +1763,7 @@ void rtl92e_update_ratr_table(struct net_device *dev)
 	}
 	ratr_value &= 0x0FFFFFFF;
 	if (ieee->ht_info->cur_tx_bw40mhz &&
-	    ieee->ht_info->bCurShortGI40MHz)
+	    ieee->ht_info->cur_short_gi_40mhz)
 		ratr_value |= 0x80000000;
 	else if (!ieee->ht_info->cur_tx_bw40mhz &&
 		  ieee->ht_info->bCurShortGI20MHz)
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
index 330dafd62656a..c73d2ac910d54 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
@@ -287,7 +287,7 @@ static void _rtl92e_dm_check_rate_adaptive(struct net_device *dev)
 
 	if (priv->rtllib->link_state == MAC80211_LINKED) {
 		bshort_gi_enabled = (ht_info->cur_tx_bw40mhz &&
-				     ht_info->bCurShortGI40MHz) ||
+				     ht_info->cur_short_gi_40mhz) ||
 				    (!ht_info->cur_tx_bw40mhz &&
 				     ht_info->bCurShortGI20MHz);
 
diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 98c1e5840e31b..f89b618f71a58 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -97,7 +97,7 @@ struct rt_hi_throughput {
 	u8 reg_bw_40mhz;
 	u8 cur_bw_40mhz;
 	u8 reg_short_gi_40mhz;
-	u8 bCurShortGI40MHz;
+	u8 cur_short_gi_40mhz;
 	u8 reg_short_gi_20mhz;
 	u8 bCurShortGI20MHz;
 	u8 reg_supp_cck;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index a421c56af9e24..f9c76aaf87911 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -109,7 +109,7 @@ static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 mcs_rate)
 
 	u8	is40MHz = (ht_info->cur_bw_40mhz) ? 1 : 0;
 	u8	isShortGI = (ht_info->cur_bw_40mhz) ?
-			    ((ht_info->bCurShortGI40MHz) ? 1 : 0) :
+			    ((ht_info->cur_short_gi_40mhz) ? 1 : 0) :
 			    ((ht_info->bCurShortGI20MHz) ? 1 : 0);
 	return MCS_DATA_RATE[is40MHz][isShortGI][(mcs_rate & 0x7f)];
 }
@@ -481,7 +481,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->bCurShortGI20MHz = ((ht_info->reg_short_gi_20mhz) ?
 				    ((pPeerHTCap->ShortGI20Mhz == 1) ?
 				    true : false) : false);
-	ht_info->bCurShortGI40MHz = ((ht_info->reg_short_gi_40mhz) ?
+	ht_info->cur_short_gi_40mhz = ((ht_info->reg_short_gi_40mhz) ?
 				     ((pPeerHTCap->ShortGI40Mhz == 1) ?
 				     true : false) : false);
 
@@ -563,7 +563,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	ht_info->cur_tx_bw40mhz = false;
 
 	ht_info->bCurShortGI20MHz = false;
-	ht_info->bCurShortGI40MHz = false;
+	ht_info->cur_short_gi_40mhz = false;
 	ht_info->forced_short_gi = false;
 
 	ht_info->bCurSuppCCK = true;
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index b8f8c9039e01f..d51f4f3310d56 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -362,7 +362,7 @@ static void rtllib_query_HTCapShortGI(struct rtllib_device *ieee,
 		return;
 	}
 
-	if (ht_info->cur_bw_40mhz && ht_info->bCurShortGI40MHz)
+	if (ht_info->cur_bw_40mhz && ht_info->cur_short_gi_40mhz)
 		tcb_desc->bUseShortGI = true;
 	else if (!ht_info->cur_bw_40mhz && ht_info->bCurShortGI20MHz)
 		tcb_desc->bUseShortGI = true;
-- 
GitLab


From 5ca1e3c9aba0a343fe1eafae567f8c63ad0dd557 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 7 Dec 2023 20:55:33 -0500
Subject: [PATCH 1055/4076] staging: rtl8192e: renamed variable
 bCurShortGI20MHz

Coding style issue, checkpatch Avoid CamelCase,
rename it. bCurShortGI20MHz -> cur_short_gi_20mhz

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231208015536.21013-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 +-
 drivers/staging/rtl8192e/rtl8192e/rtl_dm.c     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HT.h          | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c      | 6 +++---
 drivers/staging/rtl8192e/rtllib_tx.c           | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index f01240f7e514f..e6d51abd0d018 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -1766,7 +1766,7 @@ void rtl92e_update_ratr_table(struct net_device *dev)
 	    ieee->ht_info->cur_short_gi_40mhz)
 		ratr_value |= 0x80000000;
 	else if (!ieee->ht_info->cur_tx_bw40mhz &&
-		  ieee->ht_info->bCurShortGI20MHz)
+		  ieee->ht_info->cur_short_gi_20mhz)
 		ratr_value |= 0x80000000;
 	rtl92e_writel(dev, RATR0 + rate_index * 4, ratr_value);
 	rtl92e_writeb(dev, UFWP, 1);
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
index c73d2ac910d54..e2828d57d1fd4 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
@@ -289,7 +289,7 @@ static void _rtl92e_dm_check_rate_adaptive(struct net_device *dev)
 		bshort_gi_enabled = (ht_info->cur_tx_bw40mhz &&
 				     ht_info->cur_short_gi_40mhz) ||
 				    (!ht_info->cur_tx_bw40mhz &&
-				     ht_info->bCurShortGI20MHz);
+				     ht_info->cur_short_gi_20mhz);
 
 		pra->upper_rssi_threshold_ratr =
 				(pra->upper_rssi_threshold_ratr & (~BIT(31))) |
diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index f89b618f71a58..77f28d87d3c0d 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -99,7 +99,7 @@ struct rt_hi_throughput {
 	u8 reg_short_gi_40mhz;
 	u8 cur_short_gi_40mhz;
 	u8 reg_short_gi_20mhz;
-	u8 bCurShortGI20MHz;
+	u8 cur_short_gi_20mhz;
 	u8 reg_supp_cck;
 	u8 bCurSuppCCK;
 	enum ht_spec_ver ePeerHTSpecVer;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index f9c76aaf87911..633f735bdab16 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -110,7 +110,7 @@ static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 mcs_rate)
 	u8	is40MHz = (ht_info->cur_bw_40mhz) ? 1 : 0;
 	u8	isShortGI = (ht_info->cur_bw_40mhz) ?
 			    ((ht_info->cur_short_gi_40mhz) ? 1 : 0) :
-			    ((ht_info->bCurShortGI20MHz) ? 1 : 0);
+			    ((ht_info->cur_short_gi_20mhz) ? 1 : 0);
 	return MCS_DATA_RATE[is40MHz][isShortGI][(mcs_rate & 0x7f)];
 }
 
@@ -478,7 +478,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->cur_tx_bw40mhz = ((pPeerHTInfo->RecommemdedTxWidth == 1) ?
 				 true : false);
 
-	ht_info->bCurShortGI20MHz = ((ht_info->reg_short_gi_20mhz) ?
+	ht_info->cur_short_gi_20mhz = ((ht_info->reg_short_gi_20mhz) ?
 				    ((pPeerHTCap->ShortGI20Mhz == 1) ?
 				    true : false) : false);
 	ht_info->cur_short_gi_40mhz = ((ht_info->reg_short_gi_40mhz) ?
@@ -562,7 +562,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	ht_info->cur_bw_40mhz = false;
 	ht_info->cur_tx_bw40mhz = false;
 
-	ht_info->bCurShortGI20MHz = false;
+	ht_info->cur_short_gi_20mhz = false;
 	ht_info->cur_short_gi_40mhz = false;
 	ht_info->forced_short_gi = false;
 
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index d51f4f3310d56..a2ae68cc13f5a 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -364,7 +364,7 @@ static void rtllib_query_HTCapShortGI(struct rtllib_device *ieee,
 
 	if (ht_info->cur_bw_40mhz && ht_info->cur_short_gi_40mhz)
 		tcb_desc->bUseShortGI = true;
-	else if (!ht_info->cur_bw_40mhz && ht_info->bCurShortGI20MHz)
+	else if (!ht_info->cur_bw_40mhz && ht_info->cur_short_gi_20mhz)
 		tcb_desc->bUseShortGI = true;
 }
 
-- 
GitLab


From fd19bb054a66e729ec584be59f749ce133a62347 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 7 Dec 2023 20:55:34 -0500
Subject: [PATCH 1056/4076] staging: rtl8192e: renamed variable CCKOFDMRate

Coding style issue, checkpatch avoid CamelCase,
rename it. CCKOFDMRate -> cck_of_dm_rate

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231208015536.21013-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 633f735bdab16..73c0204303ec6 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -116,13 +116,13 @@ static u16 ht_mcs_to_data_rate(struct rtllib_device *ieee, u8 mcs_rate)
 
 u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 data_rate)
 {
-	u16	CCKOFDMRate[12] = {0x02, 0x04, 0x0b, 0x16, 0x0c, 0x12, 0x18,
+	u16	cck_of_dm_rate[12] = {0x02, 0x04, 0x0b, 0x16, 0x0c, 0x12, 0x18,
 				   0x24, 0x30, 0x48, 0x60, 0x6c};
 	u8	is40MHz = 0;
 	u8	isShortGI = 0;
 
 	if (data_rate < 12)
-		return CCKOFDMRate[data_rate];
+		return cck_of_dm_rate[data_rate];
 	if (data_rate >= 0x10 && data_rate <= 0x1f) {
 		is40MHz = 0;
 		isShortGI = 0;
-- 
GitLab


From 2d3f27b55f31876937af83096b239e87b6b177a4 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 7 Dec 2023 20:55:35 -0500
Subject: [PATCH 1057/4076] staging: rtl8192e: renamed variable
 HTIOTActIsCCDFsync

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTIOTActIsCCDFsync -> ht_iot_act_is_ccd_fsync

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231208015536.21013-5-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 73c0204303ec6..5486b1ab4b5af 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -218,7 +218,7 @@ static u8 ht_iot_act_is_mgnt_use_cck_6m(struct rtllib_device *ieee,
 	return retValue;
 }
 
-static u8 HTIOTActIsCCDFsync(struct rtllib_device *ieee)
+static u8 ht_iot_act_is_ccd_fsync(struct rtllib_device *ieee)
 {
 	u8	retValue = 0;
 
@@ -662,7 +662,7 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 		bIOTAction = ht_iot_act_is_mgnt_use_cck_6m(ieee, pNetwork);
 		if (bIOTAction)
 			ht_info->iot_action |= HT_IOT_ACT_MGNT_USE_CCK_6M;
-		bIOTAction = HTIOTActIsCCDFsync(ieee);
+		bIOTAction = ht_iot_act_is_ccd_fsync(ieee);
 		if (bIOTAction)
 			ht_info->iot_action |= HT_IOT_ACT_CDD_FSYNC;
 	} else {
-- 
GitLab


From 345586fed2e0666c8e62ab946948ca4f5e2121c0 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 7 Dec 2023 20:58:27 -0500
Subject: [PATCH 1058/4076] staging: rtl8192e: renamed variable IOTPeer

Coding style issue, checkpatch Avoid CamelCase,
rename it. IOTPeer -> iot_peer

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231208015827.21185-1-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 18 +++++-----
 drivers/staging/rtl8192e/rtl819x_HT.h      |  2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c  | 38 +++++++++++-----------
 3 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
index e2828d57d1fd4..92143c50c149a 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c
@@ -1142,7 +1142,7 @@ static void _rtl92e_dm_check_edca_turbo(struct net_device *dev)
 				if (priv->bis_cur_rdlstate ||
 				    !priv->bcurrent_turbo_EDCA) {
 					rtl92e_writel(dev, EDCAPARA_BE,
-						      edca_setting_UL[ht_info->IOTPeer]);
+						      edca_setting_UL[ht_info->iot_peer]);
 					priv->bis_cur_rdlstate = false;
 				}
 			} else {
@@ -1150,10 +1150,10 @@ static void _rtl92e_dm_check_edca_turbo(struct net_device *dev)
 				    !priv->bcurrent_turbo_EDCA) {
 					if (priv->rtllib->mode == WIRELESS_MODE_G)
 						rtl92e_writel(dev, EDCAPARA_BE,
-							      edca_setting_DL_GMode[ht_info->IOTPeer]);
+							      edca_setting_DL_GMode[ht_info->iot_peer]);
 					else
 						rtl92e_writel(dev, EDCAPARA_BE,
-							      edca_setting_DL[ht_info->IOTPeer]);
+							      edca_setting_DL[ht_info->iot_peer]);
 					priv->bis_cur_rdlstate = true;
 				}
 			}
@@ -1164,17 +1164,17 @@ static void _rtl92e_dm_check_edca_turbo(struct net_device *dev)
 				    !priv->bcurrent_turbo_EDCA) {
 					if (priv->rtllib->mode == WIRELESS_MODE_G)
 						rtl92e_writel(dev, EDCAPARA_BE,
-							      edca_setting_DL_GMode[ht_info->IOTPeer]);
+							      edca_setting_DL_GMode[ht_info->iot_peer]);
 					else
 						rtl92e_writel(dev, EDCAPARA_BE,
-							      edca_setting_DL[ht_info->IOTPeer]);
+							      edca_setting_DL[ht_info->iot_peer]);
 					priv->bis_cur_rdlstate = true;
 				}
 			} else {
 				if (priv->bis_cur_rdlstate ||
 				    !priv->bcurrent_turbo_EDCA) {
 					rtl92e_writel(dev, EDCAPARA_BE,
-						      edca_setting_UL[ht_info->IOTPeer]);
+						      edca_setting_UL[ht_info->iot_peer]);
 					priv->bis_cur_rdlstate = false;
 				}
 			}
@@ -1217,7 +1217,7 @@ static void _rtl92e_dm_cts_to_self(struct net_device *dev)
 		ht_info->iot_action &= ~HT_IOT_ACT_FORCED_CTS2SELF;
 		return;
 	}
-	if (ht_info->IOTPeer == HT_IOT_PEER_BROADCOM) {
+	if (ht_info->iot_peer == HT_IOT_PEER_BROADCOM) {
 		curTxOkCnt = priv->stats.txbytesunicast - lastTxOkCnt;
 		curRxOkCnt = priv->stats.rxbytesunicast - lastRxOkCnt;
 		if (curRxOkCnt > 4 * curTxOkCnt)
@@ -1713,7 +1713,7 @@ static void _rtl92e_dm_check_fsync(struct net_device *dev)
 	static u8 reg_c38_State = RegC38_Default;
 
 	if (priv->rtllib->link_state == MAC80211_LINKED &&
-	    priv->rtllib->ht_info->IOTPeer == HT_IOT_PEER_BROADCOM) {
+	    priv->rtllib->ht_info->iot_peer == HT_IOT_PEER_BROADCOM) {
 		if (priv->rtllib->bfsync_enable == 0) {
 			switch (priv->rtllib->fsync_state) {
 			case Default_Fsync:
@@ -1819,7 +1819,7 @@ static void _rtl92e_dm_dynamic_tx_power(struct net_device *dev)
 		priv->dynamic_tx_low_pwr = false;
 		return;
 	}
-	if ((priv->rtllib->ht_info->IOTPeer == HT_IOT_PEER_ATHEROS) &&
+	if ((priv->rtllib->ht_info->iot_peer == HT_IOT_PEER_ATHEROS) &&
 	    (priv->rtllib->mode == WIRELESS_MODE_G)) {
 		txhipower_threshold = TX_POWER_ATHEROAP_THRESH_HIGH;
 		txlowpower_threshold = TX_POWER_ATHEROAP_THRESH_LOW;
diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 77f28d87d3c0d..c004020099e3c 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -138,7 +138,7 @@ struct rt_hi_throughput {
 	u8 rx_reorder_win_size;
 	u8 rx_reorder_pending_time;
 	u16 rx_reorder_drop_counter;
-	u8 IOTPeer;
+	u8 iot_peer;
 	u32 iot_action;
 	u8 iot_ra_func;
 } __packed;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 5486b1ab4b5af..99626be899fd8 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -170,41 +170,41 @@ static void ht_iot_peer_determine(struct rtllib_device *ieee)
 	struct rtllib_network *net = &ieee->current_network;
 
 	if (net->bssht.bd_rt2rt_aggregation) {
-		ht_info->IOTPeer = HT_IOT_PEER_REALTEK;
+		ht_info->iot_peer = HT_IOT_PEER_REALTEK;
 		if (net->bssht.rt2rt_ht_mode & RT_HT_CAP_USE_92SE)
-			ht_info->IOTPeer = HT_IOT_PEER_REALTEK_92SE;
+			ht_info->iot_peer = HT_IOT_PEER_REALTEK_92SE;
 		if (net->bssht.rt2rt_ht_mode & RT_HT_CAP_USE_SOFTAP)
-			ht_info->IOTPeer = HT_IOT_PEER_92U_SOFTAP;
+			ht_info->iot_peer = HT_IOT_PEER_92U_SOFTAP;
 	} else if (net->broadcom_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_BROADCOM;
+		ht_info->iot_peer = HT_IOT_PEER_BROADCOM;
 	} else if (!memcmp(net->bssid, UNKNOWN_BORADCOM, 3) ||
 		 !memcmp(net->bssid, LINKSYSWRT330_LINKSYSWRT300_BROADCOM, 3) ||
 		 !memcmp(net->bssid, LINKSYSWRT350_LINKSYSWRT150_BROADCOM, 3)) {
-		ht_info->IOTPeer = HT_IOT_PEER_BROADCOM;
+		ht_info->iot_peer = HT_IOT_PEER_BROADCOM;
 	} else if ((memcmp(net->bssid, BELKINF5D8233V1_RALINK, 3) == 0) ||
 		 (memcmp(net->bssid, BELKINF5D82334V3_RALINK, 3) == 0) ||
 		 (memcmp(net->bssid, PCI_RALINK, 3) == 0) ||
 		 (memcmp(net->bssid, EDIMAX_RALINK, 3) == 0) ||
 		 (memcmp(net->bssid, AIRLINK_RALINK, 3) == 0) ||
 		  net->ralink_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_RALINK;
+		ht_info->iot_peer = HT_IOT_PEER_RALINK;
 	} else if ((net->atheros_cap_exist) ||
 		(memcmp(net->bssid, DLINK_ATHEROS_1, 3) == 0) ||
 		(memcmp(net->bssid, DLINK_ATHEROS_2, 3) == 0)) {
-		ht_info->IOTPeer = HT_IOT_PEER_ATHEROS;
+		ht_info->iot_peer = HT_IOT_PEER_ATHEROS;
 	} else if ((memcmp(net->bssid, CISCO_BROADCOM, 3) == 0) ||
 		  net->cisco_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_CISCO;
+		ht_info->iot_peer = HT_IOT_PEER_CISCO;
 	} else if ((memcmp(net->bssid, LINKSYS_MARVELL_4400N, 3) == 0) ||
 		  net->marvell_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_MARVELL;
+		ht_info->iot_peer = HT_IOT_PEER_MARVELL;
 	} else if (net->airgo_cap_exist) {
-		ht_info->IOTPeer = HT_IOT_PEER_AIRGO;
+		ht_info->iot_peer = HT_IOT_PEER_AIRGO;
 	} else {
-		ht_info->IOTPeer = HT_IOT_PEER_UNKNOWN;
+		ht_info->iot_peer = HT_IOT_PEER_UNKNOWN;
 	}
 
-	netdev_dbg(ieee->dev, "IOTPEER: %x\n", ht_info->IOTPeer);
+	netdev_dbg(ieee->dev, "IOTPEER: %x\n", ht_info->iot_peer);
 }
 
 static u8 ht_iot_act_is_mgnt_use_cck_6m(struct rtllib_device *ieee,
@@ -212,7 +212,7 @@ static u8 ht_iot_act_is_mgnt_use_cck_6m(struct rtllib_device *ieee,
 {
 	u8	retValue = 0;
 
-	if (ieee->ht_info->IOTPeer == HT_IOT_PEER_BROADCOM)
+	if (ieee->ht_info->iot_peer == HT_IOT_PEER_BROADCOM)
 		retValue = 1;
 
 	return retValue;
@@ -222,7 +222,7 @@ static u8 ht_iot_act_is_ccd_fsync(struct rtllib_device *ieee)
 {
 	u8	retValue = 0;
 
-	if (ieee->ht_info->IOTPeer == HT_IOT_PEER_BROADCOM)
+	if (ieee->ht_info->iot_peer == HT_IOT_PEER_BROADCOM)
 		retValue = 1;
 	return retValue;
 }
@@ -233,7 +233,7 @@ static void HTIOTActDetermineRaFunc(struct rtllib_device *ieee, bool bPeerRx2ss)
 
 	ht_info->iot_ra_func &= HT_IOT_RAFUNC_DISABLE_ALL;
 
-	if (ht_info->IOTPeer == HT_IOT_PEER_RALINK && !bPeerRx2ss)
+	if (ht_info->iot_peer == HT_IOT_PEER_RALINK && !bPeerRx2ss)
 		ht_info->iot_ra_func |= HT_IOT_RAFUNC_PEER_1R;
 
 	if (ht_info->iot_action & HT_IOT_ACT_AMSDU_ENABLE)
@@ -243,7 +243,7 @@ static void HTIOTActDetermineRaFunc(struct rtllib_device *ieee, bool bPeerRx2ss)
 void HTResetIOTSetting(struct rt_hi_throughput *ht_info)
 {
 	ht_info->iot_action = 0;
-	ht_info->IOTPeer = HT_IOT_PEER_UNKNOWN;
+	ht_info->iot_peer = HT_IOT_PEER_UNKNOWN;
 	ht_info->iot_ra_func = 0;
 }
 
@@ -501,8 +501,8 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->current_ampdu_enable = ht_info->ampdu_enable;
 	if (ieee->rtllib_ap_sec_type &&
 	    (ieee->rtllib_ap_sec_type(ieee) & (SEC_ALG_WEP | SEC_ALG_TKIP))) {
-		if ((ht_info->IOTPeer == HT_IOT_PEER_ATHEROS) ||
-		    (ht_info->IOTPeer == HT_IOT_PEER_UNKNOWN))
+		if ((ht_info->iot_peer == HT_IOT_PEER_ATHEROS) ||
+		    (ht_info->iot_peer == HT_IOT_PEER_UNKNOWN))
 			ht_info->current_ampdu_enable = false;
 	}
 
@@ -590,7 +590,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	ht_info->current_rt2rt_long_slot_time = false;
 	ht_info->RT2RT_HT_Mode = (enum rt_ht_capability)0;
 
-	ht_info->IOTPeer = 0;
+	ht_info->iot_peer = 0;
 	ht_info->iot_action = 0;
 	ht_info->iot_ra_func = 0;
 
-- 
GitLab


From 909484169a7bd935b4e56e1d77d63e8fccf6c6f1 Mon Sep 17 00:00:00 2001
From: Marcus Folkesson <marcus.folkesson@gmail.com>
Date: Sat, 2 Dec 2023 17:59:48 +0100
Subject: [PATCH 1059/4076] Input: pxrc - simplify mutex handling with guard
 macro

Use the guard(mutex) macro for handle mutex lock/unlocks.

Signed-off-by: Marcus Folkesson <marcus.folkesson@gmail.com>
Link: https://lore.kernel.org/r/20231202-pxrc-guard-v3-1-2ca8bc8cf689@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/pxrc.c | 42 +++++++++++++++--------------------
 1 file changed, 18 insertions(+), 24 deletions(-)

diff --git a/drivers/input/joystick/pxrc.c b/drivers/input/joystick/pxrc.c
index ea2bf5951d677..52d9eab667b7a 100644
--- a/drivers/input/joystick/pxrc.c
+++ b/drivers/input/joystick/pxrc.c
@@ -5,15 +5,17 @@
  * Copyright (C) 2018 Marcus Folkesson <marcus.folkesson@gmail.com>
  */
 
-#include <linux/kernel.h>
+#include <linux/cleanup.h>
 #include <linux/errno.h>
-#include <linux/slab.h>
+#include <linux/input.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
+
 #include <linux/usb.h>
 #include <linux/usb/input.h>
-#include <linux/mutex.h>
-#include <linux/input.h>
 
 #define PXRC_VENDOR_ID		0x1781
 #define PXRC_PRODUCT_ID		0x0898
@@ -81,33 +83,28 @@ exit:
 static int pxrc_open(struct input_dev *input)
 {
 	struct pxrc *pxrc = input_get_drvdata(input);
-	int retval;
+	int error;
 
-	mutex_lock(&pxrc->pm_mutex);
-	retval = usb_submit_urb(pxrc->urb, GFP_KERNEL);
-	if (retval) {
+	guard(mutex)(&pxrc->pm_mutex);
+	error = usb_submit_urb(pxrc->urb, GFP_KERNEL);
+	if (error) {
 		dev_err(&pxrc->intf->dev,
 			"%s - usb_submit_urb failed, error: %d\n",
-			__func__, retval);
-		retval = -EIO;
-		goto out;
+			__func__, error);
+		return -EIO;
 	}
 
 	pxrc->is_open = true;
-
-out:
-	mutex_unlock(&pxrc->pm_mutex);
-	return retval;
+	return 0;
 }
 
 static void pxrc_close(struct input_dev *input)
 {
 	struct pxrc *pxrc = input_get_drvdata(input);
 
-	mutex_lock(&pxrc->pm_mutex);
+	guard(mutex)(&pxrc->pm_mutex);
 	usb_kill_urb(pxrc->urb);
 	pxrc->is_open = false;
-	mutex_unlock(&pxrc->pm_mutex);
 }
 
 static void pxrc_free_urb(void *_pxrc)
@@ -208,10 +205,9 @@ static int pxrc_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct pxrc *pxrc = usb_get_intfdata(intf);
 
-	mutex_lock(&pxrc->pm_mutex);
+	guard(mutex)(&pxrc->pm_mutex);
 	if (pxrc->is_open)
 		usb_kill_urb(pxrc->urb);
-	mutex_unlock(&pxrc->pm_mutex);
 
 	return 0;
 }
@@ -219,14 +215,12 @@ static int pxrc_suspend(struct usb_interface *intf, pm_message_t message)
 static int pxrc_resume(struct usb_interface *intf)
 {
 	struct pxrc *pxrc = usb_get_intfdata(intf);
-	int retval = 0;
 
-	mutex_lock(&pxrc->pm_mutex);
+	guard(mutex)(&pxrc->pm_mutex);
 	if (pxrc->is_open && usb_submit_urb(pxrc->urb, GFP_KERNEL) < 0)
-		retval = -EIO;
+		return -EIO;
 
-	mutex_unlock(&pxrc->pm_mutex);
-	return retval;
+	return 0;
 }
 
 static int pxrc_pre_reset(struct usb_interface *intf)
-- 
GitLab


From 5b20755b7780464fea3e54af0af744258dcc2841 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 26 Nov 2023 16:19:14 +0900
Subject: [PATCH 1060/4076] init: move THIS_MODULE from <linux/export.h> to
 <linux/init.h>

Commit f50169324df4 ("module.h: split out the EXPORT_SYMBOL into
export.h") appropriately separated EXPORT_SYMBOL into <linux/export.h>
because modules and EXPORT_SYMBOL are orthogonal; modules are symbol
consumers, while EXPORT_SYMBOL are used by symbol providers, which
may not be necessarily a module.

However, that commit also relocated THIS_MODULE. As explained in the
commit description, the intention was to define THIS_MODULE in a
lightweight header, but I do not believe <linux/export.h> was the
best location because EXPORT_SYMBOL and THIS_MODULE are unrelated.

Move it to another lightweight header, <linux/init.h>. The reason for
choosing <linux/init.h> is to make <linux/moduleparam.h> self-contained
without relying on <linux/linkage.h> incorrectly including
<linux/export.h>.

With this adjustment, the role of <linux/export.h> becomes clearer as
it only defines EXPORT_SYMBOL.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/export.h | 18 ------------------
 include/linux/init.h   |  7 +++++++
 2 files changed, 7 insertions(+), 18 deletions(-)

diff --git a/include/linux/export.h b/include/linux/export.h
index 9911508a9604f..0bbd02fd351db 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -6,15 +6,6 @@
 #include <linux/linkage.h>
 #include <linux/stringify.h>
 
-/*
- * Export symbols from the kernel to modules.  Forked from module.h
- * to reduce the amount of pointless cruft we feed to gcc when only
- * exporting a simple symbol or two.
- *
- * Try not to add #includes here.  It slows compilation and makes kernel
- * hackers place grumpy comments in header files.
- */
-
 /*
  * This comment block is used by fixdep. Please do not remove.
  *
@@ -23,15 +14,6 @@
  * side effect of the *.o build rule.
  */
 
-#ifndef __ASSEMBLY__
-#ifdef MODULE
-extern struct module __this_module;
-#define THIS_MODULE (&__this_module)
-#else
-#define THIS_MODULE ((struct module *)0)
-#endif
-#endif /* __ASSEMBLY__ */
-
 #ifdef CONFIG_64BIT
 #define __EXPORT_SYMBOL_REF(sym)			\
 	.balign 8				ASM_NL	\
diff --git a/include/linux/init.h b/include/linux/init.h
index 01b52c9c75268..3fa3f6241350b 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -179,6 +179,13 @@ extern void (*late_time_init)(void);
 
 extern bool initcall_debug;
 
+#ifdef MODULE
+extern struct module __this_module;
+#define THIS_MODULE (&__this_module)
+#else
+#define THIS_MODULE ((struct module *)0)
+#endif
+
 #endif
   
 #ifndef MODULE
-- 
GitLab


From 53243e098397185d910c10207bc3c0c26f072383 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Wed, 29 Nov 2023 08:53:56 +0900
Subject: [PATCH 1061/4076] kbuild: deb-pkg: remove the fakeroot builds support

In 2017, the dpkg suite introduced the rootless builds support with the
following commits:

  - 2436807c87b0 ("dpkg-deb: Add support for rootless builds")
  - fca1bfe84068 ("dpkg-buildpackage: Add support for rootless builds")

This feature is available in the default dpkg on Debian 10 and Ubuntu
20.04.

Remove the old method.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/Makefile.package | 4 +---
 scripts/package/builddeb | 8 +-------
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/scripts/Makefile.package b/scripts/Makefile.package
index 0c3adc48dfe89..a81dfb1f51810 100644
--- a/scripts/Makefile.package
+++ b/scripts/Makefile.package
@@ -109,8 +109,6 @@ debian-orig: linux.tar$(debian-orig-suffix) debian
 		cp $< ../$(orig-name); \
 	fi
 
-KBUILD_PKG_ROOTCMD ?= 'fakeroot -u'
-
 PHONY += deb-pkg srcdeb-pkg bindeb-pkg
 
 deb-pkg:    private build-type := source,binary
@@ -125,7 +123,7 @@ deb-pkg srcdeb-pkg bindeb-pkg:
 	$(if $(findstring source, $(build-type)), \
 		--unsigned-source --compression=$(KDEB_SOURCE_COMPRESS)) \
 	$(if $(findstring binary, $(build-type)), \
-		-R'$(MAKE) -f debian/rules' -j1 -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch), \
+		-R'$(MAKE) -f debian/rules' -j1 -a$$(cat debian/arch), \
 		--no-check-builddeps) \
 	$(DPKG_FLAGS))
 
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index d7dd0d04c70c9..2fe51e6919da3 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -36,19 +36,13 @@ create_package() {
 	sh -c "cd '$pdir'; find . -type f ! -path './DEBIAN/*' -printf '%P\0' \
 		| xargs -r0 md5sum > DEBIAN/md5sums"
 
-	# Fix ownership and permissions
-	if [ "$DEB_RULES_REQUIRES_ROOT" = "no" ]; then
-		dpkg_deb_opts="--root-owner-group"
-	else
-		chown -R root:root "$pdir"
-	fi
 	# a+rX in case we are in a restrictive umask environment like 0077
 	# ug-s in case we build in a setuid/setgid directory
 	chmod -R go-w,a+rX,ug-s "$pdir"
 
 	# Create the package
 	dpkg-gencontrol -p$pname -P"$pdir"
-	dpkg-deb $dpkg_deb_opts ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS} --build "$pdir" ..
+	dpkg-deb --root-owner-group ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS} --build "$pdir" ..
 }
 
 install_linux_image () {
-- 
GitLab


From cbe826b058bb3547f195144fc018957871568320 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 17:05:48 +0900
Subject: [PATCH 1062/4076] kbuild: determine base DTB by suffix

When using the -dtbs syntax, you need to list the base first, as
follows:

    foo-dtbs := foo_base.dtb foo_overlay1.dtbo foo_overlay2.dtbo
    dtb-y := foo.dtb

You cannot do this arrangement:

    foo-dtbs := foo_overlay1.dtbo foo_overlay2.dtbo foo_base.dtb

This restriction comes from $(firstword ...) in the current
implementation, but it is unneeded to rely on the order in the
-dtbs syntax.

Instead, you can simply determine the base by the suffix because
the base (*.dtb) and overlays (*.dtbo) use different suffixes.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
---
 scripts/Makefile.lib | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 1a965fe68e011..cd5b181060f15 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -83,8 +83,8 @@ dtb-$(CONFIG_OF_ALL_DTBS)       += $(dtb-)
 multi-dtb-y := $(call multi-search, $(dtb-y), .dtb, -dtbs)
 # Primitive DTB compiled from *.dts
 real-dtb-y := $(call real-search, $(dtb-y), .dtb, -dtbs)
-# Base DTB that overlay is applied onto (each first word of $(*-dtbs) expansion)
-base-dtb-y := $(foreach m, $(multi-dtb-y), $(firstword $(call suffix-search, $m, .dtb, -dtbs)))
+# Base DTB that overlay is applied onto
+base-dtb-y := $(filter %.dtb, $(call real-search, $(multi-dtb-y), .dtb, -dtbs))
 
 always-y			+= $(dtb-y)
 
-- 
GitLab


From cc87b7c06f2a6a1fbc7e06ccf6123aada4d0b588 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 18:49:31 +0900
Subject: [PATCH 1063/4076] modpost: move __attribute__((format(printf, 2, 3)))
 to modpost.h

This attribute must be added to the function declaration in a header
for comprehensive checking of all the callsites.

Fixes: 6d9a89ea4b06 ("kbuild: declare the modpost error functions as printf like")
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/mod/modpost.c | 3 +--
 scripts/mod/modpost.h | 3 ++-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index cb6406f485a96..ca0a90158f85c 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -60,8 +60,7 @@ static unsigned int nr_unresolved;
 
 #define MODULE_NAME_LEN (64 - sizeof(Elf_Addr))
 
-void __attribute__((format(printf, 2, 3)))
-modpost_log(enum loglevel loglevel, const char *fmt, ...)
+void modpost_log(enum loglevel loglevel, const char *fmt, ...)
 {
 	va_list arglist;
 
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 69baf014da4fd..9fe974dc1a528 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -197,7 +197,8 @@ enum loglevel {
 	LOG_FATAL
 };
 
-void modpost_log(enum loglevel loglevel, const char *fmt, ...);
+void __attribute__((format(printf, 2, 3)))
+modpost_log(enum loglevel loglevel, const char *fmt, ...);
 
 /*
  * warn - show the given message, then let modpost continue running, still
-- 
GitLab


From 16a473f60edc30ffcdf355676263730a6028ec67 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 18:49:32 +0900
Subject: [PATCH 1064/4076] modpost: inform compilers that fatal() never
 returns

The function fatal() never returns because modpost_log() calls exit(1)
when LOG_FATAL is passed.

Inform compilers of this fact so that unreachable code flow can be
identified at compile time.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/mod/modpost.c | 3 +++
 scripts/mod/modpost.h | 5 ++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index ca0a90158f85c..c13bc9095df31 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -90,6 +90,9 @@ void modpost_log(enum loglevel loglevel, const char *fmt, ...)
 		error_occurred = true;
 }
 
+void __attribute__((alias("modpost_log")))
+modpost_log_noret(enum loglevel loglevel, const char *fmt, ...);
+
 static inline bool strends(const char *str, const char *postfix)
 {
 	if (strlen(str) < strlen(postfix))
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 9fe974dc1a528..835cababf1b09 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -200,6 +200,9 @@ enum loglevel {
 void __attribute__((format(printf, 2, 3)))
 modpost_log(enum loglevel loglevel, const char *fmt, ...);
 
+void __attribute__((format(printf, 2, 3), noreturn))
+modpost_log_noret(enum loglevel loglevel, const char *fmt, ...);
+
 /*
  * warn - show the given message, then let modpost continue running, still
  *        allowing modpost to exit successfully. This should be used when
@@ -215,4 +218,4 @@ modpost_log(enum loglevel loglevel, const char *fmt, ...);
  */
 #define warn(fmt, args...)	modpost_log(LOG_WARN, fmt, ##args)
 #define error(fmt, args...)	modpost_log(LOG_ERROR, fmt, ##args)
-#define fatal(fmt, args...)	modpost_log(LOG_FATAL, fmt, ##args)
+#define fatal(fmt, args...)	modpost_log_noret(LOG_FATAL, fmt, ##args)
-- 
GitLab


From 5cac96f937021de3b0fbc60cdc6d6c4ee5b2456d Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 18:49:33 +0900
Subject: [PATCH 1065/4076] modpost: remove unneeded initializer in
 section_rel()

This initializer was added to avoid -Wmaybe-uninitialized (gcc) and
-Wsometimes-uninitialized (clang) warnings.

Now that compilers recognize fatal() never returns, it is unneeded.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/mod/modpost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index c13bc9095df31..3233946fa5f67 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1421,7 +1421,7 @@ static void section_rel(struct module *mod, struct elf_info *elf,
 
 	for (rel = start; rel < stop; rel++) {
 		Elf_Sym *tsym;
-		Elf_Addr taddr = 0, r_offset;
+		Elf_Addr taddr, r_offset;
 		unsigned int r_type, r_sym;
 		void *loc;
 
-- 
GitLab


From c9f2b8d45aa453ee58e66a9b0e7a54e170381585 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 18:49:34 +0900
Subject: [PATCH 1066/4076] modpost: remove unreachable code after fatal()

Now compilers can recognize fatal() never returns.

While GCC 4.5 dropped support for -Wunreachable-code, Clang is capable
of detecting the unreachable code.

  $ make HOSTCC=clang HOSTCFLAGS=-Wunreachable-code-return
      [snip]
    HOSTCC  scripts/mod/modpost.o
  scripts/mod/modpost.c:520:11: warning: 'return' will never be executed [-Wunreachable-code-return]
                          return 0;
                                 ^
  scripts/mod/modpost.c:477:10: warning: 'return' will never be executed [-Wunreachable-code-return]
                  return 0;
                         ^
  2 warnings generated.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/mod/modpost.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 3233946fa5f67..e2bc180cecc81 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -476,11 +476,9 @@ static int parse_elf(struct elf_info *info, const char *filename)
 		fatal("%s: not relocatable object.", filename);
 
 	/* Check if file offset is correct */
-	if (hdr->e_shoff > info->size) {
+	if (hdr->e_shoff > info->size)
 		fatal("section header offset=%lu in file '%s' is bigger than filesize=%zu\n",
 		      (unsigned long)hdr->e_shoff, filename, info->size);
-		return 0;
-	}
 
 	if (hdr->e_shnum == SHN_UNDEF) {
 		/*
@@ -518,12 +516,11 @@ static int parse_elf(struct elf_info *info, const char *filename)
 		const char *secname;
 		int nobits = sechdrs[i].sh_type == SHT_NOBITS;
 
-		if (!nobits && sechdrs[i].sh_offset > info->size) {
+		if (!nobits && sechdrs[i].sh_offset > info->size)
 			fatal("%s is truncated. sechdrs[i].sh_offset=%lu > sizeof(*hrd)=%zu\n",
 			      filename, (unsigned long)sechdrs[i].sh_offset,
 			      sizeof(*hdr));
-			return 0;
-		}
+
 		secname = secstrings + sechdrs[i].sh_name;
 		if (strcmp(secname, ".modinfo") == 0) {
 			if (nobits)
-- 
GitLab


From 53c5adff34d77166ed69a4e4bdae3694fe961476 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 19:14:16 +0900
Subject: [PATCH 1067/4076] sparc: vdso: clean up build artifacts in
 arch/sparc/vdso/

Currently, vdso-image-*.c, vdso*.so, vdso*.so.dbg are not cleaned
because 'make clean' does not include include/config/auto.conf,
resulting in $(vdso_img-y) being empty.

Add the build artifacts to 'targets' unconditionally.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
---
 arch/sparc/vdso/Makefile | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index d08c3a0443f3a..eb52d0666ffc4 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -24,11 +24,8 @@ targets += vdso.lds $(vobjs-y)
 
 # Build the vDSO image C files and link them in.
 vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
-vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c)
-vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
 obj-y += $(vdso_img_objs)
-targets += $(vdso_img_cfiles)
-targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
+targets += $(foreach x, 32 64, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg)
 
 CPPFLAGS_vdso.lds += -P -C
 
-- 
GitLab


From 918d8f94720a103a48ffb5a3ec10c0f680ba78ad Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 19:14:17 +0900
Subject: [PATCH 1068/4076] sparc: vdso: simplify obj-y addition

Add objects to obj-y in a more straightforward way.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
---
 arch/sparc/vdso/Makefile | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index eb52d0666ffc4..03a32b6156eef 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -3,9 +3,6 @@
 # Building vDSO images for sparc.
 #
 
-VDSO64-$(CONFIG_SPARC64)	:= y
-VDSOCOMPAT-$(CONFIG_COMPAT)	:= y
-
 # files to link into the vdso
 vobjs-y := vdso-note.o vclock_gettime.o
 
@@ -13,18 +10,14 @@ vobjs-y := vdso-note.o vclock_gettime.o
 obj-y				+= vma.o
 
 # vDSO images to build
-vdso_img-$(VDSO64-y)		+= 64
-vdso_img-$(VDSOCOMPAT-y)	+= 32
+obj-$(CONFIG_SPARC64)		+= vdso-image-64.o
+obj-$(CONFIG_COMPAT)		+= vdso-image-32.o
 
 vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
 targets += vdso.lds $(vobjs-y)
-
-# Build the vDSO image C files and link them in.
-vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
-obj-y += $(vdso_img_objs)
 targets += $(foreach x, 32 64, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg)
 
 CPPFLAGS_vdso.lds += -P -C
-- 
GitLab


From d821f8a26efb6789666d70ce7a8f27df6c33c12e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 19:14:18 +0900
Subject: [PATCH 1069/4076] sparc: vdso: use $(addprefix ) instead of $(foreach
 )

$(addprefix ) is slightly shorter and more intuitive.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
---
 arch/sparc/vdso/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index 03a32b6156eef..7f5eedf1f5e0a 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -13,7 +13,7 @@ obj-y				+= vma.o
 obj-$(CONFIG_SPARC64)		+= vdso-image-64.o
 obj-$(CONFIG_COMPAT)		+= vdso-image-32.o
 
-vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+vobjs := $(addprefix $(obj)/, $(vobjs-y))
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
-- 
GitLab


From 6c07fd84977b605b6a4ceb03b38e6325974f06d6 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 19:25:23 +0900
Subject: [PATCH 1070/4076] kconfig: factor out common code shared by mconf and
 nconf

Separate out the duplicated code to mnconf-common.c.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/Makefile        |  4 +--
 scripts/kconfig/mconf.c         | 54 +--------------------------------
 scripts/kconfig/mnconf-common.c | 53 ++++++++++++++++++++++++++++++++
 scripts/kconfig/mnconf-common.h | 18 +++++++++++
 scripts/kconfig/nconf.c         | 53 +-------------------------------
 5 files changed, 75 insertions(+), 107 deletions(-)
 create mode 100644 scripts/kconfig/mnconf-common.c
 create mode 100644 scripts/kconfig/mnconf-common.h

diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 322c061b464d2..7c025f82718e2 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -174,7 +174,7 @@ conf-objs	:= conf.o $(common-objs)
 
 # nconf: Used for the nconfig target based on ncurses
 hostprogs	+= nconf
-nconf-objs	:= nconf.o nconf.gui.o $(common-objs)
+nconf-objs	:= nconf.o nconf.gui.o mnconf-common.o $(common-objs)
 
 HOSTLDLIBS_nconf       = $(call read-file, $(obj)/nconf-libs)
 HOSTCFLAGS_nconf.o     = $(call read-file, $(obj)/nconf-cflags)
@@ -187,7 +187,7 @@ $(obj)/nconf.o $(obj)/nconf.gui.o: | $(obj)/nconf-cflags
 hostprogs	+= mconf
 lxdialog	:= $(addprefix lxdialog/, \
 		     checklist.o inputbox.o menubox.o textbox.o util.o yesno.o)
-mconf-objs	:= mconf.o $(lxdialog) $(common-objs)
+mconf-objs	:= mconf.o $(lxdialog) mnconf-common.o $(common-objs)
 
 HOSTLDLIBS_mconf = $(call read-file, $(obj)/mconf-libs)
 $(foreach f, mconf.o $(lxdialog), \
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index 3795c36a9181a..5df32148a8695 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -21,6 +21,7 @@
 
 #include "lkc.h"
 #include "lxdialog/dialog.h"
+#include "mnconf-common.h"
 
 static const char mconf_readme[] =
 "Overview\n"
@@ -286,7 +287,6 @@ static int single_menu_mode;
 static int show_all_options;
 static int save_and_exit;
 static int silent;
-static int jump_key_char;
 
 static void conf(struct menu *menu, struct menu *active_menu);
 
@@ -378,58 +378,6 @@ static void show_help(struct menu *menu)
 	str_free(&help);
 }
 
-struct search_data {
-	struct list_head *head;
-	struct menu *target;
-};
-
-static int next_jump_key(int key)
-{
-	if (key < '1' || key > '9')
-		return '1';
-
-	key++;
-
-	if (key > '9')
-		key = '1';
-
-	return key;
-}
-
-static int handle_search_keys(int key, size_t start, size_t end, void *_data)
-{
-	struct search_data *data = _data;
-	struct jump_key *pos;
-	int index = 0;
-
-	if (key < '1' || key > '9')
-		return 0;
-
-	list_for_each_entry(pos, data->head, entries) {
-		index = next_jump_key(index);
-
-		if (pos->offset < start)
-			continue;
-
-		if (pos->offset >= end)
-			break;
-
-		if (key == index) {
-			data->target = pos->target;
-			return 1;
-		}
-	}
-
-	return 0;
-}
-
-int get_jump_key_char(void)
-{
-	jump_key_char = next_jump_key(jump_key_char);
-
-	return jump_key_char;
-}
-
 static void search_conf(void)
 {
 	struct symbol **sym_arr;
diff --git a/scripts/kconfig/mnconf-common.c b/scripts/kconfig/mnconf-common.c
new file mode 100644
index 0000000000000..18cb9a6c5aaad
--- /dev/null
+++ b/scripts/kconfig/mnconf-common.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "expr.h"
+#include "list.h"
+#include "mnconf-common.h"
+
+int jump_key_char;
+
+int next_jump_key(int key)
+{
+	if (key < '1' || key > '9')
+		return '1';
+
+	key++;
+
+	if (key > '9')
+		key = '1';
+
+	return key;
+}
+
+int handle_search_keys(int key, size_t start, size_t end, void *_data)
+{
+	struct search_data *data = _data;
+	struct jump_key *pos;
+	int index = 0;
+
+	if (key < '1' || key > '9')
+		return 0;
+
+	list_for_each_entry(pos, data->head, entries) {
+		index = next_jump_key(index);
+
+		if (pos->offset < start)
+			continue;
+
+		if (pos->offset >= end)
+			break;
+
+		if (key == index) {
+			data->target = pos->target;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+int get_jump_key_char(void)
+{
+	jump_key_char = next_jump_key(jump_key_char);
+
+	return jump_key_char;
+}
diff --git a/scripts/kconfig/mnconf-common.h b/scripts/kconfig/mnconf-common.h
new file mode 100644
index 0000000000000..ab6292cc4bf25
--- /dev/null
+++ b/scripts/kconfig/mnconf-common.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef MNCONF_COMMON_H
+#define MNCONF_COMMON_H
+
+#include <stddef.h>
+
+struct search_data {
+	struct list_head *head;
+	struct menu *target;
+};
+
+extern int jump_key_char;
+
+int next_jump_key(int key);
+int handle_search_keys(int key, size_t start, size_t end, void *_data);
+int get_jump_key_char(void);
+
+#endif /* MNCONF_COMMON_H */
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index 8cd72fe259740..1148163cfa7e7 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -12,6 +12,7 @@
 #include <stdlib.h>
 
 #include "lkc.h"
+#include "mnconf-common.h"
 #include "nconf.h"
 #include <ctype.h>
 
@@ -279,7 +280,6 @@ static const char *current_instructions = menu_instructions;
 
 static char *dialog_input_result;
 static int dialog_input_result_len;
-static int jump_key_char;
 
 static void selected_conf(struct menu *menu, struct menu *active_menu);
 static void conf(struct menu *menu);
@@ -691,57 +691,6 @@ static int do_exit(void)
 	return 0;
 }
 
-struct search_data {
-	struct list_head *head;
-	struct menu *target;
-};
-
-static int next_jump_key(int key)
-{
-	if (key < '1' || key > '9')
-		return '1';
-
-	key++;
-
-	if (key > '9')
-		key = '1';
-
-	return key;
-}
-
-static int handle_search_keys(int key, size_t start, size_t end, void *_data)
-{
-	struct search_data *data = _data;
-	struct jump_key *pos;
-	int index = 0;
-
-	if (key < '1' || key > '9')
-		return 0;
-
-	list_for_each_entry(pos, data->head, entries) {
-		index = next_jump_key(index);
-
-		if (pos->offset < start)
-			continue;
-
-		if (pos->offset >= end)
-			break;
-
-		if (key == index) {
-			data->target = pos->target;
-			return 1;
-		}
-	}
-
-	return 0;
-}
-
-int get_jump_key_char(void)
-{
-	jump_key_char = next_jump_key(jump_key_char);
-
-	return jump_key_char;
-}
 
 static void search_conf(void)
 {
-- 
GitLab


From 17819da62a5c7058ea0d44bd9ff711aab7a44ae3 Mon Sep 17 00:00:00 2001
From: Marcus Folkesson <marcus.folkesson@gmail.com>
Date: Wed, 6 Dec 2023 19:39:04 +0100
Subject: [PATCH 1071/4076] iio: adc: mcp3911: simplify code with guard macro

Use the guard(mutex) macro for handle mutex lock/unlocks.

Signed-off-by: Marcus Folkesson <marcus.folkesson@gmail.com>
Link: https://lore.kernel.org/r/20231206-mcp3911-guard-v4-1-30c3c5d4340f@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/mcp3911.c | 64 ++++++++++++++-------------------------
 1 file changed, 23 insertions(+), 41 deletions(-)

diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c
index d864558bc087f..7a32e7a1be9d0 100644
--- a/drivers/iio/adc/mcp3911.c
+++ b/drivers/iio/adc/mcp3911.c
@@ -7,6 +7,7 @@
  */
 #include <linux/bitfield.h>
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/err.h>
@@ -316,47 +317,37 @@ static int mcp3911_read_raw(struct iio_dev *indio_dev,
 			    int *val2, long mask)
 {
 	struct mcp3911 *adc = iio_priv(indio_dev);
-	int ret = -EINVAL;
+	int ret;
 
-	mutex_lock(&adc->lock);
+	guard(mutex)(&adc->lock);
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
 		ret = mcp3911_read(adc,
 				   MCP3911_CHANNEL(channel->channel), val, 3);
 		if (ret)
-			goto out;
+			return ret;
 
 		*val = sign_extend32(*val, 23);
-
-		ret = IIO_VAL_INT;
-		break;
-
+		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_OFFSET:
-
 		ret = adc->chip->get_offset(adc, channel->channel, val);
 		if (ret)
-			goto out;
+			return ret;
 
-		ret = IIO_VAL_INT;
-		break;
+		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
 		ret = adc->chip->get_osr(adc, val);
 		if (ret)
-			goto out;
-
-		ret = IIO_VAL_INT;
-		break;
+			return ret;
 
+		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SCALE:
 		*val = mcp3911_scale_table[ilog2(adc->gain[channel->channel])][0];
 		*val2 = mcp3911_scale_table[ilog2(adc->gain[channel->channel])][1];
-		ret = IIO_VAL_INT_PLUS_NANO;
-		break;
+		return IIO_VAL_INT_PLUS_NANO;
+	default:
+		return -EINVAL;
 	}
-
-out:
-	mutex_unlock(&adc->lock);
-	return ret;
 }
 
 static int mcp3911_write_raw(struct iio_dev *indio_dev,
@@ -364,9 +355,8 @@ static int mcp3911_write_raw(struct iio_dev *indio_dev,
 			     int val2, long mask)
 {
 	struct mcp3911 *adc = iio_priv(indio_dev);
-	int ret = -EINVAL;
 
-	mutex_lock(&adc->lock);
+	guard(mutex)(&adc->lock);
 	switch (mask) {
 	case IIO_CHAN_INFO_SCALE:
 		for (int i = 0; i < MCP3911_NUM_SCALES; i++) {
@@ -374,32 +364,25 @@ static int mcp3911_write_raw(struct iio_dev *indio_dev,
 			    val2 == mcp3911_scale_table[i][1]) {
 
 				adc->gain[channel->channel] = BIT(i);
-				ret = adc->chip->set_scale(adc, channel->channel, i);
+				return adc->chip->set_scale(adc, channel->channel, i);
 			}
 		}
-		break;
+		return -EINVAL;
 	case IIO_CHAN_INFO_OFFSET:
-		if (val2 != 0) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		ret = adc->chip->set_offset(adc, channel->channel, val);
-		break;
+		if (val2 != 0)
+			return -EINVAL;
 
+		return adc->chip->set_offset(adc, channel->channel, val);
 	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
 		for (int i = 0; i < ARRAY_SIZE(mcp3911_osr_table); i++) {
 			if (val == mcp3911_osr_table[i]) {
-				ret = adc->chip->set_osr(adc, i);
-				break;
+				return adc->chip->set_osr(adc, i);
 			}
 		}
-		break;
+		return -EINVAL;
+	default:
+		return -EINVAL;
 	}
-
-out:
-	mutex_unlock(&adc->lock);
-	return ret;
 }
 
 static int mcp3911_calc_scale_table(struct mcp3911 *adc)
@@ -532,7 +515,7 @@ static irqreturn_t mcp3911_trigger_handler(int irq, void *p)
 	int i = 0;
 	int ret;
 
-	mutex_lock(&adc->lock);
+	guard(mutex)(&adc->lock);
 	adc->tx_buf = MCP3911_REG_READ(MCP3911_CHANNEL(0), adc->dev_addr);
 	ret = spi_sync_transfer(adc->spi, xfer, ARRAY_SIZE(xfer));
 	if (ret < 0) {
@@ -549,7 +532,6 @@ static irqreturn_t mcp3911_trigger_handler(int irq, void *p)
 	iio_push_to_buffers_with_timestamp(indio_dev, &adc->scan,
 					   iio_get_time_ns(indio_dev));
 out:
-	mutex_unlock(&adc->lock);
 	iio_trigger_notify_done(indio_dev->trig);
 
 	return IRQ_HANDLED;
-- 
GitLab


From 76f028539cf360f750efd8cde560edda298e4c6b Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:24 +0100
Subject: [PATCH 1072/4076] iio: adc: ad9467: fix reset gpio handling

The reset gpio was being handled with inverted polarity. This means that
as far as gpiolib is concerned we were actually leaving the pin asserted
(in theory, this would mean reset). However, inverting the polarity in
devicetree made things work. Fix it by doing it the proper way and how
gpiolib expects it to be done.

While at it, moved the handling to it's own function and dropped
'reset_gpio' from the 'struct ad9467_state' as we only need it during
probe. On top of that, refactored things so that we now request the gpio
asserted (i.e in reset) and then de-assert it. Also note that we now use
gpiod_set_value_cansleep() instead of gpiod_direction_output() as we
already request the pin as output.

Fixes: ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
Reviewed-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-1-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad9467.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index 39eccc28debe4..4fb9e48dc782c 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -121,7 +121,6 @@ struct ad9467_state {
 	unsigned int			output_mode;
 
 	struct gpio_desc		*pwrdown_gpio;
-	struct gpio_desc		*reset_gpio;
 };
 
 static int ad9467_spi_read(struct spi_device *spi, unsigned int reg)
@@ -378,6 +377,21 @@ static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv)
 	return ad9467_outputmode_set(st->spi, st->output_mode);
 }
 
+static int ad9467_reset(struct device *dev)
+{
+	struct gpio_desc *gpio;
+
+	gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR_OR_NULL(gpio))
+		return PTR_ERR_OR_ZERO(gpio);
+
+	fsleep(1);
+	gpiod_set_value_cansleep(gpio, 0);
+	fsleep(10 * USEC_PER_MSEC);
+
+	return 0;
+}
+
 static int ad9467_probe(struct spi_device *spi)
 {
 	const struct ad9467_chip_info *info;
@@ -408,18 +422,9 @@ static int ad9467_probe(struct spi_device *spi)
 	if (IS_ERR(st->pwrdown_gpio))
 		return PTR_ERR(st->pwrdown_gpio);
 
-	st->reset_gpio = devm_gpiod_get_optional(&spi->dev, "reset",
-						 GPIOD_OUT_LOW);
-	if (IS_ERR(st->reset_gpio))
-		return PTR_ERR(st->reset_gpio);
-
-	if (st->reset_gpio) {
-		udelay(1);
-		ret = gpiod_direction_output(st->reset_gpio, 1);
-		if (ret)
-			return ret;
-		mdelay(10);
-	}
+	ret = ad9467_reset(&spi->dev);
+	if (ret)
+		return ret;
 
 	conv->chip_info = &info->axi_adc_info;
 
-- 
GitLab


From e072e149cfb827e0ab4cafb0547e9658e35393cd Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:25 +0100
Subject: [PATCH 1073/4076] iio: adc: ad9467: don't ignore error codes

Make sure functions that return errors are not ignored.

Fixes: ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
Reviewed-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-2-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad9467.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index 4fb9e48dc782c..d3c98c4eccd3a 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -162,9 +162,10 @@ static int ad9467_reg_access(struct adi_axi_adc_conv *conv, unsigned int reg,
 
 	if (readval == NULL) {
 		ret = ad9467_spi_write(spi, reg, writeval);
-		ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER,
-				 AN877_ADC_TRANSFER_SYNC);
-		return ret;
+		if (ret)
+			return ret;
+		return ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER,
+					AN877_ADC_TRANSFER_SYNC);
 	}
 
 	ret = ad9467_spi_read(spi, reg);
@@ -272,10 +273,13 @@ static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2)
 	const struct ad9467_chip_info *info1 = to_ad9467_chip_info(info);
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
 	unsigned int i, vref_val;
+	int ret;
 
-	vref_val = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF);
+	ret = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF);
+	if (ret < 0)
+		return ret;
 
-	vref_val &= info1->vref_mask;
+	vref_val = ret & info1->vref_mask;
 
 	for (i = 0; i < info->num_scales; i++) {
 		if (vref_val == info->scale_table[i][1])
@@ -296,6 +300,7 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2)
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
 	unsigned int scale_val[2];
 	unsigned int i;
+	int ret;
 
 	if (val != 0)
 		return -EINVAL;
@@ -305,11 +310,13 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2)
 		if (scale_val[0] != val || scale_val[1] != val2)
 			continue;
 
-		ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
-				 info->scale_table[i][1]);
-		ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
-				 AN877_ADC_TRANSFER_SYNC);
-		return 0;
+		ret = ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
+				       info->scale_table[i][1]);
+		if (ret < 0)
+			return ret;
+
+		return ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
+					AN877_ADC_TRANSFER_SYNC);
 	}
 
 	return -EINVAL;
-- 
GitLab


From 737720197be445bb9eec2986101e4a386e019337 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:26 +0100
Subject: [PATCH 1074/4076] iio: adc: ad9467: add mutex to struct ad9467_state

When calling ad9467_set_scale(), multiple calls to ad9467_spi_write()
are done which means we need to properly protect the whole operation so
we are sure we will be in a sane state if two concurrent calls occur.

Fixes: ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-3-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad9467.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index d3c98c4eccd3a..104c6d394a3e6 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -4,8 +4,9 @@
  *
  * Copyright 2012-2020 Analog Devices Inc.
  */
-
+#include <linux/cleanup.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -121,6 +122,8 @@ struct ad9467_state {
 	unsigned int			output_mode;
 
 	struct gpio_desc		*pwrdown_gpio;
+	/* ensure consistent state obtained on multiple related accesses */
+	struct mutex			lock;
 };
 
 static int ad9467_spi_read(struct spi_device *spi, unsigned int reg)
@@ -161,6 +164,7 @@ static int ad9467_reg_access(struct adi_axi_adc_conv *conv, unsigned int reg,
 	int ret;
 
 	if (readval == NULL) {
+		guard(mutex)(&st->lock);
 		ret = ad9467_spi_write(spi, reg, writeval);
 		if (ret)
 			return ret;
@@ -310,6 +314,7 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2)
 		if (scale_val[0] != val || scale_val[1] != val2)
 			continue;
 
+		guard(mutex)(&st->lock);
 		ret = ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
 				       info->scale_table[i][1]);
 		if (ret < 0)
-- 
GitLab


From b73f08bb7fe5a0901646ca5ceaa1e7a2d5ee6293 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:27 +0100
Subject: [PATCH 1075/4076] iio: adc: ad9467: fix scale setting

When reading in_voltage_scale we can get something like:

root@analog:/sys/bus/iio/devices/iio:device2# cat in_voltage_scale
0.038146

However, when reading the available options:

root@analog:/sys/bus/iio/devices/iio:device2# cat
in_voltage_scale_available
2000.000000 2100.000006 2200.000007 2300.000008 2400.000009 2500.000010

which does not make sense. Moreover, when trying to set a new scale we
get an error because there's no call to __ad9467_get_scale() to give us
values as given when reading in_voltage_scale. Fix it by computing the
available scales during probe and properly pass the list when
.read_available() is called.

While at it, change to use .read_available() from iio_info. Also note
that to properly fix this, adi-axi-adc.c has to be changed accordingly.

Fixes: ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-4-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad9467.c            | 47 ++++++++++++++++++
 drivers/iio/adc/adi-axi-adc.c       | 74 ++++++-----------------------
 include/linux/iio/adc/adi-axi-adc.h |  4 ++
 3 files changed, 66 insertions(+), 59 deletions(-)

diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index 104c6d394a3e6..f668313730cb6 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -120,6 +120,7 @@ struct ad9467_state {
 	struct spi_device		*spi;
 	struct clk			*clk;
 	unsigned int			output_mode;
+	unsigned int                    (*scales)[2];
 
 	struct gpio_desc		*pwrdown_gpio;
 	/* ensure consistent state obtained on multiple related accesses */
@@ -216,6 +217,7 @@ static void __ad9467_get_scale(struct adi_axi_adc_conv *conv, int index,
 	.channel = _chan,						\
 	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) |		\
 		BIT(IIO_CHAN_INFO_SAMP_FREQ),				\
+	.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE), \
 	.scan_index = _si,						\
 	.scan_type = {							\
 		.sign = _sign,						\
@@ -370,6 +372,26 @@ static int ad9467_write_raw(struct adi_axi_adc_conv *conv,
 	}
 }
 
+static int ad9467_read_avail(struct adi_axi_adc_conv *conv,
+			     struct iio_chan_spec const *chan,
+			     const int **vals, int *type, int *length,
+			     long mask)
+{
+	const struct adi_axi_adc_chip_info *info = conv->chip_info;
+	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		*vals = (const int *)st->scales;
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		/* Values are stored in a 2D matrix */
+		*length = info->num_scales * 2;
+		return IIO_AVAIL_LIST;
+	default:
+		return -EINVAL;
+	}
+}
+
 static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
 {
 	int ret;
@@ -382,6 +404,26 @@ static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
 				AN877_ADC_TRANSFER_SYNC);
 }
 
+static int ad9467_scale_fill(struct adi_axi_adc_conv *conv)
+{
+	const struct adi_axi_adc_chip_info *info = conv->chip_info;
+	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
+	unsigned int i, val1, val2;
+
+	st->scales = devm_kmalloc_array(&st->spi->dev, info->num_scales,
+					sizeof(*st->scales), GFP_KERNEL);
+	if (!st->scales)
+		return -ENOMEM;
+
+	for (i = 0; i < info->num_scales; i++) {
+		__ad9467_get_scale(conv, i, &val1, &val2);
+		st->scales[i][0] = val1;
+		st->scales[i][1] = val2;
+	}
+
+	return 0;
+}
+
 static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv)
 {
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
@@ -440,6 +482,10 @@ static int ad9467_probe(struct spi_device *spi)
 
 	conv->chip_info = &info->axi_adc_info;
 
+	ret = ad9467_scale_fill(conv);
+	if (ret)
+		return ret;
+
 	id = ad9467_spi_read(spi, AN877_ADC_REG_CHIP_ID);
 	if (id != conv->chip_info->id) {
 		dev_err(&spi->dev, "Mismatch CHIP_ID, got 0x%X, expected 0x%X\n",
@@ -450,6 +496,7 @@ static int ad9467_probe(struct spi_device *spi)
 	conv->reg_access = ad9467_reg_access;
 	conv->write_raw = ad9467_write_raw;
 	conv->read_raw = ad9467_read_raw;
+	conv->read_avail = ad9467_read_avail;
 	conv->preenable_setup = ad9467_preenable_setup;
 
 	st->output_mode = info->default_output_mode |
diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c
index aff0532a974aa..ae83ada7f9f2d 100644
--- a/drivers/iio/adc/adi-axi-adc.c
+++ b/drivers/iio/adc/adi-axi-adc.c
@@ -144,6 +144,20 @@ static int adi_axi_adc_write_raw(struct iio_dev *indio_dev,
 	return conv->write_raw(conv, chan, val, val2, mask);
 }
 
+static int adi_axi_adc_read_avail(struct iio_dev *indio_dev,
+				  struct iio_chan_spec const *chan,
+				  const int **vals, int *type, int *length,
+				  long mask)
+{
+	struct adi_axi_adc_state *st = iio_priv(indio_dev);
+	struct adi_axi_adc_conv *conv = &st->client->conv;
+
+	if (!conv->read_avail)
+		return -EOPNOTSUPP;
+
+	return conv->read_avail(conv, chan, vals, type, length, mask);
+}
+
 static int adi_axi_adc_update_scan_mode(struct iio_dev *indio_dev,
 					const unsigned long *scan_mask)
 {
@@ -228,69 +242,11 @@ struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev,
 }
 EXPORT_SYMBOL_NS_GPL(devm_adi_axi_adc_conv_register, IIO_ADI_AXI);
 
-static ssize_t in_voltage_scale_available_show(struct device *dev,
-					       struct device_attribute *attr,
-					       char *buf)
-{
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct adi_axi_adc_state *st = iio_priv(indio_dev);
-	struct adi_axi_adc_conv *conv = &st->client->conv;
-	size_t len = 0;
-	int i;
-
-	for (i = 0; i < conv->chip_info->num_scales; i++) {
-		const unsigned int *s = conv->chip_info->scale_table[i];
-
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				 "%u.%06u ", s[0], s[1]);
-	}
-	buf[len - 1] = '\n';
-
-	return len;
-}
-
-static IIO_DEVICE_ATTR_RO(in_voltage_scale_available, 0);
-
-enum {
-	ADI_AXI_ATTR_SCALE_AVAIL,
-};
-
-#define ADI_AXI_ATTR(_en_, _file_)			\
-	[ADI_AXI_ATTR_##_en_] = &iio_dev_attr_##_file_.dev_attr.attr
-
-static struct attribute *adi_axi_adc_attributes[] = {
-	ADI_AXI_ATTR(SCALE_AVAIL, in_voltage_scale_available),
-	NULL
-};
-
-static umode_t axi_adc_attr_is_visible(struct kobject *kobj,
-				       struct attribute *attr, int n)
-{
-	struct device *dev = kobj_to_dev(kobj);
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct adi_axi_adc_state *st = iio_priv(indio_dev);
-	struct adi_axi_adc_conv *conv = &st->client->conv;
-
-	switch (n) {
-	case ADI_AXI_ATTR_SCALE_AVAIL:
-		if (!conv->chip_info->num_scales)
-			return 0;
-		return attr->mode;
-	default:
-		return attr->mode;
-	}
-}
-
-static const struct attribute_group adi_axi_adc_attribute_group = {
-	.attrs = adi_axi_adc_attributes,
-	.is_visible = axi_adc_attr_is_visible,
-};
-
 static const struct iio_info adi_axi_adc_info = {
 	.read_raw = &adi_axi_adc_read_raw,
 	.write_raw = &adi_axi_adc_write_raw,
-	.attrs = &adi_axi_adc_attribute_group,
 	.update_scan_mode = &adi_axi_adc_update_scan_mode,
+	.read_avail = &adi_axi_adc_read_avail,
 };
 
 static const struct adi_axi_adc_core_info adi_axi_adc_10_0_a_info = {
diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h
index 52620e5b80522..b7904992d5619 100644
--- a/include/linux/iio/adc/adi-axi-adc.h
+++ b/include/linux/iio/adc/adi-axi-adc.h
@@ -41,6 +41,7 @@ struct adi_axi_adc_chip_info {
  * @reg_access		IIO debugfs_reg_access hook for the client ADC
  * @read_raw		IIO read_raw hook for the client ADC
  * @write_raw		IIO write_raw hook for the client ADC
+ * @read_avail		IIO read_avail hook for the client ADC
  */
 struct adi_axi_adc_conv {
 	const struct adi_axi_adc_chip_info		*chip_info;
@@ -54,6 +55,9 @@ struct adi_axi_adc_conv {
 	int (*write_raw)(struct adi_axi_adc_conv *conv,
 			 struct iio_chan_spec const *chan,
 			 int val, int val2, long mask);
+	int (*read_avail)(struct adi_axi_adc_conv *conv,
+			  struct iio_chan_spec const *chan,
+			  const int **val, int *type, int *length, long mask);
 };
 
 struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev,
-- 
GitLab


From b67cc85d45d5d2894d0e2812bba27d7b23befbe6 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:28 +0100
Subject: [PATCH 1076/4076] iio: adc: ad9467: use spi_get_device_match_data()

Make use of spi_get_device_match_data() to simplify things.

Reviewed-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-5-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad9467.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index f668313730cb6..b16d28c1adcb0 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -454,9 +454,7 @@ static int ad9467_probe(struct spi_device *spi)
 	unsigned int id;
 	int ret;
 
-	info = of_device_get_match_data(&spi->dev);
-	if (!info)
-		info = (void *)spi_get_device_id(spi)->driver_data;
+	info = spi_get_device_match_data(spi);
 	if (!info)
 		return -ENODEV;
 
-- 
GitLab


From 6dd3fa9fcc66cb71834dc2e0a222324af0d8b95d Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:29 +0100
Subject: [PATCH 1077/4076] iio: adc: ad9467: use chip_info variables instead
 of array

Instead of having an array and keeping IDs for each entry of the array,
just have a chip_info struct per device.

Reviewed-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-6-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad9467.c | 89 +++++++++++++++++++---------------------
 1 file changed, 43 insertions(+), 46 deletions(-)

diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index b16d28c1adcb0..c5ed62cc86465 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -101,12 +101,6 @@
 #define AD9467_DEF_OUTPUT_MODE		0x08
 #define AD9467_REG_VREF_MASK		0x0F
 
-enum {
-	ID_AD9265,
-	ID_AD9434,
-	ID_AD9467,
-};
-
 struct ad9467_chip_info {
 	struct adi_axi_adc_chip_info	axi_adc_info;
 	unsigned int			default_output_mode;
@@ -234,43 +228,46 @@ static const struct iio_chan_spec ad9467_channels[] = {
 	AD9467_CHAN(0, 0, 16, 'S'),
 };
 
-static const struct ad9467_chip_info ad9467_chip_tbl[] = {
-	[ID_AD9265] = {
-		.axi_adc_info = {
-			.id = CHIPID_AD9265,
-			.max_rate = 125000000UL,
-			.scale_table = ad9265_scale_table,
-			.num_scales = ARRAY_SIZE(ad9265_scale_table),
-			.channels = ad9467_channels,
-			.num_channels = ARRAY_SIZE(ad9467_channels),
-		},
-		.default_output_mode = AD9265_DEF_OUTPUT_MODE,
-		.vref_mask = AD9265_REG_VREF_MASK,
+static const struct ad9467_chip_info ad9467_chip_tbl = {
+	.axi_adc_info = {
+		.name = "ad9467",
+		.id = CHIPID_AD9467,
+		.max_rate = 250000000UL,
+		.scale_table = ad9467_scale_table,
+		.num_scales = ARRAY_SIZE(ad9467_scale_table),
+		.channels = ad9467_channels,
+		.num_channels = ARRAY_SIZE(ad9467_channels),
 	},
-	[ID_AD9434] = {
-		.axi_adc_info = {
-			.id = CHIPID_AD9434,
-			.max_rate = 500000000UL,
-			.scale_table = ad9434_scale_table,
-			.num_scales = ARRAY_SIZE(ad9434_scale_table),
-			.channels = ad9434_channels,
-			.num_channels = ARRAY_SIZE(ad9434_channels),
-		},
-		.default_output_mode = AD9434_DEF_OUTPUT_MODE,
-		.vref_mask = AD9434_REG_VREF_MASK,
+	.default_output_mode = AD9467_DEF_OUTPUT_MODE,
+	.vref_mask = AD9467_REG_VREF_MASK,
+};
+
+static const struct ad9467_chip_info ad9434_chip_tbl = {
+	.axi_adc_info = {
+		.name = "ad9434",
+		.id = CHIPID_AD9434,
+		.max_rate = 500000000UL,
+		.scale_table = ad9434_scale_table,
+		.num_scales = ARRAY_SIZE(ad9434_scale_table),
+		.channels = ad9434_channels,
+		.num_channels = ARRAY_SIZE(ad9434_channels),
 	},
-	[ID_AD9467] = {
-		.axi_adc_info = {
-			.id = CHIPID_AD9467,
-			.max_rate = 250000000UL,
-			.scale_table = ad9467_scale_table,
-			.num_scales = ARRAY_SIZE(ad9467_scale_table),
-			.channels = ad9467_channels,
-			.num_channels = ARRAY_SIZE(ad9467_channels),
-		},
-		.default_output_mode = AD9467_DEF_OUTPUT_MODE,
-		.vref_mask = AD9467_REG_VREF_MASK,
+	.default_output_mode = AD9434_DEF_OUTPUT_MODE,
+	.vref_mask = AD9434_REG_VREF_MASK,
+};
+
+static const struct ad9467_chip_info ad9265_chip_tbl = {
+	.axi_adc_info = {
+		.name = "ad9265",
+		.id = CHIPID_AD9265,
+		.max_rate = 125000000UL,
+		.scale_table = ad9265_scale_table,
+		.num_scales = ARRAY_SIZE(ad9265_scale_table),
+		.channels = ad9467_channels,
+		.num_channels = ARRAY_SIZE(ad9467_channels),
 	},
+	.default_output_mode = AD9265_DEF_OUTPUT_MODE,
+	.vref_mask = AD9265_REG_VREF_MASK,
 };
 
 static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2)
@@ -504,17 +501,17 @@ static int ad9467_probe(struct spi_device *spi)
 }
 
 static const struct of_device_id ad9467_of_match[] = {
-	{ .compatible = "adi,ad9265", .data = &ad9467_chip_tbl[ID_AD9265], },
-	{ .compatible = "adi,ad9434", .data = &ad9467_chip_tbl[ID_AD9434], },
-	{ .compatible = "adi,ad9467", .data = &ad9467_chip_tbl[ID_AD9467], },
+	{ .compatible = "adi,ad9265", .data = &ad9265_chip_tbl, },
+	{ .compatible = "adi,ad9434", .data = &ad9434_chip_tbl, },
+	{ .compatible = "adi,ad9467", .data = &ad9467_chip_tbl, },
 	{}
 };
 MODULE_DEVICE_TABLE(of, ad9467_of_match);
 
 static const struct spi_device_id ad9467_ids[] = {
-	{ "ad9265", (kernel_ulong_t)&ad9467_chip_tbl[ID_AD9265] },
-	{ "ad9434", (kernel_ulong_t)&ad9467_chip_tbl[ID_AD9434] },
-	{ "ad9467", (kernel_ulong_t)&ad9467_chip_tbl[ID_AD9467] },
+	{ "ad9265", (kernel_ulong_t)&ad9265_chip_tbl },
+	{ "ad9434", (kernel_ulong_t)&ad9434_chip_tbl },
+	{ "ad9467", (kernel_ulong_t)&ad9467_chip_tbl },
 	{}
 };
 MODULE_DEVICE_TABLE(spi, ad9467_ids);
-- 
GitLab


From 8bdfa4a2fecf4d54b9157b1294970e7ff242f042 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:30 +0100
Subject: [PATCH 1078/4076] iio: adc: ad9467: use the more common !val NULL
 check

Check !val instead of directing checking for NULL (val == NULL).
No functional changes intended.

Reviewed-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-7-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad9467.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index c5ed62cc86465..6581fce4ba959 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -158,7 +158,7 @@ static int ad9467_reg_access(struct adi_axi_adc_conv *conv, unsigned int reg,
 	struct spi_device *spi = st->spi;
 	int ret;
 
-	if (readval == NULL) {
+	if (!readval) {
 		guard(mutex)(&st->lock);
 		ret = ad9467_spi_write(spi, reg, writeval);
 		if (ret)
-- 
GitLab


From 4a2006d0c338c95352bf9f06e5b3cb8afa0bc885 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Sat, 9 Dec 2023 23:30:52 +0000
Subject: [PATCH 1079/4076] dt-bindings: pinctrl: samsung: add
 google,gs101-pinctrl compatible

Add the "google,gs101-pinctrl" compatible to the dt-schema bindings
documentation.

Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20231209233106.147416-7-peter.griffin@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
index 9f04a0c764036..118549c259765 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml
@@ -35,6 +35,7 @@ properties:
 
   compatible:
     enum:
+      - google,gs101-pinctrl
       - samsung,s3c2412-pinctrl
       - samsung,s3c2416-pinctrl
       - samsung,s3c2440-pinctrl
-- 
GitLab


From abc73e50b394f248aa8e7ecdfbd4dfa52f8e8355 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Sat, 9 Dec 2023 23:30:53 +0000
Subject: [PATCH 1080/4076] dt-bindings: pinctrl: samsung: add
 gs101-wakeup-eint compatible

gs101 is similar to newer Exynos SoCs like Exynos850 and ExynosAutov9
where more than one pin controller can do external wake-up interrupt.
So add a dedicated compatible for it.

Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20231209233106.147416-8-peter.griffin@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml       | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 2bafa867aea24..4c0e25754c6b2 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -44,6 +44,7 @@ properties:
           - const: samsung,exynos7-wakeup-eint
       - items:
           - enum:
+              - google,gs101-wakeup-eint
               - samsung,exynosautov9-wakeup-eint
               - samsung,exynosautov920-wakeup-eint
           - const: samsung,exynos850-wakeup-eint
-- 
GitLab


From 4a8ececbb50f0dd9395ffc4188ae780916df4a9c Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 22 Nov 2023 16:50:50 -0700
Subject: [PATCH 1081/4076] dt-bindings: dma: Drop undocumented examples

The compatibles "ti,omap-sdma" and "ti,dra7-dma-crossbar" aren't documented
by a schema which causes warnings:

Documentation/devicetree/bindings/dma/dma-controller.example.dtb: /example-0/dma-controller@48000000: failed to match any schema with compatible: ['ti,omap-sdma']
Documentation/devicetree/bindings/dma/dma-router.example.dtb: /example-0/dma-router@4a002b78: failed to match any schema with compatible: ['ti,dra7-dma-crossbar']

As no one has cared to fix them, just drop them.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231122235050.2966280-1-robh@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/dma/dma-controller.yaml   | 15 ---------------
 .../devicetree/bindings/dma/dma-router.yaml       | 11 -----------
 2 files changed, 26 deletions(-)

diff --git a/Documentation/devicetree/bindings/dma/dma-controller.yaml b/Documentation/devicetree/bindings/dma/dma-controller.yaml
index 04d150d4d15d3..e6afca558c2df 100644
--- a/Documentation/devicetree/bindings/dma/dma-controller.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-controller.yaml
@@ -19,19 +19,4 @@ properties:
 
 additionalProperties: true
 
-examples:
-  - |
-    dma: dma-controller@48000000 {
-        compatible = "ti,omap-sdma";
-        reg = <0x48000000 0x1000>;
-        interrupts = <0 12 0x4>,
-                     <0 13 0x4>,
-                     <0 14 0x4>,
-                     <0 15 0x4>;
-        #dma-cells = <1>;
-        dma-channels = <32>;
-        dma-requests = <127>;
-        dma-channel-mask = <0xfffe>;
-    };
-
 ...
diff --git a/Documentation/devicetree/bindings/dma/dma-router.yaml b/Documentation/devicetree/bindings/dma/dma-router.yaml
index 346fe0fa4460e..5ad2febc581e2 100644
--- a/Documentation/devicetree/bindings/dma/dma-router.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-router.yaml
@@ -40,15 +40,4 @@ required:
 
 additionalProperties: true
 
-examples:
-  - |
-    sdma_xbar: dma-router@4a002b78 {
-        compatible = "ti,dra7-dma-crossbar";
-        reg = <0x4a002b78 0xfc>;
-        #dma-cells = <1>;
-        dma-requests = <205>;
-        ti,dma-safe-map = <0>;
-        dma-masters = <&sdma>;
-    };
-
 ...
-- 
GitLab


From e1564d6f93496bcea3a6b2110eb54cc08f2aca72 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 10 Dec 2023 14:39:15 +0100
Subject: [PATCH 1082/4076] dt-bindings: pinctrl: samsung: correct
 ExynosAutov920 wake-up compatibles

ExynosAutov920 SoC wake-up pin controller has different register layout
than Exynos7, thus it should not be marked as compatible.  Neither DTS
nor Linux driver was merged yet, so the change does not impact ABI.

Cc: Jaewon Kim <jaewon02.kim@samsung.com>
Fixes: 904140fa4553 ("dt-bindings: pinctrl: samsung: use Exynos7 fallbacks for newer wake-up controllers")
Link: https://lore.kernel.org/r/20231210133915.42112-1-krzysztof.kozlowski@linaro.org
Reviewed-by: Jaewon Kim <jaewon02.kim@samsung.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml     | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
index 4c0e25754c6b2..4dfb49b0e07f7 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml
@@ -36,6 +36,7 @@ properties:
           - samsung,s5pv210-wakeup-eint
           - samsung,exynos4210-wakeup-eint
           - samsung,exynos7-wakeup-eint
+          - samsung,exynosautov920-wakeup-eint
       - items:
           - enum:
               - samsung,exynos5433-wakeup-eint
@@ -46,7 +47,6 @@ properties:
           - enum:
               - google,gs101-wakeup-eint
               - samsung,exynosautov9-wakeup-eint
-              - samsung,exynosautov920-wakeup-eint
           - const: samsung,exynos850-wakeup-eint
           - const: samsung,exynos7-wakeup-eint
 
@@ -113,6 +113,7 @@ allOf:
           contains:
             enum:
               - samsung,exynos850-wakeup-eint
+              - samsung,exynosautov920-wakeup-eint
     then:
       properties:
         interrupts: false
-- 
GitLab


From 5cc623a4edaf383eea39546104084b089f3035ca Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 6 Dec 2023 10:13:17 -0800
Subject: [PATCH 1083/4076] usb: cdns3: starfive: don't misuse /** comment

Use a common C comment "/*" instead of "/**" to prevent a warning
from scripts/kernel-doc.

cdns3-starfive.c:23: warning: expecting prototype for cdns3(). Prototype was for USB_STRAP_HOST() instead

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Minda Chen <minda.chen@starfivetech.com>
Cc: Peter Chen <peter.chen@kernel.org>
Cc: Pawel Laszczak <pawell@cadence.com>
Cc: Roger Quadros <rogerq@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc:  <linux-usb@vger.kernel.org>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/20231206181317.27515-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-starfive.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/cdns3/cdns3-starfive.c b/drivers/usb/cdns3/cdns3-starfive.c
index a7265b86e4277..c04d196abd878 100644
--- a/drivers/usb/cdns3/cdns3-starfive.c
+++ b/drivers/usb/cdns3/cdns3-starfive.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * cdns3-starfive.c - StarFive specific Glue layer for Cadence USB Controller
  *
  * Copyright (C) 2023 StarFive Technology Co., Ltd.
-- 
GitLab


From 51920207674e9e3475a91d2091583889792df99a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 6 Dec 2023 10:13:35 -0800
Subject: [PATCH 1084/4076] usb: fotg210-udc: fix function kernel-doc comments

Correct kernel-doc comments to prevent warnings from
scripts/kernel-doc.

fotg210-udc.c:1103: warning: Function parameter or member 'g' not described in 'fotg210_vbus_session'
fotg210-udc.c:1103: warning: Excess function parameter '_gadget' description in 'fotg210_vbus_session'
fotg210-udc.c:1103: warning: No description found for return value of 'fotg210_vbus_session'
fotg210-udc.c:1129: warning: No description found for return value of 'fotg210_phy_event'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc:  <linux-usb@vger.kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231206181335.27540-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/fotg210/fotg210-udc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/fotg210/fotg210-udc.c b/drivers/usb/fotg210/fotg210-udc.c
index f7ea84070554e..0bae12e34f9a7 100644
--- a/drivers/usb/fotg210/fotg210-udc.c
+++ b/drivers/usb/fotg210/fotg210-udc.c
@@ -1094,10 +1094,10 @@ static int fotg210_udc_stop(struct usb_gadget *g)
 
 /**
  * fotg210_vbus_session - Called by external transceiver to enable/disable udc
- * @_gadget: usb gadget
+ * @g: usb gadget
  * @is_active: 0 if should disable UDC VBUS, 1 if should enable
  *
- * Returns 0
+ * Returns: %0
  */
 static int fotg210_vbus_session(struct usb_gadget *g, int is_active)
 {
@@ -1122,7 +1122,7 @@ static const struct usb_gadget_ops fotg210_gadget_ops = {
  *
  * Called by the USB Phy when a cable connect or disconnect is sensed.
  *
- * Returns NOTIFY_OK or NOTIFY_DONE
+ * Returns: NOTIFY_OK or NOTIFY_DONE
  */
 static int fotg210_phy_event(struct notifier_block *nb, unsigned long action,
 			     void *data)
-- 
GitLab


From 8e578b47e6d92d5e43982ddc54045973dd4a7de5 Mon Sep 17 00:00:00 2001
From: Shravan Chippa <shravan.chippa@microchip.com>
Date: Fri, 8 Dec 2023 16:08:53 +0530
Subject: [PATCH 1085/4076] dmaengine: sf-pdma: Support
 of_dma_controller_register()

Update sf-pdma driver to adopt generic DMA device tree bindings.
It calls of_dma_controller_register() with of_dma_xlate_by_chan_id
to get the generic DMA device tree helper support and the DMA
clients can look up the sf-pdma controller using standard APIs.

Signed-off-by: Shravan Chippa <shravan.chippa@microchip.com>
Link: https://lore.kernel.org/r/20231208103856.3732998-2-shravan.chippa@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/sf-pdma/sf-pdma.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 3125a2f162b47..6109e1c5a09ea 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -20,6 +20,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
+#include <linux/of_dma.h>
 #include <linux/slab.h>
 
 #include "sf-pdma.h"
@@ -563,7 +564,20 @@ static int sf_pdma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 of_dma_xlate_by_chan_id, pdma);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"Can't register SiFive Platform OF_DMA. (%d)\n", ret);
+		goto err_unregister;
+	}
+
 	return 0;
+
+err_unregister:
+	dma_async_device_unregister(&pdma->dma_dev);
+
+	return ret;
 }
 
 static void sf_pdma_remove(struct platform_device *pdev)
@@ -583,6 +597,9 @@ static void sf_pdma_remove(struct platform_device *pdev)
 		tasklet_kill(&ch->err_tasklet);
 	}
 
+	if (pdev->dev.of_node)
+		of_dma_controller_free(pdev->dev.of_node);
+
 	dma_async_device_unregister(&pdma->dma_dev);
 }
 
-- 
GitLab


From 72b22006ba78c2e3bf39b486a7b8155dc9020133 Mon Sep 17 00:00:00 2001
From: Shravan Chippa <shravan.chippa@microchip.com>
Date: Fri, 8 Dec 2023 16:08:54 +0530
Subject: [PATCH 1086/4076] dt-bindings: dma: sf-pdma: add new compatible name

Add new compatible name microchip,mpfs-pdma to support
out of order dma transfers

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Shravan Chippa <shravan.chippa@microchip.com>
Link: https://lore.kernel.org/r/20231208103856.3732998-3-shravan.chippa@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml          | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml b/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
index a1af0b9063653..3b22183a1a379 100644
--- a/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
+++ b/Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
@@ -29,6 +29,7 @@ properties:
   compatible:
     items:
       - enum:
+          - microchip,mpfs-pdma
           - sifive,fu540-c000-pdma
       - const: sifive,pdma0
     description:
-- 
GitLab


From 58eea79a1cf285a62af886851b1a91ed5aceb401 Mon Sep 17 00:00:00 2001
From: Shravan Chippa <shravan.chippa@microchip.com>
Date: Fri, 8 Dec 2023 16:08:55 +0530
Subject: [PATCH 1087/4076] dmaengine: sf-pdma: add mpfs-pdma compatible name

Sifive platform dma (sf-pdma) has both in-order and out-of-order
configurations but sf-pdam driver configured to do in-order DMA
transfers, with out-of-order configuration got better throughput
in the PolarFire SoC platform.

Add a PolarFire SoC specific compatible and code to support
for out-of-order dma transfers

Reviewed-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Signed-off-by: Shravan Chippa <shravan.chippa@microchip.com>
Link: https://lore.kernel.org/r/20231208103856.3732998-4-shravan.chippa@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/sf-pdma/sf-pdma.c | 27 ++++++++++++++++++++++++---
 drivers/dma/sf-pdma/sf-pdma.h |  8 +++++++-
 2 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 6109e1c5a09ea..428473611115d 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -25,6 +25,8 @@
 
 #include "sf-pdma.h"
 
+#define PDMA_QUIRK_NO_STRICT_ORDERING   BIT(0)
+
 #ifndef readq
 static inline unsigned long long readq(void __iomem *addr)
 {
@@ -66,7 +68,7 @@ static struct sf_pdma_desc *sf_pdma_alloc_desc(struct sf_pdma_chan *chan)
 static void sf_pdma_fill_desc(struct sf_pdma_desc *desc,
 			      u64 dst, u64 src, u64 size)
 {
-	desc->xfer_type = PDMA_FULL_SPEED;
+	desc->xfer_type =  desc->chan->pdma->transfer_type;
 	desc->xfer_size = size;
 	desc->dst_addr = dst;
 	desc->src_addr = src;
@@ -493,6 +495,7 @@ static void sf_pdma_setup_chans(struct sf_pdma *pdma)
 
 static int sf_pdma_probe(struct platform_device *pdev)
 {
+	const struct sf_pdma_driver_platdata *ddata;
 	struct sf_pdma *pdma;
 	int ret, n_chans;
 	const enum dma_slave_buswidth widths =
@@ -518,6 +521,14 @@ static int sf_pdma_probe(struct platform_device *pdev)
 
 	pdma->n_chans = n_chans;
 
+	pdma->transfer_type = PDMA_FULL_SPEED | PDMA_STRICT_ORDERING;
+
+	ddata  = device_get_match_data(&pdev->dev);
+	if (ddata) {
+		if (ddata->quirks & PDMA_QUIRK_NO_STRICT_ORDERING)
+			pdma->transfer_type &= ~PDMA_STRICT_ORDERING;
+	}
+
 	pdma->membase = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(pdma->membase))
 		return PTR_ERR(pdma->membase);
@@ -603,9 +614,19 @@ static void sf_pdma_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&pdma->dma_dev);
 }
 
+static const struct sf_pdma_driver_platdata mpfs_pdma = {
+	.quirks = PDMA_QUIRK_NO_STRICT_ORDERING,
+};
+
 static const struct of_device_id sf_pdma_dt_ids[] = {
-	{ .compatible = "sifive,fu540-c000-pdma" },
-	{ .compatible = "sifive,pdma0" },
+	{
+		.compatible = "sifive,fu540-c000-pdma",
+	}, {
+		.compatible = "sifive,pdma0",
+	}, {
+		.compatible = "microchip,mpfs-pdma",
+		.data	    = &mpfs_pdma,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, sf_pdma_dt_ids);
diff --git a/drivers/dma/sf-pdma/sf-pdma.h b/drivers/dma/sf-pdma/sf-pdma.h
index d05772b5d8d3f..215e07183d7e2 100644
--- a/drivers/dma/sf-pdma/sf-pdma.h
+++ b/drivers/dma/sf-pdma/sf-pdma.h
@@ -48,7 +48,8 @@
 #define PDMA_ERR_STATUS_MASK				GENMASK(31, 31)
 
 /* Transfer Type */
-#define PDMA_FULL_SPEED					0xFF000008
+#define PDMA_FULL_SPEED					0xFF000000
+#define PDMA_STRICT_ORDERING				BIT(3)
 
 /* Error Recovery */
 #define MAX_RETRY					1
@@ -112,8 +113,13 @@ struct sf_pdma {
 	struct dma_device       dma_dev;
 	void __iomem            *membase;
 	void __iomem            *mappedbase;
+	u32			transfer_type;
 	u32			n_chans;
 	struct sf_pdma_chan	chans[] __counted_by(n_chans);
 };
 
+struct sf_pdma_driver_platdata {
+	u32 quirks;
+};
+
 #endif /* _SF_PDMA_H */
-- 
GitLab


From d95fcb78e7f263f909ce492c3882a704067dc534 Mon Sep 17 00:00:00 2001
From: Mohan Kumar <mkumard@nvidia.com>
Date: Tue, 28 Nov 2023 12:46:14 +0530
Subject: [PATCH 1088/4076] dt-bindings: dma: Add dma-channel-mask to
 nvidia,tegra210-adma

Add dma-channel-mask binding doc support to nvidia,tegra210-adma
to reserve the adma channel usage

Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Mohan Kumar <mkumard@nvidia.com>
Link: https://lore.kernel.org/r/20231128071615.31447-2-mkumard@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/dma/nvidia,tegra210-adma.yaml          | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
index 4003dbe94940c..877147e95ecc5 100644
--- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
+++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
@@ -53,6 +53,9 @@ properties:
       ADMA_CHn_CTRL register.
     const: 1
 
+  dma-channel-mask:
+    maxItems: 1
+
 required:
   - compatible
   - reg
-- 
GitLab


From 25b636225a0816eac20b02fcb37daf6c722d0bed Mon Sep 17 00:00:00 2001
From: Mohan Kumar <mkumard@nvidia.com>
Date: Tue, 28 Nov 2023 12:46:15 +0530
Subject: [PATCH 1089/4076] dmaengine: tegra210-adma: Support dma-channel-mask
 property

To support the flexibility to reserve the specific dma channels
add the support of dma-channel-mask property in the tegra210-adma
driver

Signed-off-by: Mohan Kumar <mkumard@nvidia.com>
Link: https://lore.kernel.org/r/20231128071615.31447-3-mkumard@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/tegra210-adma.c | 35 +++++++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 7a0586633bf32..24ad7077c53ba 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -153,6 +153,7 @@ struct tegra_adma {
 	void __iomem			*base_addr;
 	struct clk			*ahub_clk;
 	unsigned int			nr_channels;
+	unsigned long			*dma_chan_mask;
 	unsigned long			rx_requests_reserved;
 	unsigned long			tx_requests_reserved;
 
@@ -741,6 +742,10 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
 
 	for (i = 0; i < tdma->nr_channels; i++) {
 		tdc = &tdma->channels[i];
+		/* skip for reserved channels */
+		if (!tdc->tdma)
+			continue;
+
 		ch_reg = &tdc->ch_regs;
 		ch_reg->cmd = tdma_ch_read(tdc, ADMA_CH_CMD);
 		/* skip if channel is not active */
@@ -779,6 +784,9 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
 
 	for (i = 0; i < tdma->nr_channels; i++) {
 		tdc = &tdma->channels[i];
+		/* skip for reserved channels */
+		if (!tdc->tdma)
+			continue;
 		ch_reg = &tdc->ch_regs;
 		/* skip if channel was not active earlier */
 		if (!ch_reg->cmd)
@@ -867,10 +875,31 @@ static int tegra_adma_probe(struct platform_device *pdev)
 		return PTR_ERR(tdma->ahub_clk);
 	}
 
+	tdma->dma_chan_mask = devm_kzalloc(&pdev->dev,
+					   BITS_TO_LONGS(tdma->nr_channels) * sizeof(unsigned long),
+					   GFP_KERNEL);
+	if (!tdma->dma_chan_mask)
+		return -ENOMEM;
+
+	/* Enable all channels by default */
+	bitmap_fill(tdma->dma_chan_mask, tdma->nr_channels);
+
+	ret = of_property_read_u32_array(pdev->dev.of_node, "dma-channel-mask",
+					 (u32 *)tdma->dma_chan_mask,
+					 BITS_TO_U32(tdma->nr_channels));
+	if (ret < 0 && (ret != -EINVAL)) {
+		dev_err(&pdev->dev, "dma-channel-mask is not complete.\n");
+		return ret;
+	}
+
 	INIT_LIST_HEAD(&tdma->dma_dev.channels);
 	for (i = 0; i < tdma->nr_channels; i++) {
 		struct tegra_adma_chan *tdc = &tdma->channels[i];
 
+		/* skip for reserved channels */
+		if (!test_bit(i, tdma->dma_chan_mask))
+			continue;
+
 		tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset
 				 + (cdata->ch_reg_size * i);
 
@@ -957,8 +986,10 @@ static void tegra_adma_remove(struct platform_device *pdev)
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&tdma->dma_dev);
 
-	for (i = 0; i < tdma->nr_channels; ++i)
-		irq_dispose_mapping(tdma->channels[i].irq);
+	for (i = 0; i < tdma->nr_channels; ++i) {
+		if (tdma->channels[i].irq)
+			irq_dispose_mapping(tdma->channels[i].irq);
+	}
 
 	pm_runtime_disable(&pdev->dev);
 }
-- 
GitLab


From 57cdb720eaa5c4b2fcf04ba6ff6a26f638b0b474 Mon Sep 17 00:00:00 2001
From: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Date: Tue, 17 Oct 2023 09:42:36 -0500
Subject: [PATCH 1090/4076] iommu/amd: Do not flush IRTE when only updating
 isRun and destination fields

According to the recent update in the AMD IOMMU spec [1], the IsRun and
Destination fields of the Interrupt Remapping Table Entry (IRTE) are not
cached by the IOMMU hardware.

Therefore, do not issue the INVALIDATE_INTERRUPT_TABLE command when
updating IRTE[IsRun] and IRTE[Destination] when IRTE[GuestMode]=1, which
should help improve IOMMU AVIC/x2AVIC performance.

References:
[1] AMD IOMMU Spec Revision (Rev 3.08-PUB)
(Link: https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/specifications/48882_IOMMU.pdf)

Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Link: https://lore.kernel.org/r/20231017144236.8287-1-suravee.suthikulpanit@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 9f70643608283..b14046b6e1e77 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3111,8 +3111,8 @@ out:
 	return index;
 }
 
-static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
-			  struct irte_ga *irte)
+static int __modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			    struct irte_ga *irte)
 {
 	struct irq_remap_table *table;
 	struct irte_ga *entry;
@@ -3139,6 +3139,18 @@ static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 
 	raw_spin_unlock_irqrestore(&table->lock, flags);
 
+	return 0;
+}
+
+static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			  struct irte_ga *irte)
+{
+	bool ret;
+
+	ret = __modify_irte_ga(iommu, devid, index, irte);
+	if (ret)
+		return ret;
+
 	iommu_flush_irt_and_complete(iommu, devid);
 
 	return 0;
@@ -3822,8 +3834,8 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 	}
 	entry->lo.fields_vapic.is_run = is_run;
 
-	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry);
+	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+				ir_data->irq_2_irte.index, entry);
 }
 EXPORT_SYMBOL(amd_iommu_update_ga);
 #endif
-- 
GitLab


From af3263758bf0b65a040e90190ab708b8a4027947 Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:07 +0000
Subject: [PATCH 1091/4076] iommu/amd: Rename iommu_flush_all_caches() ->
 amd_iommu_flush_all_caches()

Rename function inline with driver naming convention.

No functional changes.

Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-2-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/amd_iommu.h       | 5 +++++
 drivers/iommu/amd/amd_iommu_types.h | 6 ------
 drivers/iommu/amd/init.c            | 8 ++++----
 drivers/iommu/amd/iommu.c           | 2 +-
 4 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 86be1edd50ee9..234db57cd3209 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -53,6 +53,11 @@ int amd_iommu_pdev_enable_cap_pri(struct pci_dev *pdev);
 void amd_iommu_pdev_disable_cap_pri(struct pci_dev *pdev);
 
 int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, u64 address);
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu);
 void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
 void amd_iommu_domain_update(struct protection_domain *domain);
 void amd_iommu_domain_flush_complete(struct protection_domain *domain);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 90b7d7950a9ef..809d74faa1a5d 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -902,12 +902,6 @@ extern int amd_iommu_max_glx_val;
 extern u64 amd_iommu_efr;
 extern u64 amd_iommu_efr2;
 
-/*
- * This function flushes all internal caches of
- * the IOMMU used by this driver.
- */
-void iommu_flush_all_caches(struct amd_iommu *iommu);
-
 static inline int get_ioapic_devid(int id)
 {
 	struct devid_map *entry;
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 64bcf3df37ee5..c83bd0c2a1c92 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -2223,7 +2223,7 @@ static int __init amd_iommu_init_pci(void)
 		init_device_table_dma(pci_seg);
 
 	for_each_iommu(iommu)
-		iommu_flush_all_caches(iommu);
+		amd_iommu_flush_all_caches(iommu);
 
 	print_iommu_info();
 
@@ -2773,7 +2773,7 @@ static void early_enable_iommu(struct amd_iommu *iommu)
 	iommu_enable_xt(iommu);
 	iommu_enable_irtcachedis(iommu);
 	iommu_enable(iommu);
-	iommu_flush_all_caches(iommu);
+	amd_iommu_flush_all_caches(iommu);
 }
 
 /*
@@ -2829,7 +2829,7 @@ static void early_enable_iommus(void)
 			iommu_enable_xt(iommu);
 			iommu_enable_irtcachedis(iommu);
 			iommu_set_device_table(iommu);
-			iommu_flush_all_caches(iommu);
+			amd_iommu_flush_all_caches(iommu);
 		}
 	}
 }
@@ -3293,7 +3293,7 @@ static int __init state_next(void)
 				uninit_device_table_dma(pci_seg);
 
 			for_each_iommu(iommu)
-				iommu_flush_all_caches(iommu);
+				amd_iommu_flush_all_caches(iommu);
 		}
 	}
 	return ret;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b14046b6e1e77..c2578b567e35c 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1392,7 +1392,7 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu)
 	iommu_completion_wait(iommu);
 }
 
-void iommu_flush_all_caches(struct amd_iommu *iommu)
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu)
 {
 	if (check_feature(FEATURE_IA)) {
 		amd_iommu_flush_all(iommu);
-- 
GitLab


From 3f2571fed2fa9e9ea61fd990a9a4fc20ca83b62e Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:08 +0000
Subject: [PATCH 1092/4076] iommu/amd: Remove redundant domain flush from
 attach_device()

Domain flush was introduced in attach_device() path to handle kdump
scenario. Later init code was enhanced to handle kdump scenario where
it also takes care of flushing everything including TLB
(see early_enable_iommus()).

Hence remove redundant flush from attach_device() function.

Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-3-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index c2578b567e35c..2330766863793 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1896,15 +1896,6 @@ static int attach_device(struct device *dev,
 
 	do_attach(dev_data, domain);
 
-	/*
-	 * We might boot into a crash-kernel here. The crashed kernel
-	 * left the caches in the IOMMU dirty. So we have to flush
-	 * here to evict all dirty stuff.
-	 */
-	amd_iommu_domain_flush_tlb_pde(domain);
-
-	amd_iommu_domain_flush_complete(domain);
-
 out:
 	spin_unlock(&dev_data->lock);
 
-- 
GitLab


From a976da66e8e547cd07a9792f5854c2f73c456a21 Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:09 +0000
Subject: [PATCH 1093/4076] iommu/amd: Remove redundant passing of PDE bit

Current code always sets PDE bit in INVALIDATE_IOMMU_PAGES command.
Hence get rid of 'pde' variable across functions.

We can re-introduce this bit whenever its needed.

Suggested-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-4-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 2330766863793..b1551330758b5 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1124,7 +1124,7 @@ static inline u64 build_inv_address(u64 address, size_t size)
 }
 
 static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
-				  size_t size, u16 domid, int pde)
+				  size_t size, u16 domid)
 {
 	u64 inv_address = build_inv_address(address, size);
 
@@ -1133,8 +1133,8 @@ static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
 	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-	if (pde) /* PDE bit - we want to flush everything, not only the PTEs */
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+	/* PDE bit - we want to flush everything, not only the PTEs */
+	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
 }
 
 static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
@@ -1341,7 +1341,7 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
 	for (dom_id = 0; dom_id <= last_bdf; ++dom_id) {
 		struct iommu_cmd cmd;
 		build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-				      dom_id, 1);
+				      dom_id);
 		iommu_queue_command(iommu, &cmd);
 	}
 
@@ -1352,8 +1352,7 @@ static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
 {
 	struct iommu_cmd cmd;
 
-	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-			      dom_id, 1);
+	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, dom_id);
 	iommu_queue_command(iommu, &cmd);
 
 	iommu_completion_wait(iommu);
@@ -1476,13 +1475,13 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
  * page. Otherwise it flushes the whole TLB of the IOMMU.
  */
 static void __domain_flush_pages(struct protection_domain *domain,
-				 u64 address, size_t size, int pde)
+				 u64 address, size_t size)
 {
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
 	int ret = 0, i;
 
-	build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
+	build_inv_iommu_pages(&cmd, address, size, domain->id);
 
 	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (!domain->dev_iommu[i])
@@ -1507,10 +1506,10 @@ static void __domain_flush_pages(struct protection_domain *domain,
 }
 
 static void domain_flush_pages(struct protection_domain *domain,
-			       u64 address, size_t size, int pde)
+			       u64 address, size_t size)
 {
 	if (likely(!amd_iommu_np_cache)) {
-		__domain_flush_pages(domain, address, size, pde);
+		__domain_flush_pages(domain, address, size);
 		return;
 	}
 
@@ -1543,7 +1542,7 @@ static void domain_flush_pages(struct protection_domain *domain,
 
 		flush_size = 1ul << min_alignment;
 
-		__domain_flush_pages(domain, address, flush_size, pde);
+		__domain_flush_pages(domain, address, flush_size);
 		address += flush_size;
 		size -= flush_size;
 	}
@@ -1552,7 +1551,7 @@ static void domain_flush_pages(struct protection_domain *domain,
 /* Flush the whole IO/TLB for a given protection domain - including PDE */
 void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain)
 {
-	domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
+	domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
 }
 
 void amd_iommu_domain_flush_complete(struct protection_domain *domain)
@@ -1579,7 +1578,7 @@ static void domain_flush_np_cache(struct protection_domain *domain,
 		unsigned long flags;
 
 		spin_lock_irqsave(&domain->lock, flags);
-		domain_flush_pages(domain, iova, size, 1);
+		domain_flush_pages(domain, iova, size);
 		amd_iommu_domain_flush_complete(domain);
 		spin_unlock_irqrestore(&domain->lock, flags);
 	}
@@ -2591,7 +2590,7 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
+	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1);
 	amd_iommu_domain_flush_complete(dom);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
-- 
GitLab


From cf62924daf9f0363c82e4332d9ac9630f1d76c42 Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:10 +0000
Subject: [PATCH 1094/4076] iommu/amd: Add support to invalidate multiple guest
 pages

Current interface supports invalidating single page or entire guest
translation information for a single process address space.

IOMMU CMD_INV_IOMMU_PAGES and CMD_INV_IOTLB_PAGES commands supports
invalidating range of pages. Add support to invalidate multiple pages.

This is preparatory patch before consolidating host and guest
invalidation code into single function. Following patches will
consolidation tlb invalidation code.

Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-5-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b1551330758b5..b26db4f0b6508 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1152,40 +1152,36 @@ static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
 }
 
 static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
-				  u64 address, bool size)
+				  u64 address, size_t size)
 {
-	memset(cmd, 0, sizeof(*cmd));
+	u64 inv_address = build_inv_address(address, size);
 
-	address &= ~(0xfffULL);
+	memset(cmd, 0, sizeof(*cmd));
 
 	cmd->data[0]  = pasid;
 	cmd->data[1]  = domid;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[3]  = upper_32_bits(address);
+	cmd->data[2]  = lower_32_bits(inv_address);
+	cmd->data[3]  = upper_32_bits(inv_address);
 	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
 	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	if (size)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
 	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
 }
 
 static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
-				  int qdep, u64 address, bool size)
+				  int qdep, u64 address, size_t size)
 {
-	memset(cmd, 0, sizeof(*cmd));
+	u64 inv_address = build_inv_address(address, size);
 
-	address &= ~(0xfffULL);
+	memset(cmd, 0, sizeof(*cmd));
 
 	cmd->data[0]  = devid;
 	cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
 	cmd->data[0] |= (qdep  & 0xff) << 24;
 	cmd->data[1]  = devid;
 	cmd->data[1] |= (pasid & 0xff) << 16;
-	cmd->data[2]  = lower_32_bits(address);
+	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	cmd->data[3]  = upper_32_bits(address);
-	if (size)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+	cmd->data[3]  = upper_32_bits(inv_address);
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
@@ -2656,7 +2652,7 @@ const struct iommu_ops amd_iommu_ops = {
 };
 
 static int __flush_pasid(struct protection_domain *domain, u32 pasid,
-			 u64 address, bool size)
+			 u64 address, size_t size)
 {
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
@@ -2720,7 +2716,7 @@ out:
 static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
 				  u64 address)
 {
-	return __flush_pasid(domain, pasid, address, false);
+	return __flush_pasid(domain, pasid, address, PAGE_SIZE);
 }
 
 int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
@@ -2739,8 +2735,7 @@ int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 
 static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid)
 {
-	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-			     true);
+	return __flush_pasid(domain, pasid, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
 }
 
 int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid)
-- 
GitLab


From 4f0a600799237ed95b403f24354305b0f81ccbb4 Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:11 +0000
Subject: [PATCH 1095/4076] iommu/amd: Refactor IOMMU tlb invalidation code

build_inv_iommu_pages() and build_inv_iommu_pasid() pretty much
duplicates the code. Hence enhance build_inv_iommu_pages() to
invalidate guest pages as well. And remove build_inv_iommu_pasid().

Suggested-by: Kishon Vijay Abraham I <kvijayab@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-6-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 36 ++++++++++++++----------------------
 1 file changed, 14 insertions(+), 22 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b26db4f0b6508..8c09e8f639133 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1124,17 +1124,23 @@ static inline u64 build_inv_address(u64 address, size_t size)
 }
 
 static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
-				  size_t size, u16 domid)
+				  size_t size, u16 domid,
+				  ioasid_t pasid, bool gn)
 {
 	u64 inv_address = build_inv_address(address, size);
 
 	memset(cmd, 0, sizeof(*cmd));
+
 	cmd->data[1] |= domid;
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
-	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
 	/* PDE bit - we want to flush everything, not only the PTEs */
 	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+	if (gn) {
+		cmd->data[0] |= pasid;
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
+	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
 }
 
 static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
@@ -1151,22 +1157,6 @@ static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
-static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
-				  u64 address, size_t size)
-{
-	u64 inv_address = build_inv_address(address, size);
-
-	memset(cmd, 0, sizeof(*cmd));
-
-	cmd->data[0]  = pasid;
-	cmd->data[1]  = domid;
-	cmd->data[2]  = lower_32_bits(inv_address);
-	cmd->data[3]  = upper_32_bits(inv_address);
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-}
-
 static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
 				  int qdep, u64 address, size_t size)
 {
@@ -1337,7 +1327,7 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
 	for (dom_id = 0; dom_id <= last_bdf; ++dom_id) {
 		struct iommu_cmd cmd;
 		build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-				      dom_id);
+				      dom_id, IOMMU_NO_PASID, false);
 		iommu_queue_command(iommu, &cmd);
 	}
 
@@ -1348,7 +1338,8 @@ static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
 {
 	struct iommu_cmd cmd;
 
-	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, dom_id);
+	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+			      dom_id, IOMMU_NO_PASID, false);
 	iommu_queue_command(iommu, &cmd);
 
 	iommu_completion_wait(iommu);
@@ -1477,7 +1468,8 @@ static void __domain_flush_pages(struct protection_domain *domain,
 	struct iommu_cmd cmd;
 	int ret = 0, i;
 
-	build_inv_iommu_pages(&cmd, address, size, domain->id);
+	build_inv_iommu_pages(&cmd, address, size, domain->id,
+			      IOMMU_NO_PASID, false);
 
 	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (!domain->dev_iommu[i])
@@ -2661,7 +2653,7 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 	if (!(domain->flags & PD_IOMMUV2_MASK))
 		return -EINVAL;
 
-	build_inv_iommu_pasid(&cmd, domain->id, pasid, address, size);
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, true);
 
 	/*
 	 * IOMMU TLB needs to be flushed before Device TLB to
-- 
GitLab


From bbf85fe10faadbd237a7b8df4423de4ab4bd67e7 Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:12 +0000
Subject: [PATCH 1096/4076] iommu/amd: Refactor device iotlb invalidation code

build_inv_iotlb_pages() and build_inv_iotlb_pasid() pretty much duplicates
the code. Enhance build_inv_iotlb_pages() to invalidate guest IOTLB as
well. And remove build_inv_iotlb_pasid() function.

Suggested-by: Kishon Vijay Abraham I <kvijayab@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-7-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 33 ++++++++++++---------------------
 1 file changed, 12 insertions(+), 21 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 8c09e8f639133..a071e1d52c3e8 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1144,34 +1144,24 @@ static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
 }
 
 static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
-				  u64 address, size_t size)
+				  u64 address, size_t size,
+				  ioasid_t pasid, bool gn)
 {
 	u64 inv_address = build_inv_address(address, size);
 
 	memset(cmd, 0, sizeof(*cmd));
+
 	cmd->data[0]  = devid;
 	cmd->data[0] |= (qdep & 0xff) << 24;
 	cmd->data[1]  = devid;
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
-	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
-}
-
-static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
-				  int qdep, u64 address, size_t size)
-{
-	u64 inv_address = build_inv_address(address, size);
-
-	memset(cmd, 0, sizeof(*cmd));
+	if (gn) {
+		cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
+		cmd->data[1] |= (pasid & 0xff) << 16;
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
 
-	cmd->data[0]  = devid;
-	cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
-	cmd->data[0] |= (qdep  & 0xff) << 24;
-	cmd->data[1]  = devid;
-	cmd->data[1] |= (pasid & 0xff) << 16;
-	cmd->data[2]  = lower_32_bits(inv_address);
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	cmd->data[3]  = upper_32_bits(inv_address);
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
@@ -1404,7 +1394,8 @@ static int device_flush_iotlb(struct iommu_dev_data *dev_data,
 	if (!iommu)
 		return -EINVAL;
 
-	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, size);
+	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address,
+			      size, IOMMU_NO_PASID, false);
 
 	return iommu_queue_command(iommu, &cmd);
 }
@@ -2687,8 +2678,8 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 		iommu = rlookup_amd_iommu(dev_data->dev);
 		if (!iommu)
 			continue;
-		build_inv_iotlb_pasid(&cmd, dev_data->devid, pasid,
-				      qdep, address, size);
+		build_inv_iotlb_pages(&cmd, dev_data->devid, qdep,
+				      address, size, pasid, true);
 
 		ret = iommu_queue_command(iommu, &cmd);
 		if (ret != 0)
-- 
GitLab


From 8d004ac1c67bc1584b4b6b90429487dac5b2d83f Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:13 +0000
Subject: [PATCH 1097/4076] iommu/amd: Consolidate
 amd_iommu_domain_flush_complete() call

Call amd_iommu_domain_flush_complete() from domain_flush_pages().
That way we can remove explicit call of amd_iommu_domain_flush_complete()
from various places.

Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-8-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/io_pgtable.c |  1 -
 drivers/iommu/amd/iommu.c      | 21 ++++++++++-----------
 2 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index 6c0621f6f572a..ca22546e4d1a5 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -425,7 +425,6 @@ out:
 		 * increase_address_space().
 		 */
 		amd_iommu_domain_flush_tlb_pde(dom);
-		amd_iommu_domain_flush_complete(dom);
 		spin_unlock_irqrestore(&dom->lock, flags);
 	}
 
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index a071e1d52c3e8..cb8f51d5f83dd 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1489,6 +1489,10 @@ static void domain_flush_pages(struct protection_domain *domain,
 {
 	if (likely(!amd_iommu_np_cache)) {
 		__domain_flush_pages(domain, address, size);
+
+		/* Wait until IOMMU TLB and all device IOTLB flushes are complete */
+		amd_iommu_domain_flush_complete(domain);
+
 		return;
 	}
 
@@ -1525,6 +1529,9 @@ static void domain_flush_pages(struct protection_domain *domain,
 		address += flush_size;
 		size -= flush_size;
 	}
+
+	/* Wait until IOMMU TLB and all device IOTLB flushes are complete */
+	amd_iommu_domain_flush_complete(domain);
 }
 
 /* Flush the whole IO/TLB for a given protection domain - including PDE */
@@ -1558,7 +1565,6 @@ static void domain_flush_np_cache(struct protection_domain *domain,
 
 		spin_lock_irqsave(&domain->lock, flags);
 		domain_flush_pages(domain, iova, size);
-		amd_iommu_domain_flush_complete(domain);
 		spin_unlock_irqrestore(&domain->lock, flags);
 	}
 }
@@ -1836,12 +1842,9 @@ static void do_detach(struct iommu_dev_data *dev_data)
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
 
-	/* Flush IOTLB */
+	/* Flush IOTLB and wait for the flushes to finish */
 	amd_iommu_domain_flush_tlb_pde(domain);
 
-	/* Wait for the flushes to finish */
-	amd_iommu_domain_flush_complete(domain);
-
 	/* decrease reference counters - needs to happen after the flushes */
 	domain->dev_iommu[iommu->index] -= 1;
 	domain->dev_cnt                 -= 1;
@@ -2018,7 +2021,6 @@ void amd_iommu_domain_update(struct protection_domain *domain)
 
 	/* Flush domain TLB(s) and wait for completion */
 	amd_iommu_domain_flush_tlb_pde(domain);
-	amd_iommu_domain_flush_complete(domain);
 }
 
 /*****************************************************************************
@@ -2451,10 +2453,9 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain,
 	}
 
 	/* Flush IOTLB to mark IOPTE dirty on the next translation(s) */
-	if (domain_flush) {
+	if (domain_flush)
 		amd_iommu_domain_flush_tlb_pde(pdomain);
-		amd_iommu_domain_flush_complete(pdomain);
-	}
+
 	pdomain->dirty_tracking = enable;
 	spin_unlock_irqrestore(&pdomain->lock, flags);
 
@@ -2558,7 +2559,6 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 
 	spin_lock_irqsave(&dom->lock, flags);
 	amd_iommu_domain_flush_tlb_pde(dom);
-	amd_iommu_domain_flush_complete(dom);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
@@ -2570,7 +2570,6 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 
 	spin_lock_irqsave(&dom->lock, flags);
 	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1);
-	amd_iommu_domain_flush_complete(dom);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
-- 
GitLab


From 2c535dd37d677abd11b278fce89b8bdb0a55facb Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:14 +0000
Subject: [PATCH 1098/4076] iommu/amd: Make domain_flush_pages as global
 function

- Rename domain_flush_pages() -> amd_iommu_domain_flush_pages() and make
  it as global function.

- Rename amd_iommu_domain_flush_tlb_pde() -> amd_iommu_domain_flush_all()
  and make it as static.

- Convert v1 page table (io_pgtble.c) to use amd_iommu_domain_flush_pages().

Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-9-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/amd_iommu.h  |  3 ++-
 drivers/iommu/amd/io_pgtable.c |  4 +++-
 drivers/iommu/amd/iommu.c      | 22 ++++++++++++----------
 3 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 234db57cd3209..8b3601f285fd6 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -61,7 +61,8 @@ void amd_iommu_flush_all_caches(struct amd_iommu *iommu);
 void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
 void amd_iommu_domain_update(struct protection_domain *domain);
 void amd_iommu_domain_flush_complete(struct protection_domain *domain);
-void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain);
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
+				  u64 address, size_t size);
 int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
 int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 			      unsigned long cr3);
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index ca22546e4d1a5..2a0d1e97e52fd 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -369,6 +369,8 @@ static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 	bool updated = false;
 	u64 __pte, *pte;
 	int ret, i, count;
+	size_t size = pgcount << __ffs(pgsize);
+	unsigned long o_iova = iova;
 
 	BUG_ON(!IS_ALIGNED(iova, pgsize));
 	BUG_ON(!IS_ALIGNED(paddr, pgsize));
@@ -424,7 +426,7 @@ out:
 		 * Updates and flushing already happened in
 		 * increase_address_space().
 		 */
-		amd_iommu_domain_flush_tlb_pde(dom);
+		amd_iommu_domain_flush_pages(dom, o_iova, size);
 		spin_unlock_irqrestore(&dom->lock, flags);
 	}
 
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index cb8f51d5f83dd..77cf1e3de053b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1484,8 +1484,8 @@ static void __domain_flush_pages(struct protection_domain *domain,
 	WARN_ON(ret);
 }
 
-static void domain_flush_pages(struct protection_domain *domain,
-			       u64 address, size_t size)
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
+				  u64 address, size_t size)
 {
 	if (likely(!amd_iommu_np_cache)) {
 		__domain_flush_pages(domain, address, size);
@@ -1535,9 +1535,10 @@ static void domain_flush_pages(struct protection_domain *domain,
 }
 
 /* Flush the whole IO/TLB for a given protection domain - including PDE */
-void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain)
+static void amd_iommu_domain_flush_all(struct protection_domain *domain)
 {
-	domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
+	amd_iommu_domain_flush_pages(domain, 0,
+				     CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
 }
 
 void amd_iommu_domain_flush_complete(struct protection_domain *domain)
@@ -1564,7 +1565,7 @@ static void domain_flush_np_cache(struct protection_domain *domain,
 		unsigned long flags;
 
 		spin_lock_irqsave(&domain->lock, flags);
-		domain_flush_pages(domain, iova, size);
+		amd_iommu_domain_flush_pages(domain, iova, size);
 		spin_unlock_irqrestore(&domain->lock, flags);
 	}
 }
@@ -1843,7 +1844,7 @@ static void do_detach(struct iommu_dev_data *dev_data)
 	device_flush_dte(dev_data);
 
 	/* Flush IOTLB and wait for the flushes to finish */
-	amd_iommu_domain_flush_tlb_pde(domain);
+	amd_iommu_domain_flush_all(domain);
 
 	/* decrease reference counters - needs to happen after the flushes */
 	domain->dev_iommu[iommu->index] -= 1;
@@ -2020,7 +2021,7 @@ void amd_iommu_domain_update(struct protection_domain *domain)
 	amd_iommu_update_and_flush_device_table(domain);
 
 	/* Flush domain TLB(s) and wait for completion */
-	amd_iommu_domain_flush_tlb_pde(domain);
+	amd_iommu_domain_flush_all(domain);
 }
 
 /*****************************************************************************
@@ -2454,7 +2455,7 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain,
 
 	/* Flush IOTLB to mark IOPTE dirty on the next translation(s) */
 	if (domain_flush)
-		amd_iommu_domain_flush_tlb_pde(pdomain);
+		amd_iommu_domain_flush_all(pdomain);
 
 	pdomain->dirty_tracking = enable;
 	spin_unlock_irqrestore(&pdomain->lock, flags);
@@ -2558,7 +2559,7 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	amd_iommu_domain_flush_tlb_pde(dom);
+	amd_iommu_domain_flush_all(dom);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
@@ -2569,7 +2570,8 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1);
+	amd_iommu_domain_flush_pages(dom, gather->start,
+				     gather->end - gather->start + 1);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
-- 
GitLab


From c7fc12354be0ba47566d55f4ebdc6a47bd69d5ed Mon Sep 17 00:00:00 2001
From: Vasant Hegde <vasant.hegde@amd.com>
Date: Wed, 22 Nov 2023 09:02:15 +0000
Subject: [PATCH 1099/4076] iommu/amd/pgtbl_v2: Invalidate updated page ranges
 only

Enhance __domain_flush_pages() to detect domain page table mode and use
that info to build invalidation commands. So that we can use
amd_iommu_domain_flush_pages() to invalidate v2 page table.

Also pass PASID, gn variable to device_flush_iotlb() so that it can build
IOTLB invalidation command for both v1 and v2 page table.

Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231122090215.6191-10-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/io_pgtable_v2.c | 10 ++--------
 drivers/iommu/amd/iommu.c         | 28 ++++++++++++++++++++--------
 2 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c
index f818a7e254d42..6d69ba60744f0 100644
--- a/drivers/iommu/amd/io_pgtable_v2.c
+++ b/drivers/iommu/amd/io_pgtable_v2.c
@@ -244,7 +244,6 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 	unsigned long mapped_size = 0;
 	unsigned long o_iova = iova;
 	size_t size = pgcount << __ffs(pgsize);
-	int count = 0;
 	int ret = 0;
 	bool updated = false;
 
@@ -265,19 +264,14 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 
 		*pte = set_pte_attr(paddr, map_size, prot);
 
-		count++;
 		iova += map_size;
 		paddr += map_size;
 		mapped_size += map_size;
 	}
 
 out:
-	if (updated) {
-		if (count > 1)
-			amd_iommu_flush_tlb(&pdom->domain, 0);
-		else
-			amd_iommu_flush_page(&pdom->domain, 0, o_iova);
-	}
+	if (updated)
+		amd_iommu_domain_flush_pages(pdom, o_iova, size);
 
 	if (mapped)
 		*mapped += mapped_size;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 77cf1e3de053b..255ea754c0cdd 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -85,6 +85,11 @@ static void detach_device(struct device *dev);
  *
  ****************************************************************************/
 
+static inline bool pdom_is_v2_pgtbl_mode(struct protection_domain *pdom)
+{
+	return (pdom && (pdom->flags & PD_IOMMUV2_MASK));
+}
+
 static inline int get_acpihid_device_id(struct device *dev,
 					struct acpihid_map_entry **entry)
 {
@@ -1382,8 +1387,8 @@ void amd_iommu_flush_all_caches(struct amd_iommu *iommu)
 /*
  * Command send function for flushing on-device TLB
  */
-static int device_flush_iotlb(struct iommu_dev_data *dev_data,
-			      u64 address, size_t size)
+static int device_flush_iotlb(struct iommu_dev_data *dev_data, u64 address,
+			      size_t size, ioasid_t pasid, bool gn)
 {
 	struct amd_iommu *iommu;
 	struct iommu_cmd cmd;
@@ -1395,7 +1400,7 @@ static int device_flush_iotlb(struct iommu_dev_data *dev_data,
 		return -EINVAL;
 
 	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address,
-			      size, IOMMU_NO_PASID, false);
+			      size, pasid, gn);
 
 	return iommu_queue_command(iommu, &cmd);
 }
@@ -1441,8 +1446,11 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
 			return ret;
 	}
 
-	if (dev_data->ats_enabled)
-		ret = device_flush_iotlb(dev_data, 0, ~0UL);
+	if (dev_data->ats_enabled) {
+		/* Invalidate the entire contents of an IOTLB */
+		ret = device_flush_iotlb(dev_data, 0, ~0UL,
+					 IOMMU_NO_PASID, false);
+	}
 
 	return ret;
 }
@@ -1458,9 +1466,13 @@ static void __domain_flush_pages(struct protection_domain *domain,
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
 	int ret = 0, i;
+	ioasid_t pasid = IOMMU_NO_PASID;
+	bool gn = false;
+
+	if (pdom_is_v2_pgtbl_mode(domain))
+		gn = true;
 
-	build_inv_iommu_pages(&cmd, address, size, domain->id,
-			      IOMMU_NO_PASID, false);
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, gn);
 
 	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (!domain->dev_iommu[i])
@@ -1478,7 +1490,7 @@ static void __domain_flush_pages(struct protection_domain *domain,
 		if (!dev_data->ats_enabled)
 			continue;
 
-		ret |= device_flush_iotlb(dev_data, address, size);
+		ret |= device_flush_iotlb(dev_data, address, size, pasid, gn);
 	}
 
 	WARN_ON(ret);
-- 
GitLab


From b6b2264ba2090bb63665458e4b9369781df7dd4d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Sat, 9 Dec 2023 23:12:40 +0000
Subject: [PATCH 1100/4076] iommu/apple-dart: Fix spelling mistake "grups" ->
 "groups"

There is a spelling mistake in a dev_err message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://lore.kernel.org/r/20231209231240.4056082-1-colin.i.king@gmail.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/apple-dart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index 7438e9c82ba98..497a516747bd7 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -911,7 +911,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev)
 
 		ret = apple_dart_merge_master_cfg(group_master_cfg, cfg);
 		if (ret) {
-			dev_err(dev, "Failed to merge DART IOMMU grups.\n");
+			dev_err(dev, "Failed to merge DART IOMMU groups.\n");
 			iommu_group_put(group);
 			res = ERR_PTR(ret);
 			goto out;
-- 
GitLab


From 70f008fb3ea9bd2e6727eebc858405acd49a212b Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Fri, 24 Nov 2023 17:02:35 +0100
Subject: [PATCH 1101/4076] dmaengine: dmatest: prevent using swiotlb buffer
 with nobounce parameter

Source and destination data buffers are allocated with GPF_KERNEL flag.
It means that, if the DDR is more than 2GB, buffers can be allocated above
the 32-bit addressable space. In this case, and if the dma controller is
only 32-bit compatible, swiotlb bounce buffer, located in the 32-bit
addressable space, is used and introduces a memcpy.

To prevent this extra memcpy, due to swiotlb bounce buffer use because
source or destination data buffer is allocated above the 32-bit addressable
space, force source and destination data buffers allocation with GPF_DMA
instead, when nobounce parameter is true.

Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Link: https://lore.kernel.org/r/20231124160235.2459326-1-amelie.delaunay@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmatest.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index ffe621695e472..a4f6088378492 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -21,6 +21,10 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 
+static bool nobounce;
+module_param(nobounce, bool, 0644);
+MODULE_PARM_DESC(nobounce, "Prevent using swiotlb buffer (default: use swiotlb buffer)");
+
 static unsigned int test_buf_size = 16384;
 module_param(test_buf_size, uint, 0644);
 MODULE_PARM_DESC(test_buf_size, "Size of the memcpy test buffer");
@@ -90,6 +94,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
 
 /**
  * struct dmatest_params - test parameters.
+ * @nobounce:		prevent using swiotlb buffer
  * @buf_size:		size of the memcpy test buffer
  * @channel:		bus ID of the channel to test
  * @device:		bus ID of the DMA Engine to test
@@ -106,6 +111,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
  * @polled:		use polling for completion instead of interrupts
  */
 struct dmatest_params {
+	bool		nobounce;
 	unsigned int	buf_size;
 	char		channel[20];
 	char		device[32];
@@ -215,6 +221,7 @@ struct dmatest_done {
 struct dmatest_data {
 	u8		**raw;
 	u8		**aligned;
+	gfp_t		gfp_flags;
 	unsigned int	cnt;
 	unsigned int	off;
 };
@@ -533,7 +540,7 @@ static int dmatest_alloc_test_data(struct dmatest_data *d,
 		goto err;
 
 	for (i = 0; i < d->cnt; i++) {
-		d->raw[i] = kmalloc(buf_size + align, GFP_KERNEL);
+		d->raw[i] = kmalloc(buf_size + align, d->gfp_flags);
 		if (!d->raw[i])
 			goto err;
 
@@ -655,6 +662,13 @@ static int dmatest_func(void *data)
 		goto err_free_coefs;
 	}
 
+	src->gfp_flags = GFP_KERNEL;
+	dst->gfp_flags = GFP_KERNEL;
+	if (params->nobounce) {
+		src->gfp_flags = GFP_DMA;
+		dst->gfp_flags = GFP_DMA;
+	}
+
 	if (dmatest_alloc_test_data(src, buf_size, align) < 0)
 		goto err_free_coefs;
 
@@ -1093,6 +1107,7 @@ static void add_threaded_test(struct dmatest_info *info)
 	struct dmatest_params *params = &info->params;
 
 	/* Copy test parameters */
+	params->nobounce = nobounce;
 	params->buf_size = test_buf_size;
 	strscpy(params->channel, strim(test_channel), sizeof(params->channel));
 	strscpy(params->device, strim(test_device), sizeof(params->device));
-- 
GitLab


From 21aa971d3e295c2c81d0887f8a3e85a95dd687c5 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:31 +0100
Subject: [PATCH 1102/4076] iio: adc: adi-axi-adc: convert to regmap

Use MMIO regmap interface. It makes things easier for manipulating bits.

Reviewed-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-8-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/Kconfig       |  2 +-
 drivers/iio/adc/adi-axi-adc.c | 85 +++++++++++++++++++++--------------
 2 files changed, 53 insertions(+), 34 deletions(-)

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 1e2b7a2c67c6b..4eebd51614191 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -292,7 +292,7 @@ config ADI_AXI_ADC
 	select IIO_BUFFER
 	select IIO_BUFFER_HW_CONSUMER
 	select IIO_BUFFER_DMAENGINE
-	depends on HAS_IOMEM
+	select REGMAP_MMIO
 	depends on OF
 	help
 	  Say yes here to build support for Analog Devices Generic
diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c
index ae83ada7f9f2d..c247ff1541d28 100644
--- a/drivers/iio/adc/adi-axi-adc.c
+++ b/drivers/iio/adc/adi-axi-adc.c
@@ -14,6 +14,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 
 #include <linux/iio/iio.h>
@@ -62,7 +63,7 @@ struct adi_axi_adc_state {
 	struct mutex				lock;
 
 	struct adi_axi_adc_client		*client;
-	void __iomem				*regs;
+	struct regmap				*regmap;
 };
 
 struct adi_axi_adc_client {
@@ -90,19 +91,6 @@ void *adi_axi_adc_conv_priv(struct adi_axi_adc_conv *conv)
 }
 EXPORT_SYMBOL_NS_GPL(adi_axi_adc_conv_priv, IIO_ADI_AXI);
 
-static void adi_axi_adc_write(struct adi_axi_adc_state *st,
-			      unsigned int reg,
-			      unsigned int val)
-{
-	iowrite32(val, st->regs + reg);
-}
-
-static unsigned int adi_axi_adc_read(struct adi_axi_adc_state *st,
-				     unsigned int reg)
-{
-	return ioread32(st->regs + reg);
-}
-
 static int adi_axi_adc_config_dma_buffer(struct device *dev,
 					 struct iio_dev *indio_dev)
 {
@@ -163,17 +151,20 @@ static int adi_axi_adc_update_scan_mode(struct iio_dev *indio_dev,
 {
 	struct adi_axi_adc_state *st = iio_priv(indio_dev);
 	struct adi_axi_adc_conv *conv = &st->client->conv;
-	unsigned int i, ctrl;
+	unsigned int i;
+	int ret;
 
 	for (i = 0; i < conv->chip_info->num_channels; i++) {
-		ctrl = adi_axi_adc_read(st, ADI_AXI_REG_CHAN_CTRL(i));
-
 		if (test_bit(i, scan_mask))
-			ctrl |= ADI_AXI_REG_CHAN_CTRL_ENABLE;
+			ret = regmap_set_bits(st->regmap,
+					      ADI_AXI_REG_CHAN_CTRL(i),
+					      ADI_AXI_REG_CHAN_CTRL_ENABLE);
 		else
-			ctrl &= ~ADI_AXI_REG_CHAN_CTRL_ENABLE;
-
-		adi_axi_adc_write(st, ADI_AXI_REG_CHAN_CTRL(i), ctrl);
+			ret = regmap_clear_bits(st->regmap,
+						ADI_AXI_REG_CHAN_CTRL(i),
+						ADI_AXI_REG_CHAN_CTRL_ENABLE);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -310,21 +301,32 @@ static int adi_axi_adc_setup_channels(struct device *dev,
 	}
 
 	for (i = 0; i < conv->chip_info->num_channels; i++) {
-		adi_axi_adc_write(st, ADI_AXI_REG_CHAN_CTRL(i),
-				  ADI_AXI_REG_CHAN_CTRL_DEFAULTS);
+		ret = regmap_write(st->regmap, ADI_AXI_REG_CHAN_CTRL(i),
+				   ADI_AXI_REG_CHAN_CTRL_DEFAULTS);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
 }
 
-static void axi_adc_reset(struct adi_axi_adc_state *st)
+static int axi_adc_reset(struct adi_axi_adc_state *st)
 {
-	adi_axi_adc_write(st, ADI_AXI_REG_RSTN, 0);
+	int ret;
+
+	ret = regmap_write(st->regmap, ADI_AXI_REG_RSTN, 0);
+	if (ret)
+		return ret;
+
 	mdelay(10);
-	adi_axi_adc_write(st, ADI_AXI_REG_RSTN, ADI_AXI_REG_RSTN_MMCM_RSTN);
+	ret = regmap_write(st->regmap, ADI_AXI_REG_RSTN,
+			   ADI_AXI_REG_RSTN_MMCM_RSTN);
+	if (ret)
+		return ret;
+
 	mdelay(10);
-	adi_axi_adc_write(st, ADI_AXI_REG_RSTN,
-			  ADI_AXI_REG_RSTN_RSTN | ADI_AXI_REG_RSTN_MMCM_RSTN);
+	return regmap_write(st->regmap, ADI_AXI_REG_RSTN,
+			    ADI_AXI_REG_RSTN_RSTN | ADI_AXI_REG_RSTN_MMCM_RSTN);
 }
 
 static void adi_axi_adc_cleanup(void *data)
@@ -335,12 +337,20 @@ static void adi_axi_adc_cleanup(void *data)
 	module_put(cl->dev->driver->owner);
 }
 
+static const struct regmap_config axi_adc_regmap_config = {
+	.val_bits = 32,
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.max_register = 0x0800,
+};
+
 static int adi_axi_adc_probe(struct platform_device *pdev)
 {
 	struct adi_axi_adc_conv *conv;
 	struct iio_dev *indio_dev;
 	struct adi_axi_adc_client *cl;
 	struct adi_axi_adc_state *st;
+	void __iomem *base;
 	unsigned int ver;
 	int ret;
 
@@ -361,15 +371,24 @@ static int adi_axi_adc_probe(struct platform_device *pdev)
 	cl->state = st;
 	mutex_init(&st->lock);
 
-	st->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(st->regs))
-		return PTR_ERR(st->regs);
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	st->regmap = devm_regmap_init_mmio(&pdev->dev, base,
+					   &axi_adc_regmap_config);
+	if (IS_ERR(st->regmap))
+		return PTR_ERR(st->regmap);
 
 	conv = &st->client->conv;
 
-	axi_adc_reset(st);
+	ret = axi_adc_reset(st);
+	if (ret)
+		return ret;
 
-	ver = adi_axi_adc_read(st, ADI_AXI_REG_VERSION);
+	ret = regmap_read(st->regmap, ADI_AXI_REG_VERSION, &ver);
+	if (ret)
+		return ret;
 
 	if (cl->info->version > ver) {
 		dev_err(&pdev->dev,
-- 
GitLab


From a1d1ba5e1c28b9887be1bdb3630caf0b532ec980 Mon Sep 17 00:00:00 2001
From: Crt Mori <cmo@melexis.com>
Date: Wed, 6 Dec 2023 21:49:33 +0100
Subject: [PATCH 1103/4076] iio: temperature: mlx90635 MLX90635 IR Temperature
 sensor

MLX90635 is an Infra Red contactless temperature sensor most suitable
for consumer applications where measured object temperature is in range
between -20 to 100 degrees Celsius. It has improved accuracy for
measurements within temperature range of human body and can operate in
ambient temperature range between -20 to 85 degrees Celsius.

Driver provides simple power management possibility as it returns to
lowest possible power mode (Step sleep mode) in which temperature
measurements can still be performed, yet for continuous measuring it
switches to Continuous power mode where measurements constantly change
without triggering.

Signed-off-by: Crt Mori<cmo@melexis.com>
Link: https://lore.kernel.org/r/c6590e4fb8d993a5317b486a3e45e1bb6e9e3318.1701872051.git.cmo@melexis.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS                        |    7 +
 drivers/iio/temperature/Kconfig    |   12 +
 drivers/iio/temperature/Makefile   |    1 +
 drivers/iio/temperature/mlx90635.c | 1097 ++++++++++++++++++++++++++++
 4 files changed, 1117 insertions(+)
 create mode 100644 drivers/iio/temperature/mlx90635.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 1338e1176ea5f..b797cc51a1c21 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13725,6 +13725,13 @@ S:	Supported
 W:	http://www.melexis.com
 F:	drivers/iio/temperature/mlx90632.c
 
+MELEXIS MLX90635 DRIVER
+M:	Crt Mori <cmo@melexis.com>
+L:	linux-iio@vger.kernel.org
+S:	Supported
+W:	http://www.melexis.com
+F:	drivers/iio/temperature/mlx90635.c
+
 MELFAS MIP4 TOUCHSCREEN DRIVER
 M:	Sangwon Jee <jeesw@melfas.com>
 S:	Supported
diff --git a/drivers/iio/temperature/Kconfig b/drivers/iio/temperature/Kconfig
index ea2ce364b2e91..ed0e4963362f9 100644
--- a/drivers/iio/temperature/Kconfig
+++ b/drivers/iio/temperature/Kconfig
@@ -76,6 +76,18 @@ config MLX90632
 	  This driver can also be built as a module. If so, the module will
 	  be called mlx90632.
 
+config MLX90635
+	tristate "MLX90635 contact-less infrared sensor with medical accuracy"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the Melexis
+	  MLX90635 contact-less infrared sensor with medical accuracy
+	  connected with I2C.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called mlx90635.
+
 config TMP006
 	tristate "TMP006 infrared thermopile sensor"
 	depends on I2C
diff --git a/drivers/iio/temperature/Makefile b/drivers/iio/temperature/Makefile
index 9330d4a39598d..07d6e65709f7f 100644
--- a/drivers/iio/temperature/Makefile
+++ b/drivers/iio/temperature/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_MAX31865) += max31865.o
 obj-$(CONFIG_MCP9600) += mcp9600.o
 obj-$(CONFIG_MLX90614) += mlx90614.o
 obj-$(CONFIG_MLX90632) += mlx90632.o
+obj-$(CONFIG_MLX90632) += mlx90635.o
 obj-$(CONFIG_TMP006) += tmp006.o
 obj-$(CONFIG_TMP007) += tmp007.o
 obj-$(CONFIG_TMP117) += tmp117.o
diff --git a/drivers/iio/temperature/mlx90635.c b/drivers/iio/temperature/mlx90635.c
new file mode 100644
index 0000000000000..1f5c962c1818f
--- /dev/null
+++ b/drivers/iio/temperature/mlx90635.c
@@ -0,0 +1,1097 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * mlx90635.c - Melexis MLX90635 contactless IR temperature sensor
+ *
+ * Copyright (c) 2023 Melexis <cmo@melexis.com>
+ *
+ * Driver for the Melexis MLX90635 I2C 16-bit IR thermopile sensor
+ */
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/iopoll.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/math64.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+
+#include <linux/iio/iio.h>
+
+/* Memory sections addresses */
+#define MLX90635_ADDR_RAM	0x0000 /* Start address of ram */
+#define MLX90635_ADDR_EEPROM	0x0018 /* Start address of user eeprom */
+
+/* EEPROM addresses - used at startup */
+#define MLX90635_EE_I2C_CFG	0x0018 /* I2C address register initial value */
+#define MLX90635_EE_CTRL1	0x001A /* Control register1 initial value */
+#define MLX90635_EE_CTRL2	0x001C /* Control register2 initial value */
+
+#define MLX90635_EE_Ha		0x001E /* Ha customer calib value reg 16bit */
+#define MLX90635_EE_Hb		0x0020 /* Hb customer calib value reg 16bit */
+#define MLX90635_EE_Fa		0x0026 /* Fa calibration register 32bit */
+#define MLX90635_EE_FASCALE	0x002A /* Scaling coefficient for Fa register 16bit */
+#define MLX90635_EE_Ga		0x002C /* Ga calibration register 16bit */
+#define MLX90635_EE_Fb		0x002E /* Fb calibration register 16bit */
+#define MLX90635_EE_Ea		0x0030 /* Ea calibration register 32bit */
+#define MLX90635_EE_Eb		0x0034 /* Eb calibration register 32bit */
+#define MLX90635_EE_P_G		0x0038 /* P_G calibration register 16bit */
+#define MLX90635_EE_P_O		0x003A /* P_O calibration register 16bit */
+#define MLX90635_EE_Aa		0x003C /* Aa calibration register 16bit */
+#define MLX90635_EE_VERSION	0x003E /* Version bits 4:7 and 12:15 */
+#define MLX90635_EE_Gb		0x0040 /* Gb calibration register 16bit */
+
+/* Device status register - volatile */
+#define MLX90635_REG_STATUS	0x0000
+#define   MLX90635_STAT_BUSY BIT(6) /* Device busy indicator */
+#define   MLX90635_STAT_BRST BIT(5) /* Brown out reset indicator */
+#define   MLX90635_STAT_CYCLE_POS GENMASK(4, 2) /* Data position */
+#define   MLX90635_STAT_END_CONV BIT(1) /* End of conversion indicator */
+#define   MLX90635_STAT_DATA_RDY BIT(0) /* Data ready indicator */
+
+/* EEPROM control register address - volatile */
+#define MLX90635_REG_EE		0x000C
+#define   MLX90635_EE_ACTIVE BIT(4) /* Power-on EEPROM */
+#define   MLX90635_EE_BUSY_MASK	BIT(15)
+
+#define MLX90635_REG_CMD	0x0010 /* Command register address */
+
+/* Control register1 address - volatile */
+#define MLX90635_REG_CTRL1	0x0014
+#define   MLX90635_CTRL1_REFRESH_RATE_MASK GENMASK(2, 0)
+#define   MLX90635_CTRL1_RES_CTRL_MASK GENMASK(4, 3)
+#define   MLX90635_CTRL1_TABLE_MASK BIT(15) /* Table select */
+
+/* Control register2 address - volatile */
+#define   MLX90635_REG_CTRL2	0x0016
+#define   MLX90635_CTRL2_BURST_CNT_MASK GENMASK(10, 6) /* Burst count */
+#define   MLX90635_CTRL2_MODE_MASK GENMASK(12, 11) /* Power mode */
+#define   MLX90635_CTRL2_SOB_MASK BIT(15)
+
+/* PowerModes statuses */
+#define MLX90635_PWR_STATUS_HALT 0
+#define MLX90635_PWR_STATUS_SLEEP_STEP 1
+#define MLX90635_PWR_STATUS_STEP 2
+#define MLX90635_PWR_STATUS_CONTINUOUS 3
+
+/* Measurement data addresses */
+#define MLX90635_RESULT_1   0x0002
+#define MLX90635_RESULT_2   0x0004
+#define MLX90635_RESULT_3   0x0006
+#define MLX90635_RESULT_4   0x0008
+#define MLX90635_RESULT_5   0x000A
+
+/* Timings (ms) */
+#define MLX90635_TIMING_RST_MIN 200 /* Minimum time after addressed reset command */
+#define MLX90635_TIMING_RST_MAX 250 /* Maximum time after addressed reset command */
+#define MLX90635_TIMING_POLLING 10000 /* Time between bit polling*/
+#define MLX90635_TIMING_EE_ACTIVE_MIN 100 /* Minimum time after activating the EEPROM for read */
+#define MLX90635_TIMING_EE_ACTIVE_MAX 150 /* Maximum time after activating the EEPROM for read */
+
+/* Magic constants */
+#define MLX90635_ID_DSPv1 0x01 /* EEPROM DSP version */
+#define MLX90635_RESET_CMD  0x0006 /* Reset sensor (address or global) */
+#define MLX90635_MAX_MEAS_NUM   31 /* Maximum number of measurements in list */
+#define MLX90635_PTAT_DIV 12   /* Used to divide the PTAT value in pre-processing */
+#define MLX90635_IR_DIV 24   /* Used to divide the IR value in pre-processing */
+#define MLX90635_SLEEP_DELAY_MS 6000 /* Autosleep delay */
+#define MLX90635_MEAS_MAX_TIME 2000 /* Max measurement time in ms for the lowest refresh rate */
+#define MLX90635_READ_RETRIES 100 /* Number of read retries before quitting with timeout error */
+#define MLX90635_VERSION_MASK (GENMASK(15, 12) | GENMASK(7, 4))
+#define MLX90635_DSP_VERSION(reg) (((reg & GENMASK(14, 12)) >> 9) | ((reg & GENMASK(6, 4)) >> 4))
+#define MLX90635_DSP_FIXED BIT(15)
+
+
+/**
+ * struct mlx90635_data - private data for the MLX90635 device
+ * @client: I2C client of the device
+ * @lock: Internal mutex because multiple reads are needed for single triggered
+ *	  measurement to ensure data consistency
+ * @regmap: Regmap of the device registers
+ * @regmap_ee: Regmap of the device EEPROM which can be cached
+ * @emissivity: Object emissivity from 0 to 1000 where 1000 = 1
+ * @regulator: Regulator of the device
+ * @powerstatus: Current POWER status of the device
+ * @interaction_ts: Timestamp of the last temperature read that is used
+ *		    for power management in jiffies
+ */
+struct mlx90635_data {
+	struct i2c_client *client;
+	struct mutex lock;
+	struct regmap *regmap;
+	struct regmap *regmap_ee;
+	u16 emissivity;
+	struct regulator *regulator;
+	int powerstatus;
+	unsigned long interaction_ts;
+};
+
+static const struct regmap_range mlx90635_volatile_reg_range[] = {
+	regmap_reg_range(MLX90635_REG_STATUS, MLX90635_REG_STATUS),
+	regmap_reg_range(MLX90635_RESULT_1, MLX90635_RESULT_5),
+	regmap_reg_range(MLX90635_REG_EE, MLX90635_REG_EE),
+	regmap_reg_range(MLX90635_REG_CMD, MLX90635_REG_CMD),
+	regmap_reg_range(MLX90635_REG_CTRL1, MLX90635_REG_CTRL2),
+};
+
+static const struct regmap_access_table mlx90635_volatile_regs_tbl = {
+	.yes_ranges = mlx90635_volatile_reg_range,
+	.n_yes_ranges = ARRAY_SIZE(mlx90635_volatile_reg_range),
+};
+
+static const struct regmap_range mlx90635_read_reg_range[] = {
+	regmap_reg_range(MLX90635_REG_STATUS, MLX90635_REG_STATUS),
+	regmap_reg_range(MLX90635_RESULT_1, MLX90635_RESULT_5),
+	regmap_reg_range(MLX90635_REG_EE, MLX90635_REG_EE),
+	regmap_reg_range(MLX90635_REG_CMD, MLX90635_REG_CMD),
+	regmap_reg_range(MLX90635_REG_CTRL1, MLX90635_REG_CTRL2),
+};
+
+static const struct regmap_access_table mlx90635_readable_regs_tbl = {
+	.yes_ranges = mlx90635_read_reg_range,
+	.n_yes_ranges = ARRAY_SIZE(mlx90635_read_reg_range),
+};
+
+static const struct regmap_range mlx90635_no_write_reg_range[] = {
+	regmap_reg_range(MLX90635_RESULT_1, MLX90635_RESULT_5),
+};
+
+static const struct regmap_access_table mlx90635_writeable_regs_tbl = {
+	.no_ranges = mlx90635_no_write_reg_range,
+	.n_no_ranges = ARRAY_SIZE(mlx90635_no_write_reg_range),
+};
+
+static const struct regmap_config mlx90635_regmap = {
+	.name = "mlx90635-registers",
+	.reg_stride = 1,
+	.reg_bits = 16,
+	.val_bits = 16,
+
+	.volatile_table = &mlx90635_volatile_regs_tbl,
+	.rd_table = &mlx90635_readable_regs_tbl,
+	.wr_table = &mlx90635_writeable_regs_tbl,
+
+	.use_single_read = true,
+	.use_single_write = true,
+	.can_multi_write = false,
+	.reg_format_endian = REGMAP_ENDIAN_BIG,
+	.val_format_endian = REGMAP_ENDIAN_BIG,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static const struct regmap_range mlx90635_read_ee_range[] = {
+	regmap_reg_range(MLX90635_EE_I2C_CFG, MLX90635_EE_CTRL2),
+	regmap_reg_range(MLX90635_EE_Ha, MLX90635_EE_Gb),
+};
+
+static const struct regmap_access_table mlx90635_readable_ees_tbl = {
+	.yes_ranges = mlx90635_read_ee_range,
+	.n_yes_ranges = ARRAY_SIZE(mlx90635_read_ee_range),
+};
+
+static const struct regmap_range mlx90635_no_write_ee_range[] = {
+	regmap_reg_range(MLX90635_ADDR_EEPROM, MLX90635_EE_Gb),
+};
+
+static const struct regmap_access_table mlx90635_writeable_ees_tbl = {
+	.no_ranges = mlx90635_no_write_ee_range,
+	.n_no_ranges = ARRAY_SIZE(mlx90635_no_write_ee_range),
+};
+
+static const struct regmap_config mlx90635_regmap_ee = {
+	.name = "mlx90635-eeprom",
+	.reg_stride = 1,
+	.reg_bits = 16,
+	.val_bits = 16,
+
+	.volatile_table = NULL,
+	.rd_table = &mlx90635_readable_ees_tbl,
+	.wr_table = &mlx90635_writeable_ees_tbl,
+
+	.use_single_read = true,
+	.use_single_write = true,
+	.can_multi_write = false,
+	.reg_format_endian = REGMAP_ENDIAN_BIG,
+	.val_format_endian = REGMAP_ENDIAN_BIG,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+/**
+ * mlx90635_reset_delay() - Give the mlx90635 some time to reset properly
+ * If this is not done, the following I2C command(s) will not be accepted.
+ */
+static void mlx90635_reset_delay(void)
+{
+	usleep_range(MLX90635_TIMING_RST_MIN, MLX90635_TIMING_RST_MAX);
+}
+
+static int mlx90635_pwr_sleep_step(struct mlx90635_data *data)
+{
+	int ret;
+
+	if (data->powerstatus == MLX90635_PWR_STATUS_SLEEP_STEP)
+		return 0;
+
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_CTRL2, MLX90635_CTRL2_MODE_MASK,
+				FIELD_PREP(MLX90635_CTRL2_MODE_MASK, MLX90635_PWR_STATUS_SLEEP_STEP));
+	if (ret < 0)
+		return ret;
+
+	data->powerstatus = MLX90635_PWR_STATUS_SLEEP_STEP;
+	return 0;
+}
+
+static int mlx90635_pwr_continuous(struct mlx90635_data *data)
+{
+	int ret;
+
+	if (data->powerstatus == MLX90635_PWR_STATUS_CONTINUOUS)
+		return 0;
+
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_CTRL2, MLX90635_CTRL2_MODE_MASK,
+				FIELD_PREP(MLX90635_CTRL2_MODE_MASK, MLX90635_PWR_STATUS_CONTINUOUS));
+	if (ret < 0)
+		return ret;
+
+	data->powerstatus = MLX90635_PWR_STATUS_CONTINUOUS;
+	return 0;
+}
+
+static int mlx90635_read_ee_register(struct regmap *regmap, u16 reg_lsb,
+				     s32 *reg_value)
+{
+	unsigned int read;
+	u32 value;
+	int ret;
+
+	ret = regmap_read(regmap, reg_lsb + 2, &read);
+	if (ret < 0)
+		return ret;
+
+	value = read;
+
+	ret = regmap_read(regmap, reg_lsb, &read);
+	if (ret < 0)
+		return ret;
+
+	*reg_value = (read << 16) | (value & 0xffff);
+
+	return 0;
+}
+
+static int mlx90635_read_ee_ambient(struct regmap *regmap, s16 *PG, s16 *PO, s16 *Gb)
+{
+	unsigned int read_tmp;
+	int ret;
+
+	ret = regmap_read(regmap, MLX90635_EE_P_O, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*PO = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_P_G, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*PG = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Gb, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Gb = (u16)read_tmp;
+
+	return 0;
+}
+
+static int mlx90635_read_ee_object(struct regmap *regmap, u32 *Ea, u32 *Eb, u32 *Fa, s16 *Fb,
+				   s16 *Ga, s16 *Gb, s16 *Ha, s16 *Hb, u16 *Fa_scale)
+{
+	unsigned int read_tmp;
+	int ret;
+
+	ret = mlx90635_read_ee_register(regmap, MLX90635_EE_Ea, Ea);
+	if (ret < 0)
+		return ret;
+
+	ret = mlx90635_read_ee_register(regmap, MLX90635_EE_Eb, Eb);
+	if (ret < 0)
+		return ret;
+
+	ret = mlx90635_read_ee_register(regmap, MLX90635_EE_Fa, Fa);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read(regmap, MLX90635_EE_Ha, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Ha = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Hb, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Hb = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Ga, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Ga = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Gb, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Gb = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_Fb, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Fb = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_EE_FASCALE, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*Fa_scale = (u16)read_tmp;
+
+	return 0;
+}
+
+static int mlx90635_calculate_dataset_ready_time(struct mlx90635_data *data, int *refresh_time)
+{
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(data->regmap, MLX90635_REG_CTRL1, &reg);
+	if (ret < 0)
+		return ret;
+
+	*refresh_time = 2 * (MLX90635_MEAS_MAX_TIME >> FIELD_GET(MLX90635_CTRL1_REFRESH_RATE_MASK, reg)) + 80;
+
+	return 0;
+}
+
+static int mlx90635_perform_measurement_burst(struct mlx90635_data *data)
+{
+	unsigned int reg_status;
+	int refresh_time;
+	int ret;
+
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_STATUS,
+				MLX90635_STAT_END_CONV, MLX90635_STAT_END_CONV);
+	if (ret < 0)
+		return ret;
+
+	ret = mlx90635_calculate_dataset_ready_time(data, &refresh_time);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_CTRL2,
+				FIELD_PREP(MLX90635_CTRL2_SOB_MASK, 1),
+				FIELD_PREP(MLX90635_CTRL2_SOB_MASK, 1));
+	if (ret < 0)
+		return ret;
+
+	msleep(refresh_time); /* Wait minimum time for dataset to be ready */
+
+	ret = regmap_read_poll_timeout(data->regmap, MLX90635_REG_STATUS, reg_status,
+				       (!(reg_status & MLX90635_STAT_END_CONV)) == 0,
+				       MLX90635_TIMING_POLLING, MLX90635_READ_RETRIES * 10000);
+	if (ret < 0) {
+		dev_err(&data->client->dev, "data not ready");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int mlx90635_read_ambient_raw(struct regmap *regmap,
+				     s16 *ambient_new_raw, s16 *ambient_old_raw)
+{
+	unsigned int read_tmp;
+	int ret;
+
+	ret = regmap_read(regmap, MLX90635_RESULT_2, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*ambient_new_raw = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_RESULT_3, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*ambient_old_raw = (s16)read_tmp;
+
+	return 0;
+}
+
+static int mlx90635_read_object_raw(struct regmap *regmap, s16 *object_raw)
+{
+	unsigned int read_tmp;
+	s16 read;
+	int ret;
+
+	ret = regmap_read(regmap, MLX90635_RESULT_1, &read_tmp);
+	if (ret < 0)
+		return ret;
+
+	read = (s16)read_tmp;
+
+	ret = regmap_read(regmap, MLX90635_RESULT_4, &read_tmp);
+	if (ret < 0)
+		return ret;
+	*object_raw = (read - (s16)read_tmp) / 2;
+
+	return 0;
+}
+
+static int mlx90635_read_all_channel(struct mlx90635_data *data,
+				     s16 *ambient_new_raw, s16 *ambient_old_raw,
+				     s16 *object_raw)
+{
+	int ret;
+
+	mutex_lock(&data->lock);
+	if (data->powerstatus == MLX90635_PWR_STATUS_SLEEP_STEP) {
+		/* Trigger measurement in Sleep Step mode */
+		ret = mlx90635_perform_measurement_burst(data);
+		if (ret < 0)
+			goto read_unlock;
+	}
+
+	ret = mlx90635_read_ambient_raw(data->regmap, ambient_new_raw,
+					ambient_old_raw);
+	if (ret < 0)
+		goto read_unlock;
+
+	ret = mlx90635_read_object_raw(data->regmap, object_raw);
+read_unlock:
+	mutex_unlock(&data->lock);
+	return ret;
+}
+
+static s64 mlx90635_preprocess_temp_amb(s16 ambient_new_raw,
+					s16 ambient_old_raw, s16 Gb)
+{
+	s64 VR_Ta, kGb, tmp;
+
+	kGb = ((s64)Gb * 1000LL) >> 10ULL;
+	VR_Ta = (s64)ambient_old_raw * 1000000LL +
+		kGb * div64_s64(((s64)ambient_new_raw * 1000LL),
+			(MLX90635_PTAT_DIV));
+	tmp = div64_s64(
+			 div64_s64(((s64)ambient_new_raw * 1000000000000LL),
+				   (MLX90635_PTAT_DIV)), VR_Ta);
+	return div64_s64(tmp << 19ULL, 1000LL);
+}
+
+static s64 mlx90635_preprocess_temp_obj(s16 object_raw,
+					s16 ambient_new_raw,
+					s16 ambient_old_raw, s16 Gb)
+{
+	s64 VR_IR, kGb, tmp;
+
+	kGb = ((s64)Gb * 1000LL) >> 10ULL;
+	VR_IR = (s64)ambient_old_raw * 1000000LL +
+		kGb * (div64_s64((s64)ambient_new_raw * 1000LL,
+			MLX90635_PTAT_DIV));
+	tmp = div64_s64(
+			div64_s64((s64)(object_raw * 1000000LL),
+				   MLX90635_IR_DIV) * 1000000LL,
+			VR_IR);
+	return div64_s64((tmp << 19ULL), 1000LL);
+}
+
+static s32 mlx90635_calc_temp_ambient(s16 ambient_new_raw, s16 ambient_old_raw,
+				      u16 P_G, u16 P_O, s16 Gb)
+{
+	s64 kPG, kPO, AMB;
+
+	AMB = mlx90635_preprocess_temp_amb(ambient_new_raw, ambient_old_raw,
+					   Gb);
+	kPG = ((s64)P_G * 1000000LL) >> 9ULL;
+	kPO = AMB - (((s64)P_O * 1000LL) >> 1ULL);
+
+	return 30 * 1000LL + div64_s64(kPO * 1000000LL, kPG);
+}
+
+static s32 mlx90635_calc_temp_object_iteration(s32 prev_object_temp, s64 object,
+					       s64 TAdut, s64 TAdut4, s16 Ga,
+					       u32 Fa, u16 Fa_scale, s16 Fb,
+					       s16 Ha, s16 Hb, u16 emissivity)
+{
+	s64 calcedGa, calcedGb, calcedFa, Alpha_corr;
+	s64 Ha_customer, Hb_customer;
+
+	Ha_customer = ((s64)Ha * 1000000LL) >> 14ULL;
+	Hb_customer = ((s64)Hb * 100) >> 10ULL;
+
+	calcedGa = ((s64)((s64)Ga * (prev_object_temp - 35 * 1000LL)
+			     * 1000LL)) >> 24LL;
+	calcedGb = ((s64)(Fb * (TAdut - 30 * 1000000LL))) >> 24LL;
+
+	Alpha_corr = ((s64)((s64)Fa * Ha_customer * 10000LL) >> Fa_scale);
+	Alpha_corr *= ((s64)(1 * 1000000LL + calcedGa + calcedGb));
+
+	Alpha_corr = div64_s64(Alpha_corr, 1000LL);
+	Alpha_corr *= emissivity;
+	Alpha_corr = div64_s64(Alpha_corr, 100LL);
+	calcedFa = div64_s64((s64)object * 100000000000LL, Alpha_corr);
+
+	return (int_sqrt64(int_sqrt64(calcedFa * 100000000LL + TAdut4))
+		- 27315 - Hb_customer) * 10;
+}
+
+static s64 mlx90635_calc_ta4(s64 TAdut, s64 scale)
+{
+	return (div64_s64(TAdut, scale) + 27315) *
+		(div64_s64(TAdut, scale) + 27315) *
+		(div64_s64(TAdut, scale) + 27315) *
+		(div64_s64(TAdut, scale) + 27315);
+}
+
+static s32 mlx90635_calc_temp_object(s64 object, s64 ambient, u32 Ea, u32 Eb,
+				     s16 Ga, u32 Fa, u16 Fa_scale, s16 Fb, s16 Ha, s16 Hb,
+				     u16 tmp_emi)
+{
+	s64 kTA, kTA0, TAdut, TAdut4;
+	s64 temp = 35000;
+	s8 i;
+
+	kTA = (Ea * 1000LL) >> 16LL;
+	kTA0 = (Eb * 1000LL) >> 8LL;
+	TAdut = div64_s64(((ambient - kTA0) * 1000000LL), kTA) + 30 * 1000000LL;
+	TAdut4 = mlx90635_calc_ta4(TAdut, 10000LL);
+
+	/* Iterations of calculation as described in datasheet */
+	for (i = 0; i < 5; ++i) {
+		temp = mlx90635_calc_temp_object_iteration(temp, object, TAdut, TAdut4,
+							   Ga, Fa, Fa_scale, Fb, Ha, Hb,
+							   tmp_emi);
+	}
+	return temp;
+}
+
+static int mlx90635_calc_object(struct mlx90635_data *data, int *val)
+{
+	s16 ambient_new_raw, ambient_old_raw, object_raw;
+	s16 Fb, Ga, Gb, Ha, Hb;
+	s64 object, ambient;
+	u32 Ea, Eb, Fa;
+	u16 Fa_scale;
+	int ret;
+
+	ret = mlx90635_read_ee_object(data->regmap_ee, &Ea, &Eb, &Fa, &Fb, &Ga, &Gb, &Ha, &Hb, &Fa_scale);
+	if (ret < 0)
+		return ret;
+
+	ret = mlx90635_read_all_channel(data,
+					&ambient_new_raw, &ambient_old_raw,
+					&object_raw);
+	if (ret < 0)
+		return ret;
+
+	ambient = mlx90635_preprocess_temp_amb(ambient_new_raw,
+					       ambient_old_raw, Gb);
+	object = mlx90635_preprocess_temp_obj(object_raw,
+					      ambient_new_raw,
+					      ambient_old_raw, Gb);
+
+	*val = mlx90635_calc_temp_object(object, ambient, Ea, Eb, Ga, Fa, Fa_scale, Fb,
+					 Ha, Hb, data->emissivity);
+	return 0;
+}
+
+static int mlx90635_calc_ambient(struct mlx90635_data *data, int *val)
+{
+	s16 ambient_new_raw, ambient_old_raw;
+	s16 PG, PO, Gb;
+	int ret;
+
+	ret = mlx90635_read_ee_ambient(data->regmap_ee, &PG, &PO, &Gb);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&data->lock);
+	if (data->powerstatus == MLX90635_PWR_STATUS_SLEEP_STEP) {
+		ret = mlx90635_perform_measurement_burst(data);
+		if (ret < 0)
+			goto read_ambient_unlock;
+	}
+
+	ret = mlx90635_read_ambient_raw(data->regmap, &ambient_new_raw,
+					&ambient_old_raw);
+read_ambient_unlock:
+	mutex_unlock(&data->lock);
+	if (ret < 0)
+		return ret;
+
+	*val = mlx90635_calc_temp_ambient(ambient_new_raw, ambient_old_raw,
+					  PG, PO, Gb);
+	return ret;
+}
+
+static int mlx90635_get_refresh_rate(struct mlx90635_data *data,
+				     unsigned int *refresh_rate)
+{
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(data->regmap, MLX90635_REG_CTRL1, &reg);
+	if (ret < 0)
+		return ret;
+
+	*refresh_rate = FIELD_GET(MLX90635_CTRL1_REFRESH_RATE_MASK, reg);
+
+	return 0;
+}
+
+static const struct {
+	int val;
+	int val2;
+} mlx90635_freqs[] = {
+	{ 0, 200000 },
+	{ 0, 500000 },
+	{ 0, 900000 },
+	{ 1, 700000 },
+	{ 3, 0 },
+	{ 4, 800000 },
+	{ 6, 900000 },
+	{ 8, 900000 }
+};
+
+/**
+ * mlx90635_pm_interaction_wakeup() - Measure time between user interactions to change powermode
+ * @data: pointer to mlx90635_data object containing interaction_ts information
+ *
+ * Switch to continuous mode when interaction is faster than MLX90635_MEAS_MAX_TIME. Update the
+ * interaction_ts for each function call with the jiffies to enable measurement between function
+ * calls. Initial value of the interaction_ts needs to be set before this function call.
+ */
+static int mlx90635_pm_interaction_wakeup(struct mlx90635_data *data)
+{
+	unsigned long now;
+	int ret;
+
+	now = jiffies;
+	if (time_in_range(now, data->interaction_ts,
+			  data->interaction_ts +
+			  msecs_to_jiffies(MLX90635_MEAS_MAX_TIME + 100))) {
+		ret = mlx90635_pwr_continuous(data);
+		if (ret < 0)
+			return ret;
+	}
+
+	data->interaction_ts = now;
+
+	return 0;
+}
+
+static int mlx90635_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *channel, int *val,
+			     int *val2, long mask)
+{
+	struct mlx90635_data *data = iio_priv(indio_dev);
+	int ret;
+	int cr;
+
+	pm_runtime_get_sync(&data->client->dev);
+	ret = mlx90635_pm_interaction_wakeup(data);
+	if (ret < 0)
+		goto mlx90635_read_raw_pm;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_PROCESSED:
+		switch (channel->channel2) {
+		case IIO_MOD_TEMP_AMBIENT:
+			ret = mlx90635_calc_ambient(data, val);
+			if (ret < 0)
+				goto mlx90635_read_raw_pm;
+
+			ret = IIO_VAL_INT;
+			break;
+		case IIO_MOD_TEMP_OBJECT:
+			ret = mlx90635_calc_object(data, val);
+			if (ret < 0)
+				goto mlx90635_read_raw_pm;
+
+			ret = IIO_VAL_INT;
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+		}
+		break;
+	case IIO_CHAN_INFO_CALIBEMISSIVITY:
+		if (data->emissivity == 1000) {
+			*val = 1;
+			*val2 = 0;
+		} else {
+			*val = 0;
+			*val2 = data->emissivity * 1000;
+		}
+		ret = IIO_VAL_INT_PLUS_MICRO;
+		break;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		ret = mlx90635_get_refresh_rate(data, &cr);
+		if (ret < 0)
+			goto mlx90635_read_raw_pm;
+
+		*val = mlx90635_freqs[cr].val;
+		*val2 = mlx90635_freqs[cr].val2;
+		ret = IIO_VAL_INT_PLUS_MICRO;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+mlx90635_read_raw_pm:
+	pm_runtime_mark_last_busy(&data->client->dev);
+	pm_runtime_put_autosuspend(&data->client->dev);
+	return ret;
+}
+
+static int mlx90635_write_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *channel, int val,
+			      int val2, long mask)
+{
+	struct mlx90635_data *data = iio_priv(indio_dev);
+	int ret;
+	int i;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_CALIBEMISSIVITY:
+		/* Confirm we are within 0 and 1.0 */
+		if (val < 0 || val2 < 0 || val > 1 ||
+		    (val == 1 && val2 != 0))
+			return -EINVAL;
+		data->emissivity = val * 1000 + val2 / 1000;
+		return 0;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		for (i = 0; i < ARRAY_SIZE(mlx90635_freqs); i++) {
+			if (val == mlx90635_freqs[i].val &&
+			    val2 == mlx90635_freqs[i].val2)
+				break;
+		}
+		if (i == ARRAY_SIZE(mlx90635_freqs))
+			return -EINVAL;
+
+		ret = regmap_write_bits(data->regmap, MLX90635_REG_CTRL1,
+					MLX90635_CTRL1_REFRESH_RATE_MASK, i);
+
+		return ret;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mlx90635_read_avail(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       const int **vals, int *type, int *length,
+			       long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		*vals = (int *)mlx90635_freqs;
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		*length = 2 * ARRAY_SIZE(mlx90635_freqs);
+		return IIO_AVAIL_LIST;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_chan_spec mlx90635_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.modified = 1,
+		.channel2 = IIO_MOD_TEMP_AMBIENT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+	},
+	{
+		.type = IIO_TEMP,
+		.modified = 1,
+		.channel2 = IIO_MOD_TEMP_OBJECT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED) |
+			BIT(IIO_CHAN_INFO_CALIBEMISSIVITY),
+		.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_SAMP_FREQ),
+	},
+};
+
+static const struct iio_info mlx90635_info = {
+	.read_raw = mlx90635_read_raw,
+	.write_raw = mlx90635_write_raw,
+	.read_avail = mlx90635_read_avail,
+};
+
+static void mlx90635_sleep(void *_data)
+{
+	struct mlx90635_data *data = _data;
+
+	mlx90635_pwr_sleep_step(data);
+}
+
+static int mlx90635_suspend(struct mlx90635_data *data)
+{
+	return mlx90635_pwr_sleep_step(data);
+}
+
+static int mlx90635_wakeup(struct mlx90635_data *data)
+{
+	s16 Fb, Ga, Gb, Ha, Hb, PG, PO;
+	unsigned int dsp_version;
+	u32 Ea, Eb, Fa;
+	u16 Fa_scale;
+	int ret;
+
+	regcache_cache_bypass(data->regmap_ee, false);
+	regcache_cache_only(data->regmap_ee, false);
+	regcache_cache_only(data->regmap, false);
+
+	ret = mlx90635_pwr_continuous(data);
+	if (ret < 0) {
+		dev_err(&data->client->dev, "Switch to continuous mode failed\n");
+		return ret;
+	}
+	ret = regmap_write_bits(data->regmap, MLX90635_REG_EE,
+				MLX90635_EE_ACTIVE, MLX90635_EE_ACTIVE);
+	if (ret < 0) {
+		dev_err(&data->client->dev, "Powering EEPROM failed\n");
+		return ret;
+	}
+	usleep_range(MLX90635_TIMING_EE_ACTIVE_MIN, MLX90635_TIMING_EE_ACTIVE_MAX);
+
+	regcache_mark_dirty(data->regmap_ee);
+
+	ret = regcache_sync(data->regmap_ee);
+	if (ret < 0) {
+		dev_err(&data->client->dev,
+			"Failed to sync cache: %d\n", ret);
+		return ret;
+	}
+
+	ret = mlx90635_read_ee_ambient(data->regmap_ee, &PG, &PO, &Gb);
+	if (ret < 0) {
+		dev_err(&data->client->dev,
+			"Failed to read to cache Ambient coefficients EEPROM region: %d\n", ret);
+		return ret;
+	}
+
+	ret = mlx90635_read_ee_object(data->regmap_ee, &Ea, &Eb, &Fa, &Fb, &Ga, &Gb, &Ha, &Hb, &Fa_scale);
+	if (ret < 0) {
+		dev_err(&data->client->dev,
+			"Failed to read to cache Object coefficients EEPROM region: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_read(data->regmap_ee, MLX90635_EE_VERSION, &dsp_version);
+	if (ret < 0) {
+		dev_err(&data->client->dev,
+			"Failed to read to cache of EEPROM version: %d\n", ret);
+		return ret;
+	}
+
+	regcache_cache_only(data->regmap_ee, true);
+
+	return ret;
+}
+
+static void mlx90635_disable_regulator(void *_data)
+{
+	struct mlx90635_data *data = _data;
+	int ret;
+
+	ret = regulator_disable(data->regulator);
+	if (ret < 0)
+		dev_err(regmap_get_device(data->regmap),
+			"Failed to disable power regulator: %d\n", ret);
+}
+
+static int mlx90635_enable_regulator(struct mlx90635_data *data)
+{
+	int ret;
+
+	ret = regulator_enable(data->regulator);
+	if (ret < 0) {
+		dev_err(regmap_get_device(data->regmap), "Failed to enable power regulator!\n");
+		return ret;
+	}
+
+	mlx90635_reset_delay();
+
+	return ret;
+}
+
+static int mlx90635_probe(struct i2c_client *client)
+{
+	struct mlx90635_data *mlx90635;
+	struct iio_dev *indio_dev;
+	unsigned int dsp_version;
+	struct regmap *regmap;
+	struct regmap *regmap_ee;
+	int ret;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*mlx90635));
+	if (!indio_dev)
+		return dev_err_probe(&client->dev, -ENOMEM, "failed to allocate device\n");
+
+	regmap = devm_regmap_init_i2c(client, &mlx90635_regmap);
+	if (IS_ERR(regmap))
+		return dev_err_probe(&client->dev, PTR_ERR(regmap),
+				     "failed to allocate regmap\n");
+
+	regmap_ee = devm_regmap_init_i2c(client, &mlx90635_regmap_ee);
+	if (IS_ERR(regmap))
+		return dev_err_probe(&client->dev, PTR_ERR(regmap),
+				     "failed to allocate regmap\n");
+
+	mlx90635 = iio_priv(indio_dev);
+	i2c_set_clientdata(client, indio_dev);
+	mlx90635->client = client;
+	mlx90635->regmap = regmap;
+	mlx90635->regmap_ee = regmap_ee;
+	mlx90635->powerstatus = MLX90635_PWR_STATUS_SLEEP_STEP;
+
+	mutex_init(&mlx90635->lock);
+	indio_dev->name = "mlx90635";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->info = &mlx90635_info;
+	indio_dev->channels = mlx90635_channels;
+	indio_dev->num_channels = ARRAY_SIZE(mlx90635_channels);
+
+	mlx90635->regulator = devm_regulator_get(&client->dev, "vdd");
+	if (IS_ERR(mlx90635->regulator))
+		return dev_err_probe(&client->dev, PTR_ERR(mlx90635->regulator),
+				     "failed to get vdd regulator");
+
+	ret = mlx90635_enable_regulator(mlx90635);
+	if (ret < 0)
+		return ret;
+
+	ret = devm_add_action_or_reset(&client->dev, mlx90635_disable_regulator,
+				       mlx90635);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret,
+				     "failed to setup regulator cleanup action\n");
+
+	ret = mlx90635_wakeup(mlx90635);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret, "wakeup failed\n");
+
+	ret = devm_add_action_or_reset(&client->dev, mlx90635_sleep, mlx90635);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret,
+				     "failed to setup low power cleanup\n");
+
+	ret = regmap_read(mlx90635->regmap_ee, MLX90635_EE_VERSION, &dsp_version);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret, "read of version failed\n");
+
+	dsp_version = dsp_version & MLX90635_VERSION_MASK;
+
+	if (FIELD_GET(MLX90635_DSP_FIXED, dsp_version)) {
+		if (MLX90635_DSP_VERSION(dsp_version) == MLX90635_ID_DSPv1) {
+			dev_dbg(&client->dev,
+				"Detected DSP v1 calibration %x\n", dsp_version);
+		} else {
+			dev_dbg(&client->dev,
+				"Detected Unknown EEPROM calibration %lx\n",
+				MLX90635_DSP_VERSION(dsp_version));
+		}
+	} else {
+		return dev_err_probe(&client->dev, -EPROTONOSUPPORT,
+			"Wrong fixed top bit %x (expected 0x8X0X)\n",
+			dsp_version);
+	}
+
+	mlx90635->emissivity = 1000;
+	mlx90635->interaction_ts = jiffies; /* Set initial value */
+
+	pm_runtime_get_noresume(&client->dev);
+	pm_runtime_set_active(&client->dev);
+
+	ret = devm_pm_runtime_enable(&client->dev);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				     "failed to enable powermanagement\n");
+
+	pm_runtime_set_autosuspend_delay(&client->dev, MLX90635_SLEEP_DELAY_MS);
+	pm_runtime_use_autosuspend(&client->dev);
+	pm_runtime_put_autosuspend(&client->dev);
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct i2c_device_id mlx90635_id[] = {
+	{ "mlx90635" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, mlx90635_id);
+
+static const struct of_device_id mlx90635_of_match[] = {
+	{ .compatible = "melexis,mlx90635" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mlx90635_of_match);
+
+static int mlx90635_pm_suspend(struct device *dev)
+{
+	struct mlx90635_data *data = iio_priv(dev_get_drvdata(dev));
+	int ret;
+
+	ret = mlx90635_suspend(data);
+	if (ret < 0)
+		return ret;
+
+	ret = regulator_disable(data->regulator);
+	if (ret < 0)
+		dev_err(regmap_get_device(data->regmap),
+			"Failed to disable power regulator: %d\n", ret);
+
+	return ret;
+}
+
+static int mlx90635_pm_resume(struct device *dev)
+{
+	struct mlx90635_data *data = iio_priv(dev_get_drvdata(dev));
+	int ret;
+
+	ret = mlx90635_enable_regulator(data);
+	if (ret < 0)
+		return ret;
+
+	return mlx90635_wakeup(data);
+}
+
+static int mlx90635_pm_runtime_suspend(struct device *dev)
+{
+	struct mlx90635_data *data = iio_priv(dev_get_drvdata(dev));
+
+	return mlx90635_pwr_sleep_step(data);
+}
+
+static const struct dev_pm_ops mlx90635_pm_ops = {
+	SYSTEM_SLEEP_PM_OPS(mlx90635_pm_suspend, mlx90635_pm_resume)
+	RUNTIME_PM_OPS(mlx90635_pm_runtime_suspend, NULL, NULL)
+};
+
+static struct i2c_driver mlx90635_driver = {
+	.driver = {
+		.name	= "mlx90635",
+		.of_match_table = mlx90635_of_match,
+		.pm	= pm_ptr(&mlx90635_pm_ops),
+	},
+	.probe = mlx90635_probe,
+	.id_table = mlx90635_id,
+};
+module_i2c_driver(mlx90635_driver);
+
+MODULE_AUTHOR("Crt Mori <cmo@melexis.com>");
+MODULE_DESCRIPTION("Melexis MLX90635 contactless Infra Red temperature sensor driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 464cb187585fc46decf5058d0a92e46d59582cdc Mon Sep 17 00:00:00 2001
From: Crt Mori <cmo@melexis.com>
Date: Wed, 6 Dec 2023 21:49:42 +0100
Subject: [PATCH 1104/4076] dt-bindings: iio: temperature: add MLX90635 device

Add device tree bindings for MLX90635 Infra Red contactless temperature
sensor.

Signed-off-by: Crt Mori <cmo@melexis.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/0313c3b9f7490c32891627feb5ef35d5e5d9aae9.1701872051.git.cmo@melexis.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../iio/temperature/melexis,mlx90632.yaml     | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/temperature/melexis,mlx90632.yaml b/Documentation/devicetree/bindings/iio/temperature/melexis,mlx90632.yaml
index 4a55e7f25ae7c..03bb5d4fa8b57 100644
--- a/Documentation/devicetree/bindings/iio/temperature/melexis,mlx90632.yaml
+++ b/Documentation/devicetree/bindings/iio/temperature/melexis,mlx90632.yaml
@@ -4,7 +4,7 @@
 $id: http://devicetree.org/schemas/iio/temperature/melexis,mlx90632.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Melexis MLX90632 contactless Infra Red temperature sensor
+title: Melexis MLX90632 and MLX90635 contactless Infra Red temperature sensor
 
 maintainers:
   - Crt Mori <cmo@melexis.com>
@@ -27,9 +27,24 @@ description: |
   Since measured object emissivity effects Infra Red energy emitted,
   emissivity should be set before requesting the object temperature.
 
+  https://www.melexis.com/en/documents/documentation/datasheets/datasheet-mlx90635
+
+  MLX90635 is most suitable for consumer applications where
+  measured object temperature is in range between -20 to 100 degrees
+  Celsius with relative error of measurement 2 degree Celsius in
+  object temperature range for industrial applications, while just 0.2
+  degree Celsius for human body measurement applications. Since it can
+  operate and measure ambient temperature in range of -20 to 85 degrees
+  Celsius it is suitable also for outdoor use.
+
+  Since measured object emissivity effects Infra Red energy emitted,
+  emissivity should be set before requesting the object temperature.
+
 properties:
   compatible:
-    const: melexis,mlx90632
+    enum:
+      - melexis,mlx90632
+      - melexis,mlx90635
 
   reg:
     maxItems: 1
-- 
GitLab


From 608531bd8615766fda6f423c746d89ac9db5c0d0 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Thu, 7 Dec 2023 14:41:50 +0100
Subject: [PATCH 1105/4076] doc: iio: Document intensity scale as poorly
 defined

Add comment about intensity scale being poorly defined and
having no proper units.

Signed-off-by: Marek Vasut <marex@denx.de>
Link: https://lore.kernel.org/r/20231207134200.329174-1-marex@denx.de
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-iio | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 0d3ec5fc45f2f..94b8d8461b7c7 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -618,7 +618,9 @@ KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
 		If a discrete set of scale values is available, they
-		are listed in this attribute.
+		are listed in this attribute. Unlike illumination,
+		multiplying intensity by intensity_scale does not
+		yield value with any standardized unit.
 
 What:		/sys/bus/iio/devices/iio:deviceX/out_voltageY_hardwaregain
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_hardwaregain
-- 
GitLab


From 5fc0a980cca0b0d98558abbc7691b5f24d573b1a Mon Sep 17 00:00:00 2001
From: Petre Rodan <petre.rodan@subdimension.ro>
Date: Thu, 7 Dec 2023 18:46:28 +0200
Subject: [PATCH 1106/4076] dt-bindings: iio: pressure: add honeywell,hsc030

Adds binding for digital Honeywell TruStability HSC and SSC series
pressure and temperature sensors.
Communication is one way. The sensor only requires 4 bytes worth of
clock pulses on both i2c and spi in order to push the data out.
The i2c address is hardcoded and depends on the part number.
There is no additional GPIO control.
driver is based on iio/togreg

Datasheet:
https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf [HSC]
Datasheet:
https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-ssc-series/documents/sps-siot-trustability-ssc-series-standard-accuracy-board-mount-pressure-sensors-50099533-a-en-ciid-151134.pdf [SSC]

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Petre Rodan <petre.rodan@subdimension.ro>
Link: https://lore.kernel.org/r/20231207164634.11998-1-petre.rodan@subdimension.ro
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../iio/pressure/honeywell,hsc030pa.yaml      | 142 ++++++++++++++++++
 1 file changed, 142 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml

diff --git a/Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml b/Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml
new file mode 100644
index 0000000000000..65a24ed67b3cc
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml
@@ -0,0 +1,142 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/pressure/honeywell,hsc030pa.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Honeywell TruStability HSC and SSC pressure sensor series
+
+description: |
+  support for Honeywell TruStability HSC and SSC digital pressure sensor
+  series.
+
+  These sensors have either an I2C, an SPI or an analog interface. Only the
+  digital versions are supported by this driver.
+
+  There are 118 models with different pressure ranges available in each family.
+  The vendor calls them "HSC series" and "SSC series". All of them have an
+  identical programming model but differ in pressure range, unit and transfer
+  function.
+
+  To support different models one needs to specify the pressure range as well
+  as the transfer function. Pressure range can either be provided via
+  pressure-triplet (directly extracted from the part number) or in case it's
+  a custom chip via numerical range limits converted to pascals.
+
+  The transfer function defines the ranges of raw conversion values delivered
+  by the sensor. pmin-pascal and pmax-pascal corespond to the minimum and
+  maximum pressure that can be measured.
+
+  Please note that in case of an SPI-based sensor, the clock signal should not
+  exceed 800kHz and the MOSI signal is not required.
+
+  Specifications about the devices can be found at:
+  https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf
+  https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-ssc-series/documents/sps-siot-trustability-ssc-series-standard-accuracy-board-mount-pressure-sensors-50099533-a-en-ciid-151134.pdf
+
+maintainers:
+  - Petre Rodan <petre.rodan@subdimension.ro>
+
+properties:
+  compatible:
+    const: honeywell,hsc030pa
+
+  reg:
+    maxItems: 1
+
+  honeywell,transfer-function:
+    description: |
+      Transfer function which defines the range of valid values delivered by
+      the sensor.
+      0 - A, 10% to 90% of 2^14
+      1 - B, 5% to 95% of 2^14
+      2 - C, 5% to 85% of 2^14
+      3 - F, 4% to 94% of 2^14
+    enum: [0, 1, 2, 3]
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  honeywell,pressure-triplet:
+    description: |
+      Case-sensitive five character string that defines pressure range, unit
+      and type as part of the device nomenclature. In the unlikely case of a
+      custom chip, set to "NA" and provide pmin-pascal and pmax-pascal.
+    enum: [001BA, 1.6BA, 2.5BA, 004BA, 006BA, 010BA, 1.6MD, 2.5MD, 004MD,
+           006MD, 010MD, 016MD, 025MD, 040MD, 060MD, 100MD, 160MD, 250MD,
+           400MD, 600MD, 001BD, 1.6BD, 2.5BD, 004BD, 2.5MG, 004MG, 006MG,
+           010MG, 016MG, 025MG, 040MG, 060MG, 100MG, 160MG, 250MG, 400MG,
+           600MG, 001BG, 1.6BG, 2.5BG, 004BG, 006BG, 010BG, 100KA, 160KA,
+           250KA, 400KA, 600KA, 001GA, 160LD, 250LD, 400LD, 600LD, 001KD,
+           1.6KD, 2.5KD, 004KD, 006KD, 010KD, 016KD, 025KD, 040KD, 060KD,
+           100KD, 160KD, 250KD, 400KD, 250LG, 400LG, 600LG, 001KG, 1.6KG,
+           2.5KG, 004KG, 006KG, 010KG, 016KG, 025KG, 040KG, 060KG, 100KG,
+           160KG, 250KG, 400KG, 600KG, 001GG, 015PA, 030PA, 060PA, 100PA,
+           150PA, 0.5ND, 001ND, 002ND, 004ND, 005ND, 010ND, 020ND, 030ND,
+           001PD, 005PD, 015PD, 030PD, 060PD, 001NG, 002NG, 004NG, 005NG,
+           010NG, 020NG, 030NG, 001PG, 005PG, 015PG, 030PG, 060PG, 100PG,
+           150PG, NA]
+    $ref: /schemas/types.yaml#/definitions/string
+
+  honeywell,pmin-pascal:
+    description: |
+      Minimum pressure value the sensor can measure in pascal.
+      To be specified only if honeywell,pressure-triplet is set to "NA".
+
+  honeywell,pmax-pascal:
+    description: |
+      Maximum pressure value the sensor can measure in pascal.
+      To be specified only if honeywell,pressure-triplet is set to "NA".
+
+  vdd-supply:
+    description:
+      Provide VDD power to the sensor (either 3.3V or 5V depending on the chip)
+
+  spi-max-frequency:
+    maximum: 800000
+
+required:
+  - compatible
+  - reg
+  - honeywell,transfer-function
+  - honeywell,pressure-triplet
+
+additionalProperties: false
+
+dependentSchemas:
+  honeywell,pmin-pascal:
+    properties:
+      honeywell,pressure-triplet:
+        const: NA
+  honeywell,pmax-pascal:
+    properties:
+      honeywell,pressure-triplet:
+        const: NA
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pressure@28 {
+            compatible = "honeywell,hsc030pa";
+            reg = <0x28>;
+            honeywell,transfer-function = <0>;
+            honeywell,pressure-triplet = "030PA";
+        };
+    };
+  - |
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pressure@0 {
+            compatible = "honeywell,hsc030pa";
+            reg = <0>;
+            spi-max-frequency = <800000>;
+            honeywell,transfer-function = <0>;
+            honeywell,pressure-triplet = "NA";
+            honeywell,pmin-pascal = <0>;
+            honeywell,pmax-pascal = <200000>;
+        };
+    };
+...
-- 
GitLab


From 6362d96585e35b433981b3833a9e2737cec33774 Mon Sep 17 00:00:00 2001
From: Petre Rodan <petre.rodan@subdimension.ro>
Date: Thu, 7 Dec 2023 18:46:29 +0200
Subject: [PATCH 1107/4076] iio: pressure: driver for Honeywell HSC/SSC series

Adds driver for digital Honeywell TruStability HSC and SSC series
pressure and temperature sensors.
Communication is one way. The sensor only requires 4 bytes worth of
clock pulses on both i2c and spi in order to push the data out.
The i2c address is hardcoded and depends on the part number.
There is no additional GPIO control.
code is now based on iio/togreg

Datasheet:
https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf [HSC]
Datasheet:
https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-ssc-series/documents/sps-siot-trustability-ssc-series-standard-accuracy-board-mount-pressure-sensors-50099533-a-en-ciid-151134.pdf [SSC]

Signed-off-by: Petre Rodan <petre.rodan@subdimension.ro>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231207164634.11998-2-petre.rodan@subdimension.ro
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS                         |   7 +
 drivers/iio/pressure/Kconfig        |  22 ++
 drivers/iio/pressure/Makefile       |   3 +
 drivers/iio/pressure/hsc030pa.c     | 494 ++++++++++++++++++++++++++++
 drivers/iio/pressure/hsc030pa.h     |  74 +++++
 drivers/iio/pressure/hsc030pa_i2c.c |  69 ++++
 drivers/iio/pressure/hsc030pa_spi.c |  61 ++++
 7 files changed, 730 insertions(+)
 create mode 100644 drivers/iio/pressure/hsc030pa.c
 create mode 100644 drivers/iio/pressure/hsc030pa.h
 create mode 100644 drivers/iio/pressure/hsc030pa_i2c.c
 create mode 100644 drivers/iio/pressure/hsc030pa_spi.c

diff --git a/MAINTAINERS b/MAINTAINERS
index b797cc51a1c21..cf1ce6e6c1e11 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9709,6 +9709,13 @@ F:	lib/test_hmm*
 F:	mm/hmm*
 F:	tools/testing/selftests/mm/*hmm*
 
+HONEYWELL HSC030PA PRESSURE SENSOR SERIES IIO DRIVER
+M:	Petre Rodan <petre.rodan@subdimension.ro>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/pressure/honeywell,hsc030pa.yaml
+F:	drivers/iio/pressure/hsc030pa*
+
 HONEYWELL MPRLS0025PA PRESSURE SENSOR SERIES IIO DRIVER
 M:	Andreas Klinger <ak@it-klinger.de>
 L:	linux-iio@vger.kernel.org
diff --git a/drivers/iio/pressure/Kconfig b/drivers/iio/pressure/Kconfig
index 95efa32e4289b..79adfd059c3a7 100644
--- a/drivers/iio/pressure/Kconfig
+++ b/drivers/iio/pressure/Kconfig
@@ -109,6 +109,28 @@ config HP03
 	  To compile this driver as a module, choose M here: the module
 	  will be called hp03.
 
+config HSC030PA
+	tristate "Honeywell HSC/SSC TruStability pressure sensor series"
+	depends on (I2C || SPI_MASTER)
+	select HSC030PA_I2C if I2C
+	select HSC030PA_SPI if SPI_MASTER
+	help
+	  Say Y here to build support for the Honeywell TruStability
+	  HSC and SSC pressure and temperature sensor series.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called hsc030pa.
+
+config HSC030PA_I2C
+	tristate
+	depends on HSC030PA
+	depends on I2C
+
+config HSC030PA_SPI
+	tristate
+	depends on HSC030PA
+	depends on SPI_MASTER
+
 config ICP10100
 	tristate "InvenSense ICP-101xx pressure and temperature sensor"
 	depends on I2C
diff --git a/drivers/iio/pressure/Makefile b/drivers/iio/pressure/Makefile
index 436aec7e65f3a..b0f8b94662f20 100644
--- a/drivers/iio/pressure/Makefile
+++ b/drivers/iio/pressure/Makefile
@@ -15,6 +15,9 @@ obj-$(CONFIG_DPS310) += dps310.o
 obj-$(CONFIG_IIO_CROS_EC_BARO) += cros_ec_baro.o
 obj-$(CONFIG_HID_SENSOR_PRESS)   += hid-sensor-press.o
 obj-$(CONFIG_HP03) += hp03.o
+obj-$(CONFIG_HSC030PA) += hsc030pa.o
+obj-$(CONFIG_HSC030PA_I2C) += hsc030pa_i2c.o
+obj-$(CONFIG_HSC030PA_SPI) += hsc030pa_spi.o
 obj-$(CONFIG_ICP10100) += icp10100.o
 obj-$(CONFIG_MPL115) += mpl115.o
 obj-$(CONFIG_MPL115_I2C) += mpl115_i2c.o
diff --git a/drivers/iio/pressure/hsc030pa.c b/drivers/iio/pressure/hsc030pa.c
new file mode 100644
index 0000000000000..d6a51f0c335fa
--- /dev/null
+++ b/drivers/iio/pressure/hsc030pa.c
@@ -0,0 +1,494 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Honeywell TruStability HSC Series pressure/temperature sensor
+ *
+ * Copyright (c) 2023 Petre Rodan <petre.rodan@subdimension.ro>
+ *
+ * Datasheet: https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf
+ */
+
+#include <linux/array_size.h>
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/init.h>
+#include <linux/math64.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/property.h>
+#include <linux/regulator/consumer.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/units.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+
+#include <asm/unaligned.h>
+
+#include "hsc030pa.h"
+
+/*
+ * HSC_PRESSURE_TRIPLET_LEN - length for the string that defines the
+ * pressure range, measurement unit and type as per the part nomenclature.
+ * Consult honeywell,pressure-triplet in the bindings file for details.
+ */
+#define HSC_PRESSURE_TRIPLET_LEN 6
+#define HSC_STATUS_MASK          GENMASK(7, 6)
+#define HSC_TEMPERATURE_MASK     GENMASK(15, 5)
+#define HSC_PRESSURE_MASK        GENMASK(29, 16)
+
+struct hsc_func_spec {
+	u32 output_min;
+	u32 output_max;
+};
+
+/*
+ * function A: 10% - 90% of 2^14
+ * function B:  5% - 95% of 2^14
+ * function C:  5% - 85% of 2^14
+ * function F:  4% - 94% of 2^14
+ */
+static const struct hsc_func_spec hsc_func_spec[] = {
+	[HSC_FUNCTION_A] = { .output_min = 1638, .output_max = 14746 },
+	[HSC_FUNCTION_B] = { .output_min =  819, .output_max = 15565 },
+	[HSC_FUNCTION_C] = { .output_min =  819, .output_max = 13926 },
+	[HSC_FUNCTION_F] = { .output_min =  655, .output_max = 15401 },
+};
+
+enum hsc_variants {
+	HSC001BA = 0x00, HSC1_6BA = 0x01, HSC2_5BA = 0x02, HSC004BA = 0x03,
+	HSC006BA = 0x04, HSC010BA = 0x05, HSC1_6MD = 0x06, HSC2_5MD = 0x07,
+	HSC004MD = 0x08, HSC006MD = 0x09, HSC010MD = 0x0a, HSC016MD = 0x0b,
+	HSC025MD = 0x0c, HSC040MD = 0x0d, HSC060MD = 0x0e, HSC100MD = 0x0f,
+	HSC160MD = 0x10, HSC250MD = 0x11, HSC400MD = 0x12, HSC600MD = 0x13,
+	HSC001BD = 0x14, HSC1_6BD = 0x15, HSC2_5BD = 0x16, HSC004BD = 0x17,
+	HSC2_5MG = 0x18, HSC004MG = 0x19, HSC006MG = 0x1a, HSC010MG = 0x1b,
+	HSC016MG = 0x1c, HSC025MG = 0x1d, HSC040MG = 0x1e, HSC060MG = 0x1f,
+	HSC100MG = 0x20, HSC160MG = 0x21, HSC250MG = 0x22, HSC400MG = 0x23,
+	HSC600MG = 0x24, HSC001BG = 0x25, HSC1_6BG = 0x26, HSC2_5BG = 0x27,
+	HSC004BG = 0x28, HSC006BG = 0x29, HSC010BG = 0x2a, HSC100KA = 0x2b,
+	HSC160KA = 0x2c, HSC250KA = 0x2d, HSC400KA = 0x2e, HSC600KA = 0x2f,
+	HSC001GA = 0x30, HSC160LD = 0x31, HSC250LD = 0x32, HSC400LD = 0x33,
+	HSC600LD = 0x34, HSC001KD = 0x35, HSC1_6KD = 0x36, HSC2_5KD = 0x37,
+	HSC004KD = 0x38, HSC006KD = 0x39, HSC010KD = 0x3a, HSC016KD = 0x3b,
+	HSC025KD = 0x3c, HSC040KD = 0x3d, HSC060KD = 0x3e, HSC100KD = 0x3f,
+	HSC160KD = 0x40, HSC250KD = 0x41, HSC400KD = 0x42, HSC250LG = 0x43,
+	HSC400LG = 0x44, HSC600LG = 0x45, HSC001KG = 0x46, HSC1_6KG = 0x47,
+	HSC2_5KG = 0x48, HSC004KG = 0x49, HSC006KG = 0x4a, HSC010KG = 0x4b,
+	HSC016KG = 0x4c, HSC025KG = 0x4d, HSC040KG = 0x4e, HSC060KG = 0x4f,
+	HSC100KG = 0x50, HSC160KG = 0x51, HSC250KG = 0x52, HSC400KG = 0x53,
+	HSC600KG = 0x54, HSC001GG = 0x55, HSC015PA = 0x56, HSC030PA = 0x57,
+	HSC060PA = 0x58, HSC100PA = 0x59, HSC150PA = 0x5a, HSC0_5ND = 0x5b,
+	HSC001ND = 0x5c, HSC002ND = 0x5d, HSC004ND = 0x5e, HSC005ND = 0x5f,
+	HSC010ND = 0x60, HSC020ND = 0x61, HSC030ND = 0x62, HSC001PD = 0x63,
+	HSC005PD = 0x64, HSC015PD = 0x65, HSC030PD = 0x66, HSC060PD = 0x67,
+	HSC001NG = 0x68, HSC002NG = 0x69, HSC004NG = 0x6a, HSC005NG = 0x6b,
+	HSC010NG = 0x6c, HSC020NG = 0x6d, HSC030NG = 0x6e, HSC001PG = 0x6f,
+	HSC005PG = 0x70, HSC015PG = 0x71, HSC030PG = 0x72, HSC060PG = 0x73,
+	HSC100PG = 0x74, HSC150PG = 0x75, HSC_VARIANTS_MAX
+};
+
+static const char * const hsc_triplet_variants[HSC_VARIANTS_MAX] = {
+	[HSC001BA] = "001BA", [HSC1_6BA] = "1.6BA", [HSC2_5BA] = "2.5BA",
+	[HSC004BA] = "004BA", [HSC006BA] = "006BA", [HSC010BA] = "010BA",
+	[HSC1_6MD] = "1.6MD", [HSC2_5MD] = "2.5MD", [HSC004MD] = "004MD",
+	[HSC006MD] = "006MD", [HSC010MD] = "010MD", [HSC016MD] = "016MD",
+	[HSC025MD] = "025MD", [HSC040MD] = "040MD", [HSC060MD] = "060MD",
+	[HSC100MD] = "100MD", [HSC160MD] = "160MD", [HSC250MD] = "250MD",
+	[HSC400MD] = "400MD", [HSC600MD] = "600MD", [HSC001BD] = "001BD",
+	[HSC1_6BD] = "1.6BD", [HSC2_5BD] = "2.5BD", [HSC004BD] = "004BD",
+	[HSC2_5MG] = "2.5MG", [HSC004MG] = "004MG", [HSC006MG] = "006MG",
+	[HSC010MG] = "010MG", [HSC016MG] = "016MG", [HSC025MG] = "025MG",
+	[HSC040MG] = "040MG", [HSC060MG] = "060MG", [HSC100MG] = "100MG",
+	[HSC160MG] = "160MG", [HSC250MG] = "250MG", [HSC400MG] = "400MG",
+	[HSC600MG] = "600MG", [HSC001BG] = "001BG", [HSC1_6BG] = "1.6BG",
+	[HSC2_5BG] = "2.5BG", [HSC004BG] = "004BG", [HSC006BG] = "006BG",
+	[HSC010BG] = "010BG", [HSC100KA] = "100KA", [HSC160KA] = "160KA",
+	[HSC250KA] = "250KA", [HSC400KA] = "400KA", [HSC600KA] = "600KA",
+	[HSC001GA] = "001GA", [HSC160LD] = "160LD", [HSC250LD] = "250LD",
+	[HSC400LD] = "400LD", [HSC600LD] = "600LD", [HSC001KD] = "001KD",
+	[HSC1_6KD] = "1.6KD", [HSC2_5KD] = "2.5KD", [HSC004KD] = "004KD",
+	[HSC006KD] = "006KD", [HSC010KD] = "010KD", [HSC016KD] = "016KD",
+	[HSC025KD] = "025KD", [HSC040KD] = "040KD", [HSC060KD] = "060KD",
+	[HSC100KD] = "100KD", [HSC160KD] = "160KD", [HSC250KD] = "250KD",
+	[HSC400KD] = "400KD", [HSC250LG] = "250LG", [HSC400LG] = "400LG",
+	[HSC600LG] = "600LG", [HSC001KG] = "001KG", [HSC1_6KG] = "1.6KG",
+	[HSC2_5KG] = "2.5KG", [HSC004KG] = "004KG", [HSC006KG] = "006KG",
+	[HSC010KG] = "010KG", [HSC016KG] = "016KG", [HSC025KG] = "025KG",
+	[HSC040KG] = "040KG", [HSC060KG] = "060KG", [HSC100KG] = "100KG",
+	[HSC160KG] = "160KG", [HSC250KG] = "250KG", [HSC400KG] = "400KG",
+	[HSC600KG] = "600KG", [HSC001GG] = "001GG", [HSC015PA] = "015PA",
+	[HSC030PA] = "030PA", [HSC060PA] = "060PA", [HSC100PA] = "100PA",
+	[HSC150PA] = "150PA", [HSC0_5ND] = "0.5ND", [HSC001ND] = "001ND",
+	[HSC002ND] = "002ND", [HSC004ND] = "004ND", [HSC005ND] = "005ND",
+	[HSC010ND] = "010ND", [HSC020ND] = "020ND", [HSC030ND] = "030ND",
+	[HSC001PD] = "001PD", [HSC005PD] = "005PD", [HSC015PD] = "015PD",
+	[HSC030PD] = "030PD", [HSC060PD] = "060PD", [HSC001NG] = "001NG",
+	[HSC002NG] = "002NG", [HSC004NG] = "004NG", [HSC005NG] = "005NG",
+	[HSC010NG] = "010NG", [HSC020NG] = "020NG", [HSC030NG] = "030NG",
+	[HSC001PG] = "001PG", [HSC005PG] = "005PG", [HSC015PG] = "015PG",
+	[HSC030PG] = "030PG", [HSC060PG] = "060PG", [HSC100PG] = "100PG",
+	[HSC150PG] = "150PG",
+};
+
+/**
+ * struct hsc_range_config - list of pressure ranges based on nomenclature
+ * @pmin: lowest pressure that can be measured
+ * @pmax: highest pressure that can be measured
+ */
+struct hsc_range_config {
+	const s32 pmin;
+	const s32 pmax;
+};
+
+/* All min max limits have been converted to pascals */
+static const struct hsc_range_config hsc_range_config[HSC_VARIANTS_MAX] = {
+	[HSC001BA] = { .pmin =       0, .pmax =  100000 },
+	[HSC1_6BA] = { .pmin =       0, .pmax =  160000 },
+	[HSC2_5BA] = { .pmin =       0, .pmax =  250000 },
+	[HSC004BA] = { .pmin =       0, .pmax =  400000 },
+	[HSC006BA] = { .pmin =       0, .pmax =  600000 },
+	[HSC010BA] = { .pmin =       0, .pmax = 1000000 },
+	[HSC1_6MD] = { .pmin =    -160, .pmax =     160 },
+	[HSC2_5MD] = { .pmin =    -250, .pmax =     250 },
+	[HSC004MD] = { .pmin =    -400, .pmax =     400 },
+	[HSC006MD] = { .pmin =    -600, .pmax =     600 },
+	[HSC010MD] = { .pmin =   -1000, .pmax =    1000 },
+	[HSC016MD] = { .pmin =   -1600, .pmax =    1600 },
+	[HSC025MD] = { .pmin =   -2500, .pmax =    2500 },
+	[HSC040MD] = { .pmin =   -4000, .pmax =    4000 },
+	[HSC060MD] = { .pmin =   -6000, .pmax =    6000 },
+	[HSC100MD] = { .pmin =  -10000, .pmax =   10000 },
+	[HSC160MD] = { .pmin =  -16000, .pmax =   16000 },
+	[HSC250MD] = { .pmin =  -25000, .pmax =   25000 },
+	[HSC400MD] = { .pmin =  -40000, .pmax =   40000 },
+	[HSC600MD] = { .pmin =  -60000, .pmax =   60000 },
+	[HSC001BD] = { .pmin = -100000, .pmax =  100000 },
+	[HSC1_6BD] = { .pmin = -160000, .pmax =  160000 },
+	[HSC2_5BD] = { .pmin = -250000, .pmax =  250000 },
+	[HSC004BD] = { .pmin = -400000, .pmax =  400000 },
+	[HSC2_5MG] = { .pmin =       0, .pmax =     250 },
+	[HSC004MG] = { .pmin =       0, .pmax =     400 },
+	[HSC006MG] = { .pmin =       0, .pmax =     600 },
+	[HSC010MG] = { .pmin =       0, .pmax =    1000 },
+	[HSC016MG] = { .pmin =       0, .pmax =    1600 },
+	[HSC025MG] = { .pmin =       0, .pmax =    2500 },
+	[HSC040MG] = { .pmin =       0, .pmax =    4000 },
+	[HSC060MG] = { .pmin =       0, .pmax =    6000 },
+	[HSC100MG] = { .pmin =       0, .pmax =   10000 },
+	[HSC160MG] = { .pmin =       0, .pmax =   16000 },
+	[HSC250MG] = { .pmin =       0, .pmax =   25000 },
+	[HSC400MG] = { .pmin =       0, .pmax =   40000 },
+	[HSC600MG] = { .pmin =       0, .pmax =   60000 },
+	[HSC001BG] = { .pmin =       0, .pmax =  100000 },
+	[HSC1_6BG] = { .pmin =       0, .pmax =  160000 },
+	[HSC2_5BG] = { .pmin =       0, .pmax =  250000 },
+	[HSC004BG] = { .pmin =       0, .pmax =  400000 },
+	[HSC006BG] = { .pmin =       0, .pmax =  600000 },
+	[HSC010BG] = { .pmin =       0, .pmax = 1000000 },
+	[HSC100KA] = { .pmin =       0, .pmax =  100000 },
+	[HSC160KA] = { .pmin =       0, .pmax =  160000 },
+	[HSC250KA] = { .pmin =       0, .pmax =  250000 },
+	[HSC400KA] = { .pmin =       0, .pmax =  400000 },
+	[HSC600KA] = { .pmin =       0, .pmax =  600000 },
+	[HSC001GA] = { .pmin =       0, .pmax = 1000000 },
+	[HSC160LD] = { .pmin =    -160, .pmax =     160 },
+	[HSC250LD] = { .pmin =    -250, .pmax =     250 },
+	[HSC400LD] = { .pmin =    -400, .pmax =     400 },
+	[HSC600LD] = { .pmin =    -600, .pmax =     600 },
+	[HSC001KD] = { .pmin =   -1000, .pmax =    1000 },
+	[HSC1_6KD] = { .pmin =   -1600, .pmax =    1600 },
+	[HSC2_5KD] = { .pmin =   -2500, .pmax =    2500 },
+	[HSC004KD] = { .pmin =   -4000, .pmax =    4000 },
+	[HSC006KD] = { .pmin =   -6000, .pmax =    6000 },
+	[HSC010KD] = { .pmin =  -10000, .pmax =   10000 },
+	[HSC016KD] = { .pmin =  -16000, .pmax =   16000 },
+	[HSC025KD] = { .pmin =  -25000, .pmax =   25000 },
+	[HSC040KD] = { .pmin =  -40000, .pmax =   40000 },
+	[HSC060KD] = { .pmin =  -60000, .pmax =   60000 },
+	[HSC100KD] = { .pmin = -100000, .pmax =  100000 },
+	[HSC160KD] = { .pmin = -160000, .pmax =  160000 },
+	[HSC250KD] = { .pmin = -250000, .pmax =  250000 },
+	[HSC400KD] = { .pmin = -400000, .pmax =  400000 },
+	[HSC250LG] = { .pmin =       0, .pmax =     250 },
+	[HSC400LG] = { .pmin =       0, .pmax =     400 },
+	[HSC600LG] = { .pmin =       0, .pmax =     600 },
+	[HSC001KG] = { .pmin =       0, .pmax =    1000 },
+	[HSC1_6KG] = { .pmin =       0, .pmax =    1600 },
+	[HSC2_5KG] = { .pmin =       0, .pmax =    2500 },
+	[HSC004KG] = { .pmin =       0, .pmax =    4000 },
+	[HSC006KG] = { .pmin =       0, .pmax =    6000 },
+	[HSC010KG] = { .pmin =       0, .pmax =   10000 },
+	[HSC016KG] = { .pmin =       0, .pmax =   16000 },
+	[HSC025KG] = { .pmin =       0, .pmax =   25000 },
+	[HSC040KG] = { .pmin =       0, .pmax =   40000 },
+	[HSC060KG] = { .pmin =       0, .pmax =   60000 },
+	[HSC100KG] = { .pmin =       0, .pmax =  100000 },
+	[HSC160KG] = { .pmin =       0, .pmax =  160000 },
+	[HSC250KG] = { .pmin =       0, .pmax =  250000 },
+	[HSC400KG] = { .pmin =       0, .pmax =  400000 },
+	[HSC600KG] = { .pmin =       0, .pmax =  600000 },
+	[HSC001GG] = { .pmin =       0, .pmax = 1000000 },
+	[HSC015PA] = { .pmin =       0, .pmax =  103421 },
+	[HSC030PA] = { .pmin =       0, .pmax =  206843 },
+	[HSC060PA] = { .pmin =       0, .pmax =  413685 },
+	[HSC100PA] = { .pmin =       0, .pmax =  689476 },
+	[HSC150PA] = { .pmin =       0, .pmax = 1034214 },
+	[HSC0_5ND] = { .pmin =    -125, .pmax =     125 },
+	[HSC001ND] = { .pmin =    -249, .pmax =     249 },
+	[HSC002ND] = { .pmin =    -498, .pmax =     498 },
+	[HSC004ND] = { .pmin =    -996, .pmax =     996 },
+	[HSC005ND] = { .pmin =   -1245, .pmax =    1245 },
+	[HSC010ND] = { .pmin =   -2491, .pmax =    2491 },
+	[HSC020ND] = { .pmin =   -4982, .pmax =    4982 },
+	[HSC030ND] = { .pmin =   -7473, .pmax =    7473 },
+	[HSC001PD] = { .pmin =   -6895, .pmax =    6895 },
+	[HSC005PD] = { .pmin =  -34474, .pmax =   34474 },
+	[HSC015PD] = { .pmin = -103421, .pmax =  103421 },
+	[HSC030PD] = { .pmin = -206843, .pmax =  206843 },
+	[HSC060PD] = { .pmin = -413685, .pmax =  413685 },
+	[HSC001NG] = { .pmin =       0, .pmax =     249 },
+	[HSC002NG] = { .pmin =       0, .pmax =     498 },
+	[HSC004NG] = { .pmin =       0, .pmax =     996 },
+	[HSC005NG] = { .pmin =       0, .pmax =    1245 },
+	[HSC010NG] = { .pmin =       0, .pmax =    2491 },
+	[HSC020NG] = { .pmin =       0, .pmax =    4982 },
+	[HSC030NG] = { .pmin =       0, .pmax =    7473 },
+	[HSC001PG] = { .pmin =       0, .pmax =    6895 },
+	[HSC005PG] = { .pmin =       0, .pmax =   34474 },
+	[HSC015PG] = { .pmin =       0, .pmax =  103421 },
+	[HSC030PG] = { .pmin =       0, .pmax =  206843 },
+	[HSC060PG] = { .pmin =       0, .pmax =  413685 },
+	[HSC100PG] = { .pmin =       0, .pmax =  689476 },
+	[HSC150PG] = { .pmin =       0, .pmax = 1034214 },
+};
+
+/**
+ * hsc_measurement_is_valid() - validate last conversion via status bits
+ * @data: structure containing instantiated sensor data
+ * Return: true only if both status bits are zero
+ *
+ * the two MSB from the first transfered byte contain a status code
+ *   00 - normal operation, valid data
+ *   01 - device in factory programming mode
+ *   10 - stale data
+ *   11 - diagnostic condition
+ */
+static bool hsc_measurement_is_valid(struct hsc_data *data)
+{
+	return !(data->buffer[0] & HSC_STATUS_MASK);
+}
+
+static int hsc_get_measurement(struct hsc_data *data)
+{
+	const struct hsc_chip_data *chip = data->chip;
+	int ret;
+
+	ret = data->recv_cb(data);
+	if (ret < 0)
+		return ret;
+
+	data->is_valid = chip->valid(data);
+	if (!data->is_valid)
+		return -EAGAIN;
+
+	return 0;
+}
+
+/*
+ * IIO ABI expects
+ * value = (conv + offset) * scale
+ *
+ * datasheet provides the following formula for determining the temperature
+ * temp[C] = conv * a + b
+ *   where a = 200/2047; b = -50
+ *
+ *  temp[C] = (conv + (b/a)) * a * (1000)
+ *  =>
+ *  scale = a * 1000 = .097703957 * 1000 = 97.703957
+ *  offset = b/a = -50 / .097703957 = -50000000 / 97704
+ *
+ *  based on the datasheet
+ *  pressure = (conv - Omin) * Q + Pmin =
+ *          ((conv - Omin) + Pmin/Q) * Q
+ *  =>
+ *  scale = Q = (Pmax - Pmin) / (Omax - Omin)
+ *  offset = Pmin/Q - Omin = Pmin * (Omax - Omin) / (Pmax - Pmin) - Omin
+ */
+static int hsc_read_raw(struct iio_dev *indio_dev,
+			struct iio_chan_spec const *channel, int *val,
+			int *val2, long mask)
+{
+	struct hsc_data *data = iio_priv(indio_dev);
+	int ret;
+	u32 recvd;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = hsc_get_measurement(data);
+		if (ret)
+			return ret;
+
+		recvd = get_unaligned_be32(data->buffer);
+		switch (channel->type) {
+		case IIO_PRESSURE:
+			*val = FIELD_GET(HSC_PRESSURE_MASK, recvd);
+			return IIO_VAL_INT;
+		case IIO_TEMP:
+			*val = FIELD_GET(HSC_TEMPERATURE_MASK, recvd);
+			return IIO_VAL_INT;
+		default:
+			return -EINVAL;
+		}
+
+	case IIO_CHAN_INFO_SCALE:
+		switch (channel->type) {
+		case IIO_TEMP:
+			*val = 97;
+			*val2 = 703957;
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_PRESSURE:
+			*val = data->p_scale;
+			*val2 = data->p_scale_dec;
+			return IIO_VAL_INT_PLUS_NANO;
+		default:
+			return -EINVAL;
+		}
+
+	case IIO_CHAN_INFO_OFFSET:
+		switch (channel->type) {
+		case IIO_TEMP:
+			*val = -50000000;
+			*val2 = 97704;
+			return IIO_VAL_FRACTIONAL;
+		case IIO_PRESSURE:
+			*val = data->p_offset;
+			*val2 = data->p_offset_dec;
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_chan_spec hsc_channels[] = {
+	{
+		.type = IIO_PRESSURE,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE) |
+				      BIT(IIO_CHAN_INFO_OFFSET),
+	},
+	{
+		.type = IIO_TEMP,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE) |
+				      BIT(IIO_CHAN_INFO_OFFSET),
+	},
+};
+
+static const struct iio_info hsc_info = {
+	.read_raw = hsc_read_raw,
+};
+
+static const struct hsc_chip_data hsc_chip = {
+	.valid = hsc_measurement_is_valid,
+	.channels = hsc_channels,
+	.num_channels = ARRAY_SIZE(hsc_channels),
+};
+
+int hsc_common_probe(struct device *dev, hsc_recv_fn recv)
+{
+	struct hsc_data *hsc;
+	struct iio_dev *indio_dev;
+	const char *triplet;
+	u64 tmp;
+	int ret;
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*hsc));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	hsc = iio_priv(indio_dev);
+
+	hsc->chip = &hsc_chip;
+	hsc->recv_cb = recv;
+	hsc->dev = dev;
+
+	ret = device_property_read_u32(dev, "honeywell,transfer-function",
+				       &hsc->function);
+	if (ret)
+		return dev_err_probe(dev, ret,
+			    "honeywell,transfer-function could not be read\n");
+	if (hsc->function > HSC_FUNCTION_F)
+		return dev_err_probe(dev, -EINVAL,
+				     "honeywell,transfer-function %d invalid\n",
+				     hsc->function);
+
+	ret = device_property_read_string(dev, "honeywell,pressure-triplet",
+					  &triplet);
+	if (ret)
+		return dev_err_probe(dev, ret,
+			     "honeywell,pressure-triplet could not be read\n");
+
+	if (str_has_prefix(triplet, "NA")) {
+		ret = device_property_read_u32(dev, "honeywell,pmin-pascal",
+					       &hsc->pmin);
+		if (ret)
+			return dev_err_probe(dev, ret,
+				  "honeywell,pmin-pascal could not be read\n");
+
+		ret = device_property_read_u32(dev, "honeywell,pmax-pascal",
+					       &hsc->pmax);
+		if (ret)
+			return dev_err_probe(dev, ret,
+				  "honeywell,pmax-pascal could not be read\n");
+	} else {
+		ret = device_property_match_property_string(dev,
+						  "honeywell,pressure-triplet",
+						  hsc_triplet_variants,
+						  HSC_VARIANTS_MAX);
+		if (ret < 0)
+			return dev_err_probe(dev, -EINVAL,
+				    "honeywell,pressure-triplet is invalid\n");
+
+		hsc->pmin = hsc_range_config[ret].pmin;
+		hsc->pmax = hsc_range_config[ret].pmax;
+	}
+
+	if (hsc->pmin >= hsc->pmax)
+		return dev_err_probe(dev, -EINVAL,
+				     "pressure limits are invalid\n");
+
+	ret = devm_regulator_get_enable(dev, "vdd");
+	if (ret)
+		return dev_err_probe(dev, ret, "can't get vdd supply\n");
+
+	hsc->outmin = hsc_func_spec[hsc->function].output_min;
+	hsc->outmax = hsc_func_spec[hsc->function].output_max;
+
+	tmp = div_s64(((s64)(hsc->pmax - hsc->pmin)) * MICRO,
+		      hsc->outmax - hsc->outmin);
+	hsc->p_scale = div_s64_rem(tmp, NANO, &hsc->p_scale_dec);
+	tmp = div_s64(((s64)hsc->pmin * (s64)(hsc->outmax - hsc->outmin)) * MICRO,
+		      hsc->pmax - hsc->pmin);
+	tmp -= (s64)hsc->outmin * MICRO;
+	hsc->p_offset = div_s64_rem(tmp, MICRO, &hsc->p_offset_dec);
+
+	indio_dev->name = "hsc030pa";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->info = &hsc_info;
+	indio_dev->channels = hsc->chip->channels;
+	indio_dev->num_channels = hsc->chip->num_channels;
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+EXPORT_SYMBOL_NS(hsc_common_probe, IIO_HONEYWELL_HSC030PA);
+
+MODULE_AUTHOR("Petre Rodan <petre.rodan@subdimension.ro>");
+MODULE_DESCRIPTION("Honeywell HSC and SSC pressure sensor core driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/pressure/hsc030pa.h b/drivers/iio/pressure/hsc030pa.h
new file mode 100644
index 0000000000000..d20420dba4f6b
--- /dev/null
+++ b/drivers/iio/pressure/hsc030pa.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Honeywell TruStability HSC Series pressure/temperature sensor
+ *
+ * Copyright (c) 2023 Petre Rodan <petre.rodan@subdimension.ro>
+ */
+
+#ifndef _HSC030PA_H
+#define _HSC030PA_H
+
+#include <linux/types.h>
+
+#define HSC_REG_MEASUREMENT_RD_SIZE 4
+
+struct device;
+
+struct iio_chan_spec;
+struct iio_dev;
+
+struct hsc_data;
+struct hsc_chip_data;
+
+typedef int (*hsc_recv_fn)(struct hsc_data *);
+
+/**
+ * struct hsc_data
+ * @dev: current device structure
+ * @chip: structure containing chip's channel properties
+ * @recv_cb: function that implements the chip reads
+ * @is_valid: true if last transfer has been validated
+ * @pmin: minimum measurable pressure limit
+ * @pmax: maximum measurable pressure limit
+ * @outmin: minimum raw pressure in counts (based on transfer function)
+ * @outmax: maximum raw pressure in counts (based on transfer function)
+ * @function: transfer function
+ * @p_scale: pressure scale
+ * @p_scale_dec: pressure scale, decimal places
+ * @p_offset: pressure offset
+ * @p_offset_dec: pressure offset, decimal places
+ * @buffer: raw conversion data
+ */
+struct hsc_data {
+	struct device *dev;
+	const struct hsc_chip_data *chip;
+	hsc_recv_fn recv_cb;
+	bool is_valid;
+	s32 pmin;
+	s32 pmax;
+	u32 outmin;
+	u32 outmax;
+	u32 function;
+	s64 p_scale;
+	s32 p_scale_dec;
+	s64 p_offset;
+	s32 p_offset_dec;
+	u8 buffer[HSC_REG_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN);
+};
+
+struct hsc_chip_data {
+	bool (*valid)(struct hsc_data *data);
+	const struct iio_chan_spec *channels;
+	u8 num_channels;
+};
+
+enum hsc_func_id {
+	HSC_FUNCTION_A,
+	HSC_FUNCTION_B,
+	HSC_FUNCTION_C,
+	HSC_FUNCTION_F,
+};
+
+int hsc_common_probe(struct device *dev, hsc_recv_fn recv);
+
+#endif
diff --git a/drivers/iio/pressure/hsc030pa_i2c.c b/drivers/iio/pressure/hsc030pa_i2c.c
new file mode 100644
index 0000000000000..e2b524b364170
--- /dev/null
+++ b/drivers/iio/pressure/hsc030pa_i2c.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Honeywell TruStability HSC Series pressure/temperature sensor
+ *
+ * Copyright (c) 2023 Petre Rodan <petre.rodan@subdimension.ro>
+ *
+ * Datasheet: https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf [hsc]
+ * Datasheet: https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/common/documents/sps-siot-i2c-comms-digital-output-pressure-sensors-tn-008201-3-en-ciid-45841.pdf [i2c related]
+ */
+
+#include <linux/errno.h>
+#include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+
+#include <linux/iio/iio.h>
+
+#include "hsc030pa.h"
+
+static int hsc_i2c_recv(struct hsc_data *data)
+{
+	struct i2c_client *client = to_i2c_client(data->dev);
+	struct i2c_msg msg;
+	int ret;
+
+	msg.addr = client->addr;
+	msg.flags = client->flags | I2C_M_RD;
+	msg.len = HSC_REG_MEASUREMENT_RD_SIZE;
+	msg.buf = data->buffer;
+
+	ret = i2c_transfer(client->adapter, &msg, 1);
+
+	return (ret == 2) ? 0 : ret;
+}
+
+static int hsc_i2c_probe(struct i2c_client *client)
+{
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -EOPNOTSUPP;
+
+	return hsc_common_probe(&client->dev, hsc_i2c_recv);
+}
+
+static const struct of_device_id hsc_i2c_match[] = {
+	{ .compatible = "honeywell,hsc030pa" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, hsc_i2c_match);
+
+static const struct i2c_device_id hsc_i2c_id[] = {
+	{ "hsc030pa" },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, hsc_i2c_id);
+
+static struct i2c_driver hsc_i2c_driver = {
+	.driver = {
+		.name = "hsc030pa",
+		.of_match_table = hsc_i2c_match,
+	},
+	.probe = hsc_i2c_probe,
+	.id_table = hsc_i2c_id,
+};
+module_i2c_driver(hsc_i2c_driver);
+
+MODULE_AUTHOR("Petre Rodan <petre.rodan@subdimension.ro>");
+MODULE_DESCRIPTION("Honeywell HSC and SSC pressure sensor i2c driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_HONEYWELL_HSC030PA);
diff --git a/drivers/iio/pressure/hsc030pa_spi.c b/drivers/iio/pressure/hsc030pa_spi.c
new file mode 100644
index 0000000000000..a719bade83266
--- /dev/null
+++ b/drivers/iio/pressure/hsc030pa_spi.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Honeywell TruStability HSC Series pressure/temperature sensor
+ *
+ * Copyright (c) 2023 Petre Rodan <petre.rodan@subdimension.ro>
+ *
+ * Datasheet: https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/trustability-hsc-series/documents/sps-siot-trustability-hsc-series-high-accuracy-board-mount-pressure-sensors-50099148-a-en-ciid-151133.pdf
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/spi/spi.h>
+#include <linux/stddef.h>
+
+#include <linux/iio/iio.h>
+
+#include "hsc030pa.h"
+
+static int hsc_spi_recv(struct hsc_data *data)
+{
+	struct spi_device *spi = to_spi_device(data->dev);
+	struct spi_transfer xfer = {
+		.tx_buf = NULL,
+		.rx_buf = data->buffer,
+		.len = HSC_REG_MEASUREMENT_RD_SIZE,
+	};
+
+	return spi_sync_transfer(spi, &xfer, 1);
+}
+
+static int hsc_spi_probe(struct spi_device *spi)
+{
+	return hsc_common_probe(&spi->dev, hsc_spi_recv);
+}
+
+static const struct of_device_id hsc_spi_match[] = {
+	{ .compatible = "honeywell,hsc030pa" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, hsc_spi_match);
+
+static const struct spi_device_id hsc_spi_id[] = {
+	{ "hsc030pa" },
+	{}
+};
+MODULE_DEVICE_TABLE(spi, hsc_spi_id);
+
+static struct spi_driver hsc_spi_driver = {
+	.driver = {
+		.name = "hsc030pa",
+		.of_match_table = hsc_spi_match,
+	},
+	.probe = hsc_spi_probe,
+	.id_table = hsc_spi_id,
+};
+module_spi_driver(hsc_spi_driver);
+
+MODULE_AUTHOR("Petre Rodan <petre.rodan@subdimension.ro>");
+MODULE_DESCRIPTION("Honeywell HSC and SSC pressure sensor spi driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_HONEYWELL_HSC030PA);
-- 
GitLab


From c95e0a719820054b28ef8687cc05b8deeb1c9106 Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Fri, 8 Dec 2023 10:17:15 +0800
Subject: [PATCH 1108/4076] iio: light: isl76682: remove unreachable code

The function isl76682_read_raw cannot execute return -EINVAL up to 145
lines, delete the invalid code.

drivers/iio/light/isl76682.c:145 isl76682_read_raw() warn: ignoring unreachable code.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=7698
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Link: https://lore.kernel.org/r/20231208021715.32450-1-jiapeng.chong@linux.alibaba.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/isl76682.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/iio/light/isl76682.c b/drivers/iio/light/isl76682.c
index 0a7c3b09c3c05..cf6ddee44ffc3 100644
--- a/drivers/iio/light/isl76682.c
+++ b/drivers/iio/light/isl76682.c
@@ -142,7 +142,6 @@ static int isl76682_read_raw(struct iio_dev *indio_dev,
 		default:
 			return -EINVAL;
 		}
-		return -EINVAL;
 	case IIO_CHAN_INFO_SCALE:
 		for (i = 0; i < ARRAY_SIZE(isl76682_range_table); i++) {
 			if (chip->range != isl76682_range_table[i].range)
-- 
GitLab


From 48ba7d2f24f18c6752275c18f25a396221aa2787 Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Fri, 8 Dec 2023 15:52:09 +0530
Subject: [PATCH 1109/4076] dt-bindings: iio: light: add ltr390

Add binding for Lite-On LTR390 which is an Ambient/UV light sensor that
communicates over i2c with an address of 0x53.

Datasheet: https://optoelectronics.liteon.com/upload/download/DS86-2015-0004/LTR-390UV_Final_%20DS_V1%201.pdf
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20231208102211.413019-1-anshulusr@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/light/liteon,ltr390.yaml     | 56 +++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml

diff --git a/Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml b/Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml
new file mode 100644
index 0000000000000..5d98ef2af74d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml
@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/light/liteon,ltr390.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Lite-On LTR390 ALS and UV Sensor
+
+description: |
+  The Lite-On LTR390 is an ALS (Ambient Light Sensor) and a UV sensor in a
+  single package with i2c address of 0x53.
+
+  Datasheet:
+    https://optoelectronics.liteon.com/upload/download/DS86-2015-0004/LTR-390UV_Final_%20DS_V1%201.pdf
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - liteon,ltr390
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+    description: |
+      Level interrupt pin with open drain output.
+      The sensor pulls this pin low when the measured reading is greater than
+      some configured threshold.
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        light-sensor@53 {
+            compatible = "liteon,ltr390";
+            reg = <0x53>;
+            interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+            vdd-supply = <&vdd_regulator>;
+        };
+    };
-- 
GitLab


From 8b0d4c40d704cb7d01ad4f647ff5a51881767acd Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Fri, 8 Dec 2023 15:52:10 +0530
Subject: [PATCH 1110/4076] iio: light: driver for Lite-On ltr390

Implements driver for the Ambient/UV Light sensor LTR390.
The driver exposes two ways of getting sensor readings:
  1. Raw UV Counts directly from the sensor
  2. The computed UV Index value with a percision of 2 decimal places

[NOTE] Ambient light sensing has not been implemented yet.

Driver tested on RPi Zero 2W

Datasheet: https://optoelectronics.liteon.com/upload/download/DS86-2015-0004/LTR-390UV_Final_%20DS_V1%201.pdf
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20231208102211.413019-2-anshulusr@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS                |   7 ++
 drivers/iio/light/Kconfig  |  11 +++
 drivers/iio/light/Makefile |   1 +
 drivers/iio/light/ltr390.c | 196 +++++++++++++++++++++++++++++++++++++
 4 files changed, 215 insertions(+)
 create mode 100644 drivers/iio/light/ltr390.c

diff --git a/MAINTAINERS b/MAINTAINERS
index cf1ce6e6c1e11..4eddc4212f2b8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12663,6 +12663,13 @@ S:	Maintained
 W:	http://linux-test-project.github.io/
 T:	git https://github.com/linux-test-project/ltp.git
 
+LTR390 AMBIENT/UV LIGHT SENSOR DRIVER
+M:	Anshul Dalal <anshulusr@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/light/liteon,ltr390.yaml
+F:	drivers/iio/light/ltr390.c
+
 LYNX 28G SERDES PHY DRIVER
 M:	Ioana Ciornei <ioana.ciornei@nxp.com>
 L:	netdev@vger.kernel.org
diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig
index 9ac6c737207fc..143003232d1c2 100644
--- a/drivers/iio/light/Kconfig
+++ b/drivers/iio/light/Kconfig
@@ -362,6 +362,17 @@ config SENSORS_LM3533
 	  changes. The ALS-control output values can be set per zone for the
 	  three current output channels.
 
+config LTR390
+	tristate "LTR-390UV-01 ambient light and UV sensor"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the Lite-On LTR-390UV-01
+	  ambient light and UV sensor.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called ltr390.
+
 config LTR501
 	tristate "LTR-501ALS-01 light sensor"
 	depends on I2C
diff --git a/drivers/iio/light/Makefile b/drivers/iio/light/Makefile
index 4aa0835ece5d9..2e5fdb33e0e97 100644
--- a/drivers/iio/light/Makefile
+++ b/drivers/iio/light/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_ISL29125)		+= isl29125.o
 obj-$(CONFIG_ISL76682)		+= isl76682.o
 obj-$(CONFIG_JSA1212)		+= jsa1212.o
 obj-$(CONFIG_SENSORS_LM3533)	+= lm3533-als.o
+obj-$(CONFIG_LTR390)		+= ltr390.o
 obj-$(CONFIG_LTR501)		+= ltr501.o
 obj-$(CONFIG_LTRF216A)		+= ltrf216a.o
 obj-$(CONFIG_LV0104CS)		+= lv0104cs.o
diff --git a/drivers/iio/light/ltr390.c b/drivers/iio/light/ltr390.c
new file mode 100644
index 0000000000000..fff1e899097d9
--- /dev/null
+++ b/drivers/iio/light/ltr390.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * IIO driver for Lite-On LTR390 ALS and UV sensor
+ * (7-bit I2C slave address 0x53)
+ *
+ * Based on the work of:
+ *   Shreeya Patel and Shi Zhigang (LTRF216 Driver)
+ *
+ * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com>
+ *
+ * Datasheet:
+ *   https://optoelectronics.liteon.com/upload/download/DS86-2015-0004/LTR-390UV_Final_%20DS_V1%201.pdf
+ *
+ * TODO:
+ *   - Support for configurable gain and resolution
+ *   - Sensor suspend/resume support
+ *   - Add support for reading the ALS
+ *   - Interrupt support
+ */
+
+#include <linux/i2c.h>
+#include <linux/math.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+
+#include <linux/iio/iio.h>
+
+#include <asm/unaligned.h>
+
+#define LTR390_MAIN_CTRL      0x00
+#define LTR390_PART_ID	      0x06
+#define LTR390_UVS_DATA	      0x10
+
+#define LTR390_SW_RESET	      BIT(4)
+#define LTR390_UVS_MODE	      BIT(3)
+#define LTR390_SENSOR_ENABLE  BIT(1)
+
+#define LTR390_PART_NUMBER_ID 0xb
+
+/*
+ * At 20-bit resolution (integration time: 400ms) and 18x gain, 2300 counts of
+ * the sensor are equal to 1 UV Index [Datasheet Page#8].
+ *
+ * For the default resolution of 18-bit (integration time: 100ms) and default
+ * gain of 3x, the counts/uvi are calculated as follows:
+ * 2300 / ((3/18) * (100/400)) = 95.83
+ */
+#define LTR390_COUNTS_PER_UVI 96
+
+/*
+ * Window Factor is needed when the device is under Window glass with coated
+ * tinted ink. This is to compensate for the light loss due to the lower
+ * transmission rate of the window glass and helps * in calculating lux.
+ */
+#define LTR390_WINDOW_FACTOR 1
+
+struct ltr390_data {
+	struct regmap *regmap;
+	struct i2c_client *client;
+	/* Protects device from simulataneous reads */
+	struct mutex lock;
+};
+
+static const struct regmap_config ltr390_regmap_config = {
+	.name = "ltr390",
+	.reg_bits = 8,
+	.reg_stride = 1,
+	.val_bits = 8,
+};
+
+static int ltr390_register_read(struct ltr390_data *data, u8 register_address)
+{
+	struct device *dev = &data->client->dev;
+	int ret;
+	u8 recieve_buffer[3];
+
+	guard(mutex)(&data->lock);
+
+	ret = regmap_bulk_read(data->regmap, register_address, recieve_buffer,
+			       sizeof(recieve_buffer));
+	if (ret) {
+		dev_err(dev, "failed to read measurement data");
+		return ret;
+	}
+
+	return get_unaligned_le24(recieve_buffer);
+}
+
+static int ltr390_read_raw(struct iio_dev *iio_device,
+			   struct iio_chan_spec const *chan, int *val,
+			   int *val2, long mask)
+{
+	int ret;
+	struct ltr390_data *data = iio_priv(iio_device);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = ltr390_register_read(data, LTR390_UVS_DATA);
+		if (ret < 0)
+			return ret;
+		*val = ret;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		*val = LTR390_WINDOW_FACTOR;
+		*val2 = LTR390_COUNTS_PER_UVI;
+		return IIO_VAL_FRACTIONAL;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info ltr390_info = {
+	.read_raw = ltr390_read_raw,
+};
+
+static const struct iio_chan_spec ltr390_channel = {
+	.type = IIO_UVINDEX,
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)
+};
+
+static int ltr390_probe(struct i2c_client *client)
+{
+	struct ltr390_data *data;
+	struct iio_dev *indio_dev;
+	struct device *dev;
+	int ret, part_number;
+
+	dev = &client->dev;
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	data = iio_priv(indio_dev);
+
+	data->regmap = devm_regmap_init_i2c(client, &ltr390_regmap_config);
+	if (IS_ERR(data->regmap))
+		return dev_err_probe(dev, PTR_ERR(data->regmap),
+				     "regmap initialization failed\n");
+
+	data->client = client;
+	mutex_init(&data->lock);
+
+	indio_dev->info = &ltr390_info;
+	indio_dev->channels = &ltr390_channel;
+	indio_dev->num_channels = 1;
+	indio_dev->name = "ltr390";
+
+	ret = regmap_read(data->regmap, LTR390_PART_ID, &part_number);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to get sensor's part id\n");
+	/* Lower 4 bits of `part_number` change with hardware revisions */
+	if (part_number >> 4 != LTR390_PART_NUMBER_ID)
+		dev_info(dev, "received invalid product id: 0x%x", part_number);
+	dev_dbg(dev, "LTR390, product id: 0x%x\n", part_number);
+
+	/* reset sensor, chip fails to respond to this, so ignore any errors */
+	regmap_set_bits(data->regmap, LTR390_MAIN_CTRL, LTR390_SW_RESET);
+
+	/* Wait for the registers to reset before proceeding */
+	usleep_range(1000, 2000);
+
+	ret = regmap_set_bits(data->regmap, LTR390_MAIN_CTRL,
+			      LTR390_SENSOR_ENABLE | LTR390_UVS_MODE);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to enable the sensor\n");
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct i2c_device_id ltr390_id[] = {
+	{ "ltr390" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, ltr390_id);
+
+static const struct of_device_id ltr390_of_table[] = {
+	{ .compatible = "liteon,ltr390" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ltr390_of_table);
+
+static struct i2c_driver ltr390_driver = {
+	.driver = {
+		.name = "ltr390",
+		.of_match_table = ltr390_of_table,
+	},
+	.probe = ltr390_probe,
+	.id_table = ltr390_id,
+};
+module_i2c_driver(ltr390_driver);
+
+MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>");
+MODULE_DESCRIPTION("Lite-On LTR390 ALS and UV sensor Driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 5bc2ea60897e0f899fb93930dd867dae7c8eb11f Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 11 Dec 2023 20:27:47 +0800
Subject: [PATCH 1111/4076] iio: core: introduce trough info element for
 minimum values

The IIO_CHAN_INFO_PEAK info element is used for maximum values and
currently there is no equivalent for minimum values. Instead of
overloading the existing peak info element, a new info element can
be added.

In principle there is no need to add a _TROUGH_SCALE element as the
scale will be the same as the one required for INFO_PEAK, which in
turn is sometimes omitted if a single scale for peaks and raw values
is required.

Add an IIO_CHAN_INFO_TROUGH info element for minimum values.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20231211122747.9723-1-579lpy@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 1 +
 include/linux/iio/types.h       | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index f6a123d397db5..9a85752124ddc 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -184,6 +184,7 @@ static const char * const iio_chan_info_postfix[] = {
 	[IIO_CHAN_INFO_THERMOCOUPLE_TYPE] = "thermocouple_type",
 	[IIO_CHAN_INFO_CALIBAMBIENT] = "calibambient",
 	[IIO_CHAN_INFO_ZEROPOINT] = "zeropoint",
+	[IIO_CHAN_INFO_TROUGH] = "trough_raw",
 };
 /**
  * iio_device_id() - query the unique ID for the device
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index 117bde7d6ad79..d89982c98368c 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -68,6 +68,7 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_THERMOCOUPLE_TYPE,
 	IIO_CHAN_INFO_CALIBAMBIENT,
 	IIO_CHAN_INFO_ZEROPOINT,
+	IIO_CHAN_INFO_TROUGH,
 };
 
 #endif /* _IIO_TYPES_H_ */
-- 
GitLab


From a4887e9782959e3e8f756412b53808157803de60 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 11 Dec 2023 20:28:40 +0800
Subject: [PATCH 1112/4076] iio: ABI: document temperature and humidity
 peak/trough raw attributes

The in_temp_peak_raw attribute is already in use, but its documentation
is still missing. The in_humidityrelative_raw must be documented for a
new iio user that supports this attribute. Add temp and humidityrelative
use cases.
When at it, remove an extra blank space in the description.

For users that support minimum values, a new in_<type>_trough_raw
attribute is required. Add this attribute and document the first uses of
it for temp and humidityrelative types.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20231211122840.9760-1-579lpy@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-iio | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 94b8d8461b7c7..2e6d5ebfd3c73 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -362,10 +362,21 @@ Description:
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_x_peak_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_y_peak_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_z_peak_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_humidityrelative_peak_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_temp_peak_raw
 KernelVersion:	2.6.36
 Contact:	linux-iio@vger.kernel.org
 Description:
-		Highest value since some reset condition.  These
+		Highest value since some reset condition. These
+		attributes allow access to this and are otherwise
+		the direct equivalent of the <type>Y[_name]_raw attributes.
+
+What:		/sys/bus/iio/devices/iio:deviceX/in_humidityrelative_trough_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_temp_trough_raw
+KernelVersion:	6.7
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Lowest value since some reset condition. These
 		attributes allow access to this and are otherwise
 		the direct equivalent of the <type>Y[_name]_raw attributes.
 
-- 
GitLab


From c9180b8e39befcc703940873ac49e0603ef42bf7 Mon Sep 17 00:00:00 2001
From: Li peiyu <579lpy@gmail.com>
Date: Mon, 11 Dec 2023 20:29:40 +0800
Subject: [PATCH 1113/4076] iio: humidity: Add driver for ti HDC302x humidity
 sensors

Add support for HDC302x integrated capacitive based relative
humidity (RH) and temperature sensor.
This driver supports reading values, reading the maximum and
minimum of values and controlling the integrated heater of
the sensor.

Co-developed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Signed-off-by: Li peiyu <579lpy@gmail.com>
Link: https://lore.kernel.org/r/20231211122940.9791-1-579lpy@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/humidity/hdc3020.c | 473 +++++++++++++++++++++++++++++++++
 1 file changed, 473 insertions(+)
 create mode 100644 drivers/iio/humidity/hdc3020.c

diff --git a/drivers/iio/humidity/hdc3020.c b/drivers/iio/humidity/hdc3020.c
new file mode 100644
index 0000000000000..4e3311170725b
--- /dev/null
+++ b/drivers/iio/humidity/hdc3020.c
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * hdc3020.c - Support for the TI HDC3020,HDC3021 and HDC3022
+ * temperature + relative humidity sensors
+ *
+ * Copyright (C) 2023
+ *
+ * Datasheet: https://www.ti.com/lit/ds/symlink/hdc3020.pdf
+ */
+
+#include <linux/bitops.h>
+#include <linux/cleanup.h>
+#include <linux/crc8.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+
+#include <asm/unaligned.h>
+
+#include <linux/iio/iio.h>
+
+#define HDC3020_HEATER_CMD_MSB		0x30 /* shared by all heater commands */
+#define HDC3020_HEATER_ENABLE		0x6D
+#define HDC3020_HEATER_DISABLE		0x66
+#define HDC3020_HEATER_CONFIG		0x6E
+
+#define HDC3020_READ_RETRY_TIMES	10
+#define HDC3020_BUSY_DELAY_MS		10
+
+#define HDC3020_CRC8_POLYNOMIAL		0x31
+
+static const u8 HDC3020_S_AUTO_10HZ_MOD0[2] = { 0x27, 0x37 };
+
+static const u8 HDC3020_EXIT_AUTO[2] = { 0x30, 0x93 };
+
+static const u8 HDC3020_R_T_RH_AUTO[2] = { 0xE0, 0x00 };
+static const u8 HDC3020_R_T_LOW_AUTO[2] = { 0xE0, 0x02 };
+static const u8 HDC3020_R_T_HIGH_AUTO[2] = { 0xE0, 0x03 };
+static const u8 HDC3020_R_RH_LOW_AUTO[2] = { 0xE0, 0x04 };
+static const u8 HDC3020_R_RH_HIGH_AUTO[2] = { 0xE0, 0x05 };
+
+struct hdc3020_data {
+	struct i2c_client *client;
+	/*
+	 * Ensure that the sensor configuration (currently only heater is
+	 * supported) will not be changed during the process of reading
+	 * sensor data (this driver will try HDC3020_READ_RETRY_TIMES times
+	 * if the device does not respond).
+	 */
+	struct mutex lock;
+};
+
+static const int hdc3020_heater_vals[] = {0, 1, 0x3FFF};
+
+static const struct iio_chan_spec hdc3020_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+		BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_PEAK) |
+		BIT(IIO_CHAN_INFO_TROUGH) | BIT(IIO_CHAN_INFO_OFFSET),
+	},
+	{
+		.type = IIO_HUMIDITYRELATIVE,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+		BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_PEAK) |
+		BIT(IIO_CHAN_INFO_TROUGH),
+	},
+	{
+		/*
+		 * For setting the internal heater, which can be switched on to
+		 * prevent or remove any condensation that may develop when the
+		 * ambient environment approaches its dew point temperature.
+		 */
+		.type = IIO_CURRENT,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+		.info_mask_separate_available = BIT(IIO_CHAN_INFO_RAW),
+		.output = 1,
+	},
+};
+
+DECLARE_CRC8_TABLE(hdc3020_crc8_table);
+
+static int hdc3020_write_bytes(struct hdc3020_data *data, const u8 *buf, u8 len)
+{
+	struct i2c_client *client = data->client;
+	struct i2c_msg msg;
+	int ret, cnt;
+
+	msg.addr = client->addr;
+	msg.flags = 0;
+	msg.buf = (char *)buf;
+	msg.len = len;
+
+	/*
+	 * During the measurement process, HDC3020 will not return data.
+	 * So wait for a while and try again
+	 */
+	for (cnt = 0; cnt < HDC3020_READ_RETRY_TIMES; cnt++) {
+		ret = i2c_transfer(client->adapter, &msg, 1);
+		if (ret == 1)
+			return 0;
+
+		mdelay(HDC3020_BUSY_DELAY_MS);
+	}
+	dev_err(&client->dev, "Could not write sensor command\n");
+
+	return -ETIMEDOUT;
+}
+
+static int hdc3020_read_bytes(struct hdc3020_data *data, const u8 *buf,
+			      void *val, int len)
+{
+	int ret, cnt;
+	struct i2c_client *client = data->client;
+	struct i2c_msg msg[2] = {
+		[0] = {
+			.addr = client->addr,
+			.flags = 0,
+			.buf = (char *)buf,
+			.len = 2,
+		},
+		[1] = {
+			.addr = client->addr,
+			.flags = I2C_M_RD,
+			.buf = val,
+			.len = len,
+		},
+	};
+
+	/*
+	 * During the measurement process, HDC3020 will not return data.
+	 * So wait for a while and try again
+	 */
+	for (cnt = 0; cnt < HDC3020_READ_RETRY_TIMES; cnt++) {
+		ret = i2c_transfer(client->adapter, msg, 2);
+		if (ret == 2)
+			return 0;
+
+		mdelay(HDC3020_BUSY_DELAY_MS);
+	}
+	dev_err(&client->dev, "Could not read sensor data\n");
+
+	return -ETIMEDOUT;
+}
+
+static int hdc3020_read_measurement(struct hdc3020_data *data,
+				    enum iio_chan_type type, int *val)
+{
+	u8 crc, buf[6];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_T_RH_AUTO, buf, 6);
+	if (ret < 0)
+		return ret;
+
+	/* CRC check of the temperature measurement */
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	/* CRC check of the relative humidity measurement */
+	crc = crc8(hdc3020_crc8_table, buf + 3, 2, CRC8_INIT_VALUE);
+	if (crc != buf[5])
+		return -EINVAL;
+
+	if (type == IIO_TEMP)
+		*val = get_unaligned_be16(buf);
+	else if (type == IIO_HUMIDITYRELATIVE)
+		*val = get_unaligned_be16(&buf[3]);
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * After exiting the automatic measurement mode or resetting, the peak
+ * value will be reset to the default value
+ * This method is used to get the highest temp measured during automatic
+ * measurement
+ */
+static int hdc3020_read_high_peak_t(struct hdc3020_data *data, int *val)
+{
+	u8 crc, buf[3];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_T_HIGH_AUTO, buf, 3);
+	if (ret < 0)
+		return ret;
+
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	*val = get_unaligned_be16(buf);
+
+	return 0;
+}
+
+/*
+ * This method is used to get the lowest temp measured during automatic
+ * measurement
+ */
+static int hdc3020_read_low_peak_t(struct hdc3020_data *data, int *val)
+{
+	u8 crc, buf[3];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_T_LOW_AUTO, buf, 3);
+	if (ret < 0)
+		return ret;
+
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	*val = get_unaligned_be16(buf);
+
+	return 0;
+}
+
+/*
+ * This method is used to get the highest humidity measured during automatic
+ * measurement
+ */
+static int hdc3020_read_high_peak_rh(struct hdc3020_data *data, int *val)
+{
+	u8 crc, buf[3];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_RH_HIGH_AUTO, buf, 3);
+	if (ret < 0)
+		return ret;
+
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	*val = get_unaligned_be16(buf);
+
+	return 0;
+}
+
+/*
+ * This method is used to get the lowest humidity measured during automatic
+ * measurement
+ */
+static int hdc3020_read_low_peak_rh(struct hdc3020_data *data, int *val)
+{
+	u8 crc, buf[3];
+	int ret;
+
+	ret = hdc3020_read_bytes(data, HDC3020_R_RH_LOW_AUTO, buf, 3);
+	if (ret < 0)
+		return ret;
+
+	crc = crc8(hdc3020_crc8_table, buf, 2, CRC8_INIT_VALUE);
+	if (crc != buf[2])
+		return -EINVAL;
+
+	*val = get_unaligned_be16(buf);
+
+	return 0;
+}
+
+static int hdc3020_read_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	struct hdc3020_data *data = iio_priv(indio_dev);
+	int ret;
+
+	if (chan->type != IIO_TEMP && chan->type != IIO_HUMIDITYRELATIVE)
+		return -EINVAL;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW: {
+		guard(mutex)(&data->lock);
+		ret = hdc3020_read_measurement(data, chan->type, val);
+		if (ret < 0)
+			return ret;
+
+		return IIO_VAL_INT;
+	}
+	case IIO_CHAN_INFO_PEAK: {
+		guard(mutex)(&data->lock);
+		if (chan->type == IIO_TEMP) {
+			ret = hdc3020_read_high_peak_t(data, val);
+			if (ret < 0)
+				return ret;
+		} else {
+			ret = hdc3020_read_high_peak_rh(data, val);
+			if (ret < 0)
+				return ret;
+		}
+		return IIO_VAL_INT;
+	}
+	case IIO_CHAN_INFO_TROUGH: {
+		guard(mutex)(&data->lock);
+		if (chan->type == IIO_TEMP) {
+			ret = hdc3020_read_low_peak_t(data, val);
+			if (ret < 0)
+				return ret;
+		} else {
+			ret = hdc3020_read_low_peak_rh(data, val);
+			if (ret < 0)
+				return ret;
+		}
+		return IIO_VAL_INT;
+	}
+	case IIO_CHAN_INFO_SCALE:
+		*val2 = 65536;
+		if (chan->type == IIO_TEMP)
+			*val = 175;
+		else
+			*val = 100;
+		return IIO_VAL_FRACTIONAL;
+
+	case IIO_CHAN_INFO_OFFSET:
+		if (chan->type != IIO_TEMP)
+			return -EINVAL;
+
+		*val = 16852;
+		return IIO_VAL_INT;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int hdc3020_read_available(struct iio_dev *indio_dev,
+				  struct iio_chan_spec const *chan,
+				  const int **vals,
+				  int *type, int *length, long mask)
+{
+	if (mask != IIO_CHAN_INFO_RAW || chan->type != IIO_CURRENT)
+		return -EINVAL;
+
+	*vals = hdc3020_heater_vals;
+	*type = IIO_VAL_INT;
+
+	return IIO_AVAIL_RANGE;
+}
+
+static int hdc3020_update_heater(struct hdc3020_data *data, int val)
+{
+	u8 buf[5];
+	int ret;
+
+	if (val < hdc3020_heater_vals[0] || val > hdc3020_heater_vals[2])
+		return -EINVAL;
+
+	buf[0] = HDC3020_HEATER_CMD_MSB;
+
+	if (!val) {
+		buf[1] = HDC3020_HEATER_DISABLE;
+		return hdc3020_write_bytes(data, buf, 2);
+	}
+
+	buf[1] = HDC3020_HEATER_CONFIG;
+	put_unaligned_be16(val & GENMASK(13, 0), &buf[2]);
+	buf[4] = crc8(hdc3020_crc8_table, buf + 2, 2, CRC8_INIT_VALUE);
+	ret = hdc3020_write_bytes(data, buf, 5);
+	if (ret < 0)
+		return ret;
+
+	buf[1] = HDC3020_HEATER_ENABLE;
+
+	return hdc3020_write_bytes(data, buf, 2);
+}
+
+static int hdc3020_write_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int val, int val2, long mask)
+{
+	struct hdc3020_data *data = iio_priv(indio_dev);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		if (chan->type != IIO_CURRENT)
+			return -EINVAL;
+
+		guard(mutex)(&data->lock);
+		return hdc3020_update_heater(data, val);
+	}
+
+	return -EINVAL;
+}
+
+static const struct iio_info hdc3020_info = {
+	.read_raw = hdc3020_read_raw,
+	.write_raw = hdc3020_write_raw,
+	.read_avail = hdc3020_read_available,
+};
+
+static void hdc3020_stop(void *data)
+{
+	hdc3020_write_bytes((struct hdc3020_data *)data, HDC3020_EXIT_AUTO, 2);
+}
+
+static int hdc3020_probe(struct i2c_client *client)
+{
+	struct iio_dev *indio_dev;
+	struct hdc3020_data *data;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -EOPNOTSUPP;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+	mutex_init(&data->lock);
+
+	crc8_populate_msb(hdc3020_crc8_table, HDC3020_CRC8_POLYNOMIAL);
+
+	indio_dev->name = "hdc3020";
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->info = &hdc3020_info;
+	indio_dev->channels = hdc3020_channels;
+	indio_dev->num_channels = ARRAY_SIZE(hdc3020_channels);
+
+	ret = hdc3020_write_bytes(data, HDC3020_S_AUTO_10HZ_MOD0, 2);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				     "Unable to set up measurement\n");
+
+	ret = devm_add_action_or_reset(&data->client->dev, hdc3020_stop, data);
+	if (ret)
+		return ret;
+
+	ret = devm_iio_device_register(&data->client->dev, indio_dev);
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to add device");
+
+	return 0;
+}
+
+static const struct i2c_device_id hdc3020_id[] = {
+	{ "hdc3020" },
+	{ "hdc3021" },
+	{ "hdc3022" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, hdc3020_id);
+
+static const struct of_device_id hdc3020_dt_ids[] = {
+	{ .compatible = "ti,hdc3020" },
+	{ .compatible = "ti,hdc3021" },
+	{ .compatible = "ti,hdc3022" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, hdc3020_dt_ids);
+
+static struct i2c_driver hdc3020_driver = {
+	.driver = {
+		.name = "hdc3020",
+		.of_match_table = hdc3020_dt_ids,
+	},
+	.probe = hdc3020_probe,
+	.id_table = hdc3020_id,
+};
+module_i2c_driver(hdc3020_driver);
+
+MODULE_AUTHOR("Javier Carrasco <javier.carrasco.cruz@gmail.com>");
+MODULE_AUTHOR("Li peiyu <579lpy@gmail.com>");
+MODULE_DESCRIPTION("TI HDC3020 humidity and temperature sensor driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 693af17bcee427fd9d14942fee2b03a397e06b3e Mon Sep 17 00:00:00 2001
From: Li peiyu <579lpy@gmail.com>
Date: Mon, 11 Dec 2023 20:31:01 +0800
Subject: [PATCH 1114/4076] dt-bindings: iio: humidity: Add TI HDC302x support

Add device tree bindings for HDC3020/HDC3021/HDC3022 humidity and
temperature sensors.

Signed-off-by: Li peiyu <579lpy@gmail.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231211123101.9868-1-579lpy@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/humidity/ti,hdc3020.yaml     | 55 +++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml

diff --git a/Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml b/Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml
new file mode 100644
index 0000000000000..7f6d0f9edc75e
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/humidity/ti,hdc3020.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: HDC3020/HDC3021/HDC3022 humidity and temperature iio sensors
+
+maintainers:
+  - Li peiyu <579lpy@gmail.com>
+  - Javier Carrasco <javier.carrasco.cruz@gmail.com>
+
+description:
+  https://www.ti.com/lit/ds/symlink/hdc3020.pdf
+
+  The HDC302x is an integrated capacitive based relative humidity (RH)
+  and temperature sensor.
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - ti,hdc3021
+              - ti,hdc3022
+          - const: ti,hdc3020
+      - const: ti,hdc3020
+
+  interrupts:
+    maxItems: 1
+
+  vdd-supply: true
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        humidity-sensor@47 {
+            compatible = "ti,hdc3021", "ti,hdc3020";
+            reg = <0x47>;
+            vdd-supply = <&vcc_3v3>;
+        };
+    };
-- 
GitLab


From e367e3c765f5477b2e79da0f1399aed49e2d1e37 Mon Sep 17 00:00:00 2001
From: LeoLiuoc <LeoLiu-oc@zhaoxin.com>
Date: Mon, 11 Dec 2023 17:15:43 +0800
Subject: [PATCH 1115/4076] PCI: Add ACS quirk for more Zhaoxin Root Ports

Add more Root Port Device IDs to pci_quirk_zhaoxin_pcie_ports_acs() for
some new Zhaoxin platforms.

Fixes: 299bd044a6f3 ("PCI: Add ACS quirk for Zhaoxin Root/Downstream Ports")
Link: https://lore.kernel.org/r/20231211091543.735903-1-LeoLiu-oc@zhaoxin.com
Signed-off-by: LeoLiuoc <LeoLiu-oc@zhaoxin.com>
[bhelgaas: update subject, drop changelog, add Fixes, add stable tag, fix
whitespace, wrap code comment]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: <stable@vger.kernel.org>	# 5.7
---
 drivers/pci/quirks.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index ea476252280ab..d55a3ffae4b8b 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4699,17 +4699,21 @@ static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags)
  * But the implementation could block peer-to-peer transactions between them
  * and provide ACS-like functionality.
  */
-static int  pci_quirk_zhaoxin_pcie_ports_acs(struct pci_dev *dev, u16 acs_flags)
+static int pci_quirk_zhaoxin_pcie_ports_acs(struct pci_dev *dev, u16 acs_flags)
 {
 	if (!pci_is_pcie(dev) ||
 	    ((pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) &&
 	     (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM)))
 		return -ENOTTY;
 
+	/*
+	 * Future Zhaoxin Root Ports and Switch Downstream Ports will
+	 * implement ACS capability in accordance with the PCIe Spec.
+	 */
 	switch (dev->device) {
 	case 0x0710 ... 0x071e:
 	case 0x0721:
-	case 0x0723 ... 0x0732:
+	case 0x0723 ... 0x0752:
 		return pci_acs_ctrl_enabled(acs_flags,
 			PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 	}
-- 
GitLab


From 06dc6a869597ec68b2e4ebcde8147f4a52965e96 Mon Sep 17 00:00:00 2001
From: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Date: Sun, 22 Oct 2023 11:06:33 +0200
Subject: [PATCH 1116/4076] MAINTAINERS: Add myself as maintainer of the Ralink
 architecture
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Its been a while since I am making contributions to this architecture.
Hence add myself as maintainer.

Signed-off-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Acked-by: John Crispin <john@phrozen.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index e2c6187a3ac80..b3444c8c6512e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18051,6 +18051,7 @@ F:	drivers/media/cec/usb/rainshadow/
 
 RALINK MIPS ARCHITECTURE
 M:	John Crispin <john@phrozen.org>
+M:	Sergio Paracuellos <sergio.paracuellos@gmail.com>
 L:	linux-mips@vger.kernel.org
 S:	Maintained
 F:	arch/mips/ralink
-- 
GitLab


From 01940cd4a6b9c47995a0cdaaafdd459b0d2221a2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 10 Nov 2023 19:02:13 -0800
Subject: [PATCH 1117/4076] MIPS: SGI-IP27: hubio: fix nasid kernel-doc warning

ip27-hubio.c:32: warning: Function parameter or member 'nasid' not described in 'hub_pio_map'
ip27-hubio.c:32: warning: Excess function parameter 'hub' description in 'hub_pio_map'

Fixes: 4bf841ebf17a ("MIPS: SGI-IP27: get rid of compact node ids")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: lore.kernel.org/r/202311101336.BUL1JuvU-lkp@intel.com
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Paul Burton <paulburton@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: linux-mips@vger.kernel.org
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/sgi-ip27/ip27-hubio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/sgi-ip27/ip27-hubio.c b/arch/mips/sgi-ip27/ip27-hubio.c
index 8352eb6403b43..c57f0d8f32186 100644
--- a/arch/mips/sgi-ip27/ip27-hubio.c
+++ b/arch/mips/sgi-ip27/ip27-hubio.c
@@ -21,7 +21,7 @@ static int force_fire_and_forget = 1;
 /**
  * hub_pio_map	-  establish a HUB PIO mapping
  *
- * @hub:	hub to perform PIO mapping on
+ * @nasid:	nasid to perform PIO mapping on
  * @widget:	widget ID to perform PIO mapping for
  * @xtalk_addr: xtalk_address that needs to be mapped
  * @size:	size of the PIO mapping
-- 
GitLab


From 18966f7b9458d3b19412fe9dfb421ab59401bfe1 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 11 Oct 2023 09:45:54 -0700
Subject: [PATCH 1118/4076] rcu-tasks: Mark RCU Tasks accesses to
 current->rcu_tasks_idle_cpu

The task_struct structure's ->rcu_tasks_idle_cpu can be concurrently
read and written from the RCU Tasks grace-period kthread and from the
CPU on which the task_struct structure's task is running.  This commit
therefore marks the accesses appropriately.

Reported-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 kernel/rcu/tasks.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index f54d5782eca0b..732ad5b39946a 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -975,7 +975,7 @@ static void check_holdout_task(struct task_struct *t,
 	    t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
 	    !rcu_tasks_is_holdout(t) ||
 	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
-	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
+	     !is_idle_task(t) && READ_ONCE(t->rcu_tasks_idle_cpu) >= 0)) {
 		WRITE_ONCE(t->rcu_tasks_holdout, false);
 		list_del_init(&t->rcu_tasks_holdout_list);
 		put_task_struct(t);
@@ -993,7 +993,7 @@ static void check_holdout_task(struct task_struct *t,
 		 t, ".I"[is_idle_task(t)],
 		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
 		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
-		 t->rcu_tasks_idle_cpu, cpu);
+		 data_race(t->rcu_tasks_idle_cpu), cpu);
 	sched_show_task(t);
 }
 
-- 
GitLab


From 4e58aaeebb3c27993c734c99eae6881b196b1ddb Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 1 Nov 2023 18:28:38 -0700
Subject: [PATCH 1119/4076] rcu: Restrict access to RCU CPU stall notifiers

Although the RCU CPU stall notifiers can be useful for dumping state when
tracking down delicate forward-progress bugs where NUMA effects cause
cache lines to be delivered to a given CPU regularly, but always in a
state that prevents that CPU from making forward progress.  These bugs can
be detected by the RCU CPU stall-warning mechanism, but in some cases,
the stall-warnings printk()s disrupt the forward-progress bug before
any useful state can be obtained.

Unfortunately, the notifier mechanism added by commit 5b404fdabacf ("rcu:
Add RCU CPU stall notifier") can make matters worse if used at all
carelessly. For example, if the stall warning was caused by a lock not
being released, then any attempt to acquire that lock in the notifier
will hang. This will prevent not only the notifier from producing any
useful output, but it will also prevent the stall-warning message from
ever appearing.

This commit therefore hides this new RCU CPU stall notifier
mechanism under a new RCU_CPU_STALL_NOTIFIER Kconfig option that
depends on both DEBUG_KERNEL and RCU_EXPERT.  In addition, the
rcupdate.rcu_cpu_stall_notifiers=1 kernel boot parameter must also
be specified.  The RCU_CPU_STALL_NOTIFIER Kconfig option's help text
contains a warning and explains the dangers of careless use, recommending
lockless notifier code.  In addition, a WARN() is triggered each time
that an attempt is made to register a stall-warning notifier in kernels
built with CONFIG_RCU_CPU_STALL_NOTIFIER=y.

This combination of measures will keep use of this mechanism confined to
debug kernels and away from routine deployments.

[ paulmck: Apply Dan Carpenter feedback. ]

Fixes: 5b404fdabacf ("rcu: Add RCU CPU stall notifier")
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 .../admin-guide/kernel-parameters.txt         |  6 +++++
 include/linux/rcu_notifier.h                  |  6 ++---
 kernel/rcu/Kconfig.debug                      | 25 +++++++++++++++++++
 kernel/rcu/rcu.h                              |  8 +++---
 kernel/rcu/rcutorture.c                       | 12 +++++----
 kernel/rcu/tree_stall.h                       | 11 +++++++-
 kernel/rcu/update.c                           |  6 +++++
 7 files changed, 62 insertions(+), 12 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 65731b060e3fe..b72e2049c4876 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5302,6 +5302,12 @@
 			Dump ftrace buffer after reporting RCU CPU
 			stall warning.
 
+	rcupdate.rcu_cpu_stall_notifiers= [KNL]
+			Provide RCU CPU stall notifiers, but see the
+			warnings in the RCU_CPU_STALL_NOTIFIER Kconfig
+			option's help text.  TL;DR:  You almost certainly
+			do not want rcupdate.rcu_cpu_stall_notifiers.
+
 	rcupdate.rcu_cpu_stall_suppress= [KNL]
 			Suppress RCU CPU stall warning messages.
 
diff --git a/include/linux/rcu_notifier.h b/include/linux/rcu_notifier.h
index ebf371364581d..5640f024773b3 100644
--- a/include/linux/rcu_notifier.h
+++ b/include/linux/rcu_notifier.h
@@ -13,7 +13,7 @@
 #define RCU_STALL_NOTIFY_NORM	1
 #define RCU_STALL_NOTIFY_EXP	2
 
-#ifdef CONFIG_RCU_STALL_COMMON
+#if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 
 #include <linux/notifier.h>
 #include <linux/types.h>
@@ -21,12 +21,12 @@
 int rcu_stall_chain_notifier_register(struct notifier_block *n);
 int rcu_stall_chain_notifier_unregister(struct notifier_block *n);
 
-#else // #ifdef CONFIG_RCU_STALL_COMMON
+#else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 
 // No RCU CPU stall warnings in Tiny RCU.
 static inline int rcu_stall_chain_notifier_register(struct notifier_block *n) { return -EEXIST; }
 static inline int rcu_stall_chain_notifier_unregister(struct notifier_block *n) { return -ENOENT; }
 
-#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+#endif // #else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 
 #endif /* __LINUX_RCU_NOTIFIER_H */
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 2984de629f749..9b0b52e1836fa 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -105,6 +105,31 @@ config RCU_CPU_STALL_CPUTIME
 	  The boot option rcupdate.rcu_cpu_stall_cputime has the same function
 	  as this one, but will override this if it exists.
 
+config RCU_CPU_STALL_NOTIFIER
+	bool "Provide RCU CPU-stall notifiers"
+	depends on RCU_STALL_COMMON
+	depends on DEBUG_KERNEL
+	depends on RCU_EXPERT
+	default n
+	help
+	  WARNING:  You almost certainly do not want this!!!
+
+	  Enable RCU CPU-stall notifiers, which are invoked just before
+	  printing the RCU CPU stall warning.  As such, bugs in notifier
+	  callbacks can prevent stall warnings from being printed.
+	  And the whole reason that a stall warning is being printed is
+	  that something is hung up somewhere.	Therefore, the notifier
+	  callbacks must be written extremely carefully, preferably
+	  containing only lockless code.  After all, it is quite possible
+	  that the whole reason that the RCU CPU stall is happening in
+	  the first place is that someone forgot to release whatever lock
+	  that you are thinking of acquiring.  In which case, having your
+	  notifier callback acquire that lock will hang, preventing the
+	  RCU CPU stall warning from appearing.
+
+	  Say Y here if you want RCU CPU stall notifiers (you don't want them)
+	  Say N if you are unsure.
+
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index b531c33e9545b..f94f65877f2b6 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -262,6 +262,8 @@ static inline bool rcu_stall_is_suppressed_at_boot(void)
 	return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();
 }
 
+extern int rcu_cpu_stall_notifiers;
+
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_ftrace_dump;
@@ -659,10 +661,10 @@ static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
 bool rcu_cpu_beenfullyonline(int cpu);
 #endif
 
-#ifdef CONFIG_RCU_STALL_COMMON
+#if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 int rcu_stall_notifier_call_chain(unsigned long val, void *v);
-#else // #ifdef CONFIG_RCU_STALL_COMMON
+#else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 static inline int rcu_stall_notifier_call_chain(unsigned long val, void *v) { return NOTIFY_DONE; }
-#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+#endif // #else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 30fc9d34e3297..07a6a183c5556 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -2450,10 +2450,12 @@ static int rcu_torture_stall(void *args)
 	unsigned long stop_at;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
-	ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);
-	if (ret)
-		pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",
-			__func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");
+	if (rcu_cpu_stall_notifiers) {
+		ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);
+		if (ret)
+			pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",
+				__func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");
+	}
 	if (stall_cpu_holdoff > 0) {
 		VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
 		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
@@ -2497,7 +2499,7 @@ static int rcu_torture_stall(void *args)
 		cur_ops->readunlock(idx);
 	}
 	pr_alert("%s end.\n", __func__);
-	if (!ret) {
+	if (rcu_cpu_stall_notifiers && !ret) {
 		ret = rcu_stall_chain_notifier_unregister(&rcu_torture_stall_block);
 		if (ret)
 			pr_info("%s: rcu_stall_chain_notifier_unregister() returned %d.\n", __func__, ret);
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index ac8e86babe449..5d666428546b0 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -1061,6 +1061,7 @@ static int __init rcu_sysrq_init(void)
 }
 early_initcall(rcu_sysrq_init);
 
+#ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
 
 //////////////////////////////////////////////////////////////////////////////
 //
@@ -1081,7 +1082,13 @@ static ATOMIC_NOTIFIER_HEAD(rcu_cpu_stall_notifier_list);
  */
 int rcu_stall_chain_notifier_register(struct notifier_block *n)
 {
-	return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+	int rcsn = rcu_cpu_stall_notifiers;
+
+	WARN(1, "Adding %pS() to RCU stall notifier list (%s).\n", n->notifier_call,
+	     rcsn ? "possibly suppressing RCU CPU stall warnings" : "failed, so all is well");
+	if (rcsn)
+		return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+	return -EEXIST;
 }
 EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_register);
 
@@ -1115,3 +1122,5 @@ int rcu_stall_notifier_call_chain(unsigned long val, void *v)
 {
 	return atomic_notifier_call_chain(&rcu_cpu_stall_notifier_list, val, v);
 }
+
+#endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index c534d6806d3d5..46aaaa9fe3390 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -538,9 +538,15 @@ long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 EXPORT_SYMBOL_GPL(torture_sched_setaffinity);
 #endif
 
+int rcu_cpu_stall_notifiers __read_mostly; // !0 = provide stall notifiers (rarely useful)
+EXPORT_SYMBOL_GPL(rcu_cpu_stall_notifiers);
+
 #ifdef CONFIG_RCU_STALL_COMMON
 int rcu_cpu_stall_ftrace_dump __read_mostly;
 module_param(rcu_cpu_stall_ftrace_dump, int, 0644);
+#ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
+module_param(rcu_cpu_stall_notifiers, int, 0444);
+#endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
 int rcu_cpu_stall_suppress __read_mostly; // !0 = suppress stall warnings.
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
 module_param(rcu_cpu_stall_suppress, int, 0644);
-- 
GitLab


From 23d90b2404050c00c15058710d56bb46e1c5ab36 Mon Sep 17 00:00:00 2001
From: Pedro Falcato <pedro.falcato@gmail.com>
Date: Fri, 20 Oct 2023 18:30:15 +0100
Subject: [PATCH 1120/4076] rcu: Remove unused macros from rcupdate.h

ulong2long, USHORT_CMP_GE and USHORT_CMP_LT are redundant and have been
unused for quite a few releases.

Signed-off-by: Pedro Falcato <pedro.falcato@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 include/linux/rcupdate.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f7206b2623c98..aa87c82236dd9 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -34,9 +34,6 @@
 
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
-#define ulong2long(a)		(*(long *)(&(a)))
-#define USHORT_CMP_GE(a, b)	(USHRT_MAX / 2 >= (unsigned short)((a) - (b)))
-#define USHORT_CMP_LT(a, b)	(USHRT_MAX / 2 < (unsigned short)((a) - (b)))
 
 /* Exported common interfaces */
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
-- 
GitLab


From 20eb4142397cf3ec221de43f10ea149af462c572 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Wed, 4 Oct 2023 01:29:01 +0200
Subject: [PATCH 1121/4076] srcu: Remove superfluous callbacks advancing from
 srcu_gp_start()

Callbacks advancing on SRCU must be performed on two specific places:

1) On enqueue time in order to make room for the acceleration of the
   new callback.

2) On invocation time in order to move the callbacks ready to invoke.

Any other callback advancing callsite is needless. Remove the remaining
one in srcu_gp_start().

Co-developed-by: Yong He <zhuangel570@gmail.com>
Signed-off-by: Yong He <zhuangel570@gmail.com>
Co-developed-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Co-developed-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 kernel/rcu/srcutree.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 560e99ec53335..e9356a1036261 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -772,20 +772,10 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock_nmisafe);
  */
 static void srcu_gp_start(struct srcu_struct *ssp)
 {
-	struct srcu_data *sdp;
 	int state;
 
-	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
-		sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id());
-	else
-		sdp = this_cpu_ptr(ssp->sda);
 	lockdep_assert_held(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
 	WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed));
-	spin_lock_rcu_node(sdp);  /* Interrupts already disabled. */
-	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
-	WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
-	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
 	WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies);
 	WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0);
 	smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
-- 
GitLab


From 94c55b9e21979daa88e190bf971c47432a818ebe Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Wed, 4 Oct 2023 01:29:02 +0200
Subject: [PATCH 1122/4076] srcu: No need to advance/accelerate if no callback
 enqueued

While in grace period start, there is nothing to accelerate and
therefore no need to advance the callbacks either if no callback is
to be enqueued.

Spare these needless operations in this case.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 kernel/rcu/srcutree.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index e9356a1036261..2bfc8ed1eed28 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1261,9 +1261,11 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	 *     period (gp_num = X + 8). So acceleration fails.
 	 */
 	s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
-	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
-	WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp);
+	if (rhp) {
+		rcu_segcblist_advance(&sdp->srcu_cblist,
+				      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
+		WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s));
+	}
 	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
 		sdp->srcu_gp_seq_needed = s;
 		needgp = true;
-- 
GitLab


From c21357e4461f3f9c8ff93302906b5372411ee108 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Wed, 4 Oct 2023 01:29:03 +0200
Subject: [PATCH 1123/4076] srcu: Explain why callbacks invocations can't run
 concurrently

If an SRCU barrier is queued while callbacks are running and a new
callbacks invocator for the same sdp were to run concurrently, the
RCU barrier might execute too early. As this requirement is non-obvious,
make sure to keep a record.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 kernel/rcu/srcutree.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 2bfc8ed1eed28..0351a4e83529e 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1715,6 +1715,11 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
+	/*
+	 * Although this function is theoretically re-entrant, concurrent
+	 * callbacks invocation is disallowed to avoid executing an SRCU barrier
+	 * too early.
+	 */
 	if (sdp->srcu_cblist_invoking ||
 	    !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
 		spin_unlock_irq_rcu_node(sdp);
@@ -1745,6 +1750,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	sdp->srcu_cblist_invoking = false;
 	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
 	spin_unlock_irq_rcu_node(sdp);
+	/* An SRCU barrier or callbacks from previous nesting work pending */
 	if (more)
 		srcu_schedule_cbs_sdp(sdp, 0);
 }
-- 
GitLab


From 8596ba324356a7392a6639024de8c9ae7a9fce92 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 29 Nov 2023 14:35:40 -0800
Subject: [PATCH 1124/4076] perf stat: Fix help message for
 --metric-no-threshold option

Copy-paste error led to help message for metric-no-threshold repeating
that of metric-no-merge.

Fixes: 1fd09e299bdd434b ("perf metric: Add --metric-no-threshold option")
Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231129223540.2247030-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d22228eddccbf..0bfa70791cfcf 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1255,7 +1255,7 @@ static struct option stat_options[] = {
 	OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge,
 		       "don't try to share events between metrics in a group"),
 	OPT_BOOLEAN(0, "metric-no-threshold", &stat_config.metric_no_threshold,
-		       "don't try to share events between metrics in a group  "),
+		       "disable adding events for the metric threshold calculation"),
 	OPT_BOOLEAN(0, "topdown", &topdown_run,
 			"measure top-down statistics"),
 	OPT_UINTEGER(0, "td-level", &stat_config.topdown_level,
-- 
GitLab


From 383da0c7f25428de5ad09dc2cfed7cd43c4fb6ba Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:57:54 +0200
Subject: [PATCH 1125/4076] pinctrl: core: Add a convenient define
 PINCTRL_GROUP_DESC()

Add PINCTRL_GROUP_DESC() macro for inline use.

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c | 5 +----
 drivers/pinctrl/core.h | 9 +++++++++
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index d678effcedd88..540221dc56179 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -658,10 +658,7 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 	if (!group)
 		return -ENOMEM;
 
-	group->name = name;
-	group->pins = pins;
-	group->num_pins = num_pins;
-	group->data = data;
+	*group = PINCTRL_GROUP_DESC(name, pins, num_pins, data);
 
 	error = radix_tree_insert(&pctldev->pin_group_tree, selector, group);
 	if (error)
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 8ef4b536bca50..bf971e6a78464 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -208,6 +208,15 @@ struct group_desc {
 	void *data;
 };
 
+/* Convenience macro to define a generic pin group descriptor */
+#define PINCTRL_GROUP_DESC(_name, _pins, _num_pins, _data)	\
+(struct group_desc) {						\
+	.name = _name,						\
+	.pins = _pins,						\
+	.num_pins = _num_pins,					\
+	.data = _data,						\
+}
+
 int pinctrl_generic_get_group_count(struct pinctrl_dev *pctldev);
 
 const char *pinctrl_generic_get_group_name(struct pinctrl_dev *pctldev,
-- 
GitLab


From bb5eace1562fcef3c7ac9d0bd3e01af1187e46d0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:57:55 +0200
Subject: [PATCH 1126/4076] pinctrl: mediatek: Use C99 initializers in
 PINCTRL_PIN_GROUP()

For the better flexibility use C99 initializers in PINCTRL_PIN_GROUP().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mediatek/pinctrl-moore.h | 12 ++++++------
 drivers/pinctrl/mediatek/pinctrl-paris.h | 12 ++++++------
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/pinctrl/mediatek/pinctrl-moore.h b/drivers/pinctrl/mediatek/pinctrl-moore.h
index e1b4b82b9d3db..36ee0021cf7ed 100644
--- a/drivers/pinctrl/mediatek/pinctrl-moore.h
+++ b/drivers/pinctrl/mediatek/pinctrl-moore.h
@@ -37,12 +37,12 @@
 		.funcs = NULL,				\
 	}
 
-#define PINCTRL_PIN_GROUP(name, id)			\
-	{						\
-		name,					\
-		id##_pins,				\
-		ARRAY_SIZE(id##_pins),			\
-		id##_funcs,				\
+#define PINCTRL_PIN_GROUP(_name_, id)							\
+	{										\
+		.name = _name_,								\
+		.pins = id##_pins,							\
+		.num_pins = ARRAY_SIZE(id##_pins),					\
+		.data = id##_funcs,							\
 	}
 
 int mtk_moore_pinctrl_probe(struct platform_device *pdev,
diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.h b/drivers/pinctrl/mediatek/pinctrl-paris.h
index 8762ac5993292..5c4e5b74e43e2 100644
--- a/drivers/pinctrl/mediatek/pinctrl-paris.h
+++ b/drivers/pinctrl/mediatek/pinctrl-paris.h
@@ -49,12 +49,12 @@
 			__VA_ARGS__, { } },				\
 	}
 
-#define PINCTRL_PIN_GROUP(name, id)			\
-	{						\
-		name,					\
-		id##_pins,				\
-		ARRAY_SIZE(id##_pins),			\
-		id##_funcs,				\
+#define PINCTRL_PIN_GROUP(_name_, id)							\
+	{										\
+		.name = _name_,								\
+		.pins = id##_pins,							\
+		.num_pins = ARRAY_SIZE(id##_pins),					\
+		.data = id##_funcs,							\
 	}
 
 int mtk_paris_pinctrl_probe(struct platform_device *pdev);
-- 
GitLab


From b0f24e021d58d74b83857b9d5c468bcda3785572 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:57:56 +0200
Subject: [PATCH 1127/4076] pinctrl: ingenic: Use C99 initializers in
 PINCTRL_PIN_GROUP()

For the better flexibility use C99 initializers in PINCTRL_PIN_GROUP().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-ingenic.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index ee718f6e25566..f5661dcdedf53 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -82,16 +82,21 @@
 #define PINS_PER_GPIO_CHIP			32
 #define JZ4730_PINS_PER_PAIRED_REG	16
 
-#define INGENIC_PIN_GROUP_FUNCS(name, id, funcs)		\
-	{						\
-		name,					\
-		id##_pins,				\
-		ARRAY_SIZE(id##_pins),			\
-		funcs,					\
+#define INGENIC_PIN_GROUP_FUNCS(_name_, id, funcs)					\
+	{										\
+		.name = _name_,								\
+		.pins = id##_pins,							\
+		.num_pins = ARRAY_SIZE(id##_pins),					\
+		.data = funcs,								\
 	}
 
-#define INGENIC_PIN_GROUP(name, id, func)		\
-	INGENIC_PIN_GROUP_FUNCS(name, id, (void *)(func))
+#define INGENIC_PIN_GROUP(_name_, id, func)						\
+	{										\
+		.name = _name_,								\
+		.pins = id##_pins,							\
+		.num_pins = ARRAY_SIZE(id##_pins),					\
+		.data = (void *)func,							\
+	}
 
 enum jz_version {
 	ID_JZ4730,
-- 
GitLab


From 85174ad7c30fca29a354221e01fad82c0d00d644 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:57:57 +0200
Subject: [PATCH 1128/4076] pinctrl: core: Embed struct pingroup into struct
 group_desc

struct group_desc is a particular version of the struct pingroup
with associated opaque data. Start switching pin control core and
drivers to use it explicitly.

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c | 15 ++++++++++++---
 drivers/pinctrl/core.h |  5 +++++
 2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 540221dc56179..8a457b512706e 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -557,7 +557,10 @@ const char *pinctrl_generic_get_group_name(struct pinctrl_dev *pctldev,
 	if (!group)
 		return NULL;
 
-	return group->name;
+	if (group->name)
+		return group->name;
+
+	return group->grp.name;
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_get_group_name);
 
@@ -583,8 +586,14 @@ int pinctrl_generic_get_group_pins(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 	}
 
-	*pins = group->pins;
-	*num_pins = group->num_pins;
+	if (group->pins) {
+		*pins = group->pins;
+		*num_pins = group->num_pins;
+		return 0;
+	}
+
+	*pins = group->grp.pins;
+	*num_pins = group->grp.npins;
 
 	return 0;
 }
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index bf971e6a78464..a3b75ec7b54b4 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -194,14 +194,18 @@ struct pinctrl_maps {
 
 #ifdef CONFIG_GENERIC_PINCTRL_GROUPS
 
+#include <linux/pinctrl/pinctrl.h>
+
 /**
  * struct group_desc - generic pin group descriptor
+ * @grp: generic data of the pin group (name and pins)
  * @name: name of the pin group
  * @pins: array of pins that belong to the group
  * @num_pins: number of pins in the group
  * @data: pin controller driver specific data
  */
 struct group_desc {
+	struct pingroup grp;
 	const char *name;
 	const unsigned int *pins;
 	int num_pins;
@@ -211,6 +215,7 @@ struct group_desc {
 /* Convenience macro to define a generic pin group descriptor */
 #define PINCTRL_GROUP_DESC(_name, _pins, _num_pins, _data)	\
 (struct group_desc) {						\
+	.grp = PINCTRL_PINGROUP(_name, _pins, _num_pins),	\
 	.name = _name,						\
 	.pins = _pins,						\
 	.num_pins = _num_pins,					\
-- 
GitLab


From 2a0674f25bf0f08e5756b5287205a30252b48796 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:57:58 +0200
Subject: [PATCH 1129/4076] pinctrl: bcm: Convert to use grp member

Convert drivers to use grp member embedded in struct group_desc,
because other members will be removed to avoid duplication and
desynchronisation of the generic pin group description.

Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-6-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/bcm/pinctrl-ns.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/bcm/pinctrl-ns.c b/drivers/pinctrl/bcm/pinctrl-ns.c
index d099a7f25f64c..6bb2b461950be 100644
--- a/drivers/pinctrl/bcm/pinctrl-ns.c
+++ b/drivers/pinctrl/bcm/pinctrl-ns.c
@@ -171,8 +171,8 @@ static int ns_pinctrl_set_mux(struct pinctrl_dev *pctrl_dev,
 	if (!group)
 		return -EINVAL;
 
-	for (i = 0; i < group->num_pins; i++)
-		unset |= BIT(group->pins[i]);
+	for (i = 0; i < group->grp.npins; i++)
+		unset |= BIT(group->grp.pins[i]);
 
 	tmp = readl(ns_pinctrl->base);
 	tmp &= ~unset;
-- 
GitLab


From 7e976117b1859fc849842b68935a74854157217c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:57:59 +0200
Subject: [PATCH 1130/4076] pinctrl: equilibrium: Convert to use grp member

Convert drivers to use grp member embedded in struct group_desc,
because other members will be removed to avoid duplication and
desynchronisation of the generic pin group description.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-7-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-equilibrium.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index 4ebae516d1b1e..6e1be38865c32 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -331,8 +331,8 @@ static int eqbr_pinmux_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	pinmux = grp->data;
-	for (i = 0; i < grp->num_pins; i++)
-		eqbr_set_pin_mux(pctl, pinmux[i], grp->pins[i]);
+	for (i = 0; i < grp->grp.npins; i++)
+		eqbr_set_pin_mux(pctl, pinmux[i], grp->grp.pins[i]);
 
 	return 0;
 }
-- 
GitLab


From 390270f25b414fd54b307cd68851b36b52f952b5 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:58:00 +0200
Subject: [PATCH 1131/4076] pinctrl: imx: Convert to use grp member

Convert drivers to use grp member embedded in struct group_desc,
because other members will be removed to avoid duplication and
desynchronisation of the generic pin group description.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-8-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/pinctrl-imx.c | 31 +++++++++++--------------
 1 file changed, 14 insertions(+), 17 deletions(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 28164b04b1bed..2d3d80921c0d1 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -42,7 +42,7 @@ static inline const struct group_desc *imx_pinctrl_find_group_by_name(
 
 	for (i = 0; i < pctldev->num_groups; i++) {
 		grp = pinctrl_generic_get_group(pctldev, i);
-		if (grp && !strcmp(grp->name, name))
+		if (grp && !strcmp(grp->grp.name, name))
 			break;
 	}
 
@@ -79,9 +79,9 @@ static int imx_dt_node_to_map(struct pinctrl_dev *pctldev,
 	}
 
 	if (info->flags & IMX_USE_SCU) {
-		map_num += grp->num_pins;
+		map_num += grp->grp.npins;
 	} else {
-		for (i = 0; i < grp->num_pins; i++) {
+		for (i = 0; i < grp->grp.npins; i++) {
 			pin = &((struct imx_pin *)(grp->data))[i];
 			if (!(pin->conf.mmio.config & IMX_NO_PAD_CTL))
 				map_num++;
@@ -109,7 +109,7 @@ static int imx_dt_node_to_map(struct pinctrl_dev *pctldev,
 
 	/* create config map */
 	new_map++;
-	for (i = j = 0; i < grp->num_pins; i++) {
+	for (i = j = 0; i < grp->grp.npins; i++) {
 		pin = &((struct imx_pin *)(grp->data))[i];
 
 		/*
@@ -263,10 +263,10 @@ static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
 	if (!func)
 		return -EINVAL;
 
-	npins = grp->num_pins;
+	npins = grp->grp.npins;
 
 	dev_dbg(ipctl->dev, "enable function %s group %s\n",
-		func->name, grp->name);
+		func->name, grp->grp.name);
 
 	for (i = 0; i < npins; i++) {
 		/*
@@ -423,7 +423,7 @@ static void imx_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 	if (!grp)
 		return;
 
-	for (i = 0; i < grp->num_pins; i++) {
+	for (i = 0; i < grp->grp.npins; i++) {
 		struct imx_pin *pin = &((struct imx_pin *)(grp->data))[i];
 
 		name = pin_get_name(pctldev, pin->pin);
@@ -526,7 +526,7 @@ static int imx_pinctrl_parse_groups(struct device_node *np,
 		pin_size = FSL_PIN_SIZE;
 
 	/* Initialise group */
-	grp->name = np->name;
+	grp->grp.name = np->name;
 
 	/*
 	 * the binding format is fsl,pins = <PIN_FUNC_ID CONFIG ...>,
@@ -554,19 +554,17 @@ static int imx_pinctrl_parse_groups(struct device_node *np,
 		return -EINVAL;
 	}
 
-	grp->num_pins = size / pin_size;
-	grp->data = devm_kcalloc(ipctl->dev,
-				 grp->num_pins, sizeof(struct imx_pin),
-				 GFP_KERNEL);
+	grp->grp.npins = size / pin_size;
+	grp->data = devm_kcalloc(ipctl->dev, grp->grp.npins, sizeof(*pin), GFP_KERNEL);
 	if (!grp->data)
 		return -ENOMEM;
 
-	pins = devm_kcalloc(ipctl->dev, grp->num_pins, sizeof(*pins), GFP_KERNEL);
+	pins = devm_kcalloc(ipctl->dev, grp->grp.npins, sizeof(*pins), GFP_KERNEL);
 	if (!pins)
 		return -ENOMEM;
-	grp->pins = pins;
+	grp->grp.pins = pins;
 
-	for (i = 0; i < grp->num_pins; i++) {
+	for (i = 0; i < grp->grp.npins; i++) {
 		pin = &((struct imx_pin *)(grp->data))[i];
 		if (info->flags & IMX_USE_SCU)
 			info->imx_pinctrl_parse_pin(ipctl, &pins[i], pin, &list);
@@ -613,8 +611,7 @@ static int imx_pinctrl_parse_functions(struct device_node *np,
 
 	i = 0;
 	for_each_child_of_node(np, child) {
-		grp = devm_kzalloc(ipctl->dev, sizeof(struct group_desc),
-				   GFP_KERNEL);
+		grp = devm_kzalloc(ipctl->dev, sizeof(*grp), GFP_KERNEL);
 		if (!grp) {
 			of_node_put(child);
 			return -ENOMEM;
-- 
GitLab


From 10ce59c6bb51c37759147948a87b9e7debcc40ee Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:58:01 +0200
Subject: [PATCH 1132/4076] pinctrl: ingenic: Convert to use grp member

Convert drivers to use grp member embedded in struct group_desc,
because other members will be removed to avoid duplication and
desynchronisation of the generic pin group description.

Acked-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-9-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-ingenic.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index f5661dcdedf53..bc6358a686fcd 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -84,17 +84,13 @@
 
 #define INGENIC_PIN_GROUP_FUNCS(_name_, id, funcs)					\
 	{										\
-		.name = _name_,								\
-		.pins = id##_pins,							\
-		.num_pins = ARRAY_SIZE(id##_pins),					\
+		.grp = PINCTRL_PINGROUP(_name_, id##_pins, ARRAY_SIZE(id##_pins)),	\
 		.data = funcs,								\
 	}
 
 #define INGENIC_PIN_GROUP(_name_, id, func)						\
 	{										\
-		.name = _name_,								\
-		.pins = id##_pins,							\
-		.num_pins = ARRAY_SIZE(id##_pins),					\
+		.grp = PINCTRL_PINGROUP(_name_, id##_pins, ARRAY_SIZE(id##_pins)),	\
 		.data = (void *)func,							\
 	}
 
@@ -3766,17 +3762,17 @@ static int ingenic_pinmux_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	dev_dbg(pctldev->dev, "enable function %s group %s\n",
-		func->name, grp->name);
+		func->name, grp->grp.name);
 
 	mode = (uintptr_t)grp->data;
 	if (mode <= 3) {
-		for (i = 0; i < grp->num_pins; i++)
-			ingenic_pinmux_set_pin_fn(jzpc, grp->pins[i], mode);
+		for (i = 0; i < grp->grp.npins; i++)
+			ingenic_pinmux_set_pin_fn(jzpc, grp->grp.pins[i], mode);
 	} else {
 		pin_modes = grp->data;
 
-		for (i = 0; i < grp->num_pins; i++)
-			ingenic_pinmux_set_pin_fn(jzpc, grp->pins[i], pin_modes[i]);
+		for (i = 0; i < grp->grp.npins; i++)
+			ingenic_pinmux_set_pin_fn(jzpc, grp->grp.pins[i], pin_modes[i]);
 	}
 
 	return 0;
@@ -4303,12 +4299,12 @@ static int __init ingenic_pinctrl_probe(struct platform_device *pdev)
 
 	for (i = 0; i < chip_info->num_groups; i++) {
 		const struct group_desc *group = &chip_info->groups[i];
+		const struct pingroup *grp = &group->grp;
 
-		err = pinctrl_generic_add_group(jzpc->pctl, group->name,
-				group->pins, group->num_pins, group->data);
+		err = pinctrl_generic_add_group(jzpc->pctl, grp->name, grp->pins, grp->npins,
+						group->data);
 		if (err < 0) {
-			dev_err(dev, "Failed to register group %s\n",
-					group->name);
+			dev_err(dev, "Failed to register group %s\n", grp->name);
 			return err;
 		}
 	}
-- 
GitLab


From ffc1945e1958634860a95dafb1821d10ea32e033 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:58:02 +0200
Subject: [PATCH 1133/4076] pinctrl: keembay: Convert to use grp member

Convert drivers to use grp member embedded in struct group_desc,
because other members will be removed to avoid duplication and
desynchronisation of the generic pin group description.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-10-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-keembay.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-keembay.c b/drivers/pinctrl/pinctrl-keembay.c
index 87d328853ae47..b1349ee22799d 100644
--- a/drivers/pinctrl/pinctrl-keembay.c
+++ b/drivers/pinctrl/pinctrl-keembay.c
@@ -945,7 +945,7 @@ static int keembay_set_mux(struct pinctrl_dev *pctldev, unsigned int fun_sel,
 		return -EINVAL;
 
 	/* Change modes for pins in the selected group */
-	pin = *grp->pins;
+	pin = *grp->grp.pins;
 	pin_mode = *(u8 *)(func->data);
 
 	val = keembay_read_reg(kpc->base1 + KEEMBAY_GPIO_MODE, pin);
-- 
GitLab


From a1cf1a5f9b60fbccd96b24ec295e50a84cc0c503 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:58:03 +0200
Subject: [PATCH 1134/4076] pinctrl: mediatek: Convert to use grp member

Convert drivers to use grp member embedded in struct group_desc,
because other members will be removed to avoid duplication and
desynchronisation of the generic pin group description.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-11-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mediatek/pinctrl-moore.c | 13 ++++++-------
 drivers/pinctrl/mediatek/pinctrl-moore.h |  4 +---
 drivers/pinctrl/mediatek/pinctrl-paris.h |  4 +---
 3 files changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/pinctrl/mediatek/pinctrl-moore.c b/drivers/pinctrl/mediatek/pinctrl-moore.c
index c3d59eddd994a..d972584c0519b 100644
--- a/drivers/pinctrl/mediatek/pinctrl-moore.c
+++ b/drivers/pinctrl/mediatek/pinctrl-moore.c
@@ -56,12 +56,12 @@ static int mtk_pinmux_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	dev_dbg(pctldev->dev, "enable function %s group %s\n",
-		func->name, grp->name);
+		func->name, grp->grp.name);
 
-	for (i = 0; i < grp->num_pins; i++) {
+	for (i = 0; i < grp->grp.npins; i++) {
 		const struct mtk_pin_desc *desc;
 		int *pin_modes = grp->data;
-		int pin = grp->pins[i];
+		int pin = grp->grp.pins[i];
 
 		desc = (const struct mtk_pin_desc *)&hw->soc->pins[pin];
 		if (!desc->name)
@@ -602,13 +602,12 @@ static int mtk_build_groups(struct mtk_pinctrl *hw)
 
 	for (i = 0; i < hw->soc->ngrps; i++) {
 		const struct group_desc *group = hw->soc->grps + i;
+		const struct pingroup *grp = &group->grp;
 
-		err = pinctrl_generic_add_group(hw->pctrl, group->name,
-						group->pins, group->num_pins,
+		err = pinctrl_generic_add_group(hw->pctrl, grp->name, grp->pins, grp->npins,
 						group->data);
 		if (err < 0) {
-			dev_err(hw->dev, "Failed to register group %s\n",
-				group->name);
+			dev_err(hw->dev, "Failed to register group %s\n", grp->name);
 			return err;
 		}
 	}
diff --git a/drivers/pinctrl/mediatek/pinctrl-moore.h b/drivers/pinctrl/mediatek/pinctrl-moore.h
index 36ee0021cf7ed..e0313e7a1fe00 100644
--- a/drivers/pinctrl/mediatek/pinctrl-moore.h
+++ b/drivers/pinctrl/mediatek/pinctrl-moore.h
@@ -39,9 +39,7 @@
 
 #define PINCTRL_PIN_GROUP(_name_, id)							\
 	{										\
-		.name = _name_,								\
-		.pins = id##_pins,							\
-		.num_pins = ARRAY_SIZE(id##_pins),					\
+		.grp = PINCTRL_PINGROUP(_name_, id##_pins, ARRAY_SIZE(id##_pins)),	\
 		.data = id##_funcs,							\
 	}
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.h b/drivers/pinctrl/mediatek/pinctrl-paris.h
index 5c4e5b74e43e2..948ce126aa0cb 100644
--- a/drivers/pinctrl/mediatek/pinctrl-paris.h
+++ b/drivers/pinctrl/mediatek/pinctrl-paris.h
@@ -51,9 +51,7 @@
 
 #define PINCTRL_PIN_GROUP(_name_, id)							\
 	{										\
-		.name = _name_,								\
-		.pins = id##_pins,							\
-		.num_pins = ARRAY_SIZE(id##_pins),					\
+		.grp = PINCTRL_PINGROUP(_name_,id##_pins, ARRAY_SIZE(id##_pins)),	\
 		.data = id##_funcs,							\
 	}
 
-- 
GitLab


From fc7d3b60a8fd9f7ee07f7f6cb015819da18d0113 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:58:04 +0200
Subject: [PATCH 1135/4076] pinctrl: renesas: Convert to use grp member

Convert drivers to use grp member embedded in struct group_desc,
because other members will be removed to avoid duplication and
desynchronisation of the generic pin group description.

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-12-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/renesas/pinctrl-rza1.c  |  2 +-
 drivers/pinctrl/renesas/pinctrl-rza2.c  | 10 +++++-----
 drivers/pinctrl/renesas/pinctrl-rzg2l.c |  4 ++--
 drivers/pinctrl/renesas/pinctrl-rzv2m.c |  4 ++--
 4 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c
index f43f1196fea86..edcbe7c9ad565 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza1.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza1.c
@@ -1131,7 +1131,7 @@ static int rza1_set_mux(struct pinctrl_dev *pctldev, unsigned int selector,
 		return -EINVAL;
 
 	mux_confs = (struct rza1_mux_conf *)func->data;
-	for (i = 0; i < grp->num_pins; ++i) {
+	for (i = 0; i < grp->grp.npins; ++i) {
 		int ret;
 
 		ret = rza1_pin_mux_single(rza1_pctl, &mux_confs[i]);
diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c
index 990b96d459671..af689d7c117f3 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza2.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza2.c
@@ -447,15 +447,15 @@ static int rza2_set_mux(struct pinctrl_dev *pctldev, unsigned int selector,
 
 	psel_val = func->data;
 
-	for (i = 0; i < grp->num_pins; ++i) {
+	for (i = 0; i < grp->grp.npins; ++i) {
 		dev_dbg(priv->dev, "Setting P%c_%d to PSEL=%d\n",
-			port_names[RZA2_PIN_ID_TO_PORT(grp->pins[i])],
-			RZA2_PIN_ID_TO_PIN(grp->pins[i]),
+			port_names[RZA2_PIN_ID_TO_PORT(grp->grp.pins[i])],
+			RZA2_PIN_ID_TO_PIN(grp->grp.pins[i]),
 			psel_val[i]);
 		rza2_set_pin_function(
 			priv->base,
-			RZA2_PIN_ID_TO_PORT(grp->pins[i]),
-			RZA2_PIN_ID_TO_PIN(grp->pins[i]),
+			RZA2_PIN_ID_TO_PORT(grp->grp.pins[i]),
+			RZA2_PIN_ID_TO_PIN(grp->grp.pins[i]),
 			psel_val[i]);
 	}
 
diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 68fcc2a4efbc7..f01aa51b00c4e 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -283,9 +283,9 @@ static int rzg2l_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	psel_val = func->data;
-	pins = group->pins;
+	pins = group->grp.pins;
 
-	for (i = 0; i < group->num_pins; i++) {
+	for (i = 0; i < group->grp.npins; i++) {
 		unsigned int *pin_data = pctrl->desc.pins[pins[i]].drv_data;
 		u32 off = RZG2L_PIN_CFG_TO_PORT_OFFSET(*pin_data);
 		u32 pin = RZG2L_PIN_ID_TO_PIN(pins[i]);
diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
index eb304fab17968..0767a5ac23e08 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
@@ -175,9 +175,9 @@ static int rzv2m_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	psel_val = func->data;
-	pins = group->pins;
+	pins = group->grp.pins;
 
-	for (i = 0; i < group->num_pins; i++) {
+	for (i = 0; i < group->grp.npins; i++) {
 		dev_dbg(pctrl->dev, "port:%u pin: %u PSEL:%u\n",
 			RZV2M_PIN_ID_TO_PORT(pins[i]), RZV2M_PIN_ID_TO_PIN(pins[i]),
 			psel_val[i]);
-- 
GitLab


From fcbcfe5cb7eab04df04df5228524e0e62d1c51c9 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:58:05 +0200
Subject: [PATCH 1136/4076] pinctrl: starfive: Convert to use grp member

Convert drivers to use grp member embedded in struct group_desc,
because other members will be removed to avoid duplication and
desynchronisation of the generic pin group description.

Reviewed-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-13-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c | 8 ++++----
 drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
index ea70b8c61679f..21bfbbaede723 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
@@ -654,7 +654,7 @@ static int starfive_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	pinmux = group->data;
-	for (i = 0; i < group->num_pins; i++) {
+	for (i = 0; i < group->grp.npins; i++) {
 		u32 v = pinmux[i];
 		unsigned int gpio = starfive_pinmux_to_gpio(v);
 		u32 dout = starfive_pinmux_to_dout(v);
@@ -797,7 +797,7 @@ static int starfive_pinconf_group_get(struct pinctrl_dev *pctldev,
 	if (!group)
 		return -EINVAL;
 
-	return starfive_pinconf_get(pctldev, group->pins[0], config);
+	return starfive_pinconf_get(pctldev, group->grp.pins[0], config);
 }
 
 static int starfive_pinconf_group_set(struct pinctrl_dev *pctldev,
@@ -876,8 +876,8 @@ static int starfive_pinconf_group_set(struct pinctrl_dev *pctldev,
 		}
 	}
 
-	for (i = 0; i < group->num_pins; i++)
-		starfive_padctl_rmw(sfp, group->pins[i], mask, value);
+	for (i = 0; i < group->grp.npins; i++)
+		starfive_padctl_rmw(sfp, group->grp.pins[i], mask, value);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
index 9d71e8c133102..60160965cd29a 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
@@ -307,7 +307,7 @@ static int jh7110_set_mux(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	pinmux = group->data;
-	for (i = 0; i < group->num_pins; i++) {
+	for (i = 0; i < group->grp.npins; i++) {
 		u32 v = pinmux[i];
 
 		if (info->jh7110_set_one_pin_mux)
@@ -437,7 +437,7 @@ static int jh7110_pinconf_group_get(struct pinctrl_dev *pctldev,
 	if (!group)
 		return -EINVAL;
 
-	return jh7110_pinconf_get(pctldev, group->pins[0], config);
+	return jh7110_pinconf_get(pctldev, group->grp.pins[0], config);
 }
 
 static int jh7110_pinconf_group_set(struct pinctrl_dev *pctldev,
@@ -508,8 +508,8 @@ static int jh7110_pinconf_group_set(struct pinctrl_dev *pctldev,
 		}
 	}
 
-	for (i = 0; i < group->num_pins; i++)
-		jh7110_padcfg_rmw(sfp, group->pins[i], mask, value);
+	for (i = 0; i < group->grp.npins; i++)
+		jh7110_padcfg_rmw(sfp, group->grp.pins[i], mask, value);
 
 	return 0;
 }
-- 
GitLab


From db4a9133511c4a325be04644bf8754ffdfc550bc Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 20:58:06 +0200
Subject: [PATCH 1137/4076] pinctrl: core: Remove unused members from struct
 group_desc

All drivers are converted to use embedded struct pingroup.
Remove unused members from struct group_desc.

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231211190321.307330-14-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c | 9 ---------
 drivers/pinctrl/core.h | 9 ---------
 2 files changed, 18 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 8a457b512706e..d27d5a04b1a8c 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -557,9 +557,6 @@ const char *pinctrl_generic_get_group_name(struct pinctrl_dev *pctldev,
 	if (!group)
 		return NULL;
 
-	if (group->name)
-		return group->name;
-
 	return group->grp.name;
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_get_group_name);
@@ -586,12 +583,6 @@ int pinctrl_generic_get_group_pins(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 	}
 
-	if (group->pins) {
-		*pins = group->pins;
-		*num_pins = group->num_pins;
-		return 0;
-	}
-
 	*pins = group->grp.pins;
 	*num_pins = group->grp.npins;
 
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index a3b75ec7b54b4..837fd5bd903df 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -199,16 +199,10 @@ struct pinctrl_maps {
 /**
  * struct group_desc - generic pin group descriptor
  * @grp: generic data of the pin group (name and pins)
- * @name: name of the pin group
- * @pins: array of pins that belong to the group
- * @num_pins: number of pins in the group
  * @data: pin controller driver specific data
  */
 struct group_desc {
 	struct pingroup grp;
-	const char *name;
-	const unsigned int *pins;
-	int num_pins;
 	void *data;
 };
 
@@ -216,9 +210,6 @@ struct group_desc {
 #define PINCTRL_GROUP_DESC(_name, _pins, _num_pins, _data)	\
 (struct group_desc) {						\
 	.grp = PINCTRL_PINGROUP(_name, _pins, _num_pins),	\
-	.name = _name,						\
-	.pins = _pins,						\
-	.num_pins = _num_pins,					\
 	.data = _data,						\
 }
 
-- 
GitLab


From 7803680964c025f598f827b7ea7433467ef21a56 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 5 Dec 2023 15:12:04 -0800
Subject: [PATCH 1138/4076] extcon: qcom-spmi-misc: don't use kernel-doc marker
 for comment

Do not use "/**" for non-kernel-doc comments. This prevents a warning
from scripts/kernel-doc:

warning: expecting prototype for extcon(). Prototype was for USB_ID_DEBOUNCE_MS() instead

Link: https://lore.kernel.org/lkml/20231205231204.1130-1-rdunlap@infradead.org/
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/extcon/extcon-qcom-spmi-misc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/extcon/extcon-qcom-spmi-misc.c b/drivers/extcon/extcon-qcom-spmi-misc.c
index f72e90ceca53d..53de581a393a3 100644
--- a/drivers/extcon/extcon-qcom-spmi-misc.c
+++ b/drivers/extcon/extcon-qcom-spmi-misc.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * extcon-qcom-spmi-misc.c - Qualcomm USB extcon driver to support USB ID
  *			and VBUS detection based on extcon-usb-gpio.c.
  *
-- 
GitLab


From 02db1749f30fb88638e19fb16f2470724529eb81 Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Mon, 11 Dec 2023 23:17:57 +0100
Subject: [PATCH 1139/4076] Input: omap4-keypad - react on keypresses if device
 is runtime-suspended

According to SWPU235AB, table 26-6, fclk is required to generate events
at least on OMAP4460, so keep fclk enabled all the time the device
is opened.

Suggested-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231211221757.517427-1-andreas@kemnade.info
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/omap4-keypad.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c
index d3f8688fdd9c3..040b340995d89 100644
--- a/drivers/input/keyboard/omap4-keypad.c
+++ b/drivers/input/keyboard/omap4-keypad.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 #include <linux/errno.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -83,6 +84,7 @@ struct omap4_keypad {
 	bool no_autorepeat;
 	u64 keys;
 	unsigned short *keymap;
+	struct clk *fck;
 };
 
 static int kbd_readl(struct omap4_keypad *keypad_data, u32 offset)
@@ -209,6 +211,10 @@ static int omap4_keypad_open(struct input_dev *input)
 	if (error)
 		return error;
 
+	error = clk_prepare_enable(keypad_data->fck);
+	if (error)
+		goto out;
+
 	disable_irq(keypad_data->irq);
 
 	kbd_writel(keypad_data, OMAP4_KBD_CTRL,
@@ -226,10 +232,11 @@ static int omap4_keypad_open(struct input_dev *input)
 
 	enable_irq(keypad_data->irq);
 
+out:
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
-	return 0;
+	return error;
 }
 
 static void omap4_keypad_stop(struct omap4_keypad *keypad_data)
@@ -258,6 +265,7 @@ static void omap4_keypad_close(struct input_dev *input)
 	disable_irq(keypad_data->irq);
 	omap4_keypad_stop(keypad_data);
 	enable_irq(keypad_data->irq);
+	clk_disable_unprepare(keypad_data->fck);
 
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
@@ -356,6 +364,11 @@ static int omap4_keypad_probe(struct platform_device *pdev)
 	}
 
 	keypad_data->irq = irq;
+	keypad_data->fck = devm_clk_get(&pdev->dev, "fck");
+	if (IS_ERR(keypad_data->fck))
+		return dev_err_probe(&pdev->dev, PTR_ERR(keypad_data->fck),
+				     "unable to get fck");
+
 	mutex_init(&keypad_data->lock);
 	platform_set_drvdata(pdev, keypad_data);
 
-- 
GitLab


From 97a7d8950f676862aa5d26c50cbcdeb6304f31be Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 10 Dec 2023 18:20:57 +0100
Subject: [PATCH 1140/4076] Input: xpad - remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/a3e30e30f18cc5d6f032c8013ce9d900c8e223e5.1702228806.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index ede380551e55c..1a58629c12b9a 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1665,7 +1665,7 @@ static int xpad_led_probe(struct usb_xpad *xpad)
 	if (!led)
 		return -ENOMEM;
 
-	xpad->pad_nr = ida_simple_get(&xpad_pad_seq, 0, 0, GFP_KERNEL);
+	xpad->pad_nr = ida_alloc(&xpad_pad_seq, GFP_KERNEL);
 	if (xpad->pad_nr < 0) {
 		error = xpad->pad_nr;
 		goto err_free_mem;
@@ -1688,7 +1688,7 @@ static int xpad_led_probe(struct usb_xpad *xpad)
 	return 0;
 
 err_free_id:
-	ida_simple_remove(&xpad_pad_seq, xpad->pad_nr);
+	ida_free(&xpad_pad_seq, xpad->pad_nr);
 err_free_mem:
 	kfree(led);
 	xpad->led = NULL;
@@ -1701,7 +1701,7 @@ static void xpad_led_disconnect(struct usb_xpad *xpad)
 
 	if (xpad_led) {
 		led_classdev_unregister(&xpad_led->led_cdev);
-		ida_simple_remove(&xpad_pad_seq, xpad->pad_nr);
+		ida_free(&xpad_pad_seq, xpad->pad_nr);
 		kfree(xpad_led);
 	}
 }
-- 
GitLab


From 8f23f5dba6b4693448144bde4dd6f537543442c2 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Fri, 27 Oct 2023 08:05:20 +0800
Subject: [PATCH 1141/4076] iommu: Change kconfig around IOMMU_SVA

Linus suggested that the kconfig here is confusing:

https://lore.kernel.org/all/CAHk-=wgUiAtiszwseM1p2fCJ+sC4XWQ+YN4TanFhUgvUqjr9Xw@mail.gmail.com/

Let's break it into three kconfigs controlling distinct things:

 - CONFIG_IOMMU_MM_DATA controls if the mm_struct has the additional
   fields for the IOMMU. Currently only PASID, but later patches store
   a struct iommu_mm_data *

 - CONFIG_ARCH_HAS_CPU_PASID controls if the arch needs the scheduling bit
   for keeping track of the ENQCMD instruction. x86 will select this if
   IOMMU_SVA is enabled

 - IOMMU_SVA controls if the IOMMU core compiles in the SVA support code
   for iommu driver use and the IOMMU exported API

This way ARM will not enable CONFIG_ARCH_HAS_CPU_PASID

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-2-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/Kconfig             | 5 +++++
 arch/x86/Kconfig         | 1 +
 arch/x86/kernel/traps.c  | 2 +-
 drivers/iommu/Kconfig    | 1 +
 include/linux/iommu.h    | 2 +-
 include/linux/mm_types.h | 2 +-
 include/linux/sched.h    | 2 +-
 kernel/fork.c            | 2 +-
 mm/Kconfig               | 3 +++
 mm/init-mm.c             | 2 +-
 10 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index f4b210ab06129..3e49f862670e3 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -301,6 +301,11 @@ config ARCH_HAS_DMA_CLEAR_UNCACHED
 config ARCH_HAS_CPU_FINALIZE_INIT
 	bool
 
+# The architecture has a per-task state that includes the mm's PASID
+config ARCH_HAS_CPU_PASID
+	bool
+	select IOMMU_MM_DATA
+
 # Select if arch init_task must go in the __init_task_data section
 config ARCH_TASK_STRUCT_ON_STACK
 	bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3762f41bb0929..68a2ec36a46ec 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -71,6 +71,7 @@ config X86
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
 	select ARCH_HAS_CPU_FINALIZE_INIT
+	select ARCH_HAS_CPU_PASID		if IOMMU_SVA
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c876f1d36a81a..2b62dbb3396ad 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -565,7 +565,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs)
  */
 static bool try_fixup_enqcmd_gp(void)
 {
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	u32 pasid;
 
 	/*
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 7673bb82945b6..9a29d742617e3 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -160,6 +160,7 @@ config IOMMU_DMA
 
 # Shared Virtual Addressing
 config IOMMU_SVA
+	select IOMMU_MM_DATA
 	bool
 
 config FSL_PAMU
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index c7394b39599c8..cd3f398095bf3 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -1337,7 +1337,7 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream
 	return false;
 }
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 static inline void mm_pasid_init(struct mm_struct *mm)
 {
 	mm->pasid = IOMMU_PASID_INVALID;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2a..41f248608dd98 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -938,7 +938,7 @@ struct mm_struct {
 #endif
 		struct work_struct async_put_work;
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 		u32 pasid;
 #endif
 #ifdef CONFIG_KSM
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c316972485..70888a36677b6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -954,7 +954,7 @@ struct task_struct {
 	/* Recursion prevention for eventfd_signal() */
 	unsigned			in_eventfd:1;
 #endif
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	unsigned			pasid_activated:1;
 #endif
 #ifdef	CONFIG_CPU_SUP_INTEL
diff --git a/kernel/fork.c b/kernel/fork.c
index 10917c3e1f036..43fd9bc1a5224 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1179,7 +1179,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->use_memdelay = 0;
 #endif
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	tsk->pasid_activated = 0;
 #endif
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 89971a894b605..0143f4d905c96 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1270,6 +1270,9 @@ config LOCK_MM_AND_FIND_VMA
 	bool
 	depends on !STACK_GROWSUP
 
+config IOMMU_MM_DATA
+	bool
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/init-mm.c b/mm/init-mm.c
index cfd367822cdd2..c52dc2740a3de 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -44,7 +44,7 @@ struct mm_struct init_mm = {
 #endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 	.pasid		= IOMMU_PASID_INVALID,
 #endif
 	INIT_MM_CONTEXT(init_mm)
-- 
GitLab


From 5c79705d7ce8986036c73e89024d189d4f9df1ff Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:21 +0800
Subject: [PATCH 1142/4076] iommu/vt-d: Remove mm->pasid in intel_sva_bind_mm()

The pasid is passed in as a parameter through .set_dev_pasid() callback.
Thus, intel_sva_bind_mm() can directly use it instead of retrieving the
pasid value from mm->pasid.

Suggested-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-3-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/svm.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index ac12f76c1212a..4dbfa970dab53 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -316,21 +316,22 @@ out:
 }
 
 static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
-			     struct mm_struct *mm)
+			     struct iommu_domain *domain, ioasid_t pasid)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct mm_struct *mm = domain->mm;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
 	unsigned long sflags;
 	int ret = 0;
 
-	svm = pasid_private_find(mm->pasid);
+	svm = pasid_private_find(pasid);
 	if (!svm) {
 		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
 		if (!svm)
 			return -ENOMEM;
 
-		svm->pasid = mm->pasid;
+		svm->pasid = pasid;
 		svm->mm = mm;
 		INIT_LIST_HEAD_RCU(&svm->devs);
 
@@ -368,7 +369,7 @@ static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
 
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
-	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, pasid,
 					    FLPT_DEFAULT_DID, sflags);
 	if (ret)
 		goto free_sdev;
@@ -382,7 +383,7 @@ free_sdev:
 free_svm:
 	if (list_empty(&svm->devs)) {
 		mmu_notifier_unregister(&svm->notifier, mm);
-		pasid_private_remove(mm->pasid);
+		pasid_private_remove(pasid);
 		kfree(svm);
 	}
 
@@ -822,9 +823,8 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
-	struct mm_struct *mm = domain->mm;
 
-	return intel_svm_bind_mm(iommu, dev, mm);
+	return intel_svm_bind_mm(iommu, dev, domain, pasid);
 }
 
 static void intel_svm_domain_free(struct iommu_domain *domain)
-- 
GitLab


From 2396046d75d3c0b2cfead852a77efd023f8539dc Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:22 +0800
Subject: [PATCH 1143/4076] iommu: Add mm_get_enqcmd_pasid() helper function

mm_get_enqcmd_pasid() should be used by architecture code and closely
related to learn the PASID value that the x86 ENQCMD operation should
use for the mm.

For the moment SMMUv3 uses this without any connection to ENQCMD, it
will be cleaned up similar to how the prior patch made VT-d use the
PASID argument of set_dev_pasid().

The motivation is to replace mm->pasid with an iommu private data
structure that is introduced in a later patch.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-4-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/x86/kernel/traps.c                       |  2 +-
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   | 23 ++++++++++++-------
 drivers/iommu/iommu-sva.c                     |  2 +-
 include/linux/iommu.h                         | 12 ++++++++++
 4 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 2b62dbb3396ad..5944d759afe7e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -591,7 +591,7 @@ static bool try_fixup_enqcmd_gp(void)
 	if (!mm_valid_pasid(current->mm))
 		return false;
 
-	pasid = current->mm->pasid;
+	pasid = mm_get_enqcmd_pasid(current->mm);
 
 	/*
 	 * Did this thread already have its PASID activated?
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 353248ab18e76..05722121f00e7 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -246,7 +246,8 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 						    smmu_domain);
 	}
 
-	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size);
+	arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), start,
+				size);
 }
 
 static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -264,10 +265,11 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	 * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events,
 	 * but disable translation.
 	 */
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, &quiet_cd);
+	arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm),
+					 &quiet_cd);
 
 	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid);
-	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+	arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, 0);
 
 	smmu_mn->cleared = true;
 	mutex_unlock(&sva_lock);
@@ -325,10 +327,13 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
 
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
 	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
-		ret = arm_smmu_write_ctx_desc(master, mm->pasid, cd);
+		ret = arm_smmu_write_ctx_desc(master, mm_get_enqcmd_pasid(mm),
+					      cd);
 		if (ret) {
-			list_for_each_entry_from_reverse(master, &smmu_domain->devices, domain_head)
-				arm_smmu_write_ctx_desc(master, mm->pasid, NULL);
+			list_for_each_entry_from_reverse(
+				master, &smmu_domain->devices, domain_head)
+				arm_smmu_write_ctx_desc(
+					master, mm_get_enqcmd_pasid(mm), NULL);
 			break;
 		}
 	}
@@ -358,7 +363,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 
 	list_del(&smmu_mn->list);
 
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, NULL);
+	arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm),
+					 NULL);
 
 	/*
 	 * If we went through clear(), we've already invalidated, and no
@@ -366,7 +372,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 	 */
 	if (!smmu_mn->cleared) {
 		arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid);
-		arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+		arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0,
+					0);
 	}
 
 	/* Frees smmu_mn */
diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index b78671a8a9143..4a2f5699747f1 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -141,7 +141,7 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
 
-	return domain->mm->pasid;
+	return mm_get_enqcmd_pasid(domain->mm);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index cd3f398095bf3..4fb239c6ca8d5 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -1346,6 +1346,12 @@ static inline bool mm_valid_pasid(struct mm_struct *mm)
 {
 	return mm->pasid != IOMMU_PASID_INVALID;
 }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	return mm->pasid;
+}
+
 void mm_pasid_drop(struct mm_struct *mm);
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm);
@@ -1368,6 +1374,12 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 }
 static inline void mm_pasid_init(struct mm_struct *mm) {}
 static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	return IOMMU_PASID_INVALID;
+}
+
 static inline void mm_pasid_drop(struct mm_struct *mm) {}
 #endif /* CONFIG_IOMMU_SVA */
 
-- 
GitLab


From 541a3e257d48c16b77d19f39ed939ef5832046df Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:23 +0800
Subject: [PATCH 1144/4076] mm: Add structure to keep sva information

Introduce iommu_mm_data structure to keep sva information (pasid and the
related sva domains). Add iommu_mm pointer, pointing to an instance of
iommu_mm_data structure, to mm.

Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-5-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/iommu.h    | 5 +++++
 include/linux/mm_types.h | 2 ++
 2 files changed, 7 insertions(+)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 4fb239c6ca8d5..f7b1b469e98d6 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -812,6 +812,11 @@ struct iommu_sva {
 	struct iommu_domain		*domain;
 };
 
+struct iommu_mm_data {
+	u32			pasid;
+	struct list_head	sva_domains;
+};
+
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
 		      const struct iommu_ops *ops);
 void iommu_fwspec_free(struct device *dev);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 41f248608dd98..0b4314fab4787 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -727,6 +727,7 @@ struct mm_cid {
 #endif
 
 struct kioctx_table;
+struct iommu_mm_data;
 struct mm_struct {
 	struct {
 		/*
@@ -940,6 +941,7 @@ struct mm_struct {
 
 #ifdef CONFIG_IOMMU_MM_DATA
 		u32 pasid;
+		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
 		/*
-- 
GitLab


From 092edaddb660376648acb97678570ed5d8299768 Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:24 +0800
Subject: [PATCH 1145/4076] iommu: Support mm PASID 1:n with sva domains

Each mm bound to devices gets a PASID and corresponding sva domains
allocated in iommu_sva_bind_device(), which are referenced by iommu_mm
field of the mm. The PASID is released in __mmdrop(), while a sva domain
is released when no one is using it (the reference count is decremented
in iommu_sva_unbind_device()). However, although sva domains and their
PASID are separate objects such that their own life cycles could be
handled independently, an enqcmd use case may require releasing the
PASID in releasing the mm (i.e., once a PASID is allocated for a mm, it
will be permanently used by the mm and won't be released until the end
of mm) and only allows to drop the PASID after the sva domains are
released. To this end, mmgrab() is called in iommu_sva_domain_alloc() to
increment the mm reference count and mmdrop() is invoked in
iommu_domain_free() to decrement the mm reference count.

Since the required info of PASID and sva domains is kept in struct
iommu_mm_data of a mm, use mm->iommu_mm field instead of the old pasid
field in mm struct. The sva domain list is protected by iommu_sva_lock.

Besides, this patch removes mm_pasid_init(), as with the introduced
iommu_mm structure, initializing mm pasid in mm_init() is unnecessary.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-6-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu-sva.c | 92 +++++++++++++++++++++++----------------
 include/linux/iommu.h     | 23 ++++++++--
 2 files changed, 74 insertions(+), 41 deletions(-)

diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index 4a2f5699747f1..5175e8d85247b 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -12,32 +12,42 @@
 static DEFINE_MUTEX(iommu_sva_lock);
 
 /* Allocate a PASID for the mm within range (inclusive) */
-static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev)
+static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct device *dev)
 {
+	struct iommu_mm_data *iommu_mm;
 	ioasid_t pasid;
-	int ret = 0;
+
+	lockdep_assert_held(&iommu_sva_lock);
 
 	if (!arch_pgtable_dma_compat(mm))
-		return -EBUSY;
+		return ERR_PTR(-EBUSY);
 
-	mutex_lock(&iommu_sva_lock);
+	iommu_mm = mm->iommu_mm;
 	/* Is a PASID already associated with this mm? */
-	if (mm_valid_pasid(mm)) {
-		if (mm->pasid >= dev->iommu->max_pasids)
-			ret = -EOVERFLOW;
-		goto out;
+	if (iommu_mm) {
+		if (iommu_mm->pasid >= dev->iommu->max_pasids)
+			return ERR_PTR(-EOVERFLOW);
+		return iommu_mm;
 	}
 
+	iommu_mm = kzalloc(sizeof(struct iommu_mm_data), GFP_KERNEL);
+	if (!iommu_mm)
+		return ERR_PTR(-ENOMEM);
+
 	pasid = iommu_alloc_global_pasid(dev);
 	if (pasid == IOMMU_PASID_INVALID) {
-		ret = -ENOSPC;
-		goto out;
+		kfree(iommu_mm);
+		return ERR_PTR(-ENOSPC);
 	}
-	mm->pasid = pasid;
-	ret = 0;
-out:
-	mutex_unlock(&iommu_sva_lock);
-	return ret;
+	iommu_mm->pasid = pasid;
+	INIT_LIST_HEAD(&iommu_mm->sva_domains);
+	/*
+	 * Make sure the write to mm->iommu_mm is not reordered in front of
+	 * initialization to iommu_mm fields. If it does, readers may see a
+	 * valid iommu_mm with uninitialized values.
+	 */
+	smp_store_release(&mm->iommu_mm, iommu_mm);
+	return iommu_mm;
 }
 
 /**
@@ -58,31 +68,33 @@ out:
  */
 struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
+	struct iommu_mm_data *iommu_mm;
 	struct iommu_domain *domain;
 	struct iommu_sva *handle;
 	int ret;
 
+	mutex_lock(&iommu_sva_lock);
+
 	/* Allocate mm->pasid if necessary. */
-	ret = iommu_sva_alloc_pasid(mm, dev);
-	if (ret)
-		return ERR_PTR(ret);
+	iommu_mm = iommu_alloc_mm_data(mm, dev);
+	if (IS_ERR(iommu_mm)) {
+		ret = PTR_ERR(iommu_mm);
+		goto out_unlock;
+	}
 
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_lock(&iommu_sva_lock);
-	/* Search for an existing domain. */
-	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid,
-						IOMMU_DOMAIN_SVA);
-	if (IS_ERR(domain)) {
-		ret = PTR_ERR(domain);
+	if (!handle) {
+		ret = -ENOMEM;
 		goto out_unlock;
 	}
 
-	if (domain) {
-		domain->users++;
-		goto out;
+	/* Search for an existing domain. */
+	list_for_each_entry(domain, &mm->iommu_mm->sva_domains, next) {
+		ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
+		if (!ret) {
+			domain->users++;
+			goto out;
+		}
 	}
 
 	/* Allocate a new domain and set it on device pasid. */
@@ -92,23 +104,23 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 		goto out_unlock;
 	}
 
-	ret = iommu_attach_device_pasid(domain, dev, mm->pasid);
+	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (ret)
 		goto out_free_domain;
 	domain->users = 1;
+	list_add(&domain->next, &mm->iommu_mm->sva_domains);
+
 out:
 	mutex_unlock(&iommu_sva_lock);
 	handle->dev = dev;
 	handle->domain = domain;
-
 	return handle;
 
 out_free_domain:
 	iommu_domain_free(domain);
+	kfree(handle);
 out_unlock:
 	mutex_unlock(&iommu_sva_lock);
-	kfree(handle);
-
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
@@ -124,12 +136,13 @@ EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
 void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
-	ioasid_t pasid = domain->mm->pasid;
+	struct iommu_mm_data *iommu_mm = domain->mm->iommu_mm;
 	struct device *dev = handle->dev;
 
 	mutex_lock(&iommu_sva_lock);
+	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
-		iommu_detach_device_pasid(domain, dev, pasid);
+		list_del(&domain->next);
 		iommu_domain_free(domain);
 	}
 	mutex_unlock(&iommu_sva_lock);
@@ -205,8 +218,11 @@ out_put_mm:
 
 void mm_pasid_drop(struct mm_struct *mm)
 {
-	if (likely(!mm_valid_pasid(mm)))
+	struct iommu_mm_data *iommu_mm = mm->iommu_mm;
+
+	if (!iommu_mm)
 		return;
 
-	iommu_free_global_pasid(mm->pasid);
+	iommu_free_global_pasid(iommu_mm->pasid);
+	kfree(iommu_mm);
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index f7b1b469e98d6..c6bbbe0901d0c 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -121,6 +121,11 @@ struct iommu_domain {
 		struct {	/* IOMMU_DOMAIN_SVA */
 			struct mm_struct *mm;
 			int users;
+			/*
+			 * Next iommu_domain in mm->iommu_mm->sva-domains list
+			 * protected by iommu_sva_lock.
+			 */
+			struct list_head next;
 		};
 	};
 };
@@ -1345,16 +1350,28 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream
 #ifdef CONFIG_IOMMU_MM_DATA
 static inline void mm_pasid_init(struct mm_struct *mm)
 {
-	mm->pasid = IOMMU_PASID_INVALID;
+	/*
+	 * During dup_mm(), a new mm will be memcpy'd from an old one and that makes
+	 * the new mm and the old one point to a same iommu_mm instance. When either
+	 * one of the two mms gets released, the iommu_mm instance is freed, leaving
+	 * the other mm running into a use-after-free/double-free problem. To avoid
+	 * the problem, zeroing the iommu_mm pointer of a new mm is needed here.
+	 */
+	mm->iommu_mm = NULL;
 }
+
 static inline bool mm_valid_pasid(struct mm_struct *mm)
 {
-	return mm->pasid != IOMMU_PASID_INVALID;
+	return READ_ONCE(mm->iommu_mm);
 }
 
 static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
 {
-	return mm->pasid;
+	struct iommu_mm_data *iommu_mm = READ_ONCE(mm->iommu_mm);
+
+	if (!iommu_mm)
+		return IOMMU_PASID_INVALID;
+	return iommu_mm->pasid;
 }
 
 void mm_pasid_drop(struct mm_struct *mm);
-- 
GitLab


From 1fa05c932dc71c474da38e4fd0456131128f8486 Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:25 +0800
Subject: [PATCH 1146/4076] mm: Deprecate pasid field

Drop the pasid field, as all the information needed for sva domain
management has been moved to the newly added iommu_mm field.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-7-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/mm_types.h | 1 -
 mm/init-mm.c             | 3 ---
 2 files changed, 4 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0b4314fab4787..ec71c91e210ba 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -940,7 +940,6 @@ struct mm_struct {
 		struct work_struct async_put_work;
 
 #ifdef CONFIG_IOMMU_MM_DATA
-		u32 pasid;
 		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
diff --git a/mm/init-mm.c b/mm/init-mm.c
index c52dc2740a3de..24c8093792745 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -44,9 +44,6 @@ struct mm_struct init_mm = {
 #endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,
-#ifdef CONFIG_IOMMU_MM_DATA
-	.pasid		= IOMMU_PASID_INVALID,
-#endif
 	INIT_MM_CONTEXT(init_mm)
 };
 
-- 
GitLab


From 7be423336eccc872249d37900c19c1d24f171353 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Fri, 8 Dec 2023 09:53:14 +0800
Subject: [PATCH 1147/4076] iommu: Set owner token to SVA domain

Commit a9c362db3920 ("iommu: Validate that devices match domains") added
an owner token to the iommu_domain. This token is checked during domain
attachment to RID or PASID through the generic iommu interfaces.

The SVA domains are attached to PASIDs through those iommu interfaces.
Therefore, they require the owner token to be set during allocation.
Otherwise, they fail to attach.

Set the owner token for SVA domains.

Fixes: a9c362db3920 ("iommu: Validate that devices match domains")
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231208015314.320663-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0d25468d53a68..d0a28667479a8 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -3617,6 +3617,7 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
 	domain->type = IOMMU_DOMAIN_SVA;
 	mmgrab(mm);
 	domain->mm = mm;
+	domain->owner = ops;
 	domain->iopf_handler = iommu_sva_handle_iopf;
 	domain->fault_data = mm;
 
-- 
GitLab


From 4720287c7bf76e59d19d4dfbdc3f54eeea6fd46b Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:08 -0400
Subject: [PATCH 1148/4076] iommu: Remove struct iommu_ops *iommu from
 arch_setup_dma_ops()

This is not being used to pass ops, it is just a way to tell if an
iommu driver was probed. These days this can be detected directly via
device_iommu_mapped(). Call device_iommu_mapped() in the two places that
need to check it and remove the iommu parameter everywhere.

Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Moritz Fischer <mdf@kernel.org>
Acked-by: Christoph Hellwig <hch@lst.de>
Acked-by: Rob Herring <robh@kernel.org>
Tested-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/arc/mm/dma.c               |  2 +-
 arch/arm/mm/dma-mapping-nommu.c |  2 +-
 arch/arm/mm/dma-mapping.c       | 10 +++++-----
 arch/arm64/mm/dma-mapping.c     |  4 ++--
 arch/mips/mm/dma-noncoherent.c  |  2 +-
 arch/riscv/mm/dma-noncoherent.c |  2 +-
 drivers/acpi/scan.c             |  3 +--
 drivers/hv/hv_common.c          |  2 +-
 drivers/of/device.c             |  2 +-
 include/linux/dma-map-ops.h     |  4 ++--
 10 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 2a7fbbb83b705..197707bc76588 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -91,7 +91,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
  * Plug in direct dma map ops.
  */
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	/*
 	 * IOC hardware snoops all DMA traffic keeping the caches consistent
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index cfd9c933d2f09..b94850b579952 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -34,7 +34,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 5409225b4abc0..6c359a3af8d9c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1713,7 +1713,7 @@ void arm_iommu_detach_device(struct device *dev)
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
 static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+				    bool coherent)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -1748,7 +1748,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 #else
 
 static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+				    bool coherent)
 {
 }
 
@@ -1757,7 +1757,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	/*
 	 * Due to legacy code that sets the ->dma_coherent flag from a bus
@@ -1776,8 +1776,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (dev->dma_ops)
 		return;
 
-	if (iommu)
-		arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent);
+	if (device_iommu_mapped(dev))
+		arm_setup_iommu_dma_ops(dev, dma_base, size, coherent);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3cb101e8cb29b..61886e43e3a10 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -47,7 +47,7 @@ void arch_teardown_dma_ops(struct device *dev)
 #endif
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	int cls = cache_line_size_of_cpu();
 
@@ -58,7 +58,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		   ARCH_DMA_MINALIGN, cls);
 
 	dev->dma_coherent = coherent;
-	if (iommu)
+	if (device_iommu_mapped(dev))
 		iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1);
 
 	xen_setup_dma_ops(dev);
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 3c4fc97b9f394..0f3cec663a12c 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -138,7 +138,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+		bool coherent)
 {
 	dev->dma_coherent = coherent;
 }
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index 4e4e469b8dd66..843107f834b23 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -129,7 +129,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
 		   TAINT_CPU_OUT_OF_SPEC,
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 02bb2cce423f4..444a0b3c72f2d 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1641,8 +1641,7 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
-	arch_setup_dma_ops(dev, 0, U64_MAX,
-				iommu, attr == DEV_DMA_COHERENT);
+	arch_setup_dma_ops(dev, 0, U64_MAX, attr == DEV_DMA_COHERENT);
 
 	return 0;
 }
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 4372f5d146ab2..0285a74363b3d 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -488,7 +488,7 @@ void hv_setup_dma_ops(struct device *dev, bool coherent)
 	 * Hyper-V does not offer a vIOMMU in the guest
 	 * VM, so pass 0/NULL for the IOMMU settings
 	 */
-	arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
+	arch_setup_dma_ops(dev, 0, 0, coherent);
 }
 EXPORT_SYMBOL_GPL(hv_setup_dma_ops);
 
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 1ca42ad9dd159..65c71be71a8d4 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -193,7 +193,7 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
-	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, coherent);
 
 	if (!iommu)
 		of_dma_set_restricted_buffer(dev, np);
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index a52e508d1869f..e9cc317e9d7de 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -427,10 +427,10 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent);
+		bool coherent);
 #else
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
+		u64 size, bool coherent)
 {
 }
 #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
-- 
GitLab


From 6ff6e184f1f4d4993d45ca3f934c8288890965fe Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:09 -0400
Subject: [PATCH 1149/4076] iommmu/of: Do not return struct iommu_ops from
 of_iommu_configure()

Nothing needs this pointer. Return a normal error code with the usual
IOMMU semantic that ENODEV means 'there is no IOMMU driver'.

Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Rob Herring <robh@kernel.org>
Tested-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/2-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/of_iommu.c | 31 +++++++++++++++++++------------
 drivers/of/device.c      | 22 +++++++++++++++-------
 include/linux/of_iommu.h | 13 ++++++-------
 3 files changed, 40 insertions(+), 26 deletions(-)

diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 5ecca53847d32..c6510d7e7b241 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -107,16 +107,22 @@ static int of_iommu_configure_device(struct device_node *master_np,
 		      of_iommu_configure_dev(master_np, dev);
 }
 
-const struct iommu_ops *of_iommu_configure(struct device *dev,
-					   struct device_node *master_np,
-					   const u32 *id)
+/*
+ * Returns:
+ *  0 on success, an iommu was configured
+ *  -ENODEV if the device does not have any IOMMU
+ *  -EPROBEDEFER if probing should be tried again
+ *  -errno fatal errors
+ */
+int of_iommu_configure(struct device *dev, struct device_node *master_np,
+		       const u32 *id)
 {
 	const struct iommu_ops *ops = NULL;
 	struct iommu_fwspec *fwspec;
 	int err = NO_IOMMU;
 
 	if (!master_np)
-		return NULL;
+		return -ENODEV;
 
 	/* Serialise to make dev->iommu stable under our potential fwspec */
 	mutex_lock(&iommu_probe_device_lock);
@@ -124,7 +130,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 	if (fwspec) {
 		if (fwspec->ops) {
 			mutex_unlock(&iommu_probe_device_lock);
-			return fwspec->ops;
+			return 0;
 		}
 		/* In the deferred case, start again from scratch */
 		iommu_fwspec_free(dev);
@@ -169,14 +175,15 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 		err = iommu_probe_device(dev);
 
 	/* Ignore all other errors apart from EPROBE_DEFER */
-	if (err == -EPROBE_DEFER) {
-		ops = ERR_PTR(err);
-	} else if (err < 0) {
-		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		ops = NULL;
+	if (err < 0) {
+		if (err == -EPROBE_DEFER)
+			return err;
+		dev_dbg(dev, "Adding to IOMMU failed: %pe\n", ERR_PTR(err));
+		return err;
 	}
-
-	return ops;
+	if (!ops)
+		return -ENODEV;
+	return 0;
 }
 
 static enum iommu_resv_type __maybe_unused
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 65c71be71a8d4..873d933e8e6d1 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -93,12 +93,12 @@ of_dma_set_restricted_buffer(struct device *dev, struct device_node *np)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	const struct iommu_ops *iommu;
 	const struct bus_dma_region *map = NULL;
 	struct device_node *bus_np;
 	u64 dma_start = 0;
 	u64 mask, end, size = 0;
 	bool coherent;
+	int iommu_ret;
 	int ret;
 
 	if (np == dev->of_node)
@@ -181,21 +181,29 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	dev_dbg(dev, "device is%sdma coherent\n",
 		coherent ? " " : " not ");
 
-	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+	iommu_ret = of_iommu_configure(dev, np, id);
+	if (iommu_ret == -EPROBE_DEFER) {
 		/* Don't touch range map if it wasn't set from a valid dma-ranges */
 		if (!ret)
 			dev->dma_range_map = NULL;
 		kfree(map);
 		return -EPROBE_DEFER;
-	}
+	} else if (iommu_ret == -ENODEV) {
+		dev_dbg(dev, "device is not behind an iommu\n");
+	} else if (iommu_ret) {
+		dev_err(dev, "iommu configuration for device failed with %pe\n",
+			ERR_PTR(iommu_ret));
 
-	dev_dbg(dev, "device is%sbehind an iommu\n",
-		iommu ? " " : " not ");
+		/*
+		 * Historically this routine doesn't fail driver probing
+		 * due to errors in of_iommu_configure()
+		 */
+	} else
+		dev_dbg(dev, "device is behind an iommu\n");
 
 	arch_setup_dma_ops(dev, dma_start, size, coherent);
 
-	if (!iommu)
+	if (iommu_ret)
 		of_dma_set_restricted_buffer(dev, np);
 
 	return 0;
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 9a5e6b410dd2f..e61cbbe12dac6 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -8,20 +8,19 @@ struct iommu_ops;
 
 #ifdef CONFIG_OF_IOMMU
 
-extern const struct iommu_ops *of_iommu_configure(struct device *dev,
-					struct device_node *master_np,
-					const u32 *id);
+extern int of_iommu_configure(struct device *dev, struct device_node *master_np,
+			      const u32 *id);
 
 extern void of_iommu_get_resv_regions(struct device *dev,
 				      struct list_head *list);
 
 #else
 
-static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
-					 struct device_node *master_np,
-					 const u32 *id)
+static inline int of_iommu_configure(struct device *dev,
+				     struct device_node *master_np,
+				     const u32 *id)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 static inline void of_iommu_get_resv_regions(struct device *dev,
-- 
GitLab


From 5b4ea8b06eb79234a244ffc1f7405aa968f62069 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:10 -0400
Subject: [PATCH 1150/4076] iommu/of: Use -ENODEV consistently in
 of_iommu_configure()

Instead of returning 1 and trying to handle positive error codes just
stick to the convention of returning -ENODEV. Remove references to ops
from of_iommu_configure(), a NULL ops will already generate an error code.

There is no reason to check dev->bus, if err=0 at this point then the
called configure functions thought there was an iommu and we should try to
probe it. Remove it.

Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Moritz Fischer <moritzf@google.com>
Tested-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/3-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/of_iommu.c | 49 ++++++++++++----------------------------
 1 file changed, 15 insertions(+), 34 deletions(-)

diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index c6510d7e7b241..164317bfb8a81 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -17,8 +17,6 @@
 #include <linux/slab.h>
 #include <linux/fsl/mc.h>
 
-#define NO_IOMMU	1
-
 static int of_iommu_xlate(struct device *dev,
 			  struct of_phandle_args *iommu_spec)
 {
@@ -29,7 +27,7 @@ static int of_iommu_xlate(struct device *dev,
 	ops = iommu_ops_from_fwnode(fwnode);
 	if ((ops && !ops->of_xlate) ||
 	    !of_device_is_available(iommu_spec->np))
-		return NO_IOMMU;
+		return -ENODEV;
 
 	ret = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
 	if (ret)
@@ -61,7 +59,7 @@ static int of_iommu_configure_dev_id(struct device_node *master_np,
 			 "iommu-map-mask", &iommu_spec.np,
 			 iommu_spec.args);
 	if (err)
-		return err == -ENODEV ? NO_IOMMU : err;
+		return err;
 
 	err = of_iommu_xlate(dev, &iommu_spec);
 	of_node_put(iommu_spec.np);
@@ -72,7 +70,7 @@ static int of_iommu_configure_dev(struct device_node *master_np,
 				  struct device *dev)
 {
 	struct of_phandle_args iommu_spec;
-	int err = NO_IOMMU, idx = 0;
+	int err = -ENODEV, idx = 0;
 
 	while (!of_parse_phandle_with_args(master_np, "iommus",
 					   "#iommu-cells",
@@ -117,9 +115,8 @@ static int of_iommu_configure_device(struct device_node *master_np,
 int of_iommu_configure(struct device *dev, struct device_node *master_np,
 		       const u32 *id)
 {
-	const struct iommu_ops *ops = NULL;
 	struct iommu_fwspec *fwspec;
-	int err = NO_IOMMU;
+	int err;
 
 	if (!master_np)
 		return -ENODEV;
@@ -153,37 +150,21 @@ int of_iommu_configure(struct device *dev, struct device_node *master_np,
 	} else {
 		err = of_iommu_configure_device(master_np, dev, id);
 	}
-
-	/*
-	 * Two success conditions can be represented by non-negative err here:
-	 * >0 : there is no IOMMU, or one was unavailable for non-fatal reasons
-	 *  0 : we found an IOMMU, and dev->fwspec is initialised appropriately
-	 * <0 : any actual error
-	 */
-	if (!err) {
-		/* The fwspec pointer changed, read it again */
-		fwspec = dev_iommu_fwspec_get(dev);
-		ops    = fwspec->ops;
-	}
 	mutex_unlock(&iommu_probe_device_lock);
 
-	/*
-	 * If we have reason to believe the IOMMU driver missed the initial
-	 * probe for dev, replay it to get things in order.
-	 */
-	if (!err && dev->bus)
-		err = iommu_probe_device(dev);
-
-	/* Ignore all other errors apart from EPROBE_DEFER */
-	if (err < 0) {
-		if (err == -EPROBE_DEFER)
-			return err;
-		dev_dbg(dev, "Adding to IOMMU failed: %pe\n", ERR_PTR(err));
+	if (err == -ENODEV || err == -EPROBE_DEFER)
 		return err;
-	}
-	if (!ops)
-		return -ENODEV;
+	if (err)
+		goto err_log;
+
+	err = iommu_probe_device(dev);
+	if (err)
+		goto err_log;
 	return 0;
+
+err_log:
+	dev_dbg(dev, "Adding to IOMMU failed: %pe\n", ERR_PTR(err));
+	return err;
 }
 
 static enum iommu_resv_type __maybe_unused
-- 
GitLab


From 64945d1b0ed169aeffa59020941e4ac45ebc315a Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:11 -0400
Subject: [PATCH 1151/4076] iommu: Mark dev_iommu_get() with lockdep

Allocation of dev->iommu must be done under the
iommu_probe_device_lock. Mark this with lockdep to discourage future
mistakes.

Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Tested-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Moritz Fischer <moritzf@google.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/4-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d0a28667479a8..df58025c001b3 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -334,6 +334,8 @@ static struct dev_iommu *dev_iommu_get(struct device *dev)
 {
 	struct dev_iommu *param = dev->iommu;
 
+	lockdep_assert_held(&iommu_probe_device_lock);
+
 	if (param)
 		return param;
 
-- 
GitLab


From eda1a94caf6b05482bbf57dc244e7a31a9dba77c Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:12 -0400
Subject: [PATCH 1152/4076] iommu: Mark dev_iommu_priv_set() with a lockdep

A perfect driver would only call dev_iommu_priv_set() from its probe
callback. We've made it functionally correct to call it from the of_xlate
by adding a lock around that call.

lockdep assert that iommu_probe_device_lock is held to discourage misuse.

Exclude PPC kernels with CONFIG_FSL_PAMU turned on because FSL_PAMU uses a
global static for its priv and abuses priv for its domain.

Remove the pointless stores of NULL, all these are on paths where the core
code will free dev->iommu after the op returns.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Tested-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/5-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c                   | 2 --
 drivers/iommu/apple-dart.c                  | 1 -
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 1 -
 drivers/iommu/arm/arm-smmu/arm-smmu.c       | 1 -
 drivers/iommu/intel/iommu.c                 | 2 --
 drivers/iommu/iommu.c                       | 9 +++++++++
 drivers/iommu/omap-iommu.c                  | 1 -
 include/linux/iommu.h                       | 5 +----
 8 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index fcc987f5d4edc..8199c678c2dc2 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -551,8 +551,6 @@ static void amd_iommu_uninit_device(struct device *dev)
 	if (dev_data->domain)
 		detach_device(dev);
 
-	dev_iommu_priv_set(dev, NULL);
-
 	/*
 	 * We keep dev_data around for unplugged devices and reuse it when the
 	 * device is re-plugged - not doing so would introduce a ton of races.
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index ee05f4824bfad..56cfc33042e0b 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -740,7 +740,6 @@ static void apple_dart_release_device(struct device *dev)
 {
 	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index fc4317c25b6d5..1855d3892b15f 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2695,7 +2695,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 
 err_free_master:
 	kfree(master);
-	dev_iommu_priv_set(dev, NULL);
 	return ERR_PTR(ret);
 }
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 4d09c00478927..adc7937fd8a3a 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1420,7 +1420,6 @@ static void arm_smmu_release_device(struct device *dev)
 
 	arm_smmu_rpm_put(cfg->smmu);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 897159dba47de..511589341074f 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4461,7 +4461,6 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 		ret = intel_pasid_alloc_table(dev);
 		if (ret) {
 			dev_err(dev, "PASID table allocation failed\n");
-			dev_iommu_priv_set(dev, NULL);
 			kfree(info);
 			return ERR_PTR(ret);
 		}
@@ -4479,7 +4478,6 @@ static void intel_iommu_release_device(struct device *dev)
 	dmar_remove_one_dev_info(dev);
 	intel_pasid_free_table(dev);
 	intel_iommu_debugfs_remove_dev(info);
-	dev_iommu_priv_set(dev, NULL);
 	kfree(info);
 	set_dma_ops(dev, NULL);
 }
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index df58025c001b3..68e648b557670 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -387,6 +387,15 @@ static u32 dev_iommu_get_max_pasids(struct device *dev)
 	return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids);
 }
 
+void dev_iommu_priv_set(struct device *dev, void *priv)
+{
+	/* FSL_PAMU does something weird */
+	if (!IS_ENABLED(CONFIG_FSL_PAMU))
+		lockdep_assert_held(&iommu_probe_device_lock);
+	dev->iommu->priv = priv;
+}
+EXPORT_SYMBOL_GPL(dev_iommu_priv_set);
+
 /*
  * Init the dev->iommu and dev->iommu_group in the struct device and get the
  * driver probed
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index c66b070841dd4..c9528065a59af 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1719,7 +1719,6 @@ static void omap_iommu_release_device(struct device *dev)
 	if (!dev->of_node || !arch_data)
 		return;
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(arch_data);
 
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index c6bbbe0901d0c..3a556996fea7f 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -850,10 +850,7 @@ static inline void *dev_iommu_priv_get(struct device *dev)
 		return NULL;
 }
 
-static inline void dev_iommu_priv_set(struct device *dev, void *priv)
-{
-	dev->iommu->priv = priv;
-}
+void dev_iommu_priv_set(struct device *dev, void *priv);
 
 extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
-- 
GitLab


From cdbc723f2da11331bc92858da50dc7a7610ed9bd Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:13 -0400
Subject: [PATCH 1153/4076] acpi: Do not return struct iommu_ops from
 acpi_iommu_configure_id()

Nothing needs this pointer. Return a normal error code with the usual
IOMMU semantic that ENODEV means 'there is no IOMMU driver'.

Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Moritz Fischer <moritzf@google.com>
Tested-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/6-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/acpi/scan.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 444a0b3c72f2d..340ba720c7212 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1562,8 +1562,7 @@ static inline const struct iommu_ops *acpi_iommu_fwspec_ops(struct device *dev)
 	return fwspec ? fwspec->ops : NULL;
 }
 
-static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
-						       const u32 *id_in)
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
 	int err;
 	const struct iommu_ops *ops;
@@ -1577,7 +1576,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 	ops = acpi_iommu_fwspec_ops(dev);
 	if (ops) {
 		mutex_unlock(&iommu_probe_device_lock);
-		return ops;
+		return 0;
 	}
 
 	err = iort_iommu_configure_id(dev, id_in);
@@ -1594,12 +1593,14 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 
 	/* Ignore all other errors apart from EPROBE_DEFER */
 	if (err == -EPROBE_DEFER) {
-		return ERR_PTR(err);
+		return err;
 	} else if (err) {
 		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		return NULL;
+		return -ENODEV;
 	}
-	return acpi_iommu_fwspec_ops(dev);
+	if (!acpi_iommu_fwspec_ops(dev))
+		return -ENODEV;
+	return 0;
 }
 
 #else /* !CONFIG_IOMMU_API */
@@ -1611,10 +1612,9 @@ int acpi_iommu_fwspec_init(struct device *dev, u32 id,
 	return -ENODEV;
 }
 
-static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
-						       const u32 *id_in)
+static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 #endif /* !CONFIG_IOMMU_API */
@@ -1628,7 +1628,7 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 			  const u32 *input_id)
 {
-	const struct iommu_ops *iommu;
+	int ret;
 
 	if (attr == DEV_DMA_NOT_SUPPORTED) {
 		set_dma_ops(dev, &dma_dummy_ops);
@@ -1637,10 +1637,15 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 
 	acpi_arch_dma_setup(dev);
 
-	iommu = acpi_iommu_configure_id(dev, input_id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	ret = acpi_iommu_configure_id(dev, input_id);
+	if (ret == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
+	/*
+	 * Historically this routine doesn't fail driver probing due to errors
+	 * in acpi_iommu_configure_id()
+	 */
+
 	arch_setup_dma_ops(dev, 0, U64_MAX, attr == DEV_DMA_COHERENT);
 
 	return 0;
-- 
GitLab


From bf9cd9fef9f15531680325f956f81317d46a159d Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:14 -0400
Subject: [PATCH 1154/4076] iommu/tegra: Use tegra_dev_iommu_get_stream_id() in
 the remaining places

This API was defined to formalize the access to internal iommu details on
some Tegra SOCs, but a few callers got missed. Add them.

The helper already masks by 0xFFFF so remove this code from the callers.

Suggested-by: Thierry Reding <thierry.reding@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/7-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/dma/tegra186-gpc-dma.c                  |  8 +++-----
 drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c |  9 ++-------
 drivers/memory/tegra/tegra186.c                 | 14 ++++++++------
 3 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c
index fa4d4142a68a2..88547a23825b1 100644
--- a/drivers/dma/tegra186-gpc-dma.c
+++ b/drivers/dma/tegra186-gpc-dma.c
@@ -1348,8 +1348,8 @@ static int tegra_dma_program_sid(struct tegra_dma_channel *tdc, int stream_id)
 static int tegra_dma_probe(struct platform_device *pdev)
 {
 	const struct tegra_dma_chip_data *cdata = NULL;
-	struct iommu_fwspec *iommu_spec;
-	unsigned int stream_id, i;
+	unsigned int i;
+	u32 stream_id;
 	struct tegra_dma *tdma;
 	int ret;
 
@@ -1378,12 +1378,10 @@ static int tegra_dma_probe(struct platform_device *pdev)
 
 	tdma->dma_dev.dev = &pdev->dev;
 
-	iommu_spec = dev_iommu_fwspec_get(&pdev->dev);
-	if (!iommu_spec) {
+	if (!tegra_dev_iommu_get_stream_id(&pdev->dev, &stream_id)) {
 		dev_err(&pdev->dev, "Missing iommu stream-id\n");
 		return -EINVAL;
 	}
-	stream_id = iommu_spec->ids[0] & 0xffff;
 
 	ret = device_property_read_u32(&pdev->dev, "dma-channel-mask",
 				       &tdma->chan_mask);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c
index e7e8fdf3adab7..29682722b0b36 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c
@@ -28,19 +28,14 @@ static void
 gp10b_ltc_init(struct nvkm_ltc *ltc)
 {
 	struct nvkm_device *device = ltc->subdev.device;
-	struct iommu_fwspec *spec;
+	u32 sid;
 
 	nvkm_wr32(device, 0x17e27c, ltc->ltc_nr);
 	nvkm_wr32(device, 0x17e000, ltc->ltc_nr);
 	nvkm_wr32(device, 0x100800, ltc->ltc_nr);
 
-	spec = dev_iommu_fwspec_get(device->dev);
-	if (spec) {
-		u32 sid = spec->ids[0] & 0xffff;
-
-		/* stream ID */
+	if (tegra_dev_iommu_get_stream_id(device->dev, &sid))
 		nvkm_wr32(device, 0x160000, sid << 2);
-	}
 }
 
 static const struct nvkm_ltc_func
diff --git a/drivers/memory/tegra/tegra186.c b/drivers/memory/tegra/tegra186.c
index 533f85a4b2bdb..9cbf22a10a827 100644
--- a/drivers/memory/tegra/tegra186.c
+++ b/drivers/memory/tegra/tegra186.c
@@ -111,9 +111,12 @@ static void tegra186_mc_client_sid_override(struct tegra_mc *mc,
 static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
 {
 #if IS_ENABLED(CONFIG_IOMMU_API)
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct of_phandle_args args;
 	unsigned int i, index = 0;
+	u32 sid;
+
+	if (!tegra_dev_iommu_get_stream_id(dev, &sid))
+		return 0;
 
 	while (!of_parse_phandle_with_args(dev->of_node, "interconnects", "#interconnect-cells",
 					   index, &args)) {
@@ -121,11 +124,10 @@ static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
 			for (i = 0; i < mc->soc->num_clients; i++) {
 				const struct tegra_mc_client *client = &mc->soc->clients[i];
 
-				if (client->id == args.args[0]) {
-					u32 sid = fwspec->ids[0] & MC_SID_STREAMID_OVERRIDE_MASK;
-
-					tegra186_mc_client_sid_override(mc, client, sid);
-				}
+				if (client->id == args.args[0])
+					tegra186_mc_client_sid_override(
+						mc, client,
+						sid & MC_SID_STREAMID_OVERRIDE_MASK);
 			}
 		}
 
-- 
GitLab


From 123971a193d9ac70b207c24c9f4ed6908b837bb6 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Mon, 4 Dec 2023 11:08:26 -0500
Subject: [PATCH 1155/4076] PCI: layerscape: Add function pointer for
 exit_from_l2()

Since different SoCs require different sequences for exiting L2, let's add
a separate "exit_from_l2()" callback to handle SoC specific sequences.

Change ls_pcie_exit_from_l2() return value from void to int in order
to propagate errors. Return an error if the exit_from_l2() callback
fails in the resume flow.

Link: https://lore.kernel.org/r/20231204160829.2498703-2-Frank.Li@nxp.com
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Roy Zang <Roy.Zang@nxp.com>
---
 drivers/pci/controller/dwc/pci-layerscape.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index 37956e09c65bd..aea89926bcc4f 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -39,6 +39,7 @@
 
 struct ls_pcie_drvdata {
 	const u32 pf_off;
+	int (*exit_from_l2)(struct dw_pcie_rp *pp);
 	bool pm_support;
 };
 
@@ -125,7 +126,7 @@ static void ls_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
 		dev_err(pcie->pci->dev, "PME_Turn_off timeout\n");
 }
 
-static void ls_pcie_exit_from_l2(struct dw_pcie_rp *pp)
+static int ls_pcie_exit_from_l2(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct ls_pcie *pcie = to_ls_pcie(pci);
@@ -150,6 +151,8 @@ static void ls_pcie_exit_from_l2(struct dw_pcie_rp *pp)
 				 10000);
 	if (ret)
 		dev_err(pcie->pci->dev, "L2 exit timeout\n");
+
+	return ret;
 }
 
 static int ls_pcie_host_init(struct dw_pcie_rp *pp)
@@ -180,6 +183,7 @@ static const struct ls_pcie_drvdata ls1021a_drvdata = {
 static const struct ls_pcie_drvdata layerscape_drvdata = {
 	.pf_off = 0xc0000,
 	.pm_support = true,
+	.exit_from_l2 = ls_pcie_exit_from_l2,
 };
 
 static const struct of_device_id ls_pcie_of_match[] = {
@@ -247,11 +251,14 @@ static int ls_pcie_suspend_noirq(struct device *dev)
 static int ls_pcie_resume_noirq(struct device *dev)
 {
 	struct ls_pcie *pcie = dev_get_drvdata(dev);
+	int ret;
 
 	if (!pcie->drvdata->pm_support)
 		return 0;
 
-	ls_pcie_exit_from_l2(&pcie->pci->pp);
+	ret = pcie->drvdata->exit_from_l2(&pcie->pci->pp);
+	if (ret)
+		return ret;
 
 	return dw_pcie_resume_noirq(pcie->pci);
 }
-- 
GitLab


From 6f8a41ba26230f6c04edad7daa25bd1c254c83b4 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Mon, 4 Dec 2023 11:08:27 -0500
Subject: [PATCH 1156/4076] PCI: layerscape: Add suspend/resume for ls1021a

Add suspend/resume support for Layerscape LS1021a.

In the suspend path, PME_Turn_Off message is sent to the endpoint to
transition the link to L2/L3_Ready state. In this SoC, there is no way to
check if the controller has received the PME_To_Ack from the endpoint or
not. So to be on the safer side, the driver just waits for
PCIE_PME_TO_L2_TIMEOUT_US before asserting the SoC specific PMXMTTURNOFF
bit to complete the PME_Turn_Off handshake. Then the link would enter L2/L3
state depending on the VAUX supply.

In the resume path, the link is brought back from L2 to L0 by doing a
software reset.

Link: https://lore.kernel.org/r/20231204160829.2498703-3-Frank.Li@nxp.com
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Roy Zang <Roy.Zang@nxp.com>
---
 drivers/pci/controller/dwc/pci-layerscape.c | 83 ++++++++++++++++++++-
 1 file changed, 80 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index aea89926bcc4f..711563777aeba 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -35,11 +35,19 @@
 #define PF_MCR_PTOMR		BIT(0)
 #define PF_MCR_EXL2S		BIT(1)
 
+/* LS1021A PEXn PM Write Control Register */
+#define SCFG_PEXPMWRCR(idx)	(0x5c + (idx) * 0x64)
+#define PMXMTTURNOFF		BIT(31)
+#define SCFG_PEXSFTRSTCR	0x190
+#define PEXSR(idx)		BIT(idx)
+
 #define PCIE_IATU_NUM		6
 
 struct ls_pcie_drvdata {
 	const u32 pf_off;
+	const struct dw_pcie_host_ops *ops;
 	int (*exit_from_l2)(struct dw_pcie_rp *pp);
+	bool scfg_support;
 	bool pm_support;
 };
 
@@ -47,6 +55,8 @@ struct ls_pcie {
 	struct dw_pcie *pci;
 	const struct ls_pcie_drvdata *drvdata;
 	void __iomem *pf_base;
+	struct regmap *scfg;
+	int index;
 	bool big_endian;
 };
 
@@ -171,18 +181,70 @@ static int ls_pcie_host_init(struct dw_pcie_rp *pp)
 	return 0;
 }
 
+static void scfg_pcie_send_turnoff_msg(struct regmap *scfg, u32 reg, u32 mask)
+{
+	/* Send PME_Turn_Off message */
+	regmap_write_bits(scfg, reg, mask, mask);
+
+	/*
+	 * There is no specific register to check for PME_To_Ack from endpoint.
+	 * So on the safe side, wait for PCIE_PME_TO_L2_TIMEOUT_US.
+	 */
+	mdelay(PCIE_PME_TO_L2_TIMEOUT_US/1000);
+
+	/*
+	 * Layerscape hardware reference manual recommends clearing the PMXMTTURNOFF bit
+	 * to complete the PME_Turn_Off handshake.
+	 */
+	regmap_write_bits(scfg, reg, mask, 0);
+}
+
+static void ls1021a_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct ls_pcie *pcie = to_ls_pcie(pci);
+
+	scfg_pcie_send_turnoff_msg(pcie->scfg, SCFG_PEXPMWRCR(pcie->index), PMXMTTURNOFF);
+}
+
+static int scfg_pcie_exit_from_l2(struct regmap *scfg, u32 reg, u32 mask)
+{
+	/* Reset the PEX wrapper to bring the link out of L2 */
+	regmap_write_bits(scfg, reg, mask, mask);
+	regmap_write_bits(scfg, reg, mask, 0);
+
+	return 0;
+}
+
+static int ls1021a_pcie_exit_from_l2(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct ls_pcie *pcie = to_ls_pcie(pci);
+
+	return scfg_pcie_exit_from_l2(pcie->scfg, SCFG_PEXSFTRSTCR, PEXSR(pcie->index));
+}
+
 static const struct dw_pcie_host_ops ls_pcie_host_ops = {
 	.host_init = ls_pcie_host_init,
 	.pme_turn_off = ls_pcie_send_turnoff_msg,
 };
 
+static const struct dw_pcie_host_ops ls1021a_pcie_host_ops = {
+	.host_init = ls_pcie_host_init,
+	.pme_turn_off = ls1021a_pcie_send_turnoff_msg,
+};
+
 static const struct ls_pcie_drvdata ls1021a_drvdata = {
-	.pm_support = false,
+	.pm_support = true,
+	.scfg_support = true,
+	.ops = &ls1021a_pcie_host_ops,
+	.exit_from_l2 = ls1021a_pcie_exit_from_l2,
 };
 
 static const struct ls_pcie_drvdata layerscape_drvdata = {
 	.pf_off = 0xc0000,
 	.pm_support = true,
+	.ops = &ls_pcie_host_ops,
 	.exit_from_l2 = ls_pcie_exit_from_l2,
 };
 
@@ -205,6 +267,8 @@ static int ls_pcie_probe(struct platform_device *pdev)
 	struct dw_pcie *pci;
 	struct ls_pcie *pcie;
 	struct resource *dbi_base;
+	u32 index[2];
+	int ret;
 
 	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
@@ -217,9 +281,8 @@ static int ls_pcie_probe(struct platform_device *pdev)
 	pcie->drvdata = of_device_get_match_data(dev);
 
 	pci->dev = dev;
-	pci->pp.ops = &ls_pcie_host_ops;
-
 	pcie->pci = pci;
+	pci->pp.ops = pcie->drvdata->ops;
 
 	dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
 	pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_base);
@@ -230,6 +293,20 @@ static int ls_pcie_probe(struct platform_device *pdev)
 
 	pcie->pf_base = pci->dbi_base + pcie->drvdata->pf_off;
 
+	if (pcie->drvdata->scfg_support) {
+		pcie->scfg = syscon_regmap_lookup_by_phandle(dev->of_node, "fsl,pcie-scfg");
+		if (IS_ERR(pcie->scfg)) {
+			dev_err(dev, "No syscfg phandle specified\n");
+			return PTR_ERR(pcie->scfg);
+		}
+
+		ret = of_property_read_u32_array(dev->of_node, "fsl,pcie-scfg", index, 2);
+		if (ret)
+			return ret;
+
+		pcie->index = index[1];
+	}
+
 	if (!ls_pcie_is_bridge(pcie))
 		return -ENODEV;
 
-- 
GitLab


From 762ef94b45d97c220f865f4ea288d2c488c9fd3c Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Mon, 4 Dec 2023 11:08:28 -0500
Subject: [PATCH 1157/4076] PCI: layerscape(ep): Rename pf_* as pf_lut_*

'pf' and 'lut' are two different acronyms describing the same
thing, basically it is a MMIO base address plus an offset.

Rename them to avoid duplicate pf_* and lut_* naming schemes in the
driver.

Link: https://lore.kernel.org/r/20231204160829.2498703-4-Frank.Li@nxp.com
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Roy Zang <Roy.Zang@nxp.com>
---
 .../pci/controller/dwc/pci-layerscape-ep.c    | 16 ++++-----
 drivers/pci/controller/dwc/pci-layerscape.c   | 34 +++++++++----------
 2 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 3d3c50ef4b6ff..2ca339f938a86 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -49,7 +49,7 @@ struct ls_pcie_ep {
 	bool				big_endian;
 };
 
-static u32 ls_lut_readl(struct ls_pcie_ep *pcie, u32 offset)
+static u32 ls_pcie_pf_lut_readl(struct ls_pcie_ep *pcie, u32 offset)
 {
 	struct dw_pcie *pci = pcie->pci;
 
@@ -59,7 +59,7 @@ static u32 ls_lut_readl(struct ls_pcie_ep *pcie, u32 offset)
 		return ioread32(pci->dbi_base + offset);
 }
 
-static void ls_lut_writel(struct ls_pcie_ep *pcie, u32 offset, u32 value)
+static void ls_pcie_pf_lut_writel(struct ls_pcie_ep *pcie, u32 offset, u32 value)
 {
 	struct dw_pcie *pci = pcie->pci;
 
@@ -76,8 +76,8 @@ static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id)
 	u32 val, cfg;
 	u8 offset;
 
-	val = ls_lut_readl(pcie, PEX_PF0_PME_MES_DR);
-	ls_lut_writel(pcie, PEX_PF0_PME_MES_DR, val);
+	val = ls_pcie_pf_lut_readl(pcie, PEX_PF0_PME_MES_DR);
+	ls_pcie_pf_lut_writel(pcie, PEX_PF0_PME_MES_DR, val);
 
 	if (!val)
 		return IRQ_NONE;
@@ -96,9 +96,9 @@ static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id)
 		dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, pcie->lnkcap);
 		dw_pcie_dbi_ro_wr_dis(pci);
 
-		cfg = ls_lut_readl(pcie, PEX_PF0_CONFIG);
+		cfg = ls_pcie_pf_lut_readl(pcie, PEX_PF0_CONFIG);
 		cfg |= PEX_PF0_CFG_READY;
-		ls_lut_writel(pcie, PEX_PF0_CONFIG, cfg);
+		ls_pcie_pf_lut_writel(pcie, PEX_PF0_CONFIG, cfg);
 		dw_pcie_ep_linkup(&pci->ep);
 
 		dev_dbg(pci->dev, "Link up\n");
@@ -130,10 +130,10 @@ static int ls_pcie_ep_interrupt_init(struct ls_pcie_ep *pcie,
 	}
 
 	/* Enable interrupts */
-	val = ls_lut_readl(pcie, PEX_PF0_PME_MES_IER);
+	val = ls_pcie_pf_lut_readl(pcie, PEX_PF0_PME_MES_IER);
 	val |=  PEX_PF0_PME_MES_IER_LDDIE | PEX_PF0_PME_MES_IER_HRDIE |
 		PEX_PF0_PME_MES_IER_LUDIE;
-	ls_lut_writel(pcie, PEX_PF0_PME_MES_IER, val);
+	ls_pcie_pf_lut_writel(pcie, PEX_PF0_PME_MES_IER, val);
 
 	return 0;
 }
diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index 711563777aeba..f3dfb70066fb7 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -44,7 +44,7 @@
 #define PCIE_IATU_NUM		6
 
 struct ls_pcie_drvdata {
-	const u32 pf_off;
+	const u32 pf_lut_off;
 	const struct dw_pcie_host_ops *ops;
 	int (*exit_from_l2)(struct dw_pcie_rp *pp);
 	bool scfg_support;
@@ -54,13 +54,13 @@ struct ls_pcie_drvdata {
 struct ls_pcie {
 	struct dw_pcie *pci;
 	const struct ls_pcie_drvdata *drvdata;
-	void __iomem *pf_base;
+	void __iomem *pf_lut_base;
 	struct regmap *scfg;
 	int index;
 	bool big_endian;
 };
 
-#define ls_pcie_pf_readl_addr(addr)	ls_pcie_pf_readl(pcie, addr)
+#define ls_pcie_pf_lut_readl_addr(addr)	ls_pcie_pf_lut_readl(pcie, addr)
 #define to_ls_pcie(x)	dev_get_drvdata((x)->dev)
 
 static bool ls_pcie_is_bridge(struct ls_pcie *pcie)
@@ -101,20 +101,20 @@ static void ls_pcie_fix_error_response(struct ls_pcie *pcie)
 	iowrite32(PCIE_ABSERR_SETTING, pci->dbi_base + PCIE_ABSERR);
 }
 
-static u32 ls_pcie_pf_readl(struct ls_pcie *pcie, u32 off)
+static u32 ls_pcie_pf_lut_readl(struct ls_pcie *pcie, u32 off)
 {
 	if (pcie->big_endian)
-		return ioread32be(pcie->pf_base + off);
+		return ioread32be(pcie->pf_lut_base + off);
 
-	return ioread32(pcie->pf_base + off);
+	return ioread32(pcie->pf_lut_base + off);
 }
 
-static void ls_pcie_pf_writel(struct ls_pcie *pcie, u32 off, u32 val)
+static void ls_pcie_pf_lut_writel(struct ls_pcie *pcie, u32 off, u32 val)
 {
 	if (pcie->big_endian)
-		iowrite32be(val, pcie->pf_base + off);
+		iowrite32be(val, pcie->pf_lut_base + off);
 	else
-		iowrite32(val, pcie->pf_base + off);
+		iowrite32(val, pcie->pf_lut_base + off);
 }
 
 static void ls_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
@@ -124,11 +124,11 @@ static void ls_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
 	u32 val;
 	int ret;
 
-	val = ls_pcie_pf_readl(pcie, LS_PCIE_PF_MCR);
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_PF_MCR);
 	val |= PF_MCR_PTOMR;
-	ls_pcie_pf_writel(pcie, LS_PCIE_PF_MCR, val);
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_PF_MCR, val);
 
-	ret = readx_poll_timeout(ls_pcie_pf_readl_addr, LS_PCIE_PF_MCR,
+	ret = readx_poll_timeout(ls_pcie_pf_lut_readl_addr, LS_PCIE_PF_MCR,
 				 val, !(val & PF_MCR_PTOMR),
 				 PCIE_PME_TO_L2_TIMEOUT_US/10,
 				 PCIE_PME_TO_L2_TIMEOUT_US);
@@ -147,15 +147,15 @@ static int ls_pcie_exit_from_l2(struct dw_pcie_rp *pp)
 	 * Set PF_MCR_EXL2S bit in LS_PCIE_PF_MCR register for the link
 	 * to exit L2 state.
 	 */
-	val = ls_pcie_pf_readl(pcie, LS_PCIE_PF_MCR);
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_PF_MCR);
 	val |= PF_MCR_EXL2S;
-	ls_pcie_pf_writel(pcie, LS_PCIE_PF_MCR, val);
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_PF_MCR, val);
 
 	/*
 	 * L2 exit timeout of 10ms is not defined in the specifications,
 	 * it was chosen based on empirical observations.
 	 */
-	ret = readx_poll_timeout(ls_pcie_pf_readl_addr, LS_PCIE_PF_MCR,
+	ret = readx_poll_timeout(ls_pcie_pf_lut_readl_addr, LS_PCIE_PF_MCR,
 				 val, !(val & PF_MCR_EXL2S),
 				 1000,
 				 10000);
@@ -242,7 +242,7 @@ static const struct ls_pcie_drvdata ls1021a_drvdata = {
 };
 
 static const struct ls_pcie_drvdata layerscape_drvdata = {
-	.pf_off = 0xc0000,
+	.pf_lut_off = 0xc0000,
 	.pm_support = true,
 	.ops = &ls_pcie_host_ops,
 	.exit_from_l2 = ls_pcie_exit_from_l2,
@@ -291,7 +291,7 @@ static int ls_pcie_probe(struct platform_device *pdev)
 
 	pcie->big_endian = of_property_read_bool(dev->of_node, "big-endian");
 
-	pcie->pf_base = pci->dbi_base + pcie->drvdata->pf_off;
+	pcie->pf_lut_base = pci->dbi_base + pcie->drvdata->pf_lut_off;
 
 	if (pcie->drvdata->scfg_support) {
 		pcie->scfg = syscon_regmap_lookup_by_phandle(dev->of_node, "fsl,pcie-scfg");
-- 
GitLab


From 27b3bcbf8a797d3b18c2aa95928fe65a50066159 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Mon, 4 Dec 2023 11:08:29 -0500
Subject: [PATCH 1158/4076] PCI: layerscape: Add suspend/resume for ls1043a

Add suspend/resume support for Layerscape LS1043a.

In the suspend path, PME_Turn_Off message is sent to the endpoint to
transition the link to L2/L3_Ready state. In this SoC, there is no way to
check if the controller has received the PME_To_Ack from the endpoint or
not. So to be on the safer side, the driver just waits for
PCIE_PME_TO_L2_TIMEOUT_US before asserting the SoC specific PMXMTTURNOFF
bit to complete the PME_Turn_Off handshake. Then the link would enter L2/L3
state depending on the VAUX supply.

In the resume path, the link is brought back from L2 to L0 by doing a
software reset.

Link: https://lore.kernel.org/r/20231204160829.2498703-5-Frank.Li@nxp.com
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Roy Zang <Roy.Zang@nxp.com>
---
 drivers/pci/controller/dwc/pci-layerscape.c | 63 ++++++++++++++++++++-
 1 file changed, 62 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index f3dfb70066fb7..7cdada200de7e 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -41,6 +41,15 @@
 #define SCFG_PEXSFTRSTCR	0x190
 #define PEXSR(idx)		BIT(idx)
 
+/* LS1043A PEX PME control register */
+#define SCFG_PEXPMECR		0x144
+#define PEXPME(idx)		BIT(31 - (idx) * 4)
+
+/* LS1043A PEX LUT debug register */
+#define LS_PCIE_LDBG	0x7fc
+#define LDBG_SR		BIT(30)
+#define LDBG_WE		BIT(31)
+
 #define PCIE_IATU_NUM		6
 
 struct ls_pcie_drvdata {
@@ -224,6 +233,45 @@ static int ls1021a_pcie_exit_from_l2(struct dw_pcie_rp *pp)
 	return scfg_pcie_exit_from_l2(pcie->scfg, SCFG_PEXSFTRSTCR, PEXSR(pcie->index));
 }
 
+static void ls1043a_pcie_send_turnoff_msg(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct ls_pcie *pcie = to_ls_pcie(pci);
+
+	scfg_pcie_send_turnoff_msg(pcie->scfg, SCFG_PEXPMECR, PEXPME(pcie->index));
+}
+
+static int ls1043a_pcie_exit_from_l2(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct ls_pcie *pcie = to_ls_pcie(pci);
+	u32 val;
+
+	/*
+	 * Reset the PEX wrapper to bring the link out of L2.
+	 * LDBG_WE: allows the user to have write access to the PEXDBG[SR] for both setting and
+	 *	    clearing the soft reset on the PEX module.
+	 * LDBG_SR: When SR is set to 1, the PEX module enters soft reset.
+	 */
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG);
+	val |= LDBG_WE;
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val);
+
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG);
+	val |= LDBG_SR;
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val);
+
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG);
+	val &= ~LDBG_SR;
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val);
+
+	val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG);
+	val &= ~LDBG_WE;
+	ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val);
+
+	return 0;
+}
+
 static const struct dw_pcie_host_ops ls_pcie_host_ops = {
 	.host_init = ls_pcie_host_init,
 	.pme_turn_off = ls_pcie_send_turnoff_msg,
@@ -241,6 +289,19 @@ static const struct ls_pcie_drvdata ls1021a_drvdata = {
 	.exit_from_l2 = ls1021a_pcie_exit_from_l2,
 };
 
+static const struct dw_pcie_host_ops ls1043a_pcie_host_ops = {
+	.host_init = ls_pcie_host_init,
+	.pme_turn_off = ls1043a_pcie_send_turnoff_msg,
+};
+
+static const struct ls_pcie_drvdata ls1043a_drvdata = {
+	.pf_lut_off = 0x10000,
+	.pm_support = true,
+	.scfg_support = true,
+	.ops = &ls1043a_pcie_host_ops,
+	.exit_from_l2 = ls1043a_pcie_exit_from_l2,
+};
+
 static const struct ls_pcie_drvdata layerscape_drvdata = {
 	.pf_lut_off = 0xc0000,
 	.pm_support = true,
@@ -252,7 +313,7 @@ static const struct of_device_id ls_pcie_of_match[] = {
 	{ .compatible = "fsl,ls1012a-pcie", .data = &layerscape_drvdata },
 	{ .compatible = "fsl,ls1021a-pcie", .data = &ls1021a_drvdata },
 	{ .compatible = "fsl,ls1028a-pcie", .data = &layerscape_drvdata },
-	{ .compatible = "fsl,ls1043a-pcie", .data = &ls1021a_drvdata },
+	{ .compatible = "fsl,ls1043a-pcie", .data = &ls1043a_drvdata },
 	{ .compatible = "fsl,ls1046a-pcie", .data = &layerscape_drvdata },
 	{ .compatible = "fsl,ls2080a-pcie", .data = &layerscape_drvdata },
 	{ .compatible = "fsl,ls2085a-pcie", .data = &layerscape_drvdata },
-- 
GitLab


From 54dae6d5d3f091568322c4a69ddd3459a81545ad Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 12 Nov 2023 19:45:22 +0100
Subject: [PATCH 1159/4076] dt-bindings: iommu: arm,smmu: document clocks for
 the SM8350 GPU SMMU

Document the clocks for Qualcomm SM8350 Adreno GPU SMMU, already used in
DTS:

  sm8350-hdk.dtb: iommu@3da0000: clock-names: False schema does not allow ['bus', 'iface', 'ahb', 'hlos1_vote_gpu_smmu', 'cx_gmu', 'hub_cx_int', 'hub_aon']

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231112184522.3759-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 .../devicetree/bindings/iommu/arm,smmu.yaml   | 25 ++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index aa9e1c0895a50..e89f8a5c44e42 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -429,6 +429,30 @@ allOf:
             - description: interface clock required to access smmu's registers
                 through the TCU's programming interface.
 
+  - if:
+      properties:
+        compatible:
+          items:
+            - enum:
+                - qcom,sm8350-smmu-500
+            - const: qcom,adreno-smmu
+            - const: qcom,smmu-500
+            - const: arm,mmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: bus
+            - const: iface
+            - const: ahb
+            - const: hlos1_vote_gpu_smmu
+            - const: cx_gmu
+            - const: hub_cx_int
+            - const: hub_aon
+        clocks:
+          minItems: 7
+          maxItems: 7
+
   - if:
       properties:
         compatible:
@@ -472,7 +496,6 @@ allOf:
               - qcom,sdx65-smmu-500
               - qcom,sm6350-smmu-500
               - qcom,sm6375-smmu-500
-              - qcom,sm8350-smmu-500
               - qcom,sm8450-smmu-500
               - qcom,sm8550-smmu-500
     then:
-- 
GitLab


From 61683b47df44fa7efd4039676436e711f7e31c70 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Tue, 28 Nov 2023 09:41:23 +0100
Subject: [PATCH 1160/4076] dt-bindings: iommu: arm,smmu: document the SM8650
 System MMU

Document the System MMU on the SM8650 Platform.

Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231128-topic-sm8650-upstream-bindings-smmu-v2-1-d3fbcaf1ea92@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index e89f8a5c44e42..b4b76437369a3 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -56,6 +56,7 @@ properties:
               - qcom,sm8350-smmu-500
               - qcom,sm8450-smmu-500
               - qcom,sm8550-smmu-500
+              - qcom,sm8650-smmu-500
           - const: qcom,smmu-500
           - const: arm,mmu-500
 
@@ -498,6 +499,7 @@ allOf:
               - qcom,sm6375-smmu-500
               - qcom,sm8450-smmu-500
               - qcom,sm8550-smmu-500
+              - qcom,sm8650-smmu-500
     then:
       properties:
         clock-names: false
-- 
GitLab


From fa27b35c9102e3e2b75455517f7091b294cc0552 Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <quic_rjendra@quicinc.com>
Date: Fri, 24 Nov 2023 15:36:05 +0530
Subject: [PATCH 1161/4076] dt-bindings: arm-smmu: Add compatible for X1E80100
 SoC

Add the SoC specific compatible for X1E80100 implementing arm,mmu-500.

Signed-off-by: Rajendra Nayak <quic_rjendra@quicinc.com>
Co-developed-by: Sibi Sankar <quic_sibis@quicinc.com>
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231124100608.29964-3-quic_sibis@quicinc.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index b4b76437369a3..a5adfba939243 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -57,6 +57,7 @@ properties:
               - qcom,sm8450-smmu-500
               - qcom,sm8550-smmu-500
               - qcom,sm8650-smmu-500
+              - qcom,x1e80100-smmu-500
           - const: qcom,smmu-500
           - const: arm,mmu-500
 
@@ -500,6 +501,7 @@ allOf:
               - qcom,sm8450-smmu-500
               - qcom,sm8550-smmu-500
               - qcom,sm8650-smmu-500
+              - qcom,x1e80100-smmu-500
     then:
       properties:
         clock-names: false
-- 
GitLab


From 4fff78dc2490fc0c67669c610dbc42921dd23a1c Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Mon, 4 Dec 2023 13:55:20 +0100
Subject: [PATCH 1162/4076] dt-bindings: arm-smmu: Document SM8[45]50 GPU SMMU

SM8450 and SM8550 both use a Qualcomm-modified MMU500 for their GPU.
In both cases, it requires a set of clocks to be enabled. Describe that.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231127-topic-a7xx_dt-v2-1-2a437588e563@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 .../devicetree/bindings/iommu/arm,smmu.yaml   | 48 ++++++++++++++++++-
 1 file changed, 46 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index a5adfba939243..a4042ae247702 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -91,6 +91,8 @@ properties:
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
               - qcom,sm8350-smmu-500
+              - qcom,sm8450-smmu-500
+              - qcom,sm8550-smmu-500
           - const: qcom,adreno-smmu
           - const: qcom,smmu-500
           - const: arm,mmu-500
@@ -479,6 +481,50 @@ allOf:
             - description: Voter clock required for HLOS SMMU access
             - description: Interface clock required for register access
 
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm8450-smmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: gmu
+            - const: hub
+            - const: hlos
+            - const: bus
+            - const: iface
+            - const: ahb
+
+        clocks:
+          items:
+            - description: GMU clock
+            - description: GPU HUB clock
+            - description: HLOS vote clock
+            - description: GPU memory bus clock
+            - description: GPU SNoC bus clock
+            - description: GPU AHB clock
+
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm8550-smmu-500
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: hlos
+            - const: bus
+            - const: iface
+            - const: ahb
+
+        clocks:
+          items:
+            - description: HLOS vote clock
+            - description: GPU memory bus clock
+            - description: GPU SNoC bus clock
+            - description: GPU AHB clock
+
   # Disallow clocks for all other platforms with specific compatibles
   - if:
       properties:
@@ -498,8 +544,6 @@ allOf:
               - qcom,sdx65-smmu-500
               - qcom,sm6350-smmu-500
               - qcom,sm6375-smmu-500
-              - qcom,sm8450-smmu-500
-              - qcom,sm8550-smmu-500
               - qcom,sm8650-smmu-500
               - qcom,x1e80100-smmu-500
     then:
-- 
GitLab


From afc95681c3068956fed1241a1ff1612c066c75ac Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Sun, 10 Dec 2023 10:06:53 -0800
Subject: [PATCH 1163/4076] iommu/arm-smmu-qcom: Add missing GMU entry to match
 table

In some cases the firmware expects cbndx 1 to be assigned to the GMU,
so we also want the default domain for the GMU to be an identy domain.
This way it does not get a context bank assigned.  Without this, both
of_dma_configure() and drm/msm's iommu_domain_attach() will trigger
allocating and configuring a context bank.  So GMU ends up attached to
both cbndx 1 and later cbndx 2.  This arrangement seemingly confounds
and surprises the firmware if the GPU later triggers a translation
fault, resulting (on sc8280xp / lenovo x13s, at least) in the SMMU
getting wedged and the GPU stuck without memory access.

Cc: stable@vger.kernel.org
Signed-off-by: Rob Clark <robdclark@chromium.org>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20231210180655.75542-1-robdclark@gmail.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 549ae4dba3a68..d326fa230b96e 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -243,6 +243,7 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 
 static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,adreno" },
+	{ .compatible = "qcom,adreno-gmu" },
 	{ .compatible = "qcom,mdp4" },
 	{ .compatible = "qcom,mdss" },
 	{ .compatible = "qcom,sc7180-mdss" },
-- 
GitLab


From 28af105cb65043f20a16c5e2519d66390b1f9bb9 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 29 Nov 2023 15:44:02 +0100
Subject: [PATCH 1164/4076] iommu/arm-smmu-qcom: Add QCM2290 MDSS compatible

Add the QCM2290 MDSS compatible to clients compatible list, as it also
needs the workarounds.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231125-topic-rb1_feat-v3-5-4cbb567743bb@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index d326fa230b96e..8b04ece00420d 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -246,6 +246,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,adreno-gmu" },
 	{ .compatible = "qcom,mdp4" },
 	{ .compatible = "qcom,mdss" },
+	{ .compatible = "qcom,qcm2290-mdss" },
 	{ .compatible = "qcom,sc7180-mdss" },
 	{ .compatible = "qcom,sc7180-mss-pil" },
 	{ .compatible = "qcom,sc7280-mdss" },
-- 
GitLab


From 268dd4edb748a1e2f298b04854681453df6e77a2 Mon Sep 17 00:00:00 2001
From: Vladimir Lypak <vladimir.lypak@gmail.com>
Date: Wed, 11 Oct 2023 19:57:26 +0200
Subject: [PATCH 1165/4076] iommu/qcom: restore IOMMU state if needed

If the IOMMU has a power domain then some state will be lost in
qcom_iommu_suspend and TZ will reset device if we don't call
qcom_scm_restore_sec_cfg before accessing it again.

Signed-off-by: Vladimir Lypak <vladimir.lypak@gmail.com>
[luca@z3ntu.xyz: reword commit message a bit]
Signed-off-by: Luca Weiss <luca@z3ntu.xyz>
Link: https://lore.kernel.org/r/20231011-msm8953-iommu-restore-v1-1-48a0c93809a2@z3ntu.xyz
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/qcom_iommu.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index 97b2122032b23..67abeb02cf536 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -900,8 +900,16 @@ static void qcom_iommu_device_remove(struct platform_device *pdev)
 static int __maybe_unused qcom_iommu_resume(struct device *dev)
 {
 	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+	if (ret < 0)
+		return ret;
+
+	if (dev->pm_domain)
+		return qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, 0);
 
-	return clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+	return ret;
 }
 
 static int __maybe_unused qcom_iommu_suspend(struct device *dev)
-- 
GitLab


From b41932f544586e606a7493cbc6dfb3c97c6b44d7 Mon Sep 17 00:00:00 2001
From: Wenkai Lin <linwenkai6@hisilicon.com>
Date: Wed, 6 Dec 2023 08:57:27 +0800
Subject: [PATCH 1166/4076] iommu/arm-smmu-v3: disable stall for quiet_cd

In the stall model, invalid transactions were expected to be
stalled and aborted by the IOPF handler.

However, when killing a test case with a huge amount of data, the
accelerator streamline can not stop until all data is consumed
even if the page fault handler reports errors. As a result, the
kill may take a long time, about 10 seconds with numerous iopf
interrupts.

So disable stall for quiet_cd in the non-force stall model, since
force stall model (STALL_MODEL==0b10) requires CD.S must be 1.

Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Wenkai Lin <linwenkai6@hisilicon.com>
Suggested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20231206005727.46150-1-zhangfei.gao@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 7445454c2af24..7086e5fa41ff6 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1063,6 +1063,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	bool cd_live;
 	__le64 *cdptr;
 	struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
+	struct arm_smmu_device *smmu = master->smmu;
 
 	if (WARN_ON(ssid >= (1 << cd_table->s1cdmax)))
 		return -E2BIG;
@@ -1077,6 +1078,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	if (!cd) { /* (5) */
 		val = 0;
 	} else if (cd == &quiet_cd) { /* (4) */
+		if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
+			val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R);
 		val |= CTXDESC_CD_0_TCR_EPD0;
 	} else if (cd_live) { /* (3) */
 		val &= ~CTXDESC_CD_0_ASID;
-- 
GitLab


From 1e536e10689700e006989dea33918cce348e04b6 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:37 -0800
Subject: [PATCH 1167/4076] x86/cpu: Detect TDX partial write machine check
 erratum

TDX memory has integrity and confidentiality protections.  Violations of
this integrity protection are supposed to only affect TDX operations and
are never supposed to affect the host kernel itself.  In other words,
the host kernel should never, itself, see machine checks induced by the
TDX integrity hardware.

Alas, the first few generations of TDX hardware have an erratum.  A
partial write to a TDX private memory cacheline will silently "poison"
the line.  Subsequent reads will consume the poison and generate a
machine check.  According to the TDX hardware spec, neither of these
things should have happened.

Virtually all kernel memory accesses operations happen in full
cachelines.  In practice, writing a "byte" of memory usually reads a 64
byte cacheline of memory, modifies it, then writes the whole line back.
Those operations do not trigger this problem.

This problem is triggered by "partial" writes where a write transaction
of less than cacheline lands at the memory controller.  The CPU does
these via non-temporal write instructions (like MOVNTI), or through
UC/WC memory mappings.  The issue can also be triggered away from the
CPU by devices doing partial writes via DMA.

With this erratum, there are additional things need to be done.  To
prepare for those changes, add a CPU bug bit to indicate this erratum.
Note this bug reflects the hardware thus it is detected regardless of
whether the kernel is built with TDX support or not.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-17-dave.hansen%40intel.com
---
 arch/x86/include/asm/cpufeatures.h |  1 +
 arch/x86/virt/vmx/tdx/tdx.c        | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 45ddc6b6baaa1..dbec4a0cf36a8 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -496,6 +496,7 @@
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 #define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */
 
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 6d030f64720ba..06b04b9c3236d 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -33,6 +33,8 @@
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
 #include <asm/tdx.h>
+#include <asm/intel-family.h>
+#include <asm/processor.h>
 #include "tdx.h"
 
 static u32 tdx_global_keyid __ro_after_init;
@@ -1308,6 +1310,21 @@ static struct notifier_block tdx_memory_nb = {
 	.notifier_call = tdx_memory_notifier,
 };
 
+static void __init check_tdx_erratum(void)
+{
+	/*
+	 * These CPUs have an erratum.  A partial write from non-TD
+	 * software (e.g. via MOVNTI variants or UC/WC mapping) to TDX
+	 * private memory poisons that memory, and a subsequent read of
+	 * that memory triggers #MC.
+	 */
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_SAPPHIRERAPIDS_X:
+	case INTEL_FAM6_EMERALDRAPIDS_X:
+		setup_force_cpu_bug(X86_BUG_TDX_PW_MCE);
+	}
+}
+
 void __init tdx_init(void)
 {
 	u32 tdx_keyid_start, nr_tdx_keyids;
@@ -1361,4 +1378,6 @@ void __init tdx_init(void)
 	tdx_nr_guest_keyids = nr_tdx_keyids - 1;
 
 	setup_force_cpu_cap(X86_FEATURE_TDX_HOST_PLATFORM);
+
+	check_tdx_erratum();
 }
-- 
GitLab


From 70060463cb2ba72bbb77c7ced503f53e09380f17 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:38 -0800
Subject: [PATCH 1168/4076] x86/mce: Differentiate real hardware #MCs from TDX
 erratum ones

The first few generations of TDX hardware have an erratum.  Triggering
it in Linux requires some kind of kernel bug involving relatively exotic
memory writes to TDX private memory and will manifest via
spurious-looking machine checks when reading the affected memory.

Make an effort to detect these TDX-induced machine checks and spit out
a new blurb to dmesg so folks do not think their hardware is failing.

== Background ==

Virtually all kernel memory accesses operations happen in full
cachelines.  In practice, writing a "byte" of memory usually reads a 64
byte cacheline of memory, modifies it, then writes the whole line back.
Those operations do not trigger this problem.

This problem is triggered by "partial" writes where a write transaction
of less than cacheline lands at the memory controller.  The CPU does
these via non-temporal write instructions (like MOVNTI), or through
UC/WC memory mappings.  The issue can also be triggered away from the
CPU by devices doing partial writes via DMA.

== Problem ==

A partial write to a TDX private memory cacheline will silently "poison"
the line.  Subsequent reads will consume the poison and generate a
machine check.  According to the TDX hardware spec, neither of these
things should have happened.

To add insult to injury, the Linux machine code will present these as a
literal "Hardware error" when they were, in fact, a software-triggered
issue.

== Solution ==

In the end, this issue is hard to trigger.  Rather than do something
rash (and incomplete) like unmap TDX private memory from the direct map,
improve the machine check handler.

Currently, the #MC handler doesn't distinguish whether the memory is
TDX private memory or not but just dump, for instance, below message:

 [...] mce: [Hardware Error]: CPU 147: Machine Check Exception: f Bank 1: bd80000000100134
 [...] mce: [Hardware Error]: RIP 10:<ffffffffadb69870> {__tlb_remove_page_size+0x10/0xa0}
 	...
 [...] mce: [Hardware Error]: Run the above through 'mcelog --ascii'
 [...] mce: [Hardware Error]: Machine check: Data load in unrecoverable area of kernel
 [...] Kernel panic - not syncing: Fatal local machine check

Which says "Hardware Error" and "Data load in unrecoverable area of
kernel".

Ideally, it's better for the log to say "software bug around TDX private
memory" instead of "Hardware Error".  But in reality the real hardware
memory error can happen, and sadly such software-triggered #MC cannot be
distinguished from the real hardware error.  Also, the error message is
used by userspace tool 'mcelog' to parse, so changing the output may
break userspace.

So keep the "Hardware Error".  The "Data load in unrecoverable area of
kernel" is also helpful, so keep it too.

Instead of modifying above error log, improve the error log by printing
additional TDX related message to make the log like:

  ...
 [...] mce: [Hardware Error]: Machine check: Data load in unrecoverable area of kernel
 [...] mce: [Hardware Error]: Machine Check: TDX private memory error. Possible kernel bug.

Adding this additional message requires determination of whether the
memory page is TDX private memory.  There is no existing infrastructure
to do that.  Add an interface to query the TDX module to fill this gap.

== Impact ==

This issue requires some kind of kernel bug to trigger.

TDX private memory should never be mapped UC/WC.  A partial write
originating from these mappings would require *two* bugs, first mapping
the wrong page, then writing the wrong memory.  It would also be
detectable using traditional memory corruption techniques like
DEBUG_PAGEALLOC.

MOVNTI (and friends) could cause this issue with something like a simple
buffer overrun or use-after-free on the direct map.  It should also be
detectable with normal debug techniques.

The one place where this might get nasty would be if the CPU read data
then wrote back the same data.  That would trigger this problem but
would not, for instance, set off mechanisms like slab redzoning because
it doesn't actually corrupt data.

With an IOMMU at least, the DMA exposure is similar to the UC/WC issue.
TDX private memory would first need to be incorrectly mapped into the
I/O space and then a later DMA to that mapping would actually cause the
poisoning event.

[ dhansen: changelog tweaks ]

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-18-dave.hansen%40intel.com
---
 arch/x86/include/asm/tdx.h     |   4 ++
 arch/x86/kernel/cpu/mce/core.c |  15 +++++
 arch/x86/virt/vmx/tdx/tdx.c    | 109 +++++++++++++++++++++++++++++++++
 arch/x86/virt/vmx/tdx/tdx.h    |   5 ++
 4 files changed, 133 insertions(+)

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index c54948e1999c0..eba178996d845 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -32,6 +32,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <uapi/asm/mce.h>
+
 /*
  * Used by the #VE exception handler to gather the #VE exception
  * info from the TDX module. This is a software only structure
@@ -113,10 +115,12 @@ static inline u64 sc_retry(sc_func_t func, u64 fn,
 #define seamcall_saved_ret(_fn, _args)	sc_retry(__seamcall_saved_ret, (_fn), (_args))
 int tdx_cpu_enable(void);
 int tdx_enable(void);
+const char *tdx_dump_mce_info(struct mce *m);
 #else
 static inline void tdx_init(void) { }
 static inline int tdx_cpu_enable(void) { return -ENODEV; }
 static inline int tdx_enable(void)  { return -ENODEV; }
+static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; }
 #endif	/* CONFIG_INTEL_TDX_HOST */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 7b397370b4d64..00d2b6b1dc24b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -52,6 +52,7 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/reboot.h>
+#include <asm/tdx.h>
 
 #include "internal.h"
 
@@ -228,11 +229,20 @@ static void wait_for_panic(void)
 	panic("Panicing machine check CPU died");
 }
 
+static const char *mce_dump_aux_info(struct mce *m)
+{
+	if (boot_cpu_has_bug(X86_BUG_TDX_PW_MCE))
+		return tdx_dump_mce_info(m);
+
+	return NULL;
+}
+
 static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 {
 	struct llist_node *pending;
 	struct mce_evt_llist *l;
 	int apei_err = 0;
+	const char *memmsg;
 
 	/*
 	 * Allow instrumentation around external facilities usage. Not that it
@@ -283,6 +293,11 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 	}
 	if (exp)
 		pr_emerg(HW_ERR "Machine check: %s\n", exp);
+
+	memmsg = mce_dump_aux_info(final);
+	if (memmsg)
+		pr_emerg(HW_ERR "Machine check: %s\n", memmsg);
+
 	if (!fake_panic) {
 		if (panic_timeout == 0)
 			panic_timeout = mca_cfg.panic_timeout;
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 06b04b9c3236d..4d6826a76f788 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -27,6 +27,7 @@
 #include <linux/log2.h>
 #include <linux/acpi.h>
 #include <linux/suspend.h>
+#include <linux/acpi.h>
 #include <asm/page.h>
 #include <asm/special_insns.h>
 #include <asm/msr-index.h>
@@ -35,6 +36,7 @@
 #include <asm/tdx.h>
 #include <asm/intel-family.h>
 #include <asm/processor.h>
+#include <asm/mce.h>
 #include "tdx.h"
 
 static u32 tdx_global_keyid __ro_after_init;
@@ -942,6 +944,13 @@ static int construct_tdmrs(struct list_head *tmb_list,
 	if (ret)
 		tdmrs_free_pamt_all(tdmr_list);
 
+	/*
+	 * The tdmr_info_list is read-only from here on out.
+	 * Ensure that these writes are seen by other CPUs.
+	 * Pairs with a smp_rmb() in is_pamt_page().
+	 */
+	smp_wmb();
+
 	return ret;
 }
 
@@ -1235,6 +1244,106 @@ int tdx_enable(void)
 }
 EXPORT_SYMBOL_GPL(tdx_enable);
 
+static bool is_pamt_page(unsigned long phys)
+{
+	struct tdmr_info_list *tdmr_list = &tdx_tdmr_list;
+	int i;
+
+	/* Ensure that all remote 'tdmr_list' writes are visible: */
+	smp_rmb();
+
+	/*
+	 * The TDX module is no longer returning TDX_SYS_NOT_READY and
+	 * is initialized.  The 'tdmr_list' was initialized long ago
+	 * and is now read-only.
+	 */
+	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
+		unsigned long base, size;
+
+		tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size);
+
+		if (phys >= base && phys < (base + size))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Return whether the memory page at the given physical address is TDX
+ * private memory or not.
+ *
+ * This can be imprecise for two known reasons:
+ * 1. PAMTs are private memory and exist before the TDX module is
+ *    ready and TDH_PHYMEM_PAGE_RDMD works.  This is a relatively
+ *    short window that occurs once per boot.
+ * 2. TDH_PHYMEM_PAGE_RDMD reflects the TDX module's knowledge of the
+ *    page.  However, the page can still cause #MC until it has been
+ *    fully converted to shared using 64-byte writes like MOVDIR64B.
+ *    Buggy hosts might still leave #MC-causing memory in place which
+ *    this function can not detect.
+ */
+static bool paddr_is_tdx_private(unsigned long phys)
+{
+	struct tdx_module_args args = {
+		.rcx = phys & PAGE_MASK,
+	};
+	u64 sret;
+
+	if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM))
+		return false;
+
+	/* Get page type from the TDX module */
+	sret = __seamcall_ret(TDH_PHYMEM_PAGE_RDMD, &args);
+
+	/*
+	 * The SEAMCALL will not return success unless there is a
+	 * working, "ready" TDX module.  Assume an absence of TDX
+	 * private pages until SEAMCALL is working.
+	 */
+	if (sret)
+		return false;
+
+	/*
+	 * SEAMCALL was successful -- read page type (via RCX):
+	 *
+	 *  - PT_NDA:	Page is not used by the TDX module
+	 *  - PT_RSVD:	Reserved for Non-TDX use
+	 *  - Others:	Page is used by the TDX module
+	 *
+	 * Note PAMT pages are marked as PT_RSVD but they are also TDX
+	 * private memory.
+	 */
+	switch (args.rcx) {
+	case PT_NDA:
+		return false;
+	case PT_RSVD:
+		return is_pamt_page(phys);
+	default:
+		return true;
+	}
+}
+
+/*
+ * Some TDX-capable CPUs have an erratum.  A write to TDX private
+ * memory poisons that memory, and a subsequent read of that memory
+ * triggers #MC.
+ *
+ * Help distinguish erratum-triggered #MCs from a normal hardware one.
+ * Just print additional message to show such #MC may be result of the
+ * erratum.
+ */
+const char *tdx_dump_mce_info(struct mce *m)
+{
+	if (!m || !mce_is_memory_error(m) || !mce_usable_address(m))
+		return NULL;
+
+	if (!paddr_is_tdx_private(m->addr))
+		return NULL;
+
+	return "TDX private memory error. Possible kernel bug.";
+}
+
 static __init int record_keyid_partitioning(u32 *tdx_keyid_start,
 					    u32 *nr_tdx_keyids)
 {
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index c0610f0bb88ce..b701f69485d32 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -14,6 +14,7 @@
 /*
  * TDX module SEAMCALL leaf functions
  */
+#define TDH_PHYMEM_PAGE_RDMD	24
 #define TDH_SYS_KEY_CONFIG	31
 #define TDH_SYS_INIT		33
 #define TDH_SYS_RD		34
@@ -21,6 +22,10 @@
 #define TDH_SYS_TDMR_INIT	36
 #define TDH_SYS_CONFIG		45
 
+/* TDX page types */
+#define	PT_NDA		0x0
+#define	PT_RSVD		0x1
+
 /*
  * Global scope metadata field ID.
  *
-- 
GitLab


From 4e1c7dddc71708c21d7fe69cc5f8297ffb7c6965 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Fri, 8 Dec 2023 09:07:39 -0800
Subject: [PATCH 1169/4076] Documentation/x86: Add documentation for TDX host
 support

Add documentation for TDX host kernel support.  There is already one
file Documentation/x86/tdx.rst containing documentation for TDX guest
internals.  Also reuse it for TDX host kernel support.

Introduce a new level menu "TDX Guest Support" and move existing
materials under it, and add a new menu for TDX host kernel support.

Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-19-dave.hansen%40intel.com
---
 Documentation/arch/x86/tdx.rst | 207 +++++++++++++++++++++++++++++++--
 1 file changed, 196 insertions(+), 11 deletions(-)

diff --git a/Documentation/arch/x86/tdx.rst b/Documentation/arch/x86/tdx.rst
index dc8d9fd2c3f76..719043cd8b469 100644
--- a/Documentation/arch/x86/tdx.rst
+++ b/Documentation/arch/x86/tdx.rst
@@ -10,6 +10,191 @@ encrypting the guest memory. In TDX, a special module running in a special
 mode sits between the host and the guest and manages the guest/host
 separation.
 
+TDX Host Kernel Support
+=======================
+
+TDX introduces a new CPU mode called Secure Arbitration Mode (SEAM) and
+a new isolated range pointed by the SEAM Ranger Register (SEAMRR).  A
+CPU-attested software module called 'the TDX module' runs inside the new
+isolated range to provide the functionalities to manage and run protected
+VMs.
+
+TDX also leverages Intel Multi-Key Total Memory Encryption (MKTME) to
+provide crypto-protection to the VMs.  TDX reserves part of MKTME KeyIDs
+as TDX private KeyIDs, which are only accessible within the SEAM mode.
+BIOS is responsible for partitioning legacy MKTME KeyIDs and TDX KeyIDs.
+
+Before the TDX module can be used to create and run protected VMs, it
+must be loaded into the isolated range and properly initialized.  The TDX
+architecture doesn't require the BIOS to load the TDX module, but the
+kernel assumes it is loaded by the BIOS.
+
+TDX boot-time detection
+-----------------------
+
+The kernel detects TDX by detecting TDX private KeyIDs during kernel
+boot.  Below dmesg shows when TDX is enabled by BIOS::
+
+  [..] virt/tdx: BIOS enabled: private KeyID range: [16, 64)
+
+TDX module initialization
+---------------------------------------
+
+The kernel talks to the TDX module via the new SEAMCALL instruction.  The
+TDX module implements SEAMCALL leaf functions to allow the kernel to
+initialize it.
+
+If the TDX module isn't loaded, the SEAMCALL instruction fails with a
+special error.  In this case the kernel fails the module initialization
+and reports the module isn't loaded::
+
+  [..] virt/tdx: module not loaded
+
+Initializing the TDX module consumes roughly ~1/256th system RAM size to
+use it as 'metadata' for the TDX memory.  It also takes additional CPU
+time to initialize those metadata along with the TDX module itself.  Both
+are not trivial.  The kernel initializes the TDX module at runtime on
+demand.
+
+Besides initializing the TDX module, a per-cpu initialization SEAMCALL
+must be done on one cpu before any other SEAMCALLs can be made on that
+cpu.
+
+The kernel provides two functions, tdx_enable() and tdx_cpu_enable() to
+allow the user of TDX to enable the TDX module and enable TDX on local
+cpu respectively.
+
+Making SEAMCALL requires VMXON has been done on that CPU.  Currently only
+KVM implements VMXON.  For now both tdx_enable() and tdx_cpu_enable()
+don't do VMXON internally (not trivial), but depends on the caller to
+guarantee that.
+
+To enable TDX, the caller of TDX should: 1) temporarily disable CPU
+hotplug; 2) do VMXON and tdx_enable_cpu() on all online cpus; 3) call
+tdx_enable().  For example::
+
+        cpus_read_lock();
+        on_each_cpu(vmxon_and_tdx_cpu_enable());
+        ret = tdx_enable();
+        cpus_read_unlock();
+        if (ret)
+                goto no_tdx;
+        // TDX is ready to use
+
+And the caller of TDX must guarantee the tdx_cpu_enable() has been
+successfully done on any cpu before it wants to run any other SEAMCALL.
+A typical usage is do both VMXON and tdx_cpu_enable() in CPU hotplug
+online callback, and refuse to online if tdx_cpu_enable() fails.
+
+User can consult dmesg to see whether the TDX module has been initialized.
+
+If the TDX module is initialized successfully, dmesg shows something
+like below::
+
+  [..] virt/tdx: 262668 KBs allocated for PAMT
+  [..] virt/tdx: module initialized
+
+If the TDX module failed to initialize, dmesg also shows it failed to
+initialize::
+
+  [..] virt/tdx: module initialization failed ...
+
+TDX Interaction to Other Kernel Components
+------------------------------------------
+
+TDX Memory Policy
+~~~~~~~~~~~~~~~~~
+
+TDX reports a list of "Convertible Memory Region" (CMR) to tell the
+kernel which memory is TDX compatible.  The kernel needs to build a list
+of memory regions (out of CMRs) as "TDX-usable" memory and pass those
+regions to the TDX module.  Once this is done, those "TDX-usable" memory
+regions are fixed during module's lifetime.
+
+To keep things simple, currently the kernel simply guarantees all pages
+in the page allocator are TDX memory.  Specifically, the kernel uses all
+system memory in the core-mm "at the time of TDX module initialization"
+as TDX memory, and in the meantime, refuses to online any non-TDX-memory
+in the memory hotplug.
+
+Physical Memory Hotplug
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Note TDX assumes convertible memory is always physically present during
+machine's runtime.  A non-buggy BIOS should never support hot-removal of
+any convertible memory.  This implementation doesn't handle ACPI memory
+removal but depends on the BIOS to behave correctly.
+
+CPU Hotplug
+~~~~~~~~~~~
+
+TDX module requires the per-cpu initialization SEAMCALL must be done on
+one cpu before any other SEAMCALLs can be made on that cpu.  The kernel
+provides tdx_cpu_enable() to let the user of TDX to do it when the user
+wants to use a new cpu for TDX task.
+
+TDX doesn't support physical (ACPI) CPU hotplug.  During machine boot,
+TDX verifies all boot-time present logical CPUs are TDX compatible before
+enabling TDX.  A non-buggy BIOS should never support hot-add/removal of
+physical CPU.  Currently the kernel doesn't handle physical CPU hotplug,
+but depends on the BIOS to behave correctly.
+
+Note TDX works with CPU logical online/offline, thus the kernel still
+allows to offline logical CPU and online it again.
+
+Kexec()
+~~~~~~~
+
+TDX host support currently lacks the ability to handle kexec.  For
+simplicity only one of them can be enabled in the Kconfig.  This will be
+fixed in the future.
+
+Erratum
+~~~~~~~
+
+The first few generations of TDX hardware have an erratum.  A partial
+write to a TDX private memory cacheline will silently "poison" the
+line.  Subsequent reads will consume the poison and generate a machine
+check.
+
+A partial write is a memory write where a write transaction of less than
+cacheline lands at the memory controller.  The CPU does these via
+non-temporal write instructions (like MOVNTI), or through UC/WC memory
+mappings.  Devices can also do partial writes via DMA.
+
+Theoretically, a kernel bug could do partial write to TDX private memory
+and trigger unexpected machine check.  What's more, the machine check
+code will present these as "Hardware error" when they were, in fact, a
+software-triggered issue.  But in the end, this issue is hard to trigger.
+
+If the platform has such erratum, the kernel prints additional message in
+machine check handler to tell user the machine check may be caused by
+kernel bug on TDX private memory.
+
+Interaction vs S3 and deeper states
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+TDX cannot survive from S3 and deeper states.  The hardware resets and
+disables TDX completely when platform goes to S3 and deeper.  Both TDX
+guests and the TDX module get destroyed permanently.
+
+The kernel uses S3 for suspend-to-ram, and use S4 and deeper states for
+hibernation.  Currently, for simplicity, the kernel chooses to make TDX
+mutually exclusive with S3 and hibernation.
+
+The kernel disables TDX during early boot when hibernation support is
+available::
+
+  [..] virt/tdx: initialization failed: Hibernation support is enabled
+
+Add 'nohibernate' kernel command line to disable hibernation in order to
+use TDX.
+
+ACPI S3 is disabled during kernel early boot if TDX is enabled.  The user
+needs to turn off TDX in the BIOS in order to use S3.
+
+TDX Guest Support
+=================
 Since the host cannot directly access guest registers or memory, much
 normal functionality of a hypervisor must be moved into the guest. This is
 implemented using a Virtualization Exception (#VE) that is handled by the
@@ -20,7 +205,7 @@ TDX includes new hypercall-like mechanisms for communicating from the
 guest to the hypervisor or the TDX module.
 
 New TDX Exceptions
-==================
+------------------
 
 TDX guests behave differently from bare-metal and traditional VMX guests.
 In TDX guests, otherwise normal instructions or memory accesses can cause
@@ -30,7 +215,7 @@ Instructions marked with an '*' conditionally cause exceptions.  The
 details for these instructions are discussed below.
 
 Instruction-based #VE
----------------------
+~~~~~~~~~~~~~~~~~~~~~
 
 - Port I/O (INS, OUTS, IN, OUT)
 - HLT
@@ -41,7 +226,7 @@ Instruction-based #VE
 - CPUID*
 
 Instruction-based #GP
----------------------
+~~~~~~~~~~~~~~~~~~~~~
 
 - All VMX instructions: INVEPT, INVVPID, VMCLEAR, VMFUNC, VMLAUNCH,
   VMPTRLD, VMPTRST, VMREAD, VMRESUME, VMWRITE, VMXOFF, VMXON
@@ -52,7 +237,7 @@ Instruction-based #GP
 - RDMSR*,WRMSR*
 
 RDMSR/WRMSR Behavior
---------------------
+~~~~~~~~~~~~~~~~~~~~
 
 MSR access behavior falls into three categories:
 
@@ -73,7 +258,7 @@ trapping and handling in the TDX module.  Other than possibly being slow,
 these MSRs appear to function just as they would on bare metal.
 
 CPUID Behavior
---------------
+~~~~~~~~~~~~~~
 
 For some CPUID leaves and sub-leaves, the virtualized bit fields of CPUID
 return values (in guest EAX/EBX/ECX/EDX) are configurable by the
@@ -93,7 +278,7 @@ not know how to handle. The guest kernel may ask the hypervisor for the
 value with a hypercall.
 
 #VE on Memory Accesses
-======================
+----------------------
 
 There are essentially two classes of TDX memory: private and shared.
 Private memory receives full TDX protections.  Its content is protected
@@ -107,7 +292,7 @@ entries.  This helps ensure that a guest does not place sensitive
 information in shared memory, exposing it to the untrusted hypervisor.
 
 #VE on Shared Memory
---------------------
+~~~~~~~~~~~~~~~~~~~~
 
 Access to shared mappings can cause a #VE.  The hypervisor ultimately
 controls whether a shared memory access causes a #VE, so the guest must be
@@ -127,7 +312,7 @@ be careful not to access device MMIO regions unless it is also prepared to
 handle a #VE.
 
 #VE on Private Pages
---------------------
+~~~~~~~~~~~~~~~~~~~~
 
 An access to private mappings can also cause a #VE.  Since all kernel
 memory is also private memory, the kernel might theoretically need to
@@ -145,7 +330,7 @@ The hypervisor is permitted to unilaterally move accepted pages to a
 to handle the exception.
 
 Linux #VE handler
-=================
+-----------------
 
 Just like page faults or #GP's, #VE exceptions can be either handled or be
 fatal.  Typically, an unhandled userspace #VE results in a SIGSEGV.
@@ -167,7 +352,7 @@ While the block is in place, any #VE is elevated to a double fault (#DF)
 which is not recoverable.
 
 MMIO handling
-=============
+-------------
 
 In non-TDX VMs, MMIO is usually implemented by giving a guest access to a
 mapping which will cause a VMEXIT on access, and then the hypervisor
@@ -189,7 +374,7 @@ MMIO access via other means (like structure overlays) may result in an
 oops.
 
 Shared Memory Conversions
-=========================
+-------------------------
 
 All TDX guest memory starts out as private at boot.  This memory can not
 be accessed by the hypervisor.  However, some kernel users like device
-- 
GitLab


From cb8eb06d50fcf4a478813a612f68c38cca45c742 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 8 Dec 2023 09:07:40 -0800
Subject: [PATCH 1170/4076] x86/virt/tdx: Disable TDX host support when kexec
 is enabled

TDX host support currently lacks the ability to handle kexec.  Disable TDX
when kexec is enabled.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20231208170740.53979-20-dave.hansen%40intel.com
---
 arch/x86/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e255d8ae5e77e..01cdb16acff6e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1973,6 +1973,7 @@ config INTEL_TDX_HOST
 	depends on X86_X2APIC
 	select ARCH_KEEP_MEMBLOCK
 	depends on CONTIG_ALLOC
+	depends on !KEXEC_CORE
 	help
 	  Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
 	  host and certain physical attacks.  This option enables necessary TDX
-- 
GitLab


From 48219b089d84f109e8a81d8a7fa1bbc2e6e5f97d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 28 Nov 2023 22:01:58 -0800
Subject: [PATCH 1171/4076] libperf cpumap: Rename perf_cpu_map__dummy_new() to
 perf_cpu_map__new_any_cpu()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename perf_cpu_map__dummy_new() to perf_cpu_map__new_any_cpu() to
better indicate this is creating a CPU map for the perf_event_open "any"
CPU case.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20231129060211.1890454-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/Documentation/libperf.txt | 2 +-
 tools/lib/perf/cpumap.c                  | 4 ++--
 tools/lib/perf/evsel.c                   | 2 +-
 tools/lib/perf/include/perf/cpumap.h     | 4 ++--
 tools/lib/perf/libperf.map               | 2 +-
 tools/lib/perf/tests/test-cpumap.c       | 2 +-
 tools/lib/perf/tests/test-evlist.c       | 2 +-
 tools/perf/tests/cpumap.c                | 2 +-
 tools/perf/tests/sw-clock.c              | 2 +-
 tools/perf/tests/task-exit.c             | 2 +-
 tools/perf/util/evlist.c                 | 2 +-
 tools/perf/util/evsel.c                  | 2 +-
 12 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index a8f1a237931b1..a256a26598b04 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -37,7 +37,7 @@ SYNOPSIS
 
   struct perf_cpu_map;
 
-  struct perf_cpu_map *perf_cpu_map__dummy_new(void);
+  struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
   struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
   struct perf_cpu_map *perf_cpu_map__read(FILE *file);
   struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 2a5a292173740..2bd6aba3d8c9a 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -27,7 +27,7 @@ struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
 	return result;
 }
 
-struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+struct perf_cpu_map *perf_cpu_map__new_any_cpu(void)
 {
 	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
 
@@ -271,7 +271,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	else if (*cpu_list != '\0')
 		cpus = cpu_map__default_new();
 	else
-		cpus = perf_cpu_map__dummy_new();
+		cpus = perf_cpu_map__new_any_cpu();
 invalid:
 	free(tmp_cpus);
 out:
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 8b51b008a81f1..c07160953224a 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -120,7 +120,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 		static struct perf_cpu_map *empty_cpu_map;
 
 		if (empty_cpu_map == NULL) {
-			empty_cpu_map = perf_cpu_map__dummy_new();
+			empty_cpu_map = perf_cpu_map__new_any_cpu();
 			if (empty_cpu_map == NULL)
 				return -ENOMEM;
 		}
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index e38d859a384d2..d0bf218ada119 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -19,9 +19,9 @@ struct perf_cache {
 struct perf_cpu_map;
 
 /**
- * perf_cpu_map__dummy_new - a map with a singular "any CPU"/dummy -1 value.
+ * perf_cpu_map__new_any_cpu - a map with a singular "any CPU"/dummy -1 value.
  */
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 190b56ae923ad..a8ff64baea3e1 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -1,7 +1,7 @@
 LIBPERF_0.0.1 {
 	global:
 		libperf_init;
-		perf_cpu_map__dummy_new;
+		perf_cpu_map__new_any_cpu;
 		perf_cpu_map__default_new;
 		perf_cpu_map__get;
 		perf_cpu_map__put;
diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index 87b0510a556ff..2c359bdb951ee 100644
--- a/tools/lib/perf/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
@@ -21,7 +21,7 @@ int test_cpumap(int argc, char **argv)
 
 	libperf_init(libperf_print);
 
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	if (!cpus)
 		return -1;
 
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index ed616fc19b4f2..ab63878bacb99 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -261,7 +261,7 @@ static int test_mmap_thread(void)
 	threads = perf_thread_map__new_dummy();
 	__T("failed to create threads", threads);
 
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	__T("failed to create cpus", cpus);
 
 	perf_thread_map__set_pid(threads, 0, pid);
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 7730fc2ab40b7..bd8e396f3e57b 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -213,7 +213,7 @@ static int test__cpu_map_intersect(struct test_suite *test __maybe_unused,
 
 static int test__cpu_map_equal(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
-	struct perf_cpu_map *any = perf_cpu_map__dummy_new();
+	struct perf_cpu_map *any = perf_cpu_map__new_any_cpu();
 	struct perf_cpu_map *one = perf_cpu_map__new("1");
 	struct perf_cpu_map *two = perf_cpu_map__new("2");
 	struct perf_cpu_map *empty = perf_cpu_map__intersect(one, two);
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 4d7493fa01059..290716783ac6a 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -62,7 +62,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	}
 	evlist__add(evlist, evsel);
 
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	threads = thread_map__new_by_tid(getpid());
 	if (!cpus || !threads) {
 		err = -ENOMEM;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 968dddde6ddaf..d33d0952025cf 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -70,7 +70,7 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _
 	 * evlist__prepare_workload we'll fill in the only thread
 	 * we're monitoring, the one forked there.
 	 */
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	threads = thread_map__new_by_tid(-1);
 	if (!cpus || !threads) {
 		err = -ENOMEM;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e36da58522efb..ff7f85ded89d7 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1056,7 +1056,7 @@ int evlist__create_maps(struct evlist *evlist, struct target *target)
 		return -1;
 
 	if (target__uses_dummy_map(target))
-		cpus = perf_cpu_map__dummy_new();
+		cpus = perf_cpu_map__new_any_cpu();
 	else
 		cpus = perf_cpu_map__new(target->cpu_list);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 532f34d9fcb50..6d7c9c58a9bcb 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1801,7 +1801,7 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 	if (cpus == NULL) {
 		if (empty_cpu_map == NULL) {
-			empty_cpu_map = perf_cpu_map__dummy_new();
+			empty_cpu_map = perf_cpu_map__new_any_cpu();
 			if (empty_cpu_map == NULL)
 				return -ENOMEM;
 		}
-- 
GitLab


From 8f60f870a9af53295ab4301da05ca453f115a6b6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 28 Nov 2023 22:01:59 -0800
Subject: [PATCH 1172/4076] libperf cpumap: Rename perf_cpu_map__default_new()
 to perf_cpu_map__new_online_cpus() and prefer sysfs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename perf_cpu_map__default_new() to perf_cpu_map__new_online_cpus() to
better indicate what the implementation does.

Read the online CPUs from /sys/devices/system/cpu/online first before
using sysconf() as it can't accurately configure holes in the CPU map.

If sysconf() is used, warn when the configured and online processors
disagree.

When reading from a file, if the read doesn't yield a CPU map then
return an empty map rather than the default online. This avoids
recursion but also better yields being able to detect failures.

Add more comments.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20231129060211.1890454-3-irogers@google.com
[ s/syfs/sysfs/g typo ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/cpumap.c              | 59 +++++++++++++++++-----------
 tools/lib/perf/include/perf/cpumap.h | 15 ++++++-
 tools/lib/perf/libperf.map           |  2 +-
 tools/lib/perf/tests/test-cpumap.c   |  2 +-
 4 files changed, 51 insertions(+), 27 deletions(-)

diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 2bd6aba3d8c9a..3aa80d0d26e86 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -9,6 +9,7 @@
 #include <unistd.h>
 #include <ctype.h>
 #include <limits.h>
+#include "internal.h"
 
 void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
 {
@@ -66,15 +67,21 @@ void perf_cpu_map__put(struct perf_cpu_map *map)
 	}
 }
 
-static struct perf_cpu_map *cpu_map__default_new(void)
+static struct perf_cpu_map *cpu_map__new_sysconf(void)
 {
 	struct perf_cpu_map *cpus;
-	int nr_cpus;
+	int nr_cpus, nr_cpus_conf;
 
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
 	if (nr_cpus < 0)
 		return NULL;
 
+	nr_cpus_conf = sysconf(_SC_NPROCESSORS_CONF);
+	if (nr_cpus != nr_cpus_conf) {
+		pr_warning("Number of online CPUs (%d) differs from the number configured (%d) the CPU map will only cover the first %d CPUs.",
+			nr_cpus, nr_cpus_conf, nr_cpus);
+	}
+
 	cpus = perf_cpu_map__alloc(nr_cpus);
 	if (cpus != NULL) {
 		int i;
@@ -86,9 +93,27 @@ static struct perf_cpu_map *cpu_map__default_new(void)
 	return cpus;
 }
 
-struct perf_cpu_map *perf_cpu_map__default_new(void)
+static struct perf_cpu_map *cpu_map__new_sysfs_online(void)
 {
-	return cpu_map__default_new();
+	struct perf_cpu_map *cpus = NULL;
+	FILE *onlnf;
+
+	onlnf = fopen("/sys/devices/system/cpu/online", "r");
+	if (onlnf) {
+		cpus = perf_cpu_map__read(onlnf);
+		fclose(onlnf);
+	}
+	return cpus;
+}
+
+struct perf_cpu_map *perf_cpu_map__new_online_cpus(void)
+{
+	struct perf_cpu_map *cpus = cpu_map__new_sysfs_online();
+
+	if (cpus)
+		return cpus;
+
+	return cpu_map__new_sysconf();
 }
 
 
@@ -180,27 +205,11 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 
 	if (nr_cpus > 0)
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else
-		cpus = cpu_map__default_new();
 out_free_tmp:
 	free(tmp_cpus);
 	return cpus;
 }
 
-static struct perf_cpu_map *cpu_map__read_all_cpu_map(void)
-{
-	struct perf_cpu_map *cpus = NULL;
-	FILE *onlnf;
-
-	onlnf = fopen("/sys/devices/system/cpu/online", "r");
-	if (!onlnf)
-		return cpu_map__default_new();
-
-	cpus = perf_cpu_map__read(onlnf);
-	fclose(onlnf);
-	return cpus;
-}
-
 struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 {
 	struct perf_cpu_map *cpus = NULL;
@@ -211,7 +220,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	int max_entries = 0;
 
 	if (!cpu_list)
-		return cpu_map__read_all_cpu_map();
+		return perf_cpu_map__new_online_cpus();
 
 	/*
 	 * must handle the case of empty cpumap to cover
@@ -268,9 +277,11 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 
 	if (nr_cpus > 0)
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else if (*cpu_list != '\0')
-		cpus = cpu_map__default_new();
-	else
+	else if (*cpu_list != '\0') {
+		pr_warning("Unexpected characters at end of cpu list ('%s'), using online CPUs.",
+			   cpu_list);
+		cpus = perf_cpu_map__new_online_cpus();
+	} else
 		cpus = perf_cpu_map__new_any_cpu();
 invalid:
 	free(tmp_cpus);
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index d0bf218ada119..b24bd8b8f34e1 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -22,7 +22,20 @@ struct perf_cpu_map;
  * perf_cpu_map__new_any_cpu - a map with a singular "any CPU"/dummy -1 value.
  */
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
+/**
+ * perf_cpu_map__new_online_cpus - a map read from
+ *                                 /sys/devices/system/cpu/online if
+ *                                 available. If reading wasn't possible a map
+ *                                 is created using the online processors
+ *                                 assuming the first 'n' processors are all
+ *                                 online.
+ */
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void);
+/**
+ * perf_cpu_map__new - create a map from the given cpu_list such as "0-7". If no
+ *                     cpu_list argument is provided then
+ *                     perf_cpu_map__new_online_cpus is returned.
+ */
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index a8ff64baea3e1..8a71f841498e4 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -2,7 +2,7 @@ LIBPERF_0.0.1 {
 	global:
 		libperf_init;
 		perf_cpu_map__new_any_cpu;
-		perf_cpu_map__default_new;
+		perf_cpu_map__new_online_cpus;
 		perf_cpu_map__get;
 		perf_cpu_map__put;
 		perf_cpu_map__new;
diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index 2c359bdb951ee..c998b1dae8631 100644
--- a/tools/lib/perf/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
@@ -29,7 +29,7 @@ int test_cpumap(int argc, char **argv)
 	perf_cpu_map__put(cpus);
 	perf_cpu_map__put(cpus);
 
-	cpus = perf_cpu_map__default_new();
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return -1;
 
-- 
GitLab


From 923ca62a7b1edceaa61eb6ac8dc56fdac51913b8 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 28 Nov 2023 22:02:00 -0800
Subject: [PATCH 1173/4076] libperf cpumap: Rename perf_cpu_map__empty() to
 perf_cpu_map__has_any_cpu_or_is_empty()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The name perf_cpu_map_empty is misleading as true is also returned
when the map contains an "any" CPU (aka dummy) map.

Rename to perf_cpu_map__has_any_cpu_or_is_empty(), later changes will
(re)introduce perf_cpu_map__empty() and perf_cpu_map__has_any_cpu().

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20231129060211.1890454-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/Documentation/libperf.txt |  2 +-
 tools/lib/perf/cpumap.c                  |  2 +-
 tools/lib/perf/evlist.c                  |  4 ++--
 tools/lib/perf/include/perf/cpumap.h     |  4 ++--
 tools/lib/perf/libperf.map               |  2 +-
 tools/perf/arch/arm/util/cs-etm.c        | 10 +++++-----
 tools/perf/arch/arm64/util/arm-spe.c     |  4 ++--
 tools/perf/arch/x86/util/intel-bts.c     |  4 ++--
 tools/perf/arch/x86/util/intel-pt.c      | 10 +++++-----
 tools/perf/builtin-c2c.c                 |  2 +-
 tools/perf/builtin-stat.c                |  6 +++---
 tools/perf/util/auxtrace.c               |  4 ++--
 tools/perf/util/record.c                 |  2 +-
 tools/perf/util/stat.c                   |  2 +-
 14 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index a256a26598b04..fcfb9499ef9cd 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -46,7 +46,7 @@ SYNOPSIS
   void perf_cpu_map__put(struct perf_cpu_map *map);
   int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
   int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
-  bool perf_cpu_map__empty(const struct perf_cpu_map *map);
+  bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
   int perf_cpu_map__max(struct perf_cpu_map *map);
   bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu);
 
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 3aa80d0d26e86..4adcd7920d033 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -311,7 +311,7 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 	return cpus ? __perf_cpu_map__nr(cpus) : 1;
 }
 
-bool perf_cpu_map__empty(const struct perf_cpu_map *map)
+bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map)
 {
 	return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true;
 }
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 3acbbccc19019..75f36218fdd98 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -619,7 +619,7 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
 
 	/* One for each CPU */
 	nr_mmaps = perf_cpu_map__nr(evlist->all_cpus);
-	if (perf_cpu_map__empty(evlist->all_cpus)) {
+	if (perf_cpu_map__has_any_cpu_or_is_empty(evlist->all_cpus)) {
 		/* Plus one for each thread */
 		nr_mmaps += perf_thread_map__nr(evlist->threads);
 		/* Minus the per-thread CPU (-1) */
@@ -653,7 +653,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
-	if (perf_cpu_map__empty(cpus))
+	if (perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 		return mmap_per_thread(evlist, ops, mp);
 
 	return mmap_per_cpu(evlist, ops, mp);
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index b24bd8b8f34e1..9cf361fc5edcb 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -47,9 +47,9 @@ LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 /**
- * perf_cpu_map__empty - is map either empty or the "any CPU"/dummy value.
+ * perf_cpu_map__has_any_cpu_or_is_empty - is map either empty or has the "any CPU"/dummy value.
  */
-LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
+LIBPERF_API bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 8a71f841498e4..10b3f37226426 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -9,7 +9,7 @@ LIBPERF_0.0.1 {
 		perf_cpu_map__read;
 		perf_cpu_map__nr;
 		perf_cpu_map__cpu;
-		perf_cpu_map__empty;
+		perf_cpu_map__has_any_cpu_or_is_empty;
 		perf_cpu_map__max;
 		perf_cpu_map__has;
 		perf_thread_map__new_array;
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2cf873d71dff0..c6b7b3066324e 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -211,7 +211,7 @@ static int cs_etm_validate_config(struct auxtrace_record *itr,
 		 * program can run on any CPUs in this case, thus don't skip
 		 * validation.
 		 */
-		if (!perf_cpu_map__empty(event_cpus) &&
+		if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus) &&
 		    !perf_cpu_map__has(event_cpus, cpu))
 			continue;
 
@@ -435,7 +435,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	 * Also the case of per-cpu mmaps, need the contextID in order to be notified
 	 * when a context switch happened.
 	 */
-	if (!perf_cpu_map__empty(cpus)) {
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 		evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
 					   "timestamp", 1);
 		evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
@@ -461,7 +461,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__empty(cpus))
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 		evsel__set_sample_bit(evsel, TIME);
 
 	err = cs_etm_validate_config(itr, cs_etm_evsel);
@@ -539,7 +539,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 
 	/* cpu map is not empty, we have specific CPUs to work with */
-	if (!perf_cpu_map__empty(event_cpus)) {
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
 		for (i = 0; i < cpu__max_cpu().cpu; i++) {
 			struct perf_cpu cpu = { .cpu = i, };
 
@@ -814,7 +814,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 		return -EINVAL;
 
 	/* If the cpu_map is empty all online CPUs are involved */
-	if (perf_cpu_map__empty(event_cpus)) {
+	if (perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
 		cpu_map = online_cpus;
 	} else {
 		/* Make sure all specified CPUs are online */
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index e3acc739bd002..51ccbfd3d246d 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -232,7 +232,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 * In the case of per-cpu mmaps, sample CPU for AUX event;
 	 * also enable the timestamp tracing for samples correlation.
 	 */
-	if (!perf_cpu_map__empty(cpus)) {
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(arm_spe_evsel, CPU);
 		evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
 					   "ts_enable", 1);
@@ -265,7 +265,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	tracking_evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__empty(cpus)) {
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(tracking_evsel, TIME);
 		evsel__set_sample_bit(tracking_evsel, CPU);
 
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index d2c8cac114702..af8ae4647585b 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -143,7 +143,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 	if (!opts->full_auxtrace)
 		return 0;
 
-	if (opts->full_auxtrace && !perf_cpu_map__empty(cpus)) {
+	if (opts->full_auxtrace && !perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 		pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n");
 		return -EINVAL;
 	}
@@ -224,7 +224,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
 		 */
-		if (!perf_cpu_map__empty(cpus))
+		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 			evsel__set_sample_bit(intel_bts_evsel, CPU);
 	}
 
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index fa0c718b9e727..d199619df3abe 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -369,7 +369,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 			ui__warning("Intel Processor Trace: TSC not available\n");
 	}
 
-	per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus);
+	per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(session->evlist->core.user_requested_cpus);
 
 	auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
 	auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
@@ -774,7 +774,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	 * Per-cpu recording needs sched_switch events to distinguish different
 	 * threads.
 	 */
-	if (have_timing_info && !perf_cpu_map__empty(cpus) &&
+	if (have_timing_info && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) &&
 	    !record_opts__no_switch_events(opts)) {
 		if (perf_can_record_switch_events()) {
 			bool cpu_wide = !target__none(&opts->target) &&
@@ -832,7 +832,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
 		 */
-		if (!perf_cpu_map__empty(cpus))
+		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 			evsel__set_sample_bit(intel_pt_evsel, CPU);
 	}
 
@@ -858,7 +858,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			tracking_evsel->immediate = true;
 
 		/* In per-cpu case, always need the time of mmap events etc */
-		if (!perf_cpu_map__empty(cpus)) {
+		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
 			evsel__set_sample_bit(tracking_evsel, TIME);
 			/* And the CPU for switch events */
 			evsel__set_sample_bit(tracking_evsel, CPU);
@@ -870,7 +870,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	 * Warn the user when we do not have enough information to decode i.e.
 	 * per-cpu with no sched_switch (except workload-only).
 	 */
-	if (!ptr->have_sched_switch && !perf_cpu_map__empty(cpus) &&
+	if (!ptr->have_sched_switch && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) &&
 	    !target__none(&opts->target) &&
 	    !intel_pt_evsel->core.attr.exclude_user)
 		ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n");
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index a4cf9de7a7b5a..f78eea9e21539 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2320,7 +2320,7 @@ static int setup_nodes(struct perf_session *session)
 		nodes[node] = set;
 
 		/* empty node, skip */
-		if (perf_cpu_map__empty(map))
+		if (perf_cpu_map__has_any_cpu_or_is_empty(map))
 			continue;
 
 		perf_cpu_map__for_each_cpu(cpu, idx, map) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0bfa70791cfcf..bda020c0b9d52 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1316,7 +1316,7 @@ static int cpu__get_cache_id_from_map(struct perf_cpu cpu, char *map)
 	 * be the first online CPU in the cache domain else use the
 	 * first online CPU of the cache domain as the ID.
 	 */
-	if (perf_cpu_map__empty(cpu_map))
+	if (perf_cpu_map__has_any_cpu_or_is_empty(cpu_map))
 		id = cpu.cpu;
 	else
 		id = perf_cpu_map__cpu(cpu_map, 0).cpu;
@@ -1622,7 +1622,7 @@ static int perf_stat_init_aggr_mode(void)
 	 * taking the highest cpu number to be the size of
 	 * the aggregation translate cpumap.
 	 */
-	if (!perf_cpu_map__empty(evsel_list->core.user_requested_cpus))
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(evsel_list->core.user_requested_cpus))
 		nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu;
 	else
 		nr = 0;
@@ -2289,7 +2289,7 @@ int process_stat_config_event(struct perf_session *session,
 
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 
-	if (perf_cpu_map__empty(st->cpus)) {
+	if (perf_cpu_map__has_any_cpu_or_is_empty(st->cpus)) {
 		if (st->aggr_mode != AGGR_UNSET)
 			pr_warning("warning: processing task data, aggregation mode not set\n");
 	} else if (st->aggr_mode != AGGR_UNSET) {
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index f528c4364d235..3684e6009b635 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct evlist *evlist,
 				   struct evsel *evsel, int idx)
 {
-	bool per_cpu = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
+	bool per_cpu = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
 
 	mp->mmap_needed = evsel->needs_auxtrace_mmap;
 
@@ -648,7 +648,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 
 static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
 {
-	bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
+	bool per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
 
 	if (per_cpu_mmaps) {
 		struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 9eb5c6a08999e..40290382b2d70 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -237,7 +237,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
 
 	evsel = evlist__last(temp_evlist);
 
-	if (!evlist || perf_cpu_map__empty(evlist->core.user_requested_cpus)) {
+	if (!evlist || perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) {
 		struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
 
 		if (cpus)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ec35060422173..012c4946b9c49 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -315,7 +315,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 	if (!counter->per_pkg)
 		return 0;
 
-	if (perf_cpu_map__empty(cpus))
+	if (perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 		return 0;
 
 	if (!mask) {
-- 
GitLab


From effe957c6bb70cac12918c0f5fd4cefb35967618 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 28 Nov 2023 22:02:01 -0800
Subject: [PATCH 1174/4076] libperf cpumap: Replace usage of
 perf_cpu_map__new(NULL) with perf_cpu_map__new_online_cpus()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Passing NULL to perf_cpu_map__new() performs
perf_cpu_map__new_online_cpus(), just directly call
perf_cpu_map__new_online_cpus() to be more intention revealing.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20231129060211.1890454-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/Documentation/examples/sampling.c  | 2 +-
 tools/lib/perf/Documentation/libperf-sampling.txt | 2 +-
 tools/lib/perf/evlist.c                           | 2 +-
 tools/lib/perf/tests/test-evlist.c                | 4 ++--
 tools/lib/perf/tests/test-evsel.c                 | 2 +-
 tools/perf/arch/arm/util/cs-etm.c                 | 6 +++---
 tools/perf/arch/arm64/util/header.c               | 2 +-
 tools/perf/bench/epoll-ctl.c                      | 2 +-
 tools/perf/bench/epoll-wait.c                     | 2 +-
 tools/perf/bench/futex-hash.c                     | 2 +-
 tools/perf/bench/futex-lock-pi.c                  | 2 +-
 tools/perf/bench/futex-requeue.c                  | 2 +-
 tools/perf/bench/futex-wake-parallel.c            | 2 +-
 tools/perf/bench/futex-wake.c                     | 2 +-
 tools/perf/builtin-ftrace.c                       | 2 +-
 tools/perf/tests/code-reading.c                   | 2 +-
 tools/perf/tests/keep-tracking.c                  | 2 +-
 tools/perf/tests/mmap-basic.c                     | 2 +-
 tools/perf/tests/openat-syscall-all-cpus.c        | 2 +-
 tools/perf/tests/perf-time-to-tsc.c               | 2 +-
 tools/perf/tests/switch-tracking.c                | 2 +-
 tools/perf/tests/topology.c                       | 2 +-
 tools/perf/util/bpf_counter.c                     | 2 +-
 tools/perf/util/cpumap.c                          | 2 +-
 tools/perf/util/cputopo.c                         | 2 +-
 tools/perf/util/evlist.c                          | 2 +-
 tools/perf/util/perf_api_probe.c                  | 4 ++--
 tools/perf/util/record.c                          | 2 +-
 28 files changed, 32 insertions(+), 32 deletions(-)

diff --git a/tools/lib/perf/Documentation/examples/sampling.c b/tools/lib/perf/Documentation/examples/sampling.c
index 8e1a926a9cfe6..bc142f0664b5a 100644
--- a/tools/lib/perf/Documentation/examples/sampling.c
+++ b/tools/lib/perf/Documentation/examples/sampling.c
@@ -39,7 +39,7 @@ int main(int argc, char **argv)
 
 	libperf_init(libperf_print);
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus) {
 		fprintf(stderr, "failed to create cpus\n");
 		return -1;
diff --git a/tools/lib/perf/Documentation/libperf-sampling.txt b/tools/lib/perf/Documentation/libperf-sampling.txt
index d6ca24f6ef78f..2378980fab8a6 100644
--- a/tools/lib/perf/Documentation/libperf-sampling.txt
+++ b/tools/lib/perf/Documentation/libperf-sampling.txt
@@ -97,7 +97,7 @@ In this case we will monitor all the available CPUs:
 
 [source,c]
 --
- 42         cpus = perf_cpu_map__new(NULL);
+ 42         cpus = perf_cpu_map__new_online_cpus();
  43         if (!cpus) {
  44                 fprintf(stderr, "failed to create cpus\n");
  45                 return -1;
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 75f36218fdd98..058e3ff10f9b2 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -39,7 +39,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	if (evsel->system_wide) {
 		/* System wide: set the cpu map of the evsel to all online CPUs. */
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__new(NULL);
+		evsel->cpus = perf_cpu_map__new_online_cpus();
 	} else if (evlist->has_user_cpus && evsel->is_pmu_core) {
 		/*
 		 * User requested CPUs on a core PMU, ensure the requested CPUs
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index ab63878bacb99..10f70cb41ff1d 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -46,7 +46,7 @@ static int test_stat_cpu(void)
 	};
 	int err, idx;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evlist = perf_evlist__new();
@@ -350,7 +350,7 @@ static int test_mmap_cpus(void)
 
 	attr.config = id;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evlist = perf_evlist__new();
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index a11fc51bfb688..545ec31505466 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -27,7 +27,7 @@ static int test_stat_cpu(void)
 	};
 	int err, idx;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evsel = perf_evsel__new(&attr);
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index c6b7b3066324e..77e6663c1703b 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -199,7 +199,7 @@ static int cs_etm_validate_config(struct auxtrace_record *itr,
 {
 	int i, err = -EINVAL;
 	struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 
 	/* Set option of each CPU we have */
 	for (i = 0; i < cpu__max_cpu().cpu; i++) {
@@ -536,7 +536,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 	int i;
 	int etmv3 = 0, etmv4 = 0, ete = 0;
 	struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 
 	/* cpu map is not empty, we have specific CPUs to work with */
 	if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
@@ -802,7 +802,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	u64 nr_cpu, type;
 	struct perf_cpu_map *cpu_map;
 	struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index a2eef9ec54910..97037499152ef 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -57,7 +57,7 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 
 int get_cpuid(char *buf, size_t sz)
 {
-	struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 	int ret;
 
 	if (!cpus)
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 6bfffe83dde99..d3db73dac66af 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -330,7 +330,7 @@ int bench_epoll_ctl(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		goto errmem;
 
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index cb5174b53940b..06bb3187660ab 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -444,7 +444,7 @@ int bench_epoll_wait(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		goto errmem;
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 2005a3fa30267..0c69d20efa329 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -138,7 +138,7 @@ int bench_futex_hash(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		goto errmem;
 
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 092cbd52db82b..7a4973346180f 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -172,7 +172,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	if (argc)
 		goto err;
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index c0035990a33ce..d9ad736c1a3e0 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -174,7 +174,7 @@ int bench_futex_requeue(int argc, const char **argv)
 	if (argc)
 		goto err;
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		err(EXIT_FAILURE, "cpu_map__new");
 
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 5ab0234d74e69..b66df553e5614 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -264,7 +264,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 			err(EXIT_FAILURE, "mlockall");
 	}
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 18a5894af8bb5..690fd6d3da130 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -149,7 +149,7 @@ int bench_futex_wake(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
-	cpu = perf_cpu_map__new(NULL);
+	cpu = perf_cpu_map__new_online_cpus();
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index ac2e6c75f9120..eb30c8eca4887 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -333,7 +333,7 @@ static int set_tracing_func_irqinfo(struct perf_ftrace *ftrace)
 
 static int reset_tracing_cpu(void)
 {
-	struct perf_cpu_map *cpumap = perf_cpu_map__new(NULL);
+	struct perf_cpu_map *cpumap = perf_cpu_map__new_online_cpus();
 	int ret;
 
 	ret = set_tracing_cpumask(cpumap);
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 8620146d03783..7a3a7bbbec714 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -610,7 +610,7 @@ static int do_test_code_reading(bool try_kcore)
 		goto out_put;
 	}
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus) {
 		pr_debug("perf_cpu_map__new failed\n");
 		goto out_put;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 8f4f9b632e1e5..5a3b2bed07f32 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -81,7 +81,7 @@ static int test__keep_tracking(struct test_suite *test __maybe_unused, int subte
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	CHECK_NOT_NULL__(cpus);
 
 	evlist = evlist__new();
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 886a13a77a162..012c8ae439fdc 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -52,7 +52,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
 		return -1;
 	}
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (cpus == NULL) {
 		pr_debug("perf_cpu_map__new\n");
 		goto out_free_threads;
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index f3275be83a338..fb114118c8764 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -37,7 +37,7 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
 		return -1;
 	}
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (cpus == NULL) {
 		pr_debug("perf_cpu_map__new\n");
 		goto out_thread_map_delete;
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index efcd71c2738af..bbe2ddeb9b745 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -93,7 +93,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	CHECK_NOT_NULL__(cpus);
 
 	evlist = evlist__new();
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index e52b031bedc5a..5cab17a1942e6 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -351,7 +351,7 @@ static int test__switch_tracking(struct test_suite *test __maybe_unused, int sub
 		goto out_err;
 	}
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus) {
 		pr_debug("perf_cpu_map__new failed!\n");
 		goto out_err;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 9dee63734e66a..2a842f53fbb57 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -215,7 +215,7 @@ static int test__session_topology(struct test_suite *test __maybe_unused, int su
 	if (session_write_header(path))
 		goto free_path;
 
-	map = perf_cpu_map__new(NULL);
+	map = perf_cpu_map__new_online_cpus();
 	if (map == NULL) {
 		pr_debug("failed to get system cpumap\n");
 		goto free_path;
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 7f9b0e46e008c..7a8af60e0f515 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -455,7 +455,7 @@ static int bperf__load(struct evsel *evsel, struct target *target)
 		return -1;
 
 	if (!all_cpu_map) {
-		all_cpu_map = perf_cpu_map__new(NULL);
+		all_cpu_map = perf_cpu_map__new_online_cpus();
 		if (!all_cpu_map)
 			return -1;
 	}
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 0e090e8bc3349..0581ee0fa5f27 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -672,7 +672,7 @@ struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
 	static struct perf_cpu_map *online;
 
 	if (!online)
-		online = perf_cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */
+		online = perf_cpu_map__new_online_cpus(); /* from /sys/devices/system/cpu/online */
 
 	return online;
 }
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index 81cfc85f46682..8bbeb2dc76fda 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -267,7 +267,7 @@ struct cpu_topology *cpu_topology__new(void)
 	ncpus = cpu__max_present_cpu().cpu;
 
 	/* build online CPU map */
-	map = perf_cpu_map__new(NULL);
+	map = perf_cpu_map__new_online_cpus();
 	if (map == NULL) {
 		pr_debug("failed to get system cpumap\n");
 		return NULL;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ff7f85ded89d7..0ed3ce2aa8ebf 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1352,7 +1352,7 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
 	 * error, and we may not want to do that fallback to a
 	 * default cpu identity map :-\
 	 */
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		goto out;
 
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index e1e2d701599c4..1de3b69cdf4aa 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -64,7 +64,7 @@ static bool perf_probe_api(setup_probe_fn_t fn)
 	struct perf_cpu cpu;
 	int ret, i = 0;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return false;
 	cpu = perf_cpu_map__cpu(cpus, 0);
@@ -140,7 +140,7 @@ bool perf_can_record_cpu_wide(void)
 	struct perf_cpu cpu;
 	int fd;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return false;
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 40290382b2d70..87e817b3cf7e9 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -238,7 +238,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
 	evsel = evlist__last(temp_evlist);
 
 	if (!evlist || perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) {
-		struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+		struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 
 		if (cpus)
 			cpu =  perf_cpu_map__cpu(cpus, 0);
-- 
GitLab


From 5805c82513c444333efb086017be8d666336858a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 28 Nov 2023 22:02:02 -0800
Subject: [PATCH 1175/4076] libperf cpumap: Add for_each_cpu() that skips the
 "any CPU" case
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When iterating CPUs in a CPU map it is often desirable to skip the "any
CPU" (aka dummy) case. Add a helper for this and use in builtin-record.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20231129060211.1890454-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/include/perf/cpumap.h | 6 ++++++
 tools/perf/builtin-record.c          | 4 +---
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 9cf361fc5edcb..dbe0a7352b648 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -64,6 +64,12 @@ LIBPERF_API bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map);
 	     (idx) < perf_cpu_map__nr(cpus);			\
 	     (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx))
 
+#define perf_cpu_map__for_each_cpu_skip_any(_cpu, idx, cpus)	\
+	for ((idx) = 0, (_cpu) = perf_cpu_map__cpu(cpus, idx);	\
+	     (idx) < perf_cpu_map__nr(cpus);			\
+	     (idx)++, (_cpu) = perf_cpu_map__cpu(cpus, idx))	\
+		if ((_cpu).cpu != -1)
+
 #define perf_cpu_map__for_each_idx(idx, cpus)				\
 	for ((idx) = 0; (idx) < perf_cpu_map__nr(cpus); (idx)++)
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index eb5a398ddb1d8..8a1002683fda2 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -3601,9 +3601,7 @@ static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cp
 	if (cpu_map__is_dummy(cpus))
 		return 0;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
-		if (cpu.cpu == -1)
-			continue;
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, cpus) {
 		/* Return ENODEV is input cpu is greater than max cpu */
 		if ((unsigned long)cpu.cpu > mask->nbits)
 			return -ENODEV;
-- 
GitLab


From 4a8be01a1a7a030ae7b6138602d2e060cf7a0946 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Mon, 11 Dec 2023 16:23:24 +0000
Subject: [PATCH 1176/4076] pinctrl: samsung: Add gs101 SoC pinctrl
 configuration

Add support for the pin-controller found on the gs101 SoC used in
Pixel 6 phones.

Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231211162331.435900-10-peter.griffin@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../pinctrl/samsung/pinctrl-exynos-arm64.c    | 140 ++++++++++++++++++
 drivers/pinctrl/samsung/pinctrl-samsung.c     |   2 +
 drivers/pinctrl/samsung/pinctrl-samsung.h     |   1 +
 3 files changed, 143 insertions(+)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
index cb965cf937057..8d08b29a21f6b 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
@@ -796,3 +796,143 @@ const struct samsung_pinctrl_of_match_data fsd_of_data __initconst = {
 	.ctrl		= fsd_pin_ctrl,
 	.num_ctrl	= ARRAY_SIZE(fsd_pin_ctrl),
 };
+
+/* pin banks of gs101 pin-controller (ALIVE) */
+static const struct samsung_pin_bank_data gs101_pin_alive[] = {
+	EXYNOS850_PIN_BANK_EINTW(8, 0x0, "gpa0", 0x00),
+	EXYNOS850_PIN_BANK_EINTW(7, 0x20, "gpa1", 0x04),
+	EXYNOS850_PIN_BANK_EINTW(5, 0x40, "gpa2", 0x08),
+	EXYNOS850_PIN_BANK_EINTW(4, 0x60, "gpa3", 0x0c),
+	EXYNOS850_PIN_BANK_EINTW(4, 0x80, "gpa4", 0x10),
+	EXYNOS850_PIN_BANK_EINTW(7, 0xa0, "gpa5", 0x14),
+	EXYNOS850_PIN_BANK_EINTW(8, 0xc0, "gpa9", 0x18),
+	EXYNOS850_PIN_BANK_EINTW(2, 0xe0, "gpa10", 0x1c),
+};
+
+/* pin banks of gs101 pin-controller (FAR_ALIVE) */
+static const struct samsung_pin_bank_data gs101_pin_far_alive[] = {
+	EXYNOS850_PIN_BANK_EINTW(8, 0x0, "gpa6", 0x00),
+	EXYNOS850_PIN_BANK_EINTW(4, 0x20, "gpa7", 0x04),
+	EXYNOS850_PIN_BANK_EINTW(8, 0x40, "gpa8", 0x08),
+	EXYNOS850_PIN_BANK_EINTW(2, 0x60, "gpa11", 0x0c),
+};
+
+/* pin banks of gs101 pin-controller (GSACORE) */
+static const struct samsung_pin_bank_data gs101_pin_gsacore[] = {
+	EXYNOS850_PIN_BANK_EINTG(2, 0x0, "gps0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x20, "gps1", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(3, 0x40, "gps2", 0x08),
+};
+
+/* pin banks of gs101 pin-controller (GSACTRL) */
+static const struct samsung_pin_bank_data gs101_pin_gsactrl[] = {
+	EXYNOS850_PIN_BANK_EINTW(6, 0x0, "gps3", 0x00),
+};
+
+/* pin banks of gs101 pin-controller (PERIC0) */
+static const struct samsung_pin_bank_data gs101_pin_peric0[] = {
+	EXYNOS850_PIN_BANK_EINTG(5, 0x0, "gpp0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x20, "gpp1", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x40, "gpp2", 0x08),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x60, "gpp3", 0x0c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x80, "gpp4", 0x10),
+	EXYNOS850_PIN_BANK_EINTG(2, 0xa0, "gpp5", 0x14),
+	EXYNOS850_PIN_BANK_EINTG(4, 0xc0, "gpp6", 0x18),
+	EXYNOS850_PIN_BANK_EINTG(2, 0xe0, "gpp7", 0x1c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x100, "gpp8", 0x20),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x120, "gpp9", 0x24),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x140, "gpp10", 0x28),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x160, "gpp11", 0x2c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x180, "gpp12", 0x30),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x1a0, "gpp13", 0x34),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x1c0, "gpp14", 0x38),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x1e0, "gpp15", 0x3c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x200, "gpp16", 0x40),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x220, "gpp17", 0x44),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x240, "gpp18", 0x48),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x260, "gpp19", 0x4c),
+};
+
+/* pin banks of gs101 pin-controller (PERIC1) */
+static const struct samsung_pin_bank_data gs101_pin_peric1[] = {
+	EXYNOS850_PIN_BANK_EINTG(8, 0x0, "gpp20", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x20, "gpp21", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x40, "gpp22", 0x08),
+	EXYNOS850_PIN_BANK_EINTG(8, 0x60, "gpp23", 0x0c),
+	EXYNOS850_PIN_BANK_EINTG(4, 0x80, "gpp24", 0x10),
+	EXYNOS850_PIN_BANK_EINTG(4, 0xa0, "gpp25", 0x14),
+	EXYNOS850_PIN_BANK_EINTG(5, 0xc0, "gpp26", 0x18),
+	EXYNOS850_PIN_BANK_EINTG(4, 0xe0, "gpp27", 0x1c),
+};
+
+/* pin banks of gs101 pin-controller (HSI1) */
+static const struct samsung_pin_bank_data gs101_pin_hsi1[] = {
+	EXYNOS850_PIN_BANK_EINTG(6, 0x0, "gph0", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(7, 0x20, "gph1", 0x04),
+};
+
+/* pin banks of gs101 pin-controller (HSI2) */
+static const struct samsung_pin_bank_data gs101_pin_hsi2[] = {
+	EXYNOS850_PIN_BANK_EINTG(6, 0x0, "gph2", 0x00),
+	EXYNOS850_PIN_BANK_EINTG(2, 0x20, "gph3", 0x04),
+	EXYNOS850_PIN_BANK_EINTG(6, 0x40, "gph4", 0x08),
+};
+
+static const struct samsung_pin_ctrl gs101_pin_ctrl[] __initconst = {
+	{
+		/* pin banks of gs101 pin-controller (ALIVE) */
+		.pin_banks	= gs101_pin_alive,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_alive),
+		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (FAR_ALIVE) */
+		.pin_banks	= gs101_pin_far_alive,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_far_alive),
+		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (GSACORE) */
+		.pin_banks	= gs101_pin_gsacore,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_gsacore),
+	}, {
+		/* pin banks of gs101 pin-controller (GSACTRL) */
+		.pin_banks	= gs101_pin_gsactrl,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_gsactrl),
+	}, {
+		/* pin banks of gs101 pin-controller (PERIC0) */
+		.pin_banks	= gs101_pin_peric0,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_peric0),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (PERIC1) */
+		.pin_banks	= gs101_pin_peric1,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_peric1),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume	= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (HSI1) */
+		.pin_banks	= gs101_pin_hsi1,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_hsi1),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin banks of gs101 pin-controller (HSI2) */
+		.pin_banks	= gs101_pin_hsi2,
+		.nr_banks	= ARRAY_SIZE(gs101_pin_hsi2),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	},
+};
+
+const struct samsung_pinctrl_of_match_data gs101_of_data __initconst = {
+	.ctrl		= gs101_pin_ctrl,
+	.num_ctrl	= ARRAY_SIZE(gs101_pin_ctrl),
+};
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 79babbb39cedb..5ad92600320e7 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1309,6 +1309,8 @@ static const struct of_device_id samsung_pinctrl_dt_match[] = {
 		.data = &s5pv210_of_data },
 #endif
 #ifdef CONFIG_PINCTRL_EXYNOS_ARM64
+	{ .compatible = "google,gs101-pinctrl",
+		.data = &gs101_of_data },
 	{ .compatible = "samsung,exynos5433-pinctrl",
 		.data = &exynos5433_of_data },
 	{ .compatible = "samsung,exynos7-pinctrl",
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index 9b3db50adef32..0b459651bc4aa 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -351,6 +351,7 @@ extern const struct samsung_pinctrl_of_match_data exynos7885_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos850_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov9_of_data;
 extern const struct samsung_pinctrl_of_match_data fsd_of_data;
+extern const struct samsung_pinctrl_of_match_data gs101_of_data;
 extern const struct samsung_pinctrl_of_match_data s3c64xx_of_data;
 extern const struct samsung_pinctrl_of_match_data s3c2412_of_data;
 extern const struct samsung_pinctrl_of_match_data s3c2416_of_data;
-- 
GitLab


From e45f463a9b01aabd03c49390fc5249eeba0abc5e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:37 -0500
Subject: [PATCH 1177/4076] riscv: add ISA extension parsing for Zbc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Zbc was documented in the dt-bindings but actually not supported in ISA
string parsing. Add it.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-2-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 1 +
 arch/riscv/kernel/cpufeature.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 06d30526ef3b8..afa9abc1a0b0f 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -57,6 +57,7 @@
 #define RISCV_ISA_EXT_ZIHPM		42
 #define RISCV_ISA_EXT_SMSTATEEN		43
 #define RISCV_ISA_EXT_ZICOND		44
+#define RISCV_ISA_EXT_ZBC		45
 
 #define RISCV_ISA_EXT_MAX		64
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index b3785ffc15703..eae14daa5a75b 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -176,6 +176,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
 	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
 	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
+	__RISCV_ISA_EXT_DATA(zbc, RISCV_ISA_EXT_ZBC),
 	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
 	__RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN),
-- 
GitLab


From be6bef2acb75ca980671de19d406c0310d646d2b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:38 -0500
Subject: [PATCH 1178/4076] riscv: hwprobe: export missing Zbc ISA extension
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While Zba and Zbb were exported through hwprobe, Zbc was not. Export it.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-3-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 3 +++
 arch/riscv/include/uapi/asm/hwprobe.h | 1 +
 arch/riscv/kernel/sys_riscv.c         | 1 +
 3 files changed, 5 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 7b2384de471f8..3f71da935a657 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -80,6 +80,9 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZICBOZ`: The Zicboz extension is supported, as
        ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBC` The Zbc extension is supported, as defined
+       in version 1.0 of the Bit-Manipulation ISA extensions.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index b659ffcfcdb45..aca5abc7ebee5 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -30,6 +30,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZBB		(1 << 4)
 #define		RISCV_HWPROBE_EXT_ZBS		(1 << 5)
 #define		RISCV_HWPROBE_EXT_ZICBOZ	(1 << 6)
+#define		RISCV_HWPROBE_EXT_ZBC		(1 << 7)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index c712037dbe10e..7a40145e96285 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -162,6 +162,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZBB);
 		EXT_KEY(ZBS);
 		EXT_KEY(ZICBOZ);
+		EXT_KEY(ZBC);
 #undef EXT_KEY
 	}
 
-- 
GitLab


From 0d8295ed975b6df487f0b4018770a60b070fc76d Mon Sep 17 00:00:00 2001
From: Evan Green <evan@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:39 -0500
Subject: [PATCH 1179/4076] riscv: add ISA extension parsing for scalar crypto
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Scalar Crypto specification defines Zk as a shorthand for the
Zkn, Zkr and Zkt extensions. The same follows for both Zkn, Zks and Zbk,
which are all shorthands for various other extensions. The detailed
breakdown can be found in their dt-binding entries.

Since Zkn also implies the Zbkb, Zbkc and Zbkx extensions, simply passing
"zk" through a DT should enable all of Zbkb, Zbkc, Zbkx, Zkn, Zkr and Zkt.
For example, setting the "riscv,isa" DT property to "rv64imafdc_zk"
should generate the following cpuinfo output:
"rv64imafdc_zicntr_zicsr_zifencei_zihpm_zbkb_zbkc_zbkx_zknd_zkne_zknh_zkr_zkt"

riscv_isa_ext_data grows a pair of new members, to permit setting the
relevant bits for "bundled" extensions, both while parsing the ISA string
and the new dedicated extension properties.

Co-developed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Evan Green <evan@rivosinc.com>
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114141256.126749-4-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cpufeature.h |   4 +-
 arch/riscv/include/asm/hwcap.h      |  11 +++
 arch/riscv/kernel/cpufeature.c      | 118 ++++++++++++++++++++++------
 3 files changed, 109 insertions(+), 24 deletions(-)

diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index a418c3112cd60..fbdde8b8a47ed 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -59,6 +59,8 @@ struct riscv_isa_ext_data {
 	const unsigned int id;
 	const char *name;
 	const char *property;
+	const unsigned int *subset_ext_ids;
+	const unsigned int subset_ext_size;
 };
 
 extern const struct riscv_isa_ext_data riscv_isa_ext[];
@@ -67,7 +69,7 @@ extern bool riscv_isa_fallback;
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
 
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
 #define riscv_isa_extension_available(isa_bitmap, ext)	\
 	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
 
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index afa9abc1a0b0f..b0857c64bf6e4 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -58,8 +58,19 @@
 #define RISCV_ISA_EXT_SMSTATEEN		43
 #define RISCV_ISA_EXT_ZICOND		44
 #define RISCV_ISA_EXT_ZBC		45
+#define RISCV_ISA_EXT_ZBKB		46
+#define RISCV_ISA_EXT_ZBKC		47
+#define RISCV_ISA_EXT_ZBKX		48
+#define RISCV_ISA_EXT_ZKND		49
+#define RISCV_ISA_EXT_ZKNE		50
+#define RISCV_ISA_EXT_ZKNH		51
+#define RISCV_ISA_EXT_ZKR		52
+#define RISCV_ISA_EXT_ZKSED		53
+#define RISCV_ISA_EXT_ZKSH		54
+#define RISCV_ISA_EXT_ZKT		55
 
 #define RISCV_ISA_EXT_MAX		64
+#define RISCV_ISA_EXT_INVALID		U32_MAX
 
 #ifdef CONFIG_RISCV_M_MODE
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SMAIA
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index eae14daa5a75b..a2871bceaad97 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -70,7 +70,7 @@ EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
  *
  * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
  */
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit)
 {
 	const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
 
@@ -102,17 +102,53 @@ static bool riscv_isa_extension_check(int id)
 			return false;
 		}
 		return true;
+	case RISCV_ISA_EXT_INVALID:
+		return false;
 	}
 
 	return true;
 }
 
-#define __RISCV_ISA_EXT_DATA(_name, _id) {	\
-	.name = #_name,				\
-	.property = #_name,			\
-	.id = _id,				\
+#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size) {	\
+	.name = #_name,								\
+	.property = #_name,							\
+	.id = _id,								\
+	.subset_ext_ids = _subset_exts,						\
+	.subset_ext_size = _subset_exts_size					\
 }
 
+#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0)
+
+/* Used to declare pure "lasso" extension (Zk for instance) */
+#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
+	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, ARRAY_SIZE(_bundled_exts))
+
+static const unsigned int riscv_zk_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZBKX,
+	RISCV_ISA_EXT_ZKND,
+	RISCV_ISA_EXT_ZKNE,
+	RISCV_ISA_EXT_ZKR,
+	RISCV_ISA_EXT_ZKT,
+};
+
+static const unsigned int riscv_zkn_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZBKX,
+	RISCV_ISA_EXT_ZKND,
+	RISCV_ISA_EXT_ZKNE,
+	RISCV_ISA_EXT_ZKNH,
+};
+
+static const unsigned int riscv_zks_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZKSED,
+	RISCV_ISA_EXT_ZKSH
+};
+
 /*
  * The canonical order of ISA extension names in the ISA string is defined in
  * chapter 27 of the unprivileged specification.
@@ -177,7 +213,20 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
 	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
 	__RISCV_ISA_EXT_DATA(zbc, RISCV_ISA_EXT_ZBC),
+	__RISCV_ISA_EXT_DATA(zbkb, RISCV_ISA_EXT_ZBKB),
+	__RISCV_ISA_EXT_DATA(zbkc, RISCV_ISA_EXT_ZBKC),
+	__RISCV_ISA_EXT_DATA(zbkx, RISCV_ISA_EXT_ZBKX),
 	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
+	__RISCV_ISA_EXT_BUNDLE(zk, riscv_zk_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zkn, riscv_zkn_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zknd, RISCV_ISA_EXT_ZKND),
+	__RISCV_ISA_EXT_DATA(zkne, RISCV_ISA_EXT_ZKNE),
+	__RISCV_ISA_EXT_DATA(zknh, RISCV_ISA_EXT_ZKNH),
+	__RISCV_ISA_EXT_DATA(zkr, RISCV_ISA_EXT_ZKR),
+	__RISCV_ISA_EXT_BUNDLE(zks, riscv_zks_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zkt, RISCV_ISA_EXT_ZKT),
+	__RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED),
+	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
 	__RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN),
 	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
@@ -190,6 +239,31 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 
 const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
 
+static void __init match_isa_ext(const struct riscv_isa_ext_data *ext, const char *name,
+				 const char *name_end, struct riscv_isainfo *isainfo)
+{
+	if ((name_end - name == strlen(ext->name)) &&
+	     !strncasecmp(name, ext->name, name_end - name)) {
+		/*
+		 * If this is a bundle, enable all the ISA extensions that
+		 * comprise the bundle.
+		 */
+		if (ext->subset_ext_size) {
+			for (int i = 0; i < ext->subset_ext_size; i++) {
+				if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+					set_bit(ext->subset_ext_ids[i], isainfo->isa);
+			}
+		}
+
+		/*
+		 * This is valid even for bundle extensions which uses the RISCV_ISA_EXT_INVALID id
+		 * (rejected by riscv_isa_extension_check()).
+		 */
+		if (riscv_isa_extension_check(ext->id))
+			set_bit(ext->id, isainfo->isa);
+	}
+}
+
 static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo,
 					  unsigned long *isa2hwcap, const char *isa)
 {
@@ -322,14 +396,6 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 		if (*isa == '_')
 			++isa;
 
-#define SET_ISA_EXT_MAP(name, bit)						\
-		do {								\
-			if ((ext_end - ext == strlen(name)) &&			\
-			     !strncasecmp(ext, name, strlen(name)) &&		\
-			     riscv_isa_extension_check(bit))			\
-				set_bit(bit, isainfo->isa);			\
-		} while (false)							\
-
 		if (unlikely(ext_err))
 			continue;
 		if (!ext_long) {
@@ -341,10 +407,8 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 			}
 		} else {
 			for (int i = 0; i < riscv_isa_ext_count; i++)
-				SET_ISA_EXT_MAP(riscv_isa_ext[i].name,
-						riscv_isa_ext[i].id);
+				match_isa_ext(&riscv_isa_ext[i], ext, ext_end, isainfo);
 		}
-#undef SET_ISA_EXT_MAP
 	}
 }
 
@@ -443,18 +507,26 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 		}
 
 		for (int i = 0; i < riscv_isa_ext_count; i++) {
+			const struct riscv_isa_ext_data *ext = &riscv_isa_ext[i];
+
 			if (of_property_match_string(cpu_node, "riscv,isa-extensions",
-						     riscv_isa_ext[i].property) < 0)
+						     ext->property) < 0)
 				continue;
 
-			if (!riscv_isa_extension_check(riscv_isa_ext[i].id))
-				continue;
+			if (ext->subset_ext_size) {
+				for (int j = 0; j < ext->subset_ext_size; j++) {
+					if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+						set_bit(ext->subset_ext_ids[j], isainfo->isa);
+				}
+			}
 
-			/* Only single letter extensions get set in hwcap */
-			if (strnlen(riscv_isa_ext[i].name, 2) == 1)
-				this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+			if (riscv_isa_extension_check(ext->id)) {
+				set_bit(ext->id, isainfo->isa);
 
-			set_bit(riscv_isa_ext[i].id, isainfo->isa);
+				/* Only single letter extensions get set in hwcap */
+				if (strnlen(riscv_isa_ext[i].name, 2) == 1)
+					this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+			}
 		}
 
 		of_node_put(cpu_node);
-- 
GitLab


From 794983f292cd71b27106f1226360b2cf0f4a881b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:40 -0500
Subject: [PATCH 1180/4076] riscv: hwprobe: add support for scalar crypto ISA
 extensions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export the following scalar crypto extensions through hwprobe:

- Zbkb
- Zbkc
- Zbkx
- Zknd
- Zkne
- Zknh
- Zksed
- Zksh
- Zkt

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-5-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 27 +++++++++++++++++++++++++++
 arch/riscv/include/uapi/asm/hwprobe.h |  9 +++++++++
 arch/riscv/kernel/sys_riscv.c         | 10 ++++++++++
 3 files changed, 46 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 3f71da935a657..3a18a31e32c36 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -83,6 +83,33 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZBC` The Zbc extension is supported, as defined
        in version 1.0 of the Bit-Manipulation ISA extensions.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKB` The Zbkb extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKC` The Zbkc extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBKX` The Zbkx extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKND` The Zknd extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKNE` The Zkne extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKNH` The Zknh extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKSED` The Zksed extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKSH` The Zksh extension is supported, as
+       defined in version 1.0 of the Scalar Crypto ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZKT` The Zkt extension is supported, as defined
+       in version 1.0 of the Scalar Crypto ISA extensions.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index aca5abc7ebee5..624abd5cde293 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -31,6 +31,15 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZBS		(1 << 5)
 #define		RISCV_HWPROBE_EXT_ZICBOZ	(1 << 6)
 #define		RISCV_HWPROBE_EXT_ZBC		(1 << 7)
+#define		RISCV_HWPROBE_EXT_ZBKB		(1 << 8)
+#define		RISCV_HWPROBE_EXT_ZBKC		(1 << 9)
+#define		RISCV_HWPROBE_EXT_ZBKX		(1 << 10)
+#define		RISCV_HWPROBE_EXT_ZKND		(1 << 11)
+#define		RISCV_HWPROBE_EXT_ZKNE		(1 << 12)
+#define		RISCV_HWPROBE_EXT_ZKNH		(1 << 13)
+#define		RISCV_HWPROBE_EXT_ZKSED		(1 << 14)
+#define		RISCV_HWPROBE_EXT_ZKSH		(1 << 15)
+#define		RISCV_HWPROBE_EXT_ZKT		(1 << 16)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 7a40145e96285..43aa66e71418e 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -163,6 +163,16 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZBS);
 		EXT_KEY(ZICBOZ);
 		EXT_KEY(ZBC);
+
+		EXT_KEY(ZBKB);
+		EXT_KEY(ZBKC);
+		EXT_KEY(ZBKX);
+		EXT_KEY(ZKND);
+		EXT_KEY(ZKNE);
+		EXT_KEY(ZKNH);
+		EXT_KEY(ZKSED);
+		EXT_KEY(ZKSH);
+		EXT_KEY(ZKT);
 #undef EXT_KEY
 	}
 
-- 
GitLab


From 9376396251c8a927018d465b4cc396af4b25b8d0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:41 -0500
Subject: [PATCH 1181/4076] dt-bindings: riscv: add scalar crypto ISA
 extensions description
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add description for scalar crypto ISA extensions:

- Zbkb
- Zbkc
- Zbkx
- Zknd
- Zkne
- Zknh
- Zkr
- Zksed
- Zksh
- Zkt

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114141256.126749-6-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../devicetree/bindings/riscv/extensions.yaml | 80 +++++++++++++++++++
 1 file changed, 80 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index c91ab0e466482..a3803b22cf4f3 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -190,12 +190,92 @@ properties:
             multiplication as ratified at commit 6d33919 ("Merge pull request
             #158 from hirooih/clmul-fix-loop-end-condition") of riscv-bitmanip.
 
+        - const: zbkb
+          description:
+            The standard Zbkb bitmanip instructions for cryptography as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zbkc
+          description:
+            The standard Zbkc carry-less multiply instructions as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zbkx
+          description:
+            The standard Zbkx crossbar permutation instructions as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
         - const: zbs
           description: |
             The standard Zbs bit-manipulation extension for single-bit
             instructions as ratified at commit 6d33919 ("Merge pull request #158
             from hirooih/clmul-fix-loop-end-condition") of riscv-bitmanip.
 
+        - const: zk
+          description:
+            The standard Zk Standard Scalar cryptography extension as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zkn
+          description:
+            The standard Zkn NIST algorithm suite extensions as ratified in
+            version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zknd
+          description: |
+            The standard Zknd for NIST suite: AES decryption instructions as
+            ratified in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zkne
+          description: |
+            The standard Zkne for NIST suite: AES encryption instructions as
+            ratified in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zknh
+          description: |
+            The standard Zknh for NIST suite: hash function instructions as
+            ratified in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zkr
+          description:
+            The standard Zkr entropy source extension as ratified in version
+            1.0 of RISC-V Cryptography Extensions Volume I specification.
+            This string being present means that the CSR associated to this
+            extension is accessible at the privilege level to which that
+            device-tree has been provided.
+
+        - const: zks
+          description:
+            The standard Zks ShangMi algorithm suite extensions as ratified in
+            version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
+        - const: zksed
+          description: |
+            The standard Zksed for ShangMi suite: SM4 block cipher instructions
+            as ratified in version 1.0 of RISC-V Cryptography Extensions
+            Volume I specification.
+
+        - const: zksh
+          description: |
+            The standard Zksh for ShangMi suite: SM3 hash function instructions
+            as ratified in version 1.0 of RISC-V Cryptography Extensions
+            Volume I specification.
+
+        - const: zkt
+          description:
+            The standard Zkt for data independent execution latency as ratified
+            in version 1.0 of RISC-V Cryptography Extensions Volume I
+            specification.
+
         - const: zicbom
           description:
             The standard Zicbom extension for base cache management operations as
-- 
GitLab


From aec3353963b8de889c3f1ab7cc8ba11e99626606 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:42 -0500
Subject: [PATCH 1182/4076] riscv: add ISA extension parsing for vector crypto
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add parsing of some Zv* vector crypto ISA extensions that are mentioned
in "RISC-V Cryptography Extensions Volume II" [1]. These ISA extensions
are the following:

- Zvbb: Vector Basic Bit-manipulation
- Zvbc: Vector Carryless Multiplication
- Zvkb: Vector Cryptography Bit-manipulation
- Zvkg: Vector GCM/GMAC.
- Zvkned: NIST Suite: Vector AES Block Cipher
- Zvknh[ab]: NIST Suite: Vector SHA-2 Secure Hash
- Zvksed: ShangMi Suite: SM4 Block Cipher
- Zvksh: ShangMi Suite: SM3 Secure Hash
- Zvkn: NIST Algorithm Suite
- Zvknc: NIST Algorithm Suite with carryless multiply
- Zvkng: NIST Algorithm Suite with GCM.
- Zvks: ShangMi Algorithm Suite
- Zvksc: ShangMi Algorithm Suite with carryless multiplication
- Zvksg: ShangMi Algorithm Suite with GCM.
- Zvkt: Vector Data-Independent Execution Latency.

Link: https://drive.google.com/file/d/1gb9OLH-DhbCgWp7VwpPOVrrY6f3oSJLL/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-7-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 12 ++++++-
 arch/riscv/kernel/cpufeature.c | 64 ++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index b0857c64bf6e4..477254668d826 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -68,8 +68,18 @@
 #define RISCV_ISA_EXT_ZKSED		53
 #define RISCV_ISA_EXT_ZKSH		54
 #define RISCV_ISA_EXT_ZKT		55
+#define RISCV_ISA_EXT_ZVBB		56
+#define RISCV_ISA_EXT_ZVBC		57
+#define RISCV_ISA_EXT_ZVKB		58
+#define RISCV_ISA_EXT_ZVKG		59
+#define RISCV_ISA_EXT_ZVKNED		60
+#define RISCV_ISA_EXT_ZVKNHA		61
+#define RISCV_ISA_EXT_ZVKNHB		62
+#define RISCV_ISA_EXT_ZVKSED		63
+#define RISCV_ISA_EXT_ZVKSH		64
+#define RISCV_ISA_EXT_ZVKT		65
 
-#define RISCV_ISA_EXT_MAX		64
+#define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
 
 #ifdef CONFIG_RISCV_M_MODE
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index a2871bceaad97..c4d0f16c29b91 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -123,6 +123,10 @@ static bool riscv_isa_extension_check(int id)
 #define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
 	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, ARRAY_SIZE(_bundled_exts))
 
+/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */
+#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \
+	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts))
+
 static const unsigned int riscv_zk_bundled_exts[] = {
 	RISCV_ISA_EXT_ZBKB,
 	RISCV_ISA_EXT_ZBKC,
@@ -149,6 +153,50 @@ static const unsigned int riscv_zks_bundled_exts[] = {
 	RISCV_ISA_EXT_ZKSH
 };
 
+#define RISCV_ISA_EXT_ZVKN	\
+	RISCV_ISA_EXT_ZVKNED,	\
+	RISCV_ISA_EXT_ZVKNHB,	\
+	RISCV_ISA_EXT_ZVKB,	\
+	RISCV_ISA_EXT_ZVKT
+
+static const unsigned int riscv_zvkn_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN
+};
+
+static const unsigned int riscv_zvknc_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN,
+	RISCV_ISA_EXT_ZVBC
+};
+
+static const unsigned int riscv_zvkng_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN,
+	RISCV_ISA_EXT_ZVKG
+};
+
+#define RISCV_ISA_EXT_ZVKS	\
+	RISCV_ISA_EXT_ZVKSED,	\
+	RISCV_ISA_EXT_ZVKSH,	\
+	RISCV_ISA_EXT_ZVKB,	\
+	RISCV_ISA_EXT_ZVKT
+
+static const unsigned int riscv_zvks_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS
+};
+
+static const unsigned int riscv_zvksc_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS,
+	RISCV_ISA_EXT_ZVBC
+};
+
+static const unsigned int riscv_zvksg_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS,
+	RISCV_ISA_EXT_ZVKG
+};
+
+static const unsigned int riscv_zvbb_exts[] = {
+	RISCV_ISA_EXT_ZVKB
+};
+
 /*
  * The canonical order of ISA extension names in the ISA string is defined in
  * chapter 27 of the unprivileged specification.
@@ -227,6 +275,22 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zkt, RISCV_ISA_EXT_ZKT),
 	__RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED),
 	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
+	__RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts),
+	__RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC),
+	__RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB),
+	__RISCV_ISA_EXT_DATA(zvkg, RISCV_ISA_EXT_ZVKG),
+	__RISCV_ISA_EXT_BUNDLE(zvkn, riscv_zvkn_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zvknc, riscv_zvknc_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvkned, RISCV_ISA_EXT_ZVKNED),
+	__RISCV_ISA_EXT_BUNDLE(zvkng, riscv_zvkng_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvknha, RISCV_ISA_EXT_ZVKNHA),
+	__RISCV_ISA_EXT_DATA(zvknhb, RISCV_ISA_EXT_ZVKNHB),
+	__RISCV_ISA_EXT_BUNDLE(zvks, riscv_zvks_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zvksc, riscv_zvksc_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvksed, RISCV_ISA_EXT_ZVKSED),
+	__RISCV_ISA_EXT_DATA(zvksh, RISCV_ISA_EXT_ZVKSH),
+	__RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
 	__RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN),
 	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
-- 
GitLab


From ca35b5b115856973620f425955fd0ce2505a51c4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:43 -0500
Subject: [PATCH 1183/4076] riscv: hwprobe: export vector crypto ISA extensions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export Zv* vector crypto ISA extensions that were added in "RISC-V
Cryptography Extensions Volume II" specification[1] through hwprobe.
This adds support for the following instructions:

- Zvbb: Vector Basic Bit-manipulation
- Zvbc: Vector Carryless Multiplication
- Zvkb: Vector Cryptography Bit-manipulation
- Zvkg: Vector GCM/GMAC.
- Zvkned: NIST Suite: Vector AES Block Cipher
- Zvknh[ab]: NIST Suite: Vector SHA-2 Secure Hash
- Zvksed: ShangMi Suite: SM4 Block Cipher
- Zvksh: ShangMi Suite: SM3 Secure Hash
- Zvknc: NIST Algorithm Suite with carryless multiply
- Zvkng: NIST Algorithm Suite with GCM.
- Zvksc: ShangMi Algorithm Suite with carryless multiplication
- Zvksg: ShangMi Algorithm Suite with GCM.
- Zvkt: Vector Data-Independent Execution Latency.

Zvkn and Zvks are ommited since they are a superset of other extensions.

Link: https://drive.google.com/file/d/1gb9OLH-DhbCgWp7VwpPOVrrY6f3oSJLL/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-8-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 30 +++++++++++++++++++++++++++
 arch/riscv/include/uapi/asm/hwprobe.h | 10 +++++++++
 arch/riscv/kernel/sys_riscv.c         | 13 ++++++++++++
 3 files changed, 53 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 3a18a31e32c36..a08fcd899b6db 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -110,6 +110,36 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZKT` The Zkt extension is supported, as defined
        in version 1.0 of the Scalar Crypto ISA extensions.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVBB`: The Zvbb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVBC`: The Zvbc extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKB`: The Zvkb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKG`: The Zvkg extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNED`: The Zvkned extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNHA`: The Zvknha extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKNHB`: The Zvknhb extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKSED`: The Zvksed extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKSH`: The Zvksh extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVKT`: The Zvkt extension is supported as
+       defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 624abd5cde293..89628a76ca047 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -40,6 +40,16 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZKSED		(1 << 14)
 #define		RISCV_HWPROBE_EXT_ZKSH		(1 << 15)
 #define		RISCV_HWPROBE_EXT_ZKT		(1 << 16)
+#define		RISCV_HWPROBE_EXT_ZVBB		(1 << 17)
+#define		RISCV_HWPROBE_EXT_ZVBC		(1 << 18)
+#define		RISCV_HWPROBE_EXT_ZVKB		(1 << 19)
+#define		RISCV_HWPROBE_EXT_ZVKG		(1 << 20)
+#define		RISCV_HWPROBE_EXT_ZVKNED	(1 << 21)
+#define		RISCV_HWPROBE_EXT_ZVKNHA	(1 << 22)
+#define		RISCV_HWPROBE_EXT_ZVKNHB	(1 << 23)
+#define		RISCV_HWPROBE_EXT_ZVKSED	(1 << 24)
+#define		RISCV_HWPROBE_EXT_ZVKSH		(1 << 25)
+#define		RISCV_HWPROBE_EXT_ZVKT		(1 << 26)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 43aa66e71418e..9bbcd7334d96d 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -173,6 +173,19 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZKSED);
 		EXT_KEY(ZKSH);
 		EXT_KEY(ZKT);
+
+		if (has_vector()) {
+			EXT_KEY(ZVBB);
+			EXT_KEY(ZVBC);
+			EXT_KEY(ZVKB);
+			EXT_KEY(ZVKG);
+			EXT_KEY(ZVKNED);
+			EXT_KEY(ZVKNHA);
+			EXT_KEY(ZVKNHB);
+			EXT_KEY(ZVKSED);
+			EXT_KEY(ZVKSH);
+			EXT_KEY(ZVKT);
+		}
 #undef EXT_KEY
 	}
 
-- 
GitLab


From 10815531c513f449ce477fb97e3f6e6962c14eaf Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:44 -0500
Subject: [PATCH 1184/4076] dt-bindings: riscv: add vector crypto ISA
 extensions description
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add Zv* vector crypto extensions that were added in "RISC-V Cryptography
Extensions Volume II" specificationi[1]:

- Zvbb: Vector Basic Bit-manipulation
- Zvbc: Vector Carryless Multiplication
- Zvkb: Vector Cryptography Bit-manipulation
- Zvkg: Vector GCM/GMAC.
- Zvkned: NIST Suite: Vector AES Block Cipher
- Zvknh[ab]: NIST Suite: Vector SHA-2 Secure Hash
- Zvksed: ShangMi Suite: SM4 Block Cipher
- Zvksh: ShangMi Suite: SM3 Secure Hash
- Zvkn: NIST Algorithm Suite
- Zvknc: NIST Algorithm Suite with carryless multiply
- Zvkng: NIST Algorithm Suite with GCM.
- Zvks: ShangMi Algorithm Suite
- Zvksc: ShangMi Algorithm Suite with carryless multiplication
- Zvksg: ShangMi Algorithm Suite with GCM.
- Zvkt: Vector Data-Independent Execution Latency.

Link: https://drive.google.com/file/d/1gb9OLH-DhbCgWp7VwpPOVrrY6f3oSJLL/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114141256.126749-9-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../devicetree/bindings/riscv/extensions.yaml | 96 +++++++++++++++++++
 1 file changed, 96 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index a3803b22cf4f3..e845e461b6e17 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -338,5 +338,101 @@ properties:
             in commit 2e5236 ("Ztso is now ratified.") of the
             riscv-isa-manual.
 
+        - const: zvbb
+          description:
+            The standard Zvbb extension for vectored basic bit-manipulation
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvbc
+          description:
+            The standard Zvbc extension for vectored carryless multiplication
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkb
+          description:
+            The standard Zvkb extension for vector cryptography bit-manipulation
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkg
+          description:
+            The standard Zvkg extension for vector GCM/GMAC instructions, as
+            ratified in commit 56ed795 ("Update riscv-crypto-spec-vector.adoc")
+            of riscv-crypto.
+
+        - const: zvkn
+          description:
+            The standard Zvkn extension for NIST algorithm suite instructions, as
+            ratified in commit 56ed795 ("Update riscv-crypto-spec-vector.adoc")
+            of riscv-crypto.
+
+        - const: zvknc
+          description:
+            The standard Zvknc extension for NIST algorithm suite with carryless
+            multiply instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkned
+          description:
+            The standard Zvkned extension for Vector AES block cipher
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkng
+          description:
+            The standard Zvkng extension for NIST algorithm suite with GCM
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvknha
+          description: |
+            The standard Zvknha extension for NIST suite: vector SHA-2 secure,
+            hash (SHA-256 only) instructions, as ratified in commit
+            56ed795 ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvknhb
+          description: |
+            The standard Zvknhb extension for NIST suite: vector SHA-2 secure,
+            hash (SHA-256 and SHA-512) instructions, as ratified in commit
+            56ed795 ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvks
+          description:
+            The standard Zvks extension for ShangMi algorithm suite
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvksc
+          description:
+            The standard Zvksc extension for ShangMi algorithm suite with
+            carryless multiplication instructions, as ratified in commit 56ed795
+            ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvksed
+          description: |
+            The standard Zvksed extension for ShangMi suite: SM4 block cipher
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvksh
+          description: |
+            The standard Zvksh extension for ShangMi suite: SM3 secure hash
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvksg
+          description:
+            The standard Zvksg extension for ShangMi algorithm suite with GCM
+            instructions, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
+        - const: zvkt
+          description:
+            The standard Zvkt extension for vector data-independent execution
+            latency, as ratified in commit 56ed795 ("Update
+            riscv-crypto-spec-vector.adoc") of riscv-crypto.
+
 additionalProperties: true
 ...
-- 
GitLab


From 11e8e1ee2c223585f1776e5c5d21bdae7184ca34 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:45 -0500
Subject: [PATCH 1185/4076] riscv: add ISA extension parsing for Zfh/Zfh[min]
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add parsing for Zfh[min] ISA extensions[1].

Link: https://drive.google.com/file/d/1z3tQQLm5ALsAD77PM0l0CHnapxWCeVzP/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-10-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 2 ++
 arch/riscv/kernel/cpufeature.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 477254668d826..6a6ee93a3c9a2 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -78,6 +78,8 @@
 #define RISCV_ISA_EXT_ZVKSED		63
 #define RISCV_ISA_EXT_ZVKSH		64
 #define RISCV_ISA_EXT_ZVKT		65
+#define RISCV_ISA_EXT_ZFH		66
+#define RISCV_ISA_EXT_ZFHMIN		67
 
 #define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index c4d0f16c29b91..7182cf278b1c5 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -258,6 +258,8 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
+	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
 	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
 	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
 	__RISCV_ISA_EXT_DATA(zbc, RISCV_ISA_EXT_ZBC),
-- 
GitLab


From bf4cd84111c6139313504310ff934df901a5ed3e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:46 -0500
Subject: [PATCH 1186/4076] riscv: hwprobe: export Zfh[min] ISA extensions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export Zfh[min] ISA extensions[1] through hwprobe only if FPU support
is available.

Link: https://drive.google.com/file/d/1z3tQQLm5ALsAD77PM0l0CHnapxWCeVzP/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-11-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 6 ++++++
 arch/riscv/include/uapi/asm/hwprobe.h | 2 ++
 arch/riscv/kernel/sys_riscv.c         | 5 +++++
 3 files changed, 13 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index a08fcd899b6db..397d53195f49a 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -140,6 +140,12 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZVKT`: The Zvkt extension is supported as
        defined in version 1.0 of the RISC-V Cryptography Extensions Volume II.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFH`: The Zfh extension version 1.0 is supported
+       as defined in the RISC-V ISA manual.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFHMIN`: The Zfhmin extension version 1.0 is
+       supported as defined in the RISC-V ISA manual.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 89628a76ca047..2d960777ea433 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -50,6 +50,8 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZVKSED	(1 << 24)
 #define		RISCV_HWPROBE_EXT_ZVKSH		(1 << 25)
 #define		RISCV_HWPROBE_EXT_ZVKT		(1 << 26)
+#define		RISCV_HWPROBE_EXT_ZFH		(1 << 27)
+#define		RISCV_HWPROBE_EXT_ZFHMIN	(1 << 28)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 9bbcd7334d96d..d776c6c39fcd8 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -186,6 +186,11 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZVKSH);
 			EXT_KEY(ZVKT);
 		}
+
+		if (has_fpu()) {
+			EXT_KEY(ZFH);
+			EXT_KEY(ZFHMIN);
+		}
 #undef EXT_KEY
 	}
 
-- 
GitLab


From c44714c35ff861d69db9c8bb4ae1347373f817f0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:47 -0500
Subject: [PATCH 1187/4076] dt-bindings: riscv: add Zfh[min] ISA extensions
 description
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add description of Zfh[min] ISA extensions[1].

Link: https://drive.google.com/file/d/1z3tQQLm5ALsAD77PM0l0CHnapxWCeVzP/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114141256.126749-12-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../devicetree/bindings/riscv/extensions.yaml       | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index e845e461b6e17..f3c99e69619b3 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -214,6 +214,19 @@ properties:
             instructions as ratified at commit 6d33919 ("Merge pull request #158
             from hirooih/clmul-fix-loop-end-condition") of riscv-bitmanip.
 
+        - const: zfh
+          description:
+            The standard Zfh extension for 16-bit half-precision binary
+            floating-point instructions, as ratified in commit 64074bc ("Update
+            version numbers for Zfh/Zfinx") of riscv-isa-manual.
+
+        - const: zfhmin
+          description:
+            The standard Zfhmin extension which provides minimal support for
+            16-bit half-precision binary floating-point instructions, as ratified
+            in commit 64074bc ("Update version numbers for Zfh/Zfinx") of
+            riscv-isa-manual.
+
         - const: zk
           description:
             The standard Zk Standard Scalar cryptography extension as ratified
-- 
GitLab


From eddbfa0d849fa5a315840e8c501962252b48484d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:48 -0500
Subject: [PATCH 1188/4076] riscv: add ISA extension parsing for Zihintntl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add parsing for Zihintntl ISA extension[1] that was ratified in commit
0dc91f5 ("Zihintntl is ratified") of riscv-isa-manual[2].

Link: https://drive.google.com/file/d/13_wsN8YmRfH8YWysFyTX-DjTkCnBd9hj/view [1]
Link: https://github.com/riscv/riscv-isa-manual/commit/0dc91f505e6d [2]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-13-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 1 +
 arch/riscv/kernel/cpufeature.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 6a6ee93a3c9a2..97d106fa0f548 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -80,6 +80,7 @@
 #define RISCV_ISA_EXT_ZVKT		65
 #define RISCV_ISA_EXT_ZFH		66
 #define RISCV_ISA_EXT_ZFHMIN		67
+#define RISCV_ISA_EXT_ZIHINTNTL		68
 
 #define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 7182cf278b1c5..e73ee4cfd84a1 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -256,6 +256,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
 	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
 	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
+	__RISCV_ISA_EXT_DATA(zihintntl, RISCV_ISA_EXT_ZIHINTNTL),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
 	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
-- 
GitLab


From 74ba42b250a7339c72e5803490b1ea42c3556f26 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:49 -0500
Subject: [PATCH 1189/4076] riscv: hwprobe: export Zhintntl ISA extension
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export Zihintntl extension[1] through hwprobe.

Link: https://drive.google.com/file/d/13_wsN8YmRfH8YWysFyTX-DjTkCnBd9hj/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-14-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 3 +++
 arch/riscv/include/uapi/asm/hwprobe.h | 1 +
 arch/riscv/kernel/sys_riscv.c         | 1 +
 3 files changed, 5 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 397d53195f49a..aa8ebeeddfe65 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -146,6 +146,9 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZFHMIN`: The Zfhmin extension version 1.0 is
        supported as defined in the RISC-V ISA manual.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZIHINTNTL`: The Zihintntl extension version 1.0
+       is supported as defined in the RISC-V ISA manual.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 2d960777ea433..d72c69ea0740f 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -52,6 +52,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZVKT		(1 << 26)
 #define		RISCV_HWPROBE_EXT_ZFH		(1 << 27)
 #define		RISCV_HWPROBE_EXT_ZFHMIN	(1 << 28)
+#define		RISCV_HWPROBE_EXT_ZIHINTNTL	(1 << 29)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index d776c6c39fcd8..a46e4f6821dd4 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -173,6 +173,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZKSED);
 		EXT_KEY(ZKSH);
 		EXT_KEY(ZKT);
+		EXT_KEY(ZIHINTNTL);
 
 		if (has_vector()) {
 			EXT_KEY(ZVBB);
-- 
GitLab


From 892f10c8d6ca4b3c12d149085243ad8cd75f09b3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:50 -0500
Subject: [PATCH 1190/4076] dt-bindings: riscv: add Zihintntl ISA extension
 description
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add description for Zihintntl ISA extension[1].

Link: https://drive.google.com/file/d/13_wsN8YmRfH8YWysFyTX-DjTkCnBd9hj/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114141256.126749-15-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/extensions.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index f3c99e69619b3..f953c49be90de 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -339,6 +339,12 @@ properties:
             The standard Zihintpause extension for pause hints, as ratified in
             commit d8ab5c7 ("Zihintpause is ratified") of the riscv-isa-manual.
 
+        - const: zihintntl
+          description:
+            The standard Zihintntl extension for non-temporal locality hints, as
+            ratified in commit 0dc91f5 ("Zihintntl is ratified") of the
+            riscv-isa-manual.
+
         - const: zihpm
           description:
             The standard Zihpm extension for hardware performance counters, as
-- 
GitLab


From f4961b78c37b64f48cc5c376f8aef5e1823201c1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:51 -0500
Subject: [PATCH 1191/4076] riscv: add ISA extension parsing for Zvfh[min]
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add parsing for Zvfh[min] ISA extension[1] which were ratified in
june 2023 around commit e2ccd0548d6c ("Remove draft warnings from
Zvfh[min]") in riscv-v-spec[2].

Link: https://drive.google.com/file/d/1_Yt60HGAf1r1hx7JnsIptw0sqkBd9BQ8/view [1]
Link: https://github.com/riscv/riscv-v-spec/commits/e2ccd0548d6c [2]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-16-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 2 ++
 arch/riscv/kernel/cpufeature.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 97d106fa0f548..103d4f0aaf15c 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -81,6 +81,8 @@
 #define RISCV_ISA_EXT_ZFH		66
 #define RISCV_ISA_EXT_ZFHMIN		67
 #define RISCV_ISA_EXT_ZIHINTNTL		68
+#define RISCV_ISA_EXT_ZVFH		69
+#define RISCV_ISA_EXT_ZVFHMIN		70
 
 #define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index e73ee4cfd84a1..623a5fa48cf41 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -280,6 +280,8 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
 	__RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts),
 	__RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC),
+	__RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH),
+	__RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN),
 	__RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB),
 	__RISCV_ISA_EXT_DATA(zvkg, RISCV_ISA_EXT_ZVKG),
 	__RISCV_ISA_EXT_BUNDLE(zvkn, riscv_zvkn_bundled_exts),
-- 
GitLab


From 5dadda5e6a59a5b4f547a1b14d9518e4074c6966 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:52 -0500
Subject: [PATCH 1192/4076] riscv: hwprobe: export Zvfh[min] ISA extensions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export Zvfh[min] ISA extension[1] through hwprobe.

Link: https://drive.google.com/file/d/1_Yt60HGAf1r1hx7JnsIptw0sqkBd9BQ8/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-17-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 8 ++++++++
 arch/riscv/include/uapi/asm/hwprobe.h | 2 ++
 arch/riscv/kernel/sys_riscv.c         | 2 ++
 3 files changed, 12 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index aa8ebeeddfe65..896ecfbbe5f47 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -149,6 +149,14 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZIHINTNTL`: The Zihintntl extension version 1.0
        is supported as defined in the RISC-V ISA manual.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVFH`: The Zvfh extension is supported as
+       defined in the RISC-V Vector manual starting from commit e2ccd0548d6c
+       ("Remove draft warnings from Zvfh[min]").
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZVFHMIN`: The Zvfhmin extension is supported as
+       defined in the RISC-V Vector manual starting from commit e2ccd0548d6c
+       ("Remove draft warnings from Zvfh[min]").
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index d72c69ea0740f..fffc69d9f6bae 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -53,6 +53,8 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZFH		(1 << 27)
 #define		RISCV_HWPROBE_EXT_ZFHMIN	(1 << 28)
 #define		RISCV_HWPROBE_EXT_ZIHINTNTL	(1 << 29)
+#define		RISCV_HWPROBE_EXT_ZVFH		(1 << 30)
+#define		RISCV_HWPROBE_EXT_ZVFHMIN	(1 << 31)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index a46e4f6821dd4..e90537593f5fe 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -186,6 +186,8 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZVKSED);
 			EXT_KEY(ZVKSH);
 			EXT_KEY(ZVKT);
+			EXT_KEY(ZVFH);
+			EXT_KEY(ZVFHMIN);
 		}
 
 		if (has_fpu()) {
-- 
GitLab


From e11880b4be3a8db558147409b9ed0d1855526910 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:53 -0500
Subject: [PATCH 1193/4076] dt-bindings: riscv: add Zvfh[min] ISA extension
 description
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add description for Zvfh[min] ISA extension[1].

Link: https://drive.google.com/file/d/1_Yt60HGAf1r1hx7JnsIptw0sqkBd9BQ8/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114141256.126749-18-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../devicetree/bindings/riscv/extensions.yaml        | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index f953c49be90de..b91d49b7c3a09 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -369,6 +369,18 @@ properties:
             instructions, as ratified in commit 56ed795 ("Update
             riscv-crypto-spec-vector.adoc") of riscv-crypto.
 
+        - const: zvfh
+          description:
+            The standard Zvfh extension for vectored half-precision
+            floating-point instructions, as ratified in commit e2ccd05
+            ("Remove draft warnings from Zvfh[min]") of riscv-v-spec.
+
+        - const: zvfhmin
+          description:
+            The standard Zvfhmin extension for vectored minimal half-precision
+            floating-point instructions, as ratified in commit e2ccd05
+            ("Remove draft warnings from Zvfh[min]") of riscv-v-spec.
+
         - const: zvkb
           description:
             The standard Zvkb extension for vector cryptography bit-manipulation
-- 
GitLab


From fe987e84b0120e2b41db69ed4ede166797aa8d2e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:54 -0500
Subject: [PATCH 1194/4076] riscv: add ISA extension parsing for Zfa
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add parsing for Zfa ISA extension [1] which were ratified in commit
056b6ff467c7 ("Zfa is ratified") of riscv-isa-manual[2].

Link: https://drive.google.com/file/d/1VT6QIggpb59-8QRV266dEE4T8FZTxGq4/view [1]
Link: https://github.com/riscv/riscv-isa-manual/commits/056b6ff467c7 [2]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-19-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 1 +
 arch/riscv/kernel/cpufeature.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 103d4f0aaf15c..2438d4685da67 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -83,6 +83,7 @@
 #define RISCV_ISA_EXT_ZIHINTNTL		68
 #define RISCV_ISA_EXT_ZVFH		69
 #define RISCV_ISA_EXT_ZVFHMIN		70
+#define RISCV_ISA_EXT_ZFA		71
 
 #define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 623a5fa48cf41..dc0ab3e97cd28 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -259,6 +259,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zihintntl, RISCV_ISA_EXT_ZIHINTNTL),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
 	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
 	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
 	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
-- 
GitLab


From dc6ccb21f42ce5b3e4df6f52e14edab721e1b26e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:55 -0500
Subject: [PATCH 1195/4076] riscv: hwprobe: export Zfa ISA extension
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export Zfa ISA extension[1] through hwprobe.

Link: https://drive.google.com/file/d/1VT6QIggpb59-8QRV266dEE4T8FZTxGq4/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231114141256.126749-20-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 4 ++++
 arch/riscv/include/uapi/asm/hwprobe.h | 1 +
 arch/riscv/kernel/sys_riscv.c         | 1 +
 3 files changed, 6 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 896ecfbbe5f47..41463b9322689 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -157,6 +157,10 @@ The following keys are defined:
        defined in the RISC-V Vector manual starting from commit e2ccd0548d6c
        ("Remove draft warnings from Zvfh[min]").
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZFA`: The Zfa extension is supported as
+       defined in the RISC-V ISA manual starting from commit 056b6ff467c7
+       ("Zfa is ratified").
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index fffc69d9f6bae..91fbe1a7f2e29 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -55,6 +55,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZIHINTNTL	(1 << 29)
 #define		RISCV_HWPROBE_EXT_ZVFH		(1 << 30)
 #define		RISCV_HWPROBE_EXT_ZVFHMIN	(1 << 31)
+#define		RISCV_HWPROBE_EXT_ZFA		(1ULL << 32)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index e90537593f5fe..f0bd7b480b7f2 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -193,6 +193,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		if (has_fpu()) {
 			EXT_KEY(ZFH);
 			EXT_KEY(ZFHMIN);
+			EXT_KEY(ZFA);
 		}
 #undef EXT_KEY
 	}
-- 
GitLab


From 9726acfdfa3bbf324b305e0b32fc028c278f6d43 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 14 Nov 2023 09:12:56 -0500
Subject: [PATCH 1196/4076] dt-bindings: riscv: add Zfa ISA extension
 description
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add description for the Zfa ISA extension[1].

Link: https://drive.google.com/file/d/1VT6QIggpb59-8QRV266dEE4T8FZTxGq4/view [1]
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114141256.126749-21-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/extensions.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index b91d49b7c3a09..3574a0b70be45 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -214,6 +214,12 @@ properties:
             instructions as ratified at commit 6d33919 ("Merge pull request #158
             from hirooih/clmul-fix-loop-end-condition") of riscv-bitmanip.
 
+        - const: zfa
+          description:
+            The standard Zfa extension for additional floating point
+            instructions, as ratified in commit 056b6ff ("Zfa is ratified") of
+            riscv-isa-manual.
+
         - const: zfh
           description:
             The standard Zfh extension for 16-bit half-precision binary
-- 
GitLab


From e4af6bb1f62fe30f19171322374f021bbcdc5b04 Mon Sep 17 00:00:00 2001
From: Jiri Valek - 2N <jiriv@axis.com>
Date: Mon, 11 Dec 2023 18:54:22 -0800
Subject: [PATCH 1197/4076] dt-bindings: input: microchip,cap11xx: add advanced
 sensitivity settings

Add support for advanced sensitivity settings and signal guard feature.

Signed-off-by: Jiri Valek - 2N <jiriv@axis.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231121155250.613242-2-jiriv@axis.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../bindings/input/microchip,cap11xx.yaml     | 80 ++++++++++++++++++-
 1 file changed, 77 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
index 5b5d4f7d34827..7ade03f1b32b8 100644
--- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
+++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
@@ -45,13 +45,13 @@ properties:
       Enables the Linux input system's autorepeat feature on the input device.
 
   linux,keycodes:
-    minItems: 6
-    maxItems: 6
+    minItems: 3
+    maxItems: 8
     description: |
       Specifies an array of numeric keycode values to
       be used for the channels. If this property is
       omitted, KEY_A, KEY_B, etc are used as defaults.
-      The array must have exactly six entries.
+      The number of entries must correspond to the number of channels.
 
   microchip,sensor-gain:
     $ref: /schemas/types.yaml#/definitions/uint32
@@ -70,6 +70,59 @@ properties:
       open drain. This property allows using the active
       high push-pull output.
 
+  microchip,sensitivity-delta-sense:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 32
+    enum: [1, 2, 4, 8, 16, 32, 64, 128]
+    description:
+      Controls the sensitivity multiplier of a touch detection.
+      Higher value means more sensitive settings.
+      At the more sensitive settings, touches are detected for a smaller delta
+      capacitance corresponding to a "lighter" touch.
+
+  microchip,signal-guard:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 3
+    maxItems: 8
+    items:
+      enum: [0, 1]
+    description: |
+      0 - off
+      1 - on
+      The signal guard isolates the signal from virtual grounds.
+      If enabled then the behavior of the channel is changed to signal guard.
+      The number of entries must correspond to the number of channels.
+
+  microchip,input-threshold:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 3
+    maxItems: 8
+    items:
+      minimum: 0
+      maximum: 127
+    description:
+      Specifies the delta threshold that is used to determine if a touch has
+      been detected. A higher value means a larger difference in capacitance
+      is required for a touch to be registered, making the touch sensor less
+      sensitive.
+      The number of entries must correspond to the number of channels.
+
+  microchip,calib-sensitivity:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 3
+    maxItems: 8
+    items:
+      enum: [1, 2, 4]
+    description: |
+      Specifies an array of numeric values that controls the gain
+      used by the calibration routine to enable sensor inputs
+      to be more sensitive for proximity detection.
+      Gain is based on touch pad capacitance range
+      1 - 5-50pF
+      2 - 0-25pF
+      4 - 0-12.5pF
+      The number of entries must correspond to the number of channels.
+
 patternProperties:
   "^led@[0-7]$":
     type: object
@@ -99,10 +152,29 @@ allOf:
           contains:
             enum:
               - microchip,cap1106
+              - microchip,cap1203
+              - microchip,cap1206
+              - microchip,cap1293
+              - microchip,cap1298
     then:
       patternProperties:
         "^led@[0-7]$": false
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - microchip,cap1106
+              - microchip,cap1126
+              - microchip,cap1188
+              - microchip,cap1203
+              - microchip,cap1206
+    then:
+      properties:
+        microchip,signal-guard: false
+        microchip,calib-sensitivity: false
+
 required:
   - compatible
   - interrupts
@@ -122,6 +194,8 @@ examples:
         reg = <0x28>;
         autorepeat;
         microchip,sensor-gain = <2>;
+        microchip,sensitivity-delta-sense = <16>;
+        microchip,input-threshold = <21>, <18>, <46>, <46>, <46>, <21>;
 
         linux,keycodes = <103>,	/* KEY_UP */
                          <106>,	/* KEY_RIGHT */
-- 
GitLab


From 2e3ae00021901461455b6a9ff4ef850817e9ab6d Mon Sep 17 00:00:00 2001
From: Jiri Valek - 2N <jiriv@axis.com>
Date: Mon, 11 Dec 2023 18:54:45 -0800
Subject: [PATCH 1198/4076] Input: cap11xx - add advanced sensitivity settings

Add support for advanced sensitivity settings that allows more precise
tunig of touch buttons. Input-treshold allows to set the sensitivity for
each channel separately. Also add signal guard feature for CAP129x chips.

Signed-off-by: Jiri Valek - 2N <jiriv@axis.com>
Link: https://lore.kernel.org/r/20231121155250.613242-3-jiriv@axis.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/cap11xx.c | 237 +++++++++++++++++++++++++------
 1 file changed, 192 insertions(+), 45 deletions(-)

diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 01e7ead68fead..ebcbc00d2059e 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -14,6 +14,7 @@
 #include <linux/regmap.h>
 #include <linux/i2c.h>
 #include <linux/gpio/consumer.h>
+#include <linux/bitfield.h>
 
 #define CAP11XX_REG_MAIN_CONTROL	0x00
 #define CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT	(6)
@@ -24,6 +25,7 @@
 #define CAP11XX_REG_NOISE_FLAG_STATUS	0x0a
 #define CAP11XX_REG_SENOR_DELTA(X)	(0x10 + (X))
 #define CAP11XX_REG_SENSITIVITY_CONTROL	0x1f
+#define CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK	0x70
 #define CAP11XX_REG_CONFIG		0x20
 #define CAP11XX_REG_SENSOR_ENABLE	0x21
 #define CAP11XX_REG_SENSOR_CONFIG	0x22
@@ -32,6 +34,7 @@
 #define CAP11XX_REG_CALIBRATION		0x26
 #define CAP11XX_REG_INT_ENABLE		0x27
 #define CAP11XX_REG_REPEAT_RATE		0x28
+#define CAP11XX_REG_SIGNAL_GUARD_ENABLE	0x29
 #define CAP11XX_REG_MT_CONFIG		0x2a
 #define CAP11XX_REG_MT_PATTERN_CONFIG	0x2b
 #define CAP11XX_REG_MT_PATTERN		0x2d
@@ -47,6 +50,8 @@
 #define CAP11XX_REG_SENSOR_BASE_CNT(X)	(0x50 + (X))
 #define CAP11XX_REG_LED_POLARITY	0x73
 #define CAP11XX_REG_LED_OUTPUT_CONTROL	0x74
+#define CAP11XX_REG_CALIB_SENSITIVITY_CONFIG	0x80
+#define CAP11XX_REG_CALIB_SENSITIVITY_CONFIG2	0x81
 
 #define CAP11XX_REG_LED_DUTY_CYCLE_1	0x90
 #define CAP11XX_REG_LED_DUTY_CYCLE_2	0x91
@@ -78,12 +83,20 @@ struct cap11xx_led {
 
 struct cap11xx_priv {
 	struct regmap *regmap;
+	struct device *dev;
 	struct input_dev *idev;
+	const struct cap11xx_hw_model *model;
+	u8 id;
 
 	struct cap11xx_led *leds;
 	int num_leds;
 
 	/* config */
+	u8 analog_gain;
+	u8 sensitivity_delta_sense;
+	u8 signal_guard_inputs_mask;
+	u32 thresholds[8];
+	u32 calib_sensitivities[8];
 	u32 keycodes[];
 };
 
@@ -181,6 +194,175 @@ static const struct regmap_config cap11xx_regmap_config = {
 	.volatile_reg = cap11xx_volatile_reg,
 };
 
+static int cap11xx_write_calib_sens_config_1(struct cap11xx_priv *priv)
+{
+	return regmap_write(priv->regmap,
+			    CAP11XX_REG_CALIB_SENSITIVITY_CONFIG,
+			    (priv->calib_sensitivities[3] << 6) |
+			    (priv->calib_sensitivities[2] << 4) |
+			    (priv->calib_sensitivities[1] << 2) |
+			    priv->calib_sensitivities[0]);
+}
+
+static int cap11xx_write_calib_sens_config_2(struct cap11xx_priv *priv)
+{
+	return regmap_write(priv->regmap,
+			    CAP11XX_REG_CALIB_SENSITIVITY_CONFIG2,
+			    (priv->calib_sensitivities[7] << 6) |
+			    (priv->calib_sensitivities[6] << 4) |
+			    (priv->calib_sensitivities[5] << 2) |
+			    priv->calib_sensitivities[4]);
+}
+
+static int cap11xx_init_keys(struct cap11xx_priv *priv)
+{
+	struct device_node *node = priv->dev->of_node;
+	struct device *dev = priv->dev;
+	int i, error;
+	u32 u32_val;
+
+	if (!node) {
+		dev_err(dev, "Corresponding DT entry is not available\n");
+		return -ENODEV;
+	}
+
+	if (!of_property_read_u32(node, "microchip,sensor-gain", &u32_val)) {
+		if (priv->model->no_gain) {
+			dev_warn(dev,
+				 "This model doesn't support 'sensor-gain'\n");
+		} else if (is_power_of_2(u32_val) && u32_val <= 8) {
+			priv->analog_gain = (u8)ilog2(u32_val);
+
+			error = regmap_update_bits(priv->regmap,
+				CAP11XX_REG_MAIN_CONTROL,
+				CAP11XX_REG_MAIN_CONTROL_GAIN_MASK,
+				priv->analog_gain << CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT);
+			if (error)
+				return error;
+		} else {
+			dev_err(dev, "Invalid sensor-gain value %u\n", u32_val);
+			return -EINVAL;
+		}
+	}
+
+	if (of_property_read_bool(node, "microchip,irq-active-high")) {
+		if (priv->id == CAP1106 ||
+		    priv->id == CAP1126 ||
+		    priv->id == CAP1188) {
+			error = regmap_update_bits(priv->regmap,
+						   CAP11XX_REG_CONFIG2,
+						   CAP11XX_REG_CONFIG2_ALT_POL,
+						   0);
+			if (error)
+				return error;
+		} else {
+			dev_warn(dev,
+				 "This model doesn't support 'irq-active-high'\n");
+		}
+	}
+
+	if (!of_property_read_u32(node, "microchip,sensitivity-delta-sense", &u32_val)) {
+		if (!is_power_of_2(u32_val) || u32_val > 128) {
+			dev_err(dev, "Invalid sensitivity-delta-sense value %u\n", u32_val);
+			return -EINVAL;
+		}
+
+		priv->sensitivity_delta_sense = (u8)ilog2(u32_val);
+		u32_val = ~(FIELD_PREP(CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK,
+					priv->sensitivity_delta_sense));
+
+		error = regmap_update_bits(priv->regmap,
+					   CAP11XX_REG_SENSITIVITY_CONTROL,
+					   CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK,
+					   u32_val);
+		if (error)
+			return error;
+	}
+
+	if (!of_property_read_u32_array(node, "microchip,input-threshold",
+					priv->thresholds, priv->model->num_channels)) {
+		for (i = 0; i < priv->model->num_channels; i++) {
+			if (priv->thresholds[i] > 127) {
+				dev_err(dev, "Invalid input-threshold value %u\n",
+					priv->thresholds[i]);
+				return -EINVAL;
+			}
+
+			error = regmap_write(priv->regmap,
+					     CAP11XX_REG_SENSOR_THRESH(i),
+					     priv->thresholds[i]);
+			if (error)
+				return error;
+		}
+	}
+
+	if (!of_property_read_u32_array(node, "microchip,calib-sensitivity",
+					priv->calib_sensitivities,
+					priv->model->num_channels)) {
+		if (priv->id == CAP1293 || priv->id == CAP1298) {
+			for (i = 0; i < priv->model->num_channels; i++) {
+				if (!is_power_of_2(priv->calib_sensitivities[i]) ||
+				    priv->calib_sensitivities[i] > 4) {
+					dev_err(dev, "Invalid calib-sensitivity value %u\n",
+						priv->calib_sensitivities[i]);
+					return -EINVAL;
+				}
+				priv->calib_sensitivities[i] = ilog2(priv->calib_sensitivities[i]);
+			}
+
+			error = cap11xx_write_calib_sens_config_1(priv);
+			if (error)
+				return error;
+
+			if (priv->id == CAP1298) {
+				error = cap11xx_write_calib_sens_config_2(priv);
+				if (error)
+					return error;
+			}
+		} else {
+			dev_warn(dev,
+				 "This model doesn't support 'calib-sensitivity'\n");
+		}
+	}
+
+	for (i = 0; i < priv->model->num_channels; i++) {
+		if (!of_property_read_u32_index(node, "microchip,signal-guard",
+						i, &u32_val)) {
+			if (u32_val > 1)
+				return -EINVAL;
+			if (u32_val)
+				priv->signal_guard_inputs_mask |= 0x01 << i;
+		}
+	}
+
+	if (priv->signal_guard_inputs_mask) {
+		if (priv->id == CAP1293 || priv->id == CAP1298) {
+			error = regmap_write(priv->regmap,
+					     CAP11XX_REG_SIGNAL_GUARD_ENABLE,
+					     priv->signal_guard_inputs_mask);
+			if (error)
+				return error;
+		} else {
+			dev_warn(dev,
+				 "This model doesn't support 'signal-guard'\n");
+		}
+	}
+
+	/* Provide some useful defaults */
+	for (i = 0; i < priv->model->num_channels; i++)
+		priv->keycodes[i] = KEY_A + i;
+
+	of_property_read_u32_array(node, "linux,keycodes",
+				   priv->keycodes, priv->model->num_channels);
+
+	/* Disable autorepeat. The Linux input system has its own handling. */
+	error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0);
+	if (error)
+		return error;
+
+	return 0;
+}
+
 static irqreturn_t cap11xx_thread_func(int irq_num, void *data)
 {
 	struct cap11xx_priv *priv = data;
@@ -332,11 +514,9 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	const struct i2c_device_id *id = i2c_client_get_device_id(i2c_client);
 	struct device *dev = &i2c_client->dev;
 	struct cap11xx_priv *priv;
-	struct device_node *node;
 	const struct cap11xx_hw_model *cap;
-	int i, error, gain = 0;
+	int i, error;
 	unsigned int val, rev;
-	u32 gain32;
 
 	if (id->driver_data >= ARRAY_SIZE(cap11xx_devices)) {
 		dev_err(dev, "Invalid device ID %lu\n", id->driver_data);
@@ -355,6 +535,8 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	if (!priv)
 		return -ENOMEM;
 
+	priv->dev = dev;
+
 	priv->regmap = devm_regmap_init_i2c(i2c_client, &cap11xx_regmap_config);
 	if (IS_ERR(priv->regmap))
 		return PTR_ERR(priv->regmap);
@@ -384,50 +566,15 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 		return error;
 
 	dev_info(dev, "CAP11XX detected, model %s, revision 0x%02x\n",
-		 id->name, rev);
-	node = dev->of_node;
-
-	if (!of_property_read_u32(node, "microchip,sensor-gain", &gain32)) {
-		if (cap->no_gain)
-			dev_warn(dev,
-				 "This version doesn't support sensor gain\n");
-		else if (is_power_of_2(gain32) && gain32 <= 8)
-			gain = ilog2(gain32);
-		else
-			dev_err(dev, "Invalid sensor-gain value %d\n", gain32);
-	}
+			 id->name, rev);
 
-	if (id->driver_data == CAP1106 ||
-	    id->driver_data == CAP1126 ||
-	    id->driver_data == CAP1188) {
-		if (of_property_read_bool(node, "microchip,irq-active-high")) {
-			error = regmap_update_bits(priv->regmap,
-						   CAP11XX_REG_CONFIG2,
-						   CAP11XX_REG_CONFIG2_ALT_POL,
-						   0);
-			if (error)
-				return error;
-		}
-	}
+	priv->model = cap;
+	priv->id = id->driver_data;
 
-	/* Provide some useful defaults */
-	for (i = 0; i < cap->num_channels; i++)
-		priv->keycodes[i] = KEY_A + i;
-
-	of_property_read_u32_array(node, "linux,keycodes",
-				   priv->keycodes, cap->num_channels);
-
-	if (!cap->no_gain) {
-		error = regmap_update_bits(priv->regmap,
-				CAP11XX_REG_MAIN_CONTROL,
-				CAP11XX_REG_MAIN_CONTROL_GAIN_MASK,
-				gain << CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT);
-		if (error)
-			return error;
-	}
+	dev_info(dev, "CAP11XX device detected, model %s, revision 0x%02x\n",
+		 id->name, rev);
 
-	/* Disable autorepeat. The Linux input system has its own handling. */
-	error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0);
+	error = cap11xx_init_keys(priv);
 	if (error)
 		return error;
 
@@ -439,7 +586,7 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
 	priv->idev->id.bustype = BUS_I2C;
 	priv->idev->evbit[0] = BIT_MASK(EV_KEY);
 
-	if (of_property_read_bool(node, "autorepeat"))
+	if (of_property_read_bool(dev->of_node, "autorepeat"))
 		__set_bit(EV_REP, priv->idev->evbit);
 
 	for (i = 0; i < cap->num_channels; i++)
-- 
GitLab


From 39bd68d422ba085997fb1f26160d7c686915b3cb Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Sun, 1 Oct 2023 01:43:38 +0200
Subject: [PATCH 1199/4076] Input: cap11xx - cache hardware ID registers

The cap11xx devices have three hardware identification registers which are
currently marked as volatile, preventing caching of those registers. This
is not ideal since the registers should never change at runtime, we should
be able to cache the value after the first read. Stop marking the registers
as volatile, we don't have register defaults specified in the driver so
this will result in reading from the hardware on first use.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20231001-input-maple-v1-1-ed3716051431@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/cap11xx.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index ebcbc00d2059e..8e25d7d5e64de 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -173,9 +173,6 @@ static bool cap11xx_volatile_reg(struct device *dev, unsigned int reg)
 	case CAP11XX_REG_SENOR_DELTA(3):
 	case CAP11XX_REG_SENOR_DELTA(4):
 	case CAP11XX_REG_SENOR_DELTA(5):
-	case CAP11XX_REG_PRODUCT_ID:
-	case CAP11XX_REG_MANUFACTURER_ID:
-	case CAP11XX_REG_REVISION:
 		return true;
 	}
 
-- 
GitLab


From 718963d94197626f83544b63ca5581d16cffdac2 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Sun, 1 Oct 2023 01:43:39 +0200
Subject: [PATCH 1200/4076] Input: cap11xx - convert to use maple tree register
 cache

The maple tree register cache is based on a much more modern data structure
than the rbtree cache and makes optimisation choices which are probably
more appropriate for modern systems than those made by the rbtree cache.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20231001-input-maple-v1-2-ed3716051431@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/cap11xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 8e25d7d5e64de..52fba9ee7c1d8 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -187,7 +187,7 @@ static const struct regmap_config cap11xx_regmap_config = {
 	.reg_defaults = cap11xx_reg_defaults,
 
 	.num_reg_defaults = ARRAY_SIZE(cap11xx_reg_defaults),
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_MAPLE,
 	.volatile_reg = cap11xx_volatile_reg,
 };
 
-- 
GitLab


From 5958274f1de5bcc435a11a92a5d555775c5ed341 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Sun, 1 Oct 2023 01:43:40 +0200
Subject: [PATCH 1201/4076] Input: qt1050 - convert to use maple tree register
 cache

The maple tree register cache is based on a much more modern data structure
than the rbtree cache and makes optimisation choices which are probably
more appropriate for modern systems than those made by the rbtree cache.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20231001-input-maple-v1-3-ed3716051431@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/qt1050.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/qt1050.c b/drivers/input/keyboard/qt1050.c
index 6953097db4456..b51dfcd760386 100644
--- a/drivers/input/keyboard/qt1050.c
+++ b/drivers/input/keyboard/qt1050.c
@@ -213,7 +213,7 @@ static struct regmap_config qt1050_regmap_config = {
 	.val_bits = 8,
 	.max_register = QT1050_RES_CAL,
 
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_MAPLE,
 
 	.wr_table = &qt1050_writeable_table,
 	.rd_table = &qt1050_readable_table,
-- 
GitLab


From f737020d24e47d6e8b893a2fee2b43268a6af629 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Fri, 6 Oct 2023 12:03:20 +0200
Subject: [PATCH 1202/4076] Input: max77693-haptic - add device-tree compatible
 strings

Add the needed device-tree compatible strings to the MAX77693 haptic
driver, so it can be automatically loaded when compiled as a kernel
module and given device-tree contains separate (i.e. 'motor-driver') node
under the main PMIC node. When device is instantiated from device-tree,
the driver data cannot be read via platform_get_device_id(), so get
device type from the parent MFD device instead, what works for both
cases.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231006100320.2908210-1-m.szyprowski@samsung.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/max77693-haptic.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/input/misc/max77693-haptic.c b/drivers/input/misc/max77693-haptic.c
index 80f4416ffe2fe..0e646f1b257b8 100644
--- a/drivers/input/misc/max77693-haptic.c
+++ b/drivers/input/misc/max77693-haptic.c
@@ -307,7 +307,7 @@ static int max77693_haptic_probe(struct platform_device *pdev)
 	haptic->suspend_state = false;
 
 	/* Variant-specific init */
-	haptic->dev_type = platform_get_device_id(pdev)->driver_data;
+	haptic->dev_type = max77693->type;
 	switch (haptic->dev_type) {
 	case TYPE_MAX77693:
 		haptic->regmap_haptic = max77693->regmap_haptic;
@@ -406,16 +406,24 @@ static DEFINE_SIMPLE_DEV_PM_OPS(max77693_haptic_pm_ops,
 				max77693_haptic_resume);
 
 static const struct platform_device_id max77693_haptic_id[] = {
-	{ "max77693-haptic", TYPE_MAX77693 },
-	{ "max77843-haptic", TYPE_MAX77843 },
+	{ "max77693-haptic", },
+	{ "max77843-haptic", },
 	{},
 };
 MODULE_DEVICE_TABLE(platform, max77693_haptic_id);
 
+static const struct of_device_id of_max77693_haptic_dt_match[] = {
+	{ .compatible = "maxim,max77693-haptic", },
+	{ .compatible = "maxim,max77843-haptic", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, of_max77693_haptic_dt_match);
+
 static struct platform_driver max77693_haptic_driver = {
 	.driver		= {
 		.name	= "max77693-haptic",
 		.pm	= pm_sleep_ptr(&max77693_haptic_pm_ops),
+		.of_match_table = of_max77693_haptic_dt_match,
 	},
 	.probe		= max77693_haptic_probe,
 	.id_table	= max77693_haptic_id,
-- 
GitLab


From 884fdaa53b38921165cd9afdb230502b4e1690b0 Mon Sep 17 00:00:00 2001
From: Jaewon Kim <jaewon02.kim@samsung.com>
Date: Mon, 11 Dec 2023 20:41:44 +0900
Subject: [PATCH 1203/4076] pinctrl: samsung: support ExynosAuto GPIO structure

New ExynosAuto series GPIO have a different register structure.
In the existing Exynos series, EINT control register is enumerated after
a specific offset (e.g EXYNOS_GPIO_ECON_OFFSET, EXYNOS_GPIO_EMASK_OFFSET).
However, from ExynosAutov920 SoC, the register that controls EINT belongs
to each GPIO bank, and each GPIO bank has 0x1000 align.

This is a structure to protect the GPIO bank using S2MPU in VM environment,
and will only be applied in ExynosAuto series SoCs.

--------------------------------------------------------------
| Original Exynos            | ExynosAuto                    |
|------------------------------------------------------------|
| 0x0   GPIO_CON             | 0x0   GPIO_CON                |
| 0x4   GPIO_DAT             | 0x4   GPIO_DAT                |
| 0x8   GPIO_PUD             | 0x8   GPIO_PUD                |
| 0xc   GPIO_DRV             | 0xc   GPIO_DRV                |
| 0x10  GPIO_CONPDN          | 0x10  GPIO_CONPDN             |
| 0x14  GPIO_PUDPDN          | 0x14  GPIO_PUDPDN             |
|----------------------------| 0x18  EINT_CON (per_bank)     |
| ...                        | 0x1c  EINT_FLTCON0 (per_bank) |
| ...                        | 0x20  EINT_FLTCON1 (per_bank) |
| ...                        | 0x24  EINT_MASK (per_bank)    |
| ...                        | 0x28  EINT_PEND (per_bank)    |
|----------------------------|-------------------------------|
| 0x700 EINT_CON (global)    | ...                           |
| 0x800 EINT_FLTCON (global) | ...                           |
| 0x900 EINT_MASK (global)   | ...                           |
| 0xa00 EINT_FEND (global)   | ...                           |
--------------------------------------------------------------

Signed-off-by: Jaewon Kim <jaewon02.kim@samsung.com>
Link: https://lore.kernel.org/r/20231211114145.106255-2-jaewon02.kim@samsung.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/pinctrl/samsung/pinctrl-exynos.c  | 72 ++++++++++++++++++++---
 drivers/pinctrl/samsung/pinctrl-samsung.c |  3 +
 drivers/pinctrl/samsung/pinctrl-samsung.h | 12 ++++
 3 files changed, 79 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 5d7b788282e94..71e86b2e7b21a 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -52,10 +52,15 @@ static void exynos_irq_mask(struct irq_data *irqd)
 	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
 	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
-	unsigned long reg_mask = our_chip->eint_mask + bank->eint_offset;
+	unsigned long reg_mask;
 	unsigned int mask;
 	unsigned long flags;
 
+	if (bank->eint_mask_offset)
+		reg_mask = bank->pctl_offset + bank->eint_mask_offset;
+	else
+		reg_mask = our_chip->eint_mask + bank->eint_offset;
+
 	raw_spin_lock_irqsave(&bank->slock, flags);
 
 	mask = readl(bank->eint_base + reg_mask);
@@ -70,7 +75,12 @@ static void exynos_irq_ack(struct irq_data *irqd)
 	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
 	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
-	unsigned long reg_pend = our_chip->eint_pend + bank->eint_offset;
+	unsigned long reg_pend;
+
+	if (bank->eint_pend_offset)
+		reg_pend = bank->pctl_offset + bank->eint_pend_offset;
+	else
+		reg_pend = our_chip->eint_pend + bank->eint_offset;
 
 	writel(1 << irqd->hwirq, bank->eint_base + reg_pend);
 }
@@ -80,7 +90,7 @@ static void exynos_irq_unmask(struct irq_data *irqd)
 	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
 	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
-	unsigned long reg_mask = our_chip->eint_mask + bank->eint_offset;
+	unsigned long reg_mask;
 	unsigned int mask;
 	unsigned long flags;
 
@@ -95,6 +105,11 @@ static void exynos_irq_unmask(struct irq_data *irqd)
 	if (irqd_get_trigger_type(irqd) & IRQ_TYPE_LEVEL_MASK)
 		exynos_irq_ack(irqd);
 
+	if (bank->eint_mask_offset)
+		reg_mask = bank->pctl_offset + bank->eint_mask_offset;
+	else
+		reg_mask = our_chip->eint_mask + bank->eint_offset;
+
 	raw_spin_lock_irqsave(&bank->slock, flags);
 
 	mask = readl(bank->eint_base + reg_mask);
@@ -111,7 +126,7 @@ static int exynos_irq_set_type(struct irq_data *irqd, unsigned int type)
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
 	unsigned int shift = EXYNOS_EINT_CON_LEN * irqd->hwirq;
 	unsigned int con, trig_type;
-	unsigned long reg_con = our_chip->eint_con + bank->eint_offset;
+	unsigned long reg_con;
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_RISING:
@@ -139,6 +154,11 @@ static int exynos_irq_set_type(struct irq_data *irqd, unsigned int type)
 	else
 		irq_set_handler_locked(irqd, handle_level_irq);
 
+	if (bank->eint_con_offset)
+		reg_con = bank->pctl_offset + bank->eint_con_offset;
+	else
+		reg_con = our_chip->eint_con + bank->eint_offset;
+
 	con = readl(bank->eint_base + reg_con);
 	con &= ~(EXYNOS_EINT_CON_MASK << shift);
 	con |= trig_type << shift;
@@ -669,6 +689,19 @@ static void exynos_pinctrl_suspend_bank(
 	pr_debug("%s: save    mask %#010x\n", bank->name, save->eint_mask);
 }
 
+static void exynosauto_pinctrl_suspend_bank(struct samsung_pinctrl_drv_data *drvdata,
+					    struct samsung_pin_bank *bank)
+{
+	struct exynos_eint_gpio_save *save = bank->soc_priv;
+	void __iomem *regs = bank->eint_base;
+
+	save->eint_con = readl(regs + bank->pctl_offset + bank->eint_con_offset);
+	save->eint_mask = readl(regs + bank->pctl_offset + bank->eint_mask_offset);
+
+	pr_debug("%s: save     con %#010x\n", bank->name, save->eint_con);
+	pr_debug("%s: save    mask %#010x\n", bank->name, save->eint_mask);
+}
+
 void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
 {
 	struct samsung_pin_bank *bank = drvdata->pin_banks;
@@ -676,8 +709,12 @@ void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
 	int i;
 
 	for (i = 0; i < drvdata->nr_banks; ++i, ++bank) {
-		if (bank->eint_type == EINT_TYPE_GPIO)
-			exynos_pinctrl_suspend_bank(drvdata, bank);
+		if (bank->eint_type == EINT_TYPE_GPIO) {
+			if (bank->eint_con_offset)
+				exynosauto_pinctrl_suspend_bank(drvdata, bank);
+			else
+				exynos_pinctrl_suspend_bank(drvdata, bank);
+		}
 		else if (bank->eint_type == EINT_TYPE_WKUP) {
 			if (!irq_chip) {
 				irq_chip = bank->irq_chip;
@@ -718,14 +755,33 @@ static void exynos_pinctrl_resume_bank(
 						+ bank->eint_offset);
 }
 
+static void exynosauto_pinctrl_resume_bank(struct samsung_pinctrl_drv_data *drvdata,
+					   struct samsung_pin_bank *bank)
+{
+	struct exynos_eint_gpio_save *save = bank->soc_priv;
+	void __iomem *regs = bank->eint_base;
+
+	pr_debug("%s:     con %#010x => %#010x\n", bank->name,
+		 readl(regs + bank->pctl_offset + bank->eint_con_offset), save->eint_con);
+	pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
+		 readl(regs + bank->pctl_offset + bank->eint_mask_offset), save->eint_mask);
+
+	writel(save->eint_con, regs + bank->pctl_offset + bank->eint_con_offset);
+	writel(save->eint_mask, regs + bank->pctl_offset + bank->eint_mask_offset);
+}
+
 void exynos_pinctrl_resume(struct samsung_pinctrl_drv_data *drvdata)
 {
 	struct samsung_pin_bank *bank = drvdata->pin_banks;
 	int i;
 
 	for (i = 0; i < drvdata->nr_banks; ++i, ++bank)
-		if (bank->eint_type == EINT_TYPE_GPIO)
-			exynos_pinctrl_resume_bank(drvdata, bank);
+		if (bank->eint_type == EINT_TYPE_GPIO) {
+			if (bank->eint_con_offset)
+				exynosauto_pinctrl_resume_bank(drvdata, bank);
+			else
+				exynos_pinctrl_resume_bank(drvdata, bank);
+		}
 }
 
 static void exynos_retention_enable(struct samsung_pinctrl_drv_data *drvdata)
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 5ad92600320e7..ce34f2968a160 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1106,6 +1106,9 @@ samsung_pinctrl_get_soc_data(struct samsung_pinctrl_drv_data *d,
 		bank->eint_type = bdata->eint_type;
 		bank->eint_mask = bdata->eint_mask;
 		bank->eint_offset = bdata->eint_offset;
+		bank->eint_con_offset = bdata->eint_con_offset;
+		bank->eint_mask_offset = bdata->eint_mask_offset;
+		bank->eint_pend_offset = bdata->eint_pend_offset;
 		bank->name = bdata->name;
 
 		raw_spin_lock_init(&bank->slock);
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index 0b459651bc4aa..a49d87841beca 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -122,6 +122,9 @@ struct samsung_pin_bank_type {
  * @eint_type: type of the external interrupt supported by the bank.
  * @eint_mask: bit mask of pins which support EINT function.
  * @eint_offset: SoC-specific EINT register or interrupt offset of bank.
+ * @eint_con_offset: ExynosAuto SoC-specific EINT control register offset of bank.
+ * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank.
+ * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank.
  * @name: name to be prefixed for each pin in this pin bank.
  */
 struct samsung_pin_bank_data {
@@ -133,6 +136,9 @@ struct samsung_pin_bank_data {
 	enum eint_type	eint_type;
 	u32		eint_mask;
 	u32		eint_offset;
+	u32		eint_con_offset;
+	u32		eint_mask_offset;
+	u32		eint_pend_offset;
 	const char	*name;
 };
 
@@ -147,6 +153,9 @@ struct samsung_pin_bank_data {
  * @eint_type: type of the external interrupt supported by the bank.
  * @eint_mask: bit mask of pins which support EINT function.
  * @eint_offset: SoC-specific EINT register or interrupt offset of bank.
+ * @eint_con_offset: ExynosAuto SoC-specific EINT register or interrupt offset of bank.
+ * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank.
+ * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank.
  * @name: name to be prefixed for each pin in this pin bank.
  * @id: id of the bank, propagated to the pin range.
  * @pin_base: starting pin number of the bank.
@@ -170,6 +179,9 @@ struct samsung_pin_bank {
 	enum eint_type	eint_type;
 	u32		eint_mask;
 	u32		eint_offset;
+	u32		eint_con_offset;
+	u32		eint_mask_offset;
+	u32		eint_pend_offset;
 	const char	*name;
 	u32		id;
 
-- 
GitLab


From 6cf96df77338c6a7e753229fe6d330ab60e28cda Mon Sep 17 00:00:00 2001
From: Jaewon Kim <jaewon02.kim@samsung.com>
Date: Mon, 11 Dec 2023 20:41:45 +0900
Subject: [PATCH 1204/4076] pinctrl: samsung: add exynosautov920 pinctrl

Add pinctrl data for ExynosAutov920 SoC.
It has a newly applied pinctrl register layer for ExynosAuto series.

Pinctrl data for ExynosAutoV920 SoC.
 - GPA0,GPA1 (10): External wake up interrupt
 - GPQ0 (2): SPMI (PMIC I/F)
 - GPB0,GPB1,GPB2,GPB3,GPB4,GPB5,GPB6 (47): I2S Audio
 - GPH0,GPH1,GPH2,GPH3,GPH4,GPH5,GPH6,GPH8 (49): PCIE, UFS, Ethernet
 - GPG0,GPG1,GPG2,GPG3,GPG4,GPG5 (29): General purpose
 - GPP0,GPP1,GPP2,GPP3,GPP4,GPP5,GPP6,GPP7,GPP8,GPP9,GPP10 (77): USI

Signed-off-by: Jaewon Kim <jaewon02.kim@samsung.com>
Link: https://lore.kernel.org/r/20231211114145.106255-3-jaewon02.kim@samsung.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../pinctrl/samsung/pinctrl-exynos-arm64.c    | 140 ++++++++++++++++++
 drivers/pinctrl/samsung/pinctrl-exynos.c      |  23 ++-
 drivers/pinctrl/samsung/pinctrl-exynos.h      |  25 ++++
 drivers/pinctrl/samsung/pinctrl-samsung.c     |   2 +
 drivers/pinctrl/samsung/pinctrl-samsung.h     |   1 +
 5 files changed, 190 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
index 8d08b29a21f6b..5480e0884abec 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
@@ -726,6 +726,146 @@ const struct samsung_pinctrl_of_match_data exynosautov9_of_data __initconst = {
 	.num_ctrl	= ARRAY_SIZE(exynosautov9_pin_ctrl),
 };
 
+/* pin banks of exynosautov920 pin-controller 0 (ALIVE) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks0[] = {
+	EXYNOSV920_PIN_BANK_EINTW(8, 0x0000, "gpa0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTW(2, 0x1000, "gpa1", 0x18, 0x20, 0x24),
+	EXYNOS850_PIN_BANK_EINTN(2, 0x2000, "gpq0"),
+};
+
+/* pin banks of exynosautov920 pin-controller 1 (AUD) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks1[] = {
+	EXYNOSV920_PIN_BANK_EINTG(7, 0x0000, "gpb0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(6, 0x1000, "gpb1", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x2000, "gpb2", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x3000, "gpb3", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x4000, "gpb4", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x5000, "gpb5", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x6000, "gpb6", 0x18, 0x24, 0x28),
+};
+
+/* pin banks of exynosautov920 pin-controller 2 (HSI0) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks2[] = {
+	EXYNOSV920_PIN_BANK_EINTG(6, 0x0000, "gph0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(2, 0x1000, "gph1", 0x18, 0x20, 0x24),
+};
+
+/* pin banks of exynosautov920 pin-controller 3 (HSI1) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks3[] = {
+	EXYNOSV920_PIN_BANK_EINTG(7, 0x000, "gph8", 0x18, 0x24, 0x28),
+};
+
+/* pin banks of exynosautov920 pin-controller 4 (HSI2) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks4[] = {
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x0000, "gph3", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(7, 0x1000, "gph4", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x2000, "gph5", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(7, 0x3000, "gph6", 0x18, 0x24, 0x28),
+};
+
+/* pin banks of exynosautov920 pin-controller 5 (HSI2UFS) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks5[] = {
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x000, "gph2", 0x18, 0x20, 0x24),
+};
+
+/* pin banks of exynosautov920 pin-controller 6 (PERIC0) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks6[] = {
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x0000, "gpp0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x1000, "gpp1", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x2000, "gpp2", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x3000, "gpg0", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x4000, "gpp3", 0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x5000, "gpp4", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x6000, "gpg2", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x7000, "gpg5", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(3, 0x8000, "gpg3", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x9000, "gpg4", 0x18, 0x24, 0x28),
+};
+
+/* pin banks of exynosautov920 pin-controller 7 (PERIC1) */
+static const struct samsung_pin_bank_data exynosautov920_pin_banks7[] = {
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x0000, "gpp5",  0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(5, 0x1000, "gpp6",  0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x2000, "gpp10", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x3000, "gpp7",  0x18, 0x24, 0x28),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x4000, "gpp8",  0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x5000, "gpp11", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x6000, "gpp9",  0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(4, 0x7000, "gpp12", 0x18, 0x20, 0x24),
+	EXYNOSV920_PIN_BANK_EINTG(8, 0x8000, "gpg1",  0x18, 0x24, 0x28),
+};
+
+static const struct samsung_retention_data exynosautov920_retention_data __initconst = {
+	.regs	 = NULL,
+	.nr_regs = 0,
+	.value	 = 0,
+	.refcnt	 = &exynos_shared_retention_refcnt,
+	.init	 = exynos_retention_init,
+};
+
+static const struct samsung_pin_ctrl exynosautov920_pin_ctrl[] = {
+	{
+		/* pin-controller instance 0 ALIVE data */
+		.pin_banks	= exynosautov920_pin_banks0,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks0),
+		.eint_wkup_init	= exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+		.retention_data	= &exynosautov920_retention_data,
+	}, {
+		/* pin-controller instance 1 AUD data */
+		.pin_banks	= exynosautov920_pin_banks1,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks1),
+	}, {
+		/* pin-controller instance 2 HSI0 data */
+		.pin_banks	= exynosautov920_pin_banks2,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks2),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 3 HSI1 data */
+		.pin_banks	= exynosautov920_pin_banks3,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks3),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 4 HSI2 data */
+		.pin_banks	= exynosautov920_pin_banks4,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks4),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 5 HSI2UFS data */
+		.pin_banks	= exynosautov920_pin_banks5,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks5),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 6 PERIC0 data */
+		.pin_banks	= exynosautov920_pin_banks6,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks6),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 7 PERIC1 data */
+		.pin_banks	= exynosautov920_pin_banks7,
+		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks7),
+		.eint_gpio_init	= exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	},
+};
+
+const struct samsung_pinctrl_of_match_data exynosautov920_of_data __initconst = {
+	.ctrl		= exynosautov920_pin_ctrl,
+	.num_ctrl	= ARRAY_SIZE(exynosautov920_pin_ctrl),
+};
+
 /*
  * Pinctrl driver data for Tesla FSD SoC. FSD SoC includes three
  * gpio/pin-mux/pinconfig controllers.
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 71e86b2e7b21a..d3d4b5d036c88 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -281,7 +281,10 @@ static irqreturn_t exynos_eint_gpio_irq(int irq, void *data)
 	unsigned int svc, group, pin;
 	int ret;
 
-	svc = readl(bank->eint_base + EXYNOS_SVC_OFFSET);
+	if (bank->eint_con_offset)
+		svc = readl(bank->eint_base + EXYNOSAUTO_SVC_OFFSET);
+	else
+		svc = readl(bank->eint_base + EXYNOS_SVC_OFFSET);
 	group = EXYNOS_SVC_GROUP(svc);
 	pin = svc & EXYNOS_SVC_NUM_MASK;
 
@@ -490,6 +493,22 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
 	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
 };
 
+static const struct exynos_irq_chip exynosautov920_wkup_irq_chip __initconst = {
+	.chip = {
+		.name = "exynosautov920_wkup_irq_chip",
+		.irq_unmask = exynos_irq_unmask,
+		.irq_mask = exynos_irq_mask,
+		.irq_ack = exynos_irq_ack,
+		.irq_set_type = exynos_irq_set_type,
+		.irq_set_wake = exynos_wkup_irq_set_wake,
+		.irq_request_resources = exynos_irq_request_resources,
+		.irq_release_resources = exynos_irq_release_resources,
+	},
+	.eint_wake_mask_value = &eint_wake_mask_value,
+	.eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK,
+	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
+};
+
 /* list of external wakeup controllers supported */
 static const struct of_device_id exynos_wkup_irq_ids[] = {
 	{ .compatible = "samsung,s5pv210-wakeup-eint",
@@ -502,6 +521,8 @@ static const struct of_device_id exynos_wkup_irq_ids[] = {
 			.data = &exynos7_wkup_irq_chip },
 	{ .compatible = "samsung,exynosautov9-wakeup-eint",
 			.data = &exynos7_wkup_irq_chip },
+	{ .compatible = "samsung,exynosautov920-wakeup-eint",
+			.data = &exynosautov920_wkup_irq_chip },
 	{ }
 };
 
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.h b/drivers/pinctrl/samsung/pinctrl-exynos.h
index 3ac52c2cf9984..305cb1d31de49 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.h
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.h
@@ -31,6 +31,7 @@
 #define EXYNOS7_WKUP_EMASK_OFFSET	0x900
 #define EXYNOS7_WKUP_EPEND_OFFSET	0xA00
 #define EXYNOS_SVC_OFFSET		0xB08
+#define EXYNOSAUTO_SVC_OFFSET		0xF008
 
 /* helpers to access interrupt service register */
 #define EXYNOS_SVC_GROUP_SHIFT		3
@@ -140,6 +141,30 @@
 		.name		= id				\
 	}
 
+#define EXYNOSV920_PIN_BANK_EINTG(pins, reg, id, con_offs, mask_offs, pend_offs)	\
+	{							\
+		.type			= &exynos850_bank_type_off,	\
+		.pctl_offset		= reg,				\
+		.nr_pins		= pins,				\
+		.eint_type		= EINT_TYPE_GPIO,		\
+		.eint_con_offset	= con_offs,			\
+		.eint_mask_offset	= mask_offs,			\
+		.eint_pend_offset	= pend_offs,			\
+		.name			= id				\
+	}
+
+#define EXYNOSV920_PIN_BANK_EINTW(pins, reg, id, con_offs, mask_offs, pend_offs)	\
+	{							\
+		.type			= &exynos850_bank_type_alive,	\
+		.pctl_offset		= reg,				\
+		.nr_pins		= pins,				\
+		.eint_type		= EINT_TYPE_WKUP,		\
+		.eint_con_offset	= con_offs,			\
+		.eint_mask_offset	= mask_offs,			\
+		.eint_pend_offset	= pend_offs,			\
+		.name			= id				\
+	}
+
 /**
  * struct exynos_weint_data: irq specific data for all the wakeup interrupts
  * generated by the external wakeup interrupt controller.
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index ce34f2968a160..dbf38767f15f0 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1324,6 +1324,8 @@ static const struct of_device_id samsung_pinctrl_dt_match[] = {
 		.data = &exynos850_of_data },
 	{ .compatible = "samsung,exynosautov9-pinctrl",
 		.data = &exynosautov9_of_data },
+	{ .compatible = "samsung,exynosautov920-pinctrl",
+		.data = &exynosautov920_of_data },
 	{ .compatible = "tesla,fsd-pinctrl",
 		.data = &fsd_of_data },
 #endif
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index a49d87841beca..ab791afaabf55 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -362,6 +362,7 @@ extern const struct samsung_pinctrl_of_match_data exynos7_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos7885_of_data;
 extern const struct samsung_pinctrl_of_match_data exynos850_of_data;
 extern const struct samsung_pinctrl_of_match_data exynosautov9_of_data;
+extern const struct samsung_pinctrl_of_match_data exynosautov920_of_data;
 extern const struct samsung_pinctrl_of_match_data fsd_of_data;
 extern const struct samsung_pinctrl_of_match_data gs101_of_data;
 extern const struct samsung_pinctrl_of_match_data s3c64xx_of_data;
-- 
GitLab


From 59b3e31e73322ec195e45e0a1da712c752ee1b0c Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 28 Nov 2023 04:00:10 +0000
Subject: [PATCH 1205/4076] leds: trigger: netdev: Extend speeds up to 10G

Add 2.5G, 5G and 10G as available speeds to the netdev LED trigger.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/99e7d3304c6bba7f4863a4a80764a869855f2085.1701143925.git.daniel@makrotopia.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-netdev.c | 32 ++++++++++++++++++++++++++-
 include/linux/leds.h                  |  3 +++
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index e358e77e4b38f..bd68da15c723e 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -99,6 +99,18 @@ static void set_baseline_state(struct led_netdev_data *trigger_data)
 		    trigger_data->link_speed == SPEED_1000)
 			blink_on = true;
 
+		if (test_bit(TRIGGER_NETDEV_LINK_2500, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_2500)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_5000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_5000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_10000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_10000)
+			blink_on = true;
+
 		if (test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &trigger_data->mode) &&
 		    trigger_data->duplex == DUPLEX_HALF)
 			blink_on = true;
@@ -286,6 +298,9 @@ static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 	case TRIGGER_NETDEV_LINK_10:
 	case TRIGGER_NETDEV_LINK_100:
 	case TRIGGER_NETDEV_LINK_1000:
+	case TRIGGER_NETDEV_LINK_2500:
+	case TRIGGER_NETDEV_LINK_5000:
+	case TRIGGER_NETDEV_LINK_10000:
 	case TRIGGER_NETDEV_HALF_DUPLEX:
 	case TRIGGER_NETDEV_FULL_DUPLEX:
 	case TRIGGER_NETDEV_TX:
@@ -316,6 +331,9 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	case TRIGGER_NETDEV_LINK_10:
 	case TRIGGER_NETDEV_LINK_100:
 	case TRIGGER_NETDEV_LINK_1000:
+	case TRIGGER_NETDEV_LINK_2500:
+	case TRIGGER_NETDEV_LINK_5000:
+	case TRIGGER_NETDEV_LINK_10000:
 	case TRIGGER_NETDEV_HALF_DUPLEX:
 	case TRIGGER_NETDEV_FULL_DUPLEX:
 	case TRIGGER_NETDEV_TX:
@@ -334,7 +352,10 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	if (test_bit(TRIGGER_NETDEV_LINK, &mode) &&
 	    (test_bit(TRIGGER_NETDEV_LINK_10, &mode) ||
 	     test_bit(TRIGGER_NETDEV_LINK_100, &mode) ||
-	     test_bit(TRIGGER_NETDEV_LINK_1000, &mode)))
+	     test_bit(TRIGGER_NETDEV_LINK_1000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_2500, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_5000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_10000, &mode)))
 		return -EINVAL;
 
 	cancel_delayed_work_sync(&trigger_data->work);
@@ -364,6 +385,9 @@ DEFINE_NETDEV_TRIGGER(link, TRIGGER_NETDEV_LINK);
 DEFINE_NETDEV_TRIGGER(link_10, TRIGGER_NETDEV_LINK_10);
 DEFINE_NETDEV_TRIGGER(link_100, TRIGGER_NETDEV_LINK_100);
 DEFINE_NETDEV_TRIGGER(link_1000, TRIGGER_NETDEV_LINK_1000);
+DEFINE_NETDEV_TRIGGER(link_2500, TRIGGER_NETDEV_LINK_2500);
+DEFINE_NETDEV_TRIGGER(link_5000, TRIGGER_NETDEV_LINK_5000);
+DEFINE_NETDEV_TRIGGER(link_10000, TRIGGER_NETDEV_LINK_10000);
 DEFINE_NETDEV_TRIGGER(half_duplex, TRIGGER_NETDEV_HALF_DUPLEX);
 DEFINE_NETDEV_TRIGGER(full_duplex, TRIGGER_NETDEV_FULL_DUPLEX);
 DEFINE_NETDEV_TRIGGER(tx, TRIGGER_NETDEV_TX);
@@ -422,6 +446,9 @@ static struct attribute *netdev_trig_attrs[] = {
 	&dev_attr_link_10.attr,
 	&dev_attr_link_100.attr,
 	&dev_attr_link_1000.attr,
+	&dev_attr_link_2500.attr,
+	&dev_attr_link_5000.attr,
+	&dev_attr_link_10000.attr,
 	&dev_attr_full_duplex.attr,
 	&dev_attr_half_duplex.attr,
 	&dev_attr_rx.attr,
@@ -519,6 +546,9 @@ static void netdev_trig_work(struct work_struct *work)
 			 test_bit(TRIGGER_NETDEV_LINK_10, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_LINK_100, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_LINK_1000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_2500, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_5000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_10000, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_FULL_DUPLEX, &trigger_data->mode);
 		interval = jiffies_to_msecs(
diff --git a/include/linux/leds.h b/include/linux/leds.h
index aa16dc2a8230f..1bdf7f5a0d7c0 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -588,6 +588,9 @@ enum led_trigger_netdev_modes {
 	TRIGGER_NETDEV_LINK_10,
 	TRIGGER_NETDEV_LINK_100,
 	TRIGGER_NETDEV_LINK_1000,
+	TRIGGER_NETDEV_LINK_2500,
+	TRIGGER_NETDEV_LINK_5000,
+	TRIGGER_NETDEV_LINK_10000,
 	TRIGGER_NETDEV_HALF_DUPLEX,
 	TRIGGER_NETDEV_FULL_DUPLEX,
 	TRIGGER_NETDEV_TX,
-- 
GitLab


From ee8bfb47222a5cc59dee345b7369c5f2068e78cd Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 28 Nov 2023 04:00:39 +0000
Subject: [PATCH 1206/4076] docs: ABI: sysfs-class-led-trigger-netdev: Add new
 modes and entry

Document newly introduced modes for the LED netdev trigger.

Add documentation for new modes:
- link_2500
- link_5000
- link_10000

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/e72a6794639cf3881d698e1d34b456e747da1b95.1701143925.git.daniel@makrotopia.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../testing/sysfs-class-led-trigger-netdev    | 39 +++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-netdev b/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
index f6d9d72ce77b7..a6c307c4befa0 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
@@ -114,6 +114,45 @@ Description:
 		speed of 1000Mbps of the named network device.
 		Setting this value also immediately changes the LED state.
 
+What:		/sys/class/leds/<led>/link_2500
+Date:		Nov 2023
+KernelVersion:	6.8
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal the link speed state of 2500Mbps of the named network device.
+
+		If set to 0 (default), the LED's normal state is off.
+
+		If set to 1, the LED's normal state reflects the link state
+		speed of 2500Mbps of the named network device.
+		Setting this value also immediately changes the LED state.
+
+What:		/sys/class/leds/<led>/link_5000
+Date:		Nov 2023
+KernelVersion:	6.8
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal the link speed state of 5000Mbps of the named network device.
+
+		If set to 0 (default), the LED's normal state is off.
+
+		If set to 1, the LED's normal state reflects the link state
+		speed of 5000Mbps of the named network device.
+		Setting this value also immediately changes the LED state.
+
+What:		/sys/class/leds/<led>/link_10000
+Date:		Nov 2023
+KernelVersion:	6.8
+Contact:	linux-leds@vger.kernel.org
+Description:
+		Signal the link speed state of 10000Mbps of the named network device.
+
+		If set to 0 (default), the LED's normal state is off.
+
+		If set to 1, the LED's normal state reflects the link state
+		speed of 10000Mbps of the named network device.
+		Setting this value also immediately changes the LED state.
+
 What:		/sys/class/leds/<led>/half_duplex
 Date:		Jun 2023
 KernelVersion:	6.5
-- 
GitLab


From a82cc9b8debfa3e71098a71bece2a696cc1d9624 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 25 Oct 2023 14:06:19 -0500
Subject: [PATCH 1207/4076] leds: syscon: Support 'reg' in addition to 'offset'
 for register address

The register-bit-led binding now also supports 'reg' in addition to
'offset' for the register address. Add support to the driver to get the
address from 'reg'.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231025190619.881090-2-robh@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-syscon.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/leds/leds-syscon.c b/drivers/leds/leds-syscon.c
index 360a376fa738c..d633ad519d0cd 100644
--- a/drivers/leds/leds-syscon.c
+++ b/drivers/leds/leds-syscon.c
@@ -81,7 +81,8 @@ static int syscon_led_probe(struct platform_device *pdev)
 
 	sled->map = map;
 
-	if (of_property_read_u32(np, "offset", &sled->offset))
+	if (of_property_read_u32(np, "reg", &sled->offset) &&
+	    of_property_read_u32(np, "offset", &sled->offset))
 		return -EINVAL;
 	if (of_property_read_u32(np, "mask", &sled->mask))
 		return -EINVAL;
-- 
GitLab


From 1de1da7b07822d290c5ba0f48829c7be1c684c0f Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 22 Nov 2023 13:54:17 -0700
Subject: [PATCH 1208/4076] dt-bindings: leds: Fix JSON pointer in
 max-brightness

A valid JSON pointer should begin with a '/'. The json-schema package is
lax on this allowing either form, but that's changing in new versions.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231122205418.2482076-1-robh@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 Documentation/devicetree/bindings/leds/common.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml
index c8d0ba5f23276..55a8d1385e210 100644
--- a/Documentation/devicetree/bindings/leds/common.yaml
+++ b/Documentation/devicetree/bindings/leds/common.yaml
@@ -167,7 +167,7 @@ properties:
       Note that this flag is mainly used for PWM-LEDs, where it is not possible
       to map brightness to current. Drivers for other controllers should use
       led-max-microamp.
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
 
   panic-indicator:
     description:
-- 
GitLab


From 65dcdf495a79e2b502e58a38588aeea1e92708aa Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel@sholland.org>
Date: Sun, 29 Oct 2023 16:26:55 -0500
Subject: [PATCH 1209/4076] dt-bindings: leds: Add Allwinner A100 LED
 controller

The Allwinner A100, R329, and D1 SoCs contain an LED controller designed
to drive a series of RGB LED pixels. It supports PIO and DMA transfers,
and has configurable timing and pixel format. All three implementations
appear to be identical, so use the oldest as the fallback compatible.

Acked-by: Guo Ren <guoren@kernel.org>
Acked-by: Maxime Ripard <mripard@kernel.org>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Tested-by: Trevor Woerner <twoerner@gmail.com>
Signed-off-by: Samuel Holland <samuel@sholland.org>
Link: https://lore.kernel.org/r/20231029212738.7871-2-samuel@sholland.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../leds/allwinner,sun50i-a100-ledc.yaml      | 137 ++++++++++++++++++
 1 file changed, 137 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/leds/allwinner,sun50i-a100-ledc.yaml

diff --git a/Documentation/devicetree/bindings/leds/allwinner,sun50i-a100-ledc.yaml b/Documentation/devicetree/bindings/leds/allwinner,sun50i-a100-ledc.yaml
new file mode 100644
index 0000000000000..760cb336dccb5
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/allwinner,sun50i-a100-ledc.yaml
@@ -0,0 +1,137 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/allwinner,sun50i-a100-ledc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A100 LED Controller
+
+maintainers:
+  - Samuel Holland <samuel@sholland.org>
+
+description:
+  The LED controller found in Allwinner sunxi SoCs uses a one-wire serial
+  interface to drive up to 1024 RGB LEDs.
+
+properties:
+  compatible:
+    oneOf:
+      - const: allwinner,sun50i-a100-ledc
+      - items:
+          - enum:
+              - allwinner,sun20i-d1-ledc
+              - allwinner,sun50i-r329-ledc
+          - const: allwinner,sun50i-a100-ledc
+
+  reg:
+    maxItems: 1
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Bus clock
+      - description: Module clock
+
+  clock-names:
+    items:
+      - const: bus
+      - const: mod
+
+  resets:
+    maxItems: 1
+
+  dmas:
+    maxItems: 1
+    description: TX DMA channel
+
+  dma-names:
+    const: tx
+
+  allwinner,pixel-format:
+    description: Pixel format (subpixel transmission order), default is "grb"
+    enum:
+      - bgr
+      - brg
+      - gbr
+      - grb
+      - rbg
+      - rgb
+
+  allwinner,t0h-ns:
+    default: 336
+    description: Length of high pulse when transmitting a "0" bit
+
+  allwinner,t0l-ns:
+    default: 840
+    description: Length of low pulse when transmitting a "0" bit
+
+  allwinner,t1h-ns:
+    default: 882
+    description: Length of high pulse when transmitting a "1" bit
+
+  allwinner,t1l-ns:
+    default: 294
+    description: Length of low pulse when transmitting a "1" bit
+
+  allwinner,treset-ns:
+    default: 300000
+    description: Minimum delay between transmission frames
+
+patternProperties:
+  "^multi-led@[0-9a-f]+$":
+    type: object
+    $ref: leds-class-multicolor.yaml#
+    unevaluatedProperties: false
+    properties:
+      reg:
+        minimum: 0
+        maximum: 1023
+        description: Index of the LED in the series (must be contiguous)
+
+    required:
+      - reg
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/leds/common.h>
+
+    ledc: led-controller@2008000 {
+      compatible = "allwinner,sun20i-d1-ledc",
+                   "allwinner,sun50i-a100-ledc";
+      reg = <0x2008000 0x400>;
+      interrupts = <36 IRQ_TYPE_LEVEL_HIGH>;
+      clocks = <&ccu 12>, <&ccu 34>;
+      clock-names = "bus", "mod";
+      resets = <&ccu 12>;
+      dmas = <&dma 42>;
+      dma-names = "tx";
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      multi-led@0 {
+        reg = <0x0>;
+        color = <LED_COLOR_ID_RGB>;
+        function = LED_FUNCTION_INDICATOR;
+      };
+    };
+
+...
-- 
GitLab


From ec95a68dad00c81d53ab9aa9bcbdf0a86347e0d9 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel@sholland.org>
Date: Sun, 29 Oct 2023 16:26:56 -0500
Subject: [PATCH 1210/4076] leds: sun50i-a100: New driver for the A100 LED
 controller

Some Allwinner sunxi SoCs, starting with the A100, contain an LED
controller designed to drive RGB LED pixels. Add a driver for it using
the multicolor LED framework, and with LEDs defined in the device tree.

Acked-by: Guo Ren <guoren@kernel.org>
Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Samuel Holland <samuel@sholland.org>
Link: https://lore.kernel.org/r/20231029212738.7871-3-samuel@sholland.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/Kconfig            |   9 +
 drivers/leds/Makefile           |   1 +
 drivers/leds/leds-sun50i-a100.c | 580 ++++++++++++++++++++++++++++++++
 3 files changed, 590 insertions(+)
 create mode 100644 drivers/leds/leds-sun50i-a100.c

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 6292fddcc55cd..6496ef525579a 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -298,6 +298,15 @@ config LEDS_COBALT_RAQ
 	help
 	  This option enables support for the Cobalt Raq series LEDs.
 
+config LEDS_SUN50I_A100
+	tristate "LED support for Allwinner A100 RGB LED controller"
+	depends on LEDS_CLASS_MULTICOLOR && OF
+	depends on ARCH_SUNXI || COMPILE_TEST
+	help
+	  This option enables support for the RGB LED controller found
+	  in some Allwinner sunxi SoCs, including A100, R329, and D1.
+	  It uses a one-wire interface to control up to 1024 LEDs.
+
 config LEDS_SUNFIRE
 	tristate "LED support for SunFire servers."
 	depends on LEDS_CLASS
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index d7348e8bc019a..b82a538e3f8c0 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -78,6 +78,7 @@ obj-$(CONFIG_LEDS_POWERNV)		+= leds-powernv.o
 obj-$(CONFIG_LEDS_PWM)			+= leds-pwm.o
 obj-$(CONFIG_LEDS_REGULATOR)		+= leds-regulator.o
 obj-$(CONFIG_LEDS_SC27XX_BLTC)		+= leds-sc27xx-bltc.o
+obj-$(CONFIG_LEDS_SUN50I_A100)		+= leds-sun50i-a100.o
 obj-$(CONFIG_LEDS_SUNFIRE)		+= leds-sunfire.o
 obj-$(CONFIG_LEDS_SYSCON)		+= leds-syscon.o
 obj-$(CONFIG_LEDS_TCA6507)		+= leds-tca6507.o
diff --git a/drivers/leds/leds-sun50i-a100.c b/drivers/leds/leds-sun50i-a100.c
new file mode 100644
index 0000000000000..e4a7e692a9087
--- /dev/null
+++ b/drivers/leds/leds-sun50i-a100.c
@@ -0,0 +1,580 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021-2023 Samuel Holland <samuel@sholland.org>
+ *
+ * Partly based on drivers/leds/leds-turris-omnia.c, which is:
+ *     Copyright (c) 2020 by Marek Behún <kabel@kernel.org>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/led-class-multicolor.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/reset.h>
+#include <linux/spinlock.h>
+
+#define LEDC_CTRL_REG			0x0000
+#define LEDC_CTRL_REG_DATA_LENGTH		GENMASK(28, 16)
+#define LEDC_CTRL_REG_RGB_MODE			GENMASK(8, 6)
+#define LEDC_CTRL_REG_LEDC_EN			BIT(0)
+#define LEDC_T01_TIMING_CTRL_REG	0x0004
+#define LEDC_T01_TIMING_CTRL_REG_T1H		GENMASK(26, 21)
+#define LEDC_T01_TIMING_CTRL_REG_T1L		GENMASK(20, 16)
+#define LEDC_T01_TIMING_CTRL_REG_T0H		GENMASK(10, 6)
+#define LEDC_T01_TIMING_CTRL_REG_T0L		GENMASK(5, 0)
+#define LEDC_RESET_TIMING_CTRL_REG	0x000c
+#define LEDC_RESET_TIMING_CTRL_REG_TR		GENMASK(28, 16)
+#define LEDC_RESET_TIMING_CTRL_REG_LED_NUM	GENMASK(9, 0)
+#define LEDC_DATA_REG			0x0014
+#define LEDC_DMA_CTRL_REG		0x0018
+#define LEDC_DMA_CTRL_REG_DMA_EN		BIT(5)
+#define LEDC_DMA_CTRL_REG_FIFO_TRIG_LEVEL	GENMASK(4, 0)
+#define LEDC_INT_CTRL_REG		0x001c
+#define LEDC_INT_CTRL_REG_GLOBAL_INT_EN		BIT(5)
+#define LEDC_INT_CTRL_REG_FIFO_CPUREQ_INT_EN	BIT(1)
+#define LEDC_INT_CTRL_REG_TRANS_FINISH_INT_EN	BIT(0)
+#define LEDC_INT_STS_REG		0x0020
+#define LEDC_INT_STS_REG_FIFO_WLW		GENMASK(15, 10)
+#define LEDC_INT_STS_REG_FIFO_CPUREQ_INT	BIT(1)
+#define LEDC_INT_STS_REG_TRANS_FINISH_INT	BIT(0)
+
+#define LEDC_FIFO_DEPTH			32U
+#define LEDC_MAX_LEDS			1024
+#define LEDC_CHANNELS_PER_LED		3 /* RGB */
+
+#define LEDS_TO_BYTES(n)		((n) * sizeof(u32))
+
+struct sun50i_a100_ledc_led {
+	struct led_classdev_mc mc_cdev;
+	struct mc_subled subled_info[LEDC_CHANNELS_PER_LED];
+	u32 addr;
+};
+
+#define to_ledc_led(mc) container_of(mc, struct sun50i_a100_ledc_led, mc_cdev)
+
+struct sun50i_a100_ledc_timing {
+	u32 t0h_ns;
+	u32 t0l_ns;
+	u32 t1h_ns;
+	u32 t1l_ns;
+	u32 treset_ns;
+};
+
+struct sun50i_a100_ledc {
+	struct device *dev;
+	void __iomem *base;
+	struct clk *bus_clk;
+	struct clk *mod_clk;
+	struct reset_control *reset;
+
+	u32 *buffer;
+	struct dma_chan *dma_chan;
+	dma_addr_t dma_handle;
+	unsigned int pio_length;
+	unsigned int pio_offset;
+
+	spinlock_t lock;
+	unsigned int next_length;
+	bool xfer_active;
+
+	u32 format;
+	struct sun50i_a100_ledc_timing timing;
+
+	u32 max_addr;
+	u32 num_leds;
+	struct sun50i_a100_ledc_led leds[] __counted_by(num_leds);
+};
+
+static int sun50i_a100_ledc_dma_xfer(struct sun50i_a100_ledc *priv, unsigned int length)
+{
+	struct dma_async_tx_descriptor *desc;
+	dma_cookie_t cookie;
+
+	desc = dmaengine_prep_slave_single(priv->dma_chan, priv->dma_handle,
+					   LEDS_TO_BYTES(length), DMA_MEM_TO_DEV, 0);
+	if (!desc)
+		return -ENOMEM;
+
+	cookie = dmaengine_submit(desc);
+	if (dma_submit_error(cookie))
+		return -EIO;
+
+	dma_async_issue_pending(priv->dma_chan);
+
+	return 0;
+}
+
+static void sun50i_a100_ledc_pio_xfer(struct sun50i_a100_ledc *priv, unsigned int fifo_used)
+{
+	unsigned int burst, length, offset;
+	u32 control;
+
+	length = priv->pio_length;
+	offset = priv->pio_offset;
+	burst  = min(length, LEDC_FIFO_DEPTH - fifo_used);
+
+	iowrite32_rep(priv->base + LEDC_DATA_REG, priv->buffer + offset, burst);
+
+	if (burst < length) {
+		priv->pio_length = length - burst;
+		priv->pio_offset = offset + burst;
+
+		if (!offset) {
+			control = readl(priv->base + LEDC_INT_CTRL_REG);
+			control |= LEDC_INT_CTRL_REG_FIFO_CPUREQ_INT_EN;
+			writel(control, priv->base + LEDC_INT_CTRL_REG);
+		}
+	} else {
+		/* Disable the request IRQ once all data is written. */
+		control = readl(priv->base + LEDC_INT_CTRL_REG);
+		control &= ~LEDC_INT_CTRL_REG_FIFO_CPUREQ_INT_EN;
+		writel(control, priv->base + LEDC_INT_CTRL_REG);
+	}
+}
+
+static void sun50i_a100_ledc_start_xfer(struct sun50i_a100_ledc *priv, unsigned int length)
+{
+	bool use_dma = false;
+	u32 control;
+
+	if (priv->dma_chan && length > LEDC_FIFO_DEPTH) {
+		int ret;
+
+		ret = sun50i_a100_ledc_dma_xfer(priv, length);
+		if (ret)
+			dev_warn(priv->dev, "Failed to set up DMA (%d), using PIO\n", ret);
+		else
+			use_dma = true;
+	}
+
+	/* The DMA trigger level must be at least the burst length. */
+	control = FIELD_PREP(LEDC_DMA_CTRL_REG_DMA_EN, use_dma) |
+		  FIELD_PREP_CONST(LEDC_DMA_CTRL_REG_FIFO_TRIG_LEVEL, LEDC_FIFO_DEPTH / 2);
+	writel(control, priv->base + LEDC_DMA_CTRL_REG);
+
+	control = readl(priv->base + LEDC_CTRL_REG);
+	control &= ~LEDC_CTRL_REG_DATA_LENGTH;
+	control |= FIELD_PREP(LEDC_CTRL_REG_DATA_LENGTH, length) | LEDC_CTRL_REG_LEDC_EN;
+	writel(control, priv->base + LEDC_CTRL_REG);
+
+	if (!use_dma) {
+		/* The FIFO is empty when starting a new transfer. */
+		unsigned int fifo_used = 0;
+
+		priv->pio_length = length;
+		priv->pio_offset = 0;
+
+		sun50i_a100_ledc_pio_xfer(priv, fifo_used);
+	}
+}
+
+static irqreturn_t sun50i_a100_ledc_irq(int irq, void *data)
+{
+	struct sun50i_a100_ledc *priv = data;
+	u32 status;
+
+	status = readl(priv->base + LEDC_INT_STS_REG);
+
+	if (status & LEDC_INT_STS_REG_TRANS_FINISH_INT) {
+		unsigned int next_length;
+
+		spin_lock(&priv->lock);
+
+		/* If another transfer is queued, dequeue and start it. */
+		next_length = priv->next_length;
+		if (next_length)
+			priv->next_length = 0;
+		else
+			priv->xfer_active = false;
+
+		spin_unlock(&priv->lock);
+
+		if (next_length)
+			sun50i_a100_ledc_start_xfer(priv, next_length);
+	} else if (status & LEDC_INT_STS_REG_FIFO_CPUREQ_INT) {
+		/* Continue the current transfer. */
+		sun50i_a100_ledc_pio_xfer(priv, FIELD_GET(LEDC_INT_STS_REG_FIFO_WLW, status));
+	}
+
+	/* Clear the W1C status bits. */
+	writel(status, priv->base + LEDC_INT_STS_REG);
+
+	return IRQ_HANDLED;
+}
+
+static void sun50i_a100_ledc_brightness_set(struct led_classdev *cdev,
+					    enum led_brightness brightness)
+{
+	struct sun50i_a100_ledc *priv = dev_get_drvdata(cdev->dev->parent);
+	struct led_classdev_mc *mc_cdev = lcdev_to_mccdev(cdev);
+	struct sun50i_a100_ledc_led *led = to_ledc_led(mc_cdev);
+	unsigned int next_length;
+	unsigned long flags;
+	bool xfer_active;
+
+	led_mc_calc_color_components(mc_cdev, brightness);
+
+	priv->buffer[led->addr] = led->subled_info[0].brightness << 16 |
+				  led->subled_info[1].brightness <<  8 |
+				  led->subled_info[2].brightness;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* Start, enqueue, or extend an enqueued transfer, as appropriate. */
+	next_length = max(priv->next_length, led->addr + 1);
+	xfer_active = priv->xfer_active;
+	if (xfer_active)
+		priv->next_length = next_length;
+	else
+		priv->xfer_active = true;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	if (!xfer_active)
+		sun50i_a100_ledc_start_xfer(priv, next_length);
+}
+
+static const char *const sun50i_a100_ledc_formats[] = {
+	"rgb", "rbg", "grb", "gbr", "brg", "bgr",
+};
+
+static int sun50i_a100_ledc_parse_format(const struct device_node *np,
+					 struct sun50i_a100_ledc *priv)
+{
+	const char *format = "grb";
+	u32 i;
+
+	of_property_read_string(np, "allwinner,pixel-format", &format);
+
+	for (i = 0; i < ARRAY_SIZE(sun50i_a100_ledc_formats); i++) {
+		if (!strcmp(format, sun50i_a100_ledc_formats[i])) {
+			priv->format = i;
+			return 0;
+		}
+	}
+
+	return dev_err_probe(priv->dev, -EINVAL, "Bad pixel format '%s'\n", format);
+}
+
+static void sun50i_a100_ledc_set_format(struct sun50i_a100_ledc *priv)
+{
+	u32 control;
+
+	control = readl(priv->base + LEDC_CTRL_REG);
+	control &= ~LEDC_CTRL_REG_RGB_MODE;
+	control |= FIELD_PREP(LEDC_CTRL_REG_RGB_MODE, priv->format);
+	writel(control, priv->base + LEDC_CTRL_REG);
+}
+
+static const struct sun50i_a100_ledc_timing sun50i_a100_ledc_default_timing = {
+	.t0h_ns = 336,
+	.t0l_ns = 840,
+	.t1h_ns = 882,
+	.t1l_ns = 294,
+	.treset_ns = 300000,
+};
+
+static int sun50i_a100_ledc_parse_timing(const struct device_node *np,
+					 struct sun50i_a100_ledc *priv)
+{
+	struct sun50i_a100_ledc_timing *timing = &priv->timing;
+
+	*timing = sun50i_a100_ledc_default_timing;
+
+	of_property_read_u32(np, "allwinner,t0h-ns", &timing->t0h_ns);
+	of_property_read_u32(np, "allwinner,t0l-ns", &timing->t0l_ns);
+	of_property_read_u32(np, "allwinner,t1h-ns", &timing->t1h_ns);
+	of_property_read_u32(np, "allwinner,t1l-ns", &timing->t1l_ns);
+	of_property_read_u32(np, "allwinner,treset-ns", &timing->treset_ns);
+
+	return 0;
+}
+
+static void sun50i_a100_ledc_set_timing(struct sun50i_a100_ledc *priv)
+{
+	const struct sun50i_a100_ledc_timing *timing = &priv->timing;
+	unsigned long mod_freq = clk_get_rate(priv->mod_clk);
+	u32 cycle_ns = NSEC_PER_SEC / mod_freq;
+	u32 control;
+
+	control = FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T1H, timing->t1h_ns / cycle_ns) |
+		  FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T1L, timing->t1l_ns / cycle_ns) |
+		  FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T0H, timing->t0h_ns / cycle_ns) |
+		  FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T0L, timing->t0l_ns / cycle_ns);
+	writel(control, priv->base + LEDC_T01_TIMING_CTRL_REG);
+
+	control = FIELD_PREP(LEDC_RESET_TIMING_CTRL_REG_TR, timing->treset_ns / cycle_ns) |
+		  FIELD_PREP(LEDC_RESET_TIMING_CTRL_REG_LED_NUM, priv->max_addr);
+	writel(control, priv->base + LEDC_RESET_TIMING_CTRL_REG);
+}
+
+static int sun50i_a100_ledc_resume(struct device *dev)
+{
+	struct sun50i_a100_ledc *priv = dev_get_drvdata(dev);
+	int ret;
+
+	ret = reset_control_deassert(priv->reset);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(priv->bus_clk);
+	if (ret)
+		goto err_assert_reset;
+
+	ret = clk_prepare_enable(priv->mod_clk);
+	if (ret)
+		goto err_disable_bus_clk;
+
+	sun50i_a100_ledc_set_format(priv);
+	sun50i_a100_ledc_set_timing(priv);
+
+	writel(LEDC_INT_CTRL_REG_GLOBAL_INT_EN | LEDC_INT_CTRL_REG_TRANS_FINISH_INT_EN,
+	       priv->base + LEDC_INT_CTRL_REG);
+
+	return 0;
+
+err_disable_bus_clk:
+	clk_disable_unprepare(priv->bus_clk);
+err_assert_reset:
+	reset_control_assert(priv->reset);
+
+	return ret;
+}
+
+static int sun50i_a100_ledc_suspend(struct device *dev)
+{
+	struct sun50i_a100_ledc *priv = dev_get_drvdata(dev);
+
+	/* Wait for all transfers to complete. */
+	for (;;) {
+		unsigned long flags;
+		bool xfer_active;
+
+		spin_lock_irqsave(&priv->lock, flags);
+		xfer_active = priv->xfer_active;
+		spin_unlock_irqrestore(&priv->lock, flags);
+		if (!xfer_active)
+			break;
+
+		msleep(1);
+	}
+
+	clk_disable_unprepare(priv->mod_clk);
+	clk_disable_unprepare(priv->bus_clk);
+	reset_control_assert(priv->reset);
+
+	return 0;
+}
+
+static void sun50i_a100_ledc_dma_cleanup(void *data)
+{
+	struct sun50i_a100_ledc *priv = data;
+
+	dma_release_channel(priv->dma_chan);
+}
+
+static int sun50i_a100_ledc_probe(struct platform_device *pdev)
+{
+	const struct device_node *np = pdev->dev.of_node;
+	struct dma_slave_config dma_cfg = {};
+	struct led_init_data init_data = {};
+	struct sun50i_a100_ledc_led *led;
+	struct device *dev = &pdev->dev;
+	struct sun50i_a100_ledc *priv;
+	struct device_node *child;
+	struct resource *mem;
+	u32 max_addr = 0;
+	u32 num_leds = 0;
+	int irq, ret;
+
+	/*
+	 * The maximum LED address must be known in sun50i_a100_ledc_resume() before
+	 * class device registration, so parse and validate the subnodes up front.
+	 */
+	for_each_available_child_of_node(np, child) {
+		u32 addr, color;
+
+		ret = of_property_read_u32(child, "reg", &addr);
+		if (ret || addr >= LEDC_MAX_LEDS) {
+			of_node_put(child);
+			return dev_err_probe(dev, -EINVAL, "'reg' must be between 0 and %d\n",
+					     LEDC_MAX_LEDS - 1);
+		}
+
+		ret = of_property_read_u32(child, "color", &color);
+		if (ret || color != LED_COLOR_ID_RGB) {
+			of_node_put(child);
+			return dev_err_probe(dev, -EINVAL, "'color' must be LED_COLOR_ID_RGB\n");
+		}
+
+		max_addr = max(max_addr, addr);
+		num_leds++;
+	}
+
+	if (!num_leds)
+		return -ENODEV;
+
+	priv = devm_kzalloc(dev, struct_size(priv, leds, num_leds), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = dev;
+	priv->max_addr = max_addr;
+	priv->num_leds = num_leds;
+	spin_lock_init(&priv->lock);
+	dev_set_drvdata(dev, priv);
+
+	ret = sun50i_a100_ledc_parse_format(np, priv);
+	if (ret)
+		return ret;
+
+	ret = sun50i_a100_ledc_parse_timing(np, priv);
+	if (ret)
+		return ret;
+
+	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	priv->bus_clk = devm_clk_get(dev, "bus");
+	if (IS_ERR(priv->bus_clk))
+		return PTR_ERR(priv->bus_clk);
+
+	priv->mod_clk = devm_clk_get(dev, "mod");
+	if (IS_ERR(priv->mod_clk))
+		return PTR_ERR(priv->mod_clk);
+
+	priv->reset = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(priv->reset))
+		return PTR_ERR(priv->reset);
+
+	priv->dma_chan = dma_request_chan(dev, "tx");
+	if (IS_ERR(priv->dma_chan)) {
+		if (PTR_ERR(priv->dma_chan) != -ENODEV)
+			return PTR_ERR(priv->dma_chan);
+
+		priv->dma_chan = NULL;
+
+		priv->buffer = devm_kzalloc(dev, LEDS_TO_BYTES(LEDC_MAX_LEDS), GFP_KERNEL);
+		if (!priv->buffer)
+			return -ENOMEM;
+	} else {
+		ret = devm_add_action_or_reset(dev, sun50i_a100_ledc_dma_cleanup, priv);
+		if (ret)
+			return ret;
+
+		dma_cfg.dst_addr	= mem->start + LEDC_DATA_REG;
+		dma_cfg.dst_addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_cfg.dst_maxburst	= LEDC_FIFO_DEPTH / 2;
+
+		ret = dmaengine_slave_config(priv->dma_chan, &dma_cfg);
+		if (ret)
+			return ret;
+
+		priv->buffer = dmam_alloc_attrs(dmaengine_get_dma_device(priv->dma_chan),
+						LEDS_TO_BYTES(LEDC_MAX_LEDS), &priv->dma_handle,
+						GFP_KERNEL, DMA_ATTR_WRITE_COMBINE);
+		if (!priv->buffer)
+			return -ENOMEM;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_irq(dev, irq, sun50i_a100_ledc_irq, 0, dev_name(dev), priv);
+	if (ret)
+		return ret;
+
+	ret = sun50i_a100_ledc_resume(dev);
+	if (ret)
+		return ret;
+
+	led = priv->leds;
+	for_each_available_child_of_node(np, child) {
+		struct led_classdev *cdev;
+
+		/* The node was already validated above. */
+		of_property_read_u32(child, "reg", &led->addr);
+
+		led->subled_info[0].color_index = LED_COLOR_ID_RED;
+		led->subled_info[0].channel = 0;
+		led->subled_info[1].color_index = LED_COLOR_ID_GREEN;
+		led->subled_info[1].channel = 1;
+		led->subled_info[2].color_index = LED_COLOR_ID_BLUE;
+		led->subled_info[2].channel = 2;
+
+		led->mc_cdev.num_colors = ARRAY_SIZE(led->subled_info);
+		led->mc_cdev.subled_info = led->subled_info;
+
+		cdev = &led->mc_cdev.led_cdev;
+		cdev->max_brightness = U8_MAX;
+		cdev->brightness_set = sun50i_a100_ledc_brightness_set;
+
+		init_data.fwnode = of_fwnode_handle(child);
+
+		ret = led_classdev_multicolor_register_ext(dev, &led->mc_cdev, &init_data);
+		if (ret) {
+			dev_err_probe(dev, ret, "Failed to register multicolor LED %u", led->addr);
+			goto err_put_child;
+		}
+
+		led++;
+	}
+
+	dev_info(dev, "Registered %u LEDs\n", num_leds);
+
+	return 0;
+
+err_put_child:
+	of_node_put(child);
+	while (led-- > priv->leds)
+		led_classdev_multicolor_unregister(&led->mc_cdev);
+	sun50i_a100_ledc_suspend(&pdev->dev);
+
+	return ret;
+}
+
+static void sun50i_a100_ledc_remove(struct platform_device *pdev)
+{
+	struct sun50i_a100_ledc *priv = platform_get_drvdata(pdev);
+
+	for (u32 i = 0; i < priv->num_leds; i++)
+		led_classdev_multicolor_unregister(&priv->leds[i].mc_cdev);
+	sun50i_a100_ledc_suspend(&pdev->dev);
+}
+
+static const struct of_device_id sun50i_a100_ledc_of_match[] = {
+	{ .compatible = "allwinner,sun50i-a100-ledc" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sun50i_a100_ledc_of_match);
+
+static DEFINE_SIMPLE_DEV_PM_OPS(sun50i_a100_ledc_pm,
+				sun50i_a100_ledc_suspend,
+				sun50i_a100_ledc_resume);
+
+static struct platform_driver sun50i_a100_ledc_driver = {
+	.probe		= sun50i_a100_ledc_probe,
+	.remove_new	= sun50i_a100_ledc_remove,
+	.shutdown	= sun50i_a100_ledc_remove,
+	.driver		= {
+		.name		= "sun50i-a100-ledc",
+		.of_match_table	= sun50i_a100_ledc_of_match,
+		.pm		= pm_ptr(&sun50i_a100_ledc_pm),
+	},
+};
+module_platform_driver(sun50i_a100_ledc_driver);
+
+MODULE_AUTHOR("Samuel Holland <samuel@sholland.org>");
+MODULE_DESCRIPTION("Allwinner A100 LED controller driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 75469bb0537ad2ab0fc1fb6e534a79cfc03f3b3f Mon Sep 17 00:00:00 2001
From: Dang Huynh <danct12@riseup.net>
Date: Fri, 3 Nov 2023 18:42:03 +0700
Subject: [PATCH 1211/4076] leds: aw2013: Select missing dependency REGMAP_I2C

The AW2013 driver uses devm_regmap_init_i2c, so REGMAP_I2C needs to
be selected.

Otherwise build process may fail with:
  ld: drivers/leds/leds-aw2013.o: in function `aw2013_probe':
    leds-aw2013.c:345: undefined reference to `__devm_regmap_init_i2c'

Signed-off-by: Dang Huynh <danct12@riseup.net>
Acked-by: Nikita Travkin <nikita@trvn.ru>
Fixes: 59ea3c9faf32 ("leds: add aw2013 driver")
Link: https://lore.kernel.org/r/20231103114203.1108922-1-danct12@riseup.net
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 6496ef525579a..e7697a8881599 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -110,6 +110,7 @@ config LEDS_AW200XX
 config LEDS_AW2013
 	tristate "LED support for Awinic AW2013"
 	depends on LEDS_CLASS && I2C && OF
+	select REGMAP_I2C
 	help
 	  This option enables support for the AW2013 3-channel
 	  LED driver.
-- 
GitLab


From 9bbd6b7209cf1e26390975b7617a29901c8990a1 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 3 Nov 2023 21:53:07 +0200
Subject: [PATCH 1212/4076] leds: trigger: gpio: Replace custom code for
 gpiod_get_optional()

gpiod_get_optional() and currently used fwnode_gpiod_get_index()
are both wrappers against the same engine internally. Since we
have a pointer to struct device there is no reason to use fwnode
type of GPIO call. So, replace the current fwnode call by respective
gpiod ones.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231103195310.948327-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-gpio.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 9b7fe5dd52088..d91ae7fde3cf0 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -89,10 +89,7 @@ static int gpio_trig_activate(struct led_classdev *led)
 	 * The generic property "trigger-sources" is followed,
 	 * and we hope that this is a GPIO.
 	 */
-	gpio_data->gpiod = fwnode_gpiod_get_index(dev->fwnode,
-						  "trigger-sources",
-						  0, GPIOD_IN,
-						  "led-trigger");
+	gpio_data->gpiod = gpiod_get_optional(dev, "trigger-sources", GPIOD_IN);
 	if (IS_ERR(gpio_data->gpiod)) {
 		ret = PTR_ERR(gpio_data->gpiod);
 		kfree(gpio_data);
@@ -104,6 +101,8 @@ static int gpio_trig_activate(struct led_classdev *led)
 		return -EINVAL;
 	}
 
+	gpiod_set_consumer_name(gpio_data->gpiod, "led-trigger");
+
 	gpio_data->led = led;
 	led_set_trigger_data(led, gpio_data);
 
-- 
GitLab


From 7d6766f5377686b871ab52c564327718ece233ad Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 3 Nov 2023 21:53:08 +0200
Subject: [PATCH 1213/4076] leds: trigger: gpio: Convert to use kstrtox()

sscanf() is a heavy one and moreover requires additional boundary checks.
Convert driver to use kstrtou8() in gpio_trig_inverted_store().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231103195310.948327-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-gpio.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index d91ae7fde3cf0..8a30f92281869 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -53,14 +53,12 @@ static ssize_t gpio_trig_brightness_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
 	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
-	unsigned desired_brightness;
+	u8 desired_brightness;
 	int ret;
 
-	ret = sscanf(buf, "%u", &desired_brightness);
-	if (ret < 1 || desired_brightness > 255) {
-		dev_err(dev, "invalid value\n");
-		return -EINVAL;
-	}
+	ret = kstrtou8(buf, 10, &desired_brightness);
+	if (ret)
+		return ret;
 
 	gpio_data->desired_brightness = desired_brightness;
 
-- 
GitLab


From 7b9c5500f42e92992fe7b012974e0dddb673b1f5 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 3 Nov 2023 21:53:09 +0200
Subject: [PATCH 1214/4076] leds: trigger: gpio: Use sysfs_emit() to instead of
 s*printf()

Follow the advice of the Documentation/filesystems/sysfs.rst and show()
should only use sysfs_emit() or sysfs_emit_at() when formatting the
value to be returned to user space.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231103195310.948327-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-gpio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 8a30f92281869..8824be19881f1 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -46,7 +46,7 @@ static ssize_t gpio_trig_brightness_show(struct device *dev,
 {
 	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
-	return sprintf(buf, "%u\n", gpio_data->desired_brightness);
+	return sysfs_emit(buf, "%u\n", gpio_data->desired_brightness);
 }
 
 static ssize_t gpio_trig_brightness_store(struct device *dev,
-- 
GitLab


From 804073f542077a8de17494fb3577a49513788a71 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 3 Nov 2023 21:53:10 +0200
Subject: [PATCH 1215/4076] leds: trigger: gpio: Convert to DEVICE_ATTR_RW()

Instead of custom wrapper, use DEVICE_ATTR_RW() directly.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231103195310.948327-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-gpio.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 8824be19881f1..7f6a2352b0acd 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -41,7 +41,7 @@ static irqreturn_t gpio_trig_irq(int irq, void *_led)
 	return IRQ_HANDLED;
 }
 
-static ssize_t gpio_trig_brightness_show(struct device *dev,
+static ssize_t desired_brightness_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
@@ -49,7 +49,7 @@ static ssize_t gpio_trig_brightness_show(struct device *dev,
 	return sysfs_emit(buf, "%u\n", gpio_data->desired_brightness);
 }
 
-static ssize_t gpio_trig_brightness_store(struct device *dev,
+static ssize_t desired_brightness_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
 	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
@@ -64,8 +64,7 @@ static ssize_t gpio_trig_brightness_store(struct device *dev,
 
 	return n;
 }
-static DEVICE_ATTR(desired_brightness, 0644, gpio_trig_brightness_show,
-		gpio_trig_brightness_store);
+static DEVICE_ATTR_RW(desired_brightness);
 
 static struct attribute *gpio_trig_attrs[] = {
 	&dev_attr_desired_brightness.attr,
-- 
GitLab


From 130199ec02b2cf16aed5ab0d2553da60df2c794a Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Thu, 16 Nov 2023 16:41:20 -0600
Subject: [PATCH 1216/4076] leds: tca6507: Use devm_gpiochip_add_data() to
 simplify remove path

Use devm version of gpiochip add function to handle removal for us.

Signed-off-by: Andrew Davis <afd@ti.com>
Link: https://lore.kernel.org/r/20231116224121.302150-1-afd@ti.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-tca6507.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index e190746140959..9a6af6d8b5b5d 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -638,19 +638,13 @@ static int tca6507_probe_gpios(struct device *dev,
 	tca->gpio.direction_output = tca6507_gpio_direction_output;
 	tca->gpio.set = tca6507_gpio_set_value;
 	tca->gpio.parent = dev;
-	err = gpiochip_add_data(&tca->gpio, tca);
+	err = devm_gpiochip_add_data(dev, &tca->gpio, tca);
 	if (err) {
 		tca->gpio.ngpio = 0;
 		return err;
 	}
 	return 0;
 }
-
-static void tca6507_remove_gpio(struct tca6507_chip *tca)
-{
-	if (tca->gpio.ngpio)
-		gpiochip_remove(&tca->gpio);
-}
 #else /* CONFIG_GPIOLIB */
 static int tca6507_probe_gpios(struct device *dev,
 			       struct tca6507_chip *tca,
@@ -658,9 +652,6 @@ static int tca6507_probe_gpios(struct device *dev,
 {
 	return 0;
 }
-static void tca6507_remove_gpio(struct tca6507_chip *tca)
-{
-}
 #endif /* CONFIG_GPIOLIB */
 
 static struct tca6507_platform_data *
@@ -793,7 +784,6 @@ static void tca6507_remove(struct i2c_client *client)
 		if (tca_leds[i].led_cdev.name)
 			led_classdev_unregister(&tca_leds[i].led_cdev);
 	}
-	tca6507_remove_gpio(tca);
 	cancel_work_sync(&tca->work);
 }
 
-- 
GitLab


From 1b5c2fa7081cca586237b97379f478460ec8d702 Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Thu, 16 Nov 2023 16:41:21 -0600
Subject: [PATCH 1217/4076] leds: tca6507: Use devm_led_classdev_register() to
 simplify remove path

Use devm version of LED classdev register add function to handle removal.

Signed-off-by: Andrew Davis <afd@ti.com>
Link: https://lore.kernel.org/r/20231116224121.302150-2-afd@ti.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-tca6507.c | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index 9a6af6d8b5b5d..4f22f42249467 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -753,37 +753,25 @@ static int tca6507_probe(struct i2c_client *client)
 			l->led_cdev.brightness_set = tca6507_brightness_set;
 			l->led_cdev.blink_set = tca6507_blink_set;
 			l->bank = -1;
-			err = led_classdev_register(dev, &l->led_cdev);
+			err = devm_led_classdev_register(dev, &l->led_cdev);
 			if (err < 0)
-				goto exit;
+				return err;
 		}
 	}
 	err = tca6507_probe_gpios(dev, tca, pdata);
 	if (err)
-		goto exit;
+		return err;
 	/* set all registers to known state - zero */
 	tca->reg_set = 0x7f;
 	schedule_work(&tca->work);
 
 	return 0;
-exit:
-	while (i--) {
-		if (tca->leds[i].led_cdev.name)
-			led_classdev_unregister(&tca->leds[i].led_cdev);
-	}
-	return err;
 }
 
 static void tca6507_remove(struct i2c_client *client)
 {
-	int i;
 	struct tca6507_chip *tca = i2c_get_clientdata(client);
-	struct tca6507_led *tca_leds = tca->leds;
 
-	for (i = 0; i < NUM_LEDS; i++) {
-		if (tca_leds[i].led_cdev.name)
-			led_classdev_unregister(&tca_leds[i].led_cdev);
-	}
 	cancel_work_sync(&tca->work);
 }
 
-- 
GitLab


From 736214b4b02adf8734206599e36e2081d47554a2 Mon Sep 17 00:00:00 2001
From: Patrick Rudolph <patrick.rudolph@9elements.com>
Date: Thu, 23 Nov 2023 13:28:02 +0000
Subject: [PATCH 1218/4076] leds: max5970: Add support for max5970

The MAX5970 is hot swap controller and has 4 indication LED.

Signed-off-by: Patrick Rudolph <patrick.rudolph@9elements.com>
Signed-off-by: Naresh Solanki <Naresh.Solanki@9elements.com>
Link: https://lore.kernel.org/r/20231123132803.1107174-1-naresh.solanki@9elements.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/Kconfig        |  11 ++++
 drivers/leds/Makefile       |   1 +
 drivers/leds/leds-max5970.c | 109 ++++++++++++++++++++++++++++++++++++
 3 files changed, 121 insertions(+)
 create mode 100644 drivers/leds/leds-max5970.c

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index e7697a8881599..bfa11e7b157f2 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -648,6 +648,17 @@ config LEDS_ADP5520
 	  To compile this driver as a module, choose M here: the module will
 	  be called leds-adp5520.
 
+config LEDS_MAX5970
+	tristate "LED Support for Maxim 5970"
+	depends on LEDS_CLASS
+	depends on MFD_MAX5970
+	help
+	  This option enables support for the Maxim MAX5970 & MAX5978 smart
+	  switch indication LEDs via the I2C bus.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called leds-max5970.
+
 config LEDS_MC13783
 	tristate "LED Support for MC13XXX PMIC"
 	depends on LEDS_CLASS
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index b82a538e3f8c0..ce07dc295ff00 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_LEDS_LP8501)		+= leds-lp8501.o
 obj-$(CONFIG_LEDS_LP8788)		+= leds-lp8788.o
 obj-$(CONFIG_LEDS_LP8860)		+= leds-lp8860.o
 obj-$(CONFIG_LEDS_LT3593)		+= leds-lt3593.o
+obj-$(CONFIG_LEDS_MAX5970)		+= leds-max5970.o
 obj-$(CONFIG_LEDS_MAX77650)		+= leds-max77650.o
 obj-$(CONFIG_LEDS_MAX8997)		+= leds-max8997.o
 obj-$(CONFIG_LEDS_MC13783)		+= leds-mc13783.o
diff --git a/drivers/leds/leds-max5970.c b/drivers/leds/leds-max5970.c
new file mode 100644
index 0000000000000..456a16a47450e
--- /dev/null
+++ b/drivers/leds/leds-max5970.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Device driver for leds in MAX5970 and MAX5978 IC
+ *
+ * Copyright (c) 2022 9elements GmbH
+ *
+ * Author: Patrick Rudolph <patrick.rudolph@9elements.com>
+ */
+
+#include <linux/leds.h>
+#include <linux/mfd/max5970.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#define ldev_to_maxled(c)       container_of(c, struct max5970_led, cdev)
+
+struct max5970_led {
+	struct device *dev;
+	struct regmap *regmap;
+	struct led_classdev cdev;
+	unsigned int index;
+};
+
+static int max5970_led_set_brightness(struct led_classdev *cdev,
+				      enum led_brightness brightness)
+{
+	struct max5970_led *ddata = ldev_to_maxled(cdev);
+	int ret, val;
+
+	/* Set/clear corresponding bit for given led index */
+	val = !brightness ? BIT(ddata->index) : 0;
+
+	ret = regmap_update_bits(ddata->regmap, MAX5970_REG_LED_FLASH, BIT(ddata->index), val);
+	if (ret < 0)
+		dev_err(cdev->dev, "failed to set brightness %d", ret);
+
+	return ret;
+}
+
+static int max5970_led_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev_of_node(dev->parent);
+	struct regmap *regmap;
+	struct device_node *led_node, *child;
+	struct max5970_led *ddata;
+	int ret = -ENODEV, num_leds = 0;
+
+	regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!regmap)
+		return -ENODEV;
+
+	led_node = of_get_child_by_name(np, "leds");
+	if (!led_node)
+		return -ENODEV;
+
+	for_each_available_child_of_node(led_node, child) {
+		u32 reg;
+
+		if (of_property_read_u32(child, "reg", &reg))
+			continue;
+
+		if (reg >= MAX5970_NUM_LEDS) {
+			dev_err(dev, "invalid LED (%u >= %d)\n", reg, MAX5970_NUM_LEDS);
+			continue;
+		}
+
+		ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
+		if (!ddata) {
+			of_node_put(child);
+			return -ENOMEM;
+		}
+
+		ddata->index = reg;
+		ddata->regmap = regmap;
+		ddata->dev = dev;
+
+		if (of_property_read_string(child, "label", &ddata->cdev.name))
+			ddata->cdev.name = child->name;
+
+		ddata->cdev.max_brightness = 1;
+		ddata->cdev.brightness_set_blocking = max5970_led_set_brightness;
+		ddata->cdev.default_trigger = "none";
+
+		ret = devm_led_classdev_register(dev, &ddata->cdev);
+		if (ret < 0) {
+			of_node_put(child);
+			dev_err(dev, "Failed to initialize LED %u\n", reg);
+			return ret;
+		}
+		num_leds++;
+	}
+
+	return ret;
+}
+
+static struct platform_driver max5970_led_driver = {
+	.driver = {
+		.name = "max5970-led",
+	},
+	.probe = max5970_led_probe,
+};
+
+module_platform_driver(max5970_led_driver);
+MODULE_AUTHOR("Patrick Rudolph <patrick.rudolph@9elements.com>");
+MODULE_AUTHOR("Naresh Solanki <Naresh.Solanki@9elements.com>");
+MODULE_DESCRIPTION("MAX5970_hot-swap controller LED driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 25054b232681c286fca9c678854f56494d1352cc Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Mon, 27 Nov 2023 09:16:21 +0100
Subject: [PATCH 1219/4076] leds: ledtrig-tty: Free allocated ttyname buffer on
 deactivate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ttyname buffer for the ledtrig_tty_data struct is allocated in the
sysfs ttyname_store() function. This buffer must be released on trigger
deactivation. This was missing and is thus a memory leak.

While we are at it, the TTY handler in the ledtrig_tty_data struct should
also be returned in case of the trigger deactivation call.

Cc: stable@vger.kernel.org
Fixes: fd4a641ac88f ("leds: trigger: implement a tty trigger")
Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231127081621.774866-1-fe@dev.tdt.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-tty.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c
index 8ae0d2d284aff..3e69a7bde9284 100644
--- a/drivers/leds/trigger/ledtrig-tty.c
+++ b/drivers/leds/trigger/ledtrig-tty.c
@@ -168,6 +168,10 @@ static void ledtrig_tty_deactivate(struct led_classdev *led_cdev)
 
 	cancel_delayed_work_sync(&trigger_data->dwork);
 
+	kfree(trigger_data->ttyname);
+	tty_kref_put(trigger_data->tty);
+	trigger_data->tty = NULL;
+
 	kfree(trigger_data);
 }
 
-- 
GitLab


From 9e1815f8c77155aa0818d65b1903a5a39af0ab75 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 26 Nov 2023 10:52:32 +0100
Subject: [PATCH 1220/4076] leds: qcom-lpg: Use devm_pwmchip_add() simplifying
 driver removal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With pwmchip_remove() being automatically called after switching to
devm_pwmchip_add() the remove function can be dropped completely. Yay!
With lpg_remove() gone there is no user of the platform device's drvdata
left, so platform_set_drvdata() can be dropped from .probe(), too.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231126095230.683204-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/rgb/leds-qcom-lpg.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c
index 68d82a682bf67..f5805fd0eb218 100644
--- a/drivers/leds/rgb/leds-qcom-lpg.c
+++ b/drivers/leds/rgb/leds-qcom-lpg.c
@@ -1095,7 +1095,7 @@ static int lpg_add_pwm(struct lpg *lpg)
 	lpg->pwm.npwm = lpg->num_channels;
 	lpg->pwm.ops = &lpg_pwm_ops;
 
-	ret = pwmchip_add(&lpg->pwm);
+	ret = devm_pwmchip_add(lpg->dev, &lpg->pwm);
 	if (ret)
 		dev_err(lpg->dev, "failed to add PWM chip: ret %d\n", ret);
 
@@ -1324,8 +1324,6 @@ static int lpg_probe(struct platform_device *pdev)
 	if (!lpg->data)
 		return -EINVAL;
 
-	platform_set_drvdata(pdev, lpg);
-
 	lpg->dev = &pdev->dev;
 	mutex_init(&lpg->lock);
 
@@ -1363,13 +1361,6 @@ static int lpg_probe(struct platform_device *pdev)
 	return lpg_add_pwm(lpg);
 }
 
-static void lpg_remove(struct platform_device *pdev)
-{
-	struct lpg *lpg = platform_get_drvdata(pdev);
-
-	pwmchip_remove(&lpg->pwm);
-}
-
 static const struct lpg_data pm8916_pwm_data = {
 	.num_channels = 1,
 	.channels = (const struct lpg_channel_data[]) {
@@ -1529,7 +1520,6 @@ MODULE_DEVICE_TABLE(of, lpg_of_table);
 
 static struct platform_driver lpg_driver = {
 	.probe = lpg_probe,
-	.remove_new = lpg_remove,
 	.driver = {
 		.name = "qcom-spmi-lpg",
 		.of_match_table = lpg_of_table,
-- 
GitLab


From 793bf5510d5e30dff2ce1d6e446b385cd494d5af Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 26 Nov 2023 10:52:33 +0100
Subject: [PATCH 1221/4076] leds: qcom-lpg: Consistenly use dev_err_probe() in
 .probe()'s error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

One error path already used dev_err_probe(). Adapt the other error paths
that emit an error message to also use this function for consistency and
slightly simplified code.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231126095230.683204-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/rgb/leds-qcom-lpg.c | 40 ++++++++++++++------------------
 1 file changed, 17 insertions(+), 23 deletions(-)

diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c
index f5805fd0eb218..54c90ee43ef87 100644
--- a/drivers/leds/rgb/leds-qcom-lpg.c
+++ b/drivers/leds/rgb/leds-qcom-lpg.c
@@ -552,9 +552,9 @@ static int lpg_parse_dtest(struct lpg *lpg)
 		ret = count;
 		goto err_malformed;
 	} else if (count != lpg->data->num_channels * 2) {
-		dev_err(lpg->dev, "qcom,dtest needs to be %d items\n",
-			lpg->data->num_channels * 2);
-		return -EINVAL;
+		return dev_err_probe(lpg->dev, -EINVAL,
+				     "qcom,dtest needs to be %d items\n",
+				     lpg->data->num_channels * 2);
 	}
 
 	for (i = 0; i < lpg->data->num_channels; i++) {
@@ -574,8 +574,7 @@ static int lpg_parse_dtest(struct lpg *lpg)
 	return 0;
 
 err_malformed:
-	dev_err(lpg->dev, "malformed qcom,dtest\n");
-	return ret;
+	return dev_err_probe(lpg->dev, ret, "malformed qcom,dtest\n");
 }
 
 static void lpg_apply_dtest(struct lpg_channel *chan)
@@ -1097,7 +1096,7 @@ static int lpg_add_pwm(struct lpg *lpg)
 
 	ret = devm_pwmchip_add(lpg->dev, &lpg->pwm);
 	if (ret)
-		dev_err(lpg->dev, "failed to add PWM chip: ret %d\n", ret);
+		dev_err_probe(lpg->dev, ret, "failed to add PWM chip\n");
 
 	return ret;
 }
@@ -1111,19 +1110,16 @@ static int lpg_parse_channel(struct lpg *lpg, struct device_node *np,
 	int ret;
 
 	ret = of_property_read_u32(np, "reg", &reg);
-	if (ret || !reg || reg > lpg->num_channels) {
-		dev_err(lpg->dev, "invalid \"reg\" of %pOFn\n", np);
-		return -EINVAL;
-	}
+	if (ret || !reg || reg > lpg->num_channels)
+		return dev_err_probe(lpg->dev, -EINVAL, "invalid \"reg\" of %pOFn\n", np);
 
 	chan = &lpg->channels[reg - 1];
 	chan->in_use = true;
 
 	ret = of_property_read_u32(np, "color", &color);
-	if (ret < 0 && ret != -EINVAL) {
-		dev_err(lpg->dev, "failed to parse \"color\" of %pOF\n", np);
-		return ret;
-	}
+	if (ret < 0 && ret != -EINVAL)
+		return dev_err_probe(lpg->dev, ret,
+				     "failed to parse \"color\" of %pOF\n", np);
 
 	chan->color = color;
 
@@ -1146,10 +1142,9 @@ static int lpg_add_led(struct lpg *lpg, struct device_node *np)
 	int i;
 
 	ret = of_property_read_u32(np, "color", &color);
-	if (ret < 0 && ret != -EINVAL) {
-		dev_err(lpg->dev, "failed to parse \"color\" of %pOF\n", np);
-		return ret;
-	}
+	if (ret < 0 && ret != -EINVAL)
+		return dev_err_probe(lpg->dev, ret,
+			      "failed to parse \"color\" of %pOF\n", np);
 
 	if (color == LED_COLOR_ID_RGB)
 		num_channels = of_get_available_child_count(np);
@@ -1226,7 +1221,7 @@ static int lpg_add_led(struct lpg *lpg, struct device_node *np)
 	else
 		ret = devm_led_classdev_register_ext(lpg->dev, &led->cdev, &init_data);
 	if (ret)
-		dev_err(lpg->dev, "unable to register %s\n", cdev->name);
+		dev_err_probe(lpg->dev, ret, "unable to register %s\n", cdev->name);
 
 	return ret;
 }
@@ -1272,10 +1267,9 @@ static int lpg_init_triled(struct lpg *lpg)
 
 	if (lpg->triled_has_src_sel) {
 		ret = of_property_read_u32(np, "qcom,power-source", &lpg->triled_src);
-		if (ret || lpg->triled_src == 2 || lpg->triled_src > 3) {
-			dev_err(lpg->dev, "invalid power source\n");
-			return -EINVAL;
-		}
+		if (ret || lpg->triled_src == 2 || lpg->triled_src > 3)
+			return dev_err_probe(lpg->dev, -EINVAL,
+					     "invalid power source\n");
 	}
 
 	/* Disable automatic trickle charge LED */
-- 
GitLab


From 4ff4379ce6eefe81695bcc2e021ce1dac3d707d2 Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Mon, 27 Nov 2023 12:03:08 +0100
Subject: [PATCH 1222/4076] tty: add new helper function tty_get_tiocm

There is no in-kernel function to get the status register of a tty device
like the TIOCMGET ioctl returns to userspace. Create a new function,
tty_get_tiocm(), to obtain the status register that other portions of the
kernel can call if they need this information, and move the existing
internal tty_tiocmget() function to use this interface.

Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231127110311.3583957-2-fe@dev.tdt.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/tty/tty_io.c | 28 ++++++++++++++++++++++------
 include/linux/tty.h  |  1 +
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 06414e43e0b53..e2e93404133ef 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2498,6 +2498,24 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 	return retval;
 }
 
+/**
+ * tty_get_tiocm - get tiocm status register
+ * @tty: tty device
+ *
+ * Obtain the modem status bits from the tty driver if the feature
+ * is supported.
+ */
+int tty_get_tiocm(struct tty_struct *tty)
+{
+	int retval = -ENOTTY;
+
+	if (tty->ops->tiocmget)
+		retval = tty->ops->tiocmget(tty);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(tty_get_tiocm);
+
 /**
  * tty_tiocmget - get modem status
  * @tty: tty device
@@ -2510,14 +2528,12 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
  */
 static int tty_tiocmget(struct tty_struct *tty, int __user *p)
 {
-	int retval = -ENOTTY;
+	int retval;
 
-	if (tty->ops->tiocmget) {
-		retval = tty->ops->tiocmget(tty);
+	retval = tty_get_tiocm(tty);
+	if (retval >= 0)
+		retval = put_user(retval, p);
 
-		if (retval >= 0)
-			retval = put_user(retval, p);
-	}
 	return retval;
 }
 
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 4b6340ac2af28..d219a11e3fe0f 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -419,6 +419,7 @@ bool tty_unthrottle_safe(struct tty_struct *tty);
 int tty_do_resize(struct tty_struct *tty, struct winsize *ws);
 int tty_get_icount(struct tty_struct *tty,
 		struct serial_icounter_struct *icount);
+int tty_get_tiocm(struct tty_struct *tty);
 int is_current_pgrp_orphaned(void);
 void tty_hangup(struct tty_struct *tty);
 void tty_vhangup(struct tty_struct *tty);
-- 
GitLab


From 76675f69bed5f1e8ae44ba72904ff7f97aa95c0a Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Mon, 27 Nov 2023 12:03:09 +0100
Subject: [PATCH 1223/4076] leds: ledtrig-tty: Replace mutex with completion

With this commit, the mutex handling is replaced by the completion
handling. When handling mutex, it must always be ensured that the held
mutex is also released again. This is more error-prone should the number
of code paths increase.

This is a preparatory commit to make the trigger more configurable via
additional sysfs parameters. With this change, the worker always runs and
is no longer stopped if no ttyname is set.

Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231127110311.3583957-3-fe@dev.tdt.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-tty.c | 59 +++++++++++++++---------------
 1 file changed, 30 insertions(+), 29 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c
index 3e69a7bde9284..b16bd9cb97134 100644
--- a/drivers/leds/trigger/ledtrig-tty.c
+++ b/drivers/leds/trigger/ledtrig-tty.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/leds.h>
 #include <linux/module.h>
@@ -12,15 +13,23 @@
 struct ledtrig_tty_data {
 	struct led_classdev *led_cdev;
 	struct delayed_work dwork;
-	struct mutex mutex;
+	struct completion sysfs;
 	const char *ttyname;
 	struct tty_struct *tty;
 	int rx, tx;
 };
 
-static void ledtrig_tty_restart(struct ledtrig_tty_data *trigger_data)
+static int ledtrig_tty_wait_for_completion(struct device *dev)
 {
-	schedule_delayed_work(&trigger_data->dwork, 0);
+	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
+	int ret;
+
+	ret = wait_for_completion_timeout(&trigger_data->sysfs,
+					  msecs_to_jiffies(LEDTRIG_TTY_INTERVAL * 20));
+	if (ret == 0)
+		return -ETIMEDOUT;
+
+	return ret;
 }
 
 static ssize_t ttyname_show(struct device *dev,
@@ -28,14 +37,16 @@ static ssize_t ttyname_show(struct device *dev,
 {
 	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
 	ssize_t len = 0;
+	int completion;
 
-	mutex_lock(&trigger_data->mutex);
+	reinit_completion(&trigger_data->sysfs);
+	completion = ledtrig_tty_wait_for_completion(dev);
+	if (completion < 0)
+		return completion;
 
 	if (trigger_data->ttyname)
 		len = sprintf(buf, "%s\n", trigger_data->ttyname);
 
-	mutex_unlock(&trigger_data->mutex);
-
 	return len;
 }
 
@@ -46,7 +57,7 @@ static ssize_t ttyname_store(struct device *dev,
 	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
 	char *ttyname;
 	ssize_t ret = size;
-	bool running;
+	int completion;
 
 	if (size > 0 && buf[size - 1] == '\n')
 		size -= 1;
@@ -59,9 +70,10 @@ static ssize_t ttyname_store(struct device *dev,
 		ttyname = NULL;
 	}
 
-	mutex_lock(&trigger_data->mutex);
-
-	running = trigger_data->ttyname != NULL;
+	reinit_completion(&trigger_data->sysfs);
+	completion = ledtrig_tty_wait_for_completion(dev);
+	if (completion < 0)
+		return completion;
 
 	kfree(trigger_data->ttyname);
 	tty_kref_put(trigger_data->tty);
@@ -69,11 +81,6 @@ static ssize_t ttyname_store(struct device *dev,
 
 	trigger_data->ttyname = ttyname;
 
-	mutex_unlock(&trigger_data->mutex);
-
-	if (ttyname && !running)
-		ledtrig_tty_restart(trigger_data);
-
 	return ret;
 }
 static DEVICE_ATTR_RW(ttyname);
@@ -85,13 +92,8 @@ static void ledtrig_tty_work(struct work_struct *work)
 	struct serial_icounter_struct icount;
 	int ret;
 
-	mutex_lock(&trigger_data->mutex);
-
-	if (!trigger_data->ttyname) {
-		/* exit without rescheduling */
-		mutex_unlock(&trigger_data->mutex);
-		return;
-	}
+	if (!trigger_data->ttyname)
+		goto out;
 
 	/* try to get the tty corresponding to $ttyname */
 	if (!trigger_data->tty) {
@@ -116,11 +118,8 @@ static void ledtrig_tty_work(struct work_struct *work)
 	}
 
 	ret = tty_get_icount(trigger_data->tty, &icount);
-	if (ret) {
-		dev_info(trigger_data->tty->dev, "Failed to get icount, stopped polling\n");
-		mutex_unlock(&trigger_data->mutex);
-		return;
-	}
+	if (ret)
+		goto out;
 
 	if (icount.rx != trigger_data->rx ||
 	    icount.tx != trigger_data->tx) {
@@ -134,7 +133,7 @@ static void ledtrig_tty_work(struct work_struct *work)
 	}
 
 out:
-	mutex_unlock(&trigger_data->mutex);
+	complete_all(&trigger_data->sysfs);
 	schedule_delayed_work(&trigger_data->dwork,
 			      msecs_to_jiffies(LEDTRIG_TTY_INTERVAL * 2));
 }
@@ -157,7 +156,9 @@ static int ledtrig_tty_activate(struct led_classdev *led_cdev)
 
 	INIT_DELAYED_WORK(&trigger_data->dwork, ledtrig_tty_work);
 	trigger_data->led_cdev = led_cdev;
-	mutex_init(&trigger_data->mutex);
+	init_completion(&trigger_data->sysfs);
+
+	schedule_delayed_work(&trigger_data->dwork, 0);
 
 	return 0;
 }
-- 
GitLab


From 5b755ca677dba117063c6fd8d7ce21b67376deba Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Mon, 27 Nov 2023 12:03:10 +0100
Subject: [PATCH 1224/4076] leds: ledtrig-tty: Make rx tx activitate
 configurable

Until now, the LED blinks when data is sent via the tty (rx/tx).
This is not configurable.

This change adds the possibility to make the indication for the direction
of the transmitted data independently controllable via the new rx and
tx sysfs entries.

- rx:
  Signal reception (rx) of data on the named tty device.
  If set to 0, the LED will not blink on reception.
  If set to 1 (default), the LED will blink on reception.

- tx:
  Signal transmission (tx) of data on the named tty device.
  If set to 0, the LED will not blink on transmission.
  If set to 1 (default), the LED will blink on transmission.

This new sysfs entry are on by default. Thus the trigger behaves as
before this change.

Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231127110311.3583957-4-fe@dev.tdt.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../ABI/testing/sysfs-class-led-trigger-tty   |  16 +++
 drivers/leds/trigger/ledtrig-tty.c            | 114 ++++++++++++++++--
 2 files changed, 119 insertions(+), 11 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-tty b/Documentation/ABI/testing/sysfs-class-led-trigger-tty
index 2bf6b24e781b0..504dece151b88 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-tty
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-tty
@@ -4,3 +4,19 @@ KernelVersion:	5.10
 Contact:	linux-leds@vger.kernel.org
 Description:
 		Specifies the tty device name of the triggering tty
+
+What:		/sys/class/leds/<led>/rx
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		Signal reception (rx) of data on the named tty device.
+		If set to 0, the LED will not blink on reception.
+		If set to 1 (default), the LED will blink on reception.
+
+What:		/sys/class/leds/<led>/tx
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		Signal transmission (tx) of data on the named tty device.
+		If set to 0, the LED will not blink on transmission.
+		If set to 1 (default), the LED will blink on transmission.
diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c
index b16bd9cb97134..4f1cdd0e4e89a 100644
--- a/drivers/leds/trigger/ledtrig-tty.c
+++ b/drivers/leds/trigger/ledtrig-tty.c
@@ -17,6 +17,19 @@ struct ledtrig_tty_data {
 	const char *ttyname;
 	struct tty_struct *tty;
 	int rx, tx;
+	bool mode_rx;
+	bool mode_tx;
+};
+
+/* Indicates which state the LED should now display */
+enum led_trigger_tty_state {
+	TTY_LED_BLINK,
+	TTY_LED_DISABLE,
+};
+
+enum led_trigger_tty_modes {
+	TRIGGER_TTY_RX = 0,
+	TRIGGER_TTY_TX,
 };
 
 static int ledtrig_tty_wait_for_completion(struct device *dev)
@@ -85,11 +98,69 @@ static ssize_t ttyname_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(ttyname);
 
+static ssize_t ledtrig_tty_attr_show(struct device *dev, char *buf,
+				     enum led_trigger_tty_modes attr)
+{
+	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
+	bool state;
+
+	switch (attr) {
+	case TRIGGER_TTY_RX:
+		state = trigger_data->mode_rx;
+		break;
+	case TRIGGER_TTY_TX:
+		state = trigger_data->mode_tx;
+		break;
+	}
+
+	return sysfs_emit(buf, "%u\n", state);
+}
+
+static ssize_t ledtrig_tty_attr_store(struct device *dev, const char *buf,
+				      size_t size, enum led_trigger_tty_modes attr)
+{
+	struct ledtrig_tty_data *trigger_data = led_trigger_get_drvdata(dev);
+	bool state;
+	int ret;
+
+	ret = kstrtobool(buf, &state);
+	if (ret)
+		return ret;
+
+	switch (attr) {
+	case TRIGGER_TTY_RX:
+		trigger_data->mode_rx = state;
+		break;
+	case TRIGGER_TTY_TX:
+		trigger_data->mode_tx = state;
+		break;
+	}
+
+	return size;
+}
+
+#define DEFINE_TTY_TRIGGER(trigger_name, trigger) \
+	static ssize_t trigger_name##_show(struct device *dev, \
+		struct device_attribute *attr, char *buf) \
+	{ \
+		return ledtrig_tty_attr_show(dev, buf, trigger); \
+	} \
+	static ssize_t trigger_name##_store(struct device *dev, \
+		struct device_attribute *attr, const char *buf, size_t size) \
+	{ \
+		return ledtrig_tty_attr_store(dev, buf, size, trigger); \
+	} \
+	static DEVICE_ATTR_RW(trigger_name)
+
+DEFINE_TTY_TRIGGER(rx, TRIGGER_TTY_RX);
+DEFINE_TTY_TRIGGER(tx, TRIGGER_TTY_TX);
+
 static void ledtrig_tty_work(struct work_struct *work)
 {
 	struct ledtrig_tty_data *trigger_data =
 		container_of(work, struct ledtrig_tty_data, dwork.work);
-	struct serial_icounter_struct icount;
+	enum led_trigger_tty_state state = TTY_LED_DISABLE;
+	unsigned long interval = LEDTRIG_TTY_INTERVAL;
 	int ret;
 
 	if (!trigger_data->ttyname)
@@ -117,22 +188,37 @@ static void ledtrig_tty_work(struct work_struct *work)
 		trigger_data->tty = tty;
 	}
 
-	ret = tty_get_icount(trigger_data->tty, &icount);
-	if (ret)
-		goto out;
+	if (trigger_data->mode_rx || trigger_data->mode_tx) {
+		struct serial_icounter_struct icount;
 
-	if (icount.rx != trigger_data->rx ||
-	    icount.tx != trigger_data->tx) {
-		unsigned long interval = LEDTRIG_TTY_INTERVAL;
+		ret = tty_get_icount(trigger_data->tty, &icount);
+		if (ret)
+			goto out;
 
-		led_blink_set_oneshot(trigger_data->led_cdev, &interval,
-				      &interval, 0);
+		if (trigger_data->mode_tx && (icount.tx != trigger_data->tx)) {
+			trigger_data->tx = icount.tx;
+			state = TTY_LED_BLINK;
+		}
 
-		trigger_data->rx = icount.rx;
-		trigger_data->tx = icount.tx;
+		if (trigger_data->mode_rx && (icount.rx != trigger_data->rx)) {
+			trigger_data->rx = icount.rx;
+			state = TTY_LED_BLINK;
+		}
 	}
 
 out:
+	switch (state) {
+	case TTY_LED_BLINK:
+		led_blink_set_oneshot(trigger_data->led_cdev, &interval,
+				&interval, 0);
+		break;
+	case TTY_LED_DISABLE:
+		fallthrough;
+	default:
+		led_set_brightness(trigger_data->led_cdev, LED_OFF);
+		break;
+	}
+
 	complete_all(&trigger_data->sysfs);
 	schedule_delayed_work(&trigger_data->dwork,
 			      msecs_to_jiffies(LEDTRIG_TTY_INTERVAL * 2));
@@ -140,6 +226,8 @@ out:
 
 static struct attribute *ledtrig_tty_attrs[] = {
 	&dev_attr_ttyname.attr,
+	&dev_attr_rx.attr,
+	&dev_attr_tx.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(ledtrig_tty);
@@ -152,6 +240,10 @@ static int ledtrig_tty_activate(struct led_classdev *led_cdev)
 	if (!trigger_data)
 		return -ENOMEM;
 
+	/* Enable default rx/tx mode */
+	trigger_data->mode_rx = true;
+	trigger_data->mode_tx = true;
+
 	led_set_trigger_data(led_cdev, trigger_data);
 
 	INIT_DELAYED_WORK(&trigger_data->dwork, ledtrig_tty_work);
-- 
GitLab


From 6dec659896b4e683beaea223d306e71e174e84cd Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Mon, 27 Nov 2023 12:03:11 +0100
Subject: [PATCH 1225/4076] leds: ledtrig-tty: Add additional line state
 evaluation

The serial tty interface also supports additional input signals, that
can also be evaluated within this trigger. This change is adding the
following additional input sources, which could be controlled
via the '/sys/class/<leds>/' sysfs interface.

Explanation:
DCE = Data Communication Equipment (Modem)
DTE = Data Terminal Equipment (Computer)

- cts:
  DCE is ready to accept data from the DTE (CTS = Clear To Send). If
  the line state is detected, the LED is switched on.
  If set to 0 (default), the LED will not evaluate CTS.
  If set to 1, the LED will evaluate CTS.

- dsr:
  DCE is ready to receive and send data (DSR = Data Set Ready). If the
  line state is detected, the LED is switched on.
  If set to 0 (default), the LED will not evaluate DSR.
  If set to 1, the LED will evaluate DSR.

- dcd:
  DTE is receiving a carrier from the DCE (DCD = Data Carrier Detect).
  If the line state is detected, the LED is switched on.
  If set to 0 (default), the LED will not evaluate DCD.
  If set to 1, the LED will evaluate DCD.

- rng:
  DCE has detected an incoming ring signal on the telephone line
  (RNG = Ring Indicator). If the line state is detected, the LED is
  switched on.
  If set to 0 (default), the LED will not evaluate RNG.
  If set to 1, the LED will evaluate RNG.

Also add an invert flag on LED blink, so that the LED blinks in the
correct order.

* If one off the new enabled input signals are evaluatet as 'enabled',
  and data are transmitted, then the LED should first blink 'off' and
  then 'on' (invert).
* If all the new enabled input signals are evaluatet as 'disabled',
  and data are transmitted, then the LED should first blink 'on' and
  then 'off'.

Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Reviewed-by: Maarten Brock <m.brock@vanmierlo.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231127110311.3583957-5-fe@dev.tdt.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../ABI/testing/sysfs-class-led-trigger-tty   | 40 ++++++++++
 drivers/leds/trigger/ledtrig-tty.c            | 78 ++++++++++++++++++-
 2 files changed, 117 insertions(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-tty b/Documentation/ABI/testing/sysfs-class-led-trigger-tty
index 504dece151b88..30cef9ac0f493 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-tty
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-tty
@@ -20,3 +20,43 @@ Description:
 		Signal transmission (tx) of data on the named tty device.
 		If set to 0, the LED will not blink on transmission.
 		If set to 1 (default), the LED will blink on transmission.
+
+What:		/sys/class/leds/<led>/cts
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		CTS = Clear To Send
+		DCE is ready to accept data from the DTE.
+		If the line state is detected, the LED is switched on.
+		If set to 0 (default), the LED will not evaluate CTS.
+		If set to 1, the LED will evaluate CTS.
+
+What:		/sys/class/leds/<led>/dsr
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		DSR = Data Set Ready
+		DCE is ready to receive and send data.
+		If the line state is detected, the LED is switched on.
+		If set to 0 (default), the LED will not evaluate DSR.
+		If set to 1, the LED will evaluate DSR.
+
+What:		/sys/class/leds/<led>/dcd
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		DCD = Data Carrier Detect
+		DTE is receiving a carrier from the DCE.
+		If the line state is detected, the LED is switched on.
+		If set to 0 (default), the LED will not evaluate CAR (DCD).
+		If set to 1, the LED will evaluate CAR (DCD).
+
+What:		/sys/class/leds/<led>/rng
+Date:		February 2024
+KernelVersion:	6.8
+Description:
+		RNG = Ring Indicator
+		DCE has detected an incoming ring signal on the telephone
+		line. If the line state is detected, the LED is switched on.
+		If set to 0 (default), the LED will not evaluate RNG.
+		If set to 1, the LED will evaluate RNG.
diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c
index 4f1cdd0e4e89a..8cf1485e81658 100644
--- a/drivers/leds/trigger/ledtrig-tty.c
+++ b/drivers/leds/trigger/ledtrig-tty.c
@@ -19,17 +19,26 @@ struct ledtrig_tty_data {
 	int rx, tx;
 	bool mode_rx;
 	bool mode_tx;
+	bool mode_cts;
+	bool mode_dsr;
+	bool mode_dcd;
+	bool mode_rng;
 };
 
 /* Indicates which state the LED should now display */
 enum led_trigger_tty_state {
 	TTY_LED_BLINK,
+	TTY_LED_ENABLE,
 	TTY_LED_DISABLE,
 };
 
 enum led_trigger_tty_modes {
 	TRIGGER_TTY_RX = 0,
 	TRIGGER_TTY_TX,
+	TRIGGER_TTY_CTS,
+	TRIGGER_TTY_DSR,
+	TRIGGER_TTY_DCD,
+	TRIGGER_TTY_RNG,
 };
 
 static int ledtrig_tty_wait_for_completion(struct device *dev)
@@ -111,6 +120,18 @@ static ssize_t ledtrig_tty_attr_show(struct device *dev, char *buf,
 	case TRIGGER_TTY_TX:
 		state = trigger_data->mode_tx;
 		break;
+	case TRIGGER_TTY_CTS:
+		state = trigger_data->mode_cts;
+		break;
+	case TRIGGER_TTY_DSR:
+		state = trigger_data->mode_dsr;
+		break;
+	case TRIGGER_TTY_DCD:
+		state = trigger_data->mode_dcd;
+		break;
+	case TRIGGER_TTY_RNG:
+		state = trigger_data->mode_rng;
+		break;
 	}
 
 	return sysfs_emit(buf, "%u\n", state);
@@ -134,6 +155,18 @@ static ssize_t ledtrig_tty_attr_store(struct device *dev, const char *buf,
 	case TRIGGER_TTY_TX:
 		trigger_data->mode_tx = state;
 		break;
+	case TRIGGER_TTY_CTS:
+		trigger_data->mode_cts = state;
+		break;
+	case TRIGGER_TTY_DSR:
+		trigger_data->mode_dsr = state;
+		break;
+	case TRIGGER_TTY_DCD:
+		trigger_data->mode_dcd = state;
+		break;
+	case TRIGGER_TTY_RNG:
+		trigger_data->mode_rng = state;
+		break;
 	}
 
 	return size;
@@ -154,6 +187,10 @@ static ssize_t ledtrig_tty_attr_store(struct device *dev, const char *buf,
 
 DEFINE_TTY_TRIGGER(rx, TRIGGER_TTY_RX);
 DEFINE_TTY_TRIGGER(tx, TRIGGER_TTY_TX);
+DEFINE_TTY_TRIGGER(cts, TRIGGER_TTY_CTS);
+DEFINE_TTY_TRIGGER(dsr, TRIGGER_TTY_DSR);
+DEFINE_TTY_TRIGGER(dcd, TRIGGER_TTY_DCD);
+DEFINE_TTY_TRIGGER(rng, TRIGGER_TTY_RNG);
 
 static void ledtrig_tty_work(struct work_struct *work)
 {
@@ -161,6 +198,8 @@ static void ledtrig_tty_work(struct work_struct *work)
 		container_of(work, struct ledtrig_tty_data, dwork.work);
 	enum led_trigger_tty_state state = TTY_LED_DISABLE;
 	unsigned long interval = LEDTRIG_TTY_INTERVAL;
+	bool invert = false;
+	int status;
 	int ret;
 
 	if (!trigger_data->ttyname)
@@ -188,6 +227,33 @@ static void ledtrig_tty_work(struct work_struct *work)
 		trigger_data->tty = tty;
 	}
 
+	status = tty_get_tiocm(trigger_data->tty);
+	if (status > 0) {
+		if (trigger_data->mode_cts) {
+			if (status & TIOCM_CTS)
+				state = TTY_LED_ENABLE;
+		}
+
+		if (trigger_data->mode_dsr) {
+			if (status & TIOCM_DSR)
+				state = TTY_LED_ENABLE;
+		}
+
+		if (trigger_data->mode_dcd) {
+			if (status & TIOCM_CAR)
+				state = TTY_LED_ENABLE;
+		}
+
+		if (trigger_data->mode_rng) {
+			if (status & TIOCM_RNG)
+				state = TTY_LED_ENABLE;
+		}
+	}
+
+	/*
+	 * The evaluation of rx/tx must be done after the evaluation
+	 * of TIOCM_*, because rx/tx has priority.
+	 */
 	if (trigger_data->mode_rx || trigger_data->mode_tx) {
 		struct serial_icounter_struct icount;
 
@@ -197,11 +263,13 @@ static void ledtrig_tty_work(struct work_struct *work)
 
 		if (trigger_data->mode_tx && (icount.tx != trigger_data->tx)) {
 			trigger_data->tx = icount.tx;
+			invert = state == TTY_LED_ENABLE;
 			state = TTY_LED_BLINK;
 		}
 
 		if (trigger_data->mode_rx && (icount.rx != trigger_data->rx)) {
 			trigger_data->rx = icount.rx;
+			invert = state == TTY_LED_ENABLE;
 			state = TTY_LED_BLINK;
 		}
 	}
@@ -210,7 +278,11 @@ out:
 	switch (state) {
 	case TTY_LED_BLINK:
 		led_blink_set_oneshot(trigger_data->led_cdev, &interval,
-				&interval, 0);
+				&interval, invert);
+		break;
+	case TTY_LED_ENABLE:
+		led_set_brightness(trigger_data->led_cdev,
+				trigger_data->led_cdev->blink_brightness);
 		break;
 	case TTY_LED_DISABLE:
 		fallthrough;
@@ -228,6 +300,10 @@ static struct attribute *ledtrig_tty_attrs[] = {
 	&dev_attr_ttyname.attr,
 	&dev_attr_rx.attr,
 	&dev_attr_tx.attr,
+	&dev_attr_cts.attr,
+	&dev_attr_dsr.attr,
+	&dev_attr_dcd.attr,
+	&dev_attr_rng.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(ledtrig_tty);
-- 
GitLab


From adfd4621b78d0c02da91335da2b9ad847cb7b39e Mon Sep 17 00:00:00 2001
From: Martin Kurbanov <mmkurbanov@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:09 +0300
Subject: [PATCH 1226/4076] leds: aw200xx: Fix write to DIM parameter

If write only DIM value to the page 4, LED brightness will not be
updated, as both DIM and FADE need to be written to the page 4.
Therefore, write DIM to the page 1.

Fixes: 36a87f371b7a ("leds: Add AW20xx driver")
Signed-off-by: Martin Kurbanov <mmkurbanov@salutedevices.com>
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20231125200519.1750-2-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-aw200xx.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/leds/leds-aw200xx.c b/drivers/leds/leds-aw200xx.c
index 14ca236ce29e5..f3bed4f05b34f 100644
--- a/drivers/leds/leds-aw200xx.c
+++ b/drivers/leds/leds-aw200xx.c
@@ -74,6 +74,10 @@
 #define AW200XX_LED2REG(x, columns) \
 	((x) + (((x) / (columns)) * (AW200XX_DSIZE_COLUMNS_MAX - (columns))))
 
+/* DIM current configuration register on page 1 */
+#define AW200XX_REG_DIM_PAGE1(x, columns) \
+	AW200XX_REG(AW200XX_PAGE1, AW200XX_LED2REG(x, columns))
+
 /*
  * DIM current configuration register (page 4).
  * The even address for current DIM configuration.
@@ -153,7 +157,8 @@ static ssize_t dim_store(struct device *dev, struct device_attribute *devattr,
 
 	if (dim >= 0) {
 		ret = regmap_write(chip->regmap,
-				   AW200XX_REG_DIM(led->num, columns), dim);
+				   AW200XX_REG_DIM_PAGE1(led->num, columns),
+				   dim);
 		if (ret)
 			goto out_unlock;
 	}
-- 
GitLab


From d882762f7950c3dfd56c786a35d1518397773947 Mon Sep 17 00:00:00 2001
From: Dmitry Rokosov <ddrokosov@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:10 +0300
Subject: [PATCH 1227/4076] leds: aw200xx: Support HWEN hardware control

HWEN is hardware control, which is used for enable/disable aw200xx chip.
It's high active, internally pulled down to GND.

After HWEN pin set high the chip begins to load the OTP information,
which takes 200us to complete. About 200us wait time is needed for
internal oscillator startup and display SRAM initialization. After
display SRAM initialization, the registers in page 1 to page 5 can be
configured via i2c interface.

Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Link: https://lore.kernel.org/r/20231125200519.1750-3-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-aw200xx.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/leds/leds-aw200xx.c b/drivers/leds/leds-aw200xx.c
index f3bed4f05b34f..1bef0691dc410 100644
--- a/drivers/leds/leds-aw200xx.c
+++ b/drivers/leds/leds-aw200xx.c
@@ -10,6 +10,7 @@
 #include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/container_of.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/leds.h>
 #include <linux/mod_devicetable.h>
@@ -116,6 +117,7 @@ struct aw200xx {
 	struct mutex mutex;
 	u32 num_leds;
 	u32 display_rows;
+	struct gpio_desc *hwen;
 	struct aw200xx_led leds[] __counted_by(num_leds);
 };
 
@@ -358,6 +360,25 @@ static int aw200xx_chip_check(const struct aw200xx *const chip)
 	return 0;
 }
 
+static void aw200xx_enable(const struct aw200xx *const chip)
+{
+	gpiod_set_value_cansleep(chip->hwen, 1);
+
+	/*
+	 * After HWEN pin set high the chip begins to load the OTP information,
+	 * which takes 200us to complete. About 200us wait time is needed for
+	 * internal oscillator startup and display SRAM initialization. After
+	 * display SRAM initialization, the registers in page1 to page5 can be
+	 * configured via i2c interface.
+	 */
+	fsleep(400);
+}
+
+static void aw200xx_disable(const struct aw200xx *const chip)
+{
+	return gpiod_set_value_cansleep(chip->hwen, 0);
+}
+
 static int aw200xx_probe_fw(struct device *dev, struct aw200xx *chip)
 {
 	struct fwnode_handle *child;
@@ -517,6 +538,14 @@ static int aw200xx_probe(struct i2c_client *client)
 	if (IS_ERR(chip->regmap))
 		return PTR_ERR(chip->regmap);
 
+	chip->hwen = devm_gpiod_get_optional(&client->dev, "enable",
+					     GPIOD_OUT_HIGH);
+	if (IS_ERR(chip->hwen))
+		return dev_err_probe(&client->dev, PTR_ERR(chip->hwen),
+				     "Cannot get enable GPIO");
+
+	aw200xx_enable(chip);
+
 	ret = aw200xx_chip_check(chip);
 	if (ret)
 		return ret;
@@ -537,6 +566,9 @@ static int aw200xx_probe(struct i2c_client *client)
 	ret = aw200xx_chip_init(chip);
 
 out_unlock:
+	if (ret)
+		aw200xx_disable(chip);
+
 	mutex_unlock(&chip->mutex);
 	return ret;
 }
@@ -546,6 +578,7 @@ static void aw200xx_remove(struct i2c_client *client)
 	struct aw200xx *chip = i2c_get_clientdata(client);
 
 	aw200xx_chip_reset(chip);
+	aw200xx_disable(chip);
 	mutex_destroy(&chip->mutex);
 }
 
-- 
GitLab


From 20dbf6d4a19c5bb5d2521c4993d4373fbe05f1bc Mon Sep 17 00:00:00 2001
From: Dmitry Rokosov <ddrokosov@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:11 +0300
Subject: [PATCH 1228/4076] dt-bindings: leds: aw200xx: Introduce optional
 enable-gpios property

Property 'enable-gpios' is optional, it can be used by the board
developer to connect AW200XX LED controller with appropriate 'enable'
GPIO pad.

Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231125200519.1750-4-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
index feb5febaf361a..3da3633a242c9 100644
--- a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
+++ b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
@@ -41,6 +41,9 @@ properties:
     description:
       Leds matrix size
 
+  enable-gpios:
+    maxItems: 1
+
 patternProperties:
   "^led@[0-9a-f]$":
     type: object
@@ -90,6 +93,7 @@ additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/gpio/gpio.h>
     #include <dt-bindings/leds/common.h>
 
     i2c {
@@ -102,6 +106,7 @@ examples:
             #address-cells = <1>;
             #size-cells = <0>;
             awinic,display-rows = <3>;
+            enable-gpios = <&gpio 3 GPIO_ACTIVE_HIGH>;
 
             led@0 {
                 reg = <0x0>;
-- 
GitLab


From 2b8db5729d10b23edd61e018c18fa7b865e2d76c Mon Sep 17 00:00:00 2001
From: George Stark <gnstark@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:12 +0300
Subject: [PATCH 1229/4076] leds: aw200xx: Calculate dts property display_rows
 in the driver

Get rid of device tree property "awinic,display-rows". The property
value actually means number of current switches and depends on how LEDs
are connected to the device. It should be calculated manually by max
used LED number. In the same way it is computed automatically now.
Max used LED is taken from LED definition subnodes.

Signed-off-by: George Stark <gnstark@salutedevices.com>
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20231125200519.1750-5-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-aw200xx.c | 37 +++++++++++++++++++++++++++----------
 1 file changed, 27 insertions(+), 10 deletions(-)

diff --git a/drivers/leds/leds-aw200xx.c b/drivers/leds/leds-aw200xx.c
index 1bef0691dc410..1756b012a0b7b 100644
--- a/drivers/leds/leds-aw200xx.c
+++ b/drivers/leds/leds-aw200xx.c
@@ -379,6 +379,31 @@ static void aw200xx_disable(const struct aw200xx *const chip)
 	return gpiod_set_value_cansleep(chip->hwen, 0);
 }
 
+static int aw200xx_probe_get_display_rows(struct device *dev,
+					  struct aw200xx *chip)
+{
+	struct fwnode_handle *child;
+	u32 max_source = 0;
+
+	device_for_each_child_node(dev, child) {
+		u32 source;
+		int ret;
+
+		ret = fwnode_property_read_u32(child, "reg", &source);
+		if (ret || source >= chip->cdef->channels)
+			continue;
+
+		max_source = max(max_source, source);
+	}
+
+	if (max_source == 0)
+		return -EINVAL;
+
+	chip->display_rows = max_source / chip->cdef->display_size_columns + 1;
+
+	return 0;
+}
+
 static int aw200xx_probe_fw(struct device *dev, struct aw200xx *chip)
 {
 	struct fwnode_handle *child;
@@ -386,18 +411,10 @@ static int aw200xx_probe_fw(struct device *dev, struct aw200xx *chip)
 	int ret;
 	int i;
 
-	ret = device_property_read_u32(dev, "awinic,display-rows",
-				       &chip->display_rows);
+	ret = aw200xx_probe_get_display_rows(dev, chip);
 	if (ret)
 		return dev_err_probe(dev, ret,
-				     "Failed to read 'display-rows' property\n");
-
-	if (!chip->display_rows ||
-	    chip->display_rows > chip->cdef->display_size_rows_max) {
-		return dev_err_probe(dev, -EINVAL,
-				     "Invalid leds display size %u\n",
-				     chip->display_rows);
-	}
+				     "No valid led definitions found\n");
 
 	current_max = aw200xx_imax_from_global(chip, AW200XX_IMAX_MAX_uA);
 	current_min = aw200xx_imax_from_global(chip, AW200XX_IMAX_MIN_uA);
-- 
GitLab


From aa4ed49f42400b503690fd3184d93eee0d765a88 Mon Sep 17 00:00:00 2001
From: George Stark <gnstark@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:13 +0300
Subject: [PATCH 1230/4076] dt-bindings: leds: aw200xx: Remove property
 "awinic,display-rows"

Get rid of the property "awinic,display-rows" and calculate it
in the driver using led definition nodes.

Signed-off-by: George Stark <gnstark@salutedevices.com>
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231125200519.1750-6-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../bindings/leds/awinic,aw200xx.yaml         | 28 +++----------------
 1 file changed, 4 insertions(+), 24 deletions(-)

diff --git a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
index 3da3633a242c9..a6dced59599d2 100644
--- a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
+++ b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
@@ -36,11 +36,6 @@ properties:
   "#size-cells":
     const: 0
 
-  awinic,display-rows:
-    $ref: /schemas/types.yaml#/definitions/uint32
-    description:
-      Leds matrix size
-
   enable-gpios:
     maxItems: 1
 
@@ -63,31 +58,17 @@ patternProperties:
           since the chip has a single global setting.
           The maximum output current of each LED is calculated by the
           following formula:
-            IMAXled = 160000 * (592 / 600.5) * (1 / display-rows)
+            IMAXled = 160000 * (592 / 600.5) * (1 / max-current-switch-number)
           And the minimum output current formula:
-            IMINled = 3300 * (592 / 600.5) * (1 / display-rows)
+            IMINled = 3300 * (592 / 600.5) * (1 / max-current-switch-number)
+          where max-current-switch-number is determinated by led configuration
+          and depends on how leds are physically connected to the led driver.
 
 required:
   - compatible
   - reg
   - "#address-cells"
   - "#size-cells"
-  - awinic,display-rows
-
-allOf:
-  - if:
-      properties:
-        compatible:
-          contains:
-            const: awinic,aw20036
-    then:
-      properties:
-        awinic,display-rows:
-          enum: [1, 2, 3]
-    else:
-      properties:
-        awinic,display-rows:
-          enum: [1, 2, 3, 4, 5, 6, 7]
 
 additionalProperties: false
 
@@ -105,7 +86,6 @@ examples:
             reg = <0x3a>;
             #address-cells = <1>;
             #size-cells = <0>;
-            awinic,display-rows = <3>;
             enable-gpios = <&gpio 3 GPIO_ACTIVE_HIGH>;
 
             led@0 {
-- 
GitLab


From d883a5ab2f345c2adca781901731795ab94886fb Mon Sep 17 00:00:00 2001
From: George Stark <gnstark@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:14 +0300
Subject: [PATCH 1231/4076] leds: aw200xx: Add delay after software reset

According to the datasheets of AW200xx devices, the software reset takes
at least 1ms. Therefore, it is required to add a delay after the
reset before issuing commands to the device.

Signed-off-by: George Stark <gnstark@salutedevices.com>
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Link: https://lore.kernel.org/r/20231125200519.1750-7-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-aw200xx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/leds/leds-aw200xx.c b/drivers/leds/leds-aw200xx.c
index 1756b012a0b7b..d4877722eb564 100644
--- a/drivers/leds/leds-aw200xx.c
+++ b/drivers/leds/leds-aw200xx.c
@@ -321,6 +321,9 @@ static int aw200xx_chip_reset(const struct aw200xx *const chip)
 	if (ret)
 		return ret;
 
+	/* According to the datasheet software reset takes at least 1ms */
+	fsleep(1000);
+
 	regcache_mark_dirty(chip->regmap);
 	return regmap_write(chip->regmap, AW200XX_REG_FCD, AW200XX_FCD_CLEAR);
 }
-- 
GitLab


From 96b43a108bd689159486e97cb5a8b0170fa46657 Mon Sep 17 00:00:00 2001
From: George Stark <gnstark@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:15 +0300
Subject: [PATCH 1232/4076] leds: aw200xx: Enable disable_locking flag in
 regmap config

In the driver regmap is always used under mutex so regmap's inner lock
can be disabled.

Signed-off-by: George Stark <gnstark@salutedevices.com>
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20231125200519.1750-8-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-aw200xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/leds/leds-aw200xx.c b/drivers/leds/leds-aw200xx.c
index d4877722eb564..220860258dec2 100644
--- a/drivers/leds/leds-aw200xx.c
+++ b/drivers/leds/leds-aw200xx.c
@@ -526,6 +526,7 @@ static const struct regmap_config aw200xx_regmap_config = {
 	.rd_table = &aw200xx_readable_table,
 	.wr_table = &aw200xx_writeable_table,
 	.cache_type = REGCACHE_MAPLE,
+	.disable_locking = true,
 };
 
 static int aw200xx_probe(struct i2c_client *client)
-- 
GitLab


From 150bca53652d8dcef9714d0873a86e129391f1e6 Mon Sep 17 00:00:00 2001
From: George Stark <gnstark@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:16 +0300
Subject: [PATCH 1233/4076] leds: aw200xx: Improve autodim calculation method

It is highly recommended to leverage the DIV_ROUND_UP() function as a
more refined and mathematically precise alternative to employing a
coarse division method.

Signed-off-by: George Stark <gnstark@salutedevices.com>
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20231125200519.1750-9-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-aw200xx.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/leds/leds-aw200xx.c b/drivers/leds/leds-aw200xx.c
index 220860258dec2..fe9b1565cef00 100644
--- a/drivers/leds/leds-aw200xx.c
+++ b/drivers/leds/leds-aw200xx.c
@@ -87,6 +87,8 @@
 #define AW200XX_REG_DIM(x, columns) \
 	AW200XX_REG(AW200XX_PAGE4, AW200XX_LED2REG(x, columns) * 2)
 #define AW200XX_REG_DIM2FADE(x) ((x) + 1)
+#define AW200XX_REG_FADE2DIM(fade) \
+	DIV_ROUND_UP((fade) * AW200XX_DIM_MAX, AW200XX_FADE_MAX)
 
 /*
  * Duty ratio of display scan (see p.15 of datasheet for formula):
@@ -195,9 +197,7 @@ static int aw200xx_brightness_set(struct led_classdev *cdev,
 
 	dim = led->dim;
 	if (dim < 0)
-		dim = max_t(int,
-			    brightness / (AW200XX_FADE_MAX / AW200XX_DIM_MAX),
-			    1);
+		dim = AW200XX_REG_FADE2DIM(brightness);
 
 	ret = regmap_write(chip->regmap, reg, dim);
 	if (ret)
@@ -462,6 +462,7 @@ static int aw200xx_probe_fw(struct device *dev, struct aw200xx *chip)
 		led->num = source;
 		led->chip = chip;
 		led->cdev.brightness_set_blocking = aw200xx_brightness_set;
+		led->cdev.max_brightness = AW200XX_FADE_MAX;
 		led->cdev.groups = dim_groups;
 		init_data.fwnode = child;
 
-- 
GitLab


From 634fea792a31717669094f7866cf32b8eeb932c0 Mon Sep 17 00:00:00 2001
From: George Stark <gnstark@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:17 +0300
Subject: [PATCH 1234/4076] leds: aw200xx: Add support for aw20108 device

Add support for the Awinic aw20108 device, which belongs to the same LED
drivers family. The new device supports 108 LEDs using a matrix of 12x9
outputs."

Signed-off-by: George Stark <gnstark@salutedevices.com>
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Link: https://lore.kernel.org/r/20231125200519.1750-10-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/Kconfig        | 14 +++++++++-----
 drivers/leds/leds-aw200xx.c | 10 +++++++++-
 2 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index bfa11e7b157f2..a2a4689e05020 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -95,14 +95,18 @@ config LEDS_ARIEL
 	  Say Y to if your machine is a Dell Wyse 3020 thin client.
 
 config LEDS_AW200XX
-	tristate "LED support for Awinic AW20036/AW20054/AW20072"
+	tristate "LED support for Awinic AW20036/AW20054/AW20072/AW20108"
 	depends on LEDS_CLASS
 	depends on I2C
 	help
-	  This option enables support for the AW20036/AW20054/AW20072 LED driver.
-	  It is a 3x12/6x9/6x12 matrix LED driver programmed via
-	  an I2C interface, up to 36/54/72 LEDs or 12/18/24 RGBs,
-	  3 pattern controllers for auto breathing or group dimming control.
+	  This option enables support for the Awinic AW200XX LED controllers.
+	  It is a matrix LED driver programmed via an I2C interface. Devices have
+	  a set of individually controlled LEDs and support 3 pattern controllers
+	  for auto breathing or group dimming control. Supported devices:
+	    - AW20036 (3x12) 36 LEDs
+	    - AW20054 (6x9)  54 LEDs
+	    - AW20072 (6x12) 72 LEDs
+	    - AW20108 (9x12) 108 LEDs
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called leds-aw200xx.
diff --git a/drivers/leds/leds-aw200xx.c b/drivers/leds/leds-aw200xx.c
index fe9b1565cef00..f584a7f98fc5b 100644
--- a/drivers/leds/leds-aw200xx.c
+++ b/drivers/leds/leds-aw200xx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Awinic AW20036/AW20054/AW20072 LED driver
+ * Awinic AW20036/AW20054/AW20072/AW20108 LED driver
  *
  * Copyright (c) 2023, SberDevices. All Rights Reserved.
  *
@@ -622,10 +622,17 @@ static const struct aw200xx_chipdef aw20072_cdef = {
 	.display_size_columns = 12,
 };
 
+static const struct aw200xx_chipdef aw20108_cdef = {
+	.channels = 108,
+	.display_size_rows_max = 9,
+	.display_size_columns = 12,
+};
+
 static const struct i2c_device_id aw200xx_id[] = {
 	{ "aw20036" },
 	{ "aw20054" },
 	{ "aw20072" },
+	{ "aw20108" },
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, aw200xx_id);
@@ -634,6 +641,7 @@ static const struct of_device_id aw200xx_match_table[] = {
 	{ .compatible = "awinic,aw20036", .data = &aw20036_cdef, },
 	{ .compatible = "awinic,aw20054", .data = &aw20054_cdef, },
 	{ .compatible = "awinic,aw20072", .data = &aw20072_cdef, },
+	{ .compatible = "awinic,aw20108", .data = &aw20108_cdef, },
 	{}
 };
 MODULE_DEVICE_TABLE(of, aw200xx_match_table);
-- 
GitLab


From 13b93b1dca355ac87f470b12c72c0788a3a10da5 Mon Sep 17 00:00:00 2001
From: George Stark <gnstark@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:18 +0300
Subject: [PATCH 1235/4076] dt-bindings: leds: awinic,aw200xx: Add AW20108
 device

Add aw20108 compatible for Awinic AW20108 led controller.

Signed-off-by: George Stark <gnstark@salutedevices.com>
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231125200519.1750-11-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../devicetree/bindings/leds/awinic,aw200xx.yaml    | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
index a6dced59599d2..67c1d960db1dc 100644
--- a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
+++ b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
@@ -10,15 +10,19 @@ maintainers:
   - Martin Kurbanov <mmkurbanov@sberdevices.ru>
 
 description: |
-  This controller is present on AW20036/AW20054/AW20072.
-  It is a 3x12/6x9/6x12 matrix LED programmed via
-  an I2C interface, up to 36/54/72 LEDs or 12/18/24 RGBs,
-  3 pattern controllers for auto breathing or group dimming control.
+  It is a matrix LED driver programmed via an I2C interface. Devices have
+  a set of individually controlled leds and support 3 pattern controllers
+  for auto breathing or group dimming control. Supported devices:
+    - AW20036 (3x12) 36 LEDs
+    - AW20054 (6x9)  54 LEDs
+    - AW20072 (6x12) 72 LEDs
+    - AW20108 (9x12) 108 LEDs
 
   For more product information please see the link below:
   aw20036 - https://www.awinic.com/en/productDetail/AW20036QNR#tech-docs
   aw20054 - https://www.awinic.com/en/productDetail/AW20054QNR#tech-docs
   aw20072 - https://www.awinic.com/en/productDetail/AW20072QNR#tech-docs
+  aw20108 - https://www.awinic.com/en/productDetail/AW20108QNR#tech-docs
 
 properties:
   compatible:
@@ -26,6 +30,7 @@ properties:
       - awinic,aw20036
       - awinic,aw20054
       - awinic,aw20072
+      - awinic,aw20108
 
   reg:
     maxItems: 1
-- 
GitLab


From 94d4090b61395ca5542d4af72db464eeaa298088 Mon Sep 17 00:00:00 2001
From: Dmitry Rokosov <ddrokosov@salutedevices.com>
Date: Sat, 25 Nov 2023 23:05:19 +0300
Subject: [PATCH 1236/4076] dt-bindings: leds: aw200xx: Fix led pattern and add
 reg constraints

AW200XX controllers have the capability to declare more than 0xf LEDs,
therefore, it is necessary to accept LED names using an appropriate
regex pattern.

The register offsets can be adjusted within the specified range, with
the maximum value corresponding to the highest number of LEDs that can
be connected to the controller.

Fixes: e338a05e76ca ("dt-bindings: leds: Add binding for AW200xx")
Signed-off-by: Dmitry Rokosov <ddrokosov@salutedevices.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231125200519.1750-12-ddrokosov@salutedevices.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../bindings/leds/awinic,aw200xx.yaml         | 59 ++++++++++++++++++-
 1 file changed, 58 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
index 67c1d960db1dc..54d6d1f08e248 100644
--- a/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
+++ b/Documentation/devicetree/bindings/leds/awinic,aw200xx.yaml
@@ -45,7 +45,7 @@ properties:
     maxItems: 1
 
 patternProperties:
-  "^led@[0-9a-f]$":
+  "^led@[0-9a-f]+$":
     type: object
     $ref: common.yaml#
     unevaluatedProperties: false
@@ -69,6 +69,63 @@ patternProperties:
           where max-current-switch-number is determinated by led configuration
           and depends on how leds are physically connected to the led driver.
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: awinic,aw20036
+    then:
+      patternProperties:
+        "^led@[0-9a-f]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 36
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: awinic,aw20054
+    then:
+      patternProperties:
+        "^led@[0-9a-f]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 54
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: awinic,aw20072
+    then:
+      patternProperties:
+        "^led@[0-9a-f]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 72
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: awinic,aw20108
+    then:
+      patternProperties:
+        "^led@[0-9a-f]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 108
+
 required:
   - compatible
   - reg
-- 
GitLab


From 78da55c804cb9fb4ef3f839f4b284542a59b1a45 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:19:40 +0100
Subject: [PATCH 1237/4076] dt-bindings: leds: qcom,spmi-flash-led: Fix example
 node name

The led controller is a child of an SPMI PMIC, which in turn sits on an
SPMI bus.

While at it, add some newline separators to improve readability.

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231130171940.12391-1-johan+linaro@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 .../devicetree/bindings/leds/qcom,spmi-flash-led.yaml         | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml
index a8736fd5a5390..1ba607685f5f9 100644
--- a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml
+++ b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml
@@ -89,9 +89,11 @@ additionalProperties: false
 examples:
   - |
     #include <dt-bindings/leds/common.h>
-    spmi {
+
+    pmic {
         #address-cells = <1>;
         #size-cells = <0>;
+
         led-controller@ee00 {
             compatible = "qcom,pm8350c-flash-led", "qcom,spmi-flash-led";
             reg = <0xee00>;
-- 
GitLab


From 4f9b632e1bb28e0b5ec6d63a51ea727ce0581ec0 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Wed, 6 Dec 2023 12:17:54 +0100
Subject: [PATCH 1238/4076] dt-bindings: mfd: pm8008: Clean up example node
 names

Devicetree node names should be generic; fix up the pm8008 binding
example accordingly.

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231206111754.7410-5-johan+linaro@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml b/Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml
index 9e4eed34dae8a..0c75d8bde5688 100644
--- a/Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml
+++ b/Documentation/devicetree/bindings/mfd/qcom,pm8008.yaml
@@ -99,10 +99,12 @@ examples:
   - |
     #include <dt-bindings/mfd/qcom-pm8008.h>
     #include <dt-bindings/interrupt-controller/irq.h>
-    qupv3_se13_i2c {
+
+    i2c {
       #address-cells = <1>;
       #size-cells = <0>;
-      pm8008i@8 {
+
+      pmic@8 {
         compatible = "qcom,pm8008";
         reg = <0x8>;
         #address-cells = <1>;
-- 
GitLab


From 57b89048874c9edd4a17f34c126b4a4188b7b444 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 5 Dec 2023 15:14:33 -0400
Subject: [PATCH 1239/4076] iommu/arm-smmu-v3: Add a type for the STE

Instead of passing a naked __le16 * around to represent a STE wrap it in a
"struct arm_smmu_ste" with an array of the correct size. This makes it
much clearer which functions will comprise the "STE API".

Reviewed-by: Moritz Fischer <mdf@kernel.org>
Reviewed-by: Michael Shavit <mshavit@google.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 59 ++++++++++-----------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  7 ++-
 2 files changed, 35 insertions(+), 31 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 7086e5fa41ff6..ad1e055e420d3 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1252,7 +1252,7 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
 }
 
 static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
-				      __le64 *dst)
+				      struct arm_smmu_ste *dst)
 {
 	/*
 	 * This is hideously complicated, but we only really care about
@@ -1270,7 +1270,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
 	 * 3. Update Config, sync
 	 */
-	u64 val = le64_to_cpu(dst[0]);
+	u64 val = le64_to_cpu(dst->data[0]);
 	bool ste_live = false;
 	struct arm_smmu_device *smmu = NULL;
 	struct arm_smmu_ctx_desc_cfg *cd_table = NULL;
@@ -1328,10 +1328,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		else
 			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
-		dst[0] = cpu_to_le64(val);
-		dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+		dst->data[0] = cpu_to_le64(val);
+		dst->data[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
 						STRTAB_STE_1_SHCFG_INCOMING));
-		dst[2] = 0; /* Nuke the VMID */
+		dst->data[2] = 0; /* Nuke the VMID */
 		/*
 		 * The SMMU can perform negative caching, so we must sync
 		 * the STE regardless of whether the old value was live.
@@ -1346,7 +1346,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
 
 		BUG_ON(ste_live);
-		dst[1] = cpu_to_le64(
+		dst->data[1] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
@@ -1355,7 +1355,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
 		    !master->stall_enabled)
-			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
+			dst->data[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
 		val |= (cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
 			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
@@ -1365,7 +1365,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 	if (s2_cfg) {
 		BUG_ON(ste_live);
-		dst[2] = cpu_to_le64(
+		dst->data[2] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
 			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
 #ifdef __BIG_ENDIAN
@@ -1374,18 +1374,18 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
 			 STRTAB_STE_2_S2R);
 
-		dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
+		dst->data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
 
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
 	}
 
 	if (master->ats_enabled)
-		dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
+		dst->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 	/* See comment in arm_smmu_write_ctx_desc() */
-	WRITE_ONCE(dst[0], cpu_to_le64(val));
+	WRITE_ONCE(dst->data[0], cpu_to_le64(val));
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
@@ -1393,7 +1393,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
 }
 
-static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool force)
+static void arm_smmu_init_bypass_stes(struct arm_smmu_ste *strtab,
+				      unsigned int nent, bool force)
 {
 	unsigned int i;
 	u64 val = STRTAB_STE_0_V;
@@ -1404,11 +1405,11 @@ static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool fo
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
 	for (i = 0; i < nent; ++i) {
-		strtab[0] = cpu_to_le64(val);
-		strtab[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
-						   STRTAB_STE_1_SHCFG_INCOMING));
-		strtab[2] = 0;
-		strtab += STRTAB_STE_DWORDS;
+		strtab->data[0] = cpu_to_le64(val);
+		strtab->data[1] = cpu_to_le64(FIELD_PREP(
+			STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
+		strtab->data[2] = 0;
+		strtab++;
 	}
 }
 
@@ -2212,26 +2213,23 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	return 0;
 }
 
-static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
+static struct arm_smmu_ste *
+arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 {
-	__le64 *step;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
 	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
-		struct arm_smmu_strtab_l1_desc *l1_desc;
-		int idx;
+		unsigned int idx1, idx2;
 
 		/* Two-level walk */
-		idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
-		l1_desc = &cfg->l1_desc[idx];
-		idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
-		step = &l1_desc->l2ptr[idx];
+		idx1 = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
+		idx2 = sid & ((1 << STRTAB_SPLIT) - 1);
+		return &cfg->l1_desc[idx1].l2ptr[idx2];
 	} else {
 		/* Simple linear lookup */
-		step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
+		return (struct arm_smmu_ste *)&cfg
+			       ->strtab[sid * STRTAB_STE_DWORDS];
 	}
-
-	return step;
 }
 
 static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
@@ -2241,7 +2239,8 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
 
 	for (i = 0; i < master->num_streams; ++i) {
 		u32 sid = master->streams[i].id;
-		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
+		struct arm_smmu_ste *step =
+			arm_smmu_get_step_for_sid(smmu, sid);
 
 		/* Bridged PCI devices may end up with duplicated IDs */
 		for (j = 0; j < i; j++)
@@ -3772,7 +3771,7 @@ static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
 	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
 
 	list_for_each_entry(e, &rmr_list, list) {
-		__le64 *step;
+		struct arm_smmu_ste *step;
 		struct iommu_iort_rmr_data *rmr;
 		int ret, i;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 961205ba86d25..03f9e526cbd92 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -206,6 +206,11 @@
 #define STRTAB_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 6)
 
 #define STRTAB_STE_DWORDS		8
+
+struct arm_smmu_ste {
+	__le64 data[STRTAB_STE_DWORDS];
+};
+
 #define STRTAB_STE_0_V			(1UL << 0)
 #define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
 #define STRTAB_STE_0_CFG_ABORT		0
@@ -571,7 +576,7 @@ struct arm_smmu_priq {
 struct arm_smmu_strtab_l1_desc {
 	u8				span;
 
-	__le64				*l2ptr;
+	struct arm_smmu_ste		*l2ptr;
 	dma_addr_t			l2ptr_dma;
 };
 
-- 
GitLab


From 12a48fe90d0919e4e594815122403f793a090803 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 5 Dec 2023 15:14:34 -0400
Subject: [PATCH 1240/4076] iommu/arm-smmu-v3: Master cannot be NULL in
 arm_smmu_write_strtab_ent()

The only caller is arm_smmu_install_ste_for_dev() which never has a NULL
master. Remove the confusing if.

Reviewed-by: Moritz Fischer <mdf@kernel.org>
Reviewed-by: Michael Shavit <mshavit@google.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index ad1e055e420d3..46b2555b7c5af 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1272,10 +1272,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	 */
 	u64 val = le64_to_cpu(dst->data[0]);
 	bool ste_live = false;
-	struct arm_smmu_device *smmu = NULL;
+	struct arm_smmu_device *smmu = master->smmu;
 	struct arm_smmu_ctx_desc_cfg *cd_table = NULL;
 	struct arm_smmu_s2_cfg *s2_cfg = NULL;
-	struct arm_smmu_domain *smmu_domain = NULL;
+	struct arm_smmu_domain *smmu_domain = master->domain;
 	struct arm_smmu_cmdq_ent prefetch_cmd = {
 		.opcode		= CMDQ_OP_PREFETCH_CFG,
 		.prefetch	= {
@@ -1283,11 +1283,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		},
 	};
 
-	if (master) {
-		smmu_domain = master->domain;
-		smmu = master->smmu;
-	}
-
 	if (smmu_domain) {
 		switch (smmu_domain->stage) {
 		case ARM_SMMU_DOMAIN_S1:
-- 
GitLab


From 9fde008337d3be8afa7b3b42c1787aac4b6853c9 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 5 Dec 2023 15:14:35 -0400
Subject: [PATCH 1241/4076] iommu/arm-smmu-v3: Remove ARM_SMMU_DOMAIN_NESTED

Currently this is exactly the same as ARM_SMMU_DOMAIN_S2, so just remove
it. The ongoing work to add nesting support through iommufd will do
something a little different.

Reviewed-by: Moritz Fischer <mdf@kernel.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 4 +---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 1 -
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 46b2555b7c5af..5387c90b32930 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1289,7 +1289,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			cd_table = &master->cd_table;
 			break;
 		case ARM_SMMU_DOMAIN_S2:
-		case ARM_SMMU_DOMAIN_NESTED:
 			s2_cfg = &smmu_domain->s2_cfg;
 			break;
 		default:
@@ -2170,7 +2169,6 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 		fmt = ARM_64_LPAE_S1;
 		finalise_stage_fn = arm_smmu_domain_finalise_s1;
 		break;
-	case ARM_SMMU_DOMAIN_NESTED:
 	case ARM_SMMU_DOMAIN_S2:
 		ias = smmu->ias;
 		oas = smmu->oas;
@@ -2739,7 +2737,7 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain)
 	if (smmu_domain->smmu)
 		ret = -EPERM;
 	else
-		smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
 	mutex_unlock(&smmu_domain->init_mutex);
 
 	return ret;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 03f9e526cbd92..27ddf1acd12ce 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -715,7 +715,6 @@ struct arm_smmu_master {
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
-	ARM_SMMU_DOMAIN_NESTED,
 	ARM_SMMU_DOMAIN_BYPASS,
 };
 
-- 
GitLab


From ff0f802974136c7f4c576da227565dc27cc1c69d Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 17 Oct 2023 15:11:40 -0300
Subject: [PATCH 1242/4076] iommu/arm-smmu: Reorganize
 arm_smmu_domain_add_master()

Make arm_smmu_domain_add_master() not use the smmu_domain to detect the
s2cr configuration, instead pass it in as a parameter. It always returns
zero so make it return void.

Since it no longer really does anything to do with a domain call it
arm_smmu_master_install_s2crs().

This is done to make the next two patches able to re-use this code without
forcing the creation of a struct arm_smmu_domain.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v2-c86cc8c2230e+160bb-smmu_newapi_jgg@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index d6d1a2a55cc06..e2ec1fe14ed40 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1081,21 +1081,14 @@ static void arm_smmu_master_free_smes(struct arm_smmu_master_cfg *cfg,
 	mutex_unlock(&smmu->stream_map_mutex);
 }
 
-static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
-				      struct arm_smmu_master_cfg *cfg,
-				      struct iommu_fwspec *fwspec)
+static void arm_smmu_master_install_s2crs(struct arm_smmu_master_cfg *cfg,
+					  enum arm_smmu_s2cr_type type,
+					  u8 cbndx, struct iommu_fwspec *fwspec)
 {
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_device *smmu = cfg->smmu;
 	struct arm_smmu_s2cr *s2cr = smmu->s2crs;
-	u8 cbndx = smmu_domain->cfg.cbndx;
-	enum arm_smmu_s2cr_type type;
 	int i, idx;
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS)
-		type = S2CR_TYPE_BYPASS;
-	else
-		type = S2CR_TYPE_TRANS;
-
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx)
 			continue;
@@ -1105,7 +1098,6 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 		s2cr[idx].cbndx = cbndx;
 		arm_smmu_write_s2cr(smmu, idx);
 	}
-	return 0;
 }
 
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1153,7 +1145,12 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	/* Looks ok, so add the device to the domain */
-	ret = arm_smmu_domain_add_master(smmu_domain, cfg, fwspec);
+	arm_smmu_master_install_s2crs(cfg,
+				      smmu_domain->stage ==
+						      ARM_SMMU_DOMAIN_BYPASS ?
+					      S2CR_TYPE_BYPASS :
+					      S2CR_TYPE_TRANS,
+				      smmu_domain->cfg.cbndx, fwspec);
 
 	/*
 	 * Setup an autosuspend delay to avoid bouncing runpm state.
-- 
GitLab


From 22bb7b41476a1b8dc282dc5b3ca5470090b52e46 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 17 Oct 2023 15:11:41 -0300
Subject: [PATCH 1243/4076] iommu/arm-smmu: Convert to a global static identity
 domain

Create a global static identity domain with it's own
arm_smmu_attach_dev_identity() that simply calls
arm_smmu_master_install_s2crs() with the identity parameters.

This is done by giving the attach path for identity its own unique
implementation that simply calls arm_smmu_master_install_s2crs().

Remove ARM_SMMU_DOMAIN_BYPASS and all checks of IOMMU_DOMAIN_IDENTITY.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/2-v2-c86cc8c2230e+160bb-smmu_newapi_jgg@nvidia.com
[will: Move duplicated autosuspend logic into a helper function]
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 81 ++++++++++++++++++---------
 drivers/iommu/arm/arm-smmu/arm-smmu.h |  1 -
 2 files changed, 53 insertions(+), 29 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index e2ec1fe14ed40..dec912c271412 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -82,6 +82,23 @@ static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 		pm_runtime_put_autosuspend(smmu->dev);
 }
 
+static void arm_smmu_rpm_use_autosuspend(struct arm_smmu_device *smmu)
+{
+	/*
+	 * Setup an autosuspend delay to avoid bouncing runpm state.
+	 * Otherwise, if a driver for a suspended consumer device
+	 * unmaps buffers, it will runpm resume/suspend for each one.
+	 *
+	 * For example, when used by a GPU device, when an application
+	 * or game exits, it can trigger unmapping 100s or 1000s of
+	 * buffers.  With a runpm cycle for each buffer, that adds up
+	 * to 5-10sec worth of reprogramming the context bank, while
+	 * the system appears to be locked up to the user.
+	 */
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+}
+
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct arm_smmu_domain, domain);
@@ -624,12 +641,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu_domain->smmu)
 		goto out_unlock;
 
-	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
-		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
-		smmu_domain->smmu = smmu;
-		goto out_unlock;
-	}
-
 	/*
 	 * Mapping the requested stage onto what we support is surprisingly
 	 * complicated, mainly because the spec allows S1+S2 SMMUs without
@@ -825,7 +836,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	int ret, irq;
 
-	if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
+	if (!smmu)
 		return;
 
 	ret = arm_smmu_rpm_get(smmu);
@@ -854,7 +865,7 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) {
+	if (type != IOMMU_DOMAIN_UNMANAGED) {
 		if (using_legacy_binding || type != IOMMU_DOMAIN_DMA)
 			return NULL;
 	}
@@ -1145,32 +1156,45 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	/* Looks ok, so add the device to the domain */
-	arm_smmu_master_install_s2crs(cfg,
-				      smmu_domain->stage ==
-						      ARM_SMMU_DOMAIN_BYPASS ?
-					      S2CR_TYPE_BYPASS :
-					      S2CR_TYPE_TRANS,
+	arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_TRANS,
 				      smmu_domain->cfg.cbndx, fwspec);
-
-	/*
-	 * Setup an autosuspend delay to avoid bouncing runpm state.
-	 * Otherwise, if a driver for a suspended consumer device
-	 * unmaps buffers, it will runpm resume/suspend for each one.
-	 *
-	 * For example, when used by a GPU device, when an application
-	 * or game exits, it can trigger unmapping 100s or 1000s of
-	 * buffers.  With a runpm cycle for each buffer, that adds up
-	 * to 5-10sec worth of reprogramming the context bank, while
-	 * the system appears to be locked up to the user.
-	 */
-	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
-	pm_runtime_use_autosuspend(smmu->dev);
-
+	arm_smmu_rpm_use_autosuspend(smmu);
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
 }
 
+static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
+					struct device *dev)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_device *smmu;
+	int ret;
+
+	if (!cfg)
+		return -ENODEV;
+	smmu = cfg->smmu;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return ret;
+
+	arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_BYPASS, 0, fwspec);
+	arm_smmu_rpm_use_autosuspend(smmu);
+	arm_smmu_rpm_put(smmu);
+	return 0;
+}
+
+static const struct iommu_domain_ops arm_smmu_identity_ops = {
+	.attach_dev = arm_smmu_attach_dev_identity,
+};
+
+static struct iommu_domain arm_smmu_identity_domain = {
+	.type = IOMMU_DOMAIN_IDENTITY,
+	.ops = &arm_smmu_identity_ops,
+};
+
 static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
 			      int prot, gfp_t gfp, size_t *mapped)
@@ -1557,6 +1581,7 @@ static int arm_smmu_def_domain_type(struct device *dev)
 }
 
 static struct iommu_ops arm_smmu_ops = {
+	.identity_domain	= &arm_smmu_identity_domain,
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
 	.probe_device		= arm_smmu_probe_device,
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 703fd5817ec11..836ed6799a801 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -361,7 +361,6 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
 	ARM_SMMU_DOMAIN_NESTED,
-	ARM_SMMU_DOMAIN_BYPASS,
 };
 
 struct arm_smmu_domain {
-- 
GitLab


From bbbf11eea38c0cb167edc5ce5fe76324e87ad074 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 17 Oct 2023 15:11:42 -0300
Subject: [PATCH 1244/4076] iommu/arm-smmu: Implement IOMMU_DOMAIN_BLOCKED

Using the same design as IDENTITY setup a S2CR_TYPE_FAULT s2cr for the
device.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/3-v2-c86cc8c2230e+160bb-smmu_newapi_jgg@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 28 ++++++++++++++++++++++++---
 1 file changed, 25 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index dec912c271412..c76b68a296bcb 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1164,8 +1164,8 @@ rpm_put:
 	return ret;
 }
 
-static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
-					struct device *dev)
+static int arm_smmu_attach_dev_type(struct device *dev,
+				    enum arm_smmu_s2cr_type type)
 {
 	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
@@ -1180,12 +1180,18 @@ static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
 	if (ret < 0)
 		return ret;
 
-	arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_BYPASS, 0, fwspec);
+	arm_smmu_master_install_s2crs(cfg, type, 0, fwspec);
 	arm_smmu_rpm_use_autosuspend(smmu);
 	arm_smmu_rpm_put(smmu);
 	return 0;
 }
 
+static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
+					struct device *dev)
+{
+	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_BYPASS);
+}
+
 static const struct iommu_domain_ops arm_smmu_identity_ops = {
 	.attach_dev = arm_smmu_attach_dev_identity,
 };
@@ -1195,6 +1201,21 @@ static struct iommu_domain arm_smmu_identity_domain = {
 	.ops = &arm_smmu_identity_ops,
 };
 
+static int arm_smmu_attach_dev_blocked(struct iommu_domain *domain,
+				       struct device *dev)
+{
+	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_FAULT);
+}
+
+static const struct iommu_domain_ops arm_smmu_blocked_ops = {
+	.attach_dev = arm_smmu_attach_dev_blocked,
+};
+
+static struct iommu_domain arm_smmu_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &arm_smmu_blocked_ops,
+};
+
 static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
 			      int prot, gfp_t gfp, size_t *mapped)
@@ -1582,6 +1603,7 @@ static int arm_smmu_def_domain_type(struct device *dev)
 
 static struct iommu_ops arm_smmu_ops = {
 	.identity_domain	= &arm_smmu_identity_domain,
+	.blocked_domain		= &arm_smmu_blocked_domain,
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
 	.probe_device		= arm_smmu_probe_device,
-- 
GitLab


From e0976331ad114af8e379e18483c346c6c79ca858 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 17 Oct 2023 15:11:43 -0300
Subject: [PATCH 1245/4076] iommu/arm-smmu: Pass arm_smmu_domain to internal
 functions

Keep the types consistent, all the callers of these functions already have
obtained a struct arm_smmu_domain, don't needlessly go to/from an
iommu_domain through the internal call chains.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/4-v2-c86cc8c2230e+160bb-smmu_newapi_jgg@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index c76b68a296bcb..664d53dfb3bdb 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -409,8 +409,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 {
 	u32 fsr, fsynr, cbfrsynra;
 	unsigned long iova;
-	struct iommu_domain *domain = dev;
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_domain *smmu_domain = dev;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	int idx = smmu_domain->cfg.cbndx;
 	int ret;
@@ -423,7 +422,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 	iova = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_FAR);
 	cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(idx));
 
-	ret = report_iommu_fault(domain, NULL, iova,
+	ret = report_iommu_fault(&smmu_domain->domain, NULL, iova,
 		fsynr & ARM_SMMU_FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ);
 
 	if (ret == -ENOSYS)
@@ -624,7 +623,7 @@ static int arm_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
 	return __arm_smmu_alloc_bitmap(smmu->context_map, start, smmu->num_context_banks);
 }
 
-static int arm_smmu_init_domain_context(struct iommu_domain *domain,
+static int arm_smmu_init_domain_context(struct arm_smmu_domain *smmu_domain,
 					struct arm_smmu_device *smmu,
 					struct device *dev)
 {
@@ -633,7 +632,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	struct io_pgtable_ops *pgtbl_ops;
 	struct io_pgtable_cfg pgtbl_cfg;
 	enum io_pgtable_fmt fmt;
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct iommu_domain *domain = &smmu_domain->domain;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	irqreturn_t (*context_fault)(int irq, void *dev);
 
@@ -807,8 +806,8 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	else
 		context_fault = arm_smmu_context_fault;
 
-	ret = devm_request_irq(smmu->dev, irq, context_fault,
-			       IRQF_SHARED, "arm-smmu-context-fault", domain);
+	ret = devm_request_irq(smmu->dev, irq, context_fault, IRQF_SHARED,
+			       "arm-smmu-context-fault", smmu_domain);
 	if (ret < 0) {
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
 			cfg->irptndx, irq);
@@ -829,9 +828,8 @@ out_unlock:
 	return ret;
 }
 
-static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
+static void arm_smmu_destroy_domain_context(struct arm_smmu_domain *smmu_domain)
 {
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	int ret, irq;
@@ -852,7 +850,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 
 	if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
 		irq = smmu->irqs[cfg->irptndx];
-		devm_free_irq(smmu->dev, irq, domain);
+		devm_free_irq(smmu->dev, irq, smmu_domain);
 	}
 
 	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
@@ -892,7 +890,7 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 	 * Free the domain resources. We assume that all devices have
 	 * already been detached.
 	 */
-	arm_smmu_destroy_domain_context(domain);
+	arm_smmu_destroy_domain_context(smmu_domain);
 	kfree(smmu_domain);
 }
 
@@ -1142,7 +1140,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return ret;
 
 	/* Ensure that the domain is finalised */
-	ret = arm_smmu_init_domain_context(domain, smmu, dev);
+	ret = arm_smmu_init_domain_context(smmu_domain, smmu, dev);
 	if (ret < 0)
 		goto rpm_put;
 
-- 
GitLab


From 9b3febc3a3da7fcd81ece10614b7fd6c729ba8b4 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 17 Oct 2023 15:11:44 -0300
Subject: [PATCH 1246/4076] iommu/arm-smmu: Convert to domain_alloc_paging()

Now that the BLOCKED and IDENTITY behaviors are managed with their own
domains change to the domain_alloc_paging() op.

The check for using_legacy_binding is now redundant,
arm_smmu_def_domain_type() always returns IOMMU_DOMAIN_IDENTITY for this
mode, so the core code will never attempt to create a DMA domain in the
first place.

Since commit a4fdd9762272 ("iommu: Use flush queue capability") the core
code only passes in IDENTITY/BLOCKED/UNMANAGED/DMA domain types. It will
not pass in IDENTITY or BLOCKED if the global statics exist, so the test
for DMA is also redundant now too.

Call arm_smmu_init_domain_context() early if a dev is available.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/5-v2-c86cc8c2230e+160bb-smmu_newapi_jgg@nvidia.com
[will: Simplify arm_smmu_domain_alloc_paging() since 'cfg' cannot be NULL]
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 664d53dfb3bdb..b0a6b367d8a2c 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -859,14 +859,10 @@ static void arm_smmu_destroy_domain_context(struct arm_smmu_domain *smmu_domain)
 	arm_smmu_rpm_put(smmu);
 }
 
-static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
+static struct iommu_domain *arm_smmu_domain_alloc_paging(struct device *dev)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED) {
-		if (using_legacy_binding || type != IOMMU_DOMAIN_DMA)
-			return NULL;
-	}
 	/*
 	 * Allocate the domain and initialise some of its data structures.
 	 * We can't really do anything meaningful until we've added a
@@ -879,6 +875,15 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 	mutex_init(&smmu_domain->init_mutex);
 	spin_lock_init(&smmu_domain->cb_lock);
 
+	if (dev) {
+		struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+
+		if (arm_smmu_init_domain_context(smmu_domain, cfg->smmu, dev)) {
+			kfree(smmu_domain);
+			return NULL;
+		}
+	}
+
 	return &smmu_domain->domain;
 }
 
@@ -1603,7 +1608,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.identity_domain	= &arm_smmu_identity_domain,
 	.blocked_domain		= &arm_smmu_blocked_domain,
 	.capable		= arm_smmu_capable,
-	.domain_alloc		= arm_smmu_domain_alloc,
+	.domain_alloc_paging	= arm_smmu_domain_alloc_paging,
 	.probe_device		= arm_smmu_probe_device,
 	.release_device		= arm_smmu_release_device,
 	.probe_finalize		= arm_smmu_probe_finalize,
-- 
GitLab


From 80c5227af3ba3a93b33e6e78c65d38a6f191ca91 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Mon, 11 Dec 2023 10:23:58 +0100
Subject: [PATCH 1247/4076] dt-bindings: interconnect: qcom,msm8998-bwmon: Add
 SM6115 bwmon instance

SM6115 has a single BWMONv4 intance for CPU. Document it.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231209-topic-6115iccdt-v1-1-f62da62b7276@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 .../devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml     | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
index 73f809cdb783c..e5fb7a3f4fe2d 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
@@ -29,6 +29,7 @@ properties:
               - qcom,sc7280-cpu-bwmon
               - qcom,sc8280xp-cpu-bwmon
               - qcom,sdm845-cpu-bwmon
+              - qcom,sm6115-cpu-bwmon
               - qcom,sm6350-llcc-bwmon
               - qcom,sm8250-cpu-bwmon
               - qcom,sm8550-cpu-bwmon
-- 
GitLab


From 85bfa5d497b41dbd02f247dfda04076b935728c1 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 29 Nov 2023 15:44:00 +0100
Subject: [PATCH 1248/4076] dt-bindings: interconnect: qcom,msm8998-bwmon: Add
 QCM2290 bwmon instance

QCM2290 has a single BWMONv4 intance for CPU. Document it.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231125-topic-rb1_feat-v3-3-4cbb567743bb@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 .../devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml     | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
index 73f809cdb783c..74bd4e9b32d2f 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
@@ -25,6 +25,7 @@ properties:
       - const: qcom,msm8998-bwmon       # BWMON v4
       - items:
           - enum:
+              - qcom,qcm2290-cpu-bwmon
               - qcom,sc7180-cpu-bwmon
               - qcom,sc7280-cpu-bwmon
               - qcom,sc8280xp-cpu-bwmon
-- 
GitLab


From 7d84a63a39b78443d09f2b4edf7ecb1d586379b4 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 7 Dec 2023 18:14:32 +0200
Subject: [PATCH 1249/4076] backlight: hx8357: Convert to agnostic GPIO API

The of_gpio.h is going to be removed. In preparation of that convert
the driver to the agnostic API.

Fixes: fbbbcd177a27 ("gpiolib: of: add quirk for locating reset lines with legacy bindings")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231207161513.3195509-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/gpio/gpiolib-of.c        |  4 +-
 drivers/video/backlight/hx8357.c | 74 ++++++++++----------------------
 2 files changed, 24 insertions(+), 54 deletions(-)

diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 402f7d99b0c1e..e7770eedd1469 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -184,7 +184,7 @@ static void of_gpio_try_fixup_polarity(const struct device_node *np,
 		const char *propname;
 		bool active_high;
 	} gpios[] = {
-#if !IS_ENABLED(CONFIG_LCD_HX8357)
+#if IS_ENABLED(CONFIG_LCD_HX8357)
 		/*
 		 * Himax LCD controllers used incorrectly named
 		 * "gpios-reset" property and also specified wrong
@@ -478,7 +478,7 @@ static struct gpio_desc *of_find_gpio_rename(struct device_node *np,
 		 */
 		const char *compatible;
 	} gpios[] = {
-#if !IS_ENABLED(CONFIG_LCD_HX8357)
+#if IS_ENABLED(CONFIG_LCD_HX8357)
 		/* Himax LCD controllers used "gpios-reset" */
 		{ "reset",	"gpios-reset",	"himax,hx8357" },
 		{ "reset",	"gpios-reset",	"himax,hx8369" },
diff --git a/drivers/video/backlight/hx8357.c b/drivers/video/backlight/hx8357.c
index f76d2469d4901..d7298376cf74d 100644
--- a/drivers/video/backlight/hx8357.c
+++ b/drivers/video/backlight/hx8357.c
@@ -6,11 +6,11 @@
  */
 
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/lcd.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/spi/spi.h>
 
 #define HX8357_NUM_IM_PINS	3
@@ -83,11 +83,10 @@
 #define HX8369_SET_GAMMA_CURVE_RELATED		0xe0
 
 struct hx8357_data {
-	unsigned		im_pins[HX8357_NUM_IM_PINS];
-	unsigned		reset;
+	struct gpio_descs	*im_pins;
+	struct gpio_desc	*reset;
 	struct spi_device	*spi;
 	int			state;
-	bool			use_im_pins;
 };
 
 static u8 hx8357_seq_power[] = {
@@ -321,11 +320,11 @@ static void hx8357_lcd_reset(struct lcd_device *lcdev)
 	struct hx8357_data *lcd = lcd_get_data(lcdev);
 
 	/* Reset the screen */
-	gpio_set_value(lcd->reset, 1);
+	gpiod_set_value(lcd->reset, 0);
 	usleep_range(10000, 12000);
-	gpio_set_value(lcd->reset, 0);
+	gpiod_set_value(lcd->reset, 1);
 	usleep_range(10000, 12000);
-	gpio_set_value(lcd->reset, 1);
+	gpiod_set_value(lcd->reset, 0);
 
 	/* The controller needs 120ms to recover from reset */
 	msleep(120);
@@ -340,10 +339,10 @@ static int hx8357_lcd_init(struct lcd_device *lcdev)
 	 * Set the interface selection pins to SPI mode, with three
 	 * wires
 	 */
-	if (lcd->use_im_pins) {
-		gpio_set_value_cansleep(lcd->im_pins[0], 1);
-		gpio_set_value_cansleep(lcd->im_pins[1], 0);
-		gpio_set_value_cansleep(lcd->im_pins[2], 1);
+	if (lcd->im_pins) {
+		gpiod_set_value_cansleep(lcd->im_pins->desc[0], 1);
+		gpiod_set_value_cansleep(lcd->im_pins->desc[1], 0);
+		gpiod_set_value_cansleep(lcd->im_pins->desc[2], 1);
 	}
 
 	ret = hx8357_spi_write_array(lcdev, hx8357_seq_power,
@@ -580,6 +579,7 @@ MODULE_DEVICE_TABLE(of, hx8357_dt_ids);
 
 static int hx8357_probe(struct spi_device *spi)
 {
+	struct device *dev = &spi->dev;
 	struct lcd_device *lcdev;
 	struct hx8357_data *lcd;
 	const struct of_device_id *match;
@@ -601,49 +601,19 @@ static int hx8357_probe(struct spi_device *spi)
 	if (!match || !match->data)
 		return -EINVAL;
 
-	lcd->reset = of_get_named_gpio(spi->dev.of_node, "gpios-reset", 0);
-	if (!gpio_is_valid(lcd->reset)) {
-		dev_err(&spi->dev, "Missing dt property: gpios-reset\n");
-		return -EINVAL;
-	}
+	lcd->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(lcd->reset))
+		return dev_err_probe(dev, PTR_ERR(lcd->reset), "failed to request reset GPIO\n");
+	gpiod_set_consumer_name(lcd->reset, "hx8357-reset");
 
-	ret = devm_gpio_request_one(&spi->dev, lcd->reset,
-				    GPIOF_OUT_INIT_HIGH,
-				    "hx8357-reset");
-	if (ret) {
-		dev_err(&spi->dev,
-			"failed to request gpio %d: %d\n",
-			lcd->reset, ret);
-		return -EINVAL;
-	}
+	lcd->im_pins = devm_gpiod_get_array_optional(dev, "im", GPIOD_OUT_LOW);
+	if (IS_ERR(lcd->im_pins))
+		return dev_err_probe(dev, PTR_ERR(lcd->im_pins), "failed to request im GPIOs\n");
+	if (lcd->im_pins->ndescs < HX8357_NUM_IM_PINS)
+		return dev_err_probe(dev, -EINVAL, "not enough im GPIOs\n");
 
-	if (of_property_present(spi->dev.of_node, "im-gpios")) {
-		lcd->use_im_pins = 1;
-
-		for (i = 0; i < HX8357_NUM_IM_PINS; i++) {
-			lcd->im_pins[i] = of_get_named_gpio(spi->dev.of_node,
-							    "im-gpios", i);
-			if (lcd->im_pins[i] == -EPROBE_DEFER) {
-				dev_info(&spi->dev, "GPIO requested is not here yet, deferring the probe\n");
-				return -EPROBE_DEFER;
-			}
-			if (!gpio_is_valid(lcd->im_pins[i])) {
-				dev_err(&spi->dev, "Missing dt property: im-gpios\n");
-				return -EINVAL;
-			}
-
-			ret = devm_gpio_request_one(&spi->dev, lcd->im_pins[i],
-						    GPIOF_OUT_INIT_LOW,
-						    "im_pins");
-			if (ret) {
-				dev_err(&spi->dev, "failed to request gpio %d: %d\n",
-					lcd->im_pins[i], ret);
-				return -EINVAL;
-			}
-		}
-	} else {
-		lcd->use_im_pins = 0;
-	}
+	for (i = 0; i < HX8357_NUM_IM_PINS; i++)
+		gpiod_set_consumer_name(lcd->im_pins->desc[i], "im_pins");
 
 	lcdev = devm_lcd_device_register(&spi->dev, "mxsfb", &spi->dev, lcd,
 					&hx8357_ops);
-- 
GitLab


From e7431bd7899c955e126c742fe608512f7e2e111a Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Sat, 2 Dec 2023 19:36:36 +0100
Subject: [PATCH 1250/4076] leds: gpio: Add kernel log if
 devm_fwnode_gpiod_get() fails

In case leds-gpio fails to get at least one of possibly many GPIOs
from the DT (e.g. the GPIO is already requested) neither gpiolib nor
the driver does provide any helpful error log:

    leds-gpio: probe of leds failed with error -16

As the driver knows better how to handle errors with such mandatory
GPIOs, let's implement an error log which points to the affected
GPIO.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231202183636.7055-1-wahrenst@gmx.net
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-gpio.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index 710c319ad312b..83fcd7b6afff7 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -172,6 +172,8 @@ static struct gpio_leds_priv *gpio_leds_create(struct device *dev)
 		led.gpiod = devm_fwnode_gpiod_get(dev, child, NULL, GPIOD_ASIS,
 						  NULL);
 		if (IS_ERR(led.gpiod)) {
+			dev_err_probe(dev, PTR_ERR(led.gpiod), "Failed to get GPIO '%pfw'\n",
+				      child);
 			fwnode_handle_put(child);
 			return ERR_CAST(led.gpiod);
 		}
-- 
GitLab


From 9e314ded2832908ef270468a5d8337c83f25f550 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 6 Dec 2023 12:43:19 +0100
Subject: [PATCH 1251/4076] leds: qcom-lpg: Introduce a wrapper for getting
 driver data from a pwm chip
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/4785982785812615d15c7dd6d2755270bd8670b2.1701860672.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/rgb/leds-qcom-lpg.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c
index 54c90ee43ef87..156b73d1f4a29 100644
--- a/drivers/leds/rgb/leds-qcom-lpg.c
+++ b/drivers/leds/rgb/leds-qcom-lpg.c
@@ -976,9 +976,14 @@ static int lpg_pattern_mc_clear(struct led_classdev *cdev)
 	return lpg_pattern_clear(led);
 }
 
+static inline struct lpg *lpg_pwm_from_chip(struct pwm_chip *chip)
+{
+	return container_of(chip, struct lpg, pwm);
+}
+
 static int lpg_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 {
-	struct lpg *lpg = container_of(chip, struct lpg, pwm);
+	struct lpg *lpg = lpg_pwm_from_chip(chip);
 	struct lpg_channel *chan = &lpg->channels[pwm->hwpwm];
 
 	return chan->in_use ? -EBUSY : 0;
@@ -994,7 +999,7 @@ static int lpg_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 static int lpg_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			 const struct pwm_state *state)
 {
-	struct lpg *lpg = container_of(chip, struct lpg, pwm);
+	struct lpg *lpg = lpg_pwm_from_chip(chip);
 	struct lpg_channel *chan = &lpg->channels[pwm->hwpwm];
 	int ret = 0;
 
@@ -1025,7 +1030,7 @@ out_unlock:
 static int lpg_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 			     struct pwm_state *state)
 {
-	struct lpg *lpg = container_of(chip, struct lpg, pwm);
+	struct lpg *lpg = lpg_pwm_from_chip(chip);
 	struct lpg_channel *chan = &lpg->channels[pwm->hwpwm];
 	unsigned int resolution;
 	unsigned int pre_div;
-- 
GitLab


From 825906f2ebe83977d747d8bce61675dddd72485d Mon Sep 17 00:00:00 2001
From: Kunwu Chan <chentao@kylinos.cn>
Date: Fri, 8 Dec 2023 11:33:20 +0800
Subject: [PATCH 1252/4076] mfd: tps6594: Add null pointer check to
 tps6594_device_init()

devm_kasprintf() returns a pointer to dynamically allocated memory
which can be NULL upon failure.

Fixes: 325bec7157b3 ("mfd: tps6594: Add driver for TI TPS6594 PMIC")
Suggested-by: Lee Jones <lee@kernel.org>
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Link: https://lore.kernel.org/r/20231208033320.49345-1-chentao@kylinos.cn
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/tps6594-core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/mfd/tps6594-core.c b/drivers/mfd/tps6594-core.c
index 0fb9c5cf213a4..783ee59901e86 100644
--- a/drivers/mfd/tps6594-core.c
+++ b/drivers/mfd/tps6594-core.c
@@ -433,6 +433,9 @@ int tps6594_device_init(struct tps6594 *tps, bool enable_crc)
 	tps6594_irq_chip.name = devm_kasprintf(dev, GFP_KERNEL, "%s-%ld-0x%02x",
 					       dev->driver->name, tps->chip_id, tps->reg);
 
+	if (!tps6594_irq_chip.name)
+		return -ENOMEM;
+
 	ret = devm_regmap_add_irq_chip(dev, tps->regmap, tps->irq, IRQF_SHARED | IRQF_ONESHOT,
 				       0, &tps6594_irq_chip, &tps->irq_data);
 	if (ret)
-- 
GitLab


From c82a1662d4548c454de5343b88f69b9fc82266b3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 8 Dec 2023 23:56:41 +0100
Subject: [PATCH 1253/4076] leds: trigger: Remove unused function
 led_trigger_rename_static()

This function was added with a8df7b1ab70b ("leds: add led_trigger_rename
function") 11 yrs ago, but it has no users. So remove it.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/d90f30be-f661-4db7-b0b5-d09d07a78a68@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/led-triggers.c | 13 -------------
 include/linux/leds.h        | 17 -----------------
 2 files changed, 30 deletions(-)

diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 6a5e1f41f9a45..bd59a14a4a90c 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -269,19 +269,6 @@ void led_trigger_set_default(struct led_classdev *led_cdev)
 }
 EXPORT_SYMBOL_GPL(led_trigger_set_default);
 
-void led_trigger_rename_static(const char *name, struct led_trigger *trig)
-{
-	/* new name must be on a temporary string to prevent races */
-	BUG_ON(name == trig->name);
-
-	down_write(&triggers_list_lock);
-	/* this assumes that trig->name was originaly allocated to
-	 * non constant storage */
-	strcpy((char *)trig->name, name);
-	up_write(&triggers_list_lock);
-}
-EXPORT_SYMBOL_GPL(led_trigger_rename_static);
-
 /* LED Trigger Interface */
 
 int led_trigger_register(struct led_trigger *trig)
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 1bdf7f5a0d7c0..4754b02d3a2c5 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -527,23 +527,6 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 	return led_cdev->trigger_data;
 }
 
-/**
- * led_trigger_rename_static - rename a trigger
- * @name: the new trigger name
- * @trig: the LED trigger to rename
- *
- * Change a LED trigger name by copying the string passed in
- * name into current trigger name, which MUST be large
- * enough for the new string.
- *
- * Note that name must NOT point to the same string used
- * during LED registration, as that could lead to races.
- *
- * This is meant to be used on triggers with statically
- * allocated name.
- */
-void led_trigger_rename_static(const char *name, struct led_trigger *trig);
-
 #define module_led_trigger(__led_trigger) \
 	module_driver(__led_trigger, led_trigger_register, \
 		      led_trigger_unregister)
-- 
GitLab


From 03d790f04fb2507173913cad9c213272ac983a60 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 11 Dec 2023 13:14:41 +0200
Subject: [PATCH 1254/4076] mfd: intel-lpss: Fix the fractional clock divider
 flags

The conversion to CLK_FRAC_DIVIDER_POWER_OF_TWO_PS uses wrong flags
in the parameters and hence miscalculates the values in the clock
divider. Fix this by applying the flag to the proper parameter.

Fixes: 82f53f9ee577 ("clk: fractional-divider: Introduce POWER_OF_TWO_PS flag")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reported-by: Alex Vinarskis <alex.vinarskis@gmail.com>
Link: https://lore.kernel.org/r/20231211111441.3910083-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/intel-lpss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index 177915845ba2b..eff423f7dd284 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -309,8 +309,8 @@ static int intel_lpss_register_clock_divider(struct intel_lpss *lpss,
 
 	snprintf(name, sizeof(name), "%s-div", devname);
 	tmp = clk_register_fractional_divider(NULL, name, __clk_get_name(tmp),
+					      0, lpss->priv, 1, 15, 16, 15,
 					      CLK_FRAC_DIVIDER_POWER_OF_TWO_PS,
-					      lpss->priv, 1, 15, 16, 15, 0,
 					      NULL);
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
-- 
GitLab


From 40cfa414e7f99ea0aa3b578e382eed93540c3641 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 12 Dec 2023 22:45:22 +0100
Subject: [PATCH 1255/4076] leds: sun50i-a100: Avoid division-by-zero warning

When CONFIG_COMMON_CLK is disabled, e.g. on an x86 randconfig compile test,
clang reports a field overflow from propagating the result of a division by
zero:

drivers/leds/leds-sun50i-a100.c:309:12: error: call to '__compiletime_assert_265' declared with 'error' attribute: FIELD_PREP: value too large for the field
        control = FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T1H, timing->t1h_ns / cycle_ns) |

Avoid the problem by adding an explicit check for the zero value here. Alternatively
the assertion could be avoided with a Kconfig dependency on COMMON_CLK.

Fixes: 090a25ad9798 ("leds: sun50i-a100: New driver for the A100 LED controller")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20231212214536.175327-1-arnd@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-sun50i-a100.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/leds/leds-sun50i-a100.c b/drivers/leds/leds-sun50i-a100.c
index e4a7e692a9087..171cefd1ea0d3 100644
--- a/drivers/leds/leds-sun50i-a100.c
+++ b/drivers/leds/leds-sun50i-a100.c
@@ -303,9 +303,13 @@ static void sun50i_a100_ledc_set_timing(struct sun50i_a100_ledc *priv)
 {
 	const struct sun50i_a100_ledc_timing *timing = &priv->timing;
 	unsigned long mod_freq = clk_get_rate(priv->mod_clk);
-	u32 cycle_ns = NSEC_PER_SEC / mod_freq;
+	u32 cycle_ns;
 	u32 control;
 
+	if (!mod_freq)
+		return;
+
+	cycle_ns = NSEC_PER_SEC / mod_freq;
 	control = FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T1H, timing->t1h_ns / cycle_ns) |
 		  FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T1L, timing->t1l_ns / cycle_ns) |
 		  FIELD_PREP(LEDC_T01_TIMING_CTRL_REG_T0H, timing->t0h_ns / cycle_ns) |
-- 
GitLab


From 813900d19b923fc1b241c1ce292472f68066092b Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Thu, 7 Dec 2023 16:16:34 +0800
Subject: [PATCH 1256/4076] perf header: Fix one memory leakage in
 perf_event__fprintf_event_update()

When dump the raw trace by `perf report -D` ASan reports a memory
leakage in perf_event__fprintf_event_update().

It shows that we allocated a temporary cpumap for dumping the CPUs but
doesn't release it and it's not used elsewhere. Fix this by free the
cpumap after the dumping.

Fixes: c853f9394b7bc189 ("perf tools: Add perf_event__fprintf_event_update function")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Cameron <jonathan.cameron@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linuxarm@huawei.com
Link: https://lore.kernel.org/r/20231207081635.8427-2-yangyicong@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 08cc2febabde2..a9f71f8343f08 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -4391,9 +4391,10 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 		ret += fprintf(fp, "... ");
 
 		map = cpu_map__new_data(&ev->cpus.cpus);
-		if (map)
+		if (map) {
 			ret += cpu_map__fprintf(map, fp);
-		else
+			perf_cpu_map__put(map);
+		} else
 			ret += fprintf(fp, "failed to get cpus\n");
 		break;
 	default:
-- 
GitLab


From 1bc479d665bc25a9a4e8168d5b400a47491511f9 Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Thu, 7 Dec 2023 16:16:35 +0800
Subject: [PATCH 1257/4076] perf hisi-ptt: Fix one memory leakage in
 hisi_ptt_process_auxtrace_event()

ASan complains a memory leakage in hisi_ptt_process_auxtrace_event()
that the data buffer is not freed. Since currently we only support the
raw dump trace mode, the data buffer is used only within this function.
So fix this by freeing the data buffer before going out.

Fixes: 5e91e57e68090c0e ("perf auxtrace arm64: Add support for parsing HiSilicon PCIe Trace packet")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Acked-by: Namhyung Kim <Namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Cameron <jonathan.cameron@huawei.com>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Liu <liuqi115@huawei.com>
Link: https://lore.kernel.org/r/20231207081635.8427-3-yangyicong@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hisi-ptt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c
index 43bd1ca62d582..52d0ce302ca04 100644
--- a/tools/perf/util/hisi-ptt.c
+++ b/tools/perf/util/hisi-ptt.c
@@ -123,6 +123,7 @@ static int hisi_ptt_process_auxtrace_event(struct perf_session *session,
 	if (dump_trace)
 		hisi_ptt_dump_event(ptt, data, size);
 
+	free(data);
 	return 0;
 }
 
-- 
GitLab


From 3c6b0c1c28184038d90dffe8eb542bedcb8ccf98 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 30 Nov 2023 14:27:29 +0100
Subject: [PATCH 1258/4076] srcu: Use try-lock lockdep annotation for NMI-safe
 access.

It is claimed that srcu_read_lock_nmisafe() NMI-safe. However it
triggers a lockdep if used from NMI because lockdep expects a deadlock
since nothing disables NMIs while the lock is acquired.

This is because commit f0f44752f5f61 ("rcu: Annotate SRCU's update-side
lockdep dependencies") annotates synchronize_srcu() as a write lock
usage. This helps to detect a deadlocks such as
	srcu_read_lock();
	synchronize_srcu();
	srcu_read_unlock();

The side effect is that the lock srcu_struct now has a USED usage in normal
contexts, so it conflicts with a USED_READ usage in NMI. But this shouldn't
cause a real deadlock because the write lock usage from synchronize_srcu()
is a fake one and only used for read/write deadlock detection.

Use a try-lock annotation for srcu_read_lock_nmisafe() to avoid lockdep
complains if used from NMI.

Fixes: f0f44752f5f6 ("rcu: Annotate SRCU's update-side lockdep dependencies")
Link: https://lore.kernel.org/r/20230927160231.XRCDDSK4@linutronix.de
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 include/linux/rcupdate.h | 6 ++++++
 include/linux/srcu.h     | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f7206b2623c98..31d523c4e0893 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -301,6 +301,11 @@ static inline void rcu_lock_acquire(struct lockdep_map *map)
 	lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_);
 }
 
+static inline void rcu_try_lock_acquire(struct lockdep_map *map)
+{
+	lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_);
+}
+
 static inline void rcu_lock_release(struct lockdep_map *map)
 {
 	lock_release(map, _THIS_IP_);
@@ -315,6 +320,7 @@ int rcu_read_lock_any_held(void);
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 # define rcu_lock_acquire(a)		do { } while (0)
+# define rcu_try_lock_acquire(a)	do { } while (0)
 # define rcu_lock_release(a)		do { } while (0)
 
 static inline int rcu_read_lock_held(void)
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 127ef3b2e6073..236610e4a8fa5 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -229,7 +229,7 @@ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp
 
 	srcu_check_nmi_safety(ssp, true);
 	retval = __srcu_read_lock_nmisafe(ssp);
-	rcu_lock_acquire(&ssp->dep_map);
+	rcu_try_lock_acquire(&ssp->dep_map);
 	return retval;
 }
 
-- 
GitLab


From b3ba0f6e82cb9a88d64519f1a0c455bca39d343e Mon Sep 17 00:00:00 2001
From: Matt Ranostay <mranostay@ti.com>
Date: Tue, 28 Nov 2023 11:13:58 +0530
Subject: [PATCH 1259/4076] dt-bindings: PCI: ti,j721e-pci-*: Add checks for
 num-lanes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add num-lanes schema checks based on compatible string on available lanes
for that platform.

Link: https://lore.kernel.org/linux-pci/20231128054402.2155183-2-s-vadapalli@ti.com
Signed-off-by: Matt Ranostay <mranostay@ti.com>
Signed-off-by: Achal Verma <a-verma1@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/pci/ti,j721e-pci-ep.yaml         | 27 ++++++++++++++++---
 .../bindings/pci/ti,j721e-pci-host.yaml       | 27 ++++++++++++++++---
 2 files changed, 48 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml b/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
index 62292185fe2e4..162e5c2906e17 100644
--- a/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
+++ b/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
@@ -10,9 +10,6 @@ title: TI J721E PCI EP (PCIe Wrapper)
 maintainers:
   - Kishon Vijay Abraham I <kishon@ti.com>
 
-allOf:
-  - $ref: cdns-pcie-ep.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -65,6 +62,30 @@ properties:
     items:
       - const: link_state
 
+allOf:
+  - $ref: cdns-pcie-ep.yaml#
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,am64-pcie-ep
+    then:
+      properties:
+        num-lanes:
+          const: 1
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,j7200-pcie-ep
+            - ti,j721e-pcie-ep
+    then:
+      properties:
+        num-lanes:
+          minimum: 1
+          maximum: 2
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml b/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
index a2c5eaea57f50..854dc9e08dcf1 100644
--- a/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
+++ b/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
@@ -10,9 +10,6 @@ title: TI J721E PCI Host (PCIe Wrapper)
 maintainers:
   - Kishon Vijay Abraham I <kishon@ti.com>
 
-allOf:
-  - $ref: cdns-pcie-host.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -94,6 +91,30 @@ properties:
       interrupts:
         maxItems: 1
 
+allOf:
+  - $ref: cdns-pcie-host.yaml#
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,am64-pcie-host
+    then:
+      properties:
+        num-lanes:
+          const: 1
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,j7200-pcie-host
+            - ti,j721e-pcie-host
+    then:
+      properties:
+        num-lanes:
+          minimum: 1
+          maximum: 2
+
 required:
   - compatible
   - reg
-- 
GitLab


From adc14d44d7cb676a5e2105a711e8a168eaebed6e Mon Sep 17 00:00:00 2001
From: Matt Ranostay <mranostay@ti.com>
Date: Tue, 28 Nov 2023 11:13:59 +0530
Subject: [PATCH 1260/4076] dt-bindings: PCI: ti,j721e-pci-*: Add j784s4-pci-*
 compatible strings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add definition for j784s4-pci-ep and j784s4-pci-host devices along with
schema checks for num-lanes.

Link: https://lore.kernel.org/linux-pci/20231128054402.2155183-3-s-vadapalli@ti.com
Signed-off-by: Matt Ranostay <mranostay@ti.com>
Signed-off-by: Achal Verma <a-verma1@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../devicetree/bindings/pci/ti,j721e-pci-ep.yaml     | 12 ++++++++++++
 .../devicetree/bindings/pci/ti,j721e-pci-host.yaml   | 12 ++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml b/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
index 162e5c2906e17..97f2579ea9082 100644
--- a/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
+++ b/Documentation/devicetree/bindings/pci/ti,j721e-pci-ep.yaml
@@ -14,6 +14,7 @@ properties:
   compatible:
     oneOf:
       - const: ti,j721e-pcie-ep
+      - const: ti,j784s4-pcie-ep
       - description: PCIe EP controller in AM64
         items:
           - const: ti,am64-pcie-ep
@@ -86,6 +87,17 @@ allOf:
           minimum: 1
           maximum: 2
 
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,j784s4-pcie-ep
+    then:
+      properties:
+        num-lanes:
+          minimum: 1
+          maximum: 4
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml b/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
index 854dc9e08dcf1..b7a534cef24d3 100644
--- a/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
+++ b/Documentation/devicetree/bindings/pci/ti,j721e-pci-host.yaml
@@ -14,6 +14,7 @@ properties:
   compatible:
     oneOf:
       - const: ti,j721e-pcie-host
+      - const: ti,j784s4-pcie-host
       - description: PCIe controller in AM64
         items:
           - const: ti,am64-pcie-host
@@ -115,6 +116,17 @@ allOf:
           minimum: 1
           maximum: 2
 
+  - if:
+      properties:
+        compatible:
+          enum:
+            - ti,j784s4-pcie-host
+    then:
+      properties:
+        num-lanes:
+          minimum: 1
+          maximum: 4
+
 required:
   - compatible
   - reg
-- 
GitLab


From 3ac7f14084f54bff9c31573d1ed59d047a34fe03 Mon Sep 17 00:00:00 2001
From: Matt Ranostay <mranostay@ti.com>
Date: Tue, 28 Nov 2023 11:14:00 +0530
Subject: [PATCH 1261/4076] PCI: j721e: Add per platform maximum lane settings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Various platforms have different maximum amount of lanes that can be
selected. Add max_lanes to struct j721e_pcie to allow for detection of this
which is needed to calculate the needed bitmask size for the possible lane
count.

Link: https://lore.kernel.org/linux-pci/20231128054402.2155183-4-s-vadapalli@ti.com
Signed-off-by: Matt Ranostay <mranostay@ti.com>
Signed-off-by: Achal Verma <a-verma1@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Ravi Gunasekaran <r-gunasekaran@ti.com>
---
 drivers/pci/controller/cadence/pci-j721e.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index 2c87e7728a653..63c758b14314d 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -47,8 +47,6 @@ enum link_status {
 
 #define GENERATION_SEL_MASK		GENMASK(1, 0)
 
-#define MAX_LANES			2
-
 struct j721e_pcie {
 	struct cdns_pcie	*cdns_pcie;
 	struct clk		*refclk;
@@ -71,6 +69,7 @@ struct j721e_pcie_data {
 	unsigned int		quirk_disable_flr:1;
 	u32			linkdown_irq_regfield;
 	unsigned int		byte_access_allowed:1;
+	unsigned int		max_lanes;
 };
 
 static inline u32 j721e_pcie_user_readl(struct j721e_pcie *pcie, u32 offset)
@@ -290,11 +289,13 @@ static const struct j721e_pcie_data j721e_pcie_rc_data = {
 	.quirk_retrain_flag = true,
 	.byte_access_allowed = false,
 	.linkdown_irq_regfield = LINK_DOWN,
+	.max_lanes = 2,
 };
 
 static const struct j721e_pcie_data j721e_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
 	.linkdown_irq_regfield = LINK_DOWN,
+	.max_lanes = 2,
 };
 
 static const struct j721e_pcie_data j7200_pcie_rc_data = {
@@ -302,23 +303,27 @@ static const struct j721e_pcie_data j7200_pcie_rc_data = {
 	.quirk_detect_quiet_flag = true,
 	.linkdown_irq_regfield = J7200_LINK_DOWN,
 	.byte_access_allowed = true,
+	.max_lanes = 2,
 };
 
 static const struct j721e_pcie_data j7200_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
 	.quirk_detect_quiet_flag = true,
 	.quirk_disable_flr = true,
+	.max_lanes = 2,
 };
 
 static const struct j721e_pcie_data am64_pcie_rc_data = {
 	.mode = PCI_MODE_RC,
 	.linkdown_irq_regfield = J7200_LINK_DOWN,
 	.byte_access_allowed = true,
+	.max_lanes = 1,
 };
 
 static const struct j721e_pcie_data am64_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
 	.linkdown_irq_regfield = J7200_LINK_DOWN,
+	.max_lanes = 1,
 };
 
 static const struct of_device_id of_j721e_pcie_match[] = {
@@ -432,8 +437,10 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 	pcie->user_cfg_base = base;
 
 	ret = of_property_read_u32(node, "num-lanes", &num_lanes);
-	if (ret || num_lanes > MAX_LANES)
+	if (ret || num_lanes > data->max_lanes) {
+		dev_warn(dev, "num-lanes property not provided or invalid, setting num-lanes to 1\n");
 		num_lanes = 1;
+	}
 	pcie->num_lanes = num_lanes;
 
 	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)))
-- 
GitLab


From 4490f559f75514d5a6f0e729e85235a7be6216bf Mon Sep 17 00:00:00 2001
From: Matt Ranostay <mranostay@ti.com>
Date: Tue, 28 Nov 2023 11:14:01 +0530
Subject: [PATCH 1262/4076] PCI: j721e: Add PCIe 4x lane selection support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for setting of two-bit field that allows selection of 4x lane
PCIe which was previously limited to only 2x lanes.

Link: https://lore.kernel.org/linux-pci/20231128054402.2155183-5-s-vadapalli@ti.com
Signed-off-by: Matt Ranostay <mranostay@ti.com>
Signed-off-by: Achal Verma <a-verma1@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
---
 drivers/pci/controller/cadence/pci-j721e.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index 63c758b14314d..645597856a1d9 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -42,7 +42,6 @@ enum link_status {
 };
 
 #define J721E_MODE_RC			BIT(7)
-#define LANE_COUNT_MASK			BIT(8)
 #define LANE_COUNT(n)			((n) << 8)
 
 #define GENERATION_SEL_MASK		GENMASK(1, 0)
@@ -52,6 +51,7 @@ struct j721e_pcie {
 	struct clk		*refclk;
 	u32			mode;
 	u32			num_lanes;
+	u32			max_lanes;
 	void __iomem		*user_cfg_base;
 	void __iomem		*intd_cfg_base;
 	u32			linkdown_irq_regfield;
@@ -205,11 +205,15 @@ static int j721e_pcie_set_lane_count(struct j721e_pcie *pcie,
 {
 	struct device *dev = pcie->cdns_pcie->dev;
 	u32 lanes = pcie->num_lanes;
+	u32 mask = BIT(8);
 	u32 val = 0;
 	int ret;
 
+	if (pcie->max_lanes == 4)
+		mask = GENMASK(9, 8);
+
 	val = LANE_COUNT(lanes - 1);
-	ret = regmap_update_bits(syscon, offset, LANE_COUNT_MASK, val);
+	ret = regmap_update_bits(syscon, offset, mask, val);
 	if (ret)
 		dev_err(dev, "failed to set link count\n");
 
@@ -441,7 +445,9 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 		dev_warn(dev, "num-lanes property not provided or invalid, setting num-lanes to 1\n");
 		num_lanes = 1;
 	}
+
 	pcie->num_lanes = num_lanes;
+	pcie->max_lanes = data->max_lanes;
 
 	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)))
 		return -EINVAL;
-- 
GitLab


From 906b545b16594e45f2d3433028dcf649d2c05ebb Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Thu, 7 Dec 2023 09:06:52 +0200
Subject: [PATCH 1263/4076] pinctrl: renesas: rzg2l: Move arg and index in the
 main function block

Move arg and index in the main block of the function as they are used by
more than one case block of switch-case (3 out of 4 for arg, 2 out of 4
for index). In this way some lines of code are removed.

Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231207070700.4156557-4-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index aed59c53207c7..413ef9715503c 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -842,7 +842,7 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 	struct rzg2l_pinctrl_pin_settings settings = pctrl->settings[_pin];
 	unsigned int *pin_data = pin->drv_data;
 	enum pin_config_param param;
-	unsigned int i;
+	unsigned int i, arg, index;
 	u32 cfg, off;
 	int ret;
 	u8 bit;
@@ -864,24 +864,21 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 	for (i = 0; i < num_configs; i++) {
 		param = pinconf_to_config_param(_configs[i]);
 		switch (param) {
-		case PIN_CONFIG_INPUT_ENABLE: {
-			unsigned int arg =
-					pinconf_to_config_argument(_configs[i]);
+		case PIN_CONFIG_INPUT_ENABLE:
+			arg = pinconf_to_config_argument(_configs[i]);
 
 			if (!(cfg & PIN_CFG_IEN))
 				return -EINVAL;
 
 			rzg2l_rmw_pin_config(pctrl, IEN(off), bit, IEN_MASK, !!arg);
 			break;
-		}
 
 		case PIN_CONFIG_POWER_SOURCE:
 			settings.power_source = pinconf_to_config_argument(_configs[i]);
 			break;
 
-		case PIN_CONFIG_DRIVE_STRENGTH: {
-			unsigned int arg = pinconf_to_config_argument(_configs[i]);
-			unsigned int index;
+		case PIN_CONFIG_DRIVE_STRENGTH:
+			arg = pinconf_to_config_argument(_configs[i]);
 
 			if (!(cfg & PIN_CFG_IOLH_A) || hwcfg->drive_strength_ua)
 				return -EINVAL;
@@ -896,7 +893,6 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 
 			rzg2l_rmw_pin_config(pctrl, IOLH(off), bit, IOLH_MASK, index);
 			break;
-		}
 
 		case PIN_CONFIG_DRIVE_STRENGTH_UA:
 			if (!(cfg & (PIN_CFG_IOLH_A | PIN_CFG_IOLH_B | PIN_CFG_IOLH_C)) ||
@@ -906,9 +902,8 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 			settings.drive_strength_ua = pinconf_to_config_argument(_configs[i]);
 			break;
 
-		case PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS: {
-			unsigned int arg = pinconf_to_config_argument(_configs[i]);
-			unsigned int index;
+		case PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS:
+			arg = pinconf_to_config_argument(_configs[i]);
 
 			if (!(cfg & PIN_CFG_IOLH_B) || !hwcfg->iolh_groupb_oi[0])
 				return -EINVAL;
@@ -922,7 +917,6 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 
 			rzg2l_rmw_pin_config(pctrl, IOLH(off), bit, IOLH_MASK, index);
 			break;
-		}
 
 		default:
 			return -EOPNOTSUPP;
-- 
GitLab


From 991801bc4722e287035e907a0202954a2ffb2798 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 10 Dec 2023 18:50:03 +0100
Subject: [PATCH 1264/4076] PCI: vmd: Remove usage of the deprecated
 ida_simple_xx() API
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Link: https://lore.kernel.org/linux-pci/270f25cdc154f3b0309e57b2f6421776752e2170.1702230593.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/vmd.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 94ba61fe1c441..00a4264711f1b 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -984,7 +984,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	vmd->dev = dev;
-	vmd->instance = ida_simple_get(&vmd_instance_ida, 0, 0, GFP_KERNEL);
+	vmd->instance = ida_alloc(&vmd_instance_ida, GFP_KERNEL);
 	if (vmd->instance < 0)
 		return vmd->instance;
 
@@ -1026,7 +1026,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	return 0;
 
  out_release_instance:
-	ida_simple_remove(&vmd_instance_ida, vmd->instance);
+	ida_free(&vmd_instance_ida, vmd->instance);
 	return err;
 }
 
@@ -1048,7 +1048,7 @@ static void vmd_remove(struct pci_dev *dev)
 	vmd_cleanup_srcu(vmd);
 	vmd_detach_resources(vmd);
 	vmd_remove_irq_domain(vmd);
-	ida_simple_remove(&vmd_instance_ida, vmd->instance);
+	ida_free(&vmd_instance_ida, vmd->instance);
 }
 
 static void vmd_shutdown(struct pci_dev *dev)
-- 
GitLab


From fb91e42fe3bfca0293cb85c5fbb6f98d9d173aec Mon Sep 17 00:00:00 2001
From: Charles Han <hanchunchao@inspur.com>
Date: Mon, 18 Sep 2023 11:13:09 +0800
Subject: [PATCH 1265/4076] Documentation: RCU: Remove repeated word in
 comments

Remove the repeated word "of" in comments.

Signed-off-by: Charles Han <hanchunchao@inspur.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 Documentation/RCU/torture.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/RCU/torture.rst b/Documentation/RCU/torture.rst
index b3b6dfa85248e..49e7beea6ae15 100644
--- a/Documentation/RCU/torture.rst
+++ b/Documentation/RCU/torture.rst
@@ -185,7 +185,7 @@ argument.
 Not all changes require that all scenarios be run.  For example, a change
 to Tree SRCU might run only the SRCU-N and SRCU-P scenarios using the
 --configs argument to kvm.sh as follows:  "--configs 'SRCU-N SRCU-P'".
-Large systems can run multiple copies of of the full set of scenarios,
+Large systems can run multiple copies of the full set of scenarios,
 for example, a system with 448 hardware threads can run five instances
 of the full set concurrently.  To make this happen::
 
-- 
GitLab


From 493dffa3ab07b5d2c0b7bd5de5bff6e85f01f52a Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 20 Sep 2023 11:22:12 +0200
Subject: [PATCH 1266/4076] rculist.h: docs: Fix wrong function summary

The brief summary in the docstring for function list_next_or_null_rcu()
states that the function is supposed to provide the "first" member of a
list, whereas in truth it returns the next member.

Change the docstring so it describes what the function actually does.

Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 include/linux/rculist.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index d29740be4833e..3dc1e58865f77 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -355,7 +355,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
 })
 
 /**
- * list_next_or_null_rcu - get the first element from a list
+ * list_next_or_null_rcu - get the next element from a list
  * @head:	the head for the list.
  * @ptr:        the list head to take the next element from.
  * @type:       the type of the struct this is embedded in.
-- 
GitLab


From 1b7178b23dc915fc6801ff3eeb6c4ffa51b562f7 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 3 Oct 2023 10:30:01 -0700
Subject: [PATCH 1267/4076] doc: Clarify RCU Tasks reader/updater checklist

Currently, the reader/updater compatibility rules for the three RCU
Tasks flavors are squished together in a single paragraph, which can
result in confusion.  This commit therefore splits them out into a list,
clearly showing the distinction between these flavors.

Link: https://lore.kernel.org/all/20231002211936.5948253e@gandalf.local.home/

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 Documentation/RCU/checklist.rst | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst
index bd3c58c44befd..2d42998a89a63 100644
--- a/Documentation/RCU/checklist.rst
+++ b/Documentation/RCU/checklist.rst
@@ -241,15 +241,22 @@ over a rather long period of time, but improvements are always welcome!
 	srcu_struct.  The rules for the expedited RCU grace-period-wait
 	primitives are the same as for their non-expedited counterparts.
 
-	If the updater uses call_rcu_tasks() or synchronize_rcu_tasks(),
-	then the readers must refrain from executing voluntary
-	context switches, that is, from blocking.  If the updater uses
-	call_rcu_tasks_trace() or synchronize_rcu_tasks_trace(), then
-	the corresponding readers must use rcu_read_lock_trace() and
-	rcu_read_unlock_trace().  If an updater uses call_rcu_tasks_rude()
-	or synchronize_rcu_tasks_rude(), then the corresponding readers
-	must use anything that disables preemption, for example,
-	preempt_disable() and preempt_enable().
+	Similarly, it is necessary to correctly use the RCU Tasks flavors:
+
+	a.	If the updater uses synchronize_rcu_tasks() or
+		call_rcu_tasks(), then the readers must refrain from
+		executing voluntary context switches, that is, from
+		blocking.
+
+	b.	If the updater uses call_rcu_tasks_trace()
+		or synchronize_rcu_tasks_trace(), then the
+		corresponding readers must use rcu_read_lock_trace()
+		and rcu_read_unlock_trace().
+
+	c.	If an updater uses call_rcu_tasks_rude() or
+		synchronize_rcu_tasks_rude(), then the corresponding
+		readers must use anything that disables preemption,
+		for example, preempt_disable() and preempt_enable().
 
 	Mixing things up will result in confusion and broken kernels, and
 	has even resulted in an exploitable security issue.  Therefore,
-- 
GitLab


From c49956be75152a533787f5daa06ef4b710207499 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 20 Oct 2023 10:51:26 -0700
Subject: [PATCH 1268/4076] doc: Mention address and data dependencies in
 rcu_dereference.rst

This commit adds discussion of address and data dependencies to the
beginning of rcu_dereference.rst in order to enable readers to more
easily make the connection to the Linux-kernel memory model in general
and to memory-barriers.txt in particular.

Reported-by: Jonas Oberhauser <jonas.oberhauser@huaweicloud.com>
Reported-by: Akira Yokosawa <akiyks@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 Documentation/RCU/rcu_dereference.rst | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/Documentation/RCU/rcu_dereference.rst b/Documentation/RCU/rcu_dereference.rst
index 3b739f6243c85..659d5913784d0 100644
--- a/Documentation/RCU/rcu_dereference.rst
+++ b/Documentation/RCU/rcu_dereference.rst
@@ -3,13 +3,26 @@
 PROPER CARE AND FEEDING OF RETURN VALUES FROM rcu_dereference()
 ===============================================================
 
-Most of the time, you can use values from rcu_dereference() or one of
-the similar primitives without worries.  Dereferencing (prefix "*"),
-field selection ("->"), assignment ("="), address-of ("&"), addition and
-subtraction of constants, and casts all work quite naturally and safely.
-
-It is nevertheless possible to get into trouble with other operations.
-Follow these rules to keep your RCU code working properly:
+Proper care and feeding of address and data dependencies is critically
+important to correct use of things like RCU.  To this end, the pointers
+returned from the rcu_dereference() family of primitives carry address and
+data dependencies.  These dependencies extend from the rcu_dereference()
+macro's load of the pointer to the later use of that pointer to compute
+either the address of a later memory access (representing an address
+dependency) or the value written by a later memory access (representing
+a data dependency).
+
+Most of the time, these dependencies are preserved, permitting you to
+freely use values from rcu_dereference().  For example, dereferencing
+(prefix "*"), field selection ("->"), assignment ("="), address-of
+("&"), casts, and addition or subtraction of constants all work quite
+naturally and safely.  However, because current compilers do not take
+either address or data dependencies into account it is still possible
+to get into trouble.
+
+Follow these rules to preserve the address and data dependencies emanating
+from your calls to rcu_dereference() and friends, thus keeping your RCU
+readers working properly:
 
 -	You must use one of the rcu_dereference() family of primitives
 	to load an RCU-protected pointer, otherwise CONFIG_PROVE_RCU
-- 
GitLab


From ad9446302919ee3a646ad667a9ea15f992685dca Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 20 Oct 2023 11:04:27 -0700
Subject: [PATCH 1269/4076] doc: Clarify historical disclaimers in
 memory-barriers.txt

This commit makes it clear that the reason that these sections are
historical is that smp_read_barrier_depends() is no more.  It also
removes the point about comparison operations, given that there are
other optimizations that can break address dependencies.

Suggested-by: Jonas Oberhauser <jonas.oberhauser@huaweicloud.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Andrea Parri <parri.andrea@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: <linux-arch@vger.kernel.org>
Cc: <linux-doc@vger.kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 Documentation/memory-barriers.txt | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index d414e145f912c..4202174a6262c 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -396,10 +396,11 @@ Memory barriers come in four basic varieties:
 
 
  (2) Address-dependency barriers (historical).
-     [!] This section is marked as HISTORICAL: For more up-to-date
-     information, including how compiler transformations related to pointer
-     comparisons can sometimes cause problems, see
-     Documentation/RCU/rcu_dereference.rst.
+     [!] This section is marked as HISTORICAL: it covers the long-obsolete
+     smp_read_barrier_depends() macro, the semantics of which are now
+     implicit in all marked accesses.  For more up-to-date information,
+     including how compiler transformations can sometimes break address
+     dependencies, see Documentation/RCU/rcu_dereference.rst.
 
      An address-dependency barrier is a weaker form of read barrier.  In the
      case where two loads are performed such that the second depends on the
@@ -560,9 +561,11 @@ There are certain things that the Linux kernel memory barriers do not guarantee:
 
 ADDRESS-DEPENDENCY BARRIERS (HISTORICAL)
 ----------------------------------------
-[!] This section is marked as HISTORICAL: For more up-to-date information,
-including how compiler transformations related to pointer comparisons can
-sometimes cause problems, see Documentation/RCU/rcu_dereference.rst.
+[!] This section is marked as HISTORICAL: it covers the long-obsolete
+smp_read_barrier_depends() macro, the semantics of which are now implicit
+in all marked accesses.  For more up-to-date information, including
+how compiler transformations can sometimes break address dependencies,
+see Documentation/RCU/rcu_dereference.rst.
 
 As of v4.15 of the Linux kernel, an smp_mb() was added to READ_ONCE() for
 DEC Alpha, which means that about the only people who need to pay attention
-- 
GitLab


From dee39c0c1e9624f925da4ca0bece46bdc7427257 Mon Sep 17 00:00:00 2001
From: Zqiang <qiang.zhang1211@gmail.com>
Date: Wed, 1 Nov 2023 11:35:07 +0800
Subject: [PATCH 1270/4076] rcu: Force quiescent states only for ongoing grace
 period

If an rcutorture test scenario creates an fqs_task kthread, it will
periodically invoke rcu_force_quiescent_state() in order to start
force-quiescent-state (FQS) operations.  However, an FQS operation
will be started even if there is no RCU grace period in progress.
Although testing FQS operations startup when there is no grace period in
progress is necessary, it need not happen all that often.  This commit
therefore causes rcu_force_quiescent_state() to take an early exit
if there is no grace period in progress.

Note that there will still be attempts to start an FQS scan in the
absence of a grace period because the grace period might end right
after the rcu_force_quiescent_state() function's check.  In actual
testing, this happens about once every ten minutes, which should
provide adequate testing.

Signed-off-by: Zqiang <qiang.zhang1211@gmail.com>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 kernel/rcu/tree.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3ac3c846105fb..1ae8517778066 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2338,6 +2338,8 @@ void rcu_force_quiescent_state(void)
 	struct rcu_node *rnp;
 	struct rcu_node *rnp_old = NULL;
 
+	if (!rcu_gp_in_progress())
+		return;
 	/* Funnel through hierarchy to reduce memory contention. */
 	rnp = raw_cpu_read(rcu_data.mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
-- 
GitLab


From d4db8762dc4c364dce89901ed4690588ad310bfc Mon Sep 17 00:00:00 2001
From: ye xingchen <ye.xingchen@zte.com.cn>
Date: Tue, 12 Dec 2023 22:37:16 -0800
Subject: [PATCH 1271/4076] Input: use sysfs_emit() instead of scnprintf()

Replace calls to scnprintf() in the methods showing device attributes
with sysfs_emit() to simplify the code.

Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Link: https://lore.kernel.org/r/202212021133398847947@zte.com.cn
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/input.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/input/input.c b/drivers/input/input.c
index 8c5fdb0f858ab..f71ea4fb173fd 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1365,8 +1365,8 @@ static ssize_t input_dev_show_##name(struct device *dev,		\
 {									\
 	struct input_dev *input_dev = to_input_dev(dev);		\
 									\
-	return scnprintf(buf, PAGE_SIZE, "%s\n",			\
-			 input_dev->name ? input_dev->name : "");	\
+	return sysfs_emit(buf, "%s\n",					\
+			  input_dev->name ? input_dev->name : "");	\
 }									\
 static DEVICE_ATTR(name, S_IRUGO, input_dev_show_##name, NULL)
 
@@ -1458,7 +1458,7 @@ static ssize_t inhibited_show(struct device *dev,
 {
 	struct input_dev *input_dev = to_input_dev(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", input_dev->inhibited);
+	return sysfs_emit(buf, "%d\n", input_dev->inhibited);
 }
 
 static ssize_t inhibited_store(struct device *dev,
@@ -1505,7 +1505,7 @@ static ssize_t input_dev_show_id_##name(struct device *dev,		\
 					char *buf)			\
 {									\
 	struct input_dev *input_dev = to_input_dev(dev);		\
-	return scnprintf(buf, PAGE_SIZE, "%04x\n", input_dev->id.name);	\
+	return sysfs_emit(buf, "%04x\n", input_dev->id.name);		\
 }									\
 static DEVICE_ATTR(name, S_IRUGO, input_dev_show_id_##name, NULL)
 
-- 
GitLab


From 1864a2006ee1e41960b63ca63aa79fabb690e71b Mon Sep 17 00:00:00 2001
From: ye xingchen <ye.xingchen@zte.com.cn>
Date: Tue, 12 Dec 2023 22:12:01 -0800
Subject: [PATCH 1272/4076] Input: mouse - use sysfs_emit[_at]() instead of
 scnprintf()

Replace the calls to various *printf() functions with sysfs_emit() to
simplify the code.

Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Link: https://lore.kernel.org/r/202212021453578171100@zte.com.cn
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/cyapa.c         | 22 +++++++++++-----------
 drivers/input/mouse/cyapa_gen3.c    |  2 +-
 drivers/input/mouse/cyapa_gen5.c    |  4 ++--
 drivers/input/mouse/cyapa_gen6.c    | 20 ++++++++++----------
 drivers/input/mouse/elan_i2c_core.c | 18 +++++++++---------
 5 files changed, 33 insertions(+), 33 deletions(-)

diff --git a/drivers/input/mouse/cyapa.c b/drivers/input/mouse/cyapa.c
index a84098448f5b9..5979deabe23d1 100644
--- a/drivers/input/mouse/cyapa.c
+++ b/drivers/input/mouse/cyapa.c
@@ -756,16 +756,16 @@ static ssize_t cyapa_show_suspend_scanrate(struct device *dev,
 
 	switch (pwr_cmd) {
 	case PWR_MODE_BTN_ONLY:
-		len = scnprintf(buf, PAGE_SIZE, "%s\n", BTN_ONLY_MODE_NAME);
+		len = sysfs_emit(buf, "%s\n", BTN_ONLY_MODE_NAME);
 		break;
 
 	case PWR_MODE_OFF:
-		len = scnprintf(buf, PAGE_SIZE, "%s\n", OFF_MODE_NAME);
+		len = sysfs_emit(buf, "%s\n", OFF_MODE_NAME);
 		break;
 
 	default:
-		len = scnprintf(buf, PAGE_SIZE, "%u\n",
-				cyapa->gen == CYAPA_GEN3 ?
+		len = sysfs_emit(buf, "%u\n",
+				 cyapa->gen == CYAPA_GEN3 ?
 					cyapa_pwr_cmd_to_sleep_time(pwr_cmd) :
 					sleep_time);
 		break;
@@ -877,8 +877,8 @@ static ssize_t cyapa_show_rt_suspend_scanrate(struct device *dev,
 
 	mutex_unlock(&cyapa->state_sync_lock);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			 cyapa->gen == CYAPA_GEN3 ?
+	return sysfs_emit(buf, "%u\n",
+			  cyapa->gen == CYAPA_GEN3 ?
 				cyapa_pwr_cmd_to_sleep_time(pwr_cmd) :
 				sleep_time);
 }
@@ -988,8 +988,8 @@ static ssize_t cyapa_show_fm_ver(struct device *dev,
 	error = mutex_lock_interruptible(&cyapa->state_sync_lock);
 	if (error)
 		return error;
-	error = scnprintf(buf, PAGE_SIZE, "%d.%d\n", cyapa->fw_maj_ver,
-			 cyapa->fw_min_ver);
+	error = sysfs_emit(buf, "%d.%d\n",
+			   cyapa->fw_maj_ver, cyapa->fw_min_ver);
 	mutex_unlock(&cyapa->state_sync_lock);
 	return error;
 }
@@ -1004,7 +1004,7 @@ static ssize_t cyapa_show_product_id(struct device *dev,
 	error = mutex_lock_interruptible(&cyapa->state_sync_lock);
 	if (error)
 		return error;
-	size = scnprintf(buf, PAGE_SIZE, "%s\n", cyapa->product_id);
+	size = sysfs_emit(buf, "%s\n", cyapa->product_id);
 	mutex_unlock(&cyapa->state_sync_lock);
 	return size;
 }
@@ -1209,8 +1209,8 @@ static ssize_t cyapa_show_mode(struct device *dev,
 	if (error)
 		return error;
 
-	size = scnprintf(buf, PAGE_SIZE, "gen%d %s\n",
-			cyapa->gen, cyapa_state_to_string(cyapa));
+	size = sysfs_emit(buf, "gen%d %s\n",
+			  cyapa->gen, cyapa_state_to_string(cyapa));
 
 	mutex_unlock(&cyapa->state_sync_lock);
 	return size;
diff --git a/drivers/input/mouse/cyapa_gen3.c b/drivers/input/mouse/cyapa_gen3.c
index a97f4acb64526..60c83bc71d84e 100644
--- a/drivers/input/mouse/cyapa_gen3.c
+++ b/drivers/input/mouse/cyapa_gen3.c
@@ -860,7 +860,7 @@ static ssize_t cyapa_gen3_show_baseline(struct device *dev,
 
 	dev_dbg(dev, "Baseline report successful. Max: %d Min: %d\n",
 		max_baseline, min_baseline);
-	ret = scnprintf(buf, PAGE_SIZE, "%d %d\n", max_baseline, min_baseline);
+	ret = sysfs_emit(buf, "%d %d\n", max_baseline, min_baseline);
 
 out:
 	return ret;
diff --git a/drivers/input/mouse/cyapa_gen5.c b/drivers/input/mouse/cyapa_gen5.c
index abf42f77b4c59..2e6bcb07257ed 100644
--- a/drivers/input/mouse/cyapa_gen5.c
+++ b/drivers/input/mouse/cyapa_gen5.c
@@ -2418,12 +2418,12 @@ resume_scanning:
 		return resume_error ? resume_error : error;
 
 	/* 12. Output data strings */
-	size = scnprintf(buf, PAGE_SIZE, "%d %d %d %d %d %d %d %d %d %d %d ",
+	size = sysfs_emit(buf, "%d %d %d %d %d %d %d %d %d %d %d ",
 		gidac_mutual_min, gidac_mutual_max, gidac_mutual_ave,
 		lidac_mutual_min, lidac_mutual_max, lidac_mutual_ave,
 		gidac_self_rx, gidac_self_tx,
 		lidac_self_min, lidac_self_max, lidac_self_ave);
-	size += scnprintf(buf + size, PAGE_SIZE - size,
+	size += sysfs_emit_at(buf, size,
 		"%d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d %d\n",
 		raw_cap_mutual_min, raw_cap_mutual_max, raw_cap_mutual_ave,
 		raw_cap_self_min, raw_cap_self_max, raw_cap_self_ave,
diff --git a/drivers/input/mouse/cyapa_gen6.c b/drivers/input/mouse/cyapa_gen6.c
index 0caaf3e64215d..4ffe08fee10c8 100644
--- a/drivers/input/mouse/cyapa_gen6.c
+++ b/drivers/input/mouse/cyapa_gen6.c
@@ -629,14 +629,14 @@ static ssize_t cyapa_gen6_show_baseline(struct device *dev,
 	if (error)
 		goto resume_scanning;
 
-	size = scnprintf(buf, PAGE_SIZE, "%d %d %d %d %d %d ",
-			data[0],  /* RX Attenuator Mutual */
-			data[1],  /* IDAC Mutual */
-			data[2],  /* RX Attenuator Self RX */
-			data[3],  /* IDAC Self RX */
-			data[4],  /* RX Attenuator Self TX */
-			data[5]	  /* IDAC Self TX */
-			);
+	size = sysfs_emit(buf, "%d %d %d %d %d %d ",
+			  data[0],  /* RX Attenuator Mutual */
+			  data[1],  /* IDAC Mutual */
+			  data[2],  /* RX Attenuator Self RX */
+			  data[3],  /* IDAC Self RX */
+			  data[4],  /* RX Attenuator Self TX */
+			  data[5]   /* IDAC Self TX */
+			 );
 
 	/* 3. Read Attenuator Trim. */
 	data_len = sizeof(data);
@@ -648,8 +648,8 @@ static ssize_t cyapa_gen6_show_baseline(struct device *dev,
 
 	/* set attenuator trim values. */
 	for (i = 0; i < data_len; i++)
-		size += scnprintf(buf + size, PAGE_SIZE - size,	"%d ", data[i]);
-	size += scnprintf(buf + size, PAGE_SIZE - size, "\n");
+		size += sysfs_emit_at(buf, size, "%d ", data[i]);
+	size += sysfs_emit_at(buf, size, "\n");
 
 resume_scanning:
 	/* 4. Resume Scanning*/
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 148a601396f92..8a72c200ccb5d 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -572,7 +572,7 @@ static ssize_t elan_sysfs_read_fw_checksum(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "0x%04x\n", data->fw_checksum);
+	return sysfs_emit(buf, "0x%04x\n", data->fw_checksum);
 }
 
 static ssize_t elan_sysfs_read_product_id(struct device *dev,
@@ -582,8 +582,8 @@ static ssize_t elan_sysfs_read_product_id(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, ETP_PRODUCT_ID_FORMAT_STRING "\n",
-		       data->product_id);
+	return sysfs_emit(buf, ETP_PRODUCT_ID_FORMAT_STRING "\n",
+			  data->product_id);
 }
 
 static ssize_t elan_sysfs_read_fw_ver(struct device *dev,
@@ -593,7 +593,7 @@ static ssize_t elan_sysfs_read_fw_ver(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "%d.0\n", data->fw_version);
+	return sysfs_emit(buf, "%d.0\n", data->fw_version);
 }
 
 static ssize_t elan_sysfs_read_sm_ver(struct device *dev,
@@ -603,7 +603,7 @@ static ssize_t elan_sysfs_read_sm_ver(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "%d.0\n", data->sm_version);
+	return sysfs_emit(buf, "%d.0\n", data->sm_version);
 }
 
 static ssize_t elan_sysfs_read_iap_ver(struct device *dev,
@@ -613,7 +613,7 @@ static ssize_t elan_sysfs_read_iap_ver(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "%d.0\n", data->iap_version);
+	return sysfs_emit(buf, "%d.0\n", data->iap_version);
 }
 
 static ssize_t elan_sysfs_update_fw(struct device *dev,
@@ -754,7 +754,7 @@ static ssize_t elan_sysfs_read_mode(struct device *dev,
 	if (error)
 		return error;
 
-	return sprintf(buf, "%d\n", (int)mode);
+	return sysfs_emit(buf, "%d\n", (int)mode);
 }
 
 static DEVICE_ATTR(product_id, S_IRUGO, elan_sysfs_read_product_id, NULL);
@@ -858,7 +858,7 @@ static ssize_t min_show(struct device *dev,
 		goto out;
 	}
 
-	retval = snprintf(buf, PAGE_SIZE, "%d", data->min_baseline);
+	retval = sysfs_emit(buf, "%d", data->min_baseline);
 
 out:
 	mutex_unlock(&data->sysfs_mutex);
@@ -881,7 +881,7 @@ static ssize_t max_show(struct device *dev,
 		goto out;
 	}
 
-	retval = snprintf(buf, PAGE_SIZE, "%d", data->max_baseline);
+	retval = sysfs_emit(buf, "%d", data->max_baseline);
 
 out:
 	mutex_unlock(&data->sysfs_mutex);
-- 
GitLab


From e50389f208daf1d60810e789b8860063e3256693 Mon Sep 17 00:00:00 2001
From: ye xingchen <ye.xingchen@zte.com.cn>
Date: Tue, 12 Dec 2023 21:53:40 -0800
Subject: [PATCH 1273/4076] =?UTF-8?q?Input:=20touchscreen=20-=20use=20sysf?=
 =?UTF-8?q?s=5Femit[=5Fat]()=20instead=20of=C2=A0scnprintf()?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Follow the advice of the Documentation/filesystems/sysfs.rst and show()
should only use sysfs_emit() or sysfs_emit_at() when formatting the
value to be returned to user space.

Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Oliver Graute <oliver.graute@kococonnector.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/atmel_mxt_ts.c   | 21 +++++++++------------
 drivers/input/touchscreen/edt-ft5x06.c     |  2 +-
 drivers/input/touchscreen/hideep.c         |  6 ++----
 drivers/input/touchscreen/hycon-hy46xx.c   |  2 +-
 drivers/input/touchscreen/ilitek_ts_i2c.c  | 16 ++++++++--------
 drivers/input/touchscreen/iqs5xx.c         | 12 ++++++------
 drivers/input/touchscreen/iqs7211.c        | 12 ++++++------
 drivers/input/touchscreen/melfas_mip4.c    | 16 ++++++++--------
 drivers/input/touchscreen/usbtouchscreen.c |  4 ++--
 drivers/input/touchscreen/wdt87xx_i2c.c    |  6 +++---
 10 files changed, 46 insertions(+), 51 deletions(-)

diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index 20094b9899f09..05dcacf7061b2 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -2818,8 +2818,8 @@ static ssize_t mxt_fw_version_show(struct device *dev,
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
 	struct mxt_info *info = data->info;
-	return scnprintf(buf, PAGE_SIZE, "%u.%u.%02X\n",
-			 info->version >> 4, info->version & 0xf, info->build);
+	return sysfs_emit(buf, "%u.%u.%02X\n",
+			  info->version >> 4, info->version & 0xf, info->build);
 }
 
 /* Hardware Version is returned as FamilyID.VariantID */
@@ -2828,8 +2828,7 @@ static ssize_t mxt_hw_version_show(struct device *dev,
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
 	struct mxt_info *info = data->info;
-	return scnprintf(buf, PAGE_SIZE, "%u.%u\n",
-			 info->family_id, info->variant_id);
+	return sysfs_emit(buf, "%u.%u\n", info->family_id, info->variant_id);
 }
 
 static ssize_t mxt_show_instance(char *buf, int count,
@@ -2839,19 +2838,18 @@ static ssize_t mxt_show_instance(char *buf, int count,
 	int i;
 
 	if (mxt_obj_instances(object) > 1)
-		count += scnprintf(buf + count, PAGE_SIZE - count,
-				   "Instance %u\n", instance);
+		count += sysfs_emit_at(buf, count, "Instance %u\n", instance);
 
 	for (i = 0; i < mxt_obj_size(object); i++)
-		count += scnprintf(buf + count, PAGE_SIZE - count,
-				"\t[%2u]: %02x (%d)\n", i, val[i], val[i]);
-	count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
+		count += sysfs_emit_at(buf, count, "\t[%2u]: %02x (%d)\n",
+				       i, val[i], val[i]);
+	count += sysfs_emit_at(buf, count, "\n");
 
 	return count;
 }
 
 static ssize_t mxt_object_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
+			       struct device_attribute *attr, char *buf)
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
 	struct mxt_object *object;
@@ -2872,8 +2870,7 @@ static ssize_t mxt_object_show(struct device *dev,
 		if (!mxt_object_readable(object->type))
 			continue;
 
-		count += scnprintf(buf + count, PAGE_SIZE - count,
-				"T%u:\n", object->type);
+		count += sysfs_emit_at(buf, count, "T%u:\n", object->type);
 
 		for (j = 0; j < mxt_obj_instances(object); j++) {
 			u16 size = mxt_obj_size(object);
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 3e102bcc4a1c7..2a1db11344766 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -431,7 +431,7 @@ static ssize_t edt_ft5x06_setting_show(struct device *dev,
 		*field = val;
 	}
 
-	count = scnprintf(buf, PAGE_SIZE, "%d\n", val);
+	count = sysfs_emit(buf, "%d\n", val);
 out:
 	mutex_unlock(&tsdata->mutex);
 	return error ?: count;
diff --git a/drivers/input/touchscreen/hideep.c b/drivers/input/touchscreen/hideep.c
index 0f58258306bfc..eae90676f4e55 100644
--- a/drivers/input/touchscreen/hideep.c
+++ b/drivers/input/touchscreen/hideep.c
@@ -928,8 +928,7 @@ static ssize_t hideep_fw_version_show(struct device *dev,
 	ssize_t len;
 
 	mutex_lock(&ts->dev_mutex);
-	len = scnprintf(buf, PAGE_SIZE, "%04x\n",
-			be16_to_cpu(ts->dwz_info.release_ver));
+	len = sysfs_emit(buf, "%04x\n", be16_to_cpu(ts->dwz_info.release_ver));
 	mutex_unlock(&ts->dev_mutex);
 
 	return len;
@@ -943,8 +942,7 @@ static ssize_t hideep_product_id_show(struct device *dev,
 	ssize_t len;
 
 	mutex_lock(&ts->dev_mutex);
-	len = scnprintf(buf, PAGE_SIZE, "%04x\n",
-			be16_to_cpu(ts->dwz_info.product_id));
+	len = sysfs_emit(buf, "%04x\n", be16_to_cpu(ts->dwz_info.product_id));
 	mutex_unlock(&ts->dev_mutex);
 
 	return len;
diff --git a/drivers/input/touchscreen/hycon-hy46xx.c b/drivers/input/touchscreen/hycon-hy46xx.c
index d0f257989fd6b..2e01d87977c16 100644
--- a/drivers/input/touchscreen/hycon-hy46xx.c
+++ b/drivers/input/touchscreen/hycon-hy46xx.c
@@ -202,7 +202,7 @@ static ssize_t hycon_hy46xx_setting_show(struct device *dev,
 		*field = val;
 	}
 
-	count = scnprintf(buf, PAGE_SIZE, "%d\n", val);
+	count = sysfs_emit(buf, "%d\n", val);
 
 out:
 	mutex_unlock(&tsdata->mutex);
diff --git a/drivers/input/touchscreen/ilitek_ts_i2c.c b/drivers/input/touchscreen/ilitek_ts_i2c.c
index 90c4934e750a3..fc4e39b6651a4 100644
--- a/drivers/input/touchscreen/ilitek_ts_i2c.c
+++ b/drivers/input/touchscreen/ilitek_ts_i2c.c
@@ -512,12 +512,12 @@ static ssize_t firmware_version_show(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct ilitek_ts_data *ts = i2c_get_clientdata(client);
 
-	return scnprintf(buf, PAGE_SIZE,
-			 "fw version: [%02X%02X.%02X%02X.%02X%02X.%02X%02X]\n",
-			 ts->firmware_ver[0], ts->firmware_ver[1],
-			 ts->firmware_ver[2], ts->firmware_ver[3],
-			 ts->firmware_ver[4], ts->firmware_ver[5],
-			 ts->firmware_ver[6], ts->firmware_ver[7]);
+	return sysfs_emit(buf,
+			  "fw version: [%02X%02X.%02X%02X.%02X%02X.%02X%02X]\n",
+			  ts->firmware_ver[0], ts->firmware_ver[1],
+			  ts->firmware_ver[2], ts->firmware_ver[3],
+			  ts->firmware_ver[4], ts->firmware_ver[5],
+			  ts->firmware_ver[6], ts->firmware_ver[7]);
 }
 static DEVICE_ATTR_RO(firmware_version);
 
@@ -527,8 +527,8 @@ static ssize_t product_id_show(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct ilitek_ts_data *ts = i2c_get_clientdata(client);
 
-	return scnprintf(buf, PAGE_SIZE, "product id: [%04X], module: [%s]\n",
-			 ts->mcu_ver, ts->product_id);
+	return sysfs_emit(buf, "product id: [%04X], module: [%s]\n",
+			  ts->mcu_ver, ts->product_id);
 }
 static DEVICE_ATTR_RO(product_id);
 
diff --git a/drivers/input/touchscreen/iqs5xx.c b/drivers/input/touchscreen/iqs5xx.c
index a3f4fb85bee58..4d226118f3cc2 100644
--- a/drivers/input/touchscreen/iqs5xx.c
+++ b/drivers/input/touchscreen/iqs5xx.c
@@ -943,12 +943,12 @@ static ssize_t fw_info_show(struct device *dev,
 	if (!iqs5xx->dev_id_info.bl_status)
 		return -ENODATA;
 
-	return scnprintf(buf, PAGE_SIZE, "%u.%u.%u.%u:%u.%u\n",
-			 be16_to_cpu(iqs5xx->dev_id_info.prod_num),
-			 be16_to_cpu(iqs5xx->dev_id_info.proj_num),
-			 iqs5xx->dev_id_info.major_ver,
-			 iqs5xx->dev_id_info.minor_ver,
-			 iqs5xx->exp_file[0], iqs5xx->exp_file[1]);
+	return sysfs_emit(buf, "%u.%u.%u.%u:%u.%u\n",
+			  be16_to_cpu(iqs5xx->dev_id_info.prod_num),
+			  be16_to_cpu(iqs5xx->dev_id_info.proj_num),
+			  iqs5xx->dev_id_info.major_ver,
+			  iqs5xx->dev_id_info.minor_ver,
+			  iqs5xx->exp_file[0], iqs5xx->exp_file[1]);
 }
 
 static DEVICE_ATTR_WO(fw_file);
diff --git a/drivers/input/touchscreen/iqs7211.c b/drivers/input/touchscreen/iqs7211.c
index dc084f8737620..f0a56cde899e4 100644
--- a/drivers/input/touchscreen/iqs7211.c
+++ b/drivers/input/touchscreen/iqs7211.c
@@ -2401,12 +2401,12 @@ static ssize_t fw_info_show(struct device *dev,
 {
 	struct iqs7211_private *iqs7211 = dev_get_drvdata(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u.%u.%u.%u:%u.%u\n",
-			 le16_to_cpu(iqs7211->ver_info.prod_num),
-			 le32_to_cpu(iqs7211->ver_info.patch),
-			 le16_to_cpu(iqs7211->ver_info.major),
-			 le16_to_cpu(iqs7211->ver_info.minor),
-			 iqs7211->exp_file[1], iqs7211->exp_file[0]);
+	return sysfs_emit(buf, "%u.%u.%u.%u:%u.%u\n",
+			  le16_to_cpu(iqs7211->ver_info.prod_num),
+			  le32_to_cpu(iqs7211->ver_info.patch),
+			  le16_to_cpu(iqs7211->ver_info.major),
+			  le16_to_cpu(iqs7211->ver_info.minor),
+			  iqs7211->exp_file[1], iqs7211->exp_file[0]);
 }
 
 static DEVICE_ATTR_RO(fw_info);
diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c
index aa325486f6182..78e1c63e530e0 100644
--- a/drivers/input/touchscreen/melfas_mip4.c
+++ b/drivers/input/touchscreen/melfas_mip4.c
@@ -1336,9 +1336,9 @@ static ssize_t mip4_sysfs_read_fw_version(struct device *dev,
 	/* Take lock to prevent racing with firmware update */
 	mutex_lock(&ts->input->mutex);
 
-	count = snprintf(buf, PAGE_SIZE, "%04X %04X %04X %04X\n",
-			 ts->fw_version.boot, ts->fw_version.core,
-			 ts->fw_version.app, ts->fw_version.param);
+	count = sysfs_emit(buf, "%04X %04X %04X %04X\n",
+			   ts->fw_version.boot, ts->fw_version.core,
+			   ts->fw_version.app, ts->fw_version.param);
 
 	mutex_unlock(&ts->input->mutex);
 
@@ -1362,8 +1362,8 @@ static ssize_t mip4_sysfs_read_hw_version(struct device *dev,
 	 * product_name shows the name or version of the hardware
 	 * paired with current firmware in the chip.
 	 */
-	count = snprintf(buf, PAGE_SIZE, "%.*s\n",
-			 (int)sizeof(ts->product_name), ts->product_name);
+	count = sysfs_emit(buf, "%.*s\n",
+			   (int)sizeof(ts->product_name), ts->product_name);
 
 	mutex_unlock(&ts->input->mutex);
 
@@ -1382,7 +1382,7 @@ static ssize_t mip4_sysfs_read_product_id(struct device *dev,
 
 	mutex_lock(&ts->input->mutex);
 
-	count = snprintf(buf, PAGE_SIZE, "%04X\n", ts->product_id);
+	count = sysfs_emit(buf, "%04X\n", ts->product_id);
 
 	mutex_unlock(&ts->input->mutex);
 
@@ -1401,8 +1401,8 @@ static ssize_t mip4_sysfs_read_ic_name(struct device *dev,
 
 	mutex_lock(&ts->input->mutex);
 
-	count = snprintf(buf, PAGE_SIZE, "%.*s\n",
-			 (int)sizeof(ts->ic_name), ts->ic_name);
+	count = sysfs_emit(buf, "%.*s\n",
+			   (int)sizeof(ts->ic_name), ts->ic_name);
 
 	mutex_unlock(&ts->input->mutex);
 
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index d6d04b9f04fc1..60354ebc72424 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -456,8 +456,8 @@ static ssize_t mtouch_firmware_rev_show(struct device *dev,
 	struct usbtouch_usb *usbtouch = usb_get_intfdata(intf);
 	struct mtouch_priv *priv = usbtouch->priv;
 
-	return scnprintf(output, PAGE_SIZE, "%1x.%1x\n",
-			 priv->fw_rev_major, priv->fw_rev_minor);
+	return sysfs_emit(output, "%1x.%1x\n",
+			  priv->fw_rev_major, priv->fw_rev_minor);
 }
 static DEVICE_ATTR(firmware_rev, 0444, mtouch_firmware_rev_show, NULL);
 
diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c
index 128341a6696bc..32c7be54434cf 100644
--- a/drivers/input/touchscreen/wdt87xx_i2c.c
+++ b/drivers/input/touchscreen/wdt87xx_i2c.c
@@ -887,7 +887,7 @@ static ssize_t config_csum_show(struct device *dev,
 	cfg_csum = wdt->param.xmls_id1;
 	cfg_csum = (cfg_csum << 16) | wdt->param.xmls_id2;
 
-	return scnprintf(buf, PAGE_SIZE, "%x\n", cfg_csum);
+	return sysfs_emit(buf, "%x\n", cfg_csum);
 }
 
 static ssize_t fw_version_show(struct device *dev,
@@ -896,7 +896,7 @@ static ssize_t fw_version_show(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct wdt87xx_data *wdt = i2c_get_clientdata(client);
 
-	return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.fw_id);
+	return sysfs_emit(buf, "%x\n", wdt->param.fw_id);
 }
 
 static ssize_t plat_id_show(struct device *dev,
@@ -905,7 +905,7 @@ static ssize_t plat_id_show(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct wdt87xx_data *wdt = i2c_get_clientdata(client);
 
-	return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.plat_id);
+	return sysfs_emit(buf, "%x\n", wdt->param.plat_id);
 }
 
 static ssize_t update_config_store(struct device *dev,
-- 
GitLab


From 8fbdb8fb36c68a00555a1a2593c6fff1244a65b3 Mon Sep 17 00:00:00 2001
From: ye xingchen <ye.xingchen@zte.com.cn>
Date: Tue, 12 Dec 2023 22:31:44 -0800
Subject: [PATCH 1274/4076] Input: synaptics-rmi4 - use sysfs_emit() to instead
 of scnprintf()

Replace calls to scnprintf() in the methods showing device attributes
with sysfs_emit() to simplify the code.

Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Link: https://lore.kernel.org/r/202212011551429834598@zte.com.cn
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/rmi4/rmi_f01.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/input/rmi4/rmi_f01.c b/drivers/input/rmi4/rmi_f01.c
index d7603c50f864b..cc1d4b424640e 100644
--- a/drivers/input/rmi4/rmi_f01.c
+++ b/drivers/input/rmi4/rmi_f01.c
@@ -267,8 +267,7 @@ static ssize_t rmi_driver_manufacturer_id_show(struct device *dev,
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n",
-			 f01->properties.manufacturer_id);
+	return sysfs_emit(buf, "%d\n", f01->properties.manufacturer_id);
 }
 
 static DEVICE_ATTR(manufacturer_id, 0444,
@@ -280,7 +279,7 @@ static ssize_t rmi_driver_dom_show(struct device *dev,
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%s\n", f01->properties.dom);
+	return sysfs_emit(buf, "%s\n", f01->properties.dom);
 }
 
 static DEVICE_ATTR(date_of_manufacture, 0444, rmi_driver_dom_show, NULL);
@@ -292,7 +291,7 @@ static ssize_t rmi_driver_product_id_show(struct device *dev,
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%s\n", f01->properties.product_id);
+	return sysfs_emit(buf, "%s\n", f01->properties.product_id);
 }
 
 static DEVICE_ATTR(product_id, 0444, rmi_driver_product_id_show, NULL);
@@ -304,7 +303,7 @@ static ssize_t rmi_driver_firmware_id_show(struct device *dev,
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
 	struct f01_data *f01 = dev_get_drvdata(&data->f01_container->dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", f01->properties.firmware_id);
+	return sysfs_emit(buf, "%d\n", f01->properties.firmware_id);
 }
 
 static DEVICE_ATTR(firmware_id, 0444, rmi_driver_firmware_id_show, NULL);
@@ -318,8 +317,8 @@ static ssize_t rmi_driver_package_id_show(struct device *dev,
 
 	u32 package_id = f01->properties.package_id;
 
-	return scnprintf(buf, PAGE_SIZE, "%04x.%04x\n",
-			 package_id & 0xffff, (package_id >> 16) & 0xffff);
+	return sysfs_emit(buf, "%04x.%04x\n",
+			  package_id & 0xffff, (package_id >> 16) & 0xffff);
 }
 
 static DEVICE_ATTR(package_id, 0444, rmi_driver_package_id_show, NULL);
-- 
GitLab


From 3e39104ba81dc8738c3706b55f737db5da4dbbfd Mon Sep 17 00:00:00 2001
From: ye xingchen <ye.xingchen@zte.com.cn>
Date: Tue, 12 Dec 2023 22:21:11 -0800
Subject: [PATCH 1275/4076] Input: ims-pcu - use sysfs_emit() instead of
 scnprintf()

Replace calls to scnprintf() in the methods showing device attributes
with sysfs_emit() to simplify the code.

Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Link: https://lore.kernel.org/r/202212011548387254492@zte.com.cn
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/ims-pcu.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index b2f1292e27ef7..6e8cc28debd97 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -1050,7 +1050,7 @@ static ssize_t ims_pcu_attribute_show(struct device *dev,
 			container_of(dattr, struct ims_pcu_attribute, dattr);
 	char *field = (char *)pcu + attr->field_offset;
 
-	return scnprintf(buf, PAGE_SIZE, "%.*s\n", attr->field_length, field);
+	return sysfs_emit(buf, "%.*s\n", attr->field_length, field);
 }
 
 static ssize_t ims_pcu_attribute_store(struct device *dev,
@@ -1206,7 +1206,7 @@ ims_pcu_update_firmware_status_show(struct device *dev,
 	struct usb_interface *intf = to_usb_interface(dev);
 	struct ims_pcu *pcu = usb_get_intfdata(intf);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", pcu->update_firmware_status);
+	return sysfs_emit(buf, "%d\n", pcu->update_firmware_status);
 }
 
 static DEVICE_ATTR(update_firmware_status, S_IRUGO,
@@ -1309,7 +1309,7 @@ static ssize_t ims_pcu_ofn_reg_data_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%x\n", data);
+	return sysfs_emit(buf, "%x\n", data);
 }
 
 static ssize_t ims_pcu_ofn_reg_data_store(struct device *dev,
@@ -1344,7 +1344,7 @@ static ssize_t ims_pcu_ofn_reg_addr_show(struct device *dev,
 	int error;
 
 	mutex_lock(&pcu->cmd_mutex);
-	error = scnprintf(buf, PAGE_SIZE, "%x\n", pcu->ofn_reg_addr);
+	error = sysfs_emit(buf, "%x\n", pcu->ofn_reg_addr);
 	mutex_unlock(&pcu->cmd_mutex);
 
 	return error;
@@ -1397,7 +1397,7 @@ static ssize_t ims_pcu_ofn_bit_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", !!(data & (1 << attr->nr)));
+	return sysfs_emit(buf, "%d\n", !!(data & (1 << attr->nr)));
 }
 
 static ssize_t ims_pcu_ofn_bit_store(struct device *dev,
-- 
GitLab


From 7c73226525702e89aad9fe4c4683826ed5e24361 Mon Sep 17 00:00:00 2001
From: ye xingchen <ye.xingchen@zte.com.cn>
Date: Tue, 12 Dec 2023 22:28:54 -0800
Subject: [PATCH 1276/4076] Input: iqs269a - use sysfs_emit() instead of
 scnprintf()

Replace calls to scnprintf() in the methods showing device attributes
with sysfs_emit() to simplify the code.

Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Link: https://lore.kernel.org/r/202212011548387254492@zte.com.cn
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs269a.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c
index 3c636c75e8a1f..1abce35b955e4 100644
--- a/drivers/input/misc/iqs269a.c
+++ b/drivers/input/misc/iqs269a.c
@@ -1286,7 +1286,7 @@ static ssize_t counts_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", le16_to_cpu(counts));
+	return sysfs_emit(buf, "%u\n", le16_to_cpu(counts));
 }
 
 static ssize_t hall_bin_show(struct device *dev,
@@ -1324,7 +1324,7 @@ static ssize_t hall_bin_show(struct device *dev,
 		return -EINVAL;
 	}
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+	return sysfs_emit(buf, "%u\n", val);
 }
 
 static ssize_t hall_enable_show(struct device *dev,
@@ -1332,7 +1332,7 @@ static ssize_t hall_enable_show(struct device *dev,
 {
 	struct iqs269_private *iqs269 = dev_get_drvdata(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", iqs269->hall_enable);
+	return sysfs_emit(buf, "%u\n", iqs269->hall_enable);
 }
 
 static ssize_t hall_enable_store(struct device *dev,
@@ -1362,7 +1362,7 @@ static ssize_t ch_number_show(struct device *dev,
 {
 	struct iqs269_private *iqs269 = dev_get_drvdata(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", iqs269->ch_num);
+	return sysfs_emit(buf, "%u\n", iqs269->ch_num);
 }
 
 static ssize_t ch_number_store(struct device *dev,
@@ -1391,8 +1391,7 @@ static ssize_t rx_enable_show(struct device *dev,
 	struct iqs269_private *iqs269 = dev_get_drvdata(dev);
 	struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			 ch_reg[iqs269->ch_num].rx_enable);
+	return sysfs_emit(buf, "%u\n", ch_reg[iqs269->ch_num].rx_enable);
 }
 
 static ssize_t rx_enable_store(struct device *dev,
@@ -1432,7 +1431,7 @@ static ssize_t ati_mode_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+	return sysfs_emit(buf, "%u\n", val);
 }
 
 static ssize_t ati_mode_store(struct device *dev,
@@ -1465,7 +1464,7 @@ static ssize_t ati_base_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+	return sysfs_emit(buf, "%u\n", val);
 }
 
 static ssize_t ati_base_store(struct device *dev,
@@ -1498,7 +1497,7 @@ static ssize_t ati_target_show(struct device *dev,
 	if (error)
 		return error;
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+	return sysfs_emit(buf, "%u\n", val);
 }
 
 static ssize_t ati_target_store(struct device *dev,
@@ -1525,9 +1524,9 @@ static ssize_t ati_trigger_show(struct device *dev,
 {
 	struct iqs269_private *iqs269 = dev_get_drvdata(dev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			 iqs269->ati_current &&
-			 completion_done(&iqs269->ati_done));
+	return sysfs_emit(buf, "%u\n",
+			  iqs269->ati_current &&
+			  completion_done(&iqs269->ati_done));
 }
 
 static ssize_t ati_trigger_store(struct device *dev,
-- 
GitLab


From 51835758e8a9ce089c47358ea373de82309234de Mon Sep 17 00:00:00 2001
From: ye xingchen <ye.xingchen@zte.com.cn>
Date: Tue, 12 Dec 2023 22:41:50 -0800
Subject: [PATCH 1277/4076] Input: vivaldi - convert to use sysfs_emit_at() API

Follow the advice of the Documentation/filesystems/sysfs.rst and show()
should only use sysfs_emit() or sysfs_emit_at() when formatting the
value to be returned to user space.

Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Link: https://lore.kernel.org/r/202212071644171074630@zte.com.cn
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/vivaldi-fmap.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/input/vivaldi-fmap.c b/drivers/input/vivaldi-fmap.c
index 6dae83d968067..0d29ec014e2f9 100644
--- a/drivers/input/vivaldi-fmap.c
+++ b/drivers/input/vivaldi-fmap.c
@@ -27,10 +27,10 @@ ssize_t vivaldi_function_row_physmap_show(const struct vivaldi_data *data,
 		return 0;
 
 	for (i = 0; i < data->num_function_row_keys; i++)
-		size += scnprintf(buf + size, PAGE_SIZE - size,
-				  "%s%02X", size ? " " : "", physmap[i]);
+		size += sysfs_emit_at(buf, size,
+				      "%s%02X", size ? " " : "", physmap[i]);
 	if (size)
-		size += scnprintf(buf + size, PAGE_SIZE - size, "\n");
+		size += sysfs_emit_at(buf, size, "\n");
 
 	return size;
 }
-- 
GitLab


From 6caa290684255991ffeebf228b2fd9e7e4da8f34 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 12 Dec 2023 23:02:56 -0800
Subject: [PATCH 1278/4076] Input: navpoint - convert to use GPIO descriptor

The Navpoint driver uses a GPIO line, convert this to use
a GPIO descriptor. There are no in-kernel users but out of tree
users can easily be added or converted using a GPIO descriptor
table as with numerous other drivers.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231129-descriptors-input-v1-1-9433162914a3@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/navpoint.c | 41 +++++++++++++---------------------
 include/linux/input/navpoint.h |  1 -
 2 files changed, 15 insertions(+), 27 deletions(-)

diff --git a/drivers/input/mouse/navpoint.c b/drivers/input/mouse/navpoint.c
index c00dc1275da23..ba757783c258a 100644
--- a/drivers/input/mouse/navpoint.c
+++ b/drivers/input/mouse/navpoint.c
@@ -10,7 +10,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/input.h>
 #include <linux/input/navpoint.h>
 #include <linux/interrupt.h>
@@ -32,7 +32,7 @@ struct navpoint {
 	struct ssp_device	*ssp;
 	struct input_dev	*input;
 	struct device		*dev;
-	int			gpio;
+	struct gpio_desc	*gpiod;
 	int			index;
 	u8			data[1 + HEADER_LENGTH(0xff)];
 };
@@ -170,16 +170,14 @@ static void navpoint_up(struct navpoint *navpoint)
 		dev_err(navpoint->dev,
 			"timeout waiting for SSSR[CSS] to clear\n");
 
-	if (gpio_is_valid(navpoint->gpio))
-		gpio_set_value(navpoint->gpio, 1);
+	gpiod_set_value(navpoint->gpiod, 1);
 }
 
 static void navpoint_down(struct navpoint *navpoint)
 {
 	struct ssp_device *ssp = navpoint->ssp;
 
-	if (gpio_is_valid(navpoint->gpio))
-		gpio_set_value(navpoint->gpio, 0);
+	gpiod_set_value(navpoint->gpiod, 0);
 
 	pxa_ssp_write_reg(ssp, SSCR0, 0);
 
@@ -216,18 +214,9 @@ static int navpoint_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (gpio_is_valid(pdata->gpio)) {
-		error = gpio_request_one(pdata->gpio, GPIOF_OUT_INIT_LOW,
-					 "SYNAPTICS_ON");
-		if (error)
-			return error;
-	}
-
 	ssp = pxa_ssp_request(pdata->port, pdev->name);
-	if (!ssp) {
-		error = -ENODEV;
-		goto err_free_gpio;
-	}
+	if (!ssp)
+		return -ENODEV;
 
 	/* HaRET does not disable devices before jumping into Linux */
 	if (pxa_ssp_read_reg(ssp, SSCR0) & SSCR0_SSE) {
@@ -242,10 +231,18 @@ static int navpoint_probe(struct platform_device *pdev)
 		goto err_free_mem;
 	}
 
+	navpoint->gpiod = gpiod_get_optional(&pdev->dev,
+					     NULL, GPIOD_OUT_LOW);
+	if (IS_ERR(navpoint->gpiod)) {
+		error = PTR_ERR(navpoint->gpiod);
+		dev_err(&pdev->dev, "error getting GPIO\n");
+		goto err_free_mem;
+	}
+	gpiod_set_consumer_name(navpoint->gpiod, "SYNAPTICS_ON");
+
 	navpoint->ssp = ssp;
 	navpoint->input = input;
 	navpoint->dev = &pdev->dev;
-	navpoint->gpio = pdata->gpio;
 
 	input->name = pdev->name;
 	input->dev.parent = &pdev->dev;
@@ -288,17 +285,12 @@ err_free_mem:
 	input_free_device(input);
 	kfree(navpoint);
 	pxa_ssp_free(ssp);
-err_free_gpio:
-	if (gpio_is_valid(pdata->gpio))
-		gpio_free(pdata->gpio);
 
 	return error;
 }
 
 static void navpoint_remove(struct platform_device *pdev)
 {
-	const struct navpoint_platform_data *pdata =
-					dev_get_platdata(&pdev->dev);
 	struct navpoint *navpoint = platform_get_drvdata(pdev);
 	struct ssp_device *ssp = navpoint->ssp;
 
@@ -308,9 +300,6 @@ static void navpoint_remove(struct platform_device *pdev)
 	kfree(navpoint);
 
 	pxa_ssp_free(ssp);
-
-	if (gpio_is_valid(pdata->gpio))
-		gpio_free(pdata->gpio);
 }
 
 static int navpoint_suspend(struct device *dev)
diff --git a/include/linux/input/navpoint.h b/include/linux/input/navpoint.h
index d464ffb4db52b..5192ae3f5ec1b 100644
--- a/include/linux/input/navpoint.h
+++ b/include/linux/input/navpoint.h
@@ -5,5 +5,4 @@
 
 struct navpoint_platform_data {
 	int		port;		/* PXA SSP port for pxa_ssp_request() */
-	int		gpio;		/* GPIO for power on/off */
 };
-- 
GitLab


From 1ba05c92682fcc6d0ffb2fce5db68fb517278797 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 12 Dec 2023 23:04:35 -0800
Subject: [PATCH 1279/4076] Input: tca6416-keypad - drop unused include

The TCA6416 keypad driver is including the legacy GPIO
header <linux/gpio.h> for no reason, it is not using any
of its symbols. Drop the header.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231129-descriptors-input-v1-2-9433162914a3@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/tca6416-keypad.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index 8af59ced1ec2e..677bc4baa5d19 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -14,7 +14,6 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/workqueue.h>
-#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
 #include <linux/tca6416_keypad.h>
-- 
GitLab


From e53c18da99c75f080bd99436c57824f2ab657f03 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 12 Dec 2023 23:06:55 -0800
Subject: [PATCH 1280/4076] Input: omap-keypad - drop optional GPIO support

The driver supports passing some GPIO lines for rows and columns
through the driver data, but there is no in-kernel user of this.

Further the use seems convoluted because the GPIO lines are unused
in the driver, then explicitly free:ed when removing it without
being requested when probing it, which is assymetric and just
a recepie for disaster.

Remove the support for these unused GPIOs, if need be support can
be reestablished in an organized fashion using GPIO descriptors.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231129-descriptors-input-v1-3-9433162914a3@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/omap-keypad.c      | 19 +------------------
 include/linux/platform_data/keypad-omap.h |  3 ---
 2 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c
index 454fb86756573..16f936db73058 100644
--- a/drivers/input/keyboard/omap-keypad.c
+++ b/drivers/input/keyboard/omap-keypad.c
@@ -21,7 +21,6 @@
 #include <linux/mutex.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/gpio.h>
 #include <linux/platform_data/gpio-omap.h>
 #include <linux/platform_data/keypad-omap.h>
 #include <linux/soc/ti/omap1-io.h>
@@ -49,9 +48,6 @@ struct omap_kp {
 
 static DECLARE_TASKLET_DISABLED_OLD(kp_tasklet, omap_kp_tasklet);
 
-static unsigned int *row_gpios;
-static unsigned int *col_gpios;
-
 static irqreturn_t omap_kp_interrupt(int irq, void *dev_id)
 {
 	/* disable keyboard interrupt and schedule for handling */
@@ -180,7 +176,7 @@ static int omap_kp_probe(struct platform_device *pdev)
 	struct omap_kp *omap_kp;
 	struct input_dev *input_dev;
 	struct omap_kp_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	int i, col_idx, row_idx, ret;
+	int ret;
 	unsigned int row_shift, keycodemax;
 
 	if (!pdata->rows || !pdata->cols || !pdata->keymap_data) {
@@ -209,17 +205,9 @@ static int omap_kp_probe(struct platform_device *pdev)
 	if (pdata->delay)
 		omap_kp->delay = pdata->delay;
 
-	if (pdata->row_gpios && pdata->col_gpios) {
-		row_gpios = pdata->row_gpios;
-		col_gpios = pdata->col_gpios;
-	}
-
 	omap_kp->rows = pdata->rows;
 	omap_kp->cols = pdata->cols;
 
-	col_idx = 0;
-	row_idx = 0;
-
 	timer_setup(&omap_kp->timer, omap_kp_timer, 0);
 
 	/* get the irq and init timer*/
@@ -276,11 +264,6 @@ err4:
 err3:
 	device_remove_file(&pdev->dev, &dev_attr_enable);
 err2:
-	for (i = row_idx - 1; i >= 0; i--)
-		gpio_free(row_gpios[i]);
-	for (i = col_idx - 1; i >= 0; i--)
-		gpio_free(col_gpios[i]);
-
 	kfree(omap_kp);
 	input_free_device(input_dev);
 
diff --git a/include/linux/platform_data/keypad-omap.h b/include/linux/platform_data/keypad-omap.h
index 3e7c64c854f4c..f3f1311cdf3aa 100644
--- a/include/linux/platform_data/keypad-omap.h
+++ b/include/linux/platform_data/keypad-omap.h
@@ -19,9 +19,6 @@ struct omap_kp_platform_data {
 	bool rep;
 	unsigned long delay;
 	bool dbounce;
-	/* specific to OMAP242x*/
-	unsigned int *row_gpios;
-	unsigned int *col_gpios;
 };
 
 /* Group (0..3) -- when multiple keys are pressed, only the
-- 
GitLab


From 7395de647e87476f5b5d2f9a9fe80cee86b4e7cc Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 12 Dec 2023 23:04:47 -0800
Subject: [PATCH 1281/4076] Input: as5011 - convert to GPIO descriptor

This driver does not have any in-tree users but is passing a
legacy GPIO number through platform data.

Convert it to use a GPIO descriptor, new users or outoftree
users can easily be implemented using GPIO descriptor tables
or software nodes.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231129-descriptors-input-v1-4-9433162914a3@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/as5011.c | 24 +++++++++++-------------
 include/linux/input/as5011.h    |  1 -
 2 files changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/input/joystick/as5011.c b/drivers/input/joystick/as5011.c
index bf8b1cc0ea9c7..f1822c19a289d 100644
--- a/drivers/input/joystick/as5011.c
+++ b/drivers/input/joystick/as5011.c
@@ -13,7 +13,7 @@
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/input.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/delay.h>
 #include <linux/input/as5011.h>
 #include <linux/slab.h>
@@ -61,7 +61,7 @@ MODULE_LICENSE("GPL");
 struct as5011_device {
 	struct input_dev *input_dev;
 	struct i2c_client *i2c_client;
-	unsigned int button_gpio;
+	struct gpio_desc *button_gpiod;
 	unsigned int button_irq;
 	unsigned int axis_irq;
 };
@@ -114,7 +114,7 @@ static int as5011_i2c_read(struct i2c_client *client,
 static irqreturn_t as5011_button_interrupt(int irq, void *dev_id)
 {
 	struct as5011_device *as5011 = dev_id;
-	int val = gpio_get_value_cansleep(as5011->button_gpio);
+	int val = gpiod_get_value_cansleep(as5011->button_gpiod);
 
 	input_report_key(as5011->input_dev, BTN_JOYSTICK, !val);
 	input_sync(as5011->input_dev);
@@ -248,7 +248,6 @@ static int as5011_probe(struct i2c_client *client)
 
 	as5011->i2c_client = client;
 	as5011->input_dev = input_dev;
-	as5011->button_gpio = plat_data->button_gpio;
 	as5011->axis_irq = plat_data->axis_irq;
 
 	input_dev->name = "Austria Microsystem as5011 joystick";
@@ -262,18 +261,20 @@ static int as5011_probe(struct i2c_client *client)
 	input_set_abs_params(as5011->input_dev, ABS_Y,
 		AS5011_MIN_AXIS, AS5011_MAX_AXIS, AS5011_FUZZ, AS5011_FLAT);
 
-	error = gpio_request(as5011->button_gpio, "AS5011 button");
-	if (error < 0) {
-		dev_err(&client->dev, "Failed to request button gpio\n");
+	as5011->button_gpiod = devm_gpiod_get(&client->dev, NULL, GPIOD_IN);
+	if (IS_ERR(as5011->button_gpiod)) {
+		error = PTR_ERR(as5011->button_gpiod);
+		dev_err(&client->dev, "Failed to request button GPIO\n");
 		goto err_free_mem;
 	}
+	gpiod_set_consumer_name(as5011->button_gpiod, "AS5011 button");
 
-	irq = gpio_to_irq(as5011->button_gpio);
+	irq = gpiod_to_irq(as5011->button_gpiod);
 	if (irq < 0) {
 		dev_err(&client->dev,
 			"Failed to get irq number for button gpio\n");
 		error = irq;
-		goto err_free_button_gpio;
+		goto err_free_mem;
 	}
 
 	as5011->button_irq = irq;
@@ -286,7 +287,7 @@ static int as5011_probe(struct i2c_client *client)
 	if (error < 0) {
 		dev_err(&client->dev,
 			"Can't allocate button irq %d\n", as5011->button_irq);
-		goto err_free_button_gpio;
+		goto err_free_mem;
 	}
 
 	error = as5011_configure_chip(as5011, plat_data);
@@ -317,8 +318,6 @@ err_free_axis_irq:
 	free_irq(as5011->axis_irq, as5011);
 err_free_button_irq:
 	free_irq(as5011->button_irq, as5011);
-err_free_button_gpio:
-	gpio_free(as5011->button_gpio);
 err_free_mem:
 	input_free_device(input_dev);
 	kfree(as5011);
@@ -332,7 +331,6 @@ static void as5011_remove(struct i2c_client *client)
 
 	free_irq(as5011->axis_irq, as5011);
 	free_irq(as5011->button_irq, as5011);
-	gpio_free(as5011->button_gpio);
 
 	input_unregister_device(as5011->input_dev);
 	kfree(as5011);
diff --git a/include/linux/input/as5011.h b/include/linux/input/as5011.h
index 5fba52a56cd61..5705d5de3aeae 100644
--- a/include/linux/input/as5011.h
+++ b/include/linux/input/as5011.h
@@ -7,7 +7,6 @@
  */
 
 struct as5011_platform_data {
-	unsigned int button_gpio;
 	unsigned int axis_irq; /* irq number */
 	unsigned long axis_irqflags;
 	char xp, xn; /* threshold for x axis */
-- 
GitLab


From 987fdb5a43a66764808371b54e6047834170d565 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Fri, 1 Sep 2023 13:05:02 +0530
Subject: [PATCH 1282/4076] bus: mhi: ep: Do not allocate event ring element on
 stack

It is possible that the host controller driver would use DMA framework to
write the event ring element. So avoid allocating event ring element on the
stack as DMA cannot work on vmalloc memory.

Cc: stable@vger.kernel.org
Fixes: 961aeb689224 ("bus: mhi: ep: Add support for sending events to the host")
Link: https://lore.kernel.org/r/20230901073502.69385-1-manivannan.sadhasivam@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c | 68 ++++++++++++++++++++++++++++-----------
 1 file changed, 50 insertions(+), 18 deletions(-)

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 600881808982a..e2513f5f47a61 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -71,45 +71,77 @@ err_unlock:
 static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 					struct mhi_ring_element *tre, u32 len, enum mhi_ev_ccs code)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
 
-	event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre));
-	event.dword[0] = MHI_TRE_EV_DWORD0(code, len);
-	event.dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
+	event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre));
+	event->dword[0] = MHI_TRE_EV_DWORD0(code, len);
+	event->dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, ring->er_index, &event, MHI_TRE_DATA_GET_BEI(tre));
+	ret = mhi_ep_send_event(mhi_cntrl, ring->er_index, event, MHI_TRE_DATA_GET_BEI(tre));
+	kfree(event);
+
+	return ret;
 }
 
 int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state state)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
 
-	event.dword[0] = MHI_SC_EV_DWORD0(state);
-	event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
+	event->dword[0] = MHI_SC_EV_DWORD0(state);
+	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kfree(event);
+
+	return ret;
 }
 
 int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_env)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
 
-	event.dword[0] = MHI_EE_EV_DWORD0(exec_env);
-	event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
+	event->dword[0] = MHI_EE_EV_DWORD0(exec_env);
+	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kfree(event);
+
+	return ret;
 }
 
 static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ev_ccs code)
 {
 	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_cmd->ring;
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
 
-	event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element));
-	event.dword[0] = MHI_CC_EV_DWORD0(code);
-	event.dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
+	event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element));
+	event->dword[0] = MHI_CC_EV_DWORD0(code);
+	event->dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kfree(event);
+
+	return ret;
 }
 
 static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el)
-- 
GitLab


From 6ab3d50b106c9aea123a80551a6c9deace83b914 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Tue, 7 Nov 2023 16:14:49 +0800
Subject: [PATCH 1283/4076] bus: mhi: host: Add a separate timeout parameter
 for waiting ready

Some devices(eg. SDX75) take longer than expected (default, 8 seconds) to
set ready after reboot. Hence add optional ready timeout parameter and pass
the appropriate timeout value to mhi_poll_reg_field() to wait enough for
device ready as part of power up sequence.

Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/1699344890-87076-2-git-send-email-quic_qianyu@quicinc.com
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/host/init.c     |  1 +
 drivers/bus/mhi/host/internal.h |  2 +-
 drivers/bus/mhi/host/main.c     |  5 +++--
 drivers/bus/mhi/host/pm.c       | 24 +++++++++++++++++-------
 include/linux/mhi.h             |  4 ++++
 5 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c
index f78aefd2d7a36..65ceac1837f9a 100644
--- a/drivers/bus/mhi/host/init.c
+++ b/drivers/bus/mhi/host/init.c
@@ -881,6 +881,7 @@ static int parse_config(struct mhi_controller *mhi_cntrl,
 	if (!mhi_cntrl->timeout_ms)
 		mhi_cntrl->timeout_ms = MHI_TIMEOUT_MS;
 
+	mhi_cntrl->ready_timeout_ms = config->ready_timeout_ms;
 	mhi_cntrl->bounce_buf = config->use_bounce_buf;
 	mhi_cntrl->buffer_len = config->buf_len;
 	if (!mhi_cntrl->buffer_len)
diff --git a/drivers/bus/mhi/host/internal.h b/drivers/bus/mhi/host/internal.h
index 2e139e76de4c0..30ac415a3000f 100644
--- a/drivers/bus/mhi/host/internal.h
+++ b/drivers/bus/mhi/host/internal.h
@@ -321,7 +321,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
 				    u32 *out);
 int __must_check mhi_poll_reg_field(struct mhi_controller *mhi_cntrl,
 				    void __iomem *base, u32 offset, u32 mask,
-				    u32 val, u32 delayus);
+				    u32 val, u32 delayus, u32 timeout_ms);
 void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base,
 		   u32 offset, u32 val);
 int __must_check mhi_write_reg_field(struct mhi_controller *mhi_cntrl,
diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c
index dcf627b36e829..6cf11457380b4 100644
--- a/drivers/bus/mhi/host/main.c
+++ b/drivers/bus/mhi/host/main.c
@@ -40,10 +40,11 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
 
 int __must_check mhi_poll_reg_field(struct mhi_controller *mhi_cntrl,
 				    void __iomem *base, u32 offset,
-				    u32 mask, u32 val, u32 delayus)
+				    u32 mask, u32 val, u32 delayus,
+				    u32 timeout_ms)
 {
 	int ret;
-	u32 out, retry = (mhi_cntrl->timeout_ms * 1000) / delayus;
+	u32 out, retry = (timeout_ms * 1000) / delayus;
 
 	while (retry--) {
 		ret = mhi_read_reg_field(mhi_cntrl, base, offset, mask, &out);
diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c
index 8a4362d75fc43..a2f2feef14768 100644
--- a/drivers/bus/mhi/host/pm.c
+++ b/drivers/bus/mhi/host/pm.c
@@ -163,6 +163,7 @@ int mhi_ready_state_transition(struct mhi_controller *mhi_cntrl)
 	enum mhi_pm_state cur_state;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	u32 interval_us = 25000; /* poll register field every 25 milliseconds */
+	u32 timeout_ms;
 	int ret, i;
 
 	/* Check if device entered error state */
@@ -173,14 +174,18 @@ int mhi_ready_state_transition(struct mhi_controller *mhi_cntrl)
 
 	/* Wait for RESET to be cleared and READY bit to be set by the device */
 	ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, interval_us);
+				 MHICTRL_RESET_MASK, 0, interval_us,
+				 mhi_cntrl->timeout_ms);
 	if (ret) {
 		dev_err(dev, "Device failed to clear MHI Reset\n");
 		return ret;
 	}
 
+	timeout_ms = mhi_cntrl->ready_timeout_ms ?
+		mhi_cntrl->ready_timeout_ms : mhi_cntrl->timeout_ms;
 	ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHISTATUS,
-				 MHISTATUS_READY_MASK, 1, interval_us);
+				 MHISTATUS_READY_MASK, 1, interval_us,
+				 timeout_ms);
 	if (ret) {
 		dev_err(dev, "Device failed to enter MHI Ready\n");
 		return ret;
@@ -479,7 +484,7 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)
 
 		/* Wait for the reset bit to be cleared by the device */
 		ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, 25000);
+				 MHICTRL_RESET_MASK, 0, 25000, mhi_cntrl->timeout_ms);
 		if (ret)
 			dev_err(dev, "Device failed to clear MHI Reset\n");
 
@@ -492,8 +497,8 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)
 		if (!MHI_IN_PBL(mhi_get_exec_env(mhi_cntrl))) {
 			/* wait for ready to be set */
 			ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs,
-						 MHISTATUS,
-						 MHISTATUS_READY_MASK, 1, 25000);
+						 MHISTATUS, MHISTATUS_READY_MASK,
+						 1, 25000, mhi_cntrl->timeout_ms);
 			if (ret)
 				dev_err(dev, "Device failed to enter READY state\n");
 		}
@@ -1111,7 +1116,8 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl)
 	if (state == MHI_STATE_SYS_ERR) {
 		mhi_set_mhi_state(mhi_cntrl, MHI_STATE_RESET);
 		ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, interval_us);
+				 MHICTRL_RESET_MASK, 0, interval_us,
+				 mhi_cntrl->timeout_ms);
 		if (ret) {
 			dev_info(dev, "Failed to reset MHI due to syserr state\n");
 			goto error_exit;
@@ -1202,14 +1208,18 @@ EXPORT_SYMBOL_GPL(mhi_power_down);
 int mhi_sync_power_up(struct mhi_controller *mhi_cntrl)
 {
 	int ret = mhi_async_power_up(mhi_cntrl);
+	u32 timeout_ms;
 
 	if (ret)
 		return ret;
 
+	/* Some devices need more time to set ready during power up */
+	timeout_ms = mhi_cntrl->ready_timeout_ms ?
+		mhi_cntrl->ready_timeout_ms : mhi_cntrl->timeout_ms;
 	wait_event_timeout(mhi_cntrl->state_event,
 			   MHI_IN_MISSION_MODE(mhi_cntrl->ee) ||
 			   MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state),
-			   msecs_to_jiffies(mhi_cntrl->timeout_ms));
+			   msecs_to_jiffies(timeout_ms));
 
 	ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT;
 	if (ret)
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 039943ec4d4e7..d0f9b522f328b 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -266,6 +266,7 @@ struct mhi_event_config {
  * struct mhi_controller_config - Root MHI controller configuration
  * @max_channels: Maximum number of channels supported
  * @timeout_ms: Timeout value for operations. 0 means use default
+ * @ready_timeout_ms: Timeout value for waiting device to be ready (optional)
  * @buf_len: Size of automatically allocated buffers. 0 means use default
  * @num_channels: Number of channels defined in @ch_cfg
  * @ch_cfg: Array of defined channels
@@ -277,6 +278,7 @@ struct mhi_event_config {
 struct mhi_controller_config {
 	u32 max_channels;
 	u32 timeout_ms;
+	u32 ready_timeout_ms;
 	u32 buf_len;
 	u32 num_channels;
 	const struct mhi_channel_config *ch_cfg;
@@ -330,6 +332,7 @@ struct mhi_controller_config {
  * @pm_mutex: Mutex for suspend/resume operation
  * @pm_lock: Lock for protecting MHI power management state
  * @timeout_ms: Timeout in ms for state transitions
+ * @ready_timeout_ms: Timeout in ms for waiting device to be ready (optional)
  * @pm_state: MHI power management state
  * @db_access: DB access states
  * @ee: MHI device execution environment
@@ -419,6 +422,7 @@ struct mhi_controller {
 	struct mutex pm_mutex;
 	rwlock_t pm_lock;
 	u32 timeout_ms;
+	u32 ready_timeout_ms;
 	u32 pm_state;
 	u32 db_access;
 	enum mhi_ee_type ee;
-- 
GitLab


From 5571519009d09a52c42231b2425a8ff1cc6cd813 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Tue, 7 Nov 2023 16:14:50 +0800
Subject: [PATCH 1284/4076] bus: mhi: host: pci_generic: Add SDX75 based modem
 support

Add generic info for SDX75 based modems. SDX75 takes longer to set ready
during power up. Hence use separate configuration.

Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/1699344890-87076-3-git-send-email-quic_qianyu@quicinc.com
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/host/pci_generic.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c
index 08f3f039dbddc..cd6cd14b3d29b 100644
--- a/drivers/bus/mhi/host/pci_generic.c
+++ b/drivers/bus/mhi/host/pci_generic.c
@@ -269,6 +269,16 @@ static struct mhi_event_config modem_qcom_v1_mhi_events[] = {
 	MHI_EVENT_CONFIG_HW_DATA(5, 2048, 101)
 };
 
+static const struct mhi_controller_config modem_qcom_v2_mhiv_config = {
+	.max_channels = 128,
+	.timeout_ms = 8000,
+	.ready_timeout_ms = 50000,
+	.num_channels = ARRAY_SIZE(modem_qcom_v1_mhi_channels),
+	.ch_cfg = modem_qcom_v1_mhi_channels,
+	.num_events = ARRAY_SIZE(modem_qcom_v1_mhi_events),
+	.event_cfg = modem_qcom_v1_mhi_events,
+};
+
 static const struct mhi_controller_config modem_qcom_v1_mhiv_config = {
 	.max_channels = 128,
 	.timeout_ms = 8000,
@@ -278,6 +288,16 @@ static const struct mhi_controller_config modem_qcom_v1_mhiv_config = {
 	.event_cfg = modem_qcom_v1_mhi_events,
 };
 
+static const struct mhi_pci_dev_info mhi_qcom_sdx75_info = {
+	.name = "qcom-sdx75m",
+	.fw = "qcom/sdx75m/xbl.elf",
+	.edl = "qcom/sdx75m/edl.mbn",
+	.config = &modem_qcom_v2_mhiv_config,
+	.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
+	.dma_data_width = 32,
+	.sideband_wake = false,
+};
+
 static const struct mhi_pci_dev_info mhi_qcom_sdx65_info = {
 	.name = "qcom-sdx65m",
 	.fw = "qcom/sdx65m/xbl.elf",
@@ -600,6 +620,8 @@ static const struct pci_device_id mhi_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t) &mhi_telit_fn990_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0308),
 		.driver_data = (kernel_ulong_t) &mhi_qcom_sdx65_info },
+	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0309),
+		.driver_data = (kernel_ulong_t) &mhi_qcom_sdx75_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1001), /* EM120R-GL (sdx24) */
 		.driver_data = (kernel_ulong_t) &mhi_quectel_em1xx_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1002), /* EM160R-GL (sdx24) */
-- 
GitLab


From eff9704f5332a13b08fbdbe0f84059c9e7051d5f Mon Sep 17 00:00:00 2001
From: Krishna chaitanya chundru <quic_krichai@quicinc.com>
Date: Tue, 31 Oct 2023 15:21:05 +0530
Subject: [PATCH 1285/4076] bus: mhi: host: Add alignment check for event ring
 read pointer

Though we do check the event ring read pointer by "is_valid_ring_ptr"
to make sure it is in the buffer range, but there is another risk the
pointer may be not aligned.  Since we are expecting event ring elements
are 128 bits(struct mhi_ring_element) aligned, an unaligned read pointer
could lead to multiple issues like DoS or ring buffer memory corruption.

So add a alignment check for event ring read pointer.

Fixes: ec32332df764 ("bus: mhi: core: Sanity check values from remote device before use")
cc: stable@vger.kernel.org
Signed-off-by: Krishna chaitanya chundru <quic_krichai@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20231031-alignment_check-v2-1-1441db7c5efd@quicinc.com
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/host/main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c
index 6cf11457380b4..d80975f4bba87 100644
--- a/drivers/bus/mhi/host/main.c
+++ b/drivers/bus/mhi/host/main.c
@@ -269,7 +269,8 @@ static void mhi_del_ring_element(struct mhi_controller *mhi_cntrl,
 
 static bool is_valid_ring_ptr(struct mhi_ring *ring, dma_addr_t addr)
 {
-	return addr >= ring->iommu_base && addr < ring->iommu_base + ring->len;
+	return addr >= ring->iommu_base && addr < ring->iommu_base + ring->len &&
+			!(addr & (sizeof(struct mhi_ring_element) - 1));
 }
 
 int mhi_destroy_device(struct device *dev, void *data)
-- 
GitLab


From 79fff9379e6c928d376e5d8f7f63894ebff67865 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Tue, 7 Nov 2023 13:06:25 +0200
Subject: [PATCH 1286/4076] thunderbolt: Unwind TMU configuration if
 tb_switch_set_tmu_mode_params() fails

Dan reported that the kernel test robot found an issue with the TMU code
namely in tb_switch_tmu_change_mode() where we should actually go back
to the previous mode in case of failure instead of just returning back
the error. Fix this by unwinding the configuration as we do with the
other error paths in this function.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202311030814.AXtCk7PO-lkp@intel.com/
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thunderbolt/tmu.c b/drivers/thunderbolt/tmu.c
index 11f2aec2a5d37..9a259c72e5a74 100644
--- a/drivers/thunderbolt/tmu.c
+++ b/drivers/thunderbolt/tmu.c
@@ -894,7 +894,7 @@ static int tb_switch_tmu_change_mode(struct tb_switch *sw)
 
 	ret = tb_switch_set_tmu_mode_params(sw, sw->tmu.mode_request);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* Program the new mode and the downstream router lane adapter */
 	switch (sw->tmu.mode_request) {
-- 
GitLab


From 36b6ad6ad0350554e611a8cb754ccd40857416a8 Mon Sep 17 00:00:00 2001
From: Gil Fine <gil.fine@linux.intel.com>
Date: Wed, 15 Nov 2023 15:01:36 +0200
Subject: [PATCH 1287/4076] thunderbolt: Handle lane bonding of Gen 4 XDomain
 links properly

Gen 4 links come up as bonded already so we are not supposed to initiate
lane bonding on them. However, we should still update the port
structures accordingly. Split these into their own functions to make it
easier to follow.

Signed-off-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tb.c      |  2 --
 drivers/thunderbolt/xdomain.c | 49 ++++++++++++++++++++++++++++++++++-
 2 files changed, 48 insertions(+), 3 deletions(-)

diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 5acdeb766860d..6ff3e9624301c 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -503,8 +503,6 @@ static void tb_port_unconfigure_xdomain(struct tb_port *port)
 		usb4_port_unconfigure_xdomain(port);
 	else
 		tb_lc_unconfigure_xdomain(port);
-
-	tb_port_enable(port->dual_link_port);
 }
 
 static void tb_scan_xdomain(struct tb_port *port)
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 9803f0bbf20d1..0a885ee5788d5 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -1895,6 +1895,50 @@ struct device_type tb_xdomain_type = {
 };
 EXPORT_SYMBOL_GPL(tb_xdomain_type);
 
+static void tb_xdomain_link_init(struct tb_xdomain *xd, struct tb_port *down)
+{
+	if (!down->dual_link_port)
+		return;
+
+	/*
+	 * Gen 4 links come up already as bonded so only update the port
+	 * structures here.
+	 */
+	if (tb_port_get_link_generation(down) >= 4) {
+		down->bonded = true;
+		down->dual_link_port->bonded = true;
+	} else {
+		xd->bonding_possible = true;
+	}
+}
+
+static void tb_xdomain_link_exit(struct tb_xdomain *xd)
+{
+	struct tb_port *down = tb_xdomain_downstream_port(xd);
+
+	if (!down->dual_link_port)
+		return;
+
+	if (tb_port_get_link_generation(down) >= 4) {
+		down->bonded = false;
+		down->dual_link_port->bonded = false;
+	} else if (xd->link_width > TB_LINK_WIDTH_SINGLE) {
+		/*
+		 * Just return port structures back to way they were and
+		 * update credits. No need to update userspace because
+		 * the XDomain is removed soon anyway.
+		 */
+		tb_port_lane_bonding_disable(down);
+		tb_port_update_credits(down);
+	} else if (down->dual_link_port) {
+		/*
+		 * Re-enable the lane 1 adapter we disabled at the end
+		 * of tb_xdomain_get_properties().
+		 */
+		tb_port_enable(down->dual_link_port);
+	}
+}
+
 /**
  * tb_xdomain_alloc() - Allocate new XDomain object
  * @tb: Domain where the XDomain belongs
@@ -1945,7 +1989,8 @@ struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent,
 			goto err_free_local_uuid;
 	} else {
 		xd->needs_uuid = true;
-		xd->bonding_possible = !!down->dual_link_port;
+
+		tb_xdomain_link_init(xd, down);
 	}
 
 	device_initialize(&xd->dev);
@@ -2014,6 +2059,8 @@ void tb_xdomain_remove(struct tb_xdomain *xd)
 
 	device_for_each_child_reverse(&xd->dev, xd, unregister_service);
 
+	tb_xdomain_link_exit(xd);
+
 	/*
 	 * Undo runtime PM here explicitly because it is possible that
 	 * the XDomain was never added to the bus and thus device_del()
-- 
GitLab


From 30c6759b232bf42297a9ee6c60debf9082005d41 Mon Sep 17 00:00:00 2001
From: Gil Fine <gil.fine@linux.intel.com>
Date: Sun, 5 Nov 2023 17:52:19 +0200
Subject: [PATCH 1288/4076] thunderbolt: Move width_name() helper to tb.h

We are going to use it in subsequent patches, so make it available outside of
switch.c. Also, change the name to tb_width_name() to follow the naming
conventions.

Signed-off-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/switch.c | 20 ++------------------
 drivers/thunderbolt/tb.h     | 16 ++++++++++++++++
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 1e15ffa792955..7873b173a3517 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -941,22 +941,6 @@ int tb_port_get_link_generation(struct tb_port *port)
 	}
 }
 
-static const char *width_name(enum tb_link_width width)
-{
-	switch (width) {
-	case TB_LINK_WIDTH_SINGLE:
-		return "symmetric, single lane";
-	case TB_LINK_WIDTH_DUAL:
-		return "symmetric, dual lanes";
-	case TB_LINK_WIDTH_ASYM_TX:
-		return "asymmetric, 3 transmitters, 1 receiver";
-	case TB_LINK_WIDTH_ASYM_RX:
-		return "asymmetric, 3 receivers, 1 transmitter";
-	default:
-		return "unknown";
-	}
-}
-
 /**
  * tb_port_get_link_width() - Get current link width
  * @port: Port to check (USB4 or CIO)
@@ -2769,7 +2753,7 @@ static void tb_switch_link_init(struct tb_switch *sw)
 		return;
 
 	tb_sw_dbg(sw, "current link speed %u.0 Gb/s\n", sw->link_speed);
-	tb_sw_dbg(sw, "current link width %s\n", width_name(sw->link_width));
+	tb_sw_dbg(sw, "current link width %s\n", tb_width_name(sw->link_width));
 
 	bonded = sw->link_width >= TB_LINK_WIDTH_DUAL;
 
@@ -3029,7 +3013,7 @@ int tb_switch_set_link_width(struct tb_switch *sw, enum tb_link_width width)
 
 	tb_switch_update_link_attributes(sw);
 
-	tb_sw_dbg(sw, "link width set to %s\n", width_name(width));
+	tb_sw_dbg(sw, "link width set to %s\n", tb_width_name(width));
 	return ret;
 }
 
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index e299e53473ae2..1760c21e5b12f 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -568,6 +568,22 @@ static inline struct tb_port *tb_port_at(u64 route, struct tb_switch *sw)
 	return &sw->ports[port];
 }
 
+static inline const char *tb_width_name(enum tb_link_width width)
+{
+	switch (width) {
+	case TB_LINK_WIDTH_SINGLE:
+		return "symmetric, single lane";
+	case TB_LINK_WIDTH_DUAL:
+		return "symmetric, dual lanes";
+	case TB_LINK_WIDTH_ASYM_TX:
+		return "asymmetric, 3 transmitters, 1 receiver";
+	case TB_LINK_WIDTH_ASYM_RX:
+		return "asymmetric, 3 receivers, 1 transmitter";
+	default:
+		return "unknown";
+	}
+}
+
 /**
  * tb_port_has_remote() - Does the port have switch connected downstream
  * @port: Port to check
-- 
GitLab


From ea20adddd6c154e9e107c47fbf1b4697e68180df Mon Sep 17 00:00:00 2001
From: Gil Fine <gil.fine@linux.intel.com>
Date: Tue, 7 Nov 2023 13:00:53 +0200
Subject: [PATCH 1289/4076] thunderbolt: Log XDomain link speed and width

In the same way we do for routers. This is useful for debugging
purposes.

Signed-off-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/xdomain.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 0a885ee5788d5..9495742913d5c 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -1462,6 +1462,11 @@ static int tb_xdomain_get_properties(struct tb_xdomain *xd)
 				tb_port_disable(port->dual_link_port);
 		}
 
+		dev_dbg(&xd->dev, "current link speed %u.0 Gb/s\n",
+			xd->link_speed);
+		dev_dbg(&xd->dev, "current link width %s\n",
+			tb_width_name(xd->link_width));
+
 		if (device_add(&xd->dev)) {
 			dev_err(&xd->dev, "failed to add XDomain device\n");
 			return -ENODEV;
-- 
GitLab


From 3c052ec6f4f866163573445a02d60b629805a6e7 Mon Sep 17 00:00:00 2001
From: Gil Fine <gil.fine@linux.intel.com>
Date: Wed, 15 Nov 2023 12:09:53 +0200
Subject: [PATCH 1290/4076] thunderbolt: Transition link to asymmetric only
 when both sides support it

We can transition Gen 4 link to asymmetric only when both sides of the
link support it in the required direction. For this reason make sure
that the downstream adapter also supports asymmetric link before
starting the transition.

Signed-off-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tb.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 6ff3e9624301c..f81e7cf53d691 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -1094,8 +1094,9 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 	clx = tb_disable_clx(sw);
 
 	tb_for_each_upstream_port_on_path(src_port, dst_port, up) {
+		struct tb_port *down = tb_switch_downstream_port(up->sw);
+		enum tb_link_width width_up, width_down;
 		int consumed_up, consumed_down;
-		enum tb_link_width width;
 
 		ret = tb_consumed_dp_bandwidth(tb, src_port, dst_port, up,
 					       &consumed_up, &consumed_down);
@@ -1116,7 +1117,8 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 			if (consumed_down + requested_down < asym_threshold)
 				continue;
 
-			width = TB_LINK_WIDTH_ASYM_RX;
+			width_up = TB_LINK_WIDTH_ASYM_RX;
+			width_down = TB_LINK_WIDTH_ASYM_TX;
 		} else {
 			/* Upstream, the opposite of above */
 			if (consumed_down + requested_down >= TB_ASYM_MIN) {
@@ -1126,13 +1128,15 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 			if (consumed_up + requested_up < asym_threshold)
 				continue;
 
-			width = TB_LINK_WIDTH_ASYM_TX;
+			width_up = TB_LINK_WIDTH_ASYM_TX;
+			width_down = TB_LINK_WIDTH_ASYM_RX;
 		}
 
-		if (up->sw->link_width == width)
+		if (up->sw->link_width == width_up)
 			continue;
 
-		if (!tb_port_width_supported(up, width))
+		if (!tb_port_width_supported(up, width_up) ||
+		    !tb_port_width_supported(down, width_down))
 			continue;
 
 		tb_sw_dbg(up->sw, "configuring asymmetric link\n");
@@ -1141,7 +1145,7 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 		 * Here requested + consumed > threshold so we need to
 		 * transtion the link into asymmetric now.
 		 */
-		ret = tb_switch_set_link_width(up->sw, width);
+		ret = tb_switch_set_link_width(up->sw, width_up);
 		if (ret) {
 			tb_sw_warn(up->sw, "failed to set link width\n");
 			break;
-- 
GitLab


From 09dc766bd60b7bc6a2742aaf2410e434f458893c Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Fri, 17 Nov 2023 12:58:39 +0200
Subject: [PATCH 1291/4076] thunderbolt: Disable CL states only when actually
 needed

If there is not going to be an actual transition to asymmetric or
symmetric, there is no point to disable and re-enable CL states either.
So instead disable them only when we know that an actual transition is
going to take place.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tb.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index f81e7cf53d691..cf1a20a33b9a9 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -1075,15 +1075,14 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 			     struct tb_port *dst_port, int requested_up,
 			     int requested_down)
 {
+	bool clx = false, clx_disabled = false, downstream;
 	struct tb_switch *sw;
-	bool clx, downstream;
 	struct tb_port *up;
 	int ret = 0;
 
 	if (!asym_threshold)
 		return 0;
 
-	/* Disable CL states before doing any transitions */
 	downstream = tb_port_path_direction_downstream(src_port, dst_port);
 	/* Pick up router deepest in the hierarchy */
 	if (downstream)
@@ -1091,8 +1090,6 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 	else
 		sw = src_port->sw;
 
-	clx = tb_disable_clx(sw);
-
 	tb_for_each_upstream_port_on_path(src_port, dst_port, up) {
 		struct tb_port *down = tb_switch_downstream_port(up->sw);
 		enum tb_link_width width_up, width_down;
@@ -1139,6 +1136,16 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
 		    !tb_port_width_supported(down, width_down))
 			continue;
 
+		/*
+		 * Disable CL states before doing any transitions. We
+		 * delayed it until now that we know there is a real
+		 * transition taking place.
+		 */
+		if (!clx_disabled) {
+			clx = tb_disable_clx(sw);
+			clx_disabled = true;
+		}
+
 		tb_sw_dbg(up->sw, "configuring asymmetric link\n");
 
 		/*
@@ -1175,15 +1182,14 @@ static int tb_configure_sym(struct tb *tb, struct tb_port *src_port,
 			    struct tb_port *dst_port, int requested_up,
 			    int requested_down)
 {
+	bool clx = false, clx_disabled = false, downstream;
 	struct tb_switch *sw;
-	bool clx, downstream;
 	struct tb_port *up;
 	int ret = 0;
 
 	if (!asym_threshold)
 		return 0;
 
-	/* Disable CL states before doing any transitions */
 	downstream = tb_port_path_direction_downstream(src_port, dst_port);
 	/* Pick up router deepest in the hierarchy */
 	if (downstream)
@@ -1191,8 +1197,6 @@ static int tb_configure_sym(struct tb *tb, struct tb_port *src_port,
 	else
 		sw = src_port->sw;
 
-	clx = tb_disable_clx(sw);
-
 	tb_for_each_upstream_port_on_path(src_port, dst_port, up) {
 		int consumed_up, consumed_down;
 
@@ -1225,6 +1229,12 @@ static int tb_configure_sym(struct tb *tb, struct tb_port *src_port,
 		if (up->sw->link_width == TB_LINK_WIDTH_DUAL)
 			continue;
 
+		/* Disable CL states before doing any transitions */
+		if (!clx_disabled) {
+			clx = tb_disable_clx(sw);
+			clx_disabled = true;
+		}
+
 		tb_sw_dbg(up->sw, "configuring symmetric link\n");
 
 		ret = tb_switch_set_link_width(up->sw, TB_LINK_WIDTH_DUAL);
-- 
GitLab


From 97e0a21ce835603b81a5c11de5bf45820194db10 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 23 Nov 2023 13:39:21 +0200
Subject: [PATCH 1292/4076] thunderbolt: Use tb_dp_read_cap() to read
 DP_COMMON_CAP as well

There is no point doing this separately as the register layout is the
same. For this reason rename tb_dp_read_dprx() to tb_dp_wait_dprx() and
call tb_dp_read_cap() instead.

While there add debug log if the DPRX capability read times out.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tunnel.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 8d45cb4f04abf..6297c85dea065 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -1067,8 +1067,7 @@ static int tb_dp_alloc_bandwidth(struct tb_tunnel *tunnel, int *alloc_up,
 	return 0;
 }
 
-static int tb_dp_read_dprx(struct tb_tunnel *tunnel, u32 *rate, u32 *lanes,
-			   int timeout_msec)
+static int tb_dp_wait_dprx(struct tb_tunnel *tunnel, int timeout_msec)
 {
 	ktime_t timeout = ktime_add_ms(ktime_get(), timeout_msec);
 	struct tb_port *in = tunnel->src_port;
@@ -1087,15 +1086,13 @@ static int tb_dp_read_dprx(struct tb_tunnel *tunnel, u32 *rate, u32 *lanes,
 			return ret;
 
 		if (val & DP_COMMON_CAP_DPRX_DONE) {
-			*rate = tb_dp_cap_get_rate(val);
-			*lanes = tb_dp_cap_get_lanes(val);
-
 			tb_tunnel_dbg(tunnel, "DPRX read done\n");
 			return 0;
 		}
 		usleep_range(100, 150);
 	} while (ktime_before(ktime_get(), timeout));
 
+	tb_tunnel_dbg(tunnel, "DPRX read timeout\n");
 	return -ETIMEDOUT;
 }
 
@@ -1110,6 +1107,7 @@ static int tb_dp_read_cap(struct tb_tunnel *tunnel, unsigned int cap, u32 *rate,
 	switch (cap) {
 	case DP_LOCAL_CAP:
 	case DP_REMOTE_CAP:
+	case DP_COMMON_CAP:
 		break;
 
 	default:
@@ -1182,7 +1180,7 @@ static int tb_dp_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up,
 		 * reduced one). Otherwise return the remote (possibly
 		 * reduced) caps.
 		 */
-		ret = tb_dp_read_dprx(tunnel, &rate, &lanes, 150);
+		ret = tb_dp_wait_dprx(tunnel, 150);
 		if (ret) {
 			if (ret == -ETIMEDOUT)
 				ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP,
@@ -1190,6 +1188,9 @@ static int tb_dp_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up,
 			if (ret)
 				return ret;
 		}
+		ret = tb_dp_read_cap(tunnel, DP_COMMON_CAP, &rate, &lanes);
+		if (ret)
+			return ret;
 	} else if (sw->generation >= 2) {
 		ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP, &rate, &lanes);
 		if (ret)
-- 
GitLab


From 0b663ec9fe07e5c46ede45da75951eb11fc2f215 Mon Sep 17 00:00:00 2001
From: Gil Fine <gil.fine@linux.intel.com>
Date: Wed, 15 Nov 2023 12:09:58 +0200
Subject: [PATCH 1293/4076] thunderbolt: Improve logging when DisplayPort
 resource is added due to hotplug

To allow us differentiate how DisplayPort resource is added to the
DisplayPort resources list make the debug log to append "hotplug" when
this was due to an actual hotplug.

Signed-off-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index cf1a20a33b9a9..bd211e97ee4bd 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -1903,7 +1903,7 @@ static void tb_dp_resource_available(struct tb *tb, struct tb_port *port)
 			return;
 	}
 
-	tb_port_dbg(port, "DP %s resource available\n",
+	tb_port_dbg(port, "DP %s resource available after hotplug\n",
 		    tb_port_is_dpin(port) ? "IN" : "OUT");
 	list_add_tail(&port->list, &tcm->dp_resources);
 
-- 
GitLab


From 54967f4177d3d8d6231eeedee669c2512bcbf172 Mon Sep 17 00:00:00 2001
From: Gil Fine <gil.fine@linux.intel.com>
Date: Wed, 15 Nov 2023 12:09:56 +0200
Subject: [PATCH 1294/4076] thunderbolt: Make PCIe tunnel setup and teardown
 follow CM guide

The USB4 Connection Manager guide suggests that the PCIe paths are
enabled from the upstream adapter to the downstream adapter and vice
versa on disable so make the driver follows this sequence.

Signed-off-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tunnel.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 6297c85dea065..b0c3c8373775e 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -199,14 +199,21 @@ static int tb_pci_activate(struct tb_tunnel *tunnel, bool activate)
 			return res;
 	}
 
-	res = tb_pci_port_enable(tunnel->src_port, activate);
+	if (activate)
+		res = tb_pci_port_enable(tunnel->dst_port, activate);
+	else
+		res = tb_pci_port_enable(tunnel->src_port, activate);
 	if (res)
 		return res;
 
-	if (tb_port_is_pcie_up(tunnel->dst_port)) {
-		res = tb_pci_port_enable(tunnel->dst_port, activate);
+
+	if (activate) {
+		res = tb_pci_port_enable(tunnel->src_port, activate);
 		if (res)
 			return res;
+	} else {
+		/* Downstream router could be unplugged */
+		tb_pci_port_enable(tunnel->dst_port, activate);
 	}
 
 	return activate ? 0 : tb_pci_set_ext_encapsulation(tunnel, activate);
-- 
GitLab


From 2b3a6239d286d6b74295ccf21905ba6533bcf3a9 Mon Sep 17 00:00:00 2001
From: Gil Fine <gil.fine@linux.intel.com>
Date: Wed, 15 Nov 2023 12:09:57 +0200
Subject: [PATCH 1295/4076] thunderbolt: Disable PCIe extended encapsulation
 upon teardown properly

In case of PCIe tunnel teardown (including if caused by router unplug),
PCIe extended encapsulation bit should be cleared in downstream and
upstream routers accordingly.

Signed-off-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tunnel.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index b0c3c8373775e..6fffb2c82d3d1 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -173,16 +173,28 @@ static int tb_pci_set_ext_encapsulation(struct tb_tunnel *tunnel, bool enable)
 	int ret;
 
 	/* Only supported of both routers are at least USB4 v2 */
-	if (tb_port_get_link_generation(port) < 4)
+	if ((usb4_switch_version(tunnel->src_port->sw) < 2) ||
+	   (usb4_switch_version(tunnel->dst_port->sw) < 2))
+		return 0;
+
+	if (enable && tb_port_get_link_generation(port) < 4)
 		return 0;
 
 	ret = usb4_pci_port_set_ext_encapsulation(tunnel->src_port, enable);
 	if (ret)
 		return ret;
 
+	/*
+	 * Downstream router could be unplugged so disable of encapsulation
+	 * in upstream router is still possible.
+	 */
 	ret = usb4_pci_port_set_ext_encapsulation(tunnel->dst_port, enable);
-	if (ret)
-		return ret;
+	if (ret) {
+		if (enable)
+			return ret;
+		if (ret != -ENODEV)
+			return ret;
+	}
 
 	tb_tunnel_dbg(tunnel, "extended encapsulation %s\n",
 		      str_enabled_disabled(enable));
-- 
GitLab


From 2cd3da4e37453019e21a486d9de3144f46b4fdf7 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Fri, 20 May 2022 13:47:11 +0300
Subject: [PATCH 1296/4076] thunderbolt: Add support for Intel Lunar Lake

Intel Lunar Lake has similar integrated Thunderbolt/USB4 controller as
Intel Meteor Lake with some small differences in the host router (it has
3 DP IN adapters for instance). Add the Intel Lunar Lake PCI IDs to the
driver list of supported devices.

Tested-by: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/nhi.c | 4 ++++
 drivers/thunderbolt/nhi.h | 2 ++
 2 files changed, 6 insertions(+)

diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 4b7bec74e89fb..fb4f46e51753a 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -1517,6 +1517,10 @@ static struct pci_device_id nhi_ids[] = {
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL_P_NHI1),
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI0),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI1),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) },
 
diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h
index 0f029ce758825..7a07c7c1a9c2c 100644
--- a/drivers/thunderbolt/nhi.h
+++ b/drivers/thunderbolt/nhi.h
@@ -90,6 +90,8 @@ extern const struct tb_nhi_ops icl_nhi_ops;
 #define PCI_DEVICE_ID_INTEL_TGL_H_NHI1			0x9a21
 #define PCI_DEVICE_ID_INTEL_RPL_NHI0			0xa73e
 #define PCI_DEVICE_ID_INTEL_RPL_NHI1			0xa76d
+#define PCI_DEVICE_ID_INTEL_LNL_NHI0			0xa833
+#define PCI_DEVICE_ID_INTEL_LNL_NHI1			0xa834
 
 #define PCI_CLASS_SERIAL_USB_USB4			0x0c0340
 
-- 
GitLab


From 62210a26cd4f8ad52683a71c0226dfe85de1144d Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Wed, 18 Oct 2023 17:58:12 +0530
Subject: [PATCH 1297/4076] bus: mhi: ep: Use slab allocator where applicable

Use slab allocator for allocating the memory for objects used frequently
and are of fixed size. This reduces the overheard associated with
kmalloc().

Suggested-by: Alex Elder <elder@linaro.org>
Link: https://lore.kernel.org/r/20231018122812.47261-1-manivannan.sadhasivam@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c | 66 +++++++++++++++++++++++++++++----------
 include/linux/mhi_ep.h    |  3 ++
 2 files changed, 52 insertions(+), 17 deletions(-)

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index e2513f5f47a61..517279600645f 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -74,7 +74,7 @@ static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct m
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -83,7 +83,7 @@ static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct m
 	event->dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, ring->er_index, event, MHI_TRE_DATA_GET_BEI(tre));
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -93,7 +93,7 @@ int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_stat
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -101,7 +101,7 @@ int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_stat
 	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -111,7 +111,7 @@ int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_e
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -119,7 +119,7 @@ int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_e
 	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -130,7 +130,7 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -139,7 +139,7 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	event->dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -451,7 +451,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 		mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
 	} else {
 		/* UL channel */
-		result.buf_addr = kzalloc(len, GFP_KERNEL);
+		result.buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL | GFP_DMA);
 		if (!result.buf_addr)
 			return -ENOMEM;
 
@@ -459,7 +459,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 			ret = mhi_ep_read_channel(mhi_cntrl, ring, &result, len);
 			if (ret < 0) {
 				dev_err(&mhi_chan->mhi_dev->dev, "Failed to read channel\n");
-				kfree(result.buf_addr);
+				kmem_cache_free(mhi_cntrl->tre_buf_cache, result.buf_addr);
 				return ret;
 			}
 
@@ -471,7 +471,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 			/* Read until the ring becomes empty */
 		} while (!mhi_ep_queue_is_empty(mhi_chan->mhi_dev, DMA_TO_DEVICE));
 
-		kfree(result.buf_addr);
+		kmem_cache_free(mhi_cntrl->tre_buf_cache, result.buf_addr);
 	}
 
 	return 0;
@@ -780,14 +780,14 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 		if (ret) {
 			dev_err(dev, "Error updating write offset for ring\n");
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
 		/* Sanity check to make sure there are elements in the ring */
 		if (ring->rd_offset == ring->wr_offset) {
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
@@ -799,12 +799,12 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 			dev_err(dev, "Error processing ring for channel (%u): %d\n",
 				ring->ch_id, ret);
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
 		mutex_unlock(&chan->lock);
-		kfree(itr);
+		kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 	}
 }
 
@@ -860,7 +860,7 @@ static void mhi_ep_queue_channel_db(struct mhi_ep_cntrl *mhi_cntrl, unsigned lon
 		u32 ch_id = ch_idx + i;
 
 		ring = &mhi_cntrl->mhi_chan[ch_id].ring;
-		item = kzalloc(sizeof(*item), GFP_ATOMIC);
+		item = kmem_cache_zalloc(mhi_cntrl->ring_item_cache, GFP_ATOMIC);
 		if (!item)
 			return;
 
@@ -1407,6 +1407,29 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		goto err_free_ch;
 	}
 
+	mhi_cntrl->ev_ring_el_cache = kmem_cache_create("mhi_ep_event_ring_el",
+							sizeof(struct mhi_ring_element), 0,
+							SLAB_CACHE_DMA, NULL);
+	if (!mhi_cntrl->ev_ring_el_cache) {
+		ret = -ENOMEM;
+		goto err_free_cmd;
+	}
+
+	mhi_cntrl->tre_buf_cache = kmem_cache_create("mhi_ep_tre_buf", MHI_EP_DEFAULT_MTU, 0,
+						      SLAB_CACHE_DMA, NULL);
+	if (!mhi_cntrl->tre_buf_cache) {
+		ret = -ENOMEM;
+		goto err_destroy_ev_ring_el_cache;
+	}
+
+	mhi_cntrl->ring_item_cache = kmem_cache_create("mhi_ep_ring_item",
+							sizeof(struct mhi_ep_ring_item), 0,
+							0, NULL);
+	if (!mhi_cntrl->ev_ring_el_cache) {
+		ret = -ENOMEM;
+		goto err_destroy_tre_buf_cache;
+	}
+
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
@@ -1415,7 +1438,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0);
 	if (!mhi_cntrl->wq) {
 		ret = -ENOMEM;
-		goto err_free_cmd;
+		goto err_destroy_ring_item_cache;
 	}
 
 	INIT_LIST_HEAD(&mhi_cntrl->st_transition_list);
@@ -1474,6 +1497,12 @@ err_ida_free:
 	ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index);
 err_destroy_wq:
 	destroy_workqueue(mhi_cntrl->wq);
+err_destroy_ring_item_cache:
+	kmem_cache_destroy(mhi_cntrl->ring_item_cache);
+err_destroy_ev_ring_el_cache:
+	kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache);
+err_destroy_tre_buf_cache:
+	kmem_cache_destroy(mhi_cntrl->tre_buf_cache);
 err_free_cmd:
 	kfree(mhi_cntrl->mhi_cmd);
 err_free_ch:
@@ -1495,6 +1524,9 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
 
 	free_irq(mhi_cntrl->irq, mhi_cntrl);
 
+	kmem_cache_destroy(mhi_cntrl->tre_buf_cache);
+	kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache);
+	kmem_cache_destroy(mhi_cntrl->ring_item_cache);
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_chan);
 
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index f198a8ac7ee72..ce85d42b685d6 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -128,6 +128,9 @@ struct mhi_ep_cntrl {
 	struct work_struct reset_work;
 	struct work_struct cmd_ring_work;
 	struct work_struct ch_ring_work;
+	struct kmem_cache *ring_item_cache;
+	struct kmem_cache *ev_ring_el_cache;
+	struct kmem_cache *tre_buf_cache;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
-- 
GitLab


From cea4bcbf997ab2f6c8d242f41785b21ea91d53c3 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Thu, 26 Oct 2023 10:25:13 +0530
Subject: [PATCH 1298/4076] bus: mhi: ep: Add support for interrupt moderation
 timer

MHI spec defines the interrupt moderation timer feature using which the
host can limit the number of interrupts being raised for an event ring by
the device. This feature allows the host to process multiple event ring
elements by a single IRQ from the device, thereby eliminating the need to
process IRQ for each element.

The INTMODT field in the event context array provides the value to be used
for delaying the IRQ generation from device. This value, along with the
Block Event Interrupt (BEI) flag of the TRE defines how IRQ is generated to
the host.

Support for interrupt moderation timer is implemented using delayed
workqueue in kernel. And a separate delayed work item is used for each
event ring.

Link: https://lore.kernel.org/r/20231026045513.12981-1-manivannan.sadhasivam@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/internal.h |  3 +++
 drivers/bus/mhi/ep/main.c     | 22 +++++++++++++++++++---
 drivers/bus/mhi/ep/ring.c     | 19 ++++++++++++++++++-
 3 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h
index a2125fa5fe2f9..8c5cf2b679510 100644
--- a/drivers/bus/mhi/ep/internal.h
+++ b/drivers/bus/mhi/ep/internal.h
@@ -126,6 +126,7 @@ struct mhi_ep_ring {
 	union mhi_ep_ring_ctx *ring_ctx;
 	struct mhi_ring_element *ring_cache;
 	enum mhi_ep_ring_type type;
+	struct delayed_work intmodt_work;
 	u64 rbase;
 	size_t rd_offset;
 	size_t wr_offset;
@@ -135,7 +136,9 @@ struct mhi_ep_ring {
 	u32 ch_id;
 	u32 er_index;
 	u32 irq_vector;
+	u32 intmodt;
 	bool started;
+	bool irq_pending;
 };
 
 struct mhi_ep_cmd {
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 517279600645f..c759183943eda 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -54,11 +54,27 @@ static int mhi_ep_send_event(struct mhi_ep_cntrl *mhi_cntrl, u32 ring_idx,
 	mutex_unlock(&mhi_cntrl->event_lock);
 
 	/*
-	 * Raise IRQ to host only if the BEI flag is not set in TRE. Host might
-	 * set this flag for interrupt moderation as per MHI protocol.
+	 * As per the MHI specification, section 4.3, Interrupt moderation:
+	 *
+	 * 1. If BEI flag is not set, cancel any pending intmodt work if started
+	 * for the event ring and raise IRQ immediately.
+	 *
+	 * 2. If both BEI and intmodt are set, and if no IRQ is pending for the
+	 * same event ring, start the IRQ delayed work as per the value of
+	 * intmodt. If previous IRQ is pending, then do nothing as the pending
+	 * IRQ is enough for the host to process the current event ring element.
+	 *
+	 * 3. If BEI is set and intmodt is not set, no need to raise IRQ.
 	 */
-	if (!bei)
+	if (!bei) {
+		if (READ_ONCE(ring->irq_pending))
+			cancel_delayed_work(&ring->intmodt_work);
+
 		mhi_cntrl->raise_irq(mhi_cntrl, ring->irq_vector);
+	} else if (ring->intmodt && !READ_ONCE(ring->irq_pending)) {
+		WRITE_ONCE(ring->irq_pending, true);
+		schedule_delayed_work(&ring->intmodt_work, msecs_to_jiffies(ring->intmodt));
+	}
 
 	return 0;
 
diff --git a/drivers/bus/mhi/ep/ring.c b/drivers/bus/mhi/ep/ring.c
index 115518ec76a43..a1071c13761b4 100644
--- a/drivers/bus/mhi/ep/ring.c
+++ b/drivers/bus/mhi/ep/ring.c
@@ -157,6 +157,15 @@ void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32
 	}
 }
 
+static void mhi_ep_raise_irq(struct work_struct *work)
+{
+	struct mhi_ep_ring *ring = container_of(work, struct mhi_ep_ring, intmodt_work.work);
+	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
+
+	mhi_cntrl->raise_irq(mhi_cntrl, ring->irq_vector);
+	WRITE_ONCE(ring->irq_pending, false);
+}
+
 int mhi_ep_ring_start(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 			union mhi_ep_ring_ctx *ctx)
 {
@@ -173,8 +182,13 @@ int mhi_ep_ring_start(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 	if (ring->type == RING_TYPE_CH)
 		ring->er_index = le32_to_cpu(ring->ring_ctx->ch.erindex);
 
-	if (ring->type == RING_TYPE_ER)
+	if (ring->type == RING_TYPE_ER) {
 		ring->irq_vector = le32_to_cpu(ring->ring_ctx->ev.msivec);
+		ring->intmodt = FIELD_GET(EV_CTX_INTMODT_MASK,
+					  le32_to_cpu(ring->ring_ctx->ev.intmod));
+
+		INIT_DELAYED_WORK(&ring->intmodt_work, mhi_ep_raise_irq);
+	}
 
 	/* During ring init, both rp and wp are equal */
 	memcpy_fromio(&val, (void __iomem *) &ring->ring_ctx->generic.rp, sizeof(u64));
@@ -201,6 +215,9 @@ int mhi_ep_ring_start(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 
 void mhi_ep_ring_reset(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring)
 {
+	if (ring->type == RING_TYPE_ER)
+		cancel_delayed_work_sync(&ring->intmodt_work);
+
 	ring->started = false;
 	kfree(ring->ring_cache);
 	ring->ring_cache = NULL;
-- 
GitLab


From b08ded2ef2e98768d5ee5f71da8fe768b1f7774b Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Thu, 17 Aug 2023 23:24:52 +0530
Subject: [PATCH 1299/4076] bus: mhi: ep: Pass mhi_ep_buf_info struct to
 read/write APIs

In the preparation of DMA async support, let's pass the parameters to
read_from_host() and write_to_host() APIs using mhi_ep_buf_info structure.

No functional change.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c                    | 23 +++----
 drivers/bus/mhi/ep/ring.c                    | 41 ++++++------
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 66 +++++++++++---------
 include/linux/mhi_ep.h                       | 16 ++++-
 4 files changed, 84 insertions(+), 62 deletions(-)

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index c759183943eda..b9334d548c410 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -340,10 +340,9 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 	struct mhi_ep_chan *mhi_chan = &mhi_cntrl->mhi_chan[ring->ch_id];
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	size_t tr_len, read_offset, write_offset;
+	struct mhi_ep_buf_info buf_info = {};
 	struct mhi_ring_element *el;
 	bool tr_done = false;
-	void *write_addr;
-	u64 read_addr;
 	u32 buf_left;
 	int ret;
 
@@ -372,11 +371,13 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 
 		read_offset = mhi_chan->tre_size - mhi_chan->tre_bytes_left;
 		write_offset = len - buf_left;
-		read_addr = mhi_chan->tre_loc + read_offset;
-		write_addr = result->buf_addr + write_offset;
+
+		buf_info.host_addr = mhi_chan->tre_loc + read_offset;
+		buf_info.dev_addr = result->buf_addr + write_offset;
+		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n");
 			return ret;
@@ -499,12 +500,11 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan;
 	struct device *dev = &mhi_chan->mhi_dev->dev;
+	struct mhi_ep_buf_info buf_info = {};
 	struct mhi_ring_element *el;
 	u32 buf_left, read_offset;
 	struct mhi_ep_ring *ring;
 	enum mhi_ev_ccs code;
-	void *read_addr;
-	u64 write_addr;
 	size_t tr_len;
 	u32 tre_len;
 	int ret;
@@ -533,11 +533,13 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 
 		tr_len = min(buf_left, tre_len);
 		read_offset = skb->len - buf_left;
-		read_addr = skb->data + read_offset;
-		write_addr = MHI_TRE_DATA_GET_PTR(el);
+
+		buf_info.dev_addr = skb->data + read_offset;
+		buf_info.host_addr = MHI_TRE_DATA_GET_PTR(el);
+		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->write_to_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		ret = mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(dev, "Error writing to the channel\n");
 			goto err_exit;
@@ -1445,7 +1447,6 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		ret = -ENOMEM;
 		goto err_destroy_tre_buf_cache;
 	}
-
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
diff --git a/drivers/bus/mhi/ep/ring.c b/drivers/bus/mhi/ep/ring.c
index a1071c13761b4..7ea952860def4 100644
--- a/drivers/bus/mhi/ep/ring.c
+++ b/drivers/bus/mhi/ep/ring.c
@@ -30,7 +30,8 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
-	size_t start, copy_size;
+	struct mhi_ep_buf_info buf_info = {};
+	size_t start;
 	int ret;
 
 	/* Don't proceed in the case of event ring. This happens during mhi_ep_ring_start(). */
@@ -43,30 +44,34 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 
 	start = ring->wr_offset;
 	if (start < end) {
-		copy_size = (end - start) * sizeof(struct mhi_ring_element);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase +
-						(start * sizeof(struct mhi_ring_element)),
-						&ring->ring_cache[start], copy_size);
+		buf_info.size = (end - start) * sizeof(struct mhi_ring_element);
+		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
+		buf_info.dev_addr = &ring->ring_cache[start];
+
+		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 	} else {
-		copy_size = (ring->ring_size - start) * sizeof(struct mhi_ring_element);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase +
-						(start * sizeof(struct mhi_ring_element)),
-						&ring->ring_cache[start], copy_size);
+		buf_info.size = (ring->ring_size - start) * sizeof(struct mhi_ring_element);
+		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
+		buf_info.dev_addr = &ring->ring_cache[start];
+
+		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 
 		if (end) {
-			ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase,
-							&ring->ring_cache[0],
-							end * sizeof(struct mhi_ring_element));
+			buf_info.host_addr = ring->rbase;
+			buf_info.dev_addr = &ring->ring_cache[0];
+			buf_info.size = end * sizeof(struct mhi_ring_element);
+
+			ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 			if (ret < 0)
 				return ret;
 		}
 	}
 
-	dev_dbg(dev, "Cached ring: start %zu end %zu size %zu\n", start, end, copy_size);
+	dev_dbg(dev, "Cached ring: start %zu end %zu size %zu\n", start, end, buf_info.size);
 
 	return 0;
 }
@@ -102,6 +107,7 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 {
 	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	struct mhi_ep_buf_info buf_info = {};
 	size_t old_offset = 0;
 	u32 num_free_elem;
 	__le64 rp;
@@ -133,12 +139,11 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 	rp = cpu_to_le64(ring->rd_offset * sizeof(*el) + ring->rbase);
 	memcpy_toio((void __iomem *) &ring->ring_ctx->generic.rp, &rp, sizeof(u64));
 
-	ret = mhi_cntrl->write_to_host(mhi_cntrl, el, ring->rbase + (old_offset * sizeof(*el)),
-				       sizeof(*el));
-	if (ret < 0)
-		return ret;
+	buf_info.host_addr = ring->rbase + (old_offset * sizeof(*el));
+	buf_info.dev_addr = el;
+	buf_info.size = sizeof(*el);
 
-	return 0;
+	return mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
 }
 
 void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32 id)
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index b7b9d3e21f97d..ec5f4a38178bb 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -209,28 +209,28 @@ static void pci_epf_mhi_raise_irq(struct mhi_ep_cntrl *mhi_cntrl, u32 vector)
 			  vector + 1);
 }
 
-static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
-				 void *to, size_t size)
+static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl,
+				 struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
-	size_t offset = get_align_offset(epf_mhi, from);
+	size_t offset = get_align_offset(epf_mhi, buf_info->host_addr);
 	void __iomem *tre_buf;
 	phys_addr_t tre_phys;
 	int ret;
 
 	mutex_lock(&epf_mhi->lock);
 
-	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, from, &tre_phys, &tre_buf,
-				      offset, size);
+	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, buf_info->host_addr, &tre_phys,
+				      &tre_buf, offset, buf_info->size);
 	if (ret) {
 		mutex_unlock(&epf_mhi->lock);
 		return ret;
 	}
 
-	memcpy_fromio(to, tre_buf, size);
+	memcpy_fromio(buf_info->dev_addr, tre_buf, buf_info->size);
 
-	__pci_epf_mhi_unmap_free(mhi_cntrl, from, tre_phys, tre_buf, offset,
-				 size);
+	__pci_epf_mhi_unmap_free(mhi_cntrl, buf_info->host_addr, tre_phys,
+				 tre_buf, offset, buf_info->size);
 
 	mutex_unlock(&epf_mhi->lock);
 
@@ -238,27 +238,27 @@ static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 }
 
 static int pci_epf_mhi_iatu_write(struct mhi_ep_cntrl *mhi_cntrl,
-				  void *from, u64 to, size_t size)
+				  struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
-	size_t offset = get_align_offset(epf_mhi, to);
+	size_t offset = get_align_offset(epf_mhi, buf_info->host_addr);
 	void __iomem *tre_buf;
 	phys_addr_t tre_phys;
 	int ret;
 
 	mutex_lock(&epf_mhi->lock);
 
-	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, to, &tre_phys, &tre_buf,
-				      offset, size);
+	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, buf_info->host_addr, &tre_phys,
+				      &tre_buf, offset, buf_info->size);
 	if (ret) {
 		mutex_unlock(&epf_mhi->lock);
 		return ret;
 	}
 
-	memcpy_toio(tre_buf, from, size);
+	memcpy_toio(tre_buf, buf_info->dev_addr, buf_info->size);
 
-	__pci_epf_mhi_unmap_free(mhi_cntrl, to, tre_phys, tre_buf, offset,
-				 size);
+	__pci_epf_mhi_unmap_free(mhi_cntrl, buf_info->host_addr, tre_phys,
+				 tre_buf, offset, buf_info->size);
 
 	mutex_unlock(&epf_mhi->lock);
 
@@ -270,8 +270,8 @@ static void pci_epf_mhi_dma_callback(void *param)
 	complete(param);
 }
 
-static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
-				 void *to, size_t size)
+static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl,
+				 struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
 	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
@@ -284,13 +284,13 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 	dma_addr_t dst_addr;
 	int ret;
 
-	if (size < SZ_4K)
-		return pci_epf_mhi_iatu_read(mhi_cntrl, from, to, size);
+	if (buf_info->size < SZ_4K)
+		return pci_epf_mhi_iatu_read(mhi_cntrl, buf_info);
 
 	mutex_lock(&epf_mhi->lock);
 
 	config.direction = DMA_DEV_TO_MEM;
-	config.src_addr = from;
+	config.src_addr = buf_info->host_addr;
 
 	ret = dmaengine_slave_config(chan, &config);
 	if (ret) {
@@ -298,14 +298,16 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 		goto err_unlock;
 	}
 
-	dst_addr = dma_map_single(dma_dev, to, size, DMA_FROM_DEVICE);
+	dst_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_FROM_DEVICE);
 	ret = dma_mapping_error(dma_dev, dst_addr);
 	if (ret) {
 		dev_err(dev, "Failed to map remote memory\n");
 		goto err_unlock;
 	}
 
-	desc = dmaengine_prep_slave_single(chan, dst_addr, size, DMA_DEV_TO_MEM,
+	desc = dmaengine_prep_slave_single(chan, dst_addr, buf_info->size,
+					   DMA_DEV_TO_MEM,
 					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
 	if (!desc) {
 		dev_err(dev, "Failed to prepare DMA\n");
@@ -332,15 +334,15 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 	}
 
 err_unmap:
-	dma_unmap_single(dma_dev, dst_addr, size, DMA_FROM_DEVICE);
+	dma_unmap_single(dma_dev, dst_addr, buf_info->size, DMA_FROM_DEVICE);
 err_unlock:
 	mutex_unlock(&epf_mhi->lock);
 
 	return ret;
 }
 
-static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
-				  u64 to, size_t size)
+static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl,
+				  struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
 	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
@@ -353,13 +355,13 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 	dma_addr_t src_addr;
 	int ret;
 
-	if (size < SZ_4K)
-		return pci_epf_mhi_iatu_write(mhi_cntrl, from, to, size);
+	if (buf_info->size < SZ_4K)
+		return pci_epf_mhi_iatu_write(mhi_cntrl, buf_info);
 
 	mutex_lock(&epf_mhi->lock);
 
 	config.direction = DMA_MEM_TO_DEV;
-	config.dst_addr = to;
+	config.dst_addr = buf_info->host_addr;
 
 	ret = dmaengine_slave_config(chan, &config);
 	if (ret) {
@@ -367,14 +369,16 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 		goto err_unlock;
 	}
 
-	src_addr = dma_map_single(dma_dev, from, size, DMA_TO_DEVICE);
+	src_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_TO_DEVICE);
 	ret = dma_mapping_error(dma_dev, src_addr);
 	if (ret) {
 		dev_err(dev, "Failed to map remote memory\n");
 		goto err_unlock;
 	}
 
-	desc = dmaengine_prep_slave_single(chan, src_addr, size, DMA_MEM_TO_DEV,
+	desc = dmaengine_prep_slave_single(chan, src_addr, buf_info->size,
+					   DMA_MEM_TO_DEV,
 					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
 	if (!desc) {
 		dev_err(dev, "Failed to prepare DMA\n");
@@ -401,7 +405,7 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 	}
 
 err_unmap:
-	dma_unmap_single(dma_dev, src_addr, size, DMA_FROM_DEVICE);
+	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_FROM_DEVICE);
 err_unlock:
 	mutex_unlock(&epf_mhi->lock);
 
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index ce85d42b685d6..96f3a133540db 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -49,6 +49,18 @@ struct mhi_ep_db_info {
 	u32 status;
 };
 
+/**
+ * struct mhi_ep_buf_info - MHI Endpoint transfer buffer info
+ * @dev_addr: Address of the buffer in endpoint
+ * @host_addr: Address of the bufffer in host
+ * @size: Size of the buffer
+ */
+struct mhi_ep_buf_info {
+	void *dev_addr;
+	u64 host_addr;
+	size_t size;
+};
+
 /**
  * struct mhi_ep_cntrl - MHI Endpoint controller structure
  * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
@@ -137,8 +149,8 @@ struct mhi_ep_cntrl {
 			 void __iomem **virt, size_t size);
 	void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys,
 			   void __iomem *virt, size_t size);
-	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size);
-	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size);
+	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
-- 
GitLab


From 927105244f8bc48e6841826a5644c6a961e03b5d Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 27 Nov 2023 13:57:37 +0530
Subject: [PATCH 1300/4076] bus: mhi: ep: Rename read_from_host() and
 write_to_host() APIs

In the preparation for adding async API support, let's rename the existing
APIs to read_sync() and write_sync() to make it explicit that these APIs
are used for synchronous read/write.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c                    | 4 ++--
 drivers/bus/mhi/ep/ring.c                    | 8 ++++----
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 8 ++++----
 include/linux/mhi_ep.h                       | 8 ++++----
 4 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index b9334d548c410..88e189a8463a9 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -377,7 +377,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n");
 			return ret;
@@ -539,7 +539,7 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(dev, "Error writing to the channel\n");
 			goto err_exit;
diff --git a/drivers/bus/mhi/ep/ring.c b/drivers/bus/mhi/ep/ring.c
index 7ea952860def4..aeb53b2c34a8c 100644
--- a/drivers/bus/mhi/ep/ring.c
+++ b/drivers/bus/mhi/ep/ring.c
@@ -48,7 +48,7 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
 		buf_info.dev_addr = &ring->ring_cache[start];
 
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 	} else {
@@ -56,7 +56,7 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
 		buf_info.dev_addr = &ring->ring_cache[start];
 
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 
@@ -65,7 +65,7 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 			buf_info.dev_addr = &ring->ring_cache[0];
 			buf_info.size = end * sizeof(struct mhi_ring_element);
 
-			ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
+			ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 			if (ret < 0)
 				return ret;
 		}
@@ -143,7 +143,7 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 	buf_info.dev_addr = el;
 	buf_info.size = sizeof(*el);
 
-	return mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
+	return mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
 }
 
 void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32 id)
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index ec5f4a38178bb..2c5b627eb5ee6 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -536,11 +536,11 @@ static int pci_epf_mhi_link_up(struct pci_epf *epf)
 	mhi_cntrl->alloc_map = pci_epf_mhi_alloc_map;
 	mhi_cntrl->unmap_free = pci_epf_mhi_unmap_free;
 	if (info->flags & MHI_EPF_USE_DMA) {
-		mhi_cntrl->read_from_host = pci_epf_mhi_edma_read;
-		mhi_cntrl->write_to_host = pci_epf_mhi_edma_write;
+		mhi_cntrl->read_sync = pci_epf_mhi_edma_read;
+		mhi_cntrl->write_sync = pci_epf_mhi_edma_write;
 	} else {
-		mhi_cntrl->read_from_host = pci_epf_mhi_iatu_read;
-		mhi_cntrl->write_to_host = pci_epf_mhi_iatu_write;
+		mhi_cntrl->read_sync = pci_epf_mhi_iatu_read;
+		mhi_cntrl->write_sync = pci_epf_mhi_iatu_write;
 	}
 
 	/* Register the MHI EP controller */
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 96f3a133540db..b96b543bf2f65 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -94,8 +94,8 @@ struct mhi_ep_buf_info {
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
- * @read_from_host: CB function for reading from host memory from endpoint
- * @write_to_host: CB function for writing to host memory from endpoint
+ * @read_sync: CB function for reading from host memory synchronously
+ * @write_sync: CB function for writing to host memory synchronously
  * @mhi_state: MHI Endpoint state
  * @max_chan: Maximum channels supported by the endpoint controller
  * @mru: MRU (Maximum Receive Unit) value of the endpoint controller
@@ -149,8 +149,8 @@ struct mhi_ep_cntrl {
 			 void __iomem **virt, size_t size);
 	void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys,
 			   void __iomem *virt, size_t size);
-	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
-	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*read_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
-- 
GitLab


From 8b786ed8fb089e347af21d13ba5677325fcd4cd8 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 27 Nov 2023 15:35:50 +0530
Subject: [PATCH 1301/4076] bus: mhi: ep: Introduce async read/write callbacks

These callbacks can be implemented by the controller drivers to perform
async read/write operation that increases the throughput.

For aiding the async operation, a completion callback is also introduced.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 include/linux/mhi_ep.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index b96b543bf2f65..14c6e8d3f5736 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -54,11 +54,16 @@ struct mhi_ep_db_info {
  * @dev_addr: Address of the buffer in endpoint
  * @host_addr: Address of the bufffer in host
  * @size: Size of the buffer
+ * @cb: Callback to be executed by controller drivers after transfer completion (async)
+ * @cb_buf: Opaque buffer to be passed to the callback
  */
 struct mhi_ep_buf_info {
 	void *dev_addr;
 	u64 host_addr;
 	size_t size;
+
+	void (*cb)(struct mhi_ep_buf_info *buf_info);
+	void *cb_buf;
 };
 
 /**
@@ -96,6 +101,8 @@ struct mhi_ep_buf_info {
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
  * @read_sync: CB function for reading from host memory synchronously
  * @write_sync: CB function for writing to host memory synchronously
+ * @read_async: CB function for reading from host memory asynchronously
+ * @write_async: CB function for writing to host memory asynchronously
  * @mhi_state: MHI Endpoint state
  * @max_chan: Maximum channels supported by the endpoint controller
  * @mru: MRU (Maximum Receive Unit) value of the endpoint controller
@@ -151,6 +158,8 @@ struct mhi_ep_cntrl {
 			   void __iomem *virt, size_t size);
 	int (*read_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 	int (*write_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*read_async)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_async)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
-- 
GitLab


From 5424be958b446601d6176396d9dbaad2178db610 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 27 Nov 2023 15:48:54 +0530
Subject: [PATCH 1302/4076] PCI: epf-mhi: Simulate async read/write using iATU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Even though iATU only supports synchronous read/write, the MHI stack may
call async read/write callbacks without knowing the limitations of the
controller driver. So in order to maintain compatibility, let's simulate
async read/write operation with iATU by invoking the completion callback
after memcpy.

Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Krzysztof Wilczyński <kw@linux.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index 2c5b627eb5ee6..d9f45822e6705 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -234,6 +234,9 @@ static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl,
 
 	mutex_unlock(&epf_mhi->lock);
 
+	if (buf_info->cb)
+		buf_info->cb(buf_info);
+
 	return 0;
 }
 
@@ -262,6 +265,9 @@ static int pci_epf_mhi_iatu_write(struct mhi_ep_cntrl *mhi_cntrl,
 
 	mutex_unlock(&epf_mhi->lock);
 
+	if (buf_info->cb)
+		buf_info->cb(buf_info);
+
 	return 0;
 }
 
-- 
GitLab


From 0d5d5738dc206e531d3a70c6a81fde4e9fa40b5d Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Thu, 2 Nov 2023 20:03:58 +0530
Subject: [PATCH 1303/4076] PCI: epf-mhi: Add support for DMA async read/write
 operation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver currently supports only the sync read/write operation i.e., it
waits for the DMA transfer to complete before returning to the caller
(MHI stack). But it is sub-optimal and defeats the actual purpose of using
DMA.

So let's add support for DMA async read/write operation by skipping the DMA
transfer completion and returning to the caller immediately. When the
completion actually happens later, the driver will be notified using the
DMA completion handler and in turn it will notify the caller using the
newly introduced callback in "struct mhi_ep_buf_info".

Since the DMA completion handler is invoked from the interrupt context, a
separate workqueue (epf_mhi->dma_wq) is used to notify the caller about the
completion of the transfer.

Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Krzysztof Wilczyński <kw@linux.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 231 ++++++++++++++++++-
 1 file changed, 228 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index d9f45822e6705..596fd205a3145 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -21,6 +21,15 @@
 /* Platform specific flags */
 #define MHI_EPF_USE_DMA BIT(0)
 
+struct pci_epf_mhi_dma_transfer {
+	struct pci_epf_mhi *epf_mhi;
+	struct mhi_ep_buf_info buf_info;
+	struct list_head node;
+	dma_addr_t paddr;
+	enum dma_data_direction dir;
+	size_t size;
+};
+
 struct pci_epf_mhi_ep_info {
 	const struct mhi_ep_cntrl_config *config;
 	struct pci_epf_header *epf_header;
@@ -124,6 +133,10 @@ struct pci_epf_mhi {
 	resource_size_t mmio_phys;
 	struct dma_chan *dma_chan_tx;
 	struct dma_chan *dma_chan_rx;
+	struct workqueue_struct *dma_wq;
+	struct work_struct dma_work;
+	struct list_head dma_list;
+	spinlock_t list_lock;
 	u32 mmio_size;
 	int irq;
 };
@@ -418,6 +431,198 @@ err_unlock:
 	return ret;
 }
 
+static void pci_epf_mhi_dma_worker(struct work_struct *work)
+{
+	struct pci_epf_mhi *epf_mhi = container_of(work, struct pci_epf_mhi, dma_work);
+	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
+	struct pci_epf_mhi_dma_transfer *itr, *tmp;
+	struct mhi_ep_buf_info *buf_info;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&epf_mhi->list_lock, flags);
+	list_splice_tail_init(&epf_mhi->dma_list, &head);
+	spin_unlock_irqrestore(&epf_mhi->list_lock, flags);
+
+	list_for_each_entry_safe(itr, tmp, &head, node) {
+		list_del(&itr->node);
+		dma_unmap_single(dma_dev, itr->paddr, itr->size, itr->dir);
+		buf_info = &itr->buf_info;
+		buf_info->cb(buf_info);
+		kfree(itr);
+	}
+}
+
+static void pci_epf_mhi_dma_async_callback(void *param)
+{
+	struct pci_epf_mhi_dma_transfer *transfer = param;
+	struct pci_epf_mhi *epf_mhi = transfer->epf_mhi;
+
+	spin_lock(&epf_mhi->list_lock);
+	list_add_tail(&transfer->node, &epf_mhi->dma_list);
+	spin_unlock(&epf_mhi->list_lock);
+
+	queue_work(epf_mhi->dma_wq, &epf_mhi->dma_work);
+}
+
+static int pci_epf_mhi_edma_read_async(struct mhi_ep_cntrl *mhi_cntrl,
+				       struct mhi_ep_buf_info *buf_info)
+{
+	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
+	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
+	struct pci_epf_mhi_dma_transfer *transfer = NULL;
+	struct dma_chan *chan = epf_mhi->dma_chan_rx;
+	struct device *dev = &epf_mhi->epf->dev;
+	DECLARE_COMPLETION_ONSTACK(complete);
+	struct dma_async_tx_descriptor *desc;
+	struct dma_slave_config config = {};
+	dma_cookie_t cookie;
+	dma_addr_t dst_addr;
+	int ret;
+
+	mutex_lock(&epf_mhi->lock);
+
+	config.direction = DMA_DEV_TO_MEM;
+	config.src_addr = buf_info->host_addr;
+
+	ret = dmaengine_slave_config(chan, &config);
+	if (ret) {
+		dev_err(dev, "Failed to configure DMA channel\n");
+		goto err_unlock;
+	}
+
+	dst_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_FROM_DEVICE);
+	ret = dma_mapping_error(dma_dev, dst_addr);
+	if (ret) {
+		dev_err(dev, "Failed to map remote memory\n");
+		goto err_unlock;
+	}
+
+	desc = dmaengine_prep_slave_single(chan, dst_addr, buf_info->size,
+					   DMA_DEV_TO_MEM,
+					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
+	if (!desc) {
+		dev_err(dev, "Failed to prepare DMA\n");
+		ret = -EIO;
+		goto err_unmap;
+	}
+
+	transfer = kzalloc(sizeof(*transfer), GFP_KERNEL);
+	if (!transfer) {
+		ret = -ENOMEM;
+		goto err_unmap;
+	}
+
+	transfer->epf_mhi = epf_mhi;
+	transfer->paddr = dst_addr;
+	transfer->size = buf_info->size;
+	transfer->dir = DMA_FROM_DEVICE;
+	memcpy(&transfer->buf_info, buf_info, sizeof(*buf_info));
+
+	desc->callback = pci_epf_mhi_dma_async_callback;
+	desc->callback_param = transfer;
+
+	cookie = dmaengine_submit(desc);
+	ret = dma_submit_error(cookie);
+	if (ret) {
+		dev_err(dev, "Failed to do DMA submit\n");
+		goto err_free_transfer;
+	}
+
+	dma_async_issue_pending(chan);
+
+	goto err_unlock;
+
+err_free_transfer:
+	kfree(transfer);
+err_unmap:
+	dma_unmap_single(dma_dev, dst_addr, buf_info->size, DMA_FROM_DEVICE);
+err_unlock:
+	mutex_unlock(&epf_mhi->lock);
+
+	return ret;
+}
+
+static int pci_epf_mhi_edma_write_async(struct mhi_ep_cntrl *mhi_cntrl,
+					struct mhi_ep_buf_info *buf_info)
+{
+	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
+	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
+	struct pci_epf_mhi_dma_transfer *transfer = NULL;
+	struct dma_chan *chan = epf_mhi->dma_chan_tx;
+	struct device *dev = &epf_mhi->epf->dev;
+	DECLARE_COMPLETION_ONSTACK(complete);
+	struct dma_async_tx_descriptor *desc;
+	struct dma_slave_config config = {};
+	dma_cookie_t cookie;
+	dma_addr_t src_addr;
+	int ret;
+
+	mutex_lock(&epf_mhi->lock);
+
+	config.direction = DMA_MEM_TO_DEV;
+	config.dst_addr = buf_info->host_addr;
+
+	ret = dmaengine_slave_config(chan, &config);
+	if (ret) {
+		dev_err(dev, "Failed to configure DMA channel\n");
+		goto err_unlock;
+	}
+
+	src_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_TO_DEVICE);
+	ret = dma_mapping_error(dma_dev, src_addr);
+	if (ret) {
+		dev_err(dev, "Failed to map remote memory\n");
+		goto err_unlock;
+	}
+
+	desc = dmaengine_prep_slave_single(chan, src_addr, buf_info->size,
+					   DMA_MEM_TO_DEV,
+					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
+	if (!desc) {
+		dev_err(dev, "Failed to prepare DMA\n");
+		ret = -EIO;
+		goto err_unmap;
+	}
+
+	transfer = kzalloc(sizeof(*transfer), GFP_KERNEL);
+	if (!transfer) {
+		ret = -ENOMEM;
+		goto err_unmap;
+	}
+
+	transfer->epf_mhi = epf_mhi;
+	transfer->paddr = src_addr;
+	transfer->size = buf_info->size;
+	transfer->dir = DMA_TO_DEVICE;
+	memcpy(&transfer->buf_info, buf_info, sizeof(*buf_info));
+
+	desc->callback = pci_epf_mhi_dma_async_callback;
+	desc->callback_param = transfer;
+
+	cookie = dmaengine_submit(desc);
+	ret = dma_submit_error(cookie);
+	if (ret) {
+		dev_err(dev, "Failed to do DMA submit\n");
+		goto err_free_transfer;
+	}
+
+	dma_async_issue_pending(chan);
+
+	goto err_unlock;
+
+err_free_transfer:
+	kfree(transfer);
+err_unmap:
+	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_TO_DEVICE);
+err_unlock:
+	mutex_unlock(&epf_mhi->lock);
+
+	return ret;
+}
+
 struct epf_dma_filter {
 	struct device *dev;
 	u32 dma_mask;
@@ -441,6 +646,7 @@ static int pci_epf_mhi_dma_init(struct pci_epf_mhi *epf_mhi)
 	struct device *dev = &epf_mhi->epf->dev;
 	struct epf_dma_filter filter;
 	dma_cap_mask_t mask;
+	int ret;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
@@ -459,16 +665,35 @@ static int pci_epf_mhi_dma_init(struct pci_epf_mhi *epf_mhi)
 						   &filter);
 	if (IS_ERR_OR_NULL(epf_mhi->dma_chan_rx)) {
 		dev_err(dev, "Failed to request rx channel\n");
-		dma_release_channel(epf_mhi->dma_chan_tx);
-		epf_mhi->dma_chan_tx = NULL;
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_release_tx;
+	}
+
+	epf_mhi->dma_wq = alloc_workqueue("pci_epf_mhi_dma_wq", 0, 0);
+	if (!epf_mhi->dma_wq) {
+		ret = -ENOMEM;
+		goto err_release_rx;
 	}
 
+	INIT_LIST_HEAD(&epf_mhi->dma_list);
+	INIT_WORK(&epf_mhi->dma_work, pci_epf_mhi_dma_worker);
+	spin_lock_init(&epf_mhi->list_lock);
+
 	return 0;
+
+err_release_rx:
+	dma_release_channel(epf_mhi->dma_chan_rx);
+	epf_mhi->dma_chan_rx = NULL;
+err_release_tx:
+	dma_release_channel(epf_mhi->dma_chan_tx);
+	epf_mhi->dma_chan_tx = NULL;
+
+	return ret;
 }
 
 static void pci_epf_mhi_dma_deinit(struct pci_epf_mhi *epf_mhi)
 {
+	destroy_workqueue(epf_mhi->dma_wq);
 	dma_release_channel(epf_mhi->dma_chan_tx);
 	dma_release_channel(epf_mhi->dma_chan_rx);
 	epf_mhi->dma_chan_tx = NULL;
-- 
GitLab


From d1c6f4ba4746ed41fde8269cb5fea88bddb60504 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 27 Nov 2023 16:36:24 +0530
Subject: [PATCH 1304/4076] PCI: epf-mhi: Enable MHI async read/write support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that both eDMA and iATU are prepared to support async transfer, let's
enable MHI async read/write by supplying the relevant callbacks.

In the absence of eDMA, iATU will be used for both sync and async
operations.

Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Krzysztof Wilczyński <kw@linux.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index 596fd205a3145..472bc489b754b 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -766,12 +766,13 @@ static int pci_epf_mhi_link_up(struct pci_epf *epf)
 	mhi_cntrl->raise_irq = pci_epf_mhi_raise_irq;
 	mhi_cntrl->alloc_map = pci_epf_mhi_alloc_map;
 	mhi_cntrl->unmap_free = pci_epf_mhi_unmap_free;
+	mhi_cntrl->read_sync = mhi_cntrl->read_async = pci_epf_mhi_iatu_read;
+	mhi_cntrl->write_sync = mhi_cntrl->write_async = pci_epf_mhi_iatu_write;
 	if (info->flags & MHI_EPF_USE_DMA) {
 		mhi_cntrl->read_sync = pci_epf_mhi_edma_read;
 		mhi_cntrl->write_sync = pci_epf_mhi_edma_write;
-	} else {
-		mhi_cntrl->read_sync = pci_epf_mhi_iatu_read;
-		mhi_cntrl->write_sync = pci_epf_mhi_iatu_write;
+		mhi_cntrl->read_async = pci_epf_mhi_edma_read_async;
+		mhi_cntrl->write_async = pci_epf_mhi_edma_write_async;
 	}
 
 	/* Register the MHI EP controller */
-- 
GitLab


From 7a92fc8b4d20680e4c20289a670d8fca2d1f2c1b Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 12 Dec 2023 22:34:56 +0100
Subject: [PATCH 1305/4076] mm: Introduce flush_cache_vmap_early()

The pcpu setup when using the page allocator sets up a new vmalloc
mapping very early in the boot process, so early that it cannot use the
flush_cache_vmap() function which may depend on structures not yet
initialized (for example in riscv, we currently send an IPI to flush
other cpus TLB).

But on some architectures, we must call flush_cache_vmap(): for example,
in riscv, some uarchs can cache invalid TLB entries so we need to flush
the new established mapping to avoid taking an exception.

So fix this by introducing a new function flush_cache_vmap_early() which
is called right after setting the new page table entry and before
accessing this new mapping. This new function implements a local flush
tlb on riscv and is no-op for other architectures (same as today).

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
---
 arch/arc/include/asm/cacheflush.h      | 1 +
 arch/arm/include/asm/cacheflush.h      | 2 ++
 arch/csky/abiv1/inc/abi/cacheflush.h   | 1 +
 arch/csky/abiv2/inc/abi/cacheflush.h   | 1 +
 arch/m68k/include/asm/cacheflush_mm.h  | 1 +
 arch/mips/include/asm/cacheflush.h     | 2 ++
 arch/nios2/include/asm/cacheflush.h    | 1 +
 arch/parisc/include/asm/cacheflush.h   | 1 +
 arch/riscv/include/asm/cacheflush.h    | 3 ++-
 arch/riscv/include/asm/tlbflush.h      | 1 +
 arch/riscv/mm/tlbflush.c               | 5 +++++
 arch/sh/include/asm/cacheflush.h       | 1 +
 arch/sparc/include/asm/cacheflush_32.h | 1 +
 arch/sparc/include/asm/cacheflush_64.h | 1 +
 arch/xtensa/include/asm/cacheflush.h   | 6 ++++--
 include/asm-generic/cacheflush.h       | 6 ++++++
 mm/percpu.c                            | 8 +-------
 17 files changed, 32 insertions(+), 10 deletions(-)

diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index bd5b1a9a05440..6fc74500a9f52 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -40,6 +40,7 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz);
 
 /* TBD: optimize this */
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 #define flush_cache_dup_mm(mm)			/* called on fork (VIVT only) */
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index f6181f69577fe..1075534b0a2ee 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -340,6 +340,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		dsb(ishst);
 }
 
+#define flush_cache_vmap_early(start, end)	do { } while (0)
+
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
 	if (!cache_is_vipt_nonaliasing())
diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h
index 908d8b0bc4fdc..d011a81575d21 100644
--- a/arch/csky/abiv1/inc/abi/cacheflush.h
+++ b/arch/csky/abiv1/inc/abi/cacheflush.h
@@ -43,6 +43,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
  */
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 #define flush_cache_vmap(start, end)		cache_wbinv_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		cache_wbinv_all()
 
 #define flush_icache_range(start, end)		cache_wbinv_range(start, end)
diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h
index 40be16907267d..6513ac5d25788 100644
--- a/arch/csky/abiv2/inc/abi/cacheflush.h
+++ b/arch/csky/abiv2/inc/abi/cacheflush.h
@@ -41,6 +41,7 @@ void flush_icache_mm_range(struct mm_struct *mm,
 void flush_icache_deferred(struct mm_struct *mm);
 
 #define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h
index ed12358c4783b..9a71b0148461a 100644
--- a/arch/m68k/include/asm/cacheflush_mm.h
+++ b/arch/m68k/include/asm/cacheflush_mm.h
@@ -191,6 +191,7 @@ extern void cache_push_v(unsigned long vaddr, int len);
 #define flush_cache_all() __flush_cache_all()
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 static inline void flush_cache_mm(struct mm_struct *mm)
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index f36c2519ed976..1f14132b3fc98 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -97,6 +97,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		__flush_cache_vmap();
 }
 
+#define flush_cache_vmap_early(start, end)     do { } while (0)
+
 extern void (*__flush_cache_vunmap)(void);
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h
index 348cea0977927..81484a776b333 100644
--- a/arch/nios2/include/asm/cacheflush.h
+++ b/arch/nios2/include/asm/cacheflush.h
@@ -38,6 +38,7 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
 #define flush_icache_pages flush_icache_pages
 
 #define flush_cache_vmap(start, end)		flush_dcache_range(start, end)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_dcache_range(start, end)
 
 extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index b4006f2a97052..ba4c05bc24d69 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -41,6 +41,7 @@ void flush_kernel_vmap_range(void *vaddr, int size);
 void invalidate_kernel_vmap_range(void *vaddr, int size);
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 void flush_dcache_folio(struct folio *folio);
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 3cb53c4df27cf..a129dac4521d3 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -37,7 +37,8 @@ static inline void flush_dcache_page(struct page *page)
 	flush_icache_mm(vma->vm_mm, 0)
 
 #ifdef CONFIG_64BIT
-#define flush_cache_vmap(start, end)	flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap(start, end)		flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap_early(start, end)	local_flush_tlb_kernel_range(start, end)
 #endif
 
 #ifndef CONFIG_SMP
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 8f3418c5f1724..a60416bbe1904 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -41,6 +41,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
 void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index e6659d7368b35..8aadc5f71c93b 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -66,6 +66,11 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+}
+
 static void __ipi_flush_tlb_all(void *info)
 {
 	local_flush_tlb_all();
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index 878b6b551bd2d..51112f54552b3 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -90,6 +90,7 @@ extern void copy_from_user_page(struct vm_area_struct *vma,
 	unsigned long len);
 
 #define flush_cache_vmap(start, end)		local_flush_cache_all(NULL)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		local_flush_cache_all(NULL)
 
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h
index f3b7270bf71b2..9fee0ccfccb8e 100644
--- a/arch/sparc/include/asm/cacheflush_32.h
+++ b/arch/sparc/include/asm/cacheflush_32.h
@@ -48,6 +48,7 @@ static inline void flush_dcache_page(struct page *page)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 /* When a context switch happens we must flush all user windows so that
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index 0e879004efff1..2b1261b77ecd1 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -75,6 +75,7 @@ void flush_ptrace_access(struct vm_area_struct *, struct page *,
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 #define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index 785a00ce83c11..38bcecb0e457d 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -116,8 +116,9 @@ void flush_cache_page(struct vm_area_struct*,
 #define flush_cache_mm(mm)		flush_cache_all()
 #define flush_cache_dup_mm(mm)		flush_cache_mm(mm)
 
-#define flush_cache_vmap(start,end)	flush_cache_all()
-#define flush_cache_vunmap(start,end)	flush_cache_all()
+#define flush_cache_vmap(start,end)		flush_cache_all()
+#define flush_cache_vmap_early(start,end)	do { } while (0)
+#define flush_cache_vunmap(start,end)		flush_cache_all()
 
 void flush_dcache_folio(struct folio *folio);
 #define flush_dcache_folio flush_dcache_folio
@@ -140,6 +141,7 @@ void local_flush_cache_page(struct vm_area_struct *vma,
 #define flush_cache_dup_mm(mm)				do { } while (0)
 
 #define flush_cache_vmap(start,end)			do { } while (0)
+#define flush_cache_vmap_early(start,end)		do { } while (0)
 #define flush_cache_vunmap(start,end)			do { } while (0)
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index 84ec53ccc4502..7ee8a179d1036 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -91,6 +91,12 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 }
 #endif
 
+#ifndef flush_cache_vmap_early
+static inline void flush_cache_vmap_early(unsigned long start, unsigned long end)
+{
+}
+#endif
+
 #ifndef flush_cache_vunmap
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
diff --git a/mm/percpu.c b/mm/percpu.c
index 7b97d31df7676..4e11fc1e6deff 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3333,13 +3333,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 		if (rc < 0)
 			panic("failed to map percpu area, err=%d\n", rc);
 
-		/*
-		 * FIXME: Archs with virtual cache should flush local
-		 * cache for the linear mapping here - something
-		 * equivalent to flush_cache_vmap() on the local cpu.
-		 * flush_cache_vmap() can't be used as most supporting
-		 * data structures are not set up yet.
-		 */
+		flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
 
 		/* copy static data */
 		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
-- 
GitLab


From 6b9f29b81b155af023da95f560f738f29722b306 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 12 Dec 2023 22:34:57 +0100
Subject: [PATCH 1306/4076] riscv: Enable pcpu page first chunk allocator

As explained in commit 6ea529a2037c ("percpu: make embedding first chunk
allocator check vmalloc space size"), the embedding first chunk allocator
needs the vmalloc space to be larger than the maximum distance between
units which are grouped into NUMA nodes.

On a very sparse NUMA configurations and a small vmalloc area (for example,
it is 64GB in sv39), the allocation of dynamic percpu data in the vmalloc
area could fail.

So provide the pcpu page allocator as a fallback in case we fall into
such a sparse configuration (which happened in arm64 as shown by
commit 09cea6195073 ("arm64: support page mapping percpu first chunk
allocator")).

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
---
 arch/riscv/Kconfig         | 2 ++
 arch/riscv/mm/kasan_init.c | 8 ++++++++
 2 files changed, 10 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a6..80e9b2ac34ab2 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -414,7 +414,9 @@ config NUMA
 	depends on SMP && MMU
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select GENERIC_ARCH_NUMA
+	select HAVE_SETUP_PER_CPU_AREA
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK
+	select NEED_PER_CPU_PAGE_FIRST_CHUNK
 	select OF_NUMA
 	select USE_PERCPU_NUMA_NODE_ID
 	help
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 5e39dcf23fdbc..4c9a2c527f08f 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -438,6 +438,14 @@ static void __init kasan_shallow_populate(void *start, void *end)
 	kasan_shallow_populate_pgd(vaddr, vend);
 }
 
+#ifdef CONFIG_KASAN_VMALLOC
+void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size)
+{
+	kasan_populate(kasan_mem_to_shadow(start),
+		       kasan_mem_to_shadow(start + size));
+}
+#endif
+
 static void __init create_tmp_mapping(void)
 {
 	void *ptr;
-- 
GitLab


From ec215237480478ca5523ea12f58803d9b7a8a0ea Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 7 Dec 2023 10:52:50 -0600
Subject: [PATCH 1307/4076] PCI: rcar-gen4: Replace of_device.h with explicit
 of.h include
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it was merged into the regular platform
bus.

As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h.

As a result, there's a pretty much random mix of those include files
used throughout the tree. In order to detangle these headers and replace
the implicit includes with struct declarations, users need to explicitly
include the correct includes.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20231207165251.2855783-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
---
 drivers/pci/controller/dwc/pcie-rcar-gen4.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 3bc45e513b3d5..2ca5b7983d623 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
-- 
GitLab


From b952f96a57e6fb4528c1d6be19e941c3322f9905 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sun, 5 Nov 2023 10:29:07 +0100
Subject: [PATCH 1308/4076] dt-bindings: PCI: rcar-pci-host: Add optional
 regulators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Support regulators found on the KingFisher board for miniPCIe (1.5 and
3.3v). For completeness, describe a 12v regulator while we are here.

Link: https://lore.kernel.org/linux-pci/20231105092908.3792-2-wsa+renesas@sang-engineering.com
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../devicetree/bindings/pci/rcar-pci-host.yaml        | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
index 8fdfbc763d704..b6a7cb32f61e5 100644
--- a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
+++ b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
@@ -68,6 +68,15 @@ properties:
   phy-names:
     const: pcie
 
+  vpcie1v5-supply:
+    description: The 1.5v regulator to use for PCIe.
+
+  vpcie3v3-supply:
+    description: The 3.3v regulator to use for PCIe.
+
+  vpcie12v-supply:
+    description: The 12v regulator to use for PCIe.
+
 required:
   - compatible
   - reg
@@ -121,5 +130,7 @@ examples:
              clock-names = "pcie", "pcie_bus";
              power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
              resets = <&cpg 319>;
+             vpcie3v3-supply = <&pcie_3v3>;
+             vpcie12v-supply = <&pcie_12v>;
          };
     };
-- 
GitLab


From 6797e4da2dd1e2c8dc8cec73447c77abe2a7655b Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sun, 5 Nov 2023 10:29:08 +0100
Subject: [PATCH 1309/4076] PCI: rcar-host: Add support for optional regulators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The KingFisher board has regulators for miniPCIe, so enable these
optional regulators using devm. devm will automatically disable them
when the driver releases the device. Order variables in reverse-xmas
while we are here.

[kwilczynski: update style to match rest of the code]
Link: https://lore.kernel.org/linux-pci/20231105092908.3792-3-wsa+renesas@sang-engineering.com
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Manivannan Sadhasivam <mani@kernel.org>
---
 drivers/pci/controller/pcie-rcar-host.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c
index bf7cc0b6a6957..996077ab7cfdb 100644
--- a/drivers/pci/controller/pcie-rcar-host.c
+++ b/drivers/pci/controller/pcie-rcar-host.c
@@ -29,6 +29,7 @@
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
 
 #include "pcie-rcar.h"
 
@@ -953,14 +954,22 @@ static const struct of_device_id rcar_pcie_of_match[] = {
 	{},
 };
 
+/* Design note 346 from Linear Technology says order is not important. */
+static const char * const rcar_pcie_supplies[] = {
+	"vpcie1v5",
+	"vpcie3v3",
+	"vpcie12v",
+};
+
 static int rcar_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct pci_host_bridge *bridge;
 	struct rcar_pcie_host *host;
 	struct rcar_pcie *pcie;
+	unsigned int i;
 	u32 data;
 	int err;
-	struct pci_host_bridge *bridge;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(*host));
 	if (!bridge)
@@ -971,6 +980,13 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 	pcie->dev = dev;
 	platform_set_drvdata(pdev, host);
 
+	for (i = 0; i < ARRAY_SIZE(rcar_pcie_supplies); i++) {
+		err = devm_regulator_get_enable_optional(dev, rcar_pcie_supplies[i]);
+		if (err < 0 && err != -ENODEV)
+			return dev_err_probe(dev, err, "failed to enable regulator: %s\n",
+					     rcar_pcie_supplies[i]);
+	}
+
 	pm_runtime_enable(pcie->dev);
 	err = pm_runtime_get_sync(pcie->dev);
 	if (err < 0) {
-- 
GitLab


From 6f33e6fa29d0366d6e5b3ea2930dbc0b648151fe Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 13 Dec 2023 22:02:56 -0800
Subject: [PATCH 1310/4076] perf stat: Combine the -A/--no-aggr and --no-merge
 options

The -A or --no-aggr option disables aggregation of core events:

  $ perf stat -A -e cycles,data_total -a true

   Performance counter stats for 'system wide':

  CPU0            1,287,665      cycles
  CPU1            1,831,681      cycles
  CPU2           27,345,998      cycles
  CPU3            1,964,799      cycles
  CPU4              236,174      cycles
  CPU5            3,302,825      cycles
  CPU6            9,201,446      cycles
  CPU7            1,403,043      cycles
  CPU0               110.90 MiB  data_total

         0.008961761 seconds time elapsed

The --no-merge option disables the aggregation of uncore events:

  $ perf stat --no-merge -e cycles,data_total -a true

   Performance counter stats for 'system wide':

          38,482,778      cycles
               15.04 MiB  data_total [uncore_imc_free_running_1]
               15.00 MiB  data_total [uncore_imc_free_running_0]

         0.005915155 seconds time elapsed

Having two options confuses users who generally don't appreciate the
difference in PMUs. Keep all the options but make it so they all
disable aggregation both of core and uncore events:

  $ perf stat -A -e cycles,data_total -a true

   Performance counter stats for 'system wide':

  CPU0               85,878      cycles
  CPU1               88,179      cycles
  CPU2               60,872      cycles
  CPU3            3,265,567      cycles
  CPU4               82,357      cycles
  CPU5               83,383      cycles
  CPU6               84,156      cycles
  CPU7              220,803      cycles
  CPU0                 2.38 MiB  data_total [uncore_imc_free_running_0]
  CPU0                 2.38 MiB  data_total [uncore_imc_free_running_1]

         0.001397205 seconds time elapsed

Update the relevant 'perf stat' man page information.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kaige Ye <ye@kaige.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231214060256.2094017-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-stat.txt | 52 ++++++++++++++------------
 tools/perf/builtin-stat.c              |  5 ++-
 tools/perf/util/stat-display.c         |  2 +-
 tools/perf/util/stat.c                 |  2 +-
 tools/perf/util/stat.h                 |  1 -
 5 files changed, 33 insertions(+), 29 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 8f789fa1242e0..5af2e432b54fb 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -422,7 +422,34 @@ See perf list output for the possible metrics and metricgroups.
 
 -A::
 --no-aggr::
-Do not aggregate counts across all monitored CPUs.
+--no-merge::
+Do not aggregate/merge counts across monitored CPUs or PMUs.
+
+When multiple events are created from a single event specification,
+stat will, by default, aggregate the event counts and show the result
+in a single row. This option disables that behavior and shows the
+individual events and counts.
+
+Multiple events are created from a single event specification when:
+
+1. PID monitoring isn't requested and the system has more than one
+   CPU. For example, a system with 8 SMT threads will have one event
+   opened on each thread and aggregation is performed across them.
+
+2. Prefix or glob wildcard matching is used for the PMU name. For
+   example, multiple memory controller PMUs may exist typically with a
+   suffix of _0, _1, etc. By default the event counts will all be
+   combined if the PMU is specified without the suffix such as
+   uncore_imc rather than uncore_imc_0.
+
+3. Aliases, which are listed immediately after the Kernel PMU events
+   by perf list, are used.
+
+--hybrid-merge::
+Merge core event counts from all core PMUs. In hybrid or big.LITTLE
+systems by default each core PMU will report its count
+separately. This option forces core PMU counts to be combined to give
+a behavior closer to having a single CPU type in the system.
 
 --topdown::
 Print top-down metrics supported by the CPU. This allows to determine
@@ -475,29 +502,6 @@ highlight 'tma_frontend_bound'. This metric may be drilled into with
 
 Error out if the input is higher than the supported max level.
 
---no-merge::
-Do not merge results from same PMUs.
-
-When multiple events are created from a single event specification,
-stat will, by default, aggregate the event counts and show the result
-in a single row. This option disables that behavior and shows
-the individual events and counts.
-
-Multiple events are created from a single event specification when:
-1. Prefix or glob matching is used for the PMU name.
-2. Aliases, which are listed immediately after the Kernel PMU events
-   by perf list, are used.
-
---hybrid-merge::
-Merge the hybrid event counts from all PMUs.
-
-For hybrid events, by default, the stat aggregates and reports the event
-counts per PMU. But sometimes, it's also useful to aggregate event counts
-from all PMUs. This option enables that behavior and reports the counts
-without PMUs.
-
-For non-hybrid events, it should be no effect.
-
 --smi-cost::
 Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index bda020c0b9d52..5fe9abc6a5241 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1204,8 +1204,9 @@ static struct option stat_options[] = {
 	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
 		    "list of cpus to monitor in system-wide"),
 	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
-		    "disable CPU count aggregation", AGGR_NONE),
-	OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"),
+		    "disable aggregation across CPUs or PMUs", AGGR_NONE),
+	OPT_SET_UINT(0, "no-merge", &stat_config.aggr_mode,
+		    "disable aggregation the same as -A or -no-aggr", AGGR_NONE),
 	OPT_BOOLEAN(0, "hybrid-merge", &stat_config.hybrid_merge,
 		    "Merge identical named hybrid events"),
 	OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index afe6db8e7bf4f..8c61f8627ebc9 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -898,7 +898,7 @@ static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config
 
 static void uniquify_counter(struct perf_stat_config *config, struct evsel *counter)
 {
-	if (config->no_merge || hybrid_uniquify(counter, config))
+	if (config->aggr_mode == AGGR_NONE || hybrid_uniquify(counter, config))
 		uniquify_event_name(counter);
 }
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 012c4946b9c49..b0bcf92f0f9c3 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -592,7 +592,7 @@ void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *ev
 {
 	struct evsel *evsel;
 
-	if (config->no_merge)
+	if (config->aggr_mode == AGGR_NONE)
 		return;
 
 	evlist__for_each_entry(evlist, evsel)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 325d0fad18424..4357ba1148221 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -76,7 +76,6 @@ struct perf_stat_config {
 	bool			 null_run;
 	bool			 ru_display;
 	bool			 big_num;
-	bool			 no_merge;
 	bool			 hybrid_merge;
 	bool			 walltime_run_table;
 	bool			 all_kernel;
-- 
GitLab


From 1af478903fc48c1409a8dd6b698383b62387adf1 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 11 Dec 2023 23:05:44 -0800
Subject: [PATCH 1311/4076] perf genelf: Set ELF program header addresses
 properly

The text section starts after the ELF headers so PHDR.p_vaddr and
others should have the correct addresses.

Fixes: babd04386b1df8c3 ("perf jit: Include program header in ELF files")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Lieven Hey <lieven.hey@kdab.com>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Pablo Galindo <pablogsal@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231212070547.612536-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/genelf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index fefc72066c4e8..ac17a3cb59dc0 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -293,9 +293,9 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	 */
 	phdr = elf_newphdr(e, 1);
 	phdr[0].p_type = PT_LOAD;
-	phdr[0].p_offset = 0;
-	phdr[0].p_vaddr = 0;
-	phdr[0].p_paddr = 0;
+	phdr[0].p_offset = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_vaddr = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_paddr = GEN_ELF_TEXT_OFFSET;
 	phdr[0].p_filesz = csize;
 	phdr[0].p_memsz = csize;
 	phdr[0].p_flags = PF_X | PF_R;
-- 
GitLab


From 83e1bdc94f32dcf52dfcd2025acc7a2b9376b1e8 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Thu, 14 Dec 2023 11:28:25 +1300
Subject: [PATCH 1312/4076] x86/virt/tdx: Make TDX host depend on X86_MCE

A build failure was reported that when INTEL_TDX_HOST is enabled but
X86_MCE is not, the tdx_dump_mce_info() function fails to link:

  ld: vmlinux.o: in function `tdx_dump_mce_info':
  ...: undefined reference to `mce_is_memory_error'
  ...: undefined reference to `mce_usable_address'

The reason is in such configuration, despite there's no caller of
tdx_dump_mce_info() it is still built and there's no implementation for
the two "mce_*()" functions.

Make INTEL_TDX_HOST depend on X86_MCE to fix.

It makes sense to enable MCE support for the TDX host anyway.  Because
the only way that TDX has to report integrity errors is an MCE, and it
is not good to silently ignore such MCE.  The TDX spec also suggests
the host VMM is expected to implement the MCE handler.

Note it also makes sense to make INTEL_TDX_HOST select X86_MCE but this
generates "recursive dependency detected!" error in the Kconfig.

Closes: https://lore.kernel.org/all/20231212214612.GHZXjUpBFa1IwVMTI7@fat_crate.local/T/
Fixes: 70060463cb2b ("x86/mce: Differentiate real hardware #MCs from TDX erratum ones")
Reported-by: Arnd Bergmann <arnd@kernel.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lore.kernel.org/all/20231212214612.GHZXjUpBFa1IwVMTI7@fat_crate.local/T/#m1a109c29324b2bbd0b3b1d45c218012cd3a13be6
Link: https://lore.kernel.org/all/20231213222825.286809-1-kai.huang%40intel.com
---
 arch/x86/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 01cdb16acff6e..92c03cb99b3e6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1974,6 +1974,7 @@ config INTEL_TDX_HOST
 	select ARCH_KEEP_MEMBLOCK
 	depends on CONTIG_ALLOC
 	depends on !KEXEC_CORE
+	depends on X86_MCE
 	help
 	  Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
 	  host and certain physical attacks.  This option enables necessary TDX
-- 
GitLab


From c966d23a351a33f8a977fd7efbb6f467132f7383 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 11 Dec 2023 23:05:45 -0800
Subject: [PATCH 1313/4076] perf unwind-libdw: Handle JIT-generated DSOs
 properly

Usually DSOs are mapped from the beginning of the file, so the base
address of the DSO can be calculated by map->start - map->pgoff.

However, JIT DSOs which are generated by `perf inject -j`, are mapped
only the code segment.  This makes unwind-libdw code confusing and
rejects processing unwinds in the JIT DSOs.  It should use the map
start address as base for them to fix the confusion.

Fixes: 1fe627da30331024 ("perf unwind: Take pgoff into account when reporting elf to libdwfl")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Pablo Galindo <pablogsal@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231212070547.612536-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/unwind-libdw.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 8554db3fc0d7c..6013335a8daea 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -46,6 +46,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 {
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
+	Dwarf_Addr base;
 	/*
 	 * Some callers will use al->sym, so we can't just use the
 	 * cheaper thread__find_map() here.
@@ -58,13 +59,25 @@ static int __report_module(struct addr_location *al, u64 ip,
 	if (!dso)
 		return 0;
 
+	/*
+	 * The generated JIT DSO files only map the code segment without
+	 * ELF headers.  Since JIT codes used to be packed in a memory
+	 * segment, calculating the base address using pgoff falls into
+	 * a different code in another DSO.  So just use the map->start
+	 * directly to pick the correct one.
+	 */
+	if (!strncmp(dso->long_name, "/tmp/jitted-", 12))
+		base = map__start(al->map);
+	else
+		base = map__start(al->map) - map__pgoff(al->map);
+
 	mod = dwfl_addrmodule(ui->dwfl, ip);
 	if (mod) {
 		Dwarf_Addr s;
 
 		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-		if (s != map__start(al->map) - map__pgoff(al->map))
-			mod = 0;
+		if (s != base)
+			mod = NULL;
 	}
 
 	if (!mod) {
@@ -72,14 +85,14 @@ static int __report_module(struct addr_location *al, u64 ip,
 
 		__symbol__join_symfs(filename, sizeof(filename), dso->long_name);
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
-				      map__start(al->map) - map__pgoff(al->map), false);
+				      base, false);
 	}
 	if (!mod) {
 		char filename[PATH_MAX];
 
 		if (dso__build_id_filename(dso, filename, sizeof(filename), false))
 			mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
-					      map__start(al->map) - map__pgoff(al->map), false);
+					      base, false);
 	}
 
 	if (mod) {
-- 
GitLab


From 4fb54994b2360ab5029ee3a959161f6fe6bbb349 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 11 Dec 2023 23:05:46 -0800
Subject: [PATCH 1314/4076] perf unwind-libunwind: Fix base address for
 .eh_frame

The base address of a DSO mapping should start at the start of the file.
Usually DSOs are mapped from the pgoff 0 so it doesn't matter when it
uses the start of the map address.

But generated DSOs for JIT codes doesn't start from the 0 so it should
subtract the offset to calculate the .eh_frame table offsets correctly.

Fixes: dc2cf4ca866f5715 ("perf unwind: Fix segbase for ld.lld linked objects")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Pablo Galindo <pablogsal@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231212070547.612536-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/unwind-libunwind-local.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index c0641882fd2fd..5e5c3395a4998 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -327,7 +327,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 
 	maps__for_each_entry(thread__maps(ui->thread), map_node) {
 		struct map *map = map_node->map;
-		u64 start = map__start(map);
+		u64 start = map__start(map) - map__pgoff(map);
 
 		if (map__dso(map) == dso && start < base_addr)
 			base_addr = start;
-- 
GitLab


From 5fa695e7da4975e8d21ce49f3718d6cf00ecb75e Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 14 Dec 2023 06:46:11 -0800
Subject: [PATCH 1315/4076] perf top: Use evsel's cpus to replace
 user_requested_cpus

perf top errors out on a hybrid machine
 $perf top

 Error:
 The cycles:P event is not supported.

The perf top expects that the "cycles" is collected on all CPUs in the
system. But for hybrid there is no single "cycles" event which can cover
all CPUs. Perf has to split it into two cycles events, e.g.,
cpu_core/cycles/ and cpu_atom/cycles/. Each event has its own CPU mask.
If a event is opened on the unsupported CPU. The open fails. That's the
reason of the above error out.

Perf should only open the cycles event on the corresponding CPU. The
commit ef91871c960e ("perf evlist: Propagate user CPU maps intersecting
core PMU maps") intersect the requested CPU map with the CPU map of the
PMU. Use the evsel's cpus to replace user_requested_cpus.

The evlist's threads are also propagated to the evsel's threads in
__perf_evlist__propagate_maps(). For a system-wide event, perf appends
a dummy event and assign it to the evsel's threads. For a per-thread
event, the evlist's thread_map is assigned to the evsel's threads. The
same as the other tools, e.g., perf record, using the evsel's threads
when opening an event.

Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Hector Martin <marcan@marcan.st>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Closes: https://lore.kernel.org/linux-perf-users/ZXNnDrGKXbEELMXV@kernel.org/
Link: https://lore.kernel.org/r/20231214144612.1092028-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ed83afeeced05..13e609c0c6930 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1026,8 +1026,8 @@ static int perf_top__start_counters(struct perf_top *top)
 
 	evlist__for_each_entry(evlist, counter) {
 try_again:
-		if (evsel__open(counter, top->evlist->core.user_requested_cpus,
-				     top->evlist->core.threads) < 0) {
+		if (evsel__open(counter, counter->core.cpus,
+				counter->core.threads) < 0) {
 
 			/*
 			 * Specially handle overwrite fall back.
-- 
GitLab


From a61f89bf76ef6f87ec48dd90dbc73a6cf9952edc Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 14 Dec 2023 06:46:12 -0800
Subject: [PATCH 1316/4076] perf top: Uniform the event name for the hybrid
 machine

It's hard to distinguish the default cycles events among hybrid PMUs.
For example,

  $ perf top
  Available samples
  385 cycles:P
  903 cycles:P

The other tool, e.g., perf record, uniforms the event name and adds the
hybrid PMU name before opening the event. So the events can be easily
distinguished. Apply the same methodology for the perf top as well.

The evlist__uniquify_name() will be invoked by both record and top.
Move it to util/evlist.c

With the patch:

  $ perf top
  Available samples
  148 cpu_atom/cycles:P/
  1K cpu_core/cycles:P/

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Hector Martin <marcan@marcan.st>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231214144612.1092028-2-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 28 +---------------------------
 tools/perf/builtin-top.c    |  1 +
 tools/perf/util/evlist.c    | 25 +++++++++++++++++++++++++
 tools/perf/util/evlist.h    |  1 +
 4 files changed, 28 insertions(+), 27 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8a1002683fda2..a89013c44fd53 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -2237,32 +2237,6 @@ static void hit_auxtrace_snapshot_trigger(struct record *rec)
 	}
 }
 
-static void record__uniquify_name(struct record *rec)
-{
-	struct evsel *pos;
-	struct evlist *evlist = rec->evlist;
-	char *new_name;
-	int ret;
-
-	if (perf_pmus__num_core_pmus() == 1)
-		return;
-
-	evlist__for_each_entry(evlist, pos) {
-		if (!evsel__is_hybrid(pos))
-			continue;
-
-		if (strchr(pos->name, '/'))
-			continue;
-
-		ret = asprintf(&new_name, "%s/%s/",
-			       pos->pmu_name, pos->name);
-		if (ret) {
-			free(pos->name);
-			pos->name = new_name;
-		}
-	}
-}
-
 static int record__terminate_thread(struct record_thread *thread_data)
 {
 	int err;
@@ -2496,7 +2470,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (data->is_pipe && rec->evlist->core.nr_entries == 1)
 		rec->opts.sample_id = true;
 
-	record__uniquify_name(rec);
+	evlist__uniquify_name(rec->evlist);
 
 	/* Debug message used by test scripts */
 	pr_debug3("perf record opening and mmapping events\n");
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 13e609c0c6930..baf1ab083436e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1298,6 +1298,7 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
+	evlist__uniquify_name(top->evlist);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		return ret;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 0ed3ce2aa8ebf..6f0892803c224 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -2518,3 +2518,28 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis
 	}
 	perf_cpu_map__put(user_requested_cpus);
 }
+
+void evlist__uniquify_name(struct evlist *evlist)
+{
+	struct evsel *pos;
+	char *new_name;
+	int ret;
+
+	if (perf_pmus__num_core_pmus() == 1)
+		return;
+
+	evlist__for_each_entry(evlist, pos) {
+		if (!evsel__is_hybrid(pos))
+			continue;
+
+		if (strchr(pos->name, '/'))
+			continue;
+
+		ret = asprintf(&new_name, "%s/%s/",
+			       pos->pmu_name, pos->name);
+		if (ret) {
+			free(pos->name);
+			pos->name = new_name;
+		}
+	}
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 98e7ddb2bd305..cb91dc9117a27 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -442,5 +442,6 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx);
 int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf);
 void evlist__check_mem_load_aux(struct evlist *evlist);
 void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list);
+void evlist__uniquify_name(struct evlist *evlist);
 
 #endif /* __PERF_EVLIST_H */
-- 
GitLab


From a9a36e4b4adf63e3a2ea9eed730de50d9b28302e Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Thu, 14 Dec 2023 19:36:41 +0100
Subject: [PATCH 1317/4076] interconnect: qcom: sm6115: Fix up includes

Remove some unnecessary includes and get rid of the abusive of_platform
in favor of the correct headers.

Reported-by: Rob Herring <robh+dt@kernel.org>
Reported-by: Georgi Djakov <djakov@kernel.org>
Fixes: 2eab57b131bd ("interconnect: qcom: Add SM6115 interconnect provider driver")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231214-topic-6115iccfix-v1-1-9ad999683a7d@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/sm6115.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/interconnect/qcom/sm6115.c b/drivers/interconnect/qcom/sm6115.c
index c49a83c87739d..88b67634aa2f1 100644
--- a/drivers/interconnect/qcom/sm6115.c
+++ b/drivers/interconnect/qcom/sm6115.c
@@ -6,16 +6,12 @@
  */
 
 #include <dt-bindings/interconnect/qcom,sm6115.h>
-#include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/interconnect-provider.h>
-#include <linux/io.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
-#include <linux/slab.h>
 
 #include "icc-rpm.h"
 
-- 
GitLab


From 9594f273fafe76663e502337eaf393dc4f7bf8fa Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 13 Dec 2023 21:37:15 -0800
Subject: [PATCH 1318/4076] Input: da9063 - simplify obtaining OF match data

Simplify probe() by replacing of_match_node() for retrieving match data by
device_get_match_data().

Some minor cleanups:
 * Remove the trailing comma in the terminator entry for the OF
   table making code robust against (theoretical) misrebases or other
   similar things where the new entry goes _after_ the termination without
   the compiler noticing.
 * Move OF table near to the user.
 * Arrange variables in reverse xmas tree order in probe().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://lore.kernel.org/r/20231213214803.9931-2-biju.das.jz@bp.renesas.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/da9063_onkey.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index 74808bae326a7..9351ce0bb4057 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -74,13 +74,6 @@ static const struct da906x_chip_config da9062_regs = {
 	.name = "da9062-onkey",
 };
 
-static const struct of_device_id da9063_compatible_reg_id_table[] = {
-	{ .compatible = "dlg,da9063-onkey", .data = &da9063_regs },
-	{ .compatible = "dlg,da9062-onkey", .data = &da9062_regs },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, da9063_compatible_reg_id_table);
-
 static void da9063_poll_on(struct work_struct *work)
 {
 	struct da9063_onkey *onkey = container_of(work,
@@ -187,14 +180,8 @@ static irqreturn_t da9063_onkey_irq_handler(int irq, void *data)
 static int da9063_onkey_probe(struct platform_device *pdev)
 {
 	struct da9063_onkey *onkey;
-	const struct of_device_id *match;
-	int irq;
 	int error;
-
-	match = of_match_node(da9063_compatible_reg_id_table,
-			      pdev->dev.of_node);
-	if (!match)
-		return -ENXIO;
+	int irq;
 
 	onkey = devm_kzalloc(&pdev->dev, sizeof(struct da9063_onkey),
 			     GFP_KERNEL);
@@ -203,7 +190,10 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	onkey->config = match->data;
+	onkey->config = device_get_match_data(&pdev->dev);
+	if (!onkey->config)
+		return -ENXIO;
+
 	onkey->dev = &pdev->dev;
 
 	onkey->regmap = dev_get_regmap(pdev->dev.parent, NULL);
@@ -270,6 +260,13 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id da9063_compatible_reg_id_table[] = {
+	{ .compatible = "dlg,da9063-onkey", .data = &da9063_regs },
+	{ .compatible = "dlg,da9062-onkey", .data = &da9062_regs },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, da9063_compatible_reg_id_table);
+
 static struct platform_driver da9063_onkey_driver = {
 	.probe	= da9063_onkey_probe,
 	.driver	= {
-- 
GitLab


From bd2334eda183a2888b5541605b39617c1e6b4b71 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 13 Dec 2023 23:48:38 -0800
Subject: [PATCH 1319/4076] Input: da9063 - drop redundant prints in probe()

The memory allocation core code already prints error message in case of
OOM. So, drop additional print messages for OOM cases.

While at it, input_register_device() is already printing error messages on
failure. Drop the redundant print.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://lore.kernel.org/r/20231213214803.9931-3-biju.das.jz@bp.renesas.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/da9063_onkey.c | 19 ++++---------------
 1 file changed, 4 insertions(+), 15 deletions(-)

diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index 9351ce0bb4057..5483a0576155d 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -185,10 +185,8 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 
 	onkey = devm_kzalloc(&pdev->dev, sizeof(struct da9063_onkey),
 			     GFP_KERNEL);
-	if (!onkey) {
-		dev_err(&pdev->dev, "Failed to allocate memory.\n");
+	if (!onkey)
 		return -ENOMEM;
-	}
 
 	onkey->config = device_get_match_data(&pdev->dev);
 	if (!onkey->config)
@@ -206,10 +204,8 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 						  "dlg,disable-key-power");
 
 	onkey->input = devm_input_allocate_device(&pdev->dev);
-	if (!onkey->input) {
-		dev_err(&pdev->dev, "Failed to allocated input device.\n");
+	if (!onkey->input)
 		return -ENOMEM;
-	}
 
 	onkey->input->name = onkey->config->name;
 	snprintf(onkey->phys, sizeof(onkey->phys), "%s/input0",
@@ -221,12 +217,8 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 
 	error = devm_delayed_work_autocancel(&pdev->dev, &onkey->work,
 					     da9063_poll_on);
-	if (error) {
-		dev_err(&pdev->dev,
-			"Failed to add cancel poll action: %d\n",
-			error);
+	if (error)
 		return error;
-	}
 
 	irq = platform_get_irq_byname(pdev, "ONKEY");
 	if (irq < 0)
@@ -251,11 +243,8 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 		device_init_wakeup(&pdev->dev, true);
 
 	error = input_register_device(onkey->input);
-	if (error) {
-		dev_err(&pdev->dev,
-			"Failed to register input device: %d\n", error);
+	if (error)
 		return error;
-	}
 
 	return 0;
 }
-- 
GitLab


From c67f8a13be4e9ffc862c7f60ec97a799a1547486 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Thu, 14 Dec 2023 22:05:20 -0800
Subject: [PATCH 1320/4076] Input: da9063 - use dev_err_probe()

Replace dev_err()->dev_err_probe() to simplify probe().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://lore.kernel.org/r/20231213214803.9931-4-biju.das.jz@bp.renesas.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/da9063_onkey.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index 5483a0576155d..a8b7f1cd0ec2a 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -195,10 +195,9 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 	onkey->dev = &pdev->dev;
 
 	onkey->regmap = dev_get_regmap(pdev->dev.parent, NULL);
-	if (!onkey->regmap) {
-		dev_err(&pdev->dev, "Parent regmap unavailable.\n");
-		return -ENXIO;
-	}
+	if (!onkey->regmap)
+		return dev_err_probe(&pdev->dev, -ENXIO,
+				     "Parent regmap unavailable.\n");
 
 	onkey->key_power = !of_property_read_bool(pdev->dev.of_node,
 						  "dlg,disable-key-power");
@@ -228,11 +227,9 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 					  NULL, da9063_onkey_irq_handler,
 					  IRQF_TRIGGER_LOW | IRQF_ONESHOT,
 					  "ONKEY", onkey);
-	if (error) {
-		dev_err(&pdev->dev,
-			"Failed to request IRQ %d: %d\n", irq, error);
-		return error;
-	}
+	if (error)
+		return dev_err_probe(&pdev->dev, error,
+				     "Failed to allocate onkey IRQ\n");
 
 	error = dev_pm_set_wake_irq(&pdev->dev, irq);
 	if (error)
-- 
GitLab


From a63c357b9fd56ad5fe64616f5b22835252c6a76a Mon Sep 17 00:00:00 2001
From: "Isaac J. Manjarres" <isaacmanjarres@google.com>
Date: Fri, 8 Dec 2023 15:41:40 -0800
Subject: [PATCH 1321/4076] iommu/dma: Trace bounce buffer usage when mapping
 buffers

When commit 82612d66d51d ("iommu: Allow the dma-iommu api to
use bounce buffers") was introduced, it did not add the logic
for tracing the bounce buffer usage from iommu_dma_map_page().

All of the users of swiotlb_tbl_map_single() trace their bounce
buffer usage, except iommu_dma_map_page(). This makes it difficult
to track SWIOTLB usage from that function. Thus, trace bounce buffer
usage from iommu_dma_map_page().

Fixes: 82612d66d51d ("iommu: Allow the dma-iommu api to use bounce buffers")
Cc: stable@vger.kernel.org # v5.15+
Cc: Tom Murphy <murphyt7@tcd.ie>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: Saravana Kannan <saravanak@google.com>
Signed-off-by: Isaac J. Manjarres <isaacmanjarres@google.com>
Link: https://lore.kernel.org/r/20231208234141.2356157-1-isaacmanjarres@google.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dma-iommu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 85163a83df2f6..037fcf826407f 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/swiotlb.h>
 #include <linux/vmalloc.h>
+#include <trace/events/swiotlb.h>
 
 #include "dma-iommu.h"
 
@@ -1156,6 +1157,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 			return DMA_MAPPING_ERROR;
 		}
 
+		trace_swiotlb_bounced(dev, phys, size);
+
 		aligned_size = iova_align(iovad, size);
 		phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
 					      iova_mask(iovad), dir, attrs);
-- 
GitLab


From f8aa519976b38e67aae02d2db3e2998513305e80 Mon Sep 17 00:00:00 2001
From: Andy Yan <andy.yan@rock-chips.com>
Date: Tue, 12 Dec 2023 08:57:10 +0800
Subject: [PATCH 1322/4076] dt-bindings: iommu: rockchip: Add Rockchip RK3588

Add a Rockchip RK3588 compatible

I split it from the vop2 patch series as suggested by Heiko[0]

Signed-off-by: Andy Yan <andy.yan@rock-chips.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>

[0]https://patchwork.kernel.org/project/dri-devel/patch/20231207080235.652719-1-andyshrk@163.com/

Link: https://lore.kernel.org/r/20231212005710.1837066-1-andyshrk@163.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 .../devicetree/bindings/iommu/rockchip,iommu.yaml     | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml
index ba9124f721f15..621dde0e45d85 100644
--- a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml
+++ b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml
@@ -19,9 +19,14 @@ description: |+
 
 properties:
   compatible:
-    enum:
-      - rockchip,iommu
-      - rockchip,rk3568-iommu
+    oneOf:
+      - enum:
+          - rockchip,iommu
+          - rockchip,rk3568-iommu
+      - items:
+          - enum:
+              - rockchip,rk3588-iommu
+          - const: rockchip,rk3568-iommu
 
   reg:
     items:
-- 
GitLab


From 9991a82a38174672273df44a3cc6c87ef74b18e9 Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Wed, 13 Dec 2023 03:14:50 -0800
Subject: [PATCH 1323/4076] iommu/sva: Fix memory leak in
 iommu_sva_bind_device()

Free the handle when the domain allocation fails before unlocking and
returning.

Fixes: 092edaddb660 ("iommu: Support mm PASID 1:n with sva domains")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20231213111450.2487861-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu-sva.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index 5175e8d85247b..c3fc9201d0be9 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -101,7 +101,7 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 	domain = iommu_sva_domain_alloc(dev, mm);
 	if (!domain) {
 		ret = -ENOMEM;
-		goto out_unlock;
+		goto out_free_handle;
 	}
 
 	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
@@ -118,6 +118,7 @@ out:
 
 out_free_domain:
 	iommu_domain_free(domain);
+out_free_handle:
 	kfree(handle);
 out_unlock:
 	mutex_unlock(&iommu_sva_lock);
-- 
GitLab


From ee08acb58fe47fc3bc2c137965985cdb1df40b35 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Thu, 2 Nov 2023 20:33:18 +0530
Subject: [PATCH 1324/4076] bus: mhi: ep: Add support for async DMA write
 operation

In order to optimize the data transfer, let's use the async DMA operation
for writing (queuing) data to the host.

In the async path, the completion event for the transfer ring will only be
sent to the host when the controller driver notifies the MHI stack of the
actual transfer completion using the callback (mhi_ep_skb_completion)
supplied in "struct mhi_ep_buf_info".

Also to accommodate the async operation, the transfer ring read offset
(ring->rd_offset) is cached in the "struct mhi_ep_chan" and updated locally
to let the stack queue further ring items to the controller driver. But the
actual read offset of the transfer ring will only be updated in the
completion callback.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/internal.h |  1 +
 drivers/bus/mhi/ep/main.c     | 74 +++++++++++++++++++++++++----------
 include/linux/mhi_ep.h        |  4 ++
 3 files changed, 59 insertions(+), 20 deletions(-)

diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h
index 8c5cf2b679510..577965f95fda9 100644
--- a/drivers/bus/mhi/ep/internal.h
+++ b/drivers/bus/mhi/ep/internal.h
@@ -162,6 +162,7 @@ struct mhi_ep_chan {
 	void (*xfer_cb)(struct mhi_ep_device *mhi_dev, struct mhi_result *result);
 	enum mhi_ch_state state;
 	enum dma_data_direction dir;
+	size_t rd_offset;
 	u64 tre_loc;
 	u32 tre_size;
 	u32 tre_bytes_left;
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 88e189a8463a9..48ef61ccf7379 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -199,6 +199,8 @@ static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_ele
 
 				goto err_unlock;
 			}
+
+			mhi_chan->rd_offset = ch_ring->rd_offset;
 		}
 
 		/* Set channel state to RUNNING */
@@ -328,7 +330,7 @@ bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_directio
 	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
 
-	return !!(ring->rd_offset == ring->wr_offset);
+	return !!(mhi_chan->rd_offset == ring->wr_offset);
 }
 EXPORT_SYMBOL_GPL(mhi_ep_queue_is_empty);
 
@@ -355,7 +357,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 			return -ENODEV;
 		}
 
-		el = &ring->ring_cache[ring->rd_offset];
+		el = &ring->ring_cache[mhi_chan->rd_offset];
 
 		/* Check if there is data pending to be read from previous read operation */
 		if (mhi_chan->tre_bytes_left) {
@@ -434,6 +436,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 				tr_done = true;
 			}
 
+			mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size;
 			mhi_ep_ring_inc_index(ring);
 		}
 
@@ -494,6 +497,35 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 	return 0;
 }
 
+static void mhi_ep_skb_completion(struct mhi_ep_buf_info *buf_info)
+{
+	struct mhi_ep_device *mhi_dev = buf_info->mhi_dev;
+	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan;
+	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
+	struct mhi_ring_element *el = &ring->ring_cache[ring->rd_offset];
+	struct device *dev = &mhi_dev->dev;
+	struct mhi_result result = {};
+	int ret;
+
+	if (mhi_chan->xfer_cb) {
+		result.buf_addr = buf_info->cb_buf;
+		result.dir = mhi_chan->dir;
+		result.bytes_xferd = buf_info->size;
+
+		mhi_chan->xfer_cb(mhi_dev, &result);
+	}
+
+	ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, buf_info->size,
+					   buf_info->code);
+	if (ret) {
+		dev_err(dev, "Error sending transfer completion event\n");
+		return;
+	}
+
+	mhi_ep_ring_inc_index(ring);
+}
+
 /* TODO: Handle partially formed TDs */
 int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 {
@@ -504,7 +536,6 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 	struct mhi_ring_element *el;
 	u32 buf_left, read_offset;
 	struct mhi_ep_ring *ring;
-	enum mhi_ev_ccs code;
 	size_t tr_len;
 	u32 tre_len;
 	int ret;
@@ -528,7 +559,7 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 			goto err_exit;
 		}
 
-		el = &ring->ring_cache[ring->rd_offset];
+		el = &ring->ring_cache[mhi_chan->rd_offset];
 		tre_len = MHI_TRE_DATA_GET_LEN(el);
 
 		tr_len = min(buf_left, tre_len);
@@ -537,33 +568,35 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 		buf_info.dev_addr = skb->data + read_offset;
 		buf_info.host_addr = MHI_TRE_DATA_GET_PTR(el);
 		buf_info.size = tr_len;
+		buf_info.cb = mhi_ep_skb_completion;
+		buf_info.cb_buf = skb;
+		buf_info.mhi_dev = mhi_dev;
 
-		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
-		if (ret < 0) {
-			dev_err(dev, "Error writing to the channel\n");
-			goto err_exit;
-		}
-
-		buf_left -= tr_len;
 		/*
 		 * For all TREs queued by the host for DL channel, only the EOT flag will be set.
 		 * If the packet doesn't fit into a single TRE, send the OVERFLOW event to
 		 * the host so that the host can adjust the packet boundary to next TREs. Else send
 		 * the EOT event to the host indicating the packet boundary.
 		 */
-		if (buf_left)
-			code = MHI_EV_CC_OVERFLOW;
+		if (buf_left - tr_len)
+			buf_info.code = MHI_EV_CC_OVERFLOW;
 		else
-			code = MHI_EV_CC_EOT;
+			buf_info.code = MHI_EV_CC_EOT;
 
-		ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, tr_len, code);
-		if (ret) {
-			dev_err(dev, "Error sending transfer completion event\n");
+		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
+		ret = mhi_cntrl->write_async(mhi_cntrl, &buf_info);
+		if (ret < 0) {
+			dev_err(dev, "Error writing to the channel\n");
 			goto err_exit;
 		}
 
-		mhi_ep_ring_inc_index(ring);
+		buf_left -= tr_len;
+
+		/*
+		 * Update the read offset cached in mhi_chan. Actual read offset
+		 * will be updated by the completion handler.
+		 */
+		mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size;
 	} while (buf_left);
 
 	mutex_unlock(&mhi_chan->lock);
@@ -803,7 +836,7 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 		}
 
 		/* Sanity check to make sure there are elements in the ring */
-		if (ring->rd_offset == ring->wr_offset) {
+		if (chan->rd_offset == ring->wr_offset) {
 			mutex_unlock(&chan->lock);
 			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
@@ -1447,6 +1480,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		ret = -ENOMEM;
 		goto err_destroy_tre_buf_cache;
 	}
+
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 14c6e8d3f5736..11bf3212f7822 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -51,16 +51,20 @@ struct mhi_ep_db_info {
 
 /**
  * struct mhi_ep_buf_info - MHI Endpoint transfer buffer info
+ * @mhi_dev: MHI device associated with this buffer
  * @dev_addr: Address of the buffer in endpoint
  * @host_addr: Address of the bufffer in host
  * @size: Size of the buffer
+ * @code: Transfer completion code
  * @cb: Callback to be executed by controller drivers after transfer completion (async)
  * @cb_buf: Opaque buffer to be passed to the callback
  */
 struct mhi_ep_buf_info {
+	struct mhi_ep_device *mhi_dev;
 	void *dev_addr;
 	u64 host_addr;
 	size_t size;
+	int code;
 
 	void (*cb)(struct mhi_ep_buf_info *buf_info);
 	void *cb_buf;
-- 
GitLab


From 2547beb00ddb40e55b773970622421d978f71473 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 21 Aug 2023 16:53:24 +0530
Subject: [PATCH 1325/4076] bus: mhi: ep: Add support for async DMA read
 operation

As like the async DMA write operation, let's add support for async DMA read
operation. In the async path, the data will be read from the transfer ring
continuously and when the controller driver notifies the stack using the
completion callback (mhi_ep_read_completion), then the client driver will
be notified with the read data and the completion event will be sent to the
host for the respective ring element (if requested by the host).

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c | 162 +++++++++++++++++++++-----------------
 1 file changed, 89 insertions(+), 73 deletions(-)

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 48ef61ccf7379..063c07241da78 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -334,17 +334,81 @@ bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_directio
 }
 EXPORT_SYMBOL_GPL(mhi_ep_queue_is_empty);
 
+static void mhi_ep_read_completion(struct mhi_ep_buf_info *buf_info)
+{
+	struct mhi_ep_device *mhi_dev = buf_info->mhi_dev;
+	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_ep_chan *mhi_chan = mhi_dev->ul_chan;
+	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
+	struct mhi_ring_element *el = &ring->ring_cache[ring->rd_offset];
+	struct mhi_result result = {};
+	int ret;
+
+	if (mhi_chan->xfer_cb) {
+		result.buf_addr = buf_info->cb_buf;
+		result.dir = mhi_chan->dir;
+		result.bytes_xferd = buf_info->size;
+
+		mhi_chan->xfer_cb(mhi_dev, &result);
+	}
+
+	/*
+	 * The host will split the data packet into multiple TREs if it can't fit
+	 * the packet in a single TRE. In that case, CHAIN flag will be set by the
+	 * host for all TREs except the last one.
+	 */
+	if (buf_info->code != MHI_EV_CC_OVERFLOW) {
+		if (MHI_TRE_DATA_GET_CHAIN(el)) {
+			/*
+			 * IEOB (Interrupt on End of Block) flag will be set by the host if
+			 * it expects the completion event for all TREs of a TD.
+			 */
+			if (MHI_TRE_DATA_GET_IEOB(el)) {
+				ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
+							     MHI_TRE_DATA_GET_LEN(el),
+							     MHI_EV_CC_EOB);
+				if (ret < 0) {
+					dev_err(&mhi_chan->mhi_dev->dev,
+						"Error sending transfer compl. event\n");
+					goto err_free_tre_buf;
+				}
+			}
+		} else {
+			/*
+			 * IEOT (Interrupt on End of Transfer) flag will be set by the host
+			 * for the last TRE of the TD and expects the completion event for
+			 * the same.
+			 */
+			if (MHI_TRE_DATA_GET_IEOT(el)) {
+				ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
+							     MHI_TRE_DATA_GET_LEN(el),
+							     MHI_EV_CC_EOT);
+				if (ret < 0) {
+					dev_err(&mhi_chan->mhi_dev->dev,
+						"Error sending transfer compl. event\n");
+					goto err_free_tre_buf;
+				}
+			}
+		}
+	}
+
+	mhi_ep_ring_inc_index(ring);
+
+err_free_tre_buf:
+	kmem_cache_free(mhi_cntrl->tre_buf_cache, buf_info->cb_buf);
+}
+
 static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
-				struct mhi_ep_ring *ring,
-				struct mhi_result *result,
-				u32 len)
+			       struct mhi_ep_ring *ring)
 {
 	struct mhi_ep_chan *mhi_chan = &mhi_cntrl->mhi_chan[ring->ch_id];
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	size_t tr_len, read_offset, write_offset;
 	struct mhi_ep_buf_info buf_info = {};
+	u32 len = MHI_EP_DEFAULT_MTU;
 	struct mhi_ring_element *el;
 	bool tr_done = false;
+	void *buf_addr;
 	u32 buf_left;
 	int ret;
 
@@ -374,83 +438,50 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 		read_offset = mhi_chan->tre_size - mhi_chan->tre_bytes_left;
 		write_offset = len - buf_left;
 
+		buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL | GFP_DMA);
+		if (!buf_addr)
+			return -ENOMEM;
+
 		buf_info.host_addr = mhi_chan->tre_loc + read_offset;
-		buf_info.dev_addr = result->buf_addr + write_offset;
+		buf_info.dev_addr = buf_addr + write_offset;
 		buf_info.size = tr_len;
+		buf_info.cb = mhi_ep_read_completion;
+		buf_info.cb_buf = buf_addr;
+		buf_info.mhi_dev = mhi_chan->mhi_dev;
+
+		if (mhi_chan->tre_bytes_left - tr_len)
+			buf_info.code = MHI_EV_CC_OVERFLOW;
 
 		dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->read_async(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n");
-			return ret;
+			goto err_free_buf_addr;
 		}
 
 		buf_left -= tr_len;
 		mhi_chan->tre_bytes_left -= tr_len;
 
-		/*
-		 * Once the TRE (Transfer Ring Element) of a TD (Transfer Descriptor) has been
-		 * read completely:
-		 *
-		 * 1. Send completion event to the host based on the flags set in TRE.
-		 * 2. Increment the local read offset of the transfer ring.
-		 */
 		if (!mhi_chan->tre_bytes_left) {
-			/*
-			 * The host will split the data packet into multiple TREs if it can't fit
-			 * the packet in a single TRE. In that case, CHAIN flag will be set by the
-			 * host for all TREs except the last one.
-			 */
-			if (MHI_TRE_DATA_GET_CHAIN(el)) {
-				/*
-				 * IEOB (Interrupt on End of Block) flag will be set by the host if
-				 * it expects the completion event for all TREs of a TD.
-				 */
-				if (MHI_TRE_DATA_GET_IEOB(el)) {
-					ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
-								     MHI_TRE_DATA_GET_LEN(el),
-								     MHI_EV_CC_EOB);
-					if (ret < 0) {
-						dev_err(&mhi_chan->mhi_dev->dev,
-							"Error sending transfer compl. event\n");
-						return ret;
-					}
-				}
-			} else {
-				/*
-				 * IEOT (Interrupt on End of Transfer) flag will be set by the host
-				 * for the last TRE of the TD and expects the completion event for
-				 * the same.
-				 */
-				if (MHI_TRE_DATA_GET_IEOT(el)) {
-					ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
-								     MHI_TRE_DATA_GET_LEN(el),
-								     MHI_EV_CC_EOT);
-					if (ret < 0) {
-						dev_err(&mhi_chan->mhi_dev->dev,
-							"Error sending transfer compl. event\n");
-						return ret;
-					}
-				}
-
+			if (MHI_TRE_DATA_GET_IEOT(el))
 				tr_done = true;
-			}
 
 			mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size;
-			mhi_ep_ring_inc_index(ring);
 		}
-
-		result->bytes_xferd += tr_len;
 	} while (buf_left && !tr_done);
 
 	return 0;
+
+err_free_buf_addr:
+	kmem_cache_free(mhi_cntrl->tre_buf_cache, buf_addr);
+
+	return ret;
 }
 
-static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el)
+static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
 	struct mhi_result result = {};
-	u32 len = MHI_EP_DEFAULT_MTU;
 	struct mhi_ep_chan *mhi_chan;
 	int ret;
 
@@ -471,27 +502,15 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 		mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
 	} else {
 		/* UL channel */
-		result.buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL | GFP_DMA);
-		if (!result.buf_addr)
-			return -ENOMEM;
-
 		do {
-			ret = mhi_ep_read_channel(mhi_cntrl, ring, &result, len);
+			ret = mhi_ep_read_channel(mhi_cntrl, ring);
 			if (ret < 0) {
 				dev_err(&mhi_chan->mhi_dev->dev, "Failed to read channel\n");
-				kmem_cache_free(mhi_cntrl->tre_buf_cache, result.buf_addr);
 				return ret;
 			}
 
-			result.dir = mhi_chan->dir;
-			mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
-			result.bytes_xferd = 0;
-			memset(result.buf_addr, 0, len);
-
 			/* Read until the ring becomes empty */
 		} while (!mhi_ep_queue_is_empty(mhi_chan->mhi_dev, DMA_TO_DEVICE));
-
-		kmem_cache_free(mhi_cntrl->tre_buf_cache, result.buf_addr);
 	}
 
 	return 0;
@@ -797,7 +816,6 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, ch_ring_work);
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	struct mhi_ep_ring_item *itr, *tmp;
-	struct mhi_ring_element *el;
 	struct mhi_ep_ring *ring;
 	struct mhi_ep_chan *chan;
 	unsigned long flags;
@@ -842,10 +860,8 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 			continue;
 		}
 
-		el = &ring->ring_cache[ring->rd_offset];
-
 		dev_dbg(dev, "Processing the ring for channel (%u)\n", ring->ch_id);
-		ret = mhi_ep_process_ch_ring(ring, el);
+		ret = mhi_ep_process_ch_ring(ring);
 		if (ret) {
 			dev_err(dev, "Error processing ring for channel (%u): %d\n",
 				ring->ch_id, ret);
-- 
GitLab


From 309ab14f70d137f708ca52e275dc9fd20d3e9147 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 27 Nov 2023 16:52:07 +0530
Subject: [PATCH 1326/4076] bus: mhi: ep: Add checks for read/write callbacks
 while registering controllers

The MHI EP controller drivers has to support both sync and async read/write
callbacks. Hence, add a check for it.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 063c07241da78..65fc1d738bec2 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -1464,6 +1464,10 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	if (!mhi_cntrl || !mhi_cntrl->cntrl_dev || !mhi_cntrl->mmio || !mhi_cntrl->irq)
 		return -EINVAL;
 
+	if (!mhi_cntrl->read_sync || !mhi_cntrl->write_sync ||
+	    !mhi_cntrl->read_async || !mhi_cntrl->write_async)
+		return -EINVAL;
+
 	ret = mhi_ep_chan_init(mhi_cntrl, config);
 	if (ret)
 		return ret;
-- 
GitLab


From d3aaa7203a17e8399df41e7c3f088f51368b001c Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Thu, 7 Dec 2023 09:06:53 +0200
Subject: [PATCH 1327/4076] pinctrl: renesas: rzg2l: Add pin configuration
 support for pinmux groups

On RZ/G3S different Ethernet pins need to be configured with different
settings (e.g. power-source needs to be set, RGMII TXC and TX_CTL pins
need output-enable).  Adjust the driver to allow specifying pin
configuration for pinmux groups.  With this, DT settings like the
following are taken into account by the driver:

    eth0_pins: eth0 {
	    tx_ctl {
		    pinmux = <RZG2L_PORT_PINMUX(1, 1, 1)>;  /* ET0_TX_CTL */
		    power-source = <1800>;
		    output-enable;
		    drive-strength-microamp = <5200>;
	    };
    };

Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231207070700.4156557-5-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 413ef9715503c..b27296382816c 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -376,8 +376,11 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		goto done;
 	}
 
-	if (num_pinmux)
+	if (num_pinmux) {
 		nmaps += 1;
+		if (num_configs)
+			nmaps += 1;
+	}
 
 	if (num_pins)
 		nmaps += num_pins;
@@ -462,6 +465,16 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 	maps[idx].data.mux.function = name;
 	idx++;
 
+	if (num_configs) {
+		ret = rzg2l_map_add_config(&maps[idx], name,
+					   PIN_MAP_TYPE_CONFIGS_GROUP,
+					   configs, num_configs);
+		if (ret < 0)
+			goto remove_group;
+
+		idx++;
+	}
+
 	dev_dbg(pctrl->dev, "Parsed %pOF with %d pins\n", np, num_pinmux);
 	ret = 0;
 	goto done;
-- 
GitLab


From 51996952b8b50942ed3069141ebc1dee13756b95 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Thu, 7 Dec 2023 09:06:54 +0200
Subject: [PATCH 1328/4076] pinctrl: renesas: rzg2l: Add support to select
 power source for Ethernet pins

The GPIO controller available on RZ/G3S (but also on RZ/G2L) supports
setting the power source for Ethernet pins.  Based on the interface b/w
the Ethernet controller and the Ethernet PHY, and on board design, a
specific power source needs to be selected.  The GPIO controller
supports 1.8V, 2.5V, and 3.3V power source selection for the Ethernet
pins.  This can be selected though the ETHx_POC registers (x={0, 1}).

Adjust the driver to support this, and to do proper instantiation for
the RZ/G3S and RZ/G2L SoCs.  On RZ/G2L only the get operation has been
tested at the moment.

While at it, as the power registers on RZ/G2L support access sizes of 8
bits, and these registers on RZ/G3S support access sizes of 8/16/32
bits, replace writel()/readl() on these registers with writeb()/readb().
This should allow us to use the same code on both SoCs w/o any issues.

Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231207070700.4156557-6-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 42 +++++++++++++++++++++++--
 1 file changed, 39 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index b27296382816c..923bcc49af99d 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -107,8 +107,10 @@
 #define IEN(off)		(0x1800 + (off) * 8)
 #define ISEL(off)		(0x2C00 + (off) * 8)
 #define SD_CH(off, ch)		((off) + (ch) * 4)
+#define ETH_POC(off, ch)	((off) + (ch) * 4)
 #define QSPI			(0x3008)
 
+#define PVDD_2500		2	/* I/O domain voltage 2.5V */
 #define PVDD_1800		1	/* I/O domain voltage <= 1.8V */
 #define PVDD_3300		0	/* I/O domain voltage >= 3.3V */
 
@@ -116,7 +118,6 @@
 #define PWPR_PFCWE		BIT(6)	/* PFC Register Write Enable */
 
 #define PM_MASK			0x03
-#define PVDD_MASK		0x01
 #define PFC_MASK		0x07
 #define IEN_MASK		0x01
 #define IOLH_MASK		0x03
@@ -135,10 +136,12 @@
  * struct rzg2l_register_offsets - specific register offsets
  * @pwpr: PWPR register offset
  * @sd_ch: SD_CH register offset
+ * @eth_poc: ETH_POC register offset
  */
 struct rzg2l_register_offsets {
 	u16 pwpr;
 	u16 sd_ch;
+	u16 eth_poc;
 };
 
 /**
@@ -604,6 +607,10 @@ static int rzg2l_caps_to_pwr_reg(const struct rzg2l_register_offsets *regs, u32
 		return SD_CH(regs->sd_ch, 0);
 	if (caps & PIN_CFG_IO_VMC_SD1)
 		return SD_CH(regs->sd_ch, 1);
+	if (caps & PIN_CFG_IO_VMC_ETH0)
+		return ETH_POC(regs->eth_poc, 0);
+	if (caps & PIN_CFG_IO_VMC_ETH1)
+		return ETH_POC(regs->eth_poc, 1);
 	if (caps & PIN_CFG_IO_VMC_QSPI)
 		return QSPI;
 
@@ -615,6 +622,7 @@ static int rzg2l_get_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps
 	const struct rzg2l_hwcfg *hwcfg = pctrl->data->hwcfg;
 	const struct rzg2l_register_offsets *regs = &hwcfg->regs;
 	int pwr_reg;
+	u8 val;
 
 	if (caps & PIN_CFG_SOFT_PS)
 		return pctrl->settings[pin].power_source;
@@ -623,7 +631,18 @@ static int rzg2l_get_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps
 	if (pwr_reg < 0)
 		return pwr_reg;
 
-	return (readl(pctrl->base + pwr_reg) & PVDD_MASK) ? 1800 : 3300;
+	val = readb(pctrl->base + pwr_reg);
+	switch (val) {
+	case PVDD_1800:
+		return 1800;
+	case PVDD_2500:
+		return 2500;
+	case PVDD_3300:
+		return 3300;
+	default:
+		/* Should not happen. */
+		return -EINVAL;
+	}
 }
 
 static int rzg2l_set_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps, u32 ps)
@@ -631,17 +650,32 @@ static int rzg2l_set_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps
 	const struct rzg2l_hwcfg *hwcfg = pctrl->data->hwcfg;
 	const struct rzg2l_register_offsets *regs = &hwcfg->regs;
 	int pwr_reg;
+	u8 val;
 
 	if (caps & PIN_CFG_SOFT_PS) {
 		pctrl->settings[pin].power_source = ps;
 		return 0;
 	}
 
+	switch (ps) {
+	case 1800:
+		val = PVDD_1800;
+		break;
+	case 2500:
+		val = PVDD_2500;
+		break;
+	case 3300:
+		val = PVDD_3300;
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	pwr_reg = rzg2l_caps_to_pwr_reg(regs, caps);
 	if (pwr_reg < 0)
 		return pwr_reg;
 
-	writel((ps == 1800) ? PVDD_1800 : PVDD_3300, pctrl->base + pwr_reg);
+	writeb(val, pctrl->base + pwr_reg);
 	pctrl->settings[pin].power_source = ps;
 
 	return 0;
@@ -1885,6 +1919,7 @@ static const struct rzg2l_hwcfg rzg2l_hwcfg = {
 	.regs = {
 		.pwpr = 0x3014,
 		.sd_ch = 0x3000,
+		.eth_poc = 0x300c,
 	},
 	.iolh_groupa_ua = {
 		/* 3v3 power source */
@@ -1897,6 +1932,7 @@ static const struct rzg2l_hwcfg rzg3s_hwcfg = {
 	.regs = {
 		.pwpr = 0x3000,
 		.sd_ch = 0x3004,
+		.eth_poc = 0x3010,
 	},
 	.iolh_groupa_ua = {
 		/* 1v8 power source */
-- 
GitLab


From 1bbc8ee40826164d16e32d377654c93ef48d1458 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Thu, 7 Dec 2023 09:06:55 +0200
Subject: [PATCH 1329/4076] pinctrl: renesas: rzg2l: Add output enable support

Some of the Ethernet pins on RZ/G3S (but also valid for RZ/G2L) need to
have the direction of the IO buffer set as output for Ethernet to work
properly.  On RZ/G3S, these pins are P1_0/P7_0, P1_1/P7_1, and can have
the following Ethernet functions: TXC/TX_CLK or TX_CTL/TX_EN.

As the pins supporting output enable are SoC specific, and there is a
limited number of these pins (TXC/TX_CLK and/or TX_CTL/TX_EN), specify
output enable capable port limits in the platform-based configuration
data structure, to ensure proper validation.

The OEN support has been intantiated for RZ/G3S at the moment.

Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231207070700.4156557-7-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 87 ++++++++++++++++++++++++-
 1 file changed, 85 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 923bcc49af99d..d65bc5e84fac7 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -57,6 +57,7 @@
 #define PIN_CFG_FILCLKSEL		BIT(12)
 #define PIN_CFG_IOLH_C			BIT(13)
 #define PIN_CFG_SOFT_PS			BIT(14)
+#define PIN_CFG_OEN			BIT(15)
 
 #define RZG2L_MPXED_COMMON_PIN_FUNCS(group) \
 					(PIN_CFG_IOLH_##group | \
@@ -109,6 +110,7 @@
 #define SD_CH(off, ch)		((off) + (ch) * 4)
 #define ETH_POC(off, ch)	((off) + (ch) * 4)
 #define QSPI			(0x3008)
+#define ETH_MODE		(0x3018)
 
 #define PVDD_2500		2	/* I/O domain voltage 2.5V */
 #define PVDD_1800		1	/* I/O domain voltage <= 1.8V */
@@ -170,6 +172,8 @@ enum rzg2l_iolh_index {
  * @iolh_groupb_oi: IOLH group B output impedance specific values
  * @drive_strength_ua: drive strength in uA is supported (otherwise mA is supported)
  * @func_base: base number for port function (see register PFC)
+ * @oen_max_pin: the maximum pin number supporting output enable
+ * @oen_max_port: the maximum port number supporting output enable
  */
 struct rzg2l_hwcfg {
 	const struct rzg2l_register_offsets regs;
@@ -179,6 +183,8 @@ struct rzg2l_hwcfg {
 	u16 iolh_groupb_oi[4];
 	bool drive_strength_ua;
 	u8 func_base;
+	u8 oen_max_pin;
+	u8 oen_max_port;
 };
 
 struct rzg2l_dedicated_configs {
@@ -782,6 +788,66 @@ static bool rzg2l_ds_is_supported(struct rzg2l_pinctrl *pctrl, u32 caps,
 	return false;
 }
 
+static bool rzg2l_oen_is_supported(u32 caps, u8 pin, u8 max_pin)
+{
+	if (!(caps & PIN_CFG_OEN))
+		return false;
+
+	if (pin > max_pin)
+		return false;
+
+	return true;
+}
+
+static u8 rzg2l_pin_to_oen_bit(u32 offset, u8 pin, u8 max_port)
+{
+	if (pin)
+		pin *= 2;
+
+	if (offset / RZG2L_PINS_PER_PORT == max_port)
+		pin += 1;
+
+	return pin;
+}
+
+static u32 rzg2l_read_oen(struct rzg2l_pinctrl *pctrl, u32 caps, u32 offset, u8 pin)
+{
+	u8 max_port = pctrl->data->hwcfg->oen_max_port;
+	u8 max_pin = pctrl->data->hwcfg->oen_max_pin;
+	u8 bit;
+
+	if (!rzg2l_oen_is_supported(caps, pin, max_pin))
+		return 0;
+
+	bit = rzg2l_pin_to_oen_bit(offset, pin, max_port);
+
+	return !(readb(pctrl->base + ETH_MODE) & BIT(bit));
+}
+
+static int rzg2l_write_oen(struct rzg2l_pinctrl *pctrl, u32 caps, u32 offset, u8 pin, u8 oen)
+{
+	u8 max_port = pctrl->data->hwcfg->oen_max_port;
+	u8 max_pin = pctrl->data->hwcfg->oen_max_pin;
+	unsigned long flags;
+	u8 val, bit;
+
+	if (!rzg2l_oen_is_supported(caps, pin, max_pin))
+		return -EINVAL;
+
+	bit = rzg2l_pin_to_oen_bit(offset, pin, max_port);
+
+	spin_lock_irqsave(&pctrl->lock, flags);
+	val = readb(pctrl->base + ETH_MODE);
+	if (oen)
+		val &= ~BIT(bit);
+	else
+		val |= BIT(bit);
+	writeb(val, pctrl->base + ETH_MODE);
+	spin_unlock_irqrestore(&pctrl->lock, flags);
+
+	return 0;
+}
+
 static int rzg2l_pinctrl_pinconf_get(struct pinctrl_dev *pctldev,
 				     unsigned int _pin,
 				     unsigned long *config)
@@ -819,6 +885,12 @@ static int rzg2l_pinctrl_pinconf_get(struct pinctrl_dev *pctldev,
 			return -EINVAL;
 		break;
 
+	case PIN_CONFIG_OUTPUT_ENABLE:
+		arg = rzg2l_read_oen(pctrl, cfg, _pin, bit);
+		if (!arg)
+			return -EINVAL;
+		break;
+
 	case PIN_CONFIG_POWER_SOURCE:
 		ret = rzg2l_get_power_source(pctrl, _pin, cfg);
 		if (ret < 0)
@@ -920,6 +992,13 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
 			rzg2l_rmw_pin_config(pctrl, IEN(off), bit, IEN_MASK, !!arg);
 			break;
 
+		case PIN_CONFIG_OUTPUT_ENABLE:
+			arg = pinconf_to_config_argument(_configs[i]);
+			ret = rzg2l_write_oen(pctrl, cfg, _pin, bit, !!arg);
+			if (ret)
+				return ret;
+			break;
+
 		case PIN_CONFIG_POWER_SOURCE:
 			settings.power_source = pinconf_to_config_argument(_configs[i]);
 			break;
@@ -1364,7 +1443,8 @@ static const u32 r9a07g043_gpio_configs[] = {
 static const u32 r9a08g045_gpio_configs[] = {
 	RZG2L_GPIO_PORT_PACK(4, 0x20, RZG3S_MPXED_PIN_FUNCS(A)),			/* P0  */
 	RZG2L_GPIO_PORT_PACK(5, 0x30, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
-								PIN_CFG_IO_VMC_ETH0)),	/* P1 */
+								PIN_CFG_IO_VMC_ETH0)) |
+				      PIN_CFG_OEN,					/* P1 */
 	RZG2L_GPIO_PORT_PACK(4, 0x31, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
 								PIN_CFG_IO_VMC_ETH0)),	/* P2 */
 	RZG2L_GPIO_PORT_PACK(4, 0x32, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
@@ -1374,7 +1454,8 @@ static const u32 r9a08g045_gpio_configs[] = {
 	RZG2L_GPIO_PORT_PACK(5, 0x21, RZG3S_MPXED_PIN_FUNCS(A)),			/* P5  */
 	RZG2L_GPIO_PORT_PACK(5, 0x22, RZG3S_MPXED_PIN_FUNCS(A)),			/* P6  */
 	RZG2L_GPIO_PORT_PACK(5, 0x34, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
-								PIN_CFG_IO_VMC_ETH1)),	/* P7 */
+								PIN_CFG_IO_VMC_ETH1)) |
+				      PIN_CFG_OEN,					/* P7 */
 	RZG2L_GPIO_PORT_PACK(5, 0x35, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
 								PIN_CFG_IO_VMC_ETH1)),	/* P8 */
 	RZG2L_GPIO_PORT_PACK(4, 0x36, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
@@ -1956,6 +2037,8 @@ static const struct rzg2l_hwcfg rzg3s_hwcfg = {
 	},
 	.drive_strength_ua = true,
 	.func_base = 1,
+	.oen_max_pin = 1, /* Pin 1 of P0 and P7 is the maximum OEN pin. */
+	.oen_max_port = 7, /* P7_1 is the maximum OEN port. */
 };
 
 static struct rzg2l_pinctrl_data r9a07g043_data = {
-- 
GitLab


From 9e5889c68d992b65efd10aa0a4523c96fd07077f Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Thu, 7 Dec 2023 09:06:56 +0200
Subject: [PATCH 1330/4076] pinctrl: renesas: rzg2l: Add input enable to the
 Ethernet pins

Some of the RZ/G3S Ethernet pins (P1_0, P7_0) can be configured with
input enable.  Enable this functionality for these pins.

Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20231207070700.4156557-8-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzg2l.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index d65bc5e84fac7..e90d471368893 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -1444,7 +1444,7 @@ static const u32 r9a08g045_gpio_configs[] = {
 	RZG2L_GPIO_PORT_PACK(4, 0x20, RZG3S_MPXED_PIN_FUNCS(A)),			/* P0  */
 	RZG2L_GPIO_PORT_PACK(5, 0x30, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
 								PIN_CFG_IO_VMC_ETH0)) |
-				      PIN_CFG_OEN,					/* P1 */
+				      PIN_CFG_OEN | PIN_CFG_IEN,			/* P1 */
 	RZG2L_GPIO_PORT_PACK(4, 0x31, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
 								PIN_CFG_IO_VMC_ETH0)),	/* P2 */
 	RZG2L_GPIO_PORT_PACK(4, 0x32, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
@@ -1455,7 +1455,7 @@ static const u32 r9a08g045_gpio_configs[] = {
 	RZG2L_GPIO_PORT_PACK(5, 0x22, RZG3S_MPXED_PIN_FUNCS(A)),			/* P6  */
 	RZG2L_GPIO_PORT_PACK(5, 0x34, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
 								PIN_CFG_IO_VMC_ETH1)) |
-				      PIN_CFG_OEN,					/* P7 */
+				      PIN_CFG_OEN | PIN_CFG_IEN,			/* P7 */
 	RZG2L_GPIO_PORT_PACK(5, 0x35, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
 								PIN_CFG_IO_VMC_ETH1)),	/* P8 */
 	RZG2L_GPIO_PORT_PACK(4, 0x36, RZG2L_MPXED_ETH_PIN_FUNCS(PIN_CFG_IOLH_C |
-- 
GitLab


From 327ec5f70609cf00c6f961073c01857555c6a8eb Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Thu, 14 Dec 2023 12:03:28 +0530
Subject: [PATCH 1331/4076] PCI: epf-mhi: Fix the DMA data direction of
 dma_unmap_single()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the error path of pci_epf_mhi_edma_write() function, the DMA data
direction passed (DMA_FROM_DEVICE) doesn't match the actual direction used
for the data transfer. Fix it by passing the correct one (DMA_TO_DEVICE).

Fixes: 7b99aaaddabb ("PCI: epf-mhi: Add eDMA support")
Reviewed-by: Krzysztof Wilczyński <kw@linux.com>
Link: https://lore.kernel.org/r/20231214063328.40657-1-manivannan.sadhasivam@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index 472bc489b754b..d3d6a1054036b 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -424,7 +424,7 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl,
 	}
 
 err_unmap:
-	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_FROM_DEVICE);
+	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_TO_DEVICE);
 err_unlock:
 	mutex_unlock(&epf_mhi->lock);
 
-- 
GitLab


From 7f38b70042fcaa49219045bd1a9a2836e27a58ac Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:27 +0000
Subject: [PATCH 1332/4076] of: device: Export of_device_make_bus_id()

This helper is really handy to create unique device names based on their
device tree path, we may need it outside of the OF core (in the NVMEM
subsystem) so let's export it. As this helper has nothing patform
specific, let's move it to of/device.c instead of of/platform.c so we
can add its prototype to of_device.h.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-2-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/of/device.c       | 41 +++++++++++++++++++++++++++++++++++++++
 drivers/of/platform.c     | 40 --------------------------------------
 include/linux/of_device.h |  6 ++++++
 3 files changed, 47 insertions(+), 40 deletions(-)

diff --git a/drivers/of/device.c b/drivers/of/device.c
index 1ca42ad9dd159..6e9572c4af83b 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -304,3 +304,44 @@ int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_device_uevent_modalias);
+
+/**
+ * of_device_make_bus_id - Use the device node data to assign a unique name
+ * @dev: pointer to device structure that is linked to a device tree node
+ *
+ * This routine will first try using the translated bus address to
+ * derive a unique name. If it cannot, then it will prepend names from
+ * parent nodes until a unique name can be derived.
+ */
+void of_device_make_bus_id(struct device *dev)
+{
+	struct device_node *node = dev->of_node;
+	const __be32 *reg;
+	u64 addr;
+	u32 mask;
+
+	/* Construct the name, using parent nodes if necessary to ensure uniqueness */
+	while (node->parent) {
+		/*
+		 * If the address can be translated, then that is as much
+		 * uniqueness as we need. Make it the first component and return
+		 */
+		reg = of_get_property(node, "reg", NULL);
+		if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) {
+			if (!of_property_read_u32(node, "mask", &mask))
+				dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn",
+					     addr, ffs(mask) - 1, node, dev_name(dev));
+
+			else
+				dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
+					     addr, node, dev_name(dev));
+			return;
+		}
+
+		/* format arguments only used if dev_name() resolves to NULL */
+		dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s",
+			     kbasename(node->full_name), dev_name(dev));
+		node = node->parent;
+	}
+}
+EXPORT_SYMBOL_GPL(of_device_make_bus_id);
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 126d265aa7d86..c39e49a1eba00 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -97,46 +97,6 @@ static const struct of_device_id of_skipped_node_table[] = {
  * mechanism for creating devices from device tree nodes.
  */
 
-/**
- * of_device_make_bus_id - Use the device node data to assign a unique name
- * @dev: pointer to device structure that is linked to a device tree node
- *
- * This routine will first try using the translated bus address to
- * derive a unique name. If it cannot, then it will prepend names from
- * parent nodes until a unique name can be derived.
- */
-static void of_device_make_bus_id(struct device *dev)
-{
-	struct device_node *node = dev->of_node;
-	const __be32 *reg;
-	u64 addr;
-	u32 mask;
-
-	/* Construct the name, using parent nodes if necessary to ensure uniqueness */
-	while (node->parent) {
-		/*
-		 * If the address can be translated, then that is as much
-		 * uniqueness as we need. Make it the first component and return
-		 */
-		reg = of_get_property(node, "reg", NULL);
-		if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) {
-			if (!of_property_read_u32(node, "mask", &mask))
-				dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn",
-					     addr, ffs(mask) - 1, node, dev_name(dev));
-
-			else
-				dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
-					     addr, node, dev_name(dev));
-			return;
-		}
-
-		/* format arguments only used if dev_name() resolves to NULL */
-		dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s",
-			     kbasename(node->full_name), dev_name(dev));
-		node = node->parent;
-	}
-}
-
 /**
  * of_device_alloc - Allocate and initialize an of_device
  * @np: device node to assign to device
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 2c7a3d4bc775b..a72661e47faa5 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -40,6 +40,9 @@ static inline int of_dma_configure(struct device *dev,
 {
 	return of_dma_configure_id(dev, np, force_dma, NULL);
 }
+
+void of_device_make_bus_id(struct device *dev);
+
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -82,6 +85,9 @@ static inline int of_dma_configure(struct device *dev,
 {
 	return 0;
 }
+
+static inline void of_device_make_bus_id(struct device *dev) {}
+
 #endif /* CONFIG_OF */
 
 #endif /* _LINUX_OF_DEVICE_H */
-- 
GitLab


From 4a1a40233b4a9fc159a5c7a27dc34c5c7bc5be55 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:28 +0000
Subject: [PATCH 1333/4076] nvmem: Move of_nvmem_layout_get_container() in
 another header

nvmem-consumer.h is included by consumer devices, extracting data from
NVMEM devices whereas nvmem-provider.h is included by devices providing
NVMEM content.

The only users of of_nvmem_layout_get_container() outside of the core
are layout drivers, so better move its prototype to nvmem-provider.h.

While we do so, we also move the kdoc associated with the function to
the header rather than the .c file.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-3-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           |  8 --------
 include/linux/nvmem-consumer.h |  7 -------
 include/linux/nvmem-provider.h | 21 +++++++++++++++++++++
 3 files changed, 21 insertions(+), 15 deletions(-)

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 608b352a7d91f..b5b6ec8e04bb3 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -847,14 +847,6 @@ static int nvmem_add_cells_from_layout(struct nvmem_device *nvmem)
 }
 
 #if IS_ENABLED(CONFIG_OF)
-/**
- * of_nvmem_layout_get_container() - Get OF node to layout container.
- *
- * @nvmem: nvmem device.
- *
- * Return: a node pointer with refcount incremented or NULL if no
- * container exists. Use of_node_put() on it when done.
- */
 struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
 {
 	return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout");
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 6ec4b9743e25d..2d306fa13b1a8 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -247,7 +247,6 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 				     const char *id);
 struct nvmem_device *of_nvmem_device_get(struct device_node *np,
 					 const char *name);
-struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem);
 #else
 static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 						   const char *id)
@@ -260,12 +259,6 @@ static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-
-static inline struct device_node *
-of_nvmem_layout_get_container(struct nvmem_device *nvmem)
-{
-	return NULL;
-}
 #endif /* CONFIG_NVMEM && CONFIG_OF */
 
 #endif  /* ifndef _LINUX_NVMEM_CONSUMER_H */
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index e3930835235ba..e5de21516387e 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -244,6 +244,27 @@ nvmem_layout_get_match_data(struct nvmem_device *nvmem,
 
 #endif /* CONFIG_NVMEM */
 
+#if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF)
+
+/**
+ * of_nvmem_layout_get_container() - Get OF node of layout container
+ *
+ * @nvmem: nvmem device
+ *
+ * Return: a node pointer with refcount incremented or NULL if no
+ * container exists. Use of_node_put() on it when done.
+ */
+struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem);
+
+#else  /* CONFIG_NVMEM && CONFIG_OF */
+
+static inline struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_NVMEM && CONFIG_OF */
+
 #define module_nvmem_layout_driver(__layout_driver)		\
 	module_driver(__layout_driver, nvmem_layout_register,	\
 		      nvmem_layout_unregister)
-- 
GitLab


From ec9c08a1cb8dc5e8e003f95f5f62de41dde235bb Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:29 +0000
Subject: [PATCH 1334/4076] nvmem: Create a header for internal sharing

Before adding all the NVMEM layout bus infrastructure to the core, let's
move the main nvmem_device structure in an internal header, only
available to the core. This way all the additional code can be added in
a dedicated file in order to keep the current core file tidy.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-4-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c      | 24 +-----------------------
 drivers/nvmem/internals.h | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 23 deletions(-)
 create mode 100644 drivers/nvmem/internals.h

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index b5b6ec8e04bb3..b5e5ce67398ff 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -19,29 +19,7 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 
-struct nvmem_device {
-	struct module		*owner;
-	struct device		dev;
-	int			stride;
-	int			word_size;
-	int			id;
-	struct kref		refcnt;
-	size_t			size;
-	bool			read_only;
-	bool			root_only;
-	int			flags;
-	enum nvmem_type		type;
-	struct bin_attribute	eeprom;
-	struct device		*base_dev;
-	struct list_head	cells;
-	const struct nvmem_keepout *keepout;
-	unsigned int		nkeepout;
-	nvmem_reg_read_t	reg_read;
-	nvmem_reg_write_t	reg_write;
-	struct gpio_desc	*wp_gpio;
-	struct nvmem_layout	*layout;
-	void *priv;
-};
+#include "internals.h"
 
 #define to_nvmem_device(d) container_of(d, struct nvmem_device, dev)
 
diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
new file mode 100644
index 0000000000000..ce353831cd655
--- /dev/null
+++ b/drivers/nvmem/internals.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_NVMEM_INTERNALS_H
+#define _LINUX_NVMEM_INTERNALS_H
+
+#include <linux/device.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/nvmem-provider.h>
+
+struct nvmem_device {
+	struct module		*owner;
+	struct device		dev;
+	struct list_head	node;
+	int			stride;
+	int			word_size;
+	int			id;
+	struct kref		refcnt;
+	size_t			size;
+	bool			read_only;
+	bool			root_only;
+	int			flags;
+	enum nvmem_type		type;
+	struct bin_attribute	eeprom;
+	struct device		*base_dev;
+	struct list_head	cells;
+	const struct nvmem_keepout *keepout;
+	unsigned int		nkeepout;
+	nvmem_reg_read_t	reg_read;
+	nvmem_reg_write_t	reg_write;
+	struct gpio_desc	*wp_gpio;
+	struct nvmem_layout	*layout;
+	void *priv;
+};
+
+#endif  /* ifndef _LINUX_NVMEM_INTERNALS_H */
-- 
GitLab


From 1b7c298a4ecbc28cc6ee94005734bff55eb83d22 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:30 +0000
Subject: [PATCH 1335/4076] nvmem: Simplify the ->add_cells() hook

The layout entry is not used and will anyway be made useless by the new
layout bus infrastructure coming next, so drop it. While at it, clarify
the kdoc entry.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-5-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c             | 2 +-
 drivers/nvmem/layouts/onie-tlv.c | 3 +--
 drivers/nvmem/layouts/sl28vpd.c  | 3 +--
 include/linux/nvmem-provider.h   | 8 +++-----
 4 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index b5e5ce67398ff..f63db5e01fca9 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -816,7 +816,7 @@ static int nvmem_add_cells_from_layout(struct nvmem_device *nvmem)
 	int ret;
 
 	if (layout && layout->add_cells) {
-		ret = layout->add_cells(&nvmem->dev, nvmem, layout);
+		ret = layout->add_cells(&nvmem->dev, nvmem);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c
index 59fc87ccfcffe..defd42d4375cc 100644
--- a/drivers/nvmem/layouts/onie-tlv.c
+++ b/drivers/nvmem/layouts/onie-tlv.c
@@ -182,8 +182,7 @@ static bool onie_tlv_crc_is_valid(struct device *dev, size_t table_len, u8 *tabl
 	return true;
 }
 
-static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem,
-				struct nvmem_layout *layout)
+static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem)
 {
 	struct onie_tlv_hdr hdr;
 	size_t table_len, data_len, hdr_len;
diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c
index 05671371f6316..26c7cf21b5233 100644
--- a/drivers/nvmem/layouts/sl28vpd.c
+++ b/drivers/nvmem/layouts/sl28vpd.c
@@ -80,8 +80,7 @@ static int sl28vpd_v1_check_crc(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
-static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem,
-			     struct nvmem_layout *layout)
+static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem)
 {
 	const struct nvmem_cell_info *pinfo;
 	struct nvmem_cell_info info = {0};
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index e5de21516387e..3939991b3c5f9 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -156,9 +156,8 @@ struct nvmem_cell_table {
  *
  * @name:		Layout name.
  * @of_match_table:	Open firmware match table.
- * @add_cells:		Will be called if a nvmem device is found which
- *			has this layout. The function will add layout
- *			specific cells with nvmem_add_one_cell().
+ * @add_cells:		Called to populate the layout using
+ *			nvmem_add_one_cell().
  * @fixup_cell_info:	Will be called before a cell is added. Can be
  *			used to modify the nvmem_cell_info.
  * @owner:		Pointer to struct module.
@@ -172,8 +171,7 @@ struct nvmem_cell_table {
 struct nvmem_layout {
 	const char *name;
 	const struct of_device_id *of_match_table;
-	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem,
-			 struct nvmem_layout *layout);
+	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem);
 	void (*fixup_cell_info)(struct nvmem_device *nvmem,
 				struct nvmem_layout *layout,
 				struct nvmem_cell_info *cell);
-- 
GitLab


From 1172460e716784ac7e1049a537bdca8edbf97360 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:31 +0000
Subject: [PATCH 1336/4076] nvmem: Move and rename ->fixup_cell_info()

This hook is meant to be used by any provider and instantiating a layout
just for this is useless. Let's instead move this hook to the nvmem
device and add it to the config structure to be easily shared by the
providers.

While at moving this hook, rename it ->fixup_dt_cell_info() to clarify
its main intended purpose.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-6-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           |  6 +++---
 drivers/nvmem/imx-ocotp.c      | 11 +++--------
 drivers/nvmem/internals.h      |  2 ++
 drivers/nvmem/mtk-efuse.c      | 11 +++--------
 include/linux/nvmem-provider.h |  9 ++++-----
 5 files changed, 15 insertions(+), 24 deletions(-)

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index f63db5e01fca9..a885713d6b4b7 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -675,7 +675,6 @@ static int nvmem_validate_keepouts(struct nvmem_device *nvmem)
 
 static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np)
 {
-	struct nvmem_layout *layout = nvmem->layout;
 	struct device *dev = &nvmem->dev;
 	struct device_node *child;
 	const __be32 *addr;
@@ -705,8 +704,8 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod
 
 		info.np = of_node_get(child);
 
-		if (layout && layout->fixup_cell_info)
-			layout->fixup_cell_info(nvmem, layout, &info);
+		if (nvmem->fixup_dt_cell_info)
+			nvmem->fixup_dt_cell_info(nvmem, &info);
 
 		ret = nvmem_add_one_cell(nvmem, &info);
 		kfree(info.name);
@@ -895,6 +894,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 
 	kref_init(&nvmem->refcnt);
 	INIT_LIST_HEAD(&nvmem->cells);
+	nvmem->fixup_dt_cell_info = config->fixup_dt_cell_info;
 
 	nvmem->owner = config->owner;
 	if (!nvmem->owner && config->dev->driver)
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index f1e202efaa497..79dd4fda03295 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -583,17 +583,12 @@ static const struct of_device_id imx_ocotp_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids);
 
-static void imx_ocotp_fixup_cell_info(struct nvmem_device *nvmem,
-				      struct nvmem_layout *layout,
-				      struct nvmem_cell_info *cell)
+static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem,
+					 struct nvmem_cell_info *cell)
 {
 	cell->read_post_process = imx_ocotp_cell_pp;
 }
 
-static struct nvmem_layout imx_ocotp_layout = {
-	.fixup_cell_info = imx_ocotp_fixup_cell_info,
-};
-
 static int imx_ocotp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -619,7 +614,7 @@ static int imx_ocotp_probe(struct platform_device *pdev)
 	imx_ocotp_nvmem_config.size = 4 * priv->params->nregs;
 	imx_ocotp_nvmem_config.dev = dev;
 	imx_ocotp_nvmem_config.priv = priv;
-	imx_ocotp_nvmem_config.layout = &imx_ocotp_layout;
+	imx_ocotp_nvmem_config.fixup_dt_cell_info = &imx_ocotp_fixup_dt_cell_info;
 
 	priv->config = &imx_ocotp_nvmem_config;
 
diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
index ce353831cd655..893553fbdf51a 100644
--- a/drivers/nvmem/internals.h
+++ b/drivers/nvmem/internals.h
@@ -23,6 +23,8 @@ struct nvmem_device {
 	struct bin_attribute	eeprom;
 	struct device		*base_dev;
 	struct list_head	cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
 	const struct nvmem_keepout *keepout;
 	unsigned int		nkeepout;
 	nvmem_reg_read_t	reg_read;
diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c
index 87c94686cfd21..84f05b40a4112 100644
--- a/drivers/nvmem/mtk-efuse.c
+++ b/drivers/nvmem/mtk-efuse.c
@@ -45,9 +45,8 @@ static int mtk_efuse_gpu_speedbin_pp(void *context, const char *id, int index,
 	return 0;
 }
 
-static void mtk_efuse_fixup_cell_info(struct nvmem_device *nvmem,
-				      struct nvmem_layout *layout,
-				      struct nvmem_cell_info *cell)
+static void mtk_efuse_fixup_dt_cell_info(struct nvmem_device *nvmem,
+					 struct nvmem_cell_info *cell)
 {
 	size_t sz = strlen(cell->name);
 
@@ -61,10 +60,6 @@ static void mtk_efuse_fixup_cell_info(struct nvmem_device *nvmem,
 		cell->read_post_process = mtk_efuse_gpu_speedbin_pp;
 }
 
-static struct nvmem_layout mtk_efuse_layout = {
-	.fixup_cell_info = mtk_efuse_fixup_cell_info,
-};
-
 static int mtk_efuse_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -91,7 +86,7 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	econfig.priv = priv;
 	econfig.dev = dev;
 	if (pdata->uses_post_processing)
-		econfig.layout = &mtk_efuse_layout;
+		econfig.fixup_dt_cell_info = &mtk_efuse_fixup_dt_cell_info;
 	nvmem = devm_nvmem_register(dev, &econfig);
 
 	return PTR_ERR_OR_ZERO(nvmem);
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 3939991b3c5f9..36415a602d9eb 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -83,6 +83,8 @@ struct nvmem_cell_info {
  * @cells:	Optional array of pre-defined NVMEM cells.
  * @ncells:	Number of elements in cells.
  * @add_legacy_fixed_of_cells:	Read fixed NVMEM cells from old OF syntax.
+ * @fixup_dt_cell_info: Will be called before a cell is added. Can be
+ *		used to modify the nvmem_cell_info.
  * @keepout:	Optional array of keepout ranges (sorted ascending by start).
  * @nkeepout:	Number of elements in the keepout array.
  * @type:	Type of the nvmem storage
@@ -113,6 +115,8 @@ struct nvmem_config {
 	const struct nvmem_cell_info	*cells;
 	int			ncells;
 	bool			add_legacy_fixed_of_cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
 	const struct nvmem_keepout *keepout;
 	unsigned int		nkeepout;
 	enum nvmem_type		type;
@@ -158,8 +162,6 @@ struct nvmem_cell_table {
  * @of_match_table:	Open firmware match table.
  * @add_cells:		Called to populate the layout using
  *			nvmem_add_one_cell().
- * @fixup_cell_info:	Will be called before a cell is added. Can be
- *			used to modify the nvmem_cell_info.
  * @owner:		Pointer to struct module.
  * @node:		List node.
  *
@@ -172,9 +174,6 @@ struct nvmem_layout {
 	const char *name;
 	const struct of_device_id *of_match_table;
 	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem);
-	void (*fixup_cell_info)(struct nvmem_device *nvmem,
-				struct nvmem_layout *layout,
-				struct nvmem_cell_info *cell);
 
 	/* private */
 	struct module *owner;
-- 
GitLab


From fc29fd821d9ac2ae3d32a722fac39ce874efb883 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:32 +0000
Subject: [PATCH 1337/4076] nvmem: core: Rework layouts to become regular
 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Current layout support was initially written without modules support in
mind. When the requirement for module support rose, the existing base
was improved to adopt modularization support, but kind of a design flaw
was introduced. With the existing implementation, when a storage device
registers into NVMEM, the core tries to hook a layout (if any) and
populates its cells immediately. This means, if the hardware description
expects a layout to be hooked up, but no driver was provided for that,
the storage medium will fail to probe and try later from
scratch. Even if we consider that the hardware description shall be
correct, we could still probe the storage device (especially if it
contains the rootfs).

One way to overcome this situation is to consider the layouts as
devices, and leverage the native notifier mechanism. When a new NVMEM
device is registered, we can populate its nvmem-layout child, if any,
and wait for the matching to be done in order to get the cells (the
waiting can be easily done with the NVMEM notifiers). If the layout
driver is compiled as a module, it should automatically be loaded. This
way, there is no strong order to enforce, any NVMEM device creation
or NVMEM layout driver insertion will be observed as a new event which
may lead to the creation of additional cells, without disturbing the
probes with costly (and sometimes endless) deferrals.

In order to achieve that goal we create a new bus for the nvmem-layouts
with minimal logic to match nvmem-layout devices with nvmem-layout
drivers. All this infrastructure code is created in the layouts.c file.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Tested-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-7-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/Kconfig            |   1 +
 drivers/nvmem/Makefile           |   2 +
 drivers/nvmem/core.c             | 170 ++++++++++----------------
 drivers/nvmem/internals.h        |  21 ++++
 drivers/nvmem/layouts.c          | 201 +++++++++++++++++++++++++++++++
 drivers/nvmem/layouts/Kconfig    |   8 ++
 drivers/nvmem/layouts/onie-tlv.c |  24 +++-
 drivers/nvmem/layouts/sl28vpd.c  |  24 +++-
 include/linux/nvmem-provider.h   |  38 +++---
 9 files changed, 354 insertions(+), 135 deletions(-)
 create mode 100644 drivers/nvmem/layouts.c

diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig
index 5bc9c4874fe3b..283134498fbc3 100644
--- a/drivers/nvmem/Kconfig
+++ b/drivers/nvmem/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menuconfig NVMEM
 	bool "NVMEM Support"
+	imply NVMEM_LAYOUTS
 	help
 	  Support for NVMEM(Non Volatile Memory) devices like EEPROM, EFUSES...
 
diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile
index 423baf089515c..cdd01fbf1313b 100644
--- a/drivers/nvmem/Makefile
+++ b/drivers/nvmem/Makefile
@@ -5,6 +5,8 @@
 
 obj-$(CONFIG_NVMEM)		+= nvmem_core.o
 nvmem_core-y			:= core.o
+obj-$(CONFIG_NVMEM_LAYOUTS)	+= nvmem_layouts.o
+nvmem_layouts-y			:= layouts.o
 obj-y				+= layouts/
 
 # Devices
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index a885713d6b4b7..4c2154ddf8a7f 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -55,9 +55,6 @@ static LIST_HEAD(nvmem_lookup_list);
 
 static BLOCKING_NOTIFIER_HEAD(nvmem_notifier);
 
-static DEFINE_SPINLOCK(nvmem_layout_lock);
-static LIST_HEAD(nvmem_layouts);
-
 static int __nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset,
 			    void *val, size_t bytes)
 {
@@ -740,97 +737,22 @@ static int nvmem_add_cells_from_fixed_layout(struct nvmem_device *nvmem)
 	return err;
 }
 
-int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner)
+int nvmem_layout_register(struct nvmem_layout *layout)
 {
-	layout->owner = owner;
-
-	spin_lock(&nvmem_layout_lock);
-	list_add(&layout->node, &nvmem_layouts);
-	spin_unlock(&nvmem_layout_lock);
-
-	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_LAYOUT_ADD, layout);
+	if (!layout->add_cells)
+		return -EINVAL;
 
-	return 0;
+	/* Populate the cells */
+	return layout->add_cells(&layout->nvmem->dev, layout->nvmem);
 }
-EXPORT_SYMBOL_GPL(__nvmem_layout_register);
+EXPORT_SYMBOL_GPL(nvmem_layout_register);
 
 void nvmem_layout_unregister(struct nvmem_layout *layout)
 {
-	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_LAYOUT_REMOVE, layout);
-
-	spin_lock(&nvmem_layout_lock);
-	list_del(&layout->node);
-	spin_unlock(&nvmem_layout_lock);
+	/* Keep the API even with an empty stub in case we need it later */
 }
 EXPORT_SYMBOL_GPL(nvmem_layout_unregister);
 
-static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem)
-{
-	struct device_node *layout_np;
-	struct nvmem_layout *l, *layout = ERR_PTR(-EPROBE_DEFER);
-
-	layout_np = of_nvmem_layout_get_container(nvmem);
-	if (!layout_np)
-		return NULL;
-
-	/* Fixed layouts don't have a matching driver */
-	if (of_device_is_compatible(layout_np, "fixed-layout")) {
-		of_node_put(layout_np);
-		return NULL;
-	}
-
-	/*
-	 * In case the nvmem device was built-in while the layout was built as a
-	 * module, we shall manually request the layout driver loading otherwise
-	 * we'll never have any match.
-	 */
-	of_request_module(layout_np);
-
-	spin_lock(&nvmem_layout_lock);
-
-	list_for_each_entry(l, &nvmem_layouts, node) {
-		if (of_match_node(l->of_match_table, layout_np)) {
-			if (try_module_get(l->owner))
-				layout = l;
-
-			break;
-		}
-	}
-
-	spin_unlock(&nvmem_layout_lock);
-	of_node_put(layout_np);
-
-	return layout;
-}
-
-static void nvmem_layout_put(struct nvmem_layout *layout)
-{
-	if (layout)
-		module_put(layout->owner);
-}
-
-static int nvmem_add_cells_from_layout(struct nvmem_device *nvmem)
-{
-	struct nvmem_layout *layout = nvmem->layout;
-	int ret;
-
-	if (layout && layout->add_cells) {
-		ret = layout->add_cells(&nvmem->dev, nvmem);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-#if IS_ENABLED(CONFIG_OF)
-struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
-{
-	return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout");
-}
-EXPORT_SYMBOL_GPL(of_nvmem_layout_get_container);
-#endif
-
 const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
 					struct nvmem_layout *layout)
 {
@@ -838,7 +760,7 @@ const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
 	const struct of_device_id *match;
 
 	layout_np = of_nvmem_layout_get_container(nvmem);
-	match = of_match_node(layout->of_match_table, layout_np);
+	match = of_match_node(layout->dev.driver->of_match_table, layout_np);
 
 	return match ? match->data : NULL;
 }
@@ -950,19 +872,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 			goto err_put_device;
 	}
 
-	/*
-	 * If the driver supplied a layout by config->layout, the module
-	 * pointer will be NULL and nvmem_layout_put() will be a noop.
-	 */
-	nvmem->layout = config->layout ?: nvmem_layout_get(nvmem);
-	if (IS_ERR(nvmem->layout)) {
-		rval = PTR_ERR(nvmem->layout);
-		nvmem->layout = NULL;
-
-		if (rval == -EPROBE_DEFER)
-			goto err_teardown_compat;
-	}
-
 	if (config->cells) {
 		rval = nvmem_add_cells(nvmem, config->cells, config->ncells);
 		if (rval)
@@ -983,24 +892,24 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	if (rval)
 		goto err_remove_cells;
 
-	rval = nvmem_add_cells_from_layout(nvmem);
-	if (rval)
-		goto err_remove_cells;
-
 	dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
 
 	rval = device_add(&nvmem->dev);
 	if (rval)
 		goto err_remove_cells;
 
+	rval = nvmem_populate_layout(nvmem);
+	if (rval)
+		goto err_remove_dev;
+
 	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem);
 
 	return nvmem;
 
+err_remove_dev:
+	device_del(&nvmem->dev);
 err_remove_cells:
 	nvmem_device_remove_all_cells(nvmem);
-	nvmem_layout_put(nvmem->layout);
-err_teardown_compat:
 	if (config->compat)
 		nvmem_sysfs_remove_compat(nvmem, config);
 err_put_device:
@@ -1022,7 +931,7 @@ static void nvmem_device_release(struct kref *kref)
 		device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom);
 
 	nvmem_device_remove_all_cells(nvmem);
-	nvmem_layout_put(nvmem->layout);
+	nvmem_destroy_layout(nvmem);
 	device_unregister(&nvmem->dev);
 }
 
@@ -1324,6 +1233,12 @@ nvmem_cell_get_from_lookup(struct device *dev, const char *con_id)
 	return cell;
 }
 
+static void nvmem_layout_module_put(struct nvmem_device *nvmem)
+{
+	if (nvmem->layout && nvmem->layout->dev.driver)
+		module_put(nvmem->layout->dev.driver->owner);
+}
+
 #if IS_ENABLED(CONFIG_OF)
 static struct nvmem_cell_entry *
 nvmem_find_cell_entry_by_node(struct nvmem_device *nvmem, struct device_node *np)
@@ -1342,6 +1257,18 @@ nvmem_find_cell_entry_by_node(struct nvmem_device *nvmem, struct device_node *np
 	return cell;
 }
 
+static int nvmem_layout_module_get_optional(struct nvmem_device *nvmem)
+{
+	if (!nvmem->layout)
+		return 0;
+
+	if (!nvmem->layout->dev.driver ||
+	    !try_module_get(nvmem->layout->dev.driver->owner))
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+
 /**
  * of_nvmem_cell_get() - Get a nvmem cell from given device node and cell id
  *
@@ -1404,16 +1331,29 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id)
 		return ERR_CAST(nvmem);
 	}
 
+	ret = nvmem_layout_module_get_optional(nvmem);
+	if (ret) {
+		of_node_put(cell_np);
+		__nvmem_device_put(nvmem);
+		return ERR_PTR(ret);
+	}
+
 	cell_entry = nvmem_find_cell_entry_by_node(nvmem, cell_np);
 	of_node_put(cell_np);
 	if (!cell_entry) {
 		__nvmem_device_put(nvmem);
-		return ERR_PTR(-ENOENT);
+		nvmem_layout_module_put(nvmem);
+		if (nvmem->layout)
+			return ERR_PTR(-EPROBE_DEFER);
+		else
+			return ERR_PTR(-ENOENT);
 	}
 
 	cell = nvmem_create_cell(cell_entry, id, cell_index);
-	if (IS_ERR(cell))
+	if (IS_ERR(cell)) {
 		__nvmem_device_put(nvmem);
+		nvmem_layout_module_put(nvmem);
+	}
 
 	return cell;
 }
@@ -1527,6 +1467,7 @@ void nvmem_cell_put(struct nvmem_cell *cell)
 
 	kfree(cell);
 	__nvmem_device_put(nvmem);
+	nvmem_layout_module_put(nvmem);
 }
 EXPORT_SYMBOL_GPL(nvmem_cell_put);
 
@@ -2104,11 +2045,22 @@ EXPORT_SYMBOL_GPL(nvmem_dev_name);
 
 static int __init nvmem_init(void)
 {
-	return bus_register(&nvmem_bus_type);
+	int ret;
+
+	ret = bus_register(&nvmem_bus_type);
+	if (ret)
+		return ret;
+
+	ret = nvmem_layout_bus_register();
+	if (ret)
+		bus_unregister(&nvmem_bus_type);
+
+	return ret;
 }
 
 static void __exit nvmem_exit(void)
 {
+	nvmem_layout_bus_unregister();
 	bus_unregister(&nvmem_bus_type);
 }
 
diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
index 893553fbdf51a..4946456c76c71 100644
--- a/drivers/nvmem/internals.h
+++ b/drivers/nvmem/internals.h
@@ -34,4 +34,25 @@ struct nvmem_device {
 	void *priv;
 };
 
+#if IS_ENABLED(CONFIG_OF)
+int nvmem_layout_bus_register(void);
+void nvmem_layout_bus_unregister(void);
+int nvmem_populate_layout(struct nvmem_device *nvmem);
+void nvmem_destroy_layout(struct nvmem_device *nvmem);
+#else /* CONFIG_OF */
+static inline int nvmem_layout_bus_register(void)
+{
+	return 0;
+}
+
+static inline void nvmem_layout_bus_unregister(void) {}
+
+static inline int nvmem_populate_layout(struct nvmem_device *nvmem)
+{
+	return 0;
+}
+
+static inline void nvmem_destroy_layout(struct nvmem_device *nvmem) { }
+#endif /* CONFIG_OF */
+
 #endif  /* ifndef _LINUX_NVMEM_INTERNALS_H */
diff --git a/drivers/nvmem/layouts.c b/drivers/nvmem/layouts.c
new file mode 100644
index 0000000000000..6a6aa58369ff2
--- /dev/null
+++ b/drivers/nvmem/layouts.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMEM layout bus handling
+ *
+ * Copyright (C) 2023 Bootlin
+ * Author: Miquel Raynal <miquel.raynal@bootlin.com
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/nvmem-provider.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+
+#include "internals.h"
+
+#define to_nvmem_layout_driver(drv) \
+	(container_of((drv), struct nvmem_layout_driver, driver))
+#define to_nvmem_layout_device(_dev) \
+	container_of((_dev), struct nvmem_layout, dev)
+
+static int nvmem_layout_bus_match(struct device *dev, struct device_driver *drv)
+{
+	return of_driver_match_device(dev, drv);
+}
+
+static int nvmem_layout_bus_probe(struct device *dev)
+{
+	struct nvmem_layout_driver *drv = to_nvmem_layout_driver(dev->driver);
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	if (!drv->probe || !drv->remove)
+		return -EINVAL;
+
+	return drv->probe(layout);
+}
+
+static void nvmem_layout_bus_remove(struct device *dev)
+{
+	struct nvmem_layout_driver *drv = to_nvmem_layout_driver(dev->driver);
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	return drv->remove(layout);
+}
+
+static struct bus_type nvmem_layout_bus_type = {
+	.name		= "nvmem-layout",
+	.match		= nvmem_layout_bus_match,
+	.probe		= nvmem_layout_bus_probe,
+	.remove		= nvmem_layout_bus_remove,
+};
+
+int nvmem_layout_driver_register(struct nvmem_layout_driver *drv)
+{
+	drv->driver.bus = &nvmem_layout_bus_type;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(nvmem_layout_driver_register);
+
+void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(nvmem_layout_driver_unregister);
+
+static void nvmem_layout_release_device(struct device *dev)
+{
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	of_node_put(layout->dev.of_node);
+	kfree(layout);
+}
+
+static int nvmem_layout_create_device(struct nvmem_device *nvmem,
+				      struct device_node *np)
+{
+	struct nvmem_layout *layout;
+	struct device *dev;
+	int ret;
+
+	layout = kzalloc(sizeof(*layout), GFP_KERNEL);
+	if (!layout)
+		return -ENOMEM;
+
+	/* Create a bidirectional link */
+	layout->nvmem = nvmem;
+	nvmem->layout = layout;
+
+	/* Device model registration */
+	dev = &layout->dev;
+	device_initialize(dev);
+	dev->parent = &nvmem->dev;
+	dev->bus = &nvmem_layout_bus_type;
+	dev->release = nvmem_layout_release_device;
+	dev->coherent_dma_mask = DMA_BIT_MASK(32);
+	dev->dma_mask = &dev->coherent_dma_mask;
+	device_set_node(dev, of_fwnode_handle(of_node_get(np)));
+	of_device_make_bus_id(dev);
+	of_msi_configure(dev, dev->of_node);
+
+	ret = device_add(dev);
+	if (ret) {
+		put_device(dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id of_nvmem_layout_skip_table[] = {
+	{ .compatible = "fixed-layout", },
+	{}
+};
+
+static int nvmem_layout_bus_populate(struct nvmem_device *nvmem,
+				     struct device_node *layout_dn)
+{
+	int ret;
+
+	/* Make sure it has a compatible property */
+	if (!of_get_property(layout_dn, "compatible", NULL)) {
+		pr_debug("%s() - skipping %pOF, no compatible prop\n",
+			 __func__, layout_dn);
+		return 0;
+	}
+
+	/* Fixed layouts are parsed manually somewhere else for now */
+	if (of_match_node(of_nvmem_layout_skip_table, layout_dn)) {
+		pr_debug("%s() - skipping %pOF node\n", __func__, layout_dn);
+		return 0;
+	}
+
+	if (of_node_check_flag(layout_dn, OF_POPULATED_BUS)) {
+		pr_debug("%s() - skipping %pOF, already populated\n",
+			 __func__, layout_dn);
+
+		return 0;
+	}
+
+	/* NVMEM layout buses expect only a single device representing the layout */
+	ret = nvmem_layout_create_device(nvmem, layout_dn);
+	if (ret)
+		return ret;
+
+	of_node_set_flag(layout_dn, OF_POPULATED_BUS);
+
+	return 0;
+}
+
+struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
+{
+	return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout");
+}
+EXPORT_SYMBOL_GPL(of_nvmem_layout_get_container);
+
+/*
+ * Returns the number of devices populated, 0 if the operation was not relevant
+ * for this nvmem device, an error code otherwise.
+ */
+int nvmem_populate_layout(struct nvmem_device *nvmem)
+{
+	struct device_node *layout_dn;
+	int ret;
+
+	layout_dn = of_nvmem_layout_get_container(nvmem);
+	if (!layout_dn)
+		return 0;
+
+	/* Populate the layout device */
+	device_links_supplier_sync_state_pause();
+	ret = nvmem_layout_bus_populate(nvmem, layout_dn);
+	device_links_supplier_sync_state_resume();
+
+	of_node_put(layout_dn);
+	return ret;
+}
+
+void nvmem_destroy_layout(struct nvmem_device *nvmem)
+{
+	struct device *dev;
+
+	if (!nvmem->layout)
+		return;
+
+	dev = &nvmem->layout->dev;
+	of_node_clear_flag(dev->of_node, OF_POPULATED_BUS);
+	device_unregister(dev);
+}
+
+int nvmem_layout_bus_register(void)
+{
+	return bus_register(&nvmem_layout_bus_type);
+}
+
+void nvmem_layout_bus_unregister(void)
+{
+	bus_unregister(&nvmem_layout_bus_type);
+}
diff --git a/drivers/nvmem/layouts/Kconfig b/drivers/nvmem/layouts/Kconfig
index 7ff1ee1c1f052..9c6e672fc3509 100644
--- a/drivers/nvmem/layouts/Kconfig
+++ b/drivers/nvmem/layouts/Kconfig
@@ -1,5 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
+config NVMEM_LAYOUTS
+	bool
+	depends on OF
+
+if NVMEM_LAYOUTS
+
 menu "Layout Types"
 
 config NVMEM_LAYOUT_SL28_VPD
@@ -21,3 +27,5 @@ config NVMEM_LAYOUT_ONIE_TLV
 	  If unsure, say N.
 
 endmenu
+
+endif
diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c
index defd42d4375cc..b24cc5dcc6ee8 100644
--- a/drivers/nvmem/layouts/onie-tlv.c
+++ b/drivers/nvmem/layouts/onie-tlv.c
@@ -225,16 +225,32 @@ static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
+static int onie_tlv_probe(struct nvmem_layout *layout)
+{
+	layout->add_cells = onie_tlv_parse_table;
+
+	return nvmem_layout_register(layout);
+}
+
+static void onie_tlv_remove(struct nvmem_layout *layout)
+{
+	nvmem_layout_unregister(layout);
+}
+
 static const struct of_device_id onie_tlv_of_match_table[] = {
 	{ .compatible = "onie,tlv-layout", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, onie_tlv_of_match_table);
 
-static struct nvmem_layout onie_tlv_layout = {
-	.name = "ONIE tlv layout",
-	.of_match_table = onie_tlv_of_match_table,
-	.add_cells = onie_tlv_parse_table,
+static struct nvmem_layout_driver onie_tlv_layout = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "onie-tlv-layout",
+		.of_match_table = onie_tlv_of_match_table,
+	},
+	.probe = onie_tlv_probe,
+	.remove = onie_tlv_remove,
 };
 module_nvmem_layout_driver(onie_tlv_layout);
 
diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c
index 26c7cf21b5233..b8ffae646cc26 100644
--- a/drivers/nvmem/layouts/sl28vpd.c
+++ b/drivers/nvmem/layouts/sl28vpd.c
@@ -134,16 +134,32 @@ static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
+static int sl28vpd_probe(struct nvmem_layout *layout)
+{
+	layout->add_cells = sl28vpd_add_cells;
+
+	return nvmem_layout_register(layout);
+}
+
+static void sl28vpd_remove(struct nvmem_layout *layout)
+{
+	nvmem_layout_unregister(layout);
+}
+
 static const struct of_device_id sl28vpd_of_match_table[] = {
 	{ .compatible = "kontron,sl28-vpd" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, sl28vpd_of_match_table);
 
-static struct nvmem_layout sl28vpd_layout = {
-	.name = "sl28-vpd",
-	.of_match_table = sl28vpd_of_match_table,
-	.add_cells = sl28vpd_add_cells,
+static struct nvmem_layout_driver sl28vpd_layout = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "kontron-sl28vpd-layout",
+		.of_match_table = sl28vpd_of_match_table,
+	},
+	.probe = sl28vpd_probe,
+	.remove = sl28vpd_remove,
 };
 module_nvmem_layout_driver(sl28vpd_layout);
 
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 36415a602d9eb..6fe65b35ea972 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -9,6 +9,7 @@
 #ifndef _LINUX_NVMEM_PROVIDER_H
 #define _LINUX_NVMEM_PROVIDER_H
 
+#include <linux/device.h>
 #include <linux/device/driver.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -158,12 +159,11 @@ struct nvmem_cell_table {
 /**
  * struct nvmem_layout - NVMEM layout definitions
  *
- * @name:		Layout name.
- * @of_match_table:	Open firmware match table.
- * @add_cells:		Called to populate the layout using
- *			nvmem_add_one_cell().
- * @owner:		Pointer to struct module.
- * @node:		List node.
+ * @dev:		Device-model layout device.
+ * @nvmem:		The underlying NVMEM device
+ * @add_cells:		Will be called if a nvmem device is found which
+ *			has this layout. The function will add layout
+ *			specific cells with nvmem_add_one_cell().
  *
  * A nvmem device can hold a well defined structure which can just be
  * evaluated during runtime. For example a TLV list, or a list of "name=val"
@@ -171,13 +171,15 @@ struct nvmem_cell_table {
  * cells.
  */
 struct nvmem_layout {
-	const char *name;
-	const struct of_device_id *of_match_table;
+	struct device dev;
+	struct nvmem_device *nvmem;
 	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem);
+};
 
-	/* private */
-	struct module *owner;
-	struct list_head node;
+struct nvmem_layout_driver {
+	struct device_driver driver;
+	int (*probe)(struct nvmem_layout *layout);
+	void (*remove)(struct nvmem_layout *layout);
 };
 
 #if IS_ENABLED(CONFIG_NVMEM)
@@ -194,11 +196,15 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table);
 int nvmem_add_one_cell(struct nvmem_device *nvmem,
 		       const struct nvmem_cell_info *info);
 
-int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner);
-#define nvmem_layout_register(layout) \
-	__nvmem_layout_register(layout, THIS_MODULE)
+int nvmem_layout_register(struct nvmem_layout *layout);
 void nvmem_layout_unregister(struct nvmem_layout *layout);
 
+int nvmem_layout_driver_register(struct nvmem_layout_driver *drv);
+void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv);
+#define module_nvmem_layout_driver(__nvmem_layout_driver)		\
+	module_driver(__nvmem_layout_driver, nvmem_layout_driver_register, \
+		      nvmem_layout_driver_unregister)
+
 const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
 					struct nvmem_layout *layout);
 
@@ -262,8 +268,4 @@ static inline struct device_node *of_nvmem_layout_get_container(struct nvmem_dev
 
 #endif /* CONFIG_NVMEM && CONFIG_OF */
 
-#define module_nvmem_layout_driver(__layout_driver)		\
-	module_driver(__layout_driver, nvmem_layout_register,	\
-		      nvmem_layout_unregister)
-
 #endif  /* ifndef _LINUX_NVMEM_PROVIDER_H */
-- 
GitLab


From 192048e5a5b6660079ba4fce679e82adc05cfece Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:33 +0000
Subject: [PATCH 1338/4076] ABI: sysfs-nvmem-cells: Expose cells through sysfs

The binary content of nvmem devices is available to the user so in the
easiest cases, finding the content of a cell is rather easy as it is
just a matter of looking at a known and fixed offset. However, nvmem
layouts have been recently introduced to cope with more advanced
situations, where the offset and size of the cells is not known in
advance or is dynamic. When using layouts, more advanced parsers are
used by the kernel in order to give direct access to the content of each
cell regardless of their position/size in the underlying device, but
these information were not accessible to the user.

By exposing the nvmem cells to the user through a dedicated cell/ folder
containing one file per cell, we provide a straightforward access to
useful user information without the need for re-writing a userland
parser. Content of nvmem cells is usually: product names, manufacturing
date, MAC addresses, etc,

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-8-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-nvmem-cells | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-nvmem-cells

diff --git a/Documentation/ABI/testing/sysfs-nvmem-cells b/Documentation/ABI/testing/sysfs-nvmem-cells
new file mode 100644
index 0000000000000..7af70adf3690e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-nvmem-cells
@@ -0,0 +1,21 @@
+What:		/sys/bus/nvmem/devices/.../cells/<cell-name>
+Date:		May 2023
+KernelVersion:	6.5
+Contact:	Miquel Raynal <miquel.raynal@bootlin.com>
+Description:
+		The "cells" folder contains one file per cell exposed by the
+		NVMEM device. The name of the file is: <name>@<where>, with
+		<name> being the cell name and <where> its location in the NVMEM
+		device, in hexadecimal (without the '0x' prefix, to mimic device
+		tree node names). The length of the file is the size of the cell
+		(when known). The content of the file is the binary content of
+		the cell (may sometimes be ASCII, likely without trailing
+		character).
+		Note: This file is only present if CONFIG_NVMEM_SYSFS
+		is enabled.
+
+		Example::
+
+		  hexdump -C /sys/bus/nvmem/devices/1-00563/cells/product-name@d
+		  00000000  54 4e 34 38 4d 2d 50 2d  44 4e         |TN48M-P-DN|
+		  0000000a
-- 
GitLab


From 0331c611949fffdf486652450901a4dc52bc5cca Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:34 +0000
Subject: [PATCH 1339/4076] nvmem: core: Expose cells through sysfs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The binary content of nvmem devices is available to the user so in the
easiest cases, finding the content of a cell is rather easy as it is
just a matter of looking at a known and fixed offset. However, nvmem
layouts have been recently introduced to cope with more advanced
situations, where the offset and size of the cells is not known in
advance or is dynamic. When using layouts, more advanced parsers are
used by the kernel in order to give direct access to the content of each
cell, regardless of its position/size in the underlying
device. Unfortunately, these information are not accessible by users,
unless by fully re-implementing the parser logic in userland.

Let's expose the cells and their content through sysfs to avoid these
situations. Of course the relevant NVMEM sysfs Kconfig option must be
enabled for this support to be available.

Not all nvmem devices expose cells. Indeed, the .bin_attrs attribute
group member will be filled at runtime only when relevant and will
remain empty otherwise. In this case, as the cells attribute group will
be empty, it will not lead to any additional folder/file creation.

Exposed cells are read-only. There is, in practice, everything in the
core to support a write path, but as I don't see any need for that, I
prefer to keep the interface simple (and probably safer). The interface
is documented as being in the "testing" state which means we can later
add a write attribute if though relevant.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Tested-by: Rafał Miłecki <rafal@milecki.pl>
Tested-by: Chen-Yu Tsai <wenst@chromium.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-9-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c      | 135 +++++++++++++++++++++++++++++++++++++-
 drivers/nvmem/internals.h |   1 +
 2 files changed, 135 insertions(+), 1 deletion(-)

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 4c2154ddf8a7f..ba559e81f77fa 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -299,6 +299,43 @@ static umode_t nvmem_bin_attr_is_visible(struct kobject *kobj,
 	return nvmem_bin_attr_get_umode(nvmem);
 }
 
+static struct nvmem_cell *nvmem_create_cell(struct nvmem_cell_entry *entry,
+					    const char *id, int index);
+
+static ssize_t nvmem_cell_attr_read(struct file *filp, struct kobject *kobj,
+				    struct bin_attribute *attr, char *buf,
+				    loff_t pos, size_t count)
+{
+	struct nvmem_cell_entry *entry;
+	struct nvmem_cell *cell = NULL;
+	size_t cell_sz, read_len;
+	void *content;
+
+	entry = attr->private;
+	cell = nvmem_create_cell(entry, entry->name, 0);
+	if (IS_ERR(cell))
+		return PTR_ERR(cell);
+
+	if (!cell)
+		return -EINVAL;
+
+	content = nvmem_cell_read(cell, &cell_sz);
+	if (IS_ERR(content)) {
+		read_len = PTR_ERR(content);
+		goto destroy_cell;
+	}
+
+	read_len = min_t(unsigned int, cell_sz - pos, count);
+	memcpy(buf, content + pos, read_len);
+	kfree(content);
+
+destroy_cell:
+	kfree_const(cell->id);
+	kfree(cell);
+
+	return read_len;
+}
+
 /* default read/write permissions */
 static struct bin_attribute bin_attr_rw_nvmem = {
 	.attr	= {
@@ -320,11 +357,21 @@ static const struct attribute_group nvmem_bin_group = {
 	.is_bin_visible = nvmem_bin_attr_is_visible,
 };
 
+/* Cell attributes will be dynamically allocated */
+static struct attribute_group nvmem_cells_group = {
+	.name		= "cells",
+};
+
 static const struct attribute_group *nvmem_dev_groups[] = {
 	&nvmem_bin_group,
 	NULL,
 };
 
+static const struct attribute_group *nvmem_cells_groups[] = {
+	&nvmem_cells_group,
+	NULL,
+};
+
 static struct bin_attribute bin_attr_nvmem_eeprom_compat = {
 	.attr	= {
 		.name	= "eeprom",
@@ -380,6 +427,68 @@ static void nvmem_sysfs_remove_compat(struct nvmem_device *nvmem,
 		device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom);
 }
 
+static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem)
+{
+	struct bin_attribute **cells_attrs, *attrs;
+	struct nvmem_cell_entry *entry;
+	unsigned int ncells = 0, i = 0;
+	int ret = 0;
+
+	mutex_lock(&nvmem_mutex);
+
+	if (list_empty(&nvmem->cells) || nvmem->sysfs_cells_populated) {
+		nvmem_cells_group.bin_attrs = NULL;
+		goto unlock_mutex;
+	}
+
+	/* Allocate an array of attributes with a sentinel */
+	ncells = list_count_nodes(&nvmem->cells);
+	cells_attrs = devm_kcalloc(&nvmem->dev, ncells + 1,
+				   sizeof(struct bin_attribute *), GFP_KERNEL);
+	if (!cells_attrs) {
+		ret = -ENOMEM;
+		goto unlock_mutex;
+	}
+
+	attrs = devm_kcalloc(&nvmem->dev, ncells, sizeof(struct bin_attribute), GFP_KERNEL);
+	if (!attrs) {
+		ret = -ENOMEM;
+		goto unlock_mutex;
+	}
+
+	/* Initialize each attribute to take the name and size of the cell */
+	list_for_each_entry(entry, &nvmem->cells, node) {
+		sysfs_bin_attr_init(&attrs[i]);
+		attrs[i].attr.name = devm_kasprintf(&nvmem->dev, GFP_KERNEL,
+						    "%s@%x", entry->name,
+						    entry->offset);
+		attrs[i].attr.mode = 0444;
+		attrs[i].size = entry->bytes;
+		attrs[i].read = &nvmem_cell_attr_read;
+		attrs[i].private = entry;
+		if (!attrs[i].attr.name) {
+			ret = -ENOMEM;
+			goto unlock_mutex;
+		}
+
+		cells_attrs[i] = &attrs[i];
+		i++;
+	}
+
+	nvmem_cells_group.bin_attrs = cells_attrs;
+
+	ret = devm_device_add_groups(&nvmem->dev, nvmem_cells_groups);
+	if (ret)
+		goto unlock_mutex;
+
+	nvmem->sysfs_cells_populated = true;
+
+unlock_mutex:
+	mutex_unlock(&nvmem_mutex);
+
+	return ret;
+}
+
 #else /* CONFIG_NVMEM_SYSFS */
 
 static int nvmem_sysfs_setup_compat(struct nvmem_device *nvmem,
@@ -739,11 +848,25 @@ static int nvmem_add_cells_from_fixed_layout(struct nvmem_device *nvmem)
 
 int nvmem_layout_register(struct nvmem_layout *layout)
 {
+	int ret;
+
 	if (!layout->add_cells)
 		return -EINVAL;
 
 	/* Populate the cells */
-	return layout->add_cells(&layout->nvmem->dev, layout->nvmem);
+	ret = layout->add_cells(&layout->nvmem->dev, layout->nvmem);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_NVMEM_SYSFS
+	ret = nvmem_populate_sysfs_cells(layout->nvmem);
+	if (ret) {
+		nvmem_device_remove_all_cells(layout->nvmem);
+		return ret;
+	}
+#endif
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(nvmem_layout_register);
 
@@ -902,10 +1025,20 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	if (rval)
 		goto err_remove_dev;
 
+#ifdef CONFIG_NVMEM_SYSFS
+	rval = nvmem_populate_sysfs_cells(nvmem);
+	if (rval)
+		goto err_destroy_layout;
+#endif
+
 	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem);
 
 	return nvmem;
 
+#ifdef CONFIG_NVMEM_SYSFS
+err_destroy_layout:
+	nvmem_destroy_layout(nvmem);
+#endif
 err_remove_dev:
 	device_del(&nvmem->dev);
 err_remove_cells:
diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
index 4946456c76c71..18fed57270e5e 100644
--- a/drivers/nvmem/internals.h
+++ b/drivers/nvmem/internals.h
@@ -32,6 +32,7 @@ struct nvmem_device {
 	struct gpio_desc	*wp_gpio;
 	struct nvmem_layout	*layout;
 	void *priv;
+	bool			sysfs_cells_populated;
 };
 
 #if IS_ENABLED(CONFIG_OF)
-- 
GitLab


From a729c0f57dc84da3f884d8f6090a8fd2798e32b2 Mon Sep 17 00:00:00 2001
From: Patrick Delaunay <patrick.delaunay@foss.st.com>
Date: Fri, 15 Dec 2023 11:15:35 +0000
Subject: [PATCH 1340/4076] dt-bindings: nvmem: add new stm32mp25 compatible
 for stm32-romem

Add a new compatible for stm32mp25 support.

Signed-off-by: Patrick Delaunay <patrick.delaunay@foss.st.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-10-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
index a69de3e922828..92bfe25f0571e 100644
--- a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
+++ b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
@@ -24,6 +24,7 @@ properties:
       - st,stm32f4-otp
       - st,stm32mp13-bsec
       - st,stm32mp15-bsec
+      - st,stm32mp25-bsec
 
   reg:
     maxItems: 1
-- 
GitLab


From f0ac5b23039610619ca4a4805528553ecb6bc815 Mon Sep 17 00:00:00 2001
From: Patrick Delaunay <patrick.delaunay@foss.st.com>
Date: Fri, 15 Dec 2023 11:15:36 +0000
Subject: [PATCH 1341/4076] nvmem: stm32: add support for STM32MP25 BSEC to
 control OTP data

On STM32MP25, OTP area may be read/written by using BSEC (boot, security
and OTP control). The BSEC internal peripheral is only managed by the
secure world.

The 12 Kbits of OTP (effective) are organized into the following regions:
- lower OTP (OTP0 to OTP127) = 4096 lower OTP bits,
  bitwise (1-bit) programmable
- mid OTP (OTP128 to OTP255) = 4096 middle OTP bits,
  bulk (32-bit) programmable
- upper OTP (OTP256 to OTP383) = 4096 upper OTP bits,
  bulk (32-bit) programmable,
  only accessible when BSEC is in closed state.

As HWKEY and ECIES key are only accessible by ROM code;
only 368 OTP words are managed in this driver (OTP0 to OTP267).

This patch adds the STM32MP25 configuration for reading and writing
the OTP data using the OP-TEE BSEC TA services.

Signed-off-by: Patrick Delaunay <patrick.delaunay@foss.st.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-11-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/stm32-romem.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/nvmem/stm32-romem.c b/drivers/nvmem/stm32-romem.c
index 8a553b1799a85..82879b1c9eb93 100644
--- a/drivers/nvmem/stm32-romem.c
+++ b/drivers/nvmem/stm32-romem.c
@@ -269,6 +269,19 @@ static const struct stm32_romem_cfg stm32mp13_bsec_cfg = {
 	.ta = true,
 };
 
+/*
+ * STM32MP25 BSEC OTP: 3 regions of 32-bits data words
+ *   lower OTP (OTP0 to OTP127), bitwise (1-bit) programmable
+ *   mid OTP (OTP128 to OTP255), bulk (32-bit) programmable
+ *   upper OTP (OTP256 to OTP383), bulk (32-bit) programmable
+ *              but no access to HWKEY and ECIES key: limited at OTP367
+ */
+static const struct stm32_romem_cfg stm32mp25_bsec_cfg = {
+	.size = 368 * 4,
+	.lower = 127,
+	.ta = true,
+};
+
 static const struct of_device_id stm32_romem_of_match[] __maybe_unused = {
 	{ .compatible = "st,stm32f4-otp", }, {
 		.compatible = "st,stm32mp15-bsec",
@@ -276,6 +289,9 @@ static const struct of_device_id stm32_romem_of_match[] __maybe_unused = {
 	}, {
 		.compatible = "st,stm32mp13-bsec",
 		.data = (void *)&stm32mp13_bsec_cfg,
+	}, {
+		.compatible = "st,stm32mp25-bsec",
+		.data = (void *)&stm32mp25_bsec_cfg,
 	},
 	{ /* sentinel */ },
 };
-- 
GitLab


From 1f76ce4fc0e3fcc17468ad5d7ae7fb2a8e0c4b43 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:25:58 +0100
Subject: [PATCH 1342/4076] staging: rtl8192e: Remove unused struct
 iw_range_with_scan_capa

Remove unused struct iw_range_with_scan_capa.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/8b4532b8739ca0baa9fa7c736dab68130510ffe8.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/rtl_wx.c | 22 ----------------------
 1 file changed, 22 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
index 4371ab1239ee2..4c884c5277f94 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
@@ -158,28 +158,6 @@ static int _rtl92e_wx_set_mode(struct net_device *dev,
 	return ret;
 }
 
-struct  iw_range_with_scan_capa {
-	/* Informative stuff (to choose between different interface) */
-	__u32	   throughput;     /* To give an idea... */
-	/* In theory this value should be the maximum benchmarked
-	 * TCP/IP throughput, because with most of these devices the
-	 * bit rate is meaningless (overhead an co) to estimate how
-	 * fast the connection will go and pick the fastest one.
-	 * I suggest people to play with Netperf or any benchmark...
-	 */
-
-	/* NWID (or domain id) */
-	__u32	   min_nwid;	/* Minimal NWID we are able to set */
-	__u32	   max_nwid;	/* Maximal NWID we are able to set */
-
-	/* Old Frequency (backward compat - moved lower ) */
-	__u16	   old_num_channels;
-	__u8	    old_num_frequency;
-
-	/* Scan capabilities */
-	__u8	    scan_capa;
-};
-
 static int _rtl92e_wx_get_range(struct net_device *dev,
 				struct iw_request_info *info,
 				union iwreq_data *wrqu, char *extra)
-- 
GitLab


From c2386096b8317c79d4644d960d32de00dc38915b Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:26:10 +0100
Subject: [PATCH 1343/4076] staging: rtl8192e: Remove variable
 ht_info->reg_bw_40mhz

ht_info->reg_bw_40mhz is set to 1 and unchanged. Therefore all equations
result accordingly and ht_info->reg_bw_40mhz can be removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/4ff7afdc2ada8095c95f053381834cea9f5796bf.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     |  1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 14 +++-----------
 2 files changed, 3 insertions(+), 12 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index c004020099e3c..bbfdfb79c6f21 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -94,7 +94,6 @@ enum ht_aggre_mode {
 struct rt_hi_throughput {
 	u8 enable_ht;
 	u8 current_ht_support;
-	u8 reg_bw_40mhz;
 	u8 cur_bw_40mhz;
 	u8 reg_short_gi_40mhz;
 	u8 cur_short_gi_40mhz;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 99626be899fd8..f81d9ba9c9f53 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -74,12 +74,7 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->reg_short_gi_20mhz = 1;
 	ht_info->reg_short_gi_40mhz = 1;
 
-	ht_info->reg_bw_40mhz = 1;
-
-	if (ht_info->reg_bw_40mhz)
-		ht_info->reg_supp_cck = 1;
-	else
-		ht_info->reg_supp_cck = true;
+	ht_info->reg_supp_cck = 1;
 
 	ht_info->amsdu_max_size = 7935UL;
 	ht_info->amsdu_support = 0;
@@ -275,7 +270,7 @@ void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
 		pCapELE->ChlWidth = 0;
 	else
-		pCapELE->ChlWidth = (pHT->reg_bw_40mhz ? 1 : 0);
+		pCapELE->ChlWidth = 1;
 
 	pCapELE->MimoPwrSave		= pHT->self_mimo_ps;
 	pCapELE->GreenField		= 0;
@@ -286,7 +281,7 @@ void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
 	pCapELE->RxSTBC			= 0;
 	pCapELE->DelayBA		= 0;
 	pCapELE->MaxAMSDUSize = (MAX_RECEIVE_BUFFER_SIZE >= 7935) ? 1 : 0;
-	pCapELE->DssCCk = ((pHT->reg_bw_40mhz) ? (pHT->reg_supp_cck ? 1 : 0) : 0);
+	pCapELE->DssCCk = (pHT->reg_supp_cck ? 1 : 0);
 	pCapELE->PSMP = 0;
 	pCapELE->LSigTxopProtect = 0;
 
@@ -734,9 +729,6 @@ void HTSetConnectBwMode(struct rtllib_device *ieee,
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	if (!ht_info->reg_bw_40mhz)
-		return;
-
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
 		bandwidth = HT_CHANNEL_WIDTH_20;
 
-- 
GitLab


From 923f0052a3057a84b1b1aff971e47fdca13213f0 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:26:18 +0100
Subject: [PATCH 1344/4076] staging: rtl8192e: Remove variable
 ht_info->reg_supp_cck

ht_info->reg_supp_cck is set to 1 and unchanged. Therefore all equations
result accordingly and ht_info->reg_supp_cck can be removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/2c9be9efb1c0608a7fc2658d813b9adbc1185db1.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 8 ++------
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index bbfdfb79c6f21..6556c5df958d7 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -99,7 +99,6 @@ struct rt_hi_throughput {
 	u8 cur_short_gi_40mhz;
 	u8 reg_short_gi_20mhz;
 	u8 cur_short_gi_20mhz;
-	u8 reg_supp_cck;
 	u8 bCurSuppCCK;
 	enum ht_spec_ver ePeerHTSpecVer;
 	struct ht_capab_ele SelfHTCap;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index f81d9ba9c9f53..7acc8b4c11c4a 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -74,8 +74,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->reg_short_gi_20mhz = 1;
 	ht_info->reg_short_gi_40mhz = 1;
 
-	ht_info->reg_supp_cck = 1;
-
 	ht_info->amsdu_max_size = 7935UL;
 	ht_info->amsdu_support = 0;
 
@@ -281,7 +279,7 @@ void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
 	pCapELE->RxSTBC			= 0;
 	pCapELE->DelayBA		= 0;
 	pCapELE->MaxAMSDUSize = (MAX_RECEIVE_BUFFER_SIZE >= 7935) ? 1 : 0;
-	pCapELE->DssCCk = (pHT->reg_supp_cck ? 1 : 0);
+	pCapELE->DssCCk = 1;
 	pCapELE->PSMP = 0;
 	pCapELE->LSigTxopProtect = 0;
 
@@ -480,9 +478,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 				     ((pPeerHTCap->ShortGI40Mhz == 1) ?
 				     true : false) : false);
 
-	ht_info->bCurSuppCCK = ((ht_info->reg_supp_cck) ?
-			       ((pPeerHTCap->DssCCk == 1) ? true :
-			       false) : false);
+	ht_info->bCurSuppCCK = ((pPeerHTCap->DssCCk == 1) ? true : false);
 
 	ht_info->bCurrent_AMSDU_Support = ht_info->amsdu_support;
 
-- 
GitLab


From 97c75386a5f38e3213a2cb1e450b8e51337e4198 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:26:24 +0100
Subject: [PATCH 1345/4076] staging: rtl8192e: Remove variable
 ht_info->reg_short_gi_20mhz

ht_info->reg_short_gi_20mhz is set to 1 and unchanged. Therefore all
equations result accordingly and ht_info->reg_short_gi_20mhz can be
removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/a2778d12a2bb104a980a69f8eb05ba1cabf7b545.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 5 +----
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 6556c5df958d7..8a4bd389004a2 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -97,7 +97,6 @@ struct rt_hi_throughput {
 	u8 cur_bw_40mhz;
 	u8 reg_short_gi_40mhz;
 	u8 cur_short_gi_40mhz;
-	u8 reg_short_gi_20mhz;
 	u8 cur_short_gi_20mhz;
 	u8 bCurSuppCCK;
 	enum ht_spec_ver ePeerHTSpecVer;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 7acc8b4c11c4a..ed9b3db1a3933 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -71,7 +71,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	ht_info->reg_short_gi_20mhz = 1;
 	ht_info->reg_short_gi_40mhz = 1;
 
 	ht_info->amsdu_max_size = 7935UL;
@@ -471,9 +470,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->cur_tx_bw40mhz = ((pPeerHTInfo->RecommemdedTxWidth == 1) ?
 				 true : false);
 
-	ht_info->cur_short_gi_20mhz = ((ht_info->reg_short_gi_20mhz) ?
-				    ((pPeerHTCap->ShortGI20Mhz == 1) ?
-				    true : false) : false);
+	ht_info->cur_short_gi_20mhz = ((pPeerHTCap->ShortGI20Mhz == 1) ? true : false);
 	ht_info->cur_short_gi_40mhz = ((ht_info->reg_short_gi_40mhz) ?
 				     ((pPeerHTCap->ShortGI40Mhz == 1) ?
 				     true : false) : false);
-- 
GitLab


From e5d021b73bf8cbff52ea11cc4c1191ef5f7e5aff Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:26:30 +0100
Subject: [PATCH 1346/4076] staging: rtl8192e: Remove variable
 ht_info->reg_short_gi_40mhz

ht_info->reg_short_gi_40mhz is set to 1 and unchanged. Therefore all
equations result accordingly and ht_info->reg_short_gi_40mhz can be
removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/255039e0cb27582a98a0b86340dfe88f14c08a76.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 6 +-----
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 8a4bd389004a2..0664eb86bada5 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -95,7 +95,6 @@ struct rt_hi_throughput {
 	u8 enable_ht;
 	u8 current_ht_support;
 	u8 cur_bw_40mhz;
-	u8 reg_short_gi_40mhz;
 	u8 cur_short_gi_40mhz;
 	u8 cur_short_gi_20mhz;
 	u8 bCurSuppCCK;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index ed9b3db1a3933..0a5885d6c0a05 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -71,8 +71,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	ht_info->reg_short_gi_40mhz = 1;
-
 	ht_info->amsdu_max_size = 7935UL;
 	ht_info->amsdu_support = 0;
 
@@ -471,9 +469,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 				 true : false);
 
 	ht_info->cur_short_gi_20mhz = ((pPeerHTCap->ShortGI20Mhz == 1) ? true : false);
-	ht_info->cur_short_gi_40mhz = ((ht_info->reg_short_gi_40mhz) ?
-				     ((pPeerHTCap->ShortGI40Mhz == 1) ?
-				     true : false) : false);
+	ht_info->cur_short_gi_40mhz = ((pPeerHTCap->ShortGI40Mhz == 1) ? true : false);
 
 	ht_info->bCurSuppCCK = ((pPeerHTCap->DssCCk == 1) ? true : false);
 
-- 
GitLab


From 7419f917d321546d9587656dbd41337c238dfa8d Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:26:38 +0100
Subject: [PATCH 1347/4076] staging: rtl8192e: Remove variable ForcedAMPDUMode

ForcedAMPDUMode is set to 0 and unchanged. Therefore all equations result
accordingly and ForcedAMPDUMode can be removed. As a result label
FORCED_AGG_SETTING is unused and can be removed as well.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/5bf740a2da78ec3b54249a30cbee70301b37e7eb.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h |  1 -
 drivers/staging/rtl8192e/rtllib_tx.c  | 21 ++-------------------
 2 files changed, 2 insertions(+), 20 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 0664eb86bada5..d249062e7b66a 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -113,7 +113,6 @@ struct rt_hi_throughput {
 	u8 CurrentAMPDUFactor;
 	u8 mpdu_density;
 	u8 current_mpdu_density;
-	enum ht_aggre_mode ForcedAMPDUMode;
 	u8 forced_ampdu_factor;
 	u8 forced_mpdu_density;
 	enum ht_aggre_mode ForcedAMSDUMode;
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index a2ae68cc13f5a..0fa6f674a844b 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -303,13 +303,13 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 			} else if (!ts->disable_add_ba) {
 				TsStartAddBaProcess(ieee, ts);
 			}
-			goto FORCED_AGG_SETTING;
+			return;
 		} else if (!ts->using_ba) {
 			if (SN_LESS(ts->tx_admitted_ba_record.ba_start_seq_ctrl.field.seq_num,
 				    (ts->tx_cur_seq + 1) % 4096))
 				ts->using_ba = true;
 			else
-				goto FORCED_AGG_SETTING;
+				return;
 		}
 		if (ieee->iw_mode == IW_MODE_INFRA) {
 			tcb_desc->ampdu_enable = true;
@@ -317,23 +317,6 @@ static void rtllib_tx_query_agg_cap(struct rtllib_device *ieee,
 			tcb_desc->ampdu_density = ht_info->current_mpdu_density;
 		}
 	}
-FORCED_AGG_SETTING:
-	switch (ht_info->ForcedAMPDUMode) {
-	case HT_AGG_AUTO:
-		break;
-
-	case HT_AGG_FORCE_ENABLE:
-		tcb_desc->ampdu_enable = true;
-		tcb_desc->ampdu_density = ht_info->forced_mpdu_density;
-		tcb_desc->ampdu_factor = ht_info->forced_ampdu_factor;
-		break;
-
-	case HT_AGG_FORCE_DISABLE:
-		tcb_desc->ampdu_enable = false;
-		tcb_desc->ampdu_density = 0;
-		tcb_desc->ampdu_factor = 0;
-		break;
-	}
 }
 
 static void rtllib_query_ShortPreambleMode(struct rtllib_device *ieee,
-- 
GitLab


From b1691deaec49715fbdf73ae7184bc2f3a3944b77 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:26:44 +0100
Subject: [PATCH 1348/4076] staging: rtl8192e: Remove variable ForcedAMSDUMode

ForcedAMSDUMode is set to 1 and then never evaluated.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/ae8ea27e2c3708754b798f09ba43ed50a24b8a55.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index d249062e7b66a..670affe9d57bf 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -115,7 +115,6 @@ struct rt_hi_throughput {
 	u8 current_mpdu_density;
 	u8 forced_ampdu_factor;
 	u8 forced_mpdu_density;
-	enum ht_aggre_mode ForcedAMSDUMode;
 	u8 forced_short_gi;
 	u8 current_op_mode;
 	u8 self_mimo_ps;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 0a5885d6c0a05..bedee290e7f59 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -513,7 +513,6 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 					      pPeerHTCap->MPDUDensity);
 	if (ht_info->iot_action & HT_IOT_ACT_TX_USE_AMSDU_8K) {
 		ht_info->current_ampdu_enable = false;
-		ht_info->ForcedAMSDUMode = HT_AGG_FORCE_ENABLE;
 	}
 	ht_info->cur_rx_reorder_enable = ht_info->reg_rx_reorder_enable;
 
-- 
GitLab


From b0588787b2d60ad6c5a30d2be918db8c85fc4f61 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:26:51 +0100
Subject: [PATCH 1349/4076] staging: rtl8192e: Remove equation with
 pPeerHTCap->DssCCk

Remove equation with pPeerHTCap->DssCCk as it is set to 1 and unchanged.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/16ec7f928d1c51ffe68b9a1a68d09abaaa79924a.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index bedee290e7f59..ca9da96b6f6cf 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -471,7 +471,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->cur_short_gi_20mhz = ((pPeerHTCap->ShortGI20Mhz == 1) ? true : false);
 	ht_info->cur_short_gi_40mhz = ((pPeerHTCap->ShortGI40Mhz == 1) ? true : false);
 
-	ht_info->bCurSuppCCK = ((pPeerHTCap->DssCCk == 1) ? true : false);
+	ht_info->bCurSuppCCK = true;
 
 	ht_info->bCurrent_AMSDU_Support = ht_info->amsdu_support;
 
-- 
GitLab


From a496db4815bf649bcfcd6b31dc327fa1fa76dbba Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:26:58 +0100
Subject: [PATCH 1350/4076] staging: rtl8192e: Remove variable
 ht_info->bCurSuppCCK

ht_info->bCurSuppCCK is set to 1 and unchanged. Therefore all equations
result accordingly and ht_info->bCurSuppCCK can be removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/159a1a84c7bc90042bf1618a067f02ac123dd15d.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ----
 drivers/staging/rtl8192e/rtllib_softmac.c | 5 +----
 3 files changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 670affe9d57bf..416633b884460 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -97,7 +97,6 @@ struct rt_hi_throughput {
 	u8 cur_bw_40mhz;
 	u8 cur_short_gi_40mhz;
 	u8 cur_short_gi_20mhz;
-	u8 bCurSuppCCK;
 	enum ht_spec_ver ePeerHTSpecVer;
 	struct ht_capab_ele SelfHTCap;
 	struct ht_info_ele SelfHTInfo;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index ca9da96b6f6cf..439b43faa2bb0 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -471,8 +471,6 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->cur_short_gi_20mhz = ((pPeerHTCap->ShortGI20Mhz == 1) ? true : false);
 	ht_info->cur_short_gi_40mhz = ((pPeerHTCap->ShortGI40Mhz == 1) ? true : false);
 
-	ht_info->bCurSuppCCK = true;
-
 	ht_info->bCurrent_AMSDU_Support = ht_info->amsdu_support;
 
 	nMaxAMSDUSize = (pPeerHTCap->MaxAMSDUSize == 0) ? 3839 : 7935;
@@ -549,8 +547,6 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	ht_info->cur_short_gi_40mhz = false;
 	ht_info->forced_short_gi = false;
 
-	ht_info->bCurSuppCCK = true;
-
 	ht_info->bCurrent_AMSDU_Support = false;
 	ht_info->nCurrent_AMSDU_MaxSize = ht_info->amsdu_max_size;
 	ht_info->current_mpdu_density = ht_info->mpdu_density;
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 5c89744b2bbe3..416f89ec576cd 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -173,10 +173,7 @@ static u8 MgntQuery_MgntFrameTxRate(struct rtllib_device *ieee)
 		rate = ieee->basic_rate & 0x7f;
 
 	if (rate == 0) {
-		if (ieee->mode == WIRELESS_MODE_N_24G && !ht_info->bCurSuppCCK)
-			rate = 0x0c;
-		else
-			rate = 0x02;
+		rate = 0x02;
 	}
 
 	return rate;
-- 
GitLab


From 374d8bbd1445a827d029500e43d07c4492ec745b Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Sun, 10 Dec 2023 16:27:03 +0100
Subject: [PATCH 1351/4076] staging: rtl8192e: Remove struct ht_info_ele
 SelfHTInfo

Remove struct ht_info_ele SelfHTInfo as it is unused.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/e8692d40b3cba3de1b4ceb8e72186e8d40afec73.1702212003.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 --
 2 files changed, 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 416633b884460..0f27c820ffc54 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -99,7 +99,6 @@ struct rt_hi_throughput {
 	u8 cur_short_gi_20mhz;
 	enum ht_spec_ver ePeerHTSpecVer;
 	struct ht_capab_ele SelfHTCap;
-	struct ht_info_ele SelfHTInfo;
 	u8 PeerHTCapBuf[32];
 	u8 PeerHTInfoBuf[32];
 	u8 amsdu_support;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 439b43faa2bb0..0474594a4b96a 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -554,8 +554,6 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 
 	memset((void *)(&ht_info->SelfHTCap), 0,
 	       sizeof(ht_info->SelfHTCap));
-	memset((void *)(&ht_info->SelfHTInfo), 0,
-	       sizeof(ht_info->SelfHTInfo));
 	memset((void *)(&ht_info->PeerHTCapBuf), 0,
 	       sizeof(ht_info->PeerHTCapBuf));
 	memset((void *)(&ht_info->PeerHTInfoBuf), 0,
-- 
GitLab


From 6bcb6ec33b1b680f14d91d11bd2a36bb6781465b Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sun, 10 Dec 2023 19:13:31 -0500
Subject: [PATCH 1352/4076] staging: rtl8192e: rename variable
 HTIOTActDetermineRaFunc

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTIOTActDetermineRaFunc -> ht_iot_act_determine_ra_function

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231211001335.26169-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 0474594a4b96a..2d5976c1bade5 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -217,7 +217,7 @@ static u8 ht_iot_act_is_ccd_fsync(struct rtllib_device *ieee)
 	return retValue;
 }
 
-static void HTIOTActDetermineRaFunc(struct rtllib_device *ieee, bool bPeerRx2ss)
+static void ht_iot_act_determine_ra_func(struct rtllib_device *ieee, bool bPeerRx2ss)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
@@ -517,7 +517,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	if (pPeerHTCap->MCS[0] == 0)
 		pPeerHTCap->MCS[0] = 0xff;
 
-	HTIOTActDetermineRaFunc(ieee, ((pPeerHTCap->MCS[1]) != 0));
+	ht_iot_act_determine_ra_func(ieee, ((pPeerHTCap->MCS[1]) != 0));
 
 	HTFilterMCSRate(ieee, pPeerHTCap->MCS, ieee->dot11ht_oper_rate_set);
 
-- 
GitLab


From 9ba1a16005dbe7d56dfe9920b6c6c8fc8ab6ef7a Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sun, 10 Dec 2023 19:13:32 -0500
Subject: [PATCH 1353/4076] staging: rtl8192e: rename variable
 HTResetIOTSetting

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTResetIOTSetting -> ht_reset_iot_setting

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231211001335.26169-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 2d5976c1bade5..a4405e8e32c60 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -230,7 +230,7 @@ static void ht_iot_act_determine_ra_func(struct rtllib_device *ieee, bool bPeerR
 		ht_info->iot_ra_func |= HT_IOT_RAFUNC_TX_AMSDU;
 }
 
-void HTResetIOTSetting(struct rt_hi_throughput *ht_info)
+void ht_reset_iot_setting(struct rt_hi_throughput *ht_info)
 {
 	ht_info->iot_action = 0;
 	ht_info->iot_peer = HT_IOT_PEER_UNKNOWN;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 51dcea57a3292..e8c795faf4f9a 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1772,7 +1772,7 @@ u8 HTGetHighestMCSRate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 extern u8 MCS_FILTER_ALL[];
 extern u16 MCS_DATA_RATE[2][2][77];
 u8 HTCCheck(struct rtllib_device *ieee, u8 *pFrame);
-void HTResetIOTSetting(struct rt_hi_throughput *ht_info);
+void ht_reset_iot_setting(struct rt_hi_throughput *ht_info);
 bool is_ht_half_nmode_aps(struct rtllib_device *ieee);
 u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate);
 int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 416f89ec576cd..336a5776afdbf 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1212,7 +1212,7 @@ inline void rtllib_softmac_new_net(struct rtllib_device *ieee,
 			   !(ieee->softmac_features & IEEE_SOFTMAC_SCAN))
 				rtllib_stop_scan_syncro(ieee);
 
-			HTResetIOTSetting(ieee->ht_info);
+			ht_reset_iot_setting(ieee->ht_info);
 			ieee->wmm_acm = 0;
 			if (ieee->iw_mode == IW_MODE_INFRA) {
 				/* Join the network for the first time */
-- 
GitLab


From 9ee07ff4aefb9c5b7d447e3e454cf5700866303d Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sun, 10 Dec 2023 19:13:33 -0500
Subject: [PATCH 1354/4076] staging: rtl8192e: rename variable
 HTConstructCapabilityElement

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTConstructCapabilityElement -> ht_construct_capability_element

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231211001335.26169-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index a4405e8e32c60..4d6189be6e1bf 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -237,7 +237,7 @@ void ht_reset_iot_setting(struct rt_hi_throughput *ht_info)
 	ht_info->iot_ra_func = 0;
 }
 
-void HTConstructCapabilityElement(struct rtllib_device *ieee, u8 *posHTCap,
+void ht_construct_capability_element(struct rtllib_device *ieee, u8 *posHTCap,
 				  u8 *len, u8 IsEncrypt, bool bAssoc)
 {
 	struct rt_hi_throughput *pHT = ieee->ht_info;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index e8c795faf4f9a..ff3ba9bca0237 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1755,7 +1755,7 @@ void HTSetConnectBwMode(struct rtllib_device *ieee,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset);
 void ht_update_default_setting(struct rtllib_device *ieee);
-void HTConstructCapabilityElement(struct rtllib_device *ieee,
+void ht_construct_capability_element(struct rtllib_device *ieee,
 				  u8 *posHTCap, u8 *len,
 				  u8 isEncrypt, bool bAssoc);
 void HTConstructRT2RTAggElement(struct rtllib_device *ieee,
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 336a5776afdbf..fe118548d2a34 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -730,7 +730,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
 		ht_cap_buf = (u8 *)&(ieee->ht_info->SelfHTCap);
 		ht_cap_len = sizeof(ieee->ht_info->SelfHTCap);
-		HTConstructCapabilityElement(ieee, ht_cap_buf, &ht_cap_len,
+		ht_construct_capability_element(ieee, ht_cap_buf, &ht_cap_len,
 					     encrypt, true);
 		if (ieee->ht_info->current_rt2rt_aggregation) {
 			realtek_ie_buf = ieee->ht_info->sz_rt2rt_agg_buf;
-- 
GitLab


From 83280534e7c5775e5271bd7cf12c5b2999011a17 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sun, 10 Dec 2023 19:13:34 -0500
Subject: [PATCH 1355/4076] staging: rtl8192e: rename variable
 HTConstructRT2RTAggElement

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTConstructRT2RTAggElement -> ht_construct_rt2rt_agg_element

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231211001335.26169-5-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 4d6189be6e1bf..709382ab7876f 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -318,7 +318,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *posHTCap,
 	}
 }
 
-void HTConstructRT2RTAggElement(struct rtllib_device *ieee, u8 *posRT2RTAgg,
+void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee, u8 *posRT2RTAgg,
 				u8 *len)
 {
 	if (!posRT2RTAgg) {
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index ff3ba9bca0237..0d6144548c345 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1758,7 +1758,7 @@ void ht_update_default_setting(struct rtllib_device *ieee);
 void ht_construct_capability_element(struct rtllib_device *ieee,
 				  u8 *posHTCap, u8 *len,
 				  u8 isEncrypt, bool bAssoc);
-void HTConstructRT2RTAggElement(struct rtllib_device *ieee,
+void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee,
 				u8 *posRT2RTAgg, u8 *len);
 void HTOnAssocRsp(struct rtllib_device *ieee);
 void HTInitializeHTInfo(struct rtllib_device *ieee);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index fe118548d2a34..ee527ba5d1a86 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -736,7 +736,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 			realtek_ie_buf = ieee->ht_info->sz_rt2rt_agg_buf;
 			realtek_ie_len =
 				 sizeof(ieee->ht_info->sz_rt2rt_agg_buf);
-			HTConstructRT2RTAggElement(ieee, realtek_ie_buf,
+			ht_construct_rt2rt_agg_element(ieee, realtek_ie_buf,
 						   &realtek_ie_len);
 		}
 	}
-- 
GitLab


From 07c9ef14073e96c3ef749b3830f8f0973774e860 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sun, 10 Dec 2023 19:13:35 -0500
Subject: [PATCH 1356/4076] staging: rtl8192e: rename variable HT_PickMCSRate

Coding style issue, checkpatch Avoid CamelCase,
rename it. HT_PickMCSRate -> ht_pick_mcs_rate

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231211001335.26169-6-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 709382ab7876f..0197782e0ab62 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -340,7 +340,7 @@ void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee, u8 *posRT2RTAgg,
 	*len = 6 + 2;
 }
 
-static u8 HT_PickMCSRate(struct rtllib_device *ieee, u8 *pOperateMCS)
+static u8 ht_pick_mcs_rate(struct rtllib_device *ieee, u8 *pOperateMCS)
 {
 	u8 i;
 
@@ -416,7 +416,7 @@ static u8 HTFilterMCSRate(struct rtllib_device *ieee, u8 *pSupportMCS,
 		pOperateMCS[i] = ieee->reg_dot11tx_ht_oper_rate_set[i] &
 				 pSupportMCS[i];
 
-	HT_PickMCSRate(ieee, pOperateMCS);
+	ht_pick_mcs_rate(ieee, pOperateMCS);
 
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
 		pOperateMCS[1] = 0;
-- 
GitLab


From e90337ccf4e7ac63ecaa95833df206f177343bdc Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 10 Dec 2023 11:37:02 -0800
Subject: [PATCH 1357/4076] Staging: rtl8192e: Remove variable bFirstSeg

Remove variable bFirstSeg as it is defined but never used.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231210193705.2131807-2-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 0d6144548c345..2e55de8e28296 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -103,7 +103,6 @@ struct cb_desc {
 	/* Tx Desc Related flags (8-9) */
 	u8 bLastIniPkt:1;
 	u8 bCmdOrInit:1;
-	u8 bFirstSeg:1;
 	u8 bLastSeg:1;
 	u8 bEncrypt:1;
 	u8 tx_dis_rate_fallback:1;
-- 
GitLab


From f9f0bcaa91c802c0cfb241d082e6bec306166475 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 10 Dec 2023 11:37:03 -0800
Subject: [PATCH 1358/4076] Staging: rtl8192e: Remove variable bLastSeg

Remove variable bLastSeg as it is defined but never used.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231210193705.2131807-3-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 2e55de8e28296..0dbb2c4f12848 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -103,7 +103,6 @@ struct cb_desc {
 	/* Tx Desc Related flags (8-9) */
 	u8 bLastIniPkt:1;
 	u8 bCmdOrInit:1;
-	u8 bLastSeg:1;
 	u8 bEncrypt:1;
 	u8 tx_dis_rate_fallback:1;
 	u8 tx_use_drv_assinged_rate:1;
-- 
GitLab


From 0c5e85dd078a2e57ff93a6607071f049ca919b58 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 10 Dec 2023 11:37:04 -0800
Subject: [PATCH 1359/4076] Staging: rtl8192e: Remove variable bEncrypt

Remove variable bEncrypt as it is defined but never used.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231210193705.2131807-4-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 0dbb2c4f12848..15bce05c8f152 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -103,7 +103,6 @@ struct cb_desc {
 	/* Tx Desc Related flags (8-9) */
 	u8 bLastIniPkt:1;
 	u8 bCmdOrInit:1;
-	u8 bEncrypt:1;
 	u8 tx_dis_rate_fallback:1;
 	u8 tx_use_drv_assinged_rate:1;
 	u8 bHwSec:1;
-- 
GitLab


From 9b1763331ddfbd9767d0f86edfc8eace74a3aad7 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 10 Dec 2023 11:37:05 -0800
Subject: [PATCH 1360/4076] Staging: rtl8192e: Remove variable macId

Remove variable macId as it is defined but never used.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231210193705.2131807-5-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 15bce05c8f152..cc9070f390045 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -136,7 +136,6 @@ struct cb_desc {
 	u8 bAMSDU:1;
 	u8 bFromAggrQ:1;
 	u8 reserved6:6;
-	u8 macId;
 	u8 priority;
 
 	/* Tx firmware related element(20-27) */
-- 
GitLab


From 078330abda79bf56c35dd570a989d30008618d83 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 12 Dec 2023 11:56:33 -0500
Subject: [PATCH 1361/4076] staging: rtl8192e: rename variable posHTCap

Coding style issue, checkpatch Avoid CamelCase,
rename it. posHTCap -> pos_ht_cap

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231212165637.17618-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 0197782e0ab62..7efc67af25de4 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -237,27 +237,27 @@ void ht_reset_iot_setting(struct rt_hi_throughput *ht_info)
 	ht_info->iot_ra_func = 0;
 }
 
-void ht_construct_capability_element(struct rtllib_device *ieee, u8 *posHTCap,
+void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 				  u8 *len, u8 IsEncrypt, bool bAssoc)
 {
 	struct rt_hi_throughput *pHT = ieee->ht_info;
 	struct ht_capab_ele *pCapELE = NULL;
 
-	if (!posHTCap || !pHT) {
+	if (!pos_ht_cap || !pHT) {
 		netdev_warn(ieee->dev,
 			    "%s(): posHTCap and ht_info are null\n", __func__);
 		return;
 	}
-	memset(posHTCap, 0, *len);
+	memset(pos_ht_cap, 0, *len);
 
 	if ((bAssoc) && (pHT->ePeerHTSpecVer == HT_SPEC_VER_EWC)) {
 		static const u8	EWC11NHTCap[] = { 0x00, 0x90, 0x4c, 0x33 };
 
-		memcpy(posHTCap, EWC11NHTCap, sizeof(EWC11NHTCap));
-		pCapELE = (struct ht_capab_ele *)&posHTCap[4];
+		memcpy(pos_ht_cap, EWC11NHTCap, sizeof(EWC11NHTCap));
+		pCapELE = (struct ht_capab_ele *)&pos_ht_cap[4];
 		*len = 30 + 2;
 	} else {
-		pCapELE = (struct ht_capab_ele *)posHTCap;
+		pCapELE = (struct ht_capab_ele *)pos_ht_cap;
 		*len = 26 + 2;
 	}
 
-- 
GitLab


From 1a469abcb76e4bcb487f641daea23650c584f1a4 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 12 Dec 2023 11:56:34 -0500
Subject: [PATCH 1362/4076] staging: rtl8192e: rename variable IsEncrypt

Coding style issue, checkpatch Avoid CamelCase,
rename it. IsEncrypt -> is_encrypt

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231212165637.17618-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 7efc67af25de4..eef1a93d51a48 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -238,7 +238,7 @@ void ht_reset_iot_setting(struct rt_hi_throughput *ht_info)
 }
 
 void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
-				  u8 *len, u8 IsEncrypt, bool bAssoc)
+				  u8 *len, u8 is_encrypt, bool bAssoc)
 {
 	struct rt_hi_throughput *pHT = ieee->ht_info;
 	struct ht_capab_ele *pCapELE = NULL;
@@ -284,7 +284,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 		   "TX HT cap/info ele BW=%d MaxAMSDUSize:%d DssCCk:%d\n",
 		   pCapELE->ChlWidth, pCapELE->MaxAMSDUSize, pCapELE->DssCCk);
 
-	if (IsEncrypt) {
+	if (is_encrypt) {
 		pCapELE->MPDUDensity	= 7;
 		pCapELE->MaxRxAMPDUFactor	= 2;
 	} else {
-- 
GitLab


From 145524f81550730be117c3ccfa7b2edd902ee28a Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Tue, 12 Dec 2023 11:56:35 -0500
Subject: [PATCH 1363/4076] staging: rtl8192e: rename variable bAssoc

Coding style issue, checkpatch Avoid CamelCase,
rename it. bAssoc -> assoc

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231212165637.17618-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index eef1a93d51a48..13c14de95dea2 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -238,7 +238,7 @@ void ht_reset_iot_setting(struct rt_hi_throughput *ht_info)
 }
 
 void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
-				  u8 *len, u8 is_encrypt, bool bAssoc)
+				  u8 *len, u8 is_encrypt, bool assoc)
 {
 	struct rt_hi_throughput *pHT = ieee->ht_info;
 	struct ht_capab_ele *pCapELE = NULL;
@@ -250,7 +250,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 	}
 	memset(pos_ht_cap, 0, *len);
 
-	if ((bAssoc) && (pHT->ePeerHTSpecVer == HT_SPEC_VER_EWC)) {
+	if ((assoc) && (pHT->ePeerHTSpecVer == HT_SPEC_VER_EWC)) {
 		static const u8	EWC11NHTCap[] = { 0x00, 0x90, 0x4c, 0x33 };
 
 		memcpy(pos_ht_cap, EWC11NHTCap, sizeof(EWC11NHTCap));
@@ -298,7 +298,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 
 	pCapELE->ASCap = 0;
 
-	if (bAssoc) {
+	if (assoc) {
 		if (pHT->iot_action & HT_IOT_ACT_DISABLE_MCS15)
 			pCapELE->MCS[1] &= 0x7f;
 
-- 
GitLab


From 76cf79dac048d4a1ce4200c41b755a77b567acf2 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:51:32 +0100
Subject: [PATCH 1364/4076] staging: rtl8192e: Remove variable
 bCurrent_AMSDU_Support

bCurrent_AMSDU_Support and nCurrent_AMSDU_MaxSize are set but never
evaluated.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/d2711450dbc62974162abd4db070e34c9828997d.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 --
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 9 ---------
 2 files changed, 11 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 0f27c820ffc54..bf87106dd784a 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -103,8 +103,6 @@ struct rt_hi_throughput {
 	u8 PeerHTInfoBuf[32];
 	u8 amsdu_support;
 	u16 amsdu_max_size;
-	u8 bCurrent_AMSDU_Support;
-	u16 nCurrent_AMSDU_MaxSize;
 	u8 ampdu_enable;
 	u8 current_ampdu_enable;
 	u8 ampdu_factor;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 13c14de95dea2..70866283efb97 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -471,15 +471,8 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->cur_short_gi_20mhz = ((pPeerHTCap->ShortGI20Mhz == 1) ? true : false);
 	ht_info->cur_short_gi_40mhz = ((pPeerHTCap->ShortGI40Mhz == 1) ? true : false);
 
-	ht_info->bCurrent_AMSDU_Support = ht_info->amsdu_support;
-
 	nMaxAMSDUSize = (pPeerHTCap->MaxAMSDUSize == 0) ? 3839 : 7935;
 
-	if (ht_info->amsdu_max_size > nMaxAMSDUSize)
-		ht_info->nCurrent_AMSDU_MaxSize = nMaxAMSDUSize;
-	else
-		ht_info->nCurrent_AMSDU_MaxSize = ht_info->amsdu_max_size;
-
 	ht_info->current_ampdu_enable = ht_info->ampdu_enable;
 	if (ieee->rtllib_ap_sec_type &&
 	    (ieee->rtllib_ap_sec_type(ieee) & (SEC_ALG_WEP | SEC_ALG_TKIP))) {
@@ -547,8 +540,6 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	ht_info->cur_short_gi_40mhz = false;
 	ht_info->forced_short_gi = false;
 
-	ht_info->bCurrent_AMSDU_Support = false;
-	ht_info->nCurrent_AMSDU_MaxSize = ht_info->amsdu_max_size;
 	ht_info->current_mpdu_density = ht_info->mpdu_density;
 	ht_info->CurrentAMPDUFactor = ht_info->ampdu_factor;
 
-- 
GitLab


From ce839694c5ebce6dba6ac0f40267fa203b83b2c2 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:51:45 +0100
Subject: [PATCH 1365/4076] staging: rtl8192e: Remove unused variable
 nMaxAMSDUSize

Remove unused variables nMaxAMSDUSize and amsdu_max_size.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/4df74fda70535ddbdfc90ba7c98e9d4a773f944d.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ----
 2 files changed, 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index bf87106dd784a..ff0eb0d01022e 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -102,7 +102,6 @@ struct rt_hi_throughput {
 	u8 PeerHTCapBuf[32];
 	u8 PeerHTInfoBuf[32];
 	u8 amsdu_support;
-	u16 amsdu_max_size;
 	u8 ampdu_enable;
 	u8 current_ampdu_enable;
 	u8 ampdu_factor;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 70866283efb97..ff606ece192db 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -71,7 +71,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	ht_info->amsdu_max_size = 7935UL;
 	ht_info->amsdu_support = 0;
 
 	ht_info->ampdu_enable = 1;
@@ -436,7 +435,6 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 	struct ht_capab_ele *pPeerHTCap = NULL;
 	struct ht_info_ele *pPeerHTInfo = NULL;
-	u16 nMaxAMSDUSize = 0;
 	u8 *pMcsFilter = NULL;
 
 	static const u8 EWC11NHTCap[] = { 0x00, 0x90, 0x4c, 0x33 };
@@ -471,8 +469,6 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	ht_info->cur_short_gi_20mhz = ((pPeerHTCap->ShortGI20Mhz == 1) ? true : false);
 	ht_info->cur_short_gi_40mhz = ((pPeerHTCap->ShortGI40Mhz == 1) ? true : false);
 
-	nMaxAMSDUSize = (pPeerHTCap->MaxAMSDUSize == 0) ? 3839 : 7935;
-
 	ht_info->current_ampdu_enable = ht_info->ampdu_enable;
 	if (ieee->rtllib_ap_sec_type &&
 	    (ieee->rtllib_ap_sec_type(ieee) & (SEC_ALG_WEP | SEC_ALG_TKIP))) {
-- 
GitLab


From bd027a93da95e04e72cb13665503f0a2870b774b Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:51:54 +0100
Subject: [PATCH 1366/4076] staging: rtl8192e: Remove constant variable
 self_mimo_ps

Remove constant variable self_mimo_ps and replace it at the place of
usage with the value.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/9e1bec657ddb22eec54e441a4341ddbe4ed7568e.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 5 +----
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index ff0eb0d01022e..eb2cfeab97d68 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -112,7 +112,6 @@ struct rt_hi_throughput {
 	u8 forced_mpdu_density;
 	u8 forced_short_gi;
 	u8 current_op_mode;
-	u8 self_mimo_ps;
 	u8 peer_mimo_ps;
 	enum ht_extchnl_offset CurSTAExtChnlOffset;
 	u8 cur_tx_bw40mhz;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index ff606ece192db..8c2c4051bf422 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -77,9 +77,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 	ht_info->ampdu_factor = 2;
 	ht_info->mpdu_density = 0;
 
-	ht_info->self_mimo_ps = 3;
-	if (ht_info->self_mimo_ps == 2)
-		ht_info->self_mimo_ps = 3;
 	ieee->tx_dis_rate_fallback = 0;
 	ieee->tx_use_drv_assinged_rate = 0;
 
@@ -266,7 +263,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 	else
 		pCapELE->ChlWidth = 1;
 
-	pCapELE->MimoPwrSave		= pHT->self_mimo_ps;
+	pCapELE->MimoPwrSave		= 3;
 	pCapELE->GreenField		= 0;
 	pCapELE->ShortGI20Mhz		= 1;
 	pCapELE->ShortGI40Mhz		= 1;
-- 
GitLab


From e7eeb02bf8edd17f0d8851404a3917d8c10daf7b Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:52:04 +0100
Subject: [PATCH 1367/4076] staging: rtl8192e: Remove constant variable
 peer_mimo_ps

MimoPwrSave is set to 3 and not changed. peer_mimo_ps is set to
MimoPwrSave and not changed. All evaluations of peer_mimo_ps with 0 will
have a constant result and can be removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/7b2ccccde769133db9365c693fdd0c42e9dc75f9.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 5 +----
 drivers/staging/rtl8192e/rtl819x_HT.h          | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c      | 6 +-----
 3 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index e6d51abd0d018..763ecaad66528 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -1753,10 +1753,7 @@ void rtl92e_update_ratr_table(struct net_device *dev)
 		ratr_value &= 0x00000FF7;
 		break;
 	case WIRELESS_MODE_N_24G:
-		if (ieee->ht_info->peer_mimo_ps == 0)
-			ratr_value &= 0x0007F007;
-		else
-			ratr_value &= 0x000FF007;
+		ratr_value &= 0x000FF007;
 		break;
 	default:
 		break;
diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index eb2cfeab97d68..43472b2250c2b 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -112,7 +112,6 @@ struct rt_hi_throughput {
 	u8 forced_mpdu_density;
 	u8 forced_short_gi;
 	u8 current_op_mode;
-	u8 peer_mimo_ps;
 	enum ht_extchnl_offset CurSTAExtChnlOffset;
 	u8 cur_tx_bw40mhz;
 	u8 sw_bw_in_progress;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 8c2c4051bf422..1cbd6493f089c 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -507,11 +507,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 
 	HTFilterMCSRate(ieee, pPeerHTCap->MCS, ieee->dot11ht_oper_rate_set);
 
-	ht_info->peer_mimo_ps = pPeerHTCap->MimoPwrSave;
-	if (ht_info->peer_mimo_ps == MIMO_PS_STATIC)
-		pMcsFilter = MCS_FILTER_1SS;
-	else
-		pMcsFilter = MCS_FILTER_ALL;
+	pMcsFilter = MCS_FILTER_ALL;
 	ieee->HTHighestOperaRate = HTGetHighestMCSRate(ieee,
 						       ieee->dot11ht_oper_rate_set,
 						       pMcsFilter);
-- 
GitLab


From 57125eee5f032cbdf6ef3027c829200ac3a39ad5 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:52:12 +0100
Subject: [PATCH 1368/4076] staging: rtl8192e: Remove constant variable
 forced_short_gi

ht_info->forced_short_gi is set to 0 and unchanged. Therefore all equations
result accordingly and ht_info->forced_short_gi can be removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/fc5711032c658af6ae6c5a7a98c52871c29f8c33.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 1 -
 drivers/staging/rtl8192e/rtllib_tx.c      | 5 -----
 3 files changed, 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 43472b2250c2b..e6cd906dc0aca 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -110,7 +110,6 @@ struct rt_hi_throughput {
 	u8 current_mpdu_density;
 	u8 forced_ampdu_factor;
 	u8 forced_mpdu_density;
-	u8 forced_short_gi;
 	u8 current_op_mode;
 	enum ht_extchnl_offset CurSTAExtChnlOffset;
 	u8 cur_tx_bw40mhz;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 1cbd6493f089c..3482ee008ac16 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -527,7 +527,6 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 
 	ht_info->cur_short_gi_20mhz = false;
 	ht_info->cur_short_gi_40mhz = false;
-	ht_info->forced_short_gi = false;
 
 	ht_info->current_mpdu_density = ht_info->mpdu_density;
 	ht_info->CurrentAMPDUFactor = ht_info->ampdu_factor;
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 0fa6f674a844b..f7098a2ba8b0b 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -340,11 +340,6 @@ static void rtllib_query_HTCapShortGI(struct rtllib_device *ieee,
 	if (!ht_info->current_ht_support || !ht_info->enable_ht)
 		return;
 
-	if (ht_info->forced_short_gi) {
-		tcb_desc->bUseShortGI = true;
-		return;
-	}
-
 	if (ht_info->cur_bw_40mhz && ht_info->cur_short_gi_40mhz)
 		tcb_desc->bUseShortGI = true;
 	else if (!ht_info->cur_bw_40mhz && ht_info->cur_short_gi_20mhz)
-- 
GitLab


From a78952c055b9b3c3423c1dfdff7be0be158f0621 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:52:21 +0100
Subject: [PATCH 1369/4076] staging: rtl8192e: Remove unused variable
 ht_info->amsdu_support

Remove unused variable ht_info->amsdu_support.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/b3ea8ddd16a753d9ee1ee8b99e31e990ce89133b.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 --
 2 files changed, 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index e6cd906dc0aca..c4af9968cd679 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -101,7 +101,6 @@ struct rt_hi_throughput {
 	struct ht_capab_ele SelfHTCap;
 	u8 PeerHTCapBuf[32];
 	u8 PeerHTInfoBuf[32];
-	u8 amsdu_support;
 	u8 ampdu_enable;
 	u8 current_ampdu_enable;
 	u8 ampdu_factor;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 3482ee008ac16..b1770411c8c5a 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -71,8 +71,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
-	ht_info->amsdu_support = 0;
-
 	ht_info->ampdu_enable = 1;
 	ht_info->ampdu_factor = 2;
 	ht_info->mpdu_density = 0;
-- 
GitLab


From 584c18e21dfa056f554d89819a88b3de8c6109d3 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:52:29 +0100
Subject: [PATCH 1370/4076] staging: rtl8192e: Remove variable
 ht_info->mpdu_density

ht_info->mpdu_density is set to 0 and unchanged. Therefore all equations
result accordingly and ht_info->forced_short_gi can be removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/ef90d31e0e8281235ae4d138ce2de26e35c1bbd1.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 6 ++----
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index c4af9968cd679..1da56f1c04eb0 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -105,7 +105,6 @@ struct rt_hi_throughput {
 	u8 current_ampdu_enable;
 	u8 ampdu_factor;
 	u8 CurrentAMPDUFactor;
-	u8 mpdu_density;
 	u8 current_mpdu_density;
 	u8 forced_ampdu_factor;
 	u8 forced_mpdu_density;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index b1770411c8c5a..de5e3c99e03ad 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -73,7 +73,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 
 	ht_info->ampdu_enable = 1;
 	ht_info->ampdu_factor = 2;
-	ht_info->mpdu_density = 0;
 
 	ieee->tx_dis_rate_fallback = 0;
 	ieee->tx_use_drv_assinged_rate = 0;
@@ -491,8 +490,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 							    HT_AGG_SIZE_32K);
 		}
 	}
-	ht_info->current_mpdu_density = max_t(u8, ht_info->mpdu_density,
-					      pPeerHTCap->MPDUDensity);
+	ht_info->current_mpdu_density = pPeerHTCap->MPDUDensity;
 	if (ht_info->iot_action & HT_IOT_ACT_TX_USE_AMSDU_8K) {
 		ht_info->current_ampdu_enable = false;
 	}
@@ -526,7 +524,7 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 	ht_info->cur_short_gi_20mhz = false;
 	ht_info->cur_short_gi_40mhz = false;
 
-	ht_info->current_mpdu_density = ht_info->mpdu_density;
+	ht_info->current_mpdu_density = 0;
 	ht_info->CurrentAMPDUFactor = ht_info->ampdu_factor;
 
 	memset((void *)(&ht_info->SelfHTCap), 0,
-- 
GitLab


From f77cf88b9e3f8a04c69ea685b9959022721f587d Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:52:38 +0100
Subject: [PATCH 1371/4076] staging: rtl8192e: Remove variable
 ht_info->RT2RT_HT_Mode

Remove variable ht_info->RT2RT_HT_Mode as it is always set but never
evaluated.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/b6253e56cdb346045a234d1f545d7ef92cdd220d.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 -
 drivers/staging/rtl8192e/rtl819x_HT.h        | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c    | 4 ----
 3 files changed, 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 72e89ccfb1840..bef0422331176 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -287,7 +287,6 @@ static void _rtl92e_update_beacon(void *data)
 	if (ieee->ht_info->current_ht_support)
 		HT_update_self_and_peer_setting(ieee, net);
 	ieee->ht_info->current_rt2rt_long_slot_time = net->bssht.bd_rt2rt_long_slot_time;
-	ieee->ht_info->RT2RT_HT_Mode = net->bssht.rt2rt_ht_mode;
 	_rtl92e_update_cap(dev, net->capability);
 }
 
diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 1da56f1c04eb0..315905fa4b2c4 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -113,7 +113,6 @@ struct rt_hi_throughput {
 	u8 cur_tx_bw40mhz;
 	u8 sw_bw_in_progress;
 	u8 reg_rt2rt_aggregation;
-	u8 RT2RT_HT_Mode;
 	u8 current_rt2rt_aggregation;
 	u8 current_rt2rt_long_slot_time;
 	u8 sz_rt2rt_agg_buf[10];
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index de5e3c99e03ad..23ffd0c0dce53 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -540,7 +540,6 @@ void HTInitializeHTInfo(struct rtllib_device *ieee)
 
 	ht_info->current_rt2rt_aggregation = false;
 	ht_info->current_rt2rt_long_slot_time = false;
-	ht_info->RT2RT_HT_Mode = (enum rt_ht_capability)0;
 
 	ht_info->iot_peer = 0;
 	ht_info->iot_action = 0;
@@ -601,11 +600,9 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 				 pNetwork->bssht.bd_rt2rt_aggregation;
 			ht_info->current_rt2rt_long_slot_time =
 				 pNetwork->bssht.bd_rt2rt_long_slot_time;
-			ht_info->RT2RT_HT_Mode = pNetwork->bssht.rt2rt_ht_mode;
 		} else {
 			ht_info->current_rt2rt_aggregation = false;
 			ht_info->current_rt2rt_long_slot_time = false;
-			ht_info->RT2RT_HT_Mode = (enum rt_ht_capability)0;
 		}
 
 		ht_iot_peer_determine(ieee);
@@ -621,7 +618,6 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 		ht_info->current_ht_support = false;
 		ht_info->current_rt2rt_aggregation = false;
 		ht_info->current_rt2rt_long_slot_time = false;
-		ht_info->RT2RT_HT_Mode = (enum rt_ht_capability)0;
 
 		ht_info->iot_action = 0;
 		ht_info->iot_ra_func = 0;
-- 
GitLab


From 286f01ea0fcf244d72a8bde11d87eaaa0b0ffd80 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:52:46 +0100
Subject: [PATCH 1372/4076] staging: rtl8192e: Remove constant variable
 reg_rt2rt_aggregation

ht_info->reg_rt2rt_aggregation is set to 1 and unchanged. Therefore all
equations result accordingly and ht_info->reg_rt2rt_aggregation can be
removed.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/07a0954cc6fd730d9d42054fa36346d1de07cd06.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     |  1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 37 +++++++----------------
 2 files changed, 11 insertions(+), 27 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 315905fa4b2c4..514ac9e1f3f88 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -112,7 +112,6 @@ struct rt_hi_throughput {
 	enum ht_extchnl_offset CurSTAExtChnlOffset;
 	u8 cur_tx_bw40mhz;
 	u8 sw_bw_in_progress;
-	u8 reg_rt2rt_aggregation;
 	u8 current_rt2rt_aggregation;
 	u8 current_rt2rt_long_slot_time;
 	u8 sz_rt2rt_agg_buf[10];
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 23ffd0c0dce53..fdd3b6018867c 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -79,8 +79,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 
 	ieee->tx_enable_fw_calc_dur = 1;
 
-	ht_info->reg_rt2rt_aggregation = 1;
-
 	ht_info->reg_rx_reorder_enable = 1;
 	ht_info->rx_reorder_win_size = 64;
 	ht_info->rx_reorder_pending_time = 30;
@@ -471,25 +469,17 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 			ht_info->current_ampdu_enable = false;
 	}
 
-	if (!ht_info->reg_rt2rt_aggregation) {
-		if (ht_info->ampdu_factor > pPeerHTCap->MaxRxAMPDUFactor)
+	if (ieee->current_network.bssht.bd_rt2rt_aggregation) {
+		if (ieee->pairwise_key_type != KEY_TYPE_NA)
 			ht_info->CurrentAMPDUFactor =
-						 pPeerHTCap->MaxRxAMPDUFactor;
+					 pPeerHTCap->MaxRxAMPDUFactor;
 		else
-			ht_info->CurrentAMPDUFactor = ht_info->ampdu_factor;
-
+			ht_info->CurrentAMPDUFactor = HT_AGG_SIZE_64K;
 	} else {
-		if (ieee->current_network.bssht.bd_rt2rt_aggregation) {
-			if (ieee->pairwise_key_type != KEY_TYPE_NA)
-				ht_info->CurrentAMPDUFactor =
-						 pPeerHTCap->MaxRxAMPDUFactor;
-			else
-				ht_info->CurrentAMPDUFactor = HT_AGG_SIZE_64K;
-		} else {
-			ht_info->CurrentAMPDUFactor = min_t(u32, pPeerHTCap->MaxRxAMPDUFactor,
-							    HT_AGG_SIZE_32K);
-		}
+		ht_info->CurrentAMPDUFactor = min_t(u32, pPeerHTCap->MaxRxAMPDUFactor,
+						    HT_AGG_SIZE_32K);
 	}
+
 	ht_info->current_mpdu_density = pPeerHTCap->MPDUDensity;
 	if (ht_info->iot_action & HT_IOT_ACT_TX_USE_AMSDU_8K) {
 		ht_info->current_ampdu_enable = false;
@@ -595,15 +585,10 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 			       pNetwork->bssht.bd_ht_info_buf,
 			       pNetwork->bssht.bd_ht_info_len);
 
-		if (ht_info->reg_rt2rt_aggregation) {
-			ht_info->current_rt2rt_aggregation =
-				 pNetwork->bssht.bd_rt2rt_aggregation;
-			ht_info->current_rt2rt_long_slot_time =
-				 pNetwork->bssht.bd_rt2rt_long_slot_time;
-		} else {
-			ht_info->current_rt2rt_aggregation = false;
-			ht_info->current_rt2rt_long_slot_time = false;
-		}
+		ht_info->current_rt2rt_aggregation =
+			 pNetwork->bssht.bd_rt2rt_aggregation;
+		ht_info->current_rt2rt_long_slot_time =
+			 pNetwork->bssht.bd_rt2rt_long_slot_time;
 
 		ht_iot_peer_determine(ieee);
 
-- 
GitLab


From 162440f2d7c721170917dccb2d91a932c43fe302 Mon Sep 17 00:00:00 2001
From: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Date: Wed, 13 Dec 2023 17:52:55 +0100
Subject: [PATCH 1373/4076] staging: rtl8192e: Remove constant variable
 reg_rx_reorder_enable

Remove constant variable reg_rx_reorder_enable and replace it at the place
of usage with the value.

Signed-off-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Link: https://lore.kernel.org/r/c9bf183b78bfe1fc242dc496786cd0c9f20262a4.1702406712.git.philipp.g.hortmann@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 1 -
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 514ac9e1f3f88..2911ea82dd178 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -115,7 +115,6 @@ struct rt_hi_throughput {
 	u8 current_rt2rt_aggregation;
 	u8 current_rt2rt_long_slot_time;
 	u8 sz_rt2rt_agg_buf[10];
-	u8 reg_rx_reorder_enable;
 	u8 cur_rx_reorder_enable;
 	u8 rx_reorder_win_size;
 	u8 rx_reorder_pending_time;
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index fdd3b6018867c..8836054d6897a 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -79,7 +79,6 @@ void ht_update_default_setting(struct rtllib_device *ieee)
 
 	ieee->tx_enable_fw_calc_dur = 1;
 
-	ht_info->reg_rx_reorder_enable = 1;
 	ht_info->rx_reorder_win_size = 64;
 	ht_info->rx_reorder_pending_time = 30;
 }
@@ -484,7 +483,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	if (ht_info->iot_action & HT_IOT_ACT_TX_USE_AMSDU_8K) {
 		ht_info->current_ampdu_enable = false;
 	}
-	ht_info->cur_rx_reorder_enable = ht_info->reg_rx_reorder_enable;
+	ht_info->cur_rx_reorder_enable = 1;
 
 	if (pPeerHTCap->MCS[0] == 0)
 		pPeerHTCap->MCS[0] = 0xff;
-- 
GitLab


From 36802495f55813bd5a3139b6b5e2e36001fc5fe4 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Wed, 13 Dec 2023 12:54:57 -0500
Subject: [PATCH 1374/4076] staging: rtl8192e: rename variable
 HTSetConnectBwMode

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTSetConnectBwMode -> ht_set_connect_bw_mode

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231213175459.5425-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 6 +++---
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 8836054d6897a..14c036b022a10 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -417,7 +417,7 @@ static u8 HTFilterMCSRate(struct rtllib_device *ieee, u8 *pSupportMCS,
 	return true;
 }
 
-void HTSetConnectBwMode(struct rtllib_device *ieee,
+void ht_set_connect_bw_mode(struct rtllib_device *ieee,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset);
 
@@ -452,7 +452,7 @@ void HTOnAssocRsp(struct rtllib_device *ieee)
 	print_hex_dump_bytes("%s: ", __func__, DUMP_PREFIX_NONE,
 			     pPeerHTCap, sizeof(struct ht_capab_ele));
 #endif
-	HTSetConnectBwMode(ieee, (enum ht_channel_width)(pPeerHTCap->ChlWidth),
+	ht_set_connect_bw_mode(ieee, (enum ht_channel_width)(pPeerHTCap->ChlWidth),
 			   (enum ht_extchnl_offset)(pPeerHTInfo->ExtChlOffset));
 	ht_info->cur_tx_bw40mhz = ((pPeerHTInfo->RecommemdedTxWidth == 1) ?
 				 true : false);
@@ -660,7 +660,7 @@ static void HTSetConnectBwModeCallback(struct rtllib_device *ieee)
 	ht_info->sw_bw_in_progress = false;
 }
 
-void HTSetConnectBwMode(struct rtllib_device *ieee,
+void ht_set_connect_bw_mode(struct rtllib_device *ieee,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset)
 {
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index cc9070f390045..6c9b9a4161704 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1747,7 +1747,7 @@ int rtllib_wx_get_rts(struct rtllib_device *ieee, struct iw_request_info *info,
 		      union iwreq_data *wrqu, char *extra);
 #define MAX_RECEIVE_BUFFER_SIZE 9100
 
-void HTSetConnectBwMode(struct rtllib_device *ieee,
+void ht_set_connect_bw_mode(struct rtllib_device *ieee,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset);
 void ht_update_default_setting(struct rtllib_device *ieee);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index ee527ba5d1a86..3fede7a32cd38 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1109,7 +1109,7 @@ static void rtllib_associate_procedure_wq(void *data)
 	mutex_lock(&ieee->wx_mutex);
 
 	rtllib_stop_scan(ieee);
-	HTSetConnectBwMode(ieee, HT_CHANNEL_WIDTH_20, HT_EXTCHNL_OFFSET_NO_EXT);
+	ht_set_connect_bw_mode(ieee, HT_CHANNEL_WIDTH_20, HT_EXTCHNL_OFFSET_NO_EXT);
 	if (ieee->rf_power_state == rf_off) {
 		ieee->rtllib_ips_leave_wq(ieee->dev);
 		mutex_unlock(&ieee->wx_mutex);
-- 
GitLab


From 8caf3a8e5d54466b2efc6aa979364bf6f60cd29d Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Wed, 13 Dec 2023 12:54:58 -0500
Subject: [PATCH 1375/4076] staging: rtl8192e: rename variable HTOnAssocRsp

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTOnAssocRsp -> ht_on_assoc_rsp

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231213175459.5425-5-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 14c036b022a10..b1cd52aa7e2e6 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -421,7 +421,7 @@ void ht_set_connect_bw_mode(struct rtllib_device *ieee,
 			enum ht_channel_width bandwidth,
 			enum ht_extchnl_offset Offset);
 
-void HTOnAssocRsp(struct rtllib_device *ieee)
+void ht_on_assoc_rsp(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 	struct ht_capab_ele *pPeerHTCap = NULL;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 6c9b9a4161704..8e87cbecdc681 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1756,7 +1756,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee,
 				  u8 isEncrypt, bool bAssoc);
 void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee,
 				u8 *posRT2RTAgg, u8 *len);
-void HTOnAssocRsp(struct rtllib_device *ieee);
+void ht_on_assoc_rsp(struct rtllib_device *ieee);
 void HTInitializeHTInfo(struct rtllib_device *ieee);
 void HTInitializeBssDesc(struct bss_ht *pBssHT);
 void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 3fede7a32cd38..9c94c5ceccd56 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1064,7 +1064,7 @@ static void rtllib_associate_complete_wq(void *data)
 	}
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
 		netdev_info(ieee->dev, "Successfully associated, ht enabled\n");
-		HTOnAssocRsp(ieee);
+		ht_on_assoc_rsp(ieee);
 	} else {
 		netdev_info(ieee->dev,
 			    "Successfully associated, ht not enabled(%d, %d)\n",
-- 
GitLab


From 5e8cdb6f6ebe28976876ab04995a5d3779b85082 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Wed, 13 Dec 2023 12:54:59 -0500
Subject: [PATCH 1376/4076] staging: rtl8192e: rename variable
 HTInitializeHTInfo

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTInitializeHTInfo -> ht_initialize_ht_info

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231213175459.5425-6-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_module.c  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index b1cd52aa7e2e6..90a9356d78cad 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -501,7 +501,7 @@ void ht_on_assoc_rsp(struct rtllib_device *ieee)
 	ht_info->current_op_mode = pPeerHTInfo->OptMode;
 }
 
-void HTInitializeHTInfo(struct rtllib_device *ieee)
+void ht_initialize_ht_info(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 8e87cbecdc681..b4413cfcb17e2 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1757,7 +1757,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee,
 void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee,
 				u8 *posRT2RTAgg, u8 *len);
 void ht_on_assoc_rsp(struct rtllib_device *ieee);
-void HTInitializeHTInfo(struct rtllib_device *ieee);
+void ht_initialize_ht_info(struct rtllib_device *ieee);
 void HTInitializeBssDesc(struct bss_ht *pBssHT);
 void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 				   struct rtllib_network *pNetwork);
diff --git a/drivers/staging/rtl8192e/rtllib_module.c b/drivers/staging/rtl8192e/rtllib_module.c
index 95b6d6b9429c1..e7af4a25b0bee 100644
--- a/drivers/staging/rtl8192e/rtllib_module.c
+++ b/drivers/staging/rtl8192e/rtllib_module.c
@@ -123,7 +123,7 @@ struct net_device *alloc_rtllib(int sizeof_priv)
 		goto free_softmac;
 
 	ht_update_default_setting(ieee);
-	HTInitializeHTInfo(ieee);
+	ht_initialize_ht_info(ieee);
 	rtllib_ts_init(ieee);
 	for (i = 0; i < IEEE_IBSS_MAC_HASH_SIZE; i++)
 		INIT_LIST_HEAD(&ieee->ibss_mac_hash[i]);
-- 
GitLab


From 53b5ff83d89349778bc61e67237f72c5dc6536c2 Mon Sep 17 00:00:00 2001
From: Piyush Mehta <piyush.mehta@amd.com>
Date: Tue, 21 Nov 2023 23:51:18 +0530
Subject: [PATCH 1377/4076] usb: dwc3: xilinx: improve error handling for PM
 APIs

Improve error handling for PM APIs in the dwc3_xlnx_probe function by
introducing devm_pm_runtime_enable and error label. Removed unnecessary
API pm_runtime_disable call in dwc3_xlnx_remove.

Signed-off-by: Piyush Mehta <piyush.mehta@amd.com>
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Link: https://lore.kernel.org/r/1700590878-124335-1-git-send-email-radhey.shyam.pandey@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-xilinx.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
index 5b7e92f476de9..6095f4dee6ceb 100644
--- a/drivers/usb/dwc3/dwc3-xilinx.c
+++ b/drivers/usb/dwc3/dwc3-xilinx.c
@@ -293,11 +293,15 @@ static int dwc3_xlnx_probe(struct platform_device *pdev)
 		goto err_clk_put;
 
 	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
+	ret = devm_pm_runtime_enable(dev);
+	if (ret < 0)
+		goto err_pm_set_suspended;
+
 	pm_suspend_ignore_children(dev, false);
-	pm_runtime_get_sync(dev);
+	return pm_runtime_resume_and_get(dev);
 
-	return 0;
+err_pm_set_suspended:
+	pm_runtime_set_suspended(dev);
 
 err_clk_put:
 	clk_bulk_disable_unprepare(priv_data->num_clocks, priv_data->clks);
@@ -315,7 +319,6 @@ static void dwc3_xlnx_remove(struct platform_device *pdev)
 	clk_bulk_disable_unprepare(priv_data->num_clocks, priv_data->clks);
 	priv_data->num_clocks = 0;
 
-	pm_runtime_disable(dev);
 	pm_runtime_put_noidle(dev);
 	pm_runtime_set_suspended(dev);
 }
-- 
GitLab


From 66aad7d8d3ec5a3a8ec2023841bcec2ded5f65c9 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 7 Dec 2023 14:26:30 +0100
Subject: [PATCH 1378/4076] usb: cdc-acm: return correct error code on
 unsupported break

In ACM support for sending breaks to devices is optional.
If a device says that it doenot support sending breaks,
the host must respect that.
Given the number of optional features providing tty operations
for each combination is not practical and errors need to be
returned dynamically if unsupported features are requested.

In case a device does not support break, we want the tty layer
to treat that like it treats drivers that statically cannot
support sending a break. It ignores the inability and does nothing.
This patch uses EOPNOTSUPP to indicate that.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Fixes: 9e98966c7bb94 ("tty: rework break handling")
Link: https://lore.kernel.org/r/20231207132639.18250-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c        | 3 +++
 drivers/usb/class/cdc-acm.c | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 06414e43e0b53..96617f9af819d 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2489,6 +2489,9 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 	if (!retval) {
 		msleep_interruptible(duration);
 		retval = tty->ops->break_ctl(tty, 0);
+	} else if (retval == -EOPNOTSUPP) {
+		/* some drivers can tell only dynamically */
+		retval = 0;
 	}
 	tty_write_unlock(tty);
 
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index a1f4e1ead97ff..0e7439dba8fe8 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -916,6 +916,9 @@ static int acm_tty_break_ctl(struct tty_struct *tty, int state)
 	struct acm *acm = tty->driver_data;
 	int retval;
 
+	if (!(acm->ctrl_caps & USB_CDC_CAP_BRK))
+		return -EOPNOTSUPP;
+
 	retval = acm_send_break(acm, state ? 0xffff : 0);
 	if (retval < 0)
 		dev_dbg(&acm->control->dev,
-- 
GitLab


From ecb43ef59498628a9df79afb47e67dadf777e3cd Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Thu, 7 Dec 2023 09:42:17 -0300
Subject: [PATCH 1379/4076] dt-bindings: usb: genesys,gl850g: Document
 'peer-hub'

The 'peer-hub' is a valid property for the hub.

Document it to fix the following dt-schema warning:

imx8mp-debix-som-a-bmb-08.dtb: hub@1: 'peer-hub' does not match any of the regexes: 'pinctrl-[0-9]+'
	from schema $id: http://devicetree.org/schemas/usb/genesys,gl850g.yaml#

Signed-off-by: Fabio Estevam <festevam@denx.de>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231207124217.2530457-1-festevam@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/genesys,gl850g.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/usb/genesys,gl850g.yaml b/Documentation/devicetree/bindings/usb/genesys,gl850g.yaml
index ee08b9c3721f8..37cf5249e526b 100644
--- a/Documentation/devicetree/bindings/usb/genesys,gl850g.yaml
+++ b/Documentation/devicetree/bindings/usb/genesys,gl850g.yaml
@@ -29,6 +29,11 @@ properties:
     description:
       the regulator that provides 3.3V core power to the hub.
 
+  peer-hub:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      phandle to the peer hub on the controller.
+
 required:
   - compatible
   - reg
-- 
GitLab


From 2ddc97a71a27b6f940f1ed0f1e70a4e8e62b77e5 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Thu, 7 Dec 2023 14:29:12 -0300
Subject: [PATCH 1380/4076] dt-bindings: usb: nxp,ptn5110: Fix typos in the
 title

Fix the misspelled "Controller" and "Type-C" words.

Signed-off-by: Fabio Estevam <festevam@denx.de>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231207172912.2658226-1-festevam@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml b/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml
index 28eb25ecba74e..eaedb4cc6b6cc 100644
--- a/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml
+++ b/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml
@@ -4,7 +4,7 @@
 $id: http://devicetree.org/schemas/usb/nxp,ptn5110.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: NXP PTN5110 Typec Port Cotroller
+title: NXP PTN5110 Type-C Port Controller
 
 maintainers:
   - Li Jun <jun.li@nxp.com>
-- 
GitLab


From e4e5f9e3bff79951cef7fd6912049b1cecf8a72d Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 10 Dec 2023 18:43:56 +0100
Subject: [PATCH 1381/4076] usb: chipidea: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/8bf382976c0ba0986c0dbe93427266273f0776ef.1702230217.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 7ac39a281b8cb..0af9e68035fb4 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -862,7 +862,7 @@ struct platform_device *ci_hdrc_add_device(struct device *dev,
 	if (ret)
 		return ERR_PTR(ret);
 
-	id = ida_simple_get(&ci_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&ci_ida, GFP_KERNEL);
 	if (id < 0)
 		return ERR_PTR(id);
 
@@ -892,7 +892,7 @@ struct platform_device *ci_hdrc_add_device(struct device *dev,
 err:
 	platform_device_put(pdev);
 put_id:
-	ida_simple_remove(&ci_ida, id);
+	ida_free(&ci_ida, id);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(ci_hdrc_add_device);
@@ -901,7 +901,7 @@ void ci_hdrc_remove_device(struct platform_device *pdev)
 {
 	int id = pdev->id;
 	platform_device_unregister(pdev);
-	ida_simple_remove(&ci_ida, id);
+	ida_free(&ci_ida, id);
 }
 EXPORT_SYMBOL_GPL(ci_hdrc_remove_device);
 
-- 
GitLab


From 7516f86aa5ec9f3f2ae1c5c12b56eef76c7b1a15 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 10 Dec 2023 18:36:15 +0100
Subject: [PATCH 1382/4076] usb: typec: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/c7b99c4f52649ce6405779fbf9170edc5633fdbb.1702229697.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/class.c | 8 ++++----
 drivers/usb/typec/pd.c    | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 16a670828dde1..5fe01bf795b9f 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -476,7 +476,7 @@ static int altmode_id_get(struct device *dev)
 	else
 		ids = &to_typec_port(dev)->mode_ids;
 
-	return ida_simple_get(ids, 0, 0, GFP_KERNEL);
+	return ida_alloc(ids, GFP_KERNEL);
 }
 
 static void altmode_id_remove(struct device *dev, int id)
@@ -490,7 +490,7 @@ static void altmode_id_remove(struct device *dev, int id)
 	else
 		ids = &to_typec_port(dev)->mode_ids;
 
-	ida_simple_remove(ids, id);
+	ida_free(ids, id);
 }
 
 static void typec_altmode_release(struct device *dev)
@@ -1798,7 +1798,7 @@ static void typec_release(struct device *dev)
 {
 	struct typec_port *port = to_typec_port(dev);
 
-	ida_simple_remove(&typec_index_ida, port->id);
+	ida_free(&typec_index_ida, port->id);
 	ida_destroy(&port->mode_ids);
 	typec_switch_put(port->sw);
 	typec_mux_put(port->mux);
@@ -2297,7 +2297,7 @@ struct typec_port *typec_register_port(struct device *parent,
 	if (!port)
 		return ERR_PTR(-ENOMEM);
 
-	id = ida_simple_get(&typec_index_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&typec_index_ida, GFP_KERNEL);
 	if (id < 0) {
 		kfree(port);
 		return ERR_PTR(id);
diff --git a/drivers/usb/typec/pd.c b/drivers/usb/typec/pd.c
index 85d015cdbe1fe..7f3d61f220f27 100644
--- a/drivers/usb/typec/pd.c
+++ b/drivers/usb/typec/pd.c
@@ -571,7 +571,7 @@ static void pd_release(struct device *dev)
 {
 	struct usb_power_delivery *pd = to_usb_power_delivery(dev);
 
-	ida_simple_remove(&pd_ida, pd->id);
+	ida_free(&pd_ida, pd->id);
 	kfree(pd);
 }
 
@@ -616,7 +616,7 @@ usb_power_delivery_register(struct device *parent, struct usb_power_delivery_des
 	if (!pd)
 		return ERR_PTR(-ENOMEM);
 
-	ret = ida_simple_get(&pd_ida, 0, 0, GFP_KERNEL);
+	ret = ida_alloc(&pd_ida, GFP_KERNEL);
 	if (ret < 0) {
 		kfree(pd);
 		return ERR_PTR(ret);
-- 
GitLab


From d1756ac67e7f8d4c15ba4dd0c132e593b0a56de6 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Mon, 4 Dec 2023 04:03:00 +0200
Subject: [PATCH 1383/4076] dt-bindings: connector: usb: add altmodes
 description

Add description of the USB-C AltModes supported on the particular USB-C
connector. This is required for devices like Qualcomm Robotics RB5,
which have no other way to express alternative modes supported by the
hardware platform.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231204020303.2287338-2-dmitry.baryshkov@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../bindings/connector/usb-connector.yaml     | 33 +++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml
index 7c8a3e8430d30..28660b931d0c3 100644
--- a/Documentation/devicetree/bindings/connector/usb-connector.yaml
+++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml
@@ -171,6 +171,32 @@ properties:
       offer the power, Capability Mismatch is set. Required for power sink and
       power dual role.
 
+  altmodes:
+    type: object
+    description: List of Alternative Modes supported by the schematics on the
+      particular device. This is only necessary if there are no other means to
+      discover supported alternative modes (e.g. through the UCSI firmware
+      interface).
+
+    additionalProperties: false
+
+    patternProperties:
+      "^(displayport)$":
+        type: object
+        description:
+          A single USB-C Alternative Mode as supported by the USB-C connector logic.
+
+        additionalProperties: false
+
+        properties:
+          svid:
+            $ref: /schemas/types.yaml#/definitions/uint16
+            description: Unique value assigned by USB-IF to the Vendor / AltMode.
+            enum: [ 0xff01 ]
+          vdo:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            description: VDO returned by Discover Modes USB PD command.
+
   port:
     $ref: /schemas/graph.yaml#/properties/port
     description: OF graph bindings modeling a data bus to the connector, e.g.
@@ -289,6 +315,13 @@ examples:
             compatible = "usb-c-connector";
             label = "USB-C";
 
+            altmodes {
+                displayport {
+                    svid = /bits/ 16 <0xff01>;
+                    vdo = <0x00001c46>;
+                };
+            };
+
             ports {
                 #address-cells = <1>;
                 #size-cells = <0>;
-- 
GitLab


From 0dbda971860c702c33df173b627f9d74b3152b75 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Mon, 4 Dec 2023 04:03:01 +0200
Subject: [PATCH 1384/4076] usb: typec: change altmode SVID to u16 entry

As stated in the changelog for the commit 7b458a4c5d73 ("usb: typec: Add
typec_port_register_altmodes()"), the code should be adjusted according
to the AltMode bindings. As the SVID is 16 bits wide (according to the
USB PD Spec), use fwnode_property_read_u16() to read it.

Acked-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231204020303.2287338-3-dmitry.baryshkov@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/platform/x86/intel/chtwc_int33fe.c | 2 +-
 drivers/usb/typec/class.c                  | 5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/intel/chtwc_int33fe.c b/drivers/platform/x86/intel/chtwc_int33fe.c
index 848baecc1bb02..93f75ba1dafdf 100644
--- a/drivers/platform/x86/intel/chtwc_int33fe.c
+++ b/drivers/platform/x86/intel/chtwc_int33fe.c
@@ -136,7 +136,7 @@ static const struct software_node altmodes_node = {
 };
 
 static const struct property_entry dp_altmode_properties[] = {
-	PROPERTY_ENTRY_U32("svid", 0xff01),
+	PROPERTY_ENTRY_U16("svid", 0xff01),
 	PROPERTY_ENTRY_U32("vdo", 0x0c0086),
 	{ }
 };
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 5fe01bf795b9f..aeae8009b9e3a 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -2231,7 +2231,8 @@ void typec_port_register_altmodes(struct typec_port *port,
 	struct typec_altmode_desc desc;
 	struct typec_altmode *alt;
 	size_t index = 0;
-	u32 svid, vdo;
+	u16 svid;
+	u32 vdo;
 	int ret;
 
 	altmodes_node = device_get_named_child_node(&port->dev, "altmodes");
@@ -2239,7 +2240,7 @@ void typec_port_register_altmodes(struct typec_port *port,
 		return; /* No altmodes specified */
 
 	fwnode_for_each_child_node(altmodes_node, child) {
-		ret = fwnode_property_read_u32(child, "svid", &svid);
+		ret = fwnode_property_read_u16(child, "svid", &svid);
 		if (ret) {
 			dev_err(&port->dev, "Error reading svid for altmode %s\n",
 				fwnode_get_name(child));
-- 
GitLab


From 70e6163d17dd501ef27680eeb80d78b2cf823c5e Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Mon, 4 Dec 2023 04:03:02 +0200
Subject: [PATCH 1385/4076] arm64: dts: qcom: qrb5165-rb5: use u16 for DP
 altmode svid

Follow the bindings and use 16-bit value for AltMode SVID instead of
using the full u32.

Fixes: b3dea914127e ("arm64: dts: qcom: qrb5165-rb5: enable DP altmode")
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231204020303.2287338-4-dmitry.baryshkov@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/qrb5165-rb5.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
index c8cd40a462a3f..88b37ceb13ede 100644
--- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
+++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts
@@ -1425,7 +1425,7 @@
 
 		altmodes {
 			displayport {
-				svid = <0xff01>;
+				svid = /bits/ 16 <0xff01>;
 				vdo = <0x00001c46>;
 			};
 		};
-- 
GitLab


From 7d530f4cc0632056d9f8f207245aa3d91a25d168 Mon Sep 17 00:00:00 2001
From: Kyle Tso <kyletso@google.com>
Date: Tue, 5 Dec 2023 15:47:46 +0800
Subject: [PATCH 1386/4076] usb: typec: tcpm: Query Source partner for FRS
 capability only if it is DRP

Source-only port partner will always respond NOT_SUPPORTED to
GET_SINK_CAP. Avoid this redundant AMS by bailing out querying the FRS
capability if the Source port partner is not DRP.

Signed-off-by: Kyle Tso <kyletso@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20231205074747.1821297-1-kyletso@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index ff67553b69323..8372f98de757d 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4402,7 +4402,8 @@ static void run_state_machine(struct tcpm_port *port)
 			tcpm_set_current_limit(port, tcpm_get_current_limit(port), 5000);
 		tcpm_swap_complete(port, 0);
 		tcpm_typec_connect(port);
-		mod_enable_frs_delayed_work(port, 0);
+		if (port->pd_capable && port->source_caps[0] & PDO_FIXED_DUAL_ROLE)
+			mod_enable_frs_delayed_work(port, 0);
 		tcpm_pps_complete(port, port->pps_status);
 
 		if (port->ams != NONE_AMS)
-- 
GitLab


From 44995e6f07028f798efd0c3c11a1efc78330f600 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Mon, 11 Dec 2023 07:32:41 -0800
Subject: [PATCH 1387/4076] usb: core: Fix crash w/ usb_choose_configuration()
 if no driver

It's possible that usb_choose_configuration() can get called when a
USB device has no driver. In this case the recent commit a87b8e3be926
("usb: core: Allow subclassed USB drivers to override
usb_choose_configuration()") can cause a crash since it dereferenced
the driver structure without checking for NULL. Let's add a check.

A USB device with no driver is an anomaly, so make
usb_choose_configuration() return immediately if there is no driver.

This was seen in the real world when usbguard got ahold of a r8152
device at the wrong time. It can also be simulated via this on a
computer with one r8152-based USB Ethernet adapter:
  cd /sys/bus/usb/drivers/r8152-cfgselector
  to_unbind="$(ls -d *-*)"
  real_dir="$(readlink -f "${to_unbind}")"
  echo "${to_unbind}" > unbind
  cd "${real_dir}"
  echo 0 > authorized
  echo 1 > authorized

Fixes: a87b8e3be926 ("usb: core: Allow subclassed USB drivers to override usb_choose_configuration()")
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20231211073237.v3.1.If27eb3bf7812f91ab83810f232292f032f4203e0@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/generic.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index dcb8971582284..b134bff5c3fe3 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -59,7 +59,16 @@ int usb_choose_configuration(struct usb_device *udev)
 	int num_configs;
 	int insufficient_power = 0;
 	struct usb_host_config *c, *best;
-	struct usb_device_driver *udriver = to_usb_device_driver(udev->dev.driver);
+	struct usb_device_driver *udriver;
+
+	/*
+	 * If a USB device (not an interface) doesn't have a driver then the
+	 * kernel has no business trying to select or install a configuration
+	 * for it.
+	 */
+	if (!udev->dev.driver)
+		return -1;
+	udriver = to_usb_device_driver(udev->dev.driver);
 
 	if (usb_device_is_owned(udev))
 		return 0;
-- 
GitLab


From de12c5384307d2fa2a735b7d21cf7603e1bcb5c9 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Tue, 12 Dec 2023 09:54:28 +0100
Subject: [PATCH 1388/4076] dt-bindings: usb: Document WCD939x USB SubSystem
 Altmode/Analog Audio Switch

Document the Qualcomm WCD9390/WCD9395 USB SubSystem Altmode/Analog Audio Switch
which is a separate USB SubSystem for Altmode/Analog Audio Switch accessible
over an I2C interface.

Since Audio Headphone and Microphone data path between the Codec and the USB-C Mux
subsystems are external to the IC, it requires a second port to handle USB-C altmode
& orientation switching for Audio Accessory Mode to the Codec SubSystem.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231212-topic-sm8650-upstream-wcd939x-usbss-v2-1-38961fea5867@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../bindings/usb/qcom,wcd939x-usbss.yaml      | 102 ++++++++++++++++++
 1 file changed, 102 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml

diff --git a/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml b/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml
new file mode 100644
index 0000000000000..7ddfd3313a185
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml
@@ -0,0 +1,102 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/usb/qcom,wcd939x-usbss.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm WCD9380/WCD9385 USB SubSystem Altmode/Analog Audio Switch
+
+maintainers:
+  - Neil Armstrong <neil.armstrong@linaro.org>
+
+description:
+  Qualcomm WCD9390/WCD9395 is a standalone Hi-Fi audio codec IC with a
+  functionally separate USB SubSystem for Altmode/Analog Audio Switch
+  accessible over an I2C interface.
+  The Audio Headphone and Microphone data path between the Codec and the
+  USB-C Mux subsystems are external to the IC, thus requiring DT port-endpoint
+  graph description to handle USB-C altmode & orientation switching for Audio
+  Accessory Mode.
+
+properties:
+  compatible:
+    oneOf:
+      - const: qcom,wcd9390-usbss
+      - items:
+          - const: qcom,wcd9395-usbss
+          - const: qcom,wcd9390-usbss
+
+  reg:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+
+  vdd-supply:
+    description: USBSS VDD power supply
+
+  mode-switch:
+    description: Flag the port as possible handle of altmode switching
+    type: boolean
+
+  orientation-switch:
+    description: Flag the port as possible handler of orientation switching
+    type: boolean
+
+  ports:
+    $ref: /schemas/graph.yaml#/properties/ports
+    properties:
+      port@0:
+        $ref: /schemas/graph.yaml#/properties/port
+        description:
+          A port node to link the WCD939x USB SubSystem to a TypeC controller for the
+          purpose of handling altmode muxing and orientation switching.
+
+      port@1:
+        $ref: /schemas/graph.yaml#/properties/port
+        description:
+          A port node to link the WCD939x USB SubSystem to the Codec SubSystem for the
+          purpose of handling USB-C Audio Accessory Mode muxing and orientation switching.
+
+required:
+  - compatible
+  - reg
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        typec-mux@42 {
+            compatible = "qcom,wcd9390-usbss";
+            reg = <0x42>;
+
+            vdd-supply = <&vreg_bob>;
+
+            mode-switch;
+            orientation-switch;
+
+            ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                port@0 {
+                    reg = <0>;
+                    wcd9390_usbss_sbu: endpoint {
+                        remote-endpoint = <&typec_sbu>;
+                    };
+                };
+                port@1 {
+                    reg = <1>;
+                    wcd9390_usbss_codec: endpoint {
+                        remote-endpoint = <&wcd9390_codec_usbss>;
+                    };
+                };
+            };
+        };
+    };
+...
-- 
GitLab


From 36d586c0570e075c18bcc3b4ec4de11fcdbf5dd1 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Tue, 12 Dec 2023 09:54:29 +0100
Subject: [PATCH 1389/4076] usb: typec: mux: add Qualcomm WCD939X USB SubSystem
 Altmode Mux driver

Qualcomm WCD9390/WCD9395 is a standalone Hi-Fi audio codec IC with a
functionally separate USB SubSystem for Altmode/Analog Audio Switch
accessible over an I2C interface.

It provides switching USB-C USB2.0 lines between USB and Audio Headphones
speaker lines, and the USB-C SBU lines between DisplayPort AUX and Audio
Headphones Microphone/Ground.

The Audio Headphone and Microphone data path between the Codec and the
USB-C Mux subsystems are external to the IC, thus requiring DT
port-endpoint graph description to handle USB-C altmode & orientation
switching for Audio Accessory Mode.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231212-topic-sm8650-upstream-wcd939x-usbss-v2-2-38961fea5867@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/mux/Kconfig         |  10 +
 drivers/usb/typec/mux/Makefile        |   1 +
 drivers/usb/typec/mux/wcd939x-usbss.c | 779 ++++++++++++++++++++++++++
 3 files changed, 790 insertions(+)
 create mode 100644 drivers/usb/typec/mux/wcd939x-usbss.c

diff --git a/drivers/usb/typec/mux/Kconfig b/drivers/usb/typec/mux/Kconfig
index 816b9bd08355f..71968179c1cbd 100644
--- a/drivers/usb/typec/mux/Kconfig
+++ b/drivers/usb/typec/mux/Kconfig
@@ -56,4 +56,14 @@ config TYPEC_MUX_PTN36502
 	  Say Y or M if your system has a NXP PTN36502 Type-C redriver chip
 	  found on some devices with a Type-C port.
 
+config TYPEC_MUX_WCD939X_USBSS
+	tristate "Qualcomm WCD939x USBSS Analog Audio Switch driver"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  Driver for the Qualcomm WCD939x Audio Codec USBSS domain which
+	  provides support for muxing analog audio and sideband signals on a
+	  common USB Type-C connector.
+	  If compiled as a module, the module will be named wcd939x-usbss.
+
 endmenu
diff --git a/drivers/usb/typec/mux/Makefile b/drivers/usb/typec/mux/Makefile
index 9d6a5557b0bde..57dc9ac6f8dcf 100644
--- a/drivers/usb/typec/mux/Makefile
+++ b/drivers/usb/typec/mux/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_TYPEC_MUX_PI3USB30532)	+= pi3usb30532.o
 obj-$(CONFIG_TYPEC_MUX_INTEL_PMC)	+= intel_pmc_mux.o
 obj-$(CONFIG_TYPEC_MUX_NB7VPQ904M)	+= nb7vpq904m.o
 obj-$(CONFIG_TYPEC_MUX_PTN36502)	+= ptn36502.o
+obj-$(CONFIG_TYPEC_MUX_WCD939X_USBSS)	+= wcd939x-usbss.o
diff --git a/drivers/usb/typec/mux/wcd939x-usbss.c b/drivers/usb/typec/mux/wcd939x-usbss.c
new file mode 100644
index 0000000000000..d46c353dfaf2f
--- /dev/null
+++ b/drivers/usb/typec/mux/wcd939x-usbss.c
@@ -0,0 +1,779 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (C) 2023 Linaro Ltd.
+ */
+
+#include <linux/bits.h>
+#include <linux/i2c.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/bitfield.h>
+#include <linux/gpio/consumer.h>
+#include <linux/usb/typec_dp.h>
+#include <linux/usb/typec_mux.h>
+
+#define WCD_USBSS_PMP_OUT1			0x2
+
+#define WCD_USBSS_DP_DN_MISC1			0x20
+
+#define WCD_USBSS_DP_DN_MISC1_DP_PCOMP_2X_DYN_BST_ON_EN			BIT(3)
+#define WCD_USBSS_DP_DN_MISC1_DN_PCOMP_2X_DYN_BST_ON_EN			BIT(0)
+
+#define WCD_USBSS_MG1_EN			0x24
+
+#define WCD_USBSS_MG1_EN_CT_SNS_EN					BIT(1)
+
+#define WCD_USBSS_MG1_BIAS			0x25
+
+#define WCD_USBSS_MG1_BIAS_PCOMP_DYN_BST_EN				BIT(3)
+
+#define WCD_USBSS_MG1_MISC			0x27
+
+#define WCD_USBSS_MG1_MISC_PCOMP_2X_DYN_BST_ON_EN			BIT(5)
+
+#define WCD_USBSS_MG2_EN			0x28
+
+#define WCD_USBSS_MG2_EN_CT_SNS_EN					BIT(1)
+
+#define WCD_USBSS_MG2_BIAS			0x29
+
+#define WCD_USBSS_MG2_BIAS_PCOMP_DYN_BST_EN				BIT(3)
+
+#define WCD_USBSS_MG2_MISC			0x30
+
+#define WCD_USBSS_MG2_MISC_PCOMP_2X_DYN_BST_ON_EN			BIT(5)
+
+#define WCD_USBSS_DISP_AUXP_THRESH		0x80
+
+#define WCD_USBSS_DISP_AUXP_THRESH_DISP_AUXP_OVPON_CM			GENMASK(7, 5)
+
+#define WCD_USBSS_DISP_AUXP_CTL			0x81
+
+#define WCD_USBSS_DISP_AUXP_CTL_LK_CANCEL_TRK_COEFF			GENMASK(2, 0)
+
+#define WCD_USBSS_CPLDO_CTL2			0xa1
+
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE	0x403
+
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DEVICE_ENABLE			BIT(7)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXP_TO_MGX_SWITCHES	BIT(6)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXM_TO_MGX_SWITCHES	BIT(5)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DNL_SWITCHES			BIT(4)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_DPR_SWITCHES			BIT(3)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_SENSE_SWITCHES			BIT(2)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_MIC_SWITCHES			BIT(1)
+#define WCD_USBSS_SWITCH_SETTINGS_ENABLE_AGND_SWITCHES			BIT(0)
+
+#define WCD_USBSS_SWITCH_SELECT0		0x404
+
+#define WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES			BIT(7)	/* 1-> MG2 */
+#define WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES			BIT(6)	/* 1-> MG2 */
+#define WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES				GENMASK(5, 4)
+#define WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES				GENMASK(3, 2)
+#define WCD_USBSS_SWITCH_SELECT0_SENSE_SWITCHES				BIT(1)	/* 1-> SBU2 */
+#define WCD_USBSS_SWITCH_SELECT0_MIC_SWITCHES				BIT(0)	/* 1-> MG2 */
+
+#define WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_L		0
+#define WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_DN		1
+#define WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_DN2		2
+
+#define WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_R		0
+#define WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_DP		1
+#define WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_DR2		2
+
+#define WCD_USBSS_SWITCH_SELECT1		0x405
+
+#define WCD_USBSS_SWITCH_SELECT1_AGND_SWITCHES				BIT(0)	/* 1-> MG2 */
+
+#define WCD_USBSS_DELAY_R_SW			0x40d
+#define WCD_USBSS_DELAY_MIC_SW			0x40e
+#define WCD_USBSS_DELAY_SENSE_SW		0x40f
+#define WCD_USBSS_DELAY_GND_SW			0x410
+#define WCD_USBSS_DELAY_L_SW			0x411
+
+#define WCD_USBSS_FUNCTION_ENABLE		0x413
+
+#define WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT				GENMASK(1, 0)
+
+#define WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT_MANUAL		1
+#define WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT_AUDIO_FSM	2
+
+#define WCD_USBSS_EQUALIZER1			0x415
+
+#define WCD_USBSS_EQUALIZER1_EQ_EN					BIT(7)
+#define WCD_USBSS_EQUALIZER1_BW_SETTINGS				GENMASK(6, 3)
+
+#define WCD_USBSS_USB_SS_CNTL			0x419
+
+#define WCD_USBSS_USB_SS_CNTL_STANDBY_STATE				BIT(4)
+#define WCD_USBSS_USB_SS_CNTL_RCO_EN					BIT(3)
+#define WCD_USBSS_USB_SS_CNTL_USB_SS_MODE				GENMASK(2, 0)
+
+#define WCD_USBSS_USB_SS_CNTL_USB_SS_MODE_AATC		2
+#define WCD_USBSS_USB_SS_CNTL_USB_SS_MODE_USB		5
+
+#define WCD_USBSS_AUDIO_FSM_START		0x433
+
+#define WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG			BIT(0)
+
+#define WCD_USBSS_RATIO_SPKR_REXT_L_LSB		0x461
+#define WCD_USBSS_RATIO_SPKR_REXT_L_MSB		0x462
+#define WCD_USBSS_RATIO_SPKR_REXT_R_LSB		0x463
+#define WCD_USBSS_RATIO_SPKR_REXT_R_MSB		0x464
+#define WCD_USBSS_AUD_COEF_L_K0_0		0x475
+#define WCD_USBSS_AUD_COEF_L_K0_1		0x476
+#define WCD_USBSS_AUD_COEF_L_K0_2		0x477
+#define WCD_USBSS_AUD_COEF_L_K1_0		0x478
+#define WCD_USBSS_AUD_COEF_L_K1_1		0x479
+#define WCD_USBSS_AUD_COEF_L_K2_0		0x47a
+#define WCD_USBSS_AUD_COEF_L_K2_1		0x47b
+#define WCD_USBSS_AUD_COEF_L_K3_0		0x47c
+#define WCD_USBSS_AUD_COEF_L_K3_1		0x47d
+#define WCD_USBSS_AUD_COEF_L_K4_0		0x47e
+#define WCD_USBSS_AUD_COEF_L_K4_1		0x47f
+#define WCD_USBSS_AUD_COEF_L_K5_0		0x480
+#define WCD_USBSS_AUD_COEF_L_K5_1		0x481
+#define WCD_USBSS_AUD_COEF_R_K0_0		0x482
+#define WCD_USBSS_AUD_COEF_R_K0_1		0x483
+#define WCD_USBSS_AUD_COEF_R_K0_2		0x484
+#define WCD_USBSS_AUD_COEF_R_K1_0		0x485
+#define WCD_USBSS_AUD_COEF_R_K1_1		0x486
+#define WCD_USBSS_AUD_COEF_R_K2_0		0x487
+#define WCD_USBSS_AUD_COEF_R_K2_1		0x488
+#define WCD_USBSS_AUD_COEF_R_K3_0		0x489
+#define WCD_USBSS_AUD_COEF_R_K3_1		0x48a
+#define WCD_USBSS_AUD_COEF_R_K4_0		0x48b
+#define WCD_USBSS_AUD_COEF_R_K4_1		0x48c
+#define WCD_USBSS_AUD_COEF_R_K5_0		0x48d
+#define WCD_USBSS_AUD_COEF_R_K5_1		0x48e
+#define WCD_USBSS_GND_COEF_L_K0_0		0x48f
+#define WCD_USBSS_GND_COEF_L_K0_1		0x490
+#define WCD_USBSS_GND_COEF_L_K0_2		0x491
+#define WCD_USBSS_GND_COEF_L_K1_0		0x492
+#define WCD_USBSS_GND_COEF_L_K1_1		0x493
+#define WCD_USBSS_GND_COEF_L_K2_0		0x494
+#define WCD_USBSS_GND_COEF_L_K2_1		0x495
+#define WCD_USBSS_GND_COEF_L_K3_0		0x496
+#define WCD_USBSS_GND_COEF_L_K3_1		0x497
+#define WCD_USBSS_GND_COEF_L_K4_0		0x498
+#define WCD_USBSS_GND_COEF_L_K4_1		0x499
+#define WCD_USBSS_GND_COEF_L_K5_0		0x49a
+#define WCD_USBSS_GND_COEF_L_K5_1		0x49b
+#define WCD_USBSS_GND_COEF_R_K0_0		0x49c
+#define WCD_USBSS_GND_COEF_R_K0_1		0x49d
+#define WCD_USBSS_GND_COEF_R_K0_2		0x49e
+#define WCD_USBSS_GND_COEF_R_K1_0		0x49f
+#define WCD_USBSS_GND_COEF_R_K1_1		0x4a0
+#define WCD_USBSS_GND_COEF_R_K2_0		0x4a1
+#define WCD_USBSS_GND_COEF_R_K2_1		0x4a2
+#define WCD_USBSS_GND_COEF_R_K3_0		0x4a3
+#define WCD_USBSS_GND_COEF_R_K3_1		0x4a4
+#define WCD_USBSS_GND_COEF_R_K4_0		0x4a5
+#define WCD_USBSS_GND_COEF_R_K4_1		0x4a6
+#define WCD_USBSS_GND_COEF_R_K5_0		0x4a7
+#define WCD_USBSS_GND_COEF_R_K5_1		0x4a8
+
+#define WCD_USBSS_MAX_REGISTER			0x4c1
+
+struct wcd939x_usbss {
+	struct i2c_client *client;
+	struct gpio_desc *reset_gpio;
+	struct regulator *vdd_supply;
+
+	/* used to serialize concurrent change requests */
+	struct mutex lock;
+
+	struct typec_switch_dev *sw;
+	struct typec_mux_dev *mux;
+
+	struct regmap *regmap;
+
+	struct typec_mux *codec;
+	struct typec_switch *codec_switch;
+
+	enum typec_orientation orientation;
+	unsigned long mode;
+	unsigned int svid;
+};
+
+static const struct regmap_range_cfg wcd939x_usbss_ranges[] = {
+	{
+		.range_min = 0,
+		.range_max = WCD_USBSS_MAX_REGISTER,
+		.selector_reg = 0x0,
+		.selector_mask = 0xff,
+		.selector_shift = 0,
+		.window_start = 0,
+		.window_len = 0x100,
+	},
+};
+
+static const struct regmap_config wcd939x_usbss_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = WCD_USBSS_MAX_REGISTER,
+	.ranges = wcd939x_usbss_ranges,
+	.num_ranges = ARRAY_SIZE(wcd939x_usbss_ranges),
+};
+
+/* Linearlizer coefficients for 32ohm load */
+static const struct {
+	unsigned int offset;
+	unsigned int mask;
+	unsigned int value;
+} wcd939x_usbss_coeff_init[] = {
+	{ WCD_USBSS_AUD_COEF_L_K5_0, GENMASK(7, 0), 0x39 },
+	{ WCD_USBSS_AUD_COEF_R_K5_0, GENMASK(7, 0), 0x39 },
+	{ WCD_USBSS_GND_COEF_L_K2_0, GENMASK(7, 0), 0xe8 },
+	{ WCD_USBSS_GND_COEF_L_K4_0, GENMASK(7, 0), 0x73 },
+	{ WCD_USBSS_GND_COEF_R_K2_0, GENMASK(7, 0), 0xe8 },
+	{ WCD_USBSS_GND_COEF_R_K4_0, GENMASK(7, 0), 0x73 },
+	{ WCD_USBSS_RATIO_SPKR_REXT_L_LSB, GENMASK(7, 0), 0x00 },
+	{ WCD_USBSS_RATIO_SPKR_REXT_L_MSB, GENMASK(6, 0), 0x04 },
+	{ WCD_USBSS_RATIO_SPKR_REXT_R_LSB, GENMASK(7, 0), 0x00 },
+	{ WCD_USBSS_RATIO_SPKR_REXT_R_MSB, GENMASK(6, 0), 0x04 },
+};
+
+static int wcd939x_usbss_set(struct wcd939x_usbss *usbss)
+{
+	bool reverse = (usbss->orientation == TYPEC_ORIENTATION_REVERSE);
+	bool enable_audio = false;
+	bool enable_usb = false;
+	bool enable_dp = false;
+	int ret;
+
+	/* USB Mode */
+	if (usbss->mode < TYPEC_STATE_MODAL ||
+	    (!usbss->svid && (usbss->mode == TYPEC_MODE_USB2 ||
+			      usbss->mode == TYPEC_MODE_USB3))) {
+		enable_usb = true;
+	} else if (usbss->svid) {
+		switch (usbss->mode) {
+		/* DP Only */
+		case TYPEC_DP_STATE_C:
+		case TYPEC_DP_STATE_E:
+			enable_dp = true;
+			break;
+
+		/* DP + USB */
+		case TYPEC_DP_STATE_D:
+		case TYPEC_DP_STATE_F:
+			enable_usb = true;
+			enable_dp = true;
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+	} else if (usbss->mode == TYPEC_MODE_AUDIO) {
+		enable_audio = true;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	/* Disable all switches */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXP_TO_MGX_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXM_TO_MGX_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_DPR_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_DNL_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_SENSE_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_MIC_SWITCHES |
+				WCD_USBSS_SWITCH_SETTINGS_ENABLE_AGND_SWITCHES);
+	if (ret)
+		return ret;
+
+	/* Clear switches */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+				WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_SENSE_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_MIC_SWITCHES);
+	if (ret)
+		return ret;
+
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT1,
+				WCD_USBSS_SWITCH_SELECT1_AGND_SWITCHES);
+	if (ret)
+		return ret;
+
+	/* Enable OVP_MG1_BIAS PCOMP_DYN_BST_EN */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_MG1_BIAS,
+			      WCD_USBSS_MG1_BIAS_PCOMP_DYN_BST_EN);
+	if (ret)
+		return ret;
+
+	/* Enable OVP_MG2_BIAS PCOMP_DYN_BST_EN */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_MG2_BIAS,
+			      WCD_USBSS_MG2_BIAS_PCOMP_DYN_BST_EN);
+	if (ret)
+		return ret;
+
+	/* Disable Equalizer in safe mode */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_EQUALIZER1,
+				WCD_USBSS_EQUALIZER1_EQ_EN);
+	if (ret)
+		return ret;
+
+	/* Start FSM with all disabled, force write */
+	ret = regmap_write_bits(usbss->regmap, WCD_USBSS_AUDIO_FSM_START,
+				WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG,
+				WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG);
+
+	/* 35us to allow the SBU switch to turn off */
+	usleep_range(35, 1000);
+
+	/* Setup Audio Accessory mux/switch */
+	if (enable_audio) {
+		int i;
+
+		/*
+		 * AATC switch configuration:
+		 * "Normal":
+		 * - R: DNR
+		 * - L: DNL
+		 * - Sense: GSBU2
+		 * - Mic: MG1
+		 * - AGND: MG2
+		 * "Swapped":
+		 * - R: DNR
+		 * - L: DNL
+		 * - Sense: GSBU1
+		 * - Mic: MG2
+		 * - AGND: MG1
+		 * Swapped information is given by the codec MBHC logic
+		 */
+
+		/* Set AATC mode */
+		ret = regmap_update_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+					 WCD_USBSS_USB_SS_CNTL_USB_SS_MODE,
+					 FIELD_PREP(WCD_USBSS_USB_SS_CNTL_USB_SS_MODE,
+						    WCD_USBSS_USB_SS_CNTL_USB_SS_MODE_AATC));
+		if (ret)
+			return ret;
+
+		/* Select L for DNL_SWITCHES and R for DPR_SWITCHES */
+		ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+				WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES |
+				WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES,
+				FIELD_PREP(WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES,
+					WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_L) |
+				FIELD_PREP(WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES,
+					WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_R));
+		if (ret)
+			return ret;
+
+		if (reverse)
+			/* Select MG2 for MIC, SBU1 for Sense */
+			ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+						 WCD_USBSS_SWITCH_SELECT0_MIC_SWITCHES,
+						 WCD_USBSS_SWITCH_SELECT0_MIC_SWITCHES);
+		else
+			/* Select MG1 for MIC, SBU2 for Sense */
+			ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+						 WCD_USBSS_SWITCH_SELECT0_SENSE_SWITCHES,
+						 WCD_USBSS_SWITCH_SELECT0_SENSE_SWITCHES);
+		if (ret)
+			return ret;
+
+		if (reverse)
+			/* Disable OVP_MG1_BIAS PCOMP_DYN_BST_EN */
+			ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_MG1_BIAS,
+						WCD_USBSS_MG1_BIAS_PCOMP_DYN_BST_EN);
+		else
+			/* Disable OVP_MG2_BIAS PCOMP_DYN_BST_EN */
+			ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_MG2_BIAS,
+						WCD_USBSS_MG2_BIAS_PCOMP_DYN_BST_EN);
+		if (ret)
+			return ret;
+
+		/*  Enable SENSE, MIC switches */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_SENSE_SWITCHES |
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_MIC_SWITCHES);
+		if (ret)
+			return ret;
+
+		if (reverse)
+			/* Select MG1 for AGND_SWITCHES */
+			ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT1,
+						WCD_USBSS_SWITCH_SELECT1_AGND_SWITCHES);
+		else
+			/* Select MG2 for AGND_SWITCHES */
+			ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT1,
+					      WCD_USBSS_SWITCH_SELECT1_AGND_SWITCHES);
+		if (ret)
+			return ret;
+
+		/* Enable AGND switches */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_AGND_SWITCHES);
+		if (ret)
+			return ret;
+
+		/* Enable DPR, DNL switches */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DNL_SWITCHES |
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DPR_SWITCHES);
+		if (ret)
+			return ret;
+
+		/* Setup FSM delays */
+		ret = regmap_write(usbss->regmap, WCD_USBSS_DELAY_L_SW, 0x02);
+		if (ret)
+			return ret;
+
+		ret = regmap_write(usbss->regmap, WCD_USBSS_DELAY_R_SW, 0x02);
+		if (ret)
+			return ret;
+
+		ret = regmap_write(usbss->regmap, WCD_USBSS_DELAY_MIC_SW, 0x01);
+		if (ret)
+			return ret;
+
+		/* Start FSM, force write */
+		ret = regmap_write_bits(usbss->regmap, WCD_USBSS_AUDIO_FSM_START,
+					WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG,
+					WCD_USBSS_AUDIO_FSM_START_AUDIO_FSM_AUDIO_TRIG);
+		if (ret)
+			return ret;
+
+		/* Default Linearlizer coefficients */
+		for (i = 0; i < ARRAY_SIZE(wcd939x_usbss_coeff_init); ++i)
+			regmap_update_bits(usbss->regmap,
+					   wcd939x_usbss_coeff_init[i].offset,
+					   wcd939x_usbss_coeff_init[i].mask,
+					   wcd939x_usbss_coeff_init[i].value);
+
+		return 0;
+	}
+
+	ret = regmap_update_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+				 WCD_USBSS_USB_SS_CNTL_USB_SS_MODE,
+				 FIELD_PREP(WCD_USBSS_USB_SS_CNTL_USB_SS_MODE,
+					    WCD_USBSS_USB_SS_CNTL_USB_SS_MODE_USB));
+	if (ret)
+		return ret;
+
+	/* Enable USB muxes */
+	if (enable_usb) {
+		/* Do not enable Equalizer in safe mode */
+		if (usbss->mode != TYPEC_STATE_SAFE) {
+			ret = regmap_set_bits(usbss->regmap, WCD_USBSS_EQUALIZER1,
+					      WCD_USBSS_EQUALIZER1_EQ_EN);
+			if (ret)
+				return ret;
+		}
+
+		/* Select DN for DNL_SWITCHES and DP for DPR_SWITCHES */
+		ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+					 WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES |
+					 WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES,
+					 FIELD_PREP(WCD_USBSS_SWITCH_SELECT0_DNL_SWITCHES,
+						    WCD_USBSS_SWITCH_SELECT0_DNL_SWITCH_DN) |
+					 FIELD_PREP(WCD_USBSS_SWITCH_SELECT0_DPR_SWITCHES,
+						    WCD_USBSS_SWITCH_SELECT0_DPR_SWITCH_DP));
+		if (ret)
+			return ret;
+
+		/* Enable DNL_SWITCHES and DPR_SWITCHES */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DPR_SWITCHES |
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DNL_SWITCHES);
+		if (ret)
+			return ret;
+	}
+
+	/* Enable DP AUX muxes */
+	if (enable_dp) {
+		/* Update Leakage Canceller Coefficient for AUXP pins */
+		ret = regmap_update_bits(usbss->regmap, WCD_USBSS_DISP_AUXP_CTL,
+					 WCD_USBSS_DISP_AUXP_CTL_LK_CANCEL_TRK_COEFF,
+					 FIELD_PREP(WCD_USBSS_DISP_AUXP_CTL_LK_CANCEL_TRK_COEFF,
+						    5));
+		if (ret)
+			return ret;
+
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_DISP_AUXP_THRESH,
+				      WCD_USBSS_DISP_AUXP_THRESH_DISP_AUXP_OVPON_CM);
+		if (ret)
+			return ret;
+
+		if (reverse)
+			/* Select MG2 for AUXP and MG1 for AUXM */
+			ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES |
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES,
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES);
+		else
+			/* Select MG1 for AUXP and MG2 for AUXM */
+			ret = regmap_update_bits(usbss->regmap, WCD_USBSS_SWITCH_SELECT0,
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXP_SWITCHES |
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES,
+						 WCD_USBSS_SWITCH_SELECT0_DP_AUXM_SWITCHES);
+		if (ret)
+			return ret;
+
+		/* Enable DP_AUXP_TO_MGX and DP_AUXM_TO_MGX switches */
+		ret = regmap_set_bits(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXP_TO_MGX_SWITCHES |
+				      WCD_USBSS_SWITCH_SETTINGS_ENABLE_DP_AUXM_TO_MGX_SWITCHES);
+
+		/* 15us to allow the SBU switch to turn on again */
+		usleep_range(15, 1000);
+	}
+
+	return 0;
+}
+
+static int wcd939x_usbss_switch_set(struct typec_switch_dev *sw,
+				    enum typec_orientation orientation)
+{
+	struct wcd939x_usbss *usbss = typec_switch_get_drvdata(sw);
+	int ret = 0;
+
+	mutex_lock(&usbss->lock);
+
+	if (usbss->orientation != orientation) {
+		usbss->orientation = orientation;
+
+		ret = wcd939x_usbss_set(usbss);
+	}
+
+	mutex_unlock(&usbss->lock);
+
+	if (ret)
+		return ret;
+
+	/* Report orientation to codec after switch has been done */
+	return typec_switch_set(usbss->codec_switch, orientation);
+}
+
+static int wcd939x_usbss_mux_set(struct typec_mux_dev *mux,
+				 struct typec_mux_state *state)
+{
+	struct wcd939x_usbss *usbss = typec_mux_get_drvdata(mux);
+	int ret = 0;
+
+	mutex_lock(&usbss->lock);
+
+	if (usbss->mode != state->mode) {
+		usbss->mode = state->mode;
+
+		if (state->alt)
+			usbss->svid = state->alt->svid;
+		else
+			usbss->svid = 0; // No SVID
+
+		ret = wcd939x_usbss_set(usbss);
+	}
+
+	mutex_unlock(&usbss->lock);
+
+	if (ret)
+		return ret;
+
+	/* Report event to codec after switch has been done */
+	return typec_mux_set(usbss->codec, state);
+}
+
+static int wcd939x_usbss_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct typec_switch_desc sw_desc = { };
+	struct typec_mux_desc mux_desc = { };
+	struct wcd939x_usbss *usbss;
+	int ret;
+
+	usbss = devm_kzalloc(dev, sizeof(*usbss), GFP_KERNEL);
+	if (!usbss)
+		return -ENOMEM;
+
+	usbss->client = client;
+	mutex_init(&usbss->lock);
+
+	usbss->regmap = devm_regmap_init_i2c(client, &wcd939x_usbss_regmap_config);
+	if (IS_ERR(usbss->regmap))
+		return dev_err_probe(dev, PTR_ERR(usbss->regmap), "failed to initialize regmap\n");
+
+	usbss->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(usbss->reset_gpio))
+		return dev_err_probe(dev, PTR_ERR(usbss->reset_gpio),
+				     "unable to acquire reset gpio\n");
+
+	usbss->vdd_supply = devm_regulator_get_optional(dev, "vdd");
+	if (IS_ERR(usbss->vdd_supply))
+		return PTR_ERR(usbss->vdd_supply);
+
+	/* Get Codec's MUX & Switch devices */
+	usbss->codec = fwnode_typec_mux_get(dev->fwnode);
+	if (IS_ERR(usbss->codec))
+		return dev_err_probe(dev, PTR_ERR(usbss->codec),
+				     "failed to acquire codec mode-switch\n");
+
+	usbss->codec_switch = fwnode_typec_switch_get(dev->fwnode);
+	if (IS_ERR(usbss->codec_switch)) {
+		ret = dev_err_probe(dev, PTR_ERR(usbss->codec_switch),
+				    "failed to acquire codec orientation-switch\n");
+		goto err_mux_put;
+	}
+
+	usbss->mode = TYPEC_STATE_SAFE;
+	usbss->orientation = TYPEC_ORIENTATION_NONE;
+
+	gpiod_set_value(usbss->reset_gpio, 1);
+
+	ret = regulator_enable(usbss->vdd_supply);
+	if (ret) {
+		dev_err(dev, "Failed to enable vdd: %d\n", ret);
+		goto err_mux_switch;
+	}
+
+	msleep(20);
+
+	gpiod_set_value(usbss->reset_gpio, 0);
+
+	msleep(20);
+
+	/* Disable standby */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+				WCD_USBSS_USB_SS_CNTL_STANDBY_STATE);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Set manual mode by default */
+	ret = regmap_update_bits(usbss->regmap, WCD_USBSS_FUNCTION_ENABLE,
+				 WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT,
+				 FIELD_PREP(WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT,
+					    WCD_USBSS_FUNCTION_ENABLE_SOURCE_SELECT_MANUAL));
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Enable dynamic boosting for DP and DN */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_DP_DN_MISC1,
+			      WCD_USBSS_DP_DN_MISC1_DP_PCOMP_2X_DYN_BST_ON_EN |
+			      WCD_USBSS_DP_DN_MISC1_DN_PCOMP_2X_DYN_BST_ON_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Enable dynamic boosting for MG1 OVP */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_MG1_MISC,
+			      WCD_USBSS_MG1_MISC_PCOMP_2X_DYN_BST_ON_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Enable dynamic boosting for MG2 OVP */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_MG2_MISC,
+			      WCD_USBSS_MG2_MISC_PCOMP_2X_DYN_BST_ON_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Write 0xFF to WCD_USBSS_CPLDO_CTL2 */
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_CPLDO_CTL2, 0xff);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Set RCO_EN: WCD_USBSS_USB_SS_CNTL Bit<3> --> 0x0 --> 0x1 */
+	ret = regmap_clear_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+				WCD_USBSS_USB_SS_CNTL_RCO_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	ret = regmap_set_bits(usbss->regmap, WCD_USBSS_USB_SS_CNTL,
+			      WCD_USBSS_USB_SS_CNTL_RCO_EN);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Disable all switches but enable the mux */
+	ret = regmap_write(usbss->regmap, WCD_USBSS_SWITCH_SETTINGS_ENABLE,
+			   WCD_USBSS_SWITCH_SETTINGS_ENABLE_DEVICE_ENABLE);
+	if (ret)
+		goto err_regulator_disable;
+
+	/* Setup in SAFE mode */
+	ret = wcd939x_usbss_set(usbss);
+	if (ret)
+		goto err_regulator_disable;
+
+	sw_desc.drvdata = usbss;
+	sw_desc.fwnode = dev_fwnode(dev);
+	sw_desc.set = wcd939x_usbss_switch_set;
+
+	usbss->sw = typec_switch_register(dev, &sw_desc);
+	if (IS_ERR(usbss->sw)) {
+		ret = dev_err_probe(dev, PTR_ERR(usbss->sw), "failed to register typec switch\n");
+		goto err_regulator_disable;
+	}
+
+	mux_desc.drvdata = usbss;
+	mux_desc.fwnode = dev_fwnode(dev);
+	mux_desc.set = wcd939x_usbss_mux_set;
+
+	usbss->mux = typec_mux_register(dev, &mux_desc);
+	if (IS_ERR(usbss->mux)) {
+		ret = dev_err_probe(dev, PTR_ERR(usbss->mux), "failed to register typec mux\n");
+		goto err_switch_unregister;
+	}
+
+	i2c_set_clientdata(client, usbss);
+
+	return 0;
+
+err_switch_unregister:
+	typec_switch_unregister(usbss->sw);
+
+err_regulator_disable:
+	regulator_disable(usbss->vdd_supply);
+
+err_mux_switch:
+	typec_switch_put(usbss->codec_switch);
+
+err_mux_put:
+	typec_mux_put(usbss->codec);
+
+	return ret;
+}
+
+static void wcd939x_usbss_remove(struct i2c_client *client)
+{
+	struct wcd939x_usbss *usbss = i2c_get_clientdata(client);
+
+	typec_mux_unregister(usbss->mux);
+	typec_switch_unregister(usbss->sw);
+
+	regulator_disable(usbss->vdd_supply);
+
+	typec_switch_put(usbss->codec_switch);
+	typec_mux_put(usbss->codec);
+}
+
+static const struct i2c_device_id wcd939x_usbss_table[] = {
+	{ "wcd9390-usbss" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, wcd939x_usbss_table);
+
+static const struct of_device_id wcd939x_usbss_of_table[] = {
+	{ .compatible = "qcom,wcd9390-usbss" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wcd939x_usbss_of_table);
+
+static struct i2c_driver wcd939x_usbss_driver = {
+	.driver = {
+		.name = "wcd939x-usbss",
+		.of_match_table = wcd939x_usbss_of_table,
+	},
+	.probe		= wcd939x_usbss_probe,
+	.remove		= wcd939x_usbss_remove,
+	.id_table	= wcd939x_usbss_table,
+};
+module_i2c_driver(wcd939x_usbss_driver);
+
+MODULE_DESCRIPTION("Qualcomm WCD939x USBSS driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From b8fb6db6cb04e3c35d661d0f6cf6f8dc7444ce0c Mon Sep 17 00:00:00 2001
From: Perr Zhang <perr@usb7.net>
Date: Wed, 13 Dec 2023 19:21:06 +0800
Subject: [PATCH 1390/4076] usb: f_uac1: adds support for SS and SSP

Patch adds support of SS and SSP speed.
Tested with rockchip rk3399 dwc3

Signed-off-by: Perr Zhang <perr@usb7.net>
Link: https://lore.kernel.org/r/20231213112106.605260-1-strongbox8@zoho.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uac1.c | 77 +++++++++++++++++++++++++++-
 1 file changed, 75 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/f_uac1.c b/drivers/usb/gadget/function/f_uac1.c
index 6f0e1d803dc24..78634ea7863a7 100644
--- a/drivers/usb/gadget/function/f_uac1.c
+++ b/drivers/usb/gadget/function/f_uac1.c
@@ -292,6 +292,77 @@ static struct usb_descriptor_header *f_audio_desc[] = {
 	NULL,
 };
 
+/* Standard ISO OUT Endpoint Descriptor */
+static struct usb_endpoint_descriptor ss_as_out_ep_desc  = {
+	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
+	.bDescriptorType =	USB_DT_ENDPOINT,
+	.bEndpointAddress =	USB_DIR_OUT,
+	.bmAttributes =		USB_ENDPOINT_SYNC_ADAPTIVE
+				| USB_ENDPOINT_XFER_ISOC,
+	.wMaxPacketSize	=	cpu_to_le16(UAC1_OUT_EP_MAX_PACKET_SIZE),
+	.bInterval =		4,
+};
+
+static struct usb_ss_ep_comp_descriptor ss_as_out_ep_desc_comp = {
+	.bLength		= sizeof(ss_as_out_ep_desc_comp),
+	.bDescriptorType	= USB_DT_SS_ENDPOINT_COMP,
+	.bMaxBurst		= 0,
+	.bmAttributes		= 0,
+	/* wBytesPerInterval = DYNAMIC */
+};
+
+/* Standard ISO OUT Endpoint Descriptor */
+static struct usb_endpoint_descriptor ss_as_in_ep_desc  = {
+	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
+	.bDescriptorType =	USB_DT_ENDPOINT,
+	.bEndpointAddress =	USB_DIR_IN,
+	.bmAttributes =		USB_ENDPOINT_SYNC_ASYNC
+				| USB_ENDPOINT_XFER_ISOC,
+	.wMaxPacketSize	=	cpu_to_le16(UAC1_OUT_EP_MAX_PACKET_SIZE),
+	.bInterval =		4,
+};
+
+static struct usb_ss_ep_comp_descriptor ss_as_in_ep_desc_comp = {
+	.bLength		= sizeof(ss_as_in_ep_desc_comp),
+	.bDescriptorType	= USB_DT_SS_ENDPOINT_COMP,
+	.bMaxBurst		= 0,
+	.bmAttributes		= 0,
+	/* wBytesPerInterval = DYNAMIC */
+};
+
+static struct usb_descriptor_header *f_audio_ss_desc[] = {
+	(struct usb_descriptor_header *)&ac_interface_desc,
+	(struct usb_descriptor_header *)&ac_header_desc,
+
+	(struct usb_descriptor_header *)&usb_out_it_desc,
+	(struct usb_descriptor_header *)&io_out_ot_desc,
+	(struct usb_descriptor_header *)&io_in_it_desc,
+	(struct usb_descriptor_header *)&usb_in_ot_desc,
+
+	(struct usb_descriptor_header *)&as_out_interface_alt_0_desc,
+	(struct usb_descriptor_header *)&as_out_interface_alt_1_desc,
+	(struct usb_descriptor_header *)&as_out_header_desc,
+
+	(struct usb_descriptor_header *)&as_out_type_i_desc,
+
+	//(struct usb_descriptor_header *)&as_out_ep_desc,
+	(struct usb_descriptor_header *)&ss_as_out_ep_desc,
+	(struct usb_descriptor_header *)&ss_as_out_ep_desc_comp,
+	(struct usb_descriptor_header *)&as_iso_out_desc,
+
+	(struct usb_descriptor_header *)&as_in_interface_alt_0_desc,
+	(struct usb_descriptor_header *)&as_in_interface_alt_1_desc,
+	(struct usb_descriptor_header *)&as_in_header_desc,
+
+	(struct usb_descriptor_header *)&as_in_type_i_desc,
+
+	//(struct usb_descriptor_header *)&as_in_ep_desc,
+	(struct usb_descriptor_header *)&ss_as_in_ep_desc,
+	(struct usb_descriptor_header *)&ss_as_in_ep_desc_comp,
+	(struct usb_descriptor_header *)&as_iso_in_desc,
+	NULL,
+};
+
 enum {
 	STR_AC_IF,
 	STR_USB_OUT_IT,
@@ -1352,6 +1423,7 @@ static int f_audio_bind(struct usb_configuration *c, struct usb_function *f)
 		ep = usb_ep_autoconfig(cdev->gadget, &as_out_ep_desc);
 		if (!ep)
 			goto err_free_fu;
+		ss_as_out_ep_desc.bEndpointAddress = as_out_ep_desc.bEndpointAddress;
 		audio->out_ep = ep;
 		audio->out_ep->desc = &as_out_ep_desc;
 	}
@@ -1360,6 +1432,7 @@ static int f_audio_bind(struct usb_configuration *c, struct usb_function *f)
 		ep = usb_ep_autoconfig(cdev->gadget, &as_in_ep_desc);
 		if (!ep)
 			goto err_free_fu;
+		ss_as_in_ep_desc.bEndpointAddress = as_in_ep_desc.bEndpointAddress;
 		audio->in_ep = ep;
 		audio->in_ep->desc = &as_in_ep_desc;
 	}
@@ -1367,8 +1440,8 @@ static int f_audio_bind(struct usb_configuration *c, struct usb_function *f)
 	setup_descriptor(audio_opts);
 
 	/* copy descriptors, and track endpoint copies */
-	status = usb_assign_descriptors(f, f_audio_desc, f_audio_desc, NULL,
-					NULL);
+	status = usb_assign_descriptors(f, f_audio_desc, f_audio_desc, f_audio_ss_desc,
+					f_audio_ss_desc);
 	if (status)
 		goto err_free_fu;
 
-- 
GitLab


From 0466e7e693efe6647f23532529a9c41a1fa5f4ac Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:30 +0000
Subject: [PATCH 1391/4076] usb: gadget: configfs: Replace snprintf() with the
 safer scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-2-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/configfs.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index b7d2a1313a684..ce3cfa1f36f51 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -606,10 +606,11 @@ static struct config_group *function_make(
 	char *instance_name;
 	int ret;
 
-	ret = snprintf(buf, MAX_NAME_LEN, "%s", name);
-	if (ret >= MAX_NAME_LEN)
+	if (strlen(name) >= MAX_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
+	scnprintf(buf, MAX_NAME_LEN, "%s", name);
+
 	func_name = buf;
 	instance_name = strchr(func_name, '.');
 	if (!instance_name) {
@@ -701,10 +702,12 @@ static struct config_group *config_desc_make(
 	int ret;
 
 	gi = container_of(group, struct gadget_info, configs_group);
-	ret = snprintf(buf, MAX_NAME_LEN, "%s", name);
-	if (ret >= MAX_NAME_LEN)
+
+	if (strlen(name) >= MAX_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
+	scnprintf(buf, MAX_NAME_LEN, "%s", name);
+
 	num_str = strchr(buf, '.');
 	if (!num_str) {
 		pr_err("Unable to locate . in name.bConfigurationValue\n");
-- 
GitLab


From c1a371866db9c44ab3004b5fc06df066a1b96262 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:31 +0000
Subject: [PATCH 1392/4076] usb: gadget: f_uac1: Replace snprintf() with the
 safer scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Ruslan Bilovol <ruslan.bilovol@gmail.com>
Cc: Julian Scheel <julian@jusst.de>
Cc: Bryan Wu <cooloney@kernel.org>
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-3-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uac1.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/gadget/function/f_uac1.c b/drivers/usb/gadget/function/f_uac1.c
index 78634ea7863a7..7de74a3dd3921 100644
--- a/drivers/usb/gadget/function/f_uac1.c
+++ b/drivers/usb/gadget/function/f_uac1.c
@@ -1634,7 +1634,7 @@ static ssize_t f_uac1_opts_##name##_show(struct config_item *item,	\
 	int result;							\
 									\
 	mutex_lock(&opts->lock);					\
-	result = snprintf(page, sizeof(opts->name), "%s", opts->name);	\
+	result = scnprintf(page, sizeof(opts->name), "%s", opts->name);	\
 	mutex_unlock(&opts->lock);					\
 									\
 	return result;							\
@@ -1652,7 +1652,7 @@ static ssize_t f_uac1_opts_##name##_store(struct config_item *item,	\
 		goto end;						\
 	}								\
 									\
-	ret = snprintf(opts->name, min(sizeof(opts->name), len),	\
+	ret = scnprintf(opts->name, min(sizeof(opts->name), len),	\
 			"%s", page);					\
 									\
 end:									\
@@ -1758,7 +1758,7 @@ static struct usb_function_instance *f_audio_alloc_inst(void)
 
 	opts->req_number = UAC1_DEF_REQ_NUM;
 
-	snprintf(opts->function_name, sizeof(opts->function_name), "AC Interface");
+	scnprintf(opts->function_name, sizeof(opts->function_name), "AC Interface");
 
 	return &opts->func_inst;
 }
-- 
GitLab


From 60034e0aedf507888c4a880f57011bb7f5d7700c Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:32 +0000
Subject: [PATCH 1393/4076] usb: gadget: f_uac2: Replace snprintf() with the
 safer scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: James Gruber <jimmyjgruber@gmail.com>
Cc: Yadwinder Singh <yadi.brar01@gmail.com>
Cc: Jaswinder Singh <jaswinder.singh@linaro.org>
Cc: Ruslan Bilovol <ruslan.bilovol@gmail.com>
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-4-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uac2.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index f9a0f07a7476b..383f6854cfec5 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -2045,7 +2045,7 @@ static ssize_t f_uac2_opts_##name##_show(struct config_item *item,	\
 	int result;							\
 									\
 	mutex_lock(&opts->lock);					\
-	result = snprintf(page, sizeof(opts->name), "%s", opts->name);	\
+	result = scnprintf(page, sizeof(opts->name), "%s", opts->name);	\
 	mutex_unlock(&opts->lock);					\
 									\
 	return result;							\
@@ -2063,7 +2063,7 @@ static ssize_t f_uac2_opts_##name##_store(struct config_item *item,	\
 		goto end;						\
 	}								\
 									\
-	ret = snprintf(opts->name, min(sizeof(opts->name), len),	\
+	ret = scnprintf(opts->name, min(sizeof(opts->name), len),	\
 			"%s", page);					\
 									\
 end:									\
@@ -2187,7 +2187,7 @@ static struct usb_function_instance *afunc_alloc_inst(void)
 	opts->req_number = UAC2_DEF_REQ_NUM;
 	opts->fb_max = FBACK_FAST_MAX;
 
-	snprintf(opts->function_name, sizeof(opts->function_name), "Source/Sink");
+	scnprintf(opts->function_name, sizeof(opts->function_name), "Source/Sink");
 
 	opts->p_terminal_type = UAC2_DEF_P_TERM_TYPE;
 	opts->c_terminal_type = UAC2_DEF_C_TERM_TYPE;
-- 
GitLab


From 0d12c1cca7883620b1888ce4b892a9ed27bf3682 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:33 +0000
Subject: [PATCH 1394/4076] usb: gadget: uvc: Replace snprintf() with the safer
 scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Daniel Scally <dan.scally@ideasonboard.com>
Cc: Andrzej Pietrasiewicz <andrzejtp2010@gmail.com>
Signed-off-by: Lee Jones <lee@kernel.org>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://lore.kernel.org/r/20231213164246.1021885-5-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc_configfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c
index 9bf0e985acfab..7e704b2bcfd1c 100644
--- a/drivers/usb/gadget/function/uvc_configfs.c
+++ b/drivers/usb/gadget/function/uvc_configfs.c
@@ -3414,7 +3414,7 @@ static ssize_t f_uvc_opts_string_##cname##_show(struct config_item *item,\
 	int result;							\
 									\
 	mutex_lock(&opts->lock);					\
-	result = snprintf(page, sizeof(opts->aname), "%s", opts->aname);\
+	result = scnprintf(page, sizeof(opts->aname), "%s", opts->aname);\
 	mutex_unlock(&opts->lock);					\
 									\
 	return result;							\
-- 
GitLab


From d32dcb0659bcb3b68878a985280024ec92d0db5b Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:34 +0000
Subject: [PATCH 1395/4076] usb: gadget: udc: atmel: Replace snprintf() with
 the safer scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Cristian Birsan <cristian.birsan@microchip.com>
Cc: Nicolas Ferre <nicolas.ferre@microchip.com>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Cc:  <linux-arm-kernel@lists.infradead.org>
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-6-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/atmel_usba_udc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 02b1bef5e22e2..b76885d78e8a7 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -94,7 +94,7 @@ static ssize_t queue_dbg_read(struct file *file, char __user *buf,
 
 	inode_lock(file_inode(file));
 	list_for_each_entry_safe(req, tmp_req, queue, queue) {
-		len = snprintf(tmpbuf, sizeof(tmpbuf),
+		len = scnprintf(tmpbuf, sizeof(tmpbuf),
 				"%8p %08x %c%c%c %5d %c%c%c\n",
 				req->req.buf, req->req.length,
 				req->req.no_interrupt ? 'i' : 'I',
@@ -104,7 +104,6 @@ static ssize_t queue_dbg_read(struct file *file, char __user *buf,
 				req->submitted ? 'F' : 'f',
 				req->using_dma ? 'D' : 'd',
 				req->last_transaction ? 'L' : 'l');
-		len = min(len, sizeof(tmpbuf));
 		if (len > nbytes)
 			break;
 
-- 
GitLab


From 01dc7f7c29be8b4fa853eb300f54065d981b31a9 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:35 +0000
Subject: [PATCH 1396/4076] usb: cdns2: Replace snprintf() with the safer
 scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Pawel Laszczak <pawell@cadence.com>
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-7-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/cdns2/cdns2-debug.h | 138 ++++++++++-----------
 1 file changed, 69 insertions(+), 69 deletions(-)

diff --git a/drivers/usb/gadget/udc/cdns2/cdns2-debug.h b/drivers/usb/gadget/udc/cdns2/cdns2-debug.h
index be9ae0d28a409..f5f330004190e 100644
--- a/drivers/usb/gadget/udc/cdns2/cdns2-debug.h
+++ b/drivers/usb/gadget/udc/cdns2/cdns2-debug.h
@@ -16,34 +16,34 @@ static inline const char *cdns2_decode_usb_irq(char *str, size_t size,
 {
 	int ret;
 
-	ret = snprintf(str, size, "usbirq: 0x%02x - ", usb_irq);
+	ret = scnprintf(str, size, "usbirq: 0x%02x - ", usb_irq);
 
 	if (usb_irq & USBIRQ_SOF)
-		ret += snprintf(str + ret, size - ret, "SOF ");
+		ret += scnprintf(str + ret, size - ret, "SOF ");
 	if (usb_irq & USBIRQ_SUTOK)
-		ret += snprintf(str + ret, size - ret, "SUTOK ");
+		ret += scnprintf(str + ret, size - ret, "SUTOK ");
 	if (usb_irq & USBIRQ_SUDAV)
-		ret += snprintf(str + ret, size - ret, "SETUP ");
+		ret += scnprintf(str + ret, size - ret, "SETUP ");
 	if (usb_irq & USBIRQ_SUSPEND)
-		ret += snprintf(str + ret, size - ret, "Suspend ");
+		ret += scnprintf(str + ret, size - ret, "Suspend ");
 	if (usb_irq & USBIRQ_URESET)
-		ret += snprintf(str + ret, size - ret, "Reset ");
+		ret += scnprintf(str + ret, size - ret, "Reset ");
 	if (usb_irq & USBIRQ_HSPEED)
-		ret += snprintf(str + ret, size - ret, "HS ");
+		ret += scnprintf(str + ret, size - ret, "HS ");
 	if (usb_irq & USBIRQ_LPM)
-		ret += snprintf(str + ret, size - ret, "LPM ");
+		ret += scnprintf(str + ret, size - ret, "LPM ");
 
-	ret += snprintf(str + ret, size - ret, ", EXT: 0x%02x - ", ext_irq);
+	ret += scnprintf(str + ret, size - ret, ", EXT: 0x%02x - ", ext_irq);
 
 	if (ext_irq & EXTIRQ_WAKEUP)
-		ret += snprintf(str + ret, size - ret, "Wakeup ");
+		ret += scnprintf(str + ret, size - ret, "Wakeup ");
 	if (ext_irq & EXTIRQ_VBUSFAULT_FALL)
-		ret += snprintf(str + ret, size - ret, "VBUS_FALL ");
+		ret += scnprintf(str + ret, size - ret, "VBUS_FALL ");
 	if (ext_irq & EXTIRQ_VBUSFAULT_RISE)
-		ret += snprintf(str + ret, size - ret, "VBUS_RISE ");
+		ret += scnprintf(str + ret, size - ret, "VBUS_RISE ");
 
-	if (ret >= size)
-		pr_info("CDNS2: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNS2: buffer may be truncated.\n");
 
 	return str;
 }
@@ -54,28 +54,28 @@ static inline const char *cdns2_decode_dma_irq(char *str, size_t size,
 {
 	int ret;
 
-	ret = snprintf(str, size, "ISTS: %08x, %s: %08x ",
-		       ep_ists, ep_name, ep_sts);
+	ret = scnprintf(str, size, "ISTS: %08x, %s: %08x ",
+			ep_ists, ep_name, ep_sts);
 
 	if (ep_sts & DMA_EP_STS_IOC)
-		ret += snprintf(str + ret, size - ret, "IOC ");
+		ret += scnprintf(str + ret, size - ret, "IOC ");
 	if (ep_sts & DMA_EP_STS_ISP)
-		ret += snprintf(str + ret, size - ret, "ISP ");
+		ret += scnprintf(str + ret, size - ret, "ISP ");
 	if (ep_sts & DMA_EP_STS_DESCMIS)
-		ret += snprintf(str + ret, size - ret, "DESCMIS ");
+		ret += scnprintf(str + ret, size - ret, "DESCMIS ");
 	if (ep_sts & DMA_EP_STS_TRBERR)
-		ret += snprintf(str + ret, size - ret, "TRBERR ");
+		ret += scnprintf(str + ret, size - ret, "TRBERR ");
 	if (ep_sts & DMA_EP_STS_OUTSMM)
-		ret += snprintf(str + ret, size - ret, "OUTSMM ");
+		ret += scnprintf(str + ret, size - ret, "OUTSMM ");
 	if (ep_sts & DMA_EP_STS_ISOERR)
-		ret += snprintf(str + ret, size - ret, "ISOERR ");
+		ret += scnprintf(str + ret, size - ret, "ISOERR ");
 	if (ep_sts & DMA_EP_STS_DBUSY)
-		ret += snprintf(str + ret, size - ret, "DBUSY ");
+		ret += scnprintf(str + ret, size - ret, "DBUSY ");
 	if (DMA_EP_STS_CCS(ep_sts))
-		ret += snprintf(str + ret, size - ret, "CCS ");
+		ret += scnprintf(str + ret, size - ret, "CCS ");
 
-	if (ret >= size)
-		pr_info("CDNS2: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNS2: buffer may be truncated.\n");
 
 	return str;
 }
@@ -105,43 +105,43 @@ static inline const char *cdns2_raw_ring(struct cdns2_endpoint *pep,
 	int ret;
 	int i;
 
-	ret = snprintf(str, size, "\n\t\tTR for %s:", pep->name);
+	ret = scnprintf(str, size, "\n\t\tTR for %s:", pep->name);
 
 	trb = &trbs[ring->dequeue];
 	dma = cdns2_trb_virt_to_dma(pep, trb);
-	ret += snprintf(str + ret, size - ret,
-			"\n\t\tRing deq index: %d, trb: V=%p, P=0x%pad\n",
-			ring->dequeue, trb, &dma);
+	ret += scnprintf(str + ret, size - ret,
+			 "\n\t\tRing deq index: %d, trb: V=%p, P=0x%pad\n",
+			 ring->dequeue, trb, &dma);
 
 	trb = &trbs[ring->enqueue];
 	dma = cdns2_trb_virt_to_dma(pep, trb);
-	ret += snprintf(str + ret, size - ret,
-			"\t\tRing enq index: %d, trb: V=%p, P=0x%pad\n",
-			ring->enqueue, trb, &dma);
+	ret += scnprintf(str + ret, size - ret,
+			 "\t\tRing enq index: %d, trb: V=%p, P=0x%pad\n",
+			 ring->enqueue, trb, &dma);
 
-	ret += snprintf(str + ret, size - ret,
-			"\t\tfree trbs: %d, CCS=%d, PCS=%d\n",
-			ring->free_trbs, ring->ccs, ring->pcs);
+	ret += scnprintf(str + ret, size - ret,
+			 "\t\tfree trbs: %d, CCS=%d, PCS=%d\n",
+			 ring->free_trbs, ring->ccs, ring->pcs);
 
 	if (TRBS_PER_SEGMENT > 40) {
-		ret += snprintf(str + ret, size - ret,
-				"\t\tTransfer ring %d too big\n", TRBS_PER_SEGMENT);
+		ret += scnprintf(str + ret, size - ret,
+				 "\t\tTransfer ring %d too big\n", TRBS_PER_SEGMENT);
 		return str;
 	}
 
 	dma = ring->dma;
 	for (i = 0; i < TRBS_PER_SEGMENT; ++i) {
 		trb = &trbs[i];
-		ret += snprintf(str + ret, size - ret,
-				"\t\t@%pad %08x %08x %08x\n", &dma,
-				le32_to_cpu(trb->buffer),
-				le32_to_cpu(trb->length),
-				le32_to_cpu(trb->control));
+		ret += scnprintf(str + ret, size - ret,
+				 "\t\t@%pad %08x %08x %08x\n", &dma,
+				 le32_to_cpu(trb->buffer),
+				 le32_to_cpu(trb->length),
+				 le32_to_cpu(trb->control));
 		dma += sizeof(*trb);
 	}
 
-	if (ret >= size)
-		pr_info("CDNS2: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNS2: buffer may be truncated.\n");
 
 	return str;
 }
@@ -166,36 +166,36 @@ static inline const char *cdns2_decode_trb(char *str, size_t size, u32 flags,
 
 	switch (type) {
 	case TRB_LINK:
-		ret = snprintf(str, size,
-			       "LINK %08x type '%s' flags %c:%c:%c%c:%c",
-			       buffer, cdns2_trb_type_string(type),
-			       flags & TRB_CYCLE ? 'C' : 'c',
-			       flags & TRB_TOGGLE ? 'T' : 't',
-			       flags & TRB_CHAIN ? 'C' : 'c',
-			       flags & TRB_CHAIN ? 'H' : 'h',
-			       flags & TRB_IOC ? 'I' : 'i');
+		ret = scnprintf(str, size,
+				"LINK %08x type '%s' flags %c:%c:%c%c:%c",
+				buffer, cdns2_trb_type_string(type),
+				flags & TRB_CYCLE ? 'C' : 'c',
+				flags & TRB_TOGGLE ? 'T' : 't',
+				flags & TRB_CHAIN ? 'C' : 'c',
+				flags & TRB_CHAIN ? 'H' : 'h',
+				flags & TRB_IOC ? 'I' : 'i');
 		break;
 	case TRB_NORMAL:
-		ret = snprintf(str, size,
-			       "type: '%s', Buffer: %08x, length: %ld, burst len: %ld, "
-			       "flags %c:%c:%c%c:%c",
-			       cdns2_trb_type_string(type),
-			       buffer, TRB_LEN(length),
-			       TRB_FIELD_TO_BURST(length),
-			       flags & TRB_CYCLE ? 'C' : 'c',
-			       flags & TRB_ISP ? 'I' : 'i',
-			       flags & TRB_CHAIN ? 'C' : 'c',
-			       flags & TRB_CHAIN ? 'H' : 'h',
-			       flags & TRB_IOC ? 'I' : 'i');
+		ret = scnprintf(str, size,
+				"type: '%s', Buffer: %08x, length: %ld, burst len: %ld, "
+				"flags %c:%c:%c%c:%c",
+				cdns2_trb_type_string(type),
+				buffer, TRB_LEN(length),
+				TRB_FIELD_TO_BURST(length),
+				flags & TRB_CYCLE ? 'C' : 'c',
+				flags & TRB_ISP ? 'I' : 'i',
+				flags & TRB_CHAIN ? 'C' : 'c',
+				flags & TRB_CHAIN ? 'H' : 'h',
+				flags & TRB_IOC ? 'I' : 'i');
 		break;
 	default:
-		ret = snprintf(str, size, "type '%s' -> raw %08x %08x %08x",
-			       cdns2_trb_type_string(type),
-			       buffer, length, flags);
+		ret = scnprintf(str, size, "type '%s' -> raw %08x %08x %08x",
+				cdns2_trb_type_string(type),
+				buffer, length, flags);
 	}
 
-	if (ret >= size)
-		pr_info("CDNS2: buffer overflowed.\n");
+	if (ret == size - 1)
+		pr_info("CDNS2: buffer may be truncated.\n");
 
 	return str;
 }
-- 
GitLab


From a6eef67cdb84e06112fc29176d6c6061d3ea8d79 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:36 +0000
Subject: [PATCH 1397/4076] usb: host: max3421-hcd: Replace snprintf() with the
 safer scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Cristian Birsan <cristian.birsan@microchip.com>
Cc: Nicolas Ferre <nicolas.ferre@microchip.com>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Cc:  <linux-arm-kernel@lists.infradead.org>
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-8-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/max3421-hcd.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c
index d152d72de1269..9fe4f48b18980 100644
--- a/drivers/usb/host/max3421-hcd.c
+++ b/drivers/usb/host/max3421-hcd.c
@@ -1158,12 +1158,12 @@ dump_eps(struct usb_hcd *hcd)
 		end = dp + sizeof(ubuf);
 		*dp = '\0';
 		list_for_each_entry(urb, &ep->urb_list, urb_list) {
-			ret = snprintf(dp, end - dp, " %p(%d.%s %d/%d)", urb,
-				       usb_pipetype(urb->pipe),
-				       usb_urb_dir_in(urb) ? "IN" : "OUT",
-				       urb->actual_length,
-				       urb->transfer_buffer_length);
-			if (ret < 0 || ret >= end - dp)
+			ret = scnprintf(dp, end - dp, " %p(%d.%s %d/%d)", urb,
+					usb_pipetype(urb->pipe),
+					usb_urb_dir_in(urb) ? "IN" : "OUT",
+					urb->actual_length,
+					urb->transfer_buffer_length);
+			if (ret == end - dp - 1)
 				break;	/* error or buffer full */
 			dp += ret;
 		}
@@ -1255,9 +1255,9 @@ max3421_handle_irqs(struct usb_hcd *hcd)
 			end = sbuf + sizeof(sbuf);
 			*dp = '\0';
 			for (i = 0; i < 16; ++i) {
-				int ret = snprintf(dp, end - dp, " %lu",
-						   max3421_hcd->err_stat[i]);
-				if (ret < 0 || ret >= end - dp)
+				int ret = scnprintf(dp, end - dp, " %lu",
+						    max3421_hcd->err_stat[i]);
+				if (ret == end - dp - 1)
 					break;	/* error or buffer full */
 				dp += ret;
 			}
-- 
GitLab


From 86b20af11e84c26ae3fde4dcc4f490948e3f8035 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:37 +0000
Subject: [PATCH 1398/4076] usb: yurex: Replace snprintf() with the safer
 scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Whilst we're at it, let's define some magic numbers to increase
readability and ease of maintenance.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Tomoki Sekiyama <tomoki.sekiyama@gmail.com>
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-9-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/yurex.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index c640f98d20c54..5a13cddace0e6 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -34,6 +34,8 @@
 #define YUREX_BUF_SIZE		8
 #define YUREX_WRITE_TIMEOUT	(HZ*2)
 
+#define MAX_S64_STRLEN 20 /* {-}922337203685477580{7,8} */
+
 /* table of devices that work with this driver */
 static struct usb_device_id yurex_table[] = {
 	{ USB_DEVICE(YUREX_VENDOR_ID, YUREX_PRODUCT_ID) },
@@ -401,7 +403,7 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 {
 	struct usb_yurex *dev;
 	int len = 0;
-	char in_buffer[20];
+	char in_buffer[MAX_S64_STRLEN];
 	unsigned long flags;
 
 	dev = file->private_data;
@@ -412,14 +414,14 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 		return -ENODEV;
 	}
 
+	if (WARN_ON_ONCE(dev->bbu > S64_MAX || dev->bbu < S64_MIN))
+		return -EIO;
+
 	spin_lock_irqsave(&dev->lock, flags);
-	len = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
+	scnprintf(in_buffer, MAX_S64_STRLEN, "%lld\n", dev->bbu);
 	spin_unlock_irqrestore(&dev->lock, flags);
 	mutex_unlock(&dev->io_mutex);
 
-	if (WARN_ON_ONCE(len >= sizeof(in_buffer)))
-		return -EIO;
-
 	return simple_read_from_buffer(buffer, count, ppos, in_buffer, len);
 }
 
-- 
GitLab


From 79632569619f4d57ff745398dba98e09105b5108 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:38 +0000
Subject: [PATCH 1399/4076] usb: mon_stat: Replace snprintf() with the safer
 scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-10-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/mon/mon_stat.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/mon/mon_stat.c b/drivers/usb/mon/mon_stat.c
index 98ab0cc473d67..3c23805ab1a44 100644
--- a/drivers/usb/mon/mon_stat.c
+++ b/drivers/usb/mon/mon_stat.c
@@ -35,9 +35,9 @@ static int mon_stat_open(struct inode *inode, struct file *file)
 
 	mbus = inode->i_private;
 
-	sp->slen = snprintf(sp->str, STAT_BUF_SIZE,
-	    "nreaders %d events %u text_lost %u\n",
-	    mbus->nreaders, mbus->cnt_events, mbus->cnt_text_lost);
+	sp->slen = scnprintf(sp->str, STAT_BUF_SIZE,
+			     "nreaders %d events %u text_lost %u\n",
+			     mbus->nreaders, mbus->cnt_events, mbus->cnt_text_lost);
 
 	file->private_data = sp;
 	return 0;
-- 
GitLab


From 9d4e3d15d7bf3439a6f3fb4aafc4f92ea2c5c5fd Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:39 +0000
Subject: [PATCH 1400/4076] usb: mon_text: Replace snprintf() with the safer
 scnprintf() variant

There is a general misunderstanding amongst engineers that {v}snprintf()
returns the length of the data *actually* encoded into the destination
array.  However, as per the C99 standard {v}snprintf() really returns
the length of the data that *would have been* written if there were
enough space for it.  This misunderstanding has led to buffer-overruns
in the past.  It's generally considered safer to use the {v}scnprintf()
variants in their place (or even sprintf() in simple cases).  So let's
do that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-11-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/mon/mon_text.c | 28 +++++-----------------------
 1 file changed, 5 insertions(+), 23 deletions(-)

diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c
index 39cb141646526..2fe9b95bac1d5 100644
--- a/drivers/usb/mon/mon_text.c
+++ b/drivers/usb/mon/mon_text.c
@@ -352,7 +352,7 @@ static int mon_text_open(struct inode *inode, struct file *file)
 	rp->r.rnf_error = mon_text_error;
 	rp->r.rnf_complete = mon_text_complete;
 
-	snprintf(rp->slab_name, SLAB_NAME_SZ, "mon_text_%p", rp);
+	scnprintf(rp->slab_name, SLAB_NAME_SZ, "mon_text_%p", rp);
 	rp->e_slab = kmem_cache_create(rp->slab_name,
 	    sizeof(struct mon_event_text), sizeof(long), 0,
 	    mon_text_ctor);
@@ -700,46 +700,28 @@ static const struct file_operations mon_fops_text_u = {
 
 int mon_text_add(struct mon_bus *mbus, const struct usb_bus *ubus)
 {
-	enum { NAMESZ = 10 };
+	enum { NAMESZ = 12 };
 	char name[NAMESZ];
 	int busnum = ubus? ubus->busnum: 0;
-	int rc;
 
 	if (mon_dir == NULL)
 		return 0;
 
 	if (ubus != NULL) {
-		rc = snprintf(name, NAMESZ, "%dt", busnum);
-		if (rc <= 0 || rc >= NAMESZ)
-			goto err_print_t;
+		scnprintf(name, NAMESZ, "%dt", busnum);
 		mbus->dent_t = debugfs_create_file(name, 0600, mon_dir, mbus,
 							     &mon_fops_text_t);
 	}
 
-	rc = snprintf(name, NAMESZ, "%du", busnum);
-	if (rc <= 0 || rc >= NAMESZ)
-		goto err_print_u;
+	scnprintf(name, NAMESZ, "%du", busnum);
 	mbus->dent_u = debugfs_create_file(name, 0600, mon_dir, mbus,
 					   &mon_fops_text_u);
 
-	rc = snprintf(name, NAMESZ, "%ds", busnum);
-	if (rc <= 0 || rc >= NAMESZ)
-		goto err_print_s;
+	scnprintf(name, NAMESZ, "%ds", busnum);
 	mbus->dent_s = debugfs_create_file(name, 0600, mon_dir, mbus,
 					   &mon_fops_stat);
 
 	return 1;
-
-err_print_s:
-	debugfs_remove(mbus->dent_u);
-	mbus->dent_u = NULL;
-err_print_u:
-	if (ubus != NULL) {
-		debugfs_remove(mbus->dent_t);
-		mbus->dent_t = NULL;
-	}
-err_print_t:
-	return 0;
 }
 
 void mon_text_del(struct mon_bus *mbus)
-- 
GitLab


From e5892ea81515366588e8fb00a5a3cdca687355dc Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:40 +0000
Subject: [PATCH 1401/4076] usb: phy: twl6030: Remove snprintf() from sysfs
 call-backs and replace with sysfs_emit()

Since snprintf() has the documented, but still rather strange trait of
returning the length of the data that *would have been* written to the
array if space were available, rather than the arguably more useful
length of data *actually* written, it is usually considered wise to use
something else instead in order to avoid confusion.

In the case of sysfs call-backs, new wrappers exist that do just that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Hema HK <hemahk@ti.com>
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/20231213164246.1021885-12-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/phy/phy-twl6030-usb.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c
index c3ce6b1054f1c..da09cff55abce 100644
--- a/drivers/usb/phy/phy-twl6030-usb.c
+++ b/drivers/usb/phy/phy-twl6030-usb.c
@@ -179,16 +179,16 @@ static ssize_t vbus_show(struct device *dev,
 
 	switch (twl->linkstat) {
 	case MUSB_VBUS_VALID:
-	       ret = snprintf(buf, PAGE_SIZE, "vbus\n");
+	       ret = sysfs_emit(buf, "vbus\n");
 	       break;
 	case MUSB_ID_GROUND:
-	       ret = snprintf(buf, PAGE_SIZE, "id\n");
+	       ret = sysfs_emit(buf, "id\n");
 	       break;
 	case MUSB_VBUS_OFF:
-	       ret = snprintf(buf, PAGE_SIZE, "none\n");
+	       ret = sysfs_emit(buf, "none\n");
 	       break;
 	default:
-	       ret = snprintf(buf, PAGE_SIZE, "UNKNOWN\n");
+	       ret = sysfs_emit(buf, "UNKNOWN\n");
 	}
 	spin_unlock_irqrestore(&twl->lock, flags);
 
-- 
GitLab


From 3e42084a1c4790364c28b5cafd5c66fc25396a64 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Wed, 13 Dec 2023 16:42:41 +0000
Subject: [PATCH 1402/4076] usb: storage: Remove snprintf() from sysfs
 call-backs and replace with sysfs_emit()

Since snprintf() has the documented, but still rather strange trait of
returning the length of the data that *would have been* written to the
array if space were available, rather than the arguably more useful
length of data *actually* written, it is usually considered wise to use
something else instead in order to avoid confusion.

In the case of sysfs call-backs, new wrappers exist that do just that.

Link: https://lwn.net/Articles/69419/
Link: https://github.com/KSPP/linux/issues/105
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc:  <usb-storage@lists.one-eyed-alien.net>
Signed-off-by: Lee Jones <lee@kernel.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231213164246.1021885-13-lee@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/storage/sierra_ms.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/storage/sierra_ms.c b/drivers/usb/storage/sierra_ms.c
index 0774ba22fb66e..177fa6cd143ab 100644
--- a/drivers/usb/storage/sierra_ms.c
+++ b/drivers/usb/storage/sierra_ms.c
@@ -98,26 +98,26 @@ static ssize_t truinst_show(struct device *dev, struct device_attribute *attr,
 	struct usb_device *udev = interface_to_usbdev(intf);
 	int result;
 	if (swi_tru_install == TRU_FORCE_MS) {
-		result = snprintf(buf, PAGE_SIZE, "Forced Mass Storage\n");
+		result = sysfs_emit(buf, "Forced Mass Storage\n");
 	} else {
 		swocInfo = kmalloc(sizeof(struct swoc_info), GFP_KERNEL);
 		if (!swocInfo) {
-			snprintf(buf, PAGE_SIZE, "Error\n");
+			sysfs_emit(buf, "Error\n");
 			return -ENOMEM;
 		}
 		result = sierra_get_swoc_info(udev, swocInfo);
 		if (result < 0) {
 			dev_dbg(dev, "SWIMS: failed SWoC query\n");
 			kfree(swocInfo);
-			snprintf(buf, PAGE_SIZE, "Error\n");
+			sysfs_emit(buf, "Error\n");
 			return -EIO;
 		}
 		debug_swoc(dev, swocInfo);
-		result = snprintf(buf, PAGE_SIZE,
-			"REV=%02d SKU=%04X VER=%04X\n",
-			swocInfo->rev,
-			swocInfo->LinuxSKU,
-			swocInfo->LinuxVer);
+		result = sysfs_emit(buf,
+				    "REV=%02d SKU=%04X VER=%04X\n",
+				    swocInfo->rev,
+				    swocInfo->LinuxSKU,
+				    swocInfo->LinuxVer);
 		kfree(swocInfo);
 	}
 	return result;
-- 
GitLab


From 61fbf20312bdd1394a9cac67ed8f706e205511af Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 14 Dec 2023 12:04:15 +0300
Subject: [PATCH 1403/4076] usb: gadget: f_fs: fix fortify warning

When compiling with gcc version 14.0.0 20231206 (experimental)
and CONFIG_FORTIFY_SOURCE=y, I've noticed the following warning:

...
In function 'fortify_memcpy_chk',
    inlined from '__ffs_func_bind_do_os_desc' at drivers/usb/gadget/function/f_fs.c:2934:3:
./include/linux/fortify-string.h:588:25: warning: call to '__read_overflow2_field'
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
  588 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

This call to 'memcpy()' is interpreted as an attempt to copy both
'CompatibleID' and 'SubCompatibleID' of 'struct usb_ext_compat_desc'
from an address of the first one, which causes an overread warning.
Since we actually want to copy both of them at once, use the
convenient 'struct_group()' and 'sizeof_field()' here.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://lore.kernel.org/r/20231214090428.27292-1-dmantipov@yandex.ru
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_fs.c  | 5 ++---
 include/uapi/linux/usb/functionfs.h | 6 ++++--
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index efe3e3b857695..dafedc33928dd 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2931,9 +2931,8 @@ static int __ffs_func_bind_do_os_desc(enum ffs_os_desc_type type,
 
 		t = &func->function.os_desc_table[desc->bFirstInterfaceNumber];
 		t->if_id = func->interfaces_nums[desc->bFirstInterfaceNumber];
-		memcpy(t->os_desc->ext_compat_id, &desc->CompatibleID,
-		       ARRAY_SIZE(desc->CompatibleID) +
-		       ARRAY_SIZE(desc->SubCompatibleID));
+		memcpy(t->os_desc->ext_compat_id, &desc->IDs,
+		       sizeof_field(struct usb_ext_compat_desc, IDs));
 		length = sizeof(*desc);
 	}
 		break;
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index d77ee6b65328e..078098e73fd3e 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -73,8 +73,10 @@ struct usb_os_desc_header {
 struct usb_ext_compat_desc {
 	__u8	bFirstInterfaceNumber;
 	__u8	Reserved1;
-	__u8	CompatibleID[8];
-	__u8	SubCompatibleID[8];
+	__struct_group(/* no tag */, IDs, /* no attrs */,
+		__u8	CompatibleID[8];
+		__u8	SubCompatibleID[8];
+	);
 	__u8	Reserved2[6];
 };
 
-- 
GitLab


From 776630be36935be3a51e5ecfa7fc7614c4d4e46e Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Thu, 14 Dec 2023 15:40:11 +0100
Subject: [PATCH 1404/4076] usb: cdns3: Use dev_err_probe

Create an error message or upon deferral add a description for sysfs.

Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Link: https://lore.kernel.org/r/20231214144011.1987586-1-alexander.stein@ew.tq-group.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-plat.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/cdns3/cdns3-plat.c b/drivers/usb/cdns3/cdns3-plat.c
index 2c1aca84f2264..3ef8e3c872a37 100644
--- a/drivers/usb/cdns3/cdns3-plat.c
+++ b/drivers/usb/cdns3/cdns3-plat.c
@@ -87,16 +87,20 @@ static int cdns3_plat_probe(struct platform_device *pdev)
 	cdns->dev_irq = platform_get_irq_byname(pdev, "peripheral");
 
 	if (cdns->dev_irq < 0)
-		return cdns->dev_irq;
+		return dev_err_probe(dev, cdns->dev_irq,
+				     "Failed to get peripheral IRQ\n");
 
 	regs = devm_platform_ioremap_resource_byname(pdev, "dev");
 	if (IS_ERR(regs))
-		return PTR_ERR(regs);
+		return dev_err_probe(dev, PTR_ERR(regs),
+				     "Failed to get dev base\n");
+
 	cdns->dev_regs	= regs;
 
 	cdns->otg_irq = platform_get_irq_byname(pdev, "otg");
 	if (cdns->otg_irq < 0)
-		return cdns->otg_irq;
+		return dev_err_probe(dev, cdns->otg_irq,
+				     "Failed to get otg IRQ\n");
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "otg");
 	if (!res) {
@@ -119,7 +123,8 @@ static int cdns3_plat_probe(struct platform_device *pdev)
 
 	cdns->usb2_phy = devm_phy_optional_get(dev, "cdns3,usb2-phy");
 	if (IS_ERR(cdns->usb2_phy))
-		return PTR_ERR(cdns->usb2_phy);
+		return dev_err_probe(dev, PTR_ERR(cdns->usb2_phy),
+				     "Failed to get cdn3,usb2-phy\n");
 
 	ret = phy_init(cdns->usb2_phy);
 	if (ret)
@@ -127,7 +132,8 @@ static int cdns3_plat_probe(struct platform_device *pdev)
 
 	cdns->usb3_phy = devm_phy_optional_get(dev, "cdns3,usb3-phy");
 	if (IS_ERR(cdns->usb3_phy))
-		return PTR_ERR(cdns->usb3_phy);
+		return dev_err_probe(dev, PTR_ERR(cdns->usb3_phy),
+				     "Failed to get cdn3,usb3-phy\n");
 
 	ret = phy_init(cdns->usb3_phy);
 	if (ret)
-- 
GitLab


From 4d2f8c859146672ce84f49648121c70ea84e246c Mon Sep 17 00:00:00 2001
From: Ghanshyam Agrawal <ghanshyam1898@gmail.com>
Date: Fri, 15 Dec 2023 14:09:30 +0530
Subject: [PATCH 1405/4076] usb: typec: fixed a typo

Fixed one typo.

Signed-off-by: Ghanshyam Agrawal <ghanshyam1898@gmail.com>
Link: https://lore.kernel.org/r/20231215083930.566164-1-ghanshyam1898@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/pd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/typec/pd.c b/drivers/usb/typec/pd.c
index 7f3d61f220f27..b9cca2be76fce 100644
--- a/drivers/usb/typec/pd.c
+++ b/drivers/usb/typec/pd.c
@@ -468,7 +468,7 @@ static struct device_type pd_capabilities_type = {
 /**
  * usb_power_delivery_register_capabilities - Register a set of capabilities.
  * @pd: The USB PD instance that the capabilities belong to.
- * @desc: Description of the Capablities Message.
+ * @desc: Description of the Capabilities Message.
  *
  * This function registers a Capabilities Message described in @desc. The
  * capabilities will have their own sub-directory under @pd in sysfs.
-- 
GitLab


From c51ffe929f3b34999ce19f413d3950ea72e1e5ad Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 14 Dec 2023 19:06:52 +0200
Subject: [PATCH 1406/4076] dt-bindings: usb: qcom,dwc3: Add X1E80100 binding

Add X1E80100 to the DT schema.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231214-x1e80100-usb-v1-1-c22be5c0109e@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/qcom,dwc3.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index 3ec62027f663c..473c4bfaf8a2a 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -47,6 +47,7 @@ properties:
           - qcom,sm8450-dwc3
           - qcom,sm8550-dwc3
           - qcom,sm8650-dwc3
+          - qcom,x1e80100-dwc3
       - const: qcom,dwc3
 
   reg:
@@ -264,6 +265,7 @@ allOf:
           contains:
             enum:
               - qcom,sc8280xp-dwc3
+              - qcom,x1e80100-dwc3
     then:
       properties:
         clocks:
@@ -459,6 +461,7 @@ allOf:
           contains:
             enum:
               - qcom,sc8280xp-dwc3
+              - qcom,x1e80100-dwc3
     then:
       properties:
         interrupts:
-- 
GitLab


From 9df1dd450689dccc19fa471b91c71fc977dab946 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Wed, 6 Dec 2023 13:28:41 -0300
Subject: [PATCH 1407/4076] dt-bindings: serial: imx: Properly describe the
 i.MX1 interrupts

i.MX1 has three UART interrupts instead of a single one like other
i.MX devices.

Take this into account for properly describing the i.MX1 UART
interrupts.

This fixes the following dt-schema warning:

	from schema $id: http://devicetree.org/schemas/serial/fsl-imx-uart.yaml#yaml#

imx1-ads.dtb: serial@206000: interrupts: [[30], [29], [26]] is too long
Signed-off-by: Fabio Estevam <festevam@denx.de>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231206162841.2326201-1-festevam@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../bindings/serial/fsl-imx-uart.yaml         | 29 +++++++++++++++----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
index 83035553044a2..9c6dc16f88a6f 100644
--- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
@@ -9,10 +9,6 @@ title: Freescale i.MX Universal Asynchronous Receiver/Transmitter (UART)
 maintainers:
   - Fabio Estevam <festevam@gmail.com>
 
-allOf:
-  - $ref: serial.yaml#
-  - $ref: rs485.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -68,7 +64,11 @@ properties:
       - const: tx
 
   interrupts:
-    maxItems: 1
+    items:
+      - description: UART RX Interrupt
+      - description: UART TX Interrupt
+      - description: UART RTS Interrupt
+    minItems: 1
 
   wakeup-source: true
 
@@ -110,6 +110,25 @@ required:
   - clock-names
   - interrupts
 
+allOf:
+  - $ref: serial.yaml#
+  - $ref: rs485.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: fsl,imx1-uart
+    then:
+      properties:
+        interrupts:
+          minItems: 3
+          maxItems: 3
+    else:
+      properties:
+        interrupts:
+          maxItems: 1
+
 unevaluatedProperties: false
 
 examples:
-- 
GitLab


From 2600d9939440d608e1c8128e9e47e7948c024442 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 7 Dec 2023 10:26:30 -0600
Subject: [PATCH 1408/4076] serial: esp32_acm: Add explicit platform_device.h
 include

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it was merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. Soon the implicit includes are going to be removed.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231207162632.2650356-1-robh@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/esp32_acm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/esp32_acm.c b/drivers/tty/serial/esp32_acm.c
index a4cbaedb51702..d4e8bdb1cdef1 100644
--- a/drivers/tty/serial/esp32_acm.c
+++ b/drivers/tty/serial/esp32_acm.c
@@ -8,7 +8,7 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/serial_core.h>
 #include <linux/slab.h>
 #include <linux/tty_flip.h>
-- 
GitLab


From 3d19ff562d0618a17c4f2c42c8fc84de4e2880e2 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 7 Dec 2023 10:26:31 -0600
Subject: [PATCH 1409/4076] serial: esp32_uart: Use device_get_match_data()

Use preferred device_get_match_data() instead of of_match_device() to
get the driver match data. With this, adjust the includes to explicitly
include the correct headers.

Error checking for matching was not necessary as matching is always
successful if we're already in probe and the match tables always have data
pointers.

Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231207162632.2650356-2-robh@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/esp32_uart.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/tty/serial/esp32_uart.c b/drivers/tty/serial/esp32_uart.c
index 6e12955d13158..6fc61f3233559 100644
--- a/drivers/tty/serial/esp32_uart.c
+++ b/drivers/tty/serial/esp32_uart.c
@@ -9,7 +9,8 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/serial_core.h>
 #include <linux/slab.h>
 #include <linux/tty_flip.h>
@@ -678,16 +679,11 @@ static struct uart_driver esp32_uart_reg = {
 static int esp32_uart_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	static const struct of_device_id *match;
 	struct uart_port *port;
 	struct esp32_port *sport;
 	struct resource *res;
 	int ret;
 
-	match = of_match_device(esp32_uart_dt_ids, &pdev->dev);
-	if (!match)
-		return -ENODEV;
-
 	sport = devm_kzalloc(&pdev->dev, sizeof(*sport), GFP_KERNEL);
 	if (!sport)
 		return -ENOMEM;
@@ -728,7 +724,7 @@ static int esp32_uart_probe(struct platform_device *pdev)
 	port->flags = UPF_BOOT_AUTOCONF;
 	port->has_sysrq = 1;
 	port->fifosize = ESP32_UART_TX_FIFO_SIZE;
-	port->private_data = (void *)match->data;
+	port->private_data = (void *)device_get_match_data(&pdev->dev);
 
 	esp32_uart_ports[port->line] = sport;
 
-- 
GitLab


From e0f25b8992345aa5f113da2815f5add98738c611 Mon Sep 17 00:00:00 2001
From: Adrian Reber <areber@redhat.com>
Date: Fri, 8 Dec 2023 15:36:56 +0100
Subject: [PATCH 1410/4076] tty: allow TIOCSLCKTRMIOS with
 CAP_CHECKPOINT_RESTORE

The capability CAP_CHECKPOINT_RESTORE was introduced to allow non-root
users to checkpoint and restore processes as non-root with CRIU.

This change extends CAP_CHECKPOINT_RESTORE to enable the CRIU option
'--shell-job' as non-root. CRIU's man-page describes the '--shell-job'
option like this:

  Allow one to dump shell jobs. This implies the restored task will
  inherit session and process group ID from the criu itself. This option
  also allows to migrate a single external tty connection, to migrate
  applications like top.

TIOCSLCKTRMIOS can only be done if the process has CAP_SYS_ADMIN and
this change extends it to CAP_SYS_ADMIN or CAP_CHECKPOINT_RESTORE.

With this change it is possible to checkpoint and restore processes
which have a tty connection as non-root if CAP_CHECKPOINT_RESTORE is
set.

Acked-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Adrian Reber <areber@redhat.com>
Acked-by: Andrei Vagin <avagin@gmail.com>
Link: https://lore.kernel.org/r/20231208143656.1019-1-areber@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_ioctl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 4b499301a3db1..85de90eebc7bb 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -844,7 +844,7 @@ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg)
 			ret = -EFAULT;
 		return ret;
 	case TIOCSLCKTRMIOS:
-		if (!capable(CAP_SYS_ADMIN))
+		if (!checkpoint_restore_ns_capable(&init_user_ns))
 			return -EPERM;
 		copy_termios_locked(real_tty, &kterm);
 		if (user_termios_to_kernel_termios(&kterm,
@@ -861,7 +861,7 @@ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg)
 			ret = -EFAULT;
 		return ret;
 	case TIOCSLCKTRMIOS:
-		if (!capable(CAP_SYS_ADMIN))
+		if (!checkpoint_restore_ns_capable(&init_user_ns))
 			return -EPERM;
 		copy_termios_locked(real_tty, &kterm);
 		if (user_termios_to_kernel_termios_1(&kterm,
-- 
GitLab


From 96d7e361ca4cb0e8b6fa0635a04609b6367257e6 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 10 Dec 2023 18:45:58 +0100
Subject: [PATCH 1411/4076] serdev: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/d20d3ac106bac6b7cabe39f22ad00ac86910e0a5.1702230342.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serdev/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index de8d87d4858d4..822a5cd055666 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -77,7 +77,7 @@ static bool is_serdev_device(const struct device *dev)
 static void serdev_ctrl_release(struct device *dev)
 {
 	struct serdev_controller *ctrl = to_serdev_controller(dev);
-	ida_simple_remove(&ctrl_ida, ctrl->nr);
+	ida_free(&ctrl_ida, ctrl->nr);
 	kfree(ctrl);
 }
 
@@ -489,7 +489,7 @@ struct serdev_controller *serdev_controller_alloc(struct device *host,
 	if (!ctrl)
 		return NULL;
 
-	id = ida_simple_get(&ctrl_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&ctrl_ida, GFP_KERNEL);
 	if (id < 0) {
 		dev_err(parent,
 			"unable to allocate serdev controller identifier.\n");
-- 
GitLab


From 6bcab3c8acc88e265c570dea969fd04f137c8a4c Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Mon, 11 Dec 2023 12:13:48 -0500
Subject: [PATCH 1412/4076] serial: sc16is7xx: remove wasteful static buffer in
 sc16is7xx_regmap_name()

Using a static buffer inside sc16is7xx_regmap_name() was a convenient and
simple way to set the regmap name without having to allocate and free a
buffer each time it is called. The drawback is that the static buffer
wastes memory for nothing once regmap is fully initialized.

Remove static buffer and use constant strings instead.

This also avoids a truncation warning when using "%d" or "%u" in snprintf
which was flagged by kernel test robot.

Fixes: 3837a0379533 ("serial: sc16is7xx: improve regmap debugfs by using one regmap per port")
Cc:  <stable@vger.kernel.org> # 6.1.x: 3837a03 serial: sc16is7xx: improve regmap debugfs by using one regmap per port
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231211171353.2901416-2-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 9cb503169a48a..8d1de4982b65a 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1708,13 +1708,15 @@ static struct regmap_config regcfg = {
 	.max_register = SC16IS7XX_EFCR_REG,
 };
 
-static const char *sc16is7xx_regmap_name(unsigned int port_id)
+static const char *sc16is7xx_regmap_name(u8 port_id)
 {
-	static char buf[6];
-
-	snprintf(buf, sizeof(buf), "port%d", port_id);
-
-	return buf;
+	switch (port_id) {
+	case 0:	return "port0";
+	case 1:	return "port1";
+	default:
+		WARN_ON(true);
+		return NULL;
+	}
 }
 
 static unsigned int sc16is7xx_regmap_port_mask(unsigned int port_id)
-- 
GitLab


From f6959c5217bd799bcb770b95d3c09b3244e175c6 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Mon, 11 Dec 2023 12:13:49 -0500
Subject: [PATCH 1413/4076] serial: sc16is7xx: remove global regmap from struct
 sc16is7xx_port

Remove global struct regmap so that it is more obvious that this
regmap is to be used only in the probe function.

Also add a comment to that effect in probe function.

Fixes: 3837a0379533 ("serial: sc16is7xx: improve regmap debugfs by using one regmap per port")
Cc:  <stable@vger.kernel.org>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231211171353.2901416-3-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 8d1de4982b65a..a4ad3ae8cae22 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -334,7 +334,6 @@ struct sc16is7xx_one {
 
 struct sc16is7xx_port {
 	const struct sc16is7xx_devtype	*devtype;
-	struct regmap			*regmap;
 	struct clk			*clk;
 #ifdef CONFIG_GPIOLIB
 	struct gpio_chip		gpio;
@@ -1434,7 +1433,8 @@ static void sc16is7xx_setup_irda_ports(struct sc16is7xx_port *s)
 /*
  * Configure ports designated to operate as modem control lines.
  */
-static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s)
+static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s,
+				       struct regmap *regmap)
 {
 	int i;
 	int ret;
@@ -1463,7 +1463,7 @@ static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s)
 
 	if (s->mctrl_mask)
 		regmap_update_bits(
-			s->regmap,
+			regmap,
 			SC16IS7XX_IOCONTROL_REG,
 			SC16IS7XX_IOCONTROL_MODEM_A_BIT |
 			SC16IS7XX_IOCONTROL_MODEM_B_BIT, s->mctrl_mask);
@@ -1495,6 +1495,10 @@ static int sc16is7xx_probe(struct device *dev,
 	 * This device does not have an identification register that would
 	 * tell us if we are really connected to the correct device.
 	 * The best we can do is to check if communication is at all possible.
+	 *
+	 * Note: regmap[0] is used in the probe function to access registers
+	 * common to all channels/ports, as it is guaranteed to be present on
+	 * all variants.
 	 */
 	ret = regmap_read(regmaps[0], SC16IS7XX_LSR_REG, &val);
 	if (ret < 0)
@@ -1530,7 +1534,6 @@ static int sc16is7xx_probe(struct device *dev,
 			return -EINVAL;
 	}
 
-	s->regmap = regmaps[0];
 	s->devtype = devtype;
 	dev_set_drvdata(dev, s);
 	mutex_init(&s->efr_lock);
@@ -1545,7 +1548,7 @@ static int sc16is7xx_probe(struct device *dev,
 	sched_set_fifo(s->kworker_task);
 
 	/* reset device, purging any pending irq / data */
-	regmap_write(s->regmap, SC16IS7XX_IOCONTROL_REG,
+	regmap_write(regmaps[0], SC16IS7XX_IOCONTROL_REG,
 		     SC16IS7XX_IOCONTROL_SRESET_BIT);
 
 	for (i = 0; i < devtype->nr_uart; ++i) {
@@ -1616,7 +1619,7 @@ static int sc16is7xx_probe(struct device *dev,
 
 	sc16is7xx_setup_irda_ports(s);
 
-	ret = sc16is7xx_setup_mctrl_ports(s);
+	ret = sc16is7xx_setup_mctrl_ports(s, regmaps[0]);
 	if (ret)
 		goto out_ports;
 
-- 
GitLab


From 41a308cbedb2a68a6831f0f2e992e296c4b8aff0 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Mon, 11 Dec 2023 12:13:50 -0500
Subject: [PATCH 1414/4076] serial: sc16is7xx: remove unused line structure
 member

Now that the driver has been converted to use one regmap per port, the line
structure member is no longer used, so remove it.

Fixes: 3837a0379533 ("serial: sc16is7xx: improve regmap debugfs by using one regmap per port")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231211171353.2901416-4-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index a4ad3ae8cae22..0a7a9aa5c9fae 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -322,7 +322,6 @@ struct sc16is7xx_one_config {
 
 struct sc16is7xx_one {
 	struct uart_port		port;
-	u8				line;
 	struct regmap			*regmap;
 	struct kthread_work		tx_work;
 	struct kthread_work		reg_work;
@@ -1552,7 +1551,6 @@ static int sc16is7xx_probe(struct device *dev,
 		     SC16IS7XX_IOCONTROL_SRESET_BIT);
 
 	for (i = 0; i < devtype->nr_uart; ++i) {
-		s->p[i].line		= i;
 		/* Initialize port data */
 		s->p[i].port.dev	= dev;
 		s->p[i].port.irq	= irq;
-- 
GitLab


From 4409df5866b7ff7686ba27e449ca97a92ee063c9 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Mon, 11 Dec 2023 12:13:51 -0500
Subject: [PATCH 1415/4076] serial: sc16is7xx: change EFR lock to operate on
 each channels

Now that the driver has been converted to use one regmap per port, change
efr locking to operate on a channel basis instead of on the whole IC.

Fixes: 3837a0379533 ("serial: sc16is7xx: improve regmap debugfs by using one regmap per port")
Cc:  <stable@vger.kernel.org> # 6.1.x: 3837a03 serial: sc16is7xx: improve regmap debugfs by using one regmap per port
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231211171353.2901416-5-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 49 ++++++++++++++++++----------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 0a7a9aa5c9fae..0bda9b74d096d 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -323,6 +323,7 @@ struct sc16is7xx_one_config {
 struct sc16is7xx_one {
 	struct uart_port		port;
 	struct regmap			*regmap;
+	struct mutex			efr_lock; /* EFR registers access */
 	struct kthread_work		tx_work;
 	struct kthread_work		reg_work;
 	struct kthread_delayed_work	ms_work;
@@ -342,7 +343,6 @@ struct sc16is7xx_port {
 	unsigned char			buf[SC16IS7XX_FIFO_SIZE];
 	struct kthread_worker		kworker;
 	struct task_struct		*kworker_task;
-	struct mutex			efr_lock;
 	struct sc16is7xx_one		p[];
 };
 
@@ -494,7 +494,6 @@ static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg)
 
 static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 	u8 lcr;
 	u8 prescaler = 0;
@@ -518,7 +517,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 	 * because the bulk of the interrupt processing is run as a workqueue
 	 * job in thread context.
 	 */
-	mutex_lock(&s->efr_lock);
+	mutex_lock(&one->efr_lock);
 
 	lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
 
@@ -537,7 +536,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 	/* Put LCR back to the normal mode */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
 
-	mutex_unlock(&s->efr_lock);
+	mutex_unlock(&one->efr_lock);
 
 	sc16is7xx_port_update(port, SC16IS7XX_MCR_REG,
 			      SC16IS7XX_MCR_CLKSEL_BIT,
@@ -705,11 +704,10 @@ static unsigned int sc16is7xx_get_hwmctrl(struct uart_port *port)
 static void sc16is7xx_update_mlines(struct sc16is7xx_one *one)
 {
 	struct uart_port *port = &one->port;
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	unsigned long flags;
 	unsigned int status, changed;
 
-	lockdep_assert_held_once(&s->efr_lock);
+	lockdep_assert_held_once(&one->efr_lock);
 
 	status = sc16is7xx_get_hwmctrl(port);
 	changed = status ^ one->old_mctrl;
@@ -735,15 +733,20 @@ static void sc16is7xx_update_mlines(struct sc16is7xx_one *one)
 
 static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
 {
+	bool rc = true;
 	struct uart_port *port = &s->p[portno].port;
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	mutex_lock(&one->efr_lock);
 
 	do {
 		unsigned int iir, rxlen;
-		struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
 		iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG);
-		if (iir & SC16IS7XX_IIR_NO_INT_BIT)
-			return false;
+		if (iir & SC16IS7XX_IIR_NO_INT_BIT) {
+			rc = false;
+			goto out_port_irq;
+		}
 
 		iir &= SC16IS7XX_IIR_ID_MASK;
 
@@ -783,15 +786,17 @@ static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
 			break;
 		}
 	} while (0);
-	return true;
+
+out_port_irq:
+	mutex_unlock(&one->efr_lock);
+
+	return rc;
 }
 
 static irqreturn_t sc16is7xx_irq(int irq, void *dev_id)
 {
 	struct sc16is7xx_port *s = (struct sc16is7xx_port *)dev_id;
 
-	mutex_lock(&s->efr_lock);
-
 	while (1) {
 		bool keep_polling = false;
 		int i;
@@ -802,24 +807,22 @@ static irqreturn_t sc16is7xx_irq(int irq, void *dev_id)
 			break;
 	}
 
-	mutex_unlock(&s->efr_lock);
-
 	return IRQ_HANDLED;
 }
 
 static void sc16is7xx_tx_proc(struct kthread_work *ws)
 {
 	struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port);
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 	unsigned long flags;
 
 	if ((port->rs485.flags & SER_RS485_ENABLED) &&
 	    (port->rs485.delay_rts_before_send > 0))
 		msleep(port->rs485.delay_rts_before_send);
 
-	mutex_lock(&s->efr_lock);
+	mutex_lock(&one->efr_lock);
 	sc16is7xx_handle_tx(port);
-	mutex_unlock(&s->efr_lock);
+	mutex_unlock(&one->efr_lock);
 
 	uart_port_lock_irqsave(port, &flags);
 	sc16is7xx_ier_set(port, SC16IS7XX_IER_THRI_BIT);
@@ -926,9 +929,9 @@ static void sc16is7xx_ms_proc(struct kthread_work *ws)
 	struct sc16is7xx_port *s = dev_get_drvdata(one->port.dev);
 
 	if (one->port.state) {
-		mutex_lock(&s->efr_lock);
+		mutex_lock(&one->efr_lock);
 		sc16is7xx_update_mlines(one);
-		mutex_unlock(&s->efr_lock);
+		mutex_unlock(&one->efr_lock);
 
 		kthread_queue_delayed_work(&s->kworker, &one->ms_work, HZ);
 	}
@@ -1012,7 +1015,6 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 				  struct ktermios *termios,
 				  const struct ktermios *old)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 	unsigned int lcr, flow = 0;
 	int baud;
@@ -1071,7 +1073,7 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 		port->ignore_status_mask |= SC16IS7XX_LSR_BRK_ERROR_MASK;
 
 	/* As above, claim the mutex while accessing the EFR. */
-	mutex_lock(&s->efr_lock);
+	mutex_lock(&one->efr_lock);
 
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
 			     SC16IS7XX_LCR_CONF_MODE_B);
@@ -1101,7 +1103,7 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 	/* Update LCR register */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
 
-	mutex_unlock(&s->efr_lock);
+	mutex_unlock(&one->efr_lock);
 
 	/* Get baud rate generator configuration */
 	baud = uart_get_baud_rate(port, termios, old,
@@ -1535,7 +1537,6 @@ static int sc16is7xx_probe(struct device *dev,
 
 	s->devtype = devtype;
 	dev_set_drvdata(dev, s);
-	mutex_init(&s->efr_lock);
 
 	kthread_init_worker(&s->kworker);
 	s->kworker_task = kthread_run(kthread_worker_fn, &s->kworker,
@@ -1578,6 +1579,8 @@ static int sc16is7xx_probe(struct device *dev,
 			goto out_ports;
 		}
 
+		mutex_init(&s->p[i].efr_lock);
+
 		ret = uart_get_rs485_mode(&s->p[i].port);
 		if (ret)
 			goto out_ports;
-- 
GitLab


From dbf4ab821804df071c8b566d9813083125e6d97b Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Mon, 11 Dec 2023 12:13:52 -0500
Subject: [PATCH 1416/4076] serial: sc16is7xx: convert from _raw_ to _noinc_
 regmap functions for FIFO

The SC16IS7XX IC supports a burst mode to access the FIFOs where the
initial register address is sent ($00), followed by all the FIFO data
without having to resend the register address each time. In this mode, the
IC doesn't increment the register address for each R/W byte.

The regmap_raw_read() and regmap_raw_write() are functions which can
perform IO over multiple registers. They are currently used to read/write
from/to the FIFO, and although they operate correctly in this burst mode on
the SPI bus, they would corrupt the regmap cache if it was not disabled
manually. The reason is that when the R/W size is more than 1 byte, these
functions assume that the register address is incremented and handle the
cache accordingly.

Convert FIFO R/W functions to use the regmap _noinc_ versions in order to
remove the manual cache control which was a workaround when using the
_raw_ versions. FIFO registers are properly declared as volatile so
cache will not be used/updated for FIFO accesses.

Fixes: dfeae619d781 ("serial: sc16is7xx")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231211171353.2901416-6-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 0bda9b74d096d..7e4b9b52841d6 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -381,9 +381,7 @@ static void sc16is7xx_fifo_read(struct uart_port *port, unsigned int rxlen)
 	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	regcache_cache_bypass(one->regmap, true);
-	regmap_raw_read(one->regmap, SC16IS7XX_RHR_REG, s->buf, rxlen);
-	regcache_cache_bypass(one->regmap, false);
+	regmap_noinc_read(one->regmap, SC16IS7XX_RHR_REG, s->buf, rxlen);
 }
 
 static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
@@ -398,9 +396,7 @@ static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
 	if (unlikely(!to_send))
 		return;
 
-	regcache_cache_bypass(one->regmap, true);
-	regmap_raw_write(one->regmap, SC16IS7XX_THR_REG, s->buf, to_send);
-	regcache_cache_bypass(one->regmap, false);
+	regmap_noinc_write(one->regmap, SC16IS7XX_THR_REG, s->buf, to_send);
 }
 
 static void sc16is7xx_port_update(struct uart_port *port, u8 reg,
@@ -492,6 +488,11 @@ static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg)
 	return false;
 }
 
+static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg)
+{
+	return reg == SC16IS7XX_RHR_REG;
+}
+
 static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 {
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
@@ -1709,6 +1710,10 @@ static struct regmap_config regcfg = {
 	.cache_type = REGCACHE_RBTREE,
 	.volatile_reg = sc16is7xx_regmap_volatile,
 	.precious_reg = sc16is7xx_regmap_precious,
+	.writeable_noinc_reg = sc16is7xx_regmap_noinc,
+	.readable_noinc_reg = sc16is7xx_regmap_noinc,
+	.max_raw_read = SC16IS7XX_FIFO_SIZE,
+	.max_raw_write = SC16IS7XX_FIFO_SIZE,
 	.max_register = SC16IS7XX_EFCR_REG,
 };
 
-- 
GitLab


From 9915753037eba7135b209fef4f2afeca841af816 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Mon, 11 Dec 2023 12:13:53 -0500
Subject: [PATCH 1417/4076] serial: sc16is7xx: fix unconditional activation of
 THRI interrupt

Commit cc4c1d05eb10 ("sc16is7xx: Properly resume TX after stop") changed
behavior to unconditionnaly set the THRI interrupt in sc16is7xx_tx_proc().

For example when sending a 65 bytes message, and assuming the Tx FIFO is
initially empty, sc16is7xx_handle_tx() will write the first 64 bytes of the
message to the FIFO and sc16is7xx_tx_proc() will then activate THRI. When
the THRI IRQ is fired, the driver will write the remaining byte of the
message to the FIFO, and disable THRI by calling sc16is7xx_stop_tx().

When sending a 2 bytes message, sc16is7xx_handle_tx() will write the 2
bytes of the message to the FIFO and call sc16is7xx_stop_tx(), disabling
THRI. After sc16is7xx_handle_tx() exits, control returns to
sc16is7xx_tx_proc() which will unconditionally set THRI. When the THRI IRQ
is fired, the driver simply acknowledges the interrupt and does nothing
more, since all the data has already been written to the FIFO. This results
in 2 register writes and 4 register reads all for nothing and taking
precious cycles from the I2C/SPI bus.

Fix this by enabling the THRI interrupt only when we fill the Tx FIFO to
its maximum capacity and there are remaining bytes to send in the message.

Fixes: cc4c1d05eb10 ("sc16is7xx: Properly resume TX after stop")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231211171353.2901416-7-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 7e4b9b52841d6..e40e4a99277ef 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -687,6 +687,8 @@ static void sc16is7xx_handle_tx(struct uart_port *port)
 
 	if (uart_circ_empty(xmit))
 		sc16is7xx_stop_tx(port);
+	else
+		sc16is7xx_ier_set(port, SC16IS7XX_IER_THRI_BIT);
 	uart_port_unlock_irqrestore(port, flags);
 }
 
@@ -815,7 +817,6 @@ static void sc16is7xx_tx_proc(struct kthread_work *ws)
 {
 	struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port);
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-	unsigned long flags;
 
 	if ((port->rs485.flags & SER_RS485_ENABLED) &&
 	    (port->rs485.delay_rts_before_send > 0))
@@ -824,10 +825,6 @@ static void sc16is7xx_tx_proc(struct kthread_work *ws)
 	mutex_lock(&one->efr_lock);
 	sc16is7xx_handle_tx(port);
 	mutex_unlock(&one->efr_lock);
-
-	uart_port_lock_irqsave(port, &flags);
-	sc16is7xx_ier_set(port, SC16IS7XX_IER_THRI_BIT);
-	uart_port_unlock_irqrestore(port, flags);
 }
 
 static void sc16is7xx_reconf_rs485(struct uart_port *port)
-- 
GitLab


From d54cbe1db72dbfc664bc21b40c324a624faacb16 Mon Sep 17 00:00:00 2001
From: Chunyan Zhang <chunyan.zhang@unisoc.com>
Date: Fri, 15 Dec 2023 16:56:29 +0800
Subject: [PATCH 1418/4076] dt-bindings: serial: Add a new compatible string
 for UMS9620

The UMS9620 also uses the same serial device with SC9836.

Signed-off-by: Chunyan Zhang <chunyan.zhang@unisoc.com>
Link: https://lore.kernel.org/r/20231215085630.984892-4-chunyan.zhang@unisoc.com
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/serial/sprd-uart.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/serial/sprd-uart.yaml b/Documentation/devicetree/bindings/serial/sprd-uart.yaml
index 28ff77aa86c85..f4dbb6dc2b6ef 100644
--- a/Documentation/devicetree/bindings/serial/sprd-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/sprd-uart.yaml
@@ -20,6 +20,7 @@ properties:
               - sprd,sc9860-uart
               - sprd,sc9863a-uart
               - sprd,ums512-uart
+              - sprd,ums9620-uart
           - const: sprd,sc9836-uart
       - const: sprd,sc9836-uart
 
-- 
GitLab


From 6b64f8e360c00f180cffa1806095cdd2abc55b16 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 8 Dec 2023 10:23:31 +0000
Subject: [PATCH 1419/4076] serial: ma35d1: Fix spelling mistake "ononsole" ->
 "console"

There is a spelling mistake in a pr_warn message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://lore.kernel.org/r/20231208102331.3267192-1-colin.i.king@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/ma35d1_serial.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/ma35d1_serial.c b/drivers/tty/serial/ma35d1_serial.c
index b4dcbd0c95bfd..19f0a305cc430 100644
--- a/drivers/tty/serial/ma35d1_serial.c
+++ b/drivers/tty/serial/ma35d1_serial.c
@@ -558,7 +558,7 @@ static void ma35d1serial_console_write(struct console *co, const char *s, u32 co
 	u32 ier;
 
 	if ((co->index < 0) || (co->index >= MA35_UART_NR)) {
-		pr_warn("Failed to write on ononsole port %x, out of range\n",
+		pr_warn("Failed to write on console port %x, out of range\n",
 			co->index);
 		return;
 	}
-- 
GitLab


From a5f18286083fe450d6080abc8d4341c630f682dd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 13 Dec 2023 18:43:12 +0100
Subject: [PATCH 1420/4076] serial: 8250-fsl: Only do the break workaround if
 IIR signals RLSI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It can happen that while a break is received the transmitter gets empty
and IIR signals a Transmitter holding register empty (THRI) event. In
this case it's too early for the break workaround. Still doing it then
results in the THRI event not being rereported which makes the driver
miss that and e.g. for RS485 half-duplex communication it fails to
switch back to RX mode.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231213174312.2341013-1-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_fsl.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c
index 5cf675eadefe1..b4ed442082a85 100644
--- a/drivers/tty/serial/8250/8250_fsl.c
+++ b/drivers/tty/serial/8250/8250_fsl.c
@@ -51,7 +51,8 @@ int fsl8250_handle_irq(struct uart_port *port)
 	 * immediately and interrupt the CPU again. The hardware clears LSR.BI
 	 * when the next valid char is read.)
 	 */
-	if (unlikely(up->lsr_saved_flags & UART_LSR_BI)) {
+	if (unlikely((iir & UART_IIR_ID) == UART_IIR_RLSI &&
+		     (up->lsr_saved_flags & UART_LSR_BI))) {
 		up->lsr_saved_flags &= ~UART_LSR_BI;
 		port->serial_in(port, UART_RX);
 		uart_port_unlock_irqrestore(&up->port, flags);
-- 
GitLab


From 1f78c56007ba61b7b8c3f7dbb6787b6af116d3f0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:06 +0100
Subject: [PATCH 1421/4076] tty: serial: amba: Use linux/{bits,bitfield}.h
 macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver uses bit shifts and hexadecimal expressions to declare
constants. Replace that with the BIT(), GENMASK() & FIELD_PREP_CONST()
macros to clarify intent.

include/linux/amba/serial.h gets included from arch/arm/include/debug/pl01x.S.
Avoid includes and macro tricks for the four defines that are involved:
UART01x_DR, UART01x_FR, UART01x_FR_TXFF and UART01x_FR_BUSY.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-1-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/amba/serial.h | 251 +++++++++++++++++++-----------------
 1 file changed, 130 insertions(+), 121 deletions(-)

diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index 27003ec52114c..9120de05ead08 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -10,6 +10,11 @@
 #ifndef ASM_ARM_HARDWARE_SERIAL_AMBA_H
 #define ASM_ARM_HARDWARE_SERIAL_AMBA_H
 
+#ifndef __ASSEMBLY__
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#endif
+
 #include <linux/types.h>
 
 /* -------------------------------------------------------------------------------
@@ -70,138 +75,142 @@
 #define ZX_UART011_ICR		0x4c
 #define ZX_UART011_DMACR	0x50
 
-#define UART011_DR_OE		(1 << 11)
-#define UART011_DR_BE		(1 << 10)
-#define UART011_DR_PE		(1 << 9)
-#define UART011_DR_FE		(1 << 8)
-
-#define UART01x_RSR_OE		0x08
-#define UART01x_RSR_BE		0x04
-#define UART01x_RSR_PE		0x02
-#define UART01x_RSR_FE		0x01
-
-#define UART011_FR_RI		0x100
-#define UART011_FR_TXFE		0x080
-#define UART011_FR_RXFF		0x040
-#define UART01x_FR_TXFF		0x020
-#define UART01x_FR_RXFE		0x010
-#define UART01x_FR_BUSY		0x008
-#define UART01x_FR_DCD		0x004
-#define UART01x_FR_DSR		0x002
-#define UART01x_FR_CTS		0x001
+#define UART011_DR_OE		BIT(11)
+#define UART011_DR_BE		BIT(10)
+#define UART011_DR_PE		BIT(9)
+#define UART011_DR_FE		BIT(8)
+
+#define UART01x_RSR_OE		BIT(3)
+#define UART01x_RSR_BE		BIT(2)
+#define UART01x_RSR_PE		BIT(1)
+#define UART01x_RSR_FE		BIT(0)
+
+#define UART011_FR_RI		BIT(8)
+#define UART011_FR_TXFE		BIT(7)
+#define UART011_FR_RXFF		BIT(6)
+#define UART01x_FR_TXFF		(1 << 5)	/* used in ASM */
+#define UART01x_FR_RXFE		BIT(4)
+#define UART01x_FR_BUSY		(1 << 3)	/* used in ASM */
+#define UART01x_FR_DCD		BIT(2)
+#define UART01x_FR_DSR		BIT(1)
+#define UART01x_FR_CTS		BIT(0)
 #define UART01x_FR_TMSK		(UART01x_FR_TXFF + UART01x_FR_BUSY)
 
 /*
  * Some bits of Flag Register on ZTE device have different position from
  * standard ones.
  */
-#define ZX_UART01x_FR_BUSY	0x100
-#define ZX_UART01x_FR_DSR	0x008
-#define ZX_UART01x_FR_CTS	0x002
-#define ZX_UART011_FR_RI	0x001
-
-#define UART011_CR_CTSEN	0x8000	/* CTS hardware flow control */
-#define UART011_CR_RTSEN	0x4000	/* RTS hardware flow control */
-#define UART011_CR_OUT2		0x2000	/* OUT2 */
-#define UART011_CR_OUT1		0x1000	/* OUT1 */
-#define UART011_CR_RTS		0x0800	/* RTS */
-#define UART011_CR_DTR		0x0400	/* DTR */
-#define UART011_CR_RXE		0x0200	/* receive enable */
-#define UART011_CR_TXE		0x0100	/* transmit enable */
-#define UART011_CR_LBE		0x0080	/* loopback enable */
-#define UART010_CR_RTIE		0x0040
-#define UART010_CR_TIE		0x0020
-#define UART010_CR_RIE		0x0010
-#define UART010_CR_MSIE		0x0008
-#define ST_UART011_CR_OVSFACT	0x0008	/* Oversampling factor */
-#define UART01x_CR_IIRLP	0x0004	/* SIR low power mode */
-#define UART01x_CR_SIREN	0x0002	/* SIR enable */
-#define UART01x_CR_UARTEN	0x0001	/* UART enable */
-
-#define UART011_LCRH_SPS	0x80
+#define ZX_UART01x_FR_BUSY	BIT(8)
+#define ZX_UART01x_FR_DSR	BIT(3)
+#define ZX_UART01x_FR_CTS	BIT(1)
+#define ZX_UART011_FR_RI	BIT(0)
+
+#define UART011_CR_CTSEN	BIT(15)	/* CTS hardware flow control */
+#define UART011_CR_RTSEN	BIT(14)	/* RTS hardware flow control */
+#define UART011_CR_OUT2		BIT(13)	/* OUT2 */
+#define UART011_CR_OUT1		BIT(12)	/* OUT1 */
+#define UART011_CR_RTS		BIT(11)	/* RTS */
+#define UART011_CR_DTR		BIT(10)	/* DTR */
+#define UART011_CR_RXE		BIT(9)	/* receive enable */
+#define UART011_CR_TXE		BIT(8)	/* transmit enable */
+#define UART011_CR_LBE		BIT(7)	/* loopback enable */
+#define UART010_CR_RTIE		BIT(6)
+#define UART010_CR_TIE		BIT(5)
+#define UART010_CR_RIE		BIT(4)
+#define UART010_CR_MSIE		BIT(3)
+#define ST_UART011_CR_OVSFACT	BIT(3)	/* Oversampling factor */
+#define UART01x_CR_IIRLP	BIT(2)	/* SIR low power mode */
+#define UART01x_CR_SIREN	BIT(1)	/* SIR enable */
+#define UART01x_CR_UARTEN	BIT(0)	/* UART enable */
+
+#define UART011_LCRH_SPS	BIT(7)
 #define UART01x_LCRH_WLEN_8	0x60
 #define UART01x_LCRH_WLEN_7	0x40
 #define UART01x_LCRH_WLEN_6	0x20
 #define UART01x_LCRH_WLEN_5	0x00
-#define UART01x_LCRH_FEN	0x10
-#define UART01x_LCRH_STP2	0x08
-#define UART01x_LCRH_EPS	0x04
-#define UART01x_LCRH_PEN	0x02
-#define UART01x_LCRH_BRK	0x01
-
-#define ST_UART011_DMAWM_RX_1	(0 << 3)
-#define ST_UART011_DMAWM_RX_2	(1 << 3)
-#define ST_UART011_DMAWM_RX_4	(2 << 3)
-#define ST_UART011_DMAWM_RX_8	(3 << 3)
-#define ST_UART011_DMAWM_RX_16	(4 << 3)
-#define ST_UART011_DMAWM_RX_32	(5 << 3)
-#define ST_UART011_DMAWM_RX_48	(6 << 3)
-#define ST_UART011_DMAWM_TX_1	0
-#define ST_UART011_DMAWM_TX_2	1
-#define ST_UART011_DMAWM_TX_4	2
-#define ST_UART011_DMAWM_TX_8	3
-#define ST_UART011_DMAWM_TX_16	4
-#define ST_UART011_DMAWM_TX_32	5
-#define ST_UART011_DMAWM_TX_48	6
-
-#define UART010_IIR_RTIS	0x08
-#define UART010_IIR_TIS		0x04
-#define UART010_IIR_RIS		0x02
-#define UART010_IIR_MIS		0x01
-
-#define UART011_IFLS_RX1_8	(0 << 3)
-#define UART011_IFLS_RX2_8	(1 << 3)
-#define UART011_IFLS_RX4_8	(2 << 3)
-#define UART011_IFLS_RX6_8	(3 << 3)
-#define UART011_IFLS_RX7_8	(4 << 3)
-#define UART011_IFLS_TX1_8	(0 << 0)
-#define UART011_IFLS_TX2_8	(1 << 0)
-#define UART011_IFLS_TX4_8	(2 << 0)
-#define UART011_IFLS_TX6_8	(3 << 0)
-#define UART011_IFLS_TX7_8	(4 << 0)
+#define UART01x_LCRH_FEN	BIT(4)
+#define UART01x_LCRH_STP2	BIT(3)
+#define UART01x_LCRH_EPS	BIT(2)
+#define UART01x_LCRH_PEN	BIT(1)
+#define UART01x_LCRH_BRK	BIT(0)
+
+#define ST_UART011_DMAWM_RX	GENMASK(5, 3)
+#define ST_UART011_DMAWM_RX_1	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 0)
+#define ST_UART011_DMAWM_RX_2	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 1)
+#define ST_UART011_DMAWM_RX_4	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 2)
+#define ST_UART011_DMAWM_RX_8	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 3)
+#define ST_UART011_DMAWM_RX_16	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 4)
+#define ST_UART011_DMAWM_RX_32	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 5)
+#define ST_UART011_DMAWM_RX_48	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 6)
+#define ST_UART011_DMAWM_TX	GENMASK(2, 0)
+#define ST_UART011_DMAWM_TX_1	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 0)
+#define ST_UART011_DMAWM_TX_2	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 1)
+#define ST_UART011_DMAWM_TX_4	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 2)
+#define ST_UART011_DMAWM_TX_8	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 3)
+#define ST_UART011_DMAWM_TX_16	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 4)
+#define ST_UART011_DMAWM_TX_32	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 5)
+#define ST_UART011_DMAWM_TX_48	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 6)
+
+#define UART010_IIR_RTIS	BIT(3)
+#define UART010_IIR_TIS		BIT(2)
+#define UART010_IIR_RIS		BIT(1)
+#define UART010_IIR_MIS		BIT(0)
+
+#define UART011_IFLS_RXIFLSEL	GENMASK(5, 3)
+#define UART011_IFLS_RX1_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 0)
+#define UART011_IFLS_RX2_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 1)
+#define UART011_IFLS_RX4_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 2)
+#define UART011_IFLS_RX6_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 3)
+#define UART011_IFLS_RX7_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 4)
+#define UART011_IFLS_TXIFLSEL	GENMASK(2, 0)
+#define UART011_IFLS_TX1_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 0)
+#define UART011_IFLS_TX2_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 1)
+#define UART011_IFLS_TX4_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 2)
+#define UART011_IFLS_TX6_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 3)
+#define UART011_IFLS_TX7_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 4)
 /* special values for ST vendor with deeper fifo */
-#define UART011_IFLS_RX_HALF	(5 << 3)
-#define UART011_IFLS_TX_HALF	(5 << 0)
-
-#define UART011_OEIM		(1 << 10)	/* overrun error interrupt mask */
-#define UART011_BEIM		(1 << 9)	/* break error interrupt mask */
-#define UART011_PEIM		(1 << 8)	/* parity error interrupt mask */
-#define UART011_FEIM		(1 << 7)	/* framing error interrupt mask */
-#define UART011_RTIM		(1 << 6)	/* receive timeout interrupt mask */
-#define UART011_TXIM		(1 << 5)	/* transmit interrupt mask */
-#define UART011_RXIM		(1 << 4)	/* receive interrupt mask */
-#define UART011_DSRMIM		(1 << 3)	/* DSR interrupt mask */
-#define UART011_DCDMIM		(1 << 2)	/* DCD interrupt mask */
-#define UART011_CTSMIM		(1 << 1)	/* CTS interrupt mask */
-#define UART011_RIMIM		(1 << 0)	/* RI interrupt mask */
-
-#define UART011_OEIS		(1 << 10)	/* overrun error interrupt status */
-#define UART011_BEIS		(1 << 9)	/* break error interrupt status */
-#define UART011_PEIS		(1 << 8)	/* parity error interrupt status */
-#define UART011_FEIS		(1 << 7)	/* framing error interrupt status */
-#define UART011_RTIS		(1 << 6)	/* receive timeout interrupt status */
-#define UART011_TXIS		(1 << 5)	/* transmit interrupt status */
-#define UART011_RXIS		(1 << 4)	/* receive interrupt status */
-#define UART011_DSRMIS		(1 << 3)	/* DSR interrupt status */
-#define UART011_DCDMIS		(1 << 2)	/* DCD interrupt status */
-#define UART011_CTSMIS		(1 << 1)	/* CTS interrupt status */
-#define UART011_RIMIS		(1 << 0)	/* RI interrupt status */
-
-#define UART011_OEIC		(1 << 10)	/* overrun error interrupt clear */
-#define UART011_BEIC		(1 << 9)	/* break error interrupt clear */
-#define UART011_PEIC		(1 << 8)	/* parity error interrupt clear */
-#define UART011_FEIC		(1 << 7)	/* framing error interrupt clear */
-#define UART011_RTIC		(1 << 6)	/* receive timeout interrupt clear */
-#define UART011_TXIC		(1 << 5)	/* transmit interrupt clear */
-#define UART011_RXIC		(1 << 4)	/* receive interrupt clear */
-#define UART011_DSRMIC		(1 << 3)	/* DSR interrupt clear */
-#define UART011_DCDMIC		(1 << 2)	/* DCD interrupt clear */
-#define UART011_CTSMIC		(1 << 1)	/* CTS interrupt clear */
-#define UART011_RIMIC		(1 << 0)	/* RI interrupt clear */
-
-#define UART011_DMAONERR	(1 << 2)	/* disable dma on error */
-#define UART011_TXDMAE		(1 << 1)	/* enable transmit dma */
-#define UART011_RXDMAE		(1 << 0)	/* enable receive dma */
+#define UART011_IFLS_RX_HALF	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 5)
+#define UART011_IFLS_TX_HALF	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 5)
+
+#define UART011_OEIM		BIT(10)	/* overrun error interrupt mask */
+#define UART011_BEIM		BIT(9)	/* break error interrupt mask */
+#define UART011_PEIM		BIT(8)	/* parity error interrupt mask */
+#define UART011_FEIM		BIT(7)	/* framing error interrupt mask */
+#define UART011_RTIM		BIT(6)	/* receive timeout interrupt mask */
+#define UART011_TXIM		BIT(5)	/* transmit interrupt mask */
+#define UART011_RXIM		BIT(4)	/* receive interrupt mask */
+#define UART011_DSRMIM		BIT(3)	/* DSR interrupt mask */
+#define UART011_DCDMIM		BIT(2)	/* DCD interrupt mask */
+#define UART011_CTSMIM		BIT(1)	/* CTS interrupt mask */
+#define UART011_RIMIM		BIT(0)	/* RI interrupt mask */
+
+#define UART011_OEIS		BIT(10)	/* overrun error interrupt status */
+#define UART011_BEIS		BIT(9)	/* break error interrupt status */
+#define UART011_PEIS		BIT(8)	/* parity error interrupt status */
+#define UART011_FEIS		BIT(7)	/* framing error interrupt status */
+#define UART011_RTIS		BIT(6)	/* receive timeout interrupt status */
+#define UART011_TXIS		BIT(5)	/* transmit interrupt status */
+#define UART011_RXIS		BIT(4)	/* receive interrupt status */
+#define UART011_DSRMIS		BIT(3)	/* DSR interrupt status */
+#define UART011_DCDMIS		BIT(2)	/* DCD interrupt status */
+#define UART011_CTSMIS		BIT(1)	/* CTS interrupt status */
+#define UART011_RIMIS		BIT(0)	/* RI interrupt status */
+
+#define UART011_OEIC		BIT(10)	/* overrun error interrupt clear */
+#define UART011_BEIC		BIT(9)	/* break error interrupt clear */
+#define UART011_PEIC		BIT(8)	/* parity error interrupt clear */
+#define UART011_FEIC		BIT(7)	/* framing error interrupt clear */
+#define UART011_RTIC		BIT(6)	/* receive timeout interrupt clear */
+#define UART011_TXIC		BIT(5)	/* transmit interrupt clear */
+#define UART011_RXIC		BIT(4)	/* receive interrupt clear */
+#define UART011_DSRMIC		BIT(3)	/* DSR interrupt clear */
+#define UART011_DCDMIC		BIT(2)	/* DCD interrupt clear */
+#define UART011_CTSMIC		BIT(1)	/* CTS interrupt clear */
+#define UART011_RIMIC		BIT(0)	/* RI interrupt clear */
+
+#define UART011_DMAONERR	BIT(2)	/* disable dma on error */
+#define UART011_TXDMAE		BIT(1)	/* enable transmit dma */
+#define UART011_RXDMAE		BIT(0)	/* enable receive dma */
 
 #define UART01x_RSR_ANY		(UART01x_RSR_OE | UART01x_RSR_BE | UART01x_RSR_PE | UART01x_RSR_FE)
 #define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD | UART01x_FR_DSR | UART01x_FR_CTS)
-- 
GitLab


From d93ebe0fcfbd29e2b93850b5f66f98b0d63cce9c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:07 +0100
Subject: [PATCH 1422/4076] tty: serial: amba-pl011: fix whitespace formatting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Follow recommandations from:

    $ ./scripts/checkpatch.pl --strict --file \
        drivers/tty/serial/amba-pl011.c

We fix 5 warnings and 48 checks, all related to whitespace.
Culprits are:

CHECK: Alignment should match open parenthesis
CHECK: Blank lines aren't necessary after an open brace '{'
CHECK: Lines should not end with a '('
CHECK: Please don't use multiple blank lines
CHECK: Please use a blank line after function/struct/union/enum
       declarations
CHECK: spaces preferred around that '/' (ctx:VxV)
CHECK: spaces preferred around that '|' (ctx:VxV)
WARNING: Missing a blank line after declarations
WARNING: please, no spaces at the start of a line

Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-2-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 97 +++++++++++++++------------------
 1 file changed, 45 insertions(+), 52 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 5521e36147a0e..5e7c8d74733ed 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -50,7 +50,7 @@
 
 #define AMBA_ISR_PASS_LIMIT	256
 
-#define UART_DR_ERROR		(UART011_DR_OE|UART011_DR_BE|UART011_DR_PE|UART011_DR_FE)
+#define UART_DR_ERROR		(UART011_DR_OE | UART011_DR_BE | UART011_DR_PE | UART011_DR_FE)
 #define UART_DUMMY_DR_RX	(1 << 16)
 
 enum {
@@ -125,7 +125,7 @@ static unsigned int get_fifosize_arm(struct amba_device *dev)
 
 static struct vendor_data vendor_arm = {
 	.reg_offset		= pl011_std_offsets,
-	.ifls			= UART011_IFLS_RX4_8|UART011_IFLS_TX4_8,
+	.ifls			= UART011_IFLS_RX4_8 | UART011_IFLS_TX4_8,
 	.fr_busy		= UART01x_FR_BUSY,
 	.fr_dsr			= UART01x_FR_DSR,
 	.fr_cts			= UART01x_FR_CTS,
@@ -203,7 +203,7 @@ static unsigned int get_fifosize_st(struct amba_device *dev)
 
 static struct vendor_data vendor_st = {
 	.reg_offset		= pl011_st_offsets,
-	.ifls			= UART011_IFLS_RX_HALF|UART011_IFLS_TX_HALF,
+	.ifls			= UART011_IFLS_RX_HALF | UART011_IFLS_TX_HALF,
 	.fr_busy		= UART01x_FR_BUSY,
 	.fr_dsr			= UART01x_FR_DSR,
 	.fr_cts			= UART01x_FR_CTS,
@@ -277,13 +277,13 @@ struct uart_amba_port {
 static unsigned int pl011_tx_empty(struct uart_port *port);
 
 static unsigned int pl011_reg_to_offset(const struct uart_amba_port *uap,
-	unsigned int reg)
+					unsigned int reg)
 {
 	return uap->reg_offset[reg];
 }
 
 static unsigned int pl011_read(const struct uart_amba_port *uap,
-	unsigned int reg)
+			       unsigned int reg)
 {
 	void __iomem *addr = uap->port.membase + pl011_reg_to_offset(uap, reg);
 
@@ -292,7 +292,7 @@ static unsigned int pl011_read(const struct uart_amba_port *uap,
 }
 
 static void pl011_write(unsigned int val, const struct uart_amba_port *uap,
-	unsigned int reg)
+			unsigned int reg)
 {
 	void __iomem *addr = uap->port.membase + pl011_reg_to_offset(uap, reg);
 
@@ -358,7 +358,6 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap)
 	return fifotaken;
 }
 
-
 /*
  * All the DMA operation mode stuff goes inside this ifdef.
  * This assumes that you have a generic DMA device interface,
@@ -369,7 +368,7 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap)
 #define PL011_DMA_BUFFER_SIZE PAGE_SIZE
 
 static int pl011_dmabuf_init(struct dma_chan *chan, struct pl011_dmabuf *db,
-	enum dma_data_direction dir)
+			     enum dma_data_direction dir)
 {
 	db->buf = dma_alloc_coherent(chan->device->dev, PL011_DMA_BUFFER_SIZE,
 				     &db->dma, GFP_KERNEL);
@@ -381,7 +380,7 @@ static int pl011_dmabuf_init(struct dma_chan *chan, struct pl011_dmabuf *db,
 }
 
 static void pl011_dmabuf_free(struct dma_chan *chan, struct pl011_dmabuf *db,
-	enum dma_data_direction dir)
+			      enum dma_data_direction dir)
 {
 	if (db->buf) {
 		dma_free_coherent(chan->device->dev,
@@ -424,7 +423,7 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 		dma_cap_set(DMA_SLAVE, mask);
 
 		chan = dma_request_channel(mask, plat->dma_filter,
-						plat->dma_tx_param);
+					   plat->dma_tx_param);
 		if (!chan) {
 			dev_err(uap->port.dev, "no TX DMA channel!\n");
 			return;
@@ -470,7 +469,7 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 					DMA_RESIDUE_GRANULARITY_DESCRIPTOR) {
 				dma_release_channel(chan);
 				dev_info(uap->port.dev,
-					"RX DMA disabled - no residue processing\n");
+					 "RX DMA disabled - no residue processing\n");
 				return;
 			}
 		}
@@ -499,18 +498,16 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 			else
 				uap->dmarx.poll_timeout = 3000;
 		} else if (!plat && dev->of_node) {
-			uap->dmarx.auto_poll_rate = of_property_read_bool(
-						dev->of_node, "auto-poll");
+			uap->dmarx.auto_poll_rate =
+					of_property_read_bool(dev->of_node, "auto-poll");
 			if (uap->dmarx.auto_poll_rate) {
 				u32 x;
 
-				if (0 == of_property_read_u32(dev->of_node,
-						"poll-rate-ms", &x))
+				if (0 == of_property_read_u32(dev->of_node, "poll-rate-ms", &x))
 					uap->dmarx.poll_rate = x;
 				else
 					uap->dmarx.poll_rate = 100;
-				if (0 == of_property_read_u32(dev->of_node,
-						"poll-timeout-ms", &x))
+				if (0 == of_property_read_u32(dev->of_node, "poll-timeout-ms", &x))
 					uap->dmarx.poll_timeout = x;
 				else
 					uap->dmarx.poll_timeout = 3000;
@@ -547,7 +544,7 @@ static void pl011_dma_tx_callback(void *data)
 	uart_port_lock_irqsave(&uap->port, &flags);
 	if (uap->dmatx.queued)
 		dma_unmap_single(dmatx->chan->device->dev, dmatx->dma,
-				dmatx->len, DMA_TO_DEVICE);
+				 dmatx->len, DMA_TO_DEVICE);
 
 	dmacr = uap->dmacr;
 	uap->dmacr = dmacr & ~UART011_TXDMAE;
@@ -643,7 +640,7 @@ static int pl011_dma_tx_refill(struct uart_amba_port *uap)
 	}
 
 	desc = dmaengine_prep_slave_single(chan, dmatx->dma, dmatx->len, DMA_MEM_TO_DEV,
-					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+					   DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
 		dma_unmap_single(dma_dev->dev, dmatx->dma, dmatx->len, DMA_TO_DEVICE);
 		uap->dmatx.queued = false;
@@ -832,8 +829,8 @@ static int pl011_dma_rx_trigger_dma(struct uart_amba_port *uap)
 	dbuf = uap->dmarx.use_buf_b ?
 		&uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a;
 	desc = dmaengine_prep_slave_single(rxchan, dbuf->dma, dbuf->len,
-					DMA_DEV_TO_MEM,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+					   DMA_DEV_TO_MEM,
+					   DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	/*
 	 * If the DMA engine is busy and cannot prepare a
 	 * channel, no big deal, the driver will fall back
@@ -889,14 +886,12 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 
 	/* Pick the remain data from the DMA */
 	if (pending) {
-
 		/*
 		 * First take all chars in the DMA pipe, then look in the FIFO.
 		 * Note that tty_insert_flip_buf() tries to take as many chars
 		 * as it can.
 		 */
-		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken,
-				pending);
+		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken, pending);
 
 		uap->port.icount.rx += dma_count;
 		if (dma_count < pending)
@@ -1072,7 +1067,7 @@ static void pl011_dma_rx_poll(struct timer_list *t)
 		dmataken = dbuf->len - dmarx->last_residue;
 		size = dmarx->last_residue - state.residue;
 		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken,
-				size);
+						   size);
 		if (dma_count == size)
 			dmarx->last_residue =  state.residue;
 		dmarx->last_jiffies = jiffies;
@@ -1085,7 +1080,6 @@ static void pl011_dma_rx_poll(struct timer_list *t)
 	 */
 	if (jiffies_to_msecs(jiffies - dmarx->last_jiffies)
 			> uap->dmarx.poll_timeout) {
-
 		uart_port_lock_irqsave(&uap->port, &flags);
 		pl011_dma_rx_stop(uap);
 		uap->im |= UART011_RXIM;
@@ -1097,7 +1091,7 @@ static void pl011_dma_rx_poll(struct timer_list *t)
 		del_timer(&uap->dmarx.timer);
 	} else {
 		mod_timer(&uap->dmarx.timer,
-			jiffies + msecs_to_jiffies(uap->dmarx.poll_rate));
+			  jiffies + msecs_to_jiffies(uap->dmarx.poll_rate));
 	}
 }
 
@@ -1129,7 +1123,7 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 
 	/* Allocate and map DMA RX buffers */
 	ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_a,
-			       DMA_FROM_DEVICE);
+				DMA_FROM_DEVICE);
 	if (ret) {
 		dev_err(uap->port.dev, "failed to init DMA %s: %d\n",
 			"RX buffer A", ret);
@@ -1137,12 +1131,12 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 	}
 
 	ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_b,
-			       DMA_FROM_DEVICE);
+				DMA_FROM_DEVICE);
 	if (ret) {
 		dev_err(uap->port.dev, "failed to init DMA %s: %d\n",
 			"RX buffer B", ret);
 		pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a,
-				 DMA_FROM_DEVICE);
+				  DMA_FROM_DEVICE);
 		goto skip_rx;
 	}
 
@@ -1169,8 +1163,7 @@ skip_rx:
 		if (uap->dmarx.poll_rate) {
 			timer_setup(&uap->dmarx.timer, pl011_dma_rx_poll, 0);
 			mod_timer(&uap->dmarx.timer,
-				jiffies +
-				msecs_to_jiffies(uap->dmarx.poll_rate));
+				  jiffies + msecs_to_jiffies(uap->dmarx.poll_rate));
 			uap->dmarx.last_residue = PL011_DMA_BUFFER_SIZE;
 			uap->dmarx.last_jiffies = jiffies;
 		}
@@ -1359,8 +1352,8 @@ static void pl011_stop_rx(struct uart_port *port)
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
 
-	uap->im &= ~(UART011_RXIM|UART011_RTIM|UART011_FEIM|
-		     UART011_PEIM|UART011_BEIM|UART011_OEIM);
+	uap->im &= ~(UART011_RXIM | UART011_RTIM | UART011_FEIM |
+		     UART011_PEIM | UART011_BEIM | UART011_OEIM);
 	pl011_write(uap->im, uap, REG_IMSC);
 
 	pl011_dma_rx_stop(uap);
@@ -1380,7 +1373,7 @@ static void pl011_enable_ms(struct uart_port *port)
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
 
-	uap->im |= UART011_RIMIM|UART011_CTSMIM|UART011_DCDMIM|UART011_DSRMIM;
+	uap->im |= UART011_RIMIM | UART011_CTSMIM | UART011_DCDMIM | UART011_DSRMIM;
 	pl011_write(uap->im, uap, REG_IMSC);
 }
 
@@ -1409,8 +1402,7 @@ __acquires(&uap->port.lock)
 				uap->dmarx.last_jiffies = jiffies;
 				uap->dmarx.last_residue	= PL011_DMA_BUFFER_SIZE;
 				mod_timer(&uap->dmarx.timer,
-					jiffies +
-					msecs_to_jiffies(uap->dmarx.poll_rate));
+					  jiffies + msecs_to_jiffies(uap->dmarx.poll_rate));
 			}
 #endif
 		}
@@ -1557,18 +1549,17 @@ static irqreturn_t pl011_int(int irq, void *dev_id)
 		do {
 			check_apply_cts_event_workaround(uap);
 
-			pl011_write(status & ~(UART011_TXIS|UART011_RTIS|
-					       UART011_RXIS),
+			pl011_write(status & ~(UART011_TXIS | UART011_RTIS | UART011_RXIS),
 				    uap, REG_ICR);
 
-			if (status & (UART011_RTIS|UART011_RXIS)) {
+			if (status & (UART011_RTIS | UART011_RXIS)) {
 				if (pl011_dma_rx_running(uap))
 					pl011_dma_rx_irq(uap);
 				else
 					pl011_rx_chars(uap);
 			}
-			if (status & (UART011_DSRMIS|UART011_DCDMIS|
-				      UART011_CTSMIS|UART011_RIMIS))
+			if (status & (UART011_DSRMIS | UART011_DCDMIS |
+				      UART011_CTSMIS | UART011_RIMIS))
 				pl011_modem_status(uap);
 			if (status & UART011_TXIS)
 				pl011_tx_chars(uap, true);
@@ -1707,8 +1698,7 @@ static int pl011_get_poll_char(struct uart_port *port)
 	return pl011_read(uap, REG_DR);
 }
 
-static void pl011_put_poll_char(struct uart_port *port,
-			 unsigned char ch)
+static void pl011_put_poll_char(struct uart_port *port, unsigned char ch)
 {
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
@@ -1909,14 +1899,13 @@ static int sbsa_uart_startup(struct uart_port *port)
 	return 0;
 }
 
-static void pl011_shutdown_channel(struct uart_amba_port *uap,
-					unsigned int lcrh)
+static void pl011_shutdown_channel(struct uart_amba_port *uap, unsigned int lcrh)
 {
-      unsigned long val;
+	unsigned long val;
 
-      val = pl011_read(uap, lcrh);
-      val &= ~(UART01x_LCRH_BRK | UART01x_LCRH_FEN);
-      pl011_write(val, uap, lcrh);
+	val = pl011_read(uap, lcrh);
+	val &= ~(UART01x_LCRH_BRK | UART01x_LCRH_FEN);
+	pl011_write(val, uap, lcrh);
 }
 
 /*
@@ -2065,7 +2054,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios,
 		uap->dmarx.poll_rate = DIV_ROUND_UP(10000000, baud);
 #endif
 
-	if (baud > port->uartclk/16)
+	if (baud > port->uartclk / 16)
 		quot = DIV_ROUND_CLOSEST(port->uartclk * 8, baud);
 	else
 		quot = DIV_ROUND_CLOSEST(port->uartclk * 4, baud);
@@ -2218,13 +2207,14 @@ static void pl011_config_port(struct uart_port *port, int flags)
 static int pl011_verify_port(struct uart_port *port, struct serial_struct *ser)
 {
 	int ret = 0;
+
 	if (ser->type != PORT_UNKNOWN && ser->type != PORT_AMBA)
 		ret = -EINVAL;
 	if (ser->irq < 0 || ser->irq >= nr_irqs)
 		ret = -EINVAL;
 	if (ser->baud_base < 9600)
 		ret = -EINVAL;
-	if (port->mapbase != (unsigned long) ser->iomem_base)
+	if (port->mapbase != (unsigned long)ser->iomem_base)
 		ret = -EINVAL;
 	return ret;
 }
@@ -2613,7 +2603,9 @@ static int __init pl011_early_console_setup(struct earlycon_device *device,
 
 	return 0;
 }
+
 OF_EARLYCON_DECLARE(pl011, "arm,pl011", pl011_early_console_setup);
+
 OF_EARLYCON_DECLARE(pl011, "arm,sbsa-uart", pl011_early_console_setup);
 
 /*
@@ -2636,6 +2628,7 @@ qdf2400_e44_early_console_setup(struct earlycon_device *device,
 	device->con->write = qdf2400_e44_early_write;
 	return 0;
 }
+
 EARLYCON_DECLARE(qdf2400_e44, qdf2400_e44_early_console_setup);
 
 #else
-- 
GitLab


From dc00f0cc5e04490416d4c2164011e39b4a2d29df Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:08 +0100
Subject: [PATCH 1423/4076] tty: serial: amba-pl011: replace TIOCMBIT macros by
 static functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver uses two TIOCMBIT macros inside pl011_{get,set}_mctrl to
simplify the logic. Those look scary to checkpatch because they contain
ifs without do-while loops.

Avoid the macros by creating small equivalent static functions; that
lets the compiler do its type checking & avoids checkpatch errors.

For the second instance __assign_bit is not usable because it deals with
unsigned long pointers whereas we have an unsigned int in
pl011_set_mctrl.

This addresses the following checkpatch warnings:

    $ ./scripts/checkpatch.pl --strict --file \
        drivers/tty/serial/amba-pl011.c

    ERROR: Macros starting with if should be enclosed by a do -
           while loop to avoid possible if/else logic defects

    CHECK: Macro argument 'uartbit' may be better as '(uartbit)' to
           avoid precedence issues

    ERROR: Macros starting with if should be enclosed by a do - while
           loop to avoid possible if/else logic defects

    CHECK: Macro argument 'tiocmbit' may be better as '(tiocmbit)' to
           avoid precedence issues

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-3-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 45 ++++++++++++++++++---------------
 1 file changed, 24 insertions(+), 21 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 5e7c8d74733ed..68d334df7091f 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1589,6 +1589,12 @@ static unsigned int pl011_tx_empty(struct uart_port *port)
 							0 : TIOCSER_TEMT;
 }
 
+static void pl011_maybe_set_bit(bool cond, unsigned int *ptr, unsigned int mask)
+{
+	if (cond)
+		*ptr |= mask;
+}
+
 static unsigned int pl011_get_mctrl(struct uart_port *port)
 {
 	struct uart_amba_port *uap =
@@ -1596,18 +1602,22 @@ static unsigned int pl011_get_mctrl(struct uart_port *port)
 	unsigned int result = 0;
 	unsigned int status = pl011_read(uap, REG_FR);
 
-#define TIOCMBIT(uartbit, tiocmbit)	\
-	if (status & uartbit)		\
-		result |= tiocmbit
+	pl011_maybe_set_bit(status & UART01x_FR_DCD, &result, TIOCM_CAR);
+	pl011_maybe_set_bit(status & uap->vendor->fr_dsr, &result, TIOCM_DSR);
+	pl011_maybe_set_bit(status & uap->vendor->fr_cts, &result, TIOCM_CTS);
+	pl011_maybe_set_bit(status & uap->vendor->fr_ri, &result, TIOCM_RNG);
 
-	TIOCMBIT(UART01x_FR_DCD, TIOCM_CAR);
-	TIOCMBIT(uap->vendor->fr_dsr, TIOCM_DSR);
-	TIOCMBIT(uap->vendor->fr_cts, TIOCM_CTS);
-	TIOCMBIT(uap->vendor->fr_ri, TIOCM_RNG);
-#undef TIOCMBIT
 	return result;
 }
 
+static void pl011_assign_bit(bool cond, unsigned int *ptr, unsigned int mask)
+{
+	if (cond)
+		*ptr |= mask;
+	else
+		*ptr &= ~mask;
+}
+
 static void pl011_set_mctrl(struct uart_port *port, unsigned int mctrl)
 {
 	struct uart_amba_port *uap =
@@ -1616,23 +1626,16 @@ static void pl011_set_mctrl(struct uart_port *port, unsigned int mctrl)
 
 	cr = pl011_read(uap, REG_CR);
 
-#define	TIOCMBIT(tiocmbit, uartbit)		\
-	if (mctrl & tiocmbit)		\
-		cr |= uartbit;		\
-	else				\
-		cr &= ~uartbit
-
-	TIOCMBIT(TIOCM_RTS, UART011_CR_RTS);
-	TIOCMBIT(TIOCM_DTR, UART011_CR_DTR);
-	TIOCMBIT(TIOCM_OUT1, UART011_CR_OUT1);
-	TIOCMBIT(TIOCM_OUT2, UART011_CR_OUT2);
-	TIOCMBIT(TIOCM_LOOP, UART011_CR_LBE);
+	pl011_assign_bit(mctrl & TIOCM_RTS, &cr, UART011_CR_RTS);
+	pl011_assign_bit(mctrl & TIOCM_DTR, &cr, UART011_CR_DTR);
+	pl011_assign_bit(mctrl & TIOCM_OUT1, &cr, UART011_CR_OUT1);
+	pl011_assign_bit(mctrl & TIOCM_OUT2, &cr, UART011_CR_OUT2);
+	pl011_assign_bit(mctrl & TIOCM_LOOP, &cr, UART011_CR_LBE);
 
 	if (port->status & UPSTAT_AUTORTS) {
 		/* We need to disable auto-RTS if we want to turn RTS off */
-		TIOCMBIT(TIOCM_RTS, UART011_CR_RTSEN);
+		pl011_assign_bit(mctrl & TIOCM_RTS, &cr, UART011_CR_RTSEN);
 	}
-#undef TIOCMBIT
 
 	pl011_write(cr, uap, REG_CR);
 }
-- 
GitLab


From fd64ff0966d39422f547d7935b8988e962f9f91e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:09 +0100
Subject: [PATCH 1424/4076] tty: serial: amba-pl011: avoid quoted string split
 across lines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove all instances of quoted strings split across lines. Fix four
checkpatch warnings:

    $ ./scripts/checkpatch.pl --strict --file \
        drivers/tty/serial/amba-pl011.c
    WARNING: quoted string split across lines
    [...]

Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-4-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 68d334df7091f..70996b939da00 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -973,8 +973,8 @@ static void pl011_dma_rx_irq(struct uart_amba_port *uap)
 	/* Switch buffer & re-trigger DMA job */
 	dmarx->use_buf_b = !dmarx->use_buf_b;
 	if (pl011_dma_rx_trigger_dma(uap)) {
-		dev_dbg(uap->port.dev, "could not retrigger RX DMA job "
-			"fall back to interrupt mode\n");
+		dev_dbg(uap->port.dev,
+			"could not retrigger RX DMA job fall back to interrupt mode\n");
 		uap->im |= UART011_RXIM;
 		pl011_write(uap->im, uap, REG_IMSC);
 	}
@@ -1021,8 +1021,8 @@ static void pl011_dma_rx_callback(void *data)
 	 * get some IRQ immediately from RX.
 	 */
 	if (ret) {
-		dev_dbg(uap->port.dev, "could not retrigger RX DMA job "
-			"fall back to interrupt mode\n");
+		dev_dbg(uap->port.dev,
+			"could not retrigger RX DMA job fall back to interrupt mode\n");
 		uap->im |= UART011_RXIM;
 		pl011_write(uap->im, uap, REG_IMSC);
 	}
@@ -1158,8 +1158,8 @@ skip_rx:
 
 	if (uap->using_rx_dma) {
 		if (pl011_dma_rx_trigger_dma(uap))
-			dev_dbg(uap->port.dev, "could not trigger initial "
-				"RX DMA job, fall back to interrupt mode\n");
+			dev_dbg(uap->port.dev,
+				"could not trigger initial RX DMA job, fall back to interrupt mode\n");
 		if (uap->dmarx.poll_rate) {
 			timer_setup(&uap->dmarx.timer, pl011_dma_rx_poll, 0);
 			mod_timer(&uap->dmarx.timer,
@@ -1391,8 +1391,8 @@ __acquires(&uap->port.lock)
 	 */
 	if (pl011_dma_rx_available(uap)) {
 		if (pl011_dma_rx_trigger_dma(uap)) {
-			dev_dbg(uap->port.dev, "could not trigger RX DMA job "
-				"fall back to interrupt mode again\n");
+			dev_dbg(uap->port.dev,
+				"could not trigger RX DMA job fall back to interrupt mode again\n");
 			uap->im |= UART011_RXIM;
 			pl011_write(uap->im, uap, REG_IMSC);
 		} else {
-- 
GitLab


From 28a7ec8c6679f594b4218090fe2932a647594fe2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:10 +0100
Subject: [PATCH 1425/4076] tty: serial: amba-pl011: fix formatting of
 conditions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following checkpatch warnings & checks:

	$ ./scripts/checkpatch.pl --strict --file \
        drivers/tty/serial/amba-pl011.c

    CHECK: Unbalanced braces around else statement
    CHECK: Unnecessary parentheses around '[...]'
    CHECK: braces {} should be used on all arms of this statement
    CHECK: Comparison to NULL could be written "[...]"
    WARNING: Comparisons should place the constant on the right side of the test

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-5-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 70996b939da00..ad812cb2e0fd3 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -330,10 +330,11 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap)
 				uap->port.icount.brk++;
 				if (uart_handle_break(&uap->port))
 					continue;
-			} else if (ch & UART011_DR_PE)
+			} else if (ch & UART011_DR_PE) {
 				uap->port.icount.parity++;
-			else if (ch & UART011_DR_FE)
+			} else if (ch & UART011_DR_FE) {
 				uap->port.icount.frame++;
+			}
 			if (ch & UART011_DR_OE)
 				uap->port.icount.overrun++;
 
@@ -464,7 +465,7 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 		 * If the controller does, check for suitable residue processing
 		 * otherwise assime all is well.
 		 */
-		if (0 == dma_get_slave_caps(chan, &caps)) {
+		if (dma_get_slave_caps(chan, &caps) == 0) {
 			if (caps.residue_granularity ==
 					DMA_RESIDUE_GRANULARITY_DESCRIPTOR) {
 				dma_release_channel(chan);
@@ -503,11 +504,11 @@ static void pl011_dma_probe(struct uart_amba_port *uap)
 			if (uap->dmarx.auto_poll_rate) {
 				u32 x;
 
-				if (0 == of_property_read_u32(dev->of_node, "poll-rate-ms", &x))
+				if (of_property_read_u32(dev->of_node, "poll-rate-ms", &x) == 0)
 					uap->dmarx.poll_rate = x;
 				else
 					uap->dmarx.poll_rate = 100;
-				if (0 == of_property_read_u32(dev->of_node, "poll-timeout-ms", &x))
+				if (of_property_read_u32(dev->of_node, "poll-timeout-ms", &x) == 0)
 					uap->dmarx.poll_timeout = x;
 				else
 					uap->dmarx.poll_timeout = 3000;
@@ -615,9 +616,9 @@ static int pl011_dma_tx_refill(struct uart_amba_port *uap)
 	if (count > PL011_DMA_BUFFER_SIZE)
 		count = PL011_DMA_BUFFER_SIZE;
 
-	if (xmit->tail < xmit->head)
+	if (xmit->tail < xmit->head) {
 		memcpy(&dmatx->buf[0], &xmit->buf[xmit->tail], count);
-	else {
+	} else {
 		size_t first = UART_XMIT_SIZE - xmit->tail;
 		size_t second;
 
@@ -751,8 +752,9 @@ static inline bool pl011_dma_tx_start(struct uart_amba_port *uap)
 			if (pl011_dma_tx_refill(uap) > 0) {
 				uap->im &= ~UART011_TXIM;
 				pl011_write(uap->im, uap, REG_IMSC);
-			} else
+			} else {
 				ret = false;
+			}
 		} else if (!(uap->dmacr & UART011_TXDMAE)) {
 			uap->dmacr |= UART011_TXDMAE;
 			pl011_write(uap->dmacr, uap, REG_DMACR);
@@ -2139,9 +2141,9 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios,
 	 * else we see data corruption.
 	 */
 	if (uap->vendor->oversampling) {
-		if ((baud >= 3000000) && (baud < 3250000) && (quot > 1))
+		if (baud >= 3000000 && baud < 3250000 && quot > 1)
 			quot -= 1;
-		else if ((baud > 3250000) && (quot > 2))
+		else if (baud > 3250000 && quot > 2)
 			quot -= 2;
 	}
 	/* Set baud rate */
@@ -2668,7 +2670,7 @@ static int pl011_probe_dt_alias(int index, struct device *dev)
 		ret = index;
 	} else {
 		seen_dev_with_alias = true;
-		if (ret >= ARRAY_SIZE(amba_ports) || amba_ports[ret] != NULL) {
+		if (ret >= ARRAY_SIZE(amba_ports) || amba_ports[ret]) {
 			dev_warn(dev, "requested serial port %d  not available.\n", ret);
 			ret = index;
 		}
@@ -2702,7 +2704,7 @@ static int pl011_find_free_port(void)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(amba_ports); i++)
-		if (amba_ports[i] == NULL)
+		if (!amba_ports[i])
 			return i;
 
 	return -EBUSY;
-- 
GitLab


From 826bd77ae5e8fec91a5fddb189adbdbaef3050ef Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:11 +0100
Subject: [PATCH 1426/4076] tty: serial: amba-pl011: fix miscellaneous
 checkpatch warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following messages from checkpatch:

    $ ./scripts/checkpatch.pl --strict --file \
        drivers/tty/serial/amba-pl011.c

    ERROR: do not initialise statics to false
    WARNING: Possible unnecessary 'out of memory' message
    WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
    WARNING: Prefer [subsystem eg: netdev]_info([subsystem]dev, ... then
             dev_info(dev, ... then pr_info(...  to
    CHECK: Prefer using the BIT macro

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-6-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index ad812cb2e0fd3..e15bfac5352d7 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -51,7 +51,7 @@
 #define AMBA_ISR_PASS_LIMIT	256
 
 #define UART_DR_ERROR		(UART011_DR_OE | UART011_DR_BE | UART011_DR_PE | UART011_DR_FE)
-#define UART_DUMMY_DR_RX	(1 << 16)
+#define UART_DUMMY_DR_RX	BIT(16)
 
 enum {
 	REG_DR,
@@ -1109,7 +1109,6 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 
 	uap->dmatx.buf = kmalloc(PL011_DMA_BUFFER_SIZE, GFP_KERNEL | __GFP_DMA);
 	if (!uap->dmatx.buf) {
-		dev_err(uap->port.dev, "no memory for DMA TX buffer\n");
 		uap->port.fifosize = uap->fifosize;
 		return;
 	}
@@ -2528,7 +2527,7 @@ static void qdf2400_e44_putc(struct uart_port *port, unsigned char c)
 		cpu_relax();
 }
 
-static void qdf2400_e44_early_write(struct console *con, const char *s, unsigned n)
+static void qdf2400_e44_early_write(struct console *con, const char *s, unsigned int n)
 {
 	struct earlycon_device *dev = con->data;
 
@@ -2547,7 +2546,7 @@ static void pl011_putc(struct uart_port *port, unsigned char c)
 		cpu_relax();
 }
 
-static void pl011_early_write(struct console *con, const char *s, unsigned n)
+static void pl011_early_write(struct console *con, const char *s, unsigned int n)
 {
 	struct earlycon_device *dev = con->data;
 
@@ -2653,8 +2652,8 @@ static struct uart_driver amba_reg = {
 static int pl011_probe_dt_alias(int index, struct device *dev)
 {
 	struct device_node *np;
-	static bool seen_dev_with_alias = false;
-	static bool seen_dev_without_alias = false;
+	static bool seen_dev_with_alias;
+	static bool seen_dev_without_alias;
 	int ret = index;
 
 	if (!IS_ENABLED(CONFIG_OF))
@@ -2995,7 +2994,7 @@ static struct amba_driver pl011_driver = {
 
 static int __init pl011_init(void)
 {
-	printk(KERN_INFO "Serial: AMBA PL011 UART driver\n");
+	pr_info("Serial: AMBA PL011 UART driver\n");
 
 	if (platform_driver_register(&arm_sbsa_uart_platform_driver))
 		pr_warn("could not register SBSA UART platform driver\n");
-- 
GitLab


From 8ff87406c29b43fa0d807ce80601c94821cab9bc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:12 +0100
Subject: [PATCH 1427/4076] tty: serial: amba-pl011: unindent
 pl011_console_get_options function body
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The whole function body is encapsulated inside an if-condition. Reverse
the if logic and early return to remove one indentation level.

Also turn two nested ifs into a single one at the end of the function.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-7-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 43 ++++++++++++++++-----------------
 1 file changed, 21 insertions(+), 22 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index e15bfac5352d7..8e129c58c44b5 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2363,35 +2363,34 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 static void pl011_console_get_options(struct uart_amba_port *uap, int *baud,
 				      int *parity, int *bits)
 {
-	if (pl011_read(uap, REG_CR) & UART01x_CR_UARTEN) {
-		unsigned int lcr_h, ibrd, fbrd;
+	unsigned int lcr_h, ibrd, fbrd;
 
-		lcr_h = pl011_read(uap, REG_LCRH_TX);
+	if (!(pl011_read(uap, REG_CR) & UART01x_CR_UARTEN))
+		return;
 
-		*parity = 'n';
-		if (lcr_h & UART01x_LCRH_PEN) {
-			if (lcr_h & UART01x_LCRH_EPS)
-				*parity = 'e';
-			else
-				*parity = 'o';
-		}
+	lcr_h = pl011_read(uap, REG_LCRH_TX);
 
-		if ((lcr_h & 0x60) == UART01x_LCRH_WLEN_7)
-			*bits = 7;
+	*parity = 'n';
+	if (lcr_h & UART01x_LCRH_PEN) {
+		if (lcr_h & UART01x_LCRH_EPS)
+			*parity = 'e';
 		else
-			*bits = 8;
+			*parity = 'o';
+	}
 
-		ibrd = pl011_read(uap, REG_IBRD);
-		fbrd = pl011_read(uap, REG_FBRD);
+	if ((lcr_h & 0x60) == UART01x_LCRH_WLEN_7)
+		*bits = 7;
+	else
+		*bits = 8;
 
-		*baud = uap->port.uartclk * 4 / (64 * ibrd + fbrd);
+	ibrd = pl011_read(uap, REG_IBRD);
+	fbrd = pl011_read(uap, REG_FBRD);
 
-		if (uap->vendor->oversampling) {
-			if (pl011_read(uap, REG_CR)
-				  & ST_UART011_CR_OVSFACT)
-				*baud *= 2;
-		}
-	}
+	*baud = uap->port.uartclk * 4 / (64 * ibrd + fbrd);
+
+	if (uap->vendor->oversampling &&
+	    (pl011_read(uap, REG_CR) & ST_UART011_CR_OVSFACT))
+		*baud *= 2;
 }
 
 static int pl011_console_setup(struct console *co, char *options)
-- 
GitLab


From a49a8b9d7cf5da42e61d73bd502b5a0e2b7e61c3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:13 +0100
Subject: [PATCH 1428/4076] tty: serial: amba-pl011: factor QDF2400 SoC erratum
 44 out of probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On this platform, different vendor data is used. That requires a
compile-time check as we access (1) a global boolean & (2) our local
vendor data. Both symbols are accessible only when
CONFIG_ACPI_SPCR_TABLE is enabled.

Factor the vendor data overriding to a separate function that is empty
when CONFIG_ACPI_SPCR_TABLE is not defined.

Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-8-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/amba-pl011.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 8e129c58c44b5..fccec1698a541 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2869,6 +2869,22 @@ static int pl011_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(pl011_dev_pm_ops, pl011_suspend, pl011_resume);
 
+#ifdef CONFIG_ACPI_SPCR_TABLE
+static void qpdf2400_erratum44_workaround(struct device *dev,
+					  struct uart_amba_port *uap)
+{
+	if (!qdf2400_e44_present)
+		return;
+
+	dev_info(dev, "working around QDF2400 SoC erratum 44\n");
+	uap->vendor = &vendor_qdt_qdf2400_e44;
+}
+#else
+static void qpdf2400_erratum44_workaround(struct device *dev,
+					  struct uart_amba_port *uap)
+{ /* empty */ }
+#endif
+
 static int sbsa_uart_probe(struct platform_device *pdev)
 {
 	struct uart_amba_port *uap;
@@ -2904,13 +2920,8 @@ static int sbsa_uart_probe(struct platform_device *pdev)
 		return ret;
 	uap->port.irq	= ret;
 
-#ifdef CONFIG_ACPI_SPCR_TABLE
-	if (qdf2400_e44_present) {
-		dev_info(&pdev->dev, "working around QDF2400 SoC erratum 44\n");
-		uap->vendor = &vendor_qdt_qdf2400_e44;
-	} else
-#endif
-		uap->vendor = &vendor_sbsa;
+	uap->vendor = &vendor_sbsa;
+	qpdf2400_erratum44_workaround(&pdev->dev, uap);
 
 	uap->reg_offset	= uap->vendor->reg_offset;
 	uap->fifosize	= 32;
-- 
GitLab


From 43f012df3c1e979966524f79b5371fde6545488a Mon Sep 17 00:00:00 2001
From: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Date: Thu, 14 Dec 2023 14:02:34 +0800
Subject: [PATCH 1429/4076] tty: serial: 8250: Set RS422 interface by default
 to fix Moxa RS422/RS485 PCIe boards

MOXA PCIe RS422/RS485 boards will not function by default because of the
initial default serial interface of all MOXA PCIe boards is set to
RS232.

This patch fixes the problem above by setting the initial default serial
interface to RS422 for those MOXA RS422/RS485 PCIe boards.

Signed-off-by: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231214060234.6147-1-crescentcy.hsieh@moxa.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci.c | 58 +++++++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 614be0f13a313..8ccf691935b75 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -19,6 +19,7 @@
 #include <linux/serial_core.h>
 #include <linux/8250_pci.h>
 #include <linux/bitops.h>
+#include <linux/bitfield.h>
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
@@ -1970,6 +1971,20 @@ pci_sunix_setup(struct serial_private *priv,
 
 #define MOXA_GPIO_PIN2	BIT(2)
 
+#define MOXA_RS232	0x00
+#define MOXA_RS422	0x01
+#define MOXA_RS485_4W	0x0B
+#define MOXA_RS485_2W	0x0F
+#define MOXA_UIR_OFFSET	0x04
+#define MOXA_EVEN_RS_MASK	GENMASK(3, 0)
+#define MOXA_ODD_RS_MASK	GENMASK(7, 4)
+
+enum {
+	MOXA_SUPP_RS232 = BIT(0),
+	MOXA_SUPP_RS422 = BIT(1),
+	MOXA_SUPP_RS485 = BIT(2),
+};
+
 static bool pci_moxa_is_mini_pcie(unsigned short device)
 {
 	if (device == PCI_DEVICE_ID_MOXA_CP102N	||
@@ -1983,13 +1998,54 @@ static bool pci_moxa_is_mini_pcie(unsigned short device)
 	return false;
 }
 
+static unsigned int pci_moxa_supported_rs(struct pci_dev *dev)
+{
+	switch (dev->device & 0x0F00) {
+	case 0x0000:
+	case 0x0600:
+		return MOXA_SUPP_RS232;
+	case 0x0100:
+		return MOXA_SUPP_RS232 | MOXA_SUPP_RS422 | MOXA_SUPP_RS485;
+	case 0x0300:
+		return MOXA_SUPP_RS422 | MOXA_SUPP_RS485;
+	}
+	return 0;
+}
+
+static int pci_moxa_set_interface(const struct pci_dev *dev,
+				  unsigned int port_idx,
+				  u8 mode)
+{
+	resource_size_t iobar_addr = pci_resource_start(dev, 2);
+	resource_size_t UIR_addr = iobar_addr + MOXA_UIR_OFFSET + port_idx / 2;
+	u8 val;
+
+	val = inb(UIR_addr);
+
+	if (port_idx % 2) {
+		val &= ~MOXA_ODD_RS_MASK;
+		val |= FIELD_PREP(MOXA_ODD_RS_MASK, mode);
+	} else {
+		val &= ~MOXA_EVEN_RS_MASK;
+		val |= FIELD_PREP(MOXA_EVEN_RS_MASK, mode);
+	}
+	outb(val, UIR_addr);
+
+	return 0;
+}
+
 static int pci_moxa_init(struct pci_dev *dev)
 {
 	unsigned short device = dev->device;
 	resource_size_t iobar_addr = pci_resource_start(dev, 2);
-	unsigned int num_ports = (device & 0x00F0) >> 4;
+	unsigned int num_ports = (device & 0x00F0) >> 4, i;
 	u8 val;
 
+	if (!(pci_moxa_supported_rs(dev) & MOXA_SUPP_RS232)) {
+		for (i = 0; i < num_ports; ++i)
+			pci_moxa_set_interface(dev, i, MOXA_RS422);
+	}
+
 	/*
 	 * Enable hardware buffer to prevent break signal output when system boots up.
 	 * This hardware buffer is only supported on Mini PCIe series.
-- 
GitLab


From ebe7f3393784857c487bf82f86813a8b1384e278 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 14 Dec 2023 17:46:53 +0200
Subject: [PATCH 1430/4076] pinctrl: intel: Add Intel Meteor Point pin
 controller and GPIO support

This driver supports pinctrl/GPIO hardware found on Intel Meteor Point
(a Meteor Lake PCH) providing users a pinctrl and GPIO interfaces
including GPIO interrupts.

Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/Kconfig               |   9 +
 drivers/pinctrl/intel/Makefile              |   1 +
 drivers/pinctrl/intel/pinctrl-meteorpoint.c | 465 ++++++++++++++++++++
 3 files changed, 475 insertions(+)
 create mode 100644 drivers/pinctrl/intel/pinctrl-meteorpoint.c

diff --git a/drivers/pinctrl/intel/Kconfig b/drivers/pinctrl/intel/Kconfig
index d9bdd0e0e8a2b..2101d30bd66c1 100644
--- a/drivers/pinctrl/intel/Kconfig
+++ b/drivers/pinctrl/intel/Kconfig
@@ -138,6 +138,15 @@ config PINCTRL_METEORLAKE
 	  This pinctrl driver provides an interface that allows configuring
 	  of Intel Meteor Lake pins and using them as GPIOs.
 
+config PINCTRL_METEORPOINT
+	tristate "Intel Meteor Point pinctrl and GPIO driver"
+	depends on ACPI
+	select PINCTRL_INTEL
+	help
+	  Meteor Point is the PCH of Intel Meteor Lake. This pinctrl driver
+	  provides an interface that allows configuring of PCH pins and
+	  using them as GPIOs.
+
 config PINCTRL_SUNRISEPOINT
 	tristate "Intel Sunrisepoint pinctrl and GPIO driver"
 	select PINCTRL_INTEL
diff --git a/drivers/pinctrl/intel/Makefile b/drivers/pinctrl/intel/Makefile
index 96c93ed4bd580..d0d868c9a6229 100644
--- a/drivers/pinctrl/intel/Makefile
+++ b/drivers/pinctrl/intel/Makefile
@@ -22,5 +22,6 @@ obj-$(CONFIG_PINCTRL_JASPERLAKE)	+= pinctrl-jasperlake.o
 obj-$(CONFIG_PINCTRL_LAKEFIELD)		+= pinctrl-lakefield.o
 obj-$(CONFIG_PINCTRL_LEWISBURG)		+= pinctrl-lewisburg.o
 obj-$(CONFIG_PINCTRL_METEORLAKE)	+= pinctrl-meteorlake.o
+obj-$(CONFIG_PINCTRL_METEORPOINT)	+= pinctrl-meteorpoint.o
 obj-$(CONFIG_PINCTRL_SUNRISEPOINT)	+= pinctrl-sunrisepoint.o
 obj-$(CONFIG_PINCTRL_TIGERLAKE)		+= pinctrl-tigerlake.o
diff --git a/drivers/pinctrl/intel/pinctrl-meteorpoint.c b/drivers/pinctrl/intel/pinctrl-meteorpoint.c
new file mode 100644
index 0000000000000..77e97775a60b1
--- /dev/null
+++ b/drivers/pinctrl/intel/pinctrl-meteorpoint.c
@@ -0,0 +1,465 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Meteor Point PCH pinctrl/GPIO driver
+ *
+ * Copyright (C) 2022-2023, Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-intel.h"
+
+#define MTP_PAD_OWN	0x0b0
+#define MTP_PADCFGLOCK	0x110
+#define MTP_HOSTSW_OWN	0x150
+#define MTP_GPI_IS	0x200
+#define MTP_GPI_IE	0x220
+
+#define MTP_GPP(r, s, e, g)				\
+	{						\
+		.reg_num = (r),				\
+		.base = (s),				\
+		.size = ((e) - (s) + 1),		\
+		.gpio_base = (g),			\
+	}
+
+#define MTP_COMMUNITY(b, s, e, g)			\
+	INTEL_COMMUNITY_GPPS(b, s, e, g, MTP)
+
+/* Meteor Point-S */
+static const struct pinctrl_pin_desc mtps_pins[] = {
+	/* GPP_D */
+	PINCTRL_PIN(0, "GPP_D_0"),
+	PINCTRL_PIN(1, "GPP_D_1"),
+	PINCTRL_PIN(2, "GPP_D_2"),
+	PINCTRL_PIN(3, "GPP_D_3"),
+	PINCTRL_PIN(4, "GPP_D_4"),
+	PINCTRL_PIN(5, "CNV_RF_RESET_B"),
+	PINCTRL_PIN(6, "CRF_CLKREQ"),
+	PINCTRL_PIN(7, "GPP_D_7"),
+	PINCTRL_PIN(8, "GPP_D_8"),
+	PINCTRL_PIN(9, "SML0CLK"),
+	PINCTRL_PIN(10, "SML0DATA"),
+	PINCTRL_PIN(11, "GPP_D_11"),
+	PINCTRL_PIN(12, "GPP_D_12"),
+	PINCTRL_PIN(13, "GPP_D_13"),
+	PINCTRL_PIN(14, "GPP_D_14"),
+	PINCTRL_PIN(15, "GPP_D_15"),
+	PINCTRL_PIN(16, "GPP_D_16"),
+	PINCTRL_PIN(17, "GPP_D_17"),
+	PINCTRL_PIN(18, "GPP_D_18"),
+	PINCTRL_PIN(19, "GPP_D_19"),
+	PINCTRL_PIN(20, "GPP_D_20"),
+	PINCTRL_PIN(21, "GPP_D_21"),
+	PINCTRL_PIN(22, "GPP_D_22"),
+	PINCTRL_PIN(23, "GPP_D_23"),
+	PINCTRL_PIN(24, "GSPI3_CLK_LOOPBK"),
+	/* GPP_R */
+	PINCTRL_PIN(25, "HDA_BCLK"),
+	PINCTRL_PIN(26, "HDA_SYNC"),
+	PINCTRL_PIN(27, "HDA_SDO"),
+	PINCTRL_PIN(28, "HDA_SDI_0"),
+	PINCTRL_PIN(29, "HDA_RSTB"),
+	PINCTRL_PIN(30, "GPP_R_5"),
+	PINCTRL_PIN(31, "GPP_R_6"),
+	PINCTRL_PIN(32, "GPP_R_7"),
+	PINCTRL_PIN(33, "GPP_R_8"),
+	PINCTRL_PIN(34, "GPP_R_9"),
+	PINCTRL_PIN(35, "GPP_R_10"),
+	PINCTRL_PIN(36, "GPP_R_11"),
+	PINCTRL_PIN(37, "GPP_R_12"),
+	PINCTRL_PIN(38, "GSPI2_CLK_LOOPBK"),
+	/* GPP_J */
+	PINCTRL_PIN(39, "GPP_J_0"),
+	PINCTRL_PIN(40, "CNV_BRI_DT"),
+	PINCTRL_PIN(41, "CNV_BRI_RSP"),
+	PINCTRL_PIN(42, "CNV_RGI_DT"),
+	PINCTRL_PIN(43, "CNV_RGI_RSP"),
+	PINCTRL_PIN(44, "GPP_J_5"),
+	PINCTRL_PIN(45, "GPP_J_6"),
+	PINCTRL_PIN(46, "BOOTHALT_B"),
+	PINCTRL_PIN(47, "RTCCLKOUT"),
+	PINCTRL_PIN(48, "BPKI3C_SDA"),
+	PINCTRL_PIN(49, "BPKI3C_SCL"),
+	PINCTRL_PIN(50, "DAM"),
+	PINCTRL_PIN(51, "HDACPU_SDI"),
+	PINCTRL_PIN(52, "HDACPU_SDO"),
+	PINCTRL_PIN(53, "HDACPU_BCLK"),
+	PINCTRL_PIN(54, "AUX_PWRGD"),
+	PINCTRL_PIN(55, "GLB_RST_WARN_B"),
+	PINCTRL_PIN(56, "RESET_SYNCB"),
+	/* vGPIO */
+	PINCTRL_PIN(57, "CNV_BTEN"),
+	PINCTRL_PIN(58, "CNV_BT_HOST_WAKEB"),
+	PINCTRL_PIN(59, "CNV_BT_IF_SELECT"),
+	PINCTRL_PIN(60, "vCNV_BT_UART_TXD"),
+	PINCTRL_PIN(61, "vCNV_BT_UART_RXD"),
+	PINCTRL_PIN(62, "vCNV_BT_UART_CTS_B"),
+	PINCTRL_PIN(63, "vCNV_BT_UART_RTS_B"),
+	PINCTRL_PIN(64, "vCNV_MFUART1_TXD"),
+	PINCTRL_PIN(65, "vCNV_MFUART1_RXD"),
+	PINCTRL_PIN(66, "vCNV_MFUART1_CTS_B"),
+	PINCTRL_PIN(67, "vCNV_MFUART1_RTS_B"),
+	PINCTRL_PIN(68, "vUART0_TXD"),
+	PINCTRL_PIN(69, "vUART0_RXD"),
+	PINCTRL_PIN(70, "vUART0_CTS_B"),
+	PINCTRL_PIN(71, "vUART0_RTS_B"),
+	PINCTRL_PIN(72, "vISH_UART0_TXD"),
+	PINCTRL_PIN(73, "vISH_UART0_RXD"),
+	PINCTRL_PIN(74, "vISH_UART0_CTS_B"),
+	PINCTRL_PIN(75, "vISH_UART0_RTS_B"),
+	PINCTRL_PIN(76, "vCNV_BT_I2S_BCLK"),
+	PINCTRL_PIN(77, "vCNV_BT_I2S_WS_SYNC"),
+	PINCTRL_PIN(78, "vCNV_BT_I2S_SDO"),
+	PINCTRL_PIN(79, "vCNV_BT_I2S_SDI"),
+	PINCTRL_PIN(80, "vI2S2_SCLK"),
+	PINCTRL_PIN(81, "vI2S2_SFRM"),
+	PINCTRL_PIN(82, "vI2S2_TXD"),
+	PINCTRL_PIN(83, "vI2S2_RXD"),
+	PINCTRL_PIN(84, "THC0_WOT_INT"),
+	PINCTRL_PIN(85, "THC1_WOT_INT"),
+	PINCTRL_PIN(86, "THC0_WHC_INT"),
+	PINCTRL_PIN(87, "THC1_WHC_INT"),
+	/* GPP_A */
+	PINCTRL_PIN(88, "ESPI_IO_0"),
+	PINCTRL_PIN(89, "ESPI_IO_1"),
+	PINCTRL_PIN(90, "ESPI_IO_2"),
+	PINCTRL_PIN(91, "ESPI_IO_3"),
+	PINCTRL_PIN(92, "ESPI_CS0B"),
+	PINCTRL_PIN(93, "ESPI_CLK"),
+	PINCTRL_PIN(94, "ESPI_RESETB"),
+	PINCTRL_PIN(95, "ESPI_CS1B"),
+	PINCTRL_PIN(96, "ESPI_CS2B"),
+	PINCTRL_PIN(97, "ESPI_CS3B"),
+	PINCTRL_PIN(98, "ESPI_ALERT0B"),
+	PINCTRL_PIN(99, "ESPI_ALERT1B"),
+	PINCTRL_PIN(100, "ESPI_ALERT2B"),
+	PINCTRL_PIN(101, "ESPI_ALERT3B"),
+	PINCTRL_PIN(102, "ESPI_CLK_LOOPBK"),
+	/* DIR_ESPI */
+	PINCTRL_PIN(103, "PWRBTNB_OUT"),
+	PINCTRL_PIN(104, "DMI_PERSTB"),
+	PINCTRL_PIN(105, "DMI_CLKREQB"),
+	PINCTRL_PIN(106, "DIR_ESPI_IO_0"),
+	PINCTRL_PIN(107, "DIR_ESPI_IO_1"),
+	PINCTRL_PIN(108, "DIR_ESPI_IO_2"),
+	PINCTRL_PIN(109, "DIR_ESPI_IO_3"),
+	PINCTRL_PIN(110, "DIR_ESPI_CSB"),
+	PINCTRL_PIN(111, "DIR_ESPI_RESETB"),
+	PINCTRL_PIN(112, "DIR_ESPI_CLK"),
+	PINCTRL_PIN(113, "DIR_ESPI_RCLK"),
+	PINCTRL_PIN(114, "DIR_ESPI_ALERTB"),
+	/* GPP_B */
+	PINCTRL_PIN(115, "GPP_B_0"),
+	PINCTRL_PIN(116, "GPP_B_1"),
+	PINCTRL_PIN(117, "GPP_B_2"),
+	PINCTRL_PIN(118, "GPP_B_3"),
+	PINCTRL_PIN(119, "GPP_B_4"),
+	PINCTRL_PIN(120, "GPP_B_5"),
+	PINCTRL_PIN(121, "CLKOUT_48"),
+	PINCTRL_PIN(122, "GPP_B_7"),
+	PINCTRL_PIN(123, "GPP_B_8"),
+	PINCTRL_PIN(124, "GPP_B_9"),
+	PINCTRL_PIN(125, "GPP_B_10"),
+	PINCTRL_PIN(126, "GPP_B_11"),
+	PINCTRL_PIN(127, "SLP_S0B"),
+	PINCTRL_PIN(128, "PLTRSTB"),
+	PINCTRL_PIN(129, "GPP_B_14"),
+	PINCTRL_PIN(130, "GPP_B_15"),
+	PINCTRL_PIN(131, "GPP_B_16"),
+	PINCTRL_PIN(132, "GPP_B_17"),
+	PINCTRL_PIN(133, "GPP_B_18"),
+	PINCTRL_PIN(134, "FUSA_DIAGTEST_EN"),
+	PINCTRL_PIN(135, "FUSA_DIAGTEST_MODE"),
+	PINCTRL_PIN(136, "GPP_B_21"),
+	/* SPI0 */
+	PINCTRL_PIN(137, "SPI0_IO_2"),
+	PINCTRL_PIN(138, "SPI0_IO_3"),
+	PINCTRL_PIN(139, "SPI0_MOSI_IO_0"),
+	PINCTRL_PIN(140, "SPI0_MISO_IO_1"),
+	PINCTRL_PIN(141, "SPI0_TPM_CSB"),
+	PINCTRL_PIN(142, "SPI0_FLASH_0_CSB"),
+	PINCTRL_PIN(143, "SPI0_FLASH_1_CSB"),
+	PINCTRL_PIN(144, "SPI0_CLK"),
+	PINCTRL_PIN(145, "SPI0_CLK_LOOPBK"),
+	/* GPP_C */
+	PINCTRL_PIN(146, "SMBCLK"),
+	PINCTRL_PIN(147, "SMBDATA"),
+	PINCTRL_PIN(148, "SMBALERTB"),
+	PINCTRL_PIN(149, "GPP_C_3"),
+	PINCTRL_PIN(150, "GPP_C_4"),
+	PINCTRL_PIN(151, "GPP_C_5"),
+	PINCTRL_PIN(152, "GPP_C_6"),
+	PINCTRL_PIN(153, "GPP_C_7"),
+	PINCTRL_PIN(154, "GPP_C_8"),
+	PINCTRL_PIN(155, "GPP_C_9"),
+	PINCTRL_PIN(156, "GPP_C_10"),
+	PINCTRL_PIN(157, "GPP_C_11"),
+	PINCTRL_PIN(158, "GPP_C_12"),
+	PINCTRL_PIN(159, "GPP_C_13"),
+	PINCTRL_PIN(160, "GPP_C_14"),
+	PINCTRL_PIN(161, "GPP_C_15"),
+	PINCTRL_PIN(162, "GPP_C_16"),
+	PINCTRL_PIN(163, "GPP_C_17"),
+	PINCTRL_PIN(164, "GPP_C_18"),
+	PINCTRL_PIN(165, "GPP_C_19"),
+	PINCTRL_PIN(166, "GPP_C_20"),
+	PINCTRL_PIN(167, "GPP_C_21"),
+	PINCTRL_PIN(168, "GPP_C_22"),
+	PINCTRL_PIN(169, "GPP_C_23"),
+	/* GPP_H */
+	PINCTRL_PIN(170, "GPP_H_0"),
+	PINCTRL_PIN(171, "GPP_H_1"),
+	PINCTRL_PIN(172, "GPP_H_2"),
+	PINCTRL_PIN(173, "GPP_H_3"),
+	PINCTRL_PIN(174, "GPP_H_4"),
+	PINCTRL_PIN(175, "GPP_H_5"),
+	PINCTRL_PIN(176, "GPP_H_6"),
+	PINCTRL_PIN(177, "GPP_H_7"),
+	PINCTRL_PIN(178, "GPP_H_8"),
+	PINCTRL_PIN(179, "GPP_H_9"),
+	PINCTRL_PIN(180, "GPP_H_10"),
+	PINCTRL_PIN(181, "GPP_H_11"),
+	PINCTRL_PIN(182, "GPP_H_12"),
+	PINCTRL_PIN(183, "GPP_H_13"),
+	PINCTRL_PIN(184, "GPP_H_14"),
+	PINCTRL_PIN(185, "GPP_H_15"),
+	PINCTRL_PIN(186, "GPP_H_16"),
+	PINCTRL_PIN(187, "GPP_H_17"),
+	PINCTRL_PIN(188, "GPP_H_18"),
+	PINCTRL_PIN(189, "GPP_H_19"),
+	/* vGPIO_3 */
+	PINCTRL_PIN(190, "CPU_PCIE_LNK_DN_0"),
+	PINCTRL_PIN(191, "CPU_PCIE_LNK_DN_1"),
+	PINCTRL_PIN(192, "CPU_PCIE_LNK_DN_2"),
+	PINCTRL_PIN(193, "CPU_PCIE_LNK_DN_3"),
+	/* vGPIO_0 */
+	PINCTRL_PIN(194, "ESPI_USB_OCB_0"),
+	PINCTRL_PIN(195, "ESPI_USB_OCB_1"),
+	PINCTRL_PIN(196, "ESPI_USB_OCB_2"),
+	PINCTRL_PIN(197, "ESPI_USB_OCB_3"),
+	PINCTRL_PIN(198, "USB_CPU_OCB_0"),
+	PINCTRL_PIN(199, "USB_CPU_OCB_1"),
+	PINCTRL_PIN(200, "USB_CPU_OCB_2"),
+	PINCTRL_PIN(201, "USB_CPU_OCB_3"),
+	/* vGPIO_4 */
+	PINCTRL_PIN(202, "ESPI_ISCLK_XTAL_CLKREQ"),
+	PINCTRL_PIN(203, "ISCLK_ESPI_XTAL_CLKACK"),
+	PINCTRL_PIN(204, "ME_SLPC_FTPM_ENABLE"),
+	PINCTRL_PIN(205, "GP_SLPC_DTFUS_CORE_SPITPM_DIS"),
+	PINCTRL_PIN(206, "GP_SLPC_SPI_STRAP_TOS"),
+	PINCTRL_PIN(207, "GP_SLPC_DTFUS_CORE_SPITPM_DIS_L01"),
+	PINCTRL_PIN(208, "GP_SLPC_SPI_STRAP_TOS_L01"),
+	PINCTRL_PIN(209, "LPC_PRR_TS_OVR"),
+	PINCTRL_PIN(210, "ITSS_KU1_SHTDWN"),
+	PINCTRL_PIN(211, "vGPIO_SPARE_0"),
+	PINCTRL_PIN(212, "vGPIO_SPARE_1"),
+	PINCTRL_PIN(213, "vGPIO_SPARE_2"),
+	PINCTRL_PIN(214, "vGPIO_SPARE_3"),
+	PINCTRL_PIN(215, "vGPIO_SPARE_4"),
+	PINCTRL_PIN(216, "vGPIO_SPARE_5"),
+	PINCTRL_PIN(217, "vGPIO_SPARE_6"),
+	PINCTRL_PIN(218, "vGPIO_SPARE_7"),
+	PINCTRL_PIN(219, "vGPIO_SPARE_8"),
+	PINCTRL_PIN(220, "vGPIO_SPARE_9"),
+	PINCTRL_PIN(221, "vGPIO_SPARE_10"),
+	PINCTRL_PIN(222, "vGPIO_SPARE_11"),
+	PINCTRL_PIN(223, "vGPIO_SPARE_12"),
+	PINCTRL_PIN(224, "vGPIO_SPARE_13"),
+	PINCTRL_PIN(225, "vGPIO_SPARE_14"),
+	PINCTRL_PIN(226, "vGPIO_SPARE_15"),
+	PINCTRL_PIN(227, "vGPIO_SPARE_16"),
+	PINCTRL_PIN(228, "vGPIO_SPARE_17"),
+	PINCTRL_PIN(229, "vGPIO_SPARE_18"),
+	PINCTRL_PIN(230, "vGPIO_SPARE_19"),
+	PINCTRL_PIN(231, "vGPIO_SPARE_20"),
+	PINCTRL_PIN(232, "vGPIO_SPARE_21"),
+	/* GPP_S */
+	PINCTRL_PIN(233, "GPP_S_0"),
+	PINCTRL_PIN(234, "GPP_S_1"),
+	PINCTRL_PIN(235, "GPP_S_2"),
+	PINCTRL_PIN(236, "GPP_S_3"),
+	PINCTRL_PIN(237, "GPP_S_4"),
+	PINCTRL_PIN(238, "GPP_S_5"),
+	PINCTRL_PIN(239, "GPP_S_6"),
+	PINCTRL_PIN(240, "GPP_S_7"),
+	/* GPP_E */
+	PINCTRL_PIN(241, "GPP_E_0"),
+	PINCTRL_PIN(242, "GPP_E_1"),
+	PINCTRL_PIN(243, "GPP_E_2"),
+	PINCTRL_PIN(244, "GPP_E_3"),
+	PINCTRL_PIN(245, "GPP_E_4"),
+	PINCTRL_PIN(246, "GPP_E_5"),
+	PINCTRL_PIN(247, "GPP_E_6"),
+	PINCTRL_PIN(248, "GPP_E_7"),
+	PINCTRL_PIN(249, "GPP_E_8"),
+	PINCTRL_PIN(250, "GPP_E_9"),
+	PINCTRL_PIN(251, "GPP_E_10"),
+	PINCTRL_PIN(252, "GPP_E_11"),
+	PINCTRL_PIN(253, "GPP_E_12"),
+	PINCTRL_PIN(254, "GPP_E_13"),
+	PINCTRL_PIN(255, "GPP_E_14"),
+	PINCTRL_PIN(256, "GPP_E_15"),
+	PINCTRL_PIN(257, "GPP_E_16"),
+	PINCTRL_PIN(258, "GPP_E_17"),
+	PINCTRL_PIN(259, "GPP_E_18"),
+	PINCTRL_PIN(260, "GPP_E_19"),
+	PINCTRL_PIN(261, "GPP_E_20"),
+	PINCTRL_PIN(262, "GPP_E_21"),
+	PINCTRL_PIN(263, "SPI1_CLK_LOOPBK"),
+	/* GPP_K */
+	PINCTRL_PIN(264, "GPP_K_0"),
+	PINCTRL_PIN(265, "GPP_K_1"),
+	PINCTRL_PIN(266, "GPP_K_2"),
+	PINCTRL_PIN(267, "GPP_K_3"),
+	PINCTRL_PIN(268, "GPP_K_4"),
+	PINCTRL_PIN(269, "GPP_K_5"),
+	PINCTRL_PIN(270, "FUSE_SORT_BUMP_0"),
+	PINCTRL_PIN(271, "FUSE_SORT_BUMP_1"),
+	PINCTRL_PIN(272, "CORE_VID_0"),
+	PINCTRL_PIN(273, "CORE_VID_1"),
+	PINCTRL_PIN(274, "FUSE_SORT_BUMP_2"),
+	PINCTRL_PIN(275, "MISC_SPARE"),
+	PINCTRL_PIN(276, "SYS_RESETB"),
+	PINCTRL_PIN(277, "MLK_RSTB"),
+	/* GPP_F */
+	PINCTRL_PIN(278, "SATAXPCIE_3"),
+	PINCTRL_PIN(279, "SATAXPCIE_4"),
+	PINCTRL_PIN(280, "SATAXPCIE_5"),
+	PINCTRL_PIN(281, "SATAXPCIE_6"),
+	PINCTRL_PIN(282, "SATAXPCIE_7"),
+	PINCTRL_PIN(283, "SATA_DEVSLP_3"),
+	PINCTRL_PIN(284, "SATA_DEVSLP_4"),
+	PINCTRL_PIN(285, "SATA_DEVSLP_5"),
+	PINCTRL_PIN(286, "SATA_DEVSLP_6"),
+	PINCTRL_PIN(287, "GPP_F_9"),
+	PINCTRL_PIN(288, "GPP_F_10"),
+	PINCTRL_PIN(289, "GPP_F_11"),
+	PINCTRL_PIN(290, "GPP_F_12"),
+	PINCTRL_PIN(291, "GPP_F_13"),
+	PINCTRL_PIN(292, "GPP_F_14"),
+	PINCTRL_PIN(293, "GPP_F_15"),
+	PINCTRL_PIN(294, "GPP_F_16"),
+	PINCTRL_PIN(295, "GPP_F_17"),
+	PINCTRL_PIN(296, "GPP_F_18"),
+	PINCTRL_PIN(297, "DNX_FORCE_RELOAD"),
+	PINCTRL_PIN(298, "GPP_F_20"),
+	PINCTRL_PIN(299, "GPP_F_21"),
+	PINCTRL_PIN(300, "GPP_F_22"),
+	PINCTRL_PIN(301, "GPP_F_23"),
+	/* GPP_I */
+	PINCTRL_PIN(302, "GPP_I_0"),
+	PINCTRL_PIN(303, "GPP_I_1"),
+	PINCTRL_PIN(304, "GPP_I_2"),
+	PINCTRL_PIN(305, "GPP_I_3"),
+	PINCTRL_PIN(306, "GPP_I_4"),
+	PINCTRL_PIN(307, "GPP_I_5"),
+	PINCTRL_PIN(308, "GPP_I_6"),
+	PINCTRL_PIN(309, "GPP_I_7"),
+	PINCTRL_PIN(310, "GPP_I_8"),
+	PINCTRL_PIN(311, "GPP_I_9"),
+	PINCTRL_PIN(312, "GPP_I_10"),
+	PINCTRL_PIN(313, "GPP_I_11"),
+	PINCTRL_PIN(314, "GPP_I_12"),
+	PINCTRL_PIN(315, "GPP_I_13"),
+	PINCTRL_PIN(316, "GPP_I_14"),
+	PINCTRL_PIN(317, "GPP_I_15"),
+	PINCTRL_PIN(318, "GPP_I_16"),
+	PINCTRL_PIN(319, "GSPI0_CLK_LOOPBK"),
+	PINCTRL_PIN(320, "GSPI1_CLK_LOOPBK"),
+	PINCTRL_PIN(321, "ISH_I3C0_CLK_LOOPBK"),
+	PINCTRL_PIN(322, "I3C0_CLK_LOOPBK"),
+	/* JTAG_CPU */
+	PINCTRL_PIN(323, "JTAG_TDO"),
+	PINCTRL_PIN(324, "JTAGX"),
+	PINCTRL_PIN(325, "PRDYB"),
+	PINCTRL_PIN(326, "PREQB"),
+	PINCTRL_PIN(327, "JTAG_TDI"),
+	PINCTRL_PIN(328, "JTAG_TMS"),
+	PINCTRL_PIN(329, "JTAG_TCK"),
+	PINCTRL_PIN(330, "DBG_PMODE"),
+	PINCTRL_PIN(331, "CPU_TRSTB"),
+	PINCTRL_PIN(332, "CPUPWRGD"),
+	PINCTRL_PIN(333, "PM_SPARE0"),
+	PINCTRL_PIN(334, "PM_SPARE1"),
+	PINCTRL_PIN(335, "CRASHLOG_TRIG_N"),
+	PINCTRL_PIN(336, "TRIGGER_IN"),
+	PINCTRL_PIN(337, "TRIGGER_OUT"),
+	PINCTRL_PIN(338, "FBRK_OUT_N"),
+};
+
+static const struct intel_padgroup mtps_community0_gpps[] = {
+	MTP_GPP(0, 0, 24, 0),		/* GPP_D */
+	MTP_GPP(1, 25, 38, 32),		/* GPP_R */
+	MTP_GPP(2, 39, 56, 64),		/* GPP_J */
+	MTP_GPP(3, 57, 87, 96),		/* vGPIO */
+};
+
+static const struct intel_padgroup mtps_community1_gpps[] = {
+	MTP_GPP(0, 88, 102, 128),	/* GPP_A */
+	MTP_GPP(1, 103, 114, 160),	/* DIR_ESPI */
+	MTP_GPP(2, 115, 136, 192),	/* GPP_B */
+};
+
+static const struct intel_padgroup mtps_community3_gpps[] = {
+	MTP_GPP(0, 137, 145, 224),	/* SPI0 */
+	MTP_GPP(1, 146, 169, 256),	/* GPP_C */
+	MTP_GPP(2, 170, 189, 288),	/* GPP_H */
+	MTP_GPP(3, 190, 193, 320),	/* vGPIO_3 */
+	MTP_GPP(4, 194, 201, 352),	/* vGPIO_0 */
+	MTP_GPP(5, 202, 232, 384),	/* vGPIO_4 */
+};
+
+static const struct intel_padgroup mtps_community4_gpps[] = {
+	MTP_GPP(0, 233, 240, 416),	/* GPP_S */
+	MTP_GPP(1, 241, 263, 448),	/* GPP_E */
+	MTP_GPP(2, 264, 277, 480),	/* GPP_K */
+	MTP_GPP(3, 278, 301, 512),	/* GPP_F */
+};
+
+static const struct intel_padgroup mtps_community5_gpps[] = {
+	MTP_GPP(0, 302, 322, 544),	/* GPP_I */
+	MTP_GPP(1, 323, 338, 576),	/* JTAG_CPU */
+};
+
+static const struct intel_community mtps_communities[] = {
+	MTP_COMMUNITY(0, 0, 87, mtps_community0_gpps),
+	MTP_COMMUNITY(1, 88, 136, mtps_community1_gpps),
+	MTP_COMMUNITY(2, 137, 232, mtps_community3_gpps),
+	MTP_COMMUNITY(3, 233, 301, mtps_community4_gpps),
+	MTP_COMMUNITY(4, 302, 338, mtps_community5_gpps),
+};
+
+static const struct intel_pinctrl_soc_data mtps_soc_data = {
+	.pins = mtps_pins,
+	.npins = ARRAY_SIZE(mtps_pins),
+	.communities = mtps_communities,
+	.ncommunities = ARRAY_SIZE(mtps_communities),
+};
+
+static const struct acpi_device_id mtp_pinctrl_acpi_match[] = {
+	{ "INTC1084", (kernel_ulong_t)&mtps_soc_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, mtp_pinctrl_acpi_match);
+
+static struct platform_driver mtp_pinctrl_driver = {
+	.probe = intel_pinctrl_probe_by_hid,
+	.driver = {
+		.name = "meteorpoint-pinctrl",
+		.acpi_match_table = mtp_pinctrl_acpi_match,
+		.pm = pm_sleep_ptr(&intel_pinctrl_pm_ops),
+	},
+};
+module_platform_driver(mtp_pinctrl_driver);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_DESCRIPTION("Intel Meteor Point PCH pinctrl/GPIO driver");
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(PINCTRL_INTEL);
-- 
GitLab


From a7565fc8399725d00cc006c35d0621a5cb5f9554 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 13 Dec 2023 14:40:14 -0800
Subject: [PATCH 1431/4076] mei: fix spellos in mei.h

For include/uapi/linux/mei.h, correct spellos reported by codespell.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Tomas Winkler <tomas.winkler@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231213224014.23187-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/mei.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h
index 171c5cce36411..68a0272e99b76 100644
--- a/include/uapi/linux/mei.h
+++ b/include/uapi/linux/mei.h
@@ -100,14 +100,14 @@ struct mei_connect_client_data_vtag {
  * a FW client on a tagged channel. From this point on, every read
  * and write will communicate with the associated FW client
  * on the tagged channel.
- * Upone close() the communication is terminated.
+ * Upon close() the communication is terminated.
  *
  * The IOCTL argument is a struct with a union that contains
  * the input parameter and the output parameter for this IOCTL.
  *
  * The input parameter is UUID of the FW Client, a vtag [0,255].
  * The output parameter is the properties of the FW client
- * (FW protocool version and max message size).
+ * (FW protocol version and max message size).
  *
  * Clients that do not support tagged connection
  * will respond with -EOPNOTSUPP.
-- 
GitLab


From ea0e635fe53409fc6c1060eb1851b986bf07061e Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Thu, 14 Dec 2023 16:37:52 +0200
Subject: [PATCH 1432/4076] mei: pxp: spdx should be at first line

Remove stray empty line at the beginning of the file
to have SPDX header t the first line.

Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/20231214143752.294008-1-tomas.winkler@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/pxp/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/misc/mei/pxp/Kconfig b/drivers/misc/mei/pxp/Kconfig
index 4029b96afc040..4f1ed9202cd9c 100644
--- a/drivers/misc/mei/pxp/Kconfig
+++ b/drivers/misc/mei/pxp/Kconfig
@@ -1,4 +1,3 @@
-
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (c) 2020, Intel Corporation. All rights reserved.
 #
-- 
GitLab


From 5370a431ef915b52697d25a5a32cbaf9a4cbef95 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Wed, 13 Dec 2023 11:40:55 +0200
Subject: [PATCH 1433/4076] mei: vsc: Rework firmware image names

Rework firmware image names with the users in mind---there's no need for
variation between firmware names, apart from connected sensors. All
supported SoCs use the same firmware, too.

Use a single set of firmware binaries and assume they'll be found under
intel/vsc directory.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Tested-by: Wentong Wu <wentong.wu@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231213094055.446611-1-sakari.ailus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/vsc-fw-loader.c | 72 +++++---------------------------
 1 file changed, 10 insertions(+), 62 deletions(-)

diff --git a/drivers/misc/mei/vsc-fw-loader.c b/drivers/misc/mei/vsc-fw-loader.c
index 3e151f06e85b7..ffa4ccd96a104 100644
--- a/drivers/misc/mei/vsc-fw-loader.c
+++ b/drivers/misc/mei/vsc-fw-loader.c
@@ -27,9 +27,6 @@
 #define VSC_EFUSE_ADDR			(VSC_ADDR_BASE + 0x038)
 #define VSC_STRAP_ADDR			(VSC_ADDR_BASE + 0x100)
 
-#define VSC_STRAP_KEY_SRC_MASK		BIT(0)
-#define VSC_STRAP_KEY_SRC_PRODUCT	1
-
 #define VSC_MAINSTEPPING_VERSION_MASK	GENMASK(7, 4)
 #define VSC_MAINSTEPPING_VERSION_A	0
 
@@ -49,22 +46,15 @@
 #define VSC_ROM_PKG_SIZE		256u
 #define VSC_FW_PKG_SIZE			512u
 
-#define VSC_CSI_IMAGE_NAME_FMT		"ivsc_fw_a1.bin"
-#define VSC_CSI_IMAGE_NAME_FMT_PROD	"ivsc_fw_a1_%s.bin"
-#define VSC_ACE_IMAGE_NAME_FMT		"ivsc_pkg_%s_0_a1.bin"
-#define VSC_ACE_IMAGE_NAME_FMT_PROD	"ivsc_pkg_%s_0_a1_%s.bin"
-#define VSC_CFG_IMAGE_NAME_FMT		"ivsc_skucfg_%s_0_1_a1.bin"
-#define VSC_CFG_IMAGE_NAME_FMT_PROD	"ivsc_skucfg_%s_0_1_a1_%s.bin"
+#define VSC_IMAGE_DIR			"intel/vsc/"
 
-#define VSC_IMAGE_FOLDER_FMT		"vsc/soc_a1"
-#define VSC_IMAGE_FOLDER_FMT_PROD	"vsc/soc_a1_%s"
+#define VSC_CSI_IMAGE_NAME		VSC_IMAGE_DIR "ivsc_fw.bin"
+#define VSC_ACE_IMAGE_NAME_FMT		VSC_IMAGE_DIR "ivsc_pkg_%s_0.bin"
+#define VSC_CFG_IMAGE_NAME_FMT		VSC_IMAGE_DIR "ivsc_skucfg_%s_0_1.bin"
 
-#define VSC_IMAGE_NAME_MAX_LEN		64
-#define VSC_IMAGE_PATH_MAX_LEN		128
+#define VSC_IMAGE_PATH_MAX_LEN		64
 
 #define VSC_SENSOR_NAME_MAX_LEN		16
-#define VSC_IMAGE_FOLDER_NAME_MAX_LEN	32
-#define VSC_IMAGE_NAME_SUFFIX_MAX_LEN	8
 
 /* command id */
 enum {
@@ -223,10 +213,7 @@ struct vsc_img_frag {
  * @rx_buf: rx buffer
  * @option: command option
  * @count: total image count
- * @key_src: key source
- * @folder: image folder
  * @sensor_name: camera sensor name
- * @suffix: image name suffix
  * @frags: image fragments
  */
 struct vsc_fw_loader {
@@ -242,11 +229,8 @@ struct vsc_fw_loader {
 
 	u16 option;
 	u16 count;
-	u32 key_src;
 
-	char folder[VSC_IMAGE_FOLDER_NAME_MAX_LEN];
 	char sensor_name[VSC_SENSOR_NAME_MAX_LEN];
-	char suffix[VSC_IMAGE_NAME_SUFFIX_MAX_LEN];
 
 	struct vsc_img_frag frags[VSC_IMG_FRAG_MAX];
 };
@@ -378,33 +362,18 @@ static int vsc_identify_silicon(struct vsc_fw_loader *fw_loader)
 	if (ack->token != VSC_TOKEN_DUMP_RESP)
 		return -EINVAL;
 
-	fw_loader->key_src = FIELD_GET(VSC_STRAP_KEY_SRC_MASK, ack->payload[2]);
-
-	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
-		strscpy(fw_loader->suffix, "prod", sizeof(fw_loader->suffix));
-
 	return 0;
 }
 
 static int vsc_identify_csi_image(struct vsc_fw_loader *fw_loader)
 {
-	char path[VSC_IMAGE_PATH_MAX_LEN];
-	char name[VSC_IMAGE_NAME_MAX_LEN];
 	const struct firmware *image;
 	struct vsc_fw_sign *sign;
 	struct vsc_img *img;
 	unsigned int i;
 	int ret;
 
-	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
-		snprintf(name, sizeof(name), VSC_CSI_IMAGE_NAME_FMT_PROD,
-			 fw_loader->suffix);
-	else
-		snprintf(name, sizeof(name), VSC_CSI_IMAGE_NAME_FMT);
-
-	snprintf(path, sizeof(path), "%s/%s", fw_loader->folder, name);
-
-	ret = request_firmware(&image, path, fw_loader->dev);
+	ret = request_firmware(&image, VSC_CSI_IMAGE_NAME, fw_loader->dev);
 	if (ret)
 		return ret;
 
@@ -480,21 +449,14 @@ err_release_image:
 static int vsc_identify_ace_image(struct vsc_fw_loader *fw_loader)
 {
 	char path[VSC_IMAGE_PATH_MAX_LEN];
-	char name[VSC_IMAGE_NAME_MAX_LEN];
 	const struct firmware *image;
 	struct vsc_fw_sign *sign;
 	struct vsc_img *img;
 	unsigned int i;
 	int ret;
 
-	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
-		snprintf(name, sizeof(name), VSC_ACE_IMAGE_NAME_FMT_PROD,
-			 fw_loader->sensor_name, fw_loader->suffix);
-	else
-		snprintf(name, sizeof(name), VSC_ACE_IMAGE_NAME_FMT,
-			 fw_loader->sensor_name);
-
-	snprintf(path, sizeof(path), "%s/%s", fw_loader->folder, name);
+	snprintf(path, sizeof(path), VSC_ACE_IMAGE_NAME_FMT,
+		 fw_loader->sensor_name);
 
 	ret = request_firmware(&image, path, fw_loader->dev);
 	if (ret)
@@ -571,19 +533,12 @@ static int vsc_identify_cfg_image(struct vsc_fw_loader *fw_loader)
 {
 	struct vsc_img_frag *frag = &fw_loader->frags[VSC_IMG_SKU_CFG_FRAG];
 	char path[VSC_IMAGE_PATH_MAX_LEN];
-	char name[VSC_IMAGE_NAME_MAX_LEN];
 	const struct firmware *image;
 	u32 size;
 	int ret;
 
-	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
-		snprintf(name, sizeof(name), VSC_CFG_IMAGE_NAME_FMT_PROD,
-			 fw_loader->sensor_name, fw_loader->suffix);
-	else
-		snprintf(name, sizeof(name), VSC_CFG_IMAGE_NAME_FMT,
-			 fw_loader->sensor_name);
-
-	snprintf(path, sizeof(path), "%s/%s", fw_loader->folder, name);
+	snprintf(path, sizeof(path), VSC_CFG_IMAGE_NAME_FMT,
+		 fw_loader->sensor_name);
 
 	ret = request_firmware(&image, path, fw_loader->dev);
 	if (ret)
@@ -786,13 +741,6 @@ int vsc_tp_init(struct vsc_tp *tp, struct device *dev)
 	if (ret)
 		return ret;
 
-	if (fw_loader->key_src == VSC_STRAP_KEY_SRC_PRODUCT)
-		snprintf(fw_loader->folder, sizeof(fw_loader->folder),
-			 VSC_IMAGE_FOLDER_FMT_PROD, fw_loader->suffix);
-	else
-		snprintf(fw_loader->folder, sizeof(fw_loader->folder),
-			 VSC_IMAGE_FOLDER_FMT);
-
 	ret = vsc_identify_csi_image(fw_loader);
 	if (ret)
 		return ret;
-- 
GitLab


From 95171e45663307fc33a939f0220b39afadfe7cb9 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 14 Dec 2023 18:39:31 +0000
Subject: [PATCH 1434/4076] mei: fix vsc dependency

CONFIG_INTEL_MEI_VSC_HW can be set to built-in even with CONFIG_MEI=m,
but then the driver is not built because Kbuild never enters the
drivers/misc/mei directory for built-in files, leading to a link
failure:

ERROR: modpost: "vsc_tp_reset" [drivers/misc/mei/mei-vsc.ko] undefined!
ERROR: modpost: "vsc_tp_init" [drivers/misc/mei/mei-vsc.ko] undefined!
ERROR: modpost: "vsc_tp_xfer" [drivers/misc/mei/mei-vsc.ko] undefined!
ERROR: modpost: "vsc_tp_need_read" [drivers/misc/mei/mei-vsc.ko] undefined!
ERROR: modpost: "vsc_tp_intr_enable" [drivers/misc/mei/mei-vsc.ko] undefined!
ERROR: modpost: "vsc_tp_intr_synchronize" [drivers/misc/mei/mei-vsc.ko] undefined!
ERROR: modpost: "vsc_tp_intr_disable" [drivers/misc/mei/mei-vsc.ko] undefined!
ERROR: modpost: "vsc_tp_register_event_cb" [drivers/misc/mei/mei-vsc.ko] undefined!

Add an explicit dependency on CONFIG_MEI that was apparently missing,
to ensure the VSC_HW driver cannot be built-in with MEI itself being
a loadable module.

Fixes: 566f5ca97680 ("mei: Add transport driver for IVSC device")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Wentong Wu <wentong.wu@intel.com>
Link: https://lore.kernel.org/r/20231214183946.109124-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig
index 858bd701d68c3..1e28ca23a74ad 100644
--- a/drivers/misc/mei/Kconfig
+++ b/drivers/misc/mei/Kconfig
@@ -62,6 +62,7 @@ config INTEL_MEI_GSC
 
 config INTEL_MEI_VSC_HW
 	tristate "Intel visual sensing controller device transport driver"
+	depends on INTEL_MEI
 	depends on ACPI && SPI
 	depends on GPIOLIB || COMPILE_TEST
 	help
-- 
GitLab


From d667378ade2367fc0423ebcfd79d3a0e813ebd5c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 14 Dec 2023 18:39:32 +0000
Subject: [PATCH 1435/4076] mei: rework Kconfig dependencies

The dependencies in the mei framework are inconsistent, with some symbols
using 'select INTEL_MEI' to force it being enabled and others using
'depends on INTEL_MEI'.

In general, one should not select user-visible symbols, so change all
of these to normal dependencies, but change the default on INTEL_MEI to
be enabled when building a kernel for an Intel CPU with ME or a generic
x86 kernel.

Having consistent dependencies makes the 'menuconfig' listing more
readable by using proper indentation.

A large if/endif block is just a simpler syntax than repeating the
dependencies for each symbol.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Wentong Wu <wentong.wu@intel.com>
Link: https://lore.kernel.org/r/20231214183946.109124-2-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/Kconfig           | 14 ++++++--------
 drivers/misc/mei/gsc_proxy/Kconfig |  2 +-
 drivers/misc/mei/hdcp/Kconfig      |  2 +-
 drivers/misc/mei/pxp/Kconfig       |  2 +-
 4 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig
index 1e28ca23a74ad..67d9391f18550 100644
--- a/drivers/misc/mei/Kconfig
+++ b/drivers/misc/mei/Kconfig
@@ -3,6 +3,7 @@
 config INTEL_MEI
 	tristate "Intel Management Engine Interface"
 	depends on X86 && PCI
+	default GENERIC_CPU || MCORE2 || MATOM || X86_GENERIC
 	help
 	  The Intel Management Engine (Intel ME) provides Manageability,
 	  Security and Media services for system containing Intel chipsets.
@@ -11,10 +12,11 @@ config INTEL_MEI
 	  For more information see
 	  <https://software.intel.com/en-us/manageability/>
 
+if INTEL_MEI
+
 config INTEL_MEI_ME
 	tristate "ME Enabled Intel Chipsets"
-	select INTEL_MEI
-	depends on X86 && PCI
+	default y
 	help
 	  MEI support for ME Enabled Intel chipsets.
 
@@ -38,8 +40,6 @@ config INTEL_MEI_ME
 
 config INTEL_MEI_TXE
 	tristate "Intel Trusted Execution Environment with ME Interface"
-	select INTEL_MEI
-	depends on X86 && PCI
 	help
 	  MEI Support for Trusted Execution Environment device on Intel SoCs
 
@@ -48,9 +48,7 @@ config INTEL_MEI_TXE
 
 config INTEL_MEI_GSC
 	tristate "Intel MEI GSC embedded device"
-	depends on INTEL_MEI
 	depends on INTEL_MEI_ME
-	depends on X86 && PCI
 	depends on DRM_I915
 	help
 	  Intel auxiliary driver for GSC devices embedded in Intel graphics devices.
@@ -62,7 +60,6 @@ config INTEL_MEI_GSC
 
 config INTEL_MEI_VSC_HW
 	tristate "Intel visual sensing controller device transport driver"
-	depends on INTEL_MEI
 	depends on ACPI && SPI
 	depends on GPIOLIB || COMPILE_TEST
 	help
@@ -75,7 +72,6 @@ config INTEL_MEI_VSC_HW
 config INTEL_MEI_VSC
 	tristate "Intel visual sensing controller device with ME interface"
 	depends on INTEL_MEI_VSC_HW
-	depends on INTEL_MEI
 	help
 	  Intel MEI over SPI driver for Intel visual sensing controller
 	  (IVSC) device embedded in IA platform. It supports camera sharing
@@ -88,3 +84,5 @@ config INTEL_MEI_VSC
 source "drivers/misc/mei/hdcp/Kconfig"
 source "drivers/misc/mei/pxp/Kconfig"
 source "drivers/misc/mei/gsc_proxy/Kconfig"
+
+endif
diff --git a/drivers/misc/mei/gsc_proxy/Kconfig b/drivers/misc/mei/gsc_proxy/Kconfig
index 5f68d9f3d691b..ac78b9d1eccd1 100644
--- a/drivers/misc/mei/gsc_proxy/Kconfig
+++ b/drivers/misc/mei/gsc_proxy/Kconfig
@@ -3,7 +3,7 @@
 #
 config INTEL_MEI_GSC_PROXY
 	tristate "Intel GSC Proxy services of ME Interface"
-	select INTEL_MEI_ME
+	depends on INTEL_MEI_ME
 	depends on DRM_I915
 	help
          MEI Support for GSC Proxy Services on Intel platforms.
diff --git a/drivers/misc/mei/hdcp/Kconfig b/drivers/misc/mei/hdcp/Kconfig
index 54e1c95269096..9be312ec798de 100644
--- a/drivers/misc/mei/hdcp/Kconfig
+++ b/drivers/misc/mei/hdcp/Kconfig
@@ -3,7 +3,7 @@
 #
 config INTEL_MEI_HDCP
 	tristate "Intel HDCP2.2 services of ME Interface"
-	select INTEL_MEI_ME
+	depends on INTEL_MEI_ME
 	depends on DRM_I915
 	help
 	  MEI Support for HDCP2.2 Services on Intel platforms.
diff --git a/drivers/misc/mei/pxp/Kconfig b/drivers/misc/mei/pxp/Kconfig
index 4f1ed9202cd9c..e9219b61cd92f 100644
--- a/drivers/misc/mei/pxp/Kconfig
+++ b/drivers/misc/mei/pxp/Kconfig
@@ -3,7 +3,7 @@
 #
 config INTEL_MEI_PXP
 	tristate "Intel PXP services of ME Interface"
-	select INTEL_MEI_ME
+	depends on INTEL_MEI_ME
 	depends on DRM_I915
 	help
 	  MEI Support for PXP Services on Intel platforms.
-- 
GitLab


From 3634783be125381c6d390938d08cbcc47fed3b73 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Fri, 8 Dec 2023 15:28:01 +0000
Subject: [PATCH 1436/4076] binder: use enum for binder ioctls

All of the other constants in this file are defined using enums, so make
the constants more consistent by defining the ioctls in an enum as well.

This is necessary for Rust Binder since the _IO macros are too
complicated for bindgen to see that they expand to integer constants.
Replacing the #defines with an enum forces bindgen to evaluate them
properly, which allows us to access them from Rust.

I originally intended to include this change in the first patch of the
Rust Binder patchset [1], but at plumbers Carlos Llamas told me that
this change has been discussed previously [2] and suggested that I send
it upstream separately.

Link: https://lore.kernel.org/rust-for-linux/20231101-rust-binder-v1-1-08ba9197f637@google.com/ [1]
Link: https://lore.kernel.org/all/YoIK2l6xbQMPGZHy@kroah.com/ [2]
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231208152801.3425772-1-aliceryhl@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/android/binder.h | 30 +++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h
index 5f636b5afcd74..d44a8118b2ed6 100644
--- a/include/uapi/linux/android/binder.h
+++ b/include/uapi/linux/android/binder.h
@@ -251,20 +251,22 @@ struct binder_extended_error {
 	__s32	param;
 };
 
-#define BINDER_WRITE_READ		_IOWR('b', 1, struct binder_write_read)
-#define BINDER_SET_IDLE_TIMEOUT		_IOW('b', 3, __s64)
-#define BINDER_SET_MAX_THREADS		_IOW('b', 5, __u32)
-#define BINDER_SET_IDLE_PRIORITY	_IOW('b', 6, __s32)
-#define BINDER_SET_CONTEXT_MGR		_IOW('b', 7, __s32)
-#define BINDER_THREAD_EXIT		_IOW('b', 8, __s32)
-#define BINDER_VERSION			_IOWR('b', 9, struct binder_version)
-#define BINDER_GET_NODE_DEBUG_INFO	_IOWR('b', 11, struct binder_node_debug_info)
-#define BINDER_GET_NODE_INFO_FOR_REF	_IOWR('b', 12, struct binder_node_info_for_ref)
-#define BINDER_SET_CONTEXT_MGR_EXT	_IOW('b', 13, struct flat_binder_object)
-#define BINDER_FREEZE			_IOW('b', 14, struct binder_freeze_info)
-#define BINDER_GET_FROZEN_INFO		_IOWR('b', 15, struct binder_frozen_status_info)
-#define BINDER_ENABLE_ONEWAY_SPAM_DETECTION	_IOW('b', 16, __u32)
-#define BINDER_GET_EXTENDED_ERROR	_IOWR('b', 17, struct binder_extended_error)
+enum {
+	BINDER_WRITE_READ		= _IOWR('b', 1, struct binder_write_read),
+	BINDER_SET_IDLE_TIMEOUT		= _IOW('b', 3, __s64),
+	BINDER_SET_MAX_THREADS		= _IOW('b', 5, __u32),
+	BINDER_SET_IDLE_PRIORITY	= _IOW('b', 6, __s32),
+	BINDER_SET_CONTEXT_MGR		= _IOW('b', 7, __s32),
+	BINDER_THREAD_EXIT		= _IOW('b', 8, __s32),
+	BINDER_VERSION			= _IOWR('b', 9, struct binder_version),
+	BINDER_GET_NODE_DEBUG_INFO	= _IOWR('b', 11, struct binder_node_debug_info),
+	BINDER_GET_NODE_INFO_FOR_REF	= _IOWR('b', 12, struct binder_node_info_for_ref),
+	BINDER_SET_CONTEXT_MGR_EXT	= _IOW('b', 13, struct flat_binder_object),
+	BINDER_FREEZE			= _IOW('b', 14, struct binder_freeze_info),
+	BINDER_GET_FROZEN_INFO		= _IOWR('b', 15, struct binder_frozen_status_info),
+	BINDER_ENABLE_ONEWAY_SPAM_DETECTION	= _IOW('b', 16, __u32),
+	BINDER_GET_EXTENDED_ERROR	= _IOWR('b', 17, struct binder_extended_error),
+};
 
 /*
  * NOTE: Two special error codes you should check for when calling
-- 
GitLab


From ce8df3f4d0d99ee2f76d1260fe69793ad05a13bf Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 5 Dec 2023 21:58:21 -0800
Subject: [PATCH 1437/4076] mcb: core: fix kernel-doc warnings

Correct function comments to prevent warnings from
scripts/kernel-doc.

mcb-core.c:270: warning: Function parameter or member 'carrier' not described in 'mcb_alloc_bus'
mcb-core.c:336: warning: expecting prototype for mcb_bus_put(). Prototype was for mcb_bus_get() instead
mcb-core.c:463: warning: Function parameter or member 'mem' not described in 'mcb_release_mem'
mcb-core.c:463: warning: Excess function parameter 'dev' description in 'mcb_release_mem'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Johannes Thumshirn <morbidrsa@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231206055821.17284-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/mcb/mcb-core.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c
index ba4530459de8d..61994da7bad01 100644
--- a/drivers/mcb/mcb-core.c
+++ b/drivers/mcb/mcb-core.c
@@ -263,6 +263,7 @@ static void mcb_free_bus(struct device *dev)
 
 /**
  * mcb_alloc_bus() - Allocate a new @mcb_bus
+ * @carrier: generic &struct device for the carrier device
  *
  * Allocate a new @mcb_bus.
  */
@@ -327,7 +328,7 @@ void mcb_release_bus(struct mcb_bus *bus)
 EXPORT_SYMBOL_NS_GPL(mcb_release_bus, MCB);
 
 /**
- * mcb_bus_put() - Increment refcnt
+ * mcb_bus_get() - Increment refcnt
  * @bus: The @mcb_bus
  *
  * Get a @mcb_bus' ref
@@ -455,7 +456,7 @@ EXPORT_SYMBOL_NS_GPL(mcb_request_mem, MCB);
 
 /**
  * mcb_release_mem() - Release memory requested by device
- * @dev: The @mcb_device that requested the memory
+ * @mem: The memory resource to be released
  *
  * Release memory that was prior requested via @mcb_request_mem().
  */
-- 
GitLab


From fddd9e3e4e716e3c484413b95579b40a7b6dbe41 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 6 Dec 2023 17:59:38 -0800
Subject: [PATCH 1438/4076] tools/testing/nvdimm: Add compile-test coverage for
 ndtest

Greg lamented:
"Ick, sorry about that, obviously this test isn't actually built by any
bots :("

A quick and dirty way to prevent this problem going forward is to always
compile ndtest.ko whenever nfit_test is built. While this still does not
expose the test code to any of the known build bots, it at least makes
it the case that anyone that runs the x86 tests also compiles the
powerpc test.

I.e. the Intel NVDIMM maintainers are less likely to fall into this hole
in the future.

Link: http://lore.kernel.org/r/2023112729-aids-drainable-5744@gregkh
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Yi Zhang <yi.zhang@redhat.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170191437889.426826.15528612879942432918.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/testing/nvdimm/test/Kbuild | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/nvdimm/test/Kbuild b/tools/testing/nvdimm/test/Kbuild
index 197bcb2b7f351..003d48f5f24f5 100644
--- a/tools/testing/nvdimm/test/Kbuild
+++ b/tools/testing/nvdimm/test/Kbuild
@@ -7,6 +7,7 @@ obj-m += nfit_test_iomap.o
 
 ifeq  ($(CONFIG_ACPI_NFIT),m)
 	nfit_test-y := nfit.o
+	obj-m += ndtest.o
 else
 	nfit_test-y := ndtest.o
 endif
-- 
GitLab


From ed2b5f50b043edcaa044da6ba254877224511802 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 8 Dec 2023 17:08:06 +0100
Subject: [PATCH 1439/4076] pcmcia: bcm63xx: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/33611a4245b4dabc609a75cf0e0db5e06e9a6fc8.1702051073.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pcmcia/bcm63xx_pcmcia.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pcmcia/bcm63xx_pcmcia.c b/drivers/pcmcia/bcm63xx_pcmcia.c
index dd3c260990487..a5414441834ad 100644
--- a/drivers/pcmcia/bcm63xx_pcmcia.c
+++ b/drivers/pcmcia/bcm63xx_pcmcia.c
@@ -437,7 +437,7 @@ err:
 	return ret;
 }
 
-static int bcm63xx_drv_pcmcia_remove(struct platform_device *pdev)
+static void bcm63xx_drv_pcmcia_remove(struct platform_device *pdev)
 {
 	struct bcm63xx_pcmcia_socket *skt;
 	struct resource *res;
@@ -449,12 +449,11 @@ static int bcm63xx_drv_pcmcia_remove(struct platform_device *pdev)
 	res = skt->reg_res;
 	release_mem_region(res->start, resource_size(res));
 	kfree(skt);
-	return 0;
 }
 
 struct platform_driver bcm63xx_pcmcia_driver = {
 	.probe	= bcm63xx_drv_pcmcia_probe,
-	.remove	= bcm63xx_drv_pcmcia_remove,
+	.remove_new = bcm63xx_drv_pcmcia_remove,
 	.driver	= {
 		.name	= "bcm63xx_pcmcia",
 		.owner  = THIS_MODULE,
-- 
GitLab


From 89493fc6bd2aeccfaae776b3f8a2a4a2ab69825d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 8 Dec 2023 17:08:07 +0100
Subject: [PATCH 1440/4076] pcmcia: db1xxx_ss: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/3d4c108421f2b1175d3a75ee6854e7772f8a0f82.1702051073.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pcmcia/db1xxx_ss.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c
index 87a33ecc2cf14..509713b9a502b 100644
--- a/drivers/pcmcia/db1xxx_ss.c
+++ b/drivers/pcmcia/db1xxx_ss.c
@@ -577,7 +577,7 @@ out0:
 	return ret;
 }
 
-static int db1x_pcmcia_socket_remove(struct platform_device *pdev)
+static void db1x_pcmcia_socket_remove(struct platform_device *pdev)
 {
 	struct db1x_pcmcia_sock *sock = platform_get_drvdata(pdev);
 
@@ -585,8 +585,6 @@ static int db1x_pcmcia_socket_remove(struct platform_device *pdev)
 	pcmcia_unregister_socket(&sock->socket);
 	iounmap((void *)(sock->virt_io + (u32)mips_io_port_base));
 	kfree(sock);
-
-	return 0;
 }
 
 static struct platform_driver db1x_pcmcia_socket_driver = {
@@ -594,7 +592,7 @@ static struct platform_driver db1x_pcmcia_socket_driver = {
 		.name	= "db1xxx_pcmcia",
 	},
 	.probe		= db1x_pcmcia_socket_probe,
-	.remove		= db1x_pcmcia_socket_remove,
+	.remove_new	= db1x_pcmcia_socket_remove,
 };
 
 module_platform_driver(db1x_pcmcia_socket_driver);
-- 
GitLab


From 292006710d87cb54927e551bc306401fb398a3ed Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 8 Dec 2023 17:08:08 +0100
Subject: [PATCH 1441/4076] pcmcia: electra_cf: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/7b07c8624ab53ec90554b7a665bef7662bd94295.1702051073.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pcmcia/electra_cf.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c
index efc27bc15152e..5ae826e548116 100644
--- a/drivers/pcmcia/electra_cf.c
+++ b/drivers/pcmcia/electra_cf.c
@@ -307,7 +307,7 @@ out_free_cf:
 
 }
 
-static int electra_cf_remove(struct platform_device *ofdev)
+static void electra_cf_remove(struct platform_device *ofdev)
 {
 	struct device *device = &ofdev->dev;
 	struct electra_cf_socket *cf;
@@ -326,8 +326,6 @@ static int electra_cf_remove(struct platform_device *ofdev)
 	release_region(cf->io_base, cf->io_size);
 
 	kfree(cf);
-
-	return 0;
 }
 
 static const struct of_device_id electra_cf_match[] = {
@@ -344,7 +342,7 @@ static struct platform_driver electra_cf_driver = {
 		.of_match_table = electra_cf_match,
 	},
 	.probe	  = electra_cf_probe,
-	.remove   = electra_cf_remove,
+	.remove_new = electra_cf_remove,
 };
 
 module_platform_driver(electra_cf_driver);
-- 
GitLab


From 560bb502ea1639fc3ab839c00bb28c05591fdb1b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 8 Dec 2023 17:08:09 +0100
Subject: [PATCH 1442/4076] pcmcia: omap_cf: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/9d96646b75b10f7562d4d18010e885b7fc55e0ab.1702051073.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pcmcia/omap_cf.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c
index e613818dc0bc9..80137c7afe0d9 100644
--- a/drivers/pcmcia/omap_cf.c
+++ b/drivers/pcmcia/omap_cf.c
@@ -290,7 +290,7 @@ fail0:
 	return status;
 }
 
-static int __exit omap_cf_remove(struct platform_device *pdev)
+static void __exit omap_cf_remove(struct platform_device *pdev)
 {
 	struct omap_cf_socket *cf = platform_get_drvdata(pdev);
 
@@ -300,14 +300,13 @@ static int __exit omap_cf_remove(struct platform_device *pdev)
 	release_mem_region(cf->phys_cf, SZ_8K);
 	free_irq(cf->irq, cf);
 	kfree(cf);
-	return 0;
 }
 
 static struct platform_driver omap_cf_driver = {
 	.driver = {
 		.name	= driver_name,
 	},
-	.remove		= __exit_p(omap_cf_remove),
+	.remove_new	= __exit_p(omap_cf_remove),
 };
 
 static int __init omap_cf_init(void)
-- 
GitLab


From e5b25d20b6017a808bb6a46caa7a3094813d069f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 8 Dec 2023 17:08:10 +0100
Subject: [PATCH 1443/4076] pcmcia: pxa2xx: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/fb750d46ac80b6dfdeaa26053a2cf9d2dc875d4d.1702051073.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pcmcia/pxa2xx_base.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c
index 5254028354f40..457fb81b497a1 100644
--- a/drivers/pcmcia/pxa2xx_base.c
+++ b/drivers/pcmcia/pxa2xx_base.c
@@ -313,15 +313,13 @@ err0:
 	return ret;
 }
 
-static int pxa2xx_drv_pcmcia_remove(struct platform_device *dev)
+static void pxa2xx_drv_pcmcia_remove(struct platform_device *dev)
 {
 	struct skt_dev_info *sinfo = platform_get_drvdata(dev);
 	int i;
 
 	for (i = 0; i < sinfo->nskt; i++)
 		soc_pcmcia_remove_one(&sinfo->skt[i]);
-
-	return 0;
 }
 
 static int pxa2xx_drv_pcmcia_resume(struct device *dev)
@@ -338,7 +336,7 @@ static const struct dev_pm_ops pxa2xx_drv_pcmcia_pm_ops = {
 
 static struct platform_driver pxa2xx_pcmcia_driver = {
 	.probe		= pxa2xx_drv_pcmcia_probe,
-	.remove		= pxa2xx_drv_pcmcia_remove,
+	.remove_new	= pxa2xx_drv_pcmcia_remove,
 	.driver		= {
 		.name	= "pxa2xx-pcmcia",
 		.pm	= &pxa2xx_drv_pcmcia_pm_ops,
-- 
GitLab


From c1991d49bb95be1086e5b9e6980fd00cb3d06bc3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 8 Dec 2023 17:08:11 +0100
Subject: [PATCH 1444/4076] pcmcia: sa1100: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/6473afe67fc5c320a8184d0871a8561f7685e265.1702051073.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pcmcia/sa1100_generic.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/pcmcia/sa1100_generic.c b/drivers/pcmcia/sa1100_generic.c
index 89d4ba58c8913..ccb219c387617 100644
--- a/drivers/pcmcia/sa1100_generic.c
+++ b/drivers/pcmcia/sa1100_generic.c
@@ -158,20 +158,18 @@ static int sa11x0_drv_pcmcia_probe(struct platform_device *pdev)
 	return sa11xx_drv_pcmcia_add_one(skt);
 }
 
-static int sa11x0_drv_pcmcia_remove(struct platform_device *dev)
+static void sa11x0_drv_pcmcia_remove(struct platform_device *dev)
 {
 	struct soc_pcmcia_socket *skt;
 
 	if (dev->id == -1) {
 		sa11x0_drv_pcmcia_legacy_remove(dev);
-		return 0;
+		return;
 	}
 
 	skt = platform_get_drvdata(dev);
 
 	soc_pcmcia_remove_one(skt);
-
-	return 0;
 }
 
 static struct platform_driver sa11x0_pcmcia_driver = {
@@ -179,7 +177,7 @@ static struct platform_driver sa11x0_pcmcia_driver = {
 		.name		= "sa11x0-pcmcia",
 	},
 	.probe		= sa11x0_drv_pcmcia_probe,
-	.remove		= sa11x0_drv_pcmcia_remove,
+	.remove_new	= sa11x0_drv_pcmcia_remove,
 };
 
 /* sa11x0_pcmcia_init()
-- 
GitLab


From 1b775e616ec8ea1e4faa326a73640c9cc1087368 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 8 Dec 2023 17:08:12 +0100
Subject: [PATCH 1445/4076] pcmcia: xxs1500_ss: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/09a89926787cb9f64caa73c510f04d9f04a5136f.1702051073.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pcmcia/xxs1500_ss.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pcmcia/xxs1500_ss.c b/drivers/pcmcia/xxs1500_ss.c
index b11c7abb1dc07..2a93fbbd128da 100644
--- a/drivers/pcmcia/xxs1500_ss.c
+++ b/drivers/pcmcia/xxs1500_ss.c
@@ -301,7 +301,7 @@ out0:
 	return ret;
 }
 
-static int xxs1500_pcmcia_remove(struct platform_device *pdev)
+static void xxs1500_pcmcia_remove(struct platform_device *pdev)
 {
 	struct xxs1500_pcmcia_sock *sock = platform_get_drvdata(pdev);
 
@@ -309,8 +309,6 @@ static int xxs1500_pcmcia_remove(struct platform_device *pdev)
 	free_irq(gpio_to_irq(GPIO_CDA), sock);
 	iounmap((void *)(sock->virt_io + (u32)mips_io_port_base));
 	kfree(sock);
-
-	return 0;
 }
 
 static struct platform_driver xxs1500_pcmcia_socket_driver = {
@@ -318,7 +316,7 @@ static struct platform_driver xxs1500_pcmcia_socket_driver = {
 		.name	= "xxs1500_pcmcia",
 	},
 	.probe		= xxs1500_pcmcia_probe,
-	.remove		= xxs1500_pcmcia_remove,
+	.remove_new	= xxs1500_pcmcia_remove,
 };
 
 module_platform_driver(xxs1500_pcmcia_socket_driver);
-- 
GitLab


From 1a737d5ea69d220463150523e41efa70ff17ecf4 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Mon, 11 Dec 2023 08:42:42 +0100
Subject: [PATCH 1446/4076] misc: nsm: remove selecting the non-existing config
 CBOR

Commit b9873755a6c8 ("misc: Add Nitro Secure Module driver") adds Nitro
Security Module support, which selects the non-existing config CBOR.

In the development of the commit, there was initially some code for CBOR
independent of the driver, and the driver included this code with the line
'select CBOR'. This code for CBOR was later reduced to its bare minimum of
functionality and included into the driver itself. The select CBOR remained
unnoticed and was left behind without having any further purpose.

Remove selecting the non-existing config CBOR.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Reviewed-by: Alexander Graf <graf@amazon.com>
Link: https://lore.kernel.org/r/20231211074242.22999-1-lukas.bulwahn@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 8932b6cf9595d..4fb291f0bf7c8 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -566,7 +566,6 @@ config NSM
 	tristate "Nitro (Enclaves) Security Module support"
 	depends on VIRTIO
 	select HW_RANDOM
-	select CBOR
 	help
 	  This driver provides support for the Nitro Security Module
 	  in AWS EC2 Nitro based Enclaves. The driver exposes a /dev/nsm
-- 
GitLab


From fe3de0102bc830e78d80dbf6e2dd29c520d68575 Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Fri, 8 Dec 2023 10:33:09 +0100
Subject: [PATCH 1447/4076] kernel/cgroup: use kernfs_create_dir_ns()

By passing the fsugid to kernfs_create_dir_ns(), we don't need
cgroup_kn_set_ugid() any longer.  That function was added for exactly
this purpose by commit 49957f8e2a43 ("cgroup: newly created dirs and
files should be owned by the creator").

Eliminating this piece of duplicate code means we benefit from future
improvements to kernfs_create_dir_ns(); for example, both are lacking
S_ISGID support currently, which my next patch will add to
kernfs_create_dir_ns().  It cannot (easily) be added to
cgroup_kn_set_ugid() because we can't dereference struct kernfs_iattrs
from there.

--
v1 -> v2: 12-digit commit id

Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20231208093310.297233-1-max.kellermann@ionos.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 kernel/cgroup/cgroup.c | 31 ++++---------------------------
 1 file changed, 4 insertions(+), 27 deletions(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4b9ff41ca603a..a844b421fd83f 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4169,20 +4169,6 @@ static struct kernfs_ops cgroup_kf_ops = {
 	.seq_show		= cgroup_seqfile_show,
 };
 
-/* set uid and gid of cgroup dirs and files to that of the creator */
-static int cgroup_kn_set_ugid(struct kernfs_node *kn)
-{
-	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
-			       .ia_uid = current_fsuid(),
-			       .ia_gid = current_fsgid(), };
-
-	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
-	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
-		return 0;
-
-	return kernfs_setattr(kn, &iattr);
-}
-
 static void cgroup_file_notify_timer(struct timer_list *timer)
 {
 	cgroup_file_notify(container_of(timer, struct cgroup_file,
@@ -4195,25 +4181,18 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 	char name[CGROUP_FILE_NAME_MAX];
 	struct kernfs_node *kn;
 	struct lock_class_key *key = NULL;
-	int ret;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	key = &cft->lockdep_key;
 #endif
 	kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
 				  cgroup_file_mode(cft),
-				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				  current_fsuid(), current_fsgid(),
 				  0, cft->kf_ops, cft,
 				  NULL, key);
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
 
-	ret = cgroup_kn_set_ugid(kn);
-	if (ret) {
-		kernfs_remove(kn);
-		return ret;
-	}
-
 	if (cft->file_offset) {
 		struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
@@ -5616,7 +5595,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 		goto out_cancel_ref;
 
 	/* create the directory */
-	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
+	kn = kernfs_create_dir_ns(parent->kn, name, mode,
+				  current_fsuid(), current_fsgid(),
+				  cgrp, NULL);
 	if (IS_ERR(kn)) {
 		ret = PTR_ERR(kn);
 		goto out_stat_exit;
@@ -5761,10 +5742,6 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
 	 */
 	kernfs_get(cgrp->kn);
 
-	ret = cgroup_kn_set_ugid(cgrp->kn);
-	if (ret)
-		goto out_destroy;
-
 	ret = css_populate_dir(&cgrp->self);
 	if (ret)
 		goto out_destroy;
-- 
GitLab


From 5133bee62f0ea5d4c316d503cc0040cac5637601 Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Fri, 8 Dec 2023 10:33:10 +0100
Subject: [PATCH 1448/4076] fs/kernfs/dir: obey S_ISGID

Handling of S_ISGID is usually done by inode_init_owner() in all other
filesystems, but kernfs doesn't use that function.  In kernfs, struct
kernfs_node is the primary data structure, and struct inode is only
created from it on demand.  Therefore, inode_init_owner() can't be
used and we need to imitate its behavior.

S_ISGID support is useful for the cgroup filesystem; it allows
subtrees managed by an unprivileged process to retain a certain owner
gid, which then enables sharing access to the subtree with another
unprivileged process.

--
v1 -> v2: minor coding style fix (comment)

Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20231208093310.297233-2-max.kellermann@ionos.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 8b2bd65d70e72..62d39ecf0a466 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -676,6 +676,18 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 {
 	struct kernfs_node *kn;
 
+	if (parent->mode & S_ISGID) {
+		/* this code block imitates inode_init_owner() for
+		 * kernfs
+		 */
+
+		if (parent->iattr)
+			gid = parent->iattr->ia_gid;
+
+		if (flags & KERNFS_DIR)
+			mode |= S_ISGID;
+	}
+
 	kn = __kernfs_new_node(kernfs_root(parent), parent,
 			       name, mode, uid, gid, flags);
 	if (kn) {
-- 
GitLab


From 2678fd2fe9ee2c569e9cb6b17e786bc8f0753538 Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Thu, 7 Dec 2023 23:56:54 +0000
Subject: [PATCH 1449/4076] initramfs: Expose retained initrd as sysfs file

When the kernel command line option "retain_initrd" is set, we do not
free the initrd memory. However, we also don't expose it to anyone for
consumption. That leaves us in a weird situation where the only user of
this feature is ppc64 and arm64 specific kexec tooling.

To make it more generally useful, this patch adds a kobject to the
firmware object that contains the initrd context when "retain_initrd"
is set. That way, we can access the initrd any time after boot from
user space and for example hand it into kexec as --initrd parameter
if we want to reboot the same initrd. Or inspect it directly locally.

With this patch applied, there is a new /sys/firmware/initrd file when
the kernel was booted with an initrd and "retain_initrd" command line
option is set.

Signed-off-by: Alexander Graf <graf@amazon.com>
Tested-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://lore.kernel.org/r/20231207235654.16622-1-graf@amazon.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../ABI/testing/sysfs-firmware-initrd          |  8 ++++++++
 .../admin-guide/kernel-parameters.txt          |  5 +++--
 init/initramfs.c                               | 18 +++++++++++++++++-
 3 files changed, 28 insertions(+), 3 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-firmware-initrd

diff --git a/Documentation/ABI/testing/sysfs-firmware-initrd b/Documentation/ABI/testing/sysfs-firmware-initrd
new file mode 100644
index 0000000000000..20bf7cf77a191
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-initrd
@@ -0,0 +1,8 @@
+What:		/sys/firmware/initrd
+Date:		December 2023
+Contact:	Alexander Graf <graf@amazon.com>
+Description:
+		When the kernel was booted with an initrd and the
+		"retain_initrd" option is set on the kernel command
+		line, /sys/firmware/initrd contains the contents of the
+		initrd that the kernel was booted with.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 65731b060e3fe..51575cd31741e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2438,7 +2438,7 @@
 			between unregistering the boot console and initializing
 			the real console.
 
-	keepinitrd	[HW,ARM]
+	keepinitrd	[HW,ARM] See retain_initrd.
 
 	kernelcore=	[KNL,X86,IA-64,PPC]
 			Format: nn[KMGTPE] | nn% | "mirror"
@@ -5580,7 +5580,8 @@
 			Useful for devices that are detected asynchronously
 			(e.g. USB and MMC devices).
 
-	retain_initrd	[RAM] Keep initrd memory after extraction
+	retain_initrd	[RAM] Keep initrd memory after extraction. After boot, it will
+			be accessible via /sys/firmware/initrd.
 
 	retbleed=	[X86] Control mitigation of RETBleed (Arbitrary
 			Speculative Code Execution with Return Instructions)
diff --git a/init/initramfs.c b/init/initramfs.c
index 8d0fd946cdd2b..76deb48c38cb1 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -574,6 +574,16 @@ extern unsigned long __initramfs_size;
 #include <linux/initrd.h>
 #include <linux/kexec.h>
 
+static ssize_t raw_read(struct file *file, struct kobject *kobj,
+			struct bin_attribute *attr, char *buf,
+			loff_t pos, size_t count)
+{
+	memcpy(buf, attr->private + pos, count);
+	return count;
+}
+
+static BIN_ATTR(initrd, 0440, raw_read, NULL, 0);
+
 void __init reserve_initrd_mem(void)
 {
 	phys_addr_t start;
@@ -715,8 +725,14 @@ done:
 	 * If the initrd region is overlapped with crashkernel reserved region,
 	 * free only memory that is not part of crashkernel region.
 	 */
-	if (!do_retain_initrd && initrd_start && !kexec_free_initrd())
+	if (!do_retain_initrd && initrd_start && !kexec_free_initrd()) {
 		free_initrd_mem(initrd_start, initrd_end);
+	} else if (do_retain_initrd && initrd_start) {
+		bin_attr_initrd.size = initrd_end - initrd_start;
+		bin_attr_initrd.private = (void *)initrd_start;
+		if (sysfs_create_bin_file(firmware_kobj, &bin_attr_initrd))
+			pr_err("Failed to create initrd sysfs file");
+	}
 	initrd_start = 0;
 	initrd_end = 0;
 
-- 
GitLab


From 792e04768efbf2a1b49a7162a9fa06c1fa584723 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 12 Dec 2023 13:17:38 -0800
Subject: [PATCH 1450/4076] kernfs: Convert kernfs_walk_ns() from strlcpy() to
 strscpy()

strlcpy() reads the entire source buffer first. This read may exceed
the destination size limit. This is both inefficient and can lead
to linear read overflows if a source string is not NUL-terminated[1].
Additionally, it returns the size of the source string, not the
resulting size of the destination string. In an effort to remove strlcpy()
completely[2], replace strlcpy() here with strscpy().

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [1]
Link: https://github.com/KSPP/linux/issues/89 [2]
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Azeem Shaikh <azeemshaikh38@gmail.com>
Link: https://lore.kernel.org/r/20231116192127.1558276-1-keescook@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20231212211741.164376-1-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 62d39ecf0a466..fa9077576e028 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -862,16 +862,16 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 					  const unsigned char *path,
 					  const void *ns)
 {
-	size_t len;
+	ssize_t len;
 	char *p, *name;
 
 	lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem);
 
 	spin_lock_irq(&kernfs_pr_cont_lock);
 
-	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
+	len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
-	if (len >= sizeof(kernfs_pr_cont_buf)) {
+	if (len < 0) {
 		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
-- 
GitLab


From 5b56bf5cdb8b7c989055fe4d73fe3f409427d1d5 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 12 Dec 2023 13:17:39 -0800
Subject: [PATCH 1451/4076] kernfs: Convert kernfs_name_locked() from strlcpy()
 to strscpy()

strlcpy() reads the entire source buffer first. This read may exceed
the destination size limit. This is both inefficient and can lead
to linear read overflows if a source string is not NUL-terminated[1].
Additionally, it returns the size of the source string, not the
resulting size of the destination string. In an effort to remove strlcpy()
completely[2], replace strlcpy() here with strscpy().

Nothing actually checks the return value coming from kernfs_name_locked(),
so this has no impact on error paths. The caller hierarchy is:

kernfs_name_locked()
        kernfs_name()
                pr_cont_kernfs_name()
                        return value ignored
                cgroup_name()
                        current_css_set_cg_links_read()
                                return value ignored
                        print_page_owner_memcg()
                                return value ignored

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [1]
Link: https://github.com/KSPP/linux/issues/89 [2]
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Azeem Shaikh <azeemshaikh38@gmail.com>
Link: https://lore.kernel.org/r/20231116192127.1558276-2-keescook@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20231212211741.164376-2-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index fa9077576e028..d23bf7883b083 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -54,9 +54,9 @@ static bool kernfs_lockdep(struct kernfs_node *kn)
 static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 {
 	if (!kn)
-		return strlcpy(buf, "(null)", buflen);
+		return strscpy(buf, "(null)", buflen);
 
-	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
+	return strscpy(buf, kn->parent ? kn->name : "/", buflen);
 }
 
 /* kernfs_node_depth - compute depth from @from to @to */
@@ -182,12 +182,12 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
  * @buflen: size of @buf
  *
  * Copies the name of @kn into @buf of @buflen bytes.  The behavior is
- * similar to strlcpy().
+ * similar to strscpy().
  *
  * Fills buffer with "(null)" if @kn is %NULL.
  *
- * Return: the length of @kn's name and if @buf isn't long enough,
- * it's filled up to @buflen-1 and nul terminated.
+ * Return: the resulting length of @buf. If @buf isn't long enough,
+ * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG.
  *
  * This function can be called from any context.
  */
-- 
GitLab


From ff6d413b0b59466e5acf2e42f294b1842ae130a1 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 12 Dec 2023 13:17:40 -0800
Subject: [PATCH 1452/4076] kernfs: Convert kernfs_path_from_node_locked() from
 strlcpy() to strscpy()

One of the last remaining users of strlcpy() in the kernel is
kernfs_path_from_node_locked(), which passes back the problematic "length
we _would_ have copied" return value to indicate truncation.  Convert the
chain of all callers to use the negative return value (some of which
already doing this explicitly). All callers were already also checking
for negative return values, so the risk to missed checks looks very low.

In this analysis, it was found that cgroup1_release_agent() actually
didn't handle the "too large" condition, so this is technically also a
bug fix. :)

Here's the chain of callers, and resolution identifying each one as now
handling the correct return value:

kernfs_path_from_node_locked()
        kernfs_path_from_node()
                pr_cont_kernfs_path()
                        returns void
                kernfs_path()
                        sysfs_warn_dup()
                                return value ignored
                        cgroup_path()
                                blkg_path()
                                        bfq_bic_update_cgroup()
                                                return value ignored
                                TRACE_IOCG_PATH()
                                        return value ignored
                                TRACE_CGROUP_PATH()
                                        return value ignored
                                perf_event_cgroup()
                                        return value ignored
                                task_group_path()
                                        return value ignored
                                damon_sysfs_memcg_path_eq()
                                        return value ignored
                                get_mm_memcg_path()
                                        return value ignored
                                lru_gen_seq_show()
                                        return value ignored
                        cgroup_path_from_kernfs_id()
                                return value ignored
                cgroup_show_path()
                        already converted "too large" error to negative value
                cgroup_path_ns_locked()
                        cgroup_path_ns()
                                bpf_iter_cgroup_show_fdinfo()
                                        return value ignored
                                cgroup1_release_agent()
                                        wasn't checking "too large" error
                        proc_cgroup_show()
                                already converted "too large" to negative value

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Waiman Long <longman@redhat.com>
Cc:  <cgroups@vger.kernel.org>
Co-developed-by: Azeem Shaikh <azeemshaikh38@gmail.com>
Signed-off-by: Azeem Shaikh <azeemshaikh38@gmail.com>
Link: https://lore.kernel.org/r/20231116192127.1558276-3-keescook@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20231212211741.164376-3-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c           | 34 +++++++++++++++++-----------------
 kernel/cgroup/cgroup-v1.c |  2 +-
 kernel/cgroup/cgroup.c    |  4 ++--
 kernel/cgroup/cpuset.c    |  2 +-
 4 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index d23bf7883b083..bce1d7ac95caa 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -127,7 +127,7 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a,
  *
  * [3] when @kn_to is %NULL result will be "(null)"
  *
- * Return: the length of the full path.  If the full length is equal to or
+ * Return: the length of the constructed path.  If the path would have been
  * greater than @buflen, @buf contains the truncated path with the trailing
  * '\0'.  On error, -errno is returned.
  */
@@ -138,16 +138,17 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 	struct kernfs_node *kn, *common;
 	const char parent_str[] = "/..";
 	size_t depth_from, depth_to, len = 0;
+	ssize_t copied;
 	int i, j;
 
 	if (!kn_to)
-		return strlcpy(buf, "(null)", buflen);
+		return strscpy(buf, "(null)", buflen);
 
 	if (!kn_from)
 		kn_from = kernfs_root(kn_to)->kn;
 
 	if (kn_from == kn_to)
-		return strlcpy(buf, "/", buflen);
+		return strscpy(buf, "/", buflen);
 
 	common = kernfs_common_ancestor(kn_from, kn_to);
 	if (WARN_ON(!common))
@@ -158,18 +159,19 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 
 	buf[0] = '\0';
 
-	for (i = 0; i < depth_from; i++)
-		len += strlcpy(buf + len, parent_str,
-			       len < buflen ? buflen - len : 0);
+	for (i = 0; i < depth_from; i++) {
+		copied = strscpy(buf + len, parent_str, buflen - len);
+		if (copied < 0)
+			return copied;
+		len += copied;
+	}
 
 	/* Calculate how many bytes we need for the rest */
 	for (i = depth_to - 1; i >= 0; i--) {
 		for (kn = kn_to, j = 0; j < i; j++)
 			kn = kn->parent;
-		len += strlcpy(buf + len, "/",
-			       len < buflen ? buflen - len : 0);
-		len += strlcpy(buf + len, kn->name,
-			       len < buflen ? buflen - len : 0);
+
+		len += scnprintf(buf + len, buflen - len, "/%s", kn->name);
 	}
 
 	return len;
@@ -214,7 +216,7 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
  * path (which includes '..'s) as needed to reach from @from to @to is
  * returned.
  *
- * Return: the length of the full path.  If the full length is equal to or
+ * Return: the length of the constructed path.  If the path would have been
  * greater than @buflen, @buf contains the truncated path with the trailing
  * '\0'.  On error, -errno is returned.
  */
@@ -265,12 +267,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf,
 				   sizeof(kernfs_pr_cont_buf));
 	if (sz < 0) {
-		pr_cont("(error)");
-		goto out;
-	}
-
-	if (sz >= sizeof(kernfs_pr_cont_buf)) {
-		pr_cont("(name too long)");
+		if (sz == -E2BIG)
+			pr_cont("(name too long)");
+		else
+			pr_cont("(error)");
 		goto out;
 	}
 
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 76db6c67e39a9..9cb00ebe9ac6d 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -802,7 +802,7 @@ void cgroup1_release_agent(struct work_struct *work)
 		goto out_free;
 
 	ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
-	if (ret < 0 || ret >= PATH_MAX)
+	if (ret < 0)
 		goto out_free;
 
 	argv[0] = agentbuf;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a844b421fd83f..4bc8183b669f0 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1893,7 +1893,7 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 	len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX);
 	spin_unlock_irq(&css_set_lock);
 
-	if (len >= PATH_MAX)
+	if (len == -E2BIG)
 		len = -ERANGE;
 	else if (len > 0) {
 		seq_escape(sf, buf, " \t\n\\");
@@ -6278,7 +6278,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) {
 			retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX,
 						current->nsproxy->cgroup_ns);
-			if (retval >= PATH_MAX)
+			if (retval == -E2BIG)
 				retval = -ENAMETOOLONG;
 			if (retval < 0)
 				goto out_unlock;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 615daaf87f1fc..fb29158ae825f 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -4941,7 +4941,7 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
 	retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX,
 				current->nsproxy->cgroup_ns);
 	css_put(css);
-	if (retval >= PATH_MAX)
+	if (retval == -E2BIG)
 		retval = -ENAMETOOLONG;
 	if (retval < 0)
 		goto out_free;
-- 
GitLab


From aaee477e3e2c7305a95ffc528bf831a13da3dacb Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 7 Dec 2023 10:31:27 -0600
Subject: [PATCH 1453/4076] cdx: Explicitly include correct DT includes, again

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it was merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h. As a result, there's a pretty much random mix of those include
files used throughout the tree. In order to detangle these headers and
replace the implicit includes with struct declarations, users need to
explicitly include the correct includes.

CDX was fixed once, but commit ("cdx: Remove cdx controller list from cdx
bus system") added another occurrence.

Fixes: 54b406e10f03 ("cdx: Remove cdx controller list from cdx bus system")
Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: Nikhil Agarwal <Nikhil.agarwal@amd.com>
Link: https://lore.kernel.org/r/20231207163128.2707993-2-robh@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/cdx/cdx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 4461c6c9313f0..d84d153078d75 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -57,7 +57,10 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/idr.h>
-- 
GitLab


From c27dfca4555bf74dd7dd7161d8ef2790ec1c7283 Mon Sep 17 00:00:00 2001
From: Ricky Wu <ricky_wu@realtek.com>
Date: Fri, 8 Dec 2023 11:21:43 +0800
Subject: [PATCH 1454/4076] misc: rtsx: add to support new card reader rts5264
 new definition and function

in order to support NEW chip rts5264, the definitions of some internal
registers are define in new file rts5264.h, and some callback functions
and the workflow for rts5264 are define in new file rts5264.c

also add rts5264.o to Makefile

Signed-off-by: Ricky Wu <ricky_wu@realtek.com>
Link: https://lore.kernel.org/r/20231208032145.2143580-2-ricky_wu@realtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/Makefile  |   2 +-
 drivers/misc/cardreader/rts5264.c | 886 ++++++++++++++++++++++++++++++
 drivers/misc/cardreader/rts5264.h | 278 ++++++++++
 include/linux/rtsx_pci.h          |   8 +
 4 files changed, 1173 insertions(+), 1 deletion(-)
 create mode 100644 drivers/misc/cardreader/rts5264.c
 create mode 100644 drivers/misc/cardreader/rts5264.h

diff --git a/drivers/misc/cardreader/Makefile b/drivers/misc/cardreader/Makefile
index 895128475d832..1e1bca6b0b22c 100644
--- a/drivers/misc/cardreader/Makefile
+++ b/drivers/misc/cardreader/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MISC_ALCOR_PCI)	+= alcor_pci.o
 obj-$(CONFIG_MISC_RTSX_PCI)	+= rtsx_pci.o
-rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o rts5228.o
+rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o rts5228.o rts5264.o
 obj-$(CONFIG_MISC_RTSX_USB)	+= rtsx_usb.o
diff --git a/drivers/misc/cardreader/rts5264.c b/drivers/misc/cardreader/rts5264.c
new file mode 100644
index 0000000000000..8be4ed7d9d473
--- /dev/null
+++ b/drivers/misc/cardreader/rts5264.c
@@ -0,0 +1,886 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009-2013 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Ricky Wu <ricky_wu@realtek.com>
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/rtsx_pci.h>
+
+#include "rts5264.h"
+#include "rtsx_pcr.h"
+
+static u8 rts5264_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, DUMMY_REG_RESET_0, &val);
+	return val & 0x0F;
+}
+
+static void rts5264_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
+{
+	u8 driving_3v3[4][3] = {
+		{0x88, 0x88, 0x88},
+		{0x77, 0x77, 0x77},
+		{0x99, 0x99, 0x99},
+		{0x66, 0x66, 0x66},
+	};
+	u8 driving_1v8[4][3] = {
+		{0x99, 0x99, 0x99},
+		{0x77, 0x77, 0x77},
+		{0xBB, 0xBB, 0xBB},
+		{0x65, 0x65, 0x65},
+	};
+	u8 (*driving)[3], drive_sel;
+
+	if (voltage == OUTPUT_3V3) {
+		driving = driving_3v3;
+		drive_sel = pcr->sd30_drive_sel_3v3;
+	} else {
+		driving = driving_1v8;
+		drive_sel = pcr->sd30_drive_sel_1v8;
+	}
+
+	rtsx_pci_write_register(pcr, SD30_CLK_DRIVE_SEL,
+			0xFF, driving[drive_sel][0]);
+	rtsx_pci_write_register(pcr, SD30_CMD_DRIVE_SEL,
+			0xFF, driving[drive_sel][1]);
+	rtsx_pci_write_register(pcr, SD30_DAT_DRIVE_SEL,
+			0xFF, driving[drive_sel][2]);
+}
+
+static void rts5264_force_power_down(struct rtsx_pcr *pcr, u8 pm_state, bool runtime)
+{
+	/* Set relink_time to 0 */
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 1, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 2, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 3,
+				RELINK_TIME_MASK, 0);
+
+	if (pm_state == HOST_ENTER_S3)
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3,
+					D3_DELINK_MODE_EN, D3_DELINK_MODE_EN);
+
+	if (!runtime) {
+		rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG1,
+				CD_RESUME_EN_MASK, 0);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL);
+	} else {
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, 0);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x01);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3,
+					D3_DELINK_MODE_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_FW_CTL,
+				RTS5264_INFORM_RTD3_COLD, RTS5264_INFORM_RTD3_COLD);
+		rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+				RTS5264_FORCE_PRSNT_LOW, RTS5264_FORCE_PRSNT_LOW);
+	}
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_FPDCTL,
+		SSC_POWER_DOWN, SSC_POWER_DOWN);
+}
+
+static int rts5264_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_EN);
+}
+
+static int rts5264_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_DISABLE);
+}
+
+static int rts5264_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x02);
+}
+
+static int rts5264_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x00);
+}
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5264_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5264_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+static int rts5264_sd_set_sample_push_timing_sd30(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_MODE_SELECT_MASK
+		| SD_ASYNC_FIFO_NOT_RST, SD_30_MODE | SD_ASYNC_FIFO_NOT_RST);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_write_register(pcr, CARD_CLK_SOURCE, 0xFF,
+			CRC_VAR_CLK0 | SD30_FIX_CLK | SAMPLE_VAR_CLK1);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+
+	return 0;
+}
+
+static int rts5264_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en)
+		rtsx_pci_enable_ocp(pcr);
+
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+		CFG_SD_POW_AUTO_PD, CFG_SD_POW_AUTO_PD);
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG1,
+			RTS5264_LDO1_TUNE_MASK, RTS5264_LDO1_33);
+	rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+			RTS5264_LDO1_POWERON, RTS5264_LDO1_POWERON);
+	rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+			RTS5264_LDO3318_POWERON, RTS5264_LDO3318_POWERON);
+
+	msleep(20);
+
+	rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, SD_OUTPUT_EN);
+
+	/* Initialize SD_CFG1 register */
+	rtsx_pci_write_register(pcr, SD_CFG1, 0xFF,
+			SD_CLK_DIVIDE_128 | SD_20_MODE | SD_BUS_WIDTH_1BIT);
+	rtsx_pci_write_register(pcr, SD_SAMPLE_POINT_CTL,
+			0xFF, SD20_RX_POS_EDGE);
+	rtsx_pci_write_register(pcr, SD_PUSH_POINT_CTL, 0xFF, 0);
+	rtsx_pci_write_register(pcr, CARD_STOP, SD_STOP | SD_CLR_ERR,
+			SD_STOP | SD_CLR_ERR);
+
+	/* Reset SD_CFG3 register */
+	rtsx_pci_write_register(pcr, SD_CFG3, SD30_CLK_END_EN, 0);
+	rtsx_pci_write_register(pcr, REG_SD_STOP_SDCLK_CFG,
+			SD30_CLK_STOP_CFG_EN | SD30_CLK_STOP_CFG1 |
+			SD30_CLK_STOP_CFG0, 0);
+
+	if (pcr->extra_caps & EXTRA_CAPS_SD_SDR50 ||
+	    pcr->extra_caps & EXTRA_CAPS_SD_SDR104)
+		rts5264_sd_set_sample_push_timing_sd30(pcr);
+
+	return 0;
+}
+
+static int rts5264_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	rtsx_pci_write_register(pcr, RTS5264_CARD_PWR_CTL,
+			RTS5264_PUPDC, RTS5264_PUPDC);
+
+	switch (voltage) {
+	case OUTPUT_3V3:
+		rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_TUNE_REF_LDO3318, RTS5264_TUNE_REF_LDO3318);
+		rtsx_pci_write_register(pcr, RTS5264_DV3318_CFG,
+				RTS5264_DV3318_TUNE_MASK, RTS5264_DV3318_33);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, 0);
+		break;
+	case OUTPUT_1V8:
+		rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_TUNE_REF_LDO3318, RTS5264_TUNE_REF_LDO3318_DFT);
+		rtsx_pci_write_register(pcr, RTS5264_DV3318_CFG,
+				RTS5264_DV3318_TUNE_MASK, RTS5264_DV3318_18);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, SD_IO_USING_1V8);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* set pad drive */
+	rts5264_fill_driving(pcr, voltage);
+
+	return 0;
+}
+
+static void rts5264_stop_cmd(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, STOP_CMD);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, STOP_DMA);
+	rtsx_pci_write_register(pcr, DMACTL, DMA_RST, DMA_RST);
+	rtsx_pci_write_register(pcr, RBCTL, RB_FLUSH, RB_FLUSH);
+}
+
+static void rts5264_card_before_power_off(struct rtsx_pcr *pcr)
+{
+	rts5264_stop_cmd(pcr);
+	rts5264_switch_output_voltage(pcr, OUTPUT_3V3);
+}
+
+static int rts5264_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	int err = 0;
+
+	rts5264_card_before_power_off(pcr);
+	err = rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_LDO_POWERON_MASK, 0);
+
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+		CFG_SD_POW_AUTO_PD, 0);
+	if (pcr->option.ocp_en)
+		rtsx_pci_disable_ocp(pcr);
+
+	return err;
+}
+
+static void rts5264_enable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+	u8 val = 0;
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_POW_VDET, RTS5264_POW_VDET);
+
+	mask = SD_OCP_INT_EN | SD_DETECT_EN;
+	mask |= SDVIO_OCP_INT_EN | SDVIO_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val);
+
+	mask = SD_VDD3_OCP_INT_EN | SD_VDD3_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL, mask, val);
+
+	mask = RTS5264_OVP_INT_EN | RTS5264_OVP_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL, mask, val);
+}
+
+static void rts5264_disable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+
+	mask = SD_OCP_INT_EN | SD_DETECT_EN;
+	mask |= SDVIO_OCP_INT_EN | SDVIO_DETECT_EN;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+
+	mask = SD_VDD3_OCP_INT_EN | SD_VDD3_DETECT_EN;
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL, mask, 0);
+
+	mask = RTS5264_OVP_INT_EN | RTS5264_OVP_DETECT_EN;
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL, mask, 0);
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_DET, RTS5264_POW_VDET, 0);
+}
+
+static void rts5264_init_ocp(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en) {
+		u8 mask, val;
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_THD_MASK, option->sd_800mA_ocp_thd);
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_LMT_THD_MASK,
+			RTS5264_LDO1_LMT_THD_2000);
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_THD_MASK, RTS5264_LDO2_OCP_THD_950);
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_LMT_THD_MASK,
+			RTS5264_LDO2_LMT_THD_2000);
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_THD_MASK, RTS5264_LDO3_OCP_THD_710);
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_LMT_THD_MASK,
+			RTS5264_LDO3_LMT_THD_1500);
+
+		rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_TUNE_VROV_MASK, RTS5264_TUNE_VROV_1V6);
+
+		mask = SD_OCP_GLITCH_MASK | SDVIO_OCP_GLITCH_MASK;
+		val = pcr->hw_param.ocp_glitch;
+		rtsx_pci_write_register(pcr, REG_OCPGLITCH, mask, val);
+
+	} else {
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_POW_VDET, 0);
+	}
+}
+
+static int rts5264_get_ocpstat2(struct rtsx_pcr *pcr, u8 *val)
+{
+	return rtsx_pci_read_register(pcr, RTS5264_OCP_VDD3_STS, val);
+}
+
+static int rts5264_get_ovpstat(struct rtsx_pcr *pcr, u8 *val)
+{
+	return rtsx_pci_read_register(pcr, RTS5264_OVP_STS, val);
+}
+
+static void rts5264_clear_ocpstat(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+	u8 val = 0;
+
+	mask = SD_OCP_INT_CLR | SD_OC_CLR;
+	mask |= SDVIO_OCP_INT_CLR | SDVIO_OC_CLR;
+	val = mask;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val);
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR);
+
+	udelay(1000);
+
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR, 0);
+}
+
+static void rts5264_process_ocp(struct rtsx_pcr *pcr)
+{
+	if (!pcr->option.ocp_en)
+		return;
+
+	rtsx_pci_get_ocpstat(pcr, &pcr->ocp_stat);
+	rts5264_get_ocpstat2(pcr, &pcr->ocp_stat2);
+	rts5264_get_ovpstat(pcr, &pcr->ovp_stat);
+
+	if ((pcr->ocp_stat & (SD_OC_NOW | SD_OC_EVER | SDVIO_OC_NOW | SDVIO_OC_EVER)) ||
+			(pcr->ocp_stat2 & (SD_VDD3_OC_NOW | SD_VDD3_OC_EVER)) ||
+			(pcr->ovp_stat & (RTS5264_OVP_NOW | RTS5264_OVP_EVER))) {
+		rts5264_clear_ocpstat(pcr);
+		rts5264_card_power_off(pcr, RTSX_SD_CARD);
+		rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, 0);
+		pcr->ocp_stat = 0;
+		pcr->ocp_stat2 = 0;
+		pcr->ovp_stat = 0;
+	}
+}
+
+static void rts5264_init_from_hw(struct rtsx_pcr *pcr)
+{
+	struct pci_dev *pdev = pcr->pci;
+	u32 lval1, lval2, i;
+	u16 setting_reg1, setting_reg2;
+	u8 valid, efuse_valid, tmp;
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+		REG_EFUSE_POR | REG_EFUSE_POWER_MASK,
+		REG_EFUSE_POR | REG_EFUSE_POWERON);
+	udelay(1);
+	rtsx_pci_write_register(pcr, RTS5264_EFUSE_ADDR,
+		RTS5264_EFUSE_ADDR_MASK, 0x00);
+	rtsx_pci_write_register(pcr, RTS5264_EFUSE_CTL,
+		RTS5264_EFUSE_ENABLE | RTS5264_EFUSE_MODE_MASK,
+		RTS5264_EFUSE_ENABLE);
+
+	/* Wait transfer end */
+	for (i = 0; i < MAX_RW_REG_CNT; i++) {
+		rtsx_pci_read_register(pcr, RTS5264_EFUSE_CTL, &tmp);
+		if ((tmp & 0x80) == 0)
+			break;
+	}
+	rtsx_pci_read_register(pcr, RTS5264_EFUSE_READ_DATA, &tmp);
+	efuse_valid = ((tmp & 0x0C) >> 2);
+	pcr_dbg(pcr, "Load efuse valid: 0x%x\n", efuse_valid);
+
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &lval2);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, lval2);
+	/* 0x816 */
+	valid = (u8)((lval2 >> 16) & 0x03);
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+		REG_EFUSE_POR, 0);
+	pcr_dbg(pcr, "Disable efuse por!\n");
+
+	if (efuse_valid == 2 || efuse_valid == 3) {
+		if (valid == 3) {
+			/* Bypass efuse */
+			setting_reg1 = PCR_SETTING_REG1;
+			setting_reg2 = PCR_SETTING_REG2;
+		} else {
+			/* Use efuse data */
+			setting_reg1 = PCR_SETTING_REG4;
+			setting_reg2 = PCR_SETTING_REG5;
+		}
+	} else if (efuse_valid == 0) {
+		// default
+		setting_reg1 = PCR_SETTING_REG1;
+		setting_reg2 = PCR_SETTING_REG2;
+	} else {
+		return;
+	}
+
+	pci_read_config_dword(pdev, setting_reg2, &lval2);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg2, lval2);
+
+	if (!rts5264_vendor_setting_valid(lval2)) {
+		pcr_dbg(pcr, "skip fetch vendor setting\n");
+		return;
+	}
+
+	pcr->rtd3_en = rts5264_reg_to_rtd3(lval2);
+
+	if (rts5264_reg_check_reverse_socket(lval2))
+		pcr->flags |= PCR_REVERSE_SOCKET;
+
+	pci_read_config_dword(pdev, setting_reg1, &lval1);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg1, lval1);
+
+	pcr->aspm_en = rts5264_reg_to_aspm(lval1);
+	pcr->sd30_drive_sel_1v8 = rts5264_reg_to_sd30_drive_sel_1v8(lval1);
+	pcr->sd30_drive_sel_3v3 = rts5264_reg_to_sd30_drive_sel_3v3(lval1);
+
+	if (setting_reg1 == PCR_SETTING_REG1) {
+		/* store setting */
+		rtsx_pci_write_register(pcr, 0xFF0C, 0xFF, (u8)(lval1 & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0D, 0xFF, (u8)((lval1 >> 8) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0E, 0xFF, (u8)((lval1 >> 16) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0F, 0xFF, (u8)((lval1 >> 24) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF10, 0xFF, (u8)(lval2 & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF11, 0xFF, (u8)((lval2 >> 8) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF12, 0xFF, (u8)((lval2 >> 16) & 0xFF));
+
+		pci_write_config_dword(pdev, PCR_SETTING_REG4, lval1);
+		lval2 = lval2 & 0x00FFFFFF;
+		pci_write_config_dword(pdev, PCR_SETTING_REG5, lval2);
+	}
+}
+
+static void rts5264_init_from_cfg(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+				| PM_L1_1_EN | PM_L1_2_EN))
+		rtsx_pci_disable_oobs_polling(pcr);
+	else
+		rtsx_pci_enable_oobs_polling(pcr);
+
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0);
+
+	if (option->ltr_en) {
+		if (option->ltr_enabled)
+			rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
+	}
+}
+
+static int rts5264_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG1,
+			CD_RESUME_EN_MASK, CD_RESUME_EN_MASK);
+	rtsx_pci_write_register(pcr, REG_VREF, PWD_SUSPND_EN, PWD_SUSPND_EN);
+
+	rts5264_init_from_cfg(pcr);
+	rts5264_init_from_hw(pcr);
+
+	/* power off efuse */
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+			REG_EFUSE_POWER_MASK, REG_EFUSE_POWEROFF);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG2,
+			RTS5264_CHIP_RST_N_SEL, 0);
+	rtsx_pci_write_register(pcr, RTS5264_REG_LDO12_CFG,
+			RTS5264_LDO12_SR_MASK, RTS5264_LDO12_SR_0_0_MS);
+	rtsx_pci_write_register(pcr, CDGW, 0xFF, 0x01);
+	rtsx_pci_write_register(pcr, RTS5264_CKMUX_MBIAS_PWR,
+			RTS5264_POW_CKMUX, RTS5264_POW_CKMUX);
+	rtsx_pci_write_register(pcr, RTS5264_CMD_OE_START_EARLY,
+			RTS5264_CMD_OE_EARLY_EN | RTS5264_CMD_OE_EARLY_CYCLE_MASK,
+			RTS5264_CMD_OE_EARLY_EN);
+	rtsx_pci_write_register(pcr, RTS5264_DAT_OE_START_EARLY,
+			RTS5264_DAT_OE_EARLY_EN | RTS5264_DAT_OE_EARLY_CYCLE_MASK,
+			RTS5264_DAT_OE_EARLY_EN);
+	rtsx_pci_write_register(pcr, SSC_DIV_N_0, 0xFF, 0x5D);
+
+	rtsx_pci_write_register(pcr, RTS5264_PWR_CUT,
+			RTS5264_CFG_MEM_PD, RTS5264_CFG_MEM_PD);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG1,
+			AUX_CLK_ACTIVE_SEL_MASK, MAC_CKSW_DONE);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG3, 0xFF, 0);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_AUX_CLK_16M_EN, 0);
+
+	/* Release PRSNT# */
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_FORCE_PRSNT_LOW, 0);
+	rtsx_pci_write_register(pcr, PCLK_CTL,
+			PCLK_MODE_SEL, PCLK_MODE_SEL);
+
+	/* LED shine disabled, set initial shine cycle period */
+	rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x0F, 0x02);
+
+	/* Configure driving */
+	rts5264_fill_driving(pcr, OUTPUT_3V3);
+
+	if (pcr->flags & PCR_REVERSE_SOCKET)
+		rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x30);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00);
+
+	/*
+	 * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
+	 * to drive low, and we forcibly request clock.
+	 */
+	if (option->force_clkreq_0)
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+
+	rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFF);
+	rtsx_pci_write_register(pcr, RBCTL, U_AUTO_DMA_EN_MASK, 0);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_F_HIGH_RC_MASK, RTS5264_F_HIGH_RC_400K);
+
+	if (pcr->rtd3_en) {
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, 0);
+	} else {
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL);
+	}
+	rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, D3_DELINK_MODE_EN, 0x00);
+
+	/* Clear Enter RTD3_cold Information*/
+	rtsx_pci_write_register(pcr, RTS5264_FW_CTL,
+		RTS5264_INFORM_RTD3_COLD, 0);
+
+	return 0;
+}
+
+static void rts5264_enable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	u8 val = FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	val |= (pcr->aspm_en & 0x02);
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, pcr->aspm_en);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5264_disable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	u8 val = FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, 0);
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0);
+	udelay(10);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5264_set_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	if (enable)
+		rts5264_enable_aspm(pcr, true);
+	else
+		rts5264_disable_aspm(pcr, false);
+}
+
+static void rts5264_set_l1off_cfg_sub_d0(struct rtsx_pcr *pcr, int active)
+{
+	struct rtsx_cr_option *option = &(pcr->option);
+
+	u32 interrupt = rtsx_pci_readl(pcr, RTSX_BIPR);
+	int card_exist = (interrupt & SD_EXIST);
+	int aspm_L1_1, aspm_L1_2;
+	u8 val = 0;
+
+	aspm_L1_1 = rtsx_check_dev_flag(pcr, ASPM_L1_1_EN);
+	aspm_L1_2 = rtsx_check_dev_flag(pcr, ASPM_L1_2_EN);
+
+	if (active) {
+		/* Run, latency: 60us */
+		if (aspm_L1_1)
+			val = option->ltr_l1off_snooze_sspwrgate;
+	} else {
+		/* L1off, latency: 300us */
+		if (aspm_L1_2)
+			val = option->ltr_l1off_sspwrgate;
+	}
+
+	if (aspm_L1_1 || aspm_L1_2) {
+		if (rtsx_check_dev_flag(pcr,
+					LTR_L1SS_PWR_GATE_CHECK_CARD_EN)) {
+			if (card_exist)
+				val &= ~L1OFF_MBIAS2_EN_5250;
+			else
+				val |= L1OFF_MBIAS2_EN_5250;
+		}
+	}
+	rtsx_set_l1off_sub(pcr, val);
+}
+
+static const struct pcr_ops rts5264_pcr_ops = {
+	.turn_on_led = rts5264_turn_on_led,
+	.turn_off_led = rts5264_turn_off_led,
+	.extra_init_hw = rts5264_extra_init_hw,
+	.enable_auto_blink = rts5264_enable_auto_blink,
+	.disable_auto_blink = rts5264_disable_auto_blink,
+	.card_power_on = rts5264_card_power_on,
+	.card_power_off = rts5264_card_power_off,
+	.switch_output_voltage = rts5264_switch_output_voltage,
+	.force_power_down = rts5264_force_power_down,
+	.stop_cmd = rts5264_stop_cmd,
+	.set_aspm = rts5264_set_aspm,
+	.set_l1off_cfg_sub_d0 = rts5264_set_l1off_cfg_sub_d0,
+	.enable_ocp = rts5264_enable_ocp,
+	.disable_ocp = rts5264_disable_ocp,
+	.init_ocp = rts5264_init_ocp,
+	.process_ocp = rts5264_process_ocp,
+	.clear_ocpstat = rts5264_clear_ocpstat,
+};
+
+static inline u8 double_ssc_depth(u8 depth)
+{
+	return ((depth > 1) ? (depth - 1) : depth);
+}
+
+int rts5264_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk)
+{
+	int err, clk;
+	u16 n;
+	u8 clk_divider, mcu_cnt, div;
+	static const u8 depth[] = {
+		[RTSX_SSC_DEPTH_4M] = RTS5264_SSC_DEPTH_4M,
+		[RTSX_SSC_DEPTH_2M] = RTS5264_SSC_DEPTH_2M,
+		[RTSX_SSC_DEPTH_1M] = RTS5264_SSC_DEPTH_1M,
+		[RTSX_SSC_DEPTH_500K] = RTS5264_SSC_DEPTH_512K,
+	};
+
+	if (initial_mode) {
+		/* We use 250k(around) here, in initial stage */
+		clk_divider = SD_CLK_DIVIDE_128;
+		card_clock = 30000000;
+	} else {
+		clk_divider = SD_CLK_DIVIDE_0;
+	}
+	err = rtsx_pci_write_register(pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, clk_divider);
+	if (err < 0)
+		return err;
+
+	card_clock /= 1000000;
+	pcr_dbg(pcr, "Switch card clock to %dMHz\n", card_clock);
+
+	clk = card_clock;
+	if (!initial_mode && double_clk)
+		clk = card_clock * 2;
+	pcr_dbg(pcr, "Internal SSC clock: %dMHz (cur_clock = %d)\n",
+		clk, pcr->cur_clock);
+
+	if (clk == pcr->cur_clock)
+		return 0;
+
+	if (pcr->ops->conv_clk_and_div_n)
+		n = pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N);
+	else
+		n = clk - 4;
+	if ((clk <= 4) || (n > 396))
+		return -EINVAL;
+
+	mcu_cnt = 125/clk + 3;
+	if (mcu_cnt > 15)
+		mcu_cnt = 15;
+
+	div = CLK_DIV_1;
+	while ((n < MIN_DIV_N_PCR - 4) && (div < CLK_DIV_8)) {
+		if (pcr->ops->conv_clk_and_div_n) {
+			int dbl_clk = pcr->ops->conv_clk_and_div_n(n,
+					DIV_N_TO_CLK) * 2;
+			n = pcr->ops->conv_clk_and_div_n(dbl_clk,
+					CLK_TO_DIV_N);
+		} else {
+			n = (n + 4) * 2 - 4;
+		}
+		div++;
+	}
+
+	n = (n / 2) - 1;
+	pcr_dbg(pcr, "n = %d, div = %d\n", n, div);
+
+	ssc_depth = depth[ssc_depth];
+	if (double_clk)
+		ssc_depth = double_ssc_depth(ssc_depth);
+
+	if (ssc_depth) {
+		if (div == CLK_DIV_2) {
+			if (ssc_depth > 1)
+				ssc_depth -= 1;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_4) {
+			if (ssc_depth > 2)
+				ssc_depth -= 2;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_8) {
+			if (ssc_depth > 3)
+				ssc_depth -= 3;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		}
+	} else {
+		ssc_depth = 0;
+	}
+	pcr_dbg(pcr, "ssc_depth = %d\n", ssc_depth);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL,
+				CHANGE_CLK, CHANGE_CLK);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV,
+			0xFF, (div << 4) | mcu_cnt);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2,
+			SSC_DEPTH_MASK, ssc_depth);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, n);
+
+	if (is_version(pcr, 0x5264, IC_VER_A)) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RTS5264_CARD_CLK_SRC2,
+			RTS5264_REG_BIG_KVCO_A, 0);
+	} else {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RTS5264_SYS_DUMMY_1,
+			RTS5264_REG_BIG_KVCO, 0);
+	}
+
+	if (vpclk) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 2000);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC clock stable */
+	udelay(SSC_CLOCK_STABLE_WAIT);
+	err = rtsx_pci_write_register(pcr, CLK_CTL, CHANGE_CLK, 0);
+	if (err < 0)
+		return err;
+
+	pcr->cur_clock = clk;
+	return 0;
+}
+
+void rts5264_init_params(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	struct rtsx_hw_param *hw_param = &pcr->hw_param;
+	u8 val;
+
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
+	rtsx_pci_read_register(pcr, RTS5264_FW_STATUS, &val);
+	if (!(val & RTS5264_EXPRESS_LINK_FAIL_MASK))
+		pcr->extra_caps |= EXTRA_CAPS_SD_EXPRESS;
+	pcr->num_slots = 1;
+	pcr->ops = &rts5264_pcr_ops;
+
+	pcr->flags = 0;
+	pcr->card_drive_sel = RTSX_CARD_DRIVE_DEFAULT;
+	pcr->sd30_drive_sel_1v8 = 0x00;
+	pcr->sd30_drive_sel_3v3 = 0x00;
+	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_REG;
+	pcr->tx_initial_phase = SET_CLOCK_PHASE(24, 24, 11);
+	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
+
+	pcr->ic_version = rts5264_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rts5264_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rts5264_sd_pull_ctl_disable_tbl;
+
+	pcr->reg_pm_ctrl3 = RTS5264_AUTOLOAD_CFG3;
+
+	option->dev_flags = (LTR_L1SS_PWR_GATE_CHECK_CARD_EN
+				| LTR_L1SS_PWR_GATE_EN);
+	option->ltr_en = true;
+
+	/* init latency of active, idle, L1OFF to 60us, 300us, 3ms */
+	option->ltr_active_latency = LTR_ACTIVE_LATENCY_DEF;
+	option->ltr_idle_latency = LTR_IDLE_LATENCY_DEF;
+	option->ltr_l1off_latency = LTR_L1OFF_LATENCY_DEF;
+	option->l1_snooze_delay = L1_SNOOZE_DELAY_DEF;
+	option->ltr_l1off_sspwrgate = 0x7F;
+	option->ltr_l1off_snooze_sspwrgate = 0x78;
+
+	option->ocp_en = 1;
+	hw_param->interrupt_en |= (SD_OC_INT_EN | SD_OVP_INT_EN);
+	hw_param->ocp_glitch =  SD_OCP_GLITCH_800U | SDVIO_OCP_GLITCH_800U;
+	option->sd_800mA_ocp_thd =  RTS5264_LDO1_OCP_THD_1150;
+}
diff --git a/drivers/misc/cardreader/rts5264.h b/drivers/misc/cardreader/rts5264.h
new file mode 100644
index 0000000000000..e3cbbf2fe1a43
--- /dev/null
+++ b/drivers/misc/cardreader/rts5264.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Ricky Wu <ricky_wu@realtek.com>
+ */
+#ifndef RTS5264_H
+#define RTS5264_H
+
+/*New add*/
+#define rts5264_vendor_setting_valid(reg)	((reg) & 0x010000)
+#define rts5264_reg_to_aspm(reg) \
+	(((~(reg) >> 28) & 0x02) | (((reg) >> 28) & 0x01))
+#define rts5264_reg_check_reverse_socket(reg)	((reg) & 0x04)
+#define rts5264_reg_to_sd30_drive_sel_1v8(reg)	(((reg) >> 22) & 0x03)
+#define rts5264_reg_to_sd30_drive_sel_3v3(reg)	(((reg) >> 16) & 0x03)
+#define rts5264_reg_to_rtd3(reg)		((reg) & 0x08)
+
+#define RTS5264_AUTOLOAD_CFG0		0xFF7B
+#define RTS5264_AUTOLOAD_CFG1		0xFF7C
+#define RTS5264_AUTOLOAD_CFG3		0xFF7E
+#define RTS5264_AUTOLOAD_CFG4		0xFF7F
+#define RTS5264_FORCE_PRSNT_LOW		(1 << 6)
+#define RTS5264_AUX_CLK_16M_EN		(1 << 5)
+#define RTS5264_F_HIGH_RC_MASK		(1 << 4)
+#define RTS5264_F_HIGH_RC_1_6M		(1 << 4)
+#define RTS5264_F_HIGH_RC_400K		(0 << 4)
+
+/* SSC_CTL2 0xFC12 */
+#define RTS5264_SSC_DEPTH_MASK		0x07
+#define RTS5264_SSC_DEPTH_DISALBE	0x00
+#define RTS5264_SSC_DEPTH_8M		0x01
+#define RTS5264_SSC_DEPTH_4M		0x02
+#define RTS5264_SSC_DEPTH_2M		0x03
+#define RTS5264_SSC_DEPTH_1M		0x04
+#define RTS5264_SSC_DEPTH_512K		0x05
+#define RTS5264_SSC_DEPTH_256K		0x06
+#define RTS5264_SSC_DEPTH_128K		0x07
+
+#define RTS5264_CARD_CLK_SRC2		0xFC2F
+#define RTS5264_REG_BIG_KVCO_A		0x20
+
+/* efuse control register*/
+#define RTS5264_EFUSE_CTL		0xFC30
+#define RTS5264_EFUSE_ENABLE		0x80
+/* EFUSE_MODE: 0=READ 1=PROGRAM */
+#define RTS5264_EFUSE_MODE_MASK		0x40
+#define RTS5264_EFUSE_PROGRAM		0x40
+
+#define RTS5264_EFUSE_ADDR		0xFC31
+#define	RTS5264_EFUSE_ADDR_MASK		0x3F
+
+#define RTS5264_EFUSE_WRITE_DATA	0xFC32
+#define RTS5264_EFUSE_READ_DATA		0xFC34
+
+#define RTS5264_SYS_DUMMY_1		0xFC35
+#define RTS5264_REG_BIG_KVCO		0x04
+
+/* DMACTL 0xFE2C */
+#define RTS5264_DMA_PACK_SIZE_MASK	0x70
+
+#define RTS5264_FW_CFG1			0xFF55
+#define RTS5264_SYS_CLK_SEL_MCU_CLK	(0x01<<7)
+#define RTS5264_CRC_CLK_SEL_MCU_CLK	(0x01<<6)
+#define RTS5264_FAKE_MCU_CLOCK_GATING	(0x01<<5)
+#define RTS5264_MCU_BUS_SEL_MASK	(0x01<<4)
+
+/* FW status register */
+#define RTS5264_FW_STATUS		0xFF56
+#define RTS5264_EXPRESS_LINK_FAIL_MASK	(0x01<<7)
+
+/* FW control register */
+#define RTS5264_FW_CTL			0xFF5F
+#define RTS5264_INFORM_RTD3_COLD	(0x01<<5)
+
+#define RTS5264_REG_FPDCTL		0xFF60
+
+#define RTS5264_REG_LDO12_CFG		0xFF6E
+#define RTS5264_LDO12_SR_MASK		(0x03<<6)
+#define RTS5264_LDO12_SR_1_0_MS		(0x03<<6)
+#define RTS5264_LDO12_SR_0_5_MS		(0x02<<6)
+#define RTS5264_LDO12_SR_0_2_5_MS	(0x01<<6)
+#define RTS5264_LDO12_SR_0_0_MS		(0x00<<6)
+#define RTS5264_LDO12_VO_TUNE_MASK	(0x07<<1)
+#define RTS5264_LDO12_115		(0x03<<1)
+#define RTS5264_LDO12_120		(0x04<<1)
+#define RTS5264_LDO12_125		(0x05<<1)
+#define RTS5264_LDO12_130		(0x06<<1)
+#define RTS5264_LDO12_135		(0x07<<1)
+
+/* LDO control register */
+#define RTS5264_CARD_PWR_CTL		0xFD50
+#define RTS5264_SD_CLK_ISO		(0x01<<7)
+#define RTS5264_PAD_SD_DAT_FW_CTRL	(0x01<<6)
+#define RTS5264_PUPDC			(0x01<<5)
+#define RTS5264_SD_CMD_ISO		(0x01<<4)
+
+#define RTS5264_OCP_VDD3_CTL		0xFD89
+#define SD_VDD3_DETECT_EN		0x08
+#define SD_VDD3_OCP_INT_EN		0x04
+#define SD_VDD3_OCP_INT_CLR		0x02
+#define SD_VDD3_OC_CLR			0x01
+
+#define RTS5264_OCP_VDD3_STS		0xFD8A
+#define SD_VDD3_OCP_DETECT		0x08
+#define SD_VDD3_OC_NOW			0x04
+#define SD_VDD3_OC_EVER			0x02
+
+#define RTS5264_OVP_CTL			0xFD8D
+#define RTS5264_OVP_TIME_MASK		0xF0
+#define RTS5264_OVP_TIME_DFT		0x50
+#define RTS5264_OVP_DETECT_EN		0x08
+#define RTS5264_OVP_INT_EN		0x04
+#define RTS5264_OVP_INT_CLR		0x02
+#define RTS5264_OVP_CLR			0x01
+
+#define RTS5264_OVP_STS			0xFD8E
+#define RTS5264_OVP_GLTCH_TIME_MASK	0xF0
+#define RTS5264_OVP_GLTCH_TIME_DFT	0x50
+#define RTS5264_VOVER_DET		0x08
+#define RTS5264_OVP_NOW			0x04
+#define RTS5264_OVP_EVER		0x02
+
+#define RTS5264_CMD_OE_START_EARLY		0xFDCB
+#define RTS5264_CMD_OE_EARLY_LEAVE		0x08
+#define RTS5264_CMD_OE_EARLY_CYCLE_MASK		0x06
+#define RTS5264_CMD_OE_EARLY_4CYCLE		0x06
+#define RTS5264_CMD_OE_EARLY_3CYCLE		0x04
+#define RTS5264_CMD_OE_EARLY_2CYCLE		0x02
+#define RTS5264_CMD_OE_EARLY_1CYCLE		0x00
+#define RTS5264_CMD_OE_EARLY_EN			0x01
+
+#define RTS5264_DAT_OE_START_EARLY		0xFDCC
+#define RTS5264_DAT_OE_EARLY_LEAVE		0x08
+#define RTS5264_DAT_OE_EARLY_CYCLE_MASK		0x06
+#define RTS5264_DAT_OE_EARLY_4CYCLE		0x06
+#define RTS5264_DAT_OE_EARLY_3CYCLE		0x04
+#define RTS5264_DAT_OE_EARLY_2CYCLE		0x02
+#define RTS5264_DAT_OE_EARLY_1CYCLE		0x00
+#define RTS5264_DAT_OE_EARLY_EN			0x01
+
+#define RTS5264_LDO1233318_POW_CTL	0xFF70
+#define RTS5264_TUNE_REF_LDO3318	(0x03<<6)
+#define RTS5264_TUNE_REF_LDO3318_DFT	(0x02<<6)
+#define RTS5264_LDO3318_POWERON		(0x01<<3)
+#define RTS5264_LDO3_POWERON		(0x01<<2)
+#define RTS5264_LDO2_POWERON		(0x01<<1)
+#define RTS5264_LDO1_POWERON		(0x01<<0)
+#define RTS5264_LDO_POWERON_MASK	(0x0F<<0)
+
+#define RTS5264_DV3318_CFG		0xFF71
+#define RTS5264_DV3318_TUNE_MASK	(0x07<<4)
+#define RTS5264_DV3318_18		(0x02<<4)
+#define RTS5264_DV3318_19		(0x04<<4)
+#define RTS5264_DV3318_33		(0x07<<4)
+
+#define RTS5264_LDO1_CFG0		0xFF72
+#define RTS5264_LDO1_OCP_THD_MASK	(0x07 << 5)
+#define RTS5264_LDO1_OCP_EN		(0x01 << 4)
+#define RTS5264_LDO1_OCP_LMT_THD_MASK	(0x03 << 2)
+#define RTS5264_LDO1_OCP_LMT_EN		(0x01 << 1)
+
+#define RTS5264_LDO1_OCP_THD_850	(0x00<<5)
+#define RTS5264_LDO1_OCP_THD_950	(0x01<<5)
+#define RTS5264_LDO1_OCP_THD_1050	(0x02<<5)
+#define RTS5264_LDO1_OCP_THD_1100	(0x03<<5)
+#define RTS5264_LDO1_OCP_THD_1150	(0x04<<5)
+#define RTS5264_LDO1_OCP_THD_1200	(0x05<<5)
+#define RTS5264_LDO1_OCP_THD_1300	(0x06<<5)
+#define RTS5264_LDO1_OCP_THD_1350	(0x07<<5)
+
+#define RTS5264_LDO1_LMT_THD_1700	(0x00<<2)
+#define RTS5264_LDO1_LMT_THD_1800	(0x01<<2)
+#define RTS5264_LDO1_LMT_THD_1900	(0x02<<2)
+#define RTS5264_LDO1_LMT_THD_2000	(0x03<<2)
+
+#define RTS5264_LDO1_CFG1		0xFF73
+#define RTS5264_LDO1_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO1_18			(0x05<<1)
+#define RTS5264_LDO1_33			(0x07<<1)
+#define RTS5264_LDO1_PWD_MASK		(0x01<<0)
+
+#define RTS5264_LDO2_CFG0		0xFF74
+#define RTS5264_LDO2_OCP_THD_MASK	(0x07<<5)
+#define RTS5264_LDO2_OCP_EN		(0x01<<4)
+#define RTS5264_LDO2_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5264_LDO2_OCP_LMT_EN		(0x01<<1)
+
+#define RTS5264_LDO2_OCP_THD_750	(0x00<<5)
+#define RTS5264_LDO2_OCP_THD_850	(0x01<<5)
+#define RTS5264_LDO2_OCP_THD_900	(0x02<<5)
+#define RTS5264_LDO2_OCP_THD_950	(0x03<<5)
+#define RTS5264_LDO2_OCP_THD_1050	(0x04<<5)
+#define RTS5264_LDO2_OCP_THD_1100	(0x05<<5)
+#define RTS5264_LDO2_OCP_THD_1150	(0x06<<5)
+#define RTS5264_LDO2_OCP_THD_1200	(0x07<<5)
+
+#define RTS5264_LDO2_LMT_THD_1700	(0x00<<2)
+#define RTS5264_LDO2_LMT_THD_1800	(0x01<<2)
+#define RTS5264_LDO2_LMT_THD_1900	(0x02<<2)
+#define RTS5264_LDO2_LMT_THD_2000	(0x03<<2)
+
+#define RTS5264_LDO2_CFG1		0xFF75
+#define RTS5264_LDO2_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO2_18			(0x02<<1)
+#define RTS5264_LDO2_185		(0x03<<1)
+#define RTS5264_LDO2_19			(0x04<<1)
+#define RTS5264_LDO2_195		(0x05<<1)
+#define RTS5264_LDO2_33			(0x07<<1)
+#define RTS5264_LDO2_PWD_MASK		(0x01<<0)
+
+#define RTS5264_LDO3_CFG0		0xFF76
+#define RTS5264_LDO3_OCP_THD_MASK	(0x07<<5)
+#define RTS5264_LDO3_OCP_EN		(0x01<<4)
+#define RTS5264_LDO3_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5264_LDO3_OCP_LMT_EN		(0x01<<1)
+
+#define RTS5264_LDO3_OCP_THD_610	(0x00<<5)
+#define RTS5264_LDO3_OCP_THD_630	(0x01<<5)
+#define RTS5264_LDO3_OCP_THD_670	(0x02<<5)
+#define RTS5264_LDO3_OCP_THD_710	(0x03<<5)
+#define RTS5264_LDO3_OCP_THD_750	(0x04<<5)
+#define RTS5264_LDO3_OCP_THD_770	(0x05<<5)
+#define RTS5264_LDO3_OCP_THD_810	(0x06<<5)
+#define RTS5264_LDO3_OCP_THD_850	(0x07<<5)
+
+#define RTS5264_LDO3_LMT_THD_1200	(0x00<<2)
+#define RTS5264_LDO3_LMT_THD_1300	(0x01<<2)
+#define RTS5264_LDO3_LMT_THD_1400	(0x02<<2)
+#define RTS5264_LDO3_LMT_THD_1500	(0x03<<2)
+
+#define RTS5264_LDO3_CFG1		0xFF77
+#define RTS5264_LDO3_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO3_12			(0x02<<1)
+#define RTS5264_LDO3_125		(0x03<<1)
+#define RTS5264_LDO3_13			(0x04<<1)
+#define RTS5264_LDO3_135		(0x05<<1)
+#define RTS5264_LDO3_33			(0x07<<1)
+#define RTS5264_LDO3_PWD_MASK		(0x01<<0)
+
+#define RTS5264_REG_PME_FORCE_CTL	0xFF78
+#define FORCE_PM_CONTROL		0x20
+#define FORCE_PM_VALUE			0x10
+#define REG_EFUSE_BYPASS		0x08
+#define REG_EFUSE_POR			0x04
+#define REG_EFUSE_POWER_MASK		0x03
+#define REG_EFUSE_POWERON		0x03
+#define REG_EFUSE_POWEROFF		0x00
+
+#define RTS5264_PWR_CUT			0xFF81
+#define RTS5264_CFG_MEM_PD		0xF0
+
+#define RTS5264_OVP_DET			0xFF8A
+#define RTS5264_POW_VDET		0x04
+#define RTS5264_TUNE_VROV_MASK		0x03
+#define RTS5264_TUNE_VROV_2V		0x03
+#define RTS5264_TUNE_VROV_1V8		0x02
+#define RTS5264_TUNE_VROV_1V6		0x01
+#define RTS5264_TUNE_VROV_1V4		0x00
+
+#define RTS5264_CKMUX_MBIAS_PWR		0xFF8B
+#define RTS5264_NON_XTAL_SEL		0x80
+#define RTS5264_POW_CKMUX		0x40
+#define RTS5264_LVD_MASK		0x04
+#define RTS5264_POW_PSW_MASK		0x03
+#define RTS5264_POW_PSW_DFT		0x03
+
+/* Single LUN, support SD/SD EXPRESS */
+#define DEFAULT_SINGLE		0
+#define SD_LUN			1
+#define SD_EXPRESS_LUN		2
+
+int rts5264_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
+
+#endif /* RTS5264_H */
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 534038d962e4f..4612ef09a0c76 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -60,6 +60,7 @@
 #define   SD_EXIST			(1 << 16)
 #define   DELINK_INT			GPIO0_INT
 #define   MS_OC_INT			(1 << 23)
+#define   SD_OVP_INT		(1 << 23)
 #define   SD_OC_INT			(1 << 22)
 
 #define CARD_INT		(XD_INT | MS_INT | SD_INT)
@@ -80,6 +81,7 @@
 #define   OC_INT_EN			(1 << 23)
 #define   DELINK_INT_EN			GPIO0_INT_EN
 #define   MS_OC_INT_EN			(1 << 23)
+#define   SD_OVP_INT_EN			(1 << 23)
 #define   SD_OC_INT_EN			(1 << 22)
 
 #define RTSX_DUM_REG			0x1C
@@ -583,6 +585,7 @@
 #define   OBFF_DISABLE			0x00
 
 #define CDRESUMECTL			0xFE52
+#define CDGW				0xFE53
 #define WAKE_SEL_CTL			0xFE54
 #define PCLK_CTL			0xFE55
 #define   PCLK_MODE_SEL			0x20
@@ -764,6 +767,9 @@
 #define   SD_VIO_LDO_1V8		0x40
 #define   SD_VIO_LDO_3V3		0x70
 
+#define RTS5264_AUTOLOAD_CFG2		0xFF7D
+#define RTS5264_CHIP_RST_N_SEL		(1 << 6)
+
 #define RTS5260_AUTOLOAD_CFG4		0xFF7F
 #define   RTS5260_MIMO_DISABLE		0x8A
 /*RTS5261*/
@@ -1261,6 +1267,7 @@ struct rtsx_pcr {
 	u8				dma_error_count;
 	u8			ocp_stat;
 	u8			ocp_stat2;
+	u8			ovp_stat;
 	u8			rtd3_en;
 };
 
@@ -1271,6 +1278,7 @@ struct rtsx_pcr {
 #define PID_5260	0x5260
 #define PID_5261	0x5261
 #define PID_5228	0x5228
+#define PID_5264	0x5264
 
 #define CHK_PCI_PID(pcr, pid)		((pcr)->pci->device == (pid))
 #define PCI_VID(pcr)			((pcr)->pci->vendor)
-- 
GitLab


From 6a511c9b3a0df7a10b06694c20f3ebdc08be98cd Mon Sep 17 00:00:00 2001
From: Ricky Wu <ricky_wu@realtek.com>
Date: Fri, 8 Dec 2023 11:21:44 +0800
Subject: [PATCH 1455/4076] misc: rtsx: add to support new card reader rts5264

in order to support rts5264 in rtsx_pcr add the id in and
determine whether the device is rts5264 to call rts5264
functions and do rts5264 workflows or set rts5264 registers

Signed-off-by: Ricky Wu <ricky_wu@realtek.com>
Link: https://lore.kernel.org/r/20231208032145.2143580-3-ricky_wu@realtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rtsx_pcr.c | 30 +++++++++++++++++++++++++-----
 drivers/misc/cardreader/rtsx_pcr.h |  1 +
 2 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index a30751ad37330..1a64364700eb0 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -26,6 +26,7 @@
 #include "rtsx_pcr.h"
 #include "rts5261.h"
 #include "rts5228.h"
+#include "rts5264.h"
 
 static bool msi_en = true;
 module_param(msi_en, bool, S_IRUGO | S_IWUSR);
@@ -54,6 +55,7 @@ static const struct pci_device_id rtsx_pci_ids[] = {
 	{ PCI_DEVICE(0x10EC, 0x5260), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ PCI_DEVICE(0x10EC, 0x5261), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ PCI_DEVICE(0x10EC, 0x5228), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ PCI_DEVICE(0x10EC, 0x5264), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ 0, }
 };
 
@@ -714,6 +716,9 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
 	if (PCI_PID(pcr) == PID_5228)
 		return rts5228_pci_switch_clock(pcr, card_clock,
 				ssc_depth, initial_mode, double_clk, vpclk);
+	if (PCI_PID(pcr) == PID_5264)
+		return rts5264_pci_switch_clock(pcr, card_clock,
+				ssc_depth, initial_mode, double_clk, vpclk);
 
 	if (initial_mode) {
 		/* We use 250k(around) here, in initial stage */
@@ -987,7 +992,8 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
 
 	int_reg &= (pcr->bier | 0x7FFFFF);
 
-	if (int_reg & SD_OC_INT)
+	if ((int_reg & SD_OC_INT) ||
+			((int_reg & SD_OVP_INT) && (PCI_PID(pcr) == PID_5264)))
 		rtsx_pci_process_ocp_interrupt(pcr);
 
 	if (int_reg & SD_INT) {
@@ -1159,7 +1165,9 @@ void rtsx_pci_enable_oobs_polling(struct rtsx_pcr *pcr)
 {
 	u16 val;
 
-	if ((PCI_PID(pcr) != PID_525A) && (PCI_PID(pcr) != PID_5260)) {
+	if ((PCI_PID(pcr) != PID_525A) &&
+		(PCI_PID(pcr) != PID_5260) &&
+		(PCI_PID(pcr) != PID_5264)) {
 		rtsx_pci_read_phy_register(pcr, 0x01, &val);
 		val |= 1<<9;
 		rtsx_pci_write_phy_register(pcr, 0x01, val);
@@ -1175,7 +1183,9 @@ void rtsx_pci_disable_oobs_polling(struct rtsx_pcr *pcr)
 {
 	u16 val;
 
-	if ((PCI_PID(pcr) != PID_525A) && (PCI_PID(pcr) != PID_5260)) {
+	if ((PCI_PID(pcr) != PID_525A) &&
+		(PCI_PID(pcr) != PID_5260) &&
+		(PCI_PID(pcr) != PID_5264)) {
 		rtsx_pci_read_phy_register(pcr, 0x01, &val);
 		val &= ~(1<<9);
 		rtsx_pci_write_phy_register(pcr, 0x01, val);
@@ -1226,7 +1236,7 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	rtsx_pci_enable_bus_int(pcr);
 
 	/* Power on SSC */
-	if (PCI_PID(pcr) == PID_5261) {
+	if ((PCI_PID(pcr) == PID_5261) || (PCI_PID(pcr) == PID_5264)) {
 		/* Gating real mcu clock */
 		err = rtsx_pci_write_register(pcr, RTS5261_FW_CFG1,
 			RTS5261_MCU_CLOCK_GATING, 0);
@@ -1270,6 +1280,11 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	else if (PCI_PID(pcr) == PID_5228)
 		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF,
 			RTS5228_SSC_DEPTH_2M);
+	else if (is_version(pcr, 0x5264, IC_VER_A))
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	else if (PCI_PID(pcr) == PID_5264)
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF,
+			RTS5264_SSC_DEPTH_2M);
 	else
 		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12);
 
@@ -1305,6 +1320,7 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	case PID_5260:
 	case PID_5261:
 	case PID_5228:
+	case PID_5264:
 		rtsx_pci_write_register(pcr, PM_CLK_FORCE_CTL, 1, 1);
 		break;
 	default:
@@ -1404,6 +1420,10 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
 	case 0x5228:
 		rts5228_init_params(pcr);
 		break;
+
+	case 0x5264:
+		rts5264_init_params(pcr);
+		break;
 	}
 
 	pcr_dbg(pcr, "PID: 0x%04x, IC version: 0x%02x\n",
@@ -1544,7 +1564,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 	pcr->pci = pcidev;
 	dev_set_drvdata(&pcidev->dev, handle);
 
-	if (CHK_PCI_PID(pcr, 0x525A))
+	if ((CHK_PCI_PID(pcr, 0x525A)) || (CHK_PCI_PID(pcr, 0x5264)))
 		bar = 1;
 	len = pci_resource_len(pcidev, bar);
 	base = pci_resource_start(pcidev, bar);
diff --git a/drivers/misc/cardreader/rtsx_pcr.h b/drivers/misc/cardreader/rtsx_pcr.h
index 37d1f316ae17c..9215d66de00cc 100644
--- a/drivers/misc/cardreader/rtsx_pcr.h
+++ b/drivers/misc/cardreader/rtsx_pcr.h
@@ -74,6 +74,7 @@ void rtl8411b_init_params(struct rtsx_pcr *pcr);
 void rts5260_init_params(struct rtsx_pcr *pcr);
 void rts5261_init_params(struct rtsx_pcr *pcr);
 void rts5228_init_params(struct rtsx_pcr *pcr);
+void rts5264_init_params(struct rtsx_pcr *pcr);
 
 static inline u8 map_sd_drive(int idx)
 {
-- 
GitLab


From 117cc0efb02374fb84bd546e2e706637db167bd6 Mon Sep 17 00:00:00 2001
From: Ricky Wu <ricky_wu@realtek.com>
Date: Fri, 8 Dec 2023 11:21:45 +0800
Subject: [PATCH 1456/4076] mmc: rtsx: add rts5264 to support sd express card

rts5264 can support sd express card, so add the id in sd express card init
to do rts5264 register setting when the sd express card insert

Signed-off-by: Ricky Wu <ricky_wu@realtek.com>
Link: https://lore.kernel.org/r/20231208032145.2143580-4-ricky_wu@realtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/mmc/host/rtsx_pci_sdmmc.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 87d78432a1e03..7dfe7c4e00770 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -7,6 +7,7 @@
  *   Wei WANG <wei_wang@realsil.com.cn>
  */
 
+#include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/highmem.h>
@@ -947,7 +948,7 @@ static int sd_power_on(struct realtek_pci_sdmmc *host, unsigned char power_mode)
 	/* send at least 74 clocks */
 	rtsx_pci_write_register(pcr, SD_BUS_STAT, SD_CLK_TOGGLE_EN, SD_CLK_TOGGLE_EN);
 
-	if (PCI_PID(pcr) == PID_5261) {
+	if ((PCI_PID(pcr) == PID_5261) || (PCI_PID(pcr) == PID_5264)) {
 		/*
 		 * If test mode is set switch to SD Express mandatorily,
 		 * this is only for factory testing.
@@ -1364,6 +1365,14 @@ static int sdmmc_init_sd_express(struct mmc_host *mmc, struct mmc_ios *ios)
 	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
 	struct rtsx_pcr *pcr = host->pcr;
 
+	if (PCI_PID(pcr) == PID_5264) {
+		pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL2,
+				PCI_EXP_LNKCTL2_TLS, PCI_EXP_LNKCTL2_TLS_2_5GT);
+		pci_write_config_byte(pcr->pci, 0x80e, 0x02);
+		pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL2,
+				PCI_EXP_LNKCTL2_TLS, PCI_EXP_LNKCTL2_TLS_5_0GT);
+	}
+
 	/* Set relink_time for changing to PCIe card */
 	relink_time = 0x8FFF;
 
@@ -1379,6 +1388,12 @@ static int sdmmc_init_sd_express(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (pcr->ops->disable_auto_blink)
 		pcr->ops->disable_auto_blink(pcr);
 
+	if (PCI_PID(pcr) == PID_5264) {
+		rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG2,
+			RTS5264_CHIP_RST_N_SEL, RTS5264_CHIP_RST_N_SEL);
+		rtsx_pci_write_register(pcr, GPIO_CTL, 0x02, 0x00);
+	}
+
 	/* For PCIe/NVMe mode can't enter delink issue */
 	pcr->hw_param.interrupt_en &= ~(SD_INT_EN);
 	rtsx_pci_writel(pcr, RTSX_BIER, pcr->hw_param.interrupt_en);
-- 
GitLab


From f200fff8d019f2754f91f5d715652e3e3fdf3604 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?=
 <nfraprado@collabora.com>
Date: Wed, 6 Dec 2023 15:17:24 -0800
Subject: [PATCH 1457/4076] spmi: mtk-pmif: Serialize PMIF status check and
 command submission
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Before writing the read or write command to the SPMI arbiter through the
PMIF interface, the current status of the channel is checked to ensure
it is idle. However, since the status only changes from idle when the
command is written, it is possible for two concurrent calls to determine
that the channel is idle and simultaneously send their commands. At this
point the PMIF interface hangs, with the status register no longer being
updated, and thus causing all subsequent operations to time out.

This was observed on the mt8195-cherry-tomato-r2 machine, particularly
after commit 46600ab142f8 ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for
drivers between 5.10 and 5.15") was applied, since then the two MT6315
devices present on the SPMI bus would probe assynchronously and
sometimes (during probe or at a later point) read the bus
simultaneously, breaking the PMIF interface and consequently slowing
down the whole system.

To fix the issue at its root cause, introduce locking around the channel
status check and the command write, so that both become an atomic
operation, preventing race conditions between two (or more) SPMI bus
read/write operations. A spinlock is used since this is a fast bus, as
indicated by the usage of the atomic variant of readl_poll, and
'.fast_io = true' being used in the mt6315 driver, so spinlocks are
already used for the regmap access.

Fixes: b45b3ccef8c0 ("spmi: mediatek: Add support for MT6873/8192")
Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Link: https://lore.kernel.org/r/20230724154739.493724-1-nfraprado@collabora.com
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Alexandre Mergnat <amergnat@baylibre.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-2-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/spmi-mtk-pmif.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c
index b3c991e1ea40d..54c35f5535cbe 100644
--- a/drivers/spmi/spmi-mtk-pmif.c
+++ b/drivers/spmi/spmi-mtk-pmif.c
@@ -50,6 +50,7 @@ struct pmif {
 	struct clk_bulk_data clks[PMIF_MAX_CLKS];
 	size_t nclks;
 	const struct pmif_data *data;
+	raw_spinlock_t lock;
 };
 
 static const char * const pmif_clock_names[] = {
@@ -314,6 +315,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	struct ch_reg *inf_reg;
 	int ret;
 	u32 data, cmd;
+	unsigned long flags;
 
 	/* Check for argument validation. */
 	if (sid & ~0xf) {
@@ -334,6 +336,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	else
 		return -EINVAL;
 
+	raw_spin_lock_irqsave(&arb->lock, flags);
 	/* Wait for Software Interface FSM state to be IDLE. */
 	inf_reg = &arb->chan;
 	ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
@@ -343,6 +346,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 		/* set channel ready if the data has transferred */
 		if (pmif_is_fsm_vldclr(arb))
 			pmif_writel(arb, 1, inf_reg->ch_rdy);
+		raw_spin_unlock_irqrestore(&arb->lock, flags);
 		dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
 		return ret;
 	}
@@ -350,6 +354,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	/* Send the command. */
 	cmd = (opc << 30) | (sid << 24) | ((len - 1) << 16) | addr;
 	pmif_writel(arb, cmd, inf_reg->ch_send);
+	raw_spin_unlock_irqrestore(&arb->lock, flags);
 
 	/*
 	 * Wait for Software Interface FSM state to be WFVLDCLR,
@@ -376,7 +381,8 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	struct pmif *arb = spmi_controller_get_drvdata(ctrl);
 	struct ch_reg *inf_reg;
 	int ret;
-	u32 data, cmd;
+	u32 data, wdata, cmd;
+	unsigned long flags;
 
 	if (len > 4) {
 		dev_err(&ctrl->dev, "pmif supports 1..4 bytes per trans, but:%zu requested", len);
@@ -394,6 +400,10 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	else
 		return -EINVAL;
 
+	/* Set the write data. */
+	memcpy(&wdata, buf, len);
+
+	raw_spin_lock_irqsave(&arb->lock, flags);
 	/* Wait for Software Interface FSM state to be IDLE. */
 	inf_reg = &arb->chan;
 	ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
@@ -403,17 +413,17 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 		/* set channel ready if the data has transferred */
 		if (pmif_is_fsm_vldclr(arb))
 			pmif_writel(arb, 1, inf_reg->ch_rdy);
+		raw_spin_unlock_irqrestore(&arb->lock, flags);
 		dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
 		return ret;
 	}
 
-	/* Set the write data. */
-	memcpy(&data, buf, len);
-	pmif_writel(arb, data, inf_reg->wdata);
+	pmif_writel(arb, wdata, inf_reg->wdata);
 
 	/* Send the command. */
 	cmd = (opc << 30) | BIT(29) | (sid << 24) | ((len - 1) << 16) | addr;
 	pmif_writel(arb, cmd, inf_reg->ch_send);
+	raw_spin_unlock_irqrestore(&arb->lock, flags);
 
 	return 0;
 }
@@ -488,6 +498,8 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 	arb->chan.ch_send = PMIF_SWINF_0_ACC + chan_offset;
 	arb->chan.ch_rdy = PMIF_SWINF_0_VLD_CLR + chan_offset;
 
+	raw_spin_lock_init(&arb->lock);
+
 	platform_set_drvdata(pdev, ctrl);
 
 	err = spmi_controller_add(ctrl);
-- 
GitLab


From e821d50ab5b956ed0effa49faaf29912fd4106d9 Mon Sep 17 00:00:00 2001
From: Yu-Che Cheng <giver@chromium.org>
Date: Wed, 6 Dec 2023 15:17:25 -0800
Subject: [PATCH 1458/4076] spmi: mediatek: Fix UAF on device remove

The pmif driver data that contains the clocks is allocated along with
spmi_controller.
On device remove, spmi_controller will be freed first, and then devres
, including the clocks, will be cleanup.
This leads to UAF because putting the clocks will access the clocks in
the pmif driver data, which is already freed along with spmi_controller.

This can be reproduced by enabling DEBUG_TEST_DRIVER_REMOVE and
building the kernel with KASAN.

Fix the UAF issue by using unmanaged clk_bulk_get() and putting the
clocks before freeing spmi_controller.

Reported-by: Fei Shao <fshao@chromium.org>
Signed-off-by: Yu-Che Cheng <giver@chromium.org>
Link: https://lore.kernel.org/r/20230717173934.1.If004a6e055a189c7f2d0724fa814422c26789839@changeid
Tested-by: Fei Shao <fshao@chromium.org>
Reviewed-by: Fei Shao <fshao@chromium.org>
Reviewed-by: Chen-Yu Tsai <wenst@chromium.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-3-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/spmi-mtk-pmif.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c
index 54c35f5535cbe..1261f381cae6c 100644
--- a/drivers/spmi/spmi-mtk-pmif.c
+++ b/drivers/spmi/spmi-mtk-pmif.c
@@ -475,7 +475,7 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 	for (i = 0; i < arb->nclks; i++)
 		arb->clks[i].id = pmif_clock_names[i];
 
-	err = devm_clk_bulk_get(&pdev->dev, arb->nclks, arb->clks);
+	err = clk_bulk_get(&pdev->dev, arb->nclks, arb->clks);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to get clocks: %d\n", err);
 		goto err_put_ctrl;
@@ -484,7 +484,7 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 	err = clk_bulk_prepare_enable(arb->nclks, arb->clks);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to enable clocks: %d\n", err);
-		goto err_put_ctrl;
+		goto err_put_clks;
 	}
 
 	ctrl->cmd = pmif_arb_cmd;
@@ -510,6 +510,8 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 
 err_domain_remove:
 	clk_bulk_disable_unprepare(arb->nclks, arb->clks);
+err_put_clks:
+	clk_bulk_put(arb->nclks, arb->clks);
 err_put_ctrl:
 	spmi_controller_put(ctrl);
 	return err;
@@ -521,6 +523,7 @@ static void mtk_spmi_remove(struct platform_device *pdev)
 	struct pmif *arb = spmi_controller_get_drvdata(ctrl);
 
 	clk_bulk_disable_unprepare(arb->nclks, arb->clks);
+	clk_bulk_put(arb->nclks, arb->clks);
 	spmi_controller_remove(ctrl);
 	spmi_controller_put(ctrl);
 }
-- 
GitLab


From b6e53731e07db7e8d35b789fd83565fe75540180 Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Wed, 6 Dec 2023 15:17:26 -0800
Subject: [PATCH 1459/4076] spmi: Introduce device-managed functions

Utilize the managed resource (devres) framework and add the following
devm_* helpers for the SPMI driver:

- devm_spmi_controller_alloc()
- devm_spmi_controller_add()

[sboyd@kernel.org: Rename to spmi-devres for module niceness, slap on
GPL module license]

Signed-off-by: Fei Shao <fshao@chromium.org>
Link: https://lore.kernel.org/r/20230824104101.4083400-2-fshao@chromium.org
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-4-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/Makefile      |  2 +-
 drivers/spmi/spmi-devres.c | 64 ++++++++++++++++++++++++++++++++++++++
 include/linux/spmi.h       |  3 ++
 3 files changed, 68 insertions(+), 1 deletion(-)
 create mode 100644 drivers/spmi/spmi-devres.c

diff --git a/drivers/spmi/Makefile b/drivers/spmi/Makefile
index 9d974424c8c18..7f152167bb05b 100644
--- a/drivers/spmi/Makefile
+++ b/drivers/spmi/Makefile
@@ -2,7 +2,7 @@
 #
 # Makefile for kernel SPMI framework.
 #
-obj-$(CONFIG_SPMI)	+= spmi.o
+obj-$(CONFIG_SPMI)	+= spmi.o spmi-devres.o
 
 obj-$(CONFIG_SPMI_HISI3670)	+= hisi-spmi-controller.o
 obj-$(CONFIG_SPMI_MSM_PMIC_ARB)	+= spmi-pmic-arb.o
diff --git a/drivers/spmi/spmi-devres.c b/drivers/spmi/spmi-devres.c
new file mode 100644
index 0000000000000..7683e6fdb18f5
--- /dev/null
+++ b/drivers/spmi/spmi-devres.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023 Google LLC.
+ */
+
+#include <linux/device.h>
+#include <linux/spmi.h>
+
+static void devm_spmi_controller_release(struct device *parent, void *res)
+{
+	spmi_controller_put(*(struct spmi_controller **)res);
+}
+
+struct spmi_controller *devm_spmi_controller_alloc(struct device *parent, size_t size)
+{
+	struct spmi_controller **ptr, *ctrl;
+
+	ptr = devres_alloc(devm_spmi_controller_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	ctrl = spmi_controller_alloc(parent, size);
+	if (!ctrl) {
+		devres_free(ptr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	*ptr = ctrl;
+	devres_add(parent, ptr);
+
+	return ctrl;
+}
+EXPORT_SYMBOL_GPL(devm_spmi_controller_alloc);
+
+static void devm_spmi_controller_remove(struct device *parent, void *res)
+{
+	spmi_controller_remove(*(struct spmi_controller **)res);
+}
+
+int devm_spmi_controller_add(struct device *parent, struct spmi_controller *ctrl)
+{
+	struct spmi_controller **ptr;
+	int ret;
+
+	ptr = devres_alloc(devm_spmi_controller_remove, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = spmi_controller_add(ctrl);
+	if (ret) {
+		devres_free(ptr);
+		return ret;
+	}
+
+	*ptr = ctrl;
+	devres_add(parent, ptr);
+
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(devm_spmi_controller_add);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SPMI devres helpers");
diff --git a/include/linux/spmi.h b/include/linux/spmi.h
index 2a4ce4144f9f1..28e8c8bd39441 100644
--- a/include/linux/spmi.h
+++ b/include/linux/spmi.h
@@ -120,6 +120,9 @@ static inline void spmi_controller_put(struct spmi_controller *ctrl)
 int spmi_controller_add(struct spmi_controller *ctrl);
 void spmi_controller_remove(struct spmi_controller *ctrl);
 
+struct spmi_controller *devm_spmi_controller_alloc(struct device *parent, size_t size);
+int devm_spmi_controller_add(struct device *parent, struct spmi_controller *ctrl);
+
 /**
  * struct spmi_driver - SPMI slave device driver
  * @driver:	SPMI device drivers should initialize name and owner field of
-- 
GitLab


From ffdfbafdc4f46a92e6bebaa61048b9f56301e2fa Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Wed, 6 Dec 2023 15:17:27 -0800
Subject: [PATCH 1460/4076] spmi: Use devm_spmi_controller_alloc()

Convert to the device-managed version of spmi_controller_alloc() and
simplify the excess error handling code.

Signed-off-by: Fei Shao <fshao@chromium.org>
Link: https://lore.kernel.org/r/20230824104101.4083400-3-fshao@chromium.org
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-5-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/hisi-spmi-controller.c | 22 +++-----
 drivers/spmi/spmi-mtk-pmif.c        | 26 +++------
 drivers/spmi/spmi-pmic-arb.c        | 87 ++++++++++-------------------
 3 files changed, 46 insertions(+), 89 deletions(-)

diff --git a/drivers/spmi/hisi-spmi-controller.c b/drivers/spmi/hisi-spmi-controller.c
index 9cbd473487cb0..a5525902656a6 100644
--- a/drivers/spmi/hisi-spmi-controller.c
+++ b/drivers/spmi/hisi-spmi-controller.c
@@ -267,10 +267,10 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	struct resource *iores;
 	int ret;
 
-	ctrl = spmi_controller_alloc(&pdev->dev, sizeof(*spmi_controller));
-	if (!ctrl) {
+	ctrl = devm_spmi_controller_alloc(&pdev->dev, sizeof(*spmi_controller));
+	if (IS_ERR(ctrl)) {
 		dev_err(&pdev->dev, "can not allocate spmi_controller data\n");
-		return -ENOMEM;
+		return PTR_ERR(ctrl);
 	}
 	spmi_controller = spmi_controller_get_drvdata(ctrl);
 	spmi_controller->controller = ctrl;
@@ -278,24 +278,21 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!iores) {
 		dev_err(&pdev->dev, "can not get resource!\n");
-		ret = -EINVAL;
-		goto err_put_controller;
+		return -EINVAL;
 	}
 
 	spmi_controller->base = devm_ioremap(&pdev->dev, iores->start,
 					     resource_size(iores));
 	if (!spmi_controller->base) {
 		dev_err(&pdev->dev, "can not remap base addr!\n");
-		ret = -EADDRNOTAVAIL;
-		goto err_put_controller;
+		return -EADDRNOTAVAIL;
 	}
 
 	ret = of_property_read_u32(pdev->dev.of_node, "hisilicon,spmi-channel",
 				   &spmi_controller->channel);
 	if (ret) {
 		dev_err(&pdev->dev, "can not get channel\n");
-		ret = -ENODEV;
-		goto err_put_controller;
+		return -ENODEV;
 	}
 
 	platform_set_drvdata(pdev, spmi_controller);
@@ -314,14 +311,10 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	ret = spmi_controller_add(ctrl);
 	if (ret) {
 		dev_err(&pdev->dev, "spmi_controller_add failed with error %d!\n", ret);
-		goto err_put_controller;
+		return ret;
 	}
 
 	return 0;
-
-err_put_controller:
-	spmi_controller_put(ctrl);
-	return ret;
 }
 
 static void spmi_del_controller(struct platform_device *pdev)
@@ -329,7 +322,6 @@ static void spmi_del_controller(struct platform_device *pdev)
 	struct spmi_controller *ctrl = platform_get_drvdata(pdev);
 
 	spmi_controller_remove(ctrl);
-	spmi_controller_put(ctrl);
 }
 
 static const struct of_device_id spmi_controller_match_table[] = {
diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c
index 1261f381cae6c..6ebc6901490a7 100644
--- a/drivers/spmi/spmi-mtk-pmif.c
+++ b/drivers/spmi/spmi-mtk-pmif.c
@@ -447,29 +447,24 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 	int err, i;
 	u32 chan_offset;
 
-	ctrl = spmi_controller_alloc(&pdev->dev, sizeof(*arb));
-	if (!ctrl)
-		return -ENOMEM;
+	ctrl = devm_spmi_controller_alloc(&pdev->dev, sizeof(*arb));
+	if (IS_ERR(ctrl))
+		return PTR_ERR(ctrl);
 
 	arb = spmi_controller_get_drvdata(ctrl);
 	arb->data = device_get_match_data(&pdev->dev);
 	if (!arb->data) {
-		err = -EINVAL;
 		dev_err(&pdev->dev, "Cannot get drv_data\n");
-		goto err_put_ctrl;
+		return -EINVAL;
 	}
 
 	arb->base = devm_platform_ioremap_resource_byname(pdev, "pmif");
-	if (IS_ERR(arb->base)) {
-		err = PTR_ERR(arb->base);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(arb->base))
+		return PTR_ERR(arb->base);
 
 	arb->spmimst_base = devm_platform_ioremap_resource_byname(pdev, "spmimst");
-	if (IS_ERR(arb->spmimst_base)) {
-		err = PTR_ERR(arb->spmimst_base);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(arb->spmimst_base))
+		return PTR_ERR(arb->spmimst_base);
 
 	arb->nclks = ARRAY_SIZE(pmif_clock_names);
 	for (i = 0; i < arb->nclks; i++)
@@ -478,7 +473,7 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 	err = clk_bulk_get(&pdev->dev, arb->nclks, arb->clks);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to get clocks: %d\n", err);
-		goto err_put_ctrl;
+		return err;
 	}
 
 	err = clk_bulk_prepare_enable(arb->nclks, arb->clks);
@@ -512,8 +507,6 @@ err_domain_remove:
 	clk_bulk_disable_unprepare(arb->nclks, arb->clks);
 err_put_clks:
 	clk_bulk_put(arb->nclks, arb->clks);
-err_put_ctrl:
-	spmi_controller_put(ctrl);
 	return err;
 }
 
@@ -525,7 +518,6 @@ static void mtk_spmi_remove(struct platform_device *pdev)
 	clk_bulk_disable_unprepare(arb->nclks, arb->clks);
 	clk_bulk_put(arb->nclks, arb->clks);
 	spmi_controller_remove(ctrl);
-	spmi_controller_put(ctrl);
 }
 
 static const struct of_device_id mtk_spmi_match_table[] = {
diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c
index dcb675d980d47..9ed1180fe31f1 100644
--- a/drivers/spmi/spmi-pmic-arb.c
+++ b/drivers/spmi/spmi-pmic-arb.c
@@ -1443,9 +1443,9 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 	u32 channel, ee, hw_ver;
 	int err;
 
-	ctrl = spmi_controller_alloc(&pdev->dev, sizeof(*pmic_arb));
-	if (!ctrl)
-		return -ENOMEM;
+	ctrl = devm_spmi_controller_alloc(&pdev->dev, sizeof(*pmic_arb));
+	if (IS_ERR(ctrl))
+		return PTR_ERR(ctrl);
 
 	pmic_arb = spmi_controller_get_drvdata(ctrl);
 	pmic_arb->spmic = ctrl;
@@ -1462,20 +1462,16 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 	 */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "core");
 	core = devm_ioremap(&ctrl->dev, res->start, resource_size(res));
-	if (IS_ERR(core)) {
-		err = PTR_ERR(core);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(core))
+		return PTR_ERR(core);
 
 	pmic_arb->core_size = resource_size(res);
 
 	pmic_arb->ppid_to_apid = devm_kcalloc(&ctrl->dev, PMIC_ARB_MAX_PPID,
 					      sizeof(*pmic_arb->ppid_to_apid),
 					      GFP_KERNEL);
-	if (!pmic_arb->ppid_to_apid) {
-		err = -ENOMEM;
-		goto err_put_ctrl;
-	}
+	if (!pmic_arb->ppid_to_apid)
+		return -ENOMEM;
 
 	hw_ver = readl_relaxed(core + PMIC_ARB_VERSION);
 
@@ -1499,19 +1495,15 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 						   "obsrvr");
 		pmic_arb->rd_base = devm_ioremap(&ctrl->dev, res->start,
 						 resource_size(res));
-		if (IS_ERR(pmic_arb->rd_base)) {
-			err = PTR_ERR(pmic_arb->rd_base);
-			goto err_put_ctrl;
-		}
+		if (IS_ERR(pmic_arb->rd_base))
+			return PTR_ERR(pmic_arb->rd_base);
 
 		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 						   "chnls");
 		pmic_arb->wr_base = devm_ioremap(&ctrl->dev, res->start,
 						 resource_size(res));
-		if (IS_ERR(pmic_arb->wr_base)) {
-			err = PTR_ERR(pmic_arb->wr_base);
-			goto err_put_ctrl;
-		}
+		if (IS_ERR(pmic_arb->wr_base))
+			return PTR_ERR(pmic_arb->wr_base);
 	}
 
 	pmic_arb->max_periphs = PMIC_ARB_MAX_PERIPHS;
@@ -1522,10 +1514,9 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 		of_property_read_u32(pdev->dev.of_node, "qcom,bus-id",
 					&pmic_arb->bus_instance);
 		if (pmic_arb->bus_instance > 1) {
-			err = -EINVAL;
 			dev_err(&pdev->dev, "invalid bus instance (%u) specified\n",
 				pmic_arb->bus_instance);
-			goto err_put_ctrl;
+			return -EINVAL;
 		}
 
 		if (pmic_arb->bus_instance == 0) {
@@ -1543,10 +1534,9 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 		}
 
 		if (pmic_arb->base_apid + pmic_arb->apid_count > pmic_arb->max_periphs) {
-			err = -EINVAL;
 			dev_err(&pdev->dev, "Unsupported APID count %d detected\n",
 				pmic_arb->base_apid + pmic_arb->apid_count);
-			goto err_put_ctrl;
+			return -EINVAL;
 		}
 	} else if (hw_ver >= PMIC_ARB_VERSION_V5_MIN) {
 		pmic_arb->base_apid = 0;
@@ -1554,55 +1544,45 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 					PMIC_ARB_FEATURES_PERIPH_MASK;
 
 		if (pmic_arb->apid_count > pmic_arb->max_periphs) {
-			err = -EINVAL;
 			dev_err(&pdev->dev, "Unsupported APID count %d detected\n",
 				pmic_arb->apid_count);
-			goto err_put_ctrl;
+			return -EINVAL;
 		}
 	}
 
 	pmic_arb->apid_data = devm_kcalloc(&ctrl->dev, pmic_arb->max_periphs,
 					   sizeof(*pmic_arb->apid_data),
 					   GFP_KERNEL);
-	if (!pmic_arb->apid_data) {
-		err = -ENOMEM;
-		goto err_put_ctrl;
-	}
+	if (!pmic_arb->apid_data)
+		return -ENOMEM;
 
 	dev_info(&ctrl->dev, "PMIC arbiter version %s (0x%x)\n",
 		 pmic_arb->ver_ops->ver_str, hw_ver);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "intr");
 	pmic_arb->intr = devm_ioremap_resource(&ctrl->dev, res);
-	if (IS_ERR(pmic_arb->intr)) {
-		err = PTR_ERR(pmic_arb->intr);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(pmic_arb->intr))
+		return PTR_ERR(pmic_arb->intr);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cnfg");
 	pmic_arb->cnfg = devm_ioremap_resource(&ctrl->dev, res);
-	if (IS_ERR(pmic_arb->cnfg)) {
-		err = PTR_ERR(pmic_arb->cnfg);
-		goto err_put_ctrl;
-	}
+	if (IS_ERR(pmic_arb->cnfg))
+		return PTR_ERR(pmic_arb->cnfg);
 
 	pmic_arb->irq = platform_get_irq_byname(pdev, "periph_irq");
-	if (pmic_arb->irq < 0) {
-		err = pmic_arb->irq;
-		goto err_put_ctrl;
-	}
+	if (pmic_arb->irq < 0)
+		return pmic_arb->irq;
 
 	err = of_property_read_u32(pdev->dev.of_node, "qcom,channel", &channel);
 	if (err) {
 		dev_err(&pdev->dev, "channel unspecified.\n");
-		goto err_put_ctrl;
+		return err;
 	}
 
 	if (channel > 5) {
 		dev_err(&pdev->dev, "invalid channel (%u) specified.\n",
 			channel);
-		err = -EINVAL;
-		goto err_put_ctrl;
+		return -EINVAL;
 	}
 
 	pmic_arb->channel = channel;
@@ -1610,22 +1590,19 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 	err = of_property_read_u32(pdev->dev.of_node, "qcom,ee", &ee);
 	if (err) {
 		dev_err(&pdev->dev, "EE unspecified.\n");
-		goto err_put_ctrl;
+		return err;
 	}
 
 	if (ee > 5) {
 		dev_err(&pdev->dev, "invalid EE (%u) specified\n", ee);
-		err = -EINVAL;
-		goto err_put_ctrl;
+		return -EINVAL;
 	}
 
 	pmic_arb->ee = ee;
 	mapping_table = devm_kcalloc(&ctrl->dev, pmic_arb->max_periphs,
 					sizeof(*mapping_table), GFP_KERNEL);
-	if (!mapping_table) {
-		err = -ENOMEM;
-		goto err_put_ctrl;
-	}
+	if (!mapping_table)
+		return -ENOMEM;
 
 	pmic_arb->mapping_table = mapping_table;
 	/* Initialize max_apid/min_apid to the opposite bounds, during
@@ -1645,7 +1622,7 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 		if (err) {
 			dev_err(&pdev->dev, "could not read APID->PPID mapping table, rc= %d\n",
 				err);
-			goto err_put_ctrl;
+			return err;
 		}
 	}
 
@@ -1654,8 +1631,7 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 					 &pmic_arb_irq_domain_ops, pmic_arb);
 	if (!pmic_arb->domain) {
 		dev_err(&pdev->dev, "unable to create irq_domain\n");
-		err = -ENOMEM;
-		goto err_put_ctrl;
+		return -ENOMEM;
 	}
 
 	irq_set_chained_handler_and_data(pmic_arb->irq, pmic_arb_chained_irq,
@@ -1669,8 +1645,6 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev)
 err_domain_remove:
 	irq_set_chained_handler_and_data(pmic_arb->irq, NULL, NULL);
 	irq_domain_remove(pmic_arb->domain);
-err_put_ctrl:
-	spmi_controller_put(ctrl);
 	return err;
 }
 
@@ -1681,7 +1655,6 @@ static void spmi_pmic_arb_remove(struct platform_device *pdev)
 	spmi_controller_remove(ctrl);
 	irq_set_chained_handler_and_data(pmic_arb->irq, NULL, NULL);
 	irq_domain_remove(pmic_arb->domain);
-	spmi_controller_put(ctrl);
 }
 
 static const struct of_device_id spmi_pmic_arb_match_table[] = {
-- 
GitLab


From f3e67fc406909fca9429b4283f243e855fab5c59 Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Wed, 6 Dec 2023 15:17:28 -0800
Subject: [PATCH 1461/4076] spmi: mtk-pmif: Reorder driver remove sequence

This driver enables clocks and then adds SPMI controller in probing, so
we expect the reversed sequence in removal.
Fix the order in the remove callback.

Signed-off-by: Fei Shao <fshao@chromium.org>
Link: https://lore.kernel.org/r/20230824104101.4083400-4-fshao@chromium.org
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-6-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/spmi-mtk-pmif.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c
index 6ebc6901490a7..cc660da6a0370 100644
--- a/drivers/spmi/spmi-mtk-pmif.c
+++ b/drivers/spmi/spmi-mtk-pmif.c
@@ -515,9 +515,9 @@ static void mtk_spmi_remove(struct platform_device *pdev)
 	struct spmi_controller *ctrl = platform_get_drvdata(pdev);
 	struct pmif *arb = spmi_controller_get_drvdata(ctrl);
 
+	spmi_controller_remove(ctrl);
 	clk_bulk_disable_unprepare(arb->nclks, arb->clks);
 	clk_bulk_put(arb->nclks, arb->clks);
-	spmi_controller_remove(ctrl);
 }
 
 static const struct of_device_id mtk_spmi_match_table[] = {
-- 
GitLab


From 490d88ef548d463c85bd75ef5300b25c92d71e5a Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Wed, 6 Dec 2023 15:17:29 -0800
Subject: [PATCH 1462/4076] spmi: hisi-spmi-controller: Use
 devm_spmi_controller_add()

Convert to the device-managed version of spmi_controller_add() and
delete the unnecessary driver remove callback.

Signed-off-by: Fei Shao <fshao@chromium.org>
Link: https://lore.kernel.org/r/20230824104101.4083400-5-fshao@chromium.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-7-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/hisi-spmi-controller.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/spmi/hisi-spmi-controller.c b/drivers/spmi/hisi-spmi-controller.c
index a5525902656a6..674a350cc6769 100644
--- a/drivers/spmi/hisi-spmi-controller.c
+++ b/drivers/spmi/hisi-spmi-controller.c
@@ -308,7 +308,7 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	ctrl->read_cmd = spmi_read_cmd;
 	ctrl->write_cmd = spmi_write_cmd;
 
-	ret = spmi_controller_add(ctrl);
+	ret = devm_spmi_controller_add(&pdev->dev, ctrl);
 	if (ret) {
 		dev_err(&pdev->dev, "spmi_controller_add failed with error %d!\n", ret);
 		return ret;
@@ -317,13 +317,6 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void spmi_del_controller(struct platform_device *pdev)
-{
-	struct spmi_controller *ctrl = platform_get_drvdata(pdev);
-
-	spmi_controller_remove(ctrl);
-}
-
 static const struct of_device_id spmi_controller_match_table[] = {
 	{
 		.compatible = "hisilicon,kirin970-spmi-controller",
@@ -334,7 +327,6 @@ MODULE_DEVICE_TABLE(of, spmi_controller_match_table);
 
 static struct platform_driver spmi_controller_driver = {
 	.probe		= spmi_controller_probe,
-	.remove_new	= spmi_del_controller,
 	.driver		= {
 		.name	= "hisi_spmi_controller",
 		.of_match_table = spmi_controller_match_table,
-- 
GitLab


From 3ae3cf418a01203c33113e19cc1029ac434c96b5 Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Wed, 6 Dec 2023 15:17:30 -0800
Subject: [PATCH 1463/4076] spmi: Return meaningful errors in
 spmi_controller_alloc()

spmi_controller_alloc() currently returns NULL to all types of errors,
which can be improved.

Use appropriate error code in returns and pass the errors from used
functions where possible.

Signed-off-by: Fei Shao <fshao@chromium.org>
Link: https://lore.kernel.org/r/20230824104101.4083400-6-fshao@chromium.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-8-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/spmi-devres.c | 4 ++--
 drivers/spmi/spmi.c        | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/spmi/spmi-devres.c b/drivers/spmi/spmi-devres.c
index 7683e6fdb18f5..62c4b3f24d065 100644
--- a/drivers/spmi/spmi-devres.c
+++ b/drivers/spmi/spmi-devres.c
@@ -20,9 +20,9 @@ struct spmi_controller *devm_spmi_controller_alloc(struct device *parent, size_t
 		return ERR_PTR(-ENOMEM);
 
 	ctrl = spmi_controller_alloc(parent, size);
-	if (!ctrl) {
+	if (IS_ERR(ctrl)) {
 		devres_free(ptr);
-		return ERR_PTR(-ENOMEM);
+		return ctrl;
 	}
 
 	*ptr = ctrl;
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index 93cd4a34debc7..3a60fd2e09e1f 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -448,11 +448,11 @@ struct spmi_controller *spmi_controller_alloc(struct device *parent,
 	int id;
 
 	if (WARN_ON(!parent))
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	ctrl = kzalloc(sizeof(*ctrl) + size, GFP_KERNEL);
 	if (!ctrl)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	device_initialize(&ctrl->dev);
 	ctrl->dev.type = &spmi_ctrl_type;
@@ -466,7 +466,7 @@ struct spmi_controller *spmi_controller_alloc(struct device *parent,
 		dev_err(parent,
 			"unable to allocate SPMI controller identifier.\n");
 		spmi_controller_put(ctrl);
-		return NULL;
+		return ERR_PTR(id);
 	}
 
 	ctrl->nr = id;
-- 
GitLab


From c49739235c426b05539589de2ffde2bbf71ae468 Mon Sep 17 00:00:00 2001
From: Sen Chu <sen.chu@mediatek.com>
Date: Wed, 6 Dec 2023 15:17:31 -0800
Subject: [PATCH 1464/4076] spmi: mediatek: add device id check

Add device id check for spmi write API.

Signed-off-by: Sen Chu <sen.chu@mediatek.com>
Link: https://lore.kernel.org/r/20230518040729.8789-1-sen.chu@mediatek.com
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-9-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/spmi-mtk-pmif.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c
index cc660da6a0370..5079442f8ea16 100644
--- a/drivers/spmi/spmi-mtk-pmif.c
+++ b/drivers/spmi/spmi-mtk-pmif.c
@@ -384,6 +384,12 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	u32 data, wdata, cmd;
 	unsigned long flags;
 
+	/* Check for argument validation. */
+	if (unlikely(sid & ~0xf)) {
+		dev_err(&ctrl->dev, "exceed the max slv id\n");
+		return -EINVAL;
+	}
+
 	if (len > 4) {
 		dev_err(&ctrl->dev, "pmif supports 1..4 bytes per trans, but:%zu requested", len);
 
-- 
GitLab


From bda910d81843228c18d1ac51af6b149f2e8261c7 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 9 Dec 2023 13:36:14 +0100
Subject: [PATCH 1465/4076] VMCI: Remove handle_arr_calc_size()

Use struct_size() instead of handle_arr_calc_size().
This is much more conventional.

While at it, use size_add() when computing the needed size in
vmci_handle_arr_append_entry(). This prevents from (unlikely) overflow
when computing the new size to reallocate.

Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/84e7f2d8e7c4c2eab68f958307d56546978f76e3.1702125347.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/vmw_vmci/vmci_handle_array.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.c b/drivers/misc/vmw_vmci/vmci_handle_array.c
index de7fee7ead1bc..681b3500125ab 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.c
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.c
@@ -8,12 +8,6 @@
 #include <linux/slab.h>
 #include "vmci_handle_array.h"
 
-static size_t handle_arr_calc_size(u32 capacity)
-{
-	return VMCI_HANDLE_ARRAY_HEADER_SIZE +
-	    capacity * sizeof(struct vmci_handle);
-}
-
 struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity)
 {
 	struct vmci_handle_arr *array;
@@ -25,7 +19,7 @@ struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity)
 		capacity = min((u32)VMCI_HANDLE_ARRAY_DEFAULT_CAPACITY,
 			       max_capacity);
 
-	array = kmalloc(handle_arr_calc_size(capacity), GFP_ATOMIC);
+	array = kmalloc(struct_size(array, entries, capacity), GFP_ATOMIC);
 	if (!array)
 		return NULL;
 
@@ -51,8 +45,8 @@ int vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
 		struct vmci_handle_arr *new_array;
 		u32 capacity_bump = min(array->max_capacity - array->capacity,
 					array->capacity);
-		size_t new_size = handle_arr_calc_size(array->capacity +
-						       capacity_bump);
+		size_t new_size = struct_size(array, entries,
+					      size_add(array->capacity, capacity_bump));
 
 		if (array->size >= array->max_capacity)
 			return VMCI_ERROR_NO_MEM;
-- 
GitLab


From de264ddea73d445d3982a6defae334d6b5ebc05e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 9 Dec 2023 13:36:15 +0100
Subject: [PATCH 1466/4076] VMCI: Remove VMCI_HANDLE_ARRAY_HEADER_SIZE and
 VMCI_HANDLE_ARRAY_MAX_CAPACITY

Remove VMCI_HANDLE_ARRAY_HEADER_SIZE and VMCI_HANDLE_ARRAY_MAX_CAPACITY
that are unused.

Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/00547fe74efe329b266eb8074c41f286758a3c64.1702125347.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/vmw_vmci/vmci_handle_array.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.h b/drivers/misc/vmw_vmci/vmci_handle_array.h
index 96193f85be5bb..e386c5732727d 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.h
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.h
@@ -20,14 +20,8 @@ struct vmci_handle_arr {
 	struct vmci_handle entries[];
 };
 
-#define VMCI_HANDLE_ARRAY_HEADER_SIZE				\
-	offsetof(struct vmci_handle_arr, entries)
 /* Select a default capacity that results in a 64 byte sized array */
 #define VMCI_HANDLE_ARRAY_DEFAULT_CAPACITY			6
-/* Make sure that the max array size can be expressed by a u32 */
-#define VMCI_HANDLE_ARRAY_MAX_CAPACITY				\
-	((U32_MAX - VMCI_HANDLE_ARRAY_HEADER_SIZE - 1) /	\
-	sizeof(struct vmci_handle))
 
 struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity);
 void vmci_handle_arr_destroy(struct vmci_handle_arr *array);
-- 
GitLab


From 8d6608e4f89a0a21caadcf32fb5ed700e2f5682d Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Thu, 14 Dec 2023 15:53:47 +0100
Subject: [PATCH 1467/4076] firmware: xilinx: Remove clock_setrate and
 clock_getrate api

As per the current code base, PM_CLOCK_SETRATE and PM_CLOCK_GETRATE
APIs are not supported for the runtime operations. In the case of
ZynqMP returning an error from TF-A when there is any request to
access these APIs and for Versal also it is returning an error like
NO_ACCESS from the firmware. So, just removing the unused code to
avoid the confusion around these APIs.

Also, there is no issue with the backward compatibility as these APIs
were never used since implemented. Hence no need to bump up the
version of the feature check API as well.

Signed-off-by: Ronak Jain <ronak.jain@amd.com>
Signed-off-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/6ccbffbafd1f0f48f6574d5a3bf2db6a5603fdb0.1702565618.git.michal.simek@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 38 ----------------------------
 include/linux/firmware/xlnx-zynqmp.h | 14 ----------
 2 files changed, 52 deletions(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index caa0952bfc422..2ae9da268215a 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -657,44 +657,6 @@ int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getdivider);
 
-/**
- * zynqmp_pm_clock_setrate() - Set the clock rate for given id
- * @clock_id:	ID of the clock
- * @rate:	rate value in hz
- *
- * This function is used by master to set rate for any clock.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
-{
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETRATE, NULL, 3, clock_id, lower_32_bits(rate),
-				   upper_32_bits(rate));
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setrate);
-
-/**
- * zynqmp_pm_clock_getrate() - Get the clock rate for given id
- * @clock_id:	ID of the clock
- * @rate:	rate value in hz
- *
- * This function is used by master to get rate
- * for any clock.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
-{
-	u32 ret_payload[PAYLOAD_ARG_CNT];
-	int ret;
-
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETRATE, ret_payload, 1, clock_id);
-	*rate = ((u64)ret_payload[2] << 32) | ret_payload[1];
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getrate);
-
 /**
  * zynqmp_pm_clock_setparent() - Set the clock parent for given id
  * @clock_id:	ID of the clock
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 6b48294f3c923..c6a7fb1f980b2 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -160,8 +160,6 @@ enum pm_api_id {
 	PM_CLOCK_GETSTATE = 38,
 	PM_CLOCK_SETDIVIDER = 39,
 	PM_CLOCK_GETDIVIDER = 40,
-	PM_CLOCK_SETRATE = 41,
-	PM_CLOCK_GETRATE = 42,
 	PM_CLOCK_SETPARENT = 43,
 	PM_CLOCK_GETPARENT = 44,
 	PM_FPGA_READ = 46,
@@ -533,8 +531,6 @@ int zynqmp_pm_clock_disable(u32 clock_id);
 int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state);
 int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider);
 int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider);
-int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate);
-int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate);
 int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id);
 int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id);
 int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode);
@@ -639,16 +635,6 @@ static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
-{
-	return -ENODEV;
-}
-
-static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id)
 {
 	return -ENODEV;
-- 
GitLab


From b9ae996210163e89a2a9aece7c582fb43694485a Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Thu, 14 Dec 2023 15:53:48 +0100
Subject: [PATCH 1468/4076] firmware: xilinx: Remove
 zynqmp_pm_pinctrl_get_function()

There is no user for this interface that's why remove it.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/e52a415a004e28a43e6d08e9e22d9e8fef3737df.1702565618.git.michal.simek@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 24 ------------------------
 include/linux/firmware/xlnx-zynqmp.h |  7 -------
 2 files changed, 31 deletions(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 2ae9da268215a..a55dfd9bae6bd 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -1060,30 +1060,6 @@ int zynqmp_pm_pinctrl_release(const u32 pin)
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_release);
 
-/**
- * zynqmp_pm_pinctrl_get_function - Read function id set for the given pin
- * @pin: Pin number
- * @id: Buffer to store function ID
- *
- * This function provides the function currently set for the given pin.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
-{
-	u32 ret_payload[PAYLOAD_ARG_CNT];
-	int ret;
-
-	if (!id)
-		return -EINVAL;
-
-	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_GET_FUNCTION, ret_payload, 1, pin);
-	*id = ret_payload[1];
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_get_function);
-
 /**
  * zynqmp_pm_pinctrl_set_function - Set requested function for the pin
  * @pin: Pin number
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index c6a7fb1f980b2..1478f691cc10e 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -149,7 +149,6 @@ enum pm_api_id {
 	PM_SECURE_SHA = 26,
 	PM_PINCTRL_REQUEST = 28,
 	PM_PINCTRL_RELEASE = 29,
-	PM_PINCTRL_GET_FUNCTION = 30,
 	PM_PINCTRL_SET_FUNCTION = 31,
 	PM_PINCTRL_CONFIG_PARAM_GET = 32,
 	PM_PINCTRL_CONFIG_PARAM_SET = 33,
@@ -567,7 +566,6 @@ int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype);
 int zynqmp_pm_set_boot_health_status(u32 value);
 int zynqmp_pm_pinctrl_request(const u32 pin);
 int zynqmp_pm_pinctrl_release(const u32 pin);
-int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id);
 int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id);
 int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param,
 				 u32 *value);
@@ -804,11 +802,6 @@ static inline int zynqmp_pm_pinctrl_release(const u32 pin)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id)
 {
 	return -ENODEV;
-- 
GitLab


From f1fd91a0924b6bff91ca1287461fb8e3b3b61d92 Mon Sep 17 00:00:00 2001
From: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Date: Fri, 15 Dec 2023 14:16:14 +0100
Subject: [PATCH 1469/4076] usb: gadget: webcam: Make g_webcam loadable again

commit 588b9e85609b ("usb: gadget: uvc: add v4l2 enumeration api calls")
has rendered the precomposed (aka legacy) webcam gadget unloadable.

uvc_alloc() since then has depended on certain config groups being
available in configfs tree related to the UVC function. However, legacy
gadgets do not create anything in configfs, so uvc_alloc() must fail
with -ENOENT no matter what.

This patch mimics the required configfs hierarchy to satisfy the code which
inspects formats and frames found in uvcg_streaming_header.

This has been tested with guvcview on the host side, using vivid as a
source of video stream on the device side and using the userspace program
found at https://gitlab.freedesktop.org/camera/uvc-gadget.git.

Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Fixes: 588b9e85609b ("usb: gadget: uvc: add v4l2 enumeration api calls")
Link: https://lore.kernel.org/r/20231215131614.29132-1-andrzej.p@collabora.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uvc.c |  45 ++--
 drivers/usb/gadget/function/u_uvc.h |   6 +
 drivers/usb/gadget/legacy/webcam.c  | 333 +++++++++++++++++++++-------
 3 files changed, 284 insertions(+), 100 deletions(-)

diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index 77999ed53d33e..da5f28e471b04 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -959,7 +959,8 @@ static void uvc_free(struct usb_function *f)
 	struct uvc_device *uvc = to_uvc(f);
 	struct f_uvc_opts *opts = container_of(f->fi, struct f_uvc_opts,
 					       func_inst);
-	config_item_put(&uvc->header->item);
+	if (!opts->header)
+		config_item_put(&uvc->header->item);
 	--opts->refcnt;
 	kfree(uvc);
 }
@@ -1051,25 +1052,29 @@ static struct usb_function *uvc_alloc(struct usb_function_instance *fi)
 	uvc->desc.hs_streaming = opts->hs_streaming;
 	uvc->desc.ss_streaming = opts->ss_streaming;
 
-	streaming = config_group_find_item(&opts->func_inst.group, "streaming");
-	if (!streaming)
-		goto err_config;
-
-	header = config_group_find_item(to_config_group(streaming), "header");
-	config_item_put(streaming);
-	if (!header)
-		goto err_config;
-
-	h = config_group_find_item(to_config_group(header), "h");
-	config_item_put(header);
-	if (!h)
-		goto err_config;
-
-	uvc->header = to_uvcg_streaming_header(h);
-	if (!uvc->header->linked) {
-		mutex_unlock(&opts->lock);
-		kfree(uvc);
-		return ERR_PTR(-EBUSY);
+	if (opts->header) {
+		uvc->header = opts->header;
+	} else {
+		streaming = config_group_find_item(&opts->func_inst.group, "streaming");
+		if (!streaming)
+			goto err_config;
+
+		header = config_group_find_item(to_config_group(streaming), "header");
+		config_item_put(streaming);
+		if (!header)
+			goto err_config;
+
+		h = config_group_find_item(to_config_group(header), "h");
+		config_item_put(header);
+		if (!h)
+			goto err_config;
+
+		uvc->header = to_uvcg_streaming_header(h);
+		if (!uvc->header->linked) {
+			mutex_unlock(&opts->lock);
+			kfree(uvc);
+			return ERR_PTR(-EBUSY);
+		}
 	}
 
 	uvc->desc.extension_units = &opts->extension_units;
diff --git a/drivers/usb/gadget/function/u_uvc.h b/drivers/usb/gadget/function/u_uvc.h
index 1ce58f61253c9..3ac392cbb7794 100644
--- a/drivers/usb/gadget/function/u_uvc.h
+++ b/drivers/usb/gadget/function/u_uvc.h
@@ -98,6 +98,12 @@ struct f_uvc_opts {
 	 */
 	struct mutex			lock;
 	int				refcnt;
+
+	/*
+	 * Only for legacy gadget. Shall be NULL for configfs-composed gadgets,
+	 * which is guaranteed by alloc_inst implementation of f_uvc doing kzalloc.
+	 */
+	struct uvcg_streaming_header	*header;
 };
 
 #endif /* U_UVC_H */
diff --git a/drivers/usb/gadget/legacy/webcam.c b/drivers/usb/gadget/legacy/webcam.c
index c06dd1af7a0c5..c395438d39780 100644
--- a/drivers/usb/gadget/legacy/webcam.c
+++ b/drivers/usb/gadget/legacy/webcam.c
@@ -12,6 +12,7 @@
 #include <linux/usb/video.h>
 
 #include "u_uvc.h"
+#include "uvc_configfs.h"
 
 USB_GADGET_COMPOSITE_OPTIONS();
 
@@ -84,8 +85,6 @@ static struct usb_device_descriptor webcam_device_descriptor = {
 	.bNumConfigurations	= 0, /* dynamic */
 };
 
-DECLARE_UVC_HEADER_DESCRIPTOR(1);
-
 static const struct UVC_HEADER_DESCRIPTOR(1) uvc_control_header = {
 	.bLength		= UVC_DT_HEADER_SIZE(1),
 	.bDescriptorType	= USB_DT_CS_INTERFACE,
@@ -158,43 +157,112 @@ static const struct UVC_INPUT_HEADER_DESCRIPTOR(1, 2) uvc_input_header = {
 	.bmaControls[1][0]	= 4,
 };
 
-static const struct uvc_format_uncompressed uvc_format_yuv = {
-	.bLength		= UVC_DT_FORMAT_UNCOMPRESSED_SIZE,
-	.bDescriptorType	= USB_DT_CS_INTERFACE,
-	.bDescriptorSubType	= UVC_VS_FORMAT_UNCOMPRESSED,
-	.bFormatIndex		= 1,
-	.bNumFrameDescriptors	= 2,
-	.guidFormat		=
-		{ 'Y',  'U',  'Y',  '2', 0x00, 0x00, 0x10, 0x00,
-		 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71},
-	.bBitsPerPixel		= 16,
-	.bDefaultFrameIndex	= 1,
-	.bAspectRatioX		= 0,
-	.bAspectRatioY		= 0,
-	.bmInterlaceFlags	= 0,
-	.bCopyProtect		= 0,
+static const struct uvcg_color_matching uvcg_color_matching = {
+	.desc = {
+		.bLength		= UVC_DT_COLOR_MATCHING_SIZE,
+		.bDescriptorType	= USB_DT_CS_INTERFACE,
+		.bDescriptorSubType	= UVC_VS_COLORFORMAT,
+		.bColorPrimaries	= 1,
+		.bTransferCharacteristics	= 1,
+		.bMatrixCoefficients	= 4,
+	},
+};
+
+static struct uvcg_uncompressed uvcg_format_yuv = {
+	.fmt = {
+		.type			= UVCG_UNCOMPRESSED,
+		/* add to .frames and fill .num_frames at runtime */
+		.color_matching		= (struct uvcg_color_matching *)&uvcg_color_matching,
+	},
+	.desc = {
+		.bLength		= UVC_DT_FORMAT_UNCOMPRESSED_SIZE,
+		.bDescriptorType	= USB_DT_CS_INTERFACE,
+		.bDescriptorSubType	= UVC_VS_FORMAT_UNCOMPRESSED,
+		.bFormatIndex		= 1,
+		.bNumFrameDescriptors	= 2,
+		.guidFormat		= {
+			'Y',  'U',  'Y',  '2', 0x00, 0x00, 0x10, 0x00,
+			 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71
+		},
+		.bBitsPerPixel		= 16,
+		.bDefaultFrameIndex	= 1,
+		.bAspectRatioX		= 0,
+		.bAspectRatioY		= 0,
+		.bmInterlaceFlags	= 0,
+		.bCopyProtect		= 0,
+	},
+};
+
+static struct uvcg_format_ptr uvcg_format_ptr_yuv = {
+	.fmt = &uvcg_format_yuv.fmt,
 };
 
 DECLARE_UVC_FRAME_UNCOMPRESSED(1);
 DECLARE_UVC_FRAME_UNCOMPRESSED(3);
 
+#define UVCG_WIDTH_360P			640
+#define UVCG_HEIGHT_360P		360
+#define UVCG_MIN_BITRATE_360P		18432000
+#define UVCG_MAX_BITRATE_360P		55296000
+#define UVCG_MAX_VIDEO_FB_SZ_360P	460800
+#define UVCG_FRM_INTERV_0_360P		666666
+#define UVCG_FRM_INTERV_1_360P		1000000
+#define UVCG_FRM_INTERV_2_360P		5000000
+#define UVCG_DEFAULT_FRM_INTERV_360P	UVCG_FRM_INTERV_0_360P
+
 static const struct UVC_FRAME_UNCOMPRESSED(3) uvc_frame_yuv_360p = {
 	.bLength		= UVC_DT_FRAME_UNCOMPRESSED_SIZE(3),
 	.bDescriptorType	= USB_DT_CS_INTERFACE,
 	.bDescriptorSubType	= UVC_VS_FRAME_UNCOMPRESSED,
 	.bFrameIndex		= 1,
 	.bmCapabilities		= 0,
-	.wWidth			= cpu_to_le16(640),
-	.wHeight		= cpu_to_le16(360),
-	.dwMinBitRate		= cpu_to_le32(18432000),
-	.dwMaxBitRate		= cpu_to_le32(55296000),
-	.dwMaxVideoFrameBufferSize	= cpu_to_le32(460800),
-	.dwDefaultFrameInterval	= cpu_to_le32(666666),
+	.wWidth			= cpu_to_le16(UVCG_WIDTH_360P),
+	.wHeight		= cpu_to_le16(UVCG_HEIGHT_360P),
+	.dwMinBitRate		= cpu_to_le32(UVCG_MIN_BITRATE_360P),
+	.dwMaxBitRate		= cpu_to_le32(UVCG_MAX_BITRATE_360P),
+	.dwMaxVideoFrameBufferSize	= cpu_to_le32(UVCG_MAX_VIDEO_FB_SZ_360P),
+	.dwDefaultFrameInterval	= cpu_to_le32(UVCG_DEFAULT_FRM_INTERV_360P),
 	.bFrameIntervalType	= 3,
-	.dwFrameInterval[0]	= cpu_to_le32(666666),
-	.dwFrameInterval[1]	= cpu_to_le32(1000000),
-	.dwFrameInterval[2]	= cpu_to_le32(5000000),
+	.dwFrameInterval[0]	= cpu_to_le32(UVCG_FRM_INTERV_0_360P),
+	.dwFrameInterval[1]	= cpu_to_le32(UVCG_FRM_INTERV_1_360P),
+	.dwFrameInterval[2]	= cpu_to_le32(UVCG_FRM_INTERV_2_360P),
+};
+
+static u32 uvcg_frame_yuv_360p_dw_frame_interval[] = {
+	[0] = UVCG_FRM_INTERV_0_360P,
+	[1] = UVCG_FRM_INTERV_1_360P,
+	[2] = UVCG_FRM_INTERV_2_360P,
+};
+
+static const struct uvcg_frame uvcg_frame_yuv_360p = {
+	.fmt_type		= UVCG_UNCOMPRESSED,
+	.frame = {
+		.b_length			= UVC_DT_FRAME_UNCOMPRESSED_SIZE(3),
+		.b_descriptor_type		= USB_DT_CS_INTERFACE,
+		.b_descriptor_subtype		= UVC_VS_FRAME_UNCOMPRESSED,
+		.b_frame_index			= 1,
+		.bm_capabilities		= 0,
+		.w_width			= UVCG_WIDTH_360P,
+		.w_height			= UVCG_HEIGHT_360P,
+		.dw_min_bit_rate		= UVCG_MIN_BITRATE_360P,
+		.dw_max_bit_rate		= UVCG_MAX_BITRATE_360P,
+		.dw_max_video_frame_buffer_size	= UVCG_MAX_VIDEO_FB_SZ_360P,
+		.dw_default_frame_interval	= UVCG_DEFAULT_FRM_INTERV_360P,
+		.b_frame_interval_type		= 3,
+	},
+	.dw_frame_interval	= uvcg_frame_yuv_360p_dw_frame_interval,
+};
+
+static struct uvcg_frame_ptr uvcg_frame_ptr_yuv_360p = {
+	.frm = (struct uvcg_frame *)&uvcg_frame_yuv_360p,
 };
+#define UVCG_WIDTH_720P			1280
+#define UVCG_HEIGHT_720P		720
+#define UVCG_MIN_BITRATE_720P		29491200
+#define UVCG_MAX_BITRATE_720P		29491200
+#define UVCG_MAX_VIDEO_FB_SZ_720P	1843200
+#define UVCG_FRM_INTERV_0_720P		5000000
+#define UVCG_DEFAULT_FRM_INTERV_720P	UVCG_FRM_INTERV_0_720P
 
 static const struct UVC_FRAME_UNCOMPRESSED(1) uvc_frame_yuv_720p = {
 	.bLength		= UVC_DT_FRAME_UNCOMPRESSED_SIZE(1),
@@ -202,28 +270,66 @@ static const struct UVC_FRAME_UNCOMPRESSED(1) uvc_frame_yuv_720p = {
 	.bDescriptorSubType	= UVC_VS_FRAME_UNCOMPRESSED,
 	.bFrameIndex		= 2,
 	.bmCapabilities		= 0,
-	.wWidth			= cpu_to_le16(1280),
-	.wHeight		= cpu_to_le16(720),
-	.dwMinBitRate		= cpu_to_le32(29491200),
-	.dwMaxBitRate		= cpu_to_le32(29491200),
-	.dwMaxVideoFrameBufferSize	= cpu_to_le32(1843200),
-	.dwDefaultFrameInterval	= cpu_to_le32(5000000),
+	.wWidth			= cpu_to_le16(UVCG_WIDTH_720P),
+	.wHeight		= cpu_to_le16(UVCG_HEIGHT_720P),
+	.dwMinBitRate		= cpu_to_le32(UVCG_MIN_BITRATE_720P),
+	.dwMaxBitRate		= cpu_to_le32(UVCG_MAX_BITRATE_720P),
+	.dwMaxVideoFrameBufferSize	= cpu_to_le32(UVCG_MAX_VIDEO_FB_SZ_720P),
+	.dwDefaultFrameInterval	= cpu_to_le32(UVCG_DEFAULT_FRM_INTERV_720P),
 	.bFrameIntervalType	= 1,
-	.dwFrameInterval[0]	= cpu_to_le32(5000000),
+	.dwFrameInterval[0]	= cpu_to_le32(UVCG_FRM_INTERV_0_720P),
 };
 
-static const struct uvc_format_mjpeg uvc_format_mjpg = {
-	.bLength		= UVC_DT_FORMAT_MJPEG_SIZE,
-	.bDescriptorType	= USB_DT_CS_INTERFACE,
-	.bDescriptorSubType	= UVC_VS_FORMAT_MJPEG,
-	.bFormatIndex		= 2,
-	.bNumFrameDescriptors	= 2,
-	.bmFlags		= 0,
-	.bDefaultFrameIndex	= 1,
-	.bAspectRatioX		= 0,
-	.bAspectRatioY		= 0,
-	.bmInterlaceFlags	= 0,
-	.bCopyProtect		= 0,
+static u32 uvcg_frame_yuv_720p_dw_frame_interval[] = {
+	[0] = UVCG_FRM_INTERV_0_720P,
+};
+
+static const struct uvcg_frame uvcg_frame_yuv_720p = {
+	.fmt_type		= UVCG_UNCOMPRESSED,
+	.frame = {
+		.b_length			= UVC_DT_FRAME_UNCOMPRESSED_SIZE(1),
+		.b_descriptor_type		= USB_DT_CS_INTERFACE,
+		.b_descriptor_subtype		= UVC_VS_FRAME_UNCOMPRESSED,
+		.b_frame_index			= 2,
+		.bm_capabilities		= 0,
+		.w_width			= UVCG_WIDTH_720P,
+		.w_height			= UVCG_HEIGHT_720P,
+		.dw_min_bit_rate		= UVCG_MIN_BITRATE_720P,
+		.dw_max_bit_rate		= UVCG_MAX_BITRATE_720P,
+		.dw_max_video_frame_buffer_size	= UVCG_MAX_VIDEO_FB_SZ_720P,
+		.dw_default_frame_interval	= UVCG_DEFAULT_FRM_INTERV_720P,
+		.b_frame_interval_type		= 1,
+	},
+	.dw_frame_interval	= uvcg_frame_yuv_720p_dw_frame_interval,
+};
+
+static struct uvcg_frame_ptr uvcg_frame_ptr_yuv_720p = {
+	.frm = (struct uvcg_frame *)&uvcg_frame_yuv_720p,
+};
+
+static struct uvcg_mjpeg uvcg_format_mjpeg = {
+	.fmt = {
+		.type			= UVCG_MJPEG,
+		/* add to .frames and fill .num_frames at runtime */
+		.color_matching		= (struct uvcg_color_matching *)&uvcg_color_matching,
+	},
+	.desc = {
+		.bLength		= UVC_DT_FORMAT_MJPEG_SIZE,
+		.bDescriptorType	= USB_DT_CS_INTERFACE,
+		.bDescriptorSubType	= UVC_VS_FORMAT_MJPEG,
+		.bFormatIndex		= 2,
+		.bNumFrameDescriptors	= 2,
+		.bmFlags		= 0,
+		.bDefaultFrameIndex	= 1,
+		.bAspectRatioX		= 0,
+		.bAspectRatioY		= 0,
+		.bmInterlaceFlags	= 0,
+		.bCopyProtect		= 0,
+	},
+};
+
+static struct uvcg_format_ptr uvcg_format_ptr_mjpeg = {
+	.fmt = &uvcg_format_mjpeg.fmt,
 };
 
 DECLARE_UVC_FRAME_MJPEG(1);
@@ -235,16 +341,45 @@ static const struct UVC_FRAME_MJPEG(3) uvc_frame_mjpg_360p = {
 	.bDescriptorSubType	= UVC_VS_FRAME_MJPEG,
 	.bFrameIndex		= 1,
 	.bmCapabilities		= 0,
-	.wWidth			= cpu_to_le16(640),
-	.wHeight		= cpu_to_le16(360),
-	.dwMinBitRate		= cpu_to_le32(18432000),
-	.dwMaxBitRate		= cpu_to_le32(55296000),
-	.dwMaxVideoFrameBufferSize	= cpu_to_le32(460800),
-	.dwDefaultFrameInterval	= cpu_to_le32(666666),
+	.wWidth			= cpu_to_le16(UVCG_WIDTH_360P),
+	.wHeight		= cpu_to_le16(UVCG_HEIGHT_360P),
+	.dwMinBitRate		= cpu_to_le32(UVCG_MIN_BITRATE_360P),
+	.dwMaxBitRate		= cpu_to_le32(UVCG_MAX_BITRATE_360P),
+	.dwMaxVideoFrameBufferSize	= cpu_to_le32(UVCG_MAX_VIDEO_FB_SZ_360P),
+	.dwDefaultFrameInterval	= cpu_to_le32(UVCG_DEFAULT_FRM_INTERV_360P),
 	.bFrameIntervalType	= 3,
-	.dwFrameInterval[0]	= cpu_to_le32(666666),
-	.dwFrameInterval[1]	= cpu_to_le32(1000000),
-	.dwFrameInterval[2]	= cpu_to_le32(5000000),
+	.dwFrameInterval[0]	= cpu_to_le32(UVCG_FRM_INTERV_0_360P),
+	.dwFrameInterval[1]	= cpu_to_le32(UVCG_FRM_INTERV_1_360P),
+	.dwFrameInterval[2]	= cpu_to_le32(UVCG_FRM_INTERV_2_360P),
+};
+
+static u32 uvcg_frame_mjpeg_360p_dw_frame_interval[] = {
+	[0] = UVCG_FRM_INTERV_0_360P,
+	[1] = UVCG_FRM_INTERV_1_360P,
+	[2] = UVCG_FRM_INTERV_2_360P,
+};
+
+static const struct uvcg_frame uvcg_frame_mjpeg_360p = {
+	.fmt_type		= UVCG_MJPEG,
+	.frame = {
+		.b_length			= UVC_DT_FRAME_MJPEG_SIZE(3),
+		.b_descriptor_type		= USB_DT_CS_INTERFACE,
+		.b_descriptor_subtype		= UVC_VS_FRAME_MJPEG,
+		.b_frame_index			= 1,
+		.bm_capabilities		= 0,
+		.w_width			= UVCG_WIDTH_360P,
+		.w_height			= UVCG_HEIGHT_360P,
+		.dw_min_bit_rate		= UVCG_MIN_BITRATE_360P,
+		.dw_max_bit_rate		= UVCG_MAX_BITRATE_360P,
+		.dw_max_video_frame_buffer_size	= UVCG_MAX_VIDEO_FB_SZ_360P,
+		.dw_default_frame_interval	= UVCG_DEFAULT_FRM_INTERV_360P,
+		.b_frame_interval_type		= 3,
+	},
+	.dw_frame_interval	= uvcg_frame_mjpeg_360p_dw_frame_interval,
+};
+
+static struct uvcg_frame_ptr uvcg_frame_ptr_mjpeg_360p = {
+	.frm = (struct uvcg_frame *)&uvcg_frame_mjpeg_360p,
 };
 
 static const struct UVC_FRAME_MJPEG(1) uvc_frame_mjpg_720p = {
@@ -253,23 +388,44 @@ static const struct UVC_FRAME_MJPEG(1) uvc_frame_mjpg_720p = {
 	.bDescriptorSubType	= UVC_VS_FRAME_MJPEG,
 	.bFrameIndex		= 2,
 	.bmCapabilities		= 0,
-	.wWidth			= cpu_to_le16(1280),
-	.wHeight		= cpu_to_le16(720),
-	.dwMinBitRate		= cpu_to_le32(29491200),
-	.dwMaxBitRate		= cpu_to_le32(29491200),
-	.dwMaxVideoFrameBufferSize	= cpu_to_le32(1843200),
-	.dwDefaultFrameInterval	= cpu_to_le32(5000000),
+	.wWidth			= cpu_to_le16(UVCG_WIDTH_720P),
+	.wHeight		= cpu_to_le16(UVCG_HEIGHT_720P),
+	.dwMinBitRate		= cpu_to_le32(UVCG_MIN_BITRATE_720P),
+	.dwMaxBitRate		= cpu_to_le32(UVCG_MAX_BITRATE_720P),
+	.dwMaxVideoFrameBufferSize	= cpu_to_le32(UVCG_MAX_VIDEO_FB_SZ_720P),
+	.dwDefaultFrameInterval	= cpu_to_le32(UVCG_DEFAULT_FRM_INTERV_720P),
 	.bFrameIntervalType	= 1,
-	.dwFrameInterval[0]	= cpu_to_le32(5000000),
+	.dwFrameInterval[0]	= cpu_to_le32(UVCG_FRM_INTERV_0_720P),
 };
 
-static const struct uvc_color_matching_descriptor uvc_color_matching = {
-	.bLength		= UVC_DT_COLOR_MATCHING_SIZE,
-	.bDescriptorType	= USB_DT_CS_INTERFACE,
-	.bDescriptorSubType	= UVC_VS_COLORFORMAT,
-	.bColorPrimaries	= 1,
-	.bTransferCharacteristics	= 1,
-	.bMatrixCoefficients	= 4,
+static u32 uvcg_frame_mjpeg_720p_dw_frame_interval[] = {
+	[0] = UVCG_FRM_INTERV_0_720P,
+};
+
+static const struct uvcg_frame uvcg_frame_mjpeg_720p = {
+	.fmt_type		= UVCG_MJPEG,
+	.frame = {
+		.b_length			= UVC_DT_FRAME_MJPEG_SIZE(1),
+		.b_descriptor_type		= USB_DT_CS_INTERFACE,
+		.b_descriptor_subtype		= UVC_VS_FRAME_MJPEG,
+		.b_frame_index			= 2,
+		.bm_capabilities		= 0,
+		.w_width			= UVCG_WIDTH_720P,
+		.w_height			= UVCG_HEIGHT_720P,
+		.dw_min_bit_rate		= UVCG_MIN_BITRATE_720P,
+		.dw_max_bit_rate		= UVCG_MAX_BITRATE_720P,
+		.dw_max_video_frame_buffer_size	= UVCG_MAX_VIDEO_FB_SZ_720P,
+		.dw_default_frame_interval	= UVCG_DEFAULT_FRM_INTERV_720P,
+		.b_frame_interval_type		= 1,
+	},
+	.dw_frame_interval	= uvcg_frame_mjpeg_720p_dw_frame_interval,
+};
+
+static struct uvcg_frame_ptr uvcg_frame_ptr_mjpeg_720p = {
+	.frm = (struct uvcg_frame *)&uvcg_frame_mjpeg_720p,
+};
+
+static struct uvcg_streaming_header uvcg_streaming_header = {
 };
 
 static const struct uvc_descriptor_header * const uvc_fs_control_cls[] = {
@@ -290,40 +446,40 @@ static const struct uvc_descriptor_header * const uvc_ss_control_cls[] = {
 
 static const struct uvc_descriptor_header * const uvc_fs_streaming_cls[] = {
 	(const struct uvc_descriptor_header *) &uvc_input_header,
-	(const struct uvc_descriptor_header *) &uvc_format_yuv,
+	(const struct uvc_descriptor_header *) &uvcg_format_yuv.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
-	(const struct uvc_descriptor_header *) &uvc_format_mjpg,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
+	(const struct uvc_descriptor_header *) &uvcg_format_mjpeg.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
 	NULL,
 };
 
 static const struct uvc_descriptor_header * const uvc_hs_streaming_cls[] = {
 	(const struct uvc_descriptor_header *) &uvc_input_header,
-	(const struct uvc_descriptor_header *) &uvc_format_yuv,
+	(const struct uvc_descriptor_header *) &uvcg_format_yuv.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
-	(const struct uvc_descriptor_header *) &uvc_format_mjpg,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
+	(const struct uvc_descriptor_header *) &uvcg_format_mjpeg.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
 	NULL,
 };
 
 static const struct uvc_descriptor_header * const uvc_ss_streaming_cls[] = {
 	(const struct uvc_descriptor_header *) &uvc_input_header,
-	(const struct uvc_descriptor_header *) &uvc_format_yuv,
+	(const struct uvc_descriptor_header *) &uvcg_format_yuv.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
-	(const struct uvc_descriptor_header *) &uvc_format_mjpg,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
+	(const struct uvc_descriptor_header *) &uvcg_format_mjpeg.desc,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
 	(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
-	(const struct uvc_descriptor_header *) &uvc_color_matching,
+	(const struct uvc_descriptor_header *) &uvcg_color_matching.desc,
 	NULL,
 };
 
@@ -387,6 +543,23 @@ webcam_bind(struct usb_composite_dev *cdev)
 	uvc_opts->hs_streaming = uvc_hs_streaming_cls;
 	uvc_opts->ss_streaming = uvc_ss_streaming_cls;
 
+	INIT_LIST_HEAD(&uvcg_format_yuv.fmt.frames);
+	list_add_tail(&uvcg_frame_ptr_yuv_360p.entry, &uvcg_format_yuv.fmt.frames);
+	list_add_tail(&uvcg_frame_ptr_yuv_720p.entry, &uvcg_format_yuv.fmt.frames);
+	uvcg_format_yuv.fmt.num_frames = 2;
+
+	INIT_LIST_HEAD(&uvcg_format_mjpeg.fmt.frames);
+	list_add_tail(&uvcg_frame_ptr_mjpeg_360p.entry, &uvcg_format_mjpeg.fmt.frames);
+	list_add_tail(&uvcg_frame_ptr_mjpeg_720p.entry, &uvcg_format_mjpeg.fmt.frames);
+	uvcg_format_mjpeg.fmt.num_frames = 2;
+
+	INIT_LIST_HEAD(&uvcg_streaming_header.formats);
+	list_add_tail(&uvcg_format_ptr_yuv.entry, &uvcg_streaming_header.formats);
+	list_add_tail(&uvcg_format_ptr_mjpeg.entry, &uvcg_streaming_header.formats);
+	uvcg_streaming_header.num_fmt = 2;
+
+	uvc_opts->header = &uvcg_streaming_header;
+
 	/* Allocate string descriptor numbers ... note that string contents
 	 * can be overridden by the composite_dev glue.
 	 */
-- 
GitLab


From c084af69a8f425b8cb56479ff0ea11e48aba0c62 Mon Sep 17 00:00:00 2001
From: Himanshu Bhavani <himanshu.bhavani@siliconsignals.io>
Date: Fri, 15 Dec 2023 20:04:57 +0530
Subject: [PATCH 1470/4076] usb: dwc3: imx8mp: Fix smatch warning

dwc3_imx8mp_pm_resume() warn: 'dwc3_imx->suspend_clk'
from clk_prepare_enable() not released

Signed-off-by: Himanshu Bhavani <himanshu.bhavani@siliconsignals.io>

Link: https://lore.kernel.org/r/20231215143458.158810-1-himanshu.bhavani@siliconsignals.io
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-imx8mp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/dwc3-imx8mp.c b/drivers/usb/dwc3/dwc3-imx8mp.c
index a1e15f2fffdbf..8ee4480685031 100644
--- a/drivers/usb/dwc3/dwc3-imx8mp.c
+++ b/drivers/usb/dwc3/dwc3-imx8mp.c
@@ -363,8 +363,10 @@ static int __maybe_unused dwc3_imx8mp_pm_resume(struct device *dev)
 	}
 
 	ret = clk_prepare_enable(dwc3_imx->hsio_clk);
-	if (ret)
+	if (ret) {
+		clk_disable_unprepare(dwc3_imx->suspend_clk);
 		return ret;
+	}
 
 	ret = dwc3_imx8mp_resume(dwc3_imx, PMSG_RESUME);
 
-- 
GitLab


From 80602b6b5a23b210224a5b44d9e5b5c1dc193632 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 15 Dec 2023 14:57:07 +0200
Subject: [PATCH 1471/4076] xhci: Fix null pointer dereference during S4 resume
 when resetting ep0

During device enumeration usb core resets endpoint 0 if the max packet
size value differs from the one read from the device descriptor.

usb core will additionally reset endpoint 0 during S4 resume, before
re-enumerating the device, if the device has a reset-resume flag set.

In this case the xhci device representation vdev may be lost due to
xHC restore error and re-initialization during S4 resume.

Make sure slot_id and vdev are valid before trying to re-configure max
packet size during endpoint 0 reset.
max packet size will be re-configured later during re-enumeration.

This fixes commit e34900f46cd6 ("xhci: Reconfigure endpoint 0 max packet
size only during endpoint reset") which is currently in usb-next,
on its way to 6.8

Fixes: e34900f46cd6 ("xhci: Reconfigure endpoint 0 max packet size only during endpoint reset")
Tested-by: Wendy Wang <wendy.wang@intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231215125707.1732989-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 08fbabff23a05..7d5b94905b9c5 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3077,6 +3077,9 @@ done:
  * of an endpoint that isn't in the halted state this function will issue a
  * configure endpoint command with the Drop and Add bits set for the target
  * endpoint. Refer to the additional note in xhci spcification section 4.6.8.
+ *
+ * vdev may be lost due to xHC restore error and re-initialization during S3/S4
+ * resume. A new vdev will be allocated later by xhci_discover_or_reset_device()
  */
 
 static void xhci_endpoint_reset(struct usb_hcd *hcd,
@@ -3102,9 +3105,17 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 	 * mismatch. Reconfigure the xhci ep0 endpoint context here in that case
 	 */
 	if (usb_endpoint_xfer_control(&host_ep->desc) && ep_index == 0) {
+
 		udev = container_of(host_ep, struct usb_device, ep0);
-		if (udev->speed == USB_SPEED_FULL)
-			xhci_check_ep0_maxpacket(xhci, xhci->devs[udev->slot_id]);
+		if (udev->speed != USB_SPEED_FULL || !udev->slot_id)
+			return;
+
+		vdev = xhci->devs[udev->slot_id];
+		if (!vdev || vdev->udev != udev)
+			return;
+
+		xhci_check_ep0_maxpacket(xhci, vdev);
+
 		/* Nothing else should be done here for ep0 during ep reset */
 		return;
 	}
@@ -3114,11 +3125,6 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 	udev = (struct usb_device *) host_ep->hcpriv;
 	vdev = xhci->devs[udev->slot_id];
 
-	/*
-	 * vdev may be lost due to xHC restore error and re-initialization
-	 * during S3/S4 resume. A new vdev will be allocated later by
-	 * xhci_discover_or_reset_device()
-	 */
 	if (!udev->slot_id || !vdev)
 		return;
 
-- 
GitLab


From 532888a59505da2a3fbb4abac6adad381cedb374 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 15 Dec 2023 18:45:41 +0100
Subject: [PATCH 1472/4076] driver core: Better advertise dev_err_probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Describing the usage of dev_err_probe() as being (only?) "deemed
acceptable" has a bad connotation. In fact dev_err_probe() fulfills
three tasks:

 - handling of EPROBE_DEFER (even more than degrading to dev_dbg())
 - symbolic output of the error code
 - return err for compact error code paths

Advertise these better and claim the usage to be "fine" to get rid of
the bad connotation.

Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231215174540.2438601-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 6736c1de3ba43..14d46af40f9a1 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -4944,13 +4944,14 @@ define_dev_printk_level(_dev_info, KERN_INFO);
  *
  * 	return dev_err_probe(dev, err, ...);
  *
- * Note that it is deemed acceptable to use this function for error
- * prints during probe even if the @err is known to never be -EPROBE_DEFER.
+ * Using this helper in your probe function is totally fine even if @err is
+ * known to never be -EPROBE_DEFER.
  * The benefit compared to a normal dev_err() is the standardized format
- * of the error code and the fact that the error code is returned.
+ * of the error code, it being emitted symbolically (i.e. you get "EAGAIN"
+ * instead of "-35") and the fact that the error code is returned which allows
+ * more compact error paths.
  *
  * Returns @err.
- *
  */
 int dev_err_probe(const struct device *dev, int err, const char *fmt, ...)
 {
-- 
GitLab


From 76cd718a9ffda837d4b4f1558c6e6ea08a9a7c59 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 15 Dec 2023 19:30:04 +0200
Subject: [PATCH 1473/4076] dt-bindings: connector: usb: add accessory mode
 description

Add description of the USB-C Accessory Modes supported on the particular
USB-C connector. This is required for devices like Qualcomm SM8150-HDK,
which have no other way to express accessory modes supported by the
hardware platform.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231215173005.313422-2-dmitry.baryshkov@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/connector/usb-connector.yaml | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml
index 28660b931d0c3..f5966b3a2d9ae 100644
--- a/Documentation/devicetree/bindings/connector/usb-connector.yaml
+++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml
@@ -171,6 +171,18 @@ properties:
       offer the power, Capability Mismatch is set. Required for power sink and
       power dual role.
 
+  accessory-mode-audio:
+    type: boolean
+    description: Whether the device supports Audio Adapter Accessory Mode. This
+      is only necessary if there are no other means to discover supported
+      alternative modes (e.g. through the UCSI firmware interface).
+
+  accessory-mode-debug:
+    type: boolean
+    description: Whether the device supports Debug Accessory Mode. This
+      is only necessary if there are no other means to discover supported
+      alternative modes (e.g. through the UCSI firmware interface).
+
   altmodes:
     type: object
     description: List of Alternative Modes supported by the schematics on the
-- 
GitLab


From e9158c7e55339737847cebbfa397c668713f1a15 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 15 Dec 2023 19:30:05 +0200
Subject: [PATCH 1474/4076] usb: typec: tcpm: Parse Accessory Mode information

Some of the boards supported by the TCPM drivers can support USB-C
Accessory Modes (Analog Audio, Debug). Parse information about supported
modes from the device tree.

Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231215173005.313422-3-dmitry.baryshkov@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 8372f98de757d..cf70f1cf2f618 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -6144,6 +6144,7 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 {
 	const char *opmode_str;
 	int ret;
+	int mode;
 	u32 mw, frs_current;
 
 	if (!fwnode)
@@ -6162,6 +6163,14 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 	if (ret < 0)
 		return ret;
 
+	mode = 0;
+
+	if (fwnode_property_read_bool(fwnode, "accessory-mode-audio"))
+		port->typec_caps.accessory[mode++] = TYPEC_ACCESSORY_AUDIO;
+
+	if (fwnode_property_read_bool(fwnode, "accessory-mode-debug"))
+		port->typec_caps.accessory[mode++] = TYPEC_ACCESSORY_DEBUG;
+
 	port->port_type = port->typec_caps.type;
 	port->pd_supported = !fwnode_property_read_bool(fwnode, "pd-disable");
 
-- 
GitLab


From 65fde134b0a4ffe838729f9ee11b459a2f6f2815 Mon Sep 17 00:00:00 2001
From: Cameron Williams <cang1@live.co.uk>
Date: Thu, 2 Nov 2023 21:07:05 +0000
Subject: [PATCH 1475/4076] parport: parport_serial: Add Brainboxes BAR details

Add BAR/enum entries for Brainboxes serial/parallel cards.

Cc:  <stable@vger.kernel.org>
Signed-off-by: Cameron Williams <cang1@live.co.uk>
Acked-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Link: https://lore.kernel.org/r/AS4PR02MB79035155C2D5C3333AE6FA52C4A6A@AS4PR02MB7903.eurprd02.prod.outlook.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/parport/parport_serial.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c
index 9f5d784cd95d5..11989368611a1 100644
--- a/drivers/parport/parport_serial.c
+++ b/drivers/parport/parport_serial.c
@@ -65,6 +65,10 @@ enum parport_pc_pci_cards {
 	sunix_5069a,
 	sunix_5079a,
 	sunix_5099a,
+	brainboxes_uc257,
+	brainboxes_is300,
+	brainboxes_uc414,
+	brainboxes_px263,
 };
 
 /* each element directly indexed from enum list, above */
@@ -158,6 +162,10 @@ static struct parport_pc_pci cards[] = {
 	/* sunix_5069a */		{ 1, { { 1, 2 }, } },
 	/* sunix_5079a */		{ 1, { { 1, 2 }, } },
 	/* sunix_5099a */		{ 1, { { 1, 2 }, } },
+	/* brainboxes_uc257 */	{ 1, { { 3, -1 }, } },
+	/* brainboxes_is300 */	{ 1, { { 3, -1 }, } },
+	/* brainboxes_uc414 */  { 1, { { 3, -1 }, } },
+	/* brainboxes_px263 */	{ 1, { { 3, -1 }, } },
 };
 
 static struct pci_device_id parport_serial_pci_tbl[] = {
-- 
GitLab


From 6aa1fc5a8085bbc01687aa708dcf2dbe637a5ee3 Mon Sep 17 00:00:00 2001
From: Cameron Williams <cang1@live.co.uk>
Date: Thu, 2 Nov 2023 21:07:06 +0000
Subject: [PATCH 1476/4076] parport: parport_serial: Add Brainboxes device IDs
 and geometry

Add device IDs for the Brainboxes UC-203, UC-257, UC-414, UC-475,
IS-300/IS-500 and PX-263/PX-295 and define the relevant "geometry"
for the cards.
This patch requires part 1 of this series.

Cc:  <stable@vger.kernel.org>
Signed-off-by: Cameron Williams <cang1@live.co.uk>
Acked-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Link: https://lore.kernel.org/r/AS4PR02MB7903A4094564BE28F1F926A6C4A6A@AS4PR02MB7903.eurprd02.prod.outlook.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/parport/parport_serial.c | 56 ++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c
index 11989368611a1..3644997a83425 100644
--- a/drivers/parport/parport_serial.c
+++ b/drivers/parport/parport_serial.c
@@ -285,6 +285,38 @@ static struct pci_device_id parport_serial_pci_tbl[] = {
 	{ PCI_VENDOR_ID_SUNIX, PCI_DEVICE_ID_SUNIX_1999, PCI_VENDOR_ID_SUNIX,
 	  0x0104, 0, 0, sunix_5099a },
 
+	/* Brainboxes UC-203 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0bc1,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0bc2,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+
+	/* Brainboxes UC-257 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0861,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0862,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0863,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+
+	/* Brainboxes UC-414 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0e61,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc414 },
+
+	/* Brainboxes UC-475 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0981,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0982,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 },
+
+	/* Brainboxes IS-300/IS-500 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0da0,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_is300 },
+
+	/* Brainboxes PX-263/PX-295 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x402c,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_px263 },
+
 	{ 0, } /* terminate list */
 };
 MODULE_DEVICE_TABLE(pci,parport_serial_pci_tbl);
@@ -550,6 +582,30 @@ static struct pciserial_board pci_parport_serial_boards[] = {
 		.base_baud      = 921600,
 		.uart_offset	= 0x8,
 	},
+	[brainboxes_uc257] = {
+		.flags		= FL_BASE2,
+		.num_ports	= 2,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+	},
+	[brainboxes_is300] = {
+		.flags		= FL_BASE2,
+		.num_ports	= 1,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+	},
+	[brainboxes_uc414] = {
+		.flags		= FL_BASE2,
+		.num_ports	= 4,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+	},
+	[brainboxes_px263] = {
+		.flags		= FL_BASE2,
+		.num_ports	= 4,
+		.base_baud	= 921600,
+		.uart_offset	= 8,
+	},
 };
 
 struct parport_serial_private {
-- 
GitLab


From 35259ff188e028b8fee8f1e973d0a7466df76d13 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 10 Nov 2023 15:43:15 -0600
Subject: [PATCH 1477/4076] PCI: Log device type during enumeration

Log the device type when enumeration a device.  Sample output changes:

  - pci 0000:00:00.0: [8086:1237] type 00 class 0x060000
  + pci 0000:00:00.0: [8086:1237] type 00 class 0x060000 conventional PCI endpoint

  - pci 0000:00:1c.0: [8086:a110] type 01 class 0x060400
  + pci 0000:00:1c.0: [8086:a110] type 01 class 0x060400 PCIe Root Port

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 42 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ed6b7f48736ad..6ee84dc939cab 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1817,6 +1817,43 @@ static void early_dump_pci_device(struct pci_dev *pdev)
 		       value, 256, false);
 }
 
+static const char *pci_type_str(struct pci_dev *dev)
+{
+	static const char * const str[] = {
+		"PCIe Endpoint",
+		"PCIe Legacy Endpoint",
+		"PCIe unknown",
+		"PCIe unknown",
+		"PCIe Root Port",
+		"PCIe Switch Upstream Port",
+		"PCIe Switch Downstream Port",
+		"PCIe to PCI/PCI-X bridge",
+		"PCI/PCI-X to PCIe bridge",
+		"PCIe Root Complex Integrated Endpoint",
+		"PCIe Root Complex Event Collector",
+	};
+	int type;
+
+	if (pci_is_pcie(dev)) {
+		type = pci_pcie_type(dev);
+		if (type < ARRAY_SIZE(str))
+			return str[type];
+
+		return "PCIe unknown";
+	}
+
+	switch (dev->hdr_type) {
+	case PCI_HEADER_TYPE_NORMAL:
+		return "conventional PCI endpoint";
+	case PCI_HEADER_TYPE_BRIDGE:
+		return "conventional PCI bridge";
+	case PCI_HEADER_TYPE_CARDBUS:
+		return "CardBus bridge";
+	default:
+		return "conventional PCI";
+	}
+}
+
 /**
  * pci_setup_device - Fill in class and map information of a device
  * @dev: the device structure to fill
@@ -1887,8 +1924,9 @@ int pci_setup_device(struct pci_dev *dev)
 
 	pci_set_removable(dev);
 
-	pci_info(dev, "[%04x:%04x] type %02x class %#08x\n",
-		 dev->vendor, dev->device, dev->hdr_type, dev->class);
+	pci_info(dev, "[%04x:%04x] type %02x class %#08x %s\n",
+		 dev->vendor, dev->device, dev->hdr_type, dev->class,
+		 pci_type_str(dev));
 
 	/* Device class may be changed after fixup */
 	class = dev->class >> 8;
-- 
GitLab


From 65f8e0beac5a495b8f3b387add1f9f4470678cb5 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay12@gmail.com>
Date: Sat, 6 Nov 2021 16:56:05 +0530
Subject: [PATCH 1478/4076] PCI: Update BAR # and window messages

The PCI log messages print the register offsets at some places and BAR
numbers at other places. There is no uniformity in this logging mechanism.
It would be better to print names than register offsets.

Add a helper function that aids in printing more meaningful information
about the BAR numbers like "VF BAR", "ROM", "bridge window", etc.  This
function can be called while printing PCI log messages.

[bhelgaas: fold in Lukas' static array suggestion from
https://lore.kernel.org/all/20211106115831.GA7452@wunner.de/]
Link: https://lore.kernel.org/r/20211106112606.192563-2-puranjay12@gmail.com
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/pci.h |  2 ++
 2 files changed, 62 insertions(+)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 55bc3576a9856..a06f77e8ab592 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -850,6 +850,66 @@ struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res)
 }
 EXPORT_SYMBOL(pci_find_resource);
 
+/**
+ * pci_resource_name - Return the name of the PCI resource
+ * @dev: PCI device to query
+ * @i: index of the resource
+ *
+ * Return the standard PCI resource (BAR) name according to their index.
+ */
+const char *pci_resource_name(struct pci_dev *dev, unsigned int i)
+{
+	static const char * const bar_name[] = {
+		"BAR 0",
+		"BAR 1",
+		"BAR 2",
+		"BAR 3",
+		"BAR 4",
+		"BAR 5",
+		"ROM",
+#ifdef CONFIG_PCI_IOV
+		"VF BAR 0",
+		"VF BAR 1",
+		"VF BAR 2",
+		"VF BAR 3",
+		"VF BAR 4",
+		"VF BAR 5",
+#endif
+		"bridge window",	/* "io" included in %pR */
+		"bridge window",	/* "mem" included in %pR */
+		"bridge window",	/* "mem pref" included in %pR */
+	};
+	static const char * const cardbus_name[] = {
+		"BAR 1",
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+#ifdef CONFIG_PCI_IOV
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+		"unknown",
+#endif
+		"CardBus bridge window 0",	/* I/O */
+		"CardBus bridge window 1",	/* I/O */
+		"CardBus bridge window 0",	/* mem */
+		"CardBus bridge window 1",	/* mem */
+	};
+
+	if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS &&
+	    i < ARRAY_SIZE(cardbus_name))
+		return cardbus_name[i];
+
+	if (i < ARRAY_SIZE(bar_name))
+		return bar_name[i];
+
+	return "unknown";
+}
+
 /**
  * pci_wait_for_pending - wait for @mask bit(s) to clear in status word @pos
  * @dev: the PCI device to operate on
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 5ecbcf0411793..fb9c94a1c0b54 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -255,6 +255,8 @@ void __pci_bus_assign_resources(const struct pci_bus *bus,
 				struct list_head *fail_head);
 bool pci_bus_clip_resource(struct pci_dev *dev, int idx);
 
+const char *pci_resource_name(struct pci_dev *dev, unsigned int i);
+
 void pci_reassigndev_resource_alignment(struct pci_dev *dev);
 void pci_disable_bridge_window(struct pci_dev *dev);
 struct pci_bus *pci_bus_get(struct pci_bus *bus);
-- 
GitLab


From dc4e6f21c3f844ebc1c52b6920b8ec5dfc73f4e8 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay12@gmail.com>
Date: Sat, 6 Nov 2021 16:56:06 +0530
Subject: [PATCH 1479/4076] PCI: Use resource names in PCI log messages

Use the pci_resource_name() to get the name of the resource and use it
while printing log messages.

[bhelgaas: rename to match struct resource * names, also use names in other
BAR messages]
Link: https://lore.kernel.org/r/20211106112606.192563-3-puranjay12@gmail.com
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/iov.c       |  7 ++--
 drivers/pci/pci.c       | 25 +++++++-------
 drivers/pci/probe.c     | 26 +++++++--------
 drivers/pci/quirks.c    | 15 ++++++---
 drivers/pci/setup-bus.c | 30 +++++++++++------
 drivers/pci/setup-res.c | 72 +++++++++++++++++++++++------------------
 6 files changed, 103 insertions(+), 72 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 25dbe85c42175..aaa33e8dc4c97 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -745,6 +745,7 @@ static int sriov_init(struct pci_dev *dev, int pos)
 	u16 ctrl, total;
 	struct pci_sriov *iov;
 	struct resource *res;
+	const char *res_name;
 	struct pci_dev *pdev;
 
 	pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl);
@@ -785,6 +786,8 @@ found:
 	nres = 0;
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
 		res = &dev->resource[i + PCI_IOV_RESOURCES];
+		res_name = pci_resource_name(dev, i + PCI_IOV_RESOURCES);
+
 		/*
 		 * If it is already FIXED, don't change it, something
 		 * (perhaps EA or header fixups) wants it this way.
@@ -802,8 +805,8 @@ found:
 		}
 		iov->barsz[i] = resource_size(res);
 		res->end = res->start + resource_size(res) * total - 1;
-		pci_info(dev, "VF(n) BAR%d space: %pR (contains BAR%d for %d VFs)\n",
-			 i, res, i, total);
+		pci_info(dev, "%s %pR: contains BAR %d for %d VFs\n",
+			 res_name, res, i, total);
 		i += bar64;
 		nres++;
 	}
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a06f77e8ab592..101af94af2d40 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3350,6 +3350,7 @@ static struct resource *pci_ea_get_resource(struct pci_dev *dev, u8 bei,
 static int pci_ea_read(struct pci_dev *dev, int offset)
 {
 	struct resource *res;
+	const char *res_name;
 	int ent_size, ent_offset = offset;
 	resource_size_t start, end;
 	unsigned long flags;
@@ -3379,6 +3380,7 @@ static int pci_ea_read(struct pci_dev *dev, int offset)
 		goto out;
 
 	res = pci_ea_get_resource(dev, bei, prop);
+	res_name = pci_resource_name(dev, bei);
 	if (!res) {
 		pci_err(dev, "Unsupported EA entry BEI: %u\n", bei);
 		goto out;
@@ -3452,16 +3454,16 @@ static int pci_ea_read(struct pci_dev *dev, int offset)
 	res->flags = flags;
 
 	if (bei <= PCI_EA_BEI_BAR5)
-		pci_info(dev, "BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
-			   bei, res, prop);
+		pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n",
+			 res_name, res, prop);
 	else if (bei == PCI_EA_BEI_ROM)
-		pci_info(dev, "ROM: %pR (from Enhanced Allocation, properties %#02x)\n",
-			   res, prop);
+		pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n",
+			 res_name, res, prop);
 	else if (bei >= PCI_EA_BEI_VF_BAR0 && bei <= PCI_EA_BEI_VF_BAR5)
-		pci_info(dev, "VF BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
-			   bei - PCI_EA_BEI_VF_BAR0, res, prop);
+		pci_info(dev, "%s %pR: from Enhanced Allocation, properties %#02x\n",
+			 res_name, res, prop);
 	else
-		pci_info(dev, "BEI %d res: %pR (from Enhanced Allocation, properties %#02x)\n",
+		pci_info(dev, "BEI %d %pR: from Enhanced Allocation, properties %#02x\n",
 			   bei, res, prop);
 
 out:
@@ -6749,14 +6751,15 @@ static void pci_request_resource_alignment(struct pci_dev *dev, int bar,
 					   resource_size_t align, bool resize)
 {
 	struct resource *r = &dev->resource[bar];
+	const char *r_name = pci_resource_name(dev, bar);
 	resource_size_t size;
 
 	if (!(r->flags & IORESOURCE_MEM))
 		return;
 
 	if (r->flags & IORESOURCE_PCI_FIXED) {
-		pci_info(dev, "BAR%d %pR: ignoring requested alignment %#llx\n",
-			 bar, r, (unsigned long long)align);
+		pci_info(dev, "%s %pR: ignoring requested alignment %#llx\n",
+			 r_name, r, (unsigned long long)align);
 		return;
 	}
 
@@ -6792,8 +6795,8 @@ static void pci_request_resource_alignment(struct pci_dev *dev, int bar,
 	 * devices and we use the second.
 	 */
 
-	pci_info(dev, "BAR%d %pR: requesting alignment to %#llx\n",
-		 bar, r, (unsigned long long)align);
+	pci_info(dev, "%s %pR: requesting alignment to %#llx\n",
+		 r_name, r, (unsigned long long)align);
 
 	if (resize) {
 		r->start = 0;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 6ee84dc939cab..e2669562389c1 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -180,6 +180,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 	u64 l64, sz64, mask64;
 	u16 orig_cmd;
 	struct pci_bus_region region, inverted_region;
+	const char *res_name = pci_resource_name(dev, res - dev->resource);
 
 	mask = type ? PCI_ROM_ADDRESS_MASK : ~0;
 
@@ -254,8 +255,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 
 	sz64 = pci_size(l64, sz64, mask64);
 	if (!sz64) {
-		pci_info(dev, FW_BUG "reg 0x%x: invalid BAR (can't size)\n",
-			 pos);
+		pci_info(dev, FW_BUG "%s: invalid; can't size\n", res_name);
 		goto fail;
 	}
 
@@ -265,8 +265,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED;
 			res->start = 0;
 			res->end = 0;
-			pci_err(dev, "reg 0x%x: can't handle BAR larger than 4GB (size %#010llx)\n",
-				pos, (unsigned long long)sz64);
+			pci_err(dev, "%s: can't handle BAR larger than 4GB (size %#010llx)\n",
+				res_name, (unsigned long long)sz64);
 			goto out;
 		}
 
@@ -275,8 +275,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			res->flags |= IORESOURCE_UNSET;
 			res->start = 0;
 			res->end = sz64 - 1;
-			pci_info(dev, "reg 0x%x: can't handle BAR above 4GB (bus address %#010llx)\n",
-				 pos, (unsigned long long)l64);
+			pci_info(dev, "%s: can't handle BAR above 4GB (bus address %#010llx)\n",
+				 res_name, (unsigned long long)l64);
 			goto out;
 		}
 	}
@@ -302,8 +302,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		res->flags |= IORESOURCE_UNSET;
 		res->start = 0;
 		res->end = region.end - region.start;
-		pci_info(dev, "reg 0x%x: initial BAR value %#010llx invalid\n",
-			 pos, (unsigned long long)region.start);
+		pci_info(dev, "%s: initial BAR value %#010llx invalid\n",
+			 res_name, (unsigned long long)region.start);
 	}
 
 	goto out;
@@ -313,7 +313,7 @@ fail:
 	res->flags = 0;
 out:
 	if (res->flags)
-		pci_info(dev, "reg 0x%x: %pR\n", pos, res);
+		pci_info(dev, "%s %pR\n", res_name, res);
 
 	return (res->flags & IORESOURCE_MEM_64) ? 1 : 0;
 }
@@ -1967,14 +1967,14 @@ int pci_setup_device(struct pci_dev *dev)
 				res = &dev->resource[0];
 				res->flags = LEGACY_IO_RESOURCE;
 				pcibios_bus_to_resource(dev->bus, res, &region);
-				pci_info(dev, "legacy IDE quirk: reg 0x10: %pR\n",
+				pci_info(dev, "BAR 0 %pR: legacy IDE quirk\n",
 					 res);
 				region.start = 0x3F6;
 				region.end = 0x3F6;
 				res = &dev->resource[1];
 				res->flags = LEGACY_IO_RESOURCE;
 				pcibios_bus_to_resource(dev->bus, res, &region);
-				pci_info(dev, "legacy IDE quirk: reg 0x14: %pR\n",
+				pci_info(dev, "BAR 1 %pR: legacy IDE quirk\n",
 					 res);
 			}
 			if ((progif & 4) == 0) {
@@ -1983,14 +1983,14 @@ int pci_setup_device(struct pci_dev *dev)
 				res = &dev->resource[2];
 				res->flags = LEGACY_IO_RESOURCE;
 				pcibios_bus_to_resource(dev->bus, res, &region);
-				pci_info(dev, "legacy IDE quirk: reg 0x18: %pR\n",
+				pci_info(dev, "BAR 2 %pR: legacy IDE quirk\n",
 					 res);
 				region.start = 0x376;
 				region.end = 0x376;
 				res = &dev->resource[3];
 				res->flags = LEGACY_IO_RESOURCE;
 				pcibios_bus_to_resource(dev->bus, res, &region);
-				pci_info(dev, "legacy IDE quirk: reg 0x1c: %pR\n",
+				pci_info(dev, "BAR 3 %pR: legacy IDE quirk\n",
 					 res);
 			}
 		}
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index ea476252280ab..905ff3def1bf9 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -570,13 +570,14 @@ static void quirk_extend_bar_to_page(struct pci_dev *dev)
 
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		struct resource *r = &dev->resource[i];
+		const char *r_name = pci_resource_name(dev, i);
 
 		if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) {
 			r->end = PAGE_SIZE - 1;
 			r->start = 0;
 			r->flags |= IORESOURCE_UNSET;
-			pci_info(dev, "expanded BAR %d to page size: %pR\n",
-				 i, r);
+			pci_info(dev, "%s %pR: expanded to page size\n",
+				 r_name, r);
 		}
 	}
 }
@@ -605,6 +606,7 @@ static void quirk_io(struct pci_dev *dev, int pos, unsigned int size,
 	u32 region;
 	struct pci_bus_region bus_region;
 	struct resource *res = dev->resource + pos;
+	const char *res_name = pci_resource_name(dev, pos);
 
 	pci_read_config_dword(dev, PCI_BASE_ADDRESS_0 + (pos << 2), &region);
 
@@ -622,8 +624,7 @@ static void quirk_io(struct pci_dev *dev, int pos, unsigned int size,
 	bus_region.end = region + size - 1;
 	pcibios_bus_to_resource(dev->bus, res, &bus_region);
 
-	pci_info(dev, FW_BUG "%s quirk: reg 0x%x: %pR\n",
-		 name, PCI_BASE_ADDRESS_0 + (pos << 2), res);
+	pci_info(dev, FW_BUG "%s %pR: %s quirk\n", res_name, res, name);
 }
 
 /*
@@ -670,6 +671,12 @@ static void quirk_io_region(struct pci_dev *dev, int port,
 	bus_region.end = region + size - 1;
 	pcibios_bus_to_resource(dev->bus, res, &bus_region);
 
+	/*
+	 * "res" is typically a bridge window resource that's not being
+	 * used for a bridge window, so it's just a place to stash this
+	 * non-standard resource.  Printing "nr" or pci_resource_name() of
+	 * it doesn't really make sense.
+	 */
 	if (!pci_claim_resource(dev, nr))
 		pci_info(dev, "quirk: %pR claimed by %s\n", res, name);
 }
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index fd74f1c99dbae..909e6a7c3cc31 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -213,6 +213,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 				      struct list_head *head)
 {
 	struct resource *res;
+	const char *res_name;
 	struct pci_dev_resource *add_res, *tmp;
 	struct pci_dev_resource *dev_res;
 	resource_size_t add_size, align;
@@ -222,6 +223,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 		bool found_match = false;
 
 		res = add_res->res;
+
 		/* Skip resource that has been reset */
 		if (!res->flags)
 			goto out;
@@ -237,6 +239,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 			continue;
 
 		idx = res - &add_res->dev->resource[0];
+		res_name = pci_resource_name(add_res->dev, idx);
 		add_size = add_res->add_size;
 		align = add_res->min_align;
 		if (!resource_size(res)) {
@@ -249,9 +252,9 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 				 (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN);
 			if (pci_reassign_resource(add_res->dev, idx,
 						  add_size, align))
-				pci_info(add_res->dev, "failed to add %llx res[%d]=%pR\n",
-					 (unsigned long long) add_size, idx,
-					 res);
+				pci_info(add_res->dev, "%s %pR: failed to add %llx\n",
+					 res_name, res,
+					 (unsigned long long) add_size);
 		}
 out:
 		list_del(&add_res->list);
@@ -571,6 +574,7 @@ EXPORT_SYMBOL(pci_setup_cardbus);
 static void pci_setup_bridge_io(struct pci_dev *bridge)
 {
 	struct resource *res;
+	const char *res_name;
 	struct pci_bus_region region;
 	unsigned long io_mask;
 	u8 io_base_lo, io_limit_lo;
@@ -583,6 +587,7 @@ static void pci_setup_bridge_io(struct pci_dev *bridge)
 
 	/* Set up the top and bottom of the PCI I/O segment for this bus */
 	res = &bridge->resource[PCI_BRIDGE_IO_WINDOW];
+	res_name = pci_resource_name(bridge, PCI_BRIDGE_IO_WINDOW);
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_IO) {
 		pci_read_config_word(bridge, PCI_IO_BASE, &l);
@@ -591,7 +596,7 @@ static void pci_setup_bridge_io(struct pci_dev *bridge)
 		l = ((u16) io_limit_lo << 8) | io_base_lo;
 		/* Set up upper 16 bits of I/O base/limit */
 		io_upper16 = (region.end & 0xffff0000) | (region.start >> 16);
-		pci_info(bridge, "  bridge window %pR\n", res);
+		pci_info(bridge, "  %s %pR\n", res_name, res);
 	} else {
 		/* Clear upper 16 bits of I/O base/limit */
 		io_upper16 = 0;
@@ -608,16 +613,18 @@ static void pci_setup_bridge_io(struct pci_dev *bridge)
 static void pci_setup_bridge_mmio(struct pci_dev *bridge)
 {
 	struct resource *res;
+	const char *res_name;
 	struct pci_bus_region region;
 	u32 l;
 
 	/* Set up the top and bottom of the PCI Memory segment for this bus */
 	res = &bridge->resource[PCI_BRIDGE_MEM_WINDOW];
+	res_name = pci_resource_name(bridge, PCI_BRIDGE_MEM_WINDOW);
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_MEM) {
 		l = (region.start >> 16) & 0xfff0;
 		l |= region.end & 0xfff00000;
-		pci_info(bridge, "  bridge window %pR\n", res);
+		pci_info(bridge, "  %s %pR\n", res_name, res);
 	} else {
 		l = 0x0000fff0;
 	}
@@ -627,6 +634,7 @@ static void pci_setup_bridge_mmio(struct pci_dev *bridge)
 static void pci_setup_bridge_mmio_pref(struct pci_dev *bridge)
 {
 	struct resource *res;
+	const char *res_name;
 	struct pci_bus_region region;
 	u32 l, bu, lu;
 
@@ -640,6 +648,7 @@ static void pci_setup_bridge_mmio_pref(struct pci_dev *bridge)
 	/* Set up PREF base/limit */
 	bu = lu = 0;
 	res = &bridge->resource[PCI_BRIDGE_PREF_MEM_WINDOW];
+	res_name = pci_resource_name(bridge, PCI_BRIDGE_PREF_MEM_WINDOW);
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_PREFETCH) {
 		l = (region.start >> 16) & 0xfff0;
@@ -648,7 +657,7 @@ static void pci_setup_bridge_mmio_pref(struct pci_dev *bridge)
 			bu = upper_32_bits(region.start);
 			lu = upper_32_bits(region.end);
 		}
-		pci_info(bridge, "  bridge window %pR\n", res);
+		pci_info(bridge, "  %s %pR\n", res_name, res);
 	} else {
 		l = 0x0000fff0;
 	}
@@ -1013,6 +1022,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 		int i;
 
 		pci_dev_for_each_resource(dev, r, i) {
+			const char *r_name = pci_resource_name(dev, i);
 			resource_size_t r_size;
 
 			if (r->parent || (r->flags & IORESOURCE_PCI_FIXED) ||
@@ -1043,8 +1053,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 			if (order < 0)
 				order = 0;
 			if (order >= ARRAY_SIZE(aligns)) {
-				pci_warn(dev, "disabling BAR %d: %pR (bad alignment %#llx)\n",
-					 i, r, (unsigned long long) align);
+				pci_warn(dev, "%s %pR: disabling; bad alignment %#llx\n",
+					 r_name, r, (unsigned long long) align);
 				r->flags = 0;
 				continue;
 			}
@@ -2235,6 +2245,7 @@ int pci_reassign_bridge_resources(struct pci_dev *bridge, unsigned long type)
 		for (i = PCI_BRIDGE_RESOURCES; i < PCI_BRIDGE_RESOURCE_END;
 		     i++) {
 			struct resource *res = &bridge->resource[i];
+			const char *res_name = pci_resource_name(bridge, i);
 
 			if ((res->flags ^ type) & PCI_RES_TYPE_MASK)
 				continue;
@@ -2247,8 +2258,7 @@ int pci_reassign_bridge_resources(struct pci_dev *bridge, unsigned long type)
 			if (ret)
 				goto cleanup;
 
-			pci_info(bridge, "BAR %d: releasing %pR\n",
-				 i, res);
+			pci_info(bridge, "%s %pR: releasing\n", res_name, res);
 
 			if (res->parent)
 				release_resource(res);
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index ceaa69491f5ef..c6d933ddfd464 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -30,6 +30,7 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 	u32 new, check, mask;
 	int reg;
 	struct resource *res = dev->resource + resno;
+	const char *res_name = pci_resource_name(dev, resno);
 
 	/* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */
 	if (dev->is_virtfn)
@@ -104,8 +105,8 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 	pci_read_config_dword(dev, reg, &check);
 
 	if ((new ^ check) & mask) {
-		pci_err(dev, "BAR %d: error updating (%#010x != %#010x)\n",
-			resno, new, check);
+		pci_err(dev, "%s: error updating (%#010x != %#010x)\n",
+			res_name, new, check);
 	}
 
 	if (res->flags & IORESOURCE_MEM_64) {
@@ -113,8 +114,8 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 		pci_write_config_dword(dev, reg + 4, new);
 		pci_read_config_dword(dev, reg + 4, &check);
 		if (check != new) {
-			pci_err(dev, "BAR %d: error updating (high %#010x != %#010x)\n",
-				resno, new, check);
+			pci_err(dev, "%s: error updating (high %#010x != %#010x)\n",
+				res_name, new, check);
 		}
 	}
 
@@ -135,11 +136,12 @@ void pci_update_resource(struct pci_dev *dev, int resno)
 int pci_claim_resource(struct pci_dev *dev, int resource)
 {
 	struct resource *res = &dev->resource[resource];
+	const char *res_name = pci_resource_name(dev, resource);
 	struct resource *root, *conflict;
 
 	if (res->flags & IORESOURCE_UNSET) {
-		pci_info(dev, "can't claim BAR %d %pR: no address assigned\n",
-			 resource, res);
+		pci_info(dev, "%s %pR: can't claim; no address assigned\n",
+			 res_name, res);
 		return -EINVAL;
 	}
 
@@ -153,16 +155,16 @@ int pci_claim_resource(struct pci_dev *dev, int resource)
 
 	root = pci_find_parent_resource(dev, res);
 	if (!root) {
-		pci_info(dev, "can't claim BAR %d %pR: no compatible bridge window\n",
-			 resource, res);
+		pci_info(dev, "%s %pR: can't claim; no compatible bridge window\n",
+			 res_name, res);
 		res->flags |= IORESOURCE_UNSET;
 		return -EINVAL;
 	}
 
 	conflict = request_resource_conflict(root, res);
 	if (conflict) {
-		pci_info(dev, "can't claim BAR %d %pR: address conflict with %s %pR\n",
-			 resource, res, conflict->name, conflict);
+		pci_info(dev, "%s %pR: can't claim; address conflict with %s %pR\n",
+			 res_name, res, conflict->name, conflict);
 		res->flags |= IORESOURCE_UNSET;
 		return -EBUSY;
 	}
@@ -201,6 +203,7 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
 {
 	struct resource *root, *conflict;
 	resource_size_t fw_addr, start, end;
+	const char *res_name = pci_resource_name(dev, resno);
 
 	fw_addr = pcibios_retrieve_fw_addr(dev, resno);
 	if (!fw_addr)
@@ -231,12 +234,11 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
 			root = &iomem_resource;
 	}
 
-	pci_info(dev, "BAR %d: trying firmware assignment %pR\n",
-		 resno, res);
+	pci_info(dev, "%s: trying firmware assignment %pR\n", res_name, res);
 	conflict = request_resource_conflict(root, res);
 	if (conflict) {
-		pci_info(dev, "BAR %d: %pR conflicts with %s %pR\n",
-			 resno, res, conflict->name, conflict);
+		pci_info(dev, "%s %pR: conflicts with %s %pR\n", res_name, res,
+			 conflict->name, conflict);
 		res->start = start;
 		res->end = end;
 		res->flags |= IORESOURCE_UNSET;
@@ -325,6 +327,7 @@ static int _pci_assign_resource(struct pci_dev *dev, int resno,
 int pci_assign_resource(struct pci_dev *dev, int resno)
 {
 	struct resource *res = dev->resource + resno;
+	const char *res_name = pci_resource_name(dev, resno);
 	resource_size_t align, size;
 	int ret;
 
@@ -334,8 +337,8 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 	res->flags |= IORESOURCE_UNSET;
 	align = pci_resource_alignment(dev, res);
 	if (!align) {
-		pci_info(dev, "BAR %d: can't assign %pR (bogus alignment)\n",
-			 resno, res);
+		pci_info(dev, "%s %pR: can't assign; bogus alignment\n",
+			 res_name, res);
 		return -EINVAL;
 	}
 
@@ -348,18 +351,18 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 	 * working, which is better than just leaving it disabled.
 	 */
 	if (ret < 0) {
-		pci_info(dev, "BAR %d: no space for %pR\n", resno, res);
+		pci_info(dev, "%s %pR: can't assign; no space\n", res_name, res);
 		ret = pci_revert_fw_address(res, dev, resno, size);
 	}
 
 	if (ret < 0) {
-		pci_info(dev, "BAR %d: failed to assign %pR\n", resno, res);
+		pci_info(dev, "%s %pR: failed to assign\n", res_name, res);
 		return ret;
 	}
 
 	res->flags &= ~IORESOURCE_UNSET;
 	res->flags &= ~IORESOURCE_STARTALIGN;
-	pci_info(dev, "BAR %d: assigned %pR\n", resno, res);
+	pci_info(dev, "%s %pR: assigned\n", res_name, res);
 	if (resno < PCI_BRIDGE_RESOURCES)
 		pci_update_resource(dev, resno);
 
@@ -367,10 +370,11 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 }
 EXPORT_SYMBOL(pci_assign_resource);
 
-int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsize,
-			resource_size_t min_align)
+int pci_reassign_resource(struct pci_dev *dev, int resno,
+			  resource_size_t addsize, resource_size_t min_align)
 {
 	struct resource *res = dev->resource + resno;
+	const char *res_name = pci_resource_name(dev, resno);
 	unsigned long flags;
 	resource_size_t new_size;
 	int ret;
@@ -381,8 +385,8 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 	flags = res->flags;
 	res->flags |= IORESOURCE_UNSET;
 	if (!res->parent) {
-		pci_info(dev, "BAR %d: can't reassign an unassigned resource %pR\n",
-			 resno, res);
+		pci_info(dev, "%s %pR: can't reassign; unassigned resource\n",
+			 res_name, res);
 		return -EINVAL;
 	}
 
@@ -391,15 +395,15 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 	ret = _pci_assign_resource(dev, resno, new_size, min_align);
 	if (ret) {
 		res->flags = flags;
-		pci_info(dev, "BAR %d: %pR (failed to expand by %#llx)\n",
-			 resno, res, (unsigned long long) addsize);
+		pci_info(dev, "%s %pR: failed to expand by %#llx\n",
+			 res_name, res, (unsigned long long) addsize);
 		return ret;
 	}
 
 	res->flags &= ~IORESOURCE_UNSET;
 	res->flags &= ~IORESOURCE_STARTALIGN;
-	pci_info(dev, "BAR %d: reassigned %pR (expanded by %#llx)\n",
-		 resno, res, (unsigned long long) addsize);
+	pci_info(dev, "%s %pR: reassigned; expanded by %#llx\n",
+		 res_name, res, (unsigned long long) addsize);
 	if (resno < PCI_BRIDGE_RESOURCES)
 		pci_update_resource(dev, resno);
 
@@ -409,8 +413,9 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 void pci_release_resource(struct pci_dev *dev, int resno)
 {
 	struct resource *res = dev->resource + resno;
+	const char *res_name = pci_resource_name(dev, resno);
 
-	pci_info(dev, "BAR %d: releasing %pR\n", resno, res);
+	pci_info(dev, "%s %pR: releasing\n", res_name, res);
 
 	if (!res->parent)
 		return;
@@ -480,6 +485,7 @@ int pci_enable_resources(struct pci_dev *dev, int mask)
 	u16 cmd, old_cmd;
 	int i;
 	struct resource *r;
+	const char *r_name;
 
 	pci_read_config_word(dev, PCI_COMMAND, &cmd);
 	old_cmd = cmd;
@@ -488,6 +494,8 @@ int pci_enable_resources(struct pci_dev *dev, int mask)
 		if (!(mask & (1 << i)))
 			continue;
 
+		r_name = pci_resource_name(dev, i);
+
 		if (!(r->flags & (IORESOURCE_IO | IORESOURCE_MEM)))
 			continue;
 		if ((i == PCI_ROM_RESOURCE) &&
@@ -495,14 +503,14 @@ int pci_enable_resources(struct pci_dev *dev, int mask)
 			continue;
 
 		if (r->flags & IORESOURCE_UNSET) {
-			pci_err(dev, "can't enable device: BAR %d %pR not assigned\n",
-				i, r);
+			pci_err(dev, "%s %pR: not assigned; can't enable device\n",
+				r_name, r);
 			return -EINVAL;
 		}
 
 		if (!r->parent) {
-			pci_err(dev, "can't enable device: BAR %d %pR not claimed\n",
-				i, r);
+			pci_err(dev, "%s %pR: not claimed; can't enable device\n",
+				r_name, r);
 			return -EINVAL;
 		}
 
-- 
GitLab


From 6f32099a91720b6d91da961858d48173f01a729d Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 4 Dec 2023 17:39:15 -0600
Subject: [PATCH 1480/4076] PCI: Move pci_read_bridge_windows() below
 individual window accessors

Move pci_read_bridge_windows() below the functions that read the I/O,
memory, and prefetchable memory windows, so pci_read_bridge_windows() can
use them in the future.  No functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 102 ++++++++++++++++++++++----------------------
 1 file changed, 51 insertions(+), 51 deletions(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index e2669562389c1..75bb48b72e854 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -344,57 +344,6 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 	}
 }
 
-static void pci_read_bridge_windows(struct pci_dev *bridge)
-{
-	u16 io;
-	u32 pmem, tmp;
-
-	pci_read_config_word(bridge, PCI_IO_BASE, &io);
-	if (!io) {
-		pci_write_config_word(bridge, PCI_IO_BASE, 0xe0f0);
-		pci_read_config_word(bridge, PCI_IO_BASE, &io);
-		pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
-	}
-	if (io)
-		bridge->io_window = 1;
-
-	/*
-	 * DECchip 21050 pass 2 errata: the bridge may miss an address
-	 * disconnect boundary by one PCI data phase.  Workaround: do not
-	 * use prefetching on this device.
-	 */
-	if (bridge->vendor == PCI_VENDOR_ID_DEC && bridge->device == 0x0001)
-		return;
-
-	pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
-	if (!pmem) {
-		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE,
-					       0xffe0fff0);
-		pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
-		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, 0x0);
-	}
-	if (!pmem)
-		return;
-
-	bridge->pref_window = 1;
-
-	if ((pmem & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) {
-
-		/*
-		 * Bridge claims to have a 64-bit prefetchable memory
-		 * window; verify that the upper bits are actually
-		 * writable.
-		 */
-		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &pmem);
-		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32,
-				       0xffffffff);
-		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &tmp);
-		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, pmem);
-		if (tmp)
-			bridge->pref_64_window = 1;
-	}
-}
-
 static void pci_read_bridge_io(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
@@ -510,6 +459,57 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child)
 	}
 }
 
+static void pci_read_bridge_windows(struct pci_dev *bridge)
+{
+	u16 io;
+	u32 pmem, tmp;
+
+	pci_read_config_word(bridge, PCI_IO_BASE, &io);
+	if (!io) {
+		pci_write_config_word(bridge, PCI_IO_BASE, 0xe0f0);
+		pci_read_config_word(bridge, PCI_IO_BASE, &io);
+		pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
+	}
+	if (io)
+		bridge->io_window = 1;
+
+	/*
+	 * DECchip 21050 pass 2 errata: the bridge may miss an address
+	 * disconnect boundary by one PCI data phase.  Workaround: do not
+	 * use prefetching on this device.
+	 */
+	if (bridge->vendor == PCI_VENDOR_ID_DEC && bridge->device == 0x0001)
+		return;
+
+	pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
+	if (!pmem) {
+		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE,
+					       0xffe0fff0);
+		pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
+		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, 0x0);
+	}
+	if (!pmem)
+		return;
+
+	bridge->pref_window = 1;
+
+	if ((pmem & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) {
+
+		/*
+		 * Bridge claims to have a 64-bit prefetchable memory
+		 * window; verify that the upper bits are actually
+		 * writable.
+		 */
+		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &pmem);
+		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32,
+				       0xffffffff);
+		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &tmp);
+		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, pmem);
+		if (tmp)
+			bridge->pref_64_window = 1;
+	}
+}
+
 void pci_read_bridge_bases(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
-- 
GitLab


From 281e1f137a97dae4fe47a7d30635c5b83def790b Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 22 Nov 2023 10:13:03 -0600
Subject: [PATCH 1481/4076] PCI: Supply bridge device, not secondary bus, to
 read window details

Previously we logged information about devices *below* the bridge before
logging information about the bridge itself, e.g.,

  pci 0000:00:01.0: [8086:1901] type 01 class 0x060400
  pci 0000:01:00.0: [10de:13b6] type 00 class 0x030200
  pci 0000:01:00.0: reg 0x10: [mem 0xec000000-0xecffffff]
  pci 0000:00:01.0: PCI bridge to [bus 01]
  pci 0000:00:01.0:   bridge window [io  0xe000-0xefff]

This is partly because the bridge windows are read in this path:

  pci_scan_child_bus_extend
    for (devfn = 0; devfn < 256; devfn += 8)
      pci_scan_slot(bus, devfn)       # scan below bridge
    pcibios_fixup_bus(bus)
      pci_read_bridge_bases(bus)      # read bridge windows
        pci_read_bridge_io(bus)

Remove the assumption that the secondary (child) pci_bus already exists by
passing in the bridge device (instead of the pci_bus) and a resource
pointer when reading bridge windows.  A future change can use this to log
the bridge details before we enumerate the devices below the bridge.

No functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 21 ++++++---------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 75bb48b72e854..b0b8ed7a72f3f 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -344,13 +344,11 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 	}
 }
 
-static void pci_read_bridge_io(struct pci_bus *child)
+static void pci_read_bridge_io(struct pci_dev *dev, struct resource *res)
 {
-	struct pci_dev *dev = child->self;
 	u8 io_base_lo, io_limit_lo;
 	unsigned long io_mask, io_granularity, base, limit;
 	struct pci_bus_region region;
-	struct resource *res;
 
 	io_mask = PCI_IO_RANGE_MASK;
 	io_granularity = 0x1000;
@@ -360,7 +358,6 @@ static void pci_read_bridge_io(struct pci_bus *child)
 		io_granularity = 0x400;
 	}
 
-	res = child->resource[0];
 	pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
 	pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
 	base = (io_base_lo & io_mask) << 8;
@@ -384,15 +381,12 @@ static void pci_read_bridge_io(struct pci_bus *child)
 	}
 }
 
-static void pci_read_bridge_mmio(struct pci_bus *child)
+static void pci_read_bridge_mmio(struct pci_dev *dev, struct resource *res)
 {
-	struct pci_dev *dev = child->self;
 	u16 mem_base_lo, mem_limit_lo;
 	unsigned long base, limit;
 	struct pci_bus_region region;
-	struct resource *res;
 
-	res = child->resource[1];
 	pci_read_config_word(dev, PCI_MEMORY_BASE, &mem_base_lo);
 	pci_read_config_word(dev, PCI_MEMORY_LIMIT, &mem_limit_lo);
 	base = ((unsigned long) mem_base_lo & PCI_MEMORY_RANGE_MASK) << 16;
@@ -406,16 +400,13 @@ static void pci_read_bridge_mmio(struct pci_bus *child)
 	}
 }
 
-static void pci_read_bridge_mmio_pref(struct pci_bus *child)
+static void pci_read_bridge_mmio_pref(struct pci_dev *dev, struct resource *res)
 {
-	struct pci_dev *dev = child->self;
 	u16 mem_base_lo, mem_limit_lo;
 	u64 base64, limit64;
 	pci_bus_addr_t base, limit;
 	struct pci_bus_region region;
-	struct resource *res;
 
-	res = child->resource[2];
 	pci_read_config_word(dev, PCI_PREF_MEMORY_BASE, &mem_base_lo);
 	pci_read_config_word(dev, PCI_PREF_MEMORY_LIMIT, &mem_limit_lo);
 	base64 = (mem_base_lo & PCI_PREF_RANGE_MASK) << 16;
@@ -527,9 +518,9 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
 		child->resource[i] = &dev->resource[PCI_BRIDGE_RESOURCES+i];
 
-	pci_read_bridge_io(child);
-	pci_read_bridge_mmio(child);
-	pci_read_bridge_mmio_pref(child);
+	pci_read_bridge_io(child->self, child->resource[0]);
+	pci_read_bridge_mmio(child->self, child->resource[1]);
+	pci_read_bridge_mmio_pref(child->self, child->resource[2]);
 
 	if (dev->transparent) {
 		pci_bus_for_each_resource(child->parent, res) {
-- 
GitLab


From 63c6ebb294b7c708cc987d621e59499686650683 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 4 Dec 2023 17:53:32 -0600
Subject: [PATCH 1482/4076] PCI: Log bridge windows conditionally

Previously pci_read_bridge_io(), pci_read_bridge_mmio(), and
pci_read_bridge_mmio_pref() unconditionally logged the bridge window
resource.  A future change will call these functions earlier and more
often.  Add a "log" parameter so callers can control whether to generate
the log message.  No functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index b0b8ed7a72f3f..3d39a47846b4c 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -344,7 +344,8 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 	}
 }
 
-static void pci_read_bridge_io(struct pci_dev *dev, struct resource *res)
+static void pci_read_bridge_io(struct pci_dev *dev, struct resource *res,
+			       bool log)
 {
 	u8 io_base_lo, io_limit_lo;
 	unsigned long io_mask, io_granularity, base, limit;
@@ -377,11 +378,13 @@ static void pci_read_bridge_io(struct pci_dev *dev, struct resource *res)
 		region.start = base;
 		region.end = limit + io_granularity - 1;
 		pcibios_bus_to_resource(dev->bus, res, &region);
-		pci_info(dev, "  bridge window %pR\n", res);
+		if (log)
+			pci_info(dev, "  bridge window %pR\n", res);
 	}
 }
 
-static void pci_read_bridge_mmio(struct pci_dev *dev, struct resource *res)
+static void pci_read_bridge_mmio(struct pci_dev *dev, struct resource *res,
+				 bool log)
 {
 	u16 mem_base_lo, mem_limit_lo;
 	unsigned long base, limit;
@@ -396,11 +399,13 @@ static void pci_read_bridge_mmio(struct pci_dev *dev, struct resource *res)
 		region.start = base;
 		region.end = limit + 0xfffff;
 		pcibios_bus_to_resource(dev->bus, res, &region);
-		pci_info(dev, "  bridge window %pR\n", res);
+		if (log)
+			pci_info(dev, "  bridge window %pR\n", res);
 	}
 }
 
-static void pci_read_bridge_mmio_pref(struct pci_dev *dev, struct resource *res)
+static void pci_read_bridge_mmio_pref(struct pci_dev *dev, struct resource *res,
+				      bool log)
 {
 	u16 mem_base_lo, mem_limit_lo;
 	u64 base64, limit64;
@@ -446,7 +451,8 @@ static void pci_read_bridge_mmio_pref(struct pci_dev *dev, struct resource *res)
 		region.start = base;
 		region.end = limit + 0xfffff;
 		pcibios_bus_to_resource(dev->bus, res, &region);
-		pci_info(dev, "  bridge window %pR\n", res);
+		if (log)
+			pci_info(dev, "  bridge window %pR\n", res);
 	}
 }
 
@@ -518,9 +524,9 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
 		child->resource[i] = &dev->resource[PCI_BRIDGE_RESOURCES+i];
 
-	pci_read_bridge_io(child->self, child->resource[0]);
-	pci_read_bridge_mmio(child->self, child->resource[1]);
-	pci_read_bridge_mmio_pref(child->self, child->resource[2]);
+	pci_read_bridge_io(child->self, child->resource[0], true);
+	pci_read_bridge_mmio(child->self, child->resource[1], true);
+	pci_read_bridge_mmio_pref(child->self, child->resource[2], true);
 
 	if (dev->transparent) {
 		pci_bus_for_each_resource(child->parent, res) {
-- 
GitLab


From 95140c2fbfdf3b6ca98578e5bdbc82d9922f08b9 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 22 Nov 2023 10:34:07 -0600
Subject: [PATCH 1483/4076] PCI: Log bridge info when first enumerating bridge

Log bridge secondary/subordinate bus and window information at the same
time we log the bridge BARs, just after discovering the bridge and before
scanning the bridge's secondary bus.  This logs the bridge and downstream
devices in a more logical order:

  - pci 0000:00:01.0: [8086:1901] type 01 class 0x060400
  - pci 0000:01:00.0: [10de:13b6] type 00 class 0x030200
  - pci 0000:01:00.0: reg 0x10: [mem 0xec000000-0xecffffff]
  - pci 0000:00:01.0: PCI bridge to [bus 01]
  - pci 0000:00:01.0:   bridge window [io  0xe000-0xefff]

  + pci 0000:00:01.0: [8086:1901] type 01 class 0x060400
  + pci 0000:00:01.0: PCI bridge to [bus 01]
  + pci 0000:00:01.0:   bridge window [io  0xe000-0xefff]
  + pci 0000:01:00.0: [10de:13b6] type 00 class 0x030200
  + pci 0000:01:00.0: reg 0x10: [mem 0xec000000-0xecffffff]

Note that we read the windows into a temporary struct resource that is
thrown away, not into the resources in the struct pci_bus.

The windows may be adjusted after we know what downstream devices require,
and those adjustments are logged as they are made.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 3d39a47846b4c..b7335be56008f 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -458,8 +458,17 @@ static void pci_read_bridge_mmio_pref(struct pci_dev *dev, struct resource *res,
 
 static void pci_read_bridge_windows(struct pci_dev *bridge)
 {
+	u32 buses;
 	u16 io;
 	u32 pmem, tmp;
+	struct resource res;
+
+	pci_read_config_dword(bridge, PCI_PRIMARY_BUS, &buses);
+	res.flags = IORESOURCE_BUS;
+	res.start = (buses >> 8) & 0xff;
+	res.end = (buses >> 16) & 0xff;
+	pci_info(bridge, "PCI bridge to %pR%s\n", &res,
+		 bridge->transparent ? " (subtractive decode)" : "");
 
 	pci_read_config_word(bridge, PCI_IO_BASE, &io);
 	if (!io) {
@@ -467,8 +476,12 @@ static void pci_read_bridge_windows(struct pci_dev *bridge)
 		pci_read_config_word(bridge, PCI_IO_BASE, &io);
 		pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
 	}
-	if (io)
+	if (io) {
 		bridge->io_window = 1;
+		pci_read_bridge_io(bridge, &res, true);
+	}
+
+	pci_read_bridge_mmio(bridge, &res, true);
 
 	/*
 	 * DECchip 21050 pass 2 errata: the bridge may miss an address
@@ -505,6 +518,8 @@ static void pci_read_bridge_windows(struct pci_dev *bridge)
 		if (tmp)
 			bridge->pref_64_window = 1;
 	}
+
+	pci_read_bridge_mmio_pref(bridge, &res, true);
 }
 
 void pci_read_bridge_bases(struct pci_bus *child)
@@ -524,9 +539,9 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
 		child->resource[i] = &dev->resource[PCI_BRIDGE_RESOURCES+i];
 
-	pci_read_bridge_io(child->self, child->resource[0], true);
-	pci_read_bridge_mmio(child->self, child->resource[1], true);
-	pci_read_bridge_mmio_pref(child->self, child->resource[2], true);
+	pci_read_bridge_io(child->self, child->resource[0], false);
+	pci_read_bridge_mmio(child->self, child->resource[1], false);
+	pci_read_bridge_mmio_pref(child->self, child->resource[2], false);
 
 	if (dev->transparent) {
 		pci_bus_for_each_resource(child->parent, res) {
-- 
GitLab


From 4791c44c0a982051713458cf4e66855e9f092713 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 11:51:52 +0100
Subject: [PATCH 1484/4076] dt-bindings: PCI: qcom: Adjust iommu-map for
 different SoC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PCIe controller on SDX55 has five entries in its iommu-map, MSM8998
has one and SDM845 has sixteen, so allow wider number of items to fix
dtbs_check warnings like:

  qcom-sdx55-mtp.dtb: pcie@1c00000: iommu-map: [[0, 21, 512, 1], [256, 21, 513, 1],
    [512, 21, 514, 1], [768, 21, 515, 1], [1024, 21, 516, 1]] is too long

Link: https://lore.kernel.org/linux-pci/20231208105155.36097-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
---
 Documentation/devicetree/bindings/pci/qcom,pcie.yaml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index eadba38171e13..4bf2299f70a6d 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -62,7 +62,8 @@ properties:
     maxItems: 8
 
   iommu-map:
-    maxItems: 2
+    minItems: 1
+    maxItems: 16
 
   # Common definitions for clocks, clock-names and reset.
   # Platform constraints are described later.
-- 
GitLab


From f2ab5a2455d95e50ebbd835c92ddb2a632b2d301 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 11:51:53 +0100
Subject: [PATCH 1485/4076] dt-bindings: PCI: qcom: Correct clocks for SC8180x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PCI node in Qualcomm SC8180x DTS has 8 clocks:

  sc8180x-primus.dtb: pci@1c00000: 'oneOf' conditional failed, one must be fixed:
    ['pipe', 'aux', 'cfg', 'bus_master', 'bus_slave', 'slave_q2a', 'ref', 'tbu'] is too short

Link: https://lore.kernel.org/linux-pci/20231208105155.36097-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Acked-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/pci/qcom,pcie.yaml    | 28 ++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index 4bf2299f70a6d..ce841ea1578ca 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -479,6 +479,33 @@ allOf:
           items:
             - const: pci # PCIe core reset
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,pcie-sc8180x
+    then:
+      properties:
+        clocks:
+          minItems: 8
+          maxItems: 8
+        clock-names:
+          items:
+            - const: pipe # PIPE clock
+            - const: aux # Auxiliary clock
+            - const: cfg # Configuration clock
+            - const: bus_master # Master AXI clock
+            - const: bus_slave # Slave AXI clock
+            - const: slave_q2a # Slave Q2A clock
+            - const: ref # REFERENCE clock
+            - const: tbu # PCIe TBU clock
+        resets:
+          maxItems: 1
+        reset-names:
+          items:
+            - const: pci # PCIe core reset
+
   - if:
       properties:
         compatible:
@@ -527,7 +554,6 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,pcie-sc8180x
               - qcom,pcie-sm8150
               - qcom,pcie-sm8250
     then:
-- 
GitLab


From a711253d5f706dfc018a4a193ef401b7e8cf1d93 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 11:51:54 +0100
Subject: [PATCH 1486/4076] dt-bindings: PCI: qcom: Correct clocks for SM8150
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PCI node in Qualcomm SM8150 should have exactly 8 clocks, including the
ref clock.

Suggested-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/linux-pci/20231208105155.36097-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Acked-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/pci/qcom,pcie.yaml    | 26 +++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index ce841ea1578ca..9dfb341e4f776 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -555,6 +555,32 @@ allOf:
           contains:
             enum:
               - qcom,pcie-sm8150
+    then:
+      properties:
+        clocks:
+          minItems: 8
+          maxItems: 8
+        clock-names:
+          items:
+            - const: pipe # PIPE clock
+            - const: aux # Auxiliary clock
+            - const: cfg # Configuration clock
+            - const: bus_master # Master AXI clock
+            - const: bus_slave # Slave AXI clock
+            - const: slave_q2a # Slave Q2A clock
+            - const: tbu # PCIe TBU clock
+            - const: ref # REFERENCE clock
+        resets:
+          maxItems: 1
+        reset-names:
+          items:
+            - const: pci # PCIe core reset
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - qcom,pcie-sm8250
     then:
       oneOf:
-- 
GitLab


From 3b74713a0321de5e4b1507990ef87049f8c887d8 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 11 Nov 2023 15:20:06 +0100
Subject: [PATCH 1487/4076] dt-bindings: PCI: qcom: Correct reset-names
 property
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is no "resets-names" property, but "reset-names".

Fixes: 075a9d55932e ("dt-bindings: PCI: qcom: Convert to YAML")
Link: https://lore.kernel.org/linux-pci/20231111142006.51883-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
---
 Documentation/devicetree/bindings/pci/qcom,pcie.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index 9dfb341e4f776..6be2aebdc98e0 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -89,7 +89,7 @@ properties:
     minItems: 1
     maxItems: 12
 
-  resets-names:
+  reset-names:
     minItems: 1
     maxItems: 12
 
-- 
GitLab


From 639f666cf84e9192ef2ca0b5d638a258062513b7 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@cherry.de>
Date: Wed, 6 Dec 2023 15:50:41 +0100
Subject: [PATCH 1488/4076] dt-bindings: PCI: dwc: rockchip: Document optional
 PCIe reference clock input
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On some boards the 100MHz PCIe reference clock to both controller and
devices is controllable. Add that clock to the list of clocks.

The clock is optional, so the minItems stays the same.

Link: https://lore.kernel.org/linux-pci/20231206145041.667900-1-heiko@sntech.de
Signed-off-by: Heiko Stuebner <heiko.stuebner@cherry.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
index 1ae8dcfa072ce..5f719218c472c 100644
--- a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
@@ -49,6 +49,7 @@ properties:
       - description: APB clock for PCIe
       - description: Auxiliary clock for PCIe
       - description: PIPE clock
+      - description: Reference clock for PCIe
 
   clock-names:
     minItems: 5
@@ -59,6 +60,7 @@ properties:
       - const: pclk
       - const: aux
       - const: pipe
+      - const: ref
 
   interrupts:
     items:
-- 
GitLab


From 41f757713ac38ae2f63bc02d5653aac254c5bdbf Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Tue, 28 Nov 2023 09:43:53 +0100
Subject: [PATCH 1489/4076] dt-bindings: PCI: qcom: Document the SM8650 PCIe
 Controller
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document the PCIe Controller on the SM8650 platform by using the
SM8550 bindings as a fallback.

Link: https://lore.kernel.org/linux-pci/20231128-topic-sm8650-upstream-bindings-pcie-v2-1-b72e2d13bcf1@linaro.org
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/pci/qcom,pcie.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index 6be2aebdc98e0..a93ab3b540666 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -41,6 +41,10 @@ properties:
           - qcom,pcie-sm8450-pcie0
           - qcom,pcie-sm8450-pcie1
           - qcom,pcie-sm8550
+      - items:
+          - enum:
+              - qcom,pcie-sm8650
+          - const: qcom,pcie-sm8550
       - items:
           - const: qcom,pcie-msm8998
           - const: qcom,pcie-msm8996
-- 
GitLab


From edd6ae1022a659b47586b64fa93c615ee14efd94 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Mon, 18 Sep 2023 11:22:47 +0100
Subject: [PATCH 1490/4076] PCI: dwc: Convert SOC_SIFIVE to ARCH_SIFIVE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As part of converting RISC-V SOC_FOO symbols to ARCH_FOO to match the
use of such symbols on other architectures, convert the SiFive PCI
drivers to use the newer symbol.

Link: https://lore.kernel.org/linux-pci/20230918-safeness-cornflake-62278bc3aaaa@wendy
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/dwc/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index 5ac021dbd46a4..8afacc90c63b8 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -336,7 +336,7 @@ config PCI_EXYNOS
 config PCIE_FU740
 	bool "SiFive FU740 PCIe controller"
 	depends on PCI_MSI
-	depends on SOC_SIFIVE || COMPILE_TEST
+	depends on ARCH_SIFIVE || COMPILE_TEST
 	select PCIE_DW_HOST
 	help
 	  Say Y here if you want PCIe controller support for the SiFive
-- 
GitLab


From 4fbd8b788258bb636b007f5baf440262cbff1a00 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 4 Dec 2023 10:47:40 +0100
Subject: [PATCH 1491/4076] PCI: exynos: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

In the error path emit an error message replacing the (less useful)
message by the core. Apart from the improved error message there is no
change in behaviour.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Link: https://lore.kernel.org/linux-pci/50de44ea8931465fd9cdc821854ea761cb43adf6.1701682617.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/dwc/pci-exynos.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index c6bede3469320..104397ba45bd3 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -375,7 +375,7 @@ fail_probe:
 	return ret;
 }
 
-static int exynos_pcie_remove(struct platform_device *pdev)
+static void exynos_pcie_remove(struct platform_device *pdev)
 {
 	struct exynos_pcie *ep = platform_get_drvdata(pdev);
 
@@ -385,8 +385,6 @@ static int exynos_pcie_remove(struct platform_device *pdev)
 	phy_exit(ep->phy);
 	exynos_pcie_deinit_clk_resources(ep);
 	regulator_bulk_disable(ARRAY_SIZE(ep->supplies), ep->supplies);
-
-	return 0;
 }
 
 static int exynos_pcie_suspend_noirq(struct device *dev)
@@ -431,7 +429,7 @@ static const struct of_device_id exynos_pcie_of_match[] = {
 
 static struct platform_driver exynos_pcie_driver = {
 	.probe		= exynos_pcie_probe,
-	.remove		= exynos_pcie_remove,
+	.remove_new	= exynos_pcie_remove,
 	.driver = {
 		.name	= "exynos-pcie",
 		.of_match_table = exynos_pcie_of_match,
-- 
GitLab


From 93d61d3aa996ede34226055a2525c0c2e28258db Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 4 Dec 2023 10:47:41 +0100
Subject: [PATCH 1492/4076] PCI: keystone: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

In the error path emit an error message replacing the (less useful)
message by the core. Apart from the improved error message there is no
change in behaviour.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Link: https://lore.kernel.org/linux-pci/06612aff79dfb52d5b0b20129dff5e4b1f04d3a7.1701682617.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/dwc/pci-keystone.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 0def919f89faf..41c7ff8627325 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -1302,7 +1302,7 @@ err_link:
 	return ret;
 }
 
-static int ks_pcie_remove(struct platform_device *pdev)
+static void ks_pcie_remove(struct platform_device *pdev)
 {
 	struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev);
 	struct device_link **link = ks_pcie->link;
@@ -1314,13 +1314,11 @@ static int ks_pcie_remove(struct platform_device *pdev)
 	ks_pcie_disable_phy(ks_pcie);
 	while (num_lanes--)
 		device_link_del(link[num_lanes]);
-
-	return 0;
 }
 
 static struct platform_driver ks_pcie_driver = {
 	.probe  = ks_pcie_probe,
-	.remove = ks_pcie_remove,
+	.remove_new = ks_pcie_remove,
 	.driver = {
 		.name	= "keystone-pcie",
 		.of_match_table = ks_pcie_of_match,
-- 
GitLab


From a5eee68931fcc6ecabd35651fed0c31439078e67 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 4 Dec 2023 10:47:42 +0100
Subject: [PATCH 1493/4076] PCI: kirin: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

In the error path emit an error message replacing the (less useful)
message by the core. Apart from the improved error message there is no
change in behaviour.

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Link: https://lore.kernel.org/linux-pci/c3a51791d54deaa818b8526975fc4e16ef1090ce.1701682617.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/dwc/pcie-kirin.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index 2ee146767971c..ca317cb06fbde 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -741,15 +741,13 @@ err:
 	return ret;
 }
 
-static int kirin_pcie_remove(struct platform_device *pdev)
+static void kirin_pcie_remove(struct platform_device *pdev)
 {
 	struct kirin_pcie *kirin_pcie = platform_get_drvdata(pdev);
 
 	dw_pcie_host_deinit(&kirin_pcie->pci->pp);
 
 	kirin_pcie_power_off(kirin_pcie);
-
-	return 0;
 }
 
 struct kirin_pcie_data {
@@ -818,7 +816,7 @@ static int kirin_pcie_probe(struct platform_device *pdev)
 
 static struct platform_driver kirin_pcie_driver = {
 	.probe			= kirin_pcie_probe,
-	.remove	        	= kirin_pcie_remove,
+	.remove_new		= kirin_pcie_remove,
 	.driver			= {
 		.name			= "kirin-pcie",
 		.of_match_table		= kirin_pcie_match,
-- 
GitLab


From b89b6a863dd53bc70d8e52d50f9cfaef8ef5e9c9 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Mon, 11 Dec 2023 14:42:51 +0800
Subject: [PATCH 1494/4076] bus: mhi: host: Add spinlock to protect WP access
 when queueing TREs

Protect WP accesses such that multiple threads queueing buffers for
incoming data do not race.

Meanwhile, if CONFIG_TRACE_IRQFLAGS is enabled, irq will be enabled once
__local_bh_enable_ip is called as part of write_unlock_bh. Hence, let's
take irqsave lock after TRE is generated to avoid running write_unlock_bh
when irqsave lock is held.

Cc: stable@vger.kernel.org
Fixes: 189ff97cca53 ("bus: mhi: core: Add support for data transfer")
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Tested-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/1702276972-41296-2-git-send-email-quic_qianyu@quicinc.com
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/host/main.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c
index d80975f4bba87..ad7807e4b523b 100644
--- a/drivers/bus/mhi/host/main.c
+++ b/drivers/bus/mhi/host/main.c
@@ -1124,17 +1124,15 @@ static int mhi_queue(struct mhi_device *mhi_dev, struct mhi_buf_info *buf_info,
 	if (unlikely(MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state)))
 		return -EIO;
 
-	read_lock_irqsave(&mhi_cntrl->pm_lock, flags);
-
 	ret = mhi_is_ring_full(mhi_cntrl, tre_ring);
-	if (unlikely(ret)) {
-		ret = -EAGAIN;
-		goto exit_unlock;
-	}
+	if (unlikely(ret))
+		return -EAGAIN;
 
 	ret = mhi_gen_tre(mhi_cntrl, mhi_chan, buf_info, mflags);
 	if (unlikely(ret))
-		goto exit_unlock;
+		return ret;
+
+	read_lock_irqsave(&mhi_cntrl->pm_lock, flags);
 
 	/* Packet is queued, take a usage ref to exit M3 if necessary
 	 * for host->device buffer, balanced put is done on buffer completion
@@ -1154,7 +1152,6 @@ static int mhi_queue(struct mhi_device *mhi_dev, struct mhi_buf_info *buf_info,
 	if (dir == DMA_FROM_DEVICE)
 		mhi_cntrl->runtime_put(mhi_cntrl);
 
-exit_unlock:
 	read_unlock_irqrestore(&mhi_cntrl->pm_lock, flags);
 
 	return ret;
@@ -1206,6 +1203,9 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 	int eot, eob, chain, bei;
 	int ret;
 
+	/* Protect accesses for reading and incrementing WP */
+	write_lock_bh(&mhi_chan->lock);
+
 	buf_ring = &mhi_chan->buf_ring;
 	tre_ring = &mhi_chan->tre_ring;
 
@@ -1223,8 +1223,10 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 
 	if (!info->pre_mapped) {
 		ret = mhi_cntrl->map_single(mhi_cntrl, buf_info);
-		if (ret)
+		if (ret) {
+			write_unlock_bh(&mhi_chan->lock);
 			return ret;
+		}
 	}
 
 	eob = !!(flags & MHI_EOB);
@@ -1241,6 +1243,8 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 	mhi_add_ring_element(mhi_cntrl, tre_ring);
 	mhi_add_ring_element(mhi_cntrl, buf_ring);
 
+	write_unlock_bh(&mhi_chan->lock);
+
 	return 0;
 }
 
-- 
GitLab


From 01bd694ac2f682fb8017e16148b928482bc8fa4b Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Mon, 11 Dec 2023 14:42:52 +0800
Subject: [PATCH 1495/4076] bus: mhi: host: Drop chan lock before queuing
 buffers

Ensure read and write locks for the channel are not taken in succession by
dropping the read lock from parse_xfer_event() such that a callback given
to client can potentially queue buffers and acquire the write lock in that
process. Any queueing of buffers should be done without channel read lock
acquired as it can result in multiple locks and a soft lockup.

Cc: <stable@vger.kernel.org> # 5.7
Fixes: 1d3173a3bae7 ("bus: mhi: core: Add support for processing events from client device")
Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Tested-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/1702276972-41296-3-git-send-email-quic_qianyu@quicinc.com
[mani: added fixes tag and cc'ed stable]
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/host/main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c
index ad7807e4b523b..abb561db9ae1d 100644
--- a/drivers/bus/mhi/host/main.c
+++ b/drivers/bus/mhi/host/main.c
@@ -644,6 +644,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl,
 			mhi_del_ring_element(mhi_cntrl, tre_ring);
 			local_rp = tre_ring->rp;
 
+			read_unlock_bh(&mhi_chan->lock);
+
 			/* notify client */
 			mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
 
@@ -669,6 +671,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl,
 					kfree(buf_info->cb_buf);
 				}
 			}
+
+			read_lock_bh(&mhi_chan->lock);
 		}
 		break;
 	} /* CC_EOT */
-- 
GitLab


From 9f5077ef8f8157270f51f4ebd782c985d56d33c6 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 18 Nov 2023 08:55:48 +0100
Subject: [PATCH 1496/4076] PCI: kirin: Use devm_kasprintf() to dynamically
 allocate clock names
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use devm_kasprintf() instead of open coding it.  This saves the need of
an intermediate buffer.

There was also no reason to use devm_kstrdup_const() as string is known
to be constant.

[kwilczynski: commit log, and add missing Reviewed-by tag]
Link: https://lore.kernel.org/linux-pci/1bad6879083a7d836c8a47418a0afa22485e8f69.1700294127.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/pci/controller/dwc/pcie-kirin.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index 2ee146767971c..982f854bc39c1 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -366,7 +366,6 @@ static int kirin_pcie_get_gpio_enable(struct kirin_pcie *pcie,
 				      struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	char name[32];
 	int ret, i;
 
 	/* This is an optional property */
@@ -387,9 +386,8 @@ static int kirin_pcie_get_gpio_enable(struct kirin_pcie *pcie,
 		if (pcie->gpio_id_clkreq[i] < 0)
 			return pcie->gpio_id_clkreq[i];
 
-		sprintf(name, "pcie_clkreq_%d", i);
-		pcie->clkreq_names[i] = devm_kstrdup_const(dev, name,
-							    GFP_KERNEL);
+		pcie->clkreq_names[i] = devm_kasprintf(dev, GFP_KERNEL,
+						       "pcie_clkreq_%d", i);
 		if (!pcie->clkreq_names[i])
 			return -ENOMEM;
 	}
@@ -404,7 +402,6 @@ static int kirin_pcie_parse_port(struct kirin_pcie *pcie,
 	struct device *dev = &pdev->dev;
 	struct device_node *parent, *child;
 	int ret, slot, i;
-	char name[32];
 
 	for_each_available_child_of_node(node, parent) {
 		for_each_available_child_of_node(parent, child) {
@@ -430,9 +427,9 @@ static int kirin_pcie_parse_port(struct kirin_pcie *pcie,
 
 			slot = PCI_SLOT(ret);
 
-			sprintf(name, "pcie_perst_%d", slot);
-			pcie->reset_names[i] = devm_kstrdup_const(dev, name,
-								GFP_KERNEL);
+			pcie->reset_names[i] = devm_kasprintf(dev, GFP_KERNEL,
+							      "pcie_perst_%d",
+							      slot);
 			if (!pcie->reset_names[i]) {
 				ret = -ENOMEM;
 				goto put_node;
-- 
GitLab


From 9c556b7c3f520d42c435c0d78b25c719c060f8a1 Mon Sep 17 00:00:00 2001
From: Naveen N Rao <naveen@kernel.org>
Date: Thu, 14 Dec 2023 10:47:02 +0530
Subject: [PATCH 1497/4076] trace/kprobe: Display the actual notrace function
 when rejecting a probe

Trying to probe update_sd_lb_stats() using perf results in the below
message in the kernel log:
	trace_kprobe: Could not probe notrace function _text

This is because 'perf probe' specifies the kprobe location as an offset
from '_text':
	$ sudo perf probe -D update_sd_lb_stats
	p:probe/update_sd_lb_stats _text+1830728

However, the error message is misleading and doesn't help convey the
actual notrace function that is being probed. Fix this by looking up the
actual function name that is being probed. With this fix, we now get the
below message in the kernel log:
	trace_kprobe: Could not probe notrace function update_sd_lb_stats.constprop.0

Link: https://lore.kernel.org/all/20231214051702.1687300-1-naveen@kernel.org/

Signed-off-by: Naveen N Rao <naveen@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/trace_kprobe.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 52f8b537dd0a0..c4c6e0e0068be 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -487,8 +487,8 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
 		return -EINVAL;
 
 	if (within_notrace_func(tk)) {
-		pr_warn("Could not probe notrace function %s\n",
-			trace_kprobe_symbol(tk));
+		pr_warn("Could not probe notrace function %ps\n",
+			(void *)trace_kprobe_address(tk));
 		return -EINVAL;
 	}
 
-- 
GitLab


From 08b3485540d9e94ed8335f82e5fc491fc02f8423 Mon Sep 17 00:00:00 2001
From: Ayush Singh <ayushdevel1325@gmail.com>
Date: Sun, 17 Dec 2023 17:41:32 +0530
Subject: [PATCH 1498/4076] greybus: gb-beagleplay: Remove use of pad bytes

Make gb-beagleplay greybus spec compliant by moving cport information to
transport layer instead of using `header->pad` bytes.

Greybus HDLC frame now has the following payload:
1. le16 cport
2. gb_operation_msg_hdr msg_header
3. u8 *msg_payload

Fixes: ec558bbfea67 ("greybus: Add BeaglePlay Linux Driver")
Signed-off-by: Ayush Singh <ayushdevel1325@gmail.com>
Link: https://lore.kernel.org/r/20231217121133.74703-2-ayushdevel1325@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/greybus/gb-beagleplay.c | 58 ++++++++++++++++++++++++---------
 1 file changed, 43 insertions(+), 15 deletions(-)

diff --git a/drivers/greybus/gb-beagleplay.c b/drivers/greybus/gb-beagleplay.c
index 43318c1993ba9..7d98ae1a8263a 100644
--- a/drivers/greybus/gb-beagleplay.c
+++ b/drivers/greybus/gb-beagleplay.c
@@ -85,17 +85,31 @@ struct hdlc_payload {
 	void *buf;
 };
 
+/**
+ * struct hdlc_greybus_frame - Structure to represent greybus HDLC frame payload
+ *
+ * @cport: cport id
+ * @hdr: greybus operation header
+ * @payload: greybus message payload
+ *
+ * The HDLC payload sent over UART for greybus address has cport preappended to greybus message
+ */
+struct hdlc_greybus_frame {
+	__le16 cport;
+	struct gb_operation_msg_hdr hdr;
+	u8 payload[];
+} __packed;
+
 static void hdlc_rx_greybus_frame(struct gb_beagleplay *bg, u8 *buf, u16 len)
 {
-	u16 cport_id;
-	struct gb_operation_msg_hdr *hdr = (struct gb_operation_msg_hdr *)buf;
-
-	memcpy(&cport_id, hdr->pad, sizeof(cport_id));
+	struct hdlc_greybus_frame *gb_frame = (struct hdlc_greybus_frame *)buf;
+	u16 cport_id = le16_to_cpu(gb_frame->cport);
+	u16 gb_msg_len = le16_to_cpu(gb_frame->hdr.size);
 
 	dev_dbg(&bg->sd->dev, "Greybus Operation %u type %X cport %u status %u received",
-		hdr->operation_id, hdr->type, cport_id, hdr->result);
+		gb_frame->hdr.operation_id, gb_frame->hdr.type, cport_id, gb_frame->hdr.result);
 
-	greybus_data_rcvd(bg->gb_hd, cport_id, buf, len);
+	greybus_data_rcvd(bg->gb_hd, cport_id, (u8 *)&gb_frame->hdr, gb_msg_len);
 }
 
 static void hdlc_rx_dbg_frame(const struct gb_beagleplay *bg, const char *buf, u16 len)
@@ -336,25 +350,39 @@ static struct serdev_device_ops gb_beagleplay_ops = {
 	.write_wakeup = gb_tty_wakeup,
 };
 
+/**
+ * gb_message_send() - Send greybus message using HDLC over UART
+ *
+ * @hd: pointer to greybus host device
+ * @cport: AP cport where message originates
+ * @msg: greybus message to send
+ * @mask: gfp mask
+ *
+ * Greybus HDLC frame has the following payload:
+ * 1. le16 cport
+ * 2. gb_operation_msg_hdr msg_header
+ * 3. u8 *msg_payload
+ */
 static int gb_message_send(struct gb_host_device *hd, u16 cport, struct gb_message *msg, gfp_t mask)
 {
 	struct gb_beagleplay *bg = dev_get_drvdata(&hd->dev);
-	struct hdlc_payload payloads[2];
+	struct hdlc_payload payloads[3];
+	__le16 cport_id = cpu_to_le16(cport);
 
 	dev_dbg(&hd->dev, "Sending greybus message with Operation %u, Type: %X on Cport %u",
 		msg->header->operation_id, msg->header->type, cport);
 
-	if (msg->header->size > RX_HDLC_PAYLOAD)
+	if (le16_to_cpu(msg->header->size) > RX_HDLC_PAYLOAD)
 		return dev_err_probe(&hd->dev, -E2BIG, "Greybus message too big");
 
-	memcpy(msg->header->pad, &cport, sizeof(cport));
-
-	payloads[0].buf = msg->header;
-	payloads[0].len = sizeof(*msg->header);
-	payloads[1].buf = msg->payload;
-	payloads[1].len = msg->payload_size;
+	payloads[0].buf = &cport_id;
+	payloads[0].len = sizeof(cport_id);
+	payloads[1].buf = msg->header;
+	payloads[1].len = sizeof(*msg->header);
+	payloads[2].buf = msg->payload;
+	payloads[2].len = msg->payload_size;
 
-	hdlc_tx_frames(bg, ADDRESS_GREYBUS, 0x03, payloads, 2);
+	hdlc_tx_frames(bg, ADDRESS_GREYBUS, 0x03, payloads, 3);
 	greybus_message_sent(bg->gb_hd, msg, 0);
 
 	return 0;
-- 
GitLab


From 38f0bd4cd34588b788228af081a1c86df4f494fa Mon Sep 17 00:00:00 2001
From: Jun Yan <jerrysteve1101@gmail.com>
Date: Thu, 14 Dec 2023 22:27:33 +0800
Subject: [PATCH 1499/4076] iio: accel: bmi088: update comments and Kconfig

update the comments and Kconfig file with more descriptive and
accurate information about newly added device: BMI085, BMI090L.

Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/Kconfig             | 7 ++++---
 drivers/iio/accel/bmi088-accel-core.c | 2 ++
 drivers/iio/accel/bmi088-accel-spi.c  | 2 ++
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig
index f113dae590483..91adcac875a41 100644
--- a/drivers/iio/accel/Kconfig
+++ b/drivers/iio/accel/Kconfig
@@ -260,10 +260,11 @@ config BMI088_ACCEL
 	select REGMAP
 	select BMI088_ACCEL_SPI
 	help
-	  Say yes here to build support for the Bosch BMI088 accelerometer.
+	  Say yes here to build support for the following Bosch accelerometers:
+	  BMI088, BMI085, BMI090L. Note that all of these are combo module that
+	  include both accelerometer and gyroscope.
 
-	  This is a combo module with both accelerometer and gyroscope. This
-	  driver only implements the accelerometer part, which has its own
+	  This driver only implements the accelerometer part, which has its own
 	  address and register map. BMG160 provides the gyroscope driver.
 
 config BMI088_ACCEL_SPI
diff --git a/drivers/iio/accel/bmi088-accel-core.c b/drivers/iio/accel/bmi088-accel-core.c
index 84edcc78d7961..4d989708e6c36 100644
--- a/drivers/iio/accel/bmi088-accel-core.c
+++ b/drivers/iio/accel/bmi088-accel-core.c
@@ -2,6 +2,8 @@
 /*
  * 3-axis accelerometer driver supporting following Bosch-Sensortec chips:
  *  - BMI088
+ *  - BMI085
+ *  - BMI090L
  *
  * Copyright (c) 2018-2021, Topic Embedded Products
  */
diff --git a/drivers/iio/accel/bmi088-accel-spi.c b/drivers/iio/accel/bmi088-accel-spi.c
index ee540edd84126..7b419a7b2478a 100644
--- a/drivers/iio/accel/bmi088-accel-spi.c
+++ b/drivers/iio/accel/bmi088-accel-spi.c
@@ -2,6 +2,8 @@
 /*
  * 3-axis accelerometer driver supporting following Bosch-Sensortec chips:
  *  - BMI088
+ *  - BMI085
+ *  - BMI090L
  *
  * Copyright (c) 2018-2020, Topic Embedded Products
  */
-- 
GitLab


From e68eaae67021d2e393c31c86955c675922d0870a Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Fri, 15 Dec 2023 21:53:09 +0530
Subject: [PATCH 1500/4076] dt-bindings: vendor-prefixes: add aosong

Aosong Electronic Co., LTD. is a supplier for MEMS sensors such as AHT20
temperature and humidity sensor under the brand name Asair

Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20231215162312.143568-1-anshulusr@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/vendor-prefixes.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 309b94c328c84..aedbdbd947abf 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -119,6 +119,8 @@ patternProperties:
     description: Andes Technology Corporation
   "^anvo,.*":
     description: Anvo-Systems Dresden GmbH
+  "^aosong,.*":
+    description: Guangzhou Aosong Electronic Co., Ltd.
   "^apm,.*":
     description: Applied Micro Circuits Corporation (APM)
   "^apple,.*":
-- 
GitLab


From c9c6f564b28ce68c5bb79afa282de1946e106421 Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Fri, 15 Dec 2023 21:53:10 +0530
Subject: [PATCH 1501/4076] dt-bindings: iio: chemical: add aosong,ags02ma

Add bindings for Aosong AGS02MA TVOC sensor.

The sensor communicates over i2c with the default address 0x1a.
TVOC values can be read in the units of ppb and ug/m^3 at register 0x00.

Datasheet: https://asairsensors.com/wp-content/uploads/2021/09/AGS02MA.pdf
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20231215162312.143568-2-anshulusr@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/chemical/aosong,ags02ma.yaml | 47 +++++++++++++++++++
 1 file changed, 47 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml

diff --git a/Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml b/Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml
new file mode 100644
index 0000000000000..35e7b094e878a
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml
@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/chemical/aosong,ags02ma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Aosong AGS02MA VOC Sensor
+
+description: |
+  AGS02MA is an TVOC (Total Volatile Organic Compounds) i2c sensor with default
+  address of 0x1a.
+
+  Datasheet:
+    https://asairsensors.com/wp-content/uploads/2021/09/AGS02MA.pdf
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - aosong,ags02ma
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        voc-sensor@1a {
+            compatible = "aosong,ags02ma";
+            reg = <0x1a>;
+            vdd-supply = <&vdd_regulator>;
+        };
+    };
-- 
GitLab


From d58013f39b302512b02cbf4826dd9f194bdf1865 Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Fri, 15 Dec 2023 21:53:11 +0530
Subject: [PATCH 1502/4076] iio: chemical: add support for Aosong AGS02MA

A simple driver for the TVOC (Total Volatile Organic Compounds)
sensor from Aosong: AGS02MA

Steps in reading the VOC sensor value over i2c:
  1. Read 5 bytes from the register `AGS02MA_TVOC_READ_REG` [0x00]
  2. The first 4 bytes are taken as the big endian sensor data with final
     byte being the CRC
  3. The CRC is verified and the value is returned over an
     `IIO_CHAN_INFO_RAW` channel as percents

Tested on Raspberry Pi Zero 2W

Datasheet: https://asairsensors.com/wp-content/uploads/2021/09/AGS02MA.pdf
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20231215162312.143568-3-anshulusr@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS                    |   7 ++
 drivers/iio/chemical/Kconfig   |  11 +++
 drivers/iio/chemical/Makefile  |   1 +
 drivers/iio/chemical/ags02ma.c | 165 +++++++++++++++++++++++++++++++++
 4 files changed, 184 insertions(+)
 create mode 100644 drivers/iio/chemical/ags02ma.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 4eddc4212f2b8..3029841e92a85 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3071,6 +3071,13 @@ S:	Supported
 W:	http://www.akm.com/
 F:	drivers/iio/magnetometer/ak8974.c
 
+AOSONG AGS02MA TVOC SENSOR DRIVER
+M:	Anshul Dalal <anshulusr@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/chemical/aosong,ags02ma.yaml
+F:	drivers/iio/chemical/ags02ma.c
+
 ASC7621 HARDWARE MONITOR DRIVER
 M:	George Joseph <george.joseph@fairview5.com>
 L:	linux-hwmon@vger.kernel.org
diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig
index c30657e10ee17..02649ab81b3ce 100644
--- a/drivers/iio/chemical/Kconfig
+++ b/drivers/iio/chemical/Kconfig
@@ -5,6 +5,17 @@
 
 menu "Chemical Sensors"
 
+config AOSONG_AGS02MA
+	tristate "Aosong AGS02MA TVOC sensor driver"
+	depends on I2C
+	select CRC8
+	help
+	  Say Y here to build support for Aosong AGS02MA TVOC (Total Volatile
+	  Organic Compounds) sensor.
+
+	  To compile this driver as module, choose M here: the module will be
+	  called ags02ma.
+
 config ATLAS_PH_SENSOR
 	tristate "Atlas Scientific OEM SM sensors"
 	depends on I2C
diff --git a/drivers/iio/chemical/Makefile b/drivers/iio/chemical/Makefile
index a11e777a7a005..2f3dee8bb7796 100644
--- a/drivers/iio/chemical/Makefile
+++ b/drivers/iio/chemical/Makefile
@@ -4,6 +4,7 @@
 #
 
 # When adding new entries keep the list in alphabetical order
+obj-$(CONFIG_AOSONG_AGS02MA)	+= ags02ma.o
 obj-$(CONFIG_ATLAS_PH_SENSOR)	+= atlas-sensor.o
 obj-$(CONFIG_ATLAS_EZO_SENSOR)	+= atlas-ezo-sensor.o
 obj-$(CONFIG_BME680) += bme680_core.o
diff --git a/drivers/iio/chemical/ags02ma.c b/drivers/iio/chemical/ags02ma.c
new file mode 100644
index 0000000000000..8fcd809465436
--- /dev/null
+++ b/drivers/iio/chemical/ags02ma.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com>
+ *
+ * Driver for Aosong AGS02MA
+ *
+ * Datasheet:
+ *   https://asairsensors.com/wp-content/uploads/2021/09/AGS02MA.pdf
+ * Product Page:
+ *   http://www.aosong.com/m/en/products-33.html
+ */
+
+#include <linux/crc8.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+
+#include <linux/iio/iio.h>
+
+#define AGS02MA_TVOC_READ_REG		   0x00
+#define AGS02MA_VERSION_REG		   0x11
+
+#define AGS02MA_VERSION_PROCESSING_DELAY   30
+#define AGS02MA_TVOC_READ_PROCESSING_DELAY 1500
+
+#define AGS02MA_CRC8_INIT		   0xff
+#define AGS02MA_CRC8_POLYNOMIAL		   0x31
+
+DECLARE_CRC8_TABLE(ags02ma_crc8_table);
+
+struct ags02ma_data {
+	struct i2c_client *client;
+};
+
+struct ags02ma_reading {
+	__be32 data;
+	u8 crc;
+} __packed;
+
+static int ags02ma_register_read(struct i2c_client *client, u8 reg, u16 delay,
+				 u32 *val)
+{
+	int ret;
+	u8 crc;
+	struct ags02ma_reading read_buffer;
+
+	ret = i2c_master_send(client, &reg, sizeof(reg));
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"Failed to send data to register 0x%x: %d", reg, ret);
+		return ret;
+	}
+
+	/* Processing Delay, Check Table 7.7 in the datasheet */
+	msleep_interruptible(delay);
+
+	ret = i2c_master_recv(client, (u8 *)&read_buffer, sizeof(read_buffer));
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"Failed to receive from register 0x%x: %d", reg, ret);
+		return ret;
+	}
+
+	crc = crc8(ags02ma_crc8_table, (u8 *)&read_buffer.data,
+		   sizeof(read_buffer.data), AGS02MA_CRC8_INIT);
+	if (crc != read_buffer.crc) {
+		dev_err(&client->dev, "CRC error\n");
+		return -EIO;
+	}
+
+	*val = be32_to_cpu(read_buffer.data);
+	return 0;
+}
+
+static int ags02ma_read_raw(struct iio_dev *iio_device,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	int ret;
+	struct ags02ma_data *data = iio_priv(iio_device);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = ags02ma_register_read(data->client, AGS02MA_TVOC_READ_REG,
+					    AGS02MA_TVOC_READ_PROCESSING_DELAY,
+					    val);
+		if (ret < 0)
+			return ret;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		/* The sensor reads data as ppb */
+		*val = 0;
+		*val2 = 100;
+		return IIO_VAL_INT_PLUS_NANO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info ags02ma_info = {
+	.read_raw = ags02ma_read_raw,
+};
+
+static const struct iio_chan_spec ags02ma_channel = {
+	.type = IIO_CONCENTRATION,
+	.channel2 = IIO_MOD_VOC,
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+		BIT(IIO_CHAN_INFO_SCALE),
+};
+
+static int ags02ma_probe(struct i2c_client *client)
+{
+	int ret;
+	struct ags02ma_data *data;
+	struct iio_dev *indio_dev;
+	u32 version;
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	crc8_populate_msb(ags02ma_crc8_table, AGS02MA_CRC8_POLYNOMIAL);
+
+	ret = ags02ma_register_read(client, AGS02MA_VERSION_REG,
+				    AGS02MA_VERSION_PROCESSING_DELAY, &version);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret,
+			      "Failed to read device version\n");
+	dev_dbg(&client->dev, "Aosong AGS02MA, Version: 0x%x", version);
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+	indio_dev->info = &ags02ma_info;
+	indio_dev->channels = &ags02ma_channel;
+	indio_dev->num_channels = 1;
+	indio_dev->name = "ags02ma";
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct i2c_device_id ags02ma_id_table[] = {
+	{ "ags02ma" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, ags02ma_id_table);
+
+static const struct of_device_id ags02ma_of_table[] = {
+	{ .compatible = "aosong,ags02ma" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ags02ma_of_table);
+
+static struct i2c_driver ags02ma_driver = {
+	.driver = {
+		.name = "ags02ma",
+		.of_match_table = ags02ma_of_table,
+	},
+	.id_table = ags02ma_id_table,
+	.probe = ags02ma_probe,
+};
+module_i2c_driver(ags02ma_driver);
+
+MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>");
+MODULE_DESCRIPTION("Aosong AGS02MA TVOC Driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 2f9dadba5ba02e1510a04ce57ebfb9e08fd872a8 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Sat, 16 Dec 2023 14:45:27 -0300
Subject: [PATCH 1503/4076] scripts: checkpatch: Add __aligned to the list of
 attribute notes

Checkpatch presumes attributes marked with __aligned(alignment) are part
of a function declaration and throws a warning stating that those
compiler attributes should have an identifier name which is not correct.
Add __aligned compiler attributes to the list of attribute notes
so they don't cause warnings anymore.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Acked-by: Joe Perches <joe@perches.com>
Link: https://lore.kernel.org/r/1c5c93ecbd8c46a338b22a4ef52e51648e333c01.1702746240.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 scripts/checkpatch.pl | 1 +
 1 file changed, 1 insertion(+)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 25fdb7fda1128..d56c98146da3e 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -512,6 +512,7 @@ our $Attribute	= qr{
 			__ro_after_init|
 			__kprobes|
 			$InitAttribute|
+			__aligned\s*\(.*\)|
 			____cacheline_aligned|
 			____cacheline_aligned_in_smp|
 			____cacheline_internodealigned_in_smp|
-- 
GitLab


From a25a7df518fc71b1ba981d691e9322e645d2689c Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Sat, 16 Dec 2023 14:46:11 -0300
Subject: [PATCH 1504/4076] iio: adc: ad7091r: Pass iio_dev to event handler

Previous version of ad7091r event handler received the ADC state pointer
and retrieved the iio device from driver data field with dev_get_drvdata().
However, no driver data have ever been set, which led to null pointer
dereference when running the event handler.

Pass the iio device to the event handler and retrieve the ADC state struct
from it so we avoid the null pointer dereference and save the driver from
filling the driver data field.

Fixes: ca69300173b6 ("iio: adc: Add support for AD7091R5 ADC")
Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/5024b764107463de9578d5b3b0a3d5678e307b1a.1702746240.git.marcelo.schmitt1@gmail.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 8e252cde735b9..0e5d3d2e9c985 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -174,8 +174,8 @@ static const struct iio_info ad7091r_info = {
 
 static irqreturn_t ad7091r_event_handler(int irq, void *private)
 {
-	struct ad7091r_state *st = (struct ad7091r_state *) private;
-	struct iio_dev *iio_dev = dev_get_drvdata(st->dev);
+	struct iio_dev *iio_dev = private;
+	struct ad7091r_state *st = iio_priv(iio_dev);
 	unsigned int i, read_val;
 	int ret;
 	s64 timestamp = iio_get_time_ns(iio_dev);
@@ -234,7 +234,7 @@ int ad7091r_probe(struct device *dev, const char *name,
 	if (irq) {
 		ret = devm_request_threaded_irq(dev, irq, NULL,
 				ad7091r_event_handler,
-				IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, st);
+				IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, iio_dev);
 		if (ret)
 			return ret;
 	}
-- 
GitLab


From 149694f5e79b0c7a36ceb76e7c0d590db8f151c1 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Sat, 16 Dec 2023 14:46:37 -0300
Subject: [PATCH 1505/4076] iio: adc: ad7091r: Set alert bit in config register

The ad7091r-base driver sets up an interrupt handler for firing events
when inputs are either above or below a certain threshold.
However, for the interrupt signal to come from the device it must be
configured to enable the ALERT/BUSY/GPO pin to be used as ALERT, which
was not being done until now.
Enable interrupt signals on the ALERT/BUSY/GPO pin by setting the proper
bit in the configuration register.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/e8da2ee98d6df88318b14baf3dc9630e20218418.1702746240.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 0e5d3d2e9c985..8aaa854f816fa 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -28,6 +28,7 @@
 #define AD7091R_REG_RESULT_CONV_RESULT(x)   ((x) & 0xfff)
 
 /* AD7091R_REG_CONF */
+#define AD7091R_REG_CONF_ALERT_EN   BIT(4)
 #define AD7091R_REG_CONF_AUTO   BIT(8)
 #define AD7091R_REG_CONF_CMD    BIT(10)
 
@@ -232,6 +233,11 @@ int ad7091r_probe(struct device *dev, const char *name,
 	iio_dev->channels = chip_info->channels;
 
 	if (irq) {
+		ret = regmap_update_bits(st->map, AD7091R_REG_CONF,
+					 AD7091R_REG_CONF_ALERT_EN, BIT(4));
+		if (ret)
+			return ret;
+
 		ret = devm_request_threaded_irq(dev, irq, NULL,
 				ad7091r_event_handler,
 				IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, iio_dev);
-- 
GitLab


From 2dfef50589aef3b9a2fa2190ae95b328fb664f89 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Sat, 16 Dec 2023 14:47:01 -0300
Subject: [PATCH 1506/4076] iio: adc: ad7091r: Align arguments to function call
 parenthesis

Align arguments to function call open parenthesis to comply with the
Linux kernel coding style.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/fc71a82d3b4a6bc6f511f27451dbd7a3280a8c95.1702746240.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 8aaa854f816fa..d3d287d3b9535 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -239,8 +239,9 @@ int ad7091r_probe(struct device *dev, const char *name,
 			return ret;
 
 		ret = devm_request_threaded_irq(dev, irq, NULL,
-				ad7091r_event_handler,
-				IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, iio_dev);
+						ad7091r_event_handler,
+						IRQF_TRIGGER_FALLING |
+						IRQF_ONESHOT, name, iio_dev);
 		if (ret)
 			return ret;
 	}
-- 
GitLab


From 9d598fab9731055638c6e9333c4f21aa0d174a48 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Fri, 8 Dec 2023 16:07:57 +0100
Subject: [PATCH 1507/4076] dt-bindings: remoteproc: qcom: sc7180-pas: Fix
 SC7280 MPSS PD-names

The power domains for MPSS on SC7280 are actually named CX and MSS, and
not CX and MX. Adjust the name which also aligns the bindings with the
dts and fixes validation.

Fixes: 8bb92d6fd0b3 ("dt-bindings: remoteproc: qcom,sc7180-pas: split into separate file")
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Link: https://lore.kernel.org/r/20231208-sc7280-remoteprocs-v3-1-6aa394d33edf@fairphone.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml       | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
index f10f329677d84..6f0bd6fa5d263 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
@@ -114,11 +114,11 @@ allOf:
         power-domains:
           items:
             - description: CX power domain
-            - description: MX power domain
+            - description: MSS power domain
         power-domain-names:
           items:
             - const: cx
-            - const: mx
+            - const: mss
 
 unevaluatedProperties: false
 
-- 
GitLab


From 11eff1020440060c53d2261531432927c9fb4ee3 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Fri, 8 Dec 2023 16:08:01 +0100
Subject: [PATCH 1508/4076] dt-bindings: remoteproc: qcom: sc7180-pas: Add
 SC7280 compatibles

Add the compatibles and constraints for the ADSP, CDSP and WPSS found on
the SC7280 SoC.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Link: https://lore.kernel.org/r/20231208-sc7280-remoteprocs-v3-5-6aa394d33edf@fairphone.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../bindings/remoteproc/qcom,sc7180-pas.yaml  | 21 +++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
index 6f0bd6fa5d263..c054b84fdcd5c 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,sc7180-pas.yaml
@@ -18,7 +18,10 @@ properties:
     enum:
       - qcom,sc7180-adsp-pas
       - qcom,sc7180-mpss-pas
+      - qcom,sc7280-adsp-pas
+      - qcom,sc7280-cdsp-pas
       - qcom,sc7280-mpss-pas
+      - qcom,sc7280-wpss-pas
 
   reg:
     maxItems: 1
@@ -75,6 +78,7 @@ allOf:
         compatible:
           enum:
             - qcom,sc7180-adsp-pas
+            - qcom,sc7280-adsp-pas
     then:
       properties:
         power-domains:
@@ -120,6 +124,23 @@ allOf:
             - const: cx
             - const: mss
 
+  - if:
+      properties:
+        compatible:
+          enum:
+            - qcom,sc7280-cdsp-pas
+            - qcom,sc7280-wpss-pas
+    then:
+      properties:
+        power-domains:
+          items:
+            - description: CX power domain
+            - description: MX power domain
+        power-domain-names:
+          items:
+            - const: cx
+            - const: mx
+
 unevaluatedProperties: false
 
 examples:
-- 
GitLab


From 300ed425dfa99f6926299ec196a1eedf05f47b21 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Fri, 8 Dec 2023 16:08:02 +0100
Subject: [PATCH 1509/4076] remoteproc: qcom_q6v5_pas: Add SC7280 ADSP, CDSP &
 WPSS

Add support for the ADSP, CDSP and WPSS remoteprocs found on the SC7280
SoC using the q6v5-pas driver.

This driver can be used on regular LA ("Linux Android") based releases,
however the SC7280 ChromeOS devices need different driver support due to
firmware differences.

Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Link: https://lore.kernel.org/r/20231208-sc7280-remoteprocs-v3-6-6aa394d33edf@fairphone.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_q6v5_pas.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 913a5d2068e8c..a9dd58608052c 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -1165,6 +1165,22 @@ static const struct adsp_data sm8550_mpss_resource = {
 	.region_assign_idx = 2,
 };
 
+static const struct adsp_data sc7280_wpss_resource = {
+	.crash_reason_smem = 626,
+	.firmware_name = "wpss.mdt",
+	.pas_id = 6,
+	.auto_boot = true,
+	.proxy_pd_names = (char*[]){
+		"cx",
+		"mx",
+		NULL
+	},
+	.load_state = "wpss",
+	.ssr_name = "wpss",
+	.sysmon_name = "wpss",
+	.ssctl_id = 0x19,
+};
+
 static const struct of_device_id adsp_of_match[] = {
 	{ .compatible = "qcom,msm8226-adsp-pil", .data = &adsp_resource_init},
 	{ .compatible = "qcom,msm8953-adsp-pil", .data = &msm8996_adsp_resource},
@@ -1178,7 +1194,10 @@ static const struct of_device_id adsp_of_match[] = {
 	{ .compatible = "qcom,qcs404-wcss-pas", .data = &wcss_resource_init },
 	{ .compatible = "qcom,sc7180-adsp-pas", .data = &sm8250_adsp_resource},
 	{ .compatible = "qcom,sc7180-mpss-pas", .data = &mpss_resource_init},
+	{ .compatible = "qcom,sc7280-adsp-pas", .data = &sm8350_adsp_resource},
+	{ .compatible = "qcom,sc7280-cdsp-pas", .data = &sm6350_cdsp_resource},
 	{ .compatible = "qcom,sc7280-mpss-pas", .data = &mpss_resource_init},
+	{ .compatible = "qcom,sc7280-wpss-pas", .data = &sc7280_wpss_resource},
 	{ .compatible = "qcom,sc8180x-adsp-pas", .data = &sm8150_adsp_resource},
 	{ .compatible = "qcom,sc8180x-cdsp-pas", .data = &sm8150_cdsp_resource},
 	{ .compatible = "qcom,sc8180x-mpss-pas", .data = &sc8180x_mpss_resource},
-- 
GitLab


From af838635a3eb9b1bc0d98599c101ebca98f31311 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 27 Nov 2023 23:36:50 -0600
Subject: [PATCH 1510/4076] rtc: mc146818-lib: Adjust failure return code for
 mc146818_get_time()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

mc146818_get_time() calls mc146818_avoid_UIP() to avoid fetching the
time while RTC update is in progress (UIP). When this fails, the return
code is -EIO, but actually there was no IO failure.

The reason for the return from mc146818_avoid_UIP() is that the UIP
wasn't cleared in the time period. Adjust the return code to -ETIMEDOUT
to match the behavior.

Tested-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Reviewed-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Acked-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Cc:  <stable@vger.kernel.org>
Fixes: 2a61b0ac5493 ("rtc: mc146818-lib: refactor mc146818_get_time")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20231128053653.101798-2-mario.limonciello@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-mc146818-lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c
index f1c09f1db044c..43a28e82674e8 100644
--- a/drivers/rtc/rtc-mc146818-lib.c
+++ b/drivers/rtc/rtc-mc146818-lib.c
@@ -138,7 +138,7 @@ int mc146818_get_time(struct rtc_time *time)
 
 	if (!mc146818_avoid_UIP(mc146818_get_time_callback, &p)) {
 		memset(time, 0, sizeof(*time));
-		return -EIO;
+		return -ETIMEDOUT;
 	}
 
 	if (!(p.ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-- 
GitLab


From 1311a8f0d4b23f58bbababa13623aa40b8ad4e0c Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 27 Nov 2023 23:36:51 -0600
Subject: [PATCH 1511/4076] rtc: Adjust failure return code for
 cmos_set_alarm()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When mc146818_avoid_UIP() fails to return a valid value, this is because
UIP didn't clear in the timeout period. Adjust the return code in this
case to -ETIMEDOUT.

Tested-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Reviewed-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Acked-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Cc:  <stable@vger.kernel.org>
Fixes: cdedc45c579f ("rtc: cmos: avoid UIP when reading alarm time")
Fixes: cd17420ebea5 ("rtc: cmos: avoid UIP when writing alarm time")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20231128053653.101798-3-mario.limonciello@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-cmos.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 696cfa7025ded..2a1a83caf081a 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -292,7 +292,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t)
 
 	/* This not only a rtc_op, but also called directly */
 	if (!is_valid_irq(cmos->irq))
-		return -EIO;
+		return -ETIMEDOUT;
 
 	/* Basic alarms only support hour, minute, and seconds fields.
 	 * Some also support day and month, for alarms up to a year in
@@ -557,7 +557,7 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	 * Use mc146818_avoid_UIP() to avoid this.
 	 */
 	if (!mc146818_avoid_UIP(cmos_set_alarm_callback, &p))
-		return -EIO;
+		return -ETIMEDOUT;
 
 	cmos->alarm_expires = rtc_tm_to_time64(&t->time);
 
-- 
GitLab


From 120931db07b49252aba2073096b595482d71857c Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 27 Nov 2023 23:36:52 -0600
Subject: [PATCH 1512/4076] rtc: Add support for configuring the UIP timeout
 for RTC reads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The UIP timeout is hardcoded to 10ms for all RTC reads, but in some
contexts this might not be enough time. Add a timeout parameter to
mc146818_get_time() and mc146818_get_time_callback().

If UIP timeout is configured by caller to be >=100 ms and a call
takes this long, log a warning.

Make all callers use 10ms to ensure no functional changes.

Cc:  <stable@vger.kernel.org> # 6.1.y
Fixes: ec5895c0f2d8 ("rtc: mc146818-lib: extract mc146818_avoid_UIP")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Reviewed-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Acked-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Link: https://lore.kernel.org/r/20231128053653.101798-4-mario.limonciello@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 arch/alpha/kernel/rtc.c        |  2 +-
 arch/x86/kernel/hpet.c         |  2 +-
 arch/x86/kernel/rtc.c          |  2 +-
 drivers/base/power/trace.c     |  2 +-
 drivers/rtc/rtc-cmos.c         |  6 +++---
 drivers/rtc/rtc-mc146818-lib.c | 37 ++++++++++++++++++++++++++--------
 include/linux/mc146818rtc.h    |  3 ++-
 7 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c
index fb3025396ac96..cfdf90bc8b3f8 100644
--- a/arch/alpha/kernel/rtc.c
+++ b/arch/alpha/kernel/rtc.c
@@ -80,7 +80,7 @@ init_rtc_epoch(void)
 static int
 alpha_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	int ret = mc146818_get_time(tm);
+	int ret = mc146818_get_time(tm, 10);
 
 	if (ret < 0) {
 		dev_err_ratelimited(dev, "unable to read current time\n");
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 41eecf180b7f4..17adad4cbe78c 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1438,7 +1438,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 	memset(&curr_time, 0, sizeof(struct rtc_time));
 
 	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) {
-		if (unlikely(mc146818_get_time(&curr_time) < 0)) {
+		if (unlikely(mc146818_get_time(&curr_time, 10) < 0)) {
 			pr_err_ratelimited("unable to read current time from RTC\n");
 			return IRQ_HANDLED;
 		}
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 1309b9b053386..961ebc7f18723 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now)
 		return;
 	}
 
-	if (mc146818_get_time(&tm)) {
+	if (mc146818_get_time(&tm, 10)) {
 		pr_err("Unable to read current time from RTC\n");
 		now->tv_sec = now->tv_nsec = 0;
 		return;
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 72b7a92337b18..c2e9253574748 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -120,7 +120,7 @@ static unsigned int read_magic_time(void)
 	struct rtc_time time;
 	unsigned int val;
 
-	if (mc146818_get_time(&time) < 0) {
+	if (mc146818_get_time(&time, 10) < 0) {
 		pr_err("Unable to read current time from RTC\n");
 		return 0;
 	}
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 2a1a83caf081a..468ccd99f218c 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -231,7 +231,7 @@ static int cmos_read_time(struct device *dev, struct rtc_time *t)
 	if (!pm_trace_rtc_valid())
 		return -EIO;
 
-	ret = mc146818_get_time(t);
+	ret = mc146818_get_time(t, 10);
 	if (ret < 0) {
 		dev_err_ratelimited(dev, "unable to read current time\n");
 		return ret;
@@ -307,7 +307,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t)
 	 *
 	 * Use the mc146818_avoid_UIP() function to avoid this.
 	 */
-	if (!mc146818_avoid_UIP(cmos_read_alarm_callback, &p))
+	if (!mc146818_avoid_UIP(cmos_read_alarm_callback, 10, &p))
 		return -EIO;
 
 	if (!(p.rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
@@ -556,7 +556,7 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	 *
 	 * Use mc146818_avoid_UIP() to avoid this.
 	 */
-	if (!mc146818_avoid_UIP(cmos_set_alarm_callback, &p))
+	if (!mc146818_avoid_UIP(cmos_set_alarm_callback, 10, &p))
 		return -ETIMEDOUT;
 
 	cmos->alarm_expires = rtc_tm_to_time64(&t->time);
diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c
index 43a28e82674e8..4c17b3cef11ea 100644
--- a/drivers/rtc/rtc-mc146818-lib.c
+++ b/drivers/rtc/rtc-mc146818-lib.c
@@ -8,26 +8,31 @@
 #include <linux/acpi.h>
 #endif
 
+#define UIP_RECHECK_DELAY		100	/* usec */
+#define UIP_RECHECK_DELAY_MS		(USEC_PER_MSEC / UIP_RECHECK_DELAY)
+#define UIP_RECHECK_LOOPS_MS(x)		(x / UIP_RECHECK_DELAY_MS)
+
 /*
  * Execute a function while the UIP (Update-in-progress) bit of the RTC is
- * unset.
+ * unset. The timeout is configurable by the caller in ms.
  *
  * Warning: callback may be executed more then once.
  */
 bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+			int timeout,
 			void *param)
 {
 	int i;
 	unsigned long flags;
 	unsigned char seconds;
 
-	for (i = 0; i < 100; i++) {
+	for (i = 0; UIP_RECHECK_LOOPS_MS(i) < timeout; i++) {
 		spin_lock_irqsave(&rtc_lock, flags);
 
 		/*
 		 * Check whether there is an update in progress during which the
 		 * readout is unspecified. The maximum update time is ~2ms. Poll
-		 * every 100 usec for completion.
+		 * for completion.
 		 *
 		 * Store the second value before checking UIP so a long lasting
 		 * NMI which happens to hit after the UIP check cannot make
@@ -37,7 +42,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 
 		if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
 			spin_unlock_irqrestore(&rtc_lock, flags);
-			udelay(100);
+			udelay(UIP_RECHECK_DELAY);
 			continue;
 		}
 
@@ -56,7 +61,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 		 */
 		if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
 			spin_unlock_irqrestore(&rtc_lock, flags);
-			udelay(100);
+			udelay(UIP_RECHECK_DELAY);
 			continue;
 		}
 
@@ -72,6 +77,10 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 		}
 		spin_unlock_irqrestore(&rtc_lock, flags);
 
+		if (UIP_RECHECK_LOOPS_MS(i) >= 100)
+			pr_warn("Reading current time from RTC took around %li ms\n",
+				UIP_RECHECK_LOOPS_MS(i));
+
 		return true;
 	}
 	return false;
@@ -84,7 +93,7 @@ EXPORT_SYMBOL_GPL(mc146818_avoid_UIP);
  */
 bool mc146818_does_rtc_work(void)
 {
-	return mc146818_avoid_UIP(NULL, NULL);
+	return mc146818_avoid_UIP(NULL, 10, NULL);
 }
 EXPORT_SYMBOL_GPL(mc146818_does_rtc_work);
 
@@ -130,13 +139,25 @@ static void mc146818_get_time_callback(unsigned char seconds, void *param_in)
 	p->ctrl = CMOS_READ(RTC_CONTROL);
 }
 
-int mc146818_get_time(struct rtc_time *time)
+/**
+ * mc146818_get_time - Get the current time from the RTC
+ * @time: pointer to struct rtc_time to store the current time
+ * @timeout: timeout value in ms
+ *
+ * This function reads the current time from the RTC and stores it in the
+ * provided struct rtc_time. The timeout parameter specifies the maximum
+ * time to wait for the RTC to become ready.
+ *
+ * Return: 0 on success, -ETIMEDOUT if the RTC did not become ready within
+ * the specified timeout, or another error code if an error occurred.
+ */
+int mc146818_get_time(struct rtc_time *time, int timeout)
 {
 	struct mc146818_get_time_callback_param p = {
 		.time = time
 	};
 
-	if (!mc146818_avoid_UIP(mc146818_get_time_callback, &p)) {
+	if (!mc146818_avoid_UIP(mc146818_get_time_callback, timeout, &p)) {
 		memset(time, 0, sizeof(*time));
 		return -ETIMEDOUT;
 	}
diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h
index b0da04fe087bb..34dfcc77f505a 100644
--- a/include/linux/mc146818rtc.h
+++ b/include/linux/mc146818rtc.h
@@ -126,10 +126,11 @@ struct cmos_rtc_board_info {
 #endif /* ARCH_RTC_LOCATION */
 
 bool mc146818_does_rtc_work(void);
-int mc146818_get_time(struct rtc_time *time);
+int mc146818_get_time(struct rtc_time *time, int timeout);
 int mc146818_set_time(struct rtc_time *time);
 
 bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+			int timeout,
 			void *param);
 
 #endif /* _MC146818RTC_H */
-- 
GitLab


From cef9ecc8e938dd48a560f7dd9be1246359248d20 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 27 Nov 2023 23:36:53 -0600
Subject: [PATCH 1513/4076] rtc: Extend timeout for waiting for UIP to clear to
 1s
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Specs don't say anything about UIP being cleared within 10ms. They
only say that UIP won't occur for another 244uS. If a long NMI occurs
while UIP is still updating it might not be possible to get valid
data in 10ms.

This has been observed in the wild that around s2idle some calls can
take up to 480ms before UIP is clear.

Adjust callers from outside an interrupt context to wait for up to a
1s instead of 10ms.

Cc:  <stable@vger.kernel.org> # 6.1.y
Fixes: ec5895c0f2d8 ("rtc: mc146818-lib: extract mc146818_avoid_UIP")
Reported-by: Carsten Hatger <xmb8dsv4@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217626
Tested-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Reviewed-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Acked-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20231128053653.101798-5-mario.limonciello@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 arch/x86/kernel/rtc.c          | 2 +-
 drivers/base/power/trace.c     | 2 +-
 drivers/rtc/rtc-cmos.c         | 2 +-
 drivers/rtc/rtc-mc146818-lib.c | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 961ebc7f18723..2e7066980f3e8 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now)
 		return;
 	}
 
-	if (mc146818_get_time(&tm, 10)) {
+	if (mc146818_get_time(&tm, 1000)) {
 		pr_err("Unable to read current time from RTC\n");
 		now->tv_sec = now->tv_nsec = 0;
 		return;
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index c2e9253574748..cd6e559648b21 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -120,7 +120,7 @@ static unsigned int read_magic_time(void)
 	struct rtc_time time;
 	unsigned int val;
 
-	if (mc146818_get_time(&time, 10) < 0) {
+	if (mc146818_get_time(&time, 1000) < 0) {
 		pr_err("Unable to read current time from RTC\n");
 		return 0;
 	}
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 468ccd99f218c..7d99cd2c37a0b 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -231,7 +231,7 @@ static int cmos_read_time(struct device *dev, struct rtc_time *t)
 	if (!pm_trace_rtc_valid())
 		return -EIO;
 
-	ret = mc146818_get_time(t, 10);
+	ret = mc146818_get_time(t, 1000);
 	if (ret < 0) {
 		dev_err_ratelimited(dev, "unable to read current time\n");
 		return ret;
diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c
index 4c17b3cef11ea..651bf3c279c74 100644
--- a/drivers/rtc/rtc-mc146818-lib.c
+++ b/drivers/rtc/rtc-mc146818-lib.c
@@ -93,7 +93,7 @@ EXPORT_SYMBOL_GPL(mc146818_avoid_UIP);
  */
 bool mc146818_does_rtc_work(void)
 {
-	return mc146818_avoid_UIP(NULL, 10, NULL);
+	return mc146818_avoid_UIP(NULL, 1000, NULL);
 }
 EXPORT_SYMBOL_GPL(mc146818_does_rtc_work);
 
-- 
GitLab


From 3767bba698707d7bad5099371b797d0fd6d39709 Mon Sep 17 00:00:00 2001
From: Jacky Huang <ychuang3@nuvoton.com>
Date: Mon, 25 Sep 2023 07:02:49 +0000
Subject: [PATCH 1514/4076] dt-bindings: rtc: Add Nuvoton ma35d1 rtc

Add documentation describing the Nuvoton ma35d1 rtc controller.

Signed-off-by: Jacky Huang <ychuang3@nuvoton.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230925070251.28-2-ychuang570808@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../bindings/rtc/nuvoton,ma35d1-rtc.yaml      | 48 +++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml

diff --git a/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml b/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml
new file mode 100644
index 0000000000000..5e4ade803eed1
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/nuvoton,ma35d1-rtc.yaml
@@ -0,0 +1,48 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/nuvoton,ma35d1-rtc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Nuvoton MA35D1 Real Time Clock
+
+maintainers:
+  - Min-Jen Chen <mjchen@nuvoton.com>
+
+allOf:
+  - $ref: rtc.yaml#
+
+properties:
+  compatible:
+    enum:
+      - nuvoton,ma35d1-rtc
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/nuvoton,ma35d1-clk.h>
+    rtc@40410000 {
+        compatible = "nuvoton,ma35d1-rtc";
+        reg = <0x40410000 0x200>;
+        interrupts = <GIC_SPI 5 IRQ_TYPE_EDGE_RISING>;
+        clocks = <&clk RTC_GATE>;
+    };
+
+...
-- 
GitLab


From dc0684adf3b6be6b20fec9295027980021d30353 Mon Sep 17 00:00:00 2001
From: Jacky Huang <ychuang3@nuvoton.com>
Date: Mon, 25 Sep 2023 07:02:51 +0000
Subject: [PATCH 1515/4076] rtc: Add driver for Nuvoton ma35d1 rtc controller

The ma35d1 rtc controller provides real-time and calendar messaging
capabilities. It supports programmable time tick and alarm match
interrupts. The time and calendar messages are expressed in BCD format.
This driver supports the built-in rtc controller of the ma35d1. It
enables setting and reading the rtc time and configuring and reading
the rtc alarm.

Signed-off-by: Jacky Huang <ychuang3@nuvoton.com>
Link: https://lore.kernel.org/r/20230925070251.28-4-ychuang570808@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/Kconfig      |  11 ++
 drivers/rtc/Makefile     |   1 +
 drivers/rtc/rtc-ma35d1.c | 324 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 336 insertions(+)
 create mode 100644 drivers/rtc/rtc-ma35d1.c

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 3814e0845e772..4e3c2fde2d6a6 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1930,6 +1930,17 @@ config RTC_DRV_TI_K3
 	  This driver can also be built as a module, if so, the module
 	  will be called "rtc-ti-k3".
 
+config RTC_DRV_MA35D1
+	tristate "Nuvoton MA35D1 RTC"
+	depends on ARCH_MA35 || COMPILE_TEST
+	select REGMAP_MMIO
+	help
+	   If you say yes here you get support for the Nuvoton MA35D1
+	   On-Chip Real Time Clock.
+
+	   This driver can also be built as a module, if so, the module
+	   will be called "rtc-ma35d1".
+
 comment "HID Sensor RTC drivers"
 
 config RTC_DRV_HID_SENSOR_TIME
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 7b03c3abfd786..6817ea4e44687 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -88,6 +88,7 @@ obj-$(CONFIG_RTC_DRV_M41T94)	+= rtc-m41t94.o
 obj-$(CONFIG_RTC_DRV_M48T35)	+= rtc-m48t35.o
 obj-$(CONFIG_RTC_DRV_M48T59)	+= rtc-m48t59.o
 obj-$(CONFIG_RTC_DRV_M48T86)	+= rtc-m48t86.o
+obj-$(CONFIG_RTC_DRV_MA35D1)	+= rtc-ma35d1.o
 obj-$(CONFIG_RTC_DRV_MAX6900)	+= rtc-max6900.o
 obj-$(CONFIG_RTC_DRV_MAX6902)	+= rtc-max6902.o
 obj-$(CONFIG_RTC_DRV_MAX6916)	+= rtc-max6916.o
diff --git a/drivers/rtc/rtc-ma35d1.c b/drivers/rtc/rtc-ma35d1.c
new file mode 100644
index 0000000000000..07c9a083a9d5d
--- /dev/null
+++ b/drivers/rtc/rtc-ma35d1.c
@@ -0,0 +1,324 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RTC driver for Nuvoton MA35D1
+ *
+ * Copyright (C) 2023 Nuvoton Technology Corp.
+ */
+
+#include <linux/bcd.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+
+/* MA35D1 RTC Control Registers */
+#define MA35_REG_RTC_INIT	0x00
+#define MA35_REG_RTC_SINFASTS	0x04
+#define MA35_REG_RTC_FREQADJ	0x08
+#define MA35_REG_RTC_TIME	0x0c
+#define MA35_REG_RTC_CAL	0x10
+#define MA35_REG_RTC_CLKFMT	0x14
+#define MA35_REG_RTC_WEEKDAY	0x18
+#define MA35_REG_RTC_TALM	0x1c
+#define MA35_REG_RTC_CALM	0x20
+#define MA35_REG_RTC_LEAPYEAR	0x24
+#define MA35_REG_RTC_INTEN	0x28
+#define MA35_REG_RTC_INTSTS	0x2c
+
+/* register MA35_REG_RTC_INIT */
+#define RTC_INIT_ACTIVE		BIT(0)
+#define RTC_INIT_MAGIC_CODE	0xa5eb1357
+
+/* register MA35_REG_RTC_CLKFMT */
+#define RTC_CLKFMT_24HEN	BIT(0)
+#define RTC_CLKFMT_DCOMPEN	BIT(16)
+
+/* register MA35_REG_RTC_INTEN */
+#define RTC_INTEN_ALMIEN	BIT(0)
+#define RTC_INTEN_UIEN		BIT(1)
+#define RTC_INTEN_CLKFIEN	BIT(24)
+#define RTC_INTEN_CLKSTIEN	BIT(25)
+
+/* register MA35_REG_RTC_INTSTS */
+#define RTC_INTSTS_ALMIF	BIT(0)
+#define RTC_INTSTS_UIF		BIT(1)
+#define RTC_INTSTS_CLKFIF	BIT(24)
+#define RTC_INTSTS_CLKSTIF	BIT(25)
+
+#define RTC_INIT_TIMEOUT	250
+
+struct ma35_rtc {
+	int irq_num;
+	void __iomem *rtc_reg;
+	struct rtc_device *rtcdev;
+};
+
+static u32 rtc_reg_read(struct ma35_rtc *p, u32 offset)
+{
+	return __raw_readl(p->rtc_reg + offset);
+}
+
+static inline void rtc_reg_write(struct ma35_rtc *p, u32 offset, u32 value)
+{
+	__raw_writel(value, p->rtc_reg + offset);
+}
+
+static irqreturn_t ma35d1_rtc_interrupt(int irq, void *data)
+{
+	struct ma35_rtc *rtc = (struct ma35_rtc *)data;
+	unsigned long events = 0, rtc_irq;
+
+	rtc_irq = rtc_reg_read(rtc, MA35_REG_RTC_INTSTS);
+
+	if (rtc_irq & RTC_INTSTS_ALMIF) {
+		rtc_reg_write(rtc, MA35_REG_RTC_INTSTS, RTC_INTSTS_ALMIF);
+		events |= RTC_AF | RTC_IRQF;
+	}
+
+	if (rtc_irq & RTC_INTSTS_UIF) {
+		rtc_reg_write(rtc, MA35_REG_RTC_INTSTS, RTC_INTSTS_UIF);
+		events |= RTC_UF | RTC_IRQF;
+	}
+
+	rtc_update_irq(rtc->rtcdev, 1, events);
+
+	return IRQ_HANDLED;
+}
+
+static int ma35d1_rtc_init(struct ma35_rtc *rtc, u32 ms_timeout)
+{
+	const unsigned long timeout = jiffies + msecs_to_jiffies(ms_timeout);
+
+	do {
+		if (rtc_reg_read(rtc, MA35_REG_RTC_INIT) & RTC_INIT_ACTIVE)
+			return 0;
+
+		rtc_reg_write(rtc, MA35_REG_RTC_INIT, RTC_INIT_MAGIC_CODE);
+
+		mdelay(1);
+
+	} while (time_before(jiffies, timeout));
+
+	return -ETIMEDOUT;
+}
+
+static int ma35d1_alarm_irq_enable(struct device *dev, u32 enabled)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	u32 reg_ien;
+
+	reg_ien = rtc_reg_read(rtc, MA35_REG_RTC_INTEN);
+
+	if (enabled)
+		rtc_reg_write(rtc, MA35_REG_RTC_INTEN, reg_ien | RTC_INTEN_ALMIEN);
+	else
+		rtc_reg_write(rtc, MA35_REG_RTC_INTEN, reg_ien & ~RTC_INTEN_ALMIEN);
+
+	return 0;
+}
+
+static int ma35d1_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	u32 time, cal, wday;
+
+	do {
+		time = rtc_reg_read(rtc, MA35_REG_RTC_TIME);
+		cal  = rtc_reg_read(rtc, MA35_REG_RTC_CAL);
+		wday = rtc_reg_read(rtc, MA35_REG_RTC_WEEKDAY);
+	} while (time != rtc_reg_read(rtc, MA35_REG_RTC_TIME) ||
+		 cal != rtc_reg_read(rtc, MA35_REG_RTC_CAL));
+
+	tm->tm_mday = bcd2bin(cal >> 0);
+	tm->tm_wday = wday;
+	tm->tm_mon = bcd2bin(cal >> 8);
+	tm->tm_mon = tm->tm_mon - 1;
+	tm->tm_year = bcd2bin(cal >> 16) + 100;
+
+	tm->tm_sec = bcd2bin(time >> 0);
+	tm->tm_min = bcd2bin(time >> 8);
+	tm->tm_hour = bcd2bin(time >> 16);
+
+	return rtc_valid_tm(tm);
+}
+
+static int ma35d1_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	u32 val;
+
+	val = bin2bcd(tm->tm_mday) << 0 | bin2bcd(tm->tm_mon + 1) << 8 |
+	      bin2bcd(tm->tm_year - 100) << 16;
+	rtc_reg_write(rtc, MA35_REG_RTC_CAL, val);
+
+	val = bin2bcd(tm->tm_sec) << 0 | bin2bcd(tm->tm_min) << 8 |
+	      bin2bcd(tm->tm_hour) << 16;
+	rtc_reg_write(rtc, MA35_REG_RTC_TIME, val);
+
+	val = tm->tm_wday;
+	rtc_reg_write(rtc, MA35_REG_RTC_WEEKDAY, val);
+
+	return 0;
+}
+
+static int ma35d1_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	u32 talm, calm;
+
+	talm = rtc_reg_read(rtc, MA35_REG_RTC_TALM);
+	calm = rtc_reg_read(rtc, MA35_REG_RTC_CALM);
+
+	alrm->time.tm_mday = bcd2bin(calm >> 0);
+	alrm->time.tm_mon = bcd2bin(calm >> 8);
+	alrm->time.tm_mon = alrm->time.tm_mon - 1;
+
+	alrm->time.tm_year = bcd2bin(calm >> 16) + 100;
+
+	alrm->time.tm_sec = bcd2bin(talm >> 0);
+	alrm->time.tm_min = bcd2bin(talm >> 8);
+	alrm->time.tm_hour = bcd2bin(talm >> 16);
+
+	return rtc_valid_tm(&alrm->time);
+}
+
+static int ma35d1_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct ma35_rtc *rtc = dev_get_drvdata(dev);
+	unsigned long val;
+
+	val = bin2bcd(alrm->time.tm_mday) << 0 | bin2bcd(alrm->time.tm_mon + 1) << 8 |
+	      bin2bcd(alrm->time.tm_year - 100) << 16;
+	rtc_reg_write(rtc, MA35_REG_RTC_CALM, val);
+
+	val = bin2bcd(alrm->time.tm_sec) << 0 | bin2bcd(alrm->time.tm_min) << 8 |
+	      bin2bcd(alrm->time.tm_hour) << 16;
+	rtc_reg_write(rtc, MA35_REG_RTC_TALM, val);
+
+	ma35d1_alarm_irq_enable(dev, alrm->enabled);
+
+	return 0;
+}
+
+static const struct rtc_class_ops ma35d1_rtc_ops = {
+	.read_time = ma35d1_rtc_read_time,
+	.set_time = ma35d1_rtc_set_time,
+	.read_alarm = ma35d1_rtc_read_alarm,
+	.set_alarm = ma35d1_rtc_set_alarm,
+	.alarm_irq_enable = ma35d1_alarm_irq_enable,
+};
+
+static int ma35d1_rtc_probe(struct platform_device *pdev)
+{
+	struct ma35_rtc *rtc;
+	struct clk *clk;
+	u32 regval;
+	int ret;
+
+	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
+
+	rtc->rtc_reg = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(rtc->rtc_reg))
+		return PTR_ERR(rtc->rtc_reg);
+
+	clk = of_clk_get(pdev->dev.of_node, 0);
+	if (IS_ERR(clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(clk), "failed to find rtc clock\n");
+
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		return ret;
+
+	if (!(rtc_reg_read(rtc, MA35_REG_RTC_INIT) & RTC_INIT_ACTIVE)) {
+		ret = ma35d1_rtc_init(rtc, RTC_INIT_TIMEOUT);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret, "rtc init failed\n");
+	}
+
+	rtc->irq_num = platform_get_irq(pdev, 0);
+
+	ret = devm_request_irq(&pdev->dev, rtc->irq_num, ma35d1_rtc_interrupt,
+			       IRQF_NO_SUSPEND, "ma35d1rtc", rtc);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to request rtc irq\n");
+
+	platform_set_drvdata(pdev, rtc);
+
+	device_init_wakeup(&pdev->dev, true);
+
+	rtc->rtcdev = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(rtc->rtcdev))
+		return PTR_ERR(rtc->rtcdev);
+
+	rtc->rtcdev->ops = &ma35d1_rtc_ops;
+	rtc->rtcdev->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	rtc->rtcdev->range_max = RTC_TIMESTAMP_END_2099;
+
+	ret = devm_rtc_register_device(rtc->rtcdev);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to register rtc device\n");
+
+	regval = rtc_reg_read(rtc, MA35_REG_RTC_INTEN);
+	regval |= RTC_INTEN_UIEN;
+	rtc_reg_write(rtc, MA35_REG_RTC_INTEN, regval);
+
+	return 0;
+}
+
+static int ma35d1_rtc_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct ma35_rtc *rtc = platform_get_drvdata(pdev);
+	u32 regval;
+
+	if (device_may_wakeup(&pdev->dev))
+		enable_irq_wake(rtc->irq_num);
+
+	regval = rtc_reg_read(rtc, MA35_REG_RTC_INTEN);
+	regval &= ~RTC_INTEN_UIEN;
+	rtc_reg_write(rtc, MA35_REG_RTC_INTEN, regval);
+
+	return 0;
+}
+
+static int ma35d1_rtc_resume(struct platform_device *pdev)
+{
+	struct ma35_rtc *rtc = platform_get_drvdata(pdev);
+	u32 regval;
+
+	if (device_may_wakeup(&pdev->dev))
+		disable_irq_wake(rtc->irq_num);
+
+	regval = rtc_reg_read(rtc, MA35_REG_RTC_INTEN);
+	regval |= RTC_INTEN_UIEN;
+	rtc_reg_write(rtc, MA35_REG_RTC_INTEN, regval);
+
+	return 0;
+}
+
+static const struct of_device_id ma35d1_rtc_of_match[] = {
+	{ .compatible = "nuvoton,ma35d1-rtc", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ma35d1_rtc_of_match);
+
+static struct platform_driver ma35d1_rtc_driver = {
+	.suspend    = ma35d1_rtc_suspend,
+	.resume     = ma35d1_rtc_resume,
+	.probe      = ma35d1_rtc_probe,
+	.driver		= {
+		.name	= "rtc-ma35d1",
+		.of_match_table = ma35d1_rtc_of_match,
+	},
+};
+
+module_platform_driver(ma35d1_rtc_driver);
+
+MODULE_AUTHOR("Ming-Jen Chen <mjchen@nuvoton.com>");
+MODULE_DESCRIPTION("MA35D1 RTC driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 2217fffcd63f86776c985d42e76daa43a56abdf1 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@wdc.com>
Date: Tue, 28 Nov 2023 14:22:30 +0100
Subject: [PATCH 1516/4076] PCI: dwc: endpoint: Fix dw_pcie_ep_raise_msix_irq()
 alignment support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 6f5e193bfb55 ("PCI: dwc: Fix dw_pcie_ep_raise_msix_irq() to get
correct MSI-X table address") modified dw_pcie_ep_raise_msix_irq() to
support iATUs which require a specific alignment.

However, this support cannot have been properly tested.

The whole point is for the iATU to map an address that is aligned,
using dw_pcie_ep_map_addr(), and then let the writel() write to
ep->msi_mem + aligned_offset.

Thus, modify the address that is mapped such that it is aligned.
With this change, dw_pcie_ep_raise_msix_irq() matches the logic in
dw_pcie_ep_raise_msi_irq().

Link: https://lore.kernel.org/linux-pci/20231128132231.2221614-1-nks@flawful.org
Fixes: 6f5e193bfb55 ("PCI: dwc: Fix dw_pcie_ep_raise_msix_irq() to get correct MSI-X table address")
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: stable@vger.kernel.org # 5.7
Cc: Kishon Vijay Abraham I <kishon@kernel.org>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index f6207989fc6ad..bc94d7f395357 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -615,6 +615,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	}
 
 	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
+	msg_addr &= ~aligned_offset;
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
 				  epc->mem->window.page_size);
 	if (ret)
-- 
GitLab


From b642e081f46cc95c7f1468cab1ea3c2d5e11fdab Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Mon, 30 Oct 2023 14:12:42 +0800
Subject: [PATCH 1517/4076] PCI: xilinx-xdma: Remove redundant dev_err()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is no need to call the dev_err() function directly to print a
custom message when handling an error from either the platform_get_irq()
or platform_get_irq_byname() functions as both are going to display an
appropriate error message in case of a failure.

  ./drivers/pci/controller/pcie-xilinx-dma-pl.c:688:2-9: line 688 is redundant because platform_get_irq() already prints an error
  ./drivers/pci/controller/pcie-xilinx-dma-pl.c:702:2-9: line 702 is redundant because platform_get_irq() already prints an error

Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=7074
Link: https://lore.kernel.org/linux-pci/20231030061242.51475-1-yang.lee@linux.alibaba.com
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/pcie-xilinx-dma-pl.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/controller/pcie-xilinx-dma-pl.c b/drivers/pci/controller/pcie-xilinx-dma-pl.c
index 2f7d676c683cc..4e49b12a2e2a6 100644
--- a/drivers/pci/controller/pcie-xilinx-dma-pl.c
+++ b/drivers/pci/controller/pcie-xilinx-dma-pl.c
@@ -684,10 +684,8 @@ static int xilinx_request_msi_irq(struct pl_dma_pcie *port)
 	int ret;
 
 	port->msi.irq_msi0 = platform_get_irq_byname(pdev, "msi0");
-	if (port->msi.irq_msi0 <= 0) {
-		dev_err(dev, "Unable to find msi0 IRQ line\n");
+	if (port->msi.irq_msi0 <= 0)
 		return port->msi.irq_msi0;
-	}
 
 	ret = devm_request_irq(dev, port->msi.irq_msi0, xilinx_pl_dma_pcie_msi_handler_low,
 			       IRQF_SHARED | IRQF_NO_THREAD, "xlnx-pcie-dma-pl",
@@ -698,10 +696,8 @@ static int xilinx_request_msi_irq(struct pl_dma_pcie *port)
 	}
 
 	port->msi.irq_msi1 = platform_get_irq_byname(pdev, "msi1");
-	if (port->msi.irq_msi1 <= 0) {
-		dev_err(dev, "Unable to find msi1 IRQ line\n");
+	if (port->msi.irq_msi1 <= 0)
 		return port->msi.irq_msi1;
-	}
 
 	ret = devm_request_irq(dev, port->msi.irq_msi1, xilinx_pl_dma_pcie_msi_handler_high,
 			       IRQF_SHARED | IRQF_NO_THREAD, "xlnx-pcie-dma-pl",
-- 
GitLab


From 1565c881c3df053447309ff69ec7fd5dee2085e4 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:45 +0000
Subject: [PATCH 1518/4076] KVM: arm64: Explicitly trap unsupported HFGxTR_EL2
 features

Do not rely on the value of __HFGRTR_EL2_nMASK to trap
unsupported features, since the nMASK can (and will) change as
new traps are added and as its value is updated. Instead,
explicitly specify the trap bits.

Suggested-by: Joey Gouly <joey.gouly@arm.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-6-tabba@google.com
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index f99d8af0b9afb..7b4909dfd1f56 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -110,12 +110,15 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 		compute_clr_set(vcpu, HFGWTR_EL2, w_clr, w_set);
 	}
 
-	/* The default is not to trap anything but ACCDATA_EL1 */
-	r_val = __HFGRTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	/* The default to trap everything not handled or supported in KVM. */
+	tmp = HFGxTR_EL2_nAMAIR2_EL1 | HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nS2POR_EL1 |
+	      HFGxTR_EL2_nPOR_EL1 | HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nACCDATA_EL1;
+
+	r_val = __HFGRTR_EL2_nMASK & ~tmp;
 	r_val |= r_set;
 	r_val &= ~r_clr;
 
-	w_val = __HFGWTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	w_val = __HFGWTR_EL2_nMASK & ~tmp;
 	w_val |= w_set;
 	w_val &= ~w_clr;
 
-- 
GitLab


From 9d400eb722bd1be712b007149ff1d8fb2d6470db Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:46 +0000
Subject: [PATCH 1519/4076] KVM: arm64: Add missing HFGxTR_EL2 FGT entries to
 nested virt

Add the missing nested virt FGT table entries HFGxTR_EL2. Based
on DDI0601 2023-09.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-7-tabba@google.com
---
 arch/arm64/kvm/emulate-nested.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 06185216a297d..8b473a1bbc110 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -1042,10 +1042,20 @@ enum fg_filter_id {
 
 static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	/* HFGRTR_EL2, HFGWTR_EL2 */
+	SR_FGT(SYS_AMAIR2_EL1,		HFGxTR, nAMAIR2_EL1, 0),
+	SR_FGT(SYS_MAIR2_EL1,		HFGxTR, nMAIR2_EL1, 0),
+	SR_FGT(SYS_S2POR_EL1,		HFGxTR, nS2POR_EL1, 0),
+	SR_FGT(SYS_POR_EL1,		HFGxTR, nPOR_EL1, 0),
+	SR_FGT(SYS_POR_EL0,		HFGxTR, nPOR_EL0, 0),
 	SR_FGT(SYS_PIR_EL1,		HFGxTR, nPIR_EL1, 0),
 	SR_FGT(SYS_PIRE0_EL1,		HFGxTR, nPIRE0_EL1, 0),
+	SR_FGT(SYS_RCWMASK_EL1,		HFGxTR, nRCWMASK_EL1, 0),
 	SR_FGT(SYS_TPIDR2_EL0,		HFGxTR, nTPIDR2_EL0, 0),
 	SR_FGT(SYS_SMPRI_EL1,		HFGxTR, nSMPRI_EL1, 0),
+	SR_FGT(SYS_GCSCR_EL1,		HFGxTR, nGCS_EL1, 0),
+	SR_FGT(SYS_GCSPR_EL1,		HFGxTR, nGCS_EL1, 0),
+	SR_FGT(SYS_GCSCRE0_EL1,		HFGxTR, nGCS_EL0, 0),
+	SR_FGT(SYS_GCSPR_EL0,		HFGxTR, nGCS_EL0, 0),
 	SR_FGT(SYS_ACCDATA_EL1,		HFGxTR, nACCDATA_EL1, 0),
 	SR_FGT(SYS_ERXADDR_EL1,		HFGxTR, ERXADDR_EL1, 1),
 	SR_FGT(SYS_ERXPFGCDN_EL1,	HFGxTR, ERXPFGCDN_EL1, 1),
-- 
GitLab


From 863ac38984a822ff9f4337d70853d771dcf7aae5 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:47 +0000
Subject: [PATCH 1520/4076] KVM: arm64: Add missing HFGITR_EL2 FGT entries to
 nested virt

Add the missing nested virt FGT table entries HFGITR_EL2. Based
on DDI0601 and DDI0602 2023-09.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-8-tabba@google.com
---
 arch/arm64/kvm/emulate-nested.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 8b473a1bbc110..89901550db342 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -1117,6 +1117,11 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_AFSR1_EL1, 		HFGxTR, AFSR1_EL1, 1),
 	SR_FGT(SYS_AFSR0_EL1, 		HFGxTR, AFSR0_EL1, 1),
 	/* HFGITR_EL2 */
+	SR_FGT(OP_AT_S1E1A, 		HFGITR, ATS1E1A, 1),
+	SR_FGT(OP_COSP_RCTX, 		HFGITR, COSPRCTX, 1),
+	SR_FGT(OP_GCSPUSHX, 		HFGITR, nGCSEPP, 0),
+	SR_FGT(OP_GCSPOPX, 		HFGITR, nGCSEPP, 0),
+	SR_FGT(OP_GCSPUSHM, 		HFGITR, nGCSPUSHM_EL1, 0),
 	SR_FGT(OP_BRB_IALL, 		HFGITR, nBRBIALL, 0),
 	SR_FGT(OP_BRB_INJ, 		HFGITR, nBRBINJ, 0),
 	SR_FGT(SYS_DC_CVAC, 		HFGITR, DCCVAC, 1),
-- 
GitLab


From f9d6ed0213021ea00af30efbfa33e9a06c0610f2 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:48 +0000
Subject: [PATCH 1521/4076] KVM: arm64: Add bit masks for HAFGRTR_EL2

To support HAFGRTR_EL2 supported in nested virt in the following
patch, first add its bitmask definitions based on DDI0601 2023-09.

Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-9-tabba@google.com
---
 arch/arm64/include/asm/kvm_arm.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index b85f46a73e21b..7de0a70626255 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -370,6 +370,10 @@
 #define __HDFGWTR_EL2_MASK	~__HDFGWTR_EL2_nMASK
 #define __HDFGWTR_EL2_nMASK	GENMASK(62, 60)
 
+#define __HAFGRTR_EL2_RES0	(GENMASK(63, 50) | GENMASK(16, 5))
+#define __HAFGRTR_EL2_MASK	(GENMASK(49, 17) | GENMASK(4, 0))
+#define __HAFGRTR_EL2_nMASK	0UL
+
 /* Similar definitions for HCRX_EL2 */
 #define __HCRX_EL2_RES0		(GENMASK(63, 16) | GENMASK(13, 12))
 #define __HCRX_EL2_MASK		(0)
-- 
GitLab


From 58ff9c5acb4aef58e118bbf39736cc4d6c11a3d3 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 22 Nov 2023 15:03:51 +0900
Subject: [PATCH 1522/4076] PCI: Rename PCI_IRQ_LEGACY to PCI_IRQ_INTX

Rename PCI_IRQ_LEGACY to PCI_IRQ_INTX to be more explicit about the type
of IRQ being referenced as well as to match the PCI specifications
terms. Redefine PCI_IRQ_LEGACY as an alias to PCI_IRQ_INTX to avoid the
need for doing the renaming tree-wide. New drivers and new code should
now prefer using PCI_IRQ_INTX instead of PCI_IRQ_LEGACY.

Link: https://lore.kernel.org/r/20231122060406.14695-2-dlemoal@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 include/linux/pci.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc8679..9ab4b46c0d19c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1073,11 +1073,13 @@ enum {
 	PCI_SCAN_ALL_PCIE_DEVS	= 0x00000040,	/* Scan all, not just dev 0 */
 };
 
-#define PCI_IRQ_LEGACY		(1 << 0) /* Allow legacy interrupts */
+#define PCI_IRQ_INTX		(1 << 0) /* Allow INTx interrupts */
 #define PCI_IRQ_MSI		(1 << 1) /* Allow MSI interrupts */
 #define PCI_IRQ_MSIX		(1 << 2) /* Allow MSI-X interrupts */
 #define PCI_IRQ_AFFINITY	(1 << 3) /* Auto-assign affinity */
 
+#define PCI_IRQ_LEGACY		PCI_IRQ_INTX /* Deprecated! Use PCI_IRQ_INTX */
+
 /* These external functions are only available when PCI support is enabled */
 #ifdef CONFIG_PCI
 
-- 
GitLab


From 74955cb8ccc38539f8c029336e07e6b43b6a942e Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:52 +0900
Subject: [PATCH 1523/4076] PCI: endpoint: Drop PCI_EPC_IRQ_XXX definitions

linux/pci.h defines the IRQ flags PCI_IRQ_INTX, PCI_IRQ_MSI and
PCI_IRQ_MSIX. Let's use these flags directly instead of the endpoint
definitions provided by enum pci_epc_irq_type. This removes the need
for defining this enum type completely.

Link: https://lore.kernel.org/r/20231122060406.14695-3-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/cadence/pcie-cadence-ep.c  |  9 ++++-----
 drivers/pci/controller/dwc/pci-dra7xx.c           |  6 +++---
 drivers/pci/controller/dwc/pci-imx6.c             |  9 ++++-----
 drivers/pci/controller/dwc/pci-keystone.c         |  9 ++++-----
 drivers/pci/controller/dwc/pci-layerscape-ep.c    |  8 ++++----
 drivers/pci/controller/dwc/pcie-artpec6.c         |  8 ++++----
 drivers/pci/controller/dwc/pcie-designware-ep.c   |  2 +-
 drivers/pci/controller/dwc/pcie-designware-plat.c |  9 ++++-----
 drivers/pci/controller/dwc/pcie-designware.h      |  2 +-
 drivers/pci/controller/dwc/pcie-keembay.c         | 13 ++++++-------
 drivers/pci/controller/dwc/pcie-qcom-ep.c         |  6 +++---
 drivers/pci/controller/dwc/pcie-rcar-gen4.c       |  7 +++----
 drivers/pci/controller/dwc/pcie-tegra194.c        |  9 ++++-----
 drivers/pci/controller/dwc/pcie-uniphier-ep.c     |  7 +++----
 drivers/pci/controller/pcie-rcar-ep.c             |  7 +++----
 drivers/pci/controller/pcie-rockchip-ep.c         |  7 +++----
 drivers/pci/endpoint/functions/pci-epf-mhi.c      |  2 +-
 drivers/pci/endpoint/functions/pci-epf-ntb.c      |  4 ++--
 drivers/pci/endpoint/functions/pci-epf-test.c     |  6 +++---
 drivers/pci/endpoint/functions/pci-epf-vntb.c     |  7 ++-----
 drivers/pci/endpoint/pci-epc-core.c               |  2 +-
 include/linux/pci-epc.h                           | 11 ++---------
 22 files changed, 65 insertions(+), 85 deletions(-)

diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index 3142feb8ac195..3d71d687ea649 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -532,25 +532,24 @@ static int cdns_pcie_ep_send_msix_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
 }
 
 static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
 	struct device *dev = pcie->dev;
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		if (vfn > 0) {
 			dev_err(dev, "Cannot raise legacy interrupts for VF\n");
 			return -EINVAL;
 		}
 		return cdns_pcie_ep_send_legacy_irq(ep, fn, vfn, 0);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return cdns_pcie_ep_send_msi_irq(ep, fn, vfn, interrupt_num);
 
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return cdns_pcie_ep_send_msix_irq(ep, fn, vfn, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index b445ffe95e3f0..f257a42f33146 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -404,16 +404,16 @@ static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx,
 }
 
 static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				 enum pci_epc_irq_type type, u16 interrupt_num)
+				 unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		dra7xx_pcie_raise_legacy_irq(dra7xx);
 		break;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		dra7xx_pcie_raise_msi_irq(dra7xx, interrupt_num);
 		break;
 	default:
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 74703362aeec7..a5365ab8897e3 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -1058,17 +1058,16 @@ static void imx6_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int imx6_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 0def919f89faf..84f6a4acee07a 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -900,20 +900,19 @@ static void ks_pcie_am654_raise_legacy_irq(struct keystone_pcie *ks_pcie)
 }
 
 static int ks_pcie_am654_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				   enum pci_epc_irq_type type,
-				   u16 interrupt_num)
+				   unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		ks_pcie_am654_raise_legacy_irq(ks_pcie);
 		break;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 		break;
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 		break;
 	default:
diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 3d3c50ef4b6ff..5f78a94152863 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -166,16 +166,16 @@ static void ls_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				enum pci_epc_irq_type type, u16 interrupt_num)
+				unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq_doorbell(ep, func_no,
 							  interrupt_num);
 	default:
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 9b572a2b2c9a5..fc426182443a3 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -352,15 +352,15 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type, u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		dev_err(pci->dev, "EP cannot trigger legacy IRQs\n");
+	case PCI_IRQ_INTX:
+		dev_err(pci->dev, "EP cannot trigger INTx IRQs\n");
 		return -EINVAL;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index f6207989fc6ad..87759c899fab2 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -443,7 +443,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 }
 
 static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-				enum pci_epc_irq_type type, u16 interrupt_num)
+				unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index b625841e98aa0..c83968aa0149d 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -42,17 +42,16 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				     enum pci_epc_irq_type type,
-				     u16 interrupt_num)
+				     unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 55ff76e3d3846..ffb9a62f3179e 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -335,7 +335,7 @@ struct dw_pcie_ep_ops {
 	void	(*ep_init)(struct dw_pcie_ep *ep);
 	void	(*deinit)(struct dw_pcie_ep *ep);
 	int	(*raise_irq)(struct dw_pcie_ep *ep, u8 func_no,
-			     enum pci_epc_irq_type type, u16 interrupt_num);
+			     unsigned int type, u16 interrupt_num);
 	const struct pci_epc_features* (*get_features)(struct dw_pcie_ep *ep);
 	/*
 	 * Provide a method to implement the different func config space
diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c
index 289bff99d7628..8e0e2e28ef67d 100644
--- a/drivers/pci/controller/dwc/pcie-keembay.c
+++ b/drivers/pci/controller/dwc/pcie-keembay.c
@@ -289,19 +289,18 @@ static void keembay_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int keembay_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				     enum pci_epc_irq_type type,
-				     u16 interrupt_num)
+				     unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		/* Legacy interrupts are not supported in Keem Bay */
-		dev_err(pci->dev, "Legacy IRQ is not supported\n");
+	case PCI_IRQ_INTX:
+		/* INTx interrupts are not supported in Keem Bay */
+		dev_err(pci->dev, "INTx IRQ is not supported\n");
 		return -EINVAL;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "Unknown IRQ type %d\n", type);
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 9e58f055199ad..2e5ab5fef3103 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -726,14 +726,14 @@ static int qcom_pcie_ep_enable_irq_resources(struct platform_device *pdev,
 }
 
 static int qcom_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type, u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "Unknown IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 3bc45e513b3d5..25354a82674d2 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -362,15 +362,14 @@ static void rcar_gen4_pcie_ep_deinit(struct dw_pcie_ep *ep)
 }
 
 static int rcar_gen4_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				       enum pci_epc_irq_type type,
-				       u16 interrupt_num)
+				       unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *dw = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(dw->dev, "Unknown IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 0fe113598ebbc..a1f37d2d77986 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -1979,20 +1979,19 @@ static int tegra_pcie_ep_raise_msix_irq(struct tegra_pcie_dw *pcie, u16 irq)
 }
 
 static int tegra_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				   enum pci_epc_irq_type type,
-				   u16 interrupt_num)
+				   unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return tegra_pcie_ep_raise_legacy_irq(pcie, interrupt_num);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return tegra_pcie_ep_raise_msi_irq(pcie, interrupt_num);
 
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return tegra_pcie_ep_raise_msix_irq(pcie, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
index cba3c88fcf395..d47236d5678d2 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier-ep.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
@@ -256,15 +256,14 @@ static int uniphier_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep,
 }
 
 static int uniphier_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				      enum pci_epc_irq_type type,
-				      u16 interrupt_num)
+				      unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return uniphier_pcie_ep_raise_legacy_irq(ep);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return uniphier_pcie_ep_raise_msi_irq(ep, func_no,
 						      interrupt_num);
 	default:
diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c
index 7034c0ff23d0d..e6909271def79 100644
--- a/drivers/pci/controller/pcie-rcar-ep.c
+++ b/drivers/pci/controller/pcie-rcar-ep.c
@@ -402,16 +402,15 @@ static int rcar_pcie_ep_assert_msi(struct rcar_pcie *pcie,
 }
 
 static int rcar_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return rcar_pcie_ep_assert_intx(ep, fn, 0);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return rcar_pcie_ep_assert_msi(&ep->pcie, fn, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 0af0e965fb57e..95b1c8ef59c3e 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -407,15 +407,14 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn,
 }
 
 static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				      enum pci_epc_irq_type type,
-				      u16 interrupt_num)
+				      unsigned int type, u16 interrupt_num)
 {
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return rockchip_pcie_ep_send_legacy_irq(ep, fn, 0);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return rockchip_pcie_ep_send_msi_irq(ep, fn, interrupt_num);
 	default:
 		return -EINVAL;
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index b7b9d3e21f97d..b9f8d2858cb70 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -205,7 +205,7 @@ static void pci_epf_mhi_raise_irq(struct mhi_ep_cntrl *mhi_cntrl, u32 vector)
 	 * MHI supplies 0 based MSI vectors but the API expects the vector
 	 * number to start from 1, so we need to increment the vector by 1.
 	 */
-	pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, PCI_EPC_IRQ_MSI,
+	pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, PCI_IRQ_MSI,
 			  vector + 1);
 }
 
diff --git a/drivers/pci/endpoint/functions/pci-epf-ntb.c b/drivers/pci/endpoint/functions/pci-epf-ntb.c
index 9aac2c6f3bb99..fad00b1a8335e 100644
--- a/drivers/pci/endpoint/functions/pci-epf-ntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-ntb.c
@@ -140,9 +140,9 @@ static struct pci_epf_header epf_ntb_header = {
 static int epf_ntb_link_up(struct epf_ntb *ntb, bool link_up)
 {
 	enum pci_epc_interface_type type;
-	enum pci_epc_irq_type irq_type;
 	struct epf_ntb_epc *ntb_epc;
 	struct epf_ntb_ctrl *ctrl;
+	unsigned int irq_type;
 	struct pci_epc *epc;
 	u8 func_no, vfunc_no;
 	bool is_msix;
@@ -159,7 +159,7 @@ static int epf_ntb_link_up(struct epf_ntb *ntb, bool link_up)
 			ctrl->link_status |= LINK_STATUS_UP;
 		else
 			ctrl->link_status &= ~LINK_STATUS_UP;
-		irq_type = is_msix ? PCI_EPC_IRQ_MSIX : PCI_EPC_IRQ_MSI;
+		irq_type = is_msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
 		ret = pci_epc_raise_irq(epc, func_no, vfunc_no, irq_type, 1);
 		if (ret) {
 			dev_err(&epc->dev,
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 1f0d2b84296a3..9d39fda5c348e 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -602,7 +602,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 	switch (reg->irq_type) {
 	case IRQ_TYPE_LEGACY:
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_LEGACY, 0);
+				  PCI_IRQ_INTX, 0);
 		break;
 	case IRQ_TYPE_MSI:
 		count = pci_epc_get_msi(epc, epf->func_no, epf->vfunc_no);
@@ -612,7 +612,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 			return;
 		}
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_MSI, reg->irq_number);
+				  PCI_IRQ_MSI, reg->irq_number);
 		break;
 	case IRQ_TYPE_MSIX:
 		count = pci_epc_get_msix(epc, epf->func_no, epf->vfunc_no);
@@ -622,7 +622,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 			return;
 		}
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_MSIX, reg->irq_number);
+				  PCI_IRQ_MSIX, reg->irq_number);
 		break;
 	default:
 		dev_err(dev, "Failed to raise IRQ, unknown type\n");
diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index 3f60128560ed0..e6a0bcc177e49 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -1172,11 +1172,8 @@ static int vntb_epf_peer_db_set(struct ntb_dev *ndev, u64 db_bits)
 	func_no = ntb->epf->func_no;
 	vfunc_no = ntb->epf->vfunc_no;
 
-	ret = pci_epc_raise_irq(ntb->epf->epc,
-				func_no,
-				vfunc_no,
-				PCI_EPC_IRQ_MSI,
-				interrupt_num + 1);
+	ret = pci_epc_raise_irq(ntb->epf->epc, func_no, vfunc_no,
+				PCI_IRQ_MSI, interrupt_num + 1);
 	if (ret)
 		dev_err(&ntb->ntb.dev, "Failed to raise IRQ\n");
 
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 56e1184bc6c24..0810420df42c5 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -217,7 +217,7 @@ EXPORT_SYMBOL_GPL(pci_epc_start);
  * Invoke to raise an legacy, MSI or MSI-X interrupt
  */
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		      enum pci_epc_irq_type type, u16 interrupt_num)
+		      unsigned int type, u16 interrupt_num)
 {
 	int ret;
 
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 5cb6940310729..f498f9aa2ab0e 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -19,13 +19,6 @@ enum pci_epc_interface_type {
 	SECONDARY_INTERFACE,
 };
 
-enum pci_epc_irq_type {
-	PCI_EPC_IRQ_UNKNOWN,
-	PCI_EPC_IRQ_LEGACY,
-	PCI_EPC_IRQ_MSI,
-	PCI_EPC_IRQ_MSIX,
-};
-
 static inline const char *
 pci_epc_interface_string(enum pci_epc_interface_type type)
 {
@@ -79,7 +72,7 @@ struct pci_epc_ops {
 			    u16 interrupts, enum pci_barno, u32 offset);
 	int	(*get_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 	int	(*raise_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			     enum pci_epc_irq_type type, u16 interrupt_num);
+			     unsigned int type, u16 interrupt_num);
 	int	(*map_msi_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			       phys_addr_t phys_addr, u8 interrupt_num,
 			       u32 entry_size, u32 *msi_data,
@@ -229,7 +222,7 @@ int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr, u8 interrupt_num,
 			u32 entry_size, u32 *msi_data, u32 *msi_addr_offset);
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		      enum pci_epc_irq_type type, u16 interrupt_num);
+		      unsigned int type, u16 interrupt_num);
 int pci_epc_start(struct pci_epc *epc);
 void pci_epc_stop(struct pci_epc *epc);
 const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc,
-- 
GitLab


From 8a608dac4bf6ca90f0ab7b9f99c738d4def74452 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:53 +0900
Subject: [PATCH 1524/4076] PCI: endpoint: Use INTX instead of legacy

In the endpoint controller core code, change references to "legacy"
interrupts to "INTX" interrupts to match the term used in the PCI
specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-4-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/endpoint/pci-epc-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 0810420df42c5..dcd4e66430c10 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -211,10 +211,10 @@ EXPORT_SYMBOL_GPL(pci_epc_start);
  * @epc: the EPC device which has to interrupt the host
  * @func_no: the physical endpoint function number in the EPC device
  * @vfunc_no: the virtual endpoint function number in the physical function
- * @type: specify the type of interrupt; legacy, MSI or MSI-X
+ * @type: specify the type of interrupt; INTX, MSI or MSI-X
  * @interrupt_num: the MSI or MSI-X interrupt number with range (1-N)
  *
- * Invoke to raise an legacy, MSI or MSI-X interrupt
+ * Invoke to raise an INTX, MSI or MSI-X interrupt
  */
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		      unsigned int type, u16 interrupt_num)
-- 
GitLab


From 5b0fbadc0f87364ccbfb064789a6b790b99539ea Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:54 +0900
Subject: [PATCH 1525/4076] PCI: endpoint: Rename LEGACY to INTX in test
 function driver

In the endpoint test function driver, rename IRQ_TYPE_LEGACY to
IRQ_TYPE_INTX and COMMAND_RAISE_LEGACY_IRQ to COMMAND_RAISE_INTX_IRQ
to match the term used in the PCI specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-5-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/endpoint/functions/pci-epf-test.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 9d39fda5c348e..637a6a3982031 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -19,11 +19,11 @@
 #include <linux/pci-epf.h>
 #include <linux/pci_regs.h>
 
-#define IRQ_TYPE_LEGACY			0
+#define IRQ_TYPE_INTX			0
 #define IRQ_TYPE_MSI			1
 #define IRQ_TYPE_MSIX			2
 
-#define COMMAND_RAISE_LEGACY_IRQ	BIT(0)
+#define COMMAND_RAISE_INTX_IRQ		BIT(0)
 #define COMMAND_RAISE_MSI_IRQ		BIT(1)
 #define COMMAND_RAISE_MSIX_IRQ		BIT(2)
 #define COMMAND_READ			BIT(3)
@@ -600,7 +600,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 	WRITE_ONCE(reg->status, status);
 
 	switch (reg->irq_type) {
-	case IRQ_TYPE_LEGACY:
+	case IRQ_TYPE_INTX:
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
 				  PCI_IRQ_INTX, 0);
 		break;
@@ -659,7 +659,7 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 	}
 
 	switch (command) {
-	case COMMAND_RAISE_LEGACY_IRQ:
+	case COMMAND_RAISE_INTX_IRQ:
 	case COMMAND_RAISE_MSI_IRQ:
 	case COMMAND_RAISE_MSIX_IRQ:
 		pci_epf_test_raise_irq(epf_test, reg);
-- 
GitLab


From acd288666979a49538d70e0c0d86e1118b445058 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:55 +0900
Subject: [PATCH 1526/4076] misc: pci_endpoint_test: Use INTX instead of LEGACY

In the root complex pci endpoint test function driver, change macros and
functions names using the term "legacy" to use "intx" instead to
match the term used in the PCI specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-6-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/misc/pci_endpoint_test.c | 30 +++++++++++++++---------------
 include/uapi/linux/pcitest.h     |  3 ++-
 2 files changed, 17 insertions(+), 16 deletions(-)

diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index af519088732d9..2d7822d9dfe9d 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -28,14 +28,14 @@
 #define DRV_MODULE_NAME				"pci-endpoint-test"
 
 #define IRQ_TYPE_UNDEFINED			-1
-#define IRQ_TYPE_LEGACY				0
+#define IRQ_TYPE_INTX				0
 #define IRQ_TYPE_MSI				1
 #define IRQ_TYPE_MSIX				2
 
 #define PCI_ENDPOINT_TEST_MAGIC			0x0
 
 #define PCI_ENDPOINT_TEST_COMMAND		0x4
-#define COMMAND_RAISE_LEGACY_IRQ		BIT(0)
+#define COMMAND_RAISE_INTX_IRQ			BIT(0)
 #define COMMAND_RAISE_MSI_IRQ			BIT(1)
 #define COMMAND_RAISE_MSIX_IRQ			BIT(2)
 #define COMMAND_READ				BIT(3)
@@ -183,8 +183,8 @@ static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test,
 	bool res = true;
 
 	switch (type) {
-	case IRQ_TYPE_LEGACY:
-		irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY);
+	case IRQ_TYPE_INTX:
+		irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_INTX);
 		if (irq < 0)
 			dev_err(dev, "Failed to get Legacy interrupt\n");
 		break;
@@ -244,7 +244,7 @@ static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test)
 
 fail:
 	switch (irq_type) {
-	case IRQ_TYPE_LEGACY:
+	case IRQ_TYPE_INTX:
 		dev_err(dev, "Failed to request IRQ %d for Legacy\n",
 			pci_irq_vector(pdev, i));
 		break;
@@ -291,15 +291,15 @@ static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 	return true;
 }
 
-static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test)
+static bool pci_endpoint_test_intx_irq(struct pci_endpoint_test *test)
 {
 	u32 val;
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
-				 IRQ_TYPE_LEGACY);
+				 IRQ_TYPE_INTX);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 0);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 COMMAND_RAISE_LEGACY_IRQ);
+				 COMMAND_RAISE_INTX_IRQ);
 	val = wait_for_completion_timeout(&test->irq_raised,
 					  msecs_to_jiffies(1000));
 	if (!val)
@@ -385,7 +385,7 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -521,7 +521,7 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -621,7 +621,7 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -691,7 +691,7 @@ static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test,
 	struct pci_dev *pdev = test->pdev;
 	struct device *dev = &pdev->dev;
 
-	if (req_irq_type < IRQ_TYPE_LEGACY || req_irq_type > IRQ_TYPE_MSIX) {
+	if (req_irq_type < IRQ_TYPE_INTX || req_irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		return false;
 	}
@@ -737,8 +737,8 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 			goto ret;
 		ret = pci_endpoint_test_bar(test, bar);
 		break;
-	case PCITEST_LEGACY_IRQ:
-		ret = pci_endpoint_test_legacy_irq(test);
+	case PCITEST_INTX_IRQ:
+		ret = pci_endpoint_test_intx_irq(test);
 		break;
 	case PCITEST_MSI:
 	case PCITEST_MSIX:
@@ -801,7 +801,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 	test->irq_type = IRQ_TYPE_UNDEFINED;
 
 	if (no_msi)
-		irq_type = IRQ_TYPE_LEGACY;
+		irq_type = IRQ_TYPE_INTX;
 
 	data = (struct pci_endpoint_test_data *)ent->driver_data;
 	if (data) {
diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h
index f9c1af8d141b4..94b46b043b536 100644
--- a/include/uapi/linux/pcitest.h
+++ b/include/uapi/linux/pcitest.h
@@ -11,7 +11,8 @@
 #define __UAPI_LINUX_PCITEST_H
 
 #define PCITEST_BAR		_IO('P', 0x1)
-#define PCITEST_LEGACY_IRQ	_IO('P', 0x2)
+#define PCITEST_INTX_IRQ	_IO('P', 0x2)
+#define PCITEST_LEGACY_IRQ	PCITEST_INTX_IRQ
 #define PCITEST_MSI		_IOW('P', 0x3, int)
 #define PCITEST_WRITE		_IOW('P', 0x4, unsigned long)
 #define PCITEST_READ		_IOW('P', 0x5, unsigned long)
-- 
GitLab


From 676f482354886caa9b0cfa9236f5d20ac78f8c6a Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:49 +0000
Subject: [PATCH 1527/4076] KVM: arm64: Handle HAFGRTR_EL2 trapping in nested
 virt

Add the encodings to fine grain trapping fields for HAFGRTR_EL2
and add the associated handling code in nested virt. Based on
DDI0601 2023-09. Add the missing field definitions as well,
both to generate the correct RES0 mask and to be able to toggle
their FGT bits.

Also add the code for handling FGT trapping, reading of the
register, to nested virt.

Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-10-tabba@google.com
---
 arch/arm64/include/asm/kvm_host.h       |  1 +
 arch/arm64/kvm/emulate-nested.c         | 48 +++++++++++++++++++++++++
 arch/arm64/kvm/hyp/include/hyp/switch.h | 25 +++++++++++++
 arch/arm64/kvm/sys_regs.c               |  1 +
 4 files changed, 75 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 824f29f04916a..ba14648e2de25 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -443,6 +443,7 @@ enum vcpu_sysreg {
 	HFGITR_EL2,
 	HDFGRTR_EL2,
 	HDFGWTR_EL2,
+	HAFGRTR_EL2,
 	CNTHP_CTL_EL2,
 	CNTHP_CVAL_EL2,
 	CNTHV_CTL_EL2,
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 89901550db342..431fd429932df 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -1012,6 +1012,7 @@ enum fgt_group_id {
 	HDFGRTR_GROUP,
 	HDFGWTR_GROUP,
 	HFGITR_GROUP,
+	HAFGRTR_GROUP,
 
 	/* Must be last */
 	__NR_FGT_GROUP_IDS__
@@ -1689,6 +1690,49 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_PMCR_EL0,		HDFGWTR, PMCR_EL0, 1),
 	SR_FGT(SYS_PMSWINC_EL0,		HDFGWTR, PMSWINC_EL0, 1),
 	SR_FGT(SYS_OSLAR_EL1,		HDFGWTR, OSLAR_EL1, 1),
+	/*
+	 * HAFGRTR_EL2
+	 */
+	SR_FGT(SYS_AMEVTYPER1_EL0(15),	HAFGRTR, AMEVTYPER115_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(14),	HAFGRTR, AMEVTYPER114_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(13),	HAFGRTR, AMEVTYPER113_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(12),	HAFGRTR, AMEVTYPER112_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(11),	HAFGRTR, AMEVTYPER111_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(10),	HAFGRTR, AMEVTYPER110_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(9),	HAFGRTR, AMEVTYPER19_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(8),	HAFGRTR, AMEVTYPER18_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(7),	HAFGRTR, AMEVTYPER17_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(6),	HAFGRTR, AMEVTYPER16_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(5),	HAFGRTR, AMEVTYPER15_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(4),	HAFGRTR, AMEVTYPER14_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(3),	HAFGRTR, AMEVTYPER13_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(2),	HAFGRTR, AMEVTYPER12_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(1),	HAFGRTR, AMEVTYPER11_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(0),	HAFGRTR, AMEVTYPER10_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(15),	HAFGRTR, AMEVCNTR115_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(14),	HAFGRTR, AMEVCNTR114_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(13),	HAFGRTR, AMEVCNTR113_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(12),	HAFGRTR, AMEVCNTR112_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(11),	HAFGRTR, AMEVCNTR111_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(10),	HAFGRTR, AMEVCNTR110_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(9),	HAFGRTR, AMEVCNTR19_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(8),	HAFGRTR, AMEVCNTR18_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(7),	HAFGRTR, AMEVCNTR17_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(6),	HAFGRTR, AMEVCNTR16_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(5),	HAFGRTR, AMEVCNTR15_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(4),	HAFGRTR, AMEVCNTR14_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(3),	HAFGRTR, AMEVCNTR13_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(2),	HAFGRTR, AMEVCNTR12_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(1),	HAFGRTR, AMEVCNTR11_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(0),	HAFGRTR, AMEVCNTR10_EL0, 1),
+	SR_FGT(SYS_AMCNTENCLR1_EL0,	HAFGRTR, AMCNTEN1, 1),
+	SR_FGT(SYS_AMCNTENSET1_EL0,	HAFGRTR, AMCNTEN1, 1),
+	SR_FGT(SYS_AMCNTENCLR0_EL0,	HAFGRTR, AMCNTEN0, 1),
+	SR_FGT(SYS_AMCNTENSET0_EL0,	HAFGRTR, AMCNTEN0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(3),	HAFGRTR, AMEVCNTR03_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(2),	HAFGRTR, AMEVCNTR02_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(1),	HAFGRTR, AMEVCNTR01_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(0),	HAFGRTR, AMEVCNTR00_EL0, 1),
 };
 
 static union trap_config get_trap_config(u32 sysreg)
@@ -1909,6 +1953,10 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 			val = sanitised_sys_reg(vcpu, HDFGWTR_EL2);
 		break;
 
+	case HAFGRTR_GROUP:
+		val = sanitised_sys_reg(vcpu, HAFGRTR_EL2);
+		break;
+
 	case HFGITR_GROUP:
 		val = sanitised_sys_reg(vcpu, HFGITR_EL2);
 		switch (tc.fgf) {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 7b4909dfd1f56..0436f0da98a42 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -80,6 +80,14 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	} while(0)
 
 
+static inline bool cpu_has_amu(void)
+{
+       u64 pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
+
+       return cpuid_feature_extract_unsigned_field(pfr0,
+               ID_AA64PFR0_EL1_AMU_SHIFT);
+}
+
 static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
@@ -156,6 +164,20 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 
 	write_sysreg_s(r_val, SYS_HDFGRTR_EL2);
 	write_sysreg_s(w_val, SYS_HDFGWTR_EL2);
+
+       if (!cpu_has_amu())
+               return;
+
+	ctxt_sys_reg(hctxt, HAFGRTR_EL2) = read_sysreg_s(SYS_HAFGRTR_EL2);
+
+	r_clr = r_set = 0;
+	compute_clr_set(vcpu, HAFGRTR_EL2, r_clr, r_set);
+
+	r_val = __HAFGRTR_EL2_nMASK;
+	r_val |= r_set;
+	r_val &= ~r_clr;
+
+	write_sysreg_s(r_val, SYS_HAFGRTR_EL2);
 }
 
 static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
@@ -174,6 +196,9 @@ static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	write_sysreg_s(ctxt_sys_reg(hctxt, HFGITR_EL2), SYS_HFGITR_EL2);
 	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGRTR_EL2), SYS_HDFGRTR_EL2);
 	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGWTR_EL2), SYS_HDFGWTR_EL2);
+
+	if (vcpu_has_amu())
+		write_sysreg_s(ctxt_sys_reg(hctxt, HAFGRTR_EL2), SYS_HAFGRTR_EL2);
 }
 
 static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 4735e1b37fb3e..8bb297a2df388 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2532,6 +2532,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_DACR32_EL2), trap_undef, reset_unknown, DACR32_EL2 },
 	EL2_REG(HDFGRTR_EL2, access_rw, reset_val, 0),
 	EL2_REG(HDFGWTR_EL2, access_rw, reset_val, 0),
+	EL2_REG(HAFGRTR_EL2, access_rw, reset_val, 0),
 	EL2_REG(SPSR_EL2, access_rw, reset_val, 0),
 	EL2_REG(ELR_EL2, access_rw, reset_val, 0),
 	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
-- 
GitLab


From fc04838f9c00fcbc90a8926bbd46928d6fb36477 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:50 +0000
Subject: [PATCH 1528/4076] KVM: arm64: Update and fix FGT register masks

New trap bits have been defined since the latest update to this
patch.  Moreover, the existing definitions of some of the mask
and the RES0 bits overlap, which could be wrong, confusing, or
both.

Update the bits based on DDI0601 2023-09, and ensure that the
existing bits are consistent.

Subsequent patches will use the generated RES0 fields instead of
specifying them manually. This patch keeps the manual encoding of
the bits to make it easier to review the series.

Fixes: 0fd76865006d ("KVM: arm64: Add nPIR{E0}_EL1 to HFG traps")
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-11-tabba@google.com
---
 arch/arm64/include/asm/kvm_arm.h | 39 ++++++++++++++++++++------------
 1 file changed, 24 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 7de0a70626255..b0dc3249d5cd7 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -344,30 +344,39 @@
  * Once we get to a point where the two describe the same thing, we'll
  * merge the definitions. One day.
  */
-#define __HFGRTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51))
+#define __HFGRTR_EL2_RES0	BIT(51)
 #define __HFGRTR_EL2_MASK	GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK	(GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
+#define __HFGRTR_EL2_nMASK	(GENMASK(63, 52) | BIT(50))
 
-#define __HFGWTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51) |	\
-				 BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
-				 GENMASK(26, 25) | BIT(21) | BIT(18) |	\
+#define __HFGWTR_EL2_RES0	(BIT(51) | BIT(46) | BIT(42) | BIT(40) | \
+				 BIT(28) | GENMASK(26, 25) | BIT(21) | BIT(18) | \
 				 GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
-#define __HFGWTR_EL2_MASK	GENMASK(49, 0)
-#define __HFGWTR_EL2_nMASK	(GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
+#define __HFGWTR_EL2_MASK	(GENMASK(49, 47) | GENMASK(45, 43) | \
+				 BIT(41) | GENMASK(39, 29) | BIT(27) | \
+				 GENMASK(24, 22) | GENMASK(20, 19) | \
+				 GENMASK(17, 16) | GENMASK(13, 11) | \
+				 GENMASK(8, 3) | GENMASK(1, 0))
+#define __HFGWTR_EL2_nMASK	(GENMASK(63, 52) | BIT(50))
 
-#define __HFGITR_EL2_RES0	GENMASK(63, 57)
-#define __HFGITR_EL2_MASK	GENMASK(54, 0)
-#define __HFGITR_EL2_nMASK	GENMASK(56, 55)
+#define __HFGITR_EL2_RES0	(BIT(63) | BIT(61))
+#define __HFGITR_EL2_MASK	(BIT(62) | BIT(60) | GENMASK(54, 0))
+#define __HFGITR_EL2_nMASK	GENMASK(59, 55)
 
 #define __HDFGRTR_EL2_RES0	(BIT(49) | BIT(42) | GENMASK(39, 38) |	\
 				 GENMASK(21, 20) | BIT(8))
-#define __HDFGRTR_EL2_MASK	~__HDFGRTR_EL2_nMASK
+#define __HDFGRTR_EL2_MASK	(BIT(63) | GENMASK(58, 50) | GENMASK(48, 43) | \
+				 GENMASK(41, 40) | GENMASK(37, 22) | \
+				 GENMASK(19, 9) | GENMASK(7, 0))
 #define __HDFGRTR_EL2_nMASK	GENMASK(62, 59)
 
 #define __HDFGWTR_EL2_RES0	(BIT(63) | GENMASK(59, 58) | BIT(51) | BIT(47) | \
 				 BIT(43) | GENMASK(40, 38) | BIT(34) | BIT(30) | \
 				 BIT(22) | BIT(9) | BIT(6))
-#define __HDFGWTR_EL2_MASK	~__HDFGWTR_EL2_nMASK
+#define __HDFGWTR_EL2_MASK	(GENMASK(57, 52) | GENMASK(50, 48) | \
+				 GENMASK(46, 44) | GENMASK(42, 41) | \
+				 GENMASK(37, 35) | GENMASK(33, 31) | \
+				 GENMASK(29, 23) | GENMASK(21, 10) | \
+				 GENMASK(8, 7) | GENMASK(5, 0))
 #define __HDFGWTR_EL2_nMASK	GENMASK(62, 60)
 
 #define __HAFGRTR_EL2_RES0	(GENMASK(63, 50) | GENMASK(16, 5))
@@ -375,9 +384,9 @@
 #define __HAFGRTR_EL2_nMASK	0UL
 
 /* Similar definitions for HCRX_EL2 */
-#define __HCRX_EL2_RES0		(GENMASK(63, 16) | GENMASK(13, 12))
-#define __HCRX_EL2_MASK		(0)
-#define __HCRX_EL2_nMASK	(GENMASK(15, 14) | GENMASK(4, 0))
+#define __HCRX_EL2_RES0         (GENMASK(63, 25) | GENMASK(13, 12))
+#define __HCRX_EL2_MASK		(BIT(6))
+#define __HCRX_EL2_nMASK	(GENMASK(24, 14) | GENMASK(11, 7) | GENMASK(5, 0))
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
-- 
GitLab


From 6c4abbea6d9c09df448b43624074a208c38e68e0 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:51 +0000
Subject: [PATCH 1529/4076] KVM: arm64: Add build validation for FGT trap mask
 values

These checks help ensure that all the bits are accounted for,
that there hasn't been a transcribing error from the spec nor
from the generated mask values, which will be used in subsequent
patches.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-12-tabba@google.com
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 0436f0da98a42..ecccf99619e6c 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -79,6 +79,16 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 		clr |= ~hfg & __ ## reg ## _nMASK; 			\
 	} while(0)
 
+/*
+ * Validate the fine grain trap masks.
+ * Check that the masks do not overlap and that all bits are accounted for.
+ */
+#define CHECK_FGT_MASKS(reg)							\
+	do {									\
+		BUILD_BUG_ON((__ ## reg ## _MASK) & (__ ## reg ## _nMASK));	\
+		BUILD_BUG_ON(~((__ ## reg ## _RES0) ^ (__ ## reg ## _MASK) ^	\
+			       (__ ## reg ## _nMASK)));				\
+	} while(0)
 
 static inline bool cpu_has_amu(void)
 {
@@ -94,6 +104,14 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	u64 r_clr = 0, w_clr = 0, r_set = 0, w_set = 0, tmp;
 	u64 r_val, w_val;
 
+	CHECK_FGT_MASKS(HFGRTR_EL2);
+	CHECK_FGT_MASKS(HFGWTR_EL2);
+	CHECK_FGT_MASKS(HFGITR_EL2);
+	CHECK_FGT_MASKS(HDFGRTR_EL2);
+	CHECK_FGT_MASKS(HDFGWTR_EL2);
+	CHECK_FGT_MASKS(HAFGRTR_EL2);
+	CHECK_FGT_MASKS(HCRX_EL2);
+
 	if (!cpus_have_final_cap(ARM64_HAS_FGT))
 		return;
 
-- 
GitLab


From 9ff67dd26a9eed9d73dc23aa63e87b16b3382184 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:52 +0000
Subject: [PATCH 1530/4076] KVM: arm64: Use generated FGT RES0 bits instead of
 specifying them

Now that all FGT fields are accounted for and represented, use
the generated value instead of manually specifying them.

For __HFGWTR_EL2_RES0, however, there is no generated value. Its
fields are subset of HFGRTR_EL2, with the remaining being RES0.
Therefore, add a mask that represents the HFGRTR_EL2 only bits
and define __HFGWTR_EL2_* using those and the __HFGRTR_EL2_*
fields.

No functional change intended.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-13-tabba@google.com
---
 arch/arm64/include/asm/kvm_arm.h | 34 +++++++++++++++-----------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index b0dc3249d5cd7..bd20d27f1b333 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -344,34 +344,32 @@
  * Once we get to a point where the two describe the same thing, we'll
  * merge the definitions. One day.
  */
-#define __HFGRTR_EL2_RES0	BIT(51)
+#define __HFGRTR_EL2_RES0	HFGxTR_EL2_RES0
 #define __HFGRTR_EL2_MASK	GENMASK(49, 0)
 #define __HFGRTR_EL2_nMASK	(GENMASK(63, 52) | BIT(50))
 
-#define __HFGWTR_EL2_RES0	(BIT(51) | BIT(46) | BIT(42) | BIT(40) | \
-				 BIT(28) | GENMASK(26, 25) | BIT(21) | BIT(18) | \
+/*
+ * The HFGWTR bits are a subset of HFGRTR bits. To ensure we don't miss any
+ * future additions, define __HFGWTR* macros relative to __HFGRTR* ones.
+ */
+#define __HFGRTR_ONLY_MASK	(BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
+				 GENMASK(26, 25) | BIT(21) | BIT(18) | \
 				 GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
-#define __HFGWTR_EL2_MASK	(GENMASK(49, 47) | GENMASK(45, 43) | \
-				 BIT(41) | GENMASK(39, 29) | BIT(27) | \
-				 GENMASK(24, 22) | GENMASK(20, 19) | \
-				 GENMASK(17, 16) | GENMASK(13, 11) | \
-				 GENMASK(8, 3) | GENMASK(1, 0))
-#define __HFGWTR_EL2_nMASK	(GENMASK(63, 52) | BIT(50))
-
-#define __HFGITR_EL2_RES0	(BIT(63) | BIT(61))
+#define __HFGWTR_EL2_RES0	(__HFGRTR_EL2_RES0 | __HFGRTR_ONLY_MASK)
+#define __HFGWTR_EL2_MASK	(__HFGRTR_EL2_MASK & ~__HFGRTR_ONLY_MASK)
+#define __HFGWTR_EL2_nMASK	(__HFGRTR_EL2_nMASK & ~__HFGRTR_ONLY_MASK)
+
+#define __HFGITR_EL2_RES0	HFGITR_EL2_RES0
 #define __HFGITR_EL2_MASK	(BIT(62) | BIT(60) | GENMASK(54, 0))
 #define __HFGITR_EL2_nMASK	GENMASK(59, 55)
 
-#define __HDFGRTR_EL2_RES0	(BIT(49) | BIT(42) | GENMASK(39, 38) |	\
-				 GENMASK(21, 20) | BIT(8))
+#define __HDFGRTR_EL2_RES0	HDFGRTR_EL2_RES0
 #define __HDFGRTR_EL2_MASK	(BIT(63) | GENMASK(58, 50) | GENMASK(48, 43) | \
 				 GENMASK(41, 40) | GENMASK(37, 22) | \
 				 GENMASK(19, 9) | GENMASK(7, 0))
 #define __HDFGRTR_EL2_nMASK	GENMASK(62, 59)
 
-#define __HDFGWTR_EL2_RES0	(BIT(63) | GENMASK(59, 58) | BIT(51) | BIT(47) | \
-				 BIT(43) | GENMASK(40, 38) | BIT(34) | BIT(30) | \
-				 BIT(22) | BIT(9) | BIT(6))
+#define __HDFGWTR_EL2_RES0	HDFGWTR_EL2_RES0
 #define __HDFGWTR_EL2_MASK	(GENMASK(57, 52) | GENMASK(50, 48) | \
 				 GENMASK(46, 44) | GENMASK(42, 41) | \
 				 GENMASK(37, 35) | GENMASK(33, 31) | \
@@ -379,12 +377,12 @@
 				 GENMASK(8, 7) | GENMASK(5, 0))
 #define __HDFGWTR_EL2_nMASK	GENMASK(62, 60)
 
-#define __HAFGRTR_EL2_RES0	(GENMASK(63, 50) | GENMASK(16, 5))
+#define __HAFGRTR_EL2_RES0	HAFGRTR_EL2_RES0
 #define __HAFGRTR_EL2_MASK	(GENMASK(49, 17) | GENMASK(4, 0))
 #define __HAFGRTR_EL2_nMASK	0UL
 
 /* Similar definitions for HCRX_EL2 */
-#define __HCRX_EL2_RES0         (GENMASK(63, 25) | GENMASK(13, 12))
+#define __HCRX_EL2_RES0         HCRX_EL2_RES0
 #define __HCRX_EL2_MASK		(BIT(6))
 #define __HCRX_EL2_nMASK	(GENMASK(24, 14) | GENMASK(11, 7) | GENMASK(5, 0))
 
-- 
GitLab


From 5f6bd3f3daaaab8559ad7d2266ba38345231b7ae Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:53 +0000
Subject: [PATCH 1531/4076] KVM: arm64: Define FGT nMASK bits relative to other
 fields

Now that RES0 and MASK have full coverage, no need to manually
encode nMASK. Calculate it relative to the other fields.

No functional change intended.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-14-tabba@google.com
---
 arch/arm64/include/asm/kvm_arm.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index bd20d27f1b333..b7a9fe36bb59e 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -346,7 +346,7 @@
  */
 #define __HFGRTR_EL2_RES0	HFGxTR_EL2_RES0
 #define __HFGRTR_EL2_MASK	GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK	(GENMASK(63, 52) | BIT(50))
+#define __HFGRTR_EL2_nMASK	~(__HFGRTR_EL2_RES0 | __HFGRTR_EL2_MASK)
 
 /*
  * The HFGWTR bits are a subset of HFGRTR bits. To ensure we don't miss any
@@ -357,17 +357,17 @@
 				 GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
 #define __HFGWTR_EL2_RES0	(__HFGRTR_EL2_RES0 | __HFGRTR_ONLY_MASK)
 #define __HFGWTR_EL2_MASK	(__HFGRTR_EL2_MASK & ~__HFGRTR_ONLY_MASK)
-#define __HFGWTR_EL2_nMASK	(__HFGRTR_EL2_nMASK & ~__HFGRTR_ONLY_MASK)
+#define __HFGWTR_EL2_nMASK	~(__HFGWTR_EL2_RES0 | __HFGWTR_EL2_MASK)
 
 #define __HFGITR_EL2_RES0	HFGITR_EL2_RES0
 #define __HFGITR_EL2_MASK	(BIT(62) | BIT(60) | GENMASK(54, 0))
-#define __HFGITR_EL2_nMASK	GENMASK(59, 55)
+#define __HFGITR_EL2_nMASK	~(__HFGITR_EL2_RES0 | __HFGITR_EL2_MASK)
 
 #define __HDFGRTR_EL2_RES0	HDFGRTR_EL2_RES0
 #define __HDFGRTR_EL2_MASK	(BIT(63) | GENMASK(58, 50) | GENMASK(48, 43) | \
 				 GENMASK(41, 40) | GENMASK(37, 22) | \
 				 GENMASK(19, 9) | GENMASK(7, 0))
-#define __HDFGRTR_EL2_nMASK	GENMASK(62, 59)
+#define __HDFGRTR_EL2_nMASK	~(__HDFGRTR_EL2_RES0 | __HDFGRTR_EL2_MASK)
 
 #define __HDFGWTR_EL2_RES0	HDFGWTR_EL2_RES0
 #define __HDFGWTR_EL2_MASK	(GENMASK(57, 52) | GENMASK(50, 48) | \
@@ -375,16 +375,16 @@
 				 GENMASK(37, 35) | GENMASK(33, 31) | \
 				 GENMASK(29, 23) | GENMASK(21, 10) | \
 				 GENMASK(8, 7) | GENMASK(5, 0))
-#define __HDFGWTR_EL2_nMASK	GENMASK(62, 60)
+#define __HDFGWTR_EL2_nMASK	~(__HDFGWTR_EL2_RES0 | __HDFGWTR_EL2_MASK)
 
 #define __HAFGRTR_EL2_RES0	HAFGRTR_EL2_RES0
 #define __HAFGRTR_EL2_MASK	(GENMASK(49, 17) | GENMASK(4, 0))
-#define __HAFGRTR_EL2_nMASK	0UL
+#define __HAFGRTR_EL2_nMASK	~(__HAFGRTR_EL2_RES0 | __HAFGRTR_EL2_MASK)
 
 /* Similar definitions for HCRX_EL2 */
 #define __HCRX_EL2_RES0         HCRX_EL2_RES0
 #define __HCRX_EL2_MASK		(BIT(6))
-#define __HCRX_EL2_nMASK	(GENMASK(24, 14) | GENMASK(11, 7) | GENMASK(5, 0))
+#define __HCRX_EL2_nMASK	~(__HCRX_EL2_RES0 | __HCRX_EL2_MASK)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
-- 
GitLab


From 0ccd901da1886cf9dc53ab36ad8f1160b65e41f1 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:54 +0000
Subject: [PATCH 1532/4076] KVM: arm64: Macros for setting/clearing FGT bits

There's a lot of boilerplate code for setting and clearing FGT
bits when activating guest traps. Refactor it into macros. These
macros will also be used in future patch series.

No functional change intended.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-15-tabba@google.com
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 69 ++++++++++---------------
 1 file changed, 27 insertions(+), 42 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index ecccf99619e6c..d56fef44dc314 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -79,6 +79,27 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 		clr |= ~hfg & __ ## reg ## _nMASK; 			\
 	} while(0)
 
+#define update_fgt_traps_cs(vcpu, reg, clr, set)			\
+	do {								\
+		struct kvm_cpu_context *hctxt =				\
+			&this_cpu_ptr(&kvm_host_data)->host_ctxt;	\
+		u64 c = 0, s = 0;					\
+									\
+		ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg);	\
+		compute_clr_set(vcpu, reg, c, s);			\
+		s |= set;						\
+		c |= clr;						\
+		if (c || s) {						\
+			u64 val = __ ## reg ## _nMASK;			\
+			val |= s;					\
+			val &= ~c;					\
+			write_sysreg_s(val, SYS_ ## reg);		\
+		}							\
+	} while(0)
+
+#define update_fgt_traps(vcpu, reg)		\
+	update_fgt_traps_cs(vcpu, reg, 0, 0)
+
 /*
  * Validate the fine grain trap masks.
  * Check that the masks do not overlap and that all bits are accounted for.
@@ -154,48 +175,12 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
 		return;
 
-	ctxt_sys_reg(hctxt, HFGITR_EL2) = read_sysreg_s(SYS_HFGITR_EL2);
-
-	r_set = r_clr = 0;
-	compute_clr_set(vcpu, HFGITR_EL2, r_clr, r_set);
-	r_val = __HFGITR_EL2_nMASK;
-	r_val |= r_set;
-	r_val &= ~r_clr;
-
-	write_sysreg_s(r_val, SYS_HFGITR_EL2);
-
-	ctxt_sys_reg(hctxt, HDFGRTR_EL2) = read_sysreg_s(SYS_HDFGRTR_EL2);
-	ctxt_sys_reg(hctxt, HDFGWTR_EL2) = read_sysreg_s(SYS_HDFGWTR_EL2);
-
-	r_clr = r_set = w_clr = w_set = 0;
-
-	compute_clr_set(vcpu, HDFGRTR_EL2, r_clr, r_set);
-	compute_clr_set(vcpu, HDFGWTR_EL2, w_clr, w_set);
-
-	r_val = __HDFGRTR_EL2_nMASK;
-	r_val |= r_set;
-	r_val &= ~r_clr;
-
-	w_val = __HDFGWTR_EL2_nMASK;
-	w_val |= w_set;
-	w_val &= ~w_clr;
-
-	write_sysreg_s(r_val, SYS_HDFGRTR_EL2);
-	write_sysreg_s(w_val, SYS_HDFGWTR_EL2);
-
-       if (!cpu_has_amu())
-               return;
-
-	ctxt_sys_reg(hctxt, HAFGRTR_EL2) = read_sysreg_s(SYS_HAFGRTR_EL2);
-
-	r_clr = r_set = 0;
-	compute_clr_set(vcpu, HAFGRTR_EL2, r_clr, r_set);
-
-	r_val = __HAFGRTR_EL2_nMASK;
-	r_val |= r_set;
-	r_val &= ~r_clr;
+	update_fgt_traps(vcpu, HFGITR_EL2);
+	update_fgt_traps(vcpu, HDFGRTR_EL2);
+	update_fgt_traps(vcpu, HDFGWTR_EL2);
 
-	write_sysreg_s(r_val, SYS_HAFGRTR_EL2);
+	if (cpu_has_amu())
+		update_fgt_traps(vcpu, HAFGRTR_EL2);
 }
 
 static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
@@ -215,7 +200,7 @@ static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGRTR_EL2), SYS_HDFGRTR_EL2);
 	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGWTR_EL2), SYS_HDFGWTR_EL2);
 
-	if (vcpu_has_amu())
+	if (cpu_has_amu())
 		write_sysreg_s(ctxt_sys_reg(hctxt, HAFGRTR_EL2), SYS_HAFGRTR_EL2);
 }
 
-- 
GitLab


From 73e3ce3f4a0e561e24ca71b20de00f03b427981e Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:55 +0000
Subject: [PATCH 1533/4076] KVM: arm64: Fix which features are marked as
 allowed for protected VMs

Cache maintenance operations are not trapped for protected VMs,
and shouldn't be. Mark them as allowed.

Moreover, features advertised by ID_AA64PFR2 and ID_AA64MMFR3 are
(already) not allowed, mark them as such.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-16-tabba@google.com
---
 arch/arm64/kvm/hyp/include/nvhe/fixed_config.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
index e91922daa8ca8..8d97dff4bb7b1 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
@@ -69,6 +69,8 @@
 	ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SSBS) \
 	)
 
+#define PVM_ID_AA64PFR2_ALLOW 0ULL
+
 /*
  * Allow for protected VMs:
  * - Mixed-endian
@@ -101,6 +103,7 @@
  * - Privileged Access Never
  * - SError interrupt exceptions from speculative reads
  * - Enhanced Translation Synchronization
+ * - Control for cache maintenance permission
  */
 #define PVM_ID_AA64MMFR1_ALLOW (\
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS) | \
@@ -108,7 +111,8 @@
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HPDS) | \
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_PAN) | \
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_SpecSEI) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_ETS) \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_ETS) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_CMOW) \
 	)
 
 /*
@@ -133,6 +137,8 @@
 	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_E0PD) \
 	)
 
+#define PVM_ID_AA64MMFR3_ALLOW (0ULL)
+
 /*
  * No support for Scalable Vectors for protected VMs:
  *	Requires additional support from KVM, e.g., context-switching and
-- 
GitLab


From 21de26dbc5170dde8e4dfbfa1ecb77804ed6a377 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:56 +0000
Subject: [PATCH 1534/4076] KVM: arm64: Mark PAuth as a restricted feature for
 protected VMs

Protected VMs will only support basic PAuth (FEAT_PAuth). Mark it
as restricted to ensure that later versions aren't supported for
protected guests.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-17-tabba@google.com
---
 arch/arm64/kvm/hyp/include/nvhe/fixed_config.h | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
index 8d97dff4bb7b1..51f043649146a 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
@@ -184,10 +184,18 @@
 	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RNDR) \
 	)
 
+/* Restrict pointer authentication to the basic version. */
+#define PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED (\
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA), ID_AA64ISAR1_EL1_APA_PAuth) | \
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API), ID_AA64ISAR1_EL1_API_PAuth) \
+	)
+
+#define PVM_ID_AA64ISAR2_RESTRICT_UNSIGNED (\
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3), ID_AA64ISAR2_EL1_APA3_PAuth) \
+	)
+
 #define PVM_ID_AA64ISAR1_ALLOW (\
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_DPB) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_JSCVT) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_FCMA) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_LRCPC) | \
@@ -202,8 +210,8 @@
 	)
 
 #define PVM_ID_AA64ISAR2_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_ATS1A)| \
 	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_MOPS) \
 	)
 
-- 
GitLab


From 9d52612690985fc0ee1ae1fbad61530a4f6bbb53 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 14 Dec 2023 10:01:57 +0000
Subject: [PATCH 1535/4076] KVM: arm64: Trap external trace for protected VMs

pKVM does not support external trace for protected VMs. Trap
external trace, and add the ExtTrcBuff to make it possible to
check for the feature.

Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231214100158.2305400-18-tabba@google.com
---
 arch/arm64/kvm/hyp/nvhe/pkvm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 9d23a51d7f752..84b5c3f387d80 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -136,6 +136,10 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
 			cptr_set |= CPTR_EL2_TTA;
 	}
 
+	/* Trap External Trace */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids))
+		mdcr_clear |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT;
+
 	vcpu->arch.mdcr_el2 |= mdcr_set;
 	vcpu->arch.mdcr_el2 &= ~mdcr_clear;
 	vcpu->arch.cptr_el2 |= cptr_set;
-- 
GitLab


From becfce5233a78956654f36555f1b9187f8d11d56 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Wed, 29 Nov 2023 18:34:48 +0530
Subject: [PATCH 1536/4076] soundwire: amd: drop bus freq calculation and set
 'max_clk_freq'

max_dr_freq and curr_dr_freq is calculated and set in
sdw_bus_master_add(). Setting in the driver is reduanant, so drop that.
Set max_clk_freq instead.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Tested-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Link: https://lore.kernel.org/r/20231129130449.9892-1-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/amd_manager.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index a3b1f4e6f0f90..f54bb4dd2d101 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -950,13 +950,13 @@ static int amd_sdw_manager_probe(struct platform_device *pdev)
 
 	amd_manager->reg_mask = &sdw_manager_reg_mask_array[amd_manager->instance];
 	params = &amd_manager->bus.params;
-	params->max_dr_freq = AMD_SDW_DEFAULT_CLK_FREQ * 2;
-	params->curr_dr_freq = AMD_SDW_DEFAULT_CLK_FREQ * 2;
+
 	params->col = AMD_SDW_DEFAULT_COLUMNS;
 	params->row = AMD_SDW_DEFAULT_ROWS;
 	prop = &amd_manager->bus.prop;
 	prop->clk_freq = &amd_sdw_freq_tbl[0];
 	prop->mclk_freq = AMD_SDW_BUS_BASE_FREQ;
+	prop->max_clk_freq = AMD_SDW_DEFAULT_CLK_FREQ;
 
 	ret = sdw_bus_master_add(&amd_manager->bus, dev, dev->fwnode);
 	if (ret) {
-- 
GitLab


From 1e73427f66353b7fe21c138787ff2b711ca1c0dd Mon Sep 17 00:00:00 2001
From: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Date: Wed, 13 Dec 2023 18:31:16 +0100
Subject: [PATCH 1537/4076] tools/counter: add a flexible watch events tool

This adds a new counter tool to be able to test various watch events.
A flexible watch array can be populated from command line, each field
may be tuned with a dedicated command line sub-option in "--watch" string.
Several watch events can be defined, each can have specific watch options,
by using "--watch <watch 1 options> --watch <watch 2 options>".
Watch options is a comma separated list.

It also comes with a simple default watch (to monitor overflow/underflow
events), used when no watch parameters are provided. It's equivalent to:
counter_watch_events -w comp_count,scope_count,evt_ovf_udf

The print_usage() routine proposes another example, from the command line,
which generates a 2 elements watch array, to monitor:
- overflow underflow events
- capture events, on channel 3, that reads read captured data by
  specifying the component id (capture3_component_id being 7 here).

Signed-off-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Link: https://lore.kernel.org/r/20231213173117.4174511-2-fabrice.gasnier@foss.st.com
Signed-off-by: William Breathitt Gray <william.gray@linaro.org>
---
 tools/counter/Build                  |   1 +
 tools/counter/Makefile               |  12 +-
 tools/counter/counter_watch_events.c | 406 +++++++++++++++++++++++++++
 3 files changed, 417 insertions(+), 2 deletions(-)
 create mode 100644 tools/counter/counter_watch_events.c

diff --git a/tools/counter/Build b/tools/counter/Build
index 33f4a51d715ec..4bbadb7ec93af 100644
--- a/tools/counter/Build
+++ b/tools/counter/Build
@@ -1 +1,2 @@
 counter_example-y += counter_example.o
+counter_watch_events-y += counter_watch_events.o
diff --git a/tools/counter/Makefile b/tools/counter/Makefile
index b2c2946f44c9f..d82d35a520f61 100644
--- a/tools/counter/Makefile
+++ b/tools/counter/Makefile
@@ -12,9 +12,10 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include \
+	 -I$(srctree)/tools/include
 
-ALL_TARGETS := counter_example
+ALL_TARGETS := counter_example counter_watch_events
 ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
 
 all: $(ALL_PROGRAMS)
@@ -37,12 +38,19 @@ $(COUNTER_EXAMPLE): prepare FORCE
 $(OUTPUT)counter_example: $(COUNTER_EXAMPLE)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
 
+COUNTER_WATCH_EVENTS := $(OUTPUT)counter_watch_events.o
+$(COUNTER_WATCH_EVENTS): prepare FORCE
+	$(Q)$(MAKE) $(build)=counter_watch_events
+$(OUTPUT)counter_watch_events: $(COUNTER_WATCH_EVENTS)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+
 clean:
 	rm -f $(ALL_PROGRAMS)
 	rm -rf $(OUTPUT)include/linux/counter.h
 	rm -df $(OUTPUT)include/linux
 	rm -df $(OUTPUT)include
 	find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+	find $(or $(OUTPUT),.) -name '\.*.o.cmd' -delete
 
 install: $(ALL_PROGRAMS)
 	install -d -m 755 $(DESTDIR)$(bindir);		\
diff --git a/tools/counter/counter_watch_events.c b/tools/counter/counter_watch_events.c
new file mode 100644
index 0000000000000..3898fe7e35ece
--- /dev/null
+++ b/tools/counter/counter_watch_events.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Counter Watch Events - Test various counter watch events in a userspace application
+ *
+ * Copyright (C) STMicroelectronics 2023 - All Rights Reserved
+ * Author: Fabrice Gasnier <fabrice.gasnier@foss.st.com>.
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <linux/counter.h>
+#include <linux/kernel.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+static struct counter_watch simple_watch[] = {
+	{
+		/* Component data: Count 0 count */
+		.component.type = COUNTER_COMPONENT_COUNT,
+		.component.scope = COUNTER_SCOPE_COUNT,
+		.component.parent = 0,
+		/* Event type: overflow or underflow */
+		.event = COUNTER_EVENT_OVERFLOW_UNDERFLOW,
+		/* Device event channel 0 */
+		.channel = 0,
+	},
+};
+
+static const char * const counter_event_type_name[] = {
+	"COUNTER_EVENT_OVERFLOW",
+	"COUNTER_EVENT_UNDERFLOW",
+	"COUNTER_EVENT_OVERFLOW_UNDERFLOW",
+	"COUNTER_EVENT_THRESHOLD",
+	"COUNTER_EVENT_INDEX",
+	"COUNTER_EVENT_CHANGE_OF_STATE",
+	"COUNTER_EVENT_CAPTURE",
+};
+
+static const char * const counter_component_type_name[] = {
+	"COUNTER_COMPONENT_NONE",
+	"COUNTER_COMPONENT_SIGNAL",
+	"COUNTER_COMPONENT_COUNT",
+	"COUNTER_COMPONENT_FUNCTION",
+	"COUNTER_COMPONENT_SYNAPSE_ACTION",
+	"COUNTER_COMPONENT_EXTENSION",
+};
+
+static const char * const counter_scope_name[] = {
+	"COUNTER_SCOPE_DEVICE",
+	"COUNTER_SCOPE_SIGNAL",
+	"COUNTER_SCOPE_COUNT",
+};
+
+static void print_watch(struct counter_watch *watch, int nwatch)
+{
+	int i;
+
+	/* prints the watch array in C-like structure */
+	printf("watch[%d] = {\n", nwatch);
+	for (i = 0; i < nwatch; i++) {
+		printf(" [%d] =\t{\n"
+		       "\t\t.component.type = %s\n"
+		       "\t\t.component.scope = %s\n"
+		       "\t\t.component.parent = %d\n"
+		       "\t\t.component.id = %d\n"
+		       "\t\t.event = %s\n"
+		       "\t\t.channel = %d\n"
+		       "\t},\n",
+		       i,
+		       counter_component_type_name[watch[i].component.type],
+		       counter_scope_name[watch[i].component.scope],
+		       watch[i].component.parent,
+		       watch[i].component.id,
+		       counter_event_type_name[watch[i].event],
+		       watch[i].channel);
+	}
+	printf("};\n");
+}
+
+static void print_usage(void)
+{
+	fprintf(stderr, "Usage:\n\n"
+		"counter_watch_events [options] [-w <watchoptions>]\n"
+		"counter_watch_events [options] [-w <watch1 options>] [-w <watch2 options>]...\n"
+		"\n"
+		"When no --watch option has been provided, simple watch example is used:\n"
+		"counter_watch_events [options] -w comp_count,scope_count,evt_ovf_udf\n"
+		"\n"
+		"Test various watch events for given counter device.\n"
+		"\n"
+		"Options:\n"
+		"  -d, --debug                Prints debug information\n"
+		"  -h, --help                 Prints usage\n"
+		"  -n, --device-num <n>       Use /dev/counter<n> [default: /dev/counter0]\n"
+		"  -l, --loop <n>             Loop for <n> events [default: 0 (forever)]\n"
+		"  -w, --watch <watchoptions> comma-separated list of watch options\n"
+		"\n"
+		"Watch options:\n"
+		"  scope_device               (COUNTER_SCOPE_DEVICE) [default: scope_device]\n"
+		"  scope_signal               (COUNTER_SCOPE_SIGNAL)\n"
+		"  scope_count                (COUNTER_SCOPE_COUNT)\n"
+		"\n"
+		"  comp_none                  (COUNTER_COMPONENT_NONE) [default: comp_none]\n"
+		"  comp_signal                (COUNTER_COMPONENT_SIGNAL)\n"
+		"  comp_count                 (COUNTER_COMPONENT_COUNT)\n"
+		"  comp_function              (COUNTER_COMPONENT_FUNCTION)\n"
+		"  comp_synapse_action        (COUNTER_COMPONENT_SYNAPSE_ACTION)\n"
+		"  comp_extension             (COUNTER_COMPONENT_EXTENSION)\n"
+		"\n"
+		"  evt_ovf                    (COUNTER_EVENT_OVERFLOW) [default: evt_ovf]\n"
+		"  evt_udf                    (COUNTER_EVENT_UNDERFLOW)\n"
+		"  evt_ovf_udf                (COUNTER_EVENT_OVERFLOW_UNDERFLOW)\n"
+		"  evt_threshold              (COUNTER_EVENT_THRESHOLD)\n"
+		"  evt_index                  (COUNTER_EVENT_INDEX)\n"
+		"  evt_change_of_state        (COUNTER_EVENT_CHANGE_OF_STATE)\n"
+		"  evt_capture                (COUNTER_EVENT_CAPTURE)\n"
+		"\n"
+		"  chan=<n>                   channel <n> for this watch [default: 0]\n"
+		"  id=<n>                     componend id <n> for this watch [default: 0]\n"
+		"  parent=<n>                 componend parent <n> for this watch [default: 0]\n"
+		"\n"
+		"Example with two watched events:\n\n"
+		"counter_watch_events -d \\\n"
+		"\t-w comp_count,scope_count,evt_ovf_udf \\\n"
+		"\t-w comp_extension,scope_count,evt_capture,id=7,chan=3\n"
+		);
+}
+
+static const struct option longopts[] = {
+	{ "debug",		no_argument,       0, 'd' },
+	{ "help",		no_argument,       0, 'h' },
+	{ "device-num",		required_argument, 0, 'n' },
+	{ "loop",		required_argument, 0, 'l' },
+	{ "watch",		required_argument, 0, 'w' },
+	{ },
+};
+
+/* counter watch subopts */
+enum {
+	WATCH_SCOPE_DEVICE,
+	WATCH_SCOPE_SIGNAL,
+	WATCH_SCOPE_COUNT,
+	WATCH_COMPONENT_NONE,
+	WATCH_COMPONENT_SIGNAL,
+	WATCH_COMPONENT_COUNT,
+	WATCH_COMPONENT_FUNCTION,
+	WATCH_COMPONENT_SYNAPSE_ACTION,
+	WATCH_COMPONENT_EXTENSION,
+	WATCH_EVENT_OVERFLOW,
+	WATCH_EVENT_UNDERFLOW,
+	WATCH_EVENT_OVERFLOW_UNDERFLOW,
+	WATCH_EVENT_THRESHOLD,
+	WATCH_EVENT_INDEX,
+	WATCH_EVENT_CHANGE_OF_STATE,
+	WATCH_EVENT_CAPTURE,
+	WATCH_CHANNEL,
+	WATCH_ID,
+	WATCH_PARENT,
+	WATCH_SUBOPTS_MAX,
+};
+
+static char * const counter_watch_subopts[WATCH_SUBOPTS_MAX + 1] = {
+	/* component.scope */
+	[WATCH_SCOPE_DEVICE] = "scope_device",
+	[WATCH_SCOPE_SIGNAL] = "scope_signal",
+	[WATCH_SCOPE_COUNT] = "scope_count",
+	/* component.type */
+	[WATCH_COMPONENT_NONE] = "comp_none",
+	[WATCH_COMPONENT_SIGNAL] = "comp_signal",
+	[WATCH_COMPONENT_COUNT] = "comp_count",
+	[WATCH_COMPONENT_FUNCTION] = "comp_function",
+	[WATCH_COMPONENT_SYNAPSE_ACTION] = "comp_synapse_action",
+	[WATCH_COMPONENT_EXTENSION] = "comp_extension",
+	/* event */
+	[WATCH_EVENT_OVERFLOW] = "evt_ovf",
+	[WATCH_EVENT_UNDERFLOW] = "evt_udf",
+	[WATCH_EVENT_OVERFLOW_UNDERFLOW] = "evt_ovf_udf",
+	[WATCH_EVENT_THRESHOLD] = "evt_threshold",
+	[WATCH_EVENT_INDEX] = "evt_index",
+	[WATCH_EVENT_CHANGE_OF_STATE] = "evt_change_of_state",
+	[WATCH_EVENT_CAPTURE] = "evt_capture",
+	/* channel, id, parent */
+	[WATCH_CHANNEL] = "chan",
+	[WATCH_ID] = "id",
+	[WATCH_PARENT] = "parent",
+	/* Empty entry ends the opts array */
+	NULL
+};
+
+int main(int argc, char **argv)
+{
+	int c, fd, i, ret, rc = 0, debug = 0, loop = 0, dev_num = 0, nwatch = 0;
+	struct counter_event event_data;
+	char *device_name = NULL, *subopts, *value;
+	struct counter_watch *watches;
+
+	/*
+	 * 1st pass:
+	 * - list watch events number to allocate the watch array.
+	 * - parse normal options (other than watch options)
+	 */
+	while ((c = getopt_long(argc, argv, "dhn:l:w:", longopts, NULL)) != -1) {
+		switch (c) {
+		case 'd':
+			debug = 1;
+			break;
+		case 'h':
+			print_usage();
+			return EXIT_SUCCESS;
+		case 'n':
+			dev_num = strtoul(optarg, NULL, 10);
+			if (errno) {
+				perror("strtol failed: --device-num <n>\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'l':
+			loop = strtol(optarg, NULL, 10);
+			if (errno) {
+				perror("strtol failed: --loop <n>\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'w':
+			nwatch++;
+			break;
+		default:
+			return EXIT_FAILURE;
+		};
+	};
+
+	if (nwatch) {
+		watches = calloc(nwatch, sizeof(*watches));
+		if (!watches) {
+			perror("Error allocating watches\n");
+			return EXIT_FAILURE;
+		}
+	} else {
+		/* default to simple watch example */
+		watches = simple_watch;
+		nwatch = ARRAY_SIZE(simple_watch);
+	}
+
+	/* 2nd pass: parse watch sub-options to fill in watch array */
+	optind = 1;
+	i = 0;
+	while ((c = getopt_long(argc, argv, "dhn:l:w:", longopts, NULL)) != -1) {
+		switch (c) {
+		case 'w':
+			subopts = optarg;
+			while (*subopts != '\0') {
+				ret = getsubopt(&subopts, counter_watch_subopts, &value);
+				switch (ret) {
+				case WATCH_SCOPE_DEVICE:
+				case WATCH_SCOPE_SIGNAL:
+				case WATCH_SCOPE_COUNT:
+					/* match with counter_scope */
+					watches[i].component.scope = ret;
+					break;
+				case WATCH_COMPONENT_NONE:
+				case WATCH_COMPONENT_SIGNAL:
+				case WATCH_COMPONENT_COUNT:
+				case WATCH_COMPONENT_FUNCTION:
+				case WATCH_COMPONENT_SYNAPSE_ACTION:
+				case WATCH_COMPONENT_EXTENSION:
+					/* match counter_component_type: subtract enum value */
+					ret -= WATCH_COMPONENT_NONE;
+					watches[i].component.type = ret;
+					break;
+				case WATCH_EVENT_OVERFLOW:
+				case WATCH_EVENT_UNDERFLOW:
+				case WATCH_EVENT_OVERFLOW_UNDERFLOW:
+				case WATCH_EVENT_THRESHOLD:
+				case WATCH_EVENT_INDEX:
+				case WATCH_EVENT_CHANGE_OF_STATE:
+				case WATCH_EVENT_CAPTURE:
+					/* match counter_event_type: subtract enum value */
+					ret -= WATCH_EVENT_OVERFLOW;
+					watches[i].event = ret;
+					break;
+				case WATCH_CHANNEL:
+					if (!value) {
+						fprintf(stderr, "Invalid chan=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					watches[i].channel = strtoul(value, NULL, 10);
+					if (errno) {
+						perror("strtoul failed: chan=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					break;
+				case WATCH_ID:
+					if (!value) {
+						fprintf(stderr, "Invalid id=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					watches[i].component.id = strtoul(value, NULL, 10);
+					if (errno) {
+						perror("strtoul failed: id=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					break;
+				case WATCH_PARENT:
+					if (!value) {
+						fprintf(stderr, "Invalid parent=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					watches[i].component.parent = strtoul(value, NULL, 10);
+					if (errno) {
+						perror("strtoul failed: parent=<number>\n");
+						rc = EXIT_FAILURE;
+						goto err_free_watches;
+					}
+					break;
+				default:
+					fprintf(stderr, "Unknown suboption '%s'\n", value);
+					rc = EXIT_FAILURE;
+					goto err_free_watches;
+				}
+			}
+			i++;
+			break;
+		}
+	};
+
+	if (debug)
+		print_watch(watches, nwatch);
+
+	ret = asprintf(&device_name, "/dev/counter%d", dev_num);
+	if (ret < 0) {
+		fprintf(stderr, "asprintf failed\n");
+		rc = EXIT_FAILURE;
+		goto err_free_watches;
+	}
+
+	if (debug)
+		printf("Opening %s\n", device_name);
+
+	fd = open(device_name, O_RDWR);
+	if (fd == -1) {
+		fprintf(stderr, "Unable to open %s: %s\n", device_name, strerror(errno));
+		free(device_name);
+		rc = EXIT_FAILURE;
+		goto err_free_watches;
+	}
+	free(device_name);
+
+	for (i = 0; i < nwatch; i++) {
+		ret = ioctl(fd, COUNTER_ADD_WATCH_IOCTL, watches + i);
+		if (ret == -1) {
+			fprintf(stderr, "Error adding watches[%d]: %s\n", i,
+				strerror(errno));
+			rc = EXIT_FAILURE;
+			goto err_close;
+		}
+	}
+
+	ret = ioctl(fd, COUNTER_ENABLE_EVENTS_IOCTL);
+	if (ret == -1) {
+		perror("Error enabling events");
+		rc = EXIT_FAILURE;
+		goto err_close;
+	}
+
+	for (i = 0; loop <= 0 || i < loop; i++) {
+		ret = read(fd, &event_data, sizeof(event_data));
+		if (ret == -1) {
+			perror("Failed to read event data");
+			rc = EXIT_FAILURE;
+			goto err_close;
+		}
+
+		if (ret != sizeof(event_data)) {
+			fprintf(stderr, "Failed to read event data (got: %d)\n", ret);
+			rc = EXIT_FAILURE;
+			goto err_close;
+		}
+
+		printf("Timestamp: %llu\tData: %llu\t event: %s\tch: %d\n",
+		       event_data.timestamp, event_data.value,
+		       counter_event_type_name[event_data.watch.event],
+		       event_data.watch.channel);
+
+		if (event_data.status) {
+			fprintf(stderr, "Error %d: %s\n", event_data.status,
+				strerror(event_data.status));
+		}
+	}
+
+err_close:
+	close(fd);
+err_free_watches:
+	if (watches != simple_watch)
+		free(watches);
+
+	return rc;
+}
-- 
GitLab


From 8e21e4693d8502ee31ef7984e16c3d9cab6c926a Mon Sep 17 00:00:00 2001
From: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Date: Wed, 13 Dec 2023 18:31:17 +0100
Subject: [PATCH 1538/4076] MAINTAINERS: add myself as counter watch events
 tool maintainer

Add MAINTAINERS entry for the counter watch events tool. William has
been asking to add at least me as the point of contact for this utility.

Signed-off-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Link: https://lore.kernel.org/r/20231213173117.4174511-3-fabrice.gasnier@foss.st.com
Signed-off-by: William Breathitt Gray <william.gray@linaro.org>
---
 MAINTAINERS | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index e2c6187a3ac80..d3356a2d5732f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5377,6 +5377,12 @@ F:	include/linux/counter.h
 F:	include/uapi/linux/counter.h
 F:	tools/counter/
 
+COUNTER WATCH EVENTS TOOL
+M:	Fabrice Gasnier <fabrice.gasnier@foss.st.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	tools/counter/counter_watch_events.c
+
 CP2615 I2C DRIVER
 M:	Bence Csókás <bence98@sch.bme.hu>
 S:	Maintained
-- 
GitLab


From b2264b62defb42abd748d8937b8de758f8fcabf2 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sat, 16 Dec 2023 07:53:00 -0500
Subject: [PATCH 1539/4076] staging: rtl8192e: rename variable pHT

Coding style issue, checkpatch Avoid CamelCase,
rename it. pHT -> ht

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231216125303.3404-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 90a9356d78cad..29c3d33bf5a66 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -230,17 +230,17 @@ void ht_reset_iot_setting(struct rt_hi_throughput *ht_info)
 void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 				  u8 *len, u8 is_encrypt, bool assoc)
 {
-	struct rt_hi_throughput *pHT = ieee->ht_info;
+	struct rt_hi_throughput *ht = ieee->ht_info;
 	struct ht_capab_ele *pCapELE = NULL;
 
-	if (!pos_ht_cap || !pHT) {
+	if (!pos_ht_cap || !ht) {
 		netdev_warn(ieee->dev,
 			    "%s(): posHTCap and ht_info are null\n", __func__);
 		return;
 	}
 	memset(pos_ht_cap, 0, *len);
 
-	if ((assoc) && (pHT->ePeerHTSpecVer == HT_SPEC_VER_EWC)) {
+	if ((assoc) && (ht->ePeerHTSpecVer == HT_SPEC_VER_EWC)) {
 		static const u8	EWC11NHTCap[] = { 0x00, 0x90, 0x4c, 0x33 };
 
 		memcpy(pos_ht_cap, EWC11NHTCap, sizeof(EWC11NHTCap));
@@ -289,16 +289,16 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 	pCapELE->ASCap = 0;
 
 	if (assoc) {
-		if (pHT->iot_action & HT_IOT_ACT_DISABLE_MCS15)
+		if (ht->iot_action & HT_IOT_ACT_DISABLE_MCS15)
 			pCapELE->MCS[1] &= 0x7f;
 
-		if (pHT->iot_action & HT_IOT_ACT_DISABLE_MCS14)
+		if (ht->iot_action & HT_IOT_ACT_DISABLE_MCS14)
 			pCapELE->MCS[1] &= 0xbf;
 
-		if (pHT->iot_action & HT_IOT_ACT_DISABLE_ALL_2SS)
+		if (ht->iot_action & HT_IOT_ACT_DISABLE_ALL_2SS)
 			pCapELE->MCS[1] &= 0x00;
 
-		if (pHT->iot_action & HT_IOT_ACT_DISABLE_RX_40MHZ_SHORT_GI)
+		if (ht->iot_action & HT_IOT_ACT_DISABLE_RX_40MHZ_SHORT_GI)
 			pCapELE->ShortGI40Mhz		= 0;
 
 		if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev)) {
-- 
GitLab


From d08c910ea89cf2f7e0252bb717adeb27379a119f Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sat, 16 Dec 2023 07:53:01 -0500
Subject: [PATCH 1540/4076] staging: rtl8192e: rename variable pCapELE

Coding style issue, checkpatch Avoid CamelCase,
rename it. pCapELE -> cap_ele

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231216125303.3404-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 64 +++++++++++------------
 1 file changed, 32 insertions(+), 32 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 29c3d33bf5a66..8d90371304244 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -231,7 +231,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 				  u8 *len, u8 is_encrypt, bool assoc)
 {
 	struct rt_hi_throughput *ht = ieee->ht_info;
-	struct ht_capab_ele *pCapELE = NULL;
+	struct ht_capab_ele *cap_ele = NULL;
 
 	if (!pos_ht_cap || !ht) {
 		netdev_warn(ieee->dev,
@@ -244,66 +244,66 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 		static const u8	EWC11NHTCap[] = { 0x00, 0x90, 0x4c, 0x33 };
 
 		memcpy(pos_ht_cap, EWC11NHTCap, sizeof(EWC11NHTCap));
-		pCapELE = (struct ht_capab_ele *)&pos_ht_cap[4];
+		cap_ele = (struct ht_capab_ele *)&pos_ht_cap[4];
 		*len = 30 + 2;
 	} else {
-		pCapELE = (struct ht_capab_ele *)pos_ht_cap;
+		cap_ele = (struct ht_capab_ele *)pos_ht_cap;
 		*len = 26 + 2;
 	}
 
-	pCapELE->AdvCoding		= 0;
+	cap_ele->AdvCoding		= 0;
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev))
-		pCapELE->ChlWidth = 0;
+		cap_ele->ChlWidth = 0;
 	else
-		pCapELE->ChlWidth = 1;
+		cap_ele->ChlWidth = 1;
 
-	pCapELE->MimoPwrSave		= 3;
-	pCapELE->GreenField		= 0;
-	pCapELE->ShortGI20Mhz		= 1;
-	pCapELE->ShortGI40Mhz		= 1;
+	cap_ele->MimoPwrSave		= 3;
+	cap_ele->GreenField		= 0;
+	cap_ele->ShortGI20Mhz		= 1;
+	cap_ele->ShortGI40Mhz		= 1;
 
-	pCapELE->TxSTBC			= 1;
-	pCapELE->RxSTBC			= 0;
-	pCapELE->DelayBA		= 0;
-	pCapELE->MaxAMSDUSize = (MAX_RECEIVE_BUFFER_SIZE >= 7935) ? 1 : 0;
-	pCapELE->DssCCk = 1;
-	pCapELE->PSMP = 0;
-	pCapELE->LSigTxopProtect = 0;
+	cap_ele->TxSTBC			= 1;
+	cap_ele->RxSTBC			= 0;
+	cap_ele->DelayBA		= 0;
+	cap_ele->MaxAMSDUSize = (MAX_RECEIVE_BUFFER_SIZE >= 7935) ? 1 : 0;
+	cap_ele->DssCCk = 1;
+	cap_ele->PSMP = 0;
+	cap_ele->LSigTxopProtect = 0;
 
 	netdev_dbg(ieee->dev,
 		   "TX HT cap/info ele BW=%d MaxAMSDUSize:%d DssCCk:%d\n",
-		   pCapELE->ChlWidth, pCapELE->MaxAMSDUSize, pCapELE->DssCCk);
+		   cap_ele->ChlWidth, cap_ele->MaxAMSDUSize, cap_ele->DssCCk);
 
 	if (is_encrypt) {
-		pCapELE->MPDUDensity	= 7;
-		pCapELE->MaxRxAMPDUFactor	= 2;
+		cap_ele->MPDUDensity	= 7;
+		cap_ele->MaxRxAMPDUFactor	= 2;
 	} else {
-		pCapELE->MaxRxAMPDUFactor	= 3;
-		pCapELE->MPDUDensity	= 0;
+		cap_ele->MaxRxAMPDUFactor	= 3;
+		cap_ele->MPDUDensity	= 0;
 	}
 
-	memcpy(pCapELE->MCS, ieee->reg_dot11ht_oper_rate_set, 16);
-	memset(&pCapELE->ExtHTCapInfo, 0, 2);
-	memset(pCapELE->TxBFCap, 0, 4);
+	memcpy(cap_ele->MCS, ieee->reg_dot11ht_oper_rate_set, 16);
+	memset(&cap_ele->ExtHTCapInfo, 0, 2);
+	memset(cap_ele->TxBFCap, 0, 4);
 
-	pCapELE->ASCap = 0;
+	cap_ele->ASCap = 0;
 
 	if (assoc) {
 		if (ht->iot_action & HT_IOT_ACT_DISABLE_MCS15)
-			pCapELE->MCS[1] &= 0x7f;
+			cap_ele->MCS[1] &= 0x7f;
 
 		if (ht->iot_action & HT_IOT_ACT_DISABLE_MCS14)
-			pCapELE->MCS[1] &= 0xbf;
+			cap_ele->MCS[1] &= 0xbf;
 
 		if (ht->iot_action & HT_IOT_ACT_DISABLE_ALL_2SS)
-			pCapELE->MCS[1] &= 0x00;
+			cap_ele->MCS[1] &= 0x00;
 
 		if (ht->iot_action & HT_IOT_ACT_DISABLE_RX_40MHZ_SHORT_GI)
-			pCapELE->ShortGI40Mhz		= 0;
+			cap_ele->ShortGI40Mhz		= 0;
 
 		if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev)) {
-			pCapELE->ChlWidth = 0;
-			pCapELE->MCS[1] = 0;
+			cap_ele->ChlWidth = 0;
+			cap_ele->MCS[1] = 0;
 		}
 	}
 }
-- 
GitLab


From 2e9b84b7f28fcc73570c5a50a8e08087d15bb893 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sat, 16 Dec 2023 07:53:02 -0500
Subject: [PATCH 1541/4076] staging: rtl8192e: rename variable
 HTGetHighestMCSRate

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTGetHighestMCSRate -> ht_get_highest_mcs_rate

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231216125303.3404-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_wx.c      | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 8d90371304244..6c1af19d67d2a 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -357,7 +357,7 @@ static u8 ht_pick_mcs_rate(struct rtllib_device *ieee, u8 *pOperateMCS)
 	return true;
 }
 
-u8 HTGetHighestMCSRate(struct rtllib_device *ieee, u8 *pMCSRateSet,
+u8 ht_get_highest_mcs_rate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 		       u8 *pMCSFilter)
 {
 	u8		i, j;
@@ -493,7 +493,7 @@ void ht_on_assoc_rsp(struct rtllib_device *ieee)
 	HTFilterMCSRate(ieee, pPeerHTCap->MCS, ieee->dot11ht_oper_rate_set);
 
 	pMcsFilter = MCS_FILTER_ALL;
-	ieee->HTHighestOperaRate = HTGetHighestMCSRate(ieee,
+	ieee->HTHighestOperaRate = ht_get_highest_mcs_rate(ieee,
 						       ieee->dot11ht_oper_rate_set,
 						       pMcsFilter);
 	ieee->HTCurrentOperaRate = ieee->HTHighestOperaRate;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index b4413cfcb17e2..966a62cfcfde5 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1763,7 +1763,7 @@ void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 				   struct rtllib_network *pNetwork);
 void HT_update_self_and_peer_setting(struct rtllib_device *ieee,
 				     struct rtllib_network *pNetwork);
-u8 HTGetHighestMCSRate(struct rtllib_device *ieee, u8 *pMCSRateSet,
+u8 ht_get_highest_mcs_rate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 		       u8 *pMCSFilter);
 extern u8 MCS_FILTER_ALL[];
 extern u16 MCS_DATA_RATE[2][2][77];
diff --git a/drivers/staging/rtl8192e/rtllib_wx.c b/drivers/staging/rtl8192e/rtllib_wx.c
index a37250de7ba37..f92ec0faf4d56 100644
--- a/drivers/staging/rtl8192e/rtllib_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_wx.c
@@ -134,7 +134,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee,
 				((ht_cap->ShortGI40Mhz) ? 1 : 0) :
 				((ht_cap->ShortGI20Mhz) ? 1 : 0);
 
-		max_mcs = HTGetHighestMCSRate(ieee, ht_cap->MCS,
+		max_mcs = ht_get_highest_mcs_rate(ieee, ht_cap->MCS,
 					      MCS_FILTER_ALL);
 		rate = MCS_DATA_RATE[is40M][isShortGI][max_mcs & 0x7f];
 		if (rate > max_rate)
-- 
GitLab


From 936637892020a6d7a566e86ef29be0a8a825354c Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Sat, 16 Dec 2023 07:53:03 -0500
Subject: [PATCH 1542/4076] staging: rtl8192e: renamed variable HTFilterMCSRate

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTFilterMCSRate -> ht_filter_mcs_rate

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231216125303.3404-5-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 6c1af19d67d2a..0d57bcda33b4d 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -397,7 +397,7 @@ u8 ht_get_highest_mcs_rate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 	return mcsRate | 0x80;
 }
 
-static u8 HTFilterMCSRate(struct rtllib_device *ieee, u8 *pSupportMCS,
+static u8 ht_filter_mcs_rate(struct rtllib_device *ieee, u8 *pSupportMCS,
 			  u8 *pOperateMCS)
 {
 	u8 i;
@@ -490,7 +490,7 @@ void ht_on_assoc_rsp(struct rtllib_device *ieee)
 
 	ht_iot_act_determine_ra_func(ieee, ((pPeerHTCap->MCS[1]) != 0));
 
-	HTFilterMCSRate(ieee, pPeerHTCap->MCS, ieee->dot11ht_oper_rate_set);
+	ht_filter_mcs_rate(ieee, pPeerHTCap->MCS, ieee->dot11ht_oper_rate_set);
 
 	pMcsFilter = MCS_FILTER_ALL;
 	ieee->HTHighestOperaRate = ht_get_highest_mcs_rate(ieee,
-- 
GitLab


From a99ead4e2b9f75fa29e49ba6c2c42834eb0cc60c Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sat, 16 Dec 2023 12:20:38 -0800
Subject: [PATCH 1543/4076] Staging: rtl8192e: rename linked list reference:
 List

Rename variable List to list, to fix Avoid CamelCase checkpatch warning.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231216202038.10777-1-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_TS.h     |  2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 78 +++++++++++------------
 drivers/staging/rtl8192e/rtllib.h         |  2 +-
 drivers/staging/rtl8192e/rtllib_rx.c      | 30 ++++-----
 4 files changed, 56 insertions(+), 56 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_TS.h b/drivers/staging/rtl8192e/rtl819x_TS.h
index 31f7cfbb3aa52..5b0e4cb572d26 100644
--- a/drivers/staging/rtl8192e/rtl819x_TS.h
+++ b/drivers/staging/rtl8192e/rtl819x_TS.h
@@ -17,7 +17,7 @@ enum tr_select {
 };
 
 struct ts_common_info {
-	struct list_head		List;
+	struct list_head		list;
 	u8				addr[ETH_ALEN];
 	struct qos_tsinfo tspec;
 };
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index bec73bc53dd08..86db56f3900d3 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -25,7 +25,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 		while (!list_empty(&ts->rx_pending_pkt_list)) {
 			pReorderEntry = (struct rx_reorder_entry *)
 					list_entry(ts->rx_pending_pkt_list.prev,
-					struct rx_reorder_entry, List);
+					struct rx_reorder_entry, list);
 			if (index == 0)
 				ts->rx_indicate_seq = pReorderEntry->SeqNum;
 
@@ -33,7 +33,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 				    ts->rx_indicate_seq) ||
 			    SN_EQUAL(pReorderEntry->SeqNum,
 				     ts->rx_indicate_seq)) {
-				list_del_init(&pReorderEntry->List);
+				list_del_init(&pReorderEntry->list);
 
 				if (SN_EQUAL(pReorderEntry->SeqNum,
 				    ts->rx_indicate_seq))
@@ -47,7 +47,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 							 pReorderEntry->prxb;
 				index++;
 
-				list_add_tail(&pReorderEntry->List,
+				list_add_tail(&pReorderEntry->list,
 					      &ieee->RxReorder_Unused_List);
 			} else {
 				bPktInBuf = true;
@@ -138,7 +138,7 @@ void rtllib_ts_init(struct rtllib_device *ieee)
 			    rtllib_tx_ba_inact_timeout, 0);
 
 		ResetTxTsEntry(pTxTS);
-		list_add_tail(&pTxTS->ts_common_info.List,
+		list_add_tail(&pTxTS->ts_common_info.list,
 				&ieee->Tx_TS_Unused_List);
 		pTxTS++;
 	}
@@ -155,13 +155,13 @@ void rtllib_ts_init(struct rtllib_device *ieee)
 		timer_setup(&rxts->rx_pkt_pending_timer, RxPktPendingTimeout, 0);
 
 		ResetRxTsEntry(rxts);
-		list_add_tail(&rxts->ts_common_info.List,
+		list_add_tail(&rxts->ts_common_info.list,
 			      &ieee->Rx_TS_Unused_List);
 		rxts++;
 	}
 	INIT_LIST_HEAD(&ieee->RxReorder_Unused_List);
 	for (count = 0; count < REORDER_ENTRY_NUM; count++) {
-		list_add_tail(&pRxReorderEntry->List,
+		list_add_tail(&pRxReorderEntry->list,
 			      &ieee->RxReorder_Unused_List);
 		if (count == (REORDER_ENTRY_NUM - 1))
 			break;
@@ -196,17 +196,17 @@ static struct ts_common_info *SearchAdmitTRStream(struct rtllib_device *ieee,
 	for (dir = 0; dir <= DIR_BI_DIR; dir++) {
 		if (!search_dir[dir])
 			continue;
-		list_for_each_entry(pRet, psearch_list, List) {
+		list_for_each_entry(pRet, psearch_list, list) {
 			if (memcmp(pRet->addr, addr, 6) == 0 &&
 			    pRet->tspec.ucTSID == TID &&
 			    pRet->tspec.ucDirection == dir)
 				break;
 		}
-		if (&pRet->List  != psearch_list)
+		if (&pRet->list  != psearch_list)
 			break;
 	}
 
-	if (pRet && &pRet->List  != psearch_list)
+	if (pRet && &pRet->list  != psearch_list)
 		return pRet;
 	return NULL;
 }
@@ -286,8 +286,8 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 
 	if (!list_empty(pUnusedList)) {
 		(*ppTS) = list_entry(pUnusedList->next,
-			  struct ts_common_info, List);
-		list_del_init(&(*ppTS)->List);
+			  struct ts_common_info, list);
+		list_del_init(&(*ppTS)->list);
 		if (TxRxSelect == TX_DIR) {
 			struct tx_ts_record *tmp =
 				container_of(*ppTS,
@@ -309,7 +309,7 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 		ts_info->ucDirection = Dir;
 
 		MakeTSEntry(*ppTS, addr, &tspec);
-		list_add_tail(&((*ppTS)->List), pAddmitList);
+		list_add_tail(&((*ppTS)->list), pAddmitList);
 
 		return true;
 	}
@@ -335,10 +335,10 @@ static void RemoveTsEntry(struct rtllib_device *ieee,
 		while (!list_empty(&ts->rx_pending_pkt_list)) {
 			pRxReorderEntry = (struct rx_reorder_entry *)
 					list_entry(ts->rx_pending_pkt_list.prev,
-					struct rx_reorder_entry, List);
+					struct rx_reorder_entry, list);
 			netdev_dbg(ieee->dev,  "%s(): Delete SeqNum %d!\n",
 				   __func__, pRxReorderEntry->SeqNum);
-			list_del_init(&pRxReorderEntry->List);
+			list_del_init(&pRxReorderEntry->list);
 			{
 				int i = 0;
 				struct rtllib_rxb *prxb = pRxReorderEntry->prxb;
@@ -350,7 +350,7 @@ static void RemoveTsEntry(struct rtllib_device *ieee,
 				kfree(prxb);
 				prxb = NULL;
 			}
-			list_add_tail(&pRxReorderEntry->List,
+			list_add_tail(&pRxReorderEntry->list,
 				      &ieee->RxReorder_Unused_List);
 		}
 	} else {
@@ -366,37 +366,37 @@ void RemovePeerTS(struct rtllib_device *ieee, u8 *addr)
 
 	netdev_info(ieee->dev, "===========>%s, %pM\n", __func__, addr);
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Pending_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Pending_List, list) {
 		if (memcmp(ts->addr, addr, 6) == 0) {
 			RemoveTsEntry(ieee, ts, TX_DIR);
-			list_del_init(&ts->List);
-			list_add_tail(&ts->List, &ieee->Tx_TS_Unused_List);
+			list_del_init(&ts->list);
+			list_add_tail(&ts->list, &ieee->Tx_TS_Unused_List);
 		}
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Admit_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Admit_List, list) {
 		if (memcmp(ts->addr, addr, 6) == 0) {
 			netdev_info(ieee->dev,
 				    "====>remove Tx_TS_admin_list\n");
 			RemoveTsEntry(ieee, ts, TX_DIR);
-			list_del_init(&ts->List);
-			list_add_tail(&ts->List, &ieee->Tx_TS_Unused_List);
+			list_del_init(&ts->list);
+			list_add_tail(&ts->list, &ieee->Tx_TS_Unused_List);
 		}
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Pending_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Pending_List, list) {
 		if (memcmp(ts->addr, addr, 6) == 0) {
 			RemoveTsEntry(ieee, ts, RX_DIR);
-			list_del_init(&ts->List);
-			list_add_tail(&ts->List, &ieee->Rx_TS_Unused_List);
+			list_del_init(&ts->list);
+			list_add_tail(&ts->list, &ieee->Rx_TS_Unused_List);
 		}
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Admit_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Admit_List, list) {
 		if (memcmp(ts->addr, addr, 6) == 0) {
 			RemoveTsEntry(ieee, ts, RX_DIR);
-			list_del_init(&ts->List);
-			list_add_tail(&ts->List, &ieee->Rx_TS_Unused_List);
+			list_del_init(&ts->list);
+			list_add_tail(&ts->list, &ieee->Rx_TS_Unused_List);
 		}
 	}
 }
@@ -406,28 +406,28 @@ void RemoveAllTS(struct rtllib_device *ieee)
 {
 	struct ts_common_info *ts, *pTmpTS;
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Pending_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Pending_List, list) {
 		RemoveTsEntry(ieee, ts, TX_DIR);
-		list_del_init(&ts->List);
-		list_add_tail(&ts->List, &ieee->Tx_TS_Unused_List);
+		list_del_init(&ts->list);
+		list_add_tail(&ts->list, &ieee->Tx_TS_Unused_List);
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Admit_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Tx_TS_Admit_List, list) {
 		RemoveTsEntry(ieee, ts, TX_DIR);
-		list_del_init(&ts->List);
-		list_add_tail(&ts->List, &ieee->Tx_TS_Unused_List);
+		list_del_init(&ts->list);
+		list_add_tail(&ts->list, &ieee->Tx_TS_Unused_List);
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Pending_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Pending_List, list) {
 		RemoveTsEntry(ieee, ts, RX_DIR);
-		list_del_init(&ts->List);
-		list_add_tail(&ts->List, &ieee->Rx_TS_Unused_List);
+		list_del_init(&ts->list);
+		list_add_tail(&ts->list, &ieee->Rx_TS_Unused_List);
 	}
 
-	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Admit_List, List) {
+	list_for_each_entry_safe(ts, pTmpTS, &ieee->Rx_TS_Admit_List, list) {
 		RemoveTsEntry(ieee, ts, RX_DIR);
-		list_del_init(&ts->List);
-		list_add_tail(&ts->List, &ieee->Rx_TS_Unused_List);
+		list_del_init(&ts->list);
+		list_add_tail(&ts->list, &ieee->Rx_TS_Unused_List);
 	}
 }
 
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 966a62cfcfde5..09360129d5788 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1042,7 +1042,7 @@ struct bandwidth_autoswitch {
 #define REORDER_WIN_SIZE	128
 #define REORDER_ENTRY_NUM	128
 struct rx_reorder_entry {
-	struct list_head	List;
+	struct list_head	list;
 	u16			SeqNum;
 	struct rtllib_rxb *prxb;
 };
diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index 62d02576b4418..196eacc7a768a 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -411,19 +411,19 @@ static bool AddReorderEntry(struct rx_ts_record *ts,
 	while (pList->next != &ts->rx_pending_pkt_list) {
 		if (SN_LESS(pReorderEntry->SeqNum, ((struct rx_reorder_entry *)
 		    list_entry(pList->next, struct rx_reorder_entry,
-		    List))->SeqNum))
+		    list))->SeqNum))
 			pList = pList->next;
 		else if (SN_EQUAL(pReorderEntry->SeqNum,
 			((struct rx_reorder_entry *)list_entry(pList->next,
-			struct rx_reorder_entry, List))->SeqNum))
+			struct rx_reorder_entry, list))->SeqNum))
 			return false;
 		else
 			break;
 	}
-	pReorderEntry->List.next = pList->next;
-	pReorderEntry->List.next->prev = &pReorderEntry->List;
-	pReorderEntry->List.prev = pList;
-	pList->next = &pReorderEntry->List;
+	pReorderEntry->list.next = pList->next;
+	pReorderEntry->list.next->prev = &pReorderEntry->list;
+	pReorderEntry->list.prev = pList;
+	pList->next = &pReorderEntry->list;
 
 	return true;
 }
@@ -504,15 +504,15 @@ void rtllib_FlushRxTsPendingPkts(struct rtllib_device *ieee,
 
 		pRxReorderEntry = (struct rx_reorder_entry *)
 				  list_entry(ts->rx_pending_pkt_list.prev,
-					     struct rx_reorder_entry, List);
+					     struct rx_reorder_entry, list);
 		netdev_dbg(ieee->dev, "%s(): Indicate SeqNum %d!\n", __func__,
 			   pRxReorderEntry->SeqNum);
-		list_del_init(&pRxReorderEntry->List);
+		list_del_init(&pRxReorderEntry->list);
 
 		ieee->RfdArray[RfdCnt] = pRxReorderEntry->prxb;
 
 		RfdCnt = RfdCnt + 1;
-		list_add_tail(&pRxReorderEntry->List,
+		list_add_tail(&pRxReorderEntry->list,
 			      &ieee->RxReorder_Unused_List);
 	}
 	rtllib_indicate_packets(ieee, ieee->RfdArray, RfdCnt);
@@ -601,8 +601,8 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 		if (!list_empty(&ieee->RxReorder_Unused_List)) {
 			pReorderEntry = (struct rx_reorder_entry *)
 					list_entry(ieee->RxReorder_Unused_List.next,
-					struct rx_reorder_entry, List);
-			list_del_init(&pReorderEntry->List);
+					struct rx_reorder_entry, list);
+			list_del_init(&pReorderEntry->list);
 
 			/* Make a reorder entry and insert
 			 * into a the packet list.
@@ -617,7 +617,7 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 					   "%s(): Duplicate packet is dropped. IndicateSeq: %d, NewSeq: %d\n",
 					   __func__, ts->rx_indicate_seq,
 					   SeqNum);
-				list_add_tail(&pReorderEntry->List,
+				list_add_tail(&pReorderEntry->list,
 					      &ieee->RxReorder_Unused_List);
 
 				for (i = 0; i < prxb->nr_subframes; i++)
@@ -657,7 +657,7 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 		pReorderEntry = (struct rx_reorder_entry *)
 					list_entry(ts->rx_pending_pkt_list.prev,
 						   struct rx_reorder_entry,
-						   List);
+						   list);
 		if (SN_LESS(pReorderEntry->SeqNum, ts->rx_indicate_seq) ||
 		    SN_EQUAL(pReorderEntry->SeqNum, ts->rx_indicate_seq)) {
 			/* This protect struct buffer from overflow. */
@@ -669,7 +669,7 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 				break;
 			}
 
-			list_del_init(&pReorderEntry->List);
+			list_del_init(&pReorderEntry->list);
 
 			if (SN_EQUAL(pReorderEntry->SeqNum, ts->rx_indicate_seq))
 				ts->rx_indicate_seq = (ts->rx_indicate_seq + 1) %
@@ -680,7 +680,7 @@ static void RxReorderIndicatePacket(struct rtllib_device *ieee,
 				   __func__, pReorderEntry->SeqNum);
 			index++;
 
-			list_add_tail(&pReorderEntry->List,
+			list_add_tail(&pReorderEntry->list,
 				      &ieee->RxReorder_Unused_List);
 		} else {
 			bPktInBuf = true;
-- 
GitLab


From 4f8a3fffdff13bd44123d1957fd4455f49464e4f Mon Sep 17 00:00:00 2001
From: Dipendra Khadka <kdipendra88@gmail.com>
Date: Sun, 17 Dec 2023 16:54:43 +0000
Subject: [PATCH 1544/4076] drivers: staging: rtl8712: Fixes spelling mistake
 in rtl871x_mp_phy_regdef.h

The script checkpatch.pl reported spelling error
in rtl871x_mp_phy_regdef.h as below:

'''
WARNING: 'Tranceiver' may be misspelled - perhaps 'Transceiver'?
#129:
#define rFPGA0_XA_LSSIReadBack          0x8a0   /* Tranceiver LSSI Readback */
                                                   ^^^^^^^^^^
'''

This patch corrects a spelling error,
changing "Tranceiver" to "Transceiver."

Signed-off-by: Dipendra Khadka <kdipendra88@gmail.com>
Link: https://lore.kernel.org/r/20231217165444.448133-1-kdipendra88@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h b/drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h
index a08c5d2f59e38..bb9f83d58225d 100644
--- a/drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h
+++ b/drivers/staging/rtl8712/rtl871x_mp_phy_regdef.h
@@ -126,7 +126,7 @@
 #define	rFPGA0_AnalogParameter3		0x888	/* Useless now */
 #define	rFPGA0_AnalogParameter4		0x88c
 
-#define	rFPGA0_XA_LSSIReadBack		0x8a0	/* Tranceiver LSSI Readback */
+#define	rFPGA0_XA_LSSIReadBack		0x8a0	/* Transceiver LSSI Readback */
 #define	rFPGA0_XB_LSSIReadBack		0x8a4
 #define	rFPGA0_XC_LSSIReadBack		0x8a8
 #define	rFPGA0_XD_LSSIReadBack		0x8ac
-- 
GitLab


From fd00f665454fef2bdbcf27c7efceaf5f1b880bc9 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 17 Dec 2023 15:55:15 -0800
Subject: [PATCH 1545/4076] Staging: rtl8192e: Rename array variable RxTsRecord

Rename array variable RxTsRecord to rx_ts_records to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231217235520.30377-2-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 4 ++--
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 58a950ef77ce3..401b9efb25aab 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -535,7 +535,7 @@ void rtllib_rx_ba_inact_timeout(struct timer_list *t)
 	struct rx_ts_record *ts = from_timer(ts, t,
 					      rx_admitted_ba_record.timer);
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
-				     RxTsRecord[ts->num]);
+				     rx_ts_records[ts->num]);
 
 	rx_ts_delete_ba(ieee, ts);
 	rtllib_send_DELBA(ieee, ts->ts_common_info.addr,
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 86db56f3900d3..8c7fe327ae1ef 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -12,7 +12,7 @@ static void RxPktPendingTimeout(struct timer_list *t)
 {
 	struct rx_ts_record *ts = from_timer(ts, t, rx_pkt_pending_timer);
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
-						  RxTsRecord[ts->num]);
+						  rx_ts_records[ts->num]);
 
 	struct rx_reorder_entry *pReorderEntry = NULL;
 
@@ -120,7 +120,7 @@ static void ResetRxTsEntry(struct rx_ts_record *ts)
 void rtllib_ts_init(struct rtllib_device *ieee)
 {
 	struct tx_ts_record *pTxTS  = ieee->TxTsRecord;
-	struct rx_ts_record *rxts  = ieee->RxTsRecord;
+	struct rx_ts_record *rxts  = ieee->rx_ts_records;
 	struct rx_reorder_entry *pRxReorderEntry = ieee->RxReorderEntry;
 	u8				count = 0;
 
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 09360129d5788..343ea20c1aa45 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1229,7 +1229,7 @@ struct rtllib_device {
 	struct list_head		Rx_TS_Admit_List;
 	struct list_head		Rx_TS_Pending_List;
 	struct list_head		Rx_TS_Unused_List;
-	struct rx_ts_record RxTsRecord[TOTAL_TS_NUM];
+	struct rx_ts_record rx_ts_records[TOTAL_TS_NUM];
 	struct rx_reorder_entry RxReorderEntry[128];
 	struct list_head		RxReorder_Unused_List;
 
-- 
GitLab


From 1cf5e0a3668eaf6770e2013eebb3dcfebb08771d Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 17 Dec 2023 15:55:16 -0800
Subject: [PATCH 1546/4076] Staging: rtl8192e: Rename array variable TxTsRecord

Rename array variable TxTsRecord to tx_ts_records to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231217235520.30377-3-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 4 ++--
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 401b9efb25aab..cdbda65b4d502 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -523,7 +523,7 @@ void rtllib_tx_ba_inact_timeout(struct timer_list *t)
 	struct tx_ts_record *ts = from_timer(ts, t,
 					      tx_admitted_ba_record.timer);
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
-				     TxTsRecord[ts->num]);
+				     tx_ts_records[ts->num]);
 	tx_ts_delete_ba(ieee, ts);
 	rtllib_send_DELBA(ieee, ts->ts_common_info.addr,
 			  &ts->tx_admitted_ba_record, TX_DIR,
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 8c7fe327ae1ef..2d2deeabc48d9 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -85,7 +85,7 @@ static void TsAddBaProcess(struct timer_list *t)
 	struct tx_ts_record *ts = from_timer(ts, t, ts_add_ba_timer);
 	u8 num = ts->num;
 	struct rtllib_device *ieee = container_of(ts, struct rtllib_device,
-				     TxTsRecord[num]);
+				     tx_ts_records[num]);
 
 	rtllib_ts_init_add_ba(ieee, ts, BA_POLICY_IMMEDIATE, false);
 	netdev_dbg(ieee->dev, "%s(): ADDBA Req is started\n", __func__);
@@ -119,7 +119,7 @@ static void ResetRxTsEntry(struct rx_ts_record *ts)
 
 void rtllib_ts_init(struct rtllib_device *ieee)
 {
-	struct tx_ts_record *pTxTS  = ieee->TxTsRecord;
+	struct tx_ts_record *pTxTS  = ieee->tx_ts_records;
 	struct rx_ts_record *rxts  = ieee->rx_ts_records;
 	struct rx_reorder_entry *pRxReorderEntry = ieee->RxReorderEntry;
 	u8				count = 0;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 343ea20c1aa45..4df46eae6aa89 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1225,7 +1225,7 @@ struct rtllib_device {
 	struct list_head		Tx_TS_Admit_List;
 	struct list_head		Tx_TS_Pending_List;
 	struct list_head		Tx_TS_Unused_List;
-	struct tx_ts_record TxTsRecord[TOTAL_TS_NUM];
+	struct tx_ts_record tx_ts_records[TOTAL_TS_NUM];
 	struct list_head		Rx_TS_Admit_List;
 	struct list_head		Rx_TS_Pending_List;
 	struct list_head		Rx_TS_Unused_List;
-- 
GitLab


From 66547657a8c46fda873b85b283445a400e308a5c Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 17 Dec 2023 15:55:17 -0800
Subject: [PATCH 1547/4076] Staging: rtl8192e: Rename variable ucTSID

Rename variable ucTSID to ts_id to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231217235520.30377-4-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 2 +-
 drivers/staging/rtl8192e/rtl819x_Qos.h    | 2 +-
 drivers/staging/rtl8192e/rtl819x_TSProc.c | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index cdbda65b4d502..fd0149d3f7175 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -474,7 +474,7 @@ void rtllib_ts_init_add_ba(struct rtllib_device *ieee, struct tx_ts_record *ts,
 	ba->dialog_token++;
 	ba->ba_param_set.field.amsdu_support = 0;
 	ba->ba_param_set.field.ba_policy = policy;
-	ba->ba_param_set.field.tid = ts->ts_common_info.tspec.ucTSID;
+	ba->ba_param_set.field.tid = ts->ts_common_info.tspec.ts_id;
 	ba->ba_param_set.field.buffer_size = 32;
 	ba->ba_timeout_value = 0;
 	ba->ba_start_seq_ctrl.field.seq_num = (ts->tx_cur_seq + 3) % 4096;
diff --git a/drivers/staging/rtl8192e/rtl819x_Qos.h b/drivers/staging/rtl8192e/rtl819x_Qos.h
index 1c00092ea3a59..50e01ca49a4ce 100644
--- a/drivers/staging/rtl8192e/rtl819x_Qos.h
+++ b/drivers/staging/rtl8192e/rtl819x_Qos.h
@@ -8,7 +8,7 @@
 #define __INC_QOS_TYPE_H
 
 struct qos_tsinfo {
-	u8		ucTSID:4;
+	u8		ts_id:4;
 	u8		ucDirection:2;
 };
 
diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c
index 2d2deeabc48d9..7e73d31dcccfc 100644
--- a/drivers/staging/rtl8192e/rtl819x_TSProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c
@@ -198,7 +198,7 @@ static struct ts_common_info *SearchAdmitTRStream(struct rtllib_device *ieee,
 			continue;
 		list_for_each_entry(pRet, psearch_list, list) {
 			if (memcmp(pRet->addr, addr, 6) == 0 &&
-			    pRet->tspec.ucTSID == TID &&
+			    pRet->tspec.ts_id == TID &&
 			    pRet->tspec.ucDirection == dir)
 				break;
 		}
@@ -305,7 +305,7 @@ bool rtllib_get_ts(struct rtllib_device *ieee, struct ts_common_info **ppTS,
 		netdev_dbg(ieee->dev,
 			   "to init current TS, UP:%d, Dir:%d, addr: %pM ppTs=%p\n",
 			   UP, Dir, addr, *ppTS);
-		ts_info->ucTSID = UP;
+		ts_info->ts_id = UP;
 		ts_info->ucDirection = Dir;
 
 		MakeTSEntry(*ppTS, addr, &tspec);
-- 
GitLab


From 4497af9ea95f38651451cbf08d3485cf830ffc8d Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 17 Dec 2023 15:55:18 -0800
Subject: [PATCH 1548/4076] Staging: rtl8192e: Rename variable pDelBaParamSet

Rename variable pDelBaParamSet to del_ba_param_set to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231217235520.30377-5-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index fd0149d3f7175..2fd54312c04fe 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -402,7 +402,7 @@ OnADDBARsp_Reject:
 int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 {
 	struct ieee80211_hdr_3addr *delba = NULL;
-	union delba_param_set *pDelBaParamSet = NULL;
+	union delba_param_set *del_ba_param_set = NULL;
 	u8 *dst = NULL;
 
 	if (skb->len < sizeof(struct ieee80211_hdr_3addr) + 6) {
@@ -427,17 +427,17 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 #endif
 	delba = (struct ieee80211_hdr_3addr *)skb->data;
 	dst = (u8 *)(&delba->addr2[0]);
-	pDelBaParamSet = (union delba_param_set *)&delba->seq_ctrl + 2;
+	del_ba_param_set = (union delba_param_set *)&delba->seq_ctrl + 2;
 
-	if (pDelBaParamSet->field.initiator == 1) {
+	if (del_ba_param_set->field.initiator == 1) {
 		struct rx_ts_record *ts;
 
 		if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
-			   (u8)pDelBaParamSet->field.tid, RX_DIR, false)) {
+			   (u8)del_ba_param_set->field.tid, RX_DIR, false)) {
 			netdev_warn(ieee->dev,
 				    "%s(): can't get TS for RXTS. dst:%pM TID:%d\n",
 				    __func__, dst,
-				    (u8)pDelBaParamSet->field.tid);
+				    (u8)del_ba_param_set->field.tid);
 			return -1;
 		}
 
@@ -446,7 +446,7 @@ int rtllib_rx_DELBA(struct rtllib_device *ieee, struct sk_buff *skb)
 		struct tx_ts_record *ts;
 
 		if (!rtllib_get_ts(ieee, (struct ts_common_info **)&ts, dst,
-			   (u8)pDelBaParamSet->field.tid, TX_DIR, false)) {
+			   (u8)del_ba_param_set->field.tid, TX_DIR, false)) {
 			netdev_warn(ieee->dev, "%s(): can't get TS for TXTS\n",
 				    __func__);
 			return -1;
-- 
GitLab


From 7f2c9c0bb8d575ed289943ad782776649343ee7e Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Sun, 17 Dec 2023 15:55:20 -0800
Subject: [PATCH 1549/4076] Staging: rtl8192e: Rename variable pBaStartSeqCtrl

Rename variable pBaStartSeqCtrl to ba_start_seq_ctrl to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231217235520.30377-7-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_BAProc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_BAProc.c b/drivers/staging/rtl8192e/rtl819x_BAProc.c
index 2fd54312c04fe..ee9ce392155c3 100644
--- a/drivers/staging/rtl8192e/rtl819x_BAProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_BAProc.c
@@ -219,7 +219,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	struct ba_record *ba = NULL;
 	union ba_param_set *ba_param_set = NULL;
 	u16 *ba_timeout_value = NULL;
-	union sequence_control *pBaStartSeqCtrl = NULL;
+	union sequence_control *ba_start_seq_ctrl = NULL;
 	struct rx_ts_record *ts = NULL;
 
 	if (skb->len < sizeof(struct ieee80211_hdr_3addr) + 9) {
@@ -241,7 +241,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	dialog_token = tag + 2;
 	ba_param_set = (union ba_param_set *)(tag + 3);
 	ba_timeout_value = (u16 *)(tag + 5);
-	pBaStartSeqCtrl = (union sequence_control *)(req + 7);
+	ba_start_seq_ctrl = (union sequence_control *)(req + 7);
 
 	if (!ieee->current_network.qos_data.active ||
 	    !ieee->ht_info->current_ht_support ||
@@ -274,7 +274,7 @@ int rtllib_rx_ADDBAReq(struct rtllib_device *ieee, struct sk_buff *skb)
 	ba->dialog_token = *dialog_token;
 	ba->ba_param_set = *ba_param_set;
 	ba->ba_timeout_value = *ba_timeout_value;
-	ba->ba_start_seq_ctrl = *pBaStartSeqCtrl;
+	ba->ba_start_seq_ctrl = *ba_start_seq_ctrl;
 
 	if (ieee->GetHalfNmodeSupportByAPsHandler(ieee->dev) ||
 	   (ieee->ht_info->iot_action & HT_IOT_ACT_ALLOW_PEER_AGG_ONE_PKT))
-- 
GitLab


From d5362c37e1f8a40096452fc201c30e705750e687 Mon Sep 17 00:00:00 2001
From: Xiaolei Wang <xiaolei.wang@windriver.com>
Date: Fri, 15 Dec 2023 10:00:49 +0800
Subject: [PATCH 1550/4076] rpmsg: virtio: Free driver_override when
 rpmsg_remove()

Free driver_override when rpmsg_remove(), otherwise
the following memory leak will occur:

unreferenced object 0xffff0000d55d7080 (size 128):
  comm "kworker/u8:2", pid 56, jiffies 4294893188 (age 214.272s)
  hex dump (first 32 bytes):
    72 70 6d 73 67 5f 6e 73 00 00 00 00 00 00 00 00  rpmsg_ns........
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000009c94c9c1>] __kmem_cache_alloc_node+0x1f8/0x320
    [<000000002300d89b>] __kmalloc_node_track_caller+0x44/0x70
    [<00000000228a60c3>] kstrndup+0x4c/0x90
    [<0000000077158695>] driver_set_override+0xd0/0x164
    [<000000003e9c4ea5>] rpmsg_register_device_override+0x98/0x170
    [<000000001c0c89a8>] rpmsg_ns_register_device+0x24/0x30
    [<000000008bbf8fa2>] rpmsg_probe+0x2e0/0x3ec
    [<00000000e65a68df>] virtio_dev_probe+0x1c0/0x280
    [<00000000443331cc>] really_probe+0xbc/0x2dc
    [<00000000391064b1>] __driver_probe_device+0x78/0xe0
    [<00000000a41c9a5b>] driver_probe_device+0xd8/0x160
    [<000000009c3bd5df>] __device_attach_driver+0xb8/0x140
    [<0000000043cd7614>] bus_for_each_drv+0x7c/0xd4
    [<000000003b929a36>] __device_attach+0x9c/0x19c
    [<00000000a94e0ba8>] device_initial_probe+0x14/0x20
    [<000000003c999637>] bus_probe_device+0xa0/0xac

Signed-off-by: Xiaolei Wang <xiaolei.wang@windriver.com>
Fixes: b0b03b811963 ("rpmsg: Release rpmsg devices in backends")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20231215020049.78750-1-xiaolei.wang@windriver.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/rpmsg/virtio_rpmsg_bus.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index dc87965f81641..1062939c32645 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -378,6 +378,7 @@ static void virtio_rpmsg_release_device(struct device *dev)
 	struct rpmsg_device *rpdev = to_rpmsg_device(dev);
 	struct virtio_rpmsg_channel *vch = to_virtio_rpmsg_channel(rpdev);
 
+	kfree(rpdev->driver_override);
 	kfree(vch);
 }
 
-- 
GitLab


From 86362293044b382aece355f9e4e3f7116dcd1eae Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 22 Jul 2023 16:08:44 -0700
Subject: [PATCH 1551/4076] PCI: endpoint: Make struct pci_epf_ops in
 pci_epf_driver const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pci_epf_ops struct contains a set of callbacks that are used by the
pci_epf_driver, and is never modified by the EPF core itself.

Marking the struct pointer const allows EPF drivers to declare their
pci_epf_ops struct to be const.

This allows the struct to be placed in the read-only section. Which
for example brings some security benefits as the callbacks can not be
overwritten.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20230722230848.589428-1-lars@metafoo.de
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
---
 include/linux/pci-epf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 3f44b6aec4770..764dc62b3acc9 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -98,7 +98,7 @@ struct pci_epf_driver {
 	void	(*remove)(struct pci_epf *epf);
 
 	struct device_driver	driver;
-	struct pci_epf_ops	*ops;
+	const struct pci_epf_ops *ops;
 	struct module		*owner;
 	struct list_head	epf_group;
 	const struct pci_epf_device_id	*id_table;
-- 
GitLab


From 150d04ddf3861c079fa1e9d96d3b52c399944f85 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 22 Jul 2023 16:08:45 -0700
Subject: [PATCH 1552/4076] PCI: endpoint: pci-epf-mhi: Make structs
 pci_epf_ops and pci_epf_event_ops const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Both the pci_epf_ops and pci_epf_evnt_ops structs for the PCI endpoint
MHI driver are never modified.

Mark them as const so they can be placed in the read-only section.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20230722230848.589428-2-lars@metafoo.de
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
---
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index b7b9d3e21f97d..c643222bb4aa7 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -644,7 +644,7 @@ static void pci_epf_mhi_unbind(struct pci_epf *epf)
 	pci_epc_clear_bar(epc, epf->func_no, epf->vfunc_no, epf_bar);
 }
 
-static struct pci_epc_event_ops pci_epf_mhi_event_ops = {
+static const struct pci_epc_event_ops pci_epf_mhi_event_ops = {
 	.core_init = pci_epf_mhi_core_init,
 	.link_up = pci_epf_mhi_link_up,
 	.link_down = pci_epf_mhi_link_down,
@@ -682,7 +682,7 @@ static const struct pci_epf_device_id pci_epf_mhi_ids[] = {
 	{},
 };
 
-static struct pci_epf_ops pci_epf_mhi_ops = {
+static const struct pci_epf_ops pci_epf_mhi_ops = {
 	.unbind	= pci_epf_mhi_unbind,
 	.bind	= pci_epf_mhi_bind,
 };
-- 
GitLab


From 54f22c9758dcde2dfde4bf91c8fd0bdc952f1e14 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 22 Jul 2023 16:08:46 -0700
Subject: [PATCH 1553/4076] PCI: endpoint: pci-epf-ntb: Make struct pci_epf_ops
 const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pci_epf_ops struct for the PCI endpoint NTB driver is never modified.

Mark it as const so it can be placed in the read-only section.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20230722230848.589428-3-lars@metafoo.de
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
---
 drivers/pci/endpoint/functions/pci-epf-ntb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-ntb.c b/drivers/pci/endpoint/functions/pci-epf-ntb.c
index 9aac2c6f3bb99..6301814697205 100644
--- a/drivers/pci/endpoint/functions/pci-epf-ntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-ntb.c
@@ -2099,7 +2099,7 @@ static int epf_ntb_probe(struct pci_epf *epf,
 	return 0;
 }
 
-static struct pci_epf_ops epf_ntb_ops = {
+static const struct pci_epf_ops epf_ntb_ops = {
 	.bind	= epf_ntb_bind,
 	.unbind	= epf_ntb_unbind,
 	.add_cfs = epf_ntb_add_cfs,
-- 
GitLab


From c21b53deda09a5502f0201750fe61512345468e2 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 22 Jul 2023 16:08:47 -0700
Subject: [PATCH 1554/4076] PCI: endpoint: pci-epf-vntb: Make struct
 pci_epf_ops const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pci_epf_ops struct for the PCI endpoint vNTB driver is never modified.

Mark it as const so it can be placed in the read-only section.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20230722230848.589428-4-lars@metafoo.de
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
---
 drivers/pci/endpoint/functions/pci-epf-vntb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index 3f60128560ed0..1a1f62d142e9c 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -1387,7 +1387,7 @@ static void epf_ntb_unbind(struct pci_epf *epf)
 }
 
 // EPF driver probe
-static struct pci_epf_ops epf_ntb_ops = {
+static const struct pci_epf_ops epf_ntb_ops = {
 	.bind   = epf_ntb_bind,
 	.unbind = epf_ntb_unbind,
 	.add_cfs = epf_ntb_add_cfs,
-- 
GitLab


From 6f517e044096fd78fa6f19b3da20579426980af7 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 22 Jul 2023 16:08:48 -0700
Subject: [PATCH 1555/4076] PCI: endpoint: pci-epf-test: Make struct
 pci_epf_ops const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pci_epf_ops struct for the PCI endpoint test driver is never modified.

Mark it as const so it can be placed in the read-only section.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20230722230848.589428-5-lars@metafoo.de
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
---
 drivers/pci/endpoint/functions/pci-epf-test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 1f0d2b84296a3..7cc1c5c70afc0 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -973,7 +973,7 @@ static int pci_epf_test_probe(struct pci_epf *epf,
 	return 0;
 }
 
-static struct pci_epf_ops ops = {
+static const struct pci_epf_ops ops = {
 	.unbind	= pci_epf_test_unbind,
 	.bind	= pci_epf_test_bind,
 };
-- 
GitLab


From ace196de694ebea5e2b3161e21ad169eb45accc6 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 14 Dec 2023 12:13:58 -0700
Subject: [PATCH 1556/4076] cxl: Fix unregister_region() callback parameter
 assignment

In devm_cxl_add_region(), devm_add_action_or_reset() is called by
passing in unregister_region() with data ptr of 'cxlr'. However, in
unregister_region(), the passed in parameter is incorrectly assumed to
be a 'struct device' rather than the 'cxlr' pointer. The code has been
working because 'struct device' is the first member of 'struct
cxl_region'. Issue found by inspection. Fix the assignment so that cxlr
is pointing directly to the passed in parameter.

Not flagged for -stable since there is no functional impact of this fix.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/170258123810.952211.3907381447996426480.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/region.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 56e575c79bb49..a61703c9d72ab 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2083,13 +2083,13 @@ static struct cxl_region *to_cxl_region(struct device *dev)
 	return container_of(dev, struct cxl_region, dev);
 }
 
-static void unregister_region(void *dev)
+static void unregister_region(void *_cxlr)
 {
-	struct cxl_region *cxlr = to_cxl_region(dev);
+	struct cxl_region *cxlr = _cxlr;
 	struct cxl_region_params *p = &cxlr->params;
 	int i;
 
-	device_del(dev);
+	device_del(&cxlr->dev);
 
 	/*
 	 * Now that region sysfs is shutdown, the parameter block is now
@@ -2100,7 +2100,7 @@ static void unregister_region(void *dev)
 		detach_target(cxlr, i);
 
 	cxl_region_iomem_release(cxlr);
-	put_device(dev);
+	put_device(&cxlr->dev);
 }
 
 static struct lock_class_key cxl_region_key;
-- 
GitLab


From 0b4b785d1f2557678c493dc1b431ca4ad16fde9b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Dec 2023 15:23:30 -0300
Subject: [PATCH 1557/4076] perf evlist: Move event attributes to after the /
 when uniquefying using the PMU name

When turning an event with attributes to the format including the PMU we
need to move the "event:attributes" format to "event/attributes/" so
that we can copy the event displayed and use it in the command line,
i.e. in 'perf top' we had:

 1K cpu_atom/cycles:P/
 11K cpu_core/cycles:P/

If I try to use that on the command line:

  # perf top -e cpu_atom/cycles:P/
  event syntax error: 'cpu_atom/cycles:P/'
                                \___ Bad event or PMU

  Unable to find PMU or event on a PMU of 'cpu_atom'

  Initial error:
  event syntax error: 'cpu_atom/cycles:P/'
                                \___ unknown term 'cycles:P' for pmu
  'cpu_atom'

  valid terms:

    event,pc,edge,offcore_rsp,ldlat,inv,umask,cmask,config,config1,config2,config3,name,period,freq,branch_type,time,call-graph,stack-size,no-inherit,inherit,max-stack,nr,no-overwrite,overwrite ,driver-config,percore,aux-output,aux-sample-size,metric-id,raw,legacy-cache,hardware
  Run
    'perf list' for a list of valid events

  Usage: perf top [<options>]

     -e, --event <event>   event selector. use 'perf list' to list available events
  #

Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Hector Martin <marcan@marcan.st>
Cc: Ian Rogers <irogers@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZXxyanyZgWBTOnoK@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 6f0892803c224..95f25e9fb994a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -2521,9 +2521,8 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis
 
 void evlist__uniquify_name(struct evlist *evlist)
 {
+	char *new_name, empty_attributes[2] = ":", *attributes;
 	struct evsel *pos;
-	char *new_name;
-	int ret;
 
 	if (perf_pmus__num_core_pmus() == 1)
 		return;
@@ -2535,11 +2534,17 @@ void evlist__uniquify_name(struct evlist *evlist)
 		if (strchr(pos->name, '/'))
 			continue;
 
-		ret = asprintf(&new_name, "%s/%s/",
-			       pos->pmu_name, pos->name);
-		if (ret) {
+		attributes = strchr(pos->name, ':');
+		if (attributes)
+			*attributes = '\0';
+		else
+			attributes = empty_attributes;
+
+		if (asprintf(&new_name, "%s/%s/%s", pos->pmu_name, pos->name, attributes + 1)) {
 			free(pos->name);
 			pos->name = new_name;
+		} else {
+			*attributes = ':';
 		}
 	}
 }
-- 
GitLab


From 9a07a71ed3d23b56e1f05ea808ec5f59448fcc16 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 28 Nov 2023 11:46:24 -0800
Subject: [PATCH 1558/4076] perf tests: Make DSO tests a suite rather than
 individual

Make the DSO data tests a suite rather than individual so their output
is grouped.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231128194624.1419260-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/builtin-test.c |  2 --
 tools/perf/tests/dso-data.c     | 15 ++++++++++++---
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index b8c21e81a021b..4a5973f9bb9b3 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -62,8 +62,6 @@ static struct test_suite *generic_tests[] = {
 	&suite__pmu,
 	&suite__pmu_events,
 	&suite__dso_data,
-	&suite__dso_data_cache,
-	&suite__dso_data_reopen,
 	&suite__perf_evsel__roundtrip_name_test,
 #ifdef HAVE_LIBTRACEEVENT
 	&suite__perf_evsel__tp_sched_test,
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 3419a4ab5590f..2d67422c12229 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -394,6 +394,15 @@ static int test__dso_data_reopen(struct test_suite *test __maybe_unused, int sub
 	return 0;
 }
 
-DEFINE_SUITE("DSO data read", dso_data);
-DEFINE_SUITE("DSO data cache", dso_data_cache);
-DEFINE_SUITE("DSO data reopen", dso_data_reopen);
+
+static struct test_case tests__dso_data[] = {
+	TEST_CASE("read", dso_data),
+	TEST_CASE("cache", dso_data_cache),
+	TEST_CASE("reopen", dso_data_reopen),
+	{	.name = NULL, }
+};
+
+struct test_suite suite__dso_data = {
+	.desc = "DSO data tests",
+	.test_cases = tests__dso_data,
+};
-- 
GitLab


From 3e0594f9f0f774918d63701dc7de634bb1bc7b1e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 28 Nov 2023 22:02:07 -0800
Subject: [PATCH 1559/4076] perf top: Avoid repeated function calls to
 perf_cpu_map__nr().
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a local variable to avoid repeated calls to perf_cpu_map__nr().

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Link: https://lore.kernel.org/r/20231129060211.1890454-11-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/top.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index be7157de04518..4db3d1bd686cf 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -28,6 +28,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	struct record_opts *opts = &top->record_opts;
 	struct target *target = &opts->target;
 	size_t ret = 0;
+	int nr_cpus;
 
 	if (top->samples) {
 		samples_per_sec = top->samples / top->delay_secs;
@@ -93,19 +94,17 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	else
 		ret += SNPRINTF(bf + ret, size - ret, " (all");
 
+	nr_cpus = perf_cpu_map__nr(top->evlist->core.user_requested_cpus);
 	if (target->cpu_list)
 		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
-				perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
-				? "s" : "",
+				nr_cpus > 1 ? "s" : "",
 				target->cpu_list);
 	else {
 		if (target->tid)
 			ret += SNPRINTF(bf + ret, size - ret, ")");
 		else
 			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
-					perf_cpu_map__nr(top->evlist->core.user_requested_cpus),
-					perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
-					? "s" : "");
+					nr_cpus, nr_cpus > 1 ? "s" : "");
 	}
 
 	perf_top__reset_sample_counters(top);
-- 
GitLab


From 67bc993446d340d4f059014f6be6ead35ec5f88b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 28 Nov 2023 22:02:11 -0800
Subject: [PATCH 1560/4076] libperf cpumap: Document perf_cpu_map__nr()'s
 behavior
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

perf_cpu_map__nr()'s behavior around an empty CPU map is strange as it
returns that there is 1 CPU. Changing code that may rely on this
behavior is hard, we can at least document the behavior.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Link: https://lore.kernel.org/r/20231129060211.1890454-15-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/include/perf/cpumap.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index dbe0a7352b648..228c6c629b0ce 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -44,7 +44,18 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
 							 struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__cpu - get the CPU value at the given index. Returns -1 if index
+ *                     is invalid.
+ */
 LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
+/**
+ * perf_cpu_map__nr - for an empty map returns 1, as perf_cpu_map__cpu returns a
+ *                    cpu of -1 for an invalid index, this makes an empty map
+ *                    look like it contains the "any CPU"/dummy value. Otherwise
+ *                    the result is the number CPUs in the map plus one if the
+ *                    "any CPU"/dummy value is present.
+ */
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 /**
  * perf_cpu_map__has_any_cpu_or_is_empty - is map either empty or has the "any CPU"/dummy value.
-- 
GitLab


From 5cc47ffba7b71e37d65c259f7f5778b3622f1e8f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:35 -0800
Subject: [PATCH 1561/4076] perf map: Improve map/unmap parameter names

The u64 values are either absolute or relative, try to hint better in
the parameter names.

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/map.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 3a3b7757da5fd..49756716cb132 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -105,25 +105,25 @@ static inline u64 map__dso_map_ip(const struct map *map, u64 ip)
 }
 
 /* dso rip -> ip */
-static inline u64 map__dso_unmap_ip(const struct map *map, u64 ip)
+static inline u64 map__dso_unmap_ip(const struct map *map, u64 rip)
 {
-	return ip + map__start(map) - map__pgoff(map);
+	return rip + map__start(map) - map__pgoff(map);
 }
 
-static inline u64 map__map_ip(const struct map *map, u64 ip)
+static inline u64 map__map_ip(const struct map *map, u64 ip_or_rip)
 {
 	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
-		return map__dso_map_ip(map, ip);
+		return map__dso_map_ip(map, ip_or_rip);
 	else
-		return ip;
+		return ip_or_rip;
 }
 
-static inline u64 map__unmap_ip(const struct map *map, u64 ip)
+static inline u64 map__unmap_ip(const struct map *map, u64 ip_or_rip)
 {
 	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
-		return map__dso_unmap_ip(map, ip);
+		return map__dso_unmap_ip(map, ip_or_rip);
 	else
-		return ip;
+		return ip_or_rip;
 }
 
 /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
-- 
GitLab


From 19b5bd9a59bed4e9937092e2b685d69656bfc606 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:36 -0800
Subject: [PATCH 1562/4076] perf maps: Add maps__for_each_map to iterate maps
 holding the lock

The macro maps__for_each_entry is error prone as it doesn't require
holding the maps lock.

Add a new function that iterates the maps holding the read lock.

Convert maps__find_symbol_by_name() and maps__fprintf() to use callbacks,
the latter being an example of where the read lock wasn't being held.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/maps.c | 99 ++++++++++++++++++++++++++++--------------
 tools/perf/util/maps.h |  3 ++
 2 files changed, 69 insertions(+), 33 deletions(-)

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 9a011aed4b754..160a6dce54bb6 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -196,6 +196,21 @@ void maps__put(struct maps *maps)
 		RC_CHK_PUT(maps);
 }
 
+int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data)
+{
+	struct map_rb_node *pos;
+	int ret = 0;
+
+	down_read(maps__lock(maps));
+	maps__for_each_entry(maps, pos)	{
+		ret = cb(pos->map, data);
+		if (ret)
+			break;
+	}
+	up_read(maps__lock(maps));
+	return ret;
+}
+
 struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
 {
 	struct map *map = maps__find(maps, addr);
@@ -210,31 +225,40 @@ struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
 	return NULL;
 }
 
-struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
-{
+struct maps__find_symbol_by_name_args {
+	struct map **mapp;
+	const char *name;
 	struct symbol *sym;
-	struct map_rb_node *pos;
+};
 
-	down_read(maps__lock(maps));
+static int maps__find_symbol_by_name_cb(struct map *map, void *data)
+{
+	struct maps__find_symbol_by_name_args *args = data;
 
-	maps__for_each_entry(maps, pos) {
-		sym = map__find_symbol_by_name(pos->map, name);
+	args->sym = map__find_symbol_by_name(map, args->name);
+	if (!args->sym)
+		return 0;
 
-		if (sym == NULL)
-			continue;
-		if (!map__contains_symbol(pos->map, sym)) {
-			sym = NULL;
-			continue;
-		}
-		if (mapp != NULL)
-			*mapp = pos->map;
-		goto out;
+	if (!map__contains_symbol(map, args->sym)) {
+		args->sym = NULL;
+		return 0;
 	}
 
-	sym = NULL;
-out:
-	up_read(maps__lock(maps));
-	return sym;
+	if (args->mapp != NULL)
+		*args->mapp = map__get(map);
+	return 1;
+}
+
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
+{
+	struct maps__find_symbol_by_name_args args = {
+		.mapp = mapp,
+		.name = name,
+		.sym = NULL,
+	};
+
+	maps__for_each_map(maps, maps__find_symbol_by_name_cb, &args);
+	return args.sym;
 }
 
 int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
@@ -253,25 +277,34 @@ int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
 	return ams->ms.sym ? 0 : -1;
 }
 
-size_t maps__fprintf(struct maps *maps, FILE *fp)
-{
-	size_t printed = 0;
-	struct map_rb_node *pos;
+struct maps__fprintf_args {
+	FILE *fp;
+	size_t printed;
+};
 
-	down_read(maps__lock(maps));
+static int maps__fprintf_cb(struct map *map, void *data)
+{
+	struct maps__fprintf_args *args = data;
 
-	maps__for_each_entry(maps, pos) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos->map, fp);
-		if (verbose > 2) {
-			printed += dso__fprintf(map__dso(pos->map), fp);
-			printed += fprintf(fp, "--\n");
-		}
+	args->printed += fprintf(args->fp, "Map:");
+	args->printed += map__fprintf(map, args->fp);
+	if (verbose > 2) {
+		args->printed += dso__fprintf(map__dso(map), args->fp);
+		args->printed += fprintf(args->fp, "--\n");
 	}
+	return 0;
+}
 
-	up_read(maps__lock(maps));
+size_t maps__fprintf(struct maps *maps, FILE *fp)
+{
+	struct maps__fprintf_args args = {
+		.fp = fp,
+		.printed = 0,
+	};
+
+	maps__for_each_map(maps, maps__fprintf_cb, &args);
 
-	return printed;
+	return args.printed;
 }
 
 int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index a689149be8c43..14ad959792577 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -81,6 +81,9 @@ static inline void __maps__zput(struct maps **map)
 
 #define maps__zput(map) __maps__zput(&map)
 
+/* Iterate over map calling cb for each entry. */
+int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data);
+
 static inline struct rb_root *maps__entries(struct maps *maps)
 {
 	return &RC_CHK_ACCESS(maps)->entries;
-- 
GitLab


From bc4bc56d9d74f4593f253531edcea9ea8e30e7f1 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:37 -0800
Subject: [PATCH 1563/4076] perf events x86: Use function to add missing lock

Switch from loop macro maps__for_each_entry to maps__for_each_map
function that takes a callback. The function holds the maps lock,
which should be held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/util/event.c | 103 +++++++++++++++++--------------
 1 file changed, 58 insertions(+), 45 deletions(-)

diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index 5741ffe473120..e65b7dbe27fbc 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -14,66 +14,79 @@
 
 #if defined(__x86_64__)
 
-int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine)
+struct perf_event__synthesize_extra_kmaps_cb_args {
+	struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	union perf_event *event;
+};
+
+static int perf_event__synthesize_extra_kmaps_cb(struct map *map, void *data)
 {
-	int rc = 0;
-	struct map_rb_node *pos;
-	struct maps *kmaps = machine__kernel_maps(machine);
-	union perf_event *event = zalloc(sizeof(event->mmap) +
-					 machine->id_hdr_size);
+	struct perf_event__synthesize_extra_kmaps_cb_args *args = data;
+	union perf_event *event = args->event;
+	struct kmap *kmap;
+	size_t size;
 
-	if (!event) {
-		pr_debug("Not enough memory synthesizing mmap event "
-			 "for extra kernel maps\n");
-		return -1;
-	}
+	if (!__map__is_extra_kernel_map(map))
+		return 0;
 
-	maps__for_each_entry(kmaps, pos) {
-		struct kmap *kmap;
-		size_t size;
-		struct map *map = pos->map;
+	kmap = map__kmap(map);
 
-		if (!__map__is_extra_kernel_map(map))
-			continue;
+	size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
+		      PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
+		      args->machine->id_hdr_size;
 
-		kmap = map__kmap(map);
+	memset(event, 0, size);
 
-		size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
-		       PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
-		       machine->id_hdr_size;
+	event->mmap.header.type = PERF_RECORD_MMAP;
 
-		memset(event, 0, size);
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (machine__is_host(args->machine))
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
+	else
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-		event->mmap.header.type = PERF_RECORD_MMAP;
+	event->mmap.header.size = size;
 
-		/*
-		 * kernel uses 0 for user space maps, see kernel/perf_event.c
-		 * __perf_event_mmap
-		 */
-		if (machine__is_host(machine))
-			event->header.misc = PERF_RECORD_MISC_KERNEL;
-		else
-			event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+	event->mmap.start = map__start(map);
+	event->mmap.len   = map__size(map);
+	event->mmap.pgoff = map__pgoff(map);
+	event->mmap.pid   = args->machine->pid;
 
-		event->mmap.header.size = size;
+	strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
 
-		event->mmap.start = map__start(map);
-		event->mmap.len   = map__size(map);
-		event->mmap.pgoff = map__pgoff(map);
-		event->mmap.pid   = machine->pid;
+	if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0)
+		return -1;
 
-		strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
+	return 0;
+}
 
-		if (perf_tool__process_synth_event(tool, event, machine,
-						   process) != 0) {
-			rc = -1;
-			break;
-		}
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int rc;
+	struct maps *kmaps = machine__kernel_maps(machine);
+	struct perf_event__synthesize_extra_kmaps_cb_args args = {
+		.tool = tool,
+		.process = process,
+		.machine = machine,
+		.event = zalloc(sizeof(args.event->mmap) + machine->id_hdr_size),
+	};
+
+	if (!args.event) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for extra kernel maps\n");
+		return -1;
 	}
 
-	free(event);
+	rc = maps__for_each_map(kmaps, perf_event__synthesize_extra_kmaps_cb, &args);
+
+	free(args.event);
 	return rc;
 }
 
-- 
GitLab


From 431be14b193ad19946aeb26a6016dc5b8eb6a248 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:38 -0800
Subject: [PATCH 1564/4076] perf report: Use function to add missing maps lock

Switch maps__fprintf_task from loop macro maps__for_each_entry to
maps__for_each_map function that takes a callback. The function holds
the maps lock, which should be held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c | 54 +++++++++++++++++++++++++------------
 1 file changed, 37 insertions(+), 17 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 17fb171e898b9..178fb602bc982 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -856,27 +856,47 @@ static struct task *tasks_list(struct task *task, struct machine *machine)
 	return tasks_list(parent_task, machine);
 }
 
-static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
+struct maps__fprintf_task_args {
+	int indent;
+	FILE *fp;
+	size_t printed;
+};
+
+static int maps__fprintf_task_cb(struct map *map, void *data)
 {
-	size_t printed = 0;
-	struct map_rb_node *rb_node;
+	struct maps__fprintf_task_args *args = data;
+	const struct dso *dso = map__dso(map);
+	u32 prot = map__prot(map);
+	int ret;
 
-	maps__for_each_entry(maps, rb_node) {
-		struct map *map = rb_node->map;
-		const struct dso *dso = map__dso(map);
-		u32 prot = map__prot(map);
+	ret = fprintf(args->fp,
+		"%*s  %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n",
+		args->indent, "", map__start(map), map__end(map),
+		prot & PROT_READ ? 'r' : '-',
+		prot & PROT_WRITE ? 'w' : '-',
+		prot & PROT_EXEC ? 'x' : '-',
+		map__flags(map) ? 's' : 'p',
+		map__pgoff(map),
+		dso->id.ino, dso->name);
 
-		printed += fprintf(fp, "%*s  %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n",
-				   indent, "", map__start(map), map__end(map),
-				   prot & PROT_READ ? 'r' : '-',
-				   prot & PROT_WRITE ? 'w' : '-',
-				   prot & PROT_EXEC ? 'x' : '-',
-				   map__flags(map) ? 's' : 'p',
-				   map__pgoff(map),
-				   dso->id.ino, dso->name);
-	}
+	if (ret < 0)
+		return ret;
+
+	args->printed += ret;
+	return 0;
+}
+
+static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
+{
+	struct maps__fprintf_task_args args = {
+		.indent = indent,
+		.fp = fp,
+		.printed = 0,
+	};
+
+	maps__for_each_map(maps, maps__fprintf_task_cb, &args);
 
-	return printed;
+	return args.printed;
 }
 
 static void task__print_level(struct task *task, FILE *fp, int level)
-- 
GitLab


From b1928ca950386729b3bcd555efe559eaa1e2c8cc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:39 -0800
Subject: [PATCH 1565/4076] perf tests: Use function to add missing maps lock

Switch loop macro maps__for_each_entry to maps__for_each_map function
that takes a callback. The function holds the maps lock, which should
be held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/maps.c             |  61 ++++++----
 tools/perf/tests/vmlinux-kallsyms.c | 181 +++++++++++++++-------------
 2 files changed, 136 insertions(+), 106 deletions(-)

diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c
index 5bb1123a91a7c..bb3fbfe5a73e2 100644
--- a/tools/perf/tests/maps.c
+++ b/tools/perf/tests/maps.c
@@ -14,44 +14,59 @@ struct map_def {
 	u64 end;
 };
 
+struct check_maps_cb_args {
+	struct map_def *merged;
+	unsigned int i;
+};
+
+static int check_maps_cb(struct map *map, void *data)
+{
+	struct check_maps_cb_args *args = data;
+	struct map_def *merged = &args->merged[args->i];
+
+	if (map__start(map) != merged->start ||
+	    map__end(map) != merged->end ||
+	    strcmp(map__dso(map)->name, merged->name) ||
+	    refcount_read(map__refcnt(map)) != 1) {
+		return 1;
+	}
+	args->i++;
+	return 0;
+}
+
+static int failed_cb(struct map *map, void *data __maybe_unused)
+{
+	pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: %d\n",
+		map__start(map),
+		map__end(map),
+		map__dso(map)->name,
+		refcount_read(map__refcnt(map)));
+
+	return 0;
+}
+
 static int check_maps(struct map_def *merged, unsigned int size, struct maps *maps)
 {
-	struct map_rb_node *rb_node;
-	unsigned int i = 0;
 	bool failed = false;
 
 	if (maps__nr_maps(maps) != size) {
 		pr_debug("Expected %d maps, got %d", size, maps__nr_maps(maps));
 		failed = true;
 	} else {
-		maps__for_each_entry(maps, rb_node) {
-			struct map *map = rb_node->map;
-
-			if (map__start(map) != merged[i].start ||
-			    map__end(map) != merged[i].end ||
-			    strcmp(map__dso(map)->name, merged[i].name) ||
-			    refcount_read(map__refcnt(map)) != 1) {
-				failed = true;
-			}
-			i++;
-		}
+		struct check_maps_cb_args args = {
+			.merged = merged,
+			.i = 0,
+		};
+		failed = maps__for_each_map(maps, check_maps_cb, &args);
 	}
 	if (failed) {
 		pr_debug("Expected:\n");
-		for (i = 0; i < size; i++) {
+		for (unsigned int i = 0; i < size; i++) {
 			pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: 1\n",
 				merged[i].start, merged[i].end, merged[i].name);
 		}
 		pr_debug("Got:\n");
-		maps__for_each_entry(maps, rb_node) {
-			struct map *map = rb_node->map;
-
-			pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: %d\n",
-				map__start(map),
-				map__end(map),
-				map__dso(map)->name,
-				refcount_read(map__refcnt(map)));
-		}
+		maps__for_each_map(maps, failed_cb, NULL);
 	}
 	return failed ? TEST_FAIL : TEST_OK;
 }
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 1078a93b01aa0..822f893e67d5f 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -112,18 +112,92 @@ static bool is_ignored_symbol(const char *name, char type)
 	return false;
 }
 
+struct test__vmlinux_matches_kallsyms_cb_args {
+	struct machine kallsyms;
+	struct map *vmlinux_map;
+	bool header_printed;
+};
+
+static int test__vmlinux_matches_kallsyms_cb1(struct map *map, void *data)
+{
+	struct test__vmlinux_matches_kallsyms_cb_args *args = data;
+	struct dso *dso = map__dso(map);
+	/*
+	 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
+	 * the kernel will have the path for the vmlinux file being used, so use
+	 * the short name, less descriptive but the same ("[kernel]" in both
+	 * cases.
+	 */
+	struct map *pair = maps__find_by_name(args->kallsyms.kmaps,
+					(dso->kernel ? dso->short_name : dso->name));
+
+	if (pair)
+		map__set_priv(pair, 1);
+	else {
+		if (!args->header_printed) {
+			pr_info("WARN: Maps only in vmlinux:\n");
+			args->header_printed = true;
+		}
+		map__fprintf(map, stderr);
+	}
+	return 0;
+}
+
+static int test__vmlinux_matches_kallsyms_cb2(struct map *map, void *data)
+{
+	struct test__vmlinux_matches_kallsyms_cb_args *args = data;
+	struct map *pair;
+	u64 mem_start = map__unmap_ip(args->vmlinux_map, map__start(map));
+	u64 mem_end = map__unmap_ip(args->vmlinux_map, map__end(map));
+
+	pair = maps__find(args->kallsyms.kmaps, mem_start);
+	if (pair == NULL || map__priv(pair))
+		return 0;
+
+	if (map__start(pair) == mem_start) {
+		struct dso *dso = map__dso(map);
+
+		if (!args->header_printed) {
+			pr_info("WARN: Maps in vmlinux with a different name in kallsyms:\n");
+			args->header_printed = true;
+		}
+
+		pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
+			map__start(map), map__end(map), map__pgoff(map), dso->name);
+		if (mem_end != map__end(pair))
+			pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64,
+				map__start(pair), map__end(pair), map__pgoff(pair));
+		pr_info(" %s\n", dso->name);
+		map__set_priv(pair, 1);
+	}
+	return 0;
+}
+
+static int test__vmlinux_matches_kallsyms_cb3(struct map *map, void *data)
+{
+	struct test__vmlinux_matches_kallsyms_cb_args *args = data;
+
+	if (!map__priv(map)) {
+		if (!args->header_printed) {
+			pr_info("WARN: Maps only in kallsyms:\n");
+			args->header_printed = true;
+		}
+		map__fprintf(map, stderr);
+	}
+	return 0;
+}
+
 static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused,
 					int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct rb_node *nd;
 	struct symbol *sym;
-	struct map *kallsyms_map, *vmlinux_map;
-	struct map_rb_node *rb_node;
-	struct machine kallsyms, vmlinux;
+	struct map *kallsyms_map;
+	struct machine vmlinux;
 	struct maps *maps;
 	u64 mem_start, mem_end;
-	bool header_printed;
+	struct test__vmlinux_matches_kallsyms_cb_args args;
 
 	/*
 	 * Step 1:
@@ -131,7 +205,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * Init the machines that will hold kernel, modules obtained from
 	 * both vmlinux + .ko files and from /proc/kallsyms split by modules.
 	 */
-	machine__init(&kallsyms, "", HOST_KERNEL_ID);
+	machine__init(&args.kallsyms, "", HOST_KERNEL_ID);
 	machine__init(&vmlinux, "", HOST_KERNEL_ID);
 
 	maps = machine__kernel_maps(&vmlinux);
@@ -143,7 +217,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * load /proc/kallsyms. Also create the modules maps from /proc/modules
 	 * and find the .ko files that match them in /lib/modules/`uname -r`/.
 	 */
-	if (machine__create_kernel_maps(&kallsyms) < 0) {
+	if (machine__create_kernel_maps(&args.kallsyms) < 0) {
 		pr_debug("machine__create_kernel_maps failed");
 		err = TEST_SKIP;
 		goto out;
@@ -160,7 +234,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * be compacted against the list of modules found in the "vmlinux"
 	 * code and with the one got from /proc/modules from the "kallsyms" code.
 	 */
-	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms") <= 0) {
+	if (machine__load_kallsyms(&args.kallsyms, "/proc/kallsyms") <= 0) {
 		pr_debug("machine__load_kallsyms failed");
 		err = TEST_SKIP;
 		goto out;
@@ -174,7 +248,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * to see if the running kernel was relocated by checking if it has the
 	 * same value in the vmlinux file we load.
 	 */
-	kallsyms_map = machine__kernel_map(&kallsyms);
+	kallsyms_map = machine__kernel_map(&args.kallsyms);
 
 	/*
 	 * Step 5:
@@ -186,7 +260,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 		goto out;
 	}
 
-	vmlinux_map = machine__kernel_map(&vmlinux);
+	args.vmlinux_map = machine__kernel_map(&vmlinux);
 
 	/*
 	 * Step 6:
@@ -213,7 +287,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 	 * in the kallsyms dso. For the ones that are in both, check its names and
 	 * end addresses too.
 	 */
-	map__for_each_symbol(vmlinux_map, sym, nd) {
+	map__for_each_symbol(args.vmlinux_map, sym, nd) {
 		struct symbol *pair, *first_pair;
 
 		sym  = rb_entry(nd, struct symbol, rb_node);
@@ -221,10 +295,10 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused
 		if (sym->start == sym->end)
 			continue;
 
-		mem_start = map__unmap_ip(vmlinux_map, sym->start);
-		mem_end = map__unmap_ip(vmlinux_map, sym->end);
+		mem_start = map__unmap_ip(args.vmlinux_map, sym->start);
+		mem_end = map__unmap_ip(args.vmlinux_map, sym->end);
 
-		first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL);
+		first_pair = machine__find_kernel_symbol(&args.kallsyms, mem_start, NULL);
 		pair = first_pair;
 
 		if (pair && UM(pair->start) == mem_start) {
@@ -253,7 +327,8 @@ next_pair:
 				 */
 				continue;
 			} else {
-				pair = machine__find_kernel_symbol_by_name(&kallsyms, sym->name, NULL);
+				pair = machine__find_kernel_symbol_by_name(&args.kallsyms,
+									   sym->name, NULL);
 				if (pair) {
 					if (UM(pair->start) == mem_start)
 						goto next_pair;
@@ -267,7 +342,7 @@ next_pair:
 
 				continue;
 			}
-		} else if (mem_start == map__end(kallsyms.vmlinux_map)) {
+		} else if (mem_start == map__end(args.kallsyms.vmlinux_map)) {
 			/*
 			 * Ignore aliases to _etext, i.e. to the end of the kernel text area,
 			 * such as __indirect_thunk_end.
@@ -289,78 +364,18 @@ next_pair:
 	if (verbose <= 0)
 		goto out;
 
-	header_printed = false;
-
-	maps__for_each_entry(maps, rb_node) {
-		struct map *map = rb_node->map;
-		struct dso *dso = map__dso(map);
-		/*
-		 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
-		 * the kernel will have the path for the vmlinux file being used,
-		 * so use the short name, less descriptive but the same ("[kernel]" in
-		 * both cases.
-		 */
-		struct map *pair = maps__find_by_name(kallsyms.kmaps, (dso->kernel ?
-								dso->short_name :
-								dso->name));
-		if (pair) {
-			map__set_priv(pair, 1);
-		} else {
-			if (!header_printed) {
-				pr_info("WARN: Maps only in vmlinux:\n");
-				header_printed = true;
-			}
-			map__fprintf(map, stderr);
-		}
-	}
-
-	header_printed = false;
-
-	maps__for_each_entry(maps, rb_node) {
-		struct map *pair, *map = rb_node->map;
-
-		mem_start = map__unmap_ip(vmlinux_map, map__start(map));
-		mem_end = map__unmap_ip(vmlinux_map, map__end(map));
+	args.header_printed = false;
+	maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb1, &args);
 
-		pair = maps__find(kallsyms.kmaps, mem_start);
-		if (pair == NULL || map__priv(pair))
-			continue;
-
-		if (map__start(pair) == mem_start) {
-			struct dso *dso = map__dso(map);
-
-			if (!header_printed) {
-				pr_info("WARN: Maps in vmlinux with a different name in kallsyms:\n");
-				header_printed = true;
-			}
-
-			pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
-				map__start(map), map__end(map), map__pgoff(map), dso->name);
-			if (mem_end != map__end(pair))
-				pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64,
-					map__start(pair), map__end(pair), map__pgoff(pair));
-			pr_info(" %s\n", dso->name);
-			map__set_priv(pair, 1);
-		}
-	}
-
-	header_printed = false;
-
-	maps = machine__kernel_maps(&kallsyms);
+	args.header_printed = false;
+	maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb2, &args);
 
-	maps__for_each_entry(maps, rb_node) {
-		struct map *map = rb_node->map;
+	args.header_printed = false;
+	maps = machine__kernel_maps(&args.kallsyms);
+	maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb3, &args);
 
-		if (!map__priv(map)) {
-			if (!header_printed) {
-				pr_info("WARN: Maps only in kallsyms:\n");
-				header_printed = true;
-			}
-			map__fprintf(map, stderr);
-		}
-	}
 out:
-	machine__exit(&kallsyms);
+	machine__exit(&args.kallsyms);
 	machine__exit(&vmlinux);
 	return err;
 }
-- 
GitLab


From 2dc549b1dd495e7cdaa822a0af97365a8a1de840 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:40 -0800
Subject: [PATCH 1566/4076] perf machine: Use function to add missing maps lock

Switch machine__map_x86_64_entry_trampolines and
machine__for_each_kernel_map from loop macro maps__for_each_entry to
maps__for_each_map function that takes a callback. The function holds
the maps lock, which should be held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 53 +++++++++++++++++++++------------------
 1 file changed, 29 insertions(+), 24 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c5de5363b5e75..ca855fc435ac5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1285,33 +1285,46 @@ static u64 find_entry_trampoline(struct dso *dso)
 #define X86_64_CPU_ENTRY_AREA_SIZE	0x2c000
 #define X86_64_ENTRY_TRAMPOLINE		0x6000
 
+struct machine__map_x86_64_entry_trampolines_args {
+	struct maps *kmaps;
+	bool found;
+};
+
+static int machine__map_x86_64_entry_trampolines_cb(struct map *map, void *data)
+{
+	struct machine__map_x86_64_entry_trampolines_args *args = data;
+	struct map *dest_map;
+	struct kmap *kmap = __map__kmap(map);
+
+	if (!kmap || !is_entry_trampoline(kmap->name))
+		return 0;
+
+	dest_map = maps__find(args->kmaps, map__pgoff(map));
+	if (dest_map != map)
+		map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map)));
+
+	args->found = true;
+	return 0;
+}
+
 /* Map x86_64 PTI entry trampolines */
 int machine__map_x86_64_entry_trampolines(struct machine *machine,
 					  struct dso *kernel)
 {
-	struct maps *kmaps = machine__kernel_maps(machine);
+	struct machine__map_x86_64_entry_trampolines_args args = {
+		.kmaps = machine__kernel_maps(machine),
+		.found = false,
+	};
 	int nr_cpus_avail, cpu;
-	bool found = false;
-	struct map_rb_node *rb_node;
 	u64 pgoff;
 
 	/*
 	 * In the vmlinux case, pgoff is a virtual address which must now be
 	 * mapped to a vmlinux offset.
 	 */
-	maps__for_each_entry(kmaps, rb_node) {
-		struct map *dest_map, *map = rb_node->map;
-		struct kmap *kmap = __map__kmap(map);
-
-		if (!kmap || !is_entry_trampoline(kmap->name))
-			continue;
+	maps__for_each_map(args.kmaps, machine__map_x86_64_entry_trampolines_cb, &args);
 
-		dest_map = maps__find(kmaps, map__pgoff(map));
-		if (dest_map != map)
-			map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map)));
-		found = true;
-	}
-	if (found || machine->trampolines_mapped)
+	if (args.found || machine->trampolines_mapped)
 		return 0;
 
 	pgoff = find_entry_trampoline(kernel);
@@ -3398,16 +3411,8 @@ int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv
 int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv)
 {
 	struct maps *maps = machine__kernel_maps(machine);
-	struct map_rb_node *pos;
-	int err = 0;
 
-	maps__for_each_entry(maps, pos) {
-		err = fn(pos->map, priv);
-		if (err != 0) {
-			break;
-		}
-	}
-	return err;
+	return maps__for_each_map(maps, fn, priv);
 }
 
 bool machine__is_lock_function(struct machine *machine, u64 addr)
-- 
GitLab


From 300b53d5b819a33e2d4567cc35e1d92b4b49cd9c Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:41 -0800
Subject: [PATCH 1567/4076] perf probe-event: Use function to add missing maps
 lock

Switch kernel_get_module_map from loop macro maps__for_each_entry to
maps__for_each_map function that takes a callback. The function holds
the maps lock, which should be held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-8-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/probe-event.c | 40 +++++++++++++++++++++++------------
 1 file changed, 26 insertions(+), 14 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 1a5b7fa459b23..a1a796043691f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -149,10 +149,32 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 	return 0;
 }
 
+struct kernel_get_module_map_cb_args {
+	const char *module;
+	struct map *result;
+};
+
+static int kernel_get_module_map_cb(struct map *map, void *data)
+{
+	struct kernel_get_module_map_cb_args *args = data;
+	struct dso *dso = map__dso(map);
+	const char *short_name = dso->short_name; /* short_name is "[module]" */
+	u16 short_name_len =  dso->short_name_len;
+
+	if (strncmp(short_name + 1, args->module, short_name_len - 2) == 0 &&
+	    args->module[short_name_len - 2] == '\0') {
+		args->result = map__get(map);
+		return 1;
+	}
+	return 0;
+}
+
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct maps *maps = machine__kernel_maps(host_machine);
-	struct map_rb_node *pos;
+	struct kernel_get_module_map_cb_args args = {
+		.module = module,
+		.result = NULL,
+	};
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
@@ -164,19 +186,9 @@ static struct map *kernel_get_module_map(const char *module)
 		return map__get(map);
 	}
 
-	maps__for_each_entry(maps, pos) {
-		/* short_name is "[module]" */
-		struct dso *dso = map__dso(pos->map);
-		const char *short_name = dso->short_name;
-		u16 short_name_len =  dso->short_name_len;
+	maps__for_each_map(machine__kernel_maps(host_machine), kernel_get_module_map_cb, &args);
 
-		if (strncmp(short_name + 1, module,
-			    short_name_len - 2) == 0 &&
-		    module[short_name_len - 2] == '\0') {
-			return map__get(pos->map);
-		}
-	}
-	return NULL;
+	return args.result;
 }
 
 struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user)
-- 
GitLab


From 111350c67d15ffc284801509acdcf256d77876ca Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:42 -0800
Subject: [PATCH 1568/4076] perf symbol: Use function to add missing maps lock

Switch do_validate_kcore_modules from loop macro maps__for_each_entry to
maps__for_each_map function that takes a callback. The function holds
the maps lock, which should be held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/symbol.c | 36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 1cc42b8d8afb7..72f03b875478a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1114,33 +1114,35 @@ out_delete_from:
 	return ret;
 }
 
+static int do_validate_kcore_modules_cb(struct map *old_map, void *data)
+{
+	struct rb_root *modules = data;
+	struct module_info *mi;
+	struct dso *dso;
+
+	if (!__map__is_kmodule(old_map))
+		return 0;
+
+	dso = map__dso(old_map);
+	/* Module must be in memory at the same address */
+	mi = find_module(dso->short_name, modules);
+	if (!mi || mi->start != map__start(old_map))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int do_validate_kcore_modules(const char *filename, struct maps *kmaps)
 {
 	struct rb_root modules = RB_ROOT;
-	struct map_rb_node *old_node;
 	int err;
 
 	err = read_proc_modules(filename, &modules);
 	if (err)
 		return err;
 
-	maps__for_each_entry(kmaps, old_node) {
-		struct map *old_map = old_node->map;
-		struct module_info *mi;
-		struct dso *dso;
+	err = maps__for_each_map(kmaps, do_validate_kcore_modules_cb, &modules);
 
-		if (!__map__is_kmodule(old_map)) {
-			continue;
-		}
-		dso = map__dso(old_map);
-		/* Module must be in memory at the same address */
-		mi = find_module(dso->short_name, &modules);
-		if (!mi || mi->start != map__start(old_map)) {
-			err = -EINVAL;
-			goto out;
-		}
-	}
-out:
 	delete_modules(&modules);
 	return err;
 }
-- 
GitLab


From 228493d0a83bc2aec7f4a25491621f9d3b6d7bf2 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:43 -0800
Subject: [PATCH 1569/4076] perf synthetic-events: Use function to add missing
 maps lock

Switch perf_event__synthesize_modules from loop macro
maps__for_each_entry to maps__for_each_map function that takes
a callback. The function holds the maps lock, which should be
held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-10-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/synthetic-events.c | 118 ++++++++++++++++-------------
 1 file changed, 67 insertions(+), 51 deletions(-)

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index a0579c7d7b9e9..3712186353fb9 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -665,18 +665,74 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool __maybe_unused,
 }
 #endif
 
+struct perf_event__synthesize_modules_maps_cb_args {
+	struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	union perf_event *event;
+};
+
+static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data)
+{
+	struct perf_event__synthesize_modules_maps_cb_args *args = data;
+	union perf_event *event = args->event;
+	struct dso *dso;
+	size_t size;
+
+	if (!__map__is_kmodule(map))
+		return 0;
+
+	dso = map__dso(map);
+	if (symbol_conf.buildid_mmap2) {
+		size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
+		event->mmap2.header.type = PERF_RECORD_MMAP2;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, args->machine->id_hdr_size);
+		event->mmap2.header.size += args->machine->id_hdr_size;
+		event->mmap2.start = map__start(map);
+		event->mmap2.len   = map__size(map);
+		event->mmap2.pid   = args->machine->pid;
+
+		memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1);
+
+		perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false);
+	} else {
+		size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
+		event->mmap.header.type = PERF_RECORD_MMAP;
+		event->mmap.header.size = (sizeof(event->mmap) -
+					(sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, args->machine->id_hdr_size);
+		event->mmap.header.size += args->machine->id_hdr_size;
+		event->mmap.start = map__start(map);
+		event->mmap.len   = map__size(map);
+		event->mmap.pid   = args->machine->pid;
+
+		memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1);
+	}
+
+	if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0)
+		return -1;
+
+	return 0;
+}
+
 int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process,
 				   struct machine *machine)
 {
-	int rc = 0;
-	struct map_rb_node *pos;
+	int rc;
 	struct maps *maps = machine__kernel_maps(machine);
-	union perf_event *event;
-	size_t size = symbol_conf.buildid_mmap2 ?
-			sizeof(event->mmap2) : sizeof(event->mmap);
+	struct perf_event__synthesize_modules_maps_cb_args args = {
+		.tool = tool,
+		.process = process,
+		.machine = machine,
+	};
+	size_t size = symbol_conf.buildid_mmap2
+		? sizeof(args.event->mmap2)
+		: sizeof(args.event->mmap);
 
-	event = zalloc(size + machine->id_hdr_size);
-	if (event == NULL) {
+	args.event = zalloc(size + machine->id_hdr_size);
+	if (args.event == NULL) {
 		pr_debug("Not enough memory synthesizing mmap event "
 			 "for kernel modules\n");
 		return -1;
@@ -687,53 +743,13 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t
 	 * __perf_event_mmap
 	 */
 	if (machine__is_host(machine))
-		event->header.misc = PERF_RECORD_MISC_KERNEL;
+		args.event->header.misc = PERF_RECORD_MISC_KERNEL;
 	else
-		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-
-	maps__for_each_entry(maps, pos) {
-		struct map *map = pos->map;
-		struct dso *dso;
+		args.event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-		if (!__map__is_kmodule(map))
-			continue;
+	rc = maps__for_each_map(maps, perf_event__synthesize_modules_maps_cb, &args);
 
-		dso = map__dso(map);
-		if (symbol_conf.buildid_mmap2) {
-			size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
-			event->mmap2.header.type = PERF_RECORD_MMAP2;
-			event->mmap2.header.size = (sizeof(event->mmap2) -
-						(sizeof(event->mmap2.filename) - size));
-			memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
-			event->mmap2.header.size += machine->id_hdr_size;
-			event->mmap2.start = map__start(map);
-			event->mmap2.len   = map__size(map);
-			event->mmap2.pid   = machine->pid;
-
-			memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1);
-
-			perf_record_mmap2__read_build_id(&event->mmap2, machine, false);
-		} else {
-			size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
-			event->mmap.header.type = PERF_RECORD_MMAP;
-			event->mmap.header.size = (sizeof(event->mmap) -
-						(sizeof(event->mmap.filename) - size));
-			memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-			event->mmap.header.size += machine->id_hdr_size;
-			event->mmap.start = map__start(map);
-			event->mmap.len   = map__size(map);
-			event->mmap.pid   = machine->pid;
-
-			memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1);
-		}
-
-		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
-			rc = -1;
-			break;
-		}
-	}
-
-	free(event);
+	free(args.event);
 	return rc;
 }
 
-- 
GitLab


From 71225af17f611632226a4a2fae25235fd8dad268 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:44 -0800
Subject: [PATCH 1570/4076] perf thread: Use function to add missing maps lock

Switch thread__prepare_access from loop macro maps__for_each_entry
to maps__for_each_map function that takes a callback. The function
holds the maps lock, which should be held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-11-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index b9c2039c4230c..b6986a81aa6df 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -349,34 +349,33 @@ int thread__insert_map(struct thread *thread, struct map *map)
 	return maps__insert(thread__maps(thread), map);
 }
 
-static int __thread__prepare_access(struct thread *thread)
+struct thread__prepare_access_maps_cb_args {
+	int err;
+	struct maps *maps;
+};
+
+static int thread__prepare_access_maps_cb(struct map *map, void *data)
 {
 	bool initialized = false;
-	int err = 0;
-	struct maps *maps = thread__maps(thread);
-	struct map_rb_node *rb_node;
-
-	down_read(maps__lock(maps));
-
-	maps__for_each_entry(maps, rb_node) {
-		err = unwind__prepare_access(thread__maps(thread), rb_node->map, &initialized);
-		if (err || initialized)
-			break;
-	}
+	struct thread__prepare_access_maps_cb_args *args = data;
 
-	up_read(maps__lock(maps));
+	args->err = unwind__prepare_access(args->maps, map, &initialized);
 
-	return err;
+	return (args->err || initialized) ? 1 : 0;
 }
 
 static int thread__prepare_access(struct thread *thread)
 {
-	int err = 0;
+	struct thread__prepare_access_maps_cb_args args = {
+		.err = 0,
+	};
 
-	if (dwarf_callchain_users)
-		err = __thread__prepare_access(thread);
+	if (dwarf_callchain_users) {
+		args.maps = thread__maps(thread);
+		maps__for_each_map(thread__maps(thread), thread__prepare_access_maps_cb, &args);
+	}
 
-	return err;
+	return args.err;
 }
 
 static int thread__clone_maps(struct thread *thread, struct thread *parent, bool do_maps_clone)
-- 
GitLab


From 7ab6fb505b2a7447c4a7237a12c59e3ad0c7298c Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Tue, 19 Dec 2023 10:48:27 +0800
Subject: [PATCH 1571/4076] LoongArch: KVM: Optimization for memslot hugepage
 checking

During shadow mmu page fault, there is checking for huge page for
specified memslot. Page fault is hot path, check logic can be done
when memslot is created. Here two flags are added for huge page
checking, KVM_MEM_HUGEPAGE_CAPABLE and KVM_MEM_HUGEPAGE_INCAPABLE.
Indeed for an optimized qemu, memslot for DRAM is always huge page
aligned. The flag is firstly checked during hot page fault path.

Now only huge page flag is supported, there is a long way for super
page support in LoongArch system. Since super page size is 64G for
16K pagesize and 1G for 4K pagesize, 64G physical address is rarely
used and LoongArch kernel needs support super page for 4K. Also memory
layout of LoongArch qemu VM should be 1G aligned.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/kvm_host.h |   3 +
 arch/loongarch/kvm/mmu.c              | 124 +++++++++++++++++---------
 2 files changed, 86 insertions(+), 41 deletions(-)

diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 11328700d4fa8..0e89db020481c 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -45,7 +45,10 @@ struct kvm_vcpu_stat {
 	u64 signal_exits;
 };
 
+#define KVM_MEM_HUGEPAGE_CAPABLE	(1UL << 0)
+#define KVM_MEM_HUGEPAGE_INCAPABLE	(1UL << 1)
 struct kvm_arch_memory_slot {
+	unsigned long flags;
 };
 
 struct kvm_context {
diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c
index 80480df5f5505..915f175278931 100644
--- a/arch/loongarch/kvm/mmu.c
+++ b/arch/loongarch/kvm/mmu.c
@@ -13,6 +13,16 @@
 #include <asm/tlb.h>
 #include <asm/kvm_mmu.h>
 
+static inline bool kvm_hugepage_capable(struct kvm_memory_slot *slot)
+{
+	return slot->arch.flags & KVM_MEM_HUGEPAGE_CAPABLE;
+}
+
+static inline bool kvm_hugepage_incapable(struct kvm_memory_slot *slot)
+{
+	return slot->arch.flags & KVM_MEM_HUGEPAGE_INCAPABLE;
+}
+
 static inline void kvm_ptw_prepare(struct kvm *kvm, kvm_ptw_ctx *ctx)
 {
 	ctx->level = kvm->arch.root_level;
@@ -365,6 +375,69 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_ptw_top(kvm->arch.pgd, start << PAGE_SHIFT, end << PAGE_SHIFT, &ctx);
 }
 
+int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new, enum kvm_mr_change change)
+{
+	gpa_t gpa_start;
+	hva_t hva_start;
+	size_t size, gpa_offset, hva_offset;
+
+	if ((change != KVM_MR_MOVE) && (change != KVM_MR_CREATE))
+		return 0;
+	/*
+	 * Prevent userspace from creating a memory region outside of the
+	 * VM GPA address space
+	 */
+	if ((new->base_gfn + new->npages) > (kvm->arch.gpa_size >> PAGE_SHIFT))
+		return -ENOMEM;
+
+	new->arch.flags = 0;
+	size = new->npages * PAGE_SIZE;
+	gpa_start = new->base_gfn << PAGE_SHIFT;
+	hva_start = new->userspace_addr;
+	if (IS_ALIGNED(size, PMD_SIZE) && IS_ALIGNED(gpa_start, PMD_SIZE)
+			&& IS_ALIGNED(hva_start, PMD_SIZE))
+		new->arch.flags |= KVM_MEM_HUGEPAGE_CAPABLE;
+	else {
+		/*
+		 * Pages belonging to memslots that don't have the same
+		 * alignment within a PMD for userspace and GPA cannot be
+		 * mapped with PMD entries, because we'll end up mapping
+		 * the wrong pages.
+		 *
+		 * Consider a layout like the following:
+		 *
+		 *    memslot->userspace_addr:
+		 *    +-----+--------------------+--------------------+---+
+		 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
+		 *    +-----+--------------------+--------------------+---+
+		 *
+		 *    memslot->base_gfn << PAGE_SIZE:
+		 *      +---+--------------------+--------------------+-----+
+		 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
+		 *      +---+--------------------+--------------------+-----+
+		 *
+		 * If we create those stage-2 blocks, we'll end up with this
+		 * incorrect mapping:
+		 *   d -> f
+		 *   e -> g
+		 *   f -> h
+		 */
+		gpa_offset = gpa_start & (PMD_SIZE - 1);
+		hva_offset = hva_start & (PMD_SIZE - 1);
+		if (gpa_offset != hva_offset) {
+			new->arch.flags |= KVM_MEM_HUGEPAGE_INCAPABLE;
+		} else {
+			if (gpa_offset == 0)
+				gpa_offset = PMD_SIZE;
+			if ((size + gpa_offset) < (PMD_SIZE * 2))
+				new->arch.flags |= KVM_MEM_HUGEPAGE_INCAPABLE;
+		}
+	}
+
+	return 0;
+}
+
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *old,
 				   const struct kvm_memory_slot *new,
@@ -562,47 +635,23 @@ out:
 }
 
 static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot,
-				unsigned long hva, unsigned long map_size, bool write)
+				unsigned long hva, bool write)
 {
-	size_t size;
-	gpa_t gpa_start;
-	hva_t uaddr_start, uaddr_end;
+	hva_t start, end;
 
 	/* Disable dirty logging on HugePages */
 	if (kvm_slot_dirty_track_enabled(memslot) && write)
 		return false;
 
-	size = memslot->npages * PAGE_SIZE;
-	gpa_start = memslot->base_gfn << PAGE_SHIFT;
-	uaddr_start = memslot->userspace_addr;
-	uaddr_end = uaddr_start + size;
+	if (kvm_hugepage_capable(memslot))
+		return true;
 
-	/*
-	 * Pages belonging to memslots that don't have the same alignment
-	 * within a PMD for userspace and GPA cannot be mapped with stage-2
-	 * PMD entries, because we'll end up mapping the wrong pages.
-	 *
-	 * Consider a layout like the following:
-	 *
-	 *    memslot->userspace_addr:
-	 *    +-----+--------------------+--------------------+---+
-	 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
-	 *    +-----+--------------------+--------------------+---+
-	 *
-	 *    memslot->base_gfn << PAGE_SIZE:
-	 *      +---+--------------------+--------------------+-----+
-	 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
-	 *      +---+--------------------+--------------------+-----+
-	 *
-	 * If we create those stage-2 blocks, we'll end up with this incorrect
-	 * mapping:
-	 *   d -> f
-	 *   e -> g
-	 *   f -> h
-	 */
-	if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1)))
+	if (kvm_hugepage_incapable(memslot))
 		return false;
 
+	start = memslot->userspace_addr;
+	end = start + memslot->npages * PAGE_SIZE;
+
 	/*
 	 * Next, let's make sure we're not trying to map anything not covered
 	 * by the memslot. This means we have to prohibit block size mappings
@@ -615,8 +664,7 @@ static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot,
 	 * userspace_addr or the base_gfn, as both are equally aligned (per
 	 * the check above) and equally sized.
 	 */
-	return (hva & ~(map_size - 1)) >= uaddr_start &&
-		(hva & ~(map_size - 1)) + map_size <= uaddr_end;
+	return (hva >= ALIGN(start, PMD_SIZE)) && (hva < ALIGN_DOWN(end, PMD_SIZE));
 }
 
 /*
@@ -842,7 +890,7 @@ retry:
 
 	/* Disable dirty logging on HugePages */
 	level = 0;
-	if (!fault_supports_huge_mapping(memslot, hva, PMD_SIZE, write)) {
+	if (!fault_supports_huge_mapping(memslot, hva, write)) {
 		level = 0;
 	} else {
 		level = host_pfn_mapping_level(kvm, gfn, memslot);
@@ -901,12 +949,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 
-int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old,
-				   struct kvm_memory_slot *new, enum kvm_mr_change change)
-{
-	return 0;
-}
-
 void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
 					const struct kvm_memory_slot *memslot)
 {
-- 
GitLab


From 161267320158920a601e40d83fdac60bcaa2acb5 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Tue, 19 Dec 2023 10:48:27 +0800
Subject: [PATCH 1572/4076] LoongArch: KVM: Remove SW timer switch when vcpu is
 halt polling

With halt-polling supported, there is checking for pending events or
interrupts when vcpu executes idle instruction. Pending interrupts
include injected SW interrupts and passthrough HW interrupts, such as
HW timer interrupts, since HW timer works still even if vcpu exists from
VM mode.

Since HW timer pending interrupt can be set directly with CSR status
register, and pending HW timer interrupt checking is used in vcpu block
checking function, it is not necessary to switch to SW timer during
halt-polling. This patch adds preemption disabling in function
kvm_cpu_has_pending_timer(), and removes SW timer switching in idle
instruction emulation function.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/exit.c  | 13 ++-----------
 arch/loongarch/kvm/timer.c | 12 +++++++++---
 arch/loongarch/kvm/vcpu.c  |  9 ++++++++-
 3 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index ce8de3fa472cc..e708a1786d6bd 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -200,17 +200,8 @@ int kvm_emu_idle(struct kvm_vcpu *vcpu)
 	++vcpu->stat.idle_exits;
 	trace_kvm_exit_idle(vcpu, KVM_TRACE_EXIT_IDLE);
 
-	if (!kvm_arch_vcpu_runnable(vcpu)) {
-		/*
-		 * Switch to the software timer before halt-polling/blocking as
-		 * the guest's timer may be a break event for the vCPU, and the
-		 * hypervisor timer runs only when the CPU is in guest mode.
-		 * Switch before halt-polling so that KVM recognizes an expired
-		 * timer before blocking.
-		 */
-		kvm_save_timer(vcpu);
-		kvm_vcpu_block(vcpu);
-	}
+	if (!kvm_arch_vcpu_runnable(vcpu))
+		kvm_vcpu_halt(vcpu);
 
 	return EMULATE_DONE;
 }
diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index 284bf553fefef..12d58040122dd 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -155,11 +155,17 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu)
 		 */
 		hrtimer_cancel(&vcpu->arch.swtimer);
 		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
-	} else
+	} else if (vcpu->stat.generic.blocking) {
 		/*
-		 * Inject timer interrupt so that hall polling can dectect and exit
+		 * Inject timer interrupt so that halt polling can dectect and exit.
+		 * VCPU is scheduled out already and sleeps in rcuwait queue and
+		 * will not poll pending events again. kvm_queue_irq() is not enough,
+		 * hrtimer swtimer should be used here.
 		 */
-		kvm_queue_irq(vcpu, INT_TI);
+		expire = ktime_add_ns(ktime_get(), 10);
+		vcpu->arch.expire = expire;
+		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
+	}
 }
 
 /*
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 73d0c2b9c1a57..54f544b30f32a 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -187,8 +187,15 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	return kvm_pending_timer(vcpu) ||
+	int ret;
+
+	/* Protect from TOD sync and vcpu_load/put() */
+	preempt_disable();
+	ret = kvm_pending_timer(vcpu) ||
 		kvm_read_hw_gcsr(LOONGARCH_CSR_ESTAT) & (1 << INT_TI);
+	preempt_enable();
+
+	return ret;
 }
 
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu)
-- 
GitLab


From 0d2abe67029644741bf7400b0d00c2faa3e1c455 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Tue, 19 Dec 2023 10:48:27 +0800
Subject: [PATCH 1573/4076] LoongArch: KVM: Allow to access HW timer CSR
 registers always

Currently HW timer CSR registers are allowed to access before entering
to vm and disabled if switch to SW timer in host mode, instead it is not
necessary to do so. HW timer CSR registers can be accessed always, it
is nothing to do with whether it is in vm mode or host mode. This patch
removes the limitation.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/main.c  |  1 -
 arch/loongarch/kvm/timer.c | 27 ++++++---------------------
 2 files changed, 6 insertions(+), 22 deletions(-)

diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index 1c1d5199500ee..86a2f2d0cb27e 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -287,7 +287,6 @@ int kvm_arch_hardware_enable(void)
 	if (env & CSR_GCFG_MATC_ROOT)
 		gcfg |= CSR_GCFG_MATC_ROOT;
 
-	gcfg |= CSR_GCFG_TIT;
 	write_csr_gcfg(gcfg);
 
 	kvm_flush_tlb_all();
diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index 12d58040122dd..d6d5bcea349bd 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -70,15 +70,6 @@ void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long timer_hz)
  */
 void kvm_acquire_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long cfg;
-
-	cfg = read_csr_gcfg();
-	if (!(cfg & CSR_GCFG_TIT))
-		return;
-
-	/* Enable guest access to hard timer */
-	write_csr_gcfg(cfg & ~CSR_GCFG_TIT);
-
 	/*
 	 * Freeze the soft-timer and sync the guest stable timer with it. We do
 	 * this with interrupts disabled to avoid latency.
@@ -174,21 +165,15 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu)
  */
 void kvm_save_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long cfg;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
 	preempt_disable();
-	cfg = read_csr_gcfg();
-	if (!(cfg & CSR_GCFG_TIT)) {
-		/* Disable guest use of hard timer */
-		write_csr_gcfg(cfg | CSR_GCFG_TIT);
-
-		/* Save hard timer state */
-		kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
-		kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TVAL);
-		if (kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG) & CSR_TCFG_EN)
-			_kvm_save_timer(vcpu);
-	}
+
+	/* Save hard timer state */
+	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
+	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TVAL);
+	if (kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG) & CSR_TCFG_EN)
+		_kvm_save_timer(vcpu);
 
 	/* Save timer-related state to vCPU context */
 	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
-- 
GitLab


From 1ab9c6099495f79bfbcd6058d02d7556034a89b0 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Tue, 19 Dec 2023 10:48:28 +0800
Subject: [PATCH 1574/4076] LoongArch: KVM: Remove kvm_acquire_timer() before
 entering guest

Timer emulation method in VM is switch to SW timer, there are two
places where timer emulation is needed. One is during vcpu thread
context switch, the other is halt-polling with idle instruction
emulation. SW timer switching is removed during halt-polling mode,
so it is not necessary to disable SW timer before entering to guest.

This patch removes SW timer handling before entering guest mode, and
put it in HW timer restoring flow when vcpu thread is sched-in. With
this patch, vm timer emulation is simpler, there is SW/HW timer
switch only in vcpu thread context switch scenario.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/kvm_vcpu.h |  1 -
 arch/loongarch/kvm/timer.c            | 22 ++++++--------------
 arch/loongarch/kvm/vcpu.c             | 29 ---------------------------
 3 files changed, 6 insertions(+), 46 deletions(-)

diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
index 553cfa2b2b1cf..0e87652f780a0 100644
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -55,7 +55,6 @@ void kvm_save_fpu(struct loongarch_fpu *fpu);
 void kvm_restore_fpu(struct loongarch_fpu *fpu);
 void kvm_restore_fcsr(struct loongarch_fpu *fpu);
 
-void kvm_acquire_timer(struct kvm_vcpu *vcpu);
 void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
 void kvm_reset_timer(struct kvm_vcpu *vcpu);
 void kvm_save_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index d6d5bcea349bd..d362d87a54aa1 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -64,19 +64,6 @@ void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long timer_hz)
 	kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_TVAL, 0);
 }
 
-/*
- * Restore hard timer state and enable guest to access timer registers
- * without trap, should be called with irq disabled
- */
-void kvm_acquire_timer(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * Freeze the soft-timer and sync the guest stable timer with it. We do
-	 * this with interrupts disabled to avoid latency.
-	 */
-	hrtimer_cancel(&vcpu->arch.swtimer);
-}
-
 /*
  * Restore soft timer state from saved context.
  */
@@ -98,6 +85,11 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
 		return;
 	}
 
+	/*
+	 * Freeze the soft-timer and sync the guest stable timer with it.
+	 */
+	hrtimer_cancel(&vcpu->arch.swtimer);
+
 	/*
 	 * Set remainder tick value if not expired
 	 */
@@ -115,7 +107,7 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
 		/*
 		 * Inject timer here though sw timer should inject timer
 		 * interrupt async already, since sw timer may be cancelled
-		 * during injecting intr async in function kvm_acquire_timer
+		 * during injecting intr async
 		 */
 		kvm_queue_irq(vcpu, INT_TI);
 	}
@@ -140,11 +132,9 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu)
 	vcpu->arch.expire = expire;
 	if (ticks) {
 		/*
-		 * Update hrtimer to use new timeout
 		 * HRTIMER_MODE_PINNED is suggested since vcpu may run in
 		 * the same physical cpu in next time
 		 */
-		hrtimer_cancel(&vcpu->arch.swtimer);
 		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
 	} else if (vcpu->stat.generic.blocking) {
 		/*
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 54f544b30f32a..53fcef8b24a10 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -95,7 +95,6 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
 		 * check vmid before vcpu enter guest
 		 */
 		local_irq_disable();
-		kvm_acquire_timer(vcpu);
 		kvm_deliver_intr(vcpu);
 		kvm_deliver_exception(vcpu);
 		/* Make sure the vcpu mode has been written */
@@ -251,23 +250,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
-/**
- * kvm_migrate_count() - Migrate timer.
- * @vcpu:       Virtual CPU.
- *
- * Migrate hrtimer to the current CPU by cancelling and restarting it
- * if the hrtimer is active.
- *
- * Must be called when the vCPU is migrated to a different CPU, so that
- * the timer can interrupt the guest at the new CPU, and the timer irq can
- * be delivered to the vCPU.
- */
-static void kvm_migrate_count(struct kvm_vcpu *vcpu)
-{
-	if (hrtimer_cancel(&vcpu->arch.swtimer))
-		hrtimer_restart(&vcpu->arch.swtimer);
-}
-
 static int _kvm_getcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 *val)
 {
 	unsigned long gintc;
@@ -796,17 +778,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	if (vcpu->arch.last_sched_cpu != cpu) {
-		kvm_debug("[%d->%d]KVM vCPU[%d] switch\n",
-				vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id);
-		/*
-		 * Migrate the timer interrupt to the current CPU so that it
-		 * always interrupts the guest and synchronously triggers a
-		 * guest timer interrupt.
-		 */
-		kvm_migrate_count(vcpu);
-	}
-
 	/* Restore guest state to registers */
 	_kvm_vcpu_load(vcpu, cpu);
 	local_irq_restore(flags);
-- 
GitLab


From 5b3d524993ff1fb36089be850ccb121ac3296bcf Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Tue, 19 Dec 2023 10:48:28 +0800
Subject: [PATCH 1575/4076] LoongArch: KVM: Fix timer emulation with oneshot
 mode

When timer is fired in oneshot mode, CSR TVAL will be -1 rather than 0.
There needs special handing for this situation. There are two scenarios
when oneshot timer is fired. One scenario is that time is fired after
exiting to host, CSR TVAL is set with 0 in order to inject hw interrupt,
and -1 will assigned to CSR TVAL soon.

The other situation is that timer is fired in VM and guest kernel is
hanlding timer IRQ, IRQ is acked and is ready to set next expired timer
value, then vm exits to host. Timer interrupt should not be inject at
this point, else there will be spurious timer interrupt.

Here hw timer irq status in CSR ESTAT is used to judge these two
scenarios. If CSR TVAL is -1, the oneshot timer is fired; and if timer
hw irq is on in CSR ESTAT register, it happens after exiting to host;
else if timer hw irq is off, we think that it happens in vm and timer
IRQ handler has already acked IRQ.

With this patch, runltp with version ltp20230516 passes to run in vm.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/timer.c | 68 ++++++++++++++++++++++++++++++--------
 1 file changed, 55 insertions(+), 13 deletions(-)

diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index d362d87a54aa1..111328f608728 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -69,14 +69,19 @@ void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long timer_hz)
  */
 void kvm_restore_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long cfg, delta, period;
+	unsigned long cfg, estat;
+	unsigned long ticks, delta, period;
 	ktime_t expire, now;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
 	/*
 	 * Set guest stable timer cfg csr
+	 * Disable timer before restore estat CSR register, avoid to
+	 * get invalid timer interrupt for old timer cfg
 	 */
 	cfg = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG);
+
+	write_gcsr_timercfg(0);
 	kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
 	kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
 	if (!(cfg & CSR_TCFG_EN)) {
@@ -90,20 +95,47 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
 	 */
 	hrtimer_cancel(&vcpu->arch.swtimer);
 
+	/*
+	 * From LoongArch Reference Manual Volume 1 Chapter 7.6.2
+	 * If oneshot timer is fired, CSR TVAL will be -1, there are two
+	 * conditions:
+	 *  1) timer is fired during exiting to host
+	 *  2) timer is fired and vm is doing timer irq, and then exiting to
+	 *     host. Host should not inject timer irq to avoid spurious
+	 *     timer interrupt again
+	 */
+	ticks = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TVAL);
+	estat = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_ESTAT);
+	if (!(cfg & CSR_TCFG_PERIOD) && (ticks > cfg)) {
+		/*
+		 * Writing 0 to LOONGARCH_CSR_TVAL will inject timer irq
+		 * and set CSR TVAL with -1
+		 */
+		write_gcsr_timertick(0);
+
+		/*
+		 * Writing CSR_TINTCLR_TI to LOONGARCH_CSR_TINTCLR will clear
+		 * timer interrupt, and CSR TVAL keeps unchanged with -1, it
+		 * avoids spurious timer interrupt
+		 */
+		if (!(estat & CPU_TIMER))
+			gcsr_write(CSR_TINTCLR_TI, LOONGARCH_CSR_TINTCLR);
+		return;
+	}
+
 	/*
 	 * Set remainder tick value if not expired
 	 */
+	delta = 0;
 	now = ktime_get();
 	expire = vcpu->arch.expire;
 	if (ktime_before(now, expire))
 		delta = ktime_to_tick(vcpu, ktime_sub(expire, now));
-	else {
-		if (cfg & CSR_TCFG_PERIOD) {
-			period = cfg & CSR_TCFG_VAL;
-			delta = ktime_to_tick(vcpu, ktime_sub(now, expire));
-			delta = period - (delta % period);
-		} else
-			delta = 0;
+	else if (cfg & CSR_TCFG_PERIOD) {
+		period = cfg & CSR_TCFG_VAL;
+		delta = ktime_to_tick(vcpu, ktime_sub(now, expire));
+		delta = period - (delta % period);
+
 		/*
 		 * Inject timer here though sw timer should inject timer
 		 * interrupt async already, since sw timer may be cancelled
@@ -122,15 +154,25 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
  */
 static void _kvm_save_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long ticks, delta;
+	unsigned long ticks, delta, cfg;
 	ktime_t expire;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
+	cfg = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG);
 	ticks = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TVAL);
-	delta = tick_to_ns(vcpu, ticks);
-	expire = ktime_add_ns(ktime_get(), delta);
-	vcpu->arch.expire = expire;
-	if (ticks) {
+
+	/*
+	 * From LoongArch Reference Manual Volume 1 Chapter 7.6.2
+	 * If period timer is fired, CSR TVAL will be reloaded from CSR TCFG
+	 * If oneshot timer is fired, CSR TVAL will be -1
+	 * Here judge one-shot timer fired by checking whether TVAL is larger
+	 * than TCFG
+	 */
+	if (ticks < cfg) {
+		delta = tick_to_ns(vcpu, ticks);
+		expire = ktime_add_ns(ktime_get(), delta);
+		vcpu->arch.expire = expire;
+
 		/*
 		 * HRTIMER_MODE_PINNED is suggested since vcpu may run in
 		 * the same physical cpu in next time
-- 
GitLab


From db1ecca22edf27c5a3dd66af406c88b5b5ac7cc1 Mon Sep 17 00:00:00 2001
From: Tianrui Zhao <zhaotianrui@loongson.cn>
Date: Tue, 19 Dec 2023 10:48:28 +0800
Subject: [PATCH 1576/4076] LoongArch: KVM: Add LSX (128bit SIMD) support

This patch adds LSX (128bit SIMD) support for LoongArch KVM.

There will be LSX exception in KVM when guest use the LSX instructions.
KVM will enable LSX and restore the vector registers for guest and then
return to guest to continue running.

Signed-off-by: Tianrui Zhao <zhaotianrui@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/kvm_host.h |  15 +-
 arch/loongarch/include/asm/kvm_vcpu.h |  10 ++
 arch/loongarch/include/uapi/asm/kvm.h |   1 +
 arch/loongarch/kernel/fpu.S           |   1 +
 arch/loongarch/kvm/exit.c             |  21 +++
 arch/loongarch/kvm/switch.S           |  16 ++
 arch/loongarch/kvm/trace.h            |   4 +-
 arch/loongarch/kvm/vcpu.c             | 220 +++++++++++++++++++++++++-
 8 files changed, 280 insertions(+), 8 deletions(-)

diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 0e89db020481c..b0c5cdd8014c2 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -95,8 +95,9 @@ enum emulation_result {
 };
 
 #define KVM_LARCH_FPU		(0x1 << 0)
-#define KVM_LARCH_SWCSR_LATEST	(0x1 << 1)
-#define KVM_LARCH_HWCSR_USABLE	(0x1 << 2)
+#define KVM_LARCH_LSX		(0x1 << 1)
+#define KVM_LARCH_SWCSR_LATEST	(0x1 << 2)
+#define KVM_LARCH_HWCSR_USABLE	(0x1 << 3)
 
 struct kvm_vcpu_arch {
 	/*
@@ -178,6 +179,16 @@ static inline void writel_sw_gcsr(struct loongarch_csrs *csr, int reg, unsigned
 	csr->csrs[reg] = val;
 }
 
+static inline bool kvm_guest_has_fpu(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_FP;
+}
+
+static inline bool kvm_guest_has_lsx(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_LSX;
+}
+
 /* Debug: dump vcpu state */
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
 
diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
index 0e87652f780a0..db08dd46b525a 100644
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -55,6 +55,16 @@ void kvm_save_fpu(struct loongarch_fpu *fpu);
 void kvm_restore_fpu(struct loongarch_fpu *fpu);
 void kvm_restore_fcsr(struct loongarch_fpu *fpu);
 
+#ifdef CONFIG_CPU_HAS_LSX
+int kvm_own_lsx(struct kvm_vcpu *vcpu);
+void kvm_save_lsx(struct loongarch_fpu *fpu);
+void kvm_restore_lsx(struct loongarch_fpu *fpu);
+#else
+static inline int kvm_own_lsx(struct kvm_vcpu *vcpu) { }
+static inline void kvm_save_lsx(struct loongarch_fpu *fpu) { }
+static inline void kvm_restore_lsx(struct loongarch_fpu *fpu) { }
+#endif
+
 void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
 void kvm_reset_timer(struct kvm_vcpu *vcpu);
 void kvm_save_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h
index c6ad2ee6106cb..923d0bd382941 100644
--- a/arch/loongarch/include/uapi/asm/kvm.h
+++ b/arch/loongarch/include/uapi/asm/kvm.h
@@ -79,6 +79,7 @@ struct kvm_fpu {
 #define LOONGARCH_REG_64(TYPE, REG)	(TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT))
 #define KVM_IOC_CSRID(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CSR, REG)
 #define KVM_IOC_CPUCFG(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG)
+#define KVM_LOONGARCH_VCPU_CPUCFG	0
 
 struct kvm_debug_exit_arch {
 };
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index d53ab10f46446..a400924c0348b 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -349,6 +349,7 @@ SYM_FUNC_START(_restore_lsx_upper)
 	lsx_restore_all_upper a0 t0 t1
 	jr	ra
 SYM_FUNC_END(_restore_lsx_upper)
+EXPORT_SYMBOL(_restore_lsx_upper)
 
 SYM_FUNC_START(_init_lsx_upper)
 	lsx_init_all_upper t1
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index e708a1786d6bd..676f7a3a335c2 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -634,6 +634,11 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 
+	if (!kvm_guest_has_fpu(&vcpu->arch)) {
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+		return RESUME_GUEST;
+	}
+
 	/*
 	 * If guest FPU not present, the FPU operation should have been
 	 * treated as a reserved instruction!
@@ -650,6 +655,21 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
+/*
+ * kvm_handle_lsx_disabled() - Guest used LSX while disabled in root.
+ * @vcpu:      Virtual CPU context.
+ *
+ * Handle when the guest attempts to use LSX when it is disabled in the root
+ * context.
+ */
+static int kvm_handle_lsx_disabled(struct kvm_vcpu *vcpu)
+{
+	if (kvm_own_lsx(vcpu))
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+
+	return RESUME_GUEST;
+}
+
 /*
  * LoongArch KVM callback handling for unimplemented guest exiting
  */
@@ -678,6 +698,7 @@ static exit_handle_fn kvm_fault_tables[EXCCODE_INT_START] = {
 	[EXCCODE_TLBS]			= kvm_handle_write_fault,
 	[EXCCODE_TLBM]			= kvm_handle_write_fault,
 	[EXCCODE_FPDIS]			= kvm_handle_fpu_disabled,
+	[EXCCODE_LSXDIS]		= kvm_handle_lsx_disabled,
 	[EXCCODE_GSPR]			= kvm_handle_gspr,
 };
 
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index 0ed9040307b71..00fbf772d16f9 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -245,6 +245,22 @@ SYM_FUNC_START(kvm_restore_fpu)
 	jr                 ra
 SYM_FUNC_END(kvm_restore_fpu)
 
+#ifdef CONFIG_CPU_HAS_LSX
+SYM_FUNC_START(kvm_save_lsx)
+	fpu_save_csr    a0 t1
+	fpu_save_cc     a0 t1 t2
+	lsx_save_data   a0 t1
+	jr              ra
+SYM_FUNC_END(kvm_save_lsx)
+
+SYM_FUNC_START(kvm_restore_lsx)
+	lsx_restore_data a0 t1
+	fpu_restore_cc   a0 t1 t2
+	fpu_restore_csr  a0 t1 t2
+	jr               ra
+SYM_FUNC_END(kvm_restore_lsx)
+#endif
+
 	.section ".rodata"
 SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry)
 SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest)
diff --git a/arch/loongarch/kvm/trace.h b/arch/loongarch/kvm/trace.h
index a1e35d6554185..7da4e230e896f 100644
--- a/arch/loongarch/kvm/trace.h
+++ b/arch/loongarch/kvm/trace.h
@@ -102,6 +102,7 @@ TRACE_EVENT(kvm_exit_gspr,
 #define KVM_TRACE_AUX_DISCARD		4
 
 #define KVM_TRACE_AUX_FPU		1
+#define KVM_TRACE_AUX_LSX		2
 
 #define kvm_trace_symbol_aux_op				\
 	{ KVM_TRACE_AUX_SAVE,		"save" },	\
@@ -111,7 +112,8 @@ TRACE_EVENT(kvm_exit_gspr,
 	{ KVM_TRACE_AUX_DISCARD,	"discard" }
 
 #define kvm_trace_symbol_aux_state			\
-	{ KVM_TRACE_AUX_FPU,     "FPU" }
+	{ KVM_TRACE_AUX_FPU,     "FPU" },		\
+	{ KVM_TRACE_AUX_LSX,     "LSX" }
 
 TRACE_EVENT(kvm_aux,
 	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int op,
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 53fcef8b24a10..80487d177ca4a 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -298,6 +298,69 @@ static int _kvm_setcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 val)
 	return ret;
 }
 
+static int _kvm_get_cpucfg(int id, u64 *v)
+{
+	int ret = 0;
+
+	if (id < 0 && id >= KVM_MAX_CPUCFG_REGS)
+		return -EINVAL;
+
+	switch (id) {
+	case 2:
+		/* Return CPUCFG2 features which have been supported by KVM */
+		*v = CPUCFG2_FP     | CPUCFG2_FPSP  | CPUCFG2_FPDP     |
+		     CPUCFG2_FPVERS | CPUCFG2_LLFTP | CPUCFG2_LLFTPREV |
+		     CPUCFG2_LAM;
+		/*
+		 * If LSX is supported by CPU, it is also supported by KVM,
+		 * as we implement it.
+		 */
+		if (cpu_has_lsx)
+			*v |= CPUCFG2_LSX;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static int kvm_check_cpucfg(int id, u64 val)
+{
+	u64 mask;
+	int ret = 0;
+
+	if (id < 0 && id >= KVM_MAX_CPUCFG_REGS)
+		return -EINVAL;
+
+	if (_kvm_get_cpucfg(id, &mask))
+		return ret;
+
+	switch (id) {
+	case 2:
+		/* CPUCFG2 features checking */
+		if (val & ~mask)
+			/* The unsupported features should not be set */
+			ret = -EINVAL;
+		else if (!(val & CPUCFG2_LLFTP))
+			/* The LLFTP must be set, as guest must has a constant timer */
+			ret = -EINVAL;
+		else if ((val & CPUCFG2_FP) && (!(val & CPUCFG2_FPSP) || !(val & CPUCFG2_FPDP)))
+			/* Single and double float point must both be set when enable FP */
+			ret = -EINVAL;
+		else if ((val & CPUCFG2_LSX) && !(val & CPUCFG2_FP))
+			/* FP should be set when enable LSX */
+			ret = -EINVAL;
+		else if ((val & CPUCFG2_LASX) && !(val & CPUCFG2_LSX))
+			/* LSX, FP should be set when enable LASX, and FP has been checked before. */
+			ret = -EINVAL;
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
 static int kvm_get_one_reg(struct kvm_vcpu *vcpu,
 		const struct kvm_one_reg *reg, u64 *v)
 {
@@ -367,10 +430,10 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
 		break;
 	case KVM_REG_LOONGARCH_CPUCFG:
 		id = KVM_GET_IOC_CPUCFG_IDX(reg->id);
-		if (id >= 0 && id < KVM_MAX_CPUCFG_REGS)
-			vcpu->arch.cpucfg[id] = (u32)v;
-		else
-			ret = -EINVAL;
+		ret = kvm_check_cpucfg(id, v);
+		if (ret)
+			break;
+		vcpu->arch.cpucfg[id] = (u32)v;
 		break;
 	case KVM_REG_LOONGARCH_KVM:
 		switch (reg->id) {
@@ -460,10 +523,94 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
+static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case 2:
+		return 0;
+	default:
+		return -ENXIO;
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_cpucfg_has_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	int ret = 0;
+	uint64_t val;
+	uint64_t __user *uaddr = (uint64_t __user *)attr->addr;
+
+	ret = _kvm_get_cpucfg(attr->attr, &val);
+	if (ret)
+		return ret;
+
+	put_user(val, uaddr);
+
+	return ret;
+}
+
+static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_get_cpucfg_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+
+static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_cpucfg_set_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
 	long r;
+	struct kvm_device_attr attr;
 	void __user *argp = (void __user *)arg;
 	struct kvm_vcpu *vcpu = filp->private_data;
 
@@ -503,6 +650,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
 		break;
 	}
+	case KVM_HAS_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_has_attr(vcpu, &attr);
+		break;
+	}
+	case KVM_GET_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_get_attr(vcpu, &attr);
+		break;
+	}
+	case KVM_SET_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_set_attr(vcpu, &attr);
+		break;
+	}
 	default:
 		r = -ENOIOCTLCMD;
 		break;
@@ -550,12 +718,54 @@ void kvm_own_fpu(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
+#ifdef CONFIG_CPU_HAS_LSX
+/* Enable LSX and restore context */
+int kvm_own_lsx(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_guest_has_fpu(&vcpu->arch) || !kvm_guest_has_lsx(&vcpu->arch))
+		return -EINVAL;
+
+	preempt_disable();
+
+	/* Enable LSX for guest */
+	set_csr_euen(CSR_EUEN_LSXEN | CSR_EUEN_FPEN);
+	switch (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
+	case KVM_LARCH_FPU:
+		/*
+		 * Guest FPU state already loaded,
+		 * only restore upper LSX state
+		 */
+		_restore_lsx_upper(&vcpu->arch.fpu);
+		break;
+	default:
+		/* Neither FP or LSX already active,
+		 * restore full LSX state
+		 */
+		kvm_restore_lsx(&vcpu->arch.fpu);
+		break;
+	}
+
+	trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_LSX);
+	vcpu->arch.aux_inuse |= KVM_LARCH_LSX | KVM_LARCH_FPU;
+	preempt_enable();
+
+	return 0;
+}
+#endif
+
 /* Save context and disable FPU */
 void kvm_lose_fpu(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
 
-	if (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
+	if (vcpu->arch.aux_inuse & KVM_LARCH_LSX) {
+		kvm_save_lsx(&vcpu->arch.fpu);
+		vcpu->arch.aux_inuse &= ~(KVM_LARCH_LSX | KVM_LARCH_FPU);
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_LSX);
+
+		/* Disable LSX & FPU */
+		clear_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN);
+	} else if (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
 		kvm_save_fpu(&vcpu->arch.fpu);
 		vcpu->arch.aux_inuse &= ~KVM_LARCH_FPU;
 		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_FPU);
-- 
GitLab


From 118e10cd893d57df55b3302dfd188a981b6e6d1c Mon Sep 17 00:00:00 2001
From: Tianrui Zhao <zhaotianrui@loongson.cn>
Date: Tue, 19 Dec 2023 10:48:28 +0800
Subject: [PATCH 1577/4076] LoongArch: KVM: Add LASX (256bit SIMD) support

This patch adds LASX (256bit SIMD) support for LoongArch KVM.

There will be LASX exception in KVM when guest use the LASX instructions.
KVM will enable LASX and restore the vector registers for guest and then
return to guest to continue running.

Reviewed-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Tianrui Zhao <zhaotianrui@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/kvm_host.h | 10 ++++--
 arch/loongarch/include/asm/kvm_vcpu.h | 10 ++++++
 arch/loongarch/kernel/fpu.S           |  1 +
 arch/loongarch/kvm/exit.c             | 16 +++++++++
 arch/loongarch/kvm/switch.S           | 15 ++++++++
 arch/loongarch/kvm/trace.h            |  4 ++-
 arch/loongarch/kvm/vcpu.c             | 51 ++++++++++++++++++++++++++-
 7 files changed, 103 insertions(+), 4 deletions(-)

diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index b0c5cdd8014c2..5bdb34b2c5d67 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -96,8 +96,9 @@ enum emulation_result {
 
 #define KVM_LARCH_FPU		(0x1 << 0)
 #define KVM_LARCH_LSX		(0x1 << 1)
-#define KVM_LARCH_SWCSR_LATEST	(0x1 << 2)
-#define KVM_LARCH_HWCSR_USABLE	(0x1 << 3)
+#define KVM_LARCH_LASX		(0x1 << 2)
+#define KVM_LARCH_SWCSR_LATEST	(0x1 << 3)
+#define KVM_LARCH_HWCSR_USABLE	(0x1 << 4)
 
 struct kvm_vcpu_arch {
 	/*
@@ -189,6 +190,11 @@ static inline bool kvm_guest_has_lsx(struct kvm_vcpu_arch *arch)
 	return arch->cpucfg[2] & CPUCFG2_LSX;
 }
 
+static inline bool kvm_guest_has_lasx(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_LASX;
+}
+
 /* Debug: dump vcpu state */
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
 
diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
index db08dd46b525a..e71ceb88f29ee 100644
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -65,6 +65,16 @@ static inline void kvm_save_lsx(struct loongarch_fpu *fpu) { }
 static inline void kvm_restore_lsx(struct loongarch_fpu *fpu) { }
 #endif
 
+#ifdef CONFIG_CPU_HAS_LASX
+int kvm_own_lasx(struct kvm_vcpu *vcpu);
+void kvm_save_lasx(struct loongarch_fpu *fpu);
+void kvm_restore_lasx(struct loongarch_fpu *fpu);
+#else
+static inline int kvm_own_lasx(struct kvm_vcpu *vcpu) { }
+static inline void kvm_save_lasx(struct loongarch_fpu *fpu) { }
+static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { }
+#endif
+
 void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
 void kvm_reset_timer(struct kvm_vcpu *vcpu);
 void kvm_save_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index a400924c0348b..4382e36ae3d44 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -385,6 +385,7 @@ SYM_FUNC_START(_restore_lasx_upper)
 	lasx_restore_all_upper a0 t0 t1
 	jr	ra
 SYM_FUNC_END(_restore_lasx_upper)
+EXPORT_SYMBOL(_restore_lasx_upper)
 
 SYM_FUNC_START(_init_lasx_upper)
 	lasx_init_all_upper t1
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index 676f7a3a335c2..ed1d89d53e2e6 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -670,6 +670,21 @@ static int kvm_handle_lsx_disabled(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
+/*
+ * kvm_handle_lasx_disabled() - Guest used LASX while disabled in root.
+ * @vcpu:	Virtual CPU context.
+ *
+ * Handle when the guest attempts to use LASX when it is disabled in the root
+ * context.
+ */
+static int kvm_handle_lasx_disabled(struct kvm_vcpu *vcpu)
+{
+	if (kvm_own_lasx(vcpu))
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+
+	return RESUME_GUEST;
+}
+
 /*
  * LoongArch KVM callback handling for unimplemented guest exiting
  */
@@ -699,6 +714,7 @@ static exit_handle_fn kvm_fault_tables[EXCCODE_INT_START] = {
 	[EXCCODE_TLBM]			= kvm_handle_write_fault,
 	[EXCCODE_FPDIS]			= kvm_handle_fpu_disabled,
 	[EXCCODE_LSXDIS]		= kvm_handle_lsx_disabled,
+	[EXCCODE_LASXDIS]		= kvm_handle_lasx_disabled,
 	[EXCCODE_GSPR]			= kvm_handle_gspr,
 };
 
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index 00fbf772d16f9..ba976509bfe81 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -261,6 +261,21 @@ SYM_FUNC_START(kvm_restore_lsx)
 SYM_FUNC_END(kvm_restore_lsx)
 #endif
 
+#ifdef CONFIG_CPU_HAS_LASX
+SYM_FUNC_START(kvm_save_lasx)
+	fpu_save_csr    a0 t1
+	fpu_save_cc     a0 t1 t2
+	lasx_save_data  a0 t1
+	jr              ra
+SYM_FUNC_END(kvm_save_lasx)
+
+SYM_FUNC_START(kvm_restore_lasx)
+	lasx_restore_data a0 t1
+	fpu_restore_cc    a0 t1 t2
+	fpu_restore_csr   a0 t1 t2
+	jr                ra
+SYM_FUNC_END(kvm_restore_lasx)
+#endif
 	.section ".rodata"
 SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry)
 SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest)
diff --git a/arch/loongarch/kvm/trace.h b/arch/loongarch/kvm/trace.h
index 7da4e230e896f..c2484ad4cffa2 100644
--- a/arch/loongarch/kvm/trace.h
+++ b/arch/loongarch/kvm/trace.h
@@ -103,6 +103,7 @@ TRACE_EVENT(kvm_exit_gspr,
 
 #define KVM_TRACE_AUX_FPU		1
 #define KVM_TRACE_AUX_LSX		2
+#define KVM_TRACE_AUX_LASX		3
 
 #define kvm_trace_symbol_aux_op				\
 	{ KVM_TRACE_AUX_SAVE,		"save" },	\
@@ -113,7 +114,8 @@ TRACE_EVENT(kvm_exit_gspr,
 
 #define kvm_trace_symbol_aux_state			\
 	{ KVM_TRACE_AUX_FPU,     "FPU" },		\
-	{ KVM_TRACE_AUX_LSX,     "LSX" }
+	{ KVM_TRACE_AUX_LSX,     "LSX" },		\
+	{ KVM_TRACE_AUX_LASX,    "LASX" }
 
 TRACE_EVENT(kvm_aux,
 	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int op,
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 80487d177ca4a..27701991886dd 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -317,6 +317,13 @@ static int _kvm_get_cpucfg(int id, u64 *v)
 		 */
 		if (cpu_has_lsx)
 			*v |= CPUCFG2_LSX;
+		/*
+		 * if LASX is supported by CPU, it is also supported by KVM,
+		 * as we implement it.
+		 */
+		if (cpu_has_lasx)
+			*v |= CPUCFG2_LASX;
+
 		break;
 	default:
 		ret = -EINVAL;
@@ -753,12 +760,54 @@ int kvm_own_lsx(struct kvm_vcpu *vcpu)
 }
 #endif
 
+#ifdef CONFIG_CPU_HAS_LASX
+/* Enable LASX and restore context */
+int kvm_own_lasx(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_guest_has_fpu(&vcpu->arch) || !kvm_guest_has_lsx(&vcpu->arch) || !kvm_guest_has_lasx(&vcpu->arch))
+		return -EINVAL;
+
+	preempt_disable();
+
+	set_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN | CSR_EUEN_LASXEN);
+	switch (vcpu->arch.aux_inuse & (KVM_LARCH_FPU | KVM_LARCH_LSX)) {
+	case KVM_LARCH_LSX:
+	case KVM_LARCH_LSX | KVM_LARCH_FPU:
+		/* Guest LSX state already loaded, only restore upper LASX state */
+		_restore_lasx_upper(&vcpu->arch.fpu);
+		break;
+	case KVM_LARCH_FPU:
+		/* Guest FP state already loaded, only restore upper LSX & LASX state */
+		_restore_lsx_upper(&vcpu->arch.fpu);
+		_restore_lasx_upper(&vcpu->arch.fpu);
+		break;
+	default:
+		/* Neither FP or LSX already active, restore full LASX state */
+		kvm_restore_lasx(&vcpu->arch.fpu);
+		break;
+	}
+
+	trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_LASX);
+	vcpu->arch.aux_inuse |= KVM_LARCH_LASX | KVM_LARCH_LSX | KVM_LARCH_FPU;
+	preempt_enable();
+
+	return 0;
+}
+#endif
+
 /* Save context and disable FPU */
 void kvm_lose_fpu(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
 
-	if (vcpu->arch.aux_inuse & KVM_LARCH_LSX) {
+	if (vcpu->arch.aux_inuse & KVM_LARCH_LASX) {
+		kvm_save_lasx(&vcpu->arch.fpu);
+		vcpu->arch.aux_inuse &= ~(KVM_LARCH_LSX | KVM_LARCH_FPU | KVM_LARCH_LASX);
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_LASX);
+
+		/* Disable LASX & LSX & FPU */
+		clear_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN | CSR_EUEN_LASXEN);
+	} else if (vcpu->arch.aux_inuse & KVM_LARCH_LSX) {
 		kvm_save_lsx(&vcpu->arch.fpu);
 		vcpu->arch.aux_inuse &= ~(KVM_LARCH_LSX | KVM_LARCH_FPU);
 		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_LSX);
-- 
GitLab


From d23569979ca1cd139a42c410e0c7b9e6014c3b3a Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 13 Dec 2023 09:37:01 -0500
Subject: [PATCH 1578/4076] tracing: Allow creating instances with specified
 system events

A trace instance may only need to enable specific events. As the eventfs
directory of an instance currently creates all events which adds overhead,
allow internal instances to be created with just the events in systems
that they care about. This currently only deals with systems and not
individual events, but this should bring down the overhead of creating
instances for specific use cases quite bit.

The trace_array_get_by_name() now has another parameter "systems". This
parameter is a const string pointer of a comma/space separated list of
event systems that should be created by the trace_array. (Note if the
trace_array already exists, this parameter is ignored).

The list of systems is saved and if a module is loaded, its events will
not be added unless the system for those events also match the systems
string.

Link: https://lore.kernel.org/linux-trace-kernel/20231213093701.03fddec0@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Arun Easi   <aeasi@marvell.com>
Cc: Daniel Wagner <dwagner@suse.de>
Tested-by: Dmytro Maluka <dmaluka@chromium.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 drivers/scsi/qla2xxx/qla_os.c       |  2 +-
 include/linux/trace.h               |  4 +--
 kernel/trace/trace.c                | 23 +++++++++++---
 kernel/trace/trace.h                |  1 +
 kernel/trace/trace_boot.c           |  2 +-
 kernel/trace/trace_events.c         | 48 +++++++++++++++++++++++++++--
 samples/ftrace/sample-trace-array.c |  2 +-
 7 files changed, 70 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 03348f605c2e9..dd674378f2f39 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2889,7 +2889,7 @@ static void qla2x00_iocb_work_fn(struct work_struct *work)
 static void
 qla_trace_init(void)
 {
-	qla_trc_array = trace_array_get_by_name("qla2xxx");
+	qla_trc_array = trace_array_get_by_name("qla2xxx", NULL);
 	if (!qla_trc_array) {
 		ql_log(ql_log_fatal, NULL, 0x0001,
 		       "Unable to create qla2xxx trace instance, instance logging will be disabled.\n");
diff --git a/include/linux/trace.h b/include/linux/trace.h
index 2a70a447184c9..fdcd76b7be83d 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -51,7 +51,7 @@ int trace_array_printk(struct trace_array *tr, unsigned long ip,
 		       const char *fmt, ...);
 int trace_array_init_printk(struct trace_array *tr);
 void trace_array_put(struct trace_array *tr);
-struct trace_array *trace_array_get_by_name(const char *name);
+struct trace_array *trace_array_get_by_name(const char *name, const char *systems);
 int trace_array_destroy(struct trace_array *tr);
 
 /* For osnoise tracer */
@@ -84,7 +84,7 @@ static inline int trace_array_init_printk(struct trace_array *tr)
 static inline void trace_array_put(struct trace_array *tr)
 {
 }
-static inline struct trace_array *trace_array_get_by_name(const char *name)
+static inline struct trace_array *trace_array_get_by_name(const char *name, const char *systems)
 {
 	return NULL;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 199df497db07e..59e39b652afb5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9490,7 +9490,8 @@ static int trace_array_create_dir(struct trace_array *tr)
 	return ret;
 }
 
-static struct trace_array *trace_array_create(const char *name)
+static struct trace_array *
+trace_array_create_systems(const char *name, const char *systems)
 {
 	struct trace_array *tr;
 	int ret;
@@ -9510,6 +9511,12 @@ static struct trace_array *trace_array_create(const char *name)
 	if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
 		goto out_free_tr;
 
+	if (systems) {
+		tr->system_names = kstrdup_const(systems, GFP_KERNEL);
+		if (!tr->system_names)
+			goto out_free_tr;
+	}
+
 	tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
 
 	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
@@ -9556,12 +9563,18 @@ static struct trace_array *trace_array_create(const char *name)
 	free_trace_buffers(tr);
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
+	kfree_const(tr->system_names);
 	kfree(tr->name);
 	kfree(tr);
 
 	return ERR_PTR(ret);
 }
 
+static struct trace_array *trace_array_create(const char *name)
+{
+	return trace_array_create_systems(name, NULL);
+}
+
 static int instance_mkdir(const char *name)
 {
 	struct trace_array *tr;
@@ -9587,6 +9600,7 @@ out_unlock:
 /**
  * trace_array_get_by_name - Create/Lookup a trace array, given its name.
  * @name: The name of the trace array to be looked up/created.
+ * @systems: A list of systems to create event directories for (NULL for all)
  *
  * Returns pointer to trace array with given name.
  * NULL, if it cannot be created.
@@ -9600,7 +9614,7 @@ out_unlock:
  * trace_array_put() is called, user space can not delete it.
  *
  */
-struct trace_array *trace_array_get_by_name(const char *name)
+struct trace_array *trace_array_get_by_name(const char *name, const char *systems)
 {
 	struct trace_array *tr;
 
@@ -9612,7 +9626,7 @@ struct trace_array *trace_array_get_by_name(const char *name)
 			goto out_unlock;
 	}
 
-	tr = trace_array_create(name);
+	tr = trace_array_create_systems(name, systems);
 
 	if (IS_ERR(tr))
 		tr = NULL;
@@ -9659,6 +9673,7 @@ static int __remove_instance(struct trace_array *tr)
 
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
+	kfree_const(tr->system_names);
 	kfree(tr->name);
 	kfree(tr);
 
@@ -10377,7 +10392,7 @@ __init static void enable_instances(void)
 		if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE))
 			do_allocate_snapshot(tok);
 
-		tr = trace_array_get_by_name(tok);
+		tr = trace_array_get_by_name(tok, NULL);
 		if (!tr) {
 			pr_warn("Failed to create instance buffer %s\n", curr_str);
 			continue;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0489e72c8169c..79180aed13eee 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -377,6 +377,7 @@ struct trace_array {
 	unsigned char		trace_flags_index[TRACE_FLAGS_MAX_SIZE];
 	unsigned int		flags;
 	raw_spinlock_t		start_lock;
+	const char		*system_names;
 	struct list_head	err_log;
 	struct dentry		*dir;
 	struct dentry		*options;
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 7ccc7a8e155b9..dbe29b4c6a7a0 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -633,7 +633,7 @@ trace_boot_init_instances(struct xbc_node *node)
 		if (!p || *p == '\0')
 			continue;
 
-		tr = trace_array_get_by_name(p);
+		tr = trace_array_get_by_name(p, NULL);
 		if (!tr) {
 			pr_err("Failed to get trace instance %s\n", p);
 			continue;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f29e815ca5b2e..b70d038180384 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2896,6 +2896,27 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 	up_write(&trace_event_sem);
 }
 
+static bool event_in_systems(struct trace_event_call *call,
+			     const char *systems)
+{
+	const char *system;
+	const char *p;
+
+	if (!systems)
+		return true;
+
+	system = call->class->system;
+	p = strstr(systems, system);
+	if (!p)
+		return false;
+
+	if (p != systems && !isspace(*(p - 1)) && *(p - 1) != ',')
+		return false;
+
+	p += strlen(system);
+	return !*p || isspace(*p) || *p == ',';
+}
+
 static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
@@ -2905,9 +2926,12 @@ trace_create_new_event(struct trace_event_call *call,
 	struct trace_event_file *file;
 	unsigned int first;
 
+	if (!event_in_systems(call, tr->system_names))
+		return NULL;
+
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	pid_list = rcu_dereference_protected(tr->filtered_pids,
 					     lockdep_is_held(&event_mutex));
@@ -2972,8 +2996,17 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
 	struct trace_event_file *file;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	if (eventdir_initialized)
 		return event_create_dir(tr->event_dir, file);
@@ -3012,8 +3045,17 @@ __trace_early_add_new_event(struct trace_event_call *call,
 	int ret;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	ret = event_define_fields(call);
 	if (ret)
diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c
index 6aba02a31c96c..d0ee9001c7b37 100644
--- a/samples/ftrace/sample-trace-array.c
+++ b/samples/ftrace/sample-trace-array.c
@@ -105,7 +105,7 @@ static int __init sample_trace_array_init(void)
 	 * NOTE: This function increments the reference counter
 	 * associated with the trace array - "tr".
 	 */
-	tr = trace_array_get_by_name("sample-instance");
+	tr = trace_array_get_by_name("sample-instance", "sched,timer,kprobes");
 
 	if (!tr)
 		return -1;
-- 
GitLab


From 0b9036efd83d4adefab197a1ec98c496c9df44f0 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Mon, 11 Dec 2023 13:16:23 -0500
Subject: [PATCH 1579/4076] ring-buffer: Add offset of events in dump on
 mismatch

On bugs that have the ring buffer timestamp get out of sync, the config
CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS, that checks for it and if it is
detected it causes a dump of the bad sub buffer.

It shows each event and their timestamp as well as the delta in the event.
But it's also good to see the offset into the subbuffer for that event to
know if how close to the end it is.

Also print where the last event actually ended compared to where it was
expected to end.

Link: https://lore.kernel.org/linux-trace-kernel/20231211131623.59eaebd2@gandalf.local.home

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 83eab547f1d1f..bfe2697a92ee4 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3358,29 +3358,34 @@ static void dump_buffer_page(struct buffer_data_page *bpage,
 		case RINGBUF_TYPE_TIME_EXTEND:
 			delta = rb_event_time_stamp(event);
 			ts += delta;
-			pr_warn("  [%lld] delta:%lld TIME EXTEND\n", ts, delta);
+			pr_warn(" 0x%x: [%lld] delta:%lld TIME EXTEND\n",
+				e, ts, delta);
 			break;
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
 			ts = rb_fix_abs_ts(delta, ts);
-			pr_warn("  [%lld] absolute:%lld TIME STAMP\n", ts, delta);
+			pr_warn(" 0x%x:  [%lld] absolute:%lld TIME STAMP\n",
+				e, ts, delta);
 			break;
 
 		case RINGBUF_TYPE_PADDING:
 			ts += event->time_delta;
-			pr_warn("  [%lld] delta:%d PADDING\n", ts, event->time_delta);
+			pr_warn(" 0x%x:  [%lld] delta:%d PADDING\n",
+				e, ts, event->time_delta);
 			break;
 
 		case RINGBUF_TYPE_DATA:
 			ts += event->time_delta;
-			pr_warn("  [%lld] delta:%d\n", ts, event->time_delta);
+			pr_warn(" 0x%x:  [%lld] delta:%d\n",
+				e, ts, event->time_delta);
 			break;
 
 		default:
 			break;
 		}
 	}
+	pr_warn("expected end:0x%lx last event actually ended at:0x%x\n", tail, e);
 }
 
 static DEFINE_PER_CPU(atomic_t, checking);
-- 
GitLab


From 8ec90be7f15fac42992ea821be929d3b06cd0fd9 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 12 Dec 2023 13:19:01 -0500
Subject: [PATCH 1580/4076] tracing: Allow for max buffer data size
 trace_marker writes

Allow a trace write to be as big as the ring buffer tracing data will
allow. Currently, it only allows writes of 1KB in size, but there's no
reason that it cannot allow what the ring buffer can hold.

Link: https://lore.kernel.org/linux-trace-kernel/20231212131901.5f501e72@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  1 +
 kernel/trace/ring_buffer.c  | 15 +++++++++++++++
 kernel/trace/trace.c        | 31 ++++++++++++++++++++++++-------
 3 files changed, 40 insertions(+), 7 deletions(-)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 782e14f62201f..b1b03b2c0f08e 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -141,6 +141,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
 bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter);
 
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu);
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer);
 
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu);
 void ring_buffer_reset_online_cpus(struct trace_buffer *buffer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bfe2697a92ee4..16b640d824f92 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5190,6 +5190,21 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
+/**
+ * ring_buffer_max_event_size - return the max data size of an event
+ * @buffer: The ring buffer.
+ *
+ * Returns the maximum size an event can be.
+ */
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer)
+{
+	/* If abs timestamp is requested, events have a timestamp too */
+	if (ring_buffer_time_stamp_abs(buffer))
+		return BUF_MAX_DATA_SIZE - RB_LEN_TIME_EXTEND;
+	return BUF_MAX_DATA_SIZE;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_max_event_size);
+
 static void rb_clear_buffer_page(struct buffer_page *page)
 {
 	local_set(&page->write, 0);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 59e39b652afb5..dba1328e454b3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7278,8 +7278,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	enum event_trigger_type tt = ETT_NONE;
 	struct trace_buffer *buffer;
 	struct print_entry *entry;
+	int meta_size;
 	ssize_t written;
-	int size;
+	size_t size;
 	int len;
 
 /* Used in tracing_mark_raw_write() as well */
@@ -7292,12 +7293,12 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
 		return -EINVAL;
 
-	if (cnt > TRACE_BUF_SIZE)
-		cnt = TRACE_BUF_SIZE;
-
-	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
+	if ((ssize_t)cnt < 0)
+		return -EINVAL;
 
-	size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */
+	meta_size = sizeof(*entry) + 2;  /* add '\0' and possible '\n' */
+ again:
+	size = cnt + meta_size;
 
 	/* If less than "<faulted>", then make sure we can still add that */
 	if (cnt < FAULTED_SIZE)
@@ -7306,9 +7307,25 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	buffer = tr->array_buffer.buffer;
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					    tracing_gen_ctx());
-	if (unlikely(!event))
+	if (unlikely(!event)) {
+		/*
+		 * If the size was greater than what was allowed, then
+		 * make it smaller and try again.
+		 */
+		if (size > ring_buffer_max_event_size(buffer)) {
+			/* cnt < FAULTED size should never be bigger than max */
+			if (WARN_ON_ONCE(cnt < FAULTED_SIZE))
+				return -EBADF;
+			cnt = ring_buffer_max_event_size(buffer) - meta_size;
+			/* The above should only happen once */
+			if (WARN_ON_ONCE(cnt + meta_size == size))
+				return -EBADF;
+			goto again;
+		}
+
 		/* Ring buffer disabled, return as if not open for write */
 		return -EBADF;
+	}
 
 	entry = ring_buffer_event_data(event);
 	entry->ip = _THIS_IP_;
-- 
GitLab


From 40fc60e36c60ba85b2974e507b67df40c94e9578 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Sat, 9 Dec 2023 17:52:20 -0500
Subject: [PATCH 1581/4076] trace_seq: Increase the buffer size to almost two
 pages

Now that trace_marker can hold more than 1KB string, and can write as much
as the ring buffer can hold, the trace_seq is not big enough to hold
writes:

 ~# a="1234567890"
 ~# cnt=4080
 ~# s=""
 ~# while [ $cnt -gt 10 ]; do
 ~#	s="${s}${a}"
 ~#	cnt=$((cnt-10))
 ~# done
 ~# echo $s > trace_marker
 ~# cat trace
 # tracer: nop
 #
 # entries-in-buffer/entries-written: 2/2   #P:8
 #
 #                                _-----=> irqs-off/BH-disabled
 #                               / _----=> need-resched
 #                              | / _---=> hardirq/softirq
 #                              || / _--=> preempt-depth
 #                              ||| / _-=> migrate-disable
 #                              |||| /     delay
 #           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
 #              | |         |   |||||     |         |
            <...>-860     [002] .....   105.543465: tracing_mark_write[LINE TOO BIG]
            <...>-860     [002] .....   105.543496: tracing_mark_write: 789012345678901234567890

By increasing the trace_seq buffer to almost two pages, it can now print
out the first line.

This also subtracts the rest of the trace_seq fields from the buffer, so
that the entire trace_seq is now PAGE_SIZE aligned.

Link: https://lore.kernel.org/linux-trace-kernel/20231209175220.19867af4@gandalf.local.home

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/trace_seq.h | 9 ++++++---
 kernel/trace/trace.c      | 6 +++---
 kernel/trace/trace_seq.c  | 3 ---
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 3691e0e76a1a2..9ec229dfddaa7 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -8,11 +8,14 @@
 
 /*
  * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
+ * to create a string of data to use.
  */
 
+#define TRACE_SEQ_BUFFER_SIZE	(PAGE_SIZE * 2 - \
+	(sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int)))
+
 struct trace_seq {
-	char			buffer[PAGE_SIZE];
+	char			buffer[TRACE_SEQ_BUFFER_SIZE];
 	struct seq_buf		seq;
 	size_t			readpos;
 	int			full;
@@ -21,7 +24,7 @@ struct trace_seq {
 static inline void
 trace_seq_init(struct trace_seq *s)
 {
-	seq_buf_init(&s->seq, s->buffer, PAGE_SIZE);
+	seq_buf_init(&s->seq, s->buffer, TRACE_SEQ_BUFFER_SIZE);
 	s->full = 0;
 	s->readpos = 0;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dba1328e454b3..0be30cccabb4b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3753,7 +3753,7 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
 
 	/* OK if part of the temp seq buffer */
 	if ((addr >= (unsigned long)iter->tmp_seq.buffer) &&
-	    (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE))
+	    (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE))
 		return true;
 
 	/* Core rodata can not be freed */
@@ -6932,8 +6932,8 @@ waitagain:
 		goto out;
 	}
 
-	if (cnt >= PAGE_SIZE)
-		cnt = PAGE_SIZE - 1;
+	if (cnt >= TRACE_SEQ_BUFFER_SIZE)
+		cnt = TRACE_SEQ_BUFFER_SIZE - 1;
 
 	/* reset all but tr, trace, and overruns */
 	trace_iterator_reset(iter);
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 7be97229ddf86..c158d65a8a886 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -13,9 +13,6 @@
  * trace_seq_init() more than once to reset the trace_seq to start
  * from scratch.
  * 
- * The buffer size is currently PAGE_SIZE, although it may become dynamic
- * in the future.
- *
  * A write to the buffer will either succeed or fail. That is, unlike
  * sprintf() there will not be a partial write (well it may write into
  * the buffer but it wont update the pointers). This allows users to
-- 
GitLab


From 9482341d9bdaf194552673b6c1c81a824e985e7f Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 12 Dec 2023 19:04:22 -0500
Subject: [PATCH 1582/4076] tracing: Have trace_marker break up by lines by
 size of trace_seq

If a trace_marker write is bigger than what trace_seq can hold, then it
will print "LINE TOO BIG" message and not what was written.

Instead, check if the write is bigger than the trace_seq and break it
up by that size.

Ideally, we could make the trace_seq dynamic that could hold this. But
that's for another time.

Link: https://lore.kernel.org/linux-trace-kernel/20231212190422.1eaf224f@gandalf.local.home

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0be30cccabb4b..9cf58383d2fb3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7304,6 +7304,11 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (cnt < FAULTED_SIZE)
 		size += FAULTED_SIZE - cnt;
 
+	if (size > TRACE_SEQ_BUFFER_SIZE) {
+		cnt -= size - TRACE_SEQ_BUFFER_SIZE;
+		goto again;
+	}
+
 	buffer = tr->array_buffer.buffer;
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					    tracing_gen_ctx());
-- 
GitLab


From 76ca20c748684f63bb985166850049f242797f65 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 13 Dec 2023 10:42:18 -0500
Subject: [PATCH 1583/4076] tracing: Increase size of trace_marker_raw to max
 ring buffer entry

There's no reason to give an arbitrary limit to the size of a raw trace
marker. Just let it be as big as the size that is allowed by the ring
buffer itself.

And there's also no reason to artificially break up the write to
TRACE_BUF_SIZE, as that's not even used.

Link: https://lore.kernel.org/linux-trace-kernel/20231213104218.2efc70c1@gandalf.local.home

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9cf58383d2fb3..55dabee4c78b1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7365,9 +7365,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	return written;
 }
 
-/* Limit it for now to 3K (including tag) */
-#define RAW_DATA_MAX_SIZE (1024*3)
-
 static ssize_t
 tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
@@ -7389,19 +7386,18 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 		return -EINVAL;
 
 	/* The marker must at least have a tag id */
-	if (cnt < sizeof(unsigned int) || cnt > RAW_DATA_MAX_SIZE)
+	if (cnt < sizeof(unsigned int))
 		return -EINVAL;
 
-	if (cnt > TRACE_BUF_SIZE)
-		cnt = TRACE_BUF_SIZE;
-
-	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
-
 	size = sizeof(*entry) + cnt;
 	if (cnt < FAULT_SIZE_ID)
 		size += FAULT_SIZE_ID - cnt;
 
 	buffer = tr->array_buffer.buffer;
+
+	if (size > ring_buffer_max_event_size(buffer))
+		return -EINVAL;
+
 	event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size,
 					    tracing_gen_ctx());
 	if (!event)
-- 
GitLab


From c5d973a07bb141fe1baa558dcf7cac855b030405 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:57 +0900
Subject: [PATCH 1584/4076] PCI: dra7xx: Rename dra7xx_pcie_raise_legacy_irq()

Rename the function dra7xx_pcie_raise_legacy_irq() to
dra7xx_pcie_raise_intx_irq() to match the use of the PCI_IRQ_INTX macro.

Link: https://lore.kernel.org/r/20231122060406.14695-8-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/dwc/pci-dra7xx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index f257a42f33146..caeae5c9ca2a7 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -386,7 +386,7 @@ static void dra7xx_pcie_ep_init(struct dw_pcie_ep *ep)
 	dra7xx_pcie_enable_wrapper_interrupts(dra7xx);
 }
 
-static void dra7xx_pcie_raise_legacy_irq(struct dra7xx_pcie *dra7xx)
+static void dra7xx_pcie_raise_intx_irq(struct dra7xx_pcie *dra7xx)
 {
 	dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_INTX_ASSERT, 0x1);
 	mdelay(1);
@@ -411,7 +411,7 @@ static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		dra7xx_pcie_raise_legacy_irq(dra7xx);
+		dra7xx_pcie_raise_intx_irq(dra7xx);
 		break;
 	case PCI_IRQ_MSI:
 		dra7xx_pcie_raise_msi_irq(dra7xx, interrupt_num);
-- 
GitLab


From 570e8579761a68d80c29034c291b34cff732d76d Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:58 +0900
Subject: [PATCH 1585/4076] PCI: cadence: Use INTX instead of legacy

In the Cadence endpoint controller driver, rename the function
cdns_pcie_ep_send_legacy_irq() to cdns_pcie_ep_send_intx_irq() to match
the macro PCI_IRQ_INTX name. Related comments and messages mentioning
"legacy" are also changed to refer to "intx".

Link: https://lore.kernel.org/r/20231122060406.14695-9-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/cadence/pcie-cadence-ep.c | 10 +++++-----
 drivers/pci/controller/cadence/pcie-cadence.h    | 12 ++++++------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index 3d71d687ea649..2d0a8d78bffb5 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -360,8 +360,8 @@ static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, u8 intx,
 	writel(0, ep->irq_cpu_addr + offset);
 }
 
-static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
-					u8 intx)
+static int cdns_pcie_ep_send_intx_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
+				      u8 intx)
 {
 	u16 cmd;
 
@@ -371,7 +371,7 @@ static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
 
 	cdns_pcie_ep_assert_intx(ep, fn, intx, true);
 	/*
-	 * The mdelay() value was taken from dra7xx_pcie_raise_legacy_irq()
+	 * The mdelay() value was taken from dra7xx_pcie_raise_intx_irq()
 	 */
 	mdelay(1);
 	cdns_pcie_ep_assert_intx(ep, fn, intx, false);
@@ -541,10 +541,10 @@ static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
 	switch (type) {
 	case PCI_IRQ_INTX:
 		if (vfn > 0) {
-			dev_err(dev, "Cannot raise legacy interrupts for VF\n");
+			dev_err(dev, "Cannot raise INTX interrupts for VF\n");
 			return -EINVAL;
 		}
-		return cdns_pcie_ep_send_legacy_irq(ep, fn, vfn, 0);
+		return cdns_pcie_ep_send_intx_irq(ep, fn, vfn, 0);
 
 	case PCI_IRQ_MSI:
 		return cdns_pcie_ep_send_msi_irq(ep, fn, vfn, interrupt_num);
diff --git a/drivers/pci/controller/cadence/pcie-cadence.h b/drivers/pci/controller/cadence/pcie-cadence.h
index 373cb50fcd159..03b96798f858c 100644
--- a/drivers/pci/controller/cadence/pcie-cadence.h
+++ b/drivers/pci/controller/cadence/pcie-cadence.h
@@ -347,16 +347,16 @@ struct cdns_pcie_epf {
  * @max_regions: maximum number of regions supported by hardware
  * @ob_region_map: bitmask of mapped outbound regions
  * @ob_addr: base addresses in the AXI bus where the outbound regions start
- * @irq_phys_addr: base address on the AXI bus where the MSI/legacy IRQ
+ * @irq_phys_addr: base address on the AXI bus where the MSI/INTX IRQ
  *		   dedicated outbound regions is mapped.
  * @irq_cpu_addr: base address in the CPU space where a write access triggers
- *		  the sending of a memory write (MSI) / normal message (legacy
+ *		  the sending of a memory write (MSI) / normal message (INTX
  *		  IRQ) TLP through the PCIe bus.
- * @irq_pci_addr: used to save the current mapping of the MSI/legacy IRQ
+ * @irq_pci_addr: used to save the current mapping of the MSI/INTX IRQ
  *		  dedicated outbound region.
  * @irq_pci_fn: the latest PCI function that has updated the mapping of
- *		the MSI/legacy IRQ dedicated outbound region.
- * @irq_pending: bitmask of asserted legacy IRQs.
+ *		the MSI/INTX IRQ dedicated outbound region.
+ * @irq_pending: bitmask of asserted INTX IRQs.
  * @lock: spin lock to disable interrupts while modifying PCIe controller
  *        registers fields (RMW) accessible by both remote RC and EP to
  *        minimize time between read and write
@@ -374,7 +374,7 @@ struct cdns_pcie_ep {
 	u64			irq_pci_addr;
 	u8			irq_pci_fn;
 	u8			irq_pending;
-	/* protect writing to PCI_STATUS while raising legacy interrupts */
+	/* protect writing to PCI_STATUS while raising INTX interrupts */
 	spinlock_t		lock;
 	struct cdns_pcie_epf	*epf;
 	unsigned int		quirk_detect_quiet_flag:1;
-- 
GitLab


From e9af4800d448c8e0ebfe3a1c7a29836b729d969d Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:59 +0900
Subject: [PATCH 1586/4076] PCI: dwc: Rename dw_pcie_ep_raise_legacy_irq()

Rename the function dw_pcie_ep_raise_legacy_irq() of the Designware
endpoint controller driver to dw_pcie_ep_raise_intx_irq() to match the
name of the PCI_IRQ_INTX macro.

Link: https://lore.kernel.org/r/20231122060406.14695-10-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/dwc/pci-imx6.c             | 2 +-
 drivers/pci/controller/dwc/pci-layerscape-ep.c    | 2 +-
 drivers/pci/controller/dwc/pcie-designware-ep.c   | 6 +++---
 drivers/pci/controller/dwc/pcie-designware-plat.c | 2 +-
 drivers/pci/controller/dwc/pcie-designware.h      | 4 ++--
 drivers/pci/controller/dwc/pcie-qcom-ep.c         | 2 +-
 drivers/pci/controller/dwc/pcie-rcar-gen4.c       | 2 +-
 7 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index a5365ab8897e3..f117ec286a76d 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -1064,7 +1064,7 @@ static int imx6_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
 	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	case PCI_IRQ_MSIX:
diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 5f78a94152863..9e7beb3ba09bc 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -172,7 +172,7 @@ static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
 	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	case PCI_IRQ_MSIX:
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 87759c899fab2..d8850b59094b6 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -496,16 +496,16 @@ static const struct pci_epc_ops epc_ops = {
 	.get_features		= dw_pcie_ep_get_features,
 };
 
-int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
+int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct device *dev = pci->dev;
 
-	dev_err(dev, "EP cannot trigger legacy IRQs\n");
+	dev_err(dev, "EP cannot raise INTX IRQs\n");
 
 	return -EINVAL;
 }
-EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_legacy_irq);
+EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_intx_irq);
 
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num)
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index c83968aa0149d..27047e4c402ab 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -48,7 +48,7 @@ static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
 	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	case PCI_IRQ_MSIX:
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index ffb9a62f3179e..d55b28f3f156a 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -580,7 +580,7 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep);
 int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep);
 void dw_pcie_ep_init_notify(struct dw_pcie_ep *ep);
 void dw_pcie_ep_exit(struct dw_pcie_ep *ep);
-int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no);
+int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no);
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num);
 int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
@@ -613,7 +613,7 @@ static inline void dw_pcie_ep_exit(struct dw_pcie_ep *ep)
 {
 }
 
-static inline int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
+static inline int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no)
 {
 	return 0;
 }
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 2e5ab5fef3103..71860e59cfced 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -732,7 +732,7 @@ static int qcom_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
 	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 25354a82674d2..6be20359d9fe9 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -368,7 +368,7 @@ static int rcar_gen4_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
+		return dw_pcie_ep_raise_intx_irq(ep, func_no);
 	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
-- 
GitLab


From 81957ace190f979c5e9ce6a30deca6639f959350 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:04:00 +0900
Subject: [PATCH 1587/4076] PCI: keystone: Use INTX instead of legacy

In the Keystone controller driver, change all names using "legacy" to
use "intx" instead, to match the term used in the PCI specifications.
Given that the field legacy_intc_np of struct keystone_pcie is unused,
this field is removed instead of being renamed.

Link: https://lore.kernel.org/r/20231122060406.14695-11-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/dwc/pci-keystone.c | 77 +++++++++++------------
 1 file changed, 37 insertions(+), 40 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 84f6a4acee07a..9186da7a16209 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -115,8 +115,7 @@ struct keystone_pcie {
 	struct dw_pcie		*pci;
 	/* PCI Device ID */
 	u32			device_id;
-	int			legacy_host_irqs[PCI_NUM_INTX];
-	struct			device_node *legacy_intc_np;
+	int			intx_host_irqs[PCI_NUM_INTX];
 
 	int			msi_host_irq;
 	int			num_lanes;
@@ -124,7 +123,7 @@ struct keystone_pcie {
 	struct phy		**phy;
 	struct device_link	**link;
 	struct			device_node *msi_intc_np;
-	struct irq_domain	*legacy_irq_domain;
+	struct irq_domain	*intx_irq_domain;
 	struct device_node	*np;
 
 	/* Application register space */
@@ -252,8 +251,8 @@ static int ks_pcie_msi_host_init(struct dw_pcie_rp *pp)
 	return dw_pcie_allocate_domains(pp);
 }
 
-static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie,
-				      int offset)
+static void ks_pcie_handle_intx_irq(struct keystone_pcie *ks_pcie,
+				    int offset)
 {
 	struct dw_pcie *pci = ks_pcie->pci;
 	struct device *dev = pci->dev;
@@ -263,7 +262,7 @@ static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie,
 
 	if (BIT(0) & pending) {
 		dev_dbg(dev, ": irq: irq_offset %d", offset);
-		generic_handle_domain_irq(ks_pcie->legacy_irq_domain, offset);
+		generic_handle_domain_irq(ks_pcie->intx_irq_domain, offset);
 	}
 
 	/* EOI the INTx interrupt */
@@ -307,38 +306,37 @@ static irqreturn_t ks_pcie_handle_error_irq(struct keystone_pcie *ks_pcie)
 	return IRQ_HANDLED;
 }
 
-static void ks_pcie_ack_legacy_irq(struct irq_data *d)
+static void ks_pcie_ack_intx_irq(struct irq_data *d)
 {
 }
 
-static void ks_pcie_mask_legacy_irq(struct irq_data *d)
+static void ks_pcie_mask_intx_irq(struct irq_data *d)
 {
 }
 
-static void ks_pcie_unmask_legacy_irq(struct irq_data *d)
+static void ks_pcie_unmask_intx_irq(struct irq_data *d)
 {
 }
 
-static struct irq_chip ks_pcie_legacy_irq_chip = {
-	.name = "Keystone-PCI-Legacy-IRQ",
-	.irq_ack = ks_pcie_ack_legacy_irq,
-	.irq_mask = ks_pcie_mask_legacy_irq,
-	.irq_unmask = ks_pcie_unmask_legacy_irq,
+static struct irq_chip ks_pcie_intx_irq_chip = {
+	.name = "Keystone-PCI-INTX-IRQ",
+	.irq_ack = ks_pcie_ack_intx_irq,
+	.irq_mask = ks_pcie_mask_intx_irq,
+	.irq_unmask = ks_pcie_unmask_intx_irq,
 };
 
-static int ks_pcie_init_legacy_irq_map(struct irq_domain *d,
-				       unsigned int irq,
-				       irq_hw_number_t hw_irq)
+static int ks_pcie_init_intx_irq_map(struct irq_domain *d,
+				     unsigned int irq, irq_hw_number_t hw_irq)
 {
-	irq_set_chip_and_handler(irq, &ks_pcie_legacy_irq_chip,
+	irq_set_chip_and_handler(irq, &ks_pcie_intx_irq_chip,
 				 handle_level_irq);
 	irq_set_chip_data(irq, d->host_data);
 
 	return 0;
 }
 
-static const struct irq_domain_ops ks_pcie_legacy_irq_domain_ops = {
-	.map = ks_pcie_init_legacy_irq_map,
+static const struct irq_domain_ops ks_pcie_intx_irq_domain_ops = {
+	.map = ks_pcie_init_intx_irq_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
 
@@ -605,22 +603,22 @@ static void ks_pcie_msi_irq_handler(struct irq_desc *desc)
 }
 
 /**
- * ks_pcie_legacy_irq_handler() - Handle legacy interrupt
+ * ks_pcie_intx_irq_handler() - Handle INTX interrupt
  * @desc: Pointer to irq descriptor
  *
- * Traverse through pending legacy interrupts and invoke handler for each. Also
+ * Traverse through pending INTX interrupts and invoke handler for each. Also
  * takes care of interrupt controller level mask/ack operation.
  */
-static void ks_pcie_legacy_irq_handler(struct irq_desc *desc)
+static void ks_pcie_intx_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc);
 	struct dw_pcie *pci = ks_pcie->pci;
 	struct device *dev = pci->dev;
-	u32 irq_offset = irq - ks_pcie->legacy_host_irqs[0];
+	u32 irq_offset = irq - ks_pcie->intx_host_irqs[0];
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 
-	dev_dbg(dev, ": Handling legacy irq %d\n", irq);
+	dev_dbg(dev, ": Handling INTX irq %d\n", irq);
 
 	/*
 	 * The chained irq handler installation would have replaced normal
@@ -628,7 +626,7 @@ static void ks_pcie_legacy_irq_handler(struct irq_desc *desc)
 	 * ack operation.
 	 */
 	chained_irq_enter(chip, desc);
-	ks_pcie_handle_legacy_irq(ks_pcie, irq_offset);
+	ks_pcie_handle_intx_irq(ks_pcie, irq_offset);
 	chained_irq_exit(chip, desc);
 }
 
@@ -686,10 +684,10 @@ err:
 	return ret;
 }
 
-static int ks_pcie_config_legacy_irq(struct keystone_pcie *ks_pcie)
+static int ks_pcie_config_intx_irq(struct keystone_pcie *ks_pcie)
 {
 	struct device *dev = ks_pcie->pci->dev;
-	struct irq_domain *legacy_irq_domain;
+	struct irq_domain *intx_irq_domain;
 	struct device_node *np = ks_pcie->np;
 	struct device_node *intc_np;
 	int irq_count, irq, ret = 0, i;
@@ -697,7 +695,7 @@ static int ks_pcie_config_legacy_irq(struct keystone_pcie *ks_pcie)
 	intc_np = of_get_child_by_name(np, "legacy-interrupt-controller");
 	if (!intc_np) {
 		/*
-		 * Since legacy interrupts are modeled as edge-interrupts in
+		 * Since INTX interrupts are modeled as edge-interrupts in
 		 * AM6, keep it disabled for now.
 		 */
 		if (ks_pcie->is_am6)
@@ -719,22 +717,21 @@ static int ks_pcie_config_legacy_irq(struct keystone_pcie *ks_pcie)
 			ret = -EINVAL;
 			goto err;
 		}
-		ks_pcie->legacy_host_irqs[i] = irq;
+		ks_pcie->intx_host_irqs[i] = irq;
 
 		irq_set_chained_handler_and_data(irq,
-						 ks_pcie_legacy_irq_handler,
+						 ks_pcie_intx_irq_handler,
 						 ks_pcie);
 	}
 
-	legacy_irq_domain =
-		irq_domain_add_linear(intc_np, PCI_NUM_INTX,
-				      &ks_pcie_legacy_irq_domain_ops, NULL);
-	if (!legacy_irq_domain) {
-		dev_err(dev, "Failed to add irq domain for legacy irqs\n");
+	intx_irq_domain = irq_domain_add_linear(intc_np, PCI_NUM_INTX,
+					&ks_pcie_intx_irq_domain_ops, NULL);
+	if (!intx_irq_domain) {
+		dev_err(dev, "Failed to add irq domain for INTX irqs\n");
 		ret = -EINVAL;
 		goto err;
 	}
-	ks_pcie->legacy_irq_domain = legacy_irq_domain;
+	ks_pcie->intx_irq_domain = intx_irq_domain;
 
 	for (i = 0; i < PCI_NUM_INTX; i++)
 		ks_pcie_app_writel(ks_pcie, IRQ_ENABLE_SET(i), INTx_EN);
@@ -808,7 +805,7 @@ static int __init ks_pcie_host_init(struct dw_pcie_rp *pp)
 	if (!ks_pcie->is_am6)
 		pp->bridge->child_ops = &ks_child_pcie_ops;
 
-	ret = ks_pcie_config_legacy_irq(ks_pcie);
+	ret = ks_pcie_config_intx_irq(ks_pcie);
 	if (ret)
 		return ret;
 
@@ -881,7 +878,7 @@ static void ks_pcie_am654_ep_init(struct dw_pcie_ep *ep)
 	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, flags);
 }
 
-static void ks_pcie_am654_raise_legacy_irq(struct keystone_pcie *ks_pcie)
+static void ks_pcie_am654_raise_intx_irq(struct keystone_pcie *ks_pcie)
 {
 	struct dw_pcie *pci = ks_pcie->pci;
 	u8 int_pin;
@@ -907,7 +904,7 @@ static int ks_pcie_am654_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		ks_pcie_am654_raise_legacy_irq(ks_pcie);
+		ks_pcie_am654_raise_intx_irq(ks_pcie);
 		break;
 	case PCI_IRQ_MSI:
 		dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-- 
GitLab


From 1b79b2aa9f6c20dfc1b77b51b06d5f8a6fd90a6d Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:04:01 +0900
Subject: [PATCH 1588/4076] PCI: dw-rockchip: Rename
 rockchip_pcie_legacy_int_handler()

Rename the function rockchip_pcie_legacy_int_handler() to
rockchip_pcie_intx_handler() to match the code managing INTX interrupts
(e.g. intx_domain_ops) and the term used in the PCI specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-12-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/dwc/pcie-dw-rockchip.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index 2fe42c70097fd..2b3923c528275 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -72,7 +72,7 @@ static void rockchip_pcie_writel_apb(struct rockchip_pcie *rockchip,
 	writel_relaxed(val, rockchip->apb_base + reg);
 }
 
-static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc)
+static void rockchip_pcie_intx_handler(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc);
@@ -202,7 +202,7 @@ static int rockchip_pcie_host_init(struct dw_pcie_rp *pp)
 	if (ret < 0)
 		dev_err(dev, "failed to init irq domain\n");
 
-	irq_set_chained_handler_and_data(irq, rockchip_pcie_legacy_int_handler,
+	irq_set_chained_handler_and_data(irq, rockchip_pcie_intx_handler,
 					 rockchip);
 
 	/* LTSSM enable control mode */
-- 
GitLab


From 3ba180c45b309db39eef2bd595a2564b294ea1e7 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:04:02 +0900
Subject: [PATCH 1589/4076] PCI: tegra194: Use INTX instead of legacy

In the Designware tegra194 controller driver, change all names using
"legacy" to use "intx", to match the term used in the PCI
specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-13-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/dwc/pcie-tegra194.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index a1f37d2d77986..e02dcbcb5970a 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -773,13 +773,13 @@ static void tegra_pcie_enable_system_interrupts(struct dw_pcie_rp *pp)
 			   val_w);
 }
 
-static void tegra_pcie_enable_legacy_interrupts(struct dw_pcie_rp *pp)
+static void tegra_pcie_enable_intx_interrupts(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val;
 
-	/* Enable legacy interrupt generation */
+	/* Enable INTX interrupt generation */
 	val = appl_readl(pcie, APPL_INTR_EN_L0_0);
 	val |= APPL_INTR_EN_L0_0_SYS_INTR_EN;
 	val |= APPL_INTR_EN_L0_0_INT_INT_EN;
@@ -830,7 +830,7 @@ static void tegra_pcie_enable_interrupts(struct dw_pcie_rp *pp)
 	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17);
 
 	tegra_pcie_enable_system_interrupts(pp);
-	tegra_pcie_enable_legacy_interrupts(pp);
+	tegra_pcie_enable_intx_interrupts(pp);
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_enable_msi_interrupts(pp);
 }
@@ -1947,7 +1947,7 @@ static irqreturn_t tegra_pcie_ep_pex_rst_irq(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static int tegra_pcie_ep_raise_legacy_irq(struct tegra_pcie_dw *pcie, u16 irq)
+static int tegra_pcie_ep_raise_intx_irq(struct tegra_pcie_dw *pcie, u16 irq)
 {
 	/* Tegra194 supports only INTA */
 	if (irq > 1)
@@ -1986,7 +1986,7 @@ static int tegra_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		return tegra_pcie_ep_raise_legacy_irq(pcie, interrupt_num);
+		return tegra_pcie_ep_raise_intx_irq(pcie, interrupt_num);
 
 	case PCI_IRQ_MSI:
 		return tegra_pcie_ep_raise_msi_irq(pcie, interrupt_num);
-- 
GitLab


From c0dcdeea085053f3f25ee0ad262aa0aaa86df82b Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:04:03 +0900
Subject: [PATCH 1590/4076] PCI: uniphier: Use INTX instead of legacy

In the Designware uniphier controller driver, including the endpoint
driver, change all names using "legacy" to use "intx", to match the
term used in the PCI specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-14-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/dwc/pcie-uniphier-ep.c |  4 ++--
 drivers/pci/controller/dwc/pcie-uniphier.c    | 12 ++++++------
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
index d47236d5678d2..a45f94b284a2f 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier-ep.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
@@ -212,7 +212,7 @@ static void uniphier_pcie_ep_init(struct dw_pcie_ep *ep)
 		dw_pcie_ep_reset_bar(pci, bar);
 }
 
-static int uniphier_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep)
+static int uniphier_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci);
@@ -262,7 +262,7 @@ static int uniphier_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		return uniphier_pcie_ep_raise_legacy_irq(ep);
+		return uniphier_pcie_ep_raise_intx_irq(ep);
 	case PCI_IRQ_MSI:
 		return uniphier_pcie_ep_raise_msi_irq(ep, func_no,
 						      interrupt_num);
diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c
index 48c3eba817b43..ff16b7345cfc6 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier.c
@@ -67,7 +67,7 @@ struct uniphier_pcie {
 	struct clk *clk;
 	struct reset_control *rst;
 	struct phy *phy;
-	struct irq_domain *legacy_irq_domain;
+	struct irq_domain *intx_irq_domain;
 };
 
 #define to_uniphier_pcie(x)	dev_get_drvdata((x)->dev)
@@ -253,12 +253,12 @@ static void uniphier_pcie_irq_handler(struct irq_desc *desc)
 	reg = FIELD_GET(PCL_RCV_INTX_ALL_STATUS, val);
 
 	for_each_set_bit(bit, &reg, PCI_NUM_INTX)
-		generic_handle_domain_irq(pcie->legacy_irq_domain, bit);
+		generic_handle_domain_irq(pcie->intx_irq_domain, bit);
 
 	chained_irq_exit(chip, desc);
 }
 
-static int uniphier_pcie_config_legacy_irq(struct dw_pcie_rp *pp)
+static int uniphier_pcie_config_intx_irq(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
@@ -279,9 +279,9 @@ static int uniphier_pcie_config_legacy_irq(struct dw_pcie_rp *pp)
 		goto out_put_node;
 	}
 
-	pcie->legacy_irq_domain = irq_domain_add_linear(np_intc, PCI_NUM_INTX,
+	pcie->intx_irq_domain = irq_domain_add_linear(np_intc, PCI_NUM_INTX,
 						&uniphier_intx_domain_ops, pp);
-	if (!pcie->legacy_irq_domain) {
+	if (!pcie->intx_irq_domain) {
 		dev_err(pci->dev, "Failed to get INTx domain\n");
 		ret = -ENODEV;
 		goto out_put_node;
@@ -301,7 +301,7 @@ static int uniphier_pcie_host_init(struct dw_pcie_rp *pp)
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
 	int ret;
 
-	ret = uniphier_pcie_config_legacy_irq(pp);
+	ret = uniphier_pcie_config_intx_irq(pp);
 	if (ret)
 		return ret;
 
-- 
GitLab


From 5815c2d17a74927c627f5c759bd9d772ac4c3981 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:04:04 +0900
Subject: [PATCH 1591/4076] PCI: rockchip-ep: Use INTX instead of legacy

Rename the function rockchip_pcie_ep_send_legacy_irq() of the rockchip
endpoint driver to rockchip_pcie_ep_send_intx_irq(). Uses of the term
"legacy" are also replaced with "INTX" in comments.

Link: https://lore.kernel.org/r/20231122060406.14695-15-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/pcie-rockchip-ep.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 95b1c8ef59c3e..c9046e97a1d27 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -26,16 +26,16 @@
  * @max_regions: maximum number of regions supported by hardware
  * @ob_region_map: bitmask of mapped outbound regions
  * @ob_addr: base addresses in the AXI bus where the outbound regions start
- * @irq_phys_addr: base address on the AXI bus where the MSI/legacy IRQ
+ * @irq_phys_addr: base address on the AXI bus where the MSI/INTX IRQ
  *		   dedicated outbound regions is mapped.
  * @irq_cpu_addr: base address in the CPU space where a write access triggers
- *		  the sending of a memory write (MSI) / normal message (legacy
+ *		  the sending of a memory write (MSI) / normal message (INTX
  *		  IRQ) TLP through the PCIe bus.
- * @irq_pci_addr: used to save the current mapping of the MSI/legacy IRQ
+ * @irq_pci_addr: used to save the current mapping of the MSI/INTX IRQ
  *		  dedicated outbound region.
  * @irq_pci_fn: the latest PCI function that has updated the mapping of
- *		the MSI/legacy IRQ dedicated outbound region.
- * @irq_pending: bitmask of asserted legacy IRQs.
+ *		the MSI/INTX IRQ dedicated outbound region.
+ * @irq_pending: bitmask of asserted INTX IRQs.
  */
 struct rockchip_pcie_ep {
 	struct rockchip_pcie	rockchip;
@@ -325,8 +325,8 @@ static void rockchip_pcie_ep_assert_intx(struct rockchip_pcie_ep *ep, u8 fn,
 	}
 }
 
-static int rockchip_pcie_ep_send_legacy_irq(struct rockchip_pcie_ep *ep, u8 fn,
-					    u8 intx)
+static int rockchip_pcie_ep_send_intx_irq(struct rockchip_pcie_ep *ep, u8 fn,
+					  u8 intx)
 {
 	u16 cmd;
 
@@ -413,7 +413,7 @@ static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
 
 	switch (type) {
 	case PCI_IRQ_INTX:
-		return rockchip_pcie_ep_send_legacy_irq(ep, fn, 0);
+		return rockchip_pcie_ep_send_intx_irq(ep, fn, 0);
 	case PCI_IRQ_MSI:
 		return rockchip_pcie_ep_send_msi_irq(ep, fn, interrupt_num);
 	default:
-- 
GitLab


From 95da5fedd325a6f953e06933249f371f72b41df7 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:04:05 +0900
Subject: [PATCH 1592/4076] PCI: rockchip-host: Rename
 rockchip_pcie_legacy_int_handler()

Rename the function rockchip_pcie_legacy_int_handler() of the rockchip
host driver to rockchip_pcie_intx_handler() to match the PCI_IRQ_INTX
macro name used to control this function execution, and to match the
term used in the PCI specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-16-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/pcie-rockchip-host.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index afbbdccd195d9..300b9dc85ecc7 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -505,7 +505,7 @@ static irqreturn_t rockchip_pcie_client_irq_handler(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc)
+static void rockchip_pcie_intx_handler(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc);
@@ -553,7 +553,7 @@ static int rockchip_pcie_setup_irq(struct rockchip_pcie *rockchip)
 		return irq;
 
 	irq_set_chained_handler_and_data(irq,
-					 rockchip_pcie_legacy_int_handler,
+					 rockchip_pcie_intx_handler,
 					 rockchip);
 
 	irq = platform_get_irq_byname(pdev, "client");
-- 
GitLab


From 354b2bd38aeae8af066d9b92ab1ea4d608e64562 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:04:06 +0900
Subject: [PATCH 1593/4076] PCI: xilinx-nwl: Use INTX instead of legacy

In the xilinx-nwl controller driver, change all use of "legacy" and
"leg" to "intx", to match the term used in the PCI specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-17-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/controller/pcie-xilinx-nwl.c | 52 ++++++++++++------------
 1 file changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index e307aceba5c97..0408f4d612b5a 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -166,7 +166,7 @@ struct nwl_pcie {
 	int irq_intx;
 	int irq_misc;
 	struct nwl_msi msi;
-	struct irq_domain *legacy_irq_domain;
+	struct irq_domain *intx_irq_domain;
 	struct clk *clk;
 	raw_spinlock_t leg_mask_lock;
 };
@@ -324,7 +324,7 @@ static void nwl_pcie_leg_handler(struct irq_desc *desc)
 	while ((status = nwl_bridge_readl(pcie, MSGF_LEG_STATUS) &
 				MSGF_LEG_SR_MASKALL) != 0) {
 		for_each_set_bit(bit, &status, PCI_NUM_INTX)
-			generic_handle_domain_irq(pcie->legacy_irq_domain, bit);
+			generic_handle_domain_irq(pcie->intx_irq_domain, bit);
 	}
 
 	chained_irq_exit(chip, desc);
@@ -364,7 +364,7 @@ static void nwl_pcie_msi_handler_low(struct irq_desc *desc)
 	chained_irq_exit(chip, desc);
 }
 
-static void nwl_mask_leg_irq(struct irq_data *data)
+static void nwl_mask_intx_irq(struct irq_data *data)
 {
 	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
 	unsigned long flags;
@@ -378,7 +378,7 @@ static void nwl_mask_leg_irq(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&pcie->leg_mask_lock, flags);
 }
 
-static void nwl_unmask_leg_irq(struct irq_data *data)
+static void nwl_unmask_intx_irq(struct irq_data *data)
 {
 	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
 	unsigned long flags;
@@ -392,26 +392,26 @@ static void nwl_unmask_leg_irq(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&pcie->leg_mask_lock, flags);
 }
 
-static struct irq_chip nwl_leg_irq_chip = {
+static struct irq_chip nwl_intx_irq_chip = {
 	.name = "nwl_pcie:legacy",
-	.irq_enable = nwl_unmask_leg_irq,
-	.irq_disable = nwl_mask_leg_irq,
-	.irq_mask = nwl_mask_leg_irq,
-	.irq_unmask = nwl_unmask_leg_irq,
+	.irq_enable = nwl_unmask_intx_irq,
+	.irq_disable = nwl_mask_intx_irq,
+	.irq_mask = nwl_mask_intx_irq,
+	.irq_unmask = nwl_unmask_intx_irq,
 };
 
-static int nwl_legacy_map(struct irq_domain *domain, unsigned int irq,
-			  irq_hw_number_t hwirq)
+static int nwl_intx_map(struct irq_domain *domain, unsigned int irq,
+			irq_hw_number_t hwirq)
 {
-	irq_set_chip_and_handler(irq, &nwl_leg_irq_chip, handle_level_irq);
+	irq_set_chip_and_handler(irq, &nwl_intx_irq_chip, handle_level_irq);
 	irq_set_chip_data(irq, domain->host_data);
 	irq_set_status_flags(irq, IRQ_LEVEL);
 
 	return 0;
 }
 
-static const struct irq_domain_ops legacy_domain_ops = {
-	.map = nwl_legacy_map,
+static const struct irq_domain_ops intx_domain_ops = {
+	.map = nwl_intx_map,
 	.xlate = pci_irqd_intx_xlate,
 };
 
@@ -525,20 +525,20 @@ static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
 	struct device_node *node = dev->of_node;
-	struct device_node *legacy_intc_node;
+	struct device_node *intc_node;
 
-	legacy_intc_node = of_get_next_child(node, NULL);
-	if (!legacy_intc_node) {
+	intc_node = of_get_next_child(node, NULL);
+	if (!intc_node) {
 		dev_err(dev, "No legacy intc node found\n");
 		return -EINVAL;
 	}
 
-	pcie->legacy_irq_domain = irq_domain_add_linear(legacy_intc_node,
-							PCI_NUM_INTX,
-							&legacy_domain_ops,
-							pcie);
-	of_node_put(legacy_intc_node);
-	if (!pcie->legacy_irq_domain) {
+	pcie->intx_irq_domain = irq_domain_add_linear(intc_node,
+						      PCI_NUM_INTX,
+						      &intx_domain_ops,
+						      pcie);
+	of_node_put(intc_node);
+	if (!pcie->intx_irq_domain) {
 		dev_err(dev, "failed to create IRQ domain\n");
 		return -ENOMEM;
 	}
@@ -710,14 +710,14 @@ static int nwl_pcie_bridge_init(struct nwl_pcie *pcie)
 	/* Enable all misc interrupts */
 	nwl_bridge_writel(pcie, MSGF_MISC_SR_MASKALL, MSGF_MISC_MASK);
 
-	/* Disable all legacy interrupts */
+	/* Disable all INTX interrupts */
 	nwl_bridge_writel(pcie, (u32)~MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK);
 
-	/* Clear pending legacy interrupts */
+	/* Clear pending INTX interrupts */
 	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_LEG_STATUS) &
 			  MSGF_LEG_SR_MASKALL, MSGF_LEG_STATUS);
 
-	/* Enable all legacy interrupts */
+	/* Enable all INTX interrupts */
 	nwl_bridge_writel(pcie, MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK);
 
 	/* Enable the bridge config interrupt */
-- 
GitLab


From 2bfc654b89c4dd1c372bb2cbba6b5a0eb578d214 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 9 Nov 2023 15:47:49 +0000
Subject: [PATCH 1594/4076] arm64: cpufeatures: Restrict NV support to FEAT_NV2

To anyone who has played with FEAT_NV, it is obvious that the level
of performance is rather low due to the trap amplification that it
imposes on the host hypervisor. FEAT_NV2 solves a number of the
problems that FEAT_NV had.

It also turns out that all the existing hardware that has FEAT_NV
also has FEAT_NV2. Finally, it is now allowed by the architecture
to build FEAT_NV2 *only* (as denoted by ID_AA64MMFR4_EL1.NV_frac),
which effectively seals the fate of FEAT_NV.

Restrict the NV support to NV2, and be done with it. Nobody will
cry over the old crap. NV_frac will eventually be supported once
the intrastructure is ready.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kernel/cpufeature.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 646591c67e7a5..1329e974d187c 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2339,7 +2339,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HAS_NESTED_VIRT,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_nested_virt_support,
-		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, IMP)
+		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, NV2)
 	},
 	{
 		.capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE,
-- 
GitLab


From 111903d1f5b9334d1100e1c6ee08e740fa374d91 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Mon, 13 Nov 2023 14:16:02 +0000
Subject: [PATCH 1595/4076] KVM: arm64: nv: Hoist vcpu_has_nv() into
 is_hyp_ctxt()

A rather common idiom when writing NV code as part of KVM is
to have things such has:

	if (vcpu_has_nv(vcpu) && is_hyp_ctxt(vcpu)) {
		[...]
	}

to check that we are in a hyp-related context. The second part of
the conjunction would be enough, but the first one contains a
static key that allows the rest of the checkis to be elided when
in a non-NV environment.

Rewrite is_hyp_ctxt() to directly use vcpu_has_nv(). The result
is the same, and the code easier to read. The one occurence of
this that is already merged is rewritten in the process.

In order to avoid nasty cirtular dependencies between kvm_emulate.h
and kvm_nested.h, vcpu_has_feature() is itself hoisted into kvm_host.h,
at the cost of some #deferry...

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h | 8 ++------
 arch/arm64/include/asm/kvm_host.h    | 7 +++++++
 arch/arm64/kvm/arch_timer.c          | 3 +--
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 78a550537b673..84829b7e6f1da 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -17,6 +17,7 @@
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_nested.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
 #include <asm/virt.h>
@@ -54,11 +55,6 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
 int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
 int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
 
-static inline bool vcpu_has_feature(const struct kvm_vcpu *vcpu, int feature)
-{
-	return test_bit(feature, vcpu->kvm->arch.vcpu_features);
-}
-
 #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
@@ -248,7 +244,7 @@ static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt)
 
 static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
 {
-	return __is_hyp_ctxt(&vcpu->arch.ctxt);
+	return vcpu_has_nv(vcpu) && __is_hyp_ctxt(&vcpu->arch.ctxt);
 }
 
 /*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 824f29f04916a..4103a12ecaafa 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1177,6 +1177,13 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_vm_has_ran_once(kvm)					\
 	(test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags))
 
+static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature)
+{
+	return test_bit(feature, ka->vcpu_features);
+}
+
+#define vcpu_has_feature(v, f)	__vcpu_has_feature(&(v)->kvm->arch, (f))
+
 int kvm_trng_call(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
 extern phys_addr_t hyp_mem_base;
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 13ba691b848f7..9dec8c419bf40 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -295,8 +295,7 @@ static u64 wfit_delay_ns(struct kvm_vcpu *vcpu)
 	u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
 	struct arch_timer_context *ctx;
 
-	ctx = (vcpu_has_nv(vcpu) && is_hyp_ctxt(vcpu)) ? vcpu_hvtimer(vcpu)
-						       : vcpu_vtimer(vcpu);
+	ctx = is_hyp_ctxt(vcpu) ? vcpu_hvtimer(vcpu) : vcpu_vtimer(vcpu);
 
 	return kvm_counter_compute_delta(ctx, val);
 }
-- 
GitLab


From 3ed0b5123cd5a2a4f1fe4e594e7bf319e9eaf1da Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 12 Nov 2023 21:05:14 +0000
Subject: [PATCH 1596/4076] KVM: arm64: nv: Compute NV view of idregs as a
 one-off

Now that we have a full copy of the idregs for each VM, there is
no point in repainting the sysregs on each access. Instead, we
can simply perform the transmation as a one-off and be done
with it.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h   |  1 +
 arch/arm64/include/asm/kvm_nested.h |  6 +-----
 arch/arm64/kvm/arm.c                |  6 ++++++
 arch/arm64/kvm/nested.c             | 22 +++++++++++++++-------
 arch/arm64/kvm/sys_regs.c           |  2 --
 5 files changed, 23 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 4103a12ecaafa..fce2e5f583a72 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -306,6 +306,7 @@ struct kvm_arch {
 	 * Atomic access to multiple idregs are guarded by kvm_arch.config_lock.
 	 */
 #define IDREG_IDX(id)		(((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id))
+#define IDX_IDREG(idx)		sys_reg(3, 0, 0, ((idx) >> 3) + 1, (idx) & Op2_mask)
 #define IDREG(kvm, id)		((kvm)->arch.id_regs[IDREG_IDX(id)])
 #define KVM_ARM_ID_REG_NUM	(IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
 	u64 id_regs[KVM_ARM_ID_REG_NUM];
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 6cec8e9c6c912..249b03fc2ccee 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -14,10 +14,6 @@ static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 
 extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
 
-struct sys_reg_params;
-struct sys_reg_desc;
-
-void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
-			  const struct sys_reg_desc *r);
+int kvm_init_nv_sysregs(struct kvm *kvm);
 
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e5f75f1f10853..b65df612b41b1 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -669,6 +669,12 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
+	if (vcpu_has_nv(vcpu)) {
+		ret = kvm_init_nv_sysregs(vcpu->kvm);
+		if (ret)
+			return ret;
+	}
+
 	ret = kvm_timer_enable(vcpu);
 	if (ret)
 		return ret;
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 042695a210ceb..ba95d044bc98f 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -23,13 +23,9 @@
  * This list should get updated as new features get added to the NV
  * support, and new extension to the architecture.
  */
-void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
-			  const struct sys_reg_desc *r)
+static u64 limit_nv_id_reg(u32 id, u64 val)
 {
-	u32 id = reg_to_encoding(r);
-	u64 val, tmp;
-
-	val = p->regval;
+	u64 tmp;
 
 	switch (id) {
 	case SYS_ID_AA64ISAR0_EL1:
@@ -158,5 +154,17 @@ void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 		break;
 	}
 
-	p->regval = val;
+	return val;
+}
+int kvm_init_nv_sysregs(struct kvm *kvm)
+{
+	mutex_lock(&kvm->arch.config_lock);
+
+	for (int i = 0; i < KVM_ARM_ID_REG_NUM; i++)
+		kvm->arch.id_regs[i] = limit_nv_id_reg(IDX_IDREG(i),
+						       kvm->arch.id_regs[i]);
+
+	mutex_unlock(&kvm->arch.config_lock);
+
+	return 0;
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 4735e1b37fb3e..3eae84195d482 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1505,8 +1505,6 @@ static bool access_id_reg(struct kvm_vcpu *vcpu,
 		return write_to_read_only(vcpu, p, r);
 
 	p->regval = read_id_reg(vcpu, r);
-	if (vcpu_has_nv(vcpu))
-		access_nested_id_reg(vcpu, p, r);
 
 	return true;
 }
-- 
GitLab


From 4d4f52052ba8357f1591cb9bc3086541070711af Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 8 Nov 2023 19:10:12 +0000
Subject: [PATCH 1597/4076] KVM: arm64: nv: Drop EL12 register traps that are
 redirected to VNCR

With FEAT_NV2, a bunch of system register writes are turned into
memory writes. This is specially the fate of the EL12 registers
that the guest hypervisor manipulates out of context.

Remove the trap descriptors for those, as they are never going
to be used again.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3eae84195d482..cdfc79ccc7a18 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2566,21 +2566,6 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(CNTVOFF_EL2, access_rw, reset_val, 0),
 	EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0),
 
-	EL12_REG(SCTLR, access_vm_reg, reset_val, 0x00C50078),
-	EL12_REG(CPACR, access_rw, reset_val, 0),
-	EL12_REG(TTBR0, access_vm_reg, reset_unknown, 0),
-	EL12_REG(TTBR1, access_vm_reg, reset_unknown, 0),
-	EL12_REG(TCR, access_vm_reg, reset_val, 0),
-	{ SYS_DESC(SYS_SPSR_EL12), access_spsr},
-	{ SYS_DESC(SYS_ELR_EL12), access_elr},
-	EL12_REG(AFSR0, access_vm_reg, reset_unknown, 0),
-	EL12_REG(AFSR1, access_vm_reg, reset_unknown, 0),
-	EL12_REG(ESR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(FAR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(MAIR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(AMAIR, access_vm_reg, reset_amair_el1, 0),
-	EL12_REG(VBAR, access_rw, reset_val, 0),
-	EL12_REG(CONTEXTIDR, access_vm_reg, reset_val, 0),
 	EL12_REG(CNTKCTL, access_rw, reset_val, 0),
 
 	EL2_REG(SP_EL2, NULL, reset_unknown, 0),
-- 
GitLab


From 3606e0b2e462164bced151dbb54ccfe42ac6c35b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 25 Dec 2016 10:49:48 -0500
Subject: [PATCH 1598/4076] KVM: arm64: nv: Add non-VHE-EL2->EL1 translation
 helpers

Some EL2 system registers immediately affect the current execution
of the system, so we need to use their respective EL1 counterparts.
For this we need to define a mapping between the two. In general,
this only affects non-VHE guest hypervisors, as VHE system registers
are compatible with the EL1 counterparts.

These helpers will get used in subsequent patches.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Co-developed-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h | 50 ++++++++++++++++++++++++++++-
 1 file changed, 49 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 249b03fc2ccee..4882905357f43 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -2,8 +2,9 @@
 #ifndef __ARM64_KVM_NESTED_H
 #define __ARM64_KVM_NESTED_H
 
-#include <asm/kvm_emulate.h>
+#include <linux/bitfield.h>
 #include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
 
 static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 {
@@ -12,6 +13,53 @@ static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 		vcpu_has_feature(vcpu, KVM_ARM_VCPU_HAS_EL2));
 }
 
+/* Translation helpers from non-VHE EL2 to EL1 */
+static inline u64 tcr_el2_ps_to_tcr_el1_ips(u64 tcr_el2)
+{
+	return (u64)FIELD_GET(TCR_EL2_PS_MASK, tcr_el2) << TCR_IPS_SHIFT;
+}
+
+static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr)
+{
+	return TCR_EPD1_MASK |				/* disable TTBR1_EL1 */
+	       ((tcr & TCR_EL2_TBI) ? TCR_TBI0 : 0) |
+	       tcr_el2_ps_to_tcr_el1_ips(tcr) |
+	       (tcr & TCR_EL2_TG0_MASK) |
+	       (tcr & TCR_EL2_ORGN0_MASK) |
+	       (tcr & TCR_EL2_IRGN0_MASK) |
+	       (tcr & TCR_EL2_T0SZ_MASK);
+}
+
+static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
+{
+	u64 cpacr_el1 = 0;
+
+	if (cptr_el2 & CPTR_EL2_TTA)
+		cpacr_el1 |= CPACR_ELx_TTA;
+	if (!(cptr_el2 & CPTR_EL2_TFP))
+		cpacr_el1 |= CPACR_ELx_FPEN;
+	if (!(cptr_el2 & CPTR_EL2_TZ))
+		cpacr_el1 |= CPACR_ELx_ZEN;
+
+	return cpacr_el1;
+}
+
+static inline u64 translate_sctlr_el2_to_sctlr_el1(u64 val)
+{
+	/* Only preserve the minimal set of bits we support */
+	val &= (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | SCTLR_ELx_SA |
+		SCTLR_ELx_I | SCTLR_ELx_IESB | SCTLR_ELx_WXN | SCTLR_ELx_EE);
+	val |= SCTLR_EL1_RES1;
+
+	return val;
+}
+
+static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
+{
+	/* Clear the ASID field */
+	return ttbr0 & ~GENMASK_ULL(63, 48);
+}
+
 extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
 
 int kvm_init_nv_sysregs(struct kvm *kvm);
-- 
GitLab


From 60ce16cc122aad999129d23061fa35f63d5b1e9b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 21 Jun 2019 13:54:37 +0100
Subject: [PATCH 1599/4076] KVM: arm64: nv: Add include containing the VNCR_EL2
 offsets

VNCR_EL2 points to a page containing a number of system registers
accessed by a guest hypervisor when ARMv8.4-NV is enabled.

Let's document the offsets in that page, as we are going to use
this layout.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/vncr_mapping.h | 103 ++++++++++++++++++++++++++
 1 file changed, 103 insertions(+)
 create mode 100644 arch/arm64/include/asm/vncr_mapping.h

diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h
new file mode 100644
index 0000000000000..df2c47c559728
--- /dev/null
+++ b/arch/arm64/include/asm/vncr_mapping.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * System register offsets in the VNCR page
+ * All offsets are *byte* displacements!
+ */
+
+#ifndef __ARM64_VNCR_MAPPING_H__
+#define __ARM64_VNCR_MAPPING_H__
+
+#define VNCR_VTTBR_EL2          0x020
+#define VNCR_VTCR_EL2           0x040
+#define VNCR_VMPIDR_EL2         0x050
+#define VNCR_CNTVOFF_EL2        0x060
+#define VNCR_HCR_EL2            0x078
+#define VNCR_HSTR_EL2           0x080
+#define VNCR_VPIDR_EL2          0x088
+#define VNCR_TPIDR_EL2          0x090
+#define VNCR_HCRX_EL2           0x0A0
+#define VNCR_VNCR_EL2           0x0B0
+#define VNCR_CPACR_EL1          0x100
+#define VNCR_CONTEXTIDR_EL1     0x108
+#define VNCR_SCTLR_EL1          0x110
+#define VNCR_ACTLR_EL1          0x118
+#define VNCR_TCR_EL1            0x120
+#define VNCR_AFSR0_EL1          0x128
+#define VNCR_AFSR1_EL1          0x130
+#define VNCR_ESR_EL1            0x138
+#define VNCR_MAIR_EL1           0x140
+#define VNCR_AMAIR_EL1          0x148
+#define VNCR_MDSCR_EL1          0x158
+#define VNCR_SPSR_EL1           0x160
+#define VNCR_CNTV_CVAL_EL0      0x168
+#define VNCR_CNTV_CTL_EL0       0x170
+#define VNCR_CNTP_CVAL_EL0      0x178
+#define VNCR_CNTP_CTL_EL0       0x180
+#define VNCR_SCXTNUM_EL1        0x188
+#define VNCR_TFSR_EL1		0x190
+#define VNCR_HFGRTR_EL2		0x1B8
+#define VNCR_HFGWTR_EL2		0x1C0
+#define VNCR_HFGITR_EL2		0x1C8
+#define VNCR_HDFGRTR_EL2	0x1D0
+#define VNCR_HDFGWTR_EL2	0x1D8
+#define VNCR_ZCR_EL1            0x1E0
+#define VNCR_HAFGRTR_EL2	0x1E8
+#define VNCR_TTBR0_EL1          0x200
+#define VNCR_TTBR1_EL1          0x210
+#define VNCR_FAR_EL1            0x220
+#define VNCR_ELR_EL1            0x230
+#define VNCR_SP_EL1             0x240
+#define VNCR_VBAR_EL1           0x250
+#define VNCR_TCR2_EL1		0x270
+#define VNCR_PIRE0_EL1		0x290
+#define VNCR_PIRE0_EL2		0x298
+#define VNCR_PIR_EL1		0x2A0
+#define VNCR_ICH_LR0_EL2        0x400
+#define VNCR_ICH_LR1_EL2        0x408
+#define VNCR_ICH_LR2_EL2        0x410
+#define VNCR_ICH_LR3_EL2        0x418
+#define VNCR_ICH_LR4_EL2        0x420
+#define VNCR_ICH_LR5_EL2        0x428
+#define VNCR_ICH_LR6_EL2        0x430
+#define VNCR_ICH_LR7_EL2        0x438
+#define VNCR_ICH_LR8_EL2        0x440
+#define VNCR_ICH_LR9_EL2        0x448
+#define VNCR_ICH_LR10_EL2       0x450
+#define VNCR_ICH_LR11_EL2       0x458
+#define VNCR_ICH_LR12_EL2       0x460
+#define VNCR_ICH_LR13_EL2       0x468
+#define VNCR_ICH_LR14_EL2       0x470
+#define VNCR_ICH_LR15_EL2       0x478
+#define VNCR_ICH_AP0R0_EL2      0x480
+#define VNCR_ICH_AP0R1_EL2      0x488
+#define VNCR_ICH_AP0R2_EL2      0x490
+#define VNCR_ICH_AP0R3_EL2      0x498
+#define VNCR_ICH_AP1R0_EL2      0x4A0
+#define VNCR_ICH_AP1R1_EL2      0x4A8
+#define VNCR_ICH_AP1R2_EL2      0x4B0
+#define VNCR_ICH_AP1R3_EL2      0x4B8
+#define VNCR_ICH_HCR_EL2        0x4C0
+#define VNCR_ICH_VMCR_EL2       0x4C8
+#define VNCR_VDISR_EL2          0x500
+#define VNCR_PMBLIMITR_EL1      0x800
+#define VNCR_PMBPTR_EL1         0x810
+#define VNCR_PMBSR_EL1          0x820
+#define VNCR_PMSCR_EL1          0x828
+#define VNCR_PMSEVFR_EL1        0x830
+#define VNCR_PMSICR_EL1         0x838
+#define VNCR_PMSIRR_EL1         0x840
+#define VNCR_PMSLATFR_EL1       0x848
+#define VNCR_TRFCR_EL1          0x880
+#define VNCR_MPAM1_EL1          0x900
+#define VNCR_MPAMHCR_EL2        0x930
+#define VNCR_MPAMVPMV_EL2       0x938
+#define VNCR_MPAMVPM0_EL2       0x940
+#define VNCR_MPAMVPM1_EL2       0x948
+#define VNCR_MPAMVPM2_EL2       0x950
+#define VNCR_MPAMVPM3_EL2       0x958
+#define VNCR_MPAMVPM4_EL2       0x960
+#define VNCR_MPAMVPM5_EL2       0x968
+#define VNCR_MPAMVPM6_EL2       0x970
+#define VNCR_MPAMVPM7_EL2       0x978
+
+#endif /* __ARM64_VNCR_MAPPING_H__ */
-- 
GitLab


From 2733dd10701abc6ab23d65a732f58fbeb80bd203 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Mon, 6 Nov 2023 16:42:13 +0000
Subject: [PATCH 1600/4076] KVM: arm64: Introduce a bad_trap() primitive for
 unexpected trap handling

In order to ease the debugging of NV, it is helpful to have the kernel
shout at you when an unexpected trap is handled. We already have this
in a couple of cases. Make this a more generic infrastructure that we
will make use of very shortly.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index cdfc79ccc7a18..3709c35666a26 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -45,24 +45,31 @@ static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
 static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      u64 val);
 
-static bool read_from_write_only(struct kvm_vcpu *vcpu,
-				 struct sys_reg_params *params,
-				 const struct sys_reg_desc *r)
+static bool bad_trap(struct kvm_vcpu *vcpu,
+		     struct sys_reg_params *params,
+		     const struct sys_reg_desc *r,
+		     const char *msg)
 {
-	WARN_ONCE(1, "Unexpected sys_reg read to write-only register\n");
+	WARN_ONCE(1, "Unexpected %s\n", msg);
 	print_sys_reg_instr(params);
 	kvm_inject_undefined(vcpu);
 	return false;
 }
 
+static bool read_from_write_only(struct kvm_vcpu *vcpu,
+				 struct sys_reg_params *params,
+				 const struct sys_reg_desc *r)
+{
+	return bad_trap(vcpu, params, r,
+			"sys_reg read to write-only register");
+}
+
 static bool write_to_read_only(struct kvm_vcpu *vcpu,
 			       struct sys_reg_params *params,
 			       const struct sys_reg_desc *r)
 {
-	WARN_ONCE(1, "Unexpected sys_reg write to read-only register\n");
-	print_sys_reg_instr(params);
-	kvm_inject_undefined(vcpu);
-	return false;
+	return bad_trap(vcpu, params, r,
+			"sys_reg write to read-only register");
 }
 
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
-- 
GitLab


From 9b9cce60be85e6807bdb0eaa2f520e78dbab0659 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 7 Nov 2023 09:02:10 +0000
Subject: [PATCH 1601/4076] KVM: arm64: nv: Add EL2_REG_VNCR()/EL2_REG_REDIR()
 sysreg helpers

Add two helpers to deal with EL2 registers are are either redirected
to the VNCR page, or that are redirected to their EL1 counterpart.

In either cases, no trap is expected.

THe relevant register descriptors are repainted accordingly.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 65 ++++++++++++++++++++++++++++-----------
 1 file changed, 47 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3709c35666a26..7fef170ec67b7 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1890,6 +1890,32 @@ static unsigned int el2_visibility(const struct kvm_vcpu *vcpu,
 	return REG_HIDDEN;
 }
 
+static bool bad_vncr_trap(struct kvm_vcpu *vcpu,
+			  struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	/*
+	 * We really shouldn't be here, and this is likely the result
+	 * of a misconfigured trap, as this register should target the
+	 * VNCR page, and nothing else.
+	 */
+	return bad_trap(vcpu, p, r,
+			"trap of VNCR-backed register");
+}
+
+static bool bad_redir_trap(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	/*
+	 * We really shouldn't be here, and this is likely the result
+	 * of a misconfigured trap, as this register should target the
+	 * corresponding EL1, and nothing else.
+	 */
+	return bad_trap(vcpu, p, r,
+			"trap of EL2 register redirected to EL1");
+}
+
 #define EL2_REG(name, acc, rst, v) {		\
 	SYS_DESC(SYS_##name),			\
 	.access = acc,				\
@@ -1899,6 +1925,9 @@ static unsigned int el2_visibility(const struct kvm_vcpu *vcpu,
 	.val = v,				\
 }
 
+#define EL2_REG_VNCR(name, rst, v)	EL2_REG(name, bad_vncr_trap, rst, v)
+#define EL2_REG_REDIR(name, rst, v)	EL2_REG(name, bad_redir_trap, rst, v)
+
 /*
  * EL{0,1}2 registers are the EL2 view on an EL0 or EL1 register when
  * HCR_EL2.E2H==1, and only in the sysreg table for convenience of
@@ -2513,32 +2542,32 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ PMU_SYS_REG(PMCCFILTR_EL0), .access = access_pmu_evtyper,
 	  .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 },
 
-	EL2_REG(VPIDR_EL2, access_rw, reset_unknown, 0),
-	EL2_REG(VMPIDR_EL2, access_rw, reset_unknown, 0),
+	EL2_REG_VNCR(VPIDR_EL2, reset_unknown, 0),
+	EL2_REG_VNCR(VMPIDR_EL2, reset_unknown, 0),
 	EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1),
 	EL2_REG(ACTLR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HCR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HCR_EL2, reset_val, 0),
 	EL2_REG(MDCR_EL2, access_rw, reset_val, 0),
 	EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1),
-	EL2_REG(HSTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGRTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGWTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGITR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HACR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HSTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGWTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGITR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HACR_EL2, reset_val, 0),
 
-	EL2_REG(HCRX_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HCRX_EL2, reset_val, 0),
 
 	EL2_REG(TTBR0_EL2, access_rw, reset_val, 0),
 	EL2_REG(TTBR1_EL2, access_rw, reset_val, 0),
 	EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1),
-	EL2_REG(VTTBR_EL2, access_rw, reset_val, 0),
-	EL2_REG(VTCR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(VTTBR_EL2, reset_val, 0),
+	EL2_REG_VNCR(VTCR_EL2, reset_val, 0),
 
 	{ SYS_DESC(SYS_DACR32_EL2), trap_undef, reset_unknown, DACR32_EL2 },
-	EL2_REG(HDFGRTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HDFGWTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(SPSR_EL2, access_rw, reset_val, 0),
-	EL2_REG(ELR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HDFGRTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HDFGWTR_EL2, reset_val, 0),
+	EL2_REG_REDIR(SPSR_EL2, reset_val, 0),
+	EL2_REG_REDIR(ELR_EL2, reset_val, 0),
 	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
 
 	/* AArch32 SPSR_* are RES0 if trapped from a NV guest */
@@ -2554,10 +2583,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_IFSR32_EL2), trap_undef, reset_unknown, IFSR32_EL2 },
 	EL2_REG(AFSR0_EL2, access_rw, reset_val, 0),
 	EL2_REG(AFSR1_EL2, access_rw, reset_val, 0),
-	EL2_REG(ESR_EL2, access_rw, reset_val, 0),
+	EL2_REG_REDIR(ESR_EL2, reset_val, 0),
 	{ SYS_DESC(SYS_FPEXC32_EL2), trap_undef, reset_val, FPEXC32_EL2, 0x700 },
 
-	EL2_REG(FAR_EL2, access_rw, reset_val, 0),
+	EL2_REG_REDIR(FAR_EL2, reset_val, 0),
 	EL2_REG(HPFAR_EL2, access_rw, reset_val, 0),
 
 	EL2_REG(MAIR_EL2, access_rw, reset_val, 0),
@@ -2570,7 +2599,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0),
 	EL2_REG(TPIDR_EL2, access_rw, reset_val, 0),
 
-	EL2_REG(CNTVOFF_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(CNTVOFF_EL2, reset_val, 0),
 	EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0),
 
 	EL12_REG(CNTKCTL, access_rw, reset_val, 0),
-- 
GitLab


From d8bd48e3f0ee9e1fdba2a2e453155a5354e48a8d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 26 Jun 2019 19:59:56 +0100
Subject: [PATCH 1602/4076] KVM: arm64: nv: Map VNCR-capable registers to a
 separate page

With ARMv8.4-NV, registers that can be directly accessed in memory
by the guest have to live at architected offsets in a special page.

Let's annotate the sysreg enum to reflect the offset at which they
are in this page, whith a little twist:

If running on HW that doesn't have the ARMv8.4-NV feature, or even
a VM that doesn't use NV, we store all the system registers in the
usual sys_regs array. The only difference with the pre-8.4
situation is that VNCR-capable registers are at a "similar" offset
as in the VNCR page (we can compute the actual offset at compile
time), and that the sys_regs array is both bigger and sparse.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 127 +++++++++++++++++++-----------
 1 file changed, 81 insertions(+), 46 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index fce2e5f583a72..9e8cd2bb95c3f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
+#include <asm/vncr_mapping.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
@@ -325,33 +326,33 @@ struct kvm_vcpu_fault_info {
 	u64 disr_el1;		/* Deferred [SError] Status Register */
 };
 
+/*
+ * VNCR() just places the VNCR_capable registers in the enum after
+ * __VNCR_START__, and the value (after correction) to be an 8-byte offset
+ * from the VNCR base. As we don't require the enum to be otherwise ordered,
+ * we need the terrible hack below to ensure that we correctly size the
+ * sys_regs array, no matter what.
+ *
+ * The __MAX__ macro has been lifted from Sean Eron Anderson's wonderful
+ * treasure trove of bit hacks:
+ * https://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ */
+#define __MAX__(x,y)	((x) ^ (((x) ^ (y)) & -((x) < (y))))
+#define VNCR(r)						\
+	__before_##r,					\
+	r = __VNCR_START__ + ((VNCR_ ## r) / 8),	\
+	__after_##r = __MAX__(__before_##r - 1, r)
+
 enum vcpu_sysreg {
 	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
 	MPIDR_EL1,	/* MultiProcessor Affinity Register */
 	CLIDR_EL1,	/* Cache Level ID Register */
 	CSSELR_EL1,	/* Cache Size Selection Register */
-	SCTLR_EL1,	/* System Control Register */
-	ACTLR_EL1,	/* Auxiliary Control Register */
-	CPACR_EL1,	/* Coprocessor Access Control */
-	ZCR_EL1,	/* SVE Control */
-	TTBR0_EL1,	/* Translation Table Base Register 0 */
-	TTBR1_EL1,	/* Translation Table Base Register 1 */
-	TCR_EL1,	/* Translation Control Register */
-	TCR2_EL1,	/* Extended Translation Control Register */
-	ESR_EL1,	/* Exception Syndrome Register */
-	AFSR0_EL1,	/* Auxiliary Fault Status Register 0 */
-	AFSR1_EL1,	/* Auxiliary Fault Status Register 1 */
-	FAR_EL1,	/* Fault Address Register */
-	MAIR_EL1,	/* Memory Attribute Indirection Register */
-	VBAR_EL1,	/* Vector Base Address Register */
-	CONTEXTIDR_EL1,	/* Context ID Register */
 	TPIDR_EL0,	/* Thread ID, User R/W */
 	TPIDRRO_EL0,	/* Thread ID, User R/O */
 	TPIDR_EL1,	/* Thread ID, Privileged */
-	AMAIR_EL1,	/* Aux Memory Attribute Indirection Register */
 	CNTKCTL_EL1,	/* Timer Control Register (EL1) */
 	PAR_EL1,	/* Physical Address Register */
-	MDSCR_EL1,	/* Monitor Debug System Control Register */
 	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
 	OSLSR_EL1,	/* OS Lock Status Register */
 	DISR_EL1,	/* Deferred Interrupt Status Register */
@@ -382,26 +383,11 @@ enum vcpu_sysreg {
 	APGAKEYLO_EL1,
 	APGAKEYHI_EL1,
 
-	ELR_EL1,
-	SP_EL1,
-	SPSR_EL1,
-
-	CNTVOFF_EL2,
-	CNTV_CVAL_EL0,
-	CNTV_CTL_EL0,
-	CNTP_CVAL_EL0,
-	CNTP_CTL_EL0,
-
 	/* Memory Tagging Extension registers */
 	RGSR_EL1,	/* Random Allocation Tag Seed Register */
 	GCR_EL1,	/* Tag Control Register */
-	TFSR_EL1,	/* Tag Fault Status Register (EL1) */
 	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
 
-	/* Permission Indirection Extension registers */
-	PIR_EL1,       /* Permission Indirection Register 1 (EL1) */
-	PIRE0_EL1,     /*  Permission Indirection Register 0 (EL1) */
-
 	/* 32bit specific registers. */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -409,21 +395,14 @@ enum vcpu_sysreg {
 	DBGVCR32_EL2,	/* Debug Vector Catch Register */
 
 	/* EL2 registers */
-	VPIDR_EL2,	/* Virtualization Processor ID Register */
-	VMPIDR_EL2,	/* Virtualization Multiprocessor ID Register */
 	SCTLR_EL2,	/* System Control Register (EL2) */
 	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
-	HCR_EL2,	/* Hypervisor Configuration Register */
 	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
 	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
-	HSTR_EL2,	/* Hypervisor System Trap Register */
 	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
-	HCRX_EL2,	/* Extended Hypervisor Configuration Register */
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
-	VTTBR_EL2,	/* Virtualization Translation Table Base Register */
-	VTCR_EL2,	/* Virtualization Translation Control Register */
 	SPSR_EL2,	/* EL2 saved program status register */
 	ELR_EL2,	/* EL2 exception link register */
 	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
@@ -436,19 +415,61 @@ enum vcpu_sysreg {
 	VBAR_EL2,	/* Vector Base Address Register (EL2) */
 	RVBAR_EL2,	/* Reset Vector Base Address Register */
 	CONTEXTIDR_EL2,	/* Context ID Register (EL2) */
-	TPIDR_EL2,	/* EL2 Software Thread ID Register */
 	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
 	SP_EL2,		/* EL2 Stack Pointer */
-	HFGRTR_EL2,
-	HFGWTR_EL2,
-	HFGITR_EL2,
-	HDFGRTR_EL2,
-	HDFGWTR_EL2,
 	CNTHP_CTL_EL2,
 	CNTHP_CVAL_EL2,
 	CNTHV_CTL_EL2,
 	CNTHV_CVAL_EL2,
 
+	__VNCR_START__,	/* Any VNCR-capable reg goes after this point */
+
+	VNCR(SCTLR_EL1),/* System Control Register */
+	VNCR(ACTLR_EL1),/* Auxiliary Control Register */
+	VNCR(CPACR_EL1),/* Coprocessor Access Control */
+	VNCR(ZCR_EL1),	/* SVE Control */
+	VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */
+	VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */
+	VNCR(TCR_EL1),	/* Translation Control Register */
+	VNCR(TCR2_EL1),	/* Extended Translation Control Register */
+	VNCR(ESR_EL1),	/* Exception Syndrome Register */
+	VNCR(AFSR0_EL1),/* Auxiliary Fault Status Register 0 */
+	VNCR(AFSR1_EL1),/* Auxiliary Fault Status Register 1 */
+	VNCR(FAR_EL1),	/* Fault Address Register */
+	VNCR(MAIR_EL1),	/* Memory Attribute Indirection Register */
+	VNCR(VBAR_EL1),	/* Vector Base Address Register */
+	VNCR(CONTEXTIDR_EL1),	/* Context ID Register */
+	VNCR(AMAIR_EL1),/* Aux Memory Attribute Indirection Register */
+	VNCR(MDSCR_EL1),/* Monitor Debug System Control Register */
+	VNCR(ELR_EL1),
+	VNCR(SP_EL1),
+	VNCR(SPSR_EL1),
+	VNCR(TFSR_EL1),	/* Tag Fault Status Register (EL1) */
+	VNCR(VPIDR_EL2),/* Virtualization Processor ID Register */
+	VNCR(VMPIDR_EL2),/* Virtualization Multiprocessor ID Register */
+	VNCR(HCR_EL2),	/* Hypervisor Configuration Register */
+	VNCR(HSTR_EL2),	/* Hypervisor System Trap Register */
+	VNCR(VTTBR_EL2),/* Virtualization Translation Table Base Register */
+	VNCR(VTCR_EL2),	/* Virtualization Translation Control Register */
+	VNCR(TPIDR_EL2),/* EL2 Software Thread ID Register */
+	VNCR(HCRX_EL2),	/* Extended Hypervisor Configuration Register */
+
+	/* Permission Indirection Extension registers */
+	VNCR(PIR_EL1),	 /* Permission Indirection Register 1 (EL1) */
+	VNCR(PIRE0_EL1), /*  Permission Indirection Register 0 (EL1) */
+
+	VNCR(HFGRTR_EL2),
+	VNCR(HFGWTR_EL2),
+	VNCR(HFGITR_EL2),
+	VNCR(HDFGRTR_EL2),
+	VNCR(HDFGWTR_EL2),
+
+	VNCR(CNTVOFF_EL2),
+	VNCR(CNTV_CVAL_EL0),
+	VNCR(CNTV_CTL_EL0),
+	VNCR(CNTP_CVAL_EL0),
+	VNCR(CNTP_CTL_EL0),
+
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 
@@ -465,6 +486,9 @@ struct kvm_cpu_context {
 	u64 sys_regs[NR_SYS_REGS];
 
 	struct kvm_vcpu *__hyp_running_vcpu;
+
+	/* This pointer has to be 4kB aligned. */
+	u64 *vncr_array;
 };
 
 struct kvm_host_data {
@@ -827,8 +851,19 @@ struct kvm_vcpu_arch {
  * accessed by a running VCPU.  For example, for userspace access or
  * for system registers that are never context switched, but only
  * emulated.
+ *
+ * Don't bother with VNCR-based accesses in the nVHE code, it has no
+ * business dealing with NV.
  */
-#define __ctxt_sys_reg(c,r)	(&(c)->sys_regs[(r)])
+static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
+{
+#if !defined (__KVM_NVHE_HYPERVISOR__)
+	if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
+		     r >= __VNCR_START__ && ctxt->vncr_array))
+		return &ctxt->vncr_array[r - __VNCR_START__];
+#endif
+	return (u64 *)&ctxt->sys_regs[r];
+}
 
 #define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
 
-- 
GitLab


From fedc612314acfebf506e071bf3a941076aa56d10 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 17 Dec 2022 13:28:40 +0000
Subject: [PATCH 1603/4076] KVM: arm64: nv: Handle virtual EL2 registers in
 vcpu_read/write_sys_reg()

KVM internally uses accessor functions when reading or writing the
guest's system registers. This takes care of accessing either the stored
copy or using the "live" EL1 system registers when the host uses VHE.

With the introduction of virtual EL2 we add a bunch of EL2 system
registers, which now must also be taken care of:

- If the guest is running in vEL2, and we access an EL1 sysreg, we must
  revert to the stored version of that, and not use the CPU's copy.

- If the guest is running in vEL1, and we access an EL2 sysreg, we must
  also use the stored version, since the CPU carries the EL1 copy.

- Some EL2 system registers are supposed to affect the current execution
  of the system, so we need to put them into their respective EL1
  counterparts. For this we need to define a mapping between the two.

- Some EL2 system registers have a different format than their EL1
  counterpart, so we need to translate them before writing them to the
  CPU. This is done using an (optional) translate function in the map.

All of these cases are now wrapped into the existing accessor functions,
so KVM users wouldn't need to care whether they access EL2 or EL1
registers and also which state the guest is in.

Reviewed-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Co-developed-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |   2 +
 arch/arm64/kvm/sys_regs.c         | 129 ++++++++++++++++++++++++++++--
 2 files changed, 126 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 9e8cd2bb95c3f..f17fb7c42973d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -907,6 +907,7 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
 	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
 	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
+	case SPSR_EL1:		*val = read_sysreg_s(SYS_SPSR_EL12);	break;
 	case PAR_EL1:		*val = read_sysreg_par();		break;
 	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
@@ -951,6 +952,7 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
 	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
 	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
+	case SPSR_EL1:		write_sysreg_s(val, SYS_SPSR_EL12);	break;
 	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
 	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 7fef170ec67b7..3198542dcded6 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -72,24 +72,143 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 			"sys_reg write to read-only register");
 }
 
+#define PURE_EL2_SYSREG(el2)						\
+	case el2: {							\
+		*el1r = el2;						\
+		return true;						\
+	}
+
+#define MAPPED_EL2_SYSREG(el2, el1, fn)					\
+	case el2: {							\
+		*xlate = fn;						\
+		*el1r = el1;						\
+		return true;						\
+	}
+
+static bool get_el2_to_el1_mapping(unsigned int reg,
+				   unsigned int *el1r, u64 (**xlate)(u64))
+{
+	switch (reg) {
+		PURE_EL2_SYSREG(  VPIDR_EL2	);
+		PURE_EL2_SYSREG(  VMPIDR_EL2	);
+		PURE_EL2_SYSREG(  ACTLR_EL2	);
+		PURE_EL2_SYSREG(  HCR_EL2	);
+		PURE_EL2_SYSREG(  MDCR_EL2	);
+		PURE_EL2_SYSREG(  HSTR_EL2	);
+		PURE_EL2_SYSREG(  HACR_EL2	);
+		PURE_EL2_SYSREG(  VTTBR_EL2	);
+		PURE_EL2_SYSREG(  VTCR_EL2	);
+		PURE_EL2_SYSREG(  RVBAR_EL2	);
+		PURE_EL2_SYSREG(  TPIDR_EL2	);
+		PURE_EL2_SYSREG(  HPFAR_EL2	);
+		PURE_EL2_SYSREG(  CNTHCTL_EL2	);
+		MAPPED_EL2_SYSREG(SCTLR_EL2,   SCTLR_EL1,
+				  translate_sctlr_el2_to_sctlr_el1	     );
+		MAPPED_EL2_SYSREG(CPTR_EL2,    CPACR_EL1,
+				  translate_cptr_el2_to_cpacr_el1	     );
+		MAPPED_EL2_SYSREG(TTBR0_EL2,   TTBR0_EL1,
+				  translate_ttbr0_el2_to_ttbr0_el1	     );
+		MAPPED_EL2_SYSREG(TTBR1_EL2,   TTBR1_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(TCR_EL2,     TCR_EL1,
+				  translate_tcr_el2_to_tcr_el1		     );
+		MAPPED_EL2_SYSREG(VBAR_EL2,    VBAR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(AFSR0_EL2,   AFSR0_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(AFSR1_EL2,   AFSR1_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(ESR_EL2,     ESR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(FAR_EL2,     FAR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(MAIR_EL2,    MAIR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(AMAIR_EL2,   AMAIR_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(ELR_EL2,     ELR_EL1,	    NULL	     );
+		MAPPED_EL2_SYSREG(SPSR_EL2,    SPSR_EL1,    NULL	     );
+	default:
+		return false;
+	}
+}
+
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
 	u64 val = 0x8badf00d8badf00d;
+	u64 (*xlate)(u64) = NULL;
+	unsigned int el1r;
+
+	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
+		goto memory_read;
 
-	if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-	    __vcpu_read_sys_reg_from_cpu(reg, &val))
+	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
+		if (!is_hyp_ctxt(vcpu))
+			goto memory_read;
+
+		/*
+		 * If this register does not have an EL1 counterpart,
+		 * then read the stored EL2 version.
+		 */
+		if (reg == el1r)
+			goto memory_read;
+
+		/*
+		 * If we have a non-VHE guest and that the sysreg
+		 * requires translation to be used at EL1, use the
+		 * in-memory copy instead.
+		 */
+		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
+			goto memory_read;
+
+		/* Get the current version of the EL1 counterpart. */
+		WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val));
+		return val;
+	}
+
+	/* EL1 register can't be on the CPU if the guest is in vEL2. */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		goto memory_read;
+
+	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
 		return val;
 
+memory_read:
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 {
-	if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-	    __vcpu_write_sys_reg_to_cpu(val, reg))
+	u64 (*xlate)(u64) = NULL;
+	unsigned int el1r;
+
+	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
+		goto memory_write;
+
+	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
+		if (!is_hyp_ctxt(vcpu))
+			goto memory_write;
+
+		/*
+		 * Always store a copy of the write to memory to avoid having
+		 * to reverse-translate virtual EL2 system registers for a
+		 * non-VHE guest hypervisor.
+		 */
+		__vcpu_sys_reg(vcpu, reg) = val;
+
+		/* No EL1 counterpart? We're done here.? */
+		if (reg == el1r)
+			return;
+
+		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
+			val = xlate(val);
+
+		/* Redirect this to the EL1 version of the register. */
+		WARN_ON(!__vcpu_write_sys_reg_to_cpu(val, el1r));
+		return;
+	}
+
+	/* EL1 register can't be on the CPU if the guest is in vEL2. */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		goto memory_write;
+
+	if (__vcpu_write_sys_reg_to_cpu(val, reg))
 		return;
 
-	__vcpu_sys_reg(vcpu, reg) = val;
+memory_write:
+	 __vcpu_sys_reg(vcpu, reg) = val;
 }
 
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
-- 
GitLab


From 3bf7009251f0f41cdd0188ab7b3879df81810703 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 13 Dec 2023 11:15:27 -0500
Subject: [PATCH 1604/4076] tracing/selftests: Add test to test the
 trace_marker

Add a test that writes longs strings, some over the size of the sub buffer
and make sure that the entire content is there.

Link: https://lore.kernel.org/linux-trace-kernel/20231213111527.6a4c9b58@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 .../ftrace/test.d/00basic/trace_marker.tc     | 82 +++++++++++++++++++
 1 file changed, 82 insertions(+)
 create mode 100755 tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc

diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc
new file mode 100755
index 0000000000000..9aa0db2b84fc5
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc
@@ -0,0 +1,82 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Basic tests on writing to trace_marker
+# requires: trace_marker
+# flags: instance
+
+get_buffer_data_size() {
+	sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_buffer_data_offset() {
+	sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_event_header_size() {
+	type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	total_bits=$((type_len+time_len+array_len))
+	total_bits=$((total_bits+7))
+	echo $((total_bits/8))
+}
+
+get_print_event_buf_offset() {
+	sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format
+}
+
+event_header_size=`get_event_header_size`
+print_header_size=`get_print_event_buf_offset`
+
+data_offset=`get_buffer_data_offset`
+
+marker_meta=$((event_header_size+print_header_size))
+
+make_str() {
+        cnt=$1
+	# subtract two for \n\0 as marker adds these
+	cnt=$((cnt-2))
+	printf -- 'X%.0s' $(seq $cnt)
+}
+
+write_buffer() {
+	size=$1
+
+	str=`make_str $size`
+
+	# clear the buffer
+	echo > trace
+
+	# write the string into the marker
+	echo -n $str > trace_marker
+
+	echo $str
+}
+
+test_buffer() {
+
+	size=`get_buffer_data_size`
+	oneline_size=$((size-marker_meta))
+	echo size = $size
+	echo meta size = $marker_meta
+
+	# Now add a little more the meta data overhead will overflow
+
+	str=`write_buffer $size`
+
+	# Make sure the line was broken
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace`
+
+	if [ "$new_str" = "$str" ]; then
+		exit fail;
+	fi
+
+	# Make sure the entire line can be found
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace`
+
+	if [ "$new_str" != "$str" ]; then
+		exit fail;
+	fi
+}
+
+test_buffer
-- 
GitLab


From c84897c0ff5925090af0c6a8bf61424b71481764 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 07:43:03 -0500
Subject: [PATCH 1605/4076] ring-buffer: Remove 32bit timestamp logic

Each event has a 27 bit timestamp delta that is used to hold the delta
from the last event. If the time between events is greater than 2^27, then
a timestamp is added that holds a 59 bit absolute timestamp.

Until a389d86f7fd09 ("ring-buffer: Have nested events still record running
time stamp"), if an interrupt interrupted an event in progress, all the
events delta would be zero to not deal with the races that need to be
handled. The commit a389d86f7fd09 changed that to handle the races giving
all events, even those that preempt other events, still have an accurate
timestamp.

To handle those races requires performing 64-bit cmpxchg on the
timestamps. But doing 64-bit cmpxchg on 32-bit architectures is considered
very slow. To try to deal with this the timestamp logic was broken into
two and then three 32-bit cmpxchgs, with the thought that two (or three)
32-bit cmpxchgs are still faster than a single 64-bit cmpxchg on 32-bit
architectures.

Part of the problem with this is that I didn't have any 32-bit
architectures to test on. After hitting several subtle bugs in this code,
an effort was made to try and see if three 32-bit cmpxchgs are indeed
faster than a single 64-bit. After a few people brushed off the dust of
their old 32-bit machines, tests were done, and even though 32-bit cmpxchg
was faster than a single 64-bit, it was in the order of 50% at best, not
300%.

After some more refactoring of the code, all 4 64-bit cmpxchg were removed:

 https://lore.kernel.org/linux-trace-kernel/20231211114420.36dde01b@gandalf.local.home
 https://lore.kernel.org/linux-trace-kernel/20231214222921.193037a7@gandalf.local.home
 https://lore.kernel.org/linux-trace-kernel/20231215081810.1f4f38fe@rorschach.local.home
 https://lore.kernel.org/linux-trace-kernel/20231218230712.3a76b081@gandalf.local.home/

With all the 64-bit cmpxchg removed, the complex 32-bit workaround can also be
removed.

The 32-bit and 64-bit logic is now exactly the same.

Link: https://lore.kernel.org/all/20231213214632.15047c40@gandalf.local.home/
Link: https://lore.kernel.org/linux-trace-kernel/20231219074303.28f9abda@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 176 ++-----------------------------------
 1 file changed, 9 insertions(+), 167 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 16b640d824f92..a4ada4f303c4b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -27,6 +27,7 @@
 #include <linux/cpu.h>
 #include <linux/oom.h>
 
+#include <asm/local64.h>
 #include <asm/local.h>
 
 /*
@@ -463,27 +464,9 @@ enum {
 	RB_CTX_MAX
 };
 
-#if BITS_PER_LONG == 32
-#define RB_TIME_32
-#endif
-
-/* To test on 64 bit machines */
-//#define RB_TIME_32
-
-#ifdef RB_TIME_32
-
-struct rb_time_struct {
-	local_t		cnt;
-	local_t		top;
-	local_t		bottom;
-	local_t		msb;
-};
-#else
-#include <asm/local64.h>
 struct rb_time_struct {
 	local64_t	time;
 };
-#endif
 typedef struct rb_time_struct rb_time_t;
 
 #define MAX_NEST	5
@@ -573,147 +556,14 @@ struct ring_buffer_iter {
 	int				missed_events;
 };
 
-#ifdef RB_TIME_32
-
-/*
- * On 32 bit machines, local64_t is very expensive. As the ring
- * buffer doesn't need all the features of a true 64 bit atomic,
- * on 32 bit, it uses these functions (64 still uses local64_t).
- *
- * For the ring buffer, 64 bit required operations for the time is
- * the following:
- *
- *  - Reads may fail if it interrupted a modification of the time stamp.
- *      It will succeed if it did not interrupt another write even if
- *      the read itself is interrupted by a write.
- *      It returns whether it was successful or not.
- *
- *  - Writes always succeed and will overwrite other writes and writes
- *      that were done by events interrupting the current write.
- *
- *  - A write followed by a read of the same time stamp will always succeed,
- *      but may not contain the same value.
- *
- *  - A cmpxchg will fail if it interrupted another write or cmpxchg.
- *      Other than that, it acts like a normal cmpxchg.
- *
- * The 60 bit time stamp is broken up by 30 bits in a top and bottom half
- *  (bottom being the least significant 30 bits of the 60 bit time stamp).
- *
- * The two most significant bits of each half holds a 2 bit counter (0-3).
- * Each update will increment this counter by one.
- * When reading the top and bottom, if the two counter bits match then the
- *  top and bottom together make a valid 60 bit number.
- */
-#define RB_TIME_SHIFT	30
-#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
-#define RB_TIME_MSB_SHIFT	 60
-
-static inline int rb_time_cnt(unsigned long val)
-{
-	return (val >> RB_TIME_SHIFT) & 3;
-}
-
-static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
-{
-	u64 val;
-
-	val = top & RB_TIME_VAL_MASK;
-	val <<= RB_TIME_SHIFT;
-	val |= bottom & RB_TIME_VAL_MASK;
-
-	return val;
-}
-
-static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
-{
-	unsigned long top, bottom, msb;
-	unsigned long c;
-
-	/*
-	 * If the read is interrupted by a write, then the cnt will
-	 * be different. Loop until both top and bottom have been read
-	 * without interruption.
-	 */
-	do {
-		c = local_read(&t->cnt);
-		top = local_read(&t->top);
-		bottom = local_read(&t->bottom);
-		msb = local_read(&t->msb);
-	} while (c != local_read(&t->cnt));
-
-	*cnt = rb_time_cnt(top);
-
-	/* If top, msb or bottom counts don't match, this interrupted a write */
-	if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
-		return false;
-
-	/* The shift to msb will lose its cnt bits */
-	*ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT);
-	return true;
-}
-
-static bool rb_time_read(rb_time_t *t, u64 *ret)
-{
-	unsigned long cnt;
-
-	return __rb_time_read(t, ret, &cnt);
-}
-
-static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt)
-{
-	return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT);
-}
-
-static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom,
-				 unsigned long *msb)
-{
-	*top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
-	*bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
-	*msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT);
-}
-
-static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
-{
-	val = rb_time_val_cnt(val, cnt);
-	local_set(t, val);
-}
-
-static void rb_time_set(rb_time_t *t, u64 val)
-{
-	unsigned long cnt, top, bottom, msb;
-
-	rb_time_split(val, &top, &bottom, &msb);
-
-	/* Writes always succeed with a valid number even if it gets interrupted. */
-	do {
-		cnt = local_inc_return(&t->cnt);
-		rb_time_val_set(&t->top, top, cnt);
-		rb_time_val_set(&t->bottom, bottom, cnt);
-		rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt);
-	} while (cnt != local_read(&t->cnt));
-}
-
-static inline bool
-rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
-{
-	return local_try_cmpxchg(l, &expect, set);
-}
-
-#else /* 64 bits */
-
-/* local64_t always succeeds */
-
-static inline bool rb_time_read(rb_time_t *t, u64 *ret)
+static inline void rb_time_read(rb_time_t *t, u64 *ret)
 {
 	*ret = local64_read(&t->time);
-	return true;
 }
 static void rb_time_set(rb_time_t *t, u64 val)
 {
 	local64_set(&t->time, val);
 }
-#endif
 
 /*
  * Enable this to make sure that the event passed to
@@ -820,10 +670,7 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
 	WARN_ONCE(1, "nest (%d) greater than max", nest);
 
  fail:
-	/* Can only fail on 32 bit */
-	if (!rb_time_read(&cpu_buffer->write_stamp, &ts))
-		/* Screw it, just read the current time */
-		ts = rb_time_stamp(cpu_buffer->buffer);
+	rb_time_read(&cpu_buffer->write_stamp, &ts);
 
 	return ts;
 }
@@ -2820,7 +2667,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
 		  (unsigned long long)info->ts,
 		  (unsigned long long)info->before,
 		  (unsigned long long)info->after,
-		  (unsigned long long)(rb_time_read(&cpu_buffer->write_stamp, &write_stamp) ? write_stamp : 0),
+		  (unsigned long long)({rb_time_read(&cpu_buffer->write_stamp, &write_stamp); write_stamp;}),
 		  sched_clock_stable() ? "" :
 		  "If you just came from a suspend/resume,\n"
 		  "please switch to the trace global clock:\n"
@@ -3497,16 +3344,14 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	struct ring_buffer_event *event;
 	struct buffer_page *tail_page;
 	unsigned long tail, write, w;
-	bool a_ok;
-	bool b_ok;
 
 	/* Don't let the compiler play games with cpu_buffer->tail_page */
 	tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page);
 
  /*A*/	w = local_read(&tail_page->write) & RB_WRITE_MASK;
 	barrier();
-	b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-	a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+	rb_time_read(&cpu_buffer->before_stamp, &info->before);
+	rb_time_read(&cpu_buffer->write_stamp, &info->after);
 	barrier();
 	info->ts = rb_time_stamp(cpu_buffer->buffer);
 
@@ -3521,7 +3366,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		if (!w) {
 			/* Use the sub-buffer timestamp */
 			info->delta = 0;
-		} else if (unlikely(!a_ok || !b_ok || info->before != info->after)) {
+		} else if (unlikely(info->before != info->after)) {
 			info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
 			info->length += RB_LEN_TIME_EXTEND;
 		} else {
@@ -3570,8 +3415,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		/* SLOW PATH - Interrupted between A and C */
 
 		/* Save the old before_stamp */
-		a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-		RB_WARN_ON(cpu_buffer, !a_ok);
+		rb_time_read(&cpu_buffer->before_stamp, &info->before);
 
 		/*
 		 * Read a new timestamp and update the before_stamp to make
@@ -3583,9 +3427,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		rb_time_set(&cpu_buffer->before_stamp, ts);
 
 		barrier();
- /*E*/		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-		/* Was interrupted before here, write_stamp must be valid */
-		RB_WARN_ON(cpu_buffer, !a_ok);
+ /*E*/		rb_time_read(&cpu_buffer->write_stamp, &info->after);
 		barrier();
  /*F*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
 		    info->after == info->before && info->after < ts) {
-- 
GitLab


From d40dbb617ae9a8fe57343b26b4ad2bd7bb05c130 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 07:45:42 -0500
Subject: [PATCH 1606/4076] ring-buffer: Add interrupt information to dump of
 data sub-buffer

When the ring buffer timestamp verifier triggers, it dumps the content of
the sub-buffer. But currently it only dumps the timestamps and the offset
of the data as well as the deltas. It would be even more informative if
the event data also showed the interrupt context level it was in.

That is, if each event showed that the event was written in normal,
softirq, irq or NMI context. Then a better idea about how the events may
have been interrupted from each other.

As the payload of the ring buffer is really a black box of the ring
buffer, just assume that if the payload is larger than a trace entry, that
it is a trace entry. As trace entries have the interrupt context
information saved in a flags field, look at that location and report the
output of the flags.

If the payload is not a trace entry, there's no way to really know, and
the information will be garbage. But that's OK, because this is for
debugging only (this output is not used in production as the buffer check
that calls it causes a huge overhead to the tracing). This information,
when available, is crucial for debugging timestamp issues. If it's
garbage, it will also be pretty obvious that its garbage too.

As this output usually happens in kselftests of the tracing code, the user
will know what the payload is at the time.

Link: https://lore.kernel.org/linux-trace-kernel/20231219074542.6f304601@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Suggested-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 79 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 75 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a4ada4f303c4b..c0cc45482e1e7 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3185,6 +3185,76 @@ EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 #define CHECK_FULL_PAGE		1L
 
 #ifdef CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS
+
+static const char *show_irq_str(int bits)
+{
+	const char *type[] = {
+		".",	// 0
+		"s",	// 1
+		"h",	// 2
+		"Hs",	// 3
+		"n",	// 4
+		"Ns",	// 5
+		"Nh",	// 6
+		"NHs",	// 7
+	};
+
+	return type[bits];
+}
+
+/* Assume this is an trace event */
+static const char *show_flags(struct ring_buffer_event *event)
+{
+	struct trace_entry *entry;
+	int bits = 0;
+
+	if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry))
+		return "X";
+
+	entry = ring_buffer_event_data(event);
+
+	if (entry->flags & TRACE_FLAG_SOFTIRQ)
+		bits |= 1;
+
+	if (entry->flags & TRACE_FLAG_HARDIRQ)
+		bits |= 2;
+
+	if (entry->flags & TRACE_FLAG_NMI)
+		bits |= 4;
+
+	return show_irq_str(bits);
+}
+
+static const char *show_irq(struct ring_buffer_event *event)
+{
+	struct trace_entry *entry;
+
+	if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry))
+		return "";
+
+	entry = ring_buffer_event_data(event);
+	if (entry->flags & TRACE_FLAG_IRQS_OFF)
+		return "d";
+	return "";
+}
+
+static const char *show_interrupt_level(void)
+{
+	unsigned long pc = preempt_count();
+	unsigned char level = 0;
+
+	if (pc & SOFTIRQ_OFFSET)
+		level |= 1;
+
+	if (pc & HARDIRQ_MASK)
+		level |= 2;
+
+	if (pc & NMI_MASK)
+		level |= 4;
+
+	return show_irq_str(level);
+}
+
 static void dump_buffer_page(struct buffer_data_page *bpage,
 			     struct rb_event_info *info,
 			     unsigned long tail)
@@ -3224,8 +3294,9 @@ static void dump_buffer_page(struct buffer_data_page *bpage,
 
 		case RINGBUF_TYPE_DATA:
 			ts += event->time_delta;
-			pr_warn(" 0x%x:  [%lld] delta:%d\n",
-				e, ts, event->time_delta);
+			pr_warn(" 0x%x:  [%lld] delta:%d %s%s\n",
+				e, ts, event->time_delta,
+				show_flags(event), show_irq(event));
 			break;
 
 		default:
@@ -3316,11 +3387,11 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 		atomic_inc(&cpu_buffer->record_disabled);
 		/* There's some cases in boot up that this can happen */
 		WARN_ON_ONCE(system_state != SYSTEM_BOOTING);
-		pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s\n",
+		pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s context:%s\n",
 			cpu_buffer->cpu,
 			ts + info->delta, info->ts, info->delta,
 			info->before, info->after,
-			full ? " (full)" : "");
+			full ? " (full)" : "", show_interrupt_level());
 		dump_buffer_page(bpage, info, tail);
 		atomic_dec(&ts_dump);
 		/* Do not re-enable checking */
-- 
GitLab


From f50345b49b16f7fe6dbebbec065b9248c38556ff Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 07:47:32 -0500
Subject: [PATCH 1607/4076] ring-buffer: Check if absolute timestamp goes
 backwards

The check_buffer() which checks the timestamps of the ring buffer
sub-buffer page, when enabled, only checks if the adding of deltas of the
events from the last absolute timestamp or the timestamp of the sub-buffer
page adds up to the current event.

What it does not check is if the absolute timestamp causes the time of the
events to go backwards, as that can cause issues elsewhere.

Test for the timestamp going backwards too.

This also fixes a slight issue where if the warning triggers at boot up
(because of the resetting of the tsc), it will disable all further checks,
even those that are after boot Have it continue checking if the warning
was ignored during boot up.

Link: https://lore.kernel.org/linux-trace-kernel/20231219074732.18b092d4@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 46 +++++++++++++++++++++++---------------
 1 file changed, 28 insertions(+), 18 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c0cc45482e1e7..f7dc74e45ebfa 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3309,6 +3309,23 @@ static void dump_buffer_page(struct buffer_data_page *bpage,
 static DEFINE_PER_CPU(atomic_t, checking);
 static atomic_t ts_dump;
 
+#define buffer_warn_return(fmt, ...)					\
+	do {								\
+		/* If another report is happening, ignore this one */	\
+		if (atomic_inc_return(&ts_dump) != 1) {			\
+			atomic_dec(&ts_dump);				\
+			goto out;					\
+		}							\
+		atomic_inc(&cpu_buffer->record_disabled);		\
+		pr_warn(fmt, ##__VA_ARGS__);				\
+		dump_buffer_page(bpage, info, tail);			\
+		atomic_dec(&ts_dump);					\
+		/* There's some cases in boot up that this can happen */ \
+		if (WARN_ON_ONCE(system_state != SYSTEM_BOOTING))	\
+			/* Do not re-enable checking */			\
+			return;						\
+	} while (0)
+
 /*
  * Check if the current event time stamp matches the deltas on
  * the buffer page.
@@ -3362,7 +3379,12 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
-			ts = rb_fix_abs_ts(delta, ts);
+			delta = rb_fix_abs_ts(delta, ts);
+			if (delta < ts) {
+				buffer_warn_return("[CPU: %d]ABSOLUTE TIME WENT BACKWARDS: last ts: %lld absolute ts: %lld\n",
+						   cpu_buffer->cpu, ts, delta);
+			}
+			ts = delta;
 			break;
 
 		case RINGBUF_TYPE_PADDING:
@@ -3379,23 +3401,11 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 	}
 	if ((full && ts > info->ts) ||
 	    (!full && ts + info->delta != info->ts)) {
-		/* If another report is happening, ignore this one */
-		if (atomic_inc_return(&ts_dump) != 1) {
-			atomic_dec(&ts_dump);
-			goto out;
-		}
-		atomic_inc(&cpu_buffer->record_disabled);
-		/* There's some cases in boot up that this can happen */
-		WARN_ON_ONCE(system_state != SYSTEM_BOOTING);
-		pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s context:%s\n",
-			cpu_buffer->cpu,
-			ts + info->delta, info->ts, info->delta,
-			info->before, info->after,
-			full ? " (full)" : "", show_interrupt_level());
-		dump_buffer_page(bpage, info, tail);
-		atomic_dec(&ts_dump);
-		/* Do not re-enable checking */
-		return;
+		buffer_warn_return("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s context:%s\n",
+				   cpu_buffer->cpu,
+				   ts + info->delta, info->ts, info->delta,
+				   info->before, info->after,
+				   full ? " (full)" : "", show_interrupt_level());
 	}
 out:
 	atomic_dec(this_cpu_ptr(&checking));
-- 
GitLab


From 1903ef8f0d77680e6eb36bd0cc3ea3aa6e95a050 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Dec 2023 15:34:42 +0800
Subject: [PATCH 1608/4076] iommu/vt-d: Refactor device_to_iommu() to retrieve
 iommu directly

The device_to_iommu() helper was originally designed to look up the DMAR
ACPI table to retrieve the iommu device and the request ID for a given
device. However, it was also being used in other places where there was
no need to lookup the ACPI table at all.

Retrieve the iommu device directly from the per-device iommu private data
in functions called after device is probed.

Rename the original device_to_iommu() function to a more meaningful name,
device_lookup_iommu(), to avoid mis-using it.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20231116015048.29675-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 30 ++++++++++--------------------
 drivers/iommu/intel/iommu.h |  1 -
 drivers/iommu/intel/svm.c   | 20 +++-----------------
 3 files changed, 13 insertions(+), 38 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 3531b956556c7..3b25b36bb9c73 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -703,7 +703,7 @@ static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev)
 	return false;
 }
 
-struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
+static struct intel_iommu *device_lookup_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
 	struct pci_dev *pdev = NULL;
@@ -2081,14 +2081,11 @@ static int domain_context_mapping_cb(struct pci_dev *pdev,
 static int
 domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct domain_context_mapping_data data;
+	struct intel_iommu *iommu = info->iommu;
+	u8 bus = info->bus, devfn = info->devfn;
 	struct pasid_table *table;
-	struct intel_iommu *iommu;
-	u8 bus, devfn;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
 
 	table = intel_pasid_get_table(dev);
 
@@ -2447,15 +2444,10 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 				     struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu;
+	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
-	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
 	ret = domain_attach_iommu(domain, iommu);
 	if (ret)
 		return ret;
@@ -4116,14 +4108,11 @@ static void intel_iommu_domain_free(struct iommu_domain *domain)
 int prepare_domain_attach_device(struct iommu_domain *domain,
 				 struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct intel_iommu *iommu;
+	struct intel_iommu *iommu = info->iommu;
 	int addr_width;
 
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return -ENODEV;
-
 	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
 		return -EINVAL;
 
@@ -4399,7 +4388,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_lookup_iommu(dev, &bus, &devfn);
 	if (!iommu || !iommu->iommu.ops)
 		return ERR_PTR(-ENODEV);
 
@@ -4735,8 +4724,9 @@ static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 
 static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 {
-	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dev_pasid_info *curr, *dev_pasid = NULL;
+	struct intel_iommu *iommu = info->iommu;
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
 	unsigned long flags;
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 65d37a138c75d..f8f956ce43c52 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -897,7 +897,6 @@ int dmar_ir_support(void);
 void *alloc_pgtable_page(int node, gfp_t gfp);
 void free_pgtable_page(void *vaddr);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
-struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 					       const struct iommu_user_data *user_data);
 
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 50a481c895b86..cc138e3ed4a6b 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -366,14 +366,9 @@ free_svm:
 void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid)
 {
 	struct intel_svm_dev *sdev;
-	struct intel_iommu *iommu;
 	struct intel_svm *svm;
 	struct mm_struct *mm;
 
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return;
-
 	if (pasid_to_svm_sdev(dev, pasid, &svm, &sdev))
 		return;
 	mm = svm->mm;
@@ -724,25 +719,16 @@ int intel_svm_page_response(struct device *dev,
 			    struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	u8 bus = info->bus, devfn = info->devfn;
 	struct iommu_fault_page_request *prm;
-	struct intel_iommu *iommu;
 	bool private_present;
 	bool pasid_present;
 	bool last_page;
-	u8 bus, devfn;
 	int ret = 0;
 	u16 sid;
 
-	if (!dev || !dev_is_pci(dev))
-		return -ENODEV;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
-	if (!msg || !evt)
-		return -EINVAL;
-
 	prm = &evt->fault.prm;
 	sid = PCI_DEVID(bus, devfn);
 	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
-- 
GitLab


From 47642bdd5a25cd46228221719af2902b583bd36c Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Dec 2023 15:34:43 +0800
Subject: [PATCH 1609/4076] iommu/vt-d: Remove unused parameter of
 intel_pasid_setup_pass_through()

The domain parameter of this helper is unused and can be deleted to avoid
dead code.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20231116015048.29675-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 5 ++---
 drivers/iommu/intel/pasid.c | 1 -
 drivers/iommu/intel/pasid.h | 1 -
 3 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 3b25b36bb9c73..cf4d13248bf28 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2460,7 +2460,7 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
 		/* Setup the PASID entry for requests without PASID: */
 		if (hw_pass_through && domain_type_is_si(domain))
-			ret = intel_pasid_setup_pass_through(iommu, domain,
+			ret = intel_pasid_setup_pass_through(iommu,
 					dev, IOMMU_NO_PASID);
 		else if (domain->use_first_level)
 			ret = domain_setup_first_level(iommu, domain, dev,
@@ -4797,8 +4797,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 		goto out_free;
 
 	if (domain_type_is_si(dmar_domain))
-		ret = intel_pasid_setup_pass_through(iommu, dmar_domain,
-						     dev, pasid);
+		ret = intel_pasid_setup_pass_through(iommu, dev, pasid);
 	else if (dmar_domain->use_first_level)
 		ret = domain_setup_first_level(iommu, dmar_domain,
 					       dev, pasid);
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 74e8e4c17e814..8a1bcabf71a93 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -767,7 +767,6 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
  * Set up the scalable mode pasid entry for passthrough translation type.
  */
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
-				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid)
 {
 	u16 did = FLPT_DEFAULT_DID;
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index dd37611175cc1..16265bc1f7ec6 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -111,7 +111,6 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
 				     struct device *dev, u32 pasid,
 				     bool enabled);
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
-				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid);
 int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 			     u32 pasid, struct dmar_domain *domain);
-- 
GitLab


From d2b66903464ec29e54ac0991fa43c0da2c2a4892 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Dec 2023 15:34:44 +0800
Subject: [PATCH 1610/4076] iommu/vt-d: Remove unused vcmd interfaces

Commit 99b5726b4423 ("iommu: Remove ioasid infrastructure") has removed
ioasid allocation interfaces from the iommu subsystem. As a result, these
vcmd interfaces have become obsolete. Remove them to avoid dead code.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20231116015048.29675-4-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/debugfs.c |  3 --
 drivers/iommu/intel/iommu.h   |  3 --
 drivers/iommu/intel/pasid.c   | 57 -----------------------------------
 drivers/iommu/intel/pasid.h   | 12 --------
 4 files changed, 75 deletions(-)

diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index dee61e513be6d..86b506af7daa1 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -106,9 +106,6 @@ static const struct iommu_regset iommu_regs_64[] = {
 	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK8),
 	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE9),
 	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK9),
-	IOMMU_REGSET_ENTRY(VCCAP),
-	IOMMU_REGSET_ENTRY(VCMD),
-	IOMMU_REGSET_ENTRY(VCRSP),
 };
 
 static struct dentry *intel_iommu_debug;
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index f8f956ce43c52..37ddbf03d0a40 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -140,9 +140,6 @@
 #define DMAR_ECEO_REG		0x408
 #define DMAR_ECRSP_REG		0x410
 #define DMAR_ECCAP_REG		0x430
-#define DMAR_VCCAP_REG		0xe30 /* Virtual command capability register */
-#define DMAR_VCMD_REG		0xe00 /* Virtual command register */
-#define DMAR_VCRSP_REG		0xe10 /* Virtual command response register */
 
 #define DMAR_IQER_REG_IQEI(reg)		FIELD_GET(GENMASK_ULL(3, 0), reg)
 #define DMAR_IQER_REG_ITESID(reg)	FIELD_GET(GENMASK_ULL(47, 32), reg)
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 8a1bcabf71a93..57ae716a2c70a 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -26,63 +26,6 @@
  */
 u32 intel_pasid_max_id = PASID_MAX;
 
-int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
-{
-	unsigned long flags;
-	u8 status_code;
-	int ret = 0;
-	u64 res;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flags);
-	dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC);
-	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
-		      !(res & VCMD_VRSP_IP), res);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
-
-	status_code = VCMD_VRSP_SC(res);
-	switch (status_code) {
-	case VCMD_VRSP_SC_SUCCESS:
-		*pasid = VCMD_VRSP_RESULT_PASID(res);
-		break;
-	case VCMD_VRSP_SC_NO_PASID_AVAIL:
-		pr_info("IOMMU: %s: No PASID available\n", iommu->name);
-		ret = -ENOSPC;
-		break;
-	default:
-		ret = -ENODEV;
-		pr_warn("IOMMU: %s: Unexpected error code %d\n",
-			iommu->name, status_code);
-	}
-
-	return ret;
-}
-
-void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
-{
-	unsigned long flags;
-	u8 status_code;
-	u64 res;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flags);
-	dmar_writeq(iommu->reg + DMAR_VCMD_REG,
-		    VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE);
-	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
-		      !(res & VCMD_VRSP_IP), res);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
-
-	status_code = VCMD_VRSP_SC(res);
-	switch (status_code) {
-	case VCMD_VRSP_SC_SUCCESS:
-		break;
-	case VCMD_VRSP_SC_INVALID_PASID:
-		pr_info("IOMMU: %s: Invalid PASID\n", iommu->name);
-		break;
-	default:
-		pr_warn("IOMMU: %s: Unexpected error code %d\n",
-			iommu->name, status_code);
-	}
-}
-
 /*
  * Per device pasid table management:
  */
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index 16265bc1f7ec6..00401cfc2a406 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -22,16 +22,6 @@
 #define is_pasid_enabled(entry)		(((entry)->lo >> 3) & 0x1)
 #define get_pasid_dir_size(entry)	(1 << ((((entry)->lo >> 9) & 0x7) + 7))
 
-/* Virtual command interface for enlightened pasid management. */
-#define VCMD_CMD_ALLOC			0x1
-#define VCMD_CMD_FREE			0x2
-#define VCMD_VRSP_IP			0x1
-#define VCMD_VRSP_SC(e)			(((e) & 0xff) >> 1)
-#define VCMD_VRSP_SC_SUCCESS		0
-#define VCMD_VRSP_SC_NO_PASID_AVAIL	16
-#define VCMD_VRSP_SC_INVALID_PASID	16
-#define VCMD_VRSP_RESULT_PASID(e)	(((e) >> 16) & 0xfffff)
-#define VCMD_CMD_OPERAND(e)		((e) << 16)
 /*
  * Domain ID reserved for pasid entries programmed for first-level
  * only and pass-through transfer modes.
@@ -117,8 +107,6 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 struct device *dev, u32 pasid,
 				 bool fault_ignore);
-int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
-void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
 void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
 					  struct device *dev, u32 pasid);
 #endif /* __INTEL_PASID_H */
-- 
GitLab


From 80b79e141da7251d6ea82573f058ee9418896465 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Dec 2023 15:34:45 +0800
Subject: [PATCH 1611/4076] iommu/vt-d: Move inline helpers to header files

Move inline helpers to header files so that other files can use them
without duplicating the code.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20231116015048.29675-5-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 204 ++--------------------------------
 drivers/iommu/intel/iommu.h | 175 +++++++++++++++++++++++++++++
 drivers/iommu/intel/pasid.c | 216 +-----------------------------------
 drivers/iommu/intel/pasid.h | 210 +++++++++++++++++++++++++++++++++++
 4 files changed, 400 insertions(+), 405 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index cf4d13248bf28..dc23a1a49c80f 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -46,9 +46,6 @@
 
 #define DEFAULT_DOMAIN_ADDRESS_WIDTH 57
 
-#define MAX_AGAW_WIDTH 64
-#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
-
 #define __DOMAIN_MAX_PFN(gaw)  ((((uint64_t)1) << ((gaw) - VTD_PAGE_SHIFT)) - 1)
 #define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << (gaw)) - 1)
 
@@ -63,74 +60,6 @@
 
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 
-/* page table handling */
-#define LEVEL_STRIDE		(9)
-#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
-
-static inline int agaw_to_level(int agaw)
-{
-	return agaw + 2;
-}
-
-static inline int agaw_to_width(int agaw)
-{
-	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
-}
-
-static inline int width_to_agaw(int width)
-{
-	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
-}
-
-static inline unsigned int level_to_offset_bits(int level)
-{
-	return (level - 1) * LEVEL_STRIDE;
-}
-
-static inline int pfn_level_offset(u64 pfn, int level)
-{
-	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
-}
-
-static inline u64 level_mask(int level)
-{
-	return -1ULL << level_to_offset_bits(level);
-}
-
-static inline u64 level_size(int level)
-{
-	return 1ULL << level_to_offset_bits(level);
-}
-
-static inline u64 align_to_level(u64 pfn, int level)
-{
-	return (pfn + level_size(level) - 1) & level_mask(level);
-}
-
-static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
-{
-	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
-}
-
-/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
-   are never going to work. */
-static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
-{
-	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
-}
-static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
-{
-	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
-}
-static inline unsigned long page_to_dma_pfn(struct page *pg)
-{
-	return mm_to_dma_pfn_start(page_to_pfn(pg));
-}
-static inline unsigned long virt_to_dma_pfn(void *p)
-{
-	return page_to_dma_pfn(virt_to_page(p));
-}
-
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
@@ -168,78 +97,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re)
 	return re->hi & VTD_PAGE_MASK;
 }
 
-static inline void context_set_present(struct context_entry *context)
-{
-	context->lo |= 1;
-}
-
-static inline void context_set_fault_enable(struct context_entry *context)
-{
-	context->lo &= (((u64)-1) << 2) | 1;
-}
-
-static inline void context_set_translation_type(struct context_entry *context,
-						unsigned long value)
-{
-	context->lo &= (((u64)-1) << 4) | 3;
-	context->lo |= (value & 3) << 2;
-}
-
-static inline void context_set_address_root(struct context_entry *context,
-					    unsigned long value)
-{
-	context->lo &= ~VTD_PAGE_MASK;
-	context->lo |= value & VTD_PAGE_MASK;
-}
-
-static inline void context_set_address_width(struct context_entry *context,
-					     unsigned long value)
-{
-	context->hi |= value & 7;
-}
-
-static inline void context_set_domain_id(struct context_entry *context,
-					 unsigned long value)
-{
-	context->hi |= (value & ((1 << 16) - 1)) << 8;
-}
-
-static inline void context_set_pasid(struct context_entry *context)
-{
-	context->lo |= CONTEXT_PASIDE;
-}
-
-static inline int context_domain_id(struct context_entry *c)
-{
-	return((c->hi >> 8) & 0xffff);
-}
-
-static inline void context_clear_entry(struct context_entry *context)
-{
-	context->lo = 0;
-	context->hi = 0;
-}
-
-static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	if (!iommu->copied_tables)
-		return false;
-
-	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
-static inline void
-set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
-static inline void
-clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
-
 /*
  * This domain is a statically identity mapping domain.
  *	1. This domain creats a static 1:1 mapping to all usable memory.
@@ -383,13 +240,12 @@ void free_pgtable_page(void *vaddr)
 	free_page((unsigned long)vaddr);
 }
 
-static inline int domain_type_is_si(struct dmar_domain *domain)
+static int domain_type_is_si(struct dmar_domain *domain)
 {
 	return domain->domain.type == IOMMU_DOMAIN_IDENTITY;
 }
 
-static inline int domain_pfn_supported(struct dmar_domain *domain,
-				       unsigned long pfn)
+static int domain_pfn_supported(struct dmar_domain *domain, unsigned long pfn)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 
@@ -451,7 +307,7 @@ int iommu_calculate_agaw(struct intel_iommu *iommu)
 	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 }
 
-static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
+static bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
 {
 	return sm_supported(iommu) ?
 			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
@@ -1574,9 +1430,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 }
 
 /* Notification for newly created mappings */
-static inline void __mapping_notify_one(struct intel_iommu *iommu,
-					struct dmar_domain *domain,
-					unsigned long pfn, unsigned int pages)
+static void __mapping_notify_one(struct intel_iommu *iommu, struct dmar_domain *domain,
+				 unsigned long pfn, unsigned int pages)
 {
 	/*
 	 * It's a non-present to present mapping. Only flush if caching mode
@@ -1843,7 +1698,7 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 	spin_unlock(&iommu->lock);
 }
 
-static inline int guestwidth_to_adjustwidth(int gaw)
+static int guestwidth_to_adjustwidth(int gaw)
 {
 	int agaw;
 	int r = (gaw - 12) % 9;
@@ -1877,7 +1732,7 @@ static void domain_exit(struct dmar_domain *domain)
  * Value of X in the PDTS field of a scalable mode context entry
  * indicates PASID directory with 2^(X + 7) entries.
  */
-static inline unsigned long context_get_sm_pds(struct pasid_table *table)
+static unsigned long context_get_sm_pds(struct pasid_table *table)
 {
 	unsigned long pds, max_pde;
 
@@ -1889,38 +1744,6 @@ static inline unsigned long context_get_sm_pds(struct pasid_table *table)
 	return pds - 7;
 }
 
-/*
- * Set the RID_PASID field of a scalable mode context entry. The
- * IOMMU hardware will use the PASID value set in this field for
- * DMA translations of DMA requests without PASID.
- */
-static inline void
-context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
-{
-	context->hi |= pasid & ((1 << 20) - 1);
-}
-
-/*
- * Set the DTE(Device-TLB Enable) field of a scalable mode context
- * entry.
- */
-static inline void context_set_sm_dte(struct context_entry *context)
-{
-	context->lo |= BIT_ULL(2);
-}
-
-/*
- * Set the PRE(Page Request Enable) field of a scalable mode context
- * entry.
- */
-static inline void context_set_sm_pre(struct context_entry *context)
-{
-	context->lo |= BIT_ULL(4);
-}
-
-/* Convert value to context PASID directory size field coding. */
-#define context_pdts(pds)	(((pds) & 0x7) << 9)
-
 static int domain_context_mapping_one(struct dmar_domain *domain,
 				      struct intel_iommu *iommu,
 				      struct pasid_table *table,
@@ -2102,18 +1925,15 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 }
 
 /* Returns a number of VTD pages, but aligned to MM page size */
-static inline unsigned long aligned_nrpages(unsigned long host_addr,
-					    size_t size)
+static unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
 {
 	host_addr &= ~PAGE_MASK;
 	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
 /* Return largest possible superpage level for a given mapping */
-static inline int hardware_largepage_caps(struct dmar_domain *domain,
-					  unsigned long iov_pfn,
-					  unsigned long phy_pfn,
-					  unsigned long pages)
+static int hardware_largepage_caps(struct dmar_domain *domain, unsigned long iov_pfn,
+				   unsigned long phy_pfn, unsigned long pages)
 {
 	int support, level = 1;
 	unsigned long pfnmerge;
@@ -3604,7 +3424,7 @@ void intel_iommu_shutdown(void)
 	up_write(&dmar_global_lock);
 }
 
-static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
+static struct intel_iommu *dev_to_intel_iommu(struct device *dev)
 {
 	struct iommu_device *iommu_dev = dev_to_iommu_device(dev);
 
@@ -3683,7 +3503,7 @@ const struct attribute_group *intel_iommu_groups[] = {
 	NULL,
 };
 
-static inline bool has_external_pci(void)
+static bool has_external_pci(void)
 {
 	struct pci_dev *pdev = NULL;
 
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 37ddbf03d0a40..0af1399836352 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -848,6 +848,181 @@ static inline bool context_present(struct context_entry *context)
 	return (context->lo & 1);
 }
 
+#define LEVEL_STRIDE		(9)
+#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
+#define MAX_AGAW_WIDTH		(64)
+#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
+
+static inline int agaw_to_level(int agaw)
+{
+	return agaw + 2;
+}
+
+static inline int agaw_to_width(int agaw)
+{
+	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
+}
+
+static inline int width_to_agaw(int width)
+{
+	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
+}
+
+static inline unsigned int level_to_offset_bits(int level)
+{
+	return (level - 1) * LEVEL_STRIDE;
+}
+
+static inline int pfn_level_offset(u64 pfn, int level)
+{
+	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
+}
+
+static inline u64 level_mask(int level)
+{
+	return -1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 level_size(int level)
+{
+	return 1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 align_to_level(u64 pfn, int level)
+{
+	return (pfn + level_size(level) - 1) & level_mask(level);
+}
+
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
+}
+
+/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
+   are never going to work. */
+static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
+{
+	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
+}
+static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
+{
+	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
+}
+static inline unsigned long page_to_dma_pfn(struct page *pg)
+{
+	return mm_to_dma_pfn_start(page_to_pfn(pg));
+}
+static inline unsigned long virt_to_dma_pfn(void *p)
+{
+	return page_to_dma_pfn(virt_to_page(p));
+}
+
+static inline void context_set_present(struct context_entry *context)
+{
+	context->lo |= 1;
+}
+
+static inline void context_set_fault_enable(struct context_entry *context)
+{
+	context->lo &= (((u64)-1) << 2) | 1;
+}
+
+static inline void context_set_translation_type(struct context_entry *context,
+						unsigned long value)
+{
+	context->lo &= (((u64)-1) << 4) | 3;
+	context->lo |= (value & 3) << 2;
+}
+
+static inline void context_set_address_root(struct context_entry *context,
+					    unsigned long value)
+{
+	context->lo &= ~VTD_PAGE_MASK;
+	context->lo |= value & VTD_PAGE_MASK;
+}
+
+static inline void context_set_address_width(struct context_entry *context,
+					     unsigned long value)
+{
+	context->hi |= value & 7;
+}
+
+static inline void context_set_domain_id(struct context_entry *context,
+					 unsigned long value)
+{
+	context->hi |= (value & ((1 << 16) - 1)) << 8;
+}
+
+static inline void context_set_pasid(struct context_entry *context)
+{
+	context->lo |= CONTEXT_PASIDE;
+}
+
+static inline int context_domain_id(struct context_entry *c)
+{
+	return((c->hi >> 8) & 0xffff);
+}
+
+static inline void context_clear_entry(struct context_entry *context)
+{
+	context->lo = 0;
+	context->hi = 0;
+}
+
+#ifdef CONFIG_INTEL_IOMMU
+static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu->copied_tables)
+		return false;
+
+	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+#endif /* CONFIG_INTEL_IOMMU */
+
+/*
+ * Set the RID_PASID field of a scalable mode context entry. The
+ * IOMMU hardware will use the PASID value set in this field for
+ * DMA translations of DMA requests without PASID.
+ */
+static inline void
+context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
+{
+	context->hi |= pasid & ((1 << 20) - 1);
+}
+
+/*
+ * Set the DTE(Device-TLB Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_dte(struct context_entry *context)
+{
+	context->lo |= BIT_ULL(2);
+}
+
+/*
+ * Set the PRE(Page Request Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_pre(struct context_entry *context)
+{
+	context->lo |= BIT_ULL(4);
+}
+
+/* Convert value to context PASID directory size field coding. */
+#define context_pdts(pds)	(((pds) & 0x7) << 9)
+
 struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev);
 
 int dmar_enable_qi(struct intel_iommu *iommu);
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 57ae716a2c70a..3239cefa4c337 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -173,30 +173,6 @@ retry:
 /*
  * Interfaces for PASID table entry manipulation:
  */
-static inline void pasid_clear_entry(struct pasid_entry *pe)
-{
-	WRITE_ONCE(pe->val[0], 0);
-	WRITE_ONCE(pe->val[1], 0);
-	WRITE_ONCE(pe->val[2], 0);
-	WRITE_ONCE(pe->val[3], 0);
-	WRITE_ONCE(pe->val[4], 0);
-	WRITE_ONCE(pe->val[5], 0);
-	WRITE_ONCE(pe->val[6], 0);
-	WRITE_ONCE(pe->val[7], 0);
-}
-
-static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
-{
-	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
-	WRITE_ONCE(pe->val[1], 0);
-	WRITE_ONCE(pe->val[2], 0);
-	WRITE_ONCE(pe->val[3], 0);
-	WRITE_ONCE(pe->val[4], 0);
-	WRITE_ONCE(pe->val[5], 0);
-	WRITE_ONCE(pe->val[6], 0);
-	WRITE_ONCE(pe->val[7], 0);
-}
-
 static void
 intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 {
@@ -212,192 +188,6 @@ intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 		pasid_clear_entry(pe);
 }
 
-static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
-{
-	u64 old;
-
-	old = READ_ONCE(*ptr);
-	WRITE_ONCE(*ptr, (old & ~mask) | bits);
-}
-
-static inline u64 pasid_get_bits(u64 *ptr)
-{
-	return READ_ONCE(*ptr);
-}
-
-/*
- * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
- * PASID entry.
- */
-static inline void
-pasid_set_domain_id(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
-}
-
-/*
- * Get domain ID value of a scalable mode PASID entry.
- */
-static inline u16
-pasid_get_domain_id(struct pasid_entry *pe)
-{
-	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
-}
-
-/*
- * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_slptr(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
-}
-
-/*
- * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
- * entry.
- */
-static inline void
-pasid_set_address_width(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
-}
-
-/*
- * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_translation_type(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
-}
-
-/*
- * Enable fault processing by clearing the FPD(Fault Processing
- * Disable) field (Bit 1) of a scalable mode PASID entry.
- */
-static inline void pasid_set_fault_enable(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 1, 0);
-}
-
-/*
- * Enable second level A/D bits by setting the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_ssade(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9);
-}
-
-/*
- * Disable second level A/D bits by clearing the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_clear_ssade(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 9, 0);
-}
-
-/*
- * Checks if second level A/D bits specifically the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry is set.
- */
-static inline bool pasid_get_ssade(struct pasid_entry *pe)
-{
-	return pasid_get_bits(&pe->val[0]) & (1 << 9);
-}
-
-/*
- * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_sre(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 0, 1);
-}
-
-/*
- * Setup the WPE(Write Protect Enable) field (Bit 132) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_wpe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
-}
-
-/*
- * Setup the P(Present) field (Bit 0) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_present(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 0, 1);
-}
-
-/*
- * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
-{
-	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
-}
-
-/*
- * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
- * entry. It is required when XD bit of the first level page table
- * entry is about to be set.
- */
-static inline void pasid_set_nxe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
-}
-
-/*
- * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
- * PASID entry.
- */
-static inline void
-pasid_set_pgsnp(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
-}
-
-/*
- * Setup the First Level Page table Pointer field (Bit 140~191)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_flptr(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
-}
-
-/*
- * Setup the First Level Paging Mode field (Bit 130~131) of a
- * scalable mode PASID entry.
- */
-static inline void
-pasid_set_flpm(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
-}
-
-/*
- * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
- * of a scalable mode PASID entry.
- */
-static inline void pasid_set_eafe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
-}
-
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 				    u16 did, u32 pasid)
@@ -556,9 +346,9 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
  * Skip top levels of page tables for iommu which has less agaw
  * than default. Unnecessary for PT mode.
  */
-static inline int iommu_skip_agaw(struct dmar_domain *domain,
-				  struct intel_iommu *iommu,
-				  struct dma_pte **pgd)
+static int iommu_skip_agaw(struct dmar_domain *domain,
+			   struct intel_iommu *iommu,
+			   struct dma_pte **pgd)
 {
 	int agaw;
 
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index 00401cfc2a406..8d40d4c66e319 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -86,6 +86,216 @@ static inline u16 pasid_pte_get_pgtt(struct pasid_entry *pte)
 	return (u16)((READ_ONCE(pte->val[0]) >> 6) & 0x7);
 }
 
+static inline void pasid_clear_entry(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], 0);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
+{
+	u64 old;
+
+	old = READ_ONCE(*ptr);
+	WRITE_ONCE(*ptr, (old & ~mask) | bits);
+}
+
+static inline u64 pasid_get_bits(u64 *ptr)
+{
+	return READ_ONCE(*ptr);
+}
+
+/*
+ * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_domain_id(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
+}
+
+/*
+ * Get domain ID value of a scalable mode PASID entry.
+ */
+static inline u16
+pasid_get_domain_id(struct pasid_entry *pe)
+{
+	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
+}
+
+/*
+ * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_slptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
+ * entry.
+ */
+static inline void
+pasid_set_address_width(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
+}
+
+/*
+ * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_translation_type(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
+}
+
+/*
+ * Enable fault processing by clearing the FPD(Fault Processing
+ * Disable) field (Bit 1) of a scalable mode PASID entry.
+ */
+static inline void pasid_set_fault_enable(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 1, 0);
+}
+
+/*
+ * Enable second level A/D bits by setting the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_ssade(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9);
+}
+
+/*
+ * Disable second level A/D bits by clearing the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_clear_ssade(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 9, 0);
+}
+
+/*
+ * Checks if second level A/D bits specifically the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry is set.
+ */
+static inline bool pasid_get_ssade(struct pasid_entry *pe)
+{
+	return pasid_get_bits(&pe->val[0]) & (1 << 9);
+}
+
+/*
+ * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_sre(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 0, 1);
+}
+
+/*
+ * Setup the WPE(Write Protect Enable) field (Bit 132) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_wpe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
+}
+
+/*
+ * Setup the P(Present) field (Bit 0) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_present(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 0, 1);
+}
+
+/*
+ * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
+{
+	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
+}
+
+/*
+ * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
+ * entry. It is required when XD bit of the first level page table
+ * entry is about to be set.
+ */
+static inline void pasid_set_nxe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
+}
+
+/*
+ * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_pgsnp(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
+}
+
+/*
+ * Setup the First Level Page table Pointer field (Bit 140~191)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the First Level Paging Mode field (Bit 130~131) of a
+ * scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flpm(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
+}
+
+/*
+ * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
+ * of a scalable mode PASID entry.
+ */
+static inline void pasid_set_eafe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
+}
+
 extern unsigned int intel_pasid_max_id;
 int intel_pasid_alloc_table(struct device *dev);
 void intel_pasid_free_table(struct device *dev);
-- 
GitLab


From bb57f6705960bebeb832142ce9abf43220c3eab1 Mon Sep 17 00:00:00 2001
From: Ashish Mhetre <amhetre@nvidia.com>
Date: Tue, 5 Dec 2023 12:26:56 +0530
Subject: [PATCH 1612/4076] iommu: Don't reserve 0-length IOVA region

When the bootloader/firmware doesn't setup the framebuffers, their
address and size are 0 in "iommu-addresses" property. If IOVA region is
reserved with 0 length, then it ends up corrupting the IOVA rbtree with
an entry which has pfn_hi < pfn_lo.
If we intend to use display driver in kernel without framebuffer then
it's causing the display IOMMU mappings to fail as entire valid IOVA
space is reserved when address and length are passed as 0.
An ideal solution would be firmware removing the "iommu-addresses"
property and corresponding "memory-region" if display is not present.
But the kernel should be able to handle this by checking for size of
IOVA region and skipping the IOVA reservation if size is 0. Also, add
a warning if firmware is requesting 0-length IOVA region reservation.

Fixes: a5bf3cfce8cb ("iommu: Implement of_iommu_get_resv_regions()")
Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20231205065656.9544-1-amhetre@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/of_iommu.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 164317bfb8a81..691335a903a89 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -252,6 +252,10 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 					prot |= IOMMU_CACHE;
 
 				maps = of_translate_dma_region(np, maps, &iova, &length);
+				if (length == 0) {
+					dev_warn(dev, "Cannot reserve IOVA region of 0 size\n");
+					continue;
+				}
 				type = iommu_resv_region_get_type(dev, &phys, iova, length);
 
 				region = iommu_alloc_resv_region(iova, length, prot, type,
-- 
GitLab


From 624dda101e03c3a3a155d51e37a7bb7607cb760b Mon Sep 17 00:00:00 2001
From: Veronika Molnarova <vmolnaro@redhat.com>
Date: Tue, 12 Dec 2023 17:59:08 +0100
Subject: [PATCH 1613/4076] perf archive: Add new option '--all' to pack
 perf.data with DSOs

'perf archive' has limited functionality and people from Red Hat Global
Support Services sent a request for a new feature that would pack
perf.data file together with an archive with debug symbols created by
the command 'perf archive' as customers were being confused and often
would forget to send perf.data file with the debug symbols.

With this patch 'perf archive' now accepts an option '--all' that
generates archive 'perf.all-hostname-date-time.tar.bz2' that holds file
'perf.data' and a sub-tar 'perf.symbols.tar.bz2' with debug symbols. The
functionality of the command 'perf archive' was not changed.

Committer testing:

Run 'perf record' on a Intel 14900K machine, hybrid:

  root@number:~# perf record -a sleep 5s
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 4.006 MB perf.data (15427 samples) ]
  root@number:~# perf archive --all
  Now please run:

  $ tar xvf perf.all-number-20231219-104854.tar.bz2 && tar xvf perf.symbols.tar.bz2 -C ~/.debug

  wherever you need to run 'perf report' on.
  root@number:~#

  root@number:~# perf report --header-only
  # ========
  # captured on    : Tue Dec 19 10:48:48 2023
  # header version : 1
  # data offset    : 1008
  # data size      : 4199936
  # feat offset    : 4200944
  # hostname : number
  # os release : 6.6.4-200.fc39.x86_64
  # perf version : 6.7.rc6.gca90f8e17b84
  # arch : x86_64
  # nrcpus online : 28
  # nrcpus avail : 28
  # cpudesc : Intel(R) Core(TM) i7-14700K
  # cpuid : GenuineIntel,6,183,1
  # total memory : 32610508 kB
  # cmdline : /home/acme/bin/perf (deleted) record -a sleep 5s
  # event : name = cpu_atom/cycles/P, , id = { 5088024, 5088025, 5088026, 5088027, 5088028, 5088029, 5088030, 5088031, 5088032, 5088033, 5088034, 5088035 }, type = 0 (PERF_TYPE_HARDWARE), size>
  # event : name = cpu_core/cycles/P, , id = { 5088036, 5088037, 5088038, 5088039, 5088040, 5088041, 5088042, 5088043, 5088044, 5088045, 5088046, 5088047, 5088048, 5088049, 5088050, 5088051 },>
  # event : name = dummy:u, , id = { 5088052, 5088053, 5088054, 5088055, 5088056, 5088057, 5088058, 5088059, 5088060, 5088061, 5088062, 5088063, 5088064, 5088065, 5088066, 5088067, 5088068, 50>
  # CPU_TOPOLOGY info available, use -I to display
  # NUMA_TOPOLOGY info available, use -I to display
  # pmu mappings: cpu_atom = 10, cpu_core = 4, breakpoint = 5, cstate_core = 34, cstate_pkg = 35, i915 = 14, intel_bts = 11, intel_pt = 12, kprobe = 8, msr = 13, power = 36, software = 1, trac>
  # CACHE info available, use -I to display
  # time of first sample : 124739.850375
  # time of last sample : 124744.855181
  # sample duration :   5004.806 ms
  # sample duration :   5004.806 ms
  # MEM_TOPOLOGY info available, use -I to display
  # bpf_prog_info 2: bpf_prog_7cc47bbf07148bfe_hid_tail_call addr 0xffffffffc0000978 size 113
  # bpf_prog_info 47: bpf_prog_713a545fe0530ce7_restrict_filesystems addr 0xffffffffc0000748 size 305
  # bpf_prog_info 163: bpf_prog_bd834b0730296056 addr 0xffffffffc000df14 size 331
  # bpf_prog_info 258: bpf_prog_ee0e253c78993a24_sd_devices addr 0xffffffffc001fc08 size 264
  # bpf_prog_info 259: bpf_prog_40ddf486530245f5_sd_devices addr 0xffffffffc00204bc size 318
  # bpf_prog_info 260: bpf_prog_6deef7357e7b4530_sd_fw_egress addr 0xffffffffc0020630 size 63
  # bpf_prog_info 261: bpf_prog_6deef7357e7b4530_sd_fw_ingress addr 0xffffffffc0020688 size 63
  # bpf_prog_info 262: bpf_prog_b37200ab714f0e17_sd_devices addr 0xffffffffc002072c size 110
  # bpf_prog_info 263: bpf_prog_b90a282ee45cfed9_sd_devices addr 0xffffffffc00207d8 size 393
  # bpf_prog_info 264: bpf_prog_ee0e253c78993a24_sd_devices addr 0xffffffffc002099c size 264
  # bpf_prog_info 265: bpf_prog_6deef7357e7b4530_sd_fw_egress addr 0xffffffffc0020ad4 size 63
  # bpf_prog_info 266: bpf_prog_6deef7357e7b4530_sd_fw_ingress addr 0xffffffffc0020b50 size 63
  # bpf_prog_info 267: bpf_prog_ee0e253c78993a24_sd_devices addr 0xffffffffc002d98c size 264
  # bpf_prog_info 268: bpf_prog_be31ae23198a0378_sd_devices addr 0xffffffffc002dac8 size 297
  # bpf_prog_info 269: bpf_prog_ccbbf91f3c6979c7_sd_devices addr 0xffffffffc002dc54 size 360
  # bpf_prog_info 270: bpf_prog_3a0ef5414c2f6fca_sd_devices addr 0xffffffffc002dde8 size 456
  # bpf_prog_info 271: bpf_prog_6deef7357e7b4530_sd_fw_egress addr 0xffffffffc0020bd4 size 63
  # bpf_prog_info 272: bpf_prog_6deef7357e7b4530_sd_fw_ingress addr 0xffffffffc00299b4 size 63
  # bpf_prog_info 273: bpf_prog_ee0e253c78993a24_sd_devices addr 0xffffffffc002dfd0 size 264
  # bpf_prog_info 274: bpf_prog_6deef7357e7b4530_sd_fw_egress addr 0xffffffffc0029a3c size 63
  # bpf_prog_info 275: bpf_prog_6deef7357e7b4530_sd_fw_ingress addr 0xffffffffc002d71c size 63
  # bpf_prog_info 276: bpf_prog_6deef7357e7b4530_sd_fw_egress addr 0xffffffffc002d7a8 size 63
  # bpf_prog_info 277: bpf_prog_6deef7357e7b4530_sd_fw_ingress addr 0xffffffffc002e13c size 63
  # bpf_prog_info 278: bpf_prog_6deef7357e7b4530_sd_fw_egress addr 0xffffffffc002e1a8 size 63
  # bpf_prog_info 279: bpf_prog_6deef7357e7b4530_sd_fw_ingress addr 0xffffffffc002e234 size 63
  # bpf_prog_info 280: bpf_prog_be31ae23198a0378_sd_devices addr 0xffffffffc002e2ac size 297
  # bpf_prog_info 281: bpf_prog_6deef7357e7b4530_sd_fw_egress addr 0xffffffffc002e42c size 63
  # bpf_prog_info 282: bpf_prog_6deef7357e7b4530_sd_fw_ingress addr 0xffffffffc002e49c size 63
  # bpf_prog_info 290: bpf_prog_ee0e253c78993a24_sd_devices addr 0xffffffffc0004b18 size 264
  # bpf_prog_info 294: bpf_prog_0b1566e4b83190c5_sd_devices addr 0xffffffffc0004c50 size 360
  # bpf_prog_info 295: bpf_prog_ee0e253c78993a24_sd_devices addr 0xffffffffc001cfc8 size 264
  # bpf_prog_info 296: bpf_prog_6deef7357e7b4530_sd_fw_egress addr 0xffffffffc0013abc size 63
  # bpf_prog_info 297: bpf_prog_6deef7357e7b4530_sd_fw_ingress addr 0xffffffffc0013b24 size 63
  # btf info of id 2
  # btf info of id 52
  # HYBRID_TOPOLOGY info available, use -I to display
  # cpu_atom pmu capabilities: branches=32, max_precise=3, pmu_name=alderlake_hybrid
  # cpu_core pmu capabilities: branches=32, max_precise=3, pmu_name=alderlake_hybrid
  # intel_pt pmu capabilities: topa_multiple_entries=1, psb_cyc=1, single_range_output=1, mtc_periods=249, ip_filtering=1, output_subsys=0, cr3_filtering=1, psb_periods=3f, event_trace=0, cycl>
  # missing features: TRACING_DATA BRANCH_STACK GROUP_DESC AUXTRACE STAT CLOCKID DIR_FORMAT COMPRESSED CPU_PMU_CAPS CLOCK_DATA
  # ========
  #
  root@number:~#

And then transferring it to a ARM64 machine, a Libre Computer RK3399-PC:

  root@number:~# scp perf.all-number-20231219-104854.tar.bz2 acme@192.168.86.114:.
  acme@192.168.86.114's password:
  perf.all-number-20231219-104854.tar.bz2                           100%  145MB  85.4MB/s   00:01
  root@number:~#
  root@number:~# ssh acme@192.168.86.114
  acme@192.168.86.114's password:
  Welcome to Ubuntu 23.04 (GNU/Linux 6.1.68-12200-g1c40dda3081e aarch64)

   * Documentation:  https://help.ubuntu.com
   * Management:     https://landscape.canonical.com
   * Support:        https://ubuntu.com/advantage
  Last login: Tue Dec 19 14:53:18 2023 from 192.168.86.42
  acme@roc-rk3399-pc:~$ tar xvf perf.all-number-20231219-104854.tar.bz2 && tar xvf perf.symbols.tar.bz2 -C ~/.debug
  perf.data
  perf.symbols.tar.bz2
  .build-id/ad/acc227f470409213308050b71f664322e2956c
  [kernel.kallsyms]/adacc227f470409213308050b71f664322e2956c/
  [kernel.kallsyms]/adacc227f470409213308050b71f664322e2956c/kallsyms
  [kernel.kallsyms]/adacc227f470409213308050b71f664322e2956c/probes
  .build-id/76/c91f4d62baa06bb52e07e20aba36d21a8f9797
  usr/lib64/libz.so.1.2.13/76c91f4d62baa06bb52e07e20aba36d21a8f9797/
  <SNIP>
  .build-id/09/d7e96bc1e3f599d15ca28b36959124b2d74410
  usr/lib64/librpm_sequoia.so.1/09d7e96bc1e3f599d15ca28b36959124b2d74410/
  usr/lib64/librpm_sequoia.so.1/09d7e96bc1e3f599d15ca28b36959124b2d74410/elf
  usr/lib64/librpm_sequoia.so.1/09d7e96bc1e3f599d15ca28b36959124b2d74410/probes
  acme@roc-rk3399-pc:~$
  acme@roc-rk3399-pc:~$ perf report --stdio | head -40
  # To display the perf.data header info, please use --header/--header-only options.
  #
  # Total Lost Samples: 0
  #
  # Samples: 6K of event 'cpu_atom/cycles/P'
  # Event count (approx.): 4519946621
  #
  # Overhead  Command          Shared Object                                   Symbol
  # ........  ...............  ..............................................  .........................................................................................................................................................
  #
       1.73%  swapper          [kernel.kallsyms]                               [k] intel_idle
       1.43%  sh               [kernel.kallsyms]                               [k] next_uptodate_folio
       0.94%  make             ld-linux-x86-64.so.2                            [.] do_lookup_x
       0.90%  sh               ld-linux-x86-64.so.2                            [.] do_lookup_x
       0.82%  sh               [kernel.kallsyms]                               [k] perf_event_mmap_output
       0.74%  sh               [kernel.kallsyms]                               [k] filemap_map_pages
       0.72%  sh               ld-linux-x86-64.so.2                            [.] _dl_relocate_object
       0.69%  cc1              [kernel.kallsyms]                               [k] clear_page_erms
       0.61%  sh               [kernel.kallsyms]                               [k] unmap_page_range
       0.56%  swapper          [kernel.kallsyms]                               [k] poll_idle
       0.52%  cc1              ld-linux-x86-64.so.2                            [.] do_lookup_x
       0.47%  make             ld-linux-x86-64.so.2                            [.] _dl_relocate_object
       0.44%  cc1              cc1                                             [.] make_node(tree_code)
       0.43%  sh               [kernel.kallsyms]                               [k] native_irq_return_iret
       0.38%  sh               libc.so.6                                       [.] _int_malloc
       0.38%  cc1              cc1                                             [.] decl_attributes(tree_node**, tree_node*, int, tree_node*)
       0.38%  sh               [kernel.kallsyms]                               [k] clear_page_erms
       0.37%  cc1              cc1                                             [.] ht_lookup_with_hash(ht*, unsigned char const*, unsigned long, unsigned int, ht_lookup_option)
       0.37%  make             [kernel.kallsyms]                               [k] perf_event_mmap_output
       0.37%  make             ld-linux-x86-64.so.2                            [.] _dl_lookup_symbol_x
       0.35%  sh               [kernel.kallsyms]                               [k] _compound_head
       0.35%  make             make                                            [.] hash_find_slot
       0.33%  sh               libc.so.6                                       [.] __strlen_avx2
       0.33%  cc1              cc1                                             [.] ggc_internal_alloc(unsigned long, void (*)(void*), unsigned long, unsigned long)
       0.33%  sh               [kernel.kallsyms]                               [k] perf_iterate_ctx
       0.31%  make             make                                            [.] jhash_string
       0.31%  sh               [kernel.kallsyms]                               [k] page_remove_rmap
       0.30%  cc1              libc.so.6                                       [.] _int_malloc
       0.30%  make             libc.so.6                                       [.] _int_malloc
  acme@roc-rk3399-pc:~$

Signed-off-by: Veronika Molnarova <vmolnaro@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Link: https://lore.kernel.org/r/20231212165909.14459-1-vmolnaro@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/perf-archive.sh | 40 ++++++++++++++++++++++++++++++--------
 1 file changed, 32 insertions(+), 8 deletions(-)
 mode change 100644 => 100755 tools/perf/perf-archive.sh

diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
old mode 100644
new mode 100755
index 133f0eddbcc46..a92042eae95a1
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -4,9 +4,19 @@
 # Arnaldo Carvalho de Melo <acme@redhat.com>
 
 PERF_DATA=perf.data
-if [ $# -ne 0 ] ; then
-	PERF_DATA=$1
-fi
+PERF_SYMBOLS=perf.symbols
+PERF_ALL=perf.all
+ALL=0
+
+while [ $# -gt 0 ] ; do
+	if [ $1 == "--all" ]; then
+		ALL=1
+		shift
+	else
+		PERF_DATA=$1
+		shift
+	fi
+done
 
 #
 # PERF_BUILDID_DIR environment variable set by perf
@@ -39,9 +49,23 @@ while read build_id ; do
 	echo ${filename#$PERF_BUILDID_LINKDIR} >> $MANIFEST
 done
 
-tar cjf $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
-rm $MANIFEST $BUILDIDS || true
-echo -e "Now please run:\n"
-echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
-echo "wherever you need to run 'perf report' on."
+if [ $ALL -eq 1 ]; then						# pack perf.data file together with tar containing debug symbols
+	HOSTNAME=$(hostname)
+	DATE=$(date '+%Y%m%d-%H%M%S')
+	tar cjf $PERF_SYMBOLS.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
+	tar cjf	$PERF_ALL-$HOSTNAME-$DATE.tar.bz2 $PERF_DATA $PERF_SYMBOLS.tar.bz2
+	rm $PERF_SYMBOLS.tar.bz2 $MANIFEST $BUILDIDS || true
+
+	echo -e "Now please run:\n"
+	echo -e "$ tar xvf $PERF_ALL-$HOSTNAME-$DATE.tar.bz2 && tar xvf $PERF_SYMBOLS.tar.bz2 -C ~/.debug\n"
+	echo "wherever you need to run 'perf report' on."
+else										# pack only the debug symbols
+	tar cjf $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
+	rm $MANIFEST $BUILDIDS || true
+
+	echo -e "Now please run:\n"
+	echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
+	echo "wherever you need to run 'perf report' on."
+fi
+
 exit 0
-- 
GitLab


From 838bebb4c926a573839ff1bfe1b654a6ed0f9779 Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:39 +0200
Subject: [PATCH 1614/4076] virtio: Define feature bit for administration
 virtqueue

Introduce VIRTIO_F_ADMIN_VQ which is used for administration virtqueue
support.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-2-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/uapi/linux/virtio_config.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 8881aea60f6f1..2445f365bce74 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -52,7 +52,7 @@
  * rest are per-device feature bits.
  */
 #define VIRTIO_TRANSPORT_F_START	28
-#define VIRTIO_TRANSPORT_F_END		41
+#define VIRTIO_TRANSPORT_F_END		42
 
 #ifndef VIRTIO_CONFIG_NO_LEGACY
 /* Do we get callbacks when the ring is completely used, even if we've
@@ -114,4 +114,10 @@
  * This feature indicates that the driver can reset a queue individually.
  */
 #define VIRTIO_F_RING_RESET		40
+
+/*
+ * This feature indicates that the device support administration virtqueues.
+ */
+#define VIRTIO_F_ADMIN_VQ		41
+
 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
-- 
GitLab


From fd27ef6b44bec26915c5b2b22c13856d9f0ba17a Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:40 +0200
Subject: [PATCH 1615/4076] virtio-pci: Introduce admin virtqueue

Introduce support for the admin virtqueue. By negotiating
VIRTIO_F_ADMIN_VQ feature, driver detects capability and creates one
administration virtqueue. Administration virtqueue implementation in
virtio pci generic layer, enables multiple types of upper layer
drivers such as vfio, net, blk to utilize it.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-3-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/virtio.c                | 37 +++++++++++--
 drivers/virtio/virtio_pci_common.c     |  3 ++
 drivers/virtio/virtio_pci_common.h     | 15 +++++-
 drivers/virtio/virtio_pci_modern.c     | 75 +++++++++++++++++++++++++-
 drivers/virtio/virtio_pci_modern_dev.c | 24 ++++++++-
 include/linux/virtio_config.h          |  4 ++
 include/linux/virtio_pci_modern.h      |  2 +
 include/uapi/linux/virtio_pci.h        |  5 ++
 8 files changed, 157 insertions(+), 8 deletions(-)

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 3893dc29eb263..f4080692b3513 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -302,9 +302,15 @@ static int virtio_dev_probe(struct device *_d)
 	if (err)
 		goto err;
 
+	if (dev->config->create_avq) {
+		err = dev->config->create_avq(dev);
+		if (err)
+			goto err;
+	}
+
 	err = drv->probe(dev);
 	if (err)
-		goto err;
+		goto err_probe;
 
 	/* If probe didn't do it, mark device DRIVER_OK ourselves. */
 	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
@@ -316,6 +322,10 @@ static int virtio_dev_probe(struct device *_d)
 	virtio_config_enable(dev);
 
 	return 0;
+
+err_probe:
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return err;
@@ -331,6 +341,9 @@ static void virtio_dev_remove(struct device *_d)
 
 	drv->remove(dev);
 
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
+
 	/* Driver should have reset device. */
 	WARN_ON_ONCE(dev->config->get_status(dev));
 
@@ -489,13 +502,20 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device);
 int virtio_device_freeze(struct virtio_device *dev)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
 
 	virtio_config_disable(dev);
 
 	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
 
-	if (drv && drv->freeze)
-		return drv->freeze(dev);
+	if (drv && drv->freeze) {
+		ret = drv->freeze(dev);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 
 	return 0;
 }
@@ -532,10 +552,16 @@ int virtio_device_restore(struct virtio_device *dev)
 	if (ret)
 		goto err;
 
+	if (dev->config->create_avq) {
+		ret = dev->config->create_avq(dev);
+		if (ret)
+			goto err;
+	}
+
 	if (drv->restore) {
 		ret = drv->restore(dev);
 		if (ret)
-			goto err;
+			goto err_restore;
 	}
 
 	/* If restore didn't do it, mark device DRIVER_OK ourselves. */
@@ -546,6 +572,9 @@ int virtio_device_restore(struct virtio_device *dev)
 
 	return 0;
 
+err_restore:
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return ret;
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 7a5593997e0ef..fafd13d0e4d46 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -236,6 +236,9 @@ void vp_del_vqs(struct virtio_device *vdev)
 	int i;
 
 	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		if (vp_dev->is_avq(vdev, vq->index))
+			continue;
+
 		if (vp_dev->per_vq_vectors) {
 			int v = vp_dev->vqs[vq->index]->msix_vector;
 
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 4b773bd7c58cb..7306128e63e98 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -41,6 +41,14 @@ struct virtio_pci_vq_info {
 	unsigned int msix_vector;
 };
 
+struct virtio_pci_admin_vq {
+	/* Virtqueue info associated with this admin queue. */
+	struct virtio_pci_vq_info info;
+	/* Name of the admin queue: avq.$vq_index. */
+	char name[10];
+	u16 vq_index;
+};
+
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
@@ -58,9 +66,13 @@ struct virtio_pci_device {
 	spinlock_t lock;
 	struct list_head virtqueues;
 
-	/* array of all queues for house-keeping */
+	/* Array of all virtqueues reported in the
+	 * PCI common config num_queues field
+	 */
 	struct virtio_pci_vq_info **vqs;
 
+	struct virtio_pci_admin_vq admin_vq;
+
 	/* MSI-X support */
 	int msix_enabled;
 	int intx_enabled;
@@ -86,6 +98,7 @@ struct virtio_pci_device {
 	void (*del_vq)(struct virtio_pci_vq_info *info);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
+	bool (*is_avq)(struct virtio_device *vdev, unsigned int index);
 };
 
 /* Constants for MSI-X */
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index ee6a386d250b1..ce915018b5b0f 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -19,6 +19,8 @@
 #define VIRTIO_RING_NO_LEGACY
 #include "virtio_pci_common.h"
 
+#define VIRTIO_AVQ_SGS_MAX	4
+
 static u64 vp_get_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -26,6 +28,16 @@ static u64 vp_get_features(struct virtio_device *vdev)
 	return vp_modern_get_features(&vp_dev->mdev);
 }
 
+static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	return index == vp_dev->admin_vq.vq_index;
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -37,6 +49,9 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 
 	if (features & BIT_ULL(VIRTIO_F_RING_RESET))
 		__virtio_set_bit(vdev, VIRTIO_F_RING_RESET);
+
+	if (features & BIT_ULL(VIRTIO_F_ADMIN_VQ))
+		__virtio_set_bit(vdev, VIRTIO_F_ADMIN_VQ);
 }
 
 static int __vp_check_common_size_one_feature(struct virtio_device *vdev, u32 fbit,
@@ -69,6 +84,9 @@ static int vp_check_common_size(struct virtio_device *vdev)
 	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_RING_RESET, queue_reset))
 		return -EINVAL;
 
+	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_ADMIN_VQ, admin_queue_num))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -345,6 +363,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	bool (*notify)(struct virtqueue *vq);
 	struct virtqueue *vq;
+	bool is_avq;
 	u16 num;
 	int err;
 
@@ -353,11 +372,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	else
 		notify = vp_notify;
 
-	if (index >= vp_modern_get_num_queues(mdev))
+	is_avq = vp_is_avq(&vp_dev->vdev, index);
+	if (index >= vp_modern_get_num_queues(mdev) && !is_avq)
 		return ERR_PTR(-EINVAL);
 
+	num = is_avq ?
+		VIRTIO_AVQ_SGS_MAX : vp_modern_get_queue_size(mdev, index);
 	/* Check if queue is either not available or already active. */
-	num = vp_modern_get_queue_size(mdev, index);
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
@@ -383,6 +404,9 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		goto err;
 	}
 
+	if (is_avq)
+		vp_dev->admin_vq.info.vq = vq;
+
 	return vq;
 
 err:
@@ -418,6 +442,9 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	if (vp_is_avq(&vp_dev->vdev, vq->index))
+		vp_dev->admin_vq.info.vq = NULL;
+
 	if (vp_dev->msix_enabled)
 		vp_modern_queue_vector(mdev, vq->index,
 				       VIRTIO_MSI_NO_VECTOR);
@@ -527,6 +554,45 @@ static bool vp_get_shm_region(struct virtio_device *vdev,
 	return true;
 }
 
+static int vp_modern_create_avq(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *avq;
+	struct virtqueue *vq;
+	u16 admin_q_num;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return 0;
+
+	admin_q_num = vp_modern_avq_num(&vp_dev->mdev);
+	if (!admin_q_num)
+		return -EINVAL;
+
+	avq = &vp_dev->admin_vq;
+	avq->vq_index = vp_modern_avq_index(&vp_dev->mdev);
+	sprintf(avq->name, "avq.%u", avq->vq_index);
+	vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL,
+			      avq->name, NULL, VIRTIO_MSI_NO_VECTOR);
+	if (IS_ERR(vq)) {
+		dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld",
+			PTR_ERR(vq));
+		return PTR_ERR(vq);
+	}
+
+	vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true);
+	return 0;
+}
+
+static void vp_modern_destroy_avq(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	vp_dev->del_vq(&vp_dev->admin_vq.info);
+}
+
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,
@@ -545,6 +611,8 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
+	.create_avq = vp_modern_create_avq,
+	.destroy_avq = vp_modern_destroy_avq,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -565,6 +633,8 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
+	.create_avq = vp_modern_create_avq,
+	.destroy_avq = vp_modern_destroy_avq,
 };
 
 /* the PCI probing function */
@@ -588,6 +658,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->config_vector = vp_config_vector;
 	vp_dev->setup_vq = setup_vq;
 	vp_dev->del_vq = del_vq;
+	vp_dev->is_avq = vp_is_avq;
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index 7de8b1ebabac4..0d3dbfaf4b236 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -207,6 +207,10 @@ static inline void check_offsets(void)
 		     offsetof(struct virtio_pci_modern_common_cfg, queue_notify_data));
 	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_RESET !=
 		     offsetof(struct virtio_pci_modern_common_cfg, queue_reset));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_IDX !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_index));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_NUM !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_num));
 }
 
 /*
@@ -296,7 +300,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 	mdev->common = vp_modern_map_capability(mdev, common,
 			      sizeof(struct virtio_pci_common_cfg), 4, 0,
 			      offsetofend(struct virtio_pci_modern_common_cfg,
-					  queue_reset),
+					  admin_queue_num),
 			      &mdev->common_len, NULL);
 	if (!mdev->common)
 		goto err_map_common;
@@ -719,6 +723,24 @@ void __iomem *vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev,
 }
 EXPORT_SYMBOL_GPL(vp_modern_map_vq_notify);
 
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_num);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_num);
+
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_index);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_index);
+
 MODULE_VERSION("0.1");
 MODULE_DESCRIPTION("Modern Virtio PCI Device");
 MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 2b3438de2c4d4..da9b271b54db8 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -93,6 +93,8 @@ typedef void vq_callback_t(struct virtqueue *);
  *	Returns 0 on success or error status
  *	If disable_vq_and_reset is set, then enable_vq_after_reset must also be
  *	set.
+ * @create_avq: create admin virtqueue resource.
+ * @destroy_avq: destroy admin virtqueue resource.
  */
 struct virtio_config_ops {
 	void (*get)(struct virtio_device *vdev, unsigned offset,
@@ -120,6 +122,8 @@ struct virtio_config_ops {
 			       struct virtio_shm_region *region, u8 id);
 	int (*disable_vq_and_reset)(struct virtqueue *vq);
 	int (*enable_vq_after_reset)(struct virtqueue *vq);
+	int (*create_avq)(struct virtio_device *vdev);
+	void (*destroy_avq)(struct virtio_device *vdev);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index a09e13a577a99..c0b1b1ca11635 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -125,4 +125,6 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev);
 void vp_modern_remove(struct virtio_pci_modern_device *mdev);
 int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
 void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev);
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev);
 #endif
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 44f4dd2add188..240ddeef7eae3 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -175,6 +175,9 @@ struct virtio_pci_modern_common_cfg {
 
 	__le16 queue_notify_data;	/* read-write */
 	__le16 queue_reset;		/* read-write */
+
+	__le16 admin_queue_index;	/* read-only */
+	__le16 admin_queue_num;		/* read-only */
 };
 
 /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */
@@ -215,6 +218,8 @@ struct virtio_pci_cfg_cap {
 #define VIRTIO_PCI_COMMON_Q_USEDHI	52
 #define VIRTIO_PCI_COMMON_Q_NDATA	56
 #define VIRTIO_PCI_COMMON_Q_RESET	58
+#define VIRTIO_PCI_COMMON_ADM_Q_IDX	60
+#define VIRTIO_PCI_COMMON_ADM_Q_NUM	62
 
 #endif /* VIRTIO_PCI_NO_MODERN */
 
-- 
GitLab


From 92792ac752aa80d5ee71bc291d90edd06cd76bd1 Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:41 +0200
Subject: [PATCH 1616/4076] virtio-pci: Introduce admin command sending
 function

Add support for sending admin command through admin virtqueue interface.
Abort any inflight admin commands once device reset completes. Activate
admin queue when device becomes ready; deactivate on device reset.

To comply to the below specification statement [1], the admin virtqueue
is activated for upper layer users only after setting DRIVER_OK status.

[1] The driver MUST NOT send any buffer available notifications to the
device before setting DRIVER_OK.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-4-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/virtio_pci_common.h |   6 ++
 drivers/virtio/virtio_pci_modern.c | 143 ++++++++++++++++++++++++++++-
 include/linux/virtio.h             |   8 ++
 include/uapi/linux/virtio_pci.h    |  22 +++++
 4 files changed, 177 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 7306128e63e98..282d087a92667 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -29,6 +29,7 @@
 #include <linux/virtio_pci_modern.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 
 struct virtio_pci_vq_info {
 	/* the actual virtqueue */
@@ -44,6 +45,8 @@ struct virtio_pci_vq_info {
 struct virtio_pci_admin_vq {
 	/* Virtqueue info associated with this admin queue. */
 	struct virtio_pci_vq_info info;
+	/* serializing admin commands execution and virtqueue deletion */
+	struct mutex cmd_lock;
 	/* Name of the admin queue: avq.$vq_index. */
 	char name[10];
 	u16 vq_index;
@@ -152,4 +155,7 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd);
+
 #endif
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index ce915018b5b0f..9bd66300a80aa 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -38,6 +38,132 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
 	return index == vp_dev->admin_vq.vq_index;
 }
 
+static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
+				    struct scatterlist **sgs,
+				    unsigned int out_num,
+				    unsigned int in_num,
+				    void *data)
+{
+	struct virtqueue *vq;
+	int ret, len;
+
+	vq = admin_vq->info.vq;
+	if (!vq)
+		return -EIO;
+
+	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL);
+	if (ret < 0)
+		return -EIO;
+
+	if (unlikely(!virtqueue_kick(vq)))
+		return -EIO;
+
+	while (!virtqueue_get_buf(vq, &len) &&
+	       !virtqueue_is_broken(vq))
+		cpu_relax();
+
+	if (virtqueue_is_broken(vq))
+		return -EIO;
+
+	return 0;
+}
+
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd)
+{
+	struct scatterlist *sgs[VIRTIO_AVQ_SGS_MAX], hdr, stat;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_admin_cmd_status *va_status;
+	unsigned int out_num = 0, in_num = 0;
+	struct virtio_admin_cmd_hdr *va_hdr;
+	u16 status;
+	int ret;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return -EOPNOTSUPP;
+
+	va_status = kzalloc(sizeof(*va_status), GFP_KERNEL);
+	if (!va_status)
+		return -ENOMEM;
+
+	va_hdr = kzalloc(sizeof(*va_hdr), GFP_KERNEL);
+	if (!va_hdr) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	va_hdr->opcode = cmd->opcode;
+	va_hdr->group_type = cmd->group_type;
+	va_hdr->group_member_id = cmd->group_member_id;
+
+	/* Add header */
+	sg_init_one(&hdr, va_hdr, sizeof(*va_hdr));
+	sgs[out_num] = &hdr;
+	out_num++;
+
+	if (cmd->data_sg) {
+		sgs[out_num] = cmd->data_sg;
+		out_num++;
+	}
+
+	/* Add return status */
+	sg_init_one(&stat, va_status, sizeof(*va_status));
+	sgs[out_num + in_num] = &stat;
+	in_num++;
+
+	if (cmd->result_sg) {
+		sgs[out_num + in_num] = cmd->result_sg;
+		in_num++;
+	}
+
+	mutex_lock(&vp_dev->admin_vq.cmd_lock);
+	ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq, sgs,
+				       out_num, in_num, sgs);
+	mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+
+	if (ret) {
+		dev_err(&vdev->dev,
+			"Failed to execute command on admin vq: %d\n.", ret);
+		goto err_cmd_exec;
+	}
+
+	status = le16_to_cpu(va_status->status);
+	if (status != VIRTIO_ADMIN_STATUS_OK) {
+		dev_err(&vdev->dev,
+			"admin command error: status(%#x) qualifier(%#x)\n",
+			status, le16_to_cpu(va_status->status_qualifier));
+		ret = -status;
+	}
+
+err_cmd_exec:
+	kfree(va_hdr);
+err_alloc:
+	kfree(va_status);
+	return ret;
+}
+
+static void vp_modern_avq_activate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_unbreak(admin_vq->info.vq);
+}
+
+static void vp_modern_avq_deactivate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_break(admin_vq->info.vq);
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -213,6 +339,8 @@ static void vp_set_status(struct virtio_device *vdev, u8 status)
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
 	vp_modern_set_status(&vp_dev->mdev, status);
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK)
+		vp_modern_avq_activate(vdev);
 }
 
 static void vp_reset(struct virtio_device *vdev)
@@ -229,6 +357,9 @@ static void vp_reset(struct virtio_device *vdev)
 	 */
 	while (vp_modern_get_status(mdev))
 		msleep(1);
+
+	vp_modern_avq_deactivate(vdev);
+
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
 }
@@ -404,8 +535,11 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		goto err;
 	}
 
-	if (is_avq)
+	if (is_avq) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
 		vp_dev->admin_vq.info.vq = vq;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
 
 	return vq;
 
@@ -442,8 +576,11 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
-	if (vp_is_avq(&vp_dev->vdev, vq->index))
+	if (vp_is_avq(&vp_dev->vdev, vq->index)) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
 		vp_dev->admin_vq.info.vq = NULL;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
 
 	if (vp_dev->msix_enabled)
 		vp_modern_queue_vector(mdev, vq->index,
@@ -662,6 +799,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
+	mutex_init(&vp_dev->admin_vq.cmd_lock);
 	return 0;
 }
 
@@ -669,5 +807,6 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	mutex_destroy(&vp_dev->admin_vq.cmd_lock);
 	vp_modern_remove(mdev);
 }
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4cc614a383765..b0201747a263a 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -103,6 +103,14 @@ int virtqueue_resize(struct virtqueue *vq, u32 num,
 int virtqueue_reset(struct virtqueue *vq,
 		    void (*recycle)(struct virtqueue *vq, void *buf));
 
+struct virtio_admin_cmd {
+	__le16 opcode;
+	__le16 group_type;
+	__le64 group_member_id;
+	struct scatterlist *data_sg;
+	struct scatterlist *result_sg;
+};
+
 /**
  * struct virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 240ddeef7eae3..187fd9e34a30f 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -223,4 +223,26 @@ struct virtio_pci_cfg_cap {
 
 #endif /* VIRTIO_PCI_NO_MODERN */
 
+/* Admin command status. */
+#define VIRTIO_ADMIN_STATUS_OK		0
+
+struct __packed virtio_admin_cmd_hdr {
+	__le16 opcode;
+	/*
+	 * 1 - SR-IOV
+	 * 2-65535 - reserved
+	 */
+	__le16 group_type;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved1[12];
+	__le64 group_member_id;
+};
+
+struct __packed virtio_admin_cmd_status {
+	__le16 status;
+	__le16 status_qualifier;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved2[4];
+};
+
 #endif
-- 
GitLab


From 388431b9f59bbfde2b5f2fe032b0836158b09ad0 Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:42 +0200
Subject: [PATCH 1617/4076] virtio-pci: Introduce admin commands

Introduces admin commands, as follow:

The "list query" command can be used by the driver to query the
set of admin commands supported by the virtio device.
The "list use" command is used to inform the virtio device which
admin commands the driver will use.
The "legacy common cfg rd/wr" commands are used to read from/write
into the legacy common configuration structure.
The "legacy dev cfg rd/wr" commands are used to read from/write
into the legacy device configuration structure.
The "notify info" command is used to query the notification region
information.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-5-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/uapi/linux/virtio_pci.h | 41 +++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 187fd9e34a30f..ef3810dee7efa 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -226,6 +226,20 @@ struct virtio_pci_cfg_cap {
 /* Admin command status. */
 #define VIRTIO_ADMIN_STATUS_OK		0
 
+/* Admin command opcode. */
+#define VIRTIO_ADMIN_CMD_LIST_QUERY	0x0
+#define VIRTIO_ADMIN_CMD_LIST_USE	0x1
+
+/* Admin command group type. */
+#define VIRTIO_ADMIN_GROUP_TYPE_SRIOV	0x1
+
+/* Transitional device admin command. */
+#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE	0x2
+#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ		0x3
+#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE		0x4
+#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ		0x5
+#define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO		0x6
+
 struct __packed virtio_admin_cmd_hdr {
 	__le16 opcode;
 	/*
@@ -245,4 +259,31 @@ struct __packed virtio_admin_cmd_status {
 	__u8 reserved2[4];
 };
 
+struct __packed virtio_admin_cmd_legacy_wr_data {
+	__u8 offset; /* Starting offset of the register(s) to write. */
+	__u8 reserved[7];
+	__u8 registers[];
+};
+
+struct __packed virtio_admin_cmd_legacy_rd_data {
+	__u8 offset; /* Starting offset of the register(s) to read. */
+};
+
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END 0
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_DEV 0x1
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM 0x2
+
+#define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4
+
+struct __packed virtio_admin_cmd_notify_info_data {
+	__u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */
+	__u8 bar; /* BAR of the member or the owner device */
+	__u8 padding[6];
+	__le64 offset; /* Offset within bar. */
+};
+
+struct virtio_admin_cmd_notify_info_result {
+	struct virtio_admin_cmd_notify_info_data entries[VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO];
+};
+
 #endif
-- 
GitLab


From f51e146f1e5c9de02433e51f5a344556502d9c6a Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:43 +0200
Subject: [PATCH 1618/4076] virtio-pci: Initialize the supported admin commands

Initialize the supported admin commands upon activating the admin queue.

The supported commands are saved as part of the admin queue context.

Next patches in this series will expose APIs to use them.

Reviewed-by: Feng Liu <feliu@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-6-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/Kconfig             |  5 +++
 drivers/virtio/virtio_pci_common.h | 19 ++++++++++++
 drivers/virtio/virtio_pci_modern.c | 49 ++++++++++++++++++++++++++++--
 3 files changed, 71 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 0a53a61231c29..c17193544268a 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -60,6 +60,11 @@ config VIRTIO_PCI
 
 	  If unsure, say M.
 
+config VIRTIO_PCI_ADMIN_LEGACY
+	bool
+	depends on VIRTIO_PCI && (X86 || COMPILE_TEST)
+	default y
+
 config VIRTIO_PCI_LEGACY
 	bool "Support for legacy virtio draft 0.9.X and older devices"
 	default y
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 282d087a92667..a39bffd5fd462 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -47,6 +47,7 @@ struct virtio_pci_admin_vq {
 	struct virtio_pci_vq_info info;
 	/* serializing admin commands execution and virtqueue deletion */
 	struct mutex cmd_lock;
+	u64 supported_cmds;
 	/* Name of the admin queue: avq.$vq_index. */
 	char name[10];
 	u16 vq_index;
@@ -155,6 +156,24 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
+#define VIRTIO_LEGACY_ADMIN_CMD_BITMAP \
+	(BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO))
+
+/* Unlike modern drivers which support hardware virtio devices, legacy drivers
+ * assume software-based devices: e.g. they don't use proper memory barriers
+ * on ARM, use big endian on PPC, etc. X86 drivers are mostly ok though, more
+ * or less by chance. For now, only support legacy IO on X86.
+ */
+#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
+#define VIRTIO_ADMIN_CMD_BITMAP VIRTIO_LEGACY_ADMIN_CMD_BITMAP
+#else
+#define VIRTIO_ADMIN_CMD_BITMAP 0
+#endif
+
 int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
 			     struct virtio_admin_cmd *cmd);
 
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 9bd66300a80aa..f62b530aa3b5b 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -39,6 +39,7 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
 }
 
 static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
+				    u16 opcode,
 				    struct scatterlist **sgs,
 				    unsigned int out_num,
 				    unsigned int in_num,
@@ -51,6 +52,11 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
 	if (!vq)
 		return -EIO;
 
+	if (opcode != VIRTIO_ADMIN_CMD_LIST_QUERY &&
+	    opcode != VIRTIO_ADMIN_CMD_LIST_USE &&
+	    !((1ULL << opcode) & admin_vq->supported_cmds))
+		return -EOPNOTSUPP;
+
 	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL);
 	if (ret < 0)
 		return -EIO;
@@ -117,8 +123,9 @@ int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
 	}
 
 	mutex_lock(&vp_dev->admin_vq.cmd_lock);
-	ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq, sgs,
-				       out_num, in_num, sgs);
+	ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq,
+				       le16_to_cpu(cmd->opcode),
+				       sgs, out_num, in_num, sgs);
 	mutex_unlock(&vp_dev->admin_vq.cmd_lock);
 
 	if (ret) {
@@ -142,6 +149,43 @@ err_alloc:
 	return ret;
 }
 
+static void virtio_pci_admin_cmd_list_init(struct virtio_device *virtio_dev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev);
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	struct scatterlist data_sg;
+	__le64 *data;
+	int ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	sg_init_one(&result_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LIST_QUERY);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.result_sg = &result_sg;
+
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto end;
+
+	*data &= cpu_to_le64(VIRTIO_ADMIN_CMD_BITMAP);
+	sg_init_one(&data_sg, data, sizeof(*data));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LIST_USE);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = NULL;
+
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (ret)
+		goto end;
+
+	vp_dev->admin_vq.supported_cmds = le64_to_cpu(*data);
+end:
+	kfree(data);
+}
+
 static void vp_modern_avq_activate(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -151,6 +195,7 @@ static void vp_modern_avq_activate(struct virtio_device *vdev)
 		return;
 
 	__virtqueue_unbreak(admin_vq->info.vq);
+	virtio_pci_admin_cmd_list_init(vdev);
 }
 
 static void vp_modern_avq_deactivate(struct virtio_device *vdev)
-- 
GitLab


From c3fc3e098bd64c560dde49a6e72b21b055150abe Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:44 +0200
Subject: [PATCH 1619/4076] virtio-pci: Introduce APIs to execute legacy IO
 admin commands

Introduce APIs to execute legacy IO admin commands.

It includes: io_legacy_read/write for both common and the device
configuration, io_legacy_notify_info.

In addition, exposing an API to check whether the legacy IO commands are
supported. (i.e. virtio_pci_admin_has_legacy_io()).

Those APIs will be used by the next patches from this series.

Note:
Unlike modern drivers which support hardware virtio devices, legacy
drivers assume software-based devices: e.g. they don't use proper memory
barriers on ARM, use big endian on PPC, etc. X86 drivers are mostly ok
though, more or less by chance. For now, only support legacy IO on X86.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-7-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/Makefile                     |   1 +
 drivers/virtio/virtio_pci_admin_legacy_io.c | 244 ++++++++++++++++++++
 drivers/virtio/virtio_pci_common.c          |  11 +
 drivers/virtio/virtio_pci_common.h          |   2 +
 include/linux/virtio_pci_admin.h            |  23 ++
 5 files changed, 281 insertions(+)
 create mode 100644 drivers/virtio/virtio_pci_admin_legacy_io.c
 create mode 100644 include/linux/virtio_pci_admin.h

diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 8e98d24917cc0..73ace62af4409 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
 virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
 virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
+virtio_pci-$(CONFIG_VIRTIO_PCI_ADMIN_LEGACY) += virtio_pci_admin_legacy_io.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
 obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
 obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o
diff --git a/drivers/virtio/virtio_pci_admin_legacy_io.c b/drivers/virtio/virtio_pci_admin_legacy_io.c
new file mode 100644
index 0000000000000..819cfbbc67c3b
--- /dev/null
+++ b/drivers/virtio/virtio_pci_admin_legacy_io.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/virtio_pci_admin.h>
+#include "virtio_pci_common.h"
+
+/*
+ * virtio_pci_admin_has_legacy_io - Checks whether the legacy IO
+ * commands are supported
+ * @dev: VF pci_dev
+ *
+ * Returns true on success.
+ */
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_pci_device *vp_dev;
+
+	if (!virtio_dev)
+		return false;
+
+	if (!virtio_has_feature(virtio_dev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	vp_dev = to_vp_device(virtio_dev);
+
+	if ((vp_dev->admin_vq.supported_cmds & VIRTIO_LEGACY_ADMIN_CMD_BITMAP) ==
+		VIRTIO_LEGACY_ADMIN_CMD_BITMAP)
+		return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_has_legacy_io);
+
+static int virtio_pci_admin_legacy_io_write(struct pci_dev *pdev, u16 opcode,
+					    u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_wr_data *data;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist data_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data) + size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	memcpy(data->registers, buf, size);
+	sg_init_one(&data_sg, data, sizeof(*data) + size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_io_write_common - Write legacy common configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_write);
+
+/*
+ * virtio_pci_admin_legacy_io_write_device - Write legacy device configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_write);
+
+static int virtio_pci_admin_legacy_io_read(struct pci_dev *pdev, u16 opcode,
+					   u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_rd_data *data;
+	struct scatterlist data_sg, result_sg;
+	struct virtio_admin_cmd cmd = {};
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	sg_init_one(&data_sg, data, sizeof(*data));
+	sg_init_one(&result_sg, buf, size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_device_io_read - Read legacy device configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_read);
+
+/*
+ * virtio_pci_admin_legacy_common_io_read - Read legacy common configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_read);
+
+/*
+ * virtio_pci_admin_legacy_io_notify_info - Read the queue notification
+ * information for legacy interface
+ * @dev: VF pci_dev
+ * @req_bar_flags: requested bar flags
+ * @bar: on output the BAR number of the owner or member device
+ * @bar_offset: on output the offset within bar
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_notify_info_result *result;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	result = kzalloc(sizeof(*result), GFP_KERNEL);
+	if (!result)
+		return -ENOMEM;
+
+	sg_init_one(&result_sg, result, sizeof(*result));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (!ret) {
+		struct virtio_admin_cmd_notify_info_data *entry;
+		int i;
+
+		ret = -ENOENT;
+		for (i = 0; i < VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO; i++) {
+			entry = &result->entries[i];
+			if (entry->flags == VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END)
+				break;
+			if (entry->flags != req_bar_flags)
+				continue;
+			*bar = entry->bar;
+			*bar_offset = le64_to_cpu(entry->offset);
+			ret = 0;
+			break;
+		}
+	}
+
+	kfree(result);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_io_notify_info);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index fafd13d0e4d46..9f93330fc2cc0 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -645,6 +645,17 @@ static struct pci_driver virtio_pci_driver = {
 	.sriov_configure = virtio_pci_sriov_configure,
 };
 
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev)
+{
+	struct virtio_pci_device *pf_vp_dev;
+
+	pf_vp_dev = pci_iov_get_pf_drvdata(pdev, &virtio_pci_driver);
+	if (IS_ERR(pf_vp_dev))
+		return NULL;
+
+	return &pf_vp_dev->vdev;
+}
+
 module_pci_driver(virtio_pci_driver);
 
 MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index a39bffd5fd462..7fef52bee4557 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -156,6 +156,8 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
+
 #define VIRTIO_LEGACY_ADMIN_CMD_BITMAP \
 	(BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE) | \
 	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ) | \
diff --git a/include/linux/virtio_pci_admin.h b/include/linux/virtio_pci_admin.h
new file mode 100644
index 0000000000000..f4a100a0fe2e1
--- /dev/null
+++ b/include/linux/virtio_pci_admin.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VIRTIO_PCI_ADMIN_H
+#define _LINUX_VIRTIO_PCI_ADMIN_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+
+#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev);
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf);
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf);
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf);
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf);
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset);
+#endif
+
+#endif /* _LINUX_VIRTIO_PCI_ADMIN_H */
-- 
GitLab


From 8bccc5b80678c69f7729ce4cd232c0aa98fa6277 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:45 +0200
Subject: [PATCH 1620/4076] vfio/pci: Expose vfio_pci_core_setup_barmap()

Expose vfio_pci_core_setup_barmap() to be used by drivers.

This will let drivers to mmap a BAR and re-use it from both vfio and the
driver when it's applicable.

This API will be used in the next patches by the vfio/virtio coming
driver.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/20231219093247.170936-8-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci_rdwr.c | 7 ++++---
 include/linux/vfio_pci_core.h    | 1 +
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index e27de61ac9fe7..a9887fd6de46c 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -200,7 +200,7 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 	return done;
 }
 
-static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
+int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	int ret;
@@ -223,6 +223,7 @@ static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap);
 
 ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 			size_t count, loff_t *ppos, bool iswrite)
@@ -262,7 +263,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 		}
 		x_end = end;
 	} else {
-		int ret = vfio_pci_setup_barmap(vdev, bar);
+		int ret = vfio_pci_core_setup_barmap(vdev, bar);
 		if (ret) {
 			done = ret;
 			goto out;
@@ -438,7 +439,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 		return -EINVAL;
 #endif
 
-	ret = vfio_pci_setup_barmap(vdev, bar);
+	ret = vfio_pci_core_setup_barmap(vdev, bar);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 562e8754869da..67ac58e20e1da 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -127,6 +127,7 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf);
 int vfio_pci_core_enable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_disable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev);
+int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar);
 pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 						pci_channel_state_t state);
 
-- 
GitLab


From 8486ae162b3b6cc1055366f044495cf1966231f1 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:46 +0200
Subject: [PATCH 1621/4076] vfio/pci: Expose vfio_pci_core_iowrite/read##size()

Expose vfio_pci_core_iowrite/read##size() to let it be used by drivers.

This functionality is needed to enable direct access to some physical
BAR of the device with the proper locks/checks in place.

The next patches from this series will use this functionality on a data
path flow when a direct access to the BAR is needed.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/20231219093247.170936-9-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci_rdwr.c | 50 +++++++++++++++++---------------
 include/linux/vfio_pci_core.h    | 19 ++++++++++++
 2 files changed, 45 insertions(+), 24 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index a9887fd6de46c..07fea08ea8a21 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -38,7 +38,7 @@
 #define vfio_iowrite8	iowrite8
 
 #define VFIO_IOWRITE(size) \
-static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev,		\
+int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev,	\
 			bool test_mem, u##size val, void __iomem *io)	\
 {									\
 	if (test_mem) {							\
@@ -55,7 +55,8 @@ static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev,		\
 		up_read(&vdev->memory_lock);				\
 									\
 	return 0;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(vfio_pci_core_iowrite##size);
 
 VFIO_IOWRITE(8)
 VFIO_IOWRITE(16)
@@ -65,7 +66,7 @@ VFIO_IOWRITE(64)
 #endif
 
 #define VFIO_IOREAD(size) \
-static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev,		\
+int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
 			bool test_mem, u##size *val, void __iomem *io)	\
 {									\
 	if (test_mem) {							\
@@ -82,7 +83,8 @@ static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev,		\
 		up_read(&vdev->memory_lock);				\
 									\
 	return 0;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(vfio_pci_core_ioread##size);
 
 VFIO_IOREAD(8)
 VFIO_IOREAD(16)
@@ -119,13 +121,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 4))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite32(vdev, test_mem,
-							 val, io + off);
+				ret = vfio_pci_core_iowrite32(vdev, test_mem,
+							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread32(vdev, test_mem,
-							&val, io + off);
+				ret = vfio_pci_core_ioread32(vdev, test_mem,
+							     &val, io + off);
 				if (ret)
 					return ret;
 
@@ -141,13 +143,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 2))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite16(vdev, test_mem,
-							 val, io + off);
+				ret = vfio_pci_core_iowrite16(vdev, test_mem,
+							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread16(vdev, test_mem,
-							&val, io + off);
+				ret = vfio_pci_core_ioread16(vdev, test_mem,
+							     &val, io + off);
 				if (ret)
 					return ret;
 
@@ -163,13 +165,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 1))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite8(vdev, test_mem,
-							val, io + off);
+				ret = vfio_pci_core_iowrite8(vdev, test_mem,
+							     val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread8(vdev, test_mem,
-						       &val, io + off);
+				ret = vfio_pci_core_ioread8(vdev, test_mem,
+							    &val, io + off);
 				if (ret)
 					return ret;
 
@@ -364,21 +366,21 @@ static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
 {
 	switch (ioeventfd->count) {
 	case 1:
-		vfio_pci_iowrite8(ioeventfd->vdev, test_mem,
-				  ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite8(ioeventfd->vdev, test_mem,
+				       ioeventfd->data, ioeventfd->addr);
 		break;
 	case 2:
-		vfio_pci_iowrite16(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite16(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 	case 4:
-		vfio_pci_iowrite32(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite32(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 #ifdef iowrite64
 	case 8:
-		vfio_pci_iowrite64(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite64(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 #endif
 	}
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 67ac58e20e1da..85e84b92751b6 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -131,4 +131,23 @@ int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar);
 pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 						pci_channel_state_t state);
 
+#define VFIO_IOWRITE_DECLATION(size) \
+int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev,	\
+			bool test_mem, u##size val, void __iomem *io);
+
+VFIO_IOWRITE_DECLATION(8)
+VFIO_IOWRITE_DECLATION(16)
+VFIO_IOWRITE_DECLATION(32)
+#ifdef iowrite64
+VFIO_IOWRITE_DECLATION(64)
+#endif
+
+#define VFIO_IOREAD_DECLATION(size) \
+int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
+			bool test_mem, u##size *val, void __iomem *io);
+
+VFIO_IOREAD_DECLATION(8)
+VFIO_IOREAD_DECLATION(16)
+VFIO_IOREAD_DECLATION(32)
+
 #endif /* VFIO_PCI_CORE_H */
-- 
GitLab


From eb61eca0e8c3efbdd6d3c9d2b7f70bf67e165f7d Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:47 +0200
Subject: [PATCH 1622/4076] vfio/virtio: Introduce a vfio driver over virtio
 devices

Introduce a vfio driver over virtio devices to support the legacy
interface functionality for VFs.

Background, from the virtio spec [1].
--------------------------------------------------------------------
In some systems, there is a need to support a virtio legacy driver with
a device that does not directly support the legacy interface. In such
scenarios, a group owner device can provide the legacy interface
functionality for the group member devices. The driver of the owner
device can then access the legacy interface of a member device on behalf
of the legacy member device driver.

For example, with the SR-IOV group type, group members (VFs) can not
present the legacy interface in an I/O BAR in BAR0 as expected by the
legacy pci driver. If the legacy driver is running inside a virtual
machine, the hypervisor executing the virtual machine can present a
virtual device with an I/O BAR in BAR0. The hypervisor intercepts the
legacy driver accesses to this I/O BAR and forwards them to the group
owner device (PF) using group administration commands.
--------------------------------------------------------------------

Specifically, this driver adds support for a virtio-net VF to be exposed
as a transitional device to a guest driver and allows the legacy IO BAR
functionality on top.

This allows a VM which uses a legacy virtio-net driver in the guest to
work transparently over a VF which its driver in the host is that new
driver.

The driver can be extended easily to support some other types of virtio
devices (e.g virtio-blk), by adding in a few places the specific type
properties as was done for virtio-net.

For now, only the virtio-net use case was tested and as such we introduce
the support only for such a device.

Practically,
Upon probing a VF for a virtio-net device, in case its PF supports
legacy access over the virtio admin commands and the VF doesn't have BAR
0, we set some specific 'vfio_device_ops' to be able to simulate in SW a
transitional device with I/O BAR in BAR 0.

The existence of the simulated I/O bar is reported later on by
overwriting the VFIO_DEVICE_GET_REGION_INFO command and the device
exposes itself as a transitional device by overwriting some properties
upon reading its config space.

Once we report the existence of I/O BAR as BAR 0 a legacy driver in the
guest may use it via read/write calls according to the virtio
specification.

Any read/write towards the control parts of the BAR will be captured by
the new driver and will be translated into admin commands towards the
device.

In addition, any data path read/write access (i.e. virtio driver
notifications) will be captured by the driver and forwarded to the
physical BAR which its properties were supplied by the admin command
VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO upon the probing/init flow.

With that code in place a legacy driver in the guest has the look and
feel as if having a transitional device with legacy support for both its
control and data path flows.

[1]
https://github.com/oasis-tcs/virtio-spec/commit/03c2d32e5093ca9f2a17797242fbef88efe94b8c

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/20231219093247.170936-10-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 MAINTAINERS                      |   7 +
 drivers/vfio/pci/Kconfig         |   2 +
 drivers/vfio/pci/Makefile        |   2 +
 drivers/vfio/pci/virtio/Kconfig  |  15 +
 drivers/vfio/pci/virtio/Makefile |   3 +
 drivers/vfio/pci/virtio/main.c   | 576 +++++++++++++++++++++++++++++++
 6 files changed, 605 insertions(+)
 create mode 100644 drivers/vfio/pci/virtio/Kconfig
 create mode 100644 drivers/vfio/pci/virtio/Makefile
 create mode 100644 drivers/vfio/pci/virtio/main.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 788be9ab5b733..c4cb7df15cd93 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22872,6 +22872,13 @@ L:	kvm@vger.kernel.org
 S:	Maintained
 F:	drivers/vfio/pci/mlx5/
 
+VFIO VIRTIO PCI DRIVER
+M:	Yishai Hadas <yishaih@nvidia.com>
+L:	kvm@vger.kernel.org
+L:	virtualization@lists.linux-foundation.org
+S:	Maintained
+F:	drivers/vfio/pci/virtio
+
 VFIO PCI DEVICE SPECIFIC DRIVERS
 R:	Jason Gunthorpe <jgg@nvidia.com>
 R:	Yishai Hadas <yishaih@nvidia.com>
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 8125e5f37832c..18c397df566d8 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -65,4 +65,6 @@ source "drivers/vfio/pci/hisilicon/Kconfig"
 
 source "drivers/vfio/pci/pds/Kconfig"
 
+source "drivers/vfio/pci/virtio/Kconfig"
+
 endmenu
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
index 45167be462d8f..046139a4eca5b 100644
--- a/drivers/vfio/pci/Makefile
+++ b/drivers/vfio/pci/Makefile
@@ -13,3 +13,5 @@ obj-$(CONFIG_MLX5_VFIO_PCI)           += mlx5/
 obj-$(CONFIG_HISI_ACC_VFIO_PCI) += hisilicon/
 
 obj-$(CONFIG_PDS_VFIO_PCI) += pds/
+
+obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio/
diff --git a/drivers/vfio/pci/virtio/Kconfig b/drivers/vfio/pci/virtio/Kconfig
new file mode 100644
index 0000000000000..fc3a0be9d8d42
--- /dev/null
+++ b/drivers/vfio/pci/virtio/Kconfig
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config VIRTIO_VFIO_PCI
+        tristate "VFIO support for VIRTIO NET PCI devices"
+        depends on VIRTIO_PCI_ADMIN_LEGACY
+        select VFIO_PCI_CORE
+        help
+          This provides support for exposing VIRTIO NET VF devices which support
+          legacy IO access, using the VFIO framework that can work with a legacy
+          virtio driver in the guest.
+          Based on PCIe spec, VFs do not support I/O Space.
+          As of that this driver emulates I/O BAR in software to let a VF be
+          seen as a transitional device by its users and let it work with
+          a legacy driver.
+
+          If you don't know what to do here, say N.
diff --git a/drivers/vfio/pci/virtio/Makefile b/drivers/vfio/pci/virtio/Makefile
new file mode 100644
index 0000000000000..7171105baf330
--- /dev/null
+++ b/drivers/vfio/pci/virtio/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio-vfio-pci.o
+virtio-vfio-pci-y := main.o
diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c
new file mode 100644
index 0000000000000..291c55b641f15
--- /dev/null
+++ b/drivers/vfio/pci/virtio/main.c
@@ -0,0 +1,576 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pm_runtime.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <linux/vfio_pci_core.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_net.h>
+#include <linux/virtio_pci_admin.h>
+
+struct virtiovf_pci_core_device {
+	struct vfio_pci_core_device core_device;
+	u8 *bar0_virtual_buf;
+	/* synchronize access to the virtual buf */
+	struct mutex bar_mutex;
+	void __iomem *notify_addr;
+	u64 notify_offset;
+	__le32 pci_base_addr_0;
+	__le16 pci_cmd;
+	u8 bar0_virtual_buf_size;
+	u8 notify_bar;
+};
+
+static int
+virtiovf_issue_legacy_rw_cmd(struct virtiovf_pci_core_device *virtvdev,
+			     loff_t pos, char __user *buf,
+			     size_t count, bool read)
+{
+	bool msix_enabled =
+		(virtvdev->core_device.irq_type == VFIO_PCI_MSIX_IRQ_INDEX);
+	struct pci_dev *pdev = virtvdev->core_device.pdev;
+	u8 *bar0_buf = virtvdev->bar0_virtual_buf;
+	bool common;
+	u8 offset;
+	int ret;
+
+	common = pos < VIRTIO_PCI_CONFIG_OFF(msix_enabled);
+	/* offset within the relevant configuration area */
+	offset = common ? pos : pos - VIRTIO_PCI_CONFIG_OFF(msix_enabled);
+	mutex_lock(&virtvdev->bar_mutex);
+	if (read) {
+		if (common)
+			ret = virtio_pci_admin_legacy_common_io_read(pdev, offset,
+					count, bar0_buf + pos);
+		else
+			ret = virtio_pci_admin_legacy_device_io_read(pdev, offset,
+					count, bar0_buf + pos);
+		if (ret)
+			goto out;
+		if (copy_to_user(buf, bar0_buf + pos, count))
+			ret = -EFAULT;
+	} else {
+		if (copy_from_user(bar0_buf + pos, buf, count)) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		if (common)
+			ret = virtio_pci_admin_legacy_common_io_write(pdev, offset,
+					count, bar0_buf + pos);
+		else
+			ret = virtio_pci_admin_legacy_device_io_write(pdev, offset,
+					count, bar0_buf + pos);
+	}
+out:
+	mutex_unlock(&virtvdev->bar_mutex);
+	return ret;
+}
+
+static int
+virtiovf_pci_bar0_rw(struct virtiovf_pci_core_device *virtvdev,
+		     loff_t pos, char __user *buf,
+		     size_t count, bool read)
+{
+	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
+	struct pci_dev *pdev = core_device->pdev;
+	u16 queue_notify;
+	int ret;
+
+	if (!(le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO))
+		return -EIO;
+
+	if (pos + count > virtvdev->bar0_virtual_buf_size)
+		return -EINVAL;
+
+	ret = pm_runtime_resume_and_get(&pdev->dev);
+	if (ret) {
+		pci_info_ratelimited(pdev, "runtime resume failed %d\n", ret);
+		return -EIO;
+	}
+
+	switch (pos) {
+	case VIRTIO_PCI_QUEUE_NOTIFY:
+		if (count != sizeof(queue_notify)) {
+			ret = -EINVAL;
+			goto end;
+		}
+		if (read) {
+			ret = vfio_pci_core_ioread16(core_device, true, &queue_notify,
+						     virtvdev->notify_addr);
+			if (ret)
+				goto end;
+			if (copy_to_user(buf, &queue_notify,
+					 sizeof(queue_notify))) {
+				ret = -EFAULT;
+				goto end;
+			}
+		} else {
+			if (copy_from_user(&queue_notify, buf, count)) {
+				ret = -EFAULT;
+				goto end;
+			}
+			ret = vfio_pci_core_iowrite16(core_device, true, queue_notify,
+						      virtvdev->notify_addr);
+		}
+		break;
+	default:
+		ret = virtiovf_issue_legacy_rw_cmd(virtvdev, pos, buf, count,
+						   read);
+	}
+
+end:
+	pm_runtime_put(&pdev->dev);
+	return ret ? ret : count;
+}
+
+static bool range_intersect_range(loff_t range1_start, size_t count1,
+				  loff_t range2_start, size_t count2,
+				  loff_t *start_offset,
+				  size_t *intersect_count,
+				  size_t *register_offset)
+{
+	if (range1_start <= range2_start &&
+	    range1_start + count1 > range2_start) {
+		*start_offset = range2_start - range1_start;
+		*intersect_count = min_t(size_t, count2,
+					 range1_start + count1 - range2_start);
+		*register_offset = 0;
+		return true;
+	}
+
+	if (range1_start > range2_start &&
+	    range1_start < range2_start + count2) {
+		*start_offset = 0;
+		*intersect_count = min_t(size_t, count1,
+					 range2_start + count2 - range1_start);
+		*register_offset = range1_start - range2_start;
+		return true;
+	}
+
+	return false;
+}
+
+static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev,
+					char __user *buf, size_t count,
+					loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	size_t register_offset;
+	loff_t copy_offset;
+	size_t copy_count;
+	__le32 val32;
+	__le16 val16;
+	u8 val8;
+	int ret;
+
+	ret = vfio_pci_core_read(core_vdev, buf, count, ppos);
+	if (ret < 0)
+		return ret;
+
+	if (range_intersect_range(pos, count, PCI_DEVICE_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		val16 = cpu_to_le16(VIRTIO_TRANS_ID_NET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, copy_count))
+			return -EFAULT;
+	}
+
+	if ((le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO) &&
+	    range_intersect_range(pos, count, PCI_COMMAND, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		if (copy_from_user((void *)&val16 + register_offset, buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+		val16 |= cpu_to_le16(PCI_COMMAND_IO);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_REVISION_ID, sizeof(val8),
+				  &copy_offset, &copy_count, &register_offset)) {
+		/* Transional needs to have revision 0 */
+		val8 = 0;
+		if (copy_to_user(buf + copy_offset, &val8, copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, sizeof(val32),
+				  &copy_offset, &copy_count, &register_offset)) {
+		u32 bar_mask = ~(virtvdev->bar0_virtual_buf_size - 1);
+		u32 pci_base_addr_0 = le32_to_cpu(virtvdev->pci_base_addr_0);
+
+		val32 = cpu_to_le32((pci_base_addr_0 & bar_mask) | PCI_BASE_ADDRESS_SPACE_IO);
+		if (copy_to_user(buf + copy_offset, (void *)&val32 + register_offset, copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_SUBSYSTEM_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		/*
+		 * Transitional devices use the PCI subsystem device id as
+		 * virtio device id, same as legacy driver always did.
+		 */
+		val16 = cpu_to_le16(VIRTIO_ID_NET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_SUBSYSTEM_VENDOR_ID, sizeof(val16),
+				  &copy_offset, &copy_count, &register_offset)) {
+		val16 = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET);
+		if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset,
+				 copy_count))
+			return -EFAULT;
+	}
+
+	return count;
+}
+
+static ssize_t
+virtiovf_pci_core_read(struct vfio_device *core_vdev, char __user *buf,
+		       size_t count, loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+
+	if (!count)
+		return 0;
+
+	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
+		return virtiovf_pci_read_config(core_vdev, buf, count, ppos);
+
+	if (index == VFIO_PCI_BAR0_REGION_INDEX)
+		return virtiovf_pci_bar0_rw(virtvdev, pos, buf, count, true);
+
+	return vfio_pci_core_read(core_vdev, buf, count, ppos);
+}
+
+static ssize_t virtiovf_pci_write_config(struct vfio_device *core_vdev,
+					 const char __user *buf, size_t count,
+					 loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	size_t register_offset;
+	loff_t copy_offset;
+	size_t copy_count;
+
+	if (range_intersect_range(pos, count, PCI_COMMAND, sizeof(virtvdev->pci_cmd),
+				  &copy_offset, &copy_count,
+				  &register_offset)) {
+		if (copy_from_user((void *)&virtvdev->pci_cmd + register_offset,
+				   buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+	}
+
+	if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0,
+				  sizeof(virtvdev->pci_base_addr_0),
+				  &copy_offset, &copy_count,
+				  &register_offset)) {
+		if (copy_from_user((void *)&virtvdev->pci_base_addr_0 + register_offset,
+				   buf + copy_offset,
+				   copy_count))
+			return -EFAULT;
+	}
+
+	return vfio_pci_core_write(core_vdev, buf, count, ppos);
+}
+
+static ssize_t
+virtiovf_pci_core_write(struct vfio_device *core_vdev, const char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+
+	if (!count)
+		return 0;
+
+	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
+		return virtiovf_pci_write_config(core_vdev, buf, count, ppos);
+
+	if (index == VFIO_PCI_BAR0_REGION_INDEX)
+		return virtiovf_pci_bar0_rw(virtvdev, pos, (char __user *)buf, count, false);
+
+	return vfio_pci_core_write(core_vdev, buf, count, ppos);
+}
+
+static int
+virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev,
+				   unsigned int cmd, unsigned long arg)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	unsigned long minsz = offsetofend(struct vfio_region_info, offset);
+	void __user *uarg = (void __user *)arg;
+	struct vfio_region_info info = {};
+
+	if (copy_from_user(&info, uarg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	switch (info.index) {
+	case VFIO_PCI_BAR0_REGION_INDEX:
+		info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+		info.size = virtvdev->bar0_virtual_buf_size;
+		info.flags = VFIO_REGION_INFO_FLAG_READ |
+			     VFIO_REGION_INFO_FLAG_WRITE;
+		return copy_to_user(uarg, &info, minsz) ? -EFAULT : 0;
+	default:
+		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
+	}
+}
+
+static long
+virtiovf_vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
+			     unsigned long arg)
+{
+	switch (cmd) {
+	case VFIO_DEVICE_GET_REGION_INFO:
+		return virtiovf_pci_ioctl_get_region_info(core_vdev, cmd, arg);
+	default:
+		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
+	}
+}
+
+static int
+virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev)
+{
+	struct vfio_pci_core_device *core_device = &virtvdev->core_device;
+	int ret;
+
+	/*
+	 * Setup the BAR where the 'notify' exists to be used by vfio as well
+	 * This will let us mmap it only once and use it when needed.
+	 */
+	ret = vfio_pci_core_setup_barmap(core_device,
+					 virtvdev->notify_bar);
+	if (ret)
+		return ret;
+
+	virtvdev->notify_addr = core_device->barmap[virtvdev->notify_bar] +
+			virtvdev->notify_offset;
+	return 0;
+}
+
+static int virtiovf_pci_open_device(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct vfio_pci_core_device *vdev = &virtvdev->core_device;
+	int ret;
+
+	ret = vfio_pci_core_enable(vdev);
+	if (ret)
+		return ret;
+
+	if (virtvdev->bar0_virtual_buf) {
+		/*
+		 * Upon close_device() the vfio_pci_core_disable() is called
+		 * and will close all the previous mmaps, so it seems that the
+		 * valid life cycle for the 'notify' addr is per open/close.
+		 */
+		ret = virtiovf_set_notify_addr(virtvdev);
+		if (ret) {
+			vfio_pci_core_disable(vdev);
+			return ret;
+		}
+	}
+
+	vfio_pci_core_finish_enable(vdev);
+	return 0;
+}
+
+static int virtiovf_get_device_config_size(unsigned short device)
+{
+	/* Network card */
+	return offsetofend(struct virtio_net_config, status);
+}
+
+static int virtiovf_read_notify_info(struct virtiovf_pci_core_device *virtvdev)
+{
+	u64 offset;
+	int ret;
+	u8 bar;
+
+	ret = virtio_pci_admin_legacy_io_notify_info(virtvdev->core_device.pdev,
+				VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM,
+				&bar, &offset);
+	if (ret)
+		return ret;
+
+	virtvdev->notify_bar = bar;
+	virtvdev->notify_offset = offset;
+	return 0;
+}
+
+static int virtiovf_pci_init_device(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+	struct pci_dev *pdev;
+	int ret;
+
+	ret = vfio_pci_core_init_dev(core_vdev);
+	if (ret)
+		return ret;
+
+	pdev = virtvdev->core_device.pdev;
+	ret = virtiovf_read_notify_info(virtvdev);
+	if (ret)
+		return ret;
+
+	virtvdev->bar0_virtual_buf_size = VIRTIO_PCI_CONFIG_OFF(true) +
+				virtiovf_get_device_config_size(pdev->device);
+	BUILD_BUG_ON(!is_power_of_2(virtvdev->bar0_virtual_buf_size));
+	virtvdev->bar0_virtual_buf = kzalloc(virtvdev->bar0_virtual_buf_size,
+					     GFP_KERNEL);
+	if (!virtvdev->bar0_virtual_buf)
+		return -ENOMEM;
+	mutex_init(&virtvdev->bar_mutex);
+	return 0;
+}
+
+static void virtiovf_pci_core_release_dev(struct vfio_device *core_vdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = container_of(
+		core_vdev, struct virtiovf_pci_core_device, core_device.vdev);
+
+	kfree(virtvdev->bar0_virtual_buf);
+	vfio_pci_core_release_dev(core_vdev);
+}
+
+static const struct vfio_device_ops virtiovf_vfio_pci_tran_ops = {
+	.name = "virtio-vfio-pci-trans",
+	.init = virtiovf_pci_init_device,
+	.release = virtiovf_pci_core_release_dev,
+	.open_device = virtiovf_pci_open_device,
+	.close_device = vfio_pci_core_close_device,
+	.ioctl = virtiovf_vfio_pci_core_ioctl,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = virtiovf_pci_core_read,
+	.write = virtiovf_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static const struct vfio_device_ops virtiovf_vfio_pci_ops = {
+	.name = "virtio-vfio-pci",
+	.init = vfio_pci_core_init_dev,
+	.release = vfio_pci_core_release_dev,
+	.open_device = virtiovf_pci_open_device,
+	.close_device = vfio_pci_core_close_device,
+	.ioctl = vfio_pci_core_ioctl,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = vfio_pci_core_read,
+	.write = vfio_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static bool virtiovf_bar0_exists(struct pci_dev *pdev)
+{
+	struct resource *res = pdev->resource;
+
+	return res->flags;
+}
+
+static int virtiovf_pci_probe(struct pci_dev *pdev,
+			      const struct pci_device_id *id)
+{
+	const struct vfio_device_ops *ops = &virtiovf_vfio_pci_ops;
+	struct virtiovf_pci_core_device *virtvdev;
+	int ret;
+
+	if (pdev->is_virtfn && virtio_pci_admin_has_legacy_io(pdev) &&
+	    !virtiovf_bar0_exists(pdev))
+		ops = &virtiovf_vfio_pci_tran_ops;
+
+	virtvdev = vfio_alloc_device(virtiovf_pci_core_device, core_device.vdev,
+				     &pdev->dev, ops);
+	if (IS_ERR(virtvdev))
+		return PTR_ERR(virtvdev);
+
+	dev_set_drvdata(&pdev->dev, &virtvdev->core_device);
+	ret = vfio_pci_core_register_device(&virtvdev->core_device);
+	if (ret)
+		goto out;
+	return 0;
+out:
+	vfio_put_device(&virtvdev->core_device.vdev);
+	return ret;
+}
+
+static void virtiovf_pci_remove(struct pci_dev *pdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
+
+	vfio_pci_core_unregister_device(&virtvdev->core_device);
+	vfio_put_device(&virtvdev->core_device.vdev);
+}
+
+static const struct pci_device_id virtiovf_pci_table[] = {
+	/* Only virtio-net is supported/tested so far */
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_REDHAT_QUMRANET, 0x1041) },
+	{}
+};
+
+MODULE_DEVICE_TABLE(pci, virtiovf_pci_table);
+
+void virtiovf_pci_aer_reset_done(struct pci_dev *pdev)
+{
+	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
+
+	virtvdev->pci_cmd = 0;
+}
+
+static const struct pci_error_handlers virtiovf_err_handlers = {
+	.reset_done = virtiovf_pci_aer_reset_done,
+	.error_detected = vfio_pci_core_aer_err_detected,
+};
+
+static struct pci_driver virtiovf_pci_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = virtiovf_pci_table,
+	.probe = virtiovf_pci_probe,
+	.remove = virtiovf_pci_remove,
+	.err_handler = &virtiovf_err_handlers,
+	.driver_managed_dma = true,
+};
+
+module_pci_driver(virtiovf_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Yishai Hadas <yishaih@nvidia.com>");
+MODULE_DESCRIPTION(
+	"VIRTIO VFIO PCI - User Level meta-driver for VIRTIO NET devices");
-- 
GitLab


From 64c166821e034dda14e7a1a2d648347662054e0e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 20 Dec 2023 05:22:29 +0000
Subject: [PATCH 1623/4076] kernfs: d_obtain_alias(NULL) will do the right
 thing...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/r/20231220052229.GH1674809@ZenIV
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/mount.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 4628edde2e7e1..0c93cad0f0aca 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -125,9 +125,6 @@ static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
 
 	inode = kernfs_get_inode(sb, kn);
 	kernfs_put(kn);
-	if (!inode)
-		return ERR_PTR(-ESTALE);
-
 	return d_obtain_alias(inode);
 }
 
-- 
GitLab


From 8be0c877fb3b671dac0cf56d1f1f9e65f9a9fb81 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 16:43:05 +0100
Subject: [PATCH 1624/4076] thunderbolt: make tb_bus_type const

Now that the driver core can properly handle constant struct bus_type,
move the tb_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Cc: Andreas Noever <andreas.noever@gmail.com>
Cc: Michael Jamet <michael.jamet@intel.com>
Cc: Yehezkel Bernat <YehezkelShB@gmail.com>
Cc:  <linux-usb@vger.kernel.org>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://lore.kernel.org/r/2023121904-utopia-broadcast-06d1@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/thunderbolt/domain.c | 2 +-
 include/linux/thunderbolt.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index ec7b5f65804e4..9fb1a64f3300b 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -307,7 +307,7 @@ static const struct attribute_group *domain_attr_groups[] = {
 	NULL,
 };
 
-struct bus_type tb_bus_type = {
+const struct bus_type tb_bus_type = {
 	.name = "thunderbolt",
 	.match = tb_service_match,
 	.probe = tb_service_probe,
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index 6151c210d987d..2c835e5c41f63 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -86,7 +86,7 @@ struct tb {
 	unsigned long privdata[];
 };
 
-extern struct bus_type tb_bus_type;
+extern const struct bus_type tb_bus_type;
 extern struct device_type tb_service_type;
 extern struct device_type tb_xdomain_type;
 
-- 
GitLab


From d605ba72e9c04efc35fcf225df59d4ccb1d4061f Mon Sep 17 00:00:00 2001
From: Marc Ferland <marc.ferland@sonatest.com>
Date: Mon, 18 Dec 2023 10:02:26 -0500
Subject: [PATCH 1625/4076] w1: ds2490: support block sizes larger than 128
 bytes in ds_read_block

The current ds_read_block function only supports block sizes up to
128 bytes, which is the depth of the 'data out' fifo on the ds2490.

Reading larger blocks will fail with a: -110 (ETIMEDOUT) from
usb_control_msg(). Example:

    $ dd if=/sys/bus/w1/devices/43-000000478756/eeprom bs=256 count=1

yields to the following message from the kernel:

    usb 5-1: Failed to write 1-wire data to ep0x2: err=-110.

I discovered this issue while implementing support for the ds28ec20
eeprom in the w1-2433 driver. This driver accepts reading blocks of
sizes up to the size of the entire memory (2560 bytes in the case of
the ds28ec20). Note that this issue _does not_ arise when the kernel
is configured with CONFIG_W1_SLAVE_DS2433_CRC enabled since in this
mode the driver reads one 32 byte block at a time (a single memory
page).

Also, from the ds2490 datasheet (2995.pdf, page 22, BLOCK I/O
command):

     For a block write sequence the EP2 FIFO must be pre-filled with
     data before command execution. Additionally, for block sizes
     greater then the FIFO size, the FIFO content status must be
     monitored by host SW so that additional data can be sent to the
     FIFO when necessary. A similar EP3 FIFO content monitoring
     requirement exists for block read sequences. During a block read
     the number of bytes loaded into the EP3 FIFO must be monitored so
     that the data can be read before the FIFO overflows.

Breaking the block in smaller 128 bytes chunks and simply calling the
original code sequence has solved the issue for me.

Tested with a DS1490F usb<->one-wire adapter and both the DS28EC20 and
DS2433 eeprom memories.

Signed-off-by: Marc Ferland <marc.ferland@sonatest.com>
Link: https://lore.kernel.org/r/20231218150230.1992448-2-marc.ferland@sonatest.com
[krzysztof: fix checkpatch 'spaces preferred around']
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/masters/ds2490.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c
index 5f5b97e247004..e1cac0730cbbf 100644
--- a/drivers/w1/masters/ds2490.c
+++ b/drivers/w1/masters/ds2490.c
@@ -98,6 +98,8 @@
 #define ST_EPOF				0x80
 /* Status transfer size, 16 bytes status, 16 byte result flags */
 #define ST_SIZE				0x20
+/* 1-wire data i/o fifo size, 128 bytes */
+#define FIFO_SIZE			0x80
 
 /* Result Register flags */
 #define RR_DETECT			0xA5 /* New device detected */
@@ -614,14 +616,11 @@ static int ds_read_byte(struct ds_device *dev, u8 *byte)
 	return 0;
 }
 
-static int ds_read_block(struct ds_device *dev, u8 *buf, int len)
+static int read_block_chunk(struct ds_device *dev, u8 *buf, int len)
 {
 	struct ds_status st;
 	int err;
 
-	if (len > 64*1024)
-		return -E2BIG;
-
 	memset(buf, 0xFF, len);
 
 	err = ds_send_data(dev, buf, len);
@@ -640,6 +639,24 @@ static int ds_read_block(struct ds_device *dev, u8 *buf, int len)
 	return err;
 }
 
+static int ds_read_block(struct ds_device *dev, u8 *buf, int len)
+{
+	int err, to_read, rem = len;
+
+	if (len > 64 * 1024)
+		return -E2BIG;
+
+	do {
+		to_read = rem <= FIFO_SIZE ? rem : FIFO_SIZE;
+		err = read_block_chunk(dev, &buf[len - rem], to_read);
+		if (err < 0)
+			return err;
+		rem -= to_read;
+	} while (rem);
+
+	return err;
+}
+
 static int ds_write_block(struct ds_device *dev, u8 *buf, int len)
 {
 	int err;
-- 
GitLab


From 86626c06d651c72bc10c25f263e98fa90655b5ae Mon Sep 17 00:00:00 2001
From: Marc Ferland <marc.ferland@sonatest.com>
Date: Mon, 18 Dec 2023 10:02:27 -0500
Subject: [PATCH 1626/4076] w1: ds2433: remove unused definitions

Both W1_F23_TIME and W1_PAGE_COUNT are unused, get rid of them.

Signed-off-by: Marc Ferland <marc.ferland@sonatest.com>
Link: https://lore.kernel.org/r/20231218150230.1992448-3-marc.ferland@sonatest.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/slaves/w1_ds2433.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c
index 9f21fd98f7995..cd99eceac1ae5 100644
--- a/drivers/w1/slaves/w1_ds2433.c
+++ b/drivers/w1/slaves/w1_ds2433.c
@@ -25,13 +25,10 @@
 #define W1_EEPROM_DS2433	0x23
 
 #define W1_EEPROM_SIZE		512
-#define W1_PAGE_COUNT		16
 #define W1_PAGE_SIZE		32
 #define W1_PAGE_BITS		5
 #define W1_PAGE_MASK		0x1F
 
-#define W1_F23_TIME		300
-
 #define W1_F23_READ_EEPROM	0xF0
 #define W1_F23_WRITE_SCRATCH	0x0F
 #define W1_F23_READ_SCRATCH	0xAA
-- 
GitLab


From 75f0c1c78d709f258004562a540c83bc05bfb962 Mon Sep 17 00:00:00 2001
From: Marc Ferland <marc.ferland@sonatest.com>
Date: Mon, 18 Dec 2023 10:02:28 -0500
Subject: [PATCH 1627/4076] w1: ds2433: introduce a configuration structure

Add a ds2433_config structure for parameters that are different
between the ds2433 and the ds28ec20. The goal is to reuse the same
code for both chips.

A pointer to this config structure is added to w1_f23_data and the
CONFIG_W1_SLAVE_DS2433_CRC ifdefs are adjusted since now both driver
configurations (with or without crc support) will make use of
w1_f23_data.

Also, the 'memory' buffer is now dynamically allocated based on the
size specififed in the config structure to help support memories of
different sizes.

Signed-off-by: Marc Ferland <marc.ferland@sonatest.com>
Link: https://lore.kernel.org/r/20231218150230.1992448-4-marc.ferland@sonatest.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/slaves/w1_ds2433.c | 47 ++++++++++++++++++++++++++---------
 1 file changed, 35 insertions(+), 12 deletions(-)

diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c
index cd99eceac1ae5..0c67082c8bb73 100644
--- a/drivers/w1/slaves/w1_ds2433.c
+++ b/drivers/w1/slaves/w1_ds2433.c
@@ -34,9 +34,24 @@
 #define W1_F23_READ_SCRATCH	0xAA
 #define W1_F23_COPY_SCRATCH	0x55
 
+struct ds2433_config {
+	size_t eeprom_size;		/* eeprom size in bytes */
+	unsigned int page_count;	/* number of 256 bits pages */
+	unsigned int tprog;		/* time in ms for page programming */
+};
+
+static const struct ds2433_config config_f23 = {
+	.eeprom_size = W1_EEPROM_SIZE,
+	.page_count = 16,
+	.tprog = 5,
+};
+
 struct w1_f23_data {
-	u8	memory[W1_EEPROM_SIZE];
+#ifdef CONFIG_W1_SLAVE_DS2433_CRC
+	u8	*memory;
 	u32	validcrc;
+#endif
+	const struct ds2433_config *cfg;
 };
 
 /*
@@ -95,7 +110,7 @@ static ssize_t eeprom_read(struct file *filp, struct kobject *kobj,
 	u8 wrbuf[3];
 #endif
 
-	count = w1_f23_fix_count(off, count, W1_EEPROM_SIZE);
+	count = w1_f23_fix_count(off, count, bin_attr->size);
 	if (!count)
 		return 0;
 
@@ -150,9 +165,7 @@ out_up:
  */
 static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data)
 {
-#ifdef CONFIG_W1_SLAVE_DS2433_CRC
 	struct w1_f23_data *f23 = sl->family_data;
-#endif
 	u8 wrbuf[4];
 	u8 rdbuf[W1_PAGE_SIZE + 3];
 	u8 es = (addr + len - 1) & 0x1f;
@@ -188,8 +201,8 @@ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data)
 	wrbuf[3] = es;
 	w1_write_block(sl->master, wrbuf, 4);
 
-	/* Sleep for 5 ms to wait for the write to complete */
-	msleep(5);
+	/* Sleep for tprog ms to wait for the write to complete */
+	msleep(f23->cfg->tprog);
 
 	/* Reset the bus to wake up the EEPROM (this may not be needed) */
 	w1_reset_bus(sl->master);
@@ -206,7 +219,7 @@ static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
 	int addr, len, idx;
 
-	count = w1_f23_fix_count(off, count, W1_EEPROM_SIZE);
+	count = w1_f23_fix_count(off, count, bin_attr->size);
 	if (!count)
 		return 0;
 
@@ -268,24 +281,34 @@ static const struct attribute_group *w1_f23_groups[] = {
 
 static int w1_f23_add_slave(struct w1_slave *sl)
 {
-#ifdef CONFIG_W1_SLAVE_DS2433_CRC
 	struct w1_f23_data *data;
 
 	data = kzalloc(sizeof(struct w1_f23_data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
+
+	data->cfg = &config_f23;
+
+#ifdef CONFIG_W1_SLAVE_DS2433_CRC
+	data->memory = kzalloc(data->cfg->eeprom_size, GFP_KERNEL);
+	if (!data->memory) {
+		kfree(data);
+		return -ENOMEM;
+	}
+#endif /* CONFIG_W1_SLAVE_DS2433_CRC */
 	sl->family_data = data;
 
-#endif	/* CONFIG_W1_SLAVE_DS2433_CRC */
 	return 0;
 }
 
 static void w1_f23_remove_slave(struct w1_slave *sl)
 {
-#ifdef CONFIG_W1_SLAVE_DS2433_CRC
-	kfree(sl->family_data);
+	struct w1_f23_data *data = sl->family_data;
 	sl->family_data = NULL;
-#endif	/* CONFIG_W1_SLAVE_DS2433_CRC */
+#ifdef CONFIG_W1_SLAVE_DS2433_CRC
+	kfree(data->memory);
+#endif /* CONFIG_W1_SLAVE_DS2433_CRC */
+	kfree(data);
 }
 
 static const struct w1_family_ops w1_f23_fops = {
-- 
GitLab


From 3fe3a1bfef75efcdfbcca955fe1d47ec07215110 Mon Sep 17 00:00:00 2001
From: Marc Ferland <marc.ferland@sonatest.com>
Date: Mon, 18 Dec 2023 10:02:29 -0500
Subject: [PATCH 1628/4076] w1: ds2433: use the kernel bitmap implementation

The ds2433 driver uses the 'validcrc' variable to mark out which pages
have been successfully (crc is valid) retrieved from the eeprom and
placed in the internal 'memory' buffer (see CONFIG_W1_SLAVE_DS2433_CRC).

The current implementation assumes that the number of pages will never
go beyond 32 pages (bit field is a u32). This is fine for the ds2433
since it only has 16 pages.

On the ds28ec20 though, the number of pages increases to 80 which will
not fit on a single u32.

As a solution, I replaced the u32 variable with a standard bitmap and
set the number of bits to 32 which is the same size we had before.

Signed-off-by: Marc Ferland <marc.ferland@sonatest.com>
Link: https://lore.kernel.org/r/20231218150230.1992448-5-marc.ferland@sonatest.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/slaves/w1_ds2433.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c
index 0c67082c8bb73..87df76094e03f 100644
--- a/drivers/w1/slaves/w1_ds2433.c
+++ b/drivers/w1/slaves/w1_ds2433.c
@@ -28,6 +28,7 @@
 #define W1_PAGE_SIZE		32
 #define W1_PAGE_BITS		5
 #define W1_PAGE_MASK		0x1F
+#define W1_VALIDCRC_MAX		32
 
 #define W1_F23_READ_EEPROM	0xF0
 #define W1_F23_WRITE_SCRATCH	0x0F
@@ -48,8 +49,8 @@ static const struct ds2433_config config_f23 = {
 
 struct w1_f23_data {
 #ifdef CONFIG_W1_SLAVE_DS2433_CRC
-	u8	*memory;
-	u32	validcrc;
+	u8 *memory;
+	DECLARE_BITMAP(validcrc, W1_VALIDCRC_MAX);
 #endif
 	const struct ds2433_config *cfg;
 };
@@ -76,11 +77,11 @@ static int w1_f23_refresh_block(struct w1_slave *sl, struct w1_f23_data *data,
 	u8	wrbuf[3];
 	int	off = block * W1_PAGE_SIZE;
 
-	if (data->validcrc & (1 << block))
+	if (test_bit(block, data->validcrc))
 		return 0;
 
 	if (w1_reset_select_slave(sl)) {
-		data->validcrc = 0;
+		bitmap_zero(data->validcrc, data->cfg->page_count);
 		return -EIO;
 	}
 
@@ -92,7 +93,7 @@ static int w1_f23_refresh_block(struct w1_slave *sl, struct w1_f23_data *data,
 
 	/* cache the block if the CRC is valid */
 	if (crc16(CRC16_INIT, &data->memory[off], W1_PAGE_SIZE) == CRC16_VALID)
-		data->validcrc |= (1 << block);
+		set_bit(block, data->validcrc);
 
 	return 0;
 }
@@ -207,7 +208,7 @@ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data)
 	/* Reset the bus to wake up the EEPROM (this may not be needed) */
 	w1_reset_bus(sl->master);
 #ifdef CONFIG_W1_SLAVE_DS2433_CRC
-	f23->validcrc &= ~(1 << (addr >> W1_PAGE_BITS));
+	clear_bit(addr >> W1_PAGE_BITS, f23->validcrc);
 #endif
 	return 0;
 }
@@ -290,11 +291,17 @@ static int w1_f23_add_slave(struct w1_slave *sl)
 	data->cfg = &config_f23;
 
 #ifdef CONFIG_W1_SLAVE_DS2433_CRC
+	if (data->cfg->page_count > W1_VALIDCRC_MAX) {
+		dev_err(&sl->dev, "page count too big for crc bitmap\n");
+		kfree(data);
+		return -EINVAL;
+	}
 	data->memory = kzalloc(data->cfg->eeprom_size, GFP_KERNEL);
 	if (!data->memory) {
 		kfree(data);
 		return -ENOMEM;
 	}
+	bitmap_zero(data->validcrc, data->cfg->page_count);
 #endif /* CONFIG_W1_SLAVE_DS2433_CRC */
 	sl->family_data = data;
 
-- 
GitLab


From 93c4bb3666a3d463c73a66ab3cc78a4c4b83631a Mon Sep 17 00:00:00 2001
From: Marc Ferland <marc.ferland@sonatest.com>
Date: Mon, 18 Dec 2023 10:02:30 -0500
Subject: [PATCH 1629/4076] w1: ds2433: add support for ds28ec20 eeprom

The ds28ec20 eeprom is (almost) backward compatible with the
ds2433. The only differences are:

- the eeprom size is now 2560 bytes instead of 512;
- the number of pages is now 80 (same page size as the ds2433: 256 bits);
- the programming time has increased from 5ms to 10ms;

This patch adds support for the ds28ec20 to the ds2433 driver. From
the datasheet: The DS28EC20 provides a high degree of backward
compatibility with the DS2433. Besides the different family codes, the
only protocol change that is required on an existing DS2433
implementation is a lengthening of the programming duration (tPROG)
from 5ms to 10ms.

dmesg now returns:

    w1_master_driver w1_bus_master1: Attaching one wire slave 43.000000478756 crc e0

instead of:

    w1_master_driver w1_bus_master1: Attaching one wire slave 43.000000478756 crc e0
    w1_master_driver w1_bus_master1: Family 43 for 43.000000478756.e0 is not registered.

Test script writing/reading random data (CONFIG_W1_SLAVE_DS2433_CRC is
not set):

    #!/bin/sh

    EEPROM=/sys/bus/w1/devices/43-000000478756/eeprom
    BINFILE1=/home/root/file1.bin
    BINFILE2=/home/root/file2.bin

    for BS in 1 2 3 4 8 16 32 64 128 256 512 1024 2560; do
        dd if=/dev/random of=${BINFILE1} bs=${BS} count=1 status=none
        dd if=${BINFILE1} of=${EEPROM} status=none
        dd if=${EEPROM} of=${BINFILE2} bs=${BS} count=1 status=none
        if ! cmp --silent ${BINFILE1} ${BINFILE2}; then
    	    echo file1
    	    hexdump ${BINFILE1}
    	    echo file2
    	    hexdump ${BINFILE2}
    	    echo FAIL
    	    exit 1
        fi
        echo "${BS} OK!"
    done

Results:

    # ./test.sh
    1 OK!
    2 OK!
    3 OK!
    4 OK!
    8 OK!
    16 OK!
    32 OK!
    64 OK!
    128 OK!
    256 OK!
    512 OK!
    1024 OK!
    2560 OK!

Tests with CONFIG_W1_SLAVE_DS2433_CRC=y:

    $ cat /proc/config.gz | gunzip | grep CONFIG_W1_SLAVE_DS2433
    CONFIG_W1_SLAVE_DS2433=m
    CONFIG_W1_SLAVE_DS2433_CRC=y

    # create a 32 bytes block with a crc, i.e.:
    00000000  31 32 33 34 35 36 37 38  39 3a 3b 3c 3d 3e 3f 40  |123456789:;<=>?@|
    00000010  41 42 43 44 45 46 47 48  49 4a 4b 4c 4d 4e ba 63  |ABCDEFGHIJKLMN.c|

    # fill all 80 blocks
    $ dd if=test.bin of=/sys/bus/w1/devices/43-000000478756/eeprom bs=32 count=80

    # read back all blocks, i.e.:
    $ hexdump -C /sys/bus/w1/devices/43-000000478756/eeprom
    00000000  31 32 33 34 35 36 37 38  39 3a 3b 3c 3d 3e 3f 40  |123456789:;<=>?@|
    00000010  41 42 43 44 45 46 47 48  49 4a 4b 4c 4d 4e ba 63  |ABCDEFGHIJKLMN.c|
    00000020  31 32 33 34 35 36 37 38  39 3a 3b 3c 3d 3e 3f 40  |123456789:;<=>?@|
    00000030  41 42 43 44 45 46 47 48  49 4a 4b 4c 4d 4e ba 63  |ABCDEFGHIJKLMN.c|
    ...
    000009e0  31 32 33 34 35 36 37 38  39 3a 3b 3c 3d 3e 3f 40  |123456789:;<=>?@|
    000009f0  41 42 43 44 45 46 47 48  49 4a 4b 4c 4d 4e ba 63  |ABCDEFGHIJKLMN.c|
    00000a00

Note: both memories (ds2433 and ds28ec20) have been tested with the
new driver.

Signed-off-by: Marc Ferland <marc.ferland@sonatest.com>
Co-developed-by: Jean-Francois Dagenais <jeff.dagenais@gmail.com>
Signed-off-by: Jean-Francois Dagenais <jeff.dagenais@gmail.com>
Link: https://lore.kernel.org/r/20231218150230.1992448-6-marc.ferland@sonatest.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/slaves/w1_ds2433.c | 101 +++++++++++++++++++++++++++++++---
 1 file changed, 92 insertions(+), 9 deletions(-)

diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c
index 87df76094e03f..250b7f7ec429e 100644
--- a/drivers/w1/slaves/w1_ds2433.c
+++ b/drivers/w1/slaves/w1_ds2433.c
@@ -1,8 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- *	w1_ds2433.c - w1 family 23 (DS2433) driver
+ *	w1_ds2433.c - w1 family 23 (DS2433) & 43 (DS28EC20) eeprom driver
  *
  * Copyright (c) 2005 Ben Gardner <bgardner@wabtec.com>
+ * Copyright (c) 2023 Marc Ferland <marc.ferland@sonatest.com>
  */
 
 #include <linux/kernel.h>
@@ -23,12 +24,15 @@
 #include <linux/w1.h>
 
 #define W1_EEPROM_DS2433	0x23
+#define W1_EEPROM_DS28EC20	0x43
+
+#define W1_EEPROM_DS2433_SIZE	512
+#define W1_EEPROM_DS28EC20_SIZE 2560
 
-#define W1_EEPROM_SIZE		512
 #define W1_PAGE_SIZE		32
 #define W1_PAGE_BITS		5
 #define W1_PAGE_MASK		0x1F
-#define W1_VALIDCRC_MAX		32
+#define W1_VALIDCRC_MAX		96
 
 #define W1_F23_READ_EEPROM	0xF0
 #define W1_F23_WRITE_SCRATCH	0x0F
@@ -42,11 +46,17 @@ struct ds2433_config {
 };
 
 static const struct ds2433_config config_f23 = {
-	.eeprom_size = W1_EEPROM_SIZE,
+	.eeprom_size = W1_EEPROM_DS2433_SIZE,
 	.page_count = 16,
 	.tprog = 5,
 };
 
+static const struct ds2433_config config_f43 = {
+	.eeprom_size = W1_EEPROM_DS28EC20_SIZE,
+	.page_count = 80,
+	.tprog = 10,
+};
+
 struct w1_f23_data {
 #ifdef CONFIG_W1_SLAVE_DS2433_CRC
 	u8 *memory;
@@ -264,10 +274,22 @@ out_up:
 	return count;
 }
 
-static BIN_ATTR_RW(eeprom, W1_EEPROM_SIZE);
+static struct bin_attribute bin_attr_f23_eeprom = {
+	.attr = { .name = "eeprom", .mode = 0644 },
+	.read = eeprom_read,
+	.write = eeprom_write,
+	.size = W1_EEPROM_DS2433_SIZE,
+};
+
+static struct bin_attribute bin_attr_f43_eeprom = {
+	.attr = { .name = "eeprom", .mode = 0644 },
+	.read = eeprom_read,
+	.write = eeprom_write,
+	.size = W1_EEPROM_DS28EC20_SIZE,
+};
 
 static struct bin_attribute *w1_f23_bin_attributes[] = {
-	&bin_attr_eeprom,
+	&bin_attr_f23_eeprom,
 	NULL,
 };
 
@@ -280,6 +302,20 @@ static const struct attribute_group *w1_f23_groups[] = {
 	NULL,
 };
 
+static struct bin_attribute *w1_f43_bin_attributes[] = {
+	&bin_attr_f43_eeprom,
+	NULL,
+};
+
+static const struct attribute_group w1_f43_group = {
+	.bin_attrs = w1_f43_bin_attributes,
+};
+
+static const struct attribute_group *w1_f43_groups[] = {
+	&w1_f43_group,
+	NULL,
+};
+
 static int w1_f23_add_slave(struct w1_slave *sl)
 {
 	struct w1_f23_data *data;
@@ -288,7 +324,14 @@ static int w1_f23_add_slave(struct w1_slave *sl)
 	if (!data)
 		return -ENOMEM;
 
-	data->cfg = &config_f23;
+	switch (sl->family->fid) {
+	case W1_EEPROM_DS2433:
+		data->cfg = &config_f23;
+		break;
+	case W1_EEPROM_DS28EC20:
+		data->cfg = &config_f43;
+		break;
+	}
 
 #ifdef CONFIG_W1_SLAVE_DS2433_CRC
 	if (data->cfg->page_count > W1_VALIDCRC_MAX) {
@@ -324,13 +367,53 @@ static const struct w1_family_ops w1_f23_fops = {
 	.groups		= w1_f23_groups,
 };
 
+static const struct w1_family_ops w1_f43_fops = {
+	.add_slave      = w1_f23_add_slave,
+	.remove_slave   = w1_f23_remove_slave,
+	.groups         = w1_f43_groups,
+};
+
 static struct w1_family w1_family_23 = {
 	.fid = W1_EEPROM_DS2433,
 	.fops = &w1_f23_fops,
 };
-module_w1_family(w1_family_23);
+
+static struct w1_family w1_family_43 = {
+	.fid = W1_EEPROM_DS28EC20,
+	.fops = &w1_f43_fops,
+};
+
+static int __init w1_ds2433_init(void)
+{
+	int err;
+
+	err = w1_register_family(&w1_family_23);
+	if (err)
+		return err;
+
+	err = w1_register_family(&w1_family_43);
+	if (err)
+		goto err_43;
+
+	return 0;
+
+err_43:
+	w1_unregister_family(&w1_family_23);
+	return err;
+}
+
+static void __exit w1_ds2433_exit(void)
+{
+	w1_unregister_family(&w1_family_23);
+	w1_unregister_family(&w1_family_43);
+}
+
+module_init(w1_ds2433_init);
+module_exit(w1_ds2433_exit);
 
 MODULE_AUTHOR("Ben Gardner <bgardner@wabtec.com>");
-MODULE_DESCRIPTION("w1 family 23 driver for DS2433, 4kb EEPROM");
+MODULE_AUTHOR("Marc Ferland <marc.ferland@sonatest.com>");
+MODULE_DESCRIPTION("w1 family 23/43 driver for DS2433 (4kb) and DS28EC20 (20kb)");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("w1-family-" __stringify(W1_EEPROM_DS2433));
+MODULE_ALIAS("w1-family-" __stringify(W1_EEPROM_DS28EC20));
-- 
GitLab


From caf08a8250d619cfcd2b6f5967218a2e36133ecc Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:28:34 +0100
Subject: [PATCH 1630/4076] dt-bindings: pinctrl: qcom,pmic-mpp: clean up
 example

The Multi-Purpose Pin controller block is part of an SPMI PMIC (which in
turns sits on an SPMI bus) and uses a single value for the register
property that corresponds to its base address.

Clean up the example by adding a parent PMIC node with proper
'#address-cells' and '#size-cells' properties, dropping the incorrect
second register value, adding some newline separators and increasing the
indentation to four spaces.

Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231130172834.12653-1-johan+linaro@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,pmic-mpp.yaml       | 62 ++++++++++---------
 1 file changed, 34 insertions(+), 28 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
index 80f9606718570..fe717d8d47982 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml
@@ -158,34 +158,40 @@ examples:
   - |
     #include <dt-bindings/pinctrl/qcom,pmic-mpp.h>
 
-    pm8841_mpp: mpps@a000 {
-      compatible = "qcom,pm8841-mpp", "qcom,spmi-mpp";
-      reg = <0xa000 0>;
-      gpio-controller;
-      #gpio-cells = <2>;
-      gpio-ranges = <&pm8841_mpp 0 0 4>;
-      gpio-line-names = "VDD_PX_BIAS", "WLAN_LED_CTRL",
-              "BT_LED_CTRL", "GPIO-F";
-      interrupt-controller;
-      #interrupt-cells = <2>;
-
-      pinctrl-names = "default";
-      pinctrl-0 = <&pm8841_default>;
-
-      mpp1-state {
-        pins = "mpp1";
-        function = "digital";
-        input-enable;
-        power-source = <PM8841_MPP_S3>;
-      };
-
-      default-state {
-        gpio-pins {
-          pins = "mpp1", "mpp2", "mpp3", "mpp4";
-          function = "digital";
-          input-enable;
-          power-source = <PM8841_MPP_S3>;
+    pmic {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pm8841_mpp: mpps@a000 {
+            compatible = "qcom,pm8841-mpp", "qcom,spmi-mpp";
+            reg = <0xa000>;
+
+            gpio-controller;
+            #gpio-cells = <2>;
+            gpio-ranges = <&pm8841_mpp 0 0 4>;
+            gpio-line-names = "VDD_PX_BIAS", "WLAN_LED_CTRL",
+                              "BT_LED_CTRL", "GPIO-F";
+            interrupt-controller;
+            #interrupt-cells = <2>;
+
+            pinctrl-names = "default";
+            pinctrl-0 = <&pm8841_default>;
+
+            mpp1-state {
+                pins = "mpp1";
+                function = "digital";
+                input-enable;
+                power-source = <PM8841_MPP_S3>;
+            };
+
+            default-state {
+                gpio-pins {
+                    pins = "mpp1", "mpp2", "mpp3", "mpp4";
+                    function = "digital";
+                    input-enable;
+                    power-source = <PM8841_MPP_S3>;
+                };
+            };
         };
-      };
     };
 ...
-- 
GitLab


From 7bf8b78f86dbac2f5b8332dcc91ff20cc3dfa3ce Mon Sep 17 00:00:00 2001
From: Tengfei Fan <quic_tengfan@quicinc.com>
Date: Tue, 12 Dec 2023 17:48:59 +0800
Subject: [PATCH 1631/4076] dt-bindings: pinctrl: qcom: Add SM4450 pinctrl

Add device tree binding Documentation details for Qualcomm SM4450
TLMM device.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Tengfei Fan <quic_tengfan@quicinc.com>
Link: https://lore.kernel.org/r/20231212094900.12615-2-quic_tengfan@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,sm4450-tlmm.yaml    | 151 ++++++++++++++++++
 1 file changed, 151 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml
new file mode 100644
index 0000000000000..bb08ca5a1509e
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml
@@ -0,0 +1,151 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,sm4450-tlmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. SM4450 TLMM block
+
+maintainers:
+  - Tengfei Fan <quic_tengfan@quicinc.com>
+
+description:
+  Top Level Mode Multiplexer pin controller in Qualcomm SM4450 SoC.
+
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+properties:
+  compatible:
+    const: qcom,sm4450-pinctrl
+
+  reg:
+    maxItems: 1
+
+  interrupts: true
+  interrupt-controller: true
+  "#interrupt-cells": true
+  gpio-controller: true
+
+  gpio-reserved-ranges:
+    minItems: 1
+    maxItems: 68
+
+  gpio-line-names:
+    maxItems: 136
+
+  "#gpio-cells": true
+  gpio-ranges: true
+  wakeup-parent: true
+
+patternProperties:
+  "-state$":
+    oneOf:
+      - $ref: "#/$defs/qcom-sm4450-tlmm-state"
+      - patternProperties:
+          "-pins$":
+            $ref: "#/$defs/qcom-sm4450-tlmm-state"
+        additionalProperties: false
+
+$defs:
+  qcom-sm4450-tlmm-state:
+    type: object
+    description:
+      Pinctrl node's client devices use subnodes for desired pin configuration.
+      Client device subnodes use below standard properties.
+    $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
+
+    properties:
+      pins:
+        description:
+          List of gpio pins affected by the properties specified in this
+          subnode.
+        items:
+          oneOf:
+            - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-2][0-9]|13[0-5])$"
+            - enum: [ sdc2_clk, sdc2_cmd, sdc2_data, ufs_reset ]
+          minItems: 1
+          maxItems: 36
+
+      function:
+        description:
+          Specify the alternative function to be configured for the specified
+          pins.
+        enum: [ gpio, atest_char, atest_char0, atest_char1, atest_char2,
+                atest_char3, atest_usb0, atest_usb00, atest_usb01, atest_usb02,
+                atest_usb03, audio_ref, cam_mclk, cci_async, cci_i2c,
+                cci_timer0, cci_timer1, cci_timer2, cci_timer3, cci_timer4,
+                cmu_rng0, cmu_rng1, cmu_rng2, cmu_rng3, coex_uart1, cri_trng,
+                cri_trng0, cri_trng1, dbg_out, ddr_bist, ddr_pxi0, ddr_pxi1,
+                dp0_hot, gcc_gp1, gcc_gp2, gcc_gp3, host2wlan_sol, ibi_i3c,
+                jitter_bist, mdp_vsync, mdp_vsync0, mdp_vsync1, mdp_vsync2,
+                mdp_vsync3, mi2s0_data0, mi2s0_data1, mi2s0_sck, mi2s0_ws,
+                mi2s2_data0, mi2s2_data1, mi2s2_sck, mi2s2_ws, mi2s_mclk0,
+                mi2s_mclk1, nav_gpio0, nav_gpio1, nav_gpio2, pcie0_clk,
+                phase_flag0, phase_flag1, phase_flag10, phase_flag11,
+                phase_flag12, phase_flag13, phase_flag14, phase_flag15,
+                phase_flag16, phase_flag17, phase_flag18, phase_flag19,
+                phase_flag2, phase_flag20, phase_flag21, phase_flag22,
+                phase_flag23, phase_flag24, phase_flag25, phase_flag26,
+                phase_flag27, phase_flag28, phase_flag29, phase_flag3,
+                phase_flag30, phase_flag31, phase_flag4, phase_flag5,
+                phase_flag6, phase_flag7, phase_flag8, phase_flag9,
+                pll_bist, pll_clk, prng_rosc0, prng_rosc1, prng_rosc2,
+                prng_rosc3, qdss_cti, qdss_gpio, qdss_gpio0, qdss_gpio1,
+                qdss_gpio10, qdss_gpio11, qdss_gpio12, qdss_gpio13, qdss_gpio14,
+                qdss_gpio15, qdss_gpio2, qdss_gpio3, qdss_gpio4, qdss_gpio5,
+                qdss_gpio6, qdss_gpio7, qdss_gpio8, qdss_gpio9, qlink0_enable,
+                qlink0_request, qlink0_wmss, qlink1_enable, qlink1_request,
+                qlink1_wmss, qlink2_enable, qlink2_request, qlink2_wmss,
+                qup0_se0, qup0_se1, qup0_se2, qup0_se3, qup0_se4, qup0_se5,
+                qup0_se6, qup0_se7, qup1_se0, qup1_se1, qup1_se2, qup1_se3,
+                qup1_se4, qup1_se5, qup1_se6, sd_write, tb_trig, tgu_ch0,
+                tgu_ch1, tgu_ch2, tgu_ch3, tmess_prng0, tmess_prng1,
+                tmess_prng2, tmess_prng3, tsense_pwm1, tsense_pwm2, uim0_clk,
+                uim0_data, uim0_present, uim0_reset, uim1_clk, uim1_data,
+                uim1_present, uim1_reset, usb0_hs, usb0_phy, vfr_0, vfr_1,
+                vsense_trigger ]
+
+        required:
+          - pins
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    tlmm: pinctrl@f100000 {
+        compatible = "qcom,sm4450-tlmm";
+        reg = <0x0f100000 0x300000>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        gpio-ranges = <&tlmm 0 0 137>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+        interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
+
+        gpio-wo-state {
+            pins = "gpio1";
+            function = "gpio";
+        };
+
+        uart-w-state {
+            rx-pins {
+                pins = "gpio23";
+                function = "qup1_se2";
+                bias-pull-up;
+            };
+
+            tx-pins {
+                pins = "gpio22";
+                function = "qup1_se2";
+                bias-disable;
+            };
+        };
+    };
+...
-- 
GitLab


From fa7b1fe24e10c62d3c14f3df16d5d7d5cffd1ddd Mon Sep 17 00:00:00 2001
From: Tengfei Fan <quic_tengfan@quicinc.com>
Date: Tue, 12 Dec 2023 17:49:00 +0800
Subject: [PATCH 1632/4076] pinctrl: qcom: sm4450: dd SM4450 pinctrl driver

Add pinctrl driver for TLMM block found in SM4450 SoC.
Can Guo helped out in reviewing the driver.

Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Signed-off-by: Tengfei Fan <quic_tengfan@quicinc.com>
Link: https://lore.kernel.org/r/20231212094900.12615-3-quic_tengfan@quicinc.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/Kconfig.msm      |    8 +
 drivers/pinctrl/qcom/Makefile         |    1 +
 drivers/pinctrl/qcom/pinctrl-sm4450.c | 1014 +++++++++++++++++++++++++
 3 files changed, 1023 insertions(+)
 create mode 100644 drivers/pinctrl/qcom/pinctrl-sm4450.c

diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm
index 87b6b70cfcd56..8fe459d082ede 100644
--- a/drivers/pinctrl/qcom/Kconfig.msm
+++ b/drivers/pinctrl/qcom/Kconfig.msm
@@ -286,6 +286,14 @@ config PINCTRL_SDX75
          Qualcomm Technologies Inc TLMM block found on the Qualcomm
          Technologies Inc SDX75 platform.
 
+config PINCTRL_SM4450
+	tristate "Qualcomm Technologies Inc SM4450 pin controller driver"
+	depends on ARM64 || COMPILE_TEST
+	help
+	 This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	 Qualcomm Technologies Inc TLMM block found on the Qualcomm
+	 Technologies Inc SM4450 platform.
+
 config PINCTRL_SM6115
 	tristate "Qualcomm Technologies Inc SM6115,SM4250 pin controller driver"
 	depends on ARM64 || COMPILE_TEST
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index fda23a83cb74f..e2e76071d2684 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_PINCTRL_SDM845) += pinctrl-sdm845.o
 obj-$(CONFIG_PINCTRL_SDX55) += pinctrl-sdx55.o
 obj-$(CONFIG_PINCTRL_SDX65) += pinctrl-sdx65.o
 obj-$(CONFIG_PINCTRL_SDX75) += pinctrl-sdx75.o
+obj-$(CONFIG_PINCTRL_SM4450) += pinctrl-sm4450.o
 obj-$(CONFIG_PINCTRL_SM6115) += pinctrl-sm6115.o
 obj-$(CONFIG_PINCTRL_SM6115_LPASS_LPI) += pinctrl-sm6115-lpass-lpi.o
 obj-$(CONFIG_PINCTRL_SM6125) += pinctrl-sm6125.o
diff --git a/drivers/pinctrl/qcom/pinctrl-sm4450.c b/drivers/pinctrl/qcom/pinctrl-sm4450.c
new file mode 100644
index 0000000000000..27317b86d8359
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-sm4450.c
@@ -0,0 +1,1014 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-msm.h"
+
+#define REG_SIZE 0x1000
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP("gpio" #id,     \
+			gpio##id##_pins,                \
+			ARRAY_SIZE(gpio##id##_pins)),   \
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9			\
+		},				        \
+		.nfuncs = 10,				\
+		.ctl_reg = REG_SIZE * id,			\
+		.io_reg = 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = 0x8 + REG_SIZE * id,		\
+		.intr_status_reg = 0xc + REG_SIZE * id,	\
+		.intr_target_reg = 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.egpio_enable = 12,		\
+		.egpio_present = 11,		\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,       \
+			pg_name##_pins,                 \
+			ARRAY_SIZE(pg_name##_pins)),    \
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define UFS_RESET(pg_name, offset)				\
+	{					        \
+		.grp = PINCTRL_PINGROUP(#pg_name,       \
+			pg_name##_pins,                 \
+			ARRAY_SIZE(pg_name##_pins)),    \
+		.ctl_reg = offset,			\
+		.io_reg = offset + 0x4,			\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = 3,				\
+		.drv_bit = 0,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = 0,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+
+#define QUP_I3C(qup_mode, qup_offset)			\
+	{						\
+		.mode = qup_mode,			\
+		.offset = qup_offset,			\
+	}
+
+
+static const struct pinctrl_pin_desc sm4450_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "UFS_RESET"),
+	PINCTRL_PIN(137, "SDC1_RCLK"),
+	PINCTRL_PIN(138, "SDC1_CLK"),
+	PINCTRL_PIN(139, "SDC1_CMD"),
+	PINCTRL_PIN(140, "SDC1_DATA"),
+	PINCTRL_PIN(141, "SDC2_CLK"),
+	PINCTRL_PIN(142, "SDC2_CMD"),
+	PINCTRL_PIN(143, "SDC2_DATA"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+
+static const unsigned int ufs_reset_pins[] = { 136 };
+static const unsigned int sdc1_rclk_pins[] = { 137 };
+static const unsigned int sdc1_clk_pins[] = { 138 };
+static const unsigned int sdc1_cmd_pins[] = { 139 };
+static const unsigned int sdc1_data_pins[] = { 140 };
+static const unsigned int sdc2_clk_pins[] = { 141 };
+static const unsigned int sdc2_cmd_pins[] = { 142 };
+static const unsigned int sdc2_data_pins[] = { 143 };
+
+enum sm4450_functions {
+	msm_mux_gpio,
+	msm_mux_atest_char,
+	msm_mux_atest_usb0,
+	msm_mux_audio_ref_clk,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async_in0,
+	msm_mux_cci_i2c,
+	msm_mux_cci,
+	msm_mux_cmu_rng,
+	msm_mux_coex_uart1_rx,
+	msm_mux_coex_uart1_tx,
+	msm_mux_cri_trng,
+	msm_mux_dbg_out_clk,
+	msm_mux_ddr_bist,
+	msm_mux_ddr_pxi0_test,
+	msm_mux_ddr_pxi1_test,
+	msm_mux_gcc_gp1_clk,
+	msm_mux_gcc_gp2_clk,
+	msm_mux_gcc_gp3_clk,
+	msm_mux_host2wlan_sol,
+	msm_mux_ibi_i3c_qup0,
+	msm_mux_ibi_i3c_qup1,
+	msm_mux_jitter_bist_ref,
+	msm_mux_mdp_vsync0_out,
+	msm_mux_mdp_vsync1_out,
+	msm_mux_mdp_vsync2_out,
+	msm_mux_mdp_vsync3_out,
+	msm_mux_mdp_vsync,
+	msm_mux_nav,
+	msm_mux_pcie0_clk_req,
+	msm_mux_phase_flag,
+	msm_mux_pll_bist_sync,
+	msm_mux_pll_clk_aux,
+	msm_mux_prng_rosc,
+	msm_mux_qdss_cti_trig0,
+	msm_mux_qdss_cti_trig1,
+	msm_mux_qdss_gpio,
+	msm_mux_qlink0_enable,
+	msm_mux_qlink0_request,
+	msm_mux_qlink0_wmss_reset,
+	msm_mux_qup0_se0,
+	msm_mux_qup0_se1,
+	msm_mux_qup0_se2,
+	msm_mux_qup0_se3,
+	msm_mux_qup0_se4,
+	msm_mux_qup1_se0,
+	msm_mux_qup1_se1,
+	msm_mux_qup1_se2,
+	msm_mux_qup1_se3,
+	msm_mux_qup1_se4,
+	msm_mux_sd_write_protect,
+	msm_mux_tb_trig_sdc1,
+	msm_mux_tb_trig_sdc2,
+	msm_mux_tgu_ch0_trigout,
+	msm_mux_tgu_ch1_trigout,
+	msm_mux_tgu_ch2_trigout,
+	msm_mux_tgu_ch3_trigout,
+	msm_mux_tmess_prng,
+	msm_mux_tsense_pwm1_out,
+	msm_mux_tsense_pwm2_out,
+	msm_mux_uim0,
+	msm_mux_uim1,
+	msm_mux_usb0_hs_ac,
+	msm_mux_usb0_phy_ps,
+	msm_mux_vfr_0_mira,
+	msm_mux_vfr_0_mirb,
+	msm_mux_vfr_1,
+	msm_mux_vsense_trigger_mirnat,
+	msm_mux_wlan1_adc_dtest0,
+	msm_mux_wlan1_adc_dtest1,
+	msm_mux__,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+	"gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56",
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70",
+	"gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77",
+	"gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84",
+	"gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91",
+	"gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98",
+	"gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104",
+	"gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110",
+	"gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116",
+	"gpio117", "gpio118", "gpio119", "gpio120", "gpio121", "gpio122",
+	"gpio123", "gpio124", "gpio125", "gpio126", "gpio127", "gpio128",
+	"gpio129", "gpio130", "gpio131", "gpio132", "gpio133", "gpio134",
+	"gpio135",
+};
+static const char * const atest_char_groups[] = {
+	"gpio95", "gpio97", "gpio98", "gpio99", "gpio100",
+};
+static const char * const atest_usb0_groups[] = {
+	"gpio75", "gpio10", "gpio78", "gpio79", "gpio80",
+};
+static const char * const audio_ref_clk_groups[] = {
+	"gpio71",
+};
+static const char * const cam_mclk_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+static const char * const cci_async_in0_groups[] = {
+	"gpio40",
+};
+static const char * const cci_i2c_groups[] = {
+	"gpio45", "gpio47", "gpio49", "gpio44",
+	"gpio46", "gpio48",
+};
+static const char * const cci_groups[] = {
+	"gpio40", "gpio41", "gpio42", "gpio43",
+};
+static const char * const cmu_rng_groups[] = {
+	"gpio28", "gpio3", "gpio1", "gpio0",
+};
+static const char * const coex_uart1_rx_groups[] = {
+	"gpio54",
+};
+static const char * const coex_uart1_tx_groups[] = {
+	"gpio55",
+};
+static const char * const cri_trng_groups[] = {
+	"gpio42", "gpio40", "gpio41",
+};
+static const char * const dbg_out_clk_groups[] = {
+	"gpio80",
+};
+static const char * const ddr_bist_groups[] = {
+	"gpio32", "gpio29", "gpio30", "gpio31",
+};
+static const char * const ddr_pxi0_test_groups[] = {
+	"gpio90", "gpio127",
+};
+static const char * const ddr_pxi1_test_groups[] = {
+	"gpio118", "gpio122",
+};
+static const char * const gcc_gp1_clk_groups[] = {
+	"gpio37", "gpio48",
+};
+static const char * const gcc_gp2_clk_groups[] = {
+	"gpio30", "gpio49",
+};
+static const char * const gcc_gp3_clk_groups[] = {
+	"gpio3", "gpio50",
+};
+static const char * const host2wlan_sol_groups[] = {
+	"gpio106",
+};
+static const char * const ibi_i3c_qup0_groups[] = {
+	"gpio4", "gpio5",
+};
+static const char * const ibi_i3c_qup1_groups[] = {
+	"gpio0", "gpio1",
+};
+static const char * const jitter_bist_ref_groups[] = {
+	"gpio90",
+};
+static const char * const mdp_vsync0_out_groups[] = {
+	"gpio93",
+};
+static const char * const mdp_vsync1_out_groups[] = {
+	"gpio93",
+};
+static const char * const mdp_vsync2_out_groups[] = {
+	"gpio22",
+};
+static const char * const mdp_vsync3_out_groups[] = {
+	"gpio22",
+};
+static const char * const mdp_vsync_groups[] = {
+	"gpio26", "gpio22", "gpio30", "gpio34", "gpio93", "gpio97",
+};
+static const char * const nav_groups[] = {
+	"gpio81", "gpio83", "gpio84",
+};
+static const char * const pcie0_clk_req_groups[] = {
+	"gpio107",
+};
+static const char * const phase_flag_groups[] = {
+	"gpio7", "gpio8", "gpio9", "gpio11", "gpio13", "gpio14", "gpio15",
+	"gpio17", "gpio18", "gpio19", "gpio21", "gpio24", "gpio25", "gpio31",
+	"gpio32", "gpio33", "gpio35", "gpio61", "gpio72", "gpio82", "gpio91",
+	"gpio95", "gpio97", "gpio98", "gpio99", "gpio100", "gpio105", "gpio115",
+	"gpio116", "gpio117", "gpio133", "gpio135",
+};
+static const char * const pll_bist_sync_groups[] = {
+	"gpio73",
+};
+static const char * const pll_clk_aux_groups[] = {
+	"gpio108",
+};
+static const char * const prng_rosc_groups[] = {
+	"gpio36", "gpio37", "gpio38", "gpio39",
+};
+static const char * const qdss_cti_trig0_groups[] = {
+	"gpio26", "gpio60", "gpio113", "gpio114",
+};
+static const char * const qdss_cti_trig1_groups[] = {
+	"gpio6", "gpio27", "gpio57", "gpio58",
+};
+static const char * const qdss_gpio_groups[] = {
+	"gpio0", "gpio1", "gpio3", "gpio4", "gpio5", "gpio7", "gpio8",
+	"gpio9", "gpio14", "gpio15", "gpio17", "gpio23", "gpio31", "gpio32",
+	"gpio33", "gpio35", "gpio36", "gpio37", "gpio38", "gpio39", "gpio40",
+	"gpio41", "gpio42", "gpio43", "gpio44", "gpio45", "gpio46", "gpio47",
+	"gpio49",  "gpio59", "gpio62", "gpio118", "gpio121", "gpio122", "gpio126",
+	"gpio127",
+};
+static const char * const qlink0_enable_groups[] = {
+	"gpio88",
+};
+static const char * const qlink0_request_groups[] = {
+	"gpio87",
+};
+static const char * const qlink0_wmss_reset_groups[] = {
+	"gpio89",
+};
+static const char * const qup0_se0_groups[] = {
+	"gpio4", "gpio5", "gpio34", "gpio35",
+};
+static const char * const qup0_se1_groups[] = {
+	"gpio10", "gpio11", "gpio12", "gpio13",
+};
+static const char * const qup0_se2_groups[] = {
+	"gpio14", "gpio15", "gpio16", "gpio17",
+};
+static const char * const qup0_se3_groups[] = {
+	"gpio18", "gpio19", "gpio20", "gpio21",
+};
+static const char * const qup0_se4_groups[] = {
+	"gpio6", "gpio7", "gpio8", "gpio9",
+	"gpio26", "gpio27", "gpio34",
+};
+static const char * const qup1_se0_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+static const char * const qup1_se1_groups[] = {
+	"gpio26", "gpio27", "gpio50", "gpio51",
+};
+static const char * const qup1_se2_groups[] = {
+	"gpio22", "gpio23", "gpio31", "gpio32",
+};
+static const char * const qup1_se3_groups[] = {
+	"gpio24", "gpio25", "gpio51", "gpio50",
+};
+static const char * const qup1_se4_groups[] = {
+	"gpio43", "gpio48", "gpio49", "gpio90",
+	"gpio91",
+};
+static const char * const sd_write_protect_groups[] = {
+	"gpio102",
+};
+static const char * const tb_trig_sdc1_groups[] = {
+	"gpio128",
+};
+static const char * const tb_trig_sdc2_groups[] = {
+	"gpio51",
+};
+static const char * const tgu_ch0_trigout_groups[] = {
+	"gpio20",
+};
+static const char * const tgu_ch1_trigout_groups[] = {
+	"gpio21",
+};
+static const char * const tgu_ch2_trigout_groups[] = {
+	"gpio22",
+};
+static const char * const tgu_ch3_trigout_groups[] = {
+	"gpio23",
+};
+static const char * const tmess_prng_groups[] = {
+	"gpio57", "gpio58", "gpio59", "gpio60",
+};
+static const char * const tsense_pwm1_out_groups[] = {
+	"gpio134",
+};
+static const char * const tsense_pwm2_out_groups[] = {
+	"gpio134",
+};
+static const char * const uim0_groups[] = {
+	"gpio64", "gpio63", "gpio66", "gpio65",
+};
+static const char * const uim1_groups[] = {
+	"gpio68", "gpio67", "gpio69", "gpio70",
+};
+static const char * const usb0_hs_ac_groups[] = {
+	"gpio99",
+};
+static const char * const usb0_phy_ps_groups[] = {
+	"gpio94",
+};
+static const char * const vfr_0_mira_groups[] = {
+	"gpio19",
+};
+static const char * const vfr_0_mirb_groups[] = {
+	"gpio100",
+};
+static const char * const vfr_1_groups[] = {
+	"gpio84",
+};
+static const char * const vsense_trigger_mirnat_groups[] = {
+	"gpio75",
+};
+static const char * const wlan1_adc_dtest0_groups[] = {
+	"gpio79",
+};
+static const char * const wlan1_adc_dtest1_groups[] = {
+	"gpio80",
+};
+
+static const struct pinfunction sm4450_functions[] = {
+	MSM_PIN_FUNCTION(gpio),
+	MSM_PIN_FUNCTION(atest_char),
+	MSM_PIN_FUNCTION(atest_usb0),
+	MSM_PIN_FUNCTION(audio_ref_clk),
+	MSM_PIN_FUNCTION(cam_mclk),
+	MSM_PIN_FUNCTION(cci_async_in0),
+	MSM_PIN_FUNCTION(cci_i2c),
+	MSM_PIN_FUNCTION(cci),
+	MSM_PIN_FUNCTION(cmu_rng),
+	MSM_PIN_FUNCTION(coex_uart1_rx),
+	MSM_PIN_FUNCTION(coex_uart1_tx),
+	MSM_PIN_FUNCTION(cri_trng),
+	MSM_PIN_FUNCTION(dbg_out_clk),
+	MSM_PIN_FUNCTION(ddr_bist),
+	MSM_PIN_FUNCTION(ddr_pxi0_test),
+	MSM_PIN_FUNCTION(ddr_pxi1_test),
+	MSM_PIN_FUNCTION(gcc_gp1_clk),
+	MSM_PIN_FUNCTION(gcc_gp2_clk),
+	MSM_PIN_FUNCTION(gcc_gp3_clk),
+	MSM_PIN_FUNCTION(host2wlan_sol),
+	MSM_PIN_FUNCTION(ibi_i3c_qup0),
+	MSM_PIN_FUNCTION(ibi_i3c_qup1),
+	MSM_PIN_FUNCTION(jitter_bist_ref),
+	MSM_PIN_FUNCTION(mdp_vsync0_out),
+	MSM_PIN_FUNCTION(mdp_vsync1_out),
+	MSM_PIN_FUNCTION(mdp_vsync2_out),
+	MSM_PIN_FUNCTION(mdp_vsync3_out),
+	MSM_PIN_FUNCTION(mdp_vsync),
+	MSM_PIN_FUNCTION(nav),
+	MSM_PIN_FUNCTION(pcie0_clk_req),
+	MSM_PIN_FUNCTION(phase_flag),
+	MSM_PIN_FUNCTION(pll_bist_sync),
+	MSM_PIN_FUNCTION(pll_clk_aux),
+	MSM_PIN_FUNCTION(prng_rosc),
+	MSM_PIN_FUNCTION(qdss_cti_trig0),
+	MSM_PIN_FUNCTION(qdss_cti_trig1),
+	MSM_PIN_FUNCTION(qdss_gpio),
+	MSM_PIN_FUNCTION(qlink0_enable),
+	MSM_PIN_FUNCTION(qlink0_request),
+	MSM_PIN_FUNCTION(qlink0_wmss_reset),
+	MSM_PIN_FUNCTION(qup0_se0),
+	MSM_PIN_FUNCTION(qup0_se1),
+	MSM_PIN_FUNCTION(qup0_se2),
+	MSM_PIN_FUNCTION(qup0_se3),
+	MSM_PIN_FUNCTION(qup0_se4),
+	MSM_PIN_FUNCTION(qup1_se0),
+	MSM_PIN_FUNCTION(qup1_se1),
+	MSM_PIN_FUNCTION(qup1_se2),
+	MSM_PIN_FUNCTION(qup1_se3),
+	MSM_PIN_FUNCTION(qup1_se4),
+	MSM_PIN_FUNCTION(sd_write_protect),
+	MSM_PIN_FUNCTION(tb_trig_sdc1),
+	MSM_PIN_FUNCTION(tb_trig_sdc2),
+	MSM_PIN_FUNCTION(tgu_ch0_trigout),
+	MSM_PIN_FUNCTION(tgu_ch1_trigout),
+	MSM_PIN_FUNCTION(tgu_ch2_trigout),
+	MSM_PIN_FUNCTION(tgu_ch3_trigout),
+	MSM_PIN_FUNCTION(tmess_prng),
+	MSM_PIN_FUNCTION(tsense_pwm1_out),
+	MSM_PIN_FUNCTION(tsense_pwm2_out),
+	MSM_PIN_FUNCTION(uim0),
+	MSM_PIN_FUNCTION(uim1),
+	MSM_PIN_FUNCTION(usb0_hs_ac),
+	MSM_PIN_FUNCTION(usb0_phy_ps),
+	MSM_PIN_FUNCTION(vfr_0_mira),
+	MSM_PIN_FUNCTION(vfr_0_mirb),
+	MSM_PIN_FUNCTION(vfr_1),
+	MSM_PIN_FUNCTION(vsense_trigger_mirnat),
+	MSM_PIN_FUNCTION(wlan1_adc_dtest0),
+	MSM_PIN_FUNCTION(wlan1_adc_dtest1),
+};
+
+/*
+ * Every pin is maintained as a single group, and missing or non-existing pin
+ * would be maintained as dummy group to synchronize pin group index with
+ * pin descriptor registered with pinctrl core.
+ * Clients would not be able to request these dummy pin groups.
+ */
+static const struct msm_pingroup sm4450_groups[] = {
+	[0] = PINGROUP(0, qup1_se0, ibi_i3c_qup1, cmu_rng, qdss_gpio, _, _, _, _, _),
+	[1] = PINGROUP(1, qup1_se0, ibi_i3c_qup1, cmu_rng, qdss_gpio, _, _, _, _, _),
+	[2] = PINGROUP(2, qup1_se0, _, _, _, _, _, _, _, _),
+	[3] = PINGROUP(3, qup1_se0, gcc_gp3_clk, cmu_rng, qdss_gpio, _, _, _, _, _),
+	[4] = PINGROUP(4, qup0_se0, ibi_i3c_qup0, qdss_gpio, _, _, _, _, _, _),
+	[5] = PINGROUP(5, qup0_se0, ibi_i3c_qup0, qdss_gpio, _, _, _, _, _, _),
+	[6] = PINGROUP(6, qup0_se4, qdss_cti_trig1, _, _, _, _, _, _, _),
+	[7] = PINGROUP(7, qup0_se4, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[8] = PINGROUP(8, qup0_se4, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[9] = PINGROUP(9, qup0_se4, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[10] = PINGROUP(10, qup0_se1, _, atest_usb0, _, _, _, _, _, _),
+	[11] = PINGROUP(11, qup0_se1, _, phase_flag, _, _, _, _, _, _),
+	[12] = PINGROUP(12, qup0_se1, _, _, _, _, _, _, _, _),
+	[13] = PINGROUP(13, qup0_se1, _, phase_flag, _, _, _, _, _, _),
+	[14] = PINGROUP(14, qup0_se2, _, phase_flag, _, qdss_gpio, _, _, _, _),
+	[15] = PINGROUP(15, qup0_se2, _, phase_flag, _, qdss_gpio, _, _, _, _),
+	[16] = PINGROUP(16, qup0_se2, _, _, _, _, _, _, _, _),
+	[17] = PINGROUP(17, qup0_se2, _, phase_flag, _, qdss_gpio, _, _, _, _),
+	[18] = PINGROUP(18, qup0_se3, _, phase_flag, _, _, _, _, _, _),
+	[19] = PINGROUP(19, qup0_se3, vfr_0_mira, _, phase_flag, _, _, _, _, _),
+	[20] = PINGROUP(20, qup0_se3, tgu_ch0_trigout, _, _, _, _, _, _, _),
+	[21] = PINGROUP(21, qup0_se3, _, phase_flag, tgu_ch1_trigout, _, _, _, _, _),
+	[22] = PINGROUP(22, qup1_se2, mdp_vsync, mdp_vsync2_out, mdp_vsync3_out, tgu_ch2_trigout, _, _, _, _),
+	[23] = PINGROUP(23, qup1_se2, tgu_ch3_trigout, qdss_gpio, _, _, _, _, _, _),
+	[24] = PINGROUP(24, qup1_se3, _, phase_flag, _, _, _, _, _, _),
+	[25] = PINGROUP(25, qup1_se3, _, phase_flag, _, _, _, _, _, _),
+	[26] = PINGROUP(26, qup1_se1, mdp_vsync, qup0_se4, qdss_cti_trig0, _, _, _, _, _),
+	[27] = PINGROUP(27, qup1_se1, qup0_se4, qdss_cti_trig1, _, _, _, _, _, _),
+	[28] = PINGROUP(28, cmu_rng, _, _, _, _, _, _, _, _),
+	[29] = PINGROUP(29, ddr_bist, _, _, _, _, _, _, _, _),
+	[30] = PINGROUP(30, mdp_vsync, gcc_gp2_clk, ddr_bist, _, _, _, _, _, _),
+	[31] = PINGROUP(31, qup1_se2, _, phase_flag, ddr_bist, qdss_gpio, _, _, _, _),
+	[32] = PINGROUP(32, qup1_se2, _, phase_flag, ddr_bist, qdss_gpio, _, _, _, _),
+	[33] = PINGROUP(33, _, phase_flag, qdss_gpio, _, _, _, _, _, _),
+	[34] = PINGROUP(34, qup0_se0, qup0_se4, mdp_vsync, _, _, _, _, _, _),
+	[35] = PINGROUP(35, qup0_se0, _, phase_flag, qdss_gpio, _, _, _, _, _),
+	[36] = PINGROUP(36, cam_mclk, prng_rosc, qdss_gpio, _, _, _, _, _, _),
+	[37] = PINGROUP(37, cam_mclk, gcc_gp1_clk, prng_rosc, qdss_gpio, _, _, _, _, _),
+	[38] = PINGROUP(38, cam_mclk, prng_rosc, qdss_gpio, _, _, _, _, _, _),
+	[39] = PINGROUP(39, cam_mclk, prng_rosc, qdss_gpio, _, _, _, _, _, _),
+	[40] = PINGROUP(40, cci, cci_async_in0, cri_trng, qdss_gpio, _, _, _, _, _),
+	[41] = PINGROUP(41, cci, cri_trng, qdss_gpio, _, _, _, _, _, _),
+	[42] = PINGROUP(42, cci, cri_trng, qdss_gpio, _, _, _, _, _, _),
+	[43] = PINGROUP(43, cci, qup1_se4, qdss_gpio, _, _, _, _, _, _),
+	[44] = PINGROUP(44, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[45] = PINGROUP(45, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[46] = PINGROUP(46, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[47] = PINGROUP(47, cci_i2c, qdss_gpio, _, _, _, _, _, _, _),
+	[48] = PINGROUP(48, cci_i2c, qup1_se4, gcc_gp1_clk, _, _, _, _, _, _),
+	[49] = PINGROUP(49, cci_i2c, qup1_se4, gcc_gp2_clk, qdss_gpio, _, _, _, _, _),
+	[50] = PINGROUP(50, qup1_se1, qup1_se3, _, gcc_gp3_clk, _, _, _, _, _),
+	[51] = PINGROUP(51, qup1_se1, qup1_se3, _, tb_trig_sdc2, _, _, _, _, _),
+	[52] = PINGROUP(52, _, _, _, _, _, _, _, _, _),
+	[53] = PINGROUP(53, _, _, _, _, _, _, _, _, _),
+	[54] = PINGROUP(54, coex_uart1_rx, _, _, _, _, _, _, _, _),
+	[55] = PINGROUP(55, coex_uart1_tx, _, _, _, _, _, _, _, _),
+	[56] = PINGROUP(56, _, _, _, _, _, _, _, _, _),
+	[57] = PINGROUP(57, tmess_prng, qdss_cti_trig1, _, _, _, _, _, _, _),
+	[58] = PINGROUP(58, tmess_prng, qdss_cti_trig1, _, _, _, _, _, _, _),
+	[59] = PINGROUP(59, tmess_prng, qdss_gpio, _, _, _, _, _, _, _),
+	[60] = PINGROUP(60, tmess_prng, qdss_cti_trig0, _, _, _, _, _, _, _),
+	[61] = PINGROUP(61, _, phase_flag, _, _, _, _, _, _, _),
+	[62] = PINGROUP(62, qdss_gpio, _, _, _, _, _, _, _, _),
+	[63] = PINGROUP(63, uim0, _, _, _, _, _, _, _, _),
+	[64] = PINGROUP(64, uim0, _, _, _, _, _, _, _, _),
+	[65] = PINGROUP(65, uim0, _, _, _, _, _, _, _, _),
+	[66] = PINGROUP(66, uim0, _, _, _, _, _, _, _, _),
+	[67] = PINGROUP(67, uim1, _, _, _, _, _, _, _, _),
+	[68] = PINGROUP(68, uim1, _, _, _, _, _, _, _, _),
+	[69] = PINGROUP(69, uim1, _, _, _, _, _, _, _, _),
+	[70] = PINGROUP(70, uim1, _, _, _, _, _, _, _, _),
+	[71] = PINGROUP(71, _, _, _, audio_ref_clk, _, _, _, _, _),
+	[72] = PINGROUP(72, _, _, _, phase_flag, _, _, _, _, _),
+	[73] = PINGROUP(73, _, _, _, pll_bist_sync, _, _, _, _, _),
+	[74] = PINGROUP(74, _, _, _, _, _, _, _, _, _),
+	[75] = PINGROUP(75, _, _, _, vsense_trigger_mirnat, atest_usb0, _, _, _, _),
+	[76] = PINGROUP(76, _, _, _, _, _, _, _, _, _),
+	[77] = PINGROUP(77, _, _, _, _, _, _, _, _, _),
+	[78] = PINGROUP(78, _, _, _, atest_usb0, _, _, _, _, _),
+	[79] = PINGROUP(79, _, _, _, wlan1_adc_dtest0, atest_usb0, _, _, _, _),
+	[80] = PINGROUP(80, _, _, dbg_out_clk, wlan1_adc_dtest1, atest_usb0, _, _, _, _),
+	[81] = PINGROUP(81, _, nav, _, _, _, _, _, _, _),
+	[82] = PINGROUP(82, _, _, phase_flag, _, _, _, _, _, _),
+	[83] = PINGROUP(83, nav, _, _, _, _, _, _, _, _),
+	[84] = PINGROUP(84, nav, vfr_1, _, _, _, _, _, _, _),
+	[85] = PINGROUP(85, _, _, _, _, _, _, _, _, _),
+	[86] = PINGROUP(86, _, _, _, _, _, _, _, _, _),
+	[87] = PINGROUP(87, qlink0_request, _, _, _, _, _, _, _, _),
+	[88] = PINGROUP(88, qlink0_enable, _, _, _, _, _, _, _, _),
+	[89] = PINGROUP(89, qlink0_wmss_reset, _, _, _, _, _, _, _, _),
+	[90] = PINGROUP(90, qup1_se4, jitter_bist_ref, ddr_pxi0_test, _, _, _, _, _, _),
+	[91] = PINGROUP(91, qup1_se4, _, phase_flag, _, _, _, _, _, _),
+	[92] = PINGROUP(92, _, _, _, _, _, _, _, _, _),
+	[93] = PINGROUP(93, mdp_vsync, mdp_vsync0_out, mdp_vsync1_out, _, _, _, _, _, _),
+	[94] = PINGROUP(94, usb0_phy_ps, _, _, _, _, _, _, _, _),
+	[95] = PINGROUP(95, _, phase_flag, atest_char, _, _, _, _, _, _),
+	[96] = PINGROUP(96, _, _, _, _, _, _, _, _, _),
+	[97] = PINGROUP(97, mdp_vsync, _, phase_flag, atest_char, _, _, _, _, _),
+	[98] = PINGROUP(98, _, phase_flag, atest_char, _, _, _, _, _, _),
+	[99] = PINGROUP(99, usb0_hs_ac, _, phase_flag, atest_char, _, _, _, _, _),
+	[100] = PINGROUP(100, vfr_0_mirb, _, phase_flag, atest_char, _, _, _, _, _),
+	[101] = PINGROUP(101, _, _, _, _, _, _, _, _, _),
+	[102] = PINGROUP(102, sd_write_protect, _, _, _, _, _, _, _, _),
+	[103] = PINGROUP(103, _, _, _, _, _, _, _, _, _),
+	[104] = PINGROUP(104, _, _, _, _, _, _, _, _, _),
+	[105] = PINGROUP(105, _, phase_flag, _, _, _, _, _, _, _),
+	[106] = PINGROUP(106, host2wlan_sol, _, _, _, _, _, _, _, _),
+	[107] = PINGROUP(107, pcie0_clk_req, _, _, _, _, _, _, _, _),
+	[108] = PINGROUP(108, pll_clk_aux, _, _, _, _, _, _, _, _),
+	[109] = PINGROUP(109, _, _, _, _, _, _, _, _, _),
+	[110] = PINGROUP(110, _, _, _, _, _, _, _, _, _),
+	[111] = PINGROUP(111, _, _, _, _, _, _, _, _, _),
+	[112] = PINGROUP(112, _, _, _, _, _, _, _, _, _),
+	[113] = PINGROUP(113, qdss_cti_trig0, _, _, _, _, _, _, _, _),
+	[114] = PINGROUP(114, qdss_cti_trig0, _, _, _, _, _, _, _, _),
+	[115] = PINGROUP(115, _, phase_flag, _, _, _, _, _, _, _),
+	[116] = PINGROUP(116, _, phase_flag, _, _, _, _, _, _, _),
+	[117] = PINGROUP(117, _, phase_flag, _, _, _, _, _, _, _),
+	[118] = PINGROUP(118, qdss_gpio, _, ddr_pxi1_test, _, _, _, _, _, _),
+	[119] = PINGROUP(119, _, _, _, _, _, _, _, _, _),
+	[120] = PINGROUP(120, _, _, _, _, _, _, _, _, _),
+	[121] = PINGROUP(121, qdss_gpio, _, _, _, _, _, _, _, _),
+	[122] = PINGROUP(122, qdss_gpio, _, ddr_pxi1_test, _, _, _, _, _, _),
+	[123] = PINGROUP(123, _, _, _, _, _, _, _, _, _),
+	[124] = PINGROUP(124, _, _, _, _, _, _, _, _, _),
+	[125] = PINGROUP(125, _, _, _, _, _, _, _, _, _),
+	[126] = PINGROUP(126, qdss_gpio, _, _, _, _, _, _, _, _),
+	[127] = PINGROUP(127, qdss_gpio, ddr_pxi0_test, _, _, _, _, _, _, _),
+	[128] = PINGROUP(128, tb_trig_sdc1, _, _, _, _, _, _, _, _),
+	[129] = PINGROUP(129, _, _, _, _, _, _, _, _, _),
+	[130] = PINGROUP(130, _, _, _, _, _, _, _, _, _),
+	[131] = PINGROUP(131, _, _, _, _, _, _, _, _, _),
+	[132] = PINGROUP(132, _, _, _, _, _, _, _, _, _),
+	[133] = PINGROUP(133, _, phase_flag, _, _, _, _, _, _, _),
+	[134] = PINGROUP(134, tsense_pwm1_out, tsense_pwm2_out, _, _, _, _, _, _, _),
+	[135] = PINGROUP(135, _, phase_flag, _, _, _, _, _, _, _),
+	[136] = UFS_RESET(ufs_reset, 0x97000),
+	[137] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x8c004, 0, 0),
+	[138] = SDC_QDSD_PINGROUP(sdc1_clk, 0x8c000, 13, 6),
+	[139] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x8c000, 11, 3),
+	[140] = SDC_QDSD_PINGROUP(sdc1_data, 0x8c000, 9, 0),
+	[141] = SDC_QDSD_PINGROUP(sdc2_clk, 0x8f000, 14, 6),
+	[142] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x8f000, 11, 3),
+	[143] = SDC_QDSD_PINGROUP(sdc2_data, 0x8f000, 9, 0),
+};
+
+static const struct msm_gpio_wakeirq_map sm4450_pdc_map[] = {
+	{ 0, 67 }, { 3, 82 }, { 4, 69 }, { 5, 70 }, { 6, 44 }, { 7, 43 },
+	{ 8, 71 }, { 9, 86 }, { 10, 48 }, { 11, 77 }, { 12, 90 },
+	{ 13, 54 }, { 14, 91 }, { 17, 97 }, { 18, 102 }, { 21, 103 },
+	{ 22, 104 }, { 23, 105 }, { 24, 53 }, { 25, 106 }, { 26, 65 },
+	{ 27, 55 }, { 28, 89 }, { 30, 80 }, { 31, 109 }, { 33, 87 },
+	{ 34, 81 }, { 35, 75 }, { 40, 88 }, { 41, 98 }, { 42, 110 },
+	{ 43, 95 }, { 47, 118 }, { 50, 111 }, { 52, 52 }, { 53, 114 },
+	{ 54, 115 }, { 55, 99 }, { 56, 45 }, { 57, 85 }, { 58, 56 },
+	{ 59, 84 }, { 60, 83 }, { 61, 96 }, { 62, 93 }, { 66, 116 },
+	{ 67, 113 }, { 70, 42 }, { 71, 122 }, { 73, 119 }, { 75, 121 },
+	{ 77, 120 }, { 79, 123 }, { 81, 124 }, { 83, 64 }, { 84, 128 },
+	{ 86, 129 }, { 87, 63 }, { 91, 92 }, { 92, 66 }, { 93, 125 },
+	{ 94, 76 }, { 95, 62 }, { 96, 132 }, { 97, 135 }, { 98, 73 },
+	{ 99, 133 }, { 101, 46 }, { 102, 134 }, { 103, 49 }, { 105, 58 },
+	{ 107, 94 }, { 110, 59 }, { 113, 57 }, { 114, 60 }, { 118, 107 },
+	{ 120, 61 }, { 121, 108 }, { 123, 68 }, { 125, 72 }, { 128, 112 },
+};
+
+static const struct msm_pinctrl_soc_data sm4450_tlmm = {
+	.pins = sm4450_pins,
+	.npins = ARRAY_SIZE(sm4450_pins),
+	.functions = sm4450_functions,
+	.nfunctions = ARRAY_SIZE(sm4450_functions),
+	.groups = sm4450_groups,
+	.ngroups = ARRAY_SIZE(sm4450_groups),
+	.ngpios = 137,
+	.wakeirq_map = sm4450_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(sm4450_pdc_map),
+};
+
+static int sm4450_tlmm_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &sm4450_tlmm);
+}
+
+static const struct of_device_id sm4450_tlmm_of_match[] = {
+	{ .compatible = "qcom,sm4450-tlmm", },
+	{ }
+};
+
+static struct platform_driver sm4450_tlmm_driver = {
+	.driver = {
+		.name = "sm4450-tlmm",
+		.of_match_table = sm4450_tlmm_of_match,
+	},
+	.probe = sm4450_tlmm_probe,
+	.remove_new = msm_pinctrl_remove,
+};
+MODULE_DEVICE_TABLE(of, sm4450_tlmm_of_match);
+
+static int __init sm4450_tlmm_init(void)
+{
+	return platform_driver_register(&sm4450_tlmm_driver);
+}
+arch_initcall(sm4450_tlmm_init);
+
+static void __exit sm4450_tlmm_exit(void)
+{
+	platform_driver_unregister(&sm4450_tlmm_driver);
+}
+module_exit(sm4450_tlmm_exit);
+
+MODULE_DESCRIPTION("QTI SM4450 TLMM driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 5a5ecedc4b57ec072b1ab780352087958fe2527e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:25 +0100
Subject: [PATCH 1633/4076] dt-bindings: pinctrl: qcom: create common LPASS LPI
 schema

Just like regular TLMM pin controllers in Qualcomm SoCs, the Low Power
Audio SubSystem (LPASS) Low Power Island (LPI) TLMM blocks share a lot
of properties, so common part can be moved to separate schema to reduce
code duplication and make reviewing easier.

Except the move of common part, this introduces effective changes:
1. To all LPASS LPI bindings: Reference pinmux-node.yaml in each pin
   muxing and configuration node, to bring definition of "function" and
   "pins" properties.

2. qcom,sc7280-lpass-lpi-pinctrl: Reference pinctrl.yaml in top leve.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../pinctrl/qcom,lpass-lpi-common.yaml        | 75 +++++++++++++++++++
 .../qcom,sc7280-lpass-lpi-pinctrl.yaml        | 49 ++----------
 .../qcom,sc8280xp-lpass-lpi-pinctrl.yaml      | 49 +-----------
 .../qcom,sm6115-lpass-lpi-pinctrl.yaml        | 48 +-----------
 .../qcom,sm8250-lpass-lpi-pinctrl.yaml        | 49 +-----------
 .../qcom,sm8350-lpass-lpi-pinctrl.yaml        | 49 +-----------
 .../qcom,sm8450-lpass-lpi-pinctrl.yaml        | 49 +-----------
 .../qcom,sm8550-lpass-lpi-pinctrl.yaml        | 49 +-----------
 .../qcom,sm8650-lpass-lpi-pinctrl.yaml        | 49 +-----------
 9 files changed, 109 insertions(+), 357 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,lpass-lpi-common.yaml

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,lpass-lpi-common.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,lpass-lpi-common.yaml
new file mode 100644
index 0000000000000..3b5045730471f
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,lpass-lpi-common.yaml
@@ -0,0 +1,75 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pinctrl/qcom,lpass-lpi-common.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm SoC LPASS LPI TLMM Common Properties
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+  - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+  - Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+
+description:
+  Common properties for the Top Level Mode Multiplexer pin controllers in the
+  Low Power Audio SubSystem (LPASS) Low Power Island (LPI) of Qualcomm SoCs.
+
+properties:
+  gpio-controller: true
+
+  "#gpio-cells":
+    description:
+      Specifying the pin number and flags, as defined in
+      include/dt-bindings/gpio/gpio.h
+    const: 2
+
+  gpio-ranges:
+    maxItems: 1
+
+required:
+  - gpio-controller
+  - "#gpio-cells"
+  - gpio-ranges
+
+allOf:
+  - $ref: pinctrl.yaml#
+
+additionalProperties: true
+
+$defs:
+  qcom-tlmm-state:
+    properties:
+      drive-strength:
+        enum: [2, 4, 6, 8, 10, 12, 14, 16]
+        default: 2
+        description:
+          Selects the drive strength for the specified pins, in mA.
+
+      slew-rate:
+        enum: [0, 1, 2, 3]
+        default: 0
+        description: |
+          0: No adjustments
+          1: Higher Slew rate (faster edges)
+          2: Lower Slew rate (slower edges)
+          3: Reserved (No adjustments)
+
+      bias-bus-hold: true
+      bias-pull-down: true
+      bias-pull-up: true
+      bias-disable: true
+      input-enable: true
+      output-high: true
+      output-low: true
+
+    required:
+      - pins
+      - function
+
+    allOf:
+      - $ref: pincfg-node.yaml#
+      - $ref: pinmux-node.yaml#
+
+    additionalProperties: true
+
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
index 00c5a00e35fce..08801cc4e476f 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
@@ -20,16 +20,6 @@ properties:
   reg:
     maxItems: 2
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -45,7 +35,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -68,42 +59,14 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-            0: No adjustments
-            1: Higher Slew rate (faster edges)
-            2: Lower Slew rate (slower edges)
-            3: Reserved (No adjustments)
-
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-bus-hold: true
-      bias-disable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 required:
   - compatible
   - reg
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+allOf:
+  - $ref: qcom,lpass-lpi-common.yaml#
+
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml
index a9167dac9ab58..240e6d45cc95e 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml
@@ -32,16 +32,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -57,7 +47,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -79,48 +70,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-lpass-lpi-pinctrl.yaml
index abac3311fc550..f4cf2ce86fcd4 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-lpass-lpi-pinctrl.yaml
@@ -31,16 +31,6 @@ properties:
     items:
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -56,7 +46,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -75,48 +66,17 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
 
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml
index 4b4be7efc150a..750c996c10a71 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml
@@ -30,16 +30,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -55,7 +45,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -78,48 +69,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-            0: No adjustments
-            1: Higher Slew rate (faster edges)
-            2: Lower Slew rate (slower edges)
-            3: Reserved (No adjustments)
-
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-bus-hold: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-lpass-lpi-pinctrl.yaml
index 2e65ae08dd211..9d782f910b318 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-lpass-lpi-pinctrl.yaml
@@ -33,16 +33,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -58,7 +48,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -81,48 +72,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml
index 1eefa9aa6a86c..e7565592da862 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml
@@ -32,16 +32,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -57,7 +47,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -81,48 +72,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
index ad5e32130fd75..bf4a72facae1d 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml
@@ -37,16 +37,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -62,7 +52,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -85,48 +76,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
index f5736ed140ee7..db72143623018 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-lpass-lpi-pinctrl.yaml
@@ -32,16 +32,6 @@ properties:
       - const: core
       - const: audio
 
-  gpio-controller: true
-
-  "#gpio-cells":
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
 patternProperties:
   "-state$":
     oneOf:
@@ -57,7 +47,8 @@ $defs:
     description:
       Pinctrl node's client devices use subnodes for desired pin configuration.
       Client device subnodes use below standard properties.
-    $ref: /schemas/pinctrl/pincfg-node.yaml
+    $ref: qcom,lpass-lpi-common.yaml#/$defs/qcom-tlmm-state
+    unevaluatedProperties: false
 
     properties:
       pins:
@@ -80,48 +71,16 @@ $defs:
           Specify the alternative function to be configured for the specified
           pins.
 
-      drive-strength:
-        enum: [2, 4, 6, 8, 10, 12, 14, 16]
-        default: 2
-        description:
-          Selects the drive strength for the specified pins, in mA.
-
-      slew-rate:
-        enum: [0, 1, 2, 3]
-        default: 0
-        description: |
-          0: No adjustments
-          1: Higher Slew rate (faster edges)
-          2: Lower Slew rate (slower edges)
-          3: Reserved (No adjustments)
-
-      bias-bus-hold: true
-      bias-pull-down: true
-      bias-pull-up: true
-      bias-disable: true
-      input-enable: true
-      output-high: true
-      output-low: true
-
-    required:
-      - pins
-      - function
-
-    additionalProperties: false
-
 allOf:
-  - $ref: pinctrl.yaml#
+  - $ref: qcom,lpass-lpi-common.yaml#
 
 required:
   - compatible
   - reg
   - clocks
   - clock-names
-  - gpio-controller
-  - "#gpio-cells"
-  - gpio-ranges
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
-- 
GitLab


From 98b94e055fcce71a4ccfc856e55d928218d9f612 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:26 +0100
Subject: [PATCH 1634/4076] dt-bindings: pinctrl: qcom,qdu1000-tlmm: restrict
 number of interrupts

QDU1000 TLMM pin controller comes with only one interrupt, so narrow
the number of interrupts previously defined in common TLMM bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml        | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
index 237cac4f6ce1d..47363c23f4ea6 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
@@ -23,7 +23,9 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
+  interrupts:
+    maxItems: 1
+
   interrupt-controller: true
   "#interrupt-cells": true
   gpio-controller: true
-- 
GitLab


From 43c9dd099e91474ae99076e2aeb99f3a5e68a00a Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:27 +0100
Subject: [PATCH 1635/4076] dt-bindings: pinctrl: qcom,sa8775p-tlmm: restrict
 number of interrupts

SA8775p TLMM pin controller comes with only one interrupt, so narrow
the number of interrupts previously defined in common TLMM bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml        | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
index 2173c5255638b..d27933258db73 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
@@ -22,7 +22,9 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
+  interrupts:
+    maxItems: 1
+
   interrupt-controller: true
   "#interrupt-cells": true
   gpio-controller: true
-- 
GitLab


From 8c0aa95bd0f885a9d87819e02bd28bc03630189d Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:28 +0100
Subject: [PATCH 1636/4076] dt-bindings: pinctrl: qcom,sdx75-tlmm: restrict
 number of interrupts

SDX75 TLMM pin controller comes with only one interrupt, so narrow
the number of interrupts previously defined in common TLMM bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml          | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
index 7cb96aa75b08b..62cd8f84af9cb 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
@@ -22,7 +22,9 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
+  interrupts:
+    maxItems: 1
+
   interrupt-controller: true
   "#interrupt-cells": true
   gpio-controller: true
-- 
GitLab


From fc19a5644b91bdfd141b911444f5238b6dc48562 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:29 +0100
Subject: [PATCH 1637/4076] dt-bindings: pinctrl: qcom,sm8550-tlmm: restrict
 number of interrupts

SM8550 TLMM pin controller comes with only one interrupt, so narrow
the number of interrupts previously defined in common TLMM bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-5-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml         | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
index f789c7753a92c..567e44875c297 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
@@ -22,7 +22,9 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
+  interrupts:
+    maxItems: 1
+
   interrupt-controller: true
   "#interrupt-cells": true
   gpio-controller: true
-- 
GitLab


From 6b7d9d4c0d496b2a27e7b2d10ec7679116450fbc Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:30 +0100
Subject: [PATCH 1638/4076] dt-bindings: pinctrl: qcom,sm8650-tlmm: restrict
 number of interrupts

SM8650 TLMM pin controller comes with only one interrupt, so narrow
the number of interrupts previously defined in common TLMM bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-6-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml         | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
index 30432be8fb07b..370789ce934ba 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
@@ -22,7 +22,9 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
+  interrupts:
+    maxItems: 1
+
   interrupt-controller: true
   "#interrupt-cells": true
   gpio-controller: true
-- 
GitLab


From 7e47d9d3750c17bdbbcbeac65f6ca54d633a58b5 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:31 +0100
Subject: [PATCH 1639/4076] dt-bindings: pinctrl: qcom,x1e80100-tlmm: restrict
 number of interrupts

X1E80100 TLMM pin controller comes with only one interrupt, so narrow
the number of interrupts previously defined in common TLMM bindings.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-7-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml       | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
index 2bde8845a31ef..3249c63a29cf0 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
@@ -22,7 +22,9 @@ properties:
   reg:
     maxItems: 1
 
-  interrupts: true
+  interrupts:
+    maxItems: 1
+
   interrupt-controller: true
   "#interrupt-cells": true
   gpio-controller: true
-- 
GitLab


From 6bd410fcb24f2308a380b621c67c822c338f5805 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:32 +0100
Subject: [PATCH 1640/4076] dt-bindings: pinctrl: qcom,ipq5018-tlmm: use common
 TLMM bindings

Reference common Qualcomm SoC TLMM bindings to drop commonly used
properties and also bring other schemas for common definitions.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-8-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,ipq5018-tlmm.yaml          | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5018-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5018-tlmm.yaml
index fad0118fd5219..23300606547c5 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5018-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5018-tlmm.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 24
@@ -95,7 +88,10 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+allOf:
+  - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml#
+
+unevaluatedProperties: false
 
 examples:
   - |
-- 
GitLab


From 79d770afa0d582956bc2cb577fc9e3b413702ab8 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:33 +0100
Subject: [PATCH 1641/4076] dt-bindings: pinctrl: qcom: drop common properties

Drop common properties already defined in referenced common Qualcomm SoC
TLMM bindings and use "unevaluatedProperties: false".  This makes the
binding smaller and easier to review.

In few places move the "required:" block to bottom, to match convention.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231208215534.195854-9-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,ipq5332-tlmm.yaml   |  9 +-----
 .../pinctrl/qcom,ipq8074-pinctrl.yaml         |  9 +-----
 .../bindings/pinctrl/qcom,ipq9574-tlmm.yaml   |  9 +-----
 .../bindings/pinctrl/qcom,mdm9607-tlmm.yaml   | 18 ++++-------
 .../pinctrl/qcom,msm8660-pinctrl.yaml         |  9 +-----
 .../bindings/pinctrl/qcom,msm8909-tlmm.yaml   | 18 ++++-------
 .../pinctrl/qcom,msm8916-pinctrl.yaml         |  9 +-----
 .../pinctrl/qcom,msm8960-pinctrl.yaml         |  9 +-----
 .../pinctrl/qcom,msm8974-pinctrl.yaml         |  9 +-----
 .../pinctrl/qcom,msm8976-pinctrl.yaml         |  9 +-----
 .../pinctrl/qcom,msm8994-pinctrl.yaml         |  9 +-----
 .../pinctrl/qcom,msm8996-pinctrl.yaml         |  9 +-----
 .../pinctrl/qcom,msm8998-pinctrl.yaml         |  9 +-----
 .../bindings/pinctrl/qcom,qcm2290-tlmm.yaml   |  9 +-----
 .../bindings/pinctrl/qcom,qcs404-pinctrl.yaml |  9 +-----
 .../bindings/pinctrl/qcom,qdu1000-tlmm.yaml   | 10 +------
 .../bindings/pinctrl/qcom,sa8775p-tlmm.yaml   | 19 ++++--------
 .../bindings/pinctrl/qcom,sc7180-pinctrl.yaml |  9 +-----
 .../bindings/pinctrl/qcom,sc7280-pinctrl.yaml | 30 ++-----------------
 .../bindings/pinctrl/qcom,sc8180x-tlmm.yaml   | 20 +++++--------
 .../bindings/pinctrl/qcom,sc8280xp-tlmm.yaml  | 18 ++++-------
 .../bindings/pinctrl/qcom,sdm630-pinctrl.yaml | 10 +------
 .../bindings/pinctrl/qcom,sdm670-tlmm.yaml    | 19 ++++--------
 .../bindings/pinctrl/qcom,sdm845-pinctrl.yaml | 10 +------
 .../bindings/pinctrl/qcom,sdx75-tlmm.yaml     | 10 +------
 .../bindings/pinctrl/qcom,sm6115-tlmm.yaml    |  8 +----
 .../bindings/pinctrl/qcom,sm6125-tlmm.yaml    | 20 +++++--------
 .../bindings/pinctrl/qcom,sm6350-tlmm.yaml    | 20 ++++---------
 .../bindings/pinctrl/qcom,sm6375-tlmm.yaml    | 18 ++++-------
 .../bindings/pinctrl/qcom,sm7150-tlmm.yaml    |  9 +-----
 .../bindings/pinctrl/qcom,sm8150-pinctrl.yaml |  9 +-----
 .../bindings/pinctrl/qcom,sm8250-pinctrl.yaml |  9 +-----
 .../bindings/pinctrl/qcom,sm8350-tlmm.yaml    | 20 ++++---------
 .../bindings/pinctrl/qcom,sm8450-tlmm.yaml    | 20 ++++---------
 .../bindings/pinctrl/qcom,sm8550-tlmm.yaml    | 10 +------
 .../bindings/pinctrl/qcom,sm8650-tlmm.yaml    | 10 +------
 .../bindings/pinctrl/qcom,x1e80100-tlmm.yaml  | 10 +------
 37 files changed, 95 insertions(+), 376 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml
index 3d3086ae1ba69..e571cd64418f2 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml
@@ -26,13 +26,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 27
@@ -100,7 +93,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml
index e053fbd588b51..6f90dbbdbdcce 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 35
@@ -103,7 +96,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml
index e5e9962b2174f..bca903b5da6d0 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 33
@@ -97,7 +90,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
index 5ece3b9d676b3..bd3cbb44c99a4 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
@@ -25,19 +25,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -110,6 +98,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml
index a059716117809..61f5be21f30cc 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 86
@@ -92,7 +85,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml
index 5095e86fe9a21..295dd5fcf4c3d 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml
@@ -25,19 +25,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -108,6 +96,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml
index 063d004967bbe..904af87f9eaff 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 61
@@ -114,7 +107,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml
index 9172b50f7a982..46618740bd312 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 76
@@ -108,7 +101,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml
index 8a3be65c51ede..840fdaabde127 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 73
@@ -124,7 +117,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml
index ca95de0b87a6a..d4391c194ff7c 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 73
@@ -104,7 +97,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml
index 41525ecfa8e3a..fa90981db40b3 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml
@@ -25,13 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 73
@@ -114,7 +107,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml
index 59d406b609574..c5010c175b238 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 75
@@ -133,7 +126,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml
index bd6d7caf499af..bcaa231adaf78 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml
@@ -23,13 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 75
@@ -118,7 +111,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml
index c323f6d495a44..e123beb33aef5 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml
@@ -22,13 +22,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -92,7 +85,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml
index b1b9cd319e50a..4009501b3414f 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml
@@ -29,13 +29,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 60
@@ -130,7 +123,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
index 47363c23f4ea6..88afeae530c68 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml
@@ -26,10 +26,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 76
@@ -37,10 +33,6 @@ properties:
   gpio-line-names:
     maxItems: 151
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -103,7 +95,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
index d27933258db73..e9abbf2c0689b 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml
@@ -25,13 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 74
@@ -39,12 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 148
 
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -110,6 +97,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml
index 573e459b1c44a..5606f2136ad10 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml
@@ -29,13 +29,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 60
@@ -112,7 +105,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
index c8735ab97e407..5329fe2a43978 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
@@ -23,24 +23,6 @@ properties:
     description: Specifies the TLMM summary IRQ
     maxItems: 1
 
-  interrupt-controller: true
-
-  '#interrupt-cells':
-    description:
-      Specifies the PIN numbers and Flags, as defined in defined in
-      include/dt-bindings/interrupt-controller/irq.h
-    const: 2
-
-  gpio-controller: true
-
-  '#gpio-cells':
-    description: Specifying the pin number and flags, as defined in
-      include/dt-bindings/gpio/gpio.h
-    const: 2
-
-  gpio-ranges:
-    maxItems: 1
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 88
@@ -48,8 +30,6 @@ properties:
   gpio-line-names:
     maxItems: 175
 
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -124,14 +104,8 @@ allOf:
 required:
   - compatible
   - reg
-  - interrupts
-  - interrupt-controller
-  - '#interrupt-cells'
-  - gpio-controller
-  - '#gpio-cells'
-  - gpio-ranges
-
-additionalProperties: false
+
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml
index b086a5184235a..c122bb849f0f7 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml
@@ -31,20 +31,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  '#interrupt-cells': true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  '#gpio-cells': true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-  - reg-names
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -106,6 +93,13 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+  - reg-names
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml
index 4bd6d7977d3e8..ed344deaf8b9e 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml
@@ -25,19 +25,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -108,6 +96,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml
index 508e0633b253e..a00cb43df144b 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml
@@ -34,10 +34,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 57
@@ -45,10 +41,6 @@ properties:
   gpio-line-names:
     maxItems: 114
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -130,7 +122,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml
index 84a15f77e710a..b56e717aa28e7 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml
@@ -25,23 +25,10 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 75
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -98,6 +85,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml
index d301881ddfa8e..dfe5616b9b858 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml
@@ -26,10 +26,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 75
@@ -37,10 +33,6 @@ properties:
   gpio-line-names:
     maxItems: 150
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -110,7 +102,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
index 62cd8f84af9cb..cb1d978d02c9a 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx75-tlmm.yaml
@@ -25,10 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 67
@@ -36,10 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 133
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -102,7 +94,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml
index 871df54f69a2e..7f36f9b933330 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml
@@ -29,13 +29,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
   gpio-reserved-ranges: true
-  wakeup-parent: true
 
 patternProperties:
   "-state$":
@@ -97,7 +91,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml
index 8d77707b02b9f..ddeaeaa9a450a 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml
@@ -30,20 +30,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-  - reg-names
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -105,6 +92,13 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+  - reg-names
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
index 27af379cf791a..a4771f87d9364 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
@@ -26,10 +26,6 @@ properties:
     minItems: 9
     maxItems: 9
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 78
@@ -37,16 +33,6 @@ properties:
   gpio-line-names:
     maxItems: 156
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -112,6 +98,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
index 6e02ba24825f1..047f82863f9bb 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
@@ -25,19 +25,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
 
 patternProperties:
   "-state$":
@@ -113,6 +101,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml
index ede0f3acad9c4..7f23f939ad325 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml
@@ -32,13 +32,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 60
@@ -111,7 +104,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml
index c6439626464ef..bdb7ed4be0267 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml
@@ -30,13 +30,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 88
@@ -113,7 +106,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml
index 021c547085246..b5d04347c064d 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml
@@ -28,13 +28,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 90
@@ -106,7 +99,7 @@ required:
   - reg
   - reg-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml
index 6e8f41ff0a76b..ec5e09611d810 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml
@@ -25,10 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 102
@@ -36,16 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 203
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -108,6 +94,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml
index 5163fe3f53652..16fd2c5e23393 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml
@@ -25,10 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 105
@@ -36,16 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 210
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -107,6 +93,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
index 567e44875c297..c2ae79df424fd 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml
@@ -25,10 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 105
@@ -36,10 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 210
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -119,7 +111,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
index 370789ce934ba..c0a06abf851d3 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8650-tlmm.yaml
@@ -25,10 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 105
@@ -36,10 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 210
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -112,7 +104,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
index 3249c63a29cf0..a1333e0743a9c 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,x1e80100-tlmm.yaml
@@ -25,10 +25,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-
   gpio-reserved-ranges:
     minItems: 1
     maxItems: 119
@@ -36,10 +32,6 @@ properties:
   gpio-line-names:
     maxItems: 238
 
-  "#gpio-cells": true
-  gpio-ranges: true
-  wakeup-parent: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -108,7 +100,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
-- 
GitLab


From b22794c0f7b13ece8e44245ab99b2dcdd199caf2 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 8 Dec 2023 22:55:34 +0100
Subject: [PATCH 1642/4076] dt-bindings: pinctrl: qcom: drop common properties
 and allow wakeup-parent

Drop common properties already defined in referenced common Qualcomm SoC
TLMM bindings and use "unevaluatedProperties: false".  This makes the
binding smaller and easier to review.  Additionally this allows now
"wakeup-parent" property coming from common TLMM bindings.

In few places move the "required:" block to bottom, to match convention.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231208215534.195854-10-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/qcom,ipq6018-pinctrl.yaml |  8 +-------
 .../bindings/pinctrl/qcom,mdm9615-pinctrl.yaml | 18 ++++++------------
 .../bindings/pinctrl/qcom,msm8226-pinctrl.yaml |  8 +-------
 .../bindings/pinctrl/qcom,msm8953-pinctrl.yaml |  7 +------
 .../bindings/pinctrl/qcom,sdx55-pinctrl.yaml   |  8 +-------
 .../bindings/pinctrl/qcom,sdx65-tlmm.yaml      |  8 +-------
 6 files changed, 11 insertions(+), 46 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml
index 7c3e5e043f078..ed00fbaec11b0 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml
@@ -22,12 +22,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-
 patternProperties:
   "-state$":
     oneOf:
@@ -100,7 +94,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml
index 5885aee95c98e..299e0b4b0ab42 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml
@@ -23,18 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  '#interrupt-cells': true
-  gpio-controller: true
-  '#gpio-cells': true
-  gpio-ranges: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
 patternProperties:
   "-state$":
     oneOf:
@@ -74,6 +62,12 @@ $defs:
     required:
       - pins
 
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
index a602bf0d27fbc..68d3fa2105b85 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
@@ -23,12 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-
   gpio-reserved-ranges:
     maxItems: 1
 
@@ -82,7 +76,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml
index 798aac9e6e31b..8a3a962f6c007 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml
@@ -22,12 +22,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
   gpio-reserved-ranges: true
-  "#gpio-cells": true
-  gpio-ranges: true
 
 patternProperties:
   "-state$":
@@ -117,7 +112,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml
index 67af99dd8f147..edbcff92bbf91 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml
@@ -23,12 +23,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-
   gpio-reserved-ranges:
     maxItems: 1
 
@@ -102,7 +96,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml
index 27319782d94be..a31b638c456d1 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml
@@ -22,12 +22,6 @@ properties:
   interrupts:
     maxItems: 1
 
-  interrupt-controller: true
-  "#interrupt-cells": true
-  gpio-controller: true
-  "#gpio-cells": true
-  gpio-ranges: true
-
   gpio-reserved-ranges:
     maxItems: 1
 
@@ -122,7 +116,7 @@ required:
   - compatible
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
-- 
GitLab


From ff629d300413cf6c091b4f96cf4b14472ad39a3b Mon Sep 17 00:00:00 2001
From: Wang Jinchao <wangjinchao@xfusion.com>
Date: Fri, 15 Dec 2023 18:11:44 +0800
Subject: [PATCH 1643/4076] pinctrl: qcom: lpass-lpi: remove duplicated include

remove the second #include <linux/seq_file.h>

Signed-off-by: Wang Jinchao <wangjinchao@xfusion.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/202312151810+0800-wangjinchao@xfusion.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-lpass-lpi.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
index 9e410a281bfa9..0d98008e33eea 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
@@ -338,7 +338,6 @@ static void lpi_gpio_set(struct gpio_chip *chip, unsigned int pin, int value)
 }
 
 #ifdef CONFIG_DEBUG_FS
-#include <linux/seq_file.h>
 
 static unsigned int lpi_regval_to_drive(u32 val)
 {
-- 
GitLab


From 00bb152d62825b5f659d9b4ff87d49637e44eea0 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Tue, 19 Dec 2023 15:41:02 +0100
Subject: [PATCH 1644/4076] dt-bindings: pinctrl: xilinx: Rename *gpio to
 *gpio-grp

Anything ending with gpio/gpios is taken as gpio phande/description which
is reported as the issue coming from gpio-consumer.yaml schema.
That's why rename the gpio suffix to gpio-grp to avoid name collision.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/2e3a1f1f57cf929bd05115bc081e6d01d5a53443.1702996859.git.michal.simek@amd.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml          | 2 +-
 .../devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml
index b85f9e36ce4b7..d2676f92ef5bb 100644
--- a/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml
@@ -39,7 +39,7 @@ properties:
       phandle to the SLCR.
 
 patternProperties:
-  '^(.*-)?(default|gpio)$':
+  '^(.*-)?(default|gpio-grp)$':
     type: object
     patternProperties:
       '^mux':
diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
index 01b6f2b578437..f13d315b5d5e8 100644
--- a/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
@@ -31,7 +31,7 @@ properties:
     const: xlnx,zynqmp-pinctrl
 
 patternProperties:
-  '^(.*-)?(default|gpio)$':
+  '^(.*-)?(default|gpio-grp)$':
     type: object
     patternProperties:
       '^mux':
-- 
GitLab


From 7d7cd22dc497dc79c2b1ae0e26cada1c5207d5dd Mon Sep 17 00:00:00 2001
From: Patrick Rudolph <patrick.rudolph@9elements.com>
Date: Tue, 19 Dec 2023 13:53:49 +0100
Subject: [PATCH 1645/4076] pinctrl: cy8c95x0: Cache muxed registers

Currently the port specific registers behind the PORTSEL mux aren't
cached in the regmap and thus the typical setup time for a single pin
on cy8c9560 is about 200msec on our system. The hotspot is the IRQ
(un)masking, which causes lots of R/W operations.

Introduce a separate regmap for muxed registers and helper functions
to use the newly introduced regmap for muxed register access under
the i2c lock.

With the new cache in place the typical pin setup time is reduced to
20msec, making it about 10 times faster. As a side effect the system
boot time is also reduced by 50%.

Signed-off-by: Patrick Rudolph <patrick.rudolph@9elements.com>
Link: https://lore.kernel.org/r/20231219125350.4031370-1-patrick.rudolph@9elements.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 458 ++++++++++++++++++++---------
 1 file changed, 315 insertions(+), 143 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 04285c930e945..5be0c6c6713a6 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -58,6 +58,10 @@
 
 #define CY8C95X0_PIN_TO_OFFSET(x) (((x) >= 20) ? ((x) + 4) : (x))
 
+#define CY8C95X0_MUX_REGMAP_TO_PORT(x) ((x) / MUXED_STRIDE)
+#define CY8C95X0_MUX_REGMAP_TO_REG(x) (((x) % MUXED_STRIDE) + CY8C95X0_INTMASK)
+#define CY8C95X0_MUX_REGMAP_TO_OFFSET(x, p) ((x) - CY8C95X0_INTMASK + (p) * MUXED_STRIDE)
+
 static const struct i2c_device_id cy8c95x0_id[] = {
 	{ "cy8c9520", 20, },
 	{ "cy8c9540", 40, },
@@ -119,12 +123,13 @@ static const struct dmi_system_id cy8c95x0_dmi_acpi_irq_info[] = {
 #define MAX_BANK 8
 #define BANK_SZ 8
 #define MAX_LINE	(MAX_BANK * BANK_SZ)
-
+#define MUXED_STRIDE	16
 #define CY8C95X0_GPIO_MASK		GENMASK(7, 0)
 
 /**
  * struct cy8c95x0_pinctrl - driver data
- * @regmap:         Device's regmap
+ * @regmap:         Device's regmap. Only direct access registers.
+ * @muxed_regmap:   Regmap for all muxed registers.
  * @irq_lock:       IRQ bus lock
  * @i2c_lock:       Mutex for the device internal mux register
  * @irq_mask:       I/O bits affected by interrupts
@@ -146,6 +151,7 @@ static const struct dmi_system_id cy8c95x0_dmi_acpi_irq_info[] = {
  */
 struct cy8c95x0_pinctrl {
 	struct regmap *regmap;
+	struct regmap *muxed_regmap;
 	struct mutex irq_lock;
 	struct mutex i2c_lock;
 	DECLARE_BITMAP(irq_mask, MAX_LINE);
@@ -375,6 +381,54 @@ static bool cy8c95x0_precious_register(struct device *dev, unsigned int reg)
 	}
 }
 
+static bool cy8c95x0_muxed_register(unsigned int reg)
+{
+	switch (reg) {
+	case CY8C95X0_INTMASK:
+	case CY8C95X0_PWMSEL:
+	case CY8C95X0_INVERT:
+	case CY8C95X0_DIRECTION:
+	case CY8C95X0_DRV_PU:
+	case CY8C95X0_DRV_PD:
+	case CY8C95X0_DRV_ODH:
+	case CY8C95X0_DRV_ODL:
+	case CY8C95X0_DRV_PP_FAST:
+	case CY8C95X0_DRV_PP_SLOW:
+	case CY8C95X0_DRV_HIZ:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool cy8c95x0_wc_register(unsigned int reg)
+{
+	switch (reg) {
+	case CY8C95X0_DRV_PU:
+	case CY8C95X0_DRV_PD:
+	case CY8C95X0_DRV_ODH:
+	case CY8C95X0_DRV_ODL:
+	case CY8C95X0_DRV_PP_FAST:
+	case CY8C95X0_DRV_PP_SLOW:
+	case CY8C95X0_DRV_HIZ:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool cy8c95x0_quick_path_register(unsigned int reg)
+{
+	switch (reg) {
+	case CY8C95X0_INPUT_(0) ... CY8C95X0_INPUT_(7):
+	case CY8C95X0_INTSTATUS_(0) ... CY8C95X0_INTSTATUS_(7):
+	case CY8C95X0_OUTPUT_(0) ... CY8C95X0_OUTPUT_(7):
+		return true;
+	default:
+		return false;
+	}
+}
+
 static const struct reg_default cy8c95x0_reg_defaults[] = {
 	{ CY8C95X0_OUTPUT_(0), GENMASK(7, 0) },
 	{ CY8C95X0_OUTPUT_(1), GENMASK(7, 0) },
@@ -388,7 +442,89 @@ static const struct reg_default cy8c95x0_reg_defaults[] = {
 	{ CY8C95X0_PWMSEL, 0 },
 };
 
+static int
+cy8c95x0_mux_reg_read(void *context, unsigned int off, unsigned int *val)
+{
+	struct cy8c95x0_pinctrl *chip = context;
+	u8 port = CY8C95X0_MUX_REGMAP_TO_PORT(off);
+	int ret, reg = CY8C95X0_MUX_REGMAP_TO_REG(off);
+
+	mutex_lock(&chip->i2c_lock);
+	/* Select the correct bank */
+	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * Read the register through direct access regmap. The target range
+	 * is marked volatile.
+	 */
+	ret = regmap_read(chip->regmap, reg, val);
+out:
+	mutex_unlock(&chip->i2c_lock);
+
+	return ret;
+}
+
+static int
+cy8c95x0_mux_reg_write(void *context, unsigned int off, unsigned int val)
+{
+	struct cy8c95x0_pinctrl *chip = context;
+	u8 port = CY8C95X0_MUX_REGMAP_TO_PORT(off);
+	int ret, reg = CY8C95X0_MUX_REGMAP_TO_REG(off);
+
+	mutex_lock(&chip->i2c_lock);
+	/* Select the correct bank */
+	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * Write the register through direct access regmap. The target range
+	 * is marked volatile.
+	 */
+	ret = regmap_write(chip->regmap, reg, val);
+out:
+	mutex_unlock(&chip->i2c_lock);
+
+	return ret;
+}
+
+static bool cy8c95x0_mux_accessible_register(struct device *dev, unsigned int off)
+{
+	struct i2c_client *i2c = to_i2c_client(dev);
+	struct cy8c95x0_pinctrl *chip = i2c_get_clientdata(i2c);
+	u8 port = CY8C95X0_MUX_REGMAP_TO_PORT(off);
+	u8 reg = CY8C95X0_MUX_REGMAP_TO_REG(off);
+
+	if (port >= chip->nport)
+		return false;
+
+	return cy8c95x0_muxed_register(reg);
+}
+
+static struct regmap_bus cy8c95x0_regmap_bus = {
+	.reg_read = cy8c95x0_mux_reg_read,
+	.reg_write = cy8c95x0_mux_reg_write,
+};
+
+/* Regmap for muxed registers CY8C95X0_INTMASK - CY8C95X0_DRV_HIZ */
+static const struct regmap_config cy8c95x0_muxed_regmap = {
+	.name = "muxed",
+	.reg_bits = 8,
+	.val_bits = 8,
+	.cache_type = REGCACHE_FLAT,
+	.use_single_read = true,
+	.use_single_write = true,
+	.max_register = MUXED_STRIDE * BANK_SZ,
+	.num_reg_defaults_raw = MUXED_STRIDE * BANK_SZ,
+	.readable_reg = cy8c95x0_mux_accessible_register,
+	.writeable_reg = cy8c95x0_mux_accessible_register,
+};
+
+/* Direct access regmap */
 static const struct regmap_config cy8c95x0_i2c_regmap = {
+	.name = "direct",
 	.reg_bits = 8,
 	.val_bits = 8,
 
@@ -404,6 +540,147 @@ static const struct regmap_config cy8c95x0_i2c_regmap = {
 	.max_register = CY8C95X0_COMMAND,
 };
 
+static inline int cy8c95x0_regmap_update_bits_base(struct cy8c95x0_pinctrl *chip,
+						   unsigned int reg,
+						   unsigned int port,
+						   unsigned int mask,
+						   unsigned int val,
+						   bool *change, bool async,
+						   bool force)
+{
+	struct regmap *regmap;
+	int ret, off, i, read_val;
+
+	/* Caller should never modify PORTSEL directly */
+	if (reg == CY8C95X0_PORTSEL)
+		return -EINVAL;
+
+	/* Registers behind the PORTSEL mux have their own regmap */
+	if (cy8c95x0_muxed_register(reg)) {
+		regmap = chip->muxed_regmap;
+		off = CY8C95X0_MUX_REGMAP_TO_OFFSET(reg, port);
+	} else {
+		regmap = chip->regmap;
+		/* Quick path direct access registers honor the port argument */
+		if (cy8c95x0_quick_path_register(reg))
+			off = reg + port;
+		else
+			off = reg;
+	}
+
+	ret = regmap_update_bits_base(regmap, off, mask, val, change, async, force);
+	if (ret < 0)
+		return ret;
+
+	/* Update the cache when a WC bit is written */
+	if (cy8c95x0_wc_register(reg) && (mask & val)) {
+		for (i = CY8C95X0_DRV_PU; i <= CY8C95X0_DRV_HIZ; i++) {
+			if (i == reg)
+				continue;
+			off = CY8C95X0_MUX_REGMAP_TO_OFFSET(i, port);
+
+			ret = regmap_read(regmap, off, &read_val);
+			if (ret < 0)
+				continue;
+
+			if (!(read_val & mask & val))
+				continue;
+
+			regcache_cache_only(regmap, true);
+			regmap_update_bits(regmap, off, mask & val, 0);
+			regcache_cache_only(regmap, false);
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * cy8c95x0_regmap_write_bits() - writes a register using the regmap cache
+ * @chip: The pinctrl to work on
+ * @reg: The register to write to. Can be direct access or muxed register.
+ *       MUST NOT be the PORTSEL register.
+ * @port: The port to be used for muxed registers or quick path direct access
+ *        registers. Otherwise unused.
+ * @mask: Bitmask to change
+ * @val: New value for bitmask
+ *
+ * This function handles the register writes to the direct access registers and
+ * the muxed registers while caching all register accesses, internally handling
+ * the correct state of the PORTSEL register and protecting the access to muxed
+ * registers.
+ * The caller must only use this function to change registers behind the PORTSEL mux.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int cy8c95x0_regmap_write_bits(struct cy8c95x0_pinctrl *chip, unsigned int reg,
+				      unsigned int port, unsigned int mask, unsigned int val)
+{
+	return cy8c95x0_regmap_update_bits_base(chip, reg, port, mask, val, NULL, false, true);
+}
+
+/**
+ * cy8c95x0_regmap_update_bits() - updates a register using the regmap cache
+ * @chip: The pinctrl to work on
+ * @reg: The register to write to. Can be direct access or muxed register.
+ *       MUST NOT be the PORTSEL register.
+ * @port: The port to be used for muxed registers or quick path direct access
+ *        registers. Otherwise unused.
+ * @mask: Bitmask to change
+ * @val: New value for bitmask
+ *
+ * This function handles the register updates to the direct access registers and
+ * the muxed registers while caching all register accesses, internally handling
+ * the correct state of the PORTSEL register and protecting the access to muxed
+ * registers.
+ * The caller must only use this function to change registers behind the PORTSEL mux.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int cy8c95x0_regmap_update_bits(struct cy8c95x0_pinctrl *chip, unsigned int reg,
+				       unsigned int port, unsigned int mask, unsigned int val)
+{
+	return cy8c95x0_regmap_update_bits_base(chip, reg, port, mask, val, NULL, false, false);
+}
+
+/**
+ * cy8c95x0_regmap_read() - reads a register using the regmap cache
+ * @chip: The pinctrl to work on
+ * @reg: The register to read from. Can be direct access or muxed register.
+ * @port: The port to be used for muxed registers or quick path direct access
+ *        registers. Otherwise unused.
+ * @read_val: Value read from hardware or cache
+ *
+ * This function handles the register reads from the direct access registers and
+ * the muxed registers while caching all register accesses, internally handling
+ * the correct state of the PORTSEL register and protecting the access to muxed
+ * registers.
+ * The caller must only use this function to read registers behind the PORTSEL mux.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int cy8c95x0_regmap_read(struct cy8c95x0_pinctrl *chip, unsigned int reg,
+				unsigned int port, unsigned int *read_val)
+{
+	struct regmap *regmap;
+	int off;
+
+	/* Registers behind the PORTSEL mux have their own regmap */
+	if (cy8c95x0_muxed_register(reg)) {
+		regmap = chip->muxed_regmap;
+		off = CY8C95X0_MUX_REGMAP_TO_OFFSET(reg, port);
+	} else {
+		regmap = chip->regmap;
+		/* Quick path direct access registers honor the port argument */
+		if (cy8c95x0_quick_path_register(reg))
+			off = reg + port;
+		else
+			off = reg;
+	}
+
+	return regmap_read(regmap, off, read_val);
+}
+
 static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 				    unsigned long *val, unsigned long *mask)
 {
@@ -411,7 +688,7 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	DECLARE_BITMAP(tval, MAX_LINE);
 	int write_val;
 	int ret = 0;
-	int i, off = 0;
+	int i;
 	u8 bits;
 
 	/* Add the 4 bit gap of Gport2 */
@@ -423,53 +700,22 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_shift_left(tval, tval, 4, MAX_LINE);
 	bitmap_replace(tval, tval, val, chip->shiftmask, BANK_SZ * 3);
 
-	mutex_lock(&chip->i2c_lock);
 	for (i = 0; i < chip->nport; i++) {
 		/* Skip over unused banks */
 		bits = bitmap_get_value8(tmask, i * BANK_SZ);
 		if (!bits)
 			continue;
 
-		switch (reg) {
-		/* Muxed registers */
-		case CY8C95X0_INTMASK:
-		case CY8C95X0_PWMSEL:
-		case CY8C95X0_INVERT:
-		case CY8C95X0_DIRECTION:
-		case CY8C95X0_DRV_PU:
-		case CY8C95X0_DRV_PD:
-		case CY8C95X0_DRV_ODH:
-		case CY8C95X0_DRV_ODL:
-		case CY8C95X0_DRV_PP_FAST:
-		case CY8C95X0_DRV_PP_SLOW:
-		case CY8C95X0_DRV_HIZ:
-			ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, i);
-			if (ret < 0)
-				goto out;
-			off = reg;
-			break;
-		/* Direct access registers */
-		case CY8C95X0_INPUT:
-		case CY8C95X0_OUTPUT:
-		case CY8C95X0_INTSTATUS:
-			off = reg + i;
-			break;
-		default:
-			ret = -EINVAL;
-			goto out;
-		}
-
 		write_val = bitmap_get_value8(tval, i * BANK_SZ);
 
-		ret = regmap_update_bits(chip->regmap, off, bits, write_val);
+		ret = cy8c95x0_regmap_update_bits(chip, reg, i, bits, write_val);
 		if (ret < 0)
 			goto out;
 	}
 out:
-	mutex_unlock(&chip->i2c_lock);
 
 	if (ret < 0)
-		dev_err(chip->dev, "failed writing register %d: err %d\n", off, ret);
+		dev_err(chip->dev, "failed writing register %d, port %d: err %d\n", reg, i, ret);
 
 	return ret;
 }
@@ -482,7 +728,7 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	DECLARE_BITMAP(tmp, MAX_LINE);
 	int read_val;
 	int ret = 0;
-	int i, off = 0;
+	int i;
 	u8 bits;
 
 	/* Add the 4 bit gap of Gport2 */
@@ -494,43 +740,13 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_shift_left(tval, tval, 4, MAX_LINE);
 	bitmap_replace(tval, tval, val, chip->shiftmask, BANK_SZ * 3);
 
-	mutex_lock(&chip->i2c_lock);
 	for (i = 0; i < chip->nport; i++) {
 		/* Skip over unused banks */
 		bits = bitmap_get_value8(tmask, i * BANK_SZ);
 		if (!bits)
 			continue;
 
-		switch (reg) {
-		/* Muxed registers */
-		case CY8C95X0_INTMASK:
-		case CY8C95X0_PWMSEL:
-		case CY8C95X0_INVERT:
-		case CY8C95X0_DIRECTION:
-		case CY8C95X0_DRV_PU:
-		case CY8C95X0_DRV_PD:
-		case CY8C95X0_DRV_ODH:
-		case CY8C95X0_DRV_ODL:
-		case CY8C95X0_DRV_PP_FAST:
-		case CY8C95X0_DRV_PP_SLOW:
-		case CY8C95X0_DRV_HIZ:
-			ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, i);
-			if (ret < 0)
-				goto out;
-			off = reg;
-			break;
-		/* Direct access registers */
-		case CY8C95X0_INPUT:
-		case CY8C95X0_OUTPUT:
-		case CY8C95X0_INTSTATUS:
-			off = reg + i;
-			break;
-		default:
-			ret = -EINVAL;
-			goto out;
-		}
-
-		ret = regmap_read(chip->regmap, off, &read_val);
+		ret = cy8c95x0_regmap_read(chip, reg, i, &read_val);
 		if (ret < 0)
 			goto out;
 
@@ -544,10 +760,8 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_replace(val, tmp, tval, chip->shiftmask, MAX_LINE);
 
 out:
-	mutex_unlock(&chip->i2c_lock);
-
 	if (ret < 0)
-		dev_err(chip->dev, "failed reading register %d: err %d\n", off, ret);
+		dev_err(chip->dev, "failed reading register %d, port %d: err %d\n", reg, i, ret);
 
 	return ret;
 }
@@ -562,12 +776,11 @@ static int cy8c95x0_gpio_direction_output(struct gpio_chip *gc,
 {
 	struct cy8c95x0_pinctrl *chip = gpiochip_get_data(gc);
 	u8 port = cypress_get_port(chip, off);
-	u8 outreg = CY8C95X0_OUTPUT_(port);
 	u8 bit = cypress_get_pin_mask(chip, off);
 	int ret;
 
 	/* Set output level */
-	ret = regmap_write_bits(chip->regmap, outreg, bit, val ? bit : 0);
+	ret = cy8c95x0_regmap_write_bits(chip, CY8C95X0_OUTPUT, port, bit, val ? bit : 0);
 	if (ret)
 		return ret;
 
@@ -577,12 +790,12 @@ static int cy8c95x0_gpio_direction_output(struct gpio_chip *gc,
 static int cy8c95x0_gpio_get_value(struct gpio_chip *gc, unsigned int off)
 {
 	struct cy8c95x0_pinctrl *chip = gpiochip_get_data(gc);
-	u8 inreg = CY8C95X0_INPUT_(cypress_get_port(chip, off));
+	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
 	u32 reg_val;
 	int ret;
 
-	ret = regmap_read(chip->regmap, inreg, &reg_val);
+	ret = cy8c95x0_regmap_read(chip, CY8C95X0_INPUT, port, &reg_val);
 	if (ret < 0) {
 		/*
 		 * NOTE:
@@ -600,10 +813,10 @@ static void cy8c95x0_gpio_set_value(struct gpio_chip *gc, unsigned int off,
 				    int val)
 {
 	struct cy8c95x0_pinctrl *chip = gpiochip_get_data(gc);
-	u8 outreg = CY8C95X0_OUTPUT_(cypress_get_port(chip, off));
+	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
 
-	regmap_write_bits(chip->regmap, outreg, bit, val ? bit : 0);
+	cy8c95x0_regmap_write_bits(chip, CY8C95X0_OUTPUT, port, bit, val ? bit : 0);
 }
 
 static int cy8c95x0_gpio_get_direction(struct gpio_chip *gc, unsigned int off)
@@ -614,24 +827,15 @@ static int cy8c95x0_gpio_get_direction(struct gpio_chip *gc, unsigned int off)
 	u32 reg_val;
 	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret < 0)
-		goto out;
-
-	ret = regmap_read(chip->regmap, CY8C95X0_DIRECTION, &reg_val);
+	ret = cy8c95x0_regmap_read(chip, CY8C95X0_DIRECTION, port, &reg_val);
 	if (ret < 0)
 		goto out;
 
-	mutex_unlock(&chip->i2c_lock);
-
 	if (reg_val & bit)
 		return GPIO_LINE_DIRECTION_IN;
 
 	return GPIO_LINE_DIRECTION_OUT;
 out:
-	mutex_unlock(&chip->i2c_lock);
 	return ret;
 }
 
@@ -647,13 +851,6 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 	u16 arg = 0;
 	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-
-	/* Select port */
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret < 0)
-		goto out;
-
 	switch (param) {
 	case PIN_CONFIG_BIAS_PULL_UP:
 		reg = CY8C95X0_DRV_PU;
@@ -680,7 +877,7 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 		reg = CY8C95X0_PWMSEL;
 		break;
 	case PIN_CONFIG_OUTPUT:
-		reg = CY8C95X0_OUTPUT_(port);
+		reg = CY8C95X0_OUTPUT;
 		break;
 	case PIN_CONFIG_OUTPUT_ENABLE:
 		reg = CY8C95X0_DIRECTION;
@@ -708,14 +905,15 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 	 * Writing 1 to one of the drive mode registers will automatically
 	 * clear conflicting set bits in the other drive mode registers.
 	 */
-	ret = regmap_read(chip->regmap, reg, &reg_val);
+	ret = cy8c95x0_regmap_read(chip, reg, port, &reg_val);
+	if (ret < 0)
+		goto out;
+
 	if (reg_val & bit)
 		arg = 1;
 
 	*config = pinconf_to_config_packed(param, (u16)arg);
 out:
-	mutex_unlock(&chip->i2c_lock);
-
 	return ret;
 }
 
@@ -729,13 +927,6 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	unsigned int reg;
 	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-
-	/* Select port */
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret < 0)
-		goto out;
-
 	switch (param) {
 	case PIN_CONFIG_BIAS_PULL_UP:
 		__clear_bit(off, chip->push_pull);
@@ -772,10 +963,8 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	 * Writing 1 to one of the drive mode registers will automatically
 	 * clear conflicting set bits in the other drive mode registers.
 	 */
-	ret = regmap_write_bits(chip->regmap, reg, bit, bit);
-
+	ret = cy8c95x0_regmap_write_bits(chip, reg, port, bit, bit);
 out:
-	mutex_unlock(&chip->i2c_lock);
 	return ret;
 }
 
@@ -1092,14 +1281,8 @@ static int cy8c95x0_set_mode(struct cy8c95x0_pinctrl *chip, unsigned int off, bo
 {
 	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
-	int ret;
 
-	/* Select port */
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret < 0)
-		return ret;
-
-	return regmap_write_bits(chip->regmap, CY8C95X0_PWMSEL, bit, mode ? bit : 0);
+	return cy8c95x0_regmap_write_bits(chip, CY8C95X0_PWMSEL, port, bit, mode ? bit : 0);
 }
 
 static int cy8c95x0_pinmux_mode(struct cy8c95x0_pinctrl *chip,
@@ -1117,24 +1300,19 @@ static int cy8c95x0_pinmux_mode(struct cy8c95x0_pinctrl *chip,
 		return 0;
 
 	/* Set direction to output & set output to 1 so that PWM can work */
-	ret = regmap_write_bits(chip->regmap, CY8C95X0_DIRECTION, bit, bit);
+	ret = cy8c95x0_regmap_write_bits(chip, CY8C95X0_DIRECTION, port, bit, bit);
 	if (ret < 0)
 		return ret;
 
-	return regmap_write_bits(chip->regmap, CY8C95X0_OUTPUT_(port), bit, bit);
+	return cy8c95x0_regmap_write_bits(chip, CY8C95X0_OUTPUT, port, bit, bit);
 }
 
 static int cy8c95x0_set_mux(struct pinctrl_dev *pctldev, unsigned int selector,
 			    unsigned int group)
 {
 	struct cy8c95x0_pinctrl *chip = pinctrl_dev_get_drvdata(pctldev);
-	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-	ret = cy8c95x0_pinmux_mode(chip, selector, group);
-	mutex_unlock(&chip->i2c_lock);
-
-	return ret;
+	return cy8c95x0_pinmux_mode(chip, selector, group);
 }
 
 static int cy8c95x0_gpio_request_enable(struct pinctrl_dev *pctldev,
@@ -1142,13 +1320,8 @@ static int cy8c95x0_gpio_request_enable(struct pinctrl_dev *pctldev,
 					unsigned int pin)
 {
 	struct cy8c95x0_pinctrl *chip = pinctrl_dev_get_drvdata(pctldev);
-	int ret;
-
-	mutex_lock(&chip->i2c_lock);
-	ret = cy8c95x0_set_mode(chip, pin, false);
-	mutex_unlock(&chip->i2c_lock);
 
-	return ret;
+	return cy8c95x0_set_mode(chip, pin, false);
 }
 
 static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip,
@@ -1158,13 +1331,7 @@ static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip,
 	u8 bit = cypress_get_pin_mask(chip, pin);
 	int ret;
 
-	/* Select port... */
-	ret = regmap_write(chip->regmap, CY8C95X0_PORTSEL, port);
-	if (ret)
-		return ret;
-
-	/* ...then direction */
-	ret = regmap_write_bits(chip->regmap, CY8C95X0_DIRECTION, bit, input ? bit : 0);
+	ret = cy8c95x0_regmap_write_bits(chip, CY8C95X0_DIRECTION, port, bit, input ? bit : 0);
 	if (ret)
 		return ret;
 
@@ -1173,7 +1340,7 @@ static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip,
 	 * the direction register isn't sufficient in Push-Pull mode.
 	 */
 	if (input && test_bit(pin, chip->push_pull)) {
-		ret = regmap_write_bits(chip->regmap, CY8C95X0_DRV_HIZ, bit, bit);
+		ret = cy8c95x0_regmap_write_bits(chip, CY8C95X0_DRV_HIZ, port, bit, bit);
 		if (ret)
 			return ret;
 
@@ -1188,13 +1355,8 @@ static int cy8c95x0_gpio_set_direction(struct pinctrl_dev *pctldev,
 				       unsigned int pin, bool input)
 {
 	struct cy8c95x0_pinctrl *chip = pinctrl_dev_get_drvdata(pctldev);
-	int ret;
 
-	mutex_lock(&chip->i2c_lock);
-	ret = cy8c95x0_pinmux_direction(chip, pin, input);
-	mutex_unlock(&chip->i2c_lock);
-
-	return ret;
+	return cy8c95x0_pinmux_direction(chip, pin, input);
 }
 
 static const struct pinmux_ops cy8c95x0_pmxops = {
@@ -1396,12 +1558,22 @@ static int cy8c95x0_probe(struct i2c_client *client)
 		gpiod_set_consumer_name(chip->gpio_reset, "CY8C95X0 RESET");
 	}
 
+	/* Generic regmap for direct access registers */
 	chip->regmap = devm_regmap_init_i2c(client, &cy8c95x0_i2c_regmap);
 	if (IS_ERR(chip->regmap)) {
 		ret = PTR_ERR(chip->regmap);
 		goto err_exit;
 	}
 
+	/* Port specific regmap behind PORTSEL mux */
+	chip->muxed_regmap = devm_regmap_init(&client->dev, &cy8c95x0_regmap_bus,
+					      chip, &cy8c95x0_muxed_regmap);
+	if (IS_ERR(chip->muxed_regmap)) {
+		ret = dev_err_probe(&client->dev, PTR_ERR(chip->muxed_regmap),
+				    "Failed to register muxed regmap\n");
+		goto err_exit;
+	}
+
 	bitmap_zero(chip->push_pull, MAX_LINE);
 	bitmap_zero(chip->shiftmask, MAX_LINE);
 	bitmap_set(chip->shiftmask, 0, 20);
-- 
GitLab


From d5cfbdfc96aadc96a2bf6176269b994e2ce31717 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 19 Dec 2023 13:54:15 -0500
Subject: [PATCH 1646/4076] ring-buffer: Have ring_buffer_print_page_header()
 be able to access ring_buffer_iter

In order to introduce sub-buffer size per ring buffer, some internal
refactoring is needed. As ring_buffer_print_page_header() will depend on
the trace_buffer structure, it is moved after the structure definition.

Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-2-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185627.723857541@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 60 +++++++++++++++++++-------------------
 1 file changed, 30 insertions(+), 30 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f7dc74e45ebfa..2400c8e68fd33 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -379,36 +379,6 @@ static inline bool test_time_stamp(u64 delta)
 /* Max payload is BUF_PAGE_SIZE - header (8bytes) */
 #define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
 
-int ring_buffer_print_page_header(struct trace_seq *s)
-{
-	struct buffer_data_page field;
-
-	trace_seq_printf(s, "\tfield: u64 timestamp;\t"
-			 "offset:0;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)sizeof(field.time_stamp),
-			 (unsigned int)is_signed_type(u64));
-
-	trace_seq_printf(s, "\tfield: local_t commit;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), commit),
-			 (unsigned int)sizeof(field.commit),
-			 (unsigned int)is_signed_type(long));
-
-	trace_seq_printf(s, "\tfield: int overwrite;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), commit),
-			 1,
-			 (unsigned int)is_signed_type(long));
-
-	trace_seq_printf(s, "\tfield: char data;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), data),
-			 (unsigned int)BUF_PAGE_SIZE,
-			 (unsigned int)is_signed_type(char));
-
-	return !trace_seq_has_overflowed(s);
-}
-
 struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
@@ -556,6 +526,36 @@ struct ring_buffer_iter {
 	int				missed_events;
 };
 
+int ring_buffer_print_page_header(struct trace_seq *s)
+{
+	struct buffer_data_page field;
+
+	trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+			 "offset:0;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)sizeof(field.time_stamp),
+			 (unsigned int)is_signed_type(u64));
+
+	trace_seq_printf(s, "\tfield: local_t commit;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), commit),
+			 (unsigned int)sizeof(field.commit),
+			 (unsigned int)is_signed_type(long));
+
+	trace_seq_printf(s, "\tfield: int overwrite;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), commit),
+			 1,
+			 (unsigned int)is_signed_type(long));
+
+	trace_seq_printf(s, "\tfield: char data;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), data),
+			 (unsigned int)BUF_PAGE_SIZE,
+			 (unsigned int)is_signed_type(char));
+
+	return !trace_seq_has_overflowed(s);
+}
+
 static inline void rb_time_read(rb_time_t *t, u64 *ret)
 {
 	*ret = local64_read(&t->time);
-- 
GitLab


From 139f84002145d8624f0195fb090b3a7670744a13 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 19 Dec 2023 13:54:16 -0500
Subject: [PATCH 1647/4076] ring-buffer: Page size per ring buffer

Currently the size of one sub buffer page is global for all buffers and
it is hard coded to one system page. In order to introduce configurable
ring buffer sub page size, the internal logic should be refactored to
work with sub page size per ring buffer.

Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-3-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.009147038@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  2 +-
 kernel/trace/ring_buffer.c  | 68 +++++++++++++++++++++----------------
 kernel/trace/trace.c        |  2 +-
 kernel/trace/trace.h        |  1 +
 kernel/trace/trace_events.c | 59 ++++++++++++++++++++++++--------
 5 files changed, 86 insertions(+), 46 deletions(-)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b1b03b2c0f08e..ce46218ce46df 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -200,7 +200,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page,
 struct trace_seq;
 
 int ring_buffer_print_entry_header(struct trace_seq *s);
-int ring_buffer_print_page_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 2400c8e68fd33..d9f6565024004 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -374,11 +374,6 @@ static inline bool test_time_stamp(u64 delta)
 	return !!(delta & TS_DELTA_TEST);
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
-
-/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
-#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
-
 struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
@@ -510,6 +505,9 @@ struct trace_buffer {
 
 	struct rb_irq_work		irq_work;
 	bool				time_stamp_abs;
+
+	unsigned int			subbuf_size;
+	unsigned int			max_data_size;
 };
 
 struct ring_buffer_iter {
@@ -523,10 +521,11 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 	u64				page_stamp;
 	struct ring_buffer_event	*event;
+	size_t				event_size;
 	int				missed_events;
 };
 
-int ring_buffer_print_page_header(struct trace_seq *s)
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s)
 {
 	struct buffer_data_page field;
 
@@ -550,7 +549,7 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 	trace_seq_printf(s, "\tfield: char data;\t"
 			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
 			 (unsigned int)offsetof(typeof(field), data),
-			 (unsigned int)BUF_PAGE_SIZE,
+			 (unsigned int)buffer->subbuf_size,
 			 (unsigned int)is_signed_type(char));
 
 	return !trace_seq_has_overflowed(s);
@@ -1625,7 +1624,13 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
 		goto fail_free_buffer;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	/* Default buffer page size - one system page */
+	buffer->subbuf_size = PAGE_SIZE - BUF_PAGE_HDR_SIZE;
+
+	/* Max payload is buffer page size - header (8bytes) */
+	buffer->max_data_size = buffer->subbuf_size - (sizeof(u32) * 2);
+
+	nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
 	buffer->flags = flags;
 	buffer->clock = trace_clock_local;
 	buffer->reader_lock_key = key;
@@ -1944,7 +1949,7 @@ static void update_pages_handler(struct work_struct *work)
  * @size: the new size.
  * @cpu_id: the cpu buffer to resize
  *
- * Minimum size is 2 * BUF_PAGE_SIZE.
+ * Minimum size is 2 * buffer->subbuf_size.
  *
  * Returns 0 on success and < 0 on failure.
  */
@@ -1966,7 +1971,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 	    !cpumask_test_cpu(cpu_id, buffer->cpumask))
 		return 0;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
 
 	/* we need a minimum of two pages */
 	if (nr_pages < 2)
@@ -2213,7 +2218,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
 	 */
 	barrier();
 
-	if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
+	if ((iter->head + length) > commit || length > iter->event_size)
 		/* Writer corrupted the read? */
 		goto reset;
 
@@ -2446,6 +2451,7 @@ static inline void
 rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	      unsigned long tail, struct rb_event_info *info)
 {
+	unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
 	struct buffer_page *tail_page = info->tail_page;
 	struct ring_buffer_event *event;
 	unsigned long length = info->length;
@@ -2454,13 +2460,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * Only the event that crossed the page boundary
 	 * must fill the old tail_page with padding.
 	 */
-	if (tail >= BUF_PAGE_SIZE) {
+	if (tail >= bsize) {
 		/*
 		 * If the page was filled, then we still need
 		 * to update the real_end. Reset it to zero
 		 * and the reader will ignore it.
 		 */
-		if (tail == BUF_PAGE_SIZE)
+		if (tail == bsize)
 			tail_page->real_end = 0;
 
 		local_sub(length, &tail_page->write);
@@ -2488,7 +2494,7 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * If we are less than the minimum size, we don't need to
 	 * worry about it.
 	 */
-	if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
+	if (tail > (bsize - RB_EVNT_MIN_SIZE)) {
 		/* No room for any events */
 
 		/* Mark the rest of the page with padding */
@@ -2503,19 +2509,19 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	}
 
 	/* Put in a discarded event */
-	event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
+	event->array[0] = (bsize - tail) - RB_EVNT_HDR_SIZE;
 	event->type_len = RINGBUF_TYPE_PADDING;
 	/* time delta must be non zero */
 	event->time_delta = 1;
 
 	/* account for padding bytes */
-	local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+	local_add(bsize - tail, &cpu_buffer->entries_bytes);
 
 	/* Make sure the padding is visible before the tail_page->write update */
 	smp_wmb();
 
 	/* Set write to end of buffer */
-	length = (tail + length) - BUF_PAGE_SIZE;
+	length = (tail + length) - bsize;
 	local_sub(length, &tail_page->write);
 }
 
@@ -3469,7 +3475,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	tail = write - info->length;
 
 	/* See if we shot pass the end of this buffer page */
-	if (unlikely(write > BUF_PAGE_SIZE)) {
+	if (unlikely(write > cpu_buffer->buffer->subbuf_size)) {
 		check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
 		return rb_move_tail(cpu_buffer, tail, info);
 	}
@@ -3600,7 +3606,7 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
 		add_ts_default = RB_ADD_STAMP_ABSOLUTE;
 		info.length += RB_LEN_TIME_EXTEND;
-		if (info.length > BUF_MAX_DATA_SIZE)
+		if (info.length > cpu_buffer->buffer->max_data_size)
 			goto out_fail;
 	} else {
 		add_ts_default = RB_ADD_STAMP_NONE;
@@ -3675,7 +3681,7 @@ ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length)
 	if (unlikely(atomic_read(&cpu_buffer->record_disabled)))
 		goto out;
 
-	if (unlikely(length > BUF_MAX_DATA_SIZE))
+	if (unlikely(length > buffer->max_data_size))
 		goto out;
 
 	if (unlikely(trace_recursive_lock(cpu_buffer)))
@@ -3825,7 +3831,7 @@ int ring_buffer_write(struct trace_buffer *buffer,
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
 
-	if (length > BUF_MAX_DATA_SIZE)
+	if (length > buffer->max_data_size)
 		goto out;
 
 	if (unlikely(trace_recursive_lock(cpu_buffer)))
@@ -4405,6 +4411,7 @@ static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = NULL;
+	unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
 	unsigned long overwrite;
 	unsigned long flags;
 	int nr_loops = 0;
@@ -4540,7 +4547,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 #define USECS_WAIT	1000000
         for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
 		/* If the write is past the end of page, a writer is still updating it */
-		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+		if (likely(!reader || rb_page_write(reader) <= bsize))
 			break;
 
 		udelay(1);
@@ -4984,7 +4991,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
 		return NULL;
 
 	/* Holds the entire event: data and meta data */
-	iter->event = kmalloc(BUF_PAGE_SIZE, flags);
+	iter->event_size = buffer->subbuf_size;
+	iter->event = kmalloc(iter->event_size, flags);
 	if (!iter->event) {
 		kfree(iter);
 		return NULL;
@@ -5102,14 +5110,14 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 {
 	/*
 	 * Earlier, this method returned
-	 *	BUF_PAGE_SIZE * buffer->nr_pages
+	 *	buffer->subbuf_size * buffer->nr_pages
 	 * Since the nr_pages field is now removed, we have converted this to
 	 * return the per cpu buffer value.
 	 */
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
-	return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages;
+	return buffer->subbuf_size * buffer->buffers[cpu]->nr_pages;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
@@ -5123,8 +5131,8 @@ unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer)
 {
 	/* If abs timestamp is requested, events have a timestamp too */
 	if (ring_buffer_time_stamp_abs(buffer))
-		return BUF_MAX_DATA_SIZE - RB_LEN_TIME_EXTEND;
-	return BUF_MAX_DATA_SIZE;
+		return buffer->max_data_size - RB_LEN_TIME_EXTEND;
+	return buffer->max_data_size;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_max_event_size);
 
@@ -5730,7 +5738,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		/* If there is room at the end of the page to save the
 		 * missed events, then record it there.
 		 */
-		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+		if (buffer->subbuf_size - commit >= sizeof(missed_events)) {
 			memcpy(&bpage->data[commit], &missed_events,
 			       sizeof(missed_events));
 			local_add(RB_MISSED_STORED, &bpage->commit);
@@ -5742,8 +5750,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 	/*
 	 * This page may be off to user land. Zero it out here.
 	 */
-	if (commit < BUF_PAGE_SIZE)
-		memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
+	if (commit < buffer->subbuf_size)
+		memset(&bpage->data[commit], 0, buffer->subbuf_size - commit);
 
  out_unlock:
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 55dabee4c78b1..76dd0a4c8cb5e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5018,7 +5018,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int tracing_release_generic_tr(struct inode *inode, struct file *file)
+int tracing_release_generic_tr(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 79180aed13eee..00f873910c5d9 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -616,6 +616,7 @@ void tracing_reset_all_online_cpus(void);
 void tracing_reset_all_online_cpus_unlocked(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 int tracing_open_generic_tr(struct inode *inode, struct file *filp);
+int tracing_release_generic_tr(struct inode *inode, struct file *file);
 int tracing_open_file_tr(struct inode *inode, struct file *filp);
 int tracing_release_file_tr(struct inode *inode, struct file *filp);
 int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b70d038180384..7c364b87352ee 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1893,9 +1893,9 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 }
 
 static ssize_t
-show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+show_header_page_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 {
-	int (*func)(struct trace_seq *s) = filp->private_data;
+	struct trace_array *tr = filp->private_data;
 	struct trace_seq *s;
 	int r;
 
@@ -1908,7 +1908,31 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 
 	trace_seq_init(s);
 
-	func(s);
+	ring_buffer_print_page_header(tr->array_buffer.buffer, s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos,
+				    s->buffer, trace_seq_used(s));
+
+	kfree(s);
+
+	return r;
+}
+
+static ssize_t
+show_header_event_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	ring_buffer_print_entry_header(s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos,
 				    s->buffer, trace_seq_used(s));
 
@@ -2165,10 +2189,18 @@ static const struct file_operations ftrace_tr_enable_fops = {
 	.release = subsystem_release,
 };
 
-static const struct file_operations ftrace_show_header_fops = {
-	.open = tracing_open_generic,
-	.read = show_header,
+static const struct file_operations ftrace_show_header_page_fops = {
+	.open = tracing_open_generic_tr,
+	.read = show_header_page_file,
 	.llseek = default_llseek,
+	.release = tracing_release_generic_tr,
+};
+
+static const struct file_operations ftrace_show_header_event_fops = {
+	.open = tracing_open_generic_tr,
+	.read = show_header_event_file,
+	.llseek = default_llseek,
+	.release = tracing_release_generic_tr,
 };
 
 static int
@@ -3794,17 +3826,16 @@ static int events_callback(const char *name, umode_t *mode, void **data,
 		return 1;
 	}
 
-	if (strcmp(name, "header_page") == 0)
-		*data = ring_buffer_print_page_header;
-
-	else if (strcmp(name, "header_event") == 0)
-		*data = ring_buffer_print_entry_header;
+	if (strcmp(name, "header_page") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_show_header_page_fops;
 
-	else
+	} else if (strcmp(name, "header_event") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_show_header_event_fops;
+	} else
 		return 0;
 
-	*mode = TRACE_MODE_READ;
-	*fops = &ftrace_show_header_fops;
 	return 1;
 }
 
-- 
GitLab


From 2808e31ec12e5fbe2ae25acc027fcdc67b1fb7f0 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 19 Dec 2023 13:54:17 -0500
Subject: [PATCH 1648/4076] ring-buffer: Add interface for configuring trace
 sub buffer size

The trace ring buffer sub page size can be configured, per trace
instance. A new ftrace file "buffer_subbuf_order" is added to get and
set the size of the ring buffer sub page for current trace instance.
The size must be an order of system page size, that's why the new
interface works with system page order, instead of absolute page size:
0 means the ring buffer sub page is equal to 1 system page and so
forth:
0 - 1 system page
1 - 2 system pages
2 - 4 system pages
...
The ring buffer sub page size is limited between 1 and 128 system
pages. The default value is 1 system page.
New ring buffer APIs are introduced:
 ring_buffer_subbuf_order_set()
 ring_buffer_subbuf_order_get()
 ring_buffer_subbuf_size_get()

Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-4-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.298324722@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  4 ++
 kernel/trace/ring_buffer.c  | 73 +++++++++++++++++++++++++++++++++++++
 kernel/trace/trace.c        | 48 ++++++++++++++++++++++++
 3 files changed, 125 insertions(+)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index ce46218ce46df..12573306b8892 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -202,6 +202,10 @@ struct trace_seq;
 int ring_buffer_print_entry_header(struct trace_seq *s);
 int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s);
 
+int ring_buffer_subbuf_order_get(struct trace_buffer *buffer);
+int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order);
+int ring_buffer_subbuf_size_get(struct trace_buffer *buffer);
+
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
 };
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d9f6565024004..20fc0121735d3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -507,6 +507,7 @@ struct trace_buffer {
 	bool				time_stamp_abs;
 
 	unsigned int			subbuf_size;
+	unsigned int			subbuf_order;
 	unsigned int			max_data_size;
 };
 
@@ -5761,6 +5762,78 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
+/**
+ * ring_buffer_subbuf_size_get - get size of the sub buffer.
+ * @buffer: the buffer to get the sub buffer size from
+ *
+ * Returns size of the sub buffer, in bytes.
+ */
+int ring_buffer_subbuf_size_get(struct trace_buffer *buffer)
+{
+	return buffer->subbuf_size + BUF_PAGE_HDR_SIZE;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_size_get);
+
+/**
+ * ring_buffer_subbuf_order_get - get order of system sub pages in one buffer page.
+ * @buffer: The ring_buffer to get the system sub page order from
+ *
+ * By default, one ring buffer sub page equals to one system page. This parameter
+ * is configurable, per ring buffer. The size of the ring buffer sub page can be
+ * extended, but must be an order of system page size.
+ *
+ * Returns the order of buffer sub page size, in system pages:
+ * 0 means the sub buffer size is 1 system page and so forth.
+ * In case of an error < 0 is returned.
+ */
+int ring_buffer_subbuf_order_get(struct trace_buffer *buffer)
+{
+	if (!buffer)
+		return -EINVAL;
+
+	return buffer->subbuf_order;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_get);
+
+/**
+ * ring_buffer_subbuf_order_set - set the size of ring buffer sub page.
+ * @buffer: The ring_buffer to set the new page size.
+ * @order: Order of the system pages in one sub buffer page
+ *
+ * By default, one ring buffer pages equals to one system page. This API can be
+ * used to set new size of the ring buffer page. The size must be order of
+ * system page size, that's why the input parameter @order is the order of
+ * system pages that are allocated for one ring buffer page:
+ *  0 - 1 system page
+ *  1 - 2 system pages
+ *  3 - 4 system pages
+ *  ...
+ *
+ * Returns 0 on success or < 0 in case of an error.
+ */
+int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
+{
+	int psize;
+
+	if (!buffer || order < 0)
+		return -EINVAL;
+
+	if (buffer->subbuf_order == order)
+		return 0;
+
+	psize = (1 << order) * PAGE_SIZE;
+	if (psize <= BUF_PAGE_HDR_SIZE)
+		return -EINVAL;
+
+	buffer->subbuf_order = order;
+	buffer->subbuf_size = psize - BUF_PAGE_HDR_SIZE;
+
+	/* Todo: reset the buffer with the new page size */
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set);
+
 /*
  * We only allocate new buffers, never free them if the CPU goes down.
  * If we were to free the buffer, then the user would lose any trace that was in
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 76dd0a4c8cb5e..a010aba4c4a43 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9358,6 +9358,51 @@ static const struct file_operations buffer_percent_fops = {
 	.llseek		= default_llseek,
 };
 
+static ssize_t
+buffer_order_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	char buf[64];
+	int r;
+
+	r = sprintf(buf, "%d\n", ring_buffer_subbuf_order_get(tr->array_buffer.buffer));
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+buffer_order_write(struct file *filp, const char __user *ubuf,
+		   size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	/* limit between 1 and 128 system pages */
+	if (val < 0 || val > 7)
+		return -EINVAL;
+
+	ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, val);
+	if (ret)
+		return ret;
+
+	(*ppos)++;
+
+	return cnt;
+}
+
+static const struct file_operations buffer_order_fops = {
+	.open		= tracing_open_generic_tr,
+	.read		= buffer_order_read,
+	.write		= buffer_order_write,
+	.release	= tracing_release_generic_tr,
+	.llseek		= default_llseek,
+};
+
 static struct dentry *trace_instance_dir;
 
 static void
@@ -9824,6 +9869,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer,
 			tr, &buffer_percent_fops);
 
+	trace_create_file("buffer_subbuf_order", TRACE_MODE_WRITE, d_tracer,
+			  tr, &buffer_order_fops);
+
 	create_trace_options_dir(tr);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-- 
GitLab


From f9b94daa542a8d2532f0930f01cd9aec2d19621b Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 19 Dec 2023 13:54:18 -0500
Subject: [PATCH 1649/4076] ring-buffer: Set new size of the ring buffer sub
 page

There are two approaches when changing the size of the ring buffer
sub page:
 1. Destroying all pages and allocating new pages with the new size.
 2. Allocating new pages, copying the content of the old pages before
    destroying them.
The first approach is easier, it is selected in the proposed
implementation. Changing the ring buffer sub page size is supposed to
not happen frequently. Usually, that size should be set only once,
when the buffer is not in use yet and is supposed to be empty.

Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-5-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.588995543@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 80 ++++++++++++++++++++++++++++++++++----
 1 file changed, 73 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 20fc0121735d3..b928bd03dd0eb 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -332,6 +332,7 @@ struct buffer_page {
 	unsigned	 read;		/* index for next read */
 	local_t		 entries;	/* entries on this page */
 	unsigned long	 real_end;	/* real end of data */
+	unsigned	 order;		/* order of the page */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -362,7 +363,7 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
 
 static void free_buffer_page(struct buffer_page *bpage)
 {
-	free_page((unsigned long)bpage->page);
+	free_pages((unsigned long)bpage->page, bpage->order);
 	kfree(bpage);
 }
 
@@ -1460,10 +1461,12 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 		list_add(&bpage->list, pages);
 
-		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, 0);
+		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags,
+					cpu_buffer->buffer->subbuf_order);
 		if (!page)
 			goto free_pages;
 		bpage->page = page_address(page);
+		bpage->order = cpu_buffer->buffer->subbuf_order;
 		rb_init_page(bpage->page);
 
 		if (user_thread && fatal_signal_pending(current))
@@ -1542,7 +1545,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 	rb_check_bpage(cpu_buffer, bpage);
 
 	cpu_buffer->reader_page = bpage;
-	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0);
+
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order);
 	if (!page)
 		goto fail_free_reader;
 	bpage->page = page_address(page);
@@ -1626,6 +1630,7 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 		goto fail_free_buffer;
 
 	/* Default buffer page size - one system page */
+	buffer->subbuf_order = 0;
 	buffer->subbuf_size = PAGE_SIZE - BUF_PAGE_HDR_SIZE;
 
 	/* Max payload is buffer page size - header (8bytes) */
@@ -5503,8 +5508,8 @@ void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
 	if (bpage)
 		goto out;
 
-	page = alloc_pages_node(cpu_to_node(cpu),
-				GFP_KERNEL | __GFP_NORETRY, 0);
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY,
+				cpu_buffer->buffer->subbuf_order);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -5553,7 +5558,7 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 	local_irq_restore(flags);
 
  out:
-	free_page((unsigned long)bpage);
+	free_pages((unsigned long)bpage, buffer->subbuf_order);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
 
@@ -5813,7 +5818,13 @@ EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_get);
  */
 int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 {
+	struct ring_buffer_per_cpu **cpu_buffers;
+	int old_order, old_size;
+	int nr_pages;
 	int psize;
+	int bsize;
+	int err;
+	int cpu;
 
 	if (!buffer || order < 0)
 		return -EINVAL;
@@ -5825,12 +5836,67 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	if (psize <= BUF_PAGE_HDR_SIZE)
 		return -EINVAL;
 
+	bsize = sizeof(void *) * buffer->cpus;
+	cpu_buffers = kzalloc(bsize, GFP_KERNEL);
+	if (!cpu_buffers)
+		return -ENOMEM;
+
+	old_order = buffer->subbuf_order;
+	old_size = buffer->subbuf_size;
+
+	/* prevent another thread from changing buffer sizes */
+	mutex_lock(&buffer->mutex);
+	atomic_inc(&buffer->record_disabled);
+
+	/* Make sure all commits have finished */
+	synchronize_rcu();
+
 	buffer->subbuf_order = order;
 	buffer->subbuf_size = psize - BUF_PAGE_HDR_SIZE;
 
-	/* Todo: reset the buffer with the new page size */
+	/* Make sure all new buffers are allocated, before deleting the old ones */
+	for_each_buffer_cpu(buffer, cpu) {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			continue;
+
+		nr_pages = buffer->buffers[cpu]->nr_pages;
+		cpu_buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
+		if (!cpu_buffers[cpu]) {
+			err = -ENOMEM;
+			goto error;
+		}
+	}
+
+	for_each_buffer_cpu(buffer, cpu) {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			continue;
+
+		rb_free_cpu_buffer(buffer->buffers[cpu]);
+		buffer->buffers[cpu] = cpu_buffers[cpu];
+	}
+
+	atomic_dec(&buffer->record_disabled);
+	mutex_unlock(&buffer->mutex);
+
+	kfree(cpu_buffers);
 
 	return 0;
+
+error:
+	buffer->subbuf_order = old_order;
+	buffer->subbuf_size = old_size;
+
+	atomic_dec(&buffer->record_disabled);
+	mutex_unlock(&buffer->mutex);
+
+	for_each_buffer_cpu(buffer, cpu) {
+		if (!cpu_buffers[cpu])
+			continue;
+		kfree(cpu_buffers[cpu]);
+	}
+	kfree(cpu_buffers);
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set);
 
-- 
GitLab


From bce761d757452ba5eb77e11fecc37a04b67494e7 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 19 Dec 2023 13:54:19 -0500
Subject: [PATCH 1650/4076] ring-buffer: Read and write to ring buffers with
 custom sub buffer size

As the size of the ring sub buffer page can be changed dynamically,
the logic that reads and writes to the buffer should be fixed to take
that into account. Some internal ring buffer APIs are changed:
 ring_buffer_alloc_read_page()
 ring_buffer_free_read_page()
 ring_buffer_read_page()
A new API is introduced:
 ring_buffer_read_page_data()

Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-6-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.875145995@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
[ Fixed kerneldoc on data_page parameter in ring_buffer_free_read_page() ]
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h          | 11 ++--
 kernel/trace/ring_buffer.c           | 75 ++++++++++++++++++++--------
 kernel/trace/ring_buffer_benchmark.c | 10 ++--
 kernel/trace/trace.c                 | 34 +++++++------
 4 files changed, 89 insertions(+), 41 deletions(-)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 12573306b8892..fa802db216f94 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -192,10 +192,15 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer);
 size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu);
 size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu);
 
-void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu);
-void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data);
-int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page,
+struct buffer_data_read_page;
+struct buffer_data_read_page *
+ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu);
+void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu,
+				struct buffer_data_read_page *page);
+int ring_buffer_read_page(struct trace_buffer *buffer,
+			  struct buffer_data_read_page *data_page,
 			  size_t len, int cpu, int full);
+void *ring_buffer_read_page_data(struct buffer_data_read_page *page);
 
 struct trace_seq;
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b928bd03dd0eb..c2afcf98ea912 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -318,6 +318,11 @@ struct buffer_data_page {
 	unsigned char	 data[] RB_ALIGN_DATA;	/* data of buffer page */
 };
 
+struct buffer_data_read_page {
+	unsigned		order;	/* order of the page */
+	struct buffer_data_page	*data;	/* actual data, stored in this page */
+};
+
 /*
  * Note, the buffer_page list must be first. The buffer pages
  * are allocated in cache lines, which means that each buffer
@@ -5483,40 +5488,48 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * Returns:
  *  The page allocated, or ERR_PTR
  */
-void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
+struct buffer_data_read_page *
+ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct buffer_data_page *bpage = NULL;
+	struct buffer_data_read_page *bpage = NULL;
 	unsigned long flags;
 	struct page *page;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return ERR_PTR(-ENODEV);
 
+	bpage = kzalloc(sizeof(*bpage), GFP_KERNEL);
+	if (!bpage)
+		return ERR_PTR(-ENOMEM);
+
+	bpage->order = buffer->subbuf_order;
 	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
 	if (cpu_buffer->free_page) {
-		bpage = cpu_buffer->free_page;
+		bpage->data = cpu_buffer->free_page;
 		cpu_buffer->free_page = NULL;
 	}
 
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
-	if (bpage)
+	if (bpage->data)
 		goto out;
 
 	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY,
 				cpu_buffer->buffer->subbuf_order);
-	if (!page)
+	if (!page) {
+		kfree(bpage);
 		return ERR_PTR(-ENOMEM);
+	}
 
-	bpage = page_address(page);
+	bpage->data = page_address(page);
 
  out:
-	rb_init_page(bpage);
+	rb_init_page(bpage->data);
 
 	return bpage;
 }
@@ -5526,14 +5539,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
  * ring_buffer_free_read_page - free an allocated read page
  * @buffer: the buffer the page was allocate for
  * @cpu: the cpu buffer the page came from
- * @data: the page to free
+ * @data_page: the page to free
  *
  * Free a page allocated from ring_buffer_alloc_read_page.
  */
-void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data)
+void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu,
+				struct buffer_data_read_page *data_page)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct buffer_data_page *bpage = data;
+	struct buffer_data_page *bpage = data_page->data;
 	struct page *page = virt_to_page(bpage);
 	unsigned long flags;
 
@@ -5542,8 +5556,12 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	/* If the page is still in use someplace else, we can't reuse it */
-	if (page_ref_count(page) > 1)
+	/*
+	 * If the page is still in use someplace else, or order of the page
+	 * is different from the subbuffer order of the buffer -
+	 * we can't reuse it
+	 */
+	if (page_ref_count(page) > 1 || data_page->order != buffer->subbuf_order)
 		goto out;
 
 	local_irq_save(flags);
@@ -5558,7 +5576,8 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 	local_irq_restore(flags);
 
  out:
-	free_pages((unsigned long)bpage, buffer->subbuf_order);
+	free_pages((unsigned long)bpage, data_page->order);
+	kfree(data_page);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
 
@@ -5579,9 +5598,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
  *	if (IS_ERR(rpage))
  *		return PTR_ERR(rpage);
- *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
+ *	ret = ring_buffer_read_page(buffer, rpage, len, cpu, 0);
  *	if (ret >= 0)
- *		process_page(rpage, ret);
+ *		process_page(ring_buffer_read_page_data(rpage), ret);
+ *	ring_buffer_free_read_page(buffer, cpu, rpage);
  *
  * When @full is set, the function will not return true unless
  * the writer is off the reader page.
@@ -5596,7 +5616,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *  <0 if no data has been transferred.
  */
 int ring_buffer_read_page(struct trace_buffer *buffer,
-			  void **data_page, size_t len, int cpu, int full)
+			  struct buffer_data_read_page *data_page,
+			  size_t len, int cpu, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
@@ -5621,10 +5642,12 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 
 	len -= BUF_PAGE_HDR_SIZE;
 
-	if (!data_page)
+	if (!data_page || !data_page->data)
+		goto out;
+	if (data_page->order != buffer->subbuf_order)
 		goto out;
 
-	bpage = *data_page;
+	bpage = data_page->data;
 	if (!bpage)
 		goto out;
 
@@ -5718,11 +5741,11 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		/* swap the pages */
 		rb_init_page(bpage);
 		bpage = reader->page;
-		reader->page = *data_page;
+		reader->page = data_page->data;
 		local_set(&reader->write, 0);
 		local_set(&reader->entries, 0);
 		reader->read = 0;
-		*data_page = bpage;
+		data_page->data = bpage;
 
 		/*
 		 * Use the real_end for the data size,
@@ -5767,6 +5790,18 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
+/**
+ * ring_buffer_read_page_data - get pointer to the data in the page.
+ * @page:  the page to get the data from
+ *
+ * Returns pointer to the actual data in this page.
+ */
+void *ring_buffer_read_page_data(struct buffer_data_read_page *page)
+{
+	return page->data;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_page_data);
+
 /**
  * ring_buffer_subbuf_size_get - get size of the sub buffer.
  * @buffer: the buffer to get the sub buffer size from
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index aef34673d79d0..008187ebd7fe6 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -104,10 +104,11 @@ static enum event_status read_event(int cpu)
 
 static enum event_status read_page(int cpu)
 {
+	struct buffer_data_read_page *bpage;
 	struct ring_buffer_event *event;
 	struct rb_page *rpage;
 	unsigned long commit;
-	void *bpage;
+	int page_size;
 	int *entry;
 	int ret;
 	int inc;
@@ -117,14 +118,15 @@ static enum event_status read_page(int cpu)
 	if (IS_ERR(bpage))
 		return EVENT_DROPPED;
 
-	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+	page_size = ring_buffer_subbuf_size_get(buffer);
+	ret = ring_buffer_read_page(buffer, bpage, page_size, cpu, 1);
 	if (ret >= 0) {
-		rpage = bpage;
+		rpage = ring_buffer_read_page_data(bpage);
 		/* The commit may have missed event flags set, clear them */
 		commit = local_read(&rpage->commit) & 0xfffff;
 		for (i = 0; i < commit && !test_error ; i += inc) {
 
-			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+			if (i >= (page_size - offsetof(struct rb_page, data))) {
 				TEST_ERROR();
 				break;
 			}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a010aba4c4a43..711095aa731d3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8286,6 +8286,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 {
 	struct ftrace_buffer_info *info = filp->private_data;
 	struct trace_iterator *iter = &info->iter;
+	void *trace_data;
+	int page_size;
 	ssize_t ret = 0;
 	ssize_t size;
 
@@ -8297,6 +8299,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		return -EBUSY;
 #endif
 
+	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
+
 	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer,
 							  iter->cpu_file);
@@ -8311,13 +8315,13 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		return ret;
 
 	/* Do we have previous read data to read? */
-	if (info->read < PAGE_SIZE)
+	if (info->read < page_size)
 		goto read;
 
  again:
 	trace_access_lock(iter->cpu_file);
 	ret = ring_buffer_read_page(iter->array_buffer->buffer,
-				    &info->spare,
+				    info->spare,
 				    count,
 				    iter->cpu_file, 0);
 	trace_access_unlock(iter->cpu_file);
@@ -8338,11 +8342,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	info->read = 0;
  read:
-	size = PAGE_SIZE - info->read;
+	size = page_size - info->read;
 	if (size > count)
 		size = count;
-
-	ret = copy_to_user(ubuf, info->spare + info->read, size);
+	trace_data = ring_buffer_read_page_data(info->spare);
+	ret = copy_to_user(ubuf, trace_data + info->read, size);
 	if (ret == size)
 		return -EFAULT;
 
@@ -8453,6 +8457,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
+	int page_size;
 	int entries, i;
 	ssize_t ret = 0;
 
@@ -8461,13 +8466,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		return -EBUSY;
 #endif
 
-	if (*ppos & (PAGE_SIZE - 1))
+	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
+	if (*ppos & (page_size - 1))
 		return -EINVAL;
 
-	if (len & (PAGE_SIZE - 1)) {
-		if (len < PAGE_SIZE)
+	if (len & (page_size - 1)) {
+		if (len < page_size)
 			return -EINVAL;
-		len &= PAGE_MASK;
+		len &= (~(page_size - 1));
 	}
 
 	if (splice_grow_spd(pipe, &spd))
@@ -8477,7 +8483,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file);
 
-	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) {
+	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) {
 		struct page *page;
 		int r;
 
@@ -8498,7 +8504,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		}
 		ref->cpu = iter->cpu_file;
 
-		r = ring_buffer_read_page(ref->buffer, &ref->page,
+		r = ring_buffer_read_page(ref->buffer, ref->page,
 					  len, iter->cpu_file, 1);
 		if (r < 0) {
 			ring_buffer_free_read_page(ref->buffer, ref->cpu,
@@ -8507,14 +8513,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		page = virt_to_page(ref->page);
+		page = virt_to_page(ring_buffer_read_page_data(ref->page));
 
 		spd.pages[i] = page;
-		spd.partial[i].len = PAGE_SIZE;
+		spd.partial[i].len = page_size;
 		spd.partial[i].offset = 0;
 		spd.partial[i].private = (unsigned long)ref;
 		spd.nr_pages++;
-		*ppos += PAGE_SIZE;
+		*ppos += page_size;
 
 		entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file);
 	}
-- 
GitLab


From f3e25e68ceb2abaeefcac8f930c940c4494705d0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 14 Nov 2023 12:20:11 +0100
Subject: [PATCH 1651/4076] pwm: Drop unused member "pwm" from struct
 pwm_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This member is only assigned to and never read. So drop it.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c  | 1 -
 include/linux/pwm.h | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 29078486534d4..24bb796d15f62 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -265,7 +265,6 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 		pwm = &chip->pwms[i];
 
 		pwm->chip = chip;
-		pwm->pwm = chip->base + i;
 		pwm->hwpwm = i;
 	}
 
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index cda3597b84f2c..8cadf9ee8d265 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -79,7 +79,6 @@ struct pwm_device {
 	const char *label;
 	unsigned long flags;
 	unsigned int hwpwm;
-	unsigned int pwm;
 	struct pwm_chip *chip;
 
 	struct pwm_args args;
-- 
GitLab


From 54c86dd20bba23109e32e4e2f94ff93dd9863bc3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 14 Nov 2023 12:20:12 +0100
Subject: [PATCH 1652/4076] pwm: Replace PWM chip unique base by unique ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Traditionally each PWM device had a unique ID stored in the "pwm" member
of struct pwm_device. However this number was hardly used and dropped
in the previous commit. To identify a certain PWM you're supposed to use
the chip's ID and the hwpwm of the PWM device now.

With the PWM chip base gone PWM chips can get their IDs better and
simpler using an idr.

This is expected to change the numbering of PWM chips, but nothing
should rely on the numbering anyhow.

Other than that the side effects are:

 - The PWM chip IDs are smaller and in most cases consecutive.
 - The ordering in /sys/kernel/debug/pwm is ordered by ascending PWM
   chip ID.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c  | 67 +++++++++++++++++----------------------------
 drivers/pwm/sysfs.c |  2 +-
 include/linux/pwm.h |  3 +-
 3 files changed, 27 insertions(+), 45 deletions(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 24bb796d15f62..ebe404dfdf5ba 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -8,6 +8,7 @@
 
 #include <linux/acpi.h>
 #include <linux/module.h>
+#include <linux/idr.h>
 #include <linux/of.h>
 #include <linux/pwm.h>
 #include <linux/list.h>
@@ -23,52 +24,25 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/pwm.h>
 
-#define MAX_PWMS 1024
-
 static DEFINE_MUTEX(pwm_lookup_lock);
 static LIST_HEAD(pwm_lookup_list);
 
-/* protects access to pwm_chips and allocated_pwms */
+/* protects access to pwm_chips */
 static DEFINE_MUTEX(pwm_lock);
 
-static LIST_HEAD(pwm_chips);
-static DECLARE_BITMAP(allocated_pwms, MAX_PWMS);
-
-/* Called with pwm_lock held */
-static int alloc_pwms(unsigned int count)
-{
-	unsigned int start;
-
-	start = bitmap_find_next_zero_area(allocated_pwms, MAX_PWMS, 0,
-					   count, 0);
-
-	if (start + count > MAX_PWMS)
-		return -ENOSPC;
-
-	bitmap_set(allocated_pwms, start, count);
-
-	return start;
-}
-
-/* Called with pwm_lock held */
-static void free_pwms(struct pwm_chip *chip)
-{
-	bitmap_clear(allocated_pwms, chip->base, chip->npwm);
-
-	kfree(chip->pwms);
-	chip->pwms = NULL;
-}
+static DEFINE_IDR(pwm_chips);
 
 static struct pwm_chip *pwmchip_find_by_name(const char *name)
 {
 	struct pwm_chip *chip;
+	unsigned long id, tmp;
 
 	if (!name)
 		return NULL;
 
 	mutex_lock(&pwm_lock);
 
-	list_for_each_entry(chip, &pwm_chips, list) {
+	idr_for_each_entry_ul(&pwm_chips, chip, tmp, id) {
 		const char *chip_name = dev_name(chip->dev);
 
 		if (chip_name && strcmp(chip_name, name) == 0) {
@@ -252,14 +226,14 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 
 	mutex_lock(&pwm_lock);
 
-	ret = alloc_pwms(chip->npwm);
+	ret = idr_alloc(&pwm_chips, chip, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
 		mutex_unlock(&pwm_lock);
 		kfree(chip->pwms);
 		return ret;
 	}
 
-	chip->base = ret;
+	chip->id = ret;
 
 	for (i = 0; i < chip->npwm; i++) {
 		pwm = &chip->pwms[i];
@@ -268,8 +242,6 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 		pwm->hwpwm = i;
 	}
 
-	list_add(&chip->list, &pwm_chips);
-
 	mutex_unlock(&pwm_lock);
 
 	if (IS_ENABLED(CONFIG_OF))
@@ -296,11 +268,11 @@ void pwmchip_remove(struct pwm_chip *chip)
 
 	mutex_lock(&pwm_lock);
 
-	list_del_init(&chip->list);
-
-	free_pwms(chip);
+	idr_remove(&pwm_chips, chip->id);
 
 	mutex_unlock(&pwm_lock);
+
+	kfree(chip->pwms);
 }
 EXPORT_SYMBOL_GPL(pwmchip_remove);
 
@@ -596,10 +568,11 @@ EXPORT_SYMBOL_GPL(pwm_adjust_config);
 static struct pwm_chip *fwnode_to_pwmchip(struct fwnode_handle *fwnode)
 {
 	struct pwm_chip *chip;
+	unsigned long id, tmp;
 
 	mutex_lock(&pwm_lock);
 
-	list_for_each_entry(chip, &pwm_chips, list)
+	idr_for_each_entry_ul(&pwm_chips, chip, tmp, id)
 		if (chip->dev && device_match_fwnode(chip->dev, fwnode)) {
 			mutex_unlock(&pwm_lock);
 			return chip;
@@ -1057,17 +1030,27 @@ static void pwm_dbg_show(struct pwm_chip *chip, struct seq_file *s)
 
 static void *pwm_seq_start(struct seq_file *s, loff_t *pos)
 {
+	unsigned long id = *pos;
+	void *ret;
+
 	mutex_lock(&pwm_lock);
 	s->private = "";
 
-	return seq_list_start(&pwm_chips, *pos);
+	ret = idr_get_next_ul(&pwm_chips, &id);
+	*pos = id;
+	return ret;
 }
 
 static void *pwm_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
+	unsigned long id = *pos + 1;
+	void *ret;
+
 	s->private = "\n";
 
-	return seq_list_next(v, &pwm_chips, pos);
+	ret = idr_get_next_ul(&pwm_chips, &id);
+	*pos = id;
+	return ret;
 }
 
 static void pwm_seq_stop(struct seq_file *s, void *v)
@@ -1077,7 +1060,7 @@ static void pwm_seq_stop(struct seq_file *s, void *v)
 
 static int pwm_seq_show(struct seq_file *s, void *v)
 {
-	struct pwm_chip *chip = list_entry(v, struct pwm_chip, list);
+	struct pwm_chip *chip = v;
 
 	seq_printf(s, "%s%s/%s, %d PWM device%s\n", (char *)s->private,
 		   chip->dev->bus ? chip->dev->bus->name : "no-bus",
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index 8d1254761e4dd..4edb994fa2e12 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -510,7 +510,7 @@ void pwmchip_sysfs_export(struct pwm_chip *chip)
 	 * the kernel it's just not exported.
 	 */
 	parent = device_create(&pwm_class, chip->dev, MKDEV(0, 0), chip,
-			       "pwmchip%d", chip->base);
+			       "pwmchip%d", chip->id);
 	if (IS_ERR(parent)) {
 		dev_warn(chip->dev,
 			 "device_create failed for pwm_chip sysfs export\n");
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 8cadf9ee8d265..c27a4bb76012e 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -292,7 +292,7 @@ struct pwm_chip {
 	struct device *dev;
 	const struct pwm_ops *ops;
 	struct module *owner;
-	int base;
+	unsigned int id;
 	unsigned int npwm;
 
 	struct pwm_device * (*of_xlate)(struct pwm_chip *chip,
@@ -300,7 +300,6 @@ struct pwm_chip {
 	unsigned int of_pwm_n_cells;
 
 	/* only used internally by the PWM framework */
-	struct list_head list;
 	struct pwm_device *pwms;
 };
 
-- 
GitLab


From 0360a48733729f9329483409acd048d04b43ee17 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 14 Nov 2023 12:20:13 +0100
Subject: [PATCH 1653/4076] pwm: Mention PWM chip ID in /sys/kernel/debug/pwm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While it's not hard to match the entries from /sys/kernel/debug/pwm to
the corresponding pwmchip in /sys/class/pwm, it's a bit simpler to have
the number mentioned in /sys/kernel/debug/pwm.

Link: https://lore.kernel.org/r/20230808165250.942396-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index ebe404dfdf5ba..fb36b3d559a72 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -1062,7 +1062,8 @@ static int pwm_seq_show(struct seq_file *s, void *v)
 {
 	struct pwm_chip *chip = v;
 
-	seq_printf(s, "%s%s/%s, %d PWM device%s\n", (char *)s->private,
+	seq_printf(s, "%s%d: %s/%s, %d PWM device%s\n",
+		   (char *)s->private, chip->id,
 		   chip->dev->bus ? chip->dev->bus->name : "no-bus",
 		   dev_name(chip->dev), chip->npwm,
 		   (chip->npwm != 1) ? "s" : "");
-- 
GitLab


From 6c4406ce609fb5857d52c1e42a40cb5e7e8ee94a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 16 Nov 2023 11:52:13 +0100
Subject: [PATCH 1654/4076] pwm: cros-ec: Drop unused member from driver
 private data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

.dev is unused since the driver was introduced in commit 1f0d3bb02785
("pwm: Add ChromeOS EC PWM driver"). Drop it.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-cros-ec.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c
index 4fbd23e4ef693..9a8f1b6a4e136 100644
--- a/drivers/pwm/pwm-cros-ec.c
+++ b/drivers/pwm/pwm-cros-ec.c
@@ -25,7 +25,6 @@
  * @channel: array with per-channel data
  */
 struct cros_ec_pwm_device {
-	struct device *dev;
 	struct cros_ec_device *ec;
 	struct pwm_chip chip;
 	bool use_pwm_type;
-- 
GitLab


From ded38f874eff2bb6fc46a0377aa8dcdcf4b43a2e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:18 +0200
Subject: [PATCH 1655/4076] pwm: atmel-hlcdc: Use DEFINE_SIMPLE_DEV_PM_OPS for
 PM functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
#ifdef can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel-hlcdc.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c
index 07920e0347575..3f2c5031a3ba8 100644
--- a/drivers/pwm/pwm-atmel-hlcdc.c
+++ b/drivers/pwm/pwm-atmel-hlcdc.c
@@ -180,7 +180,6 @@ static const struct atmel_hlcdc_pwm_errata atmel_hlcdc_pwm_sama5d3_errata = {
 	.div1_clk_erratum = true,
 };
 
-#ifdef CONFIG_PM_SLEEP
 static int atmel_hlcdc_pwm_suspend(struct device *dev)
 {
 	struct atmel_hlcdc_pwm *atmel = dev_get_drvdata(dev);
@@ -210,10 +209,9 @@ static int atmel_hlcdc_pwm_resume(struct device *dev)
 	return atmel_hlcdc_pwm_apply(&atmel->chip, &atmel->chip.pwms[0],
 				     &state);
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(atmel_hlcdc_pwm_pm_ops,
-			 atmel_hlcdc_pwm_suspend, atmel_hlcdc_pwm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(atmel_hlcdc_pwm_pm_ops,
+				atmel_hlcdc_pwm_suspend, atmel_hlcdc_pwm_resume);
 
 static const struct of_device_id atmel_hlcdc_dt_ids[] = {
 	{
@@ -297,7 +295,7 @@ static struct platform_driver atmel_hlcdc_pwm_driver = {
 	.driver = {
 		.name = "atmel-hlcdc-pwm",
 		.of_match_table = atmel_hlcdc_pwm_dt_ids,
-		.pm = &atmel_hlcdc_pwm_pm_ops,
+		.pm = pm_ptr(&atmel_hlcdc_pwm_pm_ops),
 	},
 	.probe = atmel_hlcdc_pwm_probe,
 	.remove_new = atmel_hlcdc_pwm_remove,
-- 
GitLab


From a7bab37f87c2a551ce12aefc30648a206550cd78 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:19 +0200
Subject: [PATCH 1656/4076] pwm: atmel-tcb: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
#ifdef can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-atmel-tcb.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index 98b33c016c3c7..d42c897cb85e5 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -489,7 +489,6 @@ static const struct of_device_id atmel_tcb_pwm_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, atmel_tcb_pwm_dt_ids);
 
-#ifdef CONFIG_PM_SLEEP
 static int atmel_tcb_pwm_suspend(struct device *dev)
 {
 	struct atmel_tcb_pwm_chip *tcbpwm = dev_get_drvdata(dev);
@@ -522,16 +521,15 @@ static int atmel_tcb_pwm_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(atmel_tcb_pwm_pm_ops, atmel_tcb_pwm_suspend,
-			 atmel_tcb_pwm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(atmel_tcb_pwm_pm_ops, atmel_tcb_pwm_suspend,
+				atmel_tcb_pwm_resume);
 
 static struct platform_driver atmel_tcb_pwm_driver = {
 	.driver = {
 		.name = "atmel-tcb-pwm",
 		.of_match_table = atmel_tcb_pwm_dt_ids,
-		.pm = &atmel_tcb_pwm_pm_ops,
+		.pm = pm_ptr(&atmel_tcb_pwm_pm_ops),
 	},
 	.probe = atmel_tcb_pwm_probe,
 	.remove_new = atmel_tcb_pwm_remove,
-- 
GitLab


From fac37751c46836fa5dc9e1f958ae160e75cd24f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:20 +0200
Subject: [PATCH 1657/4076] pwm: berlin: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
#ifdef can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-berlin.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-berlin.c b/drivers/pwm/pwm-berlin.c
index ba2d799917695..442913232dc01 100644
--- a/drivers/pwm/pwm-berlin.c
+++ b/drivers/pwm/pwm-berlin.c
@@ -226,7 +226,6 @@ static int berlin_pwm_probe(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int berlin_pwm_suspend(struct device *dev)
 {
 	struct berlin_pwm_chip *bpc = dev_get_drvdata(dev);
@@ -267,17 +266,16 @@ static int berlin_pwm_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(berlin_pwm_pm_ops, berlin_pwm_suspend,
-			 berlin_pwm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(berlin_pwm_pm_ops, berlin_pwm_suspend,
+				berlin_pwm_resume);
 
 static struct platform_driver berlin_pwm_driver = {
 	.probe = berlin_pwm_probe,
 	.driver = {
 		.name = "berlin-pwm",
 		.of_match_table = berlin_pwm_match,
-		.pm = &berlin_pwm_pm_ops,
+		.pm = pm_ptr(&berlin_pwm_pm_ops),
 	},
 };
 module_platform_driver(berlin_pwm_driver);
-- 
GitLab


From d6b81be1f5f991bdbeabc734db04cec7dd79426b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:21 +0200
Subject: [PATCH 1658/4076] pwm: brcmstb: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
#ifdef can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Acked-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-brcmstb.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-brcmstb.c b/drivers/pwm/pwm-brcmstb.c
index b723c2d4f485c..0fdeb0b2dbf37 100644
--- a/drivers/pwm/pwm-brcmstb.c
+++ b/drivers/pwm/pwm-brcmstb.c
@@ -259,7 +259,6 @@ static int brcmstb_pwm_probe(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int brcmstb_pwm_suspend(struct device *dev)
 {
 	struct brcmstb_pwm *p = dev_get_drvdata(dev);
@@ -275,17 +274,16 @@ static int brcmstb_pwm_resume(struct device *dev)
 
 	return clk_prepare_enable(p->clk);
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(brcmstb_pwm_pm_ops, brcmstb_pwm_suspend,
-			 brcmstb_pwm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(brcmstb_pwm_pm_ops, brcmstb_pwm_suspend,
+				brcmstb_pwm_resume);
 
 static struct platform_driver brcmstb_pwm_driver = {
 	.probe = brcmstb_pwm_probe,
 	.driver = {
 		.name = "pwm-brcmstb",
 		.of_match_table = brcmstb_pwm_of_match,
-		.pm = &brcmstb_pwm_pm_ops,
+		.pm = pm_ptr(&brcmstb_pwm_pm_ops),
 	},
 };
 module_platform_driver(brcmstb_pwm_driver);
-- 
GitLab


From 30b5b066fa839b7471ca1222713b055d93681a77 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:22 +0200
Subject: [PATCH 1659/4076] pwm: dwc: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
#ifdef can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-dwc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pwm/pwm-dwc.c b/drivers/pwm/pwm-dwc.c
index bd9cadb497d70..4929354f8cd95 100644
--- a/drivers/pwm/pwm-dwc.c
+++ b/drivers/pwm/pwm-dwc.c
@@ -71,7 +71,6 @@ static void dwc_pwm_remove(struct pci_dev *pci)
 	pm_runtime_get_noresume(&pci->dev);
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int dwc_pwm_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
@@ -106,9 +105,8 @@ static int dwc_pwm_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(dwc_pwm_pm_ops, dwc_pwm_suspend, dwc_pwm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(dwc_pwm_pm_ops, dwc_pwm_suspend, dwc_pwm_resume);
 
 static const struct pci_device_id dwc_pwm_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0x4bb7) }, /* Elkhart Lake */
@@ -122,7 +120,7 @@ static struct pci_driver dwc_pwm_driver = {
 	.remove = dwc_pwm_remove,
 	.id_table = dwc_pwm_id_table,
 	.driver = {
-		.pm = &dwc_pwm_pm_ops,
+		.pm = pm_ptr(&dwc_pwm_pm_ops),
 	},
 };
 
-- 
GitLab


From 9676b40e1885fca203ced4be49adfc3ca6ed6f16 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:23 +0200
Subject: [PATCH 1660/4076] pwm: imx-tpm: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
__maybe_unused can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-imx-tpm.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-imx-tpm.c b/drivers/pwm/pwm-imx-tpm.c
index dc6aafeb9f7b4..9fc290e647e1b 100644
--- a/drivers/pwm/pwm-imx-tpm.c
+++ b/drivers/pwm/pwm-imx-tpm.c
@@ -371,7 +371,7 @@ static int pwm_imx_tpm_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __maybe_unused pwm_imx_tpm_suspend(struct device *dev)
+static int pwm_imx_tpm_suspend(struct device *dev)
 {
 	struct imx_tpm_pwm_chip *tpm = dev_get_drvdata(dev);
 
@@ -390,7 +390,7 @@ static int __maybe_unused pwm_imx_tpm_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused pwm_imx_tpm_resume(struct device *dev)
+static int pwm_imx_tpm_resume(struct device *dev)
 {
 	struct imx_tpm_pwm_chip *tpm = dev_get_drvdata(dev);
 	int ret = 0;
@@ -402,8 +402,8 @@ static int __maybe_unused pwm_imx_tpm_resume(struct device *dev)
 	return ret;
 }
 
-static SIMPLE_DEV_PM_OPS(imx_tpm_pwm_pm,
-			 pwm_imx_tpm_suspend, pwm_imx_tpm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(imx_tpm_pwm_pm,
+				pwm_imx_tpm_suspend, pwm_imx_tpm_resume);
 
 static const struct of_device_id imx_tpm_pwm_dt_ids[] = {
 	{ .compatible = "fsl,imx7ulp-pwm", },
@@ -415,7 +415,7 @@ static struct platform_driver imx_tpm_pwm_driver = {
 	.driver = {
 		.name = "imx7ulp-tpm-pwm",
 		.of_match_table = imx_tpm_pwm_dt_ids,
-		.pm = &imx_tpm_pwm_pm,
+		.pm = pm_ptr(&imx_tpm_pwm_pm),
 	},
 	.probe	= pwm_imx_tpm_probe,
 };
-- 
GitLab


From e9ebab624d0a8322203cfbcc15510656b0a177d0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:24 +0200
Subject: [PATCH 1661/4076] pwm: samsung: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
#ifdef can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-samsung.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c
index 69d9f4577b347..6e77302f73687 100644
--- a/drivers/pwm/pwm-samsung.c
+++ b/drivers/pwm/pwm-samsung.c
@@ -620,7 +620,6 @@ static void pwm_samsung_remove(struct platform_device *pdev)
 	clk_disable_unprepare(our_chip->base_clk);
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int pwm_samsung_resume(struct device *dev)
 {
 	struct samsung_pwm_chip *our_chip = dev_get_drvdata(dev);
@@ -653,14 +652,13 @@ static int pwm_samsung_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(pwm_samsung_pm_ops, NULL, pwm_samsung_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(pwm_samsung_pm_ops, NULL, pwm_samsung_resume);
 
 static struct platform_driver pwm_samsung_driver = {
 	.driver		= {
 		.name	= "samsung-pwm",
-		.pm	= &pwm_samsung_pm_ops,
+		.pm	= pm_ptr(&pwm_samsung_pm_ops),
 		.of_match_table = of_match_ptr(samsung_pwm_matches),
 	},
 	.probe		= pwm_samsung_probe,
-- 
GitLab


From 39dfb60c724c59103412abe369d78b7243b31d35 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:25 +0200
Subject: [PATCH 1662/4076] pwm: stm32-lp: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
__maybe_unused can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32-lp.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c
index b67974cc18725..439068f3eca18 100644
--- a/drivers/pwm/pwm-stm32-lp.c
+++ b/drivers/pwm/pwm-stm32-lp.c
@@ -218,7 +218,7 @@ static int stm32_pwm_lp_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __maybe_unused stm32_pwm_lp_suspend(struct device *dev)
+static int stm32_pwm_lp_suspend(struct device *dev)
 {
 	struct stm32_pwm_lp *priv = dev_get_drvdata(dev);
 	struct pwm_state state;
@@ -233,13 +233,13 @@ static int __maybe_unused stm32_pwm_lp_suspend(struct device *dev)
 	return pinctrl_pm_select_sleep_state(dev);
 }
 
-static int __maybe_unused stm32_pwm_lp_resume(struct device *dev)
+static int stm32_pwm_lp_resume(struct device *dev)
 {
 	return pinctrl_pm_select_default_state(dev);
 }
 
-static SIMPLE_DEV_PM_OPS(stm32_pwm_lp_pm_ops, stm32_pwm_lp_suspend,
-			 stm32_pwm_lp_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(stm32_pwm_lp_pm_ops, stm32_pwm_lp_suspend,
+				stm32_pwm_lp_resume);
 
 static const struct of_device_id stm32_pwm_lp_of_match[] = {
 	{ .compatible = "st,stm32-pwm-lp", },
@@ -252,7 +252,7 @@ static struct platform_driver stm32_pwm_lp_driver = {
 	.driver	= {
 		.name = "stm32-pwm-lp",
 		.of_match_table = stm32_pwm_lp_of_match,
-		.pm = &stm32_pwm_lp_pm_ops,
+		.pm = pm_ptr(&stm32_pwm_lp_pm_ops),
 	},
 };
 module_platform_driver(stm32_pwm_lp_driver);
-- 
GitLab


From 3d67277607c755160531ebd6b756ffd7195de627 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:26 +0200
Subject: [PATCH 1663/4076] pwm: stm32: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
__maybe_unused can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 3303a754ea020..8be037757b8bd 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -645,7 +645,7 @@ static int stm32_pwm_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __maybe_unused stm32_pwm_suspend(struct device *dev)
+static int stm32_pwm_suspend(struct device *dev)
 {
 	struct stm32_pwm *priv = dev_get_drvdata(dev);
 	unsigned int i;
@@ -666,7 +666,7 @@ static int __maybe_unused stm32_pwm_suspend(struct device *dev)
 	return pinctrl_pm_select_sleep_state(dev);
 }
 
-static int __maybe_unused stm32_pwm_resume(struct device *dev)
+static int stm32_pwm_resume(struct device *dev)
 {
 	struct stm32_pwm *priv = dev_get_drvdata(dev);
 	int ret;
@@ -679,7 +679,7 @@ static int __maybe_unused stm32_pwm_resume(struct device *dev)
 	return stm32_pwm_apply_breakinputs(priv);
 }
 
-static SIMPLE_DEV_PM_OPS(stm32_pwm_pm_ops, stm32_pwm_suspend, stm32_pwm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(stm32_pwm_pm_ops, stm32_pwm_suspend, stm32_pwm_resume);
 
 static const struct of_device_id stm32_pwm_of_match[] = {
 	{ .compatible = "st,stm32-pwm",	},
@@ -692,7 +692,7 @@ static struct platform_driver stm32_pwm_driver = {
 	.driver	= {
 		.name = "stm32-pwm",
 		.of_match_table = stm32_pwm_of_match,
-		.pm = &stm32_pwm_pm_ops,
+		.pm = pm_ptr(&stm32_pwm_pm_ops),
 	},
 };
 module_platform_driver(stm32_pwm_driver);
-- 
GitLab


From 5d5a0aa5e261eaaea81de4f30c26d22323026714 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:27 +0200
Subject: [PATCH 1664/4076] pwm: tiecap: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
#ifdef can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-tiecap.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/pwm/pwm-tiecap.c b/drivers/pwm/pwm-tiecap.c
index 11e3549cf1034..d974f4414ac9a 100644
--- a/drivers/pwm/pwm-tiecap.c
+++ b/drivers/pwm/pwm-tiecap.c
@@ -269,7 +269,6 @@ static void ecap_pwm_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 }
 
-#ifdef CONFIG_PM_SLEEP
 static void ecap_pwm_save_context(struct ecap_pwm_chip *pc)
 {
 	pm_runtime_get_sync(pc->chip.dev);
@@ -312,15 +311,14 @@ static int ecap_pwm_resume(struct device *dev)
 	ecap_pwm_restore_context(pc);
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(ecap_pwm_pm_ops, ecap_pwm_suspend, ecap_pwm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(ecap_pwm_pm_ops, ecap_pwm_suspend, ecap_pwm_resume);
 
 static struct platform_driver ecap_pwm_driver = {
 	.driver = {
 		.name = "ecap",
 		.of_match_table = ecap_of_match,
-		.pm = &ecap_pwm_pm_ops,
+		.pm = pm_ptr(&ecap_pwm_pm_ops),
 	},
 	.probe = ecap_pwm_probe,
 	.remove_new = ecap_pwm_remove,
-- 
GitLab


From fb1b517fd87649add1e8acb813f4f8af5a28d4d9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Mon, 23 Oct 2023 19:46:28 +0200
Subject: [PATCH 1665/4076] pwm: tiehrpwm: Use DEFINE_SIMPLE_DEV_PM_OPS for PM
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This macro has the advantage over SIMPLE_DEV_PM_OPS that we don't have to
care about when the functions are actually used, so the corresponding
#ifdef can be dropped.

Also make use of pm_ptr() to discard all PM related stuff if CONFIG_PM
isn't enabled.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-tiehrpwm.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-tiehrpwm.c b/drivers/pwm/pwm-tiehrpwm.c
index 66ac2655845f7..af231fa74fa90 100644
--- a/drivers/pwm/pwm-tiehrpwm.c
+++ b/drivers/pwm/pwm-tiehrpwm.c
@@ -521,7 +521,6 @@ static void ehrpwm_pwm_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 }
 
-#ifdef CONFIG_PM_SLEEP
 static void ehrpwm_pwm_save_context(struct ehrpwm_pwm_chip *pc)
 {
 	pm_runtime_get_sync(pc->chip.dev);
@@ -589,16 +588,15 @@ static int ehrpwm_pwm_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(ehrpwm_pwm_pm_ops, ehrpwm_pwm_suspend,
-			 ehrpwm_pwm_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(ehrpwm_pwm_pm_ops, ehrpwm_pwm_suspend,
+				ehrpwm_pwm_resume);
 
 static struct platform_driver ehrpwm_pwm_driver = {
 	.driver = {
 		.name = "ehrpwm",
 		.of_match_table = ehrpwm_of_match,
-		.pm = &ehrpwm_pwm_pm_ops,
+		.pm = pm_ptr(&ehrpwm_pwm_pm_ops),
 	},
 	.probe = ehrpwm_pwm_probe,
 	.remove_new = ehrpwm_pwm_remove,
-- 
GitLab


From 1c9a2ad84f5a7450265a2ffcdb27715dbca2b980 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 09:33:23 +0100
Subject: [PATCH 1666/4076] pwm: jz4740: Add trailing \n to error messages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Error messages are supposed to end in \n. Add the line terminator to the
two error messages that lack this.

Suggested-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-jz4740.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c
index e9375de60ad62..73f96cef16621 100644
--- a/drivers/pwm/pwm-jz4740.c
+++ b/drivers/pwm/pwm-jz4740.c
@@ -149,7 +149,7 @@ static int jz4740_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 */
 	rate = clk_round_rate(clk, tmp);
 	if (rate < 0) {
-		dev_err(chip->dev, "Unable to round rate: %ld", rate);
+		dev_err(chip->dev, "Unable to round rate: %ld\n", rate);
 		return rate;
 	}
 
@@ -170,7 +170,7 @@ static int jz4740_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 
 	err = clk_set_rate(clk, rate);
 	if (err) {
-		dev_err(chip->dev, "Unable to set rate: %d", err);
+		dev_err(chip->dev, "Unable to set rate: %d\n", err);
 		return err;
 	}
 
-- 
GitLab


From b0445a18d3eef36b7dc4e07a0ccb4f7178251942 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 23 Nov 2023 10:56:20 +0100
Subject: [PATCH 1667/4076] pwm: Narrow scope of struct pwm_device pointer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the expression determining the size of the allocation for chip->pwms
it's more natural to use sizeof(*chip->pwms) than sizeof(*pwm). With
that changed, the variable pwm is only used in a for loop and its scope
can be reduced accordingly.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index fb36b3d559a72..b0e50ca9398a7 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -208,7 +208,6 @@ static bool pwm_ops_check(const struct pwm_chip *chip)
  */
 int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 {
-	struct pwm_device *pwm;
 	unsigned int i;
 	int ret;
 
@@ -220,7 +219,7 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 
 	chip->owner = owner;
 
-	chip->pwms = kcalloc(chip->npwm, sizeof(*pwm), GFP_KERNEL);
+	chip->pwms = kcalloc(chip->npwm, sizeof(*chip->pwms), GFP_KERNEL);
 	if (!chip->pwms)
 		return -ENOMEM;
 
@@ -236,7 +235,7 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 	chip->id = ret;
 
 	for (i = 0; i < chip->npwm; i++) {
-		pwm = &chip->pwms[i];
+		struct pwm_device *pwm = &chip->pwms[i];
 
 		pwm->chip = chip;
 		pwm->hwpwm = i;
-- 
GitLab


From 7ee2273197f1c1755ebdad8716eab50689401aff Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 26 Oct 2023 14:54:17 -0500
Subject: [PATCH 1668/4076] pwm: Use device_get_match_data()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use preferred device_get_match_data() instead of of_match_device() to
get the driver match data. With this, adjust the includes to explicitly
include the correct headers.

As these drivers only do DT based matching, of_match_device() will never
return NULL if we've gotten to probe(). Therefore, the NULL check and
error returns can be dropped.

Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-img.c      | 8 ++------
 drivers/pwm/pwm-rockchip.c | 9 ++-------
 2 files changed, 4 insertions(+), 13 deletions(-)

diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c
index 116fa060e3029..0d218c0b690ed 100644
--- a/drivers/pwm/pwm-img.c
+++ b/drivers/pwm/pwm-img.c
@@ -13,9 +13,9 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/pwm.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
@@ -260,7 +260,6 @@ static int img_pwm_probe(struct platform_device *pdev)
 	u64 val;
 	unsigned long clk_rate;
 	struct img_pwm_chip *imgchip;
-	const struct of_device_id *of_dev_id;
 
 	imgchip = devm_kzalloc(&pdev->dev, sizeof(*imgchip), GFP_KERNEL);
 	if (!imgchip)
@@ -272,10 +271,7 @@ static int img_pwm_probe(struct platform_device *pdev)
 	if (IS_ERR(imgchip->base))
 		return PTR_ERR(imgchip->base);
 
-	of_dev_id = of_match_device(img_pwm_of_match, &pdev->dev);
-	if (!of_dev_id)
-		return -ENODEV;
-	imgchip->data = of_dev_id->data;
+	imgchip->data = device_get_match_data(&pdev->dev);
 
 	imgchip->periph_regs = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
 							       "img,cr-periph");
diff --git a/drivers/pwm/pwm-rockchip.c b/drivers/pwm/pwm-rockchip.c
index cce4381e188af..a7c647e378373 100644
--- a/drivers/pwm/pwm-rockchip.c
+++ b/drivers/pwm/pwm-rockchip.c
@@ -10,8 +10,8 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/pwm.h>
 #include <linux/time.h>
 
@@ -296,16 +296,11 @@ MODULE_DEVICE_TABLE(of, rockchip_pwm_dt_ids);
 
 static int rockchip_pwm_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *id;
 	struct rockchip_pwm_chip *pc;
 	u32 enable_conf, ctrl;
 	bool enabled;
 	int ret, count;
 
-	id = of_match_device(rockchip_pwm_dt_ids, &pdev->dev);
-	if (!id)
-		return -EINVAL;
-
 	pc = devm_kzalloc(&pdev->dev, sizeof(*pc), GFP_KERNEL);
 	if (!pc)
 		return -ENOMEM;
@@ -344,7 +339,7 @@ static int rockchip_pwm_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pc);
 
-	pc->data = id->data;
+	pc->data = device_get_match_data(&pdev->dev);
 	pc->chip.dev = &pdev->dev;
 	pc->chip.ops = &rockchip_pwm_ops;
 	pc->chip.npwm = 1;
-- 
GitLab


From e495f47274a145dd802748fed66608f46d9ae11d Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 19 Oct 2023 22:07:00 +0200
Subject: [PATCH 1669/4076] pwm: stm32: Replace write_ccrx with regmap_write
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The TIM_CCR1...4 registers are consecutive, so replace the switch
case with a simple calculation. Since ch is known to be in the 0...3
range (it is set to hwpwm < npwm <= 4), drop the unnecessary error
handling. The return value was not checked anyway. What remains does
not warrant keeping the write_ccrx() function around, so instead call
regmap_write() directly at the singular call site.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 8be037757b8bd..2dcf6ecab4be9 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -52,21 +52,6 @@ static u32 active_channels(struct stm32_pwm *dev)
 	return ccer & TIM_CCER_CCXE;
 }
 
-static int write_ccrx(struct stm32_pwm *dev, int ch, u32 value)
-{
-	switch (ch) {
-	case 0:
-		return regmap_write(dev->regmap, TIM_CCR1, value);
-	case 1:
-		return regmap_write(dev->regmap, TIM_CCR2, value);
-	case 2:
-		return regmap_write(dev->regmap, TIM_CCR3, value);
-	case 3:
-		return regmap_write(dev->regmap, TIM_CCR4, value);
-	}
-	return -EINVAL;
-}
-
 #define TIM_CCER_CC12P (TIM_CCER_CC1P | TIM_CCER_CC2P)
 #define TIM_CCER_CC12E (TIM_CCER_CC1E | TIM_CCER_CC2E)
 #define TIM_CCER_CC34P (TIM_CCER_CC3P | TIM_CCER_CC4P)
@@ -369,7 +354,7 @@ static int stm32_pwm_config(struct stm32_pwm *priv, int ch,
 	dty = prd * duty_ns;
 	do_div(dty, period_ns);
 
-	write_ccrx(priv, ch, dty);
+	regmap_write(priv->regmap, TIM_CCR1 + 4 * ch, dty);
 
 	/* Configure output mode */
 	shift = (ch & 0x1) * CCMR_CHANNEL_SHIFT;
-- 
GitLab


From c0504f59ced46b080520c2fc15b2b58d70f9ec83 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 19 Oct 2023 22:07:01 +0200
Subject: [PATCH 1670/4076] pwm: stm32: Make ch parameter unsigned
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The channel parameter is only ever set to pwm->hwpwm.
Make it unsigned int as well.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 2dcf6ecab4be9..67c9e262dc57f 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -308,7 +308,7 @@ unlock:
 	return ret;
 }
 
-static int stm32_pwm_config(struct stm32_pwm *priv, int ch,
+static int stm32_pwm_config(struct stm32_pwm *priv, unsigned int ch,
 			    int duty_ns, int period_ns)
 {
 	unsigned long long prd, div, dty;
@@ -371,7 +371,7 @@ static int stm32_pwm_config(struct stm32_pwm *priv, int ch,
 	return 0;
 }
 
-static int stm32_pwm_set_polarity(struct stm32_pwm *priv, int ch,
+static int stm32_pwm_set_polarity(struct stm32_pwm *priv, unsigned int ch,
 				  enum pwm_polarity polarity)
 {
 	u32 mask;
@@ -386,7 +386,7 @@ static int stm32_pwm_set_polarity(struct stm32_pwm *priv, int ch,
 	return 0;
 }
 
-static int stm32_pwm_enable(struct stm32_pwm *priv, int ch)
+static int stm32_pwm_enable(struct stm32_pwm *priv, unsigned int ch)
 {
 	u32 mask;
 	int ret;
@@ -411,7 +411,7 @@ static int stm32_pwm_enable(struct stm32_pwm *priv, int ch)
 	return 0;
 }
 
-static void stm32_pwm_disable(struct stm32_pwm *priv, int ch)
+static void stm32_pwm_disable(struct stm32_pwm *priv, unsigned int ch)
 {
 	u32 mask;
 
-- 
GitLab


From 41fa8f57c0d269243fe3bde2bce71e82c884b9ad Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 19 Oct 2023 22:07:02 +0200
Subject: [PATCH 1671/4076] pwm: stm32: Use hweight32 in
 stm32_pwm_detect_channels
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use hweight32() to count the CCxE bits in stm32_pwm_detect_channels().
Since the return value is assigned to chip.npwm, change it to unsigned
int as well.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32.c | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)

diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 67c9e262dc57f..0da371291cef8 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -563,10 +563,9 @@ static void stm32_pwm_detect_complementary(struct stm32_pwm *priv)
 	priv->have_complementary_output = (ccer != 0);
 }
 
-static int stm32_pwm_detect_channels(struct stm32_pwm *priv)
+static unsigned int stm32_pwm_detect_channels(struct stm32_pwm *priv)
 {
 	u32 ccer;
-	int npwm = 0;
 
 	/*
 	 * If channels enable bits don't exist writing 1 will have no
@@ -576,19 +575,7 @@ static int stm32_pwm_detect_channels(struct stm32_pwm *priv)
 	regmap_read(priv->regmap, TIM_CCER, &ccer);
 	regmap_clear_bits(priv->regmap, TIM_CCER, TIM_CCER_CCXE);
 
-	if (ccer & TIM_CCER_CC1E)
-		npwm++;
-
-	if (ccer & TIM_CCER_CC2E)
-		npwm++;
-
-	if (ccer & TIM_CCER_CC3E)
-		npwm++;
-
-	if (ccer & TIM_CCER_CC4E)
-		npwm++;
-
-	return npwm;
+	return hweight32(ccer & TIM_CCER_CCXE);
 }
 
 static int stm32_pwm_probe(struct platform_device *pdev)
-- 
GitLab


From e56ec7b7527c2be54a0c15064c71838fd5c49d4b Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 19 Oct 2023 22:07:03 +0200
Subject: [PATCH 1672/4076] pwm: stm32: Implement .get_state()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implement the &pwm_ops->get_state callback so drivers can inherit PWM
state set by the bootloader.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
[ukl: split off from a patch that also fixes clk enable count in .probe()]
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32.c | 42 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 0da371291cef8..9a7d7891edde7 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -471,8 +471,50 @@ static int stm32_pwm_apply_locked(struct pwm_chip *chip, struct pwm_device *pwm,
 	return ret;
 }
 
+static int stm32_pwm_get_state(struct pwm_chip *chip,
+			       struct pwm_device *pwm, struct pwm_state *state)
+{
+	struct stm32_pwm *priv = to_stm32_pwm_dev(chip);
+	int ch = pwm->hwpwm;
+	unsigned long rate;
+	u32 ccer, psc, arr, ccr;
+	u64 dty, prd;
+	int ret;
+
+	mutex_lock(&priv->lock);
+
+	ret = regmap_read(priv->regmap, TIM_CCER, &ccer);
+	if (ret)
+		goto out;
+
+	state->enabled = ccer & (TIM_CCER_CC1E << (ch * 4));
+	state->polarity = (ccer & (TIM_CCER_CC1P << (ch * 4))) ?
+			  PWM_POLARITY_INVERSED : PWM_POLARITY_NORMAL;
+	ret = regmap_read(priv->regmap, TIM_PSC, &psc);
+	if (ret)
+		goto out;
+	ret = regmap_read(priv->regmap, TIM_ARR, &arr);
+	if (ret)
+		goto out;
+	ret = regmap_read(priv->regmap, TIM_CCR1 + 4 * ch, &ccr);
+	if (ret)
+		goto out;
+
+	rate = clk_get_rate(priv->clk);
+
+	prd = (u64)NSEC_PER_SEC * (psc + 1) * (arr + 1);
+	state->period = DIV_ROUND_UP_ULL(prd, rate);
+	dty = (u64)NSEC_PER_SEC * (psc + 1) * ccr;
+	state->duty_cycle = DIV_ROUND_UP_ULL(dty, rate);
+
+out:
+	mutex_unlock(&priv->lock);
+	return ret;
+}
+
 static const struct pwm_ops stm32pwm_ops = {
 	.apply = stm32_pwm_apply_locked,
+	.get_state = stm32_pwm_get_state,
 	.capture = IS_ENABLED(CONFIG_DMA_ENGINE) ? stm32_pwm_capture : NULL,
 };
 
-- 
GitLab


From 19f1016ea9600ed89bc24247c36ff5934ad94fbb Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 19 Oct 2023 22:07:04 +0200
Subject: [PATCH 1673/4076] pwm: stm32: Fix enable count for clk in .probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make the driver take over hardware state without disabling in .probe()
and enable the clock for each enabled channel.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
[ukleinek: split off from a patch that also implemented .get_state()]
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Fixes: 7edf7369205b ("pwm: Add driver for STM32 plaftorm")
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stm32.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 9a7d7891edde7..5f10cba492ecb 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -605,17 +605,21 @@ static void stm32_pwm_detect_complementary(struct stm32_pwm *priv)
 	priv->have_complementary_output = (ccer != 0);
 }
 
-static unsigned int stm32_pwm_detect_channels(struct stm32_pwm *priv)
+static unsigned int stm32_pwm_detect_channels(struct stm32_pwm *priv,
+					      unsigned int *num_enabled)
 {
-	u32 ccer;
+	u32 ccer, ccer_backup;
 
 	/*
 	 * If channels enable bits don't exist writing 1 will have no
 	 * effect so we can detect and count them.
 	 */
+	regmap_read(priv->regmap, TIM_CCER, &ccer_backup);
 	regmap_set_bits(priv->regmap, TIM_CCER, TIM_CCER_CCXE);
 	regmap_read(priv->regmap, TIM_CCER, &ccer);
-	regmap_clear_bits(priv->regmap, TIM_CCER, TIM_CCER_CCXE);
+	regmap_write(priv->regmap, TIM_CCER, ccer_backup);
+
+	*num_enabled = hweight32(ccer_backup & TIM_CCER_CCXE);
 
 	return hweight32(ccer & TIM_CCER_CCXE);
 }
@@ -626,6 +630,8 @@ static int stm32_pwm_probe(struct platform_device *pdev)
 	struct device_node *np = dev->of_node;
 	struct stm32_timers *ddata = dev_get_drvdata(pdev->dev.parent);
 	struct stm32_pwm *priv;
+	unsigned int num_enabled;
+	unsigned int i;
 	int ret;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -648,7 +654,11 @@ static int stm32_pwm_probe(struct platform_device *pdev)
 
 	priv->chip.dev = dev;
 	priv->chip.ops = &stm32pwm_ops;
-	priv->chip.npwm = stm32_pwm_detect_channels(priv);
+	priv->chip.npwm = stm32_pwm_detect_channels(priv, &num_enabled);
+
+	/* Initialize clock refcount to number of enabled PWM channels. */
+	for (i = 0; i < num_enabled; i++)
+		clk_enable(priv->clk);
 
 	ret = devm_pwmchip_add(dev, &priv->chip);
 	if (ret < 0)
-- 
GitLab


From 74ade42105bb80e67b7b07b7e88cdaaa8c3402b6 Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Thu, 23 Nov 2023 14:47:16 +0100
Subject: [PATCH 1674/4076] dt-bindings: pwm: remove Xinlei's mail
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Xinlei Lee's mail is bouncing:

<xinlei.lee@mediatek.com>: host mailgw02.mediatek.com[216.200.240.185] said:
    550 Relaying mail to xinlei.lee@mediatek.com is not allowed (in reply to
    RCPT TO command)

Remove it.

Signed-off-by: Michael Walle <mwalle@kernel.org>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml b/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml
index 153e146df7d4b..afcdeed4e88af 100644
--- a/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml
+++ b/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml
@@ -8,7 +8,6 @@ title: MediaTek DISP_PWM Controller
 
 maintainers:
   - Jitao Shi <jitao.shi@mediatek.com>
-  - Xinlei Lee <xinlei.lee@mediatek.com>
 
 allOf:
   - $ref: pwm.yaml#
-- 
GitLab


From 2d91123ae5614b8737abd3a519b81265309a1ac3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 29 Nov 2023 11:18:32 +0100
Subject: [PATCH 1675/4076] pwm: Update kernel doc for struct pwm_chip
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit c572f3b9c8b7 ("pwm: Replace PWM chip unique base by unique ID")
changed the members of struct pwm_chip, but failed to update the
documentation accordingly. Catch up and document the new member and drop
description for the two removed ones.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index c27a4bb76012e..f87655c06c825 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -281,11 +281,10 @@ struct pwm_ops {
  * @dev: device providing the PWMs
  * @ops: callbacks for this PWM controller
  * @owner: module providing this chip
- * @base: number of first PWM controlled by this chip
+ * @id: unique number of this PWM chip
  * @npwm: number of PWMs controlled by this chip
  * @of_xlate: request a PWM device given a device tree PWM specifier
  * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier
- * @list: list node for internal use
  * @pwms: array of PWM devices allocated by the framework
  */
 struct pwm_chip {
-- 
GitLab


From 80943bbdcfa8138eca3bfd71a8ed4bdf1e107f6b Mon Sep 17 00:00:00 2001
From: Thierry Reding <thierry.reding@gmail.com>
Date: Fri, 1 Dec 2023 11:22:53 +0100
Subject: [PATCH 1676/4076] pwm: Stop referencing pwm->chip
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drivers have access to the chip via a function argument already, so
there is no need to reference it via the PWM device.

Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-bcm-kona.c    | 2 +-
 drivers/pwm/pwm-img.c         | 2 +-
 drivers/pwm/pwm-jz4740.c      | 2 +-
 drivers/pwm/pwm-lpc18xx-sct.c | 2 +-
 drivers/pwm/pwm-lpc32xx.c     | 2 +-
 drivers/pwm/pwm-mediatek.c    | 2 +-
 drivers/pwm/pwm-renesas-tpu.c | 2 +-
 drivers/pwm/pwm-sti.c         | 2 +-
 drivers/pwm/pwm-stmpe.c       | 2 +-
 drivers/pwm/pwm-tegra.c       | 2 +-
 drivers/pwm/pwm-twl-led.c     | 4 ++--
 drivers/pwm/pwm-twl.c         | 4 ++--
 drivers/pwm/pwm-vt8500.c      | 2 +-
 13 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/pwm/pwm-bcm-kona.c b/drivers/pwm/pwm-bcm-kona.c
index 15d6ed03c3ce0..45046a5c20a5e 100644
--- a/drivers/pwm/pwm-bcm-kona.c
+++ b/drivers/pwm/pwm-bcm-kona.c
@@ -260,7 +260,7 @@ static int kona_pwmc_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			return err;
 	}
 
-	err = kona_pwmc_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = kona_pwmc_config(chip, pwm, state->duty_cycle, state->period);
 	if (err && !pwm->state.enabled)
 		clk_disable_unprepare(kp->clk);
 
diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c
index 0d218c0b690ed..5965ac35b32ea 100644
--- a/drivers/pwm/pwm-img.c
+++ b/drivers/pwm/pwm-img.c
@@ -196,7 +196,7 @@ static int img_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = img_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = img_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c
index 73f96cef16621..80dcff237a155 100644
--- a/drivers/pwm/pwm-jz4740.c
+++ b/drivers/pwm/pwm-jz4740.c
@@ -123,7 +123,7 @@ static void jz4740_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 static int jz4740_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			    const struct pwm_state *state)
 {
-	struct jz4740_pwm_chip *jz = to_jz4740(pwm->chip);
+	struct jz4740_pwm_chip *jz = to_jz4740(chip);
 	unsigned long long tmp = 0xffffull * NSEC_PER_SEC;
 	struct clk *clk = jz->clk[pwm->hwpwm];
 	unsigned long period, duty;
diff --git a/drivers/pwm/pwm-lpc18xx-sct.c b/drivers/pwm/pwm-lpc18xx-sct.c
index ef7d0da137ede..b3d4a955aa311 100644
--- a/drivers/pwm/pwm-lpc18xx-sct.c
+++ b/drivers/pwm/pwm-lpc18xx-sct.c
@@ -328,7 +328,7 @@ static int lpc18xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = lpc18xx_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = lpc18xx_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
diff --git a/drivers/pwm/pwm-lpc32xx.c b/drivers/pwm/pwm-lpc32xx.c
index 78f664e41e6e3..1d9f3e7a2434a 100644
--- a/drivers/pwm/pwm-lpc32xx.c
+++ b/drivers/pwm/pwm-lpc32xx.c
@@ -103,7 +103,7 @@ static int lpc32xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = lpc32xx_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = lpc32xx_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index 373abfd25acb2..17d290f847af6 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -217,7 +217,7 @@ static int pwm_mediatek_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = pwm_mediatek_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = pwm_mediatek_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
diff --git a/drivers/pwm/pwm-renesas-tpu.c b/drivers/pwm/pwm-renesas-tpu.c
index 4239f2c3e8b2a..ce92db1f85113 100644
--- a/drivers/pwm/pwm-renesas-tpu.c
+++ b/drivers/pwm/pwm-renesas-tpu.c
@@ -416,7 +416,7 @@ static int tpu_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = tpu_pwm_config(pwm->chip, pwm,
+	err = tpu_pwm_config(chip, pwm,
 			     state->duty_cycle, state->period, enabled);
 	if (err)
 		return err;
diff --git a/drivers/pwm/pwm-sti.c b/drivers/pwm/pwm-sti.c
index dc92cea31cd07..6cf55cf34d39f 100644
--- a/drivers/pwm/pwm-sti.c
+++ b/drivers/pwm/pwm-sti.c
@@ -407,7 +407,7 @@ static int sti_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = sti_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = sti_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
diff --git a/drivers/pwm/pwm-stmpe.c b/drivers/pwm/pwm-stmpe.c
index a46f5b4dd8162..d730631c6583a 100644
--- a/drivers/pwm/pwm-stmpe.c
+++ b/drivers/pwm/pwm-stmpe.c
@@ -275,7 +275,7 @@ static int stmpe_24xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = stmpe_24xx_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = stmpe_24xx_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c
index 39ea51e08c946..82ee2f0754f96 100644
--- a/drivers/pwm/pwm-tegra.c
+++ b/drivers/pwm/pwm-tegra.c
@@ -256,7 +256,7 @@ static int tegra_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = tegra_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = tegra_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
diff --git a/drivers/pwm/pwm-twl-led.c b/drivers/pwm/pwm-twl-led.c
index 625233f4703a9..8a870d0db3c69 100644
--- a/drivers/pwm/pwm-twl-led.c
+++ b/drivers/pwm/pwm-twl-led.c
@@ -175,7 +175,7 @@ static int twl4030_pwmled_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * pwm_apply_state because of !state->enabled and so the two values in
 	 * pwm->state might not be configured in hardware.
 	 */
-	ret = twl4030_pwmled_config(pwm->chip, pwm,
+	ret = twl4030_pwmled_config(chip, pwm,
 				    state->duty_cycle, state->period);
 	if (ret)
 		return ret;
@@ -275,7 +275,7 @@ static int twl6030_pwmled_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = twl6030_pwmled_config(pwm->chip, pwm,
+	err = twl6030_pwmled_config(chip, pwm,
 				    state->duty_cycle, state->period);
 	if (err)
 		return err;
diff --git a/drivers/pwm/pwm-twl.c b/drivers/pwm/pwm-twl.c
index 603d31f27470f..68e02c9a6bf9a 100644
--- a/drivers/pwm/pwm-twl.c
+++ b/drivers/pwm/pwm-twl.c
@@ -294,7 +294,7 @@ static int twl4030_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = twl_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = twl_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
@@ -319,7 +319,7 @@ static int twl6030_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		return 0;
 	}
 
-	err = twl_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = twl_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
diff --git a/drivers/pwm/pwm-vt8500.c b/drivers/pwm/pwm-vt8500.c
index 5568d5312d3ca..bdea60389487e 100644
--- a/drivers/pwm/pwm-vt8500.c
+++ b/drivers/pwm/pwm-vt8500.c
@@ -209,7 +209,7 @@ static int vt8500_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * pwm_apply_state because of !state->enabled and so the two values in
 	 * pwm->state might not be configured in hardware.
 	 */
-	err = vt8500_pwm_config(pwm->chip, pwm, state->duty_cycle, state->period);
+	err = vt8500_pwm_config(chip, pwm, state->duty_cycle, state->period);
 	if (err)
 		return err;
 
-- 
GitLab


From c748a6d77c06a78651030e17da6beb278a1c9470 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 19 Dec 2023 16:30:24 +0000
Subject: [PATCH 1677/4076] pwm: Rename pwm_apply_state() to
 pwm_apply_might_sleep()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to introduce a pwm api which can be used from atomic context,
we will need two functions for applying pwm changes:

	int pwm_apply_might_sleep(struct pwm *, struct pwm_state *);
	int pwm_apply_atomic(struct pwm *, struct pwm_state *);

This commit just deals with renaming pwm_apply_state(), a following
commit will introduce the pwm_apply_atomic() function.

Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> # for input
Acked-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Lee Jones <lee@kernel.org>
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 Documentation/driver-api/pwm.rst              |  8 +++---
 MAINTAINERS                                   |  2 +-
 .../gpu/drm/i915/display/intel_backlight.c    |  6 ++--
 drivers/gpu/drm/solomon/ssd130x.c             |  2 +-
 drivers/hwmon/pwm-fan.c                       |  8 +++---
 drivers/input/misc/da7280.c                   |  4 +--
 drivers/input/misc/pwm-beeper.c               |  4 +--
 drivers/input/misc/pwm-vibra.c                |  8 +++---
 drivers/leds/leds-pwm.c                       |  2 +-
 drivers/leds/rgb/leds-pwm-multicolor.c        |  4 +--
 drivers/media/rc/pwm-ir-tx.c                  |  4 +--
 drivers/platform/x86/lenovo-yogabook.c        |  2 +-
 drivers/pwm/core.c                            | 18 ++++++------
 drivers/pwm/pwm-twl-led.c                     |  2 +-
 drivers/pwm/pwm-vt8500.c                      |  2 +-
 drivers/pwm/sysfs.c                           | 10 +++----
 drivers/regulator/pwm-regulator.c             |  4 +--
 drivers/video/backlight/lm3630a_bl.c          |  2 +-
 drivers/video/backlight/lp855x_bl.c           |  2 +-
 drivers/video/backlight/pwm_bl.c              | 12 ++++----
 drivers/video/fbdev/ssd1307fb.c               |  2 +-
 include/linux/pwm.h                           | 28 +++++++++----------
 22 files changed, 68 insertions(+), 68 deletions(-)

diff --git a/Documentation/driver-api/pwm.rst b/Documentation/driver-api/pwm.rst
index bb264490a87a1..f1d8197c8c430 100644
--- a/Documentation/driver-api/pwm.rst
+++ b/Documentation/driver-api/pwm.rst
@@ -41,7 +41,7 @@ the getter, devm_pwm_get() and devm_fwnode_pwm_get(), also exist.
 
 After being requested, a PWM has to be configured using::
 
-	int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state);
+	int pwm_apply_might_sleep(struct pwm_device *pwm, struct pwm_state *state);
 
 This API controls both the PWM period/duty_cycle config and the
 enable/disable state.
@@ -57,13 +57,13 @@ If supported by the driver, the signal can be optimized, for example to improve
 EMI by phase shifting the individual channels of a chip.
 
 The pwm_config(), pwm_enable() and pwm_disable() functions are just wrappers
-around pwm_apply_state() and should not be used if the user wants to change
+around pwm_apply_might_sleep() and should not be used if the user wants to change
 several parameter at once. For example, if you see pwm_config() and
 pwm_{enable,disable}() calls in the same function, this probably means you
-should switch to pwm_apply_state().
+should switch to pwm_apply_might_sleep().
 
 The PWM user API also allows one to query the PWM state that was passed to the
-last invocation of pwm_apply_state() using pwm_get_state(). Note this is
+last invocation of pwm_apply_might_sleep() using pwm_get_state(). Note this is
 different to what the driver has actually implemented if the request cannot be
 satisfied exactly with the hardware in use. There is currently no way for
 consumers to get the actually implemented settings.
diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cfd..c584805952209 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17576,7 +17576,7 @@ F:	drivers/video/backlight/pwm_bl.c
 F:	include/dt-bindings/pwm/
 F:	include/linux/pwm.h
 F:	include/linux/pwm_backlight.h
-K:	pwm_(config|apply_state|ops)
+K:	pwm_(config|apply_might_sleep|ops)
 
 PXA GPIO DRIVER
 M:	Robert Jarzmik <robert.jarzmik@free.fr>
diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c
index 2e8f17c045222..ff9b9918b0a13 100644
--- a/drivers/gpu/drm/i915/display/intel_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_backlight.c
@@ -274,7 +274,7 @@ static void ext_pwm_set_backlight(const struct drm_connector_state *conn_state,
 	struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel;
 
 	pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100);
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+	pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state);
 }
 
 static void
@@ -427,7 +427,7 @@ static void ext_pwm_disable_backlight(const struct drm_connector_state *old_conn
 	intel_backlight_set_pwm_level(old_conn_state, level);
 
 	panel->backlight.pwm_state.enabled = false;
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+	pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state);
 }
 
 void intel_backlight_disable(const struct drm_connector_state *old_conn_state)
@@ -749,7 +749,7 @@ static void ext_pwm_enable_backlight(const struct intel_crtc_state *crtc_state,
 
 	pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100);
 	panel->backlight.pwm_state.enabled = true;
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+	pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state);
 }
 
 static void __intel_backlight_enable(const struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c
index e0174f82e3537..cce043a4a1dcd 100644
--- a/drivers/gpu/drm/solomon/ssd130x.c
+++ b/drivers/gpu/drm/solomon/ssd130x.c
@@ -319,7 +319,7 @@ static int ssd130x_pwm_enable(struct ssd130x_device *ssd130x)
 
 	pwm_init_state(ssd130x->pwm, &pwmstate);
 	pwm_set_relative_duty_cycle(&pwmstate, 50, 100);
-	pwm_apply_state(ssd130x->pwm, &pwmstate);
+	pwm_apply_might_sleep(ssd130x->pwm, &pwmstate);
 
 	/* Enable the PWM */
 	pwm_enable(ssd130x->pwm);
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 6e4516c2ab894..b67bc9e833c01 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -151,7 +151,7 @@ static int pwm_fan_power_on(struct pwm_fan_ctx *ctx)
 	}
 
 	state->enabled = true;
-	ret = pwm_apply_state(ctx->pwm, state);
+	ret = pwm_apply_might_sleep(ctx->pwm, state);
 	if (ret) {
 		dev_err(ctx->dev, "failed to enable PWM\n");
 		goto disable_regulator;
@@ -181,7 +181,7 @@ static int pwm_fan_power_off(struct pwm_fan_ctx *ctx)
 
 	state->enabled = false;
 	state->duty_cycle = 0;
-	ret = pwm_apply_state(ctx->pwm, state);
+	ret = pwm_apply_might_sleep(ctx->pwm, state);
 	if (ret) {
 		dev_err(ctx->dev, "failed to disable PWM\n");
 		return ret;
@@ -207,7 +207,7 @@ static int  __set_pwm(struct pwm_fan_ctx *ctx, unsigned long pwm)
 
 		period = state->period;
 		state->duty_cycle = DIV_ROUND_UP(pwm * (period - 1), MAX_PWM);
-		ret = pwm_apply_state(ctx->pwm, state);
+		ret = pwm_apply_might_sleep(ctx->pwm, state);
 		if (ret)
 			return ret;
 		ret = pwm_fan_power_on(ctx);
@@ -278,7 +278,7 @@ static int pwm_fan_update_enable(struct pwm_fan_ctx *ctx, long val)
 						    state,
 						    &enable_regulator);
 
-			pwm_apply_state(ctx->pwm, state);
+			pwm_apply_might_sleep(ctx->pwm, state);
 			pwm_fan_switch_power(ctx, enable_regulator);
 			pwm_fan_update_state(ctx, 0);
 		}
diff --git a/drivers/input/misc/da7280.c b/drivers/input/misc/da7280.c
index ce82548916bbc..c1fa75c0f970a 100644
--- a/drivers/input/misc/da7280.c
+++ b/drivers/input/misc/da7280.c
@@ -352,7 +352,7 @@ static int da7280_haptic_set_pwm(struct da7280_haptic *haptics, bool enabled)
 		state.duty_cycle = period_mag_multi;
 	}
 
-	error = pwm_apply_state(haptics->pwm_dev, &state);
+	error = pwm_apply_might_sleep(haptics->pwm_dev, &state);
 	if (error)
 		dev_err(haptics->dev, "Failed to apply pwm state: %d\n", error);
 
@@ -1175,7 +1175,7 @@ static int da7280_probe(struct i2c_client *client)
 		/* Sync up PWM state and ensure it is off. */
 		pwm_init_state(haptics->pwm_dev, &state);
 		state.enabled = false;
-		error = pwm_apply_state(haptics->pwm_dev, &state);
+		error = pwm_apply_might_sleep(haptics->pwm_dev, &state);
 		if (error) {
 			dev_err(dev, "Failed to apply PWM state: %d\n", error);
 			return error;
diff --git a/drivers/input/misc/pwm-beeper.c b/drivers/input/misc/pwm-beeper.c
index 1e731d8397c6f..5b9aedf4362f4 100644
--- a/drivers/input/misc/pwm-beeper.c
+++ b/drivers/input/misc/pwm-beeper.c
@@ -39,7 +39,7 @@ static int pwm_beeper_on(struct pwm_beeper *beeper, unsigned long period)
 	state.period = period;
 	pwm_set_relative_duty_cycle(&state, 50, 100);
 
-	error = pwm_apply_state(beeper->pwm, &state);
+	error = pwm_apply_might_sleep(beeper->pwm, &state);
 	if (error)
 		return error;
 
@@ -138,7 +138,7 @@ static int pwm_beeper_probe(struct platform_device *pdev)
 	/* Sync up PWM state and ensure it is off. */
 	pwm_init_state(beeper->pwm, &state);
 	state.enabled = false;
-	error = pwm_apply_state(beeper->pwm, &state);
+	error = pwm_apply_might_sleep(beeper->pwm, &state);
 	if (error) {
 		dev_err(dev, "failed to apply initial PWM state: %d\n",
 			error);
diff --git a/drivers/input/misc/pwm-vibra.c b/drivers/input/misc/pwm-vibra.c
index acac79c488aa1..3e5ed685ed8f5 100644
--- a/drivers/input/misc/pwm-vibra.c
+++ b/drivers/input/misc/pwm-vibra.c
@@ -56,7 +56,7 @@ static int pwm_vibrator_start(struct pwm_vibrator *vibrator)
 	pwm_set_relative_duty_cycle(&state, vibrator->level, 0xffff);
 	state.enabled = true;
 
-	err = pwm_apply_state(vibrator->pwm, &state);
+	err = pwm_apply_might_sleep(vibrator->pwm, &state);
 	if (err) {
 		dev_err(pdev, "failed to apply pwm state: %d\n", err);
 		return err;
@@ -67,7 +67,7 @@ static int pwm_vibrator_start(struct pwm_vibrator *vibrator)
 		state.duty_cycle = vibrator->direction_duty_cycle;
 		state.enabled = true;
 
-		err = pwm_apply_state(vibrator->pwm_dir, &state);
+		err = pwm_apply_might_sleep(vibrator->pwm_dir, &state);
 		if (err) {
 			dev_err(pdev, "failed to apply dir-pwm state: %d\n", err);
 			pwm_disable(vibrator->pwm);
@@ -160,7 +160,7 @@ static int pwm_vibrator_probe(struct platform_device *pdev)
 	/* Sync up PWM state and ensure it is off. */
 	pwm_init_state(vibrator->pwm, &state);
 	state.enabled = false;
-	err = pwm_apply_state(vibrator->pwm, &state);
+	err = pwm_apply_might_sleep(vibrator->pwm, &state);
 	if (err) {
 		dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
 			err);
@@ -174,7 +174,7 @@ static int pwm_vibrator_probe(struct platform_device *pdev)
 		/* Sync up PWM state and ensure it is off. */
 		pwm_init_state(vibrator->pwm_dir, &state);
 		state.enabled = false;
-		err = pwm_apply_state(vibrator->pwm_dir, &state);
+		err = pwm_apply_might_sleep(vibrator->pwm_dir, &state);
 		if (err) {
 			dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
 				err);
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index 2b3bf1353b707..4e3936a39d0ed 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -54,7 +54,7 @@ static int led_pwm_set(struct led_classdev *led_cdev,
 
 	led_dat->pwmstate.duty_cycle = duty;
 	led_dat->pwmstate.enabled = true;
-	return pwm_apply_state(led_dat->pwm, &led_dat->pwmstate);
+	return pwm_apply_might_sleep(led_dat->pwm, &led_dat->pwmstate);
 }
 
 __attribute__((nonnull))
diff --git a/drivers/leds/rgb/leds-pwm-multicolor.c b/drivers/leds/rgb/leds-pwm-multicolor.c
index 46cd062b8b24c..e1a81e0109e8a 100644
--- a/drivers/leds/rgb/leds-pwm-multicolor.c
+++ b/drivers/leds/rgb/leds-pwm-multicolor.c
@@ -51,8 +51,8 @@ static int led_pwm_mc_set(struct led_classdev *cdev,
 
 		priv->leds[i].state.duty_cycle = duty;
 		priv->leds[i].state.enabled = duty > 0;
-		ret = pwm_apply_state(priv->leds[i].pwm,
-				      &priv->leds[i].state);
+		ret = pwm_apply_might_sleep(priv->leds[i].pwm,
+					    &priv->leds[i].state);
 		if (ret)
 			break;
 	}
diff --git a/drivers/media/rc/pwm-ir-tx.c b/drivers/media/rc/pwm-ir-tx.c
index c5f37c03af9c9..cf51e27609759 100644
--- a/drivers/media/rc/pwm-ir-tx.c
+++ b/drivers/media/rc/pwm-ir-tx.c
@@ -68,7 +68,7 @@ static int pwm_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
 
 	for (i = 0; i < count; i++) {
 		state.enabled = !(i % 2);
-		pwm_apply_state(pwm, &state);
+		pwm_apply_might_sleep(pwm, &state);
 
 		edge = ktime_add_us(edge, txbuf[i]);
 		delta = ktime_us_delta(edge, ktime_get());
@@ -77,7 +77,7 @@ static int pwm_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
 	}
 
 	state.enabled = false;
-	pwm_apply_state(pwm, &state);
+	pwm_apply_might_sleep(pwm, &state);
 
 	return count;
 }
diff --git a/drivers/platform/x86/lenovo-yogabook.c b/drivers/platform/x86/lenovo-yogabook.c
index b8d0239192cbf..fd62bf746ebde 100644
--- a/drivers/platform/x86/lenovo-yogabook.c
+++ b/drivers/platform/x86/lenovo-yogabook.c
@@ -435,7 +435,7 @@ static int yogabook_pdev_set_kbd_backlight(struct yogabook_data *data, u8 level)
 		.enabled = level,
 	};
 
-	pwm_apply_state(data->kbd_bl_pwm, &state);
+	pwm_apply_might_sleep(data->kbd_bl_pwm, &state);
 	gpiod_set_value(data->kbd_bl_led_enable, level ? 1 : 0);
 	return 0;
 }
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index b0e50ca9398a7..c6228843a1a7b 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -326,8 +326,8 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip,
 }
 EXPORT_SYMBOL_GPL(pwm_request_from_chip);
 
-static void pwm_apply_state_debug(struct pwm_device *pwm,
-				  const struct pwm_state *state)
+static void pwm_apply_debug(struct pwm_device *pwm,
+			    const struct pwm_state *state)
 {
 	struct pwm_state *last = &pwm->last;
 	struct pwm_chip *chip = pwm->chip;
@@ -433,11 +433,11 @@ static void pwm_apply_state_debug(struct pwm_device *pwm,
 }
 
 /**
- * pwm_apply_state() - atomically apply a new state to a PWM device
+ * pwm_apply_might_sleep() - atomically apply a new state to a PWM device
  * @pwm: PWM device
  * @state: new state to apply
  */
-int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
+int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state)
 {
 	struct pwm_chip *chip;
 	int err;
@@ -445,7 +445,7 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
 	/*
 	 * Some lowlevel driver's implementations of .apply() make use of
 	 * mutexes, also with some drivers only returning when the new
-	 * configuration is active calling pwm_apply_state() from atomic context
+	 * configuration is active calling pwm_apply_might_sleep() from atomic context
 	 * is a bad idea. So make it explicit that calling this function might
 	 * sleep.
 	 */
@@ -475,11 +475,11 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
 	 * only do this after pwm->state was applied as some
 	 * implementations of .get_state depend on this
 	 */
-	pwm_apply_state_debug(pwm, state);
+	pwm_apply_debug(pwm, state);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(pwm_apply_state);
+EXPORT_SYMBOL_GPL(pwm_apply_might_sleep);
 
 /**
  * pwm_capture() - capture and report a PWM signal
@@ -537,7 +537,7 @@ int pwm_adjust_config(struct pwm_device *pwm)
 		state.period = pargs.period;
 		state.polarity = pargs.polarity;
 
-		return pwm_apply_state(pwm, &state);
+		return pwm_apply_might_sleep(pwm, &state);
 	}
 
 	/*
@@ -560,7 +560,7 @@ int pwm_adjust_config(struct pwm_device *pwm)
 		state.duty_cycle = state.period - state.duty_cycle;
 	}
 
-	return pwm_apply_state(pwm, &state);
+	return pwm_apply_might_sleep(pwm, &state);
 }
 EXPORT_SYMBOL_GPL(pwm_adjust_config);
 
diff --git a/drivers/pwm/pwm-twl-led.c b/drivers/pwm/pwm-twl-led.c
index 8a870d0db3c69..c670ccb816536 100644
--- a/drivers/pwm/pwm-twl-led.c
+++ b/drivers/pwm/pwm-twl-led.c
@@ -172,7 +172,7 @@ static int twl4030_pwmled_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * We cannot skip calling ->config even if state->period ==
 	 * pwm->state.period && state->duty_cycle == pwm->state.duty_cycle
 	 * because we might have exited early in the last call to
-	 * pwm_apply_state because of !state->enabled and so the two values in
+	 * pwm_apply_might_sleep because of !state->enabled and so the two values in
 	 * pwm->state might not be configured in hardware.
 	 */
 	ret = twl4030_pwmled_config(chip, pwm,
diff --git a/drivers/pwm/pwm-vt8500.c b/drivers/pwm/pwm-vt8500.c
index bdea60389487e..7bfeacee05d0f 100644
--- a/drivers/pwm/pwm-vt8500.c
+++ b/drivers/pwm/pwm-vt8500.c
@@ -206,7 +206,7 @@ static int vt8500_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * We cannot skip calling ->config even if state->period ==
 	 * pwm->state.period && state->duty_cycle == pwm->state.duty_cycle
 	 * because we might have exited early in the last call to
-	 * pwm_apply_state because of !state->enabled and so the two values in
+	 * pwm_apply_might_sleep because of !state->enabled and so the two values in
 	 * pwm->state might not be configured in hardware.
 	 */
 	err = vt8500_pwm_config(chip, pwm, state->duty_cycle, state->period);
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index 4edb994fa2e12..1698609d91c8a 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -62,7 +62,7 @@ static ssize_t period_store(struct device *child,
 	mutex_lock(&export->lock);
 	pwm_get_state(pwm, &state);
 	state.period = val;
-	ret = pwm_apply_state(pwm, &state);
+	ret = pwm_apply_might_sleep(pwm, &state);
 	mutex_unlock(&export->lock);
 
 	return ret ? : size;
@@ -97,7 +97,7 @@ static ssize_t duty_cycle_store(struct device *child,
 	mutex_lock(&export->lock);
 	pwm_get_state(pwm, &state);
 	state.duty_cycle = val;
-	ret = pwm_apply_state(pwm, &state);
+	ret = pwm_apply_might_sleep(pwm, &state);
 	mutex_unlock(&export->lock);
 
 	return ret ? : size;
@@ -144,7 +144,7 @@ static ssize_t enable_store(struct device *child,
 		goto unlock;
 	}
 
-	ret = pwm_apply_state(pwm, &state);
+	ret = pwm_apply_might_sleep(pwm, &state);
 
 unlock:
 	mutex_unlock(&export->lock);
@@ -194,7 +194,7 @@ static ssize_t polarity_store(struct device *child,
 	mutex_lock(&export->lock);
 	pwm_get_state(pwm, &state);
 	state.polarity = polarity;
-	ret = pwm_apply_state(pwm, &state);
+	ret = pwm_apply_might_sleep(pwm, &state);
 	mutex_unlock(&export->lock);
 
 	return ret ? : size;
@@ -401,7 +401,7 @@ static int pwm_class_apply_state(struct pwm_export *export,
 				 struct pwm_device *pwm,
 				 struct pwm_state *state)
 {
-	int ret = pwm_apply_state(pwm, state);
+	int ret = pwm_apply_might_sleep(pwm, state);
 
 	/* release lock taken in pwm_class_get_state */
 	mutex_unlock(&export->lock);
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 2aff6db748e2c..698c420e0869b 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -90,7 +90,7 @@ static int pwm_regulator_set_voltage_sel(struct regulator_dev *rdev,
 	pwm_set_relative_duty_cycle(&pstate,
 			drvdata->duty_cycle_table[selector].dutycycle, 100);
 
-	ret = pwm_apply_state(drvdata->pwm, &pstate);
+	ret = pwm_apply_might_sleep(drvdata->pwm, &pstate);
 	if (ret) {
 		dev_err(&rdev->dev, "Failed to configure PWM: %d\n", ret);
 		return ret;
@@ -216,7 +216,7 @@ static int pwm_regulator_set_voltage(struct regulator_dev *rdev,
 
 	pwm_set_relative_duty_cycle(&pstate, dutycycle, duty_unit);
 
-	ret = pwm_apply_state(drvdata->pwm, &pstate);
+	ret = pwm_apply_might_sleep(drvdata->pwm, &pstate);
 	if (ret) {
 		dev_err(&rdev->dev, "Failed to configure PWM: %d\n", ret);
 		return ret;
diff --git a/drivers/video/backlight/lm3630a_bl.c b/drivers/video/backlight/lm3630a_bl.c
index 8fcb62be597b8..a3412c936ca28 100644
--- a/drivers/video/backlight/lm3630a_bl.c
+++ b/drivers/video/backlight/lm3630a_bl.c
@@ -180,7 +180,7 @@ static int lm3630a_pwm_ctrl(struct lm3630a_chip *pchip, int br, int br_max)
 
 	pchip->pwmd_state.enabled = pchip->pwmd_state.duty_cycle ? true : false;
 
-	return pwm_apply_state(pchip->pwmd, &pchip->pwmd_state);
+	return pwm_apply_might_sleep(pchip->pwmd, &pchip->pwmd_state);
 }
 
 /* update and get brightness */
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index da1f124db69c0..7075bfab59c4d 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -234,7 +234,7 @@ static int lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
 	state.duty_cycle = div_u64(br * state.period, max_br);
 	state.enabled = state.duty_cycle;
 
-	return pwm_apply_state(lp->pwm, &state);
+	return pwm_apply_might_sleep(lp->pwm, &state);
 }
 
 static int lp855x_bl_update_status(struct backlight_device *bl)
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index 289bd9ce4d36d..35c716e9043c3 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -103,7 +103,7 @@ static int pwm_backlight_update_status(struct backlight_device *bl)
 		pwm_get_state(pb->pwm, &state);
 		state.duty_cycle = compute_duty_cycle(pb, brightness, &state);
 		state.enabled = true;
-		pwm_apply_state(pb->pwm, &state);
+		pwm_apply_might_sleep(pb->pwm, &state);
 
 		pwm_backlight_power_on(pb);
 	} else {
@@ -120,7 +120,7 @@ static int pwm_backlight_update_status(struct backlight_device *bl)
 		 * inactive output.
 		 */
 		state.enabled = !pb->power_supply && !pb->enable_gpio;
-		pwm_apply_state(pb->pwm, &state);
+		pwm_apply_might_sleep(pb->pwm, &state);
 	}
 
 	if (pb->notify_after)
@@ -528,7 +528,7 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	if (!state.period && (data->pwm_period_ns > 0))
 		state.period = data->pwm_period_ns;
 
-	ret = pwm_apply_state(pb->pwm, &state);
+	ret = pwm_apply_might_sleep(pb->pwm, &state);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
 			ret);
@@ -633,7 +633,7 @@ static void pwm_backlight_remove(struct platform_device *pdev)
 	pwm_get_state(pb->pwm, &state);
 	state.duty_cycle = 0;
 	state.enabled = false;
-	pwm_apply_state(pb->pwm, &state);
+	pwm_apply_might_sleep(pb->pwm, &state);
 
 	if (pb->exit)
 		pb->exit(&pdev->dev);
@@ -649,7 +649,7 @@ static void pwm_backlight_shutdown(struct platform_device *pdev)
 	pwm_get_state(pb->pwm, &state);
 	state.duty_cycle = 0;
 	state.enabled = false;
-	pwm_apply_state(pb->pwm, &state);
+	pwm_apply_might_sleep(pb->pwm, &state);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -673,7 +673,7 @@ static int pwm_backlight_suspend(struct device *dev)
 	pwm_get_state(pb->pwm, &state);
 	state.duty_cycle = 0;
 	state.enabled = false;
-	pwm_apply_state(pb->pwm, &state);
+	pwm_apply_might_sleep(pb->pwm, &state);
 
 	if (pb->notify_after)
 		pb->notify_after(pb->dev, 0);
diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c
index 5ae48e36fccb4..1a4f90ea7d5a8 100644
--- a/drivers/video/fbdev/ssd1307fb.c
+++ b/drivers/video/fbdev/ssd1307fb.c
@@ -347,7 +347,7 @@ static int ssd1307fb_init(struct ssd1307fb_par *par)
 
 		pwm_init_state(par->pwm, &pwmstate);
 		pwm_set_relative_duty_cycle(&pwmstate, 50, 100);
-		pwm_apply_state(par->pwm, &pwmstate);
+		pwm_apply_might_sleep(par->pwm, &pwmstate);
 
 		/* Enable the PWM */
 		pwm_enable(par->pwm);
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index f87655c06c825..b64b8a82415c4 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -92,8 +92,8 @@ struct pwm_device {
  * @state: state to fill with the current PWM state
  *
  * The returned PWM state represents the state that was applied by a previous call to
- * pwm_apply_state(). Drivers may have to slightly tweak that state before programming it to
- * hardware. If pwm_apply_state() was never called, this returns either the current hardware
+ * pwm_apply_might_sleep(). Drivers may have to slightly tweak that state before programming it to
+ * hardware. If pwm_apply_might_sleep() was never called, this returns either the current hardware
  * state (if supported) or the default settings.
  */
 static inline void pwm_get_state(const struct pwm_device *pwm,
@@ -157,20 +157,20 @@ static inline void pwm_get_args(const struct pwm_device *pwm,
 }
 
 /**
- * pwm_init_state() - prepare a new state to be applied with pwm_apply_state()
+ * pwm_init_state() - prepare a new state to be applied with pwm_apply_might_sleep()
  * @pwm: PWM device
  * @state: state to fill with the prepared PWM state
  *
  * This functions prepares a state that can later be tweaked and applied
- * to the PWM device with pwm_apply_state(). This is a convenient function
+ * to the PWM device with pwm_apply_might_sleep(). This is a convenient function
  * that first retrieves the current PWM state and the replaces the period
  * and polarity fields with the reference values defined in pwm->args.
  * Once the function returns, you can adjust the ->enabled and ->duty_cycle
- * fields according to your needs before calling pwm_apply_state().
+ * fields according to your needs before calling pwm_apply_might_sleep().
  *
  * ->duty_cycle is initially set to zero to avoid cases where the current
  * ->duty_cycle value exceed the pwm_args->period one, which would trigger
- * an error if the user calls pwm_apply_state() without adjusting ->duty_cycle
+ * an error if the user calls pwm_apply_might_sleep() without adjusting ->duty_cycle
  * first.
  */
 static inline void pwm_init_state(const struct pwm_device *pwm,
@@ -226,7 +226,7 @@ pwm_get_relative_duty_cycle(const struct pwm_state *state, unsigned int scale)
  *
  * pwm_init_state(pwm, &state);
  * pwm_set_relative_duty_cycle(&state, 50, 100);
- * pwm_apply_state(pwm, &state);
+ * pwm_apply_might_sleep(pwm, &state);
  *
  * This functions returns -EINVAL if @duty_cycle and/or @scale are
  * inconsistent (@scale == 0 or @duty_cycle > @scale).
@@ -304,7 +304,7 @@ struct pwm_chip {
 
 #if IS_ENABLED(CONFIG_PWM)
 /* PWM user APIs */
-int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state);
+int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state);
 int pwm_adjust_config(struct pwm_device *pwm);
 
 /**
@@ -332,7 +332,7 @@ static inline int pwm_config(struct pwm_device *pwm, int duty_ns,
 
 	state.duty_cycle = duty_ns;
 	state.period = period_ns;
-	return pwm_apply_state(pwm, &state);
+	return pwm_apply_might_sleep(pwm, &state);
 }
 
 /**
@@ -353,7 +353,7 @@ static inline int pwm_enable(struct pwm_device *pwm)
 		return 0;
 
 	state.enabled = true;
-	return pwm_apply_state(pwm, &state);
+	return pwm_apply_might_sleep(pwm, &state);
 }
 
 /**
@@ -372,7 +372,7 @@ static inline void pwm_disable(struct pwm_device *pwm)
 		return;
 
 	state.enabled = false;
-	pwm_apply_state(pwm, &state);
+	pwm_apply_might_sleep(pwm, &state);
 }
 
 /* PWM provider APIs */
@@ -403,8 +403,8 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev,
 				       struct fwnode_handle *fwnode,
 				       const char *con_id);
 #else
-static inline int pwm_apply_state(struct pwm_device *pwm,
-				  const struct pwm_state *state)
+static inline int pwm_apply_might_sleep(struct pwm_device *pwm,
+					const struct pwm_state *state)
 {
 	might_sleep();
 	return -ENOTSUPP;
@@ -521,7 +521,7 @@ static inline void pwm_apply_args(struct pwm_device *pwm)
 	state.period = pwm->args.period;
 	state.usage_power = false;
 
-	pwm_apply_state(pwm, &state);
+	pwm_apply_might_sleep(pwm, &state);
 }
 
 struct pwm_lookup {
-- 
GitLab


From dc518b378dced419baa95d76a85f4c8c405722bc Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 19 Dec 2023 16:30:25 +0000
Subject: [PATCH 1678/4076] pwm: Replace ENOTSUPP with EOPNOTSUPP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to Documentation/dev-tools/checkpatch.rst ENOTSUPP is
not recommended and EOPNOTSUPP should be used instead.

Signed-off-by: Sean Young <sean@mess.org>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index b64b8a82415c4..c9cb87b59ac80 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -407,12 +407,12 @@ static inline int pwm_apply_might_sleep(struct pwm_device *pwm,
 					const struct pwm_state *state)
 {
 	might_sleep();
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int pwm_adjust_config(struct pwm_device *pwm)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int pwm_config(struct pwm_device *pwm, int duty_ns,
-- 
GitLab


From 752193da3f8b0aa819a27fc741d46ab046be315e Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 19 Dec 2023 16:30:26 +0000
Subject: [PATCH 1679/4076] pwm: renesas: Remove unused include
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

No mutex is used in this driver.

Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-renesas-tpu.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pwm/pwm-renesas-tpu.c b/drivers/pwm/pwm-renesas-tpu.c
index ce92db1f85113..28265fdfc92a9 100644
--- a/drivers/pwm/pwm-renesas-tpu.c
+++ b/drivers/pwm/pwm-renesas-tpu.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
-- 
GitLab


From 7170d3beafc2373dd76b6b5d6e617d89e4e42b8b Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 19 Dec 2023 16:30:27 +0000
Subject: [PATCH 1680/4076] pwm: Make it possible to apply PWM changes in
 atomic context
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some PWM devices require sleeping, for example if the pwm device is
connected over I2C. However, many PWM devices could be used from atomic
context, e.g. memory mapped PWM. This is useful for, for example, the
pwm-ir-tx driver which requires precise timing. Sleeping causes havoc
with the generated IR signal.

Since not all PWM devices can support atomic context, we also add a
pwm_might_sleep() function to check if is not supported.

Signed-off-by: Sean Young <sean@mess.org>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 Documentation/driver-api/pwm.rst |  9 +++++
 MAINTAINERS                      |  2 +-
 drivers/pwm/core.c               | 62 ++++++++++++++++++++++++++------
 include/linux/pwm.h              | 25 +++++++++++++
 4 files changed, 86 insertions(+), 12 deletions(-)

diff --git a/Documentation/driver-api/pwm.rst b/Documentation/driver-api/pwm.rst
index f1d8197c8c430..3c28ccc4b6113 100644
--- a/Documentation/driver-api/pwm.rst
+++ b/Documentation/driver-api/pwm.rst
@@ -46,6 +46,15 @@ After being requested, a PWM has to be configured using::
 This API controls both the PWM period/duty_cycle config and the
 enable/disable state.
 
+PWM devices can be used from atomic context, if the PWM does not sleep. You
+can check if this the case with::
+
+        bool pwm_might_sleep(struct pwm_device *pwm);
+
+If false, the PWM can also be configured from atomic context with::
+
+	int pwm_apply_atomic(struct pwm_device *pwm, struct pwm_state *state);
+
 As a consumer, don't rely on the output's state for a disabled PWM. If it's
 easily possible, drivers are supposed to emit the inactive state, but some
 drivers cannot. If you rely on getting the inactive state, use .duty_cycle=0,
diff --git a/MAINTAINERS b/MAINTAINERS
index c584805952209..5342cf32d73ff 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17576,7 +17576,7 @@ F:	drivers/video/backlight/pwm_bl.c
 F:	include/dt-bindings/pwm/
 F:	include/linux/pwm.h
 F:	include/linux/pwm_backlight.h
-K:	pwm_(config|apply_might_sleep|ops)
+K:	pwm_(config|apply_might_sleep|apply_atomic|ops)
 
 PXA GPIO DRIVER
 M:	Robert Jarzmik <robert.jarzmik@free.fr>
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index c6228843a1a7b..f1ded8ce5ea45 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -433,24 +433,15 @@ static void pwm_apply_debug(struct pwm_device *pwm,
 }
 
 /**
- * pwm_apply_might_sleep() - atomically apply a new state to a PWM device
+ * __pwm_apply() - atomically apply a new state to a PWM device
  * @pwm: PWM device
  * @state: new state to apply
  */
-int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state)
+static int __pwm_apply(struct pwm_device *pwm, const struct pwm_state *state)
 {
 	struct pwm_chip *chip;
 	int err;
 
-	/*
-	 * Some lowlevel driver's implementations of .apply() make use of
-	 * mutexes, also with some drivers only returning when the new
-	 * configuration is active calling pwm_apply_might_sleep() from atomic context
-	 * is a bad idea. So make it explicit that calling this function might
-	 * sleep.
-	 */
-	might_sleep();
-
 	if (!pwm || !state || !state->period ||
 	    state->duty_cycle > state->period)
 		return -EINVAL;
@@ -479,8 +470,57 @@ int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state)
 
 	return 0;
 }
+
+/**
+ * pwm_apply_might_sleep() - atomically apply a new state to a PWM device
+ * Cannot be used in atomic context.
+ * @pwm: PWM device
+ * @state: new state to apply
+ */
+int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state)
+{
+	int err;
+
+	/*
+	 * Some lowlevel driver's implementations of .apply() make use of
+	 * mutexes, also with some drivers only returning when the new
+	 * configuration is active calling pwm_apply_might_sleep() from atomic context
+	 * is a bad idea. So make it explicit that calling this function might
+	 * sleep.
+	 */
+	might_sleep();
+
+	if (IS_ENABLED(CONFIG_PWM_DEBUG) && pwm->chip->atomic) {
+		/*
+		 * Catch any drivers that have been marked as atomic but
+		 * that will sleep anyway.
+		 */
+		non_block_start();
+		err = __pwm_apply(pwm, state);
+		non_block_end();
+	} else {
+		err = __pwm_apply(pwm, state);
+	}
+
+	return err;
+}
 EXPORT_SYMBOL_GPL(pwm_apply_might_sleep);
 
+/**
+ * pwm_apply_atomic() - apply a new state to a PWM device from atomic context
+ * Not all PWM devices support this function, check with pwm_might_sleep().
+ * @pwm: PWM device
+ * @state: new state to apply
+ */
+int pwm_apply_atomic(struct pwm_device *pwm, const struct pwm_state *state)
+{
+	WARN_ONCE(!pwm->chip->atomic,
+		  "sleeping PWM driver used in atomic context\n");
+
+	return __pwm_apply(pwm, state);
+}
+EXPORT_SYMBOL_GPL(pwm_apply_atomic);
+
 /**
  * pwm_capture() - capture and report a PWM signal
  * @pwm: PWM device
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index c9cb87b59ac80..495af3627939c 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -285,6 +285,7 @@ struct pwm_ops {
  * @npwm: number of PWMs controlled by this chip
  * @of_xlate: request a PWM device given a device tree PWM specifier
  * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier
+ * @atomic: can the driver's ->apply() be called in atomic context
  * @pwms: array of PWM devices allocated by the framework
  */
 struct pwm_chip {
@@ -297,6 +298,7 @@ struct pwm_chip {
 	struct pwm_device * (*of_xlate)(struct pwm_chip *chip,
 					const struct of_phandle_args *args);
 	unsigned int of_pwm_n_cells;
+	bool atomic;
 
 	/* only used internally by the PWM framework */
 	struct pwm_device *pwms;
@@ -305,6 +307,7 @@ struct pwm_chip {
 #if IS_ENABLED(CONFIG_PWM)
 /* PWM user APIs */
 int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state);
+int pwm_apply_atomic(struct pwm_device *pwm, const struct pwm_state *state);
 int pwm_adjust_config(struct pwm_device *pwm);
 
 /**
@@ -375,6 +378,17 @@ static inline void pwm_disable(struct pwm_device *pwm)
 	pwm_apply_might_sleep(pwm, &state);
 }
 
+/**
+ * pwm_might_sleep() - is pwm_apply_atomic() supported?
+ * @pwm: PWM device
+ *
+ * Returns: false if pwm_apply_atomic() can be called from atomic context.
+ */
+static inline bool pwm_might_sleep(struct pwm_device *pwm)
+{
+	return !pwm->chip->atomic;
+}
+
 /* PWM provider APIs */
 int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result,
 		unsigned long timeout);
@@ -403,6 +417,11 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev,
 				       struct fwnode_handle *fwnode,
 				       const char *con_id);
 #else
+static inline bool pwm_might_sleep(struct pwm_device *pwm)
+{
+	return true;
+}
+
 static inline int pwm_apply_might_sleep(struct pwm_device *pwm,
 					const struct pwm_state *state)
 {
@@ -410,6 +429,12 @@ static inline int pwm_apply_might_sleep(struct pwm_device *pwm,
 	return -EOPNOTSUPP;
 }
 
+static inline int pwm_apply_atomic(struct pwm_device *pwm,
+				   const struct pwm_state *state)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int pwm_adjust_config(struct pwm_device *pwm)
 {
 	return -EOPNOTSUPP;
-- 
GitLab


From daca194876a94565194f6e32ddb0355af8cf30f7 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 20 Dec 2023 10:24:56 +0200
Subject: [PATCH 1681/4076] vfio/virtio: Declare virtiovf_pci_aer_reset_done()
 static

Declare virtiovf_pci_aer_reset_done() as a static function to prevent
the below build warning.

"warning: no previous prototype for 'virtiovf_pci_aer_reset_done'
[-Wmissing-prototypes]"

Fixes: eb61eca0e8c3 ("vfio/virtio: Introduce a vfio driver over virtio devices")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/lkml/20231220143122.63337669@canb.auug.org.au/
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231220082456.241973-1-yishaih@nvidia.com
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312202115.oDmvN1VE-lkp@intel.com/
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/virtio/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c
index 291c55b641f15..d5af683837d34 100644
--- a/drivers/vfio/pci/virtio/main.c
+++ b/drivers/vfio/pci/virtio/main.c
@@ -547,7 +547,7 @@ static const struct pci_device_id virtiovf_pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, virtiovf_pci_table);
 
-void virtiovf_pci_aer_reset_done(struct pci_dev *pdev)
+static void virtiovf_pci_aer_reset_done(struct pci_dev *pdev)
 {
 	struct virtiovf_pci_core_device *virtvdev = dev_get_drvdata(&pdev->dev);
 
-- 
GitLab


From fcc76072935935082efa127b97c7ddd880d2d793 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Wed, 20 Dec 2023 14:24:25 +0000
Subject: [PATCH 1682/4076] pwm: bcm2835: Allow PWM driver to be used in atomic
 context

clk_get_rate() may do a mutex lock. Fetch the clock rate once, and prevent
rate changes using clk_rate_exclusive_get().

Signed-off-by: Sean Young <sean@mess.org>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-bcm2835.c | 38 +++++++++++++++++++++++++++++---------
 1 file changed, 29 insertions(+), 9 deletions(-)

diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c
index ab30667f4f951..307c0bd5f8855 100644
--- a/drivers/pwm/pwm-bcm2835.c
+++ b/drivers/pwm/pwm-bcm2835.c
@@ -28,6 +28,7 @@ struct bcm2835_pwm {
 	struct device *dev;
 	void __iomem *base;
 	struct clk *clk;
+	unsigned long rate;
 };
 
 static inline struct bcm2835_pwm *to_bcm2835_pwm(struct pwm_chip *chip)
@@ -63,17 +64,11 @@ static int bcm2835_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 {
 
 	struct bcm2835_pwm *pc = to_bcm2835_pwm(chip);
-	unsigned long rate = clk_get_rate(pc->clk);
 	unsigned long long period_cycles;
 	u64 max_period;
 
 	u32 val;
 
-	if (!rate) {
-		dev_err(pc->dev, "failed to get clock rate\n");
-		return -EINVAL;
-	}
-
 	/*
 	 * period_cycles must be a 32 bit value, so period * rate / NSEC_PER_SEC
 	 * must be <= U32_MAX. As U32_MAX * NSEC_PER_SEC < U64_MAX the
@@ -88,13 +83,13 @@ static int bcm2835_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * <=> period < ((U32_MAX * NSEC_PER_SEC + NSEC_PER_SEC/2) / rate
 	 * <=> period <= ceil((U32_MAX * NSEC_PER_SEC + NSEC_PER_SEC/2) / rate) - 1
 	 */
-	max_period = DIV_ROUND_UP_ULL((u64)U32_MAX * NSEC_PER_SEC + NSEC_PER_SEC / 2, rate) - 1;
+	max_period = DIV_ROUND_UP_ULL((u64)U32_MAX * NSEC_PER_SEC + NSEC_PER_SEC / 2, pc->rate) - 1;
 
 	if (state->period > max_period)
 		return -EINVAL;
 
 	/* set period */
-	period_cycles = DIV_ROUND_CLOSEST_ULL(state->period * rate, NSEC_PER_SEC);
+	period_cycles = DIV_ROUND_CLOSEST_ULL(state->period * pc->rate, NSEC_PER_SEC);
 
 	/* don't accept a period that is too small */
 	if (period_cycles < PERIOD_MIN)
@@ -103,7 +98,7 @@ static int bcm2835_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	writel(period_cycles, pc->base + PERIOD(pwm->hwpwm));
 
 	/* set duty cycle */
-	val = DIV_ROUND_CLOSEST_ULL(state->duty_cycle * rate, NSEC_PER_SEC);
+	val = DIV_ROUND_CLOSEST_ULL(state->duty_cycle * pc->rate, NSEC_PER_SEC);
 	writel(val, pc->base + DUTY(pwm->hwpwm));
 
 	/* set polarity */
@@ -131,6 +126,13 @@ static const struct pwm_ops bcm2835_pwm_ops = {
 	.apply = bcm2835_pwm_apply,
 };
 
+static void devm_clk_rate_exclusive_put(void *data)
+{
+	struct clk *clk = data;
+
+	clk_rate_exclusive_put(clk);
+}
+
 static int bcm2835_pwm_probe(struct platform_device *pdev)
 {
 	struct bcm2835_pwm *pc;
@@ -151,8 +153,26 @@ static int bcm2835_pwm_probe(struct platform_device *pdev)
 		return dev_err_probe(&pdev->dev, PTR_ERR(pc->clk),
 				     "clock not found\n");
 
+	ret = clk_rate_exclusive_get(pc->clk);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "fail to get exclusive rate\n");
+
+	ret = devm_add_action_or_reset(&pdev->dev, devm_clk_rate_exclusive_put,
+				       pc->clk);
+	if (ret) {
+		clk_rate_exclusive_put(pc->clk);
+		return ret;
+	}
+
+	pc->rate = clk_get_rate(pc->clk);
+	if (!pc->rate)
+		return dev_err_probe(&pdev->dev, -EINVAL,
+				     "failed to get clock rate\n");
+
 	pc->chip.dev = &pdev->dev;
 	pc->chip.ops = &bcm2835_pwm_ops;
+	pc->chip.atomic = true;
 	pc->chip.npwm = 2;
 
 	platform_set_drvdata(pdev, pc);
-- 
GitLab


From 363d0e56285e80cda997d41d94c22313b673557d Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 19 Dec 2023 16:30:29 +0000
Subject: [PATCH 1683/4076] media: pwm-ir-tx: Trigger edges from hrtimer
 interrupt context

This makes the generated IR much more precise. Before this change, the
driver is unreliable and many users opted to use gpio-ir-tx instead.

Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/media/rc/pwm-ir-tx.c | 83 +++++++++++++++++++++++++++++++++---
 1 file changed, 78 insertions(+), 5 deletions(-)

diff --git a/drivers/media/rc/pwm-ir-tx.c b/drivers/media/rc/pwm-ir-tx.c
index cf51e27609759..fe368aebbc139 100644
--- a/drivers/media/rc/pwm-ir-tx.c
+++ b/drivers/media/rc/pwm-ir-tx.c
@@ -10,6 +10,8 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/hrtimer.h>
+#include <linux/completion.h>
 #include <media/rc-core.h>
 
 #define DRIVER_NAME	"pwm-ir-tx"
@@ -17,8 +19,14 @@
 
 struct pwm_ir {
 	struct pwm_device *pwm;
-	unsigned int carrier;
-	unsigned int duty_cycle;
+	struct hrtimer timer;
+	struct completion tx_done;
+	struct pwm_state *state;
+	u32 carrier;
+	u32 duty_cycle;
+	const unsigned int *txbuf;
+	unsigned int txbuf_len;
+	unsigned int txbuf_index;
 };
 
 static const struct of_device_id pwm_ir_of_match[] = {
@@ -49,8 +57,8 @@ static int pwm_ir_set_carrier(struct rc_dev *dev, u32 carrier)
 	return 0;
 }
 
-static int pwm_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
-		     unsigned int count)
+static int pwm_ir_tx_sleep(struct rc_dev *dev, unsigned int *txbuf,
+			   unsigned int count)
 {
 	struct pwm_ir *pwm_ir = dev->priv;
 	struct pwm_device *pwm = pwm_ir->pwm;
@@ -82,6 +90,62 @@ static int pwm_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
 	return count;
 }
 
+static int pwm_ir_tx_atomic(struct rc_dev *dev, unsigned int *txbuf,
+			    unsigned int count)
+{
+	struct pwm_ir *pwm_ir = dev->priv;
+	struct pwm_device *pwm = pwm_ir->pwm;
+	struct pwm_state state;
+
+	pwm_init_state(pwm, &state);
+
+	state.period = DIV_ROUND_CLOSEST(NSEC_PER_SEC, pwm_ir->carrier);
+	pwm_set_relative_duty_cycle(&state, pwm_ir->duty_cycle, 100);
+
+	pwm_ir->txbuf = txbuf;
+	pwm_ir->txbuf_len = count;
+	pwm_ir->txbuf_index = 0;
+	pwm_ir->state = &state;
+
+	hrtimer_start(&pwm_ir->timer, 0, HRTIMER_MODE_REL);
+
+	wait_for_completion(&pwm_ir->tx_done);
+
+	return count;
+}
+
+static enum hrtimer_restart pwm_ir_timer(struct hrtimer *timer)
+{
+	struct pwm_ir *pwm_ir = container_of(timer, struct pwm_ir, timer);
+	ktime_t now;
+
+	/*
+	 * If we happen to hit an odd latency spike, loop through the
+	 * pulses until we catch up.
+	 */
+	do {
+		u64 ns;
+
+		pwm_ir->state->enabled = !(pwm_ir->txbuf_index % 2);
+		pwm_apply_atomic(pwm_ir->pwm, pwm_ir->state);
+
+		if (pwm_ir->txbuf_index >= pwm_ir->txbuf_len) {
+			complete(&pwm_ir->tx_done);
+
+			return HRTIMER_NORESTART;
+		}
+
+		ns = US_TO_NS(pwm_ir->txbuf[pwm_ir->txbuf_index]);
+		hrtimer_add_expires_ns(timer, ns);
+
+		pwm_ir->txbuf_index++;
+
+		now = timer->base->get_time();
+	} while (hrtimer_get_expires_tv64(timer) < now);
+
+	return HRTIMER_RESTART;
+}
+
 static int pwm_ir_probe(struct platform_device *pdev)
 {
 	struct pwm_ir *pwm_ir;
@@ -103,10 +167,19 @@ static int pwm_ir_probe(struct platform_device *pdev)
 	if (!rcdev)
 		return -ENOMEM;
 
+	if (pwm_might_sleep(pwm_ir->pwm)) {
+		dev_info(&pdev->dev, "TX will not be accurate as PWM device might sleep\n");
+		rcdev->tx_ir = pwm_ir_tx_sleep;
+	} else {
+		init_completion(&pwm_ir->tx_done);
+		hrtimer_init(&pwm_ir->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		pwm_ir->timer.function = pwm_ir_timer;
+		rcdev->tx_ir = pwm_ir_tx_atomic;
+	}
+
 	rcdev->priv = pwm_ir;
 	rcdev->driver_name = DRIVER_NAME;
 	rcdev->device_name = DEVICE_NAME;
-	rcdev->tx_ir = pwm_ir_tx;
 	rcdev->s_tx_duty_cycle = pwm_ir_set_duty_cycle;
 	rcdev->s_tx_carrier = pwm_ir_set_carrier;
 
-- 
GitLab


From 4a6b93f5629668d1dc8fa5945657fdd124629c55 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Mon, 6 Nov 2023 12:37:47 +0100
Subject: [PATCH 1684/4076] dt-bindings: riscv: cpus: Add AMD MicroBlaze V
 compatible

MicroBlaze V is new AMD/Xilinx soft-core 32bit RISC-V processor IP.
It is hardware compatible with classic MicroBlaze processor.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/d442d916204d26f82c1c3a924a4cdfb117960e1b.1699270661.git.michal.simek@amd.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/cpus.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index f392e367d673f..23646b684ea27 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -32,6 +32,7 @@ properties:
     oneOf:
       - items:
           - enum:
+              - amd,mbv32
               - andestech,ax45mp
               - canaan,k210
               - sifive,bullet0
-- 
GitLab


From 46cfec2a865ae967ea4366287a7d9a16ad5b8b6f Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 14 Nov 2023 10:27:06 +0200
Subject: [PATCH 1685/4076] dt-bindings: pwm: ti,pwm-omap-dmtimer: Update
 binding for yaml
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Update for yaml and remove the old txt binding.

As we can replace most of the custom timer API with standard Linux
frameworks such as clock framework, let's tag the properties for
ti,prescaler and ti,clock-source as deprecated.

Cc:  <linux-pwm@vger.kernel.org>
Cc: Nishanth Menon <nm@ti.com>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 .../bindings/pwm/pwm-omap-dmtimer.txt         | 22 -------
 .../bindings/pwm/ti,omap-dmtimer-pwm.yaml     | 59 +++++++++++++++++++
 2 files changed, 59 insertions(+), 22 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt
 create mode 100644 Documentation/devicetree/bindings/pwm/ti,omap-dmtimer-pwm.yaml

diff --git a/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt b/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt
deleted file mode 100644
index 25ecfe14c6989..0000000000000
--- a/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt
+++ /dev/null
@@ -1,22 +0,0 @@
-* OMAP PWM for dual-mode timers
-
-Required properties:
-- compatible: Shall contain "ti,omap-dmtimer-pwm".
-- ti,timers: phandle to PWM capable OMAP timer. See timer/ti,timer-dm.yaml for info
-  about these timers.
-- #pwm-cells: Should be 3. See pwm.yaml in this directory for a description of
-  the cells format.
-
-Optional properties:
-- ti,prescaler: Should be a value between 0 and 7, see the timers datasheet
-- ti,clock-source: Set dmtimer parent clock, values between 0 and 2:
-  - 0x00 - high-frequency system clock (timer_sys_ck)
-  - 0x01 - 32-kHz always-on clock (timer_32k_ck)
-  - 0x02 - external clock (timer_ext_ck, OMAP2 only)
-
-Example:
-	pwm9: dmtimer-pwm@9 {
-		compatible = "ti,omap-dmtimer-pwm";
-		ti,timers = <&timer9>;
-		#pwm-cells = <3>;
-	};
diff --git a/Documentation/devicetree/bindings/pwm/ti,omap-dmtimer-pwm.yaml b/Documentation/devicetree/bindings/pwm/ti,omap-dmtimer-pwm.yaml
new file mode 100644
index 0000000000000..1e8e094aad74b
--- /dev/null
+++ b/Documentation/devicetree/bindings/pwm/ti,omap-dmtimer-pwm.yaml
@@ -0,0 +1,59 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pwm/ti,omap-dmtimer-pwm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TI dual mode timer PWM controller
+
+maintainers:
+  - Tony Lindgren <tony@atomide.com>
+
+description:
+  TI dual mode timer instances have an IO pin for PWM capability
+
+allOf:
+  - $ref: pwm.yaml#
+
+properties:
+  compatible:
+    const: ti,omap-dmtimer-pwm
+
+  "#pwm-cells":
+    const: 3
+
+  ti,timers:
+    description: Timer instance phandle for the PWM
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+  ti,prescaler:
+    description: |
+      Legacy clock prescaler for timer. The timer counter is prescaled
+      with 2^n where n is the prescaler.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [ 0, 1, 2, 3, 4, 5, 6, 7 ]
+    deprecated: true
+
+  ti,clock-source:
+    description: |
+      Legacy clock for timer, please use assigned-clocks instead.
+      0x00 - high-frequency system clock (timer_sys_ck)
+      0x01 - 32-kHz always-on clock (timer_32k_ck)
+      0x02 - external clock (timer_ext_ck, OMAP2 only)
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [ 0, 1, 2 ]
+    deprecated: true
+
+required:
+  - compatible
+  - ti,timers
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    pwm9: pwm {
+      compatible = "ti,omap-dmtimer-pwm";
+      ti,timers = <&timer9>;
+      #pwm-cells = <3>;
+    };
-- 
GitLab


From 01b571fbbac40bfc266c03e84ab9a8ab2ddd2486 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 5 Dec 2023 10:56:17 +0100
Subject: [PATCH 1686/4076] pwm: omap-dmtimer: Drop locking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pwm driver only provides a single PWM line, so there are no concurrent
calls of the callbacks from different consumers. A single consumer is
expected not to do concurrent calls into the pwm framework. So there is
nothing to serialize and the lock can go away.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-omap-dmtimer.c | 20 ++++----------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c
index 13161e08dd6eb..496bd73d29fe1 100644
--- a/drivers/pwm/pwm-omap-dmtimer.c
+++ b/drivers/pwm/pwm-omap-dmtimer.c
@@ -37,7 +37,6 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <clocksource/timer-ti-dm.h>
@@ -55,7 +54,6 @@
  * struct pwm_omap_dmtimer_chip - Structure representing a pwm chip
  *				  corresponding to omap dmtimer.
  * @chip:		PWM chip structure representing PWM controller
- * @mutex:		Mutex to protect pwm apply state
  * @dm_timer:		Pointer to omap dm timer.
  * @pdata:		Pointer to omap dm timer ops.
  * @dm_timer_pdev:	Pointer to omap dm timer platform device
@@ -63,7 +61,6 @@
 struct pwm_omap_dmtimer_chip {
 	struct pwm_chip chip;
 	/* Mutex to protect pwm apply state */
-	struct mutex mutex;
 	struct omap_dm_timer *dm_timer;
 	const struct omap_dm_timer_ops *pdata;
 	struct platform_device *dm_timer_pdev;
@@ -277,13 +274,11 @@ static int pwm_omap_dmtimer_apply(struct pwm_chip *chip,
 				  const struct pwm_state *state)
 {
 	struct pwm_omap_dmtimer_chip *omap = to_pwm_omap_dmtimer_chip(chip);
-	int ret = 0;
-
-	mutex_lock(&omap->mutex);
+	int ret;
 
 	if (pwm_omap_dmtimer_is_enabled(omap) && !state->enabled) {
 		omap->pdata->stop(omap->dm_timer);
-		goto unlock_mutex;
+		return 0;
 	}
 
 	if (pwm_omap_dmtimer_polarity(omap) != state->polarity)
@@ -292,7 +287,7 @@ static int pwm_omap_dmtimer_apply(struct pwm_chip *chip,
 	ret = pwm_omap_dmtimer_config(chip, pwm, state->duty_cycle,
 				      state->period);
 	if (ret)
-		goto unlock_mutex;
+		return ret;
 
 	if (!pwm_omap_dmtimer_is_enabled(omap) && state->enabled) {
 		omap->pdata->set_pwm(omap->dm_timer,
@@ -303,10 +298,7 @@ static int pwm_omap_dmtimer_apply(struct pwm_chip *chip,
 		pwm_omap_dmtimer_start(omap);
 	}
 
-unlock_mutex:
-	mutex_unlock(&omap->mutex);
-
-	return ret;
+	return 0;
 }
 
 static const struct pwm_ops pwm_omap_dmtimer_ops = {
@@ -404,8 +396,6 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 	omap->chip.ops = &pwm_omap_dmtimer_ops;
 	omap->chip.npwm = 1;
 
-	mutex_init(&omap->mutex);
-
 	ret = pwmchip_add(&omap->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to register PWM\n");
@@ -452,8 +442,6 @@ static void pwm_omap_dmtimer_remove(struct platform_device *pdev)
 	omap->pdata->free(omap->dm_timer);
 
 	put_device(&omap->dm_timer_pdev->dev);
-
-	mutex_destroy(&omap->mutex);
 }
 
 static const struct of_device_id pwm_omap_dmtimer_of_match[] = {
-- 
GitLab


From d243221dc9e202d85ca196136d8eaa029091b42c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 30 Nov 2023 08:41:34 +0100
Subject: [PATCH 1687/4076] pwm: crc: Use consistent variable naming for driver
 data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All but one local variable of type pointer to struct crystalcove_pwm are
called "crc_pwm", the one outlier is called "pwm" which is usually
reserved for variables of type pointer to struct pwm_device.

So rename that one "pwm" to "crc_pwm" for consistency.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-crc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/pwm/pwm-crc.c b/drivers/pwm/pwm-crc.c
index 2b0b659eee979..e09358901ab50 100644
--- a/drivers/pwm/pwm-crc.c
+++ b/drivers/pwm/pwm-crc.c
@@ -160,22 +160,22 @@ static const struct pwm_ops crc_pwm_ops = {
 
 static int crystalcove_pwm_probe(struct platform_device *pdev)
 {
-	struct crystalcove_pwm *pwm;
+	struct crystalcove_pwm *crc_pwm;
 	struct device *dev = pdev->dev.parent;
 	struct intel_soc_pmic *pmic = dev_get_drvdata(dev);
 
-	pwm = devm_kzalloc(&pdev->dev, sizeof(*pwm), GFP_KERNEL);
-	if (!pwm)
+	crc_pwm = devm_kzalloc(&pdev->dev, sizeof(*crc_pwm), GFP_KERNEL);
+	if (!crc_pwm)
 		return -ENOMEM;
 
-	pwm->chip.dev = &pdev->dev;
-	pwm->chip.ops = &crc_pwm_ops;
-	pwm->chip.npwm = 1;
+	crc_pwm->chip.dev = &pdev->dev;
+	crc_pwm->chip.ops = &crc_pwm_ops;
+	crc_pwm->chip.npwm = 1;
 
 	/* get the PMIC regmap */
-	pwm->regmap = pmic->regmap;
+	crc_pwm->regmap = pmic->regmap;
 
-	return devm_pwmchip_add(&pdev->dev, &pwm->chip);
+	return devm_pwmchip_add(&pdev->dev, &crc_pwm->chip);
 }
 
 static struct platform_driver crystalcove_pwm_driver = {
-- 
GitLab


From efb704abedc7168cee8068da08eb2ca8c1eb1893 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Thu, 30 Nov 2023 08:21:06 +0100
Subject: [PATCH 1688/4076] pwm: Reduce number of pointer dereferences in
 pwm_device_request()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pwm->chip and pwm->chip->ops are used several times in this function.
Introduce local variables for these.

There is no semantical change, but with ARCH=arm, allmodconfig and
gcc-13 bloat-o-meter reports a slight improvement:

	add/remove: 1/1 grow/shrink: 1/1 up/down: 8/-36 (-28)
	Function                                     old     new   delta
	pwm_apply_state                              476     480      +4
	__initcall__kmod_core__307_1092_pwm_debugfs_init4       -       4      +4
	__initcall__kmod_core__307_1090_pwm_debugfs_init4       4       -      -4
	pwm_request_from_chip                        628     596     -32
	Total: Before=15091, After=15063, chg -0.19%

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index f1ded8ce5ea45..9a4c720c88aad 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -59,22 +59,24 @@ static struct pwm_chip *pwmchip_find_by_name(const char *name)
 static int pwm_device_request(struct pwm_device *pwm, const char *label)
 {
 	int err;
+	struct pwm_chip *chip = pwm->chip;
+	const struct pwm_ops *ops = chip->ops;
 
 	if (test_bit(PWMF_REQUESTED, &pwm->flags))
 		return -EBUSY;
 
-	if (!try_module_get(pwm->chip->owner))
+	if (!try_module_get(chip->owner))
 		return -ENODEV;
 
-	if (pwm->chip->ops->request) {
-		err = pwm->chip->ops->request(pwm->chip, pwm);
+	if (ops->request) {
+		err = ops->request(chip, pwm);
 		if (err) {
-			module_put(pwm->chip->owner);
+			module_put(chip->owner);
 			return err;
 		}
 	}
 
-	if (pwm->chip->ops->get_state) {
+	if (ops->get_state) {
 		/*
 		 * Zero-initialize state because most drivers are unaware of
 		 * .usage_power. The other members of state are supposed to be
@@ -84,7 +86,7 @@ static int pwm_device_request(struct pwm_device *pwm, const char *label)
 		 */
 		struct pwm_state state = { 0, };
 
-		err = pwm->chip->ops->get_state(pwm->chip, pwm, &state);
+		err = ops->get_state(chip, pwm, &state);
 		trace_pwm_get(pwm, &state, err);
 
 		if (!err)
-- 
GitLab


From d9eb24c6f499bf8f6625c5fea05d7511a2fecf52 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 6 Dec 2023 18:30:43 +0100
Subject: [PATCH 1689/4076] pwm: stmpe: Silence duplicate error messages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

stmpe_reg_read() and stmpe_reg_write() already emit error messages when
they fail. So the extra error messages in the pwm driver are only little
useful. They are useful in some situation, as they give a bit of context
to the failing register write. So don't remove them but degrade them to
dev_dbg().

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-stmpe.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/pwm/pwm-stmpe.c b/drivers/pwm/pwm-stmpe.c
index d730631c6583a..19c0c0f39675d 100644
--- a/drivers/pwm/pwm-stmpe.c
+++ b/drivers/pwm/pwm-stmpe.c
@@ -44,7 +44,7 @@ static int stmpe_24xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 
 	ret = stmpe_reg_read(stmpe_pwm->stmpe, STMPE24XX_PWMCS);
 	if (ret < 0) {
-		dev_err(chip->dev, "error reading PWM#%u control\n",
+		dev_dbg(chip->dev, "error reading PWM#%u control\n",
 			pwm->hwpwm);
 		return ret;
 	}
@@ -53,7 +53,7 @@ static int stmpe_24xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 
 	ret = stmpe_reg_write(stmpe_pwm->stmpe, STMPE24XX_PWMCS, value);
 	if (ret) {
-		dev_err(chip->dev, "error writing PWM#%u control\n",
+		dev_dbg(chip->dev, "error writing PWM#%u control\n",
 			pwm->hwpwm);
 		return ret;
 	}
@@ -70,7 +70,7 @@ static int stmpe_24xx_pwm_disable(struct pwm_chip *chip,
 
 	ret = stmpe_reg_read(stmpe_pwm->stmpe, STMPE24XX_PWMCS);
 	if (ret < 0) {
-		dev_err(chip->dev, "error reading PWM#%u control\n",
+		dev_dbg(chip->dev, "error reading PWM#%u control\n",
 			pwm->hwpwm);
 		return ret;
 	}
@@ -79,7 +79,7 @@ static int stmpe_24xx_pwm_disable(struct pwm_chip *chip,
 
 	ret = stmpe_reg_write(stmpe_pwm->stmpe, STMPE24XX_PWMCS, value);
 	if (ret)
-		dev_err(chip->dev, "error writing PWM#%u control\n",
+		dev_dbg(chip->dev, "error writing PWM#%u control\n",
 			pwm->hwpwm);
 	return ret;
 }
@@ -233,7 +233,7 @@ static int stmpe_24xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 
 		ret = stmpe_reg_write(stmpe_pwm->stmpe, offset, value);
 		if (ret) {
-			dev_err(chip->dev, "error writing register %02x: %d\n",
+			dev_dbg(chip->dev, "error writing register %02x: %d\n",
 				offset, ret);
 			return ret;
 		}
@@ -242,7 +242,7 @@ static int stmpe_24xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 
 		ret = stmpe_reg_write(stmpe_pwm->stmpe, offset, value);
 		if (ret) {
-			dev_err(chip->dev, "error writing register %02x: %d\n",
+			dev_dbg(chip->dev, "error writing register %02x: %d\n",
 				offset, ret);
 			return ret;
 		}
-- 
GitLab


From b41ccc3bc9da96678c1db31b9ed021b8388657f6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 6 Dec 2023 22:48:18 +0100
Subject: [PATCH 1690/4076] pwm: meson: Simplify using dev_err_probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using dev_err_probe() emitting an error message mentioning a return
value and returning that value can be done in a single statement. Make
use of that to simplify the probe part of the driver. This has the
additional advantage to emit the symbolic name for the error instead of
the integer error value.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-meson.c | 35 ++++++++++++++---------------------
 1 file changed, 14 insertions(+), 21 deletions(-)

diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c
index 5bea53243ed2f..2971bbf3b5e7c 100644
--- a/drivers/pwm/pwm-meson.c
+++ b/drivers/pwm/pwm-meson.c
@@ -468,10 +468,9 @@ static int meson_pwm_init_channels(struct meson_pwm *meson)
 		channel->mux.hw.init = &init;
 
 		err = devm_clk_hw_register(dev, &channel->mux.hw);
-		if (err) {
-			dev_err(dev, "failed to register %s: %d\n", name, err);
-			return err;
-		}
+		if (err)
+			return dev_err_probe(dev, err,
+					     "failed to register %s\n", name);
 
 		snprintf(name, sizeof(name), "%s#div%u", dev_name(dev), i);
 
@@ -491,10 +490,9 @@ static int meson_pwm_init_channels(struct meson_pwm *meson)
 		channel->div.lock = &meson->lock;
 
 		err = devm_clk_hw_register(dev, &channel->div.hw);
-		if (err) {
-			dev_err(dev, "failed to register %s: %d\n", name, err);
-			return err;
-		}
+		if (err)
+			return dev_err_probe(dev, err,
+					     "failed to register %s\n", name);
 
 		snprintf(name, sizeof(name), "%s#gate%u", dev_name(dev), i);
 
@@ -513,17 +511,13 @@ static int meson_pwm_init_channels(struct meson_pwm *meson)
 		channel->gate.lock = &meson->lock;
 
 		err = devm_clk_hw_register(dev, &channel->gate.hw);
-		if (err) {
-			dev_err(dev, "failed to register %s: %d\n", name, err);
-			return err;
-		}
+		if (err)
+			return dev_err_probe(dev, err, "failed to register %s\n", name);
 
 		channel->clk = devm_clk_hw_get_clk(dev, &channel->gate.hw, NULL);
-		if (IS_ERR(channel->clk)) {
-			err = PTR_ERR(channel->clk);
-			dev_err(dev, "failed to register %s: %d\n", name, err);
-			return err;
-		}
+		if (IS_ERR(channel->clk))
+			return dev_err_probe(dev, PTR_ERR(channel->clk),
+					     "failed to register %s\n", name);
 	}
 
 	return 0;
@@ -554,10 +548,9 @@ static int meson_pwm_probe(struct platform_device *pdev)
 		return err;
 
 	err = devm_pwmchip_add(&pdev->dev, &meson->chip);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to register PWM chip: %d\n", err);
-		return err;
-	}
+	if (err < 0)
+		return dev_err_probe(&pdev->dev, err,
+				     "failed to register PWM chip\n");
 
 	return 0;
 }
-- 
GitLab


From 4430d02dc1dfb811b0b39bb58662f006f1e4749d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 10 Dec 2023 00:00:46 +0100
Subject: [PATCH 1691/4076] pwm: lpc18xx-sct: Don't modify the cached period of
 other PWM outputs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Even though the hardware only supports a single period for all PWM
outputs, modifying the other (disabled) outputs's period is strange and
wrong. Only the pwm core is supposed to update these values.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-lpc18xx-sct.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/pwm/pwm-lpc18xx-sct.c b/drivers/pwm/pwm-lpc18xx-sct.c
index b3d4a955aa311..fe891fa71a1dd 100644
--- a/drivers/pwm/pwm-lpc18xx-sct.c
+++ b/drivers/pwm/pwm-lpc18xx-sct.c
@@ -194,7 +194,7 @@ static int lpc18xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 			      int duty_ns, int period_ns)
 {
 	struct lpc18xx_pwm_chip *lpc18xx_pwm = to_lpc18xx_pwm_chip(chip);
-	int requested_events, i;
+	int requested_events;
 
 	if (period_ns < lpc18xx_pwm->min_period_ns ||
 	    period_ns > lpc18xx_pwm->max_period_ns) {
@@ -223,8 +223,6 @@ static int lpc18xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	if ((requested_events <= 2 && lpc18xx_pwm->period_ns != period_ns) ||
 	    !lpc18xx_pwm->period_ns) {
 		lpc18xx_pwm->period_ns = period_ns;
-		for (i = 0; i < chip->npwm; i++)
-			pwm_set_period(&chip->pwms[i], period_ns);
 		lpc18xx_pwm_config_period(chip, period_ns);
 	}
 
-- 
GitLab


From 80e4a9987999e682366d60f43a7b2adefc48e222 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sun, 10 Dec 2023 00:00:47 +0100
Subject: [PATCH 1692/4076] pwm: Drop two unused API functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These functions are unused. Also I think there is no valid use case
where these are correct to be called. So drop them.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 495af3627939c..5dd665d8c909e 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -111,12 +111,6 @@ static inline bool pwm_is_enabled(const struct pwm_device *pwm)
 	return state.enabled;
 }
 
-static inline void pwm_set_period(struct pwm_device *pwm, u64 period)
-{
-	if (pwm)
-		pwm->state.period = period;
-}
-
 static inline u64 pwm_get_period(const struct pwm_device *pwm)
 {
 	struct pwm_state state;
@@ -126,12 +120,6 @@ static inline u64 pwm_get_period(const struct pwm_device *pwm)
 	return state.period;
 }
 
-static inline void pwm_set_duty_cycle(struct pwm_device *pwm, unsigned int duty)
-{
-	if (pwm)
-		pwm->state.duty_cycle = duty;
-}
-
 static inline u64 pwm_get_duty_cycle(const struct pwm_device *pwm)
 {
 	struct pwm_state state;
-- 
GitLab


From e43c64c971e48d11ee100c5a8b2eadbed056f924 Mon Sep 17 00:00:00 2001
From: Veronika Molnarova <vmolnaro@redhat.com>
Date: Tue, 12 Dec 2023 17:59:09 +0100
Subject: [PATCH 1693/4076] perf archive: Add new option '--unpack' to expand
 tarballs

Archives generated by the command 'perf archive' have to be unpacked
manually.

Following the addition of option '--all' now there also exist a nested
structure of tars, and after further discussion with Red Hat Global
Support Services, they found a feature correctly unpacking archives of
'perf archive' convenient.

Option '--unpack' of 'perf archive' unpacks archives generated by the
command 'perf archive' as well as archives generated when used with
option '--all'.

The 'perf.data' file is placed in the current directory, while debug
symbols are unpacked in '~/.debug' directory. A tar filename can be
passed as an argument, and if not provided the command tries to find a
viable perf.tar file for unpacking.

Signed-off-by: Veronika Molnarova <vmolnaro@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Link: https://lore.kernel.org/r/20231212165909.14459-2-vmolnaro@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/perf-archive.sh | 66 +++++++++++++++++++++++++++++++++-----
 1 file changed, 58 insertions(+), 8 deletions(-)

diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index a92042eae95a1..f94795794b361 100755
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -7,17 +7,72 @@ PERF_DATA=perf.data
 PERF_SYMBOLS=perf.symbols
 PERF_ALL=perf.all
 ALL=0
+UNPACK=0
 
 while [ $# -gt 0 ] ; do
 	if [ $1 == "--all" ]; then
 		ALL=1
 		shift
+	elif [ $1 == "--unpack" ]; then
+		UNPACK=1
+		shift
 	else
 		PERF_DATA=$1
+		UNPACK_TAR=$1
 		shift
 	fi
 done
 
+if [ $UNPACK -eq 1 ]; then
+	if [ ! -z "$UNPACK_TAR" ]; then					# tar given as an argument
+		if [ ! -e "$UNPACK_TAR" ]; then
+			echo "Provided file $UNPACK_TAR does not exist"
+			exit 1
+		fi
+		TARGET="$UNPACK_TAR"
+	else																# search for perf tar in the current directory
+		TARGET=`find . -regex "\./perf.*\.tar\.bz2"`
+		TARGET_NUM=`echo -n "$TARGET" | grep -c '^'`
+
+		if [ -z "$TARGET" -o $TARGET_NUM -gt 1 ]; then
+			echo -e "Error: $TARGET_NUM files found for unpacking:\n$TARGET"
+			echo "Provide the requested file as an argument"
+			exit 1
+		else
+			echo "Found target file for unpacking: $TARGET"
+		fi
+	fi
+
+	if [[ "$TARGET" =~ (\./)?$PERF_ALL.*.tar.bz2 ]]; then				# perf tar generated by --all option
+		TAR_CONTENTS=`tar tvf "$TARGET" | tr -s " " | cut -d " " -f 6`
+		VALID_TAR=`echo "$TAR_CONTENTS" | grep "$PERF_SYMBOLS.tar.bz2" | wc -l`		# check if it contains a sub-tar perf.symbols
+		if [ $VALID_TAR -ne 1 ]; then
+			echo "Error: $TARGET file is not valid (contains zero or multiple sub-tar files with debug symbols)"
+			exit 1
+		fi
+
+		INTERSECT=`comm -12 <(ls) <(echo "$TAR_CONTENTS") | tr "\n" " "`	# check for overwriting
+		if [ ! -z "$INTERSECT" ]; then										# prompt if file(s) already exist in the current directory
+			echo "File(s) ${INTERSECT::-1} already exist in the current directory."
+			while true; do
+				read -p 'Do you wish to overwrite them? ' yn
+				case $yn in
+					[Yy]* ) break;;
+					[Nn]* ) exit 1;;
+					* ) echo "Please answer yes or no.";;
+				esac
+			done
+		fi
+
+		# unzip the perf.data file in the current working directory	and debug symbols in ~/.debug directory
+		tar xvf $TARGET && tar xvf $PERF_SYMBOLS.tar.bz2 -C ~/.debug
+
+	else																# perf tar generated by perf archive (contains only debug symbols)
+		tar xvf $TARGET -C ~/.debug
+	fi
+	exit 0
+fi
+
 #
 # PERF_BUILDID_DIR environment variable set by perf
 # path to buildid directory, default to $HOME/.debug
@@ -55,17 +110,12 @@ if [ $ALL -eq 1 ]; then						# pack perf.data file together with tar containing
 	tar cjf $PERF_SYMBOLS.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
 	tar cjf	$PERF_ALL-$HOSTNAME-$DATE.tar.bz2 $PERF_DATA $PERF_SYMBOLS.tar.bz2
 	rm $PERF_SYMBOLS.tar.bz2 $MANIFEST $BUILDIDS || true
-
-	echo -e "Now please run:\n"
-	echo -e "$ tar xvf $PERF_ALL-$HOSTNAME-$DATE.tar.bz2 && tar xvf $PERF_SYMBOLS.tar.bz2 -C ~/.debug\n"
-	echo "wherever you need to run 'perf report' on."
 else										# pack only the debug symbols
 	tar cjf $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
 	rm $MANIFEST $BUILDIDS || true
-
-	echo -e "Now please run:\n"
-	echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
-	echo "wherever you need to run 'perf report' on."
 fi
 
+echo -e "Now please run:\n"
+echo -e "$ perf archive --unpack\n"
+echo "or unpack the tar manually wherever you need to run 'perf report' on."
 exit 0
-- 
GitLab


From 0647537df442e0ec818fc0bca347f13c11268202 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 19 Dec 2023 13:30:15 +0000
Subject: [PATCH 1694/4076] tools/counter: Fix spelling mistake "componend" ->
 "component"

There are two spelling mistakes in the help text. Fix them.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Link: https://lore.kernel.org/r/20231219133015.365943-1-colin.i.king@gmail.com
Signed-off-by: William Breathitt Gray <william.gray@linaro.org>
---
 tools/counter/counter_watch_events.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/counter/counter_watch_events.c b/tools/counter/counter_watch_events.c
index 3898fe7e35ece..37d1b4b3e63df 100644
--- a/tools/counter/counter_watch_events.c
+++ b/tools/counter/counter_watch_events.c
@@ -120,8 +120,8 @@ static void print_usage(void)
 		"  evt_capture                (COUNTER_EVENT_CAPTURE)\n"
 		"\n"
 		"  chan=<n>                   channel <n> for this watch [default: 0]\n"
-		"  id=<n>                     componend id <n> for this watch [default: 0]\n"
-		"  parent=<n>                 componend parent <n> for this watch [default: 0]\n"
+		"  id=<n>                     component id <n> for this watch [default: 0]\n"
+		"  parent=<n>                 component parent <n> for this watch [default: 0]\n"
 		"\n"
 		"Example with two watched events:\n\n"
 		"counter_watch_events -d \\\n"
-- 
GitLab


From b7760cf94d4f2665bf40d08dd69aa5d0b4aa593f Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Wed, 20 Dec 2023 08:51:43 +0800
Subject: [PATCH 1695/4076] tools/counter: Remove unneeded semicolon

./tools/counter/counter_watch_events.c:233:3-4: Unneeded semicolon
./tools/counter/counter_watch_events.c:234:2-3: Unneeded semicolon
./tools/counter/counter_watch_events.c:333:2-3: Unneeded semicolon

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=7782
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Link: https://lore.kernel.org/r/20231220005143.84987-1-yang.lee@linux.alibaba.com
Signed-off-by: William Breathitt Gray <william.gray@linaro.org>
---
 tools/counter/counter_watch_events.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/counter/counter_watch_events.c b/tools/counter/counter_watch_events.c
index 37d1b4b3e63df..107631e0f2e31 100644
--- a/tools/counter/counter_watch_events.c
+++ b/tools/counter/counter_watch_events.c
@@ -230,8 +230,8 @@ int main(int argc, char **argv)
 			break;
 		default:
 			return EXIT_FAILURE;
-		};
-	};
+		}
+	}
 
 	if (nwatch) {
 		watches = calloc(nwatch, sizeof(*watches));
@@ -330,7 +330,7 @@ int main(int argc, char **argv)
 			i++;
 			break;
 		}
-	};
+	}
 
 	if (debug)
 		print_watch(watches, nwatch);
-- 
GitLab


From 881791886bfa8e353c3203f95bfbaaeee25d2d50 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 07:33:17 +0100
Subject: [PATCH 1696/4076] pwm: cros-ec: Drop documentation for dropped struct
 member
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Recently an unused member was removed from struct cros_ec_pwm_device,
but the kernel doc wasn't adapted accordingly. Catch up and drop the
documentation, too.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312190757.O4M9dsln-lkp@intel.com/
Fixes: 6c4406ce609f ("pwm: cros-ec: Drop unused member from driver private data")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/pwm-cros-ec.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c
index 9a8f1b6a4e136..5fe303b8656de 100644
--- a/drivers/pwm/pwm-cros-ec.c
+++ b/drivers/pwm/pwm-cros-ec.c
@@ -18,7 +18,6 @@
 /**
  * struct cros_ec_pwm_device - Driver data for EC PWM
  *
- * @dev: Device node
  * @ec: Pointer to EC device
  * @chip: PWM controller chip
  * @use_pwm_type: Use PWM types instead of generic channels
-- 
GitLab


From c344675ad267040b1794b0b5d85147a5023c548d Mon Sep 17 00:00:00 2001
From: Ruidong Tian <tianruidong@linux.alibaba.com>
Date: Thu, 14 Dec 2023 20:33:03 +0800
Subject: [PATCH 1697/4076] perf scripts python arm-cs-trace-disasm.py: Set
 start vm addr of exectable file to 0

For exectable ELF file, which e_type is ET_EXEC, dso start address is a
absolute address other than offset. Just set vm_start to zero when dso
start is 0x400000, which means it is a exectable file.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Grant <al.grant@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Tor Jeremiassen <tor@ti.com>
Link: https://lore.kernel.org/r/20231214123304.34087-3-tianruidong@linux.alibaba.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/arm-cs-trace-disasm.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index de58991c78bb4..e33aee5c78d72 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -258,8 +258,9 @@ def process_event(param_dict):
 
 	if (options.objdump_name != None):
 		# It doesn't need to decrease virtual memory offset for disassembly
-		# for kernel dso, so in this case we set vm_start to zero.
-		if (dso == "[kernel.kallsyms]"):
+		# for kernel dso and executable file dso, so in this case we set
+		# vm_start to zero.
+		if (dso == "[kernel.kallsyms]" or dso_start == 0x400000):
 			dso_vm_start = 0
 		else:
 			dso_vm_start = int(dso_start)
-- 
GitLab


From 2d98dbb4c9c5b09c8d2411581ab17921f872dbd3 Mon Sep 17 00:00:00 2001
From: Ruidong Tian <tianruidong@linux.alibaba.com>
Date: Thu, 14 Dec 2023 20:33:04 +0800
Subject: [PATCH 1698/4076] perf scripts python arm-cs-trace-disasm.py: Do not
 ignore disam first sample

arm-cs-trace-disasm ignore disam the first branch sample, For example as
follow, the instructions beteween 0x0000ffffae878750 and
0x0000ffffae878754 is lose:

  ARM CoreSight Trace Data Assembler Dump
  Event type: branches:uH
  Sample = { cpu: 0000 addr: 0x0000ffffae878750 phys_addr: 0x0000000000000000 ip: 0x0000000000000000 pid: 4003489 tid: 4003489 period: 1 time: 26765151766034 }
  Event type: branches:uH
  Sample = { cpu: 0000 addr: 0x0000000000000000 phys_addr: 0x0000000000000000 ip: 0x0000ffffae878754 pid: 4003489 tid: 4003489 period: 1 time: 26765151766034 }

Initialize cpu_data earlier to fix it:

  ARM CoreSight Trace Data Assembler Dump
  Event type: branches:uH
  Sample = { cpu: 0000 addr: 0x0000000000000000 phys_addr: 0x0000000000000000 ip: 0x0000ffffae878754 pid: 4003489 tid: 4003489 period: 1 time: 26765151766034 }
        0000000000028740 <ioctl>: (base address is 0x0000ffffae850000)
           28750: b13ffc1f      cmn     x0, #4095
           28754: 54000042      b.hs    0x2875c <ioctl+0x1c>
            test 4003489/4003489 [0000]     26765.151766034  __GI___ioctl+0x14                        /usr/lib64/libc-2.32.so
  Event type: branches:uH
  Sample = { cpu: 0000 addr: 0x0000ffffa67535ac phys_addr: 0x0000000000000000 ip: 0x0000000000000000 pid: 4003489 tid: 4003489 period: 1 time: 26765151766034 }

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ruidong Tian <tianruidong@linux.alibaba.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Grant <al.grant@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Tor Jeremiassen <tor@ti.com>
Link: https://lore.kernel.org/r/20231214123304.34087-4-tianruidong@linux.alibaba.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../scripts/python/arm-cs-trace-disasm.py     | 21 ++++++++++---------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index e33aee5c78d72..d973c2baed1c8 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -188,6 +188,17 @@ def process_event(param_dict):
 	dso_end = get_optional(param_dict, "dso_map_end")
 	symbol = get_optional(param_dict, "symbol")
 
+	cpu = sample["cpu"]
+	ip = sample["ip"]
+	addr = sample["addr"]
+
+	# Initialize CPU data if it's empty, and directly return back
+	# if this is the first tracing event for this CPU.
+	if (cpu_data.get(str(cpu) + 'addr') == None):
+		cpu_data[str(cpu) + 'addr'] = addr
+		return
+
+
 	if (options.verbose == True):
 		print("Event type: %s" % name)
 		print_sample(sample)
@@ -209,16 +220,6 @@ def process_event(param_dict):
 	if (name[0:8] != "branches"):
 		return
 
-	cpu = sample["cpu"]
-	ip = sample["ip"]
-	addr = sample["addr"]
-
-	# Initialize CPU data if it's empty, and directly return back
-	# if this is the first tracing event for this CPU.
-	if (cpu_data.get(str(cpu) + 'addr') == None):
-		cpu_data[str(cpu) + 'addr'] = addr
-		return
-
 	# The format for packet is:
 	#
 	#		  +------------+------------+------------+
-- 
GitLab


From 16f533ade706d33e60324ff32e526bda20bccbd9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:45 -0800
Subject: [PATCH 1699/4076] perf unwind: Use function to add missing maps lock

Switch read_unwind_spec_eh_frame() from loop macro
maps__for_each_entry() to maps__for_each_map() function that takes a
callback. The function holds the maps lock, which should be held during
iteration.

Committer notes:

Fixed up conflict with:

  4fb54994b2360ab5 ("perf unwind-libunwind: Fix base address for .eh_frame")

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: changbin du <changbin.du@huawei.com>
Cc: colin ian king <colin.i.king@gmail.com>
Cc: dmitrii dolgov <9erthalion6@gmail.com>
Cc: guilherme amadio <amadio@gentoo.org>
Cc: huacai chen <chenhuacai@kernel.org>
Cc: k prateek nayak <kprateek.nayak@amd.com>
Cc: li dong <lidong@vivo.com>
Cc: liam howlett <liam.howlett@oracle.com>
Cc: miguel ojeda <ojeda@kernel.org>
Cc: ming wang <wangming01@loongson.cn>
Cc: sean christopherson <seanjc@google.com>
Cc: vincent whitchurch <vincent.whitchurch@axis.com>
Link: http://lore.kernel.org/lkml/20231207011722.1220634-12-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/unwind-libunwind-local.c | 34 +++++++++++++++++-------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 5e5c3395a4998..dac536e28360a 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -302,12 +302,31 @@ static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
 	return 0;
 }
 
+struct read_unwind_spec_eh_frame_maps_cb_args {
+	struct dso *dso;
+	u64 base_addr;
+};
+
+static int read_unwind_spec_eh_frame_maps_cb(struct map *map, void *data)
+{
+
+	struct read_unwind_spec_eh_frame_maps_cb_args *args = data;
+
+	if (map__dso(map) == args->dso && map__start(map) - map__pgoff(map) < args->base_addr)
+		args->base_addr = map__start(map) - map__pgoff(map);
+
+	return 0;
+}
+
+
 static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 				     u64 *table_data, u64 *segbase,
 				     u64 *fde_count)
 {
-	struct map_rb_node *map_node;
-	u64 base_addr = UINT64_MAX;
+	struct read_unwind_spec_eh_frame_maps_cb_args args = {
+		.dso = dso,
+		.base_addr = UINT64_MAX,
+	};
 	int ret, fd;
 
 	if (dso->data.eh_frame_hdr_offset == 0) {
@@ -325,16 +344,11 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 			return -EINVAL;
 	}
 
-	maps__for_each_entry(thread__maps(ui->thread), map_node) {
-		struct map *map = map_node->map;
-		u64 start = map__start(map) - map__pgoff(map);
+	maps__for_each_map(thread__maps(ui->thread), read_unwind_spec_eh_frame_maps_cb, &args);
 
-		if (map__dso(map) == dso && start < base_addr)
-			base_addr = start;
-	}
-	base_addr -= dso->data.elf_base_addr;
+	args.base_addr -= dso->data.elf_base_addr;
 	/* Address of .eh_frame_hdr */
-	*segbase = base_addr + dso->data.eh_frame_hdr_addr;
+	*segbase = args.base_addr + dso->data.eh_frame_hdr_addr;
 	ret = unwind_spec_ehframe(dso, ui->machine, dso->data.eh_frame_hdr_offset,
 				   table_data, fde_count);
 	if (ret)
-- 
GitLab


From 51ab715e2bf037cd0525494b7ed496c46e4013c6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:46 -0800
Subject: [PATCH 1700/4076] perf vdso: Use function to add missing maps lock

Switch machine__thread_dso_type() from loop macro maps__for_each_entry()
to maps__for_each_map() function that takes a callback. The function
holds the maps lock, which should be held during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-13-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/vdso.c | 35 +++++++++++++++++++++++------------
 1 file changed, 23 insertions(+), 12 deletions(-)

diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index ae3eee69b659c..df8963796187d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -140,23 +140,34 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	return dso;
 }
 
+struct machine__thread_dso_type_maps_cb_args {
+	struct machine *machine;
+	enum dso_type dso_type;
+};
+
+static int machine__thread_dso_type_maps_cb(struct map *map, void *data)
+{
+	struct machine__thread_dso_type_maps_cb_args *args = data;
+	struct dso *dso = map__dso(map);
+
+	if (!dso || dso->long_name[0] != '/')
+		return 0;
+
+	args->dso_type = dso__type(dso, args->machine);
+	return (args->dso_type != DSO__TYPE_UNKNOWN) ? 1 : 0;
+}
+
 static enum dso_type machine__thread_dso_type(struct machine *machine,
 					      struct thread *thread)
 {
-	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
-	struct map_rb_node *rb_node;
-
-	maps__for_each_entry(thread__maps(thread), rb_node) {
-		struct dso *dso = map__dso(rb_node->map);
+	struct machine__thread_dso_type_maps_cb_args args = {
+		.machine = machine,
+		.dso_type = DSO__TYPE_UNKNOWN,
+	};
 
-		if (!dso || dso->long_name[0] != '/')
-			continue;
-		dso_type = dso__type(dso, machine);
-		if (dso_type != DSO__TYPE_UNKNOWN)
-			break;
-	}
+	maps__for_each_map(thread__maps(thread), machine__thread_dso_type_maps_cb, &args);
 
-	return dso_type;
+	return args.dso_type;
 }
 
 #if BITS_PER_LONG == 64
-- 
GitLab


From 9cce3a161e17b5c1d50de75e85c1aeb7452d17e6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:47 -0800
Subject: [PATCH 1701/4076] perf maps: Reduce scope of maps__for_each_entry()

Reduce scope of maps__for_each_entry() as maps__for_each_map() is a safer
alternative holding the maps lock during iteration.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-14-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/maps.c | 3 +++
 tools/perf/util/maps.h | 3 ---
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 160a6dce54bb6..00e6589bba10d 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -10,6 +10,9 @@
 #include "ui/ui.h"
 #include "unwind.h"
 
+#define maps__for_each_entry(maps, map) \
+	for (map = maps__first(maps); map; map = map_rb_node__next(map))
+
 static void maps__init(struct maps *maps, struct machine *machine)
 {
 	refcount_set(maps__refcnt(maps), 1);
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 14ad959792577..8ac30cdaf5bd1 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -36,9 +36,6 @@ struct map_rb_node *map_rb_node__next(struct map_rb_node *node);
 struct map_rb_node *maps__find_node(struct maps *maps, struct map *map);
 struct map *maps__find(struct maps *maps, u64 addr);
 
-#define maps__for_each_entry(maps, map) \
-	for (map = maps__first(maps); map; map = map_rb_node__next(map))
-
 #define maps__for_each_entry_safe(maps, map, next) \
 	for (map = maps__first(maps), next = map_rb_node__next(map); map; \
 	     map = next, next = map_rb_node__next(map))
-- 
GitLab


From 8d5847a61723b4dbb3da3b356925c4928ed14de2 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:48 -0800
Subject: [PATCH 1702/4076] perf maps: Add remove maps function to remove a map
 based on callback

Removing maps wasn't being done under the write lock. Similar to
maps__for_each_map(), iterate the entries but in this case remove the
entry based on the result of the callback. If an entry was removed
then maps_by_name() also needs updating, so add missed flush.

In dso__load_kcore(), the test of map to save would always be false with
REFCNT_CHECKING because of a missing RC_CHK_ACCESS/RC_CHK_EQUAL.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-15-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/maps.c   | 24 ++++++++++++++++++++++++
 tools/perf/util/maps.h   |  6 ++----
 tools/perf/util/symbol.c | 24 ++++++++++++------------
 3 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 00e6589bba10d..f13fd3a9686b1 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -13,6 +13,10 @@
 #define maps__for_each_entry(maps, map) \
 	for (map = maps__first(maps); map; map = map_rb_node__next(map))
 
+#define maps__for_each_entry_safe(maps, map, next) \
+	for (map = maps__first(maps), next = map_rb_node__next(map); map; \
+	     map = next, next = map_rb_node__next(map))
+
 static void maps__init(struct maps *maps, struct machine *machine)
 {
 	refcount_set(maps__refcnt(maps), 1);
@@ -214,6 +218,26 @@ int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data)
 	return ret;
 }
 
+void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data)
+{
+	struct map_rb_node *pos, *next;
+	unsigned int start_nr_maps;
+
+	down_write(maps__lock(maps));
+
+	start_nr_maps = maps__nr_maps(maps);
+	maps__for_each_entry_safe(maps, pos, next)	{
+		if (cb(pos->map, data)) {
+			__maps__remove(maps, pos);
+			--RC_CHK_ACCESS(maps)->nr_maps;
+		}
+	}
+	if (maps__maps_by_name(maps) && start_nr_maps != maps__nr_maps(maps))
+		__maps__free_maps_by_name(maps);
+
+	up_write(maps__lock(maps));
+}
+
 struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
 {
 	struct map *map = maps__find(maps, addr);
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 8ac30cdaf5bd1..b94ad5c8fea74 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -36,10 +36,6 @@ struct map_rb_node *map_rb_node__next(struct map_rb_node *node);
 struct map_rb_node *maps__find_node(struct maps *maps, struct map *map);
 struct map *maps__find(struct maps *maps, u64 addr);
 
-#define maps__for_each_entry_safe(maps, map, next) \
-	for (map = maps__first(maps), next = map_rb_node__next(map); map; \
-	     map = next, next = map_rb_node__next(map))
-
 DECLARE_RC_STRUCT(maps) {
 	struct rb_root      entries;
 	struct rw_semaphore lock;
@@ -80,6 +76,8 @@ static inline void __maps__zput(struct maps **map)
 
 /* Iterate over map calling cb for each entry. */
 int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data);
+/* Iterate over map removing an entry if cb returns true. */
+void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data);
 
 static inline struct rb_root *maps__entries(struct maps *maps)
 {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 72f03b875478a..be212ba157dc3 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1239,13 +1239,23 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
 	return 0;
 }
 
+static bool remove_old_maps(struct map *map, void *data)
+{
+	const struct map *map_to_save = data;
+
+	/*
+	 * We need to preserve eBPF maps even if they are covered by kcore,
+	 * because we need to access eBPF dso for source data.
+	 */
+	return !RC_CHK_EQUAL(map, map_to_save) && !__map__is_bpf_prog(map);
+}
+
 static int dso__load_kcore(struct dso *dso, struct map *map,
 			   const char *kallsyms_filename)
 {
 	struct maps *kmaps = map__kmaps(map);
 	struct kcore_mapfn_data md;
 	struct map *replacement_map = NULL;
-	struct map_rb_node *old_node, *next;
 	struct machine *machine;
 	bool is_64_bit;
 	int err, fd;
@@ -1292,17 +1302,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	}
 
 	/* Remove old maps */
-	maps__for_each_entry_safe(kmaps, old_node, next) {
-		struct map *old_map = old_node->map;
-
-		/*
-		 * We need to preserve eBPF maps even if they are
-		 * covered by kcore, because we need to access
-		 * eBPF dso for source data.
-		 */
-		if (old_map != map && !__map__is_bpf_prog(old_map))
-			maps__remove(kmaps, old_map);
-	}
+	maps__remove_maps(kmaps, remove_old_maps, map);
 	machine->trampolines_mapped = false;
 
 	/* Find the kernel map using the '_stext' symbol */
-- 
GitLab


From ec49230cf6dda70437bf878281566dd82af9affa Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:49 -0800
Subject: [PATCH 1703/4076] perf debug: Expose debug file

Some dumping call backs need to be passed a FILE*. Expose debug file
via an accessor API for a consistent way to do this. Catch the
unlikely failure of it not being set. Switch two cases where stderr
was being used instead of debug_file.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-16-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/debug.c | 22 +++++++++++++++-------
 tools/perf/util/debug.h |  1 +
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 88378c4c5dd9e..e282b4ceb4d25 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -38,12 +38,21 @@ bool dump_trace = false, quiet = false;
 int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
-static FILE *debug_file;
+static FILE *_debug_file;
 bool debug_display_time;
 
+FILE *debug_file(void)
+{
+	if (!_debug_file) {
+		pr_warning_once("debug_file not set");
+		debug_set_file(stderr);
+	}
+	return _debug_file;
+}
+
 void debug_set_file(FILE *file)
 {
-	debug_file = file;
+	_debug_file = file;
 }
 
 void debug_set_display_time(bool set)
@@ -78,8 +87,8 @@ int veprintf(int level, int var, const char *fmt, va_list args)
 		if (use_browser >= 1 && !redirect_to_stderr) {
 			ui_helpline__vshow(fmt, args);
 		} else {
-			ret = fprintf_time(debug_file);
-			ret += vfprintf(debug_file, fmt, args);
+			ret = fprintf_time(debug_file());
+			ret += vfprintf(debug_file(), fmt, args);
 		}
 	}
 
@@ -107,9 +116,8 @@ static int veprintf_time(u64 t, const char *fmt, va_list args)
 	nsecs -= secs  * NSEC_PER_SEC;
 	usecs  = nsecs / NSEC_PER_USEC;
 
-	ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
-		      secs, usecs);
-	ret += vfprintf(stderr, fmt, args);
+	ret = fprintf(debug_file(), "[%13" PRIu64 ".%06" PRIu64 "] ", secs, usecs);
+	ret += vfprintf(debug_file(), fmt, args);
 	return ret;
 }
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index f99468a7f6817..de8870980d44a 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -77,6 +77,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5)
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+FILE *debug_file(void);
 void debug_set_file(FILE *file);
 void debug_set_display_time(bool set);
 void perf_debug_setup(void);
-- 
GitLab


From 07ef14d50cf1af1caa49cd183216a517e75e8a93 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:50 -0800
Subject: [PATCH 1704/4076] perf maps: Refactor maps__fixup_overlappings()

Rename to maps__fixup_overlap_and_insert() as the given mapping is
always inserted. Factor out first_ending_after() as a utility
function. Minor variable name changes. Switch to using debug_file()
rather than passing a debug FILE*.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-17-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/maps.c   | 57 ++++++++++++++++++++++++----------------
 tools/perf/util/maps.h   |  2 +-
 tools/perf/util/thread.c |  3 +--
 3 files changed, 37 insertions(+), 25 deletions(-)

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index f13fd3a9686b1..94a97923527df 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -334,20 +334,16 @@ size_t maps__fprintf(struct maps *maps, FILE *fp)
 	return args.printed;
 }
 
-int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
+/*
+ * Find first map where end > map->start.
+ * Same as find_vma() in kernel.
+ */
+static struct rb_node *first_ending_after(struct maps *maps, const struct map *map)
 {
 	struct rb_root *root;
 	struct rb_node *next, *first;
-	int err = 0;
-
-	down_write(maps__lock(maps));
 
 	root = maps__entries(maps);
-
-	/*
-	 * Find first map where end > map->start.
-	 * Same as find_vma() in kernel.
-	 */
 	next = root->rb_node;
 	first = NULL;
 	while (next) {
@@ -361,8 +357,23 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 		} else
 			next = next->rb_right;
 	}
+	return first;
+}
+
+/*
+ * Adds new to maps, if new overlaps existing entries then the existing maps are
+ * adjusted or removed so that new fits without overlapping any entries.
+ */
+int maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
+{
+
+	struct rb_node *next;
+	int err = 0;
+	FILE *fp = debug_file();
+
+	down_write(maps__lock(maps));
 
-	next = first;
+	next = first_ending_after(maps, new);
 	while (next && !err) {
 		struct map_rb_node *pos = rb_entry(next, struct map_rb_node, rb_node);
 		next = rb_next(&pos->rb_node);
@@ -371,27 +382,27 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 		 * Stop if current map starts after map->end.
 		 * Maps are ordered by start: next will not overlap for sure.
 		 */
-		if (map__start(pos->map) >= map__end(map))
+		if (map__start(pos->map) >= map__end(new))
 			break;
 
 		if (verbose >= 2) {
 
 			if (use_browser) {
 				pr_debug("overlapping maps in %s (disable tui for more info)\n",
-					 map__dso(map)->name);
+					 map__dso(new)->name);
 			} else {
-				fputs("overlapping maps:\n", fp);
-				map__fprintf(map, fp);
+				pr_debug("overlapping maps:\n");
+				map__fprintf(new, fp);
 				map__fprintf(pos->map, fp);
 			}
 		}
 
-		rb_erase_init(&pos->rb_node, root);
+		rb_erase_init(&pos->rb_node, maps__entries(maps));
 		/*
 		 * Now check if we need to create new maps for areas not
 		 * overlapped by the new map:
 		 */
-		if (map__start(map) > map__start(pos->map)) {
+		if (map__start(new) > map__start(pos->map)) {
 			struct map *before = map__clone(pos->map);
 
 			if (before == NULL) {
@@ -399,7 +410,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 				goto put_map;
 			}
 
-			map__set_end(before, map__start(map));
+			map__set_end(before, map__start(new));
 			err = __maps__insert(maps, before);
 			if (err) {
 				map__put(before);
@@ -411,7 +422,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 			map__put(before);
 		}
 
-		if (map__end(map) < map__end(pos->map)) {
+		if (map__end(new) < map__end(pos->map)) {
 			struct map *after = map__clone(pos->map);
 
 			if (after == NULL) {
@@ -419,10 +430,10 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 				goto put_map;
 			}
 
-			map__set_start(after, map__end(map));
-			map__add_pgoff(after, map__end(map) - map__start(pos->map));
-			assert(map__map_ip(pos->map, map__end(map)) ==
-				map__map_ip(after, map__end(map)));
+			map__set_start(after, map__end(new));
+			map__add_pgoff(after, map__end(new) - map__start(pos->map));
+			assert(map__map_ip(pos->map, map__end(new)) ==
+				map__map_ip(after, map__end(new)));
 			err = __maps__insert(maps, after);
 			if (err) {
 				map__put(after);
@@ -436,6 +447,8 @@ put_map:
 		map__put(pos->map);
 		free(pos);
 	}
+	/* Add the map. */
+	err = __maps__insert(maps, new);
 	up_write(maps__lock(maps));
 	return err;
 }
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index b94ad5c8fea74..62e94d443c029 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -133,7 +133,7 @@ struct addr_map_symbol;
 
 int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams);
 
-int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp);
+int maps__fixup_overlap_and_insert(struct maps *maps, struct map *new);
 
 struct map *maps__find_by_name(struct maps *maps, const char *name);
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index b6986a81aa6df..3d47b5c5528b2 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -345,8 +345,7 @@ int thread__insert_map(struct thread *thread, struct map *map)
 	if (ret)
 		return ret;
 
-	maps__fixup_overlappings(thread__maps(thread), map, stderr);
-	return maps__insert(thread__maps(thread), map);
+	return maps__fixup_overlap_and_insert(thread__maps(thread), map);
 }
 
 struct thread__prepare_access_maps_cb_args {
-- 
GitLab


From 980d7927213a57c9a31ff4ea685eb93fbe4b31ab Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:51 -0800
Subject: [PATCH 1705/4076] perf maps: Do simple merge if given map doesn't
 overlap

Simplify merge in for the simple case of a non-overlapping map.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-18-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/maps.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 94a97923527df..f305a4834cf09 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -697,9 +697,20 @@ void maps__fixup_end(struct maps *maps)
 int maps__merge_in(struct maps *kmaps, struct map *new_map)
 {
 	struct map_rb_node *rb_node;
+	struct rb_node *first;
+	bool overlaps;
 	LIST_HEAD(merged);
 	int err = 0;
 
+	down_read(maps__lock(kmaps));
+	first = first_ending_after(kmaps, new_map);
+	rb_node = first ? rb_entry(first, struct map_rb_node, rb_node) : NULL;
+	overlaps = rb_node && map__start(rb_node->map) < map__end(new_map);
+	up_read(maps__lock(kmaps));
+
+	if (!overlaps)
+		return maps__insert(kmaps, new_map);
+
 	maps__for_each_entry(kmaps, rb_node) {
 		struct map *old_map = rb_node->map;
 
-- 
GitLab


From 9084952704ba075de28684301ec282b6626b5e7a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:52 -0800
Subject: [PATCH 1706/4076] perf maps: Rename clone to copy from

Rename maps__clone() to maps__copy_from() to be more intention revealing
of its behavior. Pass the underlying maps rather than the thread.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-19-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 2 +-
 tools/perf/util/maps.c    | 6 +-----
 tools/perf/util/maps.h    | 3 +--
 tools/perf/util/thread.c  | 2 +-
 4 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ca855fc435ac5..38bf7108821d3 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -453,7 +453,7 @@ static struct thread *findnew_guest_code(struct machine *machine,
 	 * Guest code can be found in hypervisor process at the same address
 	 * so copy host maps.
 	 */
-	err = maps__clone(thread, thread__maps(host_thread));
+	err = maps__copy_from(thread__maps(thread), thread__maps(host_thread));
 	thread__put(host_thread);
 	if (err)
 		goto out_err;
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index f305a4834cf09..986daa1b04978 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -453,12 +453,8 @@ put_map:
 	return err;
 }
 
-/*
- * XXX This should not really _copy_ te maps, but refcount them.
- */
-int maps__clone(struct thread *thread, struct maps *parent)
+int maps__copy_from(struct maps *maps, struct maps *parent)
 {
-	struct maps *maps = thread__maps(thread);
 	int err;
 	struct map_rb_node *rb_node;
 
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 62e94d443c029..e4a49d6ff5cfc 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -14,7 +14,6 @@ struct ref_reloc_sym;
 struct machine;
 struct map;
 struct maps;
-struct thread;
 
 struct map_rb_node {
 	struct rb_node rb_node;
@@ -61,7 +60,7 @@ struct kmap {
 
 struct maps *maps__new(struct machine *machine);
 bool maps__empty(struct maps *maps);
-int maps__clone(struct thread *thread, struct maps *parent);
+int maps__copy_from(struct maps *maps, struct maps *parent);
 
 struct maps *maps__get(struct maps *maps);
 void maps__put(struct maps *maps);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 3d47b5c5528b2..89c47a5098e28 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -390,7 +390,7 @@ static int thread__clone_maps(struct thread *thread, struct thread *parent, bool
 		return 0;
 	}
 	/* But this one is new process, copy maps. */
-	return do_maps_clone ? maps__clone(thread, thread__maps(parent)) : 0;
+	return do_maps_clone ? maps__copy_from(thread__maps(thread), thread__maps(parent)) : 0;
 }
 
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
-- 
GitLab


From e77b0236cd0cd1572c6a9b25097b207eab799e74 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:53 -0800
Subject: [PATCH 1707/4076] perf maps: Add maps__load_first()

Avoid bpf_lock_contention_read touching the internal maps data structure
by adding a helper function. As access is done directly on the map in
maps, hold the read lock to stop it being removed.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-20-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf_lock_contention.c |  2 +-
 tools/perf/util/maps.c                | 13 +++++++++++++
 tools/perf/util/maps.h                |  2 ++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index f1716c089c991..31ff19afc20c1 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -318,7 +318,7 @@ int lock_contention_read(struct lock_contention *con)
 	}
 
 	/* make sure it loads the kernel map */
-	map__load(maps__first(machine->kmaps)->map);
+	maps__load_first(machine->kmaps);
 
 	prev_key = NULL;
 	while (!bpf_map_get_next_key(fd, prev_key, &key)) {
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 986daa1b04978..024a6c9f72c40 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -793,3 +793,16 @@ out:
 	}
 	return err;
 }
+
+void maps__load_first(struct maps *maps)
+{
+	struct map_rb_node *first;
+
+	down_read(maps__lock(maps));
+
+	first = maps__first(maps);
+	if (first)
+		map__load(first->map);
+
+	up_read(maps__lock(maps));
+}
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index e4a49d6ff5cfc..b7ab3ec61b7c9 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -142,4 +142,6 @@ void __maps__sort_by_name(struct maps *maps);
 
 void maps__fixup_end(struct maps *maps);
 
+void maps__load_first(struct maps *maps);
+
 #endif // __PERF_MAPS_H
-- 
GitLab


From 75858007d101cf38e9a79d682d0361bb6493d7cc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:54 -0800
Subject: [PATCH 1708/4076] perf maps: Add find next entry to give entry after
 the given map

Use to remove map_rb_node use from machine.c.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-21-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c |  7 +++----
 tools/perf/util/maps.c    | 11 +++++++++++
 tools/perf/util/maps.h    |  2 ++
 3 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 38bf7108821d3..b397a769006f4 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1762,12 +1762,11 @@ int machine__create_kernel_maps(struct machine *machine)
 
 	if (end == ~0ULL) {
 		/* update end address of the kernel map using adjacent module address */
-		struct map_rb_node *rb_node = maps__find_node(machine__kernel_maps(machine),
-							machine__kernel_map(machine));
-		struct map_rb_node *next = map_rb_node__next(rb_node);
+		struct map *next = maps__find_next_entry(machine__kernel_maps(machine),
+							 machine__kernel_map(machine));
 
 		if (next)
-			machine__set_kernel_mmap(machine, start, map__start(next->map));
+			machine__set_kernel_mmap(machine, start, map__start(next));
 	}
 
 out_put:
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 024a6c9f72c40..5b898a0e97b26 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -663,6 +663,17 @@ out_unlock:
 	return map;
 }
 
+struct map *maps__find_next_entry(struct maps *maps, struct map *map)
+{
+	struct map_rb_node *rb_node = maps__find_node(maps, map);
+	struct map_rb_node *next = map_rb_node__next(rb_node);
+
+	if (next)
+		return next->map;
+
+	return NULL;
+}
+
 void maps__fixup_end(struct maps *maps)
 {
 	struct map_rb_node *prev = NULL, *curr;
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index b7ab3ec61b7c9..84b42c8456e82 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -136,6 +136,8 @@ int maps__fixup_overlap_and_insert(struct maps *maps, struct map *new);
 
 struct map *maps__find_by_name(struct maps *maps, const char *name);
 
+struct map *maps__find_next_entry(struct maps *maps, struct map *map);
+
 int maps__merge_in(struct maps *kmaps, struct map *new_map);
 
 void __maps__sort_by_name(struct maps *maps);
-- 
GitLab


From 631bb236aa6f306fd2ba16aee9ae96083453eebc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:55 -0800
Subject: [PATCH 1709/4076] perf maps: Reduce scope of map_rb_node and maps
 internals

Avoid exposing the implementation of maps so that the internals can be
refactored.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-22-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/maps.c | 90 ++++++++++++++++++++++++++----------------
 tools/perf/util/maps.h | 23 -----------
 2 files changed, 55 insertions(+), 58 deletions(-)

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 5b898a0e97b26..dcd67384d877d 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -10,6 +10,11 @@
 #include "ui/ui.h"
 #include "unwind.h"
 
+struct map_rb_node {
+	struct rb_node rb_node;
+	struct map *map;
+};
+
 #define maps__for_each_entry(maps, map) \
 	for (map = maps__first(maps); map; map = map_rb_node__next(map))
 
@@ -17,6 +22,56 @@
 	for (map = maps__first(maps), next = map_rb_node__next(map); map; \
 	     map = next, next = map_rb_node__next(map))
 
+static struct rb_root *maps__entries(struct maps *maps)
+{
+	return &RC_CHK_ACCESS(maps)->entries;
+}
+
+static struct rw_semaphore *maps__lock(struct maps *maps)
+{
+	return &RC_CHK_ACCESS(maps)->lock;
+}
+
+static struct map **maps__maps_by_name(struct maps *maps)
+{
+	return RC_CHK_ACCESS(maps)->maps_by_name;
+}
+
+static struct map_rb_node *maps__first(struct maps *maps)
+{
+	struct rb_node *first = rb_first(maps__entries(maps));
+
+	if (first)
+		return rb_entry(first, struct map_rb_node, rb_node);
+	return NULL;
+}
+
+static struct map_rb_node *map_rb_node__next(struct map_rb_node *node)
+{
+	struct rb_node *next;
+
+	if (!node)
+		return NULL;
+
+	next = rb_next(&node->rb_node);
+
+	if (!next)
+		return NULL;
+
+	return rb_entry(next, struct map_rb_node, rb_node);
+}
+
+static struct map_rb_node *maps__find_node(struct maps *maps, struct map *map)
+{
+	struct map_rb_node *rb_node;
+
+	maps__for_each_entry(maps, rb_node) {
+		if (rb_node->RC_CHK_ACCESS(map) == RC_CHK_ACCESS(map))
+			return rb_node;
+	}
+	return NULL;
+}
+
 static void maps__init(struct maps *maps, struct machine *machine)
 {
 	refcount_set(maps__refcnt(maps), 1);
@@ -485,17 +540,6 @@ out_unlock:
 	return err;
 }
 
-struct map_rb_node *maps__find_node(struct maps *maps, struct map *map)
-{
-	struct map_rb_node *rb_node;
-
-	maps__for_each_entry(maps, rb_node) {
-		if (rb_node->RC_CHK_ACCESS(map) == RC_CHK_ACCESS(map))
-			return rb_node;
-	}
-	return NULL;
-}
-
 struct map *maps__find(struct maps *maps, u64 ip)
 {
 	struct rb_node *p;
@@ -521,30 +565,6 @@ out:
 	return m ? m->map : NULL;
 }
 
-struct map_rb_node *maps__first(struct maps *maps)
-{
-	struct rb_node *first = rb_first(maps__entries(maps));
-
-	if (first)
-		return rb_entry(first, struct map_rb_node, rb_node);
-	return NULL;
-}
-
-struct map_rb_node *map_rb_node__next(struct map_rb_node *node)
-{
-	struct rb_node *next;
-
-	if (!node)
-		return NULL;
-
-	next = rb_next(&node->rb_node);
-
-	if (!next)
-		return NULL;
-
-	return rb_entry(next, struct map_rb_node, rb_node);
-}
-
 static int map__strcmp(const void *a, const void *b)
 {
 	const struct map *map_a = *(const struct map **)a;
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 84b42c8456e82..d836d04c94022 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -15,11 +15,6 @@ struct machine;
 struct map;
 struct maps;
 
-struct map_rb_node {
-	struct rb_node rb_node;
-	struct map *map;
-};
-
 struct map_list_node {
 	struct list_head node;
 	struct map *map;
@@ -30,9 +25,6 @@ static inline struct map_list_node *map_list_node__new(void)
 	return malloc(sizeof(struct map_list_node));
 }
 
-struct map_rb_node *maps__first(struct maps *maps);
-struct map_rb_node *map_rb_node__next(struct map_rb_node *node);
-struct map_rb_node *maps__find_node(struct maps *maps, struct map *map);
 struct map *maps__find(struct maps *maps, u64 addr);
 
 DECLARE_RC_STRUCT(maps) {
@@ -78,26 +70,11 @@ int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data)
 /* Iterate over map removing an entry if cb returns true. */
 void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data);
 
-static inline struct rb_root *maps__entries(struct maps *maps)
-{
-	return &RC_CHK_ACCESS(maps)->entries;
-}
-
 static inline struct machine *maps__machine(struct maps *maps)
 {
 	return RC_CHK_ACCESS(maps)->machine;
 }
 
-static inline struct rw_semaphore *maps__lock(struct maps *maps)
-{
-	return &RC_CHK_ACCESS(maps)->lock;
-}
-
-static inline struct map **maps__maps_by_name(struct maps *maps)
-{
-	return RC_CHK_ACCESS(maps)->maps_by_name;
-}
-
 static inline unsigned int maps__nr_maps(const struct maps *maps)
 {
 	return RC_CHK_ACCESS(maps)->nr_maps;
-- 
GitLab


From 7887097c65446ff229099221975f6fc9ad9e378b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:16:56 -0800
Subject: [PATCH 1710/4076] perf maps: Fix up overlaps during fixup_end

Maps are sometimes made overlapping, in particular kernel maps. If the
end of a map overlaps the start of the next, shorten the overlapping
map. This should remove potential non-determinism in maps__find, ie
finding maps by address.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Guilherme Amadio <amadio@gentoo.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231207011722.1220634-23-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/maps.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index dcd67384d877d..0334fc18d9c65 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -701,7 +701,7 @@ void maps__fixup_end(struct maps *maps)
 	down_write(maps__lock(maps));
 
 	maps__for_each_entry(maps, curr) {
-		if (prev != NULL && !map__end(prev->map))
+		if (prev && (!map__end(prev->map) || map__end(prev->map) > map__start(curr->map)))
 			map__set_end(prev->map, map__start(curr->map));
 
 		prev = curr;
-- 
GitLab


From c30fa83b49897e708a52e122dd10616a52a4c82b Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 13 Dec 2023 21:29:58 +0100
Subject: [PATCH 1711/4076] riscv: Use WRITE_ONCE() when setting page table
 entries

To avoid any compiler "weirdness" when accessing page table entries which
are concurrently modified by the HW, let's use WRITE_ONCE() macro
(commit 20a004e7b017 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when accessing
page tables") gives a great explanation with more details).

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20231213203001.179237-2-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/pgtable-64.h | 6 +++---
 arch/riscv/include/asm/pgtable.h    | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 9a2c780a11e95..5d8431a390dd3 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -202,7 +202,7 @@ static inline int pud_user(pud_t pud)
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
-	*pudp = pud;
+	WRITE_ONCE(*pudp, pud);
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -278,7 +278,7 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
 static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	if (pgtable_l4_enabled)
-		*p4dp = p4d;
+		WRITE_ONCE(*p4dp, p4d);
 	else
 		set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
 }
@@ -351,7 +351,7 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	if (pgtable_l5_enabled)
-		*pgdp = pgd;
+		WRITE_ONCE(*pgdp, pgd);
 	else
 		set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) });
 }
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 294044429e8e1..c9f4b250b4eea 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -248,7 +248,7 @@ static inline int pmd_leaf(pmd_t pmd)
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -510,7 +510,7 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
  */
 static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
-	*ptep = pteval;
+	WRITE_ONCE(*ptep, pteval);
 }
 
 void flush_icache_pte(pte_t pte);
-- 
GitLab


From eba2591d99d1f14a04c8a8a845ab0795b93f5646 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 13 Dec 2023 21:29:59 +0100
Subject: [PATCH 1712/4076] mm: Introduce pudp/p4dp/pgdp_get() functions

Instead of directly dereferencing page tables entries, which can cause
issues (see commit 20a004e7b017 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when
accessing page tables"), let's introduce new functions to get the
pud/p4d/pgd entries (the pte and pmd versions already exist).

Note that arm pgd_t is actually an array so pgdp_get() is defined as a
macro to avoid a build error.

Those new functions will be used in subsequent commits by the riscv
architecture.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20231213203001.179237-3-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/arm/include/asm/pgtable.h |  2 ++
 include/linux/pgtable.h        | 21 +++++++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 16b02f44c7d31..d657b84b6bf70 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -151,6 +151,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
+#define pgdp_get(pgpd)		READ_ONCE(*pgdp)
+
 #define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
 #define pud_write(pud)		pmd_write(__pmd(pud_val(pud)))
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index af7639c3b0a3a..8b7daccd11bef 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -292,6 +292,27 @@ static inline pmd_t pmdp_get(pmd_t *pmdp)
 }
 #endif
 
+#ifndef pudp_get
+static inline pud_t pudp_get(pud_t *pudp)
+{
+	return READ_ONCE(*pudp);
+}
+#endif
+
+#ifndef p4dp_get
+static inline p4d_t p4dp_get(p4d_t *p4dp)
+{
+	return READ_ONCE(*p4dp);
+}
+#endif
+
+#ifndef pgdp_get
+static inline pgd_t pgdp_get(pgd_t *pgdp)
+{
+	return READ_ONCE(*pgdp);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
-- 
GitLab


From d6508999d1882ddd0db8b3b4bd7967d83e9909fa Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 13 Dec 2023 21:30:00 +0100
Subject: [PATCH 1713/4076] riscv: mm: Only compile pgtable.c if MMU

All functions defined in there depend on MMU, so no need to compile it
for !MMU configs.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20231213203001.179237-4-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/Makefile | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 3a4dfc8babcf8..2c869f8026a88 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -13,10 +13,9 @@ endif
 KCOV_INSTRUMENT_init.o := n
 
 obj-y += init.o
-obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o
+obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o
 obj-y += cacheflush.o
 obj-y += context.o
-obj-y += pgtable.o
 obj-y += pmem.o
 
 ifeq ($(CONFIG_MMU),y)
-- 
GitLab


From edf955647269422e387732870d04fc15933a25ea Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 13 Dec 2023 21:30:01 +0100
Subject: [PATCH 1714/4076] riscv: Use accessors to page table entries instead
 of direct dereference

As very well explained in commit 20a004e7b017 ("arm64: mm: Use
READ_ONCE/WRITE_ONCE when accessing page tables"), an architecture whose
page table walker can modify the PTE in parallel must use
READ_ONCE()/WRITE_ONCE() macro to avoid any compiler transformation.

So apply that to riscv which is such architecture.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Acked-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20231213203001.179237-5-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/kfence.h     |  4 +--
 arch/riscv/include/asm/pgtable-64.h | 16 ++-------
 arch/riscv/include/asm/pgtable.h    | 29 ++++------------
 arch/riscv/kernel/efi.c             |  2 +-
 arch/riscv/kvm/mmu.c                | 22 ++++++-------
 arch/riscv/mm/fault.c               | 16 ++++-----
 arch/riscv/mm/hugetlbpage.c         | 12 +++----
 arch/riscv/mm/kasan_init.c          | 45 +++++++++++++------------
 arch/riscv/mm/pageattr.c            | 44 ++++++++++++-------------
 arch/riscv/mm/pgtable.c             | 51 ++++++++++++++++++++++++++---
 10 files changed, 128 insertions(+), 113 deletions(-)

diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h
index 0bbffd528096d..7388edd88986f 100644
--- a/arch/riscv/include/asm/kfence.h
+++ b/arch/riscv/include/asm/kfence.h
@@ -18,9 +18,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 	pte_t *pte = virt_to_kpte(addr);
 
 	if (protect)
-		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT));
 	else
-		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT));
 
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 5d8431a390dd3..b42017d76924f 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -340,13 +340,7 @@ static inline struct page *p4d_page(p4d_t p4d)
 #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 
 #define pud_offset pud_offset
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
-{
-	if (pgtable_l4_enabled)
-		return p4d_pgtable(*p4d) + pud_index(address);
-
-	return (pud_t *)p4d;
-}
+pud_t *pud_offset(p4d_t *p4d, unsigned long address);
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
@@ -404,12 +398,6 @@ static inline struct page *pgd_page(pgd_t pgd)
 #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
 
 #define p4d_offset p4d_offset
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
-{
-	if (pgtable_l5_enabled)
-		return pgd_pgtable(*pgd) + p4d_index(address);
-
-	return (p4d_t *)pgd;
-}
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address);
 
 #endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index c9f4b250b4eea..3773f454f0fa0 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -544,19 +544,12 @@ static inline void pte_clear(struct mm_struct *mm,
 	__set_pte_at(ptep, __pte(0));
 }
 
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-static inline int ptep_set_access_flags(struct vm_area_struct *vma,
-					unsigned long address, pte_t *ptep,
-					pte_t entry, int dirty)
-{
-	if (!pte_same(*ptep, entry))
-		__set_pte_at(ptep, entry);
-	/*
-	 * update_mmu_cache will unconditionally execute, handling both
-	 * the case that the PTE changed and the spurious fault case.
-	 */
-	return true;
-}
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS	/* defined in mm/pgtable.c */
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+				 pte_t *ptep, pte_t entry, int dirty);
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG	/* defined in mm/pgtable.c */
+extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address,
+				     pte_t *ptep);
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
@@ -569,16 +562,6 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	return pte;
 }
 
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address,
-					    pte_t *ptep)
-{
-	if (!pte_young(*ptep))
-		return 0;
-	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
-}
-
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm,
 				      unsigned long address, pte_t *ptep)
diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c
index aa6209a74c83f..b64bf1624a052 100644
--- a/arch/riscv/kernel/efi.c
+++ b/arch/riscv/kernel/efi.c
@@ -60,7 +60,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 {
 	efi_memory_desc_t *md = data;
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	unsigned long val;
 
 	if (md->attribute & EFI_MEMORY_RO) {
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 068c745938710..a9e2fd7245e1e 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -103,7 +103,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 	*ptep_level = current_level;
 	ptep = (pte_t *)kvm->arch.pgd;
 	ptep = &ptep[gstage_pte_index(addr, current_level)];
-	while (ptep && pte_val(*ptep)) {
+	while (ptep && pte_val(ptep_get(ptep))) {
 		if (gstage_pte_leaf(ptep)) {
 			*ptep_level = current_level;
 			*ptepp = ptep;
@@ -113,7 +113,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 		if (current_level) {
 			current_level--;
 			*ptep_level = current_level;
-			ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 			ptep = &ptep[gstage_pte_index(addr, current_level)];
 		} else {
 			ptep = NULL;
@@ -149,25 +149,25 @@ static int gstage_set_pte(struct kvm *kvm, u32 level,
 		if (gstage_pte_leaf(ptep))
 			return -EEXIST;
 
-		if (!pte_val(*ptep)) {
+		if (!pte_val(ptep_get(ptep))) {
 			if (!pcache)
 				return -ENOMEM;
 			next_ptep = kvm_mmu_memory_cache_alloc(pcache);
 			if (!next_ptep)
 				return -ENOMEM;
-			*ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)),
-					__pgprot(_PAGE_TABLE));
+			set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)),
+					      __pgprot(_PAGE_TABLE)));
 		} else {
 			if (gstage_pte_leaf(ptep))
 				return -EEXIST;
-			next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		}
 
 		current_level--;
 		ptep = &next_ptep[gstage_pte_index(addr, current_level)];
 	}
 
-	*ptep = *new_pte;
+	set_pte(ptep, *new_pte);
 	if (gstage_pte_leaf(ptep))
 		gstage_remote_tlb_flush(kvm, current_level, addr);
 
@@ -239,11 +239,11 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
 
 	BUG_ON(addr & (page_size - 1));
 
-	if (!pte_val(*ptep))
+	if (!pte_val(ptep_get(ptep)))
 		return;
 
 	if (ptep_level && !gstage_pte_leaf(ptep)) {
-		next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+		next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		next_ptep_level = ptep_level - 1;
 		ret = gstage_level_to_page_size(next_ptep_level,
 						&next_page_size);
@@ -261,7 +261,7 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
 		if (op == GSTAGE_OP_CLEAR)
 			set_pte(ptep, __pte(0));
 		else if (op == GSTAGE_OP_WP)
-			set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE));
+			set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE));
 		gstage_remote_tlb_flush(kvm, ptep_level, addr);
 	}
 }
@@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 				   &ptep, &ptep_level))
 		return false;
 
-	return pte_young(*ptep);
+	return pte_young(ptep_get(ptep));
 }
 
 int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 90d4ba36d1d06..76f1df709a21b 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -136,24 +136,24 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
 	pgd_k = init_mm.pgd + index;
 
-	if (!pgd_present(*pgd_k)) {
+	if (!pgd_present(pgdp_get(pgd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	set_pgd(pgd, *pgd_k);
+	set_pgd(pgd, pgdp_get(pgd_k));
 
 	p4d_k = p4d_offset(pgd_k, addr);
-	if (!p4d_present(*p4d_k)) {
+	if (!p4d_present(p4dp_get(p4d_k))) {
 		no_context(regs, addr);
 		return;
 	}
 
 	pud_k = pud_offset(p4d_k, addr);
-	if (!pud_present(*pud_k)) {
+	if (!pud_present(pudp_get(pud_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pud_leaf(*pud_k))
+	if (pud_leaf(pudp_get(pud_k)))
 		goto flush_tlb;
 
 	/*
@@ -161,11 +161,11 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * to copy individual PTEs
 	 */
 	pmd_k = pmd_offset(pud_k, addr);
-	if (!pmd_present(*pmd_k)) {
+	if (!pmd_present(pmdp_get(pmd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pmd_leaf(*pmd_k))
+	if (pmd_leaf(pmdp_get(pmd_k)))
 		goto flush_tlb;
 
 	/*
@@ -175,7 +175,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * silently loop forever.
 	 */
 	pte_k = pte_offset_kernel(pmd_k, addr);
-	if (!pte_present(*pte_k)) {
+	if (!pte_present(ptep_get(pte_k))) {
 		no_context(regs, addr);
 		return;
 	}
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index b52f0210481fa..431596c0e20e0 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -54,7 +54,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	}
 
 	if (sz == PMD_SIZE) {
-		if (want_pmd_share(vma, addr) && pud_none(*pud))
+		if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud)))
 			pte = huge_pmd_share(mm, vma, addr, pud);
 		else
 			pte = (pte_t *)pmd_alloc(mm, pud, addr);
@@ -93,11 +93,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return NULL;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
@@ -105,7 +105,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		/* must be pud huge, non-present or none */
 		return (pte_t *)pud;
 
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
@@ -113,7 +113,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		/* must be pmd huge, non-present or none */
 		return (pte_t *)pmd;
 
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return NULL;
 
 	for_each_napot_order(order) {
@@ -293,7 +293,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		    pte_t *ptep,
 		    unsigned long sz)
 {
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	int i, pte_num;
 
 	if (!pte_napot(pte)) {
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 5e39dcf23fdbc..e962518530373 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -31,7 +31,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	phys_addr_t phys_addr;
 	pte_t *ptep, *p;
 
-	if (pmd_none(*pmd)) {
+	if (pmd_none(pmdp_get(pmd))) {
 		p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
 		set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -39,7 +39,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	ptep = pte_offset_kernel(pmd, vaddr);
 
 	do {
-		if (pte_none(*ptep)) {
+		if (pte_none(ptep_get(ptep))) {
 			phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL));
 			memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE);
@@ -53,7 +53,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	pmd_t *pmdp, *p;
 	unsigned long next;
 
-	if (pud_none(*pud)) {
+	if (pud_none(pudp_get(pud))) {
 		p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
 		set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -63,7 +63,8 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	do {
 		next = pmd_addr_end(vaddr, end);
 
-		if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) {
+		if (pmd_none(pmdp_get(pmdp)) && IS_ALIGNED(vaddr, PMD_SIZE) &&
+		    (next - vaddr) >= PMD_SIZE) {
 			phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE);
 			if (phys_addr) {
 				set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -83,7 +84,7 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	pud_t *pudp, *p;
 	unsigned long next;
 
-	if (p4d_none(*p4d)) {
+	if (p4d_none(p4dp_get(p4d))) {
 		p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
 		set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -93,7 +94,8 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		    (next - vaddr) >= PUD_SIZE) {
 			phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
 			if (phys_addr) {
 				set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -113,7 +115,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	p4d_t *p4dp, *p;
 	unsigned long next;
 
-	if (pgd_none(*pgd)) {
+	if (pgd_none(pgdp_get(pgd))) {
 		p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE);
 		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
@@ -123,7 +125,8 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) {
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		    (next - vaddr) >= P4D_SIZE) {
 			phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
 			if (phys_addr) {
 				set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
@@ -145,7 +148,7 @@ static void __init kasan_populate_pgd(pgd_t *pgdp,
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
 		    (next - vaddr) >= PGDIR_SIZE) {
 			phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
 			if (phys_addr) {
@@ -168,7 +171,7 @@ static void __init kasan_early_clear_pud(p4d_t *p4dp,
 	if (!pgtable_l4_enabled) {
 		pudp = (pud_t *)p4dp;
 	} else {
-		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
 		pudp = base_pud + pud_index(vaddr);
 	}
 
@@ -193,7 +196,7 @@ static void __init kasan_early_clear_p4d(pgd_t *pgdp,
 	if (!pgtable_l5_enabled) {
 		p4dp = (p4d_t *)pgdp;
 	} else {
-		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
 		p4dp = base_p4d + p4d_index(vaddr);
 	}
 
@@ -239,14 +242,14 @@ static void __init kasan_early_populate_pud(p4d_t *p4dp,
 	if (!pgtable_l4_enabled) {
 		pudp = (pud_t *)p4dp;
 	} else {
-		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
 		pudp = base_pud + pud_index(vaddr);
 	}
 
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
 		    (next - vaddr) >= PUD_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd);
 			set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -277,14 +280,14 @@ static void __init kasan_early_populate_p4d(pgd_t *pgdp,
 	if (!pgtable_l5_enabled) {
 		p4dp = (p4d_t *)pgdp;
 	} else {
-		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
 		p4dp = base_p4d + p4d_index(vaddr);
 	}
 
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
 		    (next - vaddr) >= P4D_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_pud);
 			set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -305,7 +308,7 @@ static void __init kasan_early_populate_pgd(pgd_t *pgdp,
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
 		    (next - vaddr) >= PGDIR_SIZE) {
 			phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d);
 			set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
@@ -381,7 +384,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d,
 	do {
 		next = pud_addr_end(vaddr, end);
 
-		if (pud_none(*pud_k)) {
+		if (pud_none(pudp_get(pud_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -401,7 +404,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd,
 	do {
 		next = p4d_addr_end(vaddr, end);
 
-		if (p4d_none(*p4d_k)) {
+		if (p4d_none(p4dp_get(p4d_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -420,7 +423,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		if (pgd_none(*pgd_k)) {
+		if (pgd_none(pgdp_get(pgd_k))) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
@@ -451,7 +454,7 @@ static void __init create_tmp_mapping(void)
 
 	/* Copy the last p4d since it is shared with the kernel mapping. */
 	if (pgtable_l5_enabled) {
-		ptr = (p4d_t *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
+		ptr = (p4d_t *)pgd_page_vaddr(pgdp_get(pgd_offset_k(KASAN_SHADOW_END)));
 		memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D);
 		set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)],
 			pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE));
@@ -462,7 +465,7 @@ static void __init create_tmp_mapping(void)
 
 	/* Copy the last pud since it is shared with the kernel mapping. */
 	if (pgtable_l4_enabled) {
-		ptr = (pud_t *)p4d_page_vaddr(*(base_p4d + p4d_index(KASAN_SHADOW_END)));
+		ptr = (pud_t *)p4d_page_vaddr(p4dp_get(base_p4d + p4d_index(KASAN_SHADOW_END)));
 		memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD);
 		set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)],
 			pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE));
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index fc5fc4f785c48..0b5e38e018c89 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -29,7 +29,7 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
 static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	p4d_t val = READ_ONCE(*p4d);
+	p4d_t val = p4dp_get(p4d);
 
 	if (p4d_leaf(val)) {
 		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
@@ -42,7 +42,7 @@ static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pud_t val = READ_ONCE(*pud);
+	pud_t val = pudp_get(pud);
 
 	if (pud_leaf(val)) {
 		val = __pud(set_pageattr_masks(pud_val(val), walk));
@@ -55,7 +55,7 @@ static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pmd_t val = READ_ONCE(*pmd);
+	pmd_t val = pmdp_get(pmd);
 
 	if (pmd_leaf(val)) {
 		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
@@ -68,7 +68,7 @@ static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pte_t val = READ_ONCE(*pte);
+	pte_t val = ptep_get(pte);
 
 	val = __pte(set_pageattr_masks(pte_val(val), walk));
 	set_pte(pte, val);
@@ -108,10 +108,10 @@ static int __split_linear_mapping_pmd(pud_t *pudp,
 		    vaddr <= (vaddr & PMD_MASK) && end >= next)
 			continue;
 
-		if (pmd_leaf(*pmdp)) {
+		if (pmd_leaf(pmdp_get(pmdp))) {
 			struct page *pte_page;
-			unsigned long pfn = _pmd_pfn(*pmdp);
-			pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _pmd_pfn(pmdp_get(pmdp));
+			pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK);
 			pte_t *ptep_new;
 			int i;
 
@@ -148,10 +148,10 @@ static int __split_linear_mapping_pud(p4d_t *p4dp,
 		    vaddr <= (vaddr & PUD_MASK) && end >= next)
 			continue;
 
-		if (pud_leaf(*pudp)) {
+		if (pud_leaf(pudp_get(pudp))) {
 			struct page *pmd_page;
-			unsigned long pfn = _pud_pfn(*pudp);
-			pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _pud_pfn(pudp_get(pudp));
+			pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK);
 			pmd_t *pmdp_new;
 			int i;
 
@@ -197,10 +197,10 @@ static int __split_linear_mapping_p4d(pgd_t *pgdp,
 		    vaddr <= (vaddr & P4D_MASK) && end >= next)
 			continue;
 
-		if (p4d_leaf(*p4dp)) {
+		if (p4d_leaf(p4dp_get(p4dp))) {
 			struct page *pud_page;
-			unsigned long pfn = _p4d_pfn(*p4dp);
-			pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK);
+			unsigned long pfn = _p4d_pfn(p4dp_get(p4dp));
+			pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK);
 			pud_t *pudp_new;
 			int i;
 
@@ -406,29 +406,29 @@ bool kernel_page_present(struct page *page)
 	pte_t *pte;
 
 	pgd = pgd_offset_k(addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return false;
-	if (pgd_leaf(*pgd))
+	if (pgd_leaf(pgdp_get(pgd)))
 		return true;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return false;
-	if (p4d_leaf(*p4d))
+	if (p4d_leaf(p4dp_get(p4d)))
 		return true;
 
 	pud = pud_offset(p4d, addr);
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return false;
-	if (pud_leaf(*pud))
+	if (pud_leaf(pudp_get(pud)))
 		return true;
 
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return false;
-	if (pmd_leaf(*pmd))
+	if (pmd_leaf(pmdp_get(pmd)))
 		return true;
 
 	pte = pte_offset_kernel(pmd, addr);
-	return pte_present(*pte);
+	return pte_present(ptep_get(pte));
 }
diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c
index fef4e7328e490..ef887efcb6790 100644
--- a/arch/riscv/mm/pgtable.c
+++ b/arch/riscv/mm/pgtable.c
@@ -5,6 +5,47 @@
 #include <linux/kernel.h>
 #include <linux/pgtable.h>
 
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	if (!pte_same(ptep_get(ptep), entry))
+		__set_pte_at(ptep, entry);
+	/*
+	 * update_mmu_cache will unconditionally execute, handling both
+	 * the case that the PTE changed and the spurious fault case.
+	 */
+	return true;
+}
+
+int ptep_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long address,
+			      pte_t *ptep)
+{
+	if (!pte_young(ptep_get(ptep)))
+		return 0;
+	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_young);
+
+#ifdef CONFIG_64BIT
+pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if (pgtable_l4_enabled)
+		return p4d_pgtable(p4dp_get(p4d)) + pud_index(address);
+
+	return (pud_t *)p4d;
+}
+
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	if (pgtable_l5_enabled)
+		return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address);
+
+	return (p4d_t *)pgd;
+}
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
 int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
@@ -25,7 +66,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
 
 int pud_clear_huge(pud_t *pud)
 {
-	if (!pud_leaf(READ_ONCE(*pud)))
+	if (!pud_leaf(pudp_get(pud)))
 		return 0;
 	pud_clear(pud);
 	return 1;
@@ -33,7 +74,7 @@ int pud_clear_huge(pud_t *pud)
 
 int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
-	pmd_t *pmd = pud_pgtable(*pud);
+	pmd_t *pmd = pud_pgtable(pudp_get(pud));
 	int i;
 
 	pud_clear(pud);
@@ -63,7 +104,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
 
 int pmd_clear_huge(pmd_t *pmd)
 {
-	if (!pmd_leaf(READ_ONCE(*pmd)))
+	if (!pmd_leaf(pmdp_get(pmd)))
 		return 0;
 	pmd_clear(pmd);
 	return 1;
@@ -71,7 +112,7 @@ int pmd_clear_huge(pmd_t *pmd)
 
 int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
-	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
+	pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd));
 
 	pmd_clear(pmd);
 
@@ -88,7 +129,7 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
 	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON(pmd_trans_huge(*pmdp));
+	VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp)));
 	/*
 	 * When leaf PTE entries (regular pages) are collapsed into a leaf
 	 * PMD entry (huge page), a valid non-leaf PTE is converted into a
-- 
GitLab


From 88388cb0c9b0c4cc337e4241fe6f905c89bd7acf Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 3 Nov 2023 03:25:18 +0000
Subject: [PATCH 1715/4076] nfsctl: switch to simple_recursive_removal()

	Use simple_recursive_removal() in nfsd_client_rmdir() rather than
open-coding it.  And use less heavy-handed locking to get from nfsctl
inode to its ->i_private...

Reviewed-by: Jeff Layton <jlayton@redhat.com>
Tested-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/nfsd/nfsctl.c | 70 ++++++++++--------------------------------------
 1 file changed, 14 insertions(+), 56 deletions(-)

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 3e15b72f421d4..50df5e9d00698 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1236,63 +1236,34 @@ static inline void _nfsd_symlink(struct dentry *parent, const char *name,
 
 #endif
 
-static void clear_ncl(struct inode *inode)
+static void clear_ncl(struct dentry *dentry)
 {
+	struct inode *inode = d_inode(dentry);
 	struct nfsdfs_client *ncl = inode->i_private;
 
+	spin_lock(&inode->i_lock);
 	inode->i_private = NULL;
+	spin_unlock(&inode->i_lock);
 	kref_put(&ncl->cl_ref, ncl->cl_release);
 }
 
-static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode)
-{
-	struct nfsdfs_client *nc = inode->i_private;
-
-	if (nc)
-		kref_get(&nc->cl_ref);
-	return nc;
-}
-
 struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
 {
 	struct nfsdfs_client *nc;
 
-	inode_lock_shared(inode);
-	nc = __get_nfsdfs_client(inode);
-	inode_unlock_shared(inode);
+	spin_lock(&inode->i_lock);
+	nc = inode->i_private;
+	if (nc)
+		kref_get(&nc->cl_ref);
+	spin_unlock(&inode->i_lock);
 	return nc;
 }
-/* from __rpc_unlink */
-static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry)
-{
-	int ret;
-
-	clear_ncl(d_inode(dentry));
-	dget(dentry);
-	ret = simple_unlink(dir, dentry);
-	d_drop(dentry);
-	fsnotify_unlink(dir, dentry);
-	dput(dentry);
-	WARN_ON_ONCE(ret);
-}
-
-static void nfsdfs_remove_files(struct dentry *root)
-{
-	struct dentry *dentry, *tmp;
-
-	list_for_each_entry_safe(dentry, tmp, &root->d_subdirs, d_child) {
-		if (!simple_positive(dentry)) {
-			WARN_ON_ONCE(1); /* I think this can't happen? */
-			continue;
-		}
-		nfsdfs_remove_file(d_inode(root), dentry);
-	}
-}
 
 /* XXX: cut'n'paste from simple_fill_super; figure out if we could share
  * code instead. */
 static  int nfsdfs_create_files(struct dentry *root,
 				const struct tree_descr *files,
+				struct nfsdfs_client *ncl,
 				struct dentry **fdentries)
 {
 	struct inode *dir = d_inode(root);
@@ -1311,8 +1282,9 @@ static  int nfsdfs_create_files(struct dentry *root,
 			dput(dentry);
 			goto out;
 		}
+		kref_get(&ncl->cl_ref);
 		inode->i_fop = files->ops;
-		inode->i_private = __get_nfsdfs_client(dir);
+		inode->i_private = ncl;
 		d_add(dentry, inode);
 		fsnotify_create(dir, dentry);
 		if (fdentries)
@@ -1321,7 +1293,6 @@ static  int nfsdfs_create_files(struct dentry *root,
 	inode_unlock(dir);
 	return 0;
 out:
-	nfsdfs_remove_files(root);
 	inode_unlock(dir);
 	return -ENOMEM;
 }
@@ -1341,7 +1312,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
 	dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
 	if (IS_ERR(dentry)) /* XXX: tossing errors? */
 		return NULL;
-	ret = nfsdfs_create_files(dentry, files, fdentries);
+	ret = nfsdfs_create_files(dentry, files, ncl, fdentries);
 	if (ret) {
 		nfsd_client_rmdir(dentry);
 		return NULL;
@@ -1352,20 +1323,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
 /* Taken from __rpc_rmdir: */
 void nfsd_client_rmdir(struct dentry *dentry)
 {
-	struct inode *dir = d_inode(dentry->d_parent);
-	struct inode *inode = d_inode(dentry);
-	int ret;
-
-	inode_lock(dir);
-	nfsdfs_remove_files(dentry);
-	clear_ncl(inode);
-	dget(dentry);
-	ret = simple_rmdir(dir, dentry);
-	WARN_ON_ONCE(ret);
-	d_drop(dentry);
-	fsnotify_rmdir(dir, dentry);
-	dput(dentry);
-	inode_unlock(dir);
+	simple_recursive_removal(dentry, clear_ncl);
 }
 
 static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
-- 
GitLab


From fe752331d4b361d43cfd0b89534b4b2176057c32 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@linux.ibm.com>
Date: Wed, 20 Dec 2023 13:53:17 +0100
Subject: [PATCH 1716/4076] KVM: s390: vsie: fix race during shadow creation

Right now it is possible to see gmap->private being zero in
kvm_s390_vsie_gmap_notifier resulting in a crash.  This is due to the
fact that we add gmap->private == kvm after creation:

static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
                               struct vsie_page *vsie_page)
{
[...]
        gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
        if (IS_ERR(gmap))
                return PTR_ERR(gmap);
        gmap->private = vcpu->kvm;

Let children inherit the private field of the parent.

Reported-by: Marc Hartmayer <mhartmay@linux.ibm.com>
Fixes: a3508fbe9dc6 ("KVM: s390: vsie: initial support for nested virtualization")
Cc: <stable@vger.kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Link: https://lore.kernel.org/r/20231220125317.4258-1-borntraeger@linux.ibm.com
---
 arch/s390/kvm/vsie.c | 1 -
 arch/s390/mm/gmap.c  | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 8207a892bbe22..db9a180de65f1 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1220,7 +1220,6 @@ static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
 	gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
 	if (IS_ERR(gmap))
 		return PTR_ERR(gmap);
-	gmap->private = vcpu->kvm;
 	vcpu->kvm->stat.gmap_shadow_create++;
 	WRITE_ONCE(vsie_page->gmap, gmap);
 	return 0;
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 6f96b5a71c638..8da39deb56ca4 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -1691,6 +1691,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 		return ERR_PTR(-ENOMEM);
 	new->mm = parent->mm;
 	new->parent = gmap_get(parent);
+	new->private = parent->private;
 	new->orig_asce = asce;
 	new->edat_level = edat_level;
 	new->initialized = false;
-- 
GitLab


From 4bb104e4f30d2202657b77c948f9ef1366ac438e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 17 Dec 2023 17:41:45 +0100
Subject: [PATCH 1717/4076] iio: buffer: Use IIO_SEPARATE instead of a
 hard-coded 0

Use an explicit IIO_SEPARATE instead of 0 for the 'shared_by' parameter
when calling __iio_add_chan_devattr().

For some reason, commit 3704432fb1fd ("iio: refactor info mask and ext_info
attribute creation.") updated only 1 place out of 4.
Update the remaining ones now.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/1d17f57423172fcb9d9797cfe7c8282f356049c2.1702831285.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-buffer.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 09c41e9ccf874..b581a7e805662 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -616,7 +616,7 @@ static int iio_buffer_add_channel_sysfs(struct iio_dev *indio_dev,
 				     &iio_show_fixed_type,
 				     NULL,
 				     0,
-				     0,
+				     IIO_SEPARATE,
 				     &indio_dev->dev,
 				     buffer,
 				     &buffer->buffer_attr_list);
@@ -629,7 +629,7 @@ static int iio_buffer_add_channel_sysfs(struct iio_dev *indio_dev,
 					     &iio_scan_el_show,
 					     &iio_scan_el_store,
 					     chan->scan_index,
-					     0,
+					     IIO_SEPARATE,
 					     &indio_dev->dev,
 					     buffer,
 					     &buffer->buffer_attr_list);
@@ -639,7 +639,7 @@ static int iio_buffer_add_channel_sysfs(struct iio_dev *indio_dev,
 					     &iio_scan_el_ts_show,
 					     &iio_scan_el_ts_store,
 					     chan->scan_index,
-					     0,
+					     IIO_SEPARATE,
 					     &indio_dev->dev,
 					     buffer,
 					     &buffer->buffer_attr_list);
-- 
GitLab


From 4cdfb6e7bc9c80142d33bf1d4653a73fa678ba56 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Thu, 21 Dec 2023 13:59:43 +0300
Subject: [PATCH 1718/4076] fs/ntfs3: Disable ATTR_LIST_ENTRY size check

The use of sizeof(struct ATTR_LIST_ENTRY) has been replaced with le_size(0)
due to alignment peculiarities on different platforms.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312071005.g6YrbaIe-lkp@intel.com/
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/attrlist.c | 8 ++++----
 fs/ntfs3/ntfs.h     | 2 --
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index 7c01735d1219d..48e7da47c6b71 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -127,12 +127,13 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 {
 	size_t off;
 	u16 sz;
+	const unsigned le_min_size = le_size(0);
 
 	if (!le) {
 		le = ni->attr_list.le;
 	} else {
 		sz = le16_to_cpu(le->size);
-		if (sz < sizeof(struct ATTR_LIST_ENTRY)) {
+		if (sz < le_min_size) {
 			/* Impossible 'cause we should not return such le. */
 			return NULL;
 		}
@@ -141,7 +142,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 
 	/* Check boundary. */
 	off = PtrOffset(ni->attr_list.le, le);
-	if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) {
+	if (off + le_min_size > ni->attr_list.size) {
 		/* The regular end of list. */
 		return NULL;
 	}
@@ -149,8 +150,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 	sz = le16_to_cpu(le->size);
 
 	/* Check le for errors. */
-	if (sz < sizeof(struct ATTR_LIST_ENTRY) ||
-	    off + sz > ni->attr_list.size ||
+	if (sz < le_min_size || off + sz > ni->attr_list.size ||
 	    sz < le->name_off + le->name_len * sizeof(short)) {
 		return NULL;
 	}
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index c8981429c7213..9c7478150a035 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -527,8 +527,6 @@ struct ATTR_LIST_ENTRY {
 
 }; // sizeof(0x20)
 
-static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20);
-
 static inline u32 le_size(u8 name_len)
 {
 	return ALIGN(offsetof(struct ATTR_LIST_ENTRY, name) +
-- 
GitLab


From ee9ec49046951eff704752669f0c388b506ddbdf Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Tue, 19 Dec 2023 18:50:02 +0100
Subject: [PATCH 1719/4076] iio: buffer-dma: Get rid of outgoing queue

The buffer-dma code was using two queues, incoming and outgoing, to
manage the state of the blocks in use.

While this totally works, it adds some complexity to the code,
especially since the code only manages 2 blocks. It is much easier to
just check each block's state manually, and keep a counter for the next
block to dequeue.

Since the new DMABUF based API wouldn't use the outgoing queue anyway,
getting rid of it now makes the upcoming changes simpler.

With this change, the IIO_BLOCK_STATE_DEQUEUED is now useless, and can
be removed.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Link: https://lore.kernel.org/r/20231219175009.65482-2-paul@crapouillou.net
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/buffer/industrialio-buffer-dma.c | 44 ++++++++++----------
 include/linux/iio/buffer-dma.h               |  7 ++--
 2 files changed, 26 insertions(+), 25 deletions(-)

diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c
index d348af8b97050..1fc91467d1aa7 100644
--- a/drivers/iio/buffer/industrialio-buffer-dma.c
+++ b/drivers/iio/buffer/industrialio-buffer-dma.c
@@ -179,7 +179,7 @@ static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
 	}
 
 	block->size = size;
-	block->state = IIO_BLOCK_STATE_DEQUEUED;
+	block->state = IIO_BLOCK_STATE_DONE;
 	block->queue = queue;
 	INIT_LIST_HEAD(&block->head);
 	kref_init(&block->kref);
@@ -191,16 +191,8 @@ static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
 
 static void _iio_dma_buffer_block_done(struct iio_dma_buffer_block *block)
 {
-	struct iio_dma_buffer_queue *queue = block->queue;
-
-	/*
-	 * The buffer has already been freed by the application, just drop the
-	 * reference.
-	 */
-	if (block->state != IIO_BLOCK_STATE_DEAD) {
+	if (block->state != IIO_BLOCK_STATE_DEAD)
 		block->state = IIO_BLOCK_STATE_DONE;
-		list_add_tail(&block->head, &queue->outgoing);
-	}
 }
 
 /**
@@ -261,7 +253,6 @@ static bool iio_dma_block_reusable(struct iio_dma_buffer_block *block)
 	 * not support abort and has not given back the block yet.
 	 */
 	switch (block->state) {
-	case IIO_BLOCK_STATE_DEQUEUED:
 	case IIO_BLOCK_STATE_QUEUED:
 	case IIO_BLOCK_STATE_DONE:
 		return true;
@@ -317,7 +308,6 @@ int iio_dma_buffer_request_update(struct iio_buffer *buffer)
 	 * dead. This means we can reset the lists without having to fear
 	 * corrution.
 	 */
-	INIT_LIST_HEAD(&queue->outgoing);
 	spin_unlock_irq(&queue->list_lock);
 
 	INIT_LIST_HEAD(&queue->incoming);
@@ -456,14 +446,20 @@ static struct iio_dma_buffer_block *iio_dma_buffer_dequeue(
 	struct iio_dma_buffer_queue *queue)
 {
 	struct iio_dma_buffer_block *block;
+	unsigned int idx;
 
 	spin_lock_irq(&queue->list_lock);
-	block = list_first_entry_or_null(&queue->outgoing, struct
-		iio_dma_buffer_block, head);
-	if (block != NULL) {
-		list_del(&block->head);
-		block->state = IIO_BLOCK_STATE_DEQUEUED;
+
+	idx = queue->fileio.next_dequeue;
+	block = queue->fileio.blocks[idx];
+
+	if (block->state == IIO_BLOCK_STATE_DONE) {
+		idx = (idx + 1) % ARRAY_SIZE(queue->fileio.blocks);
+		queue->fileio.next_dequeue = idx;
+	} else {
+		block = NULL;
 	}
+
 	spin_unlock_irq(&queue->list_lock);
 
 	return block;
@@ -539,6 +535,7 @@ size_t iio_dma_buffer_data_available(struct iio_buffer *buf)
 	struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buf);
 	struct iio_dma_buffer_block *block;
 	size_t data_available = 0;
+	unsigned int i;
 
 	/*
 	 * For counting the available bytes we'll use the size of the block not
@@ -552,8 +549,15 @@ size_t iio_dma_buffer_data_available(struct iio_buffer *buf)
 		data_available += queue->fileio.active_block->size;
 
 	spin_lock_irq(&queue->list_lock);
-	list_for_each_entry(block, &queue->outgoing, head)
-		data_available += block->size;
+
+	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
+		block = queue->fileio.blocks[i];
+
+		if (block != queue->fileio.active_block
+		    && block->state == IIO_BLOCK_STATE_DONE)
+			data_available += block->size;
+	}
+
 	spin_unlock_irq(&queue->list_lock);
 	mutex_unlock(&queue->lock);
 
@@ -617,7 +621,6 @@ int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
 	queue->ops = ops;
 
 	INIT_LIST_HEAD(&queue->incoming);
-	INIT_LIST_HEAD(&queue->outgoing);
 
 	mutex_init(&queue->lock);
 	spin_lock_init(&queue->list_lock);
@@ -645,7 +648,6 @@ void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue)
 			continue;
 		queue->fileio.blocks[i]->state = IIO_BLOCK_STATE_DEAD;
 	}
-	INIT_LIST_HEAD(&queue->outgoing);
 	spin_unlock_irq(&queue->list_lock);
 
 	INIT_LIST_HEAD(&queue->incoming);
diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h
index 6564bdcdac66c..18d3702fa95d1 100644
--- a/include/linux/iio/buffer-dma.h
+++ b/include/linux/iio/buffer-dma.h
@@ -19,14 +19,12 @@ struct device;
 
 /**
  * enum iio_block_state - State of a struct iio_dma_buffer_block
- * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued
  * @IIO_BLOCK_STATE_QUEUED: Block is on the incoming queue
  * @IIO_BLOCK_STATE_ACTIVE: Block is currently being processed by the DMA
  * @IIO_BLOCK_STATE_DONE: Block is on the outgoing queue
  * @IIO_BLOCK_STATE_DEAD: Block has been marked as to be freed
  */
 enum iio_block_state {
-	IIO_BLOCK_STATE_DEQUEUED,
 	IIO_BLOCK_STATE_QUEUED,
 	IIO_BLOCK_STATE_ACTIVE,
 	IIO_BLOCK_STATE_DONE,
@@ -73,12 +71,15 @@ struct iio_dma_buffer_block {
  * @active_block: Block being used in read()
  * @pos: Read offset in the active block
  * @block_size: Size of each block
+ * @next_dequeue: index of next block that will be dequeued
  */
 struct iio_dma_buffer_queue_fileio {
 	struct iio_dma_buffer_block *blocks[2];
 	struct iio_dma_buffer_block *active_block;
 	size_t pos;
 	size_t block_size;
+
+	unsigned int next_dequeue;
 };
 
 /**
@@ -93,7 +94,6 @@ struct iio_dma_buffer_queue_fileio {
  *   list and typically also a list of active blocks in the part that handles
  *   the DMA controller
  * @incoming: List of buffers on the incoming queue
- * @outgoing: List of buffers on the outgoing queue
  * @active: Whether the buffer is currently active
  * @fileio: FileIO state
  */
@@ -105,7 +105,6 @@ struct iio_dma_buffer_queue {
 	struct mutex lock;
 	spinlock_t list_lock;
 	struct list_head incoming;
-	struct list_head outgoing;
 
 	bool active;
 
-- 
GitLab


From 996b2e046aee6e34f36c66254db128c10d6116f0 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Tue, 19 Dec 2023 18:50:03 +0100
Subject: [PATCH 1720/4076] iio: buffer-dma: split iio_dma_buffer_fileio_free()
 function

This change splits the logic into a separate function, which will be
re-used later.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Cc: Alexandru Ardelean <ardeleanalex@gmail.com>
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Link: https://lore.kernel.org/r/20231219175009.65482-3-paul@crapouillou.net
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/buffer/industrialio-buffer-dma.c | 43 +++++++++++---------
 1 file changed, 24 insertions(+), 19 deletions(-)

diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c
index 1fc91467d1aa7..5610ba67925ef 100644
--- a/drivers/iio/buffer/industrialio-buffer-dma.c
+++ b/drivers/iio/buffer/industrialio-buffer-dma.c
@@ -346,6 +346,29 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iio_dma_buffer_request_update);
 
+static void iio_dma_buffer_fileio_free(struct iio_dma_buffer_queue *queue)
+{
+	unsigned int i;
+
+	spin_lock_irq(&queue->list_lock);
+	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
+		if (!queue->fileio.blocks[i])
+			continue;
+		queue->fileio.blocks[i]->state = IIO_BLOCK_STATE_DEAD;
+	}
+	spin_unlock_irq(&queue->list_lock);
+
+	INIT_LIST_HEAD(&queue->incoming);
+
+	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
+		if (!queue->fileio.blocks[i])
+			continue;
+		iio_buffer_block_put(queue->fileio.blocks[i]);
+		queue->fileio.blocks[i] = NULL;
+	}
+	queue->fileio.active_block = NULL;
+}
+
 static void iio_dma_buffer_submit_block(struct iio_dma_buffer_queue *queue,
 	struct iio_dma_buffer_block *block)
 {
@@ -638,27 +661,9 @@ EXPORT_SYMBOL_GPL(iio_dma_buffer_init);
  */
 void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue)
 {
-	unsigned int i;
-
 	mutex_lock(&queue->lock);
 
-	spin_lock_irq(&queue->list_lock);
-	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
-		if (!queue->fileio.blocks[i])
-			continue;
-		queue->fileio.blocks[i]->state = IIO_BLOCK_STATE_DEAD;
-	}
-	spin_unlock_irq(&queue->list_lock);
-
-	INIT_LIST_HEAD(&queue->incoming);
-
-	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
-		if (!queue->fileio.blocks[i])
-			continue;
-		iio_buffer_block_put(queue->fileio.blocks[i]);
-		queue->fileio.blocks[i] = NULL;
-	}
-	queue->fileio.active_block = NULL;
+	iio_dma_buffer_fileio_free(queue);
 	queue->ops = NULL;
 
 	mutex_unlock(&queue->lock);
-- 
GitLab


From 5ae81209491ed3718fee798db6fb2cc81214824c Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:52:36 +0100
Subject: [PATCH 1721/4076] driver core: bus: make bus_sort_breadthfirst() take
 a const pointer

For some reason, during the big "clean up the driver core for a const
struct bus_type" work, the bus_sort_breadthfirst() call was missed.  Fix
this up by changing the type to be a const * as it should be.

Cc: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/2023121935-stinking-ditzy-fd5d@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/bus.c         | 2 +-
 include/linux/device/bus.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 84a21084d67d1..33d9526959270 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -1030,7 +1030,7 @@ static void device_insertion_sort_klist(struct device *a, struct list_head *list
 	list_move_tail(&a->p->knode_bus.n_node, list);
 }
 
-void bus_sort_breadthfirst(struct bus_type *bus,
+void bus_sort_breadthfirst(const struct bus_type *bus,
 			   int (*compare)(const struct device *a,
 					  const struct device *b))
 {
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index ae10c43227543..25127f7503494 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -232,7 +232,7 @@ bus_find_device_by_acpi_dev(const struct bus_type *bus, const void *adev)
 
 int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start,
 		     void *data, int (*fn)(struct device_driver *, void *));
-void bus_sort_breadthfirst(struct bus_type *bus,
+void bus_sort_breadthfirst(const struct bus_type *bus,
 			   int (*compare)(const struct device *a,
 					  const struct device *b));
 /*
-- 
GitLab


From 32f78abe59c740b6ec34c89dc10a09208eae7e1f Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:15:09 +0100
Subject: [PATCH 1722/4076] driver core: bus: constantify subsys_register()
 calls

The functions subsys_register() and subsys_virtual_register() should be
taking a constant pointer to a struct bus_type, as they do not actually
modify anything in it, so fix up the function definitions to do so
properly.

This also changes the pointer type in struct subsys_interface to be
constant as well, as again, that's the proper signature of it.

Cc: Rafael J. Wysocki <rafael@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/2023121908-grove-genetics-f8af@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/bus.c     | 6 +++---
 include/linux/device.h | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 33d9526959270..daee55c9b2d9e 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -1194,7 +1194,7 @@ static void system_root_device_release(struct device *dev)
 	kfree(dev);
 }
 
-static int subsys_register(struct bus_type *subsys,
+static int subsys_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups,
 			   struct kobject *parent_of_root)
 {
@@ -1264,7 +1264,7 @@ err_sp:
  * directory itself and not some create fake root-device placed in
  * /sys/devices/system/<name>.
  */
-int subsys_system_register(struct bus_type *subsys,
+int subsys_system_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups)
 {
 	return subsys_register(subsys, groups, &system_kset->kobj);
@@ -1282,7 +1282,7 @@ EXPORT_SYMBOL_GPL(subsys_system_register);
  * There's no restriction on device naming.  This is for kernel software
  * constructs which need sysfs interface.
  */
-int subsys_virtual_register(struct bus_type *subsys,
+int subsys_virtual_register(const struct bus_type *subsys,
 			    const struct attribute_group **groups)
 {
 	struct kobject *virtual_dir;
diff --git a/include/linux/device.h b/include/linux/device.h
index 4aa34c8d13610..aefc5ca7f1cfc 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -63,7 +63,7 @@ struct msi_device_data;
  */
 struct subsys_interface {
 	const char *name;
-	struct bus_type *subsys;
+	const struct bus_type *subsys;
 	struct list_head node;
 	int (*add_dev)(struct device *dev, struct subsys_interface *sif);
 	void (*remove_dev)(struct device *dev, struct subsys_interface *sif);
@@ -72,9 +72,9 @@ struct subsys_interface {
 int subsys_interface_register(struct subsys_interface *sif);
 void subsys_interface_unregister(struct subsys_interface *sif);
 
-int subsys_system_register(struct bus_type *subsys,
+int subsys_system_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups);
-int subsys_virtual_register(struct bus_type *subsys,
+int subsys_virtual_register(const struct bus_type *subsys,
 			    const struct attribute_group **groups);
 
 /*
-- 
GitLab


From dedb868994d8308c6c4650203e190ec619005806 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 16:03:20 +0100
Subject: [PATCH 1723/4076] driver core: container: make container_subsys const

Now that the driver core can properly handle constant struct bus_type,
move the container_subsys variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://lore.kernel.org/r/2023121919-chatter-grumbling-9ef3@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/container.c  | 2 +-
 include/linux/container.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/base/container.c b/drivers/base/container.c
index 1ba42d2d35322..f40588ebc3f55 100644
--- a/drivers/base/container.c
+++ b/drivers/base/container.c
@@ -24,7 +24,7 @@ static int container_offline(struct device *dev)
 	return cdev->offline ? cdev->offline(cdev) : 0;
 }
 
-struct bus_type container_subsys = {
+const struct bus_type container_subsys = {
 	.name = CONTAINER_BUS_NAME,
 	.dev_name = CONTAINER_BUS_NAME,
 	.online = trivial_online,
diff --git a/include/linux/container.h b/include/linux/container.h
index 2566a1baa736a..dd00cc918a926 100644
--- a/include/linux/container.h
+++ b/include/linux/container.h
@@ -12,7 +12,7 @@
 #include <linux/device.h>
 
 /* drivers/base/power/container.c */
-extern struct bus_type container_subsys;
+extern const struct bus_type container_subsys;
 
 struct container_dev {
 	struct device dev;
-- 
GitLab


From 580fc9c750fde7404f2d726637135fb785c67e86 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 16:35:09 +0100
Subject: [PATCH 1724/4076] driver core: mark remaining local bus_type
 variables as const

Now that the driver core can properly handle constant struct bus_type,
change the local driver core bus_type variables to be a constant
structure as well, placing them into read-only memory which can not be
modified at runtime.

Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Kevin Hilman <khilman@kernel.org>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Len Brown <len.brown@intel.com>
Acked-by: William Breathitt Gray <william.gray@linaro.org>
Acked-by: Dave Ertman <david.m.ertman@intel.com>
Link: https://lore.kernel.org/r/2023121908-paver-follow-cc21@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/auxiliary.c    | 2 +-
 drivers/base/isa.c          | 2 +-
 drivers/base/memory.c       | 2 +-
 drivers/base/node.c         | 2 +-
 drivers/base/power/domain.c | 2 +-
 drivers/base/soc.c          | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index 4d4c2c8d26c48..d3a2c40c2f127 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -244,7 +244,7 @@ static void auxiliary_bus_shutdown(struct device *dev)
 		auxdrv->shutdown(auxdev);
 }
 
-static struct bus_type auxiliary_bus_type = {
+static const struct bus_type auxiliary_bus_type = {
 	.name = "auxiliary",
 	.probe = auxiliary_bus_probe,
 	.remove = auxiliary_bus_remove,
diff --git a/drivers/base/isa.c b/drivers/base/isa.c
index 675ad31392246..e23d0b49a7934 100644
--- a/drivers/base/isa.c
+++ b/drivers/base/isa.c
@@ -82,7 +82,7 @@ static int isa_bus_resume(struct device *dev)
 	return 0;
 }
 
-static struct bus_type isa_bus_type = {
+static const struct bus_type isa_bus_type = {
 	.name		= "isa",
 	.match		= isa_bus_match,
 	.probe		= isa_bus_probe,
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index f3b9a4d0fa3bb..4ac3266da6b52 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -68,7 +68,7 @@ static inline unsigned long phys_to_block_id(unsigned long phys)
 static int memory_subsys_online(struct device *dev);
 static int memory_subsys_offline(struct device *dev);
 
-static struct bus_type memory_subsys = {
+static const struct bus_type memory_subsys = {
 	.name = MEMORY_CLASS_NAME,
 	.dev_name = MEMORY_CLASS_NAME,
 	.online = memory_subsys_online,
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 4d588f4658c85..433897eecbdcc 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -21,7 +21,7 @@
 #include <linux/swap.h>
 #include <linux/slab.h>
 
-static struct bus_type node_subsys = {
+static const struct bus_type node_subsys = {
 	.name = "node",
 	.dev_name = "node",
 };
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index da1777e39eaa5..096871334cc7f 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2670,7 +2670,7 @@ static void genpd_release_dev(struct device *dev)
 	kfree(dev);
 }
 
-static struct bus_type genpd_bus_type = {
+static const struct bus_type genpd_bus_type = {
 	.name		= "genpd",
 };
 
diff --git a/drivers/base/soc.c b/drivers/base/soc.c
index c741d0845852a..282c38aece0de 100644
--- a/drivers/base/soc.c
+++ b/drivers/base/soc.c
@@ -28,7 +28,7 @@ struct soc_device {
 	int soc_dev_num;
 };
 
-static struct bus_type soc_bus_type = {
+static const struct bus_type soc_bus_type = {
 	.name  = "soc",
 };
 static bool soc_bus_registered;
-- 
GitLab


From f99c37d562250cbceed262723f91944c981eeb7b Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Tue, 12 Dec 2023 17:34:33 +0100
Subject: [PATCH 1725/4076] MIPS: compressed: Use correct instruction for 64
 bit code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The code clearing BSS already use macro or use correct instruction
depending if the CPU is 32 bits or 64 bits. However, a few
instructions remained 32 bits only.

By using the accurate MACRO, it is now possible to deal with memory
address beyond 32 bits. As a side effect, when using 64bits processor,
it also divides the loop number needed to clear the BSS by 2.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/boot/compressed/head.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/mips/boot/compressed/head.S b/arch/mips/boot/compressed/head.S
index 5795d0af1e1b2..d237a834b85ee 100644
--- a/arch/mips/boot/compressed/head.S
+++ b/arch/mips/boot/compressed/head.S
@@ -25,8 +25,8 @@
 	/* Clear BSS */
 	PTR_LA	a0, _edata
 	PTR_LA	a2, _end
-1:	sw	zero, 0(a0)
-	addiu	a0, a0, 4
+1:	PTR_S	zero, 0(a0)
+	PTR_ADDIU a0, a0, PTRSIZE
 	bne	a2, a0, 1b
 
 	PTR_LA	a0, (.heap)	     /* heap address */
-- 
GitLab


From d6c10a46b442c6998dee963f682e0b01727bc0ae Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:31:59 +0100
Subject: [PATCH 1726/4076] fpga: altera-fpga2sdram: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/017b9e17a0c88b2a633467633d304639e7765926.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/altera-fpga2sdram.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/altera-fpga2sdram.c b/drivers/fpga/altera-fpga2sdram.c
index 1fa2ccc321abf..6b60ca004345d 100644
--- a/drivers/fpga/altera-fpga2sdram.c
+++ b/drivers/fpga/altera-fpga2sdram.c
@@ -147,20 +147,18 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int alt_fpga_bridge_remove(struct platform_device *pdev)
+static void alt_fpga_bridge_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *br = platform_get_drvdata(pdev);
 
 	fpga_bridge_unregister(br);
-
-	return 0;
 }
 
 MODULE_DEVICE_TABLE(of, altera_fpga_of_match);
 
 static struct platform_driver altera_fpga_driver = {
 	.probe = alt_fpga_bridge_probe,
-	.remove = alt_fpga_bridge_remove,
+	.remove_new = alt_fpga_bridge_remove,
 	.driver = {
 		.name	= "altera_fpga2sdram_bridge",
 		.of_match_table = of_match_ptr(altera_fpga_of_match),
-- 
GitLab


From 0d0a3748a2cb38f9da1f08d357688ebd982eb788 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Sat, 2 Dec 2023 14:14:18 +0300
Subject: [PATCH 1727/4076] mips: dmi: Fix early remap on MIPS32

dmi_early_remap() has been defined as ioremap_cache() which on MIPS32 gets
to be converted to the VM-based mapping. DMI early remapping is performed
at the setup_arch() stage with no VM available. So calling the
dmi_early_remap() for MIPS32 causes the system to crash at the early boot
time. Fix that by converting dmi_early_remap() to the uncached remapping
which is always available on both 32 and 64-bits MIPS systems.

Note this change shall not cause any regressions on the current DMI
support implementation because on the early boot-up stage neither MIPS32
nor MIPS64 has the cacheable ioremapping support anyway.

Fixes: be8fa1cb444c ("MIPS: Add support for Desktop Management Interface (DMI)")
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/include/asm/dmi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/include/asm/dmi.h b/arch/mips/include/asm/dmi.h
index 27415a288adf5..dc397f630c660 100644
--- a/arch/mips/include/asm/dmi.h
+++ b/arch/mips/include/asm/dmi.h
@@ -5,7 +5,7 @@
 #include <linux/io.h>
 #include <linux/memblock.h>
 
-#define dmi_early_remap(x, l)		ioremap_cache(x, l)
+#define dmi_early_remap(x, l)		ioremap(x, l)
 #define dmi_early_unmap(x, l)		iounmap(x)
 #define dmi_remap(x, l)			ioremap_cache(x, l)
 #define dmi_unmap(x)			iounmap(x)
-- 
GitLab


From 15732fa43b50cdafb680a0389531fa75974114e6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:00 +0100
Subject: [PATCH 1728/4076] fpga: altera-freeze-bridge: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/7f4fcb23b25400c6711848105823081e032c5266.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/altera-freeze-bridge.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/altera-freeze-bridge.c b/drivers/fpga/altera-freeze-bridge.c
index 0c3fb82269089..44061cb16f877 100644
--- a/drivers/fpga/altera-freeze-bridge.c
+++ b/drivers/fpga/altera-freeze-bridge.c
@@ -253,18 +253,16 @@ static int altera_freeze_br_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int altera_freeze_br_remove(struct platform_device *pdev)
+static void altera_freeze_br_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *br = platform_get_drvdata(pdev);
 
 	fpga_bridge_unregister(br);
-
-	return 0;
 }
 
 static struct platform_driver altera_freeze_br_driver = {
 	.probe = altera_freeze_br_probe,
-	.remove = altera_freeze_br_remove,
+	.remove_new = altera_freeze_br_remove,
 	.driver = {
 		.name	= "altera_freeze_br",
 		.of_match_table = altera_freeze_br_of_match,
-- 
GitLab


From 0f5cc249ff73552d3bd864e62f85841dafaa107d Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Sat, 2 Dec 2023 14:14:19 +0300
Subject: [PATCH 1729/4076] mips: Fix incorrect max_low_pfn adjustment

max_low_pfn variable is incorrectly adjusted if the kernel is built with
high memory support and the later is detected in a running system, so the
memory which actually can be directly mapped is getting into the highmem
zone. See the ZONE_NORMAL range on my MIPS32r5 system:

> Zone ranges:
>   DMA      [mem 0x0000000000000000-0x0000000000ffffff]
>   Normal   [mem 0x0000000001000000-0x0000000007ffffff]
>   HighMem  [mem 0x0000000008000000-0x000000020fffffff]

while the zones are supposed to look as follows:

> Zone ranges:
>   DMA      [mem 0x0000000000000000-0x0000000000ffffff]
>   Normal   [mem 0x0000000001000000-0x000000001fffffff]
>   HighMem  [mem 0x0000000020000000-0x000000020fffffff]

Even though the physical memory within the range [0x08000000;0x20000000]
belongs to MMIO on our system, we don't really want it to be considered as
high memory since on MIPS32 that range still can be directly mapped.

Note there might be other problems caused by the max_low_pfn variable
misconfiguration. For instance high_memory variable is initialize with
virtual address corresponding to the max_low_pfn PFN, and by design it
must define the upper bound on direct map memory, then end of the normal
zone. That in its turn potentially may cause problems in accessing the
memory by means of the /dev/mem and /dev/kmem devices.

Let's fix the discovered misconfiguration then. It turns out the commit
a94e4f24ec83 ("MIPS: init: Drop boot_mem_map") didn't introduce the
max_low_pfn adjustment quite correct. If the kernel is built with high
memory support and the system is equipped with high memory, the
max_low_pfn variable will need to be initialized with PFN of the most
upper directly reachable memory address so the zone normal would be
correctly setup. On MIPS that PFN corresponds to PFN_DOWN(HIGHMEM_START).
If the system is built with no high memory support and one is detected in
the running system, we'll just need to adjust the max_pfn variable to
discard the found high memory from the system and leave the max_low_pfn as
is, since the later will be less than PFN_DOWN(HIGHMEM_START) anyway by
design of the for_each_memblock() loop performed a bit early in the
bootmem_init() method.

Fixes: a94e4f24ec83 ("MIPS: init: Drop boot_mem_map")
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/setup.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 2d2ca024bd47a..0461ab49e8f1a 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -321,11 +321,11 @@ static void __init bootmem_init(void)
 		panic("Incorrect memory mapping !!!");
 
 	if (max_pfn > PFN_DOWN(HIGHMEM_START)) {
+		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 #ifdef CONFIG_HIGHMEM
-		highstart_pfn = PFN_DOWN(HIGHMEM_START);
+		highstart_pfn = max_low_pfn;
 		highend_pfn = max_pfn;
 #else
-		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 		max_pfn = max_low_pfn;
 #endif
 	}
-- 
GitLab


From 52db8bdb6b1f87aa75e9991a47f5d42e22c2068f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:01 +0100
Subject: [PATCH 1730/4076] fpga: altera-hps2fpga: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/7a56558f7e5aa34bf0b21d22f9036a136a2b7322.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/altera-hps2fpga.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/altera-hps2fpga.c b/drivers/fpga/altera-hps2fpga.c
index 5786635032972..6f8e24be19c6d 100644
--- a/drivers/fpga/altera-hps2fpga.c
+++ b/drivers/fpga/altera-hps2fpga.c
@@ -191,7 +191,7 @@ err:
 	return ret;
 }
 
-static int alt_fpga_bridge_remove(struct platform_device *pdev)
+static void alt_fpga_bridge_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *bridge = platform_get_drvdata(pdev);
 	struct altera_hps2fpga_data *priv = bridge->priv;
@@ -199,15 +199,13 @@ static int alt_fpga_bridge_remove(struct platform_device *pdev)
 	fpga_bridge_unregister(bridge);
 
 	clk_disable_unprepare(priv->clk);
-
-	return 0;
 }
 
 MODULE_DEVICE_TABLE(of, altera_fpga_of_match);
 
 static struct platform_driver alt_fpga_bridge_driver = {
 	.probe = alt_fpga_bridge_probe,
-	.remove = alt_fpga_bridge_remove,
+	.remove_new = alt_fpga_bridge_remove,
 	.driver = {
 		.name	= "altera_hps2fpga_bridge",
 		.of_match_table = of_match_ptr(altera_fpga_of_match),
-- 
GitLab


From b27e9508288fbab8d95ef307d2ec124c0b5062f3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:02 +0100
Subject: [PATCH 1731/4076] fpga: dfl-afu-main: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/351a4508a2feeba05b2c311fa8596ca1ad77f467.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/dfl-afu-main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c
index 7f621e96d3b8d..c0a75ca360d69 100644
--- a/drivers/fpga/dfl-afu-main.c
+++ b/drivers/fpga/dfl-afu-main.c
@@ -932,15 +932,13 @@ exit:
 	return ret;
 }
 
-static int afu_remove(struct platform_device *pdev)
+static void afu_remove(struct platform_device *pdev)
 {
 	dev_dbg(&pdev->dev, "%s\n", __func__);
 
 	dfl_fpga_dev_ops_unregister(pdev);
 	dfl_fpga_dev_feature_uinit(pdev);
 	afu_dev_destroy(pdev);
-
-	return 0;
 }
 
 static const struct attribute_group *afu_dev_groups[] = {
@@ -956,7 +954,7 @@ static struct platform_driver afu_driver = {
 		.dev_groups = afu_dev_groups,
 	},
 	.probe   = afu_probe,
-	.remove  = afu_remove,
+	.remove_new = afu_remove,
 };
 
 static int __init afu_init(void)
-- 
GitLab


From e1a9ae45736989c972a8d1c151bc390678ae6205 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Sat, 2 Dec 2023 14:14:20 +0300
Subject: [PATCH 1732/4076] mips: Fix max_mapnr being uninitialized on early
 stages

max_mapnr variable is utilized in the pfn_valid() method in order to
determine the upper PFN space boundary. Having it uninitialized
effectively makes any PFN passed to that method invalid. That in its turn
causes the kernel mm-subsystem occasion malfunctions even after the
max_mapnr variable is actually properly updated. For instance,
pfn_valid() is called in the init_unavailable_range() method in the
framework of the calls-chain on MIPS:
setup_arch()
+-> paging_init()
    +-> free_area_init()
        +-> memmap_init()
            +-> memmap_init_zone_range()
                +-> init_unavailable_range()

Since pfn_valid() always returns "false" value before max_mapnr is
initialized in the mem_init() method, any flatmem page-holes will be left
in the poisoned/uninitialized state including the IO-memory pages. Thus
any further attempts to map/remap the IO-memory by using MMU may fail.
In particular it happened in my case on attempt to map the SRAM region.
The kernel bootup procedure just crashed on the unhandled unaligned access
bug raised in the __update_cache() method:

> Unhandled kernel unaligned access[#1]:
> CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.7.0-rc1-XXX-dirty #2056
> ...
> Call Trace:
> [<8011ef9c>] __update_cache+0x88/0x1bc
> [<80385944>] ioremap_page_range+0x110/0x2a4
> [<80126948>] ioremap_prot+0x17c/0x1f4
> [<80711b80>] __devm_ioremap+0x8c/0x120
> [<80711e0c>] __devm_ioremap_resource+0xf4/0x218
> [<808bf244>] sram_probe+0x4f4/0x930
> [<80889d20>] platform_probe+0x68/0xec
> ...

Let's fix the problem by initializing the max_mapnr variable as soon as
the required data is available. In particular it can be done right in the
paging_init() method before free_area_init() is called since all the PFN
zone boundaries have already been calculated by that time.

Cc: stable@vger.kernel.org
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/mm/init.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 5dcb525a89954..6e368a4658b54 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -422,7 +422,12 @@ void __init paging_init(void)
 		       (highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10));
 		max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn;
 	}
+
+	max_mapnr = highend_pfn ? highend_pfn : max_low_pfn;
+#else
+	max_mapnr = max_low_pfn;
 #endif
+	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 
 	free_area_init(max_zone_pfns);
 }
@@ -458,13 +463,6 @@ void __init mem_init(void)
 	 */
 	BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (PFN_PTE_SHIFT > PAGE_SHIFT));
 
-#ifdef CONFIG_HIGHMEM
-	max_mapnr = highend_pfn ? highend_pfn : max_low_pfn;
-#else
-	max_mapnr = max_low_pfn;
-#endif
-	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
-
 	maar_init();
 	memblock_free_all();
 	setup_zero_pages();	/* Setup zeroed pages.  */
-- 
GitLab


From f04ed6b174058d82a2230f70796633327dc758ba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:03 +0100
Subject: [PATCH 1733/4076] fpga: dfl-fme-br: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/be0728ae8e047c6b443492dc563cf92f397b269d.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/dfl-fme-br.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/dfl-fme-br.c b/drivers/fpga/dfl-fme-br.c
index 808d1f4d76df8..0b01b38952776 100644
--- a/drivers/fpga/dfl-fme-br.c
+++ b/drivers/fpga/dfl-fme-br.c
@@ -78,7 +78,7 @@ static int fme_br_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int fme_br_remove(struct platform_device *pdev)
+static void fme_br_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *br = platform_get_drvdata(pdev);
 	struct fme_br_priv *priv = br->priv;
@@ -89,8 +89,6 @@ static int fme_br_remove(struct platform_device *pdev)
 		put_device(&priv->port_pdev->dev);
 	if (priv->port_ops)
 		dfl_fpga_port_ops_put(priv->port_ops);
-
-	return 0;
 }
 
 static struct platform_driver fme_br_driver = {
@@ -98,7 +96,7 @@ static struct platform_driver fme_br_driver = {
 		.name    = DFL_FPGA_FME_BRIDGE,
 	},
 	.probe   = fme_br_probe,
-	.remove  = fme_br_remove,
+	.remove_new = fme_br_remove,
 };
 
 module_platform_driver(fme_br_driver);
-- 
GitLab


From 1c0150229f6a658687c245dfc4dcfa3fae69df49 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Sat, 2 Dec 2023 14:14:21 +0300
Subject: [PATCH 1734/4076] mips: Optimize max_mapnr init procedure

max_mapnr defines the upper boundary of the pages space in the system.
Currently in case if HIGHMEM is available it's calculated based on the
upper high memory PFN limit value. Seeing there is a case when it isn't
fully correct let's optimize out the max_mapnr variable initialization
procedure to cover all the handled in the paging_init() method cases:
1. If CPU has DC-aliases, then high memory is unavailable so the PFNs
upper boundary is determined by max_low_pfn.
2. Otherwise if high memory is available, use highend_pfn value
representing the upper high memory PFNs limit.
3. Otherwise no high memory is available so set max_mapnr with the
low-memory upper limit.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/mm/init.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 6e368a4658b54..b2dce07116e8a 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -421,9 +421,13 @@ void __init paging_init(void)
 		       " %ldk highmem ignored\n",
 		       (highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10));
 		max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn;
-	}
 
-	max_mapnr = highend_pfn ? highend_pfn : max_low_pfn;
+		max_mapnr = max_low_pfn;
+	} else if (highend_pfn) {
+		max_mapnr = highend_pfn;
+	} else {
+		max_mapnr = max_low_pfn;
+	}
 #else
 	max_mapnr = max_low_pfn;
 #endif
-- 
GitLab


From 851beb427b44c24dfa7baaa3ec4d790c33d43b93 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:04 +0100
Subject: [PATCH 1735/4076] fpga: dfl-fme-main: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/438bb4797984fbfd0cef501010a64fa1e42ad9f4.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/dfl-fme-main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/dfl-fme-main.c b/drivers/fpga/dfl-fme-main.c
index 3dcf990bd261f..a2b5da0093dac 100644
--- a/drivers/fpga/dfl-fme-main.c
+++ b/drivers/fpga/dfl-fme-main.c
@@ -730,13 +730,11 @@ exit:
 	return ret;
 }
 
-static int fme_remove(struct platform_device *pdev)
+static void fme_remove(struct platform_device *pdev)
 {
 	dfl_fpga_dev_ops_unregister(pdev);
 	dfl_fpga_dev_feature_uinit(pdev);
 	fme_dev_destroy(pdev);
-
-	return 0;
 }
 
 static const struct attribute_group *fme_dev_groups[] = {
@@ -751,7 +749,7 @@ static struct platform_driver fme_driver = {
 		.dev_groups = fme_dev_groups,
 	},
 	.probe   = fme_probe,
-	.remove  = fme_remove,
+	.remove_new = fme_remove,
 };
 
 module_platform_driver(fme_driver);
-- 
GitLab


From 4af318c979ec79a201a297d89b93bec20099dbdd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:05 +0100
Subject: [PATCH 1736/4076] fpga: dfl-fme-region: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/13187db1642f81f04e55be0a26045f09ccc95d37.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/dfl-fme-region.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/dfl-fme-region.c b/drivers/fpga/dfl-fme-region.c
index 4aebde0a7f1c3..71616f8b4982d 100644
--- a/drivers/fpga/dfl-fme-region.c
+++ b/drivers/fpga/dfl-fme-region.c
@@ -61,15 +61,13 @@ eprobe_mgr_put:
 	return ret;
 }
 
-static int fme_region_remove(struct platform_device *pdev)
+static void fme_region_remove(struct platform_device *pdev)
 {
 	struct fpga_region *region = platform_get_drvdata(pdev);
 	struct fpga_manager *mgr = region->mgr;
 
 	fpga_region_unregister(region);
 	fpga_mgr_put(mgr);
-
-	return 0;
 }
 
 static struct platform_driver fme_region_driver = {
@@ -77,7 +75,7 @@ static struct platform_driver fme_region_driver = {
 		.name    = DFL_FPGA_FME_REGION,
 	},
 	.probe   = fme_region_probe,
-	.remove  = fme_region_remove,
+	.remove_new = fme_region_remove,
 };
 
 module_platform_driver(fme_region_driver);
-- 
GitLab


From e540b8c5da04c66ff610d3bf84a7566d9f6bffcf Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Sat, 2 Dec 2023 14:14:22 +0300
Subject: [PATCH 1737/4076] mips: mm: add slab availability checking in
 ioremap_prot

Recent commit a5f616483110 ("mm/ioremap: add slab availability checking in
ioremap_prot") added the slab availability check to the generic
ioremap_prot() implementation. It is reasonable to be done for the
MIPS32-specific method too since it also relies on the
get_vm_area_caller() function (by means of get_vm_area()) which requires
the slab allocator being up and running before being called.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/mm/ioremap.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index b6dad2fd5575d..d8243d61ef325 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -72,6 +72,10 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, unsigned long size,
 	    flags == _CACHE_UNCACHED)
 		return (void __iomem *) CKSEG1ADDR(phys_addr);
 
+	/* Early remaps should use the unmapped regions til' VM is available */
+	if (WARN_ON_ONCE(!slab_is_available()))
+		return NULL;
+
 	/*
 	 * Don't allow anybody to remap RAM that may be allocated by the page
 	 * allocator, since that could lead to races & data clobbering.
-- 
GitLab


From 84a313b7d296bb12560bb8b5f21421be35c1704d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:06 +0100
Subject: [PATCH 1738/4076] fpga: intel-m10-bmc-sec-update: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/8d7b192ade744a70da4d7bc681ee4e00f9d04ba9.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/intel-m10-bmc-sec-update.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c
index 31af2e08c825f..89851b1337097 100644
--- a/drivers/fpga/intel-m10-bmc-sec-update.c
+++ b/drivers/fpga/intel-m10-bmc-sec-update.c
@@ -730,15 +730,13 @@ fw_name_fail:
 	return ret;
 }
 
-static int m10bmc_sec_remove(struct platform_device *pdev)
+static void m10bmc_sec_remove(struct platform_device *pdev)
 {
 	struct m10bmc_sec *sec = dev_get_drvdata(&pdev->dev);
 
 	firmware_upload_unregister(sec->fwl);
 	kfree(sec->fw_name);
 	xa_erase(&fw_upload_xa, sec->fw_name_id);
-
-	return 0;
 }
 
 static const struct platform_device_id intel_m10bmc_sec_ids[] = {
@@ -760,7 +758,7 @@ MODULE_DEVICE_TABLE(platform, intel_m10bmc_sec_ids);
 
 static struct platform_driver intel_m10bmc_sec_driver = {
 	.probe = m10bmc_sec_probe,
-	.remove = m10bmc_sec_remove,
+	.remove_new = m10bmc_sec_remove,
 	.driver = {
 		.name = "intel-m10bmc-sec-update",
 		.dev_groups = m10bmc_sec_attr_groups,
-- 
GitLab


From 8abe405a5c5f07ddb6ca65e682ea95fdcaa3beca Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:07 +0100
Subject: [PATCH 1739/4076] fpga: of-fpga-region: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/1ff30f297310bf048af567924c0fd4cb7c6c3240.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/of-fpga-region.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c
index a6affd83f2757..8526a5a86f0cb 100644
--- a/drivers/fpga/of-fpga-region.c
+++ b/drivers/fpga/of-fpga-region.c
@@ -425,20 +425,18 @@ eprobe_mgr_put:
 	return ret;
 }
 
-static int of_fpga_region_remove(struct platform_device *pdev)
+static void of_fpga_region_remove(struct platform_device *pdev)
 {
 	struct fpga_region *region = platform_get_drvdata(pdev);
 	struct fpga_manager *mgr = region->mgr;
 
 	fpga_region_unregister(region);
 	fpga_mgr_put(mgr);
-
-	return 0;
 }
 
 static struct platform_driver of_fpga_region_driver = {
 	.probe = of_fpga_region_probe,
-	.remove = of_fpga_region_remove,
+	.remove_new = of_fpga_region_remove,
 	.driver = {
 		.name	= "of-fpga-region",
 		.of_match_table = of_match_ptr(fpga_region_of_match),
-- 
GitLab


From 4bfc170a319835a58ac94f2b95317632ee180584 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:08 +0100
Subject: [PATCH 1740/4076] fpga: socfpga-a10: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/da701d72522dde185becc15096342786a3a12153.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/socfpga-a10.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/socfpga-a10.c b/drivers/fpga/socfpga-a10.c
index cc4861e345c93..4c03513b8f03b 100644
--- a/drivers/fpga/socfpga-a10.c
+++ b/drivers/fpga/socfpga-a10.c
@@ -517,15 +517,13 @@ static int socfpga_a10_fpga_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int socfpga_a10_fpga_remove(struct platform_device *pdev)
+static void socfpga_a10_fpga_remove(struct platform_device *pdev)
 {
 	struct fpga_manager *mgr = platform_get_drvdata(pdev);
 	struct a10_fpga_priv *priv = mgr->priv;
 
 	fpga_mgr_unregister(mgr);
 	clk_disable_unprepare(priv->clk);
-
-	return 0;
 }
 
 static const struct of_device_id socfpga_a10_fpga_of_match[] = {
@@ -537,7 +535,7 @@ MODULE_DEVICE_TABLE(of, socfpga_a10_fpga_of_match);
 
 static struct platform_driver socfpga_a10_fpga_driver = {
 	.probe = socfpga_a10_fpga_probe,
-	.remove = socfpga_a10_fpga_remove,
+	.remove_new = socfpga_a10_fpga_remove,
 	.driver = {
 		.name	= "socfpga_a10_fpga_manager",
 		.of_match_table = socfpga_a10_fpga_of_match,
-- 
GitLab


From 24bf6f4be4f80fd0ff3f7b2f5736ebe71dae4a28 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:09 +0100
Subject: [PATCH 1741/4076] fpga: stratix10-soc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/ab8328e82109b6ef14b2ad59889aee5f99264435.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/stratix10-soc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c
index cacb9cc5757e7..2c0def7d7cbb1 100644
--- a/drivers/fpga/stratix10-soc.c
+++ b/drivers/fpga/stratix10-soc.c
@@ -436,15 +436,13 @@ probe_err:
 	return ret;
 }
 
-static int s10_remove(struct platform_device *pdev)
+static void s10_remove(struct platform_device *pdev)
 {
 	struct fpga_manager *mgr = platform_get_drvdata(pdev);
 	struct s10_priv *priv = mgr->priv;
 
 	fpga_mgr_unregister(mgr);
 	stratix10_svc_free_channel(priv->chan);
-
-	return 0;
 }
 
 static const struct of_device_id s10_of_match[] = {
@@ -457,7 +455,7 @@ MODULE_DEVICE_TABLE(of, s10_of_match);
 
 static struct platform_driver s10_driver = {
 	.probe = s10_probe,
-	.remove = s10_remove,
+	.remove_new = s10_remove,
 	.driver = {
 		.name	= "Stratix10 SoC FPGA manager",
 		.of_match_table = of_match_ptr(s10_of_match),
-- 
GitLab


From a584df303163e9aa8bdab3902fb0fb37ce1fa3ac Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:10 +0100
Subject: [PATCH 1742/4076] fpga: xilinx-pr-decoupler: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/3e37e7cf91749fbaba67619f4ffc6a9a7352a671.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/xilinx-pr-decoupler.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/xilinx-pr-decoupler.c b/drivers/fpga/xilinx-pr-decoupler.c
index 68835896f180e..788dd2f63a652 100644
--- a/drivers/fpga/xilinx-pr-decoupler.c
+++ b/drivers/fpga/xilinx-pr-decoupler.c
@@ -150,7 +150,7 @@ err_clk:
 	return err;
 }
 
-static int xlnx_pr_decoupler_remove(struct platform_device *pdev)
+static void xlnx_pr_decoupler_remove(struct platform_device *pdev)
 {
 	struct fpga_bridge *bridge = platform_get_drvdata(pdev);
 	struct xlnx_pr_decoupler_data *p = bridge->priv;
@@ -158,13 +158,11 @@ static int xlnx_pr_decoupler_remove(struct platform_device *pdev)
 	fpga_bridge_unregister(bridge);
 
 	clk_unprepare(p->clk);
-
-	return 0;
 }
 
 static struct platform_driver xlnx_pr_decoupler_driver = {
 	.probe = xlnx_pr_decoupler_probe,
-	.remove = xlnx_pr_decoupler_remove,
+	.remove_new = xlnx_pr_decoupler_remove,
 	.driver = {
 		.name = "xlnx_pr_decoupler",
 		.of_match_table = xlnx_pr_decoupler_of_match,
-- 
GitLab


From efe8ee1a8b9a89835dcbbec8cebc9d5a27428914 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Sat, 2 Dec 2023 14:14:23 +0300
Subject: [PATCH 1743/4076] mips: Set dump-stack arch description

In the framework of the MIPS architecture the mips_set_machine_name()
method is defined to set the machine name. The name currently is only used
in the /proc/cpuinfo file content generation. Let's have it utilized to
mach-personalize the dump-stack data too in a way it's done on ARM, ARM64,
RISC-V, etc.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/prom.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index f88ce78e13e3a..6062e6fa589a8 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -28,6 +28,8 @@ __init void mips_set_machine_name(const char *name)
 
 	strscpy(mips_machine_name, name, sizeof(mips_machine_name));
 	pr_info("MIPS: machine is %s\n", mips_get_machine_name());
+
+	dump_stack_set_arch_desc(name);
 }
 
 char *mips_get_machine_name(void)
-- 
GitLab


From c849ecb2ae8413f86c84627cb0af06dffce4e215 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 19 Dec 2023 18:32:11 +0100
Subject: [PATCH 1744/4076] fpga: zynq-fpga: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Link: https://lore.kernel.org/r/e63d4155f96f3504f7e3d6a4775c3807c90dd6ce.1703006638.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
 drivers/fpga/zynq-fpga.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c
index 96611d424a104..0ac93183d2016 100644
--- a/drivers/fpga/zynq-fpga.c
+++ b/drivers/fpga/zynq-fpga.c
@@ -618,7 +618,7 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int zynq_fpga_remove(struct platform_device *pdev)
+static void zynq_fpga_remove(struct platform_device *pdev)
 {
 	struct zynq_fpga_priv *priv;
 	struct fpga_manager *mgr;
@@ -629,8 +629,6 @@ static int zynq_fpga_remove(struct platform_device *pdev)
 	fpga_mgr_unregister(mgr);
 
 	clk_unprepare(priv->clk);
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -644,7 +642,7 @@ MODULE_DEVICE_TABLE(of, zynq_fpga_of_match);
 
 static struct platform_driver zynq_fpga_driver = {
 	.probe = zynq_fpga_probe,
-	.remove = zynq_fpga_remove,
+	.remove_new = zynq_fpga_remove,
 	.driver = {
 		.name = "zynq_fpga_manager",
 		.of_match_table = of_match_ptr(zynq_fpga_of_match),
-- 
GitLab


From 5e72f1fe23839bd2093693a357a6fac8e5463483 Mon Sep 17 00:00:00 2001
From: Jean Delvare <jdelvare@suse.de>
Date: Sat, 2 Dec 2023 21:43:53 +0100
Subject: [PATCH 1745/4076] leds: rgb: Drop obsolete dependency on COMPILE_TEST

Since commit 0166dc11be91 ("of: make CONFIG_OF user selectable"), it
is possible to test-build any driver which depends on OF on any
architecture by explicitly selecting OF. Therefore depending on
COMPILE_TEST as an alternative is no longer needed.

Signed-off-by: Jean Delvare <jdelvare@suse.de>
Link: https://lore.kernel.org/r/20231202214353.7c02f23c@endymion.delvare
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/rgb/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/leds/rgb/Kconfig b/drivers/leds/rgb/Kconfig
index a6a21f5646734..e66bd21b9852e 100644
--- a/drivers/leds/rgb/Kconfig
+++ b/drivers/leds/rgb/Kconfig
@@ -4,7 +4,7 @@ if LEDS_CLASS_MULTICOLOR
 
 config LEDS_GROUP_MULTICOLOR
 	tristate "LEDs group multi-color support"
-	depends on OF || COMPILE_TEST
+	depends on OF
 	help
 	  This option enables support for monochrome LEDs that are grouped
 	  into multicolor LEDs which is useful in the case where LEDs of
-- 
GitLab


From d3578b4982e6ebccbd898806ac86b2db4b2bcc5e Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 14 Dec 2023 20:40:08 +0200
Subject: [PATCH 1746/4076] leds: max5970: Remove unused variable

leds-max5970.c:50:21: warning: variable 'num_leds' set but not used [-Wunused-but-set-variable]

Remove unused variable.

Fixes: 736214b4b02a ("leds: max5970: Add support for max5970")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231214184050.1272848-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-max5970.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/leds/leds-max5970.c b/drivers/leds/leds-max5970.c
index 456a16a47450e..7959d079ae942 100644
--- a/drivers/leds/leds-max5970.c
+++ b/drivers/leds/leds-max5970.c
@@ -45,7 +45,7 @@ static int max5970_led_probe(struct platform_device *pdev)
 	struct regmap *regmap;
 	struct device_node *led_node, *child;
 	struct max5970_led *ddata;
-	int ret = -ENODEV, num_leds = 0;
+	int ret = -ENODEV;
 
 	regmap = dev_get_regmap(pdev->dev.parent, NULL);
 	if (!regmap)
@@ -89,7 +89,6 @@ static int max5970_led_probe(struct platform_device *pdev)
 			dev_err(dev, "Failed to initialize LED %u\n", reg);
 			return ret;
 		}
-		num_leds++;
 	}
 
 	return ret;
-- 
GitLab


From 6d63d05e26f8d5e22308efc25793660101fd7602 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 14 Dec 2023 20:40:09 +0200
Subject: [PATCH 1747/4076] leds: max5970: Make use of device properties

Convert the module to be property provider agnostic and allow
it to be used on non-OF platforms.

Add mod_devicetable.h include.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231214184050.1272848-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-max5970.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/leds/leds-max5970.c b/drivers/leds/leds-max5970.c
index 7959d079ae942..de57b385b4f63 100644
--- a/drivers/leds/leds-max5970.c
+++ b/drivers/leds/leds-max5970.c
@@ -9,8 +9,9 @@
 
 #include <linux/leds.h>
 #include <linux/mfd/max5970.h>
-#include <linux/of.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 
 #define ldev_to_maxled(c)       container_of(c, struct max5970_led, cdev)
@@ -40,25 +41,24 @@ static int max5970_led_set_brightness(struct led_classdev *cdev,
 
 static int max5970_led_probe(struct platform_device *pdev)
 {
+	struct fwnode_handle *led_node, *child;
 	struct device *dev = &pdev->dev;
-	struct device_node *np = dev_of_node(dev->parent);
 	struct regmap *regmap;
-	struct device_node *led_node, *child;
 	struct max5970_led *ddata;
 	int ret = -ENODEV;
 
-	regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	regmap = dev_get_regmap(dev->parent, NULL);
 	if (!regmap)
 		return -ENODEV;
 
-	led_node = of_get_child_by_name(np, "leds");
+	led_node = device_get_named_child_node(dev->parent, "leds");
 	if (!led_node)
 		return -ENODEV;
 
-	for_each_available_child_of_node(led_node, child) {
+	fwnode_for_each_available_child_node(led_node, child) {
 		u32 reg;
 
-		if (of_property_read_u32(child, "reg", &reg))
+		if (fwnode_property_read_u32(child, "reg", &reg))
 			continue;
 
 		if (reg >= MAX5970_NUM_LEDS) {
@@ -68,7 +68,7 @@ static int max5970_led_probe(struct platform_device *pdev)
 
 		ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
 		if (!ddata) {
-			of_node_put(child);
+			fwnode_handle_put(child);
 			return -ENOMEM;
 		}
 
@@ -76,8 +76,8 @@ static int max5970_led_probe(struct platform_device *pdev)
 		ddata->regmap = regmap;
 		ddata->dev = dev;
 
-		if (of_property_read_string(child, "label", &ddata->cdev.name))
-			ddata->cdev.name = child->name;
+		if (fwnode_property_read_string(child, "label", &ddata->cdev.name))
+			ddata->cdev.name = fwnode_get_name(child);
 
 		ddata->cdev.max_brightness = 1;
 		ddata->cdev.brightness_set_blocking = max5970_led_set_brightness;
@@ -85,7 +85,7 @@ static int max5970_led_probe(struct platform_device *pdev)
 
 		ret = devm_led_classdev_register(dev, &ddata->cdev);
 		if (ret < 0) {
-			of_node_put(child);
+			fwnode_handle_put(child);
 			dev_err(dev, "Failed to initialize LED %u\n", reg);
 			return ret;
 		}
@@ -100,8 +100,8 @@ static struct platform_driver max5970_led_driver = {
 	},
 	.probe = max5970_led_probe,
 };
-
 module_platform_driver(max5970_led_driver);
+
 MODULE_AUTHOR("Patrick Rudolph <patrick.rudolph@9elements.com>");
 MODULE_AUTHOR("Naresh Solanki <Naresh.Solanki@9elements.com>");
 MODULE_DESCRIPTION("MAX5970_hot-swap controller LED driver");
-- 
GitLab


From e7baa5b437a782308b86c1517ae252fd1353eb0b Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 14 Dec 2023 20:40:10 +0200
Subject: [PATCH 1748/4076] leds: max5970: Make use of dev_err_probe()

Simplify the error handling in probe function by switching from
dev_err() to dev_err_probe().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231214184050.1272848-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-max5970.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/leds/leds-max5970.c b/drivers/leds/leds-max5970.c
index de57b385b4f63..60db3c28d7d97 100644
--- a/drivers/leds/leds-max5970.c
+++ b/drivers/leds/leds-max5970.c
@@ -62,7 +62,7 @@ static int max5970_led_probe(struct platform_device *pdev)
 			continue;
 
 		if (reg >= MAX5970_NUM_LEDS) {
-			dev_err(dev, "invalid LED (%u >= %d)\n", reg, MAX5970_NUM_LEDS);
+			dev_err_probe(dev, -EINVAL, "invalid LED (%u >= %d)\n", reg, MAX5970_NUM_LEDS);
 			continue;
 		}
 
@@ -86,8 +86,7 @@ static int max5970_led_probe(struct platform_device *pdev)
 		ret = devm_led_classdev_register(dev, &ddata->cdev);
 		if (ret < 0) {
 			fwnode_handle_put(child);
-			dev_err(dev, "Failed to initialize LED %u\n", reg);
-			return ret;
+			return dev_err_probe(dev, ret, "Failed to initialize LED %u\n", reg);
 		}
 	}
 
-- 
GitLab


From 808c7881876756dfcd8c4d0c3efc27c9262da822 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 14 Dec 2023 20:40:11 +0200
Subject: [PATCH 1749/4076] leds: max5970: Add missing headers

Don't inherit headers "by chance" from others.
Include the needed ones explicitly.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231214184050.1272848-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-max5970.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/leds/leds-max5970.c b/drivers/leds/leds-max5970.c
index 60db3c28d7d97..56a584311581a 100644
--- a/drivers/leds/leds-max5970.c
+++ b/drivers/leds/leds-max5970.c
@@ -7,9 +7,13 @@
  * Author: Patrick Rudolph <patrick.rudolph@9elements.com>
  */
 
+#include <linux/bits.h>
+#include <linux/container_of.h>
+#include <linux/device.h>
 #include <linux/leds.h>
 #include <linux/mfd/max5970.h>
 #include <linux/mod_devicetable.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
-- 
GitLab


From 06c5206ccdb459de95bb8d558602d2a722dd4bbc Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 14 Dec 2023 21:21:31 +0200
Subject: [PATCH 1750/4076] leds: sun50i-a100: Convert to be agnostic to
 property provider

Convert the driver to be agnostic to the property provider.
LEDS subsytem is not dependent on OF, so no need to make drivers
be a such.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Link: https://lore.kernel.org/r/20231214192131.1309912-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/Kconfig            |  2 +-
 drivers/leds/leds-sun50i-a100.c | 46 ++++++++++++++++-----------------
 2 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index a2a4689e05020..d721b254e1e45 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -305,7 +305,7 @@ config LEDS_COBALT_RAQ
 
 config LEDS_SUN50I_A100
 	tristate "LED support for Allwinner A100 RGB LED controller"
-	depends on LEDS_CLASS_MULTICOLOR && OF
+	depends on LEDS_CLASS_MULTICOLOR
 	depends on ARCH_SUNXI || COMPILE_TEST
 	help
 	  This option enables support for the RGB LED controller found
diff --git a/drivers/leds/leds-sun50i-a100.c b/drivers/leds/leds-sun50i-a100.c
index 171cefd1ea0d3..62d21c3a35757 100644
--- a/drivers/leds/leds-sun50i-a100.c
+++ b/drivers/leds/leds-sun50i-a100.c
@@ -15,10 +15,11 @@
 #include <linux/io.h>
 #include <linux/led-class-multicolor.h>
 #include <linux/leds.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
+#include <linux/property.h>
 #include <linux/reset.h>
 #include <linux/spinlock.h>
 
@@ -247,13 +248,13 @@ static const char *const sun50i_a100_ledc_formats[] = {
 	"rgb", "rbg", "grb", "gbr", "brg", "bgr",
 };
 
-static int sun50i_a100_ledc_parse_format(const struct device_node *np,
+static int sun50i_a100_ledc_parse_format(struct device *dev,
 					 struct sun50i_a100_ledc *priv)
 {
 	const char *format = "grb";
 	u32 i;
 
-	of_property_read_string(np, "allwinner,pixel-format", &format);
+	device_property_read_string(dev, "allwinner,pixel-format", &format);
 
 	for (i = 0; i < ARRAY_SIZE(sun50i_a100_ledc_formats); i++) {
 		if (!strcmp(format, sun50i_a100_ledc_formats[i])) {
@@ -262,7 +263,7 @@ static int sun50i_a100_ledc_parse_format(const struct device_node *np,
 		}
 	}
 
-	return dev_err_probe(priv->dev, -EINVAL, "Bad pixel format '%s'\n", format);
+	return dev_err_probe(dev, -EINVAL, "Bad pixel format '%s'\n", format);
 }
 
 static void sun50i_a100_ledc_set_format(struct sun50i_a100_ledc *priv)
@@ -283,18 +284,18 @@ static const struct sun50i_a100_ledc_timing sun50i_a100_ledc_default_timing = {
 	.treset_ns = 300000,
 };
 
-static int sun50i_a100_ledc_parse_timing(const struct device_node *np,
+static int sun50i_a100_ledc_parse_timing(struct device *dev,
 					 struct sun50i_a100_ledc *priv)
 {
 	struct sun50i_a100_ledc_timing *timing = &priv->timing;
 
 	*timing = sun50i_a100_ledc_default_timing;
 
-	of_property_read_u32(np, "allwinner,t0h-ns", &timing->t0h_ns);
-	of_property_read_u32(np, "allwinner,t0l-ns", &timing->t0l_ns);
-	of_property_read_u32(np, "allwinner,t1h-ns", &timing->t1h_ns);
-	of_property_read_u32(np, "allwinner,t1l-ns", &timing->t1l_ns);
-	of_property_read_u32(np, "allwinner,treset-ns", &timing->treset_ns);
+	device_property_read_u32(dev, "allwinner,t0h-ns", &timing->t0h_ns);
+	device_property_read_u32(dev, "allwinner,t0l-ns", &timing->t0l_ns);
+	device_property_read_u32(dev, "allwinner,t1h-ns", &timing->t1h_ns);
+	device_property_read_u32(dev, "allwinner,t1l-ns", &timing->t1l_ns);
+	device_property_read_u32(dev, "allwinner,treset-ns", &timing->treset_ns);
 
 	return 0;
 }
@@ -388,13 +389,12 @@ static void sun50i_a100_ledc_dma_cleanup(void *data)
 
 static int sun50i_a100_ledc_probe(struct platform_device *pdev)
 {
-	const struct device_node *np = pdev->dev.of_node;
 	struct dma_slave_config dma_cfg = {};
 	struct led_init_data init_data = {};
 	struct sun50i_a100_ledc_led *led;
 	struct device *dev = &pdev->dev;
 	struct sun50i_a100_ledc *priv;
-	struct device_node *child;
+	struct fwnode_handle *child;
 	struct resource *mem;
 	u32 max_addr = 0;
 	u32 num_leds = 0;
@@ -404,19 +404,19 @@ static int sun50i_a100_ledc_probe(struct platform_device *pdev)
 	 * The maximum LED address must be known in sun50i_a100_ledc_resume() before
 	 * class device registration, so parse and validate the subnodes up front.
 	 */
-	for_each_available_child_of_node(np, child) {
+	device_for_each_child_node(dev, child) {
 		u32 addr, color;
 
-		ret = of_property_read_u32(child, "reg", &addr);
+		ret = fwnode_property_read_u32(child, "reg", &addr);
 		if (ret || addr >= LEDC_MAX_LEDS) {
-			of_node_put(child);
+			fwnode_handle_put(child);
 			return dev_err_probe(dev, -EINVAL, "'reg' must be between 0 and %d\n",
 					     LEDC_MAX_LEDS - 1);
 		}
 
-		ret = of_property_read_u32(child, "color", &color);
+		ret = fwnode_property_read_u32(child, "color", &color);
 		if (ret || color != LED_COLOR_ID_RGB) {
-			of_node_put(child);
+			fwnode_handle_put(child);
 			return dev_err_probe(dev, -EINVAL, "'color' must be LED_COLOR_ID_RGB\n");
 		}
 
@@ -437,11 +437,11 @@ static int sun50i_a100_ledc_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->lock);
 	dev_set_drvdata(dev, priv);
 
-	ret = sun50i_a100_ledc_parse_format(np, priv);
+	ret = sun50i_a100_ledc_parse_format(dev, priv);
 	if (ret)
 		return ret;
 
-	ret = sun50i_a100_ledc_parse_timing(np, priv);
+	ret = sun50i_a100_ledc_parse_timing(dev, priv);
 	if (ret)
 		return ret;
 
@@ -504,11 +504,11 @@ static int sun50i_a100_ledc_probe(struct platform_device *pdev)
 		return ret;
 
 	led = priv->leds;
-	for_each_available_child_of_node(np, child) {
+	device_for_each_child_node(dev, child) {
 		struct led_classdev *cdev;
 
 		/* The node was already validated above. */
-		of_property_read_u32(child, "reg", &led->addr);
+		fwnode_property_read_u32(child, "reg", &led->addr);
 
 		led->subled_info[0].color_index = LED_COLOR_ID_RED;
 		led->subled_info[0].channel = 0;
@@ -524,7 +524,7 @@ static int sun50i_a100_ledc_probe(struct platform_device *pdev)
 		cdev->max_brightness = U8_MAX;
 		cdev->brightness_set = sun50i_a100_ledc_brightness_set;
 
-		init_data.fwnode = of_fwnode_handle(child);
+		init_data.fwnode = child;
 
 		ret = led_classdev_multicolor_register_ext(dev, &led->mc_cdev, &init_data);
 		if (ret) {
@@ -540,7 +540,7 @@ static int sun50i_a100_ledc_probe(struct platform_device *pdev)
 	return 0;
 
 err_put_child:
-	of_node_put(child);
+	fwnode_handle_put(child);
 	while (led-- > priv->leds)
 		led_classdev_multicolor_unregister(&led->mc_cdev);
 	sun50i_a100_ledc_suspend(&pdev->dev);
-- 
GitLab


From afacb21834bb02785ddb0c3ec197208803b74faa Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 16 Dec 2023 21:05:33 +0100
Subject: [PATCH 1751/4076] leds: trigger: panic: Don't register panic notifier
 if creating the trigger failed

It doesn't make sense to register the panic notifier if creating the
panic trigger failed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/8a61e229-5388-46c7-919a-4d18cc7362b2@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-panic.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/leds/trigger/ledtrig-panic.c b/drivers/leds/trigger/ledtrig-panic.c
index 64abf2e91608a..5a6b21bfeb9af 100644
--- a/drivers/leds/trigger/ledtrig-panic.c
+++ b/drivers/leds/trigger/ledtrig-panic.c
@@ -64,10 +64,13 @@ static long led_panic_blink(int state)
 
 static int __init ledtrig_panic_init(void)
 {
+	led_trigger_register_simple("panic", &trigger);
+	if (!trigger)
+		return -ENOMEM;
+
 	atomic_notifier_chain_register(&panic_notifier_list,
 				       &led_trigger_panic_nb);
 
-	led_trigger_register_simple("panic", &trigger);
 	panic_blink = led_panic_blink;
 	return 0;
 }
-- 
GitLab


From 457caadce7ab71a54ee2d4f032ee4a55b4a28776 Mon Sep 17 00:00:00 2001
From: Jing Zhang <renyu.zj@linux.alibaba.com>
Date: Thu, 21 Dec 2023 14:03:13 +0800
Subject: [PATCH 1752/4076] perf vendor events: Remove UTF-8 characters from
 cmn.json

cmn.json contains UTF-8 characters in brief description which
could break the perf build on some distros.

Fix this issue by removing the UTF-8 characters from cmn.json.

without this fix:

  $find tools/perf/pmu-events/ -name "*.json" | xargs file -i | grep -v us-ascii
  tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json:                   application/json; charset=utf-8

with it:

  $ file -i tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json
  tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json: text/plain; charset=us-ascii

Fixes: 0b4de7bdf46c5215 ("perf jevents: Add support for Arm CMN PMU aliasing")
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.com>
Signed-off-by: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/1703138593-50486-1-git-send-email-renyu.zj@linux.alibaba.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json b/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json
index 428605c37d10b..5ec157c39f0df 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json
@@ -107,7 +107,7 @@
 		"EventName": "hnf_qos_hh_retry",
 		"EventidCode": "0xe",
 		"NodeType": "0x5",
-		"BriefDescription": "Counts number of times a HighHigh priority request is protocolretried at the HN‑F.",
+		"BriefDescription": "Counts number of times a HighHigh priority request is protocolretried at the HN-F.",
 		"Unit": "arm_cmn",
 		"Compat": "(434|436|43c|43a).*"
 	},
-- 
GitLab


From 22887dfba0633c09444562722f0cf68f61ec9a50 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:20 -0500
Subject: [PATCH 1753/4076] ring-buffer: Clear pages on error in
 ring_buffer_subbuf_order_set() failure

On failure to allocate ring buffer pages, the pointer to the CPU buffer
pages is freed, but the pages that were allocated previously were not.
Make sure they are freed too.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185629.179352802@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: f9b94daa542a ("tracing: Set new size of the ring buffer sub page")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c2afcf98ea912..3c11e8e811edd 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5927,6 +5927,7 @@ error:
 	for_each_buffer_cpu(buffer, cpu) {
 		if (!cpu_buffers[cpu])
 			continue;
+		rb_free_cpu_buffer(cpu_buffers[cpu]);
 		kfree(cpu_buffers[cpu]);
 	}
 	kfree(cpu_buffers);
-- 
GitLab


From b81e03a24966dca0b119eff0549a4e44befff419 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:21 -0500
Subject: [PATCH 1754/4076] ring-buffer: Do no swap cpu buffers if order is
 different

As all the subbuffer order (subbuffer sizes) must be the same throughout
the ring buffer, check the order of the buffers that are doing a CPU
buffer swap in ring_buffer_swap_cpu() to make sure they are the same.

If the are not the same, then fail to do the swap, otherwise the ring
buffer will think the CPU buffer has a specific subbuffer size when it
does not.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185629.467894710@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3c11e8e811edd..fdcd171b09b5d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5417,6 +5417,9 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
 	if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages)
 		goto out;
 
+	if (buffer_a->subbuf_order != buffer_b->subbuf_order)
+		goto out;
+
 	ret = -EAGAIN;
 
 	if (atomic_read(&buffer_a->record_disabled))
-- 
GitLab


From 4e958db34fd5324421ef9562c31c15e2d152dc63 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:22 -0500
Subject: [PATCH 1755/4076] ring-buffer: Make sure the spare sub buffer used
 for reads has same size

Now that the ring buffer specifies the size of its sub buffers, they all
need to be the same size. When doing a read, a swap is done with a spare
page. Make sure they are the same size before doing the swap, otherwise
the read will fail.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185629.763664788@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 711095aa731d3..4dcdc30aa1100 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7582,6 +7582,7 @@ struct ftrace_buffer_info {
 	struct trace_iterator	iter;
 	void			*spare;
 	unsigned int		spare_cpu;
+	unsigned int		spare_size;
 	unsigned int		read;
 };
 
@@ -8301,6 +8302,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
 
+	/* Make sure the spare matches the current sub buffer size */
+	if (info->spare) {
+		if (page_size != info->spare_size) {
+			ring_buffer_free_read_page(iter->array_buffer->buffer,
+						   info->spare_cpu, info->spare);
+			info->spare = NULL;
+		}
+	}
+
 	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer,
 							  iter->cpu_file);
@@ -8309,6 +8319,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 			info->spare = NULL;
 		} else {
 			info->spare_cpu = iter->cpu_file;
+			info->spare_size = page_size;
 		}
 	}
 	if (!info->spare)
-- 
GitLab


From aa067682adf19ca78f81cd57539282dbfd7cce21 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:23 -0500
Subject: [PATCH 1756/4076] tracing: Update snapshot order along with main
 buffer order

When updating the order of the sub buffers for the main buffer, make sure
that if the snapshot buffer exists, that it gets its order updated as
well.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185630.054668186@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 45 ++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 43 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4dcdc30aa1100..2439e00aa4ce9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1263,10 +1263,17 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val);
 
 int tracing_alloc_snapshot_instance(struct trace_array *tr)
 {
+	int order;
 	int ret;
 
 	if (!tr->allocated_snapshot) {
 
+		/* Make the snapshot buffer have the same order as main buffer */
+		order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+		ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order);
+		if (ret < 0)
+			return ret;
+
 		/* allocate spare buffer */
 		ret = resize_buffer_duplicate_size(&tr->max_buffer,
 				   &tr->array_buffer, RING_BUFFER_ALL_CPUS);
@@ -1286,6 +1293,7 @@ static void free_snapshot(struct trace_array *tr)
 	 * The max_tr ring buffer has some state (e.g. ring->clock) and
 	 * we want preserve it.
 	 */
+	ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0);
 	ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS);
 	set_buffer_entries(&tr->max_buffer, 1);
 	tracing_reset_online_cpus(&tr->max_buffer);
@@ -9393,6 +9401,7 @@ buffer_order_write(struct file *filp, const char __user *ubuf,
 {
 	struct trace_array *tr = filp->private_data;
 	unsigned long val;
+	int old_order;
 	int ret;
 
 	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
@@ -9403,12 +9412,44 @@ buffer_order_write(struct file *filp, const char __user *ubuf,
 	if (val < 0 || val > 7)
 		return -EINVAL;
 
+	old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+	if (old_order == val)
+		return 0;
+
 	ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, val);
 	if (ret)
-		return ret;
+		return 0;
 
-	(*ppos)++;
+#ifdef CONFIG_TRACER_MAX_TRACE
+
+	if (!tr->allocated_snapshot)
+		goto out_max;
 
+	ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, val);
+	if (ret) {
+		/* Put back the old order */
+		cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order);
+		if (WARN_ON_ONCE(cnt)) {
+			/*
+			 * AARGH! We are left with different orders!
+			 * The max buffer is our "snapshot" buffer.
+			 * When a tracer needs a snapshot (one of the
+			 * latency tracers), it swaps the max buffer
+			 * with the saved snap shot. We succeeded to
+			 * update the order of the main buffer, but failed to
+			 * update the order of the max buffer. But when we tried
+			 * to reset the main buffer to the original size, we
+			 * failed there too. This is very unlikely to
+			 * happen, but if it does, warn and kill all
+			 * tracing.
+			 */
+			tracing_disabled = 1;
+		}
+		return ret;
+	}
+ out_max:
+#endif
+	(*ppos)++;
 	return cnt;
 }
 
-- 
GitLab


From 1075ee66a8c19bfa375b19c236fd6a22a867f138 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 19 Dec 2023 20:33:50 +0100
Subject: [PATCH 1757/4076] dmaengine: idxd: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Note that the upper limit of ida_simple_get() is exclusive, but the one of
ida_alloc_range() is inclusive. Sothis change allows one more device.

MINORMASK is ((1U << MINORBITS) - 1), so allowing MINORMASK as a maximum value
makes sense. It is also consistent with other "ida_.*MINORMASK" and
"ida_*MINOR()" usages.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>
Acked-by: Lijun Pan <lijun.pan@intel.com>
Link: https://lore.kernel.org/r/ac991f5f42112fa782a881d391d447529cbc4a23.1702967302.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/cdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 0423655f5a880..b00926abc69ae 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -165,7 +165,7 @@ static void idxd_cdev_dev_release(struct device *dev)
 	struct idxd_wq *wq = idxd_cdev->wq;
 
 	cdev_ctx = &ictx[wq->idxd->data->type];
-	ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
+	ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
 	kfree(idxd_cdev);
 }
 
@@ -463,7 +463,7 @@ int idxd_wq_add_cdev(struct idxd_wq *wq)
 	cdev = &idxd_cdev->cdev;
 	dev = cdev_dev(idxd_cdev);
 	cdev_ctx = &ictx[wq->idxd->data->type];
-	minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
+	minor = ida_alloc_max(&cdev_ctx->minor_ida, MINORMASK, GFP_KERNEL);
 	if (minor < 0) {
 		kfree(idxd_cdev);
 		return minor;
-- 
GitLab


From fa4b54af5ba17a59ce082e9d710eb638bdce7637 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:24 -0500
Subject: [PATCH 1758/4076] tracing: Stop the tracing while changing the ring
 buffer subbuf size

Because the main buffer and the snapshot buffer need to be the same for
some tracers, otherwise it will fail and disable all tracing, the tracers
need to be stopped while updating the sub buffer sizes so that the tracers
see the main and snapshot buffers with the same sub buffer size.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185630.353222794@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: 2808e31ec12e ("ring-buffer: Add interface for configuring trace sub buffer size")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2439e00aa4ce9..82303bd2bba13 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9412,13 +9412,16 @@ buffer_order_write(struct file *filp, const char __user *ubuf,
 	if (val < 0 || val > 7)
 		return -EINVAL;
 
+	/* Do not allow tracing while changing the order of the ring buffer */
+	tracing_stop_tr(tr);
+
 	old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
 	if (old_order == val)
-		return 0;
+		goto out;
 
 	ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, val);
 	if (ret)
-		return 0;
+		goto out;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 
@@ -9445,11 +9448,15 @@ buffer_order_write(struct file *filp, const char __user *ubuf,
 			 */
 			tracing_disabled = 1;
 		}
-		return ret;
+		goto out;
 	}
  out_max:
 #endif
 	(*ppos)++;
+ out:
+	if (ret)
+		cnt = ret;
+	tracing_start_tr(tr);
 	return cnt;
 }
 
-- 
GitLab


From 71a5197e2b872afeef8ade3099ffc4050466b542 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 17 Dec 2023 22:08:34 -0800
Subject: [PATCH 1759/4076] dmaengine: std_dma40: fix kernel-doc warnings and
 spelling

Correct kernel-doc warnings as reported by kernel test robot:

ste_dma40.c:57: warning: Excess struct member 'dev_tx' description in 'stedma40_platform_data'
ste_dma40.c:57: warning: Excess struct member 'dev_rx' description in 'stedma40_platform_data'

Correct spellos as reported by codespell.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312171417.izbQThoU-lkp@intel.com/
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Vinod Koul <vkoul@kernel.org>
Cc: dmaengine@vger.kernel.org
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231218060834.19222-1-rdunlap@infradead.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/ste_dma40.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 002833fb1fa04..2c489299148ee 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -31,13 +31,11 @@
 /**
  * struct stedma40_platform_data - Configuration struct for the dma device.
  *
- * @dev_tx: mapping between destination event line and io address
- * @dev_rx: mapping between source event line and io address
  * @disabled_channels: A vector, ending with -1, that marks physical channels
  * that are for different reasons not available for the driver.
  * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW
  * which avoids HW bug that exists in some versions of the controller.
- * SoftLLI introduces relink overhead that could impact performace for
+ * SoftLLI introduces relink overhead that could impact performance for
  * certain use cases.
  * @num_of_soft_lli_chans: The number of channels that needs to be configured
  * to use SoftLLI.
@@ -184,7 +182,7 @@ static __maybe_unused u32 d40_backup_regs[] = {
 
 /*
  * since 9540 and 8540 has the same HW revision
- * use v4a for 9540 or ealier
+ * use v4a for 9540 or earlier
  * use v4b for 8540 or later
  * HW revision:
  * DB8500ed has revision 0
@@ -411,7 +409,7 @@ struct d40_desc {
  *
  * @base: The virtual address of LCLA. 18 bit aligned.
  * @dma_addr: DMA address, if mapped
- * @base_unaligned: The orignal kmalloc pointer, if kmalloc is used.
+ * @base_unaligned: The original kmalloc pointer, if kmalloc is used.
  * This pointer is only there for clean-up on error.
  * @pages: The number of pages needed for all physical channels.
  * Only used later for clean-up on error
@@ -1655,7 +1653,7 @@ static void dma_tasklet(struct tasklet_struct *t)
 
 	return;
  check_pending_tx:
-	/* Rescue manouver if receiving double interrupts */
+	/* Rescue maneuver if receiving double interrupts */
 	if (d40c->pending_tx > 0)
 		d40c->pending_tx--;
 	spin_unlock_irqrestore(&d40c->lock, flags);
@@ -3412,7 +3410,7 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 		base->lcla_pool.base = (void *)page_list[i];
 	} else {
 		/*
-		 * After many attempts and no succees with finding the correct
+		 * After many attempts and no success with finding the correct
 		 * alignment, try with allocating a big buffer.
 		 */
 		dev_warn(base->dev,
-- 
GitLab


From 353cc219372935805218e05a7754a059ab104641 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:25 -0500
Subject: [PATCH 1760/4076] ring-buffer: Keep the same size when updating the
 order

The function ring_buffer_subbuf_order_set() just updated the sub-buffers
to the new size, but this also changes the size of the buffer in doing so.
As the size is determined by nr_pages * subbuf_size. If the subbuf_size is
increased without decreasing the nr_pages, this causes the total size of
the buffer to increase.

This broke the latency tracers as the snapshot needs to be the same size
as the main buffer. The size of the snapshot buffer is only expanded when
needed, and because the order is still the same, the size becomes out of
sync with the main buffer, as the main buffer increased in size without
the tracing system knowing.

Calculate the nr_pages to allocate with the new subbuf_size to be
buffer_size / new_subbuf_size.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185630.649397785@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: f9b94daa542a ("ring-buffer: Set new size of the ring buffer sub page")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index fdcd171b09b5d..23ead7602da0b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5897,7 +5897,10 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			continue;
 
-		nr_pages = buffer->buffers[cpu]->nr_pages;
+		/* Update the number of pages to match the new size */
+		nr_pages = old_size * buffer->buffers[cpu]->nr_pages;
+		nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size);
+
 		cpu_buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
 		if (!cpu_buffers[cpu]) {
 			err = -ENOMEM;
-- 
GitLab


From 8e7b58c27b3c567316a51079b375b846f9223bba Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:26 -0500
Subject: [PATCH 1761/4076] ring-buffer: Just update the subbuffers when
 changing their allocation order

The ring_buffer_subbuf_order_set() was creating ring_buffer_per_cpu
cpu_buffers with the new subbuffers with the updated order, and if they
all successfully were created, then they the ring_buffer's per_cpu buffers
would be freed and replaced by them.

The problem is that the freed per_cpu buffers contains state that would be
lost. Running the following commands:

1. # echo 3 > /sys/kernel/tracing/buffer_subbuf_order
2. # echo 0 > /sys/kernel/tracing/tracing_cpumask
3. # echo 1 > /sys/kernel/tracing/snapshot
4. # echo ff > /sys/kernel/tracing/tracing_cpumask
5. # echo test > /sys/kernel/tracing/trace_marker

Would result in:

 -bash: echo: write error: Bad file descriptor

That's because the state of the per_cpu buffers of the snapshot buffer is
lost when the order is changed (the order of a freed snapshot buffer goes
to 0 to save memory, and when the snapshot buffer is allocated again, it
goes back to what the main buffer is).

In operation 2, the snapshot buffers were set to "disable" (as all the
ring buffers CPUs were disabled).

In operation 3, the snapshot is allocated and a call to
ring_buffer_subbuf_order_set() replaced the per_cpu buffers losing the
"record_disable" count.

When it was enabled again, the atomic_dec(&cpu_buffer->record_disable) was
decrementing a zero, setting it to -1. Writing 1 into the snapshot would
swap the snapshot buffer with the main buffer, so now the main buffer is
"disabled", and nothing can write to the ring buffer anymore.

Instead of creating new per_cpu buffers and losing the state of the old
buffers, basically do what the resize does and just allocate new subbuf
pages into the new_pages link list of the per_cpu buffer and if they all
succeed, then replace the old sub buffers with the new ones. This keeps
the per_cpu buffer descriptor in tact and by doing so, keeps its state.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185630.944104939@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: f9b94daa542a ("ring-buffer: Set new size of the ring buffer sub page")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 88 ++++++++++++++++++++++++++++++--------
 1 file changed, 71 insertions(+), 17 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 23ead7602da0b..7ee6779bf292d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5856,11 +5856,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_get);
  */
 int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 {
-	struct ring_buffer_per_cpu **cpu_buffers;
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct buffer_page *bpage, *tmp;
 	int old_order, old_size;
 	int nr_pages;
 	int psize;
-	int bsize;
 	int err;
 	int cpu;
 
@@ -5874,11 +5874,6 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	if (psize <= BUF_PAGE_HDR_SIZE)
 		return -EINVAL;
 
-	bsize = sizeof(void *) * buffer->cpus;
-	cpu_buffers = kzalloc(bsize, GFP_KERNEL);
-	if (!cpu_buffers)
-		return -ENOMEM;
-
 	old_order = buffer->subbuf_order;
 	old_size = buffer->subbuf_size;
 
@@ -5894,33 +5889,88 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 
 	/* Make sure all new buffers are allocated, before deleting the old ones */
 	for_each_buffer_cpu(buffer, cpu) {
+
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			continue;
 
+		cpu_buffer = buffer->buffers[cpu];
+
 		/* Update the number of pages to match the new size */
 		nr_pages = old_size * buffer->buffers[cpu]->nr_pages;
 		nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size);
 
-		cpu_buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
-		if (!cpu_buffers[cpu]) {
+		/* we need a minimum of two pages */
+		if (nr_pages < 2)
+			nr_pages = 2;
+
+		cpu_buffer->nr_pages_to_update = nr_pages;
+
+		/* Include the reader page */
+		nr_pages++;
+
+		/* Allocate the new size buffer */
+		INIT_LIST_HEAD(&cpu_buffer->new_pages);
+		if (__rb_allocate_pages(cpu_buffer, nr_pages,
+					&cpu_buffer->new_pages)) {
+			/* not enough memory for new pages */
 			err = -ENOMEM;
 			goto error;
 		}
 	}
 
 	for_each_buffer_cpu(buffer, cpu) {
+
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			continue;
 
-		rb_free_cpu_buffer(buffer->buffers[cpu]);
-		buffer->buffers[cpu] = cpu_buffers[cpu];
+		cpu_buffer = buffer->buffers[cpu];
+
+		/* Clear the head bit to make the link list normal to read */
+		rb_head_page_deactivate(cpu_buffer);
+
+		/* Now walk the list and free all the old sub buffers */
+		list_for_each_entry_safe(bpage, tmp, cpu_buffer->pages, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+		/* The above loop stopped an the last page needing to be freed */
+		bpage = list_entry(cpu_buffer->pages, struct buffer_page, list);
+		free_buffer_page(bpage);
+
+		/* Free the current reader page */
+		free_buffer_page(cpu_buffer->reader_page);
+
+		/* One page was allocated for the reader page */
+		cpu_buffer->reader_page = list_entry(cpu_buffer->new_pages.next,
+						     struct buffer_page, list);
+		list_del_init(&cpu_buffer->reader_page->list);
+
+		/* The cpu_buffer pages are a link list with no head */
+		cpu_buffer->pages = cpu_buffer->new_pages.next;
+		cpu_buffer->new_pages.next->prev = cpu_buffer->new_pages.prev;
+		cpu_buffer->new_pages.prev->next = cpu_buffer->new_pages.next;
+
+		/* Clear the new_pages list */
+		INIT_LIST_HEAD(&cpu_buffer->new_pages);
+
+		cpu_buffer->head_page
+			= list_entry(cpu_buffer->pages, struct buffer_page, list);
+		cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
+
+		cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update;
+		cpu_buffer->nr_pages_to_update = 0;
+
+		free_pages((unsigned long)cpu_buffer->free_page, old_order);
+		cpu_buffer->free_page = NULL;
+
+		rb_head_page_activate(cpu_buffer);
+
+		rb_check_pages(cpu_buffer);
 	}
 
 	atomic_dec(&buffer->record_disabled);
 	mutex_unlock(&buffer->mutex);
 
-	kfree(cpu_buffers);
-
 	return 0;
 
 error:
@@ -5931,12 +5981,16 @@ error:
 	mutex_unlock(&buffer->mutex);
 
 	for_each_buffer_cpu(buffer, cpu) {
-		if (!cpu_buffers[cpu])
+		cpu_buffer = buffer->buffers[cpu];
+
+		if (!cpu_buffer->nr_pages_to_update)
 			continue;
-		rb_free_cpu_buffer(cpu_buffers[cpu]);
-		kfree(cpu_buffers[cpu]);
+
+		list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
 	}
-	kfree(cpu_buffers);
 
 	return err;
 }
-- 
GitLab


From 7c3f48026589b532ebc0d12f939f6be78bd74a58 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:27 -0500
Subject: [PATCH 1762/4076] ring-buffer: Add documentation on the
 buffer_subbuf_order file

Add to the documentation how to use the buffer_subbuf_order file to change
the size and how it affects what events can be added to the ring buffer.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185631.230636734@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 Documentation/trace/ftrace.rst | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 23572f6697c0a..231d26ceedb05 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -203,6 +203,33 @@ of ftrace. Here is a list of some of the key files:
 
 	This displays the total combined size of all the trace buffers.
 
+  buffer_subbuf_order:
+
+	This sets or displays the sub buffer page size order. The ring buffer
+	is broken up into several same size "sub buffers". An event can not be
+	bigger than the size of the sub buffer. Normally, the sub buffer is
+	the size of the architecture's page (4K on x86). The sub buffer also
+	contains meta data at the start which also limits the size of an event.
+	That means when the sub buffer is a page size, no event can be larger
+	than the page size minus the sub buffer meta data.
+
+	The buffer_subbuf_order allows the user to change the size of the sub
+	buffer. As the sub buffer is a set of pages by the power of 2, thus
+	the sub buffer total size is defined by the order:
+
+	order		size
+	----		----
+	0		PAGE_SIZE
+	1		PAGE_SIZE * 2
+	2		PAGE_SIZE * 4
+	3		PAGE_SIZE * 8
+
+	Changing the order will change the sub buffer size allowing for events
+	to be larger than the page size.
+
+	Note: When changing the order, tracing is stopped and any data in the
+	ring buffer and the snapshot buffer will be discarded.
+
   free_buffer:
 
 	If a process is performing tracing, and the ring buffer	should be
-- 
GitLab


From 1acce70374caabc2945aa07a862f834fb7c2914f Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:28 -0500
Subject: [PATCH 1763/4076] ringbuffer/selftest: Add basic selftest to test
 changing subbuf order

Add a self test that will write into the trace buffer with differ trace
sub buffer order sizes.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185631.520496304@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 .../ftrace/test.d/00basic/ringbuffer_order.tc | 95 +++++++++++++++++++
 1 file changed, 95 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_order.tc

diff --git a/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_order.tc b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_order.tc
new file mode 100644
index 0000000000000..ecbcc810e6c16
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_order.tc
@@ -0,0 +1,95 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Change the ringbuffer sub-buffer order
+# requires: buffer_subbuf_order
+# flags: instance
+
+get_buffer_data_size() {
+	sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_buffer_data_offset() {
+	sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_event_header_size() {
+	type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	total_bits=$((type_len+time_len+array_len))
+	total_bits=$((total_bits+7))
+	echo $((total_bits/8))
+}
+
+get_print_event_buf_offset() {
+	sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format
+}
+
+event_header_size=`get_event_header_size`
+print_header_size=`get_print_event_buf_offset`
+
+data_offset=`get_buffer_data_offset`
+
+marker_meta=$((event_header_size+print_header_size))
+
+make_str() {
+        cnt=$1
+	printf -- 'X%.0s' $(seq $cnt)
+}
+
+write_buffer() {
+	size=$1
+
+	str=`make_str $size`
+
+	# clear the buffer
+	echo > trace
+
+	# write the string into the marker
+	echo $str > trace_marker
+
+	echo $str
+}
+
+test_buffer() {
+	orde=$1
+	page_size=$((4096<<order))
+
+	size=`get_buffer_data_size`
+
+	# the size must be greater than or equal to page_size - data_offset
+	page_size=$((page_size-data_offset))
+	if [ $size -lt $page_size ]; then
+		exit fail
+	fi
+
+	# Now add a little more the meta data overhead will overflow
+
+	str=`write_buffer $size`
+
+	# Make sure the line was broken
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace`
+
+	if [ "$new_str" = "$str" ]; then
+		exit fail;
+	fi
+
+	# Make sure the entire line can be found
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace`
+
+	if [ "$new_str" != "$str" ]; then
+		exit fail;
+	fi
+}
+
+ORIG=`cat buffer_subbuf_order`
+
+# Could test bigger orders than 3, but then creating the string
+# to write into the ring buffer takes too long
+for a in 0 1 2 3 ; do
+	echo $a > buffer_subbuf_order
+	test_buffer $a
+done
+
+echo $ORIG > buffer_subbuf_order
+
-- 
GitLab


From 2f84b39f48476615186af5b3220ad5a2c756679b Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 13:54:29 -0500
Subject: [PATCH 1764/4076] tracing: Update subbuffer with kilobytes not page
 order

Using page order for deciding what the size of the ring buffer sub buffers
are is exposing a bit too much of the implementation. Although the sub
buffers are only allocated in orders of pages, allow the user to specify
the minimum size of each sub-buffer via kilobytes like they can with the
buffer size itself.

If the user specifies 3 via:

  echo 3 > buffer_subbuf_size_kb

Then the sub-buffer size will round up to 4kb (on a 4kb page size system).

If they specify:

  echo 6 > buffer_subbuf_size_kb

The sub-buffer size will become 8kb.

and so on.

Link: https://lore.kernel.org/linux-trace-kernel/20231219185631.809766769@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 Documentation/trace/ftrace.rst                | 46 ++++++++-----------
 kernel/trace/trace.c                          | 38 +++++++++------
 ...fer_order.tc => ringbuffer_subbuf_size.tc} | 18 ++++----
 3 files changed, 54 insertions(+), 48 deletions(-)
 rename tools/testing/selftests/ftrace/test.d/00basic/{ringbuffer_order.tc => ringbuffer_subbuf_size.tc} (85%)

diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 231d26ceedb05..933e7efb9f1b3 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -203,32 +203,26 @@ of ftrace. Here is a list of some of the key files:
 
 	This displays the total combined size of all the trace buffers.
 
-  buffer_subbuf_order:
-
-	This sets or displays the sub buffer page size order. The ring buffer
-	is broken up into several same size "sub buffers". An event can not be
-	bigger than the size of the sub buffer. Normally, the sub buffer is
-	the size of the architecture's page (4K on x86). The sub buffer also
-	contains meta data at the start which also limits the size of an event.
-	That means when the sub buffer is a page size, no event can be larger
-	than the page size minus the sub buffer meta data.
-
-	The buffer_subbuf_order allows the user to change the size of the sub
-	buffer. As the sub buffer is a set of pages by the power of 2, thus
-	the sub buffer total size is defined by the order:
-
-	order		size
-	----		----
-	0		PAGE_SIZE
-	1		PAGE_SIZE * 2
-	2		PAGE_SIZE * 4
-	3		PAGE_SIZE * 8
-
-	Changing the order will change the sub buffer size allowing for events
-	to be larger than the page size.
-
-	Note: When changing the order, tracing is stopped and any data in the
-	ring buffer and the snapshot buffer will be discarded.
+  buffer_subbuf_size_kb:
+
+	This sets or displays the sub buffer size. The ring buffer is broken up
+	into several same size "sub buffers". An event can not be bigger than
+	the size of the sub buffer. Normally, the sub buffer is the size of the
+	architecture's page (4K on x86). The sub buffer also contains meta data
+	at the start which also limits the size of an event.  That means when
+	the sub buffer is a page size, no event can be larger than the page
+	size minus the sub buffer meta data.
+
+	Note, the buffer_subbuf_size_kb is a way for the user to specify the
+	minimum size of the subbuffer. The kernel may make it bigger due to the
+	implementation details, or simply fail the operation if the kernel can
+	not handle the request.
+
+	Changing the sub buffer size allows for events to be larger than the
+	page size.
+
+	Note: When changing the sub-buffer size, tracing is stopped and any
+	data in the ring buffer and the snapshot buffer will be discarded.
 
   free_buffer:
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82303bd2bba13..46dbe22121e91 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9384,42 +9384,54 @@ static const struct file_operations buffer_percent_fops = {
 };
 
 static ssize_t
-buffer_order_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+buffer_subbuf_size_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 {
 	struct trace_array *tr = filp->private_data;
+	size_t size;
 	char buf[64];
+	int order;
 	int r;
 
-	r = sprintf(buf, "%d\n", ring_buffer_subbuf_order_get(tr->array_buffer.buffer));
+	order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+	size = (PAGE_SIZE << order) / 1024;
+
+	r = sprintf(buf, "%zd\n", size);
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
 static ssize_t
-buffer_order_write(struct file *filp, const char __user *ubuf,
-		   size_t cnt, loff_t *ppos)
+buffer_subbuf_size_write(struct file *filp, const char __user *ubuf,
+			 size_t cnt, loff_t *ppos)
 {
 	struct trace_array *tr = filp->private_data;
 	unsigned long val;
 	int old_order;
+	int order;
+	int pages;
 	int ret;
 
 	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
 	if (ret)
 		return ret;
 
+	val *= 1024; /* value passed in is in KB */
+
+	pages = DIV_ROUND_UP(val, PAGE_SIZE);
+	order = fls(pages - 1);
+
 	/* limit between 1 and 128 system pages */
-	if (val < 0 || val > 7)
+	if (order < 0 || order > 7)
 		return -EINVAL;
 
 	/* Do not allow tracing while changing the order of the ring buffer */
 	tracing_stop_tr(tr);
 
 	old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
-	if (old_order == val)
+	if (old_order == order)
 		goto out;
 
-	ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, val);
+	ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, order);
 	if (ret)
 		goto out;
 
@@ -9428,7 +9440,7 @@ buffer_order_write(struct file *filp, const char __user *ubuf,
 	if (!tr->allocated_snapshot)
 		goto out_max;
 
-	ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, val);
+	ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order);
 	if (ret) {
 		/* Put back the old order */
 		cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order);
@@ -9460,10 +9472,10 @@ buffer_order_write(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
-static const struct file_operations buffer_order_fops = {
+static const struct file_operations buffer_subbuf_size_fops = {
 	.open		= tracing_open_generic_tr,
-	.read		= buffer_order_read,
-	.write		= buffer_order_write,
+	.read		= buffer_subbuf_size_read,
+	.write		= buffer_subbuf_size_write,
 	.release	= tracing_release_generic_tr,
 	.llseek		= default_llseek,
 };
@@ -9934,8 +9946,8 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer,
 			tr, &buffer_percent_fops);
 
-	trace_create_file("buffer_subbuf_order", TRACE_MODE_WRITE, d_tracer,
-			  tr, &buffer_order_fops);
+	trace_create_file("buffer_subbuf_size_kb", TRACE_MODE_WRITE, d_tracer,
+			  tr, &buffer_subbuf_size_fops);
 
 	create_trace_options_dir(tr);
 
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_order.tc b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc
similarity index 85%
rename from tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_order.tc
rename to tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc
index ecbcc810e6c16..d44d09a33a743 100644
--- a/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_order.tc
+++ b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
-# description: Change the ringbuffer sub-buffer order
-# requires: buffer_subbuf_order
+# description: Change the ringbuffer sub-buffer size
+# requires: buffer_subbuf_size_kb
 # flags: instance
 
 get_buffer_data_size() {
@@ -52,8 +52,8 @@ write_buffer() {
 }
 
 test_buffer() {
-	orde=$1
-	page_size=$((4096<<order))
+	size_kb=$1
+	page_size=$((size_kb*1024))
 
 	size=`get_buffer_data_size`
 
@@ -82,14 +82,14 @@ test_buffer() {
 	fi
 }
 
-ORIG=`cat buffer_subbuf_order`
+ORIG=`cat buffer_subbuf_size_kb`
 
-# Could test bigger orders than 3, but then creating the string
+# Could test bigger sizes than 32K, but then creating the string
 # to write into the ring buffer takes too long
-for a in 0 1 2 3 ; do
-	echo $a > buffer_subbuf_order
+for a in 4 8 16 32 ; do
+	echo $a > buffer_subbuf_size_kb
 	test_buffer $a
 done
 
-echo $ORIG > buffer_subbuf_order
+echo $ORIG > buffer_subbuf_size_kb
 
-- 
GitLab


From 3cb3091138ca0921c4569bcf7ffa062519639b6a Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 19 Dec 2023 17:38:00 -0500
Subject: [PATCH 1765/4076] ring-buffer: Use subbuf_order for buffer page
 masking

The comparisons to PAGE_SIZE were all converted to use the
buffer->subbuf_order, but the use of PAGE_MASK was missed.

Convert all the PAGE_MASK usages over to:

  (PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1

Link: https://lore.kernel.org/linux-trace-kernel/20231219173800.66eefb7a@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: 139f84002145 ("ring-buffer: Page size per ring buffer")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7ee6779bf292d..173d2595ce2d9 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2269,11 +2269,13 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 static __always_inline unsigned
-rb_event_index(struct ring_buffer_event *event)
+rb_event_index(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event)
 {
 	unsigned long addr = (unsigned long)event;
 
-	return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
+	addr &= (PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1;
+
+	return addr - BUF_PAGE_HDR_SIZE;
 }
 
 static void rb_inc_iter(struct ring_buffer_iter *iter)
@@ -2646,7 +2648,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 
 /* Slow path */
 static struct ring_buffer_event *
-rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
+rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+		  struct ring_buffer_event *event, u64 delta, bool abs)
 {
 	if (abs)
 		event->type_len = RINGBUF_TYPE_TIME_STAMP;
@@ -2654,7 +2657,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
 		event->type_len = RINGBUF_TYPE_TIME_EXTEND;
 
 	/* Not the first event on the page, or not delta? */
-	if (abs || rb_event_index(event)) {
+	if (abs || rb_event_index(cpu_buffer, event)) {
 		event->time_delta = delta & TS_MASK;
 		event->array[0] = delta >> TS_SHIFT;
 	} else {
@@ -2728,7 +2731,7 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
 		if (!abs)
 			info->delta = 0;
 	}
-	*event = rb_add_time_stamp(*event, info->delta, abs);
+	*event = rb_add_time_stamp(cpu_buffer, *event, info->delta, abs);
 	*length -= RB_LEN_TIME_EXTEND;
 	*delta = 0;
 }
@@ -2812,10 +2815,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	struct buffer_page *bpage;
 	unsigned long addr;
 
-	new_index = rb_event_index(event);
+	new_index = rb_event_index(cpu_buffer, event);
 	old_index = new_index + rb_event_ts_length(event);
 	addr = (unsigned long)event;
-	addr &= PAGE_MASK;
+	addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1);
 
 	bpage = READ_ONCE(cpu_buffer->tail_page);
 
@@ -3726,7 +3729,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer,
 	struct buffer_page *bpage = cpu_buffer->commit_page;
 	struct buffer_page *start;
 
-	addr &= PAGE_MASK;
+	addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1);
 
 	/* Do the likely case first */
 	if (likely(bpage->page == (void *)addr)) {
-- 
GitLab


From 3b3b5339cdc67e98817d08431f8443b08880084f Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Mon, 18 Dec 2023 09:56:38 +0800
Subject: [PATCH 1766/4076] dt-bindings: dmaengine: Add Loongson LS2X APB DMA
 controller

Add Loongson LS2X APB DMA controller binding with DT schema
format using json-schema.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Link: https://lore.kernel.org/r/078307641077edaf46dd986c6d31cea15545a208.1702365725.git.zhoubinbin@loongson.cn
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/dma/loongson,ls2x-apbdma.yaml    | 62 +++++++++++++++++++
 MAINTAINERS                                   |  6 ++
 2 files changed, 68 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml

diff --git a/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml b/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
new file mode 100644
index 0000000000000..6a1b49a49a646
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/loongson,ls2x-apbdma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Loongson LS2X APB DMA controller
+
+description:
+  The Loongson LS2X APB DMA controller is used for transferring data
+  between system memory and the peripherals on the APB bus.
+
+maintainers:
+  - Binbin Zhou <zhoubinbin@loongson.cn>
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: loongson,ls2k1000-apbdma
+      - items:
+          - const: loongson,ls2k0500-apbdma
+          - const: loongson,ls2k1000-apbdma
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  '#dma-cells':
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - '#dma-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/clock/loongson,ls2k-clk.h>
+
+    dma-controller@1fe00c00 {
+        compatible = "loongson,ls2k1000-apbdma";
+        reg = <0x1fe00c00 0x8>;
+        interrupt-parent = <&liointc1>;
+        interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&clk LOONGSON2_APB_CLK>;
+        #dma-cells = <1>;
+    };
+
+...
diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cfd..c9a48bce986e0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12507,6 +12507,12 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/gpio/loongson,ls-gpio.yaml
 F:	drivers/gpio/gpio-loongson-64bit.c
 
+LOONGSON LS2X APB DMA DRIVER
+M:	Binbin Zhou <zhoubinbin@loongson.cn>
+L:	dmaengine@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
+
 LOONGSON LS2X I2C DRIVER
 M:	Binbin Zhou <zhoubinbin@loongson.cn>
 L:	linux-i2c@vger.kernel.org
-- 
GitLab


From 71e7d3cb6e55ae2eadcdb178f9243dc18499d369 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Mon, 18 Dec 2023 09:56:39 +0800
Subject: [PATCH 1767/4076] dmaengine: ls2x-apb: New driver for the Loongson
 LS2X APB DMA controller

The Loongson LS2X APB DMA controller is available on Loongson-2K chips.

It is a single-channel, configurable DMA controller IP core based on the
AXI bus, whose main function is to integrate DMA functionality on a chip
dedicated to carrying data between memory and peripherals in APB bus
(e.g. nand).

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Yingkun Meng <mengyingkun@loongson.cn>
Link: https://lore.kernel.org/r/8df2a0199434fba3535831082966c2442ecf1cae.1702365725.git.zhoubinbin@loongson.cn
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 MAINTAINERS                |   1 +
 drivers/dma/Kconfig        |  14 +
 drivers/dma/Makefile       |   1 +
 drivers/dma/ls2x-apb-dma.c | 705 +++++++++++++++++++++++++++++++++++++
 4 files changed, 721 insertions(+)
 create mode 100644 drivers/dma/ls2x-apb-dma.c

diff --git a/MAINTAINERS b/MAINTAINERS
index c9a48bce986e0..331bac4abde16 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12512,6 +12512,7 @@ M:	Binbin Zhou <zhoubinbin@loongson.cn>
 L:	dmaengine@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
+F:	drivers/dma/ls2x-apb-dma.c
 
 LOONGSON LS2X I2C DRIVER
 M:	Binbin Zhou <zhoubinbin@loongson.cn>
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 70ba506dabab5..e928f2ca0f1e9 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -378,6 +378,20 @@ config LPC18XX_DMAMUX
 	  Enable support for DMA on NXP LPC18xx/43xx platforms
 	  with PL080 and multiplexed DMA request lines.
 
+config LS2X_APB_DMA
+	tristate "Loongson LS2X APB DMA support"
+	depends on LOONGARCH || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support for the Loongson LS2X APB DMA controller driver. The
+	  DMA controller is having single DMA channel which can be
+	  configured for different peripherals like audio, nand, sdio
+	  etc which is in APB bus.
+
+	  This DMA controller transfers data from memory to peripheral fifo.
+	  It does not support memory to memory data transfer.
+
 config MCF_EDMA
 	tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs"
 	depends on M5441x || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 83553a97a010e..dfd40d14e4089 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_INTEL_IOATDMA) += ioat/
 obj-y += idxd/
 obj-$(CONFIG_K3_DMA) += k3dma.o
 obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
+obj-$(CONFIG_LS2X_APB_DMA) += ls2x-apb-dma.o
 obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
 obj-$(CONFIG_MILBEAUT_XDMAC) += milbeaut-xdmac.o
 obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
diff --git a/drivers/dma/ls2x-apb-dma.c b/drivers/dma/ls2x-apb-dma.c
new file mode 100644
index 0000000000000..a49913f3ed3f7
--- /dev/null
+++ b/drivers/dma/ls2x-apb-dma.c
@@ -0,0 +1,705 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Driver for the Loongson LS2X APB DMA Controller
+ *
+ * Copyright (C) 2017-2023 Loongson Corporation
+ */
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+/* Global Configuration Register */
+#define LDMA_ORDER_ERG		0x0
+
+/* Bitfield definitions */
+
+/* Bitfields in Global Configuration Register */
+#define LDMA_64BIT_EN		BIT(0) /* 1: 64 bit support */
+#define LDMA_UNCOHERENT_EN	BIT(1) /* 0: cache, 1: uncache */
+#define LDMA_ASK_VALID		BIT(2)
+#define LDMA_START		BIT(3) /* DMA start operation */
+#define LDMA_STOP		BIT(4) /* DMA stop operation */
+#define LDMA_CONFIG_MASK	GENMASK(4, 0) /* DMA controller config bits mask */
+
+/* Bitfields in ndesc_addr field of HW decriptor */
+#define LDMA_DESC_EN		BIT(0) /*1: The next descriptor is valid */
+#define LDMA_DESC_ADDR_LOW	GENMASK(31, 1)
+
+/* Bitfields in cmd field of HW decriptor */
+#define LDMA_INT		BIT(1) /* Enable DMA interrupts */
+#define LDMA_DATA_DIRECTION	BIT(12) /* 1: write to device, 0: read from device */
+
+#define LDMA_SLAVE_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+
+#define LDMA_MAX_TRANS_LEN	U32_MAX
+
+/*--  descriptors  -----------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_hw_desc - DMA HW descriptor
+ * @ndesc_addr: the next descriptor low address.
+ * @mem_addr: memory low address.
+ * @apb_addr: device buffer address.
+ * @len: length of a piece of carried content, in words.
+ * @step_len: length between two moved memory data blocks.
+ * @step_times: number of blocks to be carried in a single DMA operation.
+ * @cmd: descriptor command or state.
+ * @stats: DMA status.
+ * @high_ndesc_addr: the next descriptor high address.
+ * @high_mem_addr: memory high address.
+ * @reserved: reserved
+ */
+struct ls2x_dma_hw_desc {
+	u32 ndesc_addr;
+	u32 mem_addr;
+	u32 apb_addr;
+	u32 len;
+	u32 step_len;
+	u32 step_times;
+	u32 cmd;
+	u32 stats;
+	u32 high_ndesc_addr;
+	u32 high_mem_addr;
+	u32 reserved[2];
+} __packed;
+
+/*
+ * struct ls2x_dma_sg - ls2x dma scatter gather entry
+ * @hw: the pointer to DMA HW descriptor.
+ * @llp: physical address of the DMA HW descriptor.
+ * @phys: destination or source address(mem).
+ * @len: number of Bytes to read.
+ */
+struct ls2x_dma_sg {
+	struct ls2x_dma_hw_desc	*hw;
+	dma_addr_t		llp;
+	dma_addr_t		phys;
+	u32			len;
+};
+
+/*
+ * struct ls2x_dma_desc - software descriptor
+ * @vdesc: pointer to the virtual dma descriptor.
+ * @cyclic: flag to dma cyclic
+ * @burst_size: burst size of transaction, in words.
+ * @desc_num: number of sg entries.
+ * @direction: transfer direction, to or from device.
+ * @status: dma controller status.
+ * @sg: array of sgs.
+ */
+struct ls2x_dma_desc {
+	struct virt_dma_desc		vdesc;
+	bool				cyclic;
+	size_t				burst_size;
+	u32				desc_num;
+	enum dma_transfer_direction	direction;
+	enum dma_status			status;
+	struct ls2x_dma_sg		sg[] __counted_by(desc_num);
+};
+
+/*--  Channels  --------------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_chan - internal representation of an LS2X APB DMA channel
+ * @vchan: virtual dma channel entry.
+ * @desc: pointer to the ls2x sw dma descriptor.
+ * @pool: hw desc table
+ * @irq: irq line
+ * @sconfig: configuration for slave transfers, passed via .device_config
+ */
+struct ls2x_dma_chan {
+	struct virt_dma_chan	vchan;
+	struct ls2x_dma_desc	*desc;
+	void			*pool;
+	int			irq;
+	struct dma_slave_config	sconfig;
+};
+
+/*--  Controller  ------------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_priv - LS2X APB DMAC specific information
+ * @ddev: dmaengine dma_device object members
+ * @dma_clk: DMAC clock source
+ * @regs: memory mapped register base
+ * @lchan: channel to store ls2x_dma_chan structures
+ */
+struct ls2x_dma_priv {
+	struct dma_device	ddev;
+	struct clk		*dma_clk;
+	void __iomem		*regs;
+	struct ls2x_dma_chan	lchan;
+};
+
+/*--  Helper functions  ------------------------------------------------*/
+
+static inline struct ls2x_dma_desc *to_ldma_desc(struct virt_dma_desc *vdesc)
+{
+	return container_of(vdesc, struct ls2x_dma_desc, vdesc);
+}
+
+static inline struct ls2x_dma_chan *to_ldma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct ls2x_dma_chan, vchan.chan);
+}
+
+static inline struct ls2x_dma_priv *to_ldma_priv(struct dma_device *ddev)
+{
+	return container_of(ddev, struct ls2x_dma_priv, ddev);
+}
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+static void ls2x_dma_desc_free(struct virt_dma_desc *vdesc)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(vdesc->tx.chan);
+	struct ls2x_dma_desc *desc = to_ldma_desc(vdesc);
+	int i;
+
+	for (i = 0; i < desc->desc_num; i++) {
+		if (desc->sg[i].hw)
+			dma_pool_free(lchan->pool, desc->sg[i].hw,
+				      desc->sg[i].llp);
+	}
+
+	kfree(desc);
+}
+
+static void ls2x_dma_write_cmd(struct ls2x_dma_chan *lchan, bool cmd)
+{
+	struct ls2x_dma_priv *priv = to_ldma_priv(lchan->vchan.chan.device);
+	u64 val;
+
+	val = lo_hi_readq(priv->regs + LDMA_ORDER_ERG) & ~LDMA_CONFIG_MASK;
+	val |= LDMA_64BIT_EN | cmd;
+	lo_hi_writeq(val, priv->regs + LDMA_ORDER_ERG);
+}
+
+static void ls2x_dma_start_transfer(struct ls2x_dma_chan *lchan)
+{
+	struct ls2x_dma_priv *priv = to_ldma_priv(lchan->vchan.chan.device);
+	struct ls2x_dma_sg *ldma_sg;
+	struct virt_dma_desc *vdesc;
+	u64 val;
+
+	/* Get the next descriptor */
+	vdesc = vchan_next_desc(&lchan->vchan);
+	if (!vdesc) {
+		lchan->desc = NULL;
+		return;
+	}
+
+	list_del(&vdesc->node);
+	lchan->desc = to_ldma_desc(vdesc);
+	ldma_sg = &lchan->desc->sg[0];
+
+	/* Start DMA */
+	lo_hi_writeq(0, priv->regs + LDMA_ORDER_ERG);
+	val = (ldma_sg->llp & ~LDMA_CONFIG_MASK) | LDMA_64BIT_EN | LDMA_START;
+	lo_hi_writeq(val, priv->regs + LDMA_ORDER_ERG);
+}
+
+static size_t ls2x_dmac_detect_burst(struct ls2x_dma_chan *lchan)
+{
+	u32 maxburst, buswidth;
+
+	/* Reject definitely invalid configurations */
+	if ((lchan->sconfig.src_addr_width & LDMA_SLAVE_BUSWIDTHS) &&
+	    (lchan->sconfig.dst_addr_width & LDMA_SLAVE_BUSWIDTHS))
+		return 0;
+
+	if (lchan->sconfig.direction == DMA_MEM_TO_DEV) {
+		maxburst = lchan->sconfig.dst_maxburst;
+		buswidth = lchan->sconfig.dst_addr_width;
+	} else {
+		maxburst = lchan->sconfig.src_maxburst;
+		buswidth = lchan->sconfig.src_addr_width;
+	}
+
+	/* If maxburst is zero, fallback to LDMA_MAX_TRANS_LEN */
+	return maxburst ? (maxburst * buswidth) >> 2 : LDMA_MAX_TRANS_LEN;
+}
+
+static void ls2x_dma_fill_desc(struct ls2x_dma_chan *lchan, u32 sg_index,
+			       struct ls2x_dma_desc *desc)
+{
+	struct ls2x_dma_sg *ldma_sg = &desc->sg[sg_index];
+	u32 num_segments, segment_size;
+
+	if (desc->direction == DMA_MEM_TO_DEV) {
+		ldma_sg->hw->cmd = LDMA_INT | LDMA_DATA_DIRECTION;
+		ldma_sg->hw->apb_addr = lchan->sconfig.dst_addr;
+	} else {
+		ldma_sg->hw->cmd = LDMA_INT;
+		ldma_sg->hw->apb_addr = lchan->sconfig.src_addr;
+	}
+
+	ldma_sg->hw->mem_addr = lower_32_bits(ldma_sg->phys);
+	ldma_sg->hw->high_mem_addr = upper_32_bits(ldma_sg->phys);
+
+	/* Split into multiple equally sized segments if necessary */
+	num_segments = DIV_ROUND_UP((ldma_sg->len + 3) >> 2, desc->burst_size);
+	segment_size = DIV_ROUND_UP((ldma_sg->len + 3) >> 2, num_segments);
+
+	/* Word count register takes input in words */
+	ldma_sg->hw->len = segment_size;
+	ldma_sg->hw->step_times = num_segments;
+	ldma_sg->hw->step_len = 0;
+
+	/* lets make a link list */
+	if (sg_index) {
+		desc->sg[sg_index - 1].hw->ndesc_addr = ldma_sg->llp | LDMA_DESC_EN;
+		desc->sg[sg_index - 1].hw->high_ndesc_addr = upper_32_bits(ldma_sg->llp);
+	}
+}
+
+/*--  DMA Engine API  --------------------------------------------------*/
+
+/*
+ * ls2x_dma_alloc_chan_resources - allocate resources for DMA channel
+ * @chan: allocate descriptor resources for this channel
+ *
+ * return - the number of allocated descriptors
+ */
+static int ls2x_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	/* Create a pool of consistent memory blocks for hardware descriptors */
+	lchan->pool = dma_pool_create(dev_name(chan2dev(chan)),
+				      chan->device->dev, PAGE_SIZE,
+				      __alignof__(struct ls2x_dma_hw_desc), 0);
+	if (!lchan->pool) {
+		dev_err(chan2dev(chan), "No memory for descriptors\n");
+		return -ENOMEM;
+	}
+
+	return 1;
+}
+
+/*
+ * ls2x_dma_free_chan_resources - free all channel resources
+ * @chan: DMA channel
+ */
+static void ls2x_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	vchan_free_chan_resources(to_virt_chan(chan));
+	dma_pool_destroy(lchan->pool);
+	lchan->pool = NULL;
+}
+
+/*
+ * ls2x_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
+ * @chan: DMA channel
+ * @sgl: scatterlist to transfer to/from
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: tx descriptor status flags
+ * @context: transaction context (ignored)
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+ls2x_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		       u32 sg_len, enum dma_transfer_direction direction,
+		       unsigned long flags, void *context)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	struct ls2x_dma_desc *desc;
+	struct scatterlist *sg;
+	size_t burst_size;
+	int i;
+
+	if (unlikely(!sg_len || !is_slave_direction(direction)))
+		return NULL;
+
+	burst_size = ls2x_dmac_detect_burst(lchan);
+	if (!burst_size)
+		return NULL;
+
+	desc = kzalloc(struct_size(desc, sg, sg_len), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->desc_num = sg_len;
+	desc->direction = direction;
+	desc->burst_size = burst_size;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		struct ls2x_dma_sg *ldma_sg = &desc->sg[i];
+
+		/* Allocate DMA capable memory for hardware descriptor */
+		ldma_sg->hw = dma_pool_alloc(lchan->pool, GFP_NOWAIT, &ldma_sg->llp);
+		if (!ldma_sg->hw) {
+			desc->desc_num = i;
+			ls2x_dma_desc_free(&desc->vdesc);
+			return NULL;
+		}
+
+		ldma_sg->phys = sg_dma_address(sg);
+		ldma_sg->len = sg_dma_len(sg);
+
+		ls2x_dma_fill_desc(lchan, i, desc);
+	}
+
+	/* Setting the last descriptor enable bit */
+	desc->sg[sg_len - 1].hw->ndesc_addr &= ~LDMA_DESC_EN;
+	desc->status = DMA_IN_PROGRESS;
+
+	return vchan_tx_prep(&lchan->vchan, &desc->vdesc, flags);
+}
+
+/*
+ * ls2x_dma_prep_dma_cyclic - prepare the cyclic DMA transfer
+ * @chan: the DMA channel to prepare
+ * @buf_addr: physical DMA address where the buffer starts
+ * @buf_len: total number of bytes for the entire buffer
+ * @period_len: number of bytes for each period
+ * @direction: transfer direction, to or from device
+ * @flags: tx descriptor status flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+ls2x_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+			 size_t period_len, enum dma_transfer_direction direction,
+			 unsigned long flags)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	struct ls2x_dma_desc *desc;
+	size_t burst_size;
+	u32 num_periods;
+	int i;
+
+	if (unlikely(!buf_len || !period_len))
+		return NULL;
+
+	if (unlikely(!is_slave_direction(direction)))
+		return NULL;
+
+	burst_size = ls2x_dmac_detect_burst(lchan);
+	if (!burst_size)
+		return NULL;
+
+	num_periods = buf_len / period_len;
+	desc = kzalloc(struct_size(desc, sg, num_periods), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->desc_num = num_periods;
+	desc->direction = direction;
+	desc->burst_size = burst_size;
+
+	/* Build cyclic linked list */
+	for (i = 0; i < num_periods; i++) {
+		struct ls2x_dma_sg *ldma_sg = &desc->sg[i];
+
+		/* Allocate DMA capable memory for hardware descriptor */
+		ldma_sg->hw = dma_pool_alloc(lchan->pool, GFP_NOWAIT, &ldma_sg->llp);
+		if (!ldma_sg->hw) {
+			desc->desc_num = i;
+			ls2x_dma_desc_free(&desc->vdesc);
+			return NULL;
+		}
+
+		ldma_sg->phys = buf_addr + period_len * i;
+		ldma_sg->len = period_len;
+
+		ls2x_dma_fill_desc(lchan, i, desc);
+	}
+
+	/* Lets make a cyclic list */
+	desc->sg[num_periods - 1].hw->ndesc_addr = desc->sg[0].llp | LDMA_DESC_EN;
+	desc->sg[num_periods - 1].hw->high_ndesc_addr = upper_32_bits(desc->sg[0].llp);
+	desc->cyclic = true;
+	desc->status = DMA_IN_PROGRESS;
+
+	return vchan_tx_prep(&lchan->vchan, &desc->vdesc, flags);
+}
+
+/*
+ * ls2x_slave_config - set slave configuration for channel
+ * @chan: dma channel
+ * @cfg: slave configuration
+ *
+ * Sets slave configuration for channel
+ */
+static int ls2x_dma_slave_config(struct dma_chan *chan,
+				 struct dma_slave_config *config)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	memcpy(&lchan->sconfig, config, sizeof(*config));
+	return 0;
+}
+
+/*
+ * ls2x_dma_issue_pending - push pending transactions to the hardware
+ * @chan: channel
+ *
+ * When this function is called, all pending transactions are pushed to the
+ * hardware and executed.
+ */
+static void ls2x_dma_issue_pending(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (vchan_issue_pending(&lchan->vchan) && !lchan->desc)
+		ls2x_dma_start_transfer(lchan);
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+}
+
+/*
+ * ls2x_dma_terminate_all - terminate all transactions
+ * @chan: channel
+ *
+ * Stops all DMA transactions.
+ */
+static int ls2x_dma_terminate_all(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	/* Setting stop cmd */
+	ls2x_dma_write_cmd(lchan, LDMA_STOP);
+	if (lchan->desc) {
+		vchan_terminate_vdesc(&lchan->desc->vdesc);
+		lchan->desc = NULL;
+	}
+
+	vchan_get_all_descriptors(&lchan->vchan, &head);
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&lchan->vchan, &head);
+	return 0;
+}
+
+/*
+ * ls2x_dma_synchronize - Synchronizes the termination of transfers to the
+ * current context.
+ * @chan: channel
+ */
+static void ls2x_dma_synchronize(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	vchan_synchronize(&lchan->vchan);
+}
+
+static int ls2x_dma_pause(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (lchan->desc && lchan->desc->status == DMA_IN_PROGRESS) {
+		ls2x_dma_write_cmd(lchan, LDMA_STOP);
+		lchan->desc->status = DMA_PAUSED;
+	}
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	return 0;
+}
+
+static int ls2x_dma_resume(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (lchan->desc && lchan->desc->status == DMA_PAUSED) {
+		lchan->desc->status = DMA_IN_PROGRESS;
+		ls2x_dma_write_cmd(lchan, LDMA_START);
+	}
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	return 0;
+}
+
+/*
+ * ls2x_dma_isr - LS2X DMA Interrupt handler
+ * @irq: IRQ number
+ * @dev_id: Pointer to ls2x_dma_chan
+ *
+ * Return: IRQ_HANDLED/IRQ_NONE
+ */
+static irqreturn_t ls2x_dma_isr(int irq, void *dev_id)
+{
+	struct ls2x_dma_chan *lchan = dev_id;
+	struct ls2x_dma_desc *desc;
+
+	spin_lock(&lchan->vchan.lock);
+	desc = lchan->desc;
+	if (desc) {
+		if (desc->cyclic) {
+			vchan_cyclic_callback(&desc->vdesc);
+		} else {
+			desc->status = DMA_COMPLETE;
+			vchan_cookie_complete(&desc->vdesc);
+			ls2x_dma_start_transfer(lchan);
+		}
+
+		/* ls2x_dma_start_transfer() updates lchan->desc */
+		if (!lchan->desc)
+			ls2x_dma_write_cmd(lchan, LDMA_STOP);
+	}
+	spin_unlock(&lchan->vchan.lock);
+
+	return IRQ_HANDLED;
+}
+
+static int ls2x_dma_chan_init(struct platform_device *pdev,
+			      struct ls2x_dma_priv *priv)
+{
+	struct ls2x_dma_chan *lchan = &priv->lchan;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	lchan->irq = platform_get_irq(pdev, 0);
+	if (lchan->irq < 0)
+		return lchan->irq;
+
+	ret = devm_request_irq(dev, lchan->irq, ls2x_dma_isr, IRQF_TRIGGER_RISING,
+			       dev_name(&pdev->dev), lchan);
+	if (ret)
+		return ret;
+
+	/* Initialize channels related values */
+	INIT_LIST_HEAD(&priv->ddev.channels);
+	lchan->vchan.desc_free = ls2x_dma_desc_free;
+	vchan_init(&lchan->vchan, &priv->ddev);
+
+	return 0;
+}
+
+/*
+ * ls2x_dma_probe - Driver probe function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int ls2x_dma_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ls2x_dma_priv *priv;
+	struct dma_device *ddev;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->regs))
+		return dev_err_probe(dev, PTR_ERR(priv->regs),
+				     "devm_platform_ioremap_resource failed.\n");
+
+	priv->dma_clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->dma_clk))
+		return dev_err_probe(dev, PTR_ERR(priv->dma_clk), "devm_clk_get failed.\n");
+
+	ret = clk_prepare_enable(priv->dma_clk);
+	if (ret)
+		return dev_err_probe(dev, ret, "clk_prepare_enable failed.\n");
+
+	ret = ls2x_dma_chan_init(pdev, priv);
+	if (ret)
+		goto disable_clk;
+
+	ddev = &priv->ddev;
+	ddev->dev = dev;
+	dma_cap_zero(ddev->cap_mask);
+	dma_cap_set(DMA_SLAVE, ddev->cap_mask);
+	dma_cap_set(DMA_CYCLIC, ddev->cap_mask);
+
+	ddev->device_alloc_chan_resources = ls2x_dma_alloc_chan_resources;
+	ddev->device_free_chan_resources = ls2x_dma_free_chan_resources;
+	ddev->device_tx_status = dma_cookie_status;
+	ddev->device_issue_pending = ls2x_dma_issue_pending;
+	ddev->device_prep_slave_sg = ls2x_dma_prep_slave_sg;
+	ddev->device_prep_dma_cyclic = ls2x_dma_prep_dma_cyclic;
+	ddev->device_config = ls2x_dma_slave_config;
+	ddev->device_terminate_all = ls2x_dma_terminate_all;
+	ddev->device_synchronize = ls2x_dma_synchronize;
+	ddev->device_pause = ls2x_dma_pause;
+	ddev->device_resume = ls2x_dma_resume;
+
+	ddev->src_addr_widths = LDMA_SLAVE_BUSWIDTHS;
+	ddev->dst_addr_widths = LDMA_SLAVE_BUSWIDTHS;
+	ddev->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+
+	ret = dma_async_device_register(&priv->ddev);
+	if (ret < 0)
+		goto disable_clk;
+
+	ret = of_dma_controller_register(dev->of_node, of_dma_xlate_by_chan_id, priv);
+	if (ret < 0)
+		goto unregister_dmac;
+
+	platform_set_drvdata(pdev, priv);
+
+	dev_info(dev, "Loongson LS2X APB DMA driver registered successfully.\n");
+	return 0;
+
+unregister_dmac:
+	dma_async_device_unregister(&priv->ddev);
+disable_clk:
+	clk_disable_unprepare(priv->dma_clk);
+
+	return ret;
+}
+
+/*
+ * ls2x_dma_remove - Driver remove function
+ * @pdev: Pointer to the platform_device structure
+ */
+static void ls2x_dma_remove(struct platform_device *pdev)
+{
+	struct ls2x_dma_priv *priv = platform_get_drvdata(pdev);
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&priv->ddev);
+	clk_disable_unprepare(priv->dma_clk);
+}
+
+static const struct of_device_id ls2x_dma_of_match_table[] = {
+	{ .compatible = "loongson,ls2k1000-apbdma" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ls2x_dma_of_match_table);
+
+static struct platform_driver ls2x_dmac_driver = {
+	.probe		= ls2x_dma_probe,
+	.remove_new	= ls2x_dma_remove,
+	.driver = {
+		.name	= "ls2x-apbdma",
+		.of_match_table	= ls2x_dma_of_match_table,
+	},
+};
+module_platform_driver(ls2x_dmac_driver);
+
+MODULE_DESCRIPTION("Loongson LS2X APB DMA Controller driver");
+MODULE_AUTHOR("Loongson Technology Corporation Limited");
+MODULE_LICENSE("GPL");
-- 
GitLab


From a2ab7045389feab1c26ebab105a8ad6bce74a4a7 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Fri, 15 Dec 2023 14:13:09 +0100
Subject: [PATCH 1768/4076] dmaengine: axi-dmac: Small code cleanup

Use a for() loop instead of a while() loop in axi_dmac_fill_linear_sg().
This makes the code leaner and cleaner overall, and does not introduce
any functional change.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Link: https://lore.kernel.org/r/20231215131313.23840-2-paul@crapouillou.net
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dma-axi-dmac.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 2457a420c13d7..760940b21eabf 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -508,16 +508,13 @@ static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
 	segment_size = ((segment_size - 1) | chan->length_align_mask) + 1;
 
 	for (i = 0; i < num_periods; i++) {
-		len = period_len;
-
-		while (len > segment_size) {
+		for (len = period_len; len > segment_size; sg++) {
 			if (direction == DMA_DEV_TO_MEM)
 				sg->dest_addr = addr;
 			else
 				sg->src_addr = addr;
 			sg->x_len = segment_size;
 			sg->y_len = 1;
-			sg++;
 			addr += segment_size;
 			len -= segment_size;
 		}
-- 
GitLab


From 3f8fd25936ee5f52596f10d420f650c5b5e3285f Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Fri, 15 Dec 2023 14:13:10 +0100
Subject: [PATCH 1769/4076] dmaengine: axi-dmac: Allocate hardware descriptors

Change where and how the DMA transfers meta-data is stored, to prepare
for the upcoming introduction of scatter-gather support.

Allocate hardware descriptors in the format that the HDL core will be
expecting them when the scatter-gather feature is enabled, and use these
fields to store the data that was previously stored in the axi_dmac_sg
structure.

Note that the 'x_len' and 'y_len' fields now contain the transfer length
minus one, since that's what the hardware will expect in these fields.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Link: https://lore.kernel.org/r/20231215131313.23840-3-paul@crapouillou.net
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dma-axi-dmac.c | 134 ++++++++++++++++++++++++-------------
 1 file changed, 88 insertions(+), 46 deletions(-)

diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 760940b21eabf..185230a769b93 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -97,20 +97,31 @@
 /* The maximum ID allocated by the hardware is 31 */
 #define AXI_DMAC_SG_UNUSED 32U
 
+struct axi_dmac_hw_desc {
+	u32 flags;
+	u32 id;
+	u64 dest_addr;
+	u64 src_addr;
+	u64 __unused;
+	u32 y_len;
+	u32 x_len;
+	u32 src_stride;
+	u32 dst_stride;
+	u64 __pad[2];
+};
+
 struct axi_dmac_sg {
-	dma_addr_t src_addr;
-	dma_addr_t dest_addr;
-	unsigned int x_len;
-	unsigned int y_len;
-	unsigned int dest_stride;
-	unsigned int src_stride;
-	unsigned int id;
 	unsigned int partial_len;
 	bool schedule_when_free;
+
+	struct axi_dmac_hw_desc *hw;
+	dma_addr_t hw_phys;
 };
 
 struct axi_dmac_desc {
 	struct virt_dma_desc vdesc;
+	struct axi_dmac_chan *chan;
+
 	bool cyclic;
 	bool have_partial_xfer;
 
@@ -229,7 +240,7 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 	sg = &desc->sg[desc->num_submitted];
 
 	/* Already queued in cyclic mode. Wait for it to finish */
-	if (sg->id != AXI_DMAC_SG_UNUSED) {
+	if (sg->hw->id != AXI_DMAC_SG_UNUSED) {
 		sg->schedule_when_free = true;
 		return;
 	}
@@ -246,16 +257,16 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 		chan->next_desc = desc;
 	}
 
-	sg->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
+	sg->hw->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
 
 	if (axi_dmac_dest_is_mem(chan)) {
-		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->dest_addr);
-		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->dest_stride);
+		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->hw->dest_addr);
+		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->hw->dst_stride);
 	}
 
 	if (axi_dmac_src_is_mem(chan)) {
-		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->src_addr);
-		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->src_stride);
+		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->hw->src_addr);
+		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->hw->src_stride);
 	}
 
 	/*
@@ -270,8 +281,8 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 	if (chan->hw_partial_xfer)
 		flags |= AXI_DMAC_FLAG_PARTIAL_REPORT;
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->x_len - 1);
-	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->y_len - 1);
+	axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->hw->x_len);
+	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->hw->y_len);
 	axi_dmac_write(dmac, AXI_DMAC_REG_FLAGS, flags);
 	axi_dmac_write(dmac, AXI_DMAC_REG_START_TRANSFER, 1);
 }
@@ -286,9 +297,9 @@ static inline unsigned int axi_dmac_total_sg_bytes(struct axi_dmac_chan *chan,
 	struct axi_dmac_sg *sg)
 {
 	if (chan->hw_2d)
-		return sg->x_len * sg->y_len;
+		return (sg->hw->x_len + 1) * (sg->hw->y_len + 1);
 	else
-		return sg->x_len;
+		return (sg->hw->x_len + 1);
 }
 
 static void axi_dmac_dequeue_partial_xfers(struct axi_dmac_chan *chan)
@@ -307,9 +318,9 @@ static void axi_dmac_dequeue_partial_xfers(struct axi_dmac_chan *chan)
 		list_for_each_entry(desc, &chan->active_descs, vdesc.node) {
 			for (i = 0; i < desc->num_sgs; i++) {
 				sg = &desc->sg[i];
-				if (sg->id == AXI_DMAC_SG_UNUSED)
+				if (sg->hw->id == AXI_DMAC_SG_UNUSED)
 					continue;
-				if (sg->id == id) {
+				if (sg->hw->id == id) {
 					desc->have_partial_xfer = true;
 					sg->partial_len = len;
 					found_sg = true;
@@ -376,12 +387,12 @@ static bool axi_dmac_transfer_done(struct axi_dmac_chan *chan,
 
 	do {
 		sg = &active->sg[active->num_completed];
-		if (sg->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
+		if (sg->hw->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
 			break;
-		if (!(BIT(sg->id) & completed_transfers))
+		if (!(BIT(sg->hw->id) & completed_transfers))
 			break;
 		active->num_completed++;
-		sg->id = AXI_DMAC_SG_UNUSED;
+		sg->hw->id = AXI_DMAC_SG_UNUSED;
 		if (sg->schedule_when_free) {
 			sg->schedule_when_free = false;
 			start_next = true;
@@ -476,22 +487,52 @@ static void axi_dmac_issue_pending(struct dma_chan *c)
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
 }
 
-static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
+static struct axi_dmac_desc *
+axi_dmac_alloc_desc(struct axi_dmac_chan *chan, unsigned int num_sgs)
 {
+	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
+	struct device *dev = dmac->dma_dev.dev;
+	struct axi_dmac_hw_desc *hws;
 	struct axi_dmac_desc *desc;
+	dma_addr_t hw_phys;
 	unsigned int i;
 
 	desc = kzalloc(struct_size(desc, sg, num_sgs), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 	desc->num_sgs = num_sgs;
+	desc->chan = chan;
 
-	for (i = 0; i < num_sgs; i++)
-		desc->sg[i].id = AXI_DMAC_SG_UNUSED;
+	hws = dma_alloc_coherent(dev, PAGE_ALIGN(num_sgs * sizeof(*hws)),
+				&hw_phys, GFP_ATOMIC);
+	if (!hws) {
+		kfree(desc);
+		return NULL;
+	}
+
+	for (i = 0; i < num_sgs; i++) {
+		desc->sg[i].hw = &hws[i];
+		desc->sg[i].hw_phys = hw_phys + i * sizeof(*hws);
+
+		hws[i].id = AXI_DMAC_SG_UNUSED;
+		hws[i].flags = 0;
+	}
 
 	return desc;
 }
 
+static void axi_dmac_free_desc(struct axi_dmac_desc *desc)
+{
+	struct axi_dmac *dmac = chan_to_axi_dmac(desc->chan);
+	struct device *dev = dmac->dma_dev.dev;
+	struct axi_dmac_hw_desc *hw = desc->sg[0].hw;
+	dma_addr_t hw_phys = desc->sg[0].hw_phys;
+
+	dma_free_coherent(dev, PAGE_ALIGN(desc->num_sgs * sizeof(*hw)),
+			  hw, hw_phys);
+	kfree(desc);
+}
+
 static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
 	enum dma_transfer_direction direction, dma_addr_t addr,
 	unsigned int num_periods, unsigned int period_len,
@@ -510,21 +551,22 @@ static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
 	for (i = 0; i < num_periods; i++) {
 		for (len = period_len; len > segment_size; sg++) {
 			if (direction == DMA_DEV_TO_MEM)
-				sg->dest_addr = addr;
+				sg->hw->dest_addr = addr;
 			else
-				sg->src_addr = addr;
-			sg->x_len = segment_size;
-			sg->y_len = 1;
+				sg->hw->src_addr = addr;
+			sg->hw->x_len = segment_size - 1;
+			sg->hw->y_len = 0;
+			sg->hw->flags = 0;
 			addr += segment_size;
 			len -= segment_size;
 		}
 
 		if (direction == DMA_DEV_TO_MEM)
-			sg->dest_addr = addr;
+			sg->hw->dest_addr = addr;
 		else
-			sg->src_addr = addr;
-		sg->x_len = len;
-		sg->y_len = 1;
+			sg->hw->src_addr = addr;
+		sg->hw->x_len = len - 1;
+		sg->hw->y_len = 0;
 		sg++;
 		addr += len;
 	}
@@ -551,7 +593,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i)
 		num_sgs += DIV_ROUND_UP(sg_dma_len(sg), chan->max_length);
 
-	desc = axi_dmac_alloc_desc(num_sgs);
+	desc = axi_dmac_alloc_desc(chan, num_sgs);
 	if (!desc)
 		return NULL;
 
@@ -560,7 +602,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i) {
 		if (!axi_dmac_check_addr(chan, sg_dma_address(sg)) ||
 		    !axi_dmac_check_len(chan, sg_dma_len(sg))) {
-			kfree(desc);
+			axi_dmac_free_desc(desc);
 			return NULL;
 		}
 
@@ -595,7 +637,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 	num_periods = buf_len / period_len;
 	num_segments = DIV_ROUND_UP(period_len, chan->max_length);
 
-	desc = axi_dmac_alloc_desc(num_periods * num_segments);
+	desc = axi_dmac_alloc_desc(chan, num_periods * num_segments);
 	if (!desc)
 		return NULL;
 
@@ -650,26 +692,26 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_interleaved(
 			return NULL;
 	}
 
-	desc = axi_dmac_alloc_desc(1);
+	desc = axi_dmac_alloc_desc(chan, 1);
 	if (!desc)
 		return NULL;
 
 	if (axi_dmac_src_is_mem(chan)) {
-		desc->sg[0].src_addr = xt->src_start;
-		desc->sg[0].src_stride = xt->sgl[0].size + src_icg;
+		desc->sg[0].hw->src_addr = xt->src_start;
+		desc->sg[0].hw->src_stride = xt->sgl[0].size + src_icg;
 	}
 
 	if (axi_dmac_dest_is_mem(chan)) {
-		desc->sg[0].dest_addr = xt->dst_start;
-		desc->sg[0].dest_stride = xt->sgl[0].size + dst_icg;
+		desc->sg[0].hw->dest_addr = xt->dst_start;
+		desc->sg[0].hw->dst_stride = xt->sgl[0].size + dst_icg;
 	}
 
 	if (chan->hw_2d) {
-		desc->sg[0].x_len = xt->sgl[0].size;
-		desc->sg[0].y_len = xt->numf;
+		desc->sg[0].hw->x_len = xt->sgl[0].size - 1;
+		desc->sg[0].hw->y_len = xt->numf - 1;
 	} else {
-		desc->sg[0].x_len = xt->sgl[0].size * xt->numf;
-		desc->sg[0].y_len = 1;
+		desc->sg[0].hw->x_len = xt->sgl[0].size * xt->numf - 1;
+		desc->sg[0].hw->y_len = 0;
 	}
 
 	if (flags & DMA_CYCLIC)
@@ -685,7 +727,7 @@ static void axi_dmac_free_chan_resources(struct dma_chan *c)
 
 static void axi_dmac_desc_free(struct virt_dma_desc *vdesc)
 {
-	kfree(container_of(vdesc, struct axi_dmac_desc, vdesc));
+	axi_dmac_free_desc(to_axi_dmac_desc(vdesc));
 }
 
 static bool axi_dmac_regmap_rdwr(struct device *dev, unsigned int reg)
-- 
GitLab


From e97dc7435972d28ac7d96d199d4aedb868d04fd8 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Fri, 15 Dec 2023 14:13:11 +0100
Subject: [PATCH 1770/4076] dmaengine: axi-dmac: Add support for scatter-gather
 transfers

Implement support for scatter-gather transfers. Build a chain of
hardware descriptors, each one corresponding to a segment of the
transfer, and linked to the next one. The hardware will transfer the
chain and only fire interrupts when the whole chain has been
transferred.

Support for scatter-gather is automatically enabled when the driver
detects that the hardware supports it, by writing then reading the
AXI_DMAC_REG_SG_ADDRESS register. If not available, the driver will fall
back to standard DMA transfers.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Link: https://lore.kernel.org/r/20231215131313.23840-4-paul@crapouillou.net
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dma-axi-dmac.c | 135 +++++++++++++++++++++++++------------
 1 file changed, 93 insertions(+), 42 deletions(-)

diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 185230a769b93..5109530b66de9 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -81,9 +81,13 @@
 #define AXI_DMAC_REG_CURRENT_DEST_ADDR	0x438
 #define AXI_DMAC_REG_PARTIAL_XFER_LEN	0x44c
 #define AXI_DMAC_REG_PARTIAL_XFER_ID	0x450
+#define AXI_DMAC_REG_CURRENT_SG_ID	0x454
+#define AXI_DMAC_REG_SG_ADDRESS		0x47c
+#define AXI_DMAC_REG_SG_ADDRESS_HIGH	0x4bc
 
 #define AXI_DMAC_CTRL_ENABLE		BIT(0)
 #define AXI_DMAC_CTRL_PAUSE		BIT(1)
+#define AXI_DMAC_CTRL_ENABLE_SG		BIT(2)
 
 #define AXI_DMAC_IRQ_SOT		BIT(0)
 #define AXI_DMAC_IRQ_EOT		BIT(1)
@@ -97,12 +101,16 @@
 /* The maximum ID allocated by the hardware is 31 */
 #define AXI_DMAC_SG_UNUSED 32U
 
+/* Flags for axi_dmac_hw_desc.flags */
+#define AXI_DMAC_HW_FLAG_LAST		BIT(0)
+#define AXI_DMAC_HW_FLAG_IRQ		BIT(1)
+
 struct axi_dmac_hw_desc {
 	u32 flags;
 	u32 id;
 	u64 dest_addr;
 	u64 src_addr;
-	u64 __unused;
+	u64 next_sg_addr;
 	u32 y_len;
 	u32 x_len;
 	u32 src_stride;
@@ -150,6 +158,7 @@ struct axi_dmac_chan {
 	bool hw_partial_xfer;
 	bool hw_cyclic;
 	bool hw_2d;
+	bool hw_sg;
 };
 
 struct axi_dmac {
@@ -224,9 +233,11 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 	unsigned int flags = 0;
 	unsigned int val;
 
-	val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
-	if (val) /* Queue is full, wait for the next SOT IRQ */
-		return;
+	if (!chan->hw_sg) {
+		val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
+		if (val) /* Queue is full, wait for the next SOT IRQ */
+			return;
+	}
 
 	desc = chan->next_desc;
 
@@ -245,9 +256,10 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 		return;
 	}
 
-	desc->num_submitted++;
-	if (desc->num_submitted == desc->num_sgs ||
-	    desc->have_partial_xfer) {
+	if (chan->hw_sg) {
+		chan->next_desc = NULL;
+	} else if (++desc->num_submitted == desc->num_sgs ||
+		   desc->have_partial_xfer) {
 		if (desc->cyclic)
 			desc->num_submitted = 0; /* Start again */
 		else
@@ -259,14 +271,16 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 
 	sg->hw->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
 
-	if (axi_dmac_dest_is_mem(chan)) {
-		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->hw->dest_addr);
-		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->hw->dst_stride);
-	}
+	if (!chan->hw_sg) {
+		if (axi_dmac_dest_is_mem(chan)) {
+			axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->hw->dest_addr);
+			axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->hw->dst_stride);
+		}
 
-	if (axi_dmac_src_is_mem(chan)) {
-		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->hw->src_addr);
-		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->hw->src_stride);
+		if (axi_dmac_src_is_mem(chan)) {
+			axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->hw->src_addr);
+			axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->hw->src_stride);
+		}
 	}
 
 	/*
@@ -281,8 +295,14 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 	if (chan->hw_partial_xfer)
 		flags |= AXI_DMAC_FLAG_PARTIAL_REPORT;
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->hw->x_len);
-	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->hw->y_len);
+	if (chan->hw_sg) {
+		axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS, (u32)sg->hw_phys);
+		axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS_HIGH,
+			       (u64)sg->hw_phys >> 32);
+	} else {
+		axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->hw->x_len);
+		axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->hw->y_len);
+	}
 	axi_dmac_write(dmac, AXI_DMAC_REG_FLAGS, flags);
 	axi_dmac_write(dmac, AXI_DMAC_REG_START_TRANSFER, 1);
 }
@@ -359,6 +379,9 @@ static void axi_dmac_compute_residue(struct axi_dmac_chan *chan,
 	rslt->result = DMA_TRANS_NOERROR;
 	rslt->residue = 0;
 
+	if (chan->hw_sg)
+		return;
+
 	/*
 	 * We get here if the last completed segment is partial, which
 	 * means we can compute the residue from that segment onwards
@@ -385,36 +408,46 @@ static bool axi_dmac_transfer_done(struct axi_dmac_chan *chan,
 	    (completed_transfers & AXI_DMAC_FLAG_PARTIAL_XFER_DONE))
 		axi_dmac_dequeue_partial_xfers(chan);
 
-	do {
-		sg = &active->sg[active->num_completed];
-		if (sg->hw->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
-			break;
-		if (!(BIT(sg->hw->id) & completed_transfers))
-			break;
-		active->num_completed++;
-		sg->hw->id = AXI_DMAC_SG_UNUSED;
-		if (sg->schedule_when_free) {
-			sg->schedule_when_free = false;
-			start_next = true;
+	if (chan->hw_sg) {
+		if (active->cyclic) {
+			vchan_cyclic_callback(&active->vdesc);
+		} else {
+			list_del(&active->vdesc.node);
+			vchan_cookie_complete(&active->vdesc);
+			active = axi_dmac_active_desc(chan);
 		}
+	} else {
+		do {
+			sg = &active->sg[active->num_completed];
+			if (sg->hw->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
+				break;
+			if (!(BIT(sg->hw->id) & completed_transfers))
+				break;
+			active->num_completed++;
+			sg->hw->id = AXI_DMAC_SG_UNUSED;
+			if (sg->schedule_when_free) {
+				sg->schedule_when_free = false;
+				start_next = true;
+			}
 
-		if (sg->partial_len)
-			axi_dmac_compute_residue(chan, active);
+			if (sg->partial_len)
+				axi_dmac_compute_residue(chan, active);
 
-		if (active->cyclic)
-			vchan_cyclic_callback(&active->vdesc);
+			if (active->cyclic)
+				vchan_cyclic_callback(&active->vdesc);
 
-		if (active->num_completed == active->num_sgs ||
-		    sg->partial_len) {
-			if (active->cyclic) {
-				active->num_completed = 0; /* wrap around */
-			} else {
-				list_del(&active->vdesc.node);
-				vchan_cookie_complete(&active->vdesc);
-				active = axi_dmac_active_desc(chan);
+			if (active->num_completed == active->num_sgs ||
+			    sg->partial_len) {
+				if (active->cyclic) {
+					active->num_completed = 0; /* wrap around */
+				} else {
+					list_del(&active->vdesc.node);
+					vchan_cookie_complete(&active->vdesc);
+					active = axi_dmac_active_desc(chan);
+				}
 			}
-		}
-	} while (active);
+		} while (active);
+	}
 
 	return start_next;
 }
@@ -478,8 +511,12 @@ static void axi_dmac_issue_pending(struct dma_chan *c)
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
 	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
 	unsigned long flags;
+	u32 ctrl = AXI_DMAC_CTRL_ENABLE;
+
+	if (chan->hw_sg)
+		ctrl |= AXI_DMAC_CTRL_ENABLE_SG;
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, AXI_DMAC_CTRL_ENABLE);
+	axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, ctrl);
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 	if (vchan_issue_pending(&chan->vchan))
@@ -516,8 +553,14 @@ axi_dmac_alloc_desc(struct axi_dmac_chan *chan, unsigned int num_sgs)
 
 		hws[i].id = AXI_DMAC_SG_UNUSED;
 		hws[i].flags = 0;
+
+		/* Link hardware descriptors */
+		hws[i].next_sg_addr = hw_phys + (i + 1) * sizeof(*hws);
 	}
 
+	/* The last hardware descriptor will trigger an interrupt */
+	desc->sg[num_sgs - 1].hw->flags = AXI_DMAC_HW_FLAG_LAST | AXI_DMAC_HW_FLAG_IRQ;
+
 	return desc;
 }
 
@@ -753,6 +796,9 @@ static bool axi_dmac_regmap_rdwr(struct device *dev, unsigned int reg)
 	case AXI_DMAC_REG_CURRENT_DEST_ADDR:
 	case AXI_DMAC_REG_PARTIAL_XFER_LEN:
 	case AXI_DMAC_REG_PARTIAL_XFER_ID:
+	case AXI_DMAC_REG_CURRENT_SG_ID:
+	case AXI_DMAC_REG_SG_ADDRESS:
+	case AXI_DMAC_REG_SG_ADDRESS_HIGH:
 		return true;
 	default:
 		return false;
@@ -905,6 +951,10 @@ static int axi_dmac_detect_caps(struct axi_dmac *dmac, unsigned int version)
 	if (axi_dmac_read(dmac, AXI_DMAC_REG_FLAGS) == AXI_DMAC_FLAG_CYCLIC)
 		chan->hw_cyclic = true;
 
+	axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS, 0xffffffff);
+	if (axi_dmac_read(dmac, AXI_DMAC_REG_SG_ADDRESS))
+		chan->hw_sg = true;
+
 	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, 1);
 	if (axi_dmac_read(dmac, AXI_DMAC_REG_Y_LENGTH) == 1)
 		chan->hw_2d = true;
@@ -1005,6 +1055,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	dma_dev->dst_addr_widths = BIT(dmac->chan.dest_width);
 	dma_dev->directions = BIT(dmac->chan.direction);
 	dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	dma_dev->max_sg_burst = 31; /* 31 SGs maximum in one burst */
 	INIT_LIST_HEAD(&dma_dev->channels);
 
 	dmac->chan.vchan.desc_free = axi_dmac_desc_free;
-- 
GitLab


From 238f68a08e19a612b8912c8697901e9982f97811 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Fri, 15 Dec 2023 14:13:12 +0100
Subject: [PATCH 1771/4076] dmaengine: axi-dmac: Use only EOT interrupts when
 doing scatter-gather

Instead of notifying userspace in the end-of-transfer (EOT) interrupt
and program the hardware in the start-of-transfer (SOT) interrupt, we
can do both things in the EOT, allowing us to mask the SOT, and halve
the number of interrupts sent by the HDL core.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Link: https://lore.kernel.org/r/20231215131313.23840-5-paul@crapouillou.net
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dma-axi-dmac.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 5109530b66de9..f63acae511fb2 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -411,10 +411,12 @@ static bool axi_dmac_transfer_done(struct axi_dmac_chan *chan,
 	if (chan->hw_sg) {
 		if (active->cyclic) {
 			vchan_cyclic_callback(&active->vdesc);
+			start_next = true;
 		} else {
 			list_del(&active->vdesc.node);
 			vchan_cookie_complete(&active->vdesc);
 			active = axi_dmac_active_desc(chan);
+			start_next = !!active;
 		}
 	} else {
 		do {
@@ -1000,6 +1002,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	struct axi_dmac *dmac;
 	struct regmap *regmap;
 	unsigned int version;
+	u32 irq_mask = 0;
 	int ret;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
@@ -1067,7 +1070,10 @@ static int axi_dmac_probe(struct platform_device *pdev)
 
 	dma_dev->copy_align = (dmac->chan.address_align_mask + 1);
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, 0x00);
+	if (dmac->chan.hw_sg)
+		irq_mask |= AXI_DMAC_IRQ_SOT;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, irq_mask);
 
 	if (of_dma_is_coherent(pdev->dev.of_node)) {
 		ret = axi_dmac_read(dmac, AXI_DMAC_REG_COHERENCY_DESC);
-- 
GitLab


From f60dfe0c561a8f1b8e30d3770997cbaa636f57f9 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Fri, 15 Dec 2023 14:13:13 +0100
Subject: [PATCH 1772/4076] dmaengine: axi-dmac: Improve cyclic DMA transfers
 in SG mode

For cyclic transfers, chain the last descriptor to the first one, and
disable IRQ generation if there is no callback registered with the
cyclic transfer.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Link: https://lore.kernel.org/r/20231215131313.23840-6-paul@crapouillou.net
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dma-axi-dmac.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index f63acae511fb2..4e339c04fc1ea 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -285,12 +285,14 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 
 	/*
 	 * If the hardware supports cyclic transfers and there is no callback to
-	 * call and only a single segment, enable hw cyclic mode to avoid
-	 * unnecessary interrupts.
+	 * call, enable hw cyclic mode to avoid unnecessary interrupts.
 	 */
-	if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback &&
-		desc->num_sgs == 1)
-		flags |= AXI_DMAC_FLAG_CYCLIC;
+	if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback) {
+		if (chan->hw_sg)
+			desc->sg[desc->num_sgs - 1].hw->flags &= ~AXI_DMAC_HW_FLAG_IRQ;
+		else if (desc->num_sgs == 1)
+			flags |= AXI_DMAC_FLAG_CYCLIC;
+	}
 
 	if (chan->hw_partial_xfer)
 		flags |= AXI_DMAC_FLAG_PARTIAL_REPORT;
@@ -411,7 +413,6 @@ static bool axi_dmac_transfer_done(struct axi_dmac_chan *chan,
 	if (chan->hw_sg) {
 		if (active->cyclic) {
 			vchan_cyclic_callback(&active->vdesc);
-			start_next = true;
 		} else {
 			list_del(&active->vdesc.node);
 			vchan_cookie_complete(&active->vdesc);
@@ -667,7 +668,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 {
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
 	struct axi_dmac_desc *desc;
-	unsigned int num_periods, num_segments;
+	unsigned int num_periods, num_segments, num_sgs;
 
 	if (direction != chan->direction)
 		return NULL;
@@ -681,11 +682,16 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 
 	num_periods = buf_len / period_len;
 	num_segments = DIV_ROUND_UP(period_len, chan->max_length);
+	num_sgs = num_periods * num_segments;
 
-	desc = axi_dmac_alloc_desc(chan, num_periods * num_segments);
+	desc = axi_dmac_alloc_desc(chan, num_sgs);
 	if (!desc)
 		return NULL;
 
+	/* Chain the last descriptor to the first, and remove its "last" flag */
+	desc->sg[num_sgs - 1].hw->next_sg_addr = desc->sg[0].hw_phys;
+	desc->sg[num_sgs - 1].hw->flags &= ~AXI_DMAC_HW_FLAG_LAST;
+
 	axi_dmac_fill_linear_sg(chan, direction, buf_addr, num_periods,
 		period_len, desc->sg);
 
-- 
GitLab


From dc51b4442dd94ab12c146c1897bbdb40e16d5636 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 14 Nov 2023 10:48:21 -0500
Subject: [PATCH 1773/4076] dmaengine: fsl-edma: fix eDMAv4 channel allocation
 issue

The eDMAv4 channel mux has a limitation where certain requests must use
even channels, while others must use odd numbers.

Add two flags (ARGS_EVEN_CH and ARGS_ODD_CH) to reflect this limitation.
The device tree source (dts) files need to be updated accordingly.

This issue was identified by the following commit:
commit a725990557e7 ("arm64: dts: imx93: Fix the dmas entries order")

Reverting channel orders triggered this problem.

Fixes: 72f5801a4e2b ("dmaengine: fsl-edma: integrate v3 support")
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231114154824.3617255-2-Frank.Li@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/fsl-edma-main.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 4635e16d7705e..3ee08f390f810 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -24,6 +24,8 @@
 #define ARGS_RX                         BIT(0)
 #define ARGS_REMOTE                     BIT(1)
 #define ARGS_MULTI_FIFO                 BIT(2)
+#define ARGS_EVEN_CH                    BIT(3)
+#define ARGS_ODD_CH                     BIT(4)
 
 static void fsl_edma_synchronize(struct dma_chan *chan)
 {
@@ -157,6 +159,12 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec,
 		fsl_chan->is_remote = dma_spec->args[2] & ARGS_REMOTE;
 		fsl_chan->is_multi_fifo = dma_spec->args[2] & ARGS_MULTI_FIFO;
 
+		if ((dma_spec->args[2] & ARGS_EVEN_CH) && (i & 0x1))
+			continue;
+
+		if ((dma_spec->args[2] & ARGS_ODD_CH) && !(i & 0x1))
+			continue;
+
 		if (!b_chmux && i == dma_spec->args[0]) {
 			chan = dma_get_slave_channel(chan);
 			chan->device->privatecnt++;
-- 
GitLab


From 1e9b05258271b76ccc04a4b535009d2cb596506a Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 14 Nov 2023 10:48:22 -0500
Subject: [PATCH 1774/4076] dt-bindings: dma: fsl-edma: Add fsl-edma.h to
 prevent hardcoding in dts

Introduce a common dt-bindings header file, fsl-edma.h, shared between
the driver and dts files. This addition aims to eliminate hardcoded values
in dts files, promoting maintainability and consistency.

DTS header file not support BIT() macro yet. Directly use 2^n number.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231114154824.3617255-3-Frank.Li@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/dt-bindings/dma/fsl-edma.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 include/dt-bindings/dma/fsl-edma.h

diff --git a/include/dt-bindings/dma/fsl-edma.h b/include/dt-bindings/dma/fsl-edma.h
new file mode 100644
index 0000000000000..fd11478cfe9cc
--- /dev/null
+++ b/include/dt-bindings/dma/fsl-edma.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
+
+#ifndef _FSL_EDMA_DT_BINDING_H_
+#define _FSL_EDMA_DT_BINDING_H_
+
+/* Receive Channel */
+#define FSL_EDMA_RX		0x1
+
+/* iMX8 audio remote DMA */
+#define FSL_EDMA_REMOTE		0x2
+
+/* FIFO is continue memory region */
+#define FSL_EDMA_MULTI_FIFO	0x4
+
+/* Channel need stick to even channel */
+#define FSL_EDMA_EVEN_CH	0x8
+
+/* Channel need stick to odd channel */
+#define FSL_EDMA_ODD_CH		0x10
+
+#endif
-- 
GitLab


From d0e217b72f9f5c5ef35e3423d393ea8093ce98ec Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 14 Nov 2023 10:48:23 -0500
Subject: [PATCH 1775/4076] dmaengine: fsl-edma: utilize common dt-binding
 header file

Refactor the code to use the common dt-binding header file, fsl-edma.h.
Renaming ARGS* to FSL_EDMA*, ensuring no functional changes.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231114154824.3617255-4-Frank.Li@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/fsl-edma-main.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 3ee08f390f810..f53b0ec17bcbc 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -9,6 +9,7 @@
  * Vybrid and Layerscape SoCs.
  */
 
+#include <dt-bindings/dma/fsl-edma.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/clk.h>
@@ -21,12 +22,6 @@
 
 #include "fsl-edma-common.h"
 
-#define ARGS_RX                         BIT(0)
-#define ARGS_REMOTE                     BIT(1)
-#define ARGS_MULTI_FIFO                 BIT(2)
-#define ARGS_EVEN_CH                    BIT(3)
-#define ARGS_ODD_CH                     BIT(4)
-
 static void fsl_edma_synchronize(struct dma_chan *chan)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
@@ -155,14 +150,14 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec,
 		i = fsl_chan - fsl_edma->chans;
 
 		fsl_chan->priority = dma_spec->args[1];
-		fsl_chan->is_rxchan = dma_spec->args[2] & ARGS_RX;
-		fsl_chan->is_remote = dma_spec->args[2] & ARGS_REMOTE;
-		fsl_chan->is_multi_fifo = dma_spec->args[2] & ARGS_MULTI_FIFO;
+		fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX;
+		fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE;
+		fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO;
 
-		if ((dma_spec->args[2] & ARGS_EVEN_CH) && (i & 0x1))
+		if ((dma_spec->args[2] & FSL_EDMA_EVEN_CH) && (i & 0x1))
 			continue;
 
-		if ((dma_spec->args[2] & ARGS_ODD_CH) && !(i & 0x1))
+		if ((dma_spec->args[2] & FSL_EDMA_ODD_CH) && !(i & 0x1))
 			continue;
 
 		if (!b_chmux && i == dma_spec->args[0]) {
-- 
GitLab


From f5c24d94512f1b288262beda4d3dcb9629222fc7 Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Wed, 13 Dec 2023 17:04:52 +0100
Subject: [PATCH 1776/4076] dmaengine: fix NULL pointer in channel
 unregistration function

__dma_async_device_channel_register() can fail. In case of failure,
chan->local is freed (with free_percpu()), and chan->local is nullified.
When dma_async_device_unregister() is called (because of managed API or
intentionally by DMA controller driver), channels are unconditionally
unregistered, leading to this NULL pointer:
[    1.318693] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000d0
[...]
[    1.484499] Call trace:
[    1.486930]  device_del+0x40/0x394
[    1.490314]  device_unregister+0x20/0x7c
[    1.494220]  __dma_async_device_channel_unregister+0x68/0xc0

Look at dma_async_device_register() function error path, channel device
unregistration is done only if chan->local is not NULL.

Then add the same condition at the beginning of
__dma_async_device_channel_unregister() function, to avoid NULL pointer
issue whatever the API used to reach this function.

Fixes: d2fb0a043838 ("dmaengine: break out channel registration")
Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/20231213160452.2598073-1-amelie.delaunay@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index b7388ae62d7f1..491b222402216 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1103,6 +1103,9 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_register);
 static void __dma_async_device_channel_unregister(struct dma_device *device,
 						  struct dma_chan *chan)
 {
+	if (chan->local == NULL)
+		return;
+
 	WARN_ONCE(!device->device_release && chan->client_count,
 		  "%s called while %d clients hold a reference\n",
 		  __func__, chan->client_count);
-- 
GitLab


From 3b08b3775593442be52cbb99efbccbd7fe4fa3fe Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Wed, 13 Dec 2023 13:43:18 +0530
Subject: [PATCH 1777/4076] dmaengine: ti: k3-udma: Add PSIL threads for AM62P
 and J722S

Add PSIL thread information and enable UDMA support for AM62P
and J722S SoC. J722S SoC family is a superset of AM62P, thus
common PSIL thread ID map is reused for both devices.

For those interested, more details about the SoC can be found
in the Technical Reference Manual here:
	AM62P - https://www.ti.com/lit/pdf/spruj83
	J722S -	https://www.ti.com/lit/zip/sprujb3

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Signed-off-by: Bryan Brattlof <bb@ti.com>
Signed-off-by: Vaishnav Achath <vaishnav.a@ti.com>
Reviewed-by: Jai Luthra <j-luthra@ti.com>
Link: https://lore.kernel.org/r/20231213081318.26203-1-vaishnav.a@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/ti/Makefile        |   3 +-
 drivers/dma/ti/k3-psil-am62p.c | 325 +++++++++++++++++++++++++++++++++
 drivers/dma/ti/k3-psil-priv.h  |   1 +
 drivers/dma/ti/k3-psil.c       |   2 +
 drivers/dma/ti/k3-udma.c       |   2 +
 5 files changed, 332 insertions(+), 1 deletion(-)
 create mode 100644 drivers/dma/ti/k3-psil-am62p.c

diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile
index acc950bf609c3..d376c117cecf6 100644
--- a/drivers/dma/ti/Makefile
+++ b/drivers/dma/ti/Makefile
@@ -12,6 +12,7 @@ k3-psil-lib-objs := k3-psil.o \
 		    k3-psil-j721s2.o \
 		    k3-psil-am62.o \
 		    k3-psil-am62a.o \
-		    k3-psil-j784s4.o
+		    k3-psil-j784s4.o \
+		    k3-psil-am62p.o
 obj-$(CONFIG_TI_K3_PSIL) += k3-psil-lib.o
 obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o
diff --git a/drivers/dma/ti/k3-psil-am62p.c b/drivers/dma/ti/k3-psil-am62p.c
new file mode 100644
index 0000000000000..0f338e16d9710
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-am62p.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#include <linux/kernel.h>
+
+#include "k3-psil-priv.h"
+
+#define PSIL_PDMA_XY_TR(x)					\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_PDMA_XY,		\
+			.mapped_channel_id = -1,		\
+			.default_flow_id = -1,			\
+		},						\
+	}
+
+#define PSIL_PDMA_XY_PKT(x)					\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_PDMA_XY,		\
+			.mapped_channel_id = -1,		\
+			.default_flow_id = -1,			\
+			.pkt_mode = 1,				\
+		},						\
+	}
+
+#define PSIL_ETHERNET(x, ch, flow_base, flow_cnt)		\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_NATIVE,		\
+			.pkt_mode = 1,				\
+			.needs_epib = 1,			\
+			.psd_size = 16,				\
+			.mapped_channel_id = ch,		\
+			.flow_start = flow_base,		\
+			.flow_num = flow_cnt,			\
+			.default_flow_id = flow_base,		\
+		},						\
+	}
+
+#define PSIL_SAUL(x, ch, flow_base, flow_cnt, default_flow, tx)	\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_NATIVE,		\
+			.pkt_mode = 1,				\
+			.needs_epib = 1,			\
+			.psd_size = 64,				\
+			.mapped_channel_id = ch,		\
+			.flow_start = flow_base,		\
+			.flow_num = flow_cnt,			\
+			.default_flow_id = default_flow,	\
+			.notdpkt = tx,				\
+		},						\
+	}
+
+#define PSIL_PDMA_MCASP(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pdma_acc32 = 1,		\
+			.pdma_burst = 1,		\
+		},					\
+	}
+
+#define PSIL_CSI2RX(x)					\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+		},					\
+	}
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep am62p_src_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0x7504, 20, 35, 8, 35, 0),
+	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
+	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
+	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0x4300),
+	PSIL_PDMA_XY_PKT(0x4301),
+	PSIL_PDMA_XY_PKT(0x4302),
+	PSIL_PDMA_XY_PKT(0x4303),
+	PSIL_PDMA_XY_PKT(0x4304),
+	PSIL_PDMA_XY_PKT(0x4305),
+	PSIL_PDMA_XY_PKT(0x4306),
+	PSIL_PDMA_XY_PKT(0x4307),
+	PSIL_PDMA_XY_PKT(0x4308),
+	PSIL_PDMA_XY_PKT(0x4309),
+	PSIL_PDMA_XY_PKT(0x430a),
+	PSIL_PDMA_XY_PKT(0x430b),
+	/* PDMA_MAIN1 - UART0-6 */
+	PSIL_PDMA_XY_PKT(0x4400),
+	PSIL_PDMA_XY_PKT(0x4401),
+	PSIL_PDMA_XY_PKT(0x4402),
+	PSIL_PDMA_XY_PKT(0x4403),
+	PSIL_PDMA_XY_PKT(0x4404),
+	PSIL_PDMA_XY_PKT(0x4405),
+	PSIL_PDMA_XY_PKT(0x4406),
+	/* PDMA_MAIN2 - MCASP0-2 */
+	PSIL_PDMA_MCASP(0x4500),
+	PSIL_PDMA_MCASP(0x4501),
+	PSIL_PDMA_MCASP(0x4502),
+	/* CPSW3G */
+	PSIL_ETHERNET(0x4600, 19, 19, 16),
+	/* CSI2RX */
+	PSIL_CSI2RX(0x5000),
+	PSIL_CSI2RX(0x5001),
+	PSIL_CSI2RX(0x5002),
+	PSIL_CSI2RX(0x5003),
+	PSIL_CSI2RX(0x5004),
+	PSIL_CSI2RX(0x5005),
+	PSIL_CSI2RX(0x5006),
+	PSIL_CSI2RX(0x5007),
+	PSIL_CSI2RX(0x5008),
+	PSIL_CSI2RX(0x5009),
+	PSIL_CSI2RX(0x500a),
+	PSIL_CSI2RX(0x500b),
+	PSIL_CSI2RX(0x500c),
+	PSIL_CSI2RX(0x500d),
+	PSIL_CSI2RX(0x500e),
+	PSIL_CSI2RX(0x500f),
+	PSIL_CSI2RX(0x5010),
+	PSIL_CSI2RX(0x5011),
+	PSIL_CSI2RX(0x5012),
+	PSIL_CSI2RX(0x5013),
+	PSIL_CSI2RX(0x5014),
+	PSIL_CSI2RX(0x5015),
+	PSIL_CSI2RX(0x5016),
+	PSIL_CSI2RX(0x5017),
+	PSIL_CSI2RX(0x5018),
+	PSIL_CSI2RX(0x5019),
+	PSIL_CSI2RX(0x501a),
+	PSIL_CSI2RX(0x501b),
+	PSIL_CSI2RX(0x501c),
+	PSIL_CSI2RX(0x501d),
+	PSIL_CSI2RX(0x501e),
+	PSIL_CSI2RX(0x501f),
+	PSIL_CSI2RX(0x5000),
+	PSIL_CSI2RX(0x5001),
+	PSIL_CSI2RX(0x5002),
+	PSIL_CSI2RX(0x5003),
+	PSIL_CSI2RX(0x5004),
+	PSIL_CSI2RX(0x5005),
+	PSIL_CSI2RX(0x5006),
+	PSIL_CSI2RX(0x5007),
+	PSIL_CSI2RX(0x5008),
+	PSIL_CSI2RX(0x5009),
+	PSIL_CSI2RX(0x500a),
+	PSIL_CSI2RX(0x500b),
+	PSIL_CSI2RX(0x500c),
+	PSIL_CSI2RX(0x500d),
+	PSIL_CSI2RX(0x500e),
+	PSIL_CSI2RX(0x500f),
+	PSIL_CSI2RX(0x5010),
+	PSIL_CSI2RX(0x5011),
+	PSIL_CSI2RX(0x5012),
+	PSIL_CSI2RX(0x5013),
+	PSIL_CSI2RX(0x5014),
+	PSIL_CSI2RX(0x5015),
+	PSIL_CSI2RX(0x5016),
+	PSIL_CSI2RX(0x5017),
+	PSIL_CSI2RX(0x5018),
+	PSIL_CSI2RX(0x5019),
+	PSIL_CSI2RX(0x501a),
+	PSIL_CSI2RX(0x501b),
+	PSIL_CSI2RX(0x501c),
+	PSIL_CSI2RX(0x501d),
+	PSIL_CSI2RX(0x501e),
+	PSIL_CSI2RX(0x501f),
+	/* CSIRX 1-3 (only for J722S) */
+	PSIL_CSI2RX(0x5100),
+	PSIL_CSI2RX(0x5101),
+	PSIL_CSI2RX(0x5102),
+	PSIL_CSI2RX(0x5103),
+	PSIL_CSI2RX(0x5104),
+	PSIL_CSI2RX(0x5105),
+	PSIL_CSI2RX(0x5106),
+	PSIL_CSI2RX(0x5107),
+	PSIL_CSI2RX(0x5108),
+	PSIL_CSI2RX(0x5109),
+	PSIL_CSI2RX(0x510a),
+	PSIL_CSI2RX(0x510b),
+	PSIL_CSI2RX(0x510c),
+	PSIL_CSI2RX(0x510d),
+	PSIL_CSI2RX(0x510e),
+	PSIL_CSI2RX(0x510f),
+	PSIL_CSI2RX(0x5110),
+	PSIL_CSI2RX(0x5111),
+	PSIL_CSI2RX(0x5112),
+	PSIL_CSI2RX(0x5113),
+	PSIL_CSI2RX(0x5114),
+	PSIL_CSI2RX(0x5115),
+	PSIL_CSI2RX(0x5116),
+	PSIL_CSI2RX(0x5117),
+	PSIL_CSI2RX(0x5118),
+	PSIL_CSI2RX(0x5119),
+	PSIL_CSI2RX(0x511a),
+	PSIL_CSI2RX(0x511b),
+	PSIL_CSI2RX(0x511c),
+	PSIL_CSI2RX(0x511d),
+	PSIL_CSI2RX(0x511e),
+	PSIL_CSI2RX(0x511f),
+	PSIL_CSI2RX(0x5200),
+	PSIL_CSI2RX(0x5201),
+	PSIL_CSI2RX(0x5202),
+	PSIL_CSI2RX(0x5203),
+	PSIL_CSI2RX(0x5204),
+	PSIL_CSI2RX(0x5205),
+	PSIL_CSI2RX(0x5206),
+	PSIL_CSI2RX(0x5207),
+	PSIL_CSI2RX(0x5208),
+	PSIL_CSI2RX(0x5209),
+	PSIL_CSI2RX(0x520a),
+	PSIL_CSI2RX(0x520b),
+	PSIL_CSI2RX(0x520c),
+	PSIL_CSI2RX(0x520d),
+	PSIL_CSI2RX(0x520e),
+	PSIL_CSI2RX(0x520f),
+	PSIL_CSI2RX(0x5210),
+	PSIL_CSI2RX(0x5211),
+	PSIL_CSI2RX(0x5212),
+	PSIL_CSI2RX(0x5213),
+	PSIL_CSI2RX(0x5214),
+	PSIL_CSI2RX(0x5215),
+	PSIL_CSI2RX(0x5216),
+	PSIL_CSI2RX(0x5217),
+	PSIL_CSI2RX(0x5218),
+	PSIL_CSI2RX(0x5219),
+	PSIL_CSI2RX(0x521a),
+	PSIL_CSI2RX(0x521b),
+	PSIL_CSI2RX(0x521c),
+	PSIL_CSI2RX(0x521d),
+	PSIL_CSI2RX(0x521e),
+	PSIL_CSI2RX(0x521f),
+	PSIL_CSI2RX(0x5300),
+	PSIL_CSI2RX(0x5301),
+	PSIL_CSI2RX(0x5302),
+	PSIL_CSI2RX(0x5303),
+	PSIL_CSI2RX(0x5304),
+	PSIL_CSI2RX(0x5305),
+	PSIL_CSI2RX(0x5306),
+	PSIL_CSI2RX(0x5307),
+	PSIL_CSI2RX(0x5308),
+	PSIL_CSI2RX(0x5309),
+	PSIL_CSI2RX(0x530a),
+	PSIL_CSI2RX(0x530b),
+	PSIL_CSI2RX(0x530c),
+	PSIL_CSI2RX(0x530d),
+	PSIL_CSI2RX(0x530e),
+	PSIL_CSI2RX(0x530f),
+	PSIL_CSI2RX(0x5310),
+	PSIL_CSI2RX(0x5311),
+	PSIL_CSI2RX(0x5312),
+	PSIL_CSI2RX(0x5313),
+	PSIL_CSI2RX(0x5314),
+	PSIL_CSI2RX(0x5315),
+	PSIL_CSI2RX(0x5316),
+	PSIL_CSI2RX(0x5317),
+	PSIL_CSI2RX(0x5318),
+	PSIL_CSI2RX(0x5319),
+	PSIL_CSI2RX(0x531a),
+	PSIL_CSI2RX(0x531b),
+	PSIL_CSI2RX(0x531c),
+	PSIL_CSI2RX(0x531d),
+	PSIL_CSI2RX(0x531e),
+	PSIL_CSI2RX(0x531f),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep am62p_dst_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
+	PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0xc300),
+	PSIL_PDMA_XY_PKT(0xc301),
+	PSIL_PDMA_XY_PKT(0xc302),
+	PSIL_PDMA_XY_PKT(0xc303),
+	PSIL_PDMA_XY_PKT(0xc304),
+	PSIL_PDMA_XY_PKT(0xc305),
+	PSIL_PDMA_XY_PKT(0xc306),
+	PSIL_PDMA_XY_PKT(0xc307),
+	PSIL_PDMA_XY_PKT(0xc308),
+	PSIL_PDMA_XY_PKT(0xc309),
+	PSIL_PDMA_XY_PKT(0xc30a),
+	PSIL_PDMA_XY_PKT(0xc30b),
+	/* PDMA_MAIN1 - UART0-6 */
+	PSIL_PDMA_XY_PKT(0xc400),
+	PSIL_PDMA_XY_PKT(0xc401),
+	PSIL_PDMA_XY_PKT(0xc402),
+	PSIL_PDMA_XY_PKT(0xc403),
+	PSIL_PDMA_XY_PKT(0xc404),
+	PSIL_PDMA_XY_PKT(0xc405),
+	PSIL_PDMA_XY_PKT(0xc406),
+	/* PDMA_MAIN2 - MCASP0-2 */
+	PSIL_PDMA_MCASP(0xc500),
+	PSIL_PDMA_MCASP(0xc501),
+	PSIL_PDMA_MCASP(0xc502),
+	/* CPSW3G */
+	PSIL_ETHERNET(0xc600, 19, 19, 8),
+	PSIL_ETHERNET(0xc601, 20, 27, 8),
+	PSIL_ETHERNET(0xc602, 21, 35, 8),
+	PSIL_ETHERNET(0xc603, 22, 43, 8),
+	PSIL_ETHERNET(0xc604, 23, 51, 8),
+	PSIL_ETHERNET(0xc605, 24, 59, 8),
+	PSIL_ETHERNET(0xc606, 25, 67, 8),
+	PSIL_ETHERNET(0xc607, 26, 75, 8),
+};
+
+struct psil_ep_map am62p_ep_map = {
+	.name = "am62p",
+	.src = am62p_src_ep_map,
+	.src_count = ARRAY_SIZE(am62p_src_ep_map),
+	.dst = am62p_dst_ep_map,
+	.dst_count = ARRAY_SIZE(am62p_dst_ep_map),
+};
diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h
index c383723d1c8f6..a577be97e3447 100644
--- a/drivers/dma/ti/k3-psil-priv.h
+++ b/drivers/dma/ti/k3-psil-priv.h
@@ -45,5 +45,6 @@ extern struct psil_ep_map j721s2_ep_map;
 extern struct psil_ep_map am62_ep_map;
 extern struct psil_ep_map am62a_ep_map;
 extern struct psil_ep_map j784s4_ep_map;
+extern struct psil_ep_map am62p_ep_map;
 
 #endif /* K3_PSIL_PRIV_H_ */
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
index c11389d67a3f0..25148d9524720 100644
--- a/drivers/dma/ti/k3-psil.c
+++ b/drivers/dma/ti/k3-psil.c
@@ -26,6 +26,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "AM62X", .data = &am62_ep_map },
 	{ .family = "AM62AX", .data = &am62a_ep_map },
 	{ .family = "J784S4", .data = &j784s4_ep_map },
+	{ .family = "AM62PX", .data = &am62p_ep_map },
+	{ .family = "J722S", .data = &am62p_ep_map },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 30fd2f386f36a..2841a539c2648 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4441,6 +4441,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "AM62X", .data = &am64_soc_data },
 	{ .family = "AM62AX", .data = &am64_soc_data },
 	{ .family = "J784S4", .data = &j721e_soc_data },
+	{ .family = "AM62PX", .data = &am64_soc_data },
+	{ .family = "J722S", .data = &am64_soc_data },
 	{ /* sentinel */ }
 };
 
-- 
GitLab


From e271c0ba3f919c48e90c64b703538fbb7865cb63 Mon Sep 17 00:00:00 2001
From: Rex Zhang <rex.zhang@intel.com>
Date: Tue, 12 Dec 2023 10:21:58 +0800
Subject: [PATCH 1778/4076] dmaengine: idxd: Move dma_free_coherent() out of
 spinlocked context

Task may be rescheduled within dma_free_coherent(). So dma_free_coherent()
can't be called between spin_lock() and spin_unlock() to avoid Call Trace:
    Call Trace:
    <TASK>
    dump_stack_lvl+0x37/0x50
    __might_resched+0x16a/0x1c0
    vunmap+0x2c/0x70
    __iommu_dma_free+0x96/0x100
    idxd_device_evl_free+0xd5/0x100 [idxd]
    device_release_driver_internal+0x197/0x200
    unbind_store+0xa1/0xb0
    kernfs_fop_write_iter+0x120/0x1c0
    vfs_write+0x2d3/0x400
    ksys_write+0x63/0xe0
    do_syscall_64+0x44/0xa0
    entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Move it out of the context.

Fixes: 244da66cda35 ("dmaengine: idxd: setup event log configuration")
Signed-off-by: Rex Zhang <rex.zhang@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>
Link: https://lore.kernel.org/r/20231212022158.358619-2-rex.zhang@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/device.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 8f754f922217d..fa0f880beae64 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -802,6 +802,9 @@ err_bmap:
 
 static void idxd_device_evl_free(struct idxd_device *idxd)
 {
+	void *evl_log;
+	unsigned int evl_log_size;
+	dma_addr_t evl_dma;
 	union gencfg_reg gencfg;
 	union genctrl_reg genctrl;
 	struct device *dev = &idxd->pdev->dev;
@@ -822,11 +825,15 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET);
 	iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET + 8);
 
-	dma_free_coherent(dev, evl->log_size, evl->log, evl->dma);
 	bitmap_free(evl->bmap);
+	evl_log = evl->log;
+	evl_log_size = evl->log_size;
+	evl_dma = evl->dma;
 	evl->log = NULL;
 	evl->size = IDXD_EVL_SIZE_MIN;
 	spin_unlock(&evl->lock);
+
+	dma_free_coherent(dev, evl_log_size, evl_log, evl_dma);
 }
 
 static void idxd_group_config_write(struct idxd_group *group)
-- 
GitLab


From 26ee018ff6d1c326ac9b9be36513e35870ed09db Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 30 Nov 2023 12:13:12 +0100
Subject: [PATCH 1779/4076] dmaengine: xilinx: xdma: Fix the count of elapsed
 periods in cyclic mode

Xilinx DMA engine is capable of keeping track of the number of elapsed
periods and this is an increasing 32-bit counter which is only reset
when turning off the engine. No need to add this value to our local
counter.

Fixes: cd8c732ce1a5 ("dmaengine: xilinx: xdma: Support cyclic transfers")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231130111315.729430-2-miquel.raynal@bootlin.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 84a88029226fd..2c9c72d4b5a20 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -754,9 +754,9 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	if (ret)
 		goto out;
 
-	desc->completed_desc_num += complete_desc_num;
-
 	if (desc->cyclic) {
+		desc->completed_desc_num = complete_desc_num;
+
 		ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS,
 				  &st);
 		if (ret)
@@ -768,6 +768,8 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 		goto out;
 	}
 
+	desc->completed_desc_num += complete_desc_num;
+
 	/*
 	 * if all data blocks are transferred, remove and complete the request
 	 */
-- 
GitLab


From 58b61fc75ba901b1fd63c911b31249f36d17e9c4 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 30 Nov 2023 12:13:13 +0100
Subject: [PATCH 1780/4076] dmaengine: xilinx: xdma: Clarify the logic between
 cyclic/sg modes

We support both modes, but they perform totally different taks in the
interrupt handler. Clarify what shall be done in each case.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231130111315.729430-3-miquel.raynal@bootlin.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 31 ++++++++++++++-----------------
 1 file changed, 14 insertions(+), 17 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 2c9c72d4b5a20..4efef1b5f89c4 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -765,26 +765,23 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 		regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_STATUS, st);
 
 		vchan_cyclic_callback(vd);
-		goto out;
-	}
-
-	desc->completed_desc_num += complete_desc_num;
+	} else {
+		desc->completed_desc_num += complete_desc_num;
 
-	/*
-	 * if all data blocks are transferred, remove and complete the request
-	 */
-	if (desc->completed_desc_num == desc->desc_num) {
-		list_del(&vd->node);
-		vchan_cookie_complete(vd);
-		goto out;
-	}
+		/* if all data blocks are transferred, remove and complete the request */
+		if (desc->completed_desc_num == desc->desc_num) {
+			list_del(&vd->node);
+			vchan_cookie_complete(vd);
+			goto out;
+		}
 
-	if (desc->completed_desc_num > desc->desc_num ||
-	    complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
-		goto out;
+		if (desc->completed_desc_num > desc->desc_num ||
+		    complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
+			goto out;
 
-	/* transfer the rest of data (SG only) */
-	xdma_xfer_start(xchan);
+		/* transfer the rest of data */
+		xdma_xfer_start(xchan);
+	}
 
 out:
 	spin_unlock(&xchan->vchan.lock);
-- 
GitLab


From b3072be7f955e56789a0508c18e9870f45cd9a11 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 30 Nov 2023 12:13:14 +0100
Subject: [PATCH 1781/4076] dmaengine: xilinx: xdma: Better handling of the
 busy variable

The driver internal scatter-gather logic is:
* set busy to true
* start transfer
<irq>
  * set busy to false
  * trigger next transfer if any
    * set busy to true
</irq>

Setting busy to false in cyclic transfers does not make any sense and is
conceptually wrong. In order to ease the integration of additional
callbacks let's move this change to the scatter-gather path.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231130111315.729430-4-miquel.raynal@bootlin.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 4efef1b5f89c4..e931ff42209cd 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -745,7 +745,6 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	if (!vd)
 		goto out;
 
-	xchan->busy = false;
 	desc = to_xdma_desc(vd);
 	xdev = xchan->xdev_hdl;
 
@@ -766,6 +765,7 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 
 		vchan_cyclic_callback(vd);
 	} else {
+		xchan->busy = false;
 		desc->completed_desc_num += complete_desc_num;
 
 		/* if all data blocks are transferred, remove and complete the request */
-- 
GitLab


From f5c392d106e7cc58c7705799ef4c36c3b2f60b31 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 30 Nov 2023 12:13:15 +0100
Subject: [PATCH 1782/4076] dmaengine: xilinx: xdma: Add
 terminate_all/synchronize callbacks

The driver is capable of starting scatter-gather transfers and needs to
wait until their end. It is also capable of starting cyclic transfers
and will only be "reset" next time the channel will be reused. In
practice most of the time we hear no audio glitch because the sound card
stops the flow on its side so the DMA transfers are just
discarded. There are however some cases (when playing a bit with a
number of frames and with a discontinuous sound file) when the sound
card seems to be slightly too slow at stopping the flow, leading to a
glitch that can be heard.

In all cases, we need to earn better control of the DMA engine and
adding proper ->device_terminate_all() and ->device_synchronize()
callbacks feels totally relevant. With these two callbacks, no glitch
can be heard anymore.

Fixes: cd8c732ce1a5 ("dmaengine: xilinx: xdma: Support cyclic transfers")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Tested-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://lore.kernel.org/r/20231130111315.729430-5-miquel.raynal@bootlin.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 68 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index e931ff42209cd..290bb5d2d1e2b 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -371,6 +371,31 @@ static int xdma_xfer_start(struct xdma_chan *xchan)
 		return ret;
 
 	xchan->busy = true;
+
+	return 0;
+}
+
+/**
+ * xdma_xfer_stop - Stop DMA transfer
+ * @xchan: DMA channel pointer
+ */
+static int xdma_xfer_stop(struct xdma_chan *xchan)
+{
+	struct virt_dma_desc *vd = vchan_next_desc(&xchan->vchan);
+	struct xdma_device *xdev = xchan->xdev_hdl;
+	int ret;
+
+	if (!vd || !xchan->busy)
+		return -EINVAL;
+
+	/* clear run stop bit to prevent any further auto-triggering */
+	ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
+			   CHAN_CTRL_RUN_STOP);
+	if (ret)
+		return ret;
+
+	xchan->busy = false;
+
 	return 0;
 }
 
@@ -475,6 +500,47 @@ static void xdma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
 }
 
+/**
+ * xdma_terminate_all - Terminate all transactions
+ * @chan: DMA channel pointer
+ */
+static int xdma_terminate_all(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct xdma_desc *desc = NULL;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
+	xdma_xfer_stop(xdma_chan);
+
+	vd = vchan_next_desc(&xdma_chan->vchan);
+	if (vd)
+		desc = to_xdma_desc(vd);
+	if (desc) {
+		dma_cookie_complete(&desc->vdesc.tx);
+		vchan_terminate_vdesc(&desc->vdesc);
+	}
+
+	vchan_get_all_descriptors(&xdma_chan->vchan, &head);
+	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&xdma_chan->vchan, &head);
+
+	return 0;
+}
+
+/**
+ * xdma_synchronize - Synchronize terminated transactions
+ * @chan: DMA channel pointer
+ */
+static void xdma_synchronize(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+
+	vchan_synchronize(&xdma_chan->vchan);
+}
+
 /**
  * xdma_prep_device_sg - prepare a descriptor for a DMA transaction
  * @chan: DMA channel pointer
@@ -1088,6 +1154,8 @@ static int xdma_probe(struct platform_device *pdev)
 	xdev->dma_dev.device_prep_slave_sg = xdma_prep_device_sg;
 	xdev->dma_dev.device_config = xdma_device_config;
 	xdev->dma_dev.device_issue_pending = xdma_issue_pending;
+	xdev->dma_dev.device_terminate_all = xdma_terminate_all;
+	xdev->dma_dev.device_synchronize = xdma_synchronize;
 	xdev->dma_dev.filter.map = pdata->device_map;
 	xdev->dma_dev.filter.mapcnt = pdata->device_map_cnt;
 	xdev->dma_dev.filter.fn = xdma_filter_fn;
-- 
GitLab


From 6e2387183312cdfce6326b2626c0b801c2ffe686 Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Mon, 18 Dec 2023 12:39:36 +0100
Subject: [PATCH 1783/4076] dmaengine: xilinx: xdma: Get rid of unused code

Get rid of duplicated macro definitions, as these macros are defined
earlier in the file. Also, get rid of unused member
of 'struct xdma_desc'.

Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Link: https://lore.kernel.org/r/20231218113943.9099-2-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma-regs.h | 12 ------------
 drivers/dma/xilinx/xdma.c      |  2 --
 2 files changed, 14 deletions(-)

diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h
index e641a5083e14b..0b17a931f5830 100644
--- a/drivers/dma/xilinx/xdma-regs.h
+++ b/drivers/dma/xilinx/xdma-regs.h
@@ -134,18 +134,6 @@ struct xdma_hw_desc {
 #define XDMA_SGDMA_DESC_ADJ	0x4088
 #define XDMA_SGDMA_DESC_CREDIT	0x408c
 
-/* bits of the SG DMA control register */
-#define XDMA_CTRL_RUN_STOP			BIT(0)
-#define XDMA_CTRL_IE_DESC_STOPPED		BIT(1)
-#define XDMA_CTRL_IE_DESC_COMPLETED		BIT(2)
-#define XDMA_CTRL_IE_DESC_ALIGN_MISMATCH	BIT(3)
-#define XDMA_CTRL_IE_MAGIC_STOPPED		BIT(4)
-#define XDMA_CTRL_IE_IDLE_STOPPED		BIT(6)
-#define XDMA_CTRL_IE_READ_ERROR			GENMASK(13, 9)
-#define XDMA_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
-#define XDMA_CTRL_NON_INCR_ADDR			BIT(25)
-#define XDMA_CTRL_POLL_MODE_WB			BIT(26)
-
 /*
  * interrupt registers
  */
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 290bb5d2d1e2b..ddb9e7d074616 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -78,7 +78,6 @@ struct xdma_chan {
  * @vdesc: Virtual DMA descriptor
  * @chan: DMA channel pointer
  * @dir: Transferring direction of the request
- * @dev_addr: Physical address on DMA device side
  * @desc_blocks: Hardware descriptor blocks
  * @dblk_num: Number of hardware descriptor blocks
  * @desc_num: Number of hardware descriptors
@@ -91,7 +90,6 @@ struct xdma_desc {
 	struct virt_dma_desc		vdesc;
 	struct xdma_chan		*chan;
 	enum dma_transfer_direction	dir;
-	u64				dev_addr;
 	struct xdma_desc_block		*desc_blocks;
 	u32				dblk_num;
 	u32				desc_num;
-- 
GitLab


From 7a9c7f46bd0abea214d96f00f78622f24c798ad8 Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Mon, 18 Dec 2023 12:39:37 +0100
Subject: [PATCH 1784/4076] dmaengine: xilinx: xdma: Add necessary macro
 definitions

Complete lacking bits describing the status/control register values.
Add macros describing the status/control registers.

Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Link: https://lore.kernel.org/r/20231218113943.9099-3-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma-regs.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h
index 0b17a931f5830..98117e8a466fa 100644
--- a/drivers/dma/xilinx/xdma-regs.h
+++ b/drivers/dma/xilinx/xdma-regs.h
@@ -76,6 +76,7 @@ struct xdma_hw_desc {
 #define XDMA_CHAN_CONTROL_W1S		0x8
 #define XDMA_CHAN_CONTROL_W1C		0xc
 #define XDMA_CHAN_STATUS		0x40
+#define XDMA_CHAN_STATUS_RC		0x44
 #define XDMA_CHAN_COMPLETED_DESC	0x48
 #define XDMA_CHAN_ALIGNMENTS		0x4c
 #define XDMA_CHAN_INTR_ENABLE		0x90
@@ -101,6 +102,7 @@ struct xdma_hw_desc {
 #define CHAN_CTRL_IE_MAGIC_STOPPED		BIT(4)
 #define CHAN_CTRL_IE_IDLE_STOPPED		BIT(6)
 #define CHAN_CTRL_IE_READ_ERROR			GENMASK(13, 9)
+#define CHAN_CTRL_IE_WRITE_ERROR		GENMASK(18, 14)
 #define CHAN_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
 #define CHAN_CTRL_NON_INCR_ADDR			BIT(25)
 #define CHAN_CTRL_POLL_MODE_WB			BIT(26)
@@ -111,8 +113,17 @@ struct xdma_hw_desc {
 			 CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |		\
 			 CHAN_CTRL_IE_MAGIC_STOPPED |			\
 			 CHAN_CTRL_IE_READ_ERROR |			\
+			 CHAN_CTRL_IE_WRITE_ERROR |			\
 			 CHAN_CTRL_IE_DESC_ERROR)
 
+#define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START
+
+#define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |	\
+			      CHAN_CTRL_IE_MAGIC_STOPPED |		\
+			      CHAN_CTRL_IE_READ_ERROR |			\
+			      CHAN_CTRL_IE_WRITE_ERROR |		\
+			      CHAN_CTRL_IE_DESC_ERROR)
+
 /* bits of the channel interrupt enable mask */
 #define CHAN_IM_DESC_ERROR			BIT(19)
 #define CHAN_IM_READ_ERROR			BIT(9)
-- 
GitLab


From e5bc76b0e1c54906ca744ed1a7872f4f407d5d2e Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Mon, 18 Dec 2023 12:39:38 +0100
Subject: [PATCH 1785/4076] dmaengine: xilinx: xdma: Ease dma_pool alignment
 requirements

According to the XDMA datasheet (PG195), the address of any descriptor
must be 32 byte aligned. The datasheet also states that a contiguous
block of descriptors must not cross a 4k address boundary. Therefore,
it is possible to ease the pressure put on the dma_pool allocator
just by requiring sufficient alignment and boundary values. Add proper
macro definition and change the values passed into the
dma_pool_create().

Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Link: https://lore.kernel.org/r/20231218113943.9099-4-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma-regs.h | 7 ++++---
 drivers/dma/xilinx/xdma.c      | 5 ++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h
index 98117e8a466fa..98f5f6fb9ff9c 100644
--- a/drivers/dma/xilinx/xdma-regs.h
+++ b/drivers/dma/xilinx/xdma-regs.h
@@ -64,9 +64,10 @@ struct xdma_hw_desc {
 	__le64		next_desc;
 };
 
-#define XDMA_DESC_SIZE		sizeof(struct xdma_hw_desc)
-#define XDMA_DESC_BLOCK_SIZE	(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
-#define XDMA_DESC_BLOCK_ALIGN	4096
+#define XDMA_DESC_SIZE			sizeof(struct xdma_hw_desc)
+#define XDMA_DESC_BLOCK_SIZE		(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
+#define XDMA_DESC_BLOCK_ALIGN		32
+#define XDMA_DESC_BLOCK_BOUNDARY	4096
 
 /*
  * Channel registers
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index ddb9e7d074616..c22701e76b693 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -741,9 +741,8 @@ static int xdma_alloc_chan_resources(struct dma_chan *chan)
 		return -EINVAL;
 	}
 
-	xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan),
-					       dev, XDMA_DESC_BLOCK_SIZE,
-					       XDMA_DESC_BLOCK_ALIGN, 0);
+	xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan), dev, XDMA_DESC_BLOCK_SIZE,
+					       XDMA_DESC_BLOCK_ALIGN, XDMA_DESC_BLOCK_BOUNDARY);
 	if (!xdma_chan->desc_pool) {
 		xdma_err(xdev, "unable to allocate descriptor pool");
 		return -ENOMEM;
-- 
GitLab


From 4289e434c46c8cbd32cf8b67fa7689b3d2ca4361 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 17 Dec 2023 19:46:42 +0100
Subject: [PATCH 1786/4076] leds: trigger: netdev: Add core support for hw not
 supporting fallback to LED sw control

If hw doesn't support sw control of the LED and we switch to a mode
not supported by hw, currently we get lots of errors because neither
brigthness_set() nor brithness_set_blocking() is set.
Deal with this by not falling back to sw control, and return
-EOPNOTSUPP to the user. Note that we still store the new mode.
This is needed in case an intermediate unsupported mode is necessary
to switch from one supported mode to another.

Add a comment explaining how a driver for such hw is supposed to behave.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/3fd5184c-3641-4b0b-b59a-f489ec69a6cd@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-netdev.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index bd68da15c723e..836610292b37d 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -38,6 +38,16 @@
  * tx -  LED blinks on transmitted data
  * rx -  LED blinks on receive data
  *
+ * Note: If the user selects a mode that is not supported by hw, default
+ * behavior is to fall back to software control of the LED. However not every
+ * hw supports software control. LED callbacks brightness_set() and
+ * brightness_set_blocking() are NULL in this case. hw_control_is_supported()
+ * should use available means supported by hw to inform the user that selected
+ * mode isn't supported by hw. This could be switching off the LED or any
+ * hw blink mode. If software control fallback isn't possible, we return
+ * -EOPNOTSUPP to the user, but still store the selected mode. This is needed
+ * in case an intermediate unsupported mode is necessary to switch from one
+ * supported mode to another.
  */
 
 struct led_netdev_data {
@@ -318,6 +328,7 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 				     size_t size, enum led_trigger_netdev_modes attr)
 {
 	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+	struct led_classdev *led_cdev = trigger_data->led_cdev;
 	unsigned long state, mode = trigger_data->mode;
 	int ret;
 	int bit;
@@ -363,6 +374,10 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	trigger_data->mode = mode;
 	trigger_data->hw_control = can_hw_control(trigger_data);
 
+	if (!led_cdev->brightness_set && !led_cdev->brightness_set_blocking &&
+	    !trigger_data->hw_control)
+		return -EOPNOTSUPP;
+
 	set_baseline_state(trigger_data);
 
 	return size;
-- 
GitLab


From 6b626eee66a88b671585c1804667a4fb10a434ef Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Wed, 20 Dec 2023 20:49:52 +0530
Subject: [PATCH 1787/4076] dt-bindings: iio: dac: add MCP4821

Adds support for MCP48xx series of DACs.

Datasheet: https://ww1.microchip.com/downloads/en/DeviceDoc/22244B.pdf #MCP48x1
Datasheet: https://ww1.microchip.com/downloads/en/DeviceDoc/20002249B.pdf #MCP48x2
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20231220151954.154595-1-anshulusr@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/dac/microchip,mcp4821.yaml   | 86 +++++++++++++++++++
 1 file changed, 86 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml

diff --git a/Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml b/Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml
new file mode 100644
index 0000000000000..0dc577c339181
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml
@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/dac/microchip,mcp4821.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip MCP4821 and similar DACs
+
+description: |
+  Supports MCP48x1 (single channel) and MCP48x2 (dual channel) series of DACs.
+  Device supports simplex communication over SPI in Mode 0 and Mode 3.
+
+  +---------+--------------+-------------+
+  | Device  |  Resolution  |   Channels  |
+  |---------|--------------|-------------|
+  | MCP4801 |     8-bit    |      1      |
+  | MCP4802 |     8-bit    |      2      |
+  | MCP4811 |    10-bit    |      1      |
+  | MCP4812 |    10-bit    |      2      |
+  | MCP4821 |    12-bit    |      1      |
+  | MCP4822 |    12-bit    |      2      |
+  +---------+--------------+-------------+
+
+  Datasheet:
+    MCP48x1: https://ww1.microchip.com/downloads/en/DeviceDoc/22244B.pdf
+    MCP48x2: https://ww1.microchip.com/downloads/en/DeviceDoc/20002249B.pdf
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+properties:
+  compatible:
+    enum:
+      - microchip,mcp4801
+      - microchip,mcp4802
+      - microchip,mcp4811
+      - microchip,mcp4812
+      - microchip,mcp4821
+      - microchip,mcp4822
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+
+  ldac-gpios:
+    description: |
+      Active Low LDAC (Latch DAC Input) pin used to update the DAC output.
+    maxItems: 1
+
+  powerdown-gpios:
+    description: |
+      Active Low SHDN pin used to enter the shutdown mode.
+    maxItems: 1
+
+  spi-cpha: true
+  spi-cpol: true
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        dac@0 {
+            compatible = "microchip,mcp4821";
+            reg = <0>;
+            vdd-supply = <&vdd_regulator>;
+            ldac-gpios = <&gpio0 1 GPIO_ACTIVE_HIGH>;
+            powerdown-gpios = <&gpio0 2 GPIO_ACTIVE_HIGH>;
+            spi-cpha;
+            spi-cpol;
+        };
+    };
-- 
GitLab


From cdf3ecb0d8d0a83c940a8892b3e8aeaf35dc4353 Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Wed, 20 Dec 2023 20:49:53 +0530
Subject: [PATCH 1788/4076] iio: dac: driver for MCP4821

Adds driver for the MCP48xx series of DACs.

Device uses a simplex SPI channel. To set the value of an output channel,
a 16-bit data of following format must be written:

Bit field | Description
15 [MSB]  | Channel selection bit
            0 -> Channel A
            1 -> Channel B
13        | Output Gain Selection bit
            0 -> 2x Gain (Vref = 4.096V)
            1 -> 1x Gain (Vref = 2.048V)
12        | Output Shutdown Control bit
            0 -> Shutdown the selected channel
            1 -> Active mode operation
11-0 [LSB]| DAC Input Data bits
            Value's big endian representation is taken as input for the
            selected DAC channel. For devices with a resolution of less
            than 12-bits, only the x most significant bits are considered
            where x is the resolution of the device.
Reference: Page#22 [MCP48x2 Datasheet]

Supported devices:
  +---------+--------------+-------------+
  | Device  |  Resolution  |   Channels  |
  |---------|--------------|-------------|
  | MCP4801 |     8-bit    |      1      |
  | MCP4802 |     8-bit    |      2      |
  | MCP4811 |    10-bit    |      1      |
  | MCP4812 |    10-bit    |      2      |
  | MCP4821 |    12-bit    |      1      |
  | MCP4822 |    12-bit    |      2      |
  +---------+--------------+-------------+

Devices tested:
  MCP4821 [12-bit single channel]
  MCP4802 [8-bit dual channel]

Tested on Raspberry Pi Zero 2W

Datasheet: https://ww1.microchip.com/downloads/en/DeviceDoc/22244B.pdf #MCP48x1
Datasheet: https://ww1.microchip.com/downloads/en/DeviceDoc/20002249B.pdf #MCP48x2
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20231220151954.154595-2-anshulusr@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS               |   7 ++
 drivers/iio/dac/Kconfig   |  10 ++
 drivers/iio/dac/Makefile  |   1 +
 drivers/iio/dac/mcp4821.c | 236 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 254 insertions(+)
 create mode 100644 drivers/iio/dac/mcp4821.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 066707fddd90f..f61df0128c0b0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13174,6 +13174,13 @@ F:	Documentation/ABI/testing/sysfs-bus-iio-potentiometer-mcp4531
 F:	drivers/iio/potentiometer/mcp4018.c
 F:	drivers/iio/potentiometer/mcp4531.c
 
+MCP4821 DAC DRIVER
+M:	Anshul Dalal <anshulusr@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/dac/microchip,mcp4821.yaml
+F:	drivers/iio/dac/mcp4821.c
+
 MCR20A IEEE-802.15.4 RADIO DRIVER
 M:	Stefan Schmidt <stefan@datenfreihafen.org>
 L:	linux-wpan@vger.kernel.org
diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index 93b8be183de6b..34eb40bb95291 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -400,6 +400,16 @@ config MCP4728
 	  To compile this driver as a module, choose M here: the module
 	  will be called mcp4728.
 
+config MCP4821
+	tristate "MCP4801/02/11/12/21/22 DAC driver"
+	depends on SPI
+	help
+	  Say yes here to build the driver for the Microchip MCP4801
+	  MCP4802, MCP4811, MCP4812, MCP4821 and MCP4822 DAC devices.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called mcp4821.
+
 config MCP4922
 	tristate "MCP4902, MCP4912, MCP4922 DAC driver"
 	depends on SPI
diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile
index 5b2bac900d5a7..55bf89739d14b 100644
--- a/drivers/iio/dac/Makefile
+++ b/drivers/iio/dac/Makefile
@@ -42,6 +42,7 @@ obj-$(CONFIG_MAX5522) += max5522.o
 obj-$(CONFIG_MAX5821) += max5821.o
 obj-$(CONFIG_MCP4725) += mcp4725.o
 obj-$(CONFIG_MCP4728) += mcp4728.o
+obj-$(CONFIG_MCP4821) += mcp4821.o
 obj-$(CONFIG_MCP4922) += mcp4922.o
 obj-$(CONFIG_STM32_DAC_CORE) += stm32-dac-core.o
 obj-$(CONFIG_STM32_DAC) += stm32-dac.o
diff --git a/drivers/iio/dac/mcp4821.c b/drivers/iio/dac/mcp4821.c
new file mode 100644
index 0000000000000..8a0480d338450
--- /dev/null
+++ b/drivers/iio/dac/mcp4821.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com>
+ *
+ * Driver for Microchip MCP4801, MCP4802, MCP4811, MCP4812, MCP4821 and MCP4822
+ *
+ * Based on the work of:
+ *	Michael Welling (MCP4922 Driver)
+ *
+ * Datasheet:
+ *	MCP48x1: https://ww1.microchip.com/downloads/en/DeviceDoc/22244B.pdf
+ *	MCP48x2: https://ww1.microchip.com/downloads/en/DeviceDoc/20002249B.pdf
+ *
+ * TODO:
+ *	- Configurable gain
+ *	- Regulator control
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/types.h>
+
+#include <asm/unaligned.h>
+
+#define MCP4821_ACTIVE_MODE BIT(12)
+#define MCP4802_SECOND_CHAN BIT(15)
+
+/* DAC uses an internal Voltage reference of 4.096V at a gain of 2x */
+#define MCP4821_2X_GAIN_VREF_MV 4096
+
+enum mcp4821_supported_drvice_ids {
+	ID_MCP4801,
+	ID_MCP4802,
+	ID_MCP4811,
+	ID_MCP4812,
+	ID_MCP4821,
+	ID_MCP4822,
+};
+
+struct mcp4821_state {
+	struct spi_device *spi;
+	u16 dac_value[2];
+};
+
+struct mcp4821_chip_info {
+	const char *name;
+	int num_channels;
+	const struct iio_chan_spec channels[2];
+};
+
+#define MCP4821_CHAN(channel_id, resolution)                          \
+	{                                                             \
+		.type = IIO_VOLTAGE, .output = 1, .indexed = 1,       \
+		.channel = (channel_id),                              \
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),         \
+		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \
+		.scan_type = {                                        \
+			.realbits = (resolution),                     \
+			.shift = 12 - (resolution),                   \
+		},                                                    \
+	}
+
+static const struct mcp4821_chip_info mcp4821_chip_info_table[6] = {
+	[ID_MCP4801] = {
+			.name = "mcp4801",
+			.num_channels = 1,
+			.channels = {
+				MCP4821_CHAN(0, 8),
+			},
+	},
+	[ID_MCP4802] = {
+			.name = "mcp4802",
+			.num_channels = 2,
+			.channels = {
+				MCP4821_CHAN(0, 8),
+				MCP4821_CHAN(1, 8),
+			},
+	},
+	[ID_MCP4811] = {
+			.name = "mcp4811",
+			.num_channels = 1,
+			.channels = {
+				MCP4821_CHAN(0, 10),
+			},
+	},
+	[ID_MCP4812] = {
+			.name = "mcp4812",
+			.num_channels = 2,
+			.channels = {
+				MCP4821_CHAN(0, 10),
+				MCP4821_CHAN(1, 10),
+			},
+	},
+	[ID_MCP4821] = {
+			.name = "mcp4821",
+			.num_channels = 1,
+			.channels = {
+				MCP4821_CHAN(0, 12),
+			},
+	},
+	[ID_MCP4822] = {
+			.name = "mcp4822",
+			.num_channels = 2,
+			.channels = {
+				MCP4821_CHAN(0, 12),
+				MCP4821_CHAN(1, 12),
+			},
+	},
+};
+
+static int mcp4821_read_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	struct mcp4821_state *state;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		state = iio_priv(indio_dev);
+		*val = state->dac_value[chan->channel];
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		*val = MCP4821_2X_GAIN_VREF_MV;
+		*val2 = chan->scan_type.realbits;
+		return IIO_VAL_FRACTIONAL_LOG2;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mcp4821_write_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan, int val,
+			     int val2, long mask)
+{
+	struct mcp4821_state *state = iio_priv(indio_dev);
+	u16 write_val;
+	__be16 write_buffer;
+	int ret;
+
+	if (val2 != 0)
+		return -EINVAL;
+
+	if (val < 0 || val >= BIT(chan->scan_type.realbits))
+		return -EINVAL;
+
+	if (mask != IIO_CHAN_INFO_RAW)
+		return -EINVAL;
+
+	write_val = MCP4821_ACTIVE_MODE | val << chan->scan_type.shift;
+	if (chan->channel)
+		write_val |= MCP4802_SECOND_CHAN;
+
+	write_buffer = cpu_to_be16(write_val);
+	ret = spi_write(state->spi, &write_buffer, sizeof(write_buffer));
+	if (ret) {
+		dev_err(&state->spi->dev, "Failed to write to device: %d", ret);
+		return ret;
+	}
+
+	state->dac_value[chan->channel] = val;
+
+	return 0;
+}
+
+static const struct iio_info mcp4821_info = {
+	.read_raw = &mcp4821_read_raw,
+	.write_raw = &mcp4821_write_raw,
+};
+
+static int mcp4821_probe(struct spi_device *spi)
+{
+	struct iio_dev *indio_dev;
+	struct mcp4821_state *state;
+	const struct mcp4821_chip_info *info;
+
+	indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*state));
+	if (indio_dev == NULL)
+		return -ENOMEM;
+
+	state = iio_priv(indio_dev);
+	state->spi = spi;
+
+	info = spi_get_device_match_data(spi);
+	indio_dev->name = info->name;
+	indio_dev->info = &mcp4821_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = info->channels;
+	indio_dev->num_channels = info->num_channels;
+
+	return devm_iio_device_register(&spi->dev, indio_dev);
+}
+
+#define MCP4821_COMPATIBLE(of_compatible, id)        \
+	{                                            \
+		.compatible = of_compatible,         \
+		.data = &mcp4821_chip_info_table[id] \
+	}
+
+static const struct of_device_id mcp4821_of_table[] = {
+	MCP4821_COMPATIBLE("microchip,mcp4801", ID_MCP4801),
+	MCP4821_COMPATIBLE("microchip,mcp4802", ID_MCP4802),
+	MCP4821_COMPATIBLE("microchip,mcp4811", ID_MCP4811),
+	MCP4821_COMPATIBLE("microchip,mcp4812", ID_MCP4812),
+	MCP4821_COMPATIBLE("microchip,mcp4821", ID_MCP4821),
+	MCP4821_COMPATIBLE("microchip,mcp4822", ID_MCP4822),
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, mcp4821_of_table);
+
+static const struct spi_device_id mcp4821_id_table[] = {
+	{ "mcp4801", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4801]},
+	{ "mcp4802", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4802]},
+	{ "mcp4811", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4811]},
+	{ "mcp4812", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4812]},
+	{ "mcp4821", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4821]},
+	{ "mcp4822", (kernel_ulong_t)&mcp4821_chip_info_table[ID_MCP4822]},
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(spi, mcp4821_id_table);
+
+static struct spi_driver mcp4821_driver = {
+	.driver = {
+		.name = "mcp4821",
+		.of_match_table = mcp4821_of_table,
+	},
+	.probe = mcp4821_probe,
+	.id_table = mcp4821_id_table,
+};
+module_spi_driver(mcp4821_driver);
+
+MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>");
+MODULE_DESCRIPTION("Microchip MCP4821 DAC Driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 2226ec072ed3f1bd3f8dbe0cbf0e6cad699aedc2 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:19:10 +0200
Subject: [PATCH 1789/4076] phy: qcom-qmp: qserdes-com: Add some more v6
 register offsets

Add some missing V6 registers offsets that are needed by the new
Snapdragon X Elite (X1E80100) platform.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-v6-v6-20-v7-new-offsets-v3-1-dfd1c375ef61@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h  | 5 +++++
 drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h
index f420f8faf16a7..ec7291424dd1f 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v6.h
@@ -22,6 +22,8 @@
 #define QSERDES_V6_COM_DIV_FRAC_START2_MODE1			0x34
 #define QSERDES_V6_COM_DIV_FRAC_START3_MODE1			0x38
 #define QSERDES_V6_COM_HSCLK_SEL_1				0x3c
+#define QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1			0x40
+#define QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE1			0x44
 #define QSERDES_V6_COM_VCO_TUNE1_MODE1				0x48
 #define QSERDES_V6_COM_VCO_TUNE2_MODE1				0x4c
 #define QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1		0x50
@@ -48,6 +50,7 @@
 #define QSERDES_V6_COM_VCO_TUNE2_MODE0				0xac
 #define QSERDES_V6_COM_BG_TIMER					0xbc
 #define QSERDES_V6_COM_SSC_EN_CENTER				0xc0
+#define QSERDES_V6_COM_SSC_ADJ_PER1				0xc4
 #define QSERDES_V6_COM_SSC_PER1					0xcc
 #define QSERDES_V6_COM_SSC_PER2					0xd0
 #define QSERDES_V6_COM_PLL_POST_DIV_MUX				0xd8
@@ -56,6 +59,7 @@
 #define QSERDES_V6_COM_SYS_CLK_CTRL				0xe4
 #define QSERDES_V6_COM_SYSCLK_BUF_ENABLE			0xe8
 #define QSERDES_V6_COM_PLL_IVCO					0xf4
+#define QSERDES_V6_COM_PLL_IVCO_MODE1				0xf8
 #define QSERDES_V6_COM_SYSCLK_EN_SEL				0x110
 #define QSERDES_V6_COM_RESETSM_CNTRL				0x118
 #define QSERDES_V6_COM_LOCK_CMP_EN				0x120
@@ -63,6 +67,7 @@
 #define QSERDES_V6_COM_VCO_TUNE_CTRL				0x13c
 #define QSERDES_V6_COM_VCO_TUNE_MAP				0x140
 #define QSERDES_V6_COM_VCO_TUNE_INITVAL2			0x148
+#define QSERDES_V6_COM_VCO_TUNE_MAXVAL2				0x158
 #define QSERDES_V6_COM_CLK_SELECT				0x164
 #define QSERDES_V6_COM_CORE_CLK_EN				0x170
 #define QSERDES_V6_COM_CMN_CONFIG_1				0x174
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
index 8883e1de730ef..23ffcfae9efab 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
@@ -23,6 +23,7 @@
 #define QSERDES_V6_TX_PARRATE_REC_DETECT_IDLE_EN		0x60
 #define QSERDES_V6_TX_BIST_PATTERN7				0x7c
 #define QSERDES_V6_TX_LANE_MODE_1				0x84
+#define QSERDES_V6_TX_LANE_MODE_2				0x88
 #define QSERDES_V6_TX_LANE_MODE_3				0x8c
 #define QSERDES_V6_TX_LANE_MODE_4				0x90
 #define QSERDES_V6_TX_LANE_MODE_5				0x94
-- 
GitLab


From a40542507b9045da03f4e013ab8562f6e6fe8aad Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:19:11 +0200
Subject: [PATCH 1790/4076] phy: qcom-qmp: qserdes-txrx: Add some more v6.20
 register offsets

Add some missing v6.20 registers offsets that are needed by the new
Snapdragon X Elite (X1E80100) platform.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-v6-v6-20-v7-new-offsets-v3-2-dfd1c375ef61@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h
index 5385a8b609707..6ed5339fd2ea8 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_20.h
@@ -15,10 +15,13 @@
 
 #define QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_2			0x08
 #define QSERDES_V6_20_RX_UCDR_FO_GAIN_RATE_3			0x0c
+#define QSERDES_V6_20_RX_UCDR_SO_GAIN_RATE_2			0x18
 #define QSERDES_V6_20_RX_UCDR_PI_CONTROLS			0x20
 #define QSERDES_V6_20_RX_UCDR_SO_ACC_DEFAULT_VAL_RATE3		0x34
 #define QSERDES_V6_20_RX_IVCM_CAL_CTRL2				0x9c
 #define QSERDES_V6_20_RX_IVCM_POSTCAL_OFFSET			0xa0
+#define QSERDES_V6_20_RX_DFE_1					0xac
+#define QSERDES_V6_20_RX_DFE_2					0xb0
 #define QSERDES_V6_20_RX_DFE_3					0xb4
 #define QSERDES_V6_20_RX_VGA_CAL_MAN_VAL			0xe8
 #define QSERDES_V6_20_RX_GM_CAL					0x10c
@@ -41,5 +44,6 @@
 #define QSERDES_V6_20_RX_MODE_RATE3_B4				0x220
 #define QSERDES_V6_20_RX_MODE_RATE3_B5				0x224
 #define QSERDES_V6_20_RX_MODE_RATE3_B6				0x228
+#define QSERDES_V6_20_RX_BKUP_CTRL1				0x22c
 
 #endif
-- 
GitLab


From 7b98cf0e9b5f8a05a7f0f0d06d3cfa130bb576e2 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:19:12 +0200
Subject: [PATCH 1791/4076] phy: qcom-qmp: pcs: Add v7 register offsets

The X1E80100 platform bumps the HW version of QMP phy to v7 for USB,
and PCIe. Add the new PCS offsets in a dedicated header file.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-v6-v6-20-v7-new-offsets-v3-3-dfd1c375ef61@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h | 32 ++++++++++++++++++++++
 drivers/phy/qualcomm/phy-qcom-qmp.h        |  2 ++
 2 files changed, 34 insertions(+)
 create mode 100644 drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h
new file mode 100644
index 0000000000000..c7759892ed2ea
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v7.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_PCS_V7_H_
+#define QCOM_PHY_QMP_PCS_V7_H_
+
+/* Only for QMP V7 PHY - USB/PCIe PCS registers */
+#define QPHY_V7_PCS_SW_RESET			0x000
+#define QPHY_V7_PCS_PCS_STATUS1			0x014
+#define QPHY_V7_PCS_POWER_DOWN_CONTROL		0x040
+#define QPHY_V7_PCS_START_CONTROL		0x044
+#define QPHY_V7_PCS_POWER_STATE_CONFIG1		0x090
+#define QPHY_V7_PCS_LOCK_DETECT_CONFIG1		0x0c4
+#define QPHY_V7_PCS_LOCK_DETECT_CONFIG2		0x0c8
+#define QPHY_V7_PCS_LOCK_DETECT_CONFIG3		0x0cc
+#define QPHY_V7_PCS_LOCK_DETECT_CONFIG6		0x0d8
+#define QPHY_V7_PCS_REFGEN_REQ_CONFIG1		0x0dc
+#define QPHY_V7_PCS_RX_SIGDET_LVL		0x188
+#define QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_L	0x190
+#define QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_H	0x194
+#define QPHY_V7_PCS_RATE_SLEW_CNTRL1		0x198
+#define QPHY_V7_PCS_CDR_RESET_TIME		0x1b0
+#define QPHY_V7_PCS_ALIGN_DETECT_CONFIG1	0x1c0
+#define QPHY_V7_PCS_ALIGN_DETECT_CONFIG2	0x1c4
+#define QPHY_V7_PCS_PCS_TX_RX_CONFIG		0x1d0
+#define QPHY_V7_PCS_EQ_CONFIG1			0x1dc
+#define QPHY_V7_PCS_EQ_CONFIG2			0x1e0
+#define QPHY_V7_PCS_EQ_CONFIG5			0x1ec
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index 71f063f4a56e3..21f6a56e7ae37 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -44,6 +44,8 @@
 
 #include "phy-qcom-qmp-pcs-v6_20.h"
 
+#include "phy-qcom-qmp-pcs-v7.h"
+
 /* Only for QMP V3 & V4 PHY - DP COM registers */
 #define QPHY_V3_DP_COM_PHY_MODE_CTRL			0x00
 #define QPHY_V3_DP_COM_SW_RESET				0x04
-- 
GitLab


From 8d4f9f801095b120e433d935b296baf0e3bdc6a0 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:19:13 +0200
Subject: [PATCH 1792/4076] phy: qcom-qmp: pcs-usb: Add v7 register offsets

The X1E80100 platform bumps the HW version of QMP phy to v7 for USB.
Add the new PCS USB specific offsets in a dedicated header file.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-v6-v6-20-v7-new-offsets-v3-4-dfd1c375ef61@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h
new file mode 100644
index 0000000000000..24368d45ae764
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v7.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_PCS_USB_V7_H_
+#define QCOM_PHY_QMP_PCS_USB_V7_H_
+
+#define QPHY_V7_PCS_USB3_POWER_STATE_CONFIG1		0x00
+#define QPHY_V7_PCS_USB3_AUTONOMOUS_MODE_CTRL		0x08
+#define QPHY_V7_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR		0x14
+#define QPHY_V7_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL	0x18
+#define QPHY_V7_PCS_USB3_RXEQTRAINING_DFE_TIME_S2	0x3c
+#define QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_L		0x40
+#define QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_H		0x44
+
+#endif
-- 
GitLab


From bc546cc85c1d92d9ba7b278b77016b7d4334fafa Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:19:14 +0200
Subject: [PATCH 1793/4076] phy: qcom-qmp: qserdes-com: Add v7 register offsets

The X1E80100 platform bumps the HW version of QMP phy to v7 for USB
and PCIE g3x2. Add the new qserdes com offsets in a dedicated
header file.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-v6-v6-20-v7-new-offsets-v3-5-dfd1c375ef61@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../qualcomm/phy-qcom-qmp-qserdes-com-v7.h    | 87 +++++++++++++++++++
 drivers/phy/qualcomm/phy-qcom-qmp.h           |  2 +
 2 files changed, 89 insertions(+)
 create mode 100644 drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h
new file mode 100644
index 0000000000000..7430f49214779
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-com-v7.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_QSERDES_COM_V7_H_
+#define QCOM_PHY_QMP_QSERDES_COM_V7_H_
+
+/* Only for QMP V7 PHY - QSERDES COM registers */
+
+#define QSERDES_V7_COM_SSC_STEP_SIZE1_MODE1			0x00
+#define QSERDES_V7_COM_SSC_STEP_SIZE2_MODE1			0x04
+#define QSERDES_V7_COM_CP_CTRL_MODE1				0x10
+#define QSERDES_V7_COM_PLL_RCTRL_MODE1				0x14
+#define QSERDES_V7_COM_PLL_CCTRL_MODE1				0x18
+#define QSERDES_V7_COM_CORECLK_DIV_MODE1			0x1c
+#define QSERDES_V7_COM_LOCK_CMP1_MODE1				0x20
+#define QSERDES_V7_COM_LOCK_CMP2_MODE1				0x24
+#define QSERDES_V7_COM_DEC_START_MODE1				0x28
+#define QSERDES_V7_COM_DEC_START_MSB_MODE1			0x2c
+#define QSERDES_V7_COM_DIV_FRAC_START1_MODE1			0x30
+#define QSERDES_V7_COM_DIV_FRAC_START2_MODE1			0x34
+#define QSERDES_V7_COM_DIV_FRAC_START3_MODE1			0x38
+#define QSERDES_V7_COM_HSCLK_SEL_1				0x3c
+#define QSERDES_V7_COM_INTEGLOOP_GAIN0_MODE1			0x40
+#define QSERDES_V7_COM_INTEGLOOP_GAIN1_MODE1			0x44
+#define QSERDES_V7_COM_VCO_TUNE1_MODE1				0x48
+#define QSERDES_V7_COM_VCO_TUNE2_MODE1				0x4c
+#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE1		0x50
+#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE1		0x54
+#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE0		0x58
+#define QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE0		0x5c
+#define QSERDES_V7_COM_SSC_STEP_SIZE1_MODE0			0x60
+#define QSERDES_V7_COM_SSC_STEP_SIZE2_MODE0			0x64
+#define QSERDES_V7_COM_CP_CTRL_MODE0				0x70
+#define QSERDES_V7_COM_PLL_RCTRL_MODE0				0x74
+#define QSERDES_V7_COM_PLL_CCTRL_MODE0				0x78
+#define QSERDES_V7_COM_PLL_CORE_CLK_DIV_MODE0			0x7c
+#define QSERDES_V7_COM_LOCK_CMP1_MODE0				0x80
+#define QSERDES_V7_COM_LOCK_CMP2_MODE0				0x84
+#define QSERDES_V7_COM_DEC_START_MODE0				0x88
+#define QSERDES_V7_COM_DEC_START_MSB_MODE0			0x8c
+#define QSERDES_V7_COM_DIV_FRAC_START1_MODE0			0x90
+#define QSERDES_V7_COM_DIV_FRAC_START2_MODE0			0x94
+#define QSERDES_V7_COM_DIV_FRAC_START3_MODE0			0x98
+#define QSERDES_V7_COM_HSCLK_HS_SWITCH_SEL_1			0x9c
+#define QSERDES_V7_COM_INTEGLOOP_GAIN0_MODE0			0xa0
+#define QSERDES_V7_COM_INTEGLOOP_GAIN1_MODE0			0xa4
+#define QSERDES_V7_COM_VCO_TUNE1_MODE0				0xa8
+#define QSERDES_V7_COM_VCO_TUNE2_MODE0				0xac
+#define QSERDES_V7_COM_BG_TIMER					0xbc
+#define QSERDES_V7_COM_SSC_EN_CENTER				0xc0
+#define QSERDES_V7_COM_SSC_ADJ_PER1				0xc4
+#define QSERDES_V7_COM_SSC_PER1					0xcc
+#define QSERDES_V7_COM_SSC_PER2					0xd0
+#define QSERDES_V7_COM_PLL_POST_DIV_MUX				0xd8
+#define QSERDES_V7_COM_PLL_BIAS_EN_CLK_BUFLR_EN			0xdc
+#define QSERDES_V7_COM_CLK_ENABLE1				0xe0
+#define QSERDES_V7_COM_SYS_CLK_CTRL				0xe4
+#define QSERDES_V7_COM_SYSCLK_BUF_ENABLE			0xe8
+#define QSERDES_V7_COM_PLL_IVCO					0xf4
+#define QSERDES_V7_COM_PLL_IVCO_MODE1				0xf8
+#define QSERDES_V7_COM_SYSCLK_EN_SEL				0x110
+#define QSERDES_V7_COM_RESETSM_CNTRL				0x118
+#define QSERDES_V7_COM_LOCK_CMP_EN				0x120
+#define QSERDES_V7_COM_LOCK_CMP_CFG				0x124
+#define QSERDES_V7_COM_VCO_TUNE_CTRL				0x13c
+#define QSERDES_V7_COM_VCO_TUNE_MAP				0x140
+#define QSERDES_V7_COM_VCO_TUNE_INITVAL2			0x148
+#define QSERDES_V7_COM_VCO_TUNE_MAXVAL2				0x158
+#define QSERDES_V7_COM_CLK_SELECT				0x164
+#define QSERDES_V7_COM_CORE_CLK_EN				0x170
+#define QSERDES_V7_COM_CMN_CONFIG_1				0x174
+#define QSERDES_V7_COM_SVS_MODE_CLK_SEL				0x17c
+#define QSERDES_V7_COM_CMN_MISC_1				0x184
+#define QSERDES_V7_COM_CMN_MODE					0x188
+#define QSERDES_V7_COM_PLL_VCO_DC_LEVEL_CTRL			0x198
+#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_1			0x1a4
+#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_2			0x1a8
+#define QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_3			0x1ac
+#define QSERDES_V7_COM_ADDITIONAL_MISC				0x1b4
+#define QSERDES_V7_COM_ADDITIONAL_MISC_2			0x1b8
+#define QSERDES_V7_COM_ADDITIONAL_MISC_3			0x1bc
+#define QSERDES_V7_COM_CMN_STATUS				0x1d0
+#define QSERDES_V7_COM_C_READY_STATUS				0x1f8
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index 21f6a56e7ae37..3a0512c3e07ab 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -26,6 +26,8 @@
 #include "phy-qcom-qmp-qserdes-txrx-v6_20.h"
 #include "phy-qcom-qmp-qserdes-ln-shrd-v6.h"
 
+#include "phy-qcom-qmp-qserdes-com-v7.h"
+
 #include "phy-qcom-qmp-qserdes-pll.h"
 
 #include "phy-qcom-qmp-pcs-v2.h"
-- 
GitLab


From 762c3565f3c8105603089eeaa0501e5089922221 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:19:15 +0200
Subject: [PATCH 1794/4076] phy: qcom-qmp: qserdes-txrx: Add V6 N4 register
 offsets

There is a variant of V6 offsets that are different, the QMP PHY N4,
and it is found on the X1E80100 platform.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-v6-v6-20-v7-new-offsets-v3-6-dfd1c375ef61@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../phy-qcom-qmp-qserdes-txrx-v6_n4.h         | 51 +++++++++++++++++++
 drivers/phy/qualcomm/phy-qcom-qmp.h           |  1 +
 2 files changed, 52 insertions(+)
 create mode 100644 drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h
new file mode 100644
index 0000000000000..a814ad11af071
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_
+#define QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_
+
+#define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX	0x30
+#define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX	0x34
+#define QSERDES_V6_N4_TX_LANE_MODE_1			0x78
+#define QSERDES_V6_N4_TX_LANE_MODE_2			0x7c
+#define QSERDES_V6_N4_TX_LANE_MODE_3			0x80
+
+#define QSERDES_V6_N4_RX_UCDR_FO_GAIN_RATE2		0x8
+#define QSERDES_V6_N4_RX_UCDR_SO_GAIN_RATE2		0x18
+#define QSERDES_V6_N4_RX_UCDR_PI_CONTROLS		0x20
+#define QSERDES_V6_N4_RX_IVCM_CAL_CODE_OVERRIDE		0x94
+#define QSERDES_V6_N4_RX_RX_IVCM_CAL_CTRL2		0x9c
+#define QSERDES_V6_N4_RX_RX_IVCM_POSTCAL_OFFSET		0xa0
+#define QSERDES_V6_N4_RX_DFE_3				0xb4
+#define QSERDES_V6_N4_RX_VGA_CAL_CNTRL1			0xe0
+#define QSERDES_V6_N4_RX_VGA_CAL_MAN_VAL		0xe8
+#define QSERDES_V6_N4_RX_GM_CAL				0x10c
+#define QSERDES_V6_N4_RX_SIGDET_ENABLES			0x148
+#define QSERDES_V6_N4_RX_SIGDET_CNTRL			0x14c
+#define QSERDES_V6_N4_RX_SIGDET_DEGLITCH_CNTRL		0x154
+#define QSERDES_V6_N4_RX_DFE_CTLE_POST_CAL_OFFSET	0x194
+#define QSERDES_V6_N4_RX_Q_PI_INTRINSIC_BIAS_RATE32	0x1dc
+#define QSERDES_V6_N4_RX_UCDR_PI_CTRL1			0x23c
+#define QSERDES_V6_N4_RX_UCDR_PI_CTRL2			0x240
+#define QSERDES_V6_N4_RX_UCDR_SB2_GAIN2_RATE2		0x27c
+#define QSERDES_V6_N4_RX_DFE_DAC_ENABLE1		0x298
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B0		0x2b8
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B1		0x2bc
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B2		0x2c0
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B3		0x2c4
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B4		0x2c8
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B5		0x2cc
+#define QSERDES_V6_N4_RX_MODE_RATE_0_1_B6		0x2d0
+#define QSERDES_V6_N4_RX_MODE_RATE2_B0			0x2d4
+#define QSERDES_V6_N4_RX_MODE_RATE2_B1			0x2d8
+#define QSERDES_V6_N4_RX_MODE_RATE2_B2			0x2dc
+#define QSERDES_V6_N4_RX_MODE_RATE2_B3			0x2e0
+#define QSERDES_V6_N4_RX_MODE_RATE2_B4			0x2e4
+#define QSERDES_V6_N4_RX_MODE_RATE2_B5			0x2e8
+#define QSERDES_V6_N4_RX_MODE_RATE2_B6			0x2ec
+#define QSERDES_V6_N4_RX_RX_SUMMER_CAL_SPD_MODE		0x30c
+#define QSERDES_V6_N4_RX_RX_BKUP_CTRL1			0x310
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index 3a0512c3e07ab..63b3cbfcb50f2 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -24,6 +24,7 @@
 #include "phy-qcom-qmp-qserdes-com-v6.h"
 #include "phy-qcom-qmp-qserdes-txrx-v6.h"
 #include "phy-qcom-qmp-qserdes-txrx-v6_20.h"
+#include "phy-qcom-qmp-qserdes-txrx-v6_n4.h"
 #include "phy-qcom-qmp-qserdes-ln-shrd-v6.h"
 
 #include "phy-qcom-qmp-qserdes-com-v7.h"
-- 
GitLab


From ee6fcc0f337d6790b46838bab76c36e8bdd5658e Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:19:16 +0200
Subject: [PATCH 1795/4076] phy: qcom-qmp: qserdes-txrx: Add v7 register
 offsets

The X1E80100 platform bumps the HW version of QMP phy to v7 for USB and PCIE.
Add the new qserdes TX RX offsets in a dedicated header file.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-v6-v6-20-v7-new-offsets-v3-7-dfd1c375ef61@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h   | 78 +++++++++++++++++++
 drivers/phy/qualcomm/phy-qcom-qmp.h           |  1 +
 2 files changed, 79 insertions(+)
 create mode 100644 drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h
new file mode 100644
index 0000000000000..91f865b11347a
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v7.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef QCOM_PHY_QMP_QSERDES_TXRX_V7_H_
+#define QCOM_PHY_QMP_QSERDES_TXRX_V7_H_
+
+#define QSERDES_V7_TX_CLKBUF_ENABLE				0x08
+#define QSERDES_V7_TX_RESET_TSYNC_EN				0x1c
+#define QSERDES_V7_TX_PRE_STALL_LDO_BOOST_EN			0x20
+#define QSERDES_V7_TX_TX_BAND					0x24
+#define QSERDES_V7_TX_INTERFACE_SELECT				0x2c
+#define QSERDES_V7_TX_RES_CODE_LANE_TX				0x34
+#define QSERDES_V7_TX_RES_CODE_LANE_RX				0x38
+#define QSERDES_V7_TX_RES_CODE_LANE_OFFSET_TX			0x3c
+#define QSERDES_V7_TX_RES_CODE_LANE_OFFSET_RX			0x40
+#define QSERDES_V7_TX_PARRATE_REC_DETECT_IDLE_EN		0x60
+#define QSERDES_V7_TX_BIST_PATTERN7				0x7c
+#define QSERDES_V7_TX_LANE_MODE_1				0x84
+#define QSERDES_V7_TX_LANE_MODE_2				0x88
+#define QSERDES_V7_TX_LANE_MODE_3				0x8c
+#define QSERDES_V7_TX_LANE_MODE_4				0x90
+#define QSERDES_V7_TX_LANE_MODE_5				0x94
+#define QSERDES_V7_TX_RCV_DETECT_LVL_2				0xa4
+#define QSERDES_V7_TX_TRAN_DRVR_EMP_EN				0xc0
+#define QSERDES_V7_TX_TX_INTERFACE_MODE				0xc4
+#define QSERDES_V7_TX_VMODE_CTRL1				0xc8
+#define QSERDES_V7_TX_PI_QEC_CTRL				0xe4
+
+#define QSERDES_V7_RX_UCDR_FO_GAIN				0x08
+#define QSERDES_V7_RX_UCDR_SO_GAIN				0x14
+#define QSERDES_V7_RX_UCDR_FASTLOCK_FO_GAIN			0x30
+#define QSERDES_V7_RX_UCDR_SO_SATURATION_AND_ENABLE		0x34
+#define QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_LOW			0x3c
+#define QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_HIGH			0x40
+#define QSERDES_V7_RX_UCDR_PI_CONTROLS				0x44
+#define QSERDES_V7_RX_UCDR_SB2_THRESH1				0x4c
+#define QSERDES_V7_RX_UCDR_SB2_THRESH2				0x50
+#define QSERDES_V7_RX_UCDR_SB2_GAIN1				0x54
+#define QSERDES_V7_RX_UCDR_SB2_GAIN2				0x58
+#define QSERDES_V7_RX_AUX_DATA_TCOARSE_TFINE			0x60
+#define QSERDES_V7_RX_TX_ADAPT_POST_THRESH			0xcc
+#define QSERDES_V7_RX_VGA_CAL_CNTRL1				0xd4
+#define QSERDES_V7_RX_VGA_CAL_CNTRL2				0xd8
+#define QSERDES_V7_RX_GM_CAL					0xdc
+#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL2			0xec
+#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL3			0xf0
+#define QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL4			0xf4
+#define QSERDES_V7_RX_RX_IDAC_TSETTLE_LOW			0xf8
+#define QSERDES_V7_RX_RX_IDAC_TSETTLE_HIGH			0xfc
+#define QSERDES_V7_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1		0x110
+#define QSERDES_V7_RX_SIDGET_ENABLES				0x118
+#define QSERDES_V7_RX_SIGDET_CNTRL				0x11c
+#define QSERDES_V7_RX_SIGDET_DEGLITCH_CNTRL			0x124
+#define QSERDES_V7_RX_RX_MODE_00_LOW				0x15c
+#define QSERDES_V7_RX_RX_MODE_00_HIGH				0x160
+#define QSERDES_V7_RX_RX_MODE_00_HIGH2				0x164
+#define QSERDES_V7_RX_RX_MODE_00_HIGH3				0x168
+#define QSERDES_V7_RX_RX_MODE_00_HIGH4				0x16c
+#define QSERDES_V7_RX_RX_MODE_01_LOW				0x170
+#define QSERDES_V7_RX_RX_MODE_01_HIGH				0x174
+#define QSERDES_V7_RX_RX_MODE_01_HIGH2				0x178
+#define QSERDES_V7_RX_RX_MODE_01_HIGH3				0x17c
+#define QSERDES_V7_RX_RX_MODE_01_HIGH4				0x180
+#define QSERDES_V7_RX_RX_MODE_10_LOW				0x184
+#define QSERDES_V7_RX_RX_MODE_10_HIGH				0x188
+#define QSERDES_V7_RX_RX_MODE_10_HIGH2				0x18c
+#define QSERDES_V7_RX_RX_MODE_10_HIGH3				0x190
+#define QSERDES_V7_RX_RX_MODE_10_HIGH4				0x194
+#define QSERDES_V7_RX_DFE_EN_TIMER				0x1a0
+#define QSERDES_V7_RX_DFE_CTLE_POST_CAL_OFFSET			0x1a4
+#define QSERDES_V7_RX_DCC_CTRL1					0x1a8
+#define QSERDES_V7_RX_VTH_CODE					0x1b0
+#define QSERDES_V7_RX_SIGDET_CAL_CTRL1				0x1e4
+#define QSERDES_V7_RX_SIGDET_CAL_TRIM				0x1f8
+
+#endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index 63b3cbfcb50f2..6923496cbfee2 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -28,6 +28,7 @@
 #include "phy-qcom-qmp-qserdes-ln-shrd-v6.h"
 
 #include "phy-qcom-qmp-qserdes-com-v7.h"
+#include "phy-qcom-qmp-qserdes-txrx-v7.h"
 
 #include "phy-qcom-qmp-qserdes-pll.h"
 
-- 
GitLab


From 54c899f0d647e5724b02486243da40134dc91c45 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 4 Dec 2023 15:49:17 -0800
Subject: [PATCH 1796/4076] phy: renesas: phy-rcar-gen2: use select for
 GENERIC_PHY

Change the last "depends on GENERIC_PHY" to use select, like the
other 170+ Kconfig users do. This can help prevent circular
dependency issues.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: Kishon Vijay Abraham I <kishon@kernel.org>
Cc: linux-phy@lists.infradead.org
Link: https://lore.kernel.org/r/20231204234917.23509-1-rdunlap@infradead.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/renesas/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/phy/renesas/Kconfig b/drivers/phy/renesas/Kconfig
index 36505fc5f386e..e342eef0640b7 100644
--- a/drivers/phy/renesas/Kconfig
+++ b/drivers/phy/renesas/Kconfig
@@ -13,7 +13,7 @@ config PHY_R8A779F0_ETHERNET_SERDES
 config PHY_RCAR_GEN2
 	tristate "Renesas R-Car generation 2 USB PHY driver"
 	depends on ARCH_RENESAS
-	depends on GENERIC_PHY
+	select GENERIC_PHY
 	help
 	  Support for USB PHY found on Renesas R-Car generation 2 SoCs.
 
-- 
GitLab


From 21a1d02579ae75fd45555b84d20ba55632a14a19 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 18 Dec 2023 14:05:53 +0100
Subject: [PATCH 1797/4076] dt-bindings: phy: qcom,sc8280xp-qmp-usb43dp-phy:
 fix path to header

Fix the path to bindings header in description.

Fixes: e1c4c5436b4a ("dt-bindings: phy: qcom,qmp-usb3-dp: fix sc8280xp binding")
Cc: stable@vger.kernel.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://lore.kernel.org/r/20231218130553.45893-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml           | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
index ae83cb8cb21f8..59d34a2a21962 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
@@ -63,12 +63,12 @@ properties:
   "#clock-cells":
     const: 1
     description:
-      See include/dt-bindings/dt-bindings/phy/phy-qcom-qmp.h
+      See include/dt-bindings/phy/phy-qcom-qmp.h
 
   "#phy-cells":
     const: 1
     description:
-      See include/dt-bindings/dt-bindings/phy/phy-qcom-qmp.h
+      See include/dt-bindings/phy/phy-qcom-qmp.h
 
   orientation-switch:
     description:
-- 
GitLab


From 5301b7a04040b0a6191856c765146e0a9ab88ebc Mon Sep 17 00:00:00 2001
From: Can Guo <quic_cang@quicinc.com>
Date: Sat, 2 Dec 2023 04:36:15 -0800
Subject: [PATCH 1798/4076] phy: qualcomm: phy-qcom-qmp-ufs: Rectify SM8550 UFS
 HS-G4 PHY Settings

The registers, which are being touched in current SM8550 UFS PHY settings,
and the values being programmed are mainly the ones working for HS-G4 mode,
meanwhile, there are also a few ones somehow taken from HS-G5 PHY settings.
However, even consider HS-G4 mode only, some of them are incorrect and some
are missing. Rectify the HS-G4 PHY settings by strictly aligning with the
SM8550 UFS PHY Hardware Programming Guide suggested HS-G4 PHY settings.

Fixes: 1679bfef906f ("phy: qcom-qmp-ufs: Add SM8550 support")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Can Guo <quic_cang@quicinc.com>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8550-QRD
Link: https://lore.kernel.org/r/1701520577-31163-10-git-send-email-quic_cang@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../phy-qcom-qmp-qserdes-txrx-ufs-v6.h        |  1 +
 drivers/phy/qualcomm/phy-qcom-qmp-ufs.c       | 28 +++++++++++++------
 2 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
index ae220fd04d10d..35d497fd9f9a4 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-ufs-v6.h
@@ -11,6 +11,7 @@
 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX		0x30
 #define QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_RX		0x34
 #define QSERDES_UFS_V6_TX_LANE_MODE_1				0x7c
+#define QSERDES_UFS_V6_TX_FR_DCC_CTRL				0x108
 
 #define QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE2		0x08
 #define QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE4		0x10
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
index 5f79d188b435e..3c2e6255e26f6 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
@@ -763,22 +763,26 @@ static const struct qmp_phy_init_tbl sm8550_ufsphy_serdes[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14),
 	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x7f),
 	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x06),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x4c),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x0a),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x18),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x14),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x99),
-	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x4c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x07),
+};
+
+static const struct qmp_phy_init_tbl sm8550_ufsphy_hs_b_serdes[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x44),
 };
 
 static const struct qmp_phy_init_tbl sm8550_ufsphy_tx[] = {
-	QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_LANE_MODE_1, 0x05),
 	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_TX_FR_DCC_CTRL, 0x4c),
 };
 
 static const struct qmp_phy_init_tbl sm8550_ufsphy_rx[] = {
-	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE2, 0x0c),
-	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FASTLOCK_FO_GAIN_RATE4, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_UCDR_FO_GAIN_RATE2, 0x0c),
 	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_VGA_CAL_MAN_VAL, 0x0e),
 
 	QMP_PHY_INIT_CFG(QSERDES_UFS_V6_RX_MODE_RATE_0_1_B0, 0xc2),
@@ -801,6 +805,8 @@ static const struct qmp_phy_init_tbl sm8550_ufsphy_pcs[] = {
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x2b),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04),
 };
 
 static const struct qmp_phy_init_tbl sm8650_ufsphy_serdes[] = {
@@ -1357,6 +1363,10 @@ static const struct qmp_phy_cfg sm8550_ufsphy_cfg = {
 		.pcs		= sm8550_ufsphy_pcs,
 		.pcs_num	= ARRAY_SIZE(sm8550_ufsphy_pcs),
 	},
+	.tbls_hs_b = {
+		.serdes		= sm8550_ufsphy_hs_b_serdes,
+		.serdes_num	= ARRAY_SIZE(sm8550_ufsphy_hs_b_serdes),
+	},
 	.clk_list		= sdm845_ufs_phy_clk_l,
 	.num_clks		= ARRAY_SIZE(sdm845_ufs_phy_clk_l),
 	.vreg_list		= qmp_phy_vreg_l,
-- 
GitLab


From 57f31e911eaa5e682c0a03253f8b4348adee52cb Mon Sep 17 00:00:00 2001
From: Wang Jinchao <wangjinchao@xfusion.com>
Date: Fri, 15 Dec 2023 14:09:00 +0800
Subject: [PATCH 1799/4076] phy: phy-can-transceiver: insert space after
 include

Maintain Consistent Formatting: Insert Space after #include

Signed-off-by: Wang Jinchao <wangjinchao@xfusion.com>
Reviewed-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/r/202312151407+0800-wangjinchao@xfusion.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/phy-can-transceiver.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c
index 840b7f8a31c5f..ee4ce42496985 100644
--- a/drivers/phy/phy-can-transceiver.c
+++ b/drivers/phy/phy-can-transceiver.c
@@ -6,11 +6,11 @@
  *
  */
 #include <linux/of.h>
-#include<linux/phy/phy.h>
-#include<linux/platform_device.h>
-#include<linux/module.h>
-#include<linux/gpio.h>
-#include<linux/gpio/consumer.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/mux/consumer.h>
 
 struct can_transceiver_data {
-- 
GitLab


From cc230a4cd8e91f64c90b5494dfd76848197418ed Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Mon, 11 Dec 2023 10:56:23 +0800
Subject: [PATCH 1800/4076] dt-bindings: phy: mediatek: tphy: add a property
 for force-mode switch

Due to some old SoCs with shared t-phy between usb3 and pcie only support
force-mode switch, and shared and non-shared t-phy may exist at the same
time on a SoC, can't use compatible to distinguish between shared and
non-shared t-phy, add a property to supported it.
Currently, only support switch from default pcie mode to usb3 mode.
But now prefer to use "mediatek,syscon-type" on new SoC as far as possible.

Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231211025624.28991-1-chunfeng.yun@mediatek.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/mediatek,tphy.yaml | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
index 2bb91542e984e..acba0720125dd 100644
--- a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
+++ b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
@@ -235,6 +235,15 @@ patternProperties:
           Specify the flag to enable BC1.2 if support it
         type: boolean
 
+      mediatek,force-mode:
+        description:
+          The force mode is used to manually switch the shared phy mode between
+          USB3 and PCIe, when USB3 phy type is selected by the consumer, and
+          force-mode is set, will cause phy's power and pipe toggled and force
+          phy as USB3 mode which switched from default PCIe mode. But perfer to
+          use the property "mediatek,syscon-type" for newer SoCs that support it.
+        type: boolean
+
       mediatek,syscon-type:
         $ref: /schemas/types.yaml#/definitions/phandle-array
         maxItems: 1
-- 
GitLab


From 9b27303003f5af0d378f29ccccea57c7d65cc642 Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Mon, 11 Dec 2023 10:56:24 +0800
Subject: [PATCH 1801/4076] phy: mediatek: tphy: add support force phy mode
 switch

this is used to be compatible with old SoCs, such as mt8195, which shares
t-phy between usb3 and pcie controller, usually, it's default mode is pcie
rc mode, and could use force mode to switch into usb3 mode, because pericfg
layer doesn't provide mode switch, also no efuse or jumper can be used;
Currently, only support switch from default pcie mode to usb3;
Note: don't use this way on new SoCs, use pericfg layer's mode switch
instead (by perperty "mediatek,syscon-type").

Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/20231211025624.28991-2-chunfeng.yun@mediatek.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/mediatek/phy-mtk-tphy.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c
index 05eab9014132f..a4746f6cb8a18 100644
--- a/drivers/phy/mediatek/phy-mtk-tphy.c
+++ b/drivers/phy/mediatek/phy-mtk-tphy.c
@@ -185,6 +185,10 @@
 #define P3D_RG_CDR_BIR_LTD1		GENMASK(28, 24)
 #define P3D_RG_CDR_BIR_LTD0		GENMASK(12, 8)
 
+#define U3P_U3_PHYD_TOP1		0x100
+#define P3D_RG_PHY_MODE			GENMASK(2, 1)
+#define P3D_RG_FORCE_PHY_MODE		BIT(0)
+
 #define U3P_U3_PHYD_RXDET1		0x128
 #define P3D_RG_RXDET_STB2_SET		GENMASK(17, 9)
 
@@ -327,6 +331,7 @@ struct mtk_phy_instance {
 	int discth;
 	int pre_emphasis;
 	bool bc12_en;
+	bool type_force_mode;
 };
 
 struct mtk_tphy {
@@ -768,6 +773,23 @@ static void u3_phy_instance_init(struct mtk_tphy *tphy,
 	void __iomem *phya = u3_banks->phya;
 	void __iomem *phyd = u3_banks->phyd;
 
+	if (instance->type_force_mode) {
+		/* force phy as usb mode, default is pcie rc mode */
+		mtk_phy_update_field(phyd + U3P_U3_PHYD_TOP1, P3D_RG_PHY_MODE, 1);
+		mtk_phy_set_bits(phyd + U3P_U3_PHYD_TOP1, P3D_RG_FORCE_PHY_MODE);
+		/* power down phy by ip and pipe reset */
+		mtk_phy_set_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLD,
+				 P3C_FORCE_IP_SW_RST | P3C_MCU_BUS_CK_GATE_EN);
+		mtk_phy_set_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLE,
+				 P3C_RG_SWRST_U3_PHYD | P3C_RG_SWRST_U3_PHYD_FORCE_EN);
+		udelay(10);
+		/* power on phy again */
+		mtk_phy_clear_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLD,
+				   P3C_FORCE_IP_SW_RST | P3C_MCU_BUS_CK_GATE_EN);
+		mtk_phy_clear_bits(u3_banks->chip + U3P_U3_CHIP_GPIO_CTLE,
+				   P3C_RG_SWRST_U3_PHYD | P3C_RG_SWRST_U3_PHYD_FORCE_EN);
+	}
+
 	/* gating PCIe Analog XTAL clock */
 	mtk_phy_set_bits(u3_banks->spllc + U3P_SPLLC_XTALCTL3,
 			 XC3_RG_U3_XTAL_RX_PWD | XC3_RG_U3_FRC_XTAL_RX_PWD);
@@ -1120,6 +1142,9 @@ static void phy_parse_property(struct mtk_tphy *tphy,
 {
 	struct device *dev = &instance->phy->dev;
 
+	if (instance->type == PHY_TYPE_USB3)
+		instance->type_force_mode = device_property_read_bool(dev, "mediatek,force-mode");
+
 	if (instance->type != PHY_TYPE_USB2)
 		return;
 
-- 
GitLab


From ec80c175c096eb752d581ef0aafb12ed46010b2a Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:49:10 +0200
Subject: [PATCH 1802/4076] dt-bindings: phy: qcom: snps-eusb2: Document the
 X1E80100 compatible

Add the X1E80100 compatible to the list of supported PHYs.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-eusb2-x1e80100-v2-1-3ba9a8e5ade4@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
index 8f5d7362046c9..b82f7f5731ed4 100644
--- a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-phy.yaml
@@ -19,6 +19,7 @@ properties:
           - enum:
               - qcom,sdx75-snps-eusb2-phy
               - qcom,sm8650-snps-eusb2-phy
+              - qcom,x1e80100-snps-eusb2-phy
           - const: qcom,sm8550-snps-eusb2-phy
       - const: qcom,sm8550-snps-eusb2-phy
 
-- 
GitLab


From f11aeb9d49632afc7abd9dfea6bcf5b3dd8addc1 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 15:16:41 +0200
Subject: [PATCH 1803/4076] dt-bindings: phy: qcom,sc8280xp-qmp-usb43dp-phy:
 Document X1E80100 compatible

Add the X1E80100 compatible to the list.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231201-x1e80100-phy-combo-v1-1-6938ec41f3ac@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml  | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
index 59d34a2a21962..2d0d7e9e64311 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
@@ -28,6 +28,7 @@ properties:
       - qcom,sm8450-qmp-usb3-dp-phy
       - qcom,sm8550-qmp-usb3-dp-phy
       - qcom,sm8650-qmp-usb3-dp-phy
+      - qcom,x1e80100-qmp-usb3-dp-phy
 
   reg:
     maxItems: 1
@@ -130,6 +131,7 @@ allOf:
             - qcom,sm6350-qmp-usb3-dp-phy
             - qcom,sm8550-qmp-usb3-dp-phy
             - qcom,sm8650-qmp-usb3-dp-phy
+            - qcom,x1e80100-qmp-usb3-dp-phy
     then:
       required:
         - power-domains
-- 
GitLab


From d7b3579f84f74e0f7d88d180d4e15c679786b648 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 15:16:42 +0200
Subject: [PATCH 1804/4076] phy: qcom-qmp-combo: Add x1e80100 USB/DP combo phys

The X1E80100 has three copies of an USB/DP compbo PHY, add support for this
to the Qualcomm QMP PHY driver.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20231201-x1e80100-phy-combo-v1-2-6938ec41f3ac@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-combo.c | 170 ++++++++++++++++++++++
 1 file changed, 170 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
index 0417856b8e7bc..cd88f7b51088e 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
@@ -1203,6 +1203,127 @@ static const struct qmp_phy_init_tbl sc8280xp_usb43dp_pcs_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07),
 };
 
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x62),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0xc2),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0xc2),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0xba),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0xba),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x13),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_HS_SWITCH_SEL_1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CORE_CLK_DIV_MODE0, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x76),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO_MODE1, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE0, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_INITVAL2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAXVAL2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SVS_MODE_CLK_SEL, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0a),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_2, 0x50),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_LANE_MODE_3, 0x50),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX, 0x0a),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_CNTRL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_DEGLITCH_CNTRL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_SIGDET_ENABLES, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B0, 0xc3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B1, 0xc3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B2, 0xd8),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B3, 0x9e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B4, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B5, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE_0_1_B6, 0x64),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B0, 0xd6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B1, 0xee),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B2, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B3, 0x9a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B4, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B5, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_MODE_RATE2_B6, 0xe3),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_IVCM_CAL_CODE_OVERRIDE, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_IVCM_CAL_CTRL2, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_SUMMER_CAL_SPD_MODE, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_CTLE_POST_CAL_OFFSET, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CONTROLS, 0x15),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CTRL1, 0xd0),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_PI_CTRL2, 0x48),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_SB2_GAIN2_RATE2, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_IVCM_POSTCAL_OFFSET, 0x7c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_VGA_CAL_CNTRL1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_VGA_CAL_MAN_VAL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_DAC_ENABLE1, 0x88),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_DFE_3, 0x45),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_GM_CAL, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_FO_GAIN_RATE2, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_UCDR_SO_GAIN_RATE2, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_Q_PI_INTRINSIC_BIAS_RATE32, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_N4_RX_RX_BKUP_CTRL1, 0x14),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG1, 0xc4),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG2, 0x89),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG3, 0x20),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG6, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x21),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0x55),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_CDR_RESET_TIME, 0x0a),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG1, 0xd4),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG2, 0x30),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0c),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG1, 0x4b),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG5, 0x10),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_usb_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07),
+};
+
 /* list of regulators */
 struct qmp_regulator_data {
 	const char *name;
@@ -1684,6 +1805,51 @@ static const struct qmp_phy_cfg sc8280xp_usb43dpphy_cfg = {
 	.regs			= qmp_v5_5nm_usb3phy_regs_layout,
 };
 
+static const struct qmp_phy_cfg x1e80100_usb3dpphy_cfg = {
+	.offsets		= &qmp_combo_offsets_v5,
+
+	.serdes_tbl		= x1e80100_usb43dp_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(x1e80100_usb43dp_serdes_tbl),
+	.tx_tbl			= x1e80100_usb43dp_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(x1e80100_usb43dp_tx_tbl),
+	.rx_tbl			= x1e80100_usb43dp_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(x1e80100_usb43dp_rx_tbl),
+	.pcs_tbl		= x1e80100_usb43dp_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(x1e80100_usb43dp_pcs_tbl),
+	.pcs_usb_tbl		= x1e80100_usb43dp_pcs_usb_tbl,
+	.pcs_usb_tbl_num	= ARRAY_SIZE(x1e80100_usb43dp_pcs_usb_tbl),
+
+	.dp_serdes_tbl		= qmp_v6_dp_serdes_tbl,
+	.dp_serdes_tbl_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl),
+	.dp_tx_tbl		= qmp_v6_dp_tx_tbl,
+	.dp_tx_tbl_num		= ARRAY_SIZE(qmp_v6_dp_tx_tbl),
+
+	.serdes_tbl_rbr		= qmp_v6_dp_serdes_tbl_rbr,
+	.serdes_tbl_rbr_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr),
+	.serdes_tbl_hbr		= qmp_v6_dp_serdes_tbl_hbr,
+	.serdes_tbl_hbr_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr),
+	.serdes_tbl_hbr2	= qmp_v6_dp_serdes_tbl_hbr2,
+	.serdes_tbl_hbr2_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2),
+	.serdes_tbl_hbr3	= qmp_v6_dp_serdes_tbl_hbr3,
+	.serdes_tbl_hbr3_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3),
+
+	.swing_hbr_rbr		= &qmp_dp_v5_voltage_swing_hbr_rbr,
+	.pre_emphasis_hbr_rbr	= &qmp_dp_v5_pre_emphasis_hbr_rbr,
+	.swing_hbr3_hbr2	= &qmp_dp_v5_voltage_swing_hbr3_hbr2,
+	.pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2,
+
+	.dp_aux_init		= qmp_v4_dp_aux_init,
+	.configure_dp_tx	= qmp_v4_configure_dp_tx,
+	.configure_dp_phy	= qmp_v4_configure_dp_phy,
+	.calibrate_dp_phy	= qmp_v4_calibrate_dp_phy,
+
+	.reset_list		= msm8996_usb3phy_reset_l,
+	.num_resets		= ARRAY_SIZE(msm8996_usb3phy_reset_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v45_usb3phy_regs_layout,
+};
+
 static const struct qmp_phy_cfg sm6350_usb3dpphy_cfg = {
 	.offsets		= &qmp_combo_offsets_v3,
 
@@ -3562,6 +3728,10 @@ static const struct of_device_id qmp_combo_of_match_table[] = {
 		.compatible = "qcom,sm8650-qmp-usb3-dp-phy",
 		.data = &sm8550_usb3dpphy_cfg,
 	},
+	{
+		.compatible = "qcom,x1e80100-qmp-usb3-dp-phy",
+		.data = &x1e80100_usb3dpphy_cfg,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, qmp_combo_of_match_table);
-- 
GitLab


From c5ffffd714373e7c6b39d3b005dbfbaadbbb4d2d Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:34:11 +0200
Subject: [PATCH 1805/4076] dt-bindings: phy: qcom,sc8280xp-qmp-usb3-uni: Add
 X1E80100 USB PHY binding

Add compatible string for Qualcomm QMP Super Speed (SS) UNI PHY found
in X1E80100.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-usb3-uniphy-x1e80100-v3-1-273814c300f8@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml           | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
index 57702f7f2a46c..15d82c67f157b 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
@@ -32,6 +32,7 @@ properties:
       - qcom,sm8150-qmp-usb3-uni-phy
       - qcom,sm8250-qmp-usb3-uni-phy
       - qcom,sm8350-qmp-usb3-uni-phy
+      - qcom,x1e80100-qmp-usb3-uni-phy
 
 
   reg:
@@ -135,6 +136,7 @@ allOf:
               - qcom,sm8150-qmp-usb3-uni-phy
               - qcom,sm8250-qmp-usb3-uni-phy
               - qcom,sm8350-qmp-usb3-uni-phy
+              - qcom,x1e80100-qmp-usb3-uni-phy
     then:
       properties:
         clocks:
@@ -171,6 +173,7 @@ allOf:
             enum:
               - qcom,sa8775p-qmp-usb3-uni-phy
               - qcom,sc8280xp-qmp-usb3-uni-phy
+              - qcom,x1e80100-qmp-usb3-uni-phy
     then:
       required:
         - power-domains
-- 
GitLab


From 2daa9555ba9858c29b9734b3a104c338b718feab Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 7 Dec 2023 14:34:12 +0200
Subject: [PATCH 1806/4076] phy: qcom-qmp-usb: Add Qualcomm X1E80100 USB3 PHY
 support

The X1E80100 platform has two instances of the USB3 UNI phy attached
to the multi-port USB controller, add definition for these.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20231122-phy-qualcomm-usb3-uniphy-x1e80100-v3-2-273814c300f8@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-usb.c | 171 ++++++++++++++++++++++++
 1 file changed, 171 insertions(+)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 77e91b3eae79e..243cc2b9a0fb6 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -25,6 +25,7 @@
 #include "phy-qcom-qmp-pcs-usb-v4.h"
 #include "phy-qcom-qmp-pcs-usb-v5.h"
 #include "phy-qcom-qmp-pcs-usb-v6.h"
+#include "phy-qcom-qmp-pcs-usb-v7.h"
 
 /* QPHY_SW_RESET bit */
 #define SW_RESET				BIT(0)
@@ -163,6 +164,17 @@ static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = {
 	[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V6_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR,
 };
 
+static const unsigned int qmp_v7_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = {
+	[QPHY_SW_RESET]			= QPHY_V7_PCS_SW_RESET,
+	[QPHY_START_CTRL]		= QPHY_V7_PCS_START_CONTROL,
+	[QPHY_PCS_STATUS]		= QPHY_V7_PCS_PCS_STATUS1,
+	[QPHY_PCS_POWER_DOWN_CONTROL]	= QPHY_V7_PCS_POWER_DOWN_CONTROL,
+
+	/* In PCS_USB */
+	[QPHY_PCS_AUTONOMOUS_MODE_CTRL]	= QPHY_V7_PCS_USB3_AUTONOMOUS_MODE_CTRL,
+	[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V7_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR,
+};
+
 static const struct qmp_phy_init_tbl ipq9574_usb3_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x1a),
 	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x08),
@@ -1301,6 +1313,134 @@ static const struct qmp_phy_init_tbl sa8775p_usb3_uniphy_pcs_usb_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_POWER_STATE_CONFIG1, 0x6f),
 };
 
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE1_MODE1, 0xc0),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE2_MODE1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CP_CTRL_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP1_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP2_MODE1, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DEC_START_MODE1, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START1_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START2_MODE1, 0x75),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START3_MODE1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_HSCLK_SEL_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE1_MODE1, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE2_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0x5c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x5c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE1_MODE0, 0xc0),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_STEP_SIZE2_MODE0, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CP_CTRL_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP1_MODE0, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP2_MODE0, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DEC_START_MODE0, 0x41),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START1_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START2_MODE0, 0x75),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_DIV_FRAC_START3_MODE0, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE1_MODE0, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE2_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_BG_TIMER, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_PER1, 0x62),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SSC_PER2, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SYSCLK_BUF_ENABLE, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_SYSCLK_EN_SEL, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_LOCK_CMP_CFG, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_VCO_TUNE_MAP, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CORE_CLK_EN, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_CMN_CONFIG_1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37),
+	QMP_PHY_INIT_CFG(QSERDES_V7_COM_ADDITIONAL_MISC, 0x0c),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_TX, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_RX, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_OFFSET_TX, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RES_CODE_LANE_OFFSET_RX, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_1, 0xf5),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_3, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_4, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_LANE_MODE_5, 0x5f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_RCV_DETECT_LVL_2, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V7_TX_PI_QEC_CTRL, 0x21),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FO_GAIN, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SO_GAIN, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x7f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_PI_CONTROLS, 0x99),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_THRESH1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_THRESH2, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_GAIN1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_UCDR_SB2_GAIN2, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_AUX_DATA_TCOARSE_TFINE, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_VGA_CAL_CNTRL1, 0x54),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_VGA_CAL_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_GM_CAL, 0x13),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_IDAC_TSETTLE_LOW, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_IDAC_TSETTLE_HIGH, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x47),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CNTRL, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_DEGLITCH_CNTRL, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_LOW, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH, 0xbf),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH2, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH3, 0xdf),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_00_HIGH4, 0xed),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_LOW, 0xdc),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH, 0x5c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH2, 0x9c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH3, 0x1d),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_RX_MODE_01_HIGH4, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_DFE_EN_TIMER, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_DCC_CTRL1, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_VTH_CODE, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CAL_CTRL1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V7_RX_SIGDET_CAL_TRIM, 0x08),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG1, 0xc4),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG2, 0x89),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG3, 0x20),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_LOCK_DETECT_CONFIG6, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_REFGEN_REQ_CONFIG1, 0x21),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_RX_SIGDET_LVL, 0xaa),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_CDR_RESET_TIME, 0x0a),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_ALIGN_DETECT_CONFIG1, 0x88),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_ALIGN_DETECT_CONFIG2, 0x13),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_PCS_TX_RX_CONFIG, 0x0c),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_EQ_CONFIG1, 0x4b),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_EQ_CONFIG5, 0x10),
+};
+
+static const struct qmp_phy_init_tbl x1e80100_usb3_uniphy_pcs_usb_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_L, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V7_PCS_USB3_RCVR_DTCT_DLY_U3_H, 0x00),
+};
+
 struct qmp_usb_offsets {
 	u16 serdes;
 	u16 pcs;
@@ -1465,6 +1605,14 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v6 = {
 	.rx		= 0x1000,
 };
 
+static const struct qmp_usb_offsets qmp_usb_offsets_v7 = {
+	.serdes		= 0,
+	.pcs		= 0x0200,
+	.pcs_usb	= 0x1200,
+	.tx		= 0x0e00,
+	.rx		= 0x1000,
+};
+
 static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = {
 	.lanes			= 1,
 
@@ -1752,6 +1900,26 @@ static const struct qmp_phy_cfg qcm2290_usb3phy_cfg = {
 	.regs			= qmp_v3_usb3phy_regs_layout_qcm2290,
 };
 
+static const struct qmp_phy_cfg x1e80100_usb3_uniphy_cfg = {
+	.lanes			= 1,
+
+	.offsets		= &qmp_usb_offsets_v7,
+
+	.serdes_tbl		= x1e80100_usb3_uniphy_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(x1e80100_usb3_uniphy_serdes_tbl),
+	.tx_tbl			= x1e80100_usb3_uniphy_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(x1e80100_usb3_uniphy_tx_tbl),
+	.rx_tbl			= x1e80100_usb3_uniphy_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(x1e80100_usb3_uniphy_rx_tbl),
+	.pcs_tbl		= x1e80100_usb3_uniphy_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(x1e80100_usb3_uniphy_pcs_tbl),
+	.pcs_usb_tbl		= x1e80100_usb3_uniphy_pcs_usb_tbl,
+	.pcs_usb_tbl_num	= ARRAY_SIZE(x1e80100_usb3_uniphy_pcs_usb_tbl),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v7_usb3phy_regs_layout,
+};
+
 static void qmp_usb_configure_lane(void __iomem *base,
 					const struct qmp_phy_init_tbl tbl[],
 					int num,
@@ -2441,6 +2609,9 @@ static const struct of_device_id qmp_usb_of_match_table[] = {
 	}, {
 		.compatible = "qcom,sm8350-qmp-usb3-uni-phy",
 		.data = &sm8350_usb3_uniphy_cfg,
+	}, {
+		.compatible = "qcom,x1e80100-qmp-usb3-uni-phy",
+		.data = &x1e80100_usb3_uniphy_cfg,
 	},
 	{ },
 };
-- 
GitLab


From ac254dfb983deb7840bc7267418d1ae231f5694f Mon Sep 17 00:00:00 2001
From: "JiaLong.Yang" <jialong.yang@shingroup.cn>
Date: Thu, 21 Dec 2023 14:02:41 +0800
Subject: [PATCH 1807/4076] perf vendor events powerpc: Add PVN for HX-C2000
 CPU with Power8 Architecture

HX-C2000 is a new CPU made by HEXIN Technologies Co., Ltd. And a new PVN
0x0066 has been applied from the OpenPower Community for this CPU.

Here is a patch to make perf tool run in the CPU.

Reviewed-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Signed-off-by: JiaLong.Yang <jialong.yang@shingroup.cn>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: shenghui.qu@shingroup.cn
Cc: Zhao Ke <ke.zhao@shingroup.cn>
Cc: zhijie.ren@shingroup.cn
Link: https://lore.kernel.org/r/20231221060242.4532-1-jialong.yang@shingroup.cn
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/powerpc/mapfile.csv | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
index f4908af7ad66b..599a588dbeb40 100644
--- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv
+++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
@@ -11,8 +11,7 @@
 #
 # Multiple PVRs could map to a single JSON file.
 #
-
-# Power8 entries
 0x004[bcd][[:xdigit:]]{4},1,power8,core
+0x0066[[:xdigit:]]{4},1,power8,core
 0x004e[[:xdigit:]]{4},1,power9,core
 0x0080[[:xdigit:]]{4},1,power10,core
-- 
GitLab


From 855c2e1d1842f0101a051378094548ca581d7a7d Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Mon, 18 Dec 2023 12:39:39 +0100
Subject: [PATCH 1808/4076] dmaengine: xilinx: xdma: Rework
 xdma_terminate_all()

Simplify xdma_xfer_stop(). Stop the dma engine and clear its status
register unconditionally - just do what its name states. This change
also allows to call it without grabbing a lock, which minimizes
the total time spent with a spinlock held.

Delete the currently processed vd.node from the vc.desc_issued list
prior to passing it to vchan_terminate_vdesc(). In case there's more
than one descriptor pending on vc.desc_issued list, calling
vchan_terminate_desc() results in losing the link between
vc.desc_issued list head and the second descriptor on the list. Doing so
results in resources leakege, as vchan_dma_desc_free_list() won't be
able to properly free memory resources attached to descriptors,
resulting in dma_pool_destroy() failure.

Don't call vchan_dma_desc_free_list() from within xdma_terminate_all().
Move all terminated descriptors to the vc.desc_terminated list instead.
This allows to postpone freeing memory resources associated with
descriptors until the call to vchan_synchronize(), which is called from
xdma_synchronize() callback. This is the right way to do it -
xdma_terminate_all() should return as soon as possible, while freeing
resources (that may be time consuming in case of large number of
descriptors) can be done safely later.

Fixes: f5c392d106e7 ("dmaengine: xilinx: xdma: Add terminate_all/synchronize callbacks")
Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Link: https://lore.kernel.org/r/20231218113943.9099-5-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index c22701e76b693..0c73508638738 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -379,12 +379,9 @@ static int xdma_xfer_start(struct xdma_chan *xchan)
  */
 static int xdma_xfer_stop(struct xdma_chan *xchan)
 {
-	struct virt_dma_desc *vd = vchan_next_desc(&xchan->vchan);
-	struct xdma_device *xdev = xchan->xdev_hdl;
 	int ret;
-
-	if (!vd || !xchan->busy)
-		return -EINVAL;
+	u32 val;
+	struct xdma_device *xdev = xchan->xdev_hdl;
 
 	/* clear run stop bit to prevent any further auto-triggering */
 	ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
@@ -392,7 +389,10 @@ static int xdma_xfer_stop(struct xdma_chan *xchan)
 	if (ret)
 		return ret;
 
-	xchan->busy = false;
+	/* Clear the channel status register */
+	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &val);
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -505,25 +505,25 @@ static void xdma_issue_pending(struct dma_chan *chan)
 static int xdma_terminate_all(struct dma_chan *chan)
 {
 	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
-	struct xdma_desc *desc = NULL;
 	struct virt_dma_desc *vd;
 	unsigned long flags;
 	LIST_HEAD(head);
 
-	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
 	xdma_xfer_stop(xdma_chan);
 
+	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
+
+	xdma_chan->busy = false;
 	vd = vchan_next_desc(&xdma_chan->vchan);
-	if (vd)
-		desc = to_xdma_desc(vd);
-	if (desc) {
-		dma_cookie_complete(&desc->vdesc.tx);
-		vchan_terminate_vdesc(&desc->vdesc);
+	if (vd) {
+		list_del(&vd->node);
+		dma_cookie_complete(&vd->tx);
+		vchan_terminate_vdesc(vd);
 	}
-
 	vchan_get_all_descriptors(&xdma_chan->vchan, &head);
+	list_splice_tail(&head, &xdma_chan->vchan.desc_terminated);
+
 	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
-	vchan_dma_desc_free_list(&xdma_chan->vchan, &head);
 
 	return 0;
 }
-- 
GitLab


From d0f22a3f55044f91b98e5536aa2c4d51d41cf8e7 Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Mon, 18 Dec 2023 12:39:40 +0100
Subject: [PATCH 1809/4076] dmaengine: xilinx: xdma: Add error checking in
 xdma_channel_isr()

Check and clear the status register value before proceeding any
further in xdma_channel_isr(). It is necessary to do it since the
interrupt may occur on any error condition enabled at the start of a
transfer.

Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Link: https://lore.kernel.org/r/20231218113943.9099-6-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 0c73508638738..9a1d2939a333f 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -811,6 +811,18 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	desc = to_xdma_desc(vd);
 	xdev = xchan->xdev_hdl;
 
+	/* Clear-on-read the status register */
+	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &st);
+	if (ret)
+		goto out;
+
+	st &= XDMA_CHAN_STATUS_MASK;
+	if ((st & XDMA_CHAN_ERROR_MASK) ||
+	    !(st & (CHAN_CTRL_IE_DESC_COMPLETED | CHAN_CTRL_IE_DESC_STOPPED))) {
+		xdma_err(xdev, "channel error, status register value: 0x%x", st);
+		goto out;
+	}
+
 	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_COMPLETED_DESC,
 			  &complete_desc_num);
 	if (ret)
@@ -818,14 +830,6 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 
 	if (desc->cyclic) {
 		desc->completed_desc_num = complete_desc_num;
-
-		ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS,
-				  &st);
-		if (ret)
-			goto out;
-
-		regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_STATUS, st);
-
 		vchan_cyclic_callback(vd);
 	} else {
 		xchan->busy = false;
-- 
GitLab


From fd0e1d83a813d48285d39eae0053b38828cf7e1a Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Mon, 18 Dec 2023 12:39:41 +0100
Subject: [PATCH 1810/4076] dmaengine: xilinx: xdma: Add transfer error
 reporting

Extend the capability of transfer status reporting. Introduce error flag,
which allows to report error in case of a interrupt-reported error
condition.

Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Link: https://lore.kernel.org/r/20231218113943.9099-7-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 9a1d2939a333f..9f8597ed9be24 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -85,6 +85,7 @@ struct xdma_chan {
  * @cyclic: Cyclic transfer vs. scatter-gather
  * @periods: Number of periods in the cyclic transfer
  * @period_size: Size of a period in bytes in cyclic transfers
+ * @error: tx error flag
  */
 struct xdma_desc {
 	struct virt_dma_desc		vdesc;
@@ -97,6 +98,7 @@ struct xdma_desc {
 	bool				cyclic;
 	u32				periods;
 	u32				period_size;
+	bool				error;
 };
 
 #define XDMA_DEV_STATUS_REG_DMA		BIT(0)
@@ -274,6 +276,7 @@ xdma_alloc_desc(struct xdma_chan *chan, u32 desc_num, bool cyclic)
 	sw_desc->chan = chan;
 	sw_desc->desc_num = desc_num;
 	sw_desc->cyclic = cyclic;
+	sw_desc->error = false;
 	dblk_num = DIV_ROUND_UP(desc_num, XDMA_DESC_ADJACENT);
 	sw_desc->desc_blocks = kcalloc(dblk_num, sizeof(*sw_desc->desc_blocks),
 				       GFP_NOWAIT);
@@ -769,20 +772,20 @@ static enum dma_status xdma_tx_status(struct dma_chan *chan, dma_cookie_t cookie
 	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
 
 	vd = vchan_find_desc(&xdma_chan->vchan, cookie);
-	if (vd)
-		desc = to_xdma_desc(vd);
-	if (!desc || !desc->cyclic) {
-		spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
-		return ret;
-	}
-
-	period_idx = desc->completed_desc_num % desc->periods;
-	residue = (desc->periods - period_idx) * desc->period_size;
+	if (!vd)
+		goto out;
 
+	desc = to_xdma_desc(vd);
+	if (desc->error) {
+		ret = DMA_ERROR;
+	} else if (desc->cyclic) {
+		period_idx = desc->completed_desc_num % desc->periods;
+		residue = (desc->periods - period_idx) * desc->period_size;
+		dma_set_residue(state, residue);
+	}
+out:
 	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
 
-	dma_set_residue(state, residue);
-
 	return ret;
 }
 
@@ -819,6 +822,7 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	st &= XDMA_CHAN_STATUS_MASK;
 	if ((st & XDMA_CHAN_ERROR_MASK) ||
 	    !(st & (CHAN_CTRL_IE_DESC_COMPLETED | CHAN_CTRL_IE_DESC_STOPPED))) {
+		desc->error = true;
 		xdma_err(xdev, "channel error, status register value: 0x%x", st);
 		goto out;
 	}
-- 
GitLab


From 3e184e64c2e5145e51dc57872b0a64e3a6736888 Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Mon, 18 Dec 2023 12:39:42 +0100
Subject: [PATCH 1811/4076] dmaengine: xilinx: xdma: Prepare the introduction
 of interleaved DMA transfers

Make generic code generic. As descriptor-filling logic stays the same
regardless of a dmaengine's type of transfer, it is possible to write
the descriptor-filling function in a generic way, so that it can be used
for every single type of transfer preparation callback.

Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Link: https://lore.kernel.org/r/20231218113943.9099-8-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 101 +++++++++++++++++++++-----------------
 1 file changed, 57 insertions(+), 44 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 9f8597ed9be24..618cc9af6eb94 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -542,6 +542,43 @@ static void xdma_synchronize(struct dma_chan *chan)
 	vchan_synchronize(&xdma_chan->vchan);
 }
 
+/**
+ * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses
+ * @sw_desc - tx descriptor state container
+ * @src_addr - Value for a ->src_addr field of a first descriptor
+ * @dst_addr - Value for a ->dst_addr field of a first descriptor
+ * @size - Total size of a contiguous memory block
+ * @filled_descs_num - Number of filled hardware descriptors for corresponding sw_desc
+ */
+static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr,
+				  u64 dst_addr, u32 size, u32 filled_descs_num)
+{
+	u32 left = size, len, desc_num = filled_descs_num;
+	struct xdma_desc_block *dblk;
+	struct xdma_hw_desc *desc;
+
+	dblk = sw_desc->desc_blocks + (desc_num / XDMA_DESC_ADJACENT);
+	desc = dblk->virt_addr;
+	desc += desc_num & XDMA_DESC_ADJACENT_MASK;
+	do {
+		len = min_t(u32, left, XDMA_DESC_BLEN_MAX);
+		/* set hardware descriptor */
+		desc->bytes = cpu_to_le32(len);
+		desc->src_addr = cpu_to_le64(src_addr);
+		desc->dst_addr = cpu_to_le64(dst_addr);
+		if (!(++desc_num & XDMA_DESC_ADJACENT_MASK))
+			desc = (++dblk)->virt_addr;
+		else
+			desc++;
+
+		src_addr += len;
+		dst_addr += len;
+		left -= len;
+	} while (left);
+
+	return desc_num - filled_descs_num;
+}
+
 /**
  * xdma_prep_device_sg - prepare a descriptor for a DMA transaction
  * @chan: DMA channel pointer
@@ -558,13 +595,10 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 {
 	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
 	struct dma_async_tx_descriptor *tx_desc;
-	u32 desc_num = 0, i, len, rest;
-	struct xdma_desc_block *dblk;
-	struct xdma_hw_desc *desc;
 	struct xdma_desc *sw_desc;
-	u64 dev_addr, *src, *dst;
+	u32 desc_num = 0, i;
+	u64 addr, dev_addr, *src, *dst;
 	struct scatterlist *sg;
-	u64 addr;
 
 	for_each_sg(sgl, sg, sg_len, i)
 		desc_num += DIV_ROUND_UP(sg_dma_len(sg), XDMA_DESC_BLEN_MAX);
@@ -584,32 +618,11 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		dst = &addr;
 	}
 
-	dblk = sw_desc->desc_blocks;
-	desc = dblk->virt_addr;
-	desc_num = 1;
+	desc_num = 0;
 	for_each_sg(sgl, sg, sg_len, i) {
 		addr = sg_dma_address(sg);
-		rest = sg_dma_len(sg);
-
-		do {
-			len = min_t(u32, rest, XDMA_DESC_BLEN_MAX);
-			/* set hardware descriptor */
-			desc->bytes = cpu_to_le32(len);
-			desc->src_addr = cpu_to_le64(*src);
-			desc->dst_addr = cpu_to_le64(*dst);
-
-			if (!(desc_num & XDMA_DESC_ADJACENT_MASK)) {
-				dblk++;
-				desc = dblk->virt_addr;
-			} else {
-				desc++;
-			}
-
-			desc_num++;
-			dev_addr += len;
-			addr += len;
-			rest -= len;
-		} while (rest);
+		desc_num += xdma_fill_descs(sw_desc, *src, *dst, sg_dma_len(sg), desc_num);
+		dev_addr += sg_dma_len(sg);
 	}
 
 	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -643,9 +656,9 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
 	struct xdma_device *xdev = xdma_chan->xdev_hdl;
 	unsigned int periods = size / period_size;
 	struct dma_async_tx_descriptor *tx_desc;
-	struct xdma_desc_block *dblk;
-	struct xdma_hw_desc *desc;
 	struct xdma_desc *sw_desc;
+	u64 addr, dev_addr, *src, *dst;
+	u32 desc_num;
 	unsigned int i;
 
 	/*
@@ -670,21 +683,21 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
 	sw_desc->period_size = period_size;
 	sw_desc->dir = dir;
 
-	dblk = sw_desc->desc_blocks;
-	desc = dblk->virt_addr;
+	addr = address;
+	if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = xdma_chan->cfg.dst_addr;
+		src = &addr;
+		dst = &dev_addr;
+	} else {
+		dev_addr = xdma_chan->cfg.src_addr;
+		src = &dev_addr;
+		dst = &addr;
+	}
 
-	/* fill hardware descriptor */
+	desc_num = 0;
 	for (i = 0; i < periods; i++) {
-		desc->bytes = cpu_to_le32(period_size);
-		if (dir == DMA_MEM_TO_DEV) {
-			desc->src_addr = cpu_to_le64(address + i * period_size);
-			desc->dst_addr = cpu_to_le64(xdma_chan->cfg.dst_addr);
-		} else {
-			desc->src_addr = cpu_to_le64(xdma_chan->cfg.src_addr);
-			desc->dst_addr = cpu_to_le64(address + i * period_size);
-		}
-
-		desc++;
+		desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num);
+		addr += i * period_size;
 	}
 
 	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
-- 
GitLab


From 2f8f90cd2f8d237c51c2775a53ef0d8c8acaa707 Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Mon, 18 Dec 2023 12:39:43 +0100
Subject: [PATCH 1812/4076] dmaengine: xilinx: xdma: Implement interleaved DMA
 transfers

Interleaved DMA functionality allows dmaengine clients' to express
DMA transfers in an arbitrary way. This is extremely useful in FPGA
environments, where a greater transfer flexibility is needed. For
instance, in one FPGA design there may be need to do DMA to/from a FIFO
at a fixed address, and also to do DMA to/from a (non)contiguous RAM
memory.

Introduce separate tx preparation callback and add tx-flags handling
logic. Their behavior is based on the description of interleaved DMA
transfers in both source code and the DMAEngine's documentation.

Since XDMA is a fully-fledged scatter-gather dma engine, the logic of
xdma_prep_interleaved_dma() is fairly simple and similar to the other
tx preparation callbacks. The whole tx-flags handling logic resides in
xdma_channel_isr(). Transfer of a single frame from a interleaved DMA
transfer template is pretty similar to the single sg transaction.
Therefore, the transaction of the whole interleaved DMA transfer
template is basically a cyclic dma transaction with finite cycles/periods
(equal to the frame of count) of a single sg transfers.

Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Link: https://lore.kernel.org/r/20231218113943.9099-9-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 107 ++++++++++++++++++++++++++++++++++----
 1 file changed, 98 insertions(+), 9 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 618cc9af6eb94..9360b85131ef9 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -83,8 +83,10 @@ struct xdma_chan {
  * @desc_num: Number of hardware descriptors
  * @completed_desc_num: Completed hardware descriptors
  * @cyclic: Cyclic transfer vs. scatter-gather
+ * @interleaved_dma: Interleaved DMA transfer
  * @periods: Number of periods in the cyclic transfer
  * @period_size: Size of a period in bytes in cyclic transfers
+ * @frames_left: Number of frames left in interleaved DMA transfer
  * @error: tx error flag
  */
 struct xdma_desc {
@@ -96,8 +98,10 @@ struct xdma_desc {
 	u32				desc_num;
 	u32				completed_desc_num;
 	bool				cyclic;
+	bool				interleaved_dma;
 	u32				periods;
 	u32				period_size;
+	u32				frames_left;
 	bool				error;
 };
 
@@ -607,6 +611,8 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (!sw_desc)
 		return NULL;
 	sw_desc->dir = dir;
+	sw_desc->cyclic = false;
+	sw_desc->interleaved_dma = false;
 
 	if (dir == DMA_MEM_TO_DEV) {
 		dev_addr = xdma_chan->cfg.dst_addr;
@@ -682,6 +688,7 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
 	sw_desc->periods = periods;
 	sw_desc->period_size = period_size;
 	sw_desc->dir = dir;
+	sw_desc->interleaved_dma = false;
 
 	addr = address;
 	if (dir == DMA_MEM_TO_DEV) {
@@ -712,6 +719,57 @@ failed:
 	return NULL;
 }
 
+/**
+ * xdma_prep_interleaved_dma - Prepare virtual descriptor for interleaved DMA transfers
+ * @chan: DMA channel
+ * @xt: DMA transfer template
+ * @flags: tx flags
+ */
+struct dma_async_tx_descriptor *
+xdma_prep_interleaved_dma(struct dma_chan *chan,
+			  struct dma_interleaved_template *xt,
+			  unsigned long flags)
+{
+	int i;
+	u32 desc_num = 0, period_size = 0;
+	struct dma_async_tx_descriptor *tx_desc;
+	struct xdma_chan *xchan = to_xdma_chan(chan);
+	struct xdma_desc *sw_desc;
+	u64 src_addr, dst_addr;
+
+	for (i = 0; i < xt->frame_size; ++i)
+		desc_num += DIV_ROUND_UP(xt->sgl[i].size, XDMA_DESC_BLEN_MAX);
+
+	sw_desc = xdma_alloc_desc(xchan, desc_num, false);
+	if (!sw_desc)
+		return NULL;
+	sw_desc->dir = xt->dir;
+	sw_desc->interleaved_dma = true;
+	sw_desc->cyclic = flags & DMA_PREP_REPEAT;
+	sw_desc->frames_left = xt->numf;
+	sw_desc->periods = xt->numf;
+
+	desc_num = 0;
+	src_addr = xt->src_start;
+	dst_addr = xt->dst_start;
+	for (i = 0; i < xt->frame_size; ++i) {
+		desc_num += xdma_fill_descs(sw_desc, src_addr, dst_addr, xt->sgl[i].size, desc_num);
+		src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + xt->src_inc ?
+							      xt->sgl[i].size : 0;
+		dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + xt->dst_inc ?
+							      xt->sgl[i].size : 0;
+		period_size += xt->sgl[i].size;
+	}
+	sw_desc->period_size = period_size;
+
+	tx_desc = vchan_tx_prep(&xchan->vchan, &sw_desc->vdesc, flags);
+	if (tx_desc)
+		return tx_desc;
+
+	xdma_free_desc(&sw_desc->vdesc);
+	return NULL;
+}
+
 /**
  * xdma_device_config - Configure the DMA channel
  * @chan: DMA channel
@@ -811,11 +869,12 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 {
 	struct xdma_chan *xchan = dev_id;
 	u32 complete_desc_num = 0;
-	struct xdma_device *xdev;
-	struct virt_dma_desc *vd;
+	struct xdma_device *xdev = xchan->xdev_hdl;
+	struct virt_dma_desc *vd, *next_vd;
 	struct xdma_desc *desc;
 	int ret;
 	u32 st;
+	bool repeat_tx;
 
 	spin_lock(&xchan->vchan.lock);
 
@@ -824,9 +883,6 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	if (!vd)
 		goto out;
 
-	desc = to_xdma_desc(vd);
-	xdev = xchan->xdev_hdl;
-
 	/* Clear-on-read the status register */
 	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &st);
 	if (ret)
@@ -845,10 +901,36 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	if (ret)
 		goto out;
 
-	if (desc->cyclic) {
-		desc->completed_desc_num = complete_desc_num;
-		vchan_cyclic_callback(vd);
-	} else {
+	desc = to_xdma_desc(vd);
+	if (desc->interleaved_dma) {
+		xchan->busy = false;
+		desc->completed_desc_num += complete_desc_num;
+		if (complete_desc_num == XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT) {
+			xdma_xfer_start(xchan);
+			goto out;
+		}
+
+		/* last desc of any frame */
+		desc->frames_left--;
+		if (desc->frames_left)
+			goto out;
+
+		/* last desc of the last frame  */
+		repeat_tx = vd->tx.flags & DMA_PREP_REPEAT;
+		next_vd = list_first_entry_or_null(&vd->node, struct virt_dma_desc, node);
+		if (next_vd)
+			repeat_tx = repeat_tx && !(next_vd->tx.flags & DMA_PREP_LOAD_EOT);
+		if (repeat_tx) {
+			desc->frames_left = desc->periods;
+			desc->completed_desc_num = 0;
+			vchan_cyclic_callback(vd);
+		} else {
+			list_del(&vd->node);
+			vchan_cookie_complete(vd);
+		}
+		/* start (or continue) the tx of a first desc on the vc.desc_issued list, if any */
+		xdma_xfer_start(xchan);
+	} else if (!desc->cyclic) {
 		xchan->busy = false;
 		desc->completed_desc_num += complete_desc_num;
 
@@ -865,6 +947,9 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 
 		/* transfer the rest of data */
 		xdma_xfer_start(xchan);
+	} else {
+		desc->completed_desc_num = complete_desc_num;
+		vchan_cyclic_callback(vd);
 	}
 
 out:
@@ -1163,6 +1248,9 @@ static int xdma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_SLAVE, xdev->dma_dev.cap_mask);
 	dma_cap_set(DMA_PRIVATE, xdev->dma_dev.cap_mask);
 	dma_cap_set(DMA_CYCLIC, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_REPEAT, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_LOAD_EOT, xdev->dma_dev.cap_mask);
 
 	xdev->dma_dev.dev = &pdev->dev;
 	xdev->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
@@ -1178,6 +1266,7 @@ static int xdma_probe(struct platform_device *pdev)
 	xdev->dma_dev.filter.mapcnt = pdata->device_map_cnt;
 	xdev->dma_dev.filter.fn = xdma_filter_fn;
 	xdev->dma_dev.device_prep_dma_cyclic = xdma_prep_dma_cyclic;
+	xdev->dma_dev.device_prep_interleaved_dma = xdma_prep_interleaved_dma;
 
 	ret = dma_async_device_register(&xdev->dma_dev);
 	if (ret) {
-- 
GitLab


From 22a9d9585812440211b0b34a6bc02ade62314be4 Mon Sep 17 00:00:00 2001
From: Bumyong Lee <bumyong.lee@samsung.com>
Date: Tue, 19 Dec 2023 14:50:26 +0900
Subject: [PATCH 1813/4076] dmaengine: pl330: issue_pending waits until WFP
 state

According to DMA-330 errata notice[1] 71930, DMAKILL
cannot clear internal signal, named pipeline_req_active.
it makes that pl330 would wait forever in WFP state
although dma already send dma request if pl330 gets
dma request before entering WFP state.

The errata suggests that polling until entering WFP state
as workaround and then peripherals allows to issue dma request.

[1]: https://developer.arm.com/documentation/genc008428/latest

Signed-off-by: Bumyong Lee <bumyong.lee@samsung.com>
Link: https://lore.kernel.org/r/20231219055026.118695-1-bumyong.lee@samsung.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/pl330.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 3cf0b38387ae5..c29744bfdf2c2 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1053,6 +1053,9 @@ static bool _trigger(struct pl330_thread *thrd)
 
 	thrd->req_running = idx;
 
+	if (desc->rqtype == DMA_MEM_TO_DEV || desc->rqtype == DMA_DEV_TO_MEM)
+		UNTIL(thrd, PL330_STATE_WFP);
+
 	return true;
 }
 
-- 
GitLab


From 7b95382f965133ef61ce44aaabc518c16eb46909 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Dec 2023 11:15:09 +0000
Subject: [PATCH 1814/4076] KVM: arm64: vgic-v4: Restore pending state on host
 userspace write

When the VMM writes to ISPENDR0 to set the state pending state of
an SGI, we fail to convey this to the HW if this SGI is already
backed by a GICv4.1 vSGI.

This is a bit of a corner case, as this would only occur if the
vgic state is changed on an already running VM, but this can
apparently happen across a guest reset driven by the VMM.

Fix this by always writing out the pending_latch value to the
HW, and reseting it to false.

Reported-by: Kunkun Jiang <jiangkunkun@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Cc: stable@vger.kernel.org # 5.10+
Link: https://lore.kernel.org/r/7e7f2c0c-448b-10a9-8929-4b8f4f6e2a32@huawei.com
---
 arch/arm64/kvm/vgic/vgic-mmio-v3.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 89117ba2528a0..111bd7f427292 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -365,19 +365,26 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		if (test_bit(i, &val)) {
-			/*
-			 * pending_latch is set irrespective of irq type
-			 * (level or edge) to avoid dependency that VM should
-			 * restore irq config before pending info.
-			 */
-			irq->pending_latch = true;
-			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
-		} else {
+
+		/*
+		 * pending_latch is set irrespective of irq type
+		 * (level or edge) to avoid dependency that VM should
+		 * restore irq config before pending info.
+		 */
+		irq->pending_latch = test_bit(i, &val);
+
+		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
+			irq_set_irqchip_state(irq->host_irq,
+					      IRQCHIP_STATE_PENDING,
+					      irq->pending_latch);
 			irq->pending_latch = false;
-			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		}
 
+		if (irq->pending_latch)
+			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
+		else
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 
-- 
GitLab


From 13886f34444596e6eca124677cd8362a941b585b Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Tue, 19 Dec 2023 06:58:53 +0000
Subject: [PATCH 1815/4076] KVM: arm64: vgic: Use common accessor for writes to
 ISPENDR

Perhaps unsurprisingly, there is a considerable amount of duplicate
code between the MMIO and user accessors for ISPENDR. At the same
time there are some important differences between user and guest
MMIO, like how SGIs can only be made pending from userspace.

Fold user and MMIO accessors into a common helper, maintaining the
distinction between the two.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231219065855.1019608-2-oliver.upton@linux.dev
---
 arch/arm64/kvm/vgic/vgic-mmio.c | 50 ++++++++++++++-------------------
 1 file changed, 21 insertions(+), 29 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c
index ff558c05e990c..273912083056a 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio.c
@@ -301,9 +301,8 @@ static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 		vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2);
 }
 
-void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
-			      gpa_t addr, unsigned int len,
-			      unsigned long val)
+static void __set_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len,
+			  unsigned long val, bool is_user)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
@@ -312,14 +311,22 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		/* GICD_ISPENDR0 SGI bits are WI */
-		if (is_vgic_v2_sgi(vcpu, irq)) {
+		/* GICD_ISPENDR0 SGI bits are WI when written from the guest. */
+		if (is_vgic_v2_sgi(vcpu, irq) && !is_user) {
 			vgic_put_irq(vcpu->kvm, irq);
 			continue;
 		}
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
+		/*
+		 * GICv2 SGIs are terribly broken. We can't restore
+		 * the source of the interrupt, so just pick the vcpu
+		 * itself as the source...
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source |= BIT(vcpu->vcpu_id);
+
 		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
 			/* HW SGI? Ask the GIC to inject it */
 			int err;
@@ -335,7 +342,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 		}
 
 		irq->pending_latch = true;
-		if (irq->hw)
+		if (irq->hw && !is_user)
 			vgic_irq_set_phys_active(irq, true);
 
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
@@ -343,33 +350,18 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 	}
 }
 
+void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
+			      gpa_t addr, unsigned int len,
+			      unsigned long val)
+{
+	__set_pending(vcpu, addr, len, val, false);
+}
+
 int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
 				gpa_t addr, unsigned int len,
 				unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for_each_set_bit(i, &val, len * 8) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		irq->pending_latch = true;
-
-		/*
-		 * GICv2 SGIs are terribly broken. We can't restore
-		 * the source of the interrupt, so just pick the vcpu
-		 * itself as the source...
-		 */
-		if (is_vgic_v2_sgi(vcpu, irq))
-			irq->source |= BIT(vcpu->vcpu_id);
-
-		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
-
-		vgic_put_irq(vcpu->kvm, irq);
-	}
-
+	__set_pending(vcpu, addr, len, val, true);
 	return 0;
 }
 
-- 
GitLab


From 561851424d93e91083df4071781b68dc4ba1fc5a Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Tue, 19 Dec 2023 06:58:54 +0000
Subject: [PATCH 1816/4076] KVM: arm64: vgic: Use common accessor for writes to
 ICPENDR

Fold MMIO and user accessors into a common helper while maintaining the
distinction between the two.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231219065855.1019608-3-oliver.upton@linux.dev
---
 arch/arm64/kvm/vgic/vgic-mmio.c | 51 ++++++++++++++-------------------
 1 file changed, 22 insertions(+), 29 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c
index 273912083056a..cf76523a21945 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio.c
@@ -386,9 +386,9 @@ static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 		vgic_irq_set_phys_active(irq, false);
 }
 
-void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
-			      gpa_t addr, unsigned int len,
-			      unsigned long val)
+static void __clear_pending(struct kvm_vcpu *vcpu,
+			    gpa_t addr, unsigned int len,
+			    unsigned long val, bool is_user)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
@@ -397,14 +397,22 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		/* GICD_ICPENDR0 SGI bits are WI */
-		if (is_vgic_v2_sgi(vcpu, irq)) {
+		/* GICD_ICPENDR0 SGI bits are WI when written from the guest. */
+		if (is_vgic_v2_sgi(vcpu, irq) && !is_user) {
 			vgic_put_irq(vcpu->kvm, irq);
 			continue;
 		}
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
+		/*
+		 * More fun with GICv2 SGIs! If we're clearing one of them
+		 * from userspace, which source vcpu to clear? Let's not
+		 * even think of it, and blow the whole set.
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source = 0;
+
 		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
 			/* HW SGI? Ask the GIC to clear its pending bit */
 			int err;
@@ -419,7 +427,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			continue;
 		}
 
-		if (irq->hw)
+		if (irq->hw && !is_user)
 			vgic_hw_irq_cpending(vcpu, irq);
 		else
 			irq->pending_latch = false;
@@ -429,33 +437,18 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	}
 }
 
+void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
+			      gpa_t addr, unsigned int len,
+			      unsigned long val)
+{
+	__clear_pending(vcpu, addr, len, val, false);
+}
+
 int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
 				gpa_t addr, unsigned int len,
 				unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for_each_set_bit(i, &val, len * 8) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		/*
-		 * More fun with GICv2 SGIs! If we're clearing one of them
-		 * from userspace, which source vcpu to clear? Let's not
-		 * even think of it, and blow the whole set.
-		 */
-		if (is_vgic_v2_sgi(vcpu, irq))
-			irq->source = 0;
-
-		irq->pending_latch = false;
-
-		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
-
-		vgic_put_irq(vcpu->kvm, irq);
-	}
-
+	__clear_pending(vcpu, addr, len, val, true);
 	return 0;
 }
 
-- 
GitLab


From 39084ba8d0fceb477a264e2bb8dfd3553876b84c Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Tue, 19 Dec 2023 06:58:55 +0000
Subject: [PATCH 1817/4076] KVM: arm64: vgic-v3: Reinterpret user ISPENDR
 writes as I{C,S}PENDR

User writes to ISPENDR for GICv3 are treated specially, as zeroes
actually clear the pending state for interrupts (unlike HW). Reimplement
it using the ISPENDR and ICPENDR user accessors.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231219065855.1019608-4-oliver.upton@linux.dev
---
 arch/arm64/kvm/vgic/vgic-mmio-v3.c | 35 +++++-------------------------
 1 file changed, 5 insertions(+), 30 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 111bd7f427292..2962ccd8013a2 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -357,38 +357,13 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
 					 gpa_t addr, unsigned int len,
 					 unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for (i = 0; i < len * 8; i++) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-
-		/*
-		 * pending_latch is set irrespective of irq type
-		 * (level or edge) to avoid dependency that VM should
-		 * restore irq config before pending info.
-		 */
-		irq->pending_latch = test_bit(i, &val);
-
-		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
-			irq_set_irqchip_state(irq->host_irq,
-					      IRQCHIP_STATE_PENDING,
-					      irq->pending_latch);
-			irq->pending_latch = false;
-		}
-
-		if (irq->pending_latch)
-			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
-		else
-			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+	int ret;
 
-		vgic_put_irq(vcpu->kvm, irq);
-	}
+	ret = vgic_uaccess_write_spending(vcpu, addr, len, val);
+	if (ret)
+		return ret;
 
-	return 0;
+	return vgic_uaccess_write_cpending(vcpu, addr, len, ~val);
 }
 
 /* We want to avoid outer shareable. */
-- 
GitLab


From ba2a2a86de04e67bb1d7f8251894eb11eed062e9 Mon Sep 17 00:00:00 2001
From: Gil Fine <gil.fine@linux.intel.com>
Date: Mon, 4 Dec 2023 15:14:58 +0200
Subject: [PATCH 1818/4076] thunderbolt: Keep link as asymmetric if preferred
 by hardware

In case of the link is brought up as asymmetric (due to hardware preference), we
honor that and don't transition it to symmetric, unless a router with symmetric
link got plugged below, in the topology (and a bandwidth allows transition to
symmetric).

Signed-off-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/switch.c | 13 +++++++++++++
 drivers/thunderbolt/tb.c     | 28 +++++++++++++++++++++-------
 drivers/thunderbolt/tb.h     |  2 ++
 3 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 7873b173a3517..e5a622b9acc3c 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -2773,6 +2773,19 @@ static void tb_switch_link_init(struct tb_switch *sw)
 	if (down->dual_link_port)
 		down->dual_link_port->bonded = bonded;
 	tb_port_update_credits(down);
+
+	if (tb_port_get_link_generation(up) < 4)
+		return;
+
+	/*
+	 * Set the Gen 4 preferred link width. This is what the router
+	 * prefers when the link is brought up. If the router does not
+	 * support asymmetric link configuration, this also will be set
+	 * to TB_LINK_WIDTH_DUAL.
+	 */
+	sw->preferred_link_width = sw->link_width;
+	tb_sw_dbg(sw, "preferred link width %s\n",
+		  tb_width_name(sw->preferred_link_width));
 }
 
 /**
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index bd211e97ee4bd..825cc2f4d8eff 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -1173,14 +1173,15 @@ static int tb_configure_asym(struct tb *tb, struct tb_port *src_port,
  * @dst_port: Destination adapter
  * @requested_up: New lower bandwidth request upstream (Mb/s)
  * @requested_down: New lower bandwidth request downstream (Mb/s)
+ * @keep_asym: Keep asymmetric link if preferred
  *
  * Goes over each link from @src_port to @dst_port and tries to
  * transition the link to symmetric if the currently consumed bandwidth
- * allows.
+ * allows and link asymmetric preference is ignored (if @keep_asym is %false).
  */
 static int tb_configure_sym(struct tb *tb, struct tb_port *src_port,
 			    struct tb_port *dst_port, int requested_up,
-			    int requested_down)
+			    int requested_down, bool keep_asym)
 {
 	bool clx = false, clx_disabled = false, downstream;
 	struct tb_switch *sw;
@@ -1229,6 +1230,19 @@ static int tb_configure_sym(struct tb *tb, struct tb_port *src_port,
 		if (up->sw->link_width == TB_LINK_WIDTH_DUAL)
 			continue;
 
+		/*
+		 * Here consumed < threshold so we can transition the
+		 * link to symmetric.
+		 *
+		 * However, if the router prefers asymmetric link we
+		 * honor that (unless @keep_asym is %false).
+		 */
+		if (keep_asym &&
+		    up->sw->preferred_link_width > TB_LINK_WIDTH_DUAL) {
+			tb_sw_dbg(up->sw, "keeping preferred asymmetric link\n");
+			continue;
+		}
+
 		/* Disable CL states before doing any transitions */
 		if (!clx_disabled) {
 			clx = tb_disable_clx(sw);
@@ -1282,7 +1296,7 @@ static void tb_configure_link(struct tb_port *down, struct tb_port *up,
 		struct tb_port *host_port;
 
 		host_port = tb_port_at(tb_route(sw), tb->root_switch);
-		tb_configure_sym(tb, host_port, up, 0, 0);
+		tb_configure_sym(tb, host_port, up, 0, 0, false);
 	}
 
 	/* Set the link configured */
@@ -1467,7 +1481,7 @@ static void tb_deactivate_and_free_tunnel(struct tb_tunnel *tunnel)
 		 * If bandwidth on a link is < asym_threshold
 		 * transition the link to symmetric.
 		 */
-		tb_configure_sym(tb, src_port, dst_port, 0, 0);
+		tb_configure_sym(tb, src_port, dst_port, 0, 0, true);
 		/* Now we can allow the domain to runtime suspend again */
 		pm_runtime_mark_last_busy(&dst_port->sw->dev);
 		pm_runtime_put_autosuspend(&dst_port->sw->dev);
@@ -2289,7 +2303,7 @@ static int tb_alloc_dp_bandwidth(struct tb_tunnel *tunnel, int *requested_up,
 		 * If bandwidth on a link is < asym_threshold transition
 		 * the link to symmetric.
 		 */
-		tb_configure_sym(tb, in, out, *requested_up, *requested_down);
+		tb_configure_sym(tb, in, out, *requested_up, *requested_down, true);
 		/*
 		 * If requested bandwidth is less or equal than what is
 		 * currently allocated to that tunnel we simply change
@@ -2332,7 +2346,7 @@ static int tb_alloc_dp_bandwidth(struct tb_tunnel *tunnel, int *requested_up,
 		ret = tb_configure_asym(tb, in, out, *requested_up,
 					*requested_down);
 		if (ret) {
-			tb_configure_sym(tb, in, out, 0, 0);
+			tb_configure_sym(tb, in, out, 0, 0, true);
 			return ret;
 		}
 
@@ -2340,7 +2354,7 @@ static int tb_alloc_dp_bandwidth(struct tb_tunnel *tunnel, int *requested_up,
 						requested_down);
 		if (ret) {
 			tb_tunnel_warn(tunnel, "failed to allocate bandwidth\n");
-			tb_configure_sym(tb, in, out, 0, 0);
+			tb_configure_sym(tb, in, out, 0, 0, true);
 		}
 	} else {
 		ret = -ENOBUFS;
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index 1760c21e5b12f..997c5a5369052 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -125,6 +125,7 @@ struct tb_switch_tmu {
  * @device_name: Name of the device (or %NULL if not known)
  * @link_speed: Speed of the link in Gb/s
  * @link_width: Width of the upstream facing link
+ * @preferred_link_width: Router preferred link width (only set for Gen 4 links)
  * @link_usb4: Upstream link is USB4
  * @generation: Switch Thunderbolt generation
  * @cap_plug_events: Offset to the plug events capability (%0 if not found)
@@ -178,6 +179,7 @@ struct tb_switch {
 	const char *device_name;
 	unsigned int link_speed;
 	enum tb_link_width link_width;
+	enum tb_link_width preferred_link_width;
 	bool link_usb4;
 	unsigned int generation;
 	int cap_plug_events;
-- 
GitLab


From 04b99eac389adc6485f7913d83ec9ed68bbc8326 Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Wed, 20 Dec 2023 16:09:56 +0100
Subject: [PATCH 1819/4076] thunderbolt: Reduce retry timeout to speed up boot
 for some devices

This is a followup to "thunderbolt: Workaround an IOMMU fault on certain
systems with Intel Maple Ridge".

It seems like the timeout can be reduced to 250ms. This reduces the overall
delay caused by the retires to ~1s. This is about the time other things
being initialized in parallel need anyway*, so like this the effective boot
time is no longer compromised.

*I only had a single device available for my measurements: A Clevo X170KM-G
desktop replacement notebook.

Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/icm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index d8b9c734abd36..56790d50f9e32 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -1020,7 +1020,7 @@ icm_tr_driver_ready(struct tb *tb, enum tb_security_level *security_level,
 
 	memset(&reply, 0, sizeof(reply));
 	ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply),
-			  1, 10, 2000);
+			  1, 10, 250);
 	if (ret)
 		return ret;
 
-- 
GitLab


From bbcd7b588b0bf967f90df60fccd16c9c49b768ea Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Fri, 22 Dec 2023 15:10:17 +0530
Subject: [PATCH 1820/4076] dmaengine: xilinx: xdma: Workaround truncation
 compilation error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Increase length to be copied to be large enough to overcome the
following compilation error. The buf is large enough for this purpose.

drivers/dma/xilinx/xilinx_dpdma.c: In function ‘xilinx_dpdma_debugfs_desc_done_irq_read’:
drivers/dma/xilinx/xilinx_dpdma.c:313:39: error: ‘snprintf’ output may be truncated before the last format character [-Werror=format-truncation=]
  313 |         snprintf(buf, out_str_len, "%d",
      |                                       ^
drivers/dma/xilinx/xilinx_dpdma.c:313:9: note: ‘snprintf’ output between 2 and 6 bytes into a destination of size 5
  313 |         snprintf(buf, out_str_len, "%d",
      |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  314 |                  dpdma_debugfs.xilinx_dpdma_irq_done_count);
      |                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20231222094017.731917-1-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xilinx_dpdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index 69587d85a7cd2..b82815e64d24e 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -309,7 +309,7 @@ static ssize_t xilinx_dpdma_debugfs_desc_done_irq_read(char *buf)
 
 	out_str_len = strlen(XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR);
 	out_str_len = min_t(size_t, XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE,
-			    out_str_len);
+			    out_str_len + 1);
 	snprintf(buf, out_str_len, "%d",
 		 dpdma_debugfs.xilinx_dpdma_irq_done_count);
 
-- 
GitLab


From 3d0b2176e04261ab4ac095ff2a17db077fc1e46d Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Fri, 22 Dec 2023 15:10:01 +0530
Subject: [PATCH 1821/4076] dmaengine: xilinx: xdma: statify
 xdma_prep_interleaved_dma

xdma_prep_interleaved_dma() was local to file but not declared static,
leading to warning:

drivers/dma/xilinx/xdma.c:729:1: warning: no previous prototype for 'xdma_prep_interleaved_dma' [-Wmissing-prototypes]
  729 | xdma_prep_interleaved_dma(struct dma_chan *chan

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20231222094001.731889-1-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 9360b85131ef9..4ebc90b41bdb9 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -725,7 +725,7 @@ failed:
  * @xt: DMA transfer template
  * @flags: tx flags
  */
-struct dma_async_tx_descriptor *
+static struct dma_async_tx_descriptor *
 xdma_prep_interleaved_dma(struct dma_chan *chan,
 			  struct dma_interleaved_template *xt,
 			  unsigned long flags)
-- 
GitLab


From d719915ad9706a16adde231789a1d46fc12fb9c7 Mon Sep 17 00:00:00 2001
From: Chintan Vankar <c-vankar@ti.com>
Date: Thu, 21 Dec 2023 15:59:55 +0530
Subject: [PATCH 1822/4076] phy: ti: gmii-sel: Enable SGMII mode for J784S4

TI's J784S4 SoC supports SGMII mode with the CPSW9G instance of the CPSW
Ethernet Switch. Thus, enable it by adding SGMII mode to the list of the
corresponding extra_modes member.

Signed-off-by: Chintan Vankar <c-vankar@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Link: https://lore.kernel.org/r/20231221102956.754617-1-c-vankar@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-gmii-sel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index 555b323f45da1..05004c8a758f2 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -247,7 +247,7 @@ static const
 struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j784s4 = {
 	.use_of_data = true,
 	.regfields = phy_gmii_sel_fields_am654,
-	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) |
+	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) |
 		       BIT(PHY_INTERFACE_MODE_USXGMII),
 	.num_ports = 8,
 	.num_qsgmii_main_ports = 2,
-- 
GitLab


From 2029e71482fcd94dcc7df2c66c7fa635479748bf Mon Sep 17 00:00:00 2001
From: Chintan Vankar <c-vankar@ti.com>
Date: Thu, 21 Dec 2023 15:59:56 +0530
Subject: [PATCH 1823/4076] phy: ti: j721e-wiz: Add SGMII support in WIZ driver
 for J784S4

Enable full rate divider configuration support for J784S4_WIZ_10G
for SGMII.

Signed-off-by: Chintan Vankar <c-vankar@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Link: https://lore.kernel.org/r/20231221102956.754617-2-c-vankar@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-j721e-wiz.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c
index fc3cd98c60ff4..00d7e6a6de03a 100644
--- a/drivers/phy/ti/phy-j721e-wiz.c
+++ b/drivers/phy/ti/phy-j721e-wiz.c
@@ -1240,6 +1240,7 @@ static int wiz_phy_fullrt_div(struct wiz *wiz, int lane)
 	case J721E_WIZ_10G:
 	case J7200_WIZ_10G:
 	case J721S2_WIZ_10G:
+	case J784S4_WIZ_10G:
 		if (wiz->lane_phy_type[lane] == PHY_TYPE_SGMII)
 			return regmap_field_write(wiz->p0_fullrt_div[lane], 0x2);
 		break;
-- 
GitLab


From 26547691107eda45b0f20ee79bad19bbe5fcbfd7 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Fri, 22 Dec 2023 11:35:22 -0500
Subject: [PATCH 1824/4076] tracing/selftests: Remove exec permissions from
 trace_marker.tc test

The tests in the selftests should not have the exec permissions set. The
trace_marker.tc test accidentally was committed with the exec permission.

Set the permission to that file back to just read/write.

No functional nor code changes.

Link: https://lore.kernel.org/linux-trace-kernel/20231222112831.4c7fa500@gandalf.local.home/

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 mode change 100755 => 100644 tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc

diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc
old mode 100755
new mode 100644
-- 
GitLab


From 60e43fe5285e2077ce9904d78cd42a230d03b788 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:02:31 -0700
Subject: [PATCH 1825/4076] lib/firmware_table: tables: Add CDAT table parsing
 support

The CDAT table is very similar to ACPI tables when it comes to sub-table
and entry structures. The helper functions can be also used to parse the
CDAT table. Add support to the helper functions to deal with an external
CDAT table, and also handle the endieness since CDAT can be processed by a
BE host. Export a function cdat_table_parse() for CXL driver to parse
a CDAT table.

In order to minimize ACPICA code changes, __force is being utilized to deal
with the case of a big endian (BE) host parsing a CDAT. All CDAT data
structure variables are being force casted to __leX as appropriate.

Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Len Brown <lenb@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/170319615131.2212653.10932785667981494238.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/tables.c    |  5 +--
 include/linux/fw_table.h | 21 ++++++++++-
 lib/fw_table.c           | 75 +++++++++++++++++++++++++++++++++-------
 3 files changed, 86 insertions(+), 15 deletions(-)

diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index c1516337f6682..b07f7d091d133 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -251,8 +251,9 @@ int __init_or_acpilib acpi_table_parse_entries_array(
 		return -ENODEV;
 	}
 
-	count = acpi_parse_entries_array(id, table_size, table_header,
-			proc, proc_num, max_entries);
+	count = acpi_parse_entries_array(id, table_size,
+					 (union fw_table_header *)table_header,
+					 proc, proc_num, max_entries);
 
 	acpi_put_table(table_header);
 	return count;
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index ca49947f0a775..95421860397a2 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -25,16 +25,35 @@ struct acpi_subtable_proc {
 	int count;
 };
 
+union fw_table_header {
+	struct acpi_table_header acpi;
+	struct acpi_table_cdat cdat;
+};
+
 union acpi_subtable_headers {
 	struct acpi_subtable_header common;
 	struct acpi_hmat_structure hmat;
 	struct acpi_prmt_module_header prmt;
 	struct acpi_cedt_header cedt;
+	struct acpi_cdat_header cdat;
 };
 
 int acpi_parse_entries_array(char *id, unsigned long table_size,
-			     struct acpi_table_header *table_header,
+			     union fw_table_header *table_header,
 			     struct acpi_subtable_proc *proc,
 			     int proc_num, unsigned int max_entries);
 
+int cdat_table_parse(enum acpi_cdat_type type,
+		     acpi_tbl_entry_handler_arg handler_arg, void *arg,
+		     struct acpi_table_cdat *table_header);
+
+/* CXL is the only non-ACPI consumer of the FIRMWARE_TABLE library */
+#if IS_ENABLED(CONFIG_ACPI) && !IS_ENABLED(CONFIG_CXL_BUS)
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_fwtbl_lib __init_or_acpilib
+#else
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, CXL)
+#define __init_or_fwtbl_lib
+#endif
+
 #endif
diff --git a/lib/fw_table.c b/lib/fw_table.c
index 294df54e33b6f..1e5e0b2f70120 100644
--- a/lib/fw_table.c
+++ b/lib/fw_table.c
@@ -12,12 +12,14 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/fw_table.h>
 
 enum acpi_subtable_type {
 	ACPI_SUBTABLE_COMMON,
 	ACPI_SUBTABLE_HMAT,
 	ACPI_SUBTABLE_PRMT,
 	ACPI_SUBTABLE_CEDT,
+	CDAT_SUBTABLE,
 };
 
 struct acpi_subtable_entry {
@@ -25,7 +27,7 @@ struct acpi_subtable_entry {
 	enum acpi_subtable_type type;
 };
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_entry_type(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -37,11 +39,13 @@ acpi_get_entry_type(struct acpi_subtable_entry *entry)
 		return 0;
 	case ACPI_SUBTABLE_CEDT:
 		return entry->hdr->cedt.type;
+	case CDAT_SUBTABLE:
+		return entry->hdr->cdat.type;
 	}
 	return 0;
 }
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_entry_length(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -53,11 +57,16 @@ acpi_get_entry_length(struct acpi_subtable_entry *entry)
 		return entry->hdr->prmt.length;
 	case ACPI_SUBTABLE_CEDT:
 		return entry->hdr->cedt.length;
+	case CDAT_SUBTABLE: {
+		__le16 length = (__force __le16)entry->hdr->cdat.length;
+
+		return le16_to_cpu(length);
+	}
 	}
 	return 0;
 }
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_subtable_header_length(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -69,11 +78,13 @@ acpi_get_subtable_header_length(struct acpi_subtable_entry *entry)
 		return sizeof(entry->hdr->prmt);
 	case ACPI_SUBTABLE_CEDT:
 		return sizeof(entry->hdr->cedt);
+	case CDAT_SUBTABLE:
+		return sizeof(entry->hdr->cdat);
 	}
 	return 0;
 }
 
-static enum acpi_subtable_type __init_or_acpilib
+static enum acpi_subtable_type __init_or_fwtbl_lib
 acpi_get_subtable_type(char *id)
 {
 	if (strncmp(id, ACPI_SIG_HMAT, 4) == 0)
@@ -82,17 +93,32 @@ acpi_get_subtable_type(char *id)
 		return ACPI_SUBTABLE_PRMT;
 	if (strncmp(id, ACPI_SIG_CEDT, 4) == 0)
 		return ACPI_SUBTABLE_CEDT;
+	if (strncmp(id, ACPI_SIG_CDAT, 4) == 0)
+		return CDAT_SUBTABLE;
 	return ACPI_SUBTABLE_COMMON;
 }
 
-static __init_or_acpilib bool has_handler(struct acpi_subtable_proc *proc)
+static unsigned long __init_or_fwtbl_lib
+acpi_table_get_length(enum acpi_subtable_type type,
+		      union fw_table_header *header)
+{
+	if (type == CDAT_SUBTABLE) {
+		__le32 length = (__force __le32)header->cdat.length;
+
+		return le32_to_cpu(length);
+	}
+
+	return header->acpi.length;
+}
+
+static __init_or_fwtbl_lib bool has_handler(struct acpi_subtable_proc *proc)
 {
 	return proc->handler || proc->handler_arg;
 }
 
-static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc,
-					  union acpi_subtable_headers *hdr,
-					  unsigned long end)
+static __init_or_fwtbl_lib int call_handler(struct acpi_subtable_proc *proc,
+					    union acpi_subtable_headers *hdr,
+					    unsigned long end)
 {
 	if (proc->handler)
 		return proc->handler(hdr, end);
@@ -124,23 +150,26 @@ static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc,
  * On success returns sum of all matching entries for all proc handlers.
  * Otherwise, -ENODEV or -EINVAL is returned.
  */
-int __init_or_acpilib
+int __init_or_fwtbl_lib
 acpi_parse_entries_array(char *id, unsigned long table_size,
-			 struct acpi_table_header *table_header,
+			 union fw_table_header *table_header,
 			 struct acpi_subtable_proc *proc,
 			 int proc_num, unsigned int max_entries)
 {
 	unsigned long table_end, subtable_len, entry_len;
 	struct acpi_subtable_entry entry;
+	enum acpi_subtable_type type;
 	int count = 0;
 	int errs = 0;
 	int i;
 
-	table_end = (unsigned long)table_header + table_header->length;
+	type = acpi_get_subtable_type(id);
+	table_end = (unsigned long)table_header +
+		    acpi_table_get_length(type, table_header);
 
 	/* Parse all entries looking for a match. */
 
-	entry.type = acpi_get_subtable_type(id);
+	entry.type = type;
 	entry.hdr = (union acpi_subtable_headers *)
 	    ((unsigned long)table_header + table_size);
 	subtable_len = acpi_get_subtable_header_length(&entry);
@@ -186,3 +215,25 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 
 	return errs ? -EINVAL : count;
 }
+
+int __init_or_fwtbl_lib
+cdat_table_parse(enum acpi_cdat_type type,
+		 acpi_tbl_entry_handler_arg handler_arg,
+		 void *arg,
+		 struct acpi_table_cdat *table_header)
+{
+	struct acpi_subtable_proc proc = {
+		.id		= type,
+		.handler_arg	= handler_arg,
+		.arg		= arg,
+	};
+
+	if (!table_header)
+		return -EINVAL;
+
+	return acpi_parse_entries_array(ACPI_SIG_CDAT,
+					sizeof(struct acpi_table_cdat),
+					(union fw_table_header *)table_header,
+					&proc, 1, 0);
+}
+EXPORT_SYMBOL_FWTBL_LIB(cdat_table_parse);
-- 
GitLab


From 6a954e94d038f41d79c4e04348c95774d1c9337d Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:02:37 -0700
Subject: [PATCH 1826/4076] base/node / acpi: Change 'node_hmem_attrs' to
 'access_coordinates'

Dan Williams suggested changing the struct 'node_hmem_attrs' to
'access_coordinates' [1]. The struct is a container of r/w-latency and
r/w-bandwidth numbers. Moving forward, this container will also be used by
CXL to store the performance characteristics of each link hop in
the PCIE/CXL topology. So, where node_hmem_attrs is just the access
parameters of a memory-node, access_coordinates applies more broadly
to hardware topology characteristics. The observation is that seemed like
an exercise in having the application identify "where" it falls on a
spectrum of bandwidth and latency needs. For the tuple of
read/write-latency and read/write-bandwidth, "coordinates" is not a perfect
fit. Sometimes it is just conveying values in isolation and not a
"location" relative to other performance points, but in the end this data
is used to identify the performance operation point of a given memory-node.
[2]

Link: http://lore.kernel.org/r/64471313421f7_1b66294d5@dwillia2-xfh.jf.intel.com.notmuch/
Link: https://lore.kernel.org/linux-cxl/645e6215ee0de_1e6f2945e@dwillia2-xfh.jf.intel.com.notmuch/
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/170319615734.2212653.15319394025985499185.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa/hmat.c     | 28 ++++++++++++++--------------
 drivers/base/node.c          | 12 ++++++------
 include/linux/memory-tiers.h | 10 +++++-----
 include/linux/node.h         |  8 ++++----
 mm/memory-tiers.c            | 12 ++++++------
 5 files changed, 35 insertions(+), 35 deletions(-)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 9ef5f1bdcfdbc..83bc2b69401bf 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -63,7 +63,7 @@ struct memory_target {
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
 	struct resource memregions;
-	struct node_hmem_attrs hmem_attrs[2];
+	struct access_coordinate coord[2];
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
 	bool registered;
@@ -228,24 +228,24 @@ static void hmat_update_target_access(struct memory_target *target,
 {
 	switch (type) {
 	case ACPI_HMAT_ACCESS_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].read_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_READ_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
+		target->coord[access].read_latency = value;
 		break;
 	case ACPI_HMAT_WRITE_LATENCY:
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_ACCESS_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	case ACPI_HMAT_READ_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
 		break;
 	case ACPI_HMAT_WRITE_BANDWIDTH:
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	default:
 		break;
@@ -681,7 +681,7 @@ static void hmat_register_target_cache(struct memory_target *target)
 static void hmat_register_target_perf(struct memory_target *target, int access)
 {
 	unsigned mem_nid = pxm_to_node(target->memory_pxm);
-	node_set_perf_attrs(mem_nid, &target->hmem_attrs[access], access);
+	node_set_perf_attrs(mem_nid, &target->coord[access], access);
 }
 
 static void hmat_register_target_devices(struct memory_target *target)
@@ -765,7 +765,7 @@ static int hmat_set_default_dram_perf(void)
 	int rc;
 	int nid, pxm;
 	struct memory_target *target;
-	struct node_hmem_attrs *attrs;
+	struct access_coordinate *attrs;
 
 	if (!default_dram_type)
 		return -EIO;
@@ -775,7 +775,7 @@ static int hmat_set_default_dram_perf(void)
 		target = find_mem_target(pxm);
 		if (!target)
 			continue;
-		attrs = &target->hmem_attrs[1];
+		attrs = &target->coord[1];
 		rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT");
 		if (rc)
 			return rc;
@@ -789,7 +789,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
 	struct memory_target *target;
-	struct node_hmem_attrs *perf;
+	struct access_coordinate *perf;
 	int *adist = data;
 	int pxm;
 
@@ -802,7 +802,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 	hmat_update_target_attrs(target, p_nodes, 1);
 	mutex_unlock(&target_lock);
 
-	perf = &target->hmem_attrs[1];
+	perf = &target->coord[1];
 
 	if (mt_perf_to_adistance(perf, adist))
 		return NOTIFY_OK;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 493d533f83755..cb2b6cc7f6e69 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -74,14 +74,14 @@ static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
  * @dev:	Device for this memory access class
  * @list_node:	List element in the node's access list
  * @access:	The access class rank
- * @hmem_attrs: Heterogeneous memory performance attributes
+ * @coord:	Heterogeneous memory performance coordinates
  */
 struct node_access_nodes {
 	struct device		dev;
 	struct list_head	list_node;
 	unsigned int		access;
 #ifdef CONFIG_HMEM_REPORTING
-	struct node_hmem_attrs	hmem_attrs;
+	struct access_coordinate	coord;
 #endif
 };
 #define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev)
@@ -167,7 +167,7 @@ static ssize_t property##_show(struct device *dev,			\
 			   char *buf)					\
 {									\
 	return sysfs_emit(buf, "%u\n",					\
-			  to_access_nodes(dev)->hmem_attrs.property);	\
+			  to_access_nodes(dev)->coord.property);	\
 }									\
 static DEVICE_ATTR_RO(property)
 
@@ -187,10 +187,10 @@ static struct attribute *access_attrs[] = {
 /**
  * node_set_perf_attrs - Set the performance values for given access class
  * @nid: Node identifier to be set
- * @hmem_attrs: Heterogeneous memory performance attributes
+ * @coord: Heterogeneous memory performance coordinates
  * @access: The access class the for the given attributes
  */
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 			 unsigned int access)
 {
 	struct node_access_nodes *c;
@@ -205,7 +205,7 @@ void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
 	if (!c)
 		return;
 
-	c->hmem_attrs = *hmem_attrs;
+	c->coord = *coord;
 	for (i = 0; access_attrs[i] != NULL; i++) {
 		if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i],
 					    "initiators")) {
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 1e39d27bee418..69e7819000827 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -33,7 +33,7 @@ struct memory_dev_type {
 	struct kref kref;
 };
 
-struct node_hmem_attrs;
+struct access_coordinate;
 
 #ifdef CONFIG_NUMA
 extern bool numa_demotion_enabled;
@@ -45,9 +45,9 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype);
 int register_mt_adistance_algorithm(struct notifier_block *nb);
 int unregister_mt_adistance_algorithm(struct notifier_block *nb);
 int mt_calc_adistance(int node, int *adist);
-int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source);
-int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist);
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -126,13 +126,13 @@ static inline int mt_calc_adistance(int node, int *adist)
 	return NOTIFY_DONE;
 }
 
-static inline int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+static inline int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 					   const char *source)
 {
 	return -EIO;
 }
 
-static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 {
 	return -EIO;
 }
diff --git a/include/linux/node.h b/include/linux/node.h
index 427a5975cf405..25b66d705ee2e 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -20,14 +20,14 @@
 #include <linux/list.h>
 
 /**
- * struct node_hmem_attrs - heterogeneous memory performance attributes
+ * struct access_coordinate - generic performance coordinates container
  *
  * @read_bandwidth:	Read bandwidth in MB/s
  * @write_bandwidth:	Write bandwidth in MB/s
  * @read_latency:	Read latency in nanoseconds
  * @write_latency:	Write latency in nanoseconds
  */
-struct node_hmem_attrs {
+struct access_coordinate {
 	unsigned int read_bandwidth;
 	unsigned int write_bandwidth;
 	unsigned int read_latency;
@@ -65,7 +65,7 @@ struct node_cache_attrs {
 
 #ifdef CONFIG_HMEM_REPORTING
 void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs);
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 			 unsigned access);
 #else
 static inline void node_add_cache(unsigned int nid,
@@ -74,7 +74,7 @@ static inline void node_add_cache(unsigned int nid,
 }
 
 static inline void node_set_perf_attrs(unsigned int nid,
-				       struct node_hmem_attrs *hmem_attrs,
+				       struct access_coordinate *coord,
 				       unsigned access)
 {
 }
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 8d5291add2bce..5462d9e3c84c7 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -109,7 +109,7 @@ static struct demotion_nodes *node_demotion __read_mostly;
 static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms);
 
 static bool default_dram_perf_error;
-static struct node_hmem_attrs default_dram_perf;
+static struct access_coordinate default_dram_perf;
 static int default_dram_perf_ref_nid = NUMA_NO_NODE;
 static const char *default_dram_perf_ref_source;
 
@@ -601,15 +601,15 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype)
 }
 EXPORT_SYMBOL_GPL(clear_node_memory_type);
 
-static void dump_hmem_attrs(struct node_hmem_attrs *attrs, const char *prefix)
+static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix)
 {
 	pr_info(
 "%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n",
-		prefix, attrs->read_latency, attrs->write_latency,
-		attrs->read_bandwidth, attrs->write_bandwidth);
+		prefix, coord->read_latency, coord->write_latency,
+		coord->read_bandwidth, coord->write_bandwidth);
 }
 
-int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source)
 {
 	int rc = 0;
@@ -666,7 +666,7 @@ out:
 	return rc;
 }
 
-int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 {
 	if (default_dram_perf_error)
 		return -EIO;
-- 
GitLab


From 69b789b64456093819f730b3f9c13a593a5485d9 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:02:43 -0700
Subject: [PATCH 1827/4076] acpi: numa: Create enum for memory_target access
 coordinates indexing

Create enums to provide named indexing for the access coordinate array.
This is in preparation for adding generic port support which will add a
third index in the array to keep the generic port attributes separate from
the memory attributes.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/170319616332.2212653.3872789279950567889.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa/hmat.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 83bc2b69401bf..ca7aedfbb5f2d 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -58,12 +58,18 @@ struct target_cache {
 	struct node_cache_attrs cache_attrs;
 };
 
+enum {
+	NODE_ACCESS_CLASS_0 = 0,
+	NODE_ACCESS_CLASS_1,
+	NODE_ACCESS_CLASS_MAX,
+};
+
 struct memory_target {
 	struct list_head node;
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
 	struct resource memregions;
-	struct access_coordinate coord[2];
+	struct access_coordinate coord[NODE_ACCESS_CLASS_MAX];
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
 	bool registered;
@@ -339,10 +345,12 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 			if (mem_hier == ACPI_HMAT_MEMORY) {
 				target = find_mem_target(targs[targ]);
 				if (target && target->processor_pxm == inits[init]) {
-					hmat_update_target_access(target, type, value, 0);
+					hmat_update_target_access(target, type, value,
+								  NODE_ACCESS_CLASS_0);
 					/* If the node has a CPU, update access 1 */
 					if (node_state(pxm_to_node(inits[init]), N_CPU))
-						hmat_update_target_access(target, type, value, 1);
+						hmat_update_target_access(target, type, value,
+									  NODE_ACCESS_CLASS_1);
 				}
 			}
 		}
@@ -726,8 +734,8 @@ static void hmat_register_target(struct memory_target *target)
 	if (!target->registered) {
 		hmat_register_target_initiators(target);
 		hmat_register_target_cache(target);
-		hmat_register_target_perf(target, 0);
-		hmat_register_target_perf(target, 1);
+		hmat_register_target_perf(target, NODE_ACCESS_CLASS_0);
+		hmat_register_target_perf(target, NODE_ACCESS_CLASS_1);
 		target->registered = true;
 	}
 	mutex_unlock(&target_lock);
-- 
GitLab


From 6373c48b8c9dfb5c1e09fdb538e700d9cc91c45e Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:02:49 -0700
Subject: [PATCH 1828/4076] acpi: numa: Add genport target allocation to the
 HMAT parsing

Add SRAT parsing for the HMAT init in order to collect the device handle
from the Generic Port Affinity Structure. The device handle will serve as
the key to search for target data.

Consolidate the common code with alloc_memory_target() in a helper function
alloc_target().

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/170319616951.2212653.14862375982250406464.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa/hmat.c | 59 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 56 insertions(+), 3 deletions(-)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index ca7aedfbb5f2d..21722cbec324d 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -72,6 +72,7 @@ struct memory_target {
 	struct access_coordinate coord[NODE_ACCESS_CLASS_MAX];
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
+	u8 gen_port_device_handle[ACPI_SRAT_DEVICE_HANDLE_SIZE];
 	bool registered;
 };
 
@@ -126,8 +127,7 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 	list_add_tail(&initiator->node, &initiators);
 }
 
-static __init void alloc_memory_target(unsigned int mem_pxm,
-		resource_size_t start, resource_size_t len)
+static __init struct memory_target *alloc_target(unsigned int mem_pxm)
 {
 	struct memory_target *target;
 
@@ -135,7 +135,7 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 	if (!target) {
 		target = kzalloc(sizeof(*target), GFP_KERNEL);
 		if (!target)
-			return;
+			return NULL;
 		target->memory_pxm = mem_pxm;
 		target->processor_pxm = PXM_INVAL;
 		target->memregions = (struct resource) {
@@ -148,6 +148,19 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 		INIT_LIST_HEAD(&target->caches);
 	}
 
+	return target;
+}
+
+static __init void alloc_memory_target(unsigned int mem_pxm,
+				       resource_size_t start,
+				       resource_size_t len)
+{
+	struct memory_target *target;
+
+	target = alloc_target(mem_pxm);
+	if (!target)
+		return;
+
 	/*
 	 * There are potentially multiple ranges per PXM, so record each
 	 * in the per-target memregions resource tree.
@@ -158,6 +171,18 @@ static __init void alloc_memory_target(unsigned int mem_pxm,
 				start, start + len, mem_pxm);
 }
 
+static __init void alloc_genport_target(unsigned int mem_pxm, u8 *handle)
+{
+	struct memory_target *target;
+
+	target = alloc_target(mem_pxm);
+	if (!target)
+		return;
+
+	memcpy(target->gen_port_device_handle, handle,
+	       ACPI_SRAT_DEVICE_HANDLE_SIZE);
+}
+
 static __init const char *hmat_data_type(u8 type)
 {
 	switch (type) {
@@ -499,6 +524,27 @@ static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
 	return 0;
 }
 
+static __init int srat_parse_genport_affinity(union acpi_subtable_headers *header,
+					      const unsigned long end)
+{
+	struct acpi_srat_generic_affinity *ga = (void *)header;
+
+	if (!ga)
+		return -EINVAL;
+
+	if (!(ga->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED))
+		return 0;
+
+	/* Skip PCI device_handle for now */
+	if (ga->device_handle_type != 0)
+		return 0;
+
+	alloc_genport_target(ga->proximity_domain,
+			     (u8 *)ga->device_handle);
+
+	return 0;
+}
+
 static u32 hmat_initiator_perf(struct memory_target *target,
 			       struct memory_initiator *initiator,
 			       struct acpi_hmat_locality *hmat_loc)
@@ -878,6 +924,13 @@ static __init int hmat_init(void)
 				ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 				srat_parse_mem_affinity, 0) < 0)
 		goto out_put;
+
+	if (acpi_table_parse_entries(ACPI_SIG_SRAT,
+				     sizeof(struct acpi_table_srat),
+				     ACPI_SRAT_TYPE_GENERIC_PORT_AFFINITY,
+				     srat_parse_genport_affinity, 0) < 0)
+		goto out_put;
+
 	acpi_put_table(tbl);
 
 	status = acpi_get_table(ACPI_SIG_HMAT, 0, &tbl);
-- 
GitLab


From 79205651120620c2683f90c25ef3d2ac8e454026 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:02:55 -0700
Subject: [PATCH 1829/4076] acpi: Break out nesting for hmat_parse_locality()

Refactor hmat_parse_locality() to break up the deep nesting of the
function.

Suggested-by: Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/170319617537.2212653.10625501075519862509.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa/hmat.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 21722cbec324d..4cae2e84251a2 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -322,11 +322,28 @@ static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc)
 	}
 }
 
+static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_pxm,
+				      u8 mem_hier, u8 type, u32 value)
+{
+	struct memory_target *target = find_mem_target(tgt_pxm);
+
+	if (mem_hier != ACPI_HMAT_MEMORY)
+		return;
+
+	if (target && target->processor_pxm == init_pxm) {
+		hmat_update_target_access(target, type, value,
+					  NODE_ACCESS_CLASS_0);
+		/* If the node has a CPU, update access 1 */
+		if (node_state(pxm_to_node(init_pxm), N_CPU))
+			hmat_update_target_access(target, type, value,
+						  NODE_ACCESS_CLASS_1);
+	}
+}
+
 static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 				      const unsigned long end)
 {
 	struct acpi_hmat_locality *hmat_loc = (void *)header;
-	struct memory_target *target;
 	unsigned int init, targ, total_size, ipds, tpds;
 	u32 *inits, *targs, value;
 	u16 *entries;
@@ -367,17 +384,8 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 				inits[init], targs[targ], value,
 				hmat_data_type_suffix(type));
 
-			if (mem_hier == ACPI_HMAT_MEMORY) {
-				target = find_mem_target(targs[targ]);
-				if (target && target->processor_pxm == inits[init]) {
-					hmat_update_target_access(target, type, value,
-								  NODE_ACCESS_CLASS_0);
-					/* If the node has a CPU, update access 1 */
-					if (node_state(pxm_to_node(inits[init]), N_CPU))
-						hmat_update_target_access(target, type, value,
-									  NODE_ACCESS_CLASS_1);
-				}
-			}
+			hmat_update_target(targs[targ], inits[init],
+					   mem_hier, type, value);
 		}
 	}
 
-- 
GitLab


From a3a3e341f169511823f7b2d140a0bdfbd620dcbd Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:01 -0700
Subject: [PATCH 1830/4076] acpi: numa: Add setting of generic port system
 locality attributes

Add generic port support for the parsing of HMAT system locality sub-table.
The attributes will be added to the third array member of the access
coordinates in order to not mix with the existing memory attributes. It
only provides the system locality attributes from initiator to the
generic port targets and is missing the rest of the data to the actual
memory device.

The complete attributes will be updated when a memory device is
attached and the system locality information is calculated end to end.

Through hmat_update_target_attrs(), the best performance attributes will
be setup in target->coord.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/170319618135.2212653.13778540010384821833.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa/hmat.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 4cae2e84251a2..8a1802e078f3c 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -61,6 +61,7 @@ struct target_cache {
 enum {
 	NODE_ACCESS_CLASS_0 = 0,
 	NODE_ACCESS_CLASS_1,
+	NODE_ACCESS_CLASS_GENPORT_SINK,
 	NODE_ACCESS_CLASS_MAX,
 };
 
@@ -654,6 +655,11 @@ static void hmat_update_target_attrs(struct memory_target *target,
 	u32 best = 0;
 	int i;
 
+	/* Don't update for generic port if there's no device handle */
+	if (access == NODE_ACCESS_CLASS_GENPORT_SINK &&
+	    !(*(u16 *)target->gen_port_device_handle))
+		return;
+
 	bitmap_zero(p_nodes, MAX_NUMNODES);
 	/*
 	 * If the Address Range Structure provides a local processor pxm, set
@@ -723,6 +729,14 @@ static void __hmat_register_target_initiators(struct memory_target *target,
 	}
 }
 
+static void hmat_register_generic_target_initiators(struct memory_target *target)
+{
+	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
+
+	__hmat_register_target_initiators(target, p_nodes,
+					  NODE_ACCESS_CLASS_GENPORT_SINK);
+}
+
 static void hmat_register_target_initiators(struct memory_target *target)
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
@@ -774,6 +788,17 @@ static void hmat_register_target(struct memory_target *target)
 	 */
 	hmat_register_target_devices(target);
 
+	/*
+	 * Register generic port perf numbers. The nid may not be
+	 * initialized and is still NUMA_NO_NODE.
+	 */
+	mutex_lock(&target_lock);
+	if (*(u16 *)target->gen_port_device_handle) {
+		hmat_register_generic_target_initiators(target);
+		target->registered = true;
+	}
+	mutex_unlock(&target_lock);
+
 	/*
 	 * Skip offline nodes. This can happen when memory
 	 * marked EFI_MEMORY_SP, "specific purpose", is applied
-- 
GitLab


From ca53543d8e340070fb37fde93f36ed9012c76b90 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:07 -0700
Subject: [PATCH 1831/4076] acpi: numa: Add helper function to retrieve the
 performance attributes

Add helper to retrieve the performance attributes based on the device
handle.  The helper function is exported so the CXL driver can use that
to acquire the performance data between the CPU and the CXL host bridge.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/170319618721.2212653.5552947472849081786.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa/hmat.c | 41 ++++++++++++++++++++++++++++++++++++++++
 include/linux/acpi.h     | 11 +++++++++++
 2 files changed, 52 insertions(+)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 8a1802e078f3c..d6b85f0f6082f 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -108,6 +108,47 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)
 	return NULL;
 }
 
+static struct memory_target *acpi_find_genport_target(u32 uid)
+{
+	struct memory_target *target;
+	u32 target_uid;
+	u8 *uid_ptr;
+
+	list_for_each_entry(target, &targets, node) {
+		uid_ptr = target->gen_port_device_handle + 8;
+		target_uid = *(u32 *)uid_ptr;
+		if (uid == target_uid)
+			return target;
+	}
+
+	return NULL;
+}
+
+/**
+ * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port
+ * @uid: ACPI unique id
+ * @coord: The access coordinates written back out for the generic port
+ *
+ * Return: 0 on success. Errno on failure.
+ *
+ * Only supports device handles that are ACPI. Assume ACPI0016 HID for CXL.
+ */
+int acpi_get_genport_coordinates(u32 uid,
+				 struct access_coordinate *coord)
+{
+	struct memory_target *target;
+
+	guard(mutex)(&target_lock);
+	target = acpi_find_genport_target(uid);
+	if (!target)
+		return -ENOENT;
+
+	*coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK];
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(acpi_get_genport_coordinates, CXL);
+
 static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 {
 	struct memory_initiator *initiator;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4db54e928b36d..8b0761c682f99 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,6 +15,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
+#include <linux/node.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -424,6 +425,16 @@ extern int acpi_blacklisted(void);
 extern void acpi_osi_setup(char *str);
 extern bool acpi_osi_is_win8(void);
 
+#ifdef CONFIG_ACPI_HMAT
+int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord);
+#else
+static inline int acpi_get_genport_coordinates(u32 uid,
+					       struct access_coordinate *coord)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 #ifdef CONFIG_ACPI_NUMA
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
-- 
GitLab


From ad6f04c0269b0b7908f09621d3b3c90def39a297 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:13 -0700
Subject: [PATCH 1832/4076] cxl: Add callback to parse the DSMAS subtables from
 CDAT

Provide a callback function to the CDAT parser in order to parse the
Device Scoped Memory Affinity Structure (DSMAS). Each DSMAS structure
contains the DPA range and its associated attributes in each entry. See
the CDAT specification for details. The device handle and the DPA range
is saved and to be associated with the DSLBIS locality data when the
DSLBIS entries are parsed. The xarray is a local variable. When the
total path performance data is calculated and storred this xarray can be
discarded.

Coherent Device Attribute Table 1.03 2.1 Device Scoped memory Affinity
Structure (DSMAS)

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319619355.2212653.2675953129671561293.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/Kconfig       |  3 ++
 drivers/cxl/core/Makefile |  1 +
 drivers/cxl/core/cdat.c   | 92 +++++++++++++++++++++++++++++++++++++++
 drivers/cxl/cxl.h         |  2 +
 drivers/cxl/port.c        |  1 +
 tools/testing/cxl/Kbuild  |  1 +
 6 files changed, 100 insertions(+)
 create mode 100644 drivers/cxl/core/cdat.c

diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index 8ea1d340e4385..67998dbd1d46b 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -5,6 +5,7 @@ menuconfig CXL_BUS
 	select FW_LOADER
 	select FW_UPLOAD
 	select PCI_DOE
+	select FIRMWARE_TABLE
 	help
 	  CXL is a bus that is electrically compatible with PCI Express, but
 	  layers three protocols on that signalling (CXL.io, CXL.cache, and
@@ -54,8 +55,10 @@ config CXL_MEM_RAW_COMMANDS
 config CXL_ACPI
 	tristate "CXL ACPI: Platform Support"
 	depends on ACPI
+	depends on ACPI_NUMA
 	default CXL_BUS
 	select ACPI_TABLE_LIB
+	select ACPI_HMAT
 	help
 	  Enable support for host managed device memory (HDM) resources
 	  published by a platform's ACPI CXL memory layout description.  See
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 1f66b5d4d9355..9259bcc6773c8 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -13,5 +13,6 @@ cxl_core-y += mbox.o
 cxl_core-y += pci.o
 cxl_core-y += hdm.o
 cxl_core-y += pmu.o
+cxl_core-y += cdat.o
 cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
new file mode 100644
index 0000000000000..9bf4f53bf77fe
--- /dev/null
+++ b/drivers/cxl/core/cdat.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation. All rights reserved. */
+#include <linux/acpi.h>
+#include <linux/xarray.h>
+#include <linux/fw_table.h>
+#include "cxlpci.h"
+#include "cxl.h"
+
+struct dsmas_entry {
+	struct range dpa_range;
+	u8 handle;
+};
+
+static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
+			      const unsigned long end)
+{
+	struct acpi_cdat_header *hdr = &header->cdat;
+	struct acpi_cdat_dsmas *dsmas;
+	int size = sizeof(*hdr) + sizeof(*dsmas);
+	struct xarray *dsmas_xa = arg;
+	struct dsmas_entry *dent;
+	u16 len;
+	int rc;
+
+	len = le16_to_cpu((__force __le16)hdr->length);
+	if (len != size || (unsigned long)hdr + len > end) {
+		pr_warn("Malformed DSMAS table length: (%u:%u)\n", size, len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	dsmas = (struct acpi_cdat_dsmas *)(hdr + 1);
+
+	dent = kzalloc(sizeof(*dent), GFP_KERNEL);
+	if (!dent)
+		return -ENOMEM;
+
+	dent->handle = dsmas->dsmad_handle;
+	dent->dpa_range.start = le64_to_cpu((__force __le64)dsmas->dpa_base_address);
+	dent->dpa_range.end = le64_to_cpu((__force __le64)dsmas->dpa_base_address) +
+			      le64_to_cpu((__force __le64)dsmas->dpa_length) - 1;
+
+	rc = xa_insert(dsmas_xa, dent->handle, dent, GFP_KERNEL);
+	if (rc) {
+		kfree(dent);
+		return rc;
+	}
+
+	return 0;
+}
+
+static int cxl_cdat_endpoint_process(struct cxl_port *port,
+				     struct xarray *dsmas_xa)
+{
+	return cdat_table_parse(ACPI_CDAT_TYPE_DSMAS, cdat_dsmas_handler,
+				dsmas_xa, port->cdat.table);
+}
+
+static void discard_dsmas(struct xarray *xa)
+{
+	unsigned long index;
+	void *ent;
+
+	xa_for_each(xa, index, ent) {
+		xa_erase(xa, index);
+		kfree(ent);
+	}
+	xa_destroy(xa);
+}
+DEFINE_FREE(dsmas, struct xarray *, if (_T) discard_dsmas(_T))
+
+void cxl_endpoint_parse_cdat(struct cxl_port *port)
+{
+	struct xarray __dsmas_xa;
+	struct xarray *dsmas_xa __free(dsmas) = &__dsmas_xa;
+	int rc;
+
+	xa_init(&__dsmas_xa);
+	if (!port->cdat.table)
+		return;
+
+	rc = cxl_cdat_endpoint_process(port, dsmas_xa);
+	if (rc < 0) {
+		dev_dbg(&port->dev, "Failed to parse CDAT: %d\n", rc);
+		return;
+	}
+
+	/* Performance data processing */
+}
+EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
+
+MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 687043ece1018..be3b5eda875c6 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -839,6 +839,8 @@ static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
 }
 #endif
 
+void cxl_endpoint_parse_cdat(struct cxl_port *port);
+
 /*
  * Unit test builds overrides this to __weak, find the 'strong' version
  * of these symbols in tools/testing/cxl/.
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index 47bc8e0b85907..a889c4e6cb272 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -109,6 +109,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 
 	/* Cache the data early to ensure is_visible() works */
 	read_cdat_data(port);
+	cxl_endpoint_parse_cdat(port);
 
 	get_device(&cxlmd->dev);
 	rc = devm_add_action_or_reset(&port->dev, schedule_detach, cxlmd);
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 95dc58b94178b..0b12c36902d82 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -58,6 +58,7 @@ cxl_core-y += $(CXL_CORE_SRC)/mbox.o
 cxl_core-y += $(CXL_CORE_SRC)/pci.o
 cxl_core-y += $(CXL_CORE_SRC)/hdm.o
 cxl_core-y += $(CXL_CORE_SRC)/pmu.o
+cxl_core-y += $(CXL_CORE_SRC)/cdat.o
 cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
 cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
 cxl_core-y += config_check.o
-- 
GitLab


From 63cef81b9dca6ddf1c34d697016f830ddcfadf28 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:20 -0700
Subject: [PATCH 1833/4076] cxl: Add callback to parse the DSLBIS subtable from
 CDAT

Provide a callback to parse the Device Scoped Latency and Bandwidth
Information Structure (DSLBIS) in the CDAT structures. The DSLBIS
contains the bandwidth and latency information that's tied to a DSMAS
handle. The driver will retrieve the read and write latency and
bandwidth associated with the DSMAS which is tied to a DPA range.

Coherent Device Attribute Table 1.03 2.1 Device Scoped Latency and
Bandwidth Information Structure (DSLBIS)

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319620005.2212653.7475488478229720542.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/cdat.c | 102 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 100 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 9bf4f53bf77fe..97d8ef8848c66 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -3,12 +3,15 @@
 #include <linux/acpi.h>
 #include <linux/xarray.h>
 #include <linux/fw_table.h>
+#include <linux/node.h>
+#include <linux/overflow.h>
 #include "cxlpci.h"
 #include "cxl.h"
 
 struct dsmas_entry {
 	struct range dpa_range;
 	u8 handle;
+	struct access_coordinate coord;
 };
 
 static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
@@ -49,11 +52,106 @@ static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
 	return 0;
 }
 
+static void cxl_access_coordinate_set(struct access_coordinate *coord,
+				      int access, unsigned int val)
+{
+	switch (access) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+		coord->read_latency = val;
+		coord->write_latency = val;
+		break;
+	case ACPI_HMAT_READ_LATENCY:
+		coord->read_latency = val;
+		break;
+	case ACPI_HMAT_WRITE_LATENCY:
+		coord->write_latency = val;
+		break;
+	case ACPI_HMAT_ACCESS_BANDWIDTH:
+		coord->read_bandwidth = val;
+		coord->write_bandwidth = val;
+		break;
+	case ACPI_HMAT_READ_BANDWIDTH:
+		coord->read_bandwidth = val;
+		break;
+	case ACPI_HMAT_WRITE_BANDWIDTH:
+		coord->write_bandwidth = val;
+		break;
+	}
+}
+
+static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg,
+			       const unsigned long end)
+{
+	struct acpi_cdat_header *hdr = &header->cdat;
+	struct acpi_cdat_dslbis *dslbis;
+	int size = sizeof(*hdr) + sizeof(*dslbis);
+	struct xarray *dsmas_xa = arg;
+	struct dsmas_entry *dent;
+	__le64 le_base;
+	__le16 le_val;
+	u64 val;
+	u16 len;
+	int rc;
+
+	len = le16_to_cpu((__force __le16)hdr->length);
+	if (len != size || (unsigned long)hdr + len > end) {
+		pr_warn("Malformed DSLBIS table length: (%u:%u)\n", size, len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	dslbis = (struct acpi_cdat_dslbis *)(hdr + 1);
+
+	/* Skip unrecognized data type */
+	if (dslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH)
+		return 0;
+
+	/* Not a memory type, skip */
+	if ((dslbis->flags & ACPI_HMAT_MEMORY_HIERARCHY) != ACPI_HMAT_MEMORY)
+		return 0;
+
+	dent = xa_load(dsmas_xa, dslbis->handle);
+	if (!dent) {
+		pr_warn("No matching DSMAS entry for DSLBIS entry.\n");
+		return 0;
+	}
+
+	le_base = (__force __le64)dslbis->entry_base_unit;
+	le_val = (__force __le16)dslbis->entry[0];
+	rc = check_mul_overflow(le64_to_cpu(le_base),
+				le16_to_cpu(le_val), &val);
+	if (rc)
+		pr_warn("DSLBIS value overflowed.\n");
+
+	cxl_access_coordinate_set(&dent->coord, dslbis->data_type, val);
+
+	return 0;
+}
+
+static int cdat_table_parse_output(int rc)
+{
+	if (rc < 0)
+		return rc;
+	if (rc == 0)
+		return -ENOENT;
+
+	return 0;
+}
+
 static int cxl_cdat_endpoint_process(struct cxl_port *port,
 				     struct xarray *dsmas_xa)
 {
-	return cdat_table_parse(ACPI_CDAT_TYPE_DSMAS, cdat_dsmas_handler,
-				dsmas_xa, port->cdat.table);
+	int rc;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_DSMAS, cdat_dsmas_handler,
+			      dsmas_xa, port->cdat.table);
+	rc = cdat_table_parse_output(rc);
+	if (rc)
+		return rc;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_DSLBIS, cdat_dslbis_handler,
+			      dsmas_xa, port->cdat.table);
+	return cdat_table_parse_output(rc);
 }
 
 static void discard_dsmas(struct xarray *xa)
-- 
GitLab


From 80aa780dda20618be76162bf991d49cf962fda38 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:26 -0700
Subject: [PATCH 1834/4076] cxl: Add callback to parse the SSLBIS subtable from
 CDAT

Provide a callback to parse the Switched Scoped Latency and Bandwidth
Information Structure (SSLBIS) in the CDAT structures. The SSLBIS
contains the bandwidth and latency information that's tied to the
CXL switch that the data table has been read from. The extracted
values are stored to the cxl_dport correlated by the port_id
depending on the SSLBIS entry.

Coherent Device Attribute Table 1.03 2.1 Switched Scoped Latency
and Bandwidth Information Structure (DSLBIS)

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319620635.2212653.5194389158785365150.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/cdat.c | 98 +++++++++++++++++++++++++++++++++++++++++
 drivers/cxl/cxl.h       |  4 ++
 drivers/cxl/port.c      |  2 +
 3 files changed, 104 insertions(+)

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 97d8ef8848c66..b3ab47d250e16 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -187,4 +187,102 @@ void cxl_endpoint_parse_cdat(struct cxl_port *port)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
 
+static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg,
+			       const unsigned long end)
+{
+	struct acpi_cdat_sslbis *sslbis;
+	int size = sizeof(header->cdat) + sizeof(*sslbis);
+	struct cxl_port *port = arg;
+	struct device *dev = &port->dev;
+	struct acpi_cdat_sslbe *entry;
+	int remain, entries, i;
+	u16 len;
+
+	len = le16_to_cpu((__force __le16)header->cdat.length);
+	remain = len - size;
+	if (!remain || remain % sizeof(*entry) ||
+	    (unsigned long)header + len > end) {
+		dev_warn(dev, "Malformed SSLBIS table length: (%u)\n", len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	sslbis = (struct acpi_cdat_sslbis *)((unsigned long)header +
+					     sizeof(header->cdat));
+
+	/* Unrecognized data type, we can skip */
+	if (sslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH)
+		return 0;
+
+	entries = remain / sizeof(*entry);
+	entry = (struct acpi_cdat_sslbe *)((unsigned long)header + sizeof(*sslbis));
+
+	for (i = 0; i < entries; i++) {
+		u16 x = le16_to_cpu((__force __le16)entry->portx_id);
+		u16 y = le16_to_cpu((__force __le16)entry->porty_id);
+		__le64 le_base;
+		__le16 le_val;
+		struct cxl_dport *dport;
+		unsigned long index;
+		u16 dsp_id;
+		u64 val;
+
+		switch (x) {
+		case ACPI_CDAT_SSLBIS_US_PORT:
+			dsp_id = y;
+			break;
+		case ACPI_CDAT_SSLBIS_ANY_PORT:
+			switch (y) {
+			case ACPI_CDAT_SSLBIS_US_PORT:
+				dsp_id = x;
+				break;
+			case ACPI_CDAT_SSLBIS_ANY_PORT:
+				dsp_id = ACPI_CDAT_SSLBIS_ANY_PORT;
+				break;
+			default:
+				dsp_id = y;
+				break;
+			}
+			break;
+		default:
+			dsp_id = x;
+			break;
+		}
+
+		le_base = (__force __le64)sslbis->entry_base_unit;
+		le_val = (__force __le16)entry->latency_or_bandwidth;
+
+		if (check_mul_overflow(le64_to_cpu(le_base),
+				       le16_to_cpu(le_val), &val))
+			dev_warn(dev, "SSLBIS value overflowed!\n");
+
+		xa_for_each(&port->dports, index, dport) {
+			if (dsp_id == ACPI_CDAT_SSLBIS_ANY_PORT ||
+			    dsp_id == dport->port_id)
+				cxl_access_coordinate_set(&dport->sw_coord,
+							  sslbis->data_type,
+							  val);
+		}
+
+		entry++;
+	}
+
+	return 0;
+}
+
+void cxl_switch_parse_cdat(struct cxl_port *port)
+{
+	int rc;
+
+	if (!port->cdat.table)
+		return;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_SSLBIS, cdat_sslbis_handler,
+			      port, port->cdat.table);
+	rc = cdat_table_parse_output(rc);
+	if (rc)
+		dev_dbg(&port->dev, "Failed to parse SSLBIS: %d\n", rc);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL);
+
 MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index be3b5eda875c6..22f664b9f4c63 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -8,6 +8,7 @@
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/node.h>
 #include <linux/io.h>
 
 /**
@@ -634,6 +635,7 @@ struct cxl_rcrb_info {
  * @rch: Indicate whether this dport was enumerated in RCH or VH mode
  * @port: reference to cxl_port that contains this downstream port
  * @regs: Dport parsed register blocks
+ * @sw_coord: access coordinates (performance) for switch from CDAT
  */
 struct cxl_dport {
 	struct device *dport_dev;
@@ -643,6 +645,7 @@ struct cxl_dport {
 	bool rch;
 	struct cxl_port *port;
 	struct cxl_regs regs;
+	struct access_coordinate sw_coord;
 };
 
 /**
@@ -840,6 +843,7 @@ static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
 #endif
 
 void cxl_endpoint_parse_cdat(struct cxl_port *port);
+void cxl_switch_parse_cdat(struct cxl_port *port);
 
 /*
  * Unit test builds overrides this to __weak, find the 'strong' version
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index a889c4e6cb272..da3c3a08bd626 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -69,6 +69,8 @@ static int cxl_switch_port_probe(struct cxl_port *port)
 	if (rc < 0)
 		return rc;
 
+	cxl_switch_parse_cdat(port);
+
 	cxlhdm = devm_cxl_setup_hdm(port, NULL);
 	if (!IS_ERR(cxlhdm))
 		return devm_cxl_enumerate_decoders(cxlhdm, NULL);
-- 
GitLab


From 790815902ec61ba1715fd67d3cb9036e13c942bc Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:32 -0700
Subject: [PATCH 1835/4076] cxl: Add support for _DSM Function for retrieving
 QTG ID

CXL spec v3.0 9.17.3 CXL Root Device Specific Methods (_DSM)

Add support to retrieve QTG ID via ACPI _DSM call. The _DSM call requires
an input of an ACPI package with 4 dwords (read latency, write latency,
read bandwidth, write bandwidth). The call returns a package with 1 WORD
that provides the max supported QTG ID and a package that may contain 0 or
more WORDs as the recommended QTG IDs in the recommended order.

Create a cxl_root container for the root cxl_port and provide a callback
->get_qos_class() in order to retrieve the QoS class. For the ACPI case,
the _DSM helper is used to retrieve the QTG ID and returned. A
devm_cxl_add_root() function is added for root port setup and registration
of the cxl_root callback operation(s).

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/170319621294.2212653.1649682083061569256.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/acpi.c      | 132 +++++++++++++++++++++++++++++++++++++++-
 drivers/cxl/core/port.c |  49 ++++++++++++---
 drivers/cxl/cxl.h       |  25 ++++++++
 3 files changed, 193 insertions(+), 13 deletions(-)

diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index 2034eb4ce83fb..2f7de910ce572 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/acpi.h>
 #include <linux/pci.h>
+#include <linux/node.h>
 #include <asm/div64.h>
 #include "cxlpci.h"
 #include "cxl.h"
@@ -17,6 +18,10 @@ struct cxl_cxims_data {
 	u64 xormaps[] __counted_by(nr_maps);
 };
 
+static const guid_t acpi_cxl_qtg_id_guid =
+	GUID_INIT(0xF365F9A6, 0xA7DE, 0x4071,
+		  0xA6, 0x6A, 0xB4, 0x0C, 0x0B, 0x4F, 0x8E, 0x52);
+
 /*
  * Find a targets entry (n) in the host bridge interleave list.
  * CXL Specification 3.0 Table 9-22
@@ -194,6 +199,125 @@ struct cxl_cfmws_context {
 	int id;
 };
 
+/**
+ * cxl_acpi_evaluate_qtg_dsm - Retrieve QTG ids via ACPI _DSM
+ * @handle: ACPI handle
+ * @coord: performance access coordinates
+ * @entries: number of QTG IDs to return
+ * @qos_class: int array provided by caller to return QTG IDs
+ *
+ * Return: number of QTG IDs returned, or -errno for errors
+ *
+ * Issue QTG _DSM with accompanied bandwidth and latency data in order to get
+ * the QTG IDs that are suitable for the performance point in order of most
+ * suitable to least suitable. Write back array of QTG IDs and return the
+ * actual number of QTG IDs written back.
+ */
+static int
+cxl_acpi_evaluate_qtg_dsm(acpi_handle handle, struct access_coordinate *coord,
+			  int entries, int *qos_class)
+{
+	union acpi_object *out_obj, *out_buf, *obj;
+	union acpi_object in_array[4] = {
+		[0].integer = { ACPI_TYPE_INTEGER, coord->read_latency },
+		[1].integer = { ACPI_TYPE_INTEGER, coord->write_latency },
+		[2].integer = { ACPI_TYPE_INTEGER, coord->read_bandwidth },
+		[3].integer = { ACPI_TYPE_INTEGER, coord->write_bandwidth },
+	};
+	union acpi_object in_obj = {
+		.package = {
+			.type = ACPI_TYPE_PACKAGE,
+			.count = 4,
+			.elements = in_array,
+		},
+	};
+	int count, pkg_entries, i;
+	u16 max_qtg;
+	int rc;
+
+	if (!entries)
+		return -EINVAL;
+
+	out_obj = acpi_evaluate_dsm(handle, &acpi_cxl_qtg_id_guid, 1, 1, &in_obj);
+	if (!out_obj)
+		return -ENXIO;
+
+	if (out_obj->type != ACPI_TYPE_PACKAGE) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	/* Check Max QTG ID */
+	obj = &out_obj->package.elements[0];
+	if (obj->type != ACPI_TYPE_INTEGER) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	max_qtg = obj->integer.value;
+
+	/* It's legal to have 0 QTG entries */
+	pkg_entries = out_obj->package.count;
+	if (pkg_entries <= 1) {
+		rc = 0;
+		goto out;
+	}
+
+	/* Retrieve QTG IDs package */
+	obj = &out_obj->package.elements[1];
+	if (obj->type != ACPI_TYPE_PACKAGE) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	pkg_entries = obj->package.count;
+	count = min(entries, pkg_entries);
+	for (i = 0; i < count; i++) {
+		u16 qtg_id;
+
+		out_buf = &obj->package.elements[i];
+		if (out_buf->type != ACPI_TYPE_INTEGER) {
+			rc = -ENXIO;
+			goto out;
+		}
+
+		qtg_id = out_buf->integer.value;
+		if (qtg_id > max_qtg)
+			pr_warn("QTG ID %u greater than MAX %u\n",
+				qtg_id, max_qtg);
+
+		qos_class[i] = qtg_id;
+	}
+	rc = count;
+
+out:
+	ACPI_FREE(out_obj);
+	return rc;
+}
+
+static int cxl_acpi_qos_class(struct cxl_port *root_port,
+			      struct access_coordinate *coord, int entries,
+			      int *qos_class)
+{
+	acpi_handle handle;
+	struct device *dev;
+
+	dev = root_port->uport_dev;
+
+	if (!dev_is_platform(dev))
+		return -ENODEV;
+
+	handle = ACPI_HANDLE(dev);
+	if (!handle)
+		return -ENODEV;
+
+	return cxl_acpi_evaluate_qtg_dsm(handle, coord, entries, qos_class);
+}
+
+static const struct cxl_root_ops acpi_root_ops = {
+	.qos_class = cxl_acpi_qos_class,
+};
+
 static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg,
 			   const unsigned long end)
 {
@@ -656,6 +780,7 @@ static int cxl_acpi_probe(struct platform_device *pdev)
 {
 	int rc;
 	struct resource *cxl_res;
+	struct cxl_root *cxl_root;
 	struct cxl_port *root_port;
 	struct device *host = &pdev->dev;
 	struct acpi_device *adev = ACPI_COMPANION(host);
@@ -675,9 +800,10 @@ static int cxl_acpi_probe(struct platform_device *pdev)
 	cxl_res->end = -1;
 	cxl_res->flags = IORESOURCE_MEM;
 
-	root_port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL);
-	if (IS_ERR(root_port))
-		return PTR_ERR(root_port);
+	cxl_root = devm_cxl_add_root(host, &acpi_root_ops);
+	if (IS_ERR(cxl_root))
+		return PTR_ERR(cxl_root);
+	root_port = &cxl_root->port;
 
 	rc = bus_for_each_dev(adev->dev.bus, NULL, root_port,
 			      add_host_bridge_dport);
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index b7c93bb18f6e7..9393cbf046528 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -541,7 +541,10 @@ static void cxl_port_release(struct device *dev)
 	xa_destroy(&port->dports);
 	xa_destroy(&port->regions);
 	ida_free(&cxl_port_ida, port->id);
-	kfree(port);
+	if (is_cxl_root(port))
+		kfree(to_cxl_root(port));
+	else
+		kfree(port);
 }
 
 static ssize_t decoders_committed_show(struct device *dev,
@@ -669,17 +672,31 @@ static struct lock_class_key cxl_port_key;
 static struct cxl_port *cxl_port_alloc(struct device *uport_dev,
 				       struct cxl_dport *parent_dport)
 {
-	struct cxl_port *port;
+	struct cxl_root *cxl_root __free(kfree) = NULL;
+	struct cxl_port *port, *_port __free(kfree) = NULL;
 	struct device *dev;
 	int rc;
 
-	port = kzalloc(sizeof(*port), GFP_KERNEL);
-	if (!port)
-		return ERR_PTR(-ENOMEM);
+	/* No parent_dport, root cxl_port */
+	if (!parent_dport) {
+		cxl_root = kzalloc(sizeof(*cxl_root), GFP_KERNEL);
+		if (!cxl_root)
+			return ERR_PTR(-ENOMEM);
+	} else {
+		_port = kzalloc(sizeof(*port), GFP_KERNEL);
+		if (!_port)
+			return ERR_PTR(-ENOMEM);
+	}
 
 	rc = ida_alloc(&cxl_port_ida, GFP_KERNEL);
 	if (rc < 0)
-		goto err;
+		return ERR_PTR(rc);
+
+	if (cxl_root)
+		port = &no_free_ptr(cxl_root)->port;
+	else
+		port = no_free_ptr(_port);
+
 	port->id = rc;
 	port->uport_dev = uport_dev;
 
@@ -731,10 +748,6 @@ static struct cxl_port *cxl_port_alloc(struct device *uport_dev,
 	dev->type = &cxl_port_type;
 
 	return port;
-
-err:
-	kfree(port);
-	return ERR_PTR(rc);
 }
 
 static int cxl_setup_comp_regs(struct device *host, struct cxl_register_map *map,
@@ -884,6 +897,22 @@ struct cxl_port *devm_cxl_add_port(struct device *host,
 }
 EXPORT_SYMBOL_NS_GPL(devm_cxl_add_port, CXL);
 
+struct cxl_root *devm_cxl_add_root(struct device *host,
+				   const struct cxl_root_ops *ops)
+{
+	struct cxl_root *cxl_root;
+	struct cxl_port *port;
+
+	port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL);
+	if (IS_ERR(port))
+		return (struct cxl_root *)port;
+
+	cxl_root = to_cxl_root(port);
+	cxl_root->ops = ops;
+	return cxl_root;
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_root, CXL);
+
 struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port)
 {
 	/* There is no pci_bus associated with a CXL platform-root port */
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 22f664b9f4c63..abbdcd3a75961 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -615,6 +615,29 @@ struct cxl_port {
 	bool cdat_available;
 };
 
+struct cxl_root_ops {
+	int (*qos_class)(struct cxl_port *root_port,
+			 struct access_coordinate *coord, int entries,
+			 int *qos_class);
+};
+
+/**
+ * struct cxl_root - logical collection of root cxl_port items
+ *
+ * @port: cxl_port member
+ * @ops: cxl root operations
+ */
+struct cxl_root {
+	struct cxl_port port;
+	const struct cxl_root_ops *ops;
+};
+
+static inline struct cxl_root *
+to_cxl_root(const struct cxl_port *port)
+{
+	return container_of(port, struct cxl_root, port);
+}
+
 static inline struct cxl_dport *
 cxl_find_dport_by_dev(struct cxl_port *port, const struct device *dport_dev)
 {
@@ -703,6 +726,8 @@ struct cxl_port *devm_cxl_add_port(struct device *host,
 				   struct device *uport_dev,
 				   resource_size_t component_reg_phys,
 				   struct cxl_dport *parent_dport);
+struct cxl_root *devm_cxl_add_root(struct device *host,
+				   const struct cxl_root_ops *ops);
 struct cxl_port *find_cxl_root(struct cxl_port *port);
 int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd);
 void cxl_bus_rescan(void);
-- 
GitLab


From 4d07a05397c8c15c37c8c3abb7afaea1dcd2f0e7 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:39 -0700
Subject: [PATCH 1836/4076] cxl: Calculate and store PCI link latency for the
 downstream ports

The latency is calculated by dividing the flit size over the bandwidth. Add
support to retrieve the flit size for the CXL switch device and calculate
the latency of the PCIe link. Cache the latency number with cxl_dport.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319621931.2212653.6800240203604822886.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/core.h |  2 ++
 drivers/cxl/core/pci.c  | 36 ++++++++++++++++++++++++++++++++++++
 drivers/cxl/core/port.c |  6 ++++++
 drivers/cxl/cxl.h       |  4 ++++
 drivers/cxl/cxlpci.h    | 13 +++++++++++++
 drivers/pci/pci.c       | 38 ++++++++++++++++++++++++++++++++++++--
 include/linux/pci.h     |  1 +
 7 files changed, 98 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 86d7ba23235e3..3b64fb1b9ed05 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -88,4 +88,6 @@ enum cxl_poison_trace_type {
 	CXL_POISON_TRACE_CLEAR,
 };
 
+long cxl_pci_get_latency(struct pci_dev *pdev);
+
 #endif /* __CXL_CORE_H__ */
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 37e1652afbc7e..6c9c8d92f8f71 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2021 Intel Corporation. All rights reserved. */
+#include <linux/units.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/device.h>
 #include <linux/delay.h>
@@ -979,3 +980,38 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_error_detected, CXL);
+
+static int cxl_flit_size(struct pci_dev *pdev)
+{
+	if (cxl_pci_flit_256(pdev))
+		return 256;
+
+	return 68;
+}
+
+/**
+ * cxl_pci_get_latency - calculate the link latency for the PCIe link
+ * @pdev: PCI device
+ *
+ * return: calculated latency or 0 for no latency
+ *
+ * CXL Memory Device SW Guide v1.0 2.11.4 Link latency calculation
+ * Link latency = LinkPropagationLatency + FlitLatency + RetimerLatency
+ * LinkProgationLatency is negligible, so 0 will be used
+ * RetimerLatency is assumed to be negligible and 0 will be used
+ * FlitLatency = FlitSize / LinkBandwidth
+ * FlitSize is defined by spec. CXL rev3.0 4.2.1.
+ * 68B flit is used up to 32GT/s. >32GT/s, 256B flit size is used.
+ * The FlitLatency is converted to picoseconds.
+ */
+long cxl_pci_get_latency(struct pci_dev *pdev)
+{
+	long bw;
+
+	bw = pcie_link_speed_mbps(pdev);
+	if (bw < 0)
+		return 0;
+	bw /= BITS_PER_BYTE;
+
+	return cxl_flit_size(pdev) * MEGA / bw;
+}
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 9393cbf046528..b5ad227fe0d8f 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -854,6 +854,9 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
 	if (rc)
 		return ERR_PTR(rc);
 
+	if (parent_dport && dev_is_pci(uport_dev))
+		port->pci_latency = cxl_pci_get_latency(to_pci_dev(uport_dev));
+
 	return port;
 
 err:
@@ -1137,6 +1140,9 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev,
 	if (rc)
 		return ERR_PTR(rc);
 
+	if (dev_is_pci(dport_dev))
+		dport->link_latency = cxl_pci_get_latency(to_pci_dev(dport_dev));
+
 	return dport;
 }
 
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index abbdcd3a75961..7da8db919a20d 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -591,6 +591,7 @@ struct cxl_dax_region {
  * @depth: How deep this port is relative to the root. depth 0 is the root.
  * @cdat: Cached CDAT data
  * @cdat_available: Should a CDAT attribute be available in sysfs
+ * @pci_latency: Upstream latency in picoseconds
  */
 struct cxl_port {
 	struct device dev;
@@ -613,6 +614,7 @@ struct cxl_port {
 		size_t length;
 	} cdat;
 	bool cdat_available;
+	long pci_latency;
 };
 
 struct cxl_root_ops {
@@ -659,6 +661,7 @@ struct cxl_rcrb_info {
  * @port: reference to cxl_port that contains this downstream port
  * @regs: Dport parsed register blocks
  * @sw_coord: access coordinates (performance) for switch from CDAT
+ * @link_latency: calculated PCIe downstream latency
  */
 struct cxl_dport {
 	struct device *dport_dev;
@@ -669,6 +672,7 @@ struct cxl_dport {
 	struct cxl_port *port;
 	struct cxl_regs regs;
 	struct access_coordinate sw_coord;
+	long link_latency;
 };
 
 /**
diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
index 0fa4799ea316c..711b05d9a370e 100644
--- a/drivers/cxl/cxlpci.h
+++ b/drivers/cxl/cxlpci.h
@@ -85,6 +85,19 @@ struct cdat_entry_header {
 	__le16 length;
 } __packed;
 
+/*
+ * CXL v3.0 6.2.3 Table 6-4
+ * The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits
+ * mode, otherwise it's 68B flits mode.
+ */
+static inline bool cxl_pci_flit_256(struct pci_dev *pdev)
+{
+	u16 lnksta2;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &lnksta2);
+	return lnksta2 & PCI_EXP_LNKSTA2_FLIT;
+}
+
 int devm_cxl_port_enumerate_dports(struct cxl_port *port);
 struct cxl_dev_state;
 int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 55bc3576a9856..00817d403ad4e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6224,6 +6224,41 @@ int pcie_set_mps(struct pci_dev *dev, int mps)
 }
 EXPORT_SYMBOL(pcie_set_mps);
 
+static enum pci_bus_speed to_pcie_link_speed(u16 lnksta)
+{
+	return pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS, lnksta)];
+}
+
+int pcie_link_speed_mbps(struct pci_dev *pdev)
+{
+	u16 lnksta;
+	int err;
+
+	err = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta);
+	if (err)
+		return err;
+
+	switch (to_pcie_link_speed(lnksta)) {
+	case PCIE_SPEED_2_5GT:
+		return 2500;
+	case PCIE_SPEED_5_0GT:
+		return 5000;
+	case PCIE_SPEED_8_0GT:
+		return 8000;
+	case PCIE_SPEED_16_0GT:
+		return 16000;
+	case PCIE_SPEED_32_0GT:
+		return 32000;
+	case PCIE_SPEED_64_0GT:
+		return 64000;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(pcie_link_speed_mbps);
+
 /**
  * pcie_bandwidth_available - determine minimum link settings of a PCIe
  *			      device and its bandwidth limitation
@@ -6257,8 +6292,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 	while (dev) {
 		pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
 
-		next_speed = pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS,
-						       lnksta)];
+		next_speed = to_pcie_link_speed(lnksta);
 		next_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta);
 
 		next_bw = next_width * PCIE_SPEED2MBS_ENC(next_speed);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index dea043bc1e383..504a4ba2c29ef 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1364,6 +1364,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps);
 u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 			     enum pci_bus_speed *speed,
 			     enum pcie_link_width *width);
+int pcie_link_speed_mbps(struct pci_dev *pdev);
 void pcie_print_link_status(struct pci_dev *dev);
 int pcie_reset_flr(struct pci_dev *dev, bool probe);
 int pcie_flr(struct pci_dev *dev);
-- 
GitLab


From f2202f990456acc52b50f6b14c95b232ac14429b Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:45 -0700
Subject: [PATCH 1837/4076] tools/testing/cxl: Add hostbridge UID string for
 cxl_test mock hb devices

In order to support acpi_device_uid() call, add static string to
acpi_device->pnp.unique_id.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319622564.2212653.1534465446670631698.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/cxl/test/cxl.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index f4e517a0c7740..a3cdbb2be038c 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -68,15 +68,19 @@ static struct acpi_device acpi0017_mock;
 static struct acpi_device host_bridge[NR_BRIDGES] = {
 	[0] = {
 		.handle = &host_bridge[0],
+		.pnp.unique_id = "0",
 	},
 	[1] = {
 		.handle = &host_bridge[1],
+		.pnp.unique_id = "1",
 	},
 	[2] = {
 		.handle = &host_bridge[2],
+		.pnp.unique_id = "2",
 	},
 	[3] = {
 		.handle = &host_bridge[3],
+		.pnp.unique_id = "3",
 	},
 };
 
-- 
GitLab


From 1037b82fccfe9c001ffa7a883651bb4cde7b705c Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:51 -0700
Subject: [PATCH 1838/4076] cxl: Store the access coordinates for the generic
 ports

Each CXL host bridge is represented by an ACPI0016 device. A generic port
device handle that is an ACPI device is represented by a string of
ACPI0016 device HID and UID. Create a device handle from the ACPI device
and retrieve the access coordinates from the stored memory targets. The
access coordinates are stored under the cxl_dport that is associated with
the CXL host bridge.

The access coordinates struct is dynamically allocated under cxl_dport in
order for code later on to detect whether the data exists or not.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319623196.2212653.17916695743464172534.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/acpi.c | 25 +++++++++++++++++++++++++
 drivers/cxl/cxl.h  |  2 ++
 2 files changed, 27 insertions(+)

diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index 2f7de910ce572..afc712264d1c2 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -513,8 +513,29 @@ static int cxl_get_chbs(struct device *dev, struct acpi_device *hb,
 	return 0;
 }
 
+static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport)
+{
+	struct acpi_device *hb = to_cxl_host_bridge(NULL, dev);
+	u32 uid;
+	int rc;
+
+	if (kstrtou32(acpi_device_uid(hb), 0, &uid))
+		return -EINVAL;
+
+	rc = acpi_get_genport_coordinates(uid, &dport->hb_coord);
+	if (rc < 0)
+		return rc;
+
+	/* Adjust back to picoseconds from nanoseconds */
+	dport->hb_coord.read_latency *= 1000;
+	dport->hb_coord.write_latency *= 1000;
+
+	return 0;
+}
+
 static int add_host_bridge_dport(struct device *match, void *arg)
 {
+	int ret;
 	acpi_status rc;
 	struct device *bridge;
 	struct cxl_dport *dport;
@@ -564,6 +585,10 @@ static int add_host_bridge_dport(struct device *match, void *arg)
 	if (IS_ERR(dport))
 		return PTR_ERR(dport);
 
+	ret = get_genport_coordinates(match, dport);
+	if (ret)
+		dev_dbg(match, "Failed to get generic port perf coordinates.\n");
+
 	return 0;
 }
 
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 7da8db919a20d..dd234f3b9ed4d 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -661,6 +661,7 @@ struct cxl_rcrb_info {
  * @port: reference to cxl_port that contains this downstream port
  * @regs: Dport parsed register blocks
  * @sw_coord: access coordinates (performance) for switch from CDAT
+ * @hb_coord: access coordinates (performance) from ACPI generic port (host bridge)
  * @link_latency: calculated PCIe downstream latency
  */
 struct cxl_dport {
@@ -672,6 +673,7 @@ struct cxl_dport {
 	struct cxl_port *port;
 	struct cxl_regs regs;
 	struct access_coordinate sw_coord;
+	struct access_coordinate hb_coord;
 	long link_latency;
 };
 
-- 
GitLab


From 14a6960b3e928ccea22d687fb0626237885a20bd Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:58 -0700
Subject: [PATCH 1839/4076] cxl: Add helper function that calculate performance
 data for downstream ports

The CDAT information from the switch, Switch Scoped Latency and Bandwidth
Information Structure (SSLBIS), is parsed and stored under a cxl_dport
based on the correlated downstream port id from the SSLBIS entry. Walk
the entire CXL port paths and collect all the performance data. Also
pick up the link latency number that's stored under the dports. The
entire path PCIe bandwidth can be retrieved using the
pcie_bandwidth_available() call.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319623824.2212653.10302079766473698427.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/port.c | 75 +++++++++++++++++++++++++++++++++++++++++
 drivers/cxl/cxl.h       |  3 ++
 2 files changed, 78 insertions(+)

diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index b5ad227fe0d8f..8c00fd6be730e 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -9,6 +9,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
+#include <linux/node.h>
 #include <cxlmem.h>
 #include <cxlpci.h>
 #include <cxl.h>
@@ -2094,6 +2095,80 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd)
 }
 EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL);
 
+static void combine_coordinates(struct access_coordinate *c1,
+				struct access_coordinate *c2)
+{
+		if (c2->write_bandwidth)
+			c1->write_bandwidth = min(c1->write_bandwidth,
+						  c2->write_bandwidth);
+		c1->write_latency += c2->write_latency;
+
+		if (c2->read_bandwidth)
+			c1->read_bandwidth = min(c1->read_bandwidth,
+						 c2->read_bandwidth);
+		c1->read_latency += c2->read_latency;
+}
+
+/**
+ * cxl_endpoint_get_perf_coordinates - Retrieve performance numbers stored in dports
+ *				   of CXL path
+ * @port: endpoint cxl_port
+ * @coord: output performance data
+ *
+ * Return: errno on failure, 0 on success.
+ */
+int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
+				      struct access_coordinate *coord)
+{
+	struct access_coordinate c = {
+		.read_bandwidth = UINT_MAX,
+		.write_bandwidth = UINT_MAX,
+	};
+	struct cxl_port *iter = port;
+	struct cxl_dport *dport;
+	struct pci_dev *pdev;
+	unsigned int bw;
+
+	if (!is_cxl_endpoint(port))
+		return -EINVAL;
+
+	dport = iter->parent_dport;
+
+	/*
+	 * Exit the loop when the parent port of the current port is cxl root.
+	 * The iterative loop starts at the endpoint and gathers the
+	 * latency of the CXL link from the current iter to the next downstream
+	 * port each iteration. If the parent is cxl root then there is
+	 * nothing to gather.
+	 */
+	while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
+		combine_coordinates(&c, &dport->sw_coord);
+		c.write_latency += dport->link_latency;
+		c.read_latency += dport->link_latency;
+
+		iter = to_cxl_port(iter->dev.parent);
+		dport = iter->parent_dport;
+	}
+
+	/* Augment with the generic port (host bridge) perf data */
+	combine_coordinates(&c, &dport->hb_coord);
+
+	/* Get the calculated PCI paths bandwidth */
+	pdev = to_pci_dev(port->uport_dev->parent);
+	bw = pcie_bandwidth_available(pdev, NULL, NULL, NULL);
+	if (bw == 0)
+		return -ENXIO;
+	bw /= BITS_PER_BYTE;
+
+	c.write_bandwidth = min(c.write_bandwidth, bw);
+	c.read_bandwidth = min(c.read_bandwidth, bw);
+
+	*coord = c;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_endpoint_get_perf_coordinates, CXL);
+
 /* for user tooling to ensure port disable work has completed */
 static ssize_t flush_store(const struct bus_type *bus, const char *buf, size_t count)
 {
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index dd234f3b9ed4d..492dbf63935fd 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -876,6 +876,9 @@ static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
 void cxl_endpoint_parse_cdat(struct cxl_port *port);
 void cxl_switch_parse_cdat(struct cxl_port *port);
 
+int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
+				      struct access_coordinate *coord);
+
 /*
  * Unit test builds overrides this to __weak, find the 'strong' version
  * of these symbols in tools/testing/cxl/.
-- 
GitLab


From 7a4f148dd8d518bc1e012aa738b0ed6244959293 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:04:04 -0700
Subject: [PATCH 1840/4076] cxl: Compute the entire CXL path latency and
 bandwidth data

CXL Memory Device SW Guide [1] rev1.0 2.11.2 provides instruction on how to
calculate latency and bandwidth for CXL memory device. Calculate minimum
bandwidth and total latency for the path from the CXL device to the root
port. The QTG id is retrieved by providing the performance data as input
and calling the root port callback ->get_qos_class(). The retrieved id is
stored with the cxl_port of the CXL device.

For example for a device that is directly attached to a host bus:
Total Latency = Device Latency (from CDAT) + Dev to Host Bus (HB) Link
		Latency + Generic Port Latency
Min Bandwidth = Min bandwidth for link bandwidth between HB
		and CXL device, device CDAT bandwidth, and Generic Port
		Bandwidth

For a device that has a switch in between host bus and CXL device:
Total Latency = Device (CDAT) Latency + Dev to Switch Link Latency +
		Switch (CDAT) Latency + Switch to HB Link Latency +
		Generic Port Latency
Min Bandwidth = Min bandwidth for link bandwidth between CXL device
		to CXL switch, CXL device CDAT bandwidth, CXL switch CDAT
		bandwidth, CXL switch to HB bandwidth, and Generic Port
		Bandwidth.

[1]: https://cdrdv2-public.intel.com/643805/643805_CXL%20Memory%20Device%20SW%20Guide_Rev1p0.pdf

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319624458.2212653.13252496567443656371.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/cdat.c | 59 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 58 insertions(+), 1 deletion(-)

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index b3ab47d250e16..43dfef80fb847 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -12,6 +12,9 @@ struct dsmas_entry {
 	struct range dpa_range;
 	u8 handle;
 	struct access_coordinate coord;
+
+	int entries;
+	int qos_class;
 };
 
 static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
@@ -154,6 +157,55 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port,
 	return cdat_table_parse_output(rc);
 }
 
+static int cxl_port_perf_data_calculate(struct cxl_port *port,
+					struct xarray *dsmas_xa)
+{
+	struct access_coordinate c;
+	struct cxl_port *root_port;
+	struct cxl_root *cxl_root;
+	struct dsmas_entry *dent;
+	int valid_entries = 0;
+	unsigned long index;
+	int rc;
+
+	rc = cxl_endpoint_get_perf_coordinates(port, &c);
+	if (rc) {
+		dev_dbg(&port->dev, "Failed to retrieve perf coordinates.\n");
+		return rc;
+	}
+
+	root_port = find_cxl_root(port);
+	cxl_root = to_cxl_root(root_port);
+	if (!cxl_root->ops || !cxl_root->ops->qos_class)
+		return -EOPNOTSUPP;
+
+	xa_for_each(dsmas_xa, index, dent) {
+		int qos_class;
+
+		dent->coord.read_latency = dent->coord.read_latency +
+					   c.read_latency;
+		dent->coord.write_latency = dent->coord.write_latency +
+					    c.write_latency;
+		dent->coord.read_bandwidth = min_t(int, c.read_bandwidth,
+						   dent->coord.read_bandwidth);
+		dent->coord.write_bandwidth = min_t(int, c.write_bandwidth,
+						    dent->coord.write_bandwidth);
+
+		dent->entries = 1;
+		rc = cxl_root->ops->qos_class(root_port, &dent->coord, 1, &qos_class);
+		if (rc != 1)
+			continue;
+
+		valid_entries++;
+		dent->qos_class = qos_class;
+	}
+
+	if (!valid_entries)
+		return -ENOENT;
+
+	return 0;
+}
+
 static void discard_dsmas(struct xarray *xa)
 {
 	unsigned long index;
@@ -183,7 +235,12 @@ void cxl_endpoint_parse_cdat(struct cxl_port *port)
 		return;
 	}
 
-	/* Performance data processing */
+	rc = cxl_port_perf_data_calculate(port, dsmas_xa);
+	if (rc) {
+		dev_dbg(&port->dev, "Failed to do perf coord calculations.\n");
+		return;
+	}
+
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
 
-- 
GitLab


From 86557b7edf77d2a3835136c325c8baa6fe803234 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:04:11 -0700
Subject: [PATCH 1841/4076] cxl: Store QTG IDs and related info to the CXL
 memory device context

Once the QTG ID _DSM is executed successfully, the QTG ID is retrieved from
the return package. Create a list of entries in the cxl_memdev context and
store the QTG ID as qos_class token and the associated DPA range. This
information can be exposed to user space via sysfs in order to help region
setup for hot-plugged CXL memory devices.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319625109.2212653.11872111896220384056.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/cdat.c | 69 +++++++++++++++++++++++++++++++++++++++++
 drivers/cxl/core/mbox.c |  2 ++
 drivers/cxl/cxlmem.h    | 21 +++++++++++++
 3 files changed, 92 insertions(+)

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 43dfef80fb847..6189d967f399c 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -6,6 +6,7 @@
 #include <linux/node.h>
 #include <linux/overflow.h>
 #include "cxlpci.h"
+#include "cxlmem.h"
 #include "cxl.h"
 
 struct dsmas_entry {
@@ -206,6 +207,71 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 	return 0;
 }
 
+static void add_perf_entry(struct device *dev, struct dsmas_entry *dent,
+			   struct list_head *list)
+{
+	struct cxl_dpa_perf *dpa_perf;
+
+	dpa_perf = kzalloc(sizeof(*dpa_perf), GFP_KERNEL);
+	if (!dpa_perf)
+		return;
+
+	dpa_perf->dpa_range = dent->dpa_range;
+	dpa_perf->coord = dent->coord;
+	dpa_perf->qos_class = dent->qos_class;
+	list_add_tail(&dpa_perf->list, list);
+	dev_dbg(dev,
+		"DSMAS: dpa: %#llx qos: %d read_bw: %d write_bw %d read_lat: %d write_lat: %d\n",
+		dent->dpa_range.start, dpa_perf->qos_class,
+		dent->coord.read_bandwidth, dent->coord.write_bandwidth,
+		dent->coord.read_latency, dent->coord.write_latency);
+}
+
+static void free_perf_ents(void *data)
+{
+	struct cxl_memdev_state *mds = data;
+	struct cxl_dpa_perf *dpa_perf, *n;
+	LIST_HEAD(discard);
+
+	list_splice_tail_init(&mds->ram_perf_list, &discard);
+	list_splice_tail_init(&mds->pmem_perf_list, &discard);
+	list_for_each_entry_safe(dpa_perf, n, &discard, list) {
+		list_del(&dpa_perf->list);
+		kfree(dpa_perf);
+	}
+}
+
+static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
+				     struct xarray *dsmas_xa)
+{
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct device *dev = cxlds->dev;
+	struct range pmem_range = {
+		.start = cxlds->pmem_res.start,
+		.end = cxlds->pmem_res.end,
+	};
+	struct range ram_range = {
+		.start = cxlds->ram_res.start,
+		.end = cxlds->ram_res.end,
+	};
+	struct dsmas_entry *dent;
+	unsigned long index;
+
+	xa_for_each(dsmas_xa, index, dent) {
+		if (resource_size(&cxlds->ram_res) &&
+		    range_contains(&ram_range, &dent->dpa_range))
+			add_perf_entry(dev, dent, &mds->ram_perf_list);
+		else if (resource_size(&cxlds->pmem_res) &&
+			 range_contains(&pmem_range, &dent->dpa_range))
+			add_perf_entry(dev, dent, &mds->pmem_perf_list);
+		else
+			dev_dbg(dev, "no partition for dsmas dpa: %#llx\n",
+				dent->dpa_range.start);
+	}
+
+	devm_add_action_or_reset(&cxlds->cxlmd->dev, free_perf_ents, mds);
+}
+
 static void discard_dsmas(struct xarray *xa)
 {
 	unsigned long index;
@@ -221,6 +287,8 @@ DEFINE_FREE(dsmas, struct xarray *, if (_T) discard_dsmas(_T))
 
 void cxl_endpoint_parse_cdat(struct cxl_port *port)
 {
+	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct xarray __dsmas_xa;
 	struct xarray *dsmas_xa __free(dsmas) = &__dsmas_xa;
 	int rc;
@@ -241,6 +309,7 @@ void cxl_endpoint_parse_cdat(struct cxl_port *port)
 		return;
 	}
 
+	cxl_memdev_set_qos_class(cxlds, dsmas_xa);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
 
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 36270dcfb42ef..fbaa508ab2451 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1404,6 +1404,8 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev)
 	mds->cxlds.reg_map.host = dev;
 	mds->cxlds.reg_map.resource = CXL_RESOURCE_NONE;
 	mds->cxlds.type = CXL_DEVTYPE_CLASSMEM;
+	INIT_LIST_HEAD(&mds->ram_perf_list);
+	INIT_LIST_HEAD(&mds->pmem_perf_list);
 
 	return mds;
 }
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index a2fcbca253f39..205bc2a016b2b 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -6,6 +6,7 @@
 #include <linux/cdev.h>
 #include <linux/uuid.h>
 #include <linux/rcuwait.h>
+#include <linux/node.h>
 #include "cxl.h"
 
 /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
@@ -391,6 +392,20 @@ enum cxl_devtype {
 	CXL_DEVTYPE_CLASSMEM,
 };
 
+/**
+ * struct cxl_dpa_perf - DPA performance property entry
+ * @list - list entry
+ * @dpa_range - range for DPA address
+ * @coord - QoS performance data (i.e. latency, bandwidth)
+ * @qos_class - QoS Class cookies
+ */
+struct cxl_dpa_perf {
+	struct list_head list;
+	struct range dpa_range;
+	struct access_coordinate coord;
+	int qos_class;
+};
+
 /**
  * struct cxl_dev_state - The driver device state
  *
@@ -455,6 +470,8 @@ struct cxl_dev_state {
  * @security: security driver state info
  * @fw: firmware upload / activation state
  * @mbox_send: @dev specific transport for transmitting mailbox commands
+ * @ram_perf_list: performance data entries matched to RAM
+ * @pmem_perf_list: performance data entries matched to PMEM
  *
  * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for
  * details on capacity parameters.
@@ -475,6 +492,10 @@ struct cxl_memdev_state {
 	u64 active_persistent_bytes;
 	u64 next_volatile_bytes;
 	u64 next_persistent_bytes;
+
+	struct list_head ram_perf_list;
+	struct list_head pmem_perf_list;
+
 	struct cxl_event_state event;
 	struct cxl_poison_state poison;
 	struct cxl_security_state security;
-- 
GitLab


From 42834b17cf1f00fa79ff1f02134f9c576a125252 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:04:16 -0700
Subject: [PATCH 1842/4076] cxl: Export sysfs attributes for memory device QoS
 class

Export qos_class sysfs attributes for the CXL memory device. The QoS clas
should show up as /sys/bus/cxl/devices/memX/ram/qos_class for the volatile
partition and /sys/bus/cxl/devices/memX/pmem/qos_class for the persistent
partition. The QTG ID is retrieved via _DSM after supplying the
calculated bandwidth and latency for the entire CXL path from device to
the CPU. This ID is used to match up to the root decoder QoS class to
determine which CFMWS the memory range of a hotplugged CXL mem device
should be assigned under.

While there may be multiple DSMAS exported by the device CDAT, the driver
will only expose the first QTG ID per partition in sysfs for now. In the
future when multiple QTG IDs are necessary, they can be exposed. [1]

[1]: https://lore.kernel.org/linux-cxl/167571650007.587790.10040913293130712882.stgit@djiang5-mobl3.local/T/#md2a47b1ead3e1ba08f50eab29a4af1aed1d215ab

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319625698.2212653.17544381274847420961.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 Documentation/ABI/testing/sysfs-bus-cxl | 34 +++++++++++++
 drivers/cxl/mem.c                       | 67 ++++++++++++++++++++++---
 2 files changed, 95 insertions(+), 6 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
index e76c3600607f8..fff2581b80335 100644
--- a/Documentation/ABI/testing/sysfs-bus-cxl
+++ b/Documentation/ABI/testing/sysfs-bus-cxl
@@ -28,6 +28,23 @@ Description:
 		Payload in the CXL-2.0 specification.
 
 
+What:		/sys/bus/cxl/devices/memX/ram/qos_class
+Date:		May, 2023
+KernelVersion:	v6.8
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) For CXL host platforms that support "QoS Telemmetry"
+		this attribute conveys a comma delimited list of platform
+		specific cookies that identifies a QoS performance class
+		for the volatile partition of the CXL mem device. These
+		class-ids can be compared against a similar "qos_class"
+		published for a root decoder. While it is not required
+		that the endpoints map their local memory-class to a
+		matching platform class, mismatches are not recommended
+		and there are platform specific performance related
+		side-effects that may result. First class-id is displayed.
+
+
 What:		/sys/bus/cxl/devices/memX/pmem/size
 Date:		December, 2020
 KernelVersion:	v5.12
@@ -38,6 +55,23 @@ Description:
 		Payload in the CXL-2.0 specification.
 
 
+What:		/sys/bus/cxl/devices/memX/pmem/qos_class
+Date:		May, 2023
+KernelVersion:	v6.8
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) For CXL host platforms that support "QoS Telemmetry"
+		this attribute conveys a comma delimited list of platform
+		specific cookies that identifies a QoS performance class
+		for the persistent partition of the CXL mem device. These
+		class-ids can be compared against a similar "qos_class"
+		published for a root decoder. While it is not required
+		that the endpoints map their local memory-class to a
+		matching platform class, mismatches are not recommended
+		and there are platform specific performance related
+		side-effects that may result. First class-id is displayed.
+
+
 What:		/sys/bus/cxl/devices/memX/serial
 Date:		January, 2022
 KernelVersion:	v5.18
diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index e087febf9af04..c5c9d8e0d88d6 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -215,23 +215,78 @@ static ssize_t trigger_poison_list_store(struct device *dev,
 }
 static DEVICE_ATTR_WO(trigger_poison_list);
 
+static ssize_t ram_qos_class_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct cxl_dpa_perf *dpa_perf;
+
+	if (!dev->driver)
+		return -ENOENT;
+
+	if (list_empty(&mds->ram_perf_list))
+		return -ENOENT;
+
+	dpa_perf = list_first_entry(&mds->ram_perf_list, struct cxl_dpa_perf,
+				    list);
+
+	return sysfs_emit(buf, "%d\n", dpa_perf->qos_class);
+}
+
+static struct device_attribute dev_attr_ram_qos_class =
+	__ATTR(qos_class, 0444, ram_qos_class_show, NULL);
+
+static ssize_t pmem_qos_class_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct cxl_dpa_perf *dpa_perf;
+
+	if (!dev->driver)
+		return -ENOENT;
+
+	if (list_empty(&mds->pmem_perf_list))
+		return -ENOENT;
+
+	dpa_perf = list_first_entry(&mds->pmem_perf_list, struct cxl_dpa_perf,
+				    list);
+
+	return sysfs_emit(buf, "%d\n", dpa_perf->qos_class);
+}
+
+static struct device_attribute dev_attr_pmem_qos_class =
+	__ATTR(qos_class, 0444, pmem_qos_class_show, NULL);
+
 static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n)
 {
-	if (a == &dev_attr_trigger_poison_list.attr) {
-		struct device *dev = kobj_to_dev(kobj);
-		struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
-		struct cxl_memdev_state *mds =
-			to_cxl_memdev_state(cxlmd->cxlds);
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
 
+	if (a == &dev_attr_trigger_poison_list.attr)
 		if (!test_bit(CXL_POISON_ENABLED_LIST,
 			      mds->poison.enabled_cmds))
 			return 0;
-	}
+
+	if (a == &dev_attr_pmem_qos_class.attr)
+		if (list_empty(&mds->pmem_perf_list))
+			return 0;
+
+	if (a == &dev_attr_ram_qos_class.attr)
+		if (list_empty(&mds->ram_perf_list))
+			return 0;
+
 	return a->mode;
 }
 
 static struct attribute *cxl_mem_attrs[] = {
 	&dev_attr_trigger_poison_list.attr,
+	&dev_attr_ram_qos_class.attr,
+	&dev_attr_pmem_qos_class.attr,
 	NULL
 };
 
-- 
GitLab


From 185c1a489f873cb71520fc089401e02dbf302dcd Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:04:23 -0700
Subject: [PATCH 1843/4076] cxl: Check qos_class validity on memdev probe

Add a check to make sure the qos_class for the device will match one of
the root decoders qos_class. If no match is found, then the qos_class for
the device is set to invalid. Also add a check to ensure that the device's
host bridge matches to one of the root decoder's downstream targets.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319626313.2212653.9021004640856081917.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/cdat.c | 103 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 103 insertions(+)

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 6189d967f399c..cd84d87f597a6 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -272,6 +272,108 @@ static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
 	devm_add_action_or_reset(&cxlds->cxlmd->dev, free_perf_ents, mds);
 }
 
+static int match_cxlrd_qos_class(struct device *dev, void *data)
+{
+	int dev_qos_class = *(int *)data;
+	struct cxl_root_decoder *cxlrd;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxlrd = to_cxl_root_decoder(dev);
+	if (cxlrd->qos_class == CXL_QOS_CLASS_INVALID)
+		return 0;
+
+	if (cxlrd->qos_class == dev_qos_class)
+		return 1;
+
+	return 0;
+}
+
+static void cxl_qos_match(struct cxl_port *root_port,
+			  struct list_head *work_list,
+			  struct list_head *discard_list)
+{
+	struct cxl_dpa_perf *dpa_perf, *n;
+
+	list_for_each_entry_safe(dpa_perf, n, work_list, list) {
+		int rc;
+
+		if (dpa_perf->qos_class == CXL_QOS_CLASS_INVALID)
+			return;
+
+		rc = device_for_each_child(&root_port->dev,
+					   (void *)&dpa_perf->qos_class,
+					   match_cxlrd_qos_class);
+		if (!rc)
+			list_move_tail(&dpa_perf->list, discard_list);
+	}
+}
+
+static int match_cxlrd_hb(struct device *dev, void *data)
+{
+	struct device *host_bridge = data;
+	struct cxl_switch_decoder *cxlsd;
+	struct cxl_root_decoder *cxlrd;
+	unsigned int seq;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxlrd = to_cxl_root_decoder(dev);
+	cxlsd = &cxlrd->cxlsd;
+
+	do {
+		seq = read_seqbegin(&cxlsd->target_lock);
+		for (int i = 0; i < cxlsd->nr_targets; i++) {
+			if (host_bridge == cxlsd->target[i]->dport_dev)
+				return 1;
+		}
+	} while (read_seqretry(&cxlsd->target_lock, seq));
+
+	return 0;
+}
+
+static void discard_dpa_perf(struct list_head *list)
+{
+	struct cxl_dpa_perf *dpa_perf, *n;
+
+	list_for_each_entry_safe(dpa_perf, n, list, list) {
+		list_del(&dpa_perf->list);
+		kfree(dpa_perf);
+	}
+}
+DEFINE_FREE(dpa_perf, struct list_head *, if (!list_empty(_T)) discard_dpa_perf(_T))
+
+static int cxl_qos_class_verify(struct cxl_memdev *cxlmd)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct cxl_port *root_port __free(put_device) = NULL;
+	LIST_HEAD(__discard);
+	struct list_head *discard __free(dpa_perf) = &__discard;
+	int rc;
+
+	root_port = find_cxl_root(cxlmd->endpoint);
+	if (!root_port)
+		return -ENODEV;
+
+	/* Check that the QTG IDs are all sane between end device and root decoders */
+	cxl_qos_match(root_port, &mds->ram_perf_list, discard);
+	cxl_qos_match(root_port, &mds->pmem_perf_list, discard);
+
+	/* Check to make sure that the device's host bridge is under a root decoder */
+	rc = device_for_each_child(&root_port->dev,
+				   (void *)cxlmd->endpoint->host_bridge,
+				   match_cxlrd_hb);
+	if (!rc) {
+		list_splice_tail_init(&mds->ram_perf_list, discard);
+		list_splice_tail_init(&mds->pmem_perf_list, discard);
+	}
+
+	return rc;
+}
+
 static void discard_dsmas(struct xarray *xa)
 {
 	unsigned long index;
@@ -310,6 +412,7 @@ void cxl_endpoint_parse_cdat(struct cxl_port *port)
 	}
 
 	cxl_memdev_set_qos_class(cxlds, dsmas_xa);
+	cxl_qos_class_verify(cxlmd);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
 
-- 
GitLab


From aefebd19a8422eb9253cf137e526cc3b11c95a88 Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Fri, 22 Dec 2023 00:01:08 +0530
Subject: [PATCH 1844/4076] dt-bindings: input: convert drv266x to json-schema

Convert devicetree binding documentation for ti drv2665 and drv2667
haptics driver to json-schema. The previously two separate bindings have
been merged into a single drv266x.yaml.

Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231221183109.684325-1-anshulusr@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/ti,drv2665.txt  | 17 -------
 .../devicetree/bindings/input/ti,drv2667.txt  | 17 -------
 .../devicetree/bindings/input/ti,drv266x.yaml | 50 +++++++++++++++++++
 3 files changed, 50 insertions(+), 34 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/input/ti,drv2665.txt
 delete mode 100644 Documentation/devicetree/bindings/input/ti,drv2667.txt
 create mode 100644 Documentation/devicetree/bindings/input/ti,drv266x.yaml

diff --git a/Documentation/devicetree/bindings/input/ti,drv2665.txt b/Documentation/devicetree/bindings/input/ti,drv2665.txt
deleted file mode 100644
index 1ba97ac043058..0000000000000
--- a/Documentation/devicetree/bindings/input/ti,drv2665.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-* Texas Instruments - drv2665 Haptics driver
-
-Required properties:
-	- compatible - "ti,drv2665" - DRV2665
-	- reg -  I2C slave address
-	- vbat-supply - Required supply regulator
-
-Example:
-
-haptics: haptics@59 {
-	compatible = "ti,drv2665";
-	reg = <0x59>;
-	vbat-supply = <&vbat>;
-};
-
-For more product information please see the link below:
-http://www.ti.com/product/drv2665
diff --git a/Documentation/devicetree/bindings/input/ti,drv2667.txt b/Documentation/devicetree/bindings/input/ti,drv2667.txt
deleted file mode 100644
index 996382cf994a1..0000000000000
--- a/Documentation/devicetree/bindings/input/ti,drv2667.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-* Texas Instruments - drv2667 Haptics driver
-
-Required properties:
-	- compatible - "ti,drv2667" - DRV2667
-	- reg -  I2C slave address
-	- vbat-supply - Required supply regulator
-
-Example:
-
-haptics: haptics@59 {
-	compatible = "ti,drv2667";
-	reg = <0x59>;
-	vbat-supply = <&vbat>;
-};
-
-For more product information please see the link below:
-http://www.ti.com/product/drv2667
diff --git a/Documentation/devicetree/bindings/input/ti,drv266x.yaml b/Documentation/devicetree/bindings/input/ti,drv266x.yaml
new file mode 100644
index 0000000000000..da18188243738
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/ti,drv266x.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/ti,drv266x.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments - drv266x Haptics driver
+
+description: |
+  Product Page:
+    http://www.ti.com/product/drv2665
+    http://www.ti.com/product/drv2667
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - ti,drv2665
+      - ti,drv2667
+
+  reg:
+    maxItems: 1
+
+  vbat-supply:
+    description: Required supply regulator
+
+required:
+  - compatible
+  - reg
+  - vbat-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        haptics@59 {
+            compatible = "ti,drv2667";
+            reg = <0x59>;
+            vbat-supply = <&vbat>;
+        };
+    };
-- 
GitLab


From 2731d605d5478052a10ac5a7c80f7aa7e1788cc5 Mon Sep 17 00:00:00 2001
From: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Date: Tue, 19 Dec 2023 15:08:50 +0100
Subject: [PATCH 1845/4076] KVM: s390: vsie: Fix STFLE interpretive execution
 identification

STFLE can be interpretively executed.
This occurs when the facility list designation is unequal to zero.
Perform the check before applying the address mask instead of after.

Fixes: 66b630d5b7f2 ("KVM: s390: vsie: support STFLE interpretation")
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Link: https://lore.kernel.org/r/20231219140854.1042599-2-nsg@linux.ibm.com
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Message-ID: <20231219140854.1042599-2-nsg@linux.ibm.com>
---
 arch/s390/kvm/vsie.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 02dcbe82a8e51..3cf95bc0401de 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -988,10 +988,15 @@ static void retry_vsie_icpt(struct vsie_page *vsie_page)
 static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
-	__u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U;
+	__u32 fac = READ_ONCE(vsie_page->scb_o->fac);
 
 	if (fac && test_kvm_facility(vcpu->kvm, 7)) {
 		retry_vsie_icpt(vsie_page);
+		/*
+		 * The facility list origin (FLO) is in bits 1 - 28 of the FLD
+		 * so we need to mask here before reading.
+		 */
+		fac = fac & 0x7ffffff8U;
 		if (read_guest_real(vcpu, fac, &vsie_page->fac,
 				    sizeof(vsie_page->fac)))
 			return set_validity_icpt(scb_s, 0x1090U);
-- 
GitLab


From 682dbf430d27bc0e23d8d6921116b4f77f5dc9c6 Mon Sep 17 00:00:00 2001
From: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Date: Tue, 19 Dec 2023 15:08:51 +0100
Subject: [PATCH 1846/4076] KVM: s390: vsie: Fix length of facility list
 shadowed

The length of the facility list accessed when interpretively executing
STFLE is the same as the hosts facility list (in case of format-0)
The memory following the facility list doesn't need to be accessible.
The current VSIE implementation accesses a fixed length that exceeds the
guest/host facility list length and can therefore wrongly inject a
validity intercept.
Instead, find out the host facility list length by running STFLE and
copy only as much as necessary when shadowing.

Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Link: https://lore.kernel.org/r/20231219140854.1042599-3-nsg@linux.ibm.com
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Message-ID: <20231219140854.1042599-3-nsg@linux.ibm.com>
---
 arch/s390/include/asm/facility.h |  6 ++++++
 arch/s390/kernel/Makefile        |  2 +-
 arch/s390/kernel/facility.c      | 21 +++++++++++++++++++++
 arch/s390/kvm/vsie.c             | 12 +++++++++++-
 4 files changed, 39 insertions(+), 2 deletions(-)
 create mode 100644 arch/s390/kernel/facility.c

diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 94b6919026dfb..796007125dff2 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -111,4 +111,10 @@ static inline void stfle(u64 *stfle_fac_list, int size)
 	preempt_enable();
 }
 
+/**
+ * stfle_size - Actual size of the facility list as specified by stfle
+ * (number of double words)
+ */
+unsigned int stfle_size(void);
+
 #endif /* __ASM_FACILITY_H */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 353def93973b3..7a562b4199c81 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -41,7 +41,7 @@ obj-y	+= sysinfo.o lgr.o os_info.o ctlreg.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o kdebugfs.o alternative.o
 obj-y	+= nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
-obj-y	+= smp.o text_amode31.o stacktrace.o abs_lowcore.o
+obj-y	+= smp.o text_amode31.o stacktrace.o abs_lowcore.o facility.o
 
 extra-y				+= vmlinux.lds
 
diff --git a/arch/s390/kernel/facility.c b/arch/s390/kernel/facility.c
new file mode 100644
index 0000000000000..f02127219a27b
--- /dev/null
+++ b/arch/s390/kernel/facility.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2023
+ */
+
+#include <asm/facility.h>
+
+unsigned int stfle_size(void)
+{
+	static unsigned int size;
+	unsigned int r;
+	u64 dummy;
+
+	r = READ_ONCE(size);
+	if (!r) {
+		r = __stfle_asm(&dummy, 1) + 1;
+		WRITE_ONCE(size, r);
+	}
+	return r;
+}
+EXPORT_SYMBOL(stfle_size);
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 3cf95bc0401de..aa8f4ab11e33e 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -19,6 +19,7 @@
 #include <asm/nmi.h>
 #include <asm/dis.h>
 #include <asm/fpu/api.h>
+#include <asm/facility.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -990,6 +991,10 @@ static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	__u32 fac = READ_ONCE(vsie_page->scb_o->fac);
 
+	/*
+	 * Alternate-STFLE-Interpretive-Execution facilities are not supported
+	 * -> format-0 flcb
+	 */
 	if (fac && test_kvm_facility(vcpu->kvm, 7)) {
 		retry_vsie_icpt(vsie_page);
 		/*
@@ -997,8 +1002,13 @@ static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		 * so we need to mask here before reading.
 		 */
 		fac = fac & 0x7ffffff8U;
+		/*
+		 * format-0 -> size of nested guest's facility list == guest's size
+		 * guest's size == host's size, since STFLE is interpretatively executed
+		 * using a format-0 for the guest, too.
+		 */
 		if (read_guest_real(vcpu, fac, &vsie_page->fac,
-				    sizeof(vsie_page->fac)))
+				    stfle_size() * sizeof(u64)))
 			return set_validity_icpt(scb_s, 0x1090U);
 		scb_s->fac = (__u32)(__u64) &vsie_page->fac;
 	}
-- 
GitLab


From 10f7b1dcdfe05efcd26e90e337daf1bfd8f4a6da Mon Sep 17 00:00:00 2001
From: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Date: Tue, 19 Dec 2023 15:08:52 +0100
Subject: [PATCH 1847/4076] KVM: s390: cpu model: Use proper define for
 facility mask size

Use the previously unused S390_ARCH_FAC_MASK_SIZE_U64 instead of
S390_ARCH_FAC_LIST_SIZE_U64 for defining the fac_mask array.
Note that both values are the same, there is no functional change.

Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Link: https://lore.kernel.org/r/20231219140854.1042599-4-nsg@linux.ibm.com
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Message-ID: <20231219140854.1042599-4-nsg@linux.ibm.com>
---
 arch/s390/include/asm/kvm_host.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 67a298b6cf6e9..52664105a473f 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -818,7 +818,7 @@ struct s390_io_adapter {
 
 struct kvm_s390_cpu_model {
 	/* facility mask supported by kvm & hosting machine */
-	__u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64];
+	__u64 fac_mask[S390_ARCH_FAC_MASK_SIZE_U64];
 	struct kvm_s390_vm_cpu_subfunc subfuncs;
 	/* facility list requested by guest (in dma page) */
 	__u64 *fac_list;
-- 
GitLab


From 5090a4bc2a2f04b7693b49500ad1287e8d0fb6c3 Mon Sep 17 00:00:00 2001
From: Piro Yang <piroyangg@gmail.com>
Date: Wed, 20 Dec 2023 01:04:47 +0800
Subject: [PATCH 1848/4076] staging: vme_user: Fix the issue of return the
 wrong error code

Fix the issue of returning the -ENOSYS error code when an error occurs.

The error code of -ENOSYS indicates Invalid system call number, but
there is not system call error. So replace -ENOSYS error code by the
return -EINVAL error code.

Signed-off-by: Piro Yang <piroyangg@gmail.com>
Link: https://lore.kernel.org/r/20231219170447.51237-1-piroyangg@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vme_user/vme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/vme_user/vme.c b/drivers/staging/vme_user/vme.c
index 5c416c31ec576..9bc2d35405af6 100644
--- a/drivers/staging/vme_user/vme.c
+++ b/drivers/staging/vme_user/vme.c
@@ -341,7 +341,7 @@ int vme_slave_set(struct vme_resource *resource, int enabled,
 
 	if (!bridge->slave_set) {
 		dev_err(bridge->parent, "Function not supported\n");
-		return -ENOSYS;
+		return -EINVAL;
 	}
 
 	if (!(((image->address_attr & aspace) == aspace) &&
-- 
GitLab


From 6911a08ce778bd15dd42306ab17594faf0ae6149 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 21 Dec 2023 13:34:09 -0500
Subject: [PATCH 1849/4076] staging: rtl8192e: rename variable
 HTInitializeBssDesc

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTInitializeBssDesc -> ht_initialize_bss_desc

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231221183413.8349-2-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_rx.c      | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 0d57bcda33b4d..edfc2c7461ee1 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -543,7 +543,7 @@ void ht_initialize_ht_info(struct rtllib_device *ieee)
 	}
 }
 
-void HTInitializeBssDesc(struct bss_ht *pBssHT)
+void ht_initialize_bss_desc(struct bss_ht *pBssHT)
 {
 	pBssHT->bd_support_ht = false;
 	memset(pBssHT->bd_ht_cap_buf, 0, sizeof(pBssHT->bd_ht_cap_buf));
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 4df46eae6aa89..193b4a5a7c049 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1758,7 +1758,7 @@ void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee,
 				u8 *posRT2RTAgg, u8 *len);
 void ht_on_assoc_rsp(struct rtllib_device *ieee);
 void ht_initialize_ht_info(struct rtllib_device *ieee);
-void HTInitializeBssDesc(struct bss_ht *pBssHT);
+void ht_initialize_bss_desc(struct bss_ht *pBssHT);
 void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
 				   struct rtllib_network *pNetwork);
 void HT_update_self_and_peer_setting(struct rtllib_device *ieee,
diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index 196eacc7a768a..5f219cfb65eb4 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -2189,7 +2189,7 @@ static inline int rtllib_network_init(
 	network->RSSI = stats->SignalStrength;
 	network->CountryIeLen = 0;
 	memset(network->CountryIeBuf, 0, MAX_IE_LEN);
-	HTInitializeBssDesc(&network->bssht);
+	ht_initialize_bss_desc(&network->bssht);
 	network->flags |= NETWORK_HAS_CCK;
 
 	network->wpa_ie_len = 0;
-- 
GitLab


From 0901e69611a1fbe03761d1024fd65b37aa33ab8d Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 21 Dec 2023 13:34:10 -0500
Subject: [PATCH 1850/4076] staging: rtl8192e: rename variable
 HTResetSelfAndSavePeerSetting

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTResetSelfAndSavePeerSetting -> ht_reset_self_and_save_peer_setting

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231221183413.8349-3-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index edfc2c7461ee1..a32f3553df936 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -558,7 +558,7 @@ void ht_initialize_bss_desc(struct bss_ht *pBssHT)
 	pBssHT->rt2rt_ht_mode = (enum rt_ht_capability)0;
 }
 
-void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
+void ht_reset_self_and_save_peer_setting(struct rtllib_device *ieee,
 				   struct rtllib_network *pNetwork)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 193b4a5a7c049..78eae7daa3511 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1759,7 +1759,7 @@ void ht_construct_rt2rt_agg_element(struct rtllib_device *ieee,
 void ht_on_assoc_rsp(struct rtllib_device *ieee);
 void ht_initialize_ht_info(struct rtllib_device *ieee);
 void ht_initialize_bss_desc(struct bss_ht *pBssHT);
-void HTResetSelfAndSavePeerSetting(struct rtllib_device *ieee,
+void ht_reset_self_and_save_peer_setting(struct rtllib_device *ieee,
 				   struct rtllib_network *pNetwork);
 void HT_update_self_and_peer_setting(struct rtllib_device *ieee,
 				     struct rtllib_network *pNetwork);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 9c94c5ceccd56..14f34e6a591a8 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1219,7 +1219,7 @@ inline void rtllib_softmac_new_net(struct rtllib_device *ieee,
 				ieee->AsocRetryCount = 0;
 				if ((ieee->current_network.qos_data.supported == 1) &&
 				    ieee->current_network.bssht.bd_support_ht)
-					HTResetSelfAndSavePeerSetting(ieee,
+					ht_reset_self_and_save_peer_setting(ieee,
 						 &(ieee->current_network));
 				else
 					ieee->ht_info->current_ht_support = false;
-- 
GitLab


From b399e2397443b25ac6e0a83fa5daa1384cec4135 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 21 Dec 2023 13:34:11 -0500
Subject: [PATCH 1851/4076] staging: rtl8192e: rename variable HTCCheck

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTCCheck -> ht_c_check

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231221183413.8349-4-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 2 +-
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_rx.c      | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index a32f3553df936..5698b48fdcc97 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -622,7 +622,7 @@ void HT_update_self_and_peer_setting(struct rtllib_device *ieee,
 }
 EXPORT_SYMBOL(HT_update_self_and_peer_setting);
 
-u8 HTCCheck(struct rtllib_device *ieee, u8 *pFrame)
+u8 ht_c_check(struct rtllib_device *ieee, u8 *pFrame)
 {
 	if (ieee->ht_info->current_ht_support) {
 		if ((IsQoSDataFrame(pFrame) && Frame_Order(pFrame)) == 1) {
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 78eae7daa3511..341d9ddc9a1f4 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1767,7 +1767,7 @@ u8 ht_get_highest_mcs_rate(struct rtllib_device *ieee, u8 *pMCSRateSet,
 		       u8 *pMCSFilter);
 extern u8 MCS_FILTER_ALL[];
 extern u16 MCS_DATA_RATE[2][2][77];
-u8 HTCCheck(struct rtllib_device *ieee, u8 *pFrame);
+u8 ht_c_check(struct rtllib_device *ieee, u8 *pFrame);
 void ht_reset_iot_setting(struct rt_hi_throughput *ht_info);
 bool is_ht_half_nmode_aps(struct rtllib_device *ieee);
 u16  tx_count_to_data_rate(struct rtllib_device *ieee, u8 nDataRate);
diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index 5f219cfb65eb4..595ec9af25ea0 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -857,7 +857,7 @@ static size_t rtllib_rx_get_hdrlen(struct rtllib_device *ieee,
 	size_t hdrlen;
 
 	hdrlen = rtllib_get_hdrlen(fc);
-	if (HTCCheck(ieee, skb->data)) {
+	if (ht_c_check(ieee, skb->data)) {
 		if (net_ratelimit())
 			netdev_info(ieee->dev, "%s: find HTCControl!\n",
 				    __func__);
@@ -1401,7 +1401,7 @@ static int rtllib_rx_Monitor(struct rtllib_device *ieee, struct sk_buff *skb,
 		return 0;
 	}
 
-	if (HTCCheck(ieee, skb->data)) {
+	if (ht_c_check(ieee, skb->data)) {
 		if (net_ratelimit())
 			netdev_info(ieee->dev, "%s: Find HTCControl!\n",
 				    __func__);
-- 
GitLab


From 35350898acc734b748b456a196a1e6eda316ef14 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 21 Dec 2023 13:34:12 -0500
Subject: [PATCH 1852/4076] staging: rtl8192e: rename variable
 HTSetConnectBwModeCallback

Coding style issue, checkpatch Avoid CamelCase,
rename it. HTSetConnectBwModeCallback -> ht_set_connect_bw_mode_callback

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231221183413.8349-5-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index 5698b48fdcc97..ac17d510a2a5d 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -633,7 +633,7 @@ u8 ht_c_check(struct rtllib_device *ieee, u8 *pFrame)
 	return false;
 }
 
-static void HTSetConnectBwModeCallback(struct rtllib_device *ieee)
+static void ht_set_connect_bw_mode_callback(struct rtllib_device *ieee)
 {
 	struct rt_hi_throughput *ht_info = ieee->ht_info;
 
@@ -695,5 +695,5 @@ void ht_set_connect_bw_mode(struct rtllib_device *ieee,
 
 	ht_info->sw_bw_in_progress = true;
 
-	HTSetConnectBwModeCallback(ieee);
+	ht_set_connect_bw_mode_callback(ieee);
 }
-- 
GitLab


From 93235f62e8a1e111fc45c0143e0b27c6d6dd9cb6 Mon Sep 17 00:00:00 2001
From: Gary Rookard <garyrookard@fastmail.org>
Date: Thu, 21 Dec 2023 13:34:13 -0500
Subject: [PATCH 1853/4076] staging: rtl8192e: rename variable ePeerHTSpecVer

Coding style issue, checkpatch Avoid CamelCase,
rename it. ePeerHTSpecVer -> peer_ht_spec_ver

Signed-off-by: Gary Rookard <garyrookard@fastmail.org>
Link: https://lore.kernel.org/r/20231221183413.8349-6-garyrookard@fastmail.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl819x_HT.h     | 2 +-
 drivers/staging/rtl8192e/rtl819x_HTProc.c | 6 +++---
 drivers/staging/rtl8192e/rtllib_softmac.c | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h
index 2911ea82dd178..68577bffb936d 100644
--- a/drivers/staging/rtl8192e/rtl819x_HT.h
+++ b/drivers/staging/rtl8192e/rtl819x_HT.h
@@ -97,7 +97,7 @@ struct rt_hi_throughput {
 	u8 cur_bw_40mhz;
 	u8 cur_short_gi_40mhz;
 	u8 cur_short_gi_20mhz;
-	enum ht_spec_ver ePeerHTSpecVer;
+	enum ht_spec_ver peer_ht_spec_ver;
 	struct ht_capab_ele SelfHTCap;
 	u8 PeerHTCapBuf[32];
 	u8 PeerHTInfoBuf[32];
diff --git a/drivers/staging/rtl8192e/rtl819x_HTProc.c b/drivers/staging/rtl8192e/rtl819x_HTProc.c
index ac17d510a2a5d..6d0912f90198f 100644
--- a/drivers/staging/rtl8192e/rtl819x_HTProc.c
+++ b/drivers/staging/rtl8192e/rtl819x_HTProc.c
@@ -240,7 +240,7 @@ void ht_construct_capability_element(struct rtllib_device *ieee, u8 *pos_ht_cap,
 	}
 	memset(pos_ht_cap, 0, *len);
 
-	if ((assoc) && (ht->ePeerHTSpecVer == HT_SPEC_VER_EWC)) {
+	if ((assoc) && (ht->peer_ht_spec_ver == HT_SPEC_VER_EWC)) {
 		static const u8	EWC11NHTCap[] = { 0x00, 0x90, 0x4c, 0x33 };
 
 		memcpy(pos_ht_cap, EWC11NHTCap, sizeof(EWC11NHTCap));
@@ -525,7 +525,7 @@ void ht_initialize_ht_info(struct rtllib_device *ieee)
 
 	ht_info->sw_bw_in_progress = false;
 
-	ht_info->ePeerHTSpecVer = HT_SPEC_VER_IEEE;
+	ht_info->peer_ht_spec_ver = HT_SPEC_VER_IEEE;
 
 	ht_info->current_rt2rt_aggregation = false;
 	ht_info->current_rt2rt_long_slot_time = false;
@@ -569,7 +569,7 @@ void ht_reset_self_and_save_peer_setting(struct rtllib_device *ieee,
 	 */
 	if (pNetwork->bssht.bd_support_ht) {
 		ht_info->current_ht_support = true;
-		ht_info->ePeerHTSpecVer = pNetwork->bssht.bd_ht_spec_ver;
+		ht_info->peer_ht_spec_ver = pNetwork->bssht.bd_ht_spec_ver;
 
 		if (pNetwork->bssht.bd_ht_cap_len > 0 &&
 		    pNetwork->bssht.bd_ht_cap_len <= sizeof(ht_info->PeerHTCapBuf))
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 14f34e6a591a8..953222d57f0e4 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -866,7 +866,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 		tag += osCcxVerNum.Length;
 	}
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
-		if (ieee->ht_info->ePeerHTSpecVer != HT_SPEC_VER_EWC) {
+		if (ieee->ht_info->peer_ht_spec_ver != HT_SPEC_VER_EWC) {
 			tag = skb_put(skb, ht_cap_len);
 			*tag++ = MFIE_TYPE_HT_CAP;
 			*tag++ = ht_cap_len - 2;
@@ -900,7 +900,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 	}
 
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
-		if (ieee->ht_info->ePeerHTSpecVer == HT_SPEC_VER_EWC) {
+		if (ieee->ht_info->peer_ht_spec_ver == HT_SPEC_VER_EWC) {
 			tag = skb_put(skb, ht_cap_len);
 			*tag++ = MFIE_TYPE_GENERIC;
 			*tag++ = ht_cap_len - 2;
-- 
GitLab


From b249bedb76ddfb5634c1a68477ee5dd9cba60b69 Mon Sep 17 00:00:00 2001
From: Ryan England <rcengland@gmail.com>
Date: Thu, 21 Dec 2023 20:22:48 +0000
Subject: [PATCH 1854/4076] staging: rtl8712: fix open parentheses alignment

Adhere to Linux kernel coding style.

Reported by checkpatch:

CHECK: Alignment should match open parenthesis

Signed-off-by: Ryan England <rcengland@gmail.com>
Link: https://lore.kernel.org/r/ZYSemFbzTlgLROMc@kernel.ryanengland.xyz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8712/os_intfs.c            |   3 +-
 drivers/staging/rtl8712/rtl8712_efuse.c       |   9 +-
 drivers/staging/rtl8712/rtl8712_recv.c        |   3 +-
 drivers/staging/rtl8712/rtl8712_xmit.c        |  60 +++---
 drivers/staging/rtl8712/rtl871x_cmd.c         | 159 +++++---------
 drivers/staging/rtl8712/rtl871x_cmd.h         |  37 ++--
 drivers/staging/rtl8712/rtl871x_ioctl_linux.c | 203 +++++++-----------
 7 files changed, 173 insertions(+), 301 deletions(-)

diff --git a/drivers/staging/rtl8712/os_intfs.c b/drivers/staging/rtl8712/os_intfs.c
index b18e6d9c832b8..7554613fe7e1e 100644
--- a/drivers/staging/rtl8712/os_intfs.c
+++ b/drivers/staging/rtl8712/os_intfs.c
@@ -221,8 +221,7 @@ struct net_device *r8712_init_netdev(void)
 
 static u32 start_drv_threads(struct _adapter *padapter)
 {
-	padapter->cmd_thread = kthread_run(r8712_cmd_thread, padapter, "%s",
-					  padapter->pnetdev->name);
+	padapter->cmd_thread = kthread_run(r8712_cmd_thread, padapter, "%s", padapter->pnetdev->name);
 	if (IS_ERR(padapter->cmd_thread))
 		return _FAIL;
 	return _SUCCESS;
diff --git a/drivers/staging/rtl8712/rtl8712_efuse.c b/drivers/staging/rtl8712/rtl8712_efuse.c
index c9400e40a1d63..a39d6c06648f5 100644
--- a/drivers/staging/rtl8712/rtl8712_efuse.c
+++ b/drivers/staging/rtl8712/rtl8712_efuse.c
@@ -213,8 +213,8 @@ u16 r8712_efuse_get_current_size(struct _adapter *adapter)
 	u8 hworden = 0;
 	u8 efuse_data, word_cnts = 0;
 
-	while (bContinual && efuse_one_byte_read(adapter, efuse_addr,
-	       &efuse_data) && (efuse_addr < efuse_available_max_size)) {
+	while (bContinual && efuse_one_byte_read(adapter, efuse_addr, &efuse_data) &&
+	       (efuse_addr < efuse_available_max_size)) {
 		if (efuse_data != 0xFF) {
 			hworden =  efuse_data & 0x0F;
 			word_cnts = calculate_word_cnts(hworden);
@@ -252,9 +252,8 @@ u8 r8712_efuse_pg_packet_read(struct _adapter *adapter, u8 offset, u8 *data)
 				memset(tmpdata, 0xFF, PGPKT_DATA_SIZE);
 				for (tmpidx = 0; tmpidx < word_cnts * 2;
 				     tmpidx++) {
-					if (efuse_one_byte_read(adapter,
-					    efuse_addr + 1 + tmpidx,
-					    &efuse_data)) {
+					if (efuse_one_byte_read(adapter, efuse_addr + 1 + tmpidx,
+								&efuse_data)) {
 						tmpdata[tmpidx] = efuse_data;
 					} else {
 						ret = false;
diff --git a/drivers/staging/rtl8712/rtl8712_recv.c b/drivers/staging/rtl8712/rtl8712_recv.c
index 7da014ab0723e..a3c4713c59b3a 100644
--- a/drivers/staging/rtl8712/rtl8712_recv.c
+++ b/drivers/staging/rtl8712/rtl8712_recv.c
@@ -267,8 +267,7 @@ union recv_frame *r8712_recvframe_chk_defrag(struct _adapter *padapter,
 				/*the first fragment*/
 				if (!list_empty(&pdefrag_q->queue)) {
 					/*free current defrag_q */
-					r8712_free_recvframe_queue(pdefrag_q,
-							     pfree_recv_queue);
+					r8712_free_recvframe_queue(pdefrag_q, pfree_recv_queue);
 				}
 			}
 			/* Then enqueue the 0~(n-1) fragment to the defrag_q */
diff --git a/drivers/staging/rtl8712/rtl8712_xmit.c b/drivers/staging/rtl8712/rtl8712_xmit.c
index 4cb01f590673e..d7d678b04ca80 100644
--- a/drivers/staging/rtl8712/rtl8712_xmit.c
+++ b/drivers/staging/rtl8712/rtl8712_xmit.c
@@ -147,9 +147,8 @@ static u32 get_ff_hwaddr(struct xmit_frame *pxmitframe)
 }
 
 static struct xmit_frame *dequeue_one_xmitframe(struct xmit_priv *pxmitpriv,
-					 struct hw_xmit *phwxmit,
-					 struct tx_servq *ptxservq,
-					 struct  __queue *pframe_queue)
+						struct hw_xmit *phwxmit, struct tx_servq *ptxservq,
+						struct  __queue *pframe_queue)
 {
 	struct list_head *xmitframe_plist, *xmitframe_phead;
 	struct	xmit_frame *pxmitframe = NULL;
@@ -167,7 +166,7 @@ static struct xmit_frame *dequeue_one_xmitframe(struct xmit_priv *pxmitpriv,
 }
 
 static struct xmit_frame *dequeue_xframe_ex(struct xmit_priv *pxmitpriv,
-				     struct hw_xmit *phwxmit_i, sint entry)
+					    struct hw_xmit *phwxmit_i, sint entry)
 {
 	unsigned long irqL0;
 	struct list_head *sta_plist, *sta_phead;
@@ -197,11 +196,10 @@ static struct xmit_frame *dequeue_xframe_ex(struct xmit_priv *pxmitpriv,
 		sta_phead = &phwxmit->sta_queue->queue;
 		sta_plist = sta_phead->next;
 		while (!end_of_queue_search(sta_phead, sta_plist)) {
-			ptxservq = container_of(sta_plist, struct tx_servq,
-						tx_pending);
+			ptxservq = container_of(sta_plist, struct tx_servq, tx_pending);
 			pframe_queue = &ptxservq->sta_pending;
-			pxmitframe = dequeue_one_xmitframe(pxmitpriv, phwxmit,
-				     ptxservq, pframe_queue);
+			pxmitframe = dequeue_one_xmitframe(pxmitpriv, phwxmit, ptxservq,
+							   pframe_queue);
 			if (pxmitframe) {
 				phwxmit->accnt--;
 				goto exit_dequeue_xframe_ex;
@@ -221,8 +219,7 @@ exit_dequeue_xframe_ex:
 	return pxmitframe;
 }
 
-void r8712_do_queue_select(struct _adapter *padapter,
-			   struct pkt_attrib *pattrib)
+void r8712_do_queue_select(struct _adapter *padapter, struct pkt_attrib *pattrib)
 {
 	unsigned int qsel = 0;
 	struct dvobj_priv *pdvobj = &padapter->dvobjpriv;
@@ -292,14 +289,12 @@ void r8712_append_mpdu_unit(struct xmit_buf *pxmitbuf,
 	r8712_xmit_complete(padapter, pxmitframe);
 	if (pxmitframe->attrib.ether_type != 0x0806) {
 		if ((pxmitframe->attrib.ether_type != 0x888e) &&
-			(pxmitframe->attrib.dhcp_pkt != 1)) {
-			r8712_issue_addbareq_cmd(padapter,
-					pxmitframe->attrib.priority);
+		    (pxmitframe->attrib.dhcp_pkt != 1)) {
+			r8712_issue_addbareq_cmd(padapter, pxmitframe->attrib.priority);
 		}
 	}
 	pxmitframe->last[0] = 1;
-	update_txdesc(pxmitframe, (uint *)(pxmitframe->buf_addr),
-		pxmitframe->attrib.last_txcmdsz);
+	update_txdesc(pxmitframe, (uint *)(pxmitframe->buf_addr), pxmitframe->attrib.last_txcmdsz);
 	/*padding zero */
 	last_txcmdsz = pxmitframe->attrib.last_txcmdsz;
 	padding_sz = (8 - (last_txcmdsz % 8));
@@ -333,8 +328,7 @@ void r8712_xmitframe_aggr_1st(struct xmit_buf *pxmitbuf,
 	pxmitbuf->aggr_nr = 1;
 }
 
-u16 r8712_xmitframe_aggr_next(struct xmit_buf *pxmitbuf,
-			struct xmit_frame *pxmitframe)
+u16 r8712_xmitframe_aggr_next(struct xmit_buf *pxmitbuf, struct xmit_frame *pxmitframe)
 {
 	pxmitframe->pxmitbuf = pxmitbuf;
 	pxmitbuf->priv_data = pxmitframe;
@@ -374,9 +368,9 @@ void r8712_dump_aggr_xframe(struct xmit_buf *pxmitbuf,
 	pxmitframe->bpending[0] = false;
 	pxmitframe->mem_addr = pxmitbuf->pbuf;
 
-	if ((pdvobj->ishighspeed && ((total_length + TXDESC_SIZE) % 0x200) ==
-	     0) || ((!pdvobj->ishighspeed && ((total_length + TXDESC_SIZE) %
-					      0x40) == 0))) {
+	if ((pdvobj->ishighspeed && ((total_length + TXDESC_SIZE) % 0x200) == 0) ||
+	    ((!pdvobj->ishighspeed && ((total_length + TXDESC_SIZE) %
+	    0x40) == 0))) {
 		ptxdesc->txdw0 |= cpu_to_le32
 			(((TXDESC_SIZE + OFFSET_SZ + 8) << OFFSET_SHT) &
 			 0x00ff0000);
@@ -387,8 +381,8 @@ void r8712_dump_aggr_xframe(struct xmit_buf *pxmitbuf,
 			 0x00ff0000);
 		/*default = 32 bytes for TX Desc*/
 	}
-	r8712_write_port(pxmitframe->padapter, RTL8712_DMA_H2CCMD,
-			total_length + TXDESC_SIZE, (u8 *)pxmitframe);
+	r8712_write_port(pxmitframe->padapter, RTL8712_DMA_H2CCMD, total_length + TXDESC_SIZE,
+			 (u8 *)pxmitframe);
 }
 
 #endif
@@ -618,14 +612,12 @@ int r8712_xmitframe_complete(struct _adapter *padapter,
 	pxmitframe = dequeue_xframe_ex(pxmitpriv, phwxmits, hwentry);
 	/* need to remember the 1st frame */
 	if (pxmitframe) {
-
 #ifdef CONFIG_R8712_TX_AGGR
 		/* 1. dequeue 2nd frame
 		 * 2. aggr if 2nd xframe is dequeued, else dump directly
 		 */
 		if (AGGR_NR_HIGH_BOUND > 1)
-			p2ndxmitframe = dequeue_xframe_ex(pxmitpriv, phwxmits,
-							hwentry);
+			p2ndxmitframe = dequeue_xframe_ex(pxmitpriv, phwxmits, hwentry);
 		if (pxmitframe->frame_tag != DATA_FRAMETAG) {
 			r8712_free_xmitbuf(pxmitpriv, pxmitbuf);
 			return false;
@@ -639,16 +631,12 @@ int r8712_xmitframe_complete(struct _adapter *padapter,
 		if (p2ndxmitframe) {
 			u16 total_length;
 
-			total_length = r8712_xmitframe_aggr_next(
-				pxmitbuf, p2ndxmitframe);
+			total_length = r8712_xmitframe_aggr_next(pxmitbuf, p2ndxmitframe);
 			do {
-				p2ndxmitframe = dequeue_xframe_ex(
-					pxmitpriv, phwxmits, hwentry);
+				p2ndxmitframe = dequeue_xframe_ex(pxmitpriv, phwxmits, hwentry);
 				if (p2ndxmitframe)
 					total_length =
-						r8712_xmitframe_aggr_next(
-							pxmitbuf,
-							p2ndxmitframe);
+						r8712_xmitframe_aggr_next(pxmitbuf, p2ndxmitframe);
 				else
 					break;
 			} while (total_length <= 0x1800 &&
@@ -662,8 +650,8 @@ int r8712_xmitframe_complete(struct _adapter *padapter,
 		xmitframe_xmitbuf_attach(pxmitframe, pxmitbuf);
 		if (pxmitframe->frame_tag == DATA_FRAMETAG) {
 			if (pxmitframe->attrib.priority <= 15)
-				res = r8712_xmitframe_coalesce(padapter,
-					pxmitframe->pkt, pxmitframe);
+				res = r8712_xmitframe_coalesce(padapter, pxmitframe->pkt,
+							       pxmitframe);
 			/* always return ndis_packet after
 			 * r8712_xmitframe_coalesce
 			 */
@@ -714,10 +702,10 @@ static void dump_xframe(struct _adapter *padapter,
 		ff_hwaddr = get_ff_hwaddr(pxmitframe);
 #ifdef CONFIG_R8712_TX_AGGR
 		r8712_write_port(padapter, RTL8712_DMA_H2CCMD, w_sz,
-				(unsigned char *)pxmitframe);
+				 (unsigned char *)pxmitframe);
 #else
 		r8712_write_port(padapter, ff_hwaddr, w_sz,
-			   (unsigned char *)pxmitframe);
+				 (unsigned char *)pxmitframe);
 #endif
 		mem_addr += w_sz;
 		mem_addr = (u8 *)RND4(((addr_t)(mem_addr)));
diff --git a/drivers/staging/rtl8712/rtl871x_cmd.c b/drivers/staging/rtl8712/rtl871x_cmd.c
index 4be96df5a3296..bbd4a13c7bb9d 100644
--- a/drivers/staging/rtl8712/rtl871x_cmd.c
+++ b/drivers/staging/rtl8712/rtl871x_cmd.c
@@ -242,8 +242,7 @@ void r8712_set_chplan_cmd(struct _adapter *padapter, int chplan)
 		kfree(ph2c);
 		return;
 	}
-	init_h2fwcmd_w_parm_no_rsp(ph2c, psetchplanpara,
-				GEN_CMD_CODE(_SetChannelPlan));
+	init_h2fwcmd_w_parm_no_rsp(ph2c, psetchplanpara, GEN_CMD_CODE(_SetChannelPlan));
 	psetchplanpara->ChannelPlan = chplan;
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
 }
@@ -302,8 +301,7 @@ void r8712_getbbrfreg_cmdrsp_callback(struct _adapter *padapter,
 	padapter->mppriv.workparam.bcompleted = true;
 }
 
-void r8712_readtssi_cmdrsp_callback(struct _adapter *padapter,
-				struct cmd_obj *pcmd)
+void r8712_readtssi_cmdrsp_callback(struct _adapter *padapter, struct cmd_obj *pcmd)
 {
 	kfree(pcmd->parmbuf);
 	kfree(pcmd);
@@ -374,11 +372,10 @@ int r8712_joinbss_cmd(struct _adapter  *padapter, struct wlan_network *pnetwork)
 	psecuritypriv->authenticator_ie[0] = (unsigned char)
 					     psecnetwork->IELength;
 	if ((psecnetwork->IELength - 12) < (256 - 1))
-		memcpy(&psecuritypriv->authenticator_ie[1],
-			&psecnetwork->IEs[12], psecnetwork->IELength - 12);
+		memcpy(&psecuritypriv->authenticator_ie[1], &psecnetwork->IEs[12],
+		       psecnetwork->IELength - 12);
 	else
-		memcpy(&psecuritypriv->authenticator_ie[1],
-			&psecnetwork->IEs[12], (256 - 1));
+		memcpy(&psecuritypriv->authenticator_ie[1], &psecnetwork->IEs[12], (256 - 1));
 	psecnetwork->IELength = 0;
 	/*
 	 * If the driver wants to use the bssid to create the connection.
@@ -388,19 +385,15 @@ int r8712_joinbss_cmd(struct _adapter  *padapter, struct wlan_network *pnetwork)
 	if (!pmlmepriv->assoc_by_bssid)
 		ether_addr_copy(&pmlmepriv->assoc_bssid[0],
 				&pnetwork->network.MacAddress[0]);
-	psecnetwork->IELength = r8712_restruct_sec_ie(padapter,
-						&pnetwork->network.IEs[0],
-						&psecnetwork->IEs[0],
-						pnetwork->network.IELength);
+	psecnetwork->IELength = r8712_restruct_sec_ie(padapter, &pnetwork->network.IEs[0],
+						      &psecnetwork->IEs[0], pnetwork->network.IELength);
 	pqospriv->qos_option = 0;
 	if (pregistrypriv->wmm_enable) {
 		u32 tmp_len;
 
-		tmp_len = r8712_restruct_wmm_ie(padapter,
-					  &pnetwork->network.IEs[0],
-					  &psecnetwork->IEs[0],
-					  pnetwork->network.IELength,
-					  psecnetwork->IELength);
+		tmp_len = r8712_restruct_wmm_ie(padapter, &pnetwork->network.IEs[0],
+						&psecnetwork->IEs[0], pnetwork->network.IELength,
+						psecnetwork->IELength);
 		if (psecnetwork->IELength != tmp_len) {
 			psecnetwork->IELength = tmp_len;
 			pqospriv->qos_option = 1; /* WMM IE in beacon */
@@ -427,39 +420,28 @@ int r8712_joinbss_cmd(struct _adapter  *padapter, struct wlan_network *pnetwork)
 	psecuritypriv->supplicant_ie[0] = (u8)psecnetwork->IELength;
 	if (psecnetwork->IELength < 255)
 		memcpy(&psecuritypriv->supplicant_ie[1], &psecnetwork->IEs[0],
-			psecnetwork->IELength);
+		       psecnetwork->IELength);
 	else
 		memcpy(&psecuritypriv->supplicant_ie[1], &psecnetwork->IEs[0],
-			255);
+		       255);
 	/* get cmdsz before endian conversion */
 	pcmd->cmdsz = r8712_get_wlan_bssid_ex_sz(psecnetwork);
 #ifdef __BIG_ENDIAN
 	/* wlan_network endian conversion */
 	psecnetwork->Length = cpu_to_le32(psecnetwork->Length);
-	psecnetwork->Ssid.SsidLength = cpu_to_le32(
-				       psecnetwork->Ssid.SsidLength);
+	psecnetwork->Ssid.SsidLength = cpu_to_le32(psecnetwork->Ssid.SsidLength);
 	psecnetwork->Privacy = cpu_to_le32(psecnetwork->Privacy);
 	psecnetwork->Rssi = cpu_to_le32(psecnetwork->Rssi);
-	psecnetwork->NetworkTypeInUse = cpu_to_le32(
-					psecnetwork->NetworkTypeInUse);
-	psecnetwork->Configuration.ATIMWindow = cpu_to_le32(
-				psecnetwork->Configuration.ATIMWindow);
-	psecnetwork->Configuration.BeaconPeriod = cpu_to_le32(
-				 psecnetwork->Configuration.BeaconPeriod);
-	psecnetwork->Configuration.DSConfig = cpu_to_le32(
-				psecnetwork->Configuration.DSConfig);
-	psecnetwork->Configuration.FHConfig.DwellTime = cpu_to_le32(
-				psecnetwork->Configuration.FHConfig.DwellTime);
-	psecnetwork->Configuration.FHConfig.HopPattern = cpu_to_le32(
-				psecnetwork->Configuration.FHConfig.HopPattern);
-	psecnetwork->Configuration.FHConfig.HopSet = cpu_to_le32(
-				psecnetwork->Configuration.FHConfig.HopSet);
-	psecnetwork->Configuration.FHConfig.Length = cpu_to_le32(
-				psecnetwork->Configuration.FHConfig.Length);
-	psecnetwork->Configuration.Length = cpu_to_le32(
-				psecnetwork->Configuration.Length);
-	psecnetwork->InfrastructureMode = cpu_to_le32(
-				psecnetwork->InfrastructureMode);
+	psecnetwork->NetworkTypeInUse = cpu_to_le32(psecnetwork->NetworkTypeInUse);
+	psecnetwork->Configuration.ATIMWindow = cpu_to_le32(psecnetwork->Configuration.ATIMWindow);
+	psecnetwork->Configuration.BeaconPeriod = cpu_to_le32(psecnetwork->Configuration.BeaconPeriod);
+	psecnetwork->Configuration.DSConfig = cpu_to_le32(psecnetwork->Configuration.DSConfig);
+	psecnetwork->Configuration.FHConfig.DwellTime = cpu_to_le32(psecnetwork->Configuration.FHConfig.DwellTime);
+	psecnetwork->Configuration.FHConfig.HopPattern = cpu_to_le32(psecnetwork->Configuration.FHConfig.HopPattern);
+	psecnetwork->Configuration.FHConfig.HopSet = cpu_to_le32(psecnetwork->Configuration.FHConfig.HopSet);
+	psecnetwork->Configuration.FHConfig.Length = cpu_to_le32(psecnetwork->Configuration.FHConfig.Length);
+	psecnetwork->Configuration.Length = cpu_to_le32(psecnetwork->Configuration.Length);
+	psecnetwork->InfrastructureMode = cpu_to_le32(psecnetwork->InfrastructureMode);
 	psecnetwork->IELength = cpu_to_le32(psecnetwork->IELength);
 #endif
 	INIT_LIST_HEAD(&pcmd->list);
@@ -485,13 +467,12 @@ void r8712_disassoc_cmd(struct _adapter *padapter) /* for sta_mode */
 		kfree(pdisconnect_cmd);
 		return;
 	}
-	init_h2fwcmd_w_parm_no_rsp(pdisconnect_cmd, pdisconnect,
-				   _DisConnect_CMD_);
+	init_h2fwcmd_w_parm_no_rsp(pdisconnect_cmd, pdisconnect, _DisConnect_CMD_);
 	r8712_enqueue_cmd(pcmdpriv, pdisconnect_cmd);
 }
 
 void r8712_setopmode_cmd(struct _adapter *padapter,
-		 enum NDIS_802_11_NETWORK_INFRASTRUCTURE networktype)
+			 enum NDIS_802_11_NETWORK_INFRASTRUCTURE networktype)
 {
 	struct cmd_obj *ph2c;
 	struct setopmode_parm *psetop;
@@ -543,14 +524,12 @@ void r8712_setstakey_cmd(struct _adapter *padapter, u8 *psta, u8 unicast_key)
 		psetstakey_para->algorithm = (unsigned char)
 					    psecuritypriv->PrivacyAlgrthm;
 	else
-		GET_ENCRY_ALGO(psecuritypriv, sta,
-			       psetstakey_para->algorithm, false);
+		GET_ENCRY_ALGO(psecuritypriv, sta, psetstakey_para->algorithm, false);
 	if (unicast_key)
 		memcpy(&psetstakey_para->key, &sta->x_UncstKey, 16);
 	else
-		memcpy(&psetstakey_para->key,
-			&psecuritypriv->XGrpKey[
-			psecuritypriv->XGrpKeyid - 1]. skey, 16);
+		memcpy(&psetstakey_para->key, &psecuritypriv->XGrpKey[psecuritypriv->XGrpKeyid - 1].
+		       skey, 16);
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
 }
 
@@ -568,8 +547,7 @@ void r8712_setMacAddr_cmd(struct _adapter *padapter, const u8 *mac_addr)
 		kfree(ph2c);
 		return;
 	}
-	init_h2fwcmd_w_parm_no_rsp(ph2c, psetMacAddr_para,
-				   _SetMacAddress_CMD_);
+	init_h2fwcmd_w_parm_no_rsp(ph2c, psetMacAddr_para, _SetMacAddress_CMD_);
 	ether_addr_copy(psetMacAddr_para->MacAddr, mac_addr);
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
 }
@@ -589,8 +567,7 @@ void r8712_addbareq_cmd(struct _adapter *padapter, u8 tid)
 		return;
 	}
 	paddbareq_parm->tid = tid;
-	init_h2fwcmd_w_parm_no_rsp(ph2c, paddbareq_parm,
-				   GEN_CMD_CODE(_AddBAReq));
+	init_h2fwcmd_w_parm_no_rsp(ph2c, paddbareq_parm, GEN_CMD_CODE(_AddBAReq));
 	r8712_enqueue_cmd_ex(pcmdpriv, ph2c);
 }
 
@@ -644,13 +621,11 @@ void r8712_joinbss_cmd_callback(struct _adapter *padapter, struct cmd_obj *pcmd)
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
 
 	if (pcmd->res != H2C_SUCCESS)
-		mod_timer(&pmlmepriv->assoc_timer,
-			  jiffies + msecs_to_jiffies(1));
+		mod_timer(&pmlmepriv->assoc_timer, jiffies + msecs_to_jiffies(1));
 	r8712_free_cmd_obj(pcmd);
 }
 
-void r8712_createbss_cmd_callback(struct _adapter *padapter,
-				  struct cmd_obj *pcmd)
+void r8712_createbss_cmd_callback(struct _adapter *padapter, struct cmd_obj *pcmd)
 {
 	unsigned long irqL;
 	struct sta_info *psta = NULL;
@@ -660,8 +635,7 @@ void r8712_createbss_cmd_callback(struct _adapter *padapter,
 	struct wlan_network *tgt_network = &(pmlmepriv->cur_network);
 
 	if (pcmd->res != H2C_SUCCESS)
-		mod_timer(&pmlmepriv->assoc_timer,
-			  jiffies + msecs_to_jiffies(1));
+		mod_timer(&pmlmepriv->assoc_timer, jiffies + msecs_to_jiffies(1));
 	del_timer(&pmlmepriv->assoc_timer);
 #ifdef __BIG_ENDIAN
 	/* endian_convert */
@@ -670,31 +644,21 @@ void r8712_createbss_cmd_callback(struct _adapter *padapter,
 	pnetwork->Privacy = le32_to_cpu(pnetwork->Privacy);
 	pnetwork->Rssi = le32_to_cpu(pnetwork->Rssi);
 	pnetwork->NetworkTypeInUse = le32_to_cpu(pnetwork->NetworkTypeInUse);
-	pnetwork->Configuration.ATIMWindow =
-		le32_to_cpu(pnetwork->Configuration.ATIMWindow);
-	pnetwork->Configuration.DSConfig =
-		le32_to_cpu(pnetwork->Configuration.DSConfig);
-	pnetwork->Configuration.FHConfig.DwellTime =
-		le32_to_cpu(pnetwork->Configuration.FHConfig.DwellTime);
-	pnetwork->Configuration.FHConfig.HopPattern =
-		le32_to_cpu(pnetwork->Configuration.FHConfig.HopPattern);
-	pnetwork->Configuration.FHConfig.HopSet =
-		le32_to_cpu(pnetwork->Configuration.FHConfig.HopSet);
-	pnetwork->Configuration.FHConfig.Length =
-		le32_to_cpu(pnetwork->Configuration.FHConfig.Length);
-	pnetwork->Configuration.Length =
-		le32_to_cpu(pnetwork->Configuration.Length);
-	pnetwork->InfrastructureMode =
-		le32_to_cpu(pnetwork->InfrastructureMode);
+	pnetwork->Configuration.ATIMWindow = le32_to_cpu(pnetwork->Configuration.ATIMWindow);
+	pnetwork->Configuration.DSConfig = le32_to_cpu(pnetwork->Configuration.DSConfig);
+	pnetwork->Configuration.FHConfig.DwellTime = le32_to_cpu(pnetwork->Configuration.FHConfig.DwellTime);
+	pnetwork->Configuration.FHConfig.HopPattern = le32_to_cpu(pnetwork->Configuration.FHConfig.HopPattern);
+	pnetwork->Configuration.FHConfig.HopSet = le32_to_cpu(pnetwork->Configuration.FHConfig.HopSet);
+	pnetwork->Configuration.FHConfig.Length = le32_to_cpu(pnetwork->Configuration.FHConfig.Length);
+	pnetwork->Configuration.Length = le32_to_cpu(pnetwork->Configuration.Length);
+	pnetwork->InfrastructureMode = le32_to_cpu(pnetwork->InfrastructureMode);
 	pnetwork->IELength = le32_to_cpu(pnetwork->IELength);
 #endif
 	spin_lock_irqsave(&pmlmepriv->lock, irqL);
 	if ((pmlmepriv->fw_state) & WIFI_AP_STATE) {
-		psta = r8712_get_stainfo(&padapter->stapriv,
-					 pnetwork->MacAddress);
+		psta = r8712_get_stainfo(&padapter->stapriv, pnetwork->MacAddress);
 		if (!psta) {
-			psta = r8712_alloc_stainfo(&padapter->stapriv,
-						   pnetwork->MacAddress);
+			psta = r8712_alloc_stainfo(&padapter->stapriv, pnetwork->MacAddress);
 			if (!psta)
 				goto createbss_cmd_fail;
 		}
@@ -702,20 +666,17 @@ void r8712_createbss_cmd_callback(struct _adapter *padapter,
 	} else {
 		pwlan = _r8712_alloc_network(pmlmepriv);
 		if (!pwlan) {
-			pwlan = r8712_get_oldest_wlan_network(
-				&pmlmepriv->scanned_queue);
+			pwlan = r8712_get_oldest_wlan_network(&pmlmepriv->scanned_queue);
 			if (!pwlan)
 				goto createbss_cmd_fail;
 			pwlan->last_scanned = jiffies;
 		} else {
-			list_add_tail(&(pwlan->list),
-					 &pmlmepriv->scanned_queue.queue);
+			list_add_tail(&(pwlan->list), &pmlmepriv->scanned_queue.queue);
 		}
 		pnetwork->Length = r8712_get_wlan_bssid_ex_sz(pnetwork);
 		memcpy(&(pwlan->network), pnetwork, pnetwork->Length);
 		pwlan->fixed = true;
-		memcpy(&tgt_network->network, pnetwork,
-			(r8712_get_wlan_bssid_ex_sz(pnetwork)));
+		memcpy(&tgt_network->network, pnetwork, (r8712_get_wlan_bssid_ex_sz(pnetwork)));
 		if (pmlmepriv->fw_state & _FW_UNDER_LINKING)
 			pmlmepriv->fw_state ^= _FW_UNDER_LINKING;
 		/*
@@ -728,14 +689,11 @@ createbss_cmd_fail:
 	r8712_free_cmd_obj(pcmd);
 }
 
-void r8712_setstaKey_cmdrsp_callback(struct _adapter *padapter,
-				     struct cmd_obj *pcmd)
+void r8712_setstaKey_cmdrsp_callback(struct _adapter *padapter, struct cmd_obj *pcmd)
 {
 	struct sta_priv *pstapriv = &padapter->stapriv;
-	struct set_stakey_rsp *psetstakey_rsp = (struct set_stakey_rsp *)
-						(pcmd->rsp);
-	struct sta_info *psta = r8712_get_stainfo(pstapriv,
-						  psetstakey_rsp->addr);
+	struct set_stakey_rsp *psetstakey_rsp = (struct set_stakey_rsp *) (pcmd->rsp);
+	struct sta_info *psta = r8712_get_stainfo(pstapriv, psetstakey_rsp->addr);
 
 	if (!psta)
 		goto exit;
@@ -750,27 +708,23 @@ void r8712_setassocsta_cmdrsp_callback(struct _adapter *padapter,
 	unsigned long	irqL;
 	struct sta_priv *pstapriv = &padapter->stapriv;
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct set_assocsta_parm *passocsta_parm =
-				(struct set_assocsta_parm *)(pcmd->parmbuf);
-	struct set_assocsta_rsp *passocsta_rsp =
-				(struct set_assocsta_rsp *) (pcmd->rsp);
-	struct sta_info *psta = r8712_get_stainfo(pstapriv,
-						  passocsta_parm->addr);
+	struct set_assocsta_parm *passocsta_parm = (struct set_assocsta_parm *)(pcmd->parmbuf);
+	struct set_assocsta_rsp *passocsta_rsp = (struct set_assocsta_rsp *) (pcmd->rsp);
+	struct sta_info *psta = r8712_get_stainfo(pstapriv, passocsta_parm->addr);
 
 	if (!psta)
 		return;
 	psta->aid = psta->mac_id = passocsta_rsp->cam_id;
 	spin_lock_irqsave(&pmlmepriv->lock, irqL);
-	if ((check_fwstate(pmlmepriv, WIFI_MP_STATE)) &&
-	    (check_fwstate(pmlmepriv, _FW_UNDER_LINKING)))
+	if ((check_fwstate(pmlmepriv, WIFI_MP_STATE)) && (check_fwstate(pmlmepriv, _FW_UNDER_LINKING)))
 		pmlmepriv->fw_state ^= _FW_UNDER_LINKING;
 	set_fwstate(pmlmepriv, _FW_LINKED);
 	spin_unlock_irqrestore(&pmlmepriv->lock, irqL);
 	r8712_free_cmd_obj(pcmd);
 }
 
-void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl,
-			u32 tryPktCnt, u32 tryPktInterval, u32 firstStageTO)
+void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl, u32 tryPktCnt,
+				u32 tryPktInterval, u32 firstStageTO)
 {
 	struct cmd_obj *ph2c;
 	struct DisconnectCtrlEx_param *param;
@@ -790,7 +744,6 @@ void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl,
 	param->TryPktInterval = (unsigned char)tryPktInterval;
 	param->FirstStageTO = (unsigned int)firstStageTO;
 
-	init_h2fwcmd_w_parm_no_rsp(ph2c, param,
-				GEN_CMD_CODE(_DisconnectCtrlEx));
+	init_h2fwcmd_w_parm_no_rsp(ph2c, param, GEN_CMD_CODE(_DisconnectCtrlEx));
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
 }
diff --git a/drivers/staging/rtl8712/rtl871x_cmd.h b/drivers/staging/rtl8712/rtl871x_cmd.h
index 8453d8de82484..2613b3c2acfcb 100644
--- a/drivers/staging/rtl8712/rtl871x_cmd.h
+++ b/drivers/staging/rtl8712/rtl871x_cmd.h
@@ -716,39 +716,28 @@ struct DisconnectCtrlEx_param {
 #define H2C_RESERVED			0x07
 
 void r8712_setMacAddr_cmd(struct _adapter *padapter, const u8 *mac_addr);
-u8 r8712_sitesurvey_cmd(struct _adapter *padapter,
-			struct ndis_802_11_ssid *pssid);
+u8 r8712_sitesurvey_cmd(struct _adapter *padapter, struct ndis_802_11_ssid *pssid);
 int r8712_createbss_cmd(struct _adapter *padapter);
 void r8712_setstakey_cmd(struct _adapter *padapter, u8 *psta, u8 unicast_key);
-int r8712_joinbss_cmd(struct _adapter *padapter,
-		      struct wlan_network *pnetwork);
+int r8712_joinbss_cmd(struct _adapter *padapter, struct wlan_network *pnetwork);
 void r8712_disassoc_cmd(struct _adapter *padapter);
-void r8712_setopmode_cmd(struct _adapter *padapter,
-		 enum NDIS_802_11_NETWORK_INFRASTRUCTURE networktype);
+void r8712_setopmode_cmd(struct _adapter *padapter, enum NDIS_802_11_NETWORK_INFRASTRUCTURE networktype);
 int r8712_setdatarate_cmd(struct _adapter *padapter, u8 *rateset);
 void r8712_set_chplan_cmd(struct _adapter  *padapter, int chplan);
 int r8712_getrfreg_cmd(struct _adapter *padapter, u8 offset, u8 *pval);
 int r8712_setrfreg_cmd(struct _adapter  *padapter, u8 offset, u32 val);
 void r8712_addbareq_cmd(struct _adapter *padapter, u8 tid);
 void r8712_wdg_wk_cmd(struct _adapter *padapter);
-void r8712_survey_cmd_callback(struct _adapter  *padapter,
-			       struct cmd_obj *pcmd);
-void r8712_disassoc_cmd_callback(struct _adapter  *padapter,
-				 struct cmd_obj *pcmd);
-void r8712_joinbss_cmd_callback(struct _adapter  *padapter,
-				struct cmd_obj *pcmd);
-void r8712_createbss_cmd_callback(struct _adapter *padapter,
-				  struct cmd_obj *pcmd);
-void r8712_getbbrfreg_cmdrsp_callback(struct _adapter *padapter,
-				      struct cmd_obj *pcmd);
-void r8712_readtssi_cmdrsp_callback(struct _adapter *padapter,
-				struct cmd_obj *pcmd);
-void r8712_setstaKey_cmdrsp_callback(struct _adapter  *padapter,
-				     struct cmd_obj *pcmd);
-void r8712_setassocsta_cmdrsp_callback(struct _adapter  *padapter,
-				       struct cmd_obj *pcmd);
-void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl,
-			u32 tryPktCnt, u32 tryPktInterval, u32 firstStageTO);
+void r8712_survey_cmd_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_disassoc_cmd_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_joinbss_cmd_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_createbss_cmd_callback(struct _adapter *padapter, struct cmd_obj *pcmd);
+void r8712_getbbrfreg_cmdrsp_callback(struct _adapter *padapter, struct cmd_obj *pcmd);
+void r8712_readtssi_cmdrsp_callback(struct _adapter *padapter, struct cmd_obj *pcmd);
+void r8712_setstaKey_cmdrsp_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_setassocsta_cmdrsp_callback(struct _adapter  *padapter, struct cmd_obj *pcmd);
+void r8712_disconnectCtrlEx_cmd(struct _adapter *adapter, u32 enableDrvCtrl, u32 tryPktCnt, 
+				u32 tryPktInterval, u32 firstStageTO);
 
 struct _cmd_callback {
 	u32	cmd_code;
diff --git a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
index 36f6904d25abc..0653aa27b1fa2 100644
--- a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
+++ b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
@@ -59,8 +59,7 @@ void r8712_indicate_wx_assoc_event(struct _adapter *padapter)
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
 
 	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
-	memcpy(wrqu.ap_addr.sa_data, pmlmepriv->cur_network.network.MacAddress,
-		ETH_ALEN);
+	memcpy(wrqu.ap_addr.sa_data, pmlmepriv->cur_network.network.MacAddress, ETH_ALEN);
 	wireless_send_event(padapter->pnetdev, SIOCGIWAP, &wrqu, NULL);
 }
 
@@ -111,11 +110,9 @@ static inline void handle_group_key(struct ieee_param *param,
 		memcpy(grk[param->u.crypt.idx - 1].skey,
 		       &param->u.crypt.key[24], 8);
 		padapter->securitypriv.binstallGrpkey = true;
-		r8712_set_key(padapter, &padapter->securitypriv,
-			param->u.crypt.idx);
+		r8712_set_key(padapter, &padapter->securitypriv, param->u.crypt.idx);
 		if (padapter->registrypriv.power_mgnt > PS_MODE_ACTIVE) {
-			if (padapter->registrypriv.power_mgnt !=
-			    padapter->pwrctrlpriv.pwr_mode)
+			if (padapter->registrypriv.power_mgnt != padapter->pwrctrlpriv.pwr_mode)
 				mod_timer(&padapter->mlmepriv.dhcp_timer,
 					  jiffies + msecs_to_jiffies(60000));
 		}
@@ -148,13 +145,11 @@ static noinline_for_stack char *translate_scan_wpa(struct iw_request_info *info,
 		memset(iwe, 0, sizeof(*iwe));
 		iwe->cmd = IWEVCUSTOM;
 		iwe->u.data.length = (u16)strlen(buf);
-		start = iwe_stream_add_point(info, start, stop,
-			iwe, buf);
+		start = iwe_stream_add_point(info, start, stop, iwe, buf);
 		memset(iwe, 0, sizeof(*iwe));
 		iwe->cmd = IWEVGENIE;
 		iwe->u.data.length = (u16)wpa_len;
-		start = iwe_stream_add_point(info, start, stop,
-			iwe, wpa_ie);
+		start = iwe_stream_add_point(info, start, stop, iwe, wpa_ie);
 	}
 	if (rsn_len > 0) {
 		memset(buf, 0, MAX_WPA_IE_LEN);
@@ -168,13 +163,11 @@ static noinline_for_stack char *translate_scan_wpa(struct iw_request_info *info,
 		memset(iwe, 0, sizeof(*iwe));
 		iwe->cmd = IWEVCUSTOM;
 		iwe->u.data.length = strlen(buf);
-		start = iwe_stream_add_point(info, start, stop,
-			iwe, buf);
+		start = iwe_stream_add_point(info, start, stop, iwe, buf);
 		memset(iwe, 0, sizeof(*iwe));
 		iwe->cmd = IWEVGENIE;
 		iwe->u.data.length = rsn_len;
-		start = iwe_stream_add_point(info, start, stop, iwe,
-			rsn_ie);
+		start = iwe_stream_add_point(info, start, stop, iwe, rsn_ie);
 	}
 
 	return start;
@@ -189,14 +182,11 @@ static noinline_for_stack char *translate_scan_wps(struct iw_request_info *info,
 	u8 wps_ie[512];
 	uint wps_ielen;
 
-	if (r8712_get_wps_ie(pnetwork->network.IEs,
-	    pnetwork->network.IELength,
-	    wps_ie, &wps_ielen)) {
+	if (r8712_get_wps_ie(pnetwork->network.IEs, pnetwork->network.IELength, wps_ie, &wps_ielen)) {
 		if (wps_ielen > 2) {
 			iwe->cmd = IWEVGENIE;
 			iwe->u.data.length = (u16)wps_ielen;
-			start = iwe_stream_add_point(info, start, stop,
-				iwe, wps_ie);
+			start = iwe_stream_add_point(info, start, stop, iwe, wps_ie);
 		}
 	}
 
@@ -259,16 +249,14 @@ static char *translate_scan(struct _adapter *padapter,
 	start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_CHAR_LEN);
 	/* Add mode */
 	iwe.cmd = SIOCGIWMODE;
-	memcpy((u8 *)&cap, r8712_get_capability_from_ie(pnetwork->network.IEs),
-		2);
+	memcpy((u8 *)&cap, r8712_get_capability_from_ie(pnetwork->network.IEs), 2);
 	le16_to_cpus(&cap);
 	if (cap & (WLAN_CAPABILITY_IBSS | WLAN_CAPABILITY_ESS)) {
 		if (cap & WLAN_CAPABILITY_ESS)
 			iwe.u.mode = (u32)IW_MODE_MASTER;
 		else
 			iwe.u.mode = (u32)IW_MODE_ADHOC;
-		start = iwe_stream_add_event(info, start, stop, &iwe,
-			IW_EV_UINT_LEN);
+		start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_UINT_LEN);
 	}
 	/* Add frequency/channel */
 	iwe.cmd = SIOCGIWFREQ;
@@ -276,28 +264,23 @@ static char *translate_scan(struct _adapter *padapter,
 		/*  check legal index */
 		u8 dsconfig = pnetwork->network.Configuration.DSConfig;
 
-		if (dsconfig >= 1 && dsconfig <= sizeof(
-		    ieee80211_wlan_frequencies) / sizeof(long))
-			iwe.u.freq.m =
-				(s32)(ieee80211_wlan_frequencies
-				      [dsconfig - 1] * 100000);
+		if (dsconfig >= 1 && dsconfig <= sizeof(ieee80211_wlan_frequencies) / sizeof(long))
+			iwe.u.freq.m = (s32)(ieee80211_wlan_frequencies[dsconfig - 1] * 100000);
 		else
 			iwe.u.freq.m = 0;
 	}
 	iwe.u.freq.e = (s16)1;
 	iwe.u.freq.i = (u8)pnetwork->network.Configuration.DSConfig;
 	start = iwe_stream_add_event(info, start, stop, &iwe,
-		IW_EV_FREQ_LEN);
+				     IW_EV_FREQ_LEN);
 	/* Add encryption capability */
 	iwe.cmd = SIOCGIWENCODE;
 	if (cap & WLAN_CAPABILITY_PRIVACY)
-		iwe.u.data.flags = (u16)(IW_ENCODE_ENABLED |
-				    IW_ENCODE_NOKEY);
+		iwe.u.data.flags = (u16)(IW_ENCODE_ENABLED | IW_ENCODE_NOKEY);
 	else
 		iwe.u.data.flags = (u16)(IW_ENCODE_DISABLED);
 	iwe.u.data.length = (u16)0;
-	start = iwe_stream_add_point(info, start, stop, &iwe,
-		pnetwork->network.Ssid.Ssid);
+	start = iwe_stream_add_point(info, start, stop, &iwe, pnetwork->network.Ssid.Ssid);
 	/*Add basic and extended rates */
 	current_val = start + iwe_stream_lcp_len(info);
 	iwe.cmd = SIOCGIWRATE;
@@ -307,10 +290,9 @@ static char *translate_scan(struct _adapter *padapter,
 	i = 0;
 	while (pnetwork->network.rates[i] != 0) {
 		/* Bit rate given in 500 kb/s units */
-		iwe.u.bitrate.value = (pnetwork->network.rates[i++] &
-				      0x7F) * 500000;
-		current_val = iwe_stream_add_value(info, start, current_val,
-			      stop, &iwe, IW_EV_PARAM_LEN);
+		iwe.u.bitrate.value = (pnetwork->network.rates[i++] & 0x7F) * 500000;
+		current_val = iwe_stream_add_value(info, start, current_val, stop, &iwe,
+						   IW_EV_PARAM_LEN);
 	}
 	/* Check if we added any event */
 	if ((current_val - start) > iwe_stream_lcp_len(info))
@@ -324,8 +306,7 @@ static char *translate_scan(struct _adapter *padapter,
 	iwe.cmd = IWEVQUAL;
 	rssi = r8712_signal_scale_mapping(pnetwork->network.Rssi);
 	/* we only update signal_level (signal strength) that is rssi. */
-	iwe.u.qual.updated = (u8)(IW_QUAL_QUAL_INVALID | IW_QUAL_LEVEL_UPDATED |
-				  IW_QUAL_NOISE_INVALID);
+	iwe.u.qual.updated = (u8)(IW_QUAL_QUAL_INVALID | IW_QUAL_LEVEL_UPDATED | IW_QUAL_NOISE_INVALID);
 	iwe.u.qual.level = rssi;  /* signal strength */
 	iwe.u.qual.qual = 0; /* signal quality */
 	iwe.u.qual.noise = 0; /* noise level */
@@ -490,71 +471,59 @@ static int r871x_set_wpa_ie(struct _adapter *padapter, char *pie,
 			goto exit;
 		}
 		if (r8712_parse_wpa_ie(buf, ielen, &group_cipher,
-		    &pairwise_cipher) == 0) {
+				       &pairwise_cipher) == 0) {
 			padapter->securitypriv.AuthAlgrthm = 2;
 			padapter->securitypriv.ndisauthtype =
 				  Ndis802_11AuthModeWPAPSK;
 		}
 		if (r8712_parse_wpa2_ie(buf, ielen, &group_cipher,
-		    &pairwise_cipher) == 0) {
+					&pairwise_cipher) == 0) {
 			padapter->securitypriv.AuthAlgrthm = 2;
 			padapter->securitypriv.ndisauthtype =
 				  Ndis802_11AuthModeWPA2PSK;
 		}
 		switch (group_cipher) {
 		case WPA_CIPHER_NONE:
-			padapter->securitypriv.XGrpPrivacy =
-				 _NO_PRIVACY_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11EncryptionDisabled;
+			padapter->securitypriv.XGrpPrivacy = _NO_PRIVACY_;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled;
 			break;
 		case WPA_CIPHER_WEP40:
 			padapter->securitypriv.XGrpPrivacy = _WEP40_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption1Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
 			break;
 		case WPA_CIPHER_TKIP:
 			padapter->securitypriv.XGrpPrivacy = _TKIP_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption2Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled;
 			break;
 		case WPA_CIPHER_CCMP:
 			padapter->securitypriv.XGrpPrivacy = _AES_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption3Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled;
 			break;
 		case WPA_CIPHER_WEP104:
 			padapter->securitypriv.XGrpPrivacy = _WEP104_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption1Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
 			break;
 		}
 		switch (pairwise_cipher) {
 		case WPA_CIPHER_NONE:
-			padapter->securitypriv.PrivacyAlgrthm =
-				 _NO_PRIVACY_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11EncryptionDisabled;
+			padapter->securitypriv.PrivacyAlgrthm = _NO_PRIVACY_;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled;
 			break;
 		case WPA_CIPHER_WEP40:
 			padapter->securitypriv.PrivacyAlgrthm = _WEP40_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption1Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
 			break;
 		case WPA_CIPHER_TKIP:
 			padapter->securitypriv.PrivacyAlgrthm = _TKIP_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption2Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled;
 			break;
 		case WPA_CIPHER_CCMP:
 			padapter->securitypriv.PrivacyAlgrthm = _AES_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption3Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled;
 			break;
 		case WPA_CIPHER_WEP104:
 			padapter->securitypriv.PrivacyAlgrthm = _WEP104_;
-			padapter->securitypriv.ndisencryptstatus =
-				 Ndis802_11Encryption1Enabled;
+			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
 			break;
 		}
 		padapter->securitypriv.wps_phase = false;
@@ -574,8 +543,8 @@ static int r871x_set_wpa_ie(struct _adapter *padapter, char *pie,
 					    (buf[cnt + 1] + 2) :
 					    (MAX_WPA_IE_LEN << 2);
 					memcpy(padapter->securitypriv.wps_ie,
-					    &buf[cnt],
-					    padapter->securitypriv.wps_ie_len);
+					       &buf[cnt],
+					       padapter->securitypriv.wps_ie_len);
 					padapter->securitypriv.wps_phase =
 								 true;
 					netdev_info(padapter->pnetdev, "r8712u: SET WPS_IE, wps_phase==true\n");
@@ -592,8 +561,7 @@ exit:
 	return ret;
 }
 
-static int r8711_wx_get_name(struct net_device *dev,
-			     struct iw_request_info *info,
+static int r8711_wx_get_name(struct net_device *dev, struct iw_request_info *info,
 			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
@@ -604,8 +572,7 @@ static int r8711_wx_get_name(struct net_device *dev,
 	struct wlan_bssid_ex *pcur_bss = &pmlmepriv->cur_network.network;
 	u8 *prates;
 
-	if (check_fwstate(pmlmepriv, _FW_LINKED | WIFI_ADHOC_MASTER_STATE) ==
-	    true) {
+	if (check_fwstate(pmlmepriv, _FW_LINKED | WIFI_ADHOC_MASTER_STATE) == true) {
 		/* parsing HT_CAP_IE */
 		p = r8712_get_ie(&pcur_bss->IEs[12], WLAN_EID_HT_CAPABILITY,
 				 &ht_ielen, pcur_bss->IELength - 12);
@@ -658,9 +625,7 @@ static int r8711_wx_set_freq(struct net_device *dev,
 	int rc = 0;
 
 /* If setting by frequency, convert to a channel */
-	if ((fwrq->e == 1) &&
-	  (fwrq->m >= 241200000) &&
-	  (fwrq->m <= 248700000)) {
+	if ((fwrq->e == 1) && (fwrq->m >= 241200000) && (fwrq->m <= 248700000)) {
 		int f = fwrq->m / 100000;
 		int c = 0;
 
@@ -685,8 +650,7 @@ static int r8711_wx_set_freq(struct net_device *dev,
 	return rc;
 }
 
-static int r8711_wx_get_freq(struct net_device *dev,
-			     struct iw_request_info *info,
+static int r8711_wx_get_freq(struct net_device *dev, struct iw_request_info *info,
 			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
@@ -745,7 +709,7 @@ static int r8711_wx_get_mode(struct net_device *dev, struct iw_request_info *a,
 	if (check_fwstate(pmlmepriv, WIFI_STATION_STATE))
 		wrqu->mode = IW_MODE_INFRA;
 	else if (check_fwstate(pmlmepriv,
-		 WIFI_ADHOC_MASTER_STATE | WIFI_ADHOC_STATE))
+			       WIFI_ADHOC_MASTER_STATE | WIFI_ADHOC_STATE))
 		wrqu->mode = IW_MODE_ADHOC;
 	else if (check_fwstate(pmlmepriv, WIFI_AP_STATE))
 		wrqu->mode = IW_MODE_MASTER;
@@ -754,9 +718,8 @@ static int r8711_wx_get_mode(struct net_device *dev, struct iw_request_info *a,
 	return 0;
 }
 
-static int r871x_wx_set_pmkid(struct net_device *dev,
-			     struct iw_request_info *a,
-			     union iwreq_data *wrqu, char *extra)
+static int r871x_wx_set_pmkid(struct net_device *dev, struct iw_request_info *a,
+			      union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct security_priv *psecuritypriv = &padapter->securitypriv;
@@ -828,7 +791,7 @@ static int r871x_wx_set_pmkid(struct net_device *dev,
 		break;
 	case IW_PMKSA_FLUSH:
 		memset(psecuritypriv->PMKIDList, 0,
-			sizeof(struct RT_PMKID_LIST) * NUM_PMKID_CACHE);
+		       sizeof(struct RT_PMKID_LIST) * NUM_PMKID_CACHE);
 		psecuritypriv->PMKIDIndex = 0;
 		intReturn = true;
 		break;
@@ -850,9 +813,8 @@ static int r8711_wx_get_sens(struct net_device *dev,
 	return 0;
 }
 
-static int r8711_wx_get_range(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_range(struct net_device *dev, struct iw_request_info *info,
+			      union iwreq_data *wrqu, char *extra)
 {
 	struct iw_range *range = (struct iw_range *)extra;
 	u16 val;
@@ -912,9 +874,9 @@ static int r8711_wx_get_rate(struct net_device *dev,
 			     union iwreq_data *wrqu, char *extra);
 
 static int r871x_wx_set_priv(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *awrq,
-				char *extra)
+			     struct iw_request_info *info,
+			     union iwreq_data *awrq,
+			     char *extra)
 {
 	int ret = 0, len = 0;
 	char *ext;
@@ -995,12 +957,10 @@ static int r871x_wx_set_priv(struct net_device *dev,
 		);
 		sprintf(ext, "OK");
 	} else {
-		netdev_info(dev, "r8712u: %s: unknown Command %s.\n",
-			    __func__, ext);
+		netdev_info(dev, "r8712u: %s: unknown Command %s.\n", __func__, ext);
 		goto FREE_EXT;
 	}
-	if (copy_to_user(dwrq->pointer, ext,
-				min(dwrq->length, (__u16)(strlen(ext) + 1))))
+	if (copy_to_user(dwrq->pointer, ext, min(dwrq->length, (__u16)(strlen(ext) + 1))))
 		ret = -EFAULT;
 
 FREE_EXT:
@@ -1021,10 +981,8 @@ FREE_EXT:
  * For this operation to succeed, there is no need for the interface to be up.
  *
  */
-static int r8711_wx_set_wap(struct net_device *dev,
-			 struct iw_request_info *info,
-			 union iwreq_data *awrq,
-			 char *extra)
+static int r8711_wx_set_wap(struct net_device *dev, struct iw_request_info *info,
+			    union iwreq_data *awrq, char *extra)
 {
 	int ret = -EINPROGRESS;
 	struct _adapter *padapter = netdev_priv(dev);
@@ -1072,17 +1030,15 @@ static int r8711_wx_set_wap(struct net_device *dev,
 	return ret;
 }
 
-static int r8711_wx_get_wap(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_wap(struct net_device *dev, struct iw_request_info *info,
+			    union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
 	struct wlan_bssid_ex *pcur_bss = &pmlmepriv->cur_network.network;
 
 	wrqu->ap_addr.sa_family = ARPHRD_ETHER;
-	if (check_fwstate(pmlmepriv, _FW_LINKED | WIFI_ADHOC_MASTER_STATE |
-				     WIFI_AP_STATE))
+	if (check_fwstate(pmlmepriv, _FW_LINKED | WIFI_ADHOC_MASTER_STATE | WIFI_AP_STATE))
 		ether_addr_copy(wrqu->ap_addr.sa_data, pcur_bss->MacAddress);
 	else
 		eth_zero_addr(wrqu->ap_addr.sa_data);
@@ -1122,9 +1078,8 @@ static int r871x_wx_set_mlme(struct net_device *dev,
  * For this operation to succeed, the interface is brought Up beforehand.
  *
  */
-static int r8711_wx_set_scan(struct net_device *dev,
-			struct iw_request_info *a,
-			union iwreq_data *wrqu, char *extra)
+static int r8711_wx_set_scan(struct net_device *dev, struct iw_request_info *a,
+			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
@@ -1150,8 +1105,7 @@ static int r8711_wx_set_scan(struct net_device *dev,
 			unsigned long irqL;
 			u32 len = min_t(u8, req->essid_len, IW_ESSID_MAX_SIZE);
 
-			memset((unsigned char *)&ssid, 0,
-				 sizeof(struct ndis_802_11_ssid));
+			memset((unsigned char *)&ssid, 0, sizeof(struct ndis_802_11_ssid));
 			memcpy(ssid.Ssid, req->essid, len);
 			ssid.SsidLength = len;
 			spin_lock_irqsave(&pmlmepriv->lock, irqL);
@@ -1173,9 +1127,8 @@ static int r8711_wx_set_scan(struct net_device *dev,
 	return 0;
 }
 
-static int r8711_wx_get_scan(struct net_device *dev,
-				struct iw_request_info *a,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_scan(struct net_device *dev, struct iw_request_info *a,
+			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
@@ -1189,8 +1142,7 @@ static int r8711_wx_get_scan(struct net_device *dev,
 
 	if (padapter->driver_stopped)
 		return -EINVAL;
-	while (check_fwstate(pmlmepriv, _FW_UNDER_SURVEY |
-			     _FW_UNDER_LINKING)) {
+	while (check_fwstate(pmlmepriv, _FW_UNDER_SURVEY | _FW_UNDER_LINKING)) {
 		msleep(30);
 		cnt++;
 		if (cnt > 100)
@@ -1228,9 +1180,8 @@ static int r8711_wx_get_scan(struct net_device *dev,
  * For this operation to succeed, there is no need for the interface to be Up.
  *
  */
-static int r8711_wx_set_essid(struct net_device *dev,
-				struct iw_request_info *a,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_set_essid(struct net_device *dev, struct iw_request_info *a,
+			      union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
@@ -1268,8 +1219,7 @@ static int r8711_wx_set_essid(struct net_device *dev,
 			if ((!memcmp(dst_ssid, src_ssid, ndis_ssid.SsidLength))
 			    && (pnetwork->network.Ssid.SsidLength ==
 			     ndis_ssid.SsidLength)) {
-				if (check_fwstate(pmlmepriv,
-							WIFI_ADHOC_STATE)) {
+				if (check_fwstate(pmlmepriv, WIFI_ADHOC_STATE)) {
 					if (pnetwork->network.
 						InfrastructureMode
 						!=
@@ -1291,9 +1241,8 @@ static int r8711_wx_set_essid(struct net_device *dev,
 	return -EINPROGRESS;
 }
 
-static int r8711_wx_get_essid(struct net_device *dev,
-				struct iw_request_info *a,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_essid(struct net_device *dev, struct iw_request_info *a,
+			      union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
@@ -1311,9 +1260,8 @@ static int r8711_wx_get_essid(struct net_device *dev,
 	return ret;
 }
 
-static int r8711_wx_set_rate(struct net_device *dev,
-				struct iw_request_info *a,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_set_rate(struct net_device *dev, struct iw_request_info *a,
+			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 	u32 target_rate = wrqu->bitrate.value;
@@ -1382,8 +1330,7 @@ set_rate:
 	return r8712_setdatarate_cmd(padapter, datarates);
 }
 
-static int r8711_wx_get_rate(struct net_device *dev,
-			     struct iw_request_info *info,
+static int r8711_wx_get_rate(struct net_device *dev, struct iw_request_info *info,
 			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
@@ -1437,9 +1384,8 @@ static int r8711_wx_get_rate(struct net_device *dev,
 	return 0;
 }
 
-static int r8711_wx_get_rts(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_get_rts(struct net_device *dev, struct iw_request_info *info,
+			    union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 
@@ -1448,9 +1394,8 @@ static int r8711_wx_get_rts(struct net_device *dev,
 	return 0;
 }
 
-static int r8711_wx_set_frag(struct net_device *dev,
-				struct iw_request_info *info,
-				union iwreq_data *wrqu, char *extra)
+static int r8711_wx_set_frag(struct net_device *dev, struct iw_request_info *info,
+			     union iwreq_data *wrqu, char *extra)
 {
 	struct _adapter *padapter = netdev_priv(dev);
 
-- 
GitLab


From 1aa721a4648b71cee8159c5cb8af37518b8913fe Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:23 -0800
Subject: [PATCH 1855/4076] Staging: rtl8192e: Remove unnecessary braces from
 MgntQuery_MgntFrameTxRate()

Remove braces from if statement to fix checkpatch WARNING:
'braces {} are not necessary for single statement blocks'

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-2-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 953222d57f0e4..94c337e93f4ce 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -172,9 +172,8 @@ static u8 MgntQuery_MgntFrameTxRate(struct rtllib_device *ieee)
 	else
 		rate = ieee->basic_rate & 0x7f;
 
-	if (rate == 0) {
+	if (rate == 0)
 		rate = 0x02;
-	}
 
 	return rate;
 }
-- 
GitLab


From 6bb7a078a0afdb0402bbfa6db3622c9212edbf1b Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:25 -0800
Subject: [PATCH 1856/4076] Staging: rtl8192e: Remove unnecessary parenthesis
 in rtllib_association_req()

Remove parentheses to fix checkpatch Warning:
Unnecessary parentheses around hdr->info_element[0].id

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-4-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 94c337e93f4ce..94654e55618d4 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -917,7 +917,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 
 	kfree(ieee->assocreq_ies);
 	ieee->assocreq_ies = NULL;
-	ies = &(hdr->info_element[0].id);
+	ies = &hdr->info_element[0].id;
 	ieee->assocreq_ies_len = (skb->data + skb->len) - ies;
 	ieee->assocreq_ies = kmemdup(ies, ieee->assocreq_ies_len, GFP_ATOMIC);
 	if (!ieee->assocreq_ies)
-- 
GitLab


From be0d49be0c97804ff051825e152c655ea02a774d Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:26 -0800
Subject: [PATCH 1857/4076] Staging: rtl8192e: Remove unnecessary parenthesis
 in rtllib_rx_assoc_resp()

Remove parentheses to fix checkpatch Warning:
Unnecessary parentheses around resp->info_element[0].id

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-5-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 94654e55618d4..621bc62e35b55 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1619,7 +1619,7 @@ rtllib_rx_assoc_resp(struct rtllib_device *ieee, struct sk_buff *skb,
 
 			kfree(ieee->assocresp_ies);
 			ieee->assocresp_ies = NULL;
-			ies = &(assoc_resp->info_element[0].id);
+			ies = &assoc_resp->info_element[0].id;
 			ieee->assocresp_ies_len = (skb->data + skb->len) - ies;
 			ieee->assocresp_ies = kmemdup(ies,
 						      ieee->assocresp_ies_len,
-- 
GitLab


From a87f009c4f897491246d9d8f8e5e8b644fb06342 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:27 -0800
Subject: [PATCH 1858/4076] Staging: rtl8192e: Remove unnecessary parenthesis
 in rtllib_ap_sec_type()

Remove parnthesis to fix checkpatch Warning:
Unnecessary parentheses around ieee->wpa_ie[14]

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-6-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 621bc62e35b55..411763cafd2e1 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2231,7 +2231,7 @@ u8 rtllib_ap_sec_type(struct rtllib_device *ieee)
 		return SEC_ALG_WEP;
 	} else if ((wpa_ie_len != 0)) {
 		if (((ieee->wpa_ie[0] == 0xdd) &&
-		    (!memcmp(&(ieee->wpa_ie[14]), ccmp_ie, 4))) ||
+		    (!memcmp(&ieee->wpa_ie[14], ccmp_ie, 4))) ||
 		    ((ieee->wpa_ie[0] == 0x30) &&
 		    (!memcmp(&ieee->wpa_ie[10], ccmp_rsn_ie, 4))))
 			return SEC_ALG_CCMP;
-- 
GitLab


From eb2ebe15b83ead3d49a7087252c82cb1ddd7cace Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:28 -0800
Subject: [PATCH 1859/4076] Staging: rtl8192e: Remove unnecessary parenthesis
 in rtllib_association_req()

Remove parnthesis to fix checkpatch Warning:
Unnecessary parentheses around ieee->ht_info->SelfHTCap

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-7-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 411763cafd2e1..7e132f87295dd 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -727,7 +727,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 	}
 
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
-		ht_cap_buf = (u8 *)&(ieee->ht_info->SelfHTCap);
+		ht_cap_buf = (u8 *)&ieee->ht_info->SelfHTCap;
 		ht_cap_len = sizeof(ieee->ht_info->SelfHTCap);
 		ht_construct_capability_element(ieee, ht_cap_buf, &ht_cap_len,
 					     encrypt, true);
-- 
GitLab


From 7d225068d3fe10818e8cb252f79c4e1ff368663d Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:29 -0800
Subject: [PATCH 1860/4076] Staging: rtl8192e: Fixup multiple assinment in
 init_mgmt_queue()

Break multiple assignment into 2 assignment statements to fix checkpatch
Warning: multiple assignments should be avoided.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-8-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 7e132f87295dd..c7224de279f54 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -134,7 +134,8 @@ static void enqueue_mgmt(struct rtllib_device *ieee, struct sk_buff *skb)
 
 static void init_mgmt_queue(struct rtllib_device *ieee)
 {
-	ieee->mgmt_queue_tail = ieee->mgmt_queue_head = 0;
+	ieee->mgmt_queue_tail = 0;
+	ieee->mgmt_queue_head = 0;
 }
 
 u8 MgntQuery_TxRateExcludeCCKRates(struct rtllib_device *ieee)
@@ -1911,6 +1912,7 @@ static void rtllib_link_change_wq(void *data)
 				     struct rtllib_device, link_change_wq);
 	ieee->link_change(ieee->dev);
 }
+
 /* called only in userspace context */
 void rtllib_disassociate(struct rtllib_device *ieee)
 {
-- 
GitLab


From e946ef939ff73a80c6add269e46e33c378cd25bc Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:30 -0800
Subject: [PATCH 1861/4076] Staging: rtl8192e: Fix statement broken across 2
 lines in rtllib_rx_assoc_resp()

Join 2 lines, so that statment resides on one line, to fix Warning: Lines
should not end with a '('

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-9-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index c7224de279f54..bdf4f732696ec 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1636,8 +1636,7 @@ rtllib_rx_assoc_resp(struct rtllib_device *ieee, struct sk_buff *skb,
 				    "Association response status code 0x%x\n",
 				    errcode);
 			if (ieee->AsocRetryCount < RT_ASOC_RETRY_LIMIT)
-				schedule_delayed_work(
-					 &ieee->associate_procedure_wq, 0);
+				schedule_delayed_work(&ieee->associate_procedure_wq, 0);
 			else
 				rtllib_associate_abort(ieee);
 		}
-- 
GitLab


From afae5cd74171640bb677360b73d39559ea4a136a Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:31 -0800
Subject: [PATCH 1862/4076] Staging: rtl8192e: Fix function definition broken
 across multiple lines

Join 4 lines, so that function definition resides on a single line, to fix
Warning: Lines should not end with a '('

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-10-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index bdf4f732696ec..edc310a21c1a4 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2267,11 +2267,7 @@ static void rtllib_MlmeDisassociateRequest(struct rtllib_device *rtllib,
 	}
 }
 
-static void
-rtllib_MgntDisconnectAP(
-	struct rtllib_device *rtllib,
-	u8 asRsn
-)
+static void rtllib_MgntDisconnectAP(struct rtllib_device *rtllib, u8 asRsn)
 {
 	bool bFilterOutNonAssociatedBSSID = false;
 
-- 
GitLab


From 7fa14461160fe11cd57afa62d0f7f1b1ff328eb2 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:32 -0800
Subject: [PATCH 1863/4076] Staging: rtl8192e: Fixup statement broken across 2
 lines in rtllib_softmac_xmit()

Join 2 lines to fix Warning: Lines should not end with a '('

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-11-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index edc310a21c1a4..aab0d7159dbbe 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1838,8 +1838,7 @@ void rtllib_softmac_xmit(struct rtllib_txb *txb, struct rtllib_device *ieee)
 			else
 				kfree_skb(txb->fragments[i]);
 		} else {
-			ieee->softmac_data_hard_start_xmit(
-					txb->fragments[i],
+			ieee->softmac_data_hard_start_xmit(txb->fragments[i],
 					ieee->dev, ieee->rate);
 		}
 	}
-- 
GitLab


From 75a946f9ac816caf394cdb71da2422d027010a3a Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:33 -0800
Subject: [PATCH 1864/4076] Staging: rtl8192e: Fixup statement broken across 2
 lines in rtllib_softmac_new_net()

Join 2 lines to fix Warning: Lines should not end with a '('

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-12-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index aab0d7159dbbe..67638d7c71ce2 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -1225,8 +1225,7 @@ inline void rtllib_softmac_new_net(struct rtllib_device *ieee,
 					ieee->ht_info->current_ht_support = false;
 
 				ieee->link_state = RTLLIB_ASSOCIATING;
-				schedule_delayed_work(
-					   &ieee->associate_procedure_wq, 0);
+				schedule_delayed_work(&ieee->associate_procedure_wq, 0);
 			} else {
 				if (rtllib_is_54g(&ieee->current_network)) {
 					ieee->rate = 108;
-- 
GitLab


From 4f6054fb3d70b244984ac759003ecb552754fffb Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:34 -0800
Subject: [PATCH 1865/4076] Staging: rtl8192e: Rename function
 rtllib_MFIE_Brate()

Rename function rtllib_MFIE_Brate to rtllib_mfie_brate to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-13-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 67638d7c71ce2..253ff5a76aeca 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -44,7 +44,7 @@ static unsigned int rtllib_MFIE_rate_len(struct rtllib_device *ieee)
  * Then it updates the pointer so that
  * it points after the new MFIE tag added.
  */
-static void rtllib_MFIE_Brate(struct rtllib_device *ieee, u8 **tag_p)
+static void rtllib_mfie_brate(struct rtllib_device *ieee, u8 **tag_p)
 {
 	u8 *tag = *tag_p;
 
@@ -341,7 +341,7 @@ static inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee)
 	memcpy(tag, ieee->current_network.ssid, len);
 	tag += len;
 
-	rtllib_MFIE_Brate(ieee, &tag);
+	rtllib_mfie_brate(ieee, &tag);
 	rtllib_MFIE_Grate(ieee, &tag);
 
 	return skb;
-- 
GitLab


From d70c91a36e3111019bf0b18c4da7642867010abf Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:35 -0800
Subject: [PATCH 1866/4076] Staging: rtl8192e: Rename function
 rtllib_MFIE_Grate()

Rename function rtllib_MFIE_Grate to rtllib_mfie_grate to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-14-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 253ff5a76aeca..f93a9bbddbace 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -61,7 +61,7 @@ static void rtllib_mfie_brate(struct rtllib_device *ieee, u8 **tag_p)
 	*tag_p = tag;
 }
 
-static void rtllib_MFIE_Grate(struct rtllib_device *ieee, u8 **tag_p)
+static void rtllib_mfie_grate(struct rtllib_device *ieee, u8 **tag_p)
 {
 	u8 *tag = *tag_p;
 
@@ -342,7 +342,7 @@ static inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee)
 	tag += len;
 
 	rtllib_mfie_brate(ieee, &tag);
-	rtllib_MFIE_Grate(ieee, &tag);
+	rtllib_mfie_grate(ieee, &tag);
 
 	return skb;
 }
-- 
GitLab


From 1ed0f611670d922bea2ac4c55878d73cb6d1fc0e Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:36 -0800
Subject: [PATCH 1867/4076] Staging: rtl8192e: Rename function
 rtllib_WMM_Info()

Rename function rtllib_WMM_Info to rtllib_wmm_info to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-15-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index f93a9bbddbace..935d170ae01d8 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -82,7 +82,7 @@ static void rtllib_mfie_grate(struct rtllib_device *ieee, u8 **tag_p)
 	*tag_p = tag;
 }
 
-static void rtllib_WMM_Info(struct rtllib_device *ieee, u8 **tag_p)
+static void rtllib_wmm_info(struct rtllib_device *ieee, u8 **tag_p)
 {
 	u8 *tag = *tag_p;
 
@@ -888,7 +888,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 	}
 	if (wmm_info_len) {
 		tag = skb_put(skb, wmm_info_len);
-		rtllib_WMM_Info(ieee, &tag);
+		rtllib_wmm_info(ieee, &tag);
 	}
 
 	if (wps_ie_len && ieee->wps_ie)
-- 
GitLab


From 8867af6775b58d152b4018f6156ab47cfa50e046 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:37 -0800
Subject: [PATCH 1868/4076] Staging: rtl8192e: Rename function
 rtllib_TURBO_Info()

Rename function rtllib_TURBO_Info to rtllib_turbo_info to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-16-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 935d170ae01d8..d102e400cdb3f 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -98,7 +98,7 @@ static void rtllib_wmm_info(struct rtllib_device *ieee, u8 **tag_p)
 	*tag_p = tag;
 }
 
-static void rtllib_TURBO_Info(struct rtllib_device *ieee, u8 **tag_p)
+static void rtllib_turbo_info(struct rtllib_device *ieee, u8 **tag_p)
 {
 	u8 *tag = *tag_p;
 
@@ -896,7 +896,7 @@ rtllib_association_req(struct rtllib_network *beacon,
 
 	if (turbo_info_len) {
 		tag = skb_put(skb, turbo_info_len);
-		rtllib_TURBO_Info(ieee, &tag);
+		rtllib_turbo_info(ieee, &tag);
 	}
 
 	if (ieee->ht_info->current_ht_support && ieee->ht_info->enable_ht) {
-- 
GitLab


From 66dda5e3e000e1a59af69f86672d963a5d0eae37 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:38 -0800
Subject: [PATCH 1869/4076] Staging: rtl8192e: Rename variable QueryRate

Rename variable QueryRate to query_rate to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-17-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index d102e400cdb3f..63e6c3d80c712 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -141,26 +141,26 @@ static void init_mgmt_queue(struct rtllib_device *ieee)
 u8 MgntQuery_TxRateExcludeCCKRates(struct rtllib_device *ieee)
 {
 	u16	i;
-	u8	QueryRate = 0;
+	u8	query_rate = 0;
 	u8	BasicRate;
 
 	for (i = 0; i < ieee->current_network.rates_len; i++) {
 		BasicRate = ieee->current_network.rates[i] & 0x7F;
 		if (!rtllib_is_cck_rate(BasicRate)) {
-			if (QueryRate == 0) {
-				QueryRate = BasicRate;
+			if (query_rate == 0) {
+				query_rate = BasicRate;
 			} else {
-				if (BasicRate < QueryRate)
-					QueryRate = BasicRate;
+				if (BasicRate < query_rate)
+					query_rate = BasicRate;
 			}
 		}
 	}
 
-	if (QueryRate == 0) {
-		QueryRate = 12;
+	if (query_rate == 0) {
+		query_rate = 12;
 		netdev_info(ieee->dev, "No BasicRate found!!\n");
 	}
-	return QueryRate;
+	return query_rate;
 }
 
 static u8 MgntQuery_MgntFrameTxRate(struct rtllib_device *ieee)
-- 
GitLab


From 0edd0fb79ef6b8b6bf62c407dff276e2297abf36 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:39 -0800
Subject: [PATCH 1870/4076] Staging: rtl8192e: Rename variable BasicRate

Rename variable BasicRate to basic_rate to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-18-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 63e6c3d80c712..58b1aabc50ea7 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -142,23 +142,23 @@ u8 MgntQuery_TxRateExcludeCCKRates(struct rtllib_device *ieee)
 {
 	u16	i;
 	u8	query_rate = 0;
-	u8	BasicRate;
+	u8	basic_rate;
 
 	for (i = 0; i < ieee->current_network.rates_len; i++) {
-		BasicRate = ieee->current_network.rates[i] & 0x7F;
-		if (!rtllib_is_cck_rate(BasicRate)) {
+		basic_rate = ieee->current_network.rates[i] & 0x7F;
+		if (!rtllib_is_cck_rate(basic_rate)) {
 			if (query_rate == 0) {
-				query_rate = BasicRate;
+				query_rate = basic_rate;
 			} else {
-				if (BasicRate < query_rate)
-					query_rate = BasicRate;
+				if (basic_rate < query_rate)
+					query_rate = basic_rate;
 			}
 		}
 	}
 
 	if (query_rate == 0) {
 		query_rate = 12;
-		netdev_info(ieee->dev, "No BasicRate found!!\n");
+		netdev_info(ieee->dev, "No basic_rate found!!\n");
 	}
 	return query_rate;
 }
-- 
GitLab


From 6a20007654b6fe4c60cae9cd157d2c49c2072fee Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:40 -0800
Subject: [PATCH 1871/4076] Staging: rtl8192e: Rename variable skb_waitQ

Rename variable skb_waitQ to skb_waitq to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-19-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c | 4 ++--
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c    | 2 +-
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c      | 6 +++---
 drivers/staging/rtl8192e/rtllib.h                 | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c         | 8 ++++----
 5 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c
index eba8364d0ff21..7f0c160bc7419 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_cmdpkt.c
@@ -63,9 +63,9 @@ bool rtl92e_send_cmd_pkt(struct net_device *dev, u32 type, const void *data,
 
 		if (type == DESC_PACKET_TYPE_INIT &&
 		    (!priv->rtllib->check_nic_enough_desc(dev, TXCMD_QUEUE) ||
-		     (!skb_queue_empty(&priv->rtllib->skb_waitQ[TXCMD_QUEUE])) ||
+		     (!skb_queue_empty(&priv->rtllib->skb_waitq[TXCMD_QUEUE])) ||
 		     (priv->rtllib->queue_stop))) {
-			skb_queue_tail(&priv->rtllib->skb_waitQ[TXCMD_QUEUE],
+			skb_queue_tail(&priv->rtllib->skb_waitq[TXCMD_QUEUE],
 				       skb);
 		} else {
 			priv->rtllib->softmac_hard_start_xmit(skb, dev);
diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index 763ecaad66528..ed0c152c2477d 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -1728,7 +1728,7 @@ void rtl92e_stop_adapter(struct net_device *dev, bool reset)
 	}
 
 	for (i = 0; i < MAX_QUEUE_SIZE; i++)
-		skb_queue_purge(&priv->rtllib->skb_waitQ[i]);
+		skb_queue_purge(&priv->rtllib->skb_waitq[i]);
 
 	skb_queue_purge(&priv->skb_queue);
 }
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index bef0422331176..5107d06a9fd05 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -723,7 +723,7 @@ static void _rtl92e_init_priv_variable(struct net_device *dev)
 	skb_queue_head_init(&priv->skb_queue);
 
 	for (i = 0; i < MAX_QUEUE_SIZE; i++)
-		skb_queue_head_init(&priv->rtllib->skb_waitQ[i]);
+		skb_queue_head_init(&priv->rtllib->skb_waitq[i]);
 }
 
 static void _rtl92e_init_priv_lock(struct r8192_priv *priv)
@@ -1574,9 +1574,9 @@ static void _rtl92e_tx_resume(struct net_device *dev)
 
 	for (queue_index = BK_QUEUE;
 	     queue_index < MAX_QUEUE_SIZE; queue_index++) {
-		while ((!skb_queue_empty(&ieee->skb_waitQ[queue_index])) &&
+		while ((!skb_queue_empty(&ieee->skb_waitq[queue_index])) &&
 		(priv->rtllib->check_nic_enough_desc(dev, queue_index) > 0)) {
-			skb = skb_dequeue(&ieee->skb_waitQ[queue_index]);
+			skb = skb_dequeue(&ieee->skb_waitq[queue_index]);
 			ieee->softmac_data_hard_start_xmit(skb, dev, 0);
 		}
 	}
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 341d9ddc9a1f4..4a175f0146cfd 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1382,7 +1382,7 @@ struct rtllib_device {
 	int mgmt_queue_head;
 	int mgmt_queue_tail;
 	u8 AsocRetryCount;
-	struct sk_buff_head skb_waitQ[MAX_QUEUE_SIZE];
+	struct sk_buff_head skb_waitq[MAX_QUEUE_SIZE];
 
 	bool	bdynamic_txpower_enable;
 
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 58b1aabc50ea7..e6a2e70b9e91c 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -236,7 +236,7 @@ inline void softmac_mgmt_xmit(struct sk_buff *skb, struct rtllib_device *ieee)
 		/* check whether the managed packet queued greater than 5 */
 		if (!ieee->check_nic_enough_desc(ieee->dev,
 						 tcb_desc->queue_index) ||
-		    skb_queue_len(&ieee->skb_waitQ[tcb_desc->queue_index]) ||
+		    skb_queue_len(&ieee->skb_waitq[tcb_desc->queue_index]) ||
 		    ieee->queue_stop) {
 			/* insert the skb packet to the management queue
 			 *
@@ -246,7 +246,7 @@ inline void softmac_mgmt_xmit(struct sk_buff *skb, struct rtllib_device *ieee)
 			netdev_info(ieee->dev,
 			       "%s():insert to waitqueue, queue_index:%d!\n",
 			       __func__, tcb_desc->queue_index);
-			skb_queue_tail(&ieee->skb_waitQ[tcb_desc->queue_index],
+			skb_queue_tail(&ieee->skb_waitq[tcb_desc->queue_index],
 				       skb);
 		} else {
 			ieee->softmac_hard_start_xmit(skb, ieee->dev);
@@ -1823,7 +1823,7 @@ void rtllib_softmac_xmit(struct rtllib_txb *txb, struct rtllib_device *ieee)
 	 * the wait queue
 	 */
 	for (i = 0; i < txb->nr_frags; i++) {
-		queue_len = skb_queue_len(&ieee->skb_waitQ[queue_index]);
+		queue_len = skb_queue_len(&ieee->skb_waitq[queue_index]);
 		if ((queue_len  != 0) ||
 		    (!ieee->check_nic_enough_desc(ieee->dev, queue_index)) ||
 		    (ieee->queue_stop)) {
@@ -1832,7 +1832,7 @@ void rtllib_softmac_xmit(struct rtllib_txb *txb, struct rtllib_device *ieee)
 			 * to check it any more.
 			 */
 			if (queue_len < 200)
-				skb_queue_tail(&ieee->skb_waitQ[queue_index],
+				skb_queue_tail(&ieee->skb_waitq[queue_index],
 					       txb->fragments[i]);
 			else
 				kfree_skb(txb->fragments[i]);
-- 
GitLab


From 53156632ee3ceaf5a2c7a97505c24e9a8148b8d5 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:41 -0800
Subject: [PATCH 1872/4076] Staging: rtl8192e: Rename variable bInitState

Rename variable bInitState to init_state to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-20-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h         | 4 ++--
 drivers/staging/rtl8192e/rtllib_softmac.c | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 4a175f0146cfd..1c32c37818595 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1677,8 +1677,8 @@ void rtllib_sta_ps_send_pspoll_frame(struct rtllib_device *ieee);
 void rtllib_start_protocol(struct rtllib_device *ieee);
 void rtllib_stop_protocol(struct rtllib_device *ieee);
 
-void rtllib_EnableNetMonitorMode(struct net_device *dev, bool bInitState);
-void rtllib_DisableNetMonitorMode(struct net_device *dev, bool bInitState);
+void rtllib_EnableNetMonitorMode(struct net_device *dev, bool init_state);
+void rtllib_DisableNetMonitorMode(struct net_device *dev, bool init_state);
 
 void rtllib_softmac_stop_protocol(struct rtllib_device *ieee);
 void rtllib_softmac_start_protocol(struct rtllib_device *ieee);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index e6a2e70b9e91c..3c6cc3924634a 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -349,26 +349,26 @@ static inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee)
 
 /* Enables network monitor mode, all rx packets will be received. */
 void rtllib_EnableNetMonitorMode(struct net_device *dev,
-		bool bInitState)
+		bool init_state)
 {
 	struct rtllib_device *ieee = netdev_priv_rsl(dev);
 
 	netdev_info(dev, "========>Enter Monitor Mode\n");
 
-	ieee->AllowAllDestAddrHandler(dev, true, !bInitState);
+	ieee->AllowAllDestAddrHandler(dev, true, !init_state);
 }
 
 /* Disables network monitor mode. Only packets destinated to
  * us will be received.
  */
 void rtllib_DisableNetMonitorMode(struct net_device *dev,
-		bool bInitState)
+		bool init_state)
 {
 	struct rtllib_device *ieee = netdev_priv_rsl(dev);
 
 	netdev_info(dev, "========>Exit Monitor Mode\n");
 
-	ieee->AllowAllDestAddrHandler(dev, false, !bInitState);
+	ieee->AllowAllDestAddrHandler(dev, false, !init_state);
 }
 
 static void rtllib_send_probe(struct rtllib_device *ieee)
-- 
GitLab


From 9ebffbe2ad12b030b282796fed5117a182588c51 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Fri, 22 Dec 2023 17:59:42 -0800
Subject: [PATCH 1873/4076] Staging: rtl8192e: Rename function
 rtllib_DisableNetMonitorMode()

Rename function rtllib_DisableNetMonitorMode to rtllib_disable_net_monitor_mode
to fix checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231223015942.418263-21-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h            | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c    | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac_wx.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 1c32c37818595..63217444ba65d 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1678,7 +1678,7 @@ void rtllib_start_protocol(struct rtllib_device *ieee);
 void rtllib_stop_protocol(struct rtllib_device *ieee);
 
 void rtllib_EnableNetMonitorMode(struct net_device *dev, bool init_state);
-void rtllib_DisableNetMonitorMode(struct net_device *dev, bool init_state);
+void rtllib_disable_net_monitor_mode(struct net_device *dev, bool init_state);
 
 void rtllib_softmac_stop_protocol(struct rtllib_device *ieee);
 void rtllib_softmac_start_protocol(struct rtllib_device *ieee);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 3c6cc3924634a..cd5b799bcadea 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -361,7 +361,7 @@ void rtllib_EnableNetMonitorMode(struct net_device *dev,
 /* Disables network monitor mode. Only packets destinated to
  * us will be received.
  */
-void rtllib_DisableNetMonitorMode(struct net_device *dev,
+void rtllib_disable_net_monitor_mode(struct net_device *dev,
 		bool init_state)
 {
 	struct rtllib_device *ieee = netdev_priv_rsl(dev);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
index 5d165d0b134d1..eb331cbb98501 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
@@ -270,7 +270,7 @@ int rtllib_wx_set_mode(struct rtllib_device *ieee, struct iw_request_info *a,
 	} else {
 		ieee->dev->type = ARPHRD_ETHER;
 		if (ieee->iw_mode == IW_MODE_MONITOR)
-			rtllib_DisableNetMonitorMode(ieee->dev, false);
+			rtllib_disable_net_monitor_mode(ieee->dev, false);
 	}
 
 	if (!ieee->proto_started) {
-- 
GitLab


From 520adf3ba4a4bdd41450c57b17ef01f8a069fbfe Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:05:22 -0800
Subject: [PATCH 1874/4076] driver core: class: fix Excess kernel-doc
 description warning

Remove the @p: lines to prevent the kernel-doc warning:

include/linux/device/class.h:72: warning: Excess struct member 'p' description in 'class'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://lore.kernel.org/r/20231223050522.13867-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device/class.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/device/class.h b/include/linux/device/class.h
index abf3d3bfb6fe4..c576b49c55c22 100644
--- a/include/linux/device/class.h
+++ b/include/linux/device/class.h
@@ -40,8 +40,6 @@ struct fwnode_handle;
  *		for the devices belonging to the class. Usually tied to
  *		device's namespace.
  * @pm:		The default device power management operations of this class.
- * @p:		The private data of the driver core, no one other than the
- *		driver core can touch this.
  *
  * A class is a higher-level view of a device that abstracts out low-level
  * implementation details. Drivers may see a SCSI disk or an ATA disk, but,
-- 
GitLab


From ae4d90f7ca49eb71f8a3dca64d06d4c4e2193705 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:05:32 -0800
Subject: [PATCH 1875/4076] driver core: device.h: fix Excess kernel-doc
 description warning

Remove the @knode_class: line to prevent the kernel-doc warning:

include/linux/device.h:807: warning: Excess struct member 'knode_class' description in 'device'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://lore.kernel.org/r/20231223050532.13881-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/device.h b/include/linux/device.h
index aefc5ca7f1cfc..ed600dbf950e3 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -662,7 +662,6 @@ struct device_physical_location {
  * @id:		device instance
  * @devres_lock: Spinlock to protect the resource of the device.
  * @devres_head: The resources list of the device.
- * @knode_class: The node used to add the device to the class list.
  * @class:	The class of the device.
  * @groups:	Optional attribute groups.
  * @release:	Callback to free the device after all references have
-- 
GitLab


From 1760bfa7d7ca490cf8a61fe50ddeb1769cadd89e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:06:36 -0800
Subject: [PATCH 1876/4076] usb: linux/usb.h: fix Excess kernel-doc description
 warning

Remove the @removable: line to prevent the kernel-doc warning:

include/linux/usb.h:732: warning: Excess struct member 'removable' description in 'usb_device'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Link: https://lore.kernel.org/r/20231223050636.14022-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/usb.h b/include/linux/usb.h
index 618e5a0b1a223..07556341ba2b4 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -632,7 +632,6 @@ struct usb3_lpm_parameters {
  * @reset_resume: needs reset instead of resume
  * @port_is_suspended: the upstream port is suspended (L2 or U3)
  * @slot_id: Slot ID assigned by xHCI
- * @removable: Device can be physically removed from this port
  * @l1_params: best effor service latency for USB2 L1 LPM state, and L1 timeout.
  * @u1_params: exit latencies for USB3 U1 LPM state, and hub-initiated timeout.
  * @u2_params: exit latencies for USB3 U2 LPM state, and hub-initiated timeout.
-- 
GitLab


From 7037f7141ce7f736aa2b96b48002c0a17bfcf741 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 21 Dec 2023 16:44:47 +0200
Subject: [PATCH 1877/4076] pvpanic: Don't use "proxy" headers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Update header inclusions to follow IWYU (Include What You Use)
principle.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20231221144447.2762077-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/pvpanic/pvpanic-mmio.c |  7 +++----
 drivers/misc/pvpanic/pvpanic-pci.c  |  5 +----
 drivers/misc/pvpanic/pvpanic.c      | 12 ++++++++----
 drivers/misc/pvpanic/pvpanic.h      |  5 +++++
 4 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/misc/pvpanic/pvpanic-mmio.c b/drivers/misc/pvpanic/pvpanic-mmio.c
index 9715798acce3d..f3f2113a54a7e 100644
--- a/drivers/misc/pvpanic/pvpanic-mmio.c
+++ b/drivers/misc/pvpanic/pvpanic-mmio.c
@@ -7,16 +7,15 @@
  *  Copyright (C) 2021 Oracle.
  */
 
+#include <linux/device.h>
+#include <linux/err.h>
 #include <linux/io.h>
-#include <linux/kernel.h>
+#include <linux/ioport.h>
 #include <linux/kexec.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
-#include <linux/slab.h>
-
-#include <uapi/misc/pvpanic.h>
 
 #include "pvpanic.h"
 
diff --git a/drivers/misc/pvpanic/pvpanic-pci.c b/drivers/misc/pvpanic/pvpanic-pci.c
index 689af4c28c2a9..0b2ae3423f07e 100644
--- a/drivers/misc/pvpanic/pvpanic-pci.c
+++ b/drivers/misc/pvpanic/pvpanic-pci.c
@@ -5,13 +5,10 @@
  *  Copyright (C) 2021 Oracle.
  */
 
-#include <linux/kernel.h>
+#include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/types.h>
-#include <linux/slab.h>
-
-#include <uapi/misc/pvpanic.h>
 
 #include "pvpanic.h"
 
diff --git a/drivers/misc/pvpanic/pvpanic.c b/drivers/misc/pvpanic/pvpanic.c
index 305b367e0ce34..df3457ce1cb14 100644
--- a/drivers/misc/pvpanic/pvpanic.c
+++ b/drivers/misc/pvpanic/pvpanic.c
@@ -8,16 +8,20 @@
  */
 
 #include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/gfp_types.h>
 #include <linux/io.h>
-#include <linux/kernel.h>
 #include <linux/kexec.h>
+#include <linux/kstrtox.h>
+#include <linux/limits.h>
+#include <linux/list.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/platform_device.h>
 #include <linux/panic_notifier.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
 #include <linux/types.h>
-#include <linux/cdev.h>
-#include <linux/list.h>
 
 #include <uapi/misc/pvpanic.h>
 
diff --git a/drivers/misc/pvpanic/pvpanic.h b/drivers/misc/pvpanic/pvpanic.h
index 46ffb10438adf..a42fa760eed58 100644
--- a/drivers/misc/pvpanic/pvpanic.h
+++ b/drivers/misc/pvpanic/pvpanic.h
@@ -8,6 +8,11 @@
 #ifndef PVPANIC_H_
 #define PVPANIC_H_
 
+#include <linux/compiler_types.h>
+
+struct attribute_group;
+struct device;
+
 int devm_pvpanic_probe(struct device *dev, void __iomem *base);
 extern const struct attribute_group *pvpanic_dev_groups[];
 
-- 
GitLab


From 8974a86d1edd9ae83e38c520d640ffc728092eac Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 21 Dec 2023 21:25:19 -0800
Subject: [PATCH 1878/4076] virt: vbox: core: fix all kernel-doc warnings

Use kernel-doc format for functions that have comments that begin
with "/**".
This prevents 26 kernel-doc warnings.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231222052521.14333-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/vboxguest/vboxguest_core.c | 154 ++++++++++++++----------
 1 file changed, 91 insertions(+), 63 deletions(-)

diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c
index dfd69bd77f531..c6e9855998abf 100644
--- a/drivers/virt/vboxguest/vboxguest_core.c
+++ b/drivers/virt/vboxguest/vboxguest_core.c
@@ -33,16 +33,15 @@
 	 VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN)
 
 /**
- * Reserves memory in which the VMM can relocate any guest mappings
- * that are floating around.
+ * vbg_guest_mappings_init - Reserves memory in which the VMM can
+ *	relocate any guest mappings that are floating around.
+ * @gdev:		The Guest extension device.
  *
  * This operation is a little bit tricky since the VMM might not accept
  * just any address because of address clashes between the three contexts
  * it operates in, so we try several times.
  *
  * Failure to reserve the guest mappings is ignored.
- *
- * @gdev:		The Guest extension device.
  */
 static void vbg_guest_mappings_init(struct vbg_dev *gdev)
 {
@@ -125,7 +124,7 @@ out:
 }
 
 /**
- * Undo what vbg_guest_mappings_init did.
+ * vbg_guest_mappings_exit - Undo what vbg_guest_mappings_init did.
  *
  * @gdev:		The Guest extension device.
  */
@@ -166,9 +165,10 @@ static void vbg_guest_mappings_exit(struct vbg_dev *gdev)
 }
 
 /**
- * Report the guest information to the host.
- * Return: 0 or negative errno value.
+ * vbg_report_guest_info - Report the guest information to the host.
  * @gdev:		The Guest extension device.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_report_guest_info(struct vbg_dev *gdev)
 {
@@ -229,10 +229,11 @@ out_free:
 }
 
 /**
- * Report the guest driver status to the host.
- * Return: 0 or negative errno value.
+ * vbg_report_driver_status - Report the guest driver status to the host.
  * @gdev:		The Guest extension device.
  * @active:		Flag whether the driver is now active or not.
+ *
+ * Return: 0 or negative errno value.
  */
 static int vbg_report_driver_status(struct vbg_dev *gdev, bool active)
 {
@@ -261,10 +262,12 @@ static int vbg_report_driver_status(struct vbg_dev *gdev, bool active)
 }
 
 /**
- * Inflate the balloon by one chunk. The caller owns the balloon mutex.
- * Return: 0 or negative errno value.
+ * vbg_balloon_inflate - Inflate the balloon by one chunk. The caller
+ * owns the balloon mutex.
  * @gdev:		The Guest extension device.
  * @chunk_idx:		Index of the chunk.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_balloon_inflate(struct vbg_dev *gdev, u32 chunk_idx)
 {
@@ -312,10 +315,12 @@ out_error:
 }
 
 /**
- * Deflate the balloon by one chunk. The caller owns the balloon mutex.
- * Return: 0 or negative errno value.
+ * vbg_balloon_deflate - Deflate the balloon by one chunk. The caller
+ * owns the balloon mutex.
  * @gdev:		The Guest extension device.
  * @chunk_idx:		Index of the chunk.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_balloon_deflate(struct vbg_dev *gdev, u32 chunk_idx)
 {
@@ -344,7 +349,7 @@ static int vbg_balloon_deflate(struct vbg_dev *gdev, u32 chunk_idx)
 	return 0;
 }
 
-/**
+/*
  * Respond to VMMDEV_EVENT_BALLOON_CHANGE_REQUEST events, query the size
  * the host wants the balloon to be and adjust accordingly.
  */
@@ -409,7 +414,7 @@ static void vbg_balloon_work(struct work_struct *work)
 	}
 }
 
-/**
+/*
  * Callback for heartbeat timer.
  */
 static void vbg_heartbeat_timer(struct timer_list *t)
@@ -422,11 +427,12 @@ static void vbg_heartbeat_timer(struct timer_list *t)
 }
 
 /**
- * Configure the host to check guest's heartbeat
- * and get heartbeat interval from the host.
- * Return: 0 or negative errno value.
+ * vbg_heartbeat_host_config - Configure the host to check guest's heartbeat
+ *	and get heartbeat interval from the host.
  * @gdev:		The Guest extension device.
  * @enabled:		Set true to enable guest heartbeat checks on host.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled)
 {
@@ -449,9 +455,11 @@ static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled)
 }
 
 /**
- * Initializes the heartbeat timer. This feature may be disabled by the host.
- * Return: 0 or negative errno value.
+ * vbg_heartbeat_init - Initializes the heartbeat timer. This feature
+ * may be disabled by the host.
  * @gdev:		The Guest extension device.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_heartbeat_init(struct vbg_dev *gdev)
 {
@@ -481,7 +489,8 @@ static int vbg_heartbeat_init(struct vbg_dev *gdev)
 }
 
 /**
- * Cleanup hearbeat code, stop HB timer and disable host heartbeat checking.
+ * vbg_heartbeat_exit - Cleanup heartbeat code, stop HB timer and disable
+ *	host heartbeat checking.
  * @gdev:		The Guest extension device.
  */
 static void vbg_heartbeat_exit(struct vbg_dev *gdev)
@@ -493,11 +502,12 @@ static void vbg_heartbeat_exit(struct vbg_dev *gdev)
 }
 
 /**
- * Applies a change to the bit usage tracker.
- * Return: true if the mask changed, false if not.
+ * vbg_track_bit_usage - Applies a change to the bit usage tracker.
  * @tracker:		The bit usage tracker.
  * @changed:		The bits to change.
  * @previous:		The previous value of the bits.
+ *
+ * Return: %true if the mask changed, %false if not.
  */
 static bool vbg_track_bit_usage(struct vbg_bit_usage_tracker *tracker,
 				u32 changed, u32 previous)
@@ -529,10 +539,12 @@ static bool vbg_track_bit_usage(struct vbg_bit_usage_tracker *tracker,
 }
 
 /**
- * Init and termination worker for resetting the (host) event filter on the host
- * Return: 0 or negative errno value.
+ * vbg_reset_host_event_filter - Init and termination worker for
+ *	resetting the (host) event filter on the host
  * @gdev:		   The Guest extension device.
  * @fixed_events:	   Fixed events (init time).
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
 				       u32 fixed_events)
@@ -556,12 +568,8 @@ static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
 }
 
 /**
- * Changes the event filter mask for the given session.
- *
- * This is called in response to VBG_IOCTL_CHANGE_FILTER_MASK as well as to
- * do session cleanup. Takes the session mutex.
- *
- * Return: 0 or negative errno value.
+ * vbg_set_session_event_filter - Changes the event filter mask for the
+ *	given session.
  * @gdev:			The Guest extension device.
  * @session:			The session.
  * @or_mask:			The events to add.
@@ -570,6 +578,11 @@ static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
  *				This tweaks the error handling so we perform
  *				proper session cleanup even if the host
  *				misbehaves.
+ *
+ * This is called in response to VBG_IOCTL_CHANGE_FILTER_MASK as well as to
+ * do session cleanup. Takes the session mutex.
+ *
+ * Return: 0 or negative errno value.
  */
 static int vbg_set_session_event_filter(struct vbg_dev *gdev,
 					struct vbg_session *session,
@@ -637,9 +650,11 @@ out:
 }
 
 /**
- * Init and termination worker for set guest capabilities to zero on the host.
- * Return: 0 or negative errno value.
+ * vbg_reset_host_capabilities - Init and termination worker for set
+ *	guest capabilities to zero on the host.
  * @gdev:		The Guest extension device.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_reset_host_capabilities(struct vbg_dev *gdev)
 {
@@ -662,12 +677,14 @@ static int vbg_reset_host_capabilities(struct vbg_dev *gdev)
 }
 
 /**
- * Set guest capabilities on the host.
- * Must be called with gdev->session_mutex hold.
- * Return: 0 or negative errno value.
+ * vbg_set_host_capabilities - Set guest capabilities on the host.
  * @gdev:			The Guest extension device.
  * @session:			The session.
  * @session_termination:	Set if we're called by the session cleanup code.
+ *
+ * Must be called with gdev->session_mutex hold.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_set_host_capabilities(struct vbg_dev *gdev,
 				     struct vbg_session *session,
@@ -704,9 +721,8 @@ static int vbg_set_host_capabilities(struct vbg_dev *gdev,
 }
 
 /**
- * Acquire (get exclusive access) guest capabilities for a session.
- * Takes the session mutex.
- * Return: 0 or negative errno value.
+ * vbg_acquire_session_capabilities - Acquire (get exclusive access)
+ *	guest capabilities for a session.
  * @gdev:			The Guest extension device.
  * @session:			The session.
  * @flags:			Flags (VBGL_IOC_AGC_FLAGS_XXX).
@@ -716,6 +732,10 @@ static int vbg_set_host_capabilities(struct vbg_dev *gdev,
  *				This tweaks the error handling so we perform
  *				proper session cleanup even if the host
  *				misbehaves.
+ *
+ * Takes the session mutex.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_acquire_session_capabilities(struct vbg_dev *gdev,
 					    struct vbg_session *session,
@@ -811,8 +831,8 @@ out:
 }
 
 /**
- * Sets the guest capabilities for a session. Takes the session mutex.
- * Return: 0 or negative errno value.
+ * vbg_set_session_capabilities - Sets the guest capabilities for a
+ *	session. Takes the session mutex.
  * @gdev:			The Guest extension device.
  * @session:			The session.
  * @or_mask:			The capabilities to add.
@@ -821,6 +841,8 @@ out:
  *				This tweaks the error handling so we perform
  *				proper session cleanup even if the host
  *				misbehaves.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_set_session_capabilities(struct vbg_dev *gdev,
 					struct vbg_session *session,
@@ -866,9 +888,10 @@ out:
 }
 
 /**
- * vbg_query_host_version get the host feature mask and version information.
- * Return: 0 or negative errno value.
+ * vbg_query_host_version - get the host feature mask and version information.
  * @gdev:		The Guest extension device.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_query_host_version(struct vbg_dev *gdev)
 {
@@ -905,19 +928,18 @@ out:
 }
 
 /**
- * Initializes the VBoxGuest device extension when the
- * device driver is loaded.
+ * vbg_core_init - Initializes the VBoxGuest device extension when the
+ *	device driver is loaded.
+ * @gdev:		The Guest extension device.
+ * @fixed_events:	Events that will be enabled upon init and no client
+ *			will ever be allowed to mask.
  *
  * The native code locates the VMMDev on the PCI bus and retrieve
  * the MMIO and I/O port ranges, this function will take care of
  * mapping the MMIO memory (if present). Upon successful return
  * the native code should set up the interrupt handler.
  *
- * Return: 0 or negative errno value.
- *
- * @gdev:		The Guest extension device.
- * @fixed_events:	Events that will be enabled upon init and no client
- *			will ever be allowed to mask.
+ * Return: %0 or negative errno value.
  */
 int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events)
 {
@@ -1017,11 +1039,12 @@ err_free_reqs:
 }
 
 /**
- * Call this on exit to clean-up vboxguest-core managed resources.
+ * vbg_core_exit - Call this on exit to clean-up vboxguest-core managed
+ *	resources.
+ * @gdev:		The Guest extension device.
  *
  * The native code should call this before the driver is loaded,
  * but don't call this on shutdown.
- * @gdev:		The Guest extension device.
  */
 void vbg_core_exit(struct vbg_dev *gdev)
 {
@@ -1046,12 +1069,13 @@ void vbg_core_exit(struct vbg_dev *gdev)
 }
 
 /**
- * Creates a VBoxGuest user session.
+ * vbg_core_open_session - Creates a VBoxGuest user session.
+ * @gdev:		The Guest extension device.
+ * @requestor:		VMMDEV_REQUESTOR_* flags
  *
  * vboxguest_linux.c calls this when userspace opens the char-device.
+ *
  * Return: A pointer to the new session or an ERR_PTR on error.
- * @gdev:		The Guest extension device.
- * @requestor:		VMMDEV_REQUESTOR_* flags
  */
 struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor)
 {
@@ -1068,7 +1092,7 @@ struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor)
 }
 
 /**
- * Closes a VBoxGuest session.
+ * vbg_core_close_session - Closes a VBoxGuest session.
  * @session:		The session to close (and free).
  */
 void vbg_core_close_session(struct vbg_session *session)
@@ -1250,11 +1274,13 @@ static int vbg_ioctl_interrupt_all_wait_events(struct vbg_dev *gdev,
 }
 
 /**
- * Checks if the VMM request is allowed in the context of the given session.
- * Return: 0 or negative errno value.
+ * vbg_req_allowed - Checks if the VMM request is allowed in the
+ *	context of the given session.
  * @gdev:		The Guest extension device.
  * @session:		The calling session.
  * @req:		The request.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_req_allowed(struct vbg_dev *gdev, struct vbg_session *session,
 			   const struct vmmdev_request_header *req)
@@ -1670,11 +1696,12 @@ static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev,
 }
 
 /**
- * Common IOCtl for user to kernel communication.
- * Return: 0 or negative errno value.
+ * vbg_core_ioctl - Common IOCtl for user to kernel communication.
  * @session:	The client session.
  * @req:	The requested function.
  * @data:	The i/o data buffer, minimum size sizeof(struct vbg_ioctl_hdr).
+ *
+ * Return: %0 or negative errno value.
  */
 int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
 {
@@ -1744,11 +1771,12 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
 }
 
 /**
- * Report guest supported mouse-features to the host.
+ * vbg_core_set_mouse_status - Report guest supported mouse-features to the host.
  *
- * Return: 0 or negative errno value.
  * @gdev:		The Guest extension device.
  * @features:		The set of features to report to the host.
+ *
+ * Return: %0 or negative errno value.
  */
 int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features)
 {
@@ -1772,7 +1800,7 @@ int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features)
 	return vbg_status_code_to_errno(rc);
 }
 
-/** Core interrupt service routine. */
+/* Core interrupt service routine. */
 irqreturn_t vbg_core_isr(int irq, void *dev_id)
 {
 	struct vbg_dev *gdev = dev_id;
-- 
GitLab


From 2fd34a5d1df9e25edd87bc5805bf9c86aa4364fa Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 21 Dec 2023 21:25:20 -0800
Subject: [PATCH 1879/4076] virt: vbox: linux: fix all kernel-doc warnings

Use kernel-doc format for functions that are almost complete in their
kernel-doc comments.
For other functions, just change the comment to a common C comment.
This prevents 7 kernel-doc warnings.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231222052521.14333-2-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/vboxguest/vboxguest_linux.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c
index c47e62dc55da8..8c92ea5b73051 100644
--- a/drivers/virt/vboxguest/vboxguest_linux.c
+++ b/drivers/virt/vboxguest/vboxguest_linux.c
@@ -81,10 +81,11 @@ static int vbg_misc_device_user_open(struct inode *inode, struct file *filp)
 }
 
 /**
- * Close device.
- * Return: 0 on success, negated errno on failure.
+ * vbg_misc_device_close - Close device.
  * @inode:		Pointer to inode info structure.
  * @filp:		Associated file pointer.
+ *
+ * Return: %0 on success, negated errno on failure.
  */
 static int vbg_misc_device_close(struct inode *inode, struct file *filp)
 {
@@ -94,11 +95,12 @@ static int vbg_misc_device_close(struct inode *inode, struct file *filp)
 }
 
 /**
- * Device I/O Control entry point.
- * Return: 0 on success, negated errno on failure.
+ * vbg_misc_device_ioctl - Device I/O Control entry point.
  * @filp:		Associated file pointer.
  * @req:		The request specified to ioctl().
  * @arg:		The argument specified to ioctl().
+ *
+ * Return: %0 on success, negated errno on failure.
  */
 static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
 				  unsigned long arg)
@@ -173,7 +175,7 @@ out:
 	return ret;
 }
 
-/** The file_operations structures. */
+/* The file_operations structures. */
 static const struct file_operations vbg_misc_device_fops = {
 	.owner			= THIS_MODULE,
 	.open			= vbg_misc_device_open,
@@ -193,7 +195,7 @@ static const struct file_operations vbg_misc_device_user_fops = {
 #endif
 };
 
-/**
+/*
  * Called when the input device is first opened.
  *
  * Sets up absolute mouse reporting.
@@ -206,7 +208,7 @@ static int vbg_input_open(struct input_dev *input)
 	return vbg_core_set_mouse_status(gdev, feat);
 }
 
-/**
+/*
  * Called if all open handles to the input device are closed.
  *
  * Disables absolute reporting.
@@ -218,7 +220,7 @@ static void vbg_input_close(struct input_dev *input)
 	vbg_core_set_mouse_status(gdev, 0);
 }
 
-/**
+/*
  * Creates the kernel input device.
  *
  * Return: 0 on success, negated errno on failure.
@@ -277,7 +279,7 @@ static struct attribute *vbg_pci_attrs[] = {
 };
 ATTRIBUTE_GROUPS(vbg_pci);
 
-/**
+/*
  * Does the PCI detection and init of the device.
  *
  * Return: 0 on success, negated errno on failure.
@@ -453,7 +455,7 @@ void vbg_put_gdev(struct vbg_dev *gdev)
 }
 EXPORT_SYMBOL(vbg_put_gdev);
 
-/**
+/*
  * Callback for mouse events.
  *
  * This is called at the end of the ISR, after leaving the event spinlock, if
-- 
GitLab


From c9d98a562cafb6306c18e2544048ba909235d0ec Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 21 Dec 2023 21:25:21 -0800
Subject: [PATCH 1880/4076] virt: vbox: utils: fix all kernel-doc warnings

Use kernel-doc format for functions that have comments that begin
with "/**".
This prevents 6 kernel-doc warnings.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231222052521.14333-3-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/vboxguest/vboxguest_utils.c | 33 +++++++++++++++---------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c
index 8d195e3f83012..1c02b3c0d9347 100644
--- a/drivers/virt/vboxguest/vboxguest_utils.c
+++ b/drivers/virt/vboxguest/vboxguest_utils.c
@@ -237,14 +237,16 @@ static int hgcm_call_preprocess_linaddr(
 }
 
 /**
- * Preprocesses the HGCM call, validate parameters, alloc bounce buffers and
- * figure out how much extra storage we need for page lists.
- * Return: 0 or negative errno value.
+ * hgcm_call_preprocess - Preprocesses the HGCM call, validate parameters,
+ *	alloc bounce buffers and figure out how much extra storage we need for
+ *	page lists.
  * @src_parm:         Pointer to source function call parameters
  * @parm_count:       Number of function call parameters.
  * @bounce_bufs_ret:  Where to return the allocated bouncebuffer array
  * @extra:            Where to return the extra request space needed for
  *                    physical page lists.
+ *
+ * Return: %0 or negative errno value.
  */
 static int hgcm_call_preprocess(
 	const struct vmmdev_hgcm_function_parameter *src_parm,
@@ -301,10 +303,11 @@ static int hgcm_call_preprocess(
 }
 
 /**
- * Translates linear address types to page list direction flags.
+ * hgcm_call_linear_addr_type_to_pagelist_flags - Translates linear address
+ *	types to page list direction flags.
+ * @type:  The type.
  *
  * Return: page list flags.
- * @type:  The type.
  */
 static u32 hgcm_call_linear_addr_type_to_pagelist_flags(
 	enum vmmdev_hgcm_function_parameter_type type)
@@ -369,7 +372,8 @@ static void hgcm_call_init_linaddr(struct vmmdev_hgcm_call *call,
 }
 
 /**
- * Initializes the call request that we're sending to the host.
+ * hgcm_call_init_call - Initializes the call request that we're sending
+ *	to the host.
  * @call:            The call to initialize.
  * @client_id:       The client ID of the caller.
  * @function:        The function number of the function to call.
@@ -425,7 +429,9 @@ static void hgcm_call_init_call(
 }
 
 /**
- * Tries to cancel a pending HGCM call.
+ * hgcm_cancel_call - Tries to cancel a pending HGCM call.
+ * @gdev:        The VBoxGuest device extension.
+ * @call:        The call to cancel.
  *
  * Return: VBox status code
  */
@@ -459,13 +465,15 @@ static int hgcm_cancel_call(struct vbg_dev *gdev, struct vmmdev_hgcm_call *call)
 }
 
 /**
- * Performs the call and completion wait.
- * Return: 0 or negative errno value.
+ * vbg_hgcm_do_call - Performs the call and completion wait.
  * @gdev:        The VBoxGuest device extension.
  * @call:        The call to execute.
  * @timeout_ms:  Timeout in ms.
+ * @interruptible: whether this call is interruptible
  * @leak_it:     Where to return the leak it / free it, indicator.
  *               Cancellation fun.
+ *
+ * Return: %0 or negative errno value.
  */
 static int vbg_hgcm_do_call(struct vbg_dev *gdev, struct vmmdev_hgcm_call *call,
 			    u32 timeout_ms, bool interruptible, bool *leak_it)
@@ -545,13 +553,14 @@ static int vbg_hgcm_do_call(struct vbg_dev *gdev, struct vmmdev_hgcm_call *call,
 }
 
 /**
- * Copies the result of the call back to the caller info structure and user
- * buffers.
- * Return: 0 or negative errno value.
+ * hgcm_call_copy_back_result - Copies the result of the call back to
+ *	the caller info structure and user buffers.
  * @call:            HGCM call request.
  * @dst_parm:        Pointer to function call parameters destination.
  * @parm_count:      Number of function call parameters.
  * @bounce_bufs:     The bouncebuffer array.
+ *
+ * Return: %0 or negative errno value.
  */
 static int hgcm_call_copy_back_result(
 	const struct vmmdev_hgcm_call *call,
-- 
GitLab


From 60cb19b485a534a896431393a877d853bbe51b67 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:07 -0800
Subject: [PATCH 1881/4076] perf dwarf-aux: Factor out
 die_get_typename_from_type()

The die_get_typename_from_type() is to get the name of the given DIE in
C-style type name.

The difference from die_get_typename() is that it does not retrieve the
DW_AT_type and use the given DIE directly.  This will be used when users
know the type DIE already.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dwarf-aux.c | 38 ++++++++++++++++++++++++++-----------
 tools/perf/util/dwarf-aux.h |  3 +++
 2 files changed, 30 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index edd9e407bc74e..7aa5fee0da190 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1051,32 +1051,28 @@ Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 }
 
 /**
- * die_get_typename - Get the name of given variable DIE
- * @vr_die: a variable DIE
+ * die_get_typename_from_type - Get the name of given type DIE
+ * @type_die: a type DIE
  * @buf: a strbuf for result type name
  *
- * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * Get the name of @type_die and stores it to @buf. Return 0 if succeeded.
  * and Return -ENOENT if failed to find type name.
  * Note that the result will stores typedef name if possible, and stores
  * "*(function_type)" if the type is a function pointer.
  */
-int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
+int die_get_typename_from_type(Dwarf_Die *type_die, struct strbuf *buf)
 {
-	Dwarf_Die type;
 	int tag, ret;
 	const char *tmp = "";
 
-	if (__die_get_real_type(vr_die, &type) == NULL)
-		return -ENOENT;
-
-	tag = dwarf_tag(&type);
+	tag = dwarf_tag(type_die);
 	if (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
 		return strbuf_add(buf, "(function_type)", 15);
 	} else {
-		const char *name = dwarf_diename(&type);
+		const char *name = dwarf_diename(type_die);
 
 		if (tag == DW_TAG_union_type)
 			tmp = "union ";
@@ -1089,7 +1085,7 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 		/* Write a base name */
 		return strbuf_addf(buf, "%s%s", tmp, name ?: "");
 	}
-	ret = die_get_typename(&type, buf);
+	ret = die_get_typename(type_die, buf);
 	if (ret < 0) {
 		/* void pointer has no type attribute */
 		if (tag == DW_TAG_pointer_type && ret == -ENOENT)
@@ -1100,6 +1096,26 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 	return strbuf_addstr(buf, tmp);
 }
 
+/**
+ * die_get_typename - Get the name of given variable DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for result type name
+ *
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
+ * Note that the result will stores typedef name if possible, and stores
+ * "*(function_type)" if the type is a function pointer.
+ */
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
+{
+	Dwarf_Die type;
+
+	if (__die_get_real_type(vr_die, &type) == NULL)
+		return -ENOENT;
+
+	return die_get_typename_from_type(&type, buf);
+}
+
 /**
  * die_get_varname - Get the name and type of given variable DIE
  * @vr_die: a variable DIE
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 0ddf61fd3f8be..4e64caac6df83 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -116,6 +116,9 @@ Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
 Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 			   Dwarf_Die *die_mem);
 
+/* Get the name of given type DIE */
+int die_get_typename_from_type(Dwarf_Die *type_die, struct strbuf *buf);
+
 /* Get the name of given variable DIE */
 int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
-- 
GitLab


From 3eee606757ad82f32332a2da174aa032bfd9cc32 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:08 -0800
Subject: [PATCH 1882/4076] perf dwarf-regs: Add get_dwarf_regnum()

The get_dwarf_regnum() returns a DWARF register number from a register
name string according to the psABI.  Also add two pseudo encodings of
DWARF_REG_PC which is a register that are used by PC-relative addressing
and DWARF_REG_FB which is a frame base register.  They need to be
handled in a special way.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/util/dwarf-regs.c | 38 +++++++++++++++++++++++++++
 tools/perf/util/dwarf-regs.c          | 34 ++++++++++++++++++++++++
 tools/perf/util/include/dwarf-regs.h  | 19 ++++++++++++++
 3 files changed, 91 insertions(+)

diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index 5309348057108..399c4a0a29d8c 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -113,3 +113,41 @@ int regs_query_register_offset(const char *name)
 			return roff->offset;
 	return -EINVAL;
 }
+
+struct dwarf_regs_idx {
+	const char *name;
+	int idx;
+};
+
+static const struct dwarf_regs_idx x86_regidx_table[] = {
+	{ "rax", 0 }, { "eax", 0 }, { "ax", 0 }, { "al", 0 },
+	{ "rdx", 1 }, { "edx", 1 }, { "dx", 1 }, { "dl", 1 },
+	{ "rcx", 2 }, { "ecx", 2 }, { "cx", 2 }, { "cl", 2 },
+	{ "rbx", 3 }, { "edx", 3 }, { "bx", 3 }, { "bl", 3 },
+	{ "rsi", 4 }, { "esi", 4 }, { "si", 4 }, { "sil", 4 },
+	{ "rdi", 5 }, { "edi", 5 }, { "di", 5 }, { "dil", 5 },
+	{ "rbp", 6 }, { "ebp", 6 }, { "bp", 6 }, { "bpl", 6 },
+	{ "rsp", 7 }, { "esp", 7 }, { "sp", 7 }, { "spl", 7 },
+	{ "r8", 8 }, { "r8d", 8 }, { "r8w", 8 }, { "r8b", 8 },
+	{ "r9", 9 }, { "r9d", 9 }, { "r9w", 9 }, { "r9b", 9 },
+	{ "r10", 10 }, { "r10d", 10 }, { "r10w", 10 }, { "r10b", 10 },
+	{ "r11", 11 }, { "r11d", 11 }, { "r11w", 11 }, { "r11b", 11 },
+	{ "r12", 12 }, { "r12d", 12 }, { "r12w", 12 }, { "r12b", 12 },
+	{ "r13", 13 }, { "r13d", 13 }, { "r13w", 13 }, { "r13b", 13 },
+	{ "r14", 14 }, { "r14d", 14 }, { "r14w", 14 }, { "r14b", 14 },
+	{ "r15", 15 }, { "r15d", 15 }, { "r15w", 15 }, { "r15b", 15 },
+	{ "rip", DWARF_REG_PC },
+};
+
+int get_arch_regnum(const char *name)
+{
+	unsigned int i;
+
+	if (*name != '%')
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(x86_regidx_table); i++)
+		if (!strcmp(x86_regidx_table[i].name, name + 1))
+			return x86_regidx_table[i].idx;
+	return -ENOENT;
+}
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 69cfaa5953bf4..5b7f86c0063f2 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -5,9 +5,12 @@
  * Written by: Masami Hiramatsu <mhiramat@kernel.org>
  */
 
+#include <stdlib.h>
+#include <string.h>
 #include <debug.h>
 #include <dwarf-regs.h>
 #include <elf.h>
+#include <errno.h>
 #include <linux/kernel.h>
 
 #ifndef EM_AARCH64
@@ -68,3 +71,34 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine)
 	}
 	return NULL;
 }
+
+__weak int get_arch_regnum(const char *name __maybe_unused)
+{
+	return -ENOTSUP;
+}
+
+/* Return DWARF register number from architecture register name */
+int get_dwarf_regnum(const char *name, unsigned int machine)
+{
+	char *regname = strdup(name);
+	int reg = -1;
+	char *p;
+
+	if (regname == NULL)
+		return -EINVAL;
+
+	/* For convenience, remove trailing characters */
+	p = strpbrk(regname, " ,)");
+	if (p)
+		*p = '\0';
+
+	switch (machine) {
+	case EM_NONE:	/* Generic arch - use host arch */
+		reg = get_arch_regnum(regname);
+		break;
+	default:
+		pr_err("ELF MACHINE %x is not supported.\n", machine);
+	}
+	free(regname);
+	return reg;
+}
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 7d99a084e82d7..01fb25a1150af 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -2,6 +2,9 @@
 #ifndef _PERF_DWARF_REGS_H_
 #define _PERF_DWARF_REGS_H_
 
+#define DWARF_REG_PC  0xd3af9c /* random number */
+#define DWARF_REG_FB  0xd3affb /* random number */
+
 #ifdef HAVE_DWARF_SUPPORT
 const char *get_arch_regstr(unsigned int n);
 /*
@@ -10,6 +13,22 @@ const char *get_arch_regstr(unsigned int n);
  * machine: ELF machine signature (EM_*)
  */
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine);
+
+int get_arch_regnum(const char *name);
+/*
+ * get_dwarf_regnum - Returns DWARF regnum from register name
+ * name: architecture register name
+ * machine: ELF machine signature (EM_*)
+ */
+int get_dwarf_regnum(const char *name, unsigned int machine);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+static inline int get_dwarf_regnum(const char *name __maybe_unused,
+				   unsigned int machine __maybe_unused)
+{
+	return -1;
+}
 #endif
 
 #ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
-- 
GitLab


From b9c87f536c6f28c75ace8a014646faad00f0e1ec Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:09 -0800
Subject: [PATCH 1883/4076] perf annotate-data: Add find_data_type() to get
 type from memory access

The find_data_type() is to get a data type from the memory access at the
given address (IP) using a register and an offset.

It requires DWARF debug info in the DSO and searches the list of
variables and function parameters in the scope.

In a pseudo code, it does basically the following:

  find_data_type(dso, ip, reg, offset)
  {
      pc = map__rip_2objdump(ip);
      CU = dwarf_addrdie(dso->dwarf, pc);
      scopes = die_get_scopes(CU, pc);
      for_each_scope(S, scopes) {
          V = die_find_variable_by_reg(S, pc, reg);
          if (V && V.type == pointer_type) {
              T = die_get_real_type(V);
              if (offset < T.size)
                  return T;
          }
      }
      return NULL;
  }

Committer notes:

The 'size' variable in check_variable() is 64-bit, so use PRIu64 and
inttypes.h to debug it.

Ditto at find_data_type_die().

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build           |   1 +
 tools/perf/util/annotate-data.c | 164 ++++++++++++++++++++++++++++++++
 tools/perf/util/annotate-data.h |  40 ++++++++
 3 files changed, 205 insertions(+)
 create mode 100644 tools/perf/util/annotate-data.c
 create mode 100644 tools/perf/util/annotate-data.h

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 132508ebe125c..8027f450fa3e4 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -196,6 +196,7 @@ perf-$(CONFIG_DWARF) += probe-finder.o
 perf-$(CONFIG_DWARF) += dwarf-aux.o
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 perf-$(CONFIG_DWARF) += debuginfo.o
+perf-$(CONFIG_DWARF) += annotate-data.o
 
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
new file mode 100644
index 0000000000000..9739ecc841eeb
--- /dev/null
+++ b/tools/perf/util/annotate-data.c
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Convert sample address to data type using DWARF debug info.
+ *
+ * Written by Namhyung Kim <namhyung@kernel.org>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <inttypes.h>
+
+#include "annotate-data.h"
+#include "debuginfo.h"
+#include "debug.h"
+#include "dso.h"
+#include "map.h"
+#include "map_symbol.h"
+#include "strbuf.h"
+#include "symbol.h"
+
+static bool find_cu_die(struct debuginfo *di, u64 pc, Dwarf_Die *cu_die)
+{
+	Dwarf_Off off, next_off;
+	size_t header_size;
+
+	if (dwarf_addrdie(di->dbg, pc, cu_die) != NULL)
+		return cu_die;
+
+	/*
+	 * There are some kernels don't have full aranges and contain only a few
+	 * aranges entries.  Fallback to iterate all CU entries in .debug_info
+	 * in case it's missing.
+	 */
+	off = 0;
+	while (dwarf_nextcu(di->dbg, off, &next_off, &header_size,
+			    NULL, NULL, NULL) == 0) {
+		if (dwarf_offdie(di->dbg, off + header_size, cu_die) &&
+		    dwarf_haspc(cu_die, pc))
+			return true;
+
+		off = next_off;
+	}
+	return false;
+}
+
+/* The type info will be saved in @type_die */
+static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset)
+{
+	Dwarf_Word size;
+
+	/* Get the type of the variable */
+	if (die_get_real_type(var_die, type_die) == NULL) {
+		pr_debug("variable has no type\n");
+		return -1;
+	}
+
+	/*
+	 * It expects a pointer type for a memory access.
+	 * Convert to a real type it points to.
+	 */
+	if (dwarf_tag(type_die) != DW_TAG_pointer_type ||
+	    die_get_real_type(type_die, type_die) == NULL) {
+		pr_debug("no pointer or no type\n");
+		return -1;
+	}
+
+	/* Get the size of the actual type */
+	if (dwarf_aggregate_size(type_die, &size) < 0) {
+		pr_debug("type size is unknown\n");
+		return -1;
+	}
+
+	/* Minimal sanity check */
+	if ((unsigned)offset >= size) {
+		pr_debug("offset: %d is bigger than size: %" PRIu64 "\n", offset, size);
+		return -1;
+	}
+
+	return 0;
+}
+
+/* The result will be saved in @type_die */
+static int find_data_type_die(struct debuginfo *di, u64 pc,
+			      int reg, int offset, Dwarf_Die *type_die)
+{
+	Dwarf_Die cu_die, var_die;
+	Dwarf_Die *scopes = NULL;
+	int ret = -1;
+	int i, nr_scopes;
+
+	/* Get a compile_unit for this address */
+	if (!find_cu_die(di, pc, &cu_die)) {
+		pr_debug("cannot find CU for address %" PRIx64 "\n", pc);
+		return -1;
+	}
+
+	/* Get a list of nested scopes - i.e. (inlined) functions and blocks. */
+	nr_scopes = die_get_scopes(&cu_die, pc, &scopes);
+
+	/* Search from the inner-most scope to the outer */
+	for (i = nr_scopes - 1; i >= 0; i--) {
+		/* Look up variables/parameters in this scope */
+		if (!die_find_variable_by_reg(&scopes[i], pc, reg, &var_die))
+			continue;
+
+		/* Found a variable, see if it's correct */
+		ret = check_variable(&var_die, type_die, offset);
+		break;
+	}
+
+	free(scopes);
+	return ret;
+}
+
+/**
+ * find_data_type - Return a data type at the location
+ * @ms: map and symbol at the location
+ * @ip: instruction address of the memory access
+ * @reg: register that holds the base address
+ * @offset: offset from the base address
+ *
+ * This functions searches the debug information of the binary to get the data
+ * type it accesses.  The exact location is expressed by (ip, reg, offset).
+ * It return %NULL if not found.
+ */
+struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
+					   int reg, int offset)
+{
+	struct annotated_data_type *result = NULL;
+	struct dso *dso = map__dso(ms->map);
+	struct debuginfo *di;
+	Dwarf_Die type_die;
+	struct strbuf sb;
+	u64 pc;
+
+	di = debuginfo__new(dso->long_name);
+	if (di == NULL) {
+		pr_debug("cannot get the debug info\n");
+		return NULL;
+	}
+
+	/*
+	 * IP is a relative instruction address from the start of the map, as
+	 * it can be randomized/relocated, it needs to translate to PC which is
+	 * a file address for DWARF processing.
+	 */
+	pc = map__rip_2objdump(ms->map, ip);
+	if (find_data_type_die(di, pc, reg, offset, &type_die) < 0)
+		goto out;
+
+	result = zalloc(sizeof(*result));
+	if (result == NULL)
+		goto out;
+
+	strbuf_init(&sb, 32);
+	if (die_get_typename_from_type(&type_die, &sb) < 0)
+		strbuf_add(&sb, "(unknown type)", 14);
+
+	result->type_name = strbuf_detach(&sb, NULL);
+
+out:
+	debuginfo__delete(di);
+	return result;
+}
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
new file mode 100644
index 0000000000000..633147f78ca5e
--- /dev/null
+++ b/tools/perf/util/annotate-data.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PERF_ANNOTATE_DATA_H
+#define _PERF_ANNOTATE_DATA_H
+
+#include <errno.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct map_symbol;
+
+/**
+ * struct annotated_data_type - Data type to profile
+ * @type_name: Name of the data type
+ * @type_size: Size of the data type
+ *
+ * This represents a data type accessed by samples in the profile data.
+ */
+struct annotated_data_type {
+	char *type_name;
+	int type_size;
+};
+
+#ifdef HAVE_DWARF_SUPPORT
+
+/* Returns data type at the location (ip, reg, offset) */
+struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
+					   int reg, int offset);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+static inline struct annotated_data_type *
+find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
+	       int reg __maybe_unused, int offset __maybe_unused)
+{
+	return NULL;
+}
+
+#endif /* HAVE_DWARF_SUPPORT */
+
+#endif /* _PERF_ANNOTATE_DATA_H */
-- 
GitLab


From fc044c53b99fad039ac30b95b289992ebf7dd6b4 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:10 -0800
Subject: [PATCH 1884/4076] perf annotate-data: Add dso->data_types tree

To aggregate accesses to the same data type, add 'data_types' tree in
DSO to maintain data types and find it by name and size.

It might have different data types that happen to have the same name,
so it also compares the size of the type.

Even if it doesn't 100% guarantee, it reduces the possibility of
mis-handling of such conflicts.

And I don't think it's common to have different types with the same
name.

Committer notes:

Very few cases on the Linux kernel, but there are some different types
with the same name, unsure if there is a debug mode in libbpf dedup that
warns about such cases, but there are provisions in pahole for that,
see:

  "emit: Notice type shadowing, i.e. multiple types with the same name (enum, struct, union, etc)"
    https://git.kernel.org/pub/scm/devel/pahole/pahole.git/commit/?id=4f332dbfd02072e4f410db7bdcda8d6e3422974b

  $ pahole --compile > vmlinux.h
  $ rm -f a ; make a
  cc     a.c   -o a
  $ grep __[0-9] vmlinux.h
  union irte__1 {
  struct map_info__1;
  struct map_info__1 {
  	struct map_info__1 *       next;                 /*     0     8 */
  $

  drivers/iommu/amd/amd_iommu_types.h 'union irte'
  include/linux/dmar.h                'struct irte'

  include/linux/device-mapper.h:

    union map_info {
            void *ptr;
    };

  include/linux/mtd/map.h:

    struct map_info {
        const char *name;
        unsigned long size;
        resource_size_t phys;
   <SNIP>

  kernel/events/uprobes.c:

   struct map_info {
        struct map_info *next;
        struct mm_struct *mm;
        unsigned long vaddr;
  };

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate-data.c | 95 +++++++++++++++++++++++++++++----
 tools/perf/util/annotate-data.h |  9 ++++
 tools/perf/util/dso.c           |  4 ++
 tools/perf/util/dso.h           |  2 +
 4 files changed, 100 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 9739ecc841eeb..1f921971174d2 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -18,6 +18,76 @@
 #include "strbuf.h"
 #include "symbol.h"
 
+/*
+ * Compare type name and size to maintain them in a tree.
+ * I'm not sure if DWARF would have information of a single type in many
+ * different places (compilation units).  If not, it could compare the
+ * offset of the type entry in the .debug_info section.
+ */
+static int data_type_cmp(const void *_key, const struct rb_node *node)
+{
+	const struct annotated_data_type *key = _key;
+	struct annotated_data_type *type;
+
+	type = rb_entry(node, struct annotated_data_type, node);
+
+	if (key->type_size != type->type_size)
+		return key->type_size - type->type_size;
+	return strcmp(key->type_name, type->type_name);
+}
+
+static bool data_type_less(struct rb_node *node_a, const struct rb_node *node_b)
+{
+	struct annotated_data_type *a, *b;
+
+	a = rb_entry(node_a, struct annotated_data_type, node);
+	b = rb_entry(node_b, struct annotated_data_type, node);
+
+	if (a->type_size != b->type_size)
+		return a->type_size < b->type_size;
+	return strcmp(a->type_name, b->type_name) < 0;
+}
+
+static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
+							  Dwarf_Die *type_die)
+{
+	struct annotated_data_type *result = NULL;
+	struct annotated_data_type key;
+	struct rb_node *node;
+	struct strbuf sb;
+	char *type_name;
+	Dwarf_Word size;
+
+	strbuf_init(&sb, 32);
+	if (die_get_typename_from_type(type_die, &sb) < 0)
+		strbuf_add(&sb, "(unknown type)", 14);
+	type_name = strbuf_detach(&sb, NULL);
+	dwarf_aggregate_size(type_die, &size);
+
+	/* Check existing nodes in dso->data_types tree */
+	key.type_name = type_name;
+	key.type_size = size;
+	node = rb_find(&key, &dso->data_types, data_type_cmp);
+	if (node) {
+		result = rb_entry(node, struct annotated_data_type, node);
+		free(type_name);
+		return result;
+	}
+
+	/* If not, add a new one */
+	result = zalloc(sizeof(*result));
+	if (result == NULL) {
+		free(type_name);
+		return NULL;
+	}
+
+	result->type_name = type_name;
+	result->type_size = size;
+
+	rb_add(&result->node, &dso->data_types, data_type_less);
+	return result;
+}
+
 static bool find_cu_die(struct debuginfo *di, u64 pc, Dwarf_Die *cu_die)
 {
 	Dwarf_Off off, next_off;
@@ -130,7 +200,6 @@ struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
 	struct dso *dso = map__dso(ms->map);
 	struct debuginfo *di;
 	Dwarf_Die type_die;
-	struct strbuf sb;
 	u64 pc;
 
 	di = debuginfo__new(dso->long_name);
@@ -148,17 +217,23 @@ struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
 	if (find_data_type_die(di, pc, reg, offset, &type_die) < 0)
 		goto out;
 
-	result = zalloc(sizeof(*result));
-	if (result == NULL)
-		goto out;
-
-	strbuf_init(&sb, 32);
-	if (die_get_typename_from_type(&type_die, &sb) < 0)
-		strbuf_add(&sb, "(unknown type)", 14);
-
-	result->type_name = strbuf_detach(&sb, NULL);
+	result = dso__findnew_data_type(dso, &type_die);
 
 out:
 	debuginfo__delete(di);
 	return result;
 }
+
+void annotated_data_type__tree_delete(struct rb_root *root)
+{
+	struct annotated_data_type *pos;
+
+	while (!RB_EMPTY_ROOT(root)) {
+		struct rb_node *node = rb_first(root);
+
+		rb_erase(node, root);
+		pos = rb_entry(node, struct annotated_data_type, node);
+		free(pos->type_name);
+		free(pos);
+	}
+}
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index 633147f78ca5e..ab9f187bd7f13 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -4,6 +4,7 @@
 
 #include <errno.h>
 #include <linux/compiler.h>
+#include <linux/rbtree.h>
 #include <linux/types.h>
 
 struct map_symbol;
@@ -16,6 +17,7 @@ struct map_symbol;
  * This represents a data type accessed by samples in the profile data.
  */
 struct annotated_data_type {
+	struct rb_node node;
 	char *type_name;
 	int type_size;
 };
@@ -26,6 +28,9 @@ struct annotated_data_type {
 struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
 					   int reg, int offset);
 
+/* Release all data type information in the tree */
+void annotated_data_type__tree_delete(struct rb_root *root);
+
 #else /* HAVE_DWARF_SUPPORT */
 
 static inline struct annotated_data_type *
@@ -35,6 +40,10 @@ find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
 	return NULL;
 }
 
+static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe_unused)
+{
+}
+
 #endif /* HAVE_DWARF_SUPPORT */
 
 #endif /* _PERF_ANNOTATE_DATA_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 1f629b6fb7cfe..22fd5fa806ed8 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -31,6 +31,7 @@
 #include "debug.h"
 #include "string2.h"
 #include "vdso.h"
+#include "annotate-data.h"
 
 static const char * const debuglink_paths[] = {
 	"%.0s%s",
@@ -1327,6 +1328,7 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
 		dso->data.cache = RB_ROOT;
 		dso->inlined_nodes = RB_ROOT_CACHED;
 		dso->srclines = RB_ROOT_CACHED;
+		dso->data_types = RB_ROOT;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1370,6 +1372,8 @@ void dso__delete(struct dso *dso)
 	symbols__delete(&dso->symbols);
 	dso->symbol_names_len = 0;
 	zfree(&dso->symbol_names);
+	annotated_data_type__tree_delete(&dso->data_types);
+
 	if (dso->short_name_allocated) {
 		zfree((char **)&dso->short_name);
 		dso->short_name_allocated = false;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 3759de8c2267a..ce9f3849a773c 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -154,6 +154,8 @@ struct dso {
 	size_t		 symbol_names_len;
 	struct rb_root_cached inlined_nodes;
 	struct rb_root_cached srclines;
+	struct rb_root	data_types;
+
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
-- 
GitLab


From 0669729eb0afb0cf55fe1b97d7a8b1315354910f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:11 -0800
Subject: [PATCH 1885/4076] perf annotate: Factor out evsel__get_arch()

The evsel__get_arch() is to get architecture info from the environment.

It'll be used by other places later so let's factor it out.

Also add arch__is() to check the arch info by name.

Committer notes:

"get" is usually associated with refcounting, so we better rename this
at some point to a better name.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 44 +++++++++++++++++++++++++++-----------
 tools/perf/util/annotate.h |  2 ++
 2 files changed, 33 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index c81fa0791918e..27b2a9961cd5e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -843,6 +843,11 @@ static struct arch *arch__find(const char *name)
 	return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
 }
 
+bool arch__is(struct arch *arch, const char *name)
+{
+	return !strcmp(arch->name, name);
+}
+
 static struct annotated_source *annotated_source__new(void)
 {
 	struct annotated_source *src = zalloc(sizeof(*src));
@@ -2378,15 +2383,8 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 	annotation__calc_percent(notes, evsel, symbol__size(sym));
 }
 
-int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
-		     struct arch **parch)
+static int evsel__get_arch(struct evsel *evsel, struct arch **parch)
 {
-	struct symbol *sym = ms->sym;
-	struct annotation *notes = symbol__annotation(sym);
-	struct annotate_args args = {
-		.evsel		= evsel,
-		.options	= &annotate_opts,
-	};
 	struct perf_env *env = evsel__env(evsel);
 	const char *arch_name = perf_env__arch(env);
 	struct arch *arch;
@@ -2395,23 +2393,43 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (!arch_name)
 		return errno;
 
-	args.arch = arch = arch__find(arch_name);
+	*parch = arch = arch__find(arch_name);
 	if (arch == NULL) {
 		pr_err("%s: unsupported arch %s\n", __func__, arch_name);
 		return ENOTSUP;
 	}
 
-	if (parch)
-		*parch = arch;
-
 	if (arch->init) {
 		err = arch->init(arch, env ? env->cpuid : NULL);
 		if (err) {
-			pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
+			pr_err("%s: failed to initialize %s arch priv area\n",
+			       __func__, arch->name);
 			return err;
 		}
 	}
+	return 0;
+}
+
+int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
+		     struct arch **parch)
+{
+	struct symbol *sym = ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct annotate_args args = {
+		.evsel		= evsel,
+		.options	= &annotate_opts,
+	};
+	struct arch *arch = NULL;
+	int err;
+
+	err = evsel__get_arch(evsel, &arch);
+	if (err < 0)
+		return err;
+
+	if (parch)
+		*parch = arch;
 
+	args.arch = arch;
 	args.ms = *ms;
 	if (annotate_opts.full_addr)
 		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 589f8aaf02366..2ef7e7dda7bdd 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -61,6 +61,8 @@ struct ins_operands {
 
 struct arch;
 
+bool arch__is(struct arch *arch, const char *name);
+
 struct ins_ops {
 	void (*free)(struct ins_operands *ops);
 	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
-- 
GitLab


From 3a0c26edc3d2f39da3a91eb6eae404253e7ccbaa Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:12 -0800
Subject: [PATCH 1886/4076] perf annotate: Add annotate_get_insn_location()

The annotate_get_insn_location() is to get the detailed information of
instruction locations like registers and offset.  It has source and
target operands locations in an array.  Each operand can have a register
and an offset.  The offset is meaningful when mem_ref flag is set.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-7-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 107 +++++++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.h |  36 +++++++++++++
 2 files changed, 143 insertions(+)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 27b2a9961cd5e..7c597440dc2eb 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -31,6 +31,7 @@
 #include "bpf-utils.h"
 #include "block-range.h"
 #include "string2.h"
+#include "dwarf-regs.h"
 #include "util/event.h"
 #include "util/sharded_mutex.h"
 #include "arch/common.h"
@@ -3518,3 +3519,109 @@ int annotate_check_args(void)
 	}
 	return 0;
 }
+
+/*
+ * Get register number and access offset from the given instruction.
+ * It assumes AT&T x86 asm format like OFFSET(REG).  Maybe it needs
+ * to revisit the format when it handles different architecture.
+ * Fills @reg and @offset when return 0.
+ */
+static int extract_reg_offset(struct arch *arch, const char *str,
+			      struct annotated_op_loc *op_loc)
+{
+	char *p;
+	char *regname;
+
+	if (arch->objdump.register_char == 0)
+		return -1;
+
+	/*
+	 * It should start from offset, but it's possible to skip 0
+	 * in the asm.  So 0(%rax) should be same as (%rax).
+	 *
+	 * However, it also start with a segment select register like
+	 * %gs:0x18(%rbx).  In that case it should skip the part.
+	 */
+	if (*str == arch->objdump.register_char) {
+		while (*str && !isdigit(*str) &&
+		       *str != arch->objdump.memory_ref_char)
+			str++;
+	}
+
+	op_loc->offset = strtol(str, &p, 0);
+
+	p = strchr(p, arch->objdump.register_char);
+	if (p == NULL)
+		return -1;
+
+	regname = strdup(p);
+	if (regname == NULL)
+		return -1;
+
+	op_loc->reg = get_dwarf_regnum(regname, 0);
+	free(regname);
+	return 0;
+}
+
+/**
+ * annotate_get_insn_location - Get location of instruction
+ * @arch: the architecture info
+ * @dl: the target instruction
+ * @loc: a buffer to save the data
+ *
+ * Get detailed location info (register and offset) in the instruction.
+ * It needs both source and target operand and whether it accesses a
+ * memory location.  The offset field is meaningful only when the
+ * corresponding mem flag is set.
+ *
+ * Some examples on x86:
+ *
+ *   mov  (%rax), %rcx   # src_reg = rax, src_mem = 1, src_offset = 0
+ *                       # dst_reg = rcx, dst_mem = 0
+ *
+ *   mov  0x18, %r8      # src_reg = -1, dst_reg = r8
+ */
+int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
+			       struct annotated_insn_loc *loc)
+{
+	struct ins_operands *ops;
+	struct annotated_op_loc *op_loc;
+	int i;
+
+	if (!strcmp(dl->ins.name, "lock"))
+		ops = dl->ops.locked.ops;
+	else
+		ops = &dl->ops;
+
+	if (ops == NULL)
+		return -1;
+
+	memset(loc, 0, sizeof(*loc));
+
+	for_each_insn_op_loc(loc, i, op_loc) {
+		const char *insn_str = ops->source.raw;
+
+		if (i == INSN_OP_TARGET)
+			insn_str = ops->target.raw;
+
+		/* Invalidate the register by default */
+		op_loc->reg = -1;
+
+		if (insn_str == NULL)
+			continue;
+
+		if (strchr(insn_str, arch->objdump.memory_ref_char)) {
+			op_loc->mem_ref = true;
+			extract_reg_offset(arch, insn_str, op_loc);
+		} else {
+			char *s = strdup(insn_str);
+
+			if (s) {
+				op_loc->reg = get_dwarf_regnum(s, 0);
+				free(s);
+			}
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 2ef7e7dda7bdd..25ae8893d4f9b 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -439,4 +439,40 @@ int annotate_parse_percent_type(const struct option *opt, const char *_str,
 
 int annotate_check_args(void);
 
+/**
+ * struct annotated_op_loc - Location info of instruction operand
+ * @reg: Register in the operand
+ * @offset: Memory access offset in the operand
+ * @mem_ref: Whether the operand accesses memory
+ */
+struct annotated_op_loc {
+	int reg;
+	int offset;
+	bool mem_ref;
+};
+
+enum annotated_insn_ops {
+	INSN_OP_SOURCE = 0,
+	INSN_OP_TARGET = 1,
+
+	INSN_OP_MAX,
+};
+
+/**
+ * struct annotated_insn_loc - Location info of instruction
+ * @ops: Array of location info for source and target operands
+ */
+struct annotated_insn_loc {
+	struct annotated_op_loc ops[INSN_OP_MAX];
+};
+
+#define for_each_insn_op_loc(insn_loc, i, op_loc)			\
+	for (i = INSN_OP_SOURCE, op_loc = &(insn_loc)->ops[i];		\
+	     i < INSN_OP_MAX;						\
+	     i++, op_loc++)
+
+/* Get detailed location info in the instruction */
+int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
+			       struct annotated_insn_loc *loc);
+
 #endif	/* __PERF_ANNOTATE_H */
-- 
GitLab


From 67bc54bbc5a25c0488cc488558a11c14c10f5f14 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:13 -0800
Subject: [PATCH 1887/4076] perf annotate: Implement
 hist_entry__get_data_type()

It's the function to find out the type info from the given sample data
and will be called from the hist_entry sort logic when 'type' sort key
is used.

It first calls objdump to disassemble the instructions and figure out
information about memory access at the location.  Maybe we can do it
better by analyzing the instruction directly, but I'll leave it for
later work.

The memory access is determined by checking instruction operands to
have "(" and then extract register name and offset.  It'll return NULL
if no data type is found.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-8-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 88 ++++++++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.h |  4 ++
 2 files changed, 92 insertions(+)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7c597440dc2eb..8673eac4b9df4 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -25,6 +25,7 @@
 #include "units.h"
 #include "debug.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "bpf-event.h"
@@ -3625,3 +3626,90 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 
 	return 0;
 }
+
+static void symbol__ensure_annotate(struct map_symbol *ms, struct evsel *evsel)
+{
+	struct disasm_line *dl, *tmp_dl;
+	struct annotation *notes;
+
+	notes = symbol__annotation(ms->sym);
+	if (!list_empty(&notes->src->source))
+		return;
+
+	if (symbol__annotate(ms, evsel, NULL) < 0)
+		return;
+
+	/* remove non-insn disasm lines for simplicity */
+	list_for_each_entry_safe(dl, tmp_dl, &notes->src->source, al.node) {
+		if (dl->al.offset == -1) {
+			list_del(&dl->al.node);
+			free(dl);
+		}
+	}
+}
+
+static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
+{
+	struct disasm_line *dl;
+	struct annotation *notes;
+
+	notes = symbol__annotation(sym);
+
+	list_for_each_entry(dl, &notes->src->source, al.node) {
+		if (sym->start + dl->al.offset == ip)
+			return dl;
+	}
+	return NULL;
+}
+
+/**
+ * hist_entry__get_data_type - find data type for given hist entry
+ * @he: hist entry
+ *
+ * This function first annotates the instruction at @he->ip and extracts
+ * register and offset info from it.  Then it searches the DWARF debug
+ * info to get a variable and type information using the address, register,
+ * and offset.
+ */
+struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
+{
+	struct map_symbol *ms = &he->ms;
+	struct evsel *evsel = hists_to_evsel(he->hists);
+	struct arch *arch;
+	struct disasm_line *dl;
+	struct annotated_insn_loc loc;
+	struct annotated_op_loc *op_loc;
+	u64 ip = he->ip;
+	int i;
+
+	if (ms->map == NULL || ms->sym == NULL)
+		return NULL;
+
+	if (!symbol_conf.init_annotation)
+		return NULL;
+
+	if (evsel__get_arch(evsel, &arch) < 0)
+		return NULL;
+
+	/* Make sure it runs objdump to get disasm of the function */
+	symbol__ensure_annotate(ms, evsel);
+
+	/*
+	 * Get a disasm to extract the location from the insn.
+	 * This is too slow...
+	 */
+	dl = find_disasm_line(ms->sym, ip);
+	if (dl == NULL)
+		return NULL;
+
+	if (annotate_get_insn_location(arch, dl, &loc) < 0)
+		return NULL;
+
+	for_each_insn_op_loc(&loc, i, op_loc) {
+		if (!op_loc->mem_ref)
+			continue;
+
+		return find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+	}
+	return NULL;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 25ae8893d4f9b..6c75b28322860 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -23,6 +23,7 @@ struct option;
 struct perf_sample;
 struct evsel;
 struct symbol;
+struct annotated_data_type;
 
 struct ins {
 	const char     *name;
@@ -475,4 +476,7 @@ struct annotated_insn_loc {
 int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 			       struct annotated_insn_loc *loc);
 
+/* Returns a data type from the sample instruction (if any) */
+struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he);
+
 #endif	/* __PERF_ANNOTATE_H */
-- 
GitLab


From 2f2c41bdd87f450a6a71c5d090d42c248ca4bf1e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:14 -0800
Subject: [PATCH 1888/4076] perf report: Add 'type' sort key

The 'type' sort key is to aggregate hist entries by data type they
access.  Add mem_type field to hist_entry struct to save the type.  If
hist_entry__get_data_type() returns NULL, it'd use the 'unknown_type'
instance.

Committer testing:

Before:

  # perf mem record  sleep 2s
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.037 MB perf.data (4 samples) ]
  root@number:/home/acme/Downloads# perf report --stdio -s type
  Error:
  Unknown --sort key: `type'
   Usage: perf report [<options>]

      -s, --sort <key[,key2...]>
                            sort by key(s): overhead overhead_sys overhead_us overhead_guest_sys
                            overhead_guest_us overhead_children sample period
                            pid comm dso symbol parent cpu socket srcline srcfile
                            local_weight weight transaction trace symbol_size
                            dso_size cgroup cgroup_id ipc_null time code_page_size
                            local_ins_lat ins_lat local_p_stage_cyc p_stage_cyc
                            addr local_retire_lat retire_lat simd dso_from dso_to
                            symbol_from symbol_to mispredict abort in_tx cycles
                            srcline_from srcline_to ipc_lbr addr_from addr_to
                            symbol_daddr dso_daddr locked tlb mem snoop dcacheline
                            symbol_iaddr phys_daddr data_page_size blocked
  #

After:

  # perf report --stdio -s type
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 4  of event 'cpu_atom/mem-loads,ldlat=30/P'
  # Event count (approx.): 7
  #
  # Overhead  Data Type
  # ........  .........
  #
     100.00%  (unknown)

  #
  # (Tip: Print event counts in CSV format with: perf stat -x,)
  #
  # rpm -q kernel-debuginfo
  kernel-debuginfo-6.6.4-200.fc39.x86_64
  # uname -r
  6.6.4-200.fc39.x86_64
  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org>
Cc: linux-trace-devel@vger.kernel.org>
Link: https://lore.kernel.org/r/20231213001323.718046-9-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-report.txt |  1 +
 tools/perf/util/annotate-data.h          |  2 +
 tools/perf/util/hist.h                   |  1 +
 tools/perf/util/sort.c                   | 69 +++++++++++++++++++++++-
 tools/perf/util/sort.h                   |  4 ++
 5 files changed, 75 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index af068b4f1e5a6..aec34417090b0 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -118,6 +118,7 @@ OPTIONS
 	- retire_lat: On X86, this reports pipeline stall of this instruction compared
 	  to the previous instruction in cycles. And currently supported only on X86
 	- simd: Flags describing a SIMD operation. "e" for empty Arm SVE predicate. "p" for partial Arm SVE predicate
+	- type: Data type of sample memory access.
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index ab9f187bd7f13..6efdd7e21b286 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -22,6 +22,8 @@ struct annotated_data_type {
 	int type_size;
 };
 
+extern struct annotated_data_type unknown_type;
+
 #ifdef HAVE_DWARF_SUPPORT
 
 /* Returns data type at the location (ip, reg, offset) */
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 5d0db96609dff..7ebbf427b1eac 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -82,6 +82,7 @@ enum hist_column {
 	HISTC_ADDR_TO,
 	HISTC_ADDR,
 	HISTC_SIMD,
+	HISTC_TYPE,
 	HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 27b123ccd2d15..e647f0117bb56 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -24,6 +24,7 @@
 #include "strbuf.h"
 #include "mem-events.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "event.h"
 #include "time-utils.h"
 #include "cgroup.h"
@@ -2094,7 +2095,7 @@ struct sort_entry sort_dso_size = {
 	.se_width_idx	= HISTC_DSO_SIZE,
 };
 
-/* --sort dso_size */
+/* --sort addr */
 
 static int64_t
 sort__addr_cmp(struct hist_entry *left, struct hist_entry *right)
@@ -2131,6 +2132,69 @@ struct sort_entry sort_addr = {
 	.se_width_idx	= HISTC_ADDR,
 };
 
+/* --sort type */
+
+struct annotated_data_type unknown_type = {
+	.type_name = (char *)"(unknown)",
+};
+
+static int64_t
+sort__type_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__addr_cmp(left, right);
+}
+
+static void sort__type_init(struct hist_entry *he)
+{
+	if (he->mem_type)
+		return;
+
+	he->mem_type = hist_entry__get_data_type(he);
+	if (he->mem_type == NULL)
+		he->mem_type = &unknown_type;
+}
+
+static int64_t
+sort__type_collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	struct annotated_data_type *left_type = left->mem_type;
+	struct annotated_data_type *right_type = right->mem_type;
+
+	if (!left_type) {
+		sort__type_init(left);
+		left_type = left->mem_type;
+	}
+
+	if (!right_type) {
+		sort__type_init(right);
+		right_type = right->mem_type;
+	}
+
+	return strcmp(left_type->type_name, right_type->type_name);
+}
+
+static int64_t
+sort__type_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__type_collapse(left, right);
+}
+
+static int hist_entry__type_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*s", width, he->mem_type->type_name);
+}
+
+struct sort_entry sort_type = {
+	.se_header	= "Data Type",
+	.se_cmp		= sort__type_cmp,
+	.se_collapse	= sort__type_collapse,
+	.se_sort	= sort__type_sort,
+	.se_init	= sort__type_init,
+	.se_snprintf	= hist_entry__type_snprintf,
+	.se_width_idx	= HISTC_TYPE,
+};
+
 
 struct sort_dimension {
 	const char		*name;
@@ -2185,7 +2249,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_ADDR, "addr", sort_addr),
 	DIM(SORT_LOCAL_RETIRE_LAT, "local_retire_lat", sort_local_p_stage_cyc),
 	DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc),
-	DIM(SORT_SIMD, "simd", sort_simd)
+	DIM(SORT_SIMD, "simd", sort_simd),
+	DIM(SORT_ANNOTATE_DATA_TYPE, "type", sort_type),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index ecfb7f1359d5e..aabf0b8331a35 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -15,6 +15,7 @@
 
 struct option;
 struct thread;
+struct annotated_data_type;
 
 extern regex_t parent_regex;
 extern const char *sort_order;
@@ -34,6 +35,7 @@ extern struct sort_entry sort_dso_to;
 extern struct sort_entry sort_sym_from;
 extern struct sort_entry sort_sym_to;
 extern struct sort_entry sort_srcline;
+extern struct sort_entry sort_type;
 extern const char default_mem_sort_order[];
 extern bool chk_double_cl;
 
@@ -154,6 +156,7 @@ struct hist_entry {
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
 	struct hist_entry_ops	*ops;
+	struct annotated_data_type *mem_type;
 	union {
 		/* this is for hierarchical entry structure */
 		struct {
@@ -243,6 +246,7 @@ enum sort_type {
 	SORT_LOCAL_RETIRE_LAT,
 	SORT_GLOBAL_RETIRE_LAT,
 	SORT_SIMD,
+	SORT_ANNOTATE_DATA_TYPE,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
-- 
GitLab


From 81e57deec32594b124d777b1d3ca8a1415410230 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:15 -0800
Subject: [PATCH 1889/4076] perf report: Support data type profiling

Enable type annotation when the 'type' sort key is used.

It shows type of variables the samples access at the moment.  Users can
see which types are accessed frequently.

  $ perf report -s dso,type --stdio
  ...
  # Overhead  Shared Object      Data Type
  # ........  .................  .........
  #
      35.47%  [kernel.kallsyms]  (unknown)
       1.62%  [kernel.kallsyms]  struct sched_entry
       1.23%  [kernel.kallsyms]  struct cfs_rq
       0.83%  [kernel.kallsyms]  struct task_struct
       0.34%  [kernel.kallsyms]  struct list_head
       0.30%  [kernel.kallsyms]  struct mem_cgroup
  ...

Committer testing:

With the perf.data file collected in the previous cset:

  # perf report --stdio -s type
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 4  of event 'cpu_atom/mem-loads,ldlat=30/P'
  # Event count (approx.): 7
  #
  # Overhead  Data Type
  # ........  .........
  #
      42.86%  struct list_head
      42.86%  (unknown)
      14.29%  char

  #
  # (Tip: To record callchains for each sample: perf record -g)
  #
  # perf report --stdio -s dso,type
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 4  of event 'cpu_atom/mem-loads,ldlat=30/P'
  # Event count (approx.): 7
  #
  # Overhead  Shared Object         Data Type
  # ........  ....................  .........
  #
      42.86%  [kernel.kallsyms]     struct list_head
      28.57%  libc.so.6             (unknown)
      14.29%  [kernel.kallsyms]     char
      14.29%  ld-linux-x86-64.so.2  (unknown)

  #
  # (Tip: Save output of perf stat using: perf stat record <target workload>)
  #
  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-10-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 178fb602bc982..f2ed2b7e80a32 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -96,6 +96,7 @@ struct report {
 	bool			stitch_lbr;
 	bool			disable_order;
 	bool			skip_empty;
+	bool			data_type;
 	int			max_stack;
 	struct perf_read_values	show_threads_values;
 	const char		*pretty_printing_style;
@@ -170,7 +171,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	struct mem_info *mi;
 	struct branch_info *bi;
 
-	if (!ui__has_annotation() && !rep->symbol_ipc)
+	if (!ui__has_annotation() && !rep->symbol_ipc && !rep->data_type)
 		return 0;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
@@ -1639,6 +1640,16 @@ repeat:
 			sort_order = NULL;
 	}
 
+	if (sort_order && strstr(sort_order, "type")) {
+		report.data_type = true;
+		annotate_opts.annotate_src = false;
+
+#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT
+		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
+		goto error;
+#endif
+	}
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
 	else
@@ -1697,7 +1708,7 @@ repeat:
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (ui__has_annotation() || report.symbol_ipc ||
+	if (ui__has_annotation() || report.symbol_ipc || report.data_type ||
 	    report.total_cycles_mode) {
 		ret = symbol__annotation_init();
 		if (ret < 0)
-- 
GitLab


From 4a111cadac85362ed9476737d7a36e8dd3a8e476 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:16 -0800
Subject: [PATCH 1890/4076] perf annotate-data: Add member field in the data
 type

Add child member field if the current type is a composite type like a
struct or union.  The member fields are linked in the children list and
do the same recursively if the child itself is a composite type.

Add 'self' member to the annotated_data_type to handle the members in
the same way.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-11-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate-data.c | 101 ++++++++++++++++++++++++++++----
 tools/perf/util/annotate-data.h |  27 +++++++--
 tools/perf/util/sort.c          |   9 ++-
 3 files changed, 119 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 1f921971174d2..5269c6630e045 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -31,9 +31,9 @@ static int data_type_cmp(const void *_key, const struct rb_node *node)
 
 	type = rb_entry(node, struct annotated_data_type, node);
 
-	if (key->type_size != type->type_size)
-		return key->type_size - type->type_size;
-	return strcmp(key->type_name, type->type_name);
+	if (key->self.size != type->self.size)
+		return key->self.size - type->self.size;
+	return strcmp(key->self.type_name, type->self.type_name);
 }
 
 static bool data_type_less(struct rb_node *node_a, const struct rb_node *node_b)
@@ -43,9 +43,80 @@ static bool data_type_less(struct rb_node *node_a, const struct rb_node *node_b)
 	a = rb_entry(node_a, struct annotated_data_type, node);
 	b = rb_entry(node_b, struct annotated_data_type, node);
 
-	if (a->type_size != b->type_size)
-		return a->type_size < b->type_size;
-	return strcmp(a->type_name, b->type_name) < 0;
+	if (a->self.size != b->self.size)
+		return a->self.size < b->self.size;
+	return strcmp(a->self.type_name, b->self.type_name) < 0;
+}
+
+/* Recursively add new members for struct/union */
+static int __add_member_cb(Dwarf_Die *die, void *arg)
+{
+	struct annotated_member *parent = arg;
+	struct annotated_member *member;
+	Dwarf_Die member_type, die_mem;
+	Dwarf_Word size, loc;
+	Dwarf_Attribute attr;
+	struct strbuf sb;
+	int tag;
+
+	if (dwarf_tag(die) != DW_TAG_member)
+		return DIE_FIND_CB_SIBLING;
+
+	member = zalloc(sizeof(*member));
+	if (member == NULL)
+		return DIE_FIND_CB_END;
+
+	strbuf_init(&sb, 32);
+	die_get_typename(die, &sb);
+
+	die_get_real_type(die, &member_type);
+	if (dwarf_aggregate_size(&member_type, &size) < 0)
+		size = 0;
+
+	if (!dwarf_attr_integrate(die, DW_AT_data_member_location, &attr))
+		loc = 0;
+	else
+		dwarf_formudata(&attr, &loc);
+
+	member->type_name = strbuf_detach(&sb, NULL);
+	/* member->var_name can be NULL */
+	if (dwarf_diename(die))
+		member->var_name = strdup(dwarf_diename(die));
+	member->size = size;
+	member->offset = loc + parent->offset;
+	INIT_LIST_HEAD(&member->children);
+	list_add_tail(&member->node, &parent->children);
+
+	tag = dwarf_tag(&member_type);
+	switch (tag) {
+	case DW_TAG_structure_type:
+	case DW_TAG_union_type:
+		die_find_child(&member_type, __add_member_cb, member, &die_mem);
+		break;
+	default:
+		break;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+static void add_member_types(struct annotated_data_type *parent, Dwarf_Die *type)
+{
+	Dwarf_Die die_mem;
+
+	die_find_child(type, __add_member_cb, &parent->self, &die_mem);
+}
+
+static void delete_members(struct annotated_member *member)
+{
+	struct annotated_member *child, *tmp;
+
+	list_for_each_entry_safe(child, tmp, &member->children, node) {
+		list_del(&child->node);
+		delete_members(child);
+		free(child->type_name);
+		free(child->var_name);
+		free(child);
+	}
 }
 
 static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
@@ -65,8 +136,8 @@ static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
 	dwarf_aggregate_size(type_die, &size);
 
 	/* Check existing nodes in dso->data_types tree */
-	key.type_name = type_name;
-	key.type_size = size;
+	key.self.type_name = type_name;
+	key.self.size = size;
 	node = rb_find(&key, &dso->data_types, data_type_cmp);
 	if (node) {
 		result = rb_entry(node, struct annotated_data_type, node);
@@ -81,8 +152,15 @@ static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
 		return NULL;
 	}
 
-	result->type_name = type_name;
-	result->type_size = size;
+	result->self.type_name = type_name;
+	result->self.size = size;
+	INIT_LIST_HEAD(&result->self.children);
+
+	/*
+	 * Fill member info unconditionally for now,
+	 * later perf annotate would need it.
+	 */
+	add_member_types(result, type_die);
 
 	rb_add(&result->node, &dso->data_types, data_type_less);
 	return result;
@@ -233,7 +311,8 @@ void annotated_data_type__tree_delete(struct rb_root *root)
 
 		rb_erase(node, root);
 		pos = rb_entry(node, struct annotated_data_type, node);
-		free(pos->type_name);
+		delete_members(&pos->self);
+		free(pos->self.type_name);
 		free(pos);
 	}
 }
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index 6efdd7e21b286..33748222e6aa4 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -9,17 +9,36 @@
 
 struct map_symbol;
 
+/**
+ * struct annotated_member - Type of member field
+ * @node: List entry in the parent list
+ * @children: List head for child nodes
+ * @type_name: Name of the member type
+ * @var_name: Name of the member variable
+ * @offset: Offset from the outer data type
+ * @size: Size of the member field
+ *
+ * This represents a member type in a data type.
+ */
+struct annotated_member {
+	struct list_head node;
+	struct list_head children;
+	char *type_name;
+	char *var_name;
+	int offset;
+	int size;
+};
+
 /**
  * struct annotated_data_type - Data type to profile
- * @type_name: Name of the data type
- * @type_size: Size of the data type
+ * @node: RB-tree node for dso->type_tree
+ * @self: Actual type information
  *
  * This represents a data type accessed by samples in the profile data.
  */
 struct annotated_data_type {
 	struct rb_node node;
-	char *type_name;
-	int type_size;
+	struct annotated_member self;
 };
 
 extern struct annotated_data_type unknown_type;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index e647f0117bb56..a41209e242ae4 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2135,7 +2135,10 @@ struct sort_entry sort_addr = {
 /* --sort type */
 
 struct annotated_data_type unknown_type = {
-	.type_name = (char *)"(unknown)",
+	.self = {
+		.type_name = (char *)"(unknown)",
+		.children = LIST_HEAD_INIT(unknown_type.self.children),
+	},
 };
 
 static int64_t
@@ -2170,7 +2173,7 @@ sort__type_collapse(struct hist_entry *left, struct hist_entry *right)
 		right_type = right->mem_type;
 	}
 
-	return strcmp(left_type->type_name, right_type->type_name);
+	return strcmp(left_type->self.type_name, right_type->self.type_name);
 }
 
 static int64_t
@@ -2182,7 +2185,7 @@ sort__type_sort(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__type_snprintf(struct hist_entry *he, char *bf,
 				     size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*s", width, he->mem_type->type_name);
+	return repsep_snprintf(bf, size, "%-*s", width, he->mem_type->self.type_name);
 }
 
 struct sort_entry sort_type = {
-- 
GitLab


From 9bd7ddd1576164fbb8d369c6a7b018af9544e202 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:17 -0800
Subject: [PATCH 1891/4076] perf annotate-data: Update sample histogram for
 type

The annotated_data_type__update_samples() to get histogram for data type
access.

It'll be called by perf annotate to show which fields in the data type
are accessed frequently.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-12-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate-data.c | 81 +++++++++++++++++++++++++++++++++
 tools/perf/util/annotate-data.h | 42 +++++++++++++++++
 tools/perf/util/annotate.c      |  9 +++-
 3 files changed, 131 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 5269c6630e045..868f52ccdb74c 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -13,6 +13,8 @@
 #include "debuginfo.h"
 #include "debug.h"
 #include "dso.h"
+#include "evsel.h"
+#include "evlist.h"
 #include "map.h"
 #include "map_symbol.h"
 #include "strbuf.h"
@@ -302,6 +304,44 @@ out:
 	return result;
 }
 
+static int alloc_data_type_histograms(struct annotated_data_type *adt, int nr_entries)
+{
+	int i;
+	size_t sz = sizeof(struct type_hist);
+
+	sz += sizeof(struct type_hist_entry) * adt->self.size;
+
+	/* Allocate a table of pointers for each event */
+	adt->nr_histograms = nr_entries;
+	adt->histograms = calloc(nr_entries, sizeof(*adt->histograms));
+	if (adt->histograms == NULL)
+		return -ENOMEM;
+
+	/*
+	 * Each histogram is allocated for the whole size of the type.
+	 * TODO: Probably we can move the histogram to members.
+	 */
+	for (i = 0; i < nr_entries; i++) {
+		adt->histograms[i] = zalloc(sz);
+		if (adt->histograms[i] == NULL)
+			goto err;
+	}
+	return 0;
+
+err:
+	while (--i >= 0)
+		free(adt->histograms[i]);
+	free(adt->histograms);
+	return -ENOMEM;
+}
+
+static void delete_data_type_histograms(struct annotated_data_type *adt)
+{
+	for (int i = 0; i < adt->nr_histograms; i++)
+		free(adt->histograms[i]);
+	free(adt->histograms);
+}
+
 void annotated_data_type__tree_delete(struct rb_root *root)
 {
 	struct annotated_data_type *pos;
@@ -312,7 +352,48 @@ void annotated_data_type__tree_delete(struct rb_root *root)
 		rb_erase(node, root);
 		pos = rb_entry(node, struct annotated_data_type, node);
 		delete_members(&pos->self);
+		delete_data_type_histograms(pos);
 		free(pos->self.type_name);
 		free(pos);
 	}
 }
+
+/**
+ * annotated_data_type__update_samples - Update histogram
+ * @adt: Data type to update
+ * @evsel: Event to update
+ * @offset: Offset in the type
+ * @nr_samples: Number of samples at this offset
+ * @period: Event count at this offset
+ *
+ * This function updates type histogram at @ofs for @evsel.  Samples are
+ * aggregated before calling this function so it can be called with more
+ * than one samples at a certain offset.
+ */
+int annotated_data_type__update_samples(struct annotated_data_type *adt,
+					struct evsel *evsel, int offset,
+					int nr_samples, u64 period)
+{
+	struct type_hist *h;
+
+	if (adt == NULL)
+		return 0;
+
+	if (adt->histograms == NULL) {
+		int nr = evsel->evlist->core.nr_entries;
+
+		if (alloc_data_type_histograms(adt, nr) < 0)
+			return -1;
+	}
+
+	if (offset < 0 || offset >= adt->self.size)
+		return -1;
+
+	h = adt->histograms[evsel->core.idx];
+
+	h->nr_samples += nr_samples;
+	h->addr[offset].nr_samples += nr_samples;
+	h->period += period;
+	h->addr[offset].period += period;
+	return 0;
+}
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index 33748222e6aa4..d2dc025b19345 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -7,6 +7,7 @@
 #include <linux/rbtree.h>
 #include <linux/types.h>
 
+struct evsel;
 struct map_symbol;
 
 /**
@@ -29,16 +30,42 @@ struct annotated_member {
 	int size;
 };
 
+/**
+ * struct type_hist_entry - Histogram entry per offset
+ * @nr_samples: Number of samples
+ * @period: Count of event
+ */
+struct type_hist_entry {
+	int nr_samples;
+	u64 period;
+};
+
+/**
+ * struct type_hist - Type histogram for each event
+ * @nr_samples: Total number of samples in this data type
+ * @period: Total count of the event in this data type
+ * @offset: Array of histogram entry
+ */
+struct type_hist {
+	u64			nr_samples;
+	u64			period;
+	struct type_hist_entry	addr[];
+};
+
 /**
  * struct annotated_data_type - Data type to profile
  * @node: RB-tree node for dso->type_tree
  * @self: Actual type information
+ * @nr_histogram: Number of histogram entries
+ * @histograms: An array of pointers to histograms
  *
  * This represents a data type accessed by samples in the profile data.
  */
 struct annotated_data_type {
 	struct rb_node node;
 	struct annotated_member self;
+	int nr_histograms;
+	struct type_hist **histograms;
 };
 
 extern struct annotated_data_type unknown_type;
@@ -49,6 +76,11 @@ extern struct annotated_data_type unknown_type;
 struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
 					   int reg, int offset);
 
+/* Update type access histogram at the given offset */
+int annotated_data_type__update_samples(struct annotated_data_type *adt,
+					struct evsel *evsel, int offset,
+					int nr_samples, u64 period);
+
 /* Release all data type information in the tree */
 void annotated_data_type__tree_delete(struct rb_root *root);
 
@@ -61,6 +93,16 @@ find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
 	return NULL;
 }
 
+static inline int
+annotated_data_type__update_samples(struct annotated_data_type *adt __maybe_unused,
+				    struct evsel *evsel __maybe_unused,
+				    int offset __maybe_unused,
+				    int nr_samples __maybe_unused,
+				    u64 period __maybe_unused)
+{
+	return -1;
+}
+
 static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe_unused)
 {
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 8673eac4b9df4..6747779ecef82 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -3679,6 +3679,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 	struct disasm_line *dl;
 	struct annotated_insn_loc loc;
 	struct annotated_op_loc *op_loc;
+	struct annotated_data_type *mem_type;
 	u64 ip = he->ip;
 	int i;
 
@@ -3709,7 +3710,13 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		if (!op_loc->mem_ref)
 			continue;
 
-		return find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+		mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+
+		annotated_data_type__update_samples(mem_type, evsel,
+						    op_loc->offset,
+						    he->stat.nr_events,
+						    he->stat.period);
+		return mem_type;
 	}
 	return NULL;
 }
-- 
GitLab


From 871304a79f755b2ab594bbd21857ecb4c4aa57c9 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:18 -0800
Subject: [PATCH 1892/4076] perf report: Add 'typeoff' sort key

The typeoff sort key shows the data type name, offset and the name of
the field.  This is useful to see which field in the struct is accessed
most frequently.

  $ perf report -s type,typeoff --hierarchy --stdio
  ...
  #     Overhead  Data Type / Data Type Offset
  # ............  ............................
  #
  ...
        1.23%     struct cfs_rq
           0.19%    struct cfs_rq +404 (throttle_count)
           0.19%    struct cfs_rq +0 (load.weight)
           0.19%    struct cfs_rq +336 (leaf_cfs_rq_list.next)
           0.09%    struct cfs_rq +272 (propagate)
           0.09%    struct cfs_rq +196 (removed.nr)
           0.09%    struct cfs_rq +80 (curr)
           0.09%    struct cfs_rq +544 (lt_b_children_throttled)
           0.06%    struct cfs_rq +320 (rq)

Committer testing:

Again with the perf.data from the previous csets:

  # perf report --stdio -s type,typeoff
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 4  of event 'cpu_atom/mem-loads,ldlat=30/P'
  # Event count (approx.): 7
  #
  # Overhead  Data Type  Data Type Offset
  # ........  .........  ................
  #
      42.86%  struct list_head  struct list_head +8 (prev)
      42.86%  (unknown)  (unknown) +0 (no field)
      14.29%  char       char +0 (no field)

  #
  # (Tip: To see callchains in a more compact form: perf report -g folded)
  #
  # perf report --stdio -s dso,type,typeoff
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 4  of event 'cpu_atom/mem-loads,ldlat=30/P'
  # Event count (approx.): 7
  #
  # Overhead  Shared Object         Data Type  Data Type Offset
  # ........  ....................  .........  ................
  #
      42.86%  [kernel.kallsyms]     struct list_head  struct list_head +8 (prev)
      28.57%  libc.so.6             (unknown)  (unknown) +0 (no field)
      14.29%  [kernel.kallsyms]     char       char +0 (no field)
      14.29%  ld-linux-x86-64.so.2  (unknown)  (unknown) +0 (no field)

  #
  # (Tip: If you have debuginfo enabled, try: perf report -s sym,srcline)
  #
  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-13-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-report.txt |  1 +
 tools/perf/util/annotate.c               |  1 +
 tools/perf/util/hist.h                   |  1 +
 tools/perf/util/sort.c                   | 83 +++++++++++++++++++++++-
 tools/perf/util/sort.h                   |  2 +
 5 files changed, 87 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index aec34417090b0..b57eb51b47aa6 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -119,6 +119,7 @@ OPTIONS
 	  to the previous instruction in cycles. And currently supported only on X86
 	- simd: Flags describing a SIMD operation. "e" for empty Arm SVE predicate. "p" for partial Arm SVE predicate
 	- type: Data type of sample memory access.
+	- typeoff: Offset in the data type of sample memory access.
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 6747779ecef82..f966e8f83c5ec 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -3716,6 +3716,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 						    op_loc->offset,
 						    he->stat.nr_events,
 						    he->stat.period);
+		he->mem_type_off = op_loc->offset;
 		return mem_type;
 	}
 	return NULL;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 7ebbf427b1eac..18128a49309ef 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -83,6 +83,7 @@ enum hist_column {
 	HISTC_ADDR,
 	HISTC_SIMD,
 	HISTC_TYPE,
+	HISTC_TYPE_OFFSET,
 	HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index a41209e242ae4..d78e680d39880 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2153,8 +2153,10 @@ static void sort__type_init(struct hist_entry *he)
 		return;
 
 	he->mem_type = hist_entry__get_data_type(he);
-	if (he->mem_type == NULL)
+	if (he->mem_type == NULL) {
 		he->mem_type = &unknown_type;
+		he->mem_type_off = 0;
+	}
 }
 
 static int64_t
@@ -2198,6 +2200,84 @@ struct sort_entry sort_type = {
 	.se_width_idx	= HISTC_TYPE,
 };
 
+/* --sort typeoff */
+
+static int64_t
+sort__typeoff_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	struct annotated_data_type *left_type = left->mem_type;
+	struct annotated_data_type *right_type = right->mem_type;
+	int64_t ret;
+
+	if (!left_type) {
+		sort__type_init(left);
+		left_type = left->mem_type;
+	}
+
+	if (!right_type) {
+		sort__type_init(right);
+		right_type = right->mem_type;
+	}
+
+	ret = strcmp(left_type->self.type_name, right_type->self.type_name);
+	if (ret)
+		return ret;
+	return left->mem_type_off - right->mem_type_off;
+}
+
+static void fill_member_name(char *buf, size_t sz, struct annotated_member *m,
+			     int offset, bool first)
+{
+	struct annotated_member *child;
+
+	if (list_empty(&m->children))
+		return;
+
+	list_for_each_entry(child, &m->children, node) {
+		if (child->offset <= offset && offset < child->offset + child->size) {
+			int len = 0;
+
+			/* It can have anonymous struct/union members */
+			if (child->var_name) {
+				len = scnprintf(buf, sz, "%s%s",
+						first ? "" : ".", child->var_name);
+				first = false;
+			}
+
+			fill_member_name(buf + len, sz - len, child, offset, first);
+			return;
+		}
+	}
+}
+
+static int hist_entry__typeoff_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width __maybe_unused)
+{
+	struct annotated_data_type *he_type = he->mem_type;
+	char buf[4096];
+
+	buf[0] = '\0';
+	if (list_empty(&he_type->self.children))
+		snprintf(buf, sizeof(buf), "no field");
+	else
+		fill_member_name(buf, sizeof(buf), &he_type->self,
+				 he->mem_type_off, true);
+	buf[4095] = '\0';
+
+	return repsep_snprintf(bf, size, "%s %+d (%s)", he_type->self.type_name,
+			       he->mem_type_off, buf);
+}
+
+struct sort_entry sort_type_offset = {
+	.se_header	= "Data Type Offset",
+	.se_cmp		= sort__type_cmp,
+	.se_collapse	= sort__typeoff_sort,
+	.se_sort	= sort__typeoff_sort,
+	.se_init	= sort__type_init,
+	.se_snprintf	= hist_entry__typeoff_snprintf,
+	.se_width_idx	= HISTC_TYPE_OFFSET,
+};
+
 
 struct sort_dimension {
 	const char		*name;
@@ -2254,6 +2334,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc),
 	DIM(SORT_SIMD, "simd", sort_simd),
 	DIM(SORT_ANNOTATE_DATA_TYPE, "type", sort_type),
+	DIM(SORT_ANNOTATE_DATA_TYPE_OFFSET, "typeoff", sort_type_offset),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index aabf0b8331a35..d806adcc1e1ea 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -113,6 +113,7 @@ struct hist_entry {
 	u64			p_stage_cyc;
 	u8			cpumode;
 	u8			depth;
+	int			mem_type_off;
 	struct simd_flags	simd_flags;
 
 	/* We are added by hists__add_dummy_entry. */
@@ -247,6 +248,7 @@ enum sort_type {
 	SORT_GLOBAL_RETIRE_LAT,
 	SORT_SIMD,
 	SORT_ANNOTATE_DATA_TYPE,
+	SORT_ANNOTATE_DATA_TYPE_OFFSET,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
-- 
GitLab


From e2c1c8ff2d2ffec340b8fc73ee13b8fb516d1c6d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:19 -0800
Subject: [PATCH 1893/4076] perf report: Add 'symoff' sort key

The symoff sort key is to print symbol and offset of sample.  This is
useful for data type profiling to show exact instruction in the function
which refers the data.

  $ perf report -s type,sym,typeoff,symoff --hierarchy
  ...
  #       Overhead  Data Type / Symbol / Data Type Offset / Symbol Offset
  # ..............  .....................................................
  #
      1.23%         struct cfs_rq
        0.84%         update_blocked_averages
          0.19%         struct cfs_rq +336 (leaf_cfs_rq_list.next)
             0.19%         [k] update_blocked_averages+0x96
          0.19%         struct cfs_rq +0 (load.weight)
             0.14%         [k] update_blocked_averages+0x104
             0.04%         [k] update_blocked_averages+0x31c
          0.17%         struct cfs_rq +404 (throttle_count)
             0.12%         [k] update_blocked_averages+0x9d
             0.05%         [k] update_blocked_averages+0x1f9
          0.08%         struct cfs_rq +272 (propagate)
             0.07%         [k] update_blocked_averages+0x3d3
             0.02%         [k] update_blocked_averages+0x45b
  ...

Committer testing:

  # perf report --stdio -s type,typeoff,symoff
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 4  of event 'cpu_atom/mem-loads,ldlat=30/P'
  # Event count (approx.): 7
  #
  # Overhead  Data Type  Data Type Offset  Symbol Offset
  # ........  .........  ................  .............
  #
      42.86%  struct list_head  struct list_head +8 (prev)  [k] __list_del_entry_valid_or_report+0x7
      28.57%  (unknown)  (unknown) +0 (no field)  [.] _nl_intern_locale_data+0x25
      14.29%  char       char +0 (no field)  [k] strncpy_from_user+0xa5
      14.29%  (unknown)  (unknown) +0 (no field)  [.] _dl_lookup_symbol_x+0x50

  #
  # (Tip: To change sampling frequency to 100 Hz: perf record -F 100)
  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-14-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-report.txt |  1 +
 tools/perf/util/hist.h                   |  1 +
 tools/perf/util/sort.c                   | 47 ++++++++++++++++++++++++
 tools/perf/util/sort.h                   |  1 +
 4 files changed, 50 insertions(+)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index b57eb51b47aa6..38f59ac064f7d 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -120,6 +120,7 @@ OPTIONS
 	- simd: Flags describing a SIMD operation. "e" for empty Arm SVE predicate. "p" for partial Arm SVE predicate
 	- type: Data type of sample memory access.
 	- typeoff: Offset in the data type of sample memory access.
+	- symoff: Offset in the symbol.
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 18128a49309ef..4a0aea0c9e00e 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -84,6 +84,7 @@ enum hist_column {
 	HISTC_SIMD,
 	HISTC_TYPE,
 	HISTC_TYPE_OFFSET,
+	HISTC_SYMBOL_OFFSET,
 	HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d78e680d39880..0cbbd5ba8175a 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -419,6 +419,52 @@ struct sort_entry sort_sym = {
 	.se_width_idx	= HISTC_SYMBOL,
 };
 
+/* --sort symoff */
+
+static int64_t
+sort__symoff_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = sort__sym_cmp(left, right);
+	if (ret)
+		return ret;
+
+	return left->ip - right->ip;
+}
+
+static int64_t
+sort__symoff_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = sort__sym_sort(left, right);
+	if (ret)
+		return ret;
+
+	return left->ip - right->ip;
+}
+
+static int
+hist_entry__symoff_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width)
+{
+	struct symbol *sym = he->ms.sym;
+
+	if (sym == NULL)
+		return repsep_snprintf(bf, size, "[%c] %-#.*llx", he->level, width - 4, he->ip);
+
+	return repsep_snprintf(bf, size, "[%c] %s+0x%llx", he->level, sym->name, he->ip - sym->start);
+}
+
+struct sort_entry sort_sym_offset = {
+	.se_header	= "Symbol Offset",
+	.se_cmp		= sort__symoff_cmp,
+	.se_sort	= sort__symoff_sort,
+	.se_snprintf	= hist_entry__symoff_snprintf,
+	.se_filter	= hist_entry__sym_filter,
+	.se_width_idx	= HISTC_SYMBOL_OFFSET,
+};
+
 /* --sort srcline */
 
 char *hist_entry__srcline(struct hist_entry *he)
@@ -2335,6 +2381,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_SIMD, "simd", sort_simd),
 	DIM(SORT_ANNOTATE_DATA_TYPE, "type", sort_type),
 	DIM(SORT_ANNOTATE_DATA_TYPE_OFFSET, "typeoff", sort_type_offset),
+	DIM(SORT_SYM_OFFSET, "symoff", sort_sym_offset),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index d806adcc1e1ea..6f6b4189a3897 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -249,6 +249,7 @@ enum sort_type {
 	SORT_SIMD,
 	SORT_ANNOTATE_DATA_TYPE,
 	SORT_ANNOTATE_DATA_TYPE_OFFSET,
+	SORT_SYM_OFFSET,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
-- 
GitLab


From 263925bf843f5ca8257317d74992f8e6b7d222e3 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:20 -0800
Subject: [PATCH 1894/4076] perf annotate: Add --data-type option

Support data type annotation with new --data-type option.  It internally
uses type sort key to collect sample histogram for the type and display
every members like below.

  $ perf annotate --data-type
  ...
  Annotate type: 'struct cfs_rq' in [kernel.kallsyms] (13 samples):
  ============================================================================
      samples     offset       size  field
           13          0        640  struct cfs_rq         {
            2          0         16      struct load_weight       load {
            2          0          8          unsigned long        weight;
            0          8          4          u32  inv_weight;
                                         };
            0         16          8      unsigned long    runnable_weight;
            0         24          4      unsigned int     nr_running;
            1         28          4      unsigned int     h_nr_running;
  ...

For simplicity it prints the number of samples per field for now.
But it should be easy to show the overhead percentage instead.

The number at the outer struct is a sum of the numbers of the inner
members.  For example, struct cfs_rq got total 13 samples, and 2 came
from the load (struct load_weight) and 1 from h_nr_running.  Similarly,
the struct load_weight got total 2 samples and they all came from the
weight field.

I've added two new flags in the symbol_conf for this.  The
annotate_data_member is to get the members of the type.  This is also
needed for perf report with typeoff sort key.  The annotate_data_sample
is to update sample stats for each offset and used only in annotate.

Currently it only support stdio output mode, TUI support can be added
later.

Committer testing:

With the perf.data from the previous csets, a very simple, short
duration one:

  # perf annotate --data-type
  Annotate type: 'struct list_head' in [kernel.kallsyms] (1 samples):
  ============================================================================
      samples     offset       size  field
            1          0         16  struct list_head      {
            0          0          8      struct list_head*        next;
            1          8          8      struct list_head*        prev;
                                     };

  Annotate type: 'char' in [kernel.kallsyms] (1 samples):
  ============================================================================
      samples     offset       size  field
            1          0          1  char ;

  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-15-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-annotate.txt |  8 ++
 tools/perf/builtin-annotate.c              | 97 +++++++++++++++++++++-
 tools/perf/util/annotate-data.c            |  8 +-
 tools/perf/util/annotate.c                 | 10 ++-
 tools/perf/util/sort.c                     |  2 +
 tools/perf/util/symbol_conf.h              |  4 +-
 6 files changed, 118 insertions(+), 11 deletions(-)

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index fe168e8165c8d..0e6a49b7795c5 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -155,6 +155,14 @@ include::itrace.txt[]
 	stdio or stdio2 (Default: 0).  Note that this is about selection of
 	functions to display, not about lines within the function.
 
+--data-type[=TYPE_NAME]::
+	Display data type annotation instead of code.  It infers data type of
+	samples (if they are memory accessing instructions) using DWARF debug
+	information.  It can take an optional argument of data type name.  In
+	that case it'd show annotation for the type only, otherwise it'd show
+	all data types it finds.
+
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index d880f1b039fdf..8acfbbc1b9c2d 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -20,6 +20,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/annotate.h"
+#include "util/annotate-data.h"
 #include "util/event.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
@@ -55,9 +56,11 @@ struct perf_annotate {
 	bool	   skip_missing;
 	bool	   has_br_stack;
 	bool	   group_set;
+	bool	   data_type;
 	float	   min_percent;
 	const char *sym_hist_filter;
 	const char *cpu_list;
+	const char *target_data_type;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
@@ -322,6 +325,32 @@ static int hist_entry__tty_annotate(struct hist_entry *he,
 	return symbol__tty_annotate2(&he->ms, evsel);
 }
 
+static void print_annotated_data_type(struct annotated_data_type *mem_type,
+				      struct annotated_member *member,
+				      struct evsel *evsel, int indent)
+{
+	struct annotated_member *child;
+	struct type_hist *h = mem_type->histograms[evsel->core.idx];
+	int i, samples = 0;
+
+	for (i = 0; i < member->size; i++)
+		samples += h->addr[member->offset + i].nr_samples;
+
+	printf(" %10d %10d %10d  %*s%s\t%s",
+	       samples, member->offset, member->size, indent, "", member->type_name,
+	       member->var_name ?: "");
+
+	if (!list_empty(&member->children))
+		printf(" {\n");
+
+	list_for_each_entry(child, &member->children, node)
+		print_annotated_data_type(mem_type, child, evsel, indent + 4);
+
+	if (!list_empty(&member->children))
+		printf("%*s}", 35 + indent, "");
+	printf(";\n");
+}
+
 static void hists__find_annotations(struct hists *hists,
 				    struct evsel *evsel,
 				    struct perf_annotate *ann)
@@ -361,6 +390,40 @@ find_next:
 			continue;
 		}
 
+		if (ann->data_type) {
+			struct dso *dso = map__dso(he->ms.map);
+
+			/* skip unknown type */
+			if (he->mem_type->histograms == NULL)
+				goto find_next;
+
+			if (ann->target_data_type) {
+				const char *type_name = he->mem_type->self.type_name;
+
+				/* skip 'struct ' prefix in the type name */
+				if (strncmp(ann->target_data_type, "struct ", 7) &&
+				    !strncmp(type_name, "struct ", 7))
+					type_name += 7;
+
+				/* skip 'union ' prefix in the type name */
+				if (strncmp(ann->target_data_type, "union ", 6) &&
+				    !strncmp(type_name, "union ", 6))
+					type_name += 6;
+
+				if (strcmp(ann->target_data_type, type_name))
+					goto find_next;
+			}
+
+			printf("Annotate type: '%s' in %s (%d samples):\n",
+				he->mem_type->self.type_name, dso->name, he->stat.nr_events);
+			printf("============================================================================\n");
+			printf(" %10s %10s %10s  %s\n", "samples", "offset", "size", "field");
+
+			print_annotated_data_type(he->mem_type, &he->mem_type->self, evsel, 0);
+			printf("\n");
+			goto find_next;
+		}
+
 		if (use_browser == 2) {
 			int ret;
 			int (*annotate)(struct hist_entry *he,
@@ -496,6 +559,17 @@ static int parse_percent_limit(const struct option *opt, const char *str,
 	return 0;
 }
 
+static int parse_data_type(const struct option *opt, const char *str, int unset)
+{
+	struct perf_annotate *ann = opt->value;
+
+	ann->data_type = !unset;
+	if (str)
+		ann->target_data_type = strdup(str);
+
+	return 0;
+}
+
 static const char * const annotate_usage[] = {
 	"perf annotate [<options>]",
 	NULL
@@ -607,6 +681,9 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
 			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
+	OPT_CALLBACK_OPTARG(0, "data-type", &annotate, NULL, "name",
+			    "Show data type annotate for the memory accesses",
+			    parse_data_type),
 
 	OPT_END()
 	};
@@ -661,6 +738,13 @@ int cmd_annotate(int argc, const char **argv)
 	}
 #endif
 
+#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT
+	if (annotate.data_type) {
+		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
+		return -ENOTSUP;
+	}
+#endif
+
 	ret = symbol__validate_sym_arguments();
 	if (ret)
 		return ret;
@@ -703,6 +787,14 @@ int cmd_annotate(int argc, const char **argv)
 		use_browser = 2;
 #endif
 
+	/* FIXME: only support stdio for now */
+	if (annotate.data_type) {
+		use_browser = 0;
+		annotate_opts.annotate_src = false;
+		symbol_conf.annotate_data_member = true;
+		symbol_conf.annotate_data_sample = true;
+	}
+
 	setup_browser(true);
 
 	/*
@@ -710,7 +802,10 @@ int cmd_annotate(int argc, const char **argv)
 	 * symbol, we do not care about the processes in annotate,
 	 * set sort order to avoid repeated output.
 	 */
-	sort_order = "dso,symbol";
+	if (annotate.data_type)
+		sort_order = "dso,type";
+	else
+		sort_order = "dso,symbol";
 
 	/*
 	 * Set SORT_MODE__BRANCH so that annotate display IPC/Cycle
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 868f52ccdb74c..df9689f46619c 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -19,6 +19,7 @@
 #include "map_symbol.h"
 #include "strbuf.h"
 #include "symbol.h"
+#include "symbol_conf.h"
 
 /*
  * Compare type name and size to maintain them in a tree.
@@ -158,11 +159,8 @@ static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
 	result->self.size = size;
 	INIT_LIST_HEAD(&result->self.children);
 
-	/*
-	 * Fill member info unconditionally for now,
-	 * later perf annotate would need it.
-	 */
-	add_member_types(result, type_die);
+	if (symbol_conf.annotate_data_member)
+		add_member_types(result, type_die);
 
 	rb_add(&result->node, &dso->data_types, data_type_less);
 	return result;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index f966e8f83c5ec..68424ee0215e4 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -3712,10 +3712,12 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 
 		mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
 
-		annotated_data_type__update_samples(mem_type, evsel,
-						    op_loc->offset,
-						    he->stat.nr_events,
-						    he->stat.period);
+		if (symbol_conf.annotate_data_sample) {
+			annotated_data_type__update_samples(mem_type, evsel,
+							    op_loc->offset,
+							    he->stat.nr_events,
+							    he->stat.period);
+		}
 		he->mem_type_off = op_loc->offset;
 		return mem_type;
 	}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 0cbbd5ba8175a..30254eb637099 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -3401,6 +3401,8 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			list->thread = 1;
 		} else if (sd->entry == &sort_comm) {
 			list->comm = 1;
+		} else if (sd->entry == &sort_type_offset) {
+			symbol_conf.annotate_data_member = true;
 		}
 
 		return __sort_dimension__add(sd, list, level);
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index 6040286e07a65..c114bbceef401 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -44,7 +44,9 @@ struct symbol_conf {
 			buildid_mmap2,
 			guest_code,
 			lazy_load_kernel_maps,
-			keep_exited_threads;
+			keep_exited_threads,
+			annotate_data_member,
+			annotate_data_sample;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
-- 
GitLab


From 227ad323854ab48d45966461d7a0a94e03f19368 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:21 -0800
Subject: [PATCH 1895/4076] perf annotate: Support event group display

When events are grouped together, it'd be natural to show them at once
like in other mode.  Handle group leaders with members to collect the
number of samples together and display like below:

  $ perf annotate --data-type --group
  ...
  Annotate type: 'struct page' in vmlinux (1 samples):
   event[0] = cpu/mem-loads,ldlat=30/P
   event[1] = cpu/mem-stores/P
   event[2] = dummy:u
  ============================================================================
                            samples     offset       size  field
            1          0          0          0         64  struct page     {
            0          0          0          0          8      long unsigned int  flags;
            0          0          0          8         40      union       {
            0          0          0          8         40          struct          {
            0          0          0          8         16              union       {
            0          0          0          8         16                  struct list_head       lru {
            0          0          0          8          8                      struct list_head*  next;
            0          0          0         16          8                      struct list_head*  prev;
                                                                           };
            0          0          0          8         16                  struct          {
            0          0          0          8          8                      void*      __filler;
            0          0          0         16          4                      unsigned int       mlock_count;
                                                                           };
            0          0          0          8         16                  struct list_head       buddy_list {
            0          0          0          8          8                      struct list_head*  next;
            0          0          0         16          8                      struct list_head*  prev;
                                                                           };

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-16-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c | 89 ++++++++++++++++++++++++++++++-----
 1 file changed, 77 insertions(+), 12 deletions(-)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 8acfbbc1b9c2d..3956ea1334cc5 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -325,19 +325,64 @@ static int hist_entry__tty_annotate(struct hist_entry *he,
 	return symbol__tty_annotate2(&he->ms, evsel);
 }
 
+static void print_annotated_data_header(struct hist_entry *he, struct evsel *evsel)
+{
+	struct dso *dso = map__dso(he->ms.map);
+	int nr_members = 1;
+	int nr_samples = he->stat.nr_events;
+
+	if (evsel__is_group_event(evsel)) {
+		struct hist_entry *pair;
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node)
+			nr_samples += pair->stat.nr_events;
+	}
+
+	printf("Annotate type: '%s' in %s (%d samples):\n",
+	       he->mem_type->self.type_name, dso->name, nr_samples);
+
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+		int i = 0;
+
+		for_each_group_evsel(pos, evsel)
+			printf(" event[%d] = %s\n", i++, pos->name);
+
+		nr_members = evsel->core.nr_members;
+	}
+
+	printf("============================================================================\n");
+	printf("%*s %10s %10s  %s\n", 11 * nr_members, "samples", "offset", "size", "field");
+}
+
 static void print_annotated_data_type(struct annotated_data_type *mem_type,
 				      struct annotated_member *member,
 				      struct evsel *evsel, int indent)
 {
 	struct annotated_member *child;
 	struct type_hist *h = mem_type->histograms[evsel->core.idx];
-	int i, samples = 0;
+	int i, nr_events = 1, samples = 0;
 
 	for (i = 0; i < member->size; i++)
 		samples += h->addr[member->offset + i].nr_samples;
+	printf(" %10d", samples);
+
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+
+		for_each_group_member(pos, evsel) {
+			h = mem_type->histograms[pos->core.idx];
+
+			samples = 0;
+			for (i = 0; i < member->size; i++)
+				samples += h->addr[member->offset + i].nr_samples;
+			printf(" %10d", samples);
+		}
+		nr_events = evsel->core.nr_members;
+	}
 
-	printf(" %10d %10d %10d  %*s%s\t%s",
-	       samples, member->offset, member->size, indent, "", member->type_name,
+	printf(" %10d %10d  %*s%s\t%s",
+	       member->offset, member->size, indent, "", member->type_name,
 	       member->var_name ?: "");
 
 	if (!list_empty(&member->children))
@@ -347,7 +392,7 @@ static void print_annotated_data_type(struct annotated_data_type *mem_type,
 		print_annotated_data_type(mem_type, child, evsel, indent + 4);
 
 	if (!list_empty(&member->children))
-		printf("%*s}", 35 + indent, "");
+		printf("%*s}", 11 * nr_events + 24 + indent, "");
 	printf(";\n");
 }
 
@@ -391,8 +436,6 @@ find_next:
 		}
 
 		if (ann->data_type) {
-			struct dso *dso = map__dso(he->ms.map);
-
 			/* skip unknown type */
 			if (he->mem_type->histograms == NULL)
 				goto find_next;
@@ -414,11 +457,7 @@ find_next:
 					goto find_next;
 			}
 
-			printf("Annotate type: '%s' in %s (%d samples):\n",
-				he->mem_type->self.type_name, dso->name, he->stat.nr_events);
-			printf("============================================================================\n");
-			printf(" %10s %10s %10s  %s\n", "samples", "offset", "size", "field");
-
+			print_annotated_data_header(he, evsel);
 			print_annotated_data_type(he->mem_type, &he->mem_type->self, evsel, 0);
 			printf("\n");
 			goto find_next;
@@ -521,8 +560,20 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			evsel__reset_sample_bit(pos, CALLCHAIN);
 			evsel__output_resort(pos, NULL);
 
-			if (symbol_conf.event_group && !evsel__is_group_leader(pos))
+			/*
+			 * An event group needs to display other events too.
+			 * Let's delay printing until other events are processed.
+			 */
+			if (symbol_conf.event_group) {
+				if (!evsel__is_group_leader(pos)) {
+					struct hists *leader_hists;
+
+					leader_hists = evsel__hists(evsel__leader(pos));
+					hists__match(leader_hists, hists);
+					hists__link(leader_hists, hists);
+				}
 				continue;
+			}
 
 			hists__find_annotations(hists, pos, ann);
 		}
@@ -533,6 +584,20 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		goto out;
 	}
 
+	/* Display group events together */
+	evlist__for_each_entry(session->evlist, pos) {
+		struct hists *hists = evsel__hists(pos);
+		u32 nr_samples = hists->stats.nr_samples;
+
+		if (nr_samples == 0)
+			continue;
+
+		if (!symbol_conf.event_group || !evsel__is_group_leader(pos))
+			continue;
+
+		hists__find_annotations(hists, pos, ann);
+	}
+
 	if (use_browser == 2) {
 		void (*show_annotations)(void);
 
-- 
GitLab


From 61a9741e9f78c64c5178e4ae9d405eeceff04c8f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:22 -0800
Subject: [PATCH 1896/4076] perf annotate: Add --type-stat option for debugging

The --type-stat option is to be used with --data-type and to print
detailed failure reasons for the data type annotation.

  $ perf annotate --data-type --type-stat
  Annotate data type stats:
  total 294, ok 116 (39.5%), bad 178 (60.5%)
  -----------------------------------------------------------
          30 : no_sym
          40 : no_insn_ops
          33 : no_mem_ops
          63 : no_var
           4 : no_typeinfo
           8 : bad_offset

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-17-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-annotate.txt |  3 ++
 tools/perf/builtin-annotate.c              | 44 +++++++++++++++++++++-
 tools/perf/util/annotate-data.c            | 10 ++++-
 tools/perf/util/annotate-data.h            | 31 +++++++++++++++
 tools/perf/util/annotate.c                 | 27 ++++++++++---
 5 files changed, 108 insertions(+), 7 deletions(-)

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 0e6a49b7795c5..b95524bea021e 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -162,6 +162,9 @@ include::itrace.txt[]
 	that case it'd show annotation for the type only, otherwise it'd show
 	all data types it finds.
 
+--type-stat::
+	Show stats for the data type annotation.
+
 
 SEE ALSO
 --------
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 3956ea1334cc5..55f97ab1395ba 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -57,6 +57,7 @@ struct perf_annotate {
 	bool	   has_br_stack;
 	bool	   group_set;
 	bool	   data_type;
+	bool	   type_stat;
 	float	   min_percent;
 	const char *sym_hist_filter;
 	const char *cpu_list;
@@ -396,6 +397,43 @@ static void print_annotated_data_type(struct annotated_data_type *mem_type,
 	printf(";\n");
 }
 
+static void print_annotate_data_stat(struct annotated_data_stat *s)
+{
+#define PRINT_STAT(fld) if (s->fld) printf("%10d : %s\n", s->fld, #fld)
+
+	int bad = s->no_sym +
+			s->no_insn +
+			s->no_insn_ops +
+			s->no_mem_ops +
+			s->no_reg +
+			s->no_dbginfo +
+			s->no_cuinfo +
+			s->no_var +
+			s->no_typeinfo +
+			s->invalid_size +
+			s->bad_offset;
+	int ok = s->total - bad;
+
+	printf("Annotate data type stats:\n");
+	printf("total %d, ok %d (%.1f%%), bad %d (%.1f%%)\n",
+		s->total, ok, 100.0 * ok / (s->total ?: 1), bad, 100.0 * bad / (s->total ?: 1));
+	printf("-----------------------------------------------------------\n");
+	PRINT_STAT(no_sym);
+	PRINT_STAT(no_insn);
+	PRINT_STAT(no_insn_ops);
+	PRINT_STAT(no_mem_ops);
+	PRINT_STAT(no_reg);
+	PRINT_STAT(no_dbginfo);
+	PRINT_STAT(no_cuinfo);
+	PRINT_STAT(no_var);
+	PRINT_STAT(no_typeinfo);
+	PRINT_STAT(invalid_size);
+	PRINT_STAT(bad_offset);
+	printf("\n");
+
+#undef PRINT_STAT
+}
+
 static void hists__find_annotations(struct hists *hists,
 				    struct evsel *evsel,
 				    struct perf_annotate *ann)
@@ -403,6 +441,9 @@ static void hists__find_annotations(struct hists *hists,
 	struct rb_node *nd = rb_first_cached(&hists->entries), *next;
 	int key = K_RIGHT;
 
+	if (ann->type_stat)
+		print_annotate_data_stat(&ann_data_stat);
+
 	while (nd) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		struct annotation *notes;
@@ -749,7 +790,8 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK_OPTARG(0, "data-type", &annotate, NULL, "name",
 			    "Show data type annotate for the memory accesses",
 			    parse_data_type),
-
+	OPT_BOOLEAN(0, "type-stat", &annotate.type_stat,
+		    "Show stats for the data type annotation"),
 	OPT_END()
 	};
 	int ret;
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index df9689f46619c..f22b4f18271c9 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -199,6 +199,7 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset)
 	/* Get the type of the variable */
 	if (die_get_real_type(var_die, type_die) == NULL) {
 		pr_debug("variable has no type\n");
+		ann_data_stat.no_typeinfo++;
 		return -1;
 	}
 
@@ -209,18 +210,21 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset)
 	if (dwarf_tag(type_die) != DW_TAG_pointer_type ||
 	    die_get_real_type(type_die, type_die) == NULL) {
 		pr_debug("no pointer or no type\n");
+		ann_data_stat.no_typeinfo++;
 		return -1;
 	}
 
 	/* Get the size of the actual type */
 	if (dwarf_aggregate_size(type_die, &size) < 0) {
 		pr_debug("type size is unknown\n");
+		ann_data_stat.invalid_size++;
 		return -1;
 	}
 
 	/* Minimal sanity check */
 	if ((unsigned)offset >= size) {
 		pr_debug("offset: %d is bigger than size: %" PRIu64 "\n", offset, size);
+		ann_data_stat.bad_offset++;
 		return -1;
 	}
 
@@ -239,6 +243,7 @@ static int find_data_type_die(struct debuginfo *di, u64 pc,
 	/* Get a compile_unit for this address */
 	if (!find_cu_die(di, pc, &cu_die)) {
 		pr_debug("cannot find CU for address %" PRIx64 "\n", pc);
+		ann_data_stat.no_cuinfo++;
 		return -1;
 	}
 
@@ -253,9 +258,12 @@ static int find_data_type_die(struct debuginfo *di, u64 pc,
 
 		/* Found a variable, see if it's correct */
 		ret = check_variable(&var_die, type_die, offset);
-		break;
+		goto out;
 	}
+	if (ret < 0)
+		ann_data_stat.no_var++;
 
+out:
 	free(scopes);
 	return ret;
 }
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index d2dc025b19345..8e73096c01d1a 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -70,6 +70,37 @@ struct annotated_data_type {
 
 extern struct annotated_data_type unknown_type;
 
+/**
+ * struct annotated_data_stat - Debug statistics
+ * @total: Total number of entry
+ * @no_sym: No symbol or map found
+ * @no_insn: Failed to get disasm line
+ * @no_insn_ops: The instruction has no operands
+ * @no_mem_ops: The instruction has no memory operands
+ * @no_reg: Failed to extract a register from the operand
+ * @no_dbginfo: The binary has no debug information
+ * @no_cuinfo: Failed to find a compile_unit
+ * @no_var: Failed to find a matching variable
+ * @no_typeinfo: Failed to get a type info for the variable
+ * @invalid_size: Failed to get a size info of the type
+ * @bad_offset: The access offset is out of the type
+ */
+struct annotated_data_stat {
+	int total;
+	int no_sym;
+	int no_insn;
+	int no_insn_ops;
+	int no_mem_ops;
+	int no_reg;
+	int no_dbginfo;
+	int no_cuinfo;
+	int no_var;
+	int no_typeinfo;
+	int invalid_size;
+	int bad_offset;
+};
+extern struct annotated_data_stat ann_data_stat;
+
 #ifdef HAVE_DWARF_SUPPORT
 
 /* Returns data type at the location (ip, reg, offset) */
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 68424ee0215e4..9870257ce21e7 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -103,6 +103,9 @@ static struct ins_ops nop_ops;
 static struct ins_ops lock_ops;
 static struct ins_ops ret_ops;
 
+/* Data type collection debug statistics */
+struct annotated_data_stat ann_data_stat;
+
 static int arch__grow_instructions(struct arch *arch)
 {
 	struct ins *new_instructions;
@@ -3683,14 +3686,22 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 	u64 ip = he->ip;
 	int i;
 
-	if (ms->map == NULL || ms->sym == NULL)
+	ann_data_stat.total++;
+
+	if (ms->map == NULL || ms->sym == NULL) {
+		ann_data_stat.no_sym++;
 		return NULL;
+	}
 
-	if (!symbol_conf.init_annotation)
+	if (!symbol_conf.init_annotation) {
+		ann_data_stat.no_sym++;
 		return NULL;
+	}
 
-	if (evsel__get_arch(evsel, &arch) < 0)
+	if (evsel__get_arch(evsel, &arch) < 0) {
+		ann_data_stat.no_insn++;
 		return NULL;
+	}
 
 	/* Make sure it runs objdump to get disasm of the function */
 	symbol__ensure_annotate(ms, evsel);
@@ -3700,11 +3711,15 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 	 * This is too slow...
 	 */
 	dl = find_disasm_line(ms->sym, ip);
-	if (dl == NULL)
+	if (dl == NULL) {
+		ann_data_stat.no_insn++;
 		return NULL;
+	}
 
-	if (annotate_get_insn_location(arch, dl, &loc) < 0)
+	if (annotate_get_insn_location(arch, dl, &loc) < 0) {
+		ann_data_stat.no_insn_ops++;
 		return NULL;
+	}
 
 	for_each_insn_op_loc(&loc, i, op_loc) {
 		if (!op_loc->mem_ref)
@@ -3721,5 +3736,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		he->mem_type_off = op_loc->offset;
 		return mem_type;
 	}
+
+	ann_data_stat.no_mem_ops++;
 	return NULL;
 }
-- 
GitLab


From 58824fa0087e1cb732edbf1f112a5ea0b2205c8b Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 12 Dec 2023 16:13:23 -0800
Subject: [PATCH 1897/4076] perf annotate: Add --insn-stat option for debugging

This is for a debugging purpose.  It'd be useful to see per-instrucion
level success/failure stats.

  $ perf annotate --data-type --insn-stat
  Annotate Instruction stats
  total 264, ok 143 (54.2%), bad 121 (45.8%)

    Name      :  Good   Bad
  -----------------------------------------------------------
    movq      :    45    31
    movl      :    22    11
    popq      :     0    19
    cmpl      :    16     3
    addq      :     8     7
    cmpq      :    11     3
    cmpxchgl  :     3     7
    cmpxchgq  :     8     0
    incl      :     3     3
    movzbl    :     4     2
    incq      :     4     2
    decl      :     6     0
    ...

Committer notes:

So these are about being able to find the type for accesses from these
instructions, we should improve the naming, but it is for debugging, we
can improve this later:

  @@ -3726,6 +3759,10 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
                          continue;

                  mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
  +               if (mem_type)
  +                       istat->good++;
  +               else
  +                       istat->bad++;

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-18-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c | 41 +++++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.c    | 38 ++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.h    |  8 +++++++
 3 files changed, 87 insertions(+)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 55f97ab1395ba..6c1cc797692d9 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -58,6 +58,7 @@ struct perf_annotate {
 	bool	   group_set;
 	bool	   data_type;
 	bool	   type_stat;
+	bool	   insn_stat;
 	float	   min_percent;
 	const char *sym_hist_filter;
 	const char *cpu_list;
@@ -434,6 +435,42 @@ static void print_annotate_data_stat(struct annotated_data_stat *s)
 #undef PRINT_STAT
 }
 
+static void print_annotate_item_stat(struct list_head *head, const char *title)
+{
+	struct annotated_item_stat *istat, *pos, *iter;
+	int total_good, total_bad, total;
+	int sum1, sum2;
+	LIST_HEAD(tmp);
+
+	/* sort the list by count */
+	list_splice_init(head, &tmp);
+	total_good = total_bad = 0;
+
+	list_for_each_entry_safe(istat, pos, &tmp, list) {
+		total_good += istat->good;
+		total_bad += istat->bad;
+		sum1 = istat->good + istat->bad;
+
+		list_for_each_entry(iter, head, list) {
+			sum2 = iter->good + iter->bad;
+			if (sum1 > sum2)
+				break;
+		}
+		list_move_tail(&istat->list, &iter->list);
+	}
+	total = total_good + total_bad;
+
+	printf("Annotate %s stats\n", title);
+	printf("total %d, ok %d (%.1f%%), bad %d (%.1f%%)\n\n", total,
+	       total_good, 100.0 * total_good / (total ?: 1),
+	       total_bad, 100.0 * total_bad / (total ?: 1));
+	printf("  %-10s: %5s %5s\n", "Name", "Good", "Bad");
+	printf("-----------------------------------------------------------\n");
+	list_for_each_entry(istat, head, list)
+		printf("  %-10s: %5d %5d\n", istat->name, istat->good, istat->bad);
+	printf("\n");
+}
+
 static void hists__find_annotations(struct hists *hists,
 				    struct evsel *evsel,
 				    struct perf_annotate *ann)
@@ -443,6 +480,8 @@ static void hists__find_annotations(struct hists *hists,
 
 	if (ann->type_stat)
 		print_annotate_data_stat(&ann_data_stat);
+	if (ann->insn_stat)
+		print_annotate_item_stat(&ann_insn_stat, "Instruction");
 
 	while (nd) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
@@ -792,6 +831,8 @@ int cmd_annotate(int argc, const char **argv)
 			    parse_data_type),
 	OPT_BOOLEAN(0, "type-stat", &annotate.type_stat,
 		    "Show stats for the data type annotation"),
+	OPT_BOOLEAN(0, "insn-stat", &annotate.insn_stat,
+		    "Show instruction stats for the data type annotation"),
 	OPT_END()
 	};
 	int ret;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 9870257ce21e7..9b70ab110ce79 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -105,6 +105,7 @@ static struct ins_ops ret_ops;
 
 /* Data type collection debug statistics */
 struct annotated_data_stat ann_data_stat;
+LIST_HEAD(ann_insn_stat);
 
 static int arch__grow_instructions(struct arch *arch)
 {
@@ -3665,6 +3666,30 @@ static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
 	return NULL;
 }
 
+static struct annotated_item_stat *annotate_data_stat(struct list_head *head,
+						      const char *name)
+{
+	struct annotated_item_stat *istat;
+
+	list_for_each_entry(istat, head, list) {
+		if (!strcmp(istat->name, name))
+			return istat;
+	}
+
+	istat = zalloc(sizeof(*istat));
+	if (istat == NULL)
+		return NULL;
+
+	istat->name = strdup(name);
+	if (istat->name == NULL) {
+		free(istat);
+		return NULL;
+	}
+
+	list_add_tail(&istat->list, head);
+	return istat;
+}
+
 /**
  * hist_entry__get_data_type - find data type for given hist entry
  * @he: hist entry
@@ -3683,6 +3708,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 	struct annotated_insn_loc loc;
 	struct annotated_op_loc *op_loc;
 	struct annotated_data_type *mem_type;
+	struct annotated_item_stat *istat;
 	u64 ip = he->ip;
 	int i;
 
@@ -3716,8 +3742,15 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		return NULL;
 	}
 
+	istat = annotate_data_stat(&ann_insn_stat, dl->ins.name);
+	if (istat == NULL) {
+		ann_data_stat.no_insn++;
+		return NULL;
+	}
+
 	if (annotate_get_insn_location(arch, dl, &loc) < 0) {
 		ann_data_stat.no_insn_ops++;
+		istat->bad++;
 		return NULL;
 	}
 
@@ -3726,6 +3759,10 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 			continue;
 
 		mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+		if (mem_type)
+			istat->good++;
+		else
+			istat->bad++;
 
 		if (symbol_conf.annotate_data_sample) {
 			annotated_data_type__update_samples(mem_type, evsel,
@@ -3738,5 +3775,6 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 	}
 
 	ann_data_stat.no_mem_ops++;
+	istat->bad++;
 	return NULL;
 }
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 6c75b28322860..dba50762c6e80 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -479,4 +479,12 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 /* Returns a data type from the sample instruction (if any) */
 struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he);
 
+struct annotated_item_stat {
+	struct list_head list;
+	char *name;
+	int good;
+	int bad;
+};
+extern struct list_head ann_insn_stat;
+
 #endif	/* __PERF_ANNOTATE_H */
-- 
GitLab


From ad7ced12a08b5cf8fd0df7d0f764d4801a2b545a Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Sun, 24 Dec 2023 00:04:00 -0800
Subject: [PATCH 1898/4076] dt-bindings: touchscreen: convert neonode,zforce to
 json-schema

Convert Neonode infrared touchscreen controller binding to DT schema.

Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231223221213.774868-2-andreas@kemnade.info
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../input/touchscreen/neonode,zforce.yaml     | 67 +++++++++++++++++++
 .../bindings/input/touchscreen/zforce_ts.txt  | 34 ----------
 2 files changed, 67 insertions(+), 34 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml
 delete mode 100644 Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt

diff --git a/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml b/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml
new file mode 100644
index 0000000000000..c39662815a6c5
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml
@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/neonode,zforce.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Neonode infrared touchscreen controller
+
+maintainers:
+  - Heiko Stuebner <heiko@sntech.de>
+
+properties:
+  compatible:
+    const: neonode,zforce
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+
+  irq-gpios:
+    maxItems: 1
+
+  x-size:
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  y-size:
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - reset-gpios
+  - x-size
+  - y-size
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        touchscreen@50 {
+            compatible = "neonode,zforce";
+            reg = <0x50>;
+            interrupts = <2 0>;
+            vdd-supply = <&reg_zforce_vdd>;
+
+            reset-gpios = <&gpio5 9 0>; /* RST */
+            irq-gpios = <&gpio5 6 0>; /* IRQ, optional */
+
+            x-size = <800>;
+            y-size = <600>;
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt b/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt
deleted file mode 100644
index e3c27c4fd9c85..0000000000000
--- a/Documentation/devicetree/bindings/input/touchscreen/zforce_ts.txt
+++ /dev/null
@@ -1,34 +0,0 @@
-* Neonode infrared touchscreen controller
-
-Required properties:
-- compatible: must be "neonode,zforce"
-- reg: I2C address of the chip
-- interrupts: interrupt to which the chip is connected
-- reset-gpios: reset gpio the chip is connected to
-- x-size: horizontal resolution of touchscreen
-- y-size: vertical resolution of touchscreen
-
-Optional properties:
-- irq-gpios : interrupt gpio the chip is connected to
-- vdd-supply: Regulator controlling the controller supply
-
-Example:
-
-	i2c@00000000 {
-		/* ... */
-
-		zforce_ts@50 {
-			compatible = "neonode,zforce";
-			reg = <0x50>;
-			interrupts = <2 0>;
-			vdd-supply = <&reg_zforce_vdd>;
-
-			reset-gpios = <&gpio5 9 0>; /* RST */
-			irq-gpios = <&gpio5 6 0>; /* IRQ, optional */
-
-			x-size = <800>;
-			y-size = <600>;
-		};
-
-		/* ... */
-	};
-- 
GitLab


From cc040e42fed8e80409ac5cf8663f0cd9b7951028 Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Sun, 24 Dec 2023 00:04:12 -0800
Subject: [PATCH 1899/4076] dt-bindings: touchscreen: neonode,zforce: Use
 standard properties

Enable touchscreen orientation to be specified by using standard
properties.

Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231223221213.774868-3-andreas@kemnade.info
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../bindings/input/touchscreen/neonode,zforce.yaml  | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml b/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml
index c39662815a6c5..c2ee89b76ea13 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/neonode,zforce.yaml
@@ -9,6 +9,9 @@ title: Neonode infrared touchscreen controller
 maintainers:
   - Heiko Stuebner <heiko@sntech.de>
 
+allOf:
+  - $ref: touchscreen.yaml#
+
 properties:
   compatible:
     const: neonode,zforce
@@ -26,9 +29,11 @@ properties:
     maxItems: 1
 
   x-size:
+    deprecated: true
     $ref: /schemas/types.yaml#/definitions/uint32
 
   y-size:
+    deprecated: true
     $ref: /schemas/types.yaml#/definitions/uint32
 
   vdd-supply: true
@@ -38,8 +43,6 @@ required:
   - reg
   - interrupts
   - reset-gpios
-  - x-size
-  - y-size
 
 unevaluatedProperties: false
 
@@ -60,8 +63,10 @@ examples:
             reset-gpios = <&gpio5 9 0>; /* RST */
             irq-gpios = <&gpio5 6 0>; /* IRQ, optional */
 
-            x-size = <800>;
-            y-size = <600>;
+            touchscreen-min-x = <0>;
+            touchscreen-size-x = <800>;
+            touchscreen-min-y = <0>;
+            touchscreen-size-y = <600>;
         };
     };
 ...
-- 
GitLab


From 435e84ec2009bf40625ee7ca1f8453d3b22edf75 Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Sun, 24 Dec 2023 00:04:23 -0800
Subject: [PATCH 1900/4076] Input: zforce_ts - accept standard touchscreen
 properties

Only driver-specific properties were accepted, change it
to use the now-available standard properties.

Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Link: https://lore.kernel.org/r/20231223221213.774868-4-andreas@kemnade.info
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/zforce_ts.c | 34 +++++++++++++--------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 5be5112845e1e..5680075f0bb84 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -20,6 +20,7 @@
 #include <linux/device.h>
 #include <linux/sysfs.h>
 #include <linux/input/mt.h>
+#include <linux/input/touchscreen.h>
 #include <linux/platform_data/zforce_ts.h>
 #include <linux/regulator/consumer.h>
 #include <linux/of.h>
@@ -106,6 +107,7 @@ struct zforce_point {
 struct zforce_ts {
 	struct i2c_client	*client;
 	struct input_dev	*input;
+	struct touchscreen_properties prop;
 	const struct zforce_ts_platdata *pdata;
 	char			phys[32];
 
@@ -266,7 +268,6 @@ static int zforce_setconfig(struct zforce_ts *ts, char b1)
 static int zforce_start(struct zforce_ts *ts)
 {
 	struct i2c_client *client = ts->client;
-	const struct zforce_ts_platdata *pdata = ts->pdata;
 	int ret;
 
 	dev_dbg(&client->dev, "starting device\n");
@@ -277,7 +278,7 @@ static int zforce_start(struct zforce_ts *ts)
 		return ret;
 	}
 
-	ret = zforce_resolution(ts, pdata->x_max, pdata->y_max);
+	ret = zforce_resolution(ts, ts->prop.max_x, ts->prop.max_y);
 	if (ret) {
 		dev_err(&client->dev, "Unable to set resolution, %d\n", ret);
 		goto error;
@@ -337,7 +338,6 @@ static int zforce_stop(struct zforce_ts *ts)
 static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
 {
 	struct i2c_client *client = ts->client;
-	const struct zforce_ts_platdata *pdata = ts->pdata;
 	struct zforce_point point;
 	int count, i, num = 0;
 
@@ -355,8 +355,8 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
 		point.coord_y =
 			payload[9 * i + 4] << 8 | payload[9 * i + 3];
 
-		if (point.coord_x > pdata->x_max ||
-		    point.coord_y > pdata->y_max) {
+		if (point.coord_x > ts->prop.max_x ||
+		    point.coord_y > ts->prop.max_y) {
 			dev_warn(&client->dev, "coordinates (%d,%d) invalid\n",
 				point.coord_x, point.coord_y);
 			point.coord_x = point.coord_y = 0;
@@ -390,10 +390,9 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
 						point.state != STATE_UP);
 
 		if (point.state != STATE_UP) {
-			input_report_abs(ts->input, ABS_MT_POSITION_X,
-					 point.coord_x);
-			input_report_abs(ts->input, ABS_MT_POSITION_Y,
-					 point.coord_y);
+			touchscreen_report_pos(ts->input, &ts->prop,
+					       point.coord_x, point.coord_y,
+					       true);
 			input_report_abs(ts->input, ABS_MT_TOUCH_MAJOR,
 					 point.area_major);
 			input_report_abs(ts->input, ABS_MT_TOUCH_MINOR,
@@ -719,15 +718,8 @@ static struct zforce_ts_platdata *zforce_parse_dt(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	if (of_property_read_u32(np, "x-size", &pdata->x_max)) {
-		dev_err(dev, "failed to get x-size property\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	if (of_property_read_u32(np, "y-size", &pdata->y_max)) {
-		dev_err(dev, "failed to get y-size property\n");
-		return ERR_PTR(-EINVAL);
-	}
+	of_property_read_u32(np, "x-size", &pdata->x_max);
+	of_property_read_u32(np, "y-size", &pdata->y_max);
 
 	return pdata;
 }
@@ -856,6 +848,12 @@ static int zforce_probe(struct i2c_client *client)
 	input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0,
 			     pdata->y_max, 0, 0);
 
+	touchscreen_parse_properties(input_dev, true, &ts->prop);
+	if (ts->prop.max_x == 0 || ts->prop.max_y == 0) {
+		dev_err(&client->dev, "no size specified\n");
+		return -EINVAL;
+	}
+
 	input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0,
 			     ZFORCE_MAX_AREA, 0, 0);
 	input_set_abs_params(input_dev, ABS_MT_TOUCH_MINOR, 0,
-- 
GitLab


From 47757ea83a545536cdd418fec84b7a970710e48b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 20 Nov 2023 15:29:09 +0000
Subject: [PATCH 1901/4076] netfs, fscache: Move fs/fscache/* into fs/netfs/

There's a problem with dependencies between netfslib and fscache as each
wants to access some functions of the other.  Deal with this by moving
fs/fscache/* into fs/netfs/ and renaming those files to begin with
"fscache-".

For the moment, the moved files are changed as little as possible and an
fscache module is still built.  A subsequent patch will integrate them.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Christian Brauner <christian@brauner.io>
cc: linux-fsdevel@vger.kernel.org
cc: linux-cachefs@redhat.com
---
 MAINTAINERS                                   | 21 ++++++----
 fs/Kconfig                                    |  1 -
 fs/Makefile                                   |  1 -
 fs/fscache/Kconfig                            | 40 -------------------
 fs/fscache/Makefile                           | 16 --------
 fs/netfs/Kconfig                              | 39 ++++++++++++++++++
 fs/netfs/Makefile                             | 14 ++++++-
 fs/{fscache/cache.c => netfs/fscache_cache.c} |  0
 .../cookie.c => netfs/fscache_cookie.c}       |  0
 .../internal.h => netfs/fscache_internal.h}   |  0
 fs/{fscache/io.c => netfs/fscache_io.c}       |  0
 fs/{fscache/main.c => netfs/fscache_main.c}   |  0
 fs/{fscache/proc.c => netfs/fscache_proc.c}   |  0
 fs/{fscache/stats.c => netfs/fscache_stats.c} |  0
 .../volume.c => netfs/fscache_volume.c}       |  0
 fs/netfs/internal.h                           |  5 +++
 fs/netfs/main.c                               |  5 ++-
 17 files changed, 73 insertions(+), 69 deletions(-)
 delete mode 100644 fs/fscache/Kconfig
 delete mode 100644 fs/fscache/Makefile
 rename fs/{fscache/cache.c => netfs/fscache_cache.c} (100%)
 rename fs/{fscache/cookie.c => netfs/fscache_cookie.c} (100%)
 rename fs/{fscache/internal.h => netfs/fscache_internal.h} (100%)
 rename fs/{fscache/io.c => netfs/fscache_io.c} (100%)
 rename fs/{fscache/main.c => netfs/fscache_main.c} (100%)
 rename fs/{fscache/proc.c => netfs/fscache_proc.c} (100%)
 rename fs/{fscache/stats.c => netfs/fscache_stats.c} (100%)
 rename fs/{fscache/volume.c => netfs/fscache_volume.c} (100%)

diff --git a/MAINTAINERS b/MAINTAINERS
index 7cef2d2ef8d70..d836f88b0fe14 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8133,6 +8133,19 @@ S:	Supported
 F:	fs/iomap/
 F:	include/linux/iomap.h
 
+FILESYSTEMS [NETFS LIBRARY]
+M:	David Howells <dhowells@redhat.com>
+L:	linux-cachefs@redhat.com (moderated for non-subscribers)
+L:	linux-fsdevel@vger.kernel.org
+S:	Supported
+F:	Documentation/filesystems/caching/
+F:	Documentation/filesystems/netfs_library.rst
+F:	fs/netfs/
+F:	include/linux/fscache*.h
+F:	include/linux/netfs.h
+F:	include/trace/events/fscache.h
+F:	include/trace/events/netfs.h
+
 FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 M:	Riku Voipio <riku.voipio@iki.fi>
 L:	linux-hwmon@vger.kernel.org
@@ -8567,14 +8580,6 @@ F:	Documentation/power/freezing-of-tasks.rst
 F:	include/linux/freezer.h
 F:	kernel/freezer.c
 
-FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS
-M:	David Howells <dhowells@redhat.com>
-L:	linux-cachefs@redhat.com (moderated for non-subscribers)
-S:	Supported
-F:	Documentation/filesystems/caching/
-F:	fs/fscache/
-F:	include/linux/fscache*.h
-
 FSCRYPT: FILE SYSTEM LEVEL ENCRYPTION SUPPORT
 M:	Eric Biggers <ebiggers@kernel.org>
 M:	Theodore Y. Ts'o <tytso@mit.edu>
diff --git a/fs/Kconfig b/fs/Kconfig
index 42837617a55b5..c935c341eb6ed 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -140,7 +140,6 @@ source "fs/overlayfs/Kconfig"
 menu "Caches"
 
 source "fs/netfs/Kconfig"
-source "fs/fscache/Kconfig"
 source "fs/cachefiles/Kconfig"
 
 endmenu
diff --git a/fs/Makefile b/fs/Makefile
index 75522f88e7636..af7632368e987 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -60,7 +60,6 @@ obj-$(CONFIG_DLM)		+= dlm/
  
 # Do not add any filesystems before this line
 obj-$(CONFIG_NETFS_SUPPORT)	+= netfs/
-obj-$(CONFIG_FSCACHE)		+= fscache/
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT4_FS)		+= ext4/
 # We place ext4 before ext2 so that clean ext3 root fs's do NOT mount using the
diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig
deleted file mode 100644
index b313a978ae0a2..0000000000000
--- a/fs/fscache/Kconfig
+++ /dev/null
@@ -1,40 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-
-config FSCACHE
-	tristate "General filesystem local caching manager"
-	select NETFS_SUPPORT
-	help
-	  This option enables a generic filesystem caching manager that can be
-	  used by various network and other filesystems to cache data locally.
-	  Different sorts of caches can be plugged in, depending on the
-	  resources available.
-
-	  See Documentation/filesystems/caching/fscache.rst for more information.
-
-config FSCACHE_STATS
-	bool "Gather statistical information on local caching"
-	depends on FSCACHE && PROC_FS
-	select NETFS_STATS
-	help
-	  This option causes statistical information to be gathered on local
-	  caching and exported through file:
-
-		/proc/fs/fscache/stats
-
-	  The gathering of statistics adds a certain amount of overhead to
-	  execution as there are a quite a few stats gathered, and on a
-	  multi-CPU system these may be on cachelines that keep bouncing
-	  between CPUs.  On the other hand, the stats are very useful for
-	  debugging purposes.  Saying 'Y' here is recommended.
-
-	  See Documentation/filesystems/caching/fscache.rst for more information.
-
-config FSCACHE_DEBUG
-	bool "Debug FS-Cache"
-	depends on FSCACHE
-	help
-	  This permits debugging to be dynamically enabled in the local caching
-	  management module.  If this is set, the debugging output may be
-	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
-
-	  See Documentation/filesystems/caching/fscache.rst for more information.
diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile
deleted file mode 100644
index afb090ea16c40..0000000000000
--- a/fs/fscache/Makefile
+++ /dev/null
@@ -1,16 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for general filesystem caching code
-#
-
-fscache-y := \
-	cache.o \
-	cookie.o \
-	io.o \
-	main.o \
-	volume.o
-
-fscache-$(CONFIG_PROC_FS) += proc.o
-fscache-$(CONFIG_FSCACHE_STATS) += stats.o
-
-obj-$(CONFIG_FSCACHE) := fscache.o
diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig
index b4db21022cb43..b4378688357c6 100644
--- a/fs/netfs/Kconfig
+++ b/fs/netfs/Kconfig
@@ -21,3 +21,42 @@ config NETFS_STATS
 	  multi-CPU system these may be on cachelines that keep bouncing
 	  between CPUs.  On the other hand, the stats are very useful for
 	  debugging purposes.  Saying 'Y' here is recommended.
+
+config FSCACHE
+	tristate "General filesystem local caching manager"
+	select NETFS_SUPPORT
+	help
+	  This option enables a generic filesystem caching manager that can be
+	  used by various network and other filesystems to cache data locally.
+	  Different sorts of caches can be plugged in, depending on the
+	  resources available.
+
+	  See Documentation/filesystems/caching/fscache.rst for more information.
+
+config FSCACHE_STATS
+	bool "Gather statistical information on local caching"
+	depends on FSCACHE && PROC_FS
+	select NETFS_STATS
+	help
+	  This option causes statistical information to be gathered on local
+	  caching and exported through file:
+
+		/proc/fs/fscache/stats
+
+	  The gathering of statistics adds a certain amount of overhead to
+	  execution as there are a quite a few stats gathered, and on a
+	  multi-CPU system these may be on cachelines that keep bouncing
+	  between CPUs.  On the other hand, the stats are very useful for
+	  debugging purposes.  Saying 'Y' here is recommended.
+
+	  See Documentation/filesystems/caching/fscache.rst for more information.
+
+config FSCACHE_DEBUG
+	bool "Debug FS-Cache"
+	depends on FSCACHE
+	help
+	  This permits debugging to be dynamically enabled in the local caching
+	  management module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
+
+	  See Documentation/filesystems/caching/fscache.rst for more information.
diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index 386d6fb92793a..bbb2b824bd5e9 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -1,5 +1,17 @@
 # SPDX-License-Identifier: GPL-2.0
 
+fscache-y := \
+	fscache_cache.o \
+	fscache_cookie.o \
+	fscache_io.o \
+	fscache_main.o \
+	fscache_volume.o
+
+fscache-$(CONFIG_PROC_FS) += fscache_proc.o
+fscache-$(CONFIG_FSCACHE_STATS) += fscache_stats.o
+
+obj-$(CONFIG_FSCACHE) := fscache.o
+
 netfs-y := \
 	buffered_read.o \
 	io.o \
@@ -9,4 +21,4 @@ netfs-y := \
 
 netfs-$(CONFIG_NETFS_STATS) += stats.o
 
-obj-$(CONFIG_NETFS_SUPPORT) := netfs.o
+obj-$(CONFIG_NETFS_SUPPORT) += netfs.o
diff --git a/fs/fscache/cache.c b/fs/netfs/fscache_cache.c
similarity index 100%
rename from fs/fscache/cache.c
rename to fs/netfs/fscache_cache.c
diff --git a/fs/fscache/cookie.c b/fs/netfs/fscache_cookie.c
similarity index 100%
rename from fs/fscache/cookie.c
rename to fs/netfs/fscache_cookie.c
diff --git a/fs/fscache/internal.h b/fs/netfs/fscache_internal.h
similarity index 100%
rename from fs/fscache/internal.h
rename to fs/netfs/fscache_internal.h
diff --git a/fs/fscache/io.c b/fs/netfs/fscache_io.c
similarity index 100%
rename from fs/fscache/io.c
rename to fs/netfs/fscache_io.c
diff --git a/fs/fscache/main.c b/fs/netfs/fscache_main.c
similarity index 100%
rename from fs/fscache/main.c
rename to fs/netfs/fscache_main.c
diff --git a/fs/fscache/proc.c b/fs/netfs/fscache_proc.c
similarity index 100%
rename from fs/fscache/proc.c
rename to fs/netfs/fscache_proc.c
diff --git a/fs/fscache/stats.c b/fs/netfs/fscache_stats.c
similarity index 100%
rename from fs/fscache/stats.c
rename to fs/netfs/fscache_stats.c
diff --git a/fs/fscache/volume.c b/fs/netfs/fscache_volume.c
similarity index 100%
rename from fs/fscache/volume.c
rename to fs/netfs/fscache_volume.c
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 43fac1b14e40c..e96432499eb2a 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -5,9 +5,12 @@
  * Written by David Howells (dhowells@redhat.com)
  */
 
+#include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <linux/netfs.h>
 #include <linux/fscache.h>
 #include <trace/events/netfs.h>
+#include "fscache_internal.h"
 
 #ifdef pr_fmt
 #undef pr_fmt
@@ -107,6 +110,7 @@ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx)
 /*
  * debug tracing
  */
+#if 0
 #define dbgprintk(FMT, ...) \
 	printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
 
@@ -143,3 +147,4 @@ do {						\
 #define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
 #define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
 #endif
+#endif
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 068568702957e..237c54a01d971 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -8,8 +8,8 @@
 #include <linux/module.h>
 #include <linux/export.h>
 #include "internal.h"
-#define CREATE_TRACE_POINTS
-#include <trace/events/netfs.h>
+//#define CREATE_TRACE_POINTS
+//#include <trace/events/netfs.h>
 
 MODULE_DESCRIPTION("Network fs support");
 MODULE_AUTHOR("Red Hat, Inc.");
@@ -18,3 +18,4 @@ MODULE_LICENSE("GPL");
 unsigned netfs_debug;
 module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
+
-- 
GitLab


From 915cd30cdea8811cddd8f59e57dd9dd0a814b76c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 20 Nov 2023 15:55:18 +0000
Subject: [PATCH 1902/4076] netfs, fscache: Combine fscache with netfs

Now that the fscache code is moved to be colocated with the netfslib code
so that they combined into one module, do the combining.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Christian Brauner <christian@brauner.io>
cc: linux-fsdevel@vger.kernel.org
cc: linux-cachefs@redhat.com
cc: linux-nfs@vger.kernel.org,
cc: linux-erofs@lists.ozlabs.org
---
 arch/arm/configs/mxs_defconfig        |   3 +-
 arch/csky/configs/defconfig           |   3 +-
 arch/mips/configs/ip27_defconfig      |   3 +-
 arch/mips/configs/lemote2f_defconfig  |   3 +-
 arch/mips/configs/loongson3_defconfig |   3 +-
 arch/mips/configs/pic32mzda_defconfig |   3 +-
 arch/s390/configs/debug_defconfig     |   3 +-
 arch/s390/configs/defconfig           |   3 +-
 arch/sh/configs/sdk7786_defconfig     |   3 +-
 fs/cachefiles/Kconfig                 |   2 +-
 fs/erofs/Kconfig                      |   7 +-
 fs/netfs/Kconfig                      |   4 +-
 fs/netfs/Makefile                     |  24 +--
 fs/netfs/fscache_internal.h           | 267 +-------------------------
 fs/netfs/fscache_main.c               |  17 +-
 fs/netfs/internal.h                   | 192 +++++++++++++++++-
 fs/netfs/main.c                       |   4 +-
 fs/nfs/Kconfig                        |   4 +-
 18 files changed, 237 insertions(+), 311 deletions(-)

diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index feb38a94c1a70..43bc1255a5db9 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -138,7 +138,8 @@ CONFIG_PWM_MXS=y
 CONFIG_NVMEM_MXS_OCOTP=y
 CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_FSCACHE_STATS=y
 CONFIG_CACHEFILES=m
 CONFIG_VFAT_FS=y
diff --git a/arch/csky/configs/defconfig b/arch/csky/configs/defconfig
index af722e4dfb47d..ff559e5162aa1 100644
--- a/arch/csky/configs/defconfig
+++ b/arch/csky/configs/defconfig
@@ -34,7 +34,8 @@ CONFIG_GENERIC_PHY=y
 CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA=y
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_FSCACHE_STATS=y
 CONFIG_CACHEFILES=m
 CONFIG_MSDOS_FS=y
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index b51f738a39a05..4714074c8bd7f 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -287,7 +287,8 @@ CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_FSCACHE_STATS=y
 CONFIG_CACHEFILES=m
 CONFIG_PROC_KCORE=y
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 38f17b6584218..3389e6e885d9f 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -238,7 +238,8 @@ CONFIG_BTRFS_FS=m
 CONFIG_QUOTA=y
 CONFIG_QFMT_V2=m
 CONFIG_AUTOFS_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 07839a4b397e5..78f4987520664 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -356,7 +356,8 @@ CONFIG_QFMT_V2=m
 CONFIG_AUTOFS_FS=y
 CONFIG_FUSE_FS=m
 CONFIG_VIRTIO_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_MSDOS_FS=m
diff --git a/arch/mips/configs/pic32mzda_defconfig b/arch/mips/configs/pic32mzda_defconfig
index 166d2ad372d14..54774f90c23ea 100644
--- a/arch/mips/configs/pic32mzda_defconfig
+++ b/arch/mips/configs/pic32mzda_defconfig
@@ -68,7 +68,8 @@ CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 6de44ede4e14d..060c4207ef2e6 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -637,8 +637,9 @@ CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
 CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
+CONFIG_NETFS_SUPPORT=m
 CONFIG_NETFS_STATS=y
-CONFIG_FSCACHE=m
+CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index bcae47da6b7cd..dbfa2115d875d 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -622,8 +622,9 @@ CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
 CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
+CONFIG_NETFS_SUPPORT=m
 CONFIG_NETFS_STATS=y
-CONFIG_FSCACHE=m
+CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index cf59b98446e4d..7b427c17fbfec 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -171,7 +171,8 @@ CONFIG_BTRFS_FS=y
 CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
-CONFIG_FSCACHE=m
+CONFIG_NETFS_SUPPORT=m
+CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig
index 8df715640a48f..c5a070550ee33 100644
--- a/fs/cachefiles/Kconfig
+++ b/fs/cachefiles/Kconfig
@@ -2,7 +2,7 @@
 
 config CACHEFILES
 	tristate "Filesystem caching on files"
-	depends on FSCACHE && BLOCK
+	depends on NETFS_SUPPORT && FSCACHE && BLOCK
 	help
 	  This permits use of a mounted filesystem as a cache for other
 	  filesystems - primarily networking filesystems - thus allowing fast
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index 1d318f85232de..fffd3919343e4 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -114,8 +114,11 @@ config EROFS_FS_ZIP_DEFLATE
 
 config EROFS_FS_ONDEMAND
 	bool "EROFS fscache-based on-demand read support"
-	depends on CACHEFILES_ONDEMAND && (EROFS_FS=m && FSCACHE || EROFS_FS=y && FSCACHE=y)
-	default n
+	depends on EROFS_FS
+	select NETFS_SUPPORT
+	select FSCACHE
+	select CACHEFILES
+	select CACHEFILES_ONDEMAND
 	help
 	  This permits EROFS to use fscache-backed data blobs with on-demand
 	  read support.
diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig
index b4378688357c6..bec805e0c44c0 100644
--- a/fs/netfs/Kconfig
+++ b/fs/netfs/Kconfig
@@ -23,8 +23,8 @@ config NETFS_STATS
 	  debugging purposes.  Saying 'Y' here is recommended.
 
 config FSCACHE
-	tristate "General filesystem local caching manager"
-	select NETFS_SUPPORT
+	bool "General filesystem local caching manager"
+	depends on NETFS_SUPPORT
 	help
 	  This option enables a generic filesystem caching manager that can be
 	  used by various network and other filesystems to cache data locally.
diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index bbb2b824bd5e9..b57162ef9cfb3 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -1,17 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-fscache-y := \
-	fscache_cache.o \
-	fscache_cookie.o \
-	fscache_io.o \
-	fscache_main.o \
-	fscache_volume.o
-
-fscache-$(CONFIG_PROC_FS) += fscache_proc.o
-fscache-$(CONFIG_FSCACHE_STATS) += fscache_stats.o
-
-obj-$(CONFIG_FSCACHE) := fscache.o
-
 netfs-y := \
 	buffered_read.o \
 	io.o \
@@ -21,4 +9,16 @@ netfs-y := \
 
 netfs-$(CONFIG_NETFS_STATS) += stats.o
 
+netfs-$(CONFIG_FSCACHE) += \
+	fscache_cache.o \
+	fscache_cookie.o \
+	fscache_io.o \
+	fscache_main.o \
+	fscache_volume.o
+
+ifeq ($(CONFIG_PROC_FS),y)
+netfs-$(CONFIG_FSCACHE) += fscache_proc.o
+endif
+netfs-$(CONFIG_FSCACHE_STATS) += fscache_stats.o
+
 obj-$(CONFIG_NETFS_SUPPORT) += netfs.o
diff --git a/fs/netfs/fscache_internal.h b/fs/netfs/fscache_internal.h
index 1336f517e9b1a..a09b948fcef21 100644
--- a/fs/netfs/fscache_internal.h
+++ b/fs/netfs/fscache_internal.h
@@ -5,273 +5,10 @@
  * Written by David Howells (dhowells@redhat.com)
  */
 
+#include "internal.h"
+
 #ifdef pr_fmt
 #undef pr_fmt
 #endif
 
 #define pr_fmt(fmt) "FS-Cache: " fmt
-
-#include <linux/slab.h>
-#include <linux/fscache-cache.h>
-#include <trace/events/fscache.h>
-#include <linux/sched.h>
-#include <linux/seq_file.h>
-
-/*
- * cache.c
- */
-#ifdef CONFIG_PROC_FS
-extern const struct seq_operations fscache_caches_seq_ops;
-#endif
-bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why);
-void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why);
-struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache);
-void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where);
-
-static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache)
-{
-	return smp_load_acquire(&cache->state);
-}
-
-static inline bool fscache_cache_is_live(const struct fscache_cache *cache)
-{
-	return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE;
-}
-
-static inline void fscache_set_cache_state(struct fscache_cache *cache,
-					   enum fscache_cache_state new_state)
-{
-	smp_store_release(&cache->state, new_state);
-
-}
-
-static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache,
-						 enum fscache_cache_state old_state,
-						 enum fscache_cache_state new_state)
-{
-	return try_cmpxchg_release(&cache->state, &old_state, new_state);
-}
-
-/*
- * cookie.c
- */
-extern struct kmem_cache *fscache_cookie_jar;
-#ifdef CONFIG_PROC_FS
-extern const struct seq_operations fscache_cookies_seq_ops;
-#endif
-extern struct timer_list fscache_cookie_lru_timer;
-
-extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix);
-extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie,
-					enum fscache_access_trace why);
-
-static inline void fscache_see_cookie(struct fscache_cookie *cookie,
-				      enum fscache_cookie_trace where)
-{
-	trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref),
-			     where);
-}
-
-/*
- * main.c
- */
-extern unsigned fscache_debug;
-
-extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len);
-
-/*
- * proc.c
- */
-#ifdef CONFIG_PROC_FS
-extern int __init fscache_proc_init(void);
-extern void fscache_proc_cleanup(void);
-#else
-#define fscache_proc_init()	(0)
-#define fscache_proc_cleanup()	do {} while (0)
-#endif
-
-/*
- * stats.c
- */
-#ifdef CONFIG_FSCACHE_STATS
-extern atomic_t fscache_n_volumes;
-extern atomic_t fscache_n_volumes_collision;
-extern atomic_t fscache_n_volumes_nomem;
-extern atomic_t fscache_n_cookies;
-extern atomic_t fscache_n_cookies_lru;
-extern atomic_t fscache_n_cookies_lru_expired;
-extern atomic_t fscache_n_cookies_lru_removed;
-extern atomic_t fscache_n_cookies_lru_dropped;
-
-extern atomic_t fscache_n_acquires;
-extern atomic_t fscache_n_acquires_ok;
-extern atomic_t fscache_n_acquires_oom;
-
-extern atomic_t fscache_n_invalidates;
-
-extern atomic_t fscache_n_relinquishes;
-extern atomic_t fscache_n_relinquishes_retire;
-extern atomic_t fscache_n_relinquishes_dropped;
-
-extern atomic_t fscache_n_resizes;
-extern atomic_t fscache_n_resizes_null;
-
-static inline void fscache_stat(atomic_t *stat)
-{
-	atomic_inc(stat);
-}
-
-static inline void fscache_stat_d(atomic_t *stat)
-{
-	atomic_dec(stat);
-}
-
-#define __fscache_stat(stat) (stat)
-
-int fscache_stats_show(struct seq_file *m, void *v);
-#else
-
-#define __fscache_stat(stat) (NULL)
-#define fscache_stat(stat) do {} while (0)
-#define fscache_stat_d(stat) do {} while (0)
-#endif
-
-/*
- * volume.c
- */
-#ifdef CONFIG_PROC_FS
-extern const struct seq_operations fscache_volumes_seq_ops;
-#endif
-
-struct fscache_volume *fscache_get_volume(struct fscache_volume *volume,
-					  enum fscache_volume_trace where);
-void fscache_put_volume(struct fscache_volume *volume,
-			enum fscache_volume_trace where);
-bool fscache_begin_volume_access(struct fscache_volume *volume,
-				 struct fscache_cookie *cookie,
-				 enum fscache_access_trace why);
-void fscache_create_volume(struct fscache_volume *volume, bool wait);
-
-
-/*****************************************************************************/
-/*
- * debug tracing
- */
-#define dbgprintk(FMT, ...) \
-	printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
-
-#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
-#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
-#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
-
-#define kjournal(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
-
-#ifdef __KDEBUG
-#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
-#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
-#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
-
-#elif defined(CONFIG_FSCACHE_DEBUG)
-#define _enter(FMT, ...)			\
-do {						\
-	if (__do_kdebug(ENTER))			\
-		kenter(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#define _leave(FMT, ...)			\
-do {						\
-	if (__do_kdebug(LEAVE))			\
-		kleave(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#define _debug(FMT, ...)			\
-do {						\
-	if (__do_kdebug(DEBUG))			\
-		kdebug(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#else
-#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__)
-#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
-#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
-#endif
-
-/*
- * determine whether a particular optional debugging point should be logged
- * - we need to go through three steps to persuade cpp to correctly join the
- *   shorthand in FSCACHE_DEBUG_LEVEL with its prefix
- */
-#define ____do_kdebug(LEVEL, POINT) \
-	unlikely((fscache_debug & \
-		  (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3))))
-#define ___do_kdebug(LEVEL, POINT) \
-	____do_kdebug(LEVEL, POINT)
-#define __do_kdebug(POINT) \
-	___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT)
-
-#define FSCACHE_DEBUG_CACHE	0
-#define FSCACHE_DEBUG_COOKIE	1
-#define FSCACHE_DEBUG_OBJECT	2
-#define FSCACHE_DEBUG_OPERATION	3
-
-#define FSCACHE_POINT_ENTER	1
-#define FSCACHE_POINT_LEAVE	2
-#define FSCACHE_POINT_DEBUG	4
-
-#ifndef FSCACHE_DEBUG_LEVEL
-#define FSCACHE_DEBUG_LEVEL CACHE
-#endif
-
-/*
- * assertions
- */
-#if 1 /* defined(__KDEBUGALL) */
-
-#define ASSERT(X)							\
-do {									\
-	if (unlikely(!(X))) {						\
-		pr_err("\n");					\
-		pr_err("Assertion failed\n");	\
-		BUG();							\
-	}								\
-} while (0)
-
-#define ASSERTCMP(X, OP, Y)						\
-do {									\
-	if (unlikely(!((X) OP (Y)))) {					\
-		pr_err("\n");					\
-		pr_err("Assertion failed\n");	\
-		pr_err("%lx " #OP " %lx is false\n",		\
-		       (unsigned long)(X), (unsigned long)(Y));		\
-		BUG();							\
-	}								\
-} while (0)
-
-#define ASSERTIF(C, X)							\
-do {									\
-	if (unlikely((C) && !(X))) {					\
-		pr_err("\n");					\
-		pr_err("Assertion failed\n");	\
-		BUG();							\
-	}								\
-} while (0)
-
-#define ASSERTIFCMP(C, X, OP, Y)					\
-do {									\
-	if (unlikely((C) && !((X) OP (Y)))) {				\
-		pr_err("\n");					\
-		pr_err("Assertion failed\n");	\
-		pr_err("%lx " #OP " %lx is false\n",		\
-		       (unsigned long)(X), (unsigned long)(Y));		\
-		BUG();							\
-	}								\
-} while (0)
-
-#else
-
-#define ASSERT(X)			do {} while (0)
-#define ASSERTCMP(X, OP, Y)		do {} while (0)
-#define ASSERTIF(C, X)			do {} while (0)
-#define ASSERTIFCMP(C, X, OP, Y)	do {} while (0)
-
-#endif /* assert or not */
diff --git a/fs/netfs/fscache_main.c b/fs/netfs/fscache_main.c
index dad85fd84f6f9..00600a4d9ce55 100644
--- a/fs/netfs/fscache_main.c
+++ b/fs/netfs/fscache_main.c
@@ -8,18 +8,9 @@
 #define FSCACHE_DEBUG_LEVEL CACHE
 #include <linux/module.h>
 #include <linux/init.h>
-#define CREATE_TRACE_POINTS
 #include "internal.h"
-
-MODULE_DESCRIPTION("FS Cache Manager");
-MODULE_AUTHOR("Red Hat, Inc.");
-MODULE_LICENSE("GPL");
-
-unsigned fscache_debug;
-module_param_named(debug, fscache_debug, uint,
-		   S_IWUSR | S_IRUGO);
-MODULE_PARM_DESC(fscache_debug,
-		 "FS-Cache debugging mask");
+#define CREATE_TRACE_POINTS
+#include <trace/events/fscache.h>
 
 EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache);
 EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume);
@@ -92,7 +83,7 @@ static int __init fscache_init(void)
 		goto error_cookie_jar;
 	}
 
-	pr_notice("Loaded\n");
+	pr_notice("FS-Cache loaded\n");
 	return 0;
 
 error_cookie_jar:
@@ -115,7 +106,7 @@ static void __exit fscache_exit(void)
 	kmem_cache_destroy(fscache_cookie_jar);
 	fscache_proc_cleanup();
 	destroy_workqueue(fscache_wq);
-	pr_notice("Unloaded\n");
+	pr_notice("FS-Cache unloaded\n");
 }
 
 module_exit(fscache_exit);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index e96432499eb2a..43769ac606e81 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -9,8 +9,9 @@
 #include <linux/seq_file.h>
 #include <linux/netfs.h>
 #include <linux/fscache.h>
+#include <linux/fscache-cache.h>
 #include <trace/events/netfs.h>
-#include "fscache_internal.h"
+#include <trace/events/fscache.h>
 
 #ifdef pr_fmt
 #undef pr_fmt
@@ -106,11 +107,143 @@ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx)
 #endif
 }
 
+/*
+ * fscache-cache.c
+ */
+#ifdef CONFIG_PROC_FS
+extern const struct seq_operations fscache_caches_seq_ops;
+#endif
+bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why);
+void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why);
+struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache);
+void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where);
+
+static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache)
+{
+	return smp_load_acquire(&cache->state);
+}
+
+static inline bool fscache_cache_is_live(const struct fscache_cache *cache)
+{
+	return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE;
+}
+
+static inline void fscache_set_cache_state(struct fscache_cache *cache,
+					   enum fscache_cache_state new_state)
+{
+	smp_store_release(&cache->state, new_state);
+
+}
+
+static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache,
+						 enum fscache_cache_state old_state,
+						 enum fscache_cache_state new_state)
+{
+	return try_cmpxchg_release(&cache->state, &old_state, new_state);
+}
+
+/*
+ * fscache-cookie.c
+ */
+extern struct kmem_cache *fscache_cookie_jar;
+#ifdef CONFIG_PROC_FS
+extern const struct seq_operations fscache_cookies_seq_ops;
+#endif
+extern struct timer_list fscache_cookie_lru_timer;
+
+extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix);
+extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie,
+					enum fscache_access_trace why);
+
+static inline void fscache_see_cookie(struct fscache_cookie *cookie,
+				      enum fscache_cookie_trace where)
+{
+	trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref),
+			     where);
+}
+
+/*
+ * fscache-main.c
+ */
+extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len);
+
+/*
+ * fscache-proc.c
+ */
+#ifdef CONFIG_PROC_FS
+extern int __init fscache_proc_init(void);
+extern void fscache_proc_cleanup(void);
+#else
+#define fscache_proc_init()	(0)
+#define fscache_proc_cleanup()	do {} while (0)
+#endif
+
+/*
+ * fscache-stats.c
+ */
+#ifdef CONFIG_FSCACHE_STATS
+extern atomic_t fscache_n_volumes;
+extern atomic_t fscache_n_volumes_collision;
+extern atomic_t fscache_n_volumes_nomem;
+extern atomic_t fscache_n_cookies;
+extern atomic_t fscache_n_cookies_lru;
+extern atomic_t fscache_n_cookies_lru_expired;
+extern atomic_t fscache_n_cookies_lru_removed;
+extern atomic_t fscache_n_cookies_lru_dropped;
+
+extern atomic_t fscache_n_acquires;
+extern atomic_t fscache_n_acquires_ok;
+extern atomic_t fscache_n_acquires_oom;
+
+extern atomic_t fscache_n_invalidates;
+
+extern atomic_t fscache_n_relinquishes;
+extern atomic_t fscache_n_relinquishes_retire;
+extern atomic_t fscache_n_relinquishes_dropped;
+
+extern atomic_t fscache_n_resizes;
+extern atomic_t fscache_n_resizes_null;
+
+static inline void fscache_stat(atomic_t *stat)
+{
+	atomic_inc(stat);
+}
+
+static inline void fscache_stat_d(atomic_t *stat)
+{
+	atomic_dec(stat);
+}
+
+#define __fscache_stat(stat) (stat)
+
+int fscache_stats_show(struct seq_file *m, void *v);
+#else
+
+#define __fscache_stat(stat) (NULL)
+#define fscache_stat(stat) do {} while (0)
+#define fscache_stat_d(stat) do {} while (0)
+#endif
+
+/*
+ * fscache-volume.c
+ */
+#ifdef CONFIG_PROC_FS
+extern const struct seq_operations fscache_volumes_seq_ops;
+#endif
+
+struct fscache_volume *fscache_get_volume(struct fscache_volume *volume,
+					  enum fscache_volume_trace where);
+void fscache_put_volume(struct fscache_volume *volume,
+			enum fscache_volume_trace where);
+bool fscache_begin_volume_access(struct fscache_volume *volume,
+				 struct fscache_cookie *cookie,
+				 enum fscache_access_trace why);
+void fscache_create_volume(struct fscache_volume *volume, bool wait);
+
 /*****************************************************************************/
 /*
  * debug tracing
  */
-#if 0
 #define dbgprintk(FMT, ...) \
 	printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
 
@@ -147,4 +280,57 @@ do {						\
 #define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
 #define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
 #endif
-#endif
+
+/*
+ * assertions
+ */
+#if 1 /* defined(__KDEBUGALL) */
+
+#define ASSERT(X)							\
+do {									\
+	if (unlikely(!(X))) {						\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		pr_err("%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIF(C, X)							\
+do {									\
+	if (unlikely((C) && !(X))) {					\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIFCMP(C, X, OP, Y)					\
+do {									\
+	if (unlikely((C) && !((X) OP (Y)))) {				\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		pr_err("%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#else
+
+#define ASSERT(X)			do {} while (0)
+#define ASSERTCMP(X, OP, Y)		do {} while (0)
+#define ASSERTIF(C, X)			do {} while (0)
+#define ASSERTIFCMP(C, X, OP, Y)	do {} while (0)
+
+#endif /* assert or not */
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 237c54a01d971..1ba8091fcf3ec 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -8,8 +8,8 @@
 #include <linux/module.h>
 #include <linux/export.h>
 #include "internal.h"
-//#define CREATE_TRACE_POINTS
-//#include <trace/events/netfs.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/netfs.h>
 
 MODULE_DESCRIPTION("Network fs support");
 MODULE_AUTHOR("Red Hat, Inc.");
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 01ac733a63203..f7e32d76e34d7 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -169,8 +169,8 @@ config ROOT_NFS
 
 config NFS_FSCACHE
 	bool "Provide NFS client caching support"
-	depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y
-	select NETFS_SUPPORT
+	depends on NFS_FS=m && NETFS_SUPPORT || NFS_FS=y && NETFS_SUPPORT=y
+	select FSCACHE
 	help
 	  Say Y here if you want NFS data to be cached locally on disc through
 	  the general filesystem cache manager
-- 
GitLab


From 4498a8eccc97de3d65f876b6fdeddb439ef73abc Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 20 Nov 2023 17:09:47 +0000
Subject: [PATCH 1903/4076] netfs, fscache: Remove ->begin_cache_operation

Remove ->begin_cache_operation() in favour of just calling fscache directly.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Christian Brauner <christian@brauner.io>
cc: linux-fsdevel@vger.kernel.org
cc: linux-cachefs@redhat.com
---
 Documentation/filesystems/netfs_library.rst | 23 +++-----------
 fs/9p/vfs_addr.c                            | 16 ----------
 fs/afs/file.c                               | 13 --------
 fs/ceph/addr.c                              |  1 -
 fs/ceph/cache.h                             | 12 --------
 fs/netfs/buffered_read.c                    | 33 +++++++++++----------
 fs/nfs/fscache.c                            |  7 -----
 include/linux/fscache.h                     |  3 --
 include/linux/netfs.h                       |  4 +--
 9 files changed, 23 insertions(+), 89 deletions(-)

diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 48b95d04f72d5..4cc657d743f7f 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -295,7 +295,6 @@ through which it can issue requests and negotiate::
 	struct netfs_request_ops {
 		void (*init_request)(struct netfs_io_request *rreq, struct file *file);
 		void (*free_request)(struct netfs_io_request *rreq);
-		int (*begin_cache_operation)(struct netfs_io_request *rreq);
 		void (*expand_readahead)(struct netfs_io_request *rreq);
 		bool (*clamp_length)(struct netfs_io_subrequest *subreq);
 		void (*issue_read)(struct netfs_io_subrequest *subreq);
@@ -317,20 +316,6 @@ The operations are as follows:
    [Optional] This is called as the request is being deallocated so that the
    filesystem can clean up any state it has attached there.
 
- * ``begin_cache_operation()``
-
-   [Optional] This is called to ask the network filesystem to call into the
-   cache (if present) to initialise the caching state for this read.  The netfs
-   library module cannot access the cache directly, so the cache should call
-   something like fscache_begin_read_operation() to do this.
-
-   The cache gets to store its state in ->cache_resources and must set a table
-   of operations of its own there (though of a different type).
-
-   This should return 0 on success and an error code otherwise.  If an error is
-   reported, the operation may proceed anyway, just without local caching (only
-   out of memory and interruption errors cause failure here).
-
  * ``expand_readahead()``
 
    [Optional] This is called to allow the filesystem to expand the size of a
@@ -460,14 +445,14 @@ When implementing a local cache to be used by the read helpers, two things are
 required: some way for the network filesystem to initialise the caching for a
 read request and a table of operations for the helpers to call.
 
-The network filesystem's ->begin_cache_operation() method is called to set up a
-cache and this must call into the cache to do the work.  If using fscache, for
-example, the cache would call::
+To begin a cache operation on an fscache object, the following function is
+called::
 
 	int fscache_begin_read_operation(struct netfs_io_request *rreq,
 					 struct fscache_cookie *cookie);
 
-passing in the request pointer and the cookie corresponding to the file.
+passing in the request pointer and the cookie corresponding to the file.  This
+fills in the cache resources mentioned below.
 
 The netfs_io_request object contains a place for the cache to hang its
 state::
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 8a635999a7d61..39db7c01e30af 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -82,25 +82,9 @@ static void v9fs_free_request(struct netfs_io_request *rreq)
 	p9_fid_put(fid);
 }
 
-/**
- * v9fs_begin_cache_operation - Begin a cache operation for a read
- * @rreq: The read request
- */
-static int v9fs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-#ifdef CONFIG_9P_FSCACHE
-	struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode));
-
-	return fscache_begin_read_operation(&rreq->cache_resources, cookie);
-#else
-	return -ENOBUFS;
-#endif
-}
-
 const struct netfs_request_ops v9fs_req_ops = {
 	.init_request		= v9fs_init_request,
 	.free_request		= v9fs_free_request,
-	.begin_cache_operation	= v9fs_begin_cache_operation,
 	.issue_read		= v9fs_issue_read,
 };
 
diff --git a/fs/afs/file.c b/fs/afs/file.c
index d37dd201752ba..8c17e37c2e59f 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -366,18 +366,6 @@ static int afs_init_request(struct netfs_io_request *rreq, struct file *file)
 	return 0;
 }
 
-static int afs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-#ifdef CONFIG_AFS_FSCACHE
-	struct afs_vnode *vnode = AFS_FS_I(rreq->inode);
-
-	return fscache_begin_read_operation(&rreq->cache_resources,
-					    afs_vnode_cache(vnode));
-#else
-	return -ENOBUFS;
-#endif
-}
-
 static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len,
 				 struct folio **foliop, void **_fsdata)
 {
@@ -394,7 +382,6 @@ static void afs_free_request(struct netfs_io_request *rreq)
 const struct netfs_request_ops afs_req_ops = {
 	.init_request		= afs_init_request,
 	.free_request		= afs_free_request,
-	.begin_cache_operation	= afs_begin_cache_operation,
 	.check_write_begin	= afs_check_write_begin,
 	.issue_read		= afs_issue_read,
 };
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 85be3bf18cdf3..3b8641febeac0 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -509,7 +509,6 @@ static void ceph_netfs_free_request(struct netfs_io_request *rreq)
 const struct netfs_request_ops ceph_netfs_ops = {
 	.init_request		= ceph_init_request,
 	.free_request		= ceph_netfs_free_request,
-	.begin_cache_operation	= ceph_begin_cache_operation,
 	.issue_read		= ceph_netfs_issue_read,
 	.expand_readahead	= ceph_netfs_expand_readahead,
 	.clamp_length		= ceph_netfs_clamp_length,
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index dc502daac49ab..b804f10947647 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -57,13 +57,6 @@ static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
 	return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci));
 }
 
-static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(rreq->inode));
-
-	return fscache_begin_read_operation(&rreq->cache_resources, cookie);
-}
-
 static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
 	return fscache_cookie_enabled(ceph_fscache_cookie(ceph_inode(inode)));
@@ -135,11 +128,6 @@ static inline bool ceph_is_cache_enabled(struct inode *inode)
 	return false;
 }
 
-static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	return -ENOBUFS;
-}
-
 static inline void ceph_fscache_note_page_release(struct inode *inode)
 {
 }
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 2cd3ccf4c4399..d39d0ffe75d2d 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -147,6 +147,15 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq,
 	}
 }
 
+/*
+ * Begin an operation, and fetch the stored zero point value from the cookie if
+ * available.
+ */
+static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx)
+{
+	return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx));
+}
+
 /**
  * netfs_readahead - Helper to manage a read request
  * @ractl: The description of the readahead request
@@ -180,11 +189,9 @@ void netfs_readahead(struct readahead_control *ractl)
 	if (IS_ERR(rreq))
 		return;
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto cleanup_free;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto cleanup_free;
 
 	netfs_stat(&netfs_n_rh_readahead);
 	trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl),
@@ -238,11 +245,9 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 		goto alloc_error;
 	}
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto discard;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto discard;
 
 	netfs_stat(&netfs_n_rh_readpage);
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
@@ -390,11 +395,9 @@ retry:
 	rreq->no_unlock_folio	= folio_index(folio);
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto error_put;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto error_put;
 
 	netfs_stat(&netfs_n_rh_write_begin);
 	trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index b05717fe0d4e4..2d1bfee225c36 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -274,12 +274,6 @@ static void nfs_netfs_free_request(struct netfs_io_request *rreq)
 	put_nfs_open_context(rreq->netfs_priv);
 }
 
-static inline int nfs_netfs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	return fscache_begin_read_operation(&rreq->cache_resources,
-					    netfs_i_cookie(netfs_inode(rreq->inode)));
-}
-
 static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq)
 {
 	struct nfs_netfs_io_data *netfs;
@@ -387,7 +381,6 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
 const struct netfs_request_ops nfs_netfs_ops = {
 	.init_request		= nfs_netfs_init_request,
 	.free_request		= nfs_netfs_free_request,
-	.begin_cache_operation	= nfs_netfs_begin_cache_operation,
 	.issue_read		= nfs_netfs_issue_read,
 	.clamp_length		= nfs_netfs_clamp_length
 };
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 8e312c8323a8e..9ed6696aee7ab 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -437,9 +437,6 @@ const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_r
  * indicates the cache resources to which the operation state should be
  * attached; @cookie indicates the cache object that will be accessed.
  *
- * This is intended to be called from the ->begin_cache_operation() netfs lib
- * operation as implemented by the network filesystem.
- *
  * @cres->inval_counter is set from @cookie->inval_counter for comparison at
  * the end of the operation.  This allows invalidation during the operation to
  * be detected by the caller.
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index b11a84f6c32b7..d294ff8f9ae45 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -208,7 +208,6 @@ struct netfs_io_request {
 struct netfs_request_ops {
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
 	void (*free_request)(struct netfs_io_request *rreq);
-	int (*begin_cache_operation)(struct netfs_io_request *rreq);
 
 	void (*expand_readahead)(struct netfs_io_request *rreq);
 	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
@@ -229,8 +228,7 @@ enum netfs_read_from_hole {
 };
 
 /*
- * Table of operations for access to a cache.  This is obtained by
- * rreq->ops->begin_cache_operation().
+ * Table of operations for access to a cache.
  */
 struct netfs_cache_ops {
 	/* End an operation */
-- 
GitLab


From 7eb5b3e3a0a55f2d166ca949ef47ca6e0c704aab Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 21 Nov 2023 15:43:52 +0000
Subject: [PATCH 1904/4076] netfs, fscache: Move /proc/fs/fscache to
 /proc/fs/netfs and put in a symlink

Rename /proc/fs/fscache to "netfs" and make a symlink from fscache to that.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Christian Brauner <christian@brauner.io>
cc: linux-fsdevel@vger.kernel.org
cc: linux-cachefs@redhat.com
---
 fs/netfs/fscache_main.c  |  8 ++------
 fs/netfs/fscache_proc.c  | 23 ++++++++---------------
 fs/netfs/fscache_stats.c |  4 +---
 fs/netfs/internal.h      | 12 +++++++++++-
 fs/netfs/main.c          | 33 +++++++++++++++++++++++++++++++++
 fs/netfs/stats.c         | 13 +++++++------
 include/linux/netfs.h    |  1 -
 7 files changed, 62 insertions(+), 32 deletions(-)

diff --git a/fs/netfs/fscache_main.c b/fs/netfs/fscache_main.c
index 00600a4d9ce55..42e98bb523e36 100644
--- a/fs/netfs/fscache_main.c
+++ b/fs/netfs/fscache_main.c
@@ -62,7 +62,7 @@ unsigned int fscache_hash(unsigned int salt, const void *data, size_t len)
 /*
  * initialise the fs caching module
  */
-static int __init fscache_init(void)
+int __init fscache_init(void)
 {
 	int ret = -ENOMEM;
 
@@ -94,12 +94,10 @@ error_wq:
 	return ret;
 }
 
-fs_initcall(fscache_init);
-
 /*
  * clean up on module removal
  */
-static void __exit fscache_exit(void)
+void __exit fscache_exit(void)
 {
 	_enter("");
 
@@ -108,5 +106,3 @@ static void __exit fscache_exit(void)
 	destroy_workqueue(fscache_wq);
 	pr_notice("FS-Cache unloaded\n");
 }
-
-module_exit(fscache_exit);
diff --git a/fs/netfs/fscache_proc.c b/fs/netfs/fscache_proc.c
index dc3b0e9c8cce8..ecd0d1edafaa4 100644
--- a/fs/netfs/fscache_proc.c
+++ b/fs/netfs/fscache_proc.c
@@ -12,41 +12,34 @@
 #include "internal.h"
 
 /*
- * initialise the /proc/fs/fscache/ directory
+ * Add files to /proc/fs/netfs/.
  */
 int __init fscache_proc_init(void)
 {
-	if (!proc_mkdir("fs/fscache", NULL))
-		goto error_dir;
+	if (!proc_symlink("fs/fscache", NULL, "../netfs"))
+		goto error_sym;
 
-	if (!proc_create_seq("fs/fscache/caches", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/caches", S_IFREG | 0444, NULL,
 			     &fscache_caches_seq_ops))
 		goto error;
 
-	if (!proc_create_seq("fs/fscache/volumes", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/volumes", S_IFREG | 0444, NULL,
 			     &fscache_volumes_seq_ops))
 		goto error;
 
-	if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/cookies", S_IFREG | 0444, NULL,
 			     &fscache_cookies_seq_ops))
 		goto error;
-
-#ifdef CONFIG_FSCACHE_STATS
-	if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL,
-				fscache_stats_show))
-		goto error;
-#endif
-
 	return 0;
 
 error:
 	remove_proc_entry("fs/fscache", NULL);
-error_dir:
+error_sym:
 	return -ENOMEM;
 }
 
 /*
- * clean up the /proc/fs/fscache/ directory
+ * Clean up the /proc/fs/fscache symlink.
  */
 void fscache_proc_cleanup(void)
 {
diff --git a/fs/netfs/fscache_stats.c b/fs/netfs/fscache_stats.c
index fc94e5e79f1c6..aad812ead398f 100644
--- a/fs/netfs/fscache_stats.c
+++ b/fs/netfs/fscache_stats.c
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(fscache_n_culled);
 /*
  * display the general statistics
  */
-int fscache_stats_show(struct seq_file *m, void *v)
+int fscache_stats_show(struct seq_file *m)
 {
 	seq_puts(m, "FS-Cache statistics\n");
 	seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n",
@@ -96,7 +96,5 @@ int fscache_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "IO     : rd=%u wr=%u\n",
 		   atomic_read(&fscache_n_read),
 		   atomic_read(&fscache_n_write));
-
-	netfs_stats_show(m);
 	return 0;
 }
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 43769ac606e81..3f6e222294339 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -76,6 +76,7 @@ extern atomic_t netfs_n_rh_write_done;
 extern atomic_t netfs_n_rh_write_failed;
 extern atomic_t netfs_n_rh_write_zskip;
 
+int netfs_stats_show(struct seq_file *m, void *v);
 
 static inline void netfs_stat(atomic_t *stat)
 {
@@ -166,6 +167,13 @@ static inline void fscache_see_cookie(struct fscache_cookie *cookie,
  * fscache-main.c
  */
 extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len);
+#ifdef CONFIG_FSCACHE
+int __init fscache_init(void);
+void __exit fscache_exit(void);
+#else
+static inline int fscache_init(void) { return 0; }
+static inline void fscache_exit(void) {}
+#endif
 
 /*
  * fscache-proc.c
@@ -216,12 +224,14 @@ static inline void fscache_stat_d(atomic_t *stat)
 
 #define __fscache_stat(stat) (stat)
 
-int fscache_stats_show(struct seq_file *m, void *v);
+int fscache_stats_show(struct seq_file *m);
 #else
 
 #define __fscache_stat(stat) (NULL)
 #define fscache_stat(stat) do {} while (0)
 #define fscache_stat_d(stat) do {} while (0)
+
+static inline int fscache_stats_show(struct seq_file *m) { return 0; }
 #endif
 
 /*
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 1ba8091fcf3ec..c9af6e0896d31 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -7,6 +7,8 @@
 
 #include <linux/module.h>
 #include <linux/export.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include "internal.h"
 #define CREATE_TRACE_POINTS
 #include <trace/events/netfs.h>
@@ -19,3 +21,34 @@ unsigned netfs_debug;
 module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
 
+static int __init netfs_init(void)
+{
+	int ret = -ENOMEM;
+
+	if (!proc_mkdir("fs/netfs", NULL))
+		goto error;
+
+#ifdef CONFIG_FSCACHE_STATS
+	if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL,
+				netfs_stats_show))
+		goto error_proc;
+#endif
+
+	ret = fscache_init();
+	if (ret < 0)
+		goto error_proc;
+	return 0;
+
+error_proc:
+	remove_proc_entry("fs/netfs", NULL);
+error:
+	return ret;
+}
+fs_initcall(netfs_init);
+
+static void __exit netfs_exit(void)
+{
+	fscache_exit();
+	remove_proc_entry("fs/netfs", NULL);
+}
+module_exit(netfs_exit);
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index 5510a7a14a40d..6025dc485f7ea 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -28,31 +28,32 @@ atomic_t netfs_n_rh_write_done;
 atomic_t netfs_n_rh_write_failed;
 atomic_t netfs_n_rh_write_zskip;
 
-void netfs_stats_show(struct seq_file *m)
+int netfs_stats_show(struct seq_file *m, void *v)
 {
-	seq_printf(m, "RdHelp : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+	seq_printf(m, "Netfs  : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
 		   atomic_read(&netfs_n_rh_readahead),
 		   atomic_read(&netfs_n_rh_readpage),
 		   atomic_read(&netfs_n_rh_write_begin),
 		   atomic_read(&netfs_n_rh_write_zskip),
 		   atomic_read(&netfs_n_rh_rreq),
 		   atomic_read(&netfs_n_rh_sreq));
-	seq_printf(m, "RdHelp : ZR=%u sh=%u sk=%u\n",
+	seq_printf(m, "Netfs  : ZR=%u sh=%u sk=%u\n",
 		   atomic_read(&netfs_n_rh_zero),
 		   atomic_read(&netfs_n_rh_short_read),
 		   atomic_read(&netfs_n_rh_write_zskip));
-	seq_printf(m, "RdHelp : DL=%u ds=%u df=%u di=%u\n",
+	seq_printf(m, "Netfs  : DL=%u ds=%u df=%u di=%u\n",
 		   atomic_read(&netfs_n_rh_download),
 		   atomic_read(&netfs_n_rh_download_done),
 		   atomic_read(&netfs_n_rh_download_failed),
 		   atomic_read(&netfs_n_rh_download_instead));
-	seq_printf(m, "RdHelp : RD=%u rs=%u rf=%u\n",
+	seq_printf(m, "Netfs  : RD=%u rs=%u rf=%u\n",
 		   atomic_read(&netfs_n_rh_read),
 		   atomic_read(&netfs_n_rh_read_done),
 		   atomic_read(&netfs_n_rh_read_failed));
-	seq_printf(m, "RdHelp : WR=%u ws=%u wf=%u\n",
+	seq_printf(m, "Netfs  : WR=%u ws=%u wf=%u\n",
 		   atomic_read(&netfs_n_rh_write),
 		   atomic_read(&netfs_n_rh_write_done),
 		   atomic_read(&netfs_n_rh_write_failed));
+	return fscache_stats_show(m);
 }
 EXPORT_SYMBOL(netfs_stats_show);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d294ff8f9ae45..9bd91cd615d51 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -294,7 +294,6 @@ void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
 void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 			  bool was_async, enum netfs_sreq_ref_trace what);
-void netfs_stats_show(struct seq_file *);
 ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
-- 
GitLab


From c9c4ff12df110feb1b91951010f673f4b16e49e8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 27 Nov 2023 13:58:07 +0000
Subject: [PATCH 1905/4076] netfs: Move pinning-for-writeback from fscache to
 netfs

Move the resource pinning-for-writeback from fscache code to netfslib code.
This is used to keep a cache backing object pinned whilst we have dirty
pages on the netfs inode in the pagecache such that VM writeback will be
able to reach it.

Whilst we're at it, switch the parameters of netfs_unpin_writeback() to
match ->write_inode() so that it can be used for that directly.

Note that this mechanism could be more generically useful than that for
network filesystems.  Quite often they have to keep around other resources
(e.g. authentication tokens or network connections) until the writeback is
complete.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/9p/vfs_addr.c          | 33 ++++-----------
 fs/9p/vfs_inode.c         |  3 +-
 fs/9p/vfs_super.c         | 14 +------
 fs/afs/file.c             |  8 +---
 fs/afs/inode.c            |  2 +-
 fs/afs/internal.h         |  6 ---
 fs/afs/super.c            |  2 +-
 fs/afs/write.c            |  9 ----
 fs/ceph/cache.h           | 23 ++++-------
 fs/ceph/inode.c           |  2 +-
 fs/fs-writeback.c         | 10 ++---
 fs/netfs/Makefile         |  1 +
 fs/netfs/fscache_io.c     | 40 ------------------
 fs/netfs/misc.c           | 86 +++++++++++++++++++++++++++++++++++++++
 fs/smb/client/cifsfs.c    |  5 +--
 fs/smb/client/file.c      | 18 +-------
 include/linux/fs.h        |  2 +-
 include/linux/fscache.h   | 42 -------------------
 include/linux/netfs.h     |  3 ++
 include/linux/writeback.h |  2 +-
 20 files changed, 124 insertions(+), 187 deletions(-)
 create mode 100644 fs/netfs/misc.c

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 39db7c01e30af..131b83c31f85d 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -317,30 +317,15 @@ out:
 	return copied;
 }
 
-#ifdef CONFIG_9P_FSCACHE
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	struct v9fs_inode *v9inode = V9FS_I(mapping->host);
-
-	return fscache_dirty_folio(mapping, folio, v9fs_inode_cookie(v9inode));
-}
-#else
-#define v9fs_dirty_folio filemap_dirty_folio
-#endif
-
 const struct address_space_operations v9fs_addr_operations = {
-	.read_folio = netfs_read_folio,
-	.readahead = netfs_readahead,
-	.dirty_folio = v9fs_dirty_folio,
-	.writepage = v9fs_vfs_writepage,
-	.write_begin = v9fs_write_begin,
-	.write_end = v9fs_write_end,
-	.release_folio = v9fs_release_folio,
+	.read_folio	= netfs_read_folio,
+	.readahead	= netfs_readahead,
+	.dirty_folio	= netfs_dirty_folio,
+	.writepage	= v9fs_vfs_writepage,
+	.write_begin	= v9fs_write_begin,
+	.write_end	= v9fs_write_end,
+	.release_folio	= v9fs_release_folio,
 	.invalidate_folio = v9fs_invalidate_folio,
-	.launder_folio = v9fs_launder_folio,
-	.direct_IO = v9fs_direct_IO,
+	.launder_folio	= v9fs_launder_folio,
+	.direct_IO	= v9fs_direct_IO,
 };
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b845ee18a80be..74122540e00f2 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -376,8 +376,7 @@ void v9fs_evict_inode(struct inode *inode)
 
 #ifdef CONFIG_9P_FSCACHE
 	version = cpu_to_le32(v9inode->qid.version);
-	fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode,
-				      &version);
+	netfs_clear_inode_writeback(inode, &version);
 #endif
 
 	clear_inode(inode);
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 73db55c050bf1..941f7d0e0bfa2 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -289,31 +289,21 @@ static int v9fs_drop_inode(struct inode *inode)
 static int v9fs_write_inode(struct inode *inode,
 			    struct writeback_control *wbc)
 {
-	struct v9fs_inode *v9inode;
-
 	/*
 	 * send an fsync request to server irrespective of
 	 * wbc->sync_mode.
 	 */
 	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
-
-	v9inode = V9FS_I(inode);
-	fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode));
-
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static int v9fs_write_inode_dotl(struct inode *inode,
 				 struct writeback_control *wbc)
 {
-	struct v9fs_inode *v9inode;
 
-	v9inode = V9FS_I(inode);
 	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
 
-	fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode));
-
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static const struct super_operations v9fs_super_ops = {
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 8c17e37c2e59f..9142fda7dbd6c 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -55,7 +55,7 @@ const struct inode_operations afs_file_inode_operations = {
 const struct address_space_operations afs_file_aops = {
 	.read_folio	= netfs_read_folio,
 	.readahead	= netfs_readahead,
-	.dirty_folio	= afs_dirty_folio,
+	.dirty_folio	= netfs_dirty_folio,
 	.launder_folio	= afs_launder_folio,
 	.release_folio	= afs_release_folio,
 	.invalidate_folio = afs_invalidate_folio,
@@ -386,12 +386,6 @@ const struct netfs_request_ops afs_req_ops = {
 	.issue_read		= afs_issue_read,
 };
 
-int afs_write_inode(struct inode *inode, struct writeback_control *wbc)
-{
-	fscache_unpin_writeback(wbc, afs_vnode_cache(AFS_FS_I(inode)));
-	return 0;
-}
-
 /*
  * Adjust the dirty region of the page on truncation or full invalidation,
  * getting rid of the markers altogether if the region is entirely invalidated.
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 78efc97193493..6f375f0cf650d 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -823,7 +823,7 @@ void afs_evict_inode(struct inode *inode)
 	truncate_inode_pages_final(&inode->i_data);
 
 	afs_set_cache_aux(vnode, &aux);
-	fscache_clear_inode_writeback(afs_vnode_cache(vnode), inode, &aux);
+	netfs_clear_inode_writeback(inode, &aux);
 	clear_inode(inode);
 
 	while (!list_empty(&vnode->wb_keys)) {
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 7385d62c8cf50..b77797559e27c 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1073,7 +1073,6 @@ extern int afs_release(struct inode *, struct file *);
 extern int afs_fetch_data(struct afs_vnode *, struct afs_read *);
 extern struct afs_read *afs_alloc_read(gfp_t);
 extern void afs_put_read(struct afs_read *);
-extern int afs_write_inode(struct inode *, struct writeback_control *);
 
 static inline struct afs_read *afs_get_read(struct afs_read *req)
 {
@@ -1522,11 +1521,6 @@ extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *);
 /*
  * write.c
  */
-#ifdef CONFIG_AFS_FSCACHE
-bool afs_dirty_folio(struct address_space *, struct folio *);
-#else
-#define afs_dirty_folio filemap_dirty_folio
-#endif
 extern int afs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata);
diff --git a/fs/afs/super.c b/fs/afs/super.c
index a01a0fb2cdbb5..4f1b0492f1c5d 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -55,7 +55,7 @@ int afs_net_id;
 static const struct super_operations afs_super_ops = {
 	.statfs		= afs_statfs,
 	.alloc_inode	= afs_alloc_inode,
-	.write_inode	= afs_write_inode,
+	.write_inode	= netfs_unpin_writeback,
 	.drop_inode	= afs_drop_inode,
 	.destroy_inode	= afs_destroy_inode,
 	.free_inode	= afs_free_inode,
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 4a168781936b5..e40cf8e7543ab 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -23,15 +23,6 @@ static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len
 			       loff_t i_size, bool caching);
 
 #ifdef CONFIG_AFS_FSCACHE
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-bool afs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	return fscache_dirty_folio(mapping, folio,
-				afs_vnode_cache(AFS_FS_I(mapping->host)));
-}
 static void afs_folio_start_fscache(bool caching, struct folio *folio)
 {
 	if (caching)
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index b804f10947647..8fc7d828d9903 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -43,19 +43,13 @@ static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
 	}
 }
 
-static inline void ceph_fscache_unpin_writeback(struct inode *inode,
+static inline int ceph_fscache_unpin_writeback(struct inode *inode,
 						struct writeback_control *wbc)
 {
-	fscache_unpin_writeback(wbc, ceph_fscache_cookie(ceph_inode(inode)));
+	return netfs_unpin_writeback(inode, wbc);
 }
 
-static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
-		struct folio *folio)
-{
-	struct ceph_inode_info *ci = ceph_inode(mapping->host);
-
-	return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci));
-}
+#define ceph_fscache_dirty_folio netfs_dirty_folio
 
 static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
@@ -112,16 +106,13 @@ static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
 {
 }
 
-static inline void ceph_fscache_unpin_writeback(struct inode *inode,
-						struct writeback_control *wbc)
+static inline int ceph_fscache_unpin_writeback(struct inode *inode,
+					       struct writeback_control *wbc)
 {
+	return 0;
 }
 
-static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
-		struct folio *folio)
-{
-	return filemap_dirty_folio(mapping, folio);
-}
+#define ceph_fscache_dirty_folio filemap_dirty_folio
 
 static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 0679240f06db9..3149d79a9dbe5 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -694,7 +694,7 @@ void ceph_evict_inode(struct inode *inode)
 	percpu_counter_dec(&mdsc->metric.total_inodes);
 
 	truncate_inode_pages_final(&inode->i_data);
-	if (inode->i_state & I_PINNING_FSCACHE_WB)
+	if (inode->i_state & I_PINNING_NETFS_WB)
 		ceph_fscache_unuse_cookie(inode, true);
 	clear_inode(inode);
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1767493dffda7..3d84fcc471c60 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1675,11 +1675,11 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
 	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		inode->i_state |= I_DIRTY_PAGES;
-	else if (unlikely(inode->i_state & I_PINNING_FSCACHE_WB)) {
+	else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) {
 		if (!(inode->i_state & I_DIRTY_PAGES)) {
-			inode->i_state &= ~I_PINNING_FSCACHE_WB;
-			wbc->unpinned_fscache_wb = true;
-			dirty |= I_PINNING_FSCACHE_WB; /* Cause write_inode */
+			inode->i_state &= ~I_PINNING_NETFS_WB;
+			wbc->unpinned_netfs_wb = true;
+			dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */
 		}
 	}
 
@@ -1691,7 +1691,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 		if (ret == 0)
 			ret = err;
 	}
-	wbc->unpinned_fscache_wb = false;
+	wbc->unpinned_netfs_wb = false;
 	trace_writeback_single_inode(inode, wbc, nr_to_write);
 	return ret;
 }
diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index b57162ef9cfb3..a84fe9bbd3c4e 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -5,6 +5,7 @@ netfs-y := \
 	io.o \
 	iterator.o \
 	main.o \
+	misc.o \
 	objects.o
 
 netfs-$(CONFIG_NETFS_STATS) += stats.o
diff --git a/fs/netfs/fscache_io.c b/fs/netfs/fscache_io.c
index 0d2b8dec8f82c..79171a6879304 100644
--- a/fs/netfs/fscache_io.c
+++ b/fs/netfs/fscache_io.c
@@ -158,46 +158,6 @@ int __fscache_begin_write_operation(struct netfs_cache_resources *cres,
 }
 EXPORT_SYMBOL(__fscache_begin_write_operation);
 
-/**
- * fscache_dirty_folio - Mark folio dirty and pin a cache object for writeback
- * @mapping: The mapping the folio belongs to.
- * @folio: The folio being dirtied.
- * @cookie: The cookie referring to the cache object
- *
- * Set the dirty flag on a folio and pin an in-use cache object in memory
- * so that writeback can later write to it.  This is intended
- * to be called from the filesystem's ->dirty_folio() method.
- *
- * Return: true if the dirty flag was set on the folio, false otherwise.
- */
-bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio,
-				struct fscache_cookie *cookie)
-{
-	struct inode *inode = mapping->host;
-	bool need_use = false;
-
-	_enter("");
-
-	if (!filemap_dirty_folio(mapping, folio))
-		return false;
-	if (!fscache_cookie_valid(cookie))
-		return true;
-
-	if (!(inode->i_state & I_PINNING_FSCACHE_WB)) {
-		spin_lock(&inode->i_lock);
-		if (!(inode->i_state & I_PINNING_FSCACHE_WB)) {
-			inode->i_state |= I_PINNING_FSCACHE_WB;
-			need_use = true;
-		}
-		spin_unlock(&inode->i_lock);
-
-		if (need_use)
-			fscache_use_cookie(cookie, true);
-	}
-	return true;
-}
-EXPORT_SYMBOL(fscache_dirty_folio);
-
 struct fscache_write_request {
 	struct netfs_cache_resources cache_resources;
 	struct address_space	*mapping;
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
new file mode 100644
index 0000000000000..68baf55c47a43
--- /dev/null
+++ b/fs/netfs/misc.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Miscellaneous routines.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/swap.h>
+#include "internal.h"
+
+/**
+ * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback
+ * @mapping: The mapping the folio belongs to.
+ * @folio: The folio being dirtied.
+ *
+ * Set the dirty flag on a folio and pin an in-use cache object in memory so
+ * that writeback can later write to it.  This is intended to be called from
+ * the filesystem's ->dirty_folio() method.
+ *
+ * Return: true if the dirty flag was set on the folio, false otherwise.
+ */
+bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio)
+{
+	struct inode *inode = mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	struct fscache_cookie *cookie = netfs_i_cookie(ictx);
+	bool need_use = false;
+
+	_enter("");
+
+	if (!filemap_dirty_folio(mapping, folio))
+		return false;
+	if (!fscache_cookie_valid(cookie))
+		return true;
+
+	if (!(inode->i_state & I_PINNING_NETFS_WB)) {
+		spin_lock(&inode->i_lock);
+		if (!(inode->i_state & I_PINNING_NETFS_WB)) {
+			inode->i_state |= I_PINNING_NETFS_WB;
+			need_use = true;
+		}
+		spin_unlock(&inode->i_lock);
+
+		if (need_use)
+			fscache_use_cookie(cookie, true);
+	}
+	return true;
+}
+EXPORT_SYMBOL(netfs_dirty_folio);
+
+/**
+ * netfs_unpin_writeback - Unpin writeback resources
+ * @inode: The inode on which the cookie resides
+ * @wbc: The writeback control
+ *
+ * Unpin the writeback resources pinned by netfs_dirty_folio().  This is
+ * intended to be called as/by the netfs's ->write_inode() method.
+ */
+int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc)
+{
+	struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode));
+
+	if (wbc->unpinned_netfs_wb)
+		fscache_unuse_cookie(cookie, NULL, NULL);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_unpin_writeback);
+
+/**
+ * netfs_clear_inode_writeback - Clear writeback resources pinned by an inode
+ * @inode: The inode to clean up
+ * @aux: Auxiliary data to apply to the inode
+ *
+ * Clear any writeback resources held by an inode when the inode is evicted.
+ * This must be called before clear_inode() is called.
+ */
+void netfs_clear_inode_writeback(struct inode *inode, const void *aux)
+{
+	struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode));
+
+	if (inode->i_state & I_PINNING_NETFS_WB) {
+		loff_t i_size = i_size_read(inode);
+		fscache_unuse_cookie(cookie, aux, &i_size);
+	}
+}
+EXPORT_SYMBOL(netfs_clear_inode_writeback);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 2131638f26d0b..96a65cf9b5ec9 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -429,7 +429,7 @@ static void
 cifs_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
-	if (inode->i_state & I_PINNING_FSCACHE_WB)
+	if (inode->i_state & I_PINNING_NETFS_WB)
 		cifs_fscache_unuse_inode_cookie(inode, true);
 	cifs_fscache_release_inode_cookie(inode);
 	clear_inode(inode);
@@ -792,8 +792,7 @@ static int cifs_show_stats(struct seq_file *s, struct dentry *root)
 
 static int cifs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	fscache_unpin_writeback(wbc, cifs_inode_cookie(inode));
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static int cifs_drop_inode(struct inode *inode)
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 32a8525415d96..b02b7f0a47dca 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -5043,27 +5043,13 @@ static void cifs_swap_deactivate(struct file *file)
 	/* do we need to unpin (or unlock) the file */
 }
 
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-#ifdef CONFIG_CIFS_FSCACHE
-static bool cifs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	return fscache_dirty_folio(mapping, folio,
-					cifs_inode_cookie(mapping->host));
-}
-#else
-#define cifs_dirty_folio filemap_dirty_folio
-#endif
-
 const struct address_space_operations cifs_addr_ops = {
 	.read_folio = cifs_read_folio,
 	.readahead = cifs_readahead,
 	.writepages = cifs_writepages,
 	.write_begin = cifs_write_begin,
 	.write_end = cifs_write_end,
-	.dirty_folio = cifs_dirty_folio,
+	.dirty_folio = netfs_dirty_folio,
 	.release_folio = cifs_release_folio,
 	.direct_IO = cifs_direct_io,
 	.invalidate_folio = cifs_invalidate_folio,
@@ -5087,7 +5073,7 @@ const struct address_space_operations cifs_addr_ops_smallbuf = {
 	.writepages = cifs_writepages,
 	.write_begin = cifs_write_begin,
 	.write_end = cifs_write_end,
-	.dirty_folio = cifs_dirty_folio,
+	.dirty_folio = netfs_dirty_folio,
 	.release_folio = cifs_release_folio,
 	.invalidate_folio = cifs_invalidate_folio,
 	.launder_folio = cifs_launder_folio,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e3..68a9572616947 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2294,7 +2294,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
 #define I_CREATING		(1 << 15)
 #define I_DONTCACHE		(1 << 16)
 #define I_SYNC_QUEUED		(1 << 17)
-#define I_PINNING_FSCACHE_WB	(1 << 18)
+#define I_PINNING_NETFS_WB	(1 << 18)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 9ed6696aee7ab..6e8562cbcc432 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -626,48 +626,6 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie,
 
 }
 
-#if __fscache_available
-bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio,
-		struct fscache_cookie *cookie);
-#else
-#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \
-		filemap_dirty_folio(MAPPING, FOLIO)
-#endif
-
-/**
- * fscache_unpin_writeback - Unpin writeback resources
- * @wbc: The writeback control
- * @cookie: The cookie referring to the cache object
- *
- * Unpin the writeback resources pinned by fscache_dirty_folio().  This is
- * intended to be called by the netfs's ->write_inode() method.
- */
-static inline void fscache_unpin_writeback(struct writeback_control *wbc,
-					   struct fscache_cookie *cookie)
-{
-	if (wbc->unpinned_fscache_wb)
-		fscache_unuse_cookie(cookie, NULL, NULL);
-}
-
-/**
- * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode
- * @cookie: The cookie referring to the cache object
- * @inode: The inode to clean up
- * @aux: Auxiliary data to apply to the inode
- *
- * Clear any writeback resources held by an inode when the inode is evicted.
- * This must be called before clear_inode() is called.
- */
-static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie,
-						 struct inode *inode,
-						 const void *aux)
-{
-	if (inode->i_state & I_PINNING_FSCACHE_WB) {
-		loff_t i_size = i_size_read(inode);
-		fscache_unuse_cookie(cookie, aux, &i_size);
-	}
-}
-
 /**
  * fscache_note_page_release - Note that a netfs page got released
  * @cookie: The cookie corresponding to the file
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 9bd91cd615d51..32faf6c897029 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -288,6 +288,9 @@ int netfs_read_folio(struct file *, struct folio *);
 int netfs_write_begin(struct netfs_inode *, struct file *,
 		struct address_space *, loff_t pos, unsigned int len,
 		struct folio **, void **fsdata);
+bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio);
+int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
+void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
 
 void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 083387c00f0c8..1e08392fb43e1 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -60,7 +60,7 @@ struct writeback_control {
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned for_sync:1;		/* sync(2) WB_SYNC_ALL writeback */
-	unsigned unpinned_fscache_wb:1;	/* Cleared I_PINNING_FSCACHE_WB */
+	unsigned unpinned_netfs_wb:1;	/* Cleared I_PINNING_NETFS_WB */
 
 	/*
 	 * When writeback IOs are bounced through async layers, only the
-- 
GitLab


From 87b57a048964abfd5f3d8b79bc55687327f5a380 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 4 Mar 2022 10:34:27 +0000
Subject: [PATCH 1906/4076] netfs: Add a procfile to list in-progress requests

Add a procfile, /proc/fs/netfs/requests, to list in-progress netfslib I/O
requests.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/internal.h   | 22 ++++++++++++++
 fs/netfs/main.c       | 69 ++++++++++++++++++++++++++++++++++++++++++-
 fs/netfs/objects.c    |  4 ++-
 include/linux/netfs.h |  6 +++-
 4 files changed, 98 insertions(+), 3 deletions(-)

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 3f6e222294339..4708fb15446bd 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -33,6 +33,28 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync);
  * main.c
  */
 extern unsigned int netfs_debug;
+extern struct list_head netfs_io_requests;
+extern spinlock_t netfs_proc_lock;
+
+#ifdef CONFIG_PROC_FS
+static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq)
+{
+	spin_lock(&netfs_proc_lock);
+	list_add_tail_rcu(&rreq->proc_link, &netfs_io_requests);
+	spin_unlock(&netfs_proc_lock);
+}
+static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq)
+{
+	if (!list_empty(&rreq->proc_link)) {
+		spin_lock(&netfs_proc_lock);
+		list_del_rcu(&rreq->proc_link);
+		spin_unlock(&netfs_proc_lock);
+	}
+}
+#else
+static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq) {}
+static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {}
+#endif
 
 /*
  * objects.c
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index c9af6e0896d31..97ce1436615b7 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -21,13 +21,80 @@ unsigned netfs_debug;
 module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
 
+#ifdef CONFIG_PROC_FS
+LIST_HEAD(netfs_io_requests);
+DEFINE_SPINLOCK(netfs_proc_lock);
+
+static const char *netfs_origins[] = {
+	[NETFS_READAHEAD]	= "RA",
+	[NETFS_READPAGE]	= "RP",
+	[NETFS_READ_FOR_WRITE]	= "RW",
+};
+
+/*
+ * Generate a list of I/O requests in /proc/fs/netfs/requests
+ */
+static int netfs_requests_seq_show(struct seq_file *m, void *v)
+{
+	struct netfs_io_request *rreq;
+
+	if (v == &netfs_io_requests) {
+		seq_puts(m,
+			 "REQUEST  OR REF FL ERR  OPS COVERAGE\n"
+			 "======== == === == ==== === =========\n"
+			 );
+		return 0;
+	}
+
+	rreq = list_entry(v, struct netfs_io_request, proc_link);
+	seq_printf(m,
+		   "%08x %s %3d %2lx %4d %3d @%04llx %zx/%zx",
+		   rreq->debug_id,
+		   netfs_origins[rreq->origin],
+		   refcount_read(&rreq->ref),
+		   rreq->flags,
+		   rreq->error,
+		   atomic_read(&rreq->nr_outstanding),
+		   rreq->start, rreq->submitted, rreq->len);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void *netfs_requests_seq_start(struct seq_file *m, loff_t *_pos)
+	__acquires(rcu)
+{
+	rcu_read_lock();
+	return seq_list_start_head(&netfs_io_requests, *_pos);
+}
+
+static void *netfs_requests_seq_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+	return seq_list_next(v, &netfs_io_requests, _pos);
+}
+
+static void netfs_requests_seq_stop(struct seq_file *m, void *v)
+	__releases(rcu)
+{
+	rcu_read_unlock();
+}
+
+static const struct seq_operations netfs_requests_seq_ops = {
+	.start  = netfs_requests_seq_start,
+	.next   = netfs_requests_seq_next,
+	.stop   = netfs_requests_seq_stop,
+	.show   = netfs_requests_seq_show,
+};
+#endif /* CONFIG_PROC_FS */
+
 static int __init netfs_init(void)
 {
 	int ret = -ENOMEM;
 
 	if (!proc_mkdir("fs/netfs", NULL))
 		goto error;
-
+	if (!proc_create_seq("fs/netfs/requests", S_IFREG | 0444, NULL,
+			     &netfs_requests_seq_ops))
+		goto error_proc;
 #ifdef CONFIG_FSCACHE_STATS
 	if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL,
 				netfs_stats_show))
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index e17cdf53f6a78..85f428fc52e6f 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -45,6 +45,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 		}
 	}
 
+	netfs_proc_add_rreq(rreq);
 	netfs_stat(&netfs_n_rh_rreq);
 	return rreq;
 }
@@ -76,12 +77,13 @@ static void netfs_free_request(struct work_struct *work)
 		container_of(work, struct netfs_io_request, work);
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
+	netfs_proc_del_rreq(rreq);
 	netfs_clear_subrequests(rreq, false);
 	if (rreq->netfs_ops->free_request)
 		rreq->netfs_ops->free_request(rreq);
 	if (rreq->cache_resources.ops)
 		rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
-	kfree(rreq);
+	kfree_rcu(rreq, rcu);
 	netfs_stat_d(&netfs_n_rh_rreq);
 }
 
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 32faf6c897029..7244ddebd974c 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -175,10 +175,14 @@ enum netfs_io_origin {
  * operations to a variety of data stores and then stitch the result together.
  */
 struct netfs_io_request {
-	struct work_struct	work;
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 	struct inode		*inode;		/* The file being accessed */
 	struct address_space	*mapping;	/* The mapping being accessed */
 	struct netfs_cache_resources cache_resources;
+	struct list_head	proc_link;	/* Link in netfs_iorequests */
 	struct list_head	subrequests;	/* Contributory I/O operations */
 	void			*netfs_priv;	/* Private data for the netfs */
 	unsigned int		debug_id;
-- 
GitLab


From cc3cb0a18da46a51d9fc173155576ba1d068e536 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 9 Mar 2022 11:01:12 +0000
Subject: [PATCH 1907/4076] netfs: Allow the netfs to make the io (sub)request
 alloc larger

Allow the network filesystem to specify extra space to be allocated on the
end of the io (sub)request.  This allows cifs, for example, to use this
space rather than allocating its own cifs_readdata struct.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/objects.c    | 7 +++++--
 include/linux/netfs.h | 2 ++
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 85f428fc52e6f..c4229c5f3f540 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -22,7 +22,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct netfs_io_request *rreq;
 	int ret;
 
-	rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL);
+	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
+		       GFP_KERNEL);
 	if (!rreq)
 		return ERR_PTR(-ENOMEM);
 
@@ -114,7 +115,9 @@ struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq
 {
 	struct netfs_io_subrequest *subreq;
 
-	subreq = kzalloc(sizeof(struct netfs_io_subrequest), GFP_KERNEL);
+	subreq = kzalloc(rreq->netfs_ops->io_subrequest_size ?:
+			 sizeof(struct netfs_io_subrequest),
+			 GFP_KERNEL);
 	if (subreq) {
 		INIT_LIST_HEAD(&subreq->rreq_link);
 		refcount_set(&subreq->ref, 2);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 7244ddebd974c..d6f27000eeb07 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -210,6 +210,8 @@ struct netfs_io_request {
  * Operations the network filesystem can/must provide to the helpers.
  */
 struct netfs_request_ops {
+	unsigned int	io_request_size;	/* Alloc size for netfs_io_request struct */
+	unsigned int	io_subrequest_size;	/* Alloc size for netfs_io_subrequest struct */
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
 	void (*free_request)(struct netfs_io_request *rreq);
 
-- 
GitLab


From 5f5ce7ba15e7e6a6539ac8e1f845757aaebecf0d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 25 Feb 2022 11:19:14 +0000
Subject: [PATCH 1908/4076] netfs: Add a ->free_subrequest() op

Add a ->free_subrequest() op so that the netfs can clean up data attached
to a subrequest.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/objects.c    | 2 ++
 include/linux/netfs.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index c4229c5f3f540..1bd20bdad9836 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -145,6 +145,8 @@ static void netfs_free_subrequest(struct netfs_io_subrequest *subreq,
 	struct netfs_io_request *rreq = subreq->rreq;
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_free);
+	if (rreq->netfs_ops->free_subrequest)
+		rreq->netfs_ops->free_subrequest(subreq);
 	kfree(subreq);
 	netfs_stat_d(&netfs_n_rh_sreq);
 	netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d6f27000eeb07..06f57d9d09f6c 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -214,6 +214,7 @@ struct netfs_request_ops {
 	unsigned int	io_subrequest_size;	/* Alloc size for netfs_io_subrequest struct */
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
 	void (*free_request)(struct netfs_io_request *rreq);
+	void (*free_subrequest)(struct netfs_io_subrequest *rreq);
 
 	void (*expand_readahead)(struct netfs_io_request *rreq);
 	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
-- 
GitLab


From a34847d4b73c3a98b565b1d1cc6e1b70c661e18b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Dec 2022 14:12:41 +0000
Subject: [PATCH 1909/4076] afs: Don't use folio->private to record partial
 modification

AFS currently uses folio->private to store the range of bytes within a
folio that have been modified - the idea being that if we have, say, a 2MiB
folio and someone writes a single byte, we only have to write back that
single page and not the whole 2MiB folio - thereby saving on network
bandwidth.

Remove this, at least for now, and accept the extra network load (which
doesn't matter in the common case of writing a whole file at a time from
beginning to end).

This makes folio->private available for netfslib to use.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/afs/file.c              |  67 -------------
 fs/afs/internal.h          |  56 -----------
 fs/afs/write.c             | 188 ++++++++-----------------------------
 include/trace/events/afs.h |  16 +---
 4 files changed, 42 insertions(+), 285 deletions(-)

diff --git a/fs/afs/file.c b/fs/afs/file.c
index 9142fda7dbd6c..0d783e5b2147b 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -386,63 +386,6 @@ const struct netfs_request_ops afs_req_ops = {
 	.issue_read		= afs_issue_read,
 };
 
-/*
- * Adjust the dirty region of the page on truncation or full invalidation,
- * getting rid of the markers altogether if the region is entirely invalidated.
- */
-static void afs_invalidate_dirty(struct folio *folio, size_t offset,
-				 size_t length)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-	unsigned long priv;
-	unsigned int f, t, end = offset + length;
-
-	priv = (unsigned long)folio_get_private(folio);
-
-	/* we clean up only if the entire page is being invalidated */
-	if (offset == 0 && length == folio_size(folio))
-		goto full_invalidate;
-
-	 /* If the page was dirtied by page_mkwrite(), the PTE stays writable
-	  * and we don't get another notification to tell us to expand it
-	  * again.
-	  */
-	if (afs_is_folio_dirty_mmapped(priv))
-		return;
-
-	/* We may need to shorten the dirty region */
-	f = afs_folio_dirty_from(folio, priv);
-	t = afs_folio_dirty_to(folio, priv);
-
-	if (t <= offset || f >= end)
-		return; /* Doesn't overlap */
-
-	if (f < offset && t > end)
-		return; /* Splits the dirty region - just absorb it */
-
-	if (f >= offset && t <= end)
-		goto undirty;
-
-	if (f < offset)
-		t = offset;
-	else
-		f = end;
-	if (f == t)
-		goto undirty;
-
-	priv = afs_folio_dirty(folio, f, t);
-	folio_change_private(folio, (void *)priv);
-	trace_afs_folio_dirty(vnode, tracepoint_string("trunc"), folio);
-	return;
-
-undirty:
-	trace_afs_folio_dirty(vnode, tracepoint_string("undirty"), folio);
-	folio_clear_dirty_for_io(folio);
-full_invalidate:
-	trace_afs_folio_dirty(vnode, tracepoint_string("inval"), folio);
-	folio_detach_private(folio);
-}
-
 /*
  * invalidate part or all of a page
  * - release a page and clean up its private data if offset is 0 (indicating
@@ -453,11 +396,6 @@ static void afs_invalidate_folio(struct folio *folio, size_t offset,
 {
 	_enter("{%lu},%zu,%zu", folio->index, offset, length);
 
-	BUG_ON(!folio_test_locked(folio));
-
-	if (folio_get_private(folio))
-		afs_invalidate_dirty(folio, offset, length);
-
 	folio_wait_fscache(folio);
 	_leave("");
 }
@@ -485,11 +423,6 @@ static bool afs_release_folio(struct folio *folio, gfp_t gfp)
 	fscache_note_page_release(afs_vnode_cache(vnode));
 #endif
 
-	if (folio_test_private(folio)) {
-		trace_afs_folio_dirty(vnode, tracepoint_string("rel"), folio);
-		folio_detach_private(folio);
-	}
-
 	/* Indicate that the folio can be released */
 	_leave(" = T");
 	return true;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index b77797559e27c..a7c8d1d702ee0 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -894,62 +894,6 @@ static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int fl
 			   i_size_read(&vnode->netfs.inode), flags);
 }
 
-/*
- * We use folio->private to hold the amount of the folio that we've written to,
- * splitting the field into two parts.  However, we need to represent a range
- * 0...FOLIO_SIZE, so we reduce the resolution if the size of the folio
- * exceeds what we can encode.
- */
-#ifdef CONFIG_64BIT
-#define __AFS_FOLIO_PRIV_MASK		0x7fffffffUL
-#define __AFS_FOLIO_PRIV_SHIFT		32
-#define __AFS_FOLIO_PRIV_MMAPPED	0x80000000UL
-#else
-#define __AFS_FOLIO_PRIV_MASK		0x7fffUL
-#define __AFS_FOLIO_PRIV_SHIFT		16
-#define __AFS_FOLIO_PRIV_MMAPPED	0x8000UL
-#endif
-
-static inline unsigned int afs_folio_dirty_resolution(struct folio *folio)
-{
-	int shift = folio_shift(folio) - (__AFS_FOLIO_PRIV_SHIFT - 1);
-	return (shift > 0) ? shift : 0;
-}
-
-static inline size_t afs_folio_dirty_from(struct folio *folio, unsigned long priv)
-{
-	unsigned long x = priv & __AFS_FOLIO_PRIV_MASK;
-
-	/* The lower bound is inclusive */
-	return x << afs_folio_dirty_resolution(folio);
-}
-
-static inline size_t afs_folio_dirty_to(struct folio *folio, unsigned long priv)
-{
-	unsigned long x = (priv >> __AFS_FOLIO_PRIV_SHIFT) & __AFS_FOLIO_PRIV_MASK;
-
-	/* The upper bound is immediately beyond the region */
-	return (x + 1) << afs_folio_dirty_resolution(folio);
-}
-
-static inline unsigned long afs_folio_dirty(struct folio *folio, size_t from, size_t to)
-{
-	unsigned int res = afs_folio_dirty_resolution(folio);
-	from >>= res;
-	to = (to - 1) >> res;
-	return (to << __AFS_FOLIO_PRIV_SHIFT) | from;
-}
-
-static inline unsigned long afs_folio_dirty_mmapped(unsigned long priv)
-{
-	return priv | __AFS_FOLIO_PRIV_MMAPPED;
-}
-
-static inline bool afs_is_folio_dirty_mmapped(unsigned long priv)
-{
-	return priv & __AFS_FOLIO_PRIV_MMAPPED;
-}
-
 #include <trace/events/afs.h>
 
 /*****************************************************************************/
diff --git a/fs/afs/write.c b/fs/afs/write.c
index e40cf8e7543ab..80daf28d8f8b8 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -16,7 +16,8 @@
 
 static int afs_writepages_region(struct address_space *mapping,
 				 struct writeback_control *wbc,
-				 loff_t start, loff_t end, loff_t *_next,
+				 unsigned long long start,
+				 unsigned long long end, loff_t *_next,
 				 bool max_one_loop);
 
 static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len,
@@ -34,25 +35,6 @@ static void afs_folio_start_fscache(bool caching, struct folio *folio)
 }
 #endif
 
-/*
- * Flush out a conflicting write.  This may extend the write to the surrounding
- * pages if also dirty and contiguous to the conflicting region..
- */
-static int afs_flush_conflicting_write(struct address_space *mapping,
-				       struct folio *folio)
-{
-	struct writeback_control wbc = {
-		.sync_mode	= WB_SYNC_ALL,
-		.nr_to_write	= LONG_MAX,
-		.range_start	= folio_pos(folio),
-		.range_end	= LLONG_MAX,
-	};
-	loff_t next;
-
-	return afs_writepages_region(mapping, &wbc, folio_pos(folio), LLONG_MAX,
-				     &next, true);
-}
-
 /*
  * prepare to perform part of a write to a page
  */
@@ -62,10 +44,6 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 	struct folio *folio;
-	unsigned long priv;
-	unsigned f, from;
-	unsigned t, to;
-	pgoff_t index;
 	int ret;
 
 	_enter("{%llx:%llu},%llx,%x",
@@ -79,49 +57,20 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	if (ret < 0)
 		return ret;
 
-	index = folio_index(folio);
-	from = pos - index * PAGE_SIZE;
-	to = from + len;
-
 try_again:
 	/* See if this page is already partially written in a way that we can
 	 * merge the new write with.
 	 */
-	if (folio_test_private(folio)) {
-		priv = (unsigned long)folio_get_private(folio);
-		f = afs_folio_dirty_from(folio, priv);
-		t = afs_folio_dirty_to(folio, priv);
-		ASSERTCMP(f, <=, t);
-
-		if (folio_test_writeback(folio)) {
-			trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio);
-			folio_unlock(folio);
-			goto wait_for_writeback;
-		}
-		/* If the file is being filled locally, allow inter-write
-		 * spaces to be merged into writes.  If it's not, only write
-		 * back what the user gives us.
-		 */
-		if (!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags) &&
-		    (to < f || from > t))
-			goto flush_conflicting_write;
+	if (folio_test_writeback(folio)) {
+		trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio);
+		folio_unlock(folio);
+		goto wait_for_writeback;
 	}
 
 	*_page = folio_file_page(folio, pos / PAGE_SIZE);
 	_leave(" = 0");
 	return 0;
 
-	/* The previous write and this write aren't adjacent or overlapping, so
-	 * flush the page out.
-	 */
-flush_conflicting_write:
-	trace_afs_folio_dirty(vnode, tracepoint_string("confl"), folio);
-	folio_unlock(folio);
-
-	ret = afs_flush_conflicting_write(mapping, folio);
-	if (ret < 0)
-		goto error;
-
 wait_for_writeback:
 	ret = folio_wait_writeback_killable(folio);
 	if (ret < 0)
@@ -147,9 +96,6 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 {
 	struct folio *folio = page_folio(subpage);
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	unsigned long priv;
-	unsigned int f, from = offset_in_folio(folio, pos);
-	unsigned int t, to = from + copied;
 	loff_t i_size, write_end_pos;
 
 	_enter("{%llx:%llu},{%lx}",
@@ -179,23 +125,6 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 		fscache_update_cookie(afs_vnode_cache(vnode), NULL, &write_end_pos);
 	}
 
-	if (folio_test_private(folio)) {
-		priv = (unsigned long)folio_get_private(folio);
-		f = afs_folio_dirty_from(folio, priv);
-		t = afs_folio_dirty_to(folio, priv);
-		if (from < f)
-			f = from;
-		if (to > t)
-			t = to;
-		priv = afs_folio_dirty(folio, f, t);
-		folio_change_private(folio, (void *)priv);
-		trace_afs_folio_dirty(vnode, tracepoint_string("dirty+"), folio);
-	} else {
-		priv = afs_folio_dirty(folio, from, to);
-		folio_attach_private(folio, (void *)priv);
-		trace_afs_folio_dirty(vnode, tracepoint_string("dirty"), folio);
-	}
-
 	if (folio_mark_dirty(folio))
 		_debug("dirtied %lx", folio_index(folio));
 
@@ -300,7 +229,6 @@ static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsign
 		}
 
 		trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio);
-		folio_detach_private(folio);
 		folio_end_writeback(folio);
 	}
 
@@ -454,17 +382,12 @@ static void afs_extend_writeback(struct address_space *mapping,
 				 long *_count,
 				 loff_t start,
 				 loff_t max_len,
-				 bool new_content,
 				 bool caching,
-				 unsigned int *_len)
+				 size_t *_len)
 {
 	struct folio_batch fbatch;
 	struct folio *folio;
-	unsigned long priv;
-	unsigned int psize, filler = 0;
-	unsigned int f, t;
-	loff_t len = *_len;
-	pgoff_t index = (start + len) / PAGE_SIZE;
+	pgoff_t index = (start + *_len) / PAGE_SIZE;
 	bool stop = true;
 	unsigned int i;
 
@@ -492,7 +415,7 @@ static void afs_extend_writeback(struct address_space *mapping,
 				continue;
 			}
 
-			/* Has the page moved or been split? */
+			/* Has the folio moved or been split? */
 			if (unlikely(folio != xas_reload(&xas))) {
 				folio_put(folio);
 				break;
@@ -510,24 +433,13 @@ static void afs_extend_writeback(struct address_space *mapping,
 				break;
 			}
 
-			psize = folio_size(folio);
-			priv = (unsigned long)folio_get_private(folio);
-			f = afs_folio_dirty_from(folio, priv);
-			t = afs_folio_dirty_to(folio, priv);
-			if (f != 0 && !new_content) {
-				folio_unlock(folio);
-				folio_put(folio);
-				break;
-			}
-
-			len += filler + t;
-			filler = psize - t;
-			if (len >= max_len || *_count <= 0)
+			index += folio_nr_pages(folio);
+			*_count -= folio_nr_pages(folio);
+			*_len += folio_size(folio);
+			stop = false;
+			if (*_len >= max_len || *_count <= 0)
 				stop = true;
-			else if (t == psize || new_content)
-				stop = false;
 
-			index += folio_nr_pages(folio);
 			if (!folio_batch_add(&fbatch, folio))
 				break;
 			if (stop)
@@ -553,16 +465,12 @@ static void afs_extend_writeback(struct address_space *mapping,
 			if (folio_start_writeback(folio))
 				BUG();
 			afs_folio_start_fscache(caching, folio);
-
-			*_count -= folio_nr_pages(folio);
 			folio_unlock(folio);
 		}
 
 		folio_batch_release(&fbatch);
 		cond_resched();
 	} while (!stop);
-
-	*_len = len;
 }
 
 /*
@@ -572,14 +480,13 @@ static void afs_extend_writeback(struct address_space *mapping,
 static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 						struct writeback_control *wbc,
 						struct folio *folio,
-						loff_t start, loff_t end)
+						unsigned long long start,
+						unsigned long long end)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
 	struct iov_iter iter;
-	unsigned long priv;
-	unsigned int offset, to, len, max_len;
-	loff_t i_size = i_size_read(&vnode->netfs.inode);
-	bool new_content = test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
+	unsigned long long i_size = i_size_read(&vnode->netfs.inode);
+	size_t len, max_len;
 	bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode));
 	long count = wbc->nr_to_write;
 	int ret;
@@ -597,13 +504,9 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 	 * immediately lockable, is not dirty or is missing, or we reach the
 	 * end of the range.
 	 */
-	priv = (unsigned long)folio_get_private(folio);
-	offset = afs_folio_dirty_from(folio, priv);
-	to = afs_folio_dirty_to(folio, priv);
 	trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio);
 
-	len = to - offset;
-	start += offset;
+	len = folio_size(folio);
 	if (start < i_size) {
 		/* Trim the write to the EOF; the extra data is ignored.  Also
 		 * put an upper limit on the size of a single storedata op.
@@ -612,12 +515,10 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 		max_len = min_t(unsigned long long, max_len, end - start + 1);
 		max_len = min_t(unsigned long long, max_len, i_size - start);
 
-		if (len < max_len &&
-		    (to == folio_size(folio) || new_content))
+		if (len < max_len)
 			afs_extend_writeback(mapping, vnode, &count,
-					     start, max_len, new_content,
-					     caching, &len);
-		len = min_t(loff_t, len, max_len);
+					     start, max_len, caching, &len);
+		len = min_t(unsigned long long, len, i_size - start);
 	}
 
 	/* We now have a contiguous set of dirty pages, each with writeback
@@ -627,7 +528,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 	folio_unlock(folio);
 
 	if (start < i_size) {
-		_debug("write back %x @%llx [%llx]", len, start, i_size);
+		_debug("write back %zx @%llx [%llx]", len, start, i_size);
 
 		/* Speculatively write to the cache.  We have to fix this up
 		 * later if the store fails.
@@ -637,7 +538,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 		iov_iter_xarray(&iter, ITER_SOURCE, &mapping->i_pages, start, len);
 		ret = afs_store_data(vnode, &iter, start, false);
 	} else {
-		_debug("write discard %x @%llx [%llx]", len, start, i_size);
+		_debug("write discard %zx @%llx [%llx]", len, start, i_size);
 
 		/* The dirty region was entirely beyond the EOF. */
 		fscache_clear_page_bits(mapping, start, len, caching);
@@ -693,7 +594,8 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
  */
 static int afs_writepages_region(struct address_space *mapping,
 				 struct writeback_control *wbc,
-				 loff_t start, loff_t end, loff_t *_next,
+				 unsigned long long start,
+				 unsigned long long end, loff_t *_next,
 				 bool max_one_loop)
 {
 	struct folio *folio;
@@ -905,7 +807,6 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	struct inode *inode = file_inode(file);
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = file->private_data;
-	unsigned long priv;
 	vm_fault_t ret = VM_FAULT_RETRY;
 
 	_enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
@@ -929,24 +830,15 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	if (folio_lock_killable(folio) < 0)
 		goto out;
 
-	/* We mustn't change folio->private until writeback is complete as that
-	 * details the portion of the page we need to write back and we might
-	 * need to redirty the page if there's a problem.
-	 */
 	if (folio_wait_writeback_killable(folio) < 0) {
 		folio_unlock(folio);
 		goto out;
 	}
 
-	priv = afs_folio_dirty(folio, 0, folio_size(folio));
-	priv = afs_folio_dirty_mmapped(priv);
-	if (folio_test_private(folio)) {
-		folio_change_private(folio, (void *)priv);
+	if (folio_test_dirty(folio))
 		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio);
-	} else {
-		folio_attach_private(folio, (void *)priv);
+	else
 		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio);
-	}
 	file_update_time(file);
 
 	ret = VM_FAULT_LOCKED;
@@ -991,30 +883,26 @@ int afs_launder_folio(struct folio *folio)
 	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
 	struct iov_iter iter;
 	struct bio_vec bv;
-	unsigned long priv;
-	unsigned int f, t;
+	unsigned long long fend, i_size = vnode->netfs.inode.i_size;
+	size_t len;
 	int ret = 0;
 
 	_enter("{%lx}", folio->index);
 
-	priv = (unsigned long)folio_get_private(folio);
-	if (folio_clear_dirty_for_io(folio)) {
-		f = 0;
-		t = folio_size(folio);
-		if (folio_test_private(folio)) {
-			f = afs_folio_dirty_from(folio, priv);
-			t = afs_folio_dirty_to(folio, priv);
-		}
+	if (folio_clear_dirty_for_io(folio) && folio_pos(folio) < i_size) {
+		len = folio_size(folio);
+		fend = folio_pos(folio) + len;
+		if (vnode->netfs.inode.i_size < fend)
+			len = fend - i_size;
 
-		bvec_set_folio(&bv, folio, t - f, f);
-		iov_iter_bvec(&iter, ITER_SOURCE, &bv, 1, bv.bv_len);
+		bvec_set_folio(&bv, folio, len, 0);
+		iov_iter_bvec(&iter, WRITE, &bv, 1, len);
 
 		trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio);
-		ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true);
+		ret = afs_store_data(vnode, &iter, folio_pos(folio), true);
 	}
 
 	trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio);
-	folio_detach_private(folio);
 	folio_wait_fscache(folio);
 	return ret;
 }
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 597677acc6b17..08506680350c8 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -846,26 +846,18 @@ TRACE_EVENT(afs_folio_dirty,
 		    __field(struct afs_vnode *,		vnode)
 		    __field(const char *,		where)
 		    __field(pgoff_t,			index)
-		    __field(unsigned long,		from)
-		    __field(unsigned long,		to)
+		    __field(size_t,			size)
 			     ),
 
 	    TP_fast_assign(
-		    unsigned long priv = (unsigned long)folio_get_private(folio);
 		    __entry->vnode = vnode;
 		    __entry->where = where;
 		    __entry->index = folio_index(folio);
-		    __entry->from  = afs_folio_dirty_from(folio, priv);
-		    __entry->to    = afs_folio_dirty_to(folio, priv);
-		    __entry->to   |= (afs_is_folio_dirty_mmapped(priv) ?
-				      (1UL << (BITS_PER_LONG - 1)) : 0);
+		    __entry->size = folio_size(folio);
 			   ),
 
-	    TP_printk("vn=%p %lx %s %lx-%lx%s",
-		      __entry->vnode, __entry->index, __entry->where,
-		      __entry->from,
-		      __entry->to & ~(1UL << (BITS_PER_LONG - 1)),
-		      __entry->to & (1UL << (BITS_PER_LONG - 1)) ? " M" : "")
+	    TP_printk("vn=%p ix=%05lx s=%05lx %s",
+		      __entry->vnode, __entry->index, __entry->size, __entry->where)
 	    );
 
 TRACE_EVENT(afs_call_state,
-- 
GitLab


From c1ec4d7c2e13471558cfea302b7583856284f94c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 20 Aug 2021 17:08:30 +0100
Subject: [PATCH 1910/4076] netfs: Provide invalidate_folio and release_folio
 calls

Provide default invalidate_folio and release_folio calls.  These will need
to interact with invalidation correctly at some point.  They will be needed
if netfslib is to make use of folio->private for its own purposes.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/9p/vfs_addr.c      | 33 ++-------------------------
 fs/afs/file.c         | 53 ++++---------------------------------------
 fs/ceph/addr.c        | 24 ++------------------
 fs/ceph/cache.h       | 10 --------
 fs/netfs/misc.c       | 42 ++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  6 +++--
 6 files changed, 54 insertions(+), 114 deletions(-)

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 131b83c31f85d..055b672a247d7 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -88,35 +88,6 @@ const struct netfs_request_ops v9fs_req_ops = {
 	.issue_read		= v9fs_issue_read,
 };
 
-/**
- * v9fs_release_folio - release the private state associated with a folio
- * @folio: The folio to be released
- * @gfp: The caller's allocation restrictions
- *
- * Returns true if the page can be released, false otherwise.
- */
-
-static bool v9fs_release_folio(struct folio *folio, gfp_t gfp)
-{
-	if (folio_test_private(folio))
-		return false;
-#ifdef CONFIG_9P_FSCACHE
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	fscache_note_page_release(v9fs_inode_cookie(V9FS_I(folio_inode(folio))));
-#endif
-	return true;
-}
-
-static void v9fs_invalidate_folio(struct folio *folio, size_t offset,
-				 size_t length)
-{
-	folio_wait_fscache(folio);
-}
-
 #ifdef CONFIG_9P_FSCACHE
 static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
 				     bool was_async)
@@ -324,8 +295,8 @@ const struct address_space_operations v9fs_addr_operations = {
 	.writepage	= v9fs_vfs_writepage,
 	.write_begin	= v9fs_write_begin,
 	.write_end	= v9fs_write_end,
-	.release_folio	= v9fs_release_folio,
-	.invalidate_folio = v9fs_invalidate_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
 	.launder_folio	= v9fs_launder_folio,
 	.direct_IO	= v9fs_direct_IO,
 };
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 0d783e5b2147b..d152ba451f0ec 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -20,9 +20,6 @@
 
 static int afs_file_mmap(struct file *file, struct vm_area_struct *vma);
 static int afs_symlink_read_folio(struct file *file, struct folio *folio);
-static void afs_invalidate_folio(struct folio *folio, size_t offset,
-			       size_t length);
-static bool afs_release_folio(struct folio *folio, gfp_t gfp_flags);
 
 static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos,
@@ -57,8 +54,8 @@ const struct address_space_operations afs_file_aops = {
 	.readahead	= netfs_readahead,
 	.dirty_folio	= netfs_dirty_folio,
 	.launder_folio	= afs_launder_folio,
-	.release_folio	= afs_release_folio,
-	.invalidate_folio = afs_invalidate_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
 	.write_begin	= afs_write_begin,
 	.write_end	= afs_write_end,
 	.writepages	= afs_writepages,
@@ -67,8 +64,8 @@ const struct address_space_operations afs_file_aops = {
 
 const struct address_space_operations afs_symlink_aops = {
 	.read_folio	= afs_symlink_read_folio,
-	.release_folio	= afs_release_folio,
-	.invalidate_folio = afs_invalidate_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
 	.migrate_folio	= filemap_migrate_folio,
 };
 
@@ -386,48 +383,6 @@ const struct netfs_request_ops afs_req_ops = {
 	.issue_read		= afs_issue_read,
 };
 
-/*
- * invalidate part or all of a page
- * - release a page and clean up its private data if offset is 0 (indicating
- *   the entire page)
- */
-static void afs_invalidate_folio(struct folio *folio, size_t offset,
-			       size_t length)
-{
-	_enter("{%lu},%zu,%zu", folio->index, offset, length);
-
-	folio_wait_fscache(folio);
-	_leave("");
-}
-
-/*
- * release a page and clean up its private state if it's not busy
- * - return true if the page can now be released, false if not
- */
-static bool afs_release_folio(struct folio *folio, gfp_t gfp)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-
-	_enter("{{%llx:%llu}[%lu],%lx},%x",
-	       vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags,
-	       gfp);
-
-	/* deny if folio is being written to the cache and the caller hasn't
-	 * elected to wait */
-#ifdef CONFIG_AFS_FSCACHE
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	fscache_note_page_release(afs_vnode_cache(vnode));
-#endif
-
-	/* Indicate that the folio can be released */
-	_leave(" = T");
-	return true;
-}
-
 static void afs_add_open_mmap(struct afs_vnode *vnode)
 {
 	if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) {
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 3b8641febeac0..8eedc62e7ac4e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -159,27 +159,7 @@ static void ceph_invalidate_folio(struct folio *folio, size_t offset,
 		ceph_put_snap_context(snapc);
 	}
 
-	folio_wait_fscache(folio);
-}
-
-static bool ceph_release_folio(struct folio *folio, gfp_t gfp)
-{
-	struct inode *inode = folio->mapping->host;
-	struct ceph_client *cl = ceph_inode_to_client(inode);
-
-	doutc(cl, "%llx.%llx idx %lu (%sdirty)\n", ceph_vinop(inode),
-	      folio->index, folio_test_dirty(folio) ? "" : "not ");
-
-	if (folio_test_private(folio))
-		return false;
-
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	ceph_fscache_note_page_release(inode);
-	return true;
+	netfs_invalidate_folio(folio, offset, length);
 }
 
 static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
@@ -1585,7 +1565,7 @@ const struct address_space_operations ceph_aops = {
 	.write_end = ceph_write_end,
 	.dirty_folio = ceph_dirty_folio,
 	.invalidate_folio = ceph_invalidate_folio,
-	.release_folio = ceph_release_folio,
+	.release_folio = netfs_release_folio,
 	.direct_IO = noop_direct_IO,
 };
 
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 8fc7d828d9903..20efac020394e 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -56,12 +56,6 @@ static inline bool ceph_is_cache_enabled(struct inode *inode)
 	return fscache_cookie_enabled(ceph_fscache_cookie(ceph_inode(inode)));
 }
 
-static inline void ceph_fscache_note_page_release(struct inode *inode)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-
-	fscache_note_page_release(ceph_fscache_cookie(ci));
-}
 #else /* CONFIG_CEPH_FSCACHE */
 static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc,
 					   struct fs_context *fc)
@@ -118,10 +112,6 @@ static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
 	return false;
 }
-
-static inline void ceph_fscache_note_page_release(struct inode *inode)
-{
-}
 #endif /* CONFIG_CEPH_FSCACHE */
 
 #endif
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 68baf55c47a43..45bb19ec9a638 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -84,3 +84,45 @@ void netfs_clear_inode_writeback(struct inode *inode, const void *aux)
 	}
 }
 EXPORT_SYMBOL(netfs_clear_inode_writeback);
+
+/**
+ * netfs_invalidate_folio - Invalidate or partially invalidate a folio
+ * @folio: Folio proposed for release
+ * @offset: Offset of the invalidated region
+ * @length: Length of the invalidated region
+ *
+ * Invalidate part or all of a folio for a network filesystem.  The folio will
+ * be removed afterwards if the invalidated region covers the entire folio.
+ */
+void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
+{
+	_enter("{%lx},%zx,%zx", folio_index(folio), offset, length);
+
+	folio_wait_fscache(folio);
+}
+EXPORT_SYMBOL(netfs_invalidate_folio);
+
+/**
+ * netfs_release_folio - Try to release a folio
+ * @folio: Folio proposed for release
+ * @gfp: Flags qualifying the release
+ *
+ * Request release of a folio and clean up its private state if it's not busy.
+ * Returns true if the folio can now be released, false if not
+ */
+bool netfs_release_folio(struct folio *folio, gfp_t gfp)
+{
+	struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
+
+	if (folio_test_private(folio))
+		return false;
+	if (folio_test_fscache(folio)) {
+		if (current_is_kswapd() || !(gfp & __GFP_FS))
+			return false;
+		folio_wait_fscache(folio);
+	}
+
+	fscache_note_page_release(netfs_i_cookie(ctx));
+	return true;
+}
+EXPORT_SYMBOL(netfs_release_folio);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 06f57d9d09f6c..8efbfd3b28202 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -293,11 +293,13 @@ struct readahead_control;
 void netfs_readahead(struct readahead_control *);
 int netfs_read_folio(struct file *, struct folio *);
 int netfs_write_begin(struct netfs_inode *, struct file *,
-		struct address_space *, loff_t pos, unsigned int len,
-		struct folio **, void **fsdata);
+		      struct address_space *, loff_t pos, unsigned int len,
+		      struct folio **, void **fsdata);
 bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio);
 int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
 void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
+void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
+bool netfs_release_folio(struct folio *folio, gfp_t gfp);
 
 void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
-- 
GitLab


From 46ed60dcd4f2c94d27735743ce55cd8d6b93cc1d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 11 Oct 2023 15:34:07 +0100
Subject: [PATCH 1911/4076] netfs: Implement unbuffered/DIO vs buffered I/O
 locking

Borrow NFS's direct-vs-buffered I/O locking into netfslib.  Similar code is
also used in ceph.

Modify it to have the correct checker annotations for i_rwsem lock
acquisition/release and to return -ERESTARTSYS if waits are interrupted.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile     |   1 +
 fs/netfs/locking.c    | 216 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  10 ++
 3 files changed, 227 insertions(+)
 create mode 100644 fs/netfs/locking.c

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index a84fe9bbd3c4e..cf3fc847b8ace 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -4,6 +4,7 @@ netfs-y := \
 	buffered_read.o \
 	io.o \
 	iterator.o \
+	locking.o \
 	main.o \
 	misc.o \
 	objects.o
diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c
new file mode 100644
index 0000000000000..75dc52a49b3a4
--- /dev/null
+++ b/fs/netfs/locking.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * I/O and data path helper functionality.
+ *
+ * Borrowed from NFS Copyright (c) 2016 Trond Myklebust
+ */
+
+#include <linux/kernel.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/*
+ * inode_dio_wait_interruptible - wait for outstanding DIO requests to finish
+ * @inode: inode to wait for
+ *
+ * Waits for all pending direct I/O requests to finish so that we can
+ * proceed with a truncate or equivalent operation.
+ *
+ * Must be called under a lock that serializes taking new references
+ * to i_dio_count, usually by inode->i_mutex.
+ */
+static int inode_dio_wait_interruptible(struct inode *inode)
+{
+	if (!atomic_read(&inode->i_dio_count))
+		return 0;
+
+	wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP);
+	DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);
+
+	for (;;) {
+		prepare_to_wait(wq, &q.wq_entry, TASK_INTERRUPTIBLE);
+		if (!atomic_read(&inode->i_dio_count))
+			break;
+		if (signal_pending(current))
+			break;
+		schedule();
+	}
+	finish_wait(wq, &q.wq_entry);
+
+	return atomic_read(&inode->i_dio_count) ? -ERESTARTSYS : 0;
+}
+
+/* Call with exclusively locked inode->i_rwsem */
+static int netfs_block_o_direct(struct netfs_inode *ictx)
+{
+	if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags))
+		return 0;
+	clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+	return inode_dio_wait_interruptible(&ictx->inode);
+}
+
+/**
+ * netfs_start_io_read - declare the file is being used for buffered reads
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is unset,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that buffered read operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas direct I/O
+ * operations need to wait to grab an exclusive lock in order to set
+ * NETFS_ICTX_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
+ */
+int netfs_start_io_read(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	/* Be an optimist! */
+	if (down_read_interruptible(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) == 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (netfs_block_o_direct(ictx) < 0) {
+		up_write(&inode->i_rwsem);
+		return -ERESTARTSYS;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_read);
+
+/**
+ * netfs_end_io_read - declare that the buffered read operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_read(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_read(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_read);
+
+/**
+ * netfs_start_io_write - declare the file is being used for buffered writes
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ */
+int netfs_start_io_write(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (netfs_block_o_direct(ictx) < 0) {
+		up_write(&inode->i_rwsem);
+		return -ERESTARTSYS;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_write);
+
+/**
+ * netfs_end_io_write - declare that the buffered write operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered write operation is done, and release the
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_write(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_write(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_write);
+
+/* Call with exclusively locked inode->i_rwsem */
+static int netfs_block_buffered(struct inode *inode)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+	int ret;
+
+	if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags)) {
+		set_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+		if (inode->i_mapping->nrpages != 0) {
+			unmap_mapping_range(inode->i_mapping, 0, 0, 0);
+			ret = filemap_fdatawait(inode->i_mapping);
+			if (ret < 0) {
+				clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+				return ret;
+			}
+		}
+	}
+	return 0;
+}
+
+/**
+ * netfs_start_io_direct - declare the file is being used for direct i/o
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is about to start, and ensure
+ * that we block all buffered I/O.
+ * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is set,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that direct I/O operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas buffered I/O
+ * operations need to wait to grab an exclusive lock in order to clear
+ * NETFS_ICTX_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
+ */
+int netfs_start_io_direct(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+	int ret;
+
+	/* Be an optimist! */
+	if (down_read_interruptible(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) != 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	ret = netfs_block_buffered(inode);
+	if (ret < 0) {
+		up_write(&inode->i_rwsem);
+		return ret;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_direct);
+
+/**
+ * netfs_end_io_direct - declare that the direct i/o operation is done
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_direct(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_read(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_direct);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 8efbfd3b28202..fc6d9756a0294 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -129,6 +129,8 @@ struct netfs_inode {
 	struct fscache_cookie	*cache;
 #endif
 	loff_t			remote_i_size;	/* Size of the remote file */
+	unsigned long		flags;
+#define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 };
 
 /*
@@ -310,6 +312,13 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
 
+int netfs_start_io_read(struct inode *inode);
+void netfs_end_io_read(struct inode *inode);
+int netfs_start_io_write(struct inode *inode);
+void netfs_end_io_write(struct inode *inode);
+int netfs_start_io_direct(struct inode *inode);
+void netfs_end_io_direct(struct inode *inode);
+
 /**
  * netfs_inode - Get the netfs inode context from the inode
  * @inode: The inode to query
@@ -335,6 +344,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx,
 {
 	ctx->ops = ops;
 	ctx->remote_i_size = i_size_read(&ctx->inode);
+	ctx->flags = 0;
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
-- 
GitLab


From 92b6cc5d1e7cbe569f00e9c1249ac8214fd5e2d2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 26 Sep 2023 17:42:26 +0100
Subject: [PATCH 1912/4076] netfs: Add iov_iters to (sub)requests to describe
 various buffers

Add three iov_iter structs:

 (1) Add an iov_iter (->iter) to the I/O request to describe the
     unencrypted-side buffer.

 (2) Add an iov_iter (->io_iter) to the I/O request to describe the
     encrypted-side I/O buffer.  This may be a different size to the buffer
     in (1).

 (3) Add an iov_iter (->io_iter) to the I/O subrequest to describe the part
     of the I/O buffer for that subrequest.

This will allow future patches to point to a bounce buffer instead for
purposes of handling oversize writes, decryption (where we want to save the
encrypted data to the cache) and decompression.

These iov_iters persist for the lifetime of the (sub)request, and so can be
accessed multiple times without worrying about them being deallocated upon
return to the caller.

The network filesystem must appropriately advance the iterator before
terminating the request.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/afs/file.c            |  6 +---
 fs/netfs/buffered_read.c | 13 ++++++++
 fs/netfs/io.c            | 69 +++++++++++++++++++++++++++++-----------
 include/linux/netfs.h    |  3 ++
 4 files changed, 67 insertions(+), 24 deletions(-)

diff --git a/fs/afs/file.c b/fs/afs/file.c
index d152ba451f0ec..3403bb792deb8 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -323,11 +323,7 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq)
 	fsreq->len	= subreq->len   - subreq->transferred;
 	fsreq->key	= key_get(subreq->rreq->netfs_priv);
 	fsreq->vnode	= vnode;
-	fsreq->iter	= &fsreq->def_iter;
-
-	iov_iter_xarray(&fsreq->def_iter, ITER_DEST,
-			&fsreq->vnode->netfs.inode.i_mapping->i_pages,
-			fsreq->pos, fsreq->len);
+	fsreq->iter	= &subreq->io_iter;
 
 	afs_fetch_data(fsreq->vnode, fsreq);
 	afs_put_read(fsreq);
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index d39d0ffe75d2d..751556faa70b1 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -199,6 +199,10 @@ void netfs_readahead(struct readahead_control *ractl)
 
 	netfs_rreq_expand(rreq, ractl);
 
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &ractl->mapping->i_pages,
+			rreq->start, rreq->len);
+
 	/* Drop the refs on the folios here rather than in the cache or
 	 * filesystem.  The locks will be dropped in netfs_rreq_unlock().
 	 */
@@ -251,6 +255,11 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 
 	netfs_stat(&netfs_n_rh_readpage);
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
+
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+			rreq->start, rreq->len);
+
 	return netfs_begin_read(rreq, true);
 
 discard:
@@ -408,6 +417,10 @@ retry:
 	ractl._nr_pages = folio_nr_pages(folio);
 	netfs_rreq_expand(rreq, &ractl);
 
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+			rreq->start, rreq->len);
+
 	/* We hold the folio locks, so we can drop the references */
 	folio_get(folio);
 	while (readahead_folio(&ractl))
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 7f753380e047a..e9d408e211b83 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -21,12 +21,7 @@
  */
 static void netfs_clear_unread(struct netfs_io_subrequest *subreq)
 {
-	struct iov_iter iter;
-
-	iov_iter_xarray(&iter, ITER_DEST, &subreq->rreq->mapping->i_pages,
-			subreq->start + subreq->transferred,
-			subreq->len   - subreq->transferred);
-	iov_iter_zero(iov_iter_count(&iter), &iter);
+	iov_iter_zero(iov_iter_count(&subreq->io_iter), &subreq->io_iter);
 }
 
 static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error,
@@ -46,14 +41,9 @@ static void netfs_read_from_cache(struct netfs_io_request *rreq,
 				  enum netfs_read_from_hole read_hole)
 {
 	struct netfs_cache_resources *cres = &rreq->cache_resources;
-	struct iov_iter iter;
 
 	netfs_stat(&netfs_n_rh_read);
-	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages,
-			subreq->start + subreq->transferred,
-			subreq->len   - subreq->transferred);
-
-	cres->ops->read(cres, subreq->start, &iter, read_hole,
+	cres->ops->read(cres, subreq->start, &subreq->io_iter, read_hole,
 			netfs_cache_read_terminated, subreq);
 }
 
@@ -88,6 +78,11 @@ static void netfs_read_from_server(struct netfs_io_request *rreq,
 				   struct netfs_io_subrequest *subreq)
 {
 	netfs_stat(&netfs_n_rh_download);
+	if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+		pr_warn("R=%08x[%u] ITER PRE-MISMATCH %zx != %zx-%zx %lx\n",
+			rreq->debug_id, subreq->debug_index,
+			iov_iter_count(&subreq->io_iter), subreq->len,
+			subreq->transferred, subreq->flags);
 	rreq->netfs_ops->issue_read(subreq);
 }
 
@@ -259,6 +254,30 @@ static void netfs_rreq_short_read(struct netfs_io_request *rreq,
 		netfs_read_from_server(rreq, subreq);
 }
 
+/*
+ * Reset the subrequest iterator prior to resubmission.
+ */
+static void netfs_reset_subreq_iter(struct netfs_io_request *rreq,
+				    struct netfs_io_subrequest *subreq)
+{
+	size_t remaining = subreq->len - subreq->transferred;
+	size_t count = iov_iter_count(&subreq->io_iter);
+
+	if (count == remaining)
+		return;
+
+	_debug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n",
+	       rreq->debug_id, subreq->debug_index,
+	       iov_iter_count(&subreq->io_iter), subreq->transferred,
+	       subreq->len, rreq->i_size,
+	       subreq->io_iter.iter_type);
+
+	if (count < remaining)
+		iov_iter_revert(&subreq->io_iter, remaining - count);
+	else
+		iov_iter_advance(&subreq->io_iter, count - remaining);
+}
+
 /*
  * Resubmit any short or failed operations.  Returns true if we got the rreq
  * ref back.
@@ -287,6 +306,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
 			trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead);
 			netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
 			atomic_inc(&rreq->nr_outstanding);
+			netfs_reset_subreq_iter(rreq, subreq);
 			netfs_read_from_server(rreq, subreq);
 		} else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) {
 			netfs_rreq_short_read(rreq, subreq);
@@ -399,9 +419,9 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
 	struct netfs_io_request *rreq = subreq->rreq;
 	int u;
 
-	_enter("[%u]{%llx,%lx},%zd",
-	       subreq->debug_index, subreq->start, subreq->flags,
-	       transferred_or_error);
+	_enter("R=%x[%x]{%llx,%lx},%zd",
+	       rreq->debug_id, subreq->debug_index,
+	       subreq->start, subreq->flags, transferred_or_error);
 
 	switch (subreq->source) {
 	case NETFS_READ_FROM_CACHE:
@@ -501,7 +521,8 @@ static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest
  */
 static enum netfs_io_source
 netfs_rreq_prepare_read(struct netfs_io_request *rreq,
-			struct netfs_io_subrequest *subreq)
+			struct netfs_io_subrequest *subreq,
+			struct iov_iter *io_iter)
 {
 	enum netfs_io_source source;
 
@@ -528,9 +549,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		}
 	}
 
-	if (WARN_ON(subreq->len == 0))
+	if (WARN_ON(subreq->len == 0)) {
 		source = NETFS_INVALID_READ;
+		goto out;
+	}
 
+	subreq->io_iter = *io_iter;
+	iov_iter_truncate(&subreq->io_iter, subreq->len);
+	iov_iter_advance(io_iter, subreq->len);
 out:
 	subreq->source = source;
 	trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
@@ -541,6 +567,7 @@ out:
  * Slice off a piece of a read request and submit an I/O request for it.
  */
 static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
+				    struct iov_iter *io_iter,
 				    unsigned int *_debug_index)
 {
 	struct netfs_io_subrequest *subreq;
@@ -565,7 +592,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
 	 * (the starts must coincide), in which case, we go around the loop
 	 * again and ask it to download the next piece.
 	 */
-	source = netfs_rreq_prepare_read(rreq, subreq);
+	source = netfs_rreq_prepare_read(rreq, subreq, io_iter);
 	if (source == NETFS_INVALID_READ)
 		goto subreq_failed;
 
@@ -603,6 +630,7 @@ subreq_failed:
  */
 int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 {
+	struct iov_iter io_iter;
 	unsigned int debug_index = 0;
 	int ret;
 
@@ -615,6 +643,8 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 		return -EIO;
 	}
 
+	rreq->io_iter = rreq->iter;
+
 	INIT_WORK(&rreq->work, netfs_rreq_work);
 
 	if (sync)
@@ -624,8 +654,9 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	 * want and submit each one.
 	 */
 	atomic_set(&rreq->nr_outstanding, 1);
+	io_iter = rreq->io_iter;
 	do {
-		if (!netfs_rreq_submit_slice(rreq, &debug_index))
+		if (!netfs_rreq_submit_slice(rreq, &io_iter, &debug_index))
 			break;
 
 	} while (rreq->submitted < rreq->len);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index fc6d9756a0294..3da962e977f55 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -150,6 +150,7 @@ struct netfs_cache_resources {
 struct netfs_io_subrequest {
 	struct netfs_io_request *rreq;		/* Supervising I/O request */
 	struct list_head	rreq_link;	/* Link in rreq->subrequests */
+	struct iov_iter		io_iter;	/* Iterator for this subrequest */
 	loff_t			start;		/* Where to start the I/O */
 	size_t			len;		/* Size of the I/O */
 	size_t			transferred;	/* Amount of data transferred */
@@ -186,6 +187,8 @@ struct netfs_io_request {
 	struct netfs_cache_resources cache_resources;
 	struct list_head	proc_link;	/* Link in netfs_iorequests */
 	struct list_head	subrequests;	/* Contributory I/O operations */
+	struct iov_iter		iter;		/* Unencrypted-side iterator */
+	struct iov_iter		io_iter;	/* I/O (Encrypted-side) iterator */
 	void			*netfs_priv;	/* Private data for the netfs */
 	unsigned int		debug_id;
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
-- 
GitLab


From 7984d22f1315bf30433e11e5010e4ce09ca22037 Mon Sep 17 00:00:00 2001
From: Alison Schofield <alison.schofield@intel.com>
Date: Fri, 22 Dec 2023 16:47:40 -0800
Subject: [PATCH 1913/4076] cxl/region: Add dev_dbg() detail on failure to
 allocate HPA space

When the region driver fails while allocating HPA space for a
new region it can be because the parent resource, the CXL Window,
has no more available space.

In that case, the debug user sees this message:
cxl_core:alloc_hpa:555: cxl region2: failed to allocate HPA: -34

Expand the message like this:
cxl_core:alloc_hpa:555: cxl region8: HPA allocation error (-34) for size:0x20000000 in CXL Window 0 [mem 0xf010000000-0xf04fffffff flags 0x200]

Now the debug user can examine /proc/iomem and consider actions
like removing other allocations in that space or reducing the
size of their region request.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Reviewed-by: Fan Ni <fan.ni@samsung.com>
Link: https://lore.kernel.org/r/20231223004740.1401858-1-alison.schofield@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/region.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index a61703c9d72ab..d904f9752bc38 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -552,8 +552,9 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	res = alloc_free_mem_region(cxlrd->res, size, SZ_256M,
 				    dev_name(&cxlr->dev));
 	if (IS_ERR(res)) {
-		dev_dbg(&cxlr->dev, "failed to allocate HPA: %ld\n",
-			PTR_ERR(res));
+		dev_dbg(&cxlr->dev,
+			"HPA allocation error (%ld) for size:%#llx in %s %pr\n",
+			PTR_ERR(res), size, cxlrd->res->name, cxlrd->res);
 		return PTR_ERR(res);
 	}
 
-- 
GitLab


From c04c4ebd452476af1bdfa917105d9da97f01868d Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Fri, 17 Nov 2023 10:10:04 -0600
Subject: [PATCH 1914/4076] power: reset: gpio-restart: Use
 devm_register_sys_off_handler()

Use device life-cycle managed register function to simplify probe error
path and eliminate need for explicit remove function.

Signed-off-by: Andrew Davis <afd@ti.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/gpio-restart.c | 34 ++++++++----------------------
 1 file changed, 9 insertions(+), 25 deletions(-)

diff --git a/drivers/power/reset/gpio-restart.c b/drivers/power/reset/gpio-restart.c
index 3aa19765772dc..d1e177176fa1f 100644
--- a/drivers/power/reset/gpio-restart.c
+++ b/drivers/power/reset/gpio-restart.c
@@ -17,17 +17,14 @@
 
 struct gpio_restart {
 	struct gpio_desc *reset_gpio;
-	struct notifier_block restart_handler;
 	u32 active_delay_ms;
 	u32 inactive_delay_ms;
 	u32 wait_delay_ms;
 };
 
-static int gpio_restart_notify(struct notifier_block *this,
-				unsigned long mode, void *cmd)
+static int gpio_restart_notify(struct sys_off_data *data)
 {
-	struct gpio_restart *gpio_restart =
-		container_of(this, struct gpio_restart, restart_handler);
+	struct gpio_restart *gpio_restart = data->cb_data;
 
 	/* drive it active, also inactive->active edge */
 	gpiod_direction_output(gpio_restart->reset_gpio, 1);
@@ -52,6 +49,7 @@ static int gpio_restart_probe(struct platform_device *pdev)
 {
 	struct gpio_restart *gpio_restart;
 	bool open_source = false;
+	int priority = 129;
 	u32 property;
 	int ret;
 
@@ -71,8 +69,6 @@ static int gpio_restart_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	gpio_restart->restart_handler.notifier_call = gpio_restart_notify;
-	gpio_restart->restart_handler.priority = 129;
 	gpio_restart->active_delay_ms = 100;
 	gpio_restart->inactive_delay_ms = 100;
 	gpio_restart->wait_delay_ms = 3000;
@@ -83,7 +79,7 @@ static int gpio_restart_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "Invalid priority property: %u\n",
 					property);
 		else
-			gpio_restart->restart_handler.priority = property;
+			priority = property;
 	}
 
 	of_property_read_u32(pdev->dev.of_node, "active-delay",
@@ -93,9 +89,11 @@ static int gpio_restart_probe(struct platform_device *pdev)
 	of_property_read_u32(pdev->dev.of_node, "wait-delay",
 			&gpio_restart->wait_delay_ms);
 
-	platform_set_drvdata(pdev, gpio_restart);
-
-	ret = register_restart_handler(&gpio_restart->restart_handler);
+	ret = devm_register_sys_off_handler(&pdev->dev,
+					    SYS_OFF_MODE_RESTART,
+					    priority,
+					    gpio_restart_notify,
+					    gpio_restart);
 	if (ret) {
 		dev_err(&pdev->dev, "%s: cannot register restart handler, %d\n",
 				__func__, ret);
@@ -105,19 +103,6 @@ static int gpio_restart_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void gpio_restart_remove(struct platform_device *pdev)
-{
-	struct gpio_restart *gpio_restart = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = unregister_restart_handler(&gpio_restart->restart_handler);
-	if (ret) {
-		dev_err(&pdev->dev,
-				"%s: cannot unregister restart handler, %d\n",
-				__func__, ret);
-	}
-}
-
 static const struct of_device_id of_gpio_restart_match[] = {
 	{ .compatible = "gpio-restart", },
 	{},
@@ -125,7 +110,6 @@ static const struct of_device_id of_gpio_restart_match[] = {
 
 static struct platform_driver gpio_restart_driver = {
 	.probe = gpio_restart_probe,
-	.remove_new = gpio_restart_remove,
 	.driver = {
 		.name = "restart-gpio",
 		.of_match_table = of_gpio_restart_match,
-- 
GitLab


From c73cc447751898aeac5ef1c0012a03d45721949a Mon Sep 17 00:00:00 2001
From: Charalampos Mitrodimas <charmitro@posteo.net>
Date: Sat, 18 Nov 2023 13:29:57 +0000
Subject: [PATCH 1915/4076] power: supply: Fix indentation and some other
 warnings

These were mentioned by checkpatch:
	Errors:
		(1) code indent should use tabs where possible
		(2) switch and case should be at the same indent
	Warnings:
		(1) Missing a blank line after declarations

Signed-off-by: Charalampos Mitrodimas <charmitro@posteo.net>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 161 ++++++++++++-----------
 1 file changed, 81 insertions(+), 80 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 73265001dd4b2..4a5b570dff449 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -861,44 +861,44 @@ const size_t power_supply_battery_info_properties_size = ARRAY_SIZE(power_supply
 EXPORT_SYMBOL_GPL(power_supply_battery_info_properties_size);
 
 bool power_supply_battery_info_has_prop(struct power_supply_battery_info *info,
-				        enum power_supply_property psp)
+					enum power_supply_property psp)
 {
 	if (!info)
 		return false;
 
 	switch (psp) {
-		case POWER_SUPPLY_PROP_TECHNOLOGY:
-			return info->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
-		case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
-			return info->energy_full_design_uwh >= 0;
-		case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
-			return info->charge_full_design_uah >= 0;
-		case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
-			return info->voltage_min_design_uv >= 0;
-		case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
-			return info->voltage_max_design_uv >= 0;
-		case POWER_SUPPLY_PROP_PRECHARGE_CURRENT:
-			return info->precharge_current_ua >= 0;
-		case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
-			return info->charge_term_current_ua >= 0;
-		case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
-			return info->constant_charge_current_max_ua >= 0;
-		case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
-			return info->constant_charge_voltage_max_uv >= 0;
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
-			return info->temp_ambient_alert_min > INT_MIN;
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
-			return info->temp_ambient_alert_max < INT_MAX;
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
-			return info->temp_alert_min > INT_MIN;
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
-			return info->temp_alert_max < INT_MAX;
-		case POWER_SUPPLY_PROP_TEMP_MIN:
-			return info->temp_min > INT_MIN;
-		case POWER_SUPPLY_PROP_TEMP_MAX:
-			return info->temp_max < INT_MAX;
-		default:
-			return false;
+	case POWER_SUPPLY_PROP_TECHNOLOGY:
+		return info->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
+	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
+		return info->energy_full_design_uwh >= 0;
+	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
+		return info->charge_full_design_uah >= 0;
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+		return info->voltage_min_design_uv >= 0;
+	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
+		return info->voltage_max_design_uv >= 0;
+	case POWER_SUPPLY_PROP_PRECHARGE_CURRENT:
+		return info->precharge_current_ua >= 0;
+	case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
+		return info->charge_term_current_ua >= 0;
+	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
+		return info->constant_charge_current_max_ua >= 0;
+	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
+		return info->constant_charge_voltage_max_uv >= 0;
+	case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
+		return info->temp_ambient_alert_min > INT_MIN;
+	case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
+		return info->temp_ambient_alert_max < INT_MAX;
+	case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
+		return info->temp_alert_min > INT_MIN;
+	case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
+		return info->temp_alert_max < INT_MAX;
+	case POWER_SUPPLY_PROP_TEMP_MIN:
+		return info->temp_min > INT_MIN;
+	case POWER_SUPPLY_PROP_TEMP_MAX:
+		return info->temp_max < INT_MAX;
+	default:
+		return false;
 	}
 }
 EXPORT_SYMBOL_GPL(power_supply_battery_info_has_prop);
@@ -914,53 +914,53 @@ int power_supply_battery_info_get_prop(struct power_supply_battery_info *info,
 		return -EINVAL;
 
 	switch (psp) {
-		case POWER_SUPPLY_PROP_TECHNOLOGY:
-			val->intval = info->technology;
-			return 0;
-		case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
-			val->intval = info->energy_full_design_uwh;
-			return 0;
-		case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
-			val->intval = info->charge_full_design_uah;
-			return 0;
-		case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
-			val->intval = info->voltage_min_design_uv;
-			return 0;
-		case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
-			val->intval = info->voltage_max_design_uv;
-			return 0;
-		case POWER_SUPPLY_PROP_PRECHARGE_CURRENT:
-			val->intval = info->precharge_current_ua;
-			return 0;
-		case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
-			val->intval = info->charge_term_current_ua;
-			return 0;
-		case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
-			val->intval = info->constant_charge_current_max_ua;
-			return 0;
-		case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
-			val->intval = info->constant_charge_voltage_max_uv;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
-			val->intval = info->temp_ambient_alert_min;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
-			val->intval = info->temp_ambient_alert_max;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
-			val->intval = info->temp_alert_min;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
-			val->intval = info->temp_alert_max;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_MIN:
-			val->intval = info->temp_min;
-			return 0;
-		case POWER_SUPPLY_PROP_TEMP_MAX:
-			val->intval = info->temp_max;
-			return 0;
-		default:
-			return -EINVAL;
+	case POWER_SUPPLY_PROP_TECHNOLOGY:
+		val->intval = info->technology;
+		return 0;
+	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
+		val->intval = info->energy_full_design_uwh;
+		return 0;
+	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
+		val->intval = info->charge_full_design_uah;
+		return 0;
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+		val->intval = info->voltage_min_design_uv;
+		return 0;
+	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
+		val->intval = info->voltage_max_design_uv;
+		return 0;
+	case POWER_SUPPLY_PROP_PRECHARGE_CURRENT:
+		val->intval = info->precharge_current_ua;
+		return 0;
+	case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
+		val->intval = info->charge_term_current_ua;
+		return 0;
+	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
+		val->intval = info->constant_charge_current_max_ua;
+		return 0;
+	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
+		val->intval = info->constant_charge_voltage_max_uv;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
+		val->intval = info->temp_ambient_alert_min;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
+		val->intval = info->temp_ambient_alert_max;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
+		val->intval = info->temp_alert_min;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
+		val->intval = info->temp_alert_max;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_MIN:
+		val->intval = info->temp_min;
+		return 0;
+	case POWER_SUPPLY_PROP_TEMP_MAX:
+		val->intval = info->temp_max;
+		return 0;
+	default:
+		return -EINVAL;
 	}
 }
 EXPORT_SYMBOL_GPL(power_supply_battery_info_get_prop);
@@ -1255,6 +1255,7 @@ EXPORT_SYMBOL_GPL(power_supply_powers);
 static void power_supply_dev_release(struct device *dev)
 {
 	struct power_supply *psy = to_power_supply(dev);
+
 	dev_dbg(dev, "%s\n", __func__);
 	kfree(psy);
 }
-- 
GitLab


From 3cbbe1be0e3bd4cac5502eb141dd257ab34a4460 Mon Sep 17 00:00:00 2001
From: Charalampos Mitrodimas <charmitro@posteo.net>
Date: Sat, 18 Nov 2023 13:29:58 +0000
Subject: [PATCH 1916/4076] power: supply: Use multiple MODULE_AUTHOR
 statements

This resolves checkpatch warning "quoted string split across lines" on:
	1640: WARNING: quoted string split across lines
	1641: WARNING: quoted string split across lines

The motive to use multiple MODULE_AUTHOR statements came from this
comment from "include/linux/module.h":
	/*
	 * Author(s), use "Name <email>" or just "Name", for multiple
	 * authors use multiple MODULE_AUTHOR() statements/lines.
	 */
	#define MODULE_AUTHOR(_author) MODULE_INFO(author, _author)

Signed-off-by: Charalampos Mitrodimas <charmitro@posteo.net>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 4a5b570dff449..ecef35ac3b7e4 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1637,6 +1637,6 @@ subsys_initcall(power_supply_class_init);
 module_exit(power_supply_class_exit);
 
 MODULE_DESCRIPTION("Universal power supply monitor class");
-MODULE_AUTHOR("Ian Molton <spyro@f2s.com>, "
-	      "Szabolcs Gyurko, "
-	      "Anton Vorontsov <cbou@mail.ru>");
+MODULE_AUTHOR("Ian Molton <spyro@f2s.com>");
+MODULE_AUTHOR("Szabolcs Gyurko");
+MODULE_AUTHOR("Anton Vorontsov <cbou@mail.ru>");
-- 
GitLab


From 195c3167865454ea909d717557c8585ccfe1b2a3 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 20 Nov 2023 15:35:32 -0700
Subject: [PATCH 1917/4076] power: reset: at91: Drop '__init' from
 at91_wakeup_status()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building with clang, there are two section mismatch warnings:

  WARNING: modpost: vmlinux: section mismatch in reference: at91_poweroff_probe+0x7c (section: .text) -> at91_wakeup_status (section: .init.text)
  WARNING: modpost: vmlinux: section mismatch in reference: at91_shdwc_probe+0xcc (section: .text) -> at91_wakeup_status (section: .init.text)

Drop '__init' from at91_wakeup_status() to clear up the mismatch.

Fixes: dde74a5de817 ("power: reset: at91-sama5d2_shdwc: Stop using module_platform_driver_probe()")
Fixes: 099806de68b7 ("power: reset: at91-poweroff: Stop using module_platform_driver_probe()")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/reset/at91-poweroff.c      | 2 +-
 drivers/power/reset/at91-sama5d2_shdwc.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c
index 126e774e210c0..93eece0278652 100644
--- a/drivers/power/reset/at91-poweroff.c
+++ b/drivers/power/reset/at91-poweroff.c
@@ -57,7 +57,7 @@ static struct shdwc {
 	void __iomem *mpddrc_base;
 } at91_shdwc;
 
-static void __init at91_wakeup_status(struct platform_device *pdev)
+static void at91_wakeup_status(struct platform_device *pdev)
 {
 	const char *reason;
 	u32 reg = readl(at91_shdwc.shdwc_base + AT91_SHDW_SR);
diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index af95c7b39cb3c..959ce0dbe91d1 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -107,7 +107,7 @@ static const unsigned long long sdwc_dbc_period[] = {
 	0, 3, 32, 512, 4096, 32768,
 };
 
-static void __init at91_wakeup_status(struct platform_device *pdev)
+static void at91_wakeup_status(struct platform_device *pdev)
 {
 	struct shdwc *shdw = platform_get_drvdata(pdev);
 	const struct reg_config *rcfg = shdw->rcfg;
-- 
GitLab


From 88f04bc3e737155e13caddf0ba8ed19db87f0212 Mon Sep 17 00:00:00 2001
From: Kunwu Chan <chentao@kylinos.cn>
Date: Fri, 24 Nov 2023 15:50:21 +0800
Subject: [PATCH 1918/4076] power: supply: Fix null pointer dereference in
 smb2_probe

devm_kasprintf and devm_kzalloc return a pointer to dynamically
allocated memory which can be NULL upon failure.

Fixes: 8648aeb5d7b7 ("power: supply: add Qualcomm PMI8998 SMB2 Charger driver")
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Link: https://lore.kernel.org/r/20231124075021.1335289-1-chentao@kylinos.cn
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/qcom_pmi8998_charger.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/power/supply/qcom_pmi8998_charger.c b/drivers/power/supply/qcom_pmi8998_charger.c
index 8acf63ee6897f..9bb7774060138 100644
--- a/drivers/power/supply/qcom_pmi8998_charger.c
+++ b/drivers/power/supply/qcom_pmi8998_charger.c
@@ -972,10 +972,14 @@ static int smb2_probe(struct platform_device *pdev)
 	supply_config.of_node = pdev->dev.of_node;
 
 	desc = devm_kzalloc(chip->dev, sizeof(smb2_psy_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
 	memcpy(desc, &smb2_psy_desc, sizeof(smb2_psy_desc));
 	desc->name =
 		devm_kasprintf(chip->dev, GFP_KERNEL, "%s-charger",
 			       (const char *)device_get_match_data(chip->dev));
+	if (!desc->name)
+		return -ENOMEM;
 
 	chip->chg_psy =
 		devm_power_supply_register(chip->dev, desc, &supply_config);
-- 
GitLab


From 523100208bd22e3eee7b76025ee4584b5d1ea0ee Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:30:17 +0100
Subject: [PATCH 1919/4076] dt-bindings: power: reset: qcom-pon: fix
 inconsistent example

The current PON example is a bit of a mess after converting the binding
document to yaml and in the process updating parts of the example to
match the pmk8350 binding while leaving parts from the older pm8998
example in place.

Clean up the example and make it consistent by adding some newline
separators; dropping labels; removing stray spaces; fixing the PON node
name; and fixing the unit address so that it matches the interrupt
specifiers (which re-encodes the PON base address, 0x800 => 0x8).

Fixes: 76ba1900cb67 ("dt-bindings: power: reset: qcom-pon: Convert qcom PON binding to yaml")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231130173017.12723-1-johan+linaro@kernel.org
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../devicetree/bindings/power/reset/qcom,pon.yaml   | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
index 5e460128b0d10..fc8105a7b9b26 100644
--- a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
+++ b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
@@ -111,21 +111,24 @@ examples:
    #include <dt-bindings/interrupt-controller/irq.h>
    #include <dt-bindings/input/linux-event-codes.h>
    #include <dt-bindings/spmi/spmi.h>
-   spmi_bus: spmi@c440000 {
+
+   spmi@c440000 {
      reg = <0x0c440000 0x1100>;
      #address-cells = <2>;
      #size-cells = <0>;
-     pmk8350: pmic@0 {
+
+     pmic@0 {
        reg = <0x0 SPMI_USID>;
        #address-cells = <1>;
        #size-cells = <0>;
-       pmk8350_pon: pon_hlos@1300 {
-         reg = <0x1300>;
+
+       pon@800 {
          compatible = "qcom,pm8998-pon";
+         reg = <0x800>;
 
          pwrkey {
             compatible = "qcom,pm8941-pwrkey";
-            interrupts = < 0x0 0x8 0 IRQ_TYPE_EDGE_BOTH >;
+            interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>;
             debounce = <15625>;
             bias-pull-up;
             linux,code = <KEY_POWER>;
-- 
GitLab


From b43f7ddc2b7a5a90447d96cb4d3c6d142dd4a810 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Mon, 18 Dec 2023 15:41:52 +0100
Subject: [PATCH 1920/4076] power: supply: qcom_battmgr: Register the power
 supplies after PDR is up

Currently, a not-yet-entirely-initialized battmgr (e.g. with pd-mapper
not having yet started or ADSP not being up etc.) results in a couple of
zombie power supply devices hanging around.

This is particularly noticeable when trying to suspend the device (even
s2idle): the PSY-internal thermal zone is inaccessible and returns
-ENODEV, which causes log spam.

Register the power supplies only after we received some notification
indicating battmgr is ready to take off.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Tested-by: Luca Weiss <luca.weiss@fairphone.com>
Link: https://lore.kernel.org/r/20231218-topic-battmgr_fixture_attempt-v1-1-6145745f34fe@linaro.org
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/qcom_battmgr.c | 109 +++++++++++++++-------------
 1 file changed, 60 insertions(+), 49 deletions(-)

diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c
index ec163d1bcd189..a12e2a66d516f 100644
--- a/drivers/power/supply/qcom_battmgr.c
+++ b/drivers/power/supply/qcom_battmgr.c
@@ -282,6 +282,7 @@ struct qcom_battmgr_wireless {
 
 struct qcom_battmgr {
 	struct device *dev;
+	struct auxiliary_device *adev;
 	struct pmic_glink_client *client;
 
 	enum qcom_battmgr_variant variant;
@@ -1293,11 +1294,69 @@ static void qcom_battmgr_enable_worker(struct work_struct *work)
 		dev_err(battmgr->dev, "failed to request power notifications\n");
 }
 
+static char *qcom_battmgr_battery[] = { "battery" };
+
+static void qcom_battmgr_register_psy(struct qcom_battmgr *battmgr)
+{
+	struct power_supply_config psy_cfg_supply = {};
+	struct auxiliary_device *adev = battmgr->adev;
+	struct power_supply_config psy_cfg = {};
+	struct device *dev = &adev->dev;
+
+	psy_cfg.drv_data = battmgr;
+	psy_cfg.of_node = adev->dev.of_node;
+
+	psy_cfg_supply.drv_data = battmgr;
+	psy_cfg_supply.of_node = adev->dev.of_node;
+	psy_cfg_supply.supplied_to = qcom_battmgr_battery;
+	psy_cfg_supply.num_supplicants = 1;
+
+	if (battmgr->variant == QCOM_BATTMGR_SC8280XP) {
+		battmgr->bat_psy = devm_power_supply_register(dev, &sc8280xp_bat_psy_desc, &psy_cfg);
+		if (IS_ERR(battmgr->bat_psy))
+			dev_err(dev, "failed to register battery power supply (%ld)\n",
+				PTR_ERR(battmgr->bat_psy));
+
+		battmgr->ac_psy = devm_power_supply_register(dev, &sc8280xp_ac_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->ac_psy))
+			dev_err(dev, "failed to register AC power supply (%ld)\n",
+				PTR_ERR(battmgr->ac_psy));
+
+		battmgr->usb_psy = devm_power_supply_register(dev, &sc8280xp_usb_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->usb_psy))
+			dev_err(dev, "failed to register USB power supply (%ld)\n",
+				PTR_ERR(battmgr->usb_psy));
+
+		battmgr->wls_psy = devm_power_supply_register(dev, &sc8280xp_wls_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->wls_psy))
+			dev_err(dev, "failed to register wireless charing power supply (%ld)\n",
+				PTR_ERR(battmgr->wls_psy));
+	} else {
+		battmgr->bat_psy = devm_power_supply_register(dev, &sm8350_bat_psy_desc, &psy_cfg);
+		if (IS_ERR(battmgr->bat_psy))
+			dev_err(dev, "failed to register battery power supply (%ld)\n",
+				PTR_ERR(battmgr->bat_psy));
+
+		battmgr->usb_psy = devm_power_supply_register(dev, &sm8350_usb_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->usb_psy))
+			dev_err(dev, "failed to register USB power supply (%ld)\n",
+				PTR_ERR(battmgr->usb_psy));
+
+		battmgr->wls_psy = devm_power_supply_register(dev, &sm8350_wls_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->wls_psy))
+			dev_err(dev, "failed to register wireless charing power supply (%ld)\n",
+				PTR_ERR(battmgr->wls_psy));
+	}
+}
+
 static void qcom_battmgr_pdr_notify(void *priv, int state)
 {
 	struct qcom_battmgr *battmgr = priv;
 
 	if (state == SERVREG_SERVICE_STATE_UP) {
+		if (!battmgr->bat_psy)
+			qcom_battmgr_register_psy(battmgr);
+
 		battmgr->service_up = true;
 		schedule_work(&battmgr->enable_work);
 	} else {
@@ -1312,13 +1371,9 @@ static const struct of_device_id qcom_battmgr_of_variants[] = {
 	{}
 };
 
-static char *qcom_battmgr_battery[] = { "battery" };
-
 static int qcom_battmgr_probe(struct auxiliary_device *adev,
 			      const struct auxiliary_device_id *id)
 {
-	struct power_supply_config psy_cfg_supply = {};
-	struct power_supply_config psy_cfg = {};
 	const struct of_device_id *match;
 	struct qcom_battmgr *battmgr;
 	struct device *dev = &adev->dev;
@@ -1328,14 +1383,7 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev,
 		return -ENOMEM;
 
 	battmgr->dev = dev;
-
-	psy_cfg.drv_data = battmgr;
-	psy_cfg.of_node = adev->dev.of_node;
-
-	psy_cfg_supply.drv_data = battmgr;
-	psy_cfg_supply.of_node = adev->dev.of_node;
-	psy_cfg_supply.supplied_to = qcom_battmgr_battery;
-	psy_cfg_supply.num_supplicants = 1;
+	battmgr->adev = adev;
 
 	INIT_WORK(&battmgr->enable_work, qcom_battmgr_enable_worker);
 	mutex_init(&battmgr->lock);
@@ -1347,43 +1395,6 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev,
 	else
 		battmgr->variant = QCOM_BATTMGR_SM8350;
 
-	if (battmgr->variant == QCOM_BATTMGR_SC8280XP) {
-		battmgr->bat_psy = devm_power_supply_register(dev, &sc8280xp_bat_psy_desc, &psy_cfg);
-		if (IS_ERR(battmgr->bat_psy))
-			return dev_err_probe(dev, PTR_ERR(battmgr->bat_psy),
-					     "failed to register battery power supply\n");
-
-		battmgr->ac_psy = devm_power_supply_register(dev, &sc8280xp_ac_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->ac_psy))
-			return dev_err_probe(dev, PTR_ERR(battmgr->ac_psy),
-					     "failed to register AC power supply\n");
-
-		battmgr->usb_psy = devm_power_supply_register(dev, &sc8280xp_usb_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->usb_psy))
-			return dev_err_probe(dev, PTR_ERR(battmgr->usb_psy),
-					     "failed to register USB power supply\n");
-
-		battmgr->wls_psy = devm_power_supply_register(dev, &sc8280xp_wls_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->wls_psy))
-			return dev_err_probe(dev, PTR_ERR(battmgr->wls_psy),
-					     "failed to register wireless charing power supply\n");
-	} else {
-		battmgr->bat_psy = devm_power_supply_register(dev, &sm8350_bat_psy_desc, &psy_cfg);
-		if (IS_ERR(battmgr->bat_psy))
-			return dev_err_probe(dev, PTR_ERR(battmgr->bat_psy),
-					     "failed to register battery power supply\n");
-
-		battmgr->usb_psy = devm_power_supply_register(dev, &sm8350_usb_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->usb_psy))
-			return dev_err_probe(dev, PTR_ERR(battmgr->usb_psy),
-					     "failed to register USB power supply\n");
-
-		battmgr->wls_psy = devm_power_supply_register(dev, &sm8350_wls_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->wls_psy))
-			return dev_err_probe(dev, PTR_ERR(battmgr->wls_psy),
-					     "failed to register wireless charing power supply\n");
-	}
-
 	battmgr->client = devm_pmic_glink_register_client(dev,
 							  PMIC_GLINK_OWNER_BATTMGR,
 							  qcom_battmgr_callback,
-- 
GitLab


From 97b9b383976e3347b05d8c409527c6e03c90cf72 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Thu, 21 Dec 2023 13:27:56 +0100
Subject: [PATCH 1921/4076] dt-bindings: power: reset: xilinx: Rename node
 names in examples

Rename zynqmp-power node name to power-management which is more aligned
with generic node name recommendation.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/920c839ae2c9c5803c6c08b8705a0d8338bb94bc.1703161663.git.michal.simek@amd.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml    | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml b/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
index 45792e216981a..799831636194f 100644
--- a/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
+++ b/Documentation/devicetree/bindings/power/reset/xlnx,zynqmp-power.yaml
@@ -57,7 +57,7 @@ examples:
 
     firmware {
       zynqmp-firmware {
-        zynqmp-power {
+        power-management {
           compatible = "xlnx,zynqmp-power";
           interrupts = <0 35 4>;
         };
@@ -70,7 +70,7 @@ examples:
 
     firmware {
       zynqmp-firmware {
-        zynqmp-power {
+        power-management {
           compatible = "xlnx,zynqmp-power";
           interrupt-parent = <&gic>;
           interrupts = <0 35 4>;
-- 
GitLab


From 370cc1579a79a29a6dba4d9ea8d4d0147aa41861 Mon Sep 17 00:00:00 2001
From: Hermes Zhang <chenhuiz@axis.com>
Date: Fri, 8 Dec 2023 11:47:07 +0800
Subject: [PATCH 1922/4076] dt-bindings: power: supply: bq24190: Add BQ24296
 compatible

The BQ24296 is most similar to the BQ24196, but the:
1. OTG config is split from CHG config (REG01)
2. ICHG (Fast Charge Current limit) range is smaller (<=3008mA)
3. NTC fault is simplified to 2 bits

Signed-off-by: Hermes Zhang <chenhuiz@axis.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231208034708.1248389-2-Hermes.Zhang@axis.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 Documentation/devicetree/bindings/power/supply/bq24190.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/power/supply/bq24190.yaml b/Documentation/devicetree/bindings/power/supply/bq24190.yaml
index d3ebc9de8c0b4..131b7e57d22f4 100644
--- a/Documentation/devicetree/bindings/power/supply/bq24190.yaml
+++ b/Documentation/devicetree/bindings/power/supply/bq24190.yaml
@@ -20,6 +20,7 @@ properties:
       - ti,bq24192
       - ti,bq24192i
       - ti,bq24196
+      - ti,bq24296
 
   reg:
     maxItems: 1
-- 
GitLab


From b150a703b56fb6eb282d059b421652ccd9155c23 Mon Sep 17 00:00:00 2001
From: Hermes Zhang <chenhuiz@axis.com>
Date: Fri, 8 Dec 2023 11:47:08 +0800
Subject: [PATCH 1923/4076] power: supply: bq24190_charger: Add support for
 BQ24296

The BQ24296 is most similar to the BQ24196, but the:
1. OTG config is split from CHG config (REG01)
2. ICHG (Fast Charge Current limit) range is smaller (<=3008mA)
3. NTC fault is simplified to 2 bits

Signed-off-by: Hermes Zhang <chenhuiz@axis.com>
Link: https://lore.kernel.org/r/20231208034708.1248389-3-Hermes.Zhang@axis.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq24190_charger.c | 457 +++++++++++++++++++------
 1 file changed, 354 insertions(+), 103 deletions(-)

diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c
index 1db290ee2591a..a8995a21fadbf 100644
--- a/drivers/power/supply/bq24190_charger.c
+++ b/drivers/power/supply/bq24190_charger.c
@@ -36,10 +36,16 @@
 #define BQ24190_REG_POC_WDT_RESET_SHIFT		6
 #define BQ24190_REG_POC_CHG_CONFIG_MASK		(BIT(5) | BIT(4))
 #define BQ24190_REG_POC_CHG_CONFIG_SHIFT	4
-#define BQ24190_REG_POC_CHG_CONFIG_DISABLE		0x0
-#define BQ24190_REG_POC_CHG_CONFIG_CHARGE		0x1
-#define BQ24190_REG_POC_CHG_CONFIG_OTG			0x2
-#define BQ24190_REG_POC_CHG_CONFIG_OTG_ALT		0x3
+#define BQ24190_REG_POC_CHG_CONFIG_DISABLE	0x0
+#define BQ24190_REG_POC_CHG_CONFIG_CHARGE	0x1
+#define BQ24190_REG_POC_CHG_CONFIG_OTG		0x2
+#define BQ24190_REG_POC_CHG_CONFIG_OTG_ALT	0x3
+#define BQ24296_REG_POC_OTG_CONFIG_MASK		BIT(5)
+#define BQ24296_REG_POC_OTG_CONFIG_SHIFT	5
+#define BQ24296_REG_POC_CHG_CONFIG_MASK		BIT(4)
+#define BQ24296_REG_POC_CHG_CONFIG_SHIFT	4
+#define BQ24296_REG_POC_OTG_CONFIG_DISABLE	0x0
+#define BQ24296_REG_POC_OTG_CONFIG_OTG		0x1
 #define BQ24190_REG_POC_SYS_MIN_MASK		(BIT(3) | BIT(2) | BIT(1))
 #define BQ24190_REG_POC_SYS_MIN_SHIFT		1
 #define BQ24190_REG_POC_SYS_MIN_MIN			3000
@@ -134,58 +140,23 @@
 #define BQ24190_REG_F_BAT_FAULT_SHIFT		3
 #define BQ24190_REG_F_NTC_FAULT_MASK		(BIT(2) | BIT(1) | BIT(0))
 #define BQ24190_REG_F_NTC_FAULT_SHIFT		0
+#define BQ24296_REG_F_NTC_FAULT_MASK		(BIT(1) | BIT(0))
+#define BQ24296_REG_F_NTC_FAULT_SHIFT		0
 
 #define BQ24190_REG_VPRS	0x0A /* Vendor/Part/Revision Status */
 #define BQ24190_REG_VPRS_PN_MASK		(BIT(5) | BIT(4) | BIT(3))
 #define BQ24190_REG_VPRS_PN_SHIFT		3
-#define BQ24190_REG_VPRS_PN_24190			0x4
-#define BQ24190_REG_VPRS_PN_24192			0x5 /* Also 24193, 24196 */
-#define BQ24190_REG_VPRS_PN_24192I			0x3
+#define BQ24190_REG_VPRS_PN_24190		0x4
+#define BQ24190_REG_VPRS_PN_24192		0x5 /* Also 24193, 24196 */
+#define BQ24190_REG_VPRS_PN_24192I		0x3
+#define BQ24296_REG_VPRS_PN_MASK		(BIT(7) | BIT(6) | BIT(5))
+#define BQ24296_REG_VPRS_PN_SHIFT		5
+#define BQ24296_REG_VPRS_PN_24296		0x1
 #define BQ24190_REG_VPRS_TS_PROFILE_MASK	BIT(2)
 #define BQ24190_REG_VPRS_TS_PROFILE_SHIFT	2
 #define BQ24190_REG_VPRS_DEV_REG_MASK		(BIT(1) | BIT(0))
 #define BQ24190_REG_VPRS_DEV_REG_SHIFT		0
 
-/*
- * The FAULT register is latched by the bq24190 (except for NTC_FAULT)
- * so the first read after a fault returns the latched value and subsequent
- * reads return the current value.  In order to return the fault status
- * to the user, have the interrupt handler save the reg's value and retrieve
- * it in the appropriate health/status routine.
- */
-struct bq24190_dev_info {
-	struct i2c_client		*client;
-	struct device			*dev;
-	struct extcon_dev		*edev;
-	struct power_supply		*charger;
-	struct power_supply		*battery;
-	struct delayed_work		input_current_limit_work;
-	char				model_name[I2C_NAME_SIZE];
-	bool				initialized;
-	bool				irq_event;
-	bool				otg_vbus_enabled;
-	int				charge_type;
-	u16				sys_min;
-	u16				iprechg;
-	u16				iterm;
-	u32				ichg;
-	u32				ichg_max;
-	u32				vreg;
-	u32				vreg_max;
-	struct mutex			f_reg_lock;
-	u8				f_reg;
-	u8				ss_reg;
-	u8				watchdog;
-};
-
-static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi,
-					   const union power_supply_propval *val);
-
-static const unsigned int bq24190_usb_extcon_cable[] = {
-	EXTCON_USB,
-	EXTCON_NONE,
-};
-
 /*
  * The tables below provide a 2-way mapping for the value that goes in
  * the register field and the real-world value that it represents.
@@ -211,6 +182,9 @@ static const int bq24190_ccc_ichg_values[] = {
 	4096000, 4160000, 4224000, 4288000, 4352000, 4416000, 4480000, 4544000
 };
 
+/* ICHG higher than 3008mA is not supported in BQ24296 */
+#define BQ24296_CCC_ICHG_VALUES_LEN	40
+
 /* REG04[7:2] (VREG) in uV */
 static const int bq24190_cvc_vreg_values[] = {
 	3504000, 3520000, 3536000, 3552000, 3568000, 3584000, 3600000, 3616000,
@@ -228,6 +202,68 @@ static const int bq24190_ictrc_treg_values[] = {
 	600, 800, 1000, 1200
 };
 
+enum bq24190_chip {
+	BQ24190,
+	BQ24192,
+	BQ24192i,
+	BQ24196,
+	BQ24296,
+};
+
+/*
+ * The FAULT register is latched by the bq24190 (except for NTC_FAULT)
+ * so the first read after a fault returns the latched value and subsequent
+ * reads return the current value.  In order to return the fault status
+ * to the user, have the interrupt handler save the reg's value and retrieve
+ * it in the appropriate health/status routine.
+ */
+struct bq24190_dev_info {
+	struct i2c_client		*client;
+	struct device			*dev;
+	struct extcon_dev		*edev;
+	struct power_supply		*charger;
+	struct power_supply		*battery;
+	struct delayed_work		input_current_limit_work;
+	char				model_name[I2C_NAME_SIZE];
+	bool				initialized;
+	bool				irq_event;
+	bool				otg_vbus_enabled;
+	int				charge_type;
+	u16				sys_min;
+	u16				iprechg;
+	u16				iterm;
+	u32				ichg;
+	u32				ichg_max;
+	u32				vreg;
+	u32				vreg_max;
+	struct mutex			f_reg_lock;
+	u8				f_reg;
+	u8				ss_reg;
+	u8				watchdog;
+	const struct bq24190_chip_info	*info;
+};
+
+struct bq24190_chip_info {
+	int ichg_array_size;
+#ifdef CONFIG_REGULATOR
+	const struct regulator_desc vbus_desc;
+#endif
+	int (*check_chip)(struct bq24190_dev_info *bdi);
+	int (*set_chg_config)(struct bq24190_dev_info *bdi, const u8 chg_config);
+	int (*set_otg_vbus)(struct bq24190_dev_info *bdi, bool enable);
+	u8 ntc_fault_mask;
+	int (*get_ntc_status)(const u8 value);
+};
+
+static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi,
+					   const union power_supply_propval *val);
+
+static const unsigned int bq24190_usb_extcon_cable[] = {
+	EXTCON_USB,
+	EXTCON_NONE,
+};
+
+
 /*
  * Return the index in 'tbl' of greatest value that is less than or equal to
  * 'val'.  The index range returned is 0 to 'tbl_size' - 1.  Assumes that
@@ -529,6 +565,43 @@ static int bq24190_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable)
 	return ret;
 }
 
+static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable)
+{
+	int ret;
+
+	ret = pm_runtime_resume_and_get(bdi->dev);
+	if (ret < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", ret);
+		return ret;
+	}
+
+	bdi->otg_vbus_enabled = enable;
+	if (enable) {
+		ret = bq24190_write_mask(bdi, BQ24190_REG_POC,
+					 BQ24296_REG_POC_CHG_CONFIG_MASK,
+					 BQ24296_REG_POC_CHG_CONFIG_SHIFT,
+					 BQ24190_REG_POC_CHG_CONFIG_DISABLE);
+
+		if (ret < 0)
+			goto out;
+
+		ret = bq24190_write_mask(bdi, BQ24190_REG_POC,
+					 BQ24296_REG_POC_OTG_CONFIG_MASK,
+					 BQ24296_REG_POC_CHG_CONFIG_SHIFT,
+					 BQ24296_REG_POC_OTG_CONFIG_OTG);
+	} else
+		ret = bq24190_write_mask(bdi, BQ24190_REG_POC,
+					 BQ24296_REG_POC_OTG_CONFIG_MASK,
+					 BQ24296_REG_POC_CHG_CONFIG_SHIFT,
+					 BQ24296_REG_POC_OTG_CONFIG_DISABLE);
+
+out:
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+
+	return ret;
+}
+
 #ifdef CONFIG_REGULATOR
 static int bq24190_vbus_enable(struct regulator_dev *dev)
 {
@@ -567,6 +640,43 @@ static int bq24190_vbus_is_enabled(struct regulator_dev *dev)
 	return bdi->otg_vbus_enabled;
 }
 
+static int bq24296_vbus_enable(struct regulator_dev *dev)
+{
+	return bq24296_set_otg_vbus(rdev_get_drvdata(dev), true);
+}
+
+static int bq24296_vbus_disable(struct regulator_dev *dev)
+{
+	return bq24296_set_otg_vbus(rdev_get_drvdata(dev), false);
+}
+
+static int bq24296_vbus_is_enabled(struct regulator_dev *dev)
+{
+	struct bq24190_dev_info *bdi = rdev_get_drvdata(dev);
+	int ret;
+	u8 val;
+
+	ret = pm_runtime_resume_and_get(bdi->dev);
+	if (ret < 0) {
+		dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", ret);
+		return ret;
+	}
+
+	ret = bq24190_read_mask(bdi, BQ24190_REG_POC,
+				BQ24296_REG_POC_OTG_CONFIG_MASK,
+				BQ24296_REG_POC_OTG_CONFIG_SHIFT, &val);
+
+	pm_runtime_mark_last_busy(bdi->dev);
+	pm_runtime_put_autosuspend(bdi->dev);
+
+	if (ret)
+		return ret;
+
+	bdi->otg_vbus_enabled = (val == BQ24296_REG_POC_OTG_CONFIG_OTG);
+
+	return bdi->otg_vbus_enabled;
+}
+
 static const struct regulator_ops bq24190_vbus_ops = {
 	.enable = bq24190_vbus_enable,
 	.disable = bq24190_vbus_disable,
@@ -583,6 +693,22 @@ static const struct regulator_desc bq24190_vbus_desc = {
 	.n_voltages = 1,
 };
 
+static const struct regulator_ops bq24296_vbus_ops = {
+	.enable = bq24296_vbus_enable,
+	.disable = bq24296_vbus_disable,
+	.is_enabled = bq24296_vbus_is_enabled,
+};
+
+static const struct regulator_desc bq24296_vbus_desc = {
+	.name = "usb_otg_vbus",
+	.of_match = "usb-otg-vbus",
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+	.ops = &bq24296_vbus_ops,
+	.fixed_uV = 5000000,
+	.n_voltages = 1,
+};
+
 static const struct regulator_init_data bq24190_vbus_init_data = {
 	.constraints = {
 		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
@@ -602,7 +728,7 @@ static int bq24190_register_vbus_regulator(struct bq24190_dev_info *bdi)
 	else
 		cfg.init_data = &bq24190_vbus_init_data;
 	cfg.driver_data = bdi;
-	reg = devm_regulator_register(bdi->dev, &bq24190_vbus_desc, &cfg);
+	reg = devm_regulator_register(bdi->dev, &bdi->info->vbus_desc, &cfg);
 	if (IS_ERR(reg)) {
 		ret = PTR_ERR(reg);
 		dev_err(bdi->dev, "Can't register regulator: %d\n", ret);
@@ -678,7 +804,7 @@ static int bq24190_set_config(struct bq24190_dev_info *bdi)
 					    BQ24190_REG_CCC_ICHG_MASK,
 					    BQ24190_REG_CCC_ICHG_SHIFT,
 					    bq24190_ccc_ichg_values,
-					    ARRAY_SIZE(bq24190_ccc_ichg_values),
+					    bdi->info->ichg_array_size,
 					    bdi->ichg);
 		if (ret < 0)
 			return ret;
@@ -777,6 +903,24 @@ static int bq24190_charger_get_charge_type(struct bq24190_dev_info *bdi,
 	return 0;
 }
 
+static int bq24190_battery_set_chg_config(struct bq24190_dev_info *bdi,
+		const u8 chg_config)
+{
+	return bq24190_write_mask(bdi, BQ24190_REG_POC,
+			BQ24190_REG_POC_CHG_CONFIG_MASK,
+			BQ24190_REG_POC_CHG_CONFIG_SHIFT,
+			chg_config);
+}
+
+static int bq24296_battery_set_chg_config(struct bq24190_dev_info *bdi,
+		const u8 chg_config)
+{
+	return bq24190_write_mask(bdi, BQ24190_REG_POC,
+			BQ24296_REG_POC_CHG_CONFIG_MASK,
+			BQ24296_REG_POC_CHG_CONFIG_SHIFT,
+			chg_config);
+}
+
 static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi,
 		const union power_supply_propval *val)
 {
@@ -835,9 +979,50 @@ static int bq24190_charger_set_charge_type(struct bq24190_dev_info *bdi,
 			return ret;
 	}
 
-	return bq24190_write_mask(bdi, BQ24190_REG_POC,
-			BQ24190_REG_POC_CHG_CONFIG_MASK,
-			BQ24190_REG_POC_CHG_CONFIG_SHIFT, chg_config);
+	return bdi->info->set_chg_config(bdi, chg_config);
+}
+
+static int bq24190_charger_get_ntc_status(u8 value)
+{
+	int health;
+
+	switch (value >> BQ24190_REG_F_NTC_FAULT_SHIFT & 0x7) {
+	case 0x1: /* TS1  Cold */
+	case 0x3: /* TS2  Cold */
+	case 0x5: /* Both Cold */
+		health = POWER_SUPPLY_HEALTH_COLD;
+		break;
+	case 0x2: /* TS1  Hot */
+	case 0x4: /* TS2  Hot */
+	case 0x6: /* Both Hot */
+		health = POWER_SUPPLY_HEALTH_OVERHEAT;
+		break;
+	default:
+		health = POWER_SUPPLY_HEALTH_UNKNOWN;
+	}
+
+	return health;
+}
+
+static int bq24296_charger_get_ntc_status(u8 value)
+{
+	int health;
+
+	switch (value >> BQ24296_REG_F_NTC_FAULT_SHIFT & 0x3) {
+	case 0x0: /* Normal */
+		health = POWER_SUPPLY_HEALTH_GOOD;
+		break;
+	case 0x1: /* Hot */
+		health = POWER_SUPPLY_HEALTH_OVERHEAT;
+		break;
+	case 0x2: /* Cold */
+		health = POWER_SUPPLY_HEALTH_COLD;
+		break;
+	default:
+		health = POWER_SUPPLY_HEALTH_UNKNOWN;
+	}
+
+	return health;
 }
 
 static int bq24190_charger_get_health(struct bq24190_dev_info *bdi,
@@ -850,21 +1035,8 @@ static int bq24190_charger_get_health(struct bq24190_dev_info *bdi,
 	v = bdi->f_reg;
 	mutex_unlock(&bdi->f_reg_lock);
 
-	if (v & BQ24190_REG_F_NTC_FAULT_MASK) {
-		switch (v >> BQ24190_REG_F_NTC_FAULT_SHIFT & 0x7) {
-		case 0x1: /* TS1  Cold */
-		case 0x3: /* TS2  Cold */
-		case 0x5: /* Both Cold */
-			health = POWER_SUPPLY_HEALTH_COLD;
-			break;
-		case 0x2: /* TS1  Hot */
-		case 0x4: /* TS2  Hot */
-		case 0x6: /* Both Hot */
-			health = POWER_SUPPLY_HEALTH_OVERHEAT;
-			break;
-		default:
-			health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		}
+	if (v & bdi->info->ntc_fault_mask) {
+		health = bdi->info->get_ntc_status(v);
 	} else if (v & BQ24190_REG_F_BAT_FAULT_MASK) {
 		health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
 	} else if (v & BQ24190_REG_F_CHRG_FAULT_MASK) {
@@ -1015,7 +1187,7 @@ static int bq24190_charger_get_current(struct bq24190_dev_info *bdi,
 	ret = bq24190_get_field_val(bdi, BQ24190_REG_CCC,
 			BQ24190_REG_CCC_ICHG_MASK, BQ24190_REG_CCC_ICHG_SHIFT,
 			bq24190_ccc_ichg_values,
-			ARRAY_SIZE(bq24190_ccc_ichg_values), &curr);
+			bdi->info->ichg_array_size, &curr);
 	if (ret < 0)
 		return ret;
 
@@ -1055,7 +1227,7 @@ static int bq24190_charger_set_current(struct bq24190_dev_info *bdi,
 	ret = bq24190_set_field_val(bdi, BQ24190_REG_CCC,
 			BQ24190_REG_CCC_ICHG_MASK, BQ24190_REG_CCC_ICHG_SHIFT,
 			bq24190_ccc_ichg_values,
-			ARRAY_SIZE(bq24190_ccc_ichg_values), curr);
+			bdi->info->ichg_array_size, curr);
 	if (ret < 0)
 		return ret;
 
@@ -1395,26 +1567,9 @@ static int bq24190_battery_get_health(struct bq24190_dev_info *bdi,
 	if (v & BQ24190_REG_F_BAT_FAULT_MASK) {
 		health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
 	} else {
-		v &= BQ24190_REG_F_NTC_FAULT_MASK;
-		v >>= BQ24190_REG_F_NTC_FAULT_SHIFT;
+		v &= bdi->info->ntc_fault_mask;
 
-		switch (v) {
-		case 0x0: /* Normal */
-			health = POWER_SUPPLY_HEALTH_GOOD;
-			break;
-		case 0x1: /* TS1 Cold */
-		case 0x3: /* TS2 Cold */
-		case 0x5: /* Both Cold */
-			health = POWER_SUPPLY_HEALTH_COLD;
-			break;
-		case 0x2: /* TS1 Hot */
-		case 0x4: /* TS2 Hot */
-		case 0x6: /* Both Hot */
-			health = POWER_SUPPLY_HEALTH_OVERHEAT;
-			break;
-		default:
-			health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		}
+		health = v ? bdi->info->get_ntc_status(v) : POWER_SUPPLY_HEALTH_GOOD;
 	}
 
 	val->intval = health;
@@ -1601,12 +1756,13 @@ static int bq24190_configure_usb_otg(struct bq24190_dev_info *bdi, u8 ss_reg)
 static void bq24190_check_status(struct bq24190_dev_info *bdi)
 {
 	const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK;
-	const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK
-				| BQ24190_REG_F_NTC_FAULT_MASK;
+	u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK;
 	bool alert_charger = false, alert_battery = false;
 	u8 ss_reg = 0, f_reg = 0;
 	int i, ret;
 
+	battery_mask_f |= bdi->info->ntc_fault_mask;
+
 	ret = bq24190_read(bdi, BQ24190_REG_SS, &ss_reg);
 	if (ret < 0) {
 		dev_err(bdi->dev, "Can't read SS reg: %d\n", ret);
@@ -1633,7 +1789,7 @@ static void bq24190_check_status(struct bq24190_dev_info *bdi)
 			!!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK),
 			!!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK),
 			!!(f_reg & BQ24190_REG_F_BAT_FAULT_MASK),
-			!!(f_reg & BQ24190_REG_F_NTC_FAULT_MASK));
+			!!(f_reg & bdi->info->ntc_fault_mask));
 
 		mutex_lock(&bdi->f_reg_lock);
 		if ((bdi->f_reg & battery_mask_f) != (f_reg & battery_mask_f))
@@ -1696,12 +1852,11 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int bq24190_hw_init(struct bq24190_dev_info *bdi)
+static int bq24190_check_chip(struct bq24190_dev_info *bdi)
 {
 	u8 v;
 	int ret;
 
-	/* First check that the device really is what its supposed to be */
 	ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS,
 			BQ24190_REG_VPRS_PN_MASK,
 			BQ24190_REG_VPRS_PN_SHIFT,
@@ -1719,6 +1874,40 @@ static int bq24190_hw_init(struct bq24190_dev_info *bdi)
 		return -ENODEV;
 	}
 
+	return 0;
+}
+
+static int bq24296_check_chip(struct bq24190_dev_info *bdi)
+{
+	u8 v;
+	int ret;
+
+	ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS,
+			BQ24296_REG_VPRS_PN_MASK,
+			BQ24296_REG_VPRS_PN_SHIFT,
+			&v);
+	if (ret < 0)
+		return ret;
+
+	switch (v) {
+	case BQ24296_REG_VPRS_PN_24296:
+		break;
+	default:
+		dev_err(bdi->dev, "Error unknown model: 0x%02x\n", v);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int bq24190_hw_init(struct bq24190_dev_info *bdi)
+{
+	int ret;
+
+	ret = bdi->info->check_chip(bdi);
+	if (ret < 0)
+		return ret;
+
 	ret = bq24190_register_reset(bdi);
 	if (ret < 0)
 		return ret;
@@ -1736,7 +1925,8 @@ static int bq24190_get_config(struct bq24190_dev_info *bdi)
 	struct power_supply_battery_info *info;
 	int v, idx;
 
-	idx = ARRAY_SIZE(bq24190_ccc_ichg_values) - 1;
+	idx = bdi->info->ichg_array_size - 1;
+
 	bdi->ichg_max = bq24190_ccc_ichg_values[idx];
 
 	idx = ARRAY_SIZE(bq24190_cvc_vreg_values) - 1;
@@ -1781,6 +1971,64 @@ static int bq24190_get_config(struct bq24190_dev_info *bdi)
 	return 0;
 }
 
+static const struct bq24190_chip_info bq24190_chip_info_tbl[] = {
+	[BQ24190] = {
+		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = bq24190_vbus_desc,
+#endif
+		.check_chip = bq24190_check_chip,
+		.set_chg_config = bq24190_battery_set_chg_config,
+		.ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24190_charger_get_ntc_status,
+		.set_otg_vbus = bq24190_set_otg_vbus,
+	},
+	[BQ24192] = {
+		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = bq24190_vbus_desc,
+#endif
+		.check_chip = bq24190_check_chip,
+		.set_chg_config = bq24190_battery_set_chg_config,
+		.ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24190_charger_get_ntc_status,
+		.set_otg_vbus = bq24190_set_otg_vbus,
+	},
+	[BQ24192i] = {
+		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = bq24190_vbus_desc,
+#endif
+		.check_chip = bq24190_check_chip,
+		.set_chg_config = bq24190_battery_set_chg_config,
+		.ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24190_charger_get_ntc_status,
+		.set_otg_vbus = bq24190_set_otg_vbus,
+	},
+	[BQ24196] = {
+		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = bq24190_vbus_desc,
+#endif
+		.check_chip = bq24190_check_chip,
+		.set_chg_config = bq24190_battery_set_chg_config,
+		.ntc_fault_mask = BQ24190_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24190_charger_get_ntc_status,
+		.set_otg_vbus = bq24190_set_otg_vbus,
+	},
+	[BQ24296] = {
+		.ichg_array_size = BQ24296_CCC_ICHG_VALUES_LEN,
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = bq24296_vbus_desc,
+#endif
+		.check_chip = bq24296_check_chip,
+		.set_chg_config = bq24296_battery_set_chg_config,
+		.ntc_fault_mask = BQ24296_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24296_charger_get_ntc_status,
+		.set_otg_vbus = bq24296_set_otg_vbus,
+	},
+};
+
 static int bq24190_probe(struct i2c_client *client)
 {
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
@@ -1804,6 +2052,7 @@ static int bq24190_probe(struct i2c_client *client)
 	bdi->client = client;
 	bdi->dev = dev;
 	strscpy(bdi->model_name, id->name, sizeof(bdi->model_name));
+	bdi->info = i2c_get_match_data(client);
 	mutex_init(&bdi->f_reg_lock);
 	bdi->charge_type = POWER_SUPPLY_CHARGE_TYPE_FAST;
 	bdi->f_reg = 0;
@@ -1940,7 +2189,7 @@ static void bq24190_shutdown(struct i2c_client *client)
 	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
 
 	/* Turn off 5V boost regulator on shutdown */
-	bq24190_set_otg_vbus(bdi, false);
+	bdi->info->set_otg_vbus(bdi, false);
 }
 
 static __maybe_unused int bq24190_runtime_suspend(struct device *dev)
@@ -2029,19 +2278,21 @@ static const struct dev_pm_ops bq24190_pm_ops = {
 };
 
 static const struct i2c_device_id bq24190_i2c_ids[] = {
-	{ "bq24190" },
-	{ "bq24192" },
-	{ "bq24192i" },
-	{ "bq24196" },
+	{ "bq24190", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24190] },
+	{ "bq24192", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24192] },
+	{ "bq24192i", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24192i] },
+	{ "bq24196", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24196] },
+	{ "bq24296", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24296] },
 	{ },
 };
 MODULE_DEVICE_TABLE(i2c, bq24190_i2c_ids);
 
 static const struct of_device_id bq24190_of_match[] = {
-	{ .compatible = "ti,bq24190", },
-	{ .compatible = "ti,bq24192", },
-	{ .compatible = "ti,bq24192i", },
-	{ .compatible = "ti,bq24196", },
+	{ .compatible = "ti,bq24190", .data = &bq24190_chip_info_tbl[BQ24190] },
+	{ .compatible = "ti,bq24192", .data = &bq24190_chip_info_tbl[BQ24192] },
+	{ .compatible = "ti,bq24192i", .data = &bq24190_chip_info_tbl[BQ24192i] },
+	{ .compatible = "ti,bq24196", .data = &bq24190_chip_info_tbl[BQ24196] },
+	{ .compatible = "ti,bq24296", .data = &bq24190_chip_info_tbl[BQ24296] },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, bq24190_of_match);
-- 
GitLab


From c1b9f2c66eed3261db76cccd8a22a9affae8dcbf Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Thu, 20 Oct 2022 21:21:09 +0200
Subject: [PATCH 1924/4076] vdpa: Fix an error handling path in
 eni_vdpa_probe()

After a successful vp_legacy_probe() call, vp_legacy_remove() should be
called in the error handling path, as already done in the remove function.

Add the missing call.

Fixes: e85087beedca ("eni_vdpa: add vDPA driver for Alibaba ENI")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Message-Id: <a7b0ef1eabd081f1c7c894e9b11de01678e85dee.1666293559.git.christophe.jaillet@wanadoo.fr>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/alibaba/eni_vdpa.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c
index 5a09a09cca709..cce3d1837104c 100644
--- a/drivers/vdpa/alibaba/eni_vdpa.c
+++ b/drivers/vdpa/alibaba/eni_vdpa.c
@@ -497,7 +497,7 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!eni_vdpa->vring) {
 		ret = -ENOMEM;
 		ENI_ERR(pdev, "failed to allocate virtqueues\n");
-		goto err;
+		goto err_remove_vp_legacy;
 	}
 
 	for (i = 0; i < eni_vdpa->queues; i++) {
@@ -509,11 +509,13 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ret = vdpa_register_device(&eni_vdpa->vdpa, eni_vdpa->queues);
 	if (ret) {
 		ENI_ERR(pdev, "failed to register to vdpa bus\n");
-		goto err;
+		goto err_remove_vp_legacy;
 	}
 
 	return 0;
 
+err_remove_vp_legacy:
+	vp_legacy_remove(&eni_vdpa->ldev);
 err:
 	put_device(&eni_vdpa->vdpa.dev);
 	return ret;
-- 
GitLab


From 020e71c7ffc25dfe29ed9be6c2d39af7bd7f661f Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:26:01 -0300
Subject: [PATCH 1925/4076] iio: adc: ad7091r: Allow users to configure device
 events

AD7091R-5 devices are supported by the ad7091r-5 driver together with
the ad7091r-base driver. Those drivers declared iio events for notifying
user space when ADC readings fall bellow the thresholds of low limit
registers or above the values set in high limit registers.
However, to configure iio events and their thresholds, a set of callback
functions must be implemented and those were not present until now.
The consequence of trying to configure ad7091r-5 events without the
proper callback functions was a null pointer dereference in the kernel
because the pointers to the callback functions were not set.

Implement event configuration callbacks allowing users to read/write
event thresholds and enable/disable event generation.

Since the event spec structs are generic to AD7091R devices, also move
those from the ad7091r-5 driver the base driver so they can be reused
when support for ad7091r-2/-4/-8 be added.

Fixes: ca69300173b6 ("iio: adc: Add support for AD7091R5 ADC")
Suggested-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/59552d3548dabd56adc3107b7b4869afee2b0c3c.1703013352.git.marcelo.schmitt1@gmail.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 156 +++++++++++++++++++++++++++++++++
 drivers/iio/adc/ad7091r-base.h |   6 ++
 drivers/iio/adc/ad7091r5.c     |  28 +-----
 3 files changed, 166 insertions(+), 24 deletions(-)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index d3d287d3b9535..6d93da1548108 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/bitfield.h>
 #include <linux/iio/events.h>
 #include <linux/iio/iio.h>
 #include <linux/interrupt.h>
@@ -50,6 +51,27 @@ struct ad7091r_state {
 	struct mutex lock; /*lock to prevent concurent reads */
 };
 
+const struct iio_event_spec ad7091r_events[] = {
+	{
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_RISING,
+		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
+				 BIT(IIO_EV_INFO_ENABLE),
+	},
+	{
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_FALLING,
+		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
+				 BIT(IIO_EV_INFO_ENABLE),
+	},
+	{
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_EITHER,
+		.mask_separate = BIT(IIO_EV_INFO_HYSTERESIS),
+	},
+};
+EXPORT_SYMBOL_NS_GPL(ad7091r_events, IIO_AD7091R);
+
 static int ad7091r_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode)
 {
 	int ret, conf;
@@ -169,8 +191,142 @@ unlock:
 	return ret;
 }
 
+static int ad7091r_read_event_config(struct iio_dev *indio_dev,
+				     const struct iio_chan_spec *chan,
+				     enum iio_event_type type,
+				     enum iio_event_direction dir)
+{
+	struct ad7091r_state *st = iio_priv(indio_dev);
+	int val, ret;
+
+	switch (dir) {
+	case IIO_EV_DIR_RISING:
+		ret = regmap_read(st->map,
+				  AD7091R_REG_CH_HIGH_LIMIT(chan->channel),
+				  &val);
+		if (ret)
+			return ret;
+		return val != AD7091R_HIGH_LIMIT;
+	case IIO_EV_DIR_FALLING:
+		ret = regmap_read(st->map,
+				  AD7091R_REG_CH_LOW_LIMIT(chan->channel),
+				  &val);
+		if (ret)
+			return ret;
+		return val != AD7091R_LOW_LIMIT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ad7091r_write_event_config(struct iio_dev *indio_dev,
+				      const struct iio_chan_spec *chan,
+				      enum iio_event_type type,
+				      enum iio_event_direction dir, int state)
+{
+	struct ad7091r_state *st = iio_priv(indio_dev);
+
+	if (state) {
+		return regmap_set_bits(st->map, AD7091R_REG_CONF,
+				       AD7091R_REG_CONF_ALERT_EN);
+	} else {
+		/*
+		 * Set thresholds either to 0 or to 2^12 - 1 as appropriate to
+		 * prevent alerts and thus disable event generation.
+		 */
+		switch (dir) {
+		case IIO_EV_DIR_RISING:
+			return regmap_write(st->map,
+					    AD7091R_REG_CH_HIGH_LIMIT(chan->channel),
+					    AD7091R_HIGH_LIMIT);
+		case IIO_EV_DIR_FALLING:
+			return regmap_write(st->map,
+					    AD7091R_REG_CH_LOW_LIMIT(chan->channel),
+					    AD7091R_LOW_LIMIT);
+		default:
+			return -EINVAL;
+		}
+	}
+}
+
+static int ad7091r_read_event_value(struct iio_dev *indio_dev,
+				    const struct iio_chan_spec *chan,
+				    enum iio_event_type type,
+				    enum iio_event_direction dir,
+				    enum iio_event_info info, int *val, int *val2)
+{
+	struct ad7091r_state *st = iio_priv(indio_dev);
+	int ret;
+
+	switch (info) {
+	case IIO_EV_INFO_VALUE:
+		switch (dir) {
+		case IIO_EV_DIR_RISING:
+			ret = regmap_read(st->map,
+					  AD7091R_REG_CH_HIGH_LIMIT(chan->channel),
+					  val);
+			if (ret)
+				return ret;
+			return IIO_VAL_INT;
+		case IIO_EV_DIR_FALLING:
+			ret = regmap_read(st->map,
+					  AD7091R_REG_CH_LOW_LIMIT(chan->channel),
+					  val);
+			if (ret)
+				return ret;
+			return IIO_VAL_INT;
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_INFO_HYSTERESIS:
+		ret = regmap_read(st->map,
+				  AD7091R_REG_CH_HYSTERESIS(chan->channel),
+				  val);
+		if (ret)
+			return ret;
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ad7091r_write_event_value(struct iio_dev *indio_dev,
+				     const struct iio_chan_spec *chan,
+				     enum iio_event_type type,
+				     enum iio_event_direction dir,
+				     enum iio_event_info info, int val, int val2)
+{
+	struct ad7091r_state *st = iio_priv(indio_dev);
+
+	switch (info) {
+	case IIO_EV_INFO_VALUE:
+		switch (dir) {
+		case IIO_EV_DIR_RISING:
+			return regmap_write(st->map,
+					    AD7091R_REG_CH_HIGH_LIMIT(chan->channel),
+					    val);
+		case IIO_EV_DIR_FALLING:
+			return regmap_write(st->map,
+					    AD7091R_REG_CH_LOW_LIMIT(chan->channel),
+					    val);
+		default:
+			return -EINVAL;
+		}
+	case IIO_EV_INFO_HYSTERESIS:
+		return regmap_write(st->map,
+				    AD7091R_REG_CH_HYSTERESIS(chan->channel),
+				    val);
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct iio_info ad7091r_info = {
 	.read_raw = ad7091r_read_raw,
+	.read_event_config = &ad7091r_read_event_config,
+	.write_event_config = &ad7091r_write_event_config,
+	.read_event_value = &ad7091r_read_event_value,
+	.write_event_value = &ad7091r_write_event_value,
 };
 
 static irqreturn_t ad7091r_event_handler(int irq, void *private)
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index 509748aef9b19..7a78976a2f806 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -8,6 +8,10 @@
 #ifndef __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 #define __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 
+/* AD7091R_REG_CH_LIMIT */
+#define AD7091R_HIGH_LIMIT		0xFFF
+#define AD7091R_LOW_LIMIT		0x0
+
 struct device;
 struct ad7091r_state;
 
@@ -17,6 +21,8 @@ struct ad7091r_chip_info {
 	unsigned int vref_mV;
 };
 
+extern const struct iio_event_spec ad7091r_events[3];
+
 extern const struct regmap_config ad7091r_regmap_config;
 
 int ad7091r_probe(struct device *dev, const char *name,
diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c
index 2f048527b7b78..dae98c95ebb87 100644
--- a/drivers/iio/adc/ad7091r5.c
+++ b/drivers/iio/adc/ad7091r5.c
@@ -12,26 +12,6 @@
 
 #include "ad7091r-base.h"
 
-static const struct iio_event_spec ad7091r5_events[] = {
-	{
-		.type = IIO_EV_TYPE_THRESH,
-		.dir = IIO_EV_DIR_RISING,
-		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
-				 BIT(IIO_EV_INFO_ENABLE),
-	},
-	{
-		.type = IIO_EV_TYPE_THRESH,
-		.dir = IIO_EV_DIR_FALLING,
-		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
-				 BIT(IIO_EV_INFO_ENABLE),
-	},
-	{
-		.type = IIO_EV_TYPE_THRESH,
-		.dir = IIO_EV_DIR_EITHER,
-		.mask_separate = BIT(IIO_EV_INFO_HYSTERESIS),
-	},
-};
-
 #define AD7091R_CHANNEL(idx, bits, ev, num_ev) { \
 	.type = IIO_VOLTAGE, \
 	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \
@@ -44,10 +24,10 @@ static const struct iio_event_spec ad7091r5_events[] = {
 	.scan_type.realbits = bits, \
 }
 static const struct iio_chan_spec ad7091r5_channels_irq[] = {
-	AD7091R_CHANNEL(0, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)),
-	AD7091R_CHANNEL(1, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)),
-	AD7091R_CHANNEL(2, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)),
-	AD7091R_CHANNEL(3, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)),
+	AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(2, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(3, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
 };
 
 static const struct iio_chan_spec ad7091r5_channels_noirq[] = {
-- 
GitLab


From e71c5c89bcb165a02df35325aa13d1ee40112401 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:26:27 -0300
Subject: [PATCH 1926/4076] iio: adc: ad7091r: Enable internal vref if external
 vref is not supplied

The ADC needs a voltage reference to work correctly.
Users can provide an external voltage reference or use the chip internal
reference to operate the ADC.
The availability of an in chip reference for the ADC saves the user from
having to supply an external voltage reference, which makes the external
reference an optional property as described in the device tree
documentation.
Though, to use the internal reference, it must be enabled by writing to
the configuration register.
Enable AD7091R internal voltage reference if no external vref is supplied.

Fixes: 260442cc5be4 ("iio: adc: ad7091r5: Add scale and external VREF support")
Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/b865033fa6a4fc4bf2b4a98ec51a6144e0f64f77.1703013352.git.marcelo.schmitt1@gmail.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 7 +++++++
 drivers/iio/adc/ad7091r-base.h | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 6d93da1548108..7ccc9b44dcd88 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -406,7 +406,14 @@ int ad7091r_probe(struct device *dev, const char *name,
 	if (IS_ERR(st->vref)) {
 		if (PTR_ERR(st->vref) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
+
 		st->vref = NULL;
+		/* Enable internal vref */
+		ret = regmap_set_bits(st->map, AD7091R_REG_CONF,
+				      AD7091R_REG_CONF_INT_VREF);
+		if (ret)
+			return dev_err_probe(st->dev, ret,
+					     "Error on enable internal reference\n");
 	} else {
 		ret = regulator_enable(st->vref);
 		if (ret)
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index 7a78976a2f806..b9e1c8bf3440a 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -8,6 +8,8 @@
 #ifndef __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 #define __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 
+#define AD7091R_REG_CONF_INT_VREF	BIT(0)
+
 /* AD7091R_REG_CH_LIMIT */
 #define AD7091R_HIGH_LIMIT		0xFFF
 #define AD7091R_LOW_LIMIT		0x0
-- 
GitLab


From 5b035ed0a5b4857f8e0dc1328dd66e930ea6eedc Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:27:04 -0300
Subject: [PATCH 1927/4076] iio: adc: ad7091r: Move generic AD7091R code to
 base driver and header file

Some code generic to AD7091R devices such as channel definitions were in
the AD7091R-5 driver. There was also some generic register definitions
declared in the base driver which would make more sense to be in the
header file.
The device state struct will be needed for the ad7091r8 driver in a
follow up patch so that ought to be moved to the header file as well.
Lastly, a couple of regmap callback functions are also capable of
abstracting characteristics of different AD7091R devices and those are
now being exported to IIO_AD7091R name space.

Move AD7091R generic code either to the base driver or to the header
file so both the ad7091r5 and the ad7091r8 driver can use those
declaration in follow up patches.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/6376fc523ee503d47ec499e2cd2ef13bfb5fd8ba.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 29 ++++---------------------
 drivers/iio/adc/ad7091r-base.h | 39 +++++++++++++++++++++++++++++++++-
 drivers/iio/adc/ad7091r5.c     | 11 ----------
 3 files changed, 42 insertions(+), 37 deletions(-)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 7ccc9b44dcd88..3f05e94c756fc 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -16,14 +16,6 @@
 
 #include "ad7091r-base.h"
 
-#define AD7091R_REG_RESULT  0
-#define AD7091R_REG_CHANNEL 1
-#define AD7091R_REG_CONF    2
-#define AD7091R_REG_ALERT   3
-#define AD7091R_REG_CH_LOW_LIMIT(ch) ((ch) * 3 + 4)
-#define AD7091R_REG_CH_HIGH_LIMIT(ch) ((ch) * 3 + 5)
-#define AD7091R_REG_CH_HYSTERESIS(ch) ((ch) * 3 + 6)
-
 /* AD7091R_REG_RESULT */
 #define AD7091R_REG_RESULT_CH_ID(x)	    (((x) >> 13) & 0x3)
 #define AD7091R_REG_RESULT_CONV_RESULT(x)   ((x) & 0xfff)
@@ -36,21 +28,6 @@
 #define AD7091R_REG_CONF_MODE_MASK  \
 	(AD7091R_REG_CONF_AUTO | AD7091R_REG_CONF_CMD)
 
-enum ad7091r_mode {
-	AD7091R_MODE_SAMPLE,
-	AD7091R_MODE_COMMAND,
-	AD7091R_MODE_AUTOCYCLE,
-};
-
-struct ad7091r_state {
-	struct device *dev;
-	struct regmap *map;
-	struct regulator *vref;
-	const struct ad7091r_chip_info *chip_info;
-	enum ad7091r_mode mode;
-	struct mutex lock; /*lock to prevent concurent reads */
-};
-
 const struct iio_event_spec ad7091r_events[] = {
 	{
 		.type = IIO_EV_TYPE_THRESH,
@@ -432,7 +409,7 @@ int ad7091r_probe(struct device *dev, const char *name,
 }
 EXPORT_SYMBOL_NS_GPL(ad7091r_probe, IIO_AD7091R);
 
-static bool ad7091r_writeable_reg(struct device *dev, unsigned int reg)
+bool ad7091r_writeable_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case AD7091R_REG_RESULT:
@@ -442,8 +419,9 @@ static bool ad7091r_writeable_reg(struct device *dev, unsigned int reg)
 		return true;
 	}
 }
+EXPORT_SYMBOL_NS_GPL(ad7091r_writeable_reg, IIO_AD7091R);
 
-static bool ad7091r_volatile_reg(struct device *dev, unsigned int reg)
+bool ad7091r_volatile_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case AD7091R_REG_RESULT:
@@ -453,6 +431,7 @@ static bool ad7091r_volatile_reg(struct device *dev, unsigned int reg)
 		return false;
 	}
 }
+EXPORT_SYMBOL_NS_GPL(ad7091r_volatile_reg, IIO_AD7091R);
 
 const struct regmap_config ad7091r_regmap_config = {
 	.reg_bits = 8,
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index b9e1c8bf3440a..b63c658a9d238 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -8,14 +8,48 @@
 #ifndef __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 #define __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 
+#define AD7091R_REG_RESULT  0
+#define AD7091R_REG_CHANNEL 1
+#define AD7091R_REG_CONF    2
+#define AD7091R_REG_ALERT   3
+#define AD7091R_REG_CH_LOW_LIMIT(ch) ((ch) * 3 + 4)
+#define AD7091R_REG_CH_HIGH_LIMIT(ch) ((ch) * 3 + 5)
+#define AD7091R_REG_CH_HYSTERESIS(ch) ((ch) * 3 + 6)
+
 #define AD7091R_REG_CONF_INT_VREF	BIT(0)
 
 /* AD7091R_REG_CH_LIMIT */
 #define AD7091R_HIGH_LIMIT		0xFFF
 #define AD7091R_LOW_LIMIT		0x0
 
+#define AD7091R_CHANNEL(idx, bits, ev, num_ev) {			\
+	.type = IIO_VOLTAGE,						\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),			\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),		\
+	.indexed = 1,							\
+	.channel = idx,							\
+	.event_spec = ev,						\
+	.num_event_specs = num_ev,					\
+	.scan_type.storagebits = 16,					\
+	.scan_type.realbits = bits,					\
+}
+
 struct device;
-struct ad7091r_state;
+
+enum ad7091r_mode {
+	AD7091R_MODE_SAMPLE,
+	AD7091R_MODE_COMMAND,
+	AD7091R_MODE_AUTOCYCLE,
+};
+
+struct ad7091r_state {
+	struct device *dev;
+	struct regmap *map;
+	struct regulator *vref;
+	const struct ad7091r_chip_info *chip_info;
+	enum ad7091r_mode mode;
+	struct mutex lock; /*lock to prevent concurent reads */
+};
 
 struct ad7091r_chip_info {
 	unsigned int num_channels;
@@ -31,4 +65,7 @@ int ad7091r_probe(struct device *dev, const char *name,
 		const struct ad7091r_chip_info *chip_info,
 		struct regmap *map, int irq);
 
+bool ad7091r_volatile_reg(struct device *dev, unsigned int reg);
+bool ad7091r_writeable_reg(struct device *dev, unsigned int reg);
+
 #endif /* __DRIVERS_IIO_ADC_AD7091R_BASE_H__ */
diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c
index dae98c95ebb87..9d3ccfca94ecc 100644
--- a/drivers/iio/adc/ad7091r5.c
+++ b/drivers/iio/adc/ad7091r5.c
@@ -12,17 +12,6 @@
 
 #include "ad7091r-base.h"
 
-#define AD7091R_CHANNEL(idx, bits, ev, num_ev) { \
-	.type = IIO_VOLTAGE, \
-	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \
-	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \
-	.indexed = 1, \
-	.channel = idx, \
-	.event_spec = ev, \
-	.num_event_specs = num_ev, \
-	.scan_type.storagebits = 16, \
-	.scan_type.realbits = bits, \
-}
 static const struct iio_chan_spec ad7091r5_channels_irq[] = {
 	AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
 	AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
-- 
GitLab


From ca1a679049c12a100f8a72ff7e9363d08851f4d8 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:27:36 -0300
Subject: [PATCH 1928/4076] iio: adc: ad7091r: Move chip init data to container
 struct

AD7091R designs may differ on their communication protocol and resources
required for proper setup. Extract what is design specific into a
init_info struct so the base driver can use data and callback functions
from that struct rather than checking which specific chip is connected
during device initialization.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/1aca2261e227474dc58ce26442845947bcde9b14.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 27 ++++++++++-----------
 drivers/iio/adc/ad7091r-base.h | 15 +++++++++---
 drivers/iio/adc/ad7091r5.c     | 43 ++++++++++++++++++++++++----------
 3 files changed, 55 insertions(+), 30 deletions(-)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 3f05e94c756fc..b5f9423e4e6df 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -342,7 +342,7 @@ static void ad7091r_remove(void *data)
 }
 
 int ad7091r_probe(struct device *dev, const char *name,
-		const struct ad7091r_chip_info *chip_info,
+		const struct ad7091r_init_info *init_info,
 		struct regmap *map, int irq)
 {
 	struct iio_dev *iio_dev;
@@ -355,17 +355,16 @@ int ad7091r_probe(struct device *dev, const char *name,
 
 	st = iio_priv(iio_dev);
 	st->dev = dev;
-	st->chip_info = chip_info;
-	st->map = map;
+	init_info->init_adc_regmap(st, init_info->regmap_config);
+	if (IS_ERR(st->map))
+		return dev_err_probe(st->dev, PTR_ERR(st->map),
+				     "Error initializing regmap\n");
 
-	iio_dev->name = name;
 	iio_dev->info = &ad7091r_info;
 	iio_dev->modes = INDIO_DIRECT_MODE;
 
-	iio_dev->num_channels = chip_info->num_channels;
-	iio_dev->channels = chip_info->channels;
-
 	if (irq) {
+		st->chip_info = init_info->info_irq;
 		ret = regmap_update_bits(st->map, AD7091R_REG_CONF,
 					 AD7091R_REG_CONF_ALERT_EN, BIT(4));
 		if (ret)
@@ -377,8 +376,14 @@ int ad7091r_probe(struct device *dev, const char *name,
 						IRQF_ONESHOT, name, iio_dev);
 		if (ret)
 			return ret;
+	} else {
+		st->chip_info = init_info->info_no_irq;
 	}
 
+	iio_dev->name = st->chip_info->name;
+	iio_dev->num_channels = st->chip_info->num_channels;
+	iio_dev->channels = st->chip_info->channels;
+
 	st->vref = devm_regulator_get_optional(dev, "vref");
 	if (IS_ERR(st->vref)) {
 		if (PTR_ERR(st->vref) == -EPROBE_DEFER)
@@ -433,14 +438,6 @@ bool ad7091r_volatile_reg(struct device *dev, unsigned int reg)
 }
 EXPORT_SYMBOL_NS_GPL(ad7091r_volatile_reg, IIO_AD7091R);
 
-const struct regmap_config ad7091r_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 16,
-	.writeable_reg = ad7091r_writeable_reg,
-	.volatile_reg = ad7091r_volatile_reg,
-};
-EXPORT_SYMBOL_NS_GPL(ad7091r_regmap_config, IIO_AD7091R);
-
 MODULE_AUTHOR("Beniamin Bia <beniamin.bia@analog.com>");
 MODULE_DESCRIPTION("Analog Devices AD7091Rx multi-channel converters");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index b63c658a9d238..b3c43a2008251 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -8,6 +8,8 @@
 #ifndef __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 #define __DRIVERS_IIO_ADC_AD7091R_BASE_H__
 
+#include <linux/regmap.h>
+
 #define AD7091R_REG_RESULT  0
 #define AD7091R_REG_CHANNEL 1
 #define AD7091R_REG_CONF    2
@@ -52,17 +54,24 @@ struct ad7091r_state {
 };
 
 struct ad7091r_chip_info {
+	const char *name;
 	unsigned int num_channels;
 	const struct iio_chan_spec *channels;
 	unsigned int vref_mV;
 };
 
-extern const struct iio_event_spec ad7091r_events[3];
+struct ad7091r_init_info {
+	const struct ad7091r_chip_info *info_irq;
+	const struct ad7091r_chip_info *info_no_irq;
+	const struct regmap_config *regmap_config;
+	void (*init_adc_regmap)(struct ad7091r_state *st,
+				const struct regmap_config *regmap_conf);
+};
 
-extern const struct regmap_config ad7091r_regmap_config;
+extern const struct iio_event_spec ad7091r_events[3];
 
 int ad7091r_probe(struct device *dev, const char *name,
-		const struct ad7091r_chip_info *chip_info,
+		const struct ad7091r_init_info *init_info,
 		struct regmap *map, int irq);
 
 bool ad7091r_volatile_reg(struct device *dev, unsigned int reg);
diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c
index 9d3ccfca94ecc..4b8f9ba078eb2 100644
--- a/drivers/iio/adc/ad7091r5.c
+++ b/drivers/iio/adc/ad7091r5.c
@@ -27,42 +27,61 @@ static const struct iio_chan_spec ad7091r5_channels_noirq[] = {
 };
 
 static const struct ad7091r_chip_info ad7091r5_chip_info_irq = {
+	.name = "ad7091r-5",
 	.channels = ad7091r5_channels_irq,
 	.num_channels = ARRAY_SIZE(ad7091r5_channels_irq),
 	.vref_mV = 2500,
 };
 
 static const struct ad7091r_chip_info ad7091r5_chip_info_noirq = {
+	.name = "ad7091r-5",
 	.channels = ad7091r5_channels_noirq,
 	.num_channels = ARRAY_SIZE(ad7091r5_channels_noirq),
 	.vref_mV = 2500,
 };
 
+static const struct regmap_config ad7091r_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+	.writeable_reg = ad7091r_writeable_reg,
+	.volatile_reg = ad7091r_volatile_reg,
+};
+
+static void ad7091r5_regmap_init(struct ad7091r_state *st,
+				 const struct regmap_config *regmap_conf)
+{
+	struct i2c_client *i2c = container_of(st->dev, struct i2c_client, dev);
+
+	st->map = devm_regmap_init_i2c(i2c, regmap_conf);
+}
+
+static struct ad7091r_init_info ad7091r5_init_info = {
+	.info_irq = &ad7091r5_chip_info_irq,
+	.info_no_irq = &ad7091r5_chip_info_noirq,
+	.regmap_config = &ad7091r_regmap_config,
+	.init_adc_regmap = &ad7091r5_regmap_init
+};
+
 static int ad7091r5_i2c_probe(struct i2c_client *i2c)
 {
 	const struct i2c_device_id *id = i2c_client_get_device_id(i2c);
-	const struct ad7091r_chip_info *chip_info;
-	struct regmap *map = devm_regmap_init_i2c(i2c, &ad7091r_regmap_config);
-
-	if (IS_ERR(map))
-		return PTR_ERR(map);
+	const struct ad7091r_init_info *init_info;
 
-	if (i2c->irq)
-		chip_info = &ad7091r5_chip_info_irq;
-	else
-		chip_info = &ad7091r5_chip_info_noirq;
+	init_info = i2c_get_match_data(i2c);
+	if (!init_info)
+		return -EINVAL;
 
-	return ad7091r_probe(&i2c->dev, id->name, chip_info, map, i2c->irq);
+	return ad7091r_probe(&i2c->dev, id->name, init_info, NULL, i2c->irq);
 }
 
 static const struct of_device_id ad7091r5_dt_ids[] = {
-	{ .compatible = "adi,ad7091r5" },
+	{ .compatible = "adi,ad7091r5", .data = &ad7091r5_init_info },
 	{},
 };
 MODULE_DEVICE_TABLE(of, ad7091r5_dt_ids);
 
 static const struct i2c_device_id ad7091r5_i2c_ids[] = {
-	{"ad7091r5", 0},
+	{"ad7091r5", (kernel_ulong_t)&ad7091r5_init_info },
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, ad7091r5_i2c_ids);
-- 
GitLab


From 6ff545a9b87cdc920ee9988fec2edae14c1f5ecb Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:28:05 -0300
Subject: [PATCH 1929/4076] iio: adc: ad7091r: Remove unneeded probe parameters

With the grouping of ad7091r initialization data and callbacks into the
init_info struct, there is no more need to pass the device name and
register map through probe function parameters as those will be available
in the init_info object.
Remove probe parameters that are not needed anymore.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/090a6b461410a374511a8c73659de28b2665f96b.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 8 ++++----
 drivers/iio/adc/ad7091r-base.h | 5 ++---
 drivers/iio/adc/ad7091r5.c     | 3 +--
 3 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index b5f9423e4e6df..2c65c63db40c5 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -341,9 +341,8 @@ static void ad7091r_remove(void *data)
 	regulator_disable(st->vref);
 }
 
-int ad7091r_probe(struct device *dev, const char *name,
-		const struct ad7091r_init_info *init_info,
-		struct regmap *map, int irq)
+int ad7091r_probe(struct device *dev, const struct ad7091r_init_info *init_info,
+		  int irq)
 {
 	struct iio_dev *iio_dev;
 	struct ad7091r_state *st;
@@ -373,7 +372,8 @@ int ad7091r_probe(struct device *dev, const char *name,
 		ret = devm_request_threaded_irq(dev, irq, NULL,
 						ad7091r_event_handler,
 						IRQF_TRIGGER_FALLING |
-						IRQF_ONESHOT, name, iio_dev);
+						IRQF_ONESHOT,
+						st->chip_info->name, iio_dev);
 		if (ret)
 			return ret;
 	} else {
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index b3c43a2008251..a57ec36491f58 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -70,9 +70,8 @@ struct ad7091r_init_info {
 
 extern const struct iio_event_spec ad7091r_events[3];
 
-int ad7091r_probe(struct device *dev, const char *name,
-		const struct ad7091r_init_info *init_info,
-		struct regmap *map, int irq);
+int ad7091r_probe(struct device *dev, const struct ad7091r_init_info *init_info,
+		  int irq);
 
 bool ad7091r_volatile_reg(struct device *dev, unsigned int reg);
 bool ad7091r_writeable_reg(struct device *dev, unsigned int reg);
diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c
index 4b8f9ba078eb2..cb4c7865f0cc6 100644
--- a/drivers/iio/adc/ad7091r5.c
+++ b/drivers/iio/adc/ad7091r5.c
@@ -64,14 +64,13 @@ static struct ad7091r_init_info ad7091r5_init_info = {
 
 static int ad7091r5_i2c_probe(struct i2c_client *i2c)
 {
-	const struct i2c_device_id *id = i2c_client_get_device_id(i2c);
 	const struct ad7091r_init_info *init_info;
 
 	init_info = i2c_get_match_data(i2c);
 	if (!init_info)
 		return -EINVAL;
 
-	return ad7091r_probe(&i2c->dev, id->name, init_info, NULL, i2c->irq);
+	return ad7091r_probe(&i2c->dev, init_info, i2c->irq);
 }
 
 static const struct of_device_id ad7091r5_dt_ids[] = {
-- 
GitLab


From 7e3ebda32d6e8f10acbde2b204f6bf4020f7ef95 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:28:45 -0300
Subject: [PATCH 1930/4076] iio: adc: ad7091r: Set device mode through
 chip_info callback

AD7091R-5 devices have a few modes of operation (sample, command,
autocycle) which are set by writing to configuration register fields.
Follow up patches will add support for AD7091R-2/-4/-8 which don't have
those operation modes nor the register fields for setting them.
Make ad7091r_set_mode() a callback function of AD7091R chip_info struct
so the base driver can appropriately handle each design without having
to check which actual chip is connected.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/5140336980f66c2c45f05895c3b68e2f65fba1c2.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 38 +---------------------------------
 drivers/iio/adc/ad7091r-base.h |  8 +++++++
 drivers/iio/adc/ad7091r5.c     | 30 +++++++++++++++++++++++++++
 3 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 2c65c63db40c5..a4ca2e21e023b 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -20,14 +20,6 @@
 #define AD7091R_REG_RESULT_CH_ID(x)	    (((x) >> 13) & 0x3)
 #define AD7091R_REG_RESULT_CONV_RESULT(x)   ((x) & 0xfff)
 
-/* AD7091R_REG_CONF */
-#define AD7091R_REG_CONF_ALERT_EN   BIT(4)
-#define AD7091R_REG_CONF_AUTO   BIT(8)
-#define AD7091R_REG_CONF_CMD    BIT(10)
-
-#define AD7091R_REG_CONF_MODE_MASK  \
-	(AD7091R_REG_CONF_AUTO | AD7091R_REG_CONF_CMD)
-
 const struct iio_event_spec ad7091r_events[] = {
 	{
 		.type = IIO_EV_TYPE_THRESH,
@@ -49,34 +41,6 @@ const struct iio_event_spec ad7091r_events[] = {
 };
 EXPORT_SYMBOL_NS_GPL(ad7091r_events, IIO_AD7091R);
 
-static int ad7091r_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode)
-{
-	int ret, conf;
-
-	switch (mode) {
-	case AD7091R_MODE_SAMPLE:
-		conf = 0;
-		break;
-	case AD7091R_MODE_COMMAND:
-		conf = AD7091R_REG_CONF_CMD;
-		break;
-	case AD7091R_MODE_AUTOCYCLE:
-		conf = AD7091R_REG_CONF_AUTO;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ret = regmap_update_bits(st->map, AD7091R_REG_CONF,
-				 AD7091R_REG_CONF_MODE_MASK, conf);
-	if (ret)
-		return ret;
-
-	st->mode = mode;
-
-	return 0;
-}
-
 static int ad7091r_set_channel(struct ad7091r_state *st, unsigned int channel)
 {
 	unsigned int dummy;
@@ -406,7 +370,7 @@ int ad7091r_probe(struct device *dev, const struct ad7091r_init_info *init_info,
 	}
 
 	/* Use command mode by default to convert only desired channels*/
-	ret = ad7091r_set_mode(st, AD7091R_MODE_COMMAND);
+	ret = st->chip_info->set_mode(st, AD7091R_MODE_COMMAND);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index a57ec36491f58..7ba5065a63dd6 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -18,7 +18,14 @@
 #define AD7091R_REG_CH_HIGH_LIMIT(ch) ((ch) * 3 + 5)
 #define AD7091R_REG_CH_HYSTERESIS(ch) ((ch) * 3 + 6)
 
+/* AD7091R_REG_CONF */
 #define AD7091R_REG_CONF_INT_VREF	BIT(0)
+#define AD7091R_REG_CONF_ALERT_EN	BIT(4)
+#define AD7091R_REG_CONF_AUTO		BIT(8)
+#define AD7091R_REG_CONF_CMD		BIT(10)
+
+#define AD7091R_REG_CONF_MODE_MASK  \
+	(AD7091R_REG_CONF_AUTO | AD7091R_REG_CONF_CMD)
 
 /* AD7091R_REG_CH_LIMIT */
 #define AD7091R_HIGH_LIMIT		0xFFF
@@ -58,6 +65,7 @@ struct ad7091r_chip_info {
 	unsigned int num_channels;
 	const struct iio_chan_spec *channels;
 	unsigned int vref_mV;
+	int (*set_mode)(struct ad7091r_state *st, enum ad7091r_mode mode);
 };
 
 struct ad7091r_init_info {
diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c
index cb4c7865f0cc6..e1163b42609c1 100644
--- a/drivers/iio/adc/ad7091r5.c
+++ b/drivers/iio/adc/ad7091r5.c
@@ -26,11 +26,40 @@ static const struct iio_chan_spec ad7091r5_channels_noirq[] = {
 	AD7091R_CHANNEL(3, 12, NULL, 0),
 };
 
+static int ad7091r5_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode)
+{
+	int ret, conf;
+
+	switch (mode) {
+	case AD7091R_MODE_SAMPLE:
+		conf = 0;
+		break;
+	case AD7091R_MODE_COMMAND:
+		conf = AD7091R_REG_CONF_CMD;
+		break;
+	case AD7091R_MODE_AUTOCYCLE:
+		conf = AD7091R_REG_CONF_AUTO;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(st->map, AD7091R_REG_CONF,
+				 AD7091R_REG_CONF_MODE_MASK, conf);
+	if (ret)
+		return ret;
+
+	st->mode = mode;
+
+	return 0;
+}
+
 static const struct ad7091r_chip_info ad7091r5_chip_info_irq = {
 	.name = "ad7091r-5",
 	.channels = ad7091r5_channels_irq,
 	.num_channels = ARRAY_SIZE(ad7091r5_channels_irq),
 	.vref_mV = 2500,
+	.set_mode = &ad7091r5_set_mode,
 };
 
 static const struct ad7091r_chip_info ad7091r5_chip_info_noirq = {
@@ -38,6 +67,7 @@ static const struct ad7091r_chip_info ad7091r5_chip_info_noirq = {
 	.channels = ad7091r5_channels_noirq,
 	.num_channels = ARRAY_SIZE(ad7091r5_channels_noirq),
 	.vref_mV = 2500,
+	.set_mode = &ad7091r5_set_mode,
 };
 
 static const struct regmap_config ad7091r_regmap_config = {
-- 
GitLab


From 8eb5976abfc5990367ca660ce8e222bba6f812c3 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:29:30 -0300
Subject: [PATCH 1931/4076] iio: adc: ad7091r: Add chip_info callback to get
 conversion result channel

AD7091R-5 and AD7091R-2/-4/-8 have slightly different register field
layout and due to that require different masks for getting the index of
the channel associated with each read.
Add a callback function so the base driver can get correct channel ID
for each chip variant.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/1f7a40b4839b3a1c3f1a0654a1b329bea870feb6.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7091r-base.c | 6 +-----
 drivers/iio/adc/ad7091r-base.h | 6 ++++++
 drivers/iio/adc/ad7091r5.c     | 7 +++++++
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index a4ca2e21e023b..665e930d67d0f 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -16,10 +16,6 @@
 
 #include "ad7091r-base.h"
 
-/* AD7091R_REG_RESULT */
-#define AD7091R_REG_RESULT_CH_ID(x)	    (((x) >> 13) & 0x3)
-#define AD7091R_REG_RESULT_CONV_RESULT(x)   ((x) & 0xfff)
-
 const struct iio_event_spec ad7091r_events[] = {
 	{
 		.type = IIO_EV_TYPE_THRESH,
@@ -74,7 +70,7 @@ static int ad7091r_read_one(struct iio_dev *iio_dev,
 	if (ret)
 		return ret;
 
-	if (AD7091R_REG_RESULT_CH_ID(val) != channel)
+	if (st->chip_info->reg_result_chan_id(val) != channel)
 		return -EIO;
 
 	*read_val = AD7091R_REG_RESULT_CONV_RESULT(val);
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index 7ba5065a63dd6..b50024ca33e91 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -18,6 +18,11 @@
 #define AD7091R_REG_CH_HIGH_LIMIT(ch) ((ch) * 3 + 5)
 #define AD7091R_REG_CH_HYSTERESIS(ch) ((ch) * 3 + 6)
 
+/* AD7091R_REG_RESULT */
+#define AD7091R5_REG_RESULT_CH_ID(x)	    (((x) >> 13) & 0x3)
+#define AD7091R8_REG_RESULT_CH_ID(x)	    (((x) >> 13) & 0x7)
+#define AD7091R_REG_RESULT_CONV_RESULT(x)   ((x) & 0xfff)
+
 /* AD7091R_REG_CONF */
 #define AD7091R_REG_CONF_INT_VREF	BIT(0)
 #define AD7091R_REG_CONF_ALERT_EN	BIT(4)
@@ -65,6 +70,7 @@ struct ad7091r_chip_info {
 	unsigned int num_channels;
 	const struct iio_chan_spec *channels;
 	unsigned int vref_mV;
+	unsigned int (*reg_result_chan_id)(unsigned int val);
 	int (*set_mode)(struct ad7091r_state *st, enum ad7091r_mode mode);
 };
 
diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c
index e1163b42609c1..a75837334157d 100644
--- a/drivers/iio/adc/ad7091r5.c
+++ b/drivers/iio/adc/ad7091r5.c
@@ -54,11 +54,17 @@ static int ad7091r5_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode)
 	return 0;
 }
 
+static unsigned int ad7091r5_reg_result_chan_id(unsigned int val)
+{
+	return AD7091R5_REG_RESULT_CH_ID(val);
+}
+
 static const struct ad7091r_chip_info ad7091r5_chip_info_irq = {
 	.name = "ad7091r-5",
 	.channels = ad7091r5_channels_irq,
 	.num_channels = ARRAY_SIZE(ad7091r5_channels_irq),
 	.vref_mV = 2500,
+	.reg_result_chan_id = &ad7091r5_reg_result_chan_id,
 	.set_mode = &ad7091r5_set_mode,
 };
 
@@ -67,6 +73,7 @@ static const struct ad7091r_chip_info ad7091r5_chip_info_noirq = {
 	.channels = ad7091r5_channels_noirq,
 	.num_channels = ARRAY_SIZE(ad7091r5_channels_noirq),
 	.vref_mV = 2500,
+	.reg_result_chan_id = &ad7091r5_reg_result_chan_id,
 	.set_mode = &ad7091r5_set_mode,
 };
 
-- 
GitLab


From 276ceecaa2e8bd0b7b0437e3556fccca991a04f7 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:29:52 -0300
Subject: [PATCH 1932/4076] iio: adc: Split AD7091R-5 config symbol

Split AD7091R-5 kconfig symbol into one symbol for the base AD7091R driver
and another one for the I2C interface AD7091R-5 driver.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/8cae37c611c1b0fe3faef7a4b8c4cc915eaeddc7.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/Kconfig  | 4 ++++
 drivers/iio/adc/Makefile | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 4eebd51614191..9d2d32d091668 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -36,9 +36,13 @@ config AD4130
 	  To compile this driver as a module, choose M here: the module will be
 	  called ad4130.
 
+config AD7091R
+	tristate
+
 config AD7091R5
 	tristate "Analog Devices AD7091R5 ADC Driver"
 	depends on I2C
+	select AD7091R
 	select REGMAP_I2C
 	help
 	  Say yes here to build support for Analog Devices AD7091R-5 ADC.
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index c0803383a7ccb..1e289d674d4d3 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -7,7 +7,8 @@
 obj-$(CONFIG_AB8500_GPADC) += ab8500-gpadc.o
 obj-$(CONFIG_AD_SIGMA_DELTA) += ad_sigma_delta.o
 obj-$(CONFIG_AD4130) += ad4130.o
-obj-$(CONFIG_AD7091R5) += ad7091r5.o ad7091r-base.o
+obj-$(CONFIG_AD7091R) += ad7091r-base.o
+obj-$(CONFIG_AD7091R5) += ad7091r5.o
 obj-$(CONFIG_AD7124) += ad7124.o
 obj-$(CONFIG_AD7192) += ad7192.o
 obj-$(CONFIG_AD7266) += ad7266.o
-- 
GitLab


From 6875b85729f82614a8127792ad0b04c17fb56487 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:32:04 -0300
Subject: [PATCH 1933/4076] dt-bindings: iio: Add AD7091R-8

Add device tree documentation for AD7091R-8.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/632eb34801ae54feda453b6a65d60fc8ac2891fd.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../bindings/iio/adc/adi,ad7091r5.yaml        | 82 ++++++++++++++++++-
 1 file changed, 78 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml
index ce7ba634643c6..ddec9747436c2 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml
@@ -4,36 +4,92 @@
 $id: http://devicetree.org/schemas/iio/adc/adi,ad7091r5.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Analog Devices AD7091R5 4-Channel 12-Bit ADC
+title: Analog Devices AD7091R-2/-4/-5/-8 Multi-Channel 12-Bit ADCs
 
 maintainers:
   - Michael Hennerich <michael.hennerich@analog.com>
+  - Marcelo Schmitt <marcelo.schmitt@analog.com>
 
 description: |
-  Analog Devices AD7091R5 4-Channel 12-Bit ADC
+  Analog Devices AD7091R5 4-Channel 12-Bit ADC supporting I2C interface
   https://www.analog.com/media/en/technical-documentation/data-sheets/ad7091r-5.pdf
+  Analog Devices AD7091R-2/AD7091R-4/AD7091R-8 2-/4-/8-Channel 12-Bit ADCs
+  supporting SPI interface
+  https://www.analog.com/media/en/technical-documentation/data-sheets/AD7091R-2_7091R-4_7091R-8.pdf
 
 properties:
   compatible:
     enum:
+      - adi,ad7091r2
+      - adi,ad7091r4
       - adi,ad7091r5
+      - adi,ad7091r8
 
   reg:
     maxItems: 1
 
+  vdd-supply:
+    description:
+      Provide VDD power to the sensor (VDD range is from 2.7V to 5.25V).
+
+  vdrive-supply:
+    description:
+      Determines the voltage level at which the interface logic will operate.
+      The V_drive voltage range is from 1.8V to 5.25V and must not exceed VDD by
+      more than 0.3V.
+
   vref-supply:
     description:
       Phandle to the vref power supply
 
-  interrupts:
+  convst-gpios:
+    description:
+      GPIO connected to the CONVST pin.
+      This logic input is used to initiate conversions on the analog
+      input channels.
     maxItems: 1
 
+  reset-gpios:
+    maxItems: 1
+
+  interrupts:
+    description:
+      Interrupt for signaling when conversion results exceed the high limit for
+      ADC readings or fall below the low limit for them. Interrupt source must
+      be attached to ALERT/BUSY/GPO0 pin.
+    maxItems: 1
 
 required:
   - compatible
   - reg
 
-additionalProperties: false
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+  # AD7091R-2 does not have ALERT/BUSY/GPO pin
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad7091r2
+    then:
+      properties:
+        interrupts: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad7091r2
+              - adi,ad7091r4
+              - adi,ad7091r8
+    then:
+      required:
+        - convst-gpios
+
+unevaluatedProperties: false
 
 examples:
   - |
@@ -51,4 +107,22 @@ examples:
             interrupt-parent = <&gpio>;
         };
     };
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        adc@0 {
+            compatible = "adi,ad7091r8";
+            reg = <0x0>;
+            spi-max-frequency = <1000000>;
+            vref-supply = <&adc_vref>;
+            convst-gpios = <&gpio 25 GPIO_ACTIVE_LOW>;
+            reset-gpios = <&gpio 27 GPIO_ACTIVE_LOW>;
+            interrupts = <22 IRQ_TYPE_EDGE_FALLING>;
+            interrupt-parent = <&gpio>;
+        };
+    };
 ...
-- 
GitLab


From 0b76ff46c46332f3415be4dc5f9771d5eb2f0f18 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:32:36 -0300
Subject: [PATCH 1934/4076] iio: adc: Add support for AD7091R-8

Add support for Analog Devices AD7091R-2, AD7091R-4, and AD7091R-8
low power 12-Bit SAR ADCs with SPI interface.
Extend ad7091r-base driver so it can be used by the AD7091R-8 driver.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/09d1d1c4b39cecc528488efac6094233715f5659.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/Kconfig        |  12 ++
 drivers/iio/adc/Makefile       |   1 +
 drivers/iio/adc/ad7091r-base.c |   6 +
 drivers/iio/adc/ad7091r-base.h |   6 +
 drivers/iio/adc/ad7091r8.c     | 272 +++++++++++++++++++++++++++++++++
 5 files changed, 297 insertions(+)
 create mode 100644 drivers/iio/adc/ad7091r8.c

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 9d2d32d091668..3b73c509bd68e 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -47,6 +47,18 @@ config AD7091R5
 	help
 	  Say yes here to build support for Analog Devices AD7091R-5 ADC.
 
+config AD7091R8
+	tristate "Analog Devices AD7091R8 ADC Driver"
+	depends on SPI
+	select AD7091R
+	select REGMAP_SPI
+	help
+	  Say yes here to build support for Analog Devices AD7091R-2, AD7091R-4,
+	  and AD7091R-8 ADC.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called ad7091r8.
+
 config AD7124
 	tristate "Analog Devices AD7124 and similar sigma-delta ADCs driver"
 	depends on SPI_MASTER
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index 1e289d674d4d3..d2fda54a3259c 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_AD_SIGMA_DELTA) += ad_sigma_delta.o
 obj-$(CONFIG_AD4130) += ad4130.o
 obj-$(CONFIG_AD7091R) += ad7091r-base.o
 obj-$(CONFIG_AD7091R5) += ad7091r5.o
+obj-$(CONFIG_AD7091R8) += ad7091r8.o
 obj-$(CONFIG_AD7124) += ad7124.o
 obj-$(CONFIG_AD7192) += ad7192.o
 obj-$(CONFIG_AD7266) += ad7266.o
diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c
index 665e930d67d0f..f4255b91acfc9 100644
--- a/drivers/iio/adc/ad7091r-base.c
+++ b/drivers/iio/adc/ad7091r-base.c
@@ -322,6 +322,12 @@ int ad7091r_probe(struct device *dev, const struct ad7091r_init_info *init_info,
 	iio_dev->info = &ad7091r_info;
 	iio_dev->modes = INDIO_DIRECT_MODE;
 
+	if (init_info->setup) {
+		ret = init_info->setup(st);
+		if (ret < 0)
+			return ret;
+	}
+
 	if (irq) {
 		st->chip_info = init_info->info_irq;
 		ret = regmap_update_bits(st->map, AD7091R_REG_CONF,
diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h
index b50024ca33e91..696bf7a897bb5 100644
--- a/drivers/iio/adc/ad7091r-base.h
+++ b/drivers/iio/adc/ad7091r-base.h
@@ -49,6 +49,7 @@
 }
 
 struct device;
+struct gpio_desc;
 
 enum ad7091r_mode {
 	AD7091R_MODE_SAMPLE,
@@ -59,10 +60,14 @@ enum ad7091r_mode {
 struct ad7091r_state {
 	struct device *dev;
 	struct regmap *map;
+	struct gpio_desc *convst_gpio;
+	struct gpio_desc *reset_gpio;
 	struct regulator *vref;
 	const struct ad7091r_chip_info *chip_info;
 	enum ad7091r_mode mode;
 	struct mutex lock; /*lock to prevent concurent reads */
+	__be16 tx_buf __aligned(IIO_DMA_MINALIGN);
+	__be16 rx_buf;
 };
 
 struct ad7091r_chip_info {
@@ -80,6 +85,7 @@ struct ad7091r_init_info {
 	const struct regmap_config *regmap_config;
 	void (*init_adc_regmap)(struct ad7091r_state *st,
 				const struct regmap_config *regmap_conf);
+	int (*setup)(struct ad7091r_state *st);
 };
 
 extern const struct iio_event_spec ad7091r_events[3];
diff --git a/drivers/iio/adc/ad7091r8.c b/drivers/iio/adc/ad7091r8.c
new file mode 100644
index 0000000000000..57700f1248038
--- /dev/null
+++ b/drivers/iio/adc/ad7091r8.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Analog Devices AD7091R8 12-bit SAR ADC driver
+ *
+ * Copyright 2023 Analog Devices Inc.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/iio/iio.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/gpio/consumer.h>
+#include <linux/spi/spi.h>
+
+#include "ad7091r-base.h"
+
+#define AD7091R8_REG_ADDR_MSK				GENMASK(15, 11)
+#define AD7091R8_RD_WR_FLAG_MSK				BIT(10)
+#define AD7091R8_REG_DATA_MSK				GENMASK(9, 0)
+
+#define AD7091R_SPI_REGMAP_CONFIG(n) {					\
+	.reg_bits = 8,							\
+	.val_bits = 16,							\
+	.volatile_reg = ad7091r_volatile_reg,				\
+	.writeable_reg = ad7091r_writeable_reg,				\
+	.max_register = AD7091R_REG_CH_HYSTERESIS(n),			\
+}
+
+static int ad7091r8_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode)
+{
+	/* AD7091R-2/-4/-8 don't set sample/command/autocycle mode in conf reg */
+	st->mode = mode;
+	return 0;
+}
+
+static unsigned int ad7091r8_reg_result_chan_id(unsigned int val)
+{
+	return AD7091R8_REG_RESULT_CH_ID(val);
+}
+
+#define AD7091R_SPI_CHIP_INFO(_n, _name) {				\
+	.name = _name,							\
+	.channels = ad7091r##_n##_channels,				\
+	.num_channels = ARRAY_SIZE(ad7091r##_n##_channels),		\
+	.vref_mV = 2500,						\
+	.reg_result_chan_id = &ad7091r8_reg_result_chan_id,	\
+	.set_mode = &ad7091r8_set_mode,				\
+}
+
+#define AD7091R_SPI_CHIP_INFO_IRQ(_n, _name) {				\
+	.name = _name,							\
+	.channels = ad7091r##_n##_channels_irq,				\
+	.num_channels = ARRAY_SIZE(ad7091r##_n##_channels_irq),		\
+	.vref_mV = 2500,						\
+	.reg_result_chan_id = &ad7091r8_reg_result_chan_id,	\
+	.set_mode = &ad7091r8_set_mode,				\
+}
+
+enum ad7091r8_info_ids {
+	AD7091R2_INFO,
+	AD7091R4_INFO,
+	AD7091R4_INFO_IRQ,
+	AD7091R8_INFO,
+	AD7091R8_INFO_IRQ,
+};
+
+static const struct iio_chan_spec ad7091r2_channels[] = {
+	AD7091R_CHANNEL(0, 12, NULL, 0),
+	AD7091R_CHANNEL(1, 12, NULL, 0),
+};
+
+static const struct iio_chan_spec ad7091r4_channels[] = {
+	AD7091R_CHANNEL(0, 12, NULL, 0),
+	AD7091R_CHANNEL(1, 12, NULL, 0),
+	AD7091R_CHANNEL(2, 12, NULL, 0),
+	AD7091R_CHANNEL(3, 12, NULL, 0),
+};
+
+static const struct iio_chan_spec ad7091r4_channels_irq[] = {
+	AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(2, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(3, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+};
+
+static const struct iio_chan_spec ad7091r8_channels[] = {
+	AD7091R_CHANNEL(0, 12, NULL, 0),
+	AD7091R_CHANNEL(1, 12, NULL, 0),
+	AD7091R_CHANNEL(2, 12, NULL, 0),
+	AD7091R_CHANNEL(3, 12, NULL, 0),
+	AD7091R_CHANNEL(4, 12, NULL, 0),
+	AD7091R_CHANNEL(5, 12, NULL, 0),
+	AD7091R_CHANNEL(6, 12, NULL, 0),
+	AD7091R_CHANNEL(7, 12, NULL, 0),
+};
+
+static const struct iio_chan_spec ad7091r8_channels_irq[] = {
+	AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(2, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(3, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(4, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(5, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(6, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+	AD7091R_CHANNEL(7, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)),
+};
+
+static void ad7091r_pulse_convst(struct ad7091r_state *st)
+{
+	gpiod_set_value_cansleep(st->convst_gpio, 1);
+	gpiod_set_value_cansleep(st->convst_gpio, 0);
+}
+
+static int ad7091r_regmap_bus_reg_read(void *context, unsigned int reg,
+				       unsigned int *val)
+{
+	struct ad7091r_state *st = context;
+	struct spi_device *spi = container_of(st->dev, struct spi_device, dev);
+	int ret;
+
+	struct spi_transfer t[] = {
+		{
+			.tx_buf = &st->tx_buf,
+			.len = 2,
+			.cs_change = 1,
+		}, {
+			.rx_buf = &st->rx_buf,
+			.len = 2,
+		}
+	};
+
+	if (reg == AD7091R_REG_RESULT)
+		ad7091r_pulse_convst(st);
+
+	st->tx_buf = cpu_to_be16(reg << 11);
+
+	ret = spi_sync_transfer(spi, t, ARRAY_SIZE(t));
+	if (ret < 0)
+		return ret;
+
+	*val = be16_to_cpu(st->rx_buf);
+	return 0;
+}
+
+static int ad7091r_regmap_bus_reg_write(void *context, unsigned int reg,
+					unsigned int val)
+{
+	struct ad7091r_state *st = context;
+	struct spi_device *spi = container_of(st->dev, struct spi_device, dev);
+
+	/*
+	 * AD7091R-2/-4/-8 protocol (datasheet page 31) is to do a single SPI
+	 * transfer with reg address set in bits B15:B11 and value set in B9:B0.
+	 */
+	st->tx_buf = cpu_to_be16(FIELD_PREP(AD7091R8_REG_DATA_MSK, val) |
+				 FIELD_PREP(AD7091R8_RD_WR_FLAG_MSK, 1) |
+				 FIELD_PREP(AD7091R8_REG_ADDR_MSK, reg));
+
+	return spi_write(spi, &st->tx_buf, 2);
+}
+
+static struct regmap_bus ad7091r8_regmap_bus = {
+	.reg_read = ad7091r_regmap_bus_reg_read,
+	.reg_write = ad7091r_regmap_bus_reg_write,
+	.reg_format_endian_default = REGMAP_ENDIAN_BIG,
+	.val_format_endian_default = REGMAP_ENDIAN_BIG,
+};
+
+static const struct ad7091r_chip_info ad7091r8_infos[] = {
+	[AD7091R2_INFO] = AD7091R_SPI_CHIP_INFO(2, "ad7091r-2"),
+	[AD7091R4_INFO] = AD7091R_SPI_CHIP_INFO(4, "ad7091r-4"),
+	[AD7091R4_INFO_IRQ] = AD7091R_SPI_CHIP_INFO_IRQ(4, "ad7091r-4"),
+	[AD7091R8_INFO] = AD7091R_SPI_CHIP_INFO(8, "ad7091r-8"),
+	[AD7091R8_INFO_IRQ] = AD7091R_SPI_CHIP_INFO_IRQ(8, "ad7091r-8")
+};
+
+static const struct regmap_config ad7091r2_reg_conf = AD7091R_SPI_REGMAP_CONFIG(2);
+static const struct regmap_config ad7091r4_reg_conf = AD7091R_SPI_REGMAP_CONFIG(4);
+static const struct regmap_config ad7091r8_reg_conf = AD7091R_SPI_REGMAP_CONFIG(8);
+
+static void ad7091r8_regmap_init(struct ad7091r_state *st,
+				 const struct regmap_config *regmap_conf)
+{
+	st->map = devm_regmap_init(st->dev, &ad7091r8_regmap_bus, st,
+				   regmap_conf);
+}
+
+static int ad7091r8_gpio_setup(struct ad7091r_state *st)
+{
+	st->convst_gpio = devm_gpiod_get(st->dev, "convst", GPIOD_OUT_LOW);
+	if (IS_ERR(st->convst_gpio))
+		return dev_err_probe(st->dev, PTR_ERR(st->convst_gpio),
+				     "Error getting convst GPIO\n");
+
+	st->reset_gpio = devm_gpiod_get_optional(st->dev, "reset",
+						 GPIOD_OUT_HIGH);
+	if (IS_ERR(st->reset_gpio))
+		return dev_err_probe(st->dev, PTR_ERR(st->convst_gpio),
+				     "Error on requesting reset GPIO\n");
+
+	if (st->reset_gpio) {
+		fsleep(20);
+		gpiod_set_value_cansleep(st->reset_gpio, 0);
+	}
+
+	return 0;
+}
+
+static struct ad7091r_init_info ad7091r2_init_info = {
+	.info_no_irq = &ad7091r8_infos[AD7091R2_INFO],
+	.regmap_config = &ad7091r2_reg_conf,
+	.init_adc_regmap = &ad7091r8_regmap_init,
+	.setup = &ad7091r8_gpio_setup
+};
+
+static struct ad7091r_init_info ad7091r4_init_info = {
+	.info_no_irq = &ad7091r8_infos[AD7091R4_INFO],
+	.info_irq = &ad7091r8_infos[AD7091R4_INFO_IRQ],
+	.regmap_config = &ad7091r4_reg_conf,
+	.init_adc_regmap = &ad7091r8_regmap_init,
+	.setup = &ad7091r8_gpio_setup
+};
+
+static struct ad7091r_init_info ad7091r8_init_info = {
+	.info_no_irq = &ad7091r8_infos[AD7091R8_INFO],
+	.info_irq = &ad7091r8_infos[AD7091R8_INFO_IRQ],
+	.regmap_config = &ad7091r8_reg_conf,
+	.init_adc_regmap = &ad7091r8_regmap_init,
+	.setup = &ad7091r8_gpio_setup
+};
+
+static int ad7091r8_spi_probe(struct spi_device *spi)
+{
+	const struct ad7091r_init_info *init_info;
+
+	init_info = spi_get_device_match_data(spi);
+	if (!init_info)
+		return -EINVAL;
+
+	return ad7091r_probe(&spi->dev, init_info, spi->irq);
+}
+
+static const struct of_device_id ad7091r8_of_match[] = {
+	{ .compatible = "adi,ad7091r2", .data = &ad7091r2_init_info },
+	{ .compatible = "adi,ad7091r4", .data = &ad7091r4_init_info },
+	{ .compatible = "adi,ad7091r8", .data = &ad7091r8_init_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ad7091r8_of_match);
+
+static const struct spi_device_id ad7091r8_spi_id[] = {
+	{ "ad7091r2", (kernel_ulong_t)&ad7091r2_init_info },
+	{ "ad7091r4", (kernel_ulong_t)&ad7091r4_init_info },
+	{ "ad7091r8", (kernel_ulong_t)&ad7091r8_init_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, ad7091r8_spi_id);
+
+static struct spi_driver ad7091r8_driver = {
+	.driver = {
+		.name = "ad7091r8",
+		.of_match_table = ad7091r8_of_match,
+	},
+	.probe = ad7091r8_spi_probe,
+	.id_table = ad7091r8_spi_id,
+};
+module_spi_driver(ad7091r8_driver);
+
+MODULE_AUTHOR("Marcelo Schmitt <marcelo.schmitt@analog.com>");
+MODULE_DESCRIPTION("Analog Devices AD7091R8 ADC driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IIO_AD7091R);
-- 
GitLab


From de35d40926810cd3767f25a7ed24f890137f93b9 Mon Sep 17 00:00:00 2001
From: Marcelo Schmitt <marcelo.schmitt@analog.com>
Date: Tue, 19 Dec 2023 17:32:59 -0300
Subject: [PATCH 1935/4076] MAINTAINERS: Add MAINTAINERS entry for AD7091R

The driver for AD7091R was added in
ca693001: iio: adc: Add support for AD7091R5 ADC
but no MAINTAINERS file entry was added for it since then.
Add a proper MAINTAINERS file entry for the AD7091R driver.

Signed-off-by: Marcelo Schmitt <marcelo.schmitt@analog.com>
Link: https://lore.kernel.org/r/4247e653354f8eb362264189db24c612d5e4e131.1703013352.git.marcelo.schmitt1@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 MAINTAINERS | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index f61df0128c0b0..a31b1b20c6f6f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1122,6 +1122,14 @@ F:	Documentation/ABI/testing/sysfs-bus-iio-adc-ad4130
 F:	Documentation/devicetree/bindings/iio/adc/adi,ad4130.yaml
 F:	drivers/iio/adc/ad4130.c
 
+ANALOG DEVICES INC AD7091R DRIVER
+M:	Marcelo Schmitt <marcelo.schmitt@analog.com>
+L:	linux-iio@vger.kernel.org
+S:	Supported
+W:	http://ez.analog.com/community/linux-device-drivers
+F:	Documentation/devicetree/bindings/iio/adc/adi,ad7091r*
+F:	drivers/iio/adc/drivers/iio/adc/ad7091r*
+
 ANALOG DEVICES INC AD7192 DRIVER
 M:	Alexandru Tachici <alexandru.tachici@analog.com>
 L:	linux-iio@vger.kernel.org
-- 
GitLab


From 8645e659e2d227f6ce8fcea1ac640c324fbbb3e6 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:05:56 -0800
Subject: [PATCH 1936/4076] iio: linux/iio.h: fix Excess kernel-doc description
 warning

Remove the @of_xlate: lines to prevent the kernel-doc warning:

include/linux/iio/iio.h:534: warning: Excess struct member 'of_xlate' description in 'iio_info'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jonathan Cameron <jic23@kernel.org>
Cc: Lars-Peter Clausen <lars@metafoo.de>
Cc: linux-iio@vger.kernel.org
Link: https://lore.kernel.org/r/20231223050556.13948-1-rdunlap@infradead.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index d0ce3b71106aa..c5b36d2c1e735 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -434,13 +434,7 @@ struct iio_trigger; /* forward declaration */
  * @update_scan_mode:	function to configure device and scan buffer when
  *			channels have changed
  * @debugfs_reg_access:	function to read or write register value of device
- * @of_xlate:		function pointer to obtain channel specifier index.
- *			When #iio-cells is greater than '0', the driver could
- *			provide a custom of_xlate function that reads the
- *			*args* and returns the appropriate index in registered
- *			IIO channels array.
  * @fwnode_xlate:	fwnode based function pointer to obtain channel specifier index.
- *			Functionally the same as @of_xlate.
  * @hwfifo_set_watermark: function pointer to set the current hardware
  *			fifo watermark level; see hwfifo_* entries in
  *			Documentation/ABI/testing/sysfs-bus-iio for details on
-- 
GitLab


From 0942155a48e4cfc2c83e514c86a3de8f78f6af02 Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@grsecurity.net>
Date: Wed, 20 Dec 2023 14:35:05 +0100
Subject: [PATCH 1937/4076] PCI: Remove unused 'node' member from struct
 pci_driver

Remove the unused 'node' member. It got replaced by device_driver chaining
more than 20 years ago in commit 4b4a837f2b57 ("PCI: start to use common
fields of struct device_driver more...") of the history.git tree.

Link: https://lore.kernel.org/r/20231220133505.8798-1-minipli@grsecurity.net
Signed-off-by: Mathias Krause <minipli@grsecurity.net>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 1 -
 include/linux/pci.h                                     | 2 --
 2 files changed, 3 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 80220685f5e45..d7fb88bb6ae1a 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -2707,7 +2707,6 @@ MODULE_DEVICE_TABLE(pci, brcmf_pcie_devid_table);
 
 
 static struct pci_driver brcmf_pciedrvr = {
-	.node = {},
 	.name = KBUILD_MODNAME,
 	.id_table = brcmf_pcie_devid_table,
 	.probe = brcmf_pcie_probe,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc8679..1a89dc66f89ac 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -885,7 +885,6 @@ struct module;
 
 /**
  * struct pci_driver - PCI driver structure
- * @node:	List of driver structures.
  * @name:	Driver name.
  * @id_table:	Pointer to table of device IDs the driver is
  *		interested in.  Most drivers should export this
@@ -940,7 +939,6 @@ struct module;
  *		own I/O address space.
  */
 struct pci_driver {
-	struct list_head	node;
 	const char		*name;
 	const struct pci_device_id *id_table;	/* Must be non-NULL for probe to be called */
 	int  (*probe)(struct pci_dev *dev, const struct pci_device_id *id);	/* New device inserted */
-- 
GitLab


From b91cf01cf3e63a627b3b65f4284dcf9a4deb80f9 Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@outlook.com>
Date: Mon, 4 Dec 2023 17:51:08 +0800
Subject: [PATCH 1938/4076] dt-bindings: timer: thead,c900-aclint-mtimer:
 separate mtime and mtimecmp regs

The timer registers of aclint don't follow the clint layout and can
be mapped on any different offset. As sg2042 uses separated timer
and mswi for its clint, it should follow the aclint spec and have
separated registers.

The previous patch introduced a new type of T-HEAD aclint timer which
has clint timer layout. Although it has the clint timer layout, it
should follow the aclint spec and uses the separated mtime and mtimecmp
regs. So a ABI change is needed to make the timer fit the aclint spec.

To make T-HEAD aclint timer more closer to the aclint spec, use
regs-names to represent the mtimecmp register, which can avoid hack
for unsupport mtime register of T-HEAD aclint timer.

Also, as T-HEAD aclint only supports mtimecmp, it is unnecessary to
implement the whole aclint spec. To make this binding T-HEAD specific,
only add reg-name for existed register. For details, see the discussion
in the last link.

Signed-off-by: Inochi Amaoto <inochiama@outlook.com>
Fixes: 4734449f7311 ("dt-bindings: timer: Add Sophgo sg2042 CLINT timer")
Link: https://lists.infradead.org/pipermail/opensbi/2023-October/005693.html
Link: https://github.com/riscv/riscv-aclint/blob/main/riscv-aclint.adoc
Link: https://lore.kernel.org/all/IA1PR20MB4953F9D77FFC76A9D236922DBBB6A@IA1PR20MB4953.namprd20.prod.outlook.com/
Acked-by: Guo Ren <guoren@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/IA1PR20MB49531ED1BCC00D6B265C2D10BB86A@IA1PR20MB4953.namprd20.prod.outlook.com
---
 .../bindings/timer/thead,c900-aclint-mtimer.yaml         | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml b/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
index fbd235650e52c..2e92bcdeb423a 100644
--- a/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
+++ b/Documentation/devicetree/bindings/timer/thead,c900-aclint-mtimer.yaml
@@ -17,7 +17,12 @@ properties:
       - const: thead,c900-aclint-mtimer
 
   reg:
-    maxItems: 1
+    items:
+      - description: MTIMECMP Registers
+
+  reg-names:
+    items:
+      - const: mtimecmp
 
   interrupts-extended:
     minItems: 1
@@ -28,6 +33,7 @@ additionalProperties: false
 required:
   - compatible
   - reg
+  - reg-names
   - interrupts-extended
 
 examples:
@@ -39,5 +45,6 @@ examples:
                             <&cpu3intc 7>,
                             <&cpu4intc 7>;
       reg = <0xac000000 0x00010000>;
+      reg-names = "mtimecmp";
     };
 ...
-- 
GitLab


From e0cf60151e6317c654c42ba0e8b1fb6ff477489a Mon Sep 17 00:00:00 2001
From: Sia Jee Heng <jeeheng.sia@starfivetech.com>
Date: Fri, 1 Dec 2023 20:14:07 +0800
Subject: [PATCH 1939/4076] dt-bindings: timer: Add StarFive JH8100 clint

Add compatible string for the StarFive JH8100 clint.

Signed-off-by: Sia Jee Heng <jeeheng.sia@starfivetech.com>
Reviewed-by: Ley Foon Tan <leyfoon.tan@starfivetech.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20231201121410.95298-4-jeeheng.sia@starfivetech.com
---
 Documentation/devicetree/bindings/timer/sifive,clint.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
index e8be6c4703640..01254261e1563 100644
--- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml
+++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml
@@ -33,6 +33,7 @@ properties:
               - sifive,fu540-c000-clint # SiFive FU540
               - starfive,jh7100-clint   # StarFive JH7100
               - starfive,jh7110-clint   # StarFive JH7110
+              - starfive,jh8100-clint   # StarFive JH8100
           - const: sifive,clint0        # SiFive CLINT v0 IP block
       - items:
           - enum:
-- 
GitLab


From 6a902b118e7f30dbf0e6248f7b0f97e12c0939c3 Mon Sep 17 00:00:00 2001
From: Joshua Yeong <joshua.yeong@starfivetech.com>
Date: Thu, 16 Nov 2023 18:53:12 +0800
Subject: [PATCH 1940/4076] clocksource/timer-riscv: Add riscv_clock_shutdown
 callback

Add clocksource detach/shutdown callback to disable RISC-V timer interrupt when
switching out riscv timer as clock source

Signed-off-by: Joshua Yeong <joshua.yeong@starfivetech.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20231116105312.4800-1-joshua.yeong@starfivetech.com
---
 drivers/clocksource/timer-riscv.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 57857c0dfba97..e66dcbd665665 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -61,12 +61,19 @@ static int riscv_clock_next_event(unsigned long delta,
 	return 0;
 }
 
+static int riscv_clock_shutdown(struct clock_event_device *evt)
+{
+	riscv_clock_event_stop();
+	return 0;
+}
+
 static unsigned int riscv_clock_event_irq;
 static DEFINE_PER_CPU(struct clock_event_device, riscv_clock_event) = {
 	.name			= "riscv_timer_clockevent",
 	.features		= CLOCK_EVT_FEAT_ONESHOT,
 	.rating			= 100,
 	.set_next_event		= riscv_clock_next_event,
+	.set_state_shutdown	= riscv_clock_shutdown,
 };
 
 /*
-- 
GitLab


From b99a212a7697c542b460adaa15d4a98abf8223f0 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 14 Nov 2023 09:29:30 +0200
Subject: [PATCH 1941/4076] clocksource/drivers/timer-ti-dm: Fix make W=n
 kerneldoc warnings

Kernel test robot reports of kerneldoc related warnings that happen with
make W=n for "parameter or member not described".

These were caused by changes to function parameter names with
earlier commits where the kerneldoc parts were not updated.

Fixes: 49cd16bb573e ("clocksource/drivers/timer-ti-dm: Simplify register writes with dmtimer_write()")
Fixes: a6e543f61531 ("clocksource/drivers/timer-ti-dm: Move struct omap_dm_timer fields to driver")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311040403.DzIiBuwU-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202311040606.XL5OcR9O-lkp@intel.com/
Signed-off-by: Tony Lindgren <tony@atomide.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20231114072930.40615-1-tony@atomide.com
---
 drivers/clocksource/timer-ti-dm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c
index 5f60f6bd33866..56acf26172621 100644
--- a/drivers/clocksource/timer-ti-dm.c
+++ b/drivers/clocksource/timer-ti-dm.c
@@ -183,7 +183,7 @@ static inline u32 dmtimer_read(struct dmtimer *timer, u32 reg)
  * dmtimer_write - write timer registers in posted and non-posted mode
  * @timer:      timer pointer over which write operation is to perform
  * @reg:        lowest byte holds the register offset
- * @value:      data to write into the register
+ * @val:        data to write into the register
  *
  * The posted mode bit is encoded in reg. Note that in posted mode, the write
  * pending bit must be checked. Otherwise a write on a register which has a
@@ -949,7 +949,7 @@ static int omap_dm_timer_set_int_enable(struct omap_dm_timer *cookie,
 
 /**
  * omap_dm_timer_set_int_disable - disable timer interrupts
- * @timer:	pointer to timer handle
+ * @cookie:	pointer to timer cookie
  * @mask:	bit mask of interrupts to be disabled
  *
  * Disables the specified timer interrupts for a timer.
-- 
GitLab


From 0515c73467fd550249ef83062e1d03d99c718b4f Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 5 Dec 2023 15:04:48 -0800
Subject: [PATCH 1942/4076] clocksource/drivers/cadence-ttc: Fix some
 kernel-doc warnings

Fix some function kernel-doc warnings to placate scripts/kernel-doc.

timer-cadence-ttc.c:79: warning: Function parameter or member 'clk_rate_change_nb' not described in 'ttc_timer'
timer-cadence-ttc.c:158: warning: Function parameter or member 'cs' not described in '__ttc_clocksource_read'
timer-cadence-ttc.c:194: warning: expecting prototype for ttc_set_{shutdown|oneshot|periodic}(). Prototype was for ttc_shutdown() instead
timer-cadence-ttc.c:196: warning: No description found for return value of 'ttc_shutdown'
timer-cadence-ttc.c:212: warning: No description found for return value of 'ttc_set_periodic'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Michal Simek <michal.simek@amd.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Acked-by: Michal Simek <michal.simek@amd.com>
Tested-by: Michal Simek <michal.simek@amd.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20231205230448.772-1-rdunlap@infradead.org
---
 drivers/clocksource/timer-cadence-ttc.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c
index 32daaac9b1320..ca7a06489c405 100644
--- a/drivers/clocksource/timer-cadence-ttc.c
+++ b/drivers/clocksource/timer-cadence-ttc.c
@@ -69,7 +69,7 @@
  * @base_addr:	Base address of timer
  * @freq:	Timer input clock frequency
  * @clk:	Associated clock source
- * @clk_rate_change_nb	Notifier block for clock rate changes
+ * @clk_rate_change_nb:	Notifier block for clock rate changes
  */
 struct ttc_timer {
 	void __iomem *base_addr;
@@ -134,7 +134,7 @@ static void ttc_set_interval(struct ttc_timer *timer,
  * @irq:	IRQ number of the Timer
  * @dev_id:	void pointer to the ttc_timer instance
  *
- * returns: Always IRQ_HANDLED - success
+ * Returns: Always IRQ_HANDLED - success
  **/
 static irqreturn_t ttc_clock_event_interrupt(int irq, void *dev_id)
 {
@@ -151,8 +151,9 @@ static irqreturn_t ttc_clock_event_interrupt(int irq, void *dev_id)
 
 /**
  * __ttc_clocksource_read - Reads the timer counter register
+ * @cs: &clocksource to read from
  *
- * returns: Current timer counter register value
+ * Returns: Current timer counter register value
  **/
 static u64 __ttc_clocksource_read(struct clocksource *cs)
 {
@@ -173,7 +174,7 @@ static u64 notrace ttc_sched_clock_read(void)
  * @cycles:	Timer interval ticks
  * @evt:	Address of clock event instance
  *
- * returns: Always 0 - success
+ * Returns: Always %0 - success
  **/
 static int ttc_set_next_event(unsigned long cycles,
 					struct clock_event_device *evt)
@@ -186,9 +187,12 @@ static int ttc_set_next_event(unsigned long cycles,
 }
 
 /**
- * ttc_set_{shutdown|oneshot|periodic} - Sets the state of timer
- *
+ * ttc_shutdown - Sets the state of timer
  * @evt:	Address of clock event instance
+ *
+ * Used for shutdown or oneshot.
+ *
+ * Returns: Always %0 - success
  **/
 static int ttc_shutdown(struct clock_event_device *evt)
 {
@@ -202,6 +206,12 @@ static int ttc_shutdown(struct clock_event_device *evt)
 	return 0;
 }
 
+/**
+ * ttc_set_periodic - Sets the state of timer
+ * @evt:	Address of clock event instance
+ *
+ * Returns: Always %0 - success
+ */
 static int ttc_set_periodic(struct clock_event_device *evt)
 {
 	struct ttc_timer_clockevent *ttce = to_ttc_timer_clkevent(evt);
-- 
GitLab


From c0c4579d79d0df841e825c68df450909a0032faf Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 12 Dec 2023 22:46:07 +0100
Subject: [PATCH 1943/4076] clocksource/drivers/ep93xx: Fix error handling
 during probe

When the interrupt property fails to be parsed, ep93xx_timer_of_init()
return code ends up uninitialized:

drivers/clocksource/timer-ep93xx.c:160:6: error: variable 'ret' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized]
        if (irq < 0) {
            ^~~~~~~
drivers/clocksource/timer-ep93xx.c:188:9: note: uninitialized use occurs here
        return ret;
               ^~~
drivers/clocksource/timer-ep93xx.c:160:2: note: remove the 'if' if its condition is always false
        if (irq < 0) {
        ^~~~~~~~~~~~~~

Simplify this portion to use the normal construct of just checking
whether a valid interrupt was returned. Note that irq_of_parse_and_map()
never returns a negative value and no other callers check for that either.

Fixes: c28ca80ba3b5 ("clocksource: ep93xx: Add driver for Cirrus Logic EP93xx")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20231212214616.193098-1-arnd@kernel.org
---
 drivers/clocksource/timer-ep93xx.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/clocksource/timer-ep93xx.c b/drivers/clocksource/timer-ep93xx.c
index bc0ca6e123349..6981ff3ac8a94 100644
--- a/drivers/clocksource/timer-ep93xx.c
+++ b/drivers/clocksource/timer-ep93xx.c
@@ -155,9 +155,8 @@ static int __init ep93xx_timer_of_init(struct device_node *np)
 	ep93xx_tcu = tcu;
 
 	irq = irq_of_parse_and_map(np, 0);
-	if (irq == 0)
-		irq = -EINVAL;
-	if (irq < 0) {
+	if (!irq) {
+		ret = -EINVAL;
 		pr_err("EP93XX Timer Can't parse IRQ %d", irq);
 		goto out_free;
 	}
-- 
GitLab


From ab78ffe1ff7d17102972348bb9b1a16ec2696a2b Mon Sep 17 00:00:00 2001
From: Pasha Tatashin <pasha.tatashin@soleen.com>
Date: Tue, 26 Dec 2023 18:28:27 +0000
Subject: [PATCH 1944/4076] vhost-vdpa: account iommu allocations

iommu allocations should be accounted in order to allow admins to
monitor and limit the amount of iommu memory.

Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <20231226182827.294158-1-pasha.tatashin@soleen.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
---
 drivers/vhost/vdpa.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index da7ec77cdaff0..a51c69c078d93 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -968,7 +968,8 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
 			r = ops->set_map(vdpa, asid, iotlb);
 	} else {
 		r = iommu_map(v->domain, iova, pa, size,
-			      perm_to_iommu_flags(perm), GFP_KERNEL);
+			      perm_to_iommu_flags(perm),
+			      GFP_KERNEL_ACCOUNT);
 	}
 	if (r) {
 		vhost_iotlb_del_range(iotlb, iova, iova + size - 1);
-- 
GitLab


From d2c4f1928a3f7f4a1f28a0cfc022e8a145ce6903 Mon Sep 17 00:00:00 2001
From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Date: Tue, 26 Dec 2023 17:43:33 +0800
Subject: [PATCH 1945/4076] virtio_net: fix missing dma unmap for resize

For rq, we have three cases getting buffers from virtio core:

1. virtqueue_get_buf{,_ctx}
2. virtqueue_detach_unused_buf
3. callback for virtqueue_resize

But in commit 295525e29a5b("virtio_net: merge dma operations when
filling mergeable buffers"), I missed the dma unmap for the #3 case.

That will leak some memory, because I did not release the pages referred
by the unused buffers.

If we do such script, we will make the system OOM.

    while true
    do
            ethtool -G ens4 rx 128
            ethtool -G ens4 rx 256
            free -m
    done

Fixes: 295525e29a5b ("virtio_net: merge dma operations when filling mergeable buffers")
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Message-Id: <20231226094333.47740-1-xuanzhuo@linux.alibaba.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/net/virtio_net.c | 60 ++++++++++++++++++++--------------------
 1 file changed, 30 insertions(+), 30 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d16f592c2061f..51b1868d2f220 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -334,7 +334,6 @@ struct virtio_net_common_hdr {
 	};
 };
 
-static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
 static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
 
 static bool is_xdp_frame(void *ptr)
@@ -408,6 +407,17 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
 	return p;
 }
 
+static void virtnet_rq_free_buf(struct virtnet_info *vi,
+				struct receive_queue *rq, void *buf)
+{
+	if (vi->mergeable_rx_bufs)
+		put_page(virt_to_head_page(buf));
+	else if (vi->big_packets)
+		give_pages(rq, buf);
+	else
+		put_page(virt_to_head_page(buf));
+}
+
 static void enable_delayed_refill(struct virtnet_info *vi)
 {
 	spin_lock_bh(&vi->refill_lock);
@@ -634,17 +644,6 @@ static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx)
 	return buf;
 }
 
-static void *virtnet_rq_detach_unused_buf(struct receive_queue *rq)
-{
-	void *buf;
-
-	buf = virtqueue_detach_unused_buf(rq->vq);
-	if (buf && rq->do_dma)
-		virtnet_rq_unmap(rq, buf, 0);
-
-	return buf;
-}
-
 static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len)
 {
 	struct virtnet_rq_dma *dma;
@@ -744,6 +743,20 @@ static void virtnet_rq_set_premapped(struct virtnet_info *vi)
 	}
 }
 
+static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
+{
+	struct virtnet_info *vi = vq->vdev->priv;
+	struct receive_queue *rq;
+	int i = vq2rxq(vq);
+
+	rq = &vi->rq[i];
+
+	if (rq->do_dma)
+		virtnet_rq_unmap(rq, buf, 0);
+
+	virtnet_rq_free_buf(vi, rq, buf);
+}
+
 static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
 {
 	unsigned int len;
@@ -1764,7 +1777,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
 		DEV_STATS_INC(dev, rx_length_errors);
-		virtnet_rq_free_unused_buf(rq->vq, buf);
+		virtnet_rq_free_buf(vi, rq, buf);
 		return;
 	}
 
@@ -2392,7 +2405,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 	if (running)
 		napi_disable(&rq->napi);
 
-	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
+	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf);
 	if (err)
 		netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err);
 
@@ -4031,19 +4044,6 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
 		xdp_return_frame(ptr_to_xdp(buf));
 }
 
-static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
-{
-	struct virtnet_info *vi = vq->vdev->priv;
-	int i = vq2rxq(vq);
-
-	if (vi->mergeable_rx_bufs)
-		put_page(virt_to_head_page(buf));
-	else if (vi->big_packets)
-		give_pages(&vi->rq[i], buf);
-	else
-		put_page(virt_to_head_page(buf));
-}
-
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -4057,10 +4057,10 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		struct receive_queue *rq = &vi->rq[i];
+		struct virtqueue *vq = vi->rq[i].vq;
 
-		while ((buf = virtnet_rq_detach_unused_buf(rq)) != NULL)
-			virtnet_rq_free_unused_buf(rq->vq, buf);
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+			virtnet_rq_unmap_free_buf(vq, buf);
 		cond_resched();
 	}
 }
-- 
GitLab


From dff4fa0e57856045359440d05af9e9b7f7048f52 Mon Sep 17 00:00:00 2001
From: David Stevens <stevensd@chromium.org>
Date: Fri, 8 Dec 2023 16:07:54 +0900
Subject: [PATCH 1946/4076] virtio: Add support for no-reset virtio PCI PM

If a virtio_pci_device supports native PCI power management and has the
No_Soft_Reset bit set, then skip resetting and reinitializing the device
when suspending and restoring the device. This allows system-wide low
power states like s2idle to be used in systems with stateful virtio
devices that can't simply be re-initialized (e.g. virtio-fs).

Signed-off-by: David Stevens <stevensd@chromium.org>
Message-Id: <20231208070754.3132339-1-stevensd@chromium.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_pci_common.c | 34 +++++++++++++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 7a5593997e0ef..1d21d1a1b3f55 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -492,8 +492,40 @@ static int virtio_pci_restore(struct device *dev)
 	return virtio_device_restore(&vp_dev->vdev);
 }
 
+static bool vp_supports_pm_no_reset(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	u16 pmcsr;
+
+	if (!pci_dev->pm_cap)
+		return false;
+
+	pci_read_config_word(pci_dev, pci_dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+	if (PCI_POSSIBLE_ERROR(pmcsr)) {
+		dev_err(dev, "Unable to query pmcsr");
+		return false;
+	}
+
+	return pmcsr & PCI_PM_CTRL_NO_SOFT_RESET;
+}
+
+static int virtio_pci_suspend(struct device *dev)
+{
+	return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_freeze(dev);
+}
+
+static int virtio_pci_resume(struct device *dev)
+{
+	return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_restore(dev);
+}
+
 static const struct dev_pm_ops virtio_pci_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
+	.suspend = virtio_pci_suspend,
+	.resume = virtio_pci_resume,
+	.freeze = virtio_pci_freeze,
+	.thaw = virtio_pci_restore,
+	.poweroff = virtio_pci_freeze,
+	.restore = virtio_pci_restore,
 };
 #endif
 
-- 
GitLab


From c271fcd9095f066e0e7104e6d8919e2cf26f0899 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 10 Dec 2023 18:51:50 +0100
Subject: [PATCH 1947/4076] vdpa: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Message-Id: <d7534cc4caf4ff9d6b072744352c1b69487779ea.1702230703.git.christophe.jaillet@wanadoo.fr>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/vdpa.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index a7612e0783b36..d0695680b282e 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -131,7 +131,7 @@ static void vdpa_release_dev(struct device *d)
 	if (ops->free)
 		ops->free(vdev);
 
-	ida_simple_remove(&vdpa_index_ida, vdev->index);
+	ida_free(&vdpa_index_ida, vdev->index);
 	kfree(vdev->driver_override);
 	kfree(vdev);
 }
@@ -205,7 +205,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	return vdev;
 
 err_name:
-	ida_simple_remove(&vdpa_index_ida, vdev->index);
+	ida_free(&vdpa_index_ida, vdev->index);
 err_ida:
 	kfree(vdev);
 err:
-- 
GitLab


From 092e39d1456bda5c3d7dab0aa72a24e4b0b4f7a5 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 19:25:25 +0900
Subject: [PATCH 1948/4076] kconfig: squash menu_has_help() and menu_get_help()

menu_has_help() and menu_get_help() functions are only used within
menu_get_ext_help().

Squash them into menu_get_ext_help(). It revealed the if-conditional
in menu_get_help() was unneeded, as menu_has_help() has already checked
that menu->help is not NULL.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/lkc.h  |  2 --
 scripts/kconfig/menu.c | 17 ++---------------
 2 files changed, 2 insertions(+), 17 deletions(-)

diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index 471a59acecec6..5cdc8f5e6446a 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -99,8 +99,6 @@ bool menu_is_visible(struct menu *menu);
 bool menu_has_prompt(struct menu *menu);
 const char *menu_get_prompt(struct menu *menu);
 struct menu *menu_get_parent_menu(struct menu *menu);
-bool menu_has_help(struct menu *menu);
-const char *menu_get_help(struct menu *menu);
 int get_jump_key_char(void);
 struct gstr get_relations_str(struct symbol **sym_arr, struct list_head *head);
 void menu_get_ext_help(struct menu *menu, struct gstr *help);
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 61c442d84aef4..2cce8b651f615 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -673,19 +673,6 @@ struct menu *menu_get_parent_menu(struct menu *menu)
 	return menu;
 }
 
-bool menu_has_help(struct menu *menu)
-{
-	return menu->help != NULL;
-}
-
-const char *menu_get_help(struct menu *menu)
-{
-	if (menu->help)
-		return menu->help;
-	else
-		return "";
-}
-
 static void get_def_str(struct gstr *r, struct menu *menu)
 {
 	str_printf(r, "Defined at %s:%d\n",
@@ -856,10 +843,10 @@ void menu_get_ext_help(struct menu *menu, struct gstr *help)
 	struct symbol *sym = menu->sym;
 	const char *help_text = nohelp_text;
 
-	if (menu_has_help(menu)) {
+	if (menu->help) {
 		if (sym->name)
 			str_printf(help, "%s%s:\n\n", CONFIG_, sym->name);
-		help_text = menu_get_help(menu);
+		help_text = menu->help;
 	}
 	str_printf(help, "%s\n", help_text);
 	if (sym)
-- 
GitLab


From 405d2cb209b5836910b5dac01cf97fcbd186c0af Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 19:25:26 +0900
Subject: [PATCH 1949/4076] kconfig: add include guard to lkc_proto.h

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/lkc_proto.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h
index edd1e617b25c5..687d8698d801c 100644
--- a/scripts/kconfig/lkc_proto.h
+++ b/scripts/kconfig/lkc_proto.h
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LKC_PROTO_H
+#define LKC_PROTO_H
+
 #include <stdarg.h>
 
 /* confdata.c */
@@ -50,3 +53,5 @@ char *expand_one_token(const char **str);
 
 /* expr.c */
 void expr_print(struct expr *e, void (*fn)(void *, struct symbol *, const char *), void *data, int prevtoken);
+
+#endif /* LKC_PROTO_H */
-- 
GitLab


From 9ad86d747c46f2bdc097c908481647fcdda1d035 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 19:25:27 +0900
Subject: [PATCH 1950/4076] kconfig: remove unreachable printf()

Remove the unreachable code detected by clang.

  $ make HOSTCC=clang HOSTCFLAGS=-Wunreachable-code defconfig
    [ snip ]
  scripts/kconfig/expr.c:1134:2: warning: code will never be executed [-Wunreachable-code]
          printf("[%dgt%d?]", t1, t2);
          ^~~~~~
  1 warning generated.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/expr.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c
index 81ebf8108ca74..a290de36307ba 100644
--- a/scripts/kconfig/expr.c
+++ b/scripts/kconfig/expr.c
@@ -1131,7 +1131,6 @@ static int expr_compare_type(enum expr_type t1, enum expr_type t2)
 	default:
 		return -1;
 	}
-	printf("[%dgt%d?]", t1, t2);
 	return 0;
 }
 
-- 
GitLab


From 407868deb2a344e9baa7909e1b13aec35c7217b2 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 3 Dec 2023 19:25:28 +0900
Subject: [PATCH 1951/4076] kconfig: remove redundant NULL pointer check before
 free()

Passing NULL to free() is allowed and is a no-op.

Remove redundant NULL pointer checks.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/confdata.c | 3 +--
 scripts/kconfig/util.c     | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index bd14aae1db582..f1197e6724316 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -432,8 +432,7 @@ load:
 		case S_INT:
 		case S_HEX:
 		case S_STRING:
-			if (sym->def[def].val)
-				free(sym->def[def].val);
+			free(sym->def[def].val);
 			/* fall through */
 		default:
 			sym->def[def].val = NULL;
diff --git a/scripts/kconfig/util.c b/scripts/kconfig/util.c
index b78f114ad48cc..92e5b2b9761d7 100644
--- a/scripts/kconfig/util.c
+++ b/scripts/kconfig/util.c
@@ -42,8 +42,7 @@ struct gstr str_new(void)
 /* Free storage for growable string */
 void str_free(struct gstr *gs)
 {
-	if (gs->s)
-		free(gs->s);
+	free(gs->s);
 	gs->s = NULL;
 	gs->len = 0;
 }
-- 
GitLab


From ac14947c77a36270d5cb1ff07afffbf221ac8af1 Mon Sep 17 00:00:00 2001
From: Markus Schneider-Pargmann <msp@baylibre.com>
Date: Tue, 5 Dec 2023 11:45:59 +0100
Subject: [PATCH 1952/4076] kconfig: Use KCONFIG_CONFIG instead of .config

When using a custom location for kernel config files this merge config
command fails as it doesn't use the configuration set with
KCONFIG_CONFIG.

Signed-off-by: Markus Schneider-Pargmann <msp@baylibre.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 7c025f82718e2..ea1bf3b3dbde1 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -107,7 +107,7 @@ config-fragments = $(call configfiles,$@)
 
 %.config: $(obj)/conf
 	$(if $(config-fragments),, $(error $@ fragment does not exists on this architecture))
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m .config $(config-fragments)
+	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments)
 	$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 
 PHONY += tinyconfig
-- 
GitLab


From 5a602de99797bddc9dd7f73592281a507196f69d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= <ihuguet@redhat.com>
Date: Thu, 1 Jun 2023 09:53:33 +0200
Subject: [PATCH 1953/4076] Add .editorconfig file for basic formatting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

EditorConfig is a specification to define the most basic code formatting
stuff, and it's supported by many editors and IDEs, either directly or
via plugins, including VSCode/VSCodium, Vim, emacs and more.

It allows to define formatting style related to indentation, charset,
end of lines and trailing whitespaces. It also allows to apply different
formats for different files based on wildcards, so for example it is
possible to apply different configs to *.{c,h}, *.py and *.rs.

In linux project, defining a .editorconfig might help to those people
that work on different projects with different indentation styles, so
they cannot define a global style. Now they will directly see the
correct indentation on every fresh clone of the project.

See https://editorconfig.org

Co-developed-by: Danny Lin <danny@kdrag0n.dev>
Signed-off-by: Danny Lin <danny@kdrag0n.dev>
Signed-off-by: Íñigo Huguet <ihuguet@redhat.com>
Acked-by: Mickaël Salaün <mic@digikod.net>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Tested-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 .editorconfig                          | 32 ++++++++++++++++++++++++++
 .gitignore                             |  1 +
 Documentation/process/4.Coding.rst     |  4 ++++
 Documentation/process/coding-style.rst |  4 ++++
 4 files changed, 41 insertions(+)
 create mode 100644 .editorconfig

diff --git a/.editorconfig b/.editorconfig
new file mode 100644
index 0000000000000..854773350cc5a
--- /dev/null
+++ b/.editorconfig
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+root = true
+
+[{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = true
+insert_final_newline = true
+indent_style = tab
+indent_size = 8
+
+[*.{json,py,rs}]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = true
+insert_final_newline = true
+indent_style = space
+indent_size = 4
+
+# this must be below the general *.py to overwrite it
+[tools/{perf,power,rcu,testing/kunit}/**.py,]
+indent_style = tab
+indent_size = 8
+
+[*.yaml]
+charset = utf-8
+end_of_line = lf
+trim_trailing_whitespace = unset
+insert_final_newline = true
+indent_style = space
+indent_size = 2
diff --git a/.gitignore b/.gitignore
index 98274e1160d7b..689a4fa3f5477 100644
--- a/.gitignore
+++ b/.gitignore
@@ -96,6 +96,7 @@ modules.order
 #
 !.clang-format
 !.cocciconfig
+!.editorconfig
 !.get_maintainer.ignore
 !.gitattributes
 !.gitignore
diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst
index 1f0d81f44e14b..c2046dec0c2f4 100644
--- a/Documentation/process/4.Coding.rst
+++ b/Documentation/process/4.Coding.rst
@@ -66,6 +66,10 @@ for aligning variables/macros, for reflowing text and other similar tasks.
 See the file :ref:`Documentation/process/clang-format.rst <clangformat>`
 for more details.
 
+Some basic editor settings, such as indentation and line endings, will be
+set automatically if you are using an editor that is compatible with
+EditorConfig. See the official EditorConfig website for more information:
+https://editorconfig.org/
 
 Abstraction layers
 ******************
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index 6db37a46d3059..c48382c6b4774 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -735,6 +735,10 @@ for aligning variables/macros, for reflowing text and other similar tasks.
 See the file :ref:`Documentation/process/clang-format.rst <clangformat>`
 for more details.
 
+Some basic editor settings, such as indentation and line endings, will be
+set automatically if you are using an editor that is compatible with
+EditorConfig. See the official EditorConfig website for more information:
+https://editorconfig.org/
 
 10) Kconfig configuration files
 -------------------------------
-- 
GitLab


From 21d706d5cf570917594b21edee81893bdce09ab8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 9 Jul 2021 08:41:17 +0100
Subject: [PATCH 1954/4076] netfs: Add support for DIO buffering

Add a bvec array pointer and an iterator to netfs_io_request for either
holding a copy of a DIO iterator or a list of all the bits of buffer
pointed to by a DIO iterator.

There are two problems:  Firstly, if an iovec-class iov_iter is passed to
->read_iter() or ->write_iter(), this cannot be passed directly to
kernel_sendmsg() or kernel_recvmsg() as that may cause locking recursion if
a fault is generated, so we need to keep track of the pages involved
separately.

Secondly, if the I/O is asynchronous, we must copy the iov_iter describing
the buffer before returning to the caller as it may be immediately
deallocated.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/objects.c    | 10 ++++++++++
 include/linux/netfs.h |  3 +++
 2 files changed, 13 insertions(+)

diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 1bd20bdad9836..4df5e5eeada68 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -76,6 +76,7 @@ static void netfs_free_request(struct work_struct *work)
 {
 	struct netfs_io_request *rreq =
 		container_of(work, struct netfs_io_request, work);
+	unsigned int i;
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
 	netfs_proc_del_rreq(rreq);
@@ -84,6 +85,15 @@ static void netfs_free_request(struct work_struct *work)
 		rreq->netfs_ops->free_request(rreq);
 	if (rreq->cache_resources.ops)
 		rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
+	if (rreq->direct_bv) {
+		for (i = 0; i < rreq->direct_bv_count; i++) {
+			if (rreq->direct_bv[i].bv_page) {
+				if (rreq->direct_bv_unpin)
+					unpin_user_page(rreq->direct_bv[i].bv_page);
+			}
+		}
+		kvfree(rreq->direct_bv);
+	}
 	kfree_rcu(rreq, rcu);
 	netfs_stat_d(&netfs_n_rh_rreq);
 }
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 3da962e977f55..2bb1273b38f42 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -190,6 +190,8 @@ struct netfs_io_request {
 	struct iov_iter		iter;		/* Unencrypted-side iterator */
 	struct iov_iter		io_iter;	/* I/O (Encrypted-side) iterator */
 	void			*netfs_priv;	/* Private data for the netfs */
+	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
+	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
@@ -197,6 +199,7 @@ struct netfs_io_request {
 	size_t			len;		/* Length of the request */
 	short			error;		/* 0 or error that occurred */
 	enum netfs_io_origin	origin;		/* Origin of the request */
+	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
 	loff_t			i_size;		/* Size of the file */
 	loff_t			start;		/* Start position */
 	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
-- 
GitLab


From 7d828a06634799aba0fa392913c7fe2953eb64a6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 22 Sep 2023 13:25:22 +0100
Subject: [PATCH 1955/4076] netfs: Provide tools to create a buffer in an
 xarray

Provide tools to create a buffer in an xarray, with a function to add new
folios with a mark.  This will be used to create bounce buffer and can be
used more easily to create a list of folios the span of which would require
more than a page's worth of bio_vec structs.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/internal.h   | 13 +++++++
 fs/netfs/misc.c       | 81 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  4 +++
 3 files changed, 98 insertions(+)

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 4708fb15446bd..b908c7e0a9013 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -56,6 +56,19 @@ static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq) {}
 static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {}
 #endif
 
+/*
+ * misc.c
+ */
+#define NETFS_FLAG_PUT_MARK		BIT(0)
+#define NETFS_FLAG_PAGECACHE_MARK	BIT(1)
+int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
+			    struct folio *folio, unsigned int flags,
+			    gfp_t gfp_mask);
+int netfs_add_folios_to_buffer(struct xarray *buffer,
+			       struct address_space *mapping,
+			       pgoff_t index, pgoff_t to, gfp_t gfp_mask);
+void netfs_clear_buffer(struct xarray *buffer);
+
 /*
  * objects.c
  */
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 45bb19ec9a638..5d545073fe03c 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -8,6 +8,87 @@
 #include <linux/swap.h>
 #include "internal.h"
 
+/*
+ * Attach a folio to the buffer and maybe set marks on it to say that we need
+ * to put the folio later and twiddle the pagecache flags.
+ */
+int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
+			    struct folio *folio, unsigned int flags,
+			    gfp_t gfp_mask)
+{
+	XA_STATE_ORDER(xas, xa, index, folio_order(folio));
+
+retry:
+	xas_lock(&xas);
+	for (;;) {
+		xas_store(&xas, folio);
+		if (!xas_error(&xas))
+			break;
+		xas_unlock(&xas);
+		if (!xas_nomem(&xas, gfp_mask))
+			return xas_error(&xas);
+		goto retry;
+	}
+
+	if (flags & NETFS_FLAG_PUT_MARK)
+		xas_set_mark(&xas, NETFS_BUF_PUT_MARK);
+	if (flags & NETFS_FLAG_PAGECACHE_MARK)
+		xas_set_mark(&xas, NETFS_BUF_PAGECACHE_MARK);
+	xas_unlock(&xas);
+	return xas_error(&xas);
+}
+
+/*
+ * Create the specified range of folios in the buffer attached to the read
+ * request.  The folios are marked with NETFS_BUF_PUT_MARK so that we know that
+ * these need freeing later.
+ */
+int netfs_add_folios_to_buffer(struct xarray *buffer,
+			       struct address_space *mapping,
+			       pgoff_t index, pgoff_t to, gfp_t gfp_mask)
+{
+	struct folio *folio;
+	int ret;
+
+	if (to + 1 == index) /* Page range is inclusive */
+		return 0;
+
+	do {
+		/* TODO: Figure out what order folio can be allocated here */
+		folio = filemap_alloc_folio(readahead_gfp_mask(mapping), 0);
+		if (!folio)
+			return -ENOMEM;
+		folio->index = index;
+		ret = netfs_xa_store_and_mark(buffer, index, folio,
+					      NETFS_FLAG_PUT_MARK, gfp_mask);
+		if (ret < 0) {
+			folio_put(folio);
+			return ret;
+		}
+
+		index += folio_nr_pages(folio);
+	} while (index <= to && index != 0);
+
+	return 0;
+}
+
+/*
+ * Clear an xarray buffer, putting a ref on the folios that have
+ * NETFS_BUF_PUT_MARK set.
+ */
+void netfs_clear_buffer(struct xarray *buffer)
+{
+	struct folio *folio;
+	XA_STATE(xas, buffer, 0);
+
+	rcu_read_lock();
+	xas_for_each_marked(&xas, folio, ULONG_MAX, NETFS_BUF_PUT_MARK) {
+		folio_put(folio);
+	}
+	rcu_read_unlock();
+	xa_destroy(buffer);
+}
+
 /**
  * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback
  * @mapping: The mapping the folio belongs to.
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 2bb1273b38f42..c05365e3f4281 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -109,6 +109,10 @@ static inline int wait_on_page_fscache_killable(struct page *page)
 	return folio_wait_private_2_killable(page_folio(page));
 }
 
+/* Marks used on xarray-based buffers */
+#define NETFS_BUF_PUT_MARK	XA_MARK_0	/* - Page needs putting  */
+#define NETFS_BUF_PAGECACHE_MARK XA_MARK_1	/* - Page needs wb/dirty flag wrangling */
+
 enum netfs_io_source {
 	NETFS_FILL_WITH_ZEROES,
 	NETFS_DOWNLOAD_FROM_SERVER,
-- 
GitLab


From cae932d3aee55035a54415dcea8e7ecf2ec469b5 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 22 Sep 2023 14:49:47 +0100
Subject: [PATCH 1956/4076] netfs: Add func to calculate pagecount/size-limited
 span of an iterator

Add a function to work out how much of an ITER_BVEC or ITER_XARRAY iterator
we can use in a pagecount-limited and size-limited span.  This will be
used, for example, to limit the number of segments in a subrequest to the
maximum number of elements that an RDMA transfer can handle.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/iterator.c   | 97 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  2 +
 2 files changed, 99 insertions(+)

diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
index 2ff07ba655a07..b781bbbf1d8d6 100644
--- a/fs/netfs/iterator.c
+++ b/fs/netfs/iterator.c
@@ -101,3 +101,100 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 	return npages;
 }
 EXPORT_SYMBOL_GPL(netfs_extract_user_iter);
+
+/*
+ * Select the span of a bvec iterator we're going to use.  Limit it by both maximum
+ * size and maximum number of segments.  Returns the size of the span in bytes.
+ */
+static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset,
+			       size_t max_size, size_t max_segs)
+{
+	const struct bio_vec *bvecs = iter->bvec;
+	unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0;
+	size_t len, span = 0, n = iter->count;
+	size_t skip = iter->iov_offset + start_offset;
+
+	if (WARN_ON(!iov_iter_is_bvec(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+
+	while (n && ix < nbv && skip) {
+		len = bvecs[ix].bv_len;
+		if (skip < len)
+			break;
+		skip -= len;
+		n -= len;
+		ix++;
+	}
+
+	while (n && ix < nbv) {
+		len = min3(n, bvecs[ix].bv_len - skip, max_size);
+		span += len;
+		nsegs++;
+		ix++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+		skip = 0;
+		n -= len;
+	}
+
+	return min(span, max_size);
+}
+
+/*
+ * Select the span of an xarray iterator we're going to use.  Limit it by both
+ * maximum size and maximum number of segments.  It is assumed that segments
+ * can be larger than a page in size, provided they're physically contiguous.
+ * Returns the size of the span in bytes.
+ */
+static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offset,
+				 size_t max_size, size_t max_segs)
+{
+	struct folio *folio;
+	unsigned int nsegs = 0;
+	loff_t pos = iter->xarray_start + iter->iov_offset;
+	pgoff_t index = pos / PAGE_SIZE;
+	size_t span = 0, n = iter->count;
+
+	XA_STATE(xas, iter->xarray, index);
+
+	if (WARN_ON(!iov_iter_is_xarray(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+	max_size = min(max_size, n - start_offset);
+
+	rcu_read_lock();
+	xas_for_each(&xas, folio, ULONG_MAX) {
+		size_t offset, flen, len;
+		if (xas_retry(&xas, folio))
+			continue;
+		if (WARN_ON(xa_is_value(folio)))
+			break;
+		if (WARN_ON(folio_test_hugetlb(folio)))
+			break;
+
+		flen = folio_size(folio);
+		offset = offset_in_folio(folio, pos);
+		len = min(max_size, flen - offset);
+		span += len;
+		nsegs++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+	}
+
+	rcu_read_unlock();
+	return min(span, max_size);
+}
+
+size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
+			size_t max_size, size_t max_segs)
+{
+	if (iov_iter_is_bvec(iter))
+		return netfs_limit_bvec(iter, start_offset, max_size, max_segs);
+	if (iov_iter_is_xarray(iter))
+		return netfs_limit_xarray(iter, start_offset, max_size, max_segs);
+	BUG();
+}
+EXPORT_SYMBOL(netfs_limit_iter);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index c05365e3f4281..d673d0785b9d9 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -321,6 +321,8 @@ void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
+size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
+			size_t max_size, size_t max_segs);
 
 int netfs_start_io_read(struct inode *inode);
 void netfs_end_io_read(struct inode *inode);
-- 
GitLab


From 768ddb1eacf5dd997ecf393e7bab9796bad047e0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 27 May 2022 13:45:28 +0100
Subject: [PATCH 1957/4076] netfs: Limit subrequest by size or number of
 segments

Limit a subrequest to a maximum size and/or a maximum number of contiguous
physical regions.  This permits, for instance, an subreq's iterator to be
limited to the number of DMA'able segments that a large RDMA request can
handle.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/io.c                | 18 ++++++++++++++++++
 include/linux/netfs.h        |  1 +
 include/trace/events/netfs.h |  1 +
 3 files changed, 20 insertions(+)

diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index e9d408e211b83..e228bfb530ea5 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -525,6 +525,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			struct iov_iter *io_iter)
 {
 	enum netfs_io_source source;
+	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
 
@@ -547,13 +548,30 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			source = NETFS_INVALID_READ;
 			goto out;
 		}
+
+		if (subreq->max_nr_segs) {
+			lsize = netfs_limit_iter(io_iter, 0, subreq->len,
+						 subreq->max_nr_segs);
+			if (subreq->len > lsize) {
+				subreq->len = lsize;
+				trace_netfs_sreq(subreq, netfs_sreq_trace_limited);
+			}
+		}
 	}
 
+	if (subreq->len > rreq->len)
+		pr_warn("R=%08x[%u] SREQ>RREQ %zx > %zx\n",
+			rreq->debug_id, subreq->debug_index,
+			subreq->len, rreq->len);
+
 	if (WARN_ON(subreq->len == 0)) {
 		source = NETFS_INVALID_READ;
 		goto out;
 	}
 
+	subreq->source = source;
+	trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+
 	subreq->io_iter = *io_iter;
 	iov_iter_truncate(&subreq->io_iter, subreq->len);
 	iov_iter_advance(io_iter, subreq->len);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d673d0785b9d9..44cd13ad695af 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -161,6 +161,7 @@ struct netfs_io_subrequest {
 	refcount_t		ref;
 	short			error;		/* 0 or error that occurred */
 	unsigned short		debug_index;	/* Index in list (for debugging output) */
+	unsigned int		max_nr_segs;	/* 0 or max number of segments in an iterator */
 	enum netfs_io_source	source;		/* Where to read from/write to */
 	unsigned long		flags;
 #define NETFS_SREQ_COPY_TO_CACHE	0	/* Set if should copy the data to the cache */
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index beec534cbaab2..fce6d0bc78e5e 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -44,6 +44,7 @@
 #define netfs_sreq_traces					\
 	EM(netfs_sreq_trace_download_instead,	"RDOWN")	\
 	EM(netfs_sreq_trace_free,		"FREE ")	\
+	EM(netfs_sreq_trace_limited,		"LIMIT")	\
 	EM(netfs_sreq_trace_prepare,		"PREP ")	\
 	EM(netfs_sreq_trace_resubmit_short,	"SHORT")	\
 	EM(netfs_sreq_trace_submit,		"SUBMT")	\
-- 
GitLab


From 16af134ca4b7051b1587108f2066ec90ae029f74 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 9 Feb 2022 19:52:13 +0000
Subject: [PATCH 1958/4076] netfs: Extend the netfs_io_*request structs to
 handle writes

Modify the netfs_io_request struct to act as a point around which writes
can be coordinated.  It represents and pins a range of pages that need
writing and a list of regions of dirty data in that range of pages.

If RMW is required, the original data can be downloaded into the bounce
buffer, decrypted if necessary, the modifications made, then the modified
data can be reencrypted/recompressed and sent back to the server.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/internal.h          |  6 ++++++
 fs/netfs/main.c              |  3 ++-
 fs/netfs/objects.c           |  6 ++++++
 fs/netfs/stats.c             | 16 +++++++++++++---
 include/linux/netfs.h        | 15 ++++++++++++++-
 include/trace/events/netfs.h |  8 ++++++--
 6 files changed, 47 insertions(+), 7 deletions(-)

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index b908c7e0a9013..2bf2e82b2ad79 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -110,6 +110,12 @@ extern atomic_t netfs_n_rh_write_begin;
 extern atomic_t netfs_n_rh_write_done;
 extern atomic_t netfs_n_rh_write_failed;
 extern atomic_t netfs_n_rh_write_zskip;
+extern atomic_t netfs_n_wh_upload;
+extern atomic_t netfs_n_wh_upload_done;
+extern atomic_t netfs_n_wh_upload_failed;
+extern atomic_t netfs_n_wh_write;
+extern atomic_t netfs_n_wh_write_done;
+extern atomic_t netfs_n_wh_write_failed;
 
 int netfs_stats_show(struct seq_file *m, void *v);
 
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 97ce1436615b7..ab6cac1106762 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -25,10 +25,11 @@ MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
 LIST_HEAD(netfs_io_requests);
 DEFINE_SPINLOCK(netfs_proc_lock);
 
-static const char *netfs_origins[] = {
+static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READAHEAD]	= "RA",
 	[NETFS_READPAGE]	= "RP",
 	[NETFS_READ_FOR_WRITE]	= "RW",
+	[NETFS_WRITEBACK]	= "WB",
 };
 
 /*
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 4df5e5eeada68..65a17dd4ab492 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -20,6 +20,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct inode *inode = file ? file_inode(file) : mapping->host;
 	struct netfs_inode *ctx = netfs_inode(inode);
 	struct netfs_io_request *rreq;
+	bool cached = netfs_is_cache_enabled(ctx);
 	int ret;
 
 	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
@@ -37,7 +38,10 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	rreq->debug_id	= atomic_inc_return(&debug_ids);
 	INIT_LIST_HEAD(&rreq->subrequests);
 	refcount_set(&rreq->ref, 1);
+
 	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+	if (cached)
+		__set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
 	if (rreq->netfs_ops->init_request) {
 		ret = rreq->netfs_ops->init_request(rreq, file);
 		if (ret < 0) {
@@ -46,6 +50,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 		}
 	}
 
+	trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new);
 	netfs_proc_add_rreq(rreq);
 	netfs_stat(&netfs_n_rh_rreq);
 	return rreq;
@@ -129,6 +134,7 @@ struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq
 			 sizeof(struct netfs_io_subrequest),
 			 GFP_KERNEL);
 	if (subreq) {
+		INIT_WORK(&subreq->work, NULL);
 		INIT_LIST_HEAD(&subreq->rreq_link);
 		refcount_set(&subreq->ref, 2);
 		subreq->rreq = rreq;
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index 6025dc485f7ea..c1f85cd595a47 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -27,6 +27,12 @@ atomic_t netfs_n_rh_write_begin;
 atomic_t netfs_n_rh_write_done;
 atomic_t netfs_n_rh_write_failed;
 atomic_t netfs_n_rh_write_zskip;
+atomic_t netfs_n_wh_upload;
+atomic_t netfs_n_wh_upload_done;
+atomic_t netfs_n_wh_upload_failed;
+atomic_t netfs_n_wh_write;
+atomic_t netfs_n_wh_write_done;
+atomic_t netfs_n_wh_write_failed;
 
 int netfs_stats_show(struct seq_file *m, void *v)
 {
@@ -50,10 +56,14 @@ int netfs_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&netfs_n_rh_read),
 		   atomic_read(&netfs_n_rh_read_done),
 		   atomic_read(&netfs_n_rh_read_failed));
+	seq_printf(m, "Netfs  : UL=%u us=%u uf=%u\n",
+		   atomic_read(&netfs_n_wh_upload),
+		   atomic_read(&netfs_n_wh_upload_done),
+		   atomic_read(&netfs_n_wh_upload_failed));
 	seq_printf(m, "Netfs  : WR=%u ws=%u wf=%u\n",
-		   atomic_read(&netfs_n_rh_write),
-		   atomic_read(&netfs_n_rh_write_done),
-		   atomic_read(&netfs_n_rh_write_failed));
+		   atomic_read(&netfs_n_wh_write),
+		   atomic_read(&netfs_n_wh_write_done),
+		   atomic_read(&netfs_n_wh_write_failed));
 	return fscache_stats_show(m);
 }
 EXPORT_SYMBOL(netfs_stats_show);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 44cd13ad695af..f302123a3e384 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -118,6 +118,9 @@ enum netfs_io_source {
 	NETFS_DOWNLOAD_FROM_SERVER,
 	NETFS_READ_FROM_CACHE,
 	NETFS_INVALID_READ,
+	NETFS_UPLOAD_TO_SERVER,
+	NETFS_WRITE_TO_CACHE,
+	NETFS_INVALID_WRITE,
 } __mode(byte);
 
 typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error,
@@ -149,9 +152,14 @@ struct netfs_cache_resources {
 };
 
 /*
- * Descriptor for a single component subrequest.
+ * Descriptor for a single component subrequest.  Each operation represents an
+ * individual read/write from/to a server, a cache, a journal, etc..
+ *
+ * The buffer iterator is persistent for the life of the subrequest struct and
+ * the pages it points to can be relied on to exist for the duration.
  */
 struct netfs_io_subrequest {
+	struct work_struct	work;
 	struct netfs_io_request *rreq;		/* Supervising I/O request */
 	struct list_head	rreq_link;	/* Link in rreq->subrequests */
 	struct iov_iter		io_iter;	/* Iterator for this subrequest */
@@ -176,6 +184,8 @@ enum netfs_io_origin {
 	NETFS_READAHEAD,		/* This read was triggered by readahead */
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
+	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	nr__netfs_io_origin
 } __mode(byte);
 
 /*
@@ -198,6 +208,7 @@ struct netfs_io_request {
 	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
 	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
+	unsigned int		subreq_counter;	/* Next subreq->debug_index */
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
 	size_t			submitted;	/* Amount submitted for I/O so far */
@@ -216,6 +227,8 @@ struct netfs_io_request {
 #define NETFS_RREQ_DONT_UNLOCK_FOLIOS	3	/* Don't unlock the folios on completion */
 #define NETFS_RREQ_FAILED		4	/* The request failed */
 #define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
+#define NETFS_RREQ_WRITE_TO_CACHE	7	/* Need to write to the cache */
+#define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
 	const struct netfs_request_ops *netfs_ops;
 };
 
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index fce6d0bc78e5e..4ea4e34d279f2 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -24,7 +24,8 @@
 #define netfs_rreq_origins					\
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
-	E_(NETFS_READ_FOR_WRITE,		"RW")
+	EM(NETFS_READ_FOR_WRITE,		"RW")		\
+	E_(NETFS_WRITEBACK,			"WB")
 
 #define netfs_rreq_traces					\
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
@@ -39,7 +40,10 @@
 	EM(NETFS_FILL_WITH_ZEROES,		"ZERO")		\
 	EM(NETFS_DOWNLOAD_FROM_SERVER,		"DOWN")		\
 	EM(NETFS_READ_FROM_CACHE,		"READ")		\
-	E_(NETFS_INVALID_READ,			"INVL")		\
+	EM(NETFS_INVALID_READ,			"INVL")		\
+	EM(NETFS_UPLOAD_TO_SERVER,		"UPLD")		\
+	EM(NETFS_WRITE_TO_CACHE,		"WRIT")		\
+	E_(NETFS_INVALID_WRITE,			"INVL")
 
 #define netfs_sreq_traces					\
 	EM(netfs_sreq_trace_download_instead,	"RDOWN")	\
-- 
GitLab


From c6dc54dd91bbf597942b4975b8adec660a16827d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 25 Feb 2022 12:27:53 +0000
Subject: [PATCH 1959/4076] netfs: Add a hook to allow tell the netfs to update
 its i_size

Add a hook for netfslib's write helpers to call to tell the network
filesystem that it should update its i_size.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 include/linux/netfs.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index f302123a3e384..3fc41f616621b 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -242,6 +242,7 @@ struct netfs_request_ops {
 	void (*free_request)(struct netfs_io_request *rreq);
 	void (*free_subrequest)(struct netfs_io_subrequest *rreq);
 
+	/* Read request handling */
 	void (*expand_readahead)(struct netfs_io_request *rreq);
 	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
 	void (*issue_read)(struct netfs_io_subrequest *subreq);
@@ -249,6 +250,9 @@ struct netfs_request_ops {
 	int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
 				 struct folio **foliop, void **_fsdata);
 	void (*done)(struct netfs_io_request *rreq);
+
+	/* Modification handling */
+	void (*update_i_size)(struct inode *inode, loff_t i_size);
 };
 
 /*
-- 
GitLab


From 6ba22d8d1521f35ca1343e64f69d7857f0340e5e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 29 Sep 2023 14:35:17 +0100
Subject: [PATCH 1960/4076] netfs: Make netfs_put_request() handle a NULL
 pointer

Make netfs_put_request() just return if given a NULL request pointer.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/objects.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 65a17dd4ab492..3aa0bfbc04ec3 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -106,19 +106,22 @@ static void netfs_free_request(struct work_struct *work)
 void netfs_put_request(struct netfs_io_request *rreq, bool was_async,
 		       enum netfs_rreq_ref_trace what)
 {
-	unsigned int debug_id = rreq->debug_id;
+	unsigned int debug_id;
 	bool dead;
 	int r;
 
-	dead = __refcount_dec_and_test(&rreq->ref, &r);
-	trace_netfs_rreq_ref(debug_id, r - 1, what);
-	if (dead) {
-		if (was_async) {
-			rreq->work.func = netfs_free_request;
-			if (!queue_work(system_unbound_wq, &rreq->work))
-				BUG();
-		} else {
-			netfs_free_request(&rreq->work);
+	if (rreq) {
+		debug_id = rreq->debug_id;
+		dead = __refcount_dec_and_test(&rreq->ref, &r);
+		trace_netfs_rreq_ref(debug_id, r - 1, what);
+		if (dead) {
+			if (was_async) {
+				rreq->work.func = netfs_free_request;
+				if (!queue_work(system_unbound_wq, &rreq->work))
+					BUG();
+			} else {
+				netfs_free_request(&rreq->work);
+			}
 		}
 	}
 }
-- 
GitLab


From 4fcccc38ebbdcff74494701c50a8e2fe4689837e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Oct 2023 16:15:48 +0100
Subject: [PATCH 1961/4076] netfs: Make the refcounting of netfs_begin_read()
 easier to use

Make the refcounting of netfs_begin_read() easier to use by not eating the
caller's ref on the netfs_io_request it's given.  This makes it easier to
use when we need to look in the request struct after.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_read.c     |  6 +++++-
 fs/netfs/io.c                | 28 +++++++++++++---------------
 include/trace/events/netfs.h |  9 +++++----
 3 files changed, 23 insertions(+), 20 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 751556faa70b1..6b9a44cafbac6 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -210,6 +210,7 @@ void netfs_readahead(struct readahead_control *ractl)
 		;
 
 	netfs_begin_read(rreq, false);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 	return;
 
 cleanup_free:
@@ -260,7 +261,9 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
 			rreq->start, rreq->len);
 
-	return netfs_begin_read(rreq, true);
+	ret = netfs_begin_read(rreq, true);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	return ret;
 
 discard:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
@@ -429,6 +432,7 @@ retry:
 	ret = netfs_begin_read(rreq, true);
 	if (ret < 0)
 		goto error;
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 
 have_folio:
 	ret = folio_wait_fscache_killable(folio);
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index e228bfb530ea5..e83ef5835d250 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -362,6 +362,7 @@ again:
 
 	netfs_rreq_unlock_folios(rreq);
 
+	trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
 	wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
 
@@ -657,7 +658,6 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 
 	if (rreq->len == 0) {
 		pr_err("Zero-sized read [R=%x]\n", rreq->debug_id);
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len);
 		return -EIO;
 	}
 
@@ -665,12 +665,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 
 	INIT_WORK(&rreq->work, netfs_rreq_work);
 
-	if (sync)
-		netfs_get_request(rreq, netfs_rreq_trace_get_hold);
-
 	/* Chop the read into slices according to what the cache and the netfs
 	 * want and submit each one.
 	 */
+	netfs_get_request(rreq, netfs_rreq_trace_get_for_outstanding);
 	atomic_set(&rreq->nr_outstanding, 1);
 	io_iter = rreq->io_iter;
 	do {
@@ -680,25 +678,25 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	} while (rreq->submitted < rreq->len);
 
 	if (sync) {
-		/* Keep nr_outstanding incremented so that the ref always belongs to
-		 * us, and the service code isn't punted off to a random thread pool to
-		 * process.
+		/* Keep nr_outstanding incremented so that the ref always
+		 * belongs to us, and the service code isn't punted off to a
+		 * random thread pool to process.  Note that this might start
+		 * further work, such as writing to the cache.
 		 */
-		for (;;) {
-			wait_var_event(&rreq->nr_outstanding,
-				       atomic_read(&rreq->nr_outstanding) == 1);
+		wait_var_event(&rreq->nr_outstanding,
+			       atomic_read(&rreq->nr_outstanding) == 1);
+		if (atomic_dec_and_test(&rreq->nr_outstanding))
 			netfs_rreq_assess(rreq, false);
-			if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
-				break;
-			cond_resched();
-		}
+
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip);
+		wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
 
 		ret = rreq->error;
 		if (ret == 0 && rreq->submitted < rreq->len) {
 			trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
 			ret = -EIO;
 		}
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_hold);
 	} else {
 		/* If we decrement nr_outstanding to 0, the ref belongs to us. */
 		if (atomic_dec_and_test(&rreq->nr_outstanding))
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 4ea4e34d279f2..6daadf2aac8aa 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -34,7 +34,9 @@
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
 	EM(netfs_rreq_trace_unlock,		"UNLOCK ")	\
-	E_(netfs_rreq_trace_unmark,		"UNMARK ")
+	EM(netfs_rreq_trace_unmark,		"UNMARK ")	\
+	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
+	E_(netfs_rreq_trace_wake_ip,		"WAKE-IP")
 
 #define netfs_sreq_sources					\
 	EM(NETFS_FILL_WITH_ZEROES,		"ZERO")		\
@@ -65,14 +67,13 @@
 	E_(netfs_fail_prepare_write,		"prep-write")
 
 #define netfs_rreq_ref_traces					\
-	EM(netfs_rreq_trace_get_hold,		"GET HOLD   ")	\
+	EM(netfs_rreq_trace_get_for_outstanding,"GET OUTSTND")	\
 	EM(netfs_rreq_trace_get_subreq,		"GET SUBREQ ")	\
 	EM(netfs_rreq_trace_put_complete,	"PUT COMPLT ")	\
 	EM(netfs_rreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_rreq_trace_put_failed,		"PUT FAILED ")	\
-	EM(netfs_rreq_trace_put_hold,		"PUT HOLD   ")	\
+	EM(netfs_rreq_trace_put_return,		"PUT RETURN ")	\
 	EM(netfs_rreq_trace_put_subreq,		"PUT SUBREQ ")	\
-	EM(netfs_rreq_trace_put_zero_len,	"PUT ZEROLEN")	\
 	E_(netfs_rreq_trace_new,		"NEW        ")
 
 #define netfs_sreq_ref_traces					\
-- 
GitLab


From 9ebff83e648148b9ece97d4e4890dd84ca54d6ce Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 29 Sep 2023 17:28:25 +0100
Subject: [PATCH 1962/4076] netfs: Prep to use folio->private for write
 grouping and streaming write

Prepare to use folio->private to hold information write grouping and
streaming write.  These are implemented in the same commit as they both
make use of folio->private and will be both checked at the same time in
several places.

"Write grouping" involves ordering the writeback of groups of writes, such
as is needed for ceph snaps.  A group is represented by a
filesystem-supplied object which must contain a netfs_group struct.  This
contains just a refcount and a pointer to a destructor.

"Streaming write" is the storage of data in folios that are marked dirty,
but not uptodate, to avoid unnecessary reads of data.  This is represented
by a netfs_folio struct.  This contains the offset and length of the
modified region plus the otherwise displaced write grouping pointer.

The way folio->private is multiplexed is:

 (1) If private is NULL then neither is in operation on a dirty folio.

 (2) If private is set, with bit 0 clear, then this points to a group.

 (3) If private is set, with bit 0 set, then this points to a netfs_folio
     struct (with bit 0 AND'ed out).

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/internal.h   | 28 ++++++++++++++++++++++++++
 fs/netfs/misc.c       | 46 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h | 41 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 115 insertions(+)

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 2bf2e82b2ad79..d72292e40f9b9 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -149,6 +149,34 @@ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx)
 #endif
 }
 
+/*
+ * Get a ref on a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline struct netfs_group *netfs_get_group(struct netfs_group *netfs_group)
+{
+	if (netfs_group)
+		refcount_inc(&netfs_group->ref);
+	return netfs_group;
+}
+
+/*
+ * Dispose of a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline void netfs_put_group(struct netfs_group *netfs_group)
+{
+	if (netfs_group && refcount_dec_and_test(&netfs_group->ref))
+		netfs_group->free(netfs_group);
+}
+
+/*
+ * Dispose of a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline void netfs_put_group_many(struct netfs_group *netfs_group, int nr)
+{
+	if (netfs_group && refcount_sub_and_test(nr, &netfs_group->ref))
+		netfs_group->free(netfs_group);
+}
+
 /*
  * fscache-cache.c
  */
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 5d545073fe03c..eeb44abe59c52 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -177,9 +177,55 @@ EXPORT_SYMBOL(netfs_clear_inode_writeback);
  */
 void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 {
+	struct netfs_folio *finfo = NULL;
+	size_t flen = folio_size(folio);
+
 	_enter("{%lx},%zx,%zx", folio_index(folio), offset, length);
 
 	folio_wait_fscache(folio);
+
+	if (!folio_test_private(folio))
+		return;
+
+	finfo = netfs_folio_info(folio);
+
+	if (offset == 0 && length >= flen)
+		goto erase_completely;
+
+	if (finfo) {
+		/* We have a partially uptodate page from a streaming write. */
+		unsigned int fstart = finfo->dirty_offset;
+		unsigned int fend = fstart + finfo->dirty_len;
+		unsigned int end = offset + length;
+
+		if (offset >= fend)
+			return;
+		if (end <= fstart)
+			return;
+		if (offset <= fstart && end >= fend)
+			goto erase_completely;
+		if (offset <= fstart && end > fstart)
+			goto reduce_len;
+		if (offset > fstart && end >= fend)
+			goto move_start;
+		/* A partial write was split.  The caller has already zeroed
+		 * it, so just absorb the hole.
+		 */
+	}
+	return;
+
+erase_completely:
+	netfs_put_group(netfs_folio_group(folio));
+	folio_detach_private(folio);
+	folio_clear_uptodate(folio);
+	kfree(finfo);
+	return;
+reduce_len:
+	finfo->dirty_len = offset + length - finfo->dirty_offset;
+	return;
+move_start:
+	finfo->dirty_len -= offset - finfo->dirty_offset;
+	finfo->dirty_offset = offset;
 }
 EXPORT_SYMBOL(netfs_invalidate_folio);
 
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 3fc41f616621b..cfba83e3e3d2a 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -140,6 +140,47 @@ struct netfs_inode {
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 };
 
+/*
+ * A netfs group - for instance a ceph snap.  This is marked on dirty pages and
+ * pages marked with a group must be flushed before they can be written under
+ * the domain of another group.
+ */
+struct netfs_group {
+	refcount_t		ref;
+	void (*free)(struct netfs_group *netfs_group);
+};
+
+/*
+ * Information about a dirty page (attached only if necessary).
+ * folio->private
+ */
+struct netfs_folio {
+	struct netfs_group	*netfs_group;	/* Filesystem's grouping marker (or NULL). */
+	unsigned int		dirty_offset;	/* Write-streaming dirty data offset */
+	unsigned int		dirty_len;	/* Write-streaming dirty data length */
+};
+#define NETFS_FOLIO_INFO	0x1UL	/* OR'd with folio->private. */
+
+static inline struct netfs_folio *netfs_folio_info(struct folio *folio)
+{
+	void *priv = folio_get_private(folio);
+
+	if ((unsigned long)priv & NETFS_FOLIO_INFO)
+		return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO);
+	return NULL;
+}
+
+static inline struct netfs_group *netfs_folio_group(struct folio *folio)
+{
+	struct netfs_folio *finfo;
+	void *priv = folio_get_private(folio);
+
+	finfo = netfs_folio_info(folio);
+	if (finfo)
+		return finfo->netfs_group;
+	return priv;
+}
+
 /*
  * Resources required to do operations on a cache.
  */
-- 
GitLab


From 0e0f2dfe880fb19e4b15a7ca468623eb0b4ba586 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Jun 2021 22:31:48 +0100
Subject: [PATCH 1963/4076] netfs: Dispatch write requests to process a
 writeback slice

Dispatch one or more write reqeusts to process a writeback slice, where a
slice is tailored more to logical block divisions within the file (such as
crypto blocks, an object layout or cache granules) than the protocol RPC
maximum capacity.

The dispatch doesn't happen until throttling allows, at which point the
entire writeback slice is processed and queued.  A slice may be written to
multiple destinations (one or more servers and the local cache) and the
writes to each destination might be split up along different lines.

The writeback slice holds the required folios pinned.  An iov_iter is
provided in netfs_write_request that describes the buffer to be used.  This
may be part of the pagecache, may have auxiliary padding pages attached or
may be a bounce buffer resulting from crypto or compression.  Consequently,
the filesystem must not twiddle the folio markings directly.

The following API is available to the filesystem:

 (1) The ->create_write_requests() method is called to ask the filesystem
     to create the requests it needs.  This is passed the writeback slice
     to be processed.

 (2) The filesystem should then call netfs_create_write_request() to create
     the requests it needs.

 (3) Once a request is initialised, netfs_queue_write_request() can be
     called to dispatch it asynchronously, if not completed immediately.

 (4) netfs_write_request_completed() should be called to note the
     completion of a request.

 (5) netfs_get_write_request() and netfs_put_write_request() are provided
     to refcount a request.  These take constants from the netfs_wreq_trace
     enum for logging into ftrace.

 (6) The ->free_write_request is method is called to ask the filesystem to
     clean up a request.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile            |   3 +-
 fs/netfs/internal.h          |   6 +
 fs/netfs/output.c            | 363 +++++++++++++++++++++++++++++++++++
 include/linux/netfs.h        |  13 ++
 include/trace/events/netfs.h |  50 ++++-
 5 files changed, 432 insertions(+), 3 deletions(-)
 create mode 100644 fs/netfs/output.c

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index cf3fc847b8ace..c69c6775b8acf 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -7,7 +7,8 @@ netfs-y := \
 	locking.o \
 	main.o \
 	misc.o \
-	objects.o
+	objects.o \
+	output.o
 
 netfs-$(CONFIG_NETFS_STATS) += stats.o
 
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index d72292e40f9b9..0f20587f5a9b1 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -88,6 +88,12 @@ static inline void netfs_see_request(struct netfs_io_request *rreq,
 	trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), what);
 }
 
+/*
+ * output.c
+ */
+int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
+		      enum netfs_write_trace what);
+
 /*
  * stats.c
  */
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
new file mode 100644
index 0000000000000..2ad0fd8c32be2
--- /dev/null
+++ b/fs/netfs/output.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Network filesystem high-level write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/writeback.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+/**
+ * netfs_create_write_request - Create a write operation.
+ * @wreq: The write request this is storing from.
+ * @dest: The destination type
+ * @start: Start of the region this write will modify
+ * @len: Length of the modification
+ * @worker: The worker function to handle the write(s)
+ *
+ * Allocate a write operation, set it up and add it to the list on a write
+ * request.
+ */
+struct netfs_io_subrequest *netfs_create_write_request(struct netfs_io_request *wreq,
+						       enum netfs_io_source dest,
+						       loff_t start, size_t len,
+						       work_func_t worker)
+{
+	struct netfs_io_subrequest *subreq;
+
+	subreq = netfs_alloc_subrequest(wreq);
+	if (subreq) {
+		INIT_WORK(&subreq->work, worker);
+		subreq->source	= dest;
+		subreq->start	= start;
+		subreq->len	= len;
+		subreq->debug_index = wreq->subreq_counter++;
+
+		switch (subreq->source) {
+		case NETFS_UPLOAD_TO_SERVER:
+			netfs_stat(&netfs_n_wh_upload);
+			break;
+		case NETFS_WRITE_TO_CACHE:
+			netfs_stat(&netfs_n_wh_write);
+			break;
+		default:
+			BUG();
+		}
+
+		subreq->io_iter = wreq->io_iter;
+		iov_iter_advance(&subreq->io_iter, subreq->start - wreq->start);
+		iov_iter_truncate(&subreq->io_iter, subreq->len);
+
+		trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index,
+				     refcount_read(&subreq->ref),
+				     netfs_sreq_trace_new);
+		atomic_inc(&wreq->nr_outstanding);
+		list_add_tail(&subreq->rreq_link, &wreq->subrequests);
+		trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+	}
+
+	return subreq;
+}
+EXPORT_SYMBOL(netfs_create_write_request);
+
+/*
+ * Process a completed write request once all the component operations have
+ * been completed.
+ */
+static void netfs_write_terminated(struct netfs_io_request *wreq, bool was_async)
+{
+	struct netfs_io_subrequest *subreq;
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+
+	_enter("R=%x[]", wreq->debug_id);
+
+	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
+
+	list_for_each_entry(subreq, &wreq->subrequests, rreq_link) {
+		if (!subreq->error)
+			continue;
+		switch (subreq->source) {
+		case NETFS_UPLOAD_TO_SERVER:
+			/* Depending on the type of failure, this may prevent
+			 * writeback completion unless we're in disconnected
+			 * mode.
+			 */
+			if (!wreq->error)
+				wreq->error = subreq->error;
+			break;
+
+		case NETFS_WRITE_TO_CACHE:
+			/* Failure doesn't prevent writeback completion unless
+			 * we're in disconnected mode.
+			 */
+			if (subreq->error != -ENOBUFS)
+				ctx->ops->invalidate_cache(wreq);
+			break;
+
+		default:
+			WARN_ON_ONCE(1);
+			if (!wreq->error)
+				wreq->error = -EIO;
+			return;
+		}
+	}
+
+	wreq->cleanup(wreq);
+
+	_debug("finished");
+	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
+	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
+	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
+
+	netfs_clear_subrequests(wreq, was_async);
+	netfs_put_request(wreq, was_async, netfs_rreq_trace_put_complete);
+}
+
+/*
+ * Deal with the completion of writing the data to the cache.
+ */
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
+				       bool was_async)
+{
+	struct netfs_io_subrequest *subreq = _op;
+	struct netfs_io_request *wreq = subreq->rreq;
+	unsigned int u;
+
+	_enter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
+
+	switch (subreq->source) {
+	case NETFS_UPLOAD_TO_SERVER:
+		netfs_stat(&netfs_n_wh_upload_done);
+		break;
+	case NETFS_WRITE_TO_CACHE:
+		netfs_stat(&netfs_n_wh_write_done);
+		break;
+	case NETFS_INVALID_WRITE:
+		break;
+	default:
+		BUG();
+	}
+
+	if (IS_ERR_VALUE(transferred_or_error)) {
+		subreq->error = transferred_or_error;
+		trace_netfs_failure(wreq, subreq, transferred_or_error,
+				    netfs_fail_write);
+		goto failed;
+	}
+
+	if (WARN(transferred_or_error > subreq->len - subreq->transferred,
+		 "Subreq excess write: R%x[%x] %zd > %zu - %zu",
+		 wreq->debug_id, subreq->debug_index,
+		 transferred_or_error, subreq->len, subreq->transferred))
+		transferred_or_error = subreq->len - subreq->transferred;
+
+	subreq->error = 0;
+	subreq->transferred += transferred_or_error;
+
+	if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+		pr_warn("R=%08x[%u] ITER POST-MISMATCH %zx != %zx-%zx %x\n",
+			wreq->debug_id, subreq->debug_index,
+			iov_iter_count(&subreq->io_iter), subreq->len,
+			subreq->transferred, subreq->io_iter.iter_type);
+
+	if (subreq->transferred < subreq->len)
+		goto incomplete;
+
+	__clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags);
+out:
+	trace_netfs_sreq(subreq, netfs_sreq_trace_terminated);
+
+	/* If we decrement nr_outstanding to 0, the ref belongs to us. */
+	u = atomic_dec_return(&wreq->nr_outstanding);
+	if (u == 0)
+		netfs_write_terminated(wreq, was_async);
+	else if (u == 1)
+		wake_up_var(&wreq->nr_outstanding);
+
+	netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
+	return;
+
+incomplete:
+	if (transferred_or_error == 0) {
+		if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) {
+			subreq->error = -ENODATA;
+			goto failed;
+		}
+	} else {
+		__clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags);
+	}
+
+	__set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags);
+	set_bit(NETFS_RREQ_INCOMPLETE_IO, &wreq->flags);
+	goto out;
+
+failed:
+	switch (subreq->source) {
+	case NETFS_WRITE_TO_CACHE:
+		netfs_stat(&netfs_n_wh_write_failed);
+		set_bit(NETFS_RREQ_INCOMPLETE_IO, &wreq->flags);
+		break;
+	case NETFS_UPLOAD_TO_SERVER:
+		netfs_stat(&netfs_n_wh_upload_failed);
+		set_bit(NETFS_RREQ_FAILED, &wreq->flags);
+		wreq->error = subreq->error;
+		break;
+	default:
+		break;
+	}
+	goto out;
+}
+EXPORT_SYMBOL(netfs_write_subrequest_terminated);
+
+static void netfs_write_to_cache_op(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *wreq = subreq->rreq;
+	struct netfs_cache_resources *cres = &wreq->cache_resources;
+
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+
+	cres->ops->write(cres, subreq->start, &subreq->io_iter,
+			 netfs_write_subrequest_terminated, subreq);
+}
+
+static void netfs_write_to_cache_op_worker(struct work_struct *work)
+{
+	struct netfs_io_subrequest *subreq =
+		container_of(work, struct netfs_io_subrequest, work);
+
+	netfs_write_to_cache_op(subreq);
+}
+
+/**
+ * netfs_queue_write_request - Queue a write request for attention
+ * @subreq: The write request to be queued
+ *
+ * Queue the specified write request for processing by a worker thread.  We
+ * pass the caller's ref on the request to the worker thread.
+ */
+void netfs_queue_write_request(struct netfs_io_subrequest *subreq)
+{
+	if (!queue_work(system_unbound_wq, &subreq->work))
+		netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_wip);
+}
+EXPORT_SYMBOL(netfs_queue_write_request);
+
+/*
+ * Set up a op for writing to the cache.
+ */
+static void netfs_set_up_write_to_cache(struct netfs_io_request *wreq)
+{
+	struct netfs_cache_resources *cres;
+	struct netfs_io_subrequest *subreq;
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+	struct fscache_cookie *cookie = netfs_i_cookie(ctx);
+	loff_t start = wreq->start;
+	size_t len = wreq->len;
+	int ret;
+
+	if (!fscache_cookie_enabled(cookie)) {
+		clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags);
+		return;
+	}
+
+	_debug("write to cache");
+	subreq = netfs_create_write_request(wreq, NETFS_WRITE_TO_CACHE, start, len,
+					    netfs_write_to_cache_op_worker);
+	if (!subreq)
+		return;
+
+	cres = &wreq->cache_resources;
+	ret = fscache_begin_read_operation(cres, cookie);
+	if (ret < 0) {
+		netfs_write_subrequest_terminated(subreq, ret, false);
+		return;
+	}
+
+	ret = cres->ops->prepare_write(cres, &start, &len, i_size_read(wreq->inode),
+				       true);
+	if (ret < 0) {
+		netfs_write_subrequest_terminated(subreq, ret, false);
+		return;
+	}
+
+	netfs_queue_write_request(subreq);
+}
+
+/*
+ * Begin the process of writing out a chunk of data.
+ *
+ * We are given a write request that holds a series of dirty regions and
+ * (partially) covers a sequence of folios, all of which are present.  The
+ * pages must have been marked as writeback as appropriate.
+ *
+ * We need to perform the following steps:
+ *
+ * (1) If encrypting, create an output buffer and encrypt each block of the
+ *     data into it, otherwise the output buffer will point to the original
+ *     folios.
+ *
+ * (2) If the data is to be cached, set up a write op for the entire output
+ *     buffer to the cache, if the cache wants to accept it.
+ *
+ * (3) If the data is to be uploaded (ie. not merely cached):
+ *
+ *     (a) If the data is to be compressed, create a compression buffer and
+ *         compress the data into it.
+ *
+ *     (b) For each destination we want to upload to, set up write ops to write
+ *         to that destination.  We may need multiple writes if the data is not
+ *         contiguous or the span exceeds wsize for a server.
+ */
+int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
+		      enum netfs_write_trace what)
+{
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+
+	_enter("R=%x %llx-%llx f=%lx",
+	       wreq->debug_id, wreq->start, wreq->start + wreq->len - 1,
+	       wreq->flags);
+
+	trace_netfs_write(wreq, what);
+	if (wreq->len == 0 || wreq->iter.count == 0) {
+		pr_err("Zero-sized write [R=%x]\n", wreq->debug_id);
+		return -EIO;
+	}
+
+	wreq->io_iter = wreq->iter;
+
+	/* ->outstanding > 0 carries a ref */
+	netfs_get_request(wreq, netfs_rreq_trace_get_for_outstanding);
+	atomic_set(&wreq->nr_outstanding, 1);
+
+	/* Start the encryption/compression going.  We can do that in the
+	 * background whilst we generate a list of write ops that we want to
+	 * perform.
+	 */
+	// TODO: Encrypt or compress the region as appropriate
+
+	/* We need to write all of the region to the cache */
+	if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags))
+		netfs_set_up_write_to_cache(wreq);
+
+	/* However, we don't necessarily write all of the region to the server.
+	 * Caching of reads is being managed this way also.
+	 */
+	if (test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))
+		ctx->ops->create_write_requests(wreq, wreq->start, wreq->len);
+
+	if (atomic_dec_and_test(&wreq->nr_outstanding))
+		netfs_write_terminated(wreq, false);
+
+	if (!may_wait)
+		return -EIOCBQUEUED;
+
+	wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+		    TASK_UNINTERRUPTIBLE);
+	return wreq->error;
+}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index cfba83e3e3d2a..890a5d8b22992 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -249,6 +249,7 @@ struct netfs_io_request {
 	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
 	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
+	unsigned int		wsize;		/* Maximum write size (0 for none) */
 	unsigned int		subreq_counter;	/* Next subreq->debug_index */
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
@@ -271,6 +272,7 @@ struct netfs_io_request {
 #define NETFS_RREQ_WRITE_TO_CACHE	7	/* Need to write to the cache */
 #define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
 	const struct netfs_request_ops *netfs_ops;
+	void (*cleanup)(struct netfs_io_request *req);
 };
 
 /*
@@ -294,6 +296,11 @@ struct netfs_request_ops {
 
 	/* Modification handling */
 	void (*update_i_size)(struct inode *inode, loff_t i_size);
+
+	/* Write request handling */
+	void (*create_write_requests)(struct netfs_io_request *wreq,
+				      loff_t start, size_t len);
+	void (*invalidate_cache)(struct netfs_io_request *wreq);
 };
 
 /*
@@ -382,6 +389,12 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				iov_iter_extraction_t extraction_flags);
 size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
 			size_t max_size, size_t max_segs);
+struct netfs_io_subrequest *netfs_create_write_request(
+	struct netfs_io_request *wreq, enum netfs_io_source dest,
+	loff_t start, size_t len, work_func_t worker);
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
+				       bool was_async);
+void netfs_queue_write_request(struct netfs_io_subrequest *subreq);
 
 int netfs_start_io_read(struct inode *inode);
 void netfs_end_io_read(struct inode *inode);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 6daadf2aac8aa..e03635172760e 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -21,6 +21,11 @@
 	EM(netfs_read_trace_readpage,		"READPAGE ")	\
 	E_(netfs_read_trace_write_begin,	"WRITEBEGN")
 
+#define netfs_write_traces					\
+	EM(netfs_write_trace_dio_write,		"DIO-WRITE")	\
+	EM(netfs_write_trace_unbuffered_write,	"UNB-WRITE")	\
+	E_(netfs_write_trace_writeback,		"WRITEBACK")
+
 #define netfs_rreq_origins					\
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
@@ -32,11 +37,13 @@
 	EM(netfs_rreq_trace_copy,		"COPY   ")	\
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
 	EM(netfs_rreq_trace_unlock,		"UNLOCK ")	\
 	EM(netfs_rreq_trace_unmark,		"UNMARK ")	\
 	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
-	E_(netfs_rreq_trace_wake_ip,		"WAKE-IP")
+	EM(netfs_rreq_trace_wake_ip,		"WAKE-IP")	\
+	E_(netfs_rreq_trace_write_done,		"WR-DONE")
 
 #define netfs_sreq_sources					\
 	EM(NETFS_FILL_WITH_ZEROES,		"ZERO")		\
@@ -64,7 +71,8 @@
 	EM(netfs_fail_copy_to_cache,		"copy-to-cache")	\
 	EM(netfs_fail_read,			"read")			\
 	EM(netfs_fail_short_read,		"short-read")		\
-	E_(netfs_fail_prepare_write,		"prep-write")
+	EM(netfs_fail_prepare_write,		"prep-write")		\
+	E_(netfs_fail_write,			"write")
 
 #define netfs_rreq_ref_traces					\
 	EM(netfs_rreq_trace_get_for_outstanding,"GET OUTSTND")	\
@@ -74,6 +82,8 @@
 	EM(netfs_rreq_trace_put_failed,		"PUT FAILED ")	\
 	EM(netfs_rreq_trace_put_return,		"PUT RETURN ")	\
 	EM(netfs_rreq_trace_put_subreq,		"PUT SUBREQ ")	\
+	EM(netfs_rreq_trace_put_work,		"PUT WORK   ")	\
+	EM(netfs_rreq_trace_see_work,		"SEE WORK   ")	\
 	E_(netfs_rreq_trace_new,		"NEW        ")
 
 #define netfs_sreq_ref_traces					\
@@ -82,9 +92,12 @@
 	EM(netfs_sreq_trace_get_short_read,	"GET SHORTRD")	\
 	EM(netfs_sreq_trace_new,		"NEW        ")	\
 	EM(netfs_sreq_trace_put_clear,		"PUT CLEAR  ")	\
+	EM(netfs_sreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_sreq_trace_put_failed,		"PUT FAILED ")	\
 	EM(netfs_sreq_trace_put_merged,		"PUT MERGED ")	\
 	EM(netfs_sreq_trace_put_no_copy,	"PUT NO COPY")	\
+	EM(netfs_sreq_trace_put_wip,		"PUT WIP    ")	\
+	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
 	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
 
 #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
@@ -96,6 +109,7 @@
 #define E_(a, b) a
 
 enum netfs_read_trace { netfs_read_traces } __mode(byte);
+enum netfs_write_trace { netfs_write_traces } __mode(byte);
 enum netfs_rreq_trace { netfs_rreq_traces } __mode(byte);
 enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte);
 enum netfs_failure { netfs_failures } __mode(byte);
@@ -113,6 +127,7 @@ enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte);
 #define E_(a, b) TRACE_DEFINE_ENUM(a);
 
 netfs_read_traces;
+netfs_write_traces;
 netfs_rreq_origins;
 netfs_rreq_traces;
 netfs_sreq_sources;
@@ -320,6 +335,37 @@ TRACE_EVENT(netfs_sreq_ref,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(netfs_write,
+	    TP_PROTO(const struct netfs_io_request *wreq,
+		     enum netfs_write_trace what),
+
+	    TP_ARGS(wreq, what),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		wreq		)
+		    __field(unsigned int,		cookie		)
+		    __field(enum netfs_write_trace,	what		)
+		    __field(unsigned long long,		start		)
+		    __field(size_t,			len		)
+			     ),
+
+	    TP_fast_assign(
+		    struct netfs_inode *__ctx = netfs_inode(wreq->inode);
+		    struct fscache_cookie *__cookie = netfs_i_cookie(__ctx);
+		    __entry->wreq	= wreq->debug_id;
+		    __entry->cookie	= __cookie ? __cookie->debug_id : 0;
+		    __entry->what	= what;
+		    __entry->start	= wreq->start;
+		    __entry->len	= wreq->len;
+			   ),
+
+	    TP_printk("R=%08x %s c=%08x by=%llx-%llx",
+		      __entry->wreq,
+		      __print_symbolic(__entry->what, netfs_write_traces),
+		      __entry->cookie,
+		      __entry->start, __entry->start + __entry->len - 1)
+	    );
+
 #undef EM
 #undef E_
 #endif /* _TRACE_NETFS_H */
-- 
GitLab


From c38f4e96e605f17990e871214e6ea1496bc4e65f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 17 Jun 2021 13:09:21 +0100
Subject: [PATCH 1964/4076] netfs: Provide func to copy data to pagecache for
 buffered write

Provide a netfs write helper, netfs_perform_write() to buffer data to be
written in the pagecache and mark the modified folios dirty.

It will perform "streaming writes" for folios that aren't currently
resident, if possible, storing data in partially modified folios that are
marked dirty, but not uptodate.  It will also tag pages as belonging to
fs-specific write groups if so directed by the filesystem.

This is derived from generic_perform_write(), but doesn't use
->write_begin() and ->write_end(), having that logic rolled in instead.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile            |   1 +
 fs/netfs/buffered_read.c     |  49 ++++++
 fs/netfs/buffered_write.c    | 330 +++++++++++++++++++++++++++++++++++
 fs/netfs/internal.h          |   2 +
 fs/netfs/io.c                |   1 +
 include/linux/netfs.h        |   5 +
 include/trace/events/netfs.h |  73 ++++++++
 7 files changed, 461 insertions(+)
 create mode 100644 fs/netfs/buffered_write.c

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index c69c6775b8acf..85d8333a1ed46 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -2,6 +2,7 @@
 
 netfs-y := \
 	buffered_read.o \
+	buffered_write.o \
 	io.o \
 	iterator.o \
 	locking.o \
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 6b9a44cafbac6..73a6e4d61f9de 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -63,6 +63,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 				break;
 			}
 			if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) {
+				trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
 				folio_start_fscache(folio);
 				folio_started = true;
 			}
@@ -454,3 +455,51 @@ error:
 	return ret;
 }
 EXPORT_SYMBOL(netfs_write_begin);
+
+/*
+ * Preload the data into a page we're proposing to write into.
+ */
+int netfs_prefetch_for_write(struct file *file, struct folio *folio,
+			     size_t offset, size_t len)
+{
+	struct netfs_io_request *rreq;
+	struct address_space *mapping = folio_file_mapping(folio);
+	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	unsigned long long start = folio_pos(folio);
+	size_t flen = folio_size(folio);
+	int ret;
+
+	_enter("%zx @%llx", flen, start);
+
+	ret = -ENOMEM;
+
+	rreq = netfs_alloc_request(mapping, file, start, flen,
+				   NETFS_READ_FOR_WRITE);
+	if (IS_ERR(rreq)) {
+		ret = PTR_ERR(rreq);
+		goto error;
+	}
+
+	rreq->no_unlock_folio = folio_index(folio);
+	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto error_put;
+
+	netfs_stat(&netfs_n_rh_write_begin);
+	trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write);
+
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+			rreq->start, rreq->len);
+
+	ret = netfs_begin_read(rreq, true);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	return ret;
+
+error_put:
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
new file mode 100644
index 0000000000000..6e7f06d9962db
--- /dev/null
+++ b/fs/netfs/buffered_write.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Network filesystem high-level write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+/*
+ * Determined write method.  Adjust netfs_folio_traces if this is changed.
+ */
+enum netfs_how_to_modify {
+	NETFS_FOLIO_IS_UPTODATE,	/* Folio is uptodate already */
+	NETFS_JUST_PREFETCH,		/* We have to read the folio anyway */
+	NETFS_WHOLE_FOLIO_MODIFY,	/* We're going to overwrite the whole folio */
+	NETFS_MODIFY_AND_CLEAR,		/* We can assume there is no data to be downloaded. */
+	NETFS_STREAMING_WRITE,		/* Store incomplete data in non-uptodate page. */
+	NETFS_STREAMING_WRITE_CONT,	/* Continue streaming write. */
+	NETFS_FLUSH_CONTENT,		/* Flush incompatible content. */
+};
+
+static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group)
+{
+	if (netfs_group && !folio_get_private(folio))
+		folio_attach_private(folio, netfs_get_group(netfs_group));
+}
+
+/*
+ * Decide how we should modify a folio.  We might be attempting to do
+ * write-streaming, in which case we don't want to a local RMW cycle if we can
+ * avoid it.  If we're doing local caching or content crypto, we award that
+ * priority over avoiding RMW.  If the file is open readably, then we also
+ * assume that we may want to read what we wrote.
+ */
+static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
+						    struct file *file,
+						    struct folio *folio,
+						    void *netfs_group,
+						    size_t flen,
+						    size_t offset,
+						    size_t len,
+						    bool maybe_trouble)
+{
+	struct netfs_folio *finfo = netfs_folio_info(folio);
+	loff_t pos = folio_file_pos(folio);
+
+	_enter("");
+
+	if (netfs_folio_group(folio) != netfs_group)
+		return NETFS_FLUSH_CONTENT;
+
+	if (folio_test_uptodate(folio))
+		return NETFS_FOLIO_IS_UPTODATE;
+
+	if (pos >= ctx->remote_i_size)
+		return NETFS_MODIFY_AND_CLEAR;
+
+	if (!maybe_trouble && offset == 0 && len >= flen)
+		return NETFS_WHOLE_FOLIO_MODIFY;
+
+	if (file->f_mode & FMODE_READ)
+		return NETFS_JUST_PREFETCH;
+
+	if (netfs_is_cache_enabled(ctx))
+		return NETFS_JUST_PREFETCH;
+
+	if (!finfo)
+		return NETFS_STREAMING_WRITE;
+
+	/* We can continue a streaming write only if it continues on from the
+	 * previous.  If it overlaps, we must flush lest we suffer a partial
+	 * copy and disjoint dirty regions.
+	 */
+	if (offset == finfo->dirty_offset + finfo->dirty_len)
+		return NETFS_STREAMING_WRITE_CONT;
+	return NETFS_FLUSH_CONTENT;
+}
+
+/*
+ * Grab a folio for writing and lock it.
+ */
+static struct folio *netfs_grab_folio_for_write(struct address_space *mapping,
+						loff_t pos, size_t part)
+{
+	pgoff_t index = pos / PAGE_SIZE;
+
+	return __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+				   mapping_gfp_mask(mapping));
+}
+
+/**
+ * netfs_perform_write - Copy data into the pagecache.
+ * @iocb: The operation parameters
+ * @iter: The source buffer
+ * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ *
+ * Copy data into pagecache pages attached to the inode specified by @iocb.
+ * The caller must hold appropriate inode locks.
+ *
+ * Dirty pages are tagged with a netfs_folio struct if they're not up to date
+ * to indicate the range modified.  Dirty pages may also be tagged with a
+ * netfs-specific grouping such that data from an old group gets flushed before
+ * a new one is started.
+ */
+ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
+			    struct netfs_group *netfs_group)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct address_space *mapping = inode->i_mapping;
+	struct netfs_inode *ctx = netfs_inode(inode);
+	struct netfs_folio *finfo;
+	struct folio *folio;
+	enum netfs_how_to_modify howto;
+	enum netfs_folio_trace trace;
+	unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC;
+	ssize_t written = 0, ret;
+	loff_t i_size, pos = iocb->ki_pos, from, to;
+	size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
+	bool maybe_trouble = false;
+
+	do {
+		size_t flen;
+		size_t offset;	/* Offset into pagecache folio */
+		size_t part;	/* Bytes to write to folio */
+		size_t copied;	/* Bytes copied from user */
+
+		ret = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags);
+		if (unlikely(ret < 0))
+			break;
+
+		offset = pos & (max_chunk - 1);
+		part = min(max_chunk - offset, iov_iter_count(iter));
+
+		/* Bring in the user pages that we will copy from _first_ lest
+		 * we hit a nasty deadlock on copying from the same page as
+		 * we're writing to, without it being marked uptodate.
+		 *
+		 * Not only is this an optimisation, but it is also required to
+		 * check that the address is actually valid, when atomic
+		 * usercopies are used below.
+		 *
+		 * We rely on the page being held onto long enough by the LRU
+		 * that we can grab it below if this causes it to be read.
+		 */
+		ret = -EFAULT;
+		if (unlikely(fault_in_iov_iter_readable(iter, part) == part))
+			break;
+
+		ret = -ENOMEM;
+		folio = netfs_grab_folio_for_write(mapping, pos, part);
+		if (!folio)
+			break;
+
+		flen = folio_size(folio);
+		offset = pos & (flen - 1);
+		part = min_t(size_t, flen - offset, part);
+
+		if (signal_pending(current)) {
+			ret = written ? -EINTR : -ERESTARTSYS;
+			goto error_folio_unlock;
+		}
+
+		/* See if we need to prefetch the area we're going to modify.
+		 * We need to do this before we get a lock on the folio in case
+		 * there's more than one writer competing for the same cache
+		 * block.
+		 */
+		howto = netfs_how_to_modify(ctx, file, folio, netfs_group,
+					    flen, offset, part, maybe_trouble);
+		_debug("howto %u", howto);
+		switch (howto) {
+		case NETFS_JUST_PREFETCH:
+			ret = netfs_prefetch_for_write(file, folio, offset, part);
+			if (ret < 0) {
+				_debug("prefetch = %zd", ret);
+				goto error_folio_unlock;
+			}
+			break;
+		case NETFS_FOLIO_IS_UPTODATE:
+		case NETFS_WHOLE_FOLIO_MODIFY:
+		case NETFS_STREAMING_WRITE_CONT:
+			break;
+		case NETFS_MODIFY_AND_CLEAR:
+			zero_user_segment(&folio->page, 0, offset);
+			break;
+		case NETFS_STREAMING_WRITE:
+			ret = -EIO;
+			if (WARN_ON(folio_get_private(folio)))
+				goto error_folio_unlock;
+			break;
+		case NETFS_FLUSH_CONTENT:
+			trace_netfs_folio(folio, netfs_flush_content);
+			from = folio_pos(folio);
+			to = from + folio_size(folio) - 1;
+			folio_unlock(folio);
+			folio_put(folio);
+			ret = filemap_write_and_wait_range(mapping, from, to);
+			if (ret < 0)
+				goto error_folio_unlock;
+			continue;
+		}
+
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_folio(folio);
+
+		copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
+
+		flush_dcache_folio(folio);
+
+		/* Deal with a (partially) failed copy */
+		if (copied == 0) {
+			ret = -EFAULT;
+			goto error_folio_unlock;
+		}
+
+		trace = (enum netfs_folio_trace)howto;
+		switch (howto) {
+		case NETFS_FOLIO_IS_UPTODATE:
+		case NETFS_JUST_PREFETCH:
+			netfs_set_group(folio, netfs_group);
+			break;
+		case NETFS_MODIFY_AND_CLEAR:
+			zero_user_segment(&folio->page, offset + copied, flen);
+			netfs_set_group(folio, netfs_group);
+			folio_mark_uptodate(folio);
+			break;
+		case NETFS_WHOLE_FOLIO_MODIFY:
+			if (unlikely(copied < part)) {
+				maybe_trouble = true;
+				iov_iter_revert(iter, copied);
+				copied = 0;
+				goto retry;
+			}
+			netfs_set_group(folio, netfs_group);
+			folio_mark_uptodate(folio);
+			break;
+		case NETFS_STREAMING_WRITE:
+			if (offset == 0 && copied == flen) {
+				netfs_set_group(folio, netfs_group);
+				folio_mark_uptodate(folio);
+				trace = netfs_streaming_filled_page;
+				break;
+			}
+			finfo = kzalloc(sizeof(*finfo), GFP_KERNEL);
+			if (!finfo) {
+				iov_iter_revert(iter, copied);
+				ret = -ENOMEM;
+				goto error_folio_unlock;
+			}
+			finfo->netfs_group = netfs_get_group(netfs_group);
+			finfo->dirty_offset = offset;
+			finfo->dirty_len = copied;
+			folio_attach_private(folio, (void *)((unsigned long)finfo |
+							     NETFS_FOLIO_INFO));
+			break;
+		case NETFS_STREAMING_WRITE_CONT:
+			finfo = netfs_folio_info(folio);
+			finfo->dirty_len += copied;
+			if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) {
+				if (finfo->netfs_group)
+					folio_change_private(folio, finfo->netfs_group);
+				else
+					folio_detach_private(folio);
+				folio_mark_uptodate(folio);
+				kfree(finfo);
+				trace = netfs_streaming_cont_filled_page;
+			}
+			break;
+		default:
+			WARN(true, "Unexpected modify type %u ix=%lx\n",
+			     howto, folio_index(folio));
+			ret = -EIO;
+			goto error_folio_unlock;
+		}
+
+		trace_netfs_folio(folio, trace);
+
+		/* Update the inode size if we moved the EOF marker */
+		i_size = i_size_read(inode);
+		pos += copied;
+		if (pos > i_size) {
+			if (ctx->ops->update_i_size) {
+				ctx->ops->update_i_size(inode, pos);
+			} else {
+				i_size_write(inode, pos);
+#if IS_ENABLED(CONFIG_FSCACHE)
+				fscache_update_cookie(ctx->cache, NULL, &pos);
+#endif
+			}
+		}
+		written += copied;
+
+		folio_mark_dirty(folio);
+	retry:
+		folio_unlock(folio);
+		folio_put(folio);
+		folio = NULL;
+
+		cond_resched();
+	} while (iov_iter_count(iter));
+
+out:
+	if (likely(written)) {
+		/* Flush and wait for a write that requires immediate synchronisation. */
+		if (iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) {
+			_debug("dsync");
+			ret = filemap_fdatawait_range(mapping, iocb->ki_pos,
+						      iocb->ki_pos + written);
+		}
+
+		iocb->ki_pos += written;
+	}
+
+	_leave(" = %zd [%zd]", written, ret);
+	return written ? written : ret;
+
+error_folio_unlock:
+	folio_unlock(folio);
+	folio_put(folio);
+	goto out;
+}
+EXPORT_SYMBOL(netfs_perform_write);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 0f20587f5a9b1..17e4ea4456c75 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -23,6 +23,8 @@
  * buffered_read.c
  */
 void netfs_rreq_unlock_folios(struct netfs_io_request *rreq);
+int netfs_prefetch_for_write(struct file *file, struct folio *folio,
+			     size_t offset, size_t len);
 
 /*
  * io.c
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index e83ef5835d250..774aef6ea4cbc 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -125,6 +125,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
 			if (have_unlocked && folio_index(folio) <= unlocked)
 				continue;
 			unlocked = folio_index(folio);
+			trace_netfs_folio(folio, netfs_folio_trace_end_copy);
 			folio_end_fscache(folio);
 			have_unlocked = true;
 		}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 890a5d8b22992..70f578cf3715f 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -367,6 +367,11 @@ struct netfs_cache_ops {
 			       loff_t *_data_start, size_t *_data_len);
 };
 
+/* High-level write API */
+ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
+			    struct netfs_group *netfs_group);
+
+/* Address operations API */
 struct readahead_control;
 void netfs_readahead(struct readahead_control *);
 int netfs_read_folio(struct file *, struct folio *);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index e03635172760e..8308b81f36bed 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -19,6 +19,7 @@
 	EM(netfs_read_trace_expanded,		"EXPANDED ")	\
 	EM(netfs_read_trace_readahead,		"READAHEAD")	\
 	EM(netfs_read_trace_readpage,		"READPAGE ")	\
+	EM(netfs_read_trace_prefetch_for_write,	"PREFETCHW")	\
 	E_(netfs_read_trace_write_begin,	"WRITEBEGN")
 
 #define netfs_write_traces					\
@@ -100,6 +101,31 @@
 	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
 	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
 
+#define netfs_folio_traces					\
+	/* The first few correspond to enum netfs_how_to_modify */	\
+	EM(netfs_folio_is_uptodate,		"mod-uptodate")	\
+	EM(netfs_just_prefetch,			"mod-prefetch")	\
+	EM(netfs_whole_folio_modify,		"mod-whole-f")	\
+	EM(netfs_modify_and_clear,		"mod-n-clear")	\
+	EM(netfs_streaming_write,		"mod-streamw")	\
+	EM(netfs_streaming_write_cont,		"mod-streamw+")	\
+	EM(netfs_flush_content,			"flush")	\
+	EM(netfs_streaming_filled_page,		"mod-streamw-f") \
+	EM(netfs_streaming_cont_filled_page,	"mod-streamw-f+") \
+	/* The rest are for writeback */			\
+	EM(netfs_folio_trace_clear,		"clear")	\
+	EM(netfs_folio_trace_clear_s,		"clear-s")	\
+	EM(netfs_folio_trace_clear_g,		"clear-g")	\
+	EM(netfs_folio_trace_copy_to_cache,	"copy")		\
+	EM(netfs_folio_trace_end_copy,		"end-copy")	\
+	EM(netfs_folio_trace_kill,		"kill")		\
+	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
+	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
+	EM(netfs_folio_trace_redirty,		"redirty")	\
+	EM(netfs_folio_trace_redirtied,		"redirtied")	\
+	EM(netfs_folio_trace_store,		"store")	\
+	E_(netfs_folio_trace_store_plus,	"store+")
+
 #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 
@@ -115,6 +141,7 @@ enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte);
 enum netfs_failure { netfs_failures } __mode(byte);
 enum netfs_rreq_ref_trace { netfs_rreq_ref_traces } __mode(byte);
 enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte);
+enum netfs_folio_trace { netfs_folio_traces } __mode(byte);
 
 #endif
 
@@ -135,6 +162,7 @@ netfs_sreq_traces;
 netfs_failures;
 netfs_rreq_ref_traces;
 netfs_sreq_ref_traces;
+netfs_folio_traces;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -335,6 +363,51 @@ TRACE_EVENT(netfs_sreq_ref,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(netfs_folio,
+	    TP_PROTO(struct folio *folio, enum netfs_folio_trace why),
+
+	    TP_ARGS(folio, why),
+
+	    TP_STRUCT__entry(
+		    __field(ino_t,			ino)
+		    __field(pgoff_t,			index)
+		    __field(unsigned int,		nr)
+		    __field(enum netfs_folio_trace,	why)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->ino = folio->mapping->host->i_ino;
+		    __entry->why = why;
+		    __entry->index = folio_index(folio);
+		    __entry->nr = folio_nr_pages(folio);
+			   ),
+
+	    TP_printk("i=%05lx ix=%05lx-%05lx %s",
+		      __entry->ino, __entry->index, __entry->index + __entry->nr - 1,
+		      __print_symbolic(__entry->why, netfs_folio_traces))
+	    );
+
+TRACE_EVENT(netfs_write_iter,
+	    TP_PROTO(const struct kiocb *iocb, const struct iov_iter *from),
+
+	    TP_ARGS(iocb, from),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned long long,		start		)
+		    __field(size_t,			len		)
+		    __field(unsigned int,		flags		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->start	= iocb->ki_pos;
+		    __entry->len	= iov_iter_count(from);
+		    __entry->flags	= iocb->ki_flags;
+			   ),
+
+	    TP_printk("WRITE-ITER s=%llx l=%zx f=%x",
+		      __entry->start, __entry->len, __entry->flags)
+	    );
+
 TRACE_EVENT(netfs_write,
 	    TP_PROTO(const struct netfs_io_request *wreq,
 		     enum netfs_write_trace what),
-- 
GitLab


From 7f84a7b9892d1c9429a6f5d6f67916c61b3fc183 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 2 Oct 2023 12:51:19 +0100
Subject: [PATCH 1965/4076] netfs: Make netfs_read_folio() handle
 streaming-write pages

netfs_read_folio() needs to handle partially-valid pages that are marked
dirty, but not uptodate in the event that someone tries to read a page was
used to cache data by a streaming write.

In such a case, make netfs_read_folio() set up a bvec iterator that points
to the parts of the folio that need filling and to a sink page for the data
that should be discarded and use that instead of i_pages as the iterator to
be written to.

This requires netfs_rreq_unlock_folios() to convert the page into a normal
dirty uptodate page, getting rid of the partial write record and bumping
the group pointer over to folio->private.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_read.c     | 61 ++++++++++++++++++++++++++++++++++--
 include/trace/events/netfs.h |  2 ++
 2 files changed, 60 insertions(+), 3 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 73a6e4d61f9de..950f63fc156a8 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -16,6 +16,7 @@
 void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 {
 	struct netfs_io_subrequest *subreq;
+	struct netfs_folio *finfo;
 	struct folio *folio;
 	pgoff_t start_page = rreq->start / PAGE_SIZE;
 	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
@@ -87,6 +88,15 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 
 		if (!pg_failed) {
 			flush_dcache_folio(folio);
+			finfo = netfs_folio_info(folio);
+			if (finfo) {
+				trace_netfs_folio(folio, netfs_folio_trace_filled_gaps);
+				if (finfo->netfs_group)
+					folio_change_private(folio, finfo->netfs_group);
+				else
+					folio_detach_private(folio);
+				kfree(finfo);
+			}
 			folio_mark_uptodate(folio);
 		}
 
@@ -239,6 +249,7 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	struct address_space *mapping = folio_file_mapping(folio);
 	struct netfs_io_request *rreq;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	struct folio *sink = NULL;
 	int ret;
 
 	_enter("%lx", folio_index(folio));
@@ -259,12 +270,56 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
 
 	/* Set up the output buffer */
-	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
-			rreq->start, rreq->len);
+	if (folio_test_dirty(folio)) {
+		/* Handle someone trying to read from an unflushed streaming
+		 * write.  We fiddle the buffer so that a gap at the beginning
+		 * and/or a gap at the end get copied to, but the middle is
+		 * discarded.
+		 */
+		struct netfs_folio *finfo = netfs_folio_info(folio);
+		struct bio_vec *bvec;
+		unsigned int from = finfo->dirty_offset;
+		unsigned int to = from + finfo->dirty_len;
+		unsigned int off = 0, i = 0;
+		size_t flen = folio_size(folio);
+		size_t nr_bvec = flen / PAGE_SIZE + 2;
+		size_t part;
+
+		ret = -ENOMEM;
+		bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL);
+		if (!bvec)
+			goto discard;
+
+		sink = folio_alloc(GFP_KERNEL, 0);
+		if (!sink)
+			goto discard;
+
+		trace_netfs_folio(folio, netfs_folio_trace_read_gaps);
+
+		rreq->direct_bv = bvec;
+		rreq->direct_bv_count = nr_bvec;
+		if (from > 0) {
+			bvec_set_folio(&bvec[i++], folio, from, 0);
+			off = from;
+		}
+		while (off < to) {
+			part = min_t(size_t, to - off, PAGE_SIZE);
+			bvec_set_folio(&bvec[i++], sink, part, 0);
+			off += part;
+		}
+		if (to < flen)
+			bvec_set_folio(&bvec[i++], folio, flen - to, to);
+		iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len);
+	} else {
+		iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+				rreq->start, rreq->len);
+	}
 
 	ret = netfs_begin_read(rreq, true);
+	if (sink)
+		folio_put(sink);
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
-	return ret;
+	return ret < 0 ? ret : 0;
 
 discard:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 8308b81f36bed..082a5e717b58f 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -118,9 +118,11 @@
 	EM(netfs_folio_trace_clear_g,		"clear-g")	\
 	EM(netfs_folio_trace_copy_to_cache,	"copy")		\
 	EM(netfs_folio_trace_end_copy,		"end-copy")	\
+	EM(netfs_folio_trace_filled_gaps,	"filled-gaps")	\
 	EM(netfs_folio_trace_kill,		"kill")		\
 	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
 	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
+	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
 	EM(netfs_folio_trace_redirty,		"redirty")	\
 	EM(netfs_folio_trace_redirtied,		"redirtied")	\
 	EM(netfs_folio_trace_store,		"store")	\
-- 
GitLab


From e2e2e83924b1fe4c28bf5617db90e893755e9cbd Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 29 Sep 2023 20:11:31 +0100
Subject: [PATCH 1966/4076] netfs: Allocate multipage folios in the writepath

Allocate a multipage folio when copying data into the pagecache if possible
if there's sufficient data to warrant it.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 6e7f06d9962db..b76688e98f819 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -84,14 +84,19 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 }
 
 /*
- * Grab a folio for writing and lock it.
+ * Grab a folio for writing and lock it.  Attempt to allocate as large a folio
+ * as possible to hold as much of the remaining length as possible in one go.
  */
 static struct folio *netfs_grab_folio_for_write(struct address_space *mapping,
 						loff_t pos, size_t part)
 {
 	pgoff_t index = pos / PAGE_SIZE;
+	fgf_t fgp_flags = FGP_WRITEBEGIN;
 
-	return __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+	if (mapping_large_folio_support(mapping))
+		fgp_flags |= fgf_set_order(pos % PAGE_SIZE + part);
+
+	return __filemap_get_folio(mapping, index, fgp_flags,
 				   mapping_gfp_mask(mapping));
 }
 
-- 
GitLab


From 016dc8516aec8719641e7aaaacd78d344759178e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 14 Jan 2022 17:39:55 +0000
Subject: [PATCH 1967/4076] netfs: Implement unbuffered/DIO read support

Implement support for unbuffered and DIO reads in the netfs library,
utilising the existing read helper code to do block splitting and
individual queuing.  The code also handles extraction of the destination
buffer from the supplied iterator, allowing async unbuffered reads to take
place.

The read will be split up according to the rsize setting and, if supplied,
the ->clamp_length() method.  Note that the next subrequest will be issued
as soon as issue_op returns, without waiting for previous ones to finish.
The network filesystem needs to pause or handle queuing them if it doesn't
want to fire them all at the server simultaneously.

Once all the subrequests have finished, the state will be assessed and the
amount of data to be indicated as having being obtained will be
determined.  As the subrequests may finish in any order, if an intermediate
subrequest is short, any further subrequests may be copied into the buffer
and then abandoned.

In the future, this will also take care of doing an unbuffered read from
encrypted content, with the decryption being done by the library.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile            |   1 +
 fs/netfs/direct_read.c       | 125 +++++++++++++++++++++++++++++++++++
 fs/netfs/internal.h          |   1 +
 fs/netfs/io.c                |  83 ++++++++++++++++++++---
 fs/netfs/main.c              |   1 +
 fs/netfs/objects.c           |   5 +-
 fs/netfs/stats.c             |   4 +-
 include/linux/netfs.h        |   9 +++
 include/trace/events/netfs.h |   7 +-
 mm/filemap.c                 |   1 +
 10 files changed, 226 insertions(+), 11 deletions(-)
 create mode 100644 fs/netfs/direct_read.c

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index 85d8333a1ed46..e968ab1eca400 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -3,6 +3,7 @@
 netfs-y := \
 	buffered_read.o \
 	buffered_write.o \
+	direct_read.o \
 	io.o \
 	iterator.o \
 	locking.o \
diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c
new file mode 100644
index 0000000000000..ad4370b3935d6
--- /dev/null
+++ b/fs/netfs/direct_read.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Direct I/O support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <linux/sched/mm.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/**
+ * netfs_unbuffered_read_iter_locked - Perform an unbuffered or direct I/O read
+ * @iocb: The I/O control descriptor describing the read
+ * @iter: The output buffer (also specifies read length)
+ *
+ * Perform an unbuffered I/O or direct I/O from the file in @iocb to the
+ * output buffer.  No use is made of the pagecache.
+ *
+ * The caller must hold any appropriate locks.
+ */
+static ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct netfs_io_request *rreq;
+	ssize_t ret;
+	size_t orig_count = iov_iter_count(iter);
+	bool async = !is_sync_kiocb(iocb);
+
+	_enter("");
+
+	if (!orig_count)
+		return 0; /* Don't update atime */
+
+	ret = kiocb_write_and_wait(iocb, orig_count);
+	if (ret < 0)
+		return ret;
+	file_accessed(iocb->ki_filp);
+
+	rreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp,
+				   iocb->ki_pos, orig_count,
+				   NETFS_DIO_READ);
+	if (IS_ERR(rreq))
+		return PTR_ERR(rreq);
+
+	netfs_stat(&netfs_n_rh_dio_read);
+	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_dio_read);
+
+	/* If this is an async op, we have to keep track of the destination
+	 * buffer for ourselves as the caller's iterator will be trashed when
+	 * we return.
+	 *
+	 * In such a case, extract an iterator to represent as much of the the
+	 * output buffer as we can manage.  Note that the extraction might not
+	 * be able to allocate a sufficiently large bvec array and may shorten
+	 * the request.
+	 */
+	if (user_backed_iter(iter)) {
+		ret = netfs_extract_user_iter(iter, rreq->len, &rreq->iter, 0);
+		if (ret < 0)
+			goto out;
+		rreq->direct_bv = (struct bio_vec *)rreq->iter.bvec;
+		rreq->direct_bv_count = ret;
+		rreq->direct_bv_unpin = iov_iter_extract_will_pin(iter);
+		rreq->len = iov_iter_count(&rreq->iter);
+	} else {
+		rreq->iter = *iter;
+		rreq->len = orig_count;
+		rreq->direct_bv_unpin = false;
+		iov_iter_advance(iter, orig_count);
+	}
+
+	// TODO: Set up bounce buffer if needed
+
+	if (async)
+		rreq->iocb = iocb;
+
+	ret = netfs_begin_read(rreq, is_sync_kiocb(iocb));
+	if (ret < 0)
+		goto out; /* May be -EIOCBQUEUED */
+	if (!async) {
+		// TODO: Copy from bounce buffer
+		iocb->ki_pos += rreq->transferred;
+		ret = rreq->transferred;
+	}
+
+out:
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	if (ret > 0)
+		orig_count -= ret;
+	if (ret != -EIOCBQUEUED)
+		iov_iter_revert(iter, orig_count - iov_iter_count(iter));
+	return ret;
+}
+
+/**
+ * netfs_unbuffered_read_iter - Perform an unbuffered or direct I/O read
+ * @iocb: The I/O control descriptor describing the read
+ * @iter: The output buffer (also specifies read length)
+ *
+ * Perform an unbuffered I/O or direct I/O from the file in @iocb to the
+ * output buffer.  No use is made of the pagecache.
+ */
+ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	if (!iter->count)
+		return 0; /* Don't update atime */
+
+	ret = netfs_start_io_direct(inode);
+	if (ret == 0) {
+		ret = netfs_unbuffered_read_iter_locked(iocb, iter);
+		netfs_end_io_direct(inode);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(netfs_unbuffered_read_iter);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 17e4ea4456c75..886c2e8f841fb 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -100,6 +100,7 @@ int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
  * stats.c
  */
 #ifdef CONFIG_NETFS_STATS
+extern atomic_t netfs_n_rh_dio_read;
 extern atomic_t netfs_n_rh_readahead;
 extern atomic_t netfs_n_rh_readpage;
 extern atomic_t netfs_n_rh_rreq;
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 774aef6ea4cbc..c972415c8aad3 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -78,7 +78,9 @@ static void netfs_read_from_server(struct netfs_io_request *rreq,
 				   struct netfs_io_subrequest *subreq)
 {
 	netfs_stat(&netfs_n_rh_download);
-	if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+
+	if (rreq->origin != NETFS_DIO_READ &&
+	    iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
 		pr_warn("R=%08x[%u] ITER PRE-MISMATCH %zx != %zx-%zx %lx\n",
 			rreq->debug_id, subreq->debug_index,
 			iov_iter_count(&subreq->io_iter), subreq->len,
@@ -341,6 +343,43 @@ static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq)
 	}
 }
 
+/*
+ * Determine how much we can admit to having read from a DIO read.
+ */
+static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
+{
+	struct netfs_io_subrequest *subreq;
+	unsigned int i;
+	size_t transferred = 0;
+
+	for (i = 0; i < rreq->direct_bv_count; i++)
+		flush_dcache_page(rreq->direct_bv[i].bv_page);
+
+	list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+		if (subreq->error || subreq->transferred == 0)
+			break;
+		transferred += subreq->transferred;
+		if (subreq->transferred < subreq->len)
+			break;
+	}
+
+	for (i = 0; i < rreq->direct_bv_count; i++)
+		flush_dcache_page(rreq->direct_bv[i].bv_page);
+
+	rreq->transferred = transferred;
+	task_io_account_read(transferred);
+
+	if (rreq->iocb) {
+		rreq->iocb->ki_pos += transferred;
+		if (rreq->iocb->ki_complete)
+			rreq->iocb->ki_complete(
+				rreq->iocb, rreq->error ? rreq->error : transferred);
+	}
+	if (rreq->netfs_ops->done)
+		rreq->netfs_ops->done(rreq);
+	inode_dio_end(rreq->inode);
+}
+
 /*
  * Assess the state of a read request and decide what to do next.
  *
@@ -361,7 +400,10 @@ again:
 		return;
 	}
 
-	netfs_rreq_unlock_folios(rreq);
+	if (rreq->origin != NETFS_DIO_READ)
+		netfs_rreq_unlock_folios(rreq);
+	else
+		netfs_rreq_assess_dio(rreq);
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
@@ -526,14 +568,16 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			struct netfs_io_subrequest *subreq,
 			struct iov_iter *io_iter)
 {
-	enum netfs_io_source source;
+	enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER;
 	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
 
-	source = netfs_cache_prepare_read(subreq, rreq->i_size);
-	if (source == NETFS_INVALID_READ)
-		goto out;
+	if (rreq->origin != NETFS_DIO_READ) {
+		source = netfs_cache_prepare_read(subreq, rreq->i_size);
+		if (source == NETFS_INVALID_READ)
+			goto out;
+	}
 
 	if (source == NETFS_DOWNLOAD_FROM_SERVER) {
 		/* Call out to the netfs to let it shrink the request to fit
@@ -544,6 +588,8 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		 */
 		if (subreq->len > rreq->i_size - subreq->start)
 			subreq->len = rreq->i_size - subreq->start;
+		if (rreq->rsize && subreq->len > rreq->rsize)
+			subreq->len = rreq->rsize;
 
 		if (rreq->netfs_ops->clamp_length &&
 		    !rreq->netfs_ops->clamp_length(subreq)) {
@@ -662,6 +708,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 		return -EIO;
 	}
 
+	if (rreq->origin == NETFS_DIO_READ)
+		inode_dio_begin(rreq->inode);
+
+	// TODO: Use bounce buffer if requested
 	rreq->io_iter = rreq->iter;
 
 	INIT_WORK(&rreq->work, netfs_rreq_work);
@@ -673,11 +723,25 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	atomic_set(&rreq->nr_outstanding, 1);
 	io_iter = rreq->io_iter;
 	do {
+		_debug("submit %llx + %zx >= %llx",
+		       rreq->start, rreq->submitted, rreq->i_size);
+		if (rreq->origin == NETFS_DIO_READ &&
+		    rreq->start + rreq->submitted >= rreq->i_size)
+			break;
 		if (!netfs_rreq_submit_slice(rreq, &io_iter, &debug_index))
 			break;
+		if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
+		    test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags))
+			break;
 
 	} while (rreq->submitted < rreq->len);
 
+	if (!rreq->submitted) {
+		netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit);
+		ret = 0;
+		goto out;
+	}
+
 	if (sync) {
 		/* Keep nr_outstanding incremented so that the ref always
 		 * belongs to us, and the service code isn't punted off to a
@@ -694,7 +758,8 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 			    TASK_UNINTERRUPTIBLE);
 
 		ret = rreq->error;
-		if (ret == 0 && rreq->submitted < rreq->len) {
+		if (ret == 0 && rreq->submitted < rreq->len &&
+		    rreq->origin != NETFS_DIO_READ) {
 			trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
 			ret = -EIO;
 		}
@@ -702,7 +767,9 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 		/* If we decrement nr_outstanding to 0, the ref belongs to us. */
 		if (atomic_dec_and_test(&rreq->nr_outstanding))
 			netfs_rreq_assess(rreq, false);
-		ret = 0;
+		ret = -EIOCBQUEUED;
 	}
+
+out:
 	return ret;
 }
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index ab6cac1106762..abb8857486ee1 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -30,6 +30,7 @@ static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READPAGE]	= "RP",
 	[NETFS_READ_FOR_WRITE]	= "RW",
 	[NETFS_WRITEBACK]	= "WB",
+	[NETFS_DIO_READ]	= "DR",
 };
 
 /*
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 3aa0bfbc04ec3..7153f24e80341 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -20,7 +20,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct inode *inode = file ? file_inode(file) : mapping->host;
 	struct netfs_inode *ctx = netfs_inode(inode);
 	struct netfs_io_request *rreq;
-	bool cached = netfs_is_cache_enabled(ctx);
+	bool is_dio = (origin == NETFS_DIO_READ);
+	bool cached = is_dio && netfs_is_cache_enabled(ctx);
 	int ret;
 
 	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
@@ -42,6 +43,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
 	if (cached)
 		__set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
+	if (file && file->f_flags & O_NONBLOCK)
+		__set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags);
 	if (rreq->netfs_ops->init_request) {
 		ret = rreq->netfs_ops->init_request(rreq, file);
 		if (ret < 0) {
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index c1f85cd595a47..15fd5c3f0f392 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -9,6 +9,7 @@
 #include <linux/seq_file.h>
 #include "internal.h"
 
+atomic_t netfs_n_rh_dio_read;
 atomic_t netfs_n_rh_readahead;
 atomic_t netfs_n_rh_readpage;
 atomic_t netfs_n_rh_rreq;
@@ -36,7 +37,8 @@ atomic_t netfs_n_wh_write_failed;
 
 int netfs_stats_show(struct seq_file *m, void *v)
 {
-	seq_printf(m, "Netfs  : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+	seq_printf(m, "Netfs  : DR=%u RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+		   atomic_read(&netfs_n_rh_dio_read),
 		   atomic_read(&netfs_n_rh_readahead),
 		   atomic_read(&netfs_n_rh_readpage),
 		   atomic_read(&netfs_n_rh_write_begin),
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 70f578cf3715f..7c13095684598 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -226,6 +226,7 @@ enum netfs_io_origin {
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
 	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_DIO_READ,			/* This is a direct I/O read */
 	nr__netfs_io_origin
 } __mode(byte);
 
@@ -240,6 +241,7 @@ struct netfs_io_request {
 	};
 	struct inode		*inode;		/* The file being accessed */
 	struct address_space	*mapping;	/* The mapping being accessed */
+	struct kiocb		*iocb;		/* AIO completion vector */
 	struct netfs_cache_resources cache_resources;
 	struct list_head	proc_link;	/* Link in netfs_iorequests */
 	struct list_head	subrequests;	/* Contributory I/O operations */
@@ -249,12 +251,14 @@ struct netfs_io_request {
 	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
 	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
+	unsigned int		rsize;		/* Maximum read size (0 for none) */
 	unsigned int		wsize;		/* Maximum write size (0 for none) */
 	unsigned int		subreq_counter;	/* Next subreq->debug_index */
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
 	size_t			submitted;	/* Amount submitted for I/O so far */
 	size_t			len;		/* Length of the request */
+	size_t			transferred;	/* Amount to be indicated as transferred */
 	short			error;		/* 0 or error that occurred */
 	enum netfs_io_origin	origin;		/* Origin of the request */
 	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
@@ -271,6 +275,8 @@ struct netfs_io_request {
 #define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
 #define NETFS_RREQ_WRITE_TO_CACHE	7	/* Need to write to the cache */
 #define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
+#define NETFS_RREQ_NONBLOCK		9	/* Don't block if possible (O_NONBLOCK) */
+#define NETFS_RREQ_BLOCKED		10	/* We blocked */
 	const struct netfs_request_ops *netfs_ops;
 	void (*cleanup)(struct netfs_io_request *req);
 };
@@ -367,6 +373,9 @@ struct netfs_cache_ops {
 			       loff_t *_data_start, size_t *_data_len);
 };
 
+/* High-level read API. */
+ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+
 /* High-level write API */
 ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			    struct netfs_group *netfs_group);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 082a5e717b58f..5a4edadf0e59d 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -16,6 +16,7 @@
  * Define enums for tracing information.
  */
 #define netfs_read_traces					\
+	EM(netfs_read_trace_dio_read,		"DIO-READ ")	\
 	EM(netfs_read_trace_expanded,		"EXPANDED ")	\
 	EM(netfs_read_trace_readahead,		"READAHEAD")	\
 	EM(netfs_read_trace_readpage,		"READPAGE ")	\
@@ -31,7 +32,8 @@
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
 	EM(NETFS_READ_FOR_WRITE,		"RW")		\
-	E_(NETFS_WRITEBACK,			"WB")
+	EM(NETFS_WRITEBACK,			"WB")		\
+	E_(NETFS_DIO_READ,			"DR")
 
 #define netfs_rreq_traces					\
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
@@ -70,6 +72,8 @@
 #define netfs_failures							\
 	EM(netfs_fail_check_write_begin,	"check-write-begin")	\
 	EM(netfs_fail_copy_to_cache,		"copy-to-cache")	\
+	EM(netfs_fail_dio_read_short,		"dio-read-short")	\
+	EM(netfs_fail_dio_read_zero,		"dio-read-zero")	\
 	EM(netfs_fail_read,			"read")			\
 	EM(netfs_fail_short_read,		"short-read")		\
 	EM(netfs_fail_prepare_write,		"prep-write")		\
@@ -81,6 +85,7 @@
 	EM(netfs_rreq_trace_put_complete,	"PUT COMPLT ")	\
 	EM(netfs_rreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_rreq_trace_put_failed,		"PUT FAILED ")	\
+	EM(netfs_rreq_trace_put_no_submit,	"PUT NO-SUBM")	\
 	EM(netfs_rreq_trace_put_return,		"PUT RETURN ")	\
 	EM(netfs_rreq_trace_put_subreq,		"PUT SUBREQ ")	\
 	EM(netfs_rreq_trace_put_work,		"PUT WORK   ")	\
diff --git a/mm/filemap.c b/mm/filemap.c
index f1c8c278310fd..1c5271ed0cc08 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2678,6 +2678,7 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
 
 	return filemap_write_and_wait_range(mapping, pos, end);
 }
+EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
 
 int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 {
-- 
GitLab


From 153a9961b551101cd38e94e26cd92fbfd198b19b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 21 Feb 2022 11:38:17 +0000
Subject: [PATCH 1968/4076] netfs: Implement unbuffered/DIO write support

Implement support for unbuffered writes and direct I/O writes.  If the
write is misaligned with respect to the fscrypt block size, then RMW cycles
are performed if necessary.  DIO writes are a special case of unbuffered
writes with extra restriction imposed, such as block size alignment
requirements.

Also provide a field that can tell the code to add some extra space onto
the bounce buffer for use by the filesystem in the case of a
content-encrypted file.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/afs/inode.c               |   2 +-
 fs/netfs/Makefile            |   1 +
 fs/netfs/direct_write.c      | 166 +++++++++++++++++++++++++++++++++++
 fs/netfs/internal.h          |   6 ++
 fs/netfs/io.c                |   2 +-
 fs/netfs/main.c              |  12 +--
 fs/netfs/objects.c           |   6 +-
 fs/netfs/output.c            |  30 +++++++
 include/linux/netfs.h        |   4 +
 include/trace/events/netfs.h |   4 +-
 mm/filemap.c                 |   1 +
 11 files changed, 224 insertions(+), 10 deletions(-)
 create mode 100644 fs/netfs/direct_write.c

diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 6f375f0cf650d..37485ae314714 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -250,7 +250,7 @@ static void afs_apply_status(struct afs_operation *op,
 		 * what's on the server.
 		 */
 		vnode->netfs.remote_i_size = status->size;
-		if (change_size) {
+		if (change_size || status->size > i_size_read(inode)) {
 			afs_set_i_size(vnode, status->size);
 			inode_set_ctime_to_ts(inode, t);
 			inode_set_atime_to_ts(inode, t);
diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index e968ab1eca400..d4d1d799819ec 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -4,6 +4,7 @@ netfs-y := \
 	buffered_read.o \
 	buffered_write.o \
 	direct_read.o \
+	direct_write.o \
 	io.o \
 	iterator.o \
 	locking.o \
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
new file mode 100644
index 0000000000000..bb0c2718f57bd
--- /dev/null
+++ b/fs/netfs/direct_write.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Unbuffered and direct write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/uio.h>
+#include "internal.h"
+
+static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
+{
+	struct inode *inode = wreq->inode;
+	unsigned long long end = wreq->start + wreq->len;
+
+	if (!wreq->error &&
+	    i_size_read(inode) < end) {
+		if (wreq->netfs_ops->update_i_size)
+			wreq->netfs_ops->update_i_size(inode, end);
+		else
+			i_size_write(inode, end);
+	}
+}
+
+/*
+ * Perform an unbuffered write where we may have to do an RMW operation on an
+ * encrypted file.  This can also be used for direct I/O writes.
+ */
+ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
+					   struct netfs_group *netfs_group)
+{
+	struct netfs_io_request *wreq;
+	unsigned long long start = iocb->ki_pos;
+	unsigned long long end = start + iov_iter_count(iter);
+	ssize_t ret, n;
+	bool async = !is_sync_kiocb(iocb);
+
+	_enter("");
+
+	/* We're going to need a bounce buffer if what we transmit is going to
+	 * be different in some way to the source buffer, e.g. because it gets
+	 * encrypted/compressed or because it needs expanding to a block size.
+	 */
+	// TODO
+
+	_debug("uw %llx-%llx", start, end);
+
+	wreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp,
+				   start, end - start,
+				   iocb->ki_flags & IOCB_DIRECT ?
+				   NETFS_DIO_WRITE : NETFS_UNBUFFERED_WRITE);
+	if (IS_ERR(wreq))
+		return PTR_ERR(wreq);
+
+	{
+		/* If this is an async op and we're not using a bounce buffer,
+		 * we have to save the source buffer as the iterator is only
+		 * good until we return.  In such a case, extract an iterator
+		 * to represent as much of the the output buffer as we can
+		 * manage.  Note that the extraction might not be able to
+		 * allocate a sufficiently large bvec array and may shorten the
+		 * request.
+		 */
+		if (async || user_backed_iter(iter)) {
+			n = netfs_extract_user_iter(iter, wreq->len, &wreq->iter, 0);
+			if (n < 0) {
+				ret = n;
+				goto out;
+			}
+			wreq->direct_bv = (struct bio_vec *)wreq->iter.bvec;
+			wreq->direct_bv_count = n;
+			wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter);
+			wreq->len = iov_iter_count(&wreq->iter);
+		} else {
+			wreq->iter = *iter;
+		}
+
+		wreq->io_iter = wreq->iter;
+	}
+
+	/* Copy the data into the bounce buffer and encrypt it. */
+	// TODO
+
+	/* Dispatch the write. */
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	if (async)
+		wreq->iocb = iocb;
+	wreq->cleanup = netfs_cleanup_dio_write;
+	ret = netfs_begin_write(wreq, is_sync_kiocb(iocb),
+				iocb->ki_flags & IOCB_DIRECT ?
+				netfs_write_trace_dio_write :
+				netfs_write_trace_unbuffered_write);
+	if (ret < 0) {
+		_debug("begin = %zd", ret);
+		goto out;
+	}
+
+	if (!async) {
+		trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip);
+		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
+
+		ret = wreq->error;
+		_debug("waited = %zd", ret);
+		if (ret == 0) {
+			ret = wreq->transferred;
+			iocb->ki_pos += ret;
+		}
+	} else {
+		ret = -EIOCBQUEUED;
+	}
+
+out:
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	return ret;
+}
+
+/**
+ * netfs_unbuffered_write_iter - Unbuffered write to a file
+ * @iocb: IO state structure
+ * @from: iov_iter with data to write
+ *
+ * Do an unbuffered write to a file, writing the data directly to the server
+ * and not lodging the data in the pagecache.
+ *
+ * Return:
+ * * Negative error code if no data has been written at all of
+ *   vfs_fsync_range() failed for a synchronous write
+ * * Number of bytes written, even for truncated writes
+ */
+ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	ssize_t ret;
+
+	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+
+	trace_netfs_write_iter(iocb, from);
+
+	ret = netfs_start_io_direct(inode);
+	if (ret < 0)
+		return ret;
+	ret = generic_write_checks(iocb, from);
+	if (ret < 0)
+		goto out;
+	ret = file_remove_privs(file);
+	if (ret < 0)
+		goto out;
+	ret = file_update_time(file);
+	if (ret < 0)
+		goto out;
+	ret = kiocb_invalidate_pages(iocb, iov_iter_count(from));
+	if (ret < 0)
+		goto out;
+
+	fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode),
+			   FSCACHE_INVAL_DIO_WRITE);
+	ret = netfs_unbuffered_write_iter_locked(iocb, from, NULL);
+out:
+	netfs_end_io_direct(inode);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_unbuffered_write_iter);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 886c2e8f841fb..2de4f826dbe4f 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -26,6 +26,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq);
 int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len);
 
+/*
+ * direct_write.c
+ */
+ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
+					   struct netfs_group *netfs_group);
+
 /*
  * io.c
  */
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index c972415c8aad3..01c7ff27228e4 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -645,7 +645,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
 
 	subreq->debug_index	= (*_debug_index)++;
 	subreq->start		= rreq->start + rreq->submitted;
-	subreq->len		= rreq->len   - rreq->submitted;
+	subreq->len		= io_iter->count;
 
 	_debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted);
 	list_add_tail(&subreq->rreq_link, &rreq->subrequests);
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index abb8857486ee1..8e4db9ff40c40 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -26,11 +26,13 @@ LIST_HEAD(netfs_io_requests);
 DEFINE_SPINLOCK(netfs_proc_lock);
 
 static const char *netfs_origins[nr__netfs_io_origin] = {
-	[NETFS_READAHEAD]	= "RA",
-	[NETFS_READPAGE]	= "RP",
-	[NETFS_READ_FOR_WRITE]	= "RW",
-	[NETFS_WRITEBACK]	= "WB",
-	[NETFS_DIO_READ]	= "DR",
+	[NETFS_READAHEAD]		= "RA",
+	[NETFS_READPAGE]		= "RP",
+	[NETFS_READ_FOR_WRITE]		= "RW",
+	[NETFS_WRITEBACK]		= "WB",
+	[NETFS_UNBUFFERED_WRITE]	= "UW",
+	[NETFS_DIO_READ]		= "DR",
+	[NETFS_DIO_WRITE]		= "DW",
 };
 
 /*
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 7153f24e80341..93f1d74311993 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -20,8 +20,10 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct inode *inode = file ? file_inode(file) : mapping->host;
 	struct netfs_inode *ctx = netfs_inode(inode);
 	struct netfs_io_request *rreq;
-	bool is_dio = (origin == NETFS_DIO_READ);
-	bool cached = is_dio && netfs_is_cache_enabled(ctx);
+	bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE ||
+			      origin == NETFS_DIO_READ ||
+			      origin == NETFS_DIO_WRITE);
+	bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx);
 	int ret;
 
 	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
index 2ad0fd8c32be2..560cbcea0c0ae 100644
--- a/fs/netfs/output.c
+++ b/fs/netfs/output.c
@@ -74,11 +74,21 @@ static void netfs_write_terminated(struct netfs_io_request *wreq, bool was_async
 {
 	struct netfs_io_subrequest *subreq;
 	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+	size_t transferred = 0;
 
 	_enter("R=%x[]", wreq->debug_id);
 
 	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
 
+	list_for_each_entry(subreq, &wreq->subrequests, rreq_link) {
+		if (subreq->error || subreq->transferred == 0)
+			break;
+		transferred += subreq->transferred;
+		if (subreq->transferred < subreq->len)
+			break;
+	}
+	wreq->transferred = transferred;
+
 	list_for_each_entry(subreq, &wreq->subrequests, rreq_link) {
 		if (!subreq->error)
 			continue;
@@ -110,11 +120,28 @@ static void netfs_write_terminated(struct netfs_io_request *wreq, bool was_async
 
 	wreq->cleanup(wreq);
 
+	if (wreq->origin == NETFS_DIO_WRITE &&
+	    wreq->mapping->nrpages) {
+		pgoff_t first = wreq->start >> PAGE_SHIFT;
+		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
+		invalidate_inode_pages2_range(wreq->mapping, first, last);
+	}
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_end(wreq->inode);
+
 	_debug("finished");
 	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
 	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
 
+	if (wreq->iocb) {
+		wreq->iocb->ki_pos += transferred;
+		if (wreq->iocb->ki_complete)
+			wreq->iocb->ki_complete(
+				wreq->iocb, wreq->error ? wreq->error : transferred);
+	}
+
 	netfs_clear_subrequests(wreq, was_async);
 	netfs_put_request(wreq, was_async, netfs_rreq_trace_put_complete);
 }
@@ -329,6 +356,9 @@ int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
 		return -EIO;
 	}
 
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_begin(wreq->inode);
+
 	wreq->io_iter = wreq->iter;
 
 	/* ->outstanding > 0 carries a ref */
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 7c13095684598..e1dfd6775c2c3 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -138,6 +138,7 @@ struct netfs_inode {
 	loff_t			remote_i_size;	/* Size of the remote file */
 	unsigned long		flags;
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
+#define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
 };
 
 /*
@@ -226,7 +227,9 @@ enum netfs_io_origin {
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
 	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_UNBUFFERED_WRITE,		/* This is an unbuffered write */
 	NETFS_DIO_READ,			/* This is a direct I/O read */
+	NETFS_DIO_WRITE,		/* This is a direct I/O write */
 	nr__netfs_io_origin
 } __mode(byte);
 
@@ -379,6 +382,7 @@ ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 /* High-level write API */
 ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			    struct netfs_group *netfs_group);
+ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from);
 
 /* Address operations API */
 struct readahead_control;
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 5a4edadf0e59d..914a24b03d08b 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -33,7 +33,9 @@
 	EM(NETFS_READPAGE,			"RP")		\
 	EM(NETFS_READ_FOR_WRITE,		"RW")		\
 	EM(NETFS_WRITEBACK,			"WB")		\
-	E_(NETFS_DIO_READ,			"DR")
+	EM(NETFS_UNBUFFERED_WRITE,		"UW")		\
+	EM(NETFS_DIO_READ,			"DR")		\
+	E_(NETFS_DIO_WRITE,			"DW")
 
 #define netfs_rreq_traces					\
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
diff --git a/mm/filemap.c b/mm/filemap.c
index 1c5271ed0cc08..73626eb323f35 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2706,6 +2706,7 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 	return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
 					     end >> PAGE_SHIFT);
 }
+EXPORT_SYMBOL_GPL(kiocb_invalidate_pages);
 
 /**
  * generic_file_read_iter - generic filesystem read routine
-- 
GitLab


From 938e13a73b244278a3777f38fa915bd239b2efd2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 17 Jun 2021 13:09:21 +0100
Subject: [PATCH 1969/4076] netfs: Implement buffered write API

Institute a netfs write helper, netfs_file_write_iter(), to be pointed at
by the network filesystem ->write_iter() call.  Make it handled buffered
writes by calling the previously defined netfs_perform_write() to copy the
source data into the pagecache.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 83 +++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h     |  3 ++
 2 files changed, 86 insertions(+)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index b76688e98f819..f244123ab568c 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -333,3 +333,86 @@ error_folio_unlock:
 	goto out;
 }
 EXPORT_SYMBOL(netfs_perform_write);
+
+/**
+ * netfs_buffered_write_iter_locked - write data to a file
+ * @iocb:	IO state structure (file, offset, etc.)
+ * @from:	iov_iter with data to write
+ * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ *
+ * This function does all the work needed for actually writing data to a
+ * file. It does all basic checks, removes SUID from the file, updates
+ * modification times and calls proper subroutines depending on whether we
+ * do direct IO or a standard buffered write.
+ *
+ * The caller must hold appropriate locks around this function and have called
+ * generic_write_checks() already.  The caller is also responsible for doing
+ * any necessary syncing afterwards.
+ *
+ * This function does *not* take care of syncing data in case of O_SYNC write.
+ * A caller has to handle it. This is mainly due to the fact that we want to
+ * avoid syncing under i_rwsem.
+ *
+ * Return:
+ * * number of bytes written, even for truncated writes
+ * * negative error code if no data has been written at all
+ */
+ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from,
+					 struct netfs_group *netfs_group)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t ret;
+
+	trace_netfs_write_iter(iocb, from);
+
+	ret = file_remove_privs(file);
+	if (ret)
+		return ret;
+
+	ret = file_update_time(file);
+	if (ret)
+		return ret;
+
+	return netfs_perform_write(iocb, from, netfs_group);
+}
+EXPORT_SYMBOL(netfs_buffered_write_iter_locked);
+
+/**
+ * netfs_file_write_iter - write data to a file
+ * @iocb: IO state structure
+ * @from: iov_iter with data to write
+ *
+ * Perform a write to a file, writing into the pagecache if possible and doing
+ * an unbuffered write instead if not.
+ *
+ * Return:
+ * * Negative error code if no data has been written at all of
+ *   vfs_fsync_range() failed for a synchronous write
+ * * Number of bytes written, even for truncated writes
+ */
+ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	ssize_t ret;
+
+	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+
+	if ((iocb->ki_flags & IOCB_DIRECT) ||
+	    test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags))
+		return netfs_unbuffered_write_iter(iocb, from);
+
+	ret = netfs_start_io_write(inode);
+	if (ret < 0)
+		return ret;
+
+	ret = generic_write_checks(iocb, from);
+	if (ret > 0)
+		ret = netfs_buffered_write_iter_locked(iocb, from, NULL);
+	netfs_end_io_write(inode);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_file_write_iter);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index e1dfd6775c2c3..0948ecf69aa5d 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -382,7 +382,10 @@ ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 /* High-level write API */
 ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			    struct netfs_group *netfs_group);
+ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from,
+					 struct netfs_group *netfs_group);
 ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from);
+ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from);
 
 /* Address operations API */
 struct readahead_control;
-- 
GitLab


From 102a7e2c598c22bd2621fa97eb1c93c89d469a12 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 15 Feb 2022 23:15:57 +0000
Subject: [PATCH 1970/4076] netfs: Allow buffered shared-writeable mmap through
 netfs_page_mkwrite()

Provide an entry point to delegate a filesystem's ->page_mkwrite() to.
This checks for conflicting writes, then attached any netfs-specific group
marking (e.g. ceph snap) to the page to be considered dirty.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 59 +++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h     |  4 +++
 2 files changed, 63 insertions(+)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index f244123ab568c..70cb8e98d068a 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -416,3 +416,62 @@ ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	return ret;
 }
 EXPORT_SYMBOL(netfs_file_write_iter);
+
+/*
+ * Notification that a previously read-only page is about to become writable.
+ * Note that the caller indicates a single page of a multipage folio.
+ */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group)
+{
+	struct folio *folio = page_folio(vmf->page);
+	struct file *file = vmf->vma->vm_file;
+	struct inode *inode = file_inode(file);
+	vm_fault_t ret = VM_FAULT_RETRY;
+	int err;
+
+	_enter("%lx", folio->index);
+
+	sb_start_pagefault(inode->i_sb);
+
+	if (folio_wait_writeback_killable(folio))
+		goto out;
+
+	if (folio_lock_killable(folio) < 0)
+		goto out;
+
+	/* Can we see a streaming write here? */
+	if (WARN_ON(!folio_test_uptodate(folio))) {
+		ret = VM_FAULT_SIGBUS | VM_FAULT_LOCKED;
+		goto out;
+	}
+
+	if (netfs_folio_group(folio) != netfs_group) {
+		folio_unlock(folio);
+		err = filemap_fdatawait_range(inode->i_mapping,
+					      folio_pos(folio),
+					      folio_pos(folio) + folio_size(folio));
+		switch (err) {
+		case 0:
+			ret = VM_FAULT_RETRY;
+			goto out;
+		case -ENOMEM:
+			ret = VM_FAULT_OOM;
+			goto out;
+		default:
+			ret = VM_FAULT_SIGBUS;
+			goto out;
+		}
+	}
+
+	if (folio_test_dirty(folio))
+		trace_netfs_folio(folio, netfs_folio_trace_mkwrite_plus);
+	else
+		trace_netfs_folio(folio, netfs_folio_trace_mkwrite);
+	netfs_set_group(folio, netfs_group);
+	file_update_time(file);
+	ret = VM_FAULT_LOCKED;
+out:
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_page_mkwrite);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 0948ecf69aa5d..d7f324c7c22ae 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -400,6 +400,10 @@ void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
 void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 bool netfs_release_folio(struct folio *folio, gfp_t gfp);
 
+/* VMA operations API. */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group);
+
+/* (Sub)request management API. */
 void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
-- 
GitLab


From 80645bd4aa33a5c325f11b8dc6b38b38410ad5c0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 11 Oct 2023 09:29:43 +0100
Subject: [PATCH 1971/4076] netfs: Provide netfs_file_read_iter()

Provide a top-level-ish function that can be pointed to directly by
->read_iter file op.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_read.c | 73 ++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h    |  2 ++
 2 files changed, 75 insertions(+)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 950f63fc156a8..a59e7b2edaacd 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -558,3 +558,76 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 }
+
+/**
+ * netfs_buffered_read_iter - Filesystem buffered I/O read routine
+ * @iocb: kernel I/O control block
+ * @iter: destination for the data read
+ *
+ * This is the ->read_iter() routine for all filesystems that can use the page
+ * cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall be
+ * returned when no data can be read without waiting for I/O requests to
+ * complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O requests
+ * shall be made for the read or for readahead.  When no data can be read,
+ * -EAGAIN shall be returned.  When readahead would be triggered, a partial,
+ * possibly empty read shall be returned.
+ *
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
+ */
+ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct netfs_inode *ictx = netfs_inode(inode);
+	ssize_t ret;
+
+	if (WARN_ON_ONCE((iocb->ki_flags & IOCB_DIRECT) ||
+			 test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags)))
+		return -EINVAL;
+
+	ret = netfs_start_io_read(inode);
+	if (ret == 0) {
+		ret = filemap_read(iocb, iter, 0);
+		netfs_end_io_read(inode);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(netfs_buffered_read_iter);
+
+/**
+ * netfs_file_read_iter - Generic filesystem read routine
+ * @iocb: kernel I/O control block
+ * @iter: destination for the data read
+ *
+ * This is the ->read_iter() routine for all filesystems that can use the page
+ * cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall be
+ * returned when no data can be read without waiting for I/O requests to
+ * complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O requests
+ * shall be made for the read or for readahead.  When no data can be read,
+ * -EAGAIN shall be returned.  When readahead would be triggered, a partial,
+ * possibly empty read shall be returned.
+ *
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
+ */
+ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct netfs_inode *ictx = netfs_inode(iocb->ki_filp->f_mapping->host);
+
+	if ((iocb->ki_flags & IOCB_DIRECT) ||
+	    test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags))
+		return netfs_unbuffered_read_iter(iocb, iter);
+
+	return netfs_buffered_read_iter(iocb, iter);
+}
+EXPORT_SYMBOL(netfs_file_read_iter);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d7f324c7c22ae..19a41c437af3f 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -378,6 +378,8 @@ struct netfs_cache_ops {
 
 /* High-level read API. */
 ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 
 /* High-level write API */
 ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
-- 
GitLab


From e0ace6ca98bef0d8d354040f13ffc0a498813ee9 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 22 Nov 2023 17:18:17 +0000
Subject: [PATCH 1972/4076] netfs, cachefiles: Pass upper bound length to allow
 expansion

Make netfslib pass the maximum length to the ->prepare_write() op to tell
the cache how much it can expand the length of a write to.  This allows a
write to the server at the end of a file to be limited to a few bytes
whilst writing an entire block to the cache (something required by direct
I/O).

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/cachefiles/internal.h |  2 +-
 fs/cachefiles/io.c       | 10 ++++++----
 fs/cachefiles/ondemand.c |  2 +-
 fs/netfs/fscache_io.c    |  2 +-
 fs/netfs/io.c            |  2 +-
 fs/netfs/objects.c       |  1 +
 fs/netfs/output.c        | 25 ++++++++++---------------
 fs/smb/client/fscache.c  |  2 +-
 include/linux/netfs.h    |  5 +++--
 9 files changed, 25 insertions(+), 26 deletions(-)

diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 2ad58c4652084..1af48d576a34d 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -233,7 +233,7 @@ extern bool cachefiles_begin_operation(struct netfs_cache_resources *cres,
 				       enum fscache_want_state want_state);
 extern int __cachefiles_prepare_write(struct cachefiles_object *object,
 				      struct file *file,
-				      loff_t *_start, size_t *_len,
+				      loff_t *_start, size_t *_len, size_t upper_len,
 				      bool no_space_allocated_yet);
 extern int __cachefiles_write(struct cachefiles_object *object,
 			      struct file *file,
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 009d23cd435b5..bffffedce4a93 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -518,7 +518,7 @@ cachefiles_prepare_ondemand_read(struct netfs_cache_resources *cres,
  */
 int __cachefiles_prepare_write(struct cachefiles_object *object,
 			       struct file *file,
-			       loff_t *_start, size_t *_len,
+			       loff_t *_start, size_t *_len, size_t upper_len,
 			       bool no_space_allocated_yet)
 {
 	struct cachefiles_cache *cache = object->volume->cache;
@@ -530,6 +530,8 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 	down = start - round_down(start, PAGE_SIZE);
 	*_start = start - down;
 	*_len = round_up(down + len, PAGE_SIZE);
+	if (down < start || *_len > upper_len)
+		return -ENOBUFS;
 
 	/* We need to work out whether there's sufficient disk space to perform
 	 * the write - but we can skip that check if we have space already
@@ -592,8 +594,8 @@ check_space:
 }
 
 static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
-				    loff_t *_start, size_t *_len, loff_t i_size,
-				    bool no_space_allocated_yet)
+				    loff_t *_start, size_t *_len, size_t upper_len,
+				    loff_t i_size, bool no_space_allocated_yet)
 {
 	struct cachefiles_object *object = cachefiles_cres_object(cres);
 	struct cachefiles_cache *cache = object->volume->cache;
@@ -609,7 +611,7 @@ static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
 
 	cachefiles_begin_secure(cache, &saved_cred);
 	ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres),
-					 _start, _len,
+					 _start, _len, upper_len,
 					 no_space_allocated_yet);
 	cachefiles_end_secure(cache, saved_cred);
 	return ret;
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 0254ed39f68ce..9301d1eb05045 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -52,7 +52,7 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb,
 		return -ENOBUFS;
 
 	cachefiles_begin_secure(cache, &saved_cred);
-	ret = __cachefiles_prepare_write(object, file, &pos, &len, true);
+	ret = __cachefiles_prepare_write(object, file, &pos, &len, len, true);
 	cachefiles_end_secure(cache, saved_cred);
 	if (ret < 0)
 		return ret;
diff --git a/fs/netfs/fscache_io.c b/fs/netfs/fscache_io.c
index 79171a6879304..ad572f7ee897b 100644
--- a/fs/netfs/fscache_io.c
+++ b/fs/netfs/fscache_io.c
@@ -237,7 +237,7 @@ void __fscache_write_to_cache(struct fscache_cookie *cookie,
 				    fscache_access_io_write) < 0)
 		goto abandon_free;
 
-	ret = cres->ops->prepare_write(cres, &start, &len, i_size, false);
+	ret = cres->ops->prepare_write(cres, &start, &len, len, i_size, false);
 	if (ret < 0)
 		goto abandon_end;
 
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 01c7ff27228e4..14c18be5aca00 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -199,7 +199,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq)
 		}
 
 		ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
-					       rreq->i_size, true);
+					       subreq->len, rreq->i_size, true);
 		if (ret < 0) {
 			trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
 			trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 93f1d74311993..b4e3bd836e5df 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -33,6 +33,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 
 	rreq->start	= start;
 	rreq->len	= len;
+	rreq->upper_len	= len;
 	rreq->origin	= origin;
 	rreq->netfs_ops	= ctx->ops;
 	rreq->mapping	= mapping;
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
index 560cbcea0c0ae..cc9065733b423 100644
--- a/fs/netfs/output.c
+++ b/fs/netfs/output.c
@@ -280,7 +280,7 @@ EXPORT_SYMBOL(netfs_queue_write_request);
  */
 static void netfs_set_up_write_to_cache(struct netfs_io_request *wreq)
 {
-	struct netfs_cache_resources *cres;
+	struct netfs_cache_resources *cres = &wreq->cache_resources;
 	struct netfs_io_subrequest *subreq;
 	struct netfs_inode *ctx = netfs_inode(wreq->inode);
 	struct fscache_cookie *cookie = netfs_i_cookie(ctx);
@@ -294,26 +294,21 @@ static void netfs_set_up_write_to_cache(struct netfs_io_request *wreq)
 	}
 
 	_debug("write to cache");
-	subreq = netfs_create_write_request(wreq, NETFS_WRITE_TO_CACHE, start, len,
-					    netfs_write_to_cache_op_worker);
-	if (!subreq)
+	ret = fscache_begin_write_operation(cres, cookie);
+	if (ret < 0)
 		return;
 
-	cres = &wreq->cache_resources;
-	ret = fscache_begin_read_operation(cres, cookie);
-	if (ret < 0) {
-		netfs_write_subrequest_terminated(subreq, ret, false);
+	ret = cres->ops->prepare_write(cres, &start, &len, wreq->upper_len,
+				       i_size_read(wreq->inode), true);
+	if (ret < 0)
 		return;
-	}
 
-	ret = cres->ops->prepare_write(cres, &start, &len, i_size_read(wreq->inode),
-				       true);
-	if (ret < 0) {
-		netfs_write_subrequest_terminated(subreq, ret, false);
+	subreq = netfs_create_write_request(wreq, NETFS_WRITE_TO_CACHE, start, len,
+					    netfs_write_to_cache_op_worker);
+	if (!subreq)
 		return;
-	}
 
-	netfs_queue_write_request(subreq);
+	netfs_write_to_cache_op(subreq);
 }
 
 /*
diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
index e5cad149f5a2d..c4a3cb736881a 100644
--- a/fs/smb/client/fscache.c
+++ b/fs/smb/client/fscache.c
@@ -180,7 +180,7 @@ static int fscache_fallback_write_pages(struct inode *inode, loff_t start, size_
 	if (ret < 0)
 		return ret;
 
-	ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode),
+	ret = cres.ops->prepare_write(&cres, &start, &len, len, i_size_read(inode),
 				      no_space_allocated_yet);
 	if (ret == 0)
 		ret = fscache_write(&cres, start, &iter, NULL, NULL);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 19a41c437af3f..2856389f4694c 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -261,6 +261,7 @@ struct netfs_io_request {
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
 	size_t			submitted;	/* Amount submitted for I/O so far */
 	size_t			len;		/* Length of the request */
+	size_t			upper_len;	/* Length can be extended to here */
 	size_t			transferred;	/* Amount to be indicated as transferred */
 	short			error;		/* 0 or error that occurred */
 	enum netfs_io_origin	origin;		/* Origin of the request */
@@ -357,8 +358,8 @@ struct netfs_cache_ops {
 	 * actually do.
 	 */
 	int (*prepare_write)(struct netfs_cache_resources *cres,
-			     loff_t *_start, size_t *_len, loff_t i_size,
-			     bool no_space_allocated_yet);
+			     loff_t *_start, size_t *_len, size_t upper_len,
+			     loff_t i_size, bool no_space_allocated_yet);
 
 	/* Prepare an on-demand read operation, shortening it to a cached/uncached
 	 * boundary as appropriate.
-- 
GitLab


From 62c3b7481b9a108cb99ef9438dba66bb4738768b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 28 Sep 2023 11:46:49 +0100
Subject: [PATCH 1973/4076] netfs: Provide a writepages implementation

Provide an implementation of writepages for network filesystems to delegate
to.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 636 ++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h     |   2 +
 2 files changed, 638 insertions(+)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 70cb8e98d068a..c078826f7fe67 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -32,6 +32,18 @@ static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group
 		folio_attach_private(folio, netfs_get_group(netfs_group));
 }
 
+#if IS_ENABLED(CONFIG_FSCACHE)
+static void netfs_folio_start_fscache(bool caching, struct folio *folio)
+{
+	if (caching)
+		folio_start_fscache(folio);
+}
+#else
+static void netfs_folio_start_fscache(bool caching, struct folio *folio)
+{
+}
+#endif
+
 /*
  * Decide how we should modify a folio.  We might be attempting to do
  * write-streaming, in which case we don't want to a local RMW cycle if we can
@@ -475,3 +487,627 @@ out:
 	return ret;
 }
 EXPORT_SYMBOL(netfs_page_mkwrite);
+
+/*
+ * Kill all the pages in the given range
+ */
+static void netfs_kill_pages(struct address_space *mapping,
+			     loff_t start, loff_t len)
+{
+	struct folio *folio;
+	pgoff_t index = start / PAGE_SIZE;
+	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
+
+	_enter("%llx-%llx", start, start + len - 1);
+
+	do {
+		_debug("kill %lx (to %lx)", index, last);
+
+		folio = filemap_get_folio(mapping, index);
+		if (IS_ERR(folio)) {
+			next = index + 1;
+			continue;
+		}
+
+		next = folio_next_index(folio);
+
+		trace_netfs_folio(folio, netfs_folio_trace_kill);
+		folio_clear_uptodate(folio);
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		folio_end_writeback(folio);
+		folio_lock(folio);
+		generic_error_remove_page(mapping, &folio->page);
+		folio_unlock(folio);
+		folio_put(folio);
+
+	} while (index = next, index <= last);
+
+	_leave("");
+}
+
+/*
+ * Redirty all the pages in a given range.
+ */
+static void netfs_redirty_pages(struct address_space *mapping,
+				loff_t start, loff_t len)
+{
+	struct folio *folio;
+	pgoff_t index = start / PAGE_SIZE;
+	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
+
+	_enter("%llx-%llx", start, start + len - 1);
+
+	do {
+		_debug("redirty %llx @%llx", len, start);
+
+		folio = filemap_get_folio(mapping, index);
+		if (IS_ERR(folio)) {
+			next = index + 1;
+			continue;
+		}
+
+		next = folio_next_index(folio);
+		trace_netfs_folio(folio, netfs_folio_trace_redirty);
+		filemap_dirty_folio(mapping, folio);
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		folio_end_writeback(folio);
+		folio_put(folio);
+	} while (index = next, index <= last);
+
+	balance_dirty_pages_ratelimited(mapping);
+
+	_leave("");
+}
+
+/*
+ * Completion of write to server
+ */
+static void netfs_pages_written_back(struct netfs_io_request *wreq)
+{
+	struct address_space *mapping = wreq->mapping;
+	struct netfs_folio *finfo;
+	struct netfs_group *group = NULL;
+	struct folio *folio;
+	pgoff_t last;
+	int gcount = 0;
+
+	XA_STATE(xas, &mapping->i_pages, wreq->start / PAGE_SIZE);
+
+	_enter("%llx-%llx", wreq->start, wreq->start + wreq->len);
+
+	rcu_read_lock();
+
+	last = (wreq->start + wreq->len - 1) / PAGE_SIZE;
+	xas_for_each(&xas, folio, last) {
+		WARN(!folio_test_writeback(folio),
+		     "bad %zx @%llx page %lx %lx\n",
+		     wreq->len, wreq->start, folio_index(folio), last);
+
+		if ((finfo = netfs_folio_info(folio))) {
+			/* Streaming writes cannot be redirtied whilst under
+			 * writeback, so discard the streaming record.
+			 */
+			folio_detach_private(folio);
+			group = finfo->netfs_group;
+			gcount++;
+			trace_netfs_folio(folio, netfs_folio_trace_clear_s);
+			kfree(finfo);
+		} else if ((group = netfs_folio_group(folio))) {
+			/* Need to detach the group pointer if the page didn't
+			 * get redirtied.  If it has been redirtied, then it
+			 * must be within the same group.
+			 */
+			if (folio_test_dirty(folio)) {
+				trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+				goto end_wb;
+			}
+			if (folio_trylock(folio)) {
+				if (!folio_test_dirty(folio)) {
+					folio_detach_private(folio);
+					gcount++;
+					trace_netfs_folio(folio, netfs_folio_trace_clear_g);
+				} else {
+					trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+				}
+				folio_unlock(folio);
+				goto end_wb;
+			}
+
+			xas_pause(&xas);
+			rcu_read_unlock();
+			folio_lock(folio);
+			if (!folio_test_dirty(folio)) {
+				folio_detach_private(folio);
+				gcount++;
+				trace_netfs_folio(folio, netfs_folio_trace_clear_g);
+			} else {
+				trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+			}
+			folio_unlock(folio);
+			rcu_read_lock();
+		} else {
+			trace_netfs_folio(folio, netfs_folio_trace_clear);
+		}
+	end_wb:
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		folio_end_writeback(folio);
+	}
+
+	rcu_read_unlock();
+	netfs_put_group_many(group, gcount);
+	_leave("");
+}
+
+/*
+ * Deal with the disposition of the folios that are under writeback to close
+ * out the operation.
+ */
+static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq)
+{
+	struct address_space *mapping = wreq->mapping;
+
+	_enter("");
+
+	switch (wreq->error) {
+	case 0:
+		netfs_pages_written_back(wreq);
+		break;
+
+	default:
+		pr_notice("R=%08x Unexpected error %d\n", wreq->debug_id, wreq->error);
+		fallthrough;
+	case -EACCES:
+	case -EPERM:
+	case -ENOKEY:
+	case -EKEYEXPIRED:
+	case -EKEYREJECTED:
+	case -EKEYREVOKED:
+	case -ENETRESET:
+	case -EDQUOT:
+	case -ENOSPC:
+		netfs_redirty_pages(mapping, wreq->start, wreq->len);
+		break;
+
+	case -EROFS:
+	case -EIO:
+	case -EREMOTEIO:
+	case -EFBIG:
+	case -ENOENT:
+	case -ENOMEDIUM:
+	case -ENXIO:
+		netfs_kill_pages(mapping, wreq->start, wreq->len);
+		break;
+	}
+
+	if (wreq->error)
+		mapping_set_error(mapping, wreq->error);
+	if (wreq->netfs_ops->done)
+		wreq->netfs_ops->done(wreq);
+}
+
+/*
+ * Extend the region to be written back to include subsequent contiguously
+ * dirty pages if possible, but don't sleep while doing so.
+ *
+ * If this page holds new content, then we can include filler zeros in the
+ * writeback.
+ */
+static void netfs_extend_writeback(struct address_space *mapping,
+				   struct netfs_group *group,
+				   struct xa_state *xas,
+				   long *_count,
+				   loff_t start,
+				   loff_t max_len,
+				   bool caching,
+				   size_t *_len,
+				   size_t *_top)
+{
+	struct netfs_folio *finfo;
+	struct folio_batch fbatch;
+	struct folio *folio;
+	unsigned int i;
+	pgoff_t index = (start + *_len) / PAGE_SIZE;
+	size_t len;
+	void *priv;
+	bool stop = true;
+
+	folio_batch_init(&fbatch);
+
+	do {
+		/* Firstly, we gather up a batch of contiguous dirty pages
+		 * under the RCU read lock - but we can't clear the dirty flags
+		 * there if any of those pages are mapped.
+		 */
+		rcu_read_lock();
+
+		xas_for_each(xas, folio, ULONG_MAX) {
+			stop = true;
+			if (xas_retry(xas, folio))
+				continue;
+			if (xa_is_value(folio))
+				break;
+			if (folio_index(folio) != index) {
+				xas_reset(xas);
+				break;
+			}
+
+			if (!folio_try_get_rcu(folio)) {
+				xas_reset(xas);
+				continue;
+			}
+
+			/* Has the folio moved or been split? */
+			if (unlikely(folio != xas_reload(xas))) {
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+
+			if (!folio_trylock(folio)) {
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+			if (!folio_test_dirty(folio) ||
+			    folio_test_writeback(folio) ||
+			    folio_test_fscache(folio)) {
+				folio_unlock(folio);
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+
+			stop = false;
+			len = folio_size(folio);
+			priv = folio_get_private(folio);
+			if ((const struct netfs_group *)priv != group) {
+				stop = true;
+				finfo = netfs_folio_info(folio);
+				if (finfo->netfs_group != group ||
+				    finfo->dirty_offset > 0) {
+					folio_unlock(folio);
+					folio_put(folio);
+					xas_reset(xas);
+					break;
+				}
+				len = finfo->dirty_len;
+			}
+
+			*_top += folio_size(folio);
+			index += folio_nr_pages(folio);
+			*_count -= folio_nr_pages(folio);
+			*_len += len;
+			if (*_len >= max_len || *_count <= 0)
+				stop = true;
+
+			if (!folio_batch_add(&fbatch, folio))
+				break;
+			if (stop)
+				break;
+		}
+
+		xas_pause(xas);
+		rcu_read_unlock();
+
+		/* Now, if we obtained any folios, we can shift them to being
+		 * writable and mark them for caching.
+		 */
+		if (!folio_batch_count(&fbatch))
+			break;
+
+		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+			folio = fbatch.folios[i];
+			trace_netfs_folio(folio, netfs_folio_trace_store_plus);
+
+			if (!folio_clear_dirty_for_io(folio))
+				BUG();
+			folio_start_writeback(folio);
+			netfs_folio_start_fscache(caching, folio);
+			folio_unlock(folio);
+		}
+
+		folio_batch_release(&fbatch);
+		cond_resched();
+	} while (!stop);
+}
+
+/*
+ * Synchronously write back the locked page and any subsequent non-locked dirty
+ * pages.
+ */
+static ssize_t netfs_write_back_from_locked_folio(struct address_space *mapping,
+						  struct writeback_control *wbc,
+						  struct netfs_group *group,
+						  struct xa_state *xas,
+						  struct folio *folio,
+						  unsigned long long start,
+						  unsigned long long end)
+{
+	struct netfs_io_request *wreq;
+	struct netfs_folio *finfo;
+	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	unsigned long long i_size = i_size_read(&ctx->inode);
+	size_t len, max_len;
+	bool caching = netfs_is_cache_enabled(ctx);
+	long count = wbc->nr_to_write;
+	int ret;
+
+	_enter(",%lx,%llx-%llx,%u", folio_index(folio), start, end, caching);
+
+	wreq = netfs_alloc_request(mapping, NULL, start, folio_size(folio),
+				   NETFS_WRITEBACK);
+	if (IS_ERR(wreq)) {
+		folio_unlock(folio);
+		return PTR_ERR(wreq);
+	}
+
+	if (!folio_clear_dirty_for_io(folio))
+		BUG();
+	folio_start_writeback(folio);
+	netfs_folio_start_fscache(caching, folio);
+
+	count -= folio_nr_pages(folio);
+
+	/* Find all consecutive lockable dirty pages that have contiguous
+	 * written regions, stopping when we find a page that is not
+	 * immediately lockable, is not dirty or is missing, or we reach the
+	 * end of the range.
+	 */
+	trace_netfs_folio(folio, netfs_folio_trace_store);
+
+	len = wreq->len;
+	finfo = netfs_folio_info(folio);
+	if (finfo) {
+		start += finfo->dirty_offset;
+		if (finfo->dirty_offset + finfo->dirty_len != len) {
+			len = finfo->dirty_len;
+			goto cant_expand;
+		}
+		len = finfo->dirty_len;
+	}
+
+	if (start < i_size) {
+		/* Trim the write to the EOF; the extra data is ignored.  Also
+		 * put an upper limit on the size of a single storedata op.
+		 */
+		max_len = 65536 * 4096;
+		max_len = min_t(unsigned long long, max_len, end - start + 1);
+		max_len = min_t(unsigned long long, max_len, i_size - start);
+
+		if (len < max_len)
+			netfs_extend_writeback(mapping, group, xas, &count, start,
+					       max_len, caching, &len, &wreq->upper_len);
+	}
+
+cant_expand:
+	len = min_t(unsigned long long, len, i_size - start);
+
+	/* We now have a contiguous set of dirty pages, each with writeback
+	 * set; the first page is still locked at this point, but all the rest
+	 * have been unlocked.
+	 */
+	folio_unlock(folio);
+	wreq->start = start;
+	wreq->len = len;
+
+	if (start < i_size) {
+		_debug("write back %zx @%llx [%llx]", len, start, i_size);
+
+		/* Speculatively write to the cache.  We have to fix this up
+		 * later if the store fails.
+		 */
+		wreq->cleanup = netfs_cleanup_buffered_write;
+
+		iov_iter_xarray(&wreq->iter, ITER_SOURCE, &mapping->i_pages, start,
+				wreq->upper_len);
+		__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+		ret = netfs_begin_write(wreq, true, netfs_write_trace_writeback);
+		if (ret == 0 || ret == -EIOCBQUEUED)
+			wbc->nr_to_write -= len / PAGE_SIZE;
+	} else {
+		_debug("write discard %zx @%llx [%llx]", len, start, i_size);
+
+		/* The dirty region was entirely beyond the EOF. */
+		fscache_clear_page_bits(mapping, start, len, caching);
+		netfs_pages_written_back(wreq);
+		ret = 0;
+	}
+
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	_leave(" = 1");
+	return 1;
+}
+
+/*
+ * Write a region of pages back to the server
+ */
+static ssize_t netfs_writepages_begin(struct address_space *mapping,
+				      struct writeback_control *wbc,
+				      struct netfs_group *group,
+				      struct xa_state *xas,
+				      unsigned long long *_start,
+				      unsigned long long end)
+{
+	const struct netfs_folio *finfo;
+	struct folio *folio;
+	unsigned long long start = *_start;
+	ssize_t ret;
+	void *priv;
+	int skips = 0;
+
+	_enter("%llx,%llx,", start, end);
+
+search_again:
+	/* Find the first dirty page in the group. */
+	rcu_read_lock();
+
+	for (;;) {
+		folio = xas_find_marked(xas, end / PAGE_SIZE, PAGECACHE_TAG_DIRTY);
+		if (xas_retry(xas, folio) || xa_is_value(folio))
+			continue;
+		if (!folio)
+			break;
+
+		if (!folio_try_get_rcu(folio)) {
+			xas_reset(xas);
+			continue;
+		}
+
+		if (unlikely(folio != xas_reload(xas))) {
+			folio_put(folio);
+			xas_reset(xas);
+			continue;
+		}
+
+		/* Skip any dirty folio that's not in the group of interest. */
+		priv = folio_get_private(folio);
+		if ((const struct netfs_group *)priv != group) {
+			finfo = netfs_folio_info(folio);
+			if (finfo->netfs_group != group) {
+				folio_put(folio);
+				continue;
+			}
+		}
+
+		xas_pause(xas);
+		break;
+	}
+	rcu_read_unlock();
+	if (!folio)
+		return 0;
+
+	start = folio_pos(folio); /* May regress with THPs */
+
+	_debug("wback %lx", folio_index(folio));
+
+	/* At this point we hold neither the i_pages lock nor the page lock:
+	 * the page may be truncated or invalidated (changing page->mapping to
+	 * NULL), or even swizzled back from swapper_space to tmpfs file
+	 * mapping
+	 */
+lock_again:
+	if (wbc->sync_mode != WB_SYNC_NONE) {
+		ret = folio_lock_killable(folio);
+		if (ret < 0)
+			return ret;
+	} else {
+		if (!folio_trylock(folio))
+			goto search_again;
+	}
+
+	if (folio->mapping != mapping ||
+	    !folio_test_dirty(folio)) {
+		start += folio_size(folio);
+		folio_unlock(folio);
+		goto search_again;
+	}
+
+	if (folio_test_writeback(folio) ||
+	    folio_test_fscache(folio)) {
+		folio_unlock(folio);
+		if (wbc->sync_mode != WB_SYNC_NONE) {
+			folio_wait_writeback(folio);
+#ifdef CONFIG_NETFS_FSCACHE
+			folio_wait_fscache(folio);
+#endif
+			goto lock_again;
+		}
+
+		start += folio_size(folio);
+		if (wbc->sync_mode == WB_SYNC_NONE) {
+			if (skips >= 5 || need_resched()) {
+				ret = 0;
+				goto out;
+			}
+			skips++;
+		}
+		goto search_again;
+	}
+
+	ret = netfs_write_back_from_locked_folio(mapping, wbc, group, xas,
+						 folio, start, end);
+out:
+	if (ret > 0)
+		*_start = start + ret;
+	_leave(" = %zd [%llx]", ret, *_start);
+	return ret;
+}
+
+/*
+ * Write a region of pages back to the server
+ */
+static int netfs_writepages_region(struct address_space *mapping,
+				   struct writeback_control *wbc,
+				   struct netfs_group *group,
+				   unsigned long long *_start,
+				   unsigned long long end)
+{
+	ssize_t ret;
+
+	XA_STATE(xas, &mapping->i_pages, *_start / PAGE_SIZE);
+
+	do {
+		ret = netfs_writepages_begin(mapping, wbc, group, &xas,
+					     _start, end);
+		if (ret > 0 && wbc->nr_to_write > 0)
+			cond_resched();
+	} while (ret > 0 && wbc->nr_to_write > 0);
+
+	return ret > 0 ? 0 : ret;
+}
+
+/*
+ * write some of the pending data back to the server
+ */
+int netfs_writepages(struct address_space *mapping,
+		     struct writeback_control *wbc)
+{
+	struct netfs_group *group = NULL;
+	loff_t start, end;
+	int ret;
+
+	_enter("");
+
+	/* We have to be careful as we can end up racing with setattr()
+	 * truncating the pagecache since the caller doesn't take a lock here
+	 * to prevent it.
+	 */
+
+	if (wbc->range_cyclic && mapping->writeback_index) {
+		start = mapping->writeback_index * PAGE_SIZE;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, LLONG_MAX);
+		if (ret < 0)
+			goto out;
+
+		if (wbc->nr_to_write <= 0) {
+			mapping->writeback_index = start / PAGE_SIZE;
+			goto out;
+		}
+
+		start = 0;
+		end = mapping->writeback_index * PAGE_SIZE;
+		mapping->writeback_index = 0;
+		ret = netfs_writepages_region(mapping, wbc, group, &start, end);
+		if (ret == 0)
+			mapping->writeback_index = start / PAGE_SIZE;
+	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
+		start = 0;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, LLONG_MAX);
+		if (wbc->nr_to_write > 0 && ret == 0)
+			mapping->writeback_index = start / PAGE_SIZE;
+	} else {
+		start = wbc->range_start;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, wbc->range_end);
+	}
+
+out:
+	_leave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_writepages);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 2856389f4694c..86bb8cb7f8d08 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -397,6 +397,8 @@ int netfs_read_folio(struct file *, struct folio *);
 int netfs_write_begin(struct netfs_inode *, struct file *,
 		      struct address_space *, loff_t pos, unsigned int len,
 		      struct folio **, void **fsdata);
+int netfs_writepages(struct address_space *mapping,
+		     struct writeback_control *wbc);
 bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio);
 int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
 void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
-- 
GitLab


From 4a79616cfb27d76947ea37f0336745ef929d56be Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 5 Oct 2023 16:52:58 +0100
Subject: [PATCH 1974/4076] netfs: Provide a launder_folio implementation

Provide a launder_folio implementation for netfslib.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c    | 74 ++++++++++++++++++++++++++++++++++++
 fs/netfs/main.c              |  1 +
 include/linux/netfs.h        |  2 +
 include/trace/events/netfs.h |  3 ++
 4 files changed, 80 insertions(+)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index c078826f7fe67..50be8fe3ca432 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -1111,3 +1111,77 @@ out:
 	return ret;
 }
 EXPORT_SYMBOL(netfs_writepages);
+
+/*
+ * Deal with the disposition of a laundered folio.
+ */
+static void netfs_cleanup_launder_folio(struct netfs_io_request *wreq)
+{
+	if (wreq->error) {
+		pr_notice("R=%08x Laundering error %d\n", wreq->debug_id, wreq->error);
+		mapping_set_error(wreq->mapping, wreq->error);
+	}
+}
+
+/**
+ * netfs_launder_folio - Clean up a dirty folio that's being invalidated
+ * @folio: The folio to clean
+ *
+ * This is called to write back a folio that's being invalidated when an inode
+ * is getting torn down.  Ideally, writepages would be used instead.
+ */
+int netfs_launder_folio(struct folio *folio)
+{
+	struct netfs_io_request *wreq;
+	struct address_space *mapping = folio->mapping;
+	struct netfs_folio *finfo = netfs_folio_info(folio);
+	struct netfs_group *group = netfs_folio_group(folio);
+	struct bio_vec bvec;
+	unsigned long long i_size = i_size_read(mapping->host);
+	unsigned long long start = folio_pos(folio);
+	size_t offset = 0, len;
+	int ret = 0;
+
+	if (finfo) {
+		offset = finfo->dirty_offset;
+		start += offset;
+		len = finfo->dirty_len;
+	} else {
+		len = folio_size(folio);
+	}
+	len = min_t(unsigned long long, len, i_size - start);
+
+	wreq = netfs_alloc_request(mapping, NULL, start, len, NETFS_LAUNDER_WRITE);
+	if (IS_ERR(wreq)) {
+		ret = PTR_ERR(wreq);
+		goto out;
+	}
+
+	if (!folio_clear_dirty_for_io(folio))
+		goto out_put;
+
+	trace_netfs_folio(folio, netfs_folio_trace_launder);
+
+	_debug("launder %llx-%llx", start, start + len - 1);
+
+	/* Speculatively write to the cache.  We have to fix this up later if
+	 * the store fails.
+	 */
+	wreq->cleanup = netfs_cleanup_launder_folio;
+
+	bvec_set_folio(&bvec, folio, len, offset);
+	iov_iter_bvec(&wreq->iter, ITER_SOURCE, &bvec, 1, len);
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	ret = netfs_begin_write(wreq, true, netfs_write_trace_launder);
+
+out_put:
+	folio_detach_private(folio);
+	netfs_put_group(group);
+	kfree(finfo);
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+out:
+	folio_wait_fscache(folio);
+	_leave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_launder_folio);
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 8e4db9ff40c40..473f889e1bd18 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -30,6 +30,7 @@ static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READPAGE]		= "RP",
 	[NETFS_READ_FOR_WRITE]		= "RW",
 	[NETFS_WRITEBACK]		= "WB",
+	[NETFS_LAUNDER_WRITE]		= "LW",
 	[NETFS_UNBUFFERED_WRITE]	= "UW",
 	[NETFS_DIO_READ]		= "DR",
 	[NETFS_DIO_WRITE]		= "DW",
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 86bb8cb7f8d08..29c66acad9256 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -227,6 +227,7 @@ enum netfs_io_origin {
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
 	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_LAUNDER_WRITE,		/* This is triggered by ->launder_folio() */
 	NETFS_UNBUFFERED_WRITE,		/* This is an unbuffered write */
 	NETFS_DIO_READ,			/* This is a direct I/O read */
 	NETFS_DIO_WRITE,		/* This is a direct I/O write */
@@ -404,6 +405,7 @@ int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
 void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
 void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 bool netfs_release_folio(struct folio *folio, gfp_t gfp);
+int netfs_launder_folio(struct folio *folio);
 
 /* VMA operations API. */
 vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 914a24b03d08b..cc998798e20a4 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -25,6 +25,7 @@
 
 #define netfs_write_traces					\
 	EM(netfs_write_trace_dio_write,		"DIO-WRITE")	\
+	EM(netfs_write_trace_launder,		"LAUNDER  ")	\
 	EM(netfs_write_trace_unbuffered_write,	"UNB-WRITE")	\
 	E_(netfs_write_trace_writeback,		"WRITEBACK")
 
@@ -33,6 +34,7 @@
 	EM(NETFS_READPAGE,			"RP")		\
 	EM(NETFS_READ_FOR_WRITE,		"RW")		\
 	EM(NETFS_WRITEBACK,			"WB")		\
+	EM(NETFS_LAUNDER_WRITE,			"LW")		\
 	EM(NETFS_UNBUFFERED_WRITE,		"UW")		\
 	EM(NETFS_DIO_READ,			"DR")		\
 	E_(NETFS_DIO_WRITE,			"DW")
@@ -127,6 +129,7 @@
 	EM(netfs_folio_trace_end_copy,		"end-copy")	\
 	EM(netfs_folio_trace_filled_gaps,	"filled-gaps")	\
 	EM(netfs_folio_trace_kill,		"kill")		\
+	EM(netfs_folio_trace_launder,		"launder")	\
 	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
 	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
 	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
-- 
GitLab


From 41d8e7673a7726cba57cb8112d81c89cfb6c3e35 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 12 Oct 2023 09:06:24 +0100
Subject: [PATCH 1975/4076] netfs: Implement a write-through caching option

Provide a flag whereby a filesystem may request that cifs_perform_write()
perform write-through caching.  This involves putting pages directly into
writeback rather than dirty and attaching them to a write operation as we
go.

Further, the writes being made are limited to the byte range being written
rather than whole folios being written.  This can be used by cifs, for
example, to deal with strict byte-range locking.

This can't be used with content encryption as that may require expansion of
the write RPC beyond the write being made.

This doesn't affect writes via mmap - those are written back in the normal
way; similarly failed writethrough writes are marked dirty and left to
writeback to retry.  Another option would be to simply invalidate them, but
the contents can be simultaneously accessed by read() and through mmap.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c    | 69 +++++++++++++++++++++++----
 fs/netfs/internal.h          |  3 ++
 fs/netfs/main.c              |  1 +
 fs/netfs/objects.c           |  1 +
 fs/netfs/output.c            | 90 ++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h        |  2 +
 include/trace/events/netfs.h |  8 +++-
 7 files changed, 162 insertions(+), 12 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 50be8fe3ca432..6ca6c4bde5eb2 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -26,6 +26,8 @@ enum netfs_how_to_modify {
 	NETFS_FLUSH_CONTENT,		/* Flush incompatible content. */
 };
 
+static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq);
+
 static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group)
 {
 	if (netfs_group && !folio_get_private(folio))
@@ -133,6 +135,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct inode *inode = file_inode(file);
 	struct address_space *mapping = inode->i_mapping;
 	struct netfs_inode *ctx = netfs_inode(inode);
+	struct writeback_control wbc = {
+		.sync_mode	= WB_SYNC_NONE,
+		.for_sync	= true,
+		.nr_to_write	= LONG_MAX,
+		.range_start	= iocb->ki_pos,
+		.range_end	= iocb->ki_pos + iter->count,
+	};
+	struct netfs_io_request *wreq = NULL;
 	struct netfs_folio *finfo;
 	struct folio *folio;
 	enum netfs_how_to_modify howto;
@@ -143,6 +153,30 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
 	bool maybe_trouble = false;
 
+	if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) ||
+		     iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC))
+	    ) {
+		if (pos < i_size_read(inode)) {
+			ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count);
+			if (ret < 0) {
+				goto out;
+			}
+		}
+
+		wbc_attach_fdatawrite_inode(&wbc, mapping->host);
+
+		wreq = netfs_begin_writethrough(iocb, iter->count);
+		if (IS_ERR(wreq)) {
+			wbc_detach_inode(&wbc);
+			ret = PTR_ERR(wreq);
+			wreq = NULL;
+			goto out;
+		}
+		if (!is_sync_kiocb(iocb))
+			wreq->iocb = iocb;
+		wreq->cleanup = netfs_cleanup_buffered_write;
+	}
+
 	do {
 		size_t flen;
 		size_t offset;	/* Offset into pagecache folio */
@@ -315,7 +349,25 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		}
 		written += copied;
 
-		folio_mark_dirty(folio);
+		if (likely(!wreq)) {
+			folio_mark_dirty(folio);
+		} else {
+			if (folio_test_dirty(folio))
+				/* Sigh.  mmap. */
+				folio_clear_dirty_for_io(folio);
+			/* We make multiple writes to the folio... */
+			if (!folio_test_writeback(folio)) {
+				folio_wait_fscache(folio);
+				folio_start_writeback(folio);
+				folio_start_fscache(folio);
+				if (wreq->iter.count == 0)
+					trace_netfs_folio(folio, netfs_folio_trace_wthru);
+				else
+					trace_netfs_folio(folio, netfs_folio_trace_wthru_plus);
+			}
+			netfs_advance_writethrough(wreq, copied,
+						   offset + copied == flen);
+		}
 	retry:
 		folio_unlock(folio);
 		folio_put(folio);
@@ -325,17 +377,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	} while (iov_iter_count(iter));
 
 out:
-	if (likely(written)) {
-		/* Flush and wait for a write that requires immediate synchronisation. */
-		if (iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) {
-			_debug("dsync");
-			ret = filemap_fdatawait_range(mapping, iocb->ki_pos,
-						      iocb->ki_pos + written);
-		}
-
-		iocb->ki_pos += written;
+	if (unlikely(wreq)) {
+		ret = netfs_end_writethrough(wreq, iocb);
+		wbc_detach_inode(&wbc);
+		if (ret == -EIOCBQUEUED)
+			return ret;
 	}
 
+	iocb->ki_pos += written;
 	_leave(" = %zd [%zd]", written, ret);
 	return written ? written : ret;
 
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 2de4f826dbe4f..d2d63120ac60a 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -101,6 +101,9 @@ static inline void netfs_see_request(struct netfs_io_request *rreq,
  */
 int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
 		      enum netfs_write_trace what);
+struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len);
+int netfs_advance_writethrough(struct netfs_io_request *wreq, size_t copied, bool to_page_end);
+int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb);
 
 /*
  * stats.c
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 473f889e1bd18..81a13071b258a 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -30,6 +30,7 @@ static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READPAGE]		= "RP",
 	[NETFS_READ_FOR_WRITE]		= "RW",
 	[NETFS_WRITEBACK]		= "WB",
+	[NETFS_WRITETHROUGH]		= "WT",
 	[NETFS_LAUNDER_WRITE]		= "LW",
 	[NETFS_UNBUFFERED_WRITE]	= "UW",
 	[NETFS_DIO_READ]		= "DR",
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index b4e3bd836e5df..610ceb5bd86c0 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -41,6 +41,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	rreq->i_size	= i_size_read(inode);
 	rreq->debug_id	= atomic_inc_return(&debug_ids);
 	INIT_LIST_HEAD(&rreq->subrequests);
+	INIT_WORK(&rreq->work, NULL);
 	refcount_set(&rreq->ref, 1);
 
 	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
index cc9065733b423..625eb68f3e5ad 100644
--- a/fs/netfs/output.c
+++ b/fs/netfs/output.c
@@ -386,3 +386,93 @@ int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
 		    TASK_UNINTERRUPTIBLE);
 	return wreq->error;
 }
+
+/*
+ * Begin a write operation for writing through the pagecache.
+ */
+struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len)
+{
+	struct netfs_io_request *wreq;
+	struct file *file = iocb->ki_filp;
+
+	wreq = netfs_alloc_request(file->f_mapping, file, iocb->ki_pos, len,
+				   NETFS_WRITETHROUGH);
+	if (IS_ERR(wreq))
+		return wreq;
+
+	trace_netfs_write(wreq, netfs_write_trace_writethrough);
+
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	iov_iter_xarray(&wreq->iter, ITER_SOURCE, &wreq->mapping->i_pages, wreq->start, 0);
+	wreq->io_iter = wreq->iter;
+
+	/* ->outstanding > 0 carries a ref */
+	netfs_get_request(wreq, netfs_rreq_trace_get_for_outstanding);
+	atomic_set(&wreq->nr_outstanding, 1);
+	return wreq;
+}
+
+static void netfs_submit_writethrough(struct netfs_io_request *wreq, bool final)
+{
+	struct netfs_inode *ictx = netfs_inode(wreq->inode);
+	unsigned long long start;
+	size_t len;
+
+	if (!test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))
+		return;
+
+	start = wreq->start + wreq->submitted;
+	len = wreq->iter.count - wreq->submitted;
+	if (!final) {
+		len /= wreq->wsize; /* Round to number of maximum packets */
+		len *= wreq->wsize;
+	}
+
+	ictx->ops->create_write_requests(wreq, start, len);
+	wreq->submitted += len;
+}
+
+/*
+ * Advance the state of the write operation used when writing through the
+ * pagecache.  Data has been copied into the pagecache that we need to append
+ * to the request.  If we've added more than wsize then we need to create a new
+ * subrequest.
+ */
+int netfs_advance_writethrough(struct netfs_io_request *wreq, size_t copied, bool to_page_end)
+{
+	_enter("ic=%zu sb=%zu ws=%u cp=%zu tp=%u",
+	       wreq->iter.count, wreq->submitted, wreq->wsize, copied, to_page_end);
+
+	wreq->iter.count += copied;
+	wreq->io_iter.count += copied;
+	if (to_page_end && wreq->io_iter.count - wreq->submitted >= wreq->wsize)
+		netfs_submit_writethrough(wreq, false);
+
+	return wreq->error;
+}
+
+/*
+ * End a write operation used when writing through the pagecache.
+ */
+int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb)
+{
+	int ret = -EIOCBQUEUED;
+
+	_enter("ic=%zu sb=%zu ws=%u",
+	       wreq->iter.count, wreq->submitted, wreq->wsize);
+
+	if (wreq->submitted < wreq->io_iter.count)
+		netfs_submit_writethrough(wreq, true);
+
+	if (atomic_dec_and_test(&wreq->nr_outstanding))
+		netfs_write_terminated(wreq, false);
+
+	if (is_sync_kiocb(iocb)) {
+		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
+		ret = wreq->error;
+	}
+
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	return ret;
+}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 29c66acad9256..8a2dd882a7814 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -139,6 +139,7 @@ struct netfs_inode {
 	unsigned long		flags;
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
+#define NETFS_ICTX_WRITETHROUGH	2		/* Write-through caching */
 };
 
 /*
@@ -227,6 +228,7 @@ enum netfs_io_origin {
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
 	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_WRITETHROUGH,		/* This write was made by netfs_perform_write() */
 	NETFS_LAUNDER_WRITE,		/* This is triggered by ->launder_folio() */
 	NETFS_UNBUFFERED_WRITE,		/* This is an unbuffered write */
 	NETFS_DIO_READ,			/* This is a direct I/O read */
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index cc998798e20a4..447a8c21cf57d 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -27,13 +27,15 @@
 	EM(netfs_write_trace_dio_write,		"DIO-WRITE")	\
 	EM(netfs_write_trace_launder,		"LAUNDER  ")	\
 	EM(netfs_write_trace_unbuffered_write,	"UNB-WRITE")	\
-	E_(netfs_write_trace_writeback,		"WRITEBACK")
+	EM(netfs_write_trace_writeback,		"WRITEBACK")	\
+	E_(netfs_write_trace_writethrough,	"WRITETHRU")
 
 #define netfs_rreq_origins					\
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
 	EM(NETFS_READ_FOR_WRITE,		"RW")		\
 	EM(NETFS_WRITEBACK,			"WB")		\
+	EM(NETFS_WRITETHROUGH,			"WT")		\
 	EM(NETFS_LAUNDER_WRITE,			"LW")		\
 	EM(NETFS_UNBUFFERED_WRITE,		"UW")		\
 	EM(NETFS_DIO_READ,			"DR")		\
@@ -136,7 +138,9 @@
 	EM(netfs_folio_trace_redirty,		"redirty")	\
 	EM(netfs_folio_trace_redirtied,		"redirtied")	\
 	EM(netfs_folio_trace_store,		"store")	\
-	E_(netfs_folio_trace_store_plus,	"store+")
+	EM(netfs_folio_trace_store_plus,	"store+")	\
+	EM(netfs_folio_trace_wthru,		"wthru")	\
+	E_(netfs_folio_trace_wthru_plus,	"wthru+")
 
 #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
-- 
GitLab


From 100ccd18bb41ea7abb4fbb419202c06079559501 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 24 Nov 2023 13:39:02 +0000
Subject: [PATCH 1976/4076] netfs: Optimise away reads above the point at which
 there can be no data

Track the file position above which the server is not expected to have any
data (the "zero point") and preemptively assume that we can satisfy
requests by filling them with zeroes locally rather than attempting to
download them if they're over that line - even if we've written data back
to the server.  Assume that any data that was written back above that
position is held in the local cache.  Note that we have to split requests
that straddle the line.

Make use of this to optimise away some reads from the server.  We need to
set the zero point in the following circumstances:

 (1) When we see an extant remote inode and have no cache for it, we set
     the zero_point to i_size.

 (2) On local inode creation, we set zero_point to 0.

 (3) On local truncation down, we reduce zero_point to the new i_size if
     the new i_size is lower.

 (4) On local truncation up, we don't change zero_point.

 (5) On local modification, we don't change zero_point.

 (6) On remote invalidation, we set zero_point to the new i_size.

 (7) If stored data is discarded from the pagecache or culled from fscache,
     we must set zero_point above that if the data also got written to the
     server.

 (8) If dirty data is written back to the server, but not fscache, we must
     set zero_point above that.

 (9) If a direct I/O write is made, set zero_point above that.

Assuming the above, any read from the server at or above the zero_point
position will return all zeroes.

The zero_point value can be stored in the cache, provided the above rules
are applied to it by any code that culls part of the local cache.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/9p/vfs_inode.c         |  2 +-
 fs/afs/dynroot.c          |  2 +-
 fs/afs/inode.c            | 24 ++++++++++++++----------
 fs/ceph/inode.c           |  2 +-
 fs/netfs/buffered_write.c |  2 +-
 fs/netfs/direct_write.c   |  4 ++++
 fs/netfs/io.c             | 10 ++++++++++
 fs/netfs/misc.c           |  5 +++++
 fs/nfs/fscache.h          |  2 +-
 fs/smb/client/cifsfs.c    |  4 ++--
 include/linux/netfs.h     | 21 ++++++++++++++++++---
 11 files changed, 58 insertions(+), 20 deletions(-)

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 74122540e00f2..df7ae381a7088 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -249,7 +249,7 @@ void v9fs_free_inode(struct inode *inode)
 static void v9fs_set_netfs_context(struct inode *inode)
 {
 	struct v9fs_inode *v9inode = V9FS_I(inode);
-	netfs_inode_init(&v9inode->netfs, &v9fs_req_ops);
+	netfs_inode_init(&v9inode->netfs, &v9fs_req_ops, true);
 }
 
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 1f656005018ea..9c517269ff954 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -76,7 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
 	/* there shouldn't be an existing inode */
 	BUG_ON(!(inode->i_state & I_NEW));
 
-	netfs_inode_init(&vnode->netfs, NULL);
+	netfs_inode_init(&vnode->netfs, NULL, false);
 	inode->i_size		= 0;
 	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
 	if (root) {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 37485ae314714..381521e9e1183 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -58,7 +58,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
  */
 static void afs_set_netfs_context(struct afs_vnode *vnode)
 {
-	netfs_inode_init(&vnode->netfs, &afs_req_ops);
+	netfs_inode_init(&vnode->netfs, &afs_req_ops, true);
 }
 
 /*
@@ -168,6 +168,7 @@ static void afs_apply_status(struct afs_operation *op,
 	struct inode *inode = &vnode->netfs.inode;
 	struct timespec64 t;
 	umode_t mode;
+	bool unexpected_jump = false;
 	bool data_changed = false;
 	bool change_size = vp->set_size;
 
@@ -231,6 +232,7 @@ static void afs_apply_status(struct afs_operation *op,
 		}
 		change_size = true;
 		data_changed = true;
+		unexpected_jump = true;
 	} else if (vnode->status.type == AFS_FTYPE_DIR) {
 		/* Expected directory change is handled elsewhere so
 		 * that we can locally edit the directory and save on a
@@ -252,6 +254,8 @@ static void afs_apply_status(struct afs_operation *op,
 		vnode->netfs.remote_i_size = status->size;
 		if (change_size || status->size > i_size_read(inode)) {
 			afs_set_i_size(vnode, status->size);
+			if (unexpected_jump)
+				vnode->netfs.zero_point = status->size;
 			inode_set_ctime_to_ts(inode, t);
 			inode_set_atime_to_ts(inode, t);
 		}
@@ -865,17 +869,17 @@ static void afs_setattr_success(struct afs_operation *op)
 static void afs_setattr_edit_file(struct afs_operation *op)
 {
 	struct afs_vnode_param *vp = &op->file[0];
-	struct inode *inode = &vp->vnode->netfs.inode;
+	struct afs_vnode *vnode = vp->vnode;
 
 	if (op->setattr.attr->ia_valid & ATTR_SIZE) {
 		loff_t size = op->setattr.attr->ia_size;
 		loff_t i_size = op->setattr.old_i_size;
 
-		if (size < i_size)
-			truncate_pagecache(inode, size);
-		if (size != i_size)
-			fscache_resize_cookie(afs_vnode_cache(vp->vnode),
-					      vp->scb.status.size);
+		if (size != i_size) {
+			truncate_setsize(&vnode->netfs.inode, size);
+			netfs_resize_file(&vnode->netfs, size, true);
+			fscache_resize_cookie(afs_vnode_cache(vnode), size);
+		}
 	}
 }
 
@@ -943,11 +947,11 @@ int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 */
 		if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) &&
 		    attr->ia_size < i_size &&
-		    attr->ia_size > vnode->status.size) {
-			truncate_pagecache(inode, attr->ia_size);
+		    attr->ia_size > vnode->netfs.remote_i_size) {
+			truncate_setsize(inode, attr->ia_size);
+			netfs_resize_file(&vnode->netfs, size, false);
 			fscache_resize_cookie(afs_vnode_cache(vnode),
 					      attr->ia_size);
-			i_size_write(inode, attr->ia_size);
 			ret = 0;
 			goto out_unlock;
 		}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 3149d79a9dbe5..0c25d326afc41 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -574,7 +574,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	doutc(fsc->client, "%p\n", &ci->netfs.inode);
 
 	/* Set parameters for the netfs library */
-	netfs_inode_init(&ci->netfs, &ceph_netfs_ops);
+	netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false);
 
 	spin_lock_init(&ci->i_ceph_lock);
 
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 6ca6c4bde5eb2..08f28800232c3 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -73,7 +73,7 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 	if (folio_test_uptodate(folio))
 		return NETFS_FOLIO_IS_UPTODATE;
 
-	if (pos >= ctx->remote_i_size)
+	if (pos >= ctx->zero_point)
 		return NETFS_MODIFY_AND_CLEAR;
 
 	if (!maybe_trouble && offset == 0 && len >= flen)
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index bb0c2718f57bd..aad05f2349a48 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -134,6 +134,7 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct netfs_inode *ictx = netfs_inode(inode);
+	unsigned long long end;
 	ssize_t ret;
 
 	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
@@ -155,6 +156,9 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ret = kiocb_invalidate_pages(iocb, iov_iter_count(from));
 	if (ret < 0)
 		goto out;
+	end = iocb->ki_pos + iov_iter_count(from);
+	if (end > ictx->zero_point)
+		ictx->zero_point = end;
 
 	fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode),
 			   FSCACHE_INVAL_DIO_WRITE);
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 14c18be5aca00..5b5af96cd4b95 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -569,6 +569,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			struct iov_iter *io_iter)
 {
 	enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER;
+	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
@@ -586,6 +587,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		 * to make serial calls, it can indicate a short read and then
 		 * we will call it again.
 		 */
+		if (rreq->origin != NETFS_DIO_READ) {
+			if (subreq->start >= ictx->zero_point) {
+				source = NETFS_FILL_WITH_ZEROES;
+				goto set;
+			}
+			if (subreq->len > ictx->zero_point - subreq->start)
+				subreq->len = ictx->zero_point - subreq->start;
+		}
 		if (subreq->len > rreq->i_size - subreq->start)
 			subreq->len = rreq->i_size - subreq->start;
 		if (rreq->rsize && subreq->len > rreq->rsize)
@@ -607,6 +616,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		}
 	}
 
+set:
 	if (subreq->len > rreq->len)
 		pr_warn("R=%08x[%u] SREQ>RREQ %zx > %zx\n",
 			rreq->debug_id, subreq->debug_index,
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index eeb44abe59c52..0e3af37fc9243 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -240,6 +240,11 @@ EXPORT_SYMBOL(netfs_invalidate_folio);
 bool netfs_release_folio(struct folio *folio, gfp_t gfp)
 {
 	struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
+	unsigned long long end;
+
+	end = folio_pos(folio) + folio_size(folio);
+	if (end > ctx->zero_point)
+		ctx->zero_point = end;
 
 	if (folio_test_private(folio))
 		return false;
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 5407ab8c87835..e3cb4923316b2 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -80,7 +80,7 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs)
 }
 static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi)
 {
-	netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops);
+	netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false);
 }
 extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr);
 extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 96a65cf9b5ec9..07cd88897c331 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1220,7 +1220,7 @@ static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *s
 	if (rc < 0)
 		goto set_failed;
 
-	netfs_resize_file(&src_cifsi->netfs, src_end);
+	netfs_resize_file(&src_cifsi->netfs, src_end, true);
 	fscache_resize_cookie(cifs_inode_cookie(src_inode), src_end);
 	return 0;
 
@@ -1351,7 +1351,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 			smb_file_src, smb_file_target, off, len, destoff);
 		if (rc == 0 && new_size > i_size_read(target_inode)) {
 			truncate_setsize(target_inode, new_size);
-			netfs_resize_file(&target_cifsi->netfs, new_size);
+			netfs_resize_file(&target_cifsi->netfs, new_size, true);
 			fscache_resize_cookie(cifs_inode_cookie(target_inode),
 					      new_size);
 		}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 8a2dd882a7814..852956aa3c4bb 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -136,6 +136,8 @@ struct netfs_inode {
 	struct fscache_cookie	*cache;
 #endif
 	loff_t			remote_i_size;	/* Size of the remote file */
+	loff_t			zero_point;	/* Size after which we assume there's no data
+						 * on the server */
 	unsigned long		flags;
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
@@ -453,31 +455,44 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode)
  * netfs_inode_init - Initialise a netfslib inode context
  * @ctx: The netfs inode to initialise
  * @ops: The netfs's operations list
+ * @use_zero_point: True to use the zero_point read optimisation
  *
  * Initialise the netfs library context struct.  This is expected to follow on
  * directly from the VFS inode struct.
  */
 static inline void netfs_inode_init(struct netfs_inode *ctx,
-				    const struct netfs_request_ops *ops)
+				    const struct netfs_request_ops *ops,
+				    bool use_zero_point)
 {
 	ctx->ops = ops;
 	ctx->remote_i_size = i_size_read(&ctx->inode);
+	ctx->zero_point = LLONG_MAX;
 	ctx->flags = 0;
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
+	/* ->releasepage() drives zero_point */
+	if (use_zero_point) {
+		ctx->zero_point = ctx->remote_i_size;
+		mapping_set_release_always(ctx->inode.i_mapping);
+	}
 }
 
 /**
  * netfs_resize_file - Note that a file got resized
  * @ctx: The netfs inode being resized
  * @new_i_size: The new file size
+ * @changed_on_server: The change was applied to the server
  *
  * Inform the netfs lib that a file got resized so that it can adjust its state.
  */
-static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size)
+static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size,
+				     bool changed_on_server)
 {
-	ctx->remote_i_size = new_i_size;
+	if (changed_on_server)
+		ctx->remote_i_size = new_i_size;
+	if (new_i_size < ctx->zero_point)
+		ctx->zero_point = new_i_size;
 }
 
 /**
-- 
GitLab


From 545b135b72002145ade758f7e59c113915283188 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 25 Apr 2022 16:30:11 +0100
Subject: [PATCH 1977/4076] netfs: Export the netfs_sreq tracepoint

Export the netfs_sreq tracepoint so that it can be called directly from
client filesystems/cache backend modules.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 81a13071b258a..5e77618a79409 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -17,6 +17,8 @@ MODULE_DESCRIPTION("Network fs support");
 MODULE_AUTHOR("Red Hat, Inc.");
 MODULE_LICENSE("GPL");
 
+EXPORT_TRACEPOINT_SYMBOL(netfs_sreq);
+
 unsigned netfs_debug;
 module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
-- 
GitLab


From 3560358a49569d0ade0ee5c9cecb3606dac863c2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 15 Feb 2022 17:02:04 +0000
Subject: [PATCH 1978/4076] afs: Use the netfs write helpers

Make afs use the netfs write helpers.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/afs/file.c              |  70 +++-
 fs/afs/internal.h          |  10 +-
 fs/afs/write.c             | 707 ++-----------------------------------
 include/trace/events/afs.h |  23 --
 4 files changed, 84 insertions(+), 726 deletions(-)

diff --git a/fs/afs/file.c b/fs/afs/file.c
index 3403bb792deb8..833e7c2003e0c 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -34,7 +34,7 @@ const struct file_operations afs_file_operations = {
 	.release	= afs_release,
 	.llseek		= generic_file_llseek,
 	.read_iter	= afs_file_read_iter,
-	.write_iter	= afs_file_write,
+	.write_iter	= netfs_file_write_iter,
 	.mmap		= afs_file_mmap,
 	.splice_read	= afs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
@@ -50,16 +50,15 @@ const struct inode_operations afs_file_inode_operations = {
 };
 
 const struct address_space_operations afs_file_aops = {
+	.direct_IO	= noop_direct_IO,
 	.read_folio	= netfs_read_folio,
 	.readahead	= netfs_readahead,
 	.dirty_folio	= netfs_dirty_folio,
-	.launder_folio	= afs_launder_folio,
+	.launder_folio	= netfs_launder_folio,
 	.release_folio	= netfs_release_folio,
 	.invalidate_folio = netfs_invalidate_folio,
-	.write_begin	= afs_write_begin,
-	.write_end	= afs_write_end,
-	.writepages	= afs_writepages,
 	.migrate_folio	= filemap_migrate_folio,
+	.writepages	= afs_writepages,
 };
 
 const struct address_space_operations afs_symlink_aops = {
@@ -355,7 +354,10 @@ static int afs_symlink_read_folio(struct file *file, struct folio *folio)
 
 static int afs_init_request(struct netfs_io_request *rreq, struct file *file)
 {
-	rreq->netfs_priv = key_get(afs_file_key(file));
+	if (file)
+		rreq->netfs_priv = key_get(afs_file_key(file));
+	rreq->rsize = 256 * 1024;
+	rreq->wsize = 256 * 1024;
 	return 0;
 }
 
@@ -372,11 +374,36 @@ static void afs_free_request(struct netfs_io_request *rreq)
 	key_put(rreq->netfs_priv);
 }
 
+static void afs_update_i_size(struct inode *inode, loff_t new_i_size)
+{
+	struct afs_vnode *vnode = AFS_FS_I(inode);
+	loff_t i_size;
+
+	write_seqlock(&vnode->cb_lock);
+	i_size = i_size_read(&vnode->netfs.inode);
+	if (new_i_size > i_size) {
+		i_size_write(&vnode->netfs.inode, new_i_size);
+		inode_set_bytes(&vnode->netfs.inode, new_i_size);
+	}
+	write_sequnlock(&vnode->cb_lock);
+	fscache_update_cookie(afs_vnode_cache(vnode), NULL, &new_i_size);
+}
+
+static void afs_netfs_invalidate_cache(struct netfs_io_request *wreq)
+{
+	struct afs_vnode *vnode = AFS_FS_I(wreq->inode);
+
+	afs_invalidate_cache(vnode, 0);
+}
+
 const struct netfs_request_ops afs_req_ops = {
 	.init_request		= afs_init_request,
 	.free_request		= afs_free_request,
 	.check_write_begin	= afs_check_write_begin,
 	.issue_read		= afs_issue_read,
+	.update_i_size		= afs_update_i_size,
+	.invalidate_cache	= afs_netfs_invalidate_cache,
+	.create_write_requests	= afs_create_write_requests,
 };
 
 static void afs_add_open_mmap(struct afs_vnode *vnode)
@@ -445,28 +472,39 @@ static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pg
 
 static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = iocb->ki_filp->private_data;
-	int ret;
+	ssize_t ret;
 
-	ret = afs_validate(vnode, af->key);
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return netfs_unbuffered_read_iter(iocb, iter);
+
+	ret = netfs_start_io_read(inode);
 	if (ret < 0)
 		return ret;
-
-	return generic_file_read_iter(iocb, iter);
+	ret = afs_validate(vnode, af->key);
+	if (ret == 0)
+		ret = filemap_read(iocb, iter, 0);
+	netfs_end_io_read(inode);
+	return ret;
 }
 
 static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos,
 				    struct pipe_inode_info *pipe,
 				    size_t len, unsigned int flags)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(in));
+	struct inode *inode = file_inode(in);
+	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = in->private_data;
-	int ret;
+	ssize_t ret;
 
-	ret = afs_validate(vnode, af->key);
+	ret = netfs_start_io_read(inode);
 	if (ret < 0)
 		return ret;
-
-	return filemap_splice_read(in, ppos, pipe, len, flags);
+	ret = afs_validate(vnode, af->key);
+	if (ret == 0)
+		ret = filemap_splice_read(in, ppos, pipe, len, flags);
+	netfs_end_io_read(inode);
+	return ret;
 }
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index a7c8d1d702ee0..32f787f74e76c 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1465,19 +1465,11 @@ extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *);
 /*
  * write.c
  */
-extern int afs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata);
-extern int afs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata);
-extern int afs_writepage(struct page *, struct writeback_control *);
 extern int afs_writepages(struct address_space *, struct writeback_control *);
-extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *);
 extern int afs_fsync(struct file *, loff_t, loff_t, int);
 extern vm_fault_t afs_page_mkwrite(struct vm_fault *vmf);
 extern void afs_prune_wb_keys(struct afs_vnode *);
-int afs_launder_folio(struct folio *);
+void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len);
 
 /*
  * xattr.c
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 80daf28d8f8b8..09b6c0b9a28ed 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -12,228 +12,17 @@
 #include <linux/writeback.h>
 #include <linux/pagevec.h>
 #include <linux/netfs.h>
+#include <trace/events/netfs.h>
 #include "internal.h"
 
-static int afs_writepages_region(struct address_space *mapping,
-				 struct writeback_control *wbc,
-				 unsigned long long start,
-				 unsigned long long end, loff_t *_next,
-				 bool max_one_loop);
-
-static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len,
-			       loff_t i_size, bool caching);
-
-#ifdef CONFIG_AFS_FSCACHE
-static void afs_folio_start_fscache(bool caching, struct folio *folio)
-{
-	if (caching)
-		folio_start_fscache(folio);
-}
-#else
-static void afs_folio_start_fscache(bool caching, struct folio *folio)
-{
-}
-#endif
-
-/*
- * prepare to perform part of a write to a page
- */
-int afs_write_begin(struct file *file, struct address_space *mapping,
-		    loff_t pos, unsigned len,
-		    struct page **_page, void **fsdata)
-{
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	struct folio *folio;
-	int ret;
-
-	_enter("{%llx:%llu},%llx,%x",
-	       vnode->fid.vid, vnode->fid.vnode, pos, len);
-
-	/* Prefetch area to be written into the cache if we're caching this
-	 * file.  We need to do this before we get a lock on the page in case
-	 * there's more than one writer competing for the same cache block.
-	 */
-	ret = netfs_write_begin(&vnode->netfs, file, mapping, pos, len, &folio, fsdata);
-	if (ret < 0)
-		return ret;
-
-try_again:
-	/* See if this page is already partially written in a way that we can
-	 * merge the new write with.
-	 */
-	if (folio_test_writeback(folio)) {
-		trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio);
-		folio_unlock(folio);
-		goto wait_for_writeback;
-	}
-
-	*_page = folio_file_page(folio, pos / PAGE_SIZE);
-	_leave(" = 0");
-	return 0;
-
-wait_for_writeback:
-	ret = folio_wait_writeback_killable(folio);
-	if (ret < 0)
-		goto error;
-
-	ret = folio_lock_killable(folio);
-	if (ret < 0)
-		goto error;
-	goto try_again;
-
-error:
-	folio_put(folio);
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
- * finalise part of a write to a page
- */
-int afs_write_end(struct file *file, struct address_space *mapping,
-		  loff_t pos, unsigned len, unsigned copied,
-		  struct page *subpage, void *fsdata)
-{
-	struct folio *folio = page_folio(subpage);
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	loff_t i_size, write_end_pos;
-
-	_enter("{%llx:%llu},{%lx}",
-	       vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
-
-	if (!folio_test_uptodate(folio)) {
-		if (copied < len) {
-			copied = 0;
-			goto out;
-		}
-
-		folio_mark_uptodate(folio);
-	}
-
-	if (copied == 0)
-		goto out;
-
-	write_end_pos = pos + copied;
-
-	i_size = i_size_read(&vnode->netfs.inode);
-	if (write_end_pos > i_size) {
-		write_seqlock(&vnode->cb_lock);
-		i_size = i_size_read(&vnode->netfs.inode);
-		if (write_end_pos > i_size)
-			afs_set_i_size(vnode, write_end_pos);
-		write_sequnlock(&vnode->cb_lock);
-		fscache_update_cookie(afs_vnode_cache(vnode), NULL, &write_end_pos);
-	}
-
-	if (folio_mark_dirty(folio))
-		_debug("dirtied %lx", folio_index(folio));
-
-out:
-	folio_unlock(folio);
-	folio_put(folio);
-	return copied;
-}
-
-/*
- * kill all the pages in the given range
- */
-static void afs_kill_pages(struct address_space *mapping,
-			   loff_t start, loff_t len)
-{
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct folio *folio;
-	pgoff_t index = start / PAGE_SIZE;
-	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
-
-	_enter("{%llx:%llu},%llx @%llx",
-	       vnode->fid.vid, vnode->fid.vnode, len, start);
-
-	do {
-		_debug("kill %lx (to %lx)", index, last);
-
-		folio = filemap_get_folio(mapping, index);
-		if (IS_ERR(folio)) {
-			next = index + 1;
-			continue;
-		}
-
-		next = folio_next_index(folio);
-
-		folio_clear_uptodate(folio);
-		folio_end_writeback(folio);
-		folio_lock(folio);
-		generic_error_remove_page(mapping, &folio->page);
-		folio_unlock(folio);
-		folio_put(folio);
-
-	} while (index = next, index <= last);
-
-	_leave("");
-}
-
-/*
- * Redirty all the pages in a given range.
- */
-static void afs_redirty_pages(struct writeback_control *wbc,
-			      struct address_space *mapping,
-			      loff_t start, loff_t len)
-{
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct folio *folio;
-	pgoff_t index = start / PAGE_SIZE;
-	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
-
-	_enter("{%llx:%llu},%llx @%llx",
-	       vnode->fid.vid, vnode->fid.vnode, len, start);
-
-	do {
-		_debug("redirty %llx @%llx", len, start);
-
-		folio = filemap_get_folio(mapping, index);
-		if (IS_ERR(folio)) {
-			next = index + 1;
-			continue;
-		}
-
-		next = index + folio_nr_pages(folio);
-		folio_redirty_for_writepage(wbc, folio);
-		folio_end_writeback(folio);
-		folio_put(folio);
-	} while (index = next, index <= last);
-
-	_leave("");
-}
-
 /*
  * completion of write to server
  */
 static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len)
 {
-	struct address_space *mapping = vnode->netfs.inode.i_mapping;
-	struct folio *folio;
-	pgoff_t end;
-
-	XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
-
 	_enter("{%llx:%llu},{%x @%llx}",
 	       vnode->fid.vid, vnode->fid.vnode, len, start);
 
-	rcu_read_lock();
-
-	end = (start + len - 1) / PAGE_SIZE;
-	xas_for_each(&xas, folio, end) {
-		if (!folio_test_writeback(folio)) {
-			kdebug("bad %x @%llx page %lx %lx",
-			       len, start, folio_index(folio), end);
-			ASSERT(folio_test_writeback(folio));
-		}
-
-		trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio);
-		folio_end_writeback(folio);
-	}
-
-	rcu_read_unlock();
-
 	afs_prune_wb_keys(vnode);
 	_leave("");
 }
@@ -370,339 +159,53 @@ try_next_key:
 	return afs_put_operation(op);
 }
 
-/*
- * Extend the region to be written back to include subsequent contiguously
- * dirty pages if possible, but don't sleep while doing so.
- *
- * If this page holds new content, then we can include filler zeros in the
- * writeback.
- */
-static void afs_extend_writeback(struct address_space *mapping,
-				 struct afs_vnode *vnode,
-				 long *_count,
-				 loff_t start,
-				 loff_t max_len,
-				 bool caching,
-				 size_t *_len)
+static void afs_upload_to_server(struct netfs_io_subrequest *subreq)
 {
-	struct folio_batch fbatch;
-	struct folio *folio;
-	pgoff_t index = (start + *_len) / PAGE_SIZE;
-	bool stop = true;
-	unsigned int i;
-
-	XA_STATE(xas, &mapping->i_pages, index);
-	folio_batch_init(&fbatch);
-
-	do {
-		/* Firstly, we gather up a batch of contiguous dirty pages
-		 * under the RCU read lock - but we can't clear the dirty flags
-		 * there if any of those pages are mapped.
-		 */
-		rcu_read_lock();
-
-		xas_for_each(&xas, folio, ULONG_MAX) {
-			stop = true;
-			if (xas_retry(&xas, folio))
-				continue;
-			if (xa_is_value(folio))
-				break;
-			if (folio_index(folio) != index)
-				break;
-
-			if (!folio_try_get_rcu(folio)) {
-				xas_reset(&xas);
-				continue;
-			}
-
-			/* Has the folio moved or been split? */
-			if (unlikely(folio != xas_reload(&xas))) {
-				folio_put(folio);
-				break;
-			}
-
-			if (!folio_trylock(folio)) {
-				folio_put(folio);
-				break;
-			}
-			if (!folio_test_dirty(folio) ||
-			    folio_test_writeback(folio) ||
-			    folio_test_fscache(folio)) {
-				folio_unlock(folio);
-				folio_put(folio);
-				break;
-			}
-
-			index += folio_nr_pages(folio);
-			*_count -= folio_nr_pages(folio);
-			*_len += folio_size(folio);
-			stop = false;
-			if (*_len >= max_len || *_count <= 0)
-				stop = true;
-
-			if (!folio_batch_add(&fbatch, folio))
-				break;
-			if (stop)
-				break;
-		}
-
-		if (!stop)
-			xas_pause(&xas);
-		rcu_read_unlock();
-
-		/* Now, if we obtained any folios, we can shift them to being
-		 * writable and mark them for caching.
-		 */
-		if (!folio_batch_count(&fbatch))
-			break;
-
-		for (i = 0; i < folio_batch_count(&fbatch); i++) {
-			folio = fbatch.folios[i];
-			trace_afs_folio_dirty(vnode, tracepoint_string("store+"), folio);
+	struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode);
+	ssize_t ret;
 
-			if (!folio_clear_dirty_for_io(folio))
-				BUG();
-			if (folio_start_writeback(folio))
-				BUG();
-			afs_folio_start_fscache(caching, folio);
-			folio_unlock(folio);
-		}
+	_enter("%x[%x],%zx",
+	       subreq->rreq->debug_id, subreq->debug_index, subreq->io_iter.count);
 
-		folio_batch_release(&fbatch);
-		cond_resched();
-	} while (!stop);
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+	ret = afs_store_data(vnode, &subreq->io_iter, subreq->start,
+			     subreq->rreq->origin == NETFS_LAUNDER_WRITE);
+	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len,
+					  false);
 }
 
-/*
- * Synchronously write back the locked page and any subsequent non-locked dirty
- * pages.
- */
-static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
-						struct writeback_control *wbc,
-						struct folio *folio,
-						unsigned long long start,
-						unsigned long long end)
+static void afs_upload_to_server_worker(struct work_struct *work)
 {
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct iov_iter iter;
-	unsigned long long i_size = i_size_read(&vnode->netfs.inode);
-	size_t len, max_len;
-	bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode));
-	long count = wbc->nr_to_write;
-	int ret;
-
-	_enter(",%lx,%llx-%llx", folio_index(folio), start, end);
-
-	if (folio_start_writeback(folio))
-		BUG();
-	afs_folio_start_fscache(caching, folio);
-
-	count -= folio_nr_pages(folio);
-
-	/* Find all consecutive lockable dirty pages that have contiguous
-	 * written regions, stopping when we find a page that is not
-	 * immediately lockable, is not dirty or is missing, or we reach the
-	 * end of the range.
-	 */
-	trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio);
-
-	len = folio_size(folio);
-	if (start < i_size) {
-		/* Trim the write to the EOF; the extra data is ignored.  Also
-		 * put an upper limit on the size of a single storedata op.
-		 */
-		max_len = 65536 * 4096;
-		max_len = min_t(unsigned long long, max_len, end - start + 1);
-		max_len = min_t(unsigned long long, max_len, i_size - start);
-
-		if (len < max_len)
-			afs_extend_writeback(mapping, vnode, &count,
-					     start, max_len, caching, &len);
-		len = min_t(unsigned long long, len, i_size - start);
-	}
-
-	/* We now have a contiguous set of dirty pages, each with writeback
-	 * set; the first page is still locked at this point, but all the rest
-	 * have been unlocked.
-	 */
-	folio_unlock(folio);
-
-	if (start < i_size) {
-		_debug("write back %zx @%llx [%llx]", len, start, i_size);
-
-		/* Speculatively write to the cache.  We have to fix this up
-		 * later if the store fails.
-		 */
-		afs_write_to_cache(vnode, start, len, i_size, caching);
-
-		iov_iter_xarray(&iter, ITER_SOURCE, &mapping->i_pages, start, len);
-		ret = afs_store_data(vnode, &iter, start, false);
-	} else {
-		_debug("write discard %zx @%llx [%llx]", len, start, i_size);
-
-		/* The dirty region was entirely beyond the EOF. */
-		fscache_clear_page_bits(mapping, start, len, caching);
-		afs_pages_written_back(vnode, start, len);
-		ret = 0;
-	}
-
-	switch (ret) {
-	case 0:
-		wbc->nr_to_write = count;
-		ret = len;
-		break;
-
-	default:
-		pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret);
-		fallthrough;
-	case -EACCES:
-	case -EPERM:
-	case -ENOKEY:
-	case -EKEYEXPIRED:
-	case -EKEYREJECTED:
-	case -EKEYREVOKED:
-	case -ENETRESET:
-		afs_redirty_pages(wbc, mapping, start, len);
-		mapping_set_error(mapping, ret);
-		break;
-
-	case -EDQUOT:
-	case -ENOSPC:
-		afs_redirty_pages(wbc, mapping, start, len);
-		mapping_set_error(mapping, -ENOSPC);
-		break;
-
-	case -EROFS:
-	case -EIO:
-	case -EREMOTEIO:
-	case -EFBIG:
-	case -ENOENT:
-	case -ENOMEDIUM:
-	case -ENXIO:
-		trace_afs_file_error(vnode, ret, afs_file_error_writeback_fail);
-		afs_kill_pages(mapping, start, len);
-		mapping_set_error(mapping, ret);
-		break;
-	}
+	struct netfs_io_subrequest *subreq =
+		container_of(work, struct netfs_io_subrequest, work);
 
-	_leave(" = %d", ret);
-	return ret;
+	afs_upload_to_server(subreq);
 }
 
 /*
- * write a region of pages back to the server
+ * Set up write requests for a writeback slice.  We need to add a write request
+ * for each write we want to make.
  */
-static int afs_writepages_region(struct address_space *mapping,
-				 struct writeback_control *wbc,
-				 unsigned long long start,
-				 unsigned long long end, loff_t *_next,
-				 bool max_one_loop)
+void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len)
 {
-	struct folio *folio;
-	struct folio_batch fbatch;
-	ssize_t ret;
-	unsigned int i;
-	int n, skips = 0;
-
-	_enter("%llx,%llx,", start, end);
-	folio_batch_init(&fbatch);
+	struct netfs_io_subrequest *subreq;
 
-	do {
-		pgoff_t index = start / PAGE_SIZE;
+	_enter("%x,%llx-%llx", wreq->debug_id, start, start + len);
 
-		n = filemap_get_folios_tag(mapping, &index, end / PAGE_SIZE,
-					PAGECACHE_TAG_DIRTY, &fbatch);
-
-		if (!n)
-			break;
-		for (i = 0; i < n; i++) {
-			folio = fbatch.folios[i];
-			start = folio_pos(folio); /* May regress with THPs */
-
-			_debug("wback %lx", folio_index(folio));
-
-			/* At this point we hold neither the i_pages lock nor the
-			 * page lock: the page may be truncated or invalidated
-			 * (changing page->mapping to NULL), or even swizzled
-			 * back from swapper_space to tmpfs file mapping
-			 */
-try_again:
-			if (wbc->sync_mode != WB_SYNC_NONE) {
-				ret = folio_lock_killable(folio);
-				if (ret < 0) {
-					folio_batch_release(&fbatch);
-					return ret;
-				}
-			} else {
-				if (!folio_trylock(folio))
-					continue;
-			}
-
-			if (folio->mapping != mapping ||
-			    !folio_test_dirty(folio)) {
-				start += folio_size(folio);
-				folio_unlock(folio);
-				continue;
-			}
-
-			if (folio_test_writeback(folio) ||
-			    folio_test_fscache(folio)) {
-				folio_unlock(folio);
-				if (wbc->sync_mode != WB_SYNC_NONE) {
-					folio_wait_writeback(folio);
-#ifdef CONFIG_AFS_FSCACHE
-					folio_wait_fscache(folio);
-#endif
-					goto try_again;
-				}
-
-				start += folio_size(folio);
-				if (wbc->sync_mode == WB_SYNC_NONE) {
-					if (skips >= 5 || need_resched()) {
-						*_next = start;
-						folio_batch_release(&fbatch);
-						_leave(" = 0 [%llx]", *_next);
-						return 0;
-					}
-					skips++;
-				}
-				continue;
-			}
-
-			if (!folio_clear_dirty_for_io(folio))
-				BUG();
-			ret = afs_write_back_from_locked_folio(mapping, wbc,
-					folio, start, end);
-			if (ret < 0) {
-				_leave(" = %zd", ret);
-				folio_batch_release(&fbatch);
-				return ret;
-			}
-
-			start += ret;
-		}
-
-		folio_batch_release(&fbatch);
-		cond_resched();
-	} while (wbc->nr_to_write > 0);
-
-	*_next = start;
-	_leave(" = 0 [%llx]", *_next);
-	return 0;
+	subreq = netfs_create_write_request(wreq, NETFS_UPLOAD_TO_SERVER,
+					    start, len, afs_upload_to_server_worker);
+	if (subreq)
+		netfs_queue_write_request(subreq);
 }
 
 /*
  * write some of the pending data back to the server
  */
-int afs_writepages(struct address_space *mapping,
-		   struct writeback_control *wbc)
+int afs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	loff_t start, next;
 	int ret;
 
-	_enter("");
-
 	/* We have to be careful as we can end up racing with setattr()
 	 * truncating the pagecache since the caller doesn't take a lock here
 	 * to prevent it.
@@ -712,68 +215,11 @@ int afs_writepages(struct address_space *mapping,
 	else if (!down_read_trylock(&vnode->validate_lock))
 		return 0;
 
-	if (wbc->range_cyclic) {
-		start = mapping->writeback_index * PAGE_SIZE;
-		ret = afs_writepages_region(mapping, wbc, start, LLONG_MAX,
-					    &next, false);
-		if (ret == 0) {
-			mapping->writeback_index = next / PAGE_SIZE;
-			if (start > 0 && wbc->nr_to_write > 0) {
-				ret = afs_writepages_region(mapping, wbc, 0,
-							    start, &next, false);
-				if (ret == 0)
-					mapping->writeback_index =
-						next / PAGE_SIZE;
-			}
-		}
-	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
-		ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX,
-					    &next, false);
-		if (wbc->nr_to_write > 0 && ret == 0)
-			mapping->writeback_index = next / PAGE_SIZE;
-	} else {
-		ret = afs_writepages_region(mapping, wbc,
-					    wbc->range_start, wbc->range_end,
-					    &next, false);
-	}
-
+	ret = netfs_writepages(mapping, wbc);
 	up_read(&vnode->validate_lock);
-	_leave(" = %d", ret);
 	return ret;
 }
 
-/*
- * write to an AFS file
- */
-ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
-	struct afs_file *af = iocb->ki_filp->private_data;
-	ssize_t result;
-	size_t count = iov_iter_count(from);
-
-	_enter("{%llx:%llu},{%zu},",
-	       vnode->fid.vid, vnode->fid.vnode, count);
-
-	if (IS_SWAPFILE(&vnode->netfs.inode)) {
-		printk(KERN_INFO
-		       "AFS: Attempt to write to active swap file!\n");
-		return -EBUSY;
-	}
-
-	if (!count)
-		return 0;
-
-	result = afs_validate(vnode, af->key);
-	if (result < 0)
-		return result;
-
-	result = generic_file_write_iter(iocb, from);
-
-	_leave(" = %zd", result);
-	return result;
-}
-
 /*
  * flush any dirty pages for this process, and check for write errors.
  * - the return status from this call provides a reliable indication of
@@ -802,49 +248,11 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
  */
 vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 {
-	struct folio *folio = page_folio(vmf->page);
 	struct file *file = vmf->vma->vm_file;
-	struct inode *inode = file_inode(file);
-	struct afs_vnode *vnode = AFS_FS_I(inode);
-	struct afs_file *af = file->private_data;
-	vm_fault_t ret = VM_FAULT_RETRY;
-
-	_enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
-
-	afs_validate(vnode, af->key);
-
-	sb_start_pagefault(inode->i_sb);
-
-	/* Wait for the page to be written to the cache before we allow it to
-	 * be modified.  We then assume the entire page will need writing back.
-	 */
-#ifdef CONFIG_AFS_FSCACHE
-	if (folio_test_fscache(folio) &&
-	    folio_wait_fscache_killable(folio) < 0)
-		goto out;
-#endif
-
-	if (folio_wait_writeback_killable(folio))
-		goto out;
-
-	if (folio_lock_killable(folio) < 0)
-		goto out;
-
-	if (folio_wait_writeback_killable(folio) < 0) {
-		folio_unlock(folio);
-		goto out;
-	}
-
-	if (folio_test_dirty(folio))
-		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio);
-	else
-		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio);
-	file_update_time(file);
 
-	ret = VM_FAULT_LOCKED;
-out:
-	sb_end_pagefault(inode->i_sb);
-	return ret;
+	if (afs_validate(AFS_FS_I(file_inode(file)), afs_file_key(file)) < 0)
+		return VM_FAULT_SIGBUS;
+	return netfs_page_mkwrite(vmf, NULL);
 }
 
 /*
@@ -874,60 +282,3 @@ void afs_prune_wb_keys(struct afs_vnode *vnode)
 		afs_put_wb_key(wbk);
 	}
 }
-
-/*
- * Clean up a page during invalidation.
- */
-int afs_launder_folio(struct folio *folio)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-	struct iov_iter iter;
-	struct bio_vec bv;
-	unsigned long long fend, i_size = vnode->netfs.inode.i_size;
-	size_t len;
-	int ret = 0;
-
-	_enter("{%lx}", folio->index);
-
-	if (folio_clear_dirty_for_io(folio) && folio_pos(folio) < i_size) {
-		len = folio_size(folio);
-		fend = folio_pos(folio) + len;
-		if (vnode->netfs.inode.i_size < fend)
-			len = fend - i_size;
-
-		bvec_set_folio(&bv, folio, len, 0);
-		iov_iter_bvec(&iter, WRITE, &bv, 1, len);
-
-		trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio);
-		ret = afs_store_data(vnode, &iter, folio_pos(folio), true);
-	}
-
-	trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio);
-	folio_wait_fscache(folio);
-	return ret;
-}
-
-/*
- * Deal with the completion of writing the data to the cache.
- */
-static void afs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
-				    bool was_async)
-{
-	struct afs_vnode *vnode = priv;
-
-	if (IS_ERR_VALUE(transferred_or_error) &&
-	    transferred_or_error != -ENOBUFS)
-		afs_invalidate_cache(vnode, 0);
-}
-
-/*
- * Save the write to the cache also.
- */
-static void afs_write_to_cache(struct afs_vnode *vnode,
-			       loff_t start, size_t len, loff_t i_size,
-			       bool caching)
-{
-	fscache_write_to_cache(afs_vnode_cache(vnode),
-			       vnode->netfs.inode.i_mapping, start, len, i_size,
-			       afs_write_to_cache_done, vnode, caching);
-}
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 08506680350c8..7543581493722 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -837,29 +837,6 @@ TRACE_EVENT(afs_dir_check_failed,
 		      __entry->vnode, __entry->off, __entry->i_size)
 	    );
 
-TRACE_EVENT(afs_folio_dirty,
-	    TP_PROTO(struct afs_vnode *vnode, const char *where, struct folio *folio),
-
-	    TP_ARGS(vnode, where, folio),
-
-	    TP_STRUCT__entry(
-		    __field(struct afs_vnode *,		vnode)
-		    __field(const char *,		where)
-		    __field(pgoff_t,			index)
-		    __field(size_t,			size)
-			     ),
-
-	    TP_fast_assign(
-		    __entry->vnode = vnode;
-		    __entry->where = where;
-		    __entry->index = folio_index(folio);
-		    __entry->size = folio_size(folio);
-			   ),
-
-	    TP_printk("vn=%p ix=%05lx s=%05lx %s",
-		      __entry->vnode, __entry->index, __entry->size, __entry->where)
-	    );
-
 TRACE_EVENT(afs_call_state,
 	    TP_PROTO(struct afs_call *call,
 		     enum afs_call_state from,
-- 
GitLab


From 80105ed2fd2715fb09a8fdb0655a8bdc86c120db Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 6 Dec 2023 12:48:56 +0000
Subject: [PATCH 1979/4076] 9p: Use netfslib read/write_iter

Use netfslib's read and write iteration helpers, allowing netfslib to take
over the management of the page cache for 9p files and to manage local disk
caching.  In particular, this eliminates write_begin, write_end, writepage
and all mentions of struct page and struct folio from 9p.

Note that netfslib now offers the possibility of write-through caching if
that is desirable for 9p: just set the NETFS_ICTX_WRITETHROUGH flag in
v9inode->netfs.flags in v9fs_set_netfs_context().

Note also this is untested as I can't get ganesha.nfsd to correctly parse
the config to turn on 9p support.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Eric Van Hensbergen <ericvh@kernel.org>
cc: Latchesar Ionkov <lucho@ionkov.net>
cc: Dominique Martinet <asmadeus@codewreck.org>
cc: Christian Schoenebeck <linux_oss@crudebyte.com>
cc: v9fs@lists.linux.dev
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
---
 fs/9p/vfs_addr.c       | 293 ++++++++++-------------------------------
 fs/9p/vfs_file.c       |  89 ++-----------
 fs/9p/vfs_inode.c      |   5 +-
 fs/9p/vfs_inode_dotl.c |   7 +-
 4 files changed, 85 insertions(+), 309 deletions(-)

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 055b672a247d7..d8fb407189a09 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -19,12 +19,48 @@
 #include <linux/netfs.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
+#include <trace/events/netfs.h>
 
 #include "v9fs.h"
 #include "v9fs_vfs.h"
 #include "cache.h"
 #include "fid.h"
 
+static void v9fs_upload_to_server(struct netfs_io_subrequest *subreq)
+{
+	struct inode *inode = subreq->rreq->inode;
+	struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode);
+	struct p9_fid *fid = subreq->rreq->netfs_priv;
+	int err;
+
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+	p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
+	netfs_write_subrequest_terminated(subreq, err < 0 ? err : subreq->len,
+					  false);
+}
+
+static void v9fs_upload_to_server_worker(struct work_struct *work)
+{
+	struct netfs_io_subrequest *subreq =
+		container_of(work, struct netfs_io_subrequest, work);
+
+	v9fs_upload_to_server(subreq);
+}
+
+/*
+ * Set up write requests for a writeback slice.  We need to add a write request
+ * for each write we want to make.
+ */
+static void v9fs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len)
+{
+	struct netfs_io_subrequest *subreq;
+
+	subreq = netfs_create_write_request(wreq, NETFS_UPLOAD_TO_SERVER,
+					    start, len, v9fs_upload_to_server_worker);
+	if (subreq)
+		netfs_queue_write_request(subreq);
+}
+
 /**
  * v9fs_issue_read - Issue a read from 9P
  * @subreq: The read to make
@@ -33,14 +69,10 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *rreq = subreq->rreq;
 	struct p9_fid *fid = rreq->netfs_priv;
-	struct iov_iter to;
-	loff_t pos = subreq->start + subreq->transferred;
-	size_t len = subreq->len   - subreq->transferred;
 	int total, err;
 
-	iov_iter_xarray(&to, ITER_DEST, &rreq->mapping->i_pages, pos, len);
-
-	total = p9_client_read(fid, pos, &to, &err);
+	total = p9_client_read(fid, subreq->start + subreq->transferred,
+			       &subreq->io_iter, &err);
 
 	/* if we just extended the file size, any portion not in
 	 * cache won't be on server and is zeroes */
@@ -50,23 +82,37 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
 }
 
 /**
- * v9fs_init_request - Initialise a read request
+ * v9fs_init_request - Initialise a request
  * @rreq: The read request
  * @file: The file being read from
  */
 static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file)
 {
-	struct p9_fid *fid = file->private_data;
-
-	BUG_ON(!fid);
+	struct p9_fid *fid;
+	bool writing = (rreq->origin == NETFS_READ_FOR_WRITE ||
+			rreq->origin == NETFS_WRITEBACK ||
+			rreq->origin == NETFS_WRITETHROUGH ||
+			rreq->origin == NETFS_LAUNDER_WRITE ||
+			rreq->origin == NETFS_UNBUFFERED_WRITE ||
+			rreq->origin == NETFS_DIO_WRITE);
+
+	if (file) {
+		fid = file->private_data;
+		BUG_ON(!fid);
+		p9_fid_get(fid);
+	} else {
+		fid = v9fs_fid_find_inode(rreq->inode, writing, INVALID_UID, true);
+		if (!fid) {
+			WARN_ONCE(1, "folio expected an open fid inode->i_private=%p\n",
+				  rreq->inode->i_private);
+			return -EINVAL;
+		}
+	}
 
 	/* we might need to read from a fid that was opened write-only
 	 * for read-modify-write of page cache, use the writeback fid
 	 * for that */
-	WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE &&
-			!(fid->mode & P9_ORDWR));
-
-	p9_fid_get(fid);
+	WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE && !(fid->mode & P9_ORDWR));
 	rreq->netfs_priv = fid;
 	return 0;
 }
@@ -86,217 +132,16 @@ const struct netfs_request_ops v9fs_req_ops = {
 	.init_request		= v9fs_init_request,
 	.free_request		= v9fs_free_request,
 	.issue_read		= v9fs_issue_read,
+	.create_write_requests	= v9fs_create_write_requests,
 };
 
-#ifdef CONFIG_9P_FSCACHE
-static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
-				     bool was_async)
-{
-	struct v9fs_inode *v9inode = priv;
-	__le32 version;
-
-	if (IS_ERR_VALUE(transferred_or_error) &&
-	    transferred_or_error != -ENOBUFS) {
-		version = cpu_to_le32(v9inode->qid.version);
-		fscache_invalidate(v9fs_inode_cookie(v9inode), &version,
-				   i_size_read(&v9inode->netfs.inode), 0);
-	}
-}
-#endif
-
-static int v9fs_vfs_write_folio_locked(struct folio *folio)
-{
-	struct inode *inode = folio_inode(folio);
-	loff_t start = folio_pos(folio);
-	loff_t i_size = i_size_read(inode);
-	struct iov_iter from;
-	size_t len = folio_size(folio);
-	struct p9_fid *writeback_fid;
-	int err;
-	struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode);
-	struct fscache_cookie __maybe_unused *cookie = v9fs_inode_cookie(v9inode);
-
-	if (start >= i_size)
-		return 0; /* Simultaneous truncation occurred */
-
-	len = min_t(loff_t, i_size - start, len);
-
-	iov_iter_xarray(&from, ITER_SOURCE, &folio_mapping(folio)->i_pages, start, len);
-
-	writeback_fid = v9fs_fid_find_inode(inode, true, INVALID_UID, true);
-	if (!writeback_fid) {
-		WARN_ONCE(1, "folio expected an open fid inode->i_private=%p\n",
-			inode->i_private);
-		return -EINVAL;
-	}
-
-	folio_wait_fscache(folio);
-	folio_start_writeback(folio);
-
-	p9_client_write(writeback_fid, start, &from, &err);
-
-#ifdef CONFIG_9P_FSCACHE
-	if (err == 0 &&
-		fscache_cookie_enabled(cookie) &&
-		test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) {
-		folio_start_fscache(folio);
-		fscache_write_to_cache(v9fs_inode_cookie(v9inode),
-					folio_mapping(folio), start, len, i_size,
-					v9fs_write_to_cache_done, v9inode,
-					true);
-	}
-#endif
-
-	folio_end_writeback(folio);
-	p9_fid_put(writeback_fid);
-
-	return err;
-}
-
-static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-	int retval;
-
-	p9_debug(P9_DEBUG_VFS, "folio %p\n", folio);
-
-	retval = v9fs_vfs_write_folio_locked(folio);
-	if (retval < 0) {
-		if (retval == -EAGAIN) {
-			folio_redirty_for_writepage(wbc, folio);
-			retval = 0;
-		} else {
-			mapping_set_error(folio_mapping(folio), retval);
-		}
-	} else
-		retval = 0;
-
-	folio_unlock(folio);
-	return retval;
-}
-
-static int v9fs_launder_folio(struct folio *folio)
-{
-	int retval;
-
-	if (folio_clear_dirty_for_io(folio)) {
-		retval = v9fs_vfs_write_folio_locked(folio);
-		if (retval)
-			return retval;
-	}
-	folio_wait_fscache(folio);
-	return 0;
-}
-
-/**
- * v9fs_direct_IO - 9P address space operation for direct I/O
- * @iocb: target I/O control block
- * @iter: The data/buffer to use
- *
- * The presence of v9fs_direct_IO() in the address space ops vector
- * allowes open() O_DIRECT flags which would have failed otherwise.
- *
- * In the non-cached mode, we shunt off direct read and write requests before
- * the VFS gets them, so this method should never be called.
- *
- * Direct IO is not 'yet' supported in the cached mode. Hence when
- * this routine is called through generic_file_aio_read(), the read/write fails
- * with an error.
- *
- */
-static ssize_t
-v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct file *file = iocb->ki_filp;
-	loff_t pos = iocb->ki_pos;
-	ssize_t n;
-	int err = 0;
-
-	if (iov_iter_rw(iter) == WRITE) {
-		n = p9_client_write(file->private_data, pos, iter, &err);
-		if (n) {
-			struct inode *inode = file_inode(file);
-			loff_t i_size = i_size_read(inode);
-
-			if (pos + n > i_size)
-				inode_add_bytes(inode, pos + n - i_size);
-		}
-	} else {
-		n = p9_client_read(file->private_data, pos, iter, &err);
-	}
-	return n ? n : err;
-}
-
-static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
-			    loff_t pos, unsigned int len,
-			    struct page **subpagep, void **fsdata)
-{
-	int retval;
-	struct folio *folio;
-	struct v9fs_inode *v9inode = V9FS_I(mapping->host);
-
-	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
-
-	/* Prefetch area to be written into the cache if we're caching this
-	 * file.  We need to do this before we get a lock on the page in case
-	 * there's more than one writer competing for the same cache block.
-	 */
-	retval = netfs_write_begin(&v9inode->netfs, filp, mapping, pos, len, &folio, fsdata);
-	if (retval < 0)
-		return retval;
-
-	*subpagep = &folio->page;
-	return retval;
-}
-
-static int v9fs_write_end(struct file *filp, struct address_space *mapping,
-			  loff_t pos, unsigned int len, unsigned int copied,
-			  struct page *subpage, void *fsdata)
-{
-	loff_t last_pos = pos + copied;
-	struct folio *folio = page_folio(subpage);
-	struct inode *inode = mapping->host;
-
-	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
-
-	if (!folio_test_uptodate(folio)) {
-		if (unlikely(copied < len)) {
-			copied = 0;
-			goto out;
-		}
-
-		folio_mark_uptodate(folio);
-	}
-
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold the i_mutex.
-	 */
-	if (last_pos > inode->i_size) {
-		inode_add_bytes(inode, last_pos - inode->i_size);
-		i_size_write(inode, last_pos);
-#ifdef CONFIG_9P_FSCACHE
-		fscache_update_cookie(v9fs_inode_cookie(V9FS_I(inode)), NULL,
-			&last_pos);
-#endif
-	}
-	folio_mark_dirty(folio);
-out:
-	folio_unlock(folio);
-	folio_put(folio);
-
-	return copied;
-}
-
 const struct address_space_operations v9fs_addr_operations = {
-	.read_folio	= netfs_read_folio,
-	.readahead	= netfs_readahead,
-	.dirty_folio	= netfs_dirty_folio,
-	.writepage	= v9fs_vfs_writepage,
-	.write_begin	= v9fs_write_begin,
-	.write_end	= v9fs_write_end,
-	.release_folio	= netfs_release_folio,
-	.invalidate_folio = netfs_invalidate_folio,
-	.launder_folio	= v9fs_launder_folio,
-	.direct_IO	= v9fs_direct_IO,
+	.read_folio		= netfs_read_folio,
+	.readahead		= netfs_readahead,
+	.dirty_folio		= netfs_dirty_folio,
+	.release_folio		= netfs_release_folio,
+	.invalidate_folio	= netfs_invalidate_folio,
+	.launder_folio		= netfs_launder_folio,
+	.direct_IO		= noop_direct_IO,
+	.writepages		= netfs_writepages,
 };
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 11cd8d23f6f23..bae330c2f0cf0 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -353,25 +353,15 @@ static ssize_t
 v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct p9_fid *fid = iocb->ki_filp->private_data;
-	int ret, err = 0;
 
 	p9_debug(P9_DEBUG_VFS, "fid %d count %zu offset %lld\n",
 		 fid->fid, iov_iter_count(to), iocb->ki_pos);
 
-	if (!(fid->mode & P9L_DIRECT)) {
-		p9_debug(P9_DEBUG_VFS, "(cached)\n");
-		return generic_file_read_iter(iocb, to);
-	}
-
-	if (iocb->ki_filp->f_flags & O_NONBLOCK)
-		ret = p9_client_read_once(fid, iocb->ki_pos, to, &err);
-	else
-		ret = p9_client_read(fid, iocb->ki_pos, to, &err);
-	if (!ret)
-		return err;
+	if (fid->mode & P9L_DIRECT)
+		return netfs_unbuffered_read_iter(iocb, to);
 
-	iocb->ki_pos += ret;
-	return ret;
+	p9_debug(P9_DEBUG_VFS, "(cached)\n");
+	return netfs_file_read_iter(iocb, to);
 }
 
 /*
@@ -407,46 +397,14 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct p9_fid *fid = file->private_data;
-	ssize_t retval;
-	loff_t origin;
-	int err = 0;
 
 	p9_debug(P9_DEBUG_VFS, "fid %d\n", fid->fid);
 
-	if (!(fid->mode & (P9L_DIRECT | P9L_NOWRITECACHE))) {
-		p9_debug(P9_DEBUG_CACHE, "(cached)\n");
-		return generic_file_write_iter(iocb, from);
-	}
+	if (fid->mode & (P9L_DIRECT | P9L_NOWRITECACHE))
+		return netfs_unbuffered_write_iter(iocb, from);
 
-	retval = generic_write_checks(iocb, from);
-	if (retval <= 0)
-		return retval;
-
-	origin = iocb->ki_pos;
-	retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err);
-	if (retval > 0) {
-		struct inode *inode = file_inode(file);
-		loff_t i_size;
-		unsigned long pg_start, pg_end;
-
-		pg_start = origin >> PAGE_SHIFT;
-		pg_end = (origin + retval - 1) >> PAGE_SHIFT;
-		if (inode->i_mapping && inode->i_mapping->nrpages)
-			invalidate_inode_pages2_range(inode->i_mapping,
-						      pg_start, pg_end);
-		iocb->ki_pos += retval;
-		i_size = i_size_read(inode);
-		if (iocb->ki_pos > i_size) {
-			inode_add_bytes(inode, iocb->ki_pos - i_size);
-			/*
-			 * Need to serialize against i_size_write() in
-			 * v9fs_stat2inode()
-			 */
-			v9fs_i_size_write(inode, iocb->ki_pos);
-		}
-		return retval;
-	}
-	return err;
+	p9_debug(P9_DEBUG_CACHE, "(cached)\n");
+	return netfs_file_write_iter(iocb, from);
 }
 
 static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end,
@@ -519,36 +477,7 @@ v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma)
 static vm_fault_t
 v9fs_vm_page_mkwrite(struct vm_fault *vmf)
 {
-	struct folio *folio = page_folio(vmf->page);
-	struct file *filp = vmf->vma->vm_file;
-	struct inode *inode = file_inode(filp);
-
-
-	p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n",
-		 folio, (unsigned long)filp->private_data);
-
-	/* Wait for the page to be written to the cache before we allow it to
-	 * be modified.  We then assume the entire page will need writing back.
-	 */
-#ifdef CONFIG_9P_FSCACHE
-	if (folio_test_fscache(folio) &&
-	    folio_wait_fscache_killable(folio) < 0)
-		return VM_FAULT_NOPAGE;
-#endif
-
-	/* Update file times before taking page lock */
-	file_update_time(filp);
-
-	if (folio_lock_killable(folio) < 0)
-		return VM_FAULT_RETRY;
-	if (folio_mapping(folio) != inode->i_mapping)
-		goto out_unlock;
-	folio_wait_stable(folio);
-
-	return VM_FAULT_LOCKED;
-out_unlock:
-	folio_unlock(folio);
-	return VM_FAULT_NOPAGE;
+	return netfs_page_mkwrite(vmf, NULL);
 }
 
 static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index df7ae381a7088..b66466e97459c 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -374,10 +374,8 @@ void v9fs_evict_inode(struct inode *inode)
 
 	truncate_inode_pages_final(&inode->i_data);
 
-#ifdef CONFIG_9P_FSCACHE
 	version = cpu_to_le32(v9inode->qid.version);
 	netfs_clear_inode_writeback(inode, &version);
-#endif
 
 	clear_inode(inode);
 	filemap_fdatawrite(&inode->i_data);
@@ -1112,7 +1110,7 @@ static int v9fs_vfs_setattr(struct mnt_idmap *idmap,
 	if ((iattr->ia_valid & ATTR_SIZE) &&
 		 iattr->ia_size != i_size_read(inode)) {
 		truncate_setsize(inode, iattr->ia_size);
-		truncate_pagecache(inode, iattr->ia_size);
+		netfs_resize_file(netfs_inode(inode), iattr->ia_size, true);
 
 #ifdef CONFIG_9P_FSCACHE
 		if (v9ses->cache & CACHE_FSCACHE) {
@@ -1180,6 +1178,7 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 	mode |= inode->i_mode & ~S_IALLUGO;
 	inode->i_mode = mode;
 
+	v9inode->netfs.remote_i_size = stat->length;
 	if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
 		v9fs_i_size_write(inode, stat->length);
 	/* not real number of blocks, but 512 byte ones ... */
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index c7319af2f4711..e25fbc988f095 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -598,7 +598,7 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap,
 	if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size !=
 		 i_size_read(inode)) {
 		truncate_setsize(inode, iattr->ia_size);
-		truncate_pagecache(inode, iattr->ia_size);
+		netfs_resize_file(netfs_inode(inode), iattr->ia_size, true);
 
 #ifdef CONFIG_9P_FSCACHE
 		if (v9ses->cache & CACHE_FSCACHE)
@@ -655,6 +655,7 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
 		mode |= inode->i_mode & ~S_IALLUGO;
 		inode->i_mode = mode;
 
+		v9inode->netfs.remote_i_size = stat->st_size;
 		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
 			v9fs_i_size_write(inode, stat->st_size);
 		inode->i_blocks = stat->st_blocks;
@@ -683,8 +684,10 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
 			inode->i_mode = mode;
 		}
 		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) &&
-		    stat->st_result_mask & P9_STATS_SIZE)
+		    stat->st_result_mask & P9_STATS_SIZE) {
+			v9inode->netfs.remote_i_size = stat->st_size;
 			v9fs_i_size_write(inode, stat->st_size);
+		}
 		if (stat->st_result_mask & P9_STATS_BLOCKS)
 			inode->i_blocks = stat->st_blocks;
 	}
-- 
GitLab


From 1b09c2b8f849079220a9a9ddf961582f00bdc2c4 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 23 Dec 2023 20:19:02 +0100
Subject: [PATCH 1980/4076] pinctrl: samsung: constify iomem pointers

Constify few pointers to iomem, where the destination memory is not
modified, for code safety and readability.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Link: https://lore.kernel.org/r/20231223191902.22857-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/samsung/pinctrl-exynos.c  | 4 ++--
 drivers/pinctrl/samsung/pinctrl-samsung.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index d3d4b5d036c88..871c1eb46ddfd 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -693,7 +693,7 @@ static void exynos_pinctrl_suspend_bank(
 				struct samsung_pin_bank *bank)
 {
 	struct exynos_eint_gpio_save *save = bank->soc_priv;
-	void __iomem *regs = bank->eint_base;
+	const void __iomem *regs = bank->eint_base;
 
 	save->eint_con = readl(regs + EXYNOS_GPIO_ECON_OFFSET
 						+ bank->eint_offset);
@@ -714,7 +714,7 @@ static void exynosauto_pinctrl_suspend_bank(struct samsung_pinctrl_drv_data *drv
 					    struct samsung_pin_bank *bank)
 {
 	struct exynos_eint_gpio_save *save = bank->soc_priv;
-	void __iomem *regs = bank->eint_base;
+	const void __iomem *regs = bank->eint_base;
 
 	save->eint_con = readl(regs + bank->pctl_offset + bank->eint_con_offset);
 	save->eint_mask = readl(regs + bank->pctl_offset + bank->eint_mask_offset);
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index dbf38767f15f0..ed07e23e09122 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -565,7 +565,7 @@ static void samsung_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
 /* gpiolib gpio_get callback function */
 static int samsung_gpio_get(struct gpio_chip *gc, unsigned offset)
 {
-	void __iomem *reg;
+	const void __iomem *reg;
 	u32 data;
 	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
 	const struct samsung_pin_bank_type *type = bank->type;
@@ -1204,7 +1204,7 @@ static int __maybe_unused samsung_pinctrl_suspend(struct device *dev)
 
 	for (i = 0; i < drvdata->nr_banks; i++) {
 		struct samsung_pin_bank *bank = &drvdata->pin_banks[i];
-		void __iomem *reg = bank->pctl_base + bank->pctl_offset;
+		const void __iomem *reg = bank->pctl_base + bank->pctl_offset;
 		const u8 *offs = bank->type->reg_offset;
 		const u8 *widths = bank->type->fld_width;
 		enum pincfg_type type;
-- 
GitLab


From 9ca65c373f4451fdf2f82ebc30b17185253aec8f Mon Sep 17 00:00:00 2001
From: attreyee-muk <tintinm2017@gmail.com>
Date: Sun, 24 Dec 2023 00:17:20 +0530
Subject: [PATCH 1981/4076] docs: PCI: Fix typos

Fix typos in PCI docs.

Link: https://lore.kernel.org/r/20231223184720.25645-1-tintinm2017@gmail.com
Link: https://lore.kernel.org/r/20231223184412.25598-1-tintinm2017@gmail.com
Signed-off-by: Attreyee Mukherjee <tintinm2017@gmail.com>
[bhelgaas: squashed, commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>  # for "busses" only
---
 Documentation/PCI/boot-interrupts.rst | 2 +-
 Documentation/PCI/msi-howto.rst       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/PCI/boot-interrupts.rst b/Documentation/PCI/boot-interrupts.rst
index 2ec70121bfca5..931077bb09535 100644
--- a/Documentation/PCI/boot-interrupts.rst
+++ b/Documentation/PCI/boot-interrupts.rst
@@ -61,7 +61,7 @@ Conditions
 ==========
 
 The use of threaded interrupts is the most likely condition to trigger
-this problem today. Threaded interrupts may not be reenabled after the IRQ
+this problem today. Threaded interrupts may not be re-enabled after the IRQ
 handler wakes. These "one shot" conditions mean that the threaded interrupt
 needs to keep the interrupt line masked until the threaded handler has run.
 Especially when dealing with high data rate interrupts, the thread needs to
diff --git a/Documentation/PCI/msi-howto.rst b/Documentation/PCI/msi-howto.rst
index c9400f02333bf..783d30b7bb428 100644
--- a/Documentation/PCI/msi-howto.rst
+++ b/Documentation/PCI/msi-howto.rst
@@ -236,7 +236,7 @@ including a full 'lspci -v' so we can add the quirks to the kernel.
 Disabling MSIs below a bridge
 -----------------------------
 
-Some PCI bridges are not able to route MSIs between busses properly.
+Some PCI bridges are not able to route MSIs between buses properly.
 In this case, MSIs must be disabled on all devices behind the bridge.
 
 Some bridges allow you to enable MSIs by changing some bits in their
-- 
GitLab


From 683c5bbbf6aea247bc95a7eb9fdfba4fcc8c909a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 24 Oct 2023 15:26:54 +0200
Subject: [PATCH 1982/4076] riscv: kvm: Use SYM_*() assembly macros instead of
 deprecated ones
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ENTRY()/END()/WEAK() macros are deprecated and we should make use of the
new SYM_*() macros [1] for better annotation of symbols. Replace the
deprecated ones with the new ones and fix wrong usage of END()/ENDPROC()
to correctly describe the symbols.

[1] https://docs.kernel.org/core-api/asm-annotations.html

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_switch.S | 28 ++++++++++++----------------
 1 file changed, 12 insertions(+), 16 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
index d74df8eb4d71a..8b18473780ace 100644
--- a/arch/riscv/kvm/vcpu_switch.S
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -15,7 +15,7 @@
 	.altmacro
 	.option norelax
 
-ENTRY(__kvm_riscv_switch_to)
+SYM_FUNC_START(__kvm_riscv_switch_to)
 	/* Save Host GPRs (except A0 and T0-T6) */
 	REG_S	ra, (KVM_ARCH_HOST_RA)(a0)
 	REG_S	sp, (KVM_ARCH_HOST_SP)(a0)
@@ -208,9 +208,9 @@ __kvm_switch_return:
 
 	/* Return to C code */
 	ret
-ENDPROC(__kvm_riscv_switch_to)
+SYM_FUNC_END(__kvm_riscv_switch_to)
 
-ENTRY(__kvm_riscv_unpriv_trap)
+SYM_CODE_START(__kvm_riscv_unpriv_trap)
 	/*
 	 * We assume that faulting unpriv load/store instruction is
 	 * 4-byte long and blindly increment SEPC by 4.
@@ -231,12 +231,10 @@ ENTRY(__kvm_riscv_unpriv_trap)
 	csrr	a1, CSR_HTINST
 	REG_S	a1, (KVM_ARCH_TRAP_HTINST)(a0)
 	sret
-ENDPROC(__kvm_riscv_unpriv_trap)
+SYM_CODE_END(__kvm_riscv_unpriv_trap)
 
 #ifdef	CONFIG_FPU
-	.align 3
-	.global __kvm_riscv_fp_f_save
-__kvm_riscv_fp_f_save:
+SYM_FUNC_START(__kvm_riscv_fp_f_save)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	csrs CSR_SSTATUS, t1
@@ -276,10 +274,9 @@ __kvm_riscv_fp_f_save:
 	sw t0, KVM_ARCH_FP_F_FCSR(a0)
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_f_save)
 
-	.align 3
-	.global __kvm_riscv_fp_d_save
-__kvm_riscv_fp_d_save:
+SYM_FUNC_START(__kvm_riscv_fp_d_save)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	csrs CSR_SSTATUS, t1
@@ -319,10 +316,9 @@ __kvm_riscv_fp_d_save:
 	sw t0, KVM_ARCH_FP_D_FCSR(a0)
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_d_save)
 
-	.align 3
-	.global __kvm_riscv_fp_f_restore
-__kvm_riscv_fp_f_restore:
+SYM_FUNC_START(__kvm_riscv_fp_f_restore)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	lw t0, KVM_ARCH_FP_F_FCSR(a0)
@@ -362,10 +358,9 @@ __kvm_riscv_fp_f_restore:
 	fscsr t0
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_f_restore)
 
-	.align 3
-	.global __kvm_riscv_fp_d_restore
-__kvm_riscv_fp_d_restore:
+SYM_FUNC_START(__kvm_riscv_fp_d_restore)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	lw t0, KVM_ARCH_FP_D_FCSR(a0)
@@ -405,4 +400,5 @@ __kvm_riscv_fp_d_restore:
 	fscsr t0
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_d_restore)
 #endif
-- 
GitLab


From e5ff012743cbc3cf13d2243aaaf032a2ca4d0791 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Tue, 24 Oct 2023 15:26:55 +0200
Subject: [PATCH 1983/4076] riscv: kvm: use ".L" local labels in assembly when
 applicable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For the sake of coherency, use local labels in assembly when
applicable. This also avoid kprobes being confused when applying a
kprobe since the size of function is computed by checking where the
next visible symbol is located. This might end up in computing some
function size to be way shorter than expected and thus failing to apply
kprobes to the specified offset.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_switch.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
index 8b18473780ace..0c26189aa01cf 100644
--- a/arch/riscv/kvm/vcpu_switch.S
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -45,7 +45,7 @@ SYM_FUNC_START(__kvm_riscv_switch_to)
 	REG_L	t0, (KVM_ARCH_GUEST_SSTATUS)(a0)
 	REG_L	t1, (KVM_ARCH_GUEST_HSTATUS)(a0)
 	REG_L	t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
-	la	t4, __kvm_switch_return
+	la	t4, .Lkvm_switch_return
 	REG_L	t5, (KVM_ARCH_GUEST_SEPC)(a0)
 
 	/* Save Host and Restore Guest SSTATUS */
@@ -113,7 +113,7 @@ SYM_FUNC_START(__kvm_riscv_switch_to)
 
 	/* Back to Host */
 	.align 2
-__kvm_switch_return:
+.Lkvm_switch_return:
 	/* Swap Guest A0 with SSCRATCH */
 	csrrw	a0, CSR_SSCRATCH, a0
 
-- 
GitLab


From bcd08e9bae57b5585e438b7fa58aba4b145a59cf Mon Sep 17 00:00:00 2001
From: Chao Du <duchao@eswincomputing.com>
Date: Mon, 11 Dec 2023 09:40:14 +0000
Subject: [PATCH 1984/4076] RISC-V: KVM: remove a redundant condition in
 kvm_arch_vcpu_ioctl_run()

The latest ret value is updated by kvm_riscv_vcpu_aia_update(),
the loop will continue if the ret is less than or equal to zero.
So the later condition will never hit. Thus remove it.

Signed-off-by: Chao Du <duchao@eswincomputing.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index e087c809073c1..bf3952d1a621f 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -757,8 +757,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		/* Update HVIP CSR for current CPU */
 		kvm_riscv_update_hvip(vcpu);
 
-		if (ret <= 0 ||
-		    kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
+		if (kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
 		    kvm_request_pending(vcpu) ||
 		    xfer_to_guest_mode_work_pending()) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
-- 
GitLab


From c19829ba1e4d119e69b1ac9a96d5a0b86f7233e9 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Tue, 28 Nov 2023 20:23:43 +0530
Subject: [PATCH 1985/4076] KVM: riscv: selftests: Generate ISA extension
 reg_list using macros

Various ISA extension reg_list have common pattern so let us generate
these using macros.

We define two macros for the above purpose:
1) KVM_ISA_EXT_SIMPLE_CONFIG - Macro to generate reg_list for
   ISA extension without any additional ONE_REG registers
2) KVM_ISA_EXT_SUBLIST_CONFIG - Macro to generate reg_list for
   ISA extension with additional ONE_REG registers

This patch also adds the missing config for svnapot.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/riscv/get-reg-list.c        | 331 ++++--------------
 1 file changed, 76 insertions(+), 255 deletions(-)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 25de4b8bc3472..5d86c761784e6 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -583,10 +583,6 @@ static __u64 base_skips_set[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state),
 };
 
-static __u64 h_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H,
-};
-
 static __u64 zicbom_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM,
@@ -597,54 +593,6 @@ static __u64 zicboz_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ,
 };
 
-static __u64 svpbmt_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT,
-};
-
-static __u64 sstc_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC,
-};
-
-static __u64 svinval_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL,
-};
-
-static __u64 zihintpause_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE,
-};
-
-static __u64 zba_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA,
-};
-
-static __u64 zbb_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB,
-};
-
-static __u64 zbs_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS,
-};
-
-static __u64 zicntr_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR,
-};
-
-static __u64 zicond_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICOND,
-};
-
-static __u64 zicsr_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR,
-};
-
-static __u64 zifencei_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI,
-};
-
-static __u64 zihpm_regs[] = {
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM,
-};
-
 static __u64 aia_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1),
@@ -735,221 +683,94 @@ static __u64 fp_d_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D,
 };
 
-#define BASE_SUBLIST \
+#define SUBLIST_BASE \
 	{"base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), \
 	 .skips_set = base_skips_set, .skips_set_n = ARRAY_SIZE(base_skips_set),}
-#define H_REGS_SUBLIST \
-	{"h", .feature = KVM_RISCV_ISA_EXT_H, .regs = h_regs, .regs_n = ARRAY_SIZE(h_regs),}
-#define ZICBOM_REGS_SUBLIST \
+#define SUBLIST_ZICBOM \
 	{"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),}
-#define ZICBOZ_REGS_SUBLIST \
+#define SUBLIST_ZICBOZ \
 	{"zicboz", .feature = KVM_RISCV_ISA_EXT_ZICBOZ, .regs = zicboz_regs, .regs_n = ARRAY_SIZE(zicboz_regs),}
-#define SVPBMT_REGS_SUBLIST \
-	{"svpbmt", .feature = KVM_RISCV_ISA_EXT_SVPBMT, .regs = svpbmt_regs, .regs_n = ARRAY_SIZE(svpbmt_regs),}
-#define SSTC_REGS_SUBLIST \
-	{"sstc", .feature = KVM_RISCV_ISA_EXT_SSTC, .regs = sstc_regs, .regs_n = ARRAY_SIZE(sstc_regs),}
-#define SVINVAL_REGS_SUBLIST \
-	{"svinval", .feature = KVM_RISCV_ISA_EXT_SVINVAL, .regs = svinval_regs, .regs_n = ARRAY_SIZE(svinval_regs),}
-#define ZIHINTPAUSE_REGS_SUBLIST \
-	{"zihintpause", .feature = KVM_RISCV_ISA_EXT_ZIHINTPAUSE, .regs = zihintpause_regs, .regs_n = ARRAY_SIZE(zihintpause_regs),}
-#define ZBA_REGS_SUBLIST \
-	{"zba", .feature = KVM_RISCV_ISA_EXT_ZBA, .regs = zba_regs, .regs_n = ARRAY_SIZE(zba_regs),}
-#define ZBB_REGS_SUBLIST \
-	{"zbb", .feature = KVM_RISCV_ISA_EXT_ZBB, .regs = zbb_regs, .regs_n = ARRAY_SIZE(zbb_regs),}
-#define ZBS_REGS_SUBLIST \
-	{"zbs", .feature = KVM_RISCV_ISA_EXT_ZBS, .regs = zbs_regs, .regs_n = ARRAY_SIZE(zbs_regs),}
-#define ZICNTR_REGS_SUBLIST \
-	{"zicntr", .feature = KVM_RISCV_ISA_EXT_ZICNTR, .regs = zicntr_regs, .regs_n = ARRAY_SIZE(zicntr_regs),}
-#define ZICOND_REGS_SUBLIST \
-	{"zicond", .feature = KVM_RISCV_ISA_EXT_ZICOND, .regs = zicond_regs, .regs_n = ARRAY_SIZE(zicond_regs),}
-#define ZICSR_REGS_SUBLIST \
-	{"zicsr", .feature = KVM_RISCV_ISA_EXT_ZICSR, .regs = zicsr_regs, .regs_n = ARRAY_SIZE(zicsr_regs),}
-#define ZIFENCEI_REGS_SUBLIST \
-	{"zifencei", .feature = KVM_RISCV_ISA_EXT_ZIFENCEI, .regs = zifencei_regs, .regs_n = ARRAY_SIZE(zifencei_regs),}
-#define ZIHPM_REGS_SUBLIST \
-	{"zihpm", .feature = KVM_RISCV_ISA_EXT_ZIHPM, .regs = zihpm_regs, .regs_n = ARRAY_SIZE(zihpm_regs),}
-#define AIA_REGS_SUBLIST \
+#define SUBLIST_AIA \
 	{"aia", .feature = KVM_RISCV_ISA_EXT_SSAIA, .regs = aia_regs, .regs_n = ARRAY_SIZE(aia_regs),}
-#define SMSTATEEN_REGS_SUBLIST \
+#define SUBLIST_SMSTATEEN \
 	{"smstateen", .feature = KVM_RISCV_ISA_EXT_SMSTATEEN, .regs = smstateen_regs, .regs_n = ARRAY_SIZE(smstateen_regs),}
-#define FP_F_REGS_SUBLIST \
+#define SUBLIST_FP_F \
 	{"fp_f", .feature = KVM_RISCV_ISA_EXT_F, .regs = fp_f_regs, \
 		.regs_n = ARRAY_SIZE(fp_f_regs),}
-#define FP_D_REGS_SUBLIST \
+#define SUBLIST_FP_D \
 	{"fp_d", .feature = KVM_RISCV_ISA_EXT_D, .regs = fp_d_regs, \
 		.regs_n = ARRAY_SIZE(fp_d_regs),}
 
-static struct vcpu_reg_list h_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	H_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicbom_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICBOM_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicboz_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICBOZ_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list svpbmt_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	SVPBMT_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list sstc_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	SSTC_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list svinval_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	SVINVAL_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zihintpause_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZIHINTPAUSE_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zba_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZBA_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zbb_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZBB_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zbs_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZBS_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicntr_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICNTR_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicond_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICOND_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zicsr_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZICSR_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zifencei_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZIFENCEI_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list zihpm_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	ZIHPM_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list aia_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	AIA_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list smstateen_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	SMSTATEEN_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list fp_f_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	FP_F_REGS_SUBLIST,
-	{0},
-	},
-};
-
-static struct vcpu_reg_list fp_d_config = {
-	.sublists = {
-	BASE_SUBLIST,
-	FP_D_REGS_SUBLIST,
-	{0},
-	},
-};
+#define KVM_ISA_EXT_SIMPLE_CONFIG(ext, extu)			\
+static __u64 regs_##ext[] = {					\
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG |			\
+	KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_##extu,	\
+};								\
+static struct vcpu_reg_list config_##ext = {			\
+	.sublists = {						\
+		SUBLIST_BASE,					\
+		{						\
+			.name = #ext,				\
+			.feature = KVM_RISCV_ISA_EXT_##extu,	\
+			.regs = regs_##ext,			\
+			.regs_n = ARRAY_SIZE(regs_##ext),	\
+		},						\
+		{0},						\
+	},							\
+}								\
+
+#define KVM_ISA_EXT_SUBLIST_CONFIG(ext, extu)			\
+static struct vcpu_reg_list config_##ext = {			\
+	.sublists = {						\
+		SUBLIST_BASE,					\
+		SUBLIST_##extu,					\
+		{0},						\
+	},							\
+}								\
+
+/* Note: The below list is alphabetically sorted. */
+
+KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA);
+KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F);
+KVM_ISA_EXT_SUBLIST_CONFIG(fp_d, FP_D);
+KVM_ISA_EXT_SIMPLE_CONFIG(h, H);
+KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN);
+KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC);
+KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL);
+KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
+KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
+KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
+KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
+KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
+KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR);
+KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND);
+KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR);
+KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI);
+KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE);
+KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
 
 struct vcpu_reg_list *vcpu_configs[] = {
-	&h_config,
-	&zicbom_config,
-	&zicboz_config,
-	&svpbmt_config,
-	&sstc_config,
-	&svinval_config,
-	&zihintpause_config,
-	&zba_config,
-	&zbb_config,
-	&zbs_config,
-	&zicntr_config,
-	&zicond_config,
-	&zicsr_config,
-	&zifencei_config,
-	&zihpm_config,
-	&aia_config,
-	&smstateen_config,
-	&fp_f_config,
-	&fp_d_config,
+	&config_aia,
+	&config_fp_f,
+	&config_fp_d,
+	&config_h,
+	&config_smstateen,
+	&config_sstc,
+	&config_svinval,
+	&config_svnapot,
+	&config_svpbmt,
+	&config_zba,
+	&config_zbb,
+	&config_zbs,
+	&config_zicbom,
+	&config_zicboz,
+	&config_zicntr,
+	&config_zicond,
+	&config_zicsr,
+	&config_zifencei,
+	&config_zihintpause,
+	&config_zihpm,
 };
 int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
-- 
GitLab


From 7f58de96aa5e871dd553499e2c84fc801658eab6 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 13 Dec 2023 18:09:53 +0100
Subject: [PATCH 1986/4076] RISC-V: KVM: Don't add SBI multi regs in
 get-reg-list

The multi regs are derived from the single registers. Only list the
single registers in get-reg-list. This also makes the SBI extension
register listing consistent with the ISA extension register listing.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 36 ++----------------------------------
 1 file changed, 2 insertions(+), 34 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index f8c9fa0c03c5a..f9bfa8a5db211 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -933,20 +933,12 @@ static inline unsigned long num_isa_ext_regs(const struct kvm_vcpu *vcpu)
 
 static inline unsigned long num_sbi_ext_regs(void)
 {
-	/*
-	 * number of KVM_REG_RISCV_SBI_SINGLE +
-	 * 2 x (number of KVM_REG_RISCV_SBI_MULTI)
-	 */
-	return KVM_RISCV_SBI_EXT_MAX + 2*(KVM_REG_RISCV_SBI_MULTI_REG_LAST+1);
+	return KVM_RISCV_SBI_EXT_MAX;
 }
 
 static int copy_sbi_ext_reg_indices(u64 __user *uindices)
 {
-	int n;
-
-	/* copy KVM_REG_RISCV_SBI_SINGLE */
-	n = KVM_RISCV_SBI_EXT_MAX;
-	for (int i = 0; i < n; i++) {
+	for (int i = 0; i < KVM_RISCV_SBI_EXT_MAX; i++) {
 		u64 size = IS_ENABLED(CONFIG_32BIT) ?
 			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
 		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
@@ -959,30 +951,6 @@ static int copy_sbi_ext_reg_indices(u64 __user *uindices)
 		}
 	}
 
-	/* copy KVM_REG_RISCV_SBI_MULTI */
-	n = KVM_REG_RISCV_SBI_MULTI_REG_LAST + 1;
-	for (int i = 0; i < n; i++) {
-		u64 size = IS_ENABLED(CONFIG_32BIT) ?
-			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
-		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
-			  KVM_REG_RISCV_SBI_MULTI_EN | i;
-
-		if (uindices) {
-			if (put_user(reg, uindices))
-				return -EFAULT;
-			uindices++;
-		}
-
-		reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
-			  KVM_REG_RISCV_SBI_MULTI_DIS | i;
-
-		if (uindices) {
-			if (put_user(reg, uindices))
-				return -EFAULT;
-			uindices++;
-		}
-	}
-
 	return num_sbi_ext_regs();
 }
 
-- 
GitLab


From 7602730d7f18ad9738d8fc5e5fd7f52a11fee399 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 13 Dec 2023 18:09:54 +0100
Subject: [PATCH 1987/4076] KVM: riscv: selftests: Drop SBI multi registers

These registers are no longer getting added to get-reg-list.
We keep sbi_ext_multi_id_to_str() for printing, even though
we don't expect it to normally be used, because it may be
useful for debug.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/riscv/get-reg-list.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 5d86c761784e6..27d07a32a1ef0 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -571,8 +571,6 @@ static __u64 base_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL,
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR,
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_EN | 0,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_DIS | 0,
 };
 
 /*
-- 
GitLab


From 23e1dc45022eb65529aa30b1851a8d21a639c8f5 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 13 Dec 2023 18:09:55 +0100
Subject: [PATCH 1988/4076] RISC-V: KVM: Make SBI uapi consistent with ISA uapi

When an SBI extension cannot be enabled, that's a distinct state vs.
enabled and disabled. Modify enum kvm_riscv_sbi_ext_status to
accommodate it, which allows KVM userspace to tell the difference
in state too, as the SBI extension register will disappear when it
cannot be enabled, i.e. accesses to it return ENOENT. get-reg-list is
updated as well to only add SBI extension registers to the list which
may be enabled. Returning ENOENT for SBI extension registers which
cannot be enabled makes them consistent with ISA extension registers.
Any SBI extensions which were enabled by default are still enabled by
default, if they can be enabled at all.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/kvm_vcpu_sbi.h | 10 ++--
 arch/riscv/kvm/vcpu_onereg.c          | 23 +++++---
 arch/riscv/kvm/vcpu_sbi.c             | 75 +++++++++++++++------------
 arch/riscv/kvm/vcpu_sbi_replace.c     |  2 +-
 4 files changed, 65 insertions(+), 45 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index 6a453f7f8b562..bffda0ac59b61 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -15,9 +15,10 @@
 #define KVM_SBI_VERSION_MINOR 0
 
 enum kvm_riscv_sbi_ext_status {
-	KVM_RISCV_SBI_EXT_UNINITIALIZED,
-	KVM_RISCV_SBI_EXT_AVAILABLE,
-	KVM_RISCV_SBI_EXT_UNAVAILABLE,
+	KVM_RISCV_SBI_EXT_STATUS_UNINITIALIZED,
+	KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE,
+	KVM_RISCV_SBI_EXT_STATUS_ENABLED,
+	KVM_RISCV_SBI_EXT_STATUS_DISABLED,
 };
 
 struct kvm_vcpu_sbi_context {
@@ -36,7 +37,7 @@ struct kvm_vcpu_sbi_extension {
 	unsigned long extid_start;
 	unsigned long extid_end;
 
-	bool default_unavail;
+	bool default_disabled;
 
 	/**
 	 * SBI extension handler. It can be defined for a given extension or group of
@@ -61,6 +62,7 @@ int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu,
 				   const struct kvm_one_reg *reg);
 const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(
 				struct kvm_vcpu *vcpu, unsigned long extid);
+bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx);
 int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu);
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index f9bfa8a5db211..48262be73aa0f 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -931,27 +931,34 @@ static inline unsigned long num_isa_ext_regs(const struct kvm_vcpu *vcpu)
 	return copy_isa_ext_reg_indices(vcpu, NULL);;
 }
 
-static inline unsigned long num_sbi_ext_regs(void)
+static int copy_sbi_ext_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
-	return KVM_RISCV_SBI_EXT_MAX;
-}
+	unsigned int n = 0;
 
-static int copy_sbi_ext_reg_indices(u64 __user *uindices)
-{
 	for (int i = 0; i < KVM_RISCV_SBI_EXT_MAX; i++) {
 		u64 size = IS_ENABLED(CONFIG_32BIT) ?
 			   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
 		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT |
 			  KVM_REG_RISCV_SBI_SINGLE | i;
 
+		if (!riscv_vcpu_supports_sbi_ext(vcpu, i))
+			continue;
+
 		if (uindices) {
 			if (put_user(reg, uindices))
 				return -EFAULT;
 			uindices++;
 		}
+
+		n++;
 	}
 
-	return num_sbi_ext_regs();
+	return n;
+}
+
+static unsigned long num_sbi_ext_regs(struct kvm_vcpu *vcpu)
+{
+	return copy_sbi_ext_reg_indices(vcpu, NULL);
 }
 
 /*
@@ -970,7 +977,7 @@ unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu)
 	res += num_fp_f_regs(vcpu);
 	res += num_fp_d_regs(vcpu);
 	res += num_isa_ext_regs(vcpu);
-	res += num_sbi_ext_regs();
+	res += num_sbi_ext_regs(vcpu);
 
 	return res;
 }
@@ -1018,7 +1025,7 @@ int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu,
 		return ret;
 	uindices += ret;
 
-	ret = copy_sbi_ext_reg_indices(uindices);
+	ret = copy_sbi_ext_reg_indices(vcpu, uindices);
 	if (ret < 0)
 		return ret;
 
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index a04ff98085d93..dcdff44581906 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -80,6 +80,34 @@ static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = {
 	},
 };
 
+static const struct kvm_riscv_sbi_extension_entry *
+riscv_vcpu_get_sbi_ext(struct kvm_vcpu *vcpu, unsigned long idx)
+{
+	const struct kvm_riscv_sbi_extension_entry *sext = NULL;
+
+	if (idx >= KVM_RISCV_SBI_EXT_MAX)
+		return NULL;
+
+	for (int i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
+		if (sbi_ext[i].ext_idx == idx) {
+			sext = &sbi_ext[i];
+			break;
+		}
+	}
+
+	return sext;
+}
+
+bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx)
+{
+	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
+	const struct kvm_riscv_sbi_extension_entry *sext;
+
+	sext = riscv_vcpu_get_sbi_ext(vcpu, idx);
+
+	return sext && scontext->ext_status[sext->ext_idx] != KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE;
+}
+
 void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
@@ -140,28 +168,19 @@ static int riscv_vcpu_set_sbi_ext_single(struct kvm_vcpu *vcpu,
 					 unsigned long reg_num,
 					 unsigned long reg_val)
 {
-	unsigned long i;
-	const struct kvm_riscv_sbi_extension_entry *sext = NULL;
 	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
-
-	if (reg_num >= KVM_RISCV_SBI_EXT_MAX)
-		return -ENOENT;
+	const struct kvm_riscv_sbi_extension_entry *sext;
 
 	if (reg_val != 1 && reg_val != 0)
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
-		if (sbi_ext[i].ext_idx == reg_num) {
-			sext = &sbi_ext[i];
-			break;
-		}
-	}
-	if (!sext)
+	sext = riscv_vcpu_get_sbi_ext(vcpu, reg_num);
+	if (!sext || scontext->ext_status[sext->ext_idx] == KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE)
 		return -ENOENT;
 
 	scontext->ext_status[sext->ext_idx] = (reg_val) ?
-			KVM_RISCV_SBI_EXT_AVAILABLE :
-			KVM_RISCV_SBI_EXT_UNAVAILABLE;
+			KVM_RISCV_SBI_EXT_STATUS_ENABLED :
+			KVM_RISCV_SBI_EXT_STATUS_DISABLED;
 
 	return 0;
 }
@@ -170,24 +189,16 @@ static int riscv_vcpu_get_sbi_ext_single(struct kvm_vcpu *vcpu,
 					 unsigned long reg_num,
 					 unsigned long *reg_val)
 {
-	unsigned long i;
-	const struct kvm_riscv_sbi_extension_entry *sext = NULL;
 	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
+	const struct kvm_riscv_sbi_extension_entry *sext;
 
-	if (reg_num >= KVM_RISCV_SBI_EXT_MAX)
-		return -ENOENT;
-
-	for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
-		if (sbi_ext[i].ext_idx == reg_num) {
-			sext = &sbi_ext[i];
-			break;
-		}
-	}
-	if (!sext)
+	sext = riscv_vcpu_get_sbi_ext(vcpu, reg_num);
+	if (!sext || scontext->ext_status[sext->ext_idx] == KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE)
 		return -ENOENT;
 
 	*reg_val = scontext->ext_status[sext->ext_idx] ==
-				KVM_RISCV_SBI_EXT_AVAILABLE;
+				KVM_RISCV_SBI_EXT_STATUS_ENABLED;
+
 	return 0;
 }
 
@@ -325,7 +336,7 @@ const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(
 		if (ext->extid_start <= extid && ext->extid_end >= extid) {
 			if (entry->ext_idx >= KVM_RISCV_SBI_EXT_MAX ||
 			    scontext->ext_status[entry->ext_idx] ==
-						KVM_RISCV_SBI_EXT_AVAILABLE)
+						KVM_RISCV_SBI_EXT_STATUS_ENABLED)
 				return ext;
 
 			return NULL;
@@ -413,12 +424,12 @@ void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu)
 
 		if (ext->probe && !ext->probe(vcpu)) {
 			scontext->ext_status[entry->ext_idx] =
-				KVM_RISCV_SBI_EXT_UNAVAILABLE;
+				KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE;
 			continue;
 		}
 
-		scontext->ext_status[entry->ext_idx] = ext->default_unavail ?
-					KVM_RISCV_SBI_EXT_UNAVAILABLE :
-					KVM_RISCV_SBI_EXT_AVAILABLE;
+		scontext->ext_status[entry->ext_idx] = ext->default_disabled ?
+					KVM_RISCV_SBI_EXT_STATUS_DISABLED :
+					KVM_RISCV_SBI_EXT_STATUS_ENABLED;
 	}
 }
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 23b57c931b152..9c2ab3dfa93aa 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -204,6 +204,6 @@ static int kvm_sbi_ext_dbcn_handler(struct kvm_vcpu *vcpu,
 const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn = {
 	.extid_start = SBI_EXT_DBCN,
 	.extid_end = SBI_EXT_DBCN,
-	.default_unavail = true,
+	.default_disabled = true,
 	.handler = kvm_sbi_ext_dbcn_handler,
 };
-- 
GitLab


From 6ccf119a4cc886678099a3526f37db98b67024d7 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 13 Dec 2023 18:09:56 +0100
Subject: [PATCH 1989/4076] KVM: riscv: selftests: Add RISCV_SBI_EXT_REG

While adding RISCV_SBI_EXT_REG(), acknowledge that some registers
have subtypes and extend __kvm_reg_id() to take a subtype field.
Then, update all macros to set the new field appropriately. The
general CSR macro gets renamed to include "GENERAL", but the other
macros, like the new RISCV_SBI_EXT_REG, just use the SINGLE subtype.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/include/riscv/processor.h   | 40 +++++++++++--------
 .../selftests/kvm/lib/riscv/processor.c       |  4 +-
 2 files changed, 25 insertions(+), 19 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index 5b62a3d2aa9b5..e70ccda2011bf 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -10,10 +10,10 @@
 #include "kvm_util.h"
 #include <linux/stringify.h>
 
-static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
-				    uint64_t  size)
+static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
+				    uint64_t idx, uint64_t size)
 {
-	return KVM_REG_RISCV | type | idx | size;
+	return KVM_REG_RISCV | type | subtype | idx | size;
 }
 
 #if __riscv_xlen == 64
@@ -22,24 +22,30 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
 #define KVM_REG_SIZE_ULONG	KVM_REG_SIZE_U32
 #endif
 
-#define RISCV_CONFIG_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CONFIG, \
-					     KVM_REG_RISCV_CONFIG_REG(name), \
-					     KVM_REG_SIZE_ULONG)
+#define RISCV_CONFIG_REG(name)		__kvm_reg_id(KVM_REG_RISCV_CONFIG, 0,		\
+						     KVM_REG_RISCV_CONFIG_REG(name),	\
+						     KVM_REG_SIZE_ULONG)
 
-#define RISCV_CORE_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CORE, \
-					     KVM_REG_RISCV_CORE_REG(name), \
-					     KVM_REG_SIZE_ULONG)
+#define RISCV_CORE_REG(name)		__kvm_reg_id(KVM_REG_RISCV_CORE, 0,		\
+						     KVM_REG_RISCV_CORE_REG(name),	\
+						     KVM_REG_SIZE_ULONG)
 
-#define RISCV_CSR_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CSR, \
-					     KVM_REG_RISCV_CSR_REG(name), \
-					     KVM_REG_SIZE_ULONG)
+#define RISCV_GENERAL_CSR_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CSR,			\
+						     KVM_REG_RISCV_CSR_GENERAL,		\
+						     KVM_REG_RISCV_CSR_REG(name),	\
+						     KVM_REG_SIZE_ULONG)
 
-#define RISCV_TIMER_REG(name)	__kvm_reg_id(KVM_REG_RISCV_TIMER, \
-					     KVM_REG_RISCV_TIMER_REG(name), \
-					     KVM_REG_SIZE_U64)
+#define RISCV_TIMER_REG(name)		__kvm_reg_id(KVM_REG_RISCV_TIMER, 0,		\
+						     KVM_REG_RISCV_TIMER_REG(name),	\
+						     KVM_REG_SIZE_U64)
 
-#define RISCV_ISA_EXT_REG(idx)	__kvm_reg_id(KVM_REG_RISCV_ISA_EXT, \
-					     idx, KVM_REG_SIZE_ULONG)
+#define RISCV_ISA_EXT_REG(idx)		__kvm_reg_id(KVM_REG_RISCV_ISA_EXT,		\
+						     KVM_REG_RISCV_ISA_SINGLE,		\
+						     idx, KVM_REG_SIZE_ULONG)
+
+#define RISCV_SBI_EXT_REG(idx)		__kvm_reg_id(KVM_REG_RISCV_SBI_EXT,		\
+						     KVM_REG_RISCV_SBI_SINGLE,		\
+						     idx, KVM_REG_SIZE_ULONG)
 
 /* L3 index Bit[47:39] */
 #define PGTBL_L3_INDEX_MASK			0x0000FF8000000000ULL
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index d146ca71e0c09..6c25f7843ef44 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -201,7 +201,7 @@ void riscv_vcpu_mmu_setup(struct kvm_vcpu *vcpu)
 	satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN;
 	satp |= SATP_MODE_48;
 
-	vcpu_set_reg(vcpu, RISCV_CSR_REG(satp), satp);
+	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(satp), satp);
 }
 
 void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
@@ -315,7 +315,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code);
 
 	/* Setup default exception vector of guest */
-	vcpu_set_reg(vcpu, RISCV_CSR_REG(stvec), (unsigned long)guest_unexp_trap);
+	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)guest_unexp_trap);
 
 	return vcpu;
 }
-- 
GitLab


From b26e70d72d12dc9ddb276898a78b1c35c7ab9b95 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 13 Dec 2023 18:09:57 +0100
Subject: [PATCH 1990/4076] KVM: riscv: selftests: Use register subtypes

Always use register subtypes in the get-reg-list test when registers
have them. The only registers neglecting to do so were ISA extension
registers. While we don't really need to use KVM_REG_RISCV_ISA_SINGLE
(since it's zero), the main purpose is to avoid confusion and to
self-document the tests. Also add print support for the multi
registers like SBI extensions have, even though they're only used for
debugging.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/riscv/get-reg-list.c        | 113 +++++++++++-------
 1 file changed, 73 insertions(+), 40 deletions(-)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 27d07a32a1ef0..4bcc597d34b99 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -28,31 +28,31 @@ bool filter_reg(__u64 reg)
 	 *
 	 * Note: The below list is alphabetically sorted.
 	 */
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_V:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SMSTATEEN:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVNAPOT:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICOND:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
-	case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_A:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_C:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_D:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_F:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_H:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_I:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_M:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_V:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM:
 		return true;
 	/* AIA registers are always available when Ssaia can't be disabled */
 	case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect):
@@ -335,15 +335,10 @@ static const char *fp_d_id_to_str(const char *prefix, __u64 id)
 }
 
 #define KVM_ISA_EXT_ARR(ext)		\
-[KVM_RISCV_ISA_EXT_##ext] = "KVM_RISCV_ISA_EXT_" #ext
+[KVM_RISCV_ISA_EXT_##ext] = "KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_" #ext
 
-static const char *isa_ext_id_to_str(const char *prefix, __u64 id)
+static const char *isa_ext_single_id_to_str(__u64 reg_off)
 {
-	/* reg_off is the offset into unsigned long kvm_isa_ext_arr[] */
-	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_ISA_EXT);
-
-	assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT);
-
 	static const char * const kvm_isa_ext_reg_name[] = {
 		KVM_ISA_EXT_ARR(A),
 		KVM_ISA_EXT_ARR(C),
@@ -373,11 +368,48 @@ static const char *isa_ext_id_to_str(const char *prefix, __u64 id)
 	};
 
 	if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name))
-		return strdup_printf("%lld /* UNKNOWN */", reg_off);
+		return strdup_printf("KVM_REG_RISCV_ISA_SINGLE | %lld /* UNKNOWN */", reg_off);
 
 	return kvm_isa_ext_reg_name[reg_off];
 }
 
+static const char *isa_ext_multi_id_to_str(__u64 reg_subtype, __u64 reg_off)
+{
+	const char *unknown = "";
+
+	if (reg_off > KVM_REG_RISCV_ISA_MULTI_REG_LAST)
+		unknown = " /* UNKNOWN */";
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_ISA_MULTI_EN:
+		return strdup_printf("KVM_REG_RISCV_ISA_MULTI_EN | %lld%s", reg_off, unknown);
+	case KVM_REG_RISCV_ISA_MULTI_DIS:
+		return strdup_printf("KVM_REG_RISCV_ISA_MULTI_DIS | %lld%s", reg_off, unknown);
+	}
+
+	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
+}
+
+static const char *isa_ext_id_to_str(const char *prefix, __u64 id)
+{
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_ISA_EXT);
+	__u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK;
+
+	assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT);
+
+	reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_ISA_SINGLE:
+		return isa_ext_single_id_to_str(reg_off);
+	case KVM_REG_RISCV_ISA_MULTI_EN:
+	case KVM_REG_RISCV_ISA_MULTI_DIS:
+		return isa_ext_multi_id_to_str(reg_subtype, reg_off);
+	}
+
+	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
+}
+
 #define KVM_SBI_EXT_ARR(ext)		\
 [ext] = "KVM_REG_RISCV_SBI_SINGLE | " #ext
 
@@ -583,12 +615,12 @@ static __u64 base_skips_set[] = {
 
 static __u64 zicbom_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM,
 };
 
 static __u64 zicboz_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ,
 };
 
 static __u64 aia_regs[] = {
@@ -599,12 +631,12 @@ static __u64 aia_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siph),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1h),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2h),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA,
 };
 
 static __u64 smstateen_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_SMSTATEEN | KVM_REG_RISCV_CSR_SMSTATEEN_REG(sstateen0),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SMSTATEEN,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN,
 };
 
 static __u64 fp_f_regs[] = {
@@ -641,7 +673,7 @@ static __u64 fp_f_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[30]),
 	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[31]),
 	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(fcsr),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_F,
 };
 
 static __u64 fp_d_regs[] = {
@@ -678,7 +710,7 @@ static __u64 fp_d_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[30]),
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[31]),
 	KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(fcsr),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_D,
 };
 
 #define SUBLIST_BASE \
@@ -702,7 +734,8 @@ static __u64 fp_d_regs[] = {
 #define KVM_ISA_EXT_SIMPLE_CONFIG(ext, extu)			\
 static __u64 regs_##ext[] = {					\
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG |			\
-	KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_##extu,	\
+	KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE |	\
+	KVM_RISCV_ISA_EXT_##extu,				\
 };								\
 static struct vcpu_reg_list config_##ext = {			\
 	.sublists = {						\
-- 
GitLab


From bdf6aa328f137e184b0fce607fd585354c3742f1 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 13 Dec 2023 18:09:58 +0100
Subject: [PATCH 1991/4076] RISC-V: KVM: selftests: Treat SBI ext regs like ISA
 ext regs

SBI extension registers may not be present and indeed when
running on a platform without sscofpmf the PMU SBI extension
is not. Move the SBI extension registers from the base set of
registers to the filter list. Individual configs should test
for any that may or may not be present separately. Since
the PMU extension may disappear and the DBCN extension is only
present in later kernels, separate them from the rest into
their own configs. The rest are lumped together into the same
config.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/include/kvm_util_base.h     |   1 +
 .../selftests/kvm/riscv/get-reg-list.c        | 105 +++++++++++++++---
 2 files changed, 92 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index a18db6a7b3cf4..e112ee30867ff 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -129,6 +129,7 @@ struct vcpu_reg_sublist {
 	const char *name;
 	long capability;
 	int feature;
+	int feature_type;
 	bool finalize;
 	__u64 *regs;
 	__u64 regs_n;
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 4bcc597d34b99..b8da2e86bf9c5 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -12,6 +12,11 @@
 
 #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK)
 
+enum {
+	VCPU_FEATURE_ISA_EXT = 0,
+	VCPU_FEATURE_SBI_EXT,
+};
+
 static bool isa_ext_cant_disable[KVM_RISCV_ISA_EXT_MAX];
 
 bool filter_reg(__u64 reg)
@@ -53,6 +58,21 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM:
+	/*
+	 * Like ISA_EXT registers, SBI_EXT registers are only visible when the
+	 * host supports them and disabling them does not affect the visibility
+	 * of the SBI_EXT register itself.
+	 */
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR:
 		return true;
 	/* AIA registers are always available when Ssaia can't be disabled */
 	case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect):
@@ -75,12 +95,12 @@ bool check_reject_set(int err)
 	return err == EINVAL;
 }
 
-static inline bool vcpu_has_ext(struct kvm_vcpu *vcpu, int ext)
+static bool vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext_id)
 {
 	int ret;
 	unsigned long value;
 
-	ret = __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(ext), &value);
+	ret = __vcpu_get_reg(vcpu, ext_id, &value);
 	return (ret) ? false : !!value;
 }
 
@@ -88,6 +108,7 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 {
 	unsigned long isa_ext_state[KVM_RISCV_ISA_EXT_MAX] = { 0 };
 	struct vcpu_reg_sublist *s;
+	uint64_t feature;
 	int rc;
 
 	for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++)
@@ -103,15 +124,31 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 			isa_ext_cant_disable[i] = true;
 	}
 
+	for (int i = 0; i < KVM_RISCV_SBI_EXT_MAX; i++) {
+		rc = __vcpu_set_reg(vcpu, RISCV_SBI_EXT_REG(i), 0);
+		TEST_ASSERT(!rc || (rc == -1 && errno == ENOENT), "Unexpected error");
+	}
+
 	for_each_sublist(c, s) {
 		if (!s->feature)
 			continue;
 
+		switch (s->feature_type) {
+		case VCPU_FEATURE_ISA_EXT:
+			feature = RISCV_ISA_EXT_REG(s->feature);
+			break;
+		case VCPU_FEATURE_SBI_EXT:
+			feature = RISCV_SBI_EXT_REG(s->feature);
+			break;
+		default:
+			TEST_FAIL("Unknown feature type");
+		}
+
 		/* Try to enable the desired extension */
-		__vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(s->feature), 1);
+		__vcpu_set_reg(vcpu, feature, 1);
 
 		/* Double check whether the desired extension was enabled */
-		__TEST_REQUIRE(vcpu_has_ext(vcpu, s->feature),
+		__TEST_REQUIRE(vcpu_has_ext(vcpu, feature),
 			       "%s not available, skipping tests\n", s->name);
 	}
 }
@@ -593,16 +630,6 @@ static __u64 base_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(time),
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(compare),
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state),
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR,
-	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN,
 };
 
 /*
@@ -613,6 +640,17 @@ static __u64 base_skips_set[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state),
 };
 
+static __u64 sbi_base_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR,
+};
+
 static __u64 zicbom_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM,
@@ -716,6 +754,9 @@ static __u64 fp_d_regs[] = {
 #define SUBLIST_BASE \
 	{"base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), \
 	 .skips_set = base_skips_set, .skips_set_n = ARRAY_SIZE(base_skips_set),}
+#define SUBLIST_SBI_BASE \
+	{"sbi-base", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_V01, \
+	 .regs = sbi_base_regs, .regs_n = ARRAY_SIZE(sbi_base_regs),}
 #define SUBLIST_ZICBOM \
 	{"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),}
 #define SUBLIST_ZICBOZ \
@@ -750,6 +791,26 @@ static struct vcpu_reg_list config_##ext = {			\
 	},							\
 }								\
 
+#define KVM_SBI_EXT_SIMPLE_CONFIG(ext, extu)			\
+static __u64 regs_sbi_##ext[] = {				\
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG |			\
+	KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE |	\
+	KVM_RISCV_SBI_EXT_##extu,				\
+};								\
+static struct vcpu_reg_list config_sbi_##ext = {		\
+	.sublists = {						\
+		SUBLIST_BASE,					\
+		{						\
+			.name = "sbi-"#ext,			\
+			.feature_type = VCPU_FEATURE_SBI_EXT,	\
+			.feature = KVM_RISCV_SBI_EXT_##extu,	\
+			.regs = regs_sbi_##ext,			\
+			.regs_n = ARRAY_SIZE(regs_sbi_##ext),	\
+		},						\
+		{0},						\
+	},							\
+}								\
+
 #define KVM_ISA_EXT_SUBLIST_CONFIG(ext, extu)			\
 static struct vcpu_reg_list config_##ext = {			\
 	.sublists = {						\
@@ -759,8 +820,21 @@ static struct vcpu_reg_list config_##ext = {			\
 	},							\
 }								\
 
+#define KVM_SBI_EXT_SUBLIST_CONFIG(ext, extu)			\
+static struct vcpu_reg_list config_sbi_##ext = {		\
+	.sublists = {						\
+		SUBLIST_BASE,					\
+		SUBLIST_SBI_##extu,				\
+		{0},						\
+	},							\
+}								\
+
 /* Note: The below list is alphabetically sorted. */
 
+KVM_SBI_EXT_SUBLIST_CONFIG(base, BASE);
+KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU);
+KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN);
+
 KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA);
 KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F);
 KVM_ISA_EXT_SUBLIST_CONFIG(fp_d, FP_D);
@@ -783,6 +857,9 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE);
 KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
 
 struct vcpu_reg_list *vcpu_configs[] = {
+	&config_sbi_base,
+	&config_sbi_pmu,
+	&config_sbi_dbcn,
 	&config_aia,
 	&config_fp_f,
 	&config_fp_d,
-- 
GitLab


From 197bd237b67268651ac544e8fedbe1fd275d41e0 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Tue, 5 Dec 2023 14:45:07 -0300
Subject: [PATCH 1992/4076] RISC-V: KVM: set 'vlenb' in
 kvm_riscv_vcpu_alloc_vector_context()

'vlenb', added to riscv_v_ext_state by commit c35f3aa34509 ("RISC-V:
vector: export VLENB csr in __sc_riscv_v_state"), isn't being
initialized in guest_context. If we export 'vlenb' as a KVM CSR,
something we want to do in the next patch, it'll always return 0.

Set 'vlenb' to riscv_v_size/32.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_vector.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index b339a2682f252..530e49c588d6c 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -76,6 +76,7 @@ int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu,
 	cntx->vector.datap = kmalloc(riscv_v_vsize, GFP_KERNEL);
 	if (!cntx->vector.datap)
 		return -ENOMEM;
+	cntx->vector.vlenb = riscv_v_vsize / 32;
 
 	vcpu->arch.host_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
 	if (!vcpu->arch.host_context.vector.datap)
-- 
GitLab


From 2fa290372dfe7dd248b1c16f943f273a3e674f22 Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Tue, 5 Dec 2023 14:45:08 -0300
Subject: [PATCH 1993/4076] RISC-V: KVM: add 'vlenb' Vector CSR

Userspace requires 'vlenb' to be able to encode it in reg ID. Otherwise
it is not possible to retrieve any vector reg since we're returning
EINVAL if reg_size isn't vlenb (see kvm_riscv_vcpu_vreg_addr()).

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_vector.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index 530e49c588d6c..d92d1348045c8 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -116,6 +116,9 @@ static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
 		case KVM_REG_RISCV_VECTOR_CSR_REG(vcsr):
 			*reg_addr = &cntx->vector.vcsr;
 			break;
+		case KVM_REG_RISCV_VECTOR_CSR_REG(vlenb):
+			*reg_addr = &cntx->vector.vlenb;
+			break;
 		case KVM_REG_RISCV_VECTOR_CSR_REG(datap):
 		default:
 			return -ENOENT;
@@ -174,6 +177,18 @@ int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
 	if (!riscv_isa_extension_available(isa, v))
 		return -ENOENT;
 
+	if (reg_num == KVM_REG_RISCV_VECTOR_CSR_REG(vlenb)) {
+		struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+		unsigned long reg_val;
+
+		if (copy_from_user(&reg_val, uaddr, reg_size))
+			return -EFAULT;
+		if (reg_val != cntx->vector.vlenb)
+			return -EINVAL;
+
+		return 0;
+	}
+
 	rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, &reg_addr);
 	if (rc)
 		return rc;
-- 
GitLab


From 3975525e554559117bbf569239c8b41f2c2fa5cf Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Tue, 5 Dec 2023 14:45:09 -0300
Subject: [PATCH 1994/4076] RISC-V: KVM: add vector registers and CSRs in
 KVM_GET_REG_LIST

Add all vector registers and CSRs (vstart, vl, vtype, vcsr, vlenb) in
get-reg-list.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 55 ++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 48262be73aa0f..11cdbf844291a 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -961,6 +961,55 @@ static unsigned long num_sbi_ext_regs(struct kvm_vcpu *vcpu)
 	return copy_sbi_ext_reg_indices(vcpu, NULL);
 }
 
+static inline unsigned long num_vector_regs(const struct kvm_vcpu *vcpu)
+{
+	if (!riscv_isa_extension_available(vcpu->arch.isa, v))
+		return 0;
+
+	/* vstart, vl, vtype, vcsr, vlenb and 32 vector regs */
+	return 37;
+}
+
+static int copy_vector_reg_indices(const struct kvm_vcpu *vcpu,
+				u64 __user *uindices)
+{
+	const struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	int n = num_vector_regs(vcpu);
+	u64 reg, size;
+	int i;
+
+	if (n == 0)
+		return 0;
+
+	/* copy vstart, vl, vtype, vcsr and vlenb */
+	size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+	for (i = 0; i < 5; i++) {
+		reg = KVM_REG_RISCV | size | KVM_REG_RISCV_VECTOR | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	/* vector_regs have a variable 'vlenb' size */
+	size = __builtin_ctzl(cntx->vector.vlenb);
+	size <<= KVM_REG_SIZE_SHIFT;
+	for (i = 0; i < 32; i++) {
+		reg = KVM_REG_RISCV | KVM_REG_RISCV_VECTOR | size |
+			KVM_REG_RISCV_VECTOR_REG(i);
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	return n;
+}
+
 /*
  * kvm_riscv_vcpu_num_regs - how many registers do we present via KVM_GET/SET_ONE_REG
  *
@@ -976,6 +1025,7 @@ unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu)
 	res += num_timer_regs();
 	res += num_fp_f_regs(vcpu);
 	res += num_fp_d_regs(vcpu);
+	res += num_vector_regs(vcpu);
 	res += num_isa_ext_regs(vcpu);
 	res += num_sbi_ext_regs(vcpu);
 
@@ -1020,6 +1070,11 @@ int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu,
 		return ret;
 	uindices += ret;
 
+	ret = copy_vector_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
 	ret = copy_isa_ext_reg_indices(vcpu, uindices);
 	if (ret < 0)
 		return ret;
-- 
GitLab


From 4c460eb369514d53383a7c6ba1aefbca4914c68b Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Sun, 24 Dec 2023 14:04:02 +0530
Subject: [PATCH 1995/4076] RISC-V: KVM: Fix indentation in
 kvm_riscv_vcpu_set_reg_csr()

The indentation of "break" in kvm_riscv_vcpu_set_reg_csr() is
inconsistent hence let us fix it.

Fixes: c04913f2b54e ("RISCV: KVM: Add sstateen0 to ONE_REG")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312190719.kBuYl6oJ-lkp@intel.com/
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 11cdbf844291a..c0bad1aed9f09 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -485,7 +485,7 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
 		if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
 			rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num,
 							      reg_val);
-break;
+		break;
 	default:
 		rc = -ENOENT;
 		break;
-- 
GitLab


From 0b670b54119902de75fcd20a50585cf7b573f801 Mon Sep 17 00:00:00 2001
From: Hermes Zhang <chenhuiz@axis.com>
Date: Fri, 29 Dec 2023 09:36:57 +0800
Subject: [PATCH 1996/4076] Input: gpio-keys - filter gpio_keys -EPROBE_DEFER
 error messages

commit ae42f9288846 ("gpio: Return EPROBE_DEFER if gc->to_irq is NULL")
make gpiod_to_irq() possible to return -EPROBE_DEFER when the racing
happens. This causes the following error message to be printed:

    gpio-keys gpio_keys: Unable to get irq number for GPIO 0, error -517

Fix that by changing dev_err() to dev_err_probe()

Signed-off-by: Hermes Zhang <chenhuiz@axis.com>
Link: https://lore.kernel.org/r/20231229013657.692600-1-Hermes.Zhang@axis.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/gpio_keys.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index 06c09b7addf8e..9f3bcd41cf67d 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -592,9 +592,9 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 			irq = gpiod_to_irq(bdata->gpiod);
 			if (irq < 0) {
 				error = irq;
-				dev_err(dev,
-					"Unable to get irq number for GPIO %d, error %d\n",
-					button->gpio, error);
+				dev_err_probe(dev, error,
+					      "Unable to get irq number for GPIO %d\n",
+					      button->gpio);
 				return error;
 			}
 			bdata->irq = irq;
-- 
GitLab


From 15d3f7664d2776c086f813f1efbfe2ae20a85e89 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Date: Wed, 22 Nov 2023 12:47:45 +0900
Subject: [PATCH 1997/4076] kconfig: WERROR unmet symbol dependency

When KCONFIG_WERROR env variable is set treat unmet direct
symbol dependency as a terminal condition (error).

Suggested-by: Stefan Reinauer <reinauer@google.com>
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/conf.c      |  6 ++++++
 scripts/kconfig/confdata.c  | 13 ++++++++-----
 scripts/kconfig/lkc_proto.h |  2 ++
 scripts/kconfig/symbol.c    |  9 +++++++++
 4 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 33d19e419908b..662a5e7c37c28 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -827,6 +827,9 @@ int main(int ac, char **av)
 		break;
 	}
 
+	if (conf_errors())
+		exit(1);
+
 	if (sync_kconfig) {
 		name = getenv("KCONFIG_NOSILENTUPDATE");
 		if (name && *name) {
@@ -890,6 +893,9 @@ int main(int ac, char **av)
 		break;
 	}
 
+	if (sym_dep_errors())
+		exit(1);
+
 	if (input_mode == savedefconfig) {
 		if (conf_write_defconfig(defconfig_file)) {
 			fprintf(stderr, "n*** Error while saving defconfig to: %s\n\n",
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index f1197e6724316..f53dcdd445976 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -155,6 +155,13 @@ static void conf_message(const char *fmt, ...)
 static const char *conf_filename;
 static int conf_lineno, conf_warnings;
 
+bool conf_errors(void)
+{
+	if (conf_warnings)
+		return getenv("KCONFIG_WERROR");
+	return false;
+}
+
 static void conf_warning(const char *fmt, ...)
 {
 	va_list ap;
@@ -365,10 +372,9 @@ int conf_read_simple(const char *name, int def)
 	char *p, *val;
 	struct symbol *sym;
 	int i, def_flags;
-	const char *warn_unknown, *werror, *sym_name;
+	const char *warn_unknown, *sym_name;
 
 	warn_unknown = getenv("KCONFIG_WARN_UNKNOWN_SYMBOLS");
-	werror = getenv("KCONFIG_WERROR");
 	if (name) {
 		in = zconf_fopen(name);
 	} else {
@@ -525,9 +531,6 @@ load:
 	free(line);
 	fclose(in);
 
-	if (conf_warnings && werror)
-		exit(1);
-
 	return 0;
 }
 
diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h
index 687d8698d801c..a4ae5e9eadadb 100644
--- a/scripts/kconfig/lkc_proto.h
+++ b/scripts/kconfig/lkc_proto.h
@@ -15,6 +15,7 @@ void conf_set_changed(bool val);
 bool conf_get_changed(void);
 void conf_set_changed_callback(void (*fn)(void));
 void conf_set_message_callback(void (*fn)(const char *s));
+bool conf_errors(void);
 
 /* symbol.c */
 extern struct symbol * symbol_hash[SYMBOL_HASHSIZE];
@@ -25,6 +26,7 @@ void print_symbol_for_listconfig(struct symbol *sym);
 struct symbol ** sym_re_search(const char *pattern);
 const char * sym_type_name(enum symbol_type type);
 void sym_calc_value(struct symbol *sym);
+bool sym_dep_errors(void);
 enum symbol_type sym_get_type(struct symbol *sym);
 bool sym_tristate_within_range(struct symbol *sym,tristate tri);
 bool sym_set_tristate_value(struct symbol *sym,tristate tri);
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index a5a4f9153eb73..3e808528aaeab 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -31,6 +31,7 @@ struct symbol symbol_no = {
 
 struct symbol *modules_sym;
 static tristate modules_val;
+static int sym_warnings;
 
 enum symbol_type sym_get_type(struct symbol *sym)
 {
@@ -311,6 +312,14 @@ static void sym_warn_unmet_dep(struct symbol *sym)
 			       "  Selected by [m]:\n");
 
 	fputs(str_get(&gs), stderr);
+	sym_warnings++;
+}
+
+bool sym_dep_errors(void)
+{
+	if (sym_warnings)
+		return getenv("KCONFIG_WERROR");
+	return false;
 }
 
 void sym_calc_value(struct symbol *sym)
-- 
GitLab


From 67f8f1e7aa31b6fe17aeee1c581f61fc3dfa331a Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 11 Dec 2023 19:13:36 -0300
Subject: [PATCH 1998/4076] scripts: Introduce a default git.orderFile

When reviewing patches, it looks much nicer to have some changes shown
before others, which allow better understanding of the patch before the
the .c files reviewing.

Introduce a default git.orderFile, in order to help developers getting the
best ordering easier.

Signed-off-by: Leonardo Bras <leobras@redhat.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/git.orderFile | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 scripts/git.orderFile

diff --git a/scripts/git.orderFile b/scripts/git.orderFile
new file mode 100644
index 0000000000000..5102ba73357f0
--- /dev/null
+++ b/scripts/git.orderFile
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# order file for git, to produce patches which are easier to review
+# by diffing the important stuff like header changes first.
+#
+# one-off usage:
+#   git diff -O scripts/git.orderFile ...
+#
+# add to git config:
+#   git config diff.orderFile scripts/git.orderFile
+#
+
+MAINTAINERS
+
+# Documentation
+Documentation/*
+*.rst
+
+# git-specific
+.gitignore
+scripts/git.orderFile
+
+# build system
+Kconfig*
+*/Kconfig*
+Kbuild*
+*/Kbuild*
+Makefile*
+*/Makefile*
+*.mak
+*.mk
+scripts/*
+
+# semantic patches
+*.cocci
+
+# headers
+*types.h
+*.h
+
+# code
+*.c
-- 
GitLab


From 1f7f31bf7202adcab9616307bcb11a65fb565f63 Mon Sep 17 00:00:00 2001
From: John Moon <quic_johmoo@quicinc.com>
Date: Mon, 11 Dec 2023 18:02:57 -0800
Subject: [PATCH 1999/4076] check-uapi: Introduce check-uapi.sh

While the kernel community has been good at maintaining backwards
compatibility with kernel UAPIs, it would be helpful to have a tool
to check if a commit introduces changes that break backwards
compatibility.

To that end, introduce check-uapi.sh: a simple shell script that
checks for changes to UAPI headers using libabigail.

libabigail is "a framework which aims at helping developers and
software distributors to spot some ABI-related issues like interface
incompatibility in ELF shared libraries by performing a static
analysis of the ELF binaries at hand."

The script uses one of libabigail's tools, "abidiff", to compile the
changed header before and after the commit to detect any changes.

abidiff "compares the ABI of two shared libraries in ELF format. It
emits a meaningful report describing the differences between the two
ABIs."

The script also includes the ability to check the compatibility of
all UAPI headers across commits. This allows developers to inspect
the stability of the UAPIs over time.

Signed-off-by: John Moon <quic_johmoo@quicinc.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/check-uapi.sh | 573 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 573 insertions(+)
 create mode 100755 scripts/check-uapi.sh

diff --git a/scripts/check-uapi.sh b/scripts/check-uapi.sh
new file mode 100755
index 0000000000000..955581735cb3c
--- /dev/null
+++ b/scripts/check-uapi.sh
@@ -0,0 +1,573 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Script to check commits for UAPI backwards compatibility
+
+set -o errexit
+set -o pipefail
+
+print_usage() {
+	name=$(basename "$0")
+	cat << EOF
+$name - check for UAPI header stability across Git commits
+
+By default, the script will check to make sure the latest commit (or current
+dirty changes) did not introduce ABI changes when compared to HEAD^1. You can
+check against additional commit ranges with the -b and -p options.
+
+The script will not check UAPI headers for architectures other than the one
+defined in ARCH.
+
+Usage: $name [-b BASE_REF] [-p PAST_REF] [-j N] [-l ERROR_LOG] [-i] [-q] [-v]
+
+Options:
+    -b BASE_REF    Base git reference to use for comparison. If unspecified or empty,
+                   will use any dirty changes in tree to UAPI files. If there are no
+                   dirty changes, HEAD will be used.
+    -p PAST_REF    Compare BASE_REF to PAST_REF (e.g. -p v6.1). If unspecified or empty,
+                   will use BASE_REF^1. Must be an ancestor of BASE_REF. Only headers
+                   that exist on PAST_REF will be checked for compatibility.
+    -j JOBS        Number of checks to run in parallel (default: number of CPU cores).
+    -l ERROR_LOG   Write error log to file (default: no error log is generated).
+    -i             Ignore ambiguous changes that may or may not break UAPI compatibility.
+    -q             Quiet operation.
+    -v             Verbose operation (print more information about each header being checked).
+
+Environmental args:
+    ABIDIFF  Custom path to abidiff binary
+    CC       C compiler (default is "gcc")
+    ARCH     Target architecture for the UAPI check (default is host arch)
+
+Exit codes:
+    $SUCCESS) Success
+    $FAIL_ABI) ABI difference detected
+    $FAIL_PREREQ) Prerequisite not met
+EOF
+}
+
+readonly SUCCESS=0
+readonly FAIL_ABI=1
+readonly FAIL_PREREQ=2
+
+# Print to stderr
+eprintf() {
+	# shellcheck disable=SC2059
+	printf "$@" >&2
+}
+
+# Expand an array with a specific character (similar to Python string.join())
+join() {
+	local IFS="$1"
+	shift
+	printf "%s" "$*"
+}
+
+# Create abidiff suppressions
+gen_suppressions() {
+	# Common enum variant names which we don't want to worry about
+	# being shifted when new variants are added.
+	local -a enum_regex=(
+		".*_AFTER_LAST$"
+		".*_CNT$"
+		".*_COUNT$"
+		".*_END$"
+		".*_LAST$"
+		".*_MASK$"
+		".*_MAX$"
+		".*_MAX_BIT$"
+		".*_MAX_BPF_ATTACH_TYPE$"
+		".*_MAX_ID$"
+		".*_MAX_SHIFT$"
+		".*_NBITS$"
+		".*_NETDEV_NUMHOOKS$"
+		".*_NFT_META_IIFTYPE$"
+		".*_NL80211_ATTR$"
+		".*_NLDEV_NUM_OPS$"
+		".*_NUM$"
+		".*_NUM_ELEMS$"
+		".*_NUM_IRQS$"
+		".*_SIZE$"
+		".*_TLSMAX$"
+		"^MAX_.*"
+		"^NUM_.*"
+	)
+
+	# Common padding field names which can be expanded into
+	# without worrying about users.
+	local -a padding_regex=(
+		".*end$"
+		".*pad$"
+		".*pad[0-9]?$"
+		".*pad_[0-9]?$"
+		".*padding$"
+		".*padding[0-9]?$"
+		".*padding_[0-9]?$"
+		".*res$"
+		".*resv$"
+		".*resv[0-9]?$"
+		".*resv_[0-9]?$"
+		".*reserved$"
+		".*reserved[0-9]?$"
+		".*reserved_[0-9]?$"
+		".*rsvd[0-9]?$"
+		".*unused$"
+	)
+
+	cat << EOF
+[suppress_type]
+  type_kind = enum
+  changed_enumerators_regexp = $(join , "${enum_regex[@]}")
+EOF
+
+	for p in "${padding_regex[@]}"; do
+		cat << EOF
+[suppress_type]
+  type_kind = struct
+  has_data_member_inserted_at = offset_of_first_data_member_regexp(${p})
+EOF
+	done
+
+if [ "$IGNORE_AMBIGUOUS_CHANGES" = "true" ]; then
+	cat << EOF
+[suppress_type]
+  type_kind = struct
+  has_data_member_inserted_at = end
+  has_size_change = yes
+EOF
+fi
+}
+
+# Check if git tree is dirty
+tree_is_dirty() {
+	! git diff --quiet
+}
+
+# Get list of files installed in $ref
+get_file_list() {
+	local -r ref="$1"
+	local -r tree="$(get_header_tree "$ref")"
+
+	# Print all installed headers, filtering out ones that can't be compiled
+	find "$tree" -type f -name '*.h' -printf '%P\n' | grep -v -f "$INCOMPAT_LIST"
+}
+
+# Add to the list of incompatible headers
+add_to_incompat_list() {
+	local -r ref="$1"
+
+	# Start with the usr/include/Makefile to get a list of the headers
+	# that don't compile using this method.
+	if [ ! -f usr/include/Makefile ]; then
+		eprintf "error - no usr/include/Makefile present at %s\n" "$ref"
+		eprintf "Note: usr/include/Makefile was added in the v5.3 kernel release\n"
+		exit "$FAIL_PREREQ"
+	fi
+	{
+		# shellcheck disable=SC2016
+		printf 'all: ; @echo $(no-header-test)\n'
+		cat usr/include/Makefile
+	} | SRCARCH="$ARCH" make --always-make -f - | tr " " "\n" \
+	  | grep -v "asm-generic" >> "$INCOMPAT_LIST"
+
+	# The makefile also skips all asm-generic files, but prints "asm-generic/%"
+	# which won't work for our grep match. Instead, print something grep will match.
+	printf "asm-generic/.*\.h\n" >> "$INCOMPAT_LIST"
+}
+
+# Compile the simple test app
+do_compile() {
+	local -r inc_dir="$1"
+	local -r header="$2"
+	local -r out="$3"
+	printf "int main(void) { return 0; }\n" | \
+		"$CC" -c \
+		  -o "$out" \
+		  -x c \
+		  -O0 \
+		  -std=c90 \
+		  -fno-eliminate-unused-debug-types \
+		  -g \
+		  "-I${inc_dir}" \
+		  -include "$header" \
+		  -
+}
+
+# Run make headers_install
+run_make_headers_install() {
+	local -r ref="$1"
+	local -r install_dir="$(get_header_tree "$ref")"
+	make -j "$MAX_THREADS" ARCH="$ARCH" INSTALL_HDR_PATH="$install_dir" \
+		headers_install > /dev/null
+}
+
+# Install headers for both git refs
+install_headers() {
+	local -r base_ref="$1"
+	local -r past_ref="$2"
+
+	for ref in "$base_ref" "$past_ref"; do
+		printf "Installing user-facing UAPI headers from %s... " "${ref:-dirty tree}"
+		if [ -n "$ref" ]; then
+			git archive --format=tar --prefix="${ref}-archive/" "$ref" \
+				| (cd "$TMP_DIR" && tar xf -)
+			(
+				cd "${TMP_DIR}/${ref}-archive"
+				run_make_headers_install "$ref"
+				add_to_incompat_list "$ref" "$INCOMPAT_LIST"
+			)
+		else
+			run_make_headers_install "$ref"
+			add_to_incompat_list "$ref" "$INCOMPAT_LIST"
+		fi
+		printf "OK\n"
+	done
+	sort -u -o "$INCOMPAT_LIST" "$INCOMPAT_LIST"
+	sed -i -e '/^$/d' "$INCOMPAT_LIST"
+}
+
+# Print the path to the headers_install tree for a given ref
+get_header_tree() {
+	local -r ref="$1"
+	printf "%s" "${TMP_DIR}/${ref}/usr"
+}
+
+# Check file list for UAPI compatibility
+check_uapi_files() {
+	local -r base_ref="$1"
+	local -r past_ref="$2"
+	local -r abi_error_log="$3"
+
+	local passed=0;
+	local failed=0;
+	local -a threads=()
+	set -o errexit
+
+	printf "Checking changes to UAPI headers between %s and %s...\n" "$past_ref" "${base_ref:-dirty tree}"
+	# Loop over all UAPI headers that were installed by $past_ref (if they only exist on $base_ref,
+	# there's no way they're broken and no way to compare anyway)
+	while read -r file; do
+		if [ "${#threads[@]}" -ge "$MAX_THREADS" ]; then
+			if wait "${threads[0]}"; then
+				passed=$((passed + 1))
+			else
+				failed=$((failed + 1))
+			fi
+			threads=("${threads[@]:1}")
+		fi
+
+		check_individual_file "$base_ref" "$past_ref" "$file" &
+		threads+=("$!")
+	done < <(get_file_list "$past_ref")
+
+	for t in "${threads[@]}"; do
+		if wait "$t"; then
+			passed=$((passed + 1))
+		else
+			failed=$((failed + 1))
+		fi
+	done
+
+	if [ -n "$abi_error_log" ]; then
+		printf 'Generated by "%s %s" from git ref %s\n\n' \
+			"$0" "$*" "$(git rev-parse HEAD)" > "$abi_error_log"
+	fi
+
+	while read -r error_file; do
+		{
+			cat "$error_file"
+			printf "\n\n"
+		} | tee -a "${abi_error_log:-/dev/null}" >&2
+	done < <(find "$TMP_DIR" -type f -name '*.error' | sort)
+
+	total="$((passed + failed))"
+	if [ "$failed" -gt 0 ]; then
+		eprintf "error - %d/%d UAPI headers compatible with %s appear _not_ to be backwards compatible\n" \
+			"$failed" "$total" "$ARCH"
+		if [ -n "$abi_error_log" ]; then
+			eprintf "Failure summary saved to %s\n" "$abi_error_log"
+		fi
+	else
+		printf "All %d UAPI headers compatible with %s appear to be backwards compatible\n" \
+			"$total" "$ARCH"
+	fi
+
+	return "$failed"
+}
+
+# Check an individual file for UAPI compatibility
+check_individual_file() {
+	local -r base_ref="$1"
+	local -r past_ref="$2"
+	local -r file="$3"
+
+	local -r base_header="$(get_header_tree "$base_ref")/${file}"
+	local -r past_header="$(get_header_tree "$past_ref")/${file}"
+
+	if [ ! -f "$base_header" ]; then
+		mkdir -p "$(dirname "$base_header")"
+		printf "==== UAPI header %s was removed between %s and %s ====" \
+			"$file" "$past_ref" "$base_ref" \
+				> "${base_header}.error"
+		return 1
+	fi
+
+	compare_abi "$file" "$base_header" "$past_header" "$base_ref" "$past_ref"
+}
+
+# Perform the A/B compilation and compare output ABI
+compare_abi() {
+	local -r file="$1"
+	local -r base_header="$2"
+	local -r past_header="$3"
+	local -r base_ref="$4"
+	local -r past_ref="$5"
+	local -r log="${TMP_DIR}/log/${file}.log"
+	local -r error_log="${TMP_DIR}/log/${file}.error"
+
+	mkdir -p "$(dirname "$log")"
+
+	if ! do_compile "$(get_header_tree "$base_ref")/include" "$base_header" "${base_header}.bin" 2> "$log"; then
+		{
+			warn_str=$(printf "==== Could not compile version of UAPI header %s at %s ====\n" \
+				"$file" "$base_ref")
+			printf "%s\n" "$warn_str"
+			cat "$log"
+			printf -- "=%.0s" $(seq 0 ${#warn_str})
+		} > "$error_log"
+		return 1
+	fi
+
+	if ! do_compile "$(get_header_tree "$past_ref")/include" "$past_header" "${past_header}.bin" 2> "$log"; then
+		{
+			warn_str=$(printf "==== Could not compile version of UAPI header %s at %s ====\n" \
+				"$file" "$past_ref")
+			printf "%s\n" "$warn_str"
+			cat "$log"
+			printf -- "=%.0s" $(seq 0 ${#warn_str})
+		} > "$error_log"
+		return 1
+	fi
+
+	local ret=0
+	"$ABIDIFF" --non-reachable-types \
+		--suppressions "$SUPPRESSIONS" \
+		"${past_header}.bin" "${base_header}.bin" > "$log" || ret="$?"
+	if [ "$ret" -eq 0 ]; then
+		if [ "$VERBOSE" = "true" ]; then
+			printf "No ABI differences detected in %s from %s -> %s\n" \
+				"$file" "$past_ref" "$base_ref"
+		fi
+	else
+		# Bits in abidiff's return code can be used to determine the type of error
+		if [ $((ret & 0x2)) -gt 0 ]; then
+			eprintf "error - abidiff did not run properly\n"
+			exit 1
+		fi
+
+		if [ "$IGNORE_AMBIGUOUS_CHANGES" = "true" ] && [ "$ret" -eq 4 ]; then
+			return 0
+		fi
+
+		# If the only changes were additions (not modifications to existing APIs), then
+		# there's no problem. Ignore these diffs.
+		if grep "Unreachable types summary" "$log" | grep -q "0 removed" &&
+		   grep "Unreachable types summary" "$log" | grep -q "0 changed"; then
+			return 0
+		fi
+
+		{
+			warn_str=$(printf "==== ABI differences detected in %s from %s -> %s ====" \
+				"$file" "$past_ref" "$base_ref")
+			printf "%s\n" "$warn_str"
+			sed  -e '/summary:/d' -e '/changed type/d' -e '/^$/d' -e 's/^/  /g' "$log"
+			printf -- "=%.0s" $(seq 0 ${#warn_str})
+			if cmp "$past_header" "$base_header" > /dev/null 2>&1; then
+				printf "\n%s did not change between %s and %s...\n" "$file" "$past_ref" "${base_ref:-dirty tree}"
+				printf "It's possible a change to one of the headers it includes caused this error:\n"
+				grep '^#include' "$base_header"
+				printf "\n"
+			fi
+		} > "$error_log"
+
+		return 1
+	fi
+}
+
+# Check that a minimum software version number is satisfied
+min_version_is_satisfied() {
+	local -r min_version="$1"
+	local -r version_installed="$2"
+
+	printf "%s\n%s\n" "$min_version" "$version_installed" \
+		| sort -Vc > /dev/null 2>&1
+}
+
+# Make sure we have the tools we need and the arguments make sense
+check_deps() {
+	ABIDIFF="${ABIDIFF:-abidiff}"
+	CC="${CC:-gcc}"
+	ARCH="${ARCH:-$(uname -m)}"
+	if [ "$ARCH" = "x86_64" ]; then
+		ARCH="x86"
+	fi
+
+	local -r abidiff_min_version="2.4"
+	local -r libdw_min_version_if_clang="0.171"
+
+	if ! command -v "$ABIDIFF" > /dev/null 2>&1; then
+		eprintf "error - abidiff not found!\n"
+		eprintf "Please install abigail-tools version %s or greater\n" "$abidiff_min_version"
+		eprintf "See: https://sourceware.org/libabigail/manual/libabigail-overview.html\n"
+		return 1
+	fi
+
+	local -r abidiff_version="$("$ABIDIFF" --version | cut -d ' ' -f 2)"
+	if ! min_version_is_satisfied "$abidiff_min_version" "$abidiff_version"; then
+		eprintf "error - abidiff version too old: %s\n" "$abidiff_version"
+		eprintf "Please install abigail-tools version %s or greater\n" "$abidiff_min_version"
+		eprintf "See: https://sourceware.org/libabigail/manual/libabigail-overview.html\n"
+		return 1
+	fi
+
+	if ! command -v "$CC" > /dev/null 2>&1; then
+		eprintf 'error - %s not found\n' "$CC"
+		return 1
+	fi
+
+	if "$CC" --version | grep -q clang; then
+		local -r libdw_version="$(ldconfig -v 2>/dev/null | grep -v SKIPPED | grep -m 1 -o 'libdw-[0-9]\+.[0-9]\+' | cut -c 7-)"
+		if ! min_version_is_satisfied "$libdw_min_version_if_clang" "$libdw_version"; then
+			eprintf "error - libdw version too old for use with clang: %s\n" "$libdw_version"
+			eprintf "Please install libdw from elfutils version %s or greater\n" "$libdw_min_version_if_clang"
+			eprintf "See: https://sourceware.org/elfutils/\n"
+			return 1
+		fi
+	fi
+
+	if [ ! -d "arch/${ARCH}" ]; then
+		eprintf 'error - ARCH "%s" is not a subdirectory under arch/\n' "$ARCH"
+		eprintf "Please set ARCH to one of:\n%s\n" "$(find arch -maxdepth 1 -mindepth 1 -type d -printf '%f ' | fmt)"
+		return 1
+	fi
+
+	if ! git rev-parse --is-inside-work-tree > /dev/null 2>&1; then
+		eprintf "error - this script requires the kernel tree to be initialized with Git\n"
+		return 1
+	fi
+
+	if ! git rev-parse --verify "$past_ref" > /dev/null 2>&1; then
+		printf 'error - invalid git reference "%s"\n' "$past_ref"
+		return 1
+	fi
+
+	if [ -n "$base_ref" ]; then
+		if ! git merge-base --is-ancestor "$past_ref" "$base_ref" > /dev/null 2>&1; then
+			printf 'error - "%s" is not an ancestor of base ref "%s"\n' "$past_ref" "$base_ref"
+			return 1
+		fi
+		if [ "$(git rev-parse "$base_ref")" = "$(git rev-parse "$past_ref")" ]; then
+			printf 'error - "%s" and "%s" are the same reference\n' "$past_ref" "$base_ref"
+			return 1
+		fi
+	fi
+}
+
+run() {
+	local base_ref="$1"
+	local past_ref="$2"
+	local abi_error_log="$3"
+	shift 3
+
+	if [ -z "$KERNEL_SRC" ]; then
+		KERNEL_SRC="$(realpath "$(dirname "$0")"/..)"
+	fi
+
+	cd "$KERNEL_SRC"
+
+	if [ -z "$base_ref" ] && ! tree_is_dirty; then
+		base_ref=HEAD
+	fi
+
+	if [ -z "$past_ref" ]; then
+		if [ -n "$base_ref" ]; then
+			past_ref="${base_ref}^1"
+		else
+			past_ref=HEAD
+		fi
+	fi
+
+	if ! check_deps; then
+		exit "$FAIL_PREREQ"
+	fi
+
+	TMP_DIR=$(mktemp -d)
+	readonly TMP_DIR
+	trap 'rm -rf "$TMP_DIR"' EXIT
+
+	readonly INCOMPAT_LIST="${TMP_DIR}/incompat_list.txt"
+	touch "$INCOMPAT_LIST"
+
+	readonly SUPPRESSIONS="${TMP_DIR}/suppressions.txt"
+	gen_suppressions > "$SUPPRESSIONS"
+
+	# Run make install_headers for both refs
+	install_headers "$base_ref" "$past_ref"
+
+	# Check for any differences in the installed header trees
+	if diff -r -q "$(get_header_tree "$base_ref")" "$(get_header_tree "$past_ref")" > /dev/null 2>&1; then
+		printf "No changes to UAPI headers were applied between %s and %s\n" "$past_ref" "${base_ref:-dirty tree}"
+		exit "$SUCCESS"
+	fi
+
+	if ! check_uapi_files "$base_ref" "$past_ref" "$abi_error_log"; then
+		exit "$FAIL_ABI"
+	fi
+}
+
+main() {
+	MAX_THREADS=$(nproc)
+	VERBOSE="false"
+	IGNORE_AMBIGUOUS_CHANGES="false"
+	quiet="false"
+	local base_ref=""
+	while getopts "hb:p:j:l:iqv" opt; do
+		case $opt in
+		h)
+			print_usage
+			exit "$SUCCESS"
+			;;
+		b)
+			base_ref="$OPTARG"
+			;;
+		p)
+			past_ref="$OPTARG"
+			;;
+		j)
+			MAX_THREADS="$OPTARG"
+			;;
+		l)
+			abi_error_log="$OPTARG"
+			;;
+		i)
+			IGNORE_AMBIGUOUS_CHANGES="true"
+			;;
+		q)
+			quiet="true"
+			VERBOSE="false"
+			;;
+		v)
+			VERBOSE="true"
+			quiet="false"
+			;;
+		*)
+			exit "$FAIL_PREREQ"
+		esac
+	done
+
+	if [ "$quiet" = "true" ]; then
+		exec > /dev/null 2>&1
+	fi
+
+	run "$base_ref" "$past_ref" "$abi_error_log" "$@"
+}
+
+main "$@"
-- 
GitLab


From 8c88bc5b489e785c7ead94ce6fc3adb7f76e8715 Mon Sep 17 00:00:00 2001
From: John Moon <quic_johmoo@quicinc.com>
Date: Mon, 11 Dec 2023 18:02:58 -0800
Subject: [PATCH 2000/4076] docs: dev-tools: Add UAPI checker documentation

Add detailed documentation for scripts/check-uapi.sh.

Signed-off-by: John Moon <quic_johmoo@quicinc.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 Documentation/dev-tools/checkuapi.rst | 477 ++++++++++++++++++++++++++
 Documentation/dev-tools/index.rst     |   1 +
 2 files changed, 478 insertions(+)
 create mode 100644 Documentation/dev-tools/checkuapi.rst

diff --git a/Documentation/dev-tools/checkuapi.rst b/Documentation/dev-tools/checkuapi.rst
new file mode 100644
index 0000000000000..9072f21b50b0c
--- /dev/null
+++ b/Documentation/dev-tools/checkuapi.rst
@@ -0,0 +1,477 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+============
+UAPI Checker
+============
+
+The UAPI checker (``scripts/check-uapi.sh``) is a shell script which
+checks UAPI header files for userspace backwards-compatibility across
+the git tree.
+
+Options
+=======
+
+This section will describe the options with which ``check-uapi.sh``
+can be run.
+
+Usage::
+
+    check-uapi.sh [-b BASE_REF] [-p PAST_REF] [-j N] [-l ERROR_LOG] [-i] [-q] [-v]
+
+Available options::
+
+    -b BASE_REF    Base git reference to use for comparison. If unspecified or empty,
+                   will use any dirty changes in tree to UAPI files. If there are no
+                   dirty changes, HEAD will be used.
+    -p PAST_REF    Compare BASE_REF to PAST_REF (e.g. -p v6.1). If unspecified or empty,
+                   will use BASE_REF^1. Must be an ancestor of BASE_REF. Only headers
+                   that exist on PAST_REF will be checked for compatibility.
+    -j JOBS        Number of checks to run in parallel (default: number of CPU cores).
+    -l ERROR_LOG   Write error log to file (default: no error log is generated).
+    -i             Ignore ambiguous changes that may or may not break UAPI compatibility.
+    -q             Quiet operation.
+    -v             Verbose operation (print more information about each header being checked).
+
+Environmental args::
+
+    ABIDIFF  Custom path to abidiff binary
+    CC       C compiler (default is "gcc")
+    ARCH     Target architecture of C compiler (default is host arch)
+
+Exit codes::
+
+    0) Success
+    1) ABI difference detected
+    2) Prerequisite not met
+
+Examples
+========
+
+Basic Usage
+-----------
+
+First, let's try making a change to a UAPI header file that obviously
+won't break userspace::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/include/uapi/linux/acct.h
+    +++ b/include/uapi/linux/acct.h
+    @@ -21,7 +21,9 @@
+     #include <asm/param.h>
+     #include <asm/byteorder.h>
+
+    -/*
+    +#define FOO
+    +
+    +/*
+      *  comp_t is a 16-bit "floating" point number with a 3-bit base 8
+      *  exponent and a 13-bit fraction.
+      *  comp2_t is 24-bit with 5-bit base 2 exponent and 20 bit fraction
+    diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
+    EOF
+
+Now, let's use the script to validate::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+Let's add another change that *might* break userspace::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/include/uapi/linux/bpf.h
+    +++ b/include/uapi/linux/bpf.h
+    @@ -74,7 +74,7 @@ struct bpf_insn {
+            __u8    dst_reg:4;      /* dest register */
+            __u8    src_reg:4;      /* source register */
+            __s16   off;            /* signed offset */
+    -       __s32   imm;            /* signed immediate constant */
+    +       __u32   imm;            /* unsigned immediate constant */
+     };
+
+     /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
+    EOF
+
+The script will catch this::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== ABI differences detected in include/linux/bpf.h from HEAD -> dirty tree ====
+        [C] 'struct bpf_insn' changed:
+          type size hasn't changed
+          1 data member change:
+            type of '__s32 imm' changed:
+              typedef name changed from __s32 to __u32 at int-ll64.h:27:1
+              underlying type 'int' changed:
+                type name changed from 'int' to 'unsigned int'
+                type size hasn't changed
+    ==================================================================================
+
+    error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+In this case, the script is reporting the type change because it could
+break a userspace program that passes in a negative number. Now, let's
+say you know that no userspace program could possibly be using a negative
+value in ``imm``, so changing to an unsigned type there shouldn't hurt
+anything. You can pass the ``-i`` flag to the script to ignore changes
+in which the userspace backwards compatibility is ambiguous::
+
+    % ./scripts/check-uapi.sh -i
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+Now, let's make a similar change that *will* break userspace::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/include/uapi/linux/bpf.h
+    +++ b/include/uapi/linux/bpf.h
+    @@ -71,8 +71,8 @@ enum {
+
+     struct bpf_insn {
+            __u8    code;           /* opcode */
+    -       __u8    dst_reg:4;      /* dest register */
+            __u8    src_reg:4;      /* source register */
+    +       __u8    dst_reg:4;      /* dest register */
+            __s16   off;            /* signed offset */
+            __s32   imm;            /* signed immediate constant */
+     };
+    EOF
+
+Since we're re-ordering an existing struct member, there's no ambiguity,
+and the script will report the breakage even if you pass ``-i``::
+
+    % ./scripts/check-uapi.sh -i
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== ABI differences detected in include/linux/bpf.h from HEAD -> dirty tree ====
+        [C] 'struct bpf_insn' changed:
+          type size hasn't changed
+          2 data member changes:
+            '__u8 dst_reg' offset changed from 8 to 12 (in bits) (by +4 bits)
+            '__u8 src_reg' offset changed from 12 to 8 (in bits) (by -4 bits)
+    ==================================================================================
+
+    error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Let's commit the breaking change, then commit the innocuous change::
+
+    % git commit -m 'Breaking UAPI change' include/uapi/linux/bpf.h
+    [detached HEAD f758e574663a] Breaking UAPI change
+     1 file changed, 1 insertion(+), 1 deletion(-)
+    % git commit -m 'Innocuous UAPI change' include/uapi/linux/acct.h
+    [detached HEAD 2e87df769081] Innocuous UAPI change
+     1 file changed, 3 insertions(+), 1 deletion(-)
+
+Now, let's run the script again with no arguments::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from HEAD... OK
+    Installing user-facing UAPI headers from HEAD^1... OK
+    Checking changes to UAPI headers between HEAD^1 and HEAD...
+    All 912 UAPI headers compatible with x86 appear to be backwards compatible
+
+It doesn't catch any breaking change because, by default, it only
+compares ``HEAD`` to ``HEAD^1``. The breaking change was committed on
+``HEAD~2``. If we wanted the search scope to go back further, we'd have to
+use the ``-p`` option to pass a different past reference. In this case,
+let's pass ``-p HEAD~2`` to the script so it checks UAPI changes between
+``HEAD~2`` and ``HEAD``::
+
+    % ./scripts/check-uapi.sh -p HEAD~2
+    Installing user-facing UAPI headers from HEAD... OK
+    Installing user-facing UAPI headers from HEAD~2... OK
+    Checking changes to UAPI headers between HEAD~2 and HEAD...
+    ==== ABI differences detected in include/linux/bpf.h from HEAD~2 -> HEAD ====
+        [C] 'struct bpf_insn' changed:
+          type size hasn't changed
+          2 data member changes:
+            '__u8 dst_reg' offset changed from 8 to 12 (in bits) (by +4 bits)
+            '__u8 src_reg' offset changed from 12 to 8 (in bits) (by -4 bits)
+    ==============================================================================
+
+    error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Alternatively, we could have also run with ``-b HEAD~``. This would set the
+base reference to ``HEAD~`` so then the script would compare it to ``HEAD~^1``.
+
+Architecture-specific Headers
+-----------------------------
+
+Consider this change::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/arch/arm64/include/uapi/asm/sigcontext.h
+    +++ b/arch/arm64/include/uapi/asm/sigcontext.h
+    @@ -70,6 +70,7 @@ struct sigcontext {
+     struct _aarch64_ctx {
+            __u32 magic;
+            __u32 size;
+    +       __u32 new_var;
+     };
+
+     #define FPSIMD_MAGIC   0x46508001
+    EOF
+
+This is a change to an arm64-specific UAPI header file. In this example, I'm
+running the script from an x86 machine with an x86 compiler, so, by default,
+the script only checks x86-compatible UAPI header files::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    No changes to UAPI headers were applied between HEAD and dirty tree
+
+With an x86 compiler, we can't check header files in ``arch/arm64``, so the
+script doesn't even try.
+
+If we want to check the header file, we'll have to use an arm64 compiler and
+set ``ARCH`` accordingly::
+
+    % CC=aarch64-linux-gnu-gcc ARCH=arm64 ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== ABI differences detected in include/asm/sigcontext.h from HEAD -> dirty tree ====
+        [C] 'struct _aarch64_ctx' changed:
+          type size changed from 64 to 96 (in bits)
+          1 data member insertion:
+            '__u32 new_var', at offset 64 (in bits) at sigcontext.h:73:1
+        -- snip --
+        [C] 'struct zt_context' changed:
+          type size changed from 128 to 160 (in bits)
+          2 data member changes (1 filtered):
+            '__u16 nregs' offset changed from 64 to 96 (in bits) (by +32 bits)
+            '__u16 __reserved[3]' offset changed from 80 to 112 (in bits) (by +32 bits)
+    =======================================================================================
+
+    error - 1/884 UAPI headers compatible with arm64 appear _not_ to be backwards compatible
+
+We can see with ``ARCH`` and ``CC`` set properly for the file, the ABI
+change is reported properly. Also notice that the total number of UAPI
+header files checked by the script changes. This is because the number
+of headers installed for arm64 platforms is different than x86.
+
+Cross-Dependency Breakages
+--------------------------
+
+Consider this change::
+
+    cat << 'EOF' | patch -l -p1
+    --- a/include/uapi/linux/types.h
+    +++ b/include/uapi/linux/types.h
+    @@ -52,7 +52,7 @@ typedef __u32 __bitwise __wsum;
+     #define __aligned_be64 __be64 __attribute__((aligned(8)))
+     #define __aligned_le64 __le64 __attribute__((aligned(8)))
+
+    -typedef unsigned __bitwise __poll_t;
+    +typedef unsigned short __bitwise __poll_t;
+
+     #endif /*  __ASSEMBLY__ */
+     #endif /* _UAPI_LINUX_TYPES_H */
+    EOF
+
+Here, we're changing a ``typedef`` in ``types.h``. This doesn't break
+a UAPI in ``types.h``, but other UAPIs in the tree may break due to
+this change::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== ABI differences detected in include/linux/eventpoll.h from HEAD -> dirty tree ====
+        [C] 'struct epoll_event' changed:
+          type size changed from 96 to 80 (in bits)
+          2 data member changes:
+            type of '__poll_t events' changed:
+              underlying type 'unsigned int' changed:
+                type name changed from 'unsigned int' to 'unsigned short int'
+                type size changed from 32 to 16 (in bits)
+            '__u64 data' offset changed from 32 to 16 (in bits) (by -16 bits)
+    ========================================================================================
+    include/linux/eventpoll.h did not change between HEAD and dirty tree...
+    It's possible a change to one of the headers it includes caused this error:
+    #include <linux/fcntl.h>
+    #include <linux/types.h>
+
+Note that the script noticed the failing header file did not change,
+so it assumes one of its includes must have caused the breakage. Indeed,
+we can see ``linux/types.h`` is used from ``eventpoll.h``.
+
+UAPI Header Removals
+--------------------
+
+Consider this change::
+
+    cat << 'EOF' | patch -l -p1
+    diff --git a/include/uapi/asm-generic/Kbuild b/include/uapi/asm-generic/Kbuild
+    index ebb180aac74e..a9c88b0a8b3b 100644
+    --- a/include/uapi/asm-generic/Kbuild
+    +++ b/include/uapi/asm-generic/Kbuild
+    @@ -31,6 +31,6 @@ mandatory-y += stat.h
+     mandatory-y += statfs.h
+     mandatory-y += swab.h
+     mandatory-y += termbits.h
+    -mandatory-y += termios.h
+    +#mandatory-y += termios.h
+     mandatory-y += types.h
+     mandatory-y += unistd.h
+    EOF
+
+This script removes a UAPI header file from the install list. Let's run
+the script::
+
+    % ./scripts/check-uapi.sh
+    Installing user-facing UAPI headers from dirty tree... OK
+    Installing user-facing UAPI headers from HEAD... OK
+    Checking changes to UAPI headers between HEAD and dirty tree...
+    ==== UAPI header include/asm/termios.h was removed between HEAD and dirty tree ====
+
+    error - 1/912 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Removing a UAPI header is considered a breaking change, and the script
+will flag it as such.
+
+Checking Historic UAPI Compatibility
+------------------------------------
+
+You can use the ``-b`` and ``-p`` options to examine different chunks of your
+git tree. For example, to check all changed UAPI header files between tags
+v6.0 and v6.1, you'd run::
+
+    % ./scripts/check-uapi.sh -b v6.1 -p v6.0
+    Installing user-facing UAPI headers from v6.1... OK
+    Installing user-facing UAPI headers from v6.0... OK
+    Checking changes to UAPI headers between v6.0 and v6.1...
+
+    --- snip ---
+    error - 37/907 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+Note: Before v5.3, a header file needed by the script is not present,
+so the script is unable to check changes before then.
+
+You'll notice that the script detected many UAPI changes that are not
+backwards compatible. Knowing that kernel UAPIs are supposed to be stable
+forever, this is an alarming result. This brings us to the next section:
+caveats.
+
+Caveats
+=======
+
+The UAPI checker makes no assumptions about the author's intention, so some
+types of changes may be flagged even though they intentionally break UAPI.
+
+Removals For Refactoring or Deprecation
+---------------------------------------
+
+Sometimes drivers for very old hardware are removed, such as in this example::
+
+    % ./scripts/check-uapi.sh -b ba47652ba655
+    Installing user-facing UAPI headers from ba47652ba655... OK
+    Installing user-facing UAPI headers from ba47652ba655^1... OK
+    Checking changes to UAPI headers between ba47652ba655^1 and ba47652ba655...
+    ==== UAPI header include/linux/meye.h was removed between ba47652ba655^1 and ba47652ba655 ====
+
+    error - 1/910 UAPI headers compatible with x86 appear _not_ to be backwards compatible
+
+The script will always flag removals (even if they're intentional).
+
+Struct Expansions
+-----------------
+
+Depending on how a structure is handled in kernelspace, a change which
+expands a struct could be non-breaking.
+
+If a struct is used as the argument to an ioctl, then the kernel driver
+must be able to handle ioctl commands of any size. Beyond that, you need
+to be careful when copying data from the user. Say, for example, that
+``struct foo`` is changed like this::
+
+    struct foo {
+        __u64 a; /* added in version 1 */
+    +   __u32 b; /* added in version 2 */
+    +   __u32 c; /* added in version 2 */
+    }
+
+By default, the script will flag this kind of change for further review::
+
+    [C] 'struct foo' changed:
+      type size changed from 64 to 128 (in bits)
+      2 data member insertions:
+        '__u32 b', at offset 64 (in bits)
+        '__u32 c', at offset 96 (in bits)
+
+However, it is possible that this change was made safely.
+
+If a userspace program was built with version 1, it will think
+``sizeof(struct foo)`` is 8. That size will be encoded in the
+ioctl value that gets sent to the kernel. If the kernel is built
+with version 2, it will think the ``sizeof(struct foo)`` is 16.
+
+The kernel can use the ``_IOC_SIZE`` macro to get the size encoded
+in the ioctl code that the user passed in and then use
+``copy_struct_from_user()`` to safely copy the value::
+
+    int handle_ioctl(unsigned long cmd, unsigned long arg)
+    {
+        switch _IOC_NR(cmd) {
+        0x01: {
+            struct foo my_cmd;  /* size 16 in the kernel */
+
+            ret = copy_struct_from_user(&my_cmd, arg, sizeof(struct foo), _IOC_SIZE(cmd));
+            ...
+
+``copy_struct_from_user`` will zero the struct in the kernel and then copy
+only the bytes passed in from the user (leaving new members zeroized).
+If the user passed in a larger struct, the extra members are ignored.
+
+If you know this situation is accounted for in the kernel code, you can
+pass ``-i`` to the script, and struct expansions like this will be ignored.
+
+Flex Array Migration
+--------------------
+
+While the script handles expansion into an existing flex array, it does
+still flag initial migration to flex arrays from 1-element fake flex
+arrays. For example::
+
+    struct foo {
+          __u32 x;
+    -     __u32 flex[1]; /* fake flex */
+    +     __u32 flex[];  /* real flex */
+    };
+
+This change would be flagged by the script::
+
+    [C] 'struct foo' changed:
+      type size changed from 64 to 32 (in bits)
+      1 data member change:
+        type of '__u32 flex[1]' changed:
+          type name changed from '__u32[1]' to '__u32[]'
+          array type size changed from 32 to 'unknown'
+          array type subrange 1 changed length from 1 to 'unknown'
+
+At this time, there's no way to filter these types of changes, so be
+aware of this possible false positive.
+
+Summary
+-------
+
+While many types of false positives are filtered out by the script,
+it's possible there are some cases where the script flags a change
+which does not break UAPI. It's also possible a change which *does*
+break userspace would not be flagged by this script. While the script
+has been run on much of the kernel history, there could still be corner
+cases that are not accounted for.
+
+The intention is for this script to be used as a quick check for
+maintainers or automated tooling, not as the end-all authority on
+patch compatibility. It's best to remember: use your best judgment
+(and ideally a unit test in userspace) to make sure your UAPI changes
+are backwards-compatible!
diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst
index 6b0663075dc04..0876f5a2cf55a 100644
--- a/Documentation/dev-tools/index.rst
+++ b/Documentation/dev-tools/index.rst
@@ -34,6 +34,7 @@ Documentation/dev-tools/testing-overview.rst
    kselftest
    kunit/index
    ktap
+   checkuapi
 
 
 .. only::  subproject and html
-- 
GitLab


From 7beba04eb305393e3f8386390f25b4a9475f27f2 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 16 Dec 2023 01:06:37 +0900
Subject: [PATCH 2001/4076] kbuild: resolve symlinks for O= properly

Currently, Kbuild follows the logical chain of directories for the O=
option, just like 'cd' (or 'realpath --logical') does.

Example:

    $ mkdir -p /tmp/a /tmp/x/y
    $ ln -s /tmp/x/y /tmp/a/b
    $ realpath /tmp/a/b/..
    /tmp/x
    $ realpath --logical /tmp/a/b/..
    /tmp/a
    $ make O=/tmp/a/b/.. defconfig
    make[1]: Entering directory '/tmp/a'
      [snip]
    make[1]: Leaving directory '/tmp/a'

'make O=/tmp/a/b/.. defconfig' creates the kernel configuration in
/tmp/a instead of /tmp/x despite /tmp/a/b/.. resolves to /tmp/x.

This is because Kbuild internally uses the 'cd ... && pwd' for the
path resolution, but this behavior is not predictable for users.
Additionally, it is not consistent with how the Kbuild handles the
M= option or GNU Make works with 'make -C /tmp/a/b/..'.

Using the physical directory structure for the O= option seems more
reasonable.

The comment says "expand a shell special character '~'", but it has
already been expanded to the home directory in the command line.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 Makefile | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/Makefile b/Makefile
index 5a11804af640a..6204a3803a90f 100644
--- a/Makefile
+++ b/Makefile
@@ -190,14 +190,11 @@ ifeq ("$(origin O)", "command line")
 endif
 
 ifneq ($(KBUILD_OUTPUT),)
-# Make's built-in functions such as $(abspath ...), $(realpath ...) cannot
-# expand a shell special character '~'. We use a somewhat tedious way here.
-abs_objtree := $(shell mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd)
-$(if $(abs_objtree),, \
-     $(error failed to create output directory "$(KBUILD_OUTPUT)"))
-
+# $(realpath ...) gets empty if the path does not exist. Run 'mkdir -p' first.
+$(shell mkdir -p "$(KBUILD_OUTPUT)")
 # $(realpath ...) resolves symlinks
-abs_objtree := $(realpath $(abs_objtree))
+abs_objtree := $(realpath $(KBUILD_OUTPUT))
+$(if $(abs_objtree),,$(error failed to create output directory "$(KBUILD_OUTPUT)"))
 endif # ifneq ($(KBUILD_OUTPUT),)
 
 ifneq ($(words $(subst :, ,$(abs_srctree))), 1)
-- 
GitLab


From f3b2306bea33b3a86ad2df4dcfab53b629e1bc84 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Wed, 20 Dec 2023 00:33:15 +0000
Subject: [PATCH 2002/4076] gen_init_cpio: Apply mtime supplied by user to all
 file types

Currently gen_init_cpio -d <timestamp> is applied to symlinks,
directories and special files. These files are created by
gen_init_cpio from their description. Without <timestamp> option
current time(NULL) is used. And regular files that go in initramfs
are created before cpio generation, so their mtime(s) are preserved.

This is usually not an issue as reproducible builds should rebuild
everything in the distribution, including binaries, configs and whatever
other regular files may find their way into kernel's initramfs.

On the other hand, gen_initramfs.sh usage claims:
>	-d <date>      Use date for all file mtime values

Ar Arista initramfs files are managed with version control system
that preserves mtime. Those are configs, boot parameters, init scripts,
version files, platform-specific files, probably some others, too.

While it's certainly possible to work this around by copying the file
into temp directory and adjusting mtime prior to gen_init_cpio call,
I don't see why it needs workarounds.

The intended user of -d <date> option is the one that needs to create
a reproducible build, see commit a8b8017c34fe ("initramfs: Use
KBUILD_BUILD_TIMESTAMP for generated entries"). If a user wants
the build reproduction, they use -d <date>, which can be set on all
types of files, without surprising exceptions and workarounds.
Let's KISS here and just apply the time that user specified
with -d option.

Based-on-a-patch-by: Baptiste Covolato <baptiste@arista.com>
Link: https://lore.kernel.org/lkml/20181025215133.20138-1-baptiste@arista.com/
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 usr/gen_init_cpio.c | 33 +++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/usr/gen_init_cpio.c b/usr/gen_init_cpio.c
index 61230532fef10..edcdb8abfa31c 100644
--- a/usr/gen_init_cpio.c
+++ b/usr/gen_init_cpio.c
@@ -27,6 +27,7 @@
 static unsigned int offset;
 static unsigned int ino = 721;
 static time_t default_mtime;
+static bool do_file_mtime;
 static bool do_csum = false;
 
 struct file_handler {
@@ -329,6 +330,7 @@ static int cpio_mkfile(const char *name, const char *location,
 	int file;
 	int retval;
 	int rc = -1;
+	time_t mtime;
 	int namesize;
 	unsigned int i;
 	uint32_t csum = 0;
@@ -347,16 +349,21 @@ static int cpio_mkfile(const char *name, const char *location,
 		goto error;
 	}
 
-	if (buf.st_mtime > 0xffffffff) {
-		fprintf(stderr, "%s: Timestamp exceeds maximum cpio timestamp, clipping.\n",
-			location);
-		buf.st_mtime = 0xffffffff;
-	}
+	if (do_file_mtime) {
+		mtime = default_mtime;
+	} else {
+		mtime = buf.st_mtime;
+		if (mtime > 0xffffffff) {
+			fprintf(stderr, "%s: Timestamp exceeds maximum cpio timestamp, clipping.\n",
+					location);
+			mtime = 0xffffffff;
+		}
 
-	if (buf.st_mtime < 0) {
-		fprintf(stderr, "%s: Timestamp negative, clipping.\n",
-			location);
-		buf.st_mtime = 0;
+		if (mtime < 0) {
+			fprintf(stderr, "%s: Timestamp negative, clipping.\n",
+					location);
+			mtime = 0;
+		}
 	}
 
 	if (buf.st_size > 0xffffffff) {
@@ -387,7 +394,7 @@ static int cpio_mkfile(const char *name, const char *location,
 			(long) uid,		/* uid */
 			(long) gid,		/* gid */
 			nlinks,			/* nlink */
-			(long) buf.st_mtime,	/* mtime */
+			(long) mtime,		/* mtime */
 			size,			/* filesize */
 			3,			/* major */
 			1,			/* minor */
@@ -536,8 +543,9 @@ static void usage(const char *prog)
 		"file /sbin/kinit /usr/src/klibc/kinit/kinit 0755 0 0\n"
 		"\n"
 		"<timestamp> is time in seconds since Epoch that will be used\n"
-		"as mtime for symlinks, special files and directories. The default\n"
-		"is to use the current time for these entries.\n"
+		"as mtime for symlinks, directories, regular and special files.\n"
+		"The default is to use the current time for all files, but\n"
+		"preserve modification time for regular files.\n"
 		"-c: calculate and store 32-bit checksums for file data.\n",
 		prog);
 }
@@ -594,6 +602,7 @@ int main (int argc, char *argv[])
 				usage(argv[0]);
 				exit(1);
 			}
+			do_file_mtime = true;
 			break;
 		case 'c':
 			do_csum = true;
-- 
GitLab


From 9c65810cfb215f40f14d2c00694911fbc5408761 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Wed, 20 Dec 2023 00:40:49 +0900
Subject: [PATCH 2003/4076] kbuild: deb-pkg: split debian/copyright from the
 mkdebian script

Copy debian/copyright instead of generating it by the 'cat' command.

I also updated '2018' to '2023' while I was here.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/debian/copyright | 16 ++++++++++++++++
 scripts/package/mkdebian         | 21 +--------------------
 2 files changed, 17 insertions(+), 20 deletions(-)
 create mode 100644 scripts/package/debian/copyright

diff --git a/scripts/package/debian/copyright b/scripts/package/debian/copyright
new file mode 100644
index 0000000000000..4f1f06221f092
--- /dev/null
+++ b/scripts/package/debian/copyright
@@ -0,0 +1,16 @@
+This is a packaged upstream version of the Linux kernel.
+
+The sources may be found at most Linux archive sites, including:
+https://www.kernel.org/pub/linux/kernel
+
+Copyright: 1991 - 2023 Linus Torvalds and others.
+
+The git repository for mainline kernel development is at:
+git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; version 2 dated June, 1991.
+
+On Debian GNU/Linux systems, the complete text of the GNU General Public
+License version 2 can be found in `/usr/share/common-licenses/GPL-2'.
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index c1a36da85e84f..91f0e09600b11 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -188,26 +188,6 @@ $sourcename ($packageversion) $distribution; urgency=low
  -- $maintainer  $(date -R)
 EOF
 
-# Generate copyright file
-cat <<EOF > debian/copyright
-This is a packaged upstream version of the Linux kernel.
-
-The sources may be found at most Linux archive sites, including:
-https://www.kernel.org/pub/linux/kernel
-
-Copyright: 1991 - 2018 Linus Torvalds and others.
-
-The git repository for mainline kernel development is at:
-git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; version 2 dated June, 1991.
-
-On Debian GNU/Linux systems, the complete text of the GNU General Public
-License version 2 can be found in \`/usr/share/common-licenses/GPL-2'.
-EOF
-
 # Generate a control file
 cat <<EOF > debian/control
 Source: $sourcename
@@ -268,6 +248,7 @@ ARCH := ${ARCH}
 KERNELRELEASE := ${KERNELRELEASE}
 EOF
 
+cp "${srctree}/scripts/package/debian/copyright" debian/
 cp "${srctree}/scripts/package/debian/rules" debian/
 
 exit 0
-- 
GitLab


From b88365b6d74edc88a9d283c837fec05b13d401a6 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Wed, 20 Dec 2023 03:19:56 +0900
Subject: [PATCH 2004/4076] kbuild: deb-pkg: hard-code Build-Depends

The condition to require libelf-dev:native is stale because objtool is
now enabled by CONFIG_OBJTOOL instead of CONFIG_UNWINDER_ORC. Not only
objtool but also resolve_btfids requires libelf-dev:native; therefore,
CONFIG_DEBUG_INFO_BTF should be checked as well.

Similarly, CONFIG_SYSTEM_TRUSTED_KEYRING is not the only case that
requires libssl-dev:native.

Perhaps, the following code would provide better coverage, but it is
hard to maintain (and may still be imperfect).

  if is_enabled CONFIG_OBJTOOL ||
     is_enabled CONFIG_DEBUG_INFO_BTF; then
          build_depends="${build_depends}, libelf-dev:native"
  fi

  if is_enabled CONFIG_SYSTEM_TRUSTED_KEYRING ||
     is_enabled CONFIG_SYSTEM_REVOCATION_LIST ||
     is_enabled CONFIG_MODULE_SIG_FORMAT; then
          build_depends="${build_depends}, libssl-dev:native"
  fi

Let's hard-code the build dependency.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/mkdebian | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 91f0e09600b11..93a24712b9a1d 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -176,8 +176,6 @@ else
 fi
 
 echo $debarch > debian/arch
-extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev:native)"
-extra_build_depends="$extra_build_depends, $(if_enabled_echo CONFIG_SYSTEM_TRUSTED_KEYRING libssl-dev:native)"
 
 # Generate a simple changelog template
 cat <<EOF > debian/changelog
@@ -195,7 +193,8 @@ Section: kernel
 Priority: optional
 Maintainer: $maintainer
 Rules-Requires-Root: no
-Build-Depends: bc, debhelper, rsync, kmod, cpio, bison, flex $extra_build_depends
+Build-Depends: debhelper
+Build-Depends-Arch: bc, bison, cpio, flex, kmod, libelf-dev:native, libssl-dev:native, rsync
 Homepage: https://www.kernel.org/
 
 Package: $packagename-$version
-- 
GitLab


From 466e6fc43fb9eefa26ec766f78ce18616bf84b9a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 26 Dec 2023 22:52:38 +0900
Subject: [PATCH 2005/4076] kbuild: deb-pkg: factor out common Make options in
 debian/rules

This avoids code duplication between binary-arch and built-arch.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/debian/rules | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules
index 3dafa9496c636..26bc6239e200a 100755
--- a/scripts/package/debian/rules
+++ b/scripts/package/debian/rules
@@ -10,20 +10,20 @@ ifneq (,$(filter-out parallel=1,$(filter parallel=%,$(DEB_BUILD_OPTIONS))))
     MAKEFLAGS += -j$(NUMJOBS)
 endif
 
+make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE)
+
 .PHONY: binary binary-indep binary-arch
 binary: binary-arch binary-indep
 binary-indep: build-indep
 binary-arch: build-arch
-	$(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) \
-	KERNELRELEASE=$(KERNELRELEASE) \
+	$(MAKE) -f $(srctree)/Makefile $(make-opts) \
 	run-command KBUILD_RUN_COMMAND=+$(srctree)/scripts/package/builddeb
 
 .PHONY: build build-indep build-arch
 build: build-arch build-indep
 build-indep:
 build-arch:
-	$(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) \
-	KERNELRELEASE=$(KERNELRELEASE) \
+	$(MAKE) -f $(srctree)/Makefile $(make-opts) \
 	$(shell $(srctree)/scripts/package/deb-build-option) \
 	olddefconfig all
 
-- 
GitLab


From 7d4f07d5cb71728cea2b6fe8b087a0ce1dbda23a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 26 Dec 2023 22:52:39 +0900
Subject: [PATCH 2006/4076] kbuild: deb-pkg: squash
 scripts/package/deb-build-option to debian/rules

The binary-arch target needs to use the same CROSS_COMPILE as used in
build-arch; otherwise, 'make run-command' may attempt to resync the
.config file.

Squash scripts/package/deb-build-option into debian/rules, as it is a
small amount of code.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/deb-build-option | 14 --------------
 scripts/package/debian/rules     |  5 +++--
 2 files changed, 3 insertions(+), 16 deletions(-)
 delete mode 100755 scripts/package/deb-build-option

diff --git a/scripts/package/deb-build-option b/scripts/package/deb-build-option
deleted file mode 100755
index 7950eff01781a..0000000000000
--- a/scripts/package/deb-build-option
+++ /dev/null
@@ -1,14 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0-only
-
-# Set up CROSS_COMPILE if not defined yet
-if [ "${CROSS_COMPILE+set}" != "set" -a "${DEB_HOST_ARCH}" != "${DEB_BUILD_ARCH}" ]; then
-	echo CROSS_COMPILE=${DEB_HOST_GNU_TYPE}-
-fi
-
-version=$(dpkg-parsechangelog -S Version)
-debian_revision="${version##*-}"
-
-if [ "${version}" != "${debian_revision}" ]; then
-	echo KBUILD_BUILD_VERSION=${debian_revision}
-fi
diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules
index 26bc6239e200a..529b71b55efa5 100755
--- a/scripts/package/debian/rules
+++ b/scripts/package/debian/rules
@@ -10,7 +10,9 @@ ifneq (,$(filter-out parallel=1,$(filter parallel=%,$(DEB_BUILD_OPTIONS))))
     MAKEFLAGS += -j$(NUMJOBS)
 endif
 
-make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE)
+revision = $(lastword $(subst -, ,$(shell dpkg-parsechangelog -S Version)))
+CROSS_COMPILE ?= $(filter-out $(DEB_BUILD_GNU_TYPE)-, $(DEB_HOST_GNU_TYPE)-)
+make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) KBUILD_BUILD_VERSION=$(revision) $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE))
 
 .PHONY: binary binary-indep binary-arch
 binary: binary-arch binary-indep
@@ -24,7 +26,6 @@ build: build-arch build-indep
 build-indep:
 build-arch:
 	$(MAKE) -f $(srctree)/Makefile $(make-opts) \
-	$(shell $(srctree)/scripts/package/deb-build-option) \
 	olddefconfig all
 
 .PHONY: clean
-- 
GitLab


From 2cb54a19ac7153b9a26a72098c495187f64c2276 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Fri, 29 Dec 2023 06:54:41 -0800
Subject: [PATCH 2007/4076] apparmor: Fix ref count leak in task_kill

apparmor_task_kill was not putting the task_cred reference tc, or the
cred_label reference tc when dealing with a passed in cred, fix this
by using a single fn exit.

Fixes: 90c436a64a6e ("apparmor: pass cred through to audit info.")
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/lsm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 3eb992801a7f5..d851a6cc19d32 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -954,7 +954,6 @@ static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo
 		cl = aa_get_newest_cred_label(cred);
 		error = aa_may_signal(cred, cl, tc, tl, sig);
 		aa_put_label(cl);
-		return error;
 	} else {
 		cl = __begin_current_label_crit_section();
 		error = aa_may_signal(current_cred(), cl, tc, tl, sig);
-- 
GitLab


From 323925ed6dbb0ed877047b28fae4152527cc63db Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:14 +0100
Subject: [PATCH 2008/4076] RISC-V: paravirt: Add skeleton for pv-time support

Add the files and functions needed to support paravirt time on
RISC-V. Also include the common code needed for the first
application of pv-time, which is steal-time. In the next
patches we'll complete the functions to fully enable steal-time
support.

Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../admin-guide/kernel-parameters.txt         |  6 +-
 arch/riscv/include/asm/paravirt.h             | 28 +++++++
 arch/riscv/include/asm/paravirt_api_clock.h   |  1 +
 arch/riscv/kernel/Makefile                    |  1 +
 arch/riscv/kernel/paravirt.c                  | 79 +++++++++++++++++++
 arch/riscv/kernel/time.c                      |  3 +
 6 files changed, 115 insertions(+), 3 deletions(-)
 create mode 100644 arch/riscv/include/asm/paravirt.h
 create mode 100644 arch/riscv/include/asm/paravirt_api_clock.h
 create mode 100644 arch/riscv/kernel/paravirt.c

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 65731b060e3fe..a0d9259e48572 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3985,9 +3985,9 @@
 			vulnerability. System may allow data leaks with this
 			option.
 
-	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES] Disable paravirtualized
-			steal time accounting. steal time is computed, but
-			won't influence scheduler behaviour
+	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES,RISCV] Disable
+			paravirtualized steal time accounting. steal time is
+			computed, but won't influence scheduler behaviour
 
 	nosync		[HW,M68K] Disables sync negotiation for all devices.
 
diff --git a/arch/riscv/include/asm/paravirt.h b/arch/riscv/include/asm/paravirt.h
new file mode 100644
index 0000000000000..c0abde70fc2ce
--- /dev/null
+++ b/arch/riscv/include/asm/paravirt.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_PARAVIRT_H
+#define _ASM_RISCV_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+u64 dummy_steal_clock(int cpu);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return static_call(pv_steal_clock)(cpu);
+}
+
+int __init pv_time_init(void);
+
+#else
+
+#define pv_time_init() do {} while (0)
+
+#endif /* CONFIG_PARAVIRT */
+#endif /* _ASM_RISCV_PARAVIRT_H */
diff --git a/arch/riscv/include/asm/paravirt_api_clock.h b/arch/riscv/include/asm/paravirt_api_clock.h
new file mode 100644
index 0000000000000..65ac7cee0dad7
--- /dev/null
+++ b/arch/riscv/include/asm/paravirt_api_clock.h
@@ -0,0 +1 @@
+#include <asm/paravirt.h>
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index fee22a3d1b534..807c2bde1f83c 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -85,6 +85,7 @@ obj-$(CONFIG_SMP)		+= sbi-ipi.o
 obj-$(CONFIG_SMP) += cpu_ops_sbi.o
 endif
 obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_KEXEC_CORE)	+= kexec_relocate.o crash_save_regs.o machine_kexec.o
 obj-$(CONFIG_KEXEC_FILE)	+= elf_kexec.o machine_kexec_file.o
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
new file mode 100644
index 0000000000000..48d802df77399
--- /dev/null
+++ b/arch/riscv/kernel/paravirt.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ */
+
+#define pr_fmt(fmt) "riscv-pv: " fmt
+
+#include <linux/cpuhotplug.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/printk.h>
+#include <linux/static_call.h>
+#include <linux/types.h>
+
+#include <asm/paravirt.h>
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+
+static bool steal_acc = true;
+static int __init parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
+static bool __init has_pv_steal_clock(void)
+{
+	return false;
+}
+
+static int pv_time_cpu_online(unsigned int cpu)
+{
+	return 0;
+}
+
+static int pv_time_cpu_down_prepare(unsigned int cpu)
+{
+	return 0;
+}
+
+static u64 pv_time_steal_clock(int cpu)
+{
+	return 0;
+}
+
+int __init pv_time_init(void)
+{
+	int ret;
+
+	if (!has_pv_steal_clock())
+		return 0;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				"riscv/pv_time:online",
+				pv_time_cpu_online,
+				pv_time_cpu_down_prepare);
+	if (ret < 0)
+		return ret;
+
+	static_call_update(pv_steal_clock, pv_time_steal_clock);
+
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (steal_acc)
+		static_key_slow_inc(&paravirt_steal_rq_enabled);
+
+	pr_info("Computing paravirt steal-time\n");
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 23641e82a9df2..ba34771977897 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -12,6 +12,7 @@
 #include <asm/sbi.h>
 #include <asm/processor.h>
 #include <asm/timex.h>
+#include <asm/paravirt.h>
 
 unsigned long riscv_timebase __ro_after_init;
 EXPORT_SYMBOL_GPL(riscv_timebase);
@@ -45,4 +46,6 @@ void __init time_init(void)
 	timer_probe();
 
 	tick_setup_hrtimer_broadcast();
+
+	pv_time_init();
 }
-- 
GitLab


From 6cfc624576a64145b1d6d3d48de7161a7505f403 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:15 +0100
Subject: [PATCH 2009/4076] RISC-V: Add SBI STA extension definitions

The SBI STA extension enables steal-time accounting. Add the
definitions it specifies.

Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/sbi.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 0892f4421bc4a..b6f898c56940a 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -31,6 +31,7 @@ enum sbi_ext_id {
 	SBI_EXT_SRST = 0x53525354,
 	SBI_EXT_PMU = 0x504D55,
 	SBI_EXT_DBCN = 0x4442434E,
+	SBI_EXT_STA = 0x535441,
 
 	/* Experimentals extensions must lie within this range */
 	SBI_EXT_EXPERIMENTAL_START = 0x08000000,
@@ -243,6 +244,22 @@ enum sbi_ext_dbcn_fid {
 	SBI_EXT_DBCN_CONSOLE_WRITE_BYTE = 2,
 };
 
+/* SBI STA (steal-time accounting) extension */
+enum sbi_ext_sta_fid {
+	SBI_EXT_STA_STEAL_TIME_SET_SHMEM = 0,
+};
+
+struct sbi_sta_struct {
+	__le32 sequence;
+	__le32 flags;
+	__le64 steal;
+	u8 preempted;
+	u8 pad[47];
+} __packed;
+
+#define SBI_STA_SHMEM_DISABLE		-1
+
+/* SBI spec version fields */
 #define SBI_SPEC_VERSION_DEFAULT	0x1
 #define SBI_SPEC_VERSION_MAJOR_SHIFT	24
 #define SBI_SPEC_VERSION_MAJOR_MASK	0x7f
-- 
GitLab


From fdf68acccfc6af9497c34ee411d89af13b6516ed Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:16 +0100
Subject: [PATCH 2010/4076] RISC-V: paravirt: Implement steal-time support

When the SBI STA extension exists we can use it to implement
paravirt steal-time support. Fill in the empty pv-time functions
with an SBI STA implementation and add the Kconfig knobs allowing
it to be enabled.

Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/Kconfig           | 19 +++++++++++
 arch/riscv/kernel/paravirt.c | 62 ++++++++++++++++++++++++++++++++++--
 2 files changed, 78 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 24c1799e2ec49..ef8b7b012a0b5 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -724,6 +724,25 @@ config COMPAT
 
 	  If you want to execute 32-bit userspace applications, say Y.
 
+config PARAVIRT
+	bool "Enable paravirtualization code"
+	depends on RISCV_SBI
+	help
+	  This changes the kernel so it can modify itself when it is run
+	  under a hypervisor, potentially improving performance significantly
+	  over full virtualization.
+
+config PARAVIRT_TIME_ACCOUNTING
+	bool "Paravirtual steal time accounting"
+	depends on PARAVIRT
+	help
+	  Select this option to enable fine granularity task steal time
+	  accounting. Time spent executing other tasks in parallel with
+	  the current vCPU is discounted from the vCPU power. To account for
+	  that, there can be a small performance impact.
+
+	  If in doubt, say N here.
+
 config RELOCATABLE
 	bool "Build a relocatable kernel"
 	depends on MMU && 64BIT && !XIP_KERNEL
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
index 48d802df77399..8e114f5930cec 100644
--- a/arch/riscv/kernel/paravirt.c
+++ b/arch/riscv/kernel/paravirt.c
@@ -6,13 +6,21 @@
 #define pr_fmt(fmt) "riscv-pv: " fmt
 
 #include <linux/cpuhotplug.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/jump_label.h>
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/percpu-defs.h>
 #include <linux/printk.h>
 #include <linux/static_call.h>
 #include <linux/types.h>
 
+#include <asm/barrier.h>
+#include <asm/page.h>
 #include <asm/paravirt.h>
+#include <asm/sbi.h>
 
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
@@ -33,24 +41,72 @@ static int __init parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
+DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64);
+
 static bool __init has_pv_steal_clock(void)
 {
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_STA) > 0) {
+		pr_info("SBI STA extension detected\n");
+		return true;
+	}
+
 	return false;
 }
 
-static int pv_time_cpu_online(unsigned int cpu)
+static int sbi_sta_steal_time_set_shmem(unsigned long lo, unsigned long hi,
+					unsigned long flags)
 {
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_STA, SBI_EXT_STA_STEAL_TIME_SET_SHMEM,
+			lo, hi, flags, 0, 0, 0);
+	if (ret.error) {
+		if (lo == SBI_STA_SHMEM_DISABLE && hi == SBI_STA_SHMEM_DISABLE)
+			pr_warn("Failed to disable steal-time shmem");
+		else
+			pr_warn("Failed to set steal-time shmem");
+		return sbi_err_map_linux_errno(ret.error);
+	}
+
 	return 0;
 }
 
+static int pv_time_cpu_online(unsigned int cpu)
+{
+	struct sbi_sta_struct *st = this_cpu_ptr(&steal_time);
+	phys_addr_t pa = __pa(st);
+	unsigned long lo = (unsigned long)pa;
+	unsigned long hi = IS_ENABLED(CONFIG_32BIT) ? upper_32_bits((u64)pa) : 0;
+
+	return sbi_sta_steal_time_set_shmem(lo, hi, 0);
+}
+
 static int pv_time_cpu_down_prepare(unsigned int cpu)
 {
-	return 0;
+	return sbi_sta_steal_time_set_shmem(SBI_STA_SHMEM_DISABLE,
+					    SBI_STA_SHMEM_DISABLE, 0);
 }
 
 static u64 pv_time_steal_clock(int cpu)
 {
-	return 0;
+	struct sbi_sta_struct *st = per_cpu_ptr(&steal_time, cpu);
+	u32 sequence;
+	u64 steal;
+
+	/*
+	 * Check the sequence field before and after reading the steal
+	 * field. Repeat the read if it is different or odd.
+	 */
+	do {
+		sequence = READ_ONCE(st->sequence);
+		virt_rmb();
+		steal = READ_ONCE(st->steal);
+		virt_rmb();
+	} while ((le32_to_cpu(sequence) & 1) ||
+		 sequence != READ_ONCE(st->sequence));
+
+	return le64_to_cpu(steal);
 }
 
 int __init pv_time_init(void)
-- 
GitLab


From 5fed84a800e6048656c17be6e921787db2b5c6c0 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:17 +0100
Subject: [PATCH 2011/4076] RISC-V: KVM: Add SBI STA extension skeleton

Add the files and functions needed to support the SBI STA
(steal-time accounting) extension. In the next patches we'll
complete the functions to fully enable SBI STA support.

Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/kvm_vcpu_sbi.h |  1 +
 arch/riscv/include/uapi/asm/kvm.h     |  1 +
 arch/riscv/kvm/Makefile               |  1 +
 arch/riscv/kvm/vcpu_sbi.c             |  4 +++
 arch/riscv/kvm/vcpu_sbi_sta.c         | 47 +++++++++++++++++++++++++++
 5 files changed, 54 insertions(+)
 create mode 100644 arch/riscv/kvm/vcpu_sbi_sta.c

diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index bffda0ac59b61..99c23bb37a374 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -76,6 +76,7 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor;
 
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 60d3b21dead7d..e961d79622fbd 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -157,6 +157,7 @@ enum KVM_RISCV_SBI_EXT_ID {
 	KVM_RISCV_SBI_EXT_EXPERIMENTAL,
 	KVM_RISCV_SBI_EXT_VENDOR,
 	KVM_RISCV_SBI_EXT_DBCN,
+	KVM_RISCV_SBI_EXT_STA,
 	KVM_RISCV_SBI_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
index 4c2067fc59fcb..c9646521f1132 100644
--- a/arch/riscv/kvm/Makefile
+++ b/arch/riscv/kvm/Makefile
@@ -26,6 +26,7 @@ kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
 kvm-y += vcpu_sbi_base.o
 kvm-y += vcpu_sbi_replace.o
 kvm-y += vcpu_sbi_hsm.o
+kvm-y += vcpu_sbi_sta.o
 kvm-y += vcpu_timer.o
 kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o
 kvm-y += aia.o
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index dcdff44581906..088daaa23dd8a 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -70,6 +70,10 @@ static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = {
 		.ext_idx = KVM_RISCV_SBI_EXT_DBCN,
 		.ext_ptr = &vcpu_sbi_ext_dbcn,
 	},
+	{
+		.ext_idx = KVM_RISCV_SBI_EXT_STA,
+		.ext_ptr = &vcpu_sbi_ext_sta,
+	},
 	{
 		.ext_idx = KVM_RISCV_SBI_EXT_EXPERIMENTAL,
 		.ext_ptr = &vcpu_sbi_ext_experimental,
diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c
new file mode 100644
index 0000000000000..839911dcd8376
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_sbi_sta.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_vcpu_sbi.h>
+#include <asm/sbi.h>
+
+static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu)
+{
+	return SBI_ERR_FAILURE;
+}
+
+static int kvm_sbi_ext_sta_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				   struct kvm_vcpu_sbi_return *retdata)
+{
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long funcid = cp->a6;
+	int ret;
+
+	switch (funcid) {
+	case SBI_EXT_STA_STEAL_TIME_SET_SHMEM:
+		ret = kvm_sbi_sta_steal_time_set_shmem(vcpu);
+		break;
+	default:
+		ret = SBI_ERR_NOT_SUPPORTED;
+		break;
+	}
+
+	retdata->err_val = ret;
+
+	return 0;
+}
+
+static unsigned long kvm_sbi_ext_sta_probe(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta = {
+	.extid_start = SBI_EXT_STA,
+	.extid_end = SBI_EXT_STA,
+	.handler = kvm_sbi_ext_sta_handler,
+	.probe = kvm_sbi_ext_sta_probe,
+};
-- 
GitLab


From 2a1f6bf079700f0f9d8045ab77b302aeb4d12c06 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:18 +0100
Subject: [PATCH 2012/4076] RISC-V: KVM: Add steal-update vcpu request

Add a new vcpu request to inform a vcpu that it should record its
steal-time information. The request is made each time it has been
detected that the vcpu task was not assigned a cpu for some time,
which is easy to do by making the request from vcpu-load. The record
function is just a stub for now and will be filled in with the rest
of the steal-time support functions in following patches.

Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/kvm_host.h | 3 +++
 arch/riscv/kvm/vcpu.c             | 5 +++++
 arch/riscv/kvm/vcpu_sbi_sta.c     | 4 ++++
 3 files changed, 12 insertions(+)

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 0eefd9c991ae2..230b82c3118d5 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -41,6 +41,7 @@
 	KVM_ARCH_REQ_FLAGS(4, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_HFENCE			\
 	KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_STEAL_UPDATE		KVM_ARCH_REQ(6)
 
 enum kvm_riscv_hfence_type {
 	KVM_RISCV_HFENCE_UNKNOWN = 0,
@@ -372,4 +373,6 @@ bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask);
 void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
 
+void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu);
+
 #endif /* __RISCV_KVM_HOST_H__ */
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index bf3952d1a621f..6995b8b641e42 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -541,6 +541,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_riscv_vcpu_aia_load(vcpu, cpu);
 
+	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+
 	vcpu->cpu = cpu;
 }
 
@@ -614,6 +616,9 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_HFENCE, vcpu))
 			kvm_riscv_hfence_process(vcpu);
+
+		if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
+			kvm_riscv_vcpu_record_steal_time(vcpu);
 	}
 }
 
diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c
index 839911dcd8376..e28351c9488b3 100644
--- a/arch/riscv/kvm/vcpu_sbi_sta.c
+++ b/arch/riscv/kvm/vcpu_sbi_sta.c
@@ -8,6 +8,10 @@
 #include <asm/kvm_vcpu_sbi.h>
 #include <asm/sbi.h>
 
+void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu)
+{
+}
+
 static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu)
 {
 	return SBI_ERR_FAILURE;
-- 
GitLab


From 38b3390ee4880140b6245fe3273fe9ce53f65bde Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:19 +0100
Subject: [PATCH 2013/4076] RISC-V: KVM: Add SBI STA info to vcpu_arch

KVM's implementation of SBI STA needs to track the address of each
VCPU's steal-time shared memory region as well as the amount of
stolen time. Add a structure to vcpu_arch to contain this state
and make sure that the address is always set to INVALID_GPA on
vcpu reset. And, of course, ensure KVM won't try to update steal-
time when the shared memory address is invalid.

Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/kvm_host.h |  7 +++++++
 arch/riscv/kvm/vcpu.c             |  2 ++
 arch/riscv/kvm/vcpu_sbi_sta.c     | 10 ++++++++++
 3 files changed, 19 insertions(+)

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 230b82c3118d5..525cba63e0c53 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -263,6 +263,12 @@ struct kvm_vcpu_arch {
 
 	/* 'static' configurations which are set only once */
 	struct kvm_vcpu_config cfg;
+
+	/* SBI steal-time accounting */
+	struct {
+		gpa_t shmem;
+		u64 last_steal;
+	} sta;
 };
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
@@ -373,6 +379,7 @@ bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask);
 void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
 
+void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu);
 
 #endif /* __RISCV_KVM_HOST_H__ */
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 6995b8b641e42..b5ca9f2e98acd 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -83,6 +83,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	vcpu->arch.hfence_tail = 0;
 	memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue));
 
+	kvm_riscv_vcpu_sbi_sta_reset(vcpu);
+
 	/* Reset the guest CSRs for hotplug usecase */
 	if (loaded)
 		kvm_arch_vcpu_load(vcpu, smp_processor_id());
diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c
index e28351c9488b3..6592d287fc4e5 100644
--- a/arch/riscv/kvm/vcpu_sbi_sta.c
+++ b/arch/riscv/kvm/vcpu_sbi_sta.c
@@ -8,8 +8,18 @@
 #include <asm/kvm_vcpu_sbi.h>
 #include <asm/sbi.h>
 
+void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.sta.shmem = INVALID_GPA;
+	vcpu->arch.sta.last_steal = 0;
+}
+
 void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu)
 {
+	gpa_t shmem = vcpu->arch.sta.shmem;
+
+	if (shmem == INVALID_GPA)
+		return;
 }
 
 static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu)
-- 
GitLab


From 5b9e41321ba919dd051c68d2a1d2c753aa61634c Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:20 +0100
Subject: [PATCH 2014/4076] RISC-V: KVM: Add support for SBI extension
 registers

Some SBI extensions have state that needs to be saved / restored
when migrating the VM. Provide a get/set-one-reg register type
for SBI extension registers. Each SBI extension that uses this type
will have its own subtype. There are currently no subtypes defined.
The next patch introduces the first one.

Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/kvm_vcpu_sbi.h |  4 ++
 arch/riscv/include/uapi/asm/kvm.h     |  3 ++
 arch/riscv/kvm/vcpu_onereg.c          | 42 +++++++++++++++++--
 arch/riscv/kvm/vcpu_sbi.c             | 58 +++++++++++++++++++++++++++
 4 files changed, 103 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index 99c23bb37a374..dd60f73b5c36e 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -60,6 +60,10 @@ int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu,
 				   const struct kvm_one_reg *reg);
 int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu,
 				   const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_set_reg_sbi(struct kvm_vcpu *vcpu,
+			       const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_get_reg_sbi(struct kvm_vcpu *vcpu,
+			       const struct kvm_one_reg *reg);
 const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(
 				struct kvm_vcpu *vcpu, unsigned long extid);
 bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx);
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index e961d79622fbd..3471b1e48d180 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -242,6 +242,9 @@ enum KVM_RISCV_SBI_EXT_ID {
 #define KVM_REG_RISCV_VECTOR_REG(n)	\
 		((n) + sizeof(struct __riscv_v_ext_state) / sizeof(unsigned long))
 
+/* Registers for specific SBI extensions are mapped as type 10 */
+#define KVM_REG_RISCV_SBI_STATE		(0x0a << KVM_REG_RISCV_TYPE_SHIFT)
+
 /* Device Control API: RISC-V AIA */
 #define KVM_DEV_RISCV_APLIC_ALIGN		0x1000
 #define KVM_DEV_RISCV_APLIC_SIZE		0x4000
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index c0bad1aed9f09..143d0edd7f638 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -961,6 +961,29 @@ static unsigned long num_sbi_ext_regs(struct kvm_vcpu *vcpu)
 	return copy_sbi_ext_reg_indices(vcpu, NULL);
 }
 
+static inline unsigned long num_sbi_regs(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+static int copy_sbi_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	int n = num_sbi_regs(vcpu);
+
+	for (int i = 0; i < n; i++) {
+		u64 reg = KVM_REG_RISCV | KVM_REG_SIZE_U64 |
+			  KVM_REG_RISCV_SBI_STATE | i;
+
+		if (uindices) {
+			if (put_user(reg, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+	}
+
+	return n;
+}
+
 static inline unsigned long num_vector_regs(const struct kvm_vcpu *vcpu)
 {
 	if (!riscv_isa_extension_available(vcpu->arch.isa, v))
@@ -1028,6 +1051,7 @@ unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu)
 	res += num_vector_regs(vcpu);
 	res += num_isa_ext_regs(vcpu);
 	res += num_sbi_ext_regs(vcpu);
+	res += num_sbi_regs(vcpu);
 
 	return res;
 }
@@ -1083,6 +1107,12 @@ int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu,
 	ret = copy_sbi_ext_reg_indices(vcpu, uindices);
 	if (ret < 0)
 		return ret;
+	uindices += ret;
+
+	ret = copy_sbi_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
 
 	return 0;
 }
@@ -1105,12 +1135,14 @@ int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_FP_D:
 		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
 						 KVM_REG_RISCV_FP_D);
+	case KVM_REG_RISCV_VECTOR:
+		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg);
 	case KVM_REG_RISCV_ISA_EXT:
 		return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg);
 	case KVM_REG_RISCV_SBI_EXT:
 		return kvm_riscv_vcpu_set_reg_sbi_ext(vcpu, reg);
-	case KVM_REG_RISCV_VECTOR:
-		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg);
+	case KVM_REG_RISCV_SBI_STATE:
+		return kvm_riscv_vcpu_set_reg_sbi(vcpu, reg);
 	default:
 		break;
 	}
@@ -1136,12 +1168,14 @@ int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_FP_D:
 		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
 						 KVM_REG_RISCV_FP_D);
+	case KVM_REG_RISCV_VECTOR:
+		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg);
 	case KVM_REG_RISCV_ISA_EXT:
 		return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg);
 	case KVM_REG_RISCV_SBI_EXT:
 		return kvm_riscv_vcpu_get_reg_sbi_ext(vcpu, reg);
-	case KVM_REG_RISCV_VECTOR:
-		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg);
+	case KVM_REG_RISCV_SBI_STATE:
+		return kvm_riscv_vcpu_get_reg_sbi(vcpu, reg);
 	default:
 		break;
 	}
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index 088daaa23dd8a..a1997c39dfde3 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -325,6 +325,64 @@ int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+int kvm_riscv_vcpu_set_reg_sbi(struct kvm_vcpu *vcpu,
+			       const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_SBI_STATE);
+	unsigned long reg_subtype, reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
+	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_get_reg_sbi(struct kvm_vcpu *vcpu,
+			       const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_SBI_STATE);
+	unsigned long reg_subtype, reg_val;
+	int ret;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK;
+	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	default:
+		return -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
 const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(
 				struct kvm_vcpu *vcpu, unsigned long extid)
 {
-- 
GitLab


From f61ce890b1f0742f17b3a5d1f8c72574a33ffeb2 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:21 +0100
Subject: [PATCH 2015/4076] RISC-V: KVM: Add support for SBI STA registers

KVM userspace needs to be able to save and restore the steal-time
shared memory address. Provide the address through the get/set-one-reg
interface with two ulong-sized SBI STA extension registers (lo and hi).
64-bit KVM userspace must not set the hi register to anything other
than zero and is allowed to completely neglect saving/restoring it.

Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/kvm_vcpu_sbi.h |  5 +++
 arch/riscv/include/uapi/asm/kvm.h     |  9 +++++
 arch/riscv/kvm/vcpu_onereg.c          | 37 +++++++++++-------
 arch/riscv/kvm/vcpu_sbi.c             |  5 +++
 arch/riscv/kvm/vcpu_sbi_sta.c         | 55 +++++++++++++++++++++++++++
 5 files changed, 97 insertions(+), 14 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index dd60f73b5c36e..b96705258cf96 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -70,6 +70,11 @@ bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx);
 int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu);
 
+int kvm_riscv_vcpu_get_reg_sbi_sta(struct kvm_vcpu *vcpu, unsigned long reg_num,
+				   unsigned long *reg_val);
+int kvm_riscv_vcpu_set_reg_sbi_sta(struct kvm_vcpu *vcpu, unsigned long reg_num,
+				   unsigned long reg_val);
+
 #ifdef CONFIG_RISCV_SBI_V01
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01;
 #endif
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 3471b1e48d180..d6b7a5b958742 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -161,6 +161,12 @@ enum KVM_RISCV_SBI_EXT_ID {
 	KVM_RISCV_SBI_EXT_MAX,
 };
 
+/* SBI STA extension registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_sbi_sta {
+	unsigned long shmem_lo;
+	unsigned long shmem_hi;
+};
+
 /* Possible states for kvm_riscv_timer */
 #define KVM_RISCV_TIMER_STATE_OFF	0
 #define KVM_RISCV_TIMER_STATE_ON	1
@@ -244,6 +250,9 @@ enum KVM_RISCV_SBI_EXT_ID {
 
 /* Registers for specific SBI extensions are mapped as type 10 */
 #define KVM_REG_RISCV_SBI_STATE		(0x0a << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_STA		(0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_STA_REG(name)		\
+		(offsetof(struct kvm_riscv_sbi_sta, name) / sizeof(unsigned long))
 
 /* Device Control API: RISC-V AIA */
 #define KVM_DEV_RISCV_APLIC_ALIGN		0x1000
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 143d0edd7f638..fc34557f5356e 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -961,27 +961,36 @@ static unsigned long num_sbi_ext_regs(struct kvm_vcpu *vcpu)
 	return copy_sbi_ext_reg_indices(vcpu, NULL);
 }
 
-static inline unsigned long num_sbi_regs(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 static int copy_sbi_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
-	int n = num_sbi_regs(vcpu);
+	struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
+	int total = 0;
 
-	for (int i = 0; i < n; i++) {
-		u64 reg = KVM_REG_RISCV | KVM_REG_SIZE_U64 |
-			  KVM_REG_RISCV_SBI_STATE | i;
+	if (scontext->ext_status[KVM_RISCV_SBI_EXT_STA] == KVM_RISCV_SBI_EXT_STATUS_ENABLED) {
+		u64 size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+		int n = sizeof(struct kvm_riscv_sbi_sta) / sizeof(unsigned long);
 
-		if (uindices) {
-			if (put_user(reg, uindices))
-				return -EFAULT;
-			uindices++;
+		for (int i = 0; i < n; i++) {
+			u64 reg = KVM_REG_RISCV | size |
+				  KVM_REG_RISCV_SBI_STATE |
+				  KVM_REG_RISCV_SBI_STA | i;
+
+			if (uindices) {
+				if (put_user(reg, uindices))
+					return -EFAULT;
+				uindices++;
+			}
 		}
+
+		total += n;
 	}
 
-	return n;
+	return total;
+}
+
+static inline unsigned long num_sbi_regs(struct kvm_vcpu *vcpu)
+{
+	return copy_sbi_reg_indices(vcpu, NULL);
 }
 
 static inline unsigned long num_vector_regs(const struct kvm_vcpu *vcpu)
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index a1997c39dfde3..72a2ffb8dcd15 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -345,6 +345,8 @@ int kvm_riscv_vcpu_set_reg_sbi(struct kvm_vcpu *vcpu,
 	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
 
 	switch (reg_subtype) {
+	case KVM_REG_RISCV_SBI_STA:
+		return kvm_riscv_vcpu_set_reg_sbi_sta(vcpu, reg_num, reg_val);
 	default:
 		return -EINVAL;
 	}
@@ -370,6 +372,9 @@ int kvm_riscv_vcpu_get_reg_sbi(struct kvm_vcpu *vcpu,
 	reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK;
 
 	switch (reg_subtype) {
+	case KVM_REG_RISCV_SBI_STA:
+		ret = kvm_riscv_vcpu_get_reg_sbi_sta(vcpu, reg_num, &reg_val);
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c
index 6592d287fc4e5..87bf1a5f05ced 100644
--- a/arch/riscv/kvm/vcpu_sbi_sta.c
+++ b/arch/riscv/kvm/vcpu_sbi_sta.c
@@ -3,6 +3,8 @@
  * Copyright (c) 2023 Ventana Micro Systems Inc.
  */
 
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
 #include <linux/kvm_host.h>
 
 #include <asm/kvm_vcpu_sbi.h>
@@ -59,3 +61,56 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta = {
 	.handler = kvm_sbi_ext_sta_handler,
 	.probe = kvm_sbi_ext_sta_probe,
 };
+
+int kvm_riscv_vcpu_get_reg_sbi_sta(struct kvm_vcpu *vcpu,
+				   unsigned long reg_num,
+				   unsigned long *reg_val)
+{
+	switch (reg_num) {
+	case KVM_REG_RISCV_SBI_STA_REG(shmem_lo):
+		*reg_val = (unsigned long)vcpu->arch.sta.shmem;
+		break;
+	case KVM_REG_RISCV_SBI_STA_REG(shmem_hi):
+		if (IS_ENABLED(CONFIG_32BIT))
+			*reg_val = upper_32_bits(vcpu->arch.sta.shmem);
+		else
+			*reg_val = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_set_reg_sbi_sta(struct kvm_vcpu *vcpu,
+				   unsigned long reg_num,
+				   unsigned long reg_val)
+{
+	switch (reg_num) {
+	case KVM_REG_RISCV_SBI_STA_REG(shmem_lo):
+		if (IS_ENABLED(CONFIG_32BIT)) {
+			gpa_t hi = upper_32_bits(vcpu->arch.sta.shmem);
+
+			vcpu->arch.sta.shmem = reg_val;
+			vcpu->arch.sta.shmem |= hi << 32;
+		} else {
+			vcpu->arch.sta.shmem = reg_val;
+		}
+		break;
+	case KVM_REG_RISCV_SBI_STA_REG(shmem_hi):
+		if (IS_ENABLED(CONFIG_32BIT)) {
+			gpa_t lo = lower_32_bits(vcpu->arch.sta.shmem);
+
+			vcpu->arch.sta.shmem = ((gpa_t)reg_val << 32);
+			vcpu->arch.sta.shmem |= lo;
+		} else if (reg_val != 0) {
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
-- 
GitLab


From e9f12b5fff8ad0eefd0340273767d329ef65fd69 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:22 +0100
Subject: [PATCH 2016/4076] RISC-V: KVM: Implement SBI STA extension

Add a select SCHED_INFO to the KVM config in order to get run_delay
info. Then implement SBI STA's set-steal-time-shmem function and
kvm_riscv_vcpu_record_steal_time() to provide the steal-time info
to guests.

Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/Kconfig        |  1 +
 arch/riscv/kvm/vcpu_sbi_sta.c | 96 ++++++++++++++++++++++++++++++++++-
 2 files changed, 95 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index dfc237d7875b5..148e52b516cf5 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -32,6 +32,7 @@ config KVM
 	select KVM_XFER_TO_GUEST_WORK
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
+	select SCHED_INFO
 	help
 	  Support hosting virtualized guest machines.
 
diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c
index 87bf1a5f05ced..01f09fe8c3b02 100644
--- a/arch/riscv/kvm/vcpu_sbi_sta.c
+++ b/arch/riscv/kvm/vcpu_sbi_sta.c
@@ -6,9 +6,15 @@
 #include <linux/kconfig.h>
 #include <linux/kernel.h>
 #include <linux/kvm_host.h>
+#include <linux/mm.h>
+#include <linux/sizes.h>
 
+#include <asm/bug.h>
+#include <asm/current.h>
 #include <asm/kvm_vcpu_sbi.h>
+#include <asm/page.h>
 #include <asm/sbi.h>
+#include <asm/uaccess.h>
 
 void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu)
 {
@@ -19,14 +25,100 @@ void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu)
 void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu)
 {
 	gpa_t shmem = vcpu->arch.sta.shmem;
+	u64 last_steal = vcpu->arch.sta.last_steal;
+	u32 *sequence_ptr, sequence;
+	u64 *steal_ptr, steal;
+	unsigned long hva;
+	gfn_t gfn;
 
 	if (shmem == INVALID_GPA)
 		return;
+
+	/*
+	 * shmem is 64-byte aligned (see the enforcement in
+	 * kvm_sbi_sta_steal_time_set_shmem()) and the size of sbi_sta_struct
+	 * is 64 bytes, so we know all its offsets are in the same page.
+	 */
+	gfn = shmem >> PAGE_SHIFT;
+	hva = kvm_vcpu_gfn_to_hva(vcpu, gfn);
+
+	if (WARN_ON(kvm_is_error_hva(hva))) {
+		vcpu->arch.sta.shmem = INVALID_GPA;
+		return;
+	}
+
+	sequence_ptr = (u32 *)(hva + offset_in_page(shmem) +
+			       offsetof(struct sbi_sta_struct, sequence));
+	steal_ptr = (u64 *)(hva + offset_in_page(shmem) +
+			    offsetof(struct sbi_sta_struct, steal));
+
+	if (WARN_ON(get_user(sequence, sequence_ptr)))
+		return;
+
+	sequence = le32_to_cpu(sequence);
+	sequence += 1;
+
+	if (WARN_ON(put_user(cpu_to_le32(sequence), sequence_ptr)))
+		return;
+
+	if (!WARN_ON(get_user(steal, steal_ptr))) {
+		steal = le64_to_cpu(steal);
+		vcpu->arch.sta.last_steal = READ_ONCE(current->sched_info.run_delay);
+		steal += vcpu->arch.sta.last_steal - last_steal;
+		WARN_ON(put_user(cpu_to_le64(steal), steal_ptr));
+	}
+
+	sequence += 1;
+	WARN_ON(put_user(cpu_to_le32(sequence), sequence_ptr));
+
+	kvm_vcpu_mark_page_dirty(vcpu, gfn);
 }
 
 static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu)
 {
-	return SBI_ERR_FAILURE;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long shmem_phys_lo = cp->a0;
+	unsigned long shmem_phys_hi = cp->a1;
+	u32 flags = cp->a2;
+	struct sbi_sta_struct zero_sta = {0};
+	unsigned long hva;
+	bool writable;
+	gpa_t shmem;
+	int ret;
+
+	if (flags != 0)
+		return SBI_ERR_INVALID_PARAM;
+
+	if (shmem_phys_lo == SBI_STA_SHMEM_DISABLE &&
+	    shmem_phys_hi == SBI_STA_SHMEM_DISABLE) {
+		vcpu->arch.sta.shmem = INVALID_GPA;
+		return 0;
+	}
+
+	if (shmem_phys_lo & (SZ_64 - 1))
+		return SBI_ERR_INVALID_PARAM;
+
+	shmem = shmem_phys_lo;
+
+	if (shmem_phys_hi != 0) {
+		if (IS_ENABLED(CONFIG_32BIT))
+			shmem |= ((gpa_t)shmem_phys_hi << 32);
+		else
+			return SBI_ERR_INVALID_ADDRESS;
+	}
+
+	hva = kvm_vcpu_gfn_to_hva_prot(vcpu, shmem >> PAGE_SHIFT, &writable);
+	if (kvm_is_error_hva(hva) || !writable)
+		return SBI_ERR_INVALID_ADDRESS;
+
+	ret = kvm_vcpu_write_guest(vcpu, shmem, &zero_sta, sizeof(zero_sta));
+	if (ret)
+		return SBI_ERR_FAILURE;
+
+	vcpu->arch.sta.shmem = shmem;
+	vcpu->arch.sta.last_steal = current->sched_info.run_delay;
+
+	return 0;
 }
 
 static int kvm_sbi_ext_sta_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
@@ -52,7 +144,7 @@ static int kvm_sbi_ext_sta_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 static unsigned long kvm_sbi_ext_sta_probe(struct kvm_vcpu *vcpu)
 {
-	return 0;
+	return !!sched_info_on();
 }
 
 const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta = {
-- 
GitLab


From 0dcab5c4762ac166aa7e635ae4b6d649e15717e2 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:23 +0100
Subject: [PATCH 2017/4076] RISC-V: KVM: selftests: Move sbi_ecall to
 processor.c

sbi_ecall() isn't ucall specific and its prototype is already in
processor.h. Move its implementation to processor.c.

Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/lib/riscv/processor.c       | 26 +++++++++++++++++++
 tools/testing/selftests/kvm/lib/riscv/ucall.c | 26 -------------------
 2 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 6c25f7843ef44..6905a4348380c 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -367,3 +367,29 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
 {
 }
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+			unsigned long arg1, unsigned long arg2,
+			unsigned long arg3, unsigned long arg4,
+			unsigned long arg5)
+{
+	register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
+	register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
+	register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
+	register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
+	register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+	register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+	register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+	register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+	struct sbiret ret;
+
+	asm volatile (
+		"ecall"
+		: "+r" (a0), "+r" (a1)
+		: "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+		: "memory");
+	ret.error = a0;
+	ret.value = a1;
+
+	return ret;
+}
diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c
index fe6d1004f018c..14ee17151a590 100644
--- a/tools/testing/selftests/kvm/lib/riscv/ucall.c
+++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c
@@ -10,32 +10,6 @@
 #include "kvm_util.h"
 #include "processor.h"
 
-struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
-			unsigned long arg1, unsigned long arg2,
-			unsigned long arg3, unsigned long arg4,
-			unsigned long arg5)
-{
-	register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
-	register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
-	register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
-	register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
-	register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
-	register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
-	register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
-	register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
-	struct sbiret ret;
-
-	asm volatile (
-		"ecall"
-		: "+r" (a0), "+r" (a1)
-		: "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
-		: "memory");
-	ret.error = a0;
-	ret.value = a1;
-
-	return ret;
-}
-
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-- 
GitLab


From 945d880d6be0fd19bbc77d80d113bd2ca74c74f8 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:24 +0100
Subject: [PATCH 2018/4076] RISC-V: KVM: selftests: Add
 guest_sbi_probe_extension

Add guest_sbi_probe_extension(), allowing guest code to probe for
SBI extensions. As guest_sbi_probe_extension() needs
SBI_ERR_NOT_SUPPORTED, take the opportunity to bring in all SBI
error codes. We don't bring in all current extension IDs or base
extension function IDs though, even though we need one of each,
because we'd prefer to bring those in as necessary.

Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/include/riscv/processor.h   | 21 +++++++++++++++++++
 .../selftests/kvm/lib/riscv/processor.c       | 19 +++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index e70ccda2011bf..dc50ad62e150d 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -108,6 +108,17 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
 #define SATP_ASID_SHIFT				44
 #define SATP_ASID_MASK				_AC(0xFFFF, UL)
 
+/* SBI return error codes */
+#define SBI_SUCCESS				0
+#define SBI_ERR_FAILURE				-1
+#define SBI_ERR_NOT_SUPPORTED			-2
+#define SBI_ERR_INVALID_PARAM			-3
+#define SBI_ERR_DENIED				-4
+#define SBI_ERR_INVALID_ADDRESS			-5
+#define SBI_ERR_ALREADY_AVAILABLE		-6
+#define SBI_ERR_ALREADY_STARTED			-7
+#define SBI_ERR_ALREADY_STOPPED			-8
+
 #define SBI_EXT_EXPERIMENTAL_START		0x08000000
 #define SBI_EXT_EXPERIMENTAL_END		0x08FFFFFF
 
@@ -115,6 +126,14 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
 #define KVM_RISCV_SELFTESTS_SBI_UCALL		0
 #define KVM_RISCV_SELFTESTS_SBI_UNEXP		1
 
+enum sbi_ext_id {
+	SBI_EXT_BASE = 0x10,
+};
+
+enum sbi_ext_base_fid {
+	SBI_EXT_BASE_PROBE_EXT = 3,
+};
+
 struct sbiret {
 	long error;
 	long value;
@@ -125,4 +144,6 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
 			unsigned long arg3, unsigned long arg4,
 			unsigned long arg5);
 
+bool guest_sbi_probe_extension(int extid, long *out_val);
+
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 6905a4348380c..7ca736fb41940 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -393,3 +393,22 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
 
 	return ret;
 }
+
+bool guest_sbi_probe_extension(int extid, long *out_val)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid,
+			0, 0, 0, 0, 0);
+
+	__GUEST_ASSERT(!ret.error || ret.error == SBI_ERR_NOT_SUPPORTED,
+		       "ret.error=%ld, ret.value=%ld\n", ret.error, ret.value);
+
+	if (ret.error == SBI_ERR_NOT_SUPPORTED)
+		return false;
+
+	if (out_val)
+		*out_val = ret.value;
+
+	return true;
+}
-- 
GitLab


From 60b6e31c499643b25d4b3ccb4cc8e365dfdb8863 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:25 +0100
Subject: [PATCH 2019/4076] RISC-V: KVM: selftests: Add steal_time test support

With the introduction of steal-time accounting support for
RISC-V KVM we can add RISC-V support to the steal_time test.

Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/Makefile          |  5 +-
 .../selftests/kvm/include/riscv/processor.h   |  1 +
 tools/testing/selftests/kvm/steal_time.c      | 99 +++++++++++++++++++
 3 files changed, 103 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3e0c36b8ddd56..017efabcf502f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -184,12 +184,13 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test
 
 TEST_GEN_PROGS_riscv += demand_paging_test
 TEST_GEN_PROGS_riscv += dirty_log_test
-TEST_GEN_PROGS_riscv += guest_print_test
 TEST_GEN_PROGS_riscv += get-reg-list
+TEST_GEN_PROGS_riscv += guest_print_test
+TEST_GEN_PROGS_riscv += kvm_binary_stats_test
 TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
 TEST_GEN_PROGS_riscv += kvm_page_table_test
 TEST_GEN_PROGS_riscv += set_memory_region_test
-TEST_GEN_PROGS_riscv += kvm_binary_stats_test
+TEST_GEN_PROGS_riscv += steal_time
 
 SPLIT_TESTS += get-reg-list
 
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index dc50ad62e150d..a0f9efe5a2a8d 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -128,6 +128,7 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
 
 enum sbi_ext_id {
 	SBI_EXT_BASE = 0x10,
+	SBI_EXT_STA = 0x535441,
 };
 
 enum sbi_ext_base_fid {
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index 171adfb2a6cbc..bae0c5026f82f 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -11,7 +11,9 @@
 #include <pthread.h>
 #include <linux/kernel.h>
 #include <asm/kvm.h>
+#ifndef __riscv
 #include <asm/kvm_para.h>
+#endif
 
 #include "test_util.h"
 #include "kvm_util.h"
@@ -203,6 +205,103 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx)
 	pr_info("    st_time: %ld\n", st->st_time);
 }
 
+#elif defined(__riscv)
+
+/* SBI STA shmem must have 64-byte alignment */
+#define STEAL_TIME_SIZE		((sizeof(struct sta_struct) + 63) & ~63)
+
+static vm_paddr_t st_gpa[NR_VCPUS];
+
+struct sta_struct {
+	uint32_t sequence;
+	uint32_t flags;
+	uint64_t steal;
+	uint8_t preempted;
+	uint8_t pad[47];
+} __packed;
+
+static void sta_set_shmem(vm_paddr_t gpa, unsigned long flags)
+{
+	unsigned long lo = (unsigned long)gpa;
+#if __riscv_xlen == 32
+	unsigned long hi = (unsigned long)(gpa >> 32);
+#else
+	unsigned long hi = gpa == -1 ? -1 : 0;
+#endif
+	struct sbiret ret = sbi_ecall(SBI_EXT_STA, 0, lo, hi, flags, 0, 0, 0);
+
+	GUEST_ASSERT(ret.value == 0 && ret.error == 0);
+}
+
+static void check_status(struct sta_struct *st)
+{
+	GUEST_ASSERT(!(READ_ONCE(st->sequence) & 1));
+	GUEST_ASSERT(READ_ONCE(st->flags) == 0);
+	GUEST_ASSERT(READ_ONCE(st->preempted) == 0);
+}
+
+static void guest_code(int cpu)
+{
+	struct sta_struct *st = st_gva[cpu];
+	uint32_t sequence;
+	long out_val = 0;
+	bool probe;
+
+	probe = guest_sbi_probe_extension(SBI_EXT_STA, &out_val);
+	GUEST_ASSERT(probe && out_val == 1);
+
+	sta_set_shmem(st_gpa[cpu], 0);
+	GUEST_SYNC(0);
+
+	check_status(st);
+	WRITE_ONCE(guest_stolen_time[cpu], st->steal);
+	sequence = READ_ONCE(st->sequence);
+	check_status(st);
+	GUEST_SYNC(1);
+
+	check_status(st);
+	GUEST_ASSERT(sequence < READ_ONCE(st->sequence));
+	WRITE_ONCE(guest_stolen_time[cpu], st->steal);
+	check_status(st);
+	GUEST_DONE();
+}
+
+static bool is_steal_time_supported(struct kvm_vcpu *vcpu)
+{
+	uint64_t id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA);
+	unsigned long enabled;
+
+	vcpu_get_reg(vcpu, id, &enabled);
+	TEST_ASSERT(enabled == 0 || enabled == 1, "Expected boolean result");
+
+	return enabled;
+}
+
+static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i)
+{
+	/* ST_GPA_BASE is identity mapped */
+	st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE);
+	st_gpa[i] = addr_gva2gpa(vcpu->vm, (vm_vaddr_t)st_gva[i]);
+	sync_global_to_guest(vcpu->vm, st_gva[i]);
+	sync_global_to_guest(vcpu->vm, st_gpa[i]);
+}
+
+static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx)
+{
+	struct sta_struct *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]);
+	int i;
+
+	pr_info("VCPU%d:\n", vcpu_idx);
+	pr_info("    sequence:  %d\n", st->sequence);
+	pr_info("    flags:     %d\n", st->flags);
+	pr_info("    steal:     %"PRIu64"\n", st->steal);
+	pr_info("    preempted: %d\n", st->preempted);
+	pr_info("    pad:      ");
+	for (i = 0; i < 47; ++i)
+		pr_info("%d", st->pad[i]);
+	pr_info("\n");
+}
+
 #endif
 
 static void *do_steal_time(void *arg)
-- 
GitLab


From aad86da229bc9d0390dc2c02eb0db9ab1f50d059 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 20 Dec 2023 17:00:26 +0100
Subject: [PATCH 2020/4076] RISC-V: KVM: selftests: Add get-reg-list test for
 STA registers

Add SBI STA and its two registers to the get-reg-list test.

Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/riscv/get-reg-list.c        | 43 +++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index b8da2e86bf9c5..6652108816db4 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -71,6 +71,7 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR:
 		return true;
@@ -461,6 +462,7 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off)
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SRST),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_HSM),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_PMU),
+		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN),
@@ -509,6 +511,32 @@ static const char *sbi_ext_id_to_str(const char *prefix, __u64 id)
 	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
 }
 
+static const char *sbi_sta_id_to_str(__u64 reg_off)
+{
+	switch (reg_off) {
+	case 0: return "KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_lo)";
+	case 1: return "KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_hi)";
+	}
+	return strdup_printf("KVM_REG_RISCV_SBI_STA | %lld /* UNKNOWN */", reg_off);
+}
+
+static const char *sbi_id_to_str(const char *prefix, __u64 id)
+{
+	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_SBI_STATE);
+	__u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK;
+
+	assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_SBI_STATE);
+
+	reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK;
+
+	switch (reg_subtype) {
+	case KVM_REG_RISCV_SBI_STA:
+		return sbi_sta_id_to_str(reg_off);
+	}
+
+	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
+}
+
 void print_reg(const char *prefix, __u64 id)
 {
 	const char *reg_size = NULL;
@@ -565,6 +593,10 @@ void print_reg(const char *prefix, __u64 id)
 		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_SBI_EXT | %s,\n",
 				reg_size, sbi_ext_id_to_str(prefix, id));
 		break;
+	case KVM_REG_RISCV_SBI_STATE:
+		printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_SBI_STATE | %s,\n",
+				reg_size, sbi_id_to_str(prefix, id));
+		break;
 	default:
 		printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,\n",
 				reg_size, id & ~REG_MASK);
@@ -651,6 +683,12 @@ static __u64 sbi_base_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR,
 };
 
+static __u64 sbi_sta_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_lo),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_hi),
+};
+
 static __u64 zicbom_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM,
@@ -757,6 +795,9 @@ static __u64 fp_d_regs[] = {
 #define SUBLIST_SBI_BASE \
 	{"sbi-base", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_V01, \
 	 .regs = sbi_base_regs, .regs_n = ARRAY_SIZE(sbi_base_regs),}
+#define SUBLIST_SBI_STA \
+	{"sbi-sta", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_STA, \
+	 .regs = sbi_sta_regs, .regs_n = ARRAY_SIZE(sbi_sta_regs),}
 #define SUBLIST_ZICBOM \
 	{"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),}
 #define SUBLIST_ZICBOZ \
@@ -832,6 +873,7 @@ static struct vcpu_reg_list config_sbi_##ext = {		\
 /* Note: The below list is alphabetically sorted. */
 
 KVM_SBI_EXT_SUBLIST_CONFIG(base, BASE);
+KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA);
 KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU);
 KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN);
 
@@ -858,6 +900,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
 
 struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_base,
+	&config_sbi_sta,
 	&config_sbi_pmu,
 	&config_sbi_dbcn,
 	&config_aia,
-- 
GitLab


From 682fb5be353117b7321f1dfb65b7bb98cbfe59ab Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Thu, 21 Dec 2023 13:54:03 +0100
Subject: [PATCH 2021/4076] MIPS: Allow vectored interrupt handler to reside
 everywhere for 64bit

Setting up vector interrupts worked only with handlers, which resided
in CKSEG0 space. This limits the kernel placement for 64bit platforms.
By patching in the offset into vi_handlers[] instead of the full
handler address, the vectored exception handler can load the
address by itself and jump to it.

Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Reviewed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
---
 arch/mips/kernel/genex.S | 8 ++++----
 arch/mips/kernel/traps.c | 9 +++------
 2 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index b6de8e88c1bd4..a572ce36a24f2 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -272,18 +272,17 @@ NESTED(except_vec_vi, 0, sp)
 	.set	push
 	.set	noreorder
 	PTR_LA	v1, except_vec_vi_handler
-FEXPORT(except_vec_vi_lui)
-	lui	v0, 0		/* Patched */
 	jr	v1
 FEXPORT(except_vec_vi_ori)
-	 ori	v0, 0		/* Patched */
+	 ori	v0, zero, 0		/* Offset in vi_handlers[] */
 	.set	pop
 	END(except_vec_vi)
 EXPORT(except_vec_vi_end)
 
 /*
  * Common Vectored Interrupt code
- * Complete the register saves and invoke the handler which is passed in $v0
+ * Complete the register saves and invoke the handler, $v0 holds
+ * offset into vi_handlers[]
  */
 NESTED(except_vec_vi_handler, 0, sp)
 	SAVE_TEMP
@@ -331,6 +330,7 @@ NESTED(except_vec_vi_handler, 0, sp)
 	/* Save task's sp on IRQ stack so that unwinding can follow it */
 	LONG_S	s1, 0(sp)
 2:
+	PTR_L	v0, vi_handlers(v0)
 	jalr	v0
 
 	/* Restore sp */
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 246c6a6b02614..d90b189086926 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2091,16 +2091,14 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 		 * If no shadow set is selected then use the default handler
 		 * that does normal register saving and standard interrupt exit
 		 */
-		extern const u8 except_vec_vi[], except_vec_vi_lui[];
+		extern const u8 except_vec_vi[];
 		extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
 		extern const u8 rollback_except_vec_vi[];
 		const u8 *vec_start = using_rollback_handler() ?
 				      rollback_except_vec_vi : except_vec_vi;
 #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
-		const int lui_offset = except_vec_vi_lui - vec_start + 2;
 		const int ori_offset = except_vec_vi_ori - vec_start + 2;
 #else
-		const int lui_offset = except_vec_vi_lui - vec_start;
 		const int ori_offset = except_vec_vi_ori - vec_start;
 #endif
 		const int handler_len = except_vec_vi_end - vec_start;
@@ -2119,10 +2117,9 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 #else
 				handler_len);
 #endif
-		h = (u16 *)(b + lui_offset);
-		*h = (handler >> 16) & 0xffff;
+		/* insert offset into vi_handlers[] */
 		h = (u16 *)(b + ori_offset);
-		*h = (handler & 0xffff);
+		*h = n * sizeof(handler);
 		local_flush_icache_range((unsigned long)b,
 					 (unsigned long)(b+handler_len));
 	}
-- 
GitLab


From 8e1803900ef1b61ed33e6963d9e6a95028b41110 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Thu, 21 Dec 2023 13:54:04 +0100
Subject: [PATCH 2022/4076] MIPS: Remove unused shadow GPR support from vector
 irq setup

Using shadow GPRs for vectored interrupts has never been used,
time to remove it.

Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/traps.c | 88 ++++++++++++----------------------------
 1 file changed, 27 insertions(+), 61 deletions(-)

diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index d90b189086926..c1b2b18b05053 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2055,105 +2055,71 @@ static void do_default_vi(void)
 	panic("Caught unexpected vectored interrupt.");
 }
 
-static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
+void *set_vi_handler(int n, vi_handler_t addr)
 {
+	extern const u8 except_vec_vi[];
+	extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
+	extern const u8 rollback_except_vec_vi[];
 	unsigned long handler;
 	unsigned long old_handler = vi_handlers[n];
 	int srssets = current_cpu_data.srsets;
 	u16 *h;
 	unsigned char *b;
+	const u8 *vec_start;
+	int ori_offset;
+	int handler_len;
 
 	BUG_ON(!cpu_has_veic && !cpu_has_vint);
 
 	if (addr == NULL) {
 		handler = (unsigned long) do_default_vi;
-		srs = 0;
 	} else
 		handler = (unsigned long) addr;
 	vi_handlers[n] = handler;
 
 	b = (unsigned char *)(ebase + 0x200 + n*VECTORSPACING);
 
-	if (srs >= srssets)
-		panic("Shadow register set %d not supported", srs);
-
 	if (cpu_has_veic) {
 		if (board_bind_eic_interrupt)
-			board_bind_eic_interrupt(n, srs);
+			board_bind_eic_interrupt(n, 0);
 	} else if (cpu_has_vint) {
 		/* SRSMap is only defined if shadow sets are implemented */
 		if (srssets > 1)
-			change_c0_srsmap(0xf << n*4, srs << n*4);
+			change_c0_srsmap(0xf << n*4, 0 << n*4);
 	}
 
-	if (srs == 0) {
-		/*
-		 * If no shadow set is selected then use the default handler
-		 * that does normal register saving and standard interrupt exit
-		 */
-		extern const u8 except_vec_vi[];
-		extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
-		extern const u8 rollback_except_vec_vi[];
-		const u8 *vec_start = using_rollback_handler() ?
-				      rollback_except_vec_vi : except_vec_vi;
+	vec_start = using_rollback_handler() ? rollback_except_vec_vi :
+					       except_vec_vi;
 #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
-		const int ori_offset = except_vec_vi_ori - vec_start + 2;
+	ori_offset = except_vec_vi_ori - vec_start + 2;
 #else
-		const int ori_offset = except_vec_vi_ori - vec_start;
+	ori_offset = except_vec_vi_ori - vec_start;
 #endif
-		const int handler_len = except_vec_vi_end - vec_start;
-
-		if (handler_len > VECTORSPACING) {
-			/*
-			 * Sigh... panicing won't help as the console
-			 * is probably not configured :(
-			 */
-			panic("VECTORSPACING too small");
-		}
+	handler_len = except_vec_vi_end - vec_start;
 
-		set_handler(((unsigned long)b - ebase), vec_start,
-#ifdef CONFIG_CPU_MICROMIPS
-				(handler_len - 1));
-#else
-				handler_len);
-#endif
-		/* insert offset into vi_handlers[] */
-		h = (u16 *)(b + ori_offset);
-		*h = n * sizeof(handler);
-		local_flush_icache_range((unsigned long)b,
-					 (unsigned long)(b+handler_len));
-	}
-	else {
+	if (handler_len > VECTORSPACING) {
 		/*
-		 * In other cases jump directly to the interrupt handler. It
-		 * is the handler's responsibility to save registers if required
-		 * (eg hi/lo) and return from the exception using "eret".
+		 * Sigh... panicing won't help as the console
+		 * is probably not configured :(
 		 */
-		u32 insn;
+		panic("VECTORSPACING too small");
+	}
 
-		h = (u16 *)b;
-		/* j handler */
+	set_handler(((unsigned long)b - ebase), vec_start,
 #ifdef CONFIG_CPU_MICROMIPS
-		insn = 0xd4000000 | (((u32)handler & 0x07ffffff) >> 1);
+			(handler_len - 1));
 #else
-		insn = 0x08000000 | (((u32)handler & 0x0fffffff) >> 2);
+			handler_len);
 #endif
-		h[0] = (insn >> 16) & 0xffff;
-		h[1] = insn & 0xffff;
-		h[2] = 0;
-		h[3] = 0;
-		local_flush_icache_range((unsigned long)b,
-					 (unsigned long)(b+8));
-	}
+	/* insert offset into vi_handlers[] */
+	h = (u16 *)(b + ori_offset);
+	*h = n * sizeof(handler);
+	local_flush_icache_range((unsigned long)b,
+				 (unsigned long)(b+handler_len));
 
 	return (void *)old_handler;
 }
 
-void *set_vi_handler(int n, vi_handler_t addr)
-{
-	return set_vi_srs_handler(n, addr, 0);
-}
-
 extern void tlb_init(void);
 
 /*
-- 
GitLab


From 0eccea7150e3b8dfb3a08694964478966525c4c3 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 10 Dec 2023 18:50:03 +0100
Subject: [PATCH 2023/4076] PCI: vmd: Remove usage of the deprecated
 ida_simple_*() API
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove() functions.

This is also less verbose.

Link: https://lore.kernel.org/linux-pci/270f25cdc154f3b0309e57b2f6421776752e2170.1702230593.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/vmd.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 94ba61fe1c441..00a4264711f1b 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -984,7 +984,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	vmd->dev = dev;
-	vmd->instance = ida_simple_get(&vmd_instance_ida, 0, 0, GFP_KERNEL);
+	vmd->instance = ida_alloc(&vmd_instance_ida, GFP_KERNEL);
 	if (vmd->instance < 0)
 		return vmd->instance;
 
@@ -1026,7 +1026,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	return 0;
 
  out_release_instance:
-	ida_simple_remove(&vmd_instance_ida, vmd->instance);
+	ida_free(&vmd_instance_ida, vmd->instance);
 	return err;
 }
 
@@ -1048,7 +1048,7 @@ static void vmd_remove(struct pci_dev *dev)
 	vmd_cleanup_srcu(vmd);
 	vmd_detach_resources(vmd);
 	vmd_remove_irq_domain(vmd);
-	ida_simple_remove(&vmd_instance_ida, vmd->instance);
+	ida_free(&vmd_instance_ida, vmd->instance);
 }
 
 static void vmd_shutdown(struct pci_dev *dev)
-- 
GitLab


From 130f335630b6475d314658ef69b225db8e328daa Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 19 Dec 2023 07:15:37 +0100
Subject: [PATCH 2024/4076] misc: pci_endpoint_test: Remove usage of the
 deprecated ida_simple_*() API
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove() functions.

This is also less verbose.

Link: https://lore.kernel.org/linux-pci/47a30441242c4d5f0e00555cbddd7783350ff1b2.1702966523.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/misc/pci_endpoint_test.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index af519088732d9..34124bdce68ca 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -860,7 +860,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 
 	pci_set_drvdata(pdev, test);
 
-	id = ida_simple_get(&pci_endpoint_test_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&pci_endpoint_test_ida, GFP_KERNEL);
 	if (id < 0) {
 		err = id;
 		dev_err(dev, "Unable to get id\n");
@@ -907,7 +907,7 @@ err_kfree_test_name:
 	kfree(test->name);
 
 err_ida_remove:
-	ida_simple_remove(&pci_endpoint_test_ida, id);
+	ida_free(&pci_endpoint_test_ida, id);
 
 err_iounmap:
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
@@ -943,7 +943,7 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev)
 	misc_deregister(&test->miscdev);
 	kfree(misc_device->name);
 	kfree(test->name);
-	ida_simple_remove(&pci_endpoint_test_ida, id);
+	ida_free(&pci_endpoint_test_ida, id);
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
 		if (test->bar[bar])
 			pci_iounmap(pdev, test->bar[bar]);
-- 
GitLab


From 0171e067d7daf06374c3e9c6ddf1a99fca10469c Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 19 Dec 2023 07:09:54 +0100
Subject: [PATCH 2025/4076] dw-xdata: Remove usage of the deprecated
 ida_simple_*() API
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove() functions.

This is also less verbose.

Link: https://lore.kernel.org/linux-pci/cc01721cec2d416d7bdf47086943b17ef44b7286.1702966181.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/misc/dw-xdata-pcie.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/misc/dw-xdata-pcie.c b/drivers/misc/dw-xdata-pcie.c
index 257c25da51996..efd0ca8cc925d 100644
--- a/drivers/misc/dw-xdata-pcie.c
+++ b/drivers/misc/dw-xdata-pcie.c
@@ -333,7 +333,7 @@ static int dw_xdata_pcie_probe(struct pci_dev *pdev,
 
 	dw->pdev = pdev;
 
-	id = ida_simple_get(&xdata_ida, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&xdata_ida, GFP_KERNEL);
 	if (id < 0) {
 		dev_err(dev, "xData: unable to get id\n");
 		return id;
@@ -377,7 +377,7 @@ err_kfree_name:
 	kfree(dw->misc_dev.name);
 
 err_ida_remove:
-	ida_simple_remove(&xdata_ida, id);
+	ida_free(&xdata_ida, id);
 
 	return err;
 }
@@ -396,7 +396,7 @@ static void dw_xdata_pcie_remove(struct pci_dev *pdev)
 	dw_xdata_stop(dw);
 	misc_deregister(&dw->misc_dev);
 	kfree(dw->misc_dev.name);
-	ida_simple_remove(&xdata_ida, id);
+	ida_free(&xdata_ida, id);
 }
 
 static const struct pci_device_id dw_xdata_pcie_id_table[] = {
-- 
GitLab


From 65cdd3ada7dcec1863022b2ca218ae409f99c759 Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Mon, 1 Jan 2024 14:02:06 -0600
Subject: [PATCH 2026/4076] dt-bindings: input: iqs269a: Add bindings for
 slider gestures

This patch adds bindings for slider gestures that can be expressed
by the device.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/ZZMaPrbSi4IrzwKF@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/iqs269a.yaml    | 68 +++++++++++++++++++
 1 file changed, 68 insertions(+)

diff --git a/Documentation/devicetree/bindings/input/iqs269a.yaml b/Documentation/devicetree/bindings/input/iqs269a.yaml
index 3c430d38594f1..b42f07542d27d 100644
--- a/Documentation/devicetree/bindings/input/iqs269a.yaml
+++ b/Documentation/devicetree/bindings/input/iqs269a.yaml
@@ -9,6 +9,9 @@ title: Azoteq IQS269A Capacitive Touch Controller
 maintainers:
   - Jeff LaBundy <jeff@labundy.com>
 
+allOf:
+  - $ref: input.yaml#
+
 description: |
   The Azoteq IQS269A is an 8-channel capacitive touch controller that features
   additional Hall-effect and inductive sensing capabilities.
@@ -204,6 +207,63 @@ properties:
     default: 1
     description: Specifies the slider coordinate filter strength.
 
+  linux,keycodes:
+    minItems: 1
+    maxItems: 8
+    description: |
+      Specifies the numeric keycodes associated with each available gesture in
+      the following order (enter 0 for unused gestures):
+      0: Slider 0 tap
+      1: Slider 0 hold
+      2: Slider 0 positive flick or swipe
+      3: Slider 0 negative flick or swipe
+      4: Slider 1 tap
+      5: Slider 1 hold
+      6: Slider 1 positive flick or swipe
+      7: Slider 1 negative flick or swipe
+
+  azoteq,gesture-swipe:
+    type: boolean
+    description:
+      Directs the device to interpret axial gestures as a swipe (finger remains
+      on slider) instead of a flick (finger leaves slider).
+
+  azoteq,timeout-tap-ms:
+    multipleOf: 16
+    minimum: 0
+    maximum: 4080
+    default: 400
+    description:
+      Specifies the length of time (in ms) within which a slider touch must be
+      released in order to be interpreted as a tap. Default and maximum values
+      as well as step size are reduced by a factor of 4 with device version 2.
+
+  azoteq,timeout-swipe-ms:
+    multipleOf: 16
+    minimum: 0
+    maximum: 4080
+    default: 2000
+    description:
+      Specifies the length of time (in ms) within which an axial gesture must be
+      completed in order to be interpreted as a flick or swipe. Default and max-
+      imum values as well as step size are reduced by a factor of 4 with device
+      version 2.
+
+  azoteq,thresh-swipe:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 255
+    default: 128
+    description:
+      Specifies the number of points across which an axial gesture must travel
+      in order to be interpreted as a flick or swipe.
+
+dependencies:
+  azoteq,gesture-swipe: ["linux,keycodes"]
+  azoteq,timeout-tap-ms: ["linux,keycodes"]
+  azoteq,timeout-swipe-ms: ["linux,keycodes"]
+  azoteq,thresh-swipe: ["linux,keycodes"]
+
 patternProperties:
   "^channel@[0-7]$":
     type: object
@@ -484,6 +544,14 @@ examples:
                     azoteq,hall-enable;
                     azoteq,suspend-mode = <2>;
 
+                    linux,keycodes = <KEY_PLAYPAUSE>,
+                                     <KEY_STOPCD>,
+                                     <KEY_NEXTSONG>,
+                                     <KEY_PREVIOUSSONG>;
+
+                    azoteq,timeout-tap-ms = <400>;
+                    azoteq,timeout-swipe-ms = <800>;
+
                     channel@0 {
                             reg = <0x0>;
 
-- 
GitLab


From 00521a9bf96eaab358886d7a0c531d52027d3241 Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Mon, 1 Jan 2024 14:02:23 -0600
Subject: [PATCH 2027/4076] Input: iqs269a - add support for slider gestures

This patch adds support for slider gestures that can be expressed
by the device. Each gesture (e.g. tap or hold) can be mapped to a
unique keycode for either slider 0 or 1.

With this change, raw slider coordinates are reported only if the
slider has no keycodes defined. This prevents unwanted mouse cur-
sor movement when expressing axial gestures (e.g. swipe) and also
eliminates some unnecessary I2C traffic.

Different revisions of silicon use different tap and swipe timeout
step sizes. Apply an appropriate scaling factor depending on which
revision is found.

To facilitate this change, store the iqs269_ver_info struct in the
driver's private data so that other functions can use it after the
driver has probed.

Last but not least, a former reserved field in iqs269_ver_info now
contains useful information; give it a name (fw_num).

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/ZZMaT46WQq1/Nrsb@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs269a.c | 220 ++++++++++++++++++++++++++++++-----
 1 file changed, 191 insertions(+), 29 deletions(-)

diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c
index 1abce35b955e4..0d0b5cdc78303 100644
--- a/drivers/input/misc/iqs269a.c
+++ b/drivers/input/misc/iqs269a.c
@@ -9,6 +9,7 @@
  * axial sliders presented by the device.
  */
 
+#include <linux/bits.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -26,6 +27,8 @@
 
 #define IQS269_VER_INFO				0x00
 #define IQS269_VER_INFO_PROD_NUM		0x4F
+#define IQS269_VER_INFO_FW_NUM_2		0x03
+#define IQS269_VER_INFO_FW_NUM_3		0x10
 
 #define IQS269_SYS_FLAGS			0x02
 #define IQS269_SYS_FLAGS_SHOW_RESET		BIT(15)
@@ -53,6 +56,7 @@
 #define IQS269_SYS_SETTINGS_ULP_UPDATE_MASK	GENMASK(10, 8)
 #define IQS269_SYS_SETTINGS_ULP_UPDATE_SHIFT	8
 #define IQS269_SYS_SETTINGS_ULP_UPDATE_MAX	7
+#define IQS269_SYS_SETTINGS_SLIDER_SWIPE	BIT(7)
 #define IQS269_SYS_SETTINGS_RESEED_OFFSET	BIT(6)
 #define IQS269_SYS_SETTINGS_EVENT_MODE		BIT(5)
 #define IQS269_SYS_SETTINGS_EVENT_MODE_LP	BIT(4)
@@ -69,6 +73,7 @@
 #define IQS269_FILT_STR_MAX			3
 
 #define IQS269_EVENT_MASK_SYS			BIT(6)
+#define IQS269_EVENT_MASK_GESTURE		BIT(3)
 #define IQS269_EVENT_MASK_DEEP			BIT(2)
 #define IQS269_EVENT_MASK_TOUCH			BIT(1)
 #define IQS269_EVENT_MASK_PROX			BIT(0)
@@ -97,6 +102,10 @@
 #define IQS269_MISC_B_TRACKING_UI_ENABLE	BIT(4)
 #define IQS269_MISC_B_FILT_STR_SLIDER		GENMASK(1, 0)
 
+#define IQS269_TIMEOUT_TAP_MS_MAX		4080
+#define IQS269_TIMEOUT_SWIPE_MS_MAX		4080
+#define IQS269_THRESH_SWIPE_MAX			255
+
 #define IQS269_CHx_ENG_A_MEAS_CAP_SIZE		BIT(15)
 #define IQS269_CHx_ENG_A_RX_GND_INACTIVE	BIT(13)
 #define IQS269_CHx_ENG_A_LOCAL_CAP_SIZE		BIT(12)
@@ -175,6 +184,20 @@ enum iqs269_event_id {
 	IQS269_EVENT_DEEP_UP,
 };
 
+enum iqs269_slider_id {
+	IQS269_SLIDER_NONE,
+	IQS269_SLIDER_KEY,
+	IQS269_SLIDER_RAW,
+};
+
+enum iqs269_gesture_id {
+	IQS269_GESTURE_TAP,
+	IQS269_GESTURE_HOLD,
+	IQS269_GESTURE_FLICK_POS,
+	IQS269_GESTURE_FLICK_NEG,
+	IQS269_NUM_GESTURES,
+};
+
 struct iqs269_switch_desc {
 	unsigned int code;
 	bool enabled;
@@ -234,7 +257,7 @@ struct iqs269_ver_info {
 	u8 prod_num;
 	u8 sw_num;
 	u8 hw_num;
-	u8 padding;
+	u8 fw_num;
 } __packed;
 
 struct iqs269_ch_reg {
@@ -285,16 +308,33 @@ struct iqs269_private {
 	struct regmap *regmap;
 	struct mutex lock;
 	struct iqs269_switch_desc switches[ARRAY_SIZE(iqs269_events)];
+	struct iqs269_ver_info ver_info;
 	struct iqs269_sys_reg sys_reg;
 	struct completion ati_done;
 	struct input_dev *keypad;
 	struct input_dev *slider[IQS269_NUM_SL];
 	unsigned int keycode[ARRAY_SIZE(iqs269_events) * IQS269_NUM_CH];
+	unsigned int sl_code[IQS269_NUM_SL][IQS269_NUM_GESTURES];
 	unsigned int ch_num;
 	bool hall_enable;
 	bool ati_current;
 };
 
+static enum iqs269_slider_id iqs269_slider_type(struct iqs269_private *iqs269,
+						int slider_num)
+{
+	int i;
+
+	if (!iqs269->sys_reg.slider_select[slider_num])
+		return IQS269_SLIDER_NONE;
+
+	for (i = 0; i < IQS269_NUM_GESTURES; i++)
+		if (iqs269->sl_code[slider_num][i] != KEY_RESERVED)
+			return IQS269_SLIDER_KEY;
+
+	return IQS269_SLIDER_RAW;
+}
+
 static int iqs269_ati_mode_set(struct iqs269_private *iqs269,
 			       unsigned int ch_num, unsigned int mode)
 {
@@ -1004,6 +1044,76 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269)
 		general |= (val << IQS269_SYS_SETTINGS_ULP_UPDATE_SHIFT);
 	}
 
+	if (device_property_present(&client->dev, "linux,keycodes")) {
+		int scale = 1;
+		int count = device_property_count_u32(&client->dev,
+						      "linux,keycodes");
+		if (count > IQS269_NUM_GESTURES * IQS269_NUM_SL) {
+			dev_err(&client->dev, "Too many keycodes present\n");
+			return -EINVAL;
+		} else if (count < 0) {
+			dev_err(&client->dev, "Failed to count keycodes: %d\n",
+				count);
+			return count;
+		}
+
+		error = device_property_read_u32_array(&client->dev,
+						       "linux,keycodes",
+						       *iqs269->sl_code, count);
+		if (error) {
+			dev_err(&client->dev, "Failed to read keycodes: %d\n",
+				error);
+			return error;
+		}
+
+		if (device_property_present(&client->dev,
+					    "azoteq,gesture-swipe"))
+			general |= IQS269_SYS_SETTINGS_SLIDER_SWIPE;
+
+		/*
+		 * Early revisions of silicon use a more granular step size for
+		 * tap and swipe gesture timeouts; scale them appropriately.
+		 */
+		if (iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3)
+			scale = 4;
+
+		if (!device_property_read_u32(&client->dev,
+					      "azoteq,timeout-tap-ms", &val)) {
+			if (val > IQS269_TIMEOUT_TAP_MS_MAX / scale) {
+				dev_err(&client->dev, "Invalid timeout: %u\n",
+					val);
+				return -EINVAL;
+			}
+
+			sys_reg->timeout_tap = val / (16 / scale);
+		}
+
+		if (!device_property_read_u32(&client->dev,
+					      "azoteq,timeout-swipe-ms",
+					      &val)) {
+			if (val > IQS269_TIMEOUT_SWIPE_MS_MAX / scale) {
+				dev_err(&client->dev, "Invalid timeout: %u\n",
+					val);
+				return -EINVAL;
+			}
+
+			sys_reg->timeout_swipe = val / (16 / scale);
+		}
+
+		if (!device_property_read_u32(&client->dev,
+					      "azoteq,thresh-swipe", &val)) {
+			if (val > IQS269_THRESH_SWIPE_MAX) {
+				dev_err(&client->dev, "Invalid threshold: %u\n",
+					val);
+				return -EINVAL;
+			}
+
+			sys_reg->thresh_swipe = val;
+		}
+
+		sys_reg->event_mask &= ~IQS269_EVENT_MASK_GESTURE;
+	}
+
 	general &= ~IQS269_SYS_SETTINGS_RESEED_OFFSET;
 	if (device_property_present(&client->dev, "azoteq,reseed-offset"))
 		general |= IQS269_SYS_SETTINGS_RESEED_OFFSET;
@@ -1012,10 +1122,11 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269)
 
 	/*
 	 * As per the datasheet, enable streaming during normal-power mode if
-	 * either slider is in use. In that case, the device returns to event
-	 * mode during low-power mode.
+	 * raw coordinates will be read from either slider. In that case, the
+	 * device returns to event mode during low-power mode.
 	 */
-	if (sys_reg->slider_select[0] || sys_reg->slider_select[1])
+	if (iqs269_slider_type(iqs269, 0) == IQS269_SLIDER_RAW ||
+	    iqs269_slider_type(iqs269, 1) == IQS269_SLIDER_RAW)
 		general |= IQS269_SYS_SETTINGS_EVENT_MODE_LP;
 
 	general |= IQS269_SYS_SETTINGS_REDO_ATI;
@@ -1106,19 +1217,37 @@ static int iqs269_input_init(struct iqs269_private *iqs269)
 	}
 
 	for (i = 0; i < IQS269_NUM_SL; i++) {
-		if (!iqs269->sys_reg.slider_select[i])
+		if (iqs269_slider_type(iqs269, i) == IQS269_SLIDER_NONE)
 			continue;
 
 		iqs269->slider[i] = devm_input_allocate_device(&client->dev);
 		if (!iqs269->slider[i])
 			return -ENOMEM;
 
+		iqs269->slider[i]->keycodemax = ARRAY_SIZE(iqs269->sl_code[i]);
+		iqs269->slider[i]->keycode = iqs269->sl_code[i];
+		iqs269->slider[i]->keycodesize = sizeof(**iqs269->sl_code);
+
 		iqs269->slider[i]->name = i ? "iqs269a_slider_1"
 					    : "iqs269a_slider_0";
 		iqs269->slider[i]->id.bustype = BUS_I2C;
 
-		input_set_capability(iqs269->slider[i], EV_KEY, BTN_TOUCH);
-		input_set_abs_params(iqs269->slider[i], ABS_X, 0, 255, 0, 0);
+		for (j = 0; j < IQS269_NUM_GESTURES; j++)
+			if (iqs269->sl_code[i][j] != KEY_RESERVED)
+				input_set_capability(iqs269->slider[i], EV_KEY,
+						     iqs269->sl_code[i][j]);
+
+		/*
+		 * Present the slider as a narrow trackpad if one or more chan-
+		 * nels have been selected to participate, but no gestures have
+		 * been mapped to a keycode.
+		 */
+		if (iqs269_slider_type(iqs269, i) == IQS269_SLIDER_RAW) {
+			input_set_capability(iqs269->slider[i],
+					     EV_KEY, BTN_TOUCH);
+			input_set_abs_params(iqs269->slider[i],
+					     ABS_X, 0, 255, 0, 0);
+		}
 
 		error = input_register_device(iqs269->slider[i]);
 		if (error) {
@@ -1167,28 +1296,62 @@ static int iqs269_report(struct iqs269_private *iqs269)
 	if (be16_to_cpu(flags.system) & IQS269_SYS_FLAGS_IN_ATI)
 		return 0;
 
-	error = regmap_raw_read(iqs269->regmap, IQS269_SLIDER_X, slider_x,
-				sizeof(slider_x));
-	if (error) {
-		dev_err(&client->dev, "Failed to read slider position: %d\n",
-			error);
-		return error;
+	if (iqs269_slider_type(iqs269, 0) == IQS269_SLIDER_RAW ||
+	    iqs269_slider_type(iqs269, 1) == IQS269_SLIDER_RAW) {
+		error = regmap_raw_read(iqs269->regmap, IQS269_SLIDER_X,
+					slider_x, sizeof(slider_x));
+		if (error) {
+			dev_err(&client->dev,
+				"Failed to read slider position: %d\n", error);
+			return error;
+		}
 	}
 
 	for (i = 0; i < IQS269_NUM_SL; i++) {
-		if (!iqs269->sys_reg.slider_select[i])
+		flags.gesture >>= (i * IQS269_NUM_GESTURES);
+
+		switch (iqs269_slider_type(iqs269, i)) {
+		case IQS269_SLIDER_NONE:
 			continue;
 
-		/*
-		 * Report BTN_TOUCH if any channel that participates in the
-		 * slider is in a state of touch.
-		 */
-		if (flags.states[IQS269_ST_OFFS_TOUCH] &
-		    iqs269->sys_reg.slider_select[i]) {
-			input_report_key(iqs269->slider[i], BTN_TOUCH, 1);
-			input_report_abs(iqs269->slider[i], ABS_X, slider_x[i]);
-		} else {
-			input_report_key(iqs269->slider[i], BTN_TOUCH, 0);
+		case IQS269_SLIDER_KEY:
+			for (j = 0; j < IQS269_NUM_GESTURES; j++)
+				input_report_key(iqs269->slider[i],
+						 iqs269->sl_code[i][j],
+						 flags.gesture & BIT(j));
+
+			if (!(flags.gesture & (BIT(IQS269_GESTURE_FLICK_NEG) |
+					       BIT(IQS269_GESTURE_FLICK_POS) |
+					       BIT(IQS269_GESTURE_TAP))))
+				break;
+
+			input_sync(iqs269->slider[i]);
+
+			/*
+			 * Momentary gestures are followed by a complementary
+			 * release cycle so as to emulate a full keystroke.
+			 */
+			for (j = 0; j < IQS269_NUM_GESTURES; j++)
+				if (j != IQS269_GESTURE_HOLD)
+					input_report_key(iqs269->slider[i],
+							 iqs269->sl_code[i][j],
+							 0);
+			break;
+
+		case IQS269_SLIDER_RAW:
+			/*
+			 * The slider is considered to be in a state of touch
+			 * if any selected channels are in a state of touch.
+			 */
+			state = flags.states[IQS269_ST_OFFS_TOUCH];
+			state &= iqs269->sys_reg.slider_select[i];
+
+			input_report_key(iqs269->slider[i], BTN_TOUCH, state);
+
+			if (state)
+				input_report_abs(iqs269->slider[i],
+						 ABS_X, slider_x[i]);
+			break;
 		}
 
 		input_sync(iqs269->slider[i]);
@@ -1595,7 +1758,6 @@ static const struct regmap_config iqs269_regmap_config = {
 
 static int iqs269_probe(struct i2c_client *client)
 {
-	struct iqs269_ver_info ver_info;
 	struct iqs269_private *iqs269;
 	int error;
 
@@ -1617,14 +1779,14 @@ static int iqs269_probe(struct i2c_client *client)
 	mutex_init(&iqs269->lock);
 	init_completion(&iqs269->ati_done);
 
-	error = regmap_raw_read(iqs269->regmap, IQS269_VER_INFO, &ver_info,
-				sizeof(ver_info));
+	error = regmap_raw_read(iqs269->regmap, IQS269_VER_INFO,
+				&iqs269->ver_info, sizeof(iqs269->ver_info));
 	if (error)
 		return error;
 
-	if (ver_info.prod_num != IQS269_VER_INFO_PROD_NUM) {
+	if (iqs269->ver_info.prod_num != IQS269_VER_INFO_PROD_NUM) {
 		dev_err(&client->dev, "Unrecognized product number: 0x%02X\n",
-			ver_info.prod_num);
+			iqs269->ver_info.prod_num);
 		return -EINVAL;
 	}
 
-- 
GitLab


From 56c083e3f5723c68055ab5f97d21e55aab7bd8ef Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Mon, 1 Jan 2024 14:02:35 -0600
Subject: [PATCH 2028/4076] dt-bindings: input: iqs269a: Add bindings for OTP
 variants

This patch adds bindings for the D0 order code of the device. This
order code represents an OTP variant that enables a touch-and-hold
function in place of slider 1.

Also included is the ability to specify the 00 order code (default
option with no OTP customization) explicitly.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/ZZMaW9RkQ9bKXOUn@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/iqs269a.yaml    | 30 ++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/input/iqs269a.yaml b/Documentation/devicetree/bindings/input/iqs269a.yaml
index b42f07542d27d..2c3f693b8982c 100644
--- a/Documentation/devicetree/bindings/input/iqs269a.yaml
+++ b/Documentation/devicetree/bindings/input/iqs269a.yaml
@@ -20,7 +20,10 @@ description: |
 
 properties:
   compatible:
-    const: azoteq,iqs269a
+    enum:
+      - azoteq,iqs269a
+      - azoteq,iqs269a-00
+      - azoteq,iqs269a-d0
 
   reg:
     maxItems: 1
@@ -207,6 +210,16 @@ properties:
     default: 1
     description: Specifies the slider coordinate filter strength.
 
+  azoteq,touch-hold-ms:
+    multipleOf: 256
+    minimum: 256
+    maximum: 65280
+    default: 5120
+    description:
+      Specifies the length of time (in ms) for which the channel selected by
+      'azoteq,gpio3-select' must be held in a state of touch in order for an
+      approximately 60-ms pulse to be asserted on the GPIO4 pin.
+
   linux,keycodes:
     minItems: 1
     maxItems: 8
@@ -514,6 +527,21 @@ patternProperties:
 
     additionalProperties: false
 
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - azoteq,iqs269a-d0
+then:
+  patternProperties:
+    "^channel@[0-7]$":
+      properties:
+        azoteq,slider1-select: false
+else:
+  properties:
+    azoteq,touch-hold-ms: false
+
 required:
   - compatible
   - reg
-- 
GitLab


From 992bbc9e9ab9abe5bc1ea9a1a8d61331b28f848e Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Mon, 1 Jan 2024 14:02:45 -0600
Subject: [PATCH 2029/4076] Input: iqs269a - add support for OTP variants

This patch adds support for each available OTP variant of the device.
The OTP configuration cannot be read over I2C, so it is derived from
a compatible string instead.

Early revisions of the D0 order code require their OTP-enabled func-
tionality to be manually restored following a soft reset; this patch
accommodates this erratum as well.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/ZZMaZbdk6iAKUjlm@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs269a.c | 92 ++++++++++++++++++++++++++++++++++--
 1 file changed, 89 insertions(+), 3 deletions(-)

diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c
index 0d0b5cdc78303..cd14ff9f57cf2 100644
--- a/drivers/input/misc/iqs269a.c
+++ b/drivers/input/misc/iqs269a.c
@@ -102,6 +102,11 @@
 #define IQS269_MISC_B_TRACKING_UI_ENABLE	BIT(4)
 #define IQS269_MISC_B_FILT_STR_SLIDER		GENMASK(1, 0)
 
+#define IQS269_TOUCH_HOLD_SLIDER_SEL		0x89
+#define IQS269_TOUCH_HOLD_DEFAULT		0x14
+#define IQS269_TOUCH_HOLD_MS_MIN		256
+#define IQS269_TOUCH_HOLD_MS_MAX		65280
+
 #define IQS269_TIMEOUT_TAP_MS_MAX		4080
 #define IQS269_TIMEOUT_SWIPE_MS_MAX		4080
 #define IQS269_THRESH_SWIPE_MAX			255
@@ -151,6 +156,10 @@
 
 #define IQS269_MAX_REG				0xFF
 
+#define IQS269_OTP_OPTION_DEFAULT		0x00
+#define IQS269_OTP_OPTION_TWS			0xD0
+#define IQS269_OTP_OPTION_HOLD			BIT(7)
+
 #define IQS269_NUM_CH				8
 #define IQS269_NUM_SL				2
 
@@ -315,6 +324,7 @@ struct iqs269_private {
 	struct input_dev *slider[IQS269_NUM_SL];
 	unsigned int keycode[ARRAY_SIZE(iqs269_events) * IQS269_NUM_CH];
 	unsigned int sl_code[IQS269_NUM_SL][IQS269_NUM_GESTURES];
+	unsigned int otp_option;
 	unsigned int ch_num;
 	bool hall_enable;
 	bool ati_current;
@@ -325,6 +335,14 @@ static enum iqs269_slider_id iqs269_slider_type(struct iqs269_private *iqs269,
 {
 	int i;
 
+	/*
+	 * Slider 1 is unavailable if the touch-and-hold option is enabled via
+	 * OTP. In that case, the channel selection register is repurposed for
+	 * the touch-and-hold timer ceiling.
+	 */
+	if (slider_num && (iqs269->otp_option & IQS269_OTP_OPTION_HOLD))
+		return IQS269_SLIDER_NONE;
+
 	if (!iqs269->sys_reg.slider_select[slider_num])
 		return IQS269_SLIDER_NONE;
 
@@ -565,7 +583,8 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269,
 	if (fwnode_property_present(ch_node, "azoteq,slider0-select"))
 		iqs269->sys_reg.slider_select[0] |= BIT(reg);
 
-	if (fwnode_property_present(ch_node, "azoteq,slider1-select"))
+	if (fwnode_property_present(ch_node, "azoteq,slider1-select") &&
+	    !(iqs269->otp_option & IQS269_OTP_OPTION_HOLD))
 		iqs269->sys_reg.slider_select[1] |= BIT(reg);
 
 	ch_reg = &iqs269->sys_reg.ch_reg[reg];
@@ -990,7 +1009,43 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269)
 	sys_reg->blocking = 0;
 
 	sys_reg->slider_select[0] = 0;
-	sys_reg->slider_select[1] = 0;
+
+	/*
+	 * If configured via OTP to do so, the device asserts a pulse on the
+	 * GPIO4 pin for approximately 60 ms once a selected channel is held
+	 * in a state of touch for a configurable length of time.
+	 *
+	 * In that case, the register used for slider 1 channel selection is
+	 * repurposed for the touch-and-hold timer ceiling.
+	 */
+	if (iqs269->otp_option & IQS269_OTP_OPTION_HOLD) {
+		if (!device_property_read_u32(&client->dev,
+					      "azoteq,touch-hold-ms", &val)) {
+			if (val < IQS269_TOUCH_HOLD_MS_MIN ||
+			    val > IQS269_TOUCH_HOLD_MS_MAX) {
+				dev_err(&client->dev,
+					"Invalid touch-and-hold ceiling: %u\n",
+					val);
+				return -EINVAL;
+			}
+
+			sys_reg->slider_select[1] = val / 256;
+		} else if (iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3) {
+			/*
+			 * The default touch-and-hold timer ceiling initially
+			 * read from early revisions of silicon is invalid if
+			 * the device experienced a soft reset between power-
+			 * on and the read operation.
+			 *
+			 * To protect against this case, explicitly cache the
+			 * default value so that it is restored each time the
+			 * device is re-initialized.
+			 */
+			sys_reg->slider_select[1] = IQS269_TOUCH_HOLD_DEFAULT;
+		}
+	} else {
+		sys_reg->slider_select[1] = 0;
+	}
 
 	sys_reg->event_mask = ~((u8)IQS269_EVENT_MASK_SYS);
 
@@ -1137,12 +1192,30 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269)
 	return 0;
 }
 
+static const struct reg_sequence iqs269_tws_init[] = {
+	{ IQS269_TOUCH_HOLD_SLIDER_SEL, IQS269_TOUCH_HOLD_DEFAULT },
+	{ 0xF0, 0x580F },
+	{ 0xF0, 0x59EF },
+};
+
 static int iqs269_dev_init(struct iqs269_private *iqs269)
 {
 	int error;
 
 	mutex_lock(&iqs269->lock);
 
+	/*
+	 * Early revisions of silicon require the following workaround in order
+	 * to restore any OTP-enabled functionality after a soft reset.
+	 */
+	if (iqs269->otp_option == IQS269_OTP_OPTION_TWS &&
+	    iqs269->ver_info.fw_num < IQS269_VER_INFO_FW_NUM_3) {
+		error = regmap_multi_reg_write(iqs269->regmap, iqs269_tws_init,
+					       ARRAY_SIZE(iqs269_tws_init));
+		if (error)
+			goto err_mutex;
+	}
+
 	error = regmap_update_bits(iqs269->regmap, IQS269_HALL_UI,
 				   IQS269_HALL_UI_ENABLE,
 				   iqs269->hall_enable ? ~0 : 0);
@@ -1779,6 +1852,8 @@ static int iqs269_probe(struct i2c_client *client)
 	mutex_init(&iqs269->lock);
 	init_completion(&iqs269->ati_done);
 
+	iqs269->otp_option = (uintptr_t)device_get_match_data(&client->dev);
+
 	error = regmap_raw_read(iqs269->regmap, IQS269_VER_INFO,
 				&iqs269->ver_info, sizeof(iqs269->ver_info));
 	if (error)
@@ -1889,7 +1964,18 @@ static int iqs269_resume(struct device *dev)
 static DEFINE_SIMPLE_DEV_PM_OPS(iqs269_pm, iqs269_suspend, iqs269_resume);
 
 static const struct of_device_id iqs269_of_match[] = {
-	{ .compatible = "azoteq,iqs269a" },
+	{
+		.compatible = "azoteq,iqs269a",
+		.data = (void *)IQS269_OTP_OPTION_DEFAULT,
+	},
+	{
+		.compatible = "azoteq,iqs269a-00",
+		.data = (void *)IQS269_OTP_OPTION_DEFAULT,
+	},
+	{
+		.compatible = "azoteq,iqs269a-d0",
+		.data = (void *)IQS269_OTP_OPTION_TWS,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, iqs269_of_match);
-- 
GitLab


From c810729fe6471aa18e2b05bde4b7fb9d872b4ca0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ahelenia=20Ziemia=C5=84ska?=
 <nabijaczleweli@nabijaczleweli.xyz>
Date: Thu, 21 Dec 2023 15:15:42 +0100
Subject: [PATCH 2030/4076] kernfs: fix reference to renamed function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit c637b8acbe079edb477d887041755b489036f146 ("kernfs:
 s/sysfs/kernfs/ in internal functions and whatever is left")
renamed kernfs_file_open to kernfs_fop_open, but didn't update the
comment referencing it.

Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/4f2wybrepigxjpuxj4bdkh3qmksetfioedit2bdrswf6b75ebb@tarta.nabijaczleweli.xyz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index f0cb729e9a978..ffa4565c275a7 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -447,7 +447,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 	 * warnings and we don't want to add spurious locking dependency
 	 * between the two.  Check whether mmap is actually implemented
 	 * without grabbing @of->mutex by testing HAS_MMAP flag.  See the
-	 * comment in kernfs_file_open() for more details.
+	 * comment in kernfs_fop_open() for more details.
 	 */
 	if (!(of->kn->flags & KERNFS_HAS_MMAP))
 		return -ENODEV;
-- 
GitLab


From 9c6b789e954fae73c548f39332bcc56bdf0d4373 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Tue, 2 Jan 2024 11:11:41 +0200
Subject: [PATCH 2031/4076] Revert "usb: typec: class: fix
 typec_altmode_put_partner to put plugs"

This reverts commit b17b7fe6dd5c6ff74b38b0758ca799cdbb79e26e.

That commit messed up the reference counting, so it needs to
be rethought.

Fixes: b17b7fe6dd5c ("usb: typec: class: fix typec_altmode_put_partner to put plugs")
Cc:  <stable@vger.kernel.org>
Cc: RD Babiera <rdbabiera@google.com>
Reported-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Closes: https://lore.kernel.org/lkml/CAP-bSRb3SXpgo_BEdqZB-p1K5625fMegRZ17ZkPE1J8ZYgEHDg@mail.gmail.com/
Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20240102091142.2136472-1-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/class.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index aeae8009b9e3a..4d11f2b536fae 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -267,7 +267,7 @@ static void typec_altmode_put_partner(struct altmode *altmode)
 	if (!partner)
 		return;
 
-	adev = &altmode->adev;
+	adev = &partner->adev;
 
 	if (is_typec_plug(adev->dev.parent)) {
 		struct typec_plug *plug = to_typec_plug(adev->dev.parent);
@@ -497,8 +497,7 @@ static void typec_altmode_release(struct device *dev)
 {
 	struct altmode *alt = to_altmode(to_typec_altmode(dev));
 
-	if (!is_typec_port(dev->parent))
-		typec_altmode_put_partner(alt);
+	typec_altmode_put_partner(alt);
 
 	altmode_id_remove(alt->adev.dev.parent, alt->id);
 	kfree(alt);
-- 
GitLab


From ca2dc35e555e7043de585f4e46123d8fbd2b5a21 Mon Sep 17 00:00:00 2001
From: William Wu <william.wu@rock-chips.com>
Date: Tue, 26 Dec 2023 15:19:59 +0800
Subject: [PATCH 2032/4076] usb: dwc2: Disable clock gating feature on Rockchip
 SoCs

The DWC2 IP on the Rockchip SoCs doesn't support clock gating.
When a clock gating is enabled, system hangs.

Signed-off-by: William Wu <william.wu@rock-chips.com>
Acked-by: Minas Harutyunyan <hminas@synopsys.com>
Link: https://lore.kernel.org/r/1703575199-23638-1-git-send-email-william.wu@rock-chips.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc2/params.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c
index fb03162ae9b76..eb677c3cfd0b6 100644
--- a/drivers/usb/dwc2/params.c
+++ b/drivers/usb/dwc2/params.c
@@ -130,6 +130,7 @@ static void dwc2_set_rk_params(struct dwc2_hsotg *hsotg)
 	p->lpm_clock_gating = false;
 	p->besl = false;
 	p->hird_threshold_en = false;
+	p->no_clock_gating = true;
 }
 
 static void dwc2_set_ltq_params(struct dwc2_hsotg *hsotg)
-- 
GitLab


From 7059fbebcb00554c3f31e5b5d93ef6d2d96dc7b4 Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Fri, 22 Dec 2023 22:11:27 +0000
Subject: [PATCH 2033/4076] Revert "usb: dwc3: Soft reset phy on probe for
 host"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 8bea147dfdf823eaa8d3baeccc7aeb041b41944b.

The phy soft reset GUSB2PHYCFG.PHYSOFTRST only applies to UTMI phy, not
ULPI. This fix is incomplete.

Cc:  <stable@vger.kernel.org>
Fixes: 8bea147dfdf8 ("usb: dwc3: Soft reset phy on probe for host")
Reported-by: Köry Maincent <kory.maincent@bootlin.com>
Closes: https://lore.kernel.org/linux-usb/20231205151959.5236c231@kmaincent-XPS-13-7390
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/29a26593a60eba727de872a3e580a674807b3339.1703282469.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c | 39 +--------------------------------------
 1 file changed, 1 insertion(+), 38 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index b101dbf8c5dcc..832c41fec4f70 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -279,46 +279,9 @@ int dwc3_core_soft_reset(struct dwc3 *dwc)
 	 * XHCI driver will reset the host block. If dwc3 was configured for
 	 * host-only mode or current role is host, then we can return early.
 	 */
-	if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST)
+	if (dwc->dr_mode == USB_DR_MODE_HOST || dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST)
 		return 0;
 
-	/*
-	 * If the dr_mode is host and the dwc->current_dr_role is not the
-	 * corresponding DWC3_GCTL_PRTCAP_HOST, then the dwc3_core_init_mode
-	 * isn't executed yet. Ensure the phy is ready before the controller
-	 * updates the GCTL.PRTCAPDIR or other settings by soft-resetting
-	 * the phy.
-	 *
-	 * Note: GUSB3PIPECTL[n] and GUSB2PHYCFG[n] are port settings where n
-	 * is port index. If this is a multiport host, then we need to reset
-	 * all active ports.
-	 */
-	if (dwc->dr_mode == USB_DR_MODE_HOST) {
-		u32 usb3_port;
-		u32 usb2_port;
-
-		usb3_port = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0));
-		usb3_port |= DWC3_GUSB3PIPECTL_PHYSOFTRST;
-		dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), usb3_port);
-
-		usb2_port = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
-		usb2_port |= DWC3_GUSB2PHYCFG_PHYSOFTRST;
-		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), usb2_port);
-
-		/* Small delay for phy reset assertion */
-		usleep_range(1000, 2000);
-
-		usb3_port &= ~DWC3_GUSB3PIPECTL_PHYSOFTRST;
-		dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), usb3_port);
-
-		usb2_port &= ~DWC3_GUSB2PHYCFG_PHYSOFTRST;
-		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), usb2_port);
-
-		/* Wait for clock synchronization */
-		msleep(50);
-		return 0;
-	}
-
 	reg = dwc3_readl(dwc->regs, DWC3_DCTL);
 	reg |= DWC3_DCTL_CSFTRST;
 	reg &= ~DWC3_DCTL_RUN_STOP;
-- 
GitLab


From afe28cd686aeb77e8d9140d50fb1cf06a7ecb731 Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Fri, 22 Dec 2023 22:11:33 +0000
Subject: [PATCH 2034/4076] Revert "usb: dwc3: don't reset device side if dwc3
 was configured as host-only"

This reverts commit e835c0a4e23c38531dcee5ef77e8d1cf462658c7.

Don't omit soft-reset. During initialization, the driver may need to
perform a soft reset to ensure the phy is ready when the controller
updates the GCTL.PRTCAPDIR or other settings by issuing phy soft-reset.
Many platforms often have access to DCTL register for soft-reset despite
being host-only. If there are actual reported issues from the platforms
that don't expose DCTL registers, then we will need to revisit (perhaps
to teach dwc3 to perform xhci's soft-reset USBCMD.HCRST).

Cc:  <stable@vger.kernel.org>
Fixes: e835c0a4e23c ("usb: dwc3: don't reset device side if dwc3 was configured as host-only")
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/7668ab11a48f260820825274976eb41fec7f54d1.1703282469.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 832c41fec4f70..f50b5575d588a 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -277,9 +277,9 @@ int dwc3_core_soft_reset(struct dwc3 *dwc)
 	/*
 	 * We're resetting only the device side because, if we're in host mode,
 	 * XHCI driver will reset the host block. If dwc3 was configured for
-	 * host-only mode or current role is host, then we can return early.
+	 * host-only mode, then we can return early.
 	 */
-	if (dwc->dr_mode == USB_DR_MODE_HOST || dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST)
+	if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST)
 		return 0;
 
 	reg = dwc3_readl(dwc->regs, DWC3_DCTL);
-- 
GitLab


From 961410c9e8534d3c6f347c04cacf50bc5c002a3f Mon Sep 17 00:00:00 2001
From: liyouhong <liyouhong@kylinos.cn>
Date: Thu, 21 Dec 2023 10:34:25 +0800
Subject: [PATCH 2035/4076] drivers/usb/gadget/udc: Fix spelling typo in
 comments(reqest->request)

Fix spelling typo in comments.

Reported-by: k2ci <kernel-bot@kylinos.cn>
Signed-off-by: liyouhong <liyouhong@kylinos.cn>

Link: https://lore.kernel.org/r/20231221023425.1316397-1-liyouhong@kylinos.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/fsl_udc_core.c | 2 +-
 drivers/usb/gadget/udc/mv_udc_core.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index 535b6e79a198e..e8042c158f6dc 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -1360,7 +1360,7 @@ static void ch9getstatus(struct fsl_udc *udc, u8 request_type, u16 value,
 	udc->ep0_dir = USB_DIR_IN;
 	/* Borrow the per device status_req */
 	req = udc->status_req;
-	/* Fill in the reqest structure */
+	/* Fill in the request structure */
 	*((u16 *) req->req.buf) = cpu_to_le16(tmp);
 
 	req->ep = ep;
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index d888dcda2bc86..78308b64955dd 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -1451,7 +1451,7 @@ udc_prime_status(struct mv_udc *udc, u8 direction, u16 status, bool empty)
 
 	req = udc->status_req;
 
-	/* fill in the reqest structure */
+	/* fill in the request structure */
 	if (empty == false) {
 		*((u16 *) req->req.buf) = cpu_to_le16(status);
 		req->req.length = 2;
-- 
GitLab


From d49f90822015ad9c8837717e6b5967c8748626df Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco@wolfvision.net>
Date: Thu, 14 Dec 2023 17:29:09 +0100
Subject: [PATCH 2036/4076] usb: typec: tipd: add init and reset functions to
 tipd_data

The current implementation includes a number of special cases for the
tps25750. Nevertheless, init and reset functions can be generalized by
adding function pointers to the tipd_data structure in order to offer
that functionality to other parts without additional conditional
clauses.

Some functionality like the cold reset request (GAID) is shared by the
tps25750 and the tps6598x, so they can use the same reset function.

Signed-off-by: Javier Carrasco <javier.carrasco@wolfvision.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231207-tps6598x_update-v2-1-f3cfcde6d890@wolfvision.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tipd/core.c | 45 +++++++++++++++++++++++++++--------
 1 file changed, 35 insertions(+), 10 deletions(-)

diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 806ef68273ca0..f0c4cd571a377 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -115,6 +115,8 @@ struct tipd_data {
 	void (*trace_power_status)(u16 status);
 	void (*trace_status)(u32 status);
 	int (*apply_patch)(struct tps6598x *tps);
+	int (*init)(struct tps6598x *tps);
+	int (*reset)(struct tps6598x *tps);
 };
 
 struct tps6598x {
@@ -1106,6 +1108,11 @@ wait_for_app:
 	return 0;
 };
 
+static int cd321x_init(struct tps6598x *tps)
+{
+	return 0;
+}
+
 static int tps25750_init(struct tps6598x *tps)
 {
 	int ret;
@@ -1124,6 +1131,21 @@ static int tps25750_init(struct tps6598x *tps)
 	return 0;
 }
 
+static int tps6598x_init(struct tps6598x *tps)
+{
+	return 0;
+}
+
+static int cd321x_reset(struct tps6598x *tps)
+{
+	return 0;
+}
+
+static int tps6598x_reset(struct tps6598x *tps)
+{
+	return tps6598x_exec_cmd_tmo(tps, "GAID", 0, NULL, 0, NULL, 2000, 0);
+}
+
 static int
 tps25750_register_port(struct tps6598x *tps, struct fwnode_handle *fwnode)
 {
@@ -1187,7 +1209,6 @@ static int tps6598x_probe(struct i2c_client *client)
 	u32 vid;
 	int ret;
 	u64 mask1;
-	bool is_tps25750;
 
 	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
 	if (!tps)
@@ -1207,8 +1228,7 @@ static int tps6598x_probe(struct i2c_client *client)
 	if (IS_ERR(tps->regmap))
 		return PTR_ERR(tps->regmap);
 
-	is_tps25750 = device_is_compatible(tps->dev, "ti,tps25750");
-	if (!is_tps25750) {
+	if (!device_is_compatible(tps->dev, "ti,tps25750")) {
 		ret = tps6598x_read32(tps, TPS_REG_VID, &vid);
 		if (ret < 0 || !vid)
 			return -ENODEV;
@@ -1251,8 +1271,8 @@ static int tps6598x_probe(struct i2c_client *client)
 	if (ret < 0)
 		return ret;
 
-	if (is_tps25750 && ret == TPS_MODE_PTCH) {
-		ret = tps25750_init(tps);
+	if (ret == TPS_MODE_PTCH) {
+		ret = tps->data->init(tps);
 		if (ret)
 			return ret;
 	}
@@ -1340,8 +1360,8 @@ err_clear_mask:
 	tps6598x_write64(tps, TPS_REG_INT_MASK1, 0);
 err_reset_controller:
 	/* Reset PD controller to remove any applied patch */
-	if (is_tps25750)
-		tps6598x_exec_cmd_tmo(tps, "GAID", 0, NULL, 0, NULL, 2000, 0);
+	tps->data->reset(tps);
+
 	return ret;
 }
 
@@ -1358,8 +1378,7 @@ static void tps6598x_remove(struct i2c_client *client)
 	usb_role_switch_put(tps->role_sw);
 
 	/* Reset PD controller to remove any applied patch */
-	if (device_is_compatible(tps->dev, "ti,tps25750"))
-		tps6598x_exec_cmd_tmo(tps, "GAID", 0, NULL, 0, NULL, 2000, 0);
+	tps->data->reset(tps);
 
 	if (tps->reset)
 		gpiod_set_value_cansleep(tps->reset, 1);
@@ -1393,7 +1412,7 @@ static int __maybe_unused tps6598x_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	if (device_is_compatible(tps->dev, "ti,tps25750") && ret == TPS_MODE_PTCH) {
+	if (ret == TPS_MODE_PTCH) {
 		ret = tps25750_init(tps);
 		if (ret)
 			return ret;
@@ -1423,6 +1442,8 @@ static const struct tipd_data cd321x_data = {
 	.register_port = tps6598x_register_port,
 	.trace_power_status = trace_tps6598x_power_status,
 	.trace_status = trace_tps6598x_status,
+	.init = cd321x_init,
+	.reset = cd321x_reset,
 };
 
 static const struct tipd_data tps6598x_data = {
@@ -1430,6 +1451,8 @@ static const struct tipd_data tps6598x_data = {
 	.register_port = tps6598x_register_port,
 	.trace_power_status = trace_tps6598x_power_status,
 	.trace_status = trace_tps6598x_status,
+	.init = tps6598x_init,
+	.reset = tps6598x_reset,
 };
 
 static const struct tipd_data tps25750_data = {
@@ -1438,6 +1461,8 @@ static const struct tipd_data tps25750_data = {
 	.trace_power_status = trace_tps25750_power_status,
 	.trace_status = trace_tps25750_status,
 	.apply_patch = tps25750_apply_patch,
+	.init = tps25750_init,
+	.reset = tps6598x_reset,
 };
 
 static const struct of_device_id tps6598x_of_match[] = {
-- 
GitLab


From 798531b85f08c1dd128b88acd1f98c6a6b30dffd Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco@wolfvision.net>
Date: Thu, 14 Dec 2023 17:29:10 +0100
Subject: [PATCH 2037/4076] usb: typec: tipd: add function to request firmware

The firmware request process is device agnostic and can be used for
other parts.

Signed-off-by: Javier Carrasco <javier.carrasco@wolfvision.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231207-tps6598x_update-v2-2-f3cfcde6d890@wolfvision.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tipd/core.c | 35 ++++++++++++++++++++++++++---------
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index f0c4cd571a377..83e5eeecdf5c9 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -873,6 +873,30 @@ tps6598x_register_port(struct tps6598x *tps, struct fwnode_handle *fwnode)
 	return 0;
 }
 
+static int tps_request_firmware(struct tps6598x *tps, const struct firmware **fw)
+{
+	const char *firmware_name;
+	int ret;
+
+	ret = device_property_read_string(tps->dev, "firmware-name",
+					  &firmware_name);
+	if (ret)
+		return ret;
+
+	ret = request_firmware(fw, firmware_name, tps->dev);
+	if (ret) {
+		dev_err(tps->dev, "failed to retrieve \"%s\"\n", firmware_name);
+		return ret;
+	}
+
+	if ((*fw)->size == 0) {
+		release_firmware(*fw);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
 static int
 tps25750_write_firmware(struct tps6598x *tps,
 			u8 bpms_addr, const u8 *data, size_t len)
@@ -961,16 +985,9 @@ static int tps25750_start_patch_burst_mode(struct tps6598x *tps)
 	if (ret)
 		return ret;
 
-	ret = request_firmware(&fw, firmware_name, tps->dev);
-	if (ret) {
-		dev_err(tps->dev, "failed to retrieve \"%s\"\n", firmware_name);
+	ret = tps_request_firmware(tps, &fw);
+	if (ret)
 		return ret;
-	}
-
-	if (fw->size == 0) {
-		ret = -EINVAL;
-		goto release_fw;
-	}
 
 	ret = of_property_match_string(np, "reg-names", "patch-address");
 	if (ret < 0) {
-- 
GitLab


From e79ead88eeb8f3e945355b537bfaca7532dfee10 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco@wolfvision.net>
Date: Thu, 14 Dec 2023 17:29:11 +0100
Subject: [PATCH 2038/4076] usb: typec: tipd: declare in_data in as const in
 exec_cmd functions

The input data passed to execute commands with tps6598x_exec_cmd()
is not supposed to be modified by the function. Moreover, this data is
passed to tps6598x_exec_cmd_tmo() and finally to tps6598x_block_write(),
which expects a const pointer.

The current implementation does not produce any bugs, but it discards
const qualifiers from the pointers passed as arguments. This leads to
compile issues if 'discarded-qualifiers' is active and a const pointer
is passed to the function, which is the case if data from a firmware
structure is passed to execute update commands. Adding the const
modifier to in_data prevents such issues and provides code consistency.

Signed-off-by: Javier Carrasco <javier.carrasco@wolfvision.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231207-tps6598x_update-v2-3-f3cfcde6d890@wolfvision.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tipd/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 83e5eeecdf5c9..7f4bbc0629b06 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -330,7 +330,7 @@ static void tps6598x_disconnect(struct tps6598x *tps, u32 status)
 }
 
 static int tps6598x_exec_cmd_tmo(struct tps6598x *tps, const char *cmd,
-			     size_t in_len, u8 *in_data,
+			     size_t in_len, const u8 *in_data,
 			     size_t out_len, u8 *out_data,
 			     u32 cmd_timeout_ms, u32 res_delay_ms)
 {
@@ -396,7 +396,7 @@ static int tps6598x_exec_cmd_tmo(struct tps6598x *tps, const char *cmd,
 }
 
 static int tps6598x_exec_cmd(struct tps6598x *tps, const char *cmd,
-			     size_t in_len, u8 *in_data,
+			     size_t in_len, const u8 *in_data,
 			     size_t out_len, u8 *out_data)
 {
 	return tps6598x_exec_cmd_tmo(tps, cmd, in_len, in_data,
-- 
GitLab


From 4c3ea81aa8e11400f24e5541bf46c2cadb4202e9 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco@wolfvision.net>
Date: Thu, 14 Dec 2023 17:29:12 +0100
Subject: [PATCH 2039/4076] usb: typec: tipd: add patch update support for
 tps6598x

The TPS6598x PD controller supports firmware updates that can be loaded
either from an external flash memory or a host using the device's I2C
host interface. This patch implements the second approach, which is
especially relevant if no flash memory is available.

In order to make patch bundle updates, a series of tasks (special
commands) must be sent to the device as it is documented in the
TPS65987DDH and TPS65988DH Host Interface Technical Reference Manual[1],
section 4.11 (Patch Bundle Update Tasks).

The update sequence is as follows:
1. PTCs - Start Patch Load Sequence: the proposed approach includes
   device and application configuration data.
2. PTCd - Patch Download: 64-byte data chunks must be sent until the end
   of the firmware file is reached (the last chunk may be shorter).
3. PTCc - Patch Data Transfer Complete: ends the patch loading sequence.

After this sequence and if no errors occurred, the device will change
its mode to 'APP' after SETUP_MS milliseconds, and then it will be ready
for normal operation.

[1] https://www.ti.com/lit/ug/slvubh2b/slvubh2b.pdf?ts=1697623299919&ref_url=https%253A%252F%252Fwww.ti.com%252Fproduct%252FTPS65987D

Signed-off-by: Javier Carrasco <javier.carrasco@wolfvision.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231207-tps6598x_update-v2-4-f3cfcde6d890@wolfvision.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tipd/core.c     | 68 ++++++++++++++++++++++++++++++-
 drivers/usb/typec/tipd/tps6598x.h | 18 ++++++++
 2 files changed, 85 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 7f4bbc0629b06..a956eb976906a 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -1125,6 +1125,71 @@ wait_for_app:
 	return 0;
 };
 
+static int tps6598x_apply_patch(struct tps6598x *tps)
+{
+	u8 in = TPS_PTCS_CONTENT_DEV | TPS_PTCS_CONTENT_APP;
+	u8 out[TPS_MAX_LEN] = {0};
+	size_t in_len = sizeof(in);
+	size_t copied_bytes = 0;
+	size_t bytes_left;
+	const struct firmware *fw;
+	const char *firmware_name;
+	int ret;
+
+	ret = device_property_read_string(tps->dev, "firmware-name",
+					  &firmware_name);
+	if (ret)
+		return ret;
+
+	ret = tps_request_firmware(tps, &fw);
+	if (ret)
+		return ret;
+
+	ret = tps6598x_exec_cmd(tps, "PTCs", in_len, &in,
+				TPS_PTCS_OUT_BYTES, out);
+	if (ret || out[TPS_PTCS_STATUS] == TPS_PTCS_STATUS_FAIL) {
+		if (!ret)
+			ret = -EBUSY;
+		dev_err(tps->dev, "Update start failed (%d)\n", ret);
+		goto release_fw;
+	}
+
+	bytes_left = fw->size;
+	while (bytes_left) {
+		if (bytes_left < TPS_MAX_LEN)
+			in_len = bytes_left;
+		else
+			in_len = TPS_MAX_LEN;
+		ret = tps6598x_exec_cmd(tps, "PTCd", in_len,
+					fw->data + copied_bytes,
+					TPS_PTCD_OUT_BYTES, out);
+		if (ret || out[TPS_PTCD_TRANSFER_STATUS] ||
+		    out[TPS_PTCD_LOADING_STATE] == TPS_PTCD_LOAD_ERR) {
+			if (!ret)
+				ret = -EBUSY;
+			dev_err(tps->dev, "Patch download failed (%d)\n", ret);
+			goto release_fw;
+		}
+		copied_bytes += in_len;
+		bytes_left -= in_len;
+	}
+
+	ret = tps6598x_exec_cmd(tps, "PTCc", 0, NULL, TPS_PTCC_OUT_BYTES, out);
+	if (ret || out[TPS_PTCC_DEV] || out[TPS_PTCC_APP]) {
+		if (!ret)
+			ret = -EBUSY;
+		dev_err(tps->dev, "Update completion failed (%d)\n", ret);
+		goto release_fw;
+	}
+	msleep(TPS_SETUP_MS);
+	dev_info(tps->dev, "Firmware update succeeded\n");
+
+release_fw:
+	release_firmware(fw);
+
+	return ret;
+};
+
 static int cd321x_init(struct tps6598x *tps)
 {
 	return 0;
@@ -1150,7 +1215,7 @@ static int tps25750_init(struct tps6598x *tps)
 
 static int tps6598x_init(struct tps6598x *tps)
 {
-	return 0;
+	return tps->data->apply_patch(tps);
 }
 
 static int cd321x_reset(struct tps6598x *tps)
@@ -1468,6 +1533,7 @@ static const struct tipd_data tps6598x_data = {
 	.register_port = tps6598x_register_port,
 	.trace_power_status = trace_tps6598x_power_status,
 	.trace_status = trace_tps6598x_status,
+	.apply_patch = tps6598x_apply_patch,
 	.init = tps6598x_init,
 	.reset = tps6598x_reset,
 };
diff --git a/drivers/usb/typec/tipd/tps6598x.h b/drivers/usb/typec/tipd/tps6598x.h
index 01609bf509e4b..89b24519463a1 100644
--- a/drivers/usb/typec/tipd/tps6598x.h
+++ b/drivers/usb/typec/tipd/tps6598x.h
@@ -235,4 +235,22 @@
 /* SLEEP CONF REG */
 #define TPS_SLEEP_CONF_SLEEP_MODE_ALLOWED	BIT(0)
 
+/* Start Patch Download Sequence */
+#define TPS_PTCS_CONTENT_APP			BIT(0)
+#define TPS_PTCS_CONTENT_DEV			BIT(1)
+#define TPS_PTCS_OUT_BYTES			4
+#define TPS_PTCS_STATUS				1
+
+#define TPS_PTCS_STATUS_FAIL			0x80
+/* Patch Download */
+#define TPS_PTCD_OUT_BYTES			10
+#define TPS_PTCD_TRANSFER_STATUS		1
+#define TPS_PTCD_LOADING_STATE			2
+
+#define TPS_PTCD_LOAD_ERR			0x09
+/* Patch Download Complete */
+#define TPS_PTCC_OUT_BYTES			4
+#define TPS_PTCC_DEV				2
+#define TPS_PTCC_APP				3
+
 #endif /* __TPS6598X_H__ */
-- 
GitLab


From e7d3b9f28654dbfce7e09f8028210489adaf6a33 Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Mon, 18 Dec 2023 22:36:35 -0800
Subject: [PATCH 2040/4076] usb: yurex: Fix inconsistent locking bug in
 yurex_read()

Unlock before returning on the error path.

Fixes: 86b20af11e84 ("usb: yurex: Replace snprintf() with the safer scnprintf() variant")
Reported-by: Dan Carpenter <error27@gmail.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/r/202312170252.3udgrIcP-lkp@intel.com/
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Link: https://lore.kernel.org/r/20231219063639.450994-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/yurex.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 5a13cddace0e6..9a0649d236935 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -414,8 +414,10 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 		return -ENODEV;
 	}
 
-	if (WARN_ON_ONCE(dev->bbu > S64_MAX || dev->bbu < S64_MIN))
+	if (WARN_ON_ONCE(dev->bbu > S64_MAX || dev->bbu < S64_MIN)) {
+		mutex_unlock(&dev->io_mutex);
 		return -EIO;
+	}
 
 	spin_lock_irqsave(&dev->lock, flags);
 	scnprintf(in_buffer, MAX_S64_STRLEN, "%lld\n", dev->bbu);
-- 
GitLab


From ac4f1897fa5433a1b07a625503a91b6aa9d7e643 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Tue, 2 Jan 2024 19:27:00 +0200
Subject: [PATCH 2041/4076] PCI: Fix 64GT/s effective data rate calculation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unlike the lower rates, the PCIe 64GT/s Data Rate uses 1b/1b encoding, not
128b/130b (PCIe r6.1 sec 1.2, Table 1-1).  Correct the PCIE_SPEED2MBS_ENC()
calculation to reflect that.

Link: https://lore.kernel.org/r/20240102172701.65501-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 5ecbcf0411793..d9132029d6584 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -272,7 +272,7 @@ void pci_bus_put(struct pci_bus *bus);
 
 /* PCIe speed to Mb/s reduced by encoding overhead */
 #define PCIE_SPEED2MBS_ENC(speed) \
-	((speed) == PCIE_SPEED_64_0GT ? 64000*128/130 : \
+	((speed) == PCIE_SPEED_64_0GT ? 64000*1/1 : \
 	 (speed) == PCIE_SPEED_32_0GT ? 32000*128/130 : \
 	 (speed) == PCIE_SPEED_16_0GT ? 16000*128/130 : \
 	 (speed) == PCIE_SPEED_8_0GT  ?  8000*128/130 : \
-- 
GitLab


From 58f1e9d3a30438042fc9ed65b3dc56b2e5f7886a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 2 Jan 2024 09:39:17 -0800
Subject: [PATCH 2042/4076] cxl/region: use %pap format to print
 resource_size_t

Use "%pap" to print a resource_size_t (phys_addr_t derived type)
to prevent build warnings on 32-bit arches (seen on i386 and
riscv-32).

../drivers/cxl/core/region.c: In function 'alloc_hpa':
../drivers/cxl/core/region.c:556:25: warning: format '%llx' expects argument of type 'long long unsigned int', but argument 5 has type 'resource_size_t' {aka 'unsigned int'} [-Wformat=]
  556 |                         "HPA allocation error (%ld) for size:%#llx in %s %pr\n",

Fixes: 7984d22f1315 ("cxl/region: Add dev_dbg() detail on failure to allocate HPA space")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Fan Ni <fan.ni@samsung.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Jonathan Cameron <jonathan.cameron@huawei.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Alison Schofield <alison.schofield@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc:  <linux-cxl@vger.kernel.org>
Link: https://lore.kernel.org/r/20240102173917.19718-1-rdunlap@infradead.org
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/region.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index d904f9752bc38..0e88f1aed0184 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -553,8 +553,8 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 				    dev_name(&cxlr->dev));
 	if (IS_ERR(res)) {
 		dev_dbg(&cxlr->dev,
-			"HPA allocation error (%ld) for size:%#llx in %s %pr\n",
-			PTR_ERR(res), size, cxlrd->res->name, cxlrd->res);
+			"HPA allocation error (%ld) for size:%pap in %s %pr\n",
+			PTR_ERR(res), &size, cxlrd->res->name, cxlrd->res);
 		return PTR_ERR(res);
 	}
 
-- 
GitLab


From efa56305908ba20de2104f1b8508c6a7401833be Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Fri, 22 Dec 2023 16:17:48 +0100
Subject: [PATCH 2043/4076] nvmet-tcp: Fix a kernel panic when host sends an
 invalid H2C PDU length

If the host sends an H2CData command with an invalid DATAL,
the kernel may crash in nvmet_tcp_build_pdu_iovec().

Unable to handle kernel NULL pointer dereference at
virtual address 0000000000000000
lr : nvmet_tcp_io_work+0x6ac/0x718 [nvmet_tcp]
Call trace:
  process_one_work+0x174/0x3c8
  worker_thread+0x2d0/0x3e8
  kthread+0x104/0x110

Fix the bug by raising a fatal error if DATAL isn't coherent
with the packet size.
Also, the PDU length should never exceed the MAXH2CDATA parameter which
has been communicated to the host in nvmet_tcp_handle_icreq().

Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 4cc27856aa8fe..ad16795934b83 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -24,6 +24,7 @@
 #include "nvmet.h"
 
 #define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
+#define NVMET_TCP_MAXH2CDATA		0x400000 /* 16M arbitrary limit */
 
 static int param_store_val(const char *str, int *val, int min, int max)
 {
@@ -923,7 +924,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
 	icresp->hdr.pdo = 0;
 	icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
 	icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
-	icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
+	icresp->maxdata = cpu_to_le32(NVMET_TCP_MAXH2CDATA);
 	icresp->cpda = 0;
 	if (queue->hdr_digest)
 		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
@@ -978,6 +979,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 {
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
+	unsigned int plen;
 
 	if (likely(queue->nr_cmds)) {
 		if (unlikely(data->ttag >= queue->nr_cmds)) {
@@ -1001,7 +1003,16 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 		return -EPROTO;
 	}
 
+	plen = le32_to_cpu(data->hdr.plen);
 	cmd->pdu_len = le32_to_cpu(data->data_length);
+	if (unlikely(cmd->pdu_len != (plen - sizeof(*data)) ||
+		     cmd->pdu_len == 0 ||
+		     cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) {
+		pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len);
+		/* FIXME: use proper transport errors */
+		nvmet_tcp_fatal_error(queue);
+		return -EPROTO;
+	}
 	cmd->pdu_recv = 0;
 	nvmet_tcp_build_pdu_iovec(cmd);
 	queue->cmd = cmd;
-- 
GitLab


From 0849a5441358cef02586fb2d60f707c0db195628 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Fri, 22 Dec 2023 16:17:49 +0100
Subject: [PATCH 2044/4076] nvmet-tcp: fix a crash in nvmet_req_complete()

in nvmet_tcp_handle_h2c_data_pdu(), if the host sends a data_offset
different from rbytes_done, the driver ends up calling nvmet_req_complete()
passing a status error.
The problem is that at this point cmd->req is not yet initialized,
the kernel will crash after dereferencing a NULL pointer.

Fix the bug by replacing the call to nvmet_req_complete() with
nvmet_tcp_fatal_error().

Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver")
Reviewed-by: Keith Busch <kbsuch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index ad16795934b83..b4b6a8ac80895 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -998,8 +998,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 			data->ttag, le32_to_cpu(data->data_offset),
 			cmd->rbytes_done);
 		/* FIXME: use path and transport errors */
-		nvmet_req_complete(&cmd->req,
-			NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+		nvmet_tcp_fatal_error(queue);
 		return -EPROTO;
 	}
 
-- 
GitLab


From 75011bd0f9c55db523242f9f9a0b0b826165f14b Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Fri, 22 Dec 2023 16:17:50 +0100
Subject: [PATCH 2045/4076] nvmet-tcp: remove boilerplate code

Simplify the nvmet_tcp_handle_h2c_data_pdu() function by removing
boilerplate code.

Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index b4b6a8ac80895..3569c1255c5eb 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -985,8 +985,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 		if (unlikely(data->ttag >= queue->nr_cmds)) {
 			pr_err("queue %d: received out of bound ttag %u, nr_cmds %u\n",
 				queue->idx, data->ttag, queue->nr_cmds);
-			nvmet_tcp_fatal_error(queue);
-			return -EPROTO;
+			goto err_proto;
 		}
 		cmd = &queue->cmds[data->ttag];
 	} else {
@@ -997,9 +996,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 		pr_err("ttag %u unexpected data offset %u (expected %u)\n",
 			data->ttag, le32_to_cpu(data->data_offset),
 			cmd->rbytes_done);
-		/* FIXME: use path and transport errors */
-		nvmet_tcp_fatal_error(queue);
-		return -EPROTO;
+		goto err_proto;
 	}
 
 	plen = le32_to_cpu(data->hdr.plen);
@@ -1008,9 +1005,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 		     cmd->pdu_len == 0 ||
 		     cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) {
 		pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len);
-		/* FIXME: use proper transport errors */
-		nvmet_tcp_fatal_error(queue);
-		return -EPROTO;
+		goto err_proto;
 	}
 	cmd->pdu_recv = 0;
 	nvmet_tcp_build_pdu_iovec(cmd);
@@ -1018,6 +1013,11 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 	queue->rcv_state = NVMET_TCP_RECV_DATA;
 
 	return 0;
+
+err_proto:
+	/* FIXME: use proper transport errors */
+	nvmet_tcp_fatal_error(queue);
+	return -EPROTO;
 }
 
 static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue)
-- 
GitLab


From 02a06f5f1a6aa2e12b2046b51ed3462c2c340037 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 6 Dec 2023 16:42:29 -0600
Subject: [PATCH 2046/4076] PCI/AER: Use 'Correctable' and 'Uncorrectable' spec
 terms for errors

The PCIe spec classifies errors as either "Correctable" or "Uncorrectable".
Previously we printed these as "Corrected" or "Uncorrected".  To avoid
confusion, use the same terms as the spec.

One confusing situation is when one agent detects an error, but another
agent is responsible for recovery, e.g., by re-attempting the operation.
The first agent may log a "correctable" error but it has not yet been
corrected.  The recovery agent must report an uncorrectable error if it is
unable to recover.  If we print the first agent's error as "Corrected", it
gives the false impression that it has already been resolved.

Sample message change:

  - pcieport 0000:00:1c.5: AER: Corrected error received: 0000:00:1c.5
  + pcieport 0000:00:1c.5: AER: Correctable error received: 0000:00:1c.5

Link: https://lore.kernel.org/r/20231206224231.732765-2-helgaas@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
---
 drivers/pci/pcie/aer.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 42a3bd35a3e11..4e39b64a58d45 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -435,10 +435,10 @@ void pci_aer_exit(struct pci_dev *dev)
 /*
  * AER error strings
  */
-static const char *aer_error_severity_string[] = {
-	"Uncorrected (Non-Fatal)",
-	"Uncorrected (Fatal)",
-	"Corrected"
+static const char * const aer_error_severity_string[] = {
+	"Uncorrectable (Non-Fatal)",
+	"Uncorrectable (Fatal)",
+	"Correctable"
 };
 
 static const char *aer_error_layer[] = {
-- 
GitLab


From 1291b716bbf969e101d517bfb8ba18d958f758b8 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 6 Dec 2023 16:42:30 -0600
Subject: [PATCH 2047/4076] PCI/AER: Decode Requester ID when no error info
 found

When a device with AER detects an error, it logs error information in its
own AER Error Status registers.  It may send an Error Message to the Root
Port (RCEC in the case of an RCiEP), which logs the fact that an Error
Message was received (Root Error Status) and the Requester ID of the
message source (Error Source Identification).

aer_print_port_info() prints the Requester ID from the Root Port Error
Source in the usual Linux "bb:dd.f" format, but when find_source_device()
finds no error details in the hierarchy below the Root Port, it printed the
raw Requester ID without decoding it.

Decode the Requester ID in the usual Linux format so it matches other
messages.

Sample message changes:

  - pcieport 0000:00:1c.5: AER: Correctable error received: 0000:00:1c.5
  - pcieport 0000:00:1c.5: AER: can't find device of ID00e5
  + pcieport 0000:00:1c.5: AER: Correctable error message received from 0000:00:1c.5
  + pcieport 0000:00:1c.5: AER: found no error details for 0000:00:1c.5

Link: https://lore.kernel.org/r/20231206224231.732765-3-helgaas@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
---
 drivers/pci/pcie/aer.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 4e39b64a58d45..412b00bdf9188 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -740,7 +740,7 @@ static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
 	u8 bus = info->id >> 8;
 	u8 devfn = info->id & 0xff;
 
-	pci_info(dev, "%s%s error received: %04x:%02x:%02x.%d\n",
+	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
 		 info->multi_error_valid ? "Multiple " : "",
 		 aer_error_severity_string[info->severity],
 		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
@@ -929,7 +929,12 @@ static bool find_source_device(struct pci_dev *parent,
 		pci_walk_bus(parent->subordinate, find_device_iter, e_info);
 
 	if (!e_info->error_dev_num) {
-		pci_info(parent, "can't find device of ID%04x\n", e_info->id);
+		u8 bus = e_info->id >> 8;
+		u8 devfn = e_info->id & 0xff;
+
+		pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n",
+			 pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn));
 		return false;
 	}
 	return true;
-- 
GitLab


From db02e176f597a14eb696141ffa008c2429453a15 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 6 Dec 2023 16:42:31 -0600
Subject: [PATCH 2048/4076] PCI/AER: Use explicit register sizes for struct
 members

aer_irq() reads the AER Root Error Status and Error Source Identification
(PCI_ERR_ROOT_STATUS and PCI_ERR_ROOT_ERR_SRC) registers directly into
struct aer_err_source.  Both registers are 32 bits, so declare the members
explicitly as "u32" instead of "unsigned int".

Similarly, aer_get_device_error_info() reads the AER Header Log
(PCI_ERR_HEADER_LOG) registers, which are also 32 bits, into struct
aer_header_log_regs.  Declare those members as "u32" as well.

No functional changes intended.

Link: https://lore.kernel.org/r/20231206224231.732765-4-helgaas@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/pcie/aer.c | 4 ++--
 include/linux/aer.h    | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 412b00bdf9188..05fc30bb5134d 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -41,8 +41,8 @@
 #define AER_MAX_TYPEOF_UNCOR_ERRS	27	/* as per PCI_ERR_UNCOR_STATUS*/
 
 struct aer_err_source {
-	unsigned int status;
-	unsigned int id;
+	u32 status;			/* PCI_ERR_ROOT_STATUS */
+	u32 id;				/* PCI_ERR_ROOT_ERR_SRC */
 };
 
 struct aer_rpc {
diff --git a/include/linux/aer.h b/include/linux/aer.h
index f6ea2f57d8089..ae0fae70d4bd2 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -19,10 +19,10 @@
 struct pci_dev;
 
 struct aer_header_log_regs {
-	unsigned int dw0;
-	unsigned int dw1;
-	unsigned int dw2;
-	unsigned int dw3;
+	u32 dw0;
+	u32 dw1;
+	u32 dw2;
+	u32 dw3;
 };
 
 struct aer_capability_regs {
-- 
GitLab


From cbc911392c05762d27b96a376d4be90c5f21f99d Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@rivosinc.com>
Date: Fri, 10 Nov 2023 09:59:03 -0800
Subject: [PATCH 2049/4076] RISC-V: Remove the removed single-letter extensions

There were a few single-letter extensions that we had references to
floating around in the kernel, but that never ended up as actual ISA
specs and have mostly been replaced by multi-letter extensions.  This
removes the references to those extensions.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231110175903.2631-1-palmer@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 6 ------
 arch/riscv/kernel/cpufeature.c | 4 ----
 2 files changed, 10 deletions(-)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 2438d4685da67..e1a0bd4f394af 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -11,19 +11,13 @@
 #include <uapi/asm/hwcap.h>
 
 #define RISCV_ISA_EXT_a		('a' - 'a')
-#define RISCV_ISA_EXT_b		('b' - 'a')
 #define RISCV_ISA_EXT_c		('c' - 'a')
 #define RISCV_ISA_EXT_d		('d' - 'a')
 #define RISCV_ISA_EXT_f		('f' - 'a')
 #define RISCV_ISA_EXT_h		('h' - 'a')
 #define RISCV_ISA_EXT_i		('i' - 'a')
-#define RISCV_ISA_EXT_j		('j' - 'a')
-#define RISCV_ISA_EXT_k		('k' - 'a')
 #define RISCV_ISA_EXT_m		('m' - 'a')
-#define RISCV_ISA_EXT_p		('p' - 'a')
 #define RISCV_ISA_EXT_q		('q' - 'a')
-#define RISCV_ISA_EXT_s		('s' - 'a')
-#define RISCV_ISA_EXT_u		('u' - 'a')
 #define RISCV_ISA_EXT_v		('v' - 'a')
 
 /*
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index dc0ab3e97cd28..b06c8830a1949 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -244,10 +244,6 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d),
 	__RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q),
 	__RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c),
-	__RISCV_ISA_EXT_DATA(b, RISCV_ISA_EXT_b),
-	__RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k),
-	__RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j),
-	__RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p),
 	__RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v),
 	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
 	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
-- 
GitLab


From 36d842d654beba970e74ff0f6016c93623b82d37 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 22 Nov 2023 17:47:02 +0100
Subject: [PATCH 2050/4076] RISC-V: hwprobe: Clarify cpus size parameter

The "count" parameter associated with the 'cpus' parameter of the
hwprobe syscall is the size in bytes of 'cpus'. Naming it 'cpu_count'
may mislead users (it did me) to think it's the number of CPUs that
are or can be represented by 'cpus' instead. This is particularly
easy (IMO) to get wrong since 'cpus' is documented to be defined by
CPU_SET(3) and CPU_SET(3) also documents a CPU_COUNT() (the number
of CPUs in set) macro. CPU_SET(3) refers to the size of cpu sets
with 'setsize'. Adopt 'cpusetsize' for the hwprobe parameter and
specifically state it is in bytes in Documentation/riscv/hwprobe.rst
to clarify.

Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231122164700.127954-7-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst              | 15 ++++++++-------
 arch/riscv/kernel/sys_riscv.c                     | 14 +++++++-------
 arch/riscv/kernel/vdso/hwprobe.c                  | 10 +++++-----
 tools/testing/selftests/riscv/hwprobe/hwprobe.c   |  2 +-
 tools/testing/selftests/riscv/hwprobe/hwprobe.h   |  2 +-
 .../testing/selftests/riscv/vector/vstate_prctl.c | 10 +---------
 6 files changed, 23 insertions(+), 30 deletions(-)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 7b2384de471f8..132e9acaa8f45 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -12,7 +12,7 @@ is defined in <asm/hwprobe.h>::
     };
 
     long sys_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-                           size_t cpu_count, cpu_set_t *cpus,
+                           size_t cpusetsize, cpu_set_t *cpus,
                            unsigned int flags);
 
 The arguments are split into three groups: an array of key-value pairs, a CPU
@@ -20,12 +20,13 @@ set, and some flags. The key-value pairs are supplied with a count. Userspace
 must prepopulate the key field for each element, and the kernel will fill in the
 value if the key is recognized. If a key is unknown to the kernel, its key field
 will be cleared to -1, and its value set to 0. The CPU set is defined by
-CPU_SET(3). For value-like keys (eg. vendor/arch/impl), the returned value will
-be only be valid if all CPUs in the given set have the same value. Otherwise -1
-will be returned. For boolean-like keys, the value returned will be a logical
-AND of the values for the specified CPUs. Usermode can supply NULL for cpus and
-0 for cpu_count as a shortcut for all online CPUs. There are currently no flags,
-this value must be zero for future compatibility.
+CPU_SET(3) with size ``cpusetsize`` bytes. For value-like keys (eg. vendor,
+arch, impl), the returned value will only be valid if all CPUs in the given set
+have the same value. Otherwise -1 will be returned. For boolean-like keys, the
+value returned will be a logical AND of the values for the specified CPUs.
+Usermode can supply NULL for ``cpus`` and 0 for ``cpusetsize`` as a shortcut for
+all online CPUs. There are currently no flags, this value must be zero for
+future compatibility.
 
 On success 0 is returned, on failure a negative error code is returned.
 
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index c712037dbe10e..5e4deb1308b86 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -246,7 +246,7 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 }
 
 static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
-			    size_t pair_count, size_t cpu_count,
+			    size_t pair_count, size_t cpusetsize,
 			    unsigned long __user *cpus_user,
 			    unsigned int flags)
 {
@@ -264,13 +264,13 @@ static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
 	 * 0 as a shortcut to all online CPUs.
 	 */
 	cpumask_clear(&cpus);
-	if (!cpu_count && !cpus_user) {
+	if (!cpusetsize && !cpus_user) {
 		cpumask_copy(&cpus, cpu_online_mask);
 	} else {
-		if (cpu_count > cpumask_size())
-			cpu_count = cpumask_size();
+		if (cpusetsize > cpumask_size())
+			cpusetsize = cpumask_size();
 
-		ret = copy_from_user(&cpus, cpus_user, cpu_count);
+		ret = copy_from_user(&cpus, cpus_user, cpusetsize);
 		if (ret)
 			return -EFAULT;
 
@@ -347,10 +347,10 @@ arch_initcall_sync(init_hwprobe_vdso_data);
 #endif /* CONFIG_MMU */
 
 SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
-		size_t, pair_count, size_t, cpu_count, unsigned long __user *,
+		size_t, pair_count, size_t, cpusetsize, unsigned long __user *,
 		cpus, unsigned int, flags)
 {
-	return do_riscv_hwprobe(pairs, pair_count, cpu_count,
+	return do_riscv_hwprobe(pairs, pair_count, cpusetsize,
 				cpus, flags);
 }
 
diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c
index cadf725ef7983..026b7645c5ab0 100644
--- a/arch/riscv/kernel/vdso/hwprobe.c
+++ b/arch/riscv/kernel/vdso/hwprobe.c
@@ -8,21 +8,21 @@
 #include <vdso/helpers.h>
 
 extern int riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
+			 size_t cpusetsize, unsigned long *cpus,
 			 unsigned int flags);
 
 /* Add a prototype to avoid -Wmissing-prototypes warning. */
 int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
+			 size_t cpusetsize, unsigned long *cpus,
 			 unsigned int flags);
 
 int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
+			 size_t cpusetsize, unsigned long *cpus,
 			 unsigned int flags)
 {
 	const struct vdso_data *vd = __arch_get_vdso_data();
 	const struct arch_vdso_data *avd = &vd->arch_data;
-	bool all_cpus = !cpu_count && !cpus;
+	bool all_cpus = !cpusetsize && !cpus;
 	struct riscv_hwprobe *p = pairs;
 	struct riscv_hwprobe *end = pairs + pair_count;
 
@@ -33,7 +33,7 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 	 * masks.
 	 */
 	if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus))
-		return riscv_hwprobe(pairs, pair_count, cpu_count, cpus, flags);
+		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
 
 	/* This is something we can handle, fill out the pairs. */
 	while (p < end) {
diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c
index c474891df3071..d53e0889b59e1 100644
--- a/tools/testing/selftests/riscv/hwprobe/hwprobe.c
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c
@@ -47,7 +47,7 @@ int main(int argc, char **argv)
 	ksft_test_result(out != 0, "Bad CPU set\n");
 
 	out = riscv_hwprobe(pairs, 8, 1, 0, 0);
-	ksft_test_result(out != 0, "NULL CPU set with non-zero count\n");
+	ksft_test_result(out != 0, "NULL CPU set with non-zero size\n");
 
 	pairs[0].key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR;
 	out = riscv_hwprobe(pairs, 1, 1, &cpus, 0);
diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.h b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
index 721b0ce73a569..e3fccb390c4dc 100644
--- a/tools/testing/selftests/riscv/hwprobe/hwprobe.h
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
@@ -10,6 +10,6 @@
  * contain the call.
  */
 long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-		   size_t cpu_count, unsigned long *cpus, unsigned int flags);
+		   size_t cpusetsize, unsigned long *cpus, unsigned int flags);
 
 #endif
diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c
index b348b475be570..8dcd399ef7fc9 100644
--- a/tools/testing/selftests/riscv/vector/vstate_prctl.c
+++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c
@@ -1,20 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <sys/prctl.h>
 #include <unistd.h>
-#include <asm/hwprobe.h>
 #include <errno.h>
 #include <sys/wait.h>
 
+#include "../hwprobe/hwprobe.h"
 #include "../../kselftest.h"
 
-/*
- * Rather than relying on having a new enough libc to define this, just do it
- * ourselves.  This way we don't need to be coupled to a new-enough libc to
- * contain the call.
- */
-long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-		   size_t cpu_count, unsigned long *cpus, unsigned int flags);
-
 #define NEXT_PROGRAM "./vstate_exec_nolibc"
 static int launch_test(int test_inherit)
 {
-- 
GitLab


From 53b2b22850e1ff9e2729ce8efe2d846ed7d3bff4 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 22 Nov 2023 17:47:03 +0100
Subject: [PATCH 2051/4076] RISC-V: Move the hwprobe syscall to its own file

As Palmer says, hwprobe is "sort of its own thing now, and it's only
going to get bigger..."

Suggested-by: Palmer Dabbelt <palmer@dabbelt.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231122164700.127954-8-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/Makefile      |   1 +
 arch/riscv/kernel/sys_hwprobe.c | 289 ++++++++++++++++++++++++++++++++
 arch/riscv/kernel/sys_riscv.c   | 285 -------------------------------
 3 files changed, 290 insertions(+), 285 deletions(-)
 create mode 100644 arch/riscv/kernel/sys_hwprobe.c

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index fee22a3d1b534..a1f5dc1455740 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -50,6 +50,7 @@ obj-y	+= setup.o
 obj-y	+= signal.o
 obj-y	+= syscall_table.o
 obj-y	+= sys_riscv.o
+obj-y	+= sys_hwprobe.o
 obj-y	+= time.o
 obj-y	+= traps.o
 obj-y	+= riscv_ksyms.o
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
new file mode 100644
index 0000000000000..c0ccf1f45aaac
--- /dev/null
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The hwprobe interface, for allowing userspace to probe to see which features
+ * are supported by the hardware.  See Documentation/arch/riscv/hwprobe.rst for
+ * more details.
+ */
+#include <linux/syscalls.h>
+#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/hwprobe.h>
+#include <asm/sbi.h>
+#include <asm/switch_to.h>
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/vector.h>
+#include <vdso/vsyscall.h>
+
+
+static void hwprobe_arch_id(struct riscv_hwprobe *pair,
+			    const struct cpumask *cpus)
+{
+	u64 id = -1ULL;
+	bool first = true;
+	int cpu;
+
+	for_each_cpu(cpu, cpus) {
+		u64 cpu_id;
+
+		switch (pair->key) {
+		case RISCV_HWPROBE_KEY_MVENDORID:
+			cpu_id = riscv_cached_mvendorid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MIMPID:
+			cpu_id = riscv_cached_mimpid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MARCHID:
+			cpu_id = riscv_cached_marchid(cpu);
+			break;
+		}
+
+		if (first) {
+			id = cpu_id;
+			first = false;
+		}
+
+		/*
+		 * If there's a mismatch for the given set, return -1 in the
+		 * value.
+		 */
+		if (id != cpu_id) {
+			id = -1ULL;
+			break;
+		}
+	}
+
+	pair->value = id;
+}
+
+static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	int cpu;
+	u64 missing = 0;
+
+	pair->value = 0;
+	if (has_fpu())
+		pair->value |= RISCV_HWPROBE_IMA_FD;
+
+	if (riscv_isa_extension_available(NULL, c))
+		pair->value |= RISCV_HWPROBE_IMA_C;
+
+	if (has_vector())
+		pair->value |= RISCV_HWPROBE_IMA_V;
+
+	/*
+	 * Loop through and record extensions that 1) anyone has, and 2) anyone
+	 * doesn't have.
+	 */
+	for_each_cpu(cpu, cpus) {
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+#define EXT_KEY(ext)									\
+	do {										\
+		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
+			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
+		else									\
+			missing |= RISCV_HWPROBE_EXT_##ext;				\
+	} while (false)
+
+		/*
+		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
+		 * regardless of the kernel's configuration, as no other checks, besides
+		 * presence in the hart_isa bitmap, are made.
+		 */
+		EXT_KEY(ZBA);
+		EXT_KEY(ZBB);
+		EXT_KEY(ZBS);
+		EXT_KEY(ZICBOZ);
+#undef EXT_KEY
+	}
+
+	/* Now turn off reporting features if any CPU is missing it. */
+	pair->value &= ~missing;
+}
+
+static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+{
+	struct riscv_hwprobe pair;
+
+	hwprobe_isa_ext0(&pair, cpus);
+	return (pair.value & ext);
+}
+
+static u64 hwprobe_misaligned(const struct cpumask *cpus)
+{
+	int cpu;
+	u64 perf = -1ULL;
+
+	for_each_cpu(cpu, cpus) {
+		int this_perf = per_cpu(misaligned_access_speed, cpu);
+
+		if (perf == -1ULL)
+			perf = this_perf;
+
+		if (perf != this_perf) {
+			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+			break;
+		}
+	}
+
+	if (perf == -1ULL)
+		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+
+	return perf;
+}
+
+static void hwprobe_one_pair(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	switch (pair->key) {
+	case RISCV_HWPROBE_KEY_MVENDORID:
+	case RISCV_HWPROBE_KEY_MARCHID:
+	case RISCV_HWPROBE_KEY_MIMPID:
+		hwprobe_arch_id(pair, cpus);
+		break;
+	/*
+	 * The kernel already assumes that the base single-letter ISA
+	 * extensions are supported on all harts, and only supports the
+	 * IMA base, so just cheat a bit here and tell that to
+	 * userspace.
+	 */
+	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
+		pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA;
+		break;
+
+	case RISCV_HWPROBE_KEY_IMA_EXT_0:
+		hwprobe_isa_ext0(pair, cpus);
+		break;
+
+	case RISCV_HWPROBE_KEY_CPUPERF_0:
+		pair->value = hwprobe_misaligned(cpus);
+		break;
+
+	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
+		pair->value = 0;
+		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
+			pair->value = riscv_cboz_block_size;
+		break;
+
+	/*
+	 * For forward compatibility, unknown keys don't fail the whole
+	 * call, but get their element key set to -1 and value set to 0
+	 * indicating they're unrecognized.
+	 */
+	default:
+		pair->key = -1;
+		pair->value = 0;
+		break;
+	}
+}
+
+static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	size_t out;
+	int ret;
+	cpumask_t cpus;
+
+	/* Check the reserved flags. */
+	if (flags != 0)
+		return -EINVAL;
+
+	/*
+	 * The interface supports taking in a CPU mask, and returns values that
+	 * are consistent across that mask. Allow userspace to specify NULL and
+	 * 0 as a shortcut to all online CPUs.
+	 */
+	cpumask_clear(&cpus);
+	if (!cpusetsize && !cpus_user) {
+		cpumask_copy(&cpus, cpu_online_mask);
+	} else {
+		if (cpusetsize > cpumask_size())
+			cpusetsize = cpumask_size();
+
+		ret = copy_from_user(&cpus, cpus_user, cpusetsize);
+		if (ret)
+			return -EFAULT;
+
+		/*
+		 * Userspace must provide at least one online CPU, without that
+		 * there's no way to define what is supported.
+		 */
+		cpumask_and(&cpus, &cpus, cpu_online_mask);
+		if (cpumask_empty(&cpus))
+			return -EINVAL;
+	}
+
+	for (out = 0; out < pair_count; out++, pairs++) {
+		struct riscv_hwprobe pair;
+
+		if (get_user(pair.key, &pairs->key))
+			return -EFAULT;
+
+		pair.value = 0;
+		hwprobe_one_pair(&pair, &cpus);
+		ret = put_user(pair.key, &pairs->key);
+		if (ret == 0)
+			ret = put_user(pair.value, &pairs->value);
+
+		if (ret)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_MMU
+
+static int __init init_hwprobe_vdso_data(void)
+{
+	struct vdso_data *vd = __arch_get_k_vdso_data();
+	struct arch_vdso_data *avd = &vd->arch_data;
+	u64 id_bitsmash = 0;
+	struct riscv_hwprobe pair;
+	int key;
+
+	/*
+	 * Initialize vDSO data with the answers for the "all CPUs" case, to
+	 * save a syscall in the common case.
+	 */
+	for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) {
+		pair.key = key;
+		hwprobe_one_pair(&pair, cpu_online_mask);
+
+		WARN_ON_ONCE(pair.key < 0);
+
+		avd->all_cpu_hwprobe_values[key] = pair.value;
+		/*
+		 * Smash together the vendor, arch, and impl IDs to see if
+		 * they're all 0 or any negative.
+		 */
+		if (key <= RISCV_HWPROBE_KEY_MIMPID)
+			id_bitsmash |= pair.value;
+	}
+
+	/*
+	 * If the arch, vendor, and implementation ID are all the same across
+	 * all harts, then assume all CPUs are the same, and allow the vDSO to
+	 * answer queries for arbitrary masks. However if all values are 0 (not
+	 * populated) or any value returns -1 (varies across CPUs), then the
+	 * vDSO should defer to the kernel for exotic cpu masks.
+	 */
+	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
+	return 0;
+}
+
+arch_initcall_sync(init_hwprobe_vdso_data);
+
+#endif /* CONFIG_MMU */
+
+SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
+		size_t, pair_count, size_t, cpusetsize, unsigned long __user *,
+		cpus, unsigned int, flags)
+{
+	return do_riscv_hwprobe(pairs, pair_count, cpusetsize,
+				cpus, flags);
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 5e4deb1308b86..f1c1416a9f1e5 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -7,15 +7,7 @@
 
 #include <linux/syscalls.h>
 #include <asm/cacheflush.h>
-#include <asm/cpufeature.h>
-#include <asm/hwprobe.h>
-#include <asm/sbi.h>
-#include <asm/vector.h>
-#include <asm/switch_to.h>
-#include <asm/uaccess.h>
-#include <asm/unistd.h>
 #include <asm-generic/mman-common.h>
-#include <vdso/vsyscall.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -77,283 +69,6 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
 	return 0;
 }
 
-/*
- * The hwprobe interface, for allowing userspace to probe to see which features
- * are supported by the hardware.  See Documentation/arch/riscv/hwprobe.rst for more
- * details.
- */
-static void hwprobe_arch_id(struct riscv_hwprobe *pair,
-			    const struct cpumask *cpus)
-{
-	u64 id = -1ULL;
-	bool first = true;
-	int cpu;
-
-	for_each_cpu(cpu, cpus) {
-		u64 cpu_id;
-
-		switch (pair->key) {
-		case RISCV_HWPROBE_KEY_MVENDORID:
-			cpu_id = riscv_cached_mvendorid(cpu);
-			break;
-		case RISCV_HWPROBE_KEY_MIMPID:
-			cpu_id = riscv_cached_mimpid(cpu);
-			break;
-		case RISCV_HWPROBE_KEY_MARCHID:
-			cpu_id = riscv_cached_marchid(cpu);
-			break;
-		}
-
-		if (first) {
-			id = cpu_id;
-			first = false;
-		}
-
-		/*
-		 * If there's a mismatch for the given set, return -1 in the
-		 * value.
-		 */
-		if (id != cpu_id) {
-			id = -1ULL;
-			break;
-		}
-	}
-
-	pair->value = id;
-}
-
-static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
-			     const struct cpumask *cpus)
-{
-	int cpu;
-	u64 missing = 0;
-
-	pair->value = 0;
-	if (has_fpu())
-		pair->value |= RISCV_HWPROBE_IMA_FD;
-
-	if (riscv_isa_extension_available(NULL, c))
-		pair->value |= RISCV_HWPROBE_IMA_C;
-
-	if (has_vector())
-		pair->value |= RISCV_HWPROBE_IMA_V;
-
-	/*
-	 * Loop through and record extensions that 1) anyone has, and 2) anyone
-	 * doesn't have.
-	 */
-	for_each_cpu(cpu, cpus) {
-		struct riscv_isainfo *isainfo = &hart_isa[cpu];
-
-#define EXT_KEY(ext)									\
-	do {										\
-		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
-			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
-		else									\
-			missing |= RISCV_HWPROBE_EXT_##ext;				\
-	} while (false)
-
-		/*
-		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
-		 * regardless of the kernel's configuration, as no other checks, besides
-		 * presence in the hart_isa bitmap, are made.
-		 */
-		EXT_KEY(ZBA);
-		EXT_KEY(ZBB);
-		EXT_KEY(ZBS);
-		EXT_KEY(ZICBOZ);
-#undef EXT_KEY
-	}
-
-	/* Now turn off reporting features if any CPU is missing it. */
-	pair->value &= ~missing;
-}
-
-static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
-{
-	struct riscv_hwprobe pair;
-
-	hwprobe_isa_ext0(&pair, cpus);
-	return (pair.value & ext);
-}
-
-static u64 hwprobe_misaligned(const struct cpumask *cpus)
-{
-	int cpu;
-	u64 perf = -1ULL;
-
-	for_each_cpu(cpu, cpus) {
-		int this_perf = per_cpu(misaligned_access_speed, cpu);
-
-		if (perf == -1ULL)
-			perf = this_perf;
-
-		if (perf != this_perf) {
-			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
-			break;
-		}
-	}
-
-	if (perf == -1ULL)
-		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
-
-	return perf;
-}
-
-static void hwprobe_one_pair(struct riscv_hwprobe *pair,
-			     const struct cpumask *cpus)
-{
-	switch (pair->key) {
-	case RISCV_HWPROBE_KEY_MVENDORID:
-	case RISCV_HWPROBE_KEY_MARCHID:
-	case RISCV_HWPROBE_KEY_MIMPID:
-		hwprobe_arch_id(pair, cpus);
-		break;
-	/*
-	 * The kernel already assumes that the base single-letter ISA
-	 * extensions are supported on all harts, and only supports the
-	 * IMA base, so just cheat a bit here and tell that to
-	 * userspace.
-	 */
-	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
-		pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA;
-		break;
-
-	case RISCV_HWPROBE_KEY_IMA_EXT_0:
-		hwprobe_isa_ext0(pair, cpus);
-		break;
-
-	case RISCV_HWPROBE_KEY_CPUPERF_0:
-		pair->value = hwprobe_misaligned(cpus);
-		break;
-
-	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
-		pair->value = 0;
-		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
-			pair->value = riscv_cboz_block_size;
-		break;
-
-	/*
-	 * For forward compatibility, unknown keys don't fail the whole
-	 * call, but get their element key set to -1 and value set to 0
-	 * indicating they're unrecognized.
-	 */
-	default:
-		pair->key = -1;
-		pair->value = 0;
-		break;
-	}
-}
-
-static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
-			    size_t pair_count, size_t cpusetsize,
-			    unsigned long __user *cpus_user,
-			    unsigned int flags)
-{
-	size_t out;
-	int ret;
-	cpumask_t cpus;
-
-	/* Check the reserved flags. */
-	if (flags != 0)
-		return -EINVAL;
-
-	/*
-	 * The interface supports taking in a CPU mask, and returns values that
-	 * are consistent across that mask. Allow userspace to specify NULL and
-	 * 0 as a shortcut to all online CPUs.
-	 */
-	cpumask_clear(&cpus);
-	if (!cpusetsize && !cpus_user) {
-		cpumask_copy(&cpus, cpu_online_mask);
-	} else {
-		if (cpusetsize > cpumask_size())
-			cpusetsize = cpumask_size();
-
-		ret = copy_from_user(&cpus, cpus_user, cpusetsize);
-		if (ret)
-			return -EFAULT;
-
-		/*
-		 * Userspace must provide at least one online CPU, without that
-		 * there's no way to define what is supported.
-		 */
-		cpumask_and(&cpus, &cpus, cpu_online_mask);
-		if (cpumask_empty(&cpus))
-			return -EINVAL;
-	}
-
-	for (out = 0; out < pair_count; out++, pairs++) {
-		struct riscv_hwprobe pair;
-
-		if (get_user(pair.key, &pairs->key))
-			return -EFAULT;
-
-		pair.value = 0;
-		hwprobe_one_pair(&pair, &cpus);
-		ret = put_user(pair.key, &pairs->key);
-		if (ret == 0)
-			ret = put_user(pair.value, &pairs->value);
-
-		if (ret)
-			return -EFAULT;
-	}
-
-	return 0;
-}
-
-#ifdef CONFIG_MMU
-
-static int __init init_hwprobe_vdso_data(void)
-{
-	struct vdso_data *vd = __arch_get_k_vdso_data();
-	struct arch_vdso_data *avd = &vd->arch_data;
-	u64 id_bitsmash = 0;
-	struct riscv_hwprobe pair;
-	int key;
-
-	/*
-	 * Initialize vDSO data with the answers for the "all CPUs" case, to
-	 * save a syscall in the common case.
-	 */
-	for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) {
-		pair.key = key;
-		hwprobe_one_pair(&pair, cpu_online_mask);
-
-		WARN_ON_ONCE(pair.key < 0);
-
-		avd->all_cpu_hwprobe_values[key] = pair.value;
-		/*
-		 * Smash together the vendor, arch, and impl IDs to see if
-		 * they're all 0 or any negative.
-		 */
-		if (key <= RISCV_HWPROBE_KEY_MIMPID)
-			id_bitsmash |= pair.value;
-	}
-
-	/*
-	 * If the arch, vendor, and implementation ID are all the same across
-	 * all harts, then assume all CPUs are the same, and allow the vDSO to
-	 * answer queries for arbitrary masks. However if all values are 0 (not
-	 * populated) or any value returns -1 (varies across CPUs), then the
-	 * vDSO should defer to the kernel for exotic cpu masks.
-	 */
-	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
-	return 0;
-}
-
-arch_initcall_sync(init_hwprobe_vdso_data);
-
-#endif /* CONFIG_MMU */
-
-SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
-		size_t, pair_count, size_t, cpusetsize, unsigned long __user *,
-		cpus, unsigned int, flags)
-{
-	return do_riscv_hwprobe(pairs, pair_count, cpusetsize,
-				cpus, flags);
-}
-
 /* Not defined using SYSCALL_DEFINE0 to avoid error injection */
 asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *__unused)
 {
-- 
GitLab


From e178bf146e4b8c774a7b00aa2419e400f4f7894f Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 22 Nov 2023 17:47:04 +0100
Subject: [PATCH 2052/4076] RISC-V: hwprobe: Introduce which-cpus flag

Introduce the first flag for the hwprobe syscall. The flag basically
reverses its behavior, i.e. instead of populating the values of keys
for a given set of cpus, the set of cpus after the call is the result
of finding a set which supports the values of the keys. In order to
do this, we implement a pair compare function which takes the type of
value (a single value vs. a bitmask of booleans) into consideration.
We also implement vdso support for the new flag.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20231122164700.127954-9-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 17 ++++-
 arch/riscv/include/asm/hwprobe.h      | 24 +++++++
 arch/riscv/include/uapi/asm/hwprobe.h |  3 +
 arch/riscv/kernel/sys_hwprobe.c       | 94 +++++++++++++++++++++++++--
 arch/riscv/kernel/vdso/hwprobe.c      | 80 ++++++++++++++++++++---
 5 files changed, 204 insertions(+), 14 deletions(-)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 132e9acaa8f45..12f9b0a043ac0 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -25,8 +25,21 @@ arch, impl), the returned value will only be valid if all CPUs in the given set
 have the same value. Otherwise -1 will be returned. For boolean-like keys, the
 value returned will be a logical AND of the values for the specified CPUs.
 Usermode can supply NULL for ``cpus`` and 0 for ``cpusetsize`` as a shortcut for
-all online CPUs. There are currently no flags, this value must be zero for
-future compatibility.
+all online CPUs. The currently supported flags are:
+
+* :c:macro:`RISCV_HWPROBE_WHICH_CPUS`: This flag basically reverses the behavior
+  of sys_riscv_hwprobe().  Instead of populating the values of keys for a given
+  set of CPUs, the values of each key are given and the set of CPUs is reduced
+  by sys_riscv_hwprobe() to only those which match each of the key-value pairs.
+  How matching is done depends on the key type.  For value-like keys, matching
+  means to be the exact same as the value.  For boolean-like keys, matching
+  means the result of a logical AND of the pair's value with the CPU's value is
+  exactly the same as the pair's value.  Additionally, when ``cpus`` is an empty
+  set, then it is initialized to all online CPUs which fit within it, i.e. the
+  CPU set returned is the reduction of all the online CPUs which can be
+  represented with a CPU set of size ``cpusetsize``.
+
+All other flags are reserved for future compatibility and must be zero.
 
 On success 0 is returned, on failure a negative error code is returned.
 
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index 5c48f48e79a67..630507dff5ead 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -15,4 +15,28 @@ static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 	return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY;
 }
 
+static inline bool hwprobe_key_is_bitmask(__s64 key)
+{
+	switch (key) {
+	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
+	case RISCV_HWPROBE_KEY_IMA_EXT_0:
+	case RISCV_HWPROBE_KEY_CPUPERF_0:
+		return true;
+	}
+
+	return false;
+}
+
+static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair,
+					  struct riscv_hwprobe *other_pair)
+{
+	if (pair->key != other_pair->key)
+		return false;
+
+	if (hwprobe_key_is_bitmask(pair->key))
+		return (pair->value & other_pair->value) == other_pair->value;
+
+	return pair->value == other_pair->value;
+}
+
 #endif
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index b659ffcfcdb45..7aa7d5c71e790 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -40,4 +40,7 @@ struct riscv_hwprobe {
 #define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE	6
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
+/* Flags */
+#define RISCV_HWPROBE_WHICH_CPUS	(1 << 0)
+
 #endif
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index c0ccf1f45aaac..b7cfb26ce31c9 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -179,10 +179,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 	}
 }
 
-static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
-			    size_t pair_count, size_t cpusetsize,
-			    unsigned long __user *cpus_user,
-			    unsigned int flags)
+static int hwprobe_get_values(struct riscv_hwprobe __user *pairs,
+			      size_t pair_count, size_t cpusetsize,
+			      unsigned long __user *cpus_user,
+			      unsigned int flags)
 {
 	size_t out;
 	int ret;
@@ -236,6 +236,92 @@ static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
 	return 0;
 }
 
+static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	cpumask_t cpus, one_cpu;
+	bool clear_all = false;
+	size_t i;
+	int ret;
+
+	if (flags != RISCV_HWPROBE_WHICH_CPUS)
+		return -EINVAL;
+
+	if (!cpusetsize || !cpus_user)
+		return -EINVAL;
+
+	if (cpusetsize > cpumask_size())
+		cpusetsize = cpumask_size();
+
+	ret = copy_from_user(&cpus, cpus_user, cpusetsize);
+	if (ret)
+		return -EFAULT;
+
+	if (cpumask_empty(&cpus))
+		cpumask_copy(&cpus, cpu_online_mask);
+
+	cpumask_and(&cpus, &cpus, cpu_online_mask);
+
+	cpumask_clear(&one_cpu);
+
+	for (i = 0; i < pair_count; i++) {
+		struct riscv_hwprobe pair, tmp;
+		int cpu;
+
+		ret = copy_from_user(&pair, &pairs[i], sizeof(pair));
+		if (ret)
+			return -EFAULT;
+
+		if (!riscv_hwprobe_key_is_valid(pair.key)) {
+			clear_all = true;
+			pair = (struct riscv_hwprobe){ .key = -1, };
+			ret = copy_to_user(&pairs[i], &pair, sizeof(pair));
+			if (ret)
+				return -EFAULT;
+		}
+
+		if (clear_all)
+			continue;
+
+		tmp = (struct riscv_hwprobe){ .key = pair.key, };
+
+		for_each_cpu(cpu, &cpus) {
+			cpumask_set_cpu(cpu, &one_cpu);
+
+			hwprobe_one_pair(&tmp, &one_cpu);
+
+			if (!riscv_hwprobe_pair_cmp(&tmp, &pair))
+				cpumask_clear_cpu(cpu, &cpus);
+
+			cpumask_clear_cpu(cpu, &one_cpu);
+		}
+	}
+
+	if (clear_all)
+		cpumask_clear(&cpus);
+
+	ret = copy_to_user(cpus_user, &cpus, cpusetsize);
+	if (ret)
+		return -EFAULT;
+
+	return 0;
+}
+
+static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return hwprobe_get_cpus(pairs, pair_count, cpusetsize,
+					cpus_user, flags);
+
+	return hwprobe_get_values(pairs, pair_count, cpusetsize,
+				  cpus_user, flags);
+}
+
 #ifdef CONFIG_MMU
 
 static int __init init_hwprobe_vdso_data(void)
diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c
index 026b7645c5ab0..1e926e4b5881b 100644
--- a/arch/riscv/kernel/vdso/hwprobe.c
+++ b/arch/riscv/kernel/vdso/hwprobe.c
@@ -3,6 +3,7 @@
  * Copyright 2023 Rivos, Inc
  */
 
+#include <linux/string.h>
 #include <linux/types.h>
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
@@ -11,14 +12,9 @@ extern int riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 			 size_t cpusetsize, unsigned long *cpus,
 			 unsigned int flags);
 
-/* Add a prototype to avoid -Wmissing-prototypes warning. */
-int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpusetsize, unsigned long *cpus,
-			 unsigned int flags);
-
-int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpusetsize, unsigned long *cpus,
-			 unsigned int flags)
+static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count,
+				 size_t cpusetsize, unsigned long *cpus,
+				 unsigned int flags)
 {
 	const struct vdso_data *vd = __arch_get_vdso_data();
 	const struct arch_vdso_data *avd = &vd->arch_data;
@@ -50,3 +46,71 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 
 	return 0;
 }
+
+static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count,
+			       size_t cpusetsize, unsigned long *cpus,
+			       unsigned int flags)
+{
+	const struct vdso_data *vd = __arch_get_vdso_data();
+	const struct arch_vdso_data *avd = &vd->arch_data;
+	struct riscv_hwprobe *p = pairs;
+	struct riscv_hwprobe *end = pairs + pair_count;
+	unsigned char *c = (unsigned char *)cpus;
+	bool empty_cpus = true;
+	bool clear_all = false;
+	int i;
+
+	if (!cpusetsize || !cpus)
+		return -EINVAL;
+
+	for (i = 0; i < cpusetsize; i++) {
+		if (c[i]) {
+			empty_cpus = false;
+			break;
+		}
+	}
+
+	if (empty_cpus || flags != RISCV_HWPROBE_WHICH_CPUS || !avd->homogeneous_cpus)
+		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
+
+	while (p < end) {
+		if (riscv_hwprobe_key_is_valid(p->key)) {
+			struct riscv_hwprobe t = {
+				.key = p->key,
+				.value = avd->all_cpu_hwprobe_values[p->key],
+			};
+
+			if (!riscv_hwprobe_pair_cmp(&t, p))
+				clear_all = true;
+		} else {
+			clear_all = true;
+			p->key = -1;
+			p->value = 0;
+		}
+		p++;
+	}
+
+	if (clear_all) {
+		for (i = 0; i < cpusetsize; i++)
+			c[i] = 0;
+	}
+
+	return 0;
+}
+
+/* Add a prototype to avoid -Wmissing-prototypes warning. */
+int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+			 size_t cpusetsize, unsigned long *cpus,
+			 unsigned int flags);
+
+int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+			 size_t cpusetsize, unsigned long *cpus,
+			 unsigned int flags)
+{
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return riscv_vdso_get_cpus(pairs, pair_count, cpusetsize,
+					   cpus, flags);
+
+	return riscv_vdso_get_values(pairs, pair_count, cpusetsize,
+				     cpus, flags);
+}
-- 
GitLab


From ef7d6abb2cf57a18d34b332f0865c4d03bd810a3 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 22 Nov 2023 17:47:05 +0100
Subject: [PATCH 2053/4076] RISC-V: selftests: Add which-cpus hwprobe test

Test the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe. The test also
has a command line interface in order to get the cpu list for
arbitrary hwprobe pairs.

Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231122164700.127954-10-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../testing/selftests/riscv/hwprobe/Makefile  |   5 +-
 .../selftests/riscv/hwprobe/which-cpus.c      | 154 ++++++++++++++++++
 2 files changed, 158 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/riscv/hwprobe/which-cpus.c

diff --git a/tools/testing/selftests/riscv/hwprobe/Makefile b/tools/testing/selftests/riscv/hwprobe/Makefile
index f224b84591fbf..cec81610a5f27 100644
--- a/tools/testing/selftests/riscv/hwprobe/Makefile
+++ b/tools/testing/selftests/riscv/hwprobe/Makefile
@@ -4,7 +4,7 @@
 
 CFLAGS += -I$(top_srcdir)/tools/include
 
-TEST_GEN_PROGS := hwprobe cbo
+TEST_GEN_PROGS := hwprobe cbo which-cpus
 
 include ../../lib.mk
 
@@ -13,3 +13,6 @@ $(OUTPUT)/hwprobe: hwprobe.c sys_hwprobe.S
 
 $(OUTPUT)/cbo: cbo.c sys_hwprobe.S
 	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
+
+$(OUTPUT)/which-cpus: which-cpus.c sys_hwprobe.S
+	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
diff --git a/tools/testing/selftests/riscv/hwprobe/which-cpus.c b/tools/testing/selftests/riscv/hwprobe/which-cpus.c
new file mode 100644
index 0000000000000..82c121412dfc6
--- /dev/null
+++ b/tools/testing/selftests/riscv/hwprobe/which-cpus.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ *
+ * Test the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe. Also provides a command
+ * line interface to get the cpu list for arbitrary hwprobe pairs.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sched.h>
+#include <unistd.h>
+#include <assert.h>
+
+#include "hwprobe.h"
+#include "../../kselftest.h"
+
+static void help(void)
+{
+	printf("\n"
+	       "which-cpus: [-h] [<key=value> [<key=value> ...]]\n\n"
+	       "   Without parameters, tests the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe.\n"
+	       "   With parameters, where each parameter is a hwprobe pair written as\n"
+	       "   <key=value>, outputs the cpulist for cpus which all match the given set\n"
+	       "   of pairs.  'key' and 'value' should be in numeric form, e.g. 4=0x3b\n");
+}
+
+static void print_cpulist(cpu_set_t *cpus)
+{
+	int start = 0, end = 0;
+
+	if (!CPU_COUNT(cpus)) {
+		printf("cpus: None\n");
+		return;
+	}
+
+	printf("cpus:");
+	for (int i = 0, c = 0; i < CPU_COUNT(cpus); i++, c++) {
+		if (start != end && !CPU_ISSET(c, cpus))
+			printf("-%d", end);
+
+		while (!CPU_ISSET(c, cpus))
+			++c;
+
+		if (i != 0 && c == end + 1) {
+			end = c;
+			continue;
+		}
+
+		printf("%c%d", i == 0 ? ' ' : ',', c);
+		start = end = c;
+	}
+	if (start != end)
+		printf("-%d", end);
+	printf("\n");
+}
+
+static void do_which_cpus(int argc, char **argv, cpu_set_t *cpus)
+{
+	struct riscv_hwprobe *pairs;
+	int nr_pairs = argc - 1;
+	char *start, *end;
+	int rc;
+
+	pairs = malloc(nr_pairs * sizeof(struct riscv_hwprobe));
+	assert(pairs);
+
+	for (int i = 0; i < nr_pairs; i++) {
+		start = argv[i + 1];
+		pairs[i].key = strtol(start, &end, 0);
+		assert(end != start && *end == '=');
+		start = end + 1;
+		pairs[i].value = strtoul(start, &end, 0);
+		assert(end != start && *end == '\0');
+	}
+
+	rc = riscv_hwprobe(pairs, nr_pairs, sizeof(cpu_set_t), (unsigned long *)cpus, RISCV_HWPROBE_WHICH_CPUS);
+	assert(rc == 0);
+	print_cpulist(cpus);
+	free(pairs);
+}
+
+int main(int argc, char **argv)
+{
+	struct riscv_hwprobe pairs[2];
+	cpu_set_t cpus_aff, cpus;
+	__u64 ext0_all;
+	long rc;
+
+	rc = sched_getaffinity(0, sizeof(cpu_set_t), &cpus_aff);
+	assert(rc == 0);
+
+	if (argc > 1) {
+		if (!strcmp(argv[1], "-h"))
+			help();
+		else
+			do_which_cpus(argc, argv, &cpus_aff);
+		return 0;
+	}
+
+	ksft_print_header();
+	ksft_set_plan(7);
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, };
+	rc = riscv_hwprobe(pairs, 1, 0, NULL, 0);
+	assert(rc == 0 && pairs[0].key == RISCV_HWPROBE_KEY_BASE_BEHAVIOR &&
+	       pairs[0].value == RISCV_HWPROBE_BASE_BEHAVIOR_IMA);
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, };
+	rc = riscv_hwprobe(pairs, 1, 0, NULL, 0);
+	assert(rc == 0 && pairs[0].key == RISCV_HWPROBE_KEY_IMA_EXT_0);
+	ext0_all = pairs[0].value;
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 1, 0, (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == -EINVAL, "no cpusetsize\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	rc = riscv_hwprobe(pairs, 1, sizeof(cpu_set_t), NULL, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == -EINVAL, "NULL cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = 0xbadc0de, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 1, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == 0, "unknown key\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0, "duplicate keys\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ext0_all, };
+	CPU_ZERO(&cpus);
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == sysconf(_SC_NPROCESSORS_ONLN), "set all cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ext0_all, };
+	memcpy(&cpus, &cpus_aff, sizeof(cpu_set_t));
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_EQUAL(&cpus, &cpus_aff), "set all affinity cpus\n");
+
+	pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, };
+	pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ~ext0_all, };
+	memcpy(&cpus, &cpus_aff, sizeof(cpu_set_t));
+	rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS);
+	ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == 0, "clear all cpus\n");
+
+	ksft_finished();
+}
-- 
GitLab


From 7097c96411d22a1b3f6370dfd7eb2e3b7b83ff98 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 2 Jan 2024 16:28:04 +0000
Subject: [PATCH 2054/4076] cachefiles: Fix __cachefiles_prepare_write()

Fix __cachefiles_prepare_write() to correctly determine whether the
requested write will fit correctly with the DIO alignment.

Reported-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Yiqun Leng <yqleng@linux.alibaba.com>
Tested-by: Jia Zhu <zhujia.zj@bytedance.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-erofs@lists.ozlabs.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/cachefiles/io.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index bffffedce4a93..7529b40bc95a9 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -522,16 +522,22 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 			       bool no_space_allocated_yet)
 {
 	struct cachefiles_cache *cache = object->volume->cache;
-	loff_t start = *_start, pos;
-	size_t len = *_len, down;
+	unsigned long long start = *_start, pos;
+	size_t len = *_len;
 	int ret;
 
 	/* Round to DIO size */
-	down = start - round_down(start, PAGE_SIZE);
-	*_start = start - down;
-	*_len = round_up(down + len, PAGE_SIZE);
-	if (down < start || *_len > upper_len)
+	start = round_down(*_start, PAGE_SIZE);
+	if (start != *_start) {
+		kleave(" = -ENOBUFS [down]");
+		return -ENOBUFS;
+	}
+	if (*_len > upper_len) {
+		kleave(" = -ENOBUFS [up]");
 		return -ENOBUFS;
+	}
+
+	*_len = round_up(len, PAGE_SIZE);
 
 	/* We need to work out whether there's sufficient disk space to perform
 	 * the write - but we can skip that check if we have space already
@@ -542,7 +548,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 
 	pos = cachefiles_inject_read_error();
 	if (pos == 0)
-		pos = vfs_llseek(file, *_start, SEEK_DATA);
+		pos = vfs_llseek(file, start, SEEK_DATA);
 	if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) {
 		if (pos == -ENXIO)
 			goto check_space; /* Unallocated tail */
@@ -550,7 +556,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 					  cachefiles_trace_seek_error);
 		return pos;
 	}
-	if ((u64)pos >= (u64)*_start + *_len)
+	if (pos >= start + *_len)
 		goto check_space; /* Unallocated region */
 
 	/* We have a block that's at least partially filled - if we're low on
@@ -563,13 +569,13 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 
 	pos = cachefiles_inject_read_error();
 	if (pos == 0)
-		pos = vfs_llseek(file, *_start, SEEK_HOLE);
+		pos = vfs_llseek(file, start, SEEK_HOLE);
 	if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) {
 		trace_cachefiles_io_error(object, file_inode(file), pos,
 					  cachefiles_trace_seek_error);
 		return pos;
 	}
-	if ((u64)pos >= (u64)*_start + *_len)
+	if (pos >= start + *_len)
 		return 0; /* Fully allocated */
 
 	/* Partially allocated, but insufficient space: cull. */
@@ -577,7 +583,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 	ret = cachefiles_inject_remove_error();
 	if (ret == 0)
 		ret = vfs_fallocate(file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
-				    *_start, *_len);
+				    start, *_len);
 	if (ret < 0) {
 		trace_cachefiles_io_error(object, file_inode(file), ret,
 					  cachefiles_trace_fallocate_error);
-- 
GitLab


From 9546ac78b232bac56ff975072b1965e0e755ebd4 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 2 Jan 2024 20:33:17 +0000
Subject: [PATCH 2055/4076] 9p: Fix initialisation of netfs_inode for 9p

The 9p filesystem is calling netfs_inode_init() in v9fs_init_inode() -
before the struct inode fields have been initialised from the obtained file
stats (ie. after v9fs_stat2inode*() has been called), but netfslib wants to
set a couple of its fields from i_size.

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
Tested-by: Dominique Martinet <asmadeus@codewreck.org>
Acked-by: Dominique Martinet <asmadeus@codewreck.org>
cc: Eric Van Hensbergen <ericvh@kernel.org>
cc: Latchesar Ionkov <lucho@ionkov.net>
cc: Dominique Martinet <asmadeus@codewreck.org>
cc: Christian Schoenebeck <linux_oss@crudebyte.com>
cc: v9fs@lists.linux.dev
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
---
 fs/9p/v9fs_vfs.h       | 1 +
 fs/9p/vfs_inode.c      | 6 +++---
 fs/9p/vfs_inode_dotl.c | 1 +
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 731e3d14b67d3..0e8418066a482 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -42,6 +42,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb);
 void v9fs_free_inode(struct inode *inode);
 struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode,
 			     dev_t rdev);
+void v9fs_set_netfs_context(struct inode *inode);
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
 		    struct inode *inode, umode_t mode, dev_t rdev);
 void v9fs_evict_inode(struct inode *inode);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b66466e97459c..32572982f72e6 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -246,7 +246,7 @@ void v9fs_free_inode(struct inode *inode)
 /*
  * Set parameters for the netfs library
  */
-static void v9fs_set_netfs_context(struct inode *inode)
+void v9fs_set_netfs_context(struct inode *inode)
 {
 	struct v9fs_inode *v9inode = V9FS_I(inode);
 	netfs_inode_init(&v9inode->netfs, &v9fs_req_ops, true);
@@ -326,8 +326,6 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses,
 		err = -EINVAL;
 		goto error;
 	}
-
-	v9fs_set_netfs_context(inode);
 error:
 	return err;
 
@@ -359,6 +357,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev)
 		iput(inode);
 		return ERR_PTR(err);
 	}
+	v9fs_set_netfs_context(inode);
 	return inode;
 }
 
@@ -461,6 +460,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
 		goto error;
 
 	v9fs_stat2inode(st, inode, sb, 0);
+	v9fs_set_netfs_context(inode);
 	v9fs_cache_inode_get_cookie(inode);
 	unlock_new_inode(inode);
 	return inode;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index e25fbc988f095..3505227e17040 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -128,6 +128,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
 		goto error;
 
 	v9fs_stat2inode_dotl(st, inode, 0);
+	v9fs_set_netfs_context(inode);
 	v9fs_cache_inode_get_cookie(inode);
 	retval = v9fs_get_acl(inode, fid);
 	if (retval)
-- 
GitLab


From ef184b8844bf98a2a80fab8eecda1489aed5d97f Mon Sep 17 00:00:00 2001
From: Guixin Liu <kanie@linux.alibaba.com>
Date: Sun, 31 Dec 2023 14:56:44 +0800
Subject: [PATCH 2056/4076] nvme: tcp: remove unnecessary goto statement

There is no requirement to call nvme_tcp_free_queue() for queue
deallocation if the pskid is null or the queue allocation fails, as
the NVME_TCP_Q_ALLOCATED flag would not be set in such scenarios.

Signed-off-by: Guixin Liu <kanie@linux.alibaba.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d79811cfa0ce8..5056bcae2f391 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1922,14 +1922,13 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 						      ctrl->opts->subsysnqn);
 		if (!pskid) {
 			dev_err(ctrl->device, "no valid PSK found\n");
-			ret = -ENOKEY;
-			goto out_free_queue;
+			return -ENOKEY;
 		}
 	}
 
 	ret = nvme_tcp_alloc_queue(ctrl, 0, pskid);
 	if (ret)
-		goto out_free_queue;
+		return ret;
 
 	ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl));
 	if (ret)
-- 
GitLab


From 2ad28ce9b98f8b22feaecc0966c706a8ef59cbf0 Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <mgurtovoy@nvidia.com>
Date: Mon, 1 Jan 2024 12:35:27 +0200
Subject: [PATCH 2057/4076] nvme: remove unused definition

There is no users for NVMF_AUTH_HASH_LEN macro.

Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/nvme.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 44325c068b6a0..462c21e0e4176 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -20,7 +20,6 @@
 #define NVMF_TRSVCID_SIZE	32
 #define NVMF_TRADDR_SIZE	256
 #define NVMF_TSAS_SIZE		256
-#define NVMF_AUTH_HASH_LEN	64
 
 #define NVME_DISC_SUBSYS_NAME	"nqn.2014-08.org.nvmexpress.discovery"
 
-- 
GitLab


From 2abd2c39ada8200ca5f02d483dccfa82799f51a7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 26 Dec 2023 08:14:12 +0000
Subject: [PATCH 2058/4076] nvme-common: mark nvme_tls_psk_prio static

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/common/keyring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c
index ee341b83eebaf..a5c0431c101cf 100644
--- a/drivers/nvme/common/keyring.c
+++ b/drivers/nvme/common/keyring.c
@@ -111,7 +111,7 @@ static struct key *nvme_tls_psk_lookup(struct key *keyring,
  * should be preferred to 'generated' PSKs,
  * and SHA-384 should be preferred to SHA-256.
  */
-struct nvme_tls_psk_priority_list {
+static struct nvme_tls_psk_priority_list {
 	bool generated;
 	enum nvme_tcp_tls_cipher cipher;
 } nvme_tls_psk_prio[] = {
-- 
GitLab


From 3a96bff229d6e3016805fd6c3dba0655ccba01eb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 26 Dec 2023 08:13:29 +0000
Subject: [PATCH 2059/4076] nvmet-tcp: fix a missing endianess conversion in
 nvmet_tcp_try_peek_pdu

No, a __le32 cast doesn't magically byteswap on big-endian systems..

Fixes: 70525e5d82f6 ("nvmet-tcp: peek icreq before starting TLS")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 3569c1255c5eb..792828fb91ccf 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1778,7 +1778,7 @@ static int nvmet_tcp_try_peek_pdu(struct nvmet_tcp_queue *queue)
 		 (int)sizeof(struct nvme_tcp_icreq_pdu));
 	if (hdr->type == nvme_tcp_icreq &&
 	    hdr->hlen == sizeof(struct nvme_tcp_icreq_pdu) &&
-	    hdr->plen == (__le32)sizeof(struct nvme_tcp_icreq_pdu)) {
+	    hdr->plen == cpu_to_le32(sizeof(struct nvme_tcp_icreq_pdu))) {
 		pr_debug("queue %d: icreq detected\n",
 			 queue->idx);
 		return len;
-- 
GitLab


From d3074e9a73e3c0511f1033b15345e2feb9664b3c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 26 Dec 2023 08:58:41 +0000
Subject: [PATCH 2060/4076] nvme: update the explanation for not updating the
 limits in nvme_config_discard

Expeand the comment a bit to explain what is going on.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d144d1acb09a0..56107cfc97b7b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1743,7 +1743,13 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 
 	queue->limits.discard_granularity = size;
 
-	/* If discard is already enabled, don't reset queue limits */
+	/*
+	 * If discard is already enabled, don't reset queue limits.
+	 *
+	 * This works around the fact that the block layer can't cope well with
+	 * updating the hardware limits when overridden through sysfs.  This is
+	 * harmless because discard limits in NVMe are purely advisory.
+	 */
 	if (queue->limits.max_discard_sectors)
 		return;
 
-- 
GitLab


From a4be9679aa3e862adcab465122c7678c2b5d40e6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 26 Dec 2023 08:58:42 +0000
Subject: [PATCH 2061/4076] nvme: also skip discard granularity updates in
 nvme_config_discard

Don't just skip the discard sectors and segments but also the granularity
if a value was already set before.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 56107cfc97b7b..6c52b0ab382c8 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1727,7 +1727,6 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 		struct nvme_ns_head *head)
 {
 	struct request_queue *queue = disk->queue;
-	u32 size = queue_logical_block_size(queue);
 
 	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX))
 		ctrl->max_discard_sectors =
@@ -1741,8 +1740,6 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	queue->limits.discard_granularity = size;
-
 	/*
 	 * If discard is already enabled, don't reset queue limits.
 	 *
@@ -1755,6 +1752,7 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 
 	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
 	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
+	queue->limits.discard_granularity = queue_logical_block_size(queue);
 
 	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
-- 
GitLab


From f29886c249ec2ed566e423fd02f6071b8f0a3346 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 26 Dec 2023 08:58:43 +0000
Subject: [PATCH 2062/4076] nvme: fix max_discard_sectors calculation

ctrl->max_discard_sectors stores a value that is potentially based of
the DMRSL field in Identify Controller, which is in units of LBAs and
thus dependent on the Format of a namespace.

Fix this by moving the calculation of max_discard_sectors entirely
into nvme_config_discard and replacing the ctrl->max_discard_sectors
value with a local variable so that the calculation is always
namespace-specific.

Fixes: 1a86924e4f46 ("nvme: fix interpretation of DMRSL")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 20 +++++++++-----------
 drivers/nvme/host/nvme.h |  1 -
 2 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 6c52b0ab382c8..86b9a1c4876f5 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1727,12 +1727,13 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 		struct nvme_ns_head *head)
 {
 	struct request_queue *queue = disk->queue;
+	u32 max_discard_sectors;
 
-	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX))
-		ctrl->max_discard_sectors =
-			nvme_lba_to_sect(head, ctrl->dmrsl);
-
-	if (ctrl->max_discard_sectors == 0) {
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) {
+		max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl);
+	} else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
+		max_discard_sectors = UINT_MAX;
+	} else {
 		blk_queue_max_discard_sectors(queue, 0);
 		return;
 	}
@@ -1750,7 +1751,7 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 	if (queue->limits.max_discard_sectors)
 		return;
 
-	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
+	blk_queue_max_discard_sectors(queue, max_discard_sectors);
 	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
 	queue->limits.discard_granularity = queue_logical_block_size(queue);
 
@@ -2911,13 +2912,10 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	struct nvme_id_ctrl_nvm *id;
 	int ret;
 
-	if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
-		ctrl->max_discard_sectors = UINT_MAX;
+	if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
 		ctrl->max_discard_segments = NVME_DSM_MAX_RANGES;
-	} else {
-		ctrl->max_discard_sectors = 0;
+	else
 		ctrl->max_discard_segments = 0;
-	}
 
 	/*
 	 * Even though NVMe spec explicitly states that MDTS is not applicable
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 3dbd187896d8d..9a698c49ea036 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -297,7 +297,6 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
-	u32 max_discard_sectors;
 	u32 max_discard_segments;
 	u32 max_zeroes_sectors;
 #ifdef CONFIG_BLK_DEV_ZONED
-- 
GitLab


From 3b946fe1cc149b23dad3a233c77b1475834f4d6f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 26 Dec 2023 08:58:44 +0000
Subject: [PATCH 2063/4076] nvme: simplify the max_discard_segments calculation

Just stash away the DMRL value in the nvme_ctrl struture, and leave
all interpretation to nvme_config_discard, where we know DSM is
supported by the time we're configuring the number of segments.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 13 +++++--------
 drivers/nvme/host/nvme.h |  2 +-
 2 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 86b9a1c4876f5..50818dbcfa1ae 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1752,7 +1752,10 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 		return;
 
 	blk_queue_max_discard_sectors(queue, max_discard_sectors);
-	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
+	if (ctrl->dmrl)
+		blk_queue_max_discard_segments(queue, ctrl->dmrl);
+	else
+		blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
 	queue->limits.discard_granularity = queue_logical_block_size(queue);
 
 	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
@@ -2912,11 +2915,6 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	struct nvme_id_ctrl_nvm *id;
 	int ret;
 
-	if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
-		ctrl->max_discard_segments = NVME_DSM_MAX_RANGES;
-	else
-		ctrl->max_discard_segments = 0;
-
 	/*
 	 * Even though NVMe spec explicitly states that MDTS is not applicable
 	 * to the write-zeroes, we are cautious and limit the size to the
@@ -2946,8 +2944,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	if (ret)
 		goto free_data;
 
-	if (id->dmrl)
-		ctrl->max_discard_segments = id->dmrl;
+	ctrl->dmrl = id->dmrl;
 	ctrl->dmrsl = le32_to_cpu(id->dmrsl);
 	if (id->wzsl)
 		ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 9a698c49ea036..297b80430f1b6 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -297,13 +297,13 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
-	u32 max_discard_segments;
 	u32 max_zeroes_sectors;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u32 max_zone_append;
 #endif
 	u16 crdt[3];
 	u16 oncs;
+	u8 dmrl;
 	u32 dmrsl;
 	u16 oacs;
 	u16 sqsize;
-- 
GitLab


From 72e8c9379dbef2662c2479c3d142e4c44d598a5b Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Mon, 18 Dec 2023 16:30:50 +0100
Subject: [PATCH 2064/4076] nvmet-fc: remove unnecessary bracket

There is no need for the bracket around the identifier. Remove it.

Signed-off-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index bd59990b52501..bda7a3009e851 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1031,7 +1031,7 @@ nvmet_fc_match_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	list_for_each_entry(host, &tgtport->host_list, host_list) {
 		if (host->hosthandle == hosthandle && !host->invalid) {
 			if (nvmet_fc_hostport_get(host))
-				return (host);
+				return host;
 		}
 	}
 
-- 
GitLab


From 0e716cec6fb11a14c220ee17c404b67962e902f7 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Mon, 18 Dec 2023 16:30:51 +0100
Subject: [PATCH 2065/4076] nvmet-trace: avoid dereferencing pointer too early

The first command issued from the host to the target is the fabrics
connect command. At this point, neither the target queue nor the
controller have been allocated. But we already try to trace this command
in nvmet_req_init.

Reported by KASAN.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/trace.c |  6 +++---
 drivers/nvme/target/trace.h | 28 +++++++++++++++++-----------
 2 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c
index bff454d46255b..6ee1f3db81d04 100644
--- a/drivers/nvme/target/trace.c
+++ b/drivers/nvme/target/trace.c
@@ -211,7 +211,7 @@ const char *nvmet_trace_disk_name(struct trace_seq *p, char *name)
 	return ret;
 }
 
-const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl)
+const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
 
@@ -224,8 +224,8 @@ const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl)
 	 * If we can know the extra data of the connect command in this stage,
 	 * we can update this print statement later.
 	 */
-	if (ctrl)
-		trace_seq_printf(p, "%d", ctrl->cntlid);
+	if (ctrl_id)
+		trace_seq_printf(p, "%d", ctrl_id);
 	else
 		trace_seq_printf(p, "_");
 	trace_seq_putc(p, 0);
diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h
index 6109b3806b12b..2f15070ddc569 100644
--- a/drivers/nvme/target/trace.h
+++ b/drivers/nvme/target/trace.h
@@ -32,18 +32,24 @@ const char *nvmet_trace_parse_fabrics_cmd(struct trace_seq *p, u8 fctype,
 	 nvmet_trace_parse_nvm_cmd(p, opcode, cdw10) :			\
 	 nvmet_trace_parse_admin_cmd(p, opcode, cdw10)))
 
-const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl);
-#define __print_ctrl_name(ctrl)				\
-	nvmet_trace_ctrl_name(p, ctrl)
+const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id);
+#define __print_ctrl_id(ctrl_id)			\
+	nvmet_trace_ctrl_id(p, ctrl_id)
 
 const char *nvmet_trace_disk_name(struct trace_seq *p, char *name);
 #define __print_disk_name(name)				\
 	nvmet_trace_disk_name(p, name)
 
 #ifndef TRACE_HEADER_MULTI_READ
-static inline struct nvmet_ctrl *nvmet_req_to_ctrl(struct nvmet_req *req)
+static inline u16 nvmet_req_to_ctrl_id(struct nvmet_req *req)
 {
-	return req->sq->ctrl;
+	/*
+	 * The queue and controller pointers are not valid until an association
+	 * has been established.
+	 */
+	if (!req->sq || !req->sq->ctrl)
+		return 0;
+	return req->sq->ctrl->cntlid;
 }
 
 static inline void __assign_req_name(char *name, struct nvmet_req *req)
@@ -63,7 +69,7 @@ TRACE_EVENT(nvmet_req_init,
 	TP_ARGS(req, cmd),
 	TP_STRUCT__entry(
 		__field(struct nvme_command *, cmd)
-		__field(struct nvmet_ctrl *, ctrl)
+		__field(u16, ctrl_id)
 		__array(char, disk, DISK_NAME_LEN)
 		__field(int, qid)
 		__field(u16, cid)
@@ -76,7 +82,7 @@ TRACE_EVENT(nvmet_req_init,
 	),
 	TP_fast_assign(
 		__entry->cmd = cmd;
-		__entry->ctrl = nvmet_req_to_ctrl(req);
+		__entry->ctrl_id = nvmet_req_to_ctrl_id(req);
 		__assign_req_name(__entry->disk, req);
 		__entry->qid = req->sq->qid;
 		__entry->cid = cmd->common.command_id;
@@ -90,7 +96,7 @@ TRACE_EVENT(nvmet_req_init,
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, "
 		  "meta=%#llx, cmd=(%s, %s)",
-		__print_ctrl_name(__entry->ctrl),
+		__print_ctrl_id(__entry->ctrl_id),
 		__print_disk_name(__entry->disk),
 		__entry->qid, __entry->cid, __entry->nsid,
 		__entry->flags, __entry->metadata,
@@ -104,7 +110,7 @@ TRACE_EVENT(nvmet_req_complete,
 	TP_PROTO(struct nvmet_req *req),
 	TP_ARGS(req),
 	TP_STRUCT__entry(
-		__field(struct nvmet_ctrl *, ctrl)
+		__field(u16, ctrl_id)
 		__array(char, disk, DISK_NAME_LEN)
 		__field(int, qid)
 		__field(int, cid)
@@ -112,7 +118,7 @@ TRACE_EVENT(nvmet_req_complete,
 		__field(u16, status)
 	),
 	TP_fast_assign(
-		__entry->ctrl = nvmet_req_to_ctrl(req);
+		__entry->ctrl_id = nvmet_req_to_ctrl_id(req);
 		__entry->qid = req->cq->qid;
 		__entry->cid = req->cqe->command_id;
 		__entry->result = le64_to_cpu(req->cqe->result.u64);
@@ -120,7 +126,7 @@ TRACE_EVENT(nvmet_req_complete,
 		__assign_req_name(__entry->disk, req);
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x",
-		__print_ctrl_name(__entry->ctrl),
+		__print_ctrl_id(__entry->ctrl_id),
 		__print_disk_name(__entry->disk),
 		__entry->qid, __entry->cid, __entry->result, __entry->status)
 
-- 
GitLab


From 1af5aa82c976753e93eb52b72784e586a7d2844b Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 27 Nov 2023 20:59:04 +0300
Subject: [PATCH 2066/4076] apparmor: free the allocated pdb objects

policy_db objects are allocated with kzalloc() inside aa_alloc_pdb() and
are not cleared in the corresponding aa_free_pdb() function causing leak:

unreferenced object 0xffff88801f0a1400 (size 192):
  comm "apparmor_parser", pid 1247, jiffies 4295122827 (age 2306.399s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff81ddc612>] __kmem_cache_alloc_node+0x1e2/0x2d0
    [<ffffffff81c47c55>] kmalloc_trace+0x25/0xc0
    [<ffffffff83eb9a12>] aa_alloc_pdb+0x82/0x140
    [<ffffffff83ec4077>] unpack_pdb+0xc7/0x2700
    [<ffffffff83ec6b10>] unpack_profile+0x450/0x4960
    [<ffffffff83ecc129>] aa_unpack+0x309/0x15e0
    [<ffffffff83ebdb23>] aa_replace_profiles+0x213/0x33c0
    [<ffffffff83e8d341>] policy_update+0x261/0x370
    [<ffffffff83e8d66e>] profile_replace+0x20e/0x2a0
    [<ffffffff81eadfaf>] vfs_write+0x2af/0xe00
    [<ffffffff81eaf4c6>] ksys_write+0x126/0x250
    [<ffffffff890fa0b6>] do_syscall_64+0x46/0xf0
    [<ffffffff892000ea>] entry_SYSCALL_64_after_hwframe+0x6e/0x76

Free the pdbs inside aa_free_pdb(). While at it, rename the variable
representing an aa_policydb object to make the function more unified with
aa_pdb_free_kref() and aa_alloc_pdb().

Found by Linux Verification Center (linuxtesting.org).

Fixes: 98b824ff8984 ("apparmor: refcount the pdb")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index ed4c9803c8fad..957654d253dd7 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -99,13 +99,14 @@ const char *const aa_profile_mode_names[] = {
 };
 
 
-static void aa_free_pdb(struct aa_policydb *policy)
+static void aa_free_pdb(struct aa_policydb *pdb)
 {
-	if (policy) {
-		aa_put_dfa(policy->dfa);
-		if (policy->perms)
-			kvfree(policy->perms);
-		aa_free_str_table(&policy->trans);
+	if (pdb) {
+		aa_put_dfa(pdb->dfa);
+		if (pdb->perms)
+			kvfree(pdb->perms);
+		aa_free_str_table(&pdb->trans);
+		kfree(pdb);
 	}
 }
 
-- 
GitLab


From 9c51f8788b5d4e9f46afbcf563255cfd355690b3 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 17:46:55 -0800
Subject: [PATCH 2067/4076] perf env: Avoid recursively taking
 env->bpf_progs.lock

Add variants of perf_env__insert_bpf_prog_info(), perf_env__insert_btf()
and perf_env__find_btf prefixed with __ to indicate the
env->bpf_progs.lock is assumed held.

Call these variants when the lock is held to avoid recursively taking it
and potentially having a thread deadlock with itself.

Fixes: f8dfeae009effc0b ("perf bpf: Show more BPF program info in print_bpf_prog_info()")
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Song Liu <song@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20231207014655.1252484-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf-event.c |  8 +++---
 tools/perf/util/bpf-event.h | 12 ++++-----
 tools/perf/util/env.c       | 50 ++++++++++++++++++++++++-------------
 tools/perf/util/env.h       |  4 +++
 tools/perf/util/header.c    |  8 +++---
 5 files changed, 50 insertions(+), 32 deletions(-)

diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 830711cae30d3..3573e0b7ef3ed 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -545,9 +545,9 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 	return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
 }
 
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp)
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp)
 {
 	__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
 	__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
@@ -563,7 +563,7 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
 	if (info->btf_id) {
 		struct btf_node *node;
 
-		node = perf_env__find_btf(env, info->btf_id);
+		node = __perf_env__find_btf(env, info->btf_id);
 		if (node)
 			btf = btf__new((__u8 *)(node->data),
 				       node->data_size);
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 1bcbd4fb6c669..e2f0420905f59 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -33,9 +33,9 @@ struct btf_node {
 int machine__process_bpf(struct machine *machine, union perf_event *event,
 			 struct perf_sample *sample);
 int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env);
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp);
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp);
 #else
 static inline int machine__process_bpf(struct machine *machine __maybe_unused,
 				       union perf_event *event __maybe_unused,
@@ -50,9 +50,9 @@ static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,
 	return 0;
 }
 
-static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
-						  struct perf_env *env __maybe_unused,
-						  FILE *fp __maybe_unused)
+static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+						    struct perf_env *env __maybe_unused,
+						    FILE *fp __maybe_unused)
 {
 
 }
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index c68b7a004f294..a459374d0a1a1 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -24,13 +24,19 @@ struct perf_env perf_env;
 
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node)
+{
+	down_write(&env->bpf_progs.lock);
+	__perf_env__insert_bpf_prog_info(env, info_node);
+	up_write(&env->bpf_progs.lock);
+}
+
+void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node)
 {
 	__u32 prog_id = info_node->info_linear->info.id;
 	struct bpf_prog_info_node *node;
 	struct rb_node *parent = NULL;
 	struct rb_node **p;
 
-	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.infos.rb_node;
 
 	while (*p != NULL) {
@@ -42,15 +48,13 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env,
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated bpf prog info %u\n", prog_id);
-			goto out;
+			return;
 		}
 	}
 
 	rb_link_node(&info_node->rb_node, parent, p);
 	rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
 	env->bpf_progs.infos_cnt++;
-out:
-	up_write(&env->bpf_progs.lock);
 }
 
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
@@ -79,14 +83,22 @@ out:
 }
 
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
+{
+	bool ret;
+
+	down_write(&env->bpf_progs.lock);
+	ret = __perf_env__insert_btf(env, btf_node);
+	up_write(&env->bpf_progs.lock);
+	return ret;
+}
+
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 {
 	struct rb_node *parent = NULL;
 	__u32 btf_id = btf_node->id;
 	struct btf_node *node;
 	struct rb_node **p;
-	bool ret = true;
 
-	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.btfs.rb_node;
 
 	while (*p != NULL) {
@@ -98,25 +110,31 @@ bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated btf %u\n", btf_id);
-			ret = false;
-			goto out;
+			return false;
 		}
 	}
 
 	rb_link_node(&btf_node->rb_node, parent, p);
 	rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs);
 	env->bpf_progs.btfs_cnt++;
-out:
-	up_write(&env->bpf_progs.lock);
-	return ret;
+	return true;
 }
 
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
+{
+	struct btf_node *res;
+
+	down_read(&env->bpf_progs.lock);
+	res = __perf_env__find_btf(env, btf_id);
+	up_read(&env->bpf_progs.lock);
+	return res;
+}
+
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 {
 	struct btf_node *node = NULL;
 	struct rb_node *n;
 
-	down_read(&env->bpf_progs.lock);
 	n = env->bpf_progs.btfs.rb_node;
 
 	while (n) {
@@ -126,13 +144,9 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 		else if (btf_id > node->id)
 			n = n->rb_right;
 		else
-			goto out;
+			return node;
 	}
-	node = NULL;
-
-out:
-	up_read(&env->bpf_progs.lock);
-	return node;
+	return NULL;
 }
 
 /* purge data in bpf_progs.infos tree */
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index bf7e3c4c211f9..7c527e65c1864 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -175,12 +175,16 @@ const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
 
 void perf_env__init(struct perf_env *env);
+void __perf_env__insert_bpf_prog_info(struct perf_env *env,
+				      struct bpf_prog_info_node *info_node);
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node);
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 							__u32 prog_id);
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 
 int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a9f71f8343f08..3fe28edc3d017 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1849,8 +1849,8 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
 		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
 		next = rb_next(&node->rb_node);
 
-		bpf_event__print_bpf_prog_info(&node->info_linear->info,
-					       env, fp);
+		__bpf_event__print_bpf_prog_info(&node->info_linear->info,
+						 env, fp);
 	}
 
 	up_read(&env->bpf_progs.lock);
@@ -3188,7 +3188,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		/* after reading from file, translate offset to address */
 		bpil_offs_to_addr(info_linear);
 		info_node->info_linear = info_linear;
-		perf_env__insert_bpf_prog_info(env, info_node);
+		__perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
 	up_write(&env->bpf_progs.lock);
@@ -3235,7 +3235,7 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 		if (__do_read(ff, node->data, data_size))
 			goto out;
 
-		perf_env__insert_btf(env, node);
+		__perf_env__insert_btf(env, node);
 		node = NULL;
 	}
 
-- 
GitLab


From 7d1405c71df21f6c394b8a885aa8a133f749fa22 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 6 Dec 2023 18:16:27 -0800
Subject: [PATCH 2068/4076] perf record: Reduce memory for recording
 PERF_RECORD_LOST_SAMPLES event

Reduce from PERF_SAMPLE_MAX_SIZE to "sizeof(*lost) +
session->machines.host.id_hdr_size".

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231207021627.1322884-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a89013c44fd53..91e6828c38cc2 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1954,7 +1954,8 @@ static void record__read_lost_samples(struct record *rec)
 
 				if (count.lost) {
 					if (!lost) {
-						lost = zalloc(PERF_SAMPLE_MAX_SIZE);
+						lost = zalloc(sizeof(*lost) +
+							      session->machines.host.id_hdr_size);
 						if (!lost) {
 							pr_debug("Memory allocation failed\n");
 							return;
@@ -1970,7 +1971,8 @@ static void record__read_lost_samples(struct record *rec)
 		lost_count = perf_bpf_filter__lost_count(evsel);
 		if (lost_count) {
 			if (!lost) {
-				lost = zalloc(PERF_SAMPLE_MAX_SIZE);
+				lost = zalloc(sizeof(*lost) +
+					      session->machines.host.id_hdr_size);
 				if (!lost) {
 					pr_debug("Memory allocation failed\n");
 					return;
-- 
GitLab


From f2567e12a090f0eb22553a4468d4c4fe04aad906 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 11 Dec 2023 10:12:41 -0800
Subject: [PATCH 2069/4076] perf stat: Fix hard coded LL miss units

Copy-paste error where LL cache misses are reported as l1i.

Fixes: 0a57b910807ad163 ("perf stat: Use counts rather than saved_value")
Suggested-by: Guillaume Endignoux <guillaumee@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231211181242.1721059-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/stat-shadow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 1c5c3eeba4cfb..e31426167852a 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -264,7 +264,7 @@ static void print_ll_miss(struct perf_stat_config *config,
 	static const double color_ratios[3] = {20.0, 10.0, 5.0};
 
 	print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, color_ratios,
-		    "of all L1-icache accesses");
+		    "of all LL-cache accesses");
 }
 
 static void print_dtlb_miss(struct perf_stat_config *config,
-- 
GitLab


From 346878dacc81f53667381c8f4bb5018195ca10be Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan.das@amd.com>
Date: Wed, 29 Nov 2023 11:55:04 +0530
Subject: [PATCH 2070/4076] perf vendor events amd: Add Zen 4 memory controller
 events

Make the jevents parser aware of the Unified Memory Controller (UMC) PMU
and add events taken from Section 8.2.1 "UMC Performance Monitor Events"
of the Processor Programming Reference (PPR) for AMD Family 19h Model 11h
processors. The events capture UMC command activity such as CAS, ACTIVATE,
PRECHARGE etc. while the metrics derive data bus utilization and memory
bandwidth out of these events.

Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/e0d8a7e8ca8ee3e378d8029e80b456ac327d6419.1701238314.git.sandipan.das@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/x86/amdzen4/memory-controller.json   | 101 ++++++++++++++++++
 .../arch/x86/amdzen4/recommended.json         |  84 +++++++++++++++
 tools/perf/pmu-events/jevents.py              |   2 +
 3 files changed, 187 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/x86/amdzen4/memory-controller.json

diff --git a/tools/perf/pmu-events/arch/x86/amdzen4/memory-controller.json b/tools/perf/pmu-events/arch/x86/amdzen4/memory-controller.json
new file mode 100644
index 0000000000000..55263e5e4f69a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdzen4/memory-controller.json
@@ -0,0 +1,101 @@
+[
+  {
+    "EventName": "umc_mem_clk",
+    "PublicDescription": "Number of memory clock cycles.",
+    "EventCode": "0x00",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.all",
+    "PublicDescription": "Number of ACTIVATE commands sent.",
+    "EventCode": "0x05",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.rd",
+    "PublicDescription": "Number of ACTIVATE commands sent for reads.",
+    "EventCode": "0x05",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.wr",
+    "PublicDescription": "Number of ACTIVATE commands sent for writes.",
+    "EventCode": "0x05",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.all",
+    "PublicDescription": "Number of PRECHARGE commands sent.",
+    "EventCode": "0x06",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.rd",
+    "PublicDescription": "Number of PRECHARGE commands sent for reads.",
+    "EventCode": "0x06",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.wr",
+    "PublicDescription": "Number of PRECHARGE commands sent for writes.",
+    "EventCode": "0x06",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.all",
+    "PublicDescription": "Number of CAS commands sent.",
+    "EventCode": "0x0a",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.rd",
+    "PublicDescription": "Number of CAS commands sent for reads.",
+    "EventCode": "0x0a",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.wr",
+    "PublicDescription": "Number of CAS commands sent for writes.",
+    "EventCode": "0x0a",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.all",
+    "PublicDescription": "Number of clocks used by the data bus.",
+    "EventCode": "0x14",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.rd",
+    "PublicDescription": "Number of clocks used by the data bus for reads.",
+    "EventCode": "0x14",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.wr",
+    "PublicDescription": "Number of clocks used by the data bus for writes.",
+    "EventCode": "0x14",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/amdzen4/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen4/recommended.json
index 5e6a793acf7b2..96e06401c6cbb 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen4/recommended.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen4/recommended.json
@@ -330,5 +330,89 @@
     "MetricGroup": "data_fabric",
     "PerPkg": "1",
     "ScaleUnit": "6.103515625e-5MiB"
+  },
+  {
+    "MetricName": "umc_data_bus_utilization",
+    "BriefDescription": "Memory controller data bus utilization.",
+    "MetricExpr": "d_ratio(umc_data_slot_clks.all / 2, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "100%"
+  },
+  {
+    "MetricName": "umc_cas_cmd_rate",
+    "BriefDescription": "Memory controller CAS command rate.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.all * 1000, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1"
+  },
+  {
+    "MetricName": "umc_cas_cmd_read_ratio",
+    "BriefDescription": "Ratio of memory controller CAS commands for reads.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.rd, umc_cas_cmd.all)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "100%"
+  },
+  {
+    "MetricName": "umc_cas_cmd_write_ratio",
+    "BriefDescription": "Ratio of memory controller CAS commands for writes.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.wr, umc_cas_cmd.all)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "100%"
+  },
+  {
+    "MetricName": "umc_mem_read_bandwidth",
+    "BriefDescription": "Estimated memory read bandwidth.",
+    "MetricExpr": "(umc_cas_cmd.rd * 64) / 1e6 / duration_time",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "1MB/s"
+  },
+  {
+    "MetricName": "umc_mem_write_bandwidth",
+    "BriefDescription": "Estimated memory write bandwidth.",
+    "MetricExpr": "(umc_cas_cmd.wr * 64) / 1e6 / duration_time",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "1MB/s"
+  },
+  {
+    "MetricName": "umc_mem_bandwidth",
+    "BriefDescription": "Estimated combined memory bandwidth.",
+    "MetricExpr": "(umc_cas_cmd.all * 64) / 1e6 / duration_time",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "1MB/s"
+  },
+  {
+    "MetricName": "umc_cas_cmd_read_ratio",
+    "BriefDescription": "Ratio of memory controller CAS commands for reads.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.rd, umc_cas_cmd.all)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1",
+    "ScaleUnit": "100%"
+  },
+  {
+    "MetricName": "umc_cas_cmd_rate",
+    "BriefDescription": "Memory controller CAS command rate.",
+    "MetricExpr": "d_ratio(umc_cas_cmd.all * 1000, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1"
+  },
+  {
+    "MetricName": "umc_activate_cmd_rate",
+    "BriefDescription": "Memory controller ACTIVATE command rate.",
+    "MetricExpr": "d_ratio(umc_act_cmd.all * 1000, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1"
+  },
+  {
+    "MetricName": "umc_precharge_cmd_rate",
+    "BriefDescription": "Memory controller PRECHARGE command rate.",
+    "MetricExpr": "d_ratio(umc_pchg_cmd.all * 1000, umc_mem_clk)",
+    "MetricGroup": "memory_controller",
+    "PerPkg": "1"
   }
 ]
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 0093c998cb6e6..53ab050c8fa43 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -286,6 +286,7 @@ class JsonEvent:
           'imx8_ddr': 'imx8_ddr',
           'L3PMC': 'amd_l3',
           'DFPMC': 'amd_df',
+          'UMCPMC': 'amd_umc',
           'cpu_core': 'cpu_core',
           'cpu_atom': 'cpu_atom',
           'ali_drw': 'ali_drw',
@@ -354,6 +355,7 @@ class JsonEvent:
         ('SampleAfterValue', 'period='),
         ('UMask', 'umask='),
         ('NodeType', 'type='),
+        ('RdWrMask', 'rdwrmask='),
     ]
     for key, value in event_fields:
       if key in jd and jd[key] != '0':
-- 
GitLab


From eb00697b91646de22d6d9b4e6a5fadf4495fdf69 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 3 Jan 2024 09:01:58 -0800
Subject: [PATCH 2071/4076] perf x86 test: Update hybrid expectations

The legacy events cpu-cycles and instructions have sysfs event
equivalents on x86 (see /sys/devices/cpu_core/events).

As sysfs/JSON events are now higher in priority than legacy events this
causes the hybrid test expectations not to be met.

To fix this switch to legacy events that don't have sysfs versions,
namely cpu-cycles becomes cycles and instructions becomes branches.

Fixes: a24d9d9dc096fc0d ("perf parse-events: Make legacy events lower priority than sysfs/JSON")
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Closes: https://lore.kernel.org/lkml/ZYbm5L7tw7bdpDpE@kernel.org/
Link: https://lore.kernel.org/r/20240103170159.1435753-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/tests/hybrid.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tools/perf/arch/x86/tests/hybrid.c b/tools/perf/arch/x86/tests/hybrid.c
index eb152770f1485..05a5f81e81671 100644
--- a/tools/perf/arch/x86/tests/hybrid.c
+++ b/tools/perf/arch/x86/tests/hybrid.c
@@ -47,7 +47,7 @@ static int test__hybrid_hw_group_event(struct evlist *evlist)
 	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_INSTRUCTIONS));
 	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
 	return TEST_OK;
 }
@@ -102,7 +102,7 @@ static int test__hybrid_group_modifier1(struct evlist *evlist)
 	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
-	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_INSTRUCTIONS));
 	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
@@ -171,27 +171,27 @@ struct evlist_test {
 
 static const struct evlist_test test__hybrid_events[] = {
 	{
-		.name  = "cpu_core/cpu-cycles/",
+		.name  = "cpu_core/cycles/",
 		.check = test__hybrid_hw_event_with_pmu,
 		/* 0 */
 	},
 	{
-		.name  = "{cpu_core/cpu-cycles/,cpu_core/instructions/}",
+		.name  = "{cpu_core/cycles/,cpu_core/branches/}",
 		.check = test__hybrid_hw_group_event,
 		/* 1 */
 	},
 	{
-		.name  = "{cpu-clock,cpu_core/cpu-cycles/}",
+		.name  = "{cpu-clock,cpu_core/cycles/}",
 		.check = test__hybrid_sw_hw_group_event,
 		/* 2 */
 	},
 	{
-		.name  = "{cpu_core/cpu-cycles/,cpu-clock}",
+		.name  = "{cpu_core/cycles/,cpu-clock}",
 		.check = test__hybrid_hw_sw_group_event,
 		/* 3 */
 	},
 	{
-		.name  = "{cpu_core/cpu-cycles/k,cpu_core/instructions/u}",
+		.name  = "{cpu_core/cycles/k,cpu_core/branches/u}",
 		.check = test__hybrid_group_modifier1,
 		/* 4 */
 	},
-- 
GitLab


From ec5257d99e6894d65fae772ca43c53b3d6855115 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 3 Jan 2024 09:01:59 -0800
Subject: [PATCH 2072/4076] perf x86 test: Add hybrid test for conflicting
 legacy/sysfs event

The cpu-cycles event is both a legacy event and declared in
/sys/devices/cpu_core/events/cpu-cycles. The cycles event is a legacy
event but with no sysfs version.

Add a test that the sysfs version is preferred to the legacy for
cpu-cycles, while for cycles we use the legacy version.

Suggested-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240103170159.1435753-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/tests/hybrid.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tools/perf/arch/x86/tests/hybrid.c b/tools/perf/arch/x86/tests/hybrid.c
index 05a5f81e81671..40f5d17fedab6 100644
--- a/tools/perf/arch/x86/tests/hybrid.c
+++ b/tools/perf/arch/x86/tests/hybrid.c
@@ -163,6 +163,24 @@ static int test__checkevent_pmu(struct evlist *evlist)
 	return TEST_OK;
 }
 
+static int test__hybrid_hw_group_event_2(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == 0x3c);
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
 struct evlist_test {
 	const char *name;
 	bool (*valid)(void);
@@ -215,6 +233,11 @@ static const struct evlist_test test__hybrid_events[] = {
 		.check = test__hybrid_cache_event,
 		/* 8 */
 	},
+	{
+		.name  = "{cpu_core/cycles/,cpu_core/cpu-cycles/}",
+		.check = test__hybrid_hw_group_event_2,
+		/* 9 */
+	},
 };
 
 static int test_event(const struct evlist_test *e)
-- 
GitLab


From 6d0fc416c42a98b39a74151376928d577873941c Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:28 -0800
Subject: [PATCH 2073/4076] cxl/trace: Pass UUID explicitly to event traces

CXL CPER events are identified by the CPER Section Type GUID. The GUID
correlates with the CXL UUID for the event record. It turns out that a
CXL CPER record is a strict subset of the CXL event record, only the
UUID header field is chopped.

In order to unify handling between native and CPER flavors of CXL
events, prepare the code for the UUID to be passed in rather than
inferred from the record itself.

Later patches update the passed in record to only refer to the common
data between the formats.

Pass the UUID explicitly to each trace event to be able to remove the
UUID from the event structures.

Originally it was desirable to remove the UUID from the well known event
because the UUID value was redundant.  However, the trace API was
already in place.[1]

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/all/36f2d12934d64a278f2c0313cbd01abc@huawei.com [1]
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-1-1bb8a4ca2c7a@intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c  |  8 ++++----
 drivers/cxl/core/trace.h | 28 ++++++++++++++--------------
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 36270dcfb42ef..00f429c440dfe 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -870,19 +870,19 @@ static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 		struct cxl_event_gen_media *rec =
 				(struct cxl_event_gen_media *)record;
 
-		trace_cxl_general_media(cxlmd, type, rec);
+		trace_cxl_general_media(cxlmd, type, id, rec);
 	} else if (uuid_equal(id, &dram_event_uuid)) {
 		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
 
-		trace_cxl_dram(cxlmd, type, rec);
+		trace_cxl_dram(cxlmd, type, id, rec);
 	} else if (uuid_equal(id, &mem_mod_event_uuid)) {
 		struct cxl_event_mem_module *rec =
 				(struct cxl_event_mem_module *)record;
 
-		trace_cxl_memory_module(cxlmd, type, rec);
+		trace_cxl_memory_module(cxlmd, type, id, rec);
 	} else {
 		/* For unknown record types print just the header */
-		trace_cxl_generic_event(cxlmd, type, record);
+		trace_cxl_generic_event(cxlmd, type, id, record);
 	}
 }
 
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index a0b5819bc70b3..3da16026b8dbf 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -198,12 +198,12 @@ TRACE_EVENT(cxl_overflow,
 	__field(u8, hdr_length)					\
 	__field(u8, hdr_maint_op_class)
 
-#define CXL_EVT_TP_fast_assign(cxlmd, l, hdr)					\
+#define CXL_EVT_TP_fast_assign(cxlmd, l, uuid, hdr)				\
 	__assign_str(memdev, dev_name(&(cxlmd)->dev));				\
 	__assign_str(host, dev_name((cxlmd)->dev.parent));			\
 	__entry->log = (l);							\
 	__entry->serial = (cxlmd)->cxlds->serial;				\
-	memcpy(&__entry->hdr_uuid, &(hdr).id, sizeof(uuid_t));			\
+	memcpy(&__entry->hdr_uuid, (uuid), sizeof(uuid_t));			\
 	__entry->hdr_length = (hdr).length;					\
 	__entry->hdr_flags = get_unaligned_le24((hdr).flags);			\
 	__entry->hdr_handle = le16_to_cpu((hdr).handle);			\
@@ -225,9 +225,9 @@ TRACE_EVENT(cxl_overflow,
 TRACE_EVENT(cxl_generic_event,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 struct cxl_event_record_raw *rec),
+		 const uuid_t *uuid, struct cxl_event_record_raw *rec),
 
-	TP_ARGS(cxlmd, log, rec),
+	TP_ARGS(cxlmd, log, uuid, rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -235,7 +235,7 @@ TRACE_EVENT(cxl_generic_event,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, uuid, rec->hdr);
 		memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
 	),
 
@@ -315,9 +315,9 @@ TRACE_EVENT(cxl_generic_event,
 TRACE_EVENT(cxl_general_media,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 struct cxl_event_gen_media *rec),
+		 const uuid_t *uuid, struct cxl_event_gen_media *rec),
 
-	TP_ARGS(cxlmd, log, rec),
+	TP_ARGS(cxlmd, log, uuid, rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -336,7 +336,7 @@ TRACE_EVENT(cxl_general_media,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, uuid, rec->hdr);
 
 		/* General Media */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -398,9 +398,9 @@ TRACE_EVENT(cxl_general_media,
 TRACE_EVENT(cxl_dram,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 struct cxl_event_dram *rec),
+		 const uuid_t *uuid, struct cxl_event_dram *rec),
 
-	TP_ARGS(cxlmd, log, rec),
+	TP_ARGS(cxlmd, log, uuid, rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -422,7 +422,7 @@ TRACE_EVENT(cxl_dram,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, uuid, rec->hdr);
 
 		/* DRAM */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -547,9 +547,9 @@ TRACE_EVENT(cxl_dram,
 TRACE_EVENT(cxl_memory_module,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 struct cxl_event_mem_module *rec),
+		 const uuid_t *uuid, struct cxl_event_mem_module *rec),
 
-	TP_ARGS(cxlmd, log, rec),
+	TP_ARGS(cxlmd, log, uuid, rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -569,7 +569,7 @@ TRACE_EVENT(cxl_memory_module,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, uuid, rec->hdr);
 
 		/* Memory Module Event */
 		__entry->event_type = rec->event_type;
-- 
GitLab


From c7ad3dc3649730af483ee1e78be5d0362da25bfe Mon Sep 17 00:00:00 2001
From: Jim Harris <jim.harris@samsung.com>
Date: Fri, 3 Nov 2023 20:18:34 +0000
Subject: [PATCH 2074/4076] cxl/region: fix x9 interleave typo

CXL supports x3, x6 and x12 - not x9.

Fixes: 80d10a6cee050 ("cxl/region: Add interleave geometry attributes")
Signed-off-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Fan Ni <fan.ni@samsung.com>
Link: https://lore.kernel.org/r/169904271254.204936.8580772404462743630.stgit@ubuntu
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/region.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 3e817a6f94c6a..76fec47a13a4c 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -397,7 +397,7 @@ static ssize_t interleave_ways_store(struct device *dev,
 		return rc;
 
 	/*
-	 * Even for x3, x9, and x12 interleaves the region interleave must be a
+	 * Even for x3, x6, and x12 interleaves the region interleave must be a
 	 * power of 2 multiple of the host bridge interleave.
 	 */
 	if (!is_power_of_2(val / cxld->interleave_ways) ||
-- 
GitLab


From b0f7e2d739b4aac131ea1662d086a07775097b05 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 3 Jan 2024 20:52:48 -0500
Subject: [PATCH 2075/4076] eventfs: Remove "lookup" parameter from
 create_dir/file_dentry()

The "lookup" parameter is a way to differentiate the call to
create_file/dir_dentry() from when it's just a lookup (no need to up the
dentry refcount) and accessed via a readdir (need to up the refcount).

But reality, it just makes the code more complex. Just up the refcount and
let the caller decide to dput() the result or not.

Link: https://lore.kernel.org/linux-trace-kernel/20240103102553.17a19cea@gandalf.local.home
Link: https://lore.kernel.org/linux-trace-kernel/20240104015435.517502710@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ajay Kaher <akaher@vmware.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 55 +++++++++++++++-------------------------
 1 file changed, 20 insertions(+), 35 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index f0677ea0ec24e..c360300fb866e 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -390,16 +390,14 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
  * @mode: The mode of the file.
  * @data: The data to use to set the inode of the file with on open()
  * @fops: The fops of the file to be created.
- * @lookup: If called by the lookup routine, in which case, dput() the created dentry.
  *
  * Create a dentry for a file of an eventfs_inode @ei and place it into the
- * address located at @e_dentry. If the @e_dentry already has a dentry, then
- * just do a dget() on it and return. Otherwise create the dentry and attach it.
+ * address located at @e_dentry.
  */
 static struct dentry *
 create_file_dentry(struct eventfs_inode *ei, int idx,
 		   struct dentry *parent, const char *name, umode_t mode, void *data,
-		   const struct file_operations *fops, bool lookup)
+		   const struct file_operations *fops)
 {
 	struct eventfs_attr *attr = NULL;
 	struct dentry **e_dentry = &ei->d_children[idx];
@@ -414,9 +412,7 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 	}
 	/* If the e_dentry already has a dentry, use it */
 	if (*e_dentry) {
-		/* lookup does not need to up the ref count */
-		if (!lookup)
-			dget(*e_dentry);
+		dget(*e_dentry);
 		mutex_unlock(&eventfs_mutex);
 		return *e_dentry;
 	}
@@ -441,13 +437,12 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 		 * way to being freed, don't return it. If e_dentry is NULL
 		 * it means it was already freed.
 		 */
-		if (ei->is_freed)
+		if (ei->is_freed) {
 			dentry = NULL;
-		else
+		} else {
 			dentry = *e_dentry;
-		/* The lookup does not need to up the dentry refcount */
-		if (dentry && !lookup)
 			dget(dentry);
+		}
 		mutex_unlock(&eventfs_mutex);
 		return dentry;
 	}
@@ -465,9 +460,6 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 	}
 	mutex_unlock(&eventfs_mutex);
 
-	if (lookup)
-		dput(dentry);
-
 	return dentry;
 }
 
@@ -500,13 +492,12 @@ static void eventfs_post_create_dir(struct eventfs_inode *ei)
  * @pei: The eventfs_inode parent of ei.
  * @ei: The eventfs_inode to create the directory for
  * @parent: The dentry of the parent of this directory
- * @lookup: True if this is called by the lookup code
  *
  * This creates and attaches a directory dentry to the eventfs_inode @ei.
  */
 static struct dentry *
 create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
-		  struct dentry *parent, bool lookup)
+		  struct dentry *parent)
 {
 	struct dentry *dentry = NULL;
 
@@ -518,11 +509,9 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 		return NULL;
 	}
 	if (ei->dentry) {
-		/* If the dentry already has a dentry, use it */
+		/* If the eventfs_inode already has a dentry, use it */
 		dentry = ei->dentry;
-		/* lookup does not need to up the ref count */
-		if (!lookup)
-			dget(dentry);
+		dget(dentry);
 		mutex_unlock(&eventfs_mutex);
 		return dentry;
 	}
@@ -542,7 +531,7 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 		 * way to being freed.
 		 */
 		dentry = ei->dentry;
-		if (dentry && !lookup)
+		if (dentry)
 			dget(dentry);
 		mutex_unlock(&eventfs_mutex);
 		return dentry;
@@ -562,9 +551,6 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 	}
 	mutex_unlock(&eventfs_mutex);
 
-	if (lookup)
-		dput(dentry);
-
 	return dentry;
 }
 
@@ -589,8 +575,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 	struct eventfs_inode *ei;
 	struct dentry *ei_dentry = NULL;
 	struct dentry *ret = NULL;
+	struct dentry *d;
 	const char *name = dentry->d_name.name;
-	bool created = false;
 	umode_t mode;
 	void *data;
 	int idx;
@@ -626,13 +612,10 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 		ret = simple_lookup(dir, dentry, flags);
 		if (IS_ERR(ret))
 			goto out;
-		create_dir_dentry(ei, ei_child, ei_dentry, true);
-		created = true;
-		break;
-	}
-
-	if (created)
+		d = create_dir_dentry(ei, ei_child, ei_dentry);
+		dput(d);
 		goto out;
+	}
 
 	for (i = 0; i < ei->nr_entries; i++) {
 		entry = &ei->entries[i];
@@ -650,8 +633,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 			ret = simple_lookup(dir, dentry, flags);
 			if (IS_ERR(ret))
 				goto out;
-			create_file_dentry(ei, i, ei_dentry, name, mode, cdata,
-					   fops, true);
+			d = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
+			dput(d);
 			break;
 		}
 	}
@@ -768,9 +751,10 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 	inode_lock(parent->d_inode);
 	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
-		d = create_dir_dentry(ei, ei_child, parent, false);
+		d = create_dir_dentry(ei, ei_child, parent);
 		if (d) {
 			ret = add_dentries(&dentries, d, cnt);
+			dput(d);
 			if (ret < 0)
 				break;
 			cnt++;
@@ -790,9 +774,10 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 		mutex_unlock(&eventfs_mutex);
 		if (r <= 0)
 			continue;
-		d = create_file_dentry(ei, i, parent, name, mode, cdata, fops, false);
+		d = create_file_dentry(ei, i, parent, name, mode, cdata, fops);
 		if (d) {
 			ret = add_dentries(&dentries, d, cnt);
+			dput(d);
 			if (ret < 0)
 				break;
 			cnt++;
-- 
GitLab


From 493ec81a8fb8e4ada6f223b8b73791a1280d4774 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 3 Jan 2024 20:52:49 -0500
Subject: [PATCH 2076/4076] eventfs: Stop using dcache_readdir() for getdents()

The eventfs creates dynamically allocated dentries and inodes. Using the
dcache_readdir() logic for its own directory lookups requires hiding the
cursor of the dcache logic and playing games to allow the dcache_readdir()
to still have access to the cursor while the eventfs saved what it created
and what it needs to release.

Instead, just have eventfs have its own iterate_shared callback function
that will fill in the dent entries. This simplifies the code quite a bit.

Link: https://lore.kernel.org/linux-trace-kernel/20240104015435.682218477@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ajay Kaher <akaher@vmware.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 194 +++++++++++++--------------------------
 1 file changed, 64 insertions(+), 130 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index c360300fb866e..41af56f44f0a0 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -52,9 +52,7 @@ enum {
 static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags);
-static int dcache_dir_open_wrapper(struct inode *inode, struct file *file);
-static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx);
-static int eventfs_release(struct inode *inode, struct file *file);
+static int eventfs_iterate(struct file *file, struct dir_context *ctx);
 
 static void update_attr(struct eventfs_attr *attr, struct iattr *iattr)
 {
@@ -148,11 +146,9 @@ static const struct inode_operations eventfs_file_inode_operations = {
 };
 
 static const struct file_operations eventfs_file_operations = {
-	.open		= dcache_dir_open_wrapper,
 	.read		= generic_read_dir,
-	.iterate_shared	= dcache_readdir_wrapper,
+	.iterate_shared	= eventfs_iterate,
 	.llseek		= generic_file_llseek,
-	.release	= eventfs_release,
 };
 
 /* Return the evenfs_inode of the "events" directory */
@@ -643,128 +639,87 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 	return ret;
 }
 
-struct dentry_list {
-	void			*cursor;
-	struct dentry		**dentries;
-};
-
-/**
- * eventfs_release - called to release eventfs file/dir
- * @inode: inode to be released
- * @file: file to be released (not used)
- */
-static int eventfs_release(struct inode *inode, struct file *file)
-{
-	struct tracefs_inode *ti;
-	struct dentry_list *dlist = file->private_data;
-	void *cursor;
-	int i;
-
-	ti = get_tracefs(inode);
-	if (!(ti->flags & TRACEFS_EVENT_INODE))
-		return -EINVAL;
-
-	if (WARN_ON_ONCE(!dlist))
-		return -EINVAL;
-
-	for (i = 0; dlist->dentries && dlist->dentries[i]; i++) {
-		dput(dlist->dentries[i]);
-	}
-
-	cursor = dlist->cursor;
-	kfree(dlist->dentries);
-	kfree(dlist);
-	file->private_data = cursor;
-	return dcache_dir_close(inode, file);
-}
-
-static int add_dentries(struct dentry ***dentries, struct dentry *d, int cnt)
-{
-	struct dentry **tmp;
-
-	tmp = krealloc(*dentries, sizeof(d) * (cnt + 2), GFP_NOFS);
-	if (!tmp)
-		return -1;
-	tmp[cnt] = d;
-	tmp[cnt + 1] = NULL;
-	*dentries = tmp;
-	return 0;
-}
-
-/**
- * dcache_dir_open_wrapper - eventfs open wrapper
- * @inode: not used
- * @file: dir to be opened (to create it's children)
- *
- * Used to dynamic create file/dir with-in @file, all the
- * file/dir will be created. If already created then references
- * will be increased
+/*
+ * Walk the children of a eventfs_inode to fill in getdents().
  */
-static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
+static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 {
 	const struct file_operations *fops;
+	struct inode *f_inode = file_inode(file);
 	const struct eventfs_entry *entry;
 	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct dentry_list *dlist;
-	struct dentry **dentries = NULL;
-	struct dentry *parent = file_dentry(file);
-	struct dentry *d;
-	struct inode *f_inode = file_inode(file);
-	const char *name = parent->d_name.name;
+	struct dentry *ei_dentry = NULL;
+	struct dentry *dentry;
+	const char *name;
 	umode_t mode;
-	void *data;
-	int cnt = 0;
 	int idx;
-	int ret;
-	int i;
-	int r;
+	int ret = -EINVAL;
+	int ino;
+	int i, r, c;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
 
 	ti = get_tracefs(f_inode);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
 		return -EINVAL;
 
-	if (WARN_ON_ONCE(file->private_data))
-		return -EINVAL;
+	c = ctx->pos - 2;
 
 	idx = srcu_read_lock(&eventfs_srcu);
 
 	mutex_lock(&eventfs_mutex);
 	ei = READ_ONCE(ti->private);
+	if (ei && !ei->is_freed)
+		ei_dentry = READ_ONCE(ei->dentry);
 	mutex_unlock(&eventfs_mutex);
 
-	if (!ei) {
-		srcu_read_unlock(&eventfs_srcu, idx);
-		return -EINVAL;
-	}
-
-
-	data = ei->data;
+	if (!ei || !ei_dentry)
+		goto out;
 
-	dlist = kmalloc(sizeof(*dlist), GFP_KERNEL);
-	if (!dlist) {
-		srcu_read_unlock(&eventfs_srcu, idx);
-		return -ENOMEM;
-	}
+	ret = 0;
 
-	inode_lock(parent->d_inode);
+	/*
+	 * Need to create the dentries and inodes to have a consistent
+	 * inode number.
+	 */
 	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
-		d = create_dir_dentry(ei, ei_child, parent);
-		if (d) {
-			ret = add_dentries(&dentries, d, cnt);
-			dput(d);
-			if (ret < 0)
-				break;
-			cnt++;
+
+		if (c > 0) {
+			c--;
+			continue;
 		}
+
+		if (ei_child->is_freed)
+			continue;
+
+		name = ei_child->name;
+
+		dentry = create_dir_dentry(ei, ei_child, ei_dentry);
+		if (!dentry)
+			goto out;
+		ino = dentry->d_inode->i_ino;
+		dput(dentry);
+
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
+			goto out;
+		ctx->pos++;
 	}
 
 	for (i = 0; i < ei->nr_entries; i++) {
-		void *cdata = data;
+		void *cdata = ei->data;
+
+		if (c > 0) {
+			c--;
+			continue;
+		}
+
 		entry = &ei->entries[i];
 		name = entry->name;
+
 		mutex_lock(&eventfs_mutex);
 		/* If ei->is_freed, then the event itself may be too */
 		if (!ei->is_freed)
@@ -774,42 +729,21 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 		mutex_unlock(&eventfs_mutex);
 		if (r <= 0)
 			continue;
-		d = create_file_dentry(ei, i, parent, name, mode, cdata, fops);
-		if (d) {
-			ret = add_dentries(&dentries, d, cnt);
-			dput(d);
-			if (ret < 0)
-				break;
-			cnt++;
-		}
-	}
-	inode_unlock(parent->d_inode);
-	srcu_read_unlock(&eventfs_srcu, idx);
-	ret = dcache_dir_open(inode, file);
 
-	/*
-	 * dcache_dir_open() sets file->private_data to a dentry cursor.
-	 * Need to save that but also save all the dentries that were
-	 * opened by this function.
-	 */
-	dlist->cursor = file->private_data;
-	dlist->dentries = dentries;
-	file->private_data = dlist;
-	return ret;
-}
+		dentry = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
+		if (!dentry)
+			goto out;
+		ino = dentry->d_inode->i_ino;
+		dput(dentry);
 
-/*
- * This just sets the file->private_data back to the cursor and back.
- */
-static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx)
-{
-	struct dentry_list *dlist = file->private_data;
-	int ret;
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
+			goto out;
+		ctx->pos++;
+	}
+	ret = 1;
+ out:
+	srcu_read_unlock(&eventfs_srcu, idx);
 
-	file->private_data = dlist->cursor;
-	ret = dcache_readdir(file, ctx);
-	dlist->cursor = file->private_data;
-	file->private_data = dlist;
 	return ret;
 }
 
-- 
GitLab


From 8186fff7ab649085e2c60d032d9a20a85af1d87c Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 3 Jan 2024 21:50:16 -0500
Subject: [PATCH 2077/4076] tracefs/eventfs: Use root and instance inodes as
 default ownership

Instead of walking the dentries on mount/remount to update the gid values of
all the dentries if a gid option is specified on mount, just update the root
inode. Add .getattr, .setattr, and .permissions on the tracefs inode
operations to update the permissions of the files and directories.

For all files and directories in the top level instance:

 /sys/kernel/tracing/*

It will use the root inode as the default permissions. The inode that
represents: /sys/kernel/tracing (or wherever it is mounted).

When an instance is created:

 mkdir /sys/kernel/tracing/instance/foo

The directory "foo" and all its files and directories underneath will use
the default of what foo is when it was created. A remount of tracefs will
not affect it.

If a user were to modify the permissions of any file or directory in
tracefs, it will also no longer be modified by a change in ownership of a
remount.

The events directory, if it is in the top level instance, will use the
tracefs root inode as the default ownership for itself and all the files and
directories below it.

For the events directory in an instance ("foo"), it will keep the ownership
of what it was when it was created, and that will be used as the default
ownership for the files and directories beneath it.

Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wjVdGkjDXBbvLn2wbZnqP4UsH46E3gqJ9m7UG6DpX2+WA@mail.gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240103215016.1e0c9811@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c |  79 +++++++++++++++-
 fs/tracefs/inode.c       | 198 ++++++++++++++++++++++-----------------
 fs/tracefs/internal.h    |   3 +
 3 files changed, 190 insertions(+), 90 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 41af56f44f0a0..72912b5f9a90b 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -45,6 +45,7 @@ enum {
 	EVENTFS_SAVE_MODE	= BIT(16),
 	EVENTFS_SAVE_UID	= BIT(17),
 	EVENTFS_SAVE_GID	= BIT(18),
+	EVENTFS_TOPLEVEL	= BIT(19),
 };
 
 #define EVENTFS_MODE_MASK	(EVENTFS_SAVE_MODE - 1)
@@ -115,10 +116,17 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 * The events directory dentry is never freed, unless its
 		 * part of an instance that is deleted. It's attr is the
 		 * default for its child files and directories.
-		 * Do not update it. It's not used for its own mode or ownership
+		 * Do not update it. It's not used for its own mode or ownership.
 		 */
-		if (!ei->is_events)
+		if (ei->is_events) {
+			/* But it still needs to know if it was modified */
+			if (iattr->ia_valid & ATTR_UID)
+				ei->attr.mode |= EVENTFS_SAVE_UID;
+			if (iattr->ia_valid & ATTR_GID)
+				ei->attr.mode |= EVENTFS_SAVE_GID;
+		} else {
 			update_attr(&ei->attr, iattr);
+		}
 
 	} else {
 		name = dentry->d_name.name;
@@ -136,9 +144,66 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	return ret;
 }
 
+static void update_top_events_attr(struct eventfs_inode *ei, struct dentry *dentry)
+{
+	struct inode *inode;
+
+	/* Only update if the "events" was on the top level */
+	if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL))
+		return;
+
+	/* Get the tracefs root inode. */
+	inode = d_inode(dentry->d_sb->s_root);
+	ei->attr.uid = inode->i_uid;
+	ei->attr.gid = inode->i_gid;
+}
+
+static void set_top_events_ownership(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+	struct eventfs_inode *ei = ti->private;
+	struct dentry *dentry;
+
+	/* The top events directory doesn't get automatically updated */
+	if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL))
+		return;
+
+	dentry = ei->dentry;
+
+	update_top_events_attr(ei, dentry);
+
+	if (!(ei->attr.mode & EVENTFS_SAVE_UID))
+		inode->i_uid = ei->attr.uid;
+
+	if (!(ei->attr.mode & EVENTFS_SAVE_GID))
+		inode->i_gid = ei->attr.gid;
+}
+
+static int eventfs_get_attr(struct mnt_idmap *idmap,
+			    const struct path *path, struct kstat *stat,
+			    u32 request_mask, unsigned int flags)
+{
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = d_backing_inode(dentry);
+
+	set_top_events_ownership(inode);
+
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int eventfs_permission(struct mnt_idmap *idmap,
+			      struct inode *inode, int mask)
+{
+	set_top_events_ownership(inode);
+	return generic_permission(idmap, inode, mask);
+}
+
 static const struct inode_operations eventfs_root_dir_inode_operations = {
 	.lookup		= eventfs_root_lookup,
 	.setattr	= eventfs_set_attr,
+	.getattr	= eventfs_get_attr,
+	.permission	= eventfs_permission,
 };
 
 static const struct inode_operations eventfs_file_inode_operations = {
@@ -174,6 +239,8 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 	} while (!ei->is_events);
 	mutex_unlock(&eventfs_mutex);
 
+	update_top_events_attr(ei, dentry);
+
 	return ei;
 }
 
@@ -887,6 +954,14 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	uid = d_inode(dentry->d_parent)->i_uid;
 	gid = d_inode(dentry->d_parent)->i_gid;
 
+	/*
+	 * If the events directory is of the top instance, then parent
+	 * is NULL. Set the attr.mode to reflect this and its permissions will
+	 * default to the tracefs root dentry.
+	 */
+	if (!parent)
+		ei->attr.mode = EVENTFS_TOPLEVEL;
+
 	/* This is used as the default ownership of the files and directories */
 	ei->attr.uid = uid;
 	ei->attr.gid = gid;
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index bc86ffdb103bc..e1b172c0e091a 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -91,6 +91,7 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap,
 				 struct inode *inode, struct dentry *dentry,
 				 umode_t mode)
 {
+	struct tracefs_inode *ti;
 	char *name;
 	int ret;
 
@@ -98,6 +99,15 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap,
 	if (!name)
 		return -ENOMEM;
 
+	/*
+	 * This is a new directory that does not take the default of
+	 * the rootfs. It becomes the default permissions for all the
+	 * files and directories underneath it.
+	 */
+	ti = get_tracefs(inode);
+	ti->flags |= TRACEFS_INSTANCE_INODE;
+	ti->private = inode;
+
 	/*
 	 * The mkdir call can call the generic functions that create
 	 * the files within the tracefs system. It is up to the individual
@@ -141,10 +151,76 @@ static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
 	return ret;
 }
 
-static const struct inode_operations tracefs_dir_inode_operations = {
+static void set_tracefs_inode_owner(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+	struct inode *root_inode = ti->private;
+
+	/*
+	 * If this inode has never been referenced, then update
+	 * the permissions to the superblock.
+	 */
+	if (!(ti->flags & TRACEFS_UID_PERM_SET))
+		inode->i_uid = root_inode->i_uid;
+
+	if (!(ti->flags & TRACEFS_GID_PERM_SET))
+		inode->i_gid = root_inode->i_gid;
+}
+
+static int tracefs_permission(struct mnt_idmap *idmap,
+			      struct inode *inode, int mask)
+{
+	set_tracefs_inode_owner(inode);
+	return generic_permission(idmap, inode, mask);
+}
+
+static int tracefs_getattr(struct mnt_idmap *idmap,
+			   const struct path *path, struct kstat *stat,
+			   u32 request_mask, unsigned int flags)
+{
+	struct inode *inode = d_backing_inode(path->dentry);
+
+	set_tracefs_inode_owner(inode);
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int tracefs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			   struct iattr *attr)
+{
+	unsigned int ia_valid = attr->ia_valid;
+	struct inode *inode = d_inode(dentry);
+	struct tracefs_inode *ti = get_tracefs(inode);
+
+	if (ia_valid & ATTR_UID)
+		ti->flags |= TRACEFS_UID_PERM_SET;
+
+	if (ia_valid & ATTR_GID)
+		ti->flags |= TRACEFS_GID_PERM_SET;
+
+	return simple_setattr(idmap, dentry, attr);
+}
+
+static const struct inode_operations tracefs_instance_dir_inode_operations = {
 	.lookup		= simple_lookup,
 	.mkdir		= tracefs_syscall_mkdir,
 	.rmdir		= tracefs_syscall_rmdir,
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+static const struct inode_operations tracefs_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+static const struct inode_operations tracefs_file_inode_operations = {
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
 };
 
 struct inode *tracefs_get_inode(struct super_block *sb)
@@ -183,87 +259,6 @@ struct tracefs_fs_info {
 	struct tracefs_mount_opts mount_opts;
 };
 
-static void change_gid(struct dentry *dentry, kgid_t gid)
-{
-	if (!dentry->d_inode)
-		return;
-	dentry->d_inode->i_gid = gid;
-}
-
-/*
- * Taken from d_walk, but without he need for handling renames.
- * Nothing can be renamed while walking the list, as tracefs
- * does not support renames. This is only called when mounting
- * or remounting the file system, to set all the files to
- * the given gid.
- */
-static void set_gid(struct dentry *parent, kgid_t gid)
-{
-	struct dentry *this_parent;
-	struct list_head *next;
-
-	this_parent = parent;
-	spin_lock(&this_parent->d_lock);
-
-	change_gid(this_parent, gid);
-repeat:
-	next = this_parent->d_subdirs.next;
-resume:
-	while (next != &this_parent->d_subdirs) {
-		struct tracefs_inode *ti;
-		struct list_head *tmp = next;
-		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
-		next = tmp->next;
-
-		/* Note, getdents() can add a cursor dentry with no inode */
-		if (!dentry->d_inode)
-			continue;
-
-		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-
-		change_gid(dentry, gid);
-
-		/* If this is the events directory, update that too */
-		ti = get_tracefs(dentry->d_inode);
-		if (ti && (ti->flags & TRACEFS_EVENT_INODE))
-			eventfs_update_gid(dentry, gid);
-
-		if (!list_empty(&dentry->d_subdirs)) {
-			spin_unlock(&this_parent->d_lock);
-			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
-			this_parent = dentry;
-			spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
-			goto repeat;
-		}
-		spin_unlock(&dentry->d_lock);
-	}
-	/*
-	 * All done at this level ... ascend and resume the search.
-	 */
-	rcu_read_lock();
-ascend:
-	if (this_parent != parent) {
-		struct dentry *child = this_parent;
-		this_parent = child->d_parent;
-
-		spin_unlock(&child->d_lock);
-		spin_lock(&this_parent->d_lock);
-
-		/* go into the first sibling still alive */
-		do {
-			next = child->d_child.next;
-			if (next == &this_parent->d_subdirs)
-				goto ascend;
-			child = list_entry(next, struct dentry, d_child);
-		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
-		rcu_read_unlock();
-		goto resume;
-	}
-	rcu_read_unlock();
-	spin_unlock(&this_parent->d_lock);
-	return;
-}
-
 static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 {
 	substring_t args[MAX_OPT_ARGS];
@@ -336,10 +331,8 @@ static int tracefs_apply_options(struct super_block *sb, bool remount)
 	if (!remount || opts->opts & BIT(Opt_uid))
 		inode->i_uid = opts->uid;
 
-	if (!remount || opts->opts & BIT(Opt_gid)) {
-		/* Set all the group ids to the mount option */
-		set_gid(sb->s_root, opts->gid);
-	}
+	if (!remount || opts->opts & BIT(Opt_gid))
+		inode->i_gid = opts->gid;
 
 	return 0;
 }
@@ -573,6 +566,26 @@ struct dentry *eventfs_end_creating(struct dentry *dentry)
 	return dentry;
 }
 
+/* Find the inode that this will use for default */
+static struct inode *instance_inode(struct dentry *parent, struct inode *inode)
+{
+	struct tracefs_inode *ti;
+
+	/* If parent is NULL then use root inode */
+	if (!parent)
+		return d_inode(inode->i_sb->s_root);
+
+	/* Find the inode that is flagged as an instance or the root inode */
+	while (!IS_ROOT(parent)) {
+		ti = get_tracefs(d_inode(parent));
+		if (ti->flags & TRACEFS_INSTANCE_INODE)
+			break;
+		parent = parent->d_parent;
+	}
+
+	return d_inode(parent);
+}
+
 /**
  * tracefs_create_file - create a file in the tracefs filesystem
  * @name: a pointer to a string containing the name of the file to create.
@@ -603,6 +616,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops)
 {
+	struct tracefs_inode *ti;
 	struct dentry *dentry;
 	struct inode *inode;
 
@@ -621,7 +635,11 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	if (unlikely(!inode))
 		return tracefs_failed_creating(dentry);
 
+	ti = get_tracefs(inode);
+	ti->private = instance_inode(parent, inode);
+
 	inode->i_mode = mode;
+	inode->i_op = &tracefs_file_inode_operations;
 	inode->i_fop = fops ? fops : &tracefs_file_operations;
 	inode->i_private = data;
 	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
@@ -634,6 +652,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 static struct dentry *__create_dir(const char *name, struct dentry *parent,
 				   const struct inode_operations *ops)
 {
+	struct tracefs_inode *ti;
 	struct dentry *dentry = tracefs_start_creating(name, parent);
 	struct inode *inode;
 
@@ -651,6 +670,9 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent,
 	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
 	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
 
+	ti = get_tracefs(inode);
+	ti->private = instance_inode(parent, inode);
+
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
 	d_instantiate(dentry, inode);
@@ -681,7 +703,7 @@ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent)
 	if (security_locked_down(LOCKDOWN_TRACEFS))
 		return NULL;
 
-	return __create_dir(name, parent, &simple_dir_inode_operations);
+	return __create_dir(name, parent, &tracefs_dir_inode_operations);
 }
 
 /**
@@ -712,7 +734,7 @@ __init struct dentry *tracefs_create_instance_dir(const char *name,
 	if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir))
 		return NULL;
 
-	dentry = __create_dir(name, parent, &tracefs_dir_inode_operations);
+	dentry = __create_dir(name, parent, &tracefs_instance_dir_inode_operations);
 	if (!dentry)
 		return NULL;
 
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 42bdeb471a072..12b7d0150ae9e 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -5,6 +5,9 @@
 enum {
 	TRACEFS_EVENT_INODE		= BIT(1),
 	TRACEFS_EVENT_TOP_INODE		= BIT(2),
+	TRACEFS_GID_PERM_SET		= BIT(3),
+	TRACEFS_UID_PERM_SET		= BIT(4),
+	TRACEFS_INSTANCE_INODE		= BIT(5),
 };
 
 struct tracefs_inode {
-- 
GitLab


From daf7795406bf307997366f694888bd317ae5b5fa Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 18 Dec 2023 14:52:14 -0800
Subject: [PATCH 2078/4076] scsi: ufs: core: Simplify power management during
 async scan

ufshcd_init() calls pm_runtime_get_sync() before it calls
async_schedule(). ufshcd_async_scan() calls pm_runtime_put_sync() directly
or indirectly from ufshcd_add_lus(). Simplify ufshcd_async_scan() by always
calling pm_runtime_put_sync() from ufshcd_async_scan().

Cc: <stable@vger.kernel.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20231218225229.2542156-2-bvanassche@acm.org
Reviewed-by: Can Guo <quic_cang@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index d6ae5d17892c8..0ad8bde39cd19 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8711,7 +8711,6 @@ static int ufshcd_add_lus(struct ufs_hba *hba)
 
 	ufs_bsg_probe(hba);
 	scsi_scan_host(hba->host);
-	pm_runtime_put_sync(hba->dev);
 
 out:
 	return ret;
@@ -8980,15 +8979,15 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 
 	/* Probe and add UFS logical units  */
 	ret = ufshcd_add_lus(hba);
+
 out:
+	pm_runtime_put_sync(hba->dev);
 	/*
 	 * If we failed to initialize the device or the device is not
 	 * present, turn off the power/clocks etc.
 	 */
-	if (ret) {
-		pm_runtime_put_sync(hba->dev);
+	if (ret)
 		ufshcd_hba_exit(hba);
-	}
 }
 
 static enum scsi_timeout_action ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
-- 
GitLab


From ee36710912b2075c417100a8acc642c9c6496501 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 18 Dec 2023 14:52:15 -0800
Subject: [PATCH 2079/4076] scsi: ufs: core: Remove the ufshcd_hba_exit() call
 from ufshcd_async_scan()

Calling ufshcd_hba_exit() from a function that is called asynchronously
from ufshcd_init() is wrong because this triggers multiple race
conditions. Instead of calling ufshcd_hba_exit(), log an error message.

Reported-by: Daniel Mentz <danielmentz@google.com>
Fixes: 1d337ec2f35e ("ufs: improve init sequence")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20231218225229.2542156-3-bvanassche@acm.org
Reviewed-by: Can Guo <quic_cang@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0ad8bde39cd19..7c59d7a02243e 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8982,12 +8982,9 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 
 out:
 	pm_runtime_put_sync(hba->dev);
-	/*
-	 * If we failed to initialize the device or the device is not
-	 * present, turn off the power/clocks etc.
-	 */
+
 	if (ret)
-		ufshcd_hba_exit(hba);
+		dev_err(hba->dev, "%s failed: %d\n", __func__, ret);
 }
 
 static enum scsi_timeout_action ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
-- 
GitLab


From b08d86e6eb03566c5dc32e6ff10147f80aeb7511 Mon Sep 17 00:00:00 2001
From: ChanWoo Lee <cw9316.lee@samsung.com>
Date: Tue, 19 Dec 2023 17:27:40 +0900
Subject: [PATCH 2080/4076] scsi: ufs: qcom: Remove unnecessary goto statement
 from ufs_qcom_config_esi()

There is only one place where goto is used, and it is unnecessary to check
the ret value through 'goto out' because the ret value is already true.

Therefore, remove the goto statement and integrate the '!ret' condition
into the existing code.

Signed-off-by: ChanWoo Lee <cw9316.lee@samsung.com>
Link: https://lore.kernel.org/r/20231219082740.27644-1-cw9316.lee@samsung.com
Reviewed-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-qcom.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 9fd8d737edea9..0879f5ed4e5b1 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -1714,7 +1714,7 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 					     ufs_qcom_write_msi_msg);
 	if (ret) {
 		dev_err(hba->dev, "Failed to request Platform MSI %d\n", ret);
-		goto out;
+		return ret;
 	}
 
 	msi_lock_descs(hba->dev);
@@ -1748,11 +1748,8 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 				    FIELD_PREP(ESI_VEC_MASK, MAX_ESI_VEC - 1),
 				    REG_UFS_CFG3);
 		ufshcd_mcq_enable_esi(hba);
-	}
-
-out:
-	if (!ret)
 		host->esi_enabled = true;
+	}
 
 	return ret;
 }
-- 
GitLab


From c6d5aa44eaf6d119f9ceb3bfc7d22405ac04232a Mon Sep 17 00:00:00 2001
From: David Strahan <david.strahan@microchip.com>
Date: Tue, 19 Dec 2023 13:36:50 -0600
Subject: [PATCH 2081/4076] scsi: smartpqi: Add new controller PCI IDs

All PCI ID entries in Hex.

Add PCI IDs for Cisco controllers:
                                                VID  / DID  / SVID / SDID
                                                ----   ----   ----   ----
        Cisco 24G TriMode M1 RAID 4GB FBWC 32D  9005 / 028f / 1137 / 02f8
        Cisco 24G TriMode M1 RAID 4GB FBWC 16D  9005 / 028f / 1137 / 02f9
        Cisco 24G TriMode M1 HBA 16D            9005 / 028f / 1137 / 02fa

Add PCI IDs for CloudNine controllers:
                                                VID  / DID  / SVID / SDID
                                                ----   ----   ----   ----
        SmartRAID P7604N-16i                    9005 / 028f / 1f51 / 100e
        SmartRAID P7604N-8i                     9005 / 028f / 1f51 / 100f
        SmartRAID P7504N-16i                    9005 / 028f / 1f51 / 1010
        SmartRAID P7504N-8i                     9005 / 028f / 1f51 / 1011
        SmartRAID P7504N-8i                     9005 / 028f / 1f51 / 1043
        SmartHBA  P6500-8i                      9005 / 028f / 1f51 / 1044
        SmartRAID P7504-8i                      9005 / 028f / 1f51 / 1045

Reviewed-by: Murthy Bhat <Murthy.Bhat@microchip.com>
Reviewed-by: Mahesh Rajashekhara <mahesh.rajashekhara@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: David Strahan <david.strahan@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20231219193653.277553-2-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 40 +++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 9a58df9312fa7..d562011200877 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -10142,6 +10142,18 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 				0x1014, 0x0718)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1137, 0x02f8)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1137, 0x02f9)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1137, 0x02fa)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 				0x1e93, 0x1000)
@@ -10198,6 +10210,34 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 				0x1f51, 0x100a)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x100e)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x100f)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1010)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1011)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1043)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1044)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f51, 0x1045)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_ANY_ID, PCI_ANY_ID)
-- 
GitLab


From fb4cece17b4583f55b34a8538e27a4adc833c9d4 Mon Sep 17 00:00:00 2001
From: Mahesh Rajashekhara <mahesh.rajashekhara@microchip.com>
Date: Tue, 19 Dec 2023 13:36:51 -0600
Subject: [PATCH 2082/4076] scsi: smartpqi: Fix logical volume rescan race
 condition

Correct rescan flag race condition.

Multiple conditions are being evaluated before notifying OS to do a rescan.

Driver will skip rescanning the device if any one of the following
conditions are met:

 - Devices that have not yet been added to the OS or devices that have been
   removed.

 - Devices which are already marked for removal or in the phase of removal.

Under very rare conditions, after logical volume size expansion, the OS
still sees the size of the logical volume which was before expansion.

The rescan flag in the driver is used to signal the need for a logical
volume rescan. A race condition can occur in the driver, and it leads to
one thread overwriting the flag inadvertently. As a result, driver is not
notifying the OS SML to rescan the logical volume.

Move device->rescan update into new function pqi_mark_volumes_for_rescan()
and protect with a spin lock.

Move check for device->rescan into new function pqi_volume_rescan_needed()
and protect function call with a spin_lock.

Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Co-developed-by: Murthy Bhat <Murthy.Bhat@microchip.com>
Signed-off-by: Murthy Bhat <Murthy.Bhat@microchip.com>
Signed-off-by: Mahesh Rajashekhara <mahesh.rajashekhara@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20231219193653.277553-3-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi.h      |  1 -
 drivers/scsi/smartpqi/smartpqi_init.c | 43 ++++++++++++++++++++++-----
 2 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index 0419401835169..cdedc271857aa 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -1347,7 +1347,6 @@ struct pqi_ctrl_info {
 	bool		controller_online;
 	bool		block_requests;
 	bool		scan_blocked;
-	u8		logical_volume_rescan_needed : 1;
 	u8		inbound_spanning_supported : 1;
 	u8		outbound_spanning_supported : 1;
 	u8		pqi_mode_enabled : 1;
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index d562011200877..081bb2c098063 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -2093,8 +2093,6 @@ static void pqi_scsi_update_device(struct pqi_ctrl_info *ctrl_info,
 		if (existing_device->devtype == TYPE_DISK) {
 			existing_device->raid_level = new_device->raid_level;
 			existing_device->volume_status = new_device->volume_status;
-			if (ctrl_info->logical_volume_rescan_needed)
-				existing_device->rescan = true;
 			memset(existing_device->next_bypass_group, 0, sizeof(existing_device->next_bypass_group));
 			if (!pqi_raid_maps_equal(existing_device->raid_map, new_device->raid_map)) {
 				kfree(existing_device->raid_map);
@@ -2164,6 +2162,20 @@ static inline void pqi_init_device_tmf_work(struct pqi_scsi_dev *device)
 		INIT_WORK(&tmf_work->work_struct, pqi_tmf_worker);
 }
 
+static inline bool pqi_volume_rescan_needed(struct pqi_scsi_dev *device)
+{
+	if (pqi_device_in_remove(device))
+		return false;
+
+	if (device->sdev == NULL)
+		return false;
+
+	if (!scsi_device_online(device->sdev))
+		return false;
+
+	return device->rescan;
+}
+
 static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *new_device_list[], unsigned int num_new_devices)
 {
@@ -2284,9 +2296,13 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 		if (device->sdev && device->queue_depth != device->advertised_queue_depth) {
 			device->advertised_queue_depth = device->queue_depth;
 			scsi_change_queue_depth(device->sdev, device->advertised_queue_depth);
-			if (device->rescan) {
-				scsi_rescan_device(device->sdev);
+			spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
+			if (pqi_volume_rescan_needed(device)) {
 				device->rescan = false;
+				spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+				scsi_rescan_device(device->sdev);
+			} else {
+				spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
 			}
 		}
 	}
@@ -2308,8 +2324,6 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 		}
 	}
 
-	ctrl_info->logical_volume_rescan_needed = false;
-
 }
 
 static inline bool pqi_is_supported_device(struct pqi_scsi_dev *device)
@@ -3702,6 +3716,21 @@ static bool pqi_ofa_process_event(struct pqi_ctrl_info *ctrl_info,
 	return ack_event;
 }
 
+static void pqi_mark_volumes_for_rescan(struct pqi_ctrl_info *ctrl_info)
+{
+	unsigned long flags;
+	struct pqi_scsi_dev *device;
+
+	spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
+
+	list_for_each_entry(device, &ctrl_info->scsi_device_list, scsi_device_list_entry) {
+		if (pqi_is_logical_device(device) && device->devtype == TYPE_DISK)
+			device->rescan = true;
+	}
+
+	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+}
+
 static void pqi_disable_raid_bypass(struct pqi_ctrl_info *ctrl_info)
 {
 	unsigned long flags;
@@ -3742,7 +3771,7 @@ static void pqi_event_worker(struct work_struct *work)
 				ack_event = true;
 				rescan_needed = true;
 				if (event->event_type == PQI_EVENT_TYPE_LOGICAL_DEVICE)
-					ctrl_info->logical_volume_rescan_needed = true;
+					pqi_mark_volumes_for_rescan(ctrl_info);
 				else if (event->event_type == PQI_EVENT_TYPE_AIO_STATE_CHANGE)
 					pqi_disable_raid_bypass(ctrl_info);
 			}
-- 
GitLab


From 8c9955107762a23043db544d83959c4e0103bae3 Mon Sep 17 00:00:00 2001
From: Don Brace <don.brace@microchip.com>
Date: Tue, 19 Dec 2023 13:36:52 -0600
Subject: [PATCH 2083/4076] scsi: smartpqi: Bump driver version to 2.1.26-030

Reviewed-by: Mahesh Rajashekhara <mahesh.rajashekhara@microchip.com>
Reviewed-by: Murthy Bhat <Murthy.Bhat@microchip.com>
Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Mike McGowen <mike.mcgowen@microchip.com>
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/20231219193653.277553-4-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 081bb2c098063..ceff1ec13f9ea 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -33,11 +33,11 @@
 #define BUILD_TIMESTAMP
 #endif
 
-#define DRIVER_VERSION		"2.1.24-046"
+#define DRIVER_VERSION		"2.1.26-030"
 #define DRIVER_MAJOR		2
 #define DRIVER_MINOR		1
-#define DRIVER_RELEASE		24
-#define DRIVER_REVISION		46
+#define DRIVER_RELEASE		26
+#define DRIVER_REVISION		30
 
 #define DRIVER_NAME		"Microchip SmartPQI Driver (v" \
 				DRIVER_VERSION BUILD_TIMESTAMP ")"
-- 
GitLab


From 904fdd2062f3101fb09db8ee077abf7ffd95e538 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 20 Dec 2023 21:31:13 -0800
Subject: [PATCH 2084/4076] scsi: mpi3mr: Fix mpi3mr_fw.c kernel-doc warnings

Use correct format for function return values.
Delete blank lines that are reported as "bad line:".

mpi3mr_fw.c:482: warning: No description found for return value of 'mpi3mr_get_reply_desc'
mpi3mr_fw.c:1066: warning: bad line:
mpi3mr_fw.c:1109: warning: bad line:
mpi3mr_fw.c:1249: warning: No description found for return value of 'mpi3mr_revalidate_factsdata'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20231221053113.32191-1-rdunlap@infradead.org
Cc: Sathya Prakash Veerichetty <sathya.prakash@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Cc: <mpi3mr-linuxdrv.pdl@broadcom.com>
Cc: James E.J. Bottomley <jejb@linux.ibm.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: <linux-scsi@vger.kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpi3mr/mpi3mr_fw.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index d8c57a0a518f4..528f19f782f21 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -475,7 +475,7 @@ int mpi3mr_process_admin_reply_q(struct mpi3mr_ioc *mrioc)
  * @op_reply_q: op_reply_qinfo object
  * @reply_ci: operational reply descriptor's queue consumer index
  *
- * Returns reply descriptor frame address
+ * Returns: reply descriptor frame address
  */
 static inline struct mpi3_default_reply_descriptor *
 mpi3mr_get_reply_desc(struct op_reply_qinfo *op_reply_q, u32 reply_ci)
@@ -1063,7 +1063,6 @@ enum mpi3mr_iocstate mpi3mr_get_iocstate(struct mpi3mr_ioc *mrioc)
  * @mrioc: Adapter instance reference
  *
  * Free the DMA memory allocated for IOCTL handling purpose.
-
  *
  * Return: None
  */
@@ -1106,7 +1105,6 @@ static void mpi3mr_free_ioctl_dma_memory(struct mpi3mr_ioc *mrioc)
 /**
  * mpi3mr_alloc_ioctl_dma_memory - Alloc memory for ioctl dma
  * @mrioc: Adapter instance reference
-
  *
  * This function allocates dmaable memory required to handle the
  * application issued MPI3 IOCTL requests.
@@ -1241,7 +1239,7 @@ static int mpi3mr_issue_and_process_mur(struct mpi3mr_ioc *mrioc,
  * during reset/resume
  * @mrioc: Adapter instance reference
  *
- * Return zero if the new IOCFacts parameters value is compatible with
+ * Return: zero if the new IOCFacts parameters value is compatible with
  * older values else return -EPERM
  */
 static int
-- 
GitLab


From 1342ad786073e96fa813ad943c19f586157ae297 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 4 Dec 2023 21:19:44 +0300
Subject: [PATCH 2085/4076] apparmor: fix possible memory leak in
 unpack_trans_table

If we fail to unpack the transition table then the table elements which
have been already allocated are not freed on error path.

unreferenced object 0xffff88802539e000 (size 128):
  comm "apparmor_parser", pid 903, jiffies 4294914938 (age 35.085s)
  hex dump (first 32 bytes):
    20 73 6f 6d 65 20 6e 61 73 74 79 20 73 74 72 69   some nasty stri
    6e 67 20 73 6f 6d 65 20 6e 61 73 74 79 20 73 74  ng some nasty st
  backtrace:
    [<ffffffff81ddb312>] __kmem_cache_alloc_node+0x1e2/0x2d0
    [<ffffffff81c47194>] __kmalloc_node_track_caller+0x54/0x170
    [<ffffffff81c225b9>] kmemdup+0x29/0x60
    [<ffffffff83e1ee65>] aa_unpack_strdup+0xe5/0x1b0
    [<ffffffff83e20808>] unpack_pdb+0xeb8/0x2700
    [<ffffffff83e23567>] unpack_profile+0x1507/0x4a30
    [<ffffffff83e27bfa>] aa_unpack+0x36a/0x1560
    [<ffffffff83e194c3>] aa_replace_profiles+0x213/0x33c0
    [<ffffffff83de9461>] policy_update+0x261/0x370
    [<ffffffff83de978e>] profile_replace+0x20e/0x2a0
    [<ffffffff81eac8bf>] vfs_write+0x2af/0xe00
    [<ffffffff81eaddd6>] ksys_write+0x126/0x250
    [<ffffffff88f34fb6>] do_syscall_64+0x46/0xf0
    [<ffffffff890000ea>] entry_SYSCALL_64_after_hwframe+0x6e/0x76

Call aa_free_str_table() on error path as was done before the blamed
commit. It implements all necessary checks, frees str_table if it is
available and nullifies the pointers.

Found by Linux Verification Center (linuxtesting.org).

Fixes: a0792e2ceddc ("apparmor: make transition table unpack generic so it can be reused")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/lib.c           | 1 +
 security/apparmor/policy_unpack.c | 7 +++----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c
index 4c198d273f091..cd569fbbfe36d 100644
--- a/security/apparmor/lib.c
+++ b/security/apparmor/lib.c
@@ -41,6 +41,7 @@ void aa_free_str_table(struct aa_str_table *t)
 			kfree_sensitive(t->table[i]);
 		kfree_sensitive(t->table);
 		t->table = NULL;
+		t->size = 0;
 	}
 }
 
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 47ec097d6741f..9575da5fd4cb4 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -478,6 +478,8 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_str_table *strs)
 		if (!table)
 			goto fail;
 
+		strs->table = table;
+		strs->size = size;
 		for (i = 0; i < size; i++) {
 			char *str;
 			int c, j, pos, size2 = aa_unpack_strdup(e, &str, NULL);
@@ -520,14 +522,11 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_str_table *strs)
 			goto fail;
 		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
 			goto fail;
-
-		strs->table = table;
-		strs->size = size;
 	}
 	return true;
 
 fail:
-	kfree_sensitive(table);
+	aa_free_str_table(strs);
 	e->pos = saved_pos;
 	return false;
 }
-- 
GitLab


From 55a8210c9e7d21ff2644809699765796d4bfb200 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Thu, 28 Dec 2023 19:07:43 +0300
Subject: [PATCH 2086/4076] apparmor: avoid crash when parsed profile name is
 empty

When processing a packed profile in unpack_profile() described like

 "profile :ns::samba-dcerpcd /usr/lib*/samba/{,samba/}samba-dcerpcd {...}"

a string ":samba-dcerpcd" is unpacked as a fully-qualified name and then
passed to aa_splitn_fqname().

aa_splitn_fqname() treats ":samba-dcerpcd" as only containing a namespace.
Thus it returns NULL for tmpname, meanwhile tmpns is non-NULL. Later
aa_alloc_profile() crashes as the new profile name is NULL now.

general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
CPU: 6 PID: 1657 Comm: apparmor_parser Not tainted 6.7.0-rc2-dirty #16
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014
RIP: 0010:strlen+0x1e/0xa0
Call Trace:
 <TASK>
 ? strlen+0x1e/0xa0
 aa_policy_init+0x1bb/0x230
 aa_alloc_profile+0xb1/0x480
 unpack_profile+0x3bc/0x4960
 aa_unpack+0x309/0x15e0
 aa_replace_profiles+0x213/0x33c0
 policy_update+0x261/0x370
 profile_replace+0x20e/0x2a0
 vfs_write+0x2af/0xe00
 ksys_write+0x126/0x250
 do_syscall_64+0x46/0xf0
 entry_SYSCALL_64_after_hwframe+0x6e/0x76
 </TASK>
---[ end trace 0000000000000000 ]---
RIP: 0010:strlen+0x1e/0xa0

It seems such behaviour of aa_splitn_fqname() is expected and checked in
other places where it is called (e.g. aa_remove_profiles). Well, there
is an explicit comment "a ns name without a following profile is allowed"
inside.

AFAICS, nothing can prevent unpacked "name" to be in form like
":samba-dcerpcd" - it is passed from userspace.

Deny the whole profile set replacement in such case and inform user with
EPROTO and an explaining message.

Found by Linux Verification Center (linuxtesting.org).

Fixes: 04dc715e24d0 ("apparmor: audit policy ns specified in policy load")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy_unpack.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 9575da5fd4cb4..dbf7d96257ada 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -832,6 +832,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 
 	tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len);
 	if (tmpns) {
+		if (!tmpname) {
+			info = "empty profile name";
+			goto fail;
+		}
 		*ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL);
 		if (!*ns_name) {
 			info = "out of memory";
-- 
GitLab


From 6c2c1e0009e97381a032d8c84747a46082fd327c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 3 Jan 2024 12:08:46 +0000
Subject: [PATCH 2087/4076] 9p: Do a couple of cleanups

Do a couple of cleanups to 9p:

 (1) Remove a couple of unused variables.

 (2) Turn a BUG_ON() into a warning, consolidate with another warning and
     make the warning message include the inode number rather than
     whatever's in i_private (which will get hashed anyway).

Suggested-by: Dominique Martinet <asmadeus@codewreck.org>
Link: https://lore.kernel.org/r/ZZULNQAZ0n0WQv7p@codewreck.org/
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Dominique Martinet <asmadeus@codewreck.org>
cc: Eric Van Hensbergen <ericvh@kernel.org>
cc: Latchesar Ionkov <lucho@ionkov.net>
cc: Christian Schoenebeck <linux_oss@crudebyte.com>
cc: v9fs@lists.linux.dev
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
---
 fs/9p/vfs_addr.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index d8fb407189a09..f7f83eec3bccf 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -28,8 +28,6 @@
 
 static void v9fs_upload_to_server(struct netfs_io_subrequest *subreq)
 {
-	struct inode *inode = subreq->rreq->inode;
-	struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode);
 	struct p9_fid *fid = subreq->rreq->netfs_priv;
 	int err;
 
@@ -98,15 +96,13 @@ static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file)
 
 	if (file) {
 		fid = file->private_data;
-		BUG_ON(!fid);
+		if (!fid)
+			goto no_fid;
 		p9_fid_get(fid);
 	} else {
 		fid = v9fs_fid_find_inode(rreq->inode, writing, INVALID_UID, true);
-		if (!fid) {
-			WARN_ONCE(1, "folio expected an open fid inode->i_private=%p\n",
-				  rreq->inode->i_private);
-			return -EINVAL;
-		}
+		if (!fid)
+			goto no_fid;
 	}
 
 	/* we might need to read from a fid that was opened write-only
@@ -115,6 +111,11 @@ static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file)
 	WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE && !(fid->mode & P9_ORDWR));
 	rreq->netfs_priv = fid;
 	return 0;
+
+no_fid:
+	WARN_ONCE(1, "folio expected an open fid inode->i_ino=%lx\n",
+		  rreq->inode->i_ino);
+	return -EINVAL;
 }
 
 /**
-- 
GitLab


From 252cf7b2eaf7cb904580ffbb0126d23411bcb43d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 3 Jan 2024 14:30:48 +0000
Subject: [PATCH 2088/4076] 9p: Use length of data written to the server in
 preference to error

In v9fs_upload_to_server(), we pass the error to netfslib to terminate the
subreq rather than the amount of data written - even if we did actually
write something.

Further, we assume that the write is always entirely done if successful -
but it might have been partially complete - as returned by
p9_client_write(), but we ignore that.

Fix this by indicating the amount written by preference and only returning
the error if we didn't write anything.

(We might want to return both in future if both are available as this
might be useful as to whether we retry or not.)

Suggested-by: Dominique Martinet <asmadeus@codewreck.org>
Link: https://lore.kernel.org/r/ZZULNQAZ0n0WQv7p@codewreck.org/
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Dominique Martinet <asmadeus@codewreck.org>
cc: Eric Van Hensbergen <ericvh@kernel.org>
cc: Latchesar Ionkov <lucho@ionkov.net>
cc: Christian Schoenebeck <linux_oss@crudebyte.com>
cc: v9fs@lists.linux.dev
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
---
 fs/9p/vfs_addr.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index f7f83eec3bccf..047855033d32f 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -29,12 +29,11 @@
 static void v9fs_upload_to_server(struct netfs_io_subrequest *subreq)
 {
 	struct p9_fid *fid = subreq->rreq->netfs_priv;
-	int err;
+	int err, len;
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
-	p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
-	netfs_write_subrequest_terminated(subreq, err < 0 ? err : subreq->len,
-					  false);
+	len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
+	netfs_write_subrequest_terminated(subreq, len ?: err, false);
 }
 
 static void v9fs_upload_to_server_worker(struct work_struct *work)
-- 
GitLab


From 040a82be54c09a72162a3db2f5cd2ba289c0f224 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 13 Oct 2023 12:26:31 +0100
Subject: [PATCH 2089/4076] netfs: Rearrange netfs_io_subrequest to put request
 pointer first

Rearrange the netfs_io_subrequest struct to put the netfs_io_request
pointer (rreq) first.  This then allows netfs_io_subrequest to be put in a
union with a pointer to a wrapper around netfs_io_request.  This will be
useful in the future for cifs and maybe ceph.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Steve French <sfrench@samba.org>
cc: Shyam Prasad N <nspmangalore@gmail.com>
cc: Rohith Surabattula <rohiths.msft@gmail.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 include/linux/netfs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 852956aa3c4bb..d3bac60fcd6f3 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -204,8 +204,8 @@ struct netfs_cache_resources {
  * the pages it points to can be relied on to exist for the duration.
  */
 struct netfs_io_subrequest {
-	struct work_struct	work;
 	struct netfs_io_request *rreq;		/* Supervising I/O request */
+	struct work_struct	work;
 	struct list_head	rreq_link;	/* Link in rreq->subrequests */
 	struct iov_iter		io_iter;	/* Iterator for this subrequest */
 	loff_t			start;		/* Where to start the I/O */
-- 
GitLab


From 43833f2ba5ce1543148a1b7cdd2513f5a663a17c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 3 Jan 2024 21:08:11 +0000
Subject: [PATCH 2090/4076] netfs: Fix proc/fs/fscache symlink to point to
 "netfs" not "../netfs"

Fix the proc/fs/fscache symlink to point to "netfs" not "../netfs".

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: Christian Brauner <christian@brauner.io>
cc: linux-fsdevel@vger.kernel.org
cc: linux-cachefs@redhat.com
---
 fs/netfs/fscache_proc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/netfs/fscache_proc.c b/fs/netfs/fscache_proc.c
index ecd0d1edafaa4..874d951bc3901 100644
--- a/fs/netfs/fscache_proc.c
+++ b/fs/netfs/fscache_proc.c
@@ -16,7 +16,7 @@
  */
 int __init fscache_proc_init(void)
 {
-	if (!proc_symlink("fs/fscache", NULL, "../netfs"))
+	if (!proc_symlink("fs/fscache", NULL, "netfs"))
 		goto error_sym;
 
 	if (!proc_create_seq("fs/netfs/caches", S_IFREG | 0444, NULL,
-- 
GitLab


From fbfb131ef81ff0cb568196801de1a1fb46cfd592 Mon Sep 17 00:00:00 2001
From: Piro Yang <piroyangg@gmail.com>
Date: Wed, 27 Dec 2023 23:47:39 +0800
Subject: [PATCH 2091/4076] staging: vme_user: print more detailed infomation
 when an error occurs

when the slave_get function pointer belongs to the struct vme_bridge
member is NULL, it prompts that the detailed function name
"vme_slave_set" equivalent to __func__ not supported.

it is similar to the vme_slave_get function:
when vme_bridge->slave_set function pointer is NULL to print detailed
function name by using __func__.

Signed-off-by: Piro Yang <piroyangg@gmail.com>
Link: https://lore.kernel.org/r/20231227154739.6951-1-piroyangg@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vme_user/vme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/vme_user/vme.c b/drivers/staging/vme_user/vme.c
index 9bc2d35405af6..e9461a7a7ab8b 100644
--- a/drivers/staging/vme_user/vme.c
+++ b/drivers/staging/vme_user/vme.c
@@ -340,7 +340,7 @@ int vme_slave_set(struct vme_resource *resource, int enabled,
 	image = list_entry(resource->entry, struct vme_slave_resource, list);
 
 	if (!bridge->slave_set) {
-		dev_err(bridge->parent, "Function not supported\n");
+		dev_err(bridge->parent, "%s not supported\n", __func__);
 		return -EINVAL;
 	}
 
-- 
GitLab


From f36be9ce8146faabdbbf74ee0499edb2039c53a5 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:13:10 +0100
Subject: [PATCH 2092/4076] EDAC: constantify the struct bus_type usage

In many places in the edac code, struct bus_type pointers are passed
around and then eventually sent to the driver core, which can handle a
constant pointer.  So constantify all of the edac usage of these as well
because the data in them is never modified by the edac code either.

Cc: Borislav Petkov <bp@alien8.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: James Morse <james.morse@arm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: Robert Richter <rric@kernel.org>
Cc:  <linux-edac@vger.kernel.org>
Link: https://lore.kernel.org/r/2023121909-tribute-punctuate-4b22@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/edac/edac_device.h       | 2 +-
 drivers/edac/edac_device_sysfs.c | 2 +-
 drivers/edac/edac_module.c       | 4 ++--
 drivers/edac/edac_pci_sysfs.c    | 2 +-
 include/linux/edac.h             | 4 ++--
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h
index 3f44e6b9d387f..7db22a4c83ef3 100644
--- a/drivers/edac/edac_device.h
+++ b/drivers/edac/edac_device.h
@@ -176,7 +176,7 @@ struct edac_device_ctl_info {
 	struct edac_dev_sysfs_attribute *sysfs_attributes;
 
 	/* pointer to main 'edac' subsys in sysfs */
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 
 	/* the internal state of this controller instance */
 	int op_state;
diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c
index 010c26be58464..237a542e045a3 100644
--- a/drivers/edac/edac_device_sysfs.c
+++ b/drivers/edac/edac_device_sysfs.c
@@ -229,7 +229,7 @@ static struct kobj_type ktype_device_ctrl = {
 int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev)
 {
 	struct device *dev_root;
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 	int err = -ENODEV;
 
 	edac_dbg(1, "\n");
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index 32a931d0cb71f..1c9f623826665 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -67,7 +67,7 @@ char *edac_op_state_to_string(int opstate)
  * sysfs object: /sys/devices/system/edac
  *	need to export to other files
  */
-static struct bus_type edac_subsys = {
+static const struct bus_type edac_subsys = {
 	.name = "edac",
 	.dev_name = "edac",
 };
@@ -90,7 +90,7 @@ static void edac_subsys_exit(void)
 }
 
 /* return pointer to the 'edac' node in sysfs */
-struct bus_type *edac_get_sysfs_subsys(void)
+const struct bus_type *edac_get_sysfs_subsys(void)
 {
 	return &edac_subsys;
 }
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index 287cc51dbc868..e823e4da086a7 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -338,7 +338,7 @@ static struct kobj_type ktype_edac_pci_main_kobj = {
 static int edac_pci_main_kobj_setup(void)
 {
 	int err = -ENODEV;
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 	struct device *dev_root;
 
 	edac_dbg(0, "\n");
diff --git a/include/linux/edac.h b/include/linux/edac.h
index fa4bda2a70f6c..ccaf2ae0801d6 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -30,7 +30,7 @@ struct device;
 
 extern int edac_op_state;
 
-struct bus_type *edac_get_sysfs_subsys(void);
+const struct bus_type *edac_get_sysfs_subsys(void);
 
 static inline void opstate_init(void)
 {
@@ -492,7 +492,7 @@ struct edac_raw_error_desc {
  */
 struct mem_ctl_info {
 	struct device			dev;
-	struct bus_type			*bus;
+	const struct bus_type		*bus;
 
 	struct list_head link;	/* for global list of mem_ctl_info structs */
 
-- 
GitLab


From d65a2fc00fc046117875507961e610fdc9001100 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 25 Dec 2023 12:23:09 -0800
Subject: [PATCH 2093/4076] Staging: rtl8192e: Rename variable bUsed

Rename variable bUsed to used to fix checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231225202314.31869-2-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 63217444ba65d..c509018b57232 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1164,7 +1164,7 @@ struct rt_pmkid_list {
 	u8 Bssid[ETH_ALEN];
 	u8 PMKID[16];
 	u8 SsidBuf[33];
-	u8 bUsed;
+	u8 used;
 };
 
 /*************** DRIVER STATUS   *****/
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index cd5b799bcadea..d4c97f0a499c9 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -670,7 +670,7 @@ static inline int SecIsInPMKIDList(struct rtllib_device *ieee, u8 *bssid)
 	int i = 0;
 
 	do {
-		if ((ieee->PMKIDList[i].bUsed) &&
+		if ((ieee->PMKIDList[i].used) &&
 		   (memcmp(ieee->PMKIDList[i].Bssid, bssid, ETH_ALEN) == 0))
 			break;
 		i++;
-- 
GitLab


From a24e0197f343cc55024c9edd68c072d0363466b6 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 25 Dec 2023 12:23:10 -0800
Subject: [PATCH 2094/4076] Staging: rtl8192e: Rename variable NumTxOkInPeriod

Rename variable NumTxOkInPeriod to num_tx_ok_in_period to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231225202314.31869-3-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 16 ++++++++--------
 drivers/staging/rtl8192e/rtllib.h            |  2 +-
 drivers/staging/rtl8192e/rtllib_rx.c         |  2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c    |  2 +-
 4 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 5107d06a9fd05..b2c56e2099ce5 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -972,11 +972,11 @@ static void _rtl92e_watchdog_wq_cb(void *data)
 	}
 	if ((ieee->link_state == MAC80211_LINKED) && (ieee->iw_mode == IW_MODE_INFRA)) {
 		if (ieee->link_detect_info.NumRxOkInPeriod > 100 ||
-		ieee->link_detect_info.NumTxOkInPeriod > 100)
+		ieee->link_detect_info.num_tx_ok_in_period > 100)
 			bBusyTraffic = true;
 
 		if (ieee->link_detect_info.NumRxOkInPeriod > 4000 ||
-		    ieee->link_detect_info.NumTxOkInPeriod > 4000) {
+		    ieee->link_detect_info.num_tx_ok_in_period > 4000) {
 			bHigherBusyTraffic = true;
 			if (ieee->link_detect_info.NumRxOkInPeriod > 5000)
 				bHigherBusyRxTraffic = true;
@@ -985,7 +985,7 @@ static void _rtl92e_watchdog_wq_cb(void *data)
 		}
 
 		if (((ieee->link_detect_info.NumRxUnicastOkInPeriod +
-		    ieee->link_detect_info.NumTxOkInPeriod) > 8) ||
+		    ieee->link_detect_info.num_tx_ok_in_period) > 8) ||
 		    (ieee->link_detect_info.NumRxUnicastOkInPeriod > 2))
 			bEnterPS = false;
 		else
@@ -1004,7 +1004,7 @@ static void _rtl92e_watchdog_wq_cb(void *data)
 	}
 
 	ieee->link_detect_info.NumRxOkInPeriod = 0;
-	ieee->link_detect_info.NumTxOkInPeriod = 0;
+	ieee->link_detect_info.num_tx_ok_in_period = 0;
 	ieee->link_detect_info.NumRxUnicastOkInPeriod = 0;
 	ieee->link_detect_info.bBusyTraffic = bBusyTraffic;
 
@@ -1773,22 +1773,22 @@ static irqreturn_t _rtl92e_irq(int irq, void *netdev)
 		tasklet_schedule(&priv->irq_rx_tasklet);
 
 	if (inta & IMR_BKDOK) {
-		priv->rtllib->link_detect_info.NumTxOkInPeriod++;
+		priv->rtllib->link_detect_info.num_tx_ok_in_period++;
 		_rtl92e_tx_isr(dev, BK_QUEUE);
 	}
 
 	if (inta & IMR_BEDOK) {
-		priv->rtllib->link_detect_info.NumTxOkInPeriod++;
+		priv->rtllib->link_detect_info.num_tx_ok_in_period++;
 		_rtl92e_tx_isr(dev, BE_QUEUE);
 	}
 
 	if (inta & IMR_VIDOK) {
-		priv->rtllib->link_detect_info.NumTxOkInPeriod++;
+		priv->rtllib->link_detect_info.num_tx_ok_in_period++;
 		_rtl92e_tx_isr(dev, VI_QUEUE);
 	}
 
 	if (inta & IMR_VODOK) {
-		priv->rtllib->link_detect_info.NumTxOkInPeriod++;
+		priv->rtllib->link_detect_info.num_tx_ok_in_period++;
 		_rtl92e_tx_isr(dev, VO_QUEUE);
 	}
 
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index c509018b57232..013cb28191477 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1118,7 +1118,7 @@ struct rt_link_detect {
 	u16				SlotNum;
 	u16				SlotIndex;
 
-	u32				NumTxOkInPeriod;
+	u32				num_tx_ok_in_period;
 	u32				NumRxOkInPeriod;
 	u32				NumRxUnicastOkInPeriod;
 	bool				bBusyTraffic;
diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index 595ec9af25ea0..f203b409d8a4b 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -1150,7 +1150,7 @@ static void rtllib_rx_check_leave_lps(struct rtllib_device *ieee, u8 unicast,
 	if (unicast) {
 		if (ieee->link_state == MAC80211_LINKED) {
 			if (((ieee->link_detect_info.NumRxUnicastOkInPeriod +
-			    ieee->link_detect_info.NumTxOkInPeriod) > 8) ||
+			    ieee->link_detect_info.num_tx_ok_in_period) > 8) ||
 			    (ieee->link_detect_info.NumRxUnicastOkInPeriod > 2)) {
 				ieee->leisure_ps_leave(ieee->dev);
 			}
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index d4c97f0a499c9..c5efc32fbd797 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2076,7 +2076,7 @@ int rtllib_softmac_init(struct rtllib_device *ieee)
 	ieee->link_detect_info.SlotNum = 2;
 	ieee->link_detect_info.NumRecvBcnInPeriod = 0;
 	ieee->link_detect_info.NumRecvDataInPeriod = 0;
-	ieee->link_detect_info.NumTxOkInPeriod = 0;
+	ieee->link_detect_info.num_tx_ok_in_period = 0;
 	ieee->link_detect_info.NumRxOkInPeriod = 0;
 	ieee->link_detect_info.NumRxUnicastOkInPeriod = 0;
 	ieee->bIsAggregateFrame = false;
-- 
GitLab


From 5fa882a8ad81b08d2366f6ebe82fcd50a4a582cf Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 25 Dec 2023 12:23:11 -0800
Subject: [PATCH 2095/4076] Staging: rtl8192e: Rename variable NumRxOkInPeriod

Rename variable NumRxOkInPeriod to num_rx_ok_in_period to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231225202314.31869-4-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 8 ++++----
 drivers/staging/rtl8192e/rtllib.h            | 2 +-
 drivers/staging/rtl8192e/rtllib_rx.c         | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c    | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index b2c56e2099ce5..6815d18a7919e 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -971,14 +971,14 @@ static void _rtl92e_watchdog_wq_cb(void *data)
 		}
 	}
 	if ((ieee->link_state == MAC80211_LINKED) && (ieee->iw_mode == IW_MODE_INFRA)) {
-		if (ieee->link_detect_info.NumRxOkInPeriod > 100 ||
+		if (ieee->link_detect_info.num_rx_ok_in_period > 100 ||
 		ieee->link_detect_info.num_tx_ok_in_period > 100)
 			bBusyTraffic = true;
 
-		if (ieee->link_detect_info.NumRxOkInPeriod > 4000 ||
+		if (ieee->link_detect_info.num_rx_ok_in_period > 4000 ||
 		    ieee->link_detect_info.num_tx_ok_in_period > 4000) {
 			bHigherBusyTraffic = true;
-			if (ieee->link_detect_info.NumRxOkInPeriod > 5000)
+			if (ieee->link_detect_info.num_rx_ok_in_period > 5000)
 				bHigherBusyRxTraffic = true;
 			else
 				bHigherBusyRxTraffic = false;
@@ -1003,7 +1003,7 @@ static void _rtl92e_watchdog_wq_cb(void *data)
 		rtl92e_leisure_ps_leave(dev);
 	}
 
-	ieee->link_detect_info.NumRxOkInPeriod = 0;
+	ieee->link_detect_info.num_rx_ok_in_period = 0;
 	ieee->link_detect_info.num_tx_ok_in_period = 0;
 	ieee->link_detect_info.NumRxUnicastOkInPeriod = 0;
 	ieee->link_detect_info.bBusyTraffic = bBusyTraffic;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 013cb28191477..a3c5dbaeba2d4 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1119,7 +1119,7 @@ struct rt_link_detect {
 	u16				SlotIndex;
 
 	u32				num_tx_ok_in_period;
-	u32				NumRxOkInPeriod;
+	u32				num_rx_ok_in_period;
 	u32				NumRxUnicastOkInPeriod;
 	bool				bBusyTraffic;
 	bool				bHigherBusyTraffic;
diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index f203b409d8a4b..6cb71eba04a78 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -1285,7 +1285,7 @@ static int rtllib_rx_InfraAdhoc(struct rtllib_device *ieee, struct sk_buff *skb,
 
 	/* Update statstics for AP roaming */
 	ieee->link_detect_info.NumRecvDataInPeriod++;
-	ieee->link_detect_info.NumRxOkInPeriod++;
+	ieee->link_detect_info.num_rx_ok_in_period++;
 
 	/* Data frame - extract src/dst addresses */
 	rtllib_rx_extract_addr(ieee, hdr, dst, src, bssid);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index c5efc32fbd797..0971059c7572d 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2077,7 +2077,7 @@ int rtllib_softmac_init(struct rtllib_device *ieee)
 	ieee->link_detect_info.NumRecvBcnInPeriod = 0;
 	ieee->link_detect_info.NumRecvDataInPeriod = 0;
 	ieee->link_detect_info.num_tx_ok_in_period = 0;
-	ieee->link_detect_info.NumRxOkInPeriod = 0;
+	ieee->link_detect_info.num_rx_ok_in_period = 0;
 	ieee->link_detect_info.NumRxUnicastOkInPeriod = 0;
 	ieee->bIsAggregateFrame = false;
 	ieee->assoc_id = 0;
-- 
GitLab


From 2d1f383244ed271efd019236b78523c403d19818 Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 25 Dec 2023 12:23:12 -0800
Subject: [PATCH 2096/4076] Staging: rtl8192e: Rename function
 rtllib_EnableNetMonitorMode()

Rename function rtllib_EnableNetMonitorModeto to rtllib_enable_net_monitor_mode
to fix checkpatch warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231225202314.31869-5-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h            | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c    | 2 +-
 drivers/staging/rtl8192e/rtllib_softmac_wx.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index a3c5dbaeba2d4..aff2383b24e0c 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1677,7 +1677,7 @@ void rtllib_sta_ps_send_pspoll_frame(struct rtllib_device *ieee);
 void rtllib_start_protocol(struct rtllib_device *ieee);
 void rtllib_stop_protocol(struct rtllib_device *ieee);
 
-void rtllib_EnableNetMonitorMode(struct net_device *dev, bool init_state);
+void rtllib_enable_net_monitor_mode(struct net_device *dev, bool init_state);
 void rtllib_disable_net_monitor_mode(struct net_device *dev, bool init_state);
 
 void rtllib_softmac_stop_protocol(struct rtllib_device *ieee);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 0971059c7572d..e1f9ea615517f 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -348,7 +348,7 @@ static inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee)
 }
 
 /* Enables network monitor mode, all rx packets will be received. */
-void rtllib_EnableNetMonitorMode(struct net_device *dev,
+void rtllib_enable_net_monitor_mode(struct net_device *dev,
 		bool init_state)
 {
 	struct rtllib_device *ieee = netdev_priv_rsl(dev);
diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
index eb331cbb98501..2afa701e5445b 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c
@@ -266,7 +266,7 @@ int rtllib_wx_set_mode(struct rtllib_device *ieee, struct iw_request_info *a,
 
 	if (wrqu->mode == IW_MODE_MONITOR) {
 		ieee->dev->type = ARPHRD_IEEE80211;
-		rtllib_EnableNetMonitorMode(ieee->dev, false);
+		rtllib_enable_net_monitor_mode(ieee->dev, false);
 	} else {
 		ieee->dev->type = ARPHRD_ETHER;
 		if (ieee->iw_mode == IW_MODE_MONITOR)
-- 
GitLab


From 9cbaf63c14002dfc01145475b93474aa72d641ba Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 25 Dec 2023 12:23:13 -0800
Subject: [PATCH 2097/4076] Staging: rtl8192e: Rename variable
 bIsAggregateFrame

Rename variable bIsAggregateFrame to is_aggregate_frame to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231225202314.31869-6-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h         |  2 +-
 drivers/staging/rtl8192e/rtllib_rx.c      | 10 +++++-----
 drivers/staging/rtl8192e/rtllib_softmac.c |  2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index aff2383b24e0c..17ad711a7f95e 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1402,7 +1402,7 @@ struct rtllib_device {
 	bool FwRWRF;
 
 	struct rt_link_detect link_detect_info;
-	bool bIsAggregateFrame;
+	bool is_aggregate_frame;
 	struct rt_pwr_save_ctrl pwr_save_ctrl;
 
 	/* used if IEEE_SOFTMAC_TX_QUEUE is set */
diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index 6cb71eba04a78..4df20f4d6bf91 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -730,7 +730,7 @@ static u8 parse_subframe(struct rtllib_device *ieee, struct sk_buff *skb,
 
 	u16		LLCOffset = sizeof(struct ieee80211_hdr_3addr);
 	u16		ChkLength;
-	bool		bIsAggregateFrame = false;
+	bool		is_aggregate_frame = false;
 	u16		nSubframe_Length;
 	u8		nPadding_Length = 0;
 	u16		SeqNum = 0;
@@ -739,7 +739,7 @@ static u8 parse_subframe(struct rtllib_device *ieee, struct sk_buff *skb,
 	SeqNum = WLAN_GET_SEQ_SEQ(le16_to_cpu(hdr->seq_ctrl));
 	if ((RTLLIB_QOS_HAS_SEQ(fc)) &&
 	   (((union frameqos *)(skb->data + RTLLIB_3ADDR_LEN))->field.reserved))
-		bIsAggregateFrame = true;
+		is_aggregate_frame = true;
 
 	if (RTLLIB_QOS_HAS_SEQ(fc))
 		LLCOffset += 2;
@@ -752,8 +752,8 @@ static u8 parse_subframe(struct rtllib_device *ieee, struct sk_buff *skb,
 		return 0;
 
 	skb_pull(skb, LLCOffset);
-	ieee->bIsAggregateFrame = bIsAggregateFrame;
-	if (!bIsAggregateFrame) {
+	ieee->is_aggregate_frame = is_aggregate_frame;
+	if (!is_aggregate_frame) {
 		rxb->nr_subframes = 1;
 
 		/* altered by clark 3/30/2010
@@ -1358,7 +1358,7 @@ static int rtllib_rx_InfraAdhoc(struct rtllib_device *ieee, struct sk_buff *skb,
 	/* Update WAPI PN */
 
 	/* Check if leave LPS */
-	if (ieee->bIsAggregateFrame)
+	if (ieee->is_aggregate_frame)
 		nr_subframes = rxb->nr_subframes;
 	else
 		nr_subframes = 1;
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index e1f9ea615517f..a06201b758e8c 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2079,7 +2079,7 @@ int rtllib_softmac_init(struct rtllib_device *ieee)
 	ieee->link_detect_info.num_tx_ok_in_period = 0;
 	ieee->link_detect_info.num_rx_ok_in_period = 0;
 	ieee->link_detect_info.NumRxUnicastOkInPeriod = 0;
-	ieee->bIsAggregateFrame = false;
+	ieee->is_aggregate_frame = false;
 	ieee->assoc_id = 0;
 	ieee->queue_stop = 0;
 	ieee->scanning_continue = 0;
-- 
GitLab


From 0a46c21c21c1f1c9a65e29eaae243d0f240bbd6b Mon Sep 17 00:00:00 2001
From: Tree Davies <tdavies@darkphysics.net>
Date: Mon, 25 Dec 2023 12:23:14 -0800
Subject: [PATCH 2098/4076] Staging: rtl8192e: Rename variable OpMode

Rename variable OpMode to op_mode to fix checkpatch
warning Avoid CamelCase.

Signed-off-by: Tree Davies <tdavies@darkphysics.net>
Link: https://lore.kernel.org/r/20231225202314.31869-7-tdavies@darkphysics.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 10 +++++-----
 drivers/staging/rtl8192e/rtllib.h              |  2 +-
 drivers/staging/rtl8192e/rtllib_softmac.c      |  8 ++++----
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index ed0c152c2477d..c7a2eae2fdb90 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -51,12 +51,12 @@ void rtl92e_set_reg(struct net_device *dev, u8 variable, u8 *val)
 
 	case HW_VAR_MEDIA_STATUS:
 	{
-		enum rt_op_mode OpMode = *((enum rt_op_mode *)(val));
+		enum rt_op_mode op_mode = *((enum rt_op_mode *)(val));
 		u8 btMsr = rtl92e_readb(dev, MSR);
 
 		btMsr &= 0xfc;
 
-		switch (OpMode) {
+		switch (op_mode) {
 		case RT_OP_MODE_INFRASTRUCTURE:
 			btMsr |= MSR_INFRA;
 			break;
@@ -1693,12 +1693,12 @@ void rtl92e_stop_adapter(struct net_device *dev, bool reset)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
 	int i;
-	u8	OpMode;
+	u8	op_mode;
 	u8	u1bTmp;
 	u32	ulRegRead;
 
-	OpMode = RT_OP_MODE_NO_LINK;
-	priv->rtllib->SetHwRegHandler(dev, HW_VAR_MEDIA_STATUS, &OpMode);
+	op_mode = RT_OP_MODE_NO_LINK;
+	priv->rtllib->SetHwRegHandler(dev, HW_VAR_MEDIA_STATUS, &op_mode);
 
 	if (!priv->rtllib->bSupportRemoteWakeUp) {
 		u1bTmp = 0x0;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 17ad711a7f95e..7b39a1987fdd6 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1187,7 +1187,7 @@ struct rtllib_device {
 	unsigned long status;
 	u8	CntAfterLink;
 
-	enum rt_op_mode OpMode;
+	enum rt_op_mode op_mode;
 
 	/* The last AssocReq/Resp IEs */
 	u8 *assocreq_ies, *assocresp_ies;
diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index a06201b758e8c..b9278b26accd8 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -2245,7 +2245,7 @@ static void rtllib_MlmeDisassociateRequest(struct rtllib_device *rtllib,
 					   u8 *asSta, u8 asRsn)
 {
 	u8 i;
-	u8	OpMode;
+	u8	op_mode;
 
 	RemovePeerTS(rtllib, asSta);
 
@@ -2254,10 +2254,10 @@ static void rtllib_MlmeDisassociateRequest(struct rtllib_device *rtllib,
 
 		for (i = 0; i < 6; i++)
 			rtllib->current_network.bssid[i] = 0x22;
-		OpMode = RT_OP_MODE_NO_LINK;
-		rtllib->OpMode = RT_OP_MODE_NO_LINK;
+		op_mode = RT_OP_MODE_NO_LINK;
+		rtllib->op_mode = RT_OP_MODE_NO_LINK;
 		rtllib->SetHwRegHandler(rtllib->dev, HW_VAR_MEDIA_STATUS,
-					(u8 *)(&OpMode));
+					(u8 *)(&op_mode));
 		rtllib_disassociate(rtllib);
 
 		rtllib->SetHwRegHandler(rtllib->dev, HW_VAR_BSSID,
-- 
GitLab


From db2292b01b799e926abfdbd6fafa1f27f0d0e457 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 15:07:23 +0100
Subject: [PATCH 2099/4076] PM: clk: make pm_clk_add_notifier() take a const
 pointer

The driver core wants to work with const struct bus_type, so there's no
reason that pm_clk_add_notifier() should not also do the same thing,
considering that it just passes the pointer off to the driver core which
is expecting a const *.

Cc: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/2023121922-triumph-exploit-f545@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/power/clock_ops.c | 2 +-
 include/linux/pm_clock.h       | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 4110c19c08dcd..e18ba676cdf64 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -793,7 +793,7 @@ static int pm_clk_notify(struct notifier_block *nb,
  * the remaining members of @clknb should be populated prior to calling this
  * routine.
  */
-void pm_clk_add_notifier(struct bus_type *bus,
+void pm_clk_add_notifier(const struct bus_type *bus,
 				 struct pm_clk_notifier_block *clknb)
 {
 	if (!bus || !clknb)
diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h
index ada3a0ab10bf2..68669ce187204 100644
--- a/include/linux/pm_clock.h
+++ b/include/linux/pm_clock.h
@@ -91,10 +91,10 @@ static inline int devm_pm_clk_create(struct device *dev)
 #endif
 
 #ifdef CONFIG_HAVE_CLK
-extern void pm_clk_add_notifier(struct bus_type *bus,
+extern void pm_clk_add_notifier(const struct bus_type *bus,
 					struct pm_clk_notifier_block *clknb);
 #else
-static inline void pm_clk_add_notifier(struct bus_type *bus,
+static inline void pm_clk_add_notifier(const struct bus_type *bus,
 					struct pm_clk_notifier_block *clknb)
 {
 }
-- 
GitLab


From e76933a9bfa9b7f28a387f2e13cb3e689adc200d Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 15:06:19 +0100
Subject: [PATCH 2100/4076] maple: make maple_bus_type static and const

There is no need to export maple_bus_type as no one uses it outside of
maple.c, so make it static, AND make it const as it can be read-only as
no one modifies it.

Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: <linux-sh@vger.kernel.org>
Link: https://lore.kernel.org/r/2023121918-rejoicing-frostlike-d976@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/sh/maple/maple.c | 4 ++--
 include/linux/maple.h    | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index e05473c5c267f..16018009a5a67 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -59,6 +59,7 @@ struct maple_device_specify {
 static bool checked[MAPLE_PORTS];
 static bool empty[MAPLE_PORTS];
 static struct maple_device *baseunits[MAPLE_PORTS];
+static const struct bus_type maple_bus_type;
 
 /**
  * maple_driver_register - register a maple driver
@@ -773,11 +774,10 @@ static struct maple_driver maple_unsupported_device = {
 /*
  * maple_bus_type - core maple bus structure
  */
-struct bus_type maple_bus_type = {
+static const struct bus_type maple_bus_type = {
 	.name = "maple",
 	.match = maple_match_bus_driver,
 };
-EXPORT_SYMBOL_GPL(maple_bus_type);
 
 static struct device maple_bus = {
 	.init_name = "maple",
diff --git a/include/linux/maple.h b/include/linux/maple.h
index 9b140272ee165..9aae44efcfd4c 100644
--- a/include/linux/maple.h
+++ b/include/linux/maple.h
@@ -5,7 +5,6 @@
 #include <mach/maple.h>
 
 struct device;
-extern struct bus_type maple_bus_type;
 
 /* Maple Bus command and response codes */
 enum maple_code {
-- 
GitLab


From 86438841e48f6361f0a6a04805b7d7813738761f Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:41:42 +0100
Subject: [PATCH 2101/4076] dma-debug: make dma_debug_add_bus take a const
 pointer

The driver core now can handle a const struct bus_type pointer, and the
dma_debug_add_bus() call just passes on the pointer give to it to the
driver core, so make this pointer const as well to allow everyone to use
read-only struct bus_type pointers going forward.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc:  <iommu@lists.linux.dev>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/2023121941-dejected-nugget-681e@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/dma-map-ops.h | 4 ++--
 kernel/dma/debug.c          | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f2fc203fb8a1a..e401f824a007f 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -443,10 +443,10 @@ static inline void arch_teardown_dma_ops(struct device *dev)
 #endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
 
 #ifdef CONFIG_DMA_API_DEBUG
-void dma_debug_add_bus(struct bus_type *bus);
+void dma_debug_add_bus(const struct bus_type *bus);
 void debug_dma_dump_mappings(struct device *dev);
 #else
-static inline void dma_debug_add_bus(struct bus_type *bus)
+static inline void dma_debug_add_bus(const struct bus_type *bus)
 {
 }
 static inline void debug_dma_dump_mappings(struct device *dev)
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 3de494375b7b3..1a5c86dd87d59 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -876,7 +876,7 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti
 	return 0;
 }
 
-void dma_debug_add_bus(struct bus_type *bus)
+void dma_debug_add_bus(const struct bus_type *bus)
 {
 	struct notifier_block *nb;
 
-- 
GitLab


From 2e9bf5cc912365d20e3255a0779f5516157b923e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 19:33:06 +0100
Subject: [PATCH 2102/4076] locomo: make locomo_bus_type constant and static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that the driver core can properly handle constant struct bus_type,
move the locomo_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

It's also never used outside of arch/arm/common/locomo.c so make it
static and don't export it as no one is using it.

Cc: Russell King <linux@armlinux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc:  <linux-arm-kernel@lists.infradead.org>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/2023121905-idiom-opossum-1ba3@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm/common/locomo.c               | 4 +++-
 arch/arm/include/asm/hardware/locomo.h | 2 --
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 70480dd9e96db..6d0c9f7268bad 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -68,6 +68,8 @@ struct locomo {
 #endif
 };
 
+static const struct bus_type locomo_bus_type;
+
 struct locomo_dev_info {
 	unsigned long	offset;
 	unsigned long	length;
@@ -842,7 +844,7 @@ static void locomo_bus_remove(struct device *dev)
 		drv->remove(ldev);
 }
 
-struct bus_type locomo_bus_type = {
+static const struct bus_type locomo_bus_type = {
 	.name		= "locomo-bus",
 	.match		= locomo_match,
 	.probe		= locomo_bus_probe,
diff --git a/arch/arm/include/asm/hardware/locomo.h b/arch/arm/include/asm/hardware/locomo.h
index aaaedafef7cce..9fd9ad5d92020 100644
--- a/arch/arm/include/asm/hardware/locomo.h
+++ b/arch/arm/include/asm/hardware/locomo.h
@@ -158,8 +158,6 @@
 #define LOCOMO_LPT_TOH(TOH)	((TOH & 0x7) << 4)
 #define LOCOMO_LPT_TOL(TOL)	((TOL & 0x7))
 
-extern struct bus_type locomo_bus_type;
-
 #define LOCOMO_DEVID_KEYBOARD	0
 #define LOCOMO_DEVID_FRONTLIGHT	1
 #define LOCOMO_DEVID_BACKLIGHT	2
-- 
GitLab


From 730e12fbec53ab59dd807d981a204258a4cfb29a Mon Sep 17 00:00:00 2001
From: Wesley Cheng <quic_wcheng@quicinc.com>
Date: Wed, 6 Dec 2023 12:18:14 -0800
Subject: [PATCH 2103/4076] usb: dwc3: gadget: Handle EP0 request dequeuing
 properly

Current EP0 dequeue path will share the same as other EPs.  However, there
are some special considerations that need to be made for EP0 transfers:

  - EP0 transfers never transition into the started_list
  - EP0 only has one active request at a time

In case there is a vendor specific control message for a function over USB
FFS, then there is no guarantee on the timeline which the DATA/STATUS stage
is responded to.  While this occurs, any attempt to end transfers on
non-control EPs will end up having the DWC3_EP_DELAY_STOP flag set, and
defer issuing of the end transfer command.  If the USB FFS application
decides to timeout the control transfer, or if USB FFS AIO path exits, the
USB FFS driver will issue a call to usb_ep_dequeue() for the ep0 request.

In case of the AIO exit path, the AIO FS blocks until all pending USB
requests utilizing the AIO path is completed.  However, since the dequeue
of ep0 req does not happen properly, all non-control EPs with the
DWC3_EP_DELAY_STOP flag set will not be handled, and the AIO exit path will
be stuck waiting for the USB FFS data endpoints to receive a completion
callback.

Fix is to utilize dwc3_ep0_reset_state() in the dequeue API to ensure EP0
is brought back to the SETUP state, and ensures that any deferred end
transfer commands are handled.  This also will end any active transfers
on EP0, compared to the previous implementation which directly called
giveback only.

Fixes: fcd2def66392 ("usb: dwc3: gadget: Refactor dwc3_gadget_ep_dequeue")
Cc: stable <stable@kernel.org>
Signed-off-by: Wesley Cheng <quic_wcheng@quicinc.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/20231206201814.32664-1-quic_wcheng@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 858fe4c299b7a..88d8d589f0148 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2103,7 +2103,17 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 
 	list_for_each_entry(r, &dep->pending_list, list) {
 		if (r == req) {
-			dwc3_gadget_giveback(dep, req, -ECONNRESET);
+			/*
+			 * Explicitly check for EP0/1 as dequeue for those
+			 * EPs need to be handled differently.  Control EP
+			 * only deals with one USB req, and giveback will
+			 * occur during dwc3_ep0_stall_and_restart().  EP0
+			 * requests are never added to started_list.
+			 */
+			if (dep->number > 1)
+				dwc3_gadget_giveback(dep, req, -ECONNRESET);
+			else
+				dwc3_ep0_reset_state(dwc);
 			goto out;
 		}
 	}
-- 
GitLab


From 738ec5ab7acca7ee5856e36a5a6a0c41201fe88f Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Mon, 18 Dec 2023 15:47:30 +0800
Subject: [PATCH 2104/4076] usb: ueagle-atm: Use wait_event_freezable_timeout()
 in uea_wait()

A freezable kernel thread can enter frozen state during freezing by
either calling try_to_freeze() or using wait_event_freezable() and its
variants. So for the following snippet of code in a kernel thread loop:
  wait_event_interruptible_timeout();
  try_to_freeze();

We can change it to a simple wait_event_freezable_timeout() and
then eliminate a function call.

Signed-off-by: Kevin Hao <haokexin@gmail.com>
Link: https://lore.kernel.org/r/20231218074730.1898699-1-haokexin@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/atm/ueagle-atm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c
index 8d5580d8d20a8..16703815be0c4 100644
--- a/drivers/usb/atm/ueagle-atm.c
+++ b/drivers/usb/atm/ueagle-atm.c
@@ -546,7 +546,7 @@ MODULE_PARM_DESC(annex,
 
 #define uea_wait(sc, cond, timeo) \
 ({ \
-	int _r = wait_event_interruptible_timeout(sc->sync_q, \
+	int _r = wait_event_freezable_timeout(sc->sync_q, \
 			(cond) || kthread_should_stop(), timeo); \
 	if (kthread_should_stop()) \
 		_r = -ENODEV; \
@@ -1896,7 +1896,6 @@ static int uea_kthread(void *data)
 			ret = sc->stat(sc);
 		if (ret != -EAGAIN)
 			uea_wait(sc, 0, msecs_to_jiffies(1000));
-		try_to_freeze();
 	}
 	uea_leaves(INS_TO_USBDEV(sc));
 	return ret;
-- 
GitLab


From e9d40b215e38480fd94c66b06d79045717a59e9c Mon Sep 17 00:00:00 2001
From: Uttkarsh Aggarwal <quic_uaggarwa@quicinc.com>
Date: Fri, 22 Dec 2023 15:17:04 +0530
Subject: [PATCH 2105/4076] usb: dwc: ep0: Update request status in
 dwc3_ep0_stall_restart

Current implementation blocks the running operations when Plug-out and
Plug-In is performed continuously, process gets stuck in
dwc3_thread_interrupt().

Code Flow:

	CPU1

	->Gadget_start
	->dwc3_interrupt
	->dwc3_thread_interrupt
	->dwc3_process_event_buf
	->dwc3_process_event_entry
	->dwc3_endpoint_interrupt
	->dwc3_ep0_interrupt
	->dwc3_ep0_inspect_setup
	->dwc3_ep0_stall_and_restart

By this time if pending_list is not empty, it will get the next request
on the given list and calls dwc3_gadget_giveback which will unmap request
and call its complete() callback to notify upper layers that it has
completed. Currently dwc3_gadget_giveback status is set to -ECONNRESET,
whereas it should be -ESHUTDOWN based on condition if not dwc->connected
is true.

Cc:  <stable@vger.kernel.org>
Fixes: d742220b3577 ("usb: dwc3: ep0: giveback requests on stall_and_restart")
Signed-off-by: Uttkarsh Aggarwal <quic_uaggarwa@quicinc.com>
Link: https://lore.kernel.org/r/20231222094704.20276-1-quic_uaggarwa@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/ep0.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index b942432372937..6ae8a36f21cf6 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -238,7 +238,10 @@ void dwc3_ep0_stall_and_restart(struct dwc3 *dwc)
 		struct dwc3_request	*req;
 
 		req = next_request(&dep->pending_list);
-		dwc3_gadget_giveback(dep, req, -ECONNRESET);
+		if (!dwc->connected)
+			dwc3_gadget_giveback(dep, req, -ESHUTDOWN);
+		else
+			dwc3_gadget_giveback(dep, req, -ECONNRESET);
 	}
 
 	dwc->eps[0]->trb_enqueue = 0;
-- 
GitLab


From 91736d0619eb4083f33ae737b9d9763fc6b196ed Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Tue, 19 Dec 2023 09:45:59 +0530
Subject: [PATCH 2106/4076] usb: dwc3: core: set force_gen1 bit in USB31
 devices if max speed is SS

Currently for dwc3_usb31 controller, if maximum_speed is limited to
super-speed in DT, then device mode is limited to SS, but host mode
still works in SSP.

The documentation for max-speed property is as follows:

"Tells USB controllers we want to work up to a certain speed.
Incase  this isn't passed via DT, USB controllers should default to
their maximum HW capability."

It doesn't specify that the property is only for device mode.
There are cases where we need to limit the host's maximum speed to
SuperSpeed only. Use this property for host mode to contrain host's
speed to SuperSpeed.

Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/20231219041559.15789-1-quic_kriskura@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c | 12 ++++++++++++
 drivers/usb/dwc3/core.h |  5 +++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index f50b5575d588a..4447ef2cbc0f0 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1330,6 +1330,18 @@ static int dwc3_core_init(struct dwc3 *dwc)
 
 	dwc3_config_threshold(dwc);
 
+	/*
+	 * Modify this for all supported Super Speed ports when
+	 * multiport support is added.
+	 */
+	if (hw_mode != DWC3_GHWPARAMS0_MODE_GADGET &&
+	    (DWC3_IP_IS(DWC31)) &&
+	    dwc->maximum_speed == USB_SPEED_SUPER) {
+		reg = dwc3_readl(dwc->regs, DWC3_LLUCTL);
+		reg |= DWC3_LLUCTL_FORCE_GEN1;
+		dwc3_writel(dwc->regs, DWC3_LLUCTL, reg);
+	}
+
 	return 0;
 
 err_power_off_phy:
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index efe6caf4d0e87..e120611a5174f 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -172,6 +172,8 @@
 #define DWC3_OEVTEN		0xcc0C
 #define DWC3_OSTS		0xcc10
 
+#define DWC3_LLUCTL		0xd024
+
 /* Bit fields */
 
 /* Global SoC Bus Configuration INCRx Register 0 */
@@ -657,6 +659,9 @@
 #define DWC3_OSTS_VBUSVLD		BIT(1)
 #define DWC3_OSTS_CONIDSTS		BIT(0)
 
+/* Force Gen1 speed on Gen2 link */
+#define DWC3_LLUCTL_FORCE_GEN1		BIT(10)
+
 /* Structures */
 
 struct dwc3_trb;
-- 
GitLab


From 6d6887c42e946f43bed2e64571a40c8476a1e4a9 Mon Sep 17 00:00:00 2001
From: Yinbo Zhu <zhuyinbo@loongson.cn>
Date: Thu, 28 Dec 2023 15:11:13 +0800
Subject: [PATCH 2107/4076] usb: xhci-plat: fix usb disconnect issue after s4

The xhci retaining bogus hardware states cause usb disconnect devices
connected before hibernation(s4) and refer to the commit 'f3d478858be
("usb: ohci-platform: fix usb disconnect issue after s4")' which set
flag "hibernated" as true when resume-from-hibernation and that the
drivers will reset the hardware to get rid of any existing state and
make sure resume from hibernation re-enumerates everything for xhci.

Signed-off-by: Yinbo Zhu <zhuyinbo@loongson.cn>
Link: https://lore.kernel.org/r/20231228071113.1719-1-zhuyinbo@loongson.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-plat.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index e46175c38570b..f04fde19f5514 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -436,7 +436,7 @@ void xhci_plat_remove(struct platform_device *dev)
 }
 EXPORT_SYMBOL_GPL(xhci_plat_remove);
 
-static int __maybe_unused xhci_plat_suspend(struct device *dev)
+static int xhci_plat_suspend(struct device *dev)
 {
 	struct usb_hcd	*hcd = dev_get_drvdata(dev);
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
@@ -464,7 +464,7 @@ static int __maybe_unused xhci_plat_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused xhci_plat_resume(struct device *dev)
+static int xhci_plat_resume_common(struct device *dev, struct pm_message pmsg)
 {
 	struct usb_hcd	*hcd = dev_get_drvdata(dev);
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
@@ -486,7 +486,7 @@ static int __maybe_unused xhci_plat_resume(struct device *dev)
 	if (ret)
 		goto disable_clks;
 
-	ret = xhci_resume(xhci, PMSG_RESUME);
+	ret = xhci_resume(xhci, pmsg);
 	if (ret)
 		goto disable_clks;
 
@@ -505,6 +505,16 @@ disable_clks:
 	return ret;
 }
 
+static int xhci_plat_resume(struct device *dev)
+{
+	return xhci_plat_resume_common(dev, PMSG_RESUME);
+}
+
+static int xhci_plat_restore(struct device *dev)
+{
+	return xhci_plat_resume_common(dev, PMSG_RESTORE);
+}
+
 static int __maybe_unused xhci_plat_runtime_suspend(struct device *dev)
 {
 	struct usb_hcd  *hcd = dev_get_drvdata(dev);
@@ -527,7 +537,12 @@ static int __maybe_unused xhci_plat_runtime_resume(struct device *dev)
 }
 
 const struct dev_pm_ops xhci_plat_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(xhci_plat_suspend, xhci_plat_resume)
+	.suspend = pm_sleep_ptr(xhci_plat_suspend),
+	.resume = pm_sleep_ptr(xhci_plat_resume),
+	.freeze = pm_sleep_ptr(xhci_plat_suspend),
+	.thaw = pm_sleep_ptr(xhci_plat_resume),
+	.poweroff = pm_sleep_ptr(xhci_plat_suspend),
+	.restore = pm_sleep_ptr(xhci_plat_restore),
 
 	SET_RUNTIME_PM_OPS(xhci_plat_runtime_suspend,
 			   xhci_plat_runtime_resume,
-- 
GitLab


From 501b15207138e3cf85c8413fbbb746f6ee21b0a1 Mon Sep 17 00:00:00 2001
From: Kyle Tso <kyletso@google.com>
Date: Sat, 16 Dec 2023 18:46:29 +0800
Subject: [PATCH 2108/4076] dt-bindings: connector: Add child nodes for
 multiple PD capabilities

Commit 662a60102c12 ("usb: typec: Separate USB Power Delivery from USB
Type-C") allows userspace to configure the PD of a port by selecting
different set of predefined PD capabilities. Define the PD capability
sets in DT for better configurability in device modules.

Define an optional child node "capabilities" to contain multiple USB
Power Delivery capabilities.

Define child nodes with pattern (e.g. caps-0, caps-1) under
"capabilities". Each node contains PDO data of a selectable Power
Delivery capability.

Also define common properties for source-pdos, sink-pdos, and
op-sink-microwatt that can be referenced.

Signed-off-by: Kyle Tso <kyletso@google.com>
Link: https://lore.kernel.org/r/20231205030114.1349089-2-kyletso@google.com
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231216104630.2720818-2-kyletso@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../bindings/connector/usb-connector.yaml     | 81 ++++++++++++-------
 1 file changed, 50 insertions(+), 31 deletions(-)

diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml
index f5966b3a2d9ae..fb216ce68bb35 100644
--- a/Documentation/devicetree/bindings/connector/usb-connector.yaml
+++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml
@@ -66,7 +66,6 @@ properties:
       Particularly, if use an output GPIO to control a VBUS regulator, should
       model it as a regulator. See bindings/regulator/fixed-regulator.yaml
 
-  # The following are optional properties for "usb-c-connector".
   power-role:
     description: Determines the power role that the Type C connector will
       support. "dual" refers to Dual Role Port (DRP).
@@ -119,30 +118,6 @@ properties:
 
   # The following are optional properties for "usb-c-connector" with power
   # delivery support.
-  source-pdos:
-    description: An array of u32 with each entry providing supported power
-      source data object(PDO), the detailed bit definitions of PDO can be found
-      in "Universal Serial Bus Power Delivery Specification" chapter 6.4.1.2
-      Source_Capabilities Message, the order of each entry(PDO) should follow
-      the PD spec chapter 6.4.1. Required for power source and power dual role.
-      User can specify the source PDO array via PDO_FIXED/BATT/VAR/PPS_APDO()
-      defined in dt-bindings/usb/pd.h.
-    minItems: 1
-    maxItems: 7
-    $ref: /schemas/types.yaml#/definitions/uint32-array
-
-  sink-pdos:
-    description: An array of u32 with each entry providing supported power sink
-      data object(PDO), the detailed bit definitions of PDO can be found in
-      "Universal Serial Bus Power Delivery Specification" chapter 6.4.1.3
-      Sink Capabilities Message, the order of each entry(PDO) should follow the
-      PD spec chapter 6.4.1. Required for power sink and power dual role. User
-      can specify the sink PDO array via PDO_FIXED/BATT/VAR/PPS_APDO() defined
-      in dt-bindings/usb/pd.h.
-    minItems: 1
-    maxItems: 7
-    $ref: /schemas/types.yaml#/definitions/uint32-array
-
   sink-vdos:
     description: An array of u32 with each entry, a Vendor Defined Message Object (VDO),
       providing additional information corresponding to the product, the detailed bit
@@ -166,11 +141,6 @@ properties:
     maxItems: 6
     $ref: /schemas/types.yaml#/definitions/uint32-array
 
-  op-sink-microwatt:
-    description: Sink required operating power in microwatt, if source can't
-      offer the power, Capability Mismatch is set. Required for power sink and
-      power dual role.
-
   accessory-mode-audio:
     type: boolean
     description: Whether the device supports Audio Adapter Accessory Mode. This
@@ -269,6 +239,20 @@ properties:
       SNK_READY for non-pd link.
     type: boolean
 
+  capabilities:
+    description: A child node to contain all the selectable USB Power Delivery capabilities.
+    type: object
+
+    patternProperties:
+      "^caps-[0-9]+$":
+        description: Child nodes under "capabilities" node. Each node contains a selectable USB
+          Power Delivery capability.
+        type: object
+        $ref: "#/$defs/capabilities"
+        unevaluatedProperties: false
+
+    additionalProperties: false
+
 dependencies:
   sink-vdos-v1: [ sink-vdos ]
   sink-vdos: [ sink-vdos-v1 ]
@@ -276,7 +260,42 @@ dependencies:
 required:
   - compatible
 
+$defs:
+  capabilities:
+    type: object
+
+    properties:
+      source-pdos:
+        description: An array of u32 with each entry providing supported power
+          source data object(PDO), the detailed bit definitions of PDO can be found
+          in "Universal Serial Bus Power Delivery Specification" chapter 6.4.1.2
+          Source_Capabilities Message, the order of each entry(PDO) should follow
+          the PD spec chapter 6.4.1. Required for power source and power dual role.
+          User can specify the source PDO array via PDO_FIXED/BATT/VAR/PPS_APDO()
+          defined in dt-bindings/usb/pd.h.
+        minItems: 1
+        maxItems: 7
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+
+      sink-pdos:
+        description: An array of u32 with each entry providing supported power sink
+          data object(PDO), the detailed bit definitions of PDO can be found in
+          "Universal Serial Bus Power Delivery Specification" chapter 6.4.1.3
+          Sink Capabilities Message, the order of each entry(PDO) should follow the
+          PD spec chapter 6.4.1. Required for power sink and power dual role. User
+          can specify the sink PDO array via PDO_FIXED/BATT/VAR/PPS_APDO() defined
+          in dt-bindings/usb/pd.h.
+        minItems: 1
+        maxItems: 7
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+
+      op-sink-microwatt:
+        description: Sink required operating power in microwatt, if source can't
+          offer the power, Capability Mismatch is set. Required for power sink and
+          power dual role.
+
 allOf:
+  - $ref: "#/$defs/capabilities"
   - if:
       properties:
         compatible:
@@ -305,7 +324,7 @@ anyOf:
         - typec-power-opmode
         - new-source-frs-typec-current
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   # Micro-USB connector with HS lines routed via controller (MUIC).
-- 
GitLab


From cd099cde4ed264403b434d8344994f97ac2a4349 Mon Sep 17 00:00:00 2001
From: Kyle Tso <kyletso@google.com>
Date: Sat, 16 Dec 2023 18:46:30 +0800
Subject: [PATCH 2109/4076] usb: typec: tcpm: Support multiple capabilities

Refactor tcpm_fw_get_caps to support the multiple pd capabilities got
from fwnode. For backward compatibility, the original single capability
is still applicable. The fetched data is stored in the newly defined
structure "pd_data" and there is an array "pd_list" to store the
pointers to them. A dedicated array "pds" is used to store the handles
of the registered usb_power_delivery instances.

Also implement the .pd_get and .pd_set ops which are introduced in
commit a7cff92f0635 ("usb: typec: USB Power Delivery helpers for ports
and partners"). Once the .pd_set is called, the current capability will
be updated and state machine will re-negotiate the power contract if
possible.

Signed-off-by: Kyle Tso <kyletso@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231216104630.2720818-3-kyletso@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 387 ++++++++++++++++++++++++++--------
 1 file changed, 298 insertions(+), 89 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index cf70f1cf2f618..5945e3a2b0f78 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -297,6 +297,15 @@ struct pd_pps_data {
 	bool active;
 };
 
+struct pd_data {
+	struct usb_power_delivery *pd;
+	struct usb_power_delivery_capabilities *source_cap;
+	struct usb_power_delivery_capabilities_desc source_desc;
+	struct usb_power_delivery_capabilities *sink_cap;
+	struct usb_power_delivery_capabilities_desc sink_desc;
+	unsigned int operating_snk_mw;
+};
+
 struct tcpm_port {
 	struct device *dev;
 
@@ -398,12 +407,14 @@ struct tcpm_port {
 	unsigned int rx_msgid;
 
 	/* USB PD objects */
-	struct usb_power_delivery *pd;
+	struct usb_power_delivery **pds;
+	struct pd_data **pd_list;
 	struct usb_power_delivery_capabilities *port_source_caps;
 	struct usb_power_delivery_capabilities *port_sink_caps;
 	struct usb_power_delivery *partner_pd;
 	struct usb_power_delivery_capabilities *partner_source_caps;
 	struct usb_power_delivery_capabilities *partner_sink_caps;
+	struct usb_power_delivery *selected_pd;
 
 	/* Partner capabilities/requests */
 	u32 sink_request;
@@ -413,6 +424,7 @@ struct tcpm_port {
 	unsigned int nr_sink_caps;
 
 	/* Local capabilities */
+	unsigned int pd_count;
 	u32 src_pdo[PDO_MAX_OBJECTS];
 	unsigned int nr_src_pdo;
 	u32 snk_pdo[PDO_MAX_OBJECTS];
@@ -6060,12 +6072,114 @@ port_unlock:
 	return 0;
 }
 
+static struct pd_data *tcpm_find_pd_data(struct tcpm_port *port, struct usb_power_delivery *pd)
+{
+	int i;
+
+	for (i = 0; port->pd_list[i]; i++) {
+		if (port->pd_list[i]->pd == pd)
+			return port->pd_list[i];
+	}
+
+	return ERR_PTR(-ENODATA);
+}
+
+static struct usb_power_delivery **tcpm_pd_get(struct typec_port *p)
+{
+	struct tcpm_port *port = typec_get_drvdata(p);
+
+	return port->pds;
+}
+
+static int tcpm_pd_set(struct typec_port *p, struct usb_power_delivery *pd)
+{
+	struct tcpm_port *port = typec_get_drvdata(p);
+	struct pd_data *data;
+	int i, ret = 0;
+
+	mutex_lock(&port->lock);
+
+	if (port->selected_pd == pd)
+		goto unlock;
+
+	data = tcpm_find_pd_data(port, pd);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		goto unlock;
+	}
+
+	if (data->sink_desc.pdo[0]) {
+		for (i = 0; i < PDO_MAX_OBJECTS && data->sink_desc.pdo[i]; i++)
+			port->snk_pdo[i] = data->sink_desc.pdo[i];
+		port->nr_snk_pdo = i + 1;
+		port->operating_snk_mw = data->operating_snk_mw;
+	}
+
+	if (data->source_desc.pdo[0]) {
+		for (i = 0; i < PDO_MAX_OBJECTS && data->source_desc.pdo[i]; i++)
+			port->snk_pdo[i] = data->source_desc.pdo[i];
+		port->nr_src_pdo = i + 1;
+	}
+
+	switch (port->state) {
+	case SRC_UNATTACHED:
+	case SRC_ATTACH_WAIT:
+	case SRC_TRYWAIT:
+		tcpm_set_cc(port, tcpm_rp_cc(port));
+		break;
+	case SRC_SEND_CAPABILITIES:
+	case SRC_SEND_CAPABILITIES_TIMEOUT:
+	case SRC_NEGOTIATE_CAPABILITIES:
+	case SRC_READY:
+	case SRC_WAIT_NEW_CAPABILITIES:
+		port->caps_count = 0;
+		port->upcoming_state = SRC_SEND_CAPABILITIES;
+		ret = tcpm_ams_start(port, POWER_NEGOTIATION);
+		if (ret == -EAGAIN) {
+			port->upcoming_state = INVALID_STATE;
+			goto unlock;
+		}
+		break;
+	case SNK_NEGOTIATE_CAPABILITIES:
+	case SNK_NEGOTIATE_PPS_CAPABILITIES:
+	case SNK_READY:
+	case SNK_TRANSITION_SINK:
+	case SNK_TRANSITION_SINK_VBUS:
+		if (port->pps_data.active)
+			port->upcoming_state = SNK_NEGOTIATE_PPS_CAPABILITIES;
+		else if (port->pd_capable)
+			port->upcoming_state = SNK_NEGOTIATE_CAPABILITIES;
+		else
+			break;
+
+		port->update_sink_caps = true;
+
+		ret = tcpm_ams_start(port, POWER_NEGOTIATION);
+		if (ret == -EAGAIN) {
+			port->upcoming_state = INVALID_STATE;
+			goto unlock;
+		}
+		break;
+	default:
+		break;
+	}
+
+	port->port_source_caps = data->source_cap;
+	port->port_sink_caps = data->sink_cap;
+	port->selected_pd = pd;
+unlock:
+	mutex_unlock(&port->lock);
+	return ret;
+}
+
 static const struct typec_operations tcpm_ops = {
 	.try_role = tcpm_try_role,
 	.dr_set = tcpm_dr_set,
 	.pr_set = tcpm_pr_set,
 	.vconn_set = tcpm_vconn_set,
-	.port_type_set = tcpm_port_type_set
+	.port_type_set = tcpm_port_type_set,
+	.pd_get = tcpm_pd_get,
+	.pd_set = tcpm_pd_set
 };
 
 void tcpm_tcpc_reset(struct tcpm_port *port)
@@ -6079,58 +6193,63 @@ EXPORT_SYMBOL_GPL(tcpm_tcpc_reset);
 
 static void tcpm_port_unregister_pd(struct tcpm_port *port)
 {
-	usb_power_delivery_unregister_capabilities(port->port_sink_caps);
+	int i;
+
 	port->port_sink_caps = NULL;
-	usb_power_delivery_unregister_capabilities(port->port_source_caps);
 	port->port_source_caps = NULL;
-	usb_power_delivery_unregister(port->pd);
-	port->pd = NULL;
+	for (i = 0; i < port->pd_count; i++) {
+		usb_power_delivery_unregister_capabilities(port->pd_list[i]->sink_cap);
+		kfree(port->pd_list[i]->sink_cap);
+		usb_power_delivery_unregister_capabilities(port->pd_list[i]->source_cap);
+		kfree(port->pd_list[i]->source_cap);
+		devm_kfree(port->dev, port->pd_list[i]);
+		port->pd_list[i] = NULL;
+		usb_power_delivery_unregister(port->pds[i]);
+		port->pds[i] = NULL;
+	}
 }
 
 static int tcpm_port_register_pd(struct tcpm_port *port)
 {
 	struct usb_power_delivery_desc desc = { port->typec_caps.pd_revision };
-	struct usb_power_delivery_capabilities_desc caps = { };
 	struct usb_power_delivery_capabilities *cap;
-	int ret;
+	int ret, i;
 
 	if (!port->nr_src_pdo && !port->nr_snk_pdo)
 		return 0;
 
-	port->pd = usb_power_delivery_register(port->dev, &desc);
-	if (IS_ERR(port->pd)) {
-		ret = PTR_ERR(port->pd);
-		goto err_unregister;
-	}
-
-	if (port->nr_src_pdo) {
-		memcpy_and_pad(caps.pdo, sizeof(caps.pdo), port->src_pdo,
-			       port->nr_src_pdo * sizeof(u32), 0);
-		caps.role = TYPEC_SOURCE;
-
-		cap = usb_power_delivery_register_capabilities(port->pd, &caps);
-		if (IS_ERR(cap)) {
-			ret = PTR_ERR(cap);
+	for (i = 0; i < port->pd_count; i++) {
+		port->pds[i] = usb_power_delivery_register(port->dev, &desc);
+		if (IS_ERR(port->pds[i])) {
+			ret = PTR_ERR(port->pds[i]);
 			goto err_unregister;
 		}
-
-		port->port_source_caps = cap;
-	}
-
-	if (port->nr_snk_pdo) {
-		memcpy_and_pad(caps.pdo, sizeof(caps.pdo), port->snk_pdo,
-			       port->nr_snk_pdo * sizeof(u32), 0);
-		caps.role = TYPEC_SINK;
-
-		cap = usb_power_delivery_register_capabilities(port->pd, &caps);
-		if (IS_ERR(cap)) {
-			ret = PTR_ERR(cap);
-			goto err_unregister;
+		port->pd_list[i]->pd = port->pds[i];
+
+		if (port->pd_list[i]->source_desc.pdo[0]) {
+			cap = usb_power_delivery_register_capabilities(port->pds[i],
+								&port->pd_list[i]->source_desc);
+			if (IS_ERR(cap)) {
+				ret = PTR_ERR(cap);
+				goto err_unregister;
+			}
+			port->pd_list[i]->source_cap = cap;
 		}
 
-		port->port_sink_caps = cap;
+		if (port->pd_list[i]->sink_desc.pdo[0]) {
+			cap = usb_power_delivery_register_capabilities(port->pds[i],
+								&port->pd_list[i]->sink_desc);
+			if (IS_ERR(cap)) {
+				ret = PTR_ERR(cap);
+				goto err_unregister;
+			}
+			port->pd_list[i]->sink_cap = cap;
+		}
 	}
 
+	port->port_source_caps = port->pd_list[0]->source_cap;
+	port->port_sink_caps = port->pd_list[0]->sink_cap;
+	port->selected_pd = port->pds[0];
 	return 0;
 
 err_unregister:
@@ -6139,13 +6258,15 @@ err_unregister:
 	return ret;
 }
 
-static int tcpm_fw_get_caps(struct tcpm_port *port,
-			    struct fwnode_handle *fwnode)
+static int tcpm_fw_get_caps(struct tcpm_port *port, struct fwnode_handle *fwnode)
 {
+	struct fwnode_handle *capabilities, *child, *caps = NULL;
+	unsigned int nr_src_pdo, nr_snk_pdo;
 	const char *opmode_str;
-	int ret;
+	u32 *src_pdo, *snk_pdo;
+	u32 uw, frs_current;
+	int ret = 0, i;
 	int mode;
-	u32 mw, frs_current;
 
 	if (!fwnode)
 		return -EINVAL;
@@ -6173,28 +6294,10 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 
 	port->port_type = port->typec_caps.type;
 	port->pd_supported = !fwnode_property_read_bool(fwnode, "pd-disable");
-
 	port->slow_charger_loop = fwnode_property_read_bool(fwnode, "slow-charger-loop");
-	if (port->port_type == TYPEC_PORT_SNK)
-		goto sink;
-
-	/* Get Source PDOs for the PD port or Source Rp value for the non-PD port */
-	if (port->pd_supported) {
-		ret = fwnode_property_count_u32(fwnode, "source-pdos");
-		if (ret == 0)
-			return -EINVAL;
-		else if (ret < 0)
-			return ret;
+	port->self_powered = fwnode_property_read_bool(fwnode, "self-powered");
 
-		port->nr_src_pdo = min(ret, PDO_MAX_OBJECTS);
-		ret = fwnode_property_read_u32_array(fwnode, "source-pdos",
-						     port->src_pdo, port->nr_src_pdo);
-		if (ret)
-			return ret;
-		ret = tcpm_validate_caps(port, port->src_pdo, port->nr_src_pdo);
-		if (ret)
-			return ret;
-	} else {
+	if (!port->pd_supported) {
 		ret = fwnode_property_read_string(fwnode, "typec-power-opmode", &opmode_str);
 		if (ret)
 			return ret;
@@ -6202,45 +6305,150 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 		if (ret < 0)
 			return ret;
 		port->src_rp = tcpm_pwr_opmode_to_rp(ret);
-	}
-
-	if (port->port_type == TYPEC_PORT_SRC)
-		return 0;
-
-sink:
-	port->self_powered = fwnode_property_read_bool(fwnode, "self-powered");
-
-	if (!port->pd_supported)
 		return 0;
+	}
 
-	/* Get sink pdos */
-	ret = fwnode_property_count_u32(fwnode, "sink-pdos");
-	if (ret <= 0)
-		return -EINVAL;
-
-	port->nr_snk_pdo = min(ret, PDO_MAX_OBJECTS);
-	ret = fwnode_property_read_u32_array(fwnode, "sink-pdos",
-					     port->snk_pdo, port->nr_snk_pdo);
-	if ((ret < 0) || tcpm_validate_caps(port, port->snk_pdo,
-					    port->nr_snk_pdo))
-		return -EINVAL;
-
-	if (fwnode_property_read_u32(fwnode, "op-sink-microwatt", &mw) < 0)
-		return -EINVAL;
-	port->operating_snk_mw = mw / 1000;
+	/* The following code are applicable to pd-capable ports, i.e. pd_supported is true. */
 
 	/* FRS can only be supported by DRP ports */
 	if (port->port_type == TYPEC_PORT_DRP) {
 		ret = fwnode_property_read_u32(fwnode, "new-source-frs-typec-current",
 					       &frs_current);
-		if (ret >= 0 && frs_current <= FRS_5V_3A)
+		if (!ret && frs_current <= FRS_5V_3A)
 			port->new_source_frs_current = frs_current;
+
+		if (ret)
+			ret = 0;
 	}
 
+	/* For the backward compatibility, "capabilities" node is optional. */
+	capabilities = fwnode_get_named_child_node(fwnode, "capabilities");
+	if (!capabilities) {
+		port->pd_count = 1;
+	} else {
+		fwnode_for_each_child_node(capabilities, child)
+			port->pd_count++;
+
+		if (!port->pd_count) {
+			ret = -ENODATA;
+			goto put_capabilities;
+		}
+	}
+
+	port->pds = devm_kcalloc(port->dev, port->pd_count, sizeof(struct usb_power_delivery *),
+				 GFP_KERNEL);
+	if (!port->pds) {
+		ret = -ENOMEM;
+		goto put_capabilities;
+	}
+
+	port->pd_list = devm_kcalloc(port->dev, port->pd_count, sizeof(struct pd_data *),
+				     GFP_KERNEL);
+	if (!port->pd_list) {
+		ret = -ENOMEM;
+		goto put_capabilities;
+	}
+
+	for (i = 0; i < port->pd_count; i++) {
+		port->pd_list[i] = devm_kzalloc(port->dev, sizeof(struct pd_data), GFP_KERNEL);
+		if (!port->pd_list[i]) {
+			ret = -ENOMEM;
+			goto put_capabilities;
+		}
+
+		src_pdo = port->pd_list[i]->source_desc.pdo;
+		port->pd_list[i]->source_desc.role = TYPEC_SOURCE;
+		snk_pdo = port->pd_list[i]->sink_desc.pdo;
+		port->pd_list[i]->sink_desc.role = TYPEC_SINK;
+
+		/* If "capabilities" is NULL, fall back to single pd cap population. */
+		if (!capabilities)
+			caps = fwnode;
+		else
+			caps = fwnode_get_next_child_node(capabilities, caps);
+
+		if (port->port_type != TYPEC_PORT_SNK) {
+			ret = fwnode_property_count_u32(caps, "source-pdos");
+			if (ret == 0) {
+				ret = -EINVAL;
+				goto put_caps;
+			}
+			if (ret < 0)
+				goto put_caps;
+
+			nr_src_pdo = min(ret, PDO_MAX_OBJECTS);
+			ret = fwnode_property_read_u32_array(caps, "source-pdos", src_pdo,
+							     nr_src_pdo);
+			if (ret)
+				goto put_caps;
+
+			ret = tcpm_validate_caps(port, src_pdo, nr_src_pdo);
+			if (ret)
+				goto put_caps;
+
+			if (i == 0) {
+				port->nr_src_pdo = nr_src_pdo;
+				memcpy_and_pad(port->src_pdo, sizeof(u32) * PDO_MAX_OBJECTS,
+					       port->pd_list[0]->source_desc.pdo,
+					       sizeof(u32) * nr_src_pdo,
+					       0);
+			}
+		}
+
+		if (port->port_type != TYPEC_PORT_SRC) {
+			ret = fwnode_property_count_u32(caps, "sink-pdos");
+			if (ret == 0) {
+				ret = -EINVAL;
+				goto put_caps;
+			}
+
+			if (ret < 0)
+				goto put_caps;
+
+			nr_snk_pdo = min(ret, PDO_MAX_OBJECTS);
+			ret = fwnode_property_read_u32_array(caps, "sink-pdos", snk_pdo,
+							     nr_snk_pdo);
+			if (ret)
+				goto put_caps;
+
+			ret = tcpm_validate_caps(port, snk_pdo, nr_snk_pdo);
+			if (ret)
+				goto put_caps;
+
+			if (fwnode_property_read_u32(caps, "op-sink-microwatt", &uw) < 0) {
+				ret = -EINVAL;
+				goto put_caps;
+			}
+
+			port->pd_list[i]->operating_snk_mw = uw / 1000;
+
+			if (i == 0) {
+				port->nr_snk_pdo = nr_snk_pdo;
+				memcpy_and_pad(port->snk_pdo, sizeof(u32) * PDO_MAX_OBJECTS,
+					       port->pd_list[0]->sink_desc.pdo,
+					       sizeof(u32) * nr_snk_pdo,
+					       0);
+				port->operating_snk_mw = port->pd_list[0]->operating_snk_mw;
+			}
+		}
+	}
+
+put_caps:
+	if (caps != fwnode)
+		fwnode_handle_put(caps);
+put_capabilities:
+	fwnode_handle_put(capabilities);
+	return ret;
+}
+
+static int tcpm_fw_get_snk_vdos(struct tcpm_port *port, struct fwnode_handle *fwnode)
+{
+	int ret;
+
 	/* sink-vdos is optional */
 	ret = fwnode_property_count_u32(fwnode, "sink-vdos");
 	if (ret < 0)
-		ret = 0;
+		return 0;
 
 	port->nr_snk_vdo = min(ret, VDO_MAX_OBJECTS);
 	if (port->nr_snk_vdo) {
@@ -6606,12 +6814,14 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	tcpm_debugfs_init(port);
 
 	err = tcpm_fw_get_caps(port, tcpc->fwnode);
+	if (err < 0)
+		goto out_destroy_wq;
+	err = tcpm_fw_get_snk_vdos(port, tcpc->fwnode);
 	if (err < 0)
 		goto out_destroy_wq;
 
 	port->try_role = port->typec_caps.prefer_role;
 
-	port->typec_caps.fwnode = tcpc->fwnode;
 	port->typec_caps.revision = 0x0120;	/* Type-C spec release 1.2 */
 	port->typec_caps.pd_revision = 0x0300;	/* USB-PD spec release 3.0 */
 	port->typec_caps.svdm_version = SVDM_VER_2_0;
@@ -6620,7 +6830,6 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	port->typec_caps.orientation_aware = 1;
 
 	port->partner_desc.identity = &port->partner_ident;
-	port->port_type = port->typec_caps.type;
 
 	port->role_sw = usb_role_switch_get(port->dev);
 	if (!port->role_sw)
@@ -6639,7 +6848,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	if (err)
 		goto out_role_sw_put;
 
-	port->typec_caps.pd = port->pd;
+	port->typec_caps.pd = port->pds[0];
 
 	port->typec_port = typec_register_port(port->dev, &port->typec_caps);
 	if (IS_ERR(port->typec_port)) {
-- 
GitLab


From 398aa9a7e77cf23c2a6f882ddd3dcd96f21771dc Mon Sep 17 00:00:00 2001
From: Manan Aurora <maurora@google.com>
Date: Tue, 31 Oct 2023 03:46:41 +0000
Subject: [PATCH 2110/4076] usb: dwc3: Support EBC feature of DWC_usb31

Support configuration and use of bulk endpoints in the so-called EBC
mode described in the DBC_usb31 databook (appendix E)

Added a bit fifo_mode to usb_ep to indicate to the UDC driver that a
specific endpoint is to operate in the EBC (or equivalent) mode when
enabled

Added macros for bits 15 and 14 of DEPCFG parameter 1 to indicate EBC
mode and write back behaviour. These bits will be set to 1 when
configuring an EBC endpoint as described in the programming guide

Signed-off-by: Manan Aurora <maurora@google.com>
Link: https://lore.kernel.org/r/20231031034641.660606-1-maurora@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.h    | 1 +
 drivers/usb/dwc3/gadget.c  | 6 ++++++
 drivers/usb/dwc3/gadget.h  | 2 ++
 include/linux/usb/gadget.h | 1 +
 4 files changed, 10 insertions(+)

diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index e120611a5174f..e3eea965e57bf 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -376,6 +376,7 @@
 /* Global HWPARAMS4 Register */
 #define DWC3_GHWPARAMS4_HIBER_SCRATCHBUFS(n)	(((n) & (0x0f << 13)) >> 13)
 #define DWC3_MAX_HIBER_SCRATCHBUFS		15
+#define DWC3_EXT_BUFF_CONTROL		BIT(21)
 
 /* Global HWPARAMS6 Register */
 #define DWC3_GHWPARAMS6_BCSUPPORT		BIT(14)
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 88d8d589f0148..c15e965ea95a5 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -673,6 +673,12 @@ static int dwc3_gadget_set_ep_config(struct dwc3_ep *dep, unsigned int action)
 		params.param1 |= DWC3_DEPCFG_BINTERVAL_M1(bInterval_m1);
 	}
 
+	if (dep->endpoint.fifo_mode) {
+		if (!(dwc->hwparams.hwparams4 & DWC3_EXT_BUFF_CONTROL))
+			return -EINVAL;
+		params.param1 |= DWC3_DEPCFG_EBC_HWO_NOWB | DWC3_DEPCFG_USE_EBC;
+	}
+
 	return dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_SETEPCONFIG, &params);
 }
 
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 55a56cf67d736..fd7a4e94397e6 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -26,6 +26,8 @@ struct dwc3;
 #define DWC3_DEPCFG_XFER_NOT_READY_EN	BIT(10)
 #define DWC3_DEPCFG_FIFO_ERROR_EN	BIT(11)
 #define DWC3_DEPCFG_STREAM_EVENT_EN	BIT(13)
+#define DWC3_DEPCFG_EBC_HWO_NOWB	BIT(14)
+#define DWC3_DEPCFG_USE_EBC		BIT(15)
 #define DWC3_DEPCFG_BINTERVAL_M1(n)	(((n) & 0xff) << 16)
 #define DWC3_DEPCFG_STREAM_CAPABLE	BIT(24)
 #define DWC3_DEPCFG_EP_NUMBER(n)	(((n) & 0x1f) << 25)
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 6532beb587b19..a771ccc038ac9 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -236,6 +236,7 @@ struct usb_ep {
 	unsigned		max_streams:16;
 	unsigned		mult:2;
 	unsigned		maxburst:5;
+	unsigned		fifo_mode:1;
 	u8			address;
 	const struct usb_endpoint_descriptor	*desc;
 	const struct usb_ss_ep_comp_descriptor	*comp_desc;
-- 
GitLab


From 68c26fe58182f5af56bfa577d1cc0c949740baab Mon Sep 17 00:00:00 2001
From: Frank Wang <frank.wang@rock-chips.com>
Date: Wed, 6 Dec 2023 14:59:39 +0800
Subject: [PATCH 2111/4076] usb: dwc3: set pm runtime active before resume
 common

For device mode, if PM runtime autosuspend feature enabled, the
runtime power status of dwc3 may be suspended when run dwc3_resume(),
and dwc3 gadget would not be configured in dwc3_gadget_run_stop().
It would cause gadget connected failed if USB cable has been plugged
before PM resume. So move forward pm_runtime_set_active() to fix it.

Signed-off-by: Frank Wang <frank.wang@rock-chips.com>
Link: https://lore.kernel.org/r/20231206065939.16958-1-frank.wang@rock-chips.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 4447ef2cbc0f0..3e55838c00014 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -2315,12 +2315,15 @@ static int dwc3_resume(struct device *dev)
 
 	pinctrl_pm_select_default_state(dev);
 
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+
 	ret = dwc3_resume_common(dwc, PMSG_RESUME);
-	if (ret)
+	if (ret) {
+		pm_runtime_set_suspended(dev);
 		return ret;
+	}
 
-	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
 	return 0;
-- 
GitLab


From 1900daeefd3ebde61199649143085a2dfdebf55c Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Thu, 21 Dec 2023 21:02:16 +0530
Subject: [PATCH 2112/4076] usb: gadget: ncm: Add support to update
 wMaxSegmentSize via configfs

The max segment size is currently limited to the ethernet frame length of
the kernel which happens to be 1514 at this point in time. However the NCM
specification limits it to 64K for sixtenn bit NTB's. For peer to peer
connections, increasing the segment size gives better throughput.

Add support to configure this value before configfs symlink is created.
Also since the NTB Out/In buffer sizes are fixed at 16384 bytes, limit the
segment size to an upper cap of 8000 to allow at least a minimum of 2 MTU
sized datagrams to be aggregated.

Set the default MTU size for the ncm interface during function bind before
network interface is registered allowing MTU to be set in parity with
wMaxSegmentSize.

Update gadget documentation describing the new configfs property.

Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Link: https://lore.kernel.org/r/20231221153216.18657-1-quic_kriskura@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/usb/gadget-testing.rst | 20 ++++----
 drivers/usb/gadget/function/f_ncm.c  | 69 ++++++++++++++++++++++++++--
 drivers/usb/gadget/function/u_ncm.h  |  2 +
 3 files changed, 79 insertions(+), 12 deletions(-)

diff --git a/Documentation/usb/gadget-testing.rst b/Documentation/usb/gadget-testing.rst
index 29072c166d236..8cd62c466d20a 100644
--- a/Documentation/usb/gadget-testing.rst
+++ b/Documentation/usb/gadget-testing.rst
@@ -448,15 +448,17 @@ Function-specific configfs interface
 The function name to use when creating the function directory is "ncm".
 The NCM function provides these attributes in its function directory:
 
-	=============== ==================================================
-	ifname		network device interface name associated with this
-			function instance
-	qmult		queue length multiplier for high and super speed
-	host_addr	MAC address of host's end of this
-			Ethernet over USB link
-	dev_addr	MAC address of device's end of this
-			Ethernet over USB link
-	=============== ==================================================
+	===============   ==================================================
+	ifname		  network device interface name associated with this
+			  function instance
+	qmult		  queue length multiplier for high and super speed
+	host_addr	  MAC address of host's end of this
+			  Ethernet over USB link
+	dev_addr	  MAC address of device's end of this
+			  Ethernet over USB link
+	max_segment_size  Segment size required for P2P connections. This
+			  will set MTU to (max_segment_size - 14 bytes)
+	===============   ==================================================
 
 and after creating the functions/ncm.<instance name> they contain default
 values: qmult is 5, dev_addr and host_addr are randomly selected.
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index cc0ed29a4adc0..a1575a0ca568d 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -103,6 +103,16 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f)
 /* Delay for the transmit to wait before sending an unfilled NTB frame. */
 #define TX_TIMEOUT_NSECS	300000
 
+/*
+ * Although max mtu as dictated by u_ether is 15412 bytes, setting
+ * max_segment_sizeto 15426 would not be efficient. If user chooses segment
+ * size to be (>= 8192), then we can't aggregate more than one  buffer in each
+ * NTB (assuming each packet coming from network layer is >= 8192 bytes) as ep
+ * maxpacket limit is 16384. So let max_segment_size be limited to 8000 to allow
+ * at least 2 packets to be aggregated reducing wastage of NTB buffer space
+ */
+#define MAX_DATAGRAM_SIZE	8000
+
 #define FORMATS_SUPPORTED	(USB_CDC_NCM_NTB16_SUPPORTED |	\
 				 USB_CDC_NCM_NTB32_SUPPORTED)
 
@@ -179,7 +189,6 @@ static struct usb_cdc_ether_desc ecm_desc = {
 	/* this descriptor actually adds value, surprise! */
 	/* .iMACAddress = DYNAMIC */
 	.bmEthernetStatistics =	cpu_to_le32(0), /* no statistics */
-	.wMaxSegmentSize =	cpu_to_le16(ETH_FRAME_LEN),
 	.wNumberMCFilters =	cpu_to_le16(0),
 	.bNumberPowerFilters =	0,
 };
@@ -1166,11 +1175,15 @@ static int ncm_unwrap_ntb(struct gether *port,
 	struct sk_buff	*skb2;
 	int		ret = -EINVAL;
 	unsigned	ntb_max = le32_to_cpu(ntb_parameters.dwNtbOutMaxSize);
-	unsigned	frame_max = le16_to_cpu(ecm_desc.wMaxSegmentSize);
+	unsigned	frame_max;
 	const struct ndp_parser_opts *opts = ncm->parser_opts;
 	unsigned	crc_len = ncm->is_crc ? sizeof(uint32_t) : 0;
 	int		dgram_counter;
 	int		to_process = skb->len;
+	struct f_ncm_opts *ncm_opts;
+
+	ncm_opts = container_of(port->func.fi, struct f_ncm_opts, func_inst);
+	frame_max = ncm_opts->max_segment_size;
 
 parse_ntb:
 	tmp = (__le16 *)ntb_ptr;
@@ -1430,8 +1443,10 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 
 	mutex_lock(&ncm_opts->lock);
 	gether_set_gadget(ncm_opts->net, cdev->gadget);
-	if (!ncm_opts->bound)
+	if (!ncm_opts->bound) {
+		ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN);
 		status = gether_register_netdev(ncm_opts->net);
+	}
 	mutex_unlock(&ncm_opts->lock);
 
 	if (status)
@@ -1474,6 +1489,8 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	ncm_data_intf.bInterfaceNumber = status;
 	ncm_union_desc.bSlaveInterface0 = status;
 
+	ecm_desc.wMaxSegmentSize = ncm_opts->max_segment_size;
+
 	status = -ENODEV;
 
 	/* allocate instance-specific endpoints */
@@ -1576,11 +1593,56 @@ USB_ETHERNET_CONFIGFS_ITEM_ATTR_QMULT(ncm);
 /* f_ncm_opts_ifname */
 USB_ETHERNET_CONFIGFS_ITEM_ATTR_IFNAME(ncm);
 
+static ssize_t ncm_opts_max_segment_size_show(struct config_item *item,
+					      char *page)
+{
+	struct f_ncm_opts *opts = to_f_ncm_opts(item);
+	u16 segment_size;
+
+	mutex_lock(&opts->lock);
+	segment_size = opts->max_segment_size;
+	mutex_unlock(&opts->lock);
+
+	return sysfs_emit(page, "%u\n", segment_size);
+}
+
+static ssize_t ncm_opts_max_segment_size_store(struct config_item *item,
+					       const char *page, size_t len)
+{
+	struct f_ncm_opts *opts = to_f_ncm_opts(item);
+	u16 segment_size;
+	int ret;
+
+	mutex_lock(&opts->lock);
+	if (opts->refcnt) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	ret = kstrtou16(page, 0, &segment_size);
+	if (ret)
+		goto out;
+
+	if (segment_size > MAX_DATAGRAM_SIZE) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	opts->max_segment_size = segment_size;
+	ret = len;
+out:
+	mutex_unlock(&opts->lock);
+	return ret;
+}
+
+CONFIGFS_ATTR(ncm_opts_, max_segment_size);
+
 static struct configfs_attribute *ncm_attrs[] = {
 	&ncm_opts_attr_dev_addr,
 	&ncm_opts_attr_host_addr,
 	&ncm_opts_attr_qmult,
 	&ncm_opts_attr_ifname,
+	&ncm_opts_attr_max_segment_size,
 	NULL,
 };
 
@@ -1623,6 +1685,7 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 		kfree(opts);
 		return ERR_CAST(net);
 	}
+	opts->max_segment_size = cpu_to_le16(ETH_FRAME_LEN);
 	INIT_LIST_HEAD(&opts->ncm_os_desc.ext_prop);
 
 	descs[0] = &opts->ncm_os_desc;
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index 5408854d84072..49ec095cdb4b6 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -31,6 +31,8 @@ struct f_ncm_opts {
 	 */
 	struct mutex			lock;
 	int				refcnt;
+
+	u16				max_segment_size;
 };
 
 #endif /* U_NCM_H */
-- 
GitLab


From 1b8be5ecff26201bafb0a554c74e91571299fb94 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Sun, 24 Dec 2023 10:38:13 -0500
Subject: [PATCH 2113/4076] usb: cdns3: fix uvc failure work since sg support
 enabled

When IP version >= DEV_VER_V2, gadget:sg_supported is true. So uvc gadget
function driver will use sg to equeue data, first is 8bytes header, the
second is 1016bytes data.

    cdns3_prepare_trb: ep2in: trb 0000000000ac755f, dma buf: 0xbf455000, size: 8, burst: 128 ctrl: 0x00000415 (C=1, T=0, ISP, CHAIN, Normal)
    cdns3_prepare_trb: ep2in: trb 00000000a574e693, dma buf: 0xc0200fe0, size: 1016, burst: 128 ctrl: 0x00000405 (C=1, T=0, ISP, Normal)

But cdns3_ep_run_transfer() can't correctly handle this case, which only
support one TRB for ISO transfer.

The controller requires duplicate the TD for each SOF if priv_ep->interval
is not 1. DMA will read data from DDR to internal FIFO when get SOF. Send
data to bus when receive IN token. DMA always refill FIFO when get SOF
regardless host send IN token or not. If host send IN token later, some
frames data will be lost.

Fixed it by below major steps:

1. Calculate numembers of TRB base on sg_nums and priv_ep->interval.
2. Remove CHAIN flags for each end TRB of TD when duplicate TD.
3. The controller requires LINK TRB must be first TRB of TD. When check
there are not enough TRBs lefts, just fill LINK TRB for left TRBs.

.... CHAIN_TRB DATA_TRB, CHAIN_TRB DATA_TRB,  LINK_TRB ... LINK_TRB
                                                           ^End of TRB List

Cc:  <stable@vger.kernel.org>
Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231224153816.1664687-2-Frank.Li@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-gadget.c | 51 +++++++++++++++++++++++++-------
 1 file changed, 40 insertions(+), 11 deletions(-)

diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 15463b7cddd23..22a31ffa69423 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -1119,6 +1119,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	dma_addr_t trb_dma;
 	u32 togle_pcs = 1;
 	int sg_iter = 0;
+	int num_trb_req;
 	int num_trb;
 	int address;
 	u32 control;
@@ -1128,15 +1129,13 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	bool sg_supported = !!(request->num_mapped_sgs);
 	u32 ioc = request->no_interrupt ? 0 : TRB_IOC;
 
+	num_trb_req = sg_supported ? request->num_mapped_sgs : 1;
+
+	/* ISO transfer require each SOF have a TD, each TD include some TRBs */
 	if (priv_ep->type == USB_ENDPOINT_XFER_ISOC)
-		num_trb = priv_ep->interval;
+		num_trb = priv_ep->interval * num_trb_req;
 	else
-		num_trb = sg_supported ? request->num_mapped_sgs : 1;
-
-	if (num_trb > priv_ep->free_trbs) {
-		priv_ep->flags |= EP_RING_FULL;
-		return -ENOBUFS;
-	}
+		num_trb = num_trb_req;
 
 	priv_req = to_cdns3_request(request);
 	address = priv_ep->endpoint.desc->bEndpointAddress;
@@ -1185,14 +1184,31 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 
 		link_trb->control = cpu_to_le32(((priv_ep->pcs) ? TRB_CYCLE : 0) |
 				    TRB_TYPE(TRB_LINK) | TRB_TOGGLE | ch_bit);
+
+		if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) {
+			/*
+			 * ISO require LINK TRB must be first one of TD.
+			 * Fill LINK TRBs for left trb space to simply software process logic.
+			 */
+			while (priv_ep->enqueue) {
+				*trb = *link_trb;
+				trace_cdns3_prepare_trb(priv_ep, trb);
+
+				cdns3_ep_inc_enq(priv_ep);
+				trb = priv_ep->trb_pool + priv_ep->enqueue;
+				priv_req->trb = trb;
+			}
+		}
+	}
+
+	if (num_trb > priv_ep->free_trbs) {
+		priv_ep->flags |= EP_RING_FULL;
+		return -ENOBUFS;
 	}
 
 	if (priv_dev->dev_ver <= DEV_VER_V2)
 		togle_pcs = cdns3_wa1_update_guard(priv_ep, trb);
 
-	if (sg_supported)
-		s = request->sg;
-
 	/* set incorrect Cycle Bit for first trb*/
 	control = priv_ep->pcs ? 0 : TRB_CYCLE;
 	trb->length = 0;
@@ -1210,6 +1226,9 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	do {
 		u32 length;
 
+		if (!(sg_iter % num_trb_req) && sg_supported)
+			s = request->sg;
+
 		/* fill TRB */
 		control |= TRB_TYPE(TRB_NORMAL);
 		if (sg_supported) {
@@ -1251,7 +1270,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 		if (sg_supported) {
 			trb->control |= cpu_to_le32(TRB_ISP);
 			/* Don't set chain bit for last TRB */
-			if (sg_iter < num_trb - 1)
+			if ((sg_iter % num_trb_req) < num_trb_req - 1)
 				trb->control |= cpu_to_le32(TRB_CHAIN);
 
 			s = sg_next(s);
@@ -1509,6 +1528,12 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 
 		/* The TRB was changed as link TRB, and the request was handled at ep_dequeue */
 		while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) {
+
+			/* ISO ep_traddr may stop at LINK TRB */
+			if (priv_ep->dequeue == cdns3_get_dma_pos(priv_dev, priv_ep) &&
+			    priv_ep->type == USB_ENDPOINT_XFER_ISOC)
+				break;
+
 			trace_cdns3_complete_trb(priv_ep, trb);
 			cdns3_ep_inc_deq(priv_ep);
 			trb = priv_ep->trb_pool + priv_ep->dequeue;
@@ -1541,6 +1566,10 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 			}
 
 			if (request_handled) {
+				/* TRBs are duplicated by priv_ep->interval time for ISO IN */
+				if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_ep->dir)
+					request->actual /= priv_ep->interval;
+
 				cdns3_gadget_giveback(priv_ep, priv_req, 0);
 				request_handled = false;
 				transfer_end = false;
-- 
GitLab


From 92f02efa1d86d7dcaef7f38a5fe3396c4e88a93c Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Sun, 24 Dec 2023 10:38:14 -0500
Subject: [PATCH 2114/4076] usb: cdns3: fix iso transfer error when mult is not
 zero

ISO basic transfer is
	ITP(SOF) Package_0 Package_1 ... Package_n

CDNS3 DMA start dma transfer from memmory to internal FIFO when get SOF,
controller will transfer data to usb bus from internal FIFO when get IN
token.

According USB spec defination:
	Maximum number of packets = (bMaxBurst + 1) * (Mult + 1)

Internal memory should be the same as (bMaxBurst + 1) * (Mult + 1). DMA
don't fetch data advance when ISO transfer, so only reserve
(bMaxBurst + 1) * (Mult + 1) internal memory for ISO transfer.

Need save Mult and bMaxBurst information and set it into EP_CFG register,
otherwise only 1 package is sent by controller, other package will be
lost.

Cc:  <stable@vger.kernel.org>
Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231224153816.1664687-3-Frank.Li@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-gadget.c | 59 +++++++++++++++++++-------------
 drivers/usb/cdns3/cdns3-gadget.h |  3 ++
 2 files changed, 39 insertions(+), 23 deletions(-)

diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 22a31ffa69423..4c6893af22dde 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -2065,11 +2065,10 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 	bool is_iso_ep = (priv_ep->type == USB_ENDPOINT_XFER_ISOC);
 	struct cdns3_device *priv_dev = priv_ep->cdns3_dev;
 	u32 bEndpointAddress = priv_ep->num | priv_ep->dir;
-	u32 max_packet_size = 0;
-	u8 maxburst = 0;
+	u32 max_packet_size = priv_ep->wMaxPacketSize;
+	u8 maxburst = priv_ep->bMaxBurst;
 	u32 ep_cfg = 0;
 	u8 buffering;
-	u8 mult = 0;
 	int ret;
 
 	buffering = priv_dev->ep_buf_size - 1;
@@ -2091,8 +2090,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 		break;
 	default:
 		ep_cfg = EP_CFG_EPTYPE(USB_ENDPOINT_XFER_ISOC);
-		mult = priv_dev->ep_iso_burst - 1;
-		buffering = mult + 1;
+		buffering = (priv_ep->bMaxBurst + 1) * (priv_ep->mult + 1) - 1;
 	}
 
 	switch (priv_dev->gadget.speed) {
@@ -2103,17 +2101,8 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 		max_packet_size = is_iso_ep ? 1024 : 512;
 		break;
 	case USB_SPEED_SUPER:
-		/* It's limitation that driver assumes in driver. */
-		mult = 0;
-		max_packet_size = 1024;
-		if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) {
-			maxburst = priv_dev->ep_iso_burst - 1;
-			buffering = (mult + 1) *
-				    (maxburst + 1);
-
-			if (priv_ep->interval > 1)
-				buffering++;
-		} else {
+		if (priv_ep->type != USB_ENDPOINT_XFER_ISOC) {
+			max_packet_size = 1024;
 			maxburst = priv_dev->ep_buf_size - 1;
 		}
 		break;
@@ -2142,7 +2131,6 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 	if (priv_dev->dev_ver < DEV_VER_V2)
 		priv_ep->trb_burst_size = 16;
 
-	mult = min_t(u8, mult, EP_CFG_MULT_MAX);
 	buffering = min_t(u8, buffering, EP_CFG_BUFFERING_MAX);
 	maxburst = min_t(u8, maxburst, EP_CFG_MAXBURST_MAX);
 
@@ -2176,7 +2164,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
 	}
 
 	ep_cfg |= EP_CFG_MAXPKTSIZE(max_packet_size) |
-		  EP_CFG_MULT(mult) |
+		  EP_CFG_MULT(priv_ep->mult) |			/* must match EP setting */
 		  EP_CFG_BUFFERING(buffering) |
 		  EP_CFG_MAXBURST(maxburst);
 
@@ -2266,6 +2254,13 @@ usb_ep *cdns3_gadget_match_ep(struct usb_gadget *gadget,
 	priv_ep->type = usb_endpoint_type(desc);
 	priv_ep->flags |= EP_CLAIMED;
 	priv_ep->interval = desc->bInterval ? BIT(desc->bInterval - 1) : 0;
+	priv_ep->wMaxPacketSize =  usb_endpoint_maxp(desc);
+	priv_ep->mult = USB_EP_MAXP_MULT(priv_ep->wMaxPacketSize);
+	priv_ep->wMaxPacketSize &= USB_ENDPOINT_MAXP_MASK;
+	if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && comp_desc) {
+		priv_ep->mult =  USB_SS_MULT(comp_desc->bmAttributes) - 1;
+		priv_ep->bMaxBurst = comp_desc->bMaxBurst;
+	}
 
 	spin_unlock_irqrestore(&priv_dev->lock, flags);
 	return &priv_ep->endpoint;
@@ -3049,22 +3044,40 @@ static int cdns3_gadget_check_config(struct usb_gadget *gadget)
 	struct cdns3_endpoint *priv_ep;
 	struct usb_ep *ep;
 	int n_in = 0;
+	int iso = 0;
+	int out = 1;
 	int total;
+	int n;
 
 	list_for_each_entry(ep, &gadget->ep_list, ep_list) {
 		priv_ep = ep_to_cdns3_ep(ep);
-		if ((priv_ep->flags & EP_CLAIMED) && (ep->address & USB_DIR_IN))
-			n_in++;
+		if (!(priv_ep->flags & EP_CLAIMED))
+			continue;
+
+		n = (priv_ep->mult + 1) * (priv_ep->bMaxBurst + 1);
+		if (ep->address & USB_DIR_IN) {
+			/*
+			 * ISO transfer: DMA start move data when get ISO, only transfer
+			 * data as min(TD size, iso). No benefit for allocate bigger
+			 * internal memory than 'iso'.
+			 */
+			if (priv_ep->type == USB_ENDPOINT_XFER_ISOC)
+				iso += n;
+			else
+				n_in++;
+		} else {
+			if (priv_ep->type == USB_ENDPOINT_XFER_ISOC)
+				out = max_t(int, out, n);
+		}
 	}
 
 	/* 2KB are reserved for EP0, 1KB for out*/
-	total = 2 + n_in + 1;
+	total = 2 + n_in + out + iso;
 
 	if (total > priv_dev->onchip_buffers)
 		return -ENOMEM;
 
-	priv_dev->ep_buf_size = priv_dev->ep_iso_burst =
-			(priv_dev->onchip_buffers - 2) / (n_in + 1);
+	priv_dev->ep_buf_size = (priv_dev->onchip_buffers - 2 - iso) / (n_in + out);
 
 	return 0;
 }
diff --git a/drivers/usb/cdns3/cdns3-gadget.h b/drivers/usb/cdns3/cdns3-gadget.h
index fbe4a8e3aa897..086a7bb838975 100644
--- a/drivers/usb/cdns3/cdns3-gadget.h
+++ b/drivers/usb/cdns3/cdns3-gadget.h
@@ -1168,6 +1168,9 @@ struct cdns3_endpoint {
 	u8			dir;
 	u8			num;
 	u8			type;
+	u8			mult;
+	u8			bMaxBurst;
+	u16			wMaxPacketSize;
 	int			interval;
 
 	int			free_trbs;
-- 
GitLab


From 40c304109e866a7dc123661a5c8ca72f6b5e14e0 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Sun, 24 Dec 2023 10:38:15 -0500
Subject: [PATCH 2115/4076] usb: cdns3: Fix uvc fail when DMA cross 4k boundery
 since sg enabled

Supposed DMA cross 4k bounder problem should be fixed at DEV_VER_V2, but
still met problem when do ISO transfer if sg enabled.

Data pattern likes below when sg enabled, package size is 1k and mult is 2
	[UVC Header(8B) ] [data(3k - 8)] ...

The received data at offset 0xd000 will get 0xc000 data, len 0x70. Error
happen position as below pattern:
	0xd000: wrong
	0xe000: wrong
	0xf000: correct
	0x10000: wrong
	0x11000: wrong
	0x12000: correct
	...

To avoid DMA cross 4k bounder at ISO transfer, reduce burst len according
to start DMA address's alignment.

Cc:  <stable@vger.kernel.org>
Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231224153816.1664687-4-Frank.Li@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-gadget.c | 32 +++++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 4c6893af22dde..aeca902ab6cc4 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -1120,6 +1120,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 	u32 togle_pcs = 1;
 	int sg_iter = 0;
 	int num_trb_req;
+	int trb_burst;
 	int num_trb;
 	int address;
 	u32 control;
@@ -1243,7 +1244,36 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,
 			total_tdl += DIV_ROUND_UP(length,
 					       priv_ep->endpoint.maxpacket);
 
-		trb->length |= cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) |
+		trb_burst = priv_ep->trb_burst_size;
+
+		/*
+		 * Supposed DMA cross 4k bounder problem should be fixed at DEV_VER_V2, but still
+		 * met problem when do ISO transfer if sg enabled.
+		 *
+		 * Data pattern likes below when sg enabled, package size is 1k and mult is 2
+		 *       [UVC Header(8B) ] [data(3k - 8)] ...
+		 *
+		 * The received data at offset 0xd000 will get 0xc000 data, len 0x70. Error happen
+		 * as below pattern:
+		 *	0xd000: wrong
+		 *	0xe000: wrong
+		 *	0xf000: correct
+		 *	0x10000: wrong
+		 *	0x11000: wrong
+		 *	0x12000: correct
+		 *	...
+		 *
+		 * But it is still unclear about why error have not happen below 0xd000, it should
+		 * cross 4k bounder. But anyway, the below code can fix this problem.
+		 *
+		 * To avoid DMA cross 4k bounder at ISO transfer, reduce burst len according to 16.
+		 */
+		if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_dev->dev_ver <= DEV_VER_V2)
+			if (ALIGN_DOWN(trb->buffer, SZ_4K) !=
+			    ALIGN_DOWN(trb->buffer + length, SZ_4K))
+				trb_burst = 16;
+
+		trb->length |= cpu_to_le32(TRB_BURST_LEN(trb_burst) |
 					TRB_LEN(length));
 		pcs = priv_ep->pcs ? TRB_CYCLE : 0;
 
-- 
GitLab


From 895ee5aefb7e24203de5dffae7ce9a02d78fa3d1 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Sun, 24 Dec 2023 10:38:16 -0500
Subject: [PATCH 2116/4076] Revert "usb: gadget: f_uvc: change endpoint
 allocation in uvc_function_bind()"

This reverts commit 3c5b006f3ee800b4bd9ed37b3a8f271b8560126e.

gadget_is_{super|dual}speed() API check UDC controller capitblity. It
should pass down highest speed endpoint descriptor to UDC controller. So
UDC controller driver can reserve enough resource at check_config(),
especially mult and maxburst. So UDC driver (such as cdns3) can know need
at least (mult + 1) * (maxburst + 1) * wMaxPacketSize internal memory for
this uvc functions.

Cc:  <stable@vger.kernel.org>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231224153816.1664687-5-Frank.Li@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uvc.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index da5f28e471b04..929666805bd23 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -721,13 +721,29 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
 	}
 	uvc->enable_interrupt_ep = opts->enable_interrupt_ep;
 
-	ep = usb_ep_autoconfig(cdev->gadget, &uvc_fs_streaming_ep);
+	/*
+	 * gadget_is_{super|dual}speed() API check UDC controller capitblity. It should pass down
+	 * highest speed endpoint descriptor to UDC controller. So UDC controller driver can reserve
+	 * enough resource at check_config(), especially mult and maxburst. So UDC driver (such as
+	 * cdns3) can know need at least (mult + 1) * (maxburst + 1) * wMaxPacketSize internal
+	 * memory for this uvc functions. This is the only straightforward method to resolve the UDC
+	 * resource allocation issue in the current gadget framework.
+	 */
+	if (gadget_is_superspeed(c->cdev->gadget))
+		ep = usb_ep_autoconfig_ss(cdev->gadget, &uvc_ss_streaming_ep,
+					  &uvc_ss_streaming_comp);
+	else if (gadget_is_dualspeed(cdev->gadget))
+		ep = usb_ep_autoconfig(cdev->gadget, &uvc_hs_streaming_ep);
+	else
+		ep = usb_ep_autoconfig(cdev->gadget, &uvc_fs_streaming_ep);
+
 	if (!ep) {
 		uvcg_info(f, "Unable to allocate streaming EP\n");
 		goto error;
 	}
 	uvc->video.ep = ep;
 
+	uvc_fs_streaming_ep.bEndpointAddress = uvc->video.ep->address;
 	uvc_hs_streaming_ep.bEndpointAddress = uvc->video.ep->address;
 	uvc_ss_streaming_ep.bEndpointAddress = uvc->video.ep->address;
 
-- 
GitLab


From 5dbe9ac28355fd8f4a7c4732e1e2b7db4fb9f405 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Thu, 28 Dec 2023 19:07:51 +0800
Subject: [PATCH 2117/4076] usb: chipidea: ci_hdrc_imx: add wakeup clock and
 keep it always on

Some platform using ChipIdea IP  may keep 32KHz wakeup clock always
on without usb driver intervention. And some may need driver to handle
this clock. For now only i.MX93 needs this wakeup clock. This patch will
get wakeup clock and keep it always on to make controller work properly.

Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Tested-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20231228110753.1755756-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/ci_hdrc_imx.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index e28bb2f2612dc..ae9a6a17ec6e3 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -96,6 +96,7 @@ struct ci_hdrc_imx_data {
 	struct usb_phy *phy;
 	struct platform_device *ci_pdev;
 	struct clk *clk;
+	struct clk *clk_wakeup;
 	struct imx_usbmisc_data *usbmisc_data;
 	bool supports_runtime_pm;
 	bool override_phy_control;
@@ -199,7 +200,7 @@ static int imx_get_clks(struct device *dev)
 
 	data->clk_ipg = devm_clk_get(dev, "ipg");
 	if (IS_ERR(data->clk_ipg)) {
-		/* If the platform only needs one clocks */
+		/* If the platform only needs one primary clock */
 		data->clk = devm_clk_get(dev, NULL);
 		if (IS_ERR(data->clk)) {
 			ret = PTR_ERR(data->clk);
@@ -208,6 +209,13 @@ static int imx_get_clks(struct device *dev)
 				PTR_ERR(data->clk), PTR_ERR(data->clk_ipg));
 			return ret;
 		}
+		/* Get wakeup clock. Not all of the platforms need to
+		 * handle this clock. So make it optional.
+		 */
+		data->clk_wakeup = devm_clk_get_optional(dev, "usb_wakeup_clk");
+		if (IS_ERR(data->clk_wakeup))
+			ret = dev_err_probe(dev, PTR_ERR(data->clk_wakeup),
+					"Failed to get wakeup clk\n");
 		return ret;
 	}
 
@@ -423,6 +431,10 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	if (ret)
 		goto disable_hsic_regulator;
 
+	ret = clk_prepare_enable(data->clk_wakeup);
+	if (ret)
+		goto err_wakeup_clk;
+
 	data->phy = devm_usb_get_phy_by_phandle(dev, "fsl,usbphy", 0);
 	if (IS_ERR(data->phy)) {
 		ret = PTR_ERR(data->phy);
@@ -504,6 +516,8 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 disable_device:
 	ci_hdrc_remove_device(data->ci_pdev);
 err_clk:
+	clk_disable_unprepare(data->clk_wakeup);
+err_wakeup_clk:
 	imx_disable_unprepare_clks(dev);
 disable_hsic_regulator:
 	if (data->hsic_pad_regulator)
@@ -530,6 +544,7 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev)
 		usb_phy_shutdown(data->phy);
 	if (data->ci_pdev) {
 		imx_disable_unprepare_clks(&pdev->dev);
+		clk_disable_unprepare(data->clk_wakeup);
 		if (data->plat_data->flags & CI_HDRC_PMQOS)
 			cpu_latency_qos_remove_request(&data->pm_qos_req);
 		if (data->hsic_pad_regulator)
-- 
GitLab


From 128d849074d05545becf86e713715ce7676fc074 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Thu, 28 Dec 2023 19:07:52 +0800
Subject: [PATCH 2118/4076] usb: chipidea: wait controller resume finished for
 wakeup irq

After the chipidea driver introduce extcon for id and vbus, it's able
to wakeup from another irq source, in case the system with extcon ID
cable, wakeup from usb ID cable and device removal, the usb device
disconnect irq may come firstly before the extcon notifier while system
resume, so we will get 2 "wakeup" irq, one for usb device disconnect;
and one for extcon ID cable change(real wakeup event), current driver
treat them as 2 successive wakeup irq so can't handle it correctly, then
finally the usb irq can't be enabled. This patch adds a check to bypass
further usb events before controller resume finished to fix it.

Fixes: 1f874edcb731 ("usb: chipidea: add runtime power management support")
cc:  <stable@vger.kernel.org>
Acked-by: Peter Chen <peter.chen@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Li Jun <jun.li@nxp.com>
Link: https://lore.kernel.org/r/20231228110753.1755756-2-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 0af9e68035fb4..41014f93cfdf3 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -523,6 +523,13 @@ static irqreturn_t ci_irq_handler(int irq, void *data)
 	u32 otgsc = 0;
 
 	if (ci->in_lpm) {
+		/*
+		 * If we already have a wakeup irq pending there,
+		 * let's just return to wait resume finished firstly.
+		 */
+		if (ci->wakeup_int)
+			return IRQ_HANDLED;
+
 		disable_irq_nosync(irq);
 		ci->wakeup_int = true;
 		pm_runtime_get(ci->dev);
-- 
GitLab


From ff2b89de471da942a4d853443688113a44fd35ed Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Thu, 28 Dec 2023 19:07:53 +0800
Subject: [PATCH 2119/4076] usb: phy: mxs: remove CONFIG_USB_OTG condition for
 mxs_phy_is_otg_host()

When CONFIG_USB_OTG is not set, mxs_phy_is_otg_host() will always return
false. This behaviour is wrong. Since phy.last_event will always be set
for either host or device mode. Therefore, CONFIG_USB_OTG condition
can be removed.

Fixes: 5eda42aebb76 ("usb: phy: mxs: fix getting wrong state with mxs_phy_is_otg_host()")
cc:  <stable@vger.kernel.org>
Acked-by: Peter Chen <peter.chen@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20231228110753.1755756-3-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/phy/phy-mxs-usb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c
index acd46b72899e9..920a32cd094d6 100644
--- a/drivers/usb/phy/phy-mxs-usb.c
+++ b/drivers/usb/phy/phy-mxs-usb.c
@@ -388,8 +388,7 @@ static void __mxs_phy_disconnect_line(struct mxs_phy *mxs_phy, bool disconnect)
 
 static bool mxs_phy_is_otg_host(struct mxs_phy *mxs_phy)
 {
-	return IS_ENABLED(CONFIG_USB_OTG) &&
-		mxs_phy->phy.last_event == USB_EVENT_ID;
+	return mxs_phy->phy.last_event == USB_EVENT_ID;
 }
 
 static void mxs_phy_disconnect_line(struct mxs_phy *mxs_phy, bool on)
-- 
GitLab


From 3c7af52c7616c3aa6dacd2336ec748d4a65df8f4 Mon Sep 17 00:00:00 2001
From: Wesley Cheng <quic_wcheng@quicinc.com>
Date: Wed, 3 Jan 2024 13:49:46 -0800
Subject: [PATCH 2120/4076] usb: dwc3: gadget: Queue PM runtime idle on
 disconnect event

There is a scenario where DWC3 runtime suspend is blocked due to the
dwc->connected flag still being true while PM usage_count is zero after
DWC3 giveback is completed and the USB gadget session is being terminated.
This leads to a case where nothing schedules a PM runtime idle for the
device.

The exact condition is seen with the following sequence:
  1.  USB bus reset is issued by the host
  2.  Shortly after, or concurrently, a USB PD DR SWAP request is received
      (sink->source)
  3.  USB bus reset event handler runs and issues
      dwc3_stop_active_transfers(), and pending transfer are stopped
  4.  DWC3 usage_count decremented to 0, and runtime idle occurs while
      dwc->connected == true, returns -EBUSY
  5.  DWC3 disconnect event seen, dwc->connected set to false due to DR
      swap handling
  6.  No runtime idle after this point

Address this by issuing an asynchronous PM runtime idle call after the
disconnect event is completed, as it modifies the dwc->connected flag,
which is what blocks the initial runtime idle.

Fixes: fc8bb91bc83e ("usb: dwc3: implement runtime PM")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Wesley Cheng <quic_wcheng@quicinc.com>
Link: https://lore.kernel.org/r/20240103214946.2596-1-quic_wcheng@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index c15e965ea95a5..019368f8e9c4c 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -3989,6 +3989,13 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc)
 	usb_gadget_set_state(dwc->gadget, USB_STATE_NOTATTACHED);
 
 	dwc3_ep0_reset_state(dwc);
+
+	/*
+	 * Request PM idle to address condition where usage count is
+	 * already decremented to zero, but waiting for the disconnect
+	 * interrupt to set dwc->connected to FALSE.
+	 */
+	pm_request_idle(dwc->dev);
 }
 
 static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc)
-- 
GitLab


From 76c945730cdffb572c7767073cc6515fd3f646b4 Mon Sep 17 00:00:00 2001
From: Richard Acayan <mailingradian@gmail.com>
Date: Mon, 18 Dec 2023 11:45:33 -0500
Subject: [PATCH 2121/4076] usb: gadget: u_ether: Re-attach netif device to
 mirror detachment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In 6.7-rc1, there was a netif_device_detach call added to the
gether_disconnect function. This clears the __LINK_STATE_PRESENT bit of
the netif device and suppresses pings (ICMP messages) and TCP connection
requests from the connected host. If userspace temporarily disconnects
the gadget, such as by temporarily removing configuration in the gadget
configfs interface, network activity should continue to be processed
when the gadget is re-connected. Mirror the netif_device_detach call
with a netif_device_attach call in gether_connect to fix re-connecting
gadgets.

Link: https://gitlab.com/postmarketOS/pmaports/-/tree/6002e51b7090aeeb42947e0ca7ec22278d7227d0/main/postmarketos-base-ui/rootfs-usr-lib-NetworkManager-dispatcher.d-50-tethering.sh
Cc: stable <stable@kernel.org>
Fixes: f49449fbc21e ("usb: gadget: u_ether: Replace netif_stop_queue with netif_device_detach")
Signed-off-by: Richard Acayan <mailingradian@gmail.com>
Tested-by: Luca Weiss <luca@z3ntu.xyz>
Tested-by: Duje Mihanović <duje.mihanovic@skole.hr>
Link: https://lore.kernel.org/r/20231218164532.411125-2-mailingradian@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 9d1c40c152d86..3c5a6f6ac3414 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1163,6 +1163,8 @@ struct net_device *gether_connect(struct gether *link)
 		if (netif_running(dev->net))
 			eth_start(dev, GFP_ATOMIC);
 
+		netif_device_attach(dev->net);
+
 	/* on error, disable any endpoints  */
 	} else {
 		(void) usb_ep_disable(link->out_ep);
-- 
GitLab


From 53c6d854be4e93fa21b80bd40e3a666c3961e82c Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Wed, 27 Dec 2023 14:49:50 +0530
Subject: [PATCH 2122/4076] dt-bindings: usb: dwc3: Clean up hs_phy_irq in
 binding

The high speed related interrupts present on QC targets are as follows:

1. dp/dm irq's
These IRQ's directly reflect changes on the DP/DM pads of the SoC. These
are used as wakeup interrupts only on SoCs with non-QUSB2 targets with
exception of SDM670/SDM845/SM6350.

2. qusb2_phy irq
SoCs with QUSB2 PHY do not have separate DP/DM IRQs and expose only a
single IRQ whose behavior can be modified by the QUSB2PHY_INTR_CTRL
register. The required DPSE/DMSE configuration is done in
QUSB2PHY_INTR_CTRL register of phy address space.

3. hs_phy_irq
This is completely different from the above two and is present on all
targets with exception of a few IPQ ones. The interrupt is not enabled by
default and its functionality is mutually exclusive of qusb2_phy on QUSB
targets and DP/DM on femto phy targets.

The DTs of several QUSB2 PHY based SoCs incorrectly define "hs_phy_irq"
when they should have been "qusb2_phy_irq". On Femto phy targets, the
"hs_phy_irq" mentioned is either the actual "hs_phy_irq" or "pwr_event",
neither of which would never be triggered directly are non-functional
currently. The implementation tries to clean up this issue by addressing
the discrepencies involved and fixing the hs_phy_irq's in respective DT's.

Classify SoC's into four groups based on whether qusb2_phy interrupt
or {dp/dm}_hs_phy_irq is used for wakeup in high speed and whether the
SoCs have hs_phy_irq present in them or not. The ss_phy_irq is optional
interrupt because there are mutliple SoC's which either support only High
Speed or there are multiple controllers within same Soc and the secondary
controller is High Speed only capable.

This breaks ABI on targets running older kernels, but since the interrupt
definitions are given wrong on many targets and to establish proper rules
for usage of DWC3 interrupts on Qualcomm platforms, DT binding update is
necessary. The bindings put pwr_event as the first interrupt and ss_phy as
the last. Since all SoCs have the pwr_event (HS) interrupt, but not all
controllers have the SS PHY interrupt, this would prevent, to some extent,
expressing that the SS PHY is optional by keeping it last in the binding
schema and making sure that minItems = maxItems - 1.

No new targets have been added to schema. Only the existing ones have been
re-ordered.

Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231227091951.685-2-quic_kriskura@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/usb/qcom,dwc3.yaml    | 141 ++++++++----------
 1 file changed, 61 insertions(+), 80 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index 473c4bfaf8a2a..8242e22fde367 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -99,12 +99,29 @@ properties:
       - const: apps-usb
 
   interrupts:
-    minItems: 1
-    maxItems: 4
+    description: |
+      Different types of interrupts are used based on HS PHY used on target:
+        - pwr_event: Used for wakeup based on other power events.
+        - hs_phY_irq: Apart from DP/DM/QUSB2 PHY interrupts, there is
+                       hs_phy_irq which is not triggered by default and its
+                       functionality is mutually exclusive to that of
+                       {dp/dm}_hs_phy_irq and qusb2_phy_irq.
+        - qusb2_phy: SoCs with QUSB2 PHY do not have separate DP/DM IRQs and
+                      expose only a single IRQ whose behavior can be modified
+                      by the QUSB2PHY_INTR_CTRL register. The required DPSE/
+                      DMSE configuration is done in QUSB2PHY_INTR_CTRL register
+                      of PHY address space.
+        - {dp/dm}_hs_phy_irq: These IRQ's directly reflect changes on the DP/
+                               DM pads of the SoC. These are used for wakeup
+                               only on SoCs with non-QUSB2 targets with
+                               exception of SDM670/SDM845/SM6350.
+        - ss_phy_irq: Used for remote wakeup in Super Speed mode of operation.
+    minItems: 2
+    maxItems: 5
 
   interrupt-names:
-    minItems: 1
-    maxItems: 4
+    minItems: 2
+    maxItems: 5
 
   qcom,select-utmi-as-pipe-clk:
     description:
@@ -361,60 +378,20 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,ipq4019-dwc3
+              - qcom,ipq5018-dwc3
               - qcom,ipq6018-dwc3
-              - qcom,ipq8064-dwc3
               - qcom,ipq8074-dwc3
-              - qcom,msm8994-dwc3
-              - qcom,qcs404-dwc3
-              - qcom,sc7180-dwc3
-              - qcom,sdm670-dwc3
-              - qcom,sdm845-dwc3
-              - qcom,sdx55-dwc3
-              - qcom,sdx65-dwc3
-              - qcom,sdx75-dwc3
-              - qcom,sm4250-dwc3
-              - qcom,sm6350-dwc3
-              - qcom,sm8150-dwc3
-              - qcom,sm8250-dwc3
-              - qcom,sm8350-dwc3
-              - qcom,sm8450-dwc3
-              - qcom,sm8550-dwc3
-              - qcom,sm8650-dwc3
-    then:
-      properties:
-        interrupts:
-          items:
-            - description: The interrupt that is asserted
-                when a wakeup event is received on USB2 bus.
-            - description: The interrupt that is asserted
-                when a wakeup event is received on USB3 bus.
-            - description: Wakeup event on DM line.
-            - description: Wakeup event on DP line.
-        interrupt-names:
-          items:
-            - const: hs_phy_irq
-            - const: ss_phy_irq
-            - const: dm_hs_phy_irq
-            - const: dp_hs_phy_irq
-
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
               - qcom,msm8953-dwc3
-              - qcom,msm8996-dwc3
               - qcom,msm8998-dwc3
-              - qcom,sm6115-dwc3
-              - qcom,sm6125-dwc3
     then:
       properties:
         interrupts:
-          maxItems: 2
+          minItems: 2
+          maxItems: 3
         interrupt-names:
           items:
-            - const: hs_phy_irq
+            - const: pwr_event
+            - const: qusb2_phy
             - const: ss_phy_irq
 
   - if:
@@ -422,37 +399,21 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,ipq5018-dwc3
-              - qcom,ipq5332-dwc3
+              - qcom,msm8996-dwc3
+              - qcom,qcs404-dwc3
               - qcom,sdm660-dwc3
-    then:
-      properties:
-        interrupts:
-          minItems: 1
-          maxItems: 2
-        interrupt-names:
-          minItems: 1
-          items:
-            - const: hs_phy_irq
-            - const: ss_phy_irq
-
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
-              - qcom,sc7280-dwc3
+              - qcom,sm6115-dwc3
+              - qcom,sm6125-dwc3
     then:
       properties:
         interrupts:
           minItems: 3
           maxItems: 4
         interrupt-names:
-          minItems: 3
           items:
+            - const: pwr_event
+            - const: qusb2_phy
             - const: hs_phy_irq
-            - const: dp_hs_phy_irq
-            - const: dm_hs_phy_irq
             - const: ss_phy_irq
 
   - if:
@@ -460,7 +421,7 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,sc8280xp-dwc3
+              - qcom,ipq5332-dwc3
               - qcom,x1e80100-dwc3
     then:
       properties:
@@ -478,16 +439,35 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,ipq4019-dwc3
+              - qcom,ipq8064-dwc3
+              - qcom,msm8994-dwc3
               - qcom,sa8775p-dwc3
+              - qcom,sc7180-dwc3
+              - qcom,sc7280-dwc3
+              - qcom,sc8280xp-dwc3
+              - qcom,sdm670-dwc3
+              - qcom,sdm845-dwc3
+              - qcom,sdx55-dwc3
+              - qcom,sdx65-dwc3
+              - qcom,sdx75-dwc3
+              - qcom,sm4250-dwc3
+              - qcom,sm6350-dwc3
+              - qcom,sm8150-dwc3
+              - qcom,sm8250-dwc3
+              - qcom,sm8350-dwc3
+              - qcom,sm8450-dwc3
+              - qcom,sm8550-dwc3
+              - qcom,sm8650-dwc3
     then:
       properties:
         interrupts:
-          minItems: 3
-          maxItems: 4
+          minItems: 4
+          maxItems: 5
         interrupt-names:
-          minItems: 3
           items:
             - const: pwr_event
+            - const: hs_phy_irq
             - const: dp_hs_phy_irq
             - const: dm_hs_phy_irq
             - const: ss_phy_irq
@@ -525,12 +505,13 @@ examples:
                           <&gcc GCC_USB30_PRIM_MASTER_CLK>;
             assigned-clock-rates = <19200000>, <150000000>;
 
-            interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
+            interrupts = <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 489 IRQ_TYPE_EDGE_BOTH>,
                          <GIC_SPI 488 IRQ_TYPE_EDGE_BOTH>,
-                         <GIC_SPI 489 IRQ_TYPE_EDGE_BOTH>;
-            interrupt-names = "hs_phy_irq", "ss_phy_irq",
-                          "dm_hs_phy_irq", "dp_hs_phy_irq";
+                         <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "pwr_event", "hs_phy_irq",
+                          "dp_hs_phy_irq", "dm_hs_phy_irq", "ss_phy_irq";
 
             power-domains = <&gcc USB30_PRIM_GDSC>;
 
-- 
GitLab


From aefdcd89d72bd92e68fe0a8182ed98b4a6b91efa Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Wed, 27 Dec 2023 14:49:51 +0530
Subject: [PATCH 2123/4076] usb: dwc3: qcom: Rename hs_phy_irq to qusb2_phy_irq

For wakeup to work, driver needs to enable interrupts that depict what is
happening on the DP/DM lines. On QUSB targets, this is identified by
qusb2_phy whereas on SoCs using Femto PHY, separate {dp,dm}_hs_phy_irq's
are used instead.

The implementation incorrectly names qusb2_phy interrupts as "hs_phy_irq".
Clean this up so that driver would be using only qusb2/(dp & dm) for wakeup
purposes.

For devices running older kernels, this won't break any functionality
because the interrupt configurations in QUSB2 PHY based SoCs is done
by configuring QUSB2PHY_INTR_CTRL register in PHY address space and it was
never armed properly right from the start.

Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/20231227091951.685-3-quic_kriskura@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-qcom.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index fdf6d5d3c2ada..dbd6a5b2b2892 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -57,7 +57,7 @@ struct dwc3_acpi_pdata {
 	u32			qscratch_base_offset;
 	u32			qscratch_base_size;
 	u32			dwc3_core_base_size;
-	int			hs_phy_irq_index;
+	int			qusb2_phy_irq_index;
 	int			dp_hs_phy_irq_index;
 	int			dm_hs_phy_irq_index;
 	int			ss_phy_irq_index;
@@ -73,7 +73,7 @@ struct dwc3_qcom {
 	int			num_clocks;
 	struct reset_control	*resets;
 
-	int			hs_phy_irq;
+	int			qusb2_phy_irq;
 	int			dp_hs_phy_irq;
 	int			dm_hs_phy_irq;
 	int			ss_phy_irq;
@@ -372,7 +372,7 @@ static void dwc3_qcom_disable_wakeup_irq(int irq)
 
 static void dwc3_qcom_disable_interrupts(struct dwc3_qcom *qcom)
 {
-	dwc3_qcom_disable_wakeup_irq(qcom->hs_phy_irq);
+	dwc3_qcom_disable_wakeup_irq(qcom->qusb2_phy_irq);
 
 	if (qcom->usb2_speed == USB_SPEED_LOW) {
 		dwc3_qcom_disable_wakeup_irq(qcom->dm_hs_phy_irq);
@@ -389,7 +389,7 @@ static void dwc3_qcom_disable_interrupts(struct dwc3_qcom *qcom)
 
 static void dwc3_qcom_enable_interrupts(struct dwc3_qcom *qcom)
 {
-	dwc3_qcom_enable_wakeup_irq(qcom->hs_phy_irq, 0);
+	dwc3_qcom_enable_wakeup_irq(qcom->qusb2_phy_irq, 0);
 
 	/*
 	 * Configure DP/DM line interrupts based on the USB2 device attached to
@@ -542,19 +542,19 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 	int irq;
 	int ret;
 
-	irq = dwc3_qcom_get_irq(pdev, "hs_phy_irq",
-				pdata ? pdata->hs_phy_irq_index : -1);
+	irq = dwc3_qcom_get_irq(pdev, "qusb2_phy",
+				pdata ? pdata->qusb2_phy_irq_index : -1);
 	if (irq > 0) {
 		/* Keep wakeup interrupts disabled until suspend */
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
 					IRQF_ONESHOT | IRQF_NO_AUTOEN,
-					"qcom_dwc3 HS", qcom);
+					"qcom_dwc3 QUSB2", qcom);
 		if (ret) {
-			dev_err(qcom->dev, "hs_phy_irq failed: %d\n", ret);
+			dev_err(qcom->dev, "qusb2_phy_irq failed: %d\n", ret);
 			return ret;
 		}
-		qcom->hs_phy_irq = irq;
+		qcom->qusb2_phy_irq = irq;
 	}
 
 	irq = dwc3_qcom_get_irq(pdev, "dp_hs_phy_irq",
@@ -1058,7 +1058,7 @@ static const struct dwc3_acpi_pdata sdm845_acpi_pdata = {
 	.qscratch_base_offset = SDM845_QSCRATCH_BASE_OFFSET,
 	.qscratch_base_size = SDM845_QSCRATCH_SIZE,
 	.dwc3_core_base_size = SDM845_DWC3_CORE_SIZE,
-	.hs_phy_irq_index = 1,
+	.qusb2_phy_irq_index = 1,
 	.dp_hs_phy_irq_index = 4,
 	.dm_hs_phy_irq_index = 3,
 	.ss_phy_irq_index = 2
@@ -1068,7 +1068,7 @@ static const struct dwc3_acpi_pdata sdm845_acpi_urs_pdata = {
 	.qscratch_base_offset = SDM845_QSCRATCH_BASE_OFFSET,
 	.qscratch_base_size = SDM845_QSCRATCH_SIZE,
 	.dwc3_core_base_size = SDM845_DWC3_CORE_SIZE,
-	.hs_phy_irq_index = 1,
+	.qusb2_phy_irq_index = 1,
 	.dp_hs_phy_irq_index = 4,
 	.dm_hs_phy_irq_index = 3,
 	.ss_phy_irq_index = 2,
-- 
GitLab


From 7db25e95589e7a8871de2c5dad88eba5f432e2dd Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:31 +0100
Subject: [PATCH 2124/4076] dt-bindings: usb: qcom,dwc3: Fix SDM660 clock
 description

SDM660 was abusingly referencing one of the internal bus clocks, that
were recently dropped from Linux (because the original implementation
did not make much sense), circumventing the interconnect framework.

Drop it.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-1-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/qcom,dwc3.yaml | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index 8242e22fde367..63d150b216c52 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -308,8 +308,8 @@ allOf:
     then:
       properties:
         clocks:
-          minItems: 5
-          maxItems: 6
+          minItems: 4
+          maxItems: 5
         clock-names:
           oneOf:
             - items:
@@ -318,13 +318,11 @@ allOf:
                 - const: iface
                 - const: sleep
                 - const: mock_utmi
-                - const: bus
             - items:
                 - const: cfg_noc
                 - const: core
                 - const: sleep
                 - const: mock_utmi
-                - const: bus
 
   - if:
       properties:
-- 
GitLab


From 51b6148026f043cd3ec222dbe5efa82103a3e3c9 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:32 +0100
Subject: [PATCH 2125/4076] arm64: dts: qcom: msm8916: Drop RPM bus clocks

Some nodes are abusingly referencing some of the internal bus clocks,
that were recently removed in Linux (because the original implementation
did not make much sense), managing them as if they were the only devices
on an NoC bus.

These clocks are now handled from within the icc framework and are
no longer registered from within the CCF. Remove them.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-2-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/msm8916.dtsi | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index 4f799b536a92a..f7e00276b15a4 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -539,9 +539,6 @@
 			compatible = "qcom,msm8916-bimc";
 			reg = <0x00400000 0x62000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
 		};
 
 		tsens: thermal-sensor@4a9000 {
@@ -574,18 +571,12 @@
 			compatible = "qcom,msm8916-pcnoc";
 			reg = <0x00500000 0x11000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_PCNOC_CLK>,
-				 <&rpmcc RPM_SMD_PCNOC_A_CLK>;
 		};
 
 		snoc: interconnect@580000 {
 			compatible = "qcom,msm8916-snoc";
 			reg = <0x00580000 0x14000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		stm: stm@802000 {
-- 
GitLab


From 19f837ae4e4ac4ebdec861038bffff9781100a9a Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:33 +0100
Subject: [PATCH 2126/4076] arm64: dts: qcom: msm8996: Drop RPM bus clocks

Some nodes are abusingly referencing some of the internal bus clocks,
that were recently removed in Linux (because the original implementation
did not make much sense), managing them as if they were the only devices
on an NoC bus.

These clocks are now handled from within the icc framework and are
no longer registered from within the CCF. Remove them.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-3-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/msm8996.dtsi | 27 ++++-----------------------
 1 file changed, 4 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 6ba9da9e6a8b9..587e9b50a256e 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -799,9 +799,6 @@
 			compatible = "qcom,msm8996-bimc";
 			reg = <0x00408000 0x5a000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
 		};
 
 		tsens0: thermal-sensor@4a9000 {
@@ -852,18 +849,12 @@
 			compatible = "qcom,msm8996-cnoc";
 			reg = <0x00500000 0x1000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_CNOC_CLK>,
-				 <&rpmcc RPM_SMD_CNOC_A_CLK>;
 		};
 
 		snoc: interconnect@524000 {
 			compatible = "qcom,msm8996-snoc";
 			reg = <0x00524000 0x1c000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		a0noc: interconnect@543000 {
@@ -883,19 +874,14 @@
 			compatible = "qcom,msm8996-a1noc";
 			reg = <0x00562000 0x5000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_AGGR1_NOC_CLK>,
-				 <&rpmcc RPM_SMD_AGGR1_NOC_A_CLK>;
 		};
 
 		a2noc: interconnect@583000 {
 			compatible = "qcom,msm8996-a2noc";
 			reg = <0x00583000 0x7000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a", "aggre2_ufs_axi", "ufs_axi";
-			clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>,
-				 <&gcc GCC_AGGRE2_UFS_AXI_CLK>,
+			clock-names = "aggre2_ufs_axi", "ufs_axi";
+			clocks = <&gcc GCC_AGGRE2_UFS_AXI_CLK>,
 				 <&gcc GCC_UFS_AXI_CLK>;
 		};
 
@@ -903,19 +889,14 @@
 			compatible = "qcom,msm8996-mnoc";
 			reg = <0x005a4000 0x1c000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a", "iface";
-			clocks = <&rpmcc RPM_SMD_MMAXI_CLK>,
-				 <&rpmcc RPM_SMD_MMAXI_A_CLK>,
-				 <&mmcc AHB_CLK_SRC>;
+			clock-names = "iface";
+			clocks = <&mmcc AHB_CLK_SRC>;
 		};
 
 		pnoc: interconnect@5c0000 {
 			compatible = "qcom,msm8996-pnoc";
 			reg = <0x005c0000 0x3000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_PCNOC_CLK>,
-				 <&rpmcc RPM_SMD_PCNOC_A_CLK>;
 		};
 
 		tcsr_mutex: hwlock@740000 {
-- 
GitLab


From 437afcefdbec8972598f6a029a7ed4cb8f52dfd0 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:34 +0100
Subject: [PATCH 2127/4076] arm64: dts: qcom: qcs404: Drop RPM bus clocks

Some nodes are abusingly referencing some of the internal bus clocks,
that were recently removed in Linux (because the original implementation
did not make much sense), managing them as if they were the only devices
on an NoC bus.

These clocks are now handled from within the icc framework and are
no longer registered from within the CCF. Remove them.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-4-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/qcs404.dtsi | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi
index 2721f32dfb710..317a0df30b834 100644
--- a/arch/arm64/boot/dts/qcom/qcs404.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi
@@ -558,9 +558,6 @@
 			reg = <0x00400000 0x80000>;
 			compatible = "qcom,qcs404-bimc";
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				<&rpmcc RPM_SMD_BIMC_A_CLK>;
 		};
 
 		tsens: thermal-sensor@4a9000 {
@@ -601,18 +598,12 @@
 			reg = <0x00500000 0x15080>;
 			compatible = "qcom,qcs404-pcnoc";
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_PNOC_CLK>,
-				<&rpmcc RPM_SMD_PNOC_A_CLK>;
 		};
 
 		snoc: interconnect@580000 {
 			reg = <0x00580000 0x23080>;
 			compatible = "qcom,qcs404-snoc";
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				<&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		remoteproc_cdsp: remoteproc@b00000 {
-- 
GitLab


From 283730be6bbb7ec6a45ba6b9c7db5feeaad93f63 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:35 +0100
Subject: [PATCH 2128/4076] arm64: dts: qcom: sdm630: Drop RPM bus clocks

Some nodes are abusingly referencing some of the internal bus clocks,
that were recently removed in Linux (because the original implementation
did not make much sense), managing them as if they were the only devices
on an NoC bus.

These clocks are now handled from within the icc framework and are
no longer registered from within the CCF. Remove them.

Reviewed-by: Marijn Suijten <marijn.suijten@somainline.org>
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-5-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/sdm630.dtsi | 53 +++++++---------------------
 1 file changed, 12 insertions(+), 41 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi
index 775700f78e0fe..513fe5e76b688 100644
--- a/arch/arm64/boot/dts/qcom/sdm630.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi
@@ -606,9 +606,6 @@
 			compatible = "qcom,sdm660-bimc";
 			reg = <0x01008000 0x78000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
 		};
 
 		restart@10ac000 {
@@ -620,28 +617,17 @@
 			compatible = "qcom,sdm660-cnoc";
 			reg = <0x01500000 0x10000>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_CNOC_CLK>,
-				 <&rpmcc RPM_SMD_CNOC_A_CLK>;
 		};
 
 		snoc: interconnect@1626000 {
 			compatible = "qcom,sdm660-snoc";
 			reg = <0x01626000 0x7090>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 		};
 
 		anoc2_smmu: iommu@16c0000 {
 			compatible = "qcom,sdm630-smmu-v2", "qcom,smmu-v2";
 			reg = <0x016c0000 0x40000>;
-
-			assigned-clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			assigned-clock-rates = <1000>;
-			clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			clock-names = "bus";
 			#global-interrupts = <2>;
 			#iommu-cells = <1>;
 
@@ -686,16 +672,12 @@
 			compatible = "qcom,sdm660-a2noc";
 			reg = <0x01704000 0xc100>;
 			#interconnect-cells = <1>;
-			clock-names = "bus",
-				      "bus_a",
-				      "ipa",
+			clock-names = "ipa",
 				      "ufs_axi",
 				      "aggre2_ufs_axi",
 				      "aggre2_usb3_axi",
 				      "cfg_noc_usb2_axi";
-			clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>,
-				 <&rpmcc RPM_SMD_IPA_CLK>,
+			clocks = <&rpmcc RPM_SMD_IPA_CLK>,
 				 <&gcc GCC_UFS_AXI_CLK>,
 				 <&gcc GCC_AGGRE2_UFS_AXI_CLK>,
 				 <&gcc GCC_AGGRE2_USB3_AXI_CLK>,
@@ -706,10 +688,8 @@
 			compatible = "qcom,sdm660-mnoc";
 			reg = <0x01745000 0xa010>;
 			#interconnect-cells = <1>;
-			clock-names = "bus", "bus_a", "iface";
-			clocks = <&rpmcc RPM_SMD_MMSSNOC_AXI_CLK>,
-				 <&rpmcc RPM_SMD_MMSSNOC_AXI_CLK_A>,
-				 <&mmcc AHB_CLK_SRC>;
+			clock-names = "iface";
+			clocks = <&mmcc AHB_CLK_SRC>;
 		};
 
 		tsens: thermal-sensor@10ae000 {
@@ -1186,7 +1166,9 @@
 			clocks = <&gcc GCC_GPU_CFG_AHB_CLK>,
 				 <&gcc GCC_BIMC_GFX_CLK>,
 				 <&gcc GCC_GPU_BIMC_GFX_CLK>;
-			clock-names = "iface", "mem", "mem_iface";
+			clock-names = "iface",
+			              "mem",
+				      "mem_iface";
 			#global-interrupts = <2>;
 			#iommu-cells = <1>;
 
@@ -1288,20 +1270,16 @@
 				 <&gcc GCC_USB30_MASTER_CLK>,
 				 <&gcc GCC_AGGRE2_USB3_AXI_CLK>,
 				 <&gcc GCC_USB30_SLEEP_CLK>,
-				 <&gcc GCC_USB30_MOCK_UTMI_CLK>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
+				 <&gcc GCC_USB30_MOCK_UTMI_CLK>;
 			clock-names = "cfg_noc",
 				      "core",
 				      "iface",
 				      "sleep",
-				      "mock_utmi",
-				      "bus";
+				      "mock_utmi";
 
 			assigned-clocks = <&gcc GCC_USB30_MOCK_UTMI_CLK>,
-					  <&gcc GCC_USB30_MASTER_CLK>,
-					  <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			assigned-clock-rates = <19200000>, <120000000>,
-					       <19200000>;
+					  <&gcc GCC_USB30_MASTER_CLK>;
+			assigned-clock-rates = <19200000>, <120000000>;
 
 			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
@@ -2204,10 +2182,9 @@
 
 			clocks = <&mmcc MNOC_AHB_CLK>,
 				 <&mmcc BIMC_SMMU_AHB_CLK>,
-				 <&rpmcc RPM_SMD_MMSSNOC_AXI_CLK>,
 				 <&mmcc BIMC_SMMU_AXI_CLK>;
 			clock-names = "iface-mm", "iface-smmu",
-				      "bus-mm", "bus-smmu";
+				      "bus-smmu";
 			#global-interrupts = <2>;
 			#iommu-cells = <1>;
 
@@ -2324,12 +2301,6 @@
 			compatible = "qcom,sdm660-gnoc";
 			reg = <0x17900000 0xe000>;
 			#interconnect-cells = <1>;
-			/*
-			 * This one apparently features no clocks,
-			 * so let's not mess with the driver needlessly
-			 */
-			clock-names = "bus", "bus_a";
-			clocks = <&xo_board>, <&xo_board>;
 		};
 
 		apcs_glb: mailbox@17911000 {
-- 
GitLab


From 09ee216d0b9f63f44fa59651a9e7403c8fd05ea8 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:36 +0100
Subject: [PATCH 2129/4076] arm64: dts: qcom: msm8939: Drop RPM bus clocks

Some nodes are abusingly referencing some of the internal bus clocks,
that were recently removed in Linux (because the original implementation
did not make much sense), managing them as if they were the only devices
on an NoC bus.

These clocks are now handled from within the icc framework and are
no longer registered from within the CCF. Remove them.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-6-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/msm8939.dtsi | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/msm8939.dtsi b/arch/arm64/boot/dts/qcom/msm8939.dtsi
index 324b5d26db400..b2e1f2f6c620c 100644
--- a/arch/arm64/boot/dts/qcom/msm8939.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8939.dtsi
@@ -601,9 +601,6 @@
 		bimc: interconnect@400000 {
 			compatible = "qcom,msm8939-bimc";
 			reg = <0x00400000 0x62000>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_BIMC_CLK>,
-				 <&rpmcc RPM_SMD_BIMC_A_CLK>;
 			#interconnect-cells = <1>;
 		};
 
@@ -647,25 +644,16 @@
 		pcnoc: interconnect@500000 {
 			compatible = "qcom,msm8939-pcnoc";
 			reg = <0x00500000 0x11000>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_PCNOC_CLK>,
-				 <&rpmcc RPM_SMD_PCNOC_A_CLK>;
 			#interconnect-cells = <1>;
 		};
 
 		snoc: interconnect@580000 {
 			compatible = "qcom,msm8939-snoc";
 			reg = <0x00580000 0x14080>;
-			clock-names = "bus", "bus_a";
-			clocks = <&rpmcc RPM_SMD_SNOC_CLK>,
-				 <&rpmcc RPM_SMD_SNOC_A_CLK>;
 			#interconnect-cells = <1>;
 
 			snoc_mm: interconnect-snoc {
 				compatible = "qcom,msm8939-snoc-mm";
-				clock-names = "bus", "bus_a";
-				clocks = <&rpmcc RPM_SMD_SYSMMNOC_CLK>,
-					 <&rpmcc RPM_SMD_SYSMMNOC_A_CLK>;
 				#interconnect-cells = <1>;
 			};
 		};
-- 
GitLab


From 8ee8587fdcac12c8c73d1e8797b2eb9abe5cdf18 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:37 +0100
Subject: [PATCH 2130/4076] arm64: dts: qcom: msm8998: Remove AGGRE2 clock from
 SLPI

The AGGRE2 clock is a clock for the entire AGGRE2 bus, managed from
within the interconnect driver. Attaching it to SLPI was a total hack.
Get rid of it.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-7-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/msm8998.dtsi | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
index b485bf925ce61..dd676d1b038d2 100644
--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
@@ -1615,9 +1615,8 @@
 
 			px-supply = <&vreg_lvs2a_1p8>;
 
-			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			clock-names = "xo", "aggre2";
+			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>;
+			clock-names = "xo";
 
 			memory-region = <&slpi_mem>;
 
-- 
GitLab


From 30d2641df650e38aa5f8687a666bac036bc204dd Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:38 +0100
Subject: [PATCH 2131/4076] arm64: dts: qcom: msm8996: Remove AGGRE2 clock from
 SLPI

The AGGRE2 clock is a clock for the entire AGGRE2 bus, managed from
within the interconnect driver. Attaching it to SLPI was a total hack.
Get rid of it.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-8-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/msm8996.dtsi | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 587e9b50a256e..b292cace93a64 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -2434,9 +2434,8 @@
 					  "handover",
 					  "stop-ack";
 
-			clocks = <&xo_board>,
-				 <&rpmcc RPM_SMD_AGGR2_NOC_CLK>;
-			clock-names = "xo", "aggre2";
+			clocks = <&xo_board>;
+			clock-names = "xo";
 
 			memory-region = <&slpi_mem>;
 
-- 
GitLab


From 3eee5b4085e223339cfcadadc4aab6199c1f09ec Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 3 Jan 2024 21:15:39 +0100
Subject: [PATCH 2132/4076] arm64: dts: qcom: msm8996: Remove PNoC clock from
 MSS

The PNoC clock is a clock for the entire PNoC bus, managed from
within the interconnect driver. Attaching it to MSS was a total hack.
Get rid of it and take the liberty to make the clock-names entries
more readable.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20230721-topic-rpm_clk_cleanup-v3-9-a66e698932e3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/qcom/msm8996.dtsi | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index b292cace93a64..65cb3913b6197 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -2480,10 +2480,15 @@
 				 <&gcc GCC_MSS_GPLL0_DIV_CLK>,
 				 <&gcc GCC_MSS_SNOC_AXI_CLK>,
 				 <&gcc GCC_MSS_MNOC_BIMC_AXI_CLK>,
-				 <&rpmcc RPM_SMD_PCNOC_CLK>,
 				 <&rpmcc RPM_SMD_QDSS_CLK>;
-			clock-names = "iface", "bus", "mem", "xo", "gpll0_mss",
-				      "snoc_axi", "mnoc_axi", "pnoc", "qdss";
+			clock-names = "iface",
+				      "bus",
+				      "mem",
+				      "xo",
+				      "gpll0_mss",
+				      "snoc_axi",
+				      "mnoc_axi",
+				      "qdss";
 
 			resets = <&gcc GCC_MSS_RESTART>;
 			reset-names = "mss_restart";
-- 
GitLab


From 223b4ef5a3b75c4500facf07f99a925232eaf113 Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Thu, 4 Jan 2024 14:16:38 +0800
Subject: [PATCH 2133/4076] dt-bindings: usb: mtk-xhci: add a property for Gen1
 isoc-in transfer issue

For Gen1 isoc-in endpoint on controller before about SSUSB IPM v1.6.0, it
still send out unexpected ACK after receiving a short packet in burst
transfer, this will cause an exception on connected device, specially for
a 4k camera.
Add a quirk property "rx-fifo-depth" to work around this hardware issue,
prefer to use 3k bytes;
The side-effect is that it may cause performance drop about 10%, including
bulk transfer.

Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/20240104061640.7335-1-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/usb/mediatek,mtk-xhci.yaml    | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
index e9644e333d781..924fd3d748a88 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
@@ -124,6 +124,17 @@ properties:
       defined in the xHCI spec on MTK's controller.
     default: 5000
 
+  rx-fifo-depth:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      It is a quirk used to work around Gen1 isoc-in endpoint transfer issue
+      that still send out unexpected ACK after device finishes the burst
+      transfer with a short packet and cause an exception, specially on a 4K
+      camera device, it happens on controller before about IPM v1.6.0;
+      the side-effect is that it may cause performance drop about 10%,
+      including bulk transfer, prefer to use 3k here. The size is in bytes.
+    enum: [1024, 2048, 3072, 4096]
+
   # the following properties are only used for case 1
   wakeup-source:
     description: enable USB remote wakeup, see power/wakeup-source.txt
-- 
GitLab


From 017dbfc05c31284150819890b4cc86a699cbdb71 Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Thu, 4 Jan 2024 14:16:39 +0800
Subject: [PATCH 2134/4076] usb: xhci-mtk: fix a short packet issue of gen1
 isoc-in transfer

For Gen1 isoc-in transfer, host still send out unexpected ACK after device
finish the burst with a short packet, this will cause an exception on the
connected device, such as, a usb 4k camera.
It can be fixed by setting rxfifo depth less than 4k bytes, prefer to use
3k here, the side-effect is that may cause performance drop about 10%,
including bulk transfer.

Fixes: 926d60ae64a6 ("usb: xhci-mtk: modify the SOF/ITP interval for mt8195")
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/20240104061640.7335-2-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mtk.c | 40 +++++++++++++++++++++++++++++++++++--
 drivers/usb/host/xhci-mtk.h |  2 ++
 2 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index bbdf1b0b7be11..3252e3d2d79cd 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -7,6 +7,7 @@
  *  Chunfeng Yun <chunfeng.yun@mediatek.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/dma-mapping.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
@@ -73,6 +74,9 @@
 #define FRMCNT_LEV1_RANG	(0x12b << 8)
 #define FRMCNT_LEV1_RANG_MASK	GENMASK(19, 8)
 
+#define HSCH_CFG1		0x960
+#define SCH3_RXFIFO_DEPTH_MASK	GENMASK(21, 20)
+
 #define SS_GEN2_EOF_CFG		0x990
 #define SSG2EOF_OFFSET		0x3c
 
@@ -114,6 +118,8 @@
 #define SSC_IP_SLEEP_EN	BIT(4)
 #define SSC_SPM_INT_EN		BIT(1)
 
+#define SCH_FIFO_TO_KB(x)	((x) >> 10)
+
 enum ssusb_uwk_vers {
 	SSUSB_UWK_V1 = 1,
 	SSUSB_UWK_V2,
@@ -165,6 +171,35 @@ static void xhci_mtk_set_frame_interval(struct xhci_hcd_mtk *mtk)
 	writel(value, hcd->regs + SS_GEN2_EOF_CFG);
 }
 
+/*
+ * workaround: usb3.2 gen1 isoc rx hw issue
+ * host send out unexpected ACK afer device fininsh a burst transfer with
+ * a short packet.
+ */
+static void xhci_mtk_rxfifo_depth_set(struct xhci_hcd_mtk *mtk)
+{
+	struct usb_hcd *hcd = mtk->hcd;
+	u32 value;
+
+	if (!mtk->rxfifo_depth)
+		return;
+
+	value = readl(hcd->regs + HSCH_CFG1);
+	value &= ~SCH3_RXFIFO_DEPTH_MASK;
+	value |= FIELD_PREP(SCH3_RXFIFO_DEPTH_MASK,
+			    SCH_FIFO_TO_KB(mtk->rxfifo_depth) - 1);
+	writel(value, hcd->regs + HSCH_CFG1);
+}
+
+static void xhci_mtk_init_quirk(struct xhci_hcd_mtk *mtk)
+{
+	/* workaround only for mt8195 */
+	xhci_mtk_set_frame_interval(mtk);
+
+	/* workaround for SoCs using SSUSB about before IPM v1.6.0 */
+	xhci_mtk_rxfifo_depth_set(mtk);
+}
+
 static int xhci_mtk_host_enable(struct xhci_hcd_mtk *mtk)
 {
 	struct mu3c_ippc_regs __iomem *ippc = mtk->ippc_regs;
@@ -448,8 +483,7 @@ static int xhci_mtk_setup(struct usb_hcd *hcd)
 		if (ret)
 			return ret;
 
-		/* workaround only for mt8195 */
-		xhci_mtk_set_frame_interval(mtk);
+		xhci_mtk_init_quirk(mtk);
 	}
 
 	ret = xhci_gen_setup(hcd, xhci_mtk_quirks);
@@ -527,6 +561,8 @@ static int xhci_mtk_probe(struct platform_device *pdev)
 	of_property_read_u32(node, "mediatek,u2p-dis-msk",
 			     &mtk->u2p_dis_msk);
 
+	of_property_read_u32(node, "rx-fifo-depth", &mtk->rxfifo_depth);
+
 	ret = usb_wakeup_of_property_parse(mtk, node);
 	if (ret) {
 		dev_err(dev, "failed to parse uwk property\n");
diff --git a/drivers/usb/host/xhci-mtk.h b/drivers/usb/host/xhci-mtk.h
index 39f7ae7d30871..f5e2bd66bb1b2 100644
--- a/drivers/usb/host/xhci-mtk.h
+++ b/drivers/usb/host/xhci-mtk.h
@@ -171,6 +171,8 @@ struct xhci_hcd_mtk {
 	struct regmap *uwk;
 	u32 uwk_reg_base;
 	u32 uwk_vers;
+	/* quirk */
+	u32 rxfifo_depth;
 };
 
 static inline struct xhci_hcd_mtk *hcd_to_mtk(struct usb_hcd *hcd)
-- 
GitLab


From 33d4137d57997476404bc968fcc5b2ed5639a22f Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Thu, 4 Jan 2024 14:16:40 +0800
Subject: [PATCH 2135/4076] arm64: dts: mediatek: mt8195: Add 'rx-fifo-depth'
 for cherry

Add the quirk property "rx-fifo-depth" to work around Gen1 isoc-in
transfer issue which send out unexpected ACK even after device
already finished the burst transfer with a short patcket, specially
for a 4K camera device.

Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/20240104061640.7335-3-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
index 5a7cab489ff3a..d416fd3f29171 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
@@ -1183,6 +1183,7 @@
 &xhci0 {
 	status = "okay";
 
+	rx-fifo-depth = <3072>;
 	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	vbus-supply = <&usb_vbus>;
 };
@@ -1190,6 +1191,7 @@
 &xhci1 {
 	status = "okay";
 
+	rx-fifo-depth = <3072>;
 	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	vbus-supply = <&usb_vbus>;
 };
-- 
GitLab


From 49a78b05d5ca1e23fd737747a8757b8bdc319b30 Mon Sep 17 00:00:00 2001
From: Yajun Deng <yajun.deng@linux.dev>
Date: Thu, 4 Jan 2024 11:28:22 +0800
Subject: [PATCH 2136/4076] USB: core: Use device_driver directly in struct
 usb_driver and usb_device_driver

There is usbdrv_wrap in struct usb_driver and usb_device_driver, it
contains device_driver and for_devices. for_devices is used to
distinguish between device drivers and interface drivers.

Like the is_usb_device(), it tests the type of the device. We can test
that if the probe of device_driver is equal to usb_probe_device in
is_usb_device_driver(), and then the struct usbdrv_wrap is no longer
needed.

Clean up struct usbdrv_wrap, use device_driver directly in struct
usb_driver and usb_device_driver. This makes the code cleaner.

Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20240104032822.1896596-1-yajun.deng@linux.dev
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bluetooth/btusb.c                     |  6 +-
 drivers/net/can/usb/peak_usb/pcan_usb_core.c  |  2 +-
 .../broadcom/brcm80211/brcmfmac/usb.c         |  2 +-
 drivers/net/wireless/marvell/mwifiex/usb.c    |  2 +-
 drivers/usb/core/driver.c                     | 59 ++++++++++---------
 drivers/usb/core/usb.c                        |  2 +-
 drivers/usb/core/usb.h                        |  8 +--
 drivers/usb/misc/onboard_usb_hub.c            |  2 +-
 drivers/usb/serial/bus.c                      |  2 +-
 drivers/usb/serial/usb-serial.c               |  2 +-
 drivers/usb/storage/uas.c                     |  2 +-
 drivers/usb/usbip/stub_main.c                 |  8 +--
 include/linux/usb.h                           | 24 +++-----
 13 files changed, 53 insertions(+), 68 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index b8e9de887b5de..02b3b1825403a 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -4790,10 +4790,8 @@ static struct usb_driver btusb_driver = {
 	.disable_hub_initiated_lpm = 1,
 
 #ifdef CONFIG_DEV_COREDUMP
-	.drvwrap = {
-		.driver = {
-			.coredump = btusb_coredump,
-		},
+	.driver = {
+		.coredump = btusb_coredump,
 	},
 #endif
 };
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 24ad9f593a773..1efa39e134f4c 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -1143,7 +1143,7 @@ static void __exit peak_usb_exit(void)
 	int err;
 
 	/* last chance do send any synchronous commands here */
-	err = driver_for_each_device(&peak_usb_driver.drvwrap.driver, NULL,
+	err = driver_for_each_device(&peak_usb_driver.driver, NULL,
 				     NULL, peak_usb_do_device_exit);
 	if (err)
 		pr_err("%s: failed to stop all can devices (err %d)\n",
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 2178675ae1a44..0ccf735316c24 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -1581,7 +1581,7 @@ static int brcmf_usb_reset_device(struct device *dev, void *notused)
 
 void brcmf_usb_exit(void)
 {
-	struct device_driver *drv = &brcmf_usbdrvr.drvwrap.driver;
+	struct device_driver *drv = &brcmf_usbdrvr.driver;
 	int ret;
 
 	brcmf_dbg(USB, "Enter\n");
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index d3ab9572e7115..515e6db410f28 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -687,7 +687,7 @@ static struct usb_driver mwifiex_usb_driver = {
 	.suspend = mwifiex_usb_suspend,
 	.resume = mwifiex_usb_resume,
 	.soft_unbind = 1,
-	.drvwrap.driver = {
+	.driver = {
 		.coredump = mwifiex_usb_coredump,
 	},
 };
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 1dc0c04130438..e01b1913d02bf 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -189,13 +189,13 @@ static int usb_create_newid_files(struct usb_driver *usb_drv)
 		goto exit;
 
 	if (usb_drv->probe != NULL) {
-		error = driver_create_file(&usb_drv->drvwrap.driver,
+		error = driver_create_file(&usb_drv->driver,
 					   &driver_attr_new_id);
 		if (error == 0) {
-			error = driver_create_file(&usb_drv->drvwrap.driver,
+			error = driver_create_file(&usb_drv->driver,
 					&driver_attr_remove_id);
 			if (error)
-				driver_remove_file(&usb_drv->drvwrap.driver,
+				driver_remove_file(&usb_drv->driver,
 						&driver_attr_new_id);
 		}
 	}
@@ -209,9 +209,9 @@ static void usb_remove_newid_files(struct usb_driver *usb_drv)
 		return;
 
 	if (usb_drv->probe != NULL) {
-		driver_remove_file(&usb_drv->drvwrap.driver,
+		driver_remove_file(&usb_drv->driver,
 				&driver_attr_remove_id);
-		driver_remove_file(&usb_drv->drvwrap.driver,
+		driver_remove_file(&usb_drv->driver,
 				   &driver_attr_new_id);
 	}
 }
@@ -552,7 +552,7 @@ int usb_driver_claim_interface(struct usb_driver *driver,
 	if (!iface->authorized)
 		return -ENODEV;
 
-	dev->driver = &driver->drvwrap.driver;
+	dev->driver = &driver->driver;
 	usb_set_intfdata(iface, data);
 	iface->needs_binding = 0;
 
@@ -615,7 +615,7 @@ void usb_driver_release_interface(struct usb_driver *driver,
 	struct device *dev = &iface->dev;
 
 	/* this should never happen, don't release something that's not ours */
-	if (!dev->driver || dev->driver != &driver->drvwrap.driver)
+	if (!dev->driver || dev->driver != &driver->driver)
 		return;
 
 	/* don't release from within disconnect() */
@@ -950,7 +950,7 @@ static int __usb_bus_reprobe_drivers(struct device *dev, void *data)
 	int ret;
 
 	/* Don't reprobe if current driver isn't usb_generic_driver */
-	if (dev->driver != &usb_generic_driver.drvwrap.driver)
+	if (dev->driver != &usb_generic_driver.driver)
 		return 0;
 
 	udev = to_usb_device(dev);
@@ -964,6 +964,11 @@ static int __usb_bus_reprobe_drivers(struct device *dev, void *data)
 	return 0;
 }
 
+bool is_usb_device_driver(const struct device_driver *drv)
+{
+	return drv->probe == usb_probe_device;
+}
+
 /**
  * usb_register_device_driver - register a USB device (not interface) driver
  * @new_udriver: USB operations for the device driver
@@ -983,15 +988,14 @@ int usb_register_device_driver(struct usb_device_driver *new_udriver,
 	if (usb_disabled())
 		return -ENODEV;
 
-	new_udriver->drvwrap.for_devices = 1;
-	new_udriver->drvwrap.driver.name = new_udriver->name;
-	new_udriver->drvwrap.driver.bus = &usb_bus_type;
-	new_udriver->drvwrap.driver.probe = usb_probe_device;
-	new_udriver->drvwrap.driver.remove = usb_unbind_device;
-	new_udriver->drvwrap.driver.owner = owner;
-	new_udriver->drvwrap.driver.dev_groups = new_udriver->dev_groups;
+	new_udriver->driver.name = new_udriver->name;
+	new_udriver->driver.bus = &usb_bus_type;
+	new_udriver->driver.probe = usb_probe_device;
+	new_udriver->driver.remove = usb_unbind_device;
+	new_udriver->driver.owner = owner;
+	new_udriver->driver.dev_groups = new_udriver->dev_groups;
 
-	retval = driver_register(&new_udriver->drvwrap.driver);
+	retval = driver_register(&new_udriver->driver);
 
 	if (!retval) {
 		pr_info("%s: registered new device driver %s\n",
@@ -1023,7 +1027,7 @@ void usb_deregister_device_driver(struct usb_device_driver *udriver)
 	pr_info("%s: deregistering device driver %s\n",
 			usbcore_name, udriver->name);
 
-	driver_unregister(&udriver->drvwrap.driver);
+	driver_unregister(&udriver->driver);
 }
 EXPORT_SYMBOL_GPL(usb_deregister_device_driver);
 
@@ -1051,18 +1055,17 @@ int usb_register_driver(struct usb_driver *new_driver, struct module *owner,
 	if (usb_disabled())
 		return -ENODEV;
 
-	new_driver->drvwrap.for_devices = 0;
-	new_driver->drvwrap.driver.name = new_driver->name;
-	new_driver->drvwrap.driver.bus = &usb_bus_type;
-	new_driver->drvwrap.driver.probe = usb_probe_interface;
-	new_driver->drvwrap.driver.remove = usb_unbind_interface;
-	new_driver->drvwrap.driver.owner = owner;
-	new_driver->drvwrap.driver.mod_name = mod_name;
-	new_driver->drvwrap.driver.dev_groups = new_driver->dev_groups;
+	new_driver->driver.name = new_driver->name;
+	new_driver->driver.bus = &usb_bus_type;
+	new_driver->driver.probe = usb_probe_interface;
+	new_driver->driver.remove = usb_unbind_interface;
+	new_driver->driver.owner = owner;
+	new_driver->driver.mod_name = mod_name;
+	new_driver->driver.dev_groups = new_driver->dev_groups;
 	spin_lock_init(&new_driver->dynids.lock);
 	INIT_LIST_HEAD(&new_driver->dynids.list);
 
-	retval = driver_register(&new_driver->drvwrap.driver);
+	retval = driver_register(&new_driver->driver);
 	if (retval)
 		goto out;
 
@@ -1077,7 +1080,7 @@ out:
 	return retval;
 
 out_newid:
-	driver_unregister(&new_driver->drvwrap.driver);
+	driver_unregister(&new_driver->driver);
 
 	pr_err("%s: error %d registering interface driver %s\n",
 		usbcore_name, retval, new_driver->name);
@@ -1102,7 +1105,7 @@ void usb_deregister(struct usb_driver *driver)
 			usbcore_name, driver->name);
 
 	usb_remove_newid_files(driver);
-	driver_unregister(&driver->drvwrap.driver);
+	driver_unregister(&driver->driver);
 	usb_free_dynids(driver);
 }
 EXPORT_SYMBOL_GPL(usb_deregister);
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 2a938cf47ccd6..dc8d9228a5e75 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -431,7 +431,7 @@ struct usb_interface *usb_find_interface(struct usb_driver *drv, int minor)
 	struct device *dev;
 
 	argb.minor = minor;
-	argb.drv = &drv->drvwrap.driver;
+	argb.drv = &drv->driver;
 
 	dev = bus_find_device(&usb_bus_type, NULL, &argb, __find_interface);
 
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 60363153fc3f3..bfecb50773b6b 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -175,13 +175,7 @@ static inline int is_root_hub(struct usb_device *udev)
 	return (udev->parent == NULL);
 }
 
-/* Do the same for device drivers and interface drivers. */
-
-static inline int is_usb_device_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct usbdrv_wrap, driver)->
-			for_devices;
-}
+extern bool is_usb_device_driver(const struct device_driver *drv);
 
 /* for labeling diagnostics */
 extern const char *usbcore_name;
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index c09fb6bd7d7d7..0dd2b032c90b9 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -244,7 +244,7 @@ static void onboard_hub_attach_usb_driver(struct work_struct *work)
 {
 	int err;
 
-	err = driver_attach(&onboard_hub_usbdev_driver.drvwrap.driver);
+	err = driver_attach(&onboard_hub_usbdev_driver.driver);
 	if (err)
 		pr_err("Failed to attach USB driver: %pe\n", ERR_PTR(err));
 }
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 3eb8dc3a1a8f5..6c812d01b37d7 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -113,7 +113,7 @@ static ssize_t new_id_store(struct device_driver *driver,
 	if (retval >= 0 && usb_drv->usb_driver != NULL)
 		retval = usb_store_new_id(&usb_drv->usb_driver->dynids,
 					  usb_drv->usb_driver->id_table,
-					  &usb_drv->usb_driver->drvwrap.driver,
+					  &usb_drv->usb_driver->driver,
 					  buf, count);
 	return retval;
 }
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 17b09f03ef845..f1e91eb7f8a41 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1521,7 +1521,7 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[]
 
 	/* Now set udriver's id_table and look for matches */
 	udriver->id_table = id_table;
-	rc = driver_attach(&udriver->drvwrap.driver);
+	rc = driver_attach(&udriver->driver);
 	return 0;
 
 err_deregister_drivers:
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 696bb0b235992..9707f53cfda9c 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -1246,7 +1246,7 @@ static struct usb_driver uas_driver = {
 	.suspend = uas_suspend,
 	.resume = uas_resume,
 	.reset_resume = uas_reset_resume,
-	.drvwrap.driver.shutdown = uas_shutdown,
+	.driver.shutdown = uas_shutdown,
 	.id_table = uas_usb_ids,
 };
 
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index 0a6624d37929e..79110a69d697c 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -377,14 +377,14 @@ static int __init usbip_host_init(void)
 		goto err_usb_register;
 	}
 
-	ret = driver_create_file(&stub_driver.drvwrap.driver,
+	ret = driver_create_file(&stub_driver.driver,
 				 &driver_attr_match_busid);
 	if (ret) {
 		pr_err("driver_create_file failed\n");
 		goto err_create_file;
 	}
 
-	ret = driver_create_file(&stub_driver.drvwrap.driver,
+	ret = driver_create_file(&stub_driver.driver,
 				 &driver_attr_rebind);
 	if (ret) {
 		pr_err("driver_create_file failed\n");
@@ -402,10 +402,10 @@ err_usb_register:
 
 static void __exit usbip_host_exit(void)
 {
-	driver_remove_file(&stub_driver.drvwrap.driver,
+	driver_remove_file(&stub_driver.driver,
 			   &driver_attr_match_busid);
 
-	driver_remove_file(&stub_driver.drvwrap.driver,
+	driver_remove_file(&stub_driver.driver,
 			   &driver_attr_rebind);
 
 	/*
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 07556341ba2b4..9e52179872a50 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1143,16 +1143,6 @@ extern ssize_t usb_store_new_id(struct usb_dynids *dynids,
 
 extern ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf);
 
-/**
- * struct usbdrv_wrap - wrapper for driver-model structure
- * @driver: The driver-model core driver structure.
- * @for_devices: Non-zero for device drivers, 0 for interface drivers.
- */
-struct usbdrv_wrap {
-	struct device_driver driver;
-	int for_devices;
-};
-
 /**
  * struct usb_driver - identifies USB interface driver to usbcore
  * @name: The driver name should be unique among USB drivers,
@@ -1193,7 +1183,7 @@ struct usbdrv_wrap {
  *	is bound to the driver.
  * @dynids: used internally to hold the list of dynamically added device
  *	ids for this driver.
- * @drvwrap: Driver-model core structure wrapper.
+ * @driver: The driver-model core driver structure.
  * @no_dynamic_id: if set to 1, the USB core will not allow dynamic ids to be
  *	added to this driver by preventing the sysfs file from being created.
  * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
@@ -1241,13 +1231,13 @@ struct usb_driver {
 	const struct attribute_group **dev_groups;
 
 	struct usb_dynids dynids;
-	struct usbdrv_wrap drvwrap;
+	struct device_driver driver;
 	unsigned int no_dynamic_id:1;
 	unsigned int supports_autosuspend:1;
 	unsigned int disable_hub_initiated_lpm:1;
 	unsigned int soft_unbind:1;
 };
-#define	to_usb_driver(d) container_of(d, struct usb_driver, drvwrap.driver)
+#define	to_usb_driver(d) container_of(d, struct usb_driver, driver)
 
 /**
  * struct usb_device_driver - identifies USB device driver to usbcore
@@ -1268,7 +1258,7 @@ struct usb_driver {
  *	on to call the normal usb_choose_configuration().
  * @dev_groups: Attributes attached to the device that will be created once it
  *	is bound to the driver.
- * @drvwrap: Driver-model core structure wrapper.
+ * @driver: The driver-model core driver structure.
  * @id_table: used with @match() to select better matching driver at
  * 	probe() time.
  * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
@@ -1277,7 +1267,7 @@ struct usb_driver {
  *	resume and suspend functions will be called in addition to the driver's
  *	own, so this part of the setup does not need to be replicated.
  *
- * USB drivers must provide all the fields listed above except drvwrap,
+ * USB drivers must provide all the fields listed above except driver,
  * match, and id_table.
  */
 struct usb_device_driver {
@@ -1293,13 +1283,13 @@ struct usb_device_driver {
 	int (*choose_configuration) (struct usb_device *udev);
 
 	const struct attribute_group **dev_groups;
-	struct usbdrv_wrap drvwrap;
+	struct device_driver driver;
 	const struct usb_device_id *id_table;
 	unsigned int supports_autosuspend:1;
 	unsigned int generic_subclass:1;
 };
 #define	to_usb_device_driver(d) container_of(d, struct usb_device_driver, \
-		drvwrap.driver)
+		driver)
 
 /**
  * struct usb_class_driver - identifies a USB driver that wants to use the USB major number
-- 
GitLab


From c99b38c412343053e9af187e595793c8805bb9b8 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Tue, 2 Jan 2024 13:45:09 -0800
Subject: [PATCH 2137/4076] xhci: add support to allocate several interrupters

Modify the XHCI drivers to accommodate for handling multiple event rings in
case there are multiple interrupters.  Add the required APIs so clients are
able to allocate/request for an interrupter ring, and pass this information
back to the client driver.  This allows for users to handle the resource
accordingly, such as passing the event ring base address to an audio DSP.
There is no actual support for multiple MSI/MSI-X vectors.

[export xhci_initialize_ring_info() -wcheng]

Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Wesley Cheng <quic_wcheng@quicinc.com>
Link: https://lore.kernel.org/r/20240102214549.22498-2-quic_wcheng@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-debugfs.c |   2 +-
 drivers/usb/host/xhci-mem.c     | 108 ++++++++++++++++++++++++++++----
 drivers/usb/host/xhci-ring.c    |   2 +-
 drivers/usb/host/xhci.c         |  51 +++++++++------
 drivers/usb/host/xhci.h         |   6 +-
 5 files changed, 137 insertions(+), 32 deletions(-)

diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 6d142cd61bd6b..f8ba15e7c225c 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -693,7 +693,7 @@ void xhci_debugfs_init(struct xhci_hcd *xhci)
 				     "command-ring",
 				     xhci->debugfs_root);
 
-	xhci_debugfs_create_ring_dir(xhci, &xhci->interrupter->event_ring,
+	xhci_debugfs_create_ring_dir(xhci, &xhci->interrupters[0]->event_ring,
 				     "event-ring",
 				     xhci->debugfs_root);
 
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 6faa854152ef1..4460fa7e9fab9 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -323,6 +323,7 @@ void xhci_initialize_ring_info(struct xhci_ring *ring,
 	 */
 	ring->num_trbs_free = ring->num_segs * (TRBS_PER_SEGMENT - 1) - 1;
 }
+EXPORT_SYMBOL_GPL(xhci_initialize_ring_info);
 
 /* Allocate segments and link them for a ring */
 static int xhci_alloc_segments_for_ring(struct xhci_hcd *xhci,
@@ -1855,6 +1856,31 @@ xhci_free_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir)
 	kfree(ir);
 }
 
+void xhci_remove_secondary_interrupter(struct usb_hcd *hcd, struct xhci_interrupter *ir)
+{
+	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+	unsigned int intr_num;
+
+	/* interrupter 0 is primary interrupter, don't touch it */
+	if (!ir || !ir->intr_num || ir->intr_num >= xhci->max_interrupters)
+		xhci_dbg(xhci, "Invalid secondary interrupter, can't remove\n");
+
+	/* fixme, should we check xhci->interrupter[intr_num] == ir */
+	/* fixme locking */
+
+	spin_lock_irq(&xhci->lock);
+
+	intr_num = ir->intr_num;
+
+	xhci_remove_interrupter(xhci, ir);
+	xhci->interrupters[intr_num] = NULL;
+
+	spin_unlock_irq(&xhci->lock);
+
+	xhci_free_interrupter(xhci, ir);
+}
+EXPORT_SYMBOL_GPL(xhci_remove_secondary_interrupter);
+
 void xhci_mem_cleanup(struct xhci_hcd *xhci)
 {
 	struct device	*dev = xhci_to_hcd(xhci)->self.sysdev;
@@ -1862,10 +1888,14 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 
 	cancel_delayed_work_sync(&xhci->cmd_timer);
 
-	xhci_remove_interrupter(xhci, xhci->interrupter);
-	xhci_free_interrupter(xhci, xhci->interrupter);
-	xhci->interrupter = NULL;
-	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed primary event ring");
+	for (i = 0; i < xhci->max_interrupters; i++) {
+		if (xhci->interrupters[i]) {
+			xhci_remove_interrupter(xhci, xhci->interrupters[i]);
+			xhci_free_interrupter(xhci, xhci->interrupters[i]);
+			xhci->interrupters[i] = NULL;
+		}
+	}
+	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed interrupters");
 
 	if (xhci->cmd_ring)
 		xhci_ring_free(xhci, xhci->cmd_ring);
@@ -1935,6 +1965,7 @@ no_bw:
 	for (i = 0; i < xhci->num_port_caps; i++)
 		kfree(xhci->port_caps[i].psi);
 	kfree(xhci->port_caps);
+	kfree(xhci->interrupters);
 	xhci->num_port_caps = 0;
 
 	xhci->usb2_rhub.ports = NULL;
@@ -1943,6 +1974,7 @@ no_bw:
 	xhci->rh_bw = NULL;
 	xhci->ext_caps = NULL;
 	xhci->port_caps = NULL;
+	xhci->interrupters = NULL;
 
 	xhci->page_size = 0;
 	xhci->page_shift = 0;
@@ -2248,18 +2280,20 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
 }
 
 static struct xhci_interrupter *
-xhci_alloc_interrupter(struct xhci_hcd *xhci, gfp_t flags)
+xhci_alloc_interrupter(struct xhci_hcd *xhci, int segs, gfp_t flags)
 {
 	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 	struct xhci_interrupter *ir;
-	unsigned int num_segs;
+	unsigned int num_segs = segs;
 	int ret;
 
 	ir = kzalloc_node(sizeof(*ir), flags, dev_to_node(dev));
 	if (!ir)
 		return NULL;
 
-	num_segs = min_t(unsigned int, 1 << HCS_ERST_MAX(xhci->hcs_params2),
+	/* number of ring segments should be greater than 0 */
+	if (segs <= 0)
+		num_segs = min_t(unsigned int, 1 << HCS_ERST_MAX(xhci->hcs_params2),
 			 ERST_MAX_SEGS);
 
 	ir->event_ring = xhci_ring_alloc(xhci, num_segs, 1, TYPE_EVENT, 0,
@@ -2294,6 +2328,13 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir,
 		return -EINVAL;
 	}
 
+	if (xhci->interrupters[intr_num]) {
+		xhci_warn(xhci, "Interrupter %d\n already set up", intr_num);
+		return -EINVAL;
+	}
+
+	xhci->interrupters[intr_num] = ir;
+	ir->intr_num = intr_num;
 	ir->ir_set = &xhci->run_regs->ir_set[intr_num];
 
 	/* set ERST count with the number of entries in the segment table */
@@ -2313,10 +2354,52 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir,
 	return 0;
 }
 
+struct xhci_interrupter *
+xhci_create_secondary_interrupter(struct usb_hcd *hcd, int num_seg)
+{
+	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+	struct xhci_interrupter *ir;
+	unsigned int i;
+	int err = -ENOSPC;
+
+	if (!xhci->interrupters || xhci->max_interrupters <= 1)
+		return NULL;
+
+	ir = xhci_alloc_interrupter(xhci, num_seg, GFP_KERNEL);
+	if (!ir)
+		return NULL;
+
+	spin_lock_irq(&xhci->lock);
+
+	/* Find available secondary interrupter, interrupter 0 is reserved for primary */
+	for (i = 1; i < xhci->max_interrupters; i++) {
+		if (xhci->interrupters[i] == NULL) {
+			err = xhci_add_interrupter(xhci, ir, i);
+			break;
+		}
+	}
+
+	spin_unlock_irq(&xhci->lock);
+
+	if (err) {
+		xhci_warn(xhci, "Failed to add secondary interrupter, max interrupters %d\n",
+			  xhci->max_interrupters);
+		xhci_free_interrupter(xhci, ir);
+		return NULL;
+	}
+
+	xhci_dbg(xhci, "Add secondary interrupter %d, max interrupters %d\n",
+		 i, xhci->max_interrupters);
+
+	return ir;
+}
+EXPORT_SYMBOL_GPL(xhci_create_secondary_interrupter);
+
 int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 {
-	dma_addr_t	dma;
+	struct xhci_interrupter *ir;
 	struct device	*dev = xhci_to_hcd(xhci)->self.sysdev;
+	dma_addr_t	dma;
 	unsigned int	val, val2;
 	u64		val_64;
 	u32		page_size, temp;
@@ -2440,11 +2523,14 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	/* Allocate and set up primary interrupter 0 with an event ring. */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 		       "Allocating primary event ring");
-	xhci->interrupter = xhci_alloc_interrupter(xhci, flags);
-	if (!xhci->interrupter)
+	xhci->interrupters = kcalloc_node(xhci->max_interrupters, sizeof(*xhci->interrupters),
+					  flags, dev_to_node(dev));
+
+	ir = xhci_alloc_interrupter(xhci, 0, flags);
+	if (!ir)
 		goto fail;
 
-	if (xhci_add_interrupter(xhci, xhci->interrupter, 0))
+	if (xhci_add_interrupter(xhci, ir, 0))
 		goto fail;
 
 	xhci->isoc_bei_interval = AVOID_BEI_INTERVAL_MAX;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 2c1d614b3b0fb..33806ae966f90 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3061,7 +3061,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
 	writel(status, &xhci->op_regs->status);
 
 	/* This is the handler of the primary interrupter */
-	ir = xhci->interrupter;
+	ir = xhci->interrupters[0];
 	if (!hcd->msi_enabled) {
 		u32 irq_pending;
 		irq_pending = readl(&ir->ir_set->irq_pending);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 7d5b94905b9c5..c057c42c36f4c 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -480,7 +480,7 @@ static int xhci_init(struct usb_hcd *hcd)
 
 static int xhci_run_finished(struct xhci_hcd *xhci)
 {
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir = xhci->interrupters[0];
 	unsigned long	flags;
 	u32		temp;
 
@@ -532,7 +532,7 @@ int xhci_run(struct usb_hcd *hcd)
 	u64 temp_64;
 	int ret;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir = xhci->interrupters[0];
 	/* Start the xHCI host controller running only after the USB 2.0 roothub
 	 * is setup.
 	 */
@@ -596,7 +596,7 @@ void xhci_stop(struct usb_hcd *hcd)
 {
 	u32 temp;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir = xhci->interrupters[0];
 
 	mutex_lock(&xhci->mutex);
 
@@ -692,36 +692,51 @@ EXPORT_SYMBOL_GPL(xhci_shutdown);
 #ifdef CONFIG_PM
 static void xhci_save_registers(struct xhci_hcd *xhci)
 {
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir;
+	unsigned int i;
 
 	xhci->s3.command = readl(&xhci->op_regs->command);
 	xhci->s3.dev_nt = readl(&xhci->op_regs->dev_notification);
 	xhci->s3.dcbaa_ptr = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr);
 	xhci->s3.config_reg = readl(&xhci->op_regs->config_reg);
 
-	if (!ir)
-		return;
+	/* save both primary and all secondary interrupters */
+	/* fixme, shold we lock  to prevent race with remove secondary interrupter? */
+	for (i = 0; i < xhci->max_interrupters; i++) {
+		ir = xhci->interrupters[i];
+		if (!ir)
+			continue;
 
-	ir->s3_erst_size = readl(&ir->ir_set->erst_size);
-	ir->s3_erst_base = xhci_read_64(xhci, &ir->ir_set->erst_base);
-	ir->s3_erst_dequeue = xhci_read_64(xhci, &ir->ir_set->erst_dequeue);
-	ir->s3_irq_pending = readl(&ir->ir_set->irq_pending);
-	ir->s3_irq_control = readl(&ir->ir_set->irq_control);
+		ir->s3_erst_size = readl(&ir->ir_set->erst_size);
+		ir->s3_erst_base = xhci_read_64(xhci, &ir->ir_set->erst_base);
+		ir->s3_erst_dequeue = xhci_read_64(xhci, &ir->ir_set->erst_dequeue);
+		ir->s3_irq_pending = readl(&ir->ir_set->irq_pending);
+		ir->s3_irq_control = readl(&ir->ir_set->irq_control);
+	}
 }
 
 static void xhci_restore_registers(struct xhci_hcd *xhci)
 {
-	struct xhci_interrupter *ir = xhci->interrupter;
+	struct xhci_interrupter *ir;
+	unsigned int i;
 
 	writel(xhci->s3.command, &xhci->op_regs->command);
 	writel(xhci->s3.dev_nt, &xhci->op_regs->dev_notification);
 	xhci_write_64(xhci, xhci->s3.dcbaa_ptr, &xhci->op_regs->dcbaa_ptr);
 	writel(xhci->s3.config_reg, &xhci->op_regs->config_reg);
-	writel(ir->s3_erst_size, &ir->ir_set->erst_size);
-	xhci_write_64(xhci, ir->s3_erst_base, &ir->ir_set->erst_base);
-	xhci_write_64(xhci, ir->s3_erst_dequeue, &ir->ir_set->erst_dequeue);
-	writel(ir->s3_irq_pending, &ir->ir_set->irq_pending);
-	writel(ir->s3_irq_control, &ir->ir_set->irq_control);
+
+	/* FIXME should we lock to protect against freeing of interrupters */
+	for (i = 0; i < xhci->max_interrupters; i++) {
+		ir = xhci->interrupters[i];
+		if (!ir)
+			continue;
+
+		writel(ir->s3_erst_size, &ir->ir_set->erst_size);
+		xhci_write_64(xhci, ir->s3_erst_base, &ir->ir_set->erst_base);
+		xhci_write_64(xhci, ir->s3_erst_dequeue, &ir->ir_set->erst_dequeue);
+		writel(ir->s3_irq_pending, &ir->ir_set->irq_pending);
+		writel(ir->s3_irq_control, &ir->ir_set->irq_control);
+	}
 }
 
 static void xhci_set_cmd_ring_deq(struct xhci_hcd *xhci)
@@ -1084,7 +1099,7 @@ int xhci_resume(struct xhci_hcd *xhci, pm_message_t msg)
 		xhci_dbg(xhci, "// Disabling event ring interrupts\n");
 		temp = readl(&xhci->op_regs->status);
 		writel((temp & ~0x1fff) | STS_EINT, &xhci->op_regs->status);
-		xhci_disable_interrupter(xhci->interrupter);
+		xhci_disable_interrupter(xhci->interrupters[0]);
 
 		xhci_dbg(xhci, "cleaning up memory\n");
 		xhci_mem_cleanup(xhci);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 90e6b6ef7bd20..a5c72a634e6a9 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1774,7 +1774,7 @@ struct xhci_hcd {
 	struct reset_control *reset;
 	/* data structures */
 	struct xhci_device_context_array *dcbaa;
-	struct xhci_interrupter *interrupter;
+	struct xhci_interrupter **interrupters;
 	struct xhci_ring	*cmd_ring;
 	unsigned int            cmd_ring_state;
 #define CMD_RING_STATE_RUNNING         (1 << 0)
@@ -2085,6 +2085,10 @@ struct xhci_container_ctx *xhci_alloc_container_ctx(struct xhci_hcd *xhci,
 		int type, gfp_t flags);
 void xhci_free_container_ctx(struct xhci_hcd *xhci,
 		struct xhci_container_ctx *ctx);
+struct xhci_interrupter *
+xhci_create_secondary_interrupter(struct usb_hcd *hcd, int num_seg);
+void xhci_remove_secondary_interrupter(struct usb_hcd
+				       *hcd, struct xhci_interrupter *ir);
 
 /* xHCI host controller glue */
 typedef void (*xhci_get_quirks_t)(struct device *, struct xhci_hcd *);
-- 
GitLab


From b1541a80414d13b1da9b528b09e68a4a518ae8fe Mon Sep 17 00:00:00 2001
From: Wesley Cheng <quic_wcheng@quicinc.com>
Date: Tue, 2 Jan 2024 13:45:22 -0800
Subject: [PATCH 2138/4076] dt-bindings: usb: xhci: Add num-hc-interrupters
 definition

Add the definition for how many interrupts the XHCI host controller should
allocate.  XHCI can potentially support up to 1024 interrupters, which
implementations may want to limit.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Wesley Cheng <quic_wcheng@quicinc.com>
Link: https://lore.kernel.org/r/20240102214549.22498-15-quic_wcheng@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/usb-xhci.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.yaml b/Documentation/devicetree/bindings/usb/usb-xhci.yaml
index 180a261c3e8f3..4238ae896ef6f 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.yaml
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.yaml
@@ -29,6 +29,12 @@ properties:
     description: Interrupt moderation interval
     default: 5000
 
+  num-hc-interrupters:
+    description: Maximum number of interrupters to allocate
+    $ref: /schemas/types.yaml#/definitions/uint16
+    minimum: 1
+    maximum: 1024
+
 additionalProperties: true
 
 examples:
-- 
GitLab


From 79c58ab241bea76c197d09091eb85b753d5d4416 Mon Sep 17 00:00:00 2001
From: Wesley Cheng <quic_wcheng@quicinc.com>
Date: Tue, 2 Jan 2024 13:45:23 -0800
Subject: [PATCH 2139/4076] dt-bindings: usb: dwc3: Limit num-hc-interrupters
 definition

Ensure that the number of XHCI secondary interrupters defined for a DWC3
based implementation is limited to 8.  XHCI in general can potentially
support up to 1024 interrupters.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Wesley Cheng <quic_wcheng@quicinc.com>
Link: https://lore.kernel.org/r/20240102214549.22498-16-quic_wcheng@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/snps,dwc3.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
index ee5af4b381b1b..203a1eb66691f 100644
--- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
@@ -432,6 +432,10 @@ properties:
     items:
       enum: [1, 4, 8, 16, 32, 64, 128, 256]
 
+  num-hc-interrupters:
+    maximum: 8
+    default: 1
+
   port:
     $ref: /schemas/graph.yaml#/properties/port
     description:
-- 
GitLab


From cb86a3383aa7b9bb891daca691e596f6bfe52d82 Mon Sep 17 00:00:00 2001
From: Vamshi Gajjela <vamshigajjela@google.com>
Date: Thu, 9 Nov 2023 12:04:16 +0530
Subject: [PATCH 2140/4076] serial: core: Update uart_poll_timeout() function
 to return unsigned long

The function uart_fifo_timeout() returns an unsigned long value, which
is the number of jiffies. Therefore, change the variable timeout in the
function uart_poll_timeout() from int to unsigned long.
Change the return type of the function uart_poll_timeout() from int to
unsigned long to be consistent with the type of timeout values.

Signed-off-by: Vamshi Gajjela <vamshigajjela@google.com>
Link: https://lore.kernel.org/r/20231109063417.3971005-2-vamshigajjela@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/serial_core.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 89f7b6c63598c..536b2581d3e20 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -852,9 +852,9 @@ static inline unsigned long uart_fifo_timeout(struct uart_port *port)
 }
 
 /* Base timer interval for polling */
-static inline int uart_poll_timeout(struct uart_port *port)
+static inline unsigned long uart_poll_timeout(struct uart_port *port)
 {
-	int timeout = uart_fifo_timeout(port);
+	unsigned long timeout = uart_fifo_timeout(port);
 
 	return timeout > 6 ? (timeout / 2 - 2) : 1;
 }
-- 
GitLab


From d4303e0b9f51b9dc97bd682332a1e2ded919bedc Mon Sep 17 00:00:00 2001
From: Vamshi Gajjela <vamshigajjela@google.com>
Date: Thu, 9 Nov 2023 12:04:17 +0530
Subject: [PATCH 2141/4076] serial: core: Clean up uart_update_timeout()
 function

Rename the variable size to temp and change its data type from
unsigned int to u64 to avoid type casting in multiplication. Remove the
intermediate variable frame_time and use temp instead to accommodate
the nanoseconds(ns). port->frame_time is an unsigned int, therefore an
explicit cast is used to improve readability. Having said this unsigned
int is sufficinet to hold frame time duration in nanoseconds for all
the standard baudrates.

Consider 9600 baud, it takes 1/9600 seconds for one bit, for a total of
10 bits (start, 8-bit data, stop) 10/9600=1.04 ms for 1 byte transfer,
frame_time here is 1041667ns. As baudrate increases frame_time
decreases, say for 115200 baud it is 86806ns.

To avoid costly 64-bit arithmetic we do not upconvert the type for
variable frame_time as overflow happens for extremely low baudrates
which are impractical and are not used in real-world applications.

Signed-off-by: Vamshi Gajjela <vamshigajjela@google.com>
Link: https://lore.kernel.org/r/20231109063417.3971005-3-vamshigajjela@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 80085b151b34d..1147fb1b39f28 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -410,11 +410,10 @@ void
 uart_update_timeout(struct uart_port *port, unsigned int cflag,
 		    unsigned int baud)
 {
-	unsigned int size = tty_get_frame_size(cflag);
-	u64 frame_time;
+	u64 temp = tty_get_frame_size(cflag);
 
-	frame_time = (u64)size * NSEC_PER_SEC;
-	port->frame_time = DIV64_U64_ROUND_UP(frame_time, baud);
+	temp *= NSEC_PER_SEC;
+	port->frame_time = (unsigned int)DIV64_U64_ROUND_UP(temp, baud);
 }
 EXPORT_SYMBOL(uart_update_timeout);
 
-- 
GitLab


From 76ac8e29855b06331d77a1d237a28ce97ac67a38 Mon Sep 17 00:00:00 2001
From: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Date: Fri, 1 Dec 2023 15:15:53 +0800
Subject: [PATCH 2142/4076] tty: serial: Cleanup the bit shift with macro

This patch replaces the bit shift code with "_BITUL()" macro inside
"serial_rs485" struct.

Signed-off-by: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Link: https://lore.kernel.org/r/20231201071554.258607-2-crescentcy.hsieh@moxa.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/serial.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h
index 53bc1af67a411..6c75ebdd77975 100644
--- a/include/uapi/linux/serial.h
+++ b/include/uapi/linux/serial.h
@@ -11,6 +11,7 @@
 #ifndef _UAPI_LINUX_SERIAL_H
 #define _UAPI_LINUX_SERIAL_H
 
+#include <linux/const.h>
 #include <linux/types.h>
 
 #include <linux/tty_flags.h>
@@ -140,14 +141,14 @@ struct serial_icounter_struct {
  */
 struct serial_rs485 {
 	__u32	flags;
-#define SER_RS485_ENABLED		(1 << 0)
-#define SER_RS485_RTS_ON_SEND		(1 << 1)
-#define SER_RS485_RTS_AFTER_SEND	(1 << 2)
-#define SER_RS485_RX_DURING_TX		(1 << 4)
-#define SER_RS485_TERMINATE_BUS		(1 << 5)
-#define SER_RS485_ADDRB			(1 << 6)
-#define SER_RS485_ADDR_RECV		(1 << 7)
-#define SER_RS485_ADDR_DEST		(1 << 8)
+#define SER_RS485_ENABLED		_BITUL(0)
+#define SER_RS485_RTS_ON_SEND		_BITUL(1)
+#define SER_RS485_RTS_AFTER_SEND	_BITUL(2)
+#define SER_RS485_RX_DURING_TX		_BITUL(3)
+#define SER_RS485_TERMINATE_BUS		_BITUL(4)
+#define SER_RS485_ADDRB			_BITUL(5)
+#define SER_RS485_ADDR_RECV		_BITUL(6)
+#define SER_RS485_ADDR_DEST		_BITUL(7)
 
 	__u32	delay_rts_before_send;
 	__u32	delay_rts_after_send;
-- 
GitLab


From 6056f20f27e99fb67582f299468328505f130e36 Mon Sep 17 00:00:00 2001
From: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Date: Fri, 1 Dec 2023 15:15:54 +0800
Subject: [PATCH 2143/4076] tty: serial: Add RS422 flag to struct serial_rs485

Add "SER_RS485_MODE_RS422" flag to struct serial_rs485, so that serial
port can switch interface into RS422 if supported by using ioctl command
"TIOCSRS485".

By treating RS422 as a mode of RS485, which means while enabling RS422
there are two flags need to be set (SER_RS485_ENABLED and
SER_RS485_MODE_RS422), it would make things much easier. For example
some places that checks for "SER_RS485_ENABLED" won't need to be rewritten.

Signed-off-by: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Link: https://lore.kernel.org/r/20231201071554.258607-3-crescentcy.hsieh@moxa.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 6 ++++++
 include/uapi/linux/serial.h      | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 1147fb1b39f28..d35371c076b27 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1370,6 +1370,12 @@ static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs4
 		return;
 	}
 
+	/* Clear other RS485 flags but SER_RS485_TERMINATE_BUS and return if enabling RS422 */
+	if (rs485->flags & SER_RS485_MODE_RS422) {
+		rs485->flags &= (SER_RS485_ENABLED | SER_RS485_MODE_RS422 | SER_RS485_TERMINATE_BUS);
+		return;
+	}
+
 	/* Pick sane settings if the user hasn't */
 	if ((supported_flags & (SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND)) &&
 	    !(rs485->flags & SER_RS485_RTS_ON_SEND) ==
diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h
index 6c75ebdd77975..9086367db0435 100644
--- a/include/uapi/linux/serial.h
+++ b/include/uapi/linux/serial.h
@@ -138,6 +138,7 @@ struct serial_icounter_struct {
  * * %SER_RS485_ADDRB		- Enable RS485 addressing mode.
  * * %SER_RS485_ADDR_RECV - Receive address filter (enables @addr_recv). Requires %SER_RS485_ADDRB.
  * * %SER_RS485_ADDR_DEST - Destination address (enables @addr_dest). Requires %SER_RS485_ADDRB.
+ * * %SER_RS485_MODE_RS422	- Enable RS422. Requires %SER_RS485_ENABLED.
  */
 struct serial_rs485 {
 	__u32	flags;
@@ -149,6 +150,7 @@ struct serial_rs485 {
 #define SER_RS485_ADDRB			_BITUL(5)
 #define SER_RS485_ADDR_RECV		_BITUL(6)
 #define SER_RS485_ADDR_DEST		_BITUL(7)
+#define SER_RS485_MODE_RS422		_BITUL(8)
 
 	__u32	delay_rts_before_send;
 	__u32	delay_rts_after_send;
-- 
GitLab


From f0635480462f3fd03953b2af2ea8d3229e2a7e08 Mon Sep 17 00:00:00 2001
From: Antony Pavlov <antonynpavlov@gmail.com>
Date: Sun, 17 Dec 2023 22:56:01 +0300
Subject: [PATCH 2144/4076] tty/serial: altera_uart: use more informative
 labels in /proc/interrupts

Prior to this patch:

~# cat /proc/interrupts
...
 40:        123          0     GIC-0  72 Level     altera_uart
 41:          9          0     GIC-0  73 Level     altera_uart

After this patch:

~# cat /proc/interrupts
...
 40:          6          0     GIC-0  72 Level     ff200100.fpga-uart0
 41:         28          0     GIC-0  73 Level     ff200200.fpga-uart1

Signed-off-by: Antony Pavlov <antonynpavlov@gmail.com>
Acked-by: Tobias Klauser <tklauser@distanz.ch>
Link: https://lore.kernel.org/r/20231217195601.236002-1-antonynpavlov@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/altera_uart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 081bec31dbd82..897f0995b2fe7 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -305,7 +305,7 @@ static int altera_uart_startup(struct uart_port *port)
 		int ret;
 
 		ret = request_irq(port->irq, altera_uart_interrupt, 0,
-				DRV_NAME, port);
+				dev_name(port->dev), port);
 		if (ret) {
 			pr_err(DRV_NAME ": unable to attach Altera UART %d "
 			       "interrupt vector=%d\n", port->line, port->irq);
-- 
GitLab


From 3e189470cad27d41a3a9dc02649f965b7ed1c90f Mon Sep 17 00:00:00 2001
From: Christoph Niedermaier <cniedermaier@dh-electronics.com>
Date: Sun, 24 Dec 2023 10:32:09 +0100
Subject: [PATCH 2145/4076] serial: imx: Correct clock error message in
 function probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Correct the clock error message by changing the clock name.

Fixes: 1e512d45332b ("serial: imx: add error messages when .probe fails")
Signed-off-by: Christoph Niedermaier <cniedermaier@dh-electronics.com>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231224093209.2612-1-cniedermaier@dh-electronics.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index e7e952bb7bb8a..55105a4b1af80 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -2327,7 +2327,7 @@ static int imx_uart_probe(struct platform_device *pdev)
 	/* For register access, we only need to enable the ipg clock. */
 	ret = clk_prepare_enable(sport->clk_ipg);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to enable per clk: %d\n", ret);
+		dev_err(&pdev->dev, "failed to enable ipg clk: %d\n", ret);
 		return ret;
 	}
 
-- 
GitLab


From 788aeef392d27545ae99af2875068a9dd0531d5f Mon Sep 17 00:00:00 2001
From: Michael Trimarchi <michael@amarulasolutions.com>
Date: Sun, 24 Dec 2023 14:12:00 +0100
Subject: [PATCH 2146/4076] tty: serial: kgdboc: Fix 8250_* kgdb over serial

Check if port type is not PORT_UNKNOWN during poll_init.
The kgdboc calls the tty_find_polling_driver that check
if the serial is able to use poll_init. The poll_init calls
the uart uart_poll_init that try to configure the uart with the
selected boot parameters. The uart must be ready before setting
parameters. Seems that PORT_UNKNOWN is already used by other
functions in serial_core to detect uart status, so use the same
to avoid to use it in invalid state.

The crash happen for instance in am62x architecture where the 8250
register the platform driver after the 8250 core is initialized.

Follow the report crash coming from KGDB

Thread 2 received signal SIGSEGV, Segmentation fault.
[Switching to Thread 1]
_outb (addr=<optimized out>, value=<optimized out>) at ./include/asm-generic/io.h:584
584		__raw_writeb(value, PCI_IOBASE + addr);
(gdb) bt

This section of the code is too early because in this case
the omap serial is not probed

Thread 2 received signal SIGSEGV, Segmentation fault.
[Switching to Thread 1]
_outb (addr=<optimized out>, value=<optimized out>) at ./include/asm-generic/io.h:584
584		__raw_writeb(value, PCI_IOBASE + addr);
(gdb) bt

Thread 2 received signal SIGSEGV, Segmentation fault.
[Switching to Thread 1]
_outb (addr=<optimized out>, value=<optimized out>) at ./include/asm-generic/io.h:584
584		__raw_writeb(value, PCI_IOBASE + addr);
(gdb) bt
0  _outb (addr=<optimized out>, value=<optimized out>) at ./include/asm-generic/io.h:584
1  logic_outb (value=0 '\000', addr=18446739675637874689) at lib/logic_pio.c:299
2  0xffff80008082dfcc in io_serial_out (p=0x0, offset=16760830, value=0) at drivers/tty/serial/8250/8250_port.c:416
3  0xffff80008082fe34 in serial_port_out (value=<optimized out>, offset=<optimized out>, up=<optimized out>)
    at ./include/linux/serial_core.h:677
4  serial8250_do_set_termios (port=0xffff8000828ee940 <serial8250_ports+1568>, termios=0xffff80008292b93c, old=0x0)
    at drivers/tty/serial/8250/8250_port.c:2860
5  0xffff800080830064 in serial8250_set_termios (port=0xfffffbfffe800000, termios=0xffbffe, old=0x0)
    at drivers/tty/serial/8250/8250_port.c:2912
6  0xffff80008082571c in uart_set_options (port=0xffff8000828ee940 <serial8250_ports+1568>, co=0x0, baud=115200, parity=110, bits=8, flow=110)
    at drivers/tty/serial/serial_core.c:2285
7  0xffff800080828434 in uart_poll_init (driver=0xfffffbfffe800000, line=16760830, options=0xffff8000828f7506 <config+6> "115200n8")
    at drivers/tty/serial/serial_core.c:2656
8  0xffff800080801690 in tty_find_polling_driver (name=0xffff8000828f7500 <config> "ttyS2,115200n8", line=0xffff80008292ba90)
    at drivers/tty/tty_io.c:410
9  0xffff80008086c0b0 in configure_kgdboc () at drivers/tty/serial/kgdboc.c:194
10 0xffff80008086c1ec in kgdboc_probe (pdev=0xfffffbfffe800000) at drivers/tty/serial/kgdboc.c:249
11 0xffff8000808b399c in platform_probe (_dev=0xffff000000ebb810) at drivers/base/platform.c:1404
12 0xffff8000808b0b44 in call_driver_probe (drv=<optimized out>, dev=<optimized out>) at drivers/base/dd.c:579
13 really_probe (dev=0xffff000000ebb810, drv=0xffff80008277f138 <kgdboc_platform_driver+48>) at drivers/base/dd.c:658
14 0xffff8000808b0d2c in __driver_probe_device (drv=0xffff80008277f138 <kgdboc_platform_driver+48>, dev=0xffff000000ebb810)
    at drivers/base/dd.c:800
15 0xffff8000808b0eb8 in driver_probe_device (drv=0xfffffbfffe800000, dev=0xffff000000ebb810) at drivers/base/dd.c:830
16 0xffff8000808b0ff4 in __device_attach_driver (drv=0xffff80008277f138 <kgdboc_platform_driver+48>, _data=0xffff80008292bc48)
    at drivers/base/dd.c:958
17 0xffff8000808ae970 in bus_for_each_drv (bus=0xfffffbfffe800000, start=0x0, data=0xffff80008292bc48,
    fn=0xffff8000808b0f3c <__device_attach_driver>) at drivers/base/bus.c:457
18 0xffff8000808b1408 in __device_attach (dev=0xffff000000ebb810, allow_async=true) at drivers/base/dd.c:1030
19 0xffff8000808b16d8 in device_initial_probe (dev=0xfffffbfffe800000) at drivers/base/dd.c:1079
20 0xffff8000808af9f4 in bus_probe_device (dev=0xffff000000ebb810) at drivers/base/bus.c:532
21 0xffff8000808ac77c in device_add (dev=0xfffffbfffe800000) at drivers/base/core.c:3625
22 0xffff8000808b3428 in platform_device_add (pdev=0xffff000000ebb800) at drivers/base/platform.c:716
23 0xffff800081b5dc0c in init_kgdboc () at drivers/tty/serial/kgdboc.c:292
24 0xffff800080014db0 in do_one_initcall (fn=0xffff800081b5dba4 <init_kgdboc>) at init/main.c:1236
25 0xffff800081b0114c in do_initcall_level (command_line=<optimized out>, level=<optimized out>) at init/main.c:1298
26 do_initcalls () at init/main.c:1314
27 do_basic_setup () at init/main.c:1333
28 kernel_init_freeable () at init/main.c:1551
29 0xffff8000810271ec in kernel_init (unused=0xfffffbfffe800000) at init/main.c:1441
30 0xffff800080015e80 in ret_from_fork () at arch/arm64/kernel/entry.S:857

Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Link: https://lore.kernel.org/r/20231224131200.266224-1-michael@amarulasolutions.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index d35371c076b27..cc866da50b814 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2638,7 +2638,8 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options)
 	mutex_lock(&tport->mutex);
 
 	port = uart_port_check(state);
-	if (!port || !(port->ops->poll_get_char && port->ops->poll_put_char)) {
+	if (!port || port->type == PORT_UNKNOWN ||
+	    !(port->ops->poll_get_char && port->ops->poll_put_char)) {
 		ret = -1;
 		goto out;
 	}
-- 
GitLab


From c6dcd8050fb7c2efec6946ae9c49bc186b0a7475 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Tue, 26 Dec 2023 13:16:07 +0100
Subject: [PATCH 2147/4076] serial: apbuart: fix console prompt on qemu

When using a leon kernel with qemu there where no console prompt.
The root cause is the handling of the fifo size in the tx part of the
apbuart driver.

The qemu uart driver only have a very rudimentary status handling and do
not report the number of chars queued in the tx fifo in the status register.
So the driver ends up with a fifo size of 1.

In the tx path the fifo size is divided by 2 - resulting in a fifo
size of zero.

The original implementation would always try to send one char, but
after the introduction of uart_port_tx_limited() the fifo size is
respected even for the first char.

There seems to be no good reason to divide the fifo size with two - so
remove this. It looks like something copied from the original amba driver.

With qemu we now have a minimum fifo size of one char, so we show
the prompt.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Fixes: d11cc8c3c4b6 ("tty: serial: use uart_port_tx_limited()")
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc:  <linux-serial@vger.kernel.org>
Cc:  <sparclinux@vger.kernel.org>
Link: https://lore.kernel.org/r/20231226121607.GA2622970@ravnborg.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/apbuart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/apbuart.c b/drivers/tty/serial/apbuart.c
index 716cb014c028e..364599f256db8 100644
--- a/drivers/tty/serial/apbuart.c
+++ b/drivers/tty/serial/apbuart.c
@@ -122,7 +122,7 @@ static void apbuart_tx_chars(struct uart_port *port)
 {
 	u8 ch;
 
-	uart_port_tx_limited(port, ch, port->fifosize >> 1,
+	uart_port_tx_limited(port, ch, port->fifosize,
 		true,
 		UART_PUT_CHAR(port, ch),
 		({}));
-- 
GitLab


From 7c45eaa813476bd195ac1227a64b52f9cf2e2030 Mon Sep 17 00:00:00 2001
From: Christoph Niedermaier <cniedermaier@dh-electronics.com>
Date: Tue, 26 Dec 2023 12:36:47 +0100
Subject: [PATCH 2148/4076] serial: imx: Ensure that imx_uart_rs485_config() is
 called with enabled clock

There are register accesses in the function imx_uart_rs485_config(). The
clock must be enabled for these accesses. This was ensured by calling it
via the function uart_rs485_config() in the probe() function within the
range where the clock is enabled. With the commit 7c7f9bc986e6 ("serial:
Deassert Transmit Enable on probe in driver-specific way") it was removed
from the probe() function and is now only called through the function
uart_add_one_port() which is located at the end of the probe() function.
But the clock is already switched off in this area. To ensure that the
clock is enabled during register access, move the disabling of the clock
to the very end of the probe() function. To avoid leaking enabled clocks
on error also add an error path for exiting with disabling the clock.

Fixes: 7c7f9bc986e6 ("serial: Deassert Transmit Enable on probe in driver-specific way")
Cc: stable <stable@kernel.org>
Signed-off-by: Christoph Niedermaier <cniedermaier@dh-electronics.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Link: https://lore.kernel.org/r/20231226113647.39376-1-cniedermaier@dh-electronics.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 55105a4b1af80..a0fcf18cbeaca 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -2332,10 +2332,8 @@ static int imx_uart_probe(struct platform_device *pdev)
 	}
 
 	ret = uart_get_rs485_mode(&sport->port);
-	if (ret) {
-		clk_disable_unprepare(sport->clk_ipg);
-		return ret;
-	}
+	if (ret)
+		goto err_clk;
 
 	if (sport->port.rs485.flags & SER_RS485_ENABLED &&
 	    (!sport->have_rtscts && !sport->have_rtsgpio))
@@ -2419,8 +2417,6 @@ static int imx_uart_probe(struct platform_device *pdev)
 		imx_uart_writel(sport, ucr3, UCR3);
 	}
 
-	clk_disable_unprepare(sport->clk_ipg);
-
 	hrtimer_init(&sport->trigger_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_init(&sport->trigger_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	sport->trigger_start_tx.function = imx_trigger_start_tx;
@@ -2436,7 +2432,7 @@ static int imx_uart_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request rx irq: %d\n",
 				ret);
-			return ret;
+			goto err_clk;
 		}
 
 		ret = devm_request_irq(&pdev->dev, txirq, imx_uart_txint, 0,
@@ -2444,7 +2440,7 @@ static int imx_uart_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request tx irq: %d\n",
 				ret);
-			return ret;
+			goto err_clk;
 		}
 
 		ret = devm_request_irq(&pdev->dev, rtsirq, imx_uart_rtsint, 0,
@@ -2452,14 +2448,14 @@ static int imx_uart_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request rts irq: %d\n",
 				ret);
-			return ret;
+			goto err_clk;
 		}
 	} else {
 		ret = devm_request_irq(&pdev->dev, rxirq, imx_uart_int, 0,
 				       dev_name(&pdev->dev), sport);
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request irq: %d\n", ret);
-			return ret;
+			goto err_clk;
 		}
 	}
 
@@ -2467,7 +2463,12 @@ static int imx_uart_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, sport);
 
-	return uart_add_one_port(&imx_uart_uart_driver, &sport->port);
+	ret = uart_add_one_port(&imx_uart_uart_driver, &sport->port);
+
+err_clk:
+	clk_disable_unprepare(sport->clk_ipg);
+
+	return ret;
 }
 
 static void imx_uart_remove(struct platform_device *pdev)
-- 
GitLab


From d8a02844791360ed156ce5935bc50754ea22e299 Mon Sep 17 00:00:00 2001
From: Vamshi Gajjela <vamshigajjela@google.com>
Date: Sun, 31 Dec 2023 23:59:51 +0530
Subject: [PATCH 2149/4076] serial: 8250_dw: Do not bailout on UCV read
 returning zero

Designware UART has optional feature FIFO_MODE to implement FIFO.
Encoding FIFO capabilities through Component Parameter Register CPR is
optional and it can be enabled using parameter UART_ADD_ENCODED_PARAMS.

Driver can exercise fifo capabilities by decoding CPR if implemented
or from cpr_val provided from the dw8250_platform_data otherwise.

dw8250_setup_port() checks for CPR or cpr_val to determine FIFO size
only when Component Version (UCV) is non-zero. Bailing out early on UCV
read returning zero will leave fifosize as zero and !UART_CAP_FIFO,
hence prevent early return and continue to process CPR or cpr_val for
the driver to utilize FIFO.

Non-zero UCV implies ADDITIONAL_FEATURES=1, preventing early return
will not be an overhead here.

Signed-off-by: Vamshi Gajjela <vamshigajjela@google.com>
Link: https://lore.kernel.org/r/20231231182951.877805-1-vamshigajjela@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_dwlib.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_dwlib.c b/drivers/tty/serial/8250/8250_dwlib.c
index 136ad093c5b60..3e33ddf7bc800 100644
--- a/drivers/tty/serial/8250/8250_dwlib.c
+++ b/drivers/tty/serial/8250/8250_dwlib.c
@@ -271,16 +271,10 @@ void dw8250_setup_port(struct uart_port *p)
 		p->set_divisor = dw8250_set_divisor;
 	}
 
-	/*
-	 * If the Component Version Register returns zero, we know that
-	 * ADDITIONAL_FEATURES are not enabled. No need to go any further.
-	 */
 	reg = dw8250_readl_ext(p, DW_UART_UCV);
-	if (!reg)
-		return;
-
-	dev_dbg(p->dev, "Designware UART version %c.%c%c\n",
-		(reg >> 24) & 0xff, (reg >> 16) & 0xff, (reg >> 8) & 0xff);
+	if (reg)
+		dev_dbg(p->dev, "Designware UART version %c.%c%c\n",
+			(reg >> 24) & 0xff, (reg >> 16) & 0xff, (reg >> 8) & 0xff);
 
 	reg = dw8250_readl_ext(p, DW_UART_CPR);
 	if (!reg) {
-- 
GitLab


From 9903f2f2e1c0306df5e35080552502659475e751 Mon Sep 17 00:00:00 2001
From: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Date: Tue, 2 Jan 2024 13:31:33 +0800
Subject: [PATCH 2150/4076] tty: serial: 8250: Set RS232 as default for Moxa
 PCIe board initialization

After switching the serial interface of the Moxa RS232 PCIe boards, it
fails to reset to RS232 when attempting to reload 8250_pci driver.

This patch set RS232 as the default setting during the initialization of
Moxa PCIe board.

Signed-off-by: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Link: https://lore.kernel.org/r/20240102053133.9795-1-crescentcy.hsieh@moxa.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 8ccf691935b75..0d35c77fad9eb 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -2039,12 +2039,13 @@ static int pci_moxa_init(struct pci_dev *dev)
 	unsigned short device = dev->device;
 	resource_size_t iobar_addr = pci_resource_start(dev, 2);
 	unsigned int num_ports = (device & 0x00F0) >> 4, i;
-	u8 val;
+	u8 val, init_mode = MOXA_RS232;
 
 	if (!(pci_moxa_supported_rs(dev) & MOXA_SUPP_RS232)) {
-		for (i = 0; i < num_ports; ++i)
-			pci_moxa_set_interface(dev, i, MOXA_RS422);
+		init_mode = MOXA_RS422;
 	}
+	for (i = 0; i < num_ports; ++i)
+		pci_moxa_set_interface(dev, i, init_mode);
 
 	/*
 	 * Enable hardware buffer to prevent break signal output when system boots up.
-- 
GitLab


From 8c9aa6e1877de041e393b42a88e0cfd54627b3f7 Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Tue, 2 Jan 2024 11:20:06 +0530
Subject: [PATCH 2151/4076] serial: 8250_lpss: copy dma_param using
 devm_kmemdup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use devm_kmemdup() helper to copy dma_param instead of doing it manually.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://lore.kernel.org/r/20240102055006.27256-1-raag.jadav@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_lpss.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_lpss.c b/drivers/tty/serial/8250/8250_lpss.c
index 0e43bdfb74598..776ec1ef29d62 100644
--- a/drivers/tty/serial/8250/8250_lpss.c
+++ b/drivers/tty/serial/8250/8250_lpss.c
@@ -287,17 +287,14 @@ static int lpss8250_dma_setup(struct lpss8250 *lpss, struct uart_8250_port *port
 		return 0;
 	}
 
-	rx_param = devm_kzalloc(dev, sizeof(*rx_param), GFP_KERNEL);
+	rx_param = devm_kmemdup(dev, &lpss->dma_param, sizeof(*rx_param), GFP_KERNEL);
 	if (!rx_param)
 		return -ENOMEM;
 
-	tx_param = devm_kzalloc(dev, sizeof(*tx_param), GFP_KERNEL);
+	tx_param = devm_kmemdup(dev, &lpss->dma_param, sizeof(*tx_param), GFP_KERNEL);
 	if (!tx_param)
 		return -ENOMEM;
 
-	*rx_param = lpss->dma_param;
-	*tx_param = lpss->dma_param;
-
 	dma->fn = lpss8250_dma_filter;
 	dma->rx_param = rx_param;
 	dma->tx_param = tx_param;
-- 
GitLab


From e0ae1431dfb6899836f5689225ac464394570b18 Mon Sep 17 00:00:00 2001
From: Rengarajan S <rengarajan.s@microchip.com>
Date: Fri, 15 Dec 2023 20:41:20 +0530
Subject: [PATCH 2152/4076] 8250: microchip: pci1xxxx: Rearranging the
 structure declarations

Structure declarations in 8250_pci1xxxx.c have been moved above
the functions for code readability.

Signed-off-by: Rengarajan S <rengarajan.s@microchip.com>
Link: https://lore.kernel.org/r/20231215151123.41812-2-rengarajan.s@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci1xxxx.c | 26 ++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index 9f9e21981929f..48bd2f3a287d5 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -85,6 +85,19 @@
 #define MAX_PORTS				4
 #define PORT_OFFSET				0x100
 
+struct pci1xxxx_8250 {
+	unsigned int nr;
+	void __iomem *membase;
+	int line[] __counted_by(nr);
+};
+
+static const struct serial_rs485 pci1xxxx_rs485_supported = {
+	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND |
+		 SER_RS485_RTS_AFTER_SEND,
+	.delay_rts_after_send = 1,
+	/* Delay RTS before send is not supported */
+};
+
 static const int logical_to_physical_port_idx[][MAX_PORTS] = {
 	{0,  1,  2,  3}, /* PCI12000, PCI11010, PCI11101, PCI11400, PCI11414 */
 	{0,  1,  2,  3}, /* PCI4p */
@@ -104,12 +117,6 @@ static const int logical_to_physical_port_idx[][MAX_PORTS] = {
 	{3, -1, -1, -1}, /* PCI1p3 */
 };
 
-struct pci1xxxx_8250 {
-	unsigned int nr;
-	void __iomem *membase;
-	int line[] __counted_by(nr);
-};
-
 static int pci1xxxx_get_num_ports(struct pci_dev *dev)
 {
 	switch (dev->subsystem_device) {
@@ -205,13 +212,6 @@ static int pci1xxxx_rs485_config(struct uart_port *port,
 	return 0;
 }
 
-static const struct serial_rs485 pci1xxxx_rs485_supported = {
-	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND |
-		 SER_RS485_RTS_AFTER_SEND,
-	.delay_rts_after_send = 1,
-	/* Delay RTS before send is not supported */
-};
-
 static bool pci1xxxx_port_suspend(int line)
 {
 	struct uart_8250_port *up = serial8250_get_port(line);
-- 
GitLab


From b7fbca372bb6247990e2419c09fe6064d107542d Mon Sep 17 00:00:00 2001
From: Rengarajan S <rengarajan.s@microchip.com>
Date: Fri, 15 Dec 2023 20:41:21 +0530
Subject: [PATCH 2153/4076] 8250: microchip: pci1xxxx: Add Syslock support for
 reading UART system registers

Different Host drivers can attempt to access system registers
simultaneously from different memory spaces at the same time. The
syslock mechanism provides a safe option for reading UART system
registers and prevents conflicts by serializing access. Added
three padding bytes in the structure for memory alignment.

Signed-off-by: Rengarajan S <rengarajan.s@microchip.com>
Link: https://lore.kernel.org/r/20231215151123.41812-3-rengarajan.s@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci1xxxx.c | 63 +++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index 48bd2f3a287d5..6b6f3731307f5 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -9,15 +9,21 @@
 
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
+#include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/serial_core.h>
+#include <linux/serial_reg.h>
+#include <linux/serial_8250.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/units.h>
 #include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/8250_pci.h>
 
 #include <asm/byteorder.h>
 
@@ -52,6 +58,14 @@
 #define PCI_SUBDEVICE_ID_EFAR_PCI11400		PCI_DEVICE_ID_EFAR_PCI11400
 #define PCI_SUBDEVICE_ID_EFAR_PCI11414		PCI_DEVICE_ID_EFAR_PCI11414
 
+#define UART_SYSTEM_ADDR_BASE			0x1000
+#define UART_DEV_REV_REG			(UART_SYSTEM_ADDR_BASE + 0x00)
+#define UART_DEV_REV_MASK			GENMASK(7, 0)
+#define UART_SYSLOCK_REG			(UART_SYSTEM_ADDR_BASE + 0xA0)
+#define UART_SYSLOCK				BIT(2)
+#define SYSLOCK_SLEEP_TIMEOUT			100
+#define SYSLOCK_RETRY_CNT			1000
+
 #define UART_ACTV_REG				0x11
 #define UART_BLOCK_SET_ACTIVE			BIT(0)
 
@@ -87,6 +101,8 @@
 
 struct pci1xxxx_8250 {
 	unsigned int nr;
+	u8 dev_rev;
+	u8 pad[3];
 	void __iomem *membase;
 	int line[] __counted_by(nr);
 };
@@ -98,6 +114,27 @@ static const struct serial_rs485 pci1xxxx_rs485_supported = {
 	/* Delay RTS before send is not supported */
 };
 
+static int pci1xxxx_set_sys_lock(struct pci1xxxx_8250 *port)
+{
+	writel(UART_SYSLOCK, port->membase + UART_SYSLOCK_REG);
+	return readl(port->membase + UART_SYSLOCK_REG);
+}
+
+static int pci1xxxx_acquire_sys_lock(struct pci1xxxx_8250 *port)
+{
+	u32 regval;
+
+	return readx_poll_timeout(pci1xxxx_set_sys_lock, port, regval,
+				  (regval & UART_SYSLOCK),
+				  SYSLOCK_SLEEP_TIMEOUT,
+				  SYSLOCK_RETRY_CNT * SYSLOCK_SLEEP_TIMEOUT);
+}
+
+static void pci1xxxx_release_sys_lock(struct pci1xxxx_8250 *port)
+{
+	writel(0x0, port->membase + UART_SYSLOCK_REG);
+}
+
 static const int logical_to_physical_port_idx[][MAX_PORTS] = {
 	{0,  1,  2,  3}, /* PCI12000, PCI11010, PCI11101, PCI11400, PCI11414 */
 	{0,  1,  2,  3}, /* PCI4p */
@@ -370,6 +407,27 @@ static int pci1xxxx_logical_to_physical_port_translate(int subsys_dev, int port)
 	return logical_to_physical_port_idx[0][port];
 }
 
+static int pci1xxxx_get_device_revision(struct pci1xxxx_8250 *priv)
+{
+	u32 regval;
+	int ret;
+
+	/*
+	 * DEV REV is a system register, HW Syslock bit
+	 * should be acquired before accessing the register
+	 */
+	ret = pci1xxxx_acquire_sys_lock(priv);
+	if (ret)
+		return ret;
+
+	regval = readl(priv->membase + UART_DEV_REV_REG);
+	priv->dev_rev = regval & UART_DEV_REV_MASK;
+
+	pci1xxxx_release_sys_lock(priv);
+
+	return 0;
+}
+
 static int pci1xxxx_serial_probe(struct pci_dev *pdev,
 				 const struct pci_device_id *id)
 {
@@ -381,6 +439,7 @@ static int pci1xxxx_serial_probe(struct pci_dev *pdev,
 	int num_vectors;
 	int subsys_dev;
 	int port_idx;
+	int ret;
 	int rc;
 
 	rc = pcim_enable_device(pdev);
@@ -397,6 +456,10 @@ static int pci1xxxx_serial_probe(struct pci_dev *pdev,
 	if (!priv->membase)
 		return -ENOMEM;
 
+	ret = pci1xxxx_get_device_revision(priv);
+	if (ret)
+		return ret;
+
 	pci_set_master(pdev);
 
 	priv->nr = nr_ports;
-- 
GitLab


From aba8290f368d965d49c929a283b3bf41783d3ada Mon Sep 17 00:00:00 2001
From: Rengarajan S <rengarajan.s@microchip.com>
Date: Fri, 15 Dec 2023 20:41:22 +0530
Subject: [PATCH 2154/4076] 8250: microchip: pci1xxxx: Add Burst mode reception
 support in uart driver for writing into FIFO

In PCI1XXXX C0 endpoint, support for Burst mode is added.
pci1xxxx_handle_irq checks the burst status and based on that
incoming characters are received in DWORDs, RX handling is done
in pci1xxxx_rx_burst. While reading the burst status the RX error
is checked and the corresponding error statistics are updated.

Signed-off-by: Rengarajan S <rengarajan.s@microchip.com>
Link: https://lore.kernel.org/r/20231215151123.41812-4-rengarajan.s@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci1xxxx.c | 123 +++++++++++++++++++++++-
 1 file changed, 121 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index 6b6f3731307f5..558c4c7f3104e 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -66,6 +66,9 @@
 #define SYSLOCK_SLEEP_TIMEOUT			100
 #define SYSLOCK_RETRY_CNT			1000
 
+#define UART_RX_BYTE_FIFO			0x00
+#define UART_FIFO_CTL				0x02
+
 #define UART_ACTV_REG				0x11
 #define UART_BLOCK_SET_ACTIVE			BIT(0)
 
@@ -96,8 +99,23 @@
 #define UART_RESET_REG				0x94
 #define UART_RESET_D3_RESET_DISABLE		BIT(16)
 
+#define UART_BURST_STATUS_REG			0x9C
+#define UART_RX_BURST_FIFO			0xA4
+
 #define MAX_PORTS				4
 #define PORT_OFFSET				0x100
+#define RX_BUF_SIZE				512
+#define UART_BYTE_SIZE                          1
+#define UART_BURST_SIZE				4
+
+#define UART_BST_STAT_RX_COUNT_MASK		0x00FF
+#define UART_BST_STAT_IIR_INT_PEND		0x100000
+#define UART_LSR_OVERRUN_ERR_CLR		0x43
+#define UART_BST_STAT_LSR_RX_MASK		0x9F000000
+#define UART_BST_STAT_LSR_RX_ERR_MASK		0x9E000000
+#define UART_BST_STAT_LSR_OVERRUN_ERR		0x2000000
+#define UART_BST_STAT_LSR_PARITY_ERR		0x4000000
+#define UART_BST_STAT_LSR_FRAME_ERR		0x8000000
 
 struct pci1xxxx_8250 {
 	unsigned int nr;
@@ -249,6 +267,103 @@ static int pci1xxxx_rs485_config(struct uart_port *port,
 	return 0;
 }
 
+static u32 pci1xxxx_read_burst_status(struct uart_port *port)
+{
+	u32 status;
+
+	status = readl(port->membase + UART_BURST_STATUS_REG);
+	if (status & UART_BST_STAT_LSR_RX_ERR_MASK) {
+		if (status & UART_BST_STAT_LSR_OVERRUN_ERR) {
+			writeb(UART_LSR_OVERRUN_ERR_CLR,
+			       port->membase + UART_FIFO_CTL);
+			port->icount.overrun++;
+		}
+
+		if (status & UART_BST_STAT_LSR_FRAME_ERR)
+			port->icount.frame++;
+
+		if (status & UART_BST_STAT_LSR_PARITY_ERR)
+			port->icount.parity++;
+	}
+	return status;
+}
+
+static void pci1xxxx_process_read_data(struct uart_port *port,
+				       unsigned char *rx_buff, u32 *buff_index,
+				       u32 *valid_byte_count)
+{
+	u32 valid_burst_count = *valid_byte_count / UART_BURST_SIZE;
+	u32 *burst_buf;
+
+	/*
+	 * Depending on the RX Trigger Level the number of bytes that can be
+	 * stored in RX FIFO at a time varies. Each transaction reads data
+	 * in DWORDs. If there are less than four remaining valid_byte_count
+	 * to read, the data is received one byte at a time.
+	 */
+	while (valid_burst_count--) {
+		if (*buff_index > (RX_BUF_SIZE - UART_BURST_SIZE))
+			break;
+		burst_buf = (u32 *)&rx_buff[*buff_index];
+		*burst_buf = readl(port->membase + UART_RX_BURST_FIFO);
+		*buff_index += UART_BURST_SIZE;
+		*valid_byte_count -= UART_BURST_SIZE;
+	}
+
+	while (*valid_byte_count) {
+		if (*buff_index > RX_BUF_SIZE)
+			break;
+		rx_buff[*buff_index] = readb(port->membase +
+					     UART_RX_BYTE_FIFO);
+		*buff_index += UART_BYTE_SIZE;
+		*valid_byte_count -= UART_BYTE_SIZE;
+	}
+}
+
+static void pci1xxxx_rx_burst(struct uart_port *port, u32 uart_status)
+{
+	u32 valid_byte_count = uart_status & UART_BST_STAT_RX_COUNT_MASK;
+	struct tty_port *tty_port = &port->state->port;
+	unsigned char rx_buff[RX_BUF_SIZE];
+	u32 buff_index = 0;
+	u32 copied_len;
+
+	if (valid_byte_count != 0 &&
+	    valid_byte_count < RX_BUF_SIZE) {
+		pci1xxxx_process_read_data(port, rx_buff, &buff_index,
+					   &valid_byte_count);
+
+		copied_len = (u32)tty_insert_flip_string(tty_port, rx_buff,
+							 buff_index);
+
+		if (copied_len != buff_index)
+			port->icount.overrun += buff_index - copied_len;
+
+		port->icount.rx += buff_index;
+		tty_flip_buffer_push(tty_port);
+	}
+}
+
+static int pci1xxxx_handle_irq(struct uart_port *port)
+{
+	unsigned long flags;
+	u32 status;
+
+	status = pci1xxxx_read_burst_status(port);
+
+	if (status & UART_BST_STAT_IIR_INT_PEND)
+		return 0;
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	if (status & UART_BST_STAT_LSR_RX_MASK)
+		pci1xxxx_rx_burst(port, status);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return 1;
+}
+
 static bool pci1xxxx_port_suspend(int line)
 {
 	struct uart_8250_port *up = serial8250_get_port(line);
@@ -360,7 +475,7 @@ static int pci1xxxx_resume(struct device *dev)
 }
 
 static int pci1xxxx_setup(struct pci_dev *pdev,
-			  struct uart_8250_port *port, int port_idx)
+			  struct uart_8250_port *port, int port_idx, int rev)
 {
 	int ret;
 
@@ -372,6 +487,10 @@ static int pci1xxxx_setup(struct pci_dev *pdev,
 	port->port.rs485_config = pci1xxxx_rs485_config;
 	port->port.rs485_supported = pci1xxxx_rs485_supported;
 
+	/* From C0 rev Burst operation is supported */
+	if (rev >= 0xC0)
+		port->port.handle_irq = pci1xxxx_handle_irq;
+
 	ret = serial8250_pci_setup_port(pdev, port, 0, PORT_OFFSET * port_idx, 0);
 	if (ret < 0)
 		return ret;
@@ -491,7 +610,7 @@ static int pci1xxxx_serial_probe(struct pci_dev *pdev,
 		else
 			uart.port.irq = pci_irq_vector(pdev, 0);
 
-		rc = pci1xxxx_setup(pdev, &uart, port_idx);
+		rc = pci1xxxx_setup(pdev, &uart, port_idx, priv->dev_rev);
 		if (rc) {
 			dev_warn(dev, "Failed to setup port %u\n", i);
 			continue;
-- 
GitLab


From 83e571f054cd742eb9a46d46ef05193904adf53f Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Wed, 20 Dec 2023 12:43:34 +0100
Subject: [PATCH 2155/4076] serial: 8250_bcm2835aux: Restore clock error
 handling

The commit fcc446c8aa63 ("serial: 8250_bcm2835aux: Add ACPI support")
dropped the error handling for clock acquiring. But even an optional
clock needs this.

Fixes: fcc446c8aa63 ("serial: 8250_bcm2835aux: Add ACPI support")
Cc: stable <stable@kernel.org>
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20231220114334.4712-1-wahrenst@gmx.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_bcm2835aux.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/tty/serial/8250/8250_bcm2835aux.c b/drivers/tty/serial/8250/8250_bcm2835aux.c
index b5760f914a8cf..beac6b340acef 100644
--- a/drivers/tty/serial/8250/8250_bcm2835aux.c
+++ b/drivers/tty/serial/8250/8250_bcm2835aux.c
@@ -119,6 +119,8 @@ static int bcm2835aux_serial_probe(struct platform_device *pdev)
 
 	/* get the clock - this also enables the HW */
 	data->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(data->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(data->clk), "could not get clk\n");
 
 	/* get the interrupt */
 	ret = platform_get_irq(pdev, 0);
-- 
GitLab


From da680c045fde3c441bb0df5780f4ffc68327797d Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Thu, 21 Dec 2023 15:05:09 +0100
Subject: [PATCH 2156/4076] dt-bindings: serial: Describe ARM dcc interface

Debug Communication Channel (DCC) provides the way how to pass data between
target CPU and host via JTAG interface. Every CPU has own interface for
communication via dbgdtrtx_el0 and dbgdtrrx_el0 registers.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/9d7e85914eb1cdb313b28cb019093a84dd9b4773.1703167505.git.michal.simek@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/serial/arm,dcc.yaml   | 30 +++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/serial/arm,dcc.yaml

diff --git a/Documentation/devicetree/bindings/serial/arm,dcc.yaml b/Documentation/devicetree/bindings/serial/arm,dcc.yaml
new file mode 100644
index 0000000000000..fd0589356617a
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/arm,dcc.yaml
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/serial/arm,dcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ARM DCC (Data communication channel) serial emulation
+
+maintainers:
+  - Michal Simek <michal.simek@amd.com>
+
+description: |
+  ARM DCC (Data communication channel) serial emulation interface available
+  via JTAG can be also used as one of serial line tightly coupled with every
+  ARM CPU available in the system.
+
+properties:
+  compatible:
+    const: arm,dcc
+
+required:
+  - compatible
+
+additionalProperties: false
+
+examples:
+  - |
+    serial {
+      compatible = "arm,dcc";
+    };
-- 
GitLab


From 07c30ea5861fb26a77dade8cdc787252f6122fb1 Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Date: Wed, 3 Jan 2024 07:18:12 +0100
Subject: [PATCH 2157/4076] serial: Do not hold the port lock when setting
 rx-during-tx GPIO

Both the imx and stm32 driver set the rx-during-tx GPIO in rs485_config().
Since this function is called with the port lock held, this can be a
problem in case that setting the GPIO line can sleep (e.g. if a GPIO
expander is used which is connected via SPI or I2C).

Avoid this issue by moving the GPIO setting outside of the port lock into
the serial core and thus making it a generic feature.

Also with commit c54d48543689 ("serial: stm32: Add support for rs485
RX_DURING_TX output GPIO") the SER_RS485_RX_DURING_TX flag is only set if a
rx-during-tx GPIO is _not_ available, which is wrong. Fix this, too.

Furthermore reset old GPIO settings in case that changing the RS485
configuration failed.

Fixes: c54d48543689 ("serial: stm32: Add support for rs485 RX_DURING_TX output GPIO")
Fixes: ca530cfa968c ("serial: imx: Add support for RS485 RX_DURING_TX output GPIO")
Cc: Shawn Guo <shawnguo@kernel.org>
Cc: Sascha Hauer <s.hauer@pengutronix.de>
Cc:  <stable@vger.kernel.org>
Signed-off-by: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Link: https://lore.kernel.org/r/20240103061818.564-2-l.sanfilippo@kunbus.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c         |  4 ----
 drivers/tty/serial/serial_core.c | 26 ++++++++++++++++++++++++--
 drivers/tty/serial/stm32-usart.c |  8 ++------
 3 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index a0fcf18cbeaca..8b7d9c5a74551 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -1948,10 +1948,6 @@ static int imx_uart_rs485_config(struct uart_port *port, struct ktermios *termio
 	    rs485conf->flags & SER_RS485_RX_DURING_TX)
 		imx_uart_start_rx(port);
 
-	if (port->rs485_rx_during_tx_gpio)
-		gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio,
-					 !!(rs485conf->flags & SER_RS485_RX_DURING_TX));
-
 	return 0;
 }
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index cc866da50b814..8d381c283ceca 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1407,6 +1407,16 @@ static void uart_set_rs485_termination(struct uart_port *port,
 				 !!(rs485->flags & SER_RS485_TERMINATE_BUS));
 }
 
+static void uart_set_rs485_rx_during_tx(struct uart_port *port,
+					const struct serial_rs485 *rs485)
+{
+	if (!(rs485->flags & SER_RS485_ENABLED))
+		return;
+
+	gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio,
+				 !!(rs485->flags & SER_RS485_RX_DURING_TX));
+}
+
 static int uart_rs485_config(struct uart_port *port)
 {
 	struct serial_rs485 *rs485 = &port->rs485;
@@ -1418,12 +1428,17 @@ static int uart_rs485_config(struct uart_port *port)
 
 	uart_sanitize_serial_rs485(port, rs485);
 	uart_set_rs485_termination(port, rs485);
+	uart_set_rs485_rx_during_tx(port, rs485);
 
 	uart_port_lock_irqsave(port, &flags);
 	ret = port->rs485_config(port, NULL, rs485);
 	uart_port_unlock_irqrestore(port, flags);
-	if (ret)
+	if (ret) {
 		memset(rs485, 0, sizeof(*rs485));
+		/* unset GPIOs */
+		gpiod_set_value_cansleep(port->rs485_term_gpio, 0);
+		gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, 0);
+	}
 
 	return ret;
 }
@@ -1462,6 +1477,7 @@ static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port,
 		return ret;
 	uart_sanitize_serial_rs485(port, &rs485);
 	uart_set_rs485_termination(port, &rs485);
+	uart_set_rs485_rx_during_tx(port, &rs485);
 
 	uart_port_lock_irqsave(port, &flags);
 	ret = port->rs485_config(port, &tty->termios, &rs485);
@@ -1473,8 +1489,14 @@ static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port,
 			port->ops->set_mctrl(port, port->mctrl);
 	}
 	uart_port_unlock_irqrestore(port, flags);
-	if (ret)
+	if (ret) {
+		/* restore old GPIO settings */
+		gpiod_set_value_cansleep(port->rs485_term_gpio,
+			!!(port->rs485.flags & SER_RS485_TERMINATE_BUS));
+		gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio,
+			!!(port->rs485.flags & SER_RS485_RX_DURING_TX));
 		return ret;
+	}
 
 	if (copy_to_user(rs485_user, &port->rs485, sizeof(port->rs485)))
 		return -EFAULT;
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index 9781c143def29..794b775127403 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -226,12 +226,6 @@ static int stm32_usart_config_rs485(struct uart_port *port, struct ktermios *ter
 
 	stm32_usart_clr_bits(port, ofs->cr1, BIT(cfg->uart_enable_bit));
 
-	if (port->rs485_rx_during_tx_gpio)
-		gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio,
-					 !!(rs485conf->flags & SER_RS485_RX_DURING_TX));
-	else
-		rs485conf->flags |= SER_RS485_RX_DURING_TX;
-
 	if (rs485conf->flags & SER_RS485_ENABLED) {
 		cr1 = readl_relaxed(port->membase + ofs->cr1);
 		cr3 = readl_relaxed(port->membase + ofs->cr3);
@@ -256,6 +250,8 @@ static int stm32_usart_config_rs485(struct uart_port *port, struct ktermios *ter
 
 		writel_relaxed(cr3, port->membase + ofs->cr3);
 		writel_relaxed(cr1, port->membase + ofs->cr1);
+
+		rs485conf->flags |= SER_RS485_RX_DURING_TX;
 	} else {
 		stm32_usart_clr_bits(port, ofs->cr3,
 				     USART_CR3_DEM | USART_CR3_DEP);
-- 
GitLab


From 1a33e33ca0e80d485458410f149265cdc0178cfa Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Date: Wed, 3 Jan 2024 07:18:13 +0100
Subject: [PATCH 2158/4076] serial: core: set missing supported flag for RX
 during TX GPIO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the RS485 feature RX-during-TX is supported by means of a GPIO set the
according supported flag. Otherwise setting this feature from userspace may
not be possible, since in uart_sanitize_serial_rs485() the passed RS485
configuration is matched against the supported features and unsupported
settings are thereby removed and thus take no effect.

Cc:  <stable@vger.kernel.org>
Fixes: 163f080eb717 ("serial: core: Add option to output RS485 RX_DURING_TX state via GPIO")
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Link: https://lore.kernel.org/r/20240103061818.564-3-l.sanfilippo@kunbus.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 8d381c283ceca..850f24cc53e55 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -3649,6 +3649,8 @@ int uart_get_rs485_mode(struct uart_port *port)
 	if (IS_ERR(desc))
 		return dev_err_probe(dev, PTR_ERR(desc), "Cannot get rs485-rx-during-tx-gpios\n");
 	port->rs485_rx_during_tx_gpio = desc;
+	if (port->rs485_rx_during_tx_gpio)
+		port->rs485_supported.flags |= SER_RS485_RX_DURING_TX;
 
 	return 0;
 }
-- 
GitLab


From 4afeced55baa391490b61ed9164867e2927353ed Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Date: Wed, 3 Jan 2024 07:18:14 +0100
Subject: [PATCH 2159/4076] serial: core: fix sanitizing check for RTS settings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Among other things uart_sanitize_serial_rs485() tests the sanity of the RTS
settings in a RS485 configuration that has been passed by userspace.
If RTS-on-send and RTS-after-send are both set or unset the configuration
is adjusted and RTS-after-send is disabled and RTS-on-send enabled.

This however makes only sense if both RTS modes are actually supported by
the driver.

With commit be2e2cb1d281 ("serial: Sanitize rs485_struct") the code does
take the driver support into account but only checks if one of both RTS
modes are supported. This may lead to the errorneous result of RTS-on-send
being set even if only RTS-after-send is supported.

Fix this by changing the implemented logic: First clear all unsupported
flags in the RS485 configuration, then adjust an invalid RTS setting by
taking into account which RTS mode is supported.

Cc:  <stable@vger.kernel.org>
Fixes: be2e2cb1d281 ("serial: Sanitize rs485_struct")
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Link: https://lore.kernel.org/r/20240103061818.564-4-l.sanfilippo@kunbus.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 850f24cc53e55..cd8c3a70455e0 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1376,19 +1376,27 @@ static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs4
 		return;
 	}
 
+	rs485->flags &= supported_flags;
+
 	/* Pick sane settings if the user hasn't */
-	if ((supported_flags & (SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND)) &&
-	    !(rs485->flags & SER_RS485_RTS_ON_SEND) ==
+	if (!(rs485->flags & SER_RS485_RTS_ON_SEND) ==
 	    !(rs485->flags & SER_RS485_RTS_AFTER_SEND)) {
-		dev_warn_ratelimited(port->dev,
-			"%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n",
-			port->name, port->line);
-		rs485->flags |= SER_RS485_RTS_ON_SEND;
-		rs485->flags &= ~SER_RS485_RTS_AFTER_SEND;
-		supported_flags |= SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND;
-	}
+		if (supported_flags & SER_RS485_RTS_ON_SEND) {
+			rs485->flags |= SER_RS485_RTS_ON_SEND;
+			rs485->flags &= ~SER_RS485_RTS_AFTER_SEND;
 
-	rs485->flags &= supported_flags;
+			dev_warn_ratelimited(port->dev,
+				"%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n",
+				port->name, port->line);
+		} else {
+			rs485->flags |= SER_RS485_RTS_AFTER_SEND;
+			rs485->flags &= ~SER_RS485_RTS_ON_SEND;
+
+			dev_warn_ratelimited(port->dev,
+				"%s (%d): invalid RTS setting, using RTS_AFTER_SEND instead\n",
+				port->name, port->line);
+		}
+	}
 
 	uart_sanitize_serial_rs485_delays(port, rs485);
 
-- 
GitLab


From c73986913fa47e71e0b1ad7f039f6444915e8810 Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Date: Wed, 3 Jan 2024 07:18:15 +0100
Subject: [PATCH 2160/4076] serial: core: make sure RS485 cannot be enabled
 when it is not supported
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some uart drivers specify a rs485_config() function and then decide later
to disable RS485 support for some reason (e.g. imx and ar933).

In these cases userspace may be able to activate RS485 via TIOCSRS485
nevertheless, since in uart_set_rs485_config() an existing rs485_config()
function indicates that RS485 is supported.

Make sure that this is not longer possible by checking the uarts
rs485_supported.flags instead and bailing out if SER_RS485_ENABLED is not
set.

Furthermore instead of returning an empty structure return -ENOTTY if the
RS485 configuration is requested via TIOCGRS485 but RS485 is not supported.
This has a small impact on userspace visibility but it is consistent with
the -ENOTTY error for TIOCGRS485.

Fixes: e849145e1fdd ("serial: ar933x: Fill in rs485_supported")
Fixes: 55e18c6b6d42 ("serial: imx: Remove serial_rs485 sanitization")
Cc: Shawn Guo <shawnguo@kernel.org>
Cc: Sascha Hauer <s.hauer@pengutronix.de>
Cc:  <stable@vger.kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Link: https://lore.kernel.org/r/20240103061818.564-5-l.sanfilippo@kunbus.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index cd8c3a70455e0..b9606db78c923 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1474,7 +1474,7 @@ static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port,
 	int ret;
 	unsigned long flags;
 
-	if (!port->rs485_config)
+	if (!(port->rs485_supported.flags & SER_RS485_ENABLED))
 		return -ENOTTY;
 
 	if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user)))
-- 
GitLab


From 74eab89b26ac433ad857292f4707b43c1a8f0209 Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Date: Wed, 3 Jan 2024 07:18:16 +0100
Subject: [PATCH 2161/4076] serial: core, imx: do not set RS485 enabled if it
 is not supported
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the imx driver cannot support RS485 it nullifies the ports
rs485_supported structure. But it still calls uart_get_rs485_mode() which
may set the RS485_ENABLED flag nevertheless.

This may lead to an attempt to configure RS485 even if it is not supported
when the flag is evaluated in uart_configure_port() at port startup.

Avoid this by bailing out of uart_get_rs485_mode() if the RS485_ENABLED
flag is not supported by the caller.

With this fix a check for RTS availability is now obsolete in the imx
driver, since it can not evaluate to true any more. So remove this check.

Furthermore the explicit nullifcation of rs485_supported is not needed,
since the memory has already been set to zeros at allocation. So remove
this, too.

Fixes: 00d7a00e2a6f ("serial: imx: Fill in rs485_supported")
Cc: Shawn Guo <shawnguo@kernel.org>
Cc: Sascha Hauer <s.hauer@pengutronix.de>
Cc:  <stable@vger.kernel.org>
Suggested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20240103061818.564-6-l.sanfilippo@kunbus.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c         | 7 -------
 drivers/tty/serial/serial_core.c | 3 +++
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 8b7d9c5a74551..4aa72d5aeafbf 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -2211,7 +2211,6 @@ static enum hrtimer_restart imx_trigger_stop_tx(struct hrtimer *t)
 	return HRTIMER_NORESTART;
 }
 
-static const struct serial_rs485 imx_no_rs485 = {};	/* No RS485 if no RTS */
 static const struct serial_rs485 imx_rs485_supported = {
 	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND |
 		 SER_RS485_RX_DURING_TX,
@@ -2295,8 +2294,6 @@ static int imx_uart_probe(struct platform_device *pdev)
 	/* RTS is required to control the RS485 transmitter */
 	if (sport->have_rtscts || sport->have_rtsgpio)
 		sport->port.rs485_supported = imx_rs485_supported;
-	else
-		sport->port.rs485_supported = imx_no_rs485;
 	sport->port.flags = UPF_BOOT_AUTOCONF;
 	timer_setup(&sport->timer, imx_uart_timeout, 0);
 
@@ -2331,10 +2328,6 @@ static int imx_uart_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_clk;
 
-	if (sport->port.rs485.flags & SER_RS485_ENABLED &&
-	    (!sport->have_rtscts && !sport->have_rtsgpio))
-		dev_err(&pdev->dev, "no RTS control, disabling rs485\n");
-
 	/*
 	 * If using the i.MX UART RTS/CTS control then the RTS (CTS_B)
 	 * signal cannot be set low during transmission in case the
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index b9606db78c923..b56ed8c376b22 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -3607,6 +3607,9 @@ int uart_get_rs485_mode(struct uart_port *port)
 	u32 rs485_delay[2];
 	int ret;
 
+	if (!(port->rs485_supported.flags & SER_RS485_ENABLED))
+		return 0;
+
 	ret = device_property_read_u32_array(dev, "rs485-rts-delay",
 					     rs485_delay, 2);
 	if (!ret) {
-- 
GitLab


From 51f93776b84dee23e44a7be880736669a01cec2b Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Date: Wed, 3 Jan 2024 07:18:17 +0100
Subject: [PATCH 2162/4076] serial: omap: do not override settings for RS485
 support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The drivers RS485 support is deactivated if there is no RTS GPIO available.
This is done by nullifying the ports rs485_supported struct. After that
however the settings in serial_omap_rs485_supported are assigned to the
same structure unconditionally, which results in an unintended reactivation
of RS485 support.

Fix this by moving the assignment to the beginning of
serial_omap_probe_rs485() and thus before uart_get_rs485_mode() gets
called.

Also replace the assignment of rs485_config() to have the complete RS485
setup in one function.

Fixes: e2752ae3cfc9 ("serial: omap: Disallow RS-485 if rts-gpio is not specified")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20240103061818.564-7-l.sanfilippo@kunbus.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/omap-serial.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 7307556218797..f5a0b401af63b 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1483,6 +1483,13 @@ static struct omap_uart_port_info *of_get_uart_port_info(struct device *dev)
 	return omap_up_info;
 }
 
+static const struct serial_rs485 serial_omap_rs485_supported = {
+	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND |
+		 SER_RS485_RX_DURING_TX,
+	.delay_rts_before_send = 1,
+	.delay_rts_after_send = 1,
+};
+
 static int serial_omap_probe_rs485(struct uart_omap_port *up,
 				   struct device *dev)
 {
@@ -1497,6 +1504,9 @@ static int serial_omap_probe_rs485(struct uart_omap_port *up,
 	if (!np)
 		return 0;
 
+	up->port.rs485_config = serial_omap_config_rs485;
+	up->port.rs485_supported = serial_omap_rs485_supported;
+
 	ret = uart_get_rs485_mode(&up->port);
 	if (ret)
 		return ret;
@@ -1531,13 +1541,6 @@ static int serial_omap_probe_rs485(struct uart_omap_port *up,
 	return 0;
 }
 
-static const struct serial_rs485 serial_omap_rs485_supported = {
-	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND |
-		 SER_RS485_RX_DURING_TX,
-	.delay_rts_before_send = 1,
-	.delay_rts_after_send = 1,
-};
-
 static int serial_omap_probe(struct platform_device *pdev)
 {
 	struct omap_uart_port_info *omap_up_info = dev_get_platdata(&pdev->dev);
@@ -1604,17 +1607,11 @@ static int serial_omap_probe(struct platform_device *pdev)
 		dev_info(up->port.dev, "no wakeirq for uart%d\n",
 			 up->port.line);
 
-	ret = serial_omap_probe_rs485(up, &pdev->dev);
-	if (ret < 0)
-		goto err_rs485;
-
 	sprintf(up->name, "OMAP UART%d", up->port.line);
 	up->port.mapbase = mem->start;
 	up->port.membase = base;
 	up->port.flags = omap_up_info->flags;
 	up->port.uartclk = omap_up_info->uartclk;
-	up->port.rs485_config = serial_omap_config_rs485;
-	up->port.rs485_supported = serial_omap_rs485_supported;
 	if (!up->port.uartclk) {
 		up->port.uartclk = DEFAULT_CLK_SPEED;
 		dev_warn(&pdev->dev,
@@ -1622,6 +1619,10 @@ static int serial_omap_probe(struct platform_device *pdev)
 			 DEFAULT_CLK_SPEED);
 	}
 
+	ret = serial_omap_probe_rs485(up, &pdev->dev);
+	if (ret < 0)
+		goto err_rs485;
+
 	up->latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
 	up->calc_latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
 	cpu_latency_qos_add_request(&up->pm_qos_request, up->latency);
-- 
GitLab


From 0c2a5f471ce58bca8f8ab5fcb911aff91eaaa5eb Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Date: Wed, 3 Jan 2024 07:18:18 +0100
Subject: [PATCH 2163/4076] serial: 8250_exar: Set missing rs485_supported flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The UART supports an auto-RTS mode in which the RTS pin is automatically
activated during transmission. So mark this mode as being supported even
if RTS is not controlled by the driver but the UART.

Also the serial core expects now at least one of both modes rts-on-send or
rts-after-send to be supported. This is since during sanitization
unsupported flags are deleted from a RS485 configuration set by userspace.
However if the configuration ends up with both flags unset, the core prints
a warning since it considers such a configuration invalid (see
uart_sanitize_serial_rs485()).

Cc:  <stable@vger.kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Link: https://lore.kernel.org/r/20240103061818.564-8-l.sanfilippo@kunbus.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_exar.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c
index 6085d356ad86d..23366f868ae3a 100644
--- a/drivers/tty/serial/8250/8250_exar.c
+++ b/drivers/tty/serial/8250/8250_exar.c
@@ -480,7 +480,7 @@ static int sealevel_rs485_config(struct uart_port *port, struct ktermios *termio
 }
 
 static const struct serial_rs485 generic_rs485_supported = {
-	.flags = SER_RS485_ENABLED,
+	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND,
 };
 
 static const struct exar8250_platform exar8250_default_platform = {
@@ -524,7 +524,8 @@ static int iot2040_rs485_config(struct uart_port *port, struct ktermios *termios
 }
 
 static const struct serial_rs485 iot2040_rs485_supported = {
-	.flags = SER_RS485_ENABLED | SER_RS485_RX_DURING_TX | SER_RS485_TERMINATE_BUS,
+	.flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND |
+		 SER_RS485_RX_DURING_TX | SER_RS485_TERMINATE_BUS,
 };
 
 static const struct property_entry iot2040_gpio_properties[] = {
-- 
GitLab


From 8a1060ce974919f2a79807527ad82ac39336eda2 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:08 -0500
Subject: [PATCH 2164/4076] serial: sc16is7xx: fix invalid sc16is7xx_lines
 bitfield in case of probe error

If an error occurs during probing, the sc16is7xx_lines bitfield may be left
in a state that doesn't represent the correct state of lines allocation.

For example, in a system with two SC16 devices, if an error occurs only
during probing of channel (port) B of the second device, sc16is7xx_lines
final state will be 00001011b instead of the expected 00000011b.

This is caused in part because of the "i--" in the for/loop located in
the out_ports: error path.

Fix this by checking the return value of uart_add_one_port() and set line
allocation bit only if this was successful. This allows the refactor of
the obfuscated for(i--...) loop in the error path, and properly call
uart_remove_one_port() only when needed, and properly unset line allocation
bits.

Also use same mechanism in remove() when calling uart_remove_one_port().

Fixes: c64349722d14 ("sc16is7xx: support multiple devices")
Cc:  <stable@vger.kernel.org>
Cc: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-2-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 44 ++++++++++++++--------------------
 1 file changed, 18 insertions(+), 26 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index e40e4a99277ef..17b90f971f964 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -407,19 +407,6 @@ static void sc16is7xx_port_update(struct uart_port *port, u8 reg,
 	regmap_update_bits(one->regmap, reg, mask, val);
 }
 
-static int sc16is7xx_alloc_line(void)
-{
-	int i;
-
-	BUILD_BUG_ON(SC16IS7XX_MAX_DEVS > BITS_PER_LONG);
-
-	for (i = 0; i < SC16IS7XX_MAX_DEVS; i++)
-		if (!test_and_set_bit(i, &sc16is7xx_lines))
-			break;
-
-	return i;
-}
-
 static void sc16is7xx_power(struct uart_port *port, int on)
 {
 	sc16is7xx_port_update(port, SC16IS7XX_IER_REG,
@@ -1550,6 +1537,13 @@ static int sc16is7xx_probe(struct device *dev,
 		     SC16IS7XX_IOCONTROL_SRESET_BIT);
 
 	for (i = 0; i < devtype->nr_uart; ++i) {
+		s->p[i].port.line = find_first_zero_bit(&sc16is7xx_lines,
+							SC16IS7XX_MAX_DEVS);
+		if (s->p[i].port.line >= SC16IS7XX_MAX_DEVS) {
+			ret = -ERANGE;
+			goto out_ports;
+		}
+
 		/* Initialize port data */
 		s->p[i].port.dev	= dev;
 		s->p[i].port.irq	= irq;
@@ -1569,14 +1563,8 @@ static int sc16is7xx_probe(struct device *dev,
 		s->p[i].port.rs485_supported = sc16is7xx_rs485_supported;
 		s->p[i].port.ops	= &sc16is7xx_ops;
 		s->p[i].old_mctrl	= 0;
-		s->p[i].port.line	= sc16is7xx_alloc_line();
 		s->p[i].regmap		= regmaps[i];
 
-		if (s->p[i].port.line >= SC16IS7XX_MAX_DEVS) {
-			ret = -ENOMEM;
-			goto out_ports;
-		}
-
 		mutex_init(&s->p[i].efr_lock);
 
 		ret = uart_get_rs485_mode(&s->p[i].port);
@@ -1594,8 +1582,13 @@ static int sc16is7xx_probe(struct device *dev,
 		kthread_init_work(&s->p[i].tx_work, sc16is7xx_tx_proc);
 		kthread_init_work(&s->p[i].reg_work, sc16is7xx_reg_proc);
 		kthread_init_delayed_work(&s->p[i].ms_work, sc16is7xx_ms_proc);
+
 		/* Register port */
-		uart_add_one_port(&sc16is7xx_uart, &s->p[i].port);
+		ret = uart_add_one_port(&sc16is7xx_uart, &s->p[i].port);
+		if (ret)
+			goto out_ports;
+
+		set_bit(s->p[i].port.line, &sc16is7xx_lines);
 
 		/* Enable EFR */
 		sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_LCR_REG,
@@ -1653,10 +1646,9 @@ static int sc16is7xx_probe(struct device *dev,
 #endif
 
 out_ports:
-	for (i--; i >= 0; i--) {
-		uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
-		clear_bit(s->p[i].port.line, &sc16is7xx_lines);
-	}
+	for (i = 0; i < devtype->nr_uart; i++)
+		if (test_and_clear_bit(s->p[i].port.line, &sc16is7xx_lines))
+			uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
 
 	kthread_stop(s->kworker_task);
 
@@ -1678,8 +1670,8 @@ static void sc16is7xx_remove(struct device *dev)
 
 	for (i = 0; i < s->devtype->nr_uart; i++) {
 		kthread_cancel_delayed_work_sync(&s->p[i].ms_work);
-		uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
-		clear_bit(s->p[i].port.line, &sc16is7xx_lines);
+		if (test_and_clear_bit(s->p[i].port.line, &sc16is7xx_lines))
+			uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
 		sc16is7xx_power(&s->p[i].port, 0);
 	}
 
-- 
GitLab


From 6d710b769c1f5f0d55c9ad9bb49b7dce009ec103 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:09 -0500
Subject: [PATCH 2165/4076] serial: sc16is7xx: add check for unsupported SPI
 modes during probe

The original comment is confusing because it implies that variants other
than the SC16IS762 supports other SPI modes beside SPI_MODE_0.

Extract from datasheet:
    The SC16IS762 differs from the SC16IS752 in that it supports SPI clock
    speeds up to 15 Mbit/s instead of the 4 Mbit/s supported by the
    SC16IS752... In all other aspects, the SC16IS762 is functionally and
    electrically the same as the SC16IS752.

The same is also true of the SC16IS760 variant versus the SC16IS740 and
SC16IS750 variants.

For all variants, only SPI mode 0 is supported.

Change comment and abort probing if the specified SPI mode is not
SPI_MODE_0.

Fixes: 2c837a8a8f9f ("sc16is7xx: spi interface is added")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-3-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 17b90f971f964..798fa115b28a2 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1733,7 +1733,10 @@ static int sc16is7xx_spi_probe(struct spi_device *spi)
 
 	/* Setup SPI bus */
 	spi->bits_per_word	= 8;
-	/* only supports mode 0 on SC16IS762 */
+	/* For all variants, only mode 0 is supported */
+	if ((spi->mode & SPI_MODE_X_MASK) != SPI_MODE_0)
+		return dev_err_probe(&spi->dev, -EINVAL, "Unsupported SPI mode\n");
+
 	spi->mode		= spi->mode ? : SPI_MODE_0;
 	spi->max_speed_hz	= spi->max_speed_hz ? : 15000000;
 	ret = spi_setup(spi);
-- 
GitLab


From 3ef79cd1412236d884ab0c46b4d1921380807b48 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:10 -0500
Subject: [PATCH 2166/4076] serial: sc16is7xx: set safe default SPI clock
 frequency

15 MHz is supported only by 76x variants.

If the SPI clock frequency is not specified, use a safe default clock value
of 4 MHz that is supported by all variants.

Also use HZ_PER_MHZ macro to improve readability.

Fixes: 2c837a8a8f9f ("sc16is7xx: spi interface is added")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-4-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 798fa115b28a2..ced2446909a2b 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -24,6 +24,7 @@
 #include <linux/tty_flip.h>
 #include <linux/spi/spi.h>
 #include <linux/uaccess.h>
+#include <linux/units.h>
 #include <uapi/linux/sched/types.h>
 
 #define SC16IS7XX_NAME			"sc16is7xx"
@@ -1738,7 +1739,7 @@ static int sc16is7xx_spi_probe(struct spi_device *spi)
 		return dev_err_probe(&spi->dev, -EINVAL, "Unsupported SPI mode\n");
 
 	spi->mode		= spi->mode ? : SPI_MODE_0;
-	spi->max_speed_hz	= spi->max_speed_hz ? : 15000000;
+	spi->max_speed_hz	= spi->max_speed_hz ? : 4 * HZ_PER_MHZ;
 	ret = spi_setup(spi);
 	if (ret)
 		return ret;
-- 
GitLab


From ed647256e8f226241ecff7baaecdb8632ffc7ec1 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:11 -0500
Subject: [PATCH 2167/4076] serial: sc16is7xx: remove obsolete loop in
 sc16is7xx_port_irq()

Commit 834449872105 ("sc16is7xx: Fix for multi-channel stall") changed
sc16is7xx_port_irq() from looping multiple times when there was still
interrupts to serve. It simply changed the do {} while(1) loop to a
do {} while(0) loop, which makes the loop itself now obsolete.

Clean the code by removing this obsolete do {} while(0) loop.

Fixes: 834449872105 ("sc16is7xx: Fix for multi-channel stall")
Cc:  <stable@vger.kernel.org>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-5-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 85 ++++++++++++++++------------------
 1 file changed, 41 insertions(+), 44 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index ced2446909a2b..44a11c89c9491 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -725,58 +725,55 @@ static void sc16is7xx_update_mlines(struct sc16is7xx_one *one)
 static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
 {
 	bool rc = true;
+	unsigned int iir, rxlen;
 	struct uart_port *port = &s->p[portno].port;
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
 	mutex_lock(&one->efr_lock);
 
-	do {
-		unsigned int iir, rxlen;
+	iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG);
+	if (iir & SC16IS7XX_IIR_NO_INT_BIT) {
+		rc = false;
+		goto out_port_irq;
+	}
 
-		iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG);
-		if (iir & SC16IS7XX_IIR_NO_INT_BIT) {
-			rc = false;
-			goto out_port_irq;
-		}
+	iir &= SC16IS7XX_IIR_ID_MASK;
 
-		iir &= SC16IS7XX_IIR_ID_MASK;
-
-		switch (iir) {
-		case SC16IS7XX_IIR_RDI_SRC:
-		case SC16IS7XX_IIR_RLSE_SRC:
-		case SC16IS7XX_IIR_RTOI_SRC:
-		case SC16IS7XX_IIR_XOFFI_SRC:
-			rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG);
-
-			/*
-			 * There is a silicon bug that makes the chip report a
-			 * time-out interrupt but no data in the FIFO. This is
-			 * described in errata section 18.1.4.
-			 *
-			 * When this happens, read one byte from the FIFO to
-			 * clear the interrupt.
-			 */
-			if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen)
-				rxlen = 1;
-
-			if (rxlen)
-				sc16is7xx_handle_rx(port, rxlen, iir);
-			break;
+	switch (iir) {
+	case SC16IS7XX_IIR_RDI_SRC:
+	case SC16IS7XX_IIR_RLSE_SRC:
+	case SC16IS7XX_IIR_RTOI_SRC:
+	case SC16IS7XX_IIR_XOFFI_SRC:
+		rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG);
+
+		/*
+		 * There is a silicon bug that makes the chip report a
+		 * time-out interrupt but no data in the FIFO. This is
+		 * described in errata section 18.1.4.
+		 *
+		 * When this happens, read one byte from the FIFO to
+		 * clear the interrupt.
+		 */
+		if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen)
+			rxlen = 1;
+
+		if (rxlen)
+			sc16is7xx_handle_rx(port, rxlen, iir);
+		break;
 		/* CTSRTS interrupt comes only when CTS goes inactive */
-		case SC16IS7XX_IIR_CTSRTS_SRC:
-		case SC16IS7XX_IIR_MSI_SRC:
-			sc16is7xx_update_mlines(one);
-			break;
-		case SC16IS7XX_IIR_THRI_SRC:
-			sc16is7xx_handle_tx(port);
-			break;
-		default:
-			dev_err_ratelimited(port->dev,
-					    "ttySC%i: Unexpected interrupt: %x",
-					    port->line, iir);
-			break;
-		}
-	} while (0);
+	case SC16IS7XX_IIR_CTSRTS_SRC:
+	case SC16IS7XX_IIR_MSI_SRC:
+		sc16is7xx_update_mlines(one);
+		break;
+	case SC16IS7XX_IIR_THRI_SRC:
+		sc16is7xx_handle_tx(port);
+		break;
+	default:
+		dev_err_ratelimited(port->dev,
+				    "ttySC%i: Unexpected interrupt: %x",
+				    port->line, iir);
+		break;
+	}
 
 out_port_irq:
 	mutex_unlock(&one->efr_lock);
-- 
GitLab


From d5078509c8b06c5c472a60232815e41af81c6446 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:12 -0500
Subject: [PATCH 2168/4076] serial: sc16is7xx: improve do/while loop in
 sc16is7xx_irq()

Simplify and improve readability by replacing while(1) loop with
do {} while, and by using the keep_polling variable as the exit
condition, making it more explicit.

Fixes: 834449872105 ("sc16is7xx: Fix for multi-channel stall")
Cc:  <stable@vger.kernel.org>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-6-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 44a11c89c9491..8d257208cbf3c 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -783,17 +783,18 @@ out_port_irq:
 
 static irqreturn_t sc16is7xx_irq(int irq, void *dev_id)
 {
+	bool keep_polling;
+
 	struct sc16is7xx_port *s = (struct sc16is7xx_port *)dev_id;
 
-	while (1) {
-		bool keep_polling = false;
+	do {
 		int i;
 
+		keep_polling = false;
+
 		for (i = 0; i < s->devtype->nr_uart; ++i)
 			keep_polling |= sc16is7xx_port_irq(s, i);
-		if (!keep_polling)
-			break;
-	}
+	} while (keep_polling);
 
 	return IRQ_HANDLED;
 }
-- 
GitLab


From 3504c3174bfce19bbf3b6391645f159c68ba12e9 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:13 -0500
Subject: [PATCH 2169/4076] serial: sc16is7xx: use DECLARE_BITMAP for
 sc16is7xx_lines bitfield

Replace the explicit sc16is7xx_lines bitfield declaration with the generic
macro DECLARE_BITMAP() to reserve just enough memory to contain all
required bits.

This also improves code self-documentation by showing the maximum number
of bits required.

This conversion now makes sc16is7xx_lines an array, so drop the "&" before
sc16is7xx_lines in all bit access functions.

Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-7-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 8d257208cbf3c..42e1b4c70ed6f 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -347,7 +347,7 @@ struct sc16is7xx_port {
 	struct sc16is7xx_one		p[];
 };
 
-static unsigned long sc16is7xx_lines;
+static DECLARE_BITMAP(sc16is7xx_lines, SC16IS7XX_MAX_DEVS);
 
 static struct uart_driver sc16is7xx_uart = {
 	.owner		= THIS_MODULE,
@@ -1536,7 +1536,7 @@ static int sc16is7xx_probe(struct device *dev,
 		     SC16IS7XX_IOCONTROL_SRESET_BIT);
 
 	for (i = 0; i < devtype->nr_uart; ++i) {
-		s->p[i].port.line = find_first_zero_bit(&sc16is7xx_lines,
+		s->p[i].port.line = find_first_zero_bit(sc16is7xx_lines,
 							SC16IS7XX_MAX_DEVS);
 		if (s->p[i].port.line >= SC16IS7XX_MAX_DEVS) {
 			ret = -ERANGE;
@@ -1587,7 +1587,7 @@ static int sc16is7xx_probe(struct device *dev,
 		if (ret)
 			goto out_ports;
 
-		set_bit(s->p[i].port.line, &sc16is7xx_lines);
+		set_bit(s->p[i].port.line, sc16is7xx_lines);
 
 		/* Enable EFR */
 		sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_LCR_REG,
@@ -1646,7 +1646,7 @@ static int sc16is7xx_probe(struct device *dev,
 
 out_ports:
 	for (i = 0; i < devtype->nr_uart; i++)
-		if (test_and_clear_bit(s->p[i].port.line, &sc16is7xx_lines))
+		if (test_and_clear_bit(s->p[i].port.line, sc16is7xx_lines))
 			uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
 
 	kthread_stop(s->kworker_task);
@@ -1669,7 +1669,7 @@ static void sc16is7xx_remove(struct device *dev)
 
 	for (i = 0; i < s->devtype->nr_uart; i++) {
 		kthread_cancel_delayed_work_sync(&s->p[i].ms_work);
-		if (test_and_clear_bit(s->p[i].port.line, &sc16is7xx_lines))
+		if (test_and_clear_bit(s->p[i].port.line, sc16is7xx_lines))
 			uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port);
 		sc16is7xx_power(&s->p[i].port, 0);
 	}
-- 
GitLab


From 195f01ddcc8146465dff1cbdfd592aa3c4f3ce5d Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:14 -0500
Subject: [PATCH 2170/4076] serial: sc16is7xx: use spi_get_device_match_data()

Use preferred spi_get_device_match_data() instead of
device_get_match_data() and spi_get_device_id() to get the driver match
data.

Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-8-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 42e1b4c70ed6f..4161d692df409 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1742,15 +1742,9 @@ static int sc16is7xx_spi_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
-	if (spi->dev.of_node) {
-		devtype = device_get_match_data(&spi->dev);
-		if (!devtype)
-			return -ENODEV;
-	} else {
-		const struct spi_device_id *id_entry = spi_get_device_id(spi);
-
-		devtype = (struct sc16is7xx_devtype *)id_entry->driver_data;
-	}
+	devtype = spi_get_device_match_data(spi);
+	if (!devtype)
+		return dev_err_probe(&spi->dev, -ENODEV, "Failed to match device\n");
 
 	for (i = 0; i < devtype->nr_uart; i++) {
 		regcfg.name = sc16is7xx_regmap_name(i);
-- 
GitLab


From 7e2ead98b7478629b10e616ad997c24c390fbc84 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:15 -0500
Subject: [PATCH 2171/4076] serial: sc16is7xx: use i2c_get_match_data()

Use preferred i2c_get_match_data() instead of device_get_match_data()
and i2c_client_get_device_id() to get the driver match data.

Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-9-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 4161d692df409..e7f3184a70a18 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1796,18 +1796,13 @@ MODULE_ALIAS("spi:sc16is7xx");
 #ifdef CONFIG_SERIAL_SC16IS7XX_I2C
 static int sc16is7xx_i2c_probe(struct i2c_client *i2c)
 {
-	const struct i2c_device_id *id = i2c_client_get_device_id(i2c);
 	const struct sc16is7xx_devtype *devtype;
 	struct regmap *regmaps[2];
 	unsigned int i;
 
-	if (i2c->dev.of_node) {
-		devtype = device_get_match_data(&i2c->dev);
-		if (!devtype)
-			return -ENODEV;
-	} else {
-		devtype = (struct sc16is7xx_devtype *)id->driver_data;
-	}
+	devtype = i2c_get_match_data(i2c);
+	if (!devtype)
+		return dev_err_probe(&i2c->dev, -ENODEV, "Failed to match device\n");
 
 	for (i = 0; i < devtype->nr_uart; i++) {
 		regcfg.name = sc16is7xx_regmap_name(i);
-- 
GitLab


From d9ffadaf9df1c8f416a8308f8995c2f8de4cbc7f Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:16 -0500
Subject: [PATCH 2172/4076] serial: sc16is7xx: add driver name to struct
 uart_driver

Make sure that the driver name is displayed instead of "unknown" when
displaying the driver infos:

Before:
    grep ttySC /proc/tty/drivers
    unknown              /dev/ttySC    243 0-7 serial

After:
    grep ttySC /proc/tty/drivers
    sc16is7xx            /dev/ttySC    243 0-7 serial

Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-10-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index e7f3184a70a18..b73fac209f1e8 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -351,6 +351,7 @@ static DECLARE_BITMAP(sc16is7xx_lines, SC16IS7XX_MAX_DEVS);
 
 static struct uart_driver sc16is7xx_uart = {
 	.owner		= THIS_MODULE,
+	.driver_name    = SC16IS7XX_NAME,
 	.dev_name	= "ttySC",
 	.nr		= SC16IS7XX_MAX_DEVS,
 };
-- 
GitLab


From acd7f118b3b5466549e351331bedb50a6027d8d1 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:17 -0500
Subject: [PATCH 2173/4076] serial: sc16is7xx: add macro for max number of UART
 ports

Add macro to hold the maximum number of UART ports per IC/device.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-11-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index b73fac209f1e8..6181cc6f934b8 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -29,6 +29,7 @@
 
 #define SC16IS7XX_NAME			"sc16is7xx"
 #define SC16IS7XX_MAX_DEVS		8
+#define SC16IS7XX_MAX_PORTS		2 /* Maximum number of UART ports per IC. */
 
 /* SC16IS7XX register definitions */
 #define SC16IS7XX_RHR_REG		(0x00) /* RX FIFO */
@@ -1398,7 +1399,7 @@ static void sc16is7xx_setup_irda_ports(struct sc16is7xx_port *s)
 	int i;
 	int ret;
 	int count;
-	u32 irda_port[2];
+	u32 irda_port[SC16IS7XX_MAX_PORTS];
 	struct device *dev = s->p[0].port.dev;
 
 	count = device_property_count_u32(dev, "irda-mode-ports");
@@ -1425,7 +1426,7 @@ static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s,
 	int i;
 	int ret;
 	int count;
-	u32 mctrl_port[2];
+	u32 mctrl_port[SC16IS7XX_MAX_PORTS];
 	struct device *dev = s->p[0].port.dev;
 
 	count = device_property_count_u32(dev, "nxp,modem-control-line-ports");
@@ -1727,7 +1728,7 @@ static unsigned int sc16is7xx_regmap_port_mask(unsigned int port_id)
 static int sc16is7xx_spi_probe(struct spi_device *spi)
 {
 	const struct sc16is7xx_devtype *devtype;
-	struct regmap *regmaps[2];
+	struct regmap *regmaps[SC16IS7XX_MAX_PORTS];
 	unsigned int i;
 	int ret;
 
@@ -1798,7 +1799,7 @@ MODULE_ALIAS("spi:sc16is7xx");
 static int sc16is7xx_i2c_probe(struct i2c_client *i2c)
 {
 	const struct sc16is7xx_devtype *devtype;
-	struct regmap *regmaps[2];
+	struct regmap *regmaps[SC16IS7XX_MAX_PORTS];
 	unsigned int i;
 
 	devtype = i2c_get_match_data(i2c);
-- 
GitLab


From dfb104213008e68ba4dd516ce4f329d676c449fb Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:18 -0500
Subject: [PATCH 2174/4076] serial: sc16is7xx: add explicit return for some
 switch default cases

Allows to simplify code by removing the break statement in the default
switch/case in some functions.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-12-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 6181cc6f934b8..da862b8efcbef 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -460,10 +460,8 @@ static bool sc16is7xx_regmap_volatile(struct device *dev, unsigned int reg)
 	case SC16IS7XX_IOCONTROL_REG:
 		return true;
 	default:
-		break;
+		return false;
 	}
-
-	return false;
 }
 
 static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg)
@@ -472,10 +470,8 @@ static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg)
 	case SC16IS7XX_RHR_REG:
 		return true;
 	default:
-		break;
+		return false;
 	}
-
-	return false;
 }
 
 static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg)
-- 
GitLab


From 2e57cefc4477659527f7adab1f87cdbf60ef1ae6 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:19 -0500
Subject: [PATCH 2175/4076] serial: sc16is7xx: replace hardcoded divisor value
 with BIT() macro

To better show why the limit is what it is, since we have only 16 bits for
the divisor.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-13-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index da862b8efcbef..3d963fe0e78a0 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -486,7 +486,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 	u8 prescaler = 0;
 	unsigned long clk = port->uartclk, div = clk / 16 / baud;
 
-	if (div > 0xffff) {
+	if (div >= BIT(16)) {
 		prescaler = SC16IS7XX_MCR_CLKSEL_BIT;
 		div /= 4;
 	}
-- 
GitLab


From e54837da4d81bd297b8b5272594eed41664c13ca Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:20 -0500
Subject: [PATCH 2176/4076] serial: sc16is7xx: drop unneeded MODULE_ALIAS

The MODULE_DEVICE_TABLE() already creates the proper aliases for the
SPI driver.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-14-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 3d963fe0e78a0..1037a28023607 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1787,8 +1787,6 @@ static struct spi_driver sc16is7xx_spi_uart_driver = {
 	.remove		= sc16is7xx_spi_remove,
 	.id_table	= sc16is7xx_spi_id_table,
 };
-
-MODULE_ALIAS("spi:sc16is7xx");
 #endif
 
 #ifdef CONFIG_SERIAL_SC16IS7XX_I2C
-- 
GitLab


From f031d763dcb0b4dbd4bbf1d4324f7ca91761d3b1 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:21 -0500
Subject: [PATCH 2177/4076] serial: sc16is7xx: refactor FIFO access functions
 to increase commonality

Simplify FIFO access functions by avoiding to declare
a struct sc16is7xx_port *s variable within each function.

This is mainly done to have more commonality between the max310x and
sc16is7xx drivers.

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-15-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 1037a28023607..26bc595a6ca74 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -379,17 +379,15 @@ static void sc16is7xx_port_write(struct uart_port *port, u8 reg, u8 val)
 	regmap_write(one->regmap, reg, val);
 }
 
-static void sc16is7xx_fifo_read(struct uart_port *port, unsigned int rxlen)
+static void sc16is7xx_fifo_read(struct uart_port *port, u8 *rxbuf, unsigned int rxlen)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
-	regmap_noinc_read(one->regmap, SC16IS7XX_RHR_REG, s->buf, rxlen);
+	regmap_noinc_read(one->regmap, SC16IS7XX_RHR_REG, rxbuf, rxlen);
 }
 
-static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
+static void sc16is7xx_fifo_write(struct uart_port *port, u8 *txbuf, u8 to_send)
 {
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
 
 	/*
@@ -399,7 +397,7 @@ static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
 	if (unlikely(!to_send))
 		return;
 
-	regmap_noinc_write(one->regmap, SC16IS7XX_THR_REG, s->buf, to_send);
+	regmap_noinc_write(one->regmap, SC16IS7XX_THR_REG, txbuf, to_send);
 }
 
 static void sc16is7xx_port_update(struct uart_port *port, u8 reg,
@@ -575,7 +573,7 @@ static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen,
 			s->buf[0] = sc16is7xx_port_read(port, SC16IS7XX_RHR_REG);
 			bytes_read = 1;
 		} else {
-			sc16is7xx_fifo_read(port, rxlen);
+			sc16is7xx_fifo_read(port, s->buf, rxlen);
 			bytes_read = rxlen;
 		}
 
@@ -664,7 +662,7 @@ static void sc16is7xx_handle_tx(struct uart_port *port)
 			uart_xmit_advance(port, 1);
 		}
 
-		sc16is7xx_fifo_write(port, to_send);
+		sc16is7xx_fifo_write(port, s->buf, to_send);
 	}
 
 	uart_port_lock_irqsave(port, &flags);
-- 
GitLab


From 2de8a1b46756b5a79d8447f99afdfe49e914225a Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:22 -0500
Subject: [PATCH 2178/4076] serial: sc16is7xx: reorder code to remove prototype
 declarations

Move/reorder some functions to remove sc16is7xx_ier_set() and
sc16is7xx_stop_tx() prototypes declarations.

No functional change.

sc16is7xx_ier_set() was introduced in
commit cc4c1d05eb10 ("sc16is7xx: Properly resume TX after stop").

Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-16-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 75 ++++++++++++++++------------------
 1 file changed, 36 insertions(+), 39 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 26bc595a6ca74..15a46c1648218 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -357,9 +357,6 @@ static struct uart_driver sc16is7xx_uart = {
 	.nr		= SC16IS7XX_MAX_DEVS,
 };
 
-static void sc16is7xx_ier_set(struct uart_port *port, u8 bit);
-static void sc16is7xx_stop_tx(struct uart_port *port);
-
 #define to_sc16is7xx_one(p,e)	((container_of((p), struct sc16is7xx_one, e)))
 
 static u8 sc16is7xx_port_read(struct uart_port *port, u8 reg)
@@ -415,6 +412,42 @@ static void sc16is7xx_power(struct uart_port *port, int on)
 			      on ? 0 : SC16IS7XX_IER_SLEEP_BIT);
 }
 
+static void sc16is7xx_ier_clear(struct uart_port *port, u8 bit)
+{
+	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	lockdep_assert_held_once(&port->lock);
+
+	one->config.flags |= SC16IS7XX_RECONF_IER;
+	one->config.ier_mask |= bit;
+	one->config.ier_val &= ~bit;
+	kthread_queue_work(&s->kworker, &one->reg_work);
+}
+
+static void sc16is7xx_ier_set(struct uart_port *port, u8 bit)
+{
+	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	lockdep_assert_held_once(&port->lock);
+
+	one->config.flags |= SC16IS7XX_RECONF_IER;
+	one->config.ier_mask |= bit;
+	one->config.ier_val |= bit;
+	kthread_queue_work(&s->kworker, &one->reg_work);
+}
+
+static void sc16is7xx_stop_tx(struct uart_port *port)
+{
+	sc16is7xx_ier_clear(port, SC16IS7XX_IER_THRI_BIT);
+}
+
+static void sc16is7xx_stop_rx(struct uart_port *port)
+{
+	sc16is7xx_ier_clear(port, SC16IS7XX_IER_RDI_BIT);
+}
+
 static const struct sc16is7xx_devtype sc16is74x_devtype = {
 	.name		= "SC16IS74X",
 	.nr_gpio	= 0,
@@ -867,42 +900,6 @@ static void sc16is7xx_reg_proc(struct kthread_work *ws)
 		sc16is7xx_reconf_rs485(&one->port);
 }
 
-static void sc16is7xx_ier_clear(struct uart_port *port, u8 bit)
-{
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-
-	lockdep_assert_held_once(&port->lock);
-
-	one->config.flags |= SC16IS7XX_RECONF_IER;
-	one->config.ier_mask |= bit;
-	one->config.ier_val &= ~bit;
-	kthread_queue_work(&s->kworker, &one->reg_work);
-}
-
-static void sc16is7xx_ier_set(struct uart_port *port, u8 bit)
-{
-	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
-	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
-
-	lockdep_assert_held_once(&port->lock);
-
-	one->config.flags |= SC16IS7XX_RECONF_IER;
-	one->config.ier_mask |= bit;
-	one->config.ier_val |= bit;
-	kthread_queue_work(&s->kworker, &one->reg_work);
-}
-
-static void sc16is7xx_stop_tx(struct uart_port *port)
-{
-	sc16is7xx_ier_clear(port, SC16IS7XX_IER_THRI_BIT);
-}
-
-static void sc16is7xx_stop_rx(struct uart_port *port)
-{
-	sc16is7xx_ier_clear(port, SC16IS7XX_IER_RDI_BIT);
-}
-
 static void sc16is7xx_ms_proc(struct kthread_work *ws)
 {
 	struct sc16is7xx_one *one = to_sc16is7xx_one(ws, ms_work.work);
-- 
GitLab


From 0c84bea0cabc4e2b98a3de88eeb4ff798931f056 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 21 Dec 2023 18:18:23 -0500
Subject: [PATCH 2179/4076] serial: sc16is7xx: refactor EFR lock

Move common code for EFR lock/unlock of mutex into functions for code reuse
and clarity.

With the addition of old_lcr, move irda_mode within struct sc16is7xx_one to
reduce memory usage:
    Before: /* size: 752, cachelines: 12, members: 10 */
    After:  /* size: 744, cachelines: 12, members: 10 */

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-17-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 106 ++++++++++++++++++---------------
 1 file changed, 57 insertions(+), 49 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 15a46c1648218..929206a9a6e11 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -330,8 +330,9 @@ struct sc16is7xx_one {
 	struct kthread_work		reg_work;
 	struct kthread_delayed_work	ms_work;
 	struct sc16is7xx_one_config	config;
-	bool				irda_mode;
 	unsigned int			old_mctrl;
+	u8				old_lcr; /* Value before EFR access. */
+	bool				irda_mode;
 };
 
 struct sc16is7xx_port {
@@ -412,6 +413,49 @@ static void sc16is7xx_power(struct uart_port *port, int on)
 			      on ? 0 : SC16IS7XX_IER_SLEEP_BIT);
 }
 
+/*
+ * In an amazing feat of design, the Enhanced Features Register (EFR)
+ * shares the address of the Interrupt Identification Register (IIR).
+ * Access to EFR is switched on by writing a magic value (0xbf) to the
+ * Line Control Register (LCR). Any interrupt firing during this time will
+ * see the EFR where it expects the IIR to be, leading to
+ * "Unexpected interrupt" messages.
+ *
+ * Prevent this possibility by claiming a mutex while accessing the EFR,
+ * and claiming the same mutex from within the interrupt handler. This is
+ * similar to disabling the interrupt, but that doesn't work because the
+ * bulk of the interrupt processing is run as a workqueue job in thread
+ * context.
+ */
+static void sc16is7xx_efr_lock(struct uart_port *port)
+{
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	mutex_lock(&one->efr_lock);
+
+	/* Backup content of LCR. */
+	one->old_lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
+
+	/* Enable access to Enhanced register set */
+	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_CONF_MODE_B);
+
+	/* Disable cache updates when writing to EFR registers */
+	regcache_cache_bypass(one->regmap, true);
+}
+
+static void sc16is7xx_efr_unlock(struct uart_port *port)
+{
+	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+	/* Re-enable cache updates when writing to normal registers */
+	regcache_cache_bypass(one->regmap, false);
+
+	/* Restore original content of LCR */
+	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, one->old_lcr);
+
+	mutex_unlock(&one->efr_lock);
+}
+
 static void sc16is7xx_ier_clear(struct uart_port *port, u8 bit)
 {
 	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
@@ -522,45 +566,19 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 		div /= 4;
 	}
 
-	/* In an amazing feat of design, the Enhanced Features Register shares
-	 * the address of the Interrupt Identification Register, and is
-	 * switched in by writing a magic value (0xbf) to the Line Control
-	 * Register. Any interrupt firing during this time will see the EFR
-	 * where it expects the IIR to be, leading to "Unexpected interrupt"
-	 * messages.
-	 *
-	 * Prevent this possibility by claiming a mutex while accessing the
-	 * EFR, and claiming the same mutex from within the interrupt handler.
-	 * This is similar to disabling the interrupt, but that doesn't work
-	 * because the bulk of the interrupt processing is run as a workqueue
-	 * job in thread context.
-	 */
-	mutex_lock(&one->efr_lock);
-
-	lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
-
-	/* Open the LCR divisors for configuration */
-	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
-			     SC16IS7XX_LCR_CONF_MODE_B);
-
 	/* Enable enhanced features */
-	regcache_cache_bypass(one->regmap, true);
+	sc16is7xx_efr_lock(port);
 	sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
 			      SC16IS7XX_EFR_ENABLE_BIT,
 			      SC16IS7XX_EFR_ENABLE_BIT);
-
-	regcache_cache_bypass(one->regmap, false);
-
-	/* Put LCR back to the normal mode */
-	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
-
-	mutex_unlock(&one->efr_lock);
+	sc16is7xx_efr_unlock(port);
 
 	sc16is7xx_port_update(port, SC16IS7XX_MCR_REG,
 			      SC16IS7XX_MCR_CLKSEL_BIT,
 			      prescaler);
 
-	/* Open the LCR divisors for configuration */
+	/* Backup LCR and access special register set (DLL/DLH) */
+	lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
 			     SC16IS7XX_LCR_CONF_MODE_A);
 
@@ -570,7 +588,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 	sc16is7xx_port_write(port, SC16IS7XX_DLL_REG, div % 256);
 	regcache_cache_bypass(one->regmap, false);
 
-	/* Put LCR back to the normal mode */
+	/* Restore LCR and access to general register set */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
 
 	return DIV_ROUND_CLOSEST(clk / 16, div);
@@ -1049,17 +1067,7 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 	if (!(termios->c_cflag & CREAD))
 		port->ignore_status_mask |= SC16IS7XX_LSR_BRK_ERROR_MASK;
 
-	/* As above, claim the mutex while accessing the EFR. */
-	mutex_lock(&one->efr_lock);
-
-	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
-			     SC16IS7XX_LCR_CONF_MODE_B);
-
 	/* Configure flow control */
-	regcache_cache_bypass(one->regmap, true);
-	sc16is7xx_port_write(port, SC16IS7XX_XON1_REG, termios->c_cc[VSTART]);
-	sc16is7xx_port_write(port, SC16IS7XX_XOFF1_REG, termios->c_cc[VSTOP]);
-
 	port->status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS);
 	if (termios->c_cflag & CRTSCTS) {
 		flow |= SC16IS7XX_EFR_AUTOCTS_BIT |
@@ -1071,16 +1079,16 @@ static void sc16is7xx_set_termios(struct uart_port *port,
 	if (termios->c_iflag & IXOFF)
 		flow |= SC16IS7XX_EFR_SWFLOW1_BIT;
 
-	sc16is7xx_port_update(port,
-			      SC16IS7XX_EFR_REG,
-			      SC16IS7XX_EFR_FLOWCTRL_BITS,
-			      flow);
-	regcache_cache_bypass(one->regmap, false);
-
 	/* Update LCR register */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
 
-	mutex_unlock(&one->efr_lock);
+	/* Update EFR registers */
+	sc16is7xx_efr_lock(port);
+	sc16is7xx_port_write(port, SC16IS7XX_XON1_REG, termios->c_cc[VSTART]);
+	sc16is7xx_port_write(port, SC16IS7XX_XOFF1_REG, termios->c_cc[VSTOP]);
+	sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
+			      SC16IS7XX_EFR_FLOWCTRL_BITS, flow);
+	sc16is7xx_efr_unlock(port);
 
 	/* Get baud rate generator configuration */
 	baud = uart_get_baud_rate(port, termios, old,
-- 
GitLab


From 5962ded777d689cd8bf04454273e32228d7fb71f Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Wed, 3 Jan 2024 18:17:55 +0000
Subject: [PATCH 2180/4076] usb: typec: class: fix typec_altmode_put_partner to
 put plugs

When typec_altmode_put_partner is called by a plug altmode upon release,
the port altmode the plug belongs to will not remove its reference to the
plug. The check to see if the altmode being released is a plug evaluates
against the released altmode's partner instead of the calling altmode, so
change adev in typec_altmode_put_partner to properly refer to the altmode
being released.

Because typec_altmode_set_partner calls get_device() on the port altmode,
add partner_adev that points to the port altmode in typec_put_partner to
call put_device() on. typec_altmode_set_partner is not called for port
altmodes, so add a check in typec_altmode_release to prevent
typec_altmode_put_partner() calls on port altmode release.

Fixes: 8a37d87d72f0 ("usb: typec: Bus type for alternate modes")
Cc:  <stable@vger.kernel.org>
Co-developed-by: Christian A. Ehrhardt <lk@c--e.de>
Signed-off-by: Christian A. Ehrhardt <lk@c--e.de>
Signed-off-by: RD Babiera <rdbabiera@google.com>
Tested-by: Christian A. Ehrhardt <lk@c--e.de>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20240103181754.2492492-2-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/class.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 4d11f2b536fae..015aa92533536 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -263,11 +263,13 @@ static void typec_altmode_put_partner(struct altmode *altmode)
 {
 	struct altmode *partner = altmode->partner;
 	struct typec_altmode *adev;
+	struct typec_altmode *partner_adev;
 
 	if (!partner)
 		return;
 
-	adev = &partner->adev;
+	adev = &altmode->adev;
+	partner_adev = &partner->adev;
 
 	if (is_typec_plug(adev->dev.parent)) {
 		struct typec_plug *plug = to_typec_plug(adev->dev.parent);
@@ -276,7 +278,7 @@ static void typec_altmode_put_partner(struct altmode *altmode)
 	} else {
 		partner->partner = NULL;
 	}
-	put_device(&adev->dev);
+	put_device(&partner_adev->dev);
 }
 
 /**
@@ -497,7 +499,8 @@ static void typec_altmode_release(struct device *dev)
 {
 	struct altmode *alt = to_altmode(to_typec_altmode(dev));
 
-	typec_altmode_put_partner(alt);
+	if (!is_typec_port(dev->parent))
+		typec_altmode_put_partner(alt);
 
 	altmode_id_remove(alt->adev.dev.parent, alt->id);
 	kfree(alt);
-- 
GitLab


From 54ffdab820801372f3632bb86613407df34b921b Mon Sep 17 00:00:00 2001
From: Tanzir Hasan <tanzirh@google.com>
Date: Tue, 26 Dec 2023 17:09:23 +0000
Subject: [PATCH 2181/4076] android: binder: binderfs.c: removed
 asm-generic/errno-base.h

asm-generic/errno-base.h can be replaced by linux/errno.h and the file
will still build correctly. It is an asm-generic file which should be
avoided if possible.

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Tanzir Hasan <tanzirh@google.com>
Acked-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231226-binderfs-v1-1-66829e92b523@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binderfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index 1224ab7aa0708..d04ff60294800 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -29,7 +29,7 @@
 #include <linux/uaccess.h>
 #include <linux/user_namespace.h>
 #include <linux/xarray.h>
-#include <uapi/asm-generic/errno-base.h>
+#include <linux/errno.h>
 #include <uapi/linux/android/binder.h>
 #include <uapi/linux/android/binderfs.h>
 
-- 
GitLab


From d8407f71ebeaeb6f50bd89791837873e44609708 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 19 Dec 2023 06:01:47 +0100
Subject: [PATCH 2182/4076] ppdev: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/ba9da12fdd5cdb2c28180b7160af5042447d803f.1702962092.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/char/ppdev.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index 4c188e9e477cd..ee951b265213f 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -299,7 +299,7 @@ static int register_device(int minor, struct pp_struct *pp)
 		goto err;
 	}
 
-	index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
+	index = ida_alloc(&ida_index, GFP_KERNEL);
 	memset(&ppdev_cb, 0, sizeof(ppdev_cb));
 	ppdev_cb.irq_func = pp_irq;
 	ppdev_cb.flags = (pp->flags & PP_EXCL) ? PARPORT_FLAG_EXCL : 0;
@@ -310,7 +310,7 @@ static int register_device(int minor, struct pp_struct *pp)
 	if (!pdev) {
 		pr_warn("%s: failed to register device!\n", name);
 		rc = -ENXIO;
-		ida_simple_remove(&ida_index, index);
+		ida_free(&ida_index, index);
 		goto err;
 	}
 
@@ -750,7 +750,7 @@ static int pp_release(struct inode *inode, struct file *file)
 
 	if (pp->pdev) {
 		parport_unregister_device(pp->pdev);
-		ida_simple_remove(&ida_index, pp->index);
+		ida_free(&ida_index, pp->index);
 		pp->pdev = NULL;
 		pr_debug(CHRDEV "%x: unregistered pardevice\n", minor);
 	}
-- 
GitLab


From 401df0d4f4098ecc9c5278da2f50756d62e5b37d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Tue, 19 Dec 2023 13:01:03 +0100
Subject: [PATCH 2183/4076] nvmem: layouts: refactor .add_cells() callback
 arguments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Simply pass whole "struct nvmem_layout" instead of single variables.
There is nothing in "struct nvmem_layout" that we have to hide from
layout drivers. They also access it during .probe() and .remove().

Thanks to this change:

1. API gets more consistent
   All layouts drivers callbacks get the same argument

2. Layouts get correct device
   Before this change NVMEM core code was passing NVMEM device instead
   of layout device. That resulted in:
   * Confusing prints
   * Calling devm_*() helpers on wrong device
   * Helpers like of_device_get_match_data() dereferencing NULLs

3. It gets possible to get match data
   First of all nvmem_layout_get_match_data() requires passing "struct
   nvmem_layout" which .add_cells() callback didn't have before this. It
   doesn't matter much as it's rather useless now anyway (and will be
   dropped).
   What's more important however is that of_device_get_match_data() can
   be used now thanks to owning a proper device pointer.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20231219120104.3422-1-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c             | 2 +-
 drivers/nvmem/layouts/onie-tlv.c | 4 +++-
 drivers/nvmem/layouts/sl28vpd.c  | 4 +++-
 include/linux/nvmem-provider.h   | 2 +-
 4 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index ba559e81f77fa..441d132ebb61f 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -854,7 +854,7 @@ int nvmem_layout_register(struct nvmem_layout *layout)
 		return -EINVAL;
 
 	/* Populate the cells */
-	ret = layout->add_cells(&layout->nvmem->dev, layout->nvmem);
+	ret = layout->add_cells(layout);
 	if (ret)
 		return ret;
 
diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c
index b24cc5dcc6ee8..9d2ad5f2dc101 100644
--- a/drivers/nvmem/layouts/onie-tlv.c
+++ b/drivers/nvmem/layouts/onie-tlv.c
@@ -182,8 +182,10 @@ static bool onie_tlv_crc_is_valid(struct device *dev, size_t table_len, u8 *tabl
 	return true;
 }
 
-static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem)
+static int onie_tlv_parse_table(struct nvmem_layout *layout)
 {
+	struct nvmem_device *nvmem = layout->nvmem;
+	struct device *dev = &layout->dev;
 	struct onie_tlv_hdr hdr;
 	size_t table_len, data_len, hdr_len;
 	u8 *table, *data;
diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c
index b8ffae646cc26..53fa50f17dcaf 100644
--- a/drivers/nvmem/layouts/sl28vpd.c
+++ b/drivers/nvmem/layouts/sl28vpd.c
@@ -80,8 +80,10 @@ static int sl28vpd_v1_check_crc(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
-static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem)
+static int sl28vpd_add_cells(struct nvmem_layout *layout)
 {
+	struct nvmem_device *nvmem = layout->nvmem;
+	struct device *dev = &layout->dev;
 	const struct nvmem_cell_info *pinfo;
 	struct nvmem_cell_info info = {0};
 	struct device_node *layout_np;
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 6fe65b35ea972..81a67642ac553 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -173,7 +173,7 @@ struct nvmem_cell_table {
 struct nvmem_layout {
 	struct device dev;
 	struct nvmem_device *nvmem;
-	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem);
+	int (*add_cells)(struct nvmem_layout *layout);
 };
 
 struct nvmem_layout_driver {
-- 
GitLab


From 43f60e3fb62edc7bd8891de8779fb422f4ae23ae Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Tue, 19 Dec 2023 13:01:04 +0100
Subject: [PATCH 2184/4076] nvmem: drop nvmem_layout_get_match_data()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Thanks for layouts refactoring we now have "struct device" associated
with layout. Also its OF pointer points directly to the "nvmem-layout"
DT node.

All it takes to get match data is a generic of_device_get_match_data().

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20231219120104.3422-2-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           | 13 -------------
 include/linux/nvmem-provider.h | 10 ----------
 2 files changed, 23 deletions(-)

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 441d132ebb61f..4ed54076346d2 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -876,19 +876,6 @@ void nvmem_layout_unregister(struct nvmem_layout *layout)
 }
 EXPORT_SYMBOL_GPL(nvmem_layout_unregister);
 
-const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-					struct nvmem_layout *layout)
-{
-	struct device_node __maybe_unused *layout_np;
-	const struct of_device_id *match;
-
-	layout_np = of_nvmem_layout_get_container(nvmem);
-	match = of_match_node(layout->dev.driver->of_match_table, layout_np);
-
-	return match ? match->data : NULL;
-}
-EXPORT_SYMBOL_GPL(nvmem_layout_get_match_data);
-
 /**
  * nvmem_register() - Register a nvmem device for given nvmem_config.
  * Also creates a binary entry in /sys/bus/nvmem/devices/dev-name/nvmem
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 81a67642ac553..f0ba0e03218f9 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -205,9 +205,6 @@ void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv);
 	module_driver(__nvmem_layout_driver, nvmem_layout_driver_register, \
 		      nvmem_layout_driver_unregister)
 
-const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-					struct nvmem_layout *layout);
-
 #else
 
 static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c)
@@ -238,13 +235,6 @@ static inline int nvmem_layout_register(struct nvmem_layout *layout)
 
 static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {}
 
-static inline const void *
-nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-			    struct nvmem_layout *layout)
-{
-	return NULL;
-}
-
 #endif /* CONFIG_NVMEM */
 
 #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF)
-- 
GitLab


From 33cf42e68efc8ff529a7eee08a4f0ba8c8d0a207 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Thu, 21 Dec 2023 18:34:17 +0100
Subject: [PATCH 2185/4076] nvmem: core: add nvmem_dev_size() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is required by layouts that need to read whole NVMEM content. It's
especially useful for NVMEM devices without hardcoded layout (like
U-Boot environment data block).

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231221173421.13737-2-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           | 13 +++++++++++++
 include/linux/nvmem-consumer.h |  1 +
 2 files changed, 14 insertions(+)

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 4ed54076346d2..980123fb4dde0 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -2163,6 +2163,19 @@ const char *nvmem_dev_name(struct nvmem_device *nvmem)
 }
 EXPORT_SYMBOL_GPL(nvmem_dev_name);
 
+/**
+ * nvmem_dev_size() - Get the size of a given nvmem device.
+ *
+ * @nvmem: nvmem device.
+ *
+ * Return: size of the nvmem device.
+ */
+size_t nvmem_dev_size(struct nvmem_device *nvmem)
+{
+	return nvmem->size;
+}
+EXPORT_SYMBOL_GPL(nvmem_dev_size);
+
 static int __init nvmem_init(void)
 {
 	int ret;
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 2d306fa13b1a8..34c0e58dfa266 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -81,6 +81,7 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem,
 			    struct nvmem_cell_info *info, void *buf);
 
 const char *nvmem_dev_name(struct nvmem_device *nvmem);
+size_t nvmem_dev_size(struct nvmem_device *nvmem);
 
 void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries,
 			    size_t nentries);
-- 
GitLab


From 7c8979b42b1a9c5604f431ba804928e55919263c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Thu, 21 Dec 2023 18:34:18 +0100
Subject: [PATCH 2186/4076] nvmem: u-boot-env: use nvmem_add_one_cell() nvmem
 subsystem helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Simplify adding NVMEM cells.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231221173421.13737-3-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/u-boot-env.c | 55 +++++++++++++++-----------------------
 1 file changed, 21 insertions(+), 34 deletions(-)

diff --git a/drivers/nvmem/u-boot-env.c b/drivers/nvmem/u-boot-env.c
index c4ae94af4af78..dd9d0ad22712e 100644
--- a/drivers/nvmem/u-boot-env.c
+++ b/drivers/nvmem/u-boot-env.c
@@ -23,13 +23,10 @@ enum u_boot_env_format {
 
 struct u_boot_env {
 	struct device *dev;
+	struct nvmem_device *nvmem;
 	enum u_boot_env_format format;
 
 	struct mtd_info *mtd;
-
-	/* Cells */
-	struct nvmem_cell_info *cells;
-	int ncells;
 };
 
 struct u_boot_env_image_single {
@@ -94,43 +91,36 @@ static int u_boot_env_read_post_process_ethaddr(void *context, const char *id, i
 static int u_boot_env_add_cells(struct u_boot_env *priv, uint8_t *buf,
 				size_t data_offset, size_t data_len)
 {
+	struct nvmem_device *nvmem = priv->nvmem;
 	struct device *dev = priv->dev;
 	char *data = buf + data_offset;
 	char *var, *value, *eq;
-	int idx;
-
-	priv->ncells = 0;
-	for (var = data; var < data + data_len && *var; var += strlen(var) + 1)
-		priv->ncells++;
-
-	priv->cells = devm_kcalloc(dev, priv->ncells, sizeof(*priv->cells), GFP_KERNEL);
-	if (!priv->cells)
-		return -ENOMEM;
 
-	for (var = data, idx = 0;
+	for (var = data;
 	     var < data + data_len && *var;
-	     var = value + strlen(value) + 1, idx++) {
+	     var = value + strlen(value) + 1) {
+		struct nvmem_cell_info info = {};
+
 		eq = strchr(var, '=');
 		if (!eq)
 			break;
 		*eq = '\0';
 		value = eq + 1;
 
-		priv->cells[idx].name = devm_kstrdup(dev, var, GFP_KERNEL);
-		if (!priv->cells[idx].name)
+		info.name = devm_kstrdup(dev, var, GFP_KERNEL);
+		if (!info.name)
 			return -ENOMEM;
-		priv->cells[idx].offset = data_offset + value - data;
-		priv->cells[idx].bytes = strlen(value);
-		priv->cells[idx].np = of_get_child_by_name(dev->of_node, priv->cells[idx].name);
+		info.offset = data_offset + value - data;
+		info.bytes = strlen(value);
+		info.np = of_get_child_by_name(dev->of_node, info.name);
 		if (!strcmp(var, "ethaddr")) {
-			priv->cells[idx].raw_len = strlen(value);
-			priv->cells[idx].bytes = ETH_ALEN;
-			priv->cells[idx].read_post_process = u_boot_env_read_post_process_ethaddr;
+			info.raw_len = strlen(value);
+			info.bytes = ETH_ALEN;
+			info.read_post_process = u_boot_env_read_post_process_ethaddr;
 		}
-	}
 
-	if (WARN_ON(idx != priv->ncells))
-		priv->ncells = idx;
+		nvmem_add_one_cell(nvmem, &info);
+	}
 
 	return 0;
 }
@@ -209,7 +199,6 @@ static int u_boot_env_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct u_boot_env *priv;
-	int err;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -224,17 +213,15 @@ static int u_boot_env_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->mtd);
 	}
 
-	err = u_boot_env_parse(priv);
-	if (err)
-		return err;
-
 	config.dev = dev;
-	config.cells = priv->cells;
-	config.ncells = priv->ncells;
 	config.priv = priv;
 	config.size = priv->mtd->size;
 
-	return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &config));
+	priv->nvmem = devm_nvmem_register(dev, &config);
+	if (IS_ERR(priv->nvmem))
+		return PTR_ERR(priv->nvmem);
+
+	return u_boot_env_parse(priv);
 }
 
 static const struct of_device_id u_boot_env_of_match_table[] = {
-- 
GitLab


From a832556d23c5a11115f300011a5874d6107a0d62 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Thu, 21 Dec 2023 18:34:19 +0100
Subject: [PATCH 2187/4076] nvmem: u-boot-env: use nvmem device helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use nvmem_dev_size() and nvmem_device_read() to make this driver less
mtd dependent.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231221173421.13737-4-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/u-boot-env.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/nvmem/u-boot-env.c b/drivers/nvmem/u-boot-env.c
index dd9d0ad22712e..111905189341f 100644
--- a/drivers/nvmem/u-boot-env.c
+++ b/drivers/nvmem/u-boot-env.c
@@ -127,27 +127,34 @@ static int u_boot_env_add_cells(struct u_boot_env *priv, uint8_t *buf,
 
 static int u_boot_env_parse(struct u_boot_env *priv)
 {
+	struct nvmem_device *nvmem = priv->nvmem;
 	struct device *dev = priv->dev;
 	size_t crc32_data_offset;
 	size_t crc32_data_len;
 	size_t crc32_offset;
 	size_t data_offset;
 	size_t data_len;
+	size_t dev_size;
 	uint32_t crc32;
 	uint32_t calc;
-	size_t bytes;
 	uint8_t *buf;
+	int bytes;
 	int err;
 
-	buf = kcalloc(1, priv->mtd->size, GFP_KERNEL);
+	dev_size = nvmem_dev_size(nvmem);
+
+	buf = kcalloc(1, dev_size, GFP_KERNEL);
 	if (!buf) {
 		err = -ENOMEM;
 		goto err_out;
 	}
 
-	err = mtd_read(priv->mtd, 0, priv->mtd->size, &bytes, buf);
-	if ((err && !mtd_is_bitflip(err)) || bytes != priv->mtd->size) {
-		dev_err(dev, "Failed to read from mtd: %d\n", err);
+	bytes = nvmem_device_read(nvmem, 0, dev_size, buf);
+	if (bytes < 0) {
+		err = bytes;
+		goto err_kfree;
+	} else if (bytes != dev_size) {
+		err = -EIO;
 		goto err_kfree;
 	}
 
@@ -169,8 +176,8 @@ static int u_boot_env_parse(struct u_boot_env *priv)
 		break;
 	}
 	crc32 = le32_to_cpu(*(__le32 *)(buf + crc32_offset));
-	crc32_data_len = priv->mtd->size - crc32_data_offset;
-	data_len = priv->mtd->size - data_offset;
+	crc32_data_len = dev_size - crc32_data_offset;
+	data_len = dev_size - data_offset;
 
 	calc = crc32(~0, buf + crc32_data_offset, crc32_data_len) ^ ~0L;
 	if (calc != crc32) {
@@ -179,7 +186,7 @@ static int u_boot_env_parse(struct u_boot_env *priv)
 		goto err_kfree;
 	}
 
-	buf[priv->mtd->size - 1] = '\0';
+	buf[dev_size - 1] = '\0';
 	err = u_boot_env_add_cells(priv, buf, data_offset, data_len);
 	if (err)
 		dev_err(dev, "Failed to add cells: %d\n", err);
-- 
GitLab


From 6bafe07c930676d6430be471310958070816a595 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Thu, 21 Dec 2023 18:34:20 +0100
Subject: [PATCH 2188/4076] nvmem: u-boot-env: improve coding style
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

1. Prefer kzalloc() over kcalloc()
   See memory-allocation.rst which says: "to be on the safe side it's
   best to use routines that set memory to zero, like kzalloc()"
2. Drop dev_err() for u_boot_env_add_cells() fail
   It can fail only on -ENOMEM. We don't want to print error then.
3. Add extra "crc32_addr" variable
   It makes code reading header's crc32 easier to understand / review.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231221173421.13737-5-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/u-boot-env.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/nvmem/u-boot-env.c b/drivers/nvmem/u-boot-env.c
index 111905189341f..befbab156cda1 100644
--- a/drivers/nvmem/u-boot-env.c
+++ b/drivers/nvmem/u-boot-env.c
@@ -132,6 +132,7 @@ static int u_boot_env_parse(struct u_boot_env *priv)
 	size_t crc32_data_offset;
 	size_t crc32_data_len;
 	size_t crc32_offset;
+	__le32 *crc32_addr;
 	size_t data_offset;
 	size_t data_len;
 	size_t dev_size;
@@ -143,7 +144,7 @@ static int u_boot_env_parse(struct u_boot_env *priv)
 
 	dev_size = nvmem_dev_size(nvmem);
 
-	buf = kcalloc(1, dev_size, GFP_KERNEL);
+	buf = kzalloc(dev_size, GFP_KERNEL);
 	if (!buf) {
 		err = -ENOMEM;
 		goto err_out;
@@ -175,7 +176,8 @@ static int u_boot_env_parse(struct u_boot_env *priv)
 		data_offset = offsetof(struct u_boot_env_image_broadcom, data);
 		break;
 	}
-	crc32 = le32_to_cpu(*(__le32 *)(buf + crc32_offset));
+	crc32_addr = (__le32 *)(buf + crc32_offset);
+	crc32 = le32_to_cpu(*crc32_addr);
 	crc32_data_len = dev_size - crc32_data_offset;
 	data_len = dev_size - data_offset;
 
@@ -188,8 +190,6 @@ static int u_boot_env_parse(struct u_boot_env *priv)
 
 	buf[dev_size - 1] = '\0';
 	err = u_boot_env_add_cells(priv, buf, data_offset, data_len);
-	if (err)
-		dev_err(dev, "Failed to add cells: %d\n", err);
 
 err_kfree:
 	kfree(buf);
-- 
GitLab


From aeda33ab8160c7a2e24ba4f44492ad1e974ddc7d Mon Sep 17 00:00:00 2001
From: Abhijit Gangurde <abhijit.gangurde@amd.com>
Date: Fri, 22 Dec 2023 12:16:26 +0530
Subject: [PATCH 2189/4076] cdx: create sysfs bin files for cdx resources

Resource binary file contains the content of the memory regions.
These resources<x> devices can be used to mmap the MMIO regions in
the user-space.

Co-developed-by: Puneet Gupta <puneet.gupta@amd.com>
Signed-off-by: Puneet Gupta <puneet.gupta@amd.com>
Signed-off-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Link: https://lore.kernel.org/r/20231222064627.2828960-1-abhijit.gangurde@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-bus-cdx |   7 ++
 drivers/cdx/cdx.c                       | 118 +++++++++++++++++++++++-
 include/linux/cdx/cdx_bus.h             |  10 ++
 3 files changed, 134 insertions(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-bus-cdx b/Documentation/ABI/testing/sysfs-bus-cdx
index 8c067ff99e547..e84277531414b 100644
--- a/Documentation/ABI/testing/sysfs-bus-cdx
+++ b/Documentation/ABI/testing/sysfs-bus-cdx
@@ -98,6 +98,13 @@ Description:
 
 		  # echo 1 > /sys/bus/cdx/devices/.../remove
 
+What:		/sys/bus/cdx/devices/.../resource<N>
+Date:		July 2023
+Contact:	puneet.gupta@amd.com
+Description:
+		The resource binary file contains the content of the memory
+		regions. These files can be m'maped from userspace.
+
 What:		/sys/bus/cdx/devices/.../modalias
 Date:		July 2023
 Contact:	nipun.gupta@amd.com
diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index d84d153078d75..2ec1846ff063c 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -80,6 +80,8 @@ static DEFINE_MUTEX(cdx_controller_lock);
 
 static char *compat_node_name = "xlnx,versal-net-cdx";
 
+static void cdx_destroy_res_attr(struct cdx_device *cdx_dev, int num);
+
 /**
  * cdx_dev_reset - Reset a CDX device
  * @dev: CDX device
@@ -148,6 +150,7 @@ static int cdx_unregister_device(struct device *dev,
 		if (cdx_dev->enabled && cdx->ops->bus_disable)
 			cdx->ops->bus_disable(cdx, cdx_dev->bus_num);
 	} else {
+		cdx_destroy_res_attr(cdx_dev, MAX_CDX_DEV_RESOURCES);
 		kfree(cdx_dev->driver_override);
 		cdx_dev->driver_override = NULL;
 	}
@@ -643,11 +646,105 @@ static void cdx_device_release(struct device *dev)
 	kfree(cdx_dev);
 }
 
+static const struct vm_operations_struct cdx_phys_vm_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+	.access = generic_access_phys,
+#endif
+};
+
+/**
+ * cdx_mmap_resource - map a CDX resource into user memory space
+ * @fp: File pointer. Not used in this function, but required where
+ *      this API is registered as a callback.
+ * @kobj: kobject for mapping
+ * @attr: struct bin_attribute for the file being mapped
+ * @vma: struct vm_area_struct passed into the mmap
+ *
+ * Use the regular CDX mapping routines to map a CDX resource into userspace.
+ *
+ * Return: true on success, false otherwise.
+ */
+static int cdx_mmap_resource(struct file *fp, struct kobject *kobj,
+			     struct bin_attribute *attr,
+			     struct vm_area_struct *vma)
+{
+	struct cdx_device *cdx_dev = to_cdx_device(kobj_to_dev(kobj));
+	int num = (unsigned long)attr->private;
+	struct resource *res;
+	unsigned long size;
+
+	res = &cdx_dev->res[num];
+	if (iomem_is_exclusive(res->start))
+		return -EINVAL;
+
+	/* Make sure the caller is mapping a valid resource for this device */
+	size = ((cdx_resource_len(cdx_dev, num) - 1) >> PAGE_SHIFT) + 1;
+	if (vma->vm_pgoff + vma_pages(vma) > size)
+		return -EINVAL;
+
+	/*
+	 * Map memory region and vm->vm_pgoff is expected to be an
+	 * offset within that region.
+	 */
+	vma->vm_page_prot = pgprot_device(vma->vm_page_prot);
+	vma->vm_pgoff += (cdx_resource_start(cdx_dev, num) >> PAGE_SHIFT);
+	vma->vm_ops = &cdx_phys_vm_ops;
+	return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+				  vma->vm_end - vma->vm_start,
+				  vma->vm_page_prot);
+}
+
+static void cdx_destroy_res_attr(struct cdx_device *cdx_dev, int num)
+{
+	int i;
+
+	/* removing the bin attributes */
+	for (i = 0; i < num; i++) {
+		struct bin_attribute *res_attr;
+
+		res_attr = cdx_dev->res_attr[i];
+		if (res_attr) {
+			sysfs_remove_bin_file(&cdx_dev->dev.kobj, res_attr);
+			kfree(res_attr);
+		}
+	}
+}
+
+#define CDX_RES_ATTR_NAME_LEN	10
+static int cdx_create_res_attr(struct cdx_device *cdx_dev, int num)
+{
+	struct bin_attribute *res_attr;
+	char *res_attr_name;
+	int ret;
+
+	res_attr = kzalloc(sizeof(*res_attr) + CDX_RES_ATTR_NAME_LEN, GFP_ATOMIC);
+	if (!res_attr)
+		return -ENOMEM;
+
+	res_attr_name = (char *)(res_attr + 1);
+
+	sysfs_bin_attr_init(res_attr);
+
+	cdx_dev->res_attr[num] = res_attr;
+	sprintf(res_attr_name, "resource%d", num);
+
+	res_attr->mmap = cdx_mmap_resource;
+	res_attr->attr.name = res_attr_name;
+	res_attr->attr.mode = 0600;
+	res_attr->size = cdx_resource_len(cdx_dev, num);
+	res_attr->private = (void *)(unsigned long)num;
+	ret = sysfs_create_bin_file(&cdx_dev->dev.kobj, res_attr);
+	if (ret)
+		kfree(res_attr);
+
+	return ret;
+}
+
 int cdx_device_add(struct cdx_dev_params *dev_params)
 {
 	struct cdx_controller *cdx = dev_params->cdx;
 	struct cdx_device *cdx_dev;
-	int ret;
+	int ret, i;
 
 	cdx_dev = kzalloc(sizeof(*cdx_dev), GFP_KERNEL);
 	if (!cdx_dev)
@@ -690,7 +787,26 @@ int cdx_device_add(struct cdx_dev_params *dev_params)
 		goto fail;
 	}
 
+	/* Create resource<N> attributes */
+	for (i = 0; i < MAX_CDX_DEV_RESOURCES; i++) {
+		if (cdx_resource_flags(cdx_dev, i) & IORESOURCE_MEM) {
+			/* skip empty resources */
+			if (!cdx_resource_len(cdx_dev, i))
+				continue;
+
+			ret = cdx_create_res_attr(cdx_dev, i);
+			if (ret != 0) {
+				dev_err(&cdx_dev->dev,
+					"cdx device resource<%d> file creation failed: %d", i, ret);
+				goto resource_create_fail;
+			}
+		}
+	}
+
 	return 0;
+resource_create_fail:
+	cdx_destroy_res_attr(cdx_dev, i);
+	device_del(&cdx_dev->dev);
 fail:
 	/*
 	 * Do not free cdx_dev here as it would be freed in
diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h
index 94ad2c9017c9d..fab9e62c7e7d3 100644
--- a/include/linux/cdx/cdx_bus.h
+++ b/include/linux/cdx/cdx_bus.h
@@ -135,6 +135,7 @@ struct cdx_device {
 	u8 bus_num;
 	u8 dev_num;
 	struct resource res[MAX_CDX_DEV_RESOURCES];
+	struct bin_attribute *res_attr[MAX_CDX_DEV_RESOURCES];
 	u8 res_count;
 	u64 dma_mask;
 	u16 flags;
@@ -147,6 +148,15 @@ struct cdx_device {
 #define to_cdx_device(_dev) \
 	container_of(_dev, struct cdx_device, dev)
 
+#define cdx_resource_start(dev, num)	((dev)->res[(num)].start)
+#define cdx_resource_end(dev, num)	((dev)->res[(num)].end)
+#define cdx_resource_flags(dev, num)	((dev)->res[(num)].flags)
+#define cdx_resource_len(dev, num) \
+	((cdx_resource_start((dev), (num)) == 0 &&	\
+	  cdx_resource_end((dev), (num)) ==		\
+	  cdx_resource_start((dev), (num))) ? 0 :	\
+	 (cdx_resource_end((dev), (num)) -		\
+	  cdx_resource_start((dev), (num)) + 1))
 /**
  * struct cdx_driver - CDX device driver
  * @driver: Generic device driver
-- 
GitLab


From cf60af04edfe51fca488246c9959904adb2750fa Mon Sep 17 00:00:00 2001
From: Abhijit Gangurde <abhijit.gangurde@amd.com>
Date: Fri, 22 Dec 2023 12:16:27 +0530
Subject: [PATCH 2190/4076] cdx: Create resource debugfs file for cdx device

resource debugfs file contains host addresses of CDX device resources.
Each line of the resource file describe type of resource, a region
with start-end and flag fields.

Signed-off-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Link: https://lore.kernel.org/r/20231222064627.2828960-2-abhijit.gangurde@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/cdx/cdx.c           | 39 ++++++++++++++++++++++++++++++++++++-
 include/linux/cdx/cdx_bus.h |  2 ++
 2 files changed, 40 insertions(+), 1 deletion(-)

diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 2ec1846ff063c..c0fca63c7434e 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -67,6 +67,7 @@
 #include <linux/cdx/cdx_bus.h>
 #include <linux/iommu.h>
 #include <linux/dma-map-ops.h>
+#include <linux/debugfs.h>
 #include "cdx.h"
 
 /* Default DMA mask for devices on a CDX bus */
@@ -77,6 +78,8 @@
 static DEFINE_IDA(cdx_controller_ida);
 /* Lock to protect controller ops */
 static DEFINE_MUTEX(cdx_controller_lock);
+/* Debugfs dir for cdx bus */
+static struct dentry *cdx_debugfs_dir;
 
 static char *compat_node_name = "xlnx,versal-net-cdx";
 
@@ -151,6 +154,7 @@ static int cdx_unregister_device(struct device *dev,
 			cdx->ops->bus_disable(cdx, cdx_dev->bus_num);
 	} else {
 		cdx_destroy_res_attr(cdx_dev, MAX_CDX_DEV_RESOURCES);
+		debugfs_remove_recursive(cdx_dev->debugfs_dir);
 		kfree(cdx_dev->driver_override);
 		cdx_dev->driver_override = NULL;
 	}
@@ -554,6 +558,31 @@ static const struct attribute_group *cdx_dev_groups[] = {
 	NULL,
 };
 
+static int cdx_debug_resource_show(struct seq_file *s, void *data)
+{
+	struct cdx_device *cdx_dev = s->private;
+	int i;
+
+	for (i = 0; i < MAX_CDX_DEV_RESOURCES; i++) {
+		struct resource *res =  &cdx_dev->res[i];
+
+		seq_printf(s, "%pr\n", res);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(cdx_debug_resource);
+
+static void cdx_device_debugfs_init(struct cdx_device *cdx_dev)
+{
+	cdx_dev->debugfs_dir = debugfs_create_dir(dev_name(&cdx_dev->dev), cdx_debugfs_dir);
+	if (IS_ERR(cdx_dev->debugfs_dir))
+		return;
+
+	debugfs_create_file("resource", 0444, cdx_dev->debugfs_dir, cdx_dev,
+			    &cdx_debug_resource_fops);
+}
+
 static ssize_t rescan_store(const struct bus_type *bus,
 			    const char *buf, size_t count)
 {
@@ -803,6 +832,8 @@ int cdx_device_add(struct cdx_dev_params *dev_params)
 		}
 	}
 
+	cdx_device_debugfs_init(cdx_dev);
+
 	return 0;
 resource_create_fail:
 	cdx_destroy_res_attr(cdx_dev, i);
@@ -907,6 +938,12 @@ EXPORT_SYMBOL_NS_GPL(cdx_unregister_controller, CDX_BUS_CONTROLLER);
 
 static int __init cdx_bus_init(void)
 {
-	return bus_register(&cdx_bus_type);
+	int ret;
+
+	ret = bus_register(&cdx_bus_type);
+	if (!ret)
+		cdx_debugfs_dir = debugfs_create_dir(cdx_bus_type.name, NULL);
+
+	return ret;
 }
 postcore_initcall(cdx_bus_init);
diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h
index fab9e62c7e7d3..6355a36a3f815 100644
--- a/include/linux/cdx/cdx_bus.h
+++ b/include/linux/cdx/cdx_bus.h
@@ -113,6 +113,7 @@ struct cdx_controller {
  * @dev_num: Device number for this device
  * @res: array of MMIO region entries
  * @res_attr: resource binary attribute
+ * @debugfs_dir: debugfs directory for this device
  * @res_count: number of valid MMIO regions
  * @dma_mask: Default DMA mask
  * @flags: CDX device flags
@@ -136,6 +137,7 @@ struct cdx_device {
 	u8 dev_num;
 	struct resource res[MAX_CDX_DEV_RESOURCES];
 	struct bin_attribute *res_attr[MAX_CDX_DEV_RESOURCES];
+	struct dentry *debugfs_dir;
 	u8 res_count;
 	u64 dma_mask;
 	u16 flags;
-- 
GitLab


From 87736ae12e1427bb2e6fd11f37b2ff76ed69aa0f Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 2 Jan 2024 16:10:21 +0300
Subject: [PATCH 2191/4076] cdx: call of_node_put() on error path

Add a missing call to of_node_put(np) on error.

There was a second error path where "np" was NULL, but that situation is
impossible.  The for_each_compatible_node() loop iterator is always
non-NULL.  Just deleted that error path.

Fixes: 54b406e10f03 ("cdx: Remove cdx controller list from cdx bus system")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Link: https://lore.kernel.org/r/2e66efc4-a13a-4774-8c9d-763455fe4834@moroto.mountain
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/cdx/cdx.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index c0fca63c7434e..929fe3d07eeec 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -604,12 +604,11 @@ static ssize_t rescan_store(const struct bus_type *bus,
 
 	/* Rescan all the devices */
 	for_each_compatible_node(np, NULL, compat_node_name) {
-		if (!np)
-			return -EINVAL;
-
 		pd = of_find_device_by_node(np);
-		if (!pd)
+		if (!pd) {
+			of_node_put(np);
 			return -EINVAL;
+		}
 
 		cdx = platform_get_drvdata(pd);
 		if (cdx && cdx->controller_registered && cdx->ops->scan)
-- 
GitLab


From 1960932eef9183e2dab662fe75126f7fa46e0e6d Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 2 Jan 2024 16:11:16 +0300
Subject: [PATCH 2192/4076] cdx: Unlock on error path in rescan_store()

We added locking to this function but these two error paths were
accidentally overlooked.

Fixes: f0af81683466 ("cdx: Introduce lock to protect controller ops")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Link: https://lore.kernel.org/r/a7994b47-6f78-4e2c-a30a-ee5995d428ec@moroto.mountain
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/cdx/cdx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 929fe3d07eeec..b74d76afccb63 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -607,7 +607,8 @@ static ssize_t rescan_store(const struct bus_type *bus,
 		pd = of_find_device_by_node(np);
 		if (!pd) {
 			of_node_put(np);
-			return -EINVAL;
+			count = -EINVAL;
+			goto unlock;
 		}
 
 		cdx = platform_get_drvdata(pd);
@@ -617,6 +618,7 @@ static ssize_t rescan_store(const struct bus_type *bus,
 		put_device(&pd->dev);
 	}
 
+unlock:
 	mutex_unlock(&cdx_controller_lock);
 
 	return count;
-- 
GitLab


From a87e55bfa25c195b3aaa25369175905ba9527fff Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 15:26:38 +0100
Subject: [PATCH 2193/4076] moxtet: remove unused moxtet_type declaration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For some reason, moxtet_type was defined in moxtet.h, but never actually
used.  Looks like a left-over from the original commit that was
exporting the moxtet bus type, but that wasn't needed, and it was a
different variable name, so no one noticed this one dangling around.

Cc: Marek Behún <kabel@kernel.org>
Link: https://lore.kernel.org/r/2023121937-pants-heroics-17c1@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/moxtet.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h
index 79184948fab47..ac577699edfdb 100644
--- a/include/linux/moxtet.h
+++ b/include/linux/moxtet.h
@@ -35,8 +35,6 @@ enum turris_mox_module_id {
 
 #define MOXTET_NIRQS	16
 
-extern struct bus_type moxtet_type;
-
 struct moxtet {
 	struct device			*dev;
 	struct mutex			lock;
-- 
GitLab


From a6c7e0146b2db55531f9c48408daf7bcb07e4b0e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 15:26:39 +0100
Subject: [PATCH 2194/4076] moxtet: mark moxtet_bus_type as const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that the driver core can properly handle constant struct bus_type,
move the moxtet_bus_type to be a constant structure as well, placing it
into read-only memory which can not be modified at runtime.

Cc: Marek Behún <kabel@kernel.org>
Link: https://lore.kernel.org/r/2023121939-written-guru-db83@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/moxtet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c
index 5eb0fe73ddc45..5e71b4c29992d 100644
--- a/drivers/bus/moxtet.c
+++ b/drivers/bus/moxtet.c
@@ -102,7 +102,7 @@ static int moxtet_match(struct device *dev, struct device_driver *drv)
 	return 0;
 }
 
-static struct bus_type moxtet_bus_type = {
+static const struct bus_type moxtet_bus_type = {
 	.name		= "moxtet",
 	.dev_groups	= moxtet_dev_groups,
 	.match		= moxtet_match,
-- 
GitLab


From 393bd1000f8192fcf5fa4abc1e79c0919c123e9b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 19 Dec 2023 23:09:48 +0100
Subject: [PATCH 2195/4076] eeprom: ee1004: add support for temperature sensor

The EE1004 SPD data structure advertises the presence of a thermal
sensor on a DDR4 module in byte 14, bit 7. Let's use this information
to explicitly instantiate the thermal sensor I2C client instead of
having to rely on class-based I2C probing.

The temp sensor i2c address can be derived from the SPD i2c address,
so we can directly instantiate the device and don't have to probe
for it. If the temp sensor has been instantiated already by other
means (e.g. class-based auto-detection), then the busy-check in
i2c_new_client_device will detect this.

Patch was successfully tested with a Corsair Vengeance RGB PRO
DDR4 module which comes with a thermal sensor.

Link: https://www.spinics.net/lists/linux-i2c/msg65963.html
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/aa063dfb-2a92-40ba-bdab-e972781ae84b@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/eeprom/ee1004.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/misc/eeprom/ee1004.c b/drivers/misc/eeprom/ee1004.c
index fd12ce06a4d5e..21feebc3044c3 100644
--- a/drivers/misc/eeprom/ee1004.c
+++ b/drivers/misc/eeprom/ee1004.c
@@ -182,6 +182,22 @@ static struct bin_attribute *ee1004_attrs[] = {
 
 BIN_ATTRIBUTE_GROUPS(ee1004);
 
+static void ee1004_probe_temp_sensor(struct i2c_client *client)
+{
+	struct i2c_board_info info = { .type = "jc42" };
+	u8 byte14;
+	int ret;
+
+	/* byte 14, bit 7 is set if temp sensor is present */
+	ret = ee1004_eeprom_read(client, &byte14, 14, 1);
+	if (ret != 1 || !(byte14 & BIT(7)))
+		return;
+
+	info.addr = 0x18 | (client->addr & 7);
+
+	i2c_new_client_device(client->adapter, &info);
+}
+
 static void ee1004_cleanup(int idx, struct ee1004_bus_data *bd)
 {
 	if (--bd->dev_count == 0) {
@@ -234,6 +250,9 @@ static int ee1004_probe(struct i2c_client *client)
 		dev_dbg(&client->dev, "Currently selected page: %d\n", err);
 		bd->current_page = err;
 	}
+
+	ee1004_probe_temp_sensor(client);
+
 	mutex_unlock(&ee1004_bus_lock);
 
 	dev_info(&client->dev,
-- 
GitLab


From caba40ec3531b0849f44502a03117796e8c9f4a1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 20 Dec 2023 13:55:58 +0100
Subject: [PATCH 2196/4076] eeprom: at24: Probe for DDR3 thermal sensor in the
 SPD case

The DDR3 SPD data structure advertises the presence of a thermal
sensor on a DDR3 module in byte 32, bit 7. Let's use this information
to explicitly instantiate the thermal sensor I2C client instead of
having to rely on class-based I2C probing.

The temp sensor i2c address can be derived from the SPD i2c address,
so we can directly instantiate the device and don't have to probe
for it. If the temp sensor has been instantiated already by other
means (e.g. class-based auto-detection), then the busy-check in
i2c_new_client_device will detect this.

Note: Thermal sensors on DDR4 DIMM's are instantiated from the
      ee1004 driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/68113672-3724-44d5-9ff8-313dd6628f8c@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/eeprom/at24.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index f61a80597a22d..3327c8a512ad7 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -563,6 +563,31 @@ static unsigned int at24_get_offset_adj(u8 flags, unsigned int byte_len)
 	}
 }
 
+static void at24_probe_temp_sensor(struct i2c_client *client)
+{
+	struct at24_data *at24 = i2c_get_clientdata(client);
+	struct i2c_board_info info = { .type = "jc42" };
+	int ret;
+	u8 val;
+
+	/*
+	 * Byte 2 has value 11 for DDR3, earlier versions don't
+	 * support the thermal sensor present flag
+	 */
+	ret = at24_read(at24, 2, &val, 1);
+	if (ret || val != 11)
+		return;
+
+	/* Byte 32, bit 7 is set if temp sensor is present */
+	ret = at24_read(at24, 32, &val, 1);
+	if (ret || !(val & BIT(7)))
+		return;
+
+	info.addr = 0x18 | (client->addr & 7);
+
+	i2c_new_client_device(client->adapter, &info);
+}
+
 static int at24_probe(struct i2c_client *client)
 {
 	struct regmap_config regmap_config = { };
@@ -762,6 +787,10 @@ static int at24_probe(struct i2c_client *client)
 		}
 	}
 
+	/* If this a SPD EEPROM, probe for DDR3 thermal sensor */
+	if (cdata == &at24_data_spd)
+		at24_probe_temp_sensor(client);
+
 	pm_runtime_idle(dev);
 
 	if (writable)
-- 
GitLab


From e68f487133d515234bdf00b85fedd0fe6216349e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 20 Dec 2023 16:11:14 +0100
Subject: [PATCH 2197/4076] eeprom: at24: Use pm_runtime_resume_and_get to
 simplify the code

Use helper pm_runtime_resume_and_get() to simplify the code.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/c3045427-da42-4f7c-8a96-3c4756646cd0@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/eeprom/at24.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 3327c8a512ad7..a5dcd7a134682 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -439,12 +439,9 @@ static int at24_read(void *priv, unsigned int off, void *val, size_t count)
 	if (off + count > at24->byte_len)
 		return -EINVAL;
 
-	ret = pm_runtime_get_sync(dev);
-	if (ret < 0) {
-		pm_runtime_put_noidle(dev);
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
 		return ret;
-	}
-
 	/*
 	 * Read data from chip, protecting against concurrent updates
 	 * from this host, but not from other I2C masters.
@@ -486,12 +483,9 @@ static int at24_write(void *priv, unsigned int off, void *val, size_t count)
 	if (off + count > at24->byte_len)
 		return -EINVAL;
 
-	ret = pm_runtime_get_sync(dev);
-	if (ret < 0) {
-		pm_runtime_put_noidle(dev);
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
 		return ret;
-	}
-
 	/*
 	 * Write data to chip, protecting against concurrent updates
 	 * from this host, but not from other I2C masters.
-- 
GitLab


From e1be24b2e1190a7662462e8e398189ac795339cd Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 18:18:58 +0100
Subject: [PATCH 2198/4076] platform/surface: aggregator: make ssam_bus_type
 constant and static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that the driver core can properly handle constant struct bus_type,
move the ssam_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

It's also never used outside of
drivers/platform/surface/aggregator/bus.c so make it static and don't
export it as no one is using it.

Cc: Maximilian Luz <luzmaximilian@gmail.com>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Cc:  <platform-driver-x86@vger.kernel.org>
Reviewed-by: Maximilian Luz <luzmaximilian@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/2023121957-tapered-upswing-8326@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/platform/surface/aggregator/bus.c | 5 +++--
 include/linux/surface_aggregator/device.h | 1 -
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c
index 42ccd7f1c9b9c..118caa651bec4 100644
--- a/drivers/platform/surface/aggregator/bus.c
+++ b/drivers/platform/surface/aggregator/bus.c
@@ -35,6 +35,8 @@ static struct attribute *ssam_device_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ssam_device);
 
+static const struct bus_type ssam_bus_type;
+
 static int ssam_device_uevent(const struct device *dev, struct kobj_uevent_env *env)
 {
 	const struct ssam_device *sdev = to_ssam_device(dev);
@@ -329,13 +331,12 @@ static void ssam_bus_remove(struct device *dev)
 		sdrv->remove(to_ssam_device(dev));
 }
 
-struct bus_type ssam_bus_type = {
+static const struct bus_type ssam_bus_type = {
 	.name   = "surface_aggregator",
 	.match  = ssam_bus_match,
 	.probe  = ssam_bus_probe,
 	.remove = ssam_bus_remove,
 };
-EXPORT_SYMBOL_GPL(ssam_bus_type);
 
 /**
  * __ssam_device_driver_register() - Register a SSAM client device driver.
diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h
index 42b249b4c24b1..8cd8c38cf3f30 100644
--- a/include/linux/surface_aggregator/device.h
+++ b/include/linux/surface_aggregator/device.h
@@ -193,7 +193,6 @@ struct ssam_device_driver {
 
 #ifdef CONFIG_SURFACE_AGGREGATOR_BUS
 
-extern struct bus_type ssam_bus_type;
 extern const struct device_type ssam_device_type;
 
 /**
-- 
GitLab


From d3da61ea9776d3c09c7284c5e1b77e6f78ba308a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 21 Dec 2023 16:09:21 +0200
Subject: [PATCH 2199/4076] pvpanic: Kill duplicate PCI_VENDOR_ID_REDHAT
 definition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PCI_VENDOR_ID_REDHAT is already defined in pci_ids.h. Kill the dup.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20231221140921.2760432-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/pvpanic/pvpanic-pci.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/misc/pvpanic/pvpanic-pci.c b/drivers/misc/pvpanic/pvpanic-pci.c
index 0b2ae3423f07e..9ad20e82785bc 100644
--- a/drivers/misc/pvpanic/pvpanic-pci.c
+++ b/drivers/misc/pvpanic/pvpanic-pci.c
@@ -12,7 +12,6 @@
 
 #include "pvpanic.h"
 
-#define PCI_VENDOR_ID_REDHAT             0x1b36
 #define PCI_DEVICE_ID_REDHAT_PVPANIC     0x0011
 
 MODULE_AUTHOR("Mihai Carabas <mihai.carabas@oracle.com>");
-- 
GitLab


From b1b9f7a494400c0c39f8cd83de3aaa6111c55087 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Dec 2023 19:34:02 +0100
Subject: [PATCH 2200/4076] misc: lis3lv02d_i2c: Add missing setting of the
 reg_ctrl callback

The lis3lv02d_i2c driver was missing a line to set the lis3_dev's
reg_ctrl callback.

lis3_reg_ctrl(on) is called from the init callback, but due to
the missing reg_ctrl callback the regulators where never turned off
again leading to the following oops/backtrace when detaching the driver:

[   82.313527] ------------[ cut here ]------------
[   82.313546] WARNING: CPU: 1 PID: 1724 at drivers/regulator/core.c:2396 _regulator_put+0x219/0x230
...
[   82.313695] RIP: 0010:_regulator_put+0x219/0x230
...
[   82.314767] Call Trace:
[   82.314770]  <TASK>
[   82.314772]  ? _regulator_put+0x219/0x230
[   82.314777]  ? __warn+0x81/0x170
[   82.314784]  ? _regulator_put+0x219/0x230
[   82.314791]  ? report_bug+0x18d/0x1c0
[   82.314801]  ? handle_bug+0x3c/0x80
[   82.314806]  ? exc_invalid_op+0x13/0x60
[   82.314812]  ? asm_exc_invalid_op+0x16/0x20
[   82.314845]  ? _regulator_put+0x219/0x230
[   82.314857]  regulator_bulk_free+0x39/0x60
[   82.314865]  i2c_device_remove+0x22/0xb0

Add the missing setting of the callback so that the regulators
properly get turned off again when not used.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20231224183402.95640-1-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/lis3lv02d/lis3lv02d_i2c.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
index 3882e97e96a70..c6eb27d46cb06 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
+++ b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
@@ -150,6 +150,7 @@ static int lis3lv02d_i2c_probe(struct i2c_client *client)
 	lis3_dev.init	  = lis3_i2c_init;
 	lis3_dev.read	  = lis3_i2c_read;
 	lis3_dev.write	  = lis3_i2c_write;
+	lis3_dev.reg_ctrl = lis3_reg_ctrl;
 	lis3_dev.irq	  = client->irq;
 	lis3_dev.ac	  = lis3lv02d_axis_map;
 	lis3_dev.pm_dev	  = &client->dev;
-- 
GitLab


From 2765149273f4b52beb07256c3e4686c065a5f8a8 Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Thu, 4 Jan 2024 09:45:52 -0600
Subject: [PATCH 2201/4076] mux: mmio: use reg property when parent device is
 not a syscon

The DT binding for the reg-mux compatible states it can be used when the
"parent device of mux controller is not syscon device". It also allows
for a reg property. When the reg property is provided, use that to
identify the address space for this mux. If not provided fallback to
using the parent device as a regmap provider.

While here use dev_err_probe() in the error path to prevent printing
a message on probe defer which now can happen in extra ways.

Signed-off-by: Andrew Davis <afd@ti.com>
Reviewed-by: Nishanth Menon <nm@ti.com>
Acked-by: Peter Rosin <peda@axentia.se>
Link: https://lore.kernel.org/r/20240104154552.17852-1-afd@ti.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/mux/mmio.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/mux/mmio.c b/drivers/mux/mmio.c
index fd1d121a584ba..30a952c34365f 100644
--- a/drivers/mux/mmio.c
+++ b/drivers/mux/mmio.c
@@ -44,15 +44,20 @@ static int mux_mmio_probe(struct platform_device *pdev)
 	int ret;
 	int i;
 
-	if (of_device_is_compatible(np, "mmio-mux"))
+	if (of_device_is_compatible(np, "mmio-mux")) {
 		regmap = syscon_node_to_regmap(np->parent);
-	else
-		regmap = dev_get_regmap(dev->parent, NULL) ?: ERR_PTR(-ENODEV);
-	if (IS_ERR(regmap)) {
-		ret = PTR_ERR(regmap);
-		dev_err(dev, "failed to get regmap: %d\n", ret);
-		return ret;
+	} else {
+		regmap = device_node_to_regmap(np);
+		/* Fallback to checking the parent node on "real" errors. */
+		if (IS_ERR(regmap) && regmap != ERR_PTR(-EPROBE_DEFER)) {
+			regmap = dev_get_regmap(dev->parent, NULL);
+			if (!regmap)
+				regmap = ERR_PTR(-ENODEV);
+		}
 	}
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap),
+				     "failed to get regmap\n");
 
 	ret = of_property_count_u32_elems(np, "mux-reg-masks");
 	if (ret == 0 || ret % 2)
-- 
GitLab


From 927e11300d8ef19873926d67e1f5662b1b85a7c7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:25 +0100
Subject: [PATCH 2202/4076] firmware: arm_scmi: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/86165c8ccd0bb47000a29e711102795b36c8df41.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/arm_scmi/driver.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 09371f40d61f4..5355fe34fff52 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -2820,7 +2820,7 @@ clear_ida:
 	return ret;
 }
 
-static int scmi_remove(struct platform_device *pdev)
+static void scmi_remove(struct platform_device *pdev)
 {
 	int id;
 	struct scmi_info *info = platform_get_drvdata(pdev);
@@ -2854,8 +2854,6 @@ static int scmi_remove(struct platform_device *pdev)
 	scmi_cleanup_txrx_channels(info);
 
 	ida_free(&scmi_id, info->id);
-
-	return 0;
 }
 
 static ssize_t protocol_version_show(struct device *dev,
@@ -2933,7 +2931,7 @@ static struct platform_driver scmi_driver = {
 		   .dev_groups = versions_groups,
 		   },
 	.probe = scmi_probe,
-	.remove = scmi_remove,
+	.remove_new = scmi_remove,
 };
 
 /**
-- 
GitLab


From 259566503782eafc3c1eb4201347e32af2741e9f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:26 +0100
Subject: [PATCH 2203/4076] firmware: arm_scpi: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/e7b4bc389949c3613a358bd8e57d70d7acd5552b.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/arm_scpi.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
index 3f123f592cb4c..94a6b4e667de1 100644
--- a/drivers/firmware/arm_scpi.c
+++ b/drivers/firmware/arm_scpi.c
@@ -863,7 +863,7 @@ static void scpi_free_channels(void *data)
 		mbox_free_channel(info->channels[i].chan);
 }
 
-static int scpi_remove(struct platform_device *pdev)
+static void scpi_remove(struct platform_device *pdev)
 {
 	int i;
 	struct scpi_drvinfo *info = platform_get_drvdata(pdev);
@@ -874,8 +874,6 @@ static int scpi_remove(struct platform_device *pdev)
 		kfree(info->dvfs[i]->opps);
 		kfree(info->dvfs[i]);
 	}
-
-	return 0;
 }
 
 #define MAX_SCPI_XFERS		10
@@ -1048,7 +1046,7 @@ static struct platform_driver scpi_driver = {
 		.dev_groups = versions_groups,
 	},
 	.probe = scpi_probe,
-	.remove = scpi_remove,
+	.remove_new = scpi_remove,
 };
 module_platform_driver(scpi_driver);
 
-- 
GitLab


From f69583d32fcb23943271e4a1bb7265ac9af9b3e0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:27 +0100
Subject: [PATCH 2204/4076] firmware: coreboot_table: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/d323e4f24bfab3ac1480933deb51e7c5cb025b09.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/google/coreboot_table.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c
index 33ae94745aef9..2a4469bf1b81c 100644
--- a/drivers/firmware/google/coreboot_table.c
+++ b/drivers/firmware/google/coreboot_table.c
@@ -176,10 +176,9 @@ static int __cb_dev_unregister(struct device *dev, void *dummy)
 	return 0;
 }
 
-static int coreboot_table_remove(struct platform_device *pdev)
+static void coreboot_table_remove(struct platform_device *pdev)
 {
 	bus_for_each_dev(&coreboot_bus_type, NULL, NULL, __cb_dev_unregister);
-	return 0;
 }
 
 #ifdef CONFIG_ACPI
@@ -201,7 +200,7 @@ MODULE_DEVICE_TABLE(of, coreboot_of_match);
 
 static struct platform_driver coreboot_table_driver = {
 	.probe = coreboot_table_probe,
-	.remove = coreboot_table_remove,
+	.remove_new = coreboot_table_remove,
 	.driver = {
 		.name = "coreboot_table",
 		.acpi_match_table = ACPI_PTR(cros_coreboot_acpi_match),
-- 
GitLab


From 303cbf2a30cccfd600aa32f8a93067196d4d926d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:28 +0100
Subject: [PATCH 2205/4076] firmware: imx-dsp: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/f4cc1ffe30b837d5eab96f2924f51999dfa9f671.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/imx/imx-dsp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/imx/imx-dsp.c b/drivers/firmware/imx/imx-dsp.c
index a48a58e0c61f8..01c8ef14eaec3 100644
--- a/drivers/firmware/imx/imx-dsp.c
+++ b/drivers/firmware/imx/imx-dsp.c
@@ -160,7 +160,7 @@ static int imx_dsp_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int imx_dsp_remove(struct platform_device *pdev)
+static void imx_dsp_remove(struct platform_device *pdev)
 {
 	struct imx_dsp_chan *dsp_chan;
 	struct imx_dsp_ipc *dsp_ipc;
@@ -173,8 +173,6 @@ static int imx_dsp_remove(struct platform_device *pdev)
 		mbox_free_channel(dsp_chan->ch);
 		kfree(dsp_chan->name);
 	}
-
-	return 0;
 }
 
 static struct platform_driver imx_dsp_driver = {
@@ -182,7 +180,7 @@ static struct platform_driver imx_dsp_driver = {
 		.name = "imx-dsp",
 	},
 	.probe = imx_dsp_probe,
-	.remove = imx_dsp_remove,
+	.remove_new = imx_dsp_remove,
 };
 builtin_platform_driver(imx_dsp_driver);
 
-- 
GitLab


From ab45e1f40bab8d87ba59a8e41888f2792e530278 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:29 +0100
Subject: [PATCH 2206/4076] firmware: mtk-adsp-ipc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/e2ea8abb4c30190392a86cf05cecd722d0f0b493.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/mtk-adsp-ipc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/mtk-adsp-ipc.c b/drivers/firmware/mtk-adsp-ipc.c
index 85e94ddc7204d..a762302978de0 100644
--- a/drivers/firmware/mtk-adsp-ipc.c
+++ b/drivers/firmware/mtk-adsp-ipc.c
@@ -116,7 +116,7 @@ static int mtk_adsp_ipc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mtk_adsp_ipc_remove(struct platform_device *pdev)
+static void mtk_adsp_ipc_remove(struct platform_device *pdev)
 {
 	struct mtk_adsp_ipc *adsp_ipc = dev_get_drvdata(&pdev->dev);
 	struct mtk_adsp_chan *adsp_chan;
@@ -126,8 +126,6 @@ static int mtk_adsp_ipc_remove(struct platform_device *pdev)
 		adsp_chan = &adsp_ipc->chans[i];
 		mbox_free_channel(adsp_chan->ch);
 	}
-
-	return 0;
 }
 
 static struct platform_driver mtk_adsp_ipc_driver = {
@@ -135,7 +133,7 @@ static struct platform_driver mtk_adsp_ipc_driver = {
 		.name = "mtk-adsp-ipc",
 	},
 	.probe = mtk_adsp_ipc_probe,
-	.remove = mtk_adsp_ipc_remove,
+	.remove_new = mtk_adsp_ipc_remove,
 };
 builtin_platform_driver(mtk_adsp_ipc_driver);
 
-- 
GitLab


From 9eeec412265a185d1011d7b5da0baee9c3453e3e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:30 +0100
Subject: [PATCH 2207/4076] firmware: qemu_fw_cfg: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/8d7d86a24ea36985845c17b6da0933fedbf99ad8.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/qemu_fw_cfg.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 1448f61173b35..03da9a4354f88 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -731,7 +731,7 @@ err_sel:
 	return err;
 }
 
-static int fw_cfg_sysfs_remove(struct platform_device *pdev)
+static void fw_cfg_sysfs_remove(struct platform_device *pdev)
 {
 	pr_debug("fw_cfg: unloading.\n");
 	fw_cfg_sysfs_cache_cleanup();
@@ -739,7 +739,6 @@ static int fw_cfg_sysfs_remove(struct platform_device *pdev)
 	fw_cfg_io_cleanup();
 	fw_cfg_kset_unregister_recursive(fw_cfg_fname_kset);
 	fw_cfg_kobj_cleanup(fw_cfg_sel_ko);
-	return 0;
 }
 
 static const struct of_device_id fw_cfg_sysfs_mmio_match[] = {
@@ -758,7 +757,7 @@ MODULE_DEVICE_TABLE(acpi, fw_cfg_sysfs_acpi_match);
 
 static struct platform_driver fw_cfg_sysfs_driver = {
 	.probe = fw_cfg_sysfs_probe,
-	.remove = fw_cfg_sysfs_remove,
+	.remove_new = fw_cfg_sysfs_remove,
 	.driver = {
 		.name = "fw_cfg",
 		.of_match_table = fw_cfg_sysfs_mmio_match,
-- 
GitLab


From ffc3c929507d86fd8056887035f163b5341740e9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:31 +0100
Subject: [PATCH 2208/4076] firmware: raspberrypi: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/5df31ef3c069f45634631c9c639bbb60ab1d4798.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/raspberrypi.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c
index 4cd290a60fbaa..322aada20f742 100644
--- a/drivers/firmware/raspberrypi.c
+++ b/drivers/firmware/raspberrypi.c
@@ -317,7 +317,7 @@ static void rpi_firmware_shutdown(struct platform_device *pdev)
 	rpi_firmware_property(fw, RPI_FIRMWARE_NOTIFY_REBOOT, NULL, 0);
 }
 
-static int rpi_firmware_remove(struct platform_device *pdev)
+static void rpi_firmware_remove(struct platform_device *pdev)
 {
 	struct rpi_firmware *fw = platform_get_drvdata(pdev);
 
@@ -327,8 +327,6 @@ static int rpi_firmware_remove(struct platform_device *pdev)
 	rpi_clk = NULL;
 
 	rpi_firmware_put(fw);
-
-	return 0;
 }
 
 static const struct of_device_id rpi_firmware_of_match[] = {
@@ -406,7 +404,7 @@ static struct platform_driver rpi_firmware_driver = {
 	},
 	.probe		= rpi_firmware_probe,
 	.shutdown	= rpi_firmware_shutdown,
-	.remove		= rpi_firmware_remove,
+	.remove_new	= rpi_firmware_remove,
 };
 module_platform_driver(rpi_firmware_driver);
 
-- 
GitLab


From 6ac63d0bb5762566a8cd8ebde0b129dc80a007d8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:32 +0100
Subject: [PATCH 2209/4076] firmware: stratix10-rsu: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Dinh Nguyen <dinguyen@kernel.org>
Link: https://lore.kernel.org/r/06df45c697a747cb6543800a4613db6e1f5462b4.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/stratix10-rsu.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/stratix10-rsu.c b/drivers/firmware/stratix10-rsu.c
index 4f7a7abada48a..e20cee9c2d320 100644
--- a/drivers/firmware/stratix10-rsu.c
+++ b/drivers/firmware/stratix10-rsu.c
@@ -793,17 +793,16 @@ static int stratix10_rsu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int stratix10_rsu_remove(struct platform_device *pdev)
+static void stratix10_rsu_remove(struct platform_device *pdev)
 {
 	struct stratix10_rsu_priv *priv = platform_get_drvdata(pdev);
 
 	stratix10_svc_free_channel(priv->chan);
-	return 0;
 }
 
 static struct platform_driver stratix10_rsu_driver = {
 	.probe = stratix10_rsu_probe,
-	.remove = stratix10_rsu_remove,
+	.remove_new = stratix10_rsu_remove,
 	.driver = {
 		.name = "stratix10-rsu",
 		.dev_groups = rsu_groups,
-- 
GitLab


From 51e24bac2fb8a12e70e2195b3101e5777b3e0965 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:33 +0100
Subject: [PATCH 2210/4076] firmware: stratix10-svc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Dinh Nguyen <dinguyen@kernel.org>
Link: https://lore.kernel.org/r/e574041cdce2e4e69f729dfa726a6d090762cff9.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/stratix10-svc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index c693da60e9a97..528f37417aea4 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -1251,7 +1251,7 @@ err_destroy_pool:
 	return ret;
 }
 
-static int stratix10_svc_drv_remove(struct platform_device *pdev)
+static void stratix10_svc_drv_remove(struct platform_device *pdev)
 {
 	struct stratix10_svc *svc = dev_get_drvdata(&pdev->dev);
 	struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
@@ -1267,13 +1267,11 @@ static int stratix10_svc_drv_remove(struct platform_device *pdev)
 	if (ctrl->genpool)
 		gen_pool_destroy(ctrl->genpool);
 	list_del(&ctrl->node);
-
-	return 0;
 }
 
 static struct platform_driver stratix10_svc_driver = {
 	.probe = stratix10_svc_drv_probe,
-	.remove = stratix10_svc_drv_remove,
+	.remove_new = stratix10_svc_drv_remove,
 	.driver = {
 		.name = "stratix10-svc",
 		.of_match_table = stratix10_svc_drv_match,
-- 
GitLab


From 31fd8f1ddd2857070c32ca63bbe53262768f432e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:34 +0100
Subject: [PATCH 2211/4076] firmware: turris-mox-rwtm: Convert to platform
 remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Marek Behún <kabel@kernel.org>
Link: https://lore.kernel.org/r/9074d1ad2e889425991fecad664781ae27b2418a.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/turris-mox-rwtm.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c
index 2de0fb139ce17..31d962cdd6eb2 100644
--- a/drivers/firmware/turris-mox-rwtm.c
+++ b/drivers/firmware/turris-mox-rwtm.c
@@ -554,7 +554,7 @@ put_kobj:
 	return ret;
 }
 
-static int turris_mox_rwtm_remove(struct platform_device *pdev)
+static void turris_mox_rwtm_remove(struct platform_device *pdev)
 {
 	struct mox_rwtm *rwtm = platform_get_drvdata(pdev);
 
@@ -562,8 +562,6 @@ static int turris_mox_rwtm_remove(struct platform_device *pdev)
 	sysfs_remove_files(rwtm_to_kobj(rwtm), mox_rwtm_attrs);
 	kobject_put(rwtm_to_kobj(rwtm));
 	mbox_free_channel(rwtm->mbox);
-
-	return 0;
 }
 
 static const struct of_device_id turris_mox_rwtm_match[] = {
@@ -576,7 +574,7 @@ MODULE_DEVICE_TABLE(of, turris_mox_rwtm_match);
 
 static struct platform_driver turris_mox_rwtm_driver = {
 	.probe	= turris_mox_rwtm_probe,
-	.remove	= turris_mox_rwtm_remove,
+	.remove_new = turris_mox_rwtm_remove,
 	.driver	= {
 		.name		= DRIVER_NAME,
 		.of_match_table	= turris_mox_rwtm_match,
-- 
GitLab


From 408201eb2e386c8d1f3e4bcc46fee8f4c869b8a2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 17:26:35 +0100
Subject: [PATCH 2212/4076] firmware: zynqmp: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/b5a82472a6d61608c2cd7728ca364f6c88a821c3.1703693980.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index a55dfd9bae6bd..73cae6ef83ec7 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -1929,7 +1929,7 @@ static int zynqmp_firmware_probe(struct platform_device *pdev)
 	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
-static int zynqmp_firmware_remove(struct platform_device *pdev)
+static void zynqmp_firmware_remove(struct platform_device *pdev)
 {
 	struct pm_api_feature_data *feature_data;
 	struct hlist_node *tmp;
@@ -1944,8 +1944,6 @@ static int zynqmp_firmware_remove(struct platform_device *pdev)
 	}
 
 	platform_device_unregister(em_dev);
-
-	return 0;
 }
 
 static const struct of_device_id zynqmp_firmware_of_match[] = {
@@ -1962,6 +1960,6 @@ static struct platform_driver zynqmp_firmware_driver = {
 		.dev_groups = zynqmp_firmware_groups,
 	},
 	.probe = zynqmp_firmware_probe,
-	.remove = zynqmp_firmware_remove,
+	.remove_new = zynqmp_firmware_remove,
 };
 module_platform_driver(zynqmp_firmware_driver);
-- 
GitLab


From 4f3f263df57ff2bb37174ced271b7364238833d0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20Nyffenegger?= <mail@renenyffenegger.ch>
Date: Sun, 17 Dec 2023 09:27:19 +0100
Subject: [PATCH 2213/4076] scripts/tags.sh: Update comment (addition of gtags)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit f4ed1009fcea ("kbuild: add GNU GLOBAL tags generation") added
support for the GNU Global source tagging system. However, this addition
was not reflected in the script's header comment.

Fixes: f4ed1009fcea ("kbuild: add GNU GLOBAL tags generation")
Signed-off-by: René Nyffenegger <mail@renenyffenegger.ch>
Link: https://lore.kernel.org/r/20231217082719.4747-1-mail@renenyffenegger.ch
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 scripts/tags.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/tags.sh b/scripts/tags.sh
index a70d43723146d..cb96961349aaf 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -3,7 +3,7 @@
 # Generate tags or cscope files
 # Usage tags.sh <mode>
 #
-# mode may be any of: tags, TAGS, cscope
+# mode may be any of: tags, gtags, TAGS, cscope
 #
 # Uses the following environment variables:
 # SUBARCH, SRCARCH, srctree
-- 
GitLab


From f9fefa985d2e96db81954ae3b1feb09d69357f28 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@gmail.com>
Date: Fri, 29 Dec 2023 03:06:51 +0000
Subject: [PATCH 2214/4076] scripts/tags.sh: use more portable -path instead of
 -wholename

According to the manual, -path is more portable than -wholename. Also
for consistency, let's use -path here.

Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
CC: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
CC: WANG Cong <xiyou.wangcong@gmail.com>
CC: Michal Marek <mmarek@suse.cz>
Link: https://lore.kernel.org/r/20231229030654.17474-1-richard.weiyang@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 scripts/tags.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/tags.sh b/scripts/tags.sh
index cb96961349aaf..be7970b8b88ad 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -50,7 +50,7 @@ fi
 find_arch_sources()
 {
 	for i in $archincludedir; do
-		prune="$prune -wholename $i -prune -o"
+		prune="$prune ( -path $i ) -prune -o"
 	done
 	find ${tree}arch/$1 $ignore $prune -name "$2" -not -type l -print;
 }
-- 
GitLab


From 0aedf7a2dc5d23211399813bdfce5a46e836d5d7 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@gmail.com>
Date: Fri, 29 Dec 2023 03:06:52 +0000
Subject: [PATCH 2215/4076] scripts/tags.sh: add local annotation

Commit 'f81b1be40c44 tags: include headers before source files'
introduce two local variables.

Let's add local annotation to make it obvious.

Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Link: https://lore.kernel.org/r/20231229030654.17474-2-richard.weiyang@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 scripts/tags.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/tags.sh b/scripts/tags.sh
index be7970b8b88ad..c088bf4f9aa17 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -50,7 +50,7 @@ fi
 find_arch_sources()
 {
 	for i in $archincludedir; do
-		prune="$prune ( -path $i ) -prune -o"
+		local prune="$prune ( -path $i ) -prune -o"
 	done
 	find ${tree}arch/$1 $ignore $prune -name "$2" -not -type l -print;
 }
@@ -58,7 +58,7 @@ find_arch_sources()
 # find sources in arch/$1/include
 find_arch_include_sources()
 {
-	include=$(find ${tree}arch/$1/ -name include -type d -print);
+	local include=$(find ${tree}arch/$1/ -name include -type d -print);
 	if [ -n "$include" ]; then
 		archincludedir="$archincludedir $include"
 		find $include $ignore -name "$2" -not -type l -print;
-- 
GitLab


From d70a091fb412fd0410b882c0b45072e547beb070 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@gmail.com>
Date: Fri, 29 Dec 2023 03:06:53 +0000
Subject: [PATCH 2216/4076] scripts/tags.sh: use -n to test archinclude

In bash, "! -z" is equivalent to "-n", which seems to be more intuitive.

Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
CC: Sam Ravnborg <sam@ravnborg.org>
Link: https://lore.kernel.org/r/20231229030654.17474-3-richard.weiyang@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 scripts/tags.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/tags.sh b/scripts/tags.sh
index c088bf4f9aa17..f73cf3f39638c 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -89,7 +89,7 @@ find_sources()
 all_sources()
 {
 	find_arch_include_sources ${SRCARCH} '*.[chS]'
-	if [ ! -z "$archinclude" ]; then
+	if [ -n "$archinclude" ]; then
 		find_arch_include_sources $archinclude '*.[chS]'
 	fi
 	find_include_sources '*.[chS]'
-- 
GitLab


From 2ad3cc0582003f1fad74ad4c06b85613746fae47 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@gmail.com>
Date: Fri, 29 Dec 2023 03:06:54 +0000
Subject: [PATCH 2217/4076] scripts/tags.sh: remove find_sources

After commit '4f628248a578 kbuild: reintroduce ALLSOURCE_ARCHS support for
tags/cscope', find_sources only invoke find_arch_sources.

Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
CC: Jike Song <albcamus@gmail.com>
Link: https://lore.kernel.org/r/20231229030654.17474-4-richard.weiyang@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 scripts/tags.sh | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/scripts/tags.sh b/scripts/tags.sh
index f73cf3f39638c..191e0461d6d5b 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -81,11 +81,6 @@ find_other_sources()
 	       -name "$1" -not -type l -print;
 }
 
-find_sources()
-{
-	find_arch_sources $1 "$2"
-}
-
 all_sources()
 {
 	find_arch_include_sources ${SRCARCH} '*.[chS]'
@@ -95,7 +90,7 @@ all_sources()
 	find_include_sources '*.[chS]'
 	for arch in $ALLSOURCE_ARCHS
 	do
-		find_sources $arch '*.[chS]'
+		find_arch_sources $arch '*.[chS]'
 	done
 	find_other_sources '*.[chS]'
 }
@@ -125,7 +120,7 @@ all_kconfigs()
 	find ${tree}arch/ -maxdepth 1 $ignore \
 	       -name "Kconfig*" -not -type l -print;
 	for arch in $ALLSOURCE_ARCHS; do
-		find_sources $arch 'Kconfig*'
+		find_arch_sources $arch 'Kconfig*'
 	done
 	find_other_sources 'Kconfig*'
 }
-- 
GitLab


From 0c4b2255b7afbcc80f4efcc8f67425162f49c263 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Mon, 18 Dec 2023 21:50:24 -0800
Subject: [PATCH 2218/4076] firmware: xilinx: Export function to use in other
 module

Export zynqmp_pm_get_family_info() to access and find family information
in other module.

Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231219055025.27570-2-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 3 ++-
 include/linux/firmware/xlnx-zynqmp.h | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 73cae6ef83ec7..79789f0563f6a 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -463,7 +463,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_chipid);
  *
  * Return: Returns status, either success or error+reason
  */
-static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
+int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 {
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	u32 idcode;
@@ -488,6 +488,7 @@ static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(zynqmp_pm_get_family_info);
 
 /**
  * zynqmp_pm_get_trustzone_version() - Get secure trustzone firmware version
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 1478f691cc10e..06f4e6eaf13e5 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -524,6 +524,7 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...);
 #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE)
 int zynqmp_pm_get_api_version(u32 *version);
 int zynqmp_pm_get_chipid(u32 *idcode, u32 *version);
+int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily);
 int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out);
 int zynqmp_pm_clock_enable(u32 clock_id);
 int zynqmp_pm_clock_disable(u32 clock_id);
@@ -602,6 +603,11 @@ static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version)
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata,
 				       u32 *out)
 {
-- 
GitLab


From 97d62760e441af9ed393e127a46172f9534b5808 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Mon, 18 Dec 2023 21:50:25 -0800
Subject: [PATCH 2219/4076] drivers: soc: xilinx: add check for platform

Some error event IDs for Versal and Versal NET are different.
Both the platforms should access their respective error event
IDs so use sub_family_code to check for platform and check
error IDs for respective platforms. The family code is passed
via platform data to avoid platform detection again.
Platform data is setup when even driver is registered.

Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231219055025.27570-3-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/edac/versal_edac.c              |  4 ++--
 drivers/soc/xilinx/xlnx_event_manager.c | 25 ++++++++++++++++++++-----
 include/linux/firmware/xlnx-zynqmp.h    | 16 ++++++++++++----
 3 files changed, 34 insertions(+), 11 deletions(-)

diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c
index 87e730dfefa08..116ed9b375de7 100644
--- a/drivers/edac/versal_edac.c
+++ b/drivers/edac/versal_edac.c
@@ -1005,7 +1005,7 @@ static int mc_probe(struct platform_device *pdev)
 		goto free_edac_mc;
 	}
 
-	rc = xlnx_register_event(PM_NOTIFY_CB, EVENT_ERROR_PMC_ERR1,
+	rc = xlnx_register_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1,
 				 XPM_EVENT_ERROR_MASK_DDRMC_CR | XPM_EVENT_ERROR_MASK_DDRMC_NCR |
 				 XPM_EVENT_ERROR_MASK_NOC_CR | XPM_EVENT_ERROR_MASK_NOC_NCR,
 				 false, err_callback, mci);
@@ -1042,7 +1042,7 @@ static int mc_remove(struct platform_device *pdev)
 	debugfs_remove_recursive(priv->debugfs);
 #endif
 
-	xlnx_unregister_event(PM_NOTIFY_CB, EVENT_ERROR_PMC_ERR1,
+	xlnx_unregister_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1,
 			      XPM_EVENT_ERROR_MASK_DDRMC_CR |
 			      XPM_EVENT_ERROR_MASK_NOC_CR |
 			      XPM_EVENT_ERROR_MASK_NOC_NCR |
diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index 27a8d89a0a091..2ce4c8e01f57c 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -77,11 +77,26 @@ struct registered_event_data {
 
 static bool xlnx_is_error_event(const u32 node_id)
 {
-	if (node_id == EVENT_ERROR_PMC_ERR1 ||
-	    node_id == EVENT_ERROR_PMC_ERR2 ||
-	    node_id == EVENT_ERROR_PSM_ERR1 ||
-	    node_id == EVENT_ERROR_PSM_ERR2)
-		return true;
+	u32 pm_family_code, pm_sub_family_code;
+
+	zynqmp_pm_get_family_info(&pm_family_code, &pm_sub_family_code);
+
+	if (pm_sub_family_code == VERSAL_SUB_FAMILY_CODE) {
+		if (node_id == VERSAL_EVENT_ERROR_PMC_ERR1 ||
+		    node_id == VERSAL_EVENT_ERROR_PMC_ERR2 ||
+		    node_id == VERSAL_EVENT_ERROR_PSM_ERR1 ||
+		    node_id == VERSAL_EVENT_ERROR_PSM_ERR2)
+			return true;
+	} else {
+		if (node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR1 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR2 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR3 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR1 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR2 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR3 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR4)
+			return true;
+	}
 
 	return false;
 }
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 06f4e6eaf13e5..9a7e527392512 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -95,10 +95,18 @@
 /*
  * Node IDs for the Error Events.
  */
-#define EVENT_ERROR_PMC_ERR1	(0x28100000U)
-#define EVENT_ERROR_PMC_ERR2	(0x28104000U)
-#define EVENT_ERROR_PSM_ERR1	(0x28108000U)
-#define EVENT_ERROR_PSM_ERR2	(0x2810C000U)
+#define VERSAL_EVENT_ERROR_PMC_ERR1	(0x28100000U)
+#define VERSAL_EVENT_ERROR_PMC_ERR2	(0x28104000U)
+#define VERSAL_EVENT_ERROR_PSM_ERR1	(0x28108000U)
+#define VERSAL_EVENT_ERROR_PSM_ERR2	(0x2810C000U)
+
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR1	(0x28100000U)
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR2	(0x28104000U)
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR3	(0x28108000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR1	(0x2810C000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR2	(0x28110000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR3	(0x28114000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR4	(0x28118000U)
 
 /* ZynqMP SD tap delay tuning */
 #define SD_ITAPDLY	0xFF180314
-- 
GitLab


From 0c9ae0b8605078eafc3bea053cc78791e97ba2e2 Mon Sep 17 00:00:00 2001
From: Guanghui Feng <guanghuifeng@linux.alibaba.com>
Date: Thu, 21 Dec 2023 17:57:43 +0800
Subject: [PATCH 2220/4076] uio: Fix use-after-free in uio_open

core-1				core-2
-------------------------------------------------------
uio_unregister_device		uio_open
				idev = idr_find()
device_unregister(&idev->dev)
put_device(&idev->dev)
uio_device_release
				get_device(&idev->dev)
kfree(idev)
uio_free_minor(minor)
				uio_release
				put_device(&idev->dev)
				kfree(idev)
-------------------------------------------------------

In the core-1 uio_unregister_device(), the device_unregister will kfree
idev when the idev->dev kobject ref is 1. But after core-1
device_unregister, put_device and before doing kfree, the core-2 may
get_device. Then:
1. After core-1 kfree idev, the core-2 will do use-after-free for idev.
2. When core-2 do uio_release and put_device, the idev will be double
   freed.

To address this issue, we can get idev atomic & inc idev reference with
minor_lock.

Fixes: 57c5f4df0a5a ("uio: fix crash after the device is unregistered")
Cc: stable <stable@kernel.org>
Signed-off-by: Guanghui Feng <guanghuifeng@linux.alibaba.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Link: https://lore.kernel.org/r/1703152663-59949-1-git-send-email-guanghuifeng@linux.alibaba.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/uio/uio.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 62082d64ece00..2d572f6c8ec83 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -466,13 +466,13 @@ static int uio_open(struct inode *inode, struct file *filep)
 
 	mutex_lock(&minor_lock);
 	idev = idr_find(&uio_idr, iminor(inode));
-	mutex_unlock(&minor_lock);
 	if (!idev) {
 		ret = -ENODEV;
+		mutex_unlock(&minor_lock);
 		goto out;
 	}
-
 	get_device(&idev->dev);
+	mutex_unlock(&minor_lock);
 
 	if (!try_module_get(idev->owner)) {
 		ret = -ENODEV;
@@ -1064,9 +1064,8 @@ void uio_unregister_device(struct uio_info *info)
 	wake_up_interruptible(&idev->wait);
 	kill_fasync(&idev->async_queue, SIGIO, POLL_HUP);
 
-	device_unregister(&idev->dev);
-
 	uio_free_minor(minor);
+	device_unregister(&idev->dev);
 
 	return;
 }
-- 
GitLab


From 93ec4a3b76404bce01bd5c9032bef5df6feb1d62 Mon Sep 17 00:00:00 2001
From: Jing Xia <jing.xia@unisoc.com>
Date: Wed, 20 Dec 2023 10:46:03 +0800
Subject: [PATCH 2221/4076] class: fix use-after-free in class_register()

The lock_class_key is still registered and can be found in
lock_keys_hash hlist after subsys_private is freed in error
handler path.A task who iterate over the lock_keys_hash
later may cause use-after-free.So fix that up and unregister
the lock_class_key before kfree(cp).

On our platform, a driver fails to kset_register because of
creating duplicate filename '/class/xxx'.With Kasan enabled,
it prints a invalid-access bug report.

KASAN bug report:

BUG: KASAN: invalid-access in lockdep_register_key+0x19c/0x1bc
Write of size 8 at addr 15ffff808b8c0368 by task modprobe/252
Pointer tag: [15], memory tag: [fe]

CPU: 7 PID: 252 Comm: modprobe Tainted: G        W
 6.6.0-mainline-maybe-dirty #1

Call trace:
dump_backtrace+0x1b0/0x1e4
show_stack+0x2c/0x40
dump_stack_lvl+0xac/0xe0
print_report+0x18c/0x4d8
kasan_report+0xe8/0x148
__hwasan_store8_noabort+0x88/0x98
lockdep_register_key+0x19c/0x1bc
class_register+0x94/0x1ec
init_module+0xbc/0xf48 [rfkill]
do_one_initcall+0x17c/0x72c
do_init_module+0x19c/0x3f8
...
Memory state around the buggy address:
ffffff808b8c0100: 8a 8a 8a 8a 8a 8a 8a 8a 8a 8a 8a 8a 8a 8a 8a 8a
ffffff808b8c0200: 8a 8a 8a 8a 8a 8a 8a 8a fe fe fe fe fe fe fe fe
>ffffff808b8c0300: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe
                                     ^
ffffff808b8c0400: 03 03 03 03 03 03 03 03 03 03 03 03 03 03 03 03

As CONFIG_KASAN_GENERIC is not set, Kasan reports invalid-access
not use-after-free here.In this case, modprobe is manipulating
the corrupted lock_keys_hash hlish where lock_class_key is already
freed before.

It's worth noting that this only can happen if lockdep is enabled,
which is not true for normal system.

Fixes: dcfbb67e48a2 ("driver core: class: use lock_class_key already present in struct subsys_private")
Cc: stable <stable@kernel.org>
Signed-off-by: Jing Xia <jing.xia@unisoc.com>
Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
Link: https://lore.kernel.org/r/20231220024603.186078-1-jing.xia@unisoc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/class.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/base/class.c b/drivers/base/class.c
index 7e78aee0fd6c3..7b38fdf8e1d78 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -213,6 +213,7 @@ int class_register(const struct class *cls)
 	return 0;
 
 err_out:
+	lockdep_unregister_key(key);
 	kfree(cp);
 	return error;
 }
-- 
GitLab


From c312828c37a72fe2d033a961c47c227b0767e9f8 Mon Sep 17 00:00:00 2001
From: Andrea Righi <andrea.righi@canonical.com>
Date: Fri, 29 Dec 2023 08:49:16 +0100
Subject: [PATCH 2222/4076] kernfs: convert kernfs_idr_lock to an irq safe raw
 spinlock

bpf_cgroup_from_id() is basically a wrapper to cgroup_get_from_id(),
that is relying on kernfs to determine the right cgroup associated to
the target id.

As a kfunc, it has the potential to be attached to any function through
BPF, particularly in contexts where certain locks are held.

However, kernfs is not using an irq safe spinlock for kernfs_idr_lock,
that means any kernfs function that is acquiring this lock can be
interrupted and potentially hit bpf_cgroup_from_id() in the process,
triggering a deadlock.

For example, it is really easy to trigger a lockdep splat between
kernfs_idr_lock and rq->_lock, attaching a small BPF program to
__set_cpus_allowed_ptr_locked() that just calls bpf_cgroup_from_id():

 =====================================================
 WARNING: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected
 6.7.0-rc7-virtme #5 Not tainted
 -----------------------------------------------------
 repro/131 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
 ffffffffb2dc4578 (kernfs_idr_lock){+.+.}-{2:2}, at: kernfs_find_and_get_node_by_id+0x1d/0x80

 and this task is already holding:
 ffff911cbecaf218 (&rq->__lock){-.-.}-{2:2}, at: task_rq_lock+0x50/0xc0
 which would create a new lock dependency:
  (&rq->__lock){-.-.}-{2:2} -> (kernfs_idr_lock){+.+.}-{2:2}

 but this new dependency connects a HARDIRQ-irq-safe lock:
  (&rq->__lock){-.-.}-{2:2}

 ... which became HARDIRQ-irq-safe at:
   lock_acquire+0xbf/0x2b0
   _raw_spin_lock_nested+0x2e/0x40
   scheduler_tick+0x5d/0x170
   update_process_times+0x9c/0xb0
   tick_periodic+0x27/0xe0
   tick_handle_periodic+0x24/0x70
   __sysvec_apic_timer_interrupt+0x64/0x1a0
   sysvec_apic_timer_interrupt+0x6f/0x80
   asm_sysvec_apic_timer_interrupt+0x1a/0x20
   memcpy+0xc/0x20
   arch_dup_task_struct+0x15/0x30
   copy_process+0x1ce/0x1eb0
   kernel_clone+0xac/0x390
   kernel_thread+0x6f/0xa0
   kthreadd+0x199/0x230
   ret_from_fork+0x31/0x50
   ret_from_fork_asm+0x1b/0x30

 to a HARDIRQ-irq-unsafe lock:
  (kernfs_idr_lock){+.+.}-{2:2}

 ... which became HARDIRQ-irq-unsafe at:
 ...
   lock_acquire+0xbf/0x2b0
   _raw_spin_lock+0x30/0x40
   __kernfs_new_node.isra.0+0x83/0x280
   kernfs_create_root+0xf6/0x1d0
   sysfs_init+0x1b/0x70
   mnt_init+0xd9/0x2a0
   vfs_caches_init+0xcf/0xe0
   start_kernel+0x58a/0x6a0
   x86_64_start_reservations+0x18/0x30
   x86_64_start_kernel+0xc5/0xe0
   secondary_startup_64_no_verify+0x178/0x17b

 other info that might help us debug this:

  Possible interrupt unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(kernfs_idr_lock);
                                local_irq_disable();
                                lock(&rq->__lock);
                                lock(kernfs_idr_lock);
   <Interrupt>
     lock(&rq->__lock);

  *** DEADLOCK ***

Prevent this deadlock condition converting kernfs_idr_lock to a raw irq
safe spinlock.

The performance impact of this change should be negligible and it also
helps to prevent similar deadlock conditions with any other subsystems
that may depend on kernfs.

Fixes: 332ea1f697be ("bpf: Add bpf_cgroup_from_id() kfunc")
Cc: stable <stable@kernel.org>
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20231229074916.53547-1-andrea.righi@canonical.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index bce1d7ac95caa..a62960fdf73f0 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -27,7 +27,7 @@ static DEFINE_RWLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
  */
 static DEFINE_SPINLOCK(kernfs_pr_cont_lock);
 static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by pr_cont_lock */
-static DEFINE_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
+static DEFINE_RAW_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
 
@@ -539,6 +539,7 @@ void kernfs_put(struct kernfs_node *kn)
 {
 	struct kernfs_node *parent;
 	struct kernfs_root *root;
+	unsigned long flags;
 
 	if (!kn || !atomic_dec_and_test(&kn->count))
 		return;
@@ -563,9 +564,9 @@ void kernfs_put(struct kernfs_node *kn)
 		simple_xattrs_free(&kn->iattr->xattrs, NULL);
 		kmem_cache_free(kernfs_iattrs_cache, kn->iattr);
 	}
-	spin_lock(&kernfs_idr_lock);
+	raw_spin_lock_irqsave(&kernfs_idr_lock, flags);
 	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
-	spin_unlock(&kernfs_idr_lock);
+	raw_spin_unlock_irqrestore(&kernfs_idr_lock, flags);
 	kmem_cache_free(kernfs_node_cache, kn);
 
 	kn = parent;
@@ -607,6 +608,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	struct kernfs_node *kn;
 	u32 id_highbits;
 	int ret;
+	unsigned long irqflags;
 
 	name = kstrdup_const(name, GFP_KERNEL);
 	if (!name)
@@ -617,13 +619,13 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 		goto err_out1;
 
 	idr_preload(GFP_KERNEL);
-	spin_lock(&kernfs_idr_lock);
+	raw_spin_lock_irqsave(&kernfs_idr_lock, irqflags);
 	ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
 	if (ret >= 0 && ret < root->last_id_lowbits)
 		root->id_highbits++;
 	id_highbits = root->id_highbits;
 	root->last_id_lowbits = ret;
-	spin_unlock(&kernfs_idr_lock);
+	raw_spin_unlock_irqrestore(&kernfs_idr_lock, irqflags);
 	idr_preload_end();
 	if (ret < 0)
 		goto err_out2;
@@ -659,9 +661,9 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	return kn;
 
  err_out3:
-	spin_lock(&kernfs_idr_lock);
+	raw_spin_lock_irqsave(&kernfs_idr_lock, irqflags);
 	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
-	spin_unlock(&kernfs_idr_lock);
+	raw_spin_unlock_irqrestore(&kernfs_idr_lock, irqflags);
  err_out2:
 	kmem_cache_free(kernfs_node_cache, kn);
  err_out1:
@@ -714,8 +716,9 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
 	struct kernfs_node *kn;
 	ino_t ino = kernfs_id_ino(id);
 	u32 gen = kernfs_id_gen(id);
+	unsigned long flags;
 
-	spin_lock(&kernfs_idr_lock);
+	raw_spin_lock_irqsave(&kernfs_idr_lock, flags);
 
 	kn = idr_find(&root->ino_idr, (u32)ino);
 	if (!kn)
@@ -739,10 +742,10 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
 	if (unlikely(!__kernfs_active(kn) || !atomic_inc_not_zero(&kn->count)))
 		goto err_unlock;
 
-	spin_unlock(&kernfs_idr_lock);
+	raw_spin_unlock_irqrestore(&kernfs_idr_lock, flags);
 	return kn;
 err_unlock:
-	spin_unlock(&kernfs_idr_lock);
+	raw_spin_unlock_irqrestore(&kernfs_idr_lock, flags);
 	return NULL;
 }
 
-- 
GitLab


From 38709af26c33e398c3292e96837ccfde41fd9e6b Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Date: Thu, 4 Jan 2024 16:39:49 +0200
Subject: [PATCH 2223/4076] drm/rockchip: vop2: Drop superfluous include

The rockchip_drm_fb.h header contains just a single function which is
not directly used by the VOP2 driver.  Drop the unnecessary include.

Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20240104143951.85219-1-cristian.ciocaltea@collabora.com
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 574103fc79f98..a3a03e9cfe137 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -35,7 +35,6 @@
 
 #include "rockchip_drm_drv.h"
 #include "rockchip_drm_gem.h"
-#include "rockchip_drm_fb.h"
 #include "rockchip_drm_vop2.h"
 #include "rockchip_rgb.h"
 
-- 
GitLab


From ad362fe07fecf0aba839ff2cc59a3617bd42c33f Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Thu, 4 Jan 2024 18:32:32 +0000
Subject: [PATCH 2224/4076] KVM: arm64: vgic-its: Avoid potential UAF in LPI
 translation cache

There is a potential UAF scenario in the case of an LPI translation
cache hit racing with an operation that invalidates the cache, such
as a DISCARD ITS command. The root of the problem is that
vgic_its_check_cache() does not elevate the refcount on the vgic_irq
before dropping the lock that serializes refcount changes.

Have vgic_its_check_cache() raise the refcount on the returned vgic_irq
and add the corresponding decrement after queueing the interrupt.

Cc: stable@vger.kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20240104183233.3560639-1-oliver.upton@linux.dev
---
 arch/arm64/kvm/vgic/vgic-its.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 2dad2d095160d..e2764d0ffa9f3 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -590,7 +590,11 @@ static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db,
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+
 	irq = __vgic_its_check_cache(dist, db, devid, eventid);
+	if (irq)
+		vgic_get_irq_kref(irq);
+
 	raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	return irq;
@@ -769,6 +773,7 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi)
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->pending_latch = true;
 	vgic_queue_irq_unlock(kvm, irq, flags);
+	vgic_put_irq(kvm, irq);
 
 	return 0;
 }
-- 
GitLab


From 040113fa32f27096f531c377001936e0d7964597 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 4 Jan 2024 16:42:20 +0000
Subject: [PATCH 2225/4076] KVM: arm64: Add missing memory barriers when
 switching to pKVM's hyp pgd

In commit f320bc742bc23 ("KVM: arm64: Prepare the creation of s1
mappings at EL2"), pKVM switches from a temporary host-provided
page-table to its own page-table at EL2. Since there is only a single
TTBR for the nVHE hypervisor, this involves disabling and re-enabling
the MMU in __pkvm_init_switch_pgd().

Unfortunately, the memory barriers here are not quite correct.
Specifically:

  - A DSB is required to complete the TLB invalidation executed while
    the MMU is disabled.

  - An ISB is required to make the new TTBR value visible to the
    page-table walker before the MMU is enabled in the SCTLR.

An earlier version of the patch actually got this correct:

  https://lore.kernel.org/lkml/20210304184717.GB21795@willie-the-truck/

but thanks to some badly worded review comments from yours truly, these
were dropped for the version that was eventually merged.

Bring back the barriers and fix the potential issue (but note that this
was found by code inspection).

Cc: Quentin Perret <qperret@google.com>
Fixes: f320bc742bc23 ("KVM: arm64: Prepare the creation of s1 mappings at EL2")
Signed-off-by: Will Deacon <will@kernel.org>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20240104164220.7968-1-will@kernel.org
---
 arch/arm64/kvm/hyp/nvhe/hyp-init.S | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index f62a7d3602857..2994878d68ea7 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -288,6 +288,8 @@ alternative_else_nop_endif
 	mov	sp, x0
 
 	/* And turn the MMU back on! */
+	dsb	nsh
+	isb
 	set_sctlr_el2	x2
 	ret	x1
 SYM_FUNC_END(__pkvm_init_switch_pgd)
-- 
GitLab


From ec4fcc6b6a63585af8897b49d9aae92af994505d Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 20 Dec 2023 19:09:05 -0800
Subject: [PATCH 2226/4076] Input: da9063_onkey - avoid using OF-specific APIs

There is nothing OF-specific in the driver, so switch from OF properties
helpers to generic device helpers.

Reviewed-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://lore.kernel.org/r/ZYOsUfKceOFXuCt5@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/da9063_onkey.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index a8b7f1cd0ec2a..ce499c28a7b26 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -9,11 +9,12 @@
 #include <linux/errno.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/pm_wakeirq.h>
+#include <linux/property.h>
 #include <linux/workqueue.h>
 #include <linux/regmap.h>
-#include <linux/of.h>
 #include <linux/mfd/da9063/core.h>
 #include <linux/mfd/da9063/registers.h>
 #include <linux/mfd/da9062/core.h>
@@ -199,8 +200,8 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 		return dev_err_probe(&pdev->dev, -ENXIO,
 				     "Parent regmap unavailable.\n");
 
-	onkey->key_power = !of_property_read_bool(pdev->dev.of_node,
-						  "dlg,disable-key-power");
+	onkey->key_power = !device_property_read_bool(&pdev->dev,
+						      "dlg,disable-key-power");
 
 	onkey->input = devm_input_allocate_device(&pdev->dev);
 	if (!onkey->input)
-- 
GitLab


From 0c64117d112b35dc3ba2020108ec26f538b95ae6 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 20 Dec 2023 19:09:45 -0800
Subject: [PATCH 2227/4076] Input: da9063_onkey - avoid explicitly setting
 input's parent

devm_input_allocate_device() already sets parent of the new input
device, there's no need to set it up explicitly.

Reviewed-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://lore.kernel.org/r/ZYOseYfVgg0Ve6Zl@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/da9063_onkey.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index ce499c28a7b26..c338765e0ecd0 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -211,7 +211,6 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 	snprintf(onkey->phys, sizeof(onkey->phys), "%s/input0",
 		 onkey->config->name);
 	onkey->input->phys = onkey->phys;
-	onkey->input->dev.parent = &pdev->dev;
 
 	input_set_capability(onkey->input, EV_KEY, KEY_POWER);
 
-- 
GitLab


From 32253f00ac8a8073bf6db4bfe9d6511cc93c4aef Mon Sep 17 00:00:00 2001
From: Vincent Whitchurch <vincent.whitchurch@axis.com>
Date: Fri, 1 Sep 2023 15:35:43 +0200
Subject: [PATCH 2228/4076] um: virt-pci: fix platform map offset

The offset is currently always zero so the backend can't distinguish
between accesses to different ioremapped areas.

Fixes: 522c532c4fe7 ("virt-pci: add platform bus support")
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/drivers/virt-pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c
index ffe2ee8a02465..97a37c0629972 100644
--- a/arch/um/drivers/virt-pci.c
+++ b/arch/um/drivers/virt-pci.c
@@ -971,7 +971,7 @@ static long um_pci_map_platform(unsigned long offset, size_t size,
 	*ops = &um_pci_device_bar_ops;
 	*priv = &um_pci_platform_device->resptr[0];
 
-	return 0;
+	return offset;
 }
 
 static const struct logic_iomem_region_ops um_pci_platform_ops = {
-- 
GitLab


From 541d4e4d435c8b9bfd29f70a1da4a2db97794e0a Mon Sep 17 00:00:00 2001
From: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Date: Thu, 21 Sep 2023 15:34:44 +0100
Subject: [PATCH 2229/4076] um: Fix naming clash between UML and scheduler

__cant_sleep was already used and exported by the scheduler.
The name had to be changed to a UML specific one.

Signed-off-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Reviewed-by: Peter Lafreniere <peter@n8pjl.ca>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/include/shared/kern_util.h | 2 +-
 arch/um/kernel/process.c           | 2 +-
 arch/um/os-Linux/helper.c          | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index d8b8b4f07e429..444bae755b16a 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -50,7 +50,7 @@ extern void do_uml_exitcalls(void);
  * Are we disallowed to sleep? Used to choose between GFP_KERNEL and
  * GFP_ATOMIC.
  */
-extern int __cant_sleep(void);
+extern int __uml_cant_sleep(void);
 extern int get_current_pid(void);
 extern int copy_from_user_proc(void *to, void *from, int size);
 extern char *uml_strdup(const char *string);
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 106b7da2f8d6f..6daffb9d8a8d7 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -220,7 +220,7 @@ void arch_cpu_idle(void)
 	um_idle_sleep();
 }
 
-int __cant_sleep(void) {
+int __uml_cant_sleep(void) {
 	return in_atomic() || irqs_disabled() || in_interrupt();
 	/* Is in_interrupt() really needed? */
 }
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index b459745f52e24..3cb8ac63be6ed 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -46,7 +46,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv)
 	unsigned long stack, sp;
 	int pid, fds[2], ret, n;
 
-	stack = alloc_stack(0, __cant_sleep());
+	stack = alloc_stack(0, __uml_cant_sleep());
 	if (stack == 0)
 		return -ENOMEM;
 
@@ -70,7 +70,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv)
 	data.pre_data = pre_data;
 	data.argv = argv;
 	data.fd = fds[1];
-	data.buf = __cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) :
+	data.buf = __uml_cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) :
 					uml_kmalloc(PATH_MAX, UM_GFP_KERNEL);
 	pid = clone(helper_child, (void *) sp, CLONE_VM, &data);
 	if (pid < 0) {
@@ -121,7 +121,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags,
 	unsigned long stack, sp;
 	int pid, status, err;
 
-	stack = alloc_stack(0, __cant_sleep());
+	stack = alloc_stack(0, __uml_cant_sleep());
 	if (stack == 0)
 		return -ENOMEM;
 
-- 
GitLab


From 085bc003baab8223b87649ee56aa0db05c33b5b8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 25 Sep 2023 21:29:48 +0200
Subject: [PATCH 2230/4076] um: mmu: remove stub_pages

I removed all the users of this some time ago, but
evidently forgot the pointers. Remove them from the
data structure too.

Fixes: bfc58e2b98e9 ("um: remove process stub VMA")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/include/asm/mmu.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h
index 5b072aba5b658..a7555e43ed14a 100644
--- a/arch/um/include/asm/mmu.h
+++ b/arch/um/include/asm/mmu.h
@@ -12,7 +12,6 @@
 typedef struct mm_context {
 	struct mm_id id;
 	struct uml_arch_mm_context arch;
-	struct page *stub_pages[2];
 } mm_context_t;
 
 extern void __switch_mm(struct mm_id * mm_idp);
-- 
GitLab


From 982b6acec662ff06e9e89c61838f297f6544a84d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 3 Jan 2024 23:42:56 -0800
Subject: [PATCH 2231/4076] perf vendor events intel: Alderlake/rocketlake
 metric fixes

Fix that the core PMU is being specified for 2 uncore events. Specify
a PMU for the alderlake UNCORE_FREQ metric.

Conversion script updated in:

  https://github.com/intel/perfmon/pull/126

Committer testing:

Before this patch the "perf all metricgroups test" was failing, now:

  root@number:~# perf test metric
   10: PMU events                                                      :
   10.3: Parsing of PMU event table metrics                            : Ok
   10.4: Parsing of PMU event table metrics with fake PMUs             : Ok
   10.5: Parsing of metric thresholds with fake PMUs                   : Ok
   61: Parse and process metrics                                       : Ok
   98: perf stat metrics (shadow stat) test                            : Skip
  101: perf all metricgroups test                                      : Ok
  102: perf all metrics test                                           : FAILED!
  107: perf metrics value validation                                   : Ok
  root@number:~#

Test 102 is failing for another reason, not being able to get as many
counters as needed, Ian Rogers suggested disabling the NMI watchdog to
have more counters available:

  root@number:/home/acme# cat /proc/sys/kernel/nmi_watchdog
  1
  root@number:/home/acme# echo 0 > /proc/sys/kernel/nmi_watchdog
  root@number:/home/acme# perf test 102
  102: perf all metrics test                                           : Ok
  root@number:/home/acme#

Closes: https://lore.kernel.org/lkml/ZZWOdHXJJ_oecWwm@kernel.org/
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240104074259.653219-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/x86/alderlake/adl-metrics.json           | 15 ++++++++-------
 .../arch/x86/rocketlake/rkl-metrics.json          |  2 +-
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 3388b58b8f1a6..35124a4ddcb2b 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -69,12 +69,6 @@
         "MetricName": "C9_Pkg_Residency",
         "ScaleUnit": "100%"
     },
-    {
-        "BriefDescription": "Uncore frequency per die [GHZ]",
-        "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9",
-        "MetricGroup": "SoC",
-        "MetricName": "UNCORE_FREQ"
-    },
     {
         "BriefDescription": "Percentage of cycles spent in System Management Interrupts.",
         "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)",
@@ -809,6 +803,13 @@
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Uncore frequency per die [GHZ]",
+        "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9",
+        "MetricGroup": "SoC",
+        "MetricName": "UNCORE_FREQ",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)",
@@ -1838,7 +1839,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu_core@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@",
+        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
index 0c880e4156699..27433fc15ede7 100644
--- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
@@ -985,7 +985,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@",
+        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
-- 
GitLab


From 576d7fed09c7edbae7600f29a8a3ed6c1ead904f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 3 Jan 2024 23:42:57 -0800
Subject: [PATCH 2232/4076] perf vendor events intel: Update emeraldrapids
 events to v1.02

Update to v1.02 released in:
https://github.com/intel/perfmon/pull/123

Removes events AMX_OPS_RETIRED.BF16 and AMX_OPS_RETIRED.INT8. Add
events FP_ARITH_DISPATCHED.V0, FP_ARITH_DISPATCHED.V1,
FP_ARITH_DISPATCHED.V2, UNC_IIO_IOMMU0.1G_HITS, UNC_IIO_IOMMU0.2M_HITS
and UNC_IIO_IOMMU0.4K_HITS. Description updates.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240104074259.653219-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../x86/emeraldrapids/floating-point.json     | 27 +++++++++++++++--
 .../arch/x86/emeraldrapids/pipeline.json      | 18 +----------
 .../emeraldrapids/uncore-interconnect.json    |  8 ++---
 .../arch/x86/emeraldrapids/uncore-io.json     | 30 +++++++++++++++++++
 tools/perf/pmu-events/arch/x86/mapfile.csv    |  2 +-
 5 files changed, 60 insertions(+), 25 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
index 4a9d211e9d4f1..1bdefaf962877 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
@@ -23,26 +23,47 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V0",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V1",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V2",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
+    },
     {
         "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "EventCode": "0xc7",
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
index 6dcf3b763af4f..1f8200fb89647 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
@@ -1,20 +1,4 @@
 [
-    {
-        "BriefDescription": "AMX retired arithmetic BF16 operations.",
-        "EventCode": "0xce",
-        "EventName": "AMX_OPS_RETIRED.BF16",
-        "PublicDescription": "Number of AMX-based retired arithmetic bfloat16 (BF16) floating-point operations. Counts TDPBF16PS FP instructions. SW to use operation multiplier of 4",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "AMX retired arithmetic integer 8-bit operations.",
-        "EventCode": "0xce",
-        "EventName": "AMX_OPS_RETIRED.INT8",
-        "PublicDescription": "Number of AMX-based retired arithmetic integer operations of 8-bit width source operands. Counts TDPB[SS,UU,US,SU]D instructions. SW should use operation multiplier of 8.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
     {
         "BriefDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE",
         "CounterMask": "1",
@@ -505,7 +489,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
+        "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
index 09d840c7da4c9..65d088556bae8 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
@@ -4825,11 +4825,11 @@
         "Unit": "M3UPI"
     },
     {
-        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (AD Bouncable)",
+        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (AD Bounceable)",
         "EventCode": "0x47",
         "EventName": "UNC_MDF_CRS_TxR_INSERTS.AD_BNC",
         "PerPkg": "1",
-        "PublicDescription": "AD Bouncable : Number of allocations into the CRS Egress",
+        "PublicDescription": "AD Bounceable : Number of allocations into the CRS Egress",
         "UMask": "0x1",
         "Unit": "MDF"
     },
@@ -4861,11 +4861,11 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (BL Bouncable)",
+        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (BL Bounceable)",
         "EventCode": "0x47",
         "EventName": "UNC_MDF_CRS_TxR_INSERTS.BL_BNC",
         "PerPkg": "1",
-        "PublicDescription": "BL Bouncable : Number of allocations into the CRS Egress",
+        "PublicDescription": "BL Bounceable : Number of allocations into the CRS Egress",
         "UMask": "0x4",
         "Unit": "MDF"
     },
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
index 557080b74ee50..0761980c34a04 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
@@ -1185,6 +1185,36 @@
         "UMask": "0x70ff010",
         "Unit": "IIO"
     },
+    {
+        "BriefDescription": ": IOTLB Hits to a 1G Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.1G_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 1G Page : Counts if a transaction to a 1G page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x10",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": ": IOTLB Hits to a 2M Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.2M_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 2M Page : Counts if a transaction to a 2M page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x8",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": ": IOTLB Hits to a 4K Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.4K_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 4K Page : Counts if a transaction to a 4K page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x4",
+        "Unit": "IIO"
+    },
     {
         "BriefDescription": ": Context cache hits",
         "EventCode": "0x40",
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index e571683f59f3d..fd38c516c0480 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -7,7 +7,7 @@ GenuineIntel-6-56,v11,broadwellde,core
 GenuineIntel-6-4F,v22,broadwellx,core
 GenuineIntel-6-55-[56789ABCDEF],v1.20,cascadelakex,core
 GenuineIntel-6-9[6C],v1.04,elkhartlake,core
-GenuineIntel-6-CF,v1.01,emeraldrapids,core
+GenuineIntel-6-CF,v1.02,emeraldrapids,core
 GenuineIntel-6-5[CF],v13,goldmont,core
 GenuineIntel-6-7A,v1.01,goldmontplus,core
 GenuineIntel-6-B6,v1.00,grandridge,core
-- 
GitLab


From 8550506887a93cd6ff4f6b44a08e8c2cc7a4d481 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 3 Jan 2024 23:42:58 -0800
Subject: [PATCH 2233/4076] perf vendor events intel: Update icelakex events to
 v1.23

Update to v1.23 released in:

  https://github.com/intel/perfmon/pull/123

Updates to event descriptions.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240104074259.653219-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/x86/icelakex/other.json          | 2 +-
 tools/perf/pmu-events/arch/x86/icelakex/pipeline.json       | 2 +-
 .../pmu-events/arch/x86/icelakex/uncore-interconnect.json   | 6 +++---
 tools/perf/pmu-events/arch/x86/mapfile.csv                  | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/icelakex/other.json b/tools/perf/pmu-events/arch/x86/icelakex/other.json
index 63d5faf2fc43e..11810daaf1503 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/other.json
@@ -19,7 +19,7 @@
         "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
-        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchtecture).  This includes high current AVX 512-bit instructions.",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchitecture).  This includes high current AVX 512-bit instructions.",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json
index 176e5ef2a24af..45ee6bceba7f1 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json
@@ -519,7 +519,7 @@
         "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
         "EventCode": "0x5e",
         "EventName": "RS_EVENTS.EMPTY_CYCLES",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into stravation periods (e.g. branch mispredictions or i-cache misses)",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
index f87ea3f66d1be..a066a009c5117 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
@@ -38,7 +38,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.CLFLUSH",
         "PerPkg": "1",
-        "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x80",
         "Unit": "IRP"
     },
@@ -65,7 +65,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.WBMTOI",
         "PerPkg": "1",
-        "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x40",
         "Unit": "IRP"
     },
@@ -454,7 +454,7 @@
         "EventCode": "0x11",
         "EventName": "UNC_I_TRANSACTIONS.WRITES",
         "PerPkg": "1",
-        "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Trackes only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
+        "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
         "UMask": "0x2",
         "Unit": "IRP"
     },
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index fd38c516c0480..c1820eb16a19a 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -15,7 +15,7 @@ GenuineIntel-6-A[DE],v1.01,graniterapids,core
 GenuineIntel-6-(3C|45|46),v33,haswell,core
 GenuineIntel-6-3F,v28,haswellx,core
 GenuineIntel-6-7[DE],v1.19,icelake,core
-GenuineIntel-6-6[AC],v1.21,icelakex,core
+GenuineIntel-6-6[AC],v1.23,icelakex,core
 GenuineIntel-6-3A,v24,ivybridge,core
 GenuineIntel-6-3E,v24,ivytown,core
 GenuineIntel-6-2D,v24,jaketown,core
-- 
GitLab


From 360b045fceb282fb21b66131c396b0f85759ddb7 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 3 Jan 2024 23:42:59 -0800
Subject: [PATCH 2234/4076] perf vendor events intel: Update sapphirerapids
 events to v1.17

Update to v1.17 released in:

  https://github.com/intel/perfmon/pull/123

Add events FP_ARITH_DISPATCHED.V0, FP_ARITH_DISPATCHED.V1,
FP_ARITH_DISPATCHED.V2, UNC_IIO_IOMMU0.1G_HITS, UNC_IIO_IOMMU0.2M_HITS
and UNC_IIO_IOMMU0.4K_HITS. Description updates.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240104074259.653219-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/x86/mapfile.csv    |  2 +-
 .../x86/sapphirerapids/floating-point.json    | 27 +++++++++++++++--
 .../arch/x86/sapphirerapids/pipeline.json     |  2 +-
 .../sapphirerapids/uncore-interconnect.json   |  8 ++---
 .../arch/x86/sapphirerapids/uncore-io.json    | 30 +++++++++++++++++++
 5 files changed, 60 insertions(+), 9 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index c1820eb16a19a..4d1deed4437ab 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -26,7 +26,7 @@ GenuineIntel-6-1[AEF],v4,nehalemep,core
 GenuineIntel-6-2E,v4,nehalemex,core
 GenuineIntel-6-A7,v1.01,rocketlake,core
 GenuineIntel-6-2A,v19,sandybridge,core
-GenuineIntel-6-8F,v1.16,sapphirerapids,core
+GenuineIntel-6-8F,v1.17,sapphirerapids,core
 GenuineIntel-6-AF,v1.00,sierraforest,core
 GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
 GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v57,skylake,core
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
index 4a9d211e9d4f1..1bdefaf962877 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
@@ -23,26 +23,47 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5",
+        "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2]",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V0",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V1",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5]",
+        "EventCode": "0xb3",
+        "EventName": "FP_ARITH_DISPATCHED.V2",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
+    },
     {
         "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "EventCode": "0xc7",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
index 6dcf3b763af4f..2cfe814d20151 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
@@ -505,7 +505,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
+        "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
index 09d840c7da4c9..65d088556bae8 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
@@ -4825,11 +4825,11 @@
         "Unit": "M3UPI"
     },
     {
-        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (AD Bouncable)",
+        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (AD Bounceable)",
         "EventCode": "0x47",
         "EventName": "UNC_MDF_CRS_TxR_INSERTS.AD_BNC",
         "PerPkg": "1",
-        "PublicDescription": "AD Bouncable : Number of allocations into the CRS Egress",
+        "PublicDescription": "AD Bounceable : Number of allocations into the CRS Egress",
         "UMask": "0x1",
         "Unit": "MDF"
     },
@@ -4861,11 +4861,11 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (BL Bouncable)",
+        "BriefDescription": "Number of allocations into the CRS Egress  used to queue up requests destined to the mesh (BL Bounceable)",
         "EventCode": "0x47",
         "EventName": "UNC_MDF_CRS_TxR_INSERTS.BL_BNC",
         "PerPkg": "1",
-        "PublicDescription": "BL Bouncable : Number of allocations into the CRS Egress",
+        "PublicDescription": "BL Bounceable : Number of allocations into the CRS Egress",
         "UMask": "0x4",
         "Unit": "MDF"
     },
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
index 8b5f54fed1033..03596db877101 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
@@ -1249,6 +1249,36 @@
         "UMask": "0x70ff010",
         "Unit": "IIO"
     },
+    {
+        "BriefDescription": ": IOTLB Hits to a 1G Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.1G_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 1G Page : Counts if a transaction to a 1G page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x10",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": ": IOTLB Hits to a 2M Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.2M_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 2M Page : Counts if a transaction to a 2M page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x8",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": ": IOTLB Hits to a 4K Page",
+        "EventCode": "0x40",
+        "EventName": "UNC_IIO_IOMMU0.4K_HITS",
+        "PerPkg": "1",
+        "PortMask": "0x0000",
+        "PublicDescription": ": IOTLB Hits to a 4K Page : Counts if a transaction to a 4K page, on its first lookup, hits the IOTLB.",
+        "UMask": "0x4",
+        "Unit": "IIO"
+    },
     {
         "BriefDescription": ": Context cache hits",
         "EventCode": "0x40",
-- 
GitLab


From a8e75902f4d7d342350ea3f79e3e65f2bbfa4c8d Mon Sep 17 00:00:00 2001
From: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Date: Tue, 17 Oct 2023 09:32:01 +0100
Subject: [PATCH 2235/4076] um: document arch_futex_atomic_op_inuser

arch_futex_atomic_op_inuser was not documented correctly
resulting in build time warnings.

Signed-off-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/kernel/skas/uaccess.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
index aaee96f07172d..198269e384c43 100644
--- a/arch/um/kernel/skas/uaccess.c
+++ b/arch/um/kernel/skas/uaccess.c
@@ -236,7 +236,9 @@ EXPORT_SYMBOL(strnlen_user);
  *			  argument and comparison of the previous
  *			  futex value with another constant.
  *
- * @encoded_op:	encoded operation to execute
+ * @op:		operation to execute
+ * @oparg:	argument to operation
+ * @oval:	old value at uaddr
  * @uaddr:	pointer to user space address
  *
  * Return:
-- 
GitLab


From 6af6d22495efeb00cb4e220a4e6e30b5be3afdf3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ahelenia=20Ziemia=C5=84ska?=
 <nabijaczleweli@nabijaczleweli.xyz>
Date: Tue, 27 Dec 2022 21:57:40 +0100
Subject: [PATCH 2236/4076] perf TUI: Don't ignore job control
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In its infinite wisdom, by default, SLang sets susp undef, and this can
only be un-done by calling SLtty_set_suspend_state(true).  After every
SLang_init_tty().

Additionally, no provisions are made for maintaining the teletype
attributes across suspend/continue (outside of curses emulation
mode(?!), which provides full support, naturally), so we need to save
and restore the flags ourselves, as well as reset the text colours when
going under.  We need to also re-draw the screen, and raising SIGWINCH,
shockingly, Just Works.

The correct solution would be to Not Use SLang, but as a stop-gap,
this makes TUI 'perf report' usable.

Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: yaowenbin <yaowenbin1@huawei.com>
Link: https://lore.kernel.org/r/0354dcae23a8713f75f4fed609e0caec3c6e3cd5.1672174189.git.nabijaczleweli@nabijaczleweli.xyz
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/browsers/annotate.c |  1 +
 tools/perf/ui/browsers/hists.c    |  2 ++
 tools/perf/ui/browsers/scripts.c  |  1 +
 tools/perf/ui/tui/setup.c         | 22 ++++++++++++++++++++++
 4 files changed, 26 insertions(+)

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index cb2eb6dcb5321..ec5e219328760 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -938,6 +938,7 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
 	/* reset abort key so that it can get Ctrl-C as a key */
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
 
 	return map_symbol__tui_annotate(&he->ms, evsel, hbt);
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 3061dea29e6b6..0c02b3a8e121f 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -3000,6 +3000,7 @@ static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *h
 	/* reset abort key so that it can get Ctrl-C as a key */
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
 
 	if (min_pcnt)
 		browser->min_pcnt = min_pcnt;
@@ -3667,6 +3668,7 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 	/* reset abort key so that it can get Ctrl-C as a key */
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
 
 	memset(&action, 0, sizeof(action));
 
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index 47d2c7a8cbe13..50d45054ed6c1 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -166,6 +166,7 @@ void run_script(char *cmd)
 	printf("\033[c\033[H\033[J");
 	fflush(stdout);
 	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
 	SLsmg_refresh();
 }
 
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 605d9e175ea73..16c6eff4d2411 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -2,12 +2,14 @@
 #include <signal.h>
 #include <stdbool.h>
 #include <stdlib.h>
+#include <termios.h>
 #include <unistd.h>
 #include <linux/kernel.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
 
+#include "../../util/color.h"
 #include "../../util/debug.h"
 #include "../browser.h"
 #include "../helpline.h"
@@ -121,6 +123,23 @@ static void ui__signal(int sig)
 	exit(0);
 }
 
+static void ui__sigcont(int sig)
+{
+	static struct termios tty;
+
+	if (sig == SIGTSTP) {
+		while (tcgetattr(SLang_TT_Read_FD, &tty) == -1 && errno == EINTR)
+			;
+		while (write(SLang_TT_Read_FD, PERF_COLOR_RESET, sizeof(PERF_COLOR_RESET) - 1) == -1 && errno == EINTR)
+			;
+		raise(SIGSTOP);
+	} else {
+		while (tcsetattr(SLang_TT_Read_FD, TCSADRAIN, &tty) == -1 && errno == EINTR)
+			;
+		raise(SIGWINCH);
+	}
+}
+
 int ui__init(void)
 {
 	int err;
@@ -135,6 +154,7 @@ int ui__init(void)
 	err = SLang_init_tty(-1, 0, 0);
 	if (err < 0)
 		goto out;
+	SLtty_set_suspend_state(true);
 
 	err = SLkp_init();
 	if (err < 0) {
@@ -149,6 +169,8 @@ int ui__init(void)
 	signal(SIGINT, ui__signal);
 	signal(SIGQUIT, ui__signal);
 	signal(SIGTERM, ui__signal);
+	signal(SIGTSTP, ui__sigcont);
+	signal(SIGCONT, ui__sigcont);
 
 	perf_error__register(&perf_tui_eops);
 
-- 
GitLab


From ad30469a841b50dbb541df4d6971d891f703c297 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Dec 2023 16:05:13 -0800
Subject: [PATCH 2237/4076] libsubcmd: Fix memory leak in uniq()

uniq() will write one command name over another causing the overwritten
string to be leaked. Fix by doing a pass that removes duplicates and a
second that removes the holes.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Chenyuan Mi <cymi20@fudan.edu.cn>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231208000515.1693746-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/subcmd/help.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c
index adfbae27dc369..8561b0f01a247 100644
--- a/tools/lib/subcmd/help.c
+++ b/tools/lib/subcmd/help.c
@@ -52,11 +52,21 @@ void uniq(struct cmdnames *cmds)
 	if (!cmds->cnt)
 		return;
 
-	for (i = j = 1; i < cmds->cnt; i++)
-		if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
-			cmds->names[j++] = cmds->names[i];
-
+	for (i = 1; i < cmds->cnt; i++) {
+		if (!strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
+			zfree(&cmds->names[i - 1]);
+	}
+	for (i = 0, j = 0; i < cmds->cnt; i++) {
+		if (cmds->names[i]) {
+			if (i == j)
+				j++;
+			else
+				cmds->names[j++] = cmds->names[i];
+		}
+	}
 	cmds->cnt = j;
+	while (j < i)
+		cmds->names[j++] = NULL;
 }
 
 void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
-- 
GitLab


From bb177a85e82b37d3b76e65f3f773e8502be49d9b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 7 Dec 2023 09:40:57 -0800
Subject: [PATCH 2238/4076] perf tests: Add perf script test

Start a new set of shell tests for testing perf script. The initial
contribution is checking that some perf db-export functionality works
as reported in this regression by Ben Gainey <ben.gainey@arm.com>:
https://lore.kernel.org/lkml/20231207140911.3240408-1-ben.gainey@arm.com/

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ben Gainey <ben.gainey@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231207174057.1482161-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/script.sh | 66 ++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)
 create mode 100755 tools/perf/tests/shell/script.sh

diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
new file mode 100755
index 0000000000000..5ae7bd0031a82
--- /dev/null
+++ b/tools/perf/tests/shell/script.sh
@@ -0,0 +1,66 @@
+#!/bin/sh
+# perf script tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+temp_dir=$(mktemp -d /tmp/perf-test-script.XXXXXXXXXX)
+
+perfdatafile="${temp_dir}/perf.data"
+db_test="${temp_dir}/db_test.py"
+
+err=0
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	sane=$(echo "${temp_dir}" | cut -b 1-21)
+	if [ "${sane}" = "/tmp/perf-test-script" ] ; then
+		echo "--- Cleaning up ---"
+		rm -f "${temp_dir}/"*
+		rmdir "${temp_dir}"
+	fi
+}
+
+trap_cleanup()
+{
+	cleanup
+	exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
+
+test_db()
+{
+	echo "DB test"
+
+	# Check if python script is supported
+	libpython=$(perf version --build-options | grep python | grep -cv OFF)
+	if [ "${libpython}" != "1" ] ; then
+		echo "SKIP: python scripting is not supported"
+		err=2
+		return
+	fi
+
+	cat << "_end_of_file_" > "${db_test}"
+perf_db_export_mode = True
+perf_db_export_calls = False
+perf_db_export_callchains = True
+
+def sample_table(*args):
+    print(f'sample_table({args})')
+
+def call_path_table(*args):
+    print(f'call_path_table({args}')
+_end_of_file_
+	perf record -g -o "${perfdatafile}" true
+	perf script -i "${perfdatafile}" -s "${db_test}"
+	echo "DB test [Success]"
+}
+
+test_db
+
+cleanup
+
+exit $err
-- 
GitLab


From 1e24ce402c97dc3c0ab050593f1d5f6fde524564 Mon Sep 17 00:00:00 2001
From: Ben Gainey <ben.gainey@arm.com>
Date: Thu, 7 Dec 2023 14:09:11 +0000
Subject: [PATCH 2239/4076] perf db-export: Fix missing reference count get in
 call_path_from_sample()

The addr_location map and maps fields in the inner loop were missing
calls to map__get()/maps__get(). The subsequent addr_location__exit()
call in each loop puts the map/maps fields causing use-after-free
aborts.

This issue reproduces on at least arm64 and x86_64 with something
simple like `perf record -g ls` followed by `perf script -s script.py`
with the following script:

    perf_db_export_mode = True
    perf_db_export_calls = False
    perf_db_export_callchains = True

    def sample_table(*args):
        print(f'sample_table({args})')

    def call_path_table(*args):
        print(f'call_path_table({args}')

Committer testing:

This test, just introduced by Ian Rogers, now passes, not segfaulting
anymore:

  # perf test "perf script tests"
   95: perf script tests                                               : Ok
  #

Fixes: 0dd5041c9a0eaf8c ("perf addr_location: Add init/exit/copy functions")
Signed-off-by: Ben Gainey <ben.gainey@arm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231207140911.3240408-1-ben.gainey@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/db-export.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index b9fb71ab7a730..106429155c2e9 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -253,8 +253,8 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 		 */
 		addr_location__init(&al);
 		al.sym = node->ms.sym;
-		al.map = node->ms.map;
-		al.maps = thread__maps(thread);
+		al.map = map__get(node->ms.map);
+		al.maps = maps__get(thread__maps(thread));
 		al.addr = node->ip;
 
 		if (al.map && !al.sym)
-- 
GitLab


From b6d8b858dbbbd832d255c3c8a3721173e6edf036 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 19 Dec 2023 15:32:35 +0100
Subject: [PATCH 2240/4076] perf test: test case 'Setup struct perf_event_attr'
 fails on s390 on z/vm

perf test 17 'Setup struct perf_event_attr' fails on s390 z/VM guest,
using linux-next kernel.

Root cause is the fall-back from hardware counter cycles

   perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    size                             136
    config                           0 (PERF_COUNT_HW_CPU_CYCLES)
    { sample_period, sample_freq }   4000
    sample_type                      IP|TID|TIME|ADDR|PERIOD|DATA_SRC
    read_format                      ID|LOST

which returns -ENOENT on s390 z/VM guest. This causes the code to fall
back to software counter task-clock, as can be seen in the debug output:

  ------------------------------------------------------------
   perf_event_attr:
    type                             1 (PERF_TYPE_SOFTWARE)
    size                             136
    config                           0x1 (PERF_COUNT_SW_TASK_CLOCK) <-here
    { sample_period, sample_freq }   4000
    sample_type                      IP|TID|TIME|ADDR|PERIOD|DATA_SRC
    read_format                      ID|LOST

This succeeds on s390 z/VM guest.

This successful installation of the counter task-clock is not listed in
the expected results and the test case fails.

This is caused by commit eb2eac0c7b618033 ("perf evsel: Fallback to
"task-clock" when not system wide") which introduced fall back from
event 'cycles' to event 'task-clock'.

To fix this on s390 allow event number 0 (cycles) and event number 1
(task-clock) as expected result.

Output before:

  # ./perf test -Fv 17
  17: Setup struct perf_event_attr                                    :
  --- start ---
  running './tests/attr/test-stat-group1'
  unsupp  './tests/attr/test-stat-group1'
  running './tests/attr/test-record-graph-default'
  test limitation '!aarch64'
  excluded architecture list ['aarch64']
  expected config=0, got 1
  FAILED './tests/attr/test-record-graph-default' - match failure
  ---- end ----
  Setup struct perf_event_attr: FAILED!
  #

Output after:

  # ./perf test -F 17
  17: Setup struct perf_event_attr               : Ok
  #

Fixes: eb2eac0c7b618033 ("perf evsel: Fallback to "task-clock" when not system wide")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20231219143235.1075522-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/attr/base-record | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 27c21271a16c9..b44e4e6e44438 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -6,7 +6,7 @@ flags=0|8
 cpu=*
 type=0|1
 size=136
-config=0
+config=0|1
 sample_period=*
 sample_type=263
 read_format=0|4|20
-- 
GitLab


From d6488fee66472b468ed88d265b14aa3f04dc3bdf Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Fri, 8 Dec 2023 11:06:36 +0800
Subject: [PATCH 2241/4076] cxl/port: Fix decoder initialization when
 nr_targets > interleave_ways

The decoder_populate_targets() helper walks all of the targets in a port
and makes sure they can be looked up in @target_map. Where @target_map
is a lookup table from target position to target id (corresponding to a
cxl_dport instance). However @target_map is only responsible for
conveying the active dport instances as indicated by interleave_ways.

When nr_targets > interleave_ways it results in
decoder_populate_targets() walking off the end of the valid entries in
@target_map. Given target_map is initialized to 0 it results in the
dport lookup failing if position 0 is not mapped to a dport with an id
of 0:

  cxl_port port3: Failed to populate active decoder targets
  cxl_port port3: Failed to add decoder
  cxl_port port3: Failed to add decoder3.0
  cxl_bus_probe: cxl_port port3: probe: -6

This bug also highlights that when the decoder's ->targets[] array is
written in cxl_port_setup_targets() it is missing a hold of the
targets_lock to synchronize against sysfs readers of the target list. A
fix for that is saved for a later patch.

Fixes: a5c258021689 ("cxl/bus: Populate the target list at decoder create")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Huang, Ying <ying.huang@intel.com>
[djbw: rewrite the changelog, find the Fixes: tag]
Co-developed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/port.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index b7c93bb18f6e7..57495cdc181fd 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1644,7 +1644,7 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 		return -EINVAL;
 
 	write_seqlock(&cxlsd->target_lock);
-	for (i = 0; i < cxlsd->nr_targets; i++) {
+	for (i = 0; i < cxlsd->cxld.interleave_ways; i++) {
 		struct cxl_dport *dport = find_dport(port, target_map[i]);
 
 		if (!dport) {
-- 
GitLab


From 5459e186a5c9f412334321cff58d70dcb0e48a04 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 21 Dec 2023 21:05:01 -0800
Subject: [PATCH 2242/4076] cxl/port: Fix missing target list lock

cxl_port_setup_targets() modifies the ->targets[] array of a switch
decoder. target_list_show() expects to be able to emit a coherent
snapshot of that array by "holding" ->target_lock for read. The
target_lock is held for write during initialization of the ->targets[]
array, but it is not held for write during cxl_port_setup_targets().

The ->target_lock() predates the introduction of @cxl_region_rwsem. That
semaphore protects changes to host-physical-address (HPA) decode which
is precisely what writes to a switch decoder's target list affects.

Replace ->target_lock with @cxl_region_rwsem.

Now the side-effect of snapshotting a unstable view of a decoder's
target list is likely benign so the Fixes: tag is presumptive.

Fixes: 27b3f8d13830 ("cxl/region: Program target lists")
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/port.c | 22 +++++++---------------
 drivers/cxl/cxl.h       |  2 --
 2 files changed, 7 insertions(+), 17 deletions(-)

diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 57495cdc181fd..6b386771cc259 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -172,14 +172,10 @@ static ssize_t target_list_show(struct device *dev,
 {
 	struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev);
 	ssize_t offset;
-	unsigned int seq;
 	int rc;
 
-	do {
-		seq = read_seqbegin(&cxlsd->target_lock);
-		rc = emit_target_list(cxlsd, buf);
-	} while (read_seqretry(&cxlsd->target_lock, seq));
-
+	guard(rwsem_read)(&cxl_region_rwsem);
+	rc = emit_target_list(cxlsd, buf);
 	if (rc < 0)
 		return rc;
 	offset = rc;
@@ -1633,7 +1629,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_find_port, CXL);
 static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 				    struct cxl_port *port, int *target_map)
 {
-	int i, rc = 0;
+	int i;
 
 	if (!target_map)
 		return 0;
@@ -1643,19 +1639,16 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 	if (xa_empty(&port->dports))
 		return -EINVAL;
 
-	write_seqlock(&cxlsd->target_lock);
+	guard(rwsem_write)(&cxl_region_rwsem);
 	for (i = 0; i < cxlsd->cxld.interleave_ways; i++) {
 		struct cxl_dport *dport = find_dport(port, target_map[i]);
 
-		if (!dport) {
-			rc = -ENXIO;
-			break;
-		}
+		if (!dport)
+			return -ENXIO;
 		cxlsd->target[i] = dport;
 	}
-	write_sequnlock(&cxlsd->target_lock);
 
-	return rc;
+	return 0;
 }
 
 struct cxl_dport *cxl_hb_modulo(struct cxl_root_decoder *cxlrd, int pos)
@@ -1725,7 +1718,6 @@ static int cxl_switch_decoder_init(struct cxl_port *port,
 		return -EINVAL;
 
 	cxlsd->nr_targets = nr_targets;
-	seqlock_init(&cxlsd->target_lock);
 	return cxl_decoder_init(port, &cxlsd->cxld);
 }
 
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 687043ece1018..62fa96f8567e5 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -412,7 +412,6 @@ struct cxl_endpoint_decoder {
 /**
  * struct cxl_switch_decoder - Switch specific CXL HDM Decoder
  * @cxld: base cxl_decoder object
- * @target_lock: coordinate coherent reads of the target list
  * @nr_targets: number of elements in @target
  * @target: active ordered target list in current decoder configuration
  *
@@ -424,7 +423,6 @@ struct cxl_endpoint_decoder {
  */
 struct cxl_switch_decoder {
 	struct cxl_decoder cxld;
-	seqlock_t target_lock;
 	int nr_targets;
 	struct cxl_dport *target[];
 };
-- 
GitLab


From e109deadb73318cf4a3bd61287d969f705df278f Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Thu, 4 Jan 2024 16:57:12 -0500
Subject: [PATCH 2243/4076] eventfs: Have eventfs_iterate() stop immediately if
 ei->is_freed is set

If ei->is_freed is set in eventfs_iterate(), it means that the directory
that is being iterated on is in the process of being freed. Just exit the
loop immediately when that is ever detected, and separate out the return
of the entry->callback() from ei->is_freed.

Link: https://lore.kernel.org/linux-trace-kernel/20240104220048.016261289@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 72912b5f9a90b..0aca6910efb3f 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -788,11 +788,12 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 		name = entry->name;
 
 		mutex_lock(&eventfs_mutex);
-		/* If ei->is_freed, then the event itself may be too */
-		if (!ei->is_freed)
-			r = entry->callback(name, &mode, &cdata, &fops);
-		else
-			r = -1;
+		/* If ei->is_freed then just bail here, nothing more to do */
+		if (ei->is_freed) {
+			mutex_unlock(&eventfs_mutex);
+			goto out;
+		}
+		r = entry->callback(name, &mode, &cdata, &fops);
 		mutex_unlock(&eventfs_mutex);
 		if (r <= 0)
 			continue;
-- 
GitLab


From 1e4624eb5a0ecaae0d2c4e3019bece119725bb98 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Thu, 4 Jan 2024 16:57:13 -0500
Subject: [PATCH 2244/4076] eventfs: Do ctx->pos update for all iterations in
 eventfs_iterate()

The ctx->pos was only updated when it added an entry, but the "skip to
current pos" check (c--) happened for every loop regardless of if the
entry was added or not. This inconsistency caused readdir to be incorrect.

It was due to:

	for (i = 0; i < ei->nr_entries; i++) {

		if (c > 0) {
			c--;
			continue;
		}

		mutex_lock(&eventfs_mutex);
		/* If ei->is_freed then just bail here, nothing more to do */
		if (ei->is_freed) {
			mutex_unlock(&eventfs_mutex);
			goto out;
		}
		r = entry->callback(name, &mode, &cdata, &fops);
		mutex_unlock(&eventfs_mutex);

		[..]
		ctx->pos++;
	}

But this can cause the iterator to return a file that was already read.
That's because of the way the callback() works. Some events may not have
all files, and the callback can return 0 to tell eventfs to skip the file
for this directory.

for instance, we have:

 # ls /sys/kernel/tracing/events/ftrace/function
format  hist  hist_debug  id  inject

and

 # ls /sys/kernel/tracing/events/sched/sched_switch/
enable  filter  format  hist  hist_debug  id  inject  trigger

Where the function directory is missing "enable", "filter" and
"trigger". That's because the callback() for events has:

static int event_callback(const char *name, umode_t *mode, void **data,
			  const struct file_operations **fops)
{
	struct trace_event_file *file = *data;
	struct trace_event_call *call = file->event_call;

[..]

	/*
	 * Only event directories that can be enabled should have
	 * triggers or filters, with the exception of the "print"
	 * event that can have a "trigger" file.
	 */
	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
		if (call->class->reg && strcmp(name, "enable") == 0) {
			*mode = TRACE_MODE_WRITE;
			*fops = &ftrace_enable_fops;
			return 1;
		}

		if (strcmp(name, "filter") == 0) {
			*mode = TRACE_MODE_WRITE;
			*fops = &ftrace_event_filter_fops;
			return 1;
		}
	}

	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) ||
	    strcmp(trace_event_name(call), "print") == 0) {
		if (strcmp(name, "trigger") == 0) {
			*mode = TRACE_MODE_WRITE;
			*fops = &event_trigger_fops;
			return 1;
		}
	}
[..]
	return 0;
}

Where the function event has the TRACE_EVENT_FL_IGNORE_ENABLE set.

This means that the entries array elements for "enable", "filter" and
"trigger" when called on the function event will have the callback return
0 and not 1, to tell eventfs to skip these files for it.

Because the "skip to current ctx->pos" check happened for all entries, but
the ctx->pos++ only happened to entries that exist, it would confuse the
reading of a directory. Which would cause:

 # ls /sys/kernel/tracing/events/ftrace/function/
format  hist  hist  hist_debug  hist_debug  id  inject  inject

The missing "enable", "filter" and "trigger" caused ls to show "hist",
"hist_debug" and "inject" twice.

Update the ctx->pos for every iteration to keep its update and the "skip"
update consistent. This also means that on error, the ctx->pos needs to be
decremented if it was incremented without adding something.

Link: https://lore.kernel.org/all/20240104150500.38b15a62@gandalf.local.home/
Link: https://lore.kernel.org/linux-trace-kernel/20240104220048.172295263@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: 493ec81a8fb8e ("eventfs: Stop using dcache_readdir() for getdents()")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 0aca6910efb3f..c73fb1f7ddbc2 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -760,6 +760,8 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 			continue;
 		}
 
+		ctx->pos++;
+
 		if (ei_child->is_freed)
 			continue;
 
@@ -767,13 +769,12 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		dentry = create_dir_dentry(ei, ei_child, ei_dentry);
 		if (!dentry)
-			goto out;
+			goto out_dec;
 		ino = dentry->d_inode->i_ino;
 		dput(dentry);
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
-			goto out;
-		ctx->pos++;
+			goto out_dec;
 	}
 
 	for (i = 0; i < ei->nr_entries; i++) {
@@ -784,6 +785,8 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 			continue;
 		}
 
+		ctx->pos++;
+
 		entry = &ei->entries[i];
 		name = entry->name;
 
@@ -791,7 +794,7 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 		/* If ei->is_freed then just bail here, nothing more to do */
 		if (ei->is_freed) {
 			mutex_unlock(&eventfs_mutex);
-			goto out;
+			goto out_dec;
 		}
 		r = entry->callback(name, &mode, &cdata, &fops);
 		mutex_unlock(&eventfs_mutex);
@@ -800,19 +803,23 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		dentry = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
 		if (!dentry)
-			goto out;
+			goto out_dec;
 		ino = dentry->d_inode->i_ino;
 		dput(dentry);
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
-			goto out;
-		ctx->pos++;
+			goto out_dec;
 	}
 	ret = 1;
  out:
 	srcu_read_unlock(&eventfs_srcu, idx);
 
 	return ret;
+
+ out_dec:
+	/* Incremented ctx->pos without adding something, reset it */
+	ctx->pos--;
+	goto out;
 }
 
 /**
-- 
GitLab


From 704f960dbee2f1634f4b4e16f208cb16eaf41c1e Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Thu, 4 Jan 2024 16:57:14 -0500
Subject: [PATCH 2245/4076] eventfs: Read ei->entries before ei->children in
 eventfs_iterate()

In order to apply a shortcut to skip over the current ctx->pos
immediately, by using the ei->entries array, the reading of that array
should be first. Moving the array reading before the linked list reading
will make the shortcut change diff nicer to read.

Link: https://lore.kernel.org/all/CAHk-=wiKwDUDv3+jCsv-uacDcHDVTYsXtBR9=6sGM5mqX+DhOg@mail.gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240104220048.333115095@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 46 ++++++++++++++++++++--------------------
 1 file changed, 23 insertions(+), 23 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index c73fb1f7ddbc2..a1934e0eea3b7 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -752,8 +752,8 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 	 * Need to create the dentries and inodes to have a consistent
 	 * inode number.
 	 */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
+	for (i = 0; i < ei->nr_entries; i++) {
+		void *cdata = ei->data;
 
 		if (c > 0) {
 			c--;
@@ -762,23 +762,32 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		ctx->pos++;
 
-		if (ei_child->is_freed)
-			continue;
+		entry = &ei->entries[i];
+		name = entry->name;
 
-		name = ei_child->name;
+		mutex_lock(&eventfs_mutex);
+		/* If ei->is_freed then just bail here, nothing more to do */
+		if (ei->is_freed) {
+			mutex_unlock(&eventfs_mutex);
+			goto out_dec;
+		}
+		r = entry->callback(name, &mode, &cdata, &fops);
+		mutex_unlock(&eventfs_mutex);
+		if (r <= 0)
+			continue;
 
-		dentry = create_dir_dentry(ei, ei_child, ei_dentry);
+		dentry = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
 		if (!dentry)
 			goto out_dec;
 		ino = dentry->d_inode->i_ino;
 		dput(dentry);
 
-		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
 			goto out_dec;
 	}
 
-	for (i = 0; i < ei->nr_entries; i++) {
-		void *cdata = ei->data;
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
+				 srcu_read_lock_held(&eventfs_srcu)) {
 
 		if (c > 0) {
 			c--;
@@ -787,27 +796,18 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		ctx->pos++;
 
-		entry = &ei->entries[i];
-		name = entry->name;
-
-		mutex_lock(&eventfs_mutex);
-		/* If ei->is_freed then just bail here, nothing more to do */
-		if (ei->is_freed) {
-			mutex_unlock(&eventfs_mutex);
-			goto out_dec;
-		}
-		r = entry->callback(name, &mode, &cdata, &fops);
-		mutex_unlock(&eventfs_mutex);
-		if (r <= 0)
+		if (ei_child->is_freed)
 			continue;
 
-		dentry = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
+		name = ei_child->name;
+
+		dentry = create_dir_dentry(ei, ei_child, ei_dentry);
 		if (!dentry)
 			goto out_dec;
 		ino = dentry->d_inode->i_ino;
 		dput(dentry);
 
-		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
 			goto out_dec;
 	}
 	ret = 1;
-- 
GitLab


From 1de94b52d5e8d8b32f0252f14fad1f1edc2e71f1 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Thu, 4 Jan 2024 16:57:15 -0500
Subject: [PATCH 2246/4076] eventfs: Shortcut eventfs_iterate() by skipping
 entries already read

As the ei->entries array is fixed for the duration of the eventfs_inode,
it can be used to skip over already read entries in eventfs_iterate().

That is, if ctx->pos is greater than zero, there's no reason in doing the
loop across the ei->entries array for the entries less than ctx->pos.
Instead, start the lookup of the entries at the current ctx->pos.

Link: https://lore.kernel.org/all/CAHk-=wiKwDUDv3+jCsv-uacDcHDVTYsXtBR9=6sGM5mqX+DhOg@mail.gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240104220048.494956957@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index a1934e0eea3b7..fdff53d5a1f87 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -746,21 +746,15 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 	if (!ei || !ei_dentry)
 		goto out;
 
-	ret = 0;
-
 	/*
 	 * Need to create the dentries and inodes to have a consistent
 	 * inode number.
 	 */
-	for (i = 0; i < ei->nr_entries; i++) {
-		void *cdata = ei->data;
-
-		if (c > 0) {
-			c--;
-			continue;
-		}
+	ret = 0;
 
-		ctx->pos++;
+	/* Start at 'c' to jump over already read entries */
+	for (i = c; i < ei->nr_entries; i++, ctx->pos++) {
+		void *cdata = ei->data;
 
 		entry = &ei->entries[i];
 		name = entry->name;
@@ -769,7 +763,7 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 		/* If ei->is_freed then just bail here, nothing more to do */
 		if (ei->is_freed) {
 			mutex_unlock(&eventfs_mutex);
-			goto out_dec;
+			goto out;
 		}
 		r = entry->callback(name, &mode, &cdata, &fops);
 		mutex_unlock(&eventfs_mutex);
@@ -778,14 +772,17 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		dentry = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
 		if (!dentry)
-			goto out_dec;
+			goto out;
 		ino = dentry->d_inode->i_ino;
 		dput(dentry);
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
-			goto out_dec;
+			goto out;
 	}
 
+	/* Subtract the skipped entries above */
+	c -= min((unsigned int)c, (unsigned int)ei->nr_entries);
+
 	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
 
-- 
GitLab


From a55719847da0a780baa84d0baee745358f144c39 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:38 +0100
Subject: [PATCH 2247/4076] um: Drop support for hosts without
 SYSEMU_SINGLESTEP support

These features have existed since Linux 2.6.14 and can be considered
widely available at this point. Also drop the backward compatibility
code for PTRACE_SETOPTIONS.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>

----

v2:
 * Continue to define PTRACE_SYSEMU_SINGLESTEP as glibc only added it in
   version 2.27.
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/include/asm/processor-generic.h |  1 -
 arch/um/include/shared/kern_util.h      |  3 +-
 arch/um/include/shared/ptrace_user.h    | 41 ---------------
 arch/um/kernel/process.c                | 12 +----
 arch/um/kernel/ptrace.c                 |  2 -
 arch/um/kernel/signal.c                 | 12 -----
 arch/um/os-Linux/skas/process.c         | 60 ++++-----------------
 arch/um/os-Linux/start_up.c             | 70 +++----------------------
 arch/x86/um/ptrace_32.c                 | 24 ---------
 arch/x86/um/ptrace_64.c                 | 26 ---------
 arch/x86/um/shared/sysdep/ptrace_32.h   |  4 --
 arch/x86/um/shared/sysdep/ptrace_user.h | 12 ++---
 12 files changed, 24 insertions(+), 243 deletions(-)

diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index 7414154b8e9ae..6c3779541845b 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -22,7 +22,6 @@ struct mm_struct;
 struct thread_struct {
 	struct pt_regs regs;
 	struct pt_regs *segv_regs;
-	int singlestep_syscall;
 	void *fault_addr;
 	jmp_buf *fault_catcher;
 	struct task_struct *prev_sched;
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index 444bae755b16a..789b83013f355 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -34,7 +34,6 @@ extern int handle_page_fault(unsigned long address, unsigned long ip,
 
 extern unsigned int do_IRQ(int irq, struct uml_pt_regs *regs);
 extern void initial_thread_cb(void (*proc)(void *), void *arg);
-extern int is_syscall(unsigned long addr);
 
 extern void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
 
@@ -58,7 +57,7 @@ extern char *uml_strdup(const char *string);
 extern unsigned long to_irq_stack(unsigned long *mask_out);
 extern unsigned long from_irq_stack(int nested);
 
-extern int singlestepping(void *t);
+extern int singlestepping(void);
 
 extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
 extern void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs);
diff --git a/arch/um/include/shared/ptrace_user.h b/arch/um/include/shared/ptrace_user.h
index 95455e8996e72..8a705d8f96ce6 100644
--- a/arch/um/include/shared/ptrace_user.h
+++ b/arch/um/include/shared/ptrace_user.h
@@ -12,45 +12,4 @@
 extern int ptrace_getregs(long pid, unsigned long *regs_out);
 extern int ptrace_setregs(long pid, unsigned long *regs_in);
 
-/* syscall emulation path in ptrace */
-
-#ifndef PTRACE_SYSEMU
-#define PTRACE_SYSEMU 31
-#endif
-#ifndef PTRACE_SYSEMU_SINGLESTEP
-#define PTRACE_SYSEMU_SINGLESTEP 32
-#endif
-
-/* On architectures, that started to support PTRACE_O_TRACESYSGOOD
- * in linux 2.4, there are two different definitions of
- * PTRACE_SETOPTIONS: linux 2.4 uses 21 while linux 2.6 uses 0x4200.
- * For binary compatibility, 2.6 also supports the old "21", named
- * PTRACE_OLDSETOPTION. On these architectures, UML always must use
- * "21", to ensure the kernel runs on 2.4 and 2.6 host without
- * recompilation. So, we use PTRACE_OLDSETOPTIONS in UML.
- * We also want to be able to build the kernel on 2.4, which doesn't
- * have PTRACE_OLDSETOPTIONS. So, if it is missing, we declare
- * PTRACE_OLDSETOPTIONS to be the same as PTRACE_SETOPTIONS.
- *
- * On architectures, that start to support PTRACE_O_TRACESYSGOOD on
- * linux 2.6, PTRACE_OLDSETOPTIONS never is defined, and also isn't
- * supported by the host kernel. In that case, our trick lets us use
- * the new 0x4200 with the name PTRACE_OLDSETOPTIONS.
- */
-#ifndef PTRACE_OLDSETOPTIONS
-#define PTRACE_OLDSETOPTIONS PTRACE_SETOPTIONS
-#endif
-
-void set_using_sysemu(int value);
-int get_using_sysemu(void);
-extern int sysemu_supported;
-
-#define SELECT_PTRACE_OPERATION(sysemu_mode, singlestep_mode) \
-	(((int[3][3] ) { \
-		{ PTRACE_SYSCALL, PTRACE_SYSCALL, PTRACE_SINGLESTEP }, \
-		{ PTRACE_SYSEMU, PTRACE_SYSEMU, PTRACE_SINGLESTEP }, \
-		{ PTRACE_SYSEMU, PTRACE_SYSEMU_SINGLESTEP, \
-		  PTRACE_SYSEMU_SINGLESTEP } }) \
-		[sysemu_mode][singlestep_mode])
-
 #endif
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 6daffb9d8a8d7..ab95648e93e15 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -332,17 +332,9 @@ int __init make_proc_sysemu(void)
 
 late_initcall(make_proc_sysemu);
 
-int singlestepping(void * t)
+int singlestepping(void)
 {
-	struct task_struct *task = t ? t : current;
-
-	if (!test_thread_flag(TIF_SINGLESTEP))
-		return 0;
-
-	if (task->thread.singlestep_syscall)
-		return 1;
-
-	return 2;
+	return test_thread_flag(TIF_SINGLESTEP);
 }
 
 /*
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index 5154b27de580f..6600a27827967 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -12,7 +12,6 @@
 void user_enable_single_step(struct task_struct *child)
 {
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
-	child->thread.singlestep_syscall = 0;
 
 #ifdef SUBARCH_SET_SINGLESTEPPING
 	SUBARCH_SET_SINGLESTEPPING(child, 1);
@@ -22,7 +21,6 @@ void user_enable_single_step(struct task_struct *child)
 void user_disable_single_step(struct task_struct *child)
 {
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
-	child->thread.singlestep_syscall = 0;
 
 #ifdef SUBARCH_SET_SINGLESTEPPING
 	SUBARCH_SET_SINGLESTEPPING(child, 0);
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index ae4658f576ab7..a56b44522766f 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -120,18 +120,6 @@ void do_signal(struct pt_regs *regs)
 		}
 	}
 
-	/*
-	 * This closes a way to execute a system call on the host.  If
-	 * you set a breakpoint on a system call instruction and singlestep
-	 * from it, the tracing thread used to PTRACE_SINGLESTEP the process
-	 * rather than PTRACE_SYSCALL it, allowing the system call to execute
-	 * on the host.  The tracing thread will check this flag and
-	 * PTRACE_SYSCALL if necessary.
-	 */
-	if (test_thread_flag(TIF_SINGLESTEP))
-		current->thread.singlestep_syscall =
-			is_syscall(PT_REGS_IP(&current->thread.regs));
-
 	/*
 	 * if there's no signal to deliver, we just put the saved sigmask
 	 * back
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 9464833e741af..43168c51850c0 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -177,48 +177,11 @@ static void handle_segv(int pid, struct uml_pt_regs *regs, unsigned long *aux_fp
 	segv(regs->faultinfo, 0, 1, NULL);
 }
 
-/*
- * To use the same value of using_sysemu as the caller, ask it that value
- * (in local_using_sysemu
- */
-static void handle_trap(int pid, struct uml_pt_regs *regs,
-			int local_using_sysemu)
+static void handle_trap(int pid, struct uml_pt_regs *regs)
 {
-	int err, status;
-
 	if ((UPT_IP(regs) >= STUB_START) && (UPT_IP(regs) < STUB_END))
 		fatal_sigsegv();
 
-	if (!local_using_sysemu)
-	{
-		err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET,
-			     __NR_getpid);
-		if (err < 0) {
-			printk(UM_KERN_ERR "%s - nullifying syscall failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
-
-		err = ptrace(PTRACE_SYSCALL, pid, 0, 0);
-		if (err < 0) {
-			printk(UM_KERN_ERR "%s - continuing to end of syscall failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
-
-		CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL));
-		if ((err < 0) || !WIFSTOPPED(status) ||
-		    (WSTOPSIG(status) != SIGTRAP + 0x80)) {
-			err = ptrace_dump_regs(pid);
-			if (err)
-				printk(UM_KERN_ERR "Failed to get registers from process, errno = %d\n",
-				       -err);
-			printk(UM_KERN_ERR "%s - failed to wait at end of syscall, errno = %d, status = %d\n",
-			       __func__, errno, status);
-			fatal_sigsegv();
-		}
-	}
-
 	handle_syscall(regs);
 }
 
@@ -355,10 +318,10 @@ int start_userspace(unsigned long stub_stack)
 		goto out_kill;
 	}
 
-	if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL,
+	if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0) {
 		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n",
+		printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
 		       __func__, errno);
 		goto out_kill;
 	}
@@ -380,8 +343,6 @@ int start_userspace(unsigned long stub_stack)
 void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 {
 	int err, status, op, pid = userspace_pid[0];
-	/* To prevent races if using_sysemu changes under us.*/
-	int local_using_sysemu;
 	siginfo_t si;
 
 	/* Handle any immediate reschedules or signals */
@@ -411,11 +372,10 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 			fatal_sigsegv();
 		}
 
-		/* Now we set local_using_sysemu to be used for one loop */
-		local_using_sysemu = get_using_sysemu();
-
-		op = SELECT_PTRACE_OPERATION(local_using_sysemu,
-					     singlestepping(NULL));
+		if (singlestepping())
+			op = PTRACE_SYSEMU_SINGLESTEP;
+		else
+			op = PTRACE_SYSEMU;
 
 		if (ptrace(op, pid, 0, 0)) {
 			printk(UM_KERN_ERR "%s - ptrace continue failed, op = %d, errno = %d\n",
@@ -474,7 +434,7 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 				else handle_segv(pid, regs, aux_fp_regs);
 				break;
 			case SIGTRAP + 0x80:
-			        handle_trap(pid, regs, local_using_sysemu);
+				handle_trap(pid, regs);
 				break;
 			case SIGTRAP:
 				relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
@@ -597,10 +557,10 @@ int copy_context_skas0(unsigned long new_stack, int pid)
 		goto out_kill;
 	}
 
-	if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL,
+	if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
 		   (void *)PTRACE_O_TRACESYSGOOD) < 0) {
 		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n",
+		printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
 		       __func__, errno);
 		goto out_kill;
 	}
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index e3ee4db58b40d..561c08e0cc9cf 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -143,71 +143,16 @@ static int stop_ptraced_child(int pid, int exitcode, int mustexit)
 	return ret;
 }
 
-/* Changed only during early boot */
-static int force_sysemu_disabled = 0;
-
-static int __init nosysemu_cmd_param(char *str, int* add)
-{
-	force_sysemu_disabled = 1;
-	return 0;
-}
-
-__uml_setup("nosysemu", nosysemu_cmd_param,
-"nosysemu\n"
-"    Turns off syscall emulation patch for ptrace (SYSEMU).\n"
-"    SYSEMU is a performance-patch introduced by Laurent Vivier. It changes\n"
-"    behaviour of ptrace() and helps reduce host context switch rates.\n"
-"    To make it work, you need a kernel patch for your host, too.\n"
-"    See http://perso.wanadoo.fr/laurent.vivier/UML/ for further \n"
-"    information.\n\n");
-
 static void __init check_sysemu(void)
 {
-	unsigned long regs[MAX_REG_NR];
 	int pid, n, status, count=0;
 
-	os_info("Checking syscall emulation patch for ptrace...");
-	sysemu_supported = 0;
-	pid = start_ptraced_child();
-
-	if (ptrace(PTRACE_SYSEMU, pid, 0, 0) < 0)
-		goto fail;
-
-	CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED));
-	if (n < 0)
-		fatal_perror("check_sysemu : wait failed");
-	if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGTRAP))
-		fatal("check_sysemu : expected SIGTRAP, got status = %d\n",
-		      status);
-
-	if (ptrace(PTRACE_GETREGS, pid, 0, regs) < 0)
-		fatal_perror("check_sysemu : PTRACE_GETREGS failed");
-	if (PT_SYSCALL_NR(regs) != __NR_getpid) {
-		non_fatal("check_sysemu got system call number %d, "
-			  "expected %d...", PT_SYSCALL_NR(regs), __NR_getpid);
-		goto fail;
-	}
-
-	n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_RET_OFFSET, os_getpid());
-	if (n < 0) {
-		non_fatal("check_sysemu : failed to modify system call "
-			  "return");
-		goto fail;
-	}
-
-	if (stop_ptraced_child(pid, 0, 0) < 0)
-		goto fail_stopped;
-
-	sysemu_supported = 1;
-	os_info("OK\n");
-	set_using_sysemu(!force_sysemu_disabled);
-
-	os_info("Checking advanced syscall emulation patch for ptrace...");
+	os_info("Checking syscall emulation for ptrace...");
 	pid = start_ptraced_child();
 
-	if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0,
+	if ((ptrace(PTRACE_SETOPTIONS, pid, 0,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0))
-		fatal_perror("check_sysemu: PTRACE_OLDSETOPTIONS failed");
+		fatal_perror("check_sysemu: PTRACE_SETOPTIONS failed");
 
 	while (1) {
 		count++;
@@ -243,17 +188,14 @@ static void __init check_sysemu(void)
 	if (stop_ptraced_child(pid, 0, 0) < 0)
 		goto fail_stopped;
 
-	sysemu_supported = 2;
 	os_info("OK\n");
 
-	if (!force_sysemu_disabled)
-		set_using_sysemu(sysemu_supported);
 	return;
 
 fail:
 	stop_ptraced_child(pid, 1, 0);
 fail_stopped:
-	non_fatal("missing\n");
+	fatal("missing\n");
 }
 
 static void __init check_ptrace(void)
@@ -263,9 +205,9 @@ static void __init check_ptrace(void)
 	os_info("Checking that ptrace can change system call numbers...");
 	pid = start_ptraced_child();
 
-	if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0,
+	if ((ptrace(PTRACE_SETOPTIONS, pid, 0,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0))
-		fatal_perror("check_ptrace: PTRACE_OLDSETOPTIONS failed");
+		fatal_perror("check_ptrace: PTRACE_SETOPTIONS failed");
 
 	while (1) {
 		if (ptrace(PTRACE_SYSCALL, pid, 0, 0) < 0)
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index 0bc4b73a9cdea..7f1abde2c84b5 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -25,30 +25,6 @@ void arch_switch_to(struct task_struct *to)
 		printk(KERN_WARNING "arch_switch_tls failed, errno = EINVAL\n");
 }
 
-int is_syscall(unsigned long addr)
-{
-	unsigned short instr;
-	int n;
-
-	n = copy_from_user(&instr, (void __user *) addr, sizeof(instr));
-	if (n) {
-		/* access_process_vm() grants access to vsyscall and stub,
-		 * while copy_from_user doesn't. Maybe access_process_vm is
-		 * slow, but that doesn't matter, since it will be called only
-		 * in case of singlestepping, if copy_from_user failed.
-		 */
-		n = access_process_vm(current, addr, &instr, sizeof(instr),
-				FOLL_FORCE);
-		if (n != sizeof(instr)) {
-			printk(KERN_ERR "is_syscall : failed to read "
-			       "instruction from 0x%lx\n", addr);
-			return 1;
-		}
-	}
-	/* int 0x80 or sysenter */
-	return (instr == 0x80cd) || (instr == 0x340f);
-}
-
 /* determines which flags the user has access to. */
 /* 1 = access 0 = no access */
 #define FLAG_MASK 0x00044dd5
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index 289d0159b041e..aa68d83d3f441 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -188,32 +188,6 @@ int peek_user(struct task_struct *child, long addr, long data)
 	return put_user(tmp, (unsigned long *) data);
 }
 
-/* XXX Mostly copied from sys-i386 */
-int is_syscall(unsigned long addr)
-{
-	unsigned short instr;
-	int n;
-
-	n = copy_from_user(&instr, (void __user *) addr, sizeof(instr));
-	if (n) {
-		/*
-		 * access_process_vm() grants access to vsyscall and stub,
-		 * while copy_from_user doesn't. Maybe access_process_vm is
-		 * slow, but that doesn't matter, since it will be called only
-		 * in case of singlestepping, if copy_from_user failed.
-		 */
-		n = access_process_vm(current, addr, &instr, sizeof(instr),
-				FOLL_FORCE);
-		if (n != sizeof(instr)) {
-			printk("is_syscall : failed to read instruction from "
-			       "0x%lx\n", addr);
-			return 1;
-		}
-	}
-	/* sysenter */
-	return instr == 0x050f;
-}
-
 static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
 {
 	int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
diff --git a/arch/x86/um/shared/sysdep/ptrace_32.h b/arch/x86/um/shared/sysdep/ptrace_32.h
index db8478a83a097..0c4989842fbe6 100644
--- a/arch/x86/um/shared/sysdep/ptrace_32.h
+++ b/arch/x86/um/shared/sysdep/ptrace_32.h
@@ -8,10 +8,6 @@
 
 #define MAX_FP_NR HOST_FPX_SIZE
 
-void set_using_sysemu(int value);
-int get_using_sysemu(void);
-extern int sysemu_supported;
-
 #define UPT_SYSCALL_ARG1(r) UPT_BX(r)
 #define UPT_SYSCALL_ARG2(r) UPT_CX(r)
 #define UPT_SYSCALL_ARG3(r) UPT_DX(r)
diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h
index 44782bbad41ea..1d1a824fa6528 100644
--- a/arch/x86/um/shared/sysdep/ptrace_user.h
+++ b/arch/x86/um/shared/sysdep/ptrace_user.h
@@ -15,14 +15,12 @@
 #define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE)
 #else
 #define FP_SIZE HOST_FP_SIZE
+#endif
 
 /*
- * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though
- * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the
- * 2.4 name and value for 2.4 host compatibility.
+ * glibc before 2.27 does not include PTRACE_SYSEMU_SINGLESTEP in its enum,
+ * ensure we have a definition by (re-)defining it here.
  */
-#ifndef PTRACE_OLDSETOPTIONS
-#define PTRACE_OLDSETOPTIONS 21
-#endif
-
+#ifndef PTRACE_SYSEMU_SINGLESTEP
+#define PTRACE_SYSEMU_SINGLESTEP 32
 #endif
-- 
GitLab


From 571353379470f1d0aaad3cce4ad4db4b6c8f9ada Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:39 +0100
Subject: [PATCH 2248/4076] um: Drop NULL check from start_userspace

start_userspace is only called from exactly one location, and the passed
pointer for the userspace process stack cannot be NULL.

Remove the check, without changing the control flow.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/os-Linux/skas/process.c | 53 +++++++++++++++------------------
 1 file changed, 24 insertions(+), 29 deletions(-)

diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 43168c51850c0..ed20cefb29634 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -189,7 +189,7 @@ extern char __syscall_stub_start[];
 
 /**
  * userspace_tramp() - userspace trampoline
- * @stack:	pointer to the new userspace stack page, can be NULL, if? FIXME:
+ * @stack:	pointer to the new userspace stack page
  *
  * The userspace trampoline is used to setup a new userspace process in start_userspace() after it was clone()'ed.
  * This function will run on a temporary stack page.
@@ -204,9 +204,13 @@ extern char __syscall_stub_start[];
  */
 static int userspace_tramp(void *stack)
 {
+	struct sigaction sa;
 	void *addr;
 	int fd;
 	unsigned long long offset;
+	unsigned long segv_handler = STUB_CODE +
+				     (unsigned long) stub_segv_handler -
+				     (unsigned long) __syscall_stub_start;
 
 	ptrace(PTRACE_TRACEME, 0, 0, 0);
 
@@ -222,34 +226,25 @@ static int userspace_tramp(void *stack)
 		exit(1);
 	}
 
-	if (stack != NULL) {
-		fd = phys_mapping(uml_to_phys(stack), &offset);
-		addr = mmap((void *) STUB_DATA,
-			    STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
-			    MAP_FIXED | MAP_SHARED, fd, offset);
-		if (addr == MAP_FAILED) {
-			printk(UM_KERN_ERR "mapping segfault stack at 0x%lx failed, errno = %d\n",
-			       STUB_DATA, errno);
-			exit(1);
-		}
+	fd = phys_mapping(uml_to_phys(stack), &offset);
+	addr = mmap((void *) STUB_DATA,
+		    STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
+		    MAP_FIXED | MAP_SHARED, fd, offset);
+	if (addr == MAP_FAILED) {
+		printk(UM_KERN_ERR "mapping segfault stack at 0x%lx failed, errno = %d\n",
+		       STUB_DATA, errno);
+		exit(1);
 	}
-	if (stack != NULL) {
-		struct sigaction sa;
-
-		unsigned long v = STUB_CODE +
-				  (unsigned long) stub_segv_handler -
-				  (unsigned long) __syscall_stub_start;
-
-		set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
-		sigemptyset(&sa.sa_mask);
-		sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
-		sa.sa_sigaction = (void *) v;
-		sa.sa_restorer = NULL;
-		if (sigaction(SIGSEGV, &sa, NULL) < 0) {
-			printk(UM_KERN_ERR "%s - setting SIGSEGV handler failed - errno = %d\n",
-			       __func__, errno);
-			exit(1);
-		}
+
+	set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
+	sigemptyset(&sa.sa_mask);
+	sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
+	sa.sa_sigaction = (void *) segv_handler;
+	sa.sa_restorer = NULL;
+	if (sigaction(SIGSEGV, &sa, NULL) < 0) {
+		printk(UM_KERN_ERR "%s - setting SIGSEGV handler failed - errno = %d\n",
+		       __func__, errno);
+		exit(1);
 	}
 
 	kill(os_getpid(), SIGSTOP);
@@ -261,7 +256,7 @@ int kill_userspace_mm[NR_CPUS];
 
 /**
  * start_userspace() - prepare a new userspace process
- * @stub_stack:	pointer to the stub stack. Can be NULL, if? FIXME:
+ * @stub_stack:	pointer to the stub stack.
  *
  * Setups a new temporary stack page that is used while userspace_tramp() runs
  * Clones the kernel process into a new userspace process, with FDs only.
-- 
GitLab


From 9e16fb933fd1f2132c0d137f3666ebf20f93e33a Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:40 +0100
Subject: [PATCH 2249/4076] um: Make errors to stop ptraced child fatal during
 startup

For the detection code to check whether SYSEMU_SINGLESTEP works
correctly we needed some error cases while stopping to be non-fatal.
However, at this point stop_ptraced_child must always succeed, and we
can therefore simplify it slightly to exit immediately on error.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/os-Linux/start_up.c | 41 +++++++++++--------------------------
 1 file changed, 12 insertions(+), 29 deletions(-)

diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 561c08e0cc9cf..8b0e98ab842cc 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -112,35 +112,20 @@ static int start_ptraced_child(void)
 	return pid;
 }
 
-/* When testing for SYSEMU support, if it is one of the broken versions, we
- * must just avoid using sysemu, not panic, but only if SYSEMU features are
- * broken.
- * So only for SYSEMU features we test mustpanic, while normal host features
- * must work anyway!
- */
-static int stop_ptraced_child(int pid, int exitcode, int mustexit)
+static void stop_ptraced_child(int pid, int exitcode)
 {
-	int status, n, ret = 0;
+	int status, n;
+
+	if (ptrace(PTRACE_CONT, pid, 0, 0) < 0)
+		fatal_perror("stop_ptraced_child : ptrace failed");
 
-	if (ptrace(PTRACE_CONT, pid, 0, 0) < 0) {
-		perror("stop_ptraced_child : ptrace failed");
-		return -1;
-	}
 	CATCH_EINTR(n = waitpid(pid, &status, 0));
 	if (!WIFEXITED(status) || (WEXITSTATUS(status) != exitcode)) {
 		int exit_with = WEXITSTATUS(status);
-		if (exit_with == 2)
-			non_fatal("check_ptrace : child exited with status 2. "
-				  "\nDisabling SYSEMU support.\n");
-		non_fatal("check_ptrace : child exited with exitcode %d, while "
-			  "expecting %d; status 0x%x\n", exit_with,
-			  exitcode, status);
-		if (mustexit)
-			exit(1);
-		ret = -1;
+		fatal("stop_ptraced_child : child exited with exitcode %d, "
+		      "while expecting %d; status 0x%x\n", exit_with,
+		      exitcode, status);
 	}
-
-	return ret;
 }
 
 static void __init check_sysemu(void)
@@ -185,16 +170,14 @@ static void __init check_sysemu(void)
 			goto fail;
 		}
 	}
-	if (stop_ptraced_child(pid, 0, 0) < 0)
-		goto fail_stopped;
+	stop_ptraced_child(pid, 0);
 
 	os_info("OK\n");
 
 	return;
 
 fail:
-	stop_ptraced_child(pid, 1, 0);
-fail_stopped:
+	stop_ptraced_child(pid, 1);
 	fatal("missing\n");
 }
 
@@ -233,7 +216,7 @@ static void __init check_ptrace(void)
 			break;
 		}
 	}
-	stop_ptraced_child(pid, 0, 1);
+	stop_ptraced_child(pid, 0);
 	os_info("OK\n");
 	check_sysemu();
 }
@@ -312,7 +295,7 @@ void __init os_early_checks(void)
 	pid = start_ptraced_child();
 	if (init_pid_registers(pid))
 		fatal("Failed to initialize default registers");
-	stop_ptraced_child(pid, 1, 1);
+	stop_ptraced_child(pid, 1);
 }
 
 int __init parse_iomem(char *str, int *add)
-- 
GitLab


From 236f9fe39b02c15fa5530b53e9cca48354394389 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:41 +0100
Subject: [PATCH 2250/4076] um: Don't use vfprintf() for os_info()

The threads allocated inside the kernel have only a single page of
stack. Unfortunately, the vfprintf function in standard glibc may use
too much stack-space, overflowing it.

To make os_info safe to be used by helper threads, use the kernel
vscnprintf function into a smallish buffer and write out the information
to stderr.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/os-Linux/util.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index fc0f2a9dee5af..1dca4ffbd572f 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -173,23 +173,38 @@ __uml_setup("quiet", quiet_cmd_param,
 "quiet\n"
 "    Turns off information messages during boot.\n\n");
 
+/*
+ * The os_info/os_warn functions will be called by helper threads. These
+ * have a very limited stack size and using the libc formatting functions
+ * may overflow the stack.
+ * So pull in the kernel vscnprintf and use that instead with a fixed
+ * on-stack buffer.
+ */
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
+
 void os_info(const char *fmt, ...)
 {
+	char buf[256];
 	va_list list;
+	int len;
 
 	if (quiet_info)
 		return;
 
 	va_start(list, fmt);
-	vfprintf(stderr, fmt, list);
+	len = vscnprintf(buf, sizeof(buf), fmt, list);
+	fwrite(buf, len, 1, stderr);
 	va_end(list);
 }
 
 void os_warn(const char *fmt, ...)
 {
+	char buf[256];
 	va_list list;
+	int len;
 
 	va_start(list, fmt);
-	vfprintf(stderr, fmt, list);
+	len = vscnprintf(buf, sizeof(buf), fmt, list);
+	fwrite(buf, len, 1, stderr);
 	va_end(list);
 }
-- 
GitLab


From 1818b8406678a78b823dad44c91580f859403ced Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:42 +0100
Subject: [PATCH 2251/4076] um: Do not use printk in SIGWINCH helper thread

The thread is running outside of the UML kernel scope and is a helper.
As such, printk cannot work and os_info must be used instead.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/drivers/chan_user.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index 25727ed648b72..c2b83cb99aae0 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -153,8 +153,8 @@ static int winch_thread(void *arg)
 	pipe_fd = data->pipe_fd;
 	count = write(pipe_fd, &c, sizeof(c));
 	if (count != sizeof(c))
-		printk(UM_KERN_ERR "winch_thread : failed to write "
-		       "synchronization byte, err = %d\n", -count);
+		os_info("winch_thread : failed to write synchronization byte, err = %d\n",
+			-count);
 
 	/*
 	 * We are not using SIG_IGN on purpose, so don't fix it as I thought to
@@ -166,28 +166,28 @@ static int winch_thread(void *arg)
 	sigfillset(&sigs);
 	/* Block all signals possible. */
 	if (sigprocmask(SIG_SETMASK, &sigs, NULL) < 0) {
-		printk(UM_KERN_ERR "winch_thread : sigprocmask failed, "
-		       "errno = %d\n", errno);
+		os_info("winch_thread : sigprocmask failed, errno = %d\n",
+			errno);
 		exit(1);
 	}
 	/* In sigsuspend(), block anything else than SIGWINCH. */
 	sigdelset(&sigs, SIGWINCH);
 
 	if (setsid() < 0) {
-		printk(UM_KERN_ERR "winch_thread : setsid failed, errno = %d\n",
+		os_info("winch_thread : setsid failed, errno = %d\n",
 		       errno);
 		exit(1);
 	}
 
 	if (ioctl(pty_fd, TIOCSCTTY, 0) < 0) {
-		printk(UM_KERN_ERR "winch_thread : TIOCSCTTY failed on "
-		       "fd %d err = %d\n", pty_fd, errno);
+		os_info("winch_thread : TIOCSCTTY failed on "
+			"fd %d err = %d\n", pty_fd, errno);
 		exit(1);
 	}
 
 	if (tcsetpgrp(pty_fd, os_getpid()) < 0) {
-		printk(UM_KERN_ERR "winch_thread : tcsetpgrp failed on "
-		       "fd %d err = %d\n", pty_fd, errno);
+		os_info("winch_thread : tcsetpgrp failed on fd %d err = %d\n",
+			pty_fd, errno);
 		exit(1);
 	}
 
@@ -199,8 +199,8 @@ static int winch_thread(void *arg)
 	 */
 	count = read(pipe_fd, &c, sizeof(c));
 	if (count != sizeof(c))
-		printk(UM_KERN_ERR "winch_thread : failed to read "
-		       "synchronization byte, err = %d\n", errno);
+		os_info("winch_thread : failed to read synchronization byte, err = %d\n",
+			errno);
 
 	while(1) {
 		/*
@@ -211,8 +211,8 @@ static int winch_thread(void *arg)
 
 		count = write(pipe_fd, &c, sizeof(c));
 		if (count != sizeof(c))
-			printk(UM_KERN_ERR "winch_thread : write failed, "
-			       "err = %d\n", errno);
+			os_info("winch_thread : write failed, err = %d\n",
+				errno);
 	}
 }
 
-- 
GitLab


From 139e6e8ef6ee9a56fc1737240ecd8402fbcadd82 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:43 +0100
Subject: [PATCH 2252/4076] um: Reap winch thread if it fails

When the winch thread runs into an error condition, it would exit(1) and
never be reaped until shutdown time. Change this to write a command byte
which causes the driver to kill it, therefore reaping the child.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/drivers/chan_user.c | 16 +++++++++++-----
 arch/um/drivers/line.c      | 13 ++++++++-----
 2 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index c2b83cb99aae0..ed7cc830b3e7b 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -141,7 +141,7 @@ struct winch_data {
 	int pipe_fd;
 };
 
-static int winch_thread(void *arg)
+static __noreturn int winch_thread(void *arg)
 {
 	struct winch_data *data = arg;
 	sigset_t sigs;
@@ -168,7 +168,7 @@ static int winch_thread(void *arg)
 	if (sigprocmask(SIG_SETMASK, &sigs, NULL) < 0) {
 		os_info("winch_thread : sigprocmask failed, errno = %d\n",
 			errno);
-		exit(1);
+		goto wait_kill;
 	}
 	/* In sigsuspend(), block anything else than SIGWINCH. */
 	sigdelset(&sigs, SIGWINCH);
@@ -176,19 +176,19 @@ static int winch_thread(void *arg)
 	if (setsid() < 0) {
 		os_info("winch_thread : setsid failed, errno = %d\n",
 		       errno);
-		exit(1);
+		goto wait_kill;
 	}
 
 	if (ioctl(pty_fd, TIOCSCTTY, 0) < 0) {
 		os_info("winch_thread : TIOCSCTTY failed on "
 			"fd %d err = %d\n", pty_fd, errno);
-		exit(1);
+		goto wait_kill;
 	}
 
 	if (tcsetpgrp(pty_fd, os_getpid()) < 0) {
 		os_info("winch_thread : tcsetpgrp failed on fd %d err = %d\n",
 			pty_fd, errno);
-		exit(1);
+		goto wait_kill;
 	}
 
 	/*
@@ -214,6 +214,12 @@ static int winch_thread(void *arg)
 			os_info("winch_thread : write failed, err = %d\n",
 				errno);
 	}
+
+wait_kill:
+	c = 2;
+	count = write(pipe_fd, &c, sizeof(c));
+	while (1)
+		pause();
 }
 
 static int winch_tramp(int fd, struct tty_port *port, int *fd_out,
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index b98545f3edb50..449d320c3f553 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -629,15 +629,18 @@ static irqreturn_t winch_interrupt(int irq, void *data)
 
 	if (fd != -1) {
 		err = generic_read(fd, &c, NULL);
-		if (err < 0) {
+		/* A read of 2 means the winch thread failed and has warned */
+		if (err < 0 || (err == 1 && c == 2)) {
 			if (err != -EAGAIN) {
 				winch->fd = -1;
 				list_del(&winch->list);
 				os_close_file(fd);
-				printk(KERN_ERR "winch_interrupt : "
-				       "read failed, errno = %d\n", -err);
-				printk(KERN_ERR "fd %d is losing SIGWINCH "
-				       "support\n", winch->tty_fd);
+				if (err < 0) {
+					printk(KERN_ERR "winch_interrupt : read failed, errno = %d\n",
+					       -err);
+					printk(KERN_ERR "fd %d is losing SIGWINCH support\n",
+					       winch->tty_fd);
+				}
 				INIT_WORK(&winch->work, __free_winch);
 				schedule_work(&winch->work);
 				return IRQ_HANDLED;
-- 
GitLab


From 6d64095ea8698e3cb1698ec4e81acb2aa1500322 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:44 +0100
Subject: [PATCH 2253/4076] um: Do not use printk in userspace trampoline

The trampoline is running in a cloned process. It is not safe to use
printk for error printing there.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/os-Linux/skas/process.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index ed20cefb29634..1f5c3f2523d1e 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -221,8 +221,8 @@ static int userspace_tramp(void *stack)
 	addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE,
 		      PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset);
 	if (addr == MAP_FAILED) {
-		printk(UM_KERN_ERR "mapping mmap stub at 0x%lx failed, errno = %d\n",
-		       STUB_CODE, errno);
+		os_info("mapping mmap stub at 0x%lx failed, errno = %d\n",
+			STUB_CODE, errno);
 		exit(1);
 	}
 
@@ -231,8 +231,8 @@ static int userspace_tramp(void *stack)
 		    STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
 		    MAP_FIXED | MAP_SHARED, fd, offset);
 	if (addr == MAP_FAILED) {
-		printk(UM_KERN_ERR "mapping segfault stack at 0x%lx failed, errno = %d\n",
-		       STUB_DATA, errno);
+		os_info("mapping segfault stack at 0x%lx failed, errno = %d\n",
+			STUB_DATA, errno);
 		exit(1);
 	}
 
@@ -242,8 +242,8 @@ static int userspace_tramp(void *stack)
 	sa.sa_sigaction = (void *) segv_handler;
 	sa.sa_restorer = NULL;
 	if (sigaction(SIGSEGV, &sa, NULL) < 0) {
-		printk(UM_KERN_ERR "%s - setting SIGSEGV handler failed - errno = %d\n",
-		       __func__, errno);
+		os_info("%s - setting SIGSEGV handler failed - errno = %d\n",
+			__func__, errno);
 		exit(1);
 	}
 
-- 
GitLab


From 7b84543cbd8861c83a2ec7c8848e936ce214bc01 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:45 +0100
Subject: [PATCH 2254/4076] um: Always inline stub functions

The stub executable page is remapped to a different location in the
userland process. As these functions may be used by the stub, they
really need to be always inlined rather than permitting the compiler to
emit a function.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/x86/um/shared/sysdep/stub_32.h | 21 +++++++++++----------
 arch/x86/um/shared/sysdep/stub_64.h | 17 +++++++++--------
 2 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h
index 38fa894b65d08..4e763f8b380f5 100644
--- a/arch/x86/um/shared/sysdep/stub_32.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -12,7 +12,7 @@
 #define STUB_MMAP_NR __NR_mmap2
 #define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT)
 
-static inline long stub_syscall0(long syscall)
+static __always_inline long stub_syscall0(long syscall)
 {
 	long ret;
 
@@ -21,7 +21,7 @@ static inline long stub_syscall0(long syscall)
 	return ret;
 }
 
-static inline long stub_syscall1(long syscall, long arg1)
+static __always_inline long stub_syscall1(long syscall, long arg1)
 {
 	long ret;
 
@@ -30,7 +30,7 @@ static inline long stub_syscall1(long syscall, long arg1)
 	return ret;
 }
 
-static inline long stub_syscall2(long syscall, long arg1, long arg2)
+static __always_inline long stub_syscall2(long syscall, long arg1, long arg2)
 {
 	long ret;
 
@@ -40,7 +40,8 @@ static inline long stub_syscall2(long syscall, long arg1, long arg2)
 	return ret;
 }
 
-static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
+static __always_inline long stub_syscall3(long syscall, long arg1, long arg2,
+					  long arg3)
 {
 	long ret;
 
@@ -50,8 +51,8 @@ static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
 	return ret;
 }
 
-static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
-				 long arg4)
+static __always_inline long stub_syscall4(long syscall, long arg1, long arg2,
+					  long arg3, long arg4)
 {
 	long ret;
 
@@ -61,8 +62,8 @@ static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 	return ret;
 }
 
-static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
-				 long arg4, long arg5)
+static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
+					  long arg3, long arg4, long arg5)
 {
 	long ret;
 
@@ -72,12 +73,12 @@ static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
 	return ret;
 }
 
-static inline void trap_myself(void)
+static __always_inline void trap_myself(void)
 {
 	__asm("int3");
 }
 
-static inline void remap_stack_and_trap(void)
+static __always_inline void remap_stack_and_trap(void)
 {
 	__asm__ volatile (
 		"movl %%esp,%%ebx ;"
diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h
index 2de1c8f881734..b24168ef0ac49 100644
--- a/arch/x86/um/shared/sysdep/stub_64.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -16,7 +16,7 @@
 #define __syscall_clobber "r11","rcx","memory"
 #define __syscall "syscall"
 
-static inline long stub_syscall0(long syscall)
+static __always_inline long stub_syscall0(long syscall)
 {
 	long ret;
 
@@ -27,7 +27,7 @@ static inline long stub_syscall0(long syscall)
 	return ret;
 }
 
-static inline long stub_syscall2(long syscall, long arg1, long arg2)
+static __always_inline long stub_syscall2(long syscall, long arg1, long arg2)
 {
 	long ret;
 
@@ -38,7 +38,8 @@ static inline long stub_syscall2(long syscall, long arg1, long arg2)
 	return ret;
 }
 
-static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
+static __always_inline long stub_syscall3(long syscall, long arg1, long arg2,
+					  long arg3)
 {
 	long ret;
 
@@ -50,7 +51,7 @@ static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
 	return ret;
 }
 
-static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
+static __always_inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 				 long arg4)
 {
 	long ret;
@@ -64,8 +65,8 @@ static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 	return ret;
 }
 
-static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
-				 long arg4, long arg5)
+static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
+					  long arg3, long arg4, long arg5)
 {
 	long ret;
 
@@ -78,12 +79,12 @@ static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
 	return ret;
 }
 
-static inline void trap_myself(void)
+static __always_inline void trap_myself(void)
 {
 	__asm("int3");
 }
 
-static inline void remap_stack_and_trap(void)
+static __always_inline void remap_stack_and_trap(void)
 {
 	__asm__ volatile (
 		"movq %0,%%rax ;"
-- 
GitLab


From a4166aec11309d24e650e74cf8191a6d25a97fcf Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Tue, 21 Nov 2023 15:47:24 -0800
Subject: [PATCH 2255/4076] riscv: Deduplicate code in setup_smp()

Both the ACPI and DT implementations contain some of the same code.
Move it to the calling function so it is not duplicated.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231121234736.3489608-2-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/smpboot.c | 31 +++++++++++--------------------
 1 file changed, 11 insertions(+), 20 deletions(-)

diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index d162bf339beb1..1c68e61fb8529 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -125,18 +125,7 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un
 
 static void __init acpi_parse_and_init_cpus(void)
 {
-	int cpuid;
-
-	cpu_set_ops(0);
-
 	acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_rintc, 0);
-
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
-			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 #else
 #define acpi_parse_and_init_cpus(...)	do { } while (0)
@@ -150,8 +139,6 @@ static void __init of_parse_and_init_cpus(void)
 	int cpuid = 1;
 	int rc;
 
-	cpu_set_ops(0);
-
 	for_each_of_cpu_node(dn) {
 		rc = riscv_early_of_processor_hartid(dn, &hart);
 		if (rc < 0)
@@ -179,21 +166,25 @@ static void __init of_parse_and_init_cpus(void)
 	if (cpuid > nr_cpu_ids)
 		pr_warn("Total number of cpus [%d] is greater than nr_cpus option value [%d]\n",
 			cpuid, nr_cpu_ids);
-
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
-			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 
 void __init setup_smp(void)
 {
+	int cpuid;
+
+	cpu_set_ops(0);
+
 	if (acpi_disabled)
 		of_parse_and_init_cpus();
 	else
 		acpi_parse_and_init_cpus();
+
+	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
+		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
+			cpu_set_ops(cpuid);
+			set_cpu_possible(cpuid, true);
+		}
+	}
 }
 
 static int start_secondary_cpu(int cpu, struct task_struct *tidle)
-- 
GitLab


From 79093f3ec39c90edf4bd1a532d922ee6163441ec Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Tue, 21 Nov 2023 15:47:25 -0800
Subject: [PATCH 2256/4076] riscv: Remove unused members from struct
 cpu_operations

name is not used anywhere at all. cpu_prepare and cpu_disable do nothing
and always return 0 if implemented.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231121234736.3489608-3-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cpu_ops.h     | 10 ----------
 arch/riscv/kernel/cpu-hotplug.c      |  9 +--------
 arch/riscv/kernel/cpu_ops.c          |  2 --
 arch/riscv/kernel/cpu_ops_sbi.c      | 19 -------------------
 arch/riscv/kernel/cpu_ops_spinwait.c | 11 -----------
 arch/riscv/kernel/head.S             |  1 -
 arch/riscv/kernel/setup.c            |  1 -
 arch/riscv/kernel/smpboot.c          |  6 ------
 8 files changed, 1 insertion(+), 58 deletions(-)

diff --git a/arch/riscv/include/asm/cpu_ops.h b/arch/riscv/include/asm/cpu_ops.h
index aa128466c4d4e..18af75e6873c5 100644
--- a/arch/riscv/include/asm/cpu_ops.h
+++ b/arch/riscv/include/asm/cpu_ops.h
@@ -13,26 +13,16 @@
 /**
  * struct cpu_operations - Callback operations for hotplugging CPUs.
  *
- * @name:		Name of the boot protocol.
- * @cpu_prepare:	Early one-time preparation step for a cpu. If there
- *			is a mechanism for doing so, tests whether it is
- *			possible to boot the given HART.
  * @cpu_start:		Boots a cpu into the kernel.
- * @cpu_disable:	Prepares a cpu to die. May fail for some
- *			mechanism-specific reason, which will cause the hot
- *			unplug to be aborted. Called from the cpu to be killed.
  * @cpu_stop:		Makes a cpu leave the kernel. Must not fail. Called from
  *			the cpu being stopped.
  * @cpu_is_stopped:	Ensures a cpu has left the kernel. Called from another
  *			cpu.
  */
 struct cpu_operations {
-	const char	*name;
-	int		(*cpu_prepare)(unsigned int cpu);
 	int		(*cpu_start)(unsigned int cpu,
 				     struct task_struct *tidle);
 #ifdef CONFIG_HOTPLUG_CPU
-	int		(*cpu_disable)(unsigned int cpu);
 	void		(*cpu_stop)(void);
 	int		(*cpu_is_stopped)(unsigned int cpu);
 #endif
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
index 457a18efcb114..934eb64da0d0b 100644
--- a/arch/riscv/kernel/cpu-hotplug.c
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -29,25 +29,18 @@ bool cpu_has_hotplug(unsigned int cpu)
  */
 int __cpu_disable(void)
 {
-	int ret = 0;
 	unsigned int cpu = smp_processor_id();
 
 	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
 		return -EOPNOTSUPP;
 
-	if (cpu_ops[cpu]->cpu_disable)
-		ret = cpu_ops[cpu]->cpu_disable(cpu);
-
-	if (ret)
-		return ret;
-
 	remove_cpu_topology(cpu);
 	numa_remove_cpu(cpu);
 	set_cpu_online(cpu, false);
 	riscv_ipi_disable();
 	irq_migrate_all_off_this_cpu();
 
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
index eb479a88a954e..5540e2880abbb 100644
--- a/arch/riscv/kernel/cpu_ops.c
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -18,8 +18,6 @@ const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 extern const struct cpu_operations cpu_ops_sbi;
 #ifndef CONFIG_RISCV_BOOT_SPINWAIT
 const struct cpu_operations cpu_ops_spinwait = {
-	.name		= "",
-	.cpu_prepare	= NULL,
 	.cpu_start	= NULL,
 };
 #endif
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index efa0f0816634c..1cc7df740eddc 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -79,23 +79,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
 }
 
-static int sbi_cpu_prepare(unsigned int cpuid)
-{
-	if (!cpu_ops_sbi.cpu_start) {
-		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
-static int sbi_cpu_disable(unsigned int cpuid)
-{
-	if (!cpu_ops_sbi.cpu_stop)
-		return -EOPNOTSUPP;
-	return 0;
-}
-
 static void sbi_cpu_stop(void)
 {
 	int ret;
@@ -118,11 +102,8 @@ static int sbi_cpu_is_stopped(unsigned int cpuid)
 #endif
 
 const struct cpu_operations cpu_ops_sbi = {
-	.name		= "sbi",
-	.cpu_prepare	= sbi_cpu_prepare,
 	.cpu_start	= sbi_cpu_start,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable	= sbi_cpu_disable,
 	.cpu_stop	= sbi_cpu_stop,
 	.cpu_is_stopped	= sbi_cpu_is_stopped,
 #endif
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
index d98d19226b5f5..613872b0a21ac 100644
--- a/arch/riscv/kernel/cpu_ops_spinwait.c
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -39,15 +39,6 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid,
 	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
 }
 
-static int spinwait_cpu_prepare(unsigned int cpuid)
-{
-	if (!cpu_ops_spinwait.cpu_start) {
-		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 {
 	/*
@@ -64,7 +55,5 @@ static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 }
 
 const struct cpu_operations cpu_ops_spinwait = {
-	.name		= "spinwait",
-	.cpu_prepare	= spinwait_cpu_prepare,
 	.cpu_start	= spinwait_cpu_start,
 };
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index b77397432403d..0349e5cdfe1d4 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -11,7 +11,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/csr.h>
-#include <asm/cpu_ops_sbi.h>
 #include <asm/hwcap.h>
 #include <asm/image.h>
 #include <asm/scs.h>
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 535a837de55d1..2bf8828046244 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -26,7 +26,6 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
-#include <asm/cpu_ops.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 1c68e61fb8529..5551945255cdc 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -49,7 +49,6 @@ void __init smp_prepare_boot_cpu(void)
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
-	int ret;
 	unsigned int curr_cpuid;
 
 	init_cpu_topology();
@@ -66,11 +65,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	for_each_possible_cpu(cpuid) {
 		if (cpuid == curr_cpuid)
 			continue;
-		if (cpu_ops[cpuid]->cpu_prepare) {
-			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
-			if (ret)
-				continue;
-		}
 		set_cpu_present(cpuid, true);
 		numa_store_cpu_info(cpuid);
 	}
-- 
GitLab


From 62ff262227a45bf917fe198885ab7aa19be5a01f Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Tue, 21 Nov 2023 15:47:26 -0800
Subject: [PATCH 2257/4076] riscv: Use the same CPU operations for all CPUs

RISC-V provides no binding (ACPI or DT) to describe per-cpu start/stop
operations, so cpu_set_ops() will always detect the same operations for
every CPU. Replace the cpu_ops array with a single pointer to save space
and reduce boot time.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231121234736.3489608-4-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cpu_ops.h |  4 ++--
 arch/riscv/kernel/cpu-hotplug.c  | 10 +++++-----
 arch/riscv/kernel/cpu_ops.c      | 12 +++++-------
 arch/riscv/kernel/smp.c          |  2 +-
 arch/riscv/kernel/smpboot.c      | 13 +++++--------
 5 files changed, 18 insertions(+), 23 deletions(-)

diff --git a/arch/riscv/include/asm/cpu_ops.h b/arch/riscv/include/asm/cpu_ops.h
index 18af75e6873c5..176b570ef9827 100644
--- a/arch/riscv/include/asm/cpu_ops.h
+++ b/arch/riscv/include/asm/cpu_ops.h
@@ -29,7 +29,7 @@ struct cpu_operations {
 };
 
 extern const struct cpu_operations cpu_ops_spinwait;
-extern const struct cpu_operations *cpu_ops[NR_CPUS];
-void __init cpu_set_ops(int cpu);
+extern const struct cpu_operations *cpu_ops;
+void __init cpu_set_ops(void);
 
 #endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
index 934eb64da0d0b..28b58fc5ad199 100644
--- a/arch/riscv/kernel/cpu-hotplug.c
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -18,7 +18,7 @@
 
 bool cpu_has_hotplug(unsigned int cpu)
 {
-	if (cpu_ops[cpu]->cpu_stop)
+	if (cpu_ops->cpu_stop)
 		return true;
 
 	return false;
@@ -31,7 +31,7 @@ int __cpu_disable(void)
 {
 	unsigned int cpu = smp_processor_id();
 
-	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+	if (!cpu_ops->cpu_stop)
 		return -EOPNOTSUPP;
 
 	remove_cpu_topology(cpu);
@@ -55,8 +55,8 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
 	pr_notice("CPU%u: off\n", cpu);
 
 	/* Verify from the firmware if the cpu is really stopped*/
-	if (cpu_ops[cpu]->cpu_is_stopped)
-		ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+	if (cpu_ops->cpu_is_stopped)
+		ret = cpu_ops->cpu_is_stopped(cpu);
 	if (ret)
 		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
 }
@@ -70,7 +70,7 @@ void __noreturn arch_cpu_idle_dead(void)
 
 	cpuhp_ap_report_dead();
 
-	cpu_ops[smp_processor_id()]->cpu_stop();
+	cpu_ops->cpu_stop();
 	/* It should never reach here */
 	BUG();
 }
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
index 5540e2880abbb..6a8bd8f4db071 100644
--- a/arch/riscv/kernel/cpu_ops.c
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -13,7 +13,7 @@
 #include <asm/sbi.h>
 #include <asm/smp.h>
 
-const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+const struct cpu_operations *cpu_ops __ro_after_init = &cpu_ops_spinwait;
 
 extern const struct cpu_operations cpu_ops_sbi;
 #ifndef CONFIG_RISCV_BOOT_SPINWAIT
@@ -22,14 +22,12 @@ const struct cpu_operations cpu_ops_spinwait = {
 };
 #endif
 
-void __init cpu_set_ops(int cpuid)
+void __init cpu_set_ops(void)
 {
 #if IS_ENABLED(CONFIG_RISCV_SBI)
 	if (sbi_probe_extension(SBI_EXT_HSM)) {
-		if (!cpuid)
-			pr_info("SBI HSM extension detected\n");
-		cpu_ops[cpuid] = &cpu_ops_sbi;
-	} else
+		pr_info("SBI HSM extension detected\n");
+		cpu_ops = &cpu_ops_sbi;
+	}
 #endif
-		cpu_ops[cpuid] = &cpu_ops_spinwait;
 }
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 40420afbb1a09..45dd4035416ef 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -81,7 +81,7 @@ static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	if (cpu_has_hotplug(cpu))
-		cpu_ops[cpu]->cpu_stop();
+		cpu_ops->cpu_stop();
 #endif
 
 	for(;;)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 5551945255cdc..519b6bd946e5d 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -166,25 +166,22 @@ void __init setup_smp(void)
 {
 	int cpuid;
 
-	cpu_set_ops(0);
+	cpu_set_ops();
 
 	if (acpi_disabled)
 		of_parse_and_init_cpus();
 	else
 		acpi_parse_and_init_cpus();
 
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
+	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++)
+		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID)
 			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 
 static int start_secondary_cpu(int cpu, struct task_struct *tidle)
 {
-	if (cpu_ops[cpu]->cpu_start)
-		return cpu_ops[cpu]->cpu_start(cpu, tidle);
+	if (cpu_ops->cpu_start)
+		return cpu_ops->cpu_start(cpu, tidle);
 
 	return -EOPNOTSUPP;
 }
-- 
GitLab


From 7d748f60a4b82b50bf25fad1bd42d33f049f76aa Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 6 Dec 2023 09:49:46 -0700
Subject: [PATCH 2258/4076] um: net: Fix return type of uml_net_start_xmit()

With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG),
indirect call targets are validated against the expected function
pointer prototype to make sure the call target is valid to help mitigate
ROP attacks. If they are not identical, there is a failure at run time,
which manifests as either a kernel panic or thread getting killed. A
warning in clang aims to catch these at compile time, which reveals:

  arch/um/drivers/net_kern.c:353:21: warning: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Wincompatible-function-pointer-types-strict]
    353 |         .ndo_start_xmit         = uml_net_start_xmit,
        |                                   ^~~~~~~~~~~~~~~~~~
  1 warning generated.

->ndo_start_xmit() in 'struct net_device_ops' expects a return type of
'netdev_tx_t', not 'int'. Adjust the return type of uml_net_start_xmit()
to match the prototype's to resolve the warning. While UML does not
currently implement support for kCFI, it could in the future, which
means this warning becomes a fatal CFI failure at run time.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202310031340.v1vPh207-lkp@intel.com/
Acked-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/drivers/net_kern.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 3d7836c465070..cabcc501b448a 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -204,7 +204,7 @@ static int uml_net_close(struct net_device *dev)
 	return 0;
 }
 
-static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct uml_net_private *lp = netdev_priv(dev);
 	unsigned long flags;
-- 
GitLab


From abe4eaa8618bb36c2b33e9cdde0499296a23448c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 25 Oct 2023 22:45:05 +0200
Subject: [PATCH 2259/4076] um: time-travel: fix time corruption

In 'basic' time-travel mode (without =inf-cpu or =ext), we
still get timer interrupts. These can happen at arbitrary
points in time, i.e. while in timer_read(), which pushes
time forward just a little bit. Then, if we happen to get
the interrupt after calculating the new time to push to,
but before actually finishing that, the interrupt will set
the time to a value that's incompatible with the forward,
and we'll crash because time goes backwards when we do the
forwarding.

Fix this by reading the time_travel_time, calculating the
adjustment, and doing the adjustment all with interrupts
disabled.

Reported-by: Vincent Whitchurch <Vincent.Whitchurch@axis.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/kernel/time.c | 32 +++++++++++++++++++++++++++-----
 1 file changed, 27 insertions(+), 5 deletions(-)

diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index fddd1dec27e6d..3e270da6b6f67 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -432,9 +432,29 @@ static void time_travel_update_time(unsigned long long next, bool idle)
 	time_travel_del_event(&ne);
 }
 
+static void time_travel_update_time_rel(unsigned long long offs)
+{
+	unsigned long flags;
+
+	/*
+	 * Disable interrupts before calculating the new time so
+	 * that a real timer interrupt (signal) can't happen at
+	 * a bad time e.g. after we read time_travel_time but
+	 * before we've completed updating the time.
+	 */
+	local_irq_save(flags);
+	time_travel_update_time(time_travel_time + offs, false);
+	local_irq_restore(flags);
+}
+
 void time_travel_ndelay(unsigned long nsec)
 {
-	time_travel_update_time(time_travel_time + nsec, false);
+	/*
+	 * Not strictly needed to use _rel() version since this is
+	 * only used in INFCPU/EXT modes, but it doesn't hurt and
+	 * is more readable too.
+	 */
+	time_travel_update_time_rel(nsec);
 }
 EXPORT_SYMBOL(time_travel_ndelay);
 
@@ -568,7 +588,11 @@ static void time_travel_set_start(void)
 #define time_travel_time 0
 #define time_travel_ext_waiting 0
 
-static inline void time_travel_update_time(unsigned long long ns, bool retearly)
+static inline void time_travel_update_time(unsigned long long ns, bool idle)
+{
+}
+
+static inline void time_travel_update_time_rel(unsigned long long offs)
 {
 }
 
@@ -720,9 +744,7 @@ static u64 timer_read(struct clocksource *cs)
 		 */
 		if (!irqs_disabled() && !in_interrupt() && !in_softirq() &&
 		    !time_travel_ext_waiting)
-			time_travel_update_time(time_travel_time +
-						TIMER_MULTIPLIER,
-						false);
+			time_travel_update_time_rel(TIMER_MULTIPLIER);
 		return time_travel_time / TIMER_MULTIPLIER;
 	}
 
-- 
GitLab


From 32a84cfc6caf830431375c5182391284986d4066 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Winiarski?= <michal.winiarski@intel.com>
Date: Fri, 20 Oct 2023 11:21:58 +0200
Subject: [PATCH 2260/4076] arch: um: Add Clang coverage support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clang uses a different set of command line arguments for enabling
coverage.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Tested-by: David Gow <davidgow@google.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/Makefile-skas | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/um/Makefile-skas b/arch/um/Makefile-skas
index ac35de5316a6a..67323b0289999 100644
--- a/arch/um/Makefile-skas
+++ b/arch/um/Makefile-skas
@@ -4,7 +4,12 @@
 #
 
 GPROF_OPT += -pg
+
+ifdef CONFIG_CC_IS_CLANG
+GCOV_OPT += -fprofile-instr-generate -fcoverage-mapping
+else
 GCOV_OPT += -fprofile-arcs -ftest-coverage
+endif
 
 CFLAGS-$(CONFIG_GCOV) += $(GCOV_OPT)
 CFLAGS-$(CONFIG_GPROF) += $(GPROF_OPT)
-- 
GitLab


From c2e64baac4f36f7e0365218c7523bb9ba4639250 Mon Sep 17 00:00:00 2001
From: Thierry Reding <thierry.reding@gmail.com>
Date: Thu, 21 Dec 2023 11:08:02 +0100
Subject: [PATCH 2261/4076] pwm: Add pwm_apply_state() compatibility stub
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to make the transition to the new pwm_apply_might_sleep() a bit
smoother, add a compatibility stub. This will prevent new calls to the
old function introduced via other subsystems from breaking builds. Once
the next merge window has closed we can take another stab at removing
the stub.

Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 5dd665d8c909e..2a5e1154652e8 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -537,6 +537,13 @@ static inline void pwm_apply_args(struct pwm_device *pwm)
 	pwm_apply_might_sleep(pwm, &state);
 }
 
+/* only for backwards-compatibility, new code should not use this */
+static inline int pwm_apply_state(struct pwm_device *pwm,
+				  const struct pwm_state *state)
+{
+	return pwm_apply_might_sleep(pwm, state);
+}
+
 struct pwm_lookup {
 	struct list_head list;
 	const char *provider;
-- 
GitLab


From d73f444d06fb8a42a5c0623453f3ea1fe9880229 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:06:20 -0800
Subject: [PATCH 2262/4076] pwm: linux/pwm.h: fix Excess kernel-doc description
 warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the @pwm: line to prevent the kernel-doc warning:

include/linux/pwm.h:87: warning: Excess struct member 'pwm' description in 'pwm_device'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc:  <linux-pwm@vger.kernel.org>
Fixes: f3e25e68ceb2 ("pwm: Drop unused member "pwm" from struct pwm_device")
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 2a5e1154652e8..fcc2c4496f731 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -69,7 +69,6 @@ struct pwm_state {
  * @label: name of the PWM device
  * @flags: flags associated with the PWM device
  * @hwpwm: per-chip relative index of the PWM device
- * @pwm: global index of the PWM device
  * @chip: PWM chip providing this PWM device
  * @args: PWM arguments
  * @state: last applied state
-- 
GitLab


From fe814b5b0f3042f1a583734497e726ee53783cc1 Mon Sep 17 00:00:00 2001
From: Avichal Rakesh <arakesh@google.com>
Date: Thu, 4 Jan 2024 13:50:08 -0800
Subject: [PATCH 2263/4076] usb: gadget: uvc: Fix use are free during STREAMOFF

There is a path that may lead to freed memory being referenced,
causing kernel panics.

The kernel panic has the following stack trace:

Workqueue: uvcgadget uvcg_video_pump.c51fb85fece46625450f86adbf92c56c.cfi_jt
pstate: 60c00085 (nZCv daIf +PAN +UAO -TCO BTYPE=--)
pc : __list_del_entry_valid+0xc0/0xd4
lr : __list_del_entry_valid+0xc0/0xd4
Call trace:
  __list_del_entry_valid+0xc0/0xd4
  uvc_video_free_request+0x60/0x98
  uvcg_video_pump+0x1cc/0x204
  process_one_work+0x21c/0x4b8
  worker_thread+0x29c/0x574
  kthread+0x158/0x1b0
  ret_from_fork+0x10/0x30

The root cause is that uvcg_video_usb_req_queue frees the uvc_request
if is_enabled is false and returns an error status. video_pump also
frees the associated request if uvcg_video_usb_req_queue returns an
error status, leading to double free and accessing garbage memory.

To fix the issue, this patch removes freeing logic from
uvcg_video_usb_req_queue, and lets the callers to the function handle
queueing errors as they see fit.

Fixes: 6acba0345b68 ("usb:gadget:uvc Do not use worker thread to pump isoc usb requests")
Tested-by: Avichal Rakesh <arakesh@google.com>
Signed-off-by: Avichal Rakesh <arakesh@google.com>
Link: https://lore.kernel.org/r/20240104215009.2252452-1-arakesh@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc_video.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 98ba524c27f50..7f18dc471be38 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -276,10 +276,9 @@ static int uvcg_video_usb_req_queue(struct uvc_video *video,
 	bool is_bulk = video->max_payload_size;
 	struct list_head *list = NULL;
 
-	if (!video->is_enabled) {
-		uvc_video_free_request(req->context, video->ep);
+	if (!video->is_enabled)
 		return -ENODEV;
-	}
+
 	if (queue_to_ep) {
 		struct uvc_request *ureq = req->context;
 		/*
@@ -464,8 +463,15 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 		 * and this thread for isoc endpoints.
 		 */
 		ret = uvcg_video_usb_req_queue(video, to_queue, !is_bulk);
-		if (ret < 0)
+		if (ret < 0) {
+			/*
+			 * Endpoint error, but the stream is still enabled.
+			 * Put request back in req_free for it to be cleaned
+			 * up later.
+			 */
 			uvcg_queue_cancel(queue, 0);
+			list_add_tail(&to_queue->list, &video->req_free);
+		}
 	} else {
 		uvc_video_free_request(ureq, ep);
 	}
-- 
GitLab


From 9866dc4314c6c858e451933f965d64532aec00a9 Mon Sep 17 00:00:00 2001
From: Avichal Rakesh <arakesh@google.com>
Date: Thu, 4 Jan 2024 13:50:09 -0800
Subject: [PATCH 2264/4076] usb: gadget: uvc: Remove nested locking

When handling error status from uvcg_video_usb_req_queue,
uvc_video_complete currently calls uvcg_queue_cancel with
video->req_lock held. uvcg_queue_cancel internally locks
queue->irqlock, which nests queue->irqlock inside
video->req_lock. This isn't a functional bug at the
moment, but does open up possibilities for ABBA
deadlocks in the future.

This patch fixes the accidental nesting by dropping
video->req_lock before calling uvcg_queue_cancel.

Fixes: 6acba0345b68 ("usb:gadget:uvc Do not use worker thread to pump isoc usb requests")
Signed-off-by: Avichal Rakesh <arakesh@google.com>
Link: https://lore.kernel.org/r/20240104215009.2252452-2-arakesh@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc_video.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 7f18dc471be38..dd3241fc6939d 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -469,13 +469,15 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 			 * Put request back in req_free for it to be cleaned
 			 * up later.
 			 */
-			uvcg_queue_cancel(queue, 0);
 			list_add_tail(&to_queue->list, &video->req_free);
 		}
 	} else {
 		uvc_video_free_request(ureq, ep);
+		ret = 0;
 	}
 	spin_unlock_irqrestore(&video->req_lock, flags);
+	if (ret < 0)
+		uvcg_queue_cancel(queue, 0);
 }
 
 static int
-- 
GitLab


From 2dd23cc4d0e6aa55cf9fb3b05f2f4165b01de81c Mon Sep 17 00:00:00 2001
From: Gui-Dong Han <2045gemini@gmail.com>
Date: Fri, 5 Jan 2024 13:24:12 +0800
Subject: [PATCH 2265/4076] usb: mon: Fix atomicity violation in
 mon_bin_vma_fault

In mon_bin_vma_fault():
    offset = vmf->pgoff << PAGE_SHIFT;
    if (offset >= rp->b_size)
        return VM_FAULT_SIGBUS;
    chunk_idx = offset / CHUNK_SIZE;
    pageptr = rp->b_vec[chunk_idx].pg;
The code is executed without holding any lock.

In mon_bin_vma_close():
    spin_lock_irqsave(&rp->b_lock, flags);
    rp->mmap_active--;
    spin_unlock_irqrestore(&rp->b_lock, flags);

In mon_bin_ioctl():
    spin_lock_irqsave(&rp->b_lock, flags);
    if (rp->mmap_active) {
        ...
    } else {
        ...
        kfree(rp->b_vec);
        rp->b_vec  = vec;
        rp->b_size = size;
        ...
    }
    spin_unlock_irqrestore(&rp->b_lock, flags);

Concurrent execution of mon_bin_vma_fault() with mon_bin_vma_close() and
mon_bin_ioctl() could lead to atomicity violations. mon_bin_vma_fault()
accesses rp->b_size and rp->b_vec without locking, risking array
out-of-bounds access or use-after-free bugs due to possible modifications
in mon_bin_ioctl().

This possible bug is found by an experimental static analysis tool
developed by our team, BassCheck[1]. This tool analyzes the locking APIs
to extract function pairs that can be concurrently executed, and then
analyzes the instructions in the paired functions to identify possible
concurrency bugs including data races and atomicity violations. The above
possible bug is reported when our tool analyzes the source code of
Linux 6.2.

To address this issue, it is proposed to add a spin lock pair in
mon_bin_vma_fault() to ensure atomicity. With this patch applied, our tool
never reports the possible bug, with the kernel configuration allyesconfig
for x86_64. Due to the lack of associated hardware, we cannot test the
patch in runtime testing, and just verify it according to the code logic.

[1] https://sites.google.com/view/basscheck/

Fixes: 19e6317d24c2 ("usb: mon: Fix a deadlock in usbmon between ...")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Gui-Dong Han <2045gemini@gmail.com>
Link: https://lore.kernel.org/r/20240105052412.9377-1-2045gemini@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/mon/mon_bin.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c
index 9ca9305243fe5..4e30de4db1c0a 100644
--- a/drivers/usb/mon/mon_bin.c
+++ b/drivers/usb/mon/mon_bin.c
@@ -1250,14 +1250,19 @@ static vm_fault_t mon_bin_vma_fault(struct vm_fault *vmf)
 	struct mon_reader_bin *rp = vmf->vma->vm_private_data;
 	unsigned long offset, chunk_idx;
 	struct page *pageptr;
+	unsigned long flags;
 
+	spin_lock_irqsave(&rp->b_lock, flags);
 	offset = vmf->pgoff << PAGE_SHIFT;
-	if (offset >= rp->b_size)
+	if (offset >= rp->b_size) {
+		spin_unlock_irqrestore(&rp->b_lock, flags);
 		return VM_FAULT_SIGBUS;
+	}
 	chunk_idx = offset / CHUNK_SIZE;
 	pageptr = rp->b_vec[chunk_idx].pg;
 	get_page(pageptr);
 	vmf->page = pageptr;
+	spin_unlock_irqrestore(&rp->b_lock, flags);
 	return 0;
 }
 
-- 
GitLab


From 159956f34ede363e67a87bea840937e242293e91 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 26 Dec 2023 22:52:40 +0900
Subject: [PATCH 2266/4076] kbuild: deb-pkg: set DEB_* variables if
 debian/rules is directly executed

Since commit 491b146d4c13 ("kbuild: builddeb: Eliminate debian/arch
use"), direct execution of debian/rules results in the following error:

  dpkg-architecture: error: unknown option 'DEB_HOST_MULTIARCH'

The current code:

  dpkg-architecture -a$DEB_HOST_ARCH -qDEB_HOST_MULTIARCH

... does not look sensible because:

 - For this code to work correctly, DEB_HOST_ARCH must be pre-defined,
   which is true when the packages are built via dpkg-buildpackage.
   In this case, DEB_HOST_MULTIARCH is also likely defined, hence there
   is no need to query DEB_HOST_MULTIARCH in the first place.

 - If DEB_HOST_MULTIARCH is undefined, DEB_HOST_ARCH is likely undefined
   too. So, you cannot query DEB_HOST_MULTIARCH in this way. This is
   mostly the case where debian/rules is directly executed.

When debian/rules is directly executed, querying DEB_HOST_MUCHARCH is
not enough because we need to know DEB_{BUILD,HOST}_GNU_TYPE as well.

All DEB_* variables are defined when the package build is initiated by
dpkg-buildpackage, but otherwise, let's call dpkg-architecture to set
all DEB_* environment variables.

This requires dpkg 1.20.6 or newer because --print-format option
was added in dpkg commit 7c54fa2b232e ("dpkg-architecture: Add a
--print-format option").

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/builddeb     |  5 ++---
 scripts/package/debian/rules | 13 ++++++++++++-
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 2fe51e6919da3..2eb4910f0ef34 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -171,9 +171,8 @@ install_libc_headers () {
 
 	# move asm headers to /usr/include/<libc-machine>/asm to match the structure
 	# used by Debian-based distros (to support multi-arch)
-	host_arch=$(dpkg-architecture -a$DEB_HOST_ARCH -qDEB_HOST_MULTIARCH)
-	mkdir $pdir/usr/include/$host_arch
-	mv $pdir/usr/include/asm $pdir/usr/include/$host_arch/
+	mkdir "$pdir/usr/include/${DEB_HOST_MULTIARCH}"
+	mv "$pdir/usr/include/asm" "$pdir/usr/include/${DEB_HOST_MULTIARCH}"
 }
 
 rm -f debian/files
diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules
index 529b71b55efa5..3268340386dec 100755
--- a/scripts/package/debian/rules
+++ b/scripts/package/debian/rules
@@ -30,5 +30,16 @@ build-arch:
 
 .PHONY: clean
 clean:
-	rm -rf debian/files debian/linux-*
+	rm -rf debian/files debian/linux-* debian/deb-env.vars*
 	$(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) clean
+
+# If DEB_HOST_ARCH is empty, it is likely that debian/rules was executed
+# directly. Run 'dpkg-architecture --print-set --print-format=make' to
+# generate a makefile construct that exports all DEB_* variables.
+ifndef DEB_HOST_ARCH
+include debian/deb-env.vars
+
+debian/deb-env.vars:
+	dpkg-architecture -a$$(cat debian/arch) --print-set --print-format=make > $@.tmp
+	mv $@.tmp $@
+endif
-- 
GitLab


From eaf80f7f2c9c5f08d76858ec32addfcfe64ce58e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 26 Dec 2023 22:52:41 +0900
Subject: [PATCH 2267/4076] kbuild: deb-pkg: allow to run debian/rules from
 output directory

'make O=... deb-pkg' creates the debian directory in the output
directory. However, currently it is impossible to run debian/rules
created in the separate output directory.

This commit delays the $(srctree) expansion by escaping '$' and by
quoting the entire command, making it possible to run debian/rules in
the output directory.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/debian/rules | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules
index 3268340386dec..6ba756d246de1 100755
--- a/scripts/package/debian/rules
+++ b/scripts/package/debian/rules
@@ -19,7 +19,7 @@ binary: binary-arch binary-indep
 binary-indep: build-indep
 binary-arch: build-arch
 	$(MAKE) -f $(srctree)/Makefile $(make-opts) \
-	run-command KBUILD_RUN_COMMAND=+$(srctree)/scripts/package/builddeb
+	run-command KBUILD_RUN_COMMAND='+$$(srctree)/scripts/package/builddeb'
 
 .PHONY: build build-indep build-arch
 build: build-arch build-indep
-- 
GitLab


From 68e262f8017d7fa5a9ea1ef21cbaa0fd5334ecd5 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 26 Dec 2023 22:52:42 +0900
Subject: [PATCH 2268/4076] kbuild: deb-pkg: remove unneeded '-f
 $srctree/Makefile' in debian/rules

This is unneeded because the Makefile in the output directory wraps
the top-level Makefile in the srctree.

Just run $(MAKE) irrespective of the build location.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/debian/rules | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules
index 6ba756d246de1..0ffa806bbd789 100755
--- a/scripts/package/debian/rules
+++ b/scripts/package/debian/rules
@@ -3,8 +3,6 @@
 
 include debian/rules.vars
 
-srctree ?= .
-
 ifneq (,$(filter-out parallel=1,$(filter parallel=%,$(DEB_BUILD_OPTIONS))))
     NUMJOBS = $(patsubst parallel=%,%,$(filter parallel=%,$(DEB_BUILD_OPTIONS)))
     MAKEFLAGS += -j$(NUMJOBS)
@@ -18,20 +16,20 @@ make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) KBUILD_BUILD_VERSION=$(r
 binary: binary-arch binary-indep
 binary-indep: build-indep
 binary-arch: build-arch
-	$(MAKE) -f $(srctree)/Makefile $(make-opts) \
+	$(MAKE) $(make-opts) \
 	run-command KBUILD_RUN_COMMAND='+$$(srctree)/scripts/package/builddeb'
 
 .PHONY: build build-indep build-arch
 build: build-arch build-indep
 build-indep:
 build-arch:
-	$(MAKE) -f $(srctree)/Makefile $(make-opts) \
+	$(MAKE) $(make-opts) \
 	olddefconfig all
 
 .PHONY: clean
 clean:
 	rm -rf debian/files debian/linux-* debian/deb-env.vars*
-	$(MAKE) -f $(srctree)/Makefile ARCH=$(ARCH) clean
+	$(MAKE) ARCH=$(ARCH) clean
 
 # If DEB_HOST_ARCH is empty, it is likely that debian/rules was executed
 # directly. Run 'dpkg-architecture --print-set --print-format=make' to
-- 
GitLab


From 5e73758b43c3defba2578df6d3a53e942fa6b41e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 26 Dec 2023 22:52:43 +0900
Subject: [PATCH 2269/4076] kbuild: deb-pkg: use more debhelper commands in
 builddeb

Commit 36862e14e316 ("kbuild: deb-pkg: use dh_listpackages to know
enabled packages") started to require the debhelper tool suite.

Use more dh_* commands in create_package():

 - dh_installdocs to install copyright
 - dh_installchangelogs to install changelog
 - dh_compress to compress changelog
 - dh_fixperms to replace the raw chmod command
 - dh_gencontrol to replace the raw dpkg-gencontrol command
 - dh_md5sums to record the md5sum of included files
 - dh_builddeb to replace the raw dpkg-deb command

Set DEB_RULES_REQUIRES_ROOT to 'no' in case debian/rules is executed
directly.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/builddeb     | 27 ++++++++++-----------------
 scripts/package/debian/rules |  3 +++
 scripts/package/mkdebian     |  2 +-
 3 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 2eb4910f0ef34..436d55a83ab07 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -26,23 +26,16 @@ if_enabled_echo() {
 
 create_package() {
 	local pname="$1" pdir="$2"
-	local dpkg_deb_opts
-
-	mkdir -m 755 -p "$pdir/DEBIAN"
-	mkdir -p "$pdir/usr/share/doc/$pname"
-	cp debian/copyright "$pdir/usr/share/doc/$pname/"
-	cp debian/changelog "$pdir/usr/share/doc/$pname/changelog.Debian"
-	gzip -n -9 "$pdir/usr/share/doc/$pname/changelog.Debian"
-	sh -c "cd '$pdir'; find . -type f ! -path './DEBIAN/*' -printf '%P\0' \
-		| xargs -r0 md5sum > DEBIAN/md5sums"
-
-	# a+rX in case we are in a restrictive umask environment like 0077
-	# ug-s in case we build in a setuid/setgid directory
-	chmod -R go-w,a+rX,ug-s "$pdir"
-
-	# Create the package
-	dpkg-gencontrol -p$pname -P"$pdir"
-	dpkg-deb --root-owner-group ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS} --build "$pdir" ..
+
+	export DH_OPTIONS="-p${pname} -P${pdir}"
+
+	dh_installdocs
+	dh_installchangelogs
+	dh_compress
+	dh_fixperms
+	dh_gencontrol
+	dh_md5sums
+	dh_builddeb -- ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS}
 }
 
 install_linux_image () {
diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules
index 0ffa806bbd789..7ab31419579f0 100755
--- a/scripts/package/debian/rules
+++ b/scripts/package/debian/rules
@@ -1,6 +1,9 @@
 #!/usr/bin/make -f
 # SPDX-License-Identifier: GPL-2.0-only
 
+# in case debian/rules is executed directly
+export DEB_RULES_REQUIRES_ROOT := no
+
 include debian/rules.vars
 
 ifneq (,$(filter-out parallel=1,$(filter parallel=%,$(DEB_BUILD_OPTIONS))))
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 93a24712b9a1d..070149c985fea 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -193,7 +193,7 @@ Section: kernel
 Priority: optional
 Maintainer: $maintainer
 Rules-Requires-Root: no
-Build-Depends: debhelper
+Build-Depends: debhelper-compat (= 12)
 Build-Depends-Arch: bc, bison, cpio, flex, kmod, libelf-dev:native, libssl-dev:native, rsync
 Homepage: https://www.kernel.org/
 
-- 
GitLab


From 16c36f8864e354952eeeb8449034d63d372f621d Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 26 Dec 2023 23:33:59 +0900
Subject: [PATCH 2270/4076] kbuild: deb-pkg: use build ID instead of debug link
 for dbg package

There are two ways of managing separate debug info files:

 [1] The executable contains the .gnu_debuglink section, which specifies
     the name and the CRC of the separate debug info file.

 [2] The executable contains a build ID, and the corresponding debug info
     file is placed in the .build-id directory.

We could do both, but the former, which 'make deb-pkg' currently does,
results in complicated installation steps because we need to manually
strip the debug sections, create debug links, and re-sign the modules.
Besides, it is not working with module compression.

This commit abandons the approach [1], and instead opts for [2].

Debian kernel commit de26137e2a9f ("Drop not needed extra step to add
debug links") also stopped adding debug links.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/package/builddeb | 32 +++++++++++++-------------------
 1 file changed, 13 insertions(+), 19 deletions(-)

diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 436d55a83ab07..cc8c7a807fcc2 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -49,7 +49,7 @@ install_linux_image () {
 		${MAKE} -f ${srctree}/Makefile INSTALL_DTBS_PATH="${pdir}/usr/lib/linux-image-${KERNELRELEASE}" dtbs_install
 	fi
 
-	${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${pdir}" modules_install
+	${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${pdir}" INSTALL_MOD_STRIP=1 modules_install
 	rm -f "${pdir}/lib/modules/${KERNELRELEASE}/build"
 
 	# Install the kernel
@@ -110,25 +110,21 @@ install_linux_image () {
 
 install_linux_image_dbg () {
 	pdir=$1
-	image_pdir=$2
 
 	rm -rf ${pdir}
 
-	for module in $(find ${image_pdir}/lib/modules/ -name *.ko -printf '%P\n'); do
-		module=lib/modules/${module}
-		mkdir -p $(dirname ${pdir}/usr/lib/debug/${module})
-		# only keep debug symbols in the debug file
-		${OBJCOPY} --only-keep-debug ${image_pdir}/${module} ${pdir}/usr/lib/debug/${module}
-		# strip original module from debug symbols
-		${OBJCOPY} --strip-debug ${image_pdir}/${module}
-		# then add a link to those
-		${OBJCOPY} --add-gnu-debuglink=${pdir}/usr/lib/debug/${module} ${image_pdir}/${module}
-	done
+	# Parse modules.order directly because 'make modules_install' may sign,
+	# compress modules, and then run unneeded depmod.
+	while read -r mod; do
+		mod="${mod%.o}.ko"
+		dbg="${pdir}/usr/lib/debug/lib/modules/${KERNELRELEASE}/kernel/${mod}"
+		buildid=$("${READELF}" -n "${mod}" | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p')
+		link="${pdir}/usr/lib/debug/.build-id/${buildid}.debug"
 
-	# re-sign stripped modules
-	if is_enabled CONFIG_MODULE_SIG_ALL; then
-		${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${image_pdir}" modules_sign
-	fi
+		mkdir -p "${dbg%/*}" "${link%/*}"
+		"${OBJCOPY}" --only-keep-debug "${mod}" "${dbg}"
+		ln -sf --relative "${dbg}" "${link}"
+	done < modules.order
 
 	# Build debug package
 	# Different tools want the image in different locations
@@ -176,9 +172,7 @@ for package in ${packages_enabled}
 do
 	case ${package} in
 	*-dbg)
-		# This must be done after linux-image, that is, we expect the
-		# debug package appears after linux-image in debian/control.
-		install_linux_image_dbg debian/linux-image-dbg debian/linux-image;;
+		install_linux_image_dbg debian/linux-image-dbg;;
 	linux-image-*|user-mode-linux-*)
 		install_linux_image debian/linux-image ${package};;
 	linux-libc-dev)
-- 
GitLab


From 358c3f8cce6d8294e7ba72199f04771e9bff4b64 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 30 Dec 2023 21:02:52 +0900
Subject: [PATCH 2271/4076] kbuild: deb-pkg: do not search for 'scripts'
 directory under arch/

The 'scripts' directory was searched under arch/${SRCARCH} to copy
arch/ia64/scripts, but commit cf8e8658100d ("arch: Remove Itanium
(IA-64) architecture") removed arch/ia64/ entirely.

There is another 'scripts' directory in arch/um/, but this script
is never executed with SRCARCH=um because UML does not support the
linux-headers package.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/package/install-extmod-build | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build
index 8a7051fad0878..76e0765dfcd6e 100755
--- a/scripts/package/install-extmod-build
+++ b/scripts/package/install-extmod-build
@@ -20,7 +20,7 @@ mkdir -p "${destdir}"
 	find "arch/${SRCARCH}" -maxdepth 1 -name 'Makefile*'
 	find include scripts -type f -o -type l
 	find "arch/${SRCARCH}" -name Kbuild.platforms -o -name Platform
-	find "arch/${SRCARCH}" -name include -o -name scripts -type d
+	find "arch/${SRCARCH}" -name include -type d
 ) | tar -c -f - -C "${srctree}" -T - | tar -xf - -C "${destdir}"
 
 {
-- 
GitLab


From 1154e4304174e0ab4a90d5bae3fd5548aa343472 Mon Sep 17 00:00:00 2001
From: Jai Luthra <j-luthra@ti.com>
Date: Fri, 5 Jan 2024 14:36:54 +0530
Subject: [PATCH 2272/4076] usb: typec: tipd: Separate reset for TPS6598x

Some platforms like SK-AM62, SK-AM62A cannot boot up to prompt if
TPS6598x is cold-reset during unconditionally on probe failures by
sending "GAID" sequence.

The probe can fail initially because USB0 remote-endpoint may not be
probed yet, which defines the usb-role-switch property.

Fixes: d49f90822015 ("usb: typec: tipd: add init and reset functions to tipd_data")
Closes: https://lore.kernel.org/linux-usb/vmngazj6si7xxss7txenezkcukqje2glhvvs7ipdcx3vjiqvlk@ohmmhhhlryws/
Signed-off-by: Jai Luthra <j-luthra@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20240105-next-tps-fix-v1-1-158cabaec168@ti.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tipd/core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index a956eb976906a..8ba2aa05db519 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -1223,11 +1223,16 @@ static int cd321x_reset(struct tps6598x *tps)
 	return 0;
 }
 
-static int tps6598x_reset(struct tps6598x *tps)
+static int tps25750_reset(struct tps6598x *tps)
 {
 	return tps6598x_exec_cmd_tmo(tps, "GAID", 0, NULL, 0, NULL, 2000, 0);
 }
 
+static int tps6598x_reset(struct tps6598x *tps)
+{
+	return 0;
+}
+
 static int
 tps25750_register_port(struct tps6598x *tps, struct fwnode_handle *fwnode)
 {
@@ -1545,7 +1550,7 @@ static const struct tipd_data tps25750_data = {
 	.trace_status = trace_tps25750_status,
 	.apply_patch = tps25750_apply_patch,
 	.init = tps25750_init,
-	.reset = tps6598x_reset,
+	.reset = tps25750_reset,
 };
 
 static const struct of_device_id tps6598x_of_match[] = {
-- 
GitLab


From 933bb7b878ddd0f8c094db45551a7daddf806e00 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Thu, 4 Jan 2024 18:07:12 +0100
Subject: [PATCH 2273/4076] usb: typec: tipd: fix use of device-specific init
 function

The current implementation supports device-pecific callbacks for the
init function with a function pointer. The patch that introduced this
feature did not update one call to the tps25750 init function to turn it
into a call with the new pointer in the resume function.

Fixes: d49f90822015 ("usb: typec: tipd: add init and reset functions to tipd_data")
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Suggested-by: Roger Quadros <rogerq@kernel.org>
Link: https://lore.kernel.org/r/20240104-dev_spec_init-v1-1-1a57e7fd8cc8@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tipd/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 8ba2aa05db519..0717cfcd9f8ca 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -1500,7 +1500,7 @@ static int __maybe_unused tps6598x_resume(struct device *dev)
 		return ret;
 
 	if (ret == TPS_MODE_PTCH) {
-		ret = tps25750_init(tps);
+		ret = tps->data->init(tps);
 		if (ret)
 			return ret;
 	}
-- 
GitLab


From c17d8847c3bef9e4fe4aef34edecc29cee3cd06f Mon Sep 17 00:00:00 2001
From: Chen Haonan <chen.haonan2@zte.com.cn>
Date: Fri, 15 Dec 2023 11:04:40 +0100
Subject: [PATCH 2274/4076] ARM: 9331/1: ARM/dma-mapping: replace kzalloc() and
 vzalloc() with kvzalloc()

using kvzalloc() simplifies the code by avoiding the
use of different memory allocation functions for different
situations, making the code more uniform and readable.

Signed-off-by: Chen Haonan <chen.haonan2@zte.com.cn>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
 arch/arm/mm/dma-mapping.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 5409225b4abc0..d688eac6dbc14 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -859,10 +859,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 	int i = 0;
 	int order_idx = 0;
 
-	if (array_size <= PAGE_SIZE)
-		pages = kzalloc(array_size, GFP_KERNEL);
-	else
-		pages = vzalloc(array_size);
+	pages = kvzalloc(array_size, GFP_KERNEL);
 	if (!pages)
 		return NULL;
 
-- 
GitLab


From 3dbb4e3602d217d7139b95a36077a6b7252dc290 Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Thu, 4 Jan 2024 22:57:16 +0800
Subject: [PATCH 2275/4076] ASoC: dt-bindings: move tas2563 from tas2562.yaml
 to tas2781.yaml

Move tas2563 from tas2562.yaml to tas2781.yaml to unbind tas2563 from
tas2562 driver code and bind it to tas2781 driver code, because tas2563
only work in bypass-DSP mode with tas2562 driver. In order to enable DSP
mode for tas2563, it has been moved to tas2781 driver. As to the hardware
part, such as register setting and DSP firmware, all these are stored in
the binary firmware. What tas2781 drivder does is to parse the firmware
and download it to the chip, then power on the chip. So, tas2781 driver
can be resued as tas2563 driver. Only attention will be paid to
downloading corresponding firmware.

Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://msgid.link/r/20240104145721.1398-1-shenghao-ding@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/tas2562.yaml    |  2 -
 .../devicetree/bindings/sound/ti,tas2781.yaml | 78 +++++++++++++++----
 2 files changed, 63 insertions(+), 17 deletions(-)

diff --git a/Documentation/devicetree/bindings/sound/tas2562.yaml b/Documentation/devicetree/bindings/sound/tas2562.yaml
index f01c0dde0cf74..d28c102c0ce7f 100644
--- a/Documentation/devicetree/bindings/sound/tas2562.yaml
+++ b/Documentation/devicetree/bindings/sound/tas2562.yaml
@@ -18,7 +18,6 @@ description: |
 
   Specifications about the audio amplifier can be found at:
     https://www.ti.com/lit/gpn/tas2562
-    https://www.ti.com/lit/gpn/tas2563
     https://www.ti.com/lit/gpn/tas2564
     https://www.ti.com/lit/gpn/tas2110
 
@@ -29,7 +28,6 @@ properties:
   compatible:
     enum:
       - ti,tas2562
-      - ti,tas2563
       - ti,tas2564
       - ti,tas2110
 
diff --git a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
index a69e6c223308e..9762386892495 100644
--- a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
+++ b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml
@@ -5,36 +5,46 @@
 $id: http://devicetree.org/schemas/sound/ti,tas2781.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Texas Instruments TAS2781 SmartAMP
+title: Texas Instruments TAS2563/TAS2781 SmartAMP
 
 maintainers:
   - Shenghao Ding <shenghao-ding@ti.com>
 
-description:
-  The TAS2781 is a mono, digital input Class-D audio amplifier
-  optimized for efficiently driving high peak power into small
-  loudspeakers. An integrated on-chip DSP supports Texas Instruments
-  Smart Amp speaker protection algorithm. The integrated speaker
-  voltage and current sense provides for real time
+description: |
+  The TAS2563/TAS2781 is a mono, digital input Class-D audio
+  amplifier optimized for efficiently driving high peak power into
+  small loudspeakers. An integrated on-chip DSP supports Texas
+  Instruments Smart Amp speaker protection algorithm. The
+  integrated speaker voltage and current sense provides for real time
   monitoring of loudspeaker behavior.
 
-allOf:
-  - $ref: dai-common.yaml#
+  Specifications about the audio amplifier can be found at:
+    https://www.ti.com/lit/gpn/tas2563
+    https://www.ti.com/lit/gpn/tas2781
 
 properties:
   compatible:
-    enum:
-      - ti,tas2781
+    description: |
+      ti,tas2563: 6.1-W Boosted Class-D Audio Amplifier With Integrated
+      DSP and IV Sense, 16/20/24/32bit stereo I2S or multichannel TDM.
+
+      ti,tas2781: 24-V Class-D Amplifier with Real Time Integrated Speaker
+      Protection and Audio Processing, 16/20/24/32bit stereo I2S or
+      multichannel TDM.
+    oneOf:
+      - items:
+          - enum:
+              - ti,tas2563
+          - const: ti,tas2781
+      - enum:
+          - ti,tas2781
 
   reg:
     description:
-      I2C address, in multiple tas2781s case, all the i2c address
+      I2C address, in multiple-AMP case, all the i2c address
       aggregate as one Audio Device to support multiple audio slots.
     maxItems: 8
     minItems: 1
-    items:
-      minimum: 0x38
-      maximum: 0x3f
 
   reset-gpios:
     maxItems: 1
@@ -49,6 +59,44 @@ required:
   - compatible
   - reg
 
+allOf:
+  - $ref: dai-common.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - ti,tas2563
+    then:
+      properties:
+        reg:
+          description:
+            I2C address, in multiple-AMP case, all the i2c address
+            aggregate as one Audio Device to support multiple audio slots.
+          maxItems: 4
+          minItems: 1
+          items:
+            minimum: 0x4c
+            maximum: 0x4f
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - ti,tas2781
+    then:
+      properties:
+        reg:
+          description:
+            I2C address, in multiple-AMP case, all the i2c address
+            aggregate as one Audio Device to support multiple audio slots.
+          maxItems: 8
+          minItems: 1
+          items:
+            minimum: 0x38
+            maximum: 0x3f
+
 additionalProperties: false
 
 examples:
-- 
GitLab


From 645994d21287a1ad2f637818d737f7a3d84e97d7 Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Thu, 4 Jan 2024 22:57:17 +0800
Subject: [PATCH 2276/4076] ASoC: tas2562: move tas2563 from tas2562 driver to
 tas2781 driver

Move tas2563 from tas2562 driver to tas2781 driver to unbind tas2563 from
tas2562 driver code and bind it to tas2781 driver code, because tas2563
only work in bypass-DSP mode with tas2562 driver. In order to enable DSP
mode for tas2563, it has been moved to tas2781 driver. As to the hardware
part, such as register setting and DSP firmware, all these are stored in
the binary firmware. What tas2781 drivder does is to parse the firmware
and download it to the chip, then power on the chip. So, tas2781 driver
can be resued as tas2563 driver. Only attention will be paid to
downloading corresponding firmware.

Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Link: https://msgid.link/r/20240104145721.1398-2-shenghao-ding@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2562.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/sound/soc/codecs/tas2562.c b/sound/soc/codecs/tas2562.c
index 962c2cdfa0174..54561ae598b87 100644
--- a/sound/soc/codecs/tas2562.c
+++ b/sound/soc/codecs/tas2562.c
@@ -59,7 +59,6 @@ struct tas2562_data {
 
 enum tas256x_model {
 	TAS2562,
-	TAS2563,
 	TAS2564,
 	TAS2110,
 };
@@ -721,7 +720,6 @@ static int tas2562_parse_dt(struct tas2562_data *tas2562)
 
 static const struct i2c_device_id tas2562_id[] = {
 	{ "tas2562", TAS2562 },
-	{ "tas2563", TAS2563 },
 	{ "tas2564", TAS2564 },
 	{ "tas2110", TAS2110 },
 	{ }
@@ -770,7 +768,6 @@ static int tas2562_probe(struct i2c_client *client)
 #ifdef CONFIG_OF
 static const struct of_device_id tas2562_of_match[] = {
 	{ .compatible = "ti,tas2562", },
-	{ .compatible = "ti,tas2563", },
 	{ .compatible = "ti,tas2564", },
 	{ .compatible = "ti,tas2110", },
 	{ },
-- 
GitLab


From e9aa44736cb75e901d76ee59d80db1ae79d516f1 Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Thu, 4 Jan 2024 22:57:18 +0800
Subject: [PATCH 2277/4076] ASoC: tas2781: Add tas2563 into header file for DSP
 mode

Move tas2563 from tas2562 header file to tas2781 header file to unbind
tas2563 from tas2562 driver code and bind it to tas2781 driver code,
because tas2563 only work in bypass-DSP mode with tas2562 driver. In
order to enable DSP mode for tas2563, it has been moved to tas2781
driver. As to the hardware part, such as register setting and DSP
firmware, all these are stored in the binary firmware. What tas2781
drivder does is to parse the firmware and download it to the chip,
then power on the chip. So, tas2781 driver can be resued as tas2563
driver. Only attention will be paid to downloading corresponding firmware.

Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Link: https://msgid.link/r/20240104145721.1398-3-shenghao-ding@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/tas2781.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index a6c808b223183..813cf9446a58c 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -1,13 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 //
-// ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier
+// ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier
 //
 // Copyright (C) 2022 - 2023 Texas Instruments Incorporated
 // https://www.ti.com
 //
-// The TAS2781 driver implements a flexible and configurable
+// The TAS2563/TAS2781 driver implements a flexible and configurable
 // algo coefficient setting for one, two, or even multiple
-// TAS2781 chips.
+// TAS2563/TAS2781 chips.
 //
 // Author: Shenghao Ding <shenghao-ding@ti.com>
 // Author: Kevin Lu <kevin-lu@ti.com>
@@ -59,7 +59,8 @@
 #define TASDEVICE_CMD_FIELD_W		0x4
 
 enum audio_device {
-	TAS2781	= 0,
+	TAS2563,
+	TAS2781,
 };
 
 enum device_catlog_id {
-- 
GitLab


From 9f1bcd16e2bd41d758438f1d74e5f2d35f1e8c8e Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Thu, 4 Jan 2024 22:57:19 +0800
Subject: [PATCH 2278/4076] ASoC: tas2781: Add tas2563 into driver

Move tas2563 from tas2562 driver to tas2781 driver to unbind tas2563 from
tas2562 driver code and bind it to tas2781 driver code, because tas2563
only work in bypass-DSP mode with tas2562 driver. In order to enable DSP
mode for tas2563, it has been moved to tas2781 driver. As to the hardware
part, such as register setting and DSP firmware, all these are stored in
the binary firmware. What tas2781 drivder does is to parse the firmware
and download it to the chip, then power on the chip. So, tas2781 driver
can be resued as tas2563 driver. Only attention will be paid to downloading
corresponding firmware.

Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Link: https://msgid.link/r/20240104145721.1398-4-shenghao-ding@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2781-i2c.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c
index 55cd5e3c23a5d..bd5ef4ff96feb 100644
--- a/sound/soc/codecs/tas2781-i2c.c
+++ b/sound/soc/codecs/tas2781-i2c.c
@@ -1,13 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 //
-// ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier
+// ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier
 //
 // Copyright (C) 2022 - 2023 Texas Instruments Incorporated
 // https://www.ti.com
 //
-// The TAS2781 driver implements a flexible and configurable
+// The TAS2563/TAS2781 driver implements a flexible and configurable
 // algo coefficient setting for one, two, or even multiple
-// TAS2781 chips.
+// TAS2563/TAS2781 chips.
 //
 // Author: Shenghao Ding <shenghao-ding@ti.com>
 // Author: Kevin Lu <kevin-lu@ti.com>
@@ -32,6 +32,7 @@
 #include <sound/tas2781-tlv.h>
 
 static const struct i2c_device_id tasdevice_id[] = {
+	{ "tas2563", TAS2563 },
 	{ "tas2781", TAS2781 },
 	{}
 };
@@ -39,6 +40,7 @@ MODULE_DEVICE_TABLE(i2c, tasdevice_id);
 
 #ifdef CONFIG_OF
 static const struct of_device_id tasdevice_of_match[] = {
+	{ .compatible = "ti,tas2563" },
 	{ .compatible = "ti,tas2781" },
 	{},
 };
-- 
GitLab


From 0e4d464cda4c5996402343d4c9e2b6ceec716f93 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 5 Jan 2024 14:57:14 +0000
Subject: [PATCH 2279/4076] netfs: Mark netfs_unbuffered_write_iter_locked()
 static

Mark netfs_unbuffered_write_iter_locked() static as it's only called from
the file in which it is defined.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/direct_write.c | 4 ++--
 fs/netfs/internal.h     | 6 ------
 2 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index aad05f2349a48..b9cbfd6a8a01d 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -27,8 +27,8 @@ static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
  * Perform an unbuffered write where we may have to do an RMW operation on an
  * encrypted file.  This can also be used for direct I/O writes.
  */
-ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
-					   struct netfs_group *netfs_group)
+static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
+						  struct netfs_group *netfs_group)
 {
 	struct netfs_io_request *wreq;
 	unsigned long long start = iocb->ki_pos;
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index d2d63120ac60a..a6dfc88883779 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -26,12 +26,6 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq);
 int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len);
 
-/*
- * direct_write.c
- */
-ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
-					   struct netfs_group *netfs_group);
-
 /*
  * io.c
  */
-- 
GitLab


From 35040410372ca27a33cec8382d42c90b6b6c99f6 Mon Sep 17 00:00:00 2001
From: ChiYuan Huang <cy_huang@richtek.com>
Date: Fri, 29 Dec 2023 09:46:01 +0800
Subject: [PATCH 2280/4076] ASoC: codecs: rtq9128: Fix PM_RUNTIME usage

If 'pm_runtime_resume_and_get' is used, must check the return value to
prevent the active count not matched problem.

Signed-off-by: ChiYuan Huang <cy_huang@richtek.com>
Link: https://msgid.link/r/bebd9e2bed9e0528a7fd9c528d785da02caf4f1a.1703813842.git.cy_huang@richtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rtq9128.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/rtq9128.c b/sound/soc/codecs/rtq9128.c
index c22b047115cc4..bda64f9eeb624 100644
--- a/sound/soc/codecs/rtq9128.c
+++ b/sound/soc/codecs/rtq9128.c
@@ -391,7 +391,11 @@ static int rtq9128_component_probe(struct snd_soc_component *comp)
 	unsigned int val;
 	int i, ret;
 
-	pm_runtime_resume_and_get(comp->dev);
+	ret = pm_runtime_resume_and_get(comp->dev);
+	if (ret < 0) {
+		dev_err(comp->dev, "Failed to resume device (%d)\n", ret);
+		return ret;
+	}
 
 	val = snd_soc_component_read(comp, RTQ9128_REG_EFUSE_DATA);
 
-- 
GitLab


From 415d10ccef712f3ec73cd880c1fef3eb48601c3a Mon Sep 17 00:00:00 2001
From: ChiYuan Huang <cy_huang@richtek.com>
Date: Fri, 29 Dec 2023 09:46:02 +0800
Subject: [PATCH 2281/4076] ASoC: codecs: rtq9128: Fix TDM enable and DAI
 format control flow

To enable TDM mode, the current control flow limits the function
calling order should be 'set_tdm_slot->set_dai_fmt'. But not all
platform sound card like as simeple card to follow this design.
To bypass this limit, adjust the DAI format setting in runtime
'hw_param' callback.

Signed-off-by: ChiYuan Huang <cy_huang@richtek.com>
Link: https://msgid.link/r/c4c8df00d8d179b8b5b39a8521de3a85325c57e8.1703813842.git.cy_huang@richtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rtq9128.c | 67 ++++++++++++++++++++------------------
 1 file changed, 36 insertions(+), 31 deletions(-)

diff --git a/sound/soc/codecs/rtq9128.c b/sound/soc/codecs/rtq9128.c
index bda64f9eeb624..aa3eadecd9746 100644
--- a/sound/soc/codecs/rtq9128.c
+++ b/sound/soc/codecs/rtq9128.c
@@ -59,6 +59,7 @@
 
 struct rtq9128_data {
 	struct gpio_desc *enable;
+	unsigned int daifmt;
 	int tdm_slots;
 	int tdm_slot_width;
 	bool tdm_input_data2_select;
@@ -441,10 +442,7 @@ static const struct snd_soc_component_driver rtq9128_comp_driver = {
 static int rtq9128_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 {
 	struct rtq9128_data *data = snd_soc_dai_get_drvdata(dai);
-	struct snd_soc_component *comp = dai->component;
 	struct device *dev = dai->dev;
-	unsigned int audfmt, fmtval;
-	int ret;
 
 	dev_dbg(dev, "%s: fmt 0x%8x\n", __func__, fmt);
 
@@ -454,35 +452,10 @@ static int rtq9128_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		return -EINVAL;
 	}
 
-	fmtval = fmt & SND_SOC_DAIFMT_FORMAT_MASK;
-	if (data->tdm_slots && fmtval != SND_SOC_DAIFMT_DSP_A && fmtval != SND_SOC_DAIFMT_DSP_B) {
-		dev_err(dev, "TDM is used, format only support DSP_A or DSP_B\n");
-		return -EINVAL;
-	}
+	/* Store here and will be used in runtime hw_params for DAI format setting */
+	data->daifmt = fmt;
 
-	switch (fmtval) {
-	case SND_SOC_DAIFMT_I2S:
-		audfmt = 8;
-		break;
-	case SND_SOC_DAIFMT_LEFT_J:
-		audfmt = 9;
-		break;
-	case SND_SOC_DAIFMT_RIGHT_J:
-		audfmt = 10;
-		break;
-	case SND_SOC_DAIFMT_DSP_A:
-		audfmt = data->tdm_slots ? 12 : 11;
-		break;
-	case SND_SOC_DAIFMT_DSP_B:
-		audfmt = data->tdm_slots ? 4 : 3;
-		break;
-	default:
-		dev_err(dev, "Unsupported format 0x%8x\n", fmt);
-		return -EINVAL;
-	}
-
-	ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDFMT_MASK, audfmt);
-	return ret < 0 ? ret : 0;
+	return 0;
 }
 
 static int rtq9128_dai_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
@@ -558,10 +531,38 @@ static int rtq9128_dai_hw_params(struct snd_pcm_substream *stream, struct snd_pc
 	unsigned int width, slot_width, bitrate, audbit, dolen;
 	struct snd_soc_component *comp = dai->component;
 	struct device *dev = dai->dev;
+	unsigned int fmtval, audfmt;
 	int ret;
 
 	dev_dbg(dev, "%s: width %d\n", __func__, params_width(param));
 
+	fmtval = FIELD_GET(SND_SOC_DAIFMT_FORMAT_MASK, data->daifmt);
+	if (data->tdm_slots && fmtval != SND_SOC_DAIFMT_DSP_A && fmtval != SND_SOC_DAIFMT_DSP_B) {
+		dev_err(dev, "TDM is used, format only support DSP_A or DSP_B\n");
+		return -EINVAL;
+	}
+
+	switch (fmtval) {
+	case SND_SOC_DAIFMT_I2S:
+		audfmt = 8;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		audfmt = 9;
+		break;
+	case SND_SOC_DAIFMT_RIGHT_J:
+		audfmt = 10;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		audfmt = data->tdm_slots ? 12 : 11;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		audfmt = data->tdm_slots ? 4 : 3;
+		break;
+	default:
+		dev_err(dev, "Unsupported format 0x%8x\n", fmtval);
+		return -EINVAL;
+	}
+
 	switch (width = params_width(param)) {
 	case 16:
 		audbit = 0;
@@ -615,6 +616,10 @@ static int rtq9128_dai_hw_params(struct snd_pcm_substream *stream, struct snd_pc
 		return -EINVAL;
 	}
 
+	ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDFMT_MASK, audfmt);
+	if (ret < 0)
+		return ret;
+
 	ret = snd_soc_component_write_field(comp, RTQ9128_REG_I2S_OPT, RTQ9128_AUDBIT_MASK, audbit);
 	if (ret < 0)
 		return ret;
-- 
GitLab


From 4088e389476e3baababf9b22f34b9d8b3e557344 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 5 Jan 2024 14:55:52 +0000
Subject: [PATCH 2282/4076] netfs: Count DIO writes

Provide a counter for DIO writes to match that for DIO reads.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/direct_write.c |  1 +
 fs/netfs/internal.h     |  1 +
 fs/netfs/stats.c        | 11 +++++++----
 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index b9cbfd6a8a01d..60a40d293c87f 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -140,6 +140,7 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
 
 	trace_netfs_write_iter(iocb, from);
+	netfs_stat(&netfs_n_rh_dio_write);
 
 	ret = netfs_start_io_direct(inode);
 	if (ret < 0)
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index a6dfc88883779..3f9620d0fa63d 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -104,6 +104,7 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb);
  */
 #ifdef CONFIG_NETFS_STATS
 extern atomic_t netfs_n_rh_dio_read;
+extern atomic_t netfs_n_rh_dio_write;
 extern atomic_t netfs_n_rh_readahead;
 extern atomic_t netfs_n_rh_readpage;
 extern atomic_t netfs_n_rh_rreq;
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index 15fd5c3f0f392..42db36528d921 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -10,6 +10,7 @@
 #include "internal.h"
 
 atomic_t netfs_n_rh_dio_read;
+atomic_t netfs_n_rh_dio_write;
 atomic_t netfs_n_rh_readahead;
 atomic_t netfs_n_rh_readpage;
 atomic_t netfs_n_rh_rreq;
@@ -37,14 +38,13 @@ atomic_t netfs_n_wh_write_failed;
 
 int netfs_stats_show(struct seq_file *m, void *v)
 {
-	seq_printf(m, "Netfs  : DR=%u RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+	seq_printf(m, "Netfs  : DR=%u DW=%u RA=%u RP=%u WB=%u WBZ=%u\n",
 		   atomic_read(&netfs_n_rh_dio_read),
+		   atomic_read(&netfs_n_rh_dio_write),
 		   atomic_read(&netfs_n_rh_readahead),
 		   atomic_read(&netfs_n_rh_readpage),
 		   atomic_read(&netfs_n_rh_write_begin),
-		   atomic_read(&netfs_n_rh_write_zskip),
-		   atomic_read(&netfs_n_rh_rreq),
-		   atomic_read(&netfs_n_rh_sreq));
+		   atomic_read(&netfs_n_rh_write_zskip));
 	seq_printf(m, "Netfs  : ZR=%u sh=%u sk=%u\n",
 		   atomic_read(&netfs_n_rh_zero),
 		   atomic_read(&netfs_n_rh_short_read),
@@ -66,6 +66,9 @@ int netfs_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&netfs_n_wh_write),
 		   atomic_read(&netfs_n_wh_write_done),
 		   atomic_read(&netfs_n_wh_write_failed));
+	seq_printf(m, "Netfs  : rr=%u sr=%u\n",
+		   atomic_read(&netfs_n_rh_rreq),
+		   atomic_read(&netfs_n_rh_sreq));
 	return fscache_stats_show(m);
 }
 EXPORT_SYMBOL(netfs_stats_show);
-- 
GitLab


From 21822553a5f424892c12d1664b3c1235b095c6c6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Winiarski?= <michal.winiarski@intel.com>
Date: Fri, 20 Oct 2023 11:21:59 +0200
Subject: [PATCH 2283/4076] Documentation: kunit: Add clang UML coverage
 example
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

LLVM-based toolchain is using a different set of tools for coverage.
Add an example that produces output in lcov format.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: David Gow <davidgow@google.com>
[rw: Added spelling fixes from David Gow]
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 Documentation/dev-tools/kunit/running_tips.rst | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/Documentation/dev-tools/kunit/running_tips.rst b/Documentation/dev-tools/kunit/running_tips.rst
index 766f9cdea0fad..221c730b9cb25 100644
--- a/Documentation/dev-tools/kunit/running_tips.rst
+++ b/Documentation/dev-tools/kunit/running_tips.rst
@@ -139,6 +139,17 @@ If your installed version of gcc doesn't work, you can tweak the steps:
 	$ ./tools/testing/kunit/kunit.py run --make_options=CC=/usr/bin/gcc-6
 	$ lcov -t "my_kunit_tests" -o coverage.info -c -d .kunit/ --gcov-tool=/usr/bin/gcov-6
 
+Alternatively, LLVM-based toolchains can also be used:
+
+.. code-block:: bash
+
+	# Build with LLVM and append coverage options to the current config
+	$ ./tools/testing/kunit/kunit.py run --make_options LLVM=1 --kunitconfig=.kunit/ --kunitconfig=tools/testing/kunit/configs/coverage_uml.config
+	$ llvm-profdata merge -sparse default.profraw -o default.profdata
+	$ llvm-cov export --format=lcov .kunit/vmlinux -instr-profile default.profdata > coverage.info
+	# The coverage.info file is in lcov-compatible format and it can be used to e.g. generate HTML report
+	$ genhtml -o /tmp/coverage_html coverage.info
+
 
 Running tests manually
 ======================
-- 
GitLab


From 1ca1443570e4085c180ecc657d319c21b22a76f6 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:46 +0100
Subject: [PATCH 2284/4076] um: Rely on PTRACE_SETREGSET to set FS/GS base
 registers

These registers are saved/restored together with the other general
registers using ptrace. In arch_set_tls we then just need to set the
register and it will be synced back normally.

Most of this logic was introduced in commit f355559cf7845 ("[PATCH] uml:
x86_64 thread fixes"). However, at least today we can rely on ptrace to
restore the base registers for us. As such, only the part of the patch
that tracks the FS register for use as thread local storage is actually
needed.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/include/shared/os.h    |  3 --
 arch/x86/um/asm/elf.h          |  4 +--
 arch/x86/um/asm/processor_64.h |  3 --
 arch/x86/um/os-Linux/Makefile  |  1 -
 arch/x86/um/os-Linux/prctl.c   | 12 -------
 arch/x86/um/syscalls_64.c      | 62 +++++++---------------------------
 arch/x86/um/tls_64.c           |  2 +-
 7 files changed, 16 insertions(+), 71 deletions(-)
 delete mode 100644 arch/x86/um/os-Linux/prctl.c

diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 0df646c6651ea..aff8906304ea8 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -323,9 +323,6 @@ extern void sigio_broken(int fd);
 extern int __add_sigio_fd(int fd);
 extern int __ignore_sigio_fd(int fd);
 
-/* prctl.c */
-extern int os_arch_prctl(int pid, int option, unsigned long *arg2);
-
 /* tty.c */
 extern int get_pty(void);
 
diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h
index 6523eb7c3bd17..6052200fe9256 100644
--- a/arch/x86/um/asm/elf.h
+++ b/arch/x86/um/asm/elf.h
@@ -168,8 +168,8 @@ do {								\
 	(pr_reg)[18] = (_regs)->regs.gp[18];			\
 	(pr_reg)[19] = (_regs)->regs.gp[19];			\
 	(pr_reg)[20] = (_regs)->regs.gp[20];			\
-	(pr_reg)[21] = current->thread.arch.fs;			\
-	(pr_reg)[22] = 0;					\
+	(pr_reg)[21] = (_regs)->regs.gp[21];			\
+	(pr_reg)[22] = (_regs)->regs.gp[22];			\
 	(pr_reg)[23] = 0;					\
 	(pr_reg)[24] = 0;					\
 	(pr_reg)[25] = 0;					\
diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h
index 1ef9c21877bc8..f901595089365 100644
--- a/arch/x86/um/asm/processor_64.h
+++ b/arch/x86/um/asm/processor_64.h
@@ -10,13 +10,11 @@
 struct arch_thread {
         unsigned long debugregs[8];
         int debugregs_seq;
-        unsigned long fs;
         struct faultinfo faultinfo;
 };
 
 #define INIT_ARCH_THREAD { .debugregs  		= { [ 0 ... 7 ] = 0 }, \
 			   .debugregs_seq	= 0, \
-			   .fs			= 0, \
 			   .faultinfo		= { 0, 0, 0 } }
 
 #define STACKSLOTS_PER_LINE 4
@@ -28,7 +26,6 @@ static inline void arch_flush_thread(struct arch_thread *thread)
 static inline void arch_copy_thread(struct arch_thread *from,
                                     struct arch_thread *to)
 {
-	to->fs = from->fs;
 }
 
 #define current_sp() ({ void *sp; __asm__("movq %%rsp, %0" : "=r" (sp) : ); sp; })
diff --git a/arch/x86/um/os-Linux/Makefile b/arch/x86/um/os-Linux/Makefile
index ae169125d03fc..5249bbc30dcdb 100644
--- a/arch/x86/um/os-Linux/Makefile
+++ b/arch/x86/um/os-Linux/Makefile
@@ -6,7 +6,6 @@
 obj-y = registers.o task_size.o mcontext.o
 
 obj-$(CONFIG_X86_32) += tls.o
-obj-$(CONFIG_64BIT) += prctl.o
 
 USER_OBJS := $(obj-y)
 
diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c
deleted file mode 100644
index 8431e87ac3333..0000000000000
--- a/arch/x86/um/os-Linux/prctl.c
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit.com,linux.intel.com})
- * Licensed under the GPL
- */
-
-#include <sys/ptrace.h>
-#include <asm/ptrace.h>
-
-int os_arch_prctl(int pid, int option, unsigned long *arg2)
-{
-	return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option);
-}
diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c
index 27b29ae6c471b..6a00a28c9cca7 100644
--- a/arch/x86/um/syscalls_64.c
+++ b/arch/x86/um/syscalls_64.c
@@ -16,60 +16,24 @@
 long arch_prctl(struct task_struct *task, int option,
 		unsigned long __user *arg2)
 {
-	unsigned long *ptr = arg2, tmp;
-	long ret;
-	int pid = task->mm->context.id.u.pid;
-
-	/*
-	 * With ARCH_SET_FS (and ARCH_SET_GS is treated similarly to
-	 * be safe), we need to call arch_prctl on the host because
-	 * setting %fs may result in something else happening (like a
-	 * GDT or thread.fs being set instead).  So, we let the host
-	 * fiddle the registers and thread struct and restore the
-	 * registers afterwards.
-	 *
-	 * So, the saved registers are stored to the process (this
-	 * needed because a stub may have been the last thing to run),
-	 * arch_prctl is run on the host, then the registers are read
-	 * back.
-	 */
-	switch (option) {
-	case ARCH_SET_FS:
-	case ARCH_SET_GS:
-		ret = restore_pid_registers(pid, &current->thread.regs.regs);
-		if (ret)
-			return ret;
-		break;
-	case ARCH_GET_FS:
-	case ARCH_GET_GS:
-		/*
-		 * With these two, we read to a local pointer and
-		 * put_user it to the userspace pointer that we were
-		 * given.  If addr isn't valid (because it hasn't been
-		 * faulted in or is just bogus), we want put_user to
-		 * fault it in (or return -EFAULT) instead of having
-		 * the host return -EFAULT.
-		 */
-		ptr = &tmp;
-	}
-
-	ret = os_arch_prctl(pid, option, ptr);
-	if (ret)
-		return ret;
+	long ret = -EINVAL;
 
 	switch (option) {
 	case ARCH_SET_FS:
-		current->thread.arch.fs = (unsigned long) ptr;
-		ret = save_registers(pid, &current->thread.regs.regs);
+		current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] =
+			(unsigned long) arg2;
+		ret = 0;
 		break;
 	case ARCH_SET_GS:
-		ret = save_registers(pid, &current->thread.regs.regs);
+		current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)] =
+			(unsigned long) arg2;
+		ret = 0;
 		break;
 	case ARCH_GET_FS:
-		ret = put_user(tmp, arg2);
+		ret = put_user(current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)], arg2);
 		break;
 	case ARCH_GET_GS:
-		ret = put_user(tmp, arg2);
+		ret = put_user(current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)], arg2);
 		break;
 	}
 
@@ -83,10 +47,10 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 
 void arch_switch_to(struct task_struct *to)
 {
-	if ((to->thread.arch.fs == 0) || (to->mm == NULL))
-		return;
-
-	arch_prctl(to, ARCH_SET_FS, (void __user *) to->thread.arch.fs);
+	/*
+	 * Nothing needs to be done on x86_64.
+	 * The FS_BASE/GS_BASE registers are saved in the ptrace register set.
+	 */
 }
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c
index ebd3855d9b132..c51a613f6f5c4 100644
--- a/arch/x86/um/tls_64.c
+++ b/arch/x86/um/tls_64.c
@@ -12,7 +12,7 @@ int arch_set_tls(struct task_struct *t, unsigned long tls)
 	 * If CLONE_SETTLS is set, we need to save the thread id
 	 * so it can be set during context switches.
 	 */
-	t->thread.arch.fs = tls;
+	t->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] = tls;
 
 	return 0;
 }
-- 
GitLab


From 1e41c415e21ff03ddf5c3725b608d0e4f0c239e3 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:47 +0100
Subject: [PATCH 2285/4076] um: Remove unused register save/restore functions

These functions were only used when calling PTRACE_ARCH_PRCTL, but this
code has been removed.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/um/include/shared/registers.h |  2 --
 arch/um/os-Linux/registers.c       | 20 --------------------
 2 files changed, 22 deletions(-)

diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h
index 2f9c3ce5b45e8..a0450326521cd 100644
--- a/arch/um/include/shared/registers.h
+++ b/arch/um/include/shared/registers.h
@@ -14,8 +14,6 @@ extern int save_fp_registers(int pid, unsigned long *fp_regs);
 extern int restore_fp_registers(int pid, unsigned long *fp_regs);
 extern int save_fpx_registers(int pid, unsigned long *fp_regs);
 extern int restore_fpx_registers(int pid, unsigned long *fp_regs);
-extern int save_registers(int pid, struct uml_pt_regs *regs);
-extern int restore_pid_registers(int pid, struct uml_pt_regs *regs);
 extern int init_pid_registers(int pid);
 extern void get_safe_registers(unsigned long *regs, unsigned long *fp_regs);
 extern int get_fp_registers(int pid, unsigned long *regs);
diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c
index b123955be7acc..bd80b921add06 100644
--- a/arch/um/os-Linux/registers.c
+++ b/arch/um/os-Linux/registers.c
@@ -11,26 +11,6 @@
 #include <sysdep/ptrace_user.h>
 #include <registers.h>
 
-int save_registers(int pid, struct uml_pt_regs *regs)
-{
-	int err;
-
-	err = ptrace(PTRACE_GETREGS, pid, 0, regs->gp);
-	if (err < 0)
-		return -errno;
-	return 0;
-}
-
-int restore_pid_registers(int pid, struct uml_pt_regs *regs)
-{
-	int err;
-
-	err = ptrace(PTRACE_SETREGS, pid, 0, regs->gp);
-	if (err < 0)
-		return -errno;
-	return 0;
-}
-
 /* This is set once at boot time and not changed thereafter */
 
 static unsigned long exec_regs[MAX_REG_NR];
-- 
GitLab


From 83aec96c631e0fa75cfe6d6a1b113a32151aaa88 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin@sipsolutions.net>
Date: Fri, 10 Nov 2023 12:03:48 +0100
Subject: [PATCH 2286/4076] um: Mark 32bit syscall helpers as clobbering memory

The 64bit helper are marked to clobber the memory, but the 32bit ones
are not. Add the appropriate clobber to the 32bit helper routines so
that the compiler cannot do invalid optimizations.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 arch/x86/um/shared/sysdep/stub_32.h | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h
index 4e763f8b380f5..ea8b5a2d67afb 100644
--- a/arch/x86/um/shared/sysdep/stub_32.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -16,7 +16,8 @@ static __always_inline long stub_syscall0(long syscall)
 {
 	long ret;
 
-	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall));
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall)
+			: "memory");
 
 	return ret;
 }
@@ -25,7 +26,8 @@ static __always_inline long stub_syscall1(long syscall, long arg1)
 {
 	long ret;
 
-	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1));
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1)
+			: "memory");
 
 	return ret;
 }
@@ -35,7 +37,8 @@ static __always_inline long stub_syscall2(long syscall, long arg1, long arg2)
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2));
+			"c" (arg2)
+			: "memory");
 
 	return ret;
 }
@@ -46,7 +49,8 @@ static __always_inline long stub_syscall3(long syscall, long arg1, long arg2,
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3));
+			"c" (arg2), "d" (arg3)
+			: "memory");
 
 	return ret;
 }
@@ -57,7 +61,8 @@ static __always_inline long stub_syscall4(long syscall, long arg1, long arg2,
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3), "S" (arg4));
+			"c" (arg2), "d" (arg3), "S" (arg4)
+			: "memory");
 
 	return ret;
 }
@@ -68,7 +73,8 @@ static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5));
+			"c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5)
+			: "memory");
 
 	return ret;
 }
-- 
GitLab


From 738fadaa549797c777650ac8d0d433fdc20152e3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 28 Oct 2023 22:03:55 -0700
Subject: [PATCH 2287/4076] ubifs: use crypto_shash_tfm_digest() in
 ubifs_hmac_wkm()

Simplify ubifs_hmac_wkm() by using crypto_shash_tfm_digest() instead of
an alloc+init+update+final sequence.  This should also improve
performance.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Tested-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 fs/ubifs/auth.c | 19 ++-----------------
 1 file changed, 2 insertions(+), 17 deletions(-)

diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c
index 0d561ecb68694..5c414d896c9bd 100644
--- a/fs/ubifs/auth.c
+++ b/fs/ubifs/auth.c
@@ -507,28 +507,13 @@ out:
  */
 int ubifs_hmac_wkm(struct ubifs_info *c, u8 *hmac)
 {
-	SHASH_DESC_ON_STACK(shash, c->hmac_tfm);
-	int err;
 	const char well_known_message[] = "UBIFS";
 
 	if (!ubifs_authenticated(c))
 		return 0;
 
-	shash->tfm = c->hmac_tfm;
-
-	err = crypto_shash_init(shash);
-	if (err)
-		return err;
-
-	err = crypto_shash_update(shash, well_known_message,
-				  sizeof(well_known_message) - 1);
-	if (err < 0)
-		return err;
-
-	err = crypto_shash_final(shash, hmac);
-	if (err)
-		return err;
-	return 0;
+	return crypto_shash_tfm_digest(c->hmac_tfm, well_known_message,
+				       sizeof(well_known_message) - 1, hmac);
 }
 
 /*
-- 
GitLab


From 19c2fcb4a489cf7c40686e694336478093919960 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 5 Nov 2023 22:07:44 -0800
Subject: [PATCH 2288/4076] ubifs: auth.c: fix kernel-doc function prototype
 warning

Use the correct function name in the kernel-doc comment to prevent
a kernel-doc warning:

auth.c:30: warning: expecting prototype for ubifs_node_calc_hash(). Prototype was for __ubifs_node_calc_hash() instead

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: lore.kernel.org/r/202311052125.gE1Rylox-lkp@intel.com
Cc: Richard Weinberger <richard@nod.at>
Cc: linux-mtd@lists.infradead.org
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 fs/ubifs/auth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c
index 5c414d896c9bd..a4a0158f712d3 100644
--- a/fs/ubifs/auth.c
+++ b/fs/ubifs/auth.c
@@ -18,7 +18,7 @@
 #include "ubifs.h"
 
 /**
- * ubifs_node_calc_hash - calculate the hash of a UBIFS node
+ * __ubifs_node_calc_hash - calculate the hash of a UBIFS node
  * @c: UBIFS file-system description object
  * @node: the node to calculate a hash for
  * @hash: the returned hash
-- 
GitLab


From 2ba5b48938d752d09d65d1a01c8ff0d2228c5ab5 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Wed, 8 Nov 2023 07:05:06 +0100
Subject: [PATCH 2289/4076] ubifs: describe function parameters

With 16a26b20d2afd ("ubifs: authentication: Add hashes to index nodes")
insert_node() and insert_dent() got a new function parameter 'hash'. Add
a description for this new parameter.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311051618.D7YUE1Rr-lkp@intel.com/
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 fs/ubifs/replay.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index c59d47fe79396..17da28d6247ac 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -365,6 +365,7 @@ static void destroy_replay_list(struct ubifs_info *c)
  * @lnum: node logical eraseblock number
  * @offs: node offset
  * @len: node length
+ * @hash: node hash
  * @key: node key
  * @sqnum: sequence number
  * @deletion: non-zero if this is a deletion
@@ -417,6 +418,7 @@ static int insert_node(struct ubifs_info *c, int lnum, int offs, int len,
  * @lnum: node logical eraseblock number
  * @offs: node offset
  * @len: node length
+ * @hash: node hash
  * @key: node key
  * @name: directory entry name
  * @nlen: directory entry name length
-- 
GitLab


From 92a714d727ec9e7ccfcc7432d348aba730145914 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 4 Jan 2024 15:52:11 +0000
Subject: [PATCH 2290/4076] netfs: Fix interaction between write-streaming and
 cachefiles culling

An issue can occur between write-streaming (storing dirty data in partial
non-uptodate pages) and a cachefiles object being culled to make space.
The problem occurs because the cache object is only marked in use while
there are files open using it.  Once it has been released, it can be culled
and the cookie marked disabled.

At this point, a streaming write is permitted to occur (if the cache is
active, we require pages to be prefetched and cached), but the cache can
become active again before this gets flushed out - and then two effects can
occur:

 (1) The cache may be asked to write out a region that's less than its DIO
     block size (assumed by cachefiles to be PAGE_SIZE) - and this causes
     one of two debugging statements to be emitted.

 (2) netfs_how_to_modify() gets confused because it sees a page that isn't
     allowed to be non-uptodate being uptodate and tries to prefetch it -
     leading to a warning that PG_fscache is set twice.

Fix this by the following means:

 (1) Add a netfs_inode flag to disallow write-streaming to an inode and set
     it if we ever do local caching of that inode.  It remains set for the
     lifetime of that inode - even if the cookie becomes disabled.

 (2) If the no-write-streaming flag is set, then make netfs_how_to_modify()
     always want to prefetch instead.

 (3) If netfs_how_to_modify() decides it wants to prefetch a folio, but
     that folio has write-streamed data in it, then it requires the folio
     be flushed first.

 (4) Export a counter of the number of times we wanted to prefetch a
     non-uptodate page, but found it had write-streamed data in it.

 (5) Export a counter of the number of times we cancelled a write to the
     cache because it didn't DIO align and remove the debug statements.

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-erofs@lists.ozlabs.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/cachefiles/io.c            | 12 ++++++------
 fs/netfs/buffered_write.c     | 24 ++++++++++++++++++++----
 fs/netfs/fscache_stats.c      |  9 ++++++---
 fs/netfs/internal.h           |  1 +
 fs/netfs/stats.c              |  6 ++++--
 include/linux/fscache-cache.h |  3 +++
 include/linux/netfs.h         |  1 +
 7 files changed, 41 insertions(+), 15 deletions(-)

diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 7529b40bc95a9..3eec269674375 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -528,12 +528,12 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 
 	/* Round to DIO size */
 	start = round_down(*_start, PAGE_SIZE);
-	if (start != *_start) {
-		kleave(" = -ENOBUFS [down]");
-		return -ENOBUFS;
-	}
-	if (*_len > upper_len) {
-		kleave(" = -ENOBUFS [up]");
+	if (start != *_start || *_len > upper_len) {
+		/* Probably asked to cache a streaming write written into the
+		 * pagecache when the cookie was temporarily out of service to
+		 * culling.
+		 */
+		fscache_count_dio_misfit();
 		return -ENOBUFS;
 	}
 
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 08f28800232c3..6cd8f7422e9ab 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -80,10 +80,19 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 		return NETFS_WHOLE_FOLIO_MODIFY;
 
 	if (file->f_mode & FMODE_READ)
-		return NETFS_JUST_PREFETCH;
-
-	if (netfs_is_cache_enabled(ctx))
-		return NETFS_JUST_PREFETCH;
+		goto no_write_streaming;
+	if (test_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags))
+		goto no_write_streaming;
+
+	if (netfs_is_cache_enabled(ctx)) {
+		/* We don't want to get a streaming write on a file that loses
+		 * caching service temporarily because the backing store got
+		 * culled.
+		 */
+		if (!test_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags))
+			set_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags);
+		goto no_write_streaming;
+	}
 
 	if (!finfo)
 		return NETFS_STREAMING_WRITE;
@@ -95,6 +104,13 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 	if (offset == finfo->dirty_offset + finfo->dirty_len)
 		return NETFS_STREAMING_WRITE_CONT;
 	return NETFS_FLUSH_CONTENT;
+
+no_write_streaming:
+	if (finfo) {
+		netfs_stat(&netfs_n_wh_wstream_conflict);
+		return NETFS_FLUSH_CONTENT;
+	}
+	return NETFS_JUST_PREFETCH;
 }
 
 /*
diff --git a/fs/netfs/fscache_stats.c b/fs/netfs/fscache_stats.c
index aad812ead398f..add21abdf7134 100644
--- a/fs/netfs/fscache_stats.c
+++ b/fs/netfs/fscache_stats.c
@@ -48,13 +48,15 @@ atomic_t fscache_n_no_create_space;
 EXPORT_SYMBOL(fscache_n_no_create_space);
 atomic_t fscache_n_culled;
 EXPORT_SYMBOL(fscache_n_culled);
+atomic_t fscache_n_dio_misfit;
+EXPORT_SYMBOL(fscache_n_dio_misfit);
 
 /*
  * display the general statistics
  */
 int fscache_stats_show(struct seq_file *m)
 {
-	seq_puts(m, "FS-Cache statistics\n");
+	seq_puts(m, "-- FS-Cache statistics --\n");
 	seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n",
 		   atomic_read(&fscache_n_cookies),
 		   atomic_read(&fscache_n_volumes),
@@ -93,8 +95,9 @@ int fscache_stats_show(struct seq_file *m)
 		   atomic_read(&fscache_n_no_create_space),
 		   atomic_read(&fscache_n_culled));
 
-	seq_printf(m, "IO     : rd=%u wr=%u\n",
+	seq_printf(m, "IO     : rd=%u wr=%u mis=%u\n",
 		   atomic_read(&fscache_n_read),
-		   atomic_read(&fscache_n_write));
+		   atomic_read(&fscache_n_write),
+		   atomic_read(&fscache_n_dio_misfit));
 	return 0;
 }
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 3f9620d0fa63d..ec7045d24400d 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -123,6 +123,7 @@ extern atomic_t netfs_n_rh_write_begin;
 extern atomic_t netfs_n_rh_write_done;
 extern atomic_t netfs_n_rh_write_failed;
 extern atomic_t netfs_n_rh_write_zskip;
+extern atomic_t netfs_n_wh_wstream_conflict;
 extern atomic_t netfs_n_wh_upload;
 extern atomic_t netfs_n_wh_upload_done;
 extern atomic_t netfs_n_wh_upload_failed;
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index 42db36528d921..deeba9f9dcf5d 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -29,6 +29,7 @@ atomic_t netfs_n_rh_write_begin;
 atomic_t netfs_n_rh_write_done;
 atomic_t netfs_n_rh_write_failed;
 atomic_t netfs_n_rh_write_zskip;
+atomic_t netfs_n_wh_wstream_conflict;
 atomic_t netfs_n_wh_upload;
 atomic_t netfs_n_wh_upload_done;
 atomic_t netfs_n_wh_upload_failed;
@@ -66,9 +67,10 @@ int netfs_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&netfs_n_wh_write),
 		   atomic_read(&netfs_n_wh_write_done),
 		   atomic_read(&netfs_n_wh_write_failed));
-	seq_printf(m, "Netfs  : rr=%u sr=%u\n",
+	seq_printf(m, "Netfs  : rr=%u sr=%u wsc=%u\n",
 		   atomic_read(&netfs_n_rh_rreq),
-		   atomic_read(&netfs_n_rh_sreq));
+		   atomic_read(&netfs_n_rh_sreq),
+		   atomic_read(&netfs_n_wh_wstream_conflict));
 	return fscache_stats_show(m);
 }
 EXPORT_SYMBOL(netfs_stats_show);
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index a174cedf4d907..bdf7f3eddf0a2 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -189,17 +189,20 @@ extern atomic_t fscache_n_write;
 extern atomic_t fscache_n_no_write_space;
 extern atomic_t fscache_n_no_create_space;
 extern atomic_t fscache_n_culled;
+extern atomic_t fscache_n_dio_misfit;
 #define fscache_count_read() atomic_inc(&fscache_n_read)
 #define fscache_count_write() atomic_inc(&fscache_n_write)
 #define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space)
 #define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space)
 #define fscache_count_culled() atomic_inc(&fscache_n_culled)
+#define fscache_count_dio_misfit() atomic_inc(&fscache_n_dio_misfit)
 #else
 #define fscache_count_read() do {} while(0)
 #define fscache_count_write() do {} while(0)
 #define fscache_count_no_write_space() do {} while(0)
 #define fscache_count_no_create_space() do {} while(0)
 #define fscache_count_culled() do {} while(0)
+#define fscache_count_dio_misfit() do {} while(0)
 #endif
 
 #endif /* _LINUX_FSCACHE_CACHE_H */
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d3bac60fcd6f3..100cbb261269d 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -142,6 +142,7 @@ struct netfs_inode {
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
 #define NETFS_ICTX_WRITETHROUGH	2		/* Write-through caching */
+#define NETFS_ICTX_NO_WRITE_STREAMING	3	/* Don't engage in write-streaming */
 };
 
 /*
-- 
GitLab


From 17dc11a02d8dacc7e78968daa2a8c16281eb7d1e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 5 Jan 2024 15:21:00 +0100
Subject: [PATCH 2291/4076] spi: coldfire-qspi: Remove an erroneous
 clk_disable_unprepare() from the remove function

The commit in Fixes has changed a devm_clk_get()/clk_prepare_enable() into
a devm_clk_get_enabled().
It has updated the error handling path of the probe accordingly, but the
remove has been left unchanged.

Remove now the redundant clk_disable_unprepare() call from the remove
function.

Fixes: a90a987ebe00 ("spi: use devm_clk_get_enabled() in mcfqspi_probe()")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://msgid.link/r/6670aed303e1f7680e0911387606a8ae069e2cef.1704464447.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-coldfire-qspi.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index f0b630fe16c3c..b341b6908df06 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -441,7 +441,6 @@ static void mcfqspi_remove(struct platform_device *pdev)
 	mcfqspi_wr_qmr(mcfqspi, MCFQSPI_QMR_MSTR);
 
 	mcfqspi_cs_teardown(mcfqspi);
-	clk_disable_unprepare(mcfqspi->clk);
 }
 
 #ifdef CONFIG_PM_SLEEP
-- 
GitLab


From c07a4dab243a99589bdfd5ec364b5cb1db6b70f3 Mon Sep 17 00:00:00 2001
From: Zhihao Cheng <chengzhihao1@huawei.com>
Date: Mon, 20 Nov 2023 19:13:45 +0800
Subject: [PATCH 2292/4076] ubifs: Check @c->dirty_[n|p]n_cnt and @c->nroot
 state under @c->lp_mutex

The checking of @c->nroot->flags and @c->dirty_[n|p]n_cnt in function
nothing_to_commit() is not atomic, which could be raced with modifying
of lpt, for example:
       P1        P2        P3
run_gc
 ubifs_garbage_collect
              do_commit
 ubifs_return_leb
  ubifs_lpt_lookup_dirty
   dirty_cow_nnode
                       do_commit
			nothing_to_commit
			 if (test_bit(DIRTY_CNODE, &c->nroot->flags)
			 // false
   test_and_set_bit(DIRTY_CNODE, &nnode->flags)
   c->dirty_nn_cnt += 1
                         ubifs_assert(c, c->dirty_nn_cnt == 0)
			 // false !

Fetch a reproducer in Link:
 UBIFS error (ubi0:0 pid 2747): ubifs_assert_failed
 UBIFS assert failed: c->dirty_pn_cnt == 0, in fs/ubifs/commit.c
 Call Trace:
  ubifs_ro_mode+0x58/0x70 [ubifs]
  ubifs_assert_failed+0x6a/0x90 [ubifs]
  do_commit+0x5b7/0x930 [ubifs]
  ubifs_run_commit+0xc6/0x1a0 [ubifs]
  ubifs_sync_fs+0xd8/0x110 [ubifs]
  sync_filesystem+0xb4/0x120
  do_syscall_64+0x6f/0x140

Fix it by checking @c->dirty_[n|p]n_cnt and @c->nroot state with
@c->lp_mutex locked.

Fixes: 944fdef52ca9 ("UBIFS: do not start the commit if there is nothing to commit")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218162
Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 fs/ubifs/commit.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index c4fc1047fc079..5b3a840098b06 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -69,6 +69,14 @@ static int nothing_to_commit(struct ubifs_info *c)
 	if (c->zroot.znode && ubifs_zn_dirty(c->zroot.znode))
 		return 0;
 
+	/*
+	 * Increasing @c->dirty_pn_cnt/@c->dirty_nn_cnt and marking
+	 * nnodes/pnodes as dirty in run_gc() could race with following
+	 * checking, which leads inconsistent states between @c->nroot
+	 * and @c->dirty_pn_cnt/@c->dirty_nn_cnt, holding @c->lp_mutex
+	 * to avoid that.
+	 */
+	mutex_lock(&c->lp_mutex);
 	/*
 	 * Even though the TNC is clean, the LPT tree may have dirty nodes. For
 	 * example, this may happen if the budgeting subsystem invoked GC to
@@ -76,12 +84,15 @@ static int nothing_to_commit(struct ubifs_info *c)
 	 * free space. In this case GC would just change the lprops of this
 	 * LEB (by turning all space into free space) and unmap it.
 	 */
-	if (c->nroot && test_bit(DIRTY_CNODE, &c->nroot->flags))
+	if (c->nroot && test_bit(DIRTY_CNODE, &c->nroot->flags)) {
+		mutex_unlock(&c->lp_mutex);
 		return 0;
+	}
 
 	ubifs_assert(c, atomic_long_read(&c->dirty_zn_cnt) == 0);
 	ubifs_assert(c, c->dirty_pn_cnt == 0);
 	ubifs_assert(c, c->dirty_nn_cnt == 0);
+	mutex_unlock(&c->lp_mutex);
 
 	return 1;
 }
-- 
GitLab


From be12ad45e15b5ee0e2526a50266ba1d295d26a88 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Date: Mon, 20 Nov 2023 09:14:06 +0000
Subject: [PATCH 2293/4076] hisi_acc_vfio_pci: Update migration data pointer
 correctly on saving/resume

When the optional PRE_COPY support was added to speed up the device
compatibility check, it failed to update the saving/resuming data
pointers based on the fd offset. This results in migration data
corruption and when the device gets started on the destination the
following error is reported in some cases,

[  478.907684] arm-smmu-v3 arm-smmu-v3.2.auto: event 0x10 received:
[  478.913691] arm-smmu-v3 arm-smmu-v3.2.auto:  0x0000310200000010
[  478.919603] arm-smmu-v3 arm-smmu-v3.2.auto:  0x000002088000007f
[  478.925515] arm-smmu-v3 arm-smmu-v3.2.auto:  0x0000000000000000
[  478.931425] arm-smmu-v3 arm-smmu-v3.2.auto:  0x0000000000000000
[  478.947552] hisi_zip 0000:31:00.0: qm_axi_rresp [error status=0x1] found
[  478.955930] hisi_zip 0000:31:00.0: qm_db_timeout [error status=0x400] found
[  478.955944] hisi_zip 0000:31:00.0: qm sq doorbell timeout in function 2

Fixes: d9a871e4a143 ("hisi_acc_vfio_pci: Introduce support for PRE_COPY state transitions")
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231120091406.780-1-shameerali.kolothum.thodi@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index b2f9778c8366e..4d27465c8f1a8 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -694,6 +694,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 					size_t len, loff_t *pos)
 {
 	struct hisi_acc_vf_migration_file *migf = filp->private_data;
+	u8 *vf_data = (u8 *)&migf->vf_data;
 	loff_t requested_length;
 	ssize_t done = 0;
 	int ret;
@@ -715,7 +716,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 		goto out_unlock;
 	}
 
-	ret = copy_from_user(&migf->vf_data, buf, len);
+	ret = copy_from_user(vf_data + *pos, buf, len);
 	if (ret) {
 		done = -EFAULT;
 		goto out_unlock;
@@ -835,7 +836,9 @@ static ssize_t hisi_acc_vf_save_read(struct file *filp, char __user *buf, size_t
 
 	len = min_t(size_t, migf->total_length - *pos, len);
 	if (len) {
-		ret = copy_to_user(buf, &migf->vf_data, len);
+		u8 *vf_data = (u8 *)&migf->vf_data;
+
+		ret = copy_to_user(buf, vf_data + *pos, len);
 		if (ret) {
 			done = -EFAULT;
 			goto out_unlock;
-- 
GitLab


From 196da3f3f76a46905f7daab29c56974f1aba9a7a Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Date: Fri, 5 Jan 2024 19:40:06 +0200
Subject: [PATCH 2294/4076] drm/rockchip: vop2: Drop unused if_dclk_rate
 variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 5a028e8f062f ("drm/rockchip: vop2: Add support for rk3588")
introduced a variable which ended up being unused:

rockchip_drm_vop2.c:1688:23: warning: variable ‘if_dclk_rate’ set but not used [-Wunused-but-set-variable]

This has been initially used as part of a formula to compute the clock
dividers, but eventually it has been replaced by static values.

Drop the variable declaration and move its assignment to the comment
block, to serve as documentation of how the constants have been
generated.

Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20240105174007.98054-1-cristian.ciocaltea@collabora.com
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index a3a03e9cfe137..85b3b4871a1d6 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -1680,7 +1680,6 @@ static unsigned long rk3588_calc_cru_cfg(struct vop2_video_port *vp, int id,
 	unsigned long dclk_core_rate = v_pixclk >> 2;
 	unsigned long dclk_rate = v_pixclk;
 	unsigned long dclk_out_rate;
-	unsigned long if_dclk_rate;
 	unsigned long if_pixclk_rate;
 	int K = 1;
 
@@ -1695,8 +1694,8 @@ static unsigned long rk3588_calc_cru_cfg(struct vop2_video_port *vp, int id,
 		}
 
 		if_pixclk_rate = (dclk_core_rate << 1) / K;
-		if_dclk_rate = dclk_core_rate / K;
 		/*
+		 * if_dclk_rate = dclk_core_rate / K;
 		 * *if_pixclk_div = dclk_rate / if_pixclk_rate;
 		 * *if_dclk_div = dclk_rate / if_dclk_rate;
 		 */
-- 
GitLab


From f644d21baab34c837d639e9639aa8204dba7f3cf Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Mon, 18 Dec 2023 16:30:53 +0100
Subject: [PATCH 2295/4076] nvmet-fcloop: Remove remote port from list when
 unlinking

The remote port is removed too late from fcloop_nports list. Remove it
when port is unregistered.

This prevents a busy loop in fcloop_exit, because it is possible the
remote port is found in the list and thus we will never progress.

The kernel log will be spammed with

  nvme_fcloop: fcloop_exit: Failed deleting remote port
  nvme_fcloop: fcloop_exit: Failed deleting target port

Signed-off-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fcloop.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index c65a73433c05f..ead349af30f1e 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -995,11 +995,6 @@ fcloop_nport_free(struct kref *ref)
 {
 	struct fcloop_nport *nport =
 		container_of(ref, struct fcloop_nport, ref);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fcloop_lock, flags);
-	list_del(&nport->nport_list);
-	spin_unlock_irqrestore(&fcloop_lock, flags);
 
 	kfree(nport);
 }
@@ -1357,6 +1352,8 @@ __unlink_remote_port(struct fcloop_nport *nport)
 		nport->tport->remoteport = NULL;
 	nport->rport = NULL;
 
+	list_del(&nport->nport_list);
+
 	return rport;
 }
 
-- 
GitLab


From bd029a02ce46e77e4d553140b039f93cf78ee8c1 Mon Sep 17 00:00:00 2001
From: "Jim.Lin" <jim.chihjung.lin@gmail.com>
Date: Tue, 28 Nov 2023 10:57:37 +0800
Subject: [PATCH 2296/4076] nvme-pci: disable write zeroes for SK Hynix BC901

SK Hynix BC901 drive write zero will cause Chromebook takes more than 20 mins to switch to developer mode
"disable write zeroes" can fix this issue and Sk Hynix has been verified.

Signed-off-by: Jim.Lin <jim.lin@siliconmotion.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 507bc149046dc..f272026807419 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3394,6 +3394,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1c5c, 0x174a),   /* SK Hynix P31 SSD */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1c5c, 0x1D59),   /* SK Hynix BC901 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */
-- 
GitLab


From bafd590910d00327decb3937e77f6f11c3e80e4b Mon Sep 17 00:00:00 2001
From: Guixin Liu <kanie@linux.alibaba.com>
Date: Wed, 27 Dec 2023 17:31:06 +0800
Subject: [PATCH 2297/4076] nvme: introduce nvme_disk_is_ns_head helper

We currently rely on gendisk's file operations (fops) to distinguish
between a namespace head (ns_head) and a regular namespace. To enhance
code readability, introduce a helper function.
Additionally, we must ensure that the device is not an ns_head before
calling nvme_get_ns_from_dev(). To enforce this, add a WARN_ON check
within the nvme_get_ns_from_dev().

Signed-off-by: Guixin Liu <kanie@linux.alibaba.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Liu Song <liusong@linux.alibaba.com>
[include fix: https://lore.kernel.org/oe-kbuild-all/202401031943.0N72Tkji-lkp@intel.com/]
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/nvme.h  | 13 ++++++++++++-
 drivers/nvme/host/pr.c    |  2 +-
 drivers/nvme/host/sysfs.c |  8 ++++----
 3 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 297b80430f1b6..6092cc3618375 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -920,6 +920,10 @@ extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;
 
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return disk->fops == &nvme_ns_head_ops;
+}
 #else
 #define multipath false
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
@@ -997,6 +1001,10 @@ static inline void nvme_mpath_start_request(struct request *rq)
 static inline void nvme_mpath_end_request(struct request *rq)
 {
 }
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return false;
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 int nvme_revalidate_zones(struct nvme_ns *ns);
@@ -1025,7 +1033,10 @@ static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 {
-	return dev_to_disk(dev)->private_data;
+	struct gendisk *disk = dev_to_disk(dev);
+
+	WARN_ON(nvme_disk_is_ns_head(disk));
+	return disk->private_data;
 }
 
 #ifdef CONFIG_NVME_HWMON
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index 391b1465ebfd5..fc3eed00f9ff1 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -98,7 +98,7 @@ static int nvme_send_pr_command(struct block_device *bdev,
 		struct nvme_command *c, void *data, unsigned int data_len)
 {
 	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
-	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+	    nvme_disk_is_ns_head(bdev->bd_disk))
 		return nvme_send_ns_head_pr_command(bdev, c, data, data_len);
 
 	return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data,
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index ac24ad1023806..754e911110420 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -39,10 +39,9 @@ static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk->fops == &nvme_bdev_ops)
-		return nvme_get_ns_from_dev(dev)->head;
-	else
+	if (nvme_disk_is_ns_head(disk))
 		return disk->private_data;
+	return nvme_get_ns_from_dev(dev)->head;
 }
 
 static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
@@ -233,7 +232,8 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 	}
 #ifdef CONFIG_NVME_MULTIPATH
 	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
-		if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */
+		/* per-path attr */
+		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
 			return 0;
 		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
 			return 0;
-- 
GitLab


From 4ee7ffeb4ce50c80bc4504db6f39b25a2df6bcf4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 3 Jan 2024 16:56:55 +0100
Subject: [PATCH 2298/4076] nvmet: re-fix tracing strncpy() warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

An earlier patch had tried to address a warning about a string copy with
missing zero termination:

drivers/nvme/target/trace.h:52:3: warning: ‘strncpy’ specified bound 32 equals destination size [-Wstringop-truncation]

The new version causes a different warning with some compiler versions, notably
gcc-9 and gcc-10, and also misses the zero padding that was apparently done
intentionally in the original code:

drivers/nvme/target/trace.h:56:2: error: 'strncpy' specified bound depends on the length of the source argument [-Werror=stringop-overflow=]

Change it to use strscpy_pad() with the original length, which will give
a properly padded and zero-terminated string as well as avoiding the warning.

Fixes: d86481e924a7 ("nvmet: use min of device_path and disk len")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/trace.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h
index 2f15070ddc569..89020018a0e35 100644
--- a/drivers/nvme/target/trace.h
+++ b/drivers/nvme/target/trace.h
@@ -59,8 +59,7 @@ static inline void __assign_req_name(char *name, struct nvmet_req *req)
 		return;
 	}
 
-	strncpy(name, req->ns->device_path,
-		min_t(size_t, DISK_NAME_LEN, strlen(req->ns->device_path)));
+	strscpy_pad(name, req->ns->device_path, DISK_NAME_LEN);
 }
 #endif
 
-- 
GitLab


From a7de1dea76cd6a3707707af4ea2f8bc3cdeaeb11 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 3 Jan 2024 16:56:56 +0100
Subject: [PATCH 2299/4076] nvme: trace: avoid memcpy overflow warning

A previous patch introduced a struct_group() in nvme_common_command to help
stringop fortification figure out the length of the fields, but one function
is not currently using them:

In file included from drivers/nvme/target/core.c:7:
In file included from include/linux/string.h:254:
include/linux/fortify-string.h:592:4: error: call to '__read_overflow2_field' declared with 'warning' attribute: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror,-Wattribute-warning]
                        __read_overflow2_field(q_size_field, size);
                        ^

Change this one to use the correct field name to avoid the warning.

Fixes: 5c629dc9609dc ("nvme: use struct group for generic command dwords")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h
index 89020018a0e35..7f7ebf9558e50 100644
--- a/drivers/nvme/target/trace.h
+++ b/drivers/nvme/target/trace.h
@@ -90,7 +90,7 @@ TRACE_EVENT(nvmet_req_init,
 		__entry->flags = cmd->common.flags;
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
 		__entry->metadata = le64_to_cpu(cmd->common.metadata);
-		memcpy(__entry->cdw10, &cmd->common.cdw10,
+		memcpy(__entry->cdw10, &cmd->common.cdws,
 			sizeof(__entry->cdw10));
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, "
-- 
GitLab


From 98856b2ea3065d8f60e90f423d7707f4a4706ec5 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Fri, 5 Jan 2024 15:07:34 -0700
Subject: [PATCH 2300/4076] cxl: Introduce put_cxl_root() helper

Add a helper function put_cxl_root() to maintain symmetry for
find_cxl_root() function instead of relying on open coding of the
put_device() in order to dereference the 'struct device' that happens via
get_device() in find_cxl_root().

Suggested-by: Robert Richter <rrichter@amd.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Robert Richter <rrichter@amd.com>
Link: https://lore.kernel.org/r/170449245417.3779673.4566146351673989387.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/port.c | 9 +++++++++
 drivers/cxl/cxl.h       | 3 +++
 2 files changed, 12 insertions(+)

diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 8c00fd6be730e..64f30d5fe1f62 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -986,6 +986,15 @@ struct cxl_port *find_cxl_root(struct cxl_port *port)
 }
 EXPORT_SYMBOL_NS_GPL(find_cxl_root, CXL);
 
+void put_cxl_root(struct cxl_root *cxl_root)
+{
+	if (!cxl_root)
+		return;
+
+	put_device(&cxl_root->port.dev);
+}
+EXPORT_SYMBOL_NS_GPL(put_cxl_root, CXL);
+
 static struct cxl_dport *find_dport(struct cxl_port *port, int id)
 {
 	struct cxl_dport *dport;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 492dbf63935fd..df3db3e43913a 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -735,6 +735,9 @@ struct cxl_port *devm_cxl_add_port(struct device *host,
 struct cxl_root *devm_cxl_add_root(struct device *host,
 				   const struct cxl_root_ops *ops);
 struct cxl_port *find_cxl_root(struct cxl_port *port);
+void put_cxl_root(struct cxl_root *cxl_root);
+DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_cxl_root(_T))
+
 int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd);
 void cxl_bus_rescan(void);
 void cxl_bus_drain(void);
-- 
GitLab


From 44cd71ef7bacdfcf7c3e8a7b13f11a7eba69533d Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Fri, 5 Jan 2024 15:07:40 -0700
Subject: [PATCH 2301/4076] cxl: Convert find_cxl_root() to return a 'struct
 cxl_root *'

Commit 790815902ec6 ("cxl: Add support for _DSM Function for retrieving QTG ID")
introduced 'struct cxl_root', however all usages have been worked
indirectly through cxl_port. Refactor code such as find_cxl_root()
function to use 'struct cxl_root' directly.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170449246044.3779673.13035770941393418591.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/acpi.c      |  6 ++----
 drivers/cxl/core/cdat.c | 17 ++++++++++-------
 drivers/cxl/core/pmem.c |  6 ++++--
 drivers/cxl/core/port.c |  4 ++--
 drivers/cxl/cxl.h       | 14 +++++++-------
 drivers/cxl/port.c      |  4 +++-
 6 files changed, 28 insertions(+), 23 deletions(-)

diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index afc712264d1c2..dcf2b39e10488 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -295,14 +295,12 @@ out:
 	return rc;
 }
 
-static int cxl_acpi_qos_class(struct cxl_port *root_port,
+static int cxl_acpi_qos_class(struct cxl_root *cxl_root,
 			      struct access_coordinate *coord, int entries,
 			      int *qos_class)
 {
+	struct device *dev = cxl_root->port.uport_dev;
 	acpi_handle handle;
-	struct device *dev;
-
-	dev = root_port->uport_dev;
 
 	if (!dev_is_platform(dev))
 		return -ENODEV;
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index cd84d87f597a6..0df5379cf02f5 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -162,7 +162,6 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 					struct xarray *dsmas_xa)
 {
 	struct access_coordinate c;
-	struct cxl_port *root_port;
 	struct cxl_root *cxl_root;
 	struct dsmas_entry *dent;
 	int valid_entries = 0;
@@ -175,8 +174,7 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 		return rc;
 	}
 
-	root_port = find_cxl_root(port);
-	cxl_root = to_cxl_root(root_port);
+	cxl_root = find_cxl_root(port);
 	if (!cxl_root->ops || !cxl_root->ops->qos_class)
 		return -EOPNOTSUPP;
 
@@ -193,7 +191,8 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 						    dent->coord.write_bandwidth);
 
 		dent->entries = 1;
-		rc = cxl_root->ops->qos_class(root_port, &dent->coord, 1, &qos_class);
+		rc = cxl_root->ops->qos_class(cxl_root, &dent->coord, 1,
+					      &qos_class);
 		if (rc != 1)
 			continue;
 
@@ -349,15 +348,19 @@ static int cxl_qos_class_verify(struct cxl_memdev *cxlmd)
 {
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
-	struct cxl_port *root_port __free(put_device) = NULL;
 	LIST_HEAD(__discard);
 	struct list_head *discard __free(dpa_perf) = &__discard;
+	struct cxl_port *root_port;
 	int rc;
 
-	root_port = find_cxl_root(cxlmd->endpoint);
-	if (!root_port)
+	struct cxl_root *cxl_root __free(put_cxl_root) =
+		find_cxl_root(cxlmd->endpoint);
+
+	if (!cxl_root)
 		return -ENODEV;
 
+	root_port = &cxl_root->port;
+
 	/* Check that the QTG IDs are all sane between end device and root decoders */
 	cxl_qos_match(root_port, &mds->ram_perf_list, discard);
 	cxl_qos_match(root_port, &mds->pmem_perf_list, discard);
diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index fc94f52403271..da92a901b9e8c 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -64,12 +64,14 @@ static int match_nvdimm_bridge(struct device *dev, void *data)
 
 struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd)
 {
-	struct cxl_port *port = find_cxl_root(cxlmd->endpoint);
+	struct cxl_root *cxl_root = find_cxl_root(cxlmd->endpoint);
+	struct cxl_port *port;
 	struct device *dev;
 
-	if (!port)
+	if (!cxl_root)
 		return NULL;
 
+	port = &cxl_root->port;
 	dev = device_find_child(&port->dev, NULL, match_nvdimm_bridge);
 	put_device(&port->dev);
 
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 64f30d5fe1f62..63a4e3c2baed4 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -972,7 +972,7 @@ static bool dev_is_cxl_root_child(struct device *dev)
 	return false;
 }
 
-struct cxl_port *find_cxl_root(struct cxl_port *port)
+struct cxl_root *find_cxl_root(struct cxl_port *port)
 {
 	struct cxl_port *iter = port;
 
@@ -982,7 +982,7 @@ struct cxl_port *find_cxl_root(struct cxl_port *port)
 	if (!iter)
 		return NULL;
 	get_device(&iter->dev);
-	return iter;
+	return to_cxl_root(iter);
 }
 EXPORT_SYMBOL_NS_GPL(find_cxl_root, CXL);
 
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index df3db3e43913a..3a5004aab97aa 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -617,12 +617,6 @@ struct cxl_port {
 	long pci_latency;
 };
 
-struct cxl_root_ops {
-	int (*qos_class)(struct cxl_port *root_port,
-			 struct access_coordinate *coord, int entries,
-			 int *qos_class);
-};
-
 /**
  * struct cxl_root - logical collection of root cxl_port items
  *
@@ -640,6 +634,12 @@ to_cxl_root(const struct cxl_port *port)
 	return container_of(port, struct cxl_root, port);
 }
 
+struct cxl_root_ops {
+	int (*qos_class)(struct cxl_root *cxl_root,
+			 struct access_coordinate *coord, int entries,
+			 int *qos_class);
+};
+
 static inline struct cxl_dport *
 cxl_find_dport_by_dev(struct cxl_port *port, const struct device *dport_dev)
 {
@@ -734,7 +734,7 @@ struct cxl_port *devm_cxl_add_port(struct device *host,
 				   struct cxl_dport *parent_dport);
 struct cxl_root *devm_cxl_add_root(struct device *host,
 				   const struct cxl_root_ops *ops);
-struct cxl_port *find_cxl_root(struct cxl_port *port);
+struct cxl_root *find_cxl_root(struct cxl_port *port);
 void put_cxl_root(struct cxl_root *cxl_root);
 DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_cxl_root(_T))
 
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index da3c3a08bd626..4f3a08fdc9e94 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -94,6 +94,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	struct cxl_endpoint_dvsec_info info = { .port = port };
 	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_root *cxl_root;
 	struct cxl_hdm *cxlhdm;
 	struct cxl_port *root;
 	int rc;
@@ -130,7 +131,8 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	 * This can't fail in practice as CXL root exit unregisters all
 	 * descendant ports and that in turn synchronizes with cxl_port_probe()
 	 */
-	root = find_cxl_root(port);
+	cxl_root = find_cxl_root(port);
+	root = &cxl_root->port;
 
 	/*
 	 * Now that all endpoint decoders are successfully enumerated, try to
-- 
GitLab


From 98e7ab3345e105339b7d919b4918f3c1879052ed Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Fri, 5 Jan 2024 15:07:46 -0700
Subject: [PATCH 2302/4076] cxl: Fix device reference leak in
 cxl_port_perf_data_calculate()

cxl_port_perf_data_calculate() calls find_cxl_root() and does not
dereference the 'struct device' in the cxl_root->port. find_cxl_root()
calls get_device() and takes a reference on the port 'struct device'
member. Use the __free() macro to ensure the dereference happens.

Fixes: 7a4f148dd8d5 ("cxl: Compute the entire CXL path latency and bandwidth data")
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170449246681.3779673.2288926019977963333.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/cdat.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 0df5379cf02f5..c6208aab452ff 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -162,7 +162,6 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 					struct xarray *dsmas_xa)
 {
 	struct access_coordinate c;
-	struct cxl_root *cxl_root;
 	struct dsmas_entry *dent;
 	int valid_entries = 0;
 	unsigned long index;
@@ -174,7 +173,11 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 		return rc;
 	}
 
-	cxl_root = find_cxl_root(port);
+	struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
+
+	if (!cxl_root)
+		return -ENODEV;
+
 	if (!cxl_root->ops || !cxl_root->ops->qos_class)
 		return -EOPNOTSUPP;
 
-- 
GitLab


From 66f11890d35a609012037cccfd9e63ed98474f99 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Fri, 5 Jan 2024 15:07:53 -0700
Subject: [PATCH 2303/4076] cxl: Refactor to use __free() for cxl_root
 allocation in cxl_find_nvdimm_bridge()

Use scope-based resource management __free() macro to drop the open coded
put_device() in cxl_find_nvdimm_bridge().

Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170449247353.3779673.5963704495491343135.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/pmem.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index da92a901b9e8c..e69625a8d6a1d 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -64,16 +64,14 @@ static int match_nvdimm_bridge(struct device *dev, void *data)
 
 struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd)
 {
-	struct cxl_root *cxl_root = find_cxl_root(cxlmd->endpoint);
-	struct cxl_port *port;
+	struct cxl_root *cxl_root __free(put_cxl_root) =
+		find_cxl_root(cxlmd->endpoint);
 	struct device *dev;
 
 	if (!cxl_root)
 		return NULL;
 
-	port = &cxl_root->port;
-	dev = device_find_child(&port->dev, NULL, match_nvdimm_bridge);
-	put_device(&port->dev);
+	dev = device_find_child(&cxl_root->port.dev, NULL, match_nvdimm_bridge);
 
 	if (!dev)
 		return NULL;
-- 
GitLab


From 321dd36c286b3f982b341ce9a273b0f66f0e00ed Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Fri, 5 Jan 2024 15:07:59 -0700
Subject: [PATCH 2304/4076] cxl: Refactor to use __free() for cxl_root
 allocation in cxl_endpoint_port_probe()

Use scope-based resource management __free() macro to drop the open coded
put_device() in cxl_endpoint_port_probe().

Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170449247973.3779673.15088722836135359275.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/port.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index 4f3a08fdc9e94..97c21566677aa 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -94,7 +94,6 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	struct cxl_endpoint_dvsec_info info = { .port = port };
 	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
-	struct cxl_root *cxl_root;
 	struct cxl_hdm *cxlhdm;
 	struct cxl_port *root;
 	int rc;
@@ -131,7 +130,8 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	 * This can't fail in practice as CXL root exit unregisters all
 	 * descendant ports and that in turn synchronizes with cxl_port_probe()
 	 */
-	cxl_root = find_cxl_root(port);
+	struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
+
 	root = &cxl_root->port;
 
 	/*
@@ -139,7 +139,6 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	 * assemble regions from committed decoders
 	 */
 	device_for_each_child(&port->dev, root, discover_region);
-	put_device(&root->dev);
 
 	return 0;
 }
-- 
GitLab


From 807c6d09cc99cbdf9933edfadcbaa8f0b856848d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 5 Jan 2024 22:03:58 +0000
Subject: [PATCH 2305/4076] netfs: Fix the loop that unmarks folios after
 writing to the cache

In the loop in netfs_rreq_unmark_after_write() that removes the PG_fscache
from folios after they've been written to the cache, as soon as we remove
the mark from a multipage folio, it can get split - and then we might see a
fragment of folio again.

Guard against this by advancing the 'unlocked' tracker to the index of the
last page in the folio to avoid a double removal of the PG_fscache mark.

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-afs@lists.infradead.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 1 +
 fs/netfs/io.c             | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 6cd8f7422e9ab..0b2b7a60dabc0 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -698,6 +698,7 @@ static void netfs_pages_written_back(struct netfs_io_request *wreq)
 	end_wb:
 		if (folio_test_fscache(folio))
 			folio_end_fscache(folio);
+		xas_advance(&xas, folio_next_index(folio) - 1);
 		folio_end_writeback(folio);
 	}
 
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 5b5af96cd4b95..4309edf338627 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -126,7 +126,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
 			 */
 			if (have_unlocked && folio_index(folio) <= unlocked)
 				continue;
-			unlocked = folio_index(folio);
+			unlocked = folio_next_index(folio) - 1;
 			trace_netfs_folio(folio, netfs_folio_trace_end_copy);
 			folio_end_fscache(folio);
 			have_unlocked = true;
-- 
GitLab


From 26a1a86dd093a10d0653429bf013dae6e95dccbf Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:29 -0800
Subject: [PATCH 2306/4076] cxl/events: Promote CXL event structures to a core
 header

UEFI code can process CXL events through CPER records.  Those records
use almost the same format as the CXL events.

Lift the CXL event structures to a core header to be shared in later
patches.

[jic123: drop "CXL rev 3.0" mention]

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-2-1bb8a4ca2c7a@intel.com
[djbw: add F: entry to maintainers for include/linux/cxl-event.h]
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 MAINTAINERS               |  1 +
 drivers/cxl/cxlmem.h      | 90 +------------------------------------
 include/linux/cxl-event.h | 95 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 97 insertions(+), 89 deletions(-)
 create mode 100644 include/linux/cxl-event.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 7cef2d2ef8d70..04f6c52d0a8f1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5245,6 +5245,7 @@ M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-cxl@vger.kernel.org
 S:	Maintained
 F:	drivers/cxl/
+F:	include/linux/cxl-event.h
 F:	include/uapi/linux/cxl_mem.h
 F:	tools/testing/cxl/
 
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index a2fcbca253f39..f0e7ebb84f028 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -6,6 +6,7 @@
 #include <linux/cdev.h>
 #include <linux/uuid.h>
 #include <linux/rcuwait.h>
+#include <linux/cxl-event.h>
 #include "cxl.h"
 
 /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
@@ -579,27 +580,6 @@ struct cxl_mbox_identify {
 	u8 qos_telemetry_caps;
 } __packed;
 
-/*
- * Common Event Record Format
- * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
- */
-struct cxl_event_record_hdr {
-	uuid_t id;
-	u8 length;
-	u8 flags[3];
-	__le16 handle;
-	__le16 related_handle;
-	__le64 timestamp;
-	u8 maint_op_class;
-	u8 reserved[15];
-} __packed;
-
-#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
-struct cxl_event_record_raw {
-	struct cxl_event_record_hdr hdr;
-	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
-} __packed;
-
 /*
  * Get Event Records output payload
  * CXL rev 3.0 section 8.2.9.2.2; Table 8-50
@@ -641,74 +621,6 @@ struct cxl_mbox_clear_event_payload {
 } __packed;
 #define CXL_CLEAR_EVENT_MAX_HANDLES U8_MAX
 
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
-struct cxl_event_gen_media {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
-	u8 device[3];
-	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
-	u8 reserved[46];
-} __packed;
-
-/*
- * DRAM Event Record - DER
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
- */
-#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
-struct cxl_event_dram {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
-	u8 nibble_mask[3];
-	u8 bank_group;
-	u8 bank;
-	u8 row[3];
-	u8 column[2];
-	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
-	u8 reserved[0x17];
-} __packed;
-
-/*
- * Get Health Info Record
- * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
- */
-struct cxl_get_health_info {
-	u8 health_status;
-	u8 media_status;
-	u8 add_status;
-	u8 life_used;
-	u8 device_temp[2];
-	u8 dirty_shutdown_cnt[4];
-	u8 cor_vol_err_cnt[4];
-	u8 cor_per_err_cnt[4];
-} __packed;
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-struct cxl_event_mem_module {
-	struct cxl_event_record_hdr hdr;
-	u8 event_type;
-	struct cxl_get_health_info info;
-	u8 reserved[0x3d];
-} __packed;
-
 struct cxl_mbox_get_partition_info {
 	__le64 active_volatile_cap;
 	__le64 active_persistent_cap;
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
new file mode 100644
index 0000000000000..0fc068123f8ed
--- /dev/null
+++ b/include/linux/cxl-event.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Intel Corporation. */
+#ifndef _LINUX_CXL_EVENT_H
+#define _LINUX_CXL_EVENT_H
+
+/*
+ * Common Event Record Format
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_hdr {
+	uuid_t id;
+	u8 length;
+	u8 flags[3];
+	__le16 handle;
+	__le16 related_handle;
+	__le64 timestamp;
+	u8 maint_op_class;
+	u8 reserved[15];
+} __packed;
+
+#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
+struct cxl_event_record_raw {
+	struct cxl_event_record_hdr hdr;
+	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
+} __packed;
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
+struct cxl_event_gen_media {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 device[3];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 reserved[46];
+} __packed;
+
+/*
+ * DRAM Event Record - DER
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
+ */
+#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
+struct cxl_event_dram {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 nibble_mask[3];
+	u8 bank_group;
+	u8 bank;
+	u8 row[3];
+	u8 column[2];
+	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
+	u8 reserved[0x17];
+} __packed;
+
+/*
+ * Get Health Info Record
+ * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
+ */
+struct cxl_get_health_info {
+	u8 health_status;
+	u8 media_status;
+	u8 add_status;
+	u8 life_used;
+	u8 device_temp[2];
+	u8 dirty_shutdown_cnt[4];
+	u8 cor_vol_err_cnt[4];
+	u8 cor_per_err_cnt[4];
+} __packed;
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+struct cxl_event_mem_module {
+	struct cxl_event_record_hdr hdr;
+	u8 event_type;
+	struct cxl_get_health_info info;
+	u8 reserved[0x3d];
+} __packed;
+
+#endif /* _LINUX_CXL_EVENT_H */
-- 
GitLab


From e49ad667815d37dc621ffdfb7302df6a7265bab8 Mon Sep 17 00:00:00 2001
From: Matt Ranostay <mranostay@ti.com>
Date: Tue, 28 Nov 2023 11:14:02 +0530
Subject: [PATCH 2307/4076] PCI: j721e: Add TI J784S4 PCIe configuration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add PCIe configuration for J784S4 SoC platform which has 4x lane
support.

Link: https://lore.kernel.org/linux-pci/20231128054402.2155183-6-s-vadapalli@ti.com
Tested-by: Achal Verma <a-verma1@ti.com>
Signed-off-by: Matt Ranostay <mranostay@ti.com>
Signed-off-by: Achal Verma <a-verma1@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
---
 drivers/pci/controller/cadence/pci-j721e.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index 645597856a1d9..85718246016b7 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -330,6 +330,20 @@ static const struct j721e_pcie_data am64_pcie_ep_data = {
 	.max_lanes = 1,
 };
 
+static const struct j721e_pcie_data j784s4_pcie_rc_data = {
+	.mode = PCI_MODE_RC,
+	.quirk_retrain_flag = true,
+	.byte_access_allowed = false,
+	.linkdown_irq_regfield = LINK_DOWN,
+	.max_lanes = 4,
+};
+
+static const struct j721e_pcie_data j784s4_pcie_ep_data = {
+	.mode = PCI_MODE_EP,
+	.linkdown_irq_regfield = LINK_DOWN,
+	.max_lanes = 4,
+};
+
 static const struct of_device_id of_j721e_pcie_match[] = {
 	{
 		.compatible = "ti,j721e-pcie-host",
@@ -355,6 +369,14 @@ static const struct of_device_id of_j721e_pcie_match[] = {
 		.compatible = "ti,am64-pcie-ep",
 		.data = &am64_pcie_ep_data,
 	},
+	{
+		.compatible = "ti,j784s4-pcie-host",
+		.data = &j784s4_pcie_rc_data,
+	},
+	{
+		.compatible = "ti,j784s4-pcie-ep",
+		.data = &j784s4_pcie_ep_data,
+	},
 	{},
 };
 
-- 
GitLab


From 177c9ac6ab3fa585608a16877b1fa1aad832571c Mon Sep 17 00:00:00 2001
From: Peter Robinson <pbrobinson@gmail.com>
Date: Thu, 4 Jan 2024 21:39:06 +0000
Subject: [PATCH 2308/4076] PCI: j721e: Make TI J721E depend on ARCH_K3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The J721E PCIe is hardware specific to TI SoC parts so add a dependency
on that so it's available for those SoC parts and for compile testing but
not necessarily everyone who enables the Cadence PCIe controller.

Link: https://lore.kernel.org/linux-pci/20240104213910.1426843-1-pbrobinson@gmail.com
Signed-off-by: Peter Robinson <pbrobinson@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/cadence/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pci/controller/cadence/Kconfig b/drivers/pci/controller/cadence/Kconfig
index 291d127113632..1d5a70c9055ed 100644
--- a/drivers/pci/controller/cadence/Kconfig
+++ b/drivers/pci/controller/cadence/Kconfig
@@ -47,6 +47,7 @@ config PCI_J721E
 
 config PCI_J721E_HOST
 	bool "TI J721E PCIe controller (host mode)"
+	depends on ARCH_K3 || COMPILE_TEST
 	depends on OF
 	select PCIE_CADENCE_HOST
 	select PCI_J721E
@@ -57,6 +58,7 @@ config PCI_J721E_HOST
 
 config PCI_J721E_EP
 	bool "TI J721E PCIe controller (endpoint mode)"
+	depends on ARCH_K3 || COMPILE_TEST
 	depends on OF
 	depends on PCI_ENDPOINT
 	select PCIE_CADENCE_EP
-- 
GitLab


From 516f366434e1db71b83c77b970cfcc0804671e1c Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@wdc.com>
Date: Fri, 15 Dec 2023 11:59:51 +0100
Subject: [PATCH 2309/4076] misc: pci_endpoint_test: Use a unique test pattern
 for each BAR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use a unique test pattern for each BAR in. This makes it easier to
detect/debug address translation issues, since a developer can dump
the backing memory on the EP side, using e.g. devmem, to verify that
the address translation for each BAR is actually correct.

Link: https://lore.kernel.org/linux-pci/20231215105952.1531683-1-nks@flawful.org
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/misc/pci_endpoint_test.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index af519088732d9..412749fed8cf3 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -263,6 +263,15 @@ fail:
 	return false;
 }
 
+static const u32 bar_test_pattern[] = {
+	0xA0A0A0A0,
+	0xA1A1A1A1,
+	0xA2A2A2A2,
+	0xA3A3A3A3,
+	0xA4A4A4A4,
+	0xA5A5A5A5,
+};
+
 static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 				  enum pci_barno barno)
 {
@@ -280,11 +289,12 @@ static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 		size = 0x4;
 
 	for (j = 0; j < size; j += 4)
-		pci_endpoint_test_bar_writel(test, barno, j, 0xA0A0A0A0);
+		pci_endpoint_test_bar_writel(test, barno, j,
+					     bar_test_pattern[barno]);
 
 	for (j = 0; j < size; j += 4) {
 		val = pci_endpoint_test_bar_readl(test, barno, j);
-		if (val != 0xA0A0A0A0)
+		if (val != bar_test_pattern[barno])
 			return false;
 	}
 
-- 
GitLab


From aea370b2aec9d36d6fdb8c9695c8022429b84492 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Wed, 20 Dec 2023 14:38:24 +0900
Subject: [PATCH 2310/4076] PCI: dwc: Drop host prefix from struct
 dw_pcie_host_ops members
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the name of the dw_pcie_host_ops struct makes it obvious that it's
for the PCIe Host, drop the host prefix from the struct members.

[kwilczynski: commit log]
Suggested-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/linux-pci/20231220053829.1921187-2-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Acked-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Acked-by: Lei Chuanhua <lchuanhua@maxlinear.com>
Acked-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
---
 drivers/pci/controller/dwc/pci-dra7xx.c       |  2 +-
 drivers/pci/controller/dwc/pci-exynos.c       |  2 +-
 drivers/pci/controller/dwc/pci-imx6.c         |  4 +--
 drivers/pci/controller/dwc/pci-keystone.c     |  6 ++--
 drivers/pci/controller/dwc/pci-layerscape.c   |  2 +-
 drivers/pci/controller/dwc/pci-meson.c        |  2 +-
 drivers/pci/controller/dwc/pcie-al.c          |  2 +-
 drivers/pci/controller/dwc/pcie-armada8k.c    |  2 +-
 drivers/pci/controller/dwc/pcie-artpec6.c     |  2 +-
 drivers/pci/controller/dwc/pcie-bt1.c         |  4 +--
 .../pci/controller/dwc/pcie-designware-host.c | 30 +++++++++----------
 drivers/pci/controller/dwc/pcie-designware.h  |  8 ++---
 drivers/pci/controller/dwc/pcie-dw-rockchip.c |  2 +-
 drivers/pci/controller/dwc/pcie-fu740.c       |  2 +-
 drivers/pci/controller/dwc/pcie-histb.c       |  2 +-
 drivers/pci/controller/dwc/pcie-intel-gw.c    |  2 +-
 drivers/pci/controller/dwc/pcie-kirin.c       |  2 +-
 drivers/pci/controller/dwc/pcie-qcom.c        |  6 ++--
 drivers/pci/controller/dwc/pcie-rcar-gen4.c   |  4 +--
 drivers/pci/controller/dwc/pcie-spear13xx.c   |  2 +-
 drivers/pci/controller/dwc/pcie-tegra194.c    |  2 +-
 drivers/pci/controller/dwc/pcie-uniphier.c    |  2 +-
 drivers/pci/controller/dwc/pcie-visconti.c    |  2 +-
 23 files changed, 47 insertions(+), 47 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index b445ffe95e3f0..6125a838f4b1d 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -371,7 +371,7 @@ static int dra7xx_pcie_init_irq_domain(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops dra7xx_pcie_host_ops = {
-	.host_init = dra7xx_pcie_host_init,
+	.init = dra7xx_pcie_host_init,
 };
 
 static void dra7xx_pcie_ep_init(struct dw_pcie_ep *ep)
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index c6bede3469320..673ae213203fc 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -268,7 +268,7 @@ static int exynos_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops exynos_pcie_host_ops = {
-	.host_init = exynos_pcie_host_init,
+	.init = exynos_pcie_host_init,
 };
 
 static int exynos_add_pcie_port(struct exynos_pcie *ep,
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 74703362aeec7..b02f6f14a4117 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -1039,8 +1039,8 @@ static void imx6_pcie_host_exit(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops imx6_pcie_host_ops = {
-	.host_init = imx6_pcie_host_init,
-	.host_deinit = imx6_pcie_host_exit,
+	.init = imx6_pcie_host_init,
+	.deinit = imx6_pcie_host_exit,
 };
 
 static const struct dw_pcie_ops dw_pcie_ops = {
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 0def919f89faf..3711347ddc872 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -838,12 +838,12 @@ static int __init ks_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops ks_pcie_host_ops = {
-	.host_init = ks_pcie_host_init,
-	.msi_host_init = ks_pcie_msi_host_init,
+	.init = ks_pcie_host_init,
+	.msi_init = ks_pcie_msi_host_init,
 };
 
 static const struct dw_pcie_host_ops ks_pcie_am654_host_ops = {
-	.host_init = ks_pcie_host_init,
+	.init = ks_pcie_host_init,
 };
 
 static irqreturn_t ks_pcie_err_irq_handler(int irq, void *priv)
diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index 37956e09c65bd..0c3d7ef729cb6 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -169,7 +169,7 @@ static int ls_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops ls_pcie_host_ops = {
-	.host_init = ls_pcie_host_init,
+	.init = ls_pcie_host_init,
 	.pme_turn_off = ls_pcie_send_turnoff_msg,
 };
 
diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c
index 407558f5d74ac..6477c83262c20 100644
--- a/drivers/pci/controller/dwc/pci-meson.c
+++ b/drivers/pci/controller/dwc/pci-meson.c
@@ -389,7 +389,7 @@ static int meson_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops meson_pcie_host_ops = {
-	.host_init = meson_pcie_host_init,
+	.init = meson_pcie_host_init,
 };
 
 static const struct dw_pcie_ops dw_pcie_ops = {
diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c
index b8cb77c9c4bd2..6dfdda59f3283 100644
--- a/drivers/pci/controller/dwc/pcie-al.c
+++ b/drivers/pci/controller/dwc/pcie-al.c
@@ -311,7 +311,7 @@ static int al_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops al_pcie_host_ops = {
-	.host_init = al_pcie_host_init,
+	.init = al_pcie_host_init,
 };
 
 static int al_pcie_probe(struct platform_device *pdev)
diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c
index 5c999e15c357f..b5c599ccaacf0 100644
--- a/drivers/pci/controller/dwc/pcie-armada8k.c
+++ b/drivers/pci/controller/dwc/pcie-armada8k.c
@@ -225,7 +225,7 @@ static irqreturn_t armada8k_pcie_irq_handler(int irq, void *arg)
 }
 
 static const struct dw_pcie_host_ops armada8k_pcie_host_ops = {
-	.host_init = armada8k_pcie_host_init,
+	.init = armada8k_pcie_host_init,
 };
 
 static int armada8k_add_pcie_port(struct armada8k_pcie *pcie,
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 9b572a2b2c9a5..2f32fcd8933c7 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -333,7 +333,7 @@ static int artpec6_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops artpec6_pcie_host_ops = {
-	.host_init = artpec6_pcie_host_init,
+	.init = artpec6_pcie_host_init,
 };
 
 static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep)
diff --git a/drivers/pci/controller/dwc/pcie-bt1.c b/drivers/pci/controller/dwc/pcie-bt1.c
index 17e696797ff50..76d0ddea80075 100644
--- a/drivers/pci/controller/dwc/pcie-bt1.c
+++ b/drivers/pci/controller/dwc/pcie-bt1.c
@@ -559,8 +559,8 @@ static void bt1_pcie_host_deinit(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops bt1_pcie_host_ops = {
-	.host_init = bt1_pcie_host_init,
-	.host_deinit = bt1_pcie_host_deinit,
+	.init = bt1_pcie_host_init,
+	.deinit = bt1_pcie_host_deinit,
 };
 
 static struct bt1_pcie *bt1_pcie_create_data(struct platform_device *pdev)
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 7991f0e179b21..d5fc31f8345f7 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -441,14 +441,14 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 	bridge->ops = &dw_pcie_ops;
 	bridge->child_ops = &dw_child_pcie_ops;
 
-	if (pp->ops->host_init) {
-		ret = pp->ops->host_init(pp);
+	if (pp->ops->init) {
+		ret = pp->ops->init(pp);
 		if (ret)
 			return ret;
 	}
 
 	if (pci_msi_enabled()) {
-		pp->has_msi_ctrl = !(pp->ops->msi_host_init ||
+		pp->has_msi_ctrl = !(pp->ops->msi_init ||
 				     of_property_read_bool(np, "msi-parent") ||
 				     of_property_read_bool(np, "msi-map"));
 
@@ -464,8 +464,8 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 			goto err_deinit_host;
 		}
 
-		if (pp->ops->msi_host_init) {
-			ret = pp->ops->msi_host_init(pp);
+		if (pp->ops->msi_init) {
+			ret = pp->ops->msi_init(pp);
 			if (ret < 0)
 				goto err_deinit_host;
 		} else if (pp->has_msi_ctrl) {
@@ -502,8 +502,8 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 	if (ret)
 		goto err_stop_link;
 
-	if (pp->ops->host_post_init)
-		pp->ops->host_post_init(pp);
+	if (pp->ops->post_init)
+		pp->ops->post_init(pp);
 
 	return 0;
 
@@ -518,8 +518,8 @@ err_free_msi:
 		dw_pcie_free_msi(pp);
 
 err_deinit_host:
-	if (pp->ops->host_deinit)
-		pp->ops->host_deinit(pp);
+	if (pp->ops->deinit)
+		pp->ops->deinit(pp);
 
 	return ret;
 }
@@ -539,8 +539,8 @@ void dw_pcie_host_deinit(struct dw_pcie_rp *pp)
 	if (pp->has_msi_ctrl)
 		dw_pcie_free_msi(pp);
 
-	if (pp->ops->host_deinit)
-		pp->ops->host_deinit(pp);
+	if (pp->ops->deinit)
+		pp->ops->deinit(pp);
 }
 EXPORT_SYMBOL_GPL(dw_pcie_host_deinit);
 
@@ -842,8 +842,8 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci)
 		return ret;
 	}
 
-	if (pci->pp.ops->host_deinit)
-		pci->pp.ops->host_deinit(&pci->pp);
+	if (pci->pp.ops->deinit)
+		pci->pp.ops->deinit(&pci->pp);
 
 	pci->suspended = true;
 
@@ -860,8 +860,8 @@ int dw_pcie_resume_noirq(struct dw_pcie *pci)
 
 	pci->suspended = false;
 
-	if (pci->pp.ops->host_init) {
-		ret = pci->pp.ops->host_init(&pci->pp);
+	if (pci->pp.ops->init) {
+		ret = pci->pp.ops->init(&pci->pp);
 		if (ret) {
 			dev_err(pci->dev, "Host init failed: %d\n", ret);
 			return ret;
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 55ff76e3d3846..5c4518ad1bec9 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -300,10 +300,10 @@ enum dw_pcie_ltssm {
 };
 
 struct dw_pcie_host_ops {
-	int (*host_init)(struct dw_pcie_rp *pp);
-	void (*host_deinit)(struct dw_pcie_rp *pp);
-	void (*host_post_init)(struct dw_pcie_rp *pp);
-	int (*msi_host_init)(struct dw_pcie_rp *pp);
+	int (*init)(struct dw_pcie_rp *pp);
+	void (*deinit)(struct dw_pcie_rp *pp);
+	void (*post_init)(struct dw_pcie_rp *pp);
+	int (*msi_init)(struct dw_pcie_rp *pp);
 	void (*pme_turn_off)(struct dw_pcie_rp *pp);
 };
 
diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index 2fe42c70097fd..961dabcb1ec8a 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -215,7 +215,7 @@ static int rockchip_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops rockchip_pcie_host_ops = {
-	.host_init = rockchip_pcie_host_init,
+	.init = rockchip_pcie_host_init,
 };
 
 static int rockchip_pcie_clk_init(struct rockchip_pcie *rockchip)
diff --git a/drivers/pci/controller/dwc/pcie-fu740.c b/drivers/pci/controller/dwc/pcie-fu740.c
index 1e9b44b8bba48..66367252032b8 100644
--- a/drivers/pci/controller/dwc/pcie-fu740.c
+++ b/drivers/pci/controller/dwc/pcie-fu740.c
@@ -279,7 +279,7 @@ static int fu740_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops fu740_pcie_host_ops = {
-	.host_init = fu740_pcie_host_init,
+	.init = fu740_pcie_host_init,
 };
 
 static const struct dw_pcie_ops dw_pcie_ops = {
diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index fd484cc7c481d..7a11c618b9d9c 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -198,7 +198,7 @@ static int histb_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops histb_pcie_host_ops = {
-	.host_init = histb_pcie_host_init,
+	.init = histb_pcie_host_init,
 };
 
 static void histb_pcie_host_disable(struct histb_pcie *hipcie)
diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c
index c9c93524e01dc..be52e9db44af6 100644
--- a/drivers/pci/controller/dwc/pcie-intel-gw.c
+++ b/drivers/pci/controller/dwc/pcie-intel-gw.c
@@ -391,7 +391,7 @@ static const struct dw_pcie_ops intel_pcie_ops = {
 };
 
 static const struct dw_pcie_host_ops intel_pcie_dw_ops = {
-	.host_init =		intel_pcie_rc_init,
+	.init =		intel_pcie_rc_init,
 };
 
 static int intel_pcie_probe(struct platform_device *pdev)
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index 2ee146767971c..c50e183f88d62 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -672,7 +672,7 @@ static const struct dw_pcie_ops kirin_dw_pcie_ops = {
 };
 
 static const struct dw_pcie_host_ops kirin_pcie_host_ops = {
-	.host_init = kirin_pcie_host_init,
+	.init = kirin_pcie_host_init,
 };
 
 static int kirin_pcie_power_off(struct kirin_pcie *kirin_pcie)
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 6902e97719d13..cd986f50ec4a4 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -1244,9 +1244,9 @@ static void qcom_pcie_host_post_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops qcom_pcie_dw_ops = {
-	.host_init	= qcom_pcie_host_init,
-	.host_deinit	= qcom_pcie_host_deinit,
-	.host_post_init	= qcom_pcie_host_post_init,
+	.init		= qcom_pcie_host_init,
+	.deinit		= qcom_pcie_host_deinit,
+	.post_init	= qcom_pcie_host_post_init,
 };
 
 /* Qcom IP rev.: 2.1.0	Synopsys IP rev.: 4.01a */
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 3bc45e513b3d5..193ed88d3c2f3 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -307,8 +307,8 @@ static void rcar_gen4_pcie_host_deinit(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops rcar_gen4_pcie_host_ops = {
-	.host_init = rcar_gen4_pcie_host_init,
-	.host_deinit = rcar_gen4_pcie_host_deinit,
+	.init = rcar_gen4_pcie_host_init,
+	.deinit = rcar_gen4_pcie_host_deinit,
 };
 
 static int rcar_gen4_add_dw_pcie_rp(struct rcar_gen4_pcie *rcar)
diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c
index 99d47ae80331f..201dced209f08 100644
--- a/drivers/pci/controller/dwc/pcie-spear13xx.c
+++ b/drivers/pci/controller/dwc/pcie-spear13xx.c
@@ -148,7 +148,7 @@ static int spear13xx_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops spear13xx_pcie_host_ops = {
-	.host_init = spear13xx_pcie_host_init,
+	.init = spear13xx_pcie_host_init,
 };
 
 static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie,
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 0fe113598ebbc..52e26ed61380e 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -1060,7 +1060,7 @@ static const struct dw_pcie_ops tegra_dw_pcie_ops = {
 };
 
 static const struct dw_pcie_host_ops tegra_pcie_dw_host_ops = {
-	.host_init = tegra_pcie_dw_host_init,
+	.init = tegra_pcie_dw_host_init,
 };
 
 static void tegra_pcie_disable_phy(struct tegra_pcie_dw *pcie)
diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c
index 48c3eba817b43..354fb3bd0a192 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier.c
@@ -311,7 +311,7 @@ static int uniphier_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops uniphier_pcie_host_ops = {
-	.host_init = uniphier_pcie_host_init,
+	.init = uniphier_pcie_host_init,
 };
 
 static int uniphier_pcie_host_enable(struct uniphier_pcie *pcie)
diff --git a/drivers/pci/controller/dwc/pcie-visconti.c b/drivers/pci/controller/dwc/pcie-visconti.c
index 71026fefa3668..318c278e65c89 100644
--- a/drivers/pci/controller/dwc/pcie-visconti.c
+++ b/drivers/pci/controller/dwc/pcie-visconti.c
@@ -236,7 +236,7 @@ static int visconti_pcie_host_init(struct dw_pcie_rp *pp)
 }
 
 static const struct dw_pcie_host_ops visconti_pcie_host_ops = {
-	.host_init = visconti_pcie_host_init,
+	.init = visconti_pcie_host_init,
 };
 
 static int visconti_get_resources(struct platform_device *pdev,
-- 
GitLab


From 756dcb5a820aab4429e004bb070674116062dea3 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Wed, 20 Dec 2023 14:38:25 +0900
Subject: [PATCH 2311/4076] PCI: dwc: Rename .ep_init to .init in struct
 dw_pcie_ep_ops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the name of the dw_pcie_ep_ops struct makes it obvious that it's
for the PCIe Endpoint, rename the struct member .ep_init to .init.

[kwilczynski: commit log]
Suggested-by: Serge Semin <fancer.lancer@gmail.com>
Suggested-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/linux-pci/20231220053829.1921187-3-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Srikanth Thokala <srikanth.thokala@intel.com>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Acked-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
---
 drivers/pci/controller/dwc/pci-dra7xx.c           | 2 +-
 drivers/pci/controller/dwc/pci-imx6.c             | 2 +-
 drivers/pci/controller/dwc/pci-keystone.c         | 2 +-
 drivers/pci/controller/dwc/pci-layerscape-ep.c    | 2 +-
 drivers/pci/controller/dwc/pcie-artpec6.c         | 2 +-
 drivers/pci/controller/dwc/pcie-designware-ep.c   | 4 ++--
 drivers/pci/controller/dwc/pcie-designware-plat.c | 2 +-
 drivers/pci/controller/dwc/pcie-designware.h      | 2 +-
 drivers/pci/controller/dwc/pcie-keembay.c         | 2 +-
 drivers/pci/controller/dwc/pcie-qcom-ep.c         | 2 +-
 drivers/pci/controller/dwc/pcie-rcar-gen4.c       | 2 +-
 drivers/pci/controller/dwc/pcie-uniphier-ep.c     | 2 +-
 12 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index 6125a838f4b1d..1ac1be12a2355 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -436,7 +436,7 @@ dra7xx_pcie_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
-	.ep_init = dra7xx_pcie_ep_init,
+	.init = dra7xx_pcie_ep_init,
 	.raise_irq = dra7xx_pcie_raise_irq,
 	.get_features = dra7xx_pcie_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index b02f6f14a4117..644916a67a384 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -1093,7 +1093,7 @@ imx6_pcie_ep_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
-	.ep_init = imx6_pcie_ep_init,
+	.init = imx6_pcie_ep_init,
 	.raise_irq = imx6_pcie_ep_raise_irq,
 	.get_features = imx6_pcie_ep_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 3711347ddc872..d0f50cceede96 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -944,7 +944,7 @@ ks_pcie_am654_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops ks_pcie_am654_ep_ops = {
-	.ep_init = ks_pcie_am654_ep_init,
+	.init = ks_pcie_am654_ep_init,
 	.raise_irq = ks_pcie_am654_raise_irq,
 	.get_features = &ks_pcie_am654_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 3d3c50ef4b6ff..4e4b687ef508b 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -195,7 +195,7 @@ static unsigned int ls_pcie_ep_func_conf_select(struct dw_pcie_ep *ep,
 }
 
 static const struct dw_pcie_ep_ops ls_pcie_ep_ops = {
-	.ep_init = ls_pcie_ep_init,
+	.init = ls_pcie_ep_init,
 	.raise_irq = ls_pcie_ep_raise_irq,
 	.get_features = ls_pcie_ep_get_features,
 	.func_conf_select = ls_pcie_ep_func_conf_select,
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 2f32fcd8933c7..f6afa96a97e4d 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -370,7 +370,7 @@ static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 }
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
-	.ep_init = artpec6_pcie_ep_init,
+	.init = artpec6_pcie_ep_init,
 	.raise_irq = artpec6_pcie_raise_irq,
 };
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index bc94d7f395357..dea52b59d1d32 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -795,8 +795,8 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 		list_add_tail(&ep_func->list, &ep->func_list);
 	}
 
-	if (ep->ops->ep_init)
-		ep->ops->ep_init(ep);
+	if (ep->ops->init)
+		ep->ops->init(ep);
 
 	ret = pci_epc_mem_init(epc, ep->phys_base, ep->addr_size,
 			       ep->page_size);
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index b625841e98aa0..97088b7663e00 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -74,7 +74,7 @@ dw_plat_pcie_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
-	.ep_init = dw_plat_pcie_ep_init,
+	.init = dw_plat_pcie_ep_init,
 	.raise_irq = dw_plat_pcie_ep_raise_irq,
 	.get_features = dw_plat_pcie_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 5c4518ad1bec9..3bc03a93732f8 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -332,7 +332,7 @@ struct dw_pcie_rp {
 
 struct dw_pcie_ep_ops {
 	void	(*pre_init)(struct dw_pcie_ep *ep);
-	void	(*ep_init)(struct dw_pcie_ep *ep);
+	void	(*init)(struct dw_pcie_ep *ep);
 	void	(*deinit)(struct dw_pcie_ep *ep);
 	int	(*raise_irq)(struct dw_pcie_ep *ep, u8 func_no,
 			     enum pci_epc_irq_type type, u16 interrupt_num);
diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c
index 289bff99d7628..3c38e047d5edd 100644
--- a/drivers/pci/controller/dwc/pcie-keembay.c
+++ b/drivers/pci/controller/dwc/pcie-keembay.c
@@ -325,7 +325,7 @@ keembay_pcie_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops keembay_pcie_ep_ops = {
-	.ep_init	= keembay_pcie_ep_init,
+	.init	= keembay_pcie_ep_init,
 	.raise_irq	= keembay_pcie_ep_raise_irq,
 	.get_features	= keembay_pcie_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 9e58f055199ad..2b6f7c144c61d 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -796,7 +796,7 @@ static void qcom_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops pci_ep_ops = {
-	.ep_init = qcom_pcie_ep_init,
+	.init = qcom_pcie_ep_init,
 	.raise_irq = qcom_pcie_ep_raise_irq,
 	.get_features = qcom_pcie_epc_get_features,
 };
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 193ed88d3c2f3..1c017997fb3e2 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -408,7 +408,7 @@ static unsigned int rcar_gen4_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep,
 
 static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.pre_init = rcar_gen4_pcie_ep_pre_init,
-	.ep_init = rcar_gen4_pcie_ep_init,
+	.init = rcar_gen4_pcie_ep_init,
 	.deinit = rcar_gen4_pcie_ep_deinit,
 	.raise_irq = rcar_gen4_pcie_ep_raise_irq,
 	.get_features = rcar_gen4_pcie_ep_get_features,
diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
index cba3c88fcf395..40bd468f7e119 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier-ep.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
@@ -284,7 +284,7 @@ uniphier_pcie_get_features(struct dw_pcie_ep *ep)
 }
 
 static const struct dw_pcie_ep_ops uniphier_pcie_ep_ops = {
-	.ep_init = uniphier_pcie_ep_init,
+	.init = uniphier_pcie_ep_init,
 	.raise_irq = uniphier_pcie_ep_raise_irq,
 	.get_features = uniphier_pcie_get_features,
 };
-- 
GitLab


From 641f79beeebcad8f10a4e76d50cc81fc07af7cc1 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Wed, 20 Dec 2023 14:38:26 +0900
Subject: [PATCH 2312/4076] PCI: dwc: Rename .func_conf_select to
 .get_dbi_offset in struct dw_pcie_ep_ops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the struct member .func_conf_select makes the intentions behind it
difficult to ascertain from its name alone, rename it to .get_dbi_offset
to make the intended usage more obvious.

[kwilczynski: commmit log]
Suggested-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/linux-pci/20231220053829.1921187-4-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
---
 .../pci/controller/dwc/pci-layerscape-ep.c    |   5 +-
 .../pci/controller/dwc/pcie-designware-ep.c   | 108 +++++++++---------
 drivers/pci/controller/dwc/pcie-designware.h  |   2 +-
 drivers/pci/controller/dwc/pcie-rcar-gen4.c   |   4 +-
 4 files changed, 59 insertions(+), 60 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 4e4b687ef508b..961ff1b719a10 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -184,8 +184,7 @@ static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 	}
 }
 
-static unsigned int ls_pcie_ep_func_conf_select(struct dw_pcie_ep *ep,
-						u8 func_no)
+static unsigned int ls_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep, u8 func_no)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct ls_pcie_ep *pcie = to_ls_pcie_ep(pci);
@@ -198,7 +197,7 @@ static const struct dw_pcie_ep_ops ls_pcie_ep_ops = {
 	.init = ls_pcie_ep_init,
 	.raise_irq = ls_pcie_ep_raise_irq,
 	.get_features = ls_pcie_ep_get_features,
-	.func_conf_select = ls_pcie_ep_func_conf_select,
+	.get_dbi_offset = ls_pcie_ep_get_dbi_offset,
 };
 
 static const struct ls_pcie_ep_drvdata ls1_ep_drvdata = {
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index dea52b59d1d32..adef0bce84d69 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -43,14 +43,14 @@ dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no)
 	return NULL;
 }
 
-static unsigned int dw_pcie_ep_func_select(struct dw_pcie_ep *ep, u8 func_no)
+static unsigned int dw_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep, u8 func_no)
 {
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 
-	if (ep->ops->func_conf_select)
-		func_offset = ep->ops->func_conf_select(ep, func_no);
+	if (ep->ops->get_dbi_offset)
+		dbi_offset = ep->ops->get_dbi_offset(ep, func_no);
 
-	return func_offset;
+	return dbi_offset;
 }
 
 static unsigned int dw_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep, u8 func_no)
@@ -59,8 +59,8 @@ static unsigned int dw_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep, u8 func_no
 
 	if (ep->ops->get_dbi2_offset)
 		dbi2_offset = ep->ops->get_dbi2_offset(ep, func_no);
-	else if (ep->ops->func_conf_select)     /* for backward compatibility */
-		dbi2_offset = ep->ops->func_conf_select(ep, func_no);
+	else if (ep->ops->get_dbi_offset)     /* for backward compatibility */
+		dbi2_offset = ep->ops->get_dbi_offset(ep, func_no);
 
 	return dbi2_offset;
 }
@@ -68,14 +68,14 @@ static unsigned int dw_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep, u8 func_no
 static void __dw_pcie_ep_reset_bar(struct dw_pcie *pci, u8 func_no,
 				   enum pci_barno bar, int flags)
 {
-	unsigned int func_offset, dbi2_offset;
+	unsigned int dbi_offset, dbi2_offset;
 	struct dw_pcie_ep *ep = &pci->ep;
 	u32 reg, reg_dbi2;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 	dbi2_offset = dw_pcie_ep_get_dbi2_offset(ep, func_no);
 
-	reg = func_offset + PCI_BASE_ADDRESS_0 + (4 * bar);
+	reg = dbi_offset + PCI_BASE_ADDRESS_0 + (4 * bar);
 	reg_dbi2 = dbi2_offset + PCI_BASE_ADDRESS_0 + (4 * bar);
 	dw_pcie_dbi_ro_wr_en(pci);
 	dw_pcie_writel_dbi2(pci, reg_dbi2, 0x0);
@@ -102,16 +102,16 @@ static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no,
 		u8 cap_ptr, u8 cap)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 	u8 cap_id, next_cap_ptr;
 	u16 reg;
 
 	if (!cap_ptr)
 		return 0;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
-	reg = dw_pcie_readw_dbi(pci, func_offset + cap_ptr);
+	reg = dw_pcie_readw_dbi(pci, dbi_offset + cap_ptr);
 	cap_id = (reg & 0x00ff);
 
 	if (cap_id > PCI_CAP_ID_MAX)
@@ -127,13 +127,13 @@ static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no,
 static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 	u8 next_cap_ptr;
 	u16 reg;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
-	reg = dw_pcie_readw_dbi(pci, func_offset + PCI_CAPABILITY_LIST);
+	reg = dw_pcie_readw_dbi(pci, dbi_offset + PCI_CAPABILITY_LIST);
 	next_cap_ptr = (reg & 0x00ff);
 
 	return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap);
@@ -144,23 +144,23 @@ static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_VENDOR_ID, hdr->vendorid);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_DEVICE_ID, hdr->deviceid);
-	dw_pcie_writeb_dbi(pci, func_offset + PCI_REVISION_ID, hdr->revid);
-	dw_pcie_writeb_dbi(pci, func_offset + PCI_CLASS_PROG, hdr->progif_code);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_CLASS_DEVICE,
+	dw_pcie_writew_dbi(pci, dbi_offset + PCI_VENDOR_ID, hdr->vendorid);
+	dw_pcie_writew_dbi(pci, dbi_offset + PCI_DEVICE_ID, hdr->deviceid);
+	dw_pcie_writeb_dbi(pci, dbi_offset + PCI_REVISION_ID, hdr->revid);
+	dw_pcie_writeb_dbi(pci, dbi_offset + PCI_CLASS_PROG, hdr->progif_code);
+	dw_pcie_writew_dbi(pci, dbi_offset + PCI_CLASS_DEVICE,
 			   hdr->subclass_code | hdr->baseclass_code << 8);
-	dw_pcie_writeb_dbi(pci, func_offset + PCI_CACHE_LINE_SIZE,
+	dw_pcie_writeb_dbi(pci, dbi_offset + PCI_CACHE_LINE_SIZE,
 			   hdr->cache_line_size);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_SUBSYSTEM_VENDOR_ID,
+	dw_pcie_writew_dbi(pci, dbi_offset + PCI_SUBSYSTEM_VENDOR_ID,
 			   hdr->subsys_vendor_id);
-	dw_pcie_writew_dbi(pci, func_offset + PCI_SUBSYSTEM_ID, hdr->subsys_id);
-	dw_pcie_writeb_dbi(pci, func_offset + PCI_INTERRUPT_PIN,
+	dw_pcie_writew_dbi(pci, dbi_offset + PCI_SUBSYSTEM_ID, hdr->subsys_id);
+	dw_pcie_writeb_dbi(pci, dbi_offset + PCI_INTERRUPT_PIN,
 			   hdr->interrupt_pin);
 	dw_pcie_dbi_ro_wr_dis(pci);
 
@@ -243,17 +243,17 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int func_offset, dbi2_offset;
+	unsigned int dbi_offset, dbi2_offset;
 	enum pci_barno bar = epf_bar->barno;
 	size_t size = epf_bar->size;
 	int flags = epf_bar->flags;
 	u32 reg, reg_dbi2;
 	int ret, type;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 	dbi2_offset = dw_pcie_ep_get_dbi2_offset(ep, func_no);
 
-	reg = PCI_BASE_ADDRESS_0 + (4 * bar) + func_offset;
+	reg = PCI_BASE_ADDRESS_0 + (4 * bar) + dbi_offset;
 	reg_dbi2 = PCI_BASE_ADDRESS_0 + (4 * bar) + dbi2_offset;
 
 	if (!(flags & PCI_BASE_ADDRESS_SPACE))
@@ -337,16 +337,16 @@ static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	u32 val, reg;
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
-	reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS;
+	reg = ep_func->msi_cap + dbi_offset + PCI_MSI_FLAGS;
 	val = dw_pcie_readw_dbi(pci, reg);
 	if (!(val & PCI_MSI_FLAGS_ENABLE))
 		return -EINVAL;
@@ -362,16 +362,16 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	u32 val, reg;
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
-	reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS;
+	reg = ep_func->msi_cap + dbi_offset + PCI_MSI_FLAGS;
 	val = dw_pcie_readw_dbi(pci, reg);
 	val &= ~PCI_MSI_FLAGS_QMASK;
 	val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, interrupts);
@@ -387,16 +387,16 @@ static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	u32 val, reg;
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msix_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_FLAGS;
+	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_FLAGS;
 	val = dw_pcie_readw_dbi(pci, reg);
 	if (!(val & PCI_MSIX_FLAGS_ENABLE))
 		return -EINVAL;
@@ -412,7 +412,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	u32 val, reg;
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
@@ -421,19 +421,19 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 
 	dw_pcie_dbi_ro_wr_en(pci);
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_FLAGS;
+	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_FLAGS;
 	val = dw_pcie_readw_dbi(pci, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
 	val |= interrupts;
 	dw_pcie_writew_dbi(pci, reg, val);
 
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_TABLE;
+	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_TABLE;
 	val = offset | bir;
 	dw_pcie_writel_dbi(pci, reg, val);
 
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_PBA;
+	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_PBA;
 	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
 	dw_pcie_writel_dbi(pci, reg, val);
 
@@ -514,7 +514,7 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	struct dw_pcie_ep_func *ep_func;
 	struct pci_epc *epc = ep->epc;
 	unsigned int aligned_offset;
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 	u16 msg_ctrl, msg_data;
 	u32 msg_addr_lower, msg_addr_upper, reg;
 	u64 msg_addr;
@@ -525,22 +525,22 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
 	/* Raise MSI per the PCI Local Bus Specification Revision 3.0, 6.8.1. */
-	reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS;
+	reg = ep_func->msi_cap + dbi_offset + PCI_MSI_FLAGS;
 	msg_ctrl = dw_pcie_readw_dbi(pci, reg);
 	has_upper = !!(msg_ctrl & PCI_MSI_FLAGS_64BIT);
-	reg = ep_func->msi_cap + func_offset + PCI_MSI_ADDRESS_LO;
+	reg = ep_func->msi_cap + dbi_offset + PCI_MSI_ADDRESS_LO;
 	msg_addr_lower = dw_pcie_readl_dbi(pci, reg);
 	if (has_upper) {
-		reg = ep_func->msi_cap + func_offset + PCI_MSI_ADDRESS_HI;
+		reg = ep_func->msi_cap + dbi_offset + PCI_MSI_ADDRESS_HI;
 		msg_addr_upper = dw_pcie_readl_dbi(pci, reg);
-		reg = ep_func->msi_cap + func_offset + PCI_MSI_DATA_64;
+		reg = ep_func->msi_cap + dbi_offset + PCI_MSI_DATA_64;
 		msg_data = dw_pcie_readw_dbi(pci, reg);
 	} else {
 		msg_addr_upper = 0;
-		reg = ep_func->msi_cap + func_offset + PCI_MSI_DATA_32;
+		reg = ep_func->msi_cap + dbi_offset + PCI_MSI_DATA_32;
 		msg_data = dw_pcie_readw_dbi(pci, reg);
 	}
 	aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1);
@@ -585,7 +585,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	struct dw_pcie_ep_func *ep_func;
 	struct pci_epf_msix_tbl *msix_tbl;
 	struct pci_epc *epc = ep->epc;
-	unsigned int func_offset = 0;
+	unsigned int dbi_offset = 0;
 	u32 reg, msg_data, vec_ctrl;
 	unsigned int aligned_offset;
 	u32 tbl_offset;
@@ -597,9 +597,9 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	if (!ep_func || !ep_func->msix_cap)
 		return -EINVAL;
 
-	func_offset = dw_pcie_ep_func_select(ep, func_no);
+	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
-	reg = ep_func->msix_cap + func_offset + PCI_MSIX_TABLE;
+	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_TABLE;
 	tbl_offset = dw_pcie_readl_dbi(pci, reg);
 	bir = FIELD_GET(PCI_MSIX_TABLE_BIR, tbl_offset);
 	tbl_offset &= PCI_MSIX_TABLE_OFFSET;
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 3bc03a93732f8..5e36da166ffe8 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -344,7 +344,7 @@ struct dw_pcie_ep_ops {
 	 * return a 0, and implement code in callback function of platform
 	 * driver.
 	 */
-	unsigned int (*func_conf_select)(struct dw_pcie_ep *ep, u8 func_no);
+	unsigned int (*get_dbi_offset)(struct dw_pcie_ep *ep, u8 func_no);
 	unsigned int (*get_dbi2_offset)(struct dw_pcie_ep *ep, u8 func_no);
 };
 
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 1c017997fb3e2..70492f562e48f 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -394,7 +394,7 @@ rcar_gen4_pcie_ep_get_features(struct dw_pcie_ep *ep)
 	return &rcar_gen4_pcie_epc_features;
 }
 
-static unsigned int rcar_gen4_pcie_ep_func_conf_select(struct dw_pcie_ep *ep,
+static unsigned int rcar_gen4_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep,
 						       u8 func_no)
 {
 	return func_no * RCAR_GEN4_PCIE_EP_FUNC_DBI_OFFSET;
@@ -412,7 +412,7 @@ static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.deinit = rcar_gen4_pcie_ep_deinit,
 	.raise_irq = rcar_gen4_pcie_ep_raise_irq,
 	.get_features = rcar_gen4_pcie_ep_get_features,
-	.func_conf_select = rcar_gen4_pcie_ep_func_conf_select,
+	.get_dbi_offset = rcar_gen4_pcie_ep_get_dbi_offset,
 	.get_dbi2_offset = rcar_gen4_pcie_ep_get_dbi2_offset,
 };
 
-- 
GitLab


From 70fa02ca14466ee35c5a6b69175475b43b4931f8 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Wed, 20 Dec 2023 14:38:27 +0900
Subject: [PATCH 2313/4076] PCI: dwc: Add dw_pcie_ep_{read,write}_dbi[2]
 helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current code calculated some dbi[2] registers' offset by calling
dw_pcie_ep_get_dbi[2]_offset() in each function. To improve the code
readability, add dw_pcie_ep_{read,write}_dbi[2} and some data-width
related helpers.

Link: https://lore.kernel.org/linux-pci/20231220053829.1921187-5-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 .../pci/controller/dwc/pcie-designware-ep.c   | 184 ++++++------------
 drivers/pci/controller/dwc/pcie-designware.h  |  93 +++++++++
 2 files changed, 153 insertions(+), 124 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index adef0bce84d69..e0917839d49b1 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -43,46 +43,19 @@ dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no)
 	return NULL;
 }
 
-static unsigned int dw_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep, u8 func_no)
-{
-	unsigned int dbi_offset = 0;
-
-	if (ep->ops->get_dbi_offset)
-		dbi_offset = ep->ops->get_dbi_offset(ep, func_no);
-
-	return dbi_offset;
-}
-
-static unsigned int dw_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep, u8 func_no)
-{
-	unsigned int dbi2_offset = 0;
-
-	if (ep->ops->get_dbi2_offset)
-		dbi2_offset = ep->ops->get_dbi2_offset(ep, func_no);
-	else if (ep->ops->get_dbi_offset)     /* for backward compatibility */
-		dbi2_offset = ep->ops->get_dbi_offset(ep, func_no);
-
-	return dbi2_offset;
-}
-
 static void __dw_pcie_ep_reset_bar(struct dw_pcie *pci, u8 func_no,
 				   enum pci_barno bar, int flags)
 {
-	unsigned int dbi_offset, dbi2_offset;
 	struct dw_pcie_ep *ep = &pci->ep;
-	u32 reg, reg_dbi2;
-
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-	dbi2_offset = dw_pcie_ep_get_dbi2_offset(ep, func_no);
+	u32 reg;
 
-	reg = dbi_offset + PCI_BASE_ADDRESS_0 + (4 * bar);
-	reg_dbi2 = dbi2_offset + PCI_BASE_ADDRESS_0 + (4 * bar);
+	reg = PCI_BASE_ADDRESS_0 + (4 * bar);
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writel_dbi2(pci, reg_dbi2, 0x0);
-	dw_pcie_writel_dbi(pci, reg, 0x0);
+	dw_pcie_ep_writel_dbi2(ep, func_no, reg, 0x0);
+	dw_pcie_ep_writel_dbi(ep, func_no, reg, 0x0);
 	if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) {
-		dw_pcie_writel_dbi2(pci, reg_dbi2 + 4, 0x0);
-		dw_pcie_writel_dbi(pci, reg + 4, 0x0);
+		dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, 0x0);
+		dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0x0);
 	}
 	dw_pcie_dbi_ro_wr_dis(pci);
 }
@@ -99,19 +72,15 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar)
 EXPORT_SYMBOL_GPL(dw_pcie_ep_reset_bar);
 
 static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no,
-		u8 cap_ptr, u8 cap)
+				     u8 cap_ptr, u8 cap)
 {
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int dbi_offset = 0;
 	u8 cap_id, next_cap_ptr;
 	u16 reg;
 
 	if (!cap_ptr)
 		return 0;
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-
-	reg = dw_pcie_readw_dbi(pci, dbi_offset + cap_ptr);
+	reg = dw_pcie_ep_readw_dbi(ep, func_no, cap_ptr);
 	cap_id = (reg & 0x00ff);
 
 	if (cap_id > PCI_CAP_ID_MAX)
@@ -126,14 +95,10 @@ static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no,
 
 static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap)
 {
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int dbi_offset = 0;
 	u8 next_cap_ptr;
 	u16 reg;
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-
-	reg = dw_pcie_readw_dbi(pci, dbi_offset + PCI_CAPABILITY_LIST);
+	reg = dw_pcie_ep_readw_dbi(ep, func_no, PCI_CAPABILITY_LIST);
 	next_cap_ptr = (reg & 0x00ff);
 
 	return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap);
@@ -144,24 +109,21 @@ static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int dbi_offset = 0;
-
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
 
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writew_dbi(pci, dbi_offset + PCI_VENDOR_ID, hdr->vendorid);
-	dw_pcie_writew_dbi(pci, dbi_offset + PCI_DEVICE_ID, hdr->deviceid);
-	dw_pcie_writeb_dbi(pci, dbi_offset + PCI_REVISION_ID, hdr->revid);
-	dw_pcie_writeb_dbi(pci, dbi_offset + PCI_CLASS_PROG, hdr->progif_code);
-	dw_pcie_writew_dbi(pci, dbi_offset + PCI_CLASS_DEVICE,
-			   hdr->subclass_code | hdr->baseclass_code << 8);
-	dw_pcie_writeb_dbi(pci, dbi_offset + PCI_CACHE_LINE_SIZE,
-			   hdr->cache_line_size);
-	dw_pcie_writew_dbi(pci, dbi_offset + PCI_SUBSYSTEM_VENDOR_ID,
-			   hdr->subsys_vendor_id);
-	dw_pcie_writew_dbi(pci, dbi_offset + PCI_SUBSYSTEM_ID, hdr->subsys_id);
-	dw_pcie_writeb_dbi(pci, dbi_offset + PCI_INTERRUPT_PIN,
-			   hdr->interrupt_pin);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_VENDOR_ID, hdr->vendorid);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_DEVICE_ID, hdr->deviceid);
+	dw_pcie_ep_writeb_dbi(ep, func_no, PCI_REVISION_ID, hdr->revid);
+	dw_pcie_ep_writeb_dbi(ep, func_no, PCI_CLASS_PROG, hdr->progif_code);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_CLASS_DEVICE,
+			      hdr->subclass_code | hdr->baseclass_code << 8);
+	dw_pcie_ep_writeb_dbi(ep, func_no, PCI_CACHE_LINE_SIZE,
+			      hdr->cache_line_size);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_SUBSYSTEM_VENDOR_ID,
+			      hdr->subsys_vendor_id);
+	dw_pcie_ep_writew_dbi(ep, func_no, PCI_SUBSYSTEM_ID, hdr->subsys_id);
+	dw_pcie_ep_writeb_dbi(ep, func_no, PCI_INTERRUPT_PIN,
+			      hdr->interrupt_pin);
 	dw_pcie_dbi_ro_wr_dis(pci);
 
 	return 0;
@@ -243,18 +205,13 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	unsigned int dbi_offset, dbi2_offset;
 	enum pci_barno bar = epf_bar->barno;
 	size_t size = epf_bar->size;
 	int flags = epf_bar->flags;
-	u32 reg, reg_dbi2;
 	int ret, type;
+	u32 reg;
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-	dbi2_offset = dw_pcie_ep_get_dbi2_offset(ep, func_no);
-
-	reg = PCI_BASE_ADDRESS_0 + (4 * bar) + dbi_offset;
-	reg_dbi2 = PCI_BASE_ADDRESS_0 + (4 * bar) + dbi2_offset;
+	reg = PCI_BASE_ADDRESS_0 + (4 * bar);
 
 	if (!(flags & PCI_BASE_ADDRESS_SPACE))
 		type = PCIE_ATU_TYPE_MEM;
@@ -270,12 +227,12 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 
 	dw_pcie_dbi_ro_wr_en(pci);
 
-	dw_pcie_writel_dbi2(pci, reg_dbi2, lower_32_bits(size - 1));
-	dw_pcie_writel_dbi(pci, reg, flags);
+	dw_pcie_ep_writel_dbi2(ep, func_no, reg, lower_32_bits(size - 1));
+	dw_pcie_ep_writel_dbi(ep, func_no, reg, flags);
 
 	if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) {
-		dw_pcie_writel_dbi2(pci, reg_dbi2 + 4, upper_32_bits(size - 1));
-		dw_pcie_writel_dbi(pci, reg + 4, 0);
+		dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, upper_32_bits(size - 1));
+		dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0);
 	}
 
 	ep->epf_bar[bar] = epf_bar;
@@ -335,19 +292,15 @@ static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	u32 val, reg;
-	unsigned int dbi_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
+	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-
-	reg = ep_func->msi_cap + dbi_offset + PCI_MSI_FLAGS;
-	val = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msi_cap + PCI_MSI_FLAGS;
+	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	if (!(val & PCI_MSI_FLAGS_ENABLE))
 		return -EINVAL;
 
@@ -361,22 +314,19 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	u32 val, reg;
-	unsigned int dbi_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
+	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-
-	reg = ep_func->msi_cap + dbi_offset + PCI_MSI_FLAGS;
-	val = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msi_cap + PCI_MSI_FLAGS;
+	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSI_FLAGS_QMASK;
 	val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, interrupts);
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writew_dbi(pci, reg, val);
+	dw_pcie_ep_writew_dbi(ep, func_no, reg, val);
 	dw_pcie_dbi_ro_wr_dis(pci);
 
 	return 0;
@@ -385,19 +335,15 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	u32 val, reg;
-	unsigned int dbi_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
+	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msix_cap)
 		return -EINVAL;
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-
-	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_FLAGS;
-	val = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msix_cap + PCI_MSIX_FLAGS;
+	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	if (!(val & PCI_MSIX_FLAGS_ENABLE))
 		return -EINVAL;
 
@@ -411,9 +357,8 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	u32 val, reg;
-	unsigned int dbi_offset = 0;
 	struct dw_pcie_ep_func *ep_func;
+	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msix_cap)
@@ -421,21 +366,19 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 
 	dw_pcie_dbi_ro_wr_en(pci);
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-
-	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_FLAGS;
-	val = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msix_cap + PCI_MSIX_FLAGS;
+	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
 	val |= interrupts;
 	dw_pcie_writew_dbi(pci, reg, val);
 
-	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_TABLE;
+	reg = ep_func->msix_cap + PCI_MSIX_TABLE;
 	val = offset | bir;
-	dw_pcie_writel_dbi(pci, reg, val);
+	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
-	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_PBA;
+	reg = ep_func->msix_cap + PCI_MSIX_PBA;
 	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
-	dw_pcie_writel_dbi(pci, reg, val);
+	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
 	dw_pcie_dbi_ro_wr_dis(pci);
 
@@ -510,38 +453,34 @@ EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_legacy_irq);
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num)
 {
-	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 msg_addr_lower, msg_addr_upper, reg;
 	struct dw_pcie_ep_func *ep_func;
 	struct pci_epc *epc = ep->epc;
 	unsigned int aligned_offset;
-	unsigned int dbi_offset = 0;
 	u16 msg_ctrl, msg_data;
-	u32 msg_addr_lower, msg_addr_upper, reg;
-	u64 msg_addr;
 	bool has_upper;
+	u64 msg_addr;
 	int ret;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msi_cap)
 		return -EINVAL;
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-
 	/* Raise MSI per the PCI Local Bus Specification Revision 3.0, 6.8.1. */
-	reg = ep_func->msi_cap + dbi_offset + PCI_MSI_FLAGS;
-	msg_ctrl = dw_pcie_readw_dbi(pci, reg);
+	reg = ep_func->msi_cap + PCI_MSI_FLAGS;
+	msg_ctrl = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	has_upper = !!(msg_ctrl & PCI_MSI_FLAGS_64BIT);
-	reg = ep_func->msi_cap + dbi_offset + PCI_MSI_ADDRESS_LO;
-	msg_addr_lower = dw_pcie_readl_dbi(pci, reg);
+	reg = ep_func->msi_cap + PCI_MSI_ADDRESS_LO;
+	msg_addr_lower = dw_pcie_ep_readl_dbi(ep, func_no, reg);
 	if (has_upper) {
-		reg = ep_func->msi_cap + dbi_offset + PCI_MSI_ADDRESS_HI;
-		msg_addr_upper = dw_pcie_readl_dbi(pci, reg);
-		reg = ep_func->msi_cap + dbi_offset + PCI_MSI_DATA_64;
-		msg_data = dw_pcie_readw_dbi(pci, reg);
+		reg = ep_func->msi_cap + PCI_MSI_ADDRESS_HI;
+		msg_addr_upper = dw_pcie_ep_readl_dbi(ep, func_no, reg);
+		reg = ep_func->msi_cap + PCI_MSI_DATA_64;
+		msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	} else {
 		msg_addr_upper = 0;
-		reg = ep_func->msi_cap + dbi_offset + PCI_MSI_DATA_32;
-		msg_data = dw_pcie_readw_dbi(pci, reg);
+		reg = ep_func->msi_cap + PCI_MSI_DATA_32;
+		msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	}
 	aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1);
 	msg_addr = ((u64)msg_addr_upper) << 32 |
@@ -582,10 +521,9 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 			      u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	struct dw_pcie_ep_func *ep_func;
 	struct pci_epf_msix_tbl *msix_tbl;
+	struct dw_pcie_ep_func *ep_func;
 	struct pci_epc *epc = ep->epc;
-	unsigned int dbi_offset = 0;
 	u32 reg, msg_data, vec_ctrl;
 	unsigned int aligned_offset;
 	u32 tbl_offset;
@@ -597,10 +535,8 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	if (!ep_func || !ep_func->msix_cap)
 		return -EINVAL;
 
-	dbi_offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
-
-	reg = ep_func->msix_cap + dbi_offset + PCI_MSIX_TABLE;
-	tbl_offset = dw_pcie_readl_dbi(pci, reg);
+	reg = ep_func->msix_cap + PCI_MSIX_TABLE;
+	tbl_offset = dw_pcie_ep_readl_dbi(ep, func_no, reg);
 	bir = FIELD_GET(PCI_MSIX_TABLE_BIR, tbl_offset);
 	tbl_offset &= PCI_MSIX_TABLE_OFFSET;
 
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 5e36da166ffe8..e8ec4f11ce9d1 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -486,6 +486,99 @@ static inline void dw_pcie_writel_dbi2(struct dw_pcie *pci, u32 reg, u32 val)
 	dw_pcie_write_dbi2(pci, reg, 0x4, val);
 }
 
+static inline unsigned int dw_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep,
+						     u8 func_no)
+{
+	unsigned int dbi_offset = 0;
+
+	if (ep->ops->get_dbi_offset)
+		dbi_offset = ep->ops->get_dbi_offset(ep, func_no);
+
+	return dbi_offset;
+}
+
+static inline u32 dw_pcie_ep_read_dbi(struct dw_pcie_ep *ep, u8 func_no,
+				      u32 reg, size_t size)
+{
+	unsigned int offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+
+	return dw_pcie_read_dbi(pci, offset + reg, size);
+}
+
+static inline void dw_pcie_ep_write_dbi(struct dw_pcie_ep *ep, u8 func_no,
+					u32 reg, size_t size, u32 val)
+{
+	unsigned int offset = dw_pcie_ep_get_dbi_offset(ep, func_no);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+
+	dw_pcie_write_dbi(pci, offset + reg, size, val);
+}
+
+static inline void dw_pcie_ep_writel_dbi(struct dw_pcie_ep *ep, u8 func_no,
+					 u32 reg, u32 val)
+{
+	dw_pcie_ep_write_dbi(ep, func_no, reg, 0x4, val);
+}
+
+static inline u32 dw_pcie_ep_readl_dbi(struct dw_pcie_ep *ep, u8 func_no,
+				       u32 reg)
+{
+	return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x4);
+}
+
+static inline void dw_pcie_ep_writew_dbi(struct dw_pcie_ep *ep, u8 func_no,
+					 u32 reg, u16 val)
+{
+	dw_pcie_ep_write_dbi(ep, func_no, reg, 0x2, val);
+}
+
+static inline u16 dw_pcie_ep_readw_dbi(struct dw_pcie_ep *ep, u8 func_no,
+				       u32 reg)
+{
+	return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x2);
+}
+
+static inline void dw_pcie_ep_writeb_dbi(struct dw_pcie_ep *ep, u8 func_no,
+					 u32 reg, u8 val)
+{
+	dw_pcie_ep_write_dbi(ep, func_no, reg, 0x1, val);
+}
+
+static inline u8 dw_pcie_ep_readb_dbi(struct dw_pcie_ep *ep, u8 func_no,
+				      u32 reg)
+{
+	return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x1);
+}
+
+static inline unsigned int dw_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep,
+						      u8 func_no)
+{
+	unsigned int dbi2_offset = 0;
+
+	if (ep->ops->get_dbi2_offset)
+		dbi2_offset = ep->ops->get_dbi2_offset(ep, func_no);
+	else if (ep->ops->get_dbi_offset)     /* for backward compatibility */
+		dbi2_offset = ep->ops->get_dbi_offset(ep, func_no);
+
+	return dbi2_offset;
+}
+
+static inline void dw_pcie_ep_write_dbi2(struct dw_pcie_ep *ep, u8 func_no,
+					 u32 reg, size_t size, u32 val)
+{
+	unsigned int offset = dw_pcie_ep_get_dbi2_offset(ep, func_no);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+
+	dw_pcie_write_dbi2(pci, offset + reg, size, val);
+}
+
+static inline void dw_pcie_ep_writel_dbi2(struct dw_pcie_ep *ep, u8 func_no,
+					  u32 reg, u32 val)
+{
+	dw_pcie_ep_write_dbi2(ep, func_no, reg, 0x4, val);
+}
+
 static inline void dw_pcie_dbi_ro_wr_en(struct dw_pcie *pci)
 {
 	u32 reg;
-- 
GitLab


From f72896721621689460967301a54a3d380d0e9434 Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Wed, 20 Dec 2023 14:38:28 +0900
Subject: [PATCH 2314/4076] PCI: iproc: Fix -Wvoid-pointer-to-enum-cast warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building with clang 18, the following warning will be reported:

  drivers/pci/controller/pcie-iproc-platform.c:54:15: warning: cast to smaller integer type 'enum iproc_pcie_type' from 'const void *' [-Wvoid-pointer-to-enum-cast]
     55 |         pcie->type = (enum iproc_pcie_type) of_device_get_match_data(dev);

To fix this issue, cast the data the of_device_get_match_data() helper
returns to uintptr_t rather than the iproc_pcie_type enum.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20231220053829.1921187-6-yoshihiro.shimoda.uh@renesas.com
Link: https://github.com/ClangBuiltLinux/linux/issues/1910
Reported-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/pcie-iproc-platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c
index acdc583d29802..4e6aa882a567a 100644
--- a/drivers/pci/controller/pcie-iproc-platform.c
+++ b/drivers/pci/controller/pcie-iproc-platform.c
@@ -52,7 +52,7 @@ static int iproc_pltfm_pcie_probe(struct platform_device *pdev)
 	pcie = pci_host_bridge_priv(bridge);
 
 	pcie->dev = dev;
-	pcie->type = (enum iproc_pcie_type) of_device_get_match_data(dev);
+	pcie->type = (uintptr_t)of_device_get_match_data(dev);
 
 	ret = of_address_to_resource(np, 0, &reg);
 	if (ret < 0) {
-- 
GitLab


From 7682f19c3c8c709ff4ef0e1d475f00907ade868f Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Wed, 20 Dec 2023 14:38:29 +0900
Subject: [PATCH 2315/4076] PCI: rcar-gen4: Fix -Wvoid-pointer-to-enum-cast
 error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building with clang 18 with the -Werror compiler option enabled,
the following error will be reported:

  drivers/pci/controller/dwc/pcie-rcar-gen4.c:439:15: error: cast to smaller integer type 'enum dw_pcie_device_mode' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast]
    439 |         rcar->mode = (enum dw_pcie_device_mode)of_device_get_match_data(&rcar->pdev->dev);

To fix this issue, cast the data the of_device_get_match_data() helper
returns to uintptr_t rather than the dw_pcie_device_mode enum.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20231220053829.1921187-7-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/dwc/pcie-rcar-gen4.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 70492f562e48f..a1eb10e878f14 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -436,7 +436,7 @@ static void rcar_gen4_remove_dw_pcie_ep(struct rcar_gen4_pcie *rcar)
 /* Common */
 static int rcar_gen4_add_dw_pcie(struct rcar_gen4_pcie *rcar)
 {
-	rcar->mode = (enum dw_pcie_device_mode)of_device_get_match_data(&rcar->pdev->dev);
+	rcar->mode = (uintptr_t)of_device_get_match_data(&rcar->pdev->dev);
 
 	switch (rcar->mode) {
 	case DW_PCIE_RC_TYPE:
-- 
GitLab


From 7aa5f8fcd6d95b713a39fe52c296a6892eda7f02 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= <kwilczynski@kernel.org>
Date: Sat, 6 Jan 2024 12:43:28 +0000
Subject: [PATCH 2316/4076] PCI: xilinx-xdma: Fix uninitialized symbols in
 xilinx_pl_dma_pcie_setup_irq()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The error paths that follow calls to the devm_request_irq() functions
within the xilinx_pl_dma_pcie_setup_irq() reference an uninitialized
symbol each that also so happens to be incorrect.

Thus, fix this omission and reference the correct variable when invoking
a given dev_err() function following an error.

This problem was found using smatch via the 0-DAY CI Kernel Test service:

  drivers/pci/controller/pcie-xilinx-dma-pl.c:638 xilinx_pl_dma_pcie_setup_irq() error: uninitialized symbol 'irq'.
  drivers/pci/controller/pcie-xilinx-dma-pl.c:645 xilinx_pl_dma_pcie_setup_irq() error: uninitialized symbol 'irq'.

Fixes: 8d786149d78c ("PCI: xilinx-xdma: Add Xilinx XDMA Root Port driver")
Link: https://lore.kernel.org/oe-kbuild/202312120248.5DblxkBp-lkp@intel.com/
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202312120248.5DblxkBp-lkp@intel.com/
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/pcie-xilinx-dma-pl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pcie-xilinx-dma-pl.c b/drivers/pci/controller/pcie-xilinx-dma-pl.c
index 4e49b12a2e2a6..9c79754dc8fab 100644
--- a/drivers/pci/controller/pcie-xilinx-dma-pl.c
+++ b/drivers/pci/controller/pcie-xilinx-dma-pl.c
@@ -635,14 +635,14 @@ static int xilinx_pl_dma_pcie_setup_irq(struct pl_dma_pcie *port)
 	err = devm_request_irq(dev, port->intx_irq, xilinx_pl_dma_pcie_intx_flow,
 			       IRQF_SHARED | IRQF_NO_THREAD, NULL, port);
 	if (err) {
-		dev_err(dev, "Failed to request INTx IRQ %d\n", irq);
+		dev_err(dev, "Failed to request INTx IRQ %d\n", port->intx_irq);
 		return err;
 	}
 
 	err = devm_request_irq(dev, port->irq, xilinx_pl_dma_pcie_event_flow,
 			       IRQF_SHARED | IRQF_NO_THREAD, NULL, port);
 	if (err) {
-		dev_err(dev, "Failed to request event IRQ %d\n", irq);
+		dev_err(dev, "Failed to request event IRQ %d\n", port->irq);
 		return err;
 	}
 
-- 
GitLab


From 1e022216dcd248326a5bb95609d12a6815bca4e2 Mon Sep 17 00:00:00 2001
From: Zhihao Cheng <chengzhihao1@huawei.com>
Date: Fri, 22 Dec 2023 16:54:46 +0800
Subject: [PATCH 2317/4076] ubifs: ubifs_symlink: Fix memleak of inode->i_link
 in error path

For error handling path in ubifs_symlink(), inode will be marked as
bad first, then iput() is invoked. If inode->i_link is initialized by
fscrypt_encrypt_symlink() in encryption scenario, inode->i_link won't
be freed by callchain ubifs_free_inode -> fscrypt_free_inode in error
handling path, because make_bad_inode() has changed 'inode->i_mode' as
'S_IFREG'.
Following kmemleak is easy to be reproduced by injecting error in
ubifs_jnl_update() when doing symlink in encryption scenario:
 unreferenced object 0xffff888103da3d98 (size 8):
  comm "ln", pid 1692, jiffies 4294914701 (age 12.045s)
  backtrace:
   kmemdup+0x32/0x70
   __fscrypt_encrypt_symlink+0xed/0x1c0
   ubifs_symlink+0x210/0x300 [ubifs]
   vfs_symlink+0x216/0x360
   do_symlinkat+0x11a/0x190
   do_syscall_64+0x3b/0xe0
There are two ways fixing it:
 1. Remove make_bad_inode() in error handling path. We can do that
    because ubifs_evict_inode() will do same processes for good
    symlink inode and bad symlink inode, for inode->i_nlink checking
    is before is_bad_inode().
 2. Free inode->i_link before marking inode bad.
Method 2 is picked, it has less influence, personally, I think.

Cc: stable@vger.kernel.org
Fixes: 2c58d548f570 ("fscrypt: cache decrypted symlink target in ->i_link")
Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Suggested-by: Eric Biggers <ebiggers@kernel.org>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 fs/ubifs/dir.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 3b13c648d4900..e413a9cf8ee38 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -1234,6 +1234,8 @@ out_cancel:
 	dir_ui->ui_size = dir->i_size;
 	mutex_unlock(&dir_ui->ui_mutex);
 out_inode:
+	/* Free inode->i_link before inode is marked as bad. */
+	fscrypt_free_inode(inode);
 	make_bad_inode(inode);
 	iput(inode);
 out_fname:
-- 
GitLab


From 6931fb44858c3b9da9f35fdc8d9cbeef0b4b50a3 Mon Sep 17 00:00:00 2001
From: ZhaoLong Wang <wangzhaolong1@huawei.com>
Date: Tue, 26 Dec 2023 09:01:09 +0800
Subject: [PATCH 2318/4076] ubi: Use the fault injection framework to enhance
 the fault injection capability

To make debug parameters configurable at run time, use the
fault injection framework to reconstruct the debugfs interface,
and retain the legacy fault injection interface.

Now, the file emulate_failures and fault_attr files control whether
to enable fault emmulation.

The file emulate_failures receives a mask that controls type and
process of fault injection. Generally, for ease of use, you can
directly enter a mask with all 1s.

echo 0xffff > /sys/kernel/debug/ubi/ubi0/emulate_failures

And you need to configure other fault-injection capabilities for
testing purpose:

echo 100 > /sys/kernel/debug/ubi/fault_inject/emulate_power_cut/probability
echo 15 > /sys/kernel/debug/ubi/fault_inject/emulate_power_cut/space
echo 2 > /sys/kernel/debug/ubi/fault_inject/emulate_power_cut/verbose
echo -1 > /sys/kernel/debug/ubi/fault_inject/emulate_power_cut/times

The CONFIG_MTD_UBI_FAULT_INJECTION to enable the Fault Injection is
added to kconfig.

Signed-off-by: ZhaoLong Wang <wangzhaolong1@huawei.com>
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 drivers/mtd/ubi/Kconfig |   9 +++
 drivers/mtd/ubi/debug.c |  69 +++++++++++++++++--
 drivers/mtd/ubi/debug.h | 142 +++++++++++++++++++++++++++++++++-------
 drivers/mtd/ubi/io.c    |  10 ++-
 drivers/mtd/ubi/ubi.h   |  15 ++---
 5 files changed, 203 insertions(+), 42 deletions(-)

diff --git a/drivers/mtd/ubi/Kconfig b/drivers/mtd/ubi/Kconfig
index 2ed77b7b3fcb5..7499a540121e8 100644
--- a/drivers/mtd/ubi/Kconfig
+++ b/drivers/mtd/ubi/Kconfig
@@ -104,4 +104,13 @@ config MTD_UBI_BLOCK
 
 	   If in doubt, say "N".
 
+config MTD_UBI_FAULT_INJECTION
+	bool "Fault injection capability of UBI device"
+	default n
+	depends on FAULT_INJECTION_DEBUG_FS
+	help
+	   This option enables fault-injection support for UBI devices for
+	   testing purposes.
+
+	   If in doubt, say "N".
 endif # MTD_UBI
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index 27168f511d6d4..fd101ad6f12fc 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -10,7 +10,23 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
+#include <linux/fault-inject.h>
 
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+static DECLARE_FAULT_ATTR(fault_bitflips_attr);
+static DECLARE_FAULT_ATTR(fault_io_failures_attr);
+static DECLARE_FAULT_ATTR(fault_power_cut_attr);
+
+#define FAIL_ACTION(name, fault_attr)			\
+bool should_fail_##name(void)				\
+{							\
+	return should_fail(&fault_attr, 1);		\
+}
+
+FAIL_ACTION(bitflips,		fault_bitflips_attr)
+FAIL_ACTION(io_failures,	fault_io_failures_attr)
+FAIL_ACTION(power_cut,		fault_power_cut_attr)
+#endif
 
 /**
  * ubi_dump_flash - dump a region of flash.
@@ -212,6 +228,31 @@ void ubi_dump_mkvol_req(const struct ubi_mkvol_req *req)
  */
 static struct dentry *dfs_rootdir;
 
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+static void dfs_create_fault_entry(struct dentry *parent)
+{
+	struct dentry *dir;
+
+	dir = debugfs_create_dir("fault_inject", parent);
+	if (IS_ERR_OR_NULL(dir)) {
+		int err = dir ? PTR_ERR(dir) : -ENODEV;
+
+		pr_warn("UBI error: cannot create \"fault_inject\" debugfs directory, error %d\n",
+			 err);
+		return;
+	}
+
+	fault_create_debugfs_attr("emulate_bitflips", dir,
+				  &fault_bitflips_attr);
+
+	fault_create_debugfs_attr("emulate_io_failures", dir,
+				  &fault_io_failures_attr);
+
+	fault_create_debugfs_attr("emulate_power_cut", dir,
+				  &fault_power_cut_attr);
+}
+#endif
+
 /**
  * ubi_debugfs_init - create UBI debugfs directory.
  *
@@ -232,6 +273,10 @@ int ubi_debugfs_init(void)
 		return err;
 	}
 
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+	dfs_create_fault_entry(dfs_rootdir);
+#endif
+
 	return 0;
 }
 
@@ -272,7 +317,12 @@ static ssize_t dfs_file_read(struct file *file, char __user *user_buf,
 		val = d->emulate_bitflips;
 	else if (dent == d->dfs_emulate_io_failures)
 		val = d->emulate_io_failures;
-	else if (dent == d->dfs_emulate_power_cut) {
+	else if (dent == d->dfs_emulate_failures) {
+		snprintf(buf, sizeof(buf), "0x%04x\n", d->emulate_failures);
+		count = simple_read_from_buffer(user_buf, count, ppos,
+						buf, strlen(buf));
+		goto out;
+	} else if (dent == d->dfs_emulate_power_cut) {
 		snprintf(buf, sizeof(buf), "%u\n", d->emulate_power_cut);
 		count = simple_read_from_buffer(user_buf, count, ppos,
 						buf, strlen(buf));
@@ -287,8 +337,7 @@ static ssize_t dfs_file_read(struct file *file, char __user *user_buf,
 		count = simple_read_from_buffer(user_buf, count, ppos,
 						buf, strlen(buf));
 		goto out;
-	}
-	else {
+	} else {
 		count = -EINVAL;
 		goto out;
 	}
@@ -330,7 +379,11 @@ static ssize_t dfs_file_write(struct file *file, const char __user *user_buf,
 		goto out;
 	}
 
-	if (dent == d->dfs_power_cut_min) {
+	if (dent == d->dfs_emulate_failures) {
+		if (kstrtouint(buf, 0, &d->emulate_failures) != 0)
+			count = -EINVAL;
+		goto out;
+	} else if (dent == d->dfs_power_cut_min) {
 		if (kstrtouint(buf, 0, &d->power_cut_min) != 0)
 			count = -EINVAL;
 		goto out;
@@ -559,6 +612,12 @@ int ubi_debugfs_init_dev(struct ubi_device *ubi)
 	debugfs_create_file("detailed_erase_block_info", S_IRUSR, d->dfs_dir,
 			    (void *)ubi_num, &eraseblk_count_fops);
 
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+	d->dfs_emulate_failures = debugfs_create_file("emulate_failures",
+						       mode, d->dfs_dir,
+						       (void *)ubi_num,
+						       &dfs_fops);
+#endif
 	return 0;
 }
 
@@ -600,7 +659,5 @@ int ubi_dbg_power_cut(struct ubi_device *ubi, int caller)
 	if (ubi->dbg.power_cut_counter)
 		return 0;
 
-	ubi_msg(ubi, "XXXXXXXXXXXXXXX emulating a power cut XXXXXXXXXXXXXXXX");
-	ubi_ro_mode(ubi);
 	return 1;
 }
diff --git a/drivers/mtd/ubi/debug.h b/drivers/mtd/ubi/debug.h
index 23676f32b6812..f2f499feff49f 100644
--- a/drivers/mtd/ubi/debug.h
+++ b/drivers/mtd/ubi/debug.h
@@ -53,56 +53,153 @@ int ubi_debugfs_init_dev(struct ubi_device *ubi);
 void ubi_debugfs_exit_dev(struct ubi_device *ubi);
 
 /**
- * ubi_dbg_is_bgt_disabled - if the background thread is disabled.
+ * The following function is a legacy implementation of UBI fault-injection
+ * hook. When using more powerful fault injection capabilities, the legacy
+ * fault injection interface should be retained.
+ */
+int ubi_dbg_power_cut(struct ubi_device *ubi, int caller);
+
+static inline int ubi_dbg_bitflip(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_bitflips)
+		return !get_random_u32_below(200);
+	return 0;
+}
+
+static inline int ubi_dbg_write_failure(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_io_failures)
+		return !get_random_u32_below(500);
+	return 0;
+}
+
+static inline int ubi_dbg_erase_failure(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_io_failures)
+		return !get_random_u32_below(400);
+	return 0;
+}
+
+/**
+ * MASK_XXX: Mask for emulate_failures in ubi_debug_info.The mask is used to
+ * precisely control the type and process of fault injection.
+ */
+/* Emulate a power cut when writing EC/VID header */
+#define MASK_POWER_CUT_EC			(1 << 0)
+#define MASK_POWER_CUT_VID			(1 << 1)
+
+#ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+/* Emulate bit-flips */
+#define MASK_BITFLIPS				(1 << 2)
+/* Emulates -EIO during write/erase */
+#define MASK_IO_FAILURE				(1 << 3)
+
+extern bool should_fail_bitflips(void);
+extern bool should_fail_io_failures(void);
+extern bool should_fail_power_cut(void);
+
+static inline bool ubi_dbg_fail_bitflip(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_failures & MASK_BITFLIPS)
+		return should_fail_bitflips();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_write(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_failures & MASK_IO_FAILURE)
+		return should_fail_io_failures();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_erase(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_failures & MASK_IO_FAILURE)
+		return should_fail_io_failures();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_power_cut(const struct ubi_device *ubi,
+					unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_power_cut();
+	return false;
+}
+
+#else /* CONFIG_MTD_UBI_FAULT_INJECTION */
+
+#define ubi_dbg_fail_bitflip(u)             false
+#define ubi_dbg_fail_write(u)               false
+#define ubi_dbg_fail_erase(u)               false
+#define ubi_dbg_fail_power_cut(u, c)        false
+#endif
+
+/**
+ * ubi_dbg_is_power_cut - if it is time to emulate power cut.
  * @ubi: UBI device description object
  *
- * Returns non-zero if the UBI background thread is disabled for testing
- * purposes.
+ * Returns true if power cut should be emulated, otherwise returns false.
  */
-static inline int ubi_dbg_is_bgt_disabled(const struct ubi_device *ubi)
+static inline bool ubi_dbg_is_power_cut(struct ubi_device *ubi,
+					unsigned int caller)
 {
-	return ubi->dbg.disable_bgt;
+	if (ubi_dbg_power_cut(ubi, caller))
+		return true;
+	return ubi_dbg_fail_power_cut(ubi, caller);
 }
 
 /**
  * ubi_dbg_is_bitflip - if it is time to emulate a bit-flip.
  * @ubi: UBI device description object
  *
- * Returns non-zero if a bit-flip should be emulated, otherwise returns zero.
+ * Returns true if a bit-flip should be emulated, otherwise returns false.
  */
-static inline int ubi_dbg_is_bitflip(const struct ubi_device *ubi)
+static inline bool ubi_dbg_is_bitflip(const struct ubi_device *ubi)
 {
-	if (ubi->dbg.emulate_bitflips)
-		return !get_random_u32_below(200);
-	return 0;
+	if (ubi_dbg_bitflip(ubi))
+		return true;
+	return ubi_dbg_fail_bitflip(ubi);
 }
 
 /**
  * ubi_dbg_is_write_failure - if it is time to emulate a write failure.
  * @ubi: UBI device description object
  *
- * Returns non-zero if a write failure should be emulated, otherwise returns
- * zero.
+ * Returns true if a write failure should be emulated, otherwise returns
+ * false.
  */
-static inline int ubi_dbg_is_write_failure(const struct ubi_device *ubi)
+static inline bool ubi_dbg_is_write_failure(const struct ubi_device *ubi)
 {
-	if (ubi->dbg.emulate_io_failures)
-		return !get_random_u32_below(500);
-	return 0;
+	if (ubi_dbg_write_failure(ubi))
+		return true;
+	return ubi_dbg_fail_write(ubi);
 }
 
 /**
  * ubi_dbg_is_erase_failure - if its time to emulate an erase failure.
  * @ubi: UBI device description object
  *
- * Returns non-zero if an erase failure should be emulated, otherwise returns
- * zero.
+ * Returns true if an erase failure should be emulated, otherwise returns
+ * false.
  */
-static inline int ubi_dbg_is_erase_failure(const struct ubi_device *ubi)
+static inline bool ubi_dbg_is_erase_failure(const struct ubi_device *ubi)
 {
-	if (ubi->dbg.emulate_io_failures)
-		return !get_random_u32_below(400);
-	return 0;
+	if (ubi_dbg_erase_failure(ubi))
+		return true;
+	return ubi_dbg_fail_erase(ubi);
+}
+
+/**
+ * ubi_dbg_is_bgt_disabled - if the background thread is disabled.
+ * @ubi: UBI device description object
+ *
+ * Returns non-zero if the UBI background thread is disabled for testing
+ * purposes.
+ */
+static inline int ubi_dbg_is_bgt_disabled(const struct ubi_device *ubi)
+{
+	return ubi->dbg.disable_bgt;
 }
 
 static inline int ubi_dbg_chk_io(const struct ubi_device *ubi)
@@ -125,5 +222,4 @@ static inline void ubi_enable_dbg_chk_fastmap(struct ubi_device *ubi)
 	ubi->dbg.chk_fastmap = 1;
 }
 
-int ubi_dbg_power_cut(struct ubi_device *ubi, int caller);
 #endif /* !__UBI_DEBUG_H__ */
diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c
index 01b6448612533..fb70f5227f182 100644
--- a/drivers/mtd/ubi/io.c
+++ b/drivers/mtd/ubi/io.c
@@ -821,8 +821,11 @@ int ubi_io_write_ec_hdr(struct ubi_device *ubi, int pnum,
 	if (err)
 		return err;
 
-	if (ubi_dbg_power_cut(ubi, POWER_CUT_EC_WRITE))
+	if (ubi_dbg_is_power_cut(ubi, MASK_POWER_CUT_EC)) {
+		ubi_warn(ubi, "emulating a power cut when writing EC header");
+		ubi_ro_mode(ubi);
 		return -EROFS;
+	}
 
 	err = ubi_io_write(ubi, ec_hdr, pnum, 0, ubi->ec_hdr_alsize);
 	return err;
@@ -1071,8 +1074,11 @@ int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum,
 	if (err)
 		return err;
 
-	if (ubi_dbg_power_cut(ubi, POWER_CUT_VID_WRITE))
+	if (ubi_dbg_is_power_cut(ubi, MASK_POWER_CUT_VID)) {
+		ubi_warn(ubi, "emulating a power cut when writing VID header");
+		ubi_ro_mode(ubi);
 		return -EROFS;
+	}
 
 	err = ubi_io_write(ubi, p, pnum, ubi->vid_hdr_aloffset,
 			   ubi->vid_hdr_alsize);
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index a5ec566df0d74..cc4777983bd29 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -145,17 +145,6 @@ enum {
 	UBI_BAD_FASTMAP,
 };
 
-/*
- * Flags for emulate_power_cut in ubi_debug_info
- *
- * POWER_CUT_EC_WRITE: Emulate a power cut when writing an EC header
- * POWER_CUT_VID_WRITE: Emulate a power cut when writing a VID header
- */
-enum {
-	POWER_CUT_EC_WRITE = 0x01,
-	POWER_CUT_VID_WRITE = 0x02,
-};
-
 /**
  * struct ubi_vid_io_buf - VID buffer used to read/write VID info to/from the
  *			   flash.
@@ -404,6 +393,7 @@ struct ubi_volume_desc {
  * @power_cut_counter: count down for writes left until emulated power cut
  * @power_cut_min: minimum number of writes before emulating a power cut
  * @power_cut_max: maximum number of writes until emulating a power cut
+ * @emulate_failures: emulate failures for testing purposes
  * @dfs_dir_name: name of debugfs directory containing files of this UBI device
  * @dfs_dir: direntry object of the UBI device debugfs directory
  * @dfs_chk_gen: debugfs knob to enable UBI general extra checks
@@ -415,6 +405,7 @@ struct ubi_volume_desc {
  * @dfs_emulate_power_cut: debugfs knob to emulate power cuts
  * @dfs_power_cut_min: debugfs knob for minimum writes before power cut
  * @dfs_power_cut_max: debugfs knob for maximum writes until power cut
+ * @dfs_emulate_failures: debugfs entry to control the fault injection type
  */
 struct ubi_debug_info {
 	unsigned int chk_gen:1;
@@ -427,6 +418,7 @@ struct ubi_debug_info {
 	unsigned int power_cut_counter;
 	unsigned int power_cut_min;
 	unsigned int power_cut_max;
+	unsigned int emulate_failures;
 	char dfs_dir_name[UBI_DFS_DIR_LEN + 1];
 	struct dentry *dfs_dir;
 	struct dentry *dfs_chk_gen;
@@ -438,6 +430,7 @@ struct ubi_debug_info {
 	struct dentry *dfs_emulate_power_cut;
 	struct dentry *dfs_power_cut_min;
 	struct dentry *dfs_power_cut_max;
+	struct dentry *dfs_emulate_failures;
 };
 
 /**
-- 
GitLab


From e30948f7c0730d9fb2271ff3eadd43eda4e44740 Mon Sep 17 00:00:00 2001
From: ZhaoLong Wang <wangzhaolong1@huawei.com>
Date: Tue, 26 Dec 2023 09:01:10 +0800
Subject: [PATCH 2319/4076] ubi: Split io_failures into write_failure and
 erase_failure

The emulate_io_failures debugfs entry controls both write
failure and erase failure. This patch split io_failures
to write_failure and erase_failure.

Signed-off-by: ZhaoLong Wang <wangzhaolong1@huawei.com>
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 drivers/mtd/ubi/debug.c | 13 +++++++++----
 drivers/mtd/ubi/debug.h | 14 ++++++++------
 2 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index fd101ad6f12fc..186306228b4d9 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -14,7 +14,8 @@
 
 #ifdef CONFIG_MTD_UBI_FAULT_INJECTION
 static DECLARE_FAULT_ATTR(fault_bitflips_attr);
-static DECLARE_FAULT_ATTR(fault_io_failures_attr);
+static DECLARE_FAULT_ATTR(fault_write_failure_attr);
+static DECLARE_FAULT_ATTR(fault_erase_failure_attr);
 static DECLARE_FAULT_ATTR(fault_power_cut_attr);
 
 #define FAIL_ACTION(name, fault_attr)			\
@@ -24,7 +25,8 @@ bool should_fail_##name(void)				\
 }
 
 FAIL_ACTION(bitflips,		fault_bitflips_attr)
-FAIL_ACTION(io_failures,	fault_io_failures_attr)
+FAIL_ACTION(write_failure,	fault_write_failure_attr)
+FAIL_ACTION(erase_failure,	fault_erase_failure_attr)
 FAIL_ACTION(power_cut,		fault_power_cut_attr)
 #endif
 
@@ -245,8 +247,11 @@ static void dfs_create_fault_entry(struct dentry *parent)
 	fault_create_debugfs_attr("emulate_bitflips", dir,
 				  &fault_bitflips_attr);
 
-	fault_create_debugfs_attr("emulate_io_failures", dir,
-				  &fault_io_failures_attr);
+	fault_create_debugfs_attr("emulate_write_failure", dir,
+				  &fault_write_failure_attr);
+
+	fault_create_debugfs_attr("emulate_erase_failure", dir,
+				  &fault_erase_failure_attr);
 
 	fault_create_debugfs_attr("emulate_power_cut", dir,
 				  &fault_power_cut_attr);
diff --git a/drivers/mtd/ubi/debug.h b/drivers/mtd/ubi/debug.h
index f2f499feff49f..8cdd25eee0138 100644
--- a/drivers/mtd/ubi/debug.h
+++ b/drivers/mtd/ubi/debug.h
@@ -92,10 +92,12 @@ static inline int ubi_dbg_erase_failure(const struct ubi_device *ubi)
 /* Emulate bit-flips */
 #define MASK_BITFLIPS				(1 << 2)
 /* Emulates -EIO during write/erase */
-#define MASK_IO_FAILURE				(1 << 3)
+#define MASK_WRITE_FAILURE			(1 << 3)
+#define MASK_ERASE_FAILURE			(1 << 4)
 
 extern bool should_fail_bitflips(void);
-extern bool should_fail_io_failures(void);
+extern bool should_fail_write_failure(void);
+extern bool should_fail_erase_failure(void);
 extern bool should_fail_power_cut(void);
 
 static inline bool ubi_dbg_fail_bitflip(const struct ubi_device *ubi)
@@ -107,15 +109,15 @@ static inline bool ubi_dbg_fail_bitflip(const struct ubi_device *ubi)
 
 static inline bool ubi_dbg_fail_write(const struct ubi_device *ubi)
 {
-	if (ubi->dbg.emulate_failures & MASK_IO_FAILURE)
-		return should_fail_io_failures();
+	if (ubi->dbg.emulate_failures & MASK_WRITE_FAILURE)
+		return should_fail_write_failure();
 	return false;
 }
 
 static inline bool ubi_dbg_fail_erase(const struct ubi_device *ubi)
 {
-	if (ubi->dbg.emulate_failures & MASK_IO_FAILURE)
-		return should_fail_io_failures();
+	if (ubi->dbg.emulate_failures & MASK_ERASE_FAILURE)
+		return should_fail_erase_failure();
 	return false;
 }
 
-- 
GitLab


From 7cd8d1f8475d83c8871917430a2daf362c68e742 Mon Sep 17 00:00:00 2001
From: ZhaoLong Wang <wangzhaolong1@huawei.com>
Date: Tue, 26 Dec 2023 09:01:11 +0800
Subject: [PATCH 2320/4076] ubi: Add six fault injection type for testing

This commit adds six fault injection type for testing to cover the
abnormal path of the UBI driver.

Inject the following faults when the UBI reads the LEB:
 +----------------------------+-----------------------------------+
 |    Interface name          |       emulate behavior            |
 +----------------------------+-----------------------------------+
 |  emulate_eccerr            | ECC error                         |
 +----------------------------+-----------------------------------+
 |  emulate_read_failure      | read failure                      |
 |----------------------------+-----------------------------------+
 |  emulate_io_ff             | read content as all FF            |
 |----------------------------+-----------------------------------+
 |  emulate_io_ff_bitflips    | content FF with MTD err reported  |
 +----------------------------+-----------------------------------+
 |  emulate_bad_hdr           | bad leb header                    |
 |----------------------------+-----------------------------------+
 |  emulate_bad_hdr_ebadmsg   | bad header with ECC err           |
 +----------------------------+-----------------------------------+

Signed-off-by: ZhaoLong Wang <wangzhaolong1@huawei.com>
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 drivers/mtd/ubi/debug.c |  30 +++++++
 drivers/mtd/ubi/debug.h | 172 ++++++++++++++++++++++++++++++++++++++--
 drivers/mtd/ubi/io.c    |  76 +++++++++++++++++-
 drivers/mtd/ubi/ubi.h   |  30 ++++---
 4 files changed, 287 insertions(+), 21 deletions(-)

diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index 186306228b4d9..007f82d71020e 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -13,10 +13,16 @@
 #include <linux/fault-inject.h>
 
 #ifdef CONFIG_MTD_UBI_FAULT_INJECTION
+static DECLARE_FAULT_ATTR(fault_eccerr_attr);
 static DECLARE_FAULT_ATTR(fault_bitflips_attr);
+static DECLARE_FAULT_ATTR(fault_read_failure_attr);
 static DECLARE_FAULT_ATTR(fault_write_failure_attr);
 static DECLARE_FAULT_ATTR(fault_erase_failure_attr);
 static DECLARE_FAULT_ATTR(fault_power_cut_attr);
+static DECLARE_FAULT_ATTR(fault_io_ff_attr);
+static DECLARE_FAULT_ATTR(fault_io_ff_bitflips_attr);
+static DECLARE_FAULT_ATTR(fault_bad_hdr_attr);
+static DECLARE_FAULT_ATTR(fault_bad_hdr_ebadmsg_attr);
 
 #define FAIL_ACTION(name, fault_attr)			\
 bool should_fail_##name(void)				\
@@ -24,10 +30,16 @@ bool should_fail_##name(void)				\
 	return should_fail(&fault_attr, 1);		\
 }
 
+FAIL_ACTION(eccerr,		fault_eccerr_attr)
 FAIL_ACTION(bitflips,		fault_bitflips_attr)
+FAIL_ACTION(read_failure,	fault_read_failure_attr)
 FAIL_ACTION(write_failure,	fault_write_failure_attr)
 FAIL_ACTION(erase_failure,	fault_erase_failure_attr)
 FAIL_ACTION(power_cut,		fault_power_cut_attr)
+FAIL_ACTION(io_ff,		fault_io_ff_attr)
+FAIL_ACTION(io_ff_bitflips,	fault_io_ff_bitflips_attr)
+FAIL_ACTION(bad_hdr,		fault_bad_hdr_attr)
+FAIL_ACTION(bad_hdr_ebadmsg,	fault_bad_hdr_ebadmsg_attr)
 #endif
 
 /**
@@ -244,6 +256,12 @@ static void dfs_create_fault_entry(struct dentry *parent)
 		return;
 	}
 
+	fault_create_debugfs_attr("emulate_eccerr", dir,
+				  &fault_eccerr_attr);
+
+	fault_create_debugfs_attr("emulate_read_failure", dir,
+				  &fault_read_failure_attr);
+
 	fault_create_debugfs_attr("emulate_bitflips", dir,
 				  &fault_bitflips_attr);
 
@@ -255,6 +273,18 @@ static void dfs_create_fault_entry(struct dentry *parent)
 
 	fault_create_debugfs_attr("emulate_power_cut", dir,
 				  &fault_power_cut_attr);
+
+	fault_create_debugfs_attr("emulate_io_ff", dir,
+				  &fault_io_ff_attr);
+
+	fault_create_debugfs_attr("emulate_io_ff_bitflips", dir,
+				  &fault_io_ff_bitflips_attr);
+
+	fault_create_debugfs_attr("emulate_bad_hdr", dir,
+				  &fault_bad_hdr_attr);
+
+	fault_create_debugfs_attr("emulate_bad_hdr_ebadmsg", dir,
+				  &fault_bad_hdr_ebadmsg_attr);
 }
 #endif
 
diff --git a/drivers/mtd/ubi/debug.h b/drivers/mtd/ubi/debug.h
index 8cdd25eee0138..b2fd975488084 100644
--- a/drivers/mtd/ubi/debug.h
+++ b/drivers/mtd/ubi/debug.h
@@ -87,18 +87,45 @@ static inline int ubi_dbg_erase_failure(const struct ubi_device *ubi)
 /* Emulate a power cut when writing EC/VID header */
 #define MASK_POWER_CUT_EC			(1 << 0)
 #define MASK_POWER_CUT_VID			(1 << 1)
+/* Emulate a power cut when writing data*/
+#define MASK_POWER_CUT_DATA			(1 << 2)
+/* Emulate bit-flips */
+#define MASK_BITFLIPS				(1 << 3)
+/* Emulate ecc error */
+#define MASK_ECCERR				(1 << 4)
+/* Emulates -EIO during data read */
+#define MASK_READ_FAILURE			(1 << 5)
+#define MASK_READ_FAILURE_EC			(1 << 6)
+#define MASK_READ_FAILURE_VID			(1 << 7)
+/* Emulates -EIO during data write */
+#define MASK_WRITE_FAILURE			(1 << 8)
+/* Emulates -EIO during erase a PEB*/
+#define MASK_ERASE_FAILURE			(1 << 9)
+/* Return UBI_IO_FF when reading EC/VID header */
+#define MASK_IO_FF_EC				(1 << 10)
+#define MASK_IO_FF_VID				(1 << 11)
+/* Return UBI_IO_FF_BITFLIPS when reading EC/VID header */
+#define MASK_IO_FF_BITFLIPS_EC			(1 << 12)
+#define MASK_IO_FF_BITFLIPS_VID			(1 << 13)
+/* Return UBI_IO_BAD_HDR when reading EC/VID header */
+#define MASK_BAD_HDR_EC				(1 << 14)
+#define MASK_BAD_HDR_VID			(1 << 15)
+/* Return UBI_IO_BAD_HDR_EBADMSG when reading EC/VID header */
+#define MASK_BAD_HDR_EBADMSG_EC			(1 << 16)
+#define MASK_BAD_HDR_EBADMSG_VID		(1 << 17)
 
 #ifdef CONFIG_MTD_UBI_FAULT_INJECTION
-/* Emulate bit-flips */
-#define MASK_BITFLIPS				(1 << 2)
-/* Emulates -EIO during write/erase */
-#define MASK_WRITE_FAILURE			(1 << 3)
-#define MASK_ERASE_FAILURE			(1 << 4)
 
+extern bool should_fail_eccerr(void);
 extern bool should_fail_bitflips(void);
+extern bool should_fail_read_failure(void);
 extern bool should_fail_write_failure(void);
 extern bool should_fail_erase_failure(void);
 extern bool should_fail_power_cut(void);
+extern bool should_fail_io_ff(void);
+extern bool should_fail_io_ff_bitflips(void);
+extern bool should_fail_bad_hdr(void);
+extern bool should_fail_bad_hdr_ebadmsg(void);
 
 static inline bool ubi_dbg_fail_bitflip(const struct ubi_device *ubi)
 {
@@ -122,19 +149,72 @@ static inline bool ubi_dbg_fail_erase(const struct ubi_device *ubi)
 }
 
 static inline bool ubi_dbg_fail_power_cut(const struct ubi_device *ubi,
-					unsigned int caller)
+					  unsigned int caller)
 {
 	if (ubi->dbg.emulate_failures & caller)
 		return should_fail_power_cut();
 	return false;
 }
 
+static inline bool ubi_dbg_fail_read(const struct ubi_device *ubi,
+				     unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_read_failure();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_eccerr(const struct ubi_device *ubi)
+{
+	if (ubi->dbg.emulate_failures & MASK_ECCERR)
+		return should_fail_eccerr();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_ff(const struct ubi_device *ubi,
+				   unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_io_ff();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_ff_bitflips(const struct ubi_device *ubi,
+					    unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_io_ff_bitflips();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_bad_hdr(const struct ubi_device *ubi,
+					 unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_bad_hdr();
+	return false;
+}
+
+static inline bool ubi_dbg_fail_bad_hdr_ebadmsg(const struct ubi_device *ubi,
+						 unsigned int caller)
+{
+	if (ubi->dbg.emulate_failures & caller)
+		return should_fail_bad_hdr_ebadmsg();
+	return false;
+}
 #else /* CONFIG_MTD_UBI_FAULT_INJECTION */
 
 #define ubi_dbg_fail_bitflip(u)             false
 #define ubi_dbg_fail_write(u)               false
 #define ubi_dbg_fail_erase(u)               false
 #define ubi_dbg_fail_power_cut(u, c)        false
+#define ubi_dbg_fail_read(u, c)             false
+#define ubi_dbg_fail_eccerr(u)              false
+#define ubi_dbg_fail_ff(u, c)               false
+#define ubi_dbg_fail_ff_bitflips(u, v)      false
+#define ubi_dbg_fail_bad_hdr(u, c)          false
+#define ubi_dbg_fail_bad_hdr_ebadmsg(u, c)  false
+
 #endif
 
 /**
@@ -192,6 +272,86 @@ static inline bool ubi_dbg_is_erase_failure(const struct ubi_device *ubi)
 	return ubi_dbg_fail_erase(ubi);
 }
 
+/**
+ * ubi_dbg_is_eccerr - if it is time to emulate ECC error.
+ * @ubi: UBI device description object
+ *
+ * Returns true if a ECC error should be emulated, otherwise returns false.
+ */
+static inline bool ubi_dbg_is_eccerr(const struct ubi_device *ubi)
+{
+	return ubi_dbg_fail_eccerr(ubi);
+}
+
+/**
+ * ubi_dbg_is_read_failure - if it is time to emulate a read failure.
+ * @ubi: UBI device description object
+ *
+ * Returns true if a read failure should be emulated, otherwise returns
+ * false.
+ */
+static inline bool ubi_dbg_is_read_failure(const struct ubi_device *ubi,
+					   unsigned int caller)
+{
+	return ubi_dbg_fail_read(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_ff - if it is time to emulate that read region is only 0xFF.
+ * @ubi: UBI device description object
+ *
+ * Returns true if read region should be emulated 0xFF, otherwise
+ * returns false.
+ */
+static inline bool ubi_dbg_is_ff(const struct ubi_device *ubi,
+				 unsigned int caller)
+{
+	return ubi_dbg_fail_ff(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_ff_bitflips - if it is time to emulate that read region is only 0xFF
+ * with error reported by the MTD driver
+ *
+ * @ubi: UBI device description object
+ *
+ * Returns true if read region should be emulated 0xFF and error
+ * reported by the MTD driver, otherwise returns false.
+ */
+static inline bool ubi_dbg_is_ff_bitflips(const struct ubi_device *ubi,
+					  unsigned int caller)
+{
+	return ubi_dbg_fail_ff_bitflips(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_bad_hdr - if it is time to emulate a bad header
+ * @ubi: UBI device description object
+ *
+ * Returns true if a bad header error should be emulated, otherwise
+ * returns false.
+ */
+static inline bool ubi_dbg_is_bad_hdr(const struct ubi_device *ubi,
+				      unsigned int caller)
+{
+	return ubi_dbg_fail_bad_hdr(ubi, caller);
+}
+
+/**
+ * ubi_dbg_is_bad_hdr_ebadmsg - if it is time to emulate a bad header with
+ * ECC error.
+ *
+ * @ubi: UBI device description object
+ *
+ * Returns true if a bad header with ECC error should be emulated, otherwise
+ * returns false.
+ */
+static inline bool ubi_dbg_is_bad_hdr_ebadmsg(const struct ubi_device *ubi,
+					      unsigned int caller)
+{
+	return ubi_dbg_fail_bad_hdr_ebadmsg(ubi, caller);
+}
+
 /**
  * ubi_dbg_is_bgt_disabled - if the background thread is disabled.
  * @ubi: UBI device description object
diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c
index fb70f5227f182..a4999bce435f5 100644
--- a/drivers/mtd/ubi/io.c
+++ b/drivers/mtd/ubi/io.c
@@ -195,7 +195,19 @@ retry:
 
 		if (ubi_dbg_is_bitflip(ubi)) {
 			dbg_gen("bit-flip (emulated)");
-			err = UBI_IO_BITFLIPS;
+			return UBI_IO_BITFLIPS;
+		}
+
+		if (ubi_dbg_is_read_failure(ubi, MASK_READ_FAILURE)) {
+			ubi_warn(ubi, "cannot read %d bytes from PEB %d:%d (emulated)",
+				 len, pnum, offset);
+			return -EIO;
+		}
+
+		if (ubi_dbg_is_eccerr(ubi)) {
+			ubi_warn(ubi, "ECC error (emulated) while reading %d bytes from PEB %d:%d, read %zd bytes",
+				 len, pnum, offset, read);
+			return -EBADMSG;
 		}
 	}
 
@@ -782,7 +794,36 @@ int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum,
 	 * If there was %-EBADMSG, but the header CRC is still OK, report about
 	 * a bit-flip to force scrubbing on this PEB.
 	 */
-	return read_err ? UBI_IO_BITFLIPS : 0;
+	if (read_err)
+		return UBI_IO_BITFLIPS;
+
+	if (ubi_dbg_is_read_failure(ubi, MASK_READ_FAILURE_EC)) {
+		ubi_warn(ubi, "cannot read EC header from PEB %d (emulated)",
+			 pnum);
+		return -EIO;
+	}
+
+	if (ubi_dbg_is_ff(ubi, MASK_IO_FF_EC)) {
+		ubi_warn(ubi, "bit-all-ff (emulated)");
+		return UBI_IO_FF;
+	}
+
+	if (ubi_dbg_is_ff_bitflips(ubi, MASK_IO_FF_BITFLIPS_EC)) {
+		ubi_warn(ubi, "bit-all-ff with error reported by MTD driver (emulated)");
+		return UBI_IO_FF_BITFLIPS;
+	}
+
+	if (ubi_dbg_is_bad_hdr(ubi, MASK_BAD_HDR_EC)) {
+		ubi_warn(ubi, "bad_hdr (emulated)");
+		return UBI_IO_BAD_HDR;
+	}
+
+	if (ubi_dbg_is_bad_hdr_ebadmsg(ubi, MASK_BAD_HDR_EBADMSG_EC)) {
+		ubi_warn(ubi, "bad_hdr with ECC error (emulated)");
+		return UBI_IO_BAD_HDR_EBADMSG;
+	}
+
+	return 0;
 }
 
 /**
@@ -1032,7 +1073,36 @@ int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
 		return -EINVAL;
 	}
 
-	return read_err ? UBI_IO_BITFLIPS : 0;
+	if (read_err)
+		return UBI_IO_BITFLIPS;
+
+	if (ubi_dbg_is_read_failure(ubi, MASK_READ_FAILURE_VID)) {
+		ubi_warn(ubi, "cannot read VID header from PEB %d (emulated)",
+			 pnum);
+		return -EIO;
+	}
+
+	if (ubi_dbg_is_ff(ubi, MASK_IO_FF_VID)) {
+		ubi_warn(ubi, "bit-all-ff (emulated)");
+		return UBI_IO_FF;
+	}
+
+	if (ubi_dbg_is_ff_bitflips(ubi, MASK_IO_FF_BITFLIPS_VID)) {
+		ubi_warn(ubi, "bit-all-ff with error reported by MTD driver (emulated)");
+		return UBI_IO_FF_BITFLIPS;
+	}
+
+	if (ubi_dbg_is_bad_hdr(ubi, MASK_BAD_HDR_VID)) {
+		ubi_warn(ubi, "bad_hdr (emulated)");
+		return UBI_IO_BAD_HDR;
+	}
+
+	if (ubi_dbg_is_bad_hdr_ebadmsg(ubi, MASK_BAD_HDR_EBADMSG_VID)) {
+		ubi_warn(ubi, "bad_hdr with ECC error (emulated)");
+		return UBI_IO_BAD_HDR_EBADMSG;
+	}
+
+	return 0;
 }
 
 /**
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index cc4777983bd29..0b42bb45dd840 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -1123,6 +1123,19 @@ static inline struct ubi_vid_hdr *ubi_get_vid_hdr(struct ubi_vid_io_buf *vidb)
 	return vidb->hdr;
 }
 
+/**
+ * ubi_ro_mode - switch to read-only mode.
+ * @ubi: UBI device description object
+ */
+static inline void ubi_ro_mode(struct ubi_device *ubi)
+{
+	if (!ubi->ro_mode) {
+		ubi->ro_mode = 1;
+		ubi_warn(ubi, "switch to read-only mode");
+		dump_stack();
+	}
+}
+
 /*
  * This function is equivalent to 'ubi_io_read()', but @offset is relative to
  * the beginning of the logical eraseblock, not to the beginning of the
@@ -1144,20 +1157,13 @@ static inline int ubi_io_write_data(struct ubi_device *ubi, const void *buf,
 				    int pnum, int offset, int len)
 {
 	ubi_assert(offset >= 0);
-	return ubi_io_write(ubi, buf, pnum, offset + ubi->leb_start, len);
-}
 
-/**
- * ubi_ro_mode - switch to read-only mode.
- * @ubi: UBI device description object
- */
-static inline void ubi_ro_mode(struct ubi_device *ubi)
-{
-	if (!ubi->ro_mode) {
-		ubi->ro_mode = 1;
-		ubi_warn(ubi, "switch to read-only mode");
-		dump_stack();
+	if (ubi_dbg_power_cut(ubi, MASK_POWER_CUT_DATA)) {
+		ubi_warn(ubi, "XXXXX emulating a power cut when writing data XXXXX");
+		ubi_ro_mode(ubi);
+		return -EROFS;
 	}
+	return ubi_io_write(ubi, buf, pnum, offset + ubi->leb_start, len);
 }
 
 /**
-- 
GitLab


From 4d0deb380a5b53471cde1d8c0e0fbd1b53bfbc64 Mon Sep 17 00:00:00 2001
From: ZhaoLong Wang <wangzhaolong1@huawei.com>
Date: Tue, 26 Dec 2023 09:01:12 +0800
Subject: [PATCH 2321/4076] ubi: Reserve sufficient buffer length for the input
 mask

Because the mask received by the emulate_failures interface
is a 32-bit unsigned integer, ensure that there is sufficient
buffer length to receive and display this value.

Signed-off-by: ZhaoLong Wang <wangzhaolong1@huawei.com>
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 drivers/mtd/ubi/debug.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index 007f82d71020e..d57f52bd2ff3c 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -332,7 +332,7 @@ static ssize_t dfs_file_read(struct file *file, char __user *user_buf,
 	struct dentry *dent = file->f_path.dentry;
 	struct ubi_device *ubi;
 	struct ubi_debug_info *d;
-	char buf[8];
+	char buf[16];
 	int val;
 
 	ubi = ubi_get_device(ubi_num);
@@ -400,7 +400,7 @@ static ssize_t dfs_file_write(struct file *file, const char __user *user_buf,
 	struct ubi_device *ubi;
 	struct ubi_debug_info *d;
 	size_t buf_size;
-	char buf[8] = {0};
+	char buf[16] = {0};
 	int val;
 
 	ubi = ubi_get_device(ubi_num);
-- 
GitLab


From 2fe48aaab2669b3fbb11bf1b822a1b07424eef56 Mon Sep 17 00:00:00 2001
From: ZhaoLong Wang <wangzhaolong1@huawei.com>
Date: Tue, 26 Dec 2023 09:01:13 +0800
Subject: [PATCH 2322/4076] mtd: Add several functions to the fail_function
 list

add mtd_read(), mtd_write(), mtd_erase(), mtd_block_markbad() to
fail_function list for testing purpose

- Specify the function to inject the fault
echo mtd_read > /sys/kernel/debug/fail_function/inject

- Specifies the return value of the function to inject the fault
printf %#x -12 > /sys/kernel/debug/fail_function/mtd_read/retval

- Specify other fault injection configuration parameters.
echo -1 > /sys/kernel/debug/fail_function/times
echo 100 > /sys/kernel/debug/fail_function/probability
echo 15 > /sys/kernel/debug/fail_function/space

Signed-off-by: ZhaoLong Wang <wangzhaolong1@huawei.com>
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 drivers/mtd/mtdcore.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index bb0759ca12f1c..e451b28840d58 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -30,6 +30,7 @@
 #include <linux/debugfs.h>
 #include <linux/nvmem-provider.h>
 #include <linux/root_dev.h>
+#include <linux/error-injection.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
@@ -1412,6 +1413,7 @@ int mtd_erase(struct mtd_info *mtd, struct erase_info *instr)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mtd_erase);
+ALLOW_ERROR_INJECTION(mtd_erase, ERRNO);
 
 /*
  * This stuff for eXecute-In-Place. phys is optional and may be set to NULL.
@@ -1511,6 +1513,7 @@ int mtd_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mtd_read);
+ALLOW_ERROR_INJECTION(mtd_read, ERRNO);
 
 int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
 	      const u_char *buf)
@@ -1527,6 +1530,7 @@ int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mtd_write);
+ALLOW_ERROR_INJECTION(mtd_write, ERRNO);
 
 /*
  * In blackbox flight recorder like scenarios we want to make successful writes
@@ -2347,6 +2351,7 @@ int mtd_block_markbad(struct mtd_info *mtd, loff_t ofs)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mtd_block_markbad);
+ALLOW_ERROR_INJECTION(mtd_block_markbad, ERRNO);
 
 /*
  * default_mtd_writev - the default writev method
-- 
GitLab


From ac8e9f64f51b6e61e7181a44525e1d4cd1cb338a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 5 Dec 2023 18:48:50 -0800
Subject: [PATCH 2323/4076] ubifs: fix kernel-doc warnings

Fix kernel-doc warnings found when using "W=1".

file.c:1385: warning: Excess function parameter 'time' description in 'ubifs_update_time'
and 9 warnings like this one:
file.c:326: warning: No description found for return value of 'allocate_budget'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/oe-kbuild-all/202312030417.66c5PwHj-lkp@intel.com/
Cc: Richard Weinberger <richard@nod.at>
Cc: linux-mtd@lists.infradead.org
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
[rw: massaged patch to resolve conflict ]
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 fs/ubifs/file.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 2d2b39f843ce9..5029eb3390a56 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -318,8 +318,9 @@ static int write_begin_slow(struct address_space *mapping,
  * This is a helper function for 'ubifs_write_begin()' which allocates budget
  * for the operation. The budget is allocated differently depending on whether
  * this is appending, whether the page is dirty or not, and so on. This
- * function leaves the @ui->ui_mutex locked in case of appending. Returns zero
- * in case of success and %-ENOSPC in case of failure.
+ * function leaves the @ui->ui_mutex locked in case of appending.
+ *
+ * Returns: %0 in case of success and %-ENOSPC in case of failure.
  */
 static int allocate_budget(struct ubifs_info *c, struct page *page,
 			   struct ubifs_inode *ui, int appending)
@@ -600,7 +601,7 @@ out:
  * @bu: bulk-read information
  * @n: next zbranch slot
  *
- * This function returns %0 on success and a negative error code on failure.
+ * Returns: %0 on success and a negative error code on failure.
  */
 static int populate_page(struct ubifs_info *c, struct page *page,
 			 struct bu_info *bu, int *n)
@@ -711,7 +712,7 @@ out_err:
  * @bu: bulk-read information
  * @page1: first page to read
  *
- * This function returns %1 if the bulk-read is done, otherwise %0 is returned.
+ * Returns: %1 if the bulk-read is done, otherwise %0 is returned.
  */
 static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
 			      struct page *page1)
@@ -821,7 +822,9 @@ out_bu_off:
  * Some flash media are capable of reading sequentially at faster rates. UBIFS
  * bulk-read facility is designed to take advantage of that, by reading in one
  * go consecutive data nodes that are also located consecutively in the same
- * LEB. This function returns %1 if a bulk-read is done and %0 otherwise.
+ * LEB.
+ *
+ * Returns: %1 if a bulk-read is done and %0 otherwise.
  */
 static int ubifs_bulk_read(struct page *page)
 {
@@ -1109,7 +1112,9 @@ static void do_attr_changes(struct inode *inode, const struct iattr *attr)
  * @attr: inode attribute changes description
  *
  * This function implements VFS '->setattr()' call when the inode is truncated
- * to a smaller size. Returns zero in case of success and a negative error code
+ * to a smaller size.
+ *
+ * Returns: %0 in case of success and a negative error code
  * in case of failure.
  */
 static int do_truncation(struct ubifs_info *c, struct inode *inode,
@@ -1215,7 +1220,9 @@ out_budg:
  * @attr: inode attribute changes description
  *
  * This function implements VFS '->setattr()' call for all cases except
- * truncations to smaller size. Returns zero in case of success and a negative
+ * truncations to smaller size.
+ *
+ * Returns: %0 in case of success and a negative
  * error code in case of failure.
  */
 static int do_setattr(struct ubifs_info *c, struct inode *inode,
@@ -1360,6 +1367,8 @@ out:
  * This helper function checks if the inode mtime/ctime should be updated or
  * not. If current values of the time-stamps are within the UBIFS inode time
  * granularity, they are not updated. This is an optimization.
+ *
+ * Returns: %1 if time update is needed, %0 if not
  */
 static inline int mctime_update_needed(const struct inode *inode,
 				       const struct timespec64 *now)
@@ -1375,11 +1384,12 @@ static inline int mctime_update_needed(const struct inode *inode,
 /**
  * ubifs_update_time - update time of inode.
  * @inode: inode to update
- * @time:  timespec structure to hold the current time value
  * @flags: time updating control flag determines updating
  *	    which time fields of @inode
  *
  * This function updates time of the inode.
+ *
+ * Returns: %0 for success or a negative error code otherwise.
  */
 int ubifs_update_time(struct inode *inode, int flags)
 {
@@ -1413,7 +1423,9 @@ int ubifs_update_time(struct inode *inode, int flags)
  * @inode: inode to update
  *
  * This function updates mtime and ctime of the inode if it is not equivalent to
- * current time. Returns zero in case of success and a negative error code in
+ * current time.
+ *
+ * Returns: %0 in case of success and a negative error code in
  * case of failure.
  */
 static int update_mctime(struct inode *inode)
-- 
GitLab


From adbf4c4954e33e623897058a617c583d65a177f6 Mon Sep 17 00:00:00 2001
From: Li Nan <linan122@huawei.com>
Date: Fri, 8 Dec 2023 15:46:29 +0800
Subject: [PATCH 2324/4076] ubi: block: fix memleak in ubiblock_create()

If idr_alloc() fails, dev->gd will be put after goto out_cleanup_disk in
ubiblock_create(), but dev->gd has not been assigned yet at this time, and
'gd' will not be put anymore. Fix it by putting 'gd' directly.

Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 drivers/mtd/ubi/block.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 309a42aeaa4cd..654bd7372cd8c 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -434,7 +434,7 @@ out_remove_minor:
 	list_del(&dev->list);
 	idr_remove(&ubiblock_minor_idr, gd->first_minor);
 out_cleanup_disk:
-	put_disk(dev->gd);
+	put_disk(gd);
 out_free_tags:
 	blk_mq_free_tag_set(&dev->tag_set);
 out_free_dev:
-- 
GitLab


From 5850edccec30325707f953bc088497b3b9041231 Mon Sep 17 00:00:00 2001
From: Tanzir Hasan <tanzirh@google.com>
Date: Thu, 4 Jan 2024 19:31:36 +0000
Subject: [PATCH 2325/4076] android: removed duplicate linux/errno

There are two linux/errno.h inclusions in this file. The second one has
been removed and the file builds correctly.

Fixes: 54ffdab82080 ("android: binder: binderfs.c: removed asm-generic/errno-base.h")
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Tanzir Hasan <tanzirh@google.com>
Acked-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20240104-removeduperror-v1-1-d170d4b3675a@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binderfs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index d04ff60294800..3001d754ac369 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -29,7 +29,6 @@
 #include <linux/uaccess.h>
 #include <linux/user_namespace.h>
 #include <linux/xarray.h>
-#include <linux/errno.h>
 #include <uapi/linux/android/binder.h>
 #include <uapi/linux/android/binderfs.h>
 
-- 
GitLab


From 735ae74f73e55c191d48689bd11ff4a06ea0508f Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 3 Jan 2024 21:02:16 +0100
Subject: [PATCH 2326/4076] parisc/firmware: Fix F-extend for PDC addresses

When running with narrow firmware (64-bit kernel using a 32-bit
firmware), extend PDC addresses into the 0xfffffff0.00000000
region instead of the 0xf0f0f0f0.00000000 region.

This fixes the power button on the C3700 machine in qemu (64-bit CPU
with 32-bit firmware), and my assumption is that the previous code was
really never used (because most 64-bit machines have a 64-bit firmware),
or it just worked on very old machines because they may only decode
40-bit of virtual addresses.

Cc: stable@vger.kernel.org
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/firmware.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index 904ca3b9e7a71..c69f6d5946e90 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -123,10 +123,10 @@ static unsigned long f_extend(unsigned long address)
 #ifdef CONFIG_64BIT
 	if(unlikely(parisc_narrow_firmware)) {
 		if((address & 0xff000000) == 0xf0000000)
-			return 0xf0f0f0f000000000UL | (u32)address;
+			return (0xfffffff0UL << 32) | (u32)address;
 
 		if((address & 0xf0000000) == 0xf0000000)
-			return 0xffffffff00000000UL | (u32)address;
+			return (0xffffffffUL << 32) | (u32)address;
 	}
 #endif
 	return address;
-- 
GitLab


From 6472036581f947109b20664121db1d143e916f0b Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 3 Jan 2024 21:17:23 +0100
Subject: [PATCH 2327/4076] parisc/power: Fix power soft-off button emulation
 on qemu

Make sure to start the kthread to check the power button on qemu as
well if the power button address was provided.
This fixes the qemu built-in system_powerdown runtime command.

Fixes: d0c219472980 ("parisc/power: Add power soft-off when running on qemu")
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: stable@vger.kernel.org # v6.0+
---
 drivers/parisc/power.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c
index bb0d92461b08b..7a6a3e7f2825b 100644
--- a/drivers/parisc/power.c
+++ b/drivers/parisc/power.c
@@ -213,7 +213,7 @@ static int __init power_init(void)
 	if (running_on_qemu && soft_power_reg)
 		register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, SYS_OFF_PRIO_DEFAULT,
 					qemu_power_off, (void *)soft_power_reg);
-	else
+	if (!running_on_qemu || soft_power_reg)
 		power_task = kthread_run(kpowerswd, (void*)soft_power_reg,
 					KTHREAD_NAME);
 	if (IS_ERR(power_task)) {
-- 
GitLab


From 317bacf960a4879af22d12175f47d284930b3273 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 1 Dec 2023 17:25:27 -0500
Subject: [PATCH 2328/4076] i3c: master: add enable(disable) hot join in sys
 entry

Add hotjoin entry in sys file system allow user enable/disable hotjoin
feature.

Add (*enable(disable)_hotjoin)() to i3c_master_controller_ops.
Add api i3c_master_enable(disable)_hotjoin();

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231201222532.2431484-2-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c       | 83 ++++++++++++++++++++++++++++++++++++++
 include/linux/i3c/master.h |  5 +++
 2 files changed, 88 insertions(+)

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 8b729ebae2a6e..3afa530c5e322 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -557,6 +557,88 @@ static ssize_t i2c_scl_frequency_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(i2c_scl_frequency);
 
+static int i3c_set_hotjoin(struct i3c_master_controller *master, bool enable)
+{
+	int ret;
+
+	if (!master || !master->ops)
+		return -EINVAL;
+
+	if (!master->ops->enable_hotjoin || !master->ops->disable_hotjoin)
+		return -EINVAL;
+
+	i3c_bus_normaluse_lock(&master->bus);
+
+	if (enable)
+		ret = master->ops->enable_hotjoin(master);
+	else
+		ret = master->ops->disable_hotjoin(master);
+
+	master->hotjoin = enable;
+
+	i3c_bus_normaluse_unlock(&master->bus);
+
+	return ret;
+}
+
+static ssize_t hotjoin_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct i3c_bus *i3cbus = dev_to_i3cbus(dev);
+	int ret;
+	bool res;
+
+	if (!i3cbus->cur_master)
+		return -EINVAL;
+
+	if (kstrtobool(buf, &res))
+		return -EINVAL;
+
+	ret = i3c_set_hotjoin(i3cbus->cur_master->common.master, res);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+/*
+ * i3c_master_enable_hotjoin - Enable hotjoin
+ * @master: I3C master object
+ *
+ * Return: a 0 in case of success, an negative error code otherwise.
+ */
+int i3c_master_enable_hotjoin(struct i3c_master_controller *master)
+{
+	return i3c_set_hotjoin(master, true);
+}
+EXPORT_SYMBOL_GPL(i3c_master_enable_hotjoin);
+
+/*
+ * i3c_master_disable_hotjoin - Disable hotjoin
+ * @master: I3C master object
+ *
+ * Return: a 0 in case of success, an negative error code otherwise.
+ */
+int i3c_master_disable_hotjoin(struct i3c_master_controller *master)
+{
+	return i3c_set_hotjoin(master, false);
+}
+EXPORT_SYMBOL_GPL(i3c_master_disable_hotjoin);
+
+static ssize_t hotjoin_show(struct device *dev, struct device_attribute *da, char *buf)
+{
+	struct i3c_bus *i3cbus = dev_to_i3cbus(dev);
+	ssize_t ret;
+
+	i3c_bus_normaluse_lock(i3cbus);
+	ret = sysfs_emit(buf, "%d\n", i3cbus->cur_master->common.master->hotjoin);
+	i3c_bus_normaluse_unlock(i3cbus);
+
+	return ret;
+}
+
+static DEVICE_ATTR_RW(hotjoin);
+
 static struct attribute *i3c_masterdev_attrs[] = {
 	&dev_attr_mode.attr,
 	&dev_attr_current_master.attr,
@@ -567,6 +649,7 @@ static struct attribute *i3c_masterdev_attrs[] = {
 	&dev_attr_pid.attr,
 	&dev_attr_dynamic_address.attr,
 	&dev_attr_hdrcap.attr,
+	&dev_attr_hotjoin.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(i3c_masterdev);
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 24c1863b86e2b..3b5bd8e3257c1 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -460,6 +460,8 @@ struct i3c_master_controller_ops {
 	int (*disable_ibi)(struct i3c_dev_desc *dev);
 	void (*recycle_ibi_slot)(struct i3c_dev_desc *dev,
 				 struct i3c_ibi_slot *slot);
+	int (*enable_hotjoin)(struct i3c_master_controller *master);
+	int (*disable_hotjoin)(struct i3c_master_controller *master);
 };
 
 /**
@@ -495,6 +497,7 @@ struct i3c_master_controller {
 	const struct i3c_master_controller_ops *ops;
 	unsigned int secondary : 1;
 	unsigned int init_done : 1;
+	unsigned int hotjoin: 1;
 	struct {
 		struct list_head i3c;
 		struct list_head i2c;
@@ -551,6 +554,8 @@ int i3c_master_register(struct i3c_master_controller *master,
 			const struct i3c_master_controller_ops *ops,
 			bool secondary);
 void i3c_master_unregister(struct i3c_master_controller *master);
+int i3c_master_enable_hotjoin(struct i3c_master_controller *master);
+int i3c_master_disable_hotjoin(struct i3c_master_controller *master);
 
 /**
  * i3c_dev_get_master_data() - get master private data attached to an I3C
-- 
GitLab


From 05b26c31a4859af9e75b7de77458e99358364fe1 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 1 Dec 2023 17:25:28 -0500
Subject: [PATCH 2329/4076] i3c: master: svc: add hot join support

Add hot join support for svc master controller. Disable hot join by
default.
User can use sysfs entry to enable hot join.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231201222532.2431484-3-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 61 +++++++++++++++++++++++++++--
 1 file changed, 57 insertions(+), 4 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index cf703c00f6334..a993ccfc4033d 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -128,6 +128,9 @@
 /* This parameter depends on the implementation and may be tuned */
 #define SVC_I3C_FIFO_SIZE 16
 
+#define SVC_I3C_EVENT_IBI	BIT(0)
+#define SVC_I3C_EVENT_HOTJOIN	BIT(1)
+
 struct svc_i3c_cmd {
 	u8 addr;
 	bool rnw;
@@ -177,6 +180,7 @@ struct svc_i3c_regs_save {
  * @ibi.tbq_slot: To be queued IBI slot
  * @ibi.lock: IBI lock
  * @lock: Transfer lock, protect between IBI work thread and callbacks from master
+ * @enabled_events: Bit masks for enable events (IBI, HotJoin).
  */
 struct svc_i3c_master {
 	struct i3c_master_controller base;
@@ -206,6 +210,7 @@ struct svc_i3c_master {
 		spinlock_t lock;
 	} ibi;
 	struct mutex lock;
+	int enabled_events;
 };
 
 /**
@@ -220,6 +225,11 @@ struct svc_i3c_i2c_dev_data {
 	struct i3c_generic_ibi_pool *ibi_pool;
 };
 
+static inline bool is_events_enabled(struct svc_i3c_master *master, u32 mask)
+{
+	return !!(master->enabled_events & mask);
+}
+
 static bool svc_i3c_master_error(struct svc_i3c_master *master)
 {
 	u32 mstatus, merrwarn;
@@ -429,13 +439,16 @@ static void svc_i3c_master_ibi_work(struct work_struct *work)
 	switch (ibitype) {
 	case SVC_I3C_MSTATUS_IBITYPE_IBI:
 		dev = svc_i3c_master_dev_from_addr(master, ibiaddr);
-		if (!dev)
+		if (!dev || !is_events_enabled(master, SVC_I3C_EVENT_IBI))
 			svc_i3c_master_nack_ibi(master);
 		else
 			svc_i3c_master_handle_ibi(master, dev);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_HOT_JOIN:
-		svc_i3c_master_ack_ibi(master, false);
+		if (is_events_enabled(master, SVC_I3C_EVENT_HOTJOIN))
+			svc_i3c_master_ack_ibi(master, false);
+		else
+			svc_i3c_master_nack_ibi(master);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_MASTER_REQUEST:
 		svc_i3c_master_nack_ibi(master);
@@ -472,7 +485,9 @@ static void svc_i3c_master_ibi_work(struct work_struct *work)
 		svc_i3c_master_emit_stop(master);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_HOT_JOIN:
-		queue_work(master->base.wq, &master->hj_work);
+		svc_i3c_master_emit_stop(master);
+		if (is_events_enabled(master, SVC_I3C_EVENT_HOTJOIN))
+			queue_work(master->base.wq, &master->hj_work);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_MASTER_REQUEST:
 	default:
@@ -1472,6 +1487,7 @@ static int svc_i3c_master_enable_ibi(struct i3c_dev_desc *dev)
 		return ret;
 	}
 
+	master->enabled_events |= SVC_I3C_EVENT_IBI;
 	svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART);
 
 	return i3c_master_enec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR);
@@ -1483,7 +1499,9 @@ static int svc_i3c_master_disable_ibi(struct i3c_dev_desc *dev)
 	struct svc_i3c_master *master = to_svc_i3c_master(m);
 	int ret;
 
-	svc_i3c_master_disable_interrupts(master);
+	master->enabled_events &= ~SVC_I3C_EVENT_IBI;
+	if (!master->enabled_events)
+		svc_i3c_master_disable_interrupts(master);
 
 	ret = i3c_master_disec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR);
 
@@ -1493,6 +1511,39 @@ static int svc_i3c_master_disable_ibi(struct i3c_dev_desc *dev)
 	return ret;
 }
 
+static int svc_i3c_master_enable_hotjoin(struct i3c_master_controller *m)
+{
+	struct svc_i3c_master *master = to_svc_i3c_master(m);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(master->dev);
+	if (ret < 0) {
+		dev_err(master->dev, "<%s> Cannot get runtime PM.\n", __func__);
+		return ret;
+	}
+
+	master->enabled_events |= SVC_I3C_EVENT_HOTJOIN;
+
+	svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART);
+
+	return 0;
+}
+
+static int svc_i3c_master_disable_hotjoin(struct i3c_master_controller *m)
+{
+	struct svc_i3c_master *master = to_svc_i3c_master(m);
+
+	master->enabled_events &= ~SVC_I3C_EVENT_HOTJOIN;
+
+	if (!master->enabled_events)
+		svc_i3c_master_disable_interrupts(master);
+
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
+
+	return 0;
+}
+
 static void svc_i3c_master_recycle_ibi_slot(struct i3c_dev_desc *dev,
 					    struct i3c_ibi_slot *slot)
 {
@@ -1519,6 +1570,8 @@ static const struct i3c_master_controller_ops svc_i3c_master_ops = {
 	.recycle_ibi_slot = svc_i3c_master_recycle_ibi_slot,
 	.enable_ibi = svc_i3c_master_enable_ibi,
 	.disable_ibi = svc_i3c_master_disable_ibi,
+	.enable_hotjoin = svc_i3c_master_enable_hotjoin,
+	.disable_hotjoin = svc_i3c_master_disable_hotjoin,
 };
 
 static int svc_i3c_master_prepare_clks(struct svc_i3c_master *master)
-- 
GitLab


From e5e3df06ac98d15cfb10bb5c12356709365e91b2 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 1 Dec 2023 17:25:29 -0500
Subject: [PATCH 2330/4076] i3c: add actual_len in i3c_priv_xfer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In MIPI I3C Specification:

"Ninth Bit of SDR Target Returned (Read) Data as End-of-Data: In I2C, the
ninth Data bit from Target to Controller is an ACK by the Controller. By
contrast, in I3C this bit allows the Target to end a Read, and allows the
Controller to Abort a Read. In SDR terms, the ninth bit of Read data is
referred to as the T-Bit (for ‘Transition’)"

I3C allow devices early terminate data transfer. So need "actual_len" field
to indicate how much get by i3c_priv_xfer.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231201222532.2431484-4-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/device.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h
index 84ed77c049400..e119f11948efe 100644
--- a/include/linux/i3c/device.h
+++ b/include/linux/i3c/device.h
@@ -54,6 +54,7 @@ enum i3c_hdr_mode {
  * struct i3c_priv_xfer - I3C SDR private transfer
  * @rnw: encodes the transfer direction. true for a read, false for a write
  * @len: transfer length in bytes of the transfer
+ * @actual_len: actual length in bytes are transferred by the controller
  * @data: input/output buffer
  * @data.in: input buffer. Must point to a DMA-able buffer
  * @data.out: output buffer. Must point to a DMA-able buffer
@@ -62,6 +63,7 @@ enum i3c_hdr_mode {
 struct i3c_priv_xfer {
 	u8 rnw;
 	u16 len;
+	u16 actual_len;
 	union {
 		void *in;
 		const void *out;
-- 
GitLab


From 6fb61734a74eaa307a5b6a0bee770e736d8acf89 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 1 Dec 2023 17:25:30 -0500
Subject: [PATCH 2331/4076] i3c: master: svc: rename read_len as actual_len

I3C transfer (SDR), target can early terminate read transfer.
I3C transfer (HDR), target can end write transfer.
I2C transfer, target can NACK write transfer.

'actual_len' is better name than 'read_len'.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231201222532.2431484-5-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index a993ccfc4033d..ad2f486ccf888 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -137,7 +137,7 @@ struct svc_i3c_cmd {
 	u8 *in;
 	const void *out;
 	unsigned int len;
-	unsigned int read_len;
+	unsigned int actual_len;
 	bool continued;
 };
 
@@ -1039,7 +1039,7 @@ static int svc_i3c_master_write(struct svc_i3c_master *master,
 static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 			       bool rnw, unsigned int xfer_type, u8 addr,
 			       u8 *in, const u8 *out, unsigned int xfer_len,
-			       unsigned int *read_len, bool continued)
+			       unsigned int *actual_len, bool continued)
 {
 	u32 reg;
 	int ret;
@@ -1052,7 +1052,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 	       SVC_I3C_MCTRL_IBIRESP_NACK |
 	       SVC_I3C_MCTRL_DIR(rnw) |
 	       SVC_I3C_MCTRL_ADDR(addr) |
-	       SVC_I3C_MCTRL_RDTERM(*read_len),
+	       SVC_I3C_MCTRL_RDTERM(*actual_len),
 	       master->regs + SVC_I3C_MCTRL);
 
 	ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
@@ -1090,7 +1090,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 		goto emit_stop;
 
 	if (rnw)
-		*read_len = ret;
+		*actual_len = ret;
 
 	ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
 				 SVC_I3C_MSTATUS_COMPLETE(reg), 0, 1000);
@@ -1172,7 +1172,7 @@ static void svc_i3c_master_start_xfer_locked(struct svc_i3c_master *master)
 
 		ret = svc_i3c_master_xfer(master, cmd->rnw, xfer->type,
 					  cmd->addr, cmd->in, cmd->out,
-					  cmd->len, &cmd->read_len,
+					  cmd->len, &cmd->actual_len,
 					  cmd->continued);
 		if (ret)
 			break;
@@ -1258,7 +1258,7 @@ static int svc_i3c_master_send_bdcast_ccc_cmd(struct svc_i3c_master *master,
 	cmd->in = NULL;
 	cmd->out = buf;
 	cmd->len = xfer_len;
-	cmd->read_len = 0;
+	cmd->actual_len = 0;
 	cmd->continued = false;
 
 	mutex_lock(&master->lock);
@@ -1278,7 +1278,7 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 					      struct i3c_ccc_cmd *ccc)
 {
 	unsigned int xfer_len = ccc->dests[0].payload.len;
-	unsigned int read_len = ccc->rnw ? xfer_len : 0;
+	unsigned int actual_len = ccc->rnw ? xfer_len : 0;
 	struct svc_i3c_xfer *xfer;
 	struct svc_i3c_cmd *cmd;
 	int ret;
@@ -1296,7 +1296,7 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 	cmd->in = NULL;
 	cmd->out = &ccc->id;
 	cmd->len = 1;
-	cmd->read_len = 0;
+	cmd->actual_len = 0;
 	cmd->continued = true;
 
 	/* Directed message */
@@ -1306,7 +1306,7 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 	cmd->in = ccc->rnw ? ccc->dests[0].payload.data : NULL;
 	cmd->out = ccc->rnw ? NULL : ccc->dests[0].payload.data,
 	cmd->len = xfer_len;
-	cmd->read_len = read_len;
+	cmd->actual_len = actual_len;
 	cmd->continued = false;
 
 	mutex_lock(&master->lock);
@@ -1315,8 +1315,8 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 		svc_i3c_master_dequeue_xfer(master, xfer);
 	mutex_unlock(&master->lock);
 
-	if (cmd->read_len != xfer_len)
-		ccc->dests[0].payload.len = cmd->read_len;
+	if (cmd->actual_len != xfer_len)
+		ccc->dests[0].payload.len = cmd->actual_len;
 
 	ret = xfer->ret;
 	svc_i3c_master_free_xfer(xfer);
@@ -1366,7 +1366,7 @@ static int svc_i3c_master_priv_xfers(struct i3c_dev_desc *dev,
 		cmd->in = xfers[i].rnw ? xfers[i].data.in : NULL;
 		cmd->out = xfers[i].rnw ? NULL : xfers[i].data.out;
 		cmd->len = xfers[i].len;
-		cmd->read_len = xfers[i].rnw ? xfers[i].len : 0;
+		cmd->actual_len = xfers[i].rnw ? xfers[i].len : 0;
 		cmd->continued = (i + 1) < nxfers;
 	}
 
@@ -1406,7 +1406,7 @@ static int svc_i3c_master_i2c_xfers(struct i2c_dev_desc *dev,
 		cmd->in = cmd->rnw ? xfers[i].buf : NULL;
 		cmd->out = cmd->rnw ? NULL : xfers[i].buf;
 		cmd->len = xfers[i].len;
-		cmd->read_len = cmd->rnw ? xfers[i].len : 0;
+		cmd->actual_len = cmd->rnw ? xfers[i].len : 0;
 		cmd->continued = (i + 1 < nxfers);
 	}
 
-- 
GitLab


From 6d1a19d34e2cc07ca9cdad8892da94e716e9d15f Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 1 Dec 2023 17:25:31 -0500
Subject: [PATCH 2332/4076] i3c: master: svc: return actual transfer data len

I3C allow devices early terminate data transfer. So set "actual_len" to
indicate how much data get by i3c_priv_xfer.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231201222532.2431484-6-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/svc-i3c-master.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index ad2f486ccf888..5ee4db68988e2 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -138,6 +138,7 @@ struct svc_i3c_cmd {
 	const void *out;
 	unsigned int len;
 	unsigned int actual_len;
+	struct i3c_priv_xfer *xfer;
 	bool continued;
 };
 
@@ -1062,6 +1063,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 
 	if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
 		ret = -ENXIO;
+		*actual_len = 0;
 		goto emit_stop;
 	}
 
@@ -1079,6 +1081,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 	 */
 	if (SVC_I3C_MSTATUS_IBIWON(reg)) {
 		ret = -ENXIO;
+		*actual_len = 0;
 		goto emit_stop;
 	}
 
@@ -1174,6 +1177,10 @@ static void svc_i3c_master_start_xfer_locked(struct svc_i3c_master *master)
 					  cmd->addr, cmd->in, cmd->out,
 					  cmd->len, &cmd->actual_len,
 					  cmd->continued);
+		/* cmd->xfer is NULL if I2C or CCC transfer */
+		if (cmd->xfer)
+			cmd->xfer->actual_len = cmd->actual_len;
+
 		if (ret)
 			break;
 	}
@@ -1361,6 +1368,7 @@ static int svc_i3c_master_priv_xfers(struct i3c_dev_desc *dev,
 	for (i = 0; i < nxfers; i++) {
 		struct svc_i3c_cmd *cmd = &xfer->cmds[i];
 
+		cmd->xfer = &xfers[i];
 		cmd->addr = master->addrs[data->index];
 		cmd->rnw = xfers[i].rnw;
 		cmd->in = xfers[i].rnw ? xfers[i].data.in : NULL;
-- 
GitLab


From 18e5794879905a788e06fb2bc40b6f5b58eae5c2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:05:42 -0800
Subject: [PATCH 2333/4076] i3c: master: fix Excess kernel-doc description
 warning

Remove the @boardinfo: line to prevent the kernel-doc warning:

include/linux/i3c/master.h:98: warning: Excess struct member 'boardinfo' description in 'i2c_dev_desc'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc:  <linux-i3c@lists.infradead.org>
Link: https://lore.kernel.org/r/20231223050542.13930-1-rdunlap@infradead.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/master.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 3b5bd8e3257c1..1ecd73b17ff5d 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -76,7 +76,6 @@ struct i2c_dev_boardinfo {
 /**
  * struct i2c_dev_desc - I2C device descriptor
  * @common: common part of the I2C device descriptor
- * @boardinfo: pointer to the boardinfo attached to this I2C device
  * @dev: I2C device object registered to the I2C framework
  * @addr: I2C device address
  * @lvr: LVR (Legacy Virtual Register) needed by the I3C core to know about
-- 
GitLab


From 374c13f9080a1b9835a5ed3e7bea93cf8e2dc262 Mon Sep 17 00:00:00 2001
From: Harshit Shah <harshitshah.opendev@gmail.com>
Date: Sat, 30 Dec 2023 14:41:23 +0530
Subject: [PATCH 2334/4076] i3c: master: cdns: Update maximum prescaler value
 for i2c clock

As per the Cadence IP document fixed the I2C clock divider value limit from
16 bits instead of 10 bits. Without this change setting up the I2C clock to
low frequencies will not work as the prescaler value might be greater than
10 bit number.

I3C clock divider value is 10 bits only. Updating the macro names for both.

Signed-off-by: Harshit Shah <harshitshah.opendev@gmail.com>
Link: https://lore.kernel.org/r/1703927483-28682-1-git-send-email-harshitshah.opendev@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/i3c-master-cdns.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c
index bcbe8f914149b..c1627f3552ce3 100644
--- a/drivers/i3c/master/i3c-master-cdns.c
+++ b/drivers/i3c/master/i3c-master-cdns.c
@@ -76,7 +76,8 @@
 #define PRESCL_CTRL0			0x14
 #define PRESCL_CTRL0_I2C(x)		((x) << 16)
 #define PRESCL_CTRL0_I3C(x)		(x)
-#define PRESCL_CTRL0_MAX		GENMASK(9, 0)
+#define PRESCL_CTRL0_I3C_MAX		GENMASK(9, 0)
+#define PRESCL_CTRL0_I2C_MAX		GENMASK(15, 0)
 
 #define PRESCL_CTRL1			0x18
 #define PRESCL_CTRL1_PP_LOW_MASK	GENMASK(15, 8)
@@ -1233,7 +1234,7 @@ static int cdns_i3c_master_bus_init(struct i3c_master_controller *m)
 		return -EINVAL;
 
 	pres = DIV_ROUND_UP(sysclk_rate, (bus->scl_rate.i3c * 4)) - 1;
-	if (pres > PRESCL_CTRL0_MAX)
+	if (pres > PRESCL_CTRL0_I3C_MAX)
 		return -ERANGE;
 
 	bus->scl_rate.i3c = sysclk_rate / ((pres + 1) * 4);
@@ -1246,7 +1247,7 @@ static int cdns_i3c_master_bus_init(struct i3c_master_controller *m)
 	max_i2cfreq = bus->scl_rate.i2c;
 
 	pres = (sysclk_rate / (max_i2cfreq * 5)) - 1;
-	if (pres > PRESCL_CTRL0_MAX)
+	if (pres > PRESCL_CTRL0_I2C_MAX)
 		return -ERANGE;
 
 	bus->scl_rate.i2c = sysclk_rate / ((pres + 1) * 5);
-- 
GitLab


From 9f67c1e63976d3403f0b250b03ffe959c890f9db Mon Sep 17 00:00:00 2001
From: Esteban Blanc <eblanc@baylibre.com>
Date: Tue, 7 Nov 2023 10:47:01 +0100
Subject: [PATCH 2335/4076] rtc: tps6594: Add driver for TPS6594 RTC

TPS6594 PMIC is a MFD. This patch adds support for
the RTC found inside TPS6594 family of PMIC.

Alarm is also supported.

Signed-off-by: Esteban Blanc <eblanc@baylibre.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Tested-by: Thomas Richard <thomas.richard@bootlin.com>
Link: https://lore.kernel.org/r/20231107094701.2223486-1-eblanc@baylibre.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/Kconfig       |  12 +
 drivers/rtc/Makefile      |   1 +
 drivers/rtc/rtc-tps6594.c | 454 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 467 insertions(+)
 create mode 100644 drivers/rtc/rtc-tps6594.c

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 4e3c2fde2d6a6..68a530ef10669 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -578,6 +578,18 @@ config RTC_DRV_TPS6586X
 	  along with alarm. This driver supports the RTC driver for
 	  the TPS6586X RTC module.
 
+config RTC_DRV_TPS6594
+	tristate "TI TPS6594 RTC driver"
+	depends on MFD_TPS6594
+	default MFD_TPS6594
+	help
+	  TI Power Management IC TPS6594 supports RTC functionality
+	  along with alarm. This driver supports the RTC driver for
+	  the TPS6594 RTC module.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-tps6594.
+
 config RTC_DRV_TPS65910
 	tristate "TI TPS65910 RTC driver"
 	depends on MFD_TPS65910
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 6817ea4e44687..31c4606fd9bf0 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -177,6 +177,7 @@ obj-$(CONFIG_RTC_DRV_TEGRA)	+= rtc-tegra.o
 obj-$(CONFIG_RTC_DRV_TEST)	+= rtc-test.o
 obj-$(CONFIG_RTC_DRV_TI_K3)	+= rtc-ti-k3.o
 obj-$(CONFIG_RTC_DRV_TPS6586X)	+= rtc-tps6586x.o
+obj-$(CONFIG_RTC_DRV_TPS6594)	+= rtc-tps6594.o
 obj-$(CONFIG_RTC_DRV_TPS65910)	+= rtc-tps65910.o
 obj-$(CONFIG_RTC_DRV_TWL4030)	+= rtc-twl.o
 obj-$(CONFIG_RTC_DRV_VT8500)	+= rtc-vt8500.o
diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c
new file mode 100644
index 0000000000000..838ae8562a351
--- /dev/null
+++ b/drivers/rtc/rtc-tps6594.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RTC driver for tps6594 PMIC
+ *
+ * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/
+ */
+
+#include <linux/bcd.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/math64.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mod_devicetable.h>
+#include <linux/property.h>
+#include <linux/rtc.h>
+#include <linux/types.h>
+#include <linux/units.h>
+
+#include <linux/mfd/tps6594.h>
+
+// Total number of RTC registers needed to set time
+#define NUM_TIME_REGS (TPS6594_REG_RTC_WEEKS - TPS6594_REG_RTC_SECONDS + 1)
+
+// Total number of RTC alarm registers
+#define NUM_TIME_ALARM_REGS (NUM_TIME_REGS - 1)
+
+/*
+ * Min and max values supported by 'offset' interface (swapped sign).
+ * After conversion, the values do not exceed the range [-32767, 33767]
+ * which COMP_REG must conform to.
+ */
+#define MIN_OFFSET (-277774)
+#define MAX_OFFSET (277774)
+
+// Number of ticks per hour
+#define TICKS_PER_HOUR (32768 * 3600)
+
+// Multiplier for ppb conversions
+#define PPB_MULT NANO
+
+static int tps6594_rtc_alarm_irq_enable(struct device *dev,
+					unsigned int enabled)
+{
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	u8 val;
+
+	val = enabled ? TPS6594_BIT_IT_ALARM : 0;
+
+	return regmap_update_bits(tps->regmap, TPS6594_REG_RTC_INTERRUPTS,
+				  TPS6594_BIT_IT_ALARM, val);
+}
+
+/* Pulse GET_TIME field of RTC_CTRL_1 to store a timestamp in shadow registers. */
+static int tps6594_rtc_shadow_timestamp(struct device *dev, struct tps6594 *tps)
+{
+	int ret;
+
+	/*
+	 * Set GET_TIME to 0. Next time we set GET_TIME to 1 we will be sure to store
+	 * an up-to-date timestamp.
+	 */
+	ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+				TPS6594_BIT_GET_TIME);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Copy content of RTC registers to shadow registers or latches to read
+	 * a coherent timestamp.
+	 */
+	return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+			       TPS6594_BIT_GET_TIME);
+}
+
+static int tps6594_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	unsigned char rtc_data[NUM_TIME_REGS];
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	int ret;
+
+	// Check if RTC is running.
+	ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS,
+			       TPS6594_BIT_RUN);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		return -EINVAL;
+
+	ret = tps6594_rtc_shadow_timestamp(dev, tps);
+	if (ret < 0)
+		return ret;
+
+	// Read shadowed RTC registers.
+	ret = regmap_bulk_read(tps->regmap, TPS6594_REG_RTC_SECONDS, rtc_data,
+			       NUM_TIME_REGS);
+	if (ret < 0)
+		return ret;
+
+	tm->tm_sec = bcd2bin(rtc_data[0]);
+	tm->tm_min = bcd2bin(rtc_data[1]);
+	tm->tm_hour = bcd2bin(rtc_data[2]);
+	tm->tm_mday = bcd2bin(rtc_data[3]);
+	tm->tm_mon = bcd2bin(rtc_data[4]) - 1;
+	tm->tm_year = bcd2bin(rtc_data[5]) + 100;
+	tm->tm_wday = bcd2bin(rtc_data[6]);
+
+	return 0;
+}
+
+static int tps6594_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	unsigned char rtc_data[NUM_TIME_REGS];
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	int ret;
+
+	rtc_data[0] = bin2bcd(tm->tm_sec);
+	rtc_data[1] = bin2bcd(tm->tm_min);
+	rtc_data[2] = bin2bcd(tm->tm_hour);
+	rtc_data[3] = bin2bcd(tm->tm_mday);
+	rtc_data[4] = bin2bcd(tm->tm_mon + 1);
+	rtc_data[5] = bin2bcd(tm->tm_year - 100);
+	rtc_data[6] = bin2bcd(tm->tm_wday);
+
+	// Stop RTC while updating the RTC time registers.
+	ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+				TPS6594_BIT_STOP_RTC);
+	if (ret < 0)
+		return ret;
+
+	// Update all the time registers in one shot.
+	ret = regmap_bulk_write(tps->regmap, TPS6594_REG_RTC_SECONDS, rtc_data,
+				NUM_TIME_REGS);
+	if (ret < 0)
+		return ret;
+
+	// Start back RTC.
+	return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+			       TPS6594_BIT_STOP_RTC);
+}
+
+static int tps6594_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
+{
+	unsigned char alarm_data[NUM_TIME_ALARM_REGS];
+	u32 int_val;
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	int ret;
+
+	ret = regmap_bulk_read(tps->regmap, TPS6594_REG_ALARM_SECONDS,
+			       alarm_data, NUM_TIME_ALARM_REGS);
+	if (ret < 0)
+		return ret;
+
+	alm->time.tm_sec = bcd2bin(alarm_data[0]);
+	alm->time.tm_min = bcd2bin(alarm_data[1]);
+	alm->time.tm_hour = bcd2bin(alarm_data[2]);
+	alm->time.tm_mday = bcd2bin(alarm_data[3]);
+	alm->time.tm_mon = bcd2bin(alarm_data[4]) - 1;
+	alm->time.tm_year = bcd2bin(alarm_data[5]) + 100;
+
+	ret = regmap_read(tps->regmap, TPS6594_REG_RTC_INTERRUPTS, &int_val);
+	if (ret < 0)
+		return ret;
+
+	alm->enabled = int_val & TPS6594_BIT_IT_ALARM;
+
+	return 0;
+}
+
+static int tps6594_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
+{
+	unsigned char alarm_data[NUM_TIME_ALARM_REGS];
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	int ret;
+
+	// Disable alarm irq before changing the alarm timestamp.
+	ret = tps6594_rtc_alarm_irq_enable(dev, 0);
+	if (ret)
+		return ret;
+
+	alarm_data[0] = bin2bcd(alm->time.tm_sec);
+	alarm_data[1] = bin2bcd(alm->time.tm_min);
+	alarm_data[2] = bin2bcd(alm->time.tm_hour);
+	alarm_data[3] = bin2bcd(alm->time.tm_mday);
+	alarm_data[4] = bin2bcd(alm->time.tm_mon + 1);
+	alarm_data[5] = bin2bcd(alm->time.tm_year - 100);
+
+	// Update all the alarm registers in one shot.
+	ret = regmap_bulk_write(tps->regmap, TPS6594_REG_ALARM_SECONDS,
+				alarm_data, NUM_TIME_ALARM_REGS);
+	if (ret < 0)
+		return ret;
+
+	if (alm->enabled)
+		ret = tps6594_rtc_alarm_irq_enable(dev, 1);
+
+	return ret;
+}
+
+static int tps6594_rtc_set_calibration(struct device *dev, int calibration)
+{
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	__le16 value;
+	int ret;
+
+	/*
+	 * TPS6594 uses two's complement 16 bit value for compensation of RTC
+	 * crystal inaccuracies. One time every hour when seconds counter
+	 * increments from 0 to 1 compensation value will be added to internal
+	 * RTC counter value.
+	 *
+	 * Valid range for compensation value: [-32767 .. 32767].
+	 */
+	if (calibration < S16_MIN + 1 || calibration > S16_MAX)
+		return -ERANGE;
+
+	value = cpu_to_le16(calibration);
+
+	// Update all the compensation registers in one shot.
+	ret = regmap_bulk_write(tps->regmap, TPS6594_REG_RTC_COMP_LSB, &value,
+				sizeof(value));
+	if (ret < 0)
+		return ret;
+
+	// Enable automatic compensation.
+	return regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+			       TPS6594_BIT_AUTO_COMP);
+}
+
+static int tps6594_rtc_get_calibration(struct device *dev, int *calibration)
+{
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	unsigned int ctrl;
+	__le16 value;
+	int ret;
+
+	ret = regmap_read(tps->regmap, TPS6594_REG_RTC_CTRL_1, &ctrl);
+	if (ret < 0)
+		return ret;
+
+	// If automatic compensation is not enabled report back zero.
+	if (!(ctrl & TPS6594_BIT_AUTO_COMP)) {
+		*calibration = 0;
+		return 0;
+	}
+
+	ret = regmap_bulk_read(tps->regmap, TPS6594_REG_RTC_COMP_LSB, &value,
+			       sizeof(value));
+	if (ret < 0)
+		return ret;
+
+	*calibration = le16_to_cpu(value);
+
+	return 0;
+}
+
+static int tps6594_rtc_read_offset(struct device *dev, long *offset)
+{
+	int calibration;
+	s64 tmp;
+	int ret;
+
+	ret = tps6594_rtc_get_calibration(dev, &calibration);
+	if (ret < 0)
+		return ret;
+
+	// Convert from RTC calibration register format to ppb format.
+	tmp = calibration * PPB_MULT;
+
+	if (tmp < 0)
+		tmp -= TICKS_PER_HOUR / 2LL;
+	else
+		tmp += TICKS_PER_HOUR / 2LL;
+	tmp = div_s64(tmp, TICKS_PER_HOUR);
+
+	/*
+	 * SAFETY:
+	 * Computatiion is the reverse operation of the one done in
+	 * `tps6594_rtc_set_offset`. The safety remarks applie here too.
+	 */
+
+	/*
+	 * Offset value operates in negative way, so swap sign.
+	 * See 8.3.10.5, (32768 - COMP_REG).
+	 */
+	*offset = (long)-tmp;
+
+	return 0;
+}
+
+static int tps6594_rtc_set_offset(struct device *dev, long offset)
+{
+	int calibration;
+	s64 tmp;
+
+	// Make sure offset value is within supported range.
+	if (offset < MIN_OFFSET || offset > MAX_OFFSET)
+		return -ERANGE;
+
+	// Convert from ppb format to RTC calibration register format.
+
+	tmp = offset * TICKS_PER_HOUR;
+	if (tmp < 0)
+		tmp -= PPB_MULT / 2LL;
+	else
+		tmp += PPB_MULT / 2LL;
+	tmp = div_s64(tmp, PPB_MULT);
+
+	/*
+	 * SAFETY:
+	 * - tmp = offset * TICK_PER_HOUR :
+	 *	`offset` can't be more than 277774, so `tmp` can't exceed 277774000000000
+	 *	which is lower than the maximum value in an `s64` (2^63-1). No overflow here.
+	 *
+	 * - tmp += TICK_PER_HOUR / 2LL :
+	 *	tmp will have a maximum value of 277774117964800 which is still inferior to 2^63-1.
+	 */
+
+	// Offset value operates in negative way, so swap sign.
+	calibration = (int)-tmp;
+
+	return tps6594_rtc_set_calibration(dev, calibration);
+}
+
+static irqreturn_t tps6594_rtc_interrupt(int irq, void *rtc)
+{
+	struct device *dev = rtc;
+	struct tps6594 *tps = dev_get_drvdata(dev->parent);
+	struct rtc_device *rtc_dev = dev_get_drvdata(dev);
+	int ret;
+	u32 rtc_reg;
+
+	ret = regmap_read(tps->regmap, TPS6594_REG_RTC_STATUS, &rtc_reg);
+	if (ret)
+		return IRQ_NONE;
+
+	rtc_update_irq(rtc_dev, 1, RTC_IRQF | RTC_AF);
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops tps6594_rtc_ops = {
+	.read_time = tps6594_rtc_read_time,
+	.set_time = tps6594_rtc_set_time,
+	.read_alarm = tps6594_rtc_read_alarm,
+	.set_alarm = tps6594_rtc_set_alarm,
+	.alarm_irq_enable = tps6594_rtc_alarm_irq_enable,
+	.read_offset = tps6594_rtc_read_offset,
+	.set_offset = tps6594_rtc_set_offset,
+};
+
+static int tps6594_rtc_probe(struct platform_device *pdev)
+{
+	struct tps6594 *tps = dev_get_drvdata(pdev->dev.parent);
+	struct device *dev = &pdev->dev;
+	struct rtc_device *rtc;
+	int irq;
+	int ret;
+
+	rtc = devm_kzalloc(dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
+
+	rtc = devm_rtc_allocate_device(dev);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	// Enable crystal oscillator.
+	ret = regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_2,
+			      TPS6594_BIT_XTAL_EN);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS,
+			       TPS6594_BIT_RUN);
+	if (ret < 0)
+		return ret;
+	// RTC not running.
+	if (ret == 0) {
+		ret = regmap_set_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+				      TPS6594_BIT_STOP_RTC);
+		if (ret < 0)
+			return ret;
+
+		/*
+		 * On some boards, a 40 ms delay is needed before BIT_RUN is set.
+		 * 80 ms should provide sufficient margin.
+		 */
+		mdelay(80);
+
+		/*
+		 * RTC should be running now. Check if this is the case.
+		 * If not it might be a missing oscillator.
+		 */
+		ret = regmap_test_bits(tps->regmap, TPS6594_REG_RTC_STATUS,
+				       TPS6594_BIT_RUN);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			return -ENODEV;
+
+		// Stop RTC until first call to `tps6594_rtc_set_time`.
+		ret = regmap_clear_bits(tps->regmap, TPS6594_REG_RTC_CTRL_1,
+					TPS6594_BIT_STOP_RTC);
+		if (ret < 0)
+			return ret;
+	}
+
+	platform_set_drvdata(pdev, rtc);
+
+	irq = platform_get_irq_byname(pdev, TPS6594_IRQ_NAME_ALARM);
+	if (irq < 0)
+		return dev_err_probe(dev, irq, "Failed to get irq\n");
+
+	ret = devm_request_threaded_irq(dev, irq, NULL, tps6594_rtc_interrupt,
+					IRQF_ONESHOT, TPS6594_IRQ_NAME_ALARM,
+					dev);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+				     "Failed to request_threaded_irq\n");
+
+	ret = device_init_wakeup(dev, true);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+				     "Failed to init rtc as wakeup source\n");
+
+	rtc->ops = &tps6594_rtc_ops;
+	rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	rtc->range_max = RTC_TIMESTAMP_END_2099;
+
+	return devm_rtc_register_device(rtc);
+}
+
+static const struct platform_device_id tps6594_rtc_id_table[] = {
+	{ "tps6594-rtc", },
+	{}
+};
+MODULE_DEVICE_TABLE(platform, tps6594_rtc_id_table);
+
+static struct platform_driver tps6594_rtc_driver = {
+	.probe		= tps6594_rtc_probe,
+	.driver		= {
+		.name	= "tps6594-rtc",
+	},
+	.id_table = tps6594_rtc_id_table,
+};
+
+module_platform_driver(tps6594_rtc_driver);
+MODULE_AUTHOR("Esteban Blanc <eblanc@baylibre.com>");
+MODULE_DESCRIPTION("TPS6594 RTC driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From cd0d7d6639de4468d181c87e45cfd07d51b525da Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Tue, 14 Nov 2023 13:45:31 +0200
Subject: [PATCH 2336/4076] rtc: lpc24xx: add missing dependency

The driver depends on COMMON_CLK. Add the dependency in Kconfig.

Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Link: https://lore.kernel.org/r/20231114114532.37840-1-antoniu.miclaus@analog.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 68a530ef10669..1ea9c76001505 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1717,6 +1717,7 @@ config RTC_DRV_LPC24XX
 	tristate "NXP RTC for LPC178x/18xx/408x/43xx"
 	depends on ARCH_LPC18XX || COMPILE_TEST
 	depends on OF && HAS_IOMEM
+	depends on COMMON_CLK
 	help
 	  This enables support for the NXP RTC found which can be found on
 	  NXP LPC178x/18xx/408x/43xx devices.
-- 
GitLab


From 3628d999e31e2e31b51f78b0f68e91275854c179 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sat, 18 Nov 2023 18:22:00 +0900
Subject: [PATCH 2337/4076] rtc: ds3232: avoid unused-const-variable warning

Fix the following warning when CONFIG_I2C is not set but CONFIG_SPI_MASTER
is set.

warning: 'ds3232_pm_ops' defined but not used [-Wunused-const-variable=]

'ds3232_pm_ops' is only used by rtc-ds3232 i2c driver, so move the device
PM callbacks inside #if IS_ENABLED(CONFIG_I2C).

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311172325.33tTniaJ-lkp@intel.com/
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Link: https://lore.kernel.org/r/20231118092200.829808-1-akinobu.mita@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-ds3232.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index 89d7b085f7219..1485a6ae51e61 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -536,6 +536,8 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_I2C)
+
 #ifdef CONFIG_PM_SLEEP
 static int ds3232_suspend(struct device *dev)
 {
@@ -564,8 +566,6 @@ static const struct dev_pm_ops ds3232_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(ds3232_suspend, ds3232_resume)
 };
 
-#if IS_ENABLED(CONFIG_I2C)
-
 static int ds3232_i2c_probe(struct i2c_client *client)
 {
 	struct regmap *regmap;
-- 
GitLab


From 2f80de657f83a1f6495e557096847f4626d57164 Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <eichest@gmail.com>
Date: Wed, 22 Nov 2023 19:16:11 +0100
Subject: [PATCH 2338/4076] rtc: rv8803: Add power management support

Add power management support to the driver. This allows a SoC to wake
from suspend using the nINT provided by the RTC. Only register it as a
wakeup device if the interrupt is provided and handled.

Signed-off-by: Stefan Eichenberger <eichest@gmail.com>
Link: https://lore.kernel.org/r/20231122181611.164792-1-eichest@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-rv8803.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 1a3ec1bb5b814..11e6b0d31f5d7 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/rtc.h>
+#include <linux/pm_wakeirq.h>
 
 #define RV8803_I2C_TRY_COUNT		4
 
@@ -607,6 +608,28 @@ static int rv8803_regs_configure(struct rv8803_data *rv8803)
 	return 0;
 }
 
+static int rv8803_resume(struct device *dev)
+{
+	struct rv8803_data *rv8803 = dev_get_drvdata(dev);
+
+	if (rv8803->client->irq > 0 && device_may_wakeup(dev))
+		disable_irq_wake(rv8803->client->irq);
+
+	return 0;
+}
+
+static int rv8803_suspend(struct device *dev)
+{
+	struct rv8803_data *rv8803 = dev_get_drvdata(dev);
+
+	if (rv8803->client->irq > 0 && device_may_wakeup(dev))
+		enable_irq_wake(rv8803->client->irq);
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(rv8803_pm_ops, rv8803_suspend, rv8803_resume);
+
 static const struct i2c_device_id rv8803_id[] = {
 	{ "rv8803", rv_8803 },
 	{ "rv8804", rx_8804 },
@@ -683,6 +706,11 @@ static int rv8803_probe(struct i2c_client *client)
 		if (err) {
 			dev_warn(&client->dev, "unable to request IRQ, alarms disabled\n");
 			client->irq = 0;
+		} else {
+			device_init_wakeup(&client->dev, true);
+			err = dev_pm_set_wake_irq(&client->dev, client->irq);
+			if (err)
+				dev_err(&client->dev, "failed to set wake IRQ\n");
 		}
 	}
 	if (!client->irq)
@@ -737,6 +765,7 @@ static struct i2c_driver rv8803_driver = {
 	.driver = {
 		.name = "rtc-rv8803",
 		.of_match_table = of_match_ptr(rv8803_of_match),
+		.pm = &rv8803_pm_ops,
 	},
 	.probe		= rv8803_probe,
 	.id_table	= rv8803_id,
-- 
GitLab


From 33f4ac16540509af518580abe730d409e8098aca Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Thu, 30 Nov 2023 18:32:23 +0100
Subject: [PATCH 2339/4076] dt-bindings: rtc: qcom-pm8xxx: fix inconsistent
 example

The PM8921 is an SSBI PMIC but in the binding example it is described
as being part of an SPMI PMIC while using an SSBI address.

Make the example consistent by using the sibling PM8941 SPMI PMIC
instead.

Fixes: 8138c5f0318c ("dt-bindings: rtc: qcom-pm8xxx-rtc: Add qcom pm8xxx rtc bindings")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231130173223.12794-1-johan+linaro@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../bindings/rtc/qcom-pm8xxx-rtc.yaml         | 36 +++++++++----------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
index b95a69cc9ae0f..d274bb7a534b5 100644
--- a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
@@ -61,27 +61,27 @@ additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/interrupt-controller/irq.h>
     #include <dt-bindings/spmi/spmi.h>
-    spmi_bus: spmi@c440000 {
-      reg = <0x0c440000 0x1100>;
-      #address-cells = <2>;
-      #size-cells = <0>;
-      pmicintc: pmic@0 {
-        reg = <0x0 SPMI_USID>;
-        compatible = "qcom,pm8921";
-        interrupts = <104 8>;
-        #interrupt-cells = <2>;
-        interrupt-controller;
-        #address-cells = <1>;
+
+    spmi {
+        #address-cells = <2>;
         #size-cells = <0>;
 
-        pm8921_rtc: rtc@11d {
-          compatible = "qcom,pm8921-rtc";
-          reg = <0x11d>;
-          interrupts = <0x27 0>;
-          nvmem-cells = <&rtc_offset>;
-          nvmem-cell-names = "offset";
+        pmic@0 {
+            compatible = "qcom,pm8941", "qcom,spmi-pmic";
+            reg = <0x0 SPMI_USID>;
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            rtc@6000 {
+                compatible = "qcom,pm8941-rtc";
+                reg = <0x6000>, <0x6100>;
+                reg-names = "rtc", "alarm";
+                interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>;
+                nvmem-cells = <&rtc_offset>;
+                nvmem-cell-names = "offset";
+            };
         };
-      };
     };
 ...
-- 
GitLab


From e9a2162495ce387647bae565483f978369a29839 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Sun, 17 Dec 2023 23:58:31 +0100
Subject: [PATCH 2340/4076] rtc: ma35d1: remove hardcoded UIE support

Let the core handle UIE instead of enabling it forcefully at probe which
means the RTC will generate an interrupt every second even when nobody
cares.

Link: https://lore.kernel.org/r/20231217225831.48581-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-ma35d1.c | 20 --------------------
 1 file changed, 20 deletions(-)

diff --git a/drivers/rtc/rtc-ma35d1.c b/drivers/rtc/rtc-ma35d1.c
index 07c9a083a9d5d..cfcfc28060f62 100644
--- a/drivers/rtc/rtc-ma35d1.c
+++ b/drivers/rtc/rtc-ma35d1.c
@@ -79,11 +79,6 @@ static irqreturn_t ma35d1_rtc_interrupt(int irq, void *data)
 		events |= RTC_AF | RTC_IRQF;
 	}
 
-	if (rtc_irq & RTC_INTSTS_UIF) {
-		rtc_reg_write(rtc, MA35_REG_RTC_INTSTS, RTC_INTSTS_UIF);
-		events |= RTC_UF | RTC_IRQF;
-	}
-
 	rtc_update_irq(rtc->rtcdev, 1, events);
 
 	return IRQ_HANDLED;
@@ -216,7 +211,6 @@ static int ma35d1_rtc_probe(struct platform_device *pdev)
 {
 	struct ma35_rtc *rtc;
 	struct clk *clk;
-	u32 regval;
 	int ret;
 
 	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
@@ -264,40 +258,26 @@ static int ma35d1_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret, "Failed to register rtc device\n");
 
-	regval = rtc_reg_read(rtc, MA35_REG_RTC_INTEN);
-	regval |= RTC_INTEN_UIEN;
-	rtc_reg_write(rtc, MA35_REG_RTC_INTEN, regval);
-
 	return 0;
 }
 
 static int ma35d1_rtc_suspend(struct platform_device *pdev, pm_message_t state)
 {
 	struct ma35_rtc *rtc = platform_get_drvdata(pdev);
-	u32 regval;
 
 	if (device_may_wakeup(&pdev->dev))
 		enable_irq_wake(rtc->irq_num);
 
-	regval = rtc_reg_read(rtc, MA35_REG_RTC_INTEN);
-	regval &= ~RTC_INTEN_UIEN;
-	rtc_reg_write(rtc, MA35_REG_RTC_INTEN, regval);
-
 	return 0;
 }
 
 static int ma35d1_rtc_resume(struct platform_device *pdev)
 {
 	struct ma35_rtc *rtc = platform_get_drvdata(pdev);
-	u32 regval;
 
 	if (device_may_wakeup(&pdev->dev))
 		disable_irq_wake(rtc->irq_num);
 
-	regval = rtc_reg_read(rtc, MA35_REG_RTC_INTEN);
-	regval |= RTC_INTEN_UIEN;
-	rtc_reg_write(rtc, MA35_REG_RTC_INTEN, regval);
-
 	return 0;
 }
 
-- 
GitLab


From 54e1898e113dc65974103620bbe7a9f856f80f6e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 11 Dec 2023 14:26:00 +0100
Subject: [PATCH 2341/4076] rtc: MAINTAINERS: drop Alessandro Zummo
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Last email from Alessandro was in 2016, so remove him from maintainers
of the RTC subsystem.  Stale maintainer entries hide information whether
subsystem needs help, has a bus-factor or is even orphaned.

Link: https://lore.kernel.org/all/?q=f%3A%22Alessandro+Zummo%22
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231211132600.101090-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cfd..2635f7b59e3ca 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18286,7 +18286,6 @@ X:	include/linux/srcu*.h
 X:	kernel/rcu/srcu*.c
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
-M:	Alessandro Zummo <a.zummo@towertech.it>
 M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
 L:	linux-rtc@vger.kernel.org
 S:	Maintained
-- 
GitLab


From e3d3fe7e7bf08820a83c9d9a4c38c7b29a2927f1 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 19 Dec 2023 06:07:12 +0100
Subject: [PATCH 2342/4076] rtc: class: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/4f2c049cb09d46fed336e22445c71988b4f340d6.1702962419.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/class.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index edfd942f8c549..921ee18279743 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -256,7 +256,7 @@ static int rtc_device_get_id(struct device *dev)
 		of_id = of_alias_get_id(dev->parent->of_node, "rtc");
 
 	if (of_id >= 0) {
-		id = ida_simple_get(&rtc_ida, of_id, of_id + 1, GFP_KERNEL);
+		id = ida_alloc_range(&rtc_ida, of_id, of_id, GFP_KERNEL);
 		if (id < 0)
 			dev_warn(dev, "/aliases ID %d not available\n", of_id);
 	}
-- 
GitLab


From c7ec4f2d684e17d69bbdd7c4324db0ef5daac26a Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Mon, 8 Jan 2024 07:41:39 +0100
Subject: [PATCH 2343/4076] xen-netback: don't produce zero-size SKB frags

While frontends may submit zero-size requests (wasting a precious slot),
core networking code as of at least 3ece782693c4b ("sock: skb_copy_ubufs
support for compound pages") can't deal with SKBs when they have all
zero-size fragments. Respond to empty requests right when populating
fragments; all further processing is fragment based and hence won't
encounter these empty requests anymore.

In a way this should have been that way from the beginning: When no data
is to be transferred for a particular request, there's not even a point
in validating the respective grant ref. That's no different from e.g.
passing NULL into memcpy() when at the same time the size is 0.

This is XSA-448 / CVE-2023-46838.

Cc: stable@vger.kernel.org
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>
---
 drivers/net/xen-netback/netback.c | 44 ++++++++++++++++++++++++++-----
 1 file changed, 38 insertions(+), 6 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 88f760a7cbc35..d7503aef599f0 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -463,12 +463,25 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 	}
 
 	for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS;
-	     shinfo->nr_frags++, gop++, nr_slots--) {
+	     nr_slots--) {
+		if (unlikely(!txp->size)) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&queue->response_lock, flags);
+			make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY);
+			push_tx_responses(queue);
+			spin_unlock_irqrestore(&queue->response_lock, flags);
+			++txp;
+			continue;
+		}
+
 		index = pending_index(queue->pending_cons++);
 		pending_idx = queue->pending_ring[index];
 		xenvif_tx_create_map_op(queue, pending_idx, txp,
 				        txp == first ? extra_count : 0, gop);
 		frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
+		++shinfo->nr_frags;
+		++gop;
 
 		if (txp == first)
 			txp = txfrags;
@@ -481,20 +494,39 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 		shinfo = skb_shinfo(nskb);
 		frags = shinfo->frags;
 
-		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots;
-		     shinfo->nr_frags++, txp++, gop++) {
+		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) {
+			if (unlikely(!txp->size)) {
+				unsigned long flags;
+
+				spin_lock_irqsave(&queue->response_lock, flags);
+				make_tx_response(queue, txp, 0,
+						 XEN_NETIF_RSP_OKAY);
+				push_tx_responses(queue);
+				spin_unlock_irqrestore(&queue->response_lock,
+						       flags);
+				continue;
+			}
+
 			index = pending_index(queue->pending_cons++);
 			pending_idx = queue->pending_ring[index];
 			xenvif_tx_create_map_op(queue, pending_idx, txp, 0,
 						gop);
 			frag_set_pending_idx(&frags[shinfo->nr_frags],
 					     pending_idx);
+			++shinfo->nr_frags;
+			++gop;
 		}
 
-		skb_shinfo(skb)->frag_list = nskb;
-	} else if (nskb) {
+		if (shinfo->nr_frags) {
+			skb_shinfo(skb)->frag_list = nskb;
+			nskb = NULL;
+		}
+	}
+
+	if (nskb) {
 		/* A frag_list skb was allocated but it is no longer needed
-		 * because enough slots were converted to copy ops above.
+		 * because enough slots were converted to copy ops above or some
+		 * were empty.
 		 */
 		kfree_skb(nskb);
 	}
-- 
GitLab


From 2f9060b1db4aa2c21c248e34476d8936a2b69cf6 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 3 Jan 2024 17:16:03 -0600
Subject: [PATCH 2344/4076] MIPS: Fix typos

Fix typos, most reported by "codespell arch/mips".  Only touches comments,
no code changes.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: linux-mips@vger.kernel.org
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/bcm47xx/buttons.c                            | 6 +++---
 arch/mips/bcm63xx/clk.c                                | 4 ++--
 arch/mips/boot/compressed/dbg.c                        | 2 +-
 arch/mips/boot/elf2ecoff.c                             | 2 +-
 arch/mips/cavium-octeon/csrc-octeon.c                  | 2 +-
 arch/mips/cavium-octeon/executive/cvmx-boot-vector.c   | 2 +-
 arch/mips/cavium-octeon/executive/cvmx-bootmem.c       | 2 +-
 arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c     | 4 ++--
 arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c   | 2 +-
 arch/mips/cavium-octeon/executive/cvmx-pko.c           | 2 +-
 arch/mips/cavium-octeon/octeon-platform.c              | 2 +-
 arch/mips/fw/arc/promlib.c                             | 6 +++---
 arch/mips/include/asm/debug.h                          | 2 +-
 arch/mips/include/asm/io.h                             | 4 ++--
 arch/mips/include/asm/mach-au1x00/au1000_dma.h         | 2 +-
 arch/mips/include/asm/mach-au1x00/gpio-au1000.h        | 2 +-
 arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h  | 2 +-
 arch/mips/include/asm/mach-loongson64/loongson_hwmon.h | 2 +-
 arch/mips/include/asm/mach-loongson64/loongson_regs.h  | 2 +-
 arch/mips/include/asm/mach-malta/spaces.h              | 4 ++--
 arch/mips/include/asm/mips-boards/bonito64.h           | 2 +-
 arch/mips/include/asm/mips-cpc.h                       | 2 +-
 arch/mips/include/asm/mipsregs.h                       | 4 ++--
 arch/mips/include/asm/octeon/cvmx-bootinfo.h           | 2 +-
 arch/mips/include/asm/octeon/cvmx-cmd-queue.h          | 6 +++---
 arch/mips/include/asm/octeon/cvmx-pko.h                | 2 +-
 arch/mips/include/asm/octeon/cvmx-pow.h                | 4 ++--
 arch/mips/include/asm/octeon/octeon-model.h            | 4 ++--
 arch/mips/include/asm/page.h                           | 2 +-
 arch/mips/include/asm/pci.h                            | 2 +-
 arch/mips/include/asm/pgtable-bits.h                   | 2 +-
 arch/mips/include/asm/sgi/mc.h                         | 2 +-
 arch/mips/include/asm/sn/klconfig.h                    | 2 +-
 arch/mips/include/asm/sync.h                           | 2 +-
 arch/mips/include/asm/thread_info.h                    | 2 +-
 arch/mips/include/asm/timex.h                          | 2 +-
 arch/mips/include/asm/vdso/vdso.h                      | 2 +-
 arch/mips/include/uapi/asm/mman.h                      | 2 +-
 arch/mips/include/uapi/asm/msgbuf.h                    | 2 +-
 arch/mips/kernel/cpu-probe.c                           | 2 +-
 arch/mips/kernel/kprobes.c                             | 2 +-
 arch/mips/kernel/relocate.c                            | 2 +-
 arch/mips/kernel/relocate_kernel.S                     | 2 +-
 arch/mips/kernel/setup.c                               | 2 +-
 arch/mips/kernel/signal.c                              | 2 +-
 arch/mips/kernel/traps.c                               | 2 +-
 arch/mips/kernel/vpe.c                                 | 4 ++--
 arch/mips/kvm/emulate.c                                | 2 +-
 arch/mips/loongson2ef/common/platform.c                | 2 +-
 arch/mips/loongson64/smp.c                             | 2 +-
 arch/mips/mm/c-r4k.c                                   | 2 +-
 arch/mips/mm/cex-gen.S                                 | 2 +-
 arch/mips/mm/tlb-r3k.c                                 | 2 +-
 arch/mips/mm/tlb-r4k.c                                 | 2 +-
 arch/mips/mm/tlbex.c                                   | 4 ++--
 arch/mips/net/bpf_jit_comp32.c                         | 2 +-
 arch/mips/pci/ops-loongson2.c                          | 2 +-
 arch/mips/pci/pci-alchemy.c                            | 2 +-
 arch/mips/pci/pci-ar2315.c                             | 2 +-
 arch/mips/pci/pci-lantiq.c                             | 2 +-
 arch/mips/pci/pci-octeon.c                             | 2 +-
 arch/mips/pci/pci-xtalk-bridge.c                       | 2 +-
 arch/mips/pci/pcie-octeon.c                            | 2 +-
 arch/mips/ralink/mt7621.c                              | 2 +-
 arch/mips/txx9/generic/pci.c                           | 2 +-
 65 files changed, 80 insertions(+), 80 deletions(-)

diff --git a/arch/mips/bcm47xx/buttons.c b/arch/mips/bcm47xx/buttons.c
index 437a737c01dd0..46994f9bb8219 100644
--- a/arch/mips/bcm47xx/buttons.c
+++ b/arch/mips/bcm47xx/buttons.c
@@ -147,21 +147,21 @@ static const struct gpio_keys_button
 bcm47xx_buttons_buffalo_whr_g125[] __initconst = {
 	BCM47XX_GPIO_KEY(0, KEY_WPS_BUTTON),
 	BCM47XX_GPIO_KEY(4, KEY_RESTART),
-	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode swtich */
+	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode switch */
 };
 
 static const struct gpio_keys_button
 bcm47xx_buttons_buffalo_whr_g54s[] __initconst = {
 	BCM47XX_GPIO_KEY(0, KEY_WPS_BUTTON),
 	BCM47XX_GPIO_KEY_H(4, KEY_RESTART),
-	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode swtich */
+	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode switch */
 };
 
 static const struct gpio_keys_button
 bcm47xx_buttons_buffalo_whr_hp_g54[] __initconst = {
 	BCM47XX_GPIO_KEY(0, KEY_WPS_BUTTON),
 	BCM47XX_GPIO_KEY(4, KEY_RESTART),
-	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode swtich */
+	BCM47XX_GPIO_KEY(5, BTN_0), /* Router / AP mode switch */
 };
 
 static const struct gpio_keys_button
diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c
index 86a6e25908664..3144965fb7dc4 100644
--- a/arch/mips/bcm63xx/clk.c
+++ b/arch/mips/bcm63xx/clk.c
@@ -174,7 +174,7 @@ static void enetsw_set(struct clk *clk, int enable)
 	}
 
 	if (enable) {
-		/* reset switch core afer clock change */
+		/* reset switch core after clock change */
 		bcm63xx_core_set_reset(BCM63XX_RESET_ENETSW, 1);
 		msleep(10);
 		bcm63xx_core_set_reset(BCM63XX_RESET_ENETSW, 0);
@@ -304,7 +304,7 @@ static void xtm_set(struct clk *clk, int enable)
 	bcm_hwclock_set(CKCTL_6368_SAR_EN, enable);
 
 	if (enable) {
-		/* reset sar core afer clock change */
+		/* reset sar core after clock change */
 		bcm63xx_core_set_reset(BCM63XX_RESET_SAR, 1);
 		mdelay(1);
 		bcm63xx_core_set_reset(BCM63XX_RESET_SAR, 0);
diff --git a/arch/mips/boot/compressed/dbg.c b/arch/mips/boot/compressed/dbg.c
index f6728a8fd1c3d..98dfb2e59dfee 100644
--- a/arch/mips/boot/compressed/dbg.c
+++ b/arch/mips/boot/compressed/dbg.c
@@ -3,7 +3,7 @@
  * MIPS-specific debug support for pre-boot environment
  *
  * NOTE: putc() is board specific, if your board have a 16550 compatible uart,
- * please select SYS_SUPPORTS_ZBOOT_UART16550 for your machine. othewise, you
+ * please select SYS_SUPPORTS_ZBOOT_UART16550 for your machine. otherwise, you
  * need to implement your own putc().
  */
 #include <linux/compiler.h>
diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c
index 6972b97235daf..549c5d6ef6d7c 100644
--- a/arch/mips/boot/elf2ecoff.c
+++ b/arch/mips/boot/elf2ecoff.c
@@ -443,7 +443,7 @@ int main(int argc, char *argv[])
 	efh.f_symptr = 0;
 	efh.f_nsyms = 0;
 	efh.f_opthdr = sizeof eah;
-	efh.f_flags = 0x100f;	/* Stripped, not sharable. */
+	efh.f_flags = 0x100f;	/* Stripped, not shareable. */
 
 	memset(esecs, 0, sizeof esecs);
 	strcpy(esecs[0].s_name, ".text");
diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c
index 124817609ce01..af62a210a40b9 100644
--- a/arch/mips/cavium-octeon/csrc-octeon.c
+++ b/arch/mips/cavium-octeon/csrc-octeon.c
@@ -113,7 +113,7 @@ static struct clocksource clocksource_mips = {
 
 unsigned long long notrace sched_clock(void)
 {
-	/* 64-bit arithmatic can overflow, so use 128-bit.  */
+	/* 64-bit arithmetic can overflow, so use 128-bit.  */
 	u64 t1, t2, t3;
 	unsigned long long rv;
 	u64 mult = clocksource_mips.mult;
diff --git a/arch/mips/cavium-octeon/executive/cvmx-boot-vector.c b/arch/mips/cavium-octeon/executive/cvmx-boot-vector.c
index b7019d21808e0..76446db66defd 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-boot-vector.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-boot-vector.c
@@ -143,7 +143,7 @@ static void cvmx_boot_vector_init(void *mem)
 		uint64_t v = _cvmx_bootvector_data[i];
 
 		if (OCTEON_IS_OCTEON1PLUS() && (i == 0 || i == 7))
-			v &= 0xffffffff00000000ull; /* KScratch not availble. */
+			v &= 0xffffffff00000000ull; /* KScratch not available */
 		cvmx_write_csr(CVMX_MIO_BOOT_LOC_ADR, i * 8);
 		cvmx_write_csr(CVMX_MIO_BOOT_LOC_DAT, v);
 	}
diff --git a/arch/mips/cavium-octeon/executive/cvmx-bootmem.c b/arch/mips/cavium-octeon/executive/cvmx-bootmem.c
index 334bf8e577e50..628ebdf4b9c55 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-bootmem.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-bootmem.c
@@ -264,7 +264,7 @@ int64_t cvmx_bootmem_phy_alloc(uint64_t req_size, uint64_t address_min,
 	 * Convert !0 address_min and 0 address_max to special case of
 	 * range that specifies an exact memory block to allocate.  Do
 	 * this before other checks and adjustments so that this
-	 * tranformation will be validated.
+	 * transformation will be validated.
 	 */
 	if (address_min && !address_max)
 		address_max = address_min + req_size;
diff --git a/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c b/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
index aa7bbf8d0df55..042a6bc44b5c2 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
@@ -192,7 +192,7 @@ cvmx_cmd_queue_result_t cvmx_cmd_queue_initialize(cvmx_cmd_queue_id_t queue_id,
 }
 
 /*
- * Shutdown a queue a free it's command buffers to the FPA. The
+ * Shutdown a queue and free its command buffers to the FPA. The
  * hardware connected to the queue must be stopped before this
  * function is called.
  *
@@ -285,7 +285,7 @@ int cvmx_cmd_queue_length(cvmx_cmd_queue_id_t queue_id)
 
 /*
  * Return the command buffer to be written to. The purpose of this
- * function is to allow CVMX routine access t othe low level buffer
+ * function is to allow CVMX routine access to the low level buffer
  * for initial hardware setup. User applications should not call this
  * function directly.
  *
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c b/arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c
index 607b4e6595797..1fceb7fd2c944 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-jtag.c
@@ -103,7 +103,7 @@ uint32_t cvmx_helper_qlm_jtag_shift(int qlm, int bits, uint32_t data)
 /**
  * Shift long sequences of zeros into the QLM JTAG chain. It is
  * common to need to shift more than 32 bits of zeros into the
- * chain. This function is a convience wrapper around
+ * chain. This function is a convenience wrapper around
  * cvmx_helper_qlm_jtag_shift() to shift more than 32 bits of
  * zeros at a time.
  *
diff --git a/arch/mips/cavium-octeon/executive/cvmx-pko.c b/arch/mips/cavium-octeon/executive/cvmx-pko.c
index 15faca494c807..6e70b859a0ac6 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-pko.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-pko.c
@@ -615,7 +615,7 @@ int cvmx_pko_rate_limit_bits(int port, uint64_t bits_s, int burst)
 	/*
 	 * Each packet has a 12 bytes of interframe gap, an 8 byte
 	 * preamble, and a 4 byte CRC. These are not included in the
-	 * per word count. Multiply by 8 to covert to bits and divide
+	 * per word count. Multiply by 8 to convert to bits and divide
 	 * by 256 for limit granularity.
 	 */
 	pko_mem_port_rate0.s.rate_pkt = (12 + 8 + 4) * 8 * tokens_per_bit / 256;
diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index f76783c24338b..5e1dd4e6e82fb 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -973,7 +973,7 @@ int __init octeon_prune_device_tree(void)
 			 * zero.
 			 */
 
-			/* Asume that CS1 immediately follows. */
+			/* Assume that CS1 immediately follows. */
 			mio_boot_reg_cfg.u64 =
 				cvmx_read_csr(CVMX_MIO_BOOT_REG_CFGX(cs + 1));
 			region1_base = mio_boot_reg_cfg.s.base << 16;
diff --git a/arch/mips/fw/arc/promlib.c b/arch/mips/fw/arc/promlib.c
index 5e9e840a93144..93e1e70393eeb 100644
--- a/arch/mips/fw/arc/promlib.c
+++ b/arch/mips/fw/arc/promlib.c
@@ -15,11 +15,11 @@
 /*
  * For 64bit kernels working with a 32bit ARC PROM pointer arguments
  * for ARC calls need to reside in CKEG0/1. But as soon as the kernel
- * switches to it's first kernel thread stack is set to an address in
+ * switches to its first kernel thread stack is set to an address in
  * XKPHYS, so anything on stack can't be used anymore. This is solved
- * by using a * static declartion variables are put into BSS, which is
+ * by using a * static declaration variables are put into BSS, which is
  * linked to a CKSEG0 address. Since this is only used on UP platforms
- * there is not spinlock needed
+ * there is no spinlock needed
  */
 #define O32_STATIC	static
 #else
diff --git a/arch/mips/include/asm/debug.h b/arch/mips/include/asm/debug.h
index c7013e1cb53fb..e70392429246e 100644
--- a/arch/mips/include/asm/debug.h
+++ b/arch/mips/include/asm/debug.h
@@ -10,7 +10,7 @@
 
 /*
  * mips_debugfs_dir corresponds to the "mips" directory at the top level
- * of the DebugFS hierarchy. MIPS-specific DebugFS entires should be
+ * of the DebugFS hierarchy. MIPS-specific DebugFS entries should be
  * placed beneath this directory.
  */
 extern struct dentry *mips_debugfs_dir;
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 062dd4e6b954e..bba327dc1226f 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -179,7 +179,7 @@ void iounmap(const volatile void __iomem *addr);
  * address is not guaranteed to be usable directly as a virtual
  * address.
  *
- * This version of ioremap ensures that the memory is marked cachable by
+ * This version of ioremap ensures that the memory is marked cacheable by
  * the CPU.  Also enables full write-combining.	 Useful for some
  * memory-like regions on I/O busses.
  */
@@ -197,7 +197,7 @@ void iounmap(const volatile void __iomem *addr);
  * address is not guaranteed to be usable directly as a virtual
  * address.
  *
- * This version of ioremap ensures that the memory is marked uncachable
+ * This version of ioremap ensures that the memory is marked uncacheable
  * but accelerated by means of write-combining feature. It is specifically
  * useful for PCIe prefetchable windows, which may vastly improve a
  * communications performance. If it was determined on boot stage, what
diff --git a/arch/mips/include/asm/mach-au1x00/au1000_dma.h b/arch/mips/include/asm/mach-au1x00/au1000_dma.h
index 0a0cd4270c6f2..b82e513c8523a 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000_dma.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000_dma.h
@@ -259,7 +259,7 @@ static inline void set_dma_mode(unsigned int dmanr, unsigned int mode)
 	if (!chan)
 		return;
 	/*
-	 * set_dma_mode is only allowed to change endianess, direction,
+	 * set_dma_mode is only allowed to change endianness, direction,
 	 * transfer size, device FIFO width, and coherency settings.
 	 * Make sure anything else is masked off.
 	 */
diff --git a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
index 82bc2766e2ec1..d820b481ac564 100644
--- a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
@@ -435,7 +435,7 @@ static inline void alchemy_gpio2_disable_int(int gpio2)
 /**
  * alchemy_gpio2_enable -  Activate GPIO2 block.
  *
- * The GPIO2 block must be enabled excplicitly to work.	 On systems
+ * The GPIO2 block must be enabled explicitly to work.	 On systems
  * where this isn't done by the bootloader, this macro can be used.
  */
 static inline void alchemy_gpio2_enable(void)
diff --git a/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
index 5855ba1bd1ecf..40eaa72e54d07 100644
--- a/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
+++ b/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h
@@ -55,7 +55,7 @@ extern __iomem void *ltq_sys1_membase;
 #define ltq_sys1_w32_mask(clear, set, reg)   \
 	ltq_sys1_w32((ltq_sys1_r32(reg) & ~(clear)) | (set), reg)
 
-/* allow the gpio and pinctrl drivers to talk to eachother */
+/* allow the gpio and pinctrl drivers to talk to each other */
 extern int pinctrl_falcon_get_range_size(int id);
 extern void pinctrl_falcon_add_gpio_range(struct pinctrl_gpio_range *range);
 
diff --git a/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h b/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
index 545f91f2ae16a..721eafc4644e5 100644
--- a/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
+++ b/arch/mips/include/asm/mach-loongson64/loongson_hwmon.h
@@ -42,7 +42,7 @@ struct loongson_fan_policy {
 	/* period between two check. (Unit: S) */
 	u8	adjust_period;
 
-	/* fan adjust usually depend on a temprature input */
+	/* fan adjust usually depend on a temperature input */
 	get_temp_fun	depend_temp;
 
 	/* up_step/down_step used when type is STEP_SPEED_POLICY */
diff --git a/arch/mips/include/asm/mach-loongson64/loongson_regs.h b/arch/mips/include/asm/mach-loongson64/loongson_regs.h
index b5be7511f6cde..fec7675076049 100644
--- a/arch/mips/include/asm/mach-loongson64/loongson_regs.h
+++ b/arch/mips/include/asm/mach-loongson64/loongson_regs.h
@@ -227,7 +227,7 @@ static inline void csr_writeq(u64 val, u32 reg)
 #define LOONGSON_CSR_NODECNT	0x408
 #define LOONGSON_CSR_CPUTEMP	0x428
 
-/* PerCore CSR, only accessable by local cores */
+/* PerCore CSR, only accessible by local cores */
 #define LOONGSON_CSR_IPI_STATUS	0x1000
 #define LOONGSON_CSR_IPI_EN	0x1004
 #define LOONGSON_CSR_IPI_SET	0x1008
diff --git a/arch/mips/include/asm/mach-malta/spaces.h b/arch/mips/include/asm/mach-malta/spaces.h
index d7e54971ec668..1ce4ba97852f7 100644
--- a/arch/mips/include/asm/mach-malta/spaces.h
+++ b/arch/mips/include/asm/mach-malta/spaces.h
@@ -23,13 +23,13 @@
  * The kernel is still located in 0x80000000(kseg0). However,
  * the physical mask has been shifted to 0x80000000 which exploits the alias
  * on the Malta board. As a result of which, we override the __pa_symbol
- * to peform direct mapping from virtual to physical addresses. In other
+ * to perform direct mapping from virtual to physical addresses. In other
  * words, the 0x80000000 virtual address maps to 0x80000000 physical address
  * which in turn aliases to 0x0. We do this in order to be able to use a flat
  * 2GB of memory (0x80000000 - 0xffffffff) so we can avoid the I/O hole in
  * 0x10000000 - 0x1fffffff.
  * The last 64KB of physical memory are reserved for correct HIGHMEM
- * macros arithmetics.
+ * macros arithmetic.
  *
  */
 
diff --git a/arch/mips/include/asm/mips-boards/bonito64.h b/arch/mips/include/asm/mips-boards/bonito64.h
index 5368891d424b7..31a31fe78d775 100644
--- a/arch/mips/include/asm/mips-boards/bonito64.h
+++ b/arch/mips/include/asm/mips-boards/bonito64.h
@@ -16,7 +16,7 @@
  */
 
 /* Revision 1.48 autogenerated on 08/17/99 15:20:01 */
-/* This bonito64 version editted from bonito.h Revision 1.48 on 11/09/00 */
+/* This bonito64 version edited from bonito.h Revision 1.48 on 11/09/00 */
 
 #ifndef _ASM_MIPS_BOARDS_BONITO64_H
 #define _ASM_MIPS_BOARDS_BONITO64_H
diff --git a/arch/mips/include/asm/mips-cpc.h b/arch/mips/include/asm/mips-cpc.h
index b54453f1648c1..5f3a7a9f42bf0 100644
--- a/arch/mips/include/asm/mips-cpc.h
+++ b/arch/mips/include/asm/mips-cpc.h
@@ -22,7 +22,7 @@ extern void __iomem *mips_cpc_base;
  *                              the CPC
  *
  * Returns the default physical base address of the Cluster Power Controller
- * memory mapped registers. This is platform dependant & must therefore be
+ * memory mapped registers. This is platform dependent & must therefore be
  * implemented per-platform.
  */
 extern phys_addr_t mips_cpc_default_phys_base(void);
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 2d53704d9f246..ec58cb76d076d 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -98,7 +98,7 @@
 
 /*
  * R4640/R4650 cp0 register names.  These registers are listed
- * here only for completeness; without MMU these CPUs are not useable
+ * here only for completeness; without MMU these CPUs are not usable
  * by Linux.  A future ELKS port might take make Linux run on them
  * though ...
  */
@@ -461,7 +461,7 @@
 #define EXCCODE_THREAD		25	/* Thread exceptions (MT) */
 #define EXCCODE_DSPDIS		26	/* DSP disabled exception */
 #define EXCCODE_GE		27	/* Virtualized guest exception (VZ) */
-#define EXCCODE_CACHEERR	30	/* Parity/ECC occured on a core */
+#define EXCCODE_CACHEERR	30	/* Parity/ECC occurred on a core */
 
 /* Implementation specific trap codes used by MIPS cores */
 #define MIPS_EXCCODE_TLBPAR	16	/* TLB parity error exception */
diff --git a/arch/mips/include/asm/octeon/cvmx-bootinfo.h b/arch/mips/include/asm/octeon/cvmx-bootinfo.h
index c1c0b3230e0a9..028bf1d6daeeb 100644
--- a/arch/mips/include/asm/octeon/cvmx-bootinfo.h
+++ b/arch/mips/include/asm/octeon/cvmx-bootinfo.h
@@ -114,7 +114,7 @@ struct cvmx_bootinfo {
 
 	/*
 	 * flags indicating various configuration options.  These
-	 * flags supercede the 'flags' variable and should be used
+	 * flags supersede the 'flags' variable and should be used
 	 * instead if available.
 	 */
 	uint32_t config_flags;
diff --git a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
index a07a36f7d8141..67e1b2162b194 100644
--- a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
+++ b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
@@ -145,7 +145,7 @@ typedef struct {
 /**
  * This structure contains the global state of all command queues.
  * It is stored in a bootmem named block and shared by all
- * applications running on Octeon. Tickets are stored in a differnet
+ * applications running on Octeon. Tickets are stored in a different
  * cache line that queue information to reduce the contention on the
  * ll/sc used to get a ticket. If this is not the case, the update
  * of queue state causes the ll/sc to fail quite often.
@@ -172,7 +172,7 @@ cvmx_cmd_queue_result_t cvmx_cmd_queue_initialize(cvmx_cmd_queue_id_t queue_id,
 						  int pool_size);
 
 /**
- * Shutdown a queue a free it's command buffers to the FPA. The
+ * Shutdown a queue and free its command buffers to the FPA. The
  * hardware connected to the queue must be stopped before this
  * function is called.
  *
@@ -194,7 +194,7 @@ int cvmx_cmd_queue_length(cvmx_cmd_queue_id_t queue_id);
 
 /**
  * Return the command buffer to be written to. The purpose of this
- * function is to allow CVMX routine access t othe low level buffer
+ * function is to allow CVMX routine access to the low level buffer
  * for initial hardware setup. User applications should not call this
  * function directly.
  *
diff --git a/arch/mips/include/asm/octeon/cvmx-pko.h b/arch/mips/include/asm/octeon/cvmx-pko.h
index 5fec8476e4212..f18a7f24daf82 100644
--- a/arch/mips/include/asm/octeon/cvmx-pko.h
+++ b/arch/mips/include/asm/octeon/cvmx-pko.h
@@ -91,7 +91,7 @@ typedef enum {
 } cvmx_pko_status_t;
 
 /**
- * This enumeration represents the differnet locking modes supported by PKO.
+ * This enumeration represents the different locking modes supported by PKO.
  */
 typedef enum {
 	/*
diff --git a/arch/mips/include/asm/octeon/cvmx-pow.h b/arch/mips/include/asm/octeon/cvmx-pow.h
index a3b23811e0c30..21b4378244faf 100644
--- a/arch/mips/include/asm/octeon/cvmx-pow.h
+++ b/arch/mips/include/asm/octeon/cvmx-pow.h
@@ -1342,7 +1342,7 @@ static inline void cvmx_pow_tag_sw_wait(void)
  * This function does NOT wait for previous tag switches to complete,
  * so the caller must ensure that there is not a pending tag switch.
  *
- * @wait:   When set, call stalls until work becomes avaiable, or times out.
+ * @wait:   When set, call stalls until work becomes available, or times out.
  *		 If not set, returns immediately.
  *
  * Returns: the WQE pointer from POW. Returns NULL if no work
@@ -1376,7 +1376,7 @@ static inline struct cvmx_wqe *cvmx_pow_work_request_sync_nocheck(cvmx_pow_wait_
  * This function waits for any previous tag switch to complete before
  * requesting the new work.
  *
- * @wait:   When set, call stalls until work becomes avaiable, or times out.
+ * @wait:   When set, call stalls until work becomes available, or times out.
  *		 If not set, returns immediately.
  *
  * Returns: the WQE pointer from POW. Returns NULL if no work
diff --git a/arch/mips/include/asm/octeon/octeon-model.h b/arch/mips/include/asm/octeon/octeon-model.h
index 6c68517c27702..e53b61a8e32f1 100644
--- a/arch/mips/include/asm/octeon/octeon-model.h
+++ b/arch/mips/include/asm/octeon/octeon-model.h
@@ -54,7 +54,7 @@
 #define OM_CHECK_SUBMODEL	  0x02000000
 /* Match all models previous than the one specified */
 #define OM_MATCH_PREVIOUS_MODELS  0x04000000
-/* Ignores the minor revison on newer parts */
+/* Ignores the minor revision on newer parts */
 #define OM_IGNORE_MINOR_REVISION  0x08000000
 #define OM_FLAG_MASK		  0xff000000
 
@@ -226,7 +226,7 @@
 #define OCTEON_CN52XX_PASS2	OCTEON_CN52XX_PASS2_X
 
 /*
- * CN3XXX models with old revision enconding
+ * CN3XXX models with old revision encoding
  */
 #define OCTEON_CN38XX_PASS1	0x000d0000
 #define OCTEON_CN38XX_PASS2	0x000d0001
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index 5978a8dfb917b..ef9585d96f6b0 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -173,7 +173,7 @@ static inline unsigned long ___pa(unsigned long x)
 	if (IS_ENABLED(CONFIG_64BIT)) {
 		/*
 		 * For MIPS64 the virtual address may either be in one of
-		 * the compatibility segements ckseg0 or ckseg1, or it may
+		 * the compatibility segments ckseg0 or ckseg1, or it may
 		 * be in xkphys.
 		 */
 		return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x);
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 3fd6e22c108b4..d993df6302dcf 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -23,7 +23,7 @@
 #ifdef CONFIG_PCI_DRIVERS_LEGACY
 
 /*
- * Each pci channel is a top-level PCI bus seem by CPU.	 A machine  with
+ * Each PCI channel is a top-level PCI bus seem by CPU.	 A machine with
  * multiple PCI channels may have multiple PCI host controllers or a
  * single controller supporting multiple channels.
  */
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index 421e78c30253c..088623ba7b8b1 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -201,7 +201,7 @@ enum pgtable_bits {
  * The final layouts of the PTE bits are:
  *
  *   64-bit, R1 or earlier:     CCC D V G [S H] M A W R P
- *   32-bit, R1 or earler:      CCC D V G M A W R P
+ *   32-bit, R1 or earlier:     CCC D V G M A W R P
  *   64-bit, R2 or later:       CCC D V G RI/R XI [S H] M A W P
  *   32-bit, R2 or later:       CCC D V G RI/R XI M A W P
  */
diff --git a/arch/mips/include/asm/sgi/mc.h b/arch/mips/include/asm/sgi/mc.h
index 3a070cec97e7d..5e96f9d326249 100644
--- a/arch/mips/include/asm/sgi/mc.h
+++ b/arch/mips/include/asm/sgi/mc.h
@@ -96,7 +96,7 @@ struct sgimc_regs {
 	volatile u32 lbursttp;	/* Time period for long bursts */
 
 	/* MC chip can drive up to 4 bank 4 SIMMs each. All SIMMs in bank must
-	 * be the same size. The size encoding for supported SIMMs is bellow */
+	 * be the same size. The size encoding for supported SIMMs is below */
 	u32 _unused11[9];
 	volatile u32 mconfig0;	/* Memory config register zero */
 	u32 _unused12;
diff --git a/arch/mips/include/asm/sn/klconfig.h b/arch/mips/include/asm/sn/klconfig.h
index 117f85e4bef59..3d1670b3e0527 100644
--- a/arch/mips/include/asm/sn/klconfig.h
+++ b/arch/mips/include/asm/sn/klconfig.h
@@ -851,7 +851,7 @@ typedef union kldev_s {	     /* for device structure allocation */
 /*
  * TBD - Allocation issues.
  *
- * Do we need to Mark off sepatate heaps for lboard_t, rboard_t, component,
+ * Do we need to Mark off separate heaps for lboard_t, rboard_t, component,
  * errinfo and allocate from them, or have a single heap and allocate all
  * structures from it. Debug is easier in the former method since we can
  * dump all similar structs in one command, but there will be lots of holes,
diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h
index aabd097933fe9..44c04a82d0b7d 100644
--- a/arch/mips/include/asm/sync.h
+++ b/arch/mips/include/asm/sync.h
@@ -19,7 +19,7 @@
  *
  * Ordering barriers can be more efficient than completion barriers, since:
  *
- *   a) Ordering barriers only require memory access instructions which preceed
+ *   a) Ordering barriers only require memory access instructions which precede
  *      them in program order (older instructions) to reach a point in the
  *      load/store datapath beyond which reordering is not possible before
  *      allowing memory access instructions which follow them (younger
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index ecae7470faa40..b9d76e8ac5a23 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -27,7 +27,7 @@ struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	unsigned long		tp_value;	/* thread pointer */
 	__u32			cpu;		/* current CPU */
-	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
+	int			preempt_count;	/* 0 => preemptible, <0 => BUG */
 	struct pt_regs		*regs;
 	long			syscall;	/* syscall number */
 };
diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h
index 2e107886f97ac..7ef06dcdc46ec 100644
--- a/arch/mips/include/asm/timex.h
+++ b/arch/mips/include/asm/timex.h
@@ -46,7 +46,7 @@ typedef unsigned int cycles_t;
  *
  * There is a suggested workaround and also the erratum can't strike if
  * the compare interrupt isn't being used as the clock source device.
- * However for now the implementaton of this function doesn't get these
+ * However for now the implementation of this function doesn't get these
  * fine details right.
  */
 static inline int can_use_mips_counter(unsigned int prid)
diff --git a/arch/mips/include/asm/vdso/vdso.h b/arch/mips/include/asm/vdso/vdso.h
index a327ca21270ec..6cd88191fefa9 100644
--- a/arch/mips/include/asm/vdso/vdso.h
+++ b/arch/mips/include/asm/vdso/vdso.h
@@ -32,7 +32,7 @@ static inline unsigned long get_vdso_base(void)
 #else
 	/*
 	 * Get the base load address of the VDSO. We have to avoid generating
-	 * relocations and references to the GOT because ld.so does not peform
+	 * relocations and references to the GOT because ld.so does not perform
 	 * relocations on the VDSO. We use the current offset from the VDSO base
 	 * and perform a PC-relative branch which gives the absolute address in
 	 * ra, and take the difference. The assembler chokes on
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index c6e1fc77c9968..9c48d9a21aa01 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -88,7 +88,7 @@
 #define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
 #define MADV_NOHUGEPAGE 15		/* Not worth backing with hugepages */
 
-#define MADV_DONTDUMP	16		/* Explicity exclude from the core dump,
+#define MADV_DONTDUMP	16		/* Explicitly exclude from core dump,
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	17		/* Clear the MADV_NODUMP flag */
 
diff --git a/arch/mips/include/uapi/asm/msgbuf.h b/arch/mips/include/uapi/asm/msgbuf.h
index 128af72f2dfea..d546642fc67e6 100644
--- a/arch/mips/include/uapi/asm/msgbuf.h
+++ b/arch/mips/include/uapi/asm/msgbuf.h
@@ -62,7 +62,7 @@ struct msqid64_ds {
 	unsigned long  __unused5;
 };
 #else
-#warning no endianess set
+#warning no endianness set
 #endif
 
 #endif /* _ASM_MSGBUF_H */
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index b406d8bfb15a3..2f4fafdc5fccf 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1139,7 +1139,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 		 * This processor doesn't have an MMU, so it's not
 		 * "real easy" to run Linux on it. It is left purely
 		 * for documentation.  Commented out because it shares
-		 * it's c0_prid id number with the TX3900.
+		 * its c0_prid id number with the TX3900.
 		 */
 		c->cputype = CPU_R4650;
 		__cpu_name[cpu] = "R4650";
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 316b27d0d2fbd..dc39f5b3fb830 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -55,7 +55,7 @@ NOKPROBE_SYMBOL(insn_has_delayslot);
  * one; putting breakpoint on top of atomic ll/sc pair is bad idea;
  * so we need to prevent it and refuse kprobes insertion for such
  * instructions; cannot do much about breakpoint in the middle of
- * ll/sc pair; it is upto user to avoid those places
+ * ll/sc pair; it is up to user to avoid those places
  */
 static int insn_has_ll_or_sc(union mips_instruction insn)
 {
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index 58fc8d089402b..7eeeaf1ff95d2 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -380,7 +380,7 @@ void *__init relocate_kernel(void)
 		}
 #endif /* CONFIG_USE_OF */
 
-		/* Copy the kernel to it's new location */
+		/* Copy the kernel to its new location */
 		memcpy(loc_new, &_text, kernel_length);
 
 		/* Perform relocations on the new kernel */
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index 8f0a7263a9d61..de894a0211d7a 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -70,7 +70,7 @@ copy_word:
 done:
 #ifdef CONFIG_SMP
 	/* kexec_flag reset is signal to other CPUs what kernel
-	   was moved to it's location. Note - we need relocated address
+	   was moved to its location. Note - we need relocated address
 	   of kexec_flag.  */
 
 	bal		1f
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 0461ab49e8f1a..844307a86b159 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -146,7 +146,7 @@ static unsigned long __init init_initrd(void)
 	/*
 	 * Board specific code or command line parser should have
 	 * already set up initrd_start and initrd_end. In these cases
-	 * perfom sanity checks and use them if all looks good.
+	 * perform sanity checks and use them if all looks good.
 	 */
 	if (!initrd_start || initrd_end <= initrd_start)
 		goto disable;
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 479999b7f2de7..a8e20fdc7afd7 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -569,7 +569,7 @@ void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		return (void __user __force *)(-1UL);
 
 	/*
-	 * FPU emulator may have it's own trampoline active just
+	 * FPU emulator may have its own trampoline active just
 	 * above the user stack, 16-bytes before the next lowest
 	 * 16 byte boundary.  Try to avoid trashing it.
 	 */
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index c1b2b18b05053..0e3f2f2fa732b 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2381,7 +2381,7 @@ void __init trap_init(void)
 		set_except_vector(i, handle_reserved);
 
 	/*
-	 * Copy the EJTAG debug exception vector handler code to it's final
+	 * Copy the EJTAG debug exception vector handler code to its final
 	 * destination.
 	 */
 	if (cpu_has_ejtag && board_ejtag_handler_setup)
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index e9a0cfd02ae20..737d0d4fdcd35 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -6,9 +6,9 @@
  * Copyright (C) 2004, 2005 MIPS Technologies, Inc.  All rights reserved.
  * Copyright (C) 2013 Imagination Technologies Ltd.
  *
- * VPE spport module for loading a MIPS SP program into VPE1. The SP
+ * VPE support module for loading a MIPS SP program into VPE1. The SP
  * environment is rather simple since there are no TLBs. It needs
- * to be relocatable (or partiall linked). Initialize your stack in
+ * to be relocatable (or partially linked). Initialize your stack in
  * the startup-code. The loader looks for the symbol __start and sets
  * up the execution to resume from there. To load and run, simply do
  * a cat SP 'binary' to the /dev/vpe1 device.
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index e64372b8f66af..0feec52222fb9 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -531,7 +531,7 @@ static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
  * to be used for a period of time, but the exact ktime corresponding to the
  * final Count that must be restored is not known.
  *
- * It is gauranteed that a timer interrupt immediately after restore will be
+ * It is guaranteed that a timer interrupt immediately after restore will be
  * handled, but not if CP0_Compare is exactly at @count. That case should
  * already be handled when the hardware timer state is saved.
  *
diff --git a/arch/mips/loongson2ef/common/platform.c b/arch/mips/loongson2ef/common/platform.c
index 0084820cffaa8..b10300a527af2 100644
--- a/arch/mips/loongson2ef/common/platform.c
+++ b/arch/mips/loongson2ef/common/platform.c
@@ -17,7 +17,7 @@ static int __init loongson2_cpufreq_init(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
 
-	/* Only 2F revision and it's successors support CPUFreq */
+	/* Only 2F revision and its successors support CPUFreq */
 	if ((c->processor_id & PRID_REV_MASK) >= PRID_REV_LOONGSON2F)
 		return platform_device_register(&loongson2_cpufreq_device);
 
diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
index e015a26a40f7a..4f6c714430daa 100644
--- a/arch/mips/loongson64/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -516,7 +516,7 @@ static void __init loongson3_prepare_cpus(unsigned int max_cpus)
 }
 
 /*
- * Setup the PC, SP, and GP of a secondary processor and start it runing!
+ * Setup the PC, SP, and GP of a secondary processor and start it running!
  */
 static int loongson3_boot_secondary(int cpu, struct task_struct *idle)
 {
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 187d1c16361cf..20d37773b162b 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1654,7 +1654,7 @@ static void coherency_setup(void)
 
 	/*
 	 * c0_status.cu=0 specifies that updates by the sc instruction use
-	 * the coherency mode specified by the TLB; 1 means cachable
+	 * the coherency mode specified by the TLB; 1 means cacheable
 	 * coherent update on write will be used.  Not all processors have
 	 * this bit and; some wire it to zero, others like Toshiba had the
 	 * silly idea of putting something else there ...
diff --git a/arch/mips/mm/cex-gen.S b/arch/mips/mm/cex-gen.S
index 45dff5cd4b8e7..e528583d13311 100644
--- a/arch/mips/mm/cex-gen.S
+++ b/arch/mips/mm/cex-gen.S
@@ -25,7 +25,7 @@
 	 * This is a very bad place to be.  Our cache error
 	 * detection has triggered.  If we have write-back data
 	 * in the cache, we may not be able to recover.	 As a
-	 * first-order desperate measure, turn off KSEG0 cacheing.
+	 * first-order desperate measure, turn off KSEG0 caching.
 	 */
 	mfc0	k0,CP0_CONFIG
 	li	k1,~CONF_CM_CMASK
diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c
index 53dfa2b9316ba..22a8f488ae1d6 100644
--- a/arch/mips/mm/tlb-r3k.c
+++ b/arch/mips/mm/tlb-r3k.c
@@ -183,7 +183,7 @@ void __update_tlb(struct vm_area_struct *vma, unsigned long address, pte_t pte)
 	int idx, pid;
 
 	/*
-	 * Handle debugger faulting in for debugee.
+	 * Handle debugger faulting in for debuggee.
 	 */
 	if (current->active_mm != vma->vm_mm)
 		return;
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 93c2d695588a1..128a0a5ec2b7f 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -301,7 +301,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	int idx, pid;
 
 	/*
-	 * Handle debugger faulting in for debugee.
+	 * Handle debugger faulting in for debuggee.
 	 */
 	if (current->active_mm != vma->vm_mm)
 		return;
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index b4e1c783e6177..4017fa0e2f68d 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -789,7 +789,7 @@ void build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 
 	if (check_for_high_segbits) {
 		/*
-		 * The kernel currently implicitely assumes that the
+		 * The kernel currently implicitly assumes that the
 		 * MIPS SEGBITS parameter for the processor is
 		 * (PGDIR_SHIFT+PGDIR_BITS) or less, and will never
 		 * allocate virtual addresses outside the maximum
@@ -1715,7 +1715,7 @@ iPTE_SW(u32 **p, struct uasm_reloc **r, unsigned int pte, unsigned int ptr,
 /*
  * Check if PTE is present, if not then jump to LABEL. PTR points to
  * the page table where this PTE is located, PTE will be re-loaded
- * with it's original value.
+ * with its original value.
  */
 static void
 build_pte_present(u32 **p, struct uasm_reloc **r,
diff --git a/arch/mips/net/bpf_jit_comp32.c b/arch/mips/net/bpf_jit_comp32.c
index ace5db3fbd171..40a878b672f5d 100644
--- a/arch/mips/net/bpf_jit_comp32.c
+++ b/arch/mips/net/bpf_jit_comp32.c
@@ -95,7 +95,7 @@
 /*
  * Mapping of 64-bit eBPF registers to 32-bit native MIPS registers.
  *
- * 1) Native register pairs are ordered according to CPU endiannes, following
+ * 1) Native register pairs are ordered according to CPU endianness, following
  *    the MIPS convention for passing 64-bit arguments and return values.
  * 2) The eBPF return value, arguments and callee-saved registers are mapped
  *    to their native MIPS equivalents.
diff --git a/arch/mips/pci/ops-loongson2.c b/arch/mips/pci/ops-loongson2.c
index 0d1b36ba1c21c..068113f5c49d4 100644
--- a/arch/mips/pci/ops-loongson2.c
+++ b/arch/mips/pci/ops-loongson2.c
@@ -49,7 +49,7 @@ static int loongson_pcibios_config_access(unsigned char access_type,
 		 */
 #ifdef CONFIG_CS5536
 		/* cs5536_pci_conf_read4/write4() will call _rdmsr/_wrmsr() to
-		 * access the regsters PCI_MSR_ADDR, PCI_MSR_DATA_LO,
+		 * access the registers PCI_MSR_ADDR, PCI_MSR_DATA_LO,
 		 * PCI_MSR_DATA_HI, which is bigger than PCI_MSR_CTRL, so, it
 		 * will not go this branch, but the others. so, no calling dead
 		 * loop here.
diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c
index 1c722dd0c1302..58625d1b64658 100644
--- a/arch/mips/pci/pci-alchemy.c
+++ b/arch/mips/pci/pci-alchemy.c
@@ -453,7 +453,7 @@ static int alchemy_pci_probe(struct platform_device *pdev)
 
 	/* we can't ioremap the entire pci config space because it's too large,
 	 * nor can we dynamically ioremap it because some drivers use the
-	 * PCI config routines from within atomic contex and that becomes a
+	 * PCI config routines from within atomic context and that becomes a
 	 * problem in get_vm_area().  Instead we use one wired TLB entry to
 	 * handle all config accesses for all busses.
 	 */
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index e17d862cfa4c6..a925842ee1256 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -16,7 +16,7 @@
  * the CFG_SEL bit in the PCI_MISC_CONFIG register.
  *
  * Devices on the bus can perform DMA requests via chip BAR1. PCI host
- * controller BARs are programmend as if an external device is programmed.
+ * controller BARs are programmed as if an external device is programmed.
  * Which means that during configuration, IDSEL pin of the chip should be
  * asserted.
  *
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 80f7293166bb7..68a8cefed420b 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -152,7 +152,7 @@ static int ltq_pci_startup(struct platform_device *pdev)
 		temp_buffer &= ~0xf0000;
 	/* enable internal arbiter */
 	temp_buffer |= (1 << INTERNAL_ARB_ENABLE_BIT);
-	/* enable internal PCI master reqest */
+	/* enable internal PCI master request */
 	temp_buffer &= (~(3 << PCI_MASTER0_REQ_MASK_2BITS));
 
 	/* enable EBU request */
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index d19d9d4563092..36d12cea35122 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -376,7 +376,7 @@ static void octeon_pci_initialize(void)
 	ctl_status.s.timer = 1;
 	cvmx_write_csr(CVMX_NPI_CTL_STATUS, ctl_status.u64);
 
-	/* Deassert PCI reset and advertize PCX Host Mode Device Capability
+	/* Deassert PCI reset and advertise PCX Host Mode Device Capability
 	   (64b) */
 	cvmx_write_csr(CVMX_CIU_SOFT_PRST, 0x4);
 	cvmx_read_csr(CVMX_CIU_SOFT_PRST);
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 68d5211afea8b..45ddbaa6c1237 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -114,7 +114,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC3,
  *
  * The function is complicated by the ultimate brokenness of the IOC3 chip
  * which is used in SGI systems.  The IOC3 can only handle 32-bit PCI
- * accesses and does only decode parts of it's address space.
+ * accesses and does only decode parts of its address space.
  */
 static int pci_conf0_read_config(struct pci_bus *bus, unsigned int devfn,
 				 int where, int size, u32 *value)
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index c9edd3fb380df..2583e318e8c6b 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -1037,7 +1037,7 @@ retry:
 			in_fif_p_count = dbg_data.s.data & 0xff;
 		} while (in_fif_p_count != ((old_in_fif_p_count+1) & 0xff));
 
-		/* Update in_fif_p_count for it's offset with respect to out_p_count */
+		/* Update in_fif_p_count for its offset with respect to out_p_count */
 		in_fif_p_count = (in_fif_p_count + in_p_offset) & 0xff;
 
 		/* Read the OUT_P_COUNT from the debug select */
diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c
index 137781d0bd0a1..5a9fd3fe41d7c 100644
--- a/arch/mips/ralink/mt7621.c
+++ b/arch/mips/ralink/mt7621.c
@@ -175,7 +175,7 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info)
 		 * mips_cm_probe() wipes out bootloader
 		 * config for CM regions and we have to configure them
 		 * again. This SoC cannot talk to pamlbus devices
-		 * witout proper iocu region set up.
+		 * without proper iocu region set up.
 		 *
 		 * FIXME: it would be better to do this with values
 		 * from DT, but we need this very early because
diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c
index 5ae30b78d38d3..d9249f5a632e0 100644
--- a/arch/mips/txx9/generic/pci.c
+++ b/arch/mips/txx9/generic/pci.c
@@ -348,7 +348,7 @@ static void final_fixup(struct pci_dev *dev)
 	unsigned char bist;
 	int ret;
 
-	/* Do build-in self test */
+	/* Do built-in self test */
 	ret = pci_read_config_byte(dev, PCI_BIST, &bist);
 	if ((ret != PCIBIOS_SUCCESSFUL) || !(bist & PCI_BIST_CAPABLE))
 		return;
-- 
GitLab


From 59b946ea30806064c4ac78f0ac93642655dd4f2e Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Mon, 8 Jan 2024 11:48:41 +0200
Subject: [PATCH 2345/4076] ASoC: Intel: bxt_da7219_max98357a: Fix kernel ops
 due to COMP_DUMMY change

The change to avoid dummy components will leave the component name and
dai_name NULL which will cause NULL dereference when trying to access to
it in the machine driver when applying fixups.

Link: https://github.com/thesofproject/linux/pull/4759#issuecomment-1878641868
Fixes: 13f58267cda3 ("ASoC: soc.h: don't create dummy Component via COMP_DUMMY()")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://msgid.link/r/20240108094842.28782-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bxt_da7219_max98357a.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index 816fad8c1ff0e..540f7a29310a9 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -797,6 +797,9 @@ static int broxton_audio_probe(struct platform_device *pdev)
 		broxton_audio_card.name = "glkda7219max";
 		/* Fixup the SSP entries for geminilake */
 		for (i = 0; i < ARRAY_SIZE(broxton_dais); i++) {
+			if (!broxton_dais[i].codecs->dai_name)
+				continue;
+
 			/* MAXIM_CODEC is connected to SSP1. */
 			if (!strcmp(broxton_dais[i].codecs->dai_name,
 				    BXT_MAXIM_CODEC_DAI)) {
@@ -822,6 +825,9 @@ static int broxton_audio_probe(struct platform_device *pdev)
 			broxton_audio_card.name = "cmlda7219max";
 
 		for (i = 0; i < ARRAY_SIZE(broxton_dais); i++) {
+			if (!broxton_dais[i].codecs->dai_name)
+				continue;
+
 			/* MAXIM_CODEC is connected to SSP1. */
 			if (!strcmp(broxton_dais[i].codecs->dai_name,
 					BXT_MAXIM_CODEC_DAI)) {
-- 
GitLab


From 3ec71290db4de298b67659ef2bc2a8f84cf9537b Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Mon, 8 Jan 2024 11:48:42 +0200
Subject: [PATCH 2346/4076] ASoC: Intel: bxt_rt298: Fix kernel ops due to
 COMP_DUMMY change

The change to avoid dummy components will leave the component name and
dai_name NULL which will cause NULL dereference when trying to access to
it in the machine driver when applying fixups.

Link: https://github.com/thesofproject/linux/pull/4759#issuecomment-1878641868
Fixes: 13f58267cda3 ("ASoC: soc.h: don't create dummy Component via COMP_DUMMY()")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://msgid.link/r/20240108094842.28782-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bxt_rt298.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index 4631106f2a282..c0eb65c14aa97 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -604,7 +604,8 @@ static int broxton_audio_probe(struct platform_device *pdev)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(broxton_rt298_dais); i++) {
-		if (!strncmp(card->dai_link[i].codecs->name, "i2c-INT343A:00",
+		if (card->dai_link[i].codecs->name &&
+		    !strncmp(card->dai_link[i].codecs->name, "i2c-INT343A:00",
 			     I2C_NAME_SIZE)) {
 			if (!strncmp(card->name, "broxton-rt298",
 				     PLATFORM_NAME_SIZE)) {
-- 
GitLab


From 7423546040194e0e74fcfedd089a8b2720fcfc6e Mon Sep 17 00:00:00 2001
From: John Sanpe <sanpeqf@gmail.com>
Date: Tue, 5 Dec 2023 23:58:37 +0800
Subject: [PATCH 2347/4076] exfat: using hweight instead of internal logic

Replace the internal table lookup algorithm with the hweight
library, which has instruction set acceleration capabilities.

Use it to increase the length of a single calculation of
the exfat_find_free_bitmap function to the long type.

Signed-off-by: John Sanpe <sanpeqf@gmail.com>
Acked-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/balloc.c | 48 +++++++++++++++++++++--------------------------
 1 file changed, 21 insertions(+), 27 deletions(-)

diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c
index e918decb37358..3e3e9e4cce2f2 100644
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -5,11 +5,22 @@
 
 #include <linux/blkdev.h>
 #include <linux/slab.h>
+#include <linux/bitmap.h>
 #include <linux/buffer_head.h>
 
 #include "exfat_raw.h"
 #include "exfat_fs.h"
 
+#if BITS_PER_LONG == 32
+#define __le_long __le32
+#define lel_to_cpu(A) le32_to_cpu(A)
+#elif BITS_PER_LONG == 64
+#define __le_long __le64
+#define lel_to_cpu(A) le64_to_cpu(A)
+#else
+#error "BITS_PER_LONG not 32 or 64"
+#endif
+
 static const unsigned char free_bit[] = {
 	0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2,/*  0 ~  19*/
 	0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 5, 0, 1, 0, 2, 0, 1, 0, 3,/* 20 ~  39*/
@@ -26,22 +37,6 @@ static const unsigned char free_bit[] = {
 	0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0                /*240 ~ 254*/
 };
 
-static const unsigned char used_bit[] = {
-	0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4, 1, 2, 2, 3,/*  0 ~  19*/
-	2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, 1, 2, 2, 3, 2, 3, 3, 4,/* 20 ~  39*/
-	2, 3, 3, 4, 3, 4, 4, 5, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5,/* 40 ~  59*/
-	4, 5, 5, 6, 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,/* 60 ~  79*/
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 2, 3, 3, 4,/* 80 ~  99*/
-	3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5, 4, 5, 5, 6,/*100 ~ 119*/
-	4, 5, 5, 6, 5, 6, 6, 7, 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4,/*120 ~ 139*/
-	3, 4, 4, 5, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,/*140 ~ 159*/
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5,/*160 ~ 179*/
-	4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, 2, 3, 3, 4, 3, 4, 4, 5,/*180 ~ 199*/
-	3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6,/*200 ~ 219*/
-	5, 6, 6, 7, 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,/*220 ~ 239*/
-	4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8             /*240 ~ 255*/
-};
-
 /*
  *  Allocation Bitmap Management Functions
  */
@@ -244,25 +239,24 @@ int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count)
 	unsigned int count = 0;
 	unsigned int i, map_i = 0, map_b = 0;
 	unsigned int total_clus = EXFAT_DATA_CLUSTER_COUNT(sbi);
-	unsigned int last_mask = total_clus & BITS_PER_BYTE_MASK;
-	unsigned char clu_bits;
-	const unsigned char last_bit_mask[] = {0, 0b00000001, 0b00000011,
-		0b00000111, 0b00001111, 0b00011111, 0b00111111, 0b01111111};
+	unsigned int last_mask = total_clus & (BITS_PER_LONG - 1);
+	unsigned long *bitmap, clu_bits;
 
 	total_clus &= ~last_mask;
-	for (i = 0; i < total_clus; i += BITS_PER_BYTE) {
-		clu_bits = *(sbi->vol_amap[map_i]->b_data + map_b);
-		count += used_bit[clu_bits];
-		if (++map_b >= (unsigned int)sb->s_blocksize) {
+	for (i = 0; i < total_clus; i += BITS_PER_LONG) {
+		bitmap = (void *)(sbi->vol_amap[map_i]->b_data + map_b);
+		count += hweight_long(*bitmap);
+		map_b += sizeof(long);
+		if (map_b >= (unsigned int)sb->s_blocksize) {
 			map_i++;
 			map_b = 0;
 		}
 	}
 
 	if (last_mask) {
-		clu_bits = *(sbi->vol_amap[map_i]->b_data + map_b);
-		clu_bits &= last_bit_mask[last_mask];
-		count += used_bit[clu_bits];
+		bitmap = (void *)(sbi->vol_amap[map_i]->b_data + map_b);
+		clu_bits = lel_to_cpu(*(__le_long *)bitmap);
+		count += hweight_long(clu_bits & BITMAP_LAST_WORD_MASK(last_mask));
 	}
 
 	*ret_count = count;
-- 
GitLab


From 34939ae005ec402ee183956114b1a74cb57b8b9d Mon Sep 17 00:00:00 2001
From: John Sanpe <sanpeqf@gmail.com>
Date: Fri, 8 Dec 2023 07:47:01 +0800
Subject: [PATCH 2348/4076] exfat: using ffs instead of internal logic

Replaced the internal table lookup algorithm with ffs of
the bitops library with better performance.

Use it to increase the single processing length of the
exfat_find_free_bitmap function, from single-byte search to long type.

Signed-off-by: John Sanpe <sanpeqf@gmail.com>
Acked-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/balloc.c   | 41 +++++++++++++++--------------------------
 fs/exfat/exfat_fs.h |  3 +--
 2 files changed, 16 insertions(+), 28 deletions(-)

diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c
index 3e3e9e4cce2f2..0356c88252bd3 100644
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -14,29 +14,15 @@
 #if BITS_PER_LONG == 32
 #define __le_long __le32
 #define lel_to_cpu(A) le32_to_cpu(A)
+#define cpu_to_lel(A) cpu_to_le32(A)
 #elif BITS_PER_LONG == 64
 #define __le_long __le64
 #define lel_to_cpu(A) le64_to_cpu(A)
+#define cpu_to_lel(A) cpu_to_le64(A)
 #else
 #error "BITS_PER_LONG not 32 or 64"
 #endif
 
-static const unsigned char free_bit[] = {
-	0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2,/*  0 ~  19*/
-	0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 5, 0, 1, 0, 2, 0, 1, 0, 3,/* 20 ~  39*/
-	0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2,/* 40 ~  59*/
-	0, 1, 0, 6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4,/* 60 ~  79*/
-	0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 5, 0, 1, 0, 2,/* 80 ~  99*/
-	0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2, 0, 1, 0, 3,/*100 ~ 119*/
-	0, 1, 0, 2, 0, 1, 0, 7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2,/*120 ~ 139*/
-	0, 1, 0, 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 5,/*140 ~ 159*/
-	0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2,/*160 ~ 179*/
-	0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 6, 0, 1, 0, 2, 0, 1, 0, 3,/*180 ~ 199*/
-	0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2,/*200 ~ 219*/
-	0, 1, 0, 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4,/*220 ~ 239*/
-	0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0                /*240 ~ 254*/
-};
-
 /*
  *  Allocation Bitmap Management Functions
  */
@@ -195,32 +181,35 @@ unsigned int exfat_find_free_bitmap(struct super_block *sb, unsigned int clu)
 {
 	unsigned int i, map_i, map_b, ent_idx;
 	unsigned int clu_base, clu_free;
-	unsigned char k, clu_mask;
+	unsigned long clu_bits, clu_mask;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
+	__le_long bitval;
 
 	WARN_ON(clu < EXFAT_FIRST_CLUSTER);
-	ent_idx = CLUSTER_TO_BITMAP_ENT(clu);
-	clu_base = BITMAP_ENT_TO_CLUSTER(ent_idx & ~(BITS_PER_BYTE_MASK));
+	ent_idx = ALIGN_DOWN(CLUSTER_TO_BITMAP_ENT(clu), BITS_PER_LONG);
+	clu_base = BITMAP_ENT_TO_CLUSTER(ent_idx);
 	clu_mask = IGNORED_BITS_REMAINED(clu, clu_base);
 
 	map_i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx);
 	map_b = BITMAP_OFFSET_BYTE_IN_SECTOR(sb, ent_idx);
 
 	for (i = EXFAT_FIRST_CLUSTER; i < sbi->num_clusters;
-	     i += BITS_PER_BYTE) {
-		k = *(sbi->vol_amap[map_i]->b_data + map_b);
+	     i += BITS_PER_LONG) {
+		bitval = *(__le_long *)(sbi->vol_amap[map_i]->b_data + map_b);
 		if (clu_mask > 0) {
-			k |= clu_mask;
+			bitval |= cpu_to_lel(clu_mask);
 			clu_mask = 0;
 		}
-		if (k < 0xFF) {
-			clu_free = clu_base + free_bit[k];
+		if (lel_to_cpu(bitval) != ULONG_MAX) {
+			clu_bits = lel_to_cpu(bitval);
+			clu_free = clu_base + ffz(clu_bits);
 			if (clu_free < sbi->num_clusters)
 				return clu_free;
 		}
-		clu_base += BITS_PER_BYTE;
+		clu_base += BITS_PER_LONG;
+		map_b += sizeof(long);
 
-		if (++map_b >= sb->s_blocksize ||
+		if (map_b >= sb->s_blocksize ||
 		    clu_base >= sbi->num_clusters) {
 			if (++map_i >= sbi->map_sectors) {
 				clu_base = EXFAT_FIRST_CLUSTER;
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index a7a2c35d74fbd..8030780a199b4 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -135,8 +135,7 @@ enum {
 #define BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent) (ent & BITS_PER_SECTOR_MASK(sb))
 #define BITMAP_OFFSET_BYTE_IN_SECTOR(sb, ent) \
 	((ent / BITS_PER_BYTE) & ((sb)->s_blocksize - 1))
-#define BITS_PER_BYTE_MASK	0x7
-#define IGNORED_BITS_REMAINED(clu, clu_base) ((1 << ((clu) - (clu_base))) - 1)
+#define IGNORED_BITS_REMAINED(clu, clu_base) ((1UL << ((clu) - (clu_base))) - 1)
 
 #define ES_ENTRY_NUM(name_len)	(ES_IDX_LAST_FILENAME(name_len) + 1)
 /* 19 entries = 1 file entry + 1 stream entry + 17 filename entries */
-- 
GitLab


From 11a347fb6cef62ce47e84b97c45f2b2497c7593b Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Mon, 13 Mar 2023 12:38:53 +0800
Subject: [PATCH 2349/4076] exfat: change to get file size from DataLength

In stream extension directory entry, the ValidDataLength
field describes how far into the data stream user data has
been written, and the DataLength field describes the file
size.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Andy Wu <Andy.Wu@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/exfat_fs.h |   2 +
 fs/exfat/file.c     | 118 ++++++++++++++++++++++++++++++++++++++++-
 fs/exfat/inode.c    | 124 ++++++++++++++++++++++++++++++++++++++------
 fs/exfat/namei.c    |   6 +++
 4 files changed, 231 insertions(+), 19 deletions(-)

diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 8030780a199b4..9474cd50da6d4 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -207,6 +207,7 @@ struct exfat_dir_entry {
 	unsigned char flags;
 	unsigned short attr;
 	loff_t size;
+	loff_t valid_size;
 	unsigned int num_subdirs;
 	struct timespec64 atime;
 	struct timespec64 mtime;
@@ -316,6 +317,7 @@ struct exfat_inode_info {
 	loff_t i_size_aligned;
 	/* on-disk position of directory entry or 0 */
 	loff_t i_pos;
+	loff_t valid_size;
 	/* hash by i_location */
 	struct hlist_node i_hash_fat;
 	/* protect bmap against truncate */
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index bfdfafe009930..270e2f934124e 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -11,6 +11,7 @@
 #include <linux/fsnotify.h>
 #include <linux/security.h>
 #include <linux/msdos_fs.h>
+#include <linux/writeback.h>
 
 #include "exfat_raw.h"
 #include "exfat_fs.h"
@@ -26,6 +27,7 @@ static int exfat_cont_expand(struct inode *inode, loff_t size)
 		return err;
 
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+	EXFAT_I(inode)->valid_size = size;
 	mark_inode_dirty(inode);
 
 	if (!IS_SYNC(inode))
@@ -146,6 +148,9 @@ int __exfat_truncate(struct inode *inode)
 		ei->start_clu = EXFAT_EOF_CLUSTER;
 	}
 
+	if (i_size_read(inode) < ei->valid_size)
+		ei->valid_size = i_size_read(inode);
+
 	if (ei->type == TYPE_FILE)
 		ei->attr |= EXFAT_ATTR_ARCHIVE;
 
@@ -474,15 +479,124 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	return blkdev_issue_flush(inode->i_sb->s_bdev);
 }
 
+static int exfat_file_zeroed_range(struct file *file, loff_t start, loff_t end)
+{
+	int err;
+	struct inode *inode = file_inode(file);
+	struct address_space *mapping = inode->i_mapping;
+	const struct address_space_operations *ops = mapping->a_ops;
+
+	while (start < end) {
+		u32 zerofrom, len;
+		struct page *page = NULL;
+
+		zerofrom = start & (PAGE_SIZE - 1);
+		len = PAGE_SIZE - zerofrom;
+		if (start + len > end)
+			len = end - start;
+
+		err = ops->write_begin(file, mapping, start, len, &page, NULL);
+		if (err)
+			goto out;
+
+		zero_user_segment(page, zerofrom, zerofrom + len);
+
+		err = ops->write_end(file, mapping, start, len, len, page, NULL);
+		if (err < 0)
+			goto out;
+		start += len;
+
+		balance_dirty_pages_ratelimited(mapping);
+		cond_resched();
+	}
+
+out:
+	return err;
+}
+
+static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	ssize_t ret;
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	loff_t pos = iocb->ki_pos;
+	loff_t valid_size;
+
+	inode_lock(inode);
+
+	valid_size = ei->valid_size;
+
+	ret = generic_write_checks(iocb, iter);
+	if (ret < 0)
+		goto unlock;
+
+	if (pos > valid_size) {
+		ret = exfat_file_zeroed_range(file, valid_size, pos);
+		if (ret < 0 && ret != -ENOSPC) {
+			exfat_err(inode->i_sb,
+				"write: fail to zero from %llu to %llu(%zd)",
+				valid_size, pos, ret);
+		}
+		if (ret < 0)
+			goto unlock;
+	}
+
+	ret = __generic_file_write_iter(iocb, iter);
+	if (ret < 0)
+		goto unlock;
+
+	inode_unlock(inode);
+
+	if (pos > valid_size)
+		pos = valid_size;
+
+	if (iocb_is_dsync(iocb) && iocb->ki_pos > pos) {
+		ssize_t err = vfs_fsync_range(file, pos, iocb->ki_pos - 1,
+				iocb->ki_flags & IOCB_SYNC);
+		if (err < 0)
+			return err;
+	}
+
+	return ret;
+
+unlock:
+	inode_unlock(inode);
+
+	return ret;
+}
+
+static int exfat_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int ret;
+	struct inode *inode = file_inode(file);
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	loff_t start = ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	loff_t end = min_t(loff_t, i_size_read(inode),
+			start + vma->vm_end - vma->vm_start);
+
+	if ((vma->vm_flags & VM_WRITE) && ei->valid_size < end) {
+		ret = exfat_file_zeroed_range(file, ei->valid_size, end);
+		if (ret < 0) {
+			exfat_err(inode->i_sb,
+				  "mmap: fail to zero from %llu to %llu(%d)",
+				  start, end, ret);
+			return ret;
+		}
+	}
+
+	return generic_file_mmap(file, vma);
+}
+
 const struct file_operations exfat_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
-	.write_iter	= generic_file_write_iter,
+	.write_iter	= exfat_file_write_iter,
 	.unlocked_ioctl = exfat_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = exfat_compat_ioctl,
 #endif
-	.mmap		= generic_file_mmap,
+	.mmap		= exfat_file_mmap,
 	.fsync		= exfat_file_fsync,
 	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index e7ff58b8e68c7..b02677c9fd459 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -75,8 +75,8 @@ int __exfat_write_inode(struct inode *inode, int sync)
 	if (ei->start_clu == EXFAT_EOF_CLUSTER)
 		on_disk_size = 0;
 
-	ep2->dentry.stream.valid_size = cpu_to_le64(on_disk_size);
-	ep2->dentry.stream.size = ep2->dentry.stream.valid_size;
+	ep2->dentry.stream.valid_size = cpu_to_le64(ei->valid_size);
+	ep2->dentry.stream.size = cpu_to_le64(on_disk_size);
 	if (on_disk_size) {
 		ep2->dentry.stream.flags = ei->flags;
 		ep2->dentry.stream.start_clu = cpu_to_le32(ei->start_clu);
@@ -278,6 +278,7 @@ static int exfat_get_block(struct inode *inode, sector_t iblock,
 	unsigned int cluster, sec_offset;
 	sector_t last_block;
 	sector_t phys = 0;
+	sector_t valid_blks;
 	loff_t pos;
 
 	mutex_lock(&sbi->s_lock);
@@ -306,17 +307,32 @@ static int exfat_get_block(struct inode *inode, sector_t iblock,
 	mapped_blocks = sbi->sect_per_clus - sec_offset;
 	max_blocks = min(mapped_blocks, max_blocks);
 
-	/* Treat newly added block / cluster */
-	if (iblock < last_block)
-		create = 0;
-
-	if (create || buffer_delay(bh_result)) {
-		pos = EXFAT_BLK_TO_B((iblock + 1), sb);
+	pos = EXFAT_BLK_TO_B((iblock + 1), sb);
+	if ((create && iblock >= last_block) || buffer_delay(bh_result)) {
 		if (ei->i_size_ondisk < pos)
 			ei->i_size_ondisk = pos;
 	}
 
+	map_bh(bh_result, sb, phys);
+	if (buffer_delay(bh_result))
+		clear_buffer_delay(bh_result);
+
 	if (create) {
+		valid_blks = EXFAT_B_TO_BLK_ROUND_UP(ei->valid_size, sb);
+
+		if (iblock + max_blocks < valid_blks) {
+			/* The range has been written, map it */
+			goto done;
+		} else if (iblock < valid_blks) {
+			/*
+			 * The range has been partially written,
+			 * map the written part.
+			 */
+			max_blocks = valid_blks - iblock;
+			goto done;
+		}
+
+		/* The area has not been written, map and mark as new. */
 		err = exfat_map_new_buffer(ei, bh_result, pos);
 		if (err) {
 			exfat_fs_error(sb,
@@ -324,11 +340,55 @@ static int exfat_get_block(struct inode *inode, sector_t iblock,
 					pos, ei->i_size_aligned);
 			goto unlock_ret;
 		}
+	} else {
+		valid_blks = EXFAT_B_TO_BLK(ei->valid_size, sb);
+
+		if (iblock + max_blocks < valid_blks) {
+			/* The range has been written, map it */
+			goto done;
+		} else if (iblock < valid_blks) {
+			/*
+			 * The area has been partially written,
+			 * map the written part.
+			 */
+			max_blocks = valid_blks - iblock;
+			goto done;
+		} else if (iblock == valid_blks &&
+			   (ei->valid_size & (sb->s_blocksize - 1))) {
+			/*
+			 * The block has been partially written,
+			 * zero the unwritten part and map the block.
+			 */
+			loff_t size, off;
+
+			max_blocks = 1;
+
+			/*
+			 * For direct read, the unwritten part will be zeroed in
+			 * exfat_direct_IO()
+			 */
+			if (!bh_result->b_folio)
+				goto done;
+
+			pos -= sb->s_blocksize;
+			size = ei->valid_size - pos;
+			off = pos & (PAGE_SIZE - 1);
+
+			folio_set_bh(bh_result, bh_result->b_folio, off);
+			err = bh_read(bh_result, 0);
+			if (err < 0)
+				goto unlock_ret;
+
+			folio_zero_segment(bh_result->b_folio, off + size,
+					off + sb->s_blocksize);
+		} else {
+			/*
+			 * The range has not been written, clear the mapped flag
+			 * to only zero the cache and do not read from disk.
+			 */
+			clear_buffer_mapped(bh_result);
+		}
 	}
-
-	if (buffer_delay(bh_result))
-		clear_buffer_delay(bh_result);
-	map_bh(bh_result, sb, phys);
 done:
 	bh_result->b_size = EXFAT_BLK_TO_B(max_blocks, sb);
 unlock_ret:
@@ -343,6 +403,17 @@ static int exfat_read_folio(struct file *file, struct folio *folio)
 
 static void exfat_readahead(struct readahead_control *rac)
 {
+	struct address_space *mapping = rac->mapping;
+	struct inode *inode = mapping->host;
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	loff_t pos = readahead_pos(rac);
+
+	/* Range cross valid_size, read it page by page. */
+	if (ei->valid_size < i_size_read(inode) &&
+	    pos <= ei->valid_size &&
+	    ei->valid_size < pos + readahead_length(rac))
+		return;
+
 	mpage_readahead(rac, exfat_get_block);
 }
 
@@ -370,9 +441,7 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
-			       exfat_get_block,
-			       &EXFAT_I(mapping->host)->i_size_ondisk);
+	ret = block_write_begin(mapping, pos, len, pagep, exfat_get_block);
 
 	if (ret < 0)
 		exfat_write_failed(mapping, pos+len);
@@ -400,6 +469,11 @@ static int exfat_write_end(struct file *file, struct address_space *mapping,
 	if (err < len)
 		exfat_write_failed(mapping, pos+len);
 
+	if (!(err < 0) && pos + err > ei->valid_size) {
+		ei->valid_size = pos + err;
+		mark_inode_dirty(inode);
+	}
+
 	if (!(err < 0) && !(ei->attr & EXFAT_ATTR_ARCHIVE)) {
 		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 		ei->attr |= EXFAT_ATTR_ARCHIVE;
@@ -413,6 +487,8 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = mapping->host;
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	loff_t pos = iocb->ki_pos;
 	loff_t size = iocb->ki_pos + iov_iter_count(iter);
 	int rw = iov_iter_rw(iter);
 	ssize_t ret;
@@ -436,8 +512,21 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	 * condition of exfat_get_block() and ->truncate().
 	 */
 	ret = blockdev_direct_IO(iocb, inode, iter, exfat_get_block);
-	if (ret < 0 && (rw & WRITE))
-		exfat_write_failed(mapping, size);
+	if (ret < 0) {
+		if (rw == WRITE)
+			exfat_write_failed(mapping, size);
+
+		if (ret != -EIOCBQUEUED)
+			return ret;
+	} else
+		size = pos + ret;
+
+	/* zero the unwritten part in the partially written block */
+	if (rw == READ && pos < ei->valid_size && ei->valid_size < size) {
+		iov_iter_revert(iter, size - ei->valid_size);
+		iov_iter_zero(size - ei->valid_size, iter);
+	}
+
 	return ret;
 }
 
@@ -537,6 +626,7 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info)
 	ei->start_clu = info->start_clu;
 	ei->flags = info->flags;
 	ei->type = info->type;
+	ei->valid_size = info->valid_size;
 
 	ei->version = 0;
 	ei->hint_stat.eidx = 0;
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 5d737e0b639a1..9c549fd11fc84 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -406,6 +406,7 @@ static int exfat_find_empty_entry(struct inode *inode,
 		i_size_write(inode, size);
 		ei->i_size_ondisk += sbi->cluster_size;
 		ei->i_size_aligned += sbi->cluster_size;
+		ei->valid_size += sbi->cluster_size;
 		ei->flags = p_dir->flags;
 		inode->i_blocks += sbi->cluster_size >> 9;
 	}
@@ -558,6 +559,8 @@ static int exfat_add_entry(struct inode *inode, const char *path,
 		info->size = clu_size;
 		info->num_subdirs = EXFAT_MIN_SUBDIR;
 	}
+	info->valid_size = info->size;
+
 	memset(&info->crtime, 0, sizeof(info->crtime));
 	memset(&info->mtime, 0, sizeof(info->mtime));
 	memset(&info->atime, 0, sizeof(info->atime));
@@ -660,6 +663,8 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
 	info->type = exfat_get_entry_type(ep);
 	info->attr = le16_to_cpu(ep->dentry.file.attr);
 	info->size = le64_to_cpu(ep2->dentry.stream.valid_size);
+	info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size);
+	info->size = le64_to_cpu(ep2->dentry.stream.size);
 	if (info->size == 0) {
 		info->flags = ALLOC_NO_FAT_CHAIN;
 		info->start_clu = EXFAT_EOF_CLUSTER;
@@ -1288,6 +1293,7 @@ static int __exfat_rename(struct inode *old_parent_inode,
 			}
 
 			i_size_write(new_inode, 0);
+			new_ei->valid_size = 0;
 			new_ei->start_clu = EXFAT_EOF_CLUSTER;
 			new_ei->flags = ALLOC_NO_FAT_CHAIN;
 		}
-- 
GitLab


From f55c096f62f100aa9f5f48d86e1b6846ecbd67e7 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Tue, 30 May 2023 17:35:00 +0800
Subject: [PATCH 2350/4076] exfat: do not zero the extended part

Since the read operation beyond the ValidDataLength returns zero,
if we just extend the size of the file, we don't need to zero the
extended part, but only change the DataLength without changing
the ValidDataLength.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Andy Wu <Andy.Wu@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/file.c  | 77 +++++++++++++++++++++++++++++++++++-------------
 fs/exfat/inode.c | 14 ++++++++-
 2 files changed, 70 insertions(+), 21 deletions(-)

diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 270e2f934124e..d25a96a148af4 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -18,32 +18,69 @@
 
 static int exfat_cont_expand(struct inode *inode, loff_t size)
 {
-	struct address_space *mapping = inode->i_mapping;
-	loff_t start = i_size_read(inode), count = size - i_size_read(inode);
-	int err, err2;
+	int ret;
+	unsigned int num_clusters, new_num_clusters, last_clu;
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	struct super_block *sb = inode->i_sb;
+	struct exfat_sb_info *sbi = EXFAT_SB(sb);
+	struct exfat_chain clu;
 
-	err = generic_cont_expand_simple(inode, size);
-	if (err)
-		return err;
+	ret = inode_newsize_ok(inode, size);
+	if (ret)
+		return ret;
+
+	num_clusters = EXFAT_B_TO_CLU_ROUND_UP(ei->i_size_ondisk, sbi);
+	new_num_clusters = EXFAT_B_TO_CLU_ROUND_UP(size, sbi);
+
+	if (new_num_clusters == num_clusters)
+		goto out;
+
+	exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags);
+	ret = exfat_find_last_cluster(sb, &clu, &last_clu);
+	if (ret)
+		return ret;
 
+	clu.dir = (last_clu == EXFAT_EOF_CLUSTER) ?
+			EXFAT_EOF_CLUSTER : last_clu + 1;
+	clu.size = 0;
+	clu.flags = ei->flags;
+
+	ret = exfat_alloc_cluster(inode, new_num_clusters - num_clusters,
+			&clu, IS_DIRSYNC(inode));
+	if (ret)
+		return ret;
+
+	/* Append new clusters to chain */
+	if (clu.flags != ei->flags) {
+		exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters);
+		ei->flags = ALLOC_FAT_CHAIN;
+	}
+	if (clu.flags == ALLOC_FAT_CHAIN)
+		if (exfat_ent_set(sb, last_clu, clu.dir))
+			goto free_clu;
+
+	if (num_clusters == 0)
+		ei->start_clu = clu.dir;
+
+out:
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
-	EXFAT_I(inode)->valid_size = size;
-	mark_inode_dirty(inode);
+	/* Expanded range not zeroed, do not update valid_size */
+	i_size_write(inode, size);
 
-	if (!IS_SYNC(inode))
-		return 0;
+	ei->i_size_aligned = round_up(size, sb->s_blocksize);
+	ei->i_size_ondisk = ei->i_size_aligned;
+	inode->i_blocks = round_up(size, sbi->cluster_size) >> 9;
 
-	err = filemap_fdatawrite_range(mapping, start, start + count - 1);
-	err2 = sync_mapping_buffers(mapping);
-	if (!err)
-		err = err2;
-	err2 = write_inode_now(inode, 1);
-	if (!err)
-		err = err2;
-	if (err)
-		return err;
+	if (IS_DIRSYNC(inode))
+		return write_inode_now(inode, 1);
+
+	mark_inode_dirty(inode);
+
+	return 0;
 
-	return filemap_fdatawait_range(mapping, start, start + count - 1);
+free_clu:
+	exfat_free_cluster(inode, &clu);
+	return -EIO;
 }
 
 static bool exfat_allow_set_time(struct exfat_sb_info *sbi, struct inode *inode)
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index b02677c9fd459..522edcbb2ce4d 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -75,8 +75,17 @@ int __exfat_write_inode(struct inode *inode, int sync)
 	if (ei->start_clu == EXFAT_EOF_CLUSTER)
 		on_disk_size = 0;
 
-	ep2->dentry.stream.valid_size = cpu_to_le64(ei->valid_size);
 	ep2->dentry.stream.size = cpu_to_le64(on_disk_size);
+	/*
+	 * mmap write does not use exfat_write_end(), valid_size may be
+	 * extended to the sector-aligned length in exfat_get_block().
+	 * So we need to fixup valid_size to the writren length.
+	 */
+	if (on_disk_size < ei->valid_size)
+		ep2->dentry.stream.valid_size = ep2->dentry.stream.size;
+	else
+		ep2->dentry.stream.valid_size = cpu_to_le64(ei->valid_size);
+
 	if (on_disk_size) {
 		ep2->dentry.stream.flags = ei->flags;
 		ep2->dentry.stream.start_clu = cpu_to_le32(ei->start_clu);
@@ -340,6 +349,9 @@ static int exfat_get_block(struct inode *inode, sector_t iblock,
 					pos, ei->i_size_aligned);
 			goto unlock_ret;
 		}
+
+		ei->valid_size = EXFAT_BLK_TO_B(iblock + max_blocks, sb);
+		mark_inode_dirty(inode);
 	} else {
 		valid_blks = EXFAT_B_TO_BLK(ei->valid_size, sb);
 
-- 
GitLab


From caadf876bb7449bf25ef817afe7fb881df8198a2 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 4 Jan 2024 11:15:07 -0500
Subject: [PATCH 2351/4076] KVM: introduce CONFIG_KVM_COMMON

CONFIG_HAVE_KVM is currently used by some architectures to either
enabled the KVM config proper, or to enable host-side code that is
not part of the KVM module.  However, CONFIG_KVM's "select" statement
in virt/kvm/Kconfig corresponds to a third meaning, namely to
enable common Kconfigs required by all architectures that support
KVM.

These three meanings can be replaced respectively by an
architecture-specific Kconfig, by IS_ENABLED(CONFIG_KVM), or by
a new Kconfig symbol that is in turn selected by the
architecture-specific "config KVM".

Start by introducing such a new Kconfig symbol, CONFIG_KVM_COMMON.
Unlike CONFIG_HAVE_KVM, it is selected by CONFIG_KVM, not by
architecture code, and it brings in all dependencies of common
KVM code.  In particular, INTERVAL_TREE was missing in loongarch
and riscv, so that is another thing that is fixed.

Fixes: 8132d887a702 ("KVM: remove CONFIG_HAVE_KVM_EVENTFD", 2023-12-08)
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Closes: https://lore.kernel.org/all/44907c6b-c5bd-4e4a-a921-e4d3825539d8@infradead.org/
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/Kconfig     | 3 +--
 arch/loongarch/kvm/Kconfig | 2 +-
 arch/mips/kvm/Kconfig      | 3 +--
 arch/powerpc/kvm/Kconfig   | 3 +--
 arch/riscv/kvm/Kconfig     | 2 +-
 arch/s390/kvm/Kconfig      | 3 +--
 arch/x86/kvm/Kconfig       | 3 +--
 virt/kvm/Kconfig           | 5 +++++
 8 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index b07c60c9737dc..6c3c8ca73e7fd 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,9 +21,9 @@ if VIRTUALIZATION
 menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
+	select KVM_COMMON
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_GENERIC_MMU_NOTIFIER
-	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
@@ -39,7 +39,6 @@ menuconfig KVM
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
-	select INTERVAL_TREE
 	select XARRAY_MULTI
 	help
 	  Support hosting virtualized guest machines.
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index daba4cd5e87d1..61f7e33b1f957 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -23,12 +23,12 @@ config KVM
 	depends on HAVE_KVM
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
+	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
-	select PREEMPT_NOTIFIERS
 	help
 	  Support hosting virtualized guest machines using
 	  hardware virtualization extensions. You will need
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index 428141b0b48f5..18e7a17d51158 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -20,12 +20,11 @@ config KVM
 	depends on HAVE_KVM
 	depends on MIPS_FP_SUPPORT
 	select EXPORT_UASM
-	select PREEMPT_NOTIFIERS
+	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_MMIO
 	select KVM_GENERIC_MMU_NOTIFIER
-	select INTERVAL_TREE
 	select KVM_GENERIC_HARDWARE_ENABLING
 	help
 	  Support for hosting Guest kernels.
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index b47196085a42d..074263429faf2 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -19,12 +19,11 @@ if VIRTUALIZATION
 
 config KVM
 	bool
-	select PREEMPT_NOTIFIERS
+	select KVM_COMMON
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_VFIO
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
-	select INTERVAL_TREE
 
 config KVM_BOOK3S_HANDLER
 	bool
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index 1fd76aee3b719..d490db9438588 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -24,12 +24,12 @@ config KVM
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
+	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_GENERIC_MMU_NOTIFIER
-	select PREEMPT_NOTIFIERS
 	select SCHED_INFO
 	help
 	  Support hosting virtualized guest machines.
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index bb6d903511194..72e9b7dcdf7d9 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -20,17 +20,16 @@ config KVM
 	def_tristate y
 	prompt "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
-	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_ASYNC_PF
 	select KVM_ASYNC_PF_SYNC
+	select KVM_COMMON
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_INVALID_WAKEUPS
 	select HAVE_KVM_NO_POLL
 	select KVM_VFIO
-	select INTERVAL_TREE
 	select MMU_NOTIFIER
 	help
 	  Support hosting paravirtualized guest machines using the SIE
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b07247b0b958e..cce3dea279206 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -23,7 +23,7 @@ config KVM
 	depends on HAVE_KVM
 	depends on HIGH_RES_TIMERS
 	depends on X86_LOCAL_APIC
-	select PREEMPT_NOTIFIERS
+	select KVM_COMMON
 	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
@@ -44,7 +44,6 @@ config KVM
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_VFIO
-	select INTERVAL_TREE
 	select HAVE_KVM_PM_NOTIFIER if PM
 	select KVM_GENERIC_HARDWARE_ENABLING
 	help
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 6793211a0b642..ace72be98fb20 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -3,7 +3,12 @@
 
 config HAVE_KVM
        bool
+
+config KVM_COMMON
+       bool
        select EVENTFD
+       select INTERVAL_TREE
+       select PREEMPT_NOTIFIERS
 
 config HAVE_KVM_PFNCACHE
        bool
-- 
GitLab


From 3a373e027d8b0ed14963cc84b48a11e69e4506b6 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sat, 6 Jan 2024 02:24:00 -0500
Subject: [PATCH 2352/4076] KVM: fix direction of dependency on MMU notifiers

KVM_GENERIC_MEMORY_ATTRIBUTES requires the generic MMU notifier code, because
it uses kvm_mmu_invalidate_begin/end.  However, it would not work with a bespoke
implementation of MMU notifiers that does not use KVM_GENERIC_MMU_NOTIFIER,
because most likely it would not synchronize correctly on invalidation.  So
the right thing to do is to note the problematic configuration if the
architecture does not select itself KVM_GENERIC_MMU_NOTIFIER; not to
enable it blindly.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index ace72be98fb20..184dab4ee871c 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -97,7 +97,7 @@ config KVM_GENERIC_MMU_NOTIFIER
        bool
 
 config KVM_GENERIC_MEMORY_ATTRIBUTES
-       select KVM_GENERIC_MMU_NOTIFIER
+       depends on KVM_GENERIC_MMU_NOTIFIER
        bool
 
 config KVM_PRIVATE_MEM
-- 
GitLab


From 783288010035e4c250a0b6491a4642cdb8d30548 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 8 Jan 2024 07:51:26 -0500
Subject: [PATCH 2353/4076] KVM: x86: add missing "depends on KVM"

Support for KVM software-protected VMs should not be configurable,
if KVM is not available at all.

Fixes: 89ea60c2c7b5 ("KVM: x86: Add support for "protected VMs" that can utilize private memory")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index cce3dea279206..10c56603cc060 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -77,7 +77,7 @@ config KVM_WERROR
 config KVM_SW_PROTECTED_VM
 	bool "Enable support for KVM software-protected VMs"
 	depends on EXPERT
-	depends on X86_64
+	depends on KVM && X86_64
 	select KVM_GENERIC_PRIVATE_MEM
 	help
 	  Enable support for KVM software-protected VMs.  Currently "protected"
-- 
GitLab


From 83303a4c776ce1032d88df59e811183479acea77 Mon Sep 17 00:00:00 2001
From: Eric Farman <farman@linux.ibm.com>
Date: Fri, 1 Dec 2023 19:16:57 +0100
Subject: [PATCH 2354/4076] KVM: s390: fix cc for successful PQAP

The various errors that are possible when processing a PQAP
instruction (the absence of a driver hook, an error FROM that
hook), all correctly set the PSW condition code to 3. But if
that processing works successfully, CC0 needs to be set to
convey that everything was fine.

Fix the check so that the guest can examine the condition code
to determine whether GPR1 has meaningful data.

Fixes: e5282de93105 ("s390: ap: kvm: add PQAP interception for AQIC")
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Link: https://lore.kernel.org/r/20231201181657.1614645-1-farman@linux.ibm.com
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Message-Id: <20231201181657.1614645-1-farman@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
---
 arch/s390/kvm/priv.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 621a17fd1a1bb..f875a404a0a02 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -676,8 +676,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
 	if (vcpu->kvm->arch.crypto.pqap_hook) {
 		pqap_hook = *vcpu->kvm->arch.crypto.pqap_hook;
 		ret = pqap_hook(vcpu);
-		if (!ret && vcpu->run->s.regs.gprs[1] & 0x00ff0000)
-			kvm_s390_set_psw_cc(vcpu, 3);
+		if (!ret) {
+			if (vcpu->run->s.regs.gprs[1] & 0x00ff0000)
+				kvm_s390_set_psw_cc(vcpu, 3);
+			else
+				kvm_s390_set_psw_cc(vcpu, 0);
+		}
 		up_read(&vcpu->kvm->arch.crypto.pqap_hook_rwsem);
 		return ret;
 	}
-- 
GitLab


From 1c6d984f523f67ecfad1083bb04c55d91977bb15 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 5 Dec 2023 03:45:01 +0300
Subject: [PATCH 2355/4076] x86/kvm: Do not try to disable kvmclock if it was
 not enabled

kvm_guest_cpu_offline() tries to disable kvmclock regardless if it is
present in the VM. It leads to write to a MSR that doesn't exist on some
configurations, namely in TDX guest:

	unchecked MSR access error: WRMSR to 0x12 (tried to write 0x0000000000000000)
	at rIP: 0xffffffff8110687c (kvmclock_disable+0x1c/0x30)

kvmclock enabling is gated by CLOCKSOURCE and CLOCKSOURCE2 KVM paravirt
features.

Do not disable kvmclock if it was not enabled.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Fixes: c02027b5742b ("x86/kvm: Disable kvmclock on all CPUs on shutdown")
Reviewed-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Cc: stable@vger.kernel.org
Message-Id: <20231205004510.27164-6-kirill.shutemov@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kernel/kvmclock.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index fb8f52149be9a..f2fff625576d5 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -24,8 +24,8 @@
 
 static int kvmclock __initdata = 1;
 static int kvmclock_vsyscall __initdata = 1;
-static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
-static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
+static int msr_kvm_system_time __ro_after_init;
+static int msr_kvm_wall_clock __ro_after_init;
 static u64 kvm_sched_clock_offset __ro_after_init;
 
 static int __init parse_no_kvmclock(char *arg)
@@ -195,7 +195,8 @@ static void kvm_setup_secondary_clock(void)
 
 void kvmclock_disable(void)
 {
-	native_write_msr(msr_kvm_system_time, 0, 0);
+	if (msr_kvm_system_time)
+		native_write_msr(msr_kvm_system_time, 0, 0);
 }
 
 static void __init kvmclock_init_mem(void)
@@ -294,7 +295,10 @@ void __init kvmclock_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
 		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
 		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
-	} else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
+	} else if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
+		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
+	} else {
 		return;
 	}
 
-- 
GitLab


From 2324be17b5e05ac682e7c81fcbfc7b36a9b1becb Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Mon, 30 Oct 2023 00:27:57 -0700
Subject: [PATCH 2356/4076] PCI: xilinx-xdma: Fix error code in
 xilinx_pl_dma_pcie_init_irq_domain()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, if the function irq_domain_add_linear() fails to allocate
a new IRQ domain and returns NULL, we would then still return a success
from the xilinx_pl_dma_pcie_init_irq_domain() function regardless, as
the PTR_ERR(NULL) would return a value of zero.  This is not a desirable
outcome.

Thus, fix the incorrect error code and return the -ENOMEM error code if
the irq_domain_add_linear() fails to allocate a new IRQ domain.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20231030072757.3236546-1-harshit.m.mogalapalli@oracle.com
Fixes: 8d786149d78c ("PCI: xilinx-xdma: Add Xilinx XDMA Root Port driver")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/pcie-xilinx-dma-pl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-xilinx-dma-pl.c b/drivers/pci/controller/pcie-xilinx-dma-pl.c
index 9c79754dc8fab..5be5dfd8398f2 100644
--- a/drivers/pci/controller/pcie-xilinx-dma-pl.c
+++ b/drivers/pci/controller/pcie-xilinx-dma-pl.c
@@ -576,7 +576,7 @@ static int xilinx_pl_dma_pcie_init_irq_domain(struct pl_dma_pcie *port)
 						  &intx_domain_ops, port);
 	if (!port->intx_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
-		return PTR_ERR(port->intx_domain);
+		return -ENOMEM;
 	}
 
 	irq_domain_update_bus_token(port->intx_domain, DOMAIN_BUS_WIRED);
-- 
GitLab


From 172fb49600c2b96a4ade255fbfc3fe7098b8afd3 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 6 Dec 2023 10:48:30 -0800
Subject: [PATCH 2357/4076] nvme-pci: enhance timeout kernel log

Kernel configs don't necessarily have opcode decoding, and some opcodes
are not even decodable. It is still interesting for debugging SSD issues
to know what opcode is timing out, what request type it came from, and
the data size (if applicable).

Also print the command_id along side blk-mq's tag to help match commands
with protocol wire traces and firmware logs,

Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index f272026807419..75e763ce09aa0 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1284,6 +1284,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	struct request *abort_req;
 	struct nvme_command cmd = { };
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
+	u8 opcode;
 
 	/* If PCI error recovery process is happening, we cannot reset or
 	 * the recovery mechanism will surely fail.
@@ -1310,8 +1311,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 
 	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, completion polled\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, completion polled\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		return BLK_EH_DONE;
 	}
 
@@ -1327,8 +1328,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 		fallthrough;
 	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
-			 "I/O %d QID %d timeout, disable controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, disable controller\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
@@ -1343,10 +1344,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * command was already aborted once before and still hasn't been
 	 * returned to the driver, or if this is the admin queue.
 	 */
+	opcode = nvme_req(req)->cmd->common.opcode;
 	if (!nvmeq->qid || iod->aborted) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, reset controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n",
+			 req->tag, nvme_cid(req), opcode,
+			 nvme_opcode_str(nvmeq->qid, opcode, 0), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		goto disable;
 	}
@@ -1362,10 +1365,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
 
 	dev_warn(nvmeq->dev->ctrl.device,
-		"I/O %d (%s) QID %d timeout, aborting\n",
-		 req->tag,
-		 nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode),
-		 nvmeq->qid);
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, aborting req_op:%s(%u) size:%u\n",
+		 req->tag, nvme_cid(req), opcode, nvme_get_opcode_str(opcode),
+		 nvmeq->qid, blk_op_str(req_op(req)), req_op(req),
+		 blk_rq_bytes(req));
 
 	abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd),
 					 BLK_MQ_REQ_NOWAIT);
-- 
GitLab


From a5c1a87ce0876192d4343cdf5f0a22d737eb0ec3 Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <mgurtovoy@nvidia.com>
Date: Sun, 7 Jan 2024 02:29:49 +0200
Subject: [PATCH 2358/4076] nvme-rdma: enhance timeout kernel log

Print the command_id along side blk-mq's tag to help match commands with
protocol wire traces and logs.

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/rdma.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index bc90ec3c51b07..2e77c0f25f710 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1941,9 +1941,14 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
-
-	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
-		 rq->tag, nvme_rdma_queue_idx(queue));
+	u8 opcode = req->req.cmd->common.opcode;
+	u8 fctype = req->req.cmd->fabrics.fctype;
+	int qid = nvme_rdma_queue_idx(queue);
+
+	dev_warn(ctrl->ctrl.device,
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), opcode,
+		 nvme_opcode_str(qid, opcode, fctype), qid);
 
 	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
 		/*
-- 
GitLab


From 45c36f04f1beb7c4c45f5910a1f69d6d9d5a19fb Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <mgurtovoy@nvidia.com>
Date: Sun, 7 Jan 2024 02:29:50 +0200
Subject: [PATCH 2359/4076] nvme-tcp: enhance timeout kernel log

Print the command_id along side blk-mq's tag to help match commands with
protocol wire traces and logs.

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 5056bcae2f391..b234f0674aebb 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2425,9 +2425,9 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 	int qid = nvme_tcp_queue_id(req->queue);
 
 	dev_warn(ctrl->device,
-		"queue %d: timeout cid %#x type %d opcode %#x (%s)\n",
-		nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type,
-		opc, nvme_opcode_str(qid, opc, fctype));
+		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), pdu->hdr.type, opc,
+		 nvme_opcode_str(qid, opc, fctype), qid);
 
 	if (ctrl->state != NVME_CTRL_LIVE) {
 		/*
-- 
GitLab


From 9a1abc24850eb759e36a2f8869161c3b7254c904 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Fri, 5 Jan 2024 09:14:44 +0100
Subject: [PATCH 2360/4076] nvmet-tcp: Fix the H2C expected PDU len calculation

The nvmet_tcp_handle_h2c_data_pdu() function should take into
consideration the possibility that the header digest and/or the data
digests are enabled when calculating the expected PDU length, before
comparing it to the value stored in cmd->pdu_len.

Fixes: efa56305908b ("nvmet-tcp: Fix a kernel panic when host sends an invalid H2C PDU length")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 792828fb91ccf..4dc60cbcb205b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -979,7 +979,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 {
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
-	unsigned int plen;
+	unsigned int exp_data_len;
 
 	if (likely(queue->nr_cmds)) {
 		if (unlikely(data->ttag >= queue->nr_cmds)) {
@@ -999,9 +999,13 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 		goto err_proto;
 	}
 
-	plen = le32_to_cpu(data->hdr.plen);
+	exp_data_len = le32_to_cpu(data->hdr.plen) -
+			nvmet_tcp_hdgst_len(queue) -
+			nvmet_tcp_ddgst_len(queue) -
+			sizeof(*data);
+
 	cmd->pdu_len = le32_to_cpu(data->data_length);
-	if (unlikely(cmd->pdu_len != (plen - sizeof(*data)) ||
+	if (unlikely(cmd->pdu_len != exp_data_len ||
 		     cmd->pdu_len == 0 ||
 		     cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) {
 		pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len);
-- 
GitLab


From 4f1991a92cfe89096b2d1f5583a2e093bdd55c37 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Sun, 7 Jan 2024 20:32:58 -0500
Subject: [PATCH 2361/4076] tracing histograms: Simplify parse_actions()
 function

The parse_actions() function uses 'len = str_has_prefix()' to test which
action is in the string being parsed. But then it goes and repeats the
logic for each different action. This logic can be simplified and
duplicate code can be removed as 'len' contains the length of the found
prefix which should be used for all actions.

Link: https://lore.kernel.org/all/20240107112044.6702cb66@gandalf.local.home/
Link: https://lore.kernel.org/linux-trace-kernel/20240107203258.37e26d2b@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andy Shevchenko <andy@kernel.org>
Cc: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 49 ++++++++++++++++----------------
 1 file changed, 24 insertions(+), 25 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 5ecf3c8bde205..6ece1308d36a0 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4805,36 +4805,35 @@ static int parse_actions(struct hist_trigger_data *hist_data)
 	int len;
 
 	for (i = 0; i < hist_data->attrs->n_actions; i++) {
+		enum handler_id hid = 0;
+		char *action_str;
+
 		str = hist_data->attrs->action_str[i];
 
-		if ((len = str_has_prefix(str, "onmatch("))) {
-			char *action_str = str + len;
+		if ((len = str_has_prefix(str, "onmatch(")))
+			hid = HANDLER_ONMATCH;
+		else if ((len = str_has_prefix(str, "onmax(")))
+			hid = HANDLER_ONMAX;
+		else if ((len = str_has_prefix(str, "onchange(")))
+			hid = HANDLER_ONCHANGE;
 
-			data = onmatch_parse(tr, action_str);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else if ((len = str_has_prefix(str, "onmax("))) {
-			char *action_str = str + len;
+		action_str = str + len;
 
-			data = track_data_parse(hist_data, action_str,
-						HANDLER_ONMAX);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else if ((len = str_has_prefix(str, "onchange("))) {
-			char *action_str = str + len;
+		switch (hid) {
+		case HANDLER_ONMATCH:
+			data = onmatch_parse(tr, action_str);
+			break;
+		case HANDLER_ONMAX:
+		case HANDLER_ONCHANGE:
+			data = track_data_parse(hist_data, action_str, hid);
+			break;
+		default:
+			data = ERR_PTR(-EINVAL);
+			break;
+		}
 
-			data = track_data_parse(hist_data, action_str,
-						HANDLER_ONCHANGE);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else {
-			ret = -EINVAL;
+		if (IS_ERR(data)) {
+			ret = PTR_ERR(data);
 			break;
 		}
 
-- 
GitLab


From 3b7cb745473aec7255d66e3854abaa9c3f46f952 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 8 Jan 2024 11:50:16 -0700
Subject: [PATCH 2362/4076] block: move __get_task_ioprio() into header file

We call this once per IO, which can be millions of times per second.
Since nobody really uses io priorities, or at least it isn't very
common, this is all wasted time and can amount to as much as 3% of
the total kernel time.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioprio.c         | 26 --------------------------
 include/linux/ioprio.h | 25 ++++++++++++++++++++++++-
 2 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/block/ioprio.c b/block/ioprio.c
index b5a942519a797..73301a261429f 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -139,32 +139,6 @@ out:
 	return ret;
 }
 
-/*
- * If the task has set an I/O priority, use that. Otherwise, return
- * the default I/O priority.
- *
- * Expected to be called for current task or with task_lock() held to keep
- * io_context stable.
- */
-int __get_task_ioprio(struct task_struct *p)
-{
-	struct io_context *ioc = p->io_context;
-	int prio;
-
-	if (p != current)
-		lockdep_assert_held(&p->alloc_lock);
-	if (ioc)
-		prio = ioc->ioprio;
-	else
-		prio = IOPRIO_DEFAULT;
-
-	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
-		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
-					 task_nice_ioprio(p));
-	return prio;
-}
-EXPORT_SYMBOL_GPL(__get_task_ioprio);
-
 static int get_task_ioprio(struct task_struct *p)
 {
 	int ret;
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index 7578d4f6a969a..d6a9b5b7ed167 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -47,7 +47,30 @@ static inline int task_nice_ioclass(struct task_struct *task)
 }
 
 #ifdef CONFIG_BLOCK
-int __get_task_ioprio(struct task_struct *p);
+/*
+ * If the task has set an I/O priority, use that. Otherwise, return
+ * the default I/O priority.
+ *
+ * Expected to be called for current task or with task_lock() held to keep
+ * io_context stable.
+ */
+static inline int __get_task_ioprio(struct task_struct *p)
+{
+	struct io_context *ioc = p->io_context;
+	int prio;
+
+	if (p != current)
+		lockdep_assert_held(&p->alloc_lock);
+	if (ioc)
+		prio = ioc->ioprio;
+	else
+		prio = IOPRIO_DEFAULT;
+
+	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
+		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
+					 task_nice_ioprio(p));
+	return prio;
+}
 #else
 static inline int __get_task_ioprio(struct task_struct *p)
 {
-- 
GitLab


From 53889bcaf536b3abedeaf104019877cee37dd08b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 8 Jan 2024 11:51:57 -0700
Subject: [PATCH 2363/4076] block: make __get_task_ioprio() easier to read

We don't need to do any gymnastics if we don't have an io_context
assigned at all, so just return early with our default priority.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/ioprio.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index d6a9b5b7ed167..db1249cd96920 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -59,13 +59,13 @@ static inline int __get_task_ioprio(struct task_struct *p)
 	struct io_context *ioc = p->io_context;
 	int prio;
 
+	if (!ioc)
+		return IOPRIO_DEFAULT;
+
 	if (p != current)
 		lockdep_assert_held(&p->alloc_lock);
-	if (ioc)
-		prio = ioc->ioprio;
-	else
-		prio = IOPRIO_DEFAULT;
 
+	prio = ioc->ioprio;
 	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
 		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
 					 task_nice_ioprio(p));
-- 
GitLab


From d988c9f511af71a3445b6a4f3a2c67208ff8e480 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 8 Jan 2024 17:11:13 -0300
Subject: [PATCH 2364/4076] MAINTAINERS: Add Namhyung as tools/perf/
 co-maintainer

Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/lkml/ZZxbCeVPnOjShbMQ@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9104430e148e6..041ef848d7369 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16896,10 +16896,10 @@ PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
+M:	Namhyung Kim <namhyung@kernel.org>
 R:	Mark Rutland <mark.rutland@arm.com>
 R:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 R:	Jiri Olsa <jolsa@kernel.org>
-R:	Namhyung Kim <namhyung@kernel.org>
 R:	Ian Rogers <irogers@google.com>
 R:	Adrian Hunter <adrian.hunter@intel.com>
 L:	linux-perf-users@vger.kernel.org
-- 
GitLab


From 4d4e1b6319e5c4425ea3faeaf9a10b8b4c16c1e1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?=
 <nfraprado@collabora.com>
Date: Mon, 8 Jan 2024 17:44:58 -0300
Subject: [PATCH 2365/4076] ASoC: mediatek: mt8192: Check existence of dai_name
 before dereferencing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Following commit 13f58267cda3 ("ASoC: soc.h: don't create dummy
Component via COMP_DUMMY()"), the dai_name field is only populated for
dummy components after the card is registered. This causes a null
pointer dereference in the mt8192-mt6359 sound card driver's probe
function when searching for a dai_name among all the card's dai links.

Verify that the dai_name is non-null before passing it to strcmp. While
at it, also check that there's at least one codec.

Reported-by: kernelci.org bot <bot@kernelci.org>
Closes: https://linux.kernelci.org/test/case/id/6582cd6d992645c680e13478/
Fixes: 13f58267cda3 ("ASoC: soc.h: don't create dummy Component via COMP_DUMMY()")
Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Link: https://msgid.link/r/20240108204508.691739-1-nfraprado@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c b/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c
index 5bd6addd14505..bfcb2c486c39d 100644
--- a/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c
+++ b/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c
@@ -1208,7 +1208,8 @@ static int mt8192_mt6359_dev_probe(struct platform_device *pdev)
 			dai_link->ignore = 0;
 		}
 
-		if (strcmp(dai_link->codecs[0].dai_name, RT1015_CODEC_DAI) == 0)
+		if (dai_link->num_codecs && dai_link->codecs[0].dai_name &&
+		    strcmp(dai_link->codecs[0].dai_name, RT1015_CODEC_DAI) == 0)
 			dai_link->ops = &mt8192_rt1015_i2s_ops;
 
 		if (!dai_link->platforms->name)
-- 
GitLab


From 024b32db43a359e0ded3fcc6cd86247cbbed4224 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Thu, 21 Dec 2023 13:55:48 -0800
Subject: [PATCH 2366/4076] drm/bridge: parade-ps8640: Wait for HPD when doing
 an AUX transfer

Unlike what is claimed in commit f5aa7d46b0ee ("drm/bridge:
parade-ps8640: Provide wait_hpd_asserted() in struct drm_dp_aux"), if
someone manually tries to do an AUX transfer (like via `i2cdump ${bus}
0x50 i`) while the panel is off we don't just get a simple transfer
error. Instead, the whole ps8640 gets thrown for a loop and goes into
a bad state.

Let's put the function to wait for the HPD (and the magical 50 ms
after first reset) back in when we're doing an AUX transfer. This
shouldn't actually make things much slower (assuming the panel is on)
because we should immediately poll and see the HPD high. Mostly this
is just an extra i2c transfer to the bridge.

Fixes: f5aa7d46b0ee ("drm/bridge: parade-ps8640: Provide wait_hpd_asserted() in struct drm_dp_aux")
Tested-by: Pin-yen Lin <treapking@chromium.org>
Reviewed-by: Pin-yen Lin <treapking@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231221135548.1.I10f326a9305d57ad32cee7f8d9c60518c8be20fb@changeid
---
 drivers/gpu/drm/bridge/parade-ps8640.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c
index 541e4f5afc4c8..fb5e9ae9ad81d 100644
--- a/drivers/gpu/drm/bridge/parade-ps8640.c
+++ b/drivers/gpu/drm/bridge/parade-ps8640.c
@@ -346,6 +346,11 @@ static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux,
 	int ret;
 
 	pm_runtime_get_sync(dev);
+	ret = _ps8640_wait_hpd_asserted(ps_bridge, 200 * 1000);
+	if (ret) {
+		pm_runtime_put_sync_suspend(dev);
+		return ret;
+	}
 	ret = ps8640_aux_transfer_msg(aux, msg);
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
-- 
GitLab


From 571c7ed0baa928447bac29ef79a90bd6525d1ebc Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 13 Dec 2023 16:42:01 -0600
Subject: [PATCH 2367/4076] dt-bindings: display: samsung,exynos-mixer: Fix
 'regs' typo

The correct property name is 'reg' not 'regs'.

Fixes: 68e89bb36d58 ("dt-bindings: display: samsung,exynos-mixer: convert to dtschema")
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 .../bindings/display/samsung/samsung,exynos-mixer.yaml      | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml
index 25d53fde92e11..597c9cc6a312a 100644
--- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml
+++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml
@@ -85,7 +85,7 @@ allOf:
         clocks:
           minItems: 6
           maxItems: 6
-        regs:
+        reg:
           minItems: 2
           maxItems: 2
 
@@ -99,7 +99,7 @@ allOf:
         clocks:
           minItems: 4
           maxItems: 4
-        regs:
+        reg:
           minItems: 2
           maxItems: 2
 
@@ -116,7 +116,7 @@ allOf:
         clocks:
           minItems: 3
           maxItems: 3
-        regs:
+        reg:
           minItems: 1
           maxItems: 1
 
-- 
GitLab


From c12ca110c613a81cb0f0099019c839d078cd0f38 Mon Sep 17 00:00:00 2001
From: Siddharth Vadapalli <s-vadapalli@ti.com>
Date: Wed, 27 Sep 2023 09:48:45 +0530
Subject: [PATCH 2368/4076] PCI: keystone: Fix race condition when initializing
 PHYs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PCI driver invokes the PHY APIs using the ks_pcie_enable_phy()
function. The PHY in this case is the Serdes. It is possible that the
PCI instance is configured for two lane operation across two different
Serdes instances, using one lane of each Serdes.

In such a configuration, if the reference clock for one Serdes is
provided by the other Serdes, it results in a race condition. After the
Serdes providing the reference clock is initialized by the PCI driver by
invoking its PHY APIs, it is not guaranteed that this Serdes remains
powered on long enough for the PHY APIs based initialization of the
dependent Serdes. In such cases, the PLL of the dependent Serdes fails
to lock due to the absence of the reference clock from the former Serdes
which has been powered off by the PM Core.

Fix this by obtaining reference to the PHYs before invoking the PHY
initialization APIs and releasing reference after the initialization is
complete.

Link: https://lore.kernel.org/linux-pci/20230927041845.1222080-1-s-vadapalli@ti.com
Fixes: 49229238ab47 ("PCI: keystone: Cleanup PHY handling")
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Acked-by: Ravi Gunasekaran <r-gunasekaran@ti.com>
---
 drivers/pci/controller/dwc/pci-keystone.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 0def919f89faf..cf3836561316d 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -1218,7 +1218,16 @@ static int ks_pcie_probe(struct platform_device *pdev)
 		goto err_link;
 	}
 
+	/* Obtain references to the PHYs */
+	for (i = 0; i < num_lanes; i++)
+		phy_pm_runtime_get_sync(ks_pcie->phy[i]);
+
 	ret = ks_pcie_enable_phy(ks_pcie);
+
+	/* Release references to the PHYs */
+	for (i = 0; i < num_lanes; i++)
+		phy_pm_runtime_put_sync(ks_pcie->phy[i]);
+
 	if (ret) {
 		dev_err(dev, "failed to enable phy\n");
 		goto err_link;
-- 
GitLab


From 8ead196be219adade3bd0d4115cc9b8506643121 Mon Sep 17 00:00:00 2001
From: Gaosheng Cui <cuigaosheng1@huawei.com>
Date: Fri, 5 Jan 2024 10:01:26 +0800
Subject: [PATCH 2369/4076] apparmor: Fix memory leak in unpack_profile()

The aa_put_pdb(rules->file) should be called when rules->file is
reassigned, otherwise there may be a memory leak.

This was found via kmemleak:

unreferenced object 0xffff986c17056600 (size 192):
  comm "apparmor_parser", pid 875, jiffies 4294893488
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 89 14 04 6c 98 ff ff  ............l...
    00 00 8c 11 6c 98 ff ff bc 0c 00 00 00 00 00 00  ....l...........
  backtrace (crc e28c80c4):
    [<ffffffffba25087f>] kmemleak_alloc+0x4f/0x90
    [<ffffffffb95ecd42>] kmalloc_trace+0x2d2/0x340
    [<ffffffffb98a7b3d>] aa_alloc_pdb+0x4d/0x90
    [<ffffffffb98ab3b8>] unpack_pdb+0x48/0x660
    [<ffffffffb98ac073>] unpack_profile+0x693/0x1090
    [<ffffffffb98acf5a>] aa_unpack+0x10a/0x6e0
    [<ffffffffb98a93e3>] aa_replace_profiles+0xa3/0x1210
    [<ffffffffb989a183>] policy_update+0x163/0x2a0
    [<ffffffffb989a381>] profile_replace+0xb1/0x130
    [<ffffffffb966cb64>] vfs_write+0xd4/0x3d0
    [<ffffffffb966d05b>] ksys_write+0x6b/0xf0
    [<ffffffffb966d10e>] __x64_sys_write+0x1e/0x30
    [<ffffffffba242316>] do_syscall_64+0x76/0x120
    [<ffffffffba4000e5>] entry_SYSCALL_64_after_hwframe+0x6c/0x74

So add aa_put_pdb(rules->file) to fix it when rules->file is reassigned.

Fixes: 98b824ff8984 ("apparmor: refcount the pdb")
Signed-off-by: Gaosheng Cui <cuigaosheng1@huawei.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy_unpack.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index dbf7d96257ada..5e578ef0ddffb 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -1025,8 +1025,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 		}
 	} else if (rules->policy->dfa &&
 		   rules->policy->start[AA_CLASS_FILE]) {
+		aa_put_pdb(rules->file);
 		rules->file = aa_get_pdb(rules->policy);
 	} else {
+		aa_put_pdb(rules->file);
 		rules->file = aa_get_pdb(nullpdb);
 	}
 	error = -EPROTO;
-- 
GitLab


From 125c0a646a257fd58de223f2c3e1fe8a99085644 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 5 Dec 2023 12:51:21 +0100
Subject: [PATCH 2370/4076] xen: update PV-device interface headers

Update the Xen PV-device interface headers in order to avoid undefined
behavior with flexible arrays being defined with one array element.

Reported-by: Pry Mar <pryorm09@gmail.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Stefano Stabellini <sstabellini@kernel.org>
Link: https://lore.kernel.org/r/20231205115121.11627-1-jgross@suse.com
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 include/xen/interface/io/displif.h | 2 +-
 include/xen/interface/io/ring.h    | 2 +-
 include/xen/interface/io/sndif.h   | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/xen/interface/io/displif.h b/include/xen/interface/io/displif.h
index 18417b0178699..60e42d3b760e0 100644
--- a/include/xen/interface/io/displif.h
+++ b/include/xen/interface/io/displif.h
@@ -537,7 +537,7 @@ struct xendispl_dbuf_create_req {
 
 struct xendispl_page_directory {
 	grant_ref_t gref_dir_next_page;
-	grant_ref_t gref[1]; /* Variable length */
+	grant_ref_t gref[];
 };
 
 /*
diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h
index ba4c4274b7146..4fef1efcdcab5 100644
--- a/include/xen/interface/io/ring.h
+++ b/include/xen/interface/io/ring.h
@@ -95,7 +95,7 @@ struct __name##_sring {                                                 \
     RING_IDX req_prod, req_event;                                       \
     RING_IDX rsp_prod, rsp_event;                                       \
     uint8_t __pad[48];                                                  \
-    union __name##_sring_entry ring[1]; /* variable-length */           \
+    union __name##_sring_entry ring[];                                  \
 };                                                                      \
                                                                         \
 /* "Front" end's private variables */                                   \
diff --git a/include/xen/interface/io/sndif.h b/include/xen/interface/io/sndif.h
index 445657cdb1def..b818517588b50 100644
--- a/include/xen/interface/io/sndif.h
+++ b/include/xen/interface/io/sndif.h
@@ -659,7 +659,7 @@ struct xensnd_open_req {
 
 struct xensnd_page_directory {
 	grant_ref_t gref_dir_next_page;
-	grant_ref_t gref[1]; /* Variable length */
+	grant_ref_t gref[];
 };
 
 /*
-- 
GitLab


From f1479f0a4f53ef4fc12108a59caee61c39bc6843 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 6 Dec 2023 10:17:24 -0800
Subject: [PATCH 2371/4076] xen/xenbus: client: fix kernel-doc comments

Correct function kernel-doc notation to prevent warnings from
scripts/kernel-doc.

xenbus_client.c:134: warning: No description found for return value of 'xenbus_watch_path'
xenbus_client.c:177: warning: No description found for return value of 'xenbus_watch_pathfmt'
xenbus_client.c:258: warning: missing initial short description on line:
 * xenbus_switch_state
xenbus_client.c:267: warning: No description found for return value of 'xenbus_switch_state'
xenbus_client.c:308: warning: missing initial short description on line:
 * xenbus_dev_error
xenbus_client.c:327: warning: missing initial short description on line:
 * xenbus_dev_fatal
xenbus_client.c:350: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * Equivalent to xenbus_dev_fatal(dev, err, fmt, args), but helps
xenbus_client.c:457: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * Allocate an event channel for the given xenbus_device, assigning the newly
xenbus_client.c:486: warning: expecting prototype for Free an existing event channel. Returns 0 on success or(). Prototype was for xenbus_free_evtchn() instead
xenbus_client.c:502: warning: missing initial short description on line:
 * xenbus_map_ring_valloc
xenbus_client.c:517: warning: No description found for return value of 'xenbus_map_ring_valloc'
xenbus_client.c:602: warning: missing initial short description on line:
 * xenbus_unmap_ring
xenbus_client.c:614: warning: No description found for return value of 'xenbus_unmap_ring'
xenbus_client.c:715: warning: missing initial short description on line:
 * xenbus_unmap_ring_vfree
xenbus_client.c:727: warning: No description found for return value of 'xenbus_unmap_ring_vfree'
xenbus_client.c:919: warning: missing initial short description on line:
 * xenbus_read_driver_state
xenbus_client.c:926: warning: No description found for return value of 'xenbus_read_driver_state'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: xen-devel@lists.xenproject.org
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20231206181724.27767-1-rdunlap@infradead.org
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 drivers/xen/xenbus/xenbus_client.c | 59 +++++++++++++++++-------------
 1 file changed, 34 insertions(+), 25 deletions(-)

diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index d4b2519257962..32835b4b9bc50 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -119,11 +119,13 @@ EXPORT_SYMBOL_GPL(xenbus_strstate);
  * @callback: callback to register
  *
  * Register a @watch on the given path, using the given xenbus_watch structure
- * for storage, and the given @callback function as the callback.  Return 0 on
- * success, or -errno on error.  On success, the given @path will be saved as
- * @watch->node, and remains the caller's to free.  On error, @watch->node will
+ * for storage, and the given @callback function as the callback.  On success,
+ * the given @path will be saved as @watch->node, and remains the
+ * caller's to free.  On error, @watch->node will
  * be NULL, the device will switch to %XenbusStateClosing, and the error will
  * be saved in the store.
+ *
+ * Returns: %0 on success or -errno on error
  */
 int xenbus_watch_path(struct xenbus_device *dev, const char *path,
 		      struct xenbus_watch *watch,
@@ -160,12 +162,14 @@ EXPORT_SYMBOL_GPL(xenbus_watch_path);
  * @pathfmt: format of path to watch
  *
  * Register a watch on the given @path, using the given xenbus_watch
- * structure for storage, and the given @callback function as the callback.
- * Return 0 on success, or -errno on error.  On success, the watched path
- * (@path/@path2) will be saved as @watch->node, and becomes the caller's to
- * kfree().  On error, watch->node will be NULL, so the caller has nothing to
+ * structure for storage, and the given @callback function as the
+ * callback.  On success, the watched path (@path/@path2) will be saved
+ * as @watch->node, and becomes the caller's to kfree().
+ * On error, watch->node will be NULL, so the caller has nothing to
  * free, the device will switch to %XenbusStateClosing, and the error will be
  * saved in the store.
+ *
+ * Returns: %0 on success or -errno on error
  */
 int xenbus_watch_pathfmt(struct xenbus_device *dev,
 			 struct xenbus_watch *watch,
@@ -255,13 +259,15 @@ abort:
 }
 
 /**
- * xenbus_switch_state
+ * xenbus_switch_state - save the new state of a driver
  * @dev: xenbus device
  * @state: new state
  *
  * Advertise in the store a change of the given driver to the given new_state.
- * Return 0 on success, or -errno on error.  On error, the device will switch
- * to XenbusStateClosing, and the error will be saved in the store.
+ * On error, the device will switch to XenbusStateClosing, and the error
+ * will be saved in the store.
+ *
+ * Returns: %0 on success or -errno on error
  */
 int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state state)
 {
@@ -305,7 +311,7 @@ static void xenbus_va_dev_error(struct xenbus_device *dev, int err,
 }
 
 /**
- * xenbus_dev_error
+ * xenbus_dev_error - place an error message into the store
  * @dev: xenbus device
  * @err: error to report
  * @fmt: error message format
@@ -324,7 +330,7 @@ void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...)
 EXPORT_SYMBOL_GPL(xenbus_dev_error);
 
 /**
- * xenbus_dev_fatal
+ * xenbus_dev_fatal - put an error messages into the store and then shutdown
  * @dev: xenbus device
  * @err: error to report
  * @fmt: error message format
@@ -346,7 +352,7 @@ void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...)
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_fatal);
 
-/**
+/*
  * Equivalent to xenbus_dev_fatal(dev, err, fmt, args), but helps
  * avoiding recursion within xenbus_switch_state.
  */
@@ -453,7 +459,7 @@ void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages,
 }
 EXPORT_SYMBOL_GPL(xenbus_teardown_ring);
 
-/**
+/*
  * Allocate an event channel for the given xenbus_device, assigning the newly
  * created local port to *port.  Return 0 on success, or -errno on error.  On
  * error, the device will switch to XenbusStateClosing, and the error will be
@@ -479,7 +485,7 @@ int xenbus_alloc_evtchn(struct xenbus_device *dev, evtchn_port_t *port)
 EXPORT_SYMBOL_GPL(xenbus_alloc_evtchn);
 
 
-/**
+/*
  * Free an existing event channel. Returns 0 on success or -errno on error.
  */
 int xenbus_free_evtchn(struct xenbus_device *dev, evtchn_port_t port)
@@ -499,7 +505,7 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
 
 
 /**
- * xenbus_map_ring_valloc
+ * xenbus_map_ring_valloc - allocate & map pages of VA space
  * @dev: xenbus device
  * @gnt_refs: grant reference array
  * @nr_grefs: number of grant references
@@ -507,10 +513,11 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
  *
  * Map @nr_grefs pages of memory into this domain from another
  * domain's grant table.  xenbus_map_ring_valloc allocates @nr_grefs
- * pages of virtual address space, maps the pages to that address, and
- * sets *vaddr to that address.  Returns 0 on success, and -errno on
- * error. If an error is returned, device will switch to
+ * pages of virtual address space, maps the pages to that address, and sets
+ * *vaddr to that address.  If an error is returned, device will switch to
  * XenbusStateClosing and the error message will be saved in XenStore.
+ *
+ * Returns: %0 on success or -errno on error
  */
 int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs,
 			   unsigned int nr_grefs, void **vaddr)
@@ -599,14 +606,15 @@ static int __xenbus_map_ring(struct xenbus_device *dev,
 }
 
 /**
- * xenbus_unmap_ring
+ * xenbus_unmap_ring - unmap memory from another domain
  * @dev: xenbus device
  * @handles: grant handle array
  * @nr_handles: number of handles in the array
  * @vaddrs: addresses to unmap
  *
  * Unmap memory in this domain that was imported from another domain.
- * Returns 0 on success and returns GNTST_* on error
+ *
+ * Returns: %0 on success or GNTST_* on error
  * (see xen/include/interface/grant_table.h).
  */
 static int xenbus_unmap_ring(struct xenbus_device *dev, grant_handle_t *handles,
@@ -712,7 +720,7 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
 }
 
 /**
- * xenbus_unmap_ring_vfree
+ * xenbus_unmap_ring_vfree - unmap a page of memory from another domain
  * @dev: xenbus device
  * @vaddr: addr to unmap
  *
@@ -720,7 +728,8 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
  * Unmap a page of memory in this domain that was imported from another domain.
  * Use xenbus_unmap_ring_vfree if you mapped in your memory with
  * xenbus_map_ring_valloc (it will free the virtual address space).
- * Returns 0 on success and returns GNTST_* on error
+ *
+ * Returns: %0 on success or GNTST_* on error
  * (see xen/include/interface/grant_table.h).
  */
 int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
@@ -916,10 +925,10 @@ static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr)
 }
 
 /**
- * xenbus_read_driver_state
+ * xenbus_read_driver_state - read state from a store path
  * @path: path for driver
  *
- * Return the state of the driver rooted at the given store path, or
+ * Returns: the state of the driver rooted at the given store path, or
  * XenbusStateUnknown if no state can be read.
  */
 enum xenbus_state xenbus_read_driver_state(const char *path)
-- 
GitLab


From 7e72fc41d4243800206ff76615cfebb15d632027 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 3 Jan 2024 12:49:57 +0100
Subject: [PATCH 2372/4076] thermal: netlink: Pass pointers to
 thermal_notify_tz_trip_change()

Instead of requiring the caller of thermal_notify_tz_trip_change() to
provide specific values needed to populate struct param in it, make it
extract those values from objects passed to it by the caller via const
pointers.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_netlink.c | 14 ++++++++------
 drivers/thermal/thermal_netlink.h | 11 +++++++----
 drivers/thermal/thermal_trip.c    |  8 ++------
 3 files changed, 17 insertions(+), 16 deletions(-)

diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 332052e24a86c..4a2c299c04626 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -377,12 +377,14 @@ int thermal_notify_tz_trip_delete(int tz_id, int trip_id)
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_DELETE, &p);
 }
 
-int thermal_notify_tz_trip_change(int tz_id, int trip_id, int trip_type,
-				  int trip_temp, int trip_hyst)
-{
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id,
-			   .trip_type = trip_type, .trip_temp = trip_temp,
-			   .trip_hyst = trip_hyst };
+int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
+				  const struct thermal_trip *trip)
+{
+	struct param p = { .tz_id = tz->id,
+			   .trip_id = thermal_zone_trip_id(tz, trip),
+			   .trip_type = trip->type,
+			   .trip_temp = trip->temperature,
+			   .trip_hyst = trip->hysteresis };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_CHANGE, &p);
 }
diff --git a/drivers/thermal/thermal_netlink.h b/drivers/thermal/thermal_netlink.h
index 0a9987c3bc578..bb4c47d685e3c 100644
--- a/drivers/thermal/thermal_netlink.h
+++ b/drivers/thermal/thermal_netlink.h
@@ -10,6 +10,9 @@ struct thermal_genl_cpu_caps {
 	int efficiency;
 };
 
+struct thermal_zone_device;
+struct thermal_trip;
+
 /* Netlink notification function */
 #ifdef CONFIG_THERMAL_NETLINK
 int __init thermal_netlink_init(void);
@@ -23,8 +26,8 @@ int thermal_notify_tz_trip_up(int tz_id, int id, int temp);
 int thermal_notify_tz_trip_delete(int tz_id, int id);
 int thermal_notify_tz_trip_add(int tz_id, int id, int type,
 			       int temp, int hyst);
-int thermal_notify_tz_trip_change(int tz_id, int id, int type,
-				  int temp, int hyst);
+int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
+				  const struct thermal_trip *trip);
 int thermal_notify_cdev_state_update(int cdev_id, int state);
 int thermal_notify_cdev_add(int cdev_id, const char *name, int max_state);
 int thermal_notify_cdev_delete(int cdev_id);
@@ -79,8 +82,8 @@ static inline int thermal_notify_tz_trip_add(int tz_id, int id, int type,
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_change(int tz_id, int id, int type,
-						int temp, int hyst)
+static inline int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
+						const struct thermal_trip *trip)
 {
 	return 0;
 }
diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
index 8bffa1e5e2063..c875a26d5adf4 100644
--- a/drivers/thermal/thermal_trip.c
+++ b/drivers/thermal/thermal_trip.c
@@ -155,9 +155,7 @@ int thermal_zone_trip_id(const struct thermal_zone_device *tz,
 void thermal_zone_trip_updated(struct thermal_zone_device *tz,
 			       const struct thermal_trip *trip)
 {
-	thermal_notify_tz_trip_change(tz->id, thermal_zone_trip_id(tz, trip),
-				      trip->type, trip->temperature,
-				      trip->hysteresis);
+	thermal_notify_tz_trip_change(tz, trip);
 	__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
 }
 
@@ -168,8 +166,6 @@ void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
 		return;
 
 	trip->temperature = temp;
-	thermal_notify_tz_trip_change(tz->id, thermal_zone_trip_id(tz, trip),
-				      trip->type, trip->temperature,
-				      trip->hysteresis);
+	thermal_notify_tz_trip_change(tz, trip);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_set_trip_temp);
-- 
GitLab


From f52557edf0648b471e2006f9377ea0ba4f73f9b2 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 15 Dec 2023 20:57:50 +0100
Subject: [PATCH 2373/4076] thermal: netlink: Pass pointers to
 thermal_notify_tz_trip_up/down()

Instead of requiring the callers of thermal_notify_tz_trip_up/down() to
provide specific values needed to populate struct param in them, make
them extract those values from objects passed by the callers via const
pointers.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_core.c    |  8 ++------
 drivers/thermal/thermal_netlink.c | 14 ++++++++++----
 drivers/thermal/thermal_netlink.h | 12 ++++++++----
 3 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index fa88d87072416..a7e2008d34c9b 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -381,9 +381,7 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		 * the threshold and the trip temperature will be equal.
 		 */
 		if (tz->temperature >= trip->temperature) {
-			thermal_notify_tz_trip_up(tz->id,
-						  thermal_zone_trip_id(tz, trip),
-						  tz->temperature);
+			thermal_notify_tz_trip_up(tz, trip);
 			trip->threshold = trip->temperature - trip->hysteresis;
 		} else {
 			trip->threshold = trip->temperature;
@@ -400,9 +398,7 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		 * the trip.
 		 */
 		if (tz->temperature < trip->temperature - trip->hysteresis) {
-			thermal_notify_tz_trip_down(tz->id,
-						    thermal_zone_trip_id(tz, trip),
-						    tz->temperature);
+			thermal_notify_tz_trip_down(tz, trip);
 			trip->threshold = trip->temperature;
 		} else {
 			trip->threshold = trip->temperature - trip->hysteresis;
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 4a2c299c04626..46e4ea45d67dc 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -346,16 +346,22 @@ int thermal_notify_tz_disable(int tz_id)
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DISABLE, &p);
 }
 
-int thermal_notify_tz_trip_down(int tz_id, int trip_id, int temp)
+int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz,
+				const struct thermal_trip *trip)
 {
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id, .temp = temp };
+	struct param p = { .tz_id = tz->id,
+			   .trip_id = thermal_zone_trip_id(tz, trip),
+			   .temp = tz->temperature };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_DOWN, &p);
 }
 
-int thermal_notify_tz_trip_up(int tz_id, int trip_id, int temp)
+int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip)
 {
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id, .temp = temp };
+	struct param p = { .tz_id = tz->id,
+			   .trip_id = thermal_zone_trip_id(tz, trip),
+			   .temp = tz->temperature };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_UP, &p);
 }
diff --git a/drivers/thermal/thermal_netlink.h b/drivers/thermal/thermal_netlink.h
index bb4c47d685e3c..907dc88d33170 100644
--- a/drivers/thermal/thermal_netlink.h
+++ b/drivers/thermal/thermal_netlink.h
@@ -21,8 +21,10 @@ int thermal_notify_tz_create(int tz_id, const char *name);
 int thermal_notify_tz_delete(int tz_id);
 int thermal_notify_tz_enable(int tz_id);
 int thermal_notify_tz_disable(int tz_id);
-int thermal_notify_tz_trip_down(int tz_id, int id, int temp);
-int thermal_notify_tz_trip_up(int tz_id, int id, int temp);
+int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz,
+				const struct thermal_trip *trip);
+int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip);
 int thermal_notify_tz_trip_delete(int tz_id, int id);
 int thermal_notify_tz_trip_add(int tz_id, int id, int type,
 			       int temp, int hyst);
@@ -61,12 +63,14 @@ static inline int thermal_notify_tz_disable(int tz_id)
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_down(int tz_id, int id, int temp)
+static inline int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz,
+					      const struct thermal_trip *trip)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_up(int tz_id, int id, int temp)
+static inline int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
+					    const struct thermal_trip *trip)
 {
 	return 0;
 }
-- 
GitLab


From 4ae535f37d0e3c5731f90c385e883c0bada59fc9 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 15 Dec 2023 20:59:08 +0100
Subject: [PATCH 2374/4076] thermal: netlink: Drop
 thermal_notify_tz_trip_add/delete()

Because thermal_notify_tz_trip_add/delete() are never used, drop them
entirely along with the related code.

The addition or removal of trip points is not supported by the thermal
core and is unlikely to be supported in the future, so it is also
unlikely that these functions will ever be needed.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_netlink.c | 33 +------------------------------
 drivers/thermal/thermal_netlink.h | 14 -------------
 2 files changed, 1 insertion(+), 46 deletions(-)

diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 46e4ea45d67dc..91992181e845c 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -148,7 +148,7 @@ static int thermal_genl_event_tz_trip_up(struct param *p)
 	return 0;
 }
 
-static int thermal_genl_event_tz_trip_add(struct param *p)
+static int thermal_genl_event_tz_trip_change(struct param *p)
 {
 	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
 	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id) ||
@@ -160,15 +160,6 @@ static int thermal_genl_event_tz_trip_add(struct param *p)
 	return 0;
 }
 
-static int thermal_genl_event_tz_trip_delete(struct param *p)
-{
-	if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) ||
-	    nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id))
-		return -EMSGSIZE;
-
-	return 0;
-}
-
 static int thermal_genl_event_cdev_add(struct param *p)
 {
 	if (nla_put_string(p->msg, THERMAL_GENL_ATTR_CDEV_NAME,
@@ -258,9 +249,6 @@ int thermal_genl_event_tz_disable(struct param *p)
 int thermal_genl_event_tz_trip_down(struct param *p)
 	__attribute__((alias("thermal_genl_event_tz_trip_up")));
 
-int thermal_genl_event_tz_trip_change(struct param *p)
-	__attribute__((alias("thermal_genl_event_tz_trip_add")));
-
 static cb_t event_cb[] = {
 	[THERMAL_GENL_EVENT_TZ_CREATE]		= thermal_genl_event_tz_create,
 	[THERMAL_GENL_EVENT_TZ_DELETE]		= thermal_genl_event_tz_delete,
@@ -269,8 +257,6 @@ static cb_t event_cb[] = {
 	[THERMAL_GENL_EVENT_TZ_TRIP_UP]		= thermal_genl_event_tz_trip_up,
 	[THERMAL_GENL_EVENT_TZ_TRIP_DOWN]	= thermal_genl_event_tz_trip_down,
 	[THERMAL_GENL_EVENT_TZ_TRIP_CHANGE]	= thermal_genl_event_tz_trip_change,
-	[THERMAL_GENL_EVENT_TZ_TRIP_ADD]	= thermal_genl_event_tz_trip_add,
-	[THERMAL_GENL_EVENT_TZ_TRIP_DELETE]	= thermal_genl_event_tz_trip_delete,
 	[THERMAL_GENL_EVENT_CDEV_ADD]		= thermal_genl_event_cdev_add,
 	[THERMAL_GENL_EVENT_CDEV_DELETE]	= thermal_genl_event_cdev_delete,
 	[THERMAL_GENL_EVENT_CDEV_STATE_UPDATE]	= thermal_genl_event_cdev_state_update,
@@ -366,23 +352,6 @@ int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_UP, &p);
 }
 
-int thermal_notify_tz_trip_add(int tz_id, int trip_id, int trip_type,
-			       int trip_temp, int trip_hyst)
-{
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id,
-			   .trip_type = trip_type, .trip_temp = trip_temp,
-			   .trip_hyst = trip_hyst };
-
-	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_ADD, &p);
-}
-
-int thermal_notify_tz_trip_delete(int tz_id, int trip_id)
-{
-	struct param p = { .tz_id = tz_id, .trip_id = trip_id };
-
-	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_DELETE, &p);
-}
-
 int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
 				  const struct thermal_trip *trip)
 {
diff --git a/drivers/thermal/thermal_netlink.h b/drivers/thermal/thermal_netlink.h
index 907dc88d33170..e780ce3f7db6e 100644
--- a/drivers/thermal/thermal_netlink.h
+++ b/drivers/thermal/thermal_netlink.h
@@ -25,9 +25,6 @@ int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz,
 				const struct thermal_trip *trip);
 int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
 			      const struct thermal_trip *trip);
-int thermal_notify_tz_trip_delete(int tz_id, int id);
-int thermal_notify_tz_trip_add(int tz_id, int id, int type,
-			       int temp, int hyst);
 int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
 				  const struct thermal_trip *trip);
 int thermal_notify_cdev_state_update(int cdev_id, int state);
@@ -75,17 +72,6 @@ static inline int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz
 	return 0;
 }
 
-static inline int thermal_notify_tz_trip_delete(int tz_id, int id)
-{
-	return 0;
-}
-
-static inline int thermal_notify_tz_trip_add(int tz_id, int id, int type,
-					     int temp, int hyst)
-{
-	return 0;
-}
-
 static inline int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
 						const struct thermal_trip *trip)
 {
-- 
GitLab


From 2f521890aa5b8a5619d31a95caec0b08d4cb9e1a Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 3 Jan 2024 12:59:10 +0100
Subject: [PATCH 2375/4076] thermal: netlink: Pass thermal zone pointer to
 notify routines

There are several rountines in the thermal netlink API that take a
thermal zone ID or a thermal zone type as their arguments, but from
their callers perspective it would be more convenient to pass a thermal
zone pointer to them and let them extract the necessary data from the
given thermal zone object by themselves.

Modify the code accordingly.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_core.c    | 13 +++++--------
 drivers/thermal/thermal_netlink.c | 21 +++++++++++----------
 drivers/thermal/thermal_netlink.h | 22 ++++++++++++----------
 3 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index a7e2008d34c9b..c0b012e075f34 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -211,7 +211,7 @@ exit:
 	mutex_unlock(&tz->lock);
 	mutex_unlock(&thermal_governor_lock);
 
-	thermal_notify_tz_gov_change(tz->id, policy);
+	thermal_notify_tz_gov_change(tz, policy);
 
 	return ret;
 }
@@ -501,9 +501,9 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 	mutex_unlock(&tz->lock);
 
 	if (mode == THERMAL_DEVICE_ENABLED)
-		thermal_notify_tz_enable(tz->id);
+		thermal_notify_tz_enable(tz);
 	else
-		thermal_notify_tz_disable(tz->id);
+		thermal_notify_tz_disable(tz);
 
 	return ret;
 }
@@ -1407,7 +1407,7 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	if (atomic_cmpxchg(&tz->need_update, 1, 0))
 		thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
 
-	thermal_notify_tz_create(tz->id, tz->type);
+	thermal_notify_tz_create(tz);
 
 	return tz;
 
@@ -1466,15 +1466,12 @@ EXPORT_SYMBOL_GPL(thermal_zone_device);
  */
 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 {
-	int tz_id;
 	struct thermal_cooling_device *cdev;
 	struct thermal_zone_device *pos = NULL;
 
 	if (!tz)
 		return;
 
-	tz_id = tz->id;
-
 	mutex_lock(&thermal_list_lock);
 	list_for_each_entry(pos, &thermal_tz_list, node)
 		if (pos == tz)
@@ -1510,7 +1507,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 
 	put_device(&tz->device);
 
-	thermal_notify_tz_delete(tz_id);
+	thermal_notify_tz_delete(tz);
 
 	wait_for_completion(&tz->removal);
 	kfree(tz);
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 91992181e845c..46b0156a63191 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -304,30 +304,30 @@ out_free_msg:
 	return ret;
 }
 
-int thermal_notify_tz_create(int tz_id, const char *name)
+int thermal_notify_tz_create(const struct thermal_zone_device *tz)
 {
-	struct param p = { .tz_id = tz_id, .name = name };
+	struct param p = { .tz_id = tz->id, .name = tz->type };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_CREATE, &p);
 }
 
-int thermal_notify_tz_delete(int tz_id)
+int thermal_notify_tz_delete(const struct thermal_zone_device *tz)
 {
-	struct param p = { .tz_id = tz_id };
+	struct param p = { .tz_id = tz->id };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DELETE, &p);
 }
 
-int thermal_notify_tz_enable(int tz_id)
+int thermal_notify_tz_enable(const struct thermal_zone_device *tz)
 {
-	struct param p = { .tz_id = tz_id };
+	struct param p = { .tz_id = tz->id };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_ENABLE, &p);
 }
 
-int thermal_notify_tz_disable(int tz_id)
+int thermal_notify_tz_disable(const struct thermal_zone_device *tz)
 {
-	struct param p = { .tz_id = tz_id };
+	struct param p = { .tz_id = tz->id };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DISABLE, &p);
 }
@@ -386,9 +386,10 @@ int thermal_notify_cdev_delete(int cdev_id)
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_DELETE, &p);
 }
 
-int thermal_notify_tz_gov_change(int tz_id, const char *name)
+int thermal_notify_tz_gov_change(const struct thermal_zone_device *tz,
+				 const char *name)
 {
-	struct param p = { .tz_id = tz_id, .name = name };
+	struct param p = { .tz_id = tz->id, .name = name };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_GOV_CHANGE, &p);
 }
diff --git a/drivers/thermal/thermal_netlink.h b/drivers/thermal/thermal_netlink.h
index e780ce3f7db6e..13ea2ad23d3ab 100644
--- a/drivers/thermal/thermal_netlink.h
+++ b/drivers/thermal/thermal_netlink.h
@@ -17,10 +17,10 @@ struct thermal_trip;
 #ifdef CONFIG_THERMAL_NETLINK
 int __init thermal_netlink_init(void);
 void __init thermal_netlink_exit(void);
-int thermal_notify_tz_create(int tz_id, const char *name);
-int thermal_notify_tz_delete(int tz_id);
-int thermal_notify_tz_enable(int tz_id);
-int thermal_notify_tz_disable(int tz_id);
+int thermal_notify_tz_create(const struct thermal_zone_device *tz);
+int thermal_notify_tz_delete(const struct thermal_zone_device *tz);
+int thermal_notify_tz_enable(const struct thermal_zone_device *tz);
+int thermal_notify_tz_disable(const struct thermal_zone_device *tz);
 int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz,
 				const struct thermal_trip *trip);
 int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
@@ -30,7 +30,8 @@ int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
 int thermal_notify_cdev_state_update(int cdev_id, int state);
 int thermal_notify_cdev_add(int cdev_id, const char *name, int max_state);
 int thermal_notify_cdev_delete(int cdev_id);
-int thermal_notify_tz_gov_change(int tz_id, const char *name);
+int thermal_notify_tz_gov_change(const struct thermal_zone_device *tz,
+				 const char *name);
 int thermal_genl_sampling_temp(int id, int temp);
 int thermal_genl_cpu_capability_event(int count,
 				      struct thermal_genl_cpu_caps *caps);
@@ -40,22 +41,22 @@ static inline int thermal_netlink_init(void)
 	return 0;
 }
 
-static inline int thermal_notify_tz_create(int tz_id, const char *name)
+static inline int thermal_notify_tz_create(const struct thermal_zone_device *tz)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_delete(int tz_id)
+static inline int thermal_notify_tz_delete(const struct thermal_zone_device *tz)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_enable(int tz_id)
+static inline int thermal_notify_tz_enable(const struct thermal_zone_device *tz)
 {
 	return 0;
 }
 
-static inline int thermal_notify_tz_disable(int tz_id)
+static inline int thermal_notify_tz_disable(const struct thermal_zone_device *tz)
 {
 	return 0;
 }
@@ -94,7 +95,8 @@ static inline int thermal_notify_cdev_delete(int cdev_id)
 	return 0;
 }
 
-static inline int thermal_notify_tz_gov_change(int tz_id, const char *name)
+static inline int thermal_notify_tz_gov_change(const struct thermal_zone_device *tz,
+					       const char *name)
 {
 	return 0;
 }
-- 
GitLab


From 3d1d4aa0cc13b1883a5a56c945837a2e0ecb5143 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 8 Jan 2024 10:02:55 +0000
Subject: [PATCH 2376/4076] cachefiles: Fix signed/unsigned mixup

In __cachefiles_prepare_write(), the start and pos variables were made
unsigned 64-bit so that the casts in the checking could be got rid of -
which should be fine since absolute file offsets can't be negative, except
that an error code may be obtained from vfs_llseek(), which *would* be
negative.  This breaks the error check.

Fix this for now by reverting pos and start to be signed and putting back
the casts.  Unfortunately, the error value checks cannot be replaced with
IS_ERR_VALUE() as long might be 32-bits.

Fixes: 7097c96411d2 ("cachefiles: Fix __cachefiles_prepare_write()")
Reported-by: Simon Horman <horms@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401071152.DbKqMQMu-lkp@intel.com/
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
cc: Yiqun Leng <yqleng@linux.alibaba.com>
cc: Jia Zhu <zhujia.zj@bytedance.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-erofs@lists.ozlabs.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/cachefiles/io.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 3eec269674375..9a2cb2868e901 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -522,7 +522,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 			       bool no_space_allocated_yet)
 {
 	struct cachefiles_cache *cache = object->volume->cache;
-	unsigned long long start = *_start, pos;
+	loff_t start = *_start, pos;
 	size_t len = *_len;
 	int ret;
 
@@ -556,7 +556,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 					  cachefiles_trace_seek_error);
 		return pos;
 	}
-	if (pos >= start + *_len)
+	if ((u64)pos >= (u64)start + *_len)
 		goto check_space; /* Unallocated region */
 
 	/* We have a block that's at least partially filled - if we're low on
@@ -575,7 +575,7 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 					  cachefiles_trace_seek_error);
 		return pos;
 	}
-	if (pos >= start + *_len)
+	if ((u64)pos >= (u64)start + *_len)
 		return 0; /* Fully allocated */
 
 	/* Partially allocated, but insufficient space: cull. */
-- 
GitLab


From e2bdb5272f4314256f51d91eee7babcae58b194b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 8 Jan 2024 21:30:49 +0000
Subject: [PATCH 2377/4076] netfs: Fix wrong #ifdef hiding wait

netfs_writepages_begin() has the wait on the fscache folio conditional on
CONFIG_NETFS_FSCACHE - which doesn't exist.

Fix it to be conditional on CONFIG_FSCACHE instead.

Fixes: 62c3b7481b9a ("netfs: Provide a writepages implementation")
Reported-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-afs@lists.infradead.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20240109083257.GK132648@kernel.org/
---
 fs/netfs/buffered_write.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 0b2b7a60dabc0..de517ca70d916 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -1076,7 +1076,7 @@ lock_again:
 		folio_unlock(folio);
 		if (wbc->sync_mode != WB_SYNC_NONE) {
 			folio_wait_writeback(folio);
-#ifdef CONFIG_NETFS_FSCACHE
+#ifdef CONFIG_FSCACHE
 			folio_wait_fscache(folio);
 #endif
 			goto lock_again;
-- 
GitLab


From 022e6f5184ff73eaaf6aa7a89b7fafc7c2bd8c9c Mon Sep 17 00:00:00 2001
From: Erick Archer <erick.archer@gmx.com>
Date: Fri, 5 Jan 2024 18:11:04 +0000
Subject: [PATCH 2378/4076] PM: QoS: Use kcalloc() instead of kzalloc()

Use 2-factor multiplication argument form kcalloc() instead
of kzalloc().

Link: https://github.com/KSPP/linux/issues/162
Signed-off-by: Erick Archer <erick.archer@gmx.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/qos.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 8e93167f1783a..bd77f6734f14c 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -201,7 +201,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	if (!qos)
 		return -ENOMEM;
 
-	n = kzalloc(3 * sizeof(*n), GFP_KERNEL);
+	n = kcalloc(3, sizeof(*n), GFP_KERNEL);
 	if (!n) {
 		kfree(qos);
 		return -ENOMEM;
-- 
GitLab


From 2fb7e4dd35c52933b18ff127bf92d703c8e2e897 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 5 Jan 2024 13:51:21 +0100
Subject: [PATCH 2379/4076] PNP: make pnp_bus_type const

Now that the driver core can properly handle constant struct bus_type,
move the pnp_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/pnp/driver.c | 2 +-
 include/linux/pnp.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c
index 46c534f6b1c97..0a5d0d8befa84 100644
--- a/drivers/pnp/driver.c
+++ b/drivers/pnp/driver.c
@@ -256,7 +256,7 @@ static const struct dev_pm_ops pnp_bus_dev_pm_ops = {
 	.restore = pnp_bus_resume,
 };
 
-struct bus_type pnp_bus_type = {
+const struct bus_type pnp_bus_type = {
 	.name    = "pnp",
 	.match   = pnp_bus_match,
 	.probe   = pnp_device_probe,
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index 267fb8a4fb6e0..ddbe7c3ca4ce2 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -435,7 +435,7 @@ struct pnp_protocol {
 #define protocol_for_each_dev(protocol, dev)	\
 	list_for_each_entry(dev, &(protocol)->devices, protocol_list)
 
-extern struct bus_type pnp_bus_type;
+extern const struct bus_type pnp_bus_type;
 
 #if defined(CONFIG_PNP)
 
-- 
GitLab


From d2aaf19965045f70bb2ece514399cdc6fcce2e73 Mon Sep 17 00:00:00 2001
From: Ben Mayo <benny1091@gmail.com>
Date: Sat, 6 Jan 2024 21:13:23 -0500
Subject: [PATCH 2380/4076] ACPI: resource: Add DMI quirks for ASUS Vivobook
 E1504GA and E1504GAB

Asus Vivobook E1504GA and E1504GAB notebooks are affected by bug #216158
(DSDT specifies the kbd IRQ as level active-low and using the override
changes this to rising edge, stopping the keyboard from working).

Users of these notebooks do not have a working keyboard unless they add
their DMI information to the struct irq1_level_low_skip_override array
and compile a custom kernel.

Add support for these computers to the Linux kernel without requiring
the end-user to recompile the kernel.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=216158
Signed-off-by: Ben Mayo <benny1091@gmail.com>
[ rjw: Link tag, subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/resource.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 0e2c397b13995..b59bcfdbe48a4 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -482,6 +482,20 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "B2502CBA"),
 		},
 	},
+	{
+		/* Asus Vivobook E1504GA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "E1504GA"),
+		},
+	},
+	{
+		/* Asus Vivobook E1504GAB */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "E1504GAB"),
+		},
+	},
 	{
 		/* LG Electronics 17U70P */
 		.matches = {
-- 
GitLab


From e315e8692f7922cd1b2a26bd7a1741cc8ce77085 Mon Sep 17 00:00:00 2001
From: Michael Maltsev <mekosko@projectyo.network>
Date: Sun, 7 Jan 2024 13:53:07 +0500
Subject: [PATCH 2381/4076] ACPI: resource: Skip IRQ override on ASUS
 ExpertBook B1502CGA

Like the ASUS ExpertBook B1502CBA and various ASUS laptops, the
ASUS ExpertBook B1502CGA has an ACPI DSDT table that describes IRQ 1 as
ActiveLow while the kernel overrides it to Edge_High.

	$ sudo dmesg | grep DMI
	[    0.000000] DMI: ASUSTeK COMPUTER INC. ASUS EXPERTBOOK B1502CGA_B1502CGA/B1502CGA, BIOS B1502CGA.303 06/05/2023
	$ grep -A 40 PS2K dsdt.dsl | grep IRQ -A 1
	                IRQ (Level, ActiveLow, Exclusive, )
	                    {1}

This prevents the keyboard from working. To fix this issue, add this laptop
to the skip_override_table so that the kernel does not override IRQ 1.

Signed-off-by: Michael Maltsev <mekosko@projectyo.network>
[ rjw: rebase, replace .ident field with a comment ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/resource.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index b59bcfdbe48a4..dacad1d846c0d 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -461,6 +461,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "B1502CBA"),
 		},
 	},
+	{
+		/* Asus ExpertBook B1502CGA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B1502CGA"),
+		},
+	},
 	{
 		/* Asus ExpertBook B2402CBA */
 		.matches = {
-- 
GitLab


From cb1210a7c03c55f9fb7496bd44155c6a024fe458 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Wed, 27 Dec 2023 12:00:36 +0100
Subject: [PATCH 2382/4076] ACPICA: MADT: Add GICC online capable bit handling

ACPICA commit 16f0befdeddf25756f317907798192bbaa417e5e

Implement code to handle the GICC online capable bit management
added into ACPI v6.5.

Link: https://github.com/acpica/acpica/commit/16f0befd
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actbl2.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index 3751ae69432f1..2b4dd2c3348f3 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -1046,6 +1046,7 @@ struct acpi_madt_generic_interrupt {
 /* ACPI_MADT_ENABLED                    (1)      Processor is usable if set */
 #define ACPI_MADT_PERFORMANCE_IRQ_MODE  (1<<1)	/* 01: Performance Interrupt Mode */
 #define ACPI_MADT_VGIC_IRQ_MODE         (1<<2)	/* 02: VGIC Maintenance Interrupt mode */
+#define ACPI_MADT_GICC_ONLINE_CAPABLE   (1<<3)	/* 03: Processor is online capable  */
 
 /* 12: Generic Distributor (ACPI 5.0 + ACPI 6.0 changes) */
 
-- 
GitLab


From 3be8fb1bc6fc10b6c8e79052126fa5a423698fd1 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Wed, 27 Dec 2023 12:00:37 +0100
Subject: [PATCH 2383/4076] ACPICA: MADT: Add new MADT GICC/GICR/ITS
 non-coherent flags handling

ACPICA commit c5d2010744b1bf7efba0bd04a8a9c200ef8fb610

Add new flags and related fields to the MADT GICC/GICR/ITS
structures according to the code first ECR:

https://bugzilla.tianocore.org/show_bug.cgi?id=4557

Update the MADT template to the latest MADT revision.

Link: https://github.com/acpica/acpica/commit/c5d20107
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actbl2.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index 2b4dd2c3348f3..9775384d61c69 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -1047,6 +1047,7 @@ struct acpi_madt_generic_interrupt {
 #define ACPI_MADT_PERFORMANCE_IRQ_MODE  (1<<1)	/* 01: Performance Interrupt Mode */
 #define ACPI_MADT_VGIC_IRQ_MODE         (1<<2)	/* 02: VGIC Maintenance Interrupt mode */
 #define ACPI_MADT_GICC_ONLINE_CAPABLE   (1<<3)	/* 03: Processor is online capable  */
+#define ACPI_MADT_GICC_NON_COHERENT     (1<<4)	/* 04: GIC redistributor is not coherent */
 
 /* 12: Generic Distributor (ACPI 5.0 + ACPI 6.0 changes) */
 
@@ -1091,21 +1092,27 @@ struct acpi_madt_generic_msi_frame {
 
 struct acpi_madt_generic_redistributor {
 	struct acpi_subtable_header header;
-	u16 reserved;		/* reserved - must be zero */
+	u8 flags;
+	u8 reserved;		/* reserved - must be zero */
 	u64 base_address;
 	u32 length;
 };
 
+#define ACPI_MADT_GICR_NON_COHERENT     (1)
+
 /* 15: Generic Translator (ACPI 6.0) */
 
 struct acpi_madt_generic_translator {
 	struct acpi_subtable_header header;
-	u16 reserved;		/* reserved - must be zero */
+	u8 flags;
+	u8 reserved;		/* reserved - must be zero */
 	u32 translation_id;
 	u64 base_address;
 	u32 reserved2;
 };
 
+#define ACPI_MADT_ITS_NON_COHERENT      (1)
+
 /* 16: Multiprocessor wakeup (ACPI 6.4) */
 
 struct acpi_madt_multiproc_wakeup {
-- 
GitLab


From 3dc2f209208dddc73ffd1d817081711343de3242 Mon Sep 17 00:00:00 2001
From: ZhangPeng <zhangpeng362@huawei.com>
Date: Tue, 9 Jan 2024 10:45:47 +0800
Subject: [PATCH 2384/4076] swiotlb: check alloc_size before the allocation of
 a new memory pool

The allocation request for swiotlb contiguous memory greater than
128*2KB cannot be fulfilled because it exceeds the maximum contiguous
memory limit. If the swiotlb memory we allocate is larger than 128*2KB,
swiotlb_find_slots() will still schedule the allocation of a new memory
pool, which will increase memory overhead.

Fix it by adding a check with alloc_size no more than 128*2KB before
scheduling the allocation of a new memory pool in swiotlb_find_slots().

Signed-off-by: ZhangPeng <zhangpeng362@huawei.com>
Reviewed-by: Petr Tesarik <petr.tesarik1@huawei-partners.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/swiotlb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index e20b856255ef6..96f832d828fd4 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1136,6 +1136,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	int cpu, i;
 	int index;
 
+	if (alloc_size > IO_TLB_SEGSIZE * IO_TLB_SIZE)
+		return -1;
+
 	cpu = raw_smp_processor_id();
 	for (i = 0; i < default_nareas; ++i) {
 		index = swiotlb_search_area(dev, cpu, i, orig_addr, alloc_size,
-- 
GitLab


From ff5912b96f039cc3609eb1d8edc20dfccbfb3a25 Mon Sep 17 00:00:00 2001
From: David Heidelberg <david@ixit.cz>
Date: Sun, 3 Dec 2023 00:47:17 +0100
Subject: [PATCH 2385/4076] dt-bindings: arm: merge qcom,idle-state with
 idle-state

Merge Qualcomm-specific idle-state binding with generic one.

Signed-off-by: David Heidelberg <david@ixit.cz>
Link: https://lore.kernel.org/r/20231202234832.155306-1-david@ixit.cz
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../bindings/arm/msm/qcom,idle-state.txt      | 84 -------------------
 .../devicetree/bindings/cpu/idle-states.yaml  | 81 +++++++++++++++++-
 2 files changed, 77 insertions(+), 88 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt

diff --git a/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt b/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt
deleted file mode 100644
index 606b4b1b709da..0000000000000
--- a/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-QCOM Idle States for cpuidle driver
-
-ARM provides idle-state node to define the cpuidle states, as defined in [1].
-cpuidle-qcom is the cpuidle driver for Qualcomm SoCs and uses these idle
-states. Idle states have different enter/exit latency and residency values.
-The idle states supported by the QCOM SoC are defined as -
-
-    * Standby
-    * Retention
-    * Standalone Power Collapse (Standalone PC or SPC)
-    * Power Collapse (PC)
-
-Standby: Standby does a little more in addition to architectural clock gating.
-When the WFI instruction is executed the ARM core would gate its internal
-clocks. In addition to gating the clocks, QCOM cpus use this instruction as a
-trigger to execute the SPM state machine. The SPM state machine waits for the
-interrupt to trigger the core back in to active. This triggers the cache
-hierarchy to enter standby states, when all cpus are idle. An interrupt brings
-the SPM state machine out of its wait, the next step is to ensure that the
-cache hierarchy is also out of standby, and then the cpu is allowed to resume
-execution. This state is defined as a generic ARM WFI state by the ARM cpuidle
-driver and is not defined in the DT. The SPM state machine should be
-configured to execute this state by default and after executing every other
-state below.
-
-Retention: Retention is a low power state where the core is clock gated and
-the memory and the registers associated with the core are retained. The
-voltage may be reduced to the minimum value needed to keep the processor
-registers active. The SPM should be configured to execute the retention
-sequence and would wait for interrupt, before restoring the cpu to execution
-state. Retention may have a slightly higher latency than Standby.
-
-Standalone PC: A cpu can power down and warmboot if there is a sufficient time
-between the time it enters idle and the next known wake up. SPC mode is used
-to indicate a core entering a power down state without consulting any other
-cpu or the system resources. This helps save power only on that core.  The SPM
-sequence for this idle state is programmed to power down the supply to the
-core, wait for the interrupt, restore power to the core, and ensure the
-system state including cache hierarchy is ready before allowing core to
-resume. Applying power and resetting the core causes the core to warmboot
-back into Elevation Level (EL) which trampolines the control back to the
-kernel. Entering a power down state for the cpu, needs to be done by trapping
-into a EL. Failing to do so, would result in a crash enforced by the warm boot
-code in the EL for the SoC. On SoCs with write-back L1 cache, the cache has to
-be flushed in s/w, before powering down the core.
-
-Power Collapse: This state is similar to the SPC mode, but distinguishes
-itself in that the cpu acknowledges and permits the SoC to enter deeper sleep
-modes. In a hierarchical power domain SoC, this means L2 and other caches can
-be flushed, system bus, clocks - lowered, and SoC main XO clock gated and
-voltages reduced, provided all cpus enter this state.  Since the span of low
-power modes possible at this state is vast, the exit latency and the residency
-of this low power mode would be considered high even though at a cpu level,
-this essentially is cpu power down. The SPM in this state also may handshake
-with the Resource power manager (RPM) processor in the SoC to indicate a
-complete application processor subsystem shut down.
-
-The idle-state for QCOM SoCs are distinguished by the compatible property of
-the idle-states device node.
-
-The devicetree representation of the idle state should be -
-
-Required properties:
-
-- compatible: Must be one of -
-			"qcom,idle-state-ret",
-			"qcom,idle-state-spc",
-			"qcom,idle-state-pc",
-		and "arm,idle-state".
-
-Other required and optional properties are specified in [1].
-
-Example:
-
-	idle-states {
-		CPU_SPC: spc {
-			compatible = "qcom,idle-state-spc", "arm,idle-state";
-			entry-latency-us = <150>;
-			exit-latency-us = <200>;
-			min-residency-us = <2000>;
-		};
-	};
-
-[1]. Documentation/devicetree/bindings/cpu/idle-states.yaml
diff --git a/Documentation/devicetree/bindings/cpu/idle-states.yaml b/Documentation/devicetree/bindings/cpu/idle-states.yaml
index b3a5356f9916e..239480ef7c30d 100644
--- a/Documentation/devicetree/bindings/cpu/idle-states.yaml
+++ b/Documentation/devicetree/bindings/cpu/idle-states.yaml
@@ -243,7 +243,64 @@ description: |+
   just supports idle_standby, an idle-states node is not required.
 
   ===========================================
-  6 - References
+  6 - Qualcomm specific STATES
+  ===========================================
+
+  Idle states have different enter/exit latency and residency values.
+  The idle states supported by the QCOM SoC are defined as -
+
+    * Standby
+    * Retention
+    * Standalone Power Collapse (Standalone PC or SPC)
+    * Power Collapse (PC)
+
+  Standby: Standby does a little more in addition to architectural clock gating.
+  When the WFI instruction is executed the ARM core would gate its internal
+  clocks. In addition to gating the clocks, QCOM cpus use this instruction as a
+  trigger to execute the SPM state machine. The SPM state machine waits for the
+  interrupt to trigger the core back in to active. This triggers the cache
+  hierarchy to enter standby states, when all cpus are idle. An interrupt brings
+  the SPM state machine out of its wait, the next step is to ensure that the
+  cache hierarchy is also out of standby, and then the cpu is allowed to resume
+  execution. This state is defined as a generic ARM WFI state by the ARM cpuidle
+  driver and is not defined in the DT. The SPM state machine should be
+  configured to execute this state by default and after executing every other
+  state below.
+
+  Retention: Retention is a low power state where the core is clock gated and
+  the memory and the registers associated with the core are retained. The
+  voltage may be reduced to the minimum value needed to keep the processor
+  registers active. The SPM should be configured to execute the retention
+  sequence and would wait for interrupt, before restoring the cpu to execution
+  state. Retention may have a slightly higher latency than Standby.
+
+  Standalone PC: A cpu can power down and warmboot if there is a sufficient time
+  between the time it enters idle and the next known wake up. SPC mode is used
+  to indicate a core entering a power down state without consulting any other
+  cpu or the system resources. This helps save power only on that core.  The SPM
+  sequence for this idle state is programmed to power down the supply to the
+  core, wait for the interrupt, restore power to the core, and ensure the
+  system state including cache hierarchy is ready before allowing core to
+  resume. Applying power and resetting the core causes the core to warmboot
+  back into Elevation Level (EL) which trampolines the control back to the
+  kernel. Entering a power down state for the cpu, needs to be done by trapping
+  into a EL. Failing to do so, would result in a crash enforced by the warm boot
+  code in the EL for the SoC. On SoCs with write-back L1 cache, the cache has to
+  be flushed in s/w, before powering down the core.
+
+  Power Collapse: This state is similar to the SPC mode, but distinguishes
+  itself in that the cpu acknowledges and permits the SoC to enter deeper sleep
+  modes. In a hierarchical power domain SoC, this means L2 and other caches can
+  be flushed, system bus, clocks - lowered, and SoC main XO clock gated and
+  voltages reduced, provided all cpus enter this state.  Since the span of low
+  power modes possible at this state is vast, the exit latency and the residency
+  of this low power mode would be considered high even though at a cpu level,
+  this essentially is cpu power down. The SPM in this state also may handshake
+  with the Resource power manager (RPM) processor in the SoC to indicate a
+  complete application processor subsystem shut down.
+
+  ===========================================
+  7 - References
   ===========================================
 
   [1] ARM Linux Kernel documentation - CPUs bindings
@@ -301,9 +358,16 @@ patternProperties:
 
     properties:
       compatible:
-        enum:
-          - arm,idle-state
-          - riscv,idle-state
+        oneOf:
+          - items:
+              - enum:
+                  - qcom,idle-state-ret
+                  - qcom,idle-state-spc
+                  - qcom,idle-state-pc
+              - const: arm,idle-state
+          - enum:
+              - arm,idle-state
+              - riscv,idle-state
 
       arm,psci-suspend-param:
         $ref: /schemas/types.yaml#/definitions/uint32
@@ -852,4 +916,13 @@ examples:
         };
     };
 
+    // Example 4 - Qualcomm SPC
+    idle-states {
+      cpu_spc: cpu-spc {
+        compatible = "qcom,idle-state-spc", "arm,idle-state";
+        entry-latency-us = <150>;
+        exit-latency-us = <200>;
+        min-residency-us = <2000>;
+      };
+    };
 ...
-- 
GitLab


From 9de97e2a4e3afc6454bcb7be28beb2f20c7559a6 Mon Sep 17 00:00:00 2001
From: Michael Trimarchi <michael@amarulasolutions.com>
Date: Wed, 13 Dec 2023 15:03:44 +0100
Subject: [PATCH 2386/4076] dt-bindings: display: panel: Add synaptics r63353
 panel controller

Add documentation for "synaptics,r63353" panel.

Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231213140437.2769508-4-dario.binacchi@amarulasolutions.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../display/panel/synaptics,r63353.yaml       | 61 +++++++++++++++++++
 1 file changed, 61 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/synaptics,r63353.yaml

diff --git a/Documentation/devicetree/bindings/display/panel/synaptics,r63353.yaml b/Documentation/devicetree/bindings/display/panel/synaptics,r63353.yaml
new file mode 100644
index 0000000000000..e5617d125567d
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/synaptics,r63353.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/synaptics,r63353.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Synaptics R63353 based MIPI-DSI panels
+
+maintainers:
+  - Michael Trimarchi <michael@amarulasolutions.com>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - sharp,ls068b3sx02
+      - const: syna,r63353
+
+  avdd-supply: true
+  dvdd-supply: true
+  reg: true
+
+required:
+  - compatible
+  - avdd-supply
+  - dvdd-supply
+  - reg
+  - reset-gpios
+  - port
+  - backlight
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    dsi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        panel@0 {
+            compatible = "sharp,ls068b3sx02", "syna,r63353";
+            reg = <0>;
+            avdd-supply = <&avdd_display>;
+            dvdd-supply = <&dvdd_display>;
+            reset-gpios = <&r_pio 0 5 GPIO_ACTIVE_LOW>; /* PL05 */
+            backlight = <&backlight>;
+
+            port {
+                panel_in: endpoint {
+                    remote-endpoint = <&mipi_dsi_out>;
+                };
+            };
+        };
+    };
+
+...
-- 
GitLab


From a1499b7541cc26bac360cf07e49fd1e2ab3dd17f Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 14 Dec 2023 13:55:52 -0600
Subject: [PATCH 2387/4076] media: dt-bindings: samsung,s5p-mfc: Fix iommu
 properties schemas

The iommus and iommu-names property schemas have several issues. First,
'iommus-names' in the if/then schemas is the wrong name. As all the names
are the same, they can be defined at the top level instead. Then the
if/then schemas just need to define how many entries. The iommus if/then
schemas are also redundant. Best I can tell, the desire was to require 2
entries for "samsung,exynos5433-mfc", "samsung,mfc-v5", "samsung,mfc-v6",
and "samsung,mfc-v8".

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Aakarsh Jain <aakarsh.jain@samsung.com>
Link: https://lore.kernel.org/r/20231214195553.862920-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../bindings/media/samsung,s5p-mfc.yaml       | 33 ++++++++-----------
 1 file changed, 13 insertions(+), 20 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/samsung,s5p-mfc.yaml b/Documentation/devicetree/bindings/media/samsung,s5p-mfc.yaml
index 084b44582a434..4c3250985ac36 100644
--- a/Documentation/devicetree/bindings/media/samsung,s5p-mfc.yaml
+++ b/Documentation/devicetree/bindings/media/samsung,s5p-mfc.yaml
@@ -49,7 +49,9 @@ properties:
 
   iommu-names:
     minItems: 1
-    maxItems: 2
+    items:
+      - const: left
+      - const: right
 
   power-domains:
     maxItems: 1
@@ -84,7 +86,7 @@ allOf:
             - const: sclk_mfc
         iommus:
           maxItems: 1
-        iommus-names: false
+        iommu-names: false
 
   - if:
       properties:
@@ -102,11 +104,9 @@ allOf:
             - const: aclk
             - const: aclk_xiu
         iommus:
-          maxItems: 2
-        iommus-names:
-          items:
-            - const: left
-            - const: right
+          minItems: 2
+        iommu-names:
+          minItems: 2
 
   - if:
       properties:
@@ -123,11 +123,9 @@ allOf:
             - const: mfc
             - const: sclk_mfc
         iommus:
-          maxItems: 2
-        iommus-names:
-          items:
-            - const: left
-            - const: right
+          minItems: 2
+        iommu-names:
+          minItems: 2
 
   - if:
       properties:
@@ -144,11 +142,9 @@ allOf:
           items:
             - const: mfc
         iommus:
-          maxItems: 2
-        iommus-names:
-          items:
-            - const: left
-            - const: right
+          minItems: 2
+        iommu-names:
+          minItems: 2
 
   - if:
       properties:
@@ -161,9 +157,6 @@ allOf:
         clocks:
           minItems: 1
           maxItems: 2
-        iommus:
-          minItems: 1
-          maxItems: 2
 
 examples:
   - |
-- 
GitLab


From 30e0bbf50a704750d86c986744b7fb1e6f4c3c1d Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 13 Dec 2023 16:42:19 -0600
Subject: [PATCH 2388/4076] dt-bindings: mmc: sdhci-pxa: Fix 'regs' typo

The correct property name is 'reg' not 'regs'.

Fixes: ae5c0585dfc2 ("dt-bindings: mmc: Convert sdhci-pxa to json-schema")
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231213224219.2191721-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/mmc/sdhci-pxa.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/mmc/sdhci-pxa.yaml b/Documentation/devicetree/bindings/mmc/sdhci-pxa.yaml
index 09455f9fa8deb..4869ddef36fd8 100644
--- a/Documentation/devicetree/bindings/mmc/sdhci-pxa.yaml
+++ b/Documentation/devicetree/bindings/mmc/sdhci-pxa.yaml
@@ -18,7 +18,7 @@ allOf:
             const: marvell,armada-380-sdhci
     then:
       properties:
-        regs:
+        reg:
           minItems: 3
         reg-names:
           minItems: 3
@@ -26,7 +26,7 @@ allOf:
         - reg-names
     else:
       properties:
-        regs:
+        reg:
           maxItems: 1
         reg-names:
           maxItems: 1
-- 
GitLab


From 76156d06769b20fed37d09b505808a74433b5e55 Mon Sep 17 00:00:00 2001
From: Mao Jinlong <quic_jinlmao@quicinc.com>
Date: Sat, 9 Dec 2023 23:26:28 -0800
Subject: [PATCH 2389/4076] dt-bindings: arm: Add remote etm dt-binding

Remote ETM(Embedded Trace Macrocell) is to capture information of
the executed processor instructions of remote processors like modem.
Add new coresight-remote-etm.yaml file describing the bindings
required to define coresight remote etm in the device trees.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Mao Jinlong <quic_jinlmao@quicinc.com>
Link: https://lore.kernel.org/r/20231210072633.4243-2-quic_jinlmao@quicinc.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../arm/qcom,coresight-remote-etm.yaml        | 51 +++++++++++++++++++
 1 file changed, 51 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/arm/qcom,coresight-remote-etm.yaml

diff --git a/Documentation/devicetree/bindings/arm/qcom,coresight-remote-etm.yaml b/Documentation/devicetree/bindings/arm/qcom,coresight-remote-etm.yaml
new file mode 100644
index 0000000000000..4fd5752978cd0
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/qcom,coresight-remote-etm.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/qcom,coresight-remote-etm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Coresight Remote ETM(Embedded Trace Macrocell)
+
+maintainers:
+  - Jinlong Mao <quic_jinlmao@quicinc.com>
+  - Tao Zhang <quic_taozha@quicinc.com>
+
+description:
+  Support for ETM trace collection on remote processor using coresight
+  framework. Enabling this will allow turning on ETM tracing on remote
+  processor like modem processor via sysfs and collecting the trace
+  via coresight TMC sinks.
+
+properties:
+  compatible:
+    const: qcom,coresight-remote-etm
+
+  out-ports:
+    $ref: /schemas/graph.yaml#/properties/ports
+    additionalProperties: false
+
+    properties:
+      port:
+        description: Output connection to the CoreSight Trace bus.
+        $ref: /schemas/graph.yaml#/properties/port
+
+required:
+  - compatible
+  - out-ports
+
+additionalProperties: false
+
+examples:
+  - |
+    etm {
+        compatible = "qcom,coresight-remote-etm";
+
+        out-ports {
+            port {
+                modem_etm0_out_funnel_modem: endpoint {
+                    remote-endpoint = <&funnel_modem_in_modem_etm0>;
+                };
+            };
+        };
+    };
+...
-- 
GitLab


From 4ec295efef1ac4969a9667b40e1e91fa45d90c4a Mon Sep 17 00:00:00 2001
From: Alex Bee <knaerzche@gmail.com>
Date: Fri, 22 Dec 2023 18:41:52 +0100
Subject: [PATCH 2390/4076] dt-bindings: display: rockchip,inno-hdmi: Document
 RK3128 compatible

The integration for this SoC is different from the currently existing: It
needs it's PHY's reference clock rate to calculate the DDC bus frequency
correctly. The controller is also part of a powerdomain, so this gets added
as an mandatory property for this variant.

Signed-off-by: Alex Bee <knaerzche@gmail.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231222174220.55249-2-knaerzche@gmail.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../display/rockchip/rockchip,inno-hdmi.yaml  | 40 ++++++++++++++++++-
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip,inno-hdmi.yaml b/Documentation/devicetree/bindings/display/rockchip/rockchip,inno-hdmi.yaml
index 96889c86849ab..be78dcfa1c762 100644
--- a/Documentation/devicetree/bindings/display/rockchip/rockchip,inno-hdmi.yaml
+++ b/Documentation/devicetree/bindings/display/rockchip/rockchip,inno-hdmi.yaml
@@ -14,6 +14,7 @@ properties:
   compatible:
     enum:
       - rockchip,rk3036-inno-hdmi
+      - rockchip,rk3128-inno-hdmi
 
   reg:
     maxItems: 1
@@ -22,10 +23,19 @@ properties:
     maxItems: 1
 
   clocks:
-    maxItems: 1
+    minItems: 1
+    items:
+      - description: The HDMI controller main clock
+      - description: The HDMI PHY reference clock
 
   clock-names:
-    const: pclk
+    minItems: 1
+    items:
+      - const: pclk
+      - const: ref
+
+  power-domains:
+    maxItems: 1
 
   ports:
     $ref: /schemas/graph.yaml#/properties/ports
@@ -55,6 +65,32 @@ required:
   - pinctrl-names
   - ports
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: rockchip,rk3036-inno-hdmi
+
+    then:
+      properties:
+        power-domains: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: rockchip,rk3128-inno-hdmi
+
+    then:
+      properties:
+        clocks:
+          minItems: 2
+        clock-names:
+          minItems: 2
+      required:
+        - power-domains
+
 additionalProperties: false
 
 examples:
-- 
GitLab


From 26c9d152ebf3a16661f2d2a619bd71099c71299d Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sun, 17 Dec 2023 11:13:31 +0100
Subject: [PATCH 2391/4076] dt-bindings: tpm: Consolidate TCG TIS bindings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A significant number of Trusted Platform Modules conform to the "TIS"
specification published by the Trusted Computing Group ("TCG PC Client
Specific TPM Interface Specification").  These chips typically use an
SPI, I²C or LPC bus as transport (via MMIO in the latter case).  Some
of them even support multiple of those buses (selectable through a
config strap) or the same chip is available in multiple SKUs, each with
a different bus interface.

The devicetree bindings for these TPMs have not been converted to DT
schema yet and are spread out across 3 generic files and 2 chip-specific
files.  A few TPM compatible strings were added to trivial-devices.yaml
even though additional properties are documented in the plaintext
bindings.

Consolidate the devicetree bindings into 3 yaml files, one per bus.

Move common properties to a separate tpm-common.yaml.

Document compatible strings which are supported by the TPM TIS driver
but were neglected to be added to the devicetree bindings.

Document the memory-region property recently introduced by commit
1e2714bb83fc ("tpm: Add reserved memory event log").

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/953fd4c7519030db88e5b5e12ab6307414ebdd21.1702806810.git.lukas@wunner.de
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../bindings/security/tpm/st33zp24-i2c.txt    | 34 -------
 .../bindings/security/tpm/st33zp24-spi.txt    | 32 -------
 .../bindings/security/tpm/tpm-i2c.txt         | 26 ------
 .../bindings/security/tpm/tpm_tis_mmio.txt    | 25 ------
 .../bindings/security/tpm/tpm_tis_spi.txt     | 23 -----
 .../bindings/tpm/tcg,tpm-tis-i2c.yaml         | 90 +++++++++++++++++++
 .../bindings/tpm/tcg,tpm-tis-mmio.yaml        | 49 ++++++++++
 .../bindings/tpm/tcg,tpm_tis-spi.yaml         | 75 ++++++++++++++++
 .../devicetree/bindings/tpm/tpm-common.yaml   | 87 ++++++++++++++++++
 .../devicetree/bindings/trivial-devices.yaml  | 16 ----
 10 files changed, 301 insertions(+), 156 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
 delete mode 100644 Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
 delete mode 100644 Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
 delete mode 100644 Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
 delete mode 100644 Documentation/devicetree/bindings/security/tpm/tpm_tis_spi.txt
 create mode 100644 Documentation/devicetree/bindings/tpm/tcg,tpm-tis-i2c.yaml
 create mode 100644 Documentation/devicetree/bindings/tpm/tcg,tpm-tis-mmio.yaml
 create mode 100644 Documentation/devicetree/bindings/tpm/tcg,tpm_tis-spi.yaml
 create mode 100644 Documentation/devicetree/bindings/tpm/tpm-common.yaml

diff --git a/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt b/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
deleted file mode 100644
index 0dc121b6eace9..0000000000000
--- a/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
+++ /dev/null
@@ -1,34 +0,0 @@
-* STMicroelectronics SAS. ST33ZP24 TPM SoC
-
-Required properties:
-- compatible: Should be "st,st33zp24-i2c".
-- clock-frequency: I²C work frequency.
-- reg: address on the bus
-
-Optional ST33ZP24 Properties:
-- interrupts: GPIO interrupt to which the chip is connected
-- lpcpd-gpios: Output GPIO pin used for ST33ZP24 power management D1/D2 state.
-If set, power must be present when the platform is going into sleep/hibernate mode.
-
-Optional SoC Specific Properties:
-- pinctrl-names: Contains only one value - "default".
-- pintctrl-0: Specifies the pin control groups used for this controller.
-
-Example (for ARM-based BeagleBoard xM with ST33ZP24 on I2C2):
-
-&i2c2 {
-
-
-        st33zp24: st33zp24@13 {
-
-                compatible = "st,st33zp24-i2c";
-
-                reg = <0x13>;
-                clock-frequency = <400000>;
-
-                interrupt-parent = <&gpio5>;
-                interrupts = <7 IRQ_TYPE_LEVEL_HIGH>;
-
-                lpcpd-gpios = <&gpio5 15 GPIO_ACTIVE_HIGH>;
-        };
-};
diff --git a/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt b/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
deleted file mode 100644
index 37198971f17b6..0000000000000
--- a/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-* STMicroelectronics SAS. ST33ZP24 TPM SoC
-
-Required properties:
-- compatible: Should be "st,st33zp24-spi".
-- spi-max-frequency: Maximum SPI frequency (<= 10000000).
-
-Optional ST33ZP24 Properties:
-- interrupts: GPIO interrupt to which the chip is connected
-- lpcpd-gpios: Output GPIO pin used for ST33ZP24 power management D1/D2 state.
-If set, power must be present when the platform is going into sleep/hibernate mode.
-
-Optional SoC Specific Properties:
-- pinctrl-names: Contains only one value - "default".
-- pintctrl-0: Specifies the pin control groups used for this controller.
-
-Example (for ARM-based BeagleBoard xM with ST33ZP24 on SPI4):
-
-&mcspi4 {
-
-
-        st33zp24@0 {
-
-                compatible = "st,st33zp24-spi";
-
-                spi-max-frequency = <10000000>;
-
-                interrupt-parent = <&gpio5>;
-                interrupts = <7 IRQ_TYPE_LEVEL_HIGH>;
-
-                lpcpd-gpios = <&gpio5 15 GPIO_ACTIVE_HIGH>;
-        };
-};
diff --git a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
deleted file mode 100644
index a65d7b71e81a2..0000000000000
--- a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
+++ /dev/null
@@ -1,26 +0,0 @@
-* Device Tree Bindings for I2C based Trusted Platform Module(TPM)
-
-Required properties:
-
-- compatible     : 'manufacturer,model', eg. nuvoton,npct650
-- label          : human readable string describing the device, eg. "tpm"
-- linux,sml-base : 64-bit base address of the reserved memory allocated for
-                   the firmware event log
-- linux,sml-size : size of the memory allocated for the firmware event log
-
-Optional properties:
-
-- powered-while-suspended: present when the TPM is left powered on between
-                           suspend and resume (makes the suspend/resume
-                           callbacks do nothing).
-
-Example (for OpenPower Systems with Nuvoton TPM 2.0 on I2C)
-----------------------------------------------------------
-
-tpm@57 {
-	reg = <0x57>;
-	label = "tpm";
-	compatible = "nuvoton,npct650", "nuvoton,npct601";
-	linux,sml-base = <0x7f 0xfd450000>;
-	linux,sml-size = <0x10000>;
-};
diff --git a/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt b/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
deleted file mode 100644
index 7c6304426da1a..0000000000000
--- a/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
+++ /dev/null
@@ -1,25 +0,0 @@
-Trusted Computing Group MMIO Trusted Platform Module
-
-The TCG defines multi vendor standard for accessing a TPM chip, this
-is the standard protocol defined to access the TPM via MMIO. Typically
-this interface will be implemented over Intel's LPC bus.
-
-Refer to the 'TCG PC Client Specific TPM Interface Specification (TIS)' TCG
-publication for the specification.
-
-Required properties:
-
-- compatible: should contain a string below for the chip, followed by
-              "tcg,tpm-tis-mmio". Valid chip strings are:
-	          * "atmel,at97sc3204"
-- reg: The location of the MMIO registers, should be at least 0x5000 bytes
-- interrupts: An optional interrupt indicating command completion.
-
-Example:
-
-	tpm_tis@90000 {
-				compatible = "atmel,at97sc3204", "tcg,tpm-tis-mmio";
-				reg = <0x90000 0x5000>;
-				interrupt-parent = <&EIC0>;
-				interrupts = <1 2>;
-	};
diff --git a/Documentation/devicetree/bindings/security/tpm/tpm_tis_spi.txt b/Documentation/devicetree/bindings/security/tpm/tpm_tis_spi.txt
deleted file mode 100644
index b800667da92b8..0000000000000
--- a/Documentation/devicetree/bindings/security/tpm/tpm_tis_spi.txt
+++ /dev/null
@@ -1,23 +0,0 @@
-Required properties:
-- compatible: should be one of the following
-    "st,st33htpm-spi"
-    "infineon,slb9670"
-    "tcg,tpm_tis-spi"
-- spi-max-frequency: Maximum SPI frequency (depends on TPMs).
-
-Optional SoC Specific Properties:
-- pinctrl-names: Contains only one value - "default".
-- pintctrl-0: Specifies the pin control groups used for this controller.
-
-Example (for ARM-based BeagleBoard xM with TPM_TIS on SPI4):
-
-&mcspi4 {
-
-
-        tpm_tis@0 {
-
-                compatible = "tcg,tpm_tis-spi";
-
-                spi-max-frequency = <10000000>;
-        };
-};
diff --git a/Documentation/devicetree/bindings/tpm/tcg,tpm-tis-i2c.yaml b/Documentation/devicetree/bindings/tpm/tcg,tpm-tis-i2c.yaml
new file mode 100644
index 0000000000000..3ab4434b73524
--- /dev/null
+++ b/Documentation/devicetree/bindings/tpm/tcg,tpm-tis-i2c.yaml
@@ -0,0 +1,90 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/tpm/tcg,tpm-tis-i2c.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: I²C-attached Trusted Platform Module conforming to TCG TIS specification
+
+maintainers:
+  - Lukas Wunner <lukas@wunner.de>
+
+description: |
+  The Trusted Computing Group (TCG) has defined a multi-vendor standard
+  for accessing a TPM chip.  It can be transported over various buses,
+  one of them being I²C.  The standard is named:
+  TCG PC Client Specific TPM Interface Specification (TIS)
+  https://trustedcomputinggroup.org/resource/pc-client-work-group-pc-client-specific-tpm-interface-specification-tis/
+
+  The I²C interface was not originally part of the standard, but added
+  in 2017 with a separate document:
+  TCG PC Client Platform TPM Profile Specification for TPM 2.0 (PTP)
+  https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
+
+  Recent TPM 2.0 chips conform to this generic interface, others use a
+  vendor-specific I²C interface.
+
+properties:
+  compatible:
+    oneOf:
+      - description: Generic TPM 2.0 chips conforming to TCG PTP interface
+        items:
+          - enum:
+              - infineon,slb9673
+              - nuvoton,npct75x
+          - const: tcg,tpm-tis-i2c
+
+      - description: TPM 1.2 and 2.0 chips with vendor-specific I²C interface
+        items:
+          - enum:
+              - atmel,at97sc3204t # TPM 1.2
+              - infineon,slb9635tt # TPM 1.2 (maximum 100 kHz)
+              - infineon,slb9645tt # TPM 1.2 (maximum 400 kHz)
+              - infineon,tpm_i2c_infineon # TPM 1.2
+              - nuvoton,npct501 # TPM 1.2
+              - nuvoton,npct601 # TPM 2.0
+              - st,st33zp24-i2c # TPM 2.0
+              - winbond,wpct301 # TPM 1.2
+
+  reg:
+    description: address of TPM on the I²C bus
+
+allOf:
+  - $ref: tpm-common.yaml#
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        tpm@57 {
+            label = "tpm";
+            compatible = "nuvoton,npct601";
+            reg = <0x57>;
+            linux,sml-base = <0x7f 0xfd450000>;
+            linux,sml-size = <0x10000>;
+        };
+    };
+
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        tpm@13 {
+            reg = <0x13>;
+            compatible = "st,st33zp24-i2c";
+            interrupt-parent = <&gpio5>;
+            interrupts = <7 IRQ_TYPE_LEVEL_HIGH>;
+            lpcpd-gpios = <&gpio5 15 GPIO_ACTIVE_HIGH>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/tpm/tcg,tpm-tis-mmio.yaml b/Documentation/devicetree/bindings/tpm/tcg,tpm-tis-mmio.yaml
new file mode 100644
index 0000000000000..87bce0692129f
--- /dev/null
+++ b/Documentation/devicetree/bindings/tpm/tcg,tpm-tis-mmio.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/tpm/tcg,tpm-tis-mmio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MMIO-accessed Trusted Platform Module conforming to TCG TIS specification
+
+maintainers:
+  - Lukas Wunner <lukas@wunner.de>
+
+description: |
+  The Trusted Computing Group (TCG) has defined a multi-vendor standard
+  for accessing a TPM chip.  It can be transported over various buses,
+  one of them being LPC (via MMIO).  The standard is named:
+  TCG PC Client Specific TPM Interface Specification (TIS)
+  https://trustedcomputinggroup.org/resource/pc-client-work-group-pc-client-specific-tpm-interface-specification-tis/
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - at97sc3201
+          - atmel,at97sc3204
+          - socionext,synquacer-tpm-mmio
+      - const: tcg,tpm-tis-mmio
+
+  reg:
+    description:
+      location and length of the MMIO registers, length should be
+      at least 0x5000 bytes
+
+allOf:
+  - $ref: tpm-common.yaml#
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    tpm@90000 {
+        compatible = "atmel,at97sc3204", "tcg,tpm-tis-mmio";
+        reg = <0x90000 0x5000>;
+        interrupt-parent = <&EIC0>;
+        interrupts = <1 2>;
+    };
diff --git a/Documentation/devicetree/bindings/tpm/tcg,tpm_tis-spi.yaml b/Documentation/devicetree/bindings/tpm/tcg,tpm_tis-spi.yaml
new file mode 100644
index 0000000000000..c3413b47ac3df
--- /dev/null
+++ b/Documentation/devicetree/bindings/tpm/tcg,tpm_tis-spi.yaml
@@ -0,0 +1,75 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/tpm/tcg,tpm_tis-spi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: SPI-attached Trusted Platform Module conforming to TCG TIS specification
+
+maintainers:
+  - Lukas Wunner <lukas@wunner.de>
+
+description: |
+  The Trusted Computing Group (TCG) has defined a multi-vendor standard
+  for accessing a TPM chip.  It can be transported over various buses,
+  one of them being SPI.  The standard is named:
+  TCG PC Client Specific TPM Interface Specification (TIS)
+  https://trustedcomputinggroup.org/resource/pc-client-work-group-pc-client-specific-tpm-interface-specification-tis/
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - infineon,slb9670
+          - st,st33htpm-spi
+          - st,st33zp24-spi
+      - const: tcg,tpm_tis-spi
+
+allOf:
+  - $ref: tpm-common.yaml#
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: st,st33zp24-spi
+    then:
+      properties:
+        spi-max-frequency:
+          maximum: 10000000
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        tpm@0 {
+            reg = <0>;
+            compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
+            spi-max-frequency = <10000000>;
+        };
+    };
+
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        tpm@0 {
+            reg = <0>;
+            compatible = "st,st33zp24-spi", "tcg,tpm_tis-spi";
+            spi-max-frequency = <10000000>;
+            interrupt-parent = <&gpio5>;
+            interrupts = <7 IRQ_TYPE_LEVEL_HIGH>;
+            lpcpd-gpios = <&gpio5 15 GPIO_ACTIVE_HIGH>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/tpm/tpm-common.yaml b/Documentation/devicetree/bindings/tpm/tpm-common.yaml
new file mode 100644
index 0000000000000..90390624a8be5
--- /dev/null
+++ b/Documentation/devicetree/bindings/tpm/tpm-common.yaml
@@ -0,0 +1,87 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/tpm/tpm-common.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Trusted Platform Module common properties
+
+maintainers:
+  - Lukas Wunner <lukas@wunner.de>
+
+properties:
+  $nodename:
+    pattern: '^tpm(@[0-9a-f]+)?$'
+
+  interrupts:
+    description: indicates command completion
+    maxItems: 1
+
+  label:
+    description: human readable string describing the device, e.g. "tpm"
+
+  linux,sml-base:
+    description:
+      base address of reserved memory allocated for firmware event log
+    $ref: /schemas/types.yaml#/definitions/uint64
+
+  linux,sml-size:
+    description:
+      size of reserved memory allocated for firmware event log
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  memory-region:
+    description: reserved memory allocated for firmware event log
+    maxItems: 1
+
+  powered-while-suspended:
+    description:
+      present when the TPM is left powered on between suspend and resume
+      (makes the suspend/resume callbacks do nothing)
+    type: boolean
+
+  resets:
+    description: Reset controller to reset the TPM
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+  reset-gpios:
+    description: Output GPIO pin to reset the TPM
+    maxItems: 1
+
+# must always have both linux,sml-base and linux,sml-size
+dependentRequired:
+  linux,sml-base: ['linux,sml-size']
+  linux,sml-size: ['linux,sml-base']
+
+# must only have either memory-region or linux,sml-base
+# as well as either resets or reset-gpios
+dependentSchemas:
+  memory-region:
+    properties:
+      linux,sml-base: false
+  linux,sml-base:
+    properties:
+      memory-region: false
+  resets:
+    properties:
+      reset-gpios: false
+  reset-gpios:
+    properties:
+      resets: false
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            pattern: '^st,st33zp24'
+    then:
+      properties:
+        lpcpd-gpios:
+          description:
+            Output GPIO pin used for ST33ZP24 power management of D1/D2 state.
+            If set, power must be present when the platform is going into
+            sleep/hibernate mode.
+          maxItems: 1
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index c3190f2a168a2..29aed5ddba6be 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -49,8 +49,6 @@ properties:
           - ams,iaq-core
             # i2c serial eeprom (24cxx)
           - at,24c08
-            # i2c trusted platform module (TPM)
-          - atmel,at97sc3204t
             # ATSHA204 - i2c h/w symmetric crypto module
           - atmel,atsha204
             # ATSHA204A - i2c h/w symmetric crypto module
@@ -145,12 +143,6 @@ properties:
           - infineon,ir38263
             # Infineon IRPS5401 Voltage Regulator (PMIC)
           - infineon,irps5401
-            # Infineon SLB9635 (Soft-) I2C TPM (old protocol, max 100khz)
-          - infineon,slb9635tt
-            # Infineon SLB9645 I2C TPM (new protocol, max 400khz)
-          - infineon,slb9645tt
-            # Infineon SLB9673 I2C TPM 2.0
-          - infineon,slb9673
             # Infineon TLV493D-A1B6 I2C 3D Magnetic Sensor
           - infineon,tlv493d-a1b6
             # Infineon Multi-phase Digital VR Controller xdpe11280
@@ -301,10 +293,6 @@ properties:
           - national,lm85
             # I2C ±0.33°C Accurate, 12-Bit + Sign Temperature Sensor and Thermal Window Comparator
           - national,lm92
-            # i2c trusted platform module (TPM)
-          - nuvoton,npct501
-            # i2c trusted platform module (TPM2)
-          - nuvoton,npct601
             # Nuvoton Temperature Sensor
           - nuvoton,w83773g
             # OKI ML86V7667 video decoder
@@ -349,8 +337,6 @@ properties:
           - silabs,si7020
             # Skyworks SKY81452: Six-Channel White LED Driver with Touch Panel Bias Supply
           - skyworks,sky81452
-            # Socionext SynQuacer TPM MMIO module
-          - socionext,synquacer-tpm-mmio
             # SparkFun Qwiic Joystick (COM-15168) with i2c interface
           - sparkfun,qwiic-joystick
             # i2c serial eeprom (24cxx)
@@ -405,8 +391,6 @@ properties:
           - winbond,w83793
             # Vicor Corporation Digital Supervisor
           - vicor,pli1209bc
-            # i2c trusted platform module (TPM)
-          - winbond,wpct301
 
 required:
   - compatible
-- 
GitLab


From d3b8b0855a1181b5a9f8ef58022474f34cba09fd Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sun, 17 Dec 2023 11:13:32 +0100
Subject: [PATCH 2392/4076] dt-bindings: tpm: Convert Google Cr50 bindings to
 DT schema
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Convert the devicetree bindings for the Google Security Chip H1 running
Cr50 firmware to DT schema.

The chip can be attached to SPI or I²C.  Existing devicetrees use the
same "google,cr50" compatible string for both cases without additionally
specifying a generic "tcg,tpm_tis-spi" or "tcg,tpm-tis-i2c" compatible.

The chip therefore cannot be documented in the tcg,tpm_tis-spi.yaml and
tcg,tpm-tis-i2c.yaml schemas:  The validator would select both of them
and complain about SPI properties when the chip is an I²C peripheral.

So document the chip in a schema of its own which includes both, SPI and
I²C properties by reference.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/52635205818ab201cacb0c0f37c7fa48149c7f8e.1702806810.git.lukas@wunner.de
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../bindings/security/tpm/google,cr50.txt     | 19 ------
 .../devicetree/bindings/tpm/google,cr50.yaml  | 65 +++++++++++++++++++
 2 files changed, 65 insertions(+), 19 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/security/tpm/google,cr50.txt
 create mode 100644 Documentation/devicetree/bindings/tpm/google,cr50.yaml

diff --git a/Documentation/devicetree/bindings/security/tpm/google,cr50.txt b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt
deleted file mode 100644
index cd69c2efdd371..0000000000000
--- a/Documentation/devicetree/bindings/security/tpm/google,cr50.txt
+++ /dev/null
@@ -1,19 +0,0 @@
-* H1 Secure Microcontroller with Cr50 Firmware on SPI Bus.
-
-H1 Secure Microcontroller running Cr50 firmware provides several
-functions, including TPM-like functionality. It communicates over
-SPI using the FIFO protocol described in the PTP Spec, section 6.
-
-Required properties:
-- compatible: Should be "google,cr50".
-- spi-max-frequency: Maximum SPI frequency.
-
-Example:
-
-&spi0 {
-	tpm@0 {
-		compatible = "google,cr50";
-		reg = <0>;
-		spi-max-frequency = <800000>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/tpm/google,cr50.yaml b/Documentation/devicetree/bindings/tpm/google,cr50.yaml
new file mode 100644
index 0000000000000..9302e12e9fc7f
--- /dev/null
+++ b/Documentation/devicetree/bindings/tpm/google,cr50.yaml
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/tpm/google,cr50.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Google Security Chip H1 (running Cr50 firmware)
+
+maintainers:
+  - Andrey Pronin <apronin@chromium.org>
+
+description: |
+  Google has designed a family of security chips called "Titan".
+  One member is the H1 built into Chromebooks and running Cr50 firmware:
+  https://www.osfc.io/2018/talks/google-secure-microcontroller-and-ccd-closed-case-debugging/
+
+  The chip provides several functions, including TPM 2.0 like functionality.
+  It communicates over SPI or I²C using the FIFO protocol described in the
+  TCG PC Client Platform TPM Profile Specification for TPM 2.0 (PTP), sec 6:
+  https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
+
+properties:
+  compatible:
+    const: google,cr50
+
+allOf:
+  - $ref: tpm-common.yaml#
+
+anyOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+  - $ref: tcg,tpm-tis-i2c.yaml#/properties/reg
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        tpm@0 {
+            reg = <0>;
+            compatible = "google,cr50";
+            spi-max-frequency = <800000>;
+        };
+    };
+
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        tpm@50 {
+            compatible = "google,cr50";
+            reg = <0x50>;
+            interrupts-extended = <&pio 88 IRQ_TYPE_EDGE_FALLING>;
+            pinctrl-names = "default";
+            pinctrl-0 = <&cr50_int>;
+        };
+    };
-- 
GitLab


From cd6366c0c9996ff8d33c1f68d58869e0e31de4d9 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sun, 17 Dec 2023 11:13:33 +0100
Subject: [PATCH 2393/4076] dt-bindings: tpm: Convert IBM vTPM bindings to DT
 schema

Convert the devicetree bindings for the IBM Virtual Trusted Platform
Module to DT schema.  Drop properties which are already documented in
tpm-common.yaml.

Document the "IBM,vtpm20" compatible string introduced by commit
18b3670d79ae ("tpm: ibmvtpm: Add support for TPM2").

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/5c41e045dfe7cc3f27dd41c08c62ed8c4a90d8a4.1702806810.git.lukas@wunner.de
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../bindings/security/tpm/ibmvtpm.txt         |  41 -------
 .../devicetree/bindings/tpm/ibm,vtpm.yaml     | 104 ++++++++++++++++++
 2 files changed, 104 insertions(+), 41 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/security/tpm/ibmvtpm.txt
 create mode 100644 Documentation/devicetree/bindings/tpm/ibm,vtpm.yaml

diff --git a/Documentation/devicetree/bindings/security/tpm/ibmvtpm.txt b/Documentation/devicetree/bindings/security/tpm/ibmvtpm.txt
deleted file mode 100644
index d89f99971368c..0000000000000
--- a/Documentation/devicetree/bindings/security/tpm/ibmvtpm.txt
+++ /dev/null
@@ -1,41 +0,0 @@
-* Device Tree Bindings for IBM Virtual Trusted Platform Module(vtpm)
-
-Required properties:
-
-- compatible            : property name that conveys the platform architecture
-                          identifiers, as 'IBM,vtpm'
-- device_type           : specifies type of virtual device
-- interrupts            : property specifying the interrupt source number and
-                          sense code associated with this virtual I/O Adapters
-- ibm,my-drc-index      : integer index for the connector between the device
-                          and its parent - present only if Dynamic
-                          Reconfiguration(DR) Connector is enabled
-- ibm,#dma-address-cells: specifies the number of cells that are used to
-                          encode the physical address field of dma-window
-                          properties
-- ibm,#dma-size-cells   : specifies the number of cells that are used to
-                          encode the size field of dma-window properties
-- ibm,my-dma-window     : specifies DMA window associated with this virtual
-                          IOA
-- ibm,loc-code          : specifies the unique and persistent location code
-                          associated with this virtual I/O Adapters
-- linux,sml-base        : 64-bit base address of the reserved memory allocated
-                          for the firmware event log
-- linux,sml-size        : size of the memory allocated for the firmware event log
-
-Example (IBM Virtual Trusted Platform Module)
----------------------------------------------
-
-                vtpm@30000003 {
-                        ibm,#dma-size-cells = <0x2>;
-                        compatible = "IBM,vtpm";
-                        device_type = "IBM,vtpm";
-                        ibm,my-drc-index = <0x30000003>;
-                        ibm,#dma-address-cells = <0x2>;
-                        linux,sml-base = <0xc60e 0x0>;
-                        interrupts = <0xa0003 0x0>;
-                        ibm,my-dma-window = <0x10000003 0x0 0x0 0x0 0x10000000>;
-                        ibm,loc-code = "U8286.41A.10082DV-V3-C3";
-                        reg = <0x30000003>;
-                        linux,sml-size = <0xbce10200>;
-                };
diff --git a/Documentation/devicetree/bindings/tpm/ibm,vtpm.yaml b/Documentation/devicetree/bindings/tpm/ibm,vtpm.yaml
new file mode 100644
index 0000000000000..50a3fd31241cb
--- /dev/null
+++ b/Documentation/devicetree/bindings/tpm/ibm,vtpm.yaml
@@ -0,0 +1,104 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/tpm/ibm,vtpm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: IBM Virtual Trusted Platform Module (vTPM)
+
+maintainers:
+  - Nayna Jain <nayna@linux.ibm.com>
+
+description: |
+  Virtual TPM is used on IBM POWER7+ and POWER8 systems running POWERVM.
+  It is supported through the adjunct partition with firmware release 740
+  or higher.  With vTPM support, each lpar is able to have its own vTPM
+  without the physical TPM hardware.  The TPM functionality is provided by
+  communicating with the vTPM adjunct partition through Hypervisor calls
+  (Hcalls) and Command/Response Queue (CRQ) commands.
+
+properties:
+  compatible:
+    enum:
+      - IBM,vtpm
+      - IBM,vtpm20
+
+  device_type:
+    description:
+      type of virtual device
+    enum:
+      - IBM,vtpm
+      - IBM,vtpm20
+
+  reg:
+    maxItems: 1
+
+  'ibm,#dma-address-cells':
+    description:
+      number of cells that are used to encode the physical address field of
+      dma-window properties
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+
+  'ibm,#dma-size-cells':
+    description:
+      number of cells that are used to encode the size field of
+      dma-window properties
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+
+  ibm,my-dma-window:
+    description:
+      DMA window associated with this virtual I/O Adapter
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 5
+    maxItems: 5
+
+  ibm,my-drc-index:
+    description:
+      integer index for the connector between the device and its parent;
+      present only if Dynamic Reconfiguration (DR) Connector is enabled
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  ibm,loc-code:
+    description:
+      unique and persistent location code associated with this virtual
+      I/O Adapter
+    $ref: /schemas/types.yaml#/definitions/string
+
+required:
+  - compatible
+  - device_type
+  - reg
+  - interrupts
+  - ibm,#dma-address-cells
+  - ibm,#dma-size-cells
+  - ibm,my-dma-window
+  - ibm,my-drc-index
+  - ibm,loc-code
+  - linux,sml-base
+  - linux,sml-size
+
+allOf:
+  - $ref: tpm-common.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    soc {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        tpm@30000003 {
+            compatible = "IBM,vtpm";
+            device_type = "IBM,vtpm";
+            reg = <0x30000003>;
+            interrupts = <0xa0003 0x0>;
+            ibm,#dma-address-cells = <0x2>;
+            ibm,#dma-size-cells = <0x2>;
+            ibm,my-dma-window = <0x10000003 0x0 0x0 0x0 0x10000000>;
+            ibm,my-drc-index = <0x30000003>;
+            ibm,loc-code = "U8286.41A.10082DV-V3-C3";
+            linux,sml-base = <0xc60e 0x0>;
+            linux,sml-size = <0xbce10200>;
+        };
+    };
-- 
GitLab


From 3f4cc70d89099f8c40b6838a13ccac322dfa0a38 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sun, 17 Dec 2023 11:13:34 +0100
Subject: [PATCH 2394/4076] dt-bindings: tpm: Document Microsoft fTPM bindings

A driver for Microsoft's firmware-based Trusted Platform Module (fTPM)
was merged with commit 09e574831b27 ("tpm/tpm_ftpm_tee: A driver for
firmware TPM running inside TEE"), but its devicetree bindings were not.

This is the only remaining undocumented compatible string for a TPM,
so add a DT schema based on the patch linked below.

Link: https://lore.kernel.org/all/20190409184958.7476-2-sashal@kernel.org/
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/99523409eb5aec9276055ff358ae6f2ceb10be6d.1702806810.git.lukas@wunner.de
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../bindings/tpm/microsoft,ftpm.yaml          | 47 +++++++++++++++++++
 1 file changed, 47 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/tpm/microsoft,ftpm.yaml

diff --git a/Documentation/devicetree/bindings/tpm/microsoft,ftpm.yaml b/Documentation/devicetree/bindings/tpm/microsoft,ftpm.yaml
new file mode 100644
index 0000000000000..fdb81968f03d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/tpm/microsoft,ftpm.yaml
@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/tpm/microsoft,ftpm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microsoft firmware-based Trusted Platform Module (fTPM)
+
+maintainers:
+  - Thirupathaiah Annapureddy <thiruan@microsoft.com>
+  - Sasha Levin <sashal@kernel.org>
+
+description: |
+  Commodity CPU architectures, such as ARM and Intel CPUs, have started to
+  offer trusted computing features in their CPUs aimed at displacing dedicated
+  trusted hardware.  Unfortunately, these CPU architectures raise serious
+  challenges to building trusted systems because they omit providing secure
+  resources outside the CPU perimeter.
+
+  Microsoft's firmware-based TPM 2.0 (fTPM) leverages ARM TrustZone to overcome
+  these challenges and provide software with security guarantees similar to
+  those of dedicated trusted hardware.
+
+  https://www.microsoft.com/en-us/research/publication/ftpm-software-implementation-tpm-chip/
+  https://github.com/Microsoft/ms-tpm-20-ref/tree/main/Samples/ARM32-FirmwareTPM
+
+properties:
+  compatible:
+    const: microsoft,ftpm
+
+required:
+  - compatible
+  - linux,sml-base
+  - linux,sml-size
+
+allOf:
+  - $ref: tpm-common.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    tpm {
+        compatible = "microsoft,ftpm";
+        linux,sml-base = <0x0 0xc0000000>;
+        linux,sml-size = <0x10000>;
+    };
-- 
GitLab


From 09c49315f4c764366fdcf8ff096dd6fad8b8577c Mon Sep 17 00:00:00 2001
From: Muzammil Ashraf <m.muzzammilashraf@gmail.com>
Date: Tue, 19 Dec 2023 11:23:17 +0500
Subject: [PATCH 2395/4076] drivers: of: Fixed kernel doc warning

property.c:1220 : Fixed excess struct member definition warning
property.c:444 	: Fixed missing a blank line after declarations

Signed-off-by: Muzammil Ashraf <m.muzzammilashraf@gmail.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20231219062317.17650-1-muzammil@dreambigsemi.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/property.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/of/property.c b/drivers/of/property.c
index afdaefbd03f61..641a40cf5cf34 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -441,6 +441,7 @@ int of_property_read_string(const struct device_node *np, const char *propname,
 				const char **out_string)
 {
 	const struct property *prop = of_find_property(np, propname, NULL);
+
 	if (!prop)
 		return -EINVAL;
 	if (!prop->length)
@@ -1217,9 +1218,9 @@ static struct device_node *parse_##fname(struct device_node *np,	     \
  *
  * @parse_prop: function name
  *	parse_prop() finds the node corresponding to a supplier phandle
- * @parse_prop.np: Pointer to device node holding supplier phandle property
- * @parse_prop.prop_name: Name of property holding a phandle value
- * @parse_prop.index: For properties holding a list of phandles, this is the
+ *  parse_prop.np: Pointer to device node holding supplier phandle property
+ *  parse_prop.prop_name: Name of property holding a phandle value
+ *  parse_prop.index: For properties holding a list of phandles, this is the
  *		      index into the list
  * @optional: Describes whether a supplier is mandatory or not
  * @node_not_dev: The consumer node containing the property is never converted
-- 
GitLab


From 5e3ef45468196498ad1a7132f274d6709e3a1146 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Wed, 20 Dec 2023 14:55:37 +0000
Subject: [PATCH 2396/4076] dt-bindings: ignore paths outside kernel for
 DT_SCHEMA_FILES
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the location of the kernel sources contains the string that we're
filtering for using DT_SCHEMA_FILES, then all schemas will currently be
matched, returned and checked, not just the ones we actually expected.
As an example, if the kernel sources happen to be below a directory
'google', and DT_SCHEMA_FILES=google, everything is checked. More
common examples might be having the sources below people's home
directories that contain the string st or arm and then searching for
those. The list is endless.

Fix this by only matching for schemas below the kernel source's
bindings directory.

Note that I opted for the implementation here so as to not having to
deal with escaping DT_SCHEMA_FILES, which would have been the
alternative if the grep match itself had been updated.

Cc: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20231220145537.2163811-1-andre.draszik@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile
index 3e886194b043b..2323fd5b7cdae 100644
--- a/Documentation/devicetree/bindings/Makefile
+++ b/Documentation/devicetree/bindings/Makefile
@@ -28,7 +28,7 @@ $(obj)/%.example.dts: $(src)/%.yaml check_dtschema_version FORCE
 find_all_cmd = find $(srctree)/$(src) \( -name '*.yaml' ! \
 		-name 'processed-schema*' \)
 
-find_cmd = $(find_all_cmd) | grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))"
+find_cmd = $(find_all_cmd) | sed 's|^$(srctree)/$(src)/||' | grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | sed 's|^|$(srctree)/$(src)/|'
 CHK_DT_DOCS := $(shell $(find_cmd))
 
 quiet_cmd_yamllint = LINT    $(src)
-- 
GitLab


From 89fe46019a62bc1d0cb49c9615cb3520096c4bc1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ma=C3=ADra=20Canal?= <mcanal@igalia.com>
Date: Tue, 9 Jan 2024 08:30:40 -0300
Subject: [PATCH 2397/4076] drm/v3d: Fix support for register debugging on the
 RPi 4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RPi 4 uses V3D 4.2, which is currently not supported by the register
definition stated at `v3d_core_reg_defs`. We should be able to support
V3D 4.2, therefore, change the maximum version of the register
definition to 42, not 41.

Fixes: 0ad5bc1ce463 ("drm/v3d: fix up register addresses for V3D 7.x")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240109113126.929446-1-mcanal@igalia.com
---
 drivers/gpu/drm/v3d/v3d_debugfs.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_debugfs.c b/drivers/gpu/drm/v3d/v3d_debugfs.c
index f843a50d5dce6..94eafcecc65b0 100644
--- a/drivers/gpu/drm/v3d/v3d_debugfs.c
+++ b/drivers/gpu/drm/v3d/v3d_debugfs.c
@@ -62,9 +62,9 @@ static const struct v3d_reg_def v3d_core_reg_defs[] = {
 	REGDEF(33, 71, V3D_PTB_BPCA),
 	REGDEF(33, 71, V3D_PTB_BPCS),
 
-	REGDEF(33, 41, V3D_GMP_STATUS(33)),
-	REGDEF(33, 41, V3D_GMP_CFG(33)),
-	REGDEF(33, 41, V3D_GMP_VIO_ADDR(33)),
+	REGDEF(33, 42, V3D_GMP_STATUS(33)),
+	REGDEF(33, 42, V3D_GMP_CFG(33)),
+	REGDEF(33, 42, V3D_GMP_VIO_ADDR(33)),
 
 	REGDEF(33, 71, V3D_ERR_FDBGO),
 	REGDEF(33, 71, V3D_ERR_FDBGB),
@@ -74,13 +74,13 @@ static const struct v3d_reg_def v3d_core_reg_defs[] = {
 
 static const struct v3d_reg_def v3d_csd_reg_defs[] = {
 	REGDEF(41, 71, V3D_CSD_STATUS),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG0(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG1(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG2(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG3(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG4(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG5(41)),
-	REGDEF(41, 41, V3D_CSD_CURRENT_CFG6(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG0(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG1(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG2(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG3(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG4(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG5(41)),
+	REGDEF(41, 42, V3D_CSD_CURRENT_CFG6(41)),
 	REGDEF(71, 71, V3D_CSD_CURRENT_CFG0(71)),
 	REGDEF(71, 71, V3D_CSD_CURRENT_CFG1(71)),
 	REGDEF(71, 71, V3D_CSD_CURRENT_CFG2(71)),
-- 
GitLab


From f9cfe7e7f96a9414a17d596e288693c4f2325d49 Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Tue, 9 Jan 2024 21:39:57 +0800
Subject: [PATCH 2398/4076] md: Fix md_seq_ops() regressions

Commit cf1b6d4441ff ("md: simplify md_seq_ops") introduce following
regressions:

1) If list all_mddevs is emptly, personalities and unused devices won't
   be showed to user anymore.
2) If seq_file buffer overflowed from md_seq_show(), then md_seq_start()
   will be called again, hence personalities will be showed to user
   again.
3) If seq_file buffer overflowed from md_seq_stop(), seq_read_iter()
   doesn't handle this, hence unused devices won't be showed to user.

Fix above problems by printing personalities and unused devices in
md_seq_show().

Fixes: cf1b6d4441ff ("md: simplify md_seq_ops")
Cc: stable@vger.kernel.org # v6.7+
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240109133957.2975272-1-yukuai1@huaweicloud.com
---
 drivers/md/md.c | 40 +++++++++++++++++++++++++++-------------
 1 file changed, 27 insertions(+), 13 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index e351e6c51cc72..ff3057c787c1b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8135,6 +8135,19 @@ static void status_unused(struct seq_file *seq)
 	seq_printf(seq, "\n");
 }
 
+static void status_personalities(struct seq_file *seq)
+{
+	struct md_personality *pers;
+
+	seq_puts(seq, "Personalities : ");
+	spin_lock(&pers_lock);
+	list_for_each_entry(pers, &pers_list, list)
+		seq_printf(seq, "[%s] ", pers->name);
+
+	spin_unlock(&pers_lock);
+	seq_puts(seq, "\n");
+}
+
 static int status_resync(struct seq_file *seq, struct mddev *mddev)
 {
 	sector_t max_sectors, resync, res;
@@ -8276,20 +8289,10 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 static void *md_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(&all_mddevs_lock)
 {
-	struct md_personality *pers;
-
-	seq_puts(seq, "Personalities : ");
-	spin_lock(&pers_lock);
-	list_for_each_entry(pers, &pers_list, list)
-		seq_printf(seq, "[%s] ", pers->name);
-
-	spin_unlock(&pers_lock);
-	seq_puts(seq, "\n");
 	seq->poll_event = atomic_read(&md_event_count);
-
 	spin_lock(&all_mddevs_lock);
 
-	return seq_list_start(&all_mddevs, *pos);
+	return seq_list_start_head(&all_mddevs, *pos);
 }
 
 static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
@@ -8300,16 +8303,23 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static void md_seq_stop(struct seq_file *seq, void *v)
 	__releases(&all_mddevs_lock)
 {
-	status_unused(seq);
 	spin_unlock(&all_mddevs_lock);
 }
 
 static int md_seq_show(struct seq_file *seq, void *v)
 {
-	struct mddev *mddev = list_entry(v, struct mddev, all_mddevs);
+	struct mddev *mddev;
 	sector_t sectors;
 	struct md_rdev *rdev;
 
+	if (v == &all_mddevs) {
+		status_personalities(seq);
+		if (list_empty(&all_mddevs))
+			status_unused(seq);
+		return 0;
+	}
+
+	mddev = list_entry(v, struct mddev, all_mddevs);
 	if (!mddev_get(mddev))
 		return 0;
 
@@ -8385,6 +8395,10 @@ static int md_seq_show(struct seq_file *seq, void *v)
 	}
 	spin_unlock(&mddev->lock);
 	spin_lock(&all_mddevs_lock);
+
+	if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs))
+		status_unused(seq);
+
 	if (atomic_dec_and_test(&mddev->active))
 		__mddev_put(mddev);
 
-- 
GitLab


From 4dde83569832f9377362e50f7748463340c5db6b Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Fri, 29 Dec 2023 11:54:11 +0100
Subject: [PATCH 2399/4076] of: Fix double free in
 of_parse_phandle_with_args_map

In of_parse_phandle_with_args_map() the inner loop that
iterates through the map entries calls of_node_put(new)
to free the reference acquired by the previous iteration
of the inner loop. This assumes that the value of "new" is
NULL on the first iteration of the inner loop.

Make sure that this is true in all iterations of the outer
loop by setting "new" to NULL after its value is assigned to "cur".

Extend the unittest to detect the double free and add an additional
test case that actually triggers this path.

Fixes: bd6f2fd5a1 ("of: Support parsing phandle argument lists through a nexus node")
Cc: Stephen Boyd <stephen.boyd@linaro.org>
Signed-off-by: "Christian A. Ehrhardt" <lk@c--e.de>
Link: https://lore.kernel.org/r/20231229105411.1603434-1-lk@c--e.de
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/base.c                           |  1 +
 drivers/of/unittest-data/tests-phandle.dtsi | 10 ++-
 drivers/of/unittest.c                       | 74 ++++++++++++---------
 3 files changed, 53 insertions(+), 32 deletions(-)

diff --git a/drivers/of/base.c b/drivers/of/base.c
index 8d93cb6ea9cde..b0ad8fc06e80e 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1464,6 +1464,7 @@ int of_parse_phandle_with_args_map(const struct device_node *np,
 		out_args->np = new;
 		of_node_put(cur);
 		cur = new;
+		new = NULL;
 	}
 put:
 	of_node_put(cur);
diff --git a/drivers/of/unittest-data/tests-phandle.dtsi b/drivers/of/unittest-data/tests-phandle.dtsi
index d01f92f0f0db7..554a996b2ef18 100644
--- a/drivers/of/unittest-data/tests-phandle.dtsi
+++ b/drivers/of/unittest-data/tests-phandle.dtsi
@@ -40,6 +40,13 @@
 				phandle-map-pass-thru = <0x0 0xf0>;
 			};
 
+			provider5: provider5 {
+				#phandle-cells = <2>;
+				phandle-map = <2 7 &provider4 2 3>;
+				phandle-map-mask = <0xff 0xf>;
+				phandle-map-pass-thru = <0x0 0xf0>;
+			};
+
 			consumer-a {
 				phandle-list =	<&provider1 1>,
 						<&provider2 2 0>,
@@ -66,7 +73,8 @@
 						<&provider4 4 0x100>,
 						<&provider4 0 0x61>,
 						<&provider0>,
-						<&provider4 19 0x20>;
+						<&provider4 19 0x20>,
+						<&provider5 2 7>;
 				phandle-list-bad-phandle = <12345678 0 0>;
 				phandle-list-bad-args = <&provider2 1 0>,
 							<&provider4 0>;
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index e9e90e96600e4..45bd0d28c7173 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -456,6 +456,9 @@ static void __init of_unittest_parse_phandle_with_args(void)
 
 		unittest(passed, "index %i - data error on node %pOF rc=%i\n",
 			 i, args.np, rc);
+
+		if (rc == 0)
+			of_node_put(args.np);
 	}
 
 	/* Check for missing list property */
@@ -545,8 +548,9 @@ static void __init of_unittest_parse_phandle_with_args(void)
 
 static void __init of_unittest_parse_phandle_with_args_map(void)
 {
-	struct device_node *np, *p0, *p1, *p2, *p3;
+	struct device_node *np, *p[6] = {};
 	struct of_phandle_args args;
+	unsigned int prefs[6];
 	int i, rc;
 
 	np = of_find_node_by_path("/testcase-data/phandle-tests/consumer-b");
@@ -555,34 +559,24 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 		return;
 	}
 
-	p0 = of_find_node_by_path("/testcase-data/phandle-tests/provider0");
-	if (!p0) {
-		pr_err("missing testcase data\n");
-		return;
-	}
-
-	p1 = of_find_node_by_path("/testcase-data/phandle-tests/provider1");
-	if (!p1) {
-		pr_err("missing testcase data\n");
-		return;
-	}
-
-	p2 = of_find_node_by_path("/testcase-data/phandle-tests/provider2");
-	if (!p2) {
-		pr_err("missing testcase data\n");
-		return;
-	}
-
-	p3 = of_find_node_by_path("/testcase-data/phandle-tests/provider3");
-	if (!p3) {
-		pr_err("missing testcase data\n");
-		return;
+	p[0] = of_find_node_by_path("/testcase-data/phandle-tests/provider0");
+	p[1] = of_find_node_by_path("/testcase-data/phandle-tests/provider1");
+	p[2] = of_find_node_by_path("/testcase-data/phandle-tests/provider2");
+	p[3] = of_find_node_by_path("/testcase-data/phandle-tests/provider3");
+	p[4] = of_find_node_by_path("/testcase-data/phandle-tests/provider4");
+	p[5] = of_find_node_by_path("/testcase-data/phandle-tests/provider5");
+	for (i = 0; i < ARRAY_SIZE(p); ++i) {
+		if (!p[i]) {
+			pr_err("missing testcase data\n");
+			return;
+		}
+		prefs[i] = kref_read(&p[i]->kobj.kref);
 	}
 
 	rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells");
-	unittest(rc == 7, "of_count_phandle_with_args() returned %i, expected 7\n", rc);
+	unittest(rc == 8, "of_count_phandle_with_args() returned %i, expected 7\n", rc);
 
-	for (i = 0; i < 8; i++) {
+	for (i = 0; i < 9; i++) {
 		bool passed = true;
 
 		memset(&args, 0, sizeof(args));
@@ -593,13 +587,13 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 		switch (i) {
 		case 0:
 			passed &= !rc;
-			passed &= (args.np == p1);
+			passed &= (args.np == p[1]);
 			passed &= (args.args_count == 1);
 			passed &= (args.args[0] == 1);
 			break;
 		case 1:
 			passed &= !rc;
-			passed &= (args.np == p3);
+			passed &= (args.np == p[3]);
 			passed &= (args.args_count == 3);
 			passed &= (args.args[0] == 2);
 			passed &= (args.args[1] == 5);
@@ -610,28 +604,36 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 			break;
 		case 3:
 			passed &= !rc;
-			passed &= (args.np == p0);
+			passed &= (args.np == p[0]);
 			passed &= (args.args_count == 0);
 			break;
 		case 4:
 			passed &= !rc;
-			passed &= (args.np == p1);
+			passed &= (args.np == p[1]);
 			passed &= (args.args_count == 1);
 			passed &= (args.args[0] == 3);
 			break;
 		case 5:
 			passed &= !rc;
-			passed &= (args.np == p0);
+			passed &= (args.np == p[0]);
 			passed &= (args.args_count == 0);
 			break;
 		case 6:
 			passed &= !rc;
-			passed &= (args.np == p2);
+			passed &= (args.np == p[2]);
 			passed &= (args.args_count == 2);
 			passed &= (args.args[0] == 15);
 			passed &= (args.args[1] == 0x20);
 			break;
 		case 7:
+			passed &= !rc;
+			passed &= (args.np == p[3]);
+			passed &= (args.args_count == 3);
+			passed &= (args.args[0] == 2);
+			passed &= (args.args[1] == 5);
+			passed &= (args.args[2] == 3);
+			break;
+		case 8:
 			passed &= (rc == -ENOENT);
 			break;
 		default:
@@ -640,6 +642,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 
 		unittest(passed, "index %i - data error on node %s rc=%i\n",
 			 i, args.np->full_name, rc);
+
+		if (rc == 0)
+			of_node_put(args.np);
 	}
 
 	/* Check for missing list property */
@@ -686,6 +691,13 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 		   "OF: /testcase-data/phandle-tests/consumer-b: #phandle-cells = 2 found 1");
 
 	unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
+
+	for (i = 0; i < ARRAY_SIZE(p); ++i) {
+		unittest(prefs[i] == kref_read(&p[i]->kobj.kref),
+			 "provider%d: expected:%d got:%d\n",
+			 i, prefs[i], kref_read(&p[i]->kobj.kref));
+		of_node_put(p[i]);
+	}
 }
 
 static void __init of_unittest_property_string(void)
-- 
GitLab


From 420370f3ae3d3b883813fd3051a38805160b2b9f Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Thu, 14 Dec 2023 10:19:26 +0100
Subject: [PATCH 2400/4076] riscv: Check if the code to patch lies in the exit
 section

Otherwise we fall through to vmalloc_to_page() which panics since the
address does not lie in the vmalloc region.

Fixes: 043cb41a85de ("riscv: introduce interfaces to patch kernel code")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231214091926.203439-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/sections.h   |  1 +
 arch/riscv/kernel/patch.c           | 11 ++++++++++-
 arch/riscv/kernel/vmlinux-xip.lds.S |  2 ++
 arch/riscv/kernel/vmlinux.lds.S     |  2 ++
 4 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h
index 32336e8a17cb0..a393d5035c543 100644
--- a/arch/riscv/include/asm/sections.h
+++ b/arch/riscv/include/asm/sections.h
@@ -13,6 +13,7 @@ extern char _start_kernel[];
 extern char __init_data_begin[], __init_data_end[];
 extern char __init_text_begin[], __init_text_end[];
 extern char __alt_start[], __alt_end[];
+extern char __exittext_begin[], __exittext_end[];
 
 static inline bool is_va_kernel_text(uintptr_t va)
 {
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 13ee7bf589a15..37e87fdcf6a00 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -14,6 +14,7 @@
 #include <asm/fixmap.h>
 #include <asm/ftrace.h>
 #include <asm/patch.h>
+#include <asm/sections.h>
 
 struct patch_insn {
 	void *addr;
@@ -25,6 +26,14 @@ struct patch_insn {
 int riscv_patch_in_stop_machine = false;
 
 #ifdef CONFIG_MMU
+
+static inline bool is_kernel_exittext(uintptr_t addr)
+{
+	return system_state < SYSTEM_RUNNING &&
+		addr >= (uintptr_t)__exittext_begin &&
+		addr < (uintptr_t)__exittext_end;
+}
+
 /*
  * The fix_to_virt(, idx) needs a const value (not a dynamic variable of
  * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses".
@@ -35,7 +44,7 @@ static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
 	uintptr_t uintaddr = (uintptr_t) addr;
 	struct page *page;
 
-	if (core_kernel_text(uintaddr))
+	if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr))
 		page = phys_to_page(__pa_symbol(addr));
 	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
 		page = vmalloc_to_page(addr);
diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S
index 50767647fbc64..8c3daa1b05313 100644
--- a/arch/riscv/kernel/vmlinux-xip.lds.S
+++ b/arch/riscv/kernel/vmlinux-xip.lds.S
@@ -29,10 +29,12 @@ SECTIONS
 	HEAD_TEXT_SECTION
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
 	.exit.text :
 	{
 		EXIT_TEXT
 	}
+	__exittext_end = .;
 
 	.text : {
 		_text = .;
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 492dd4b8f3d69..002ca58dd998c 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -69,10 +69,12 @@ SECTIONS
 		__soc_builtin_dtb_table_end = .;
 	}
 	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
 	.exit.text :
 	{
 		EXIT_TEXT
 	}
+	__exittext_end = .;
 
 	__init_text_end = .;
 	. = ALIGN(SECTION_ALIGN);
-- 
GitLab


From c29fc621e1a49949a14c7fa031dd4760087bfb29 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 12 Dec 2023 20:54:00 +0100
Subject: [PATCH 2401/4076] riscv: Fix wrong usage of lm_alias() when splitting
 a huge linear mapping

lm_alias() can only be used on kernel mappings since it explicitly uses
__pa_symbol(), so simply fix this by checking where the address belongs
to before.

Fixes: 311cd2f6e253 ("riscv: Fix set_memory_XX() and set_direct_map_XX() by splitting huge linear mappings")
Reported-by: syzbot+afb726d49f84c8d95ee1@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-riscv/000000000000620dd0060c02c5e1@google.com/
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231212195400.128457-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/pageattr.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index fc5fc4f785c48..96cbda683936b 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -305,8 +305,13 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 				goto unlock;
 		}
 	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
-		lm_start = (unsigned long)lm_alias(start);
-		lm_end = (unsigned long)lm_alias(end);
+		if (is_kernel_mapping(start)) {
+			lm_start = (unsigned long)lm_alias(start);
+			lm_end = (unsigned long)lm_alias(end);
+		} else {
+			lm_start = start;
+			lm_end = end;
+		}
 
 		ret = split_linear_mapping(lm_start, lm_end);
 		if (ret)
-- 
GitLab


From 749b94b08005929bbc636df21a23322733166e35 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 13 Dec 2023 14:40:26 +0100
Subject: [PATCH 2402/4076] riscv: Fix module_alloc() that did not reset the
 linear mapping permissions

After unloading a module, we must reset the linear mapping permissions,
see the example below:

Before unloading a module:

0xffffaf809d65d000-0xffffaf809d6dc000    0x000000011d65d000       508K PTE .   ..     ..   D A G . . W R V
0xffffaf809d6dc000-0xffffaf809d6dd000    0x000000011d6dc000         4K PTE .   ..     ..   D A G . . . R V
0xffffaf809d6dd000-0xffffaf809d6e1000    0x000000011d6dd000        16K PTE .   ..     ..   D A G . . W R V
0xffffaf809d6e1000-0xffffaf809d6e7000    0x000000011d6e1000        24K PTE .   ..     ..   D A G . X . R V

After unloading a module:

0xffffaf809d65d000-0xffffaf809d6e1000    0x000000011d65d000       528K PTE .   ..     ..   D A G . . W R V
0xffffaf809d6e1000-0xffffaf809d6e7000    0x000000011d6e1000        24K PTE .   ..     ..   D A G . X W R V

The last mapping is not reset and we end up with WX mappings in the linear
mapping.

So add VM_FLUSH_RESET_PERMS to our module_alloc() definition.

Fixes: 0cff8bff7af8 ("riscv: avoid the PIC offset of static percpu data in module beyond 2G limits")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20231213134027.155327-2-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/module.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index aac019ed63b1b..862834bb1d643 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -894,7 +894,8 @@ void *module_alloc(unsigned long size)
 {
 	return __vmalloc_node_range(size, 1, MODULES_VADDR,
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, VM_FLUSH_RESET_PERMS,
+				    NUMA_NO_NODE,
 				    __builtin_return_address(0));
 }
 #endif
-- 
GitLab


From b8b2711336f03ece539de61479d6ffc44fb603d3 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 13 Dec 2023 14:40:27 +0100
Subject: [PATCH 2403/4076] riscv: Fix set_direct_map_default_noflush() to
 reset _PAGE_EXEC

When resetting the linear mapping permissions, we must make sure that we
clear the X bit so that do not end up with WX mappings (since we set
PAGE_KERNEL).

Fixes: 395a21ff859c ("riscv: add ARCH_HAS_SET_DIRECT_MAP support")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20231213134027.155327-3-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/pageattr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 96cbda683936b..01398fee5cf82 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -383,7 +383,7 @@ int set_direct_map_invalid_noflush(struct page *page)
 int set_direct_map_default_noflush(struct page *page)
 {
 	return __set_memory((unsigned long)page_address(page), 1,
-			    PAGE_KERNEL, __pgprot(0));
+			    PAGE_KERNEL, __pgprot(_PAGE_EXEC));
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-- 
GitLab


From 47bf0f83fc86df1bf42b385a91aadb910137c5c9 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <felix.kuehling@amd.com>
Date: Tue, 2 Jan 2024 15:07:44 -0500
Subject: [PATCH 2404/4076] drm/amdkfd: Fix lock dependency warning

======================================================
WARNING: possible circular locking dependency detected
6.5.0-kfd-fkuehlin #276 Not tainted
------------------------------------------------------
kworker/8:2/2676 is trying to acquire lock:
ffff9435aae95c88 ((work_completion)(&svm_bo->eviction_work)){+.+.}-{0:0}, at: __flush_work+0x52/0x550

but task is already holding lock:
ffff9435cd8e1720 (&svms->lock){+.+.}-{3:3}, at: svm_range_deferred_list_work+0xe8/0x340 [amdgpu]

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #2 (&svms->lock){+.+.}-{3:3}:
       __mutex_lock+0x97/0xd30
       kfd_ioctl_alloc_memory_of_gpu+0x6d/0x3c0 [amdgpu]
       kfd_ioctl+0x1b2/0x5d0 [amdgpu]
       __x64_sys_ioctl+0x86/0xc0
       do_syscall_64+0x39/0x80
       entry_SYSCALL_64_after_hwframe+0x63/0xcd

-> #1 (&mm->mmap_lock){++++}-{3:3}:
       down_read+0x42/0x160
       svm_range_evict_svm_bo_worker+0x8b/0x340 [amdgpu]
       process_one_work+0x27a/0x540
       worker_thread+0x53/0x3e0
       kthread+0xeb/0x120
       ret_from_fork+0x31/0x50
       ret_from_fork_asm+0x11/0x20

-> #0 ((work_completion)(&svm_bo->eviction_work)){+.+.}-{0:0}:
       __lock_acquire+0x1426/0x2200
       lock_acquire+0xc1/0x2b0
       __flush_work+0x80/0x550
       __cancel_work_timer+0x109/0x190
       svm_range_bo_release+0xdc/0x1c0 [amdgpu]
       svm_range_free+0x175/0x180 [amdgpu]
       svm_range_deferred_list_work+0x15d/0x340 [amdgpu]
       process_one_work+0x27a/0x540
       worker_thread+0x53/0x3e0
       kthread+0xeb/0x120
       ret_from_fork+0x31/0x50
       ret_from_fork_asm+0x11/0x20

other info that might help us debug this:

Chain exists of:
  (work_completion)(&svm_bo->eviction_work) --> &mm->mmap_lock --> &svms->lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&svms->lock);
                               lock(&mm->mmap_lock);
                               lock(&svms->lock);
  lock((work_completion)(&svm_bo->eviction_work));

I believe this cannot really lead to a deadlock in practice, because
svm_range_evict_svm_bo_worker only takes the mmap_read_lock if the BO
refcount is non-0. That means it's impossible that svm_range_bo_release
is running concurrently. However, there is no good way to annotate this.

To avoid the problem, take a BO reference in
svm_range_schedule_evict_svm_bo instead of in the worker. That way it's
impossible for a BO to get freed while eviction work is pending and the
cancel_work_sync call in svm_range_bo_release can be eliminated.

v2: Use svm_bo_ref_unless_zero and explained why that's safe. Also
removed redundant checks that are already done in
amdkfd_fence_enable_signaling.

Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Philip Yang <philip.yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 26 ++++++++++----------------
 1 file changed, 10 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index ac84c4a2ca072..d46c145835e09 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -404,14 +404,9 @@ static void svm_range_bo_release(struct kref *kref)
 		spin_lock(&svm_bo->list_lock);
 	}
 	spin_unlock(&svm_bo->list_lock);
-	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) {
-		/* We're not in the eviction worker.
-		 * Signal the fence and synchronize with any
-		 * pending eviction work.
-		 */
+	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base))
+		/* We're not in the eviction worker. Signal the fence. */
 		dma_fence_signal(&svm_bo->eviction_fence->base);
-		cancel_work_sync(&svm_bo->eviction_work);
-	}
 	dma_fence_put(&svm_bo->eviction_fence->base);
 	amdgpu_bo_unref(&svm_bo->bo);
 	kfree(svm_bo);
@@ -3432,13 +3427,14 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
 {
-	if (!fence)
-		return -EINVAL;
-
-	if (dma_fence_is_signaled(&fence->base))
-		return 0;
-
-	if (fence->svm_bo) {
+	/* Dereferencing fence->svm_bo is safe here because the fence hasn't
+	 * signaled yet and we're under the protection of the fence->lock.
+	 * After the fence is signaled in svm_range_bo_release, we cannot get
+	 * here any more.
+	 *
+	 * Reference is dropped in svm_range_evict_svm_bo_worker.
+	 */
+	if (svm_bo_ref_unless_zero(fence->svm_bo)) {
 		WRITE_ONCE(fence->svm_bo->evicting, 1);
 		schedule_work(&fence->svm_bo->eviction_work);
 	}
@@ -3453,8 +3449,6 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	int r = 0;
 
 	svm_bo = container_of(work, struct svm_range_bo, eviction_work);
-	if (!svm_bo_ref_unless_zero(svm_bo))
-		return; /* svm_bo was freed while eviction was pending */
 
 	if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
 		mm = svm_bo->eviction_fence->mm;
-- 
GitLab


From 17e74e11ac2b46e7514705ae7abfb93ac0e20bd6 Mon Sep 17 00:00:00 2001
From: Martin Tsai <martin.tsai@amd.com>
Date: Mon, 18 Dec 2023 16:36:44 +0800
Subject: [PATCH 2405/4076] drm/amd/display: To adjust dprefclk by down spread
 percentage

[Why]
Panels show corruption with high refresh rate timings when ssc is
enabled.

[How]
Read down-spread percentage from lut to adjust dprefclk. Issues come
from S0i3 with this commit has been fixed by SMU.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Martin Tsai <martin.tsai@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../dc/clk_mgr/dcn314/dcn314_clk_mgr.c        | 71 ++++++++++++++++++-
 .../dc/clk_mgr/dcn314/dcn314_clk_mgr.h        | 11 +++
 .../gpu/drm/amd/display/dc/dce/dce_audio.c    |  2 +-
 .../drm/amd/display/dc/dce/dce_clock_source.c |  9 ++-
 .../amd/display/dc/hwss/dce110/dce110_hwseq.c |  2 +-
 .../gpu/drm/amd/display/dc/inc/hw/clk_mgr.h   |  1 +
 .../gpu/drm/amd/display/include/audio_types.h |  2 +-
 7 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 7575282563267..878c0e7b78abd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -87,6 +87,20 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
 #define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK	0x0000F000L
 #define CLK1_CLK_PLL_REQ__FbMult_frac_MASK	0xFFFF0000L
 
+#define regCLK1_CLK2_BYPASS_CNTL			0x029c
+#define regCLK1_CLK2_BYPASS_CNTL_BASE_IDX	0
+
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL__SHIFT	0x0
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV__SHIFT	0x10
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK		0x00000007L
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK		0x000F0000L
+
+#define regCLK6_0_CLK6_spll_field_8				0x464b
+#define regCLK6_0_CLK6_spll_field_8_BASE_IDX	0
+
+#define CLK6_0_CLK6_spll_field_8__spll_ssc_en__SHIFT	0xd
+#define CLK6_0_CLK6_spll_field_8__spll_ssc_en_MASK		0x00002000L
+
 #define REG(reg_name) \
 	(CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
 
@@ -160,6 +174,37 @@ static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state
 	}
 }
 
+bool dcn314_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+	uint32_t ssc_enable;
+
+	REG_GET(CLK6_0_CLK6_spll_field_8, spll_ssc_en, &ssc_enable);
+
+	return ssc_enable == 1;
+}
+
+void dcn314_init_clocks(struct clk_mgr *clk_mgr)
+{
+	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
+	uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
+
+	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
+	// Assumption is that boot state always supports pstate
+	clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk;	// restore ref_dtbclk
+	clk_mgr->clks.p_state_change_support = true;
+	clk_mgr->clks.prev_p_state_change_support = true;
+	clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
+	clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
+
+	// to adjust dp_dto reference clock if ssc is enable otherwise to apply dprefclk
+	if (dcn314_is_spll_ssc_enabled(clk_mgr))
+		clk_mgr->dp_dto_source_clock_in_khz =
+			dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz);
+	else
+		clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
+}
+
 void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
 			bool safe_to_lower)
@@ -436,6 +481,11 @@ static DpmClocks314_t dummy_clocks;
 
 static struct dcn314_watermarks dummy_wms = { 0 };
 
+static struct dcn314_ss_info_table ss_info_table = {
+	.ss_divider = 1000,
+	.ss_percentage = {0, 0, 375, 375, 375}
+};
+
 static void dcn314_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn314_watermarks *table)
 {
 	int i, num_valid_sets;
@@ -708,13 +758,31 @@ static struct clk_mgr_funcs dcn314_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 	.update_clocks = dcn314_update_clocks,
-	.init_clocks = dcn31_init_clocks,
+	.init_clocks = dcn314_init_clocks,
 	.enable_pme_wa = dcn314_enable_pme_wa,
 	.are_clock_states_equal = dcn314_are_clock_states_equal,
 	.notify_wm_ranges = dcn314_notify_wm_ranges
 };
 extern struct clk_mgr_funcs dcn3_fpga_funcs;
 
+static void dcn314_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
+{
+	uint32_t clock_source;
+	//uint32_t ssc_enable;
+
+	REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
+	//REG_GET(CLK6_0_CLK6_spll_field_8, spll_ssc_en, &ssc_enable);
+
+	if (dcn314_is_spll_ssc_enabled(&clk_mgr->base) && (clock_source < ARRAY_SIZE(ss_info_table.ss_percentage))) {
+		clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
+
+		if (clk_mgr->dprefclk_ss_percentage != 0) {
+			clk_mgr->ss_on_dprefclk = true;
+			clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
+		}
+	}
+}
+
 void dcn314_clk_mgr_construct(
 		struct dc_context *ctx,
 		struct clk_mgr_dcn314 *clk_mgr,
@@ -782,6 +850,7 @@ void dcn314_clk_mgr_construct(
 	clk_mgr->base.base.dprefclk_khz = 600000;
 	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
 	dce_clock_read_ss_info(&clk_mgr->base);
+	dcn314_read_ss_info_from_lut(&clk_mgr->base);
 	/*if bios enabled SS, driver needs to adjust dtb clock, only enable with correct bios*/
 
 	clk_mgr->base.base.bw_params = &dcn314_bw_params;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
index 171f84340eb2f..002c28e807208 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
@@ -28,6 +28,8 @@
 #define __DCN314_CLK_MGR_H__
 #include "clk_mgr_internal.h"
 
+#define DCN314_NUM_CLOCK_SOURCES   5
+
 struct dcn314_watermarks;
 
 struct dcn314_smu_watermark_set {
@@ -40,9 +42,18 @@ struct clk_mgr_dcn314 {
 	struct dcn314_smu_watermark_set smu_wm_set;
 };
 
+struct dcn314_ss_info_table {
+	uint32_t ss_divider;
+	uint32_t ss_percentage[DCN314_NUM_CLOCK_SOURCES];
+};
+
 bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 		struct dc_clocks *b);
 
+bool dcn314_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base);
+
+void dcn314_init_clocks(struct clk_mgr *clk_mgr);
+
 void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
 			bool safe_to_lower);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
index 140598f18bbdd..f0458b8f00af8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
@@ -782,7 +782,7 @@ static void get_azalia_clock_info_dp(
 	/*audio_dto_module = dpDtoSourceClockInkhz * 10,000;
 	 *  [khz] ->[100Hz] */
 	azalia_clock_info->audio_dto_module =
-		pll_info->dp_dto_source_clock_in_khz * 10;
+		pll_info->audio_dto_source_clock_in_khz * 10;
 }
 
 void dce_aud_wall_dto_setup(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 5d3f6fa1011e8..970644b695cd4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -975,6 +975,9 @@ static bool dcn31_program_pix_clk(
 			look_up_in_video_optimized_rate_tlb(pix_clk_params->requested_pix_clk_100hz / 10);
 	struct bp_pixel_clock_parameters bp_pc_params = {0};
 	enum transmitter_color_depth bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24;
+
+	if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
+		dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
 	// For these signal types Driver to program DP_DTO without calling VBIOS Command table
 	if (dc_is_dp_signal(pix_clk_params->signal_type) || dc_is_virtual_signal(pix_clk_params->signal_type)) {
 		if (e) {
@@ -1088,6 +1091,10 @@ static bool get_pixel_clk_frequency_100hz(
 	struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source);
 	unsigned int clock_hz = 0;
 	unsigned int modulo_hz = 0;
+	unsigned int dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dprefclk_khz;
+
+	if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
+		dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
 
 	if (clock_source->id == CLOCK_SOURCE_ID_DP_DTO) {
 		clock_hz = REG_READ(PHASE[inst]);
@@ -1100,7 +1107,7 @@ static bool get_pixel_clk_frequency_100hz(
 			modulo_hz = REG_READ(MODULO[inst]);
 			if (modulo_hz)
 				*pixel_clk_khz = div_u64((uint64_t)clock_hz*
-					clock_source->ctx->dc->clk_mgr->dprefclk_khz*10,
+					dp_dto_ref_khz*10,
 					modulo_hz);
 			else
 				*pixel_clk_khz = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index fb328cd06cea2..5660f15da291e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1354,7 +1354,7 @@ static void build_audio_output(
 	if (state->clk_mgr &&
 		(pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
 			pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)) {
-		audio_output->pll_info.dp_dto_source_clock_in_khz =
+		audio_output->pll_info.audio_dto_source_clock_in_khz =
 				state->clk_mgr->funcs->get_dp_ref_clk_frequency(
 						state->clk_mgr);
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index cbba39d251e53..17e014d3bdc84 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -333,6 +333,7 @@ struct clk_mgr {
 	bool force_smu_not_present;
 	bool dc_mode_softmax_enabled;
 	int dprefclk_khz; // Used by program pixel clock in clock source funcs, need to figureout where this goes
+	int dp_dto_source_clock_in_khz; // Used to program DP DTO with ss adjustment on DCN314
 	int dentist_vco_freq_khz;
 	struct clk_state_registers_and_bypass boot_snapshot;
 	struct clk_bw_params *bw_params;
diff --git a/drivers/gpu/drm/amd/display/include/audio_types.h b/drivers/gpu/drm/amd/display/include/audio_types.h
index 66a54da0641ce..915a031a43cb2 100644
--- a/drivers/gpu/drm/amd/display/include/audio_types.h
+++ b/drivers/gpu/drm/amd/display/include/audio_types.h
@@ -64,7 +64,7 @@ enum audio_dto_source {
 /* PLL information required for AZALIA DTO calculation */
 
 struct audio_pll_info {
-	uint32_t dp_dto_source_clock_in_khz;
+	uint32_t audio_dto_source_clock_in_khz;
 	uint32_t feed_back_divider;
 	enum audio_dto_source dto_source;
 	bool ss_enabled;
-- 
GitLab


From 7bdbfb4e36e34eb788e44f27666bf0a2b3b90803 Mon Sep 17 00:00:00 2001
From: George Shen <george.shen@amd.com>
Date: Sun, 17 Dec 2023 17:17:57 -0500
Subject: [PATCH 2406/4076] drm/amd/display: Disconnect phantom pipe OPP from
 OPTC being disabled

[Why]
If an OPP is used for a different OPTC without first being disconnected
from the previous OPTC, unexpected behaviour can occur. This also
applies to phantom pipes, which is what the current logic missed.

[How]
Disconnect OPPs from OPTC for phantom pipes before disabling OTG master.

Also move the disconnection to before the OTG master disable, since the
register is double buffered.

Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Acked-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: George Shen <george.shen@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/optc/dcn32/dcn32_optc.c    | 19 +++++++++++++------
 .../amd/display/dc/optc/dcn35/dcn35_optc.c    | 12 ++++++------
 2 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
index 91ea0d4da06a9..1788eb29474b4 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
@@ -166,12 +166,6 @@ static bool optc32_disable_crtc(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
-	/* disable otg request until end of the first line
-	 * in the vertical blank region
-	 */
-	REG_UPDATE(OTG_CONTROL,
-			OTG_MASTER_EN, 0);
-
 	REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
 			OPTC_SEG0_SRC_SEL, 0xf,
 			OPTC_SEG1_SRC_SEL, 0xf,
@@ -179,6 +173,12 @@ static bool optc32_disable_crtc(struct timing_generator *optc)
 			OPTC_SEG3_SRC_SEL, 0xf,
 			OPTC_NUM_OF_INPUT_SEGMENT, 0);
 
+	/* disable otg request until end of the first line
+	 * in the vertical blank region
+	 */
+	REG_UPDATE(OTG_CONTROL,
+			OTG_MASTER_EN, 0);
+
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 0);
 
@@ -205,6 +205,13 @@ static void optc32_disable_phantom_otg(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
+	REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
+			OPTC_SEG0_SRC_SEL, 0xf,
+			OPTC_SEG1_SRC_SEL, 0xf,
+			OPTC_SEG2_SRC_SEL, 0xf,
+			OPTC_SEG3_SRC_SEL, 0xf,
+			OPTC_NUM_OF_INPUT_SEGMENT, 0);
+
 	REG_UPDATE(OTG_CONTROL, OTG_MASTER_EN, 0);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
index 08a59cf449cae..3d6c1b2c2b4d6 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
@@ -138,12 +138,6 @@ static bool optc35_disable_crtc(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
-	/* disable otg request until end of the first line
-	 * in the vertical blank region
-	 */
-	REG_UPDATE(OTG_CONTROL,
-			OTG_MASTER_EN, 0);
-
 	REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT,
 			OPTC_SEG0_SRC_SEL, 0xf,
 			OPTC_SEG1_SRC_SEL, 0xf,
@@ -151,6 +145,12 @@ static bool optc35_disable_crtc(struct timing_generator *optc)
 			OPTC_SEG3_SRC_SEL, 0xf,
 			OPTC_NUM_OF_INPUT_SEGMENT, 0);
 
+	/* disable otg request until end of the first line
+	 * in the vertical blank region
+	 */
+	REG_UPDATE(OTG_CONTROL,
+			OTG_MASTER_EN, 0);
+
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 0);
 
-- 
GitLab


From 51c7e6ac24101af3147ebc45627810da367c6b66 Mon Sep 17 00:00:00 2001
From: Martin Leung <martin.leung@amd.com>
Date: Wed, 20 Dec 2023 16:54:05 -0500
Subject: [PATCH 2407/4076] drm/amd/display: revert "for FPO & SubVP/DRR config
 program vmin/max"

This reverts commit 6b2b782ad6a25734ae847d1659bea3f613dbb563.

The original commit causes issues with certain features when DRR is
disabled, need to revisit this change later after resolving issues with
new DRR policy.

Reviewed-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Martin Leung <martin.leung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/core/dc_resource.c | 14 -------
 .../display/dc/dcn32/dcn32_resource_helpers.c | 14 +++++++
 .../drm/amd/display/dc/dml/dcn32/dcn32_fpu.c  | 11 +++---
 .../amd/display/dc/hwss/dcn20/dcn20_hwseq.c   | 37 -------------------
 drivers/gpu/drm/amd/display/dc/inc/resource.h |  3 --
 .../dc/resource/dcn32/dcn32_resource.c        |  2 +-
 .../dc/resource/dcn32/dcn32_resource.h        |  3 ++
 .../dc/resource/dcn321/dcn321_resource.c      |  2 +-
 8 files changed, 24 insertions(+), 62 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 57f0ddd159239..f2abc1096ffb6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -4986,20 +4986,6 @@ enum dc_status update_dp_encoder_resources_for_test_harness(const struct dc *dc,
 	return DC_OK;
 }
 
-bool resource_subvp_in_use(struct dc *dc,
-		struct dc_state *context)
-{
-	uint32_t i;
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_NONE)
-			return true;
-	}
-	return false;
-}
-
 bool check_subvp_sw_cursor_fallback_req(const struct dc *dc, struct dc_stream_state *stream)
 {
 	if (!dc->debug.disable_subvp_high_refresh && is_subvp_high_refresh_candidate(stream))
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index e4a328b45c8a5..87760600e154d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -183,6 +183,20 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
 	return true;
 }
 
+bool dcn32_subvp_in_use(struct dc *dc,
+		struct dc_state *context)
+{
+	uint32_t i;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_NONE)
+			return true;
+	}
+	return false;
+}
+
 bool dcn32_mpo_in_use(struct dc_state *context)
 {
 	uint32_t i;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index aa68d010cbfd2..9f37f717a1f86 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -33,7 +33,6 @@
 #include "dcn30/dcn30_resource.h"
 #include "link.h"
 #include "dc_state_priv.h"
-#include "resource.h"
 
 #define DC_LOGGER_INIT(logger)
 
@@ -292,7 +291,7 @@ int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc,
 
 		/* for subvp + DRR case, if subvp pipes are still present we support pstate */
 		if (vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported &&
-				resource_subvp_in_use(dc, context))
+				dcn32_subvp_in_use(dc, context))
 			vba->DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = temp_clock_change_support;
 
 		if (vlevel < context->bw_ctx.dml.vba.soc.num_states &&
@@ -2273,7 +2272,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	unsigned int dummy_latency_index = 0;
 	int maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb;
 	unsigned int min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed;
-	bool subvp_active = resource_subvp_in_use(dc, context);
+	bool subvp_in_use = dcn32_subvp_in_use(dc, context);
 	unsigned int min_dram_speed_mts_margin;
 	bool need_fclk_lat_as_dummy = false;
 	bool is_subvp_p_drr = false;
@@ -2282,7 +2281,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	dc_assert_fp_enabled();
 
 	/* need to find dummy latency index for subvp */
-	if (subvp_active) {
+	if (subvp_in_use) {
 		/* Override DRAMClockChangeSupport for SubVP + DRR case where the DRR cannot switch without stretching it's VBLANK */
 		if (!pstate_en) {
 			context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] = dm_dram_clock_change_vblank_w_mall_sub_vp;
@@ -2468,7 +2467,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 				dc->clk_mgr->bw_params->clk_table.entries[min_dram_speed_mts_offset].memclk_mhz * 16;
 		}
 
-		if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_active) {
+		if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_in_use) {
 			/* find largest table entry that is lower than dram speed,
 			 * but lower than DPM0 still uses DPM0
 			 */
@@ -3528,7 +3527,7 @@ void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb)
 void dcn32_override_min_req_memclk(struct dc *dc, struct dc_state *context)
 {
 	// WA: restrict FPO and SubVP to use first non-strobe mode (DCN32 BW issue)
-	if ((context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || resource_subvp_in_use(dc, context)) &&
+	if ((context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dcn32_subvp_in_use(dc, context)) &&
 			dc->dml.soc.num_chans <= 8) {
 		int num_mclk_levels = dc->clk_mgr->bw_params->clk_table.num_entries_per_clk.num_memclk_levels;
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index bc71a9b058fed..0dfcb3cdcd20c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -1882,42 +1882,6 @@ static void dcn20_program_pipe(
 	}
 }
 
-static void update_vmin_vmax_fams(struct dc *dc,
-		struct dc_state *context)
-{
-	uint32_t i;
-	struct drr_params params = {0};
-	bool subvp_in_use = resource_subvp_in_use(dc, context);
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (resource_is_pipe_type(pipe, OTG_MASTER) &&
-				((subvp_in_use && dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM &&
-				pipe->stream->allow_freesync) || (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && pipe->stream->fpo_in_use))) {
-			if (!pipe->stream->vrr_active_variable && !pipe->stream->vrr_active_fixed) {
-				struct timing_generator *tg = context->res_ctx.pipe_ctx[i].stream_res.tg;
-
-				/* DRR should be configured already if we're in active variable
-				 * or active fixed, so only program if we're not in this state
-				 */
-				params.vertical_total_min = pipe->stream->timing.v_total;
-				params.vertical_total_max = pipe->stream->timing.v_total;
-				tg->funcs->set_drr(tg, &params);
-			}
-		} else {
-			if (resource_is_pipe_type(pipe, OTG_MASTER) &&
-					!pipe->stream->vrr_active_variable &&
-					!pipe->stream->vrr_active_fixed) {
-				struct timing_generator *tg = context->res_ctx.pipe_ctx[i].stream_res.tg;
-				params.vertical_total_min = 0;
-				params.vertical_total_max = 0;
-				tg->funcs->set_drr(tg, &params);
-			}
-		}
-	}
-}
-
 void dcn20_program_front_end_for_ctx(
 		struct dc *dc,
 		struct dc_state *context)
@@ -1994,7 +1958,6 @@ void dcn20_program_front_end_for_ctx(
 				&& context->res_ctx.pipe_ctx[i].stream)
 			hws->funcs.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true);
 
-	update_vmin_vmax_fams(dc, context);
 
 	/* Disconnect mpcc */
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 1d51fed12e200..c958ef37b78a6 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -609,9 +609,6 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm_legacy(
 		struct pipe_ctx *sec_pipe,
 		bool odm);
 
-bool resource_subvp_in_use(struct dc *dc,
-		struct dc_state *context);
-
 /* A test harness interface that modifies dp encoder resources in the given dc
  * state and bypasses the need to revalidate. The interface assumes that the
  * test harness interface is called with pre-validated link config stored in the
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index ac04a9c9a3d86..c4d71e7f18af4 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1899,7 +1899,7 @@ int dcn32_populate_dml_pipes_from_context(
 
 static struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn20_get_dcc_compression_cap,
-	.get_subvp_en = resource_subvp_in_use,
+	.get_subvp_en = dcn32_subvp_in_use,
 };
 
 void dcn32_calculate_wm_and_dlg(struct dc *dc, struct dc_state *context,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
index 62611acd4bcb5..0c87b0fabba7d 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
@@ -131,6 +131,9 @@ void dcn32_merge_pipes_for_subvp(struct dc *dc,
 bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
 		struct dc_state *context);
 
+bool dcn32_subvp_in_use(struct dc *dc,
+		struct dc_state *context);
+
 bool dcn32_mpo_in_use(struct dc_state *context);
 
 bool dcn32_any_surfaces_rotated(struct dc *dc, struct dc_state *context);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
index e1ab207c46f15..74412e5f03fef 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
@@ -1574,7 +1574,7 @@ static void dcn321_destroy_resource_pool(struct resource_pool **pool)
 
 static struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn20_get_dcc_compression_cap,
-	.get_subvp_en = resource_subvp_in_use,
+	.get_subvp_en = dcn32_subvp_in_use,
 };
 
 static void dcn321_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
-- 
GitLab


From a465536ebff88fcc42e131a1b09bbe3df829117b Mon Sep 17 00:00:00 2001
From: Martin Leung <martin.leung@amd.com>
Date: Wed, 20 Dec 2023 16:56:11 -0500
Subject: [PATCH 2408/4076] drm/amd/display: revert "Optimize VRR updates to
 only necessary ones"

This reverts commit 6e4337f695c25162f0296934152506ad596fcebf.

The original commit causes regression in corner case with HDMI at
specific timings. Reverting from staging to get the full suite to
retest.

Reviewed-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Martin Leung <martin.leung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c           | 14 +++++++++-----
 drivers/gpu/drm/amd/display/dc/dc.h                |  1 +
 drivers/gpu/drm/amd/display/dc/dc_stream.h         |  2 ++
 .../drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c    |  2 +-
 .../drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c    |  8 ++++----
 5 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 2d7205058c64a..69e726630241d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -411,12 +411,9 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	 * avoid conflicting with firmware updates.
 	 */
 	if (dc->ctx->dce_version > DCE_VERSION_MAX)
-		if (dc->optimized_required)
+		if (dc->optimized_required || dc->wm_optimized_required)
 			return false;
 
-	if (!memcmp(&stream->adjust, adjust, sizeof(*adjust)))
-		return true;
-
 	stream->adjust.v_total_max = adjust->v_total_max;
 	stream->adjust.v_total_mid = adjust->v_total_mid;
 	stream->adjust.v_total_mid_frame_num = adjust->v_total_mid_frame_num;
@@ -2230,6 +2227,7 @@ void dc_post_update_surfaces_to_stream(struct dc *dc)
 	}
 
 	dc->optimized_required = false;
+	dc->wm_optimized_required = false;
 }
 
 bool dc_set_generic_gpio_for_stereo(bool enable,
@@ -2652,6 +2650,8 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
 		} else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) {
 			dc->optimized_required = true;
 		}
+
+		dc->optimized_required |= dc->wm_optimized_required;
 	}
 
 	return type;
@@ -2859,6 +2859,9 @@ static void copy_stream_update_to_stream(struct dc *dc,
 	if (update->vrr_active_fixed)
 		stream->vrr_active_fixed = *update->vrr_active_fixed;
 
+	if (update->crtc_timing_adjust)
+		stream->adjust = *update->crtc_timing_adjust;
+
 	if (update->dpms_off)
 		stream->dpms_off = *update->dpms_off;
 
@@ -4288,7 +4291,8 @@ static bool full_update_required(struct dc *dc,
 			stream_update->mst_bw_update ||
 			stream_update->func_shaper ||
 			stream_update->lut3d_func ||
-			stream_update->pending_test_pattern))
+			stream_update->pending_test_pattern ||
+			stream_update->crtc_timing_adjust))
 		return true;
 
 	if (stream) {
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index f30a341bc0901..7222f63caf28a 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1036,6 +1036,7 @@ struct dc {
 
 	/* Require to optimize clocks and bandwidth for added/removed planes */
 	bool optimized_required;
+	bool wm_optimized_required;
 	bool idle_optimizations_allowed;
 	bool enable_c20_dtm_b0;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index a23eebd9933b7..ee10941caa598 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -139,6 +139,7 @@ union stream_update_flags {
 		uint32_t wb_update:1;
 		uint32_t dsc_changed : 1;
 		uint32_t mst_bw : 1;
+		uint32_t crtc_timing_adjust : 1;
 		uint32_t fams_changed : 1;
 	} bits;
 
@@ -325,6 +326,7 @@ struct dc_stream_update {
 	struct dc_3dlut *lut3d_func;
 
 	struct test_pattern *pending_test_pattern;
+	struct dc_crtc_timing_adjust *crtc_timing_adjust;
 };
 
 bool dc_is_stream_unchanged(
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 51dd2ae09b2a6..6dd479e8a3485 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -3076,7 +3076,7 @@ void dcn10_prepare_bandwidth(
 			context,
 			false);
 
-	dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+	dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub,
 			&context->bw_ctx.bw.dcn.watermarks,
 			dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 			true);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 0dfcb3cdcd20c..e931342fcf4cf 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -2159,10 +2159,10 @@ void dcn20_prepare_bandwidth(
 	}
 
 	/* program dchubbub watermarks:
-	 * For assigning optimized_required, use |= operator since we don't want
+	 * For assigning wm_optimized_required, use |= operator since we don't want
 	 * to clear the value if the optimize has not happened yet
 	 */
-	dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+	dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub,
 					&context->bw_ctx.bw.dcn.watermarks,
 					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 					false);
@@ -2175,10 +2175,10 @@ void dcn20_prepare_bandwidth(
 	if (hubbub->funcs->program_compbuf_size) {
 		if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) {
 			compbuf_size_kb = context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes;
-			dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
+			dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
 		} else {
 			compbuf_size_kb = context->bw_ctx.bw.dcn.compbuf_size_kb;
-			dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
+			dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
 		}
 
 		hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, false);
-- 
GitLab


From 5f3bce13266e6fe2f7a46f94d8bc94d5274e276b Mon Sep 17 00:00:00 2001
From: Peichen Huang <peichen.huang@amd.com>
Date: Thu, 14 Dec 2023 23:16:34 +0800
Subject: [PATCH 2409/4076] drm/amd/display: Request usb4 bw for mst streams

[WHY]
When usb4 bandwidth allocation mode is enabled, driver need to request
bandwidth from connection manager. For mst link,  the requested
bandwidth should be big enough for all remote streams.

[HOW]
- If mst link, the requested bandwidth should be the sum of all mst
  streams bandwidth added with dp MTPH overhead.
- Allocate/deallcate usb4 bandwidth when setting dpms on/off.
- When doing display mode validation, driver also need to consider total
  bandwidth of all mst streams for mst link.

Reviewed-by: Cruise Hung <cruise.hung@amd.com>
Acked-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Peichen Huang <peichen.huang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_types.h     | 12 ++--
 .../gpu/drm/amd/display/dc/link/link_dpms.c   | 42 ++++++++++---
 .../drm/amd/display/dc/link/link_validation.c | 60 +++++++++++++++----
 .../dc/link/protocols/link_dp_dpia_bw.c       | 59 +++++++++++++-----
 .../dc/link/protocols/link_dp_dpia_bw.h       |  9 +++
 5 files changed, 144 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 4f276169e05a9..b08ccb8c68bc3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1140,23 +1140,25 @@ struct dc_panel_config {
 	} ilr;
 };
 
+#define MAX_SINKS_PER_LINK 4
+
 /*
  *  USB4 DPIA BW ALLOCATION STRUCTS
  */
 struct dc_dpia_bw_alloc {
-	int sink_verified_bw;  // The Verified BW that sink can allocated and use that has been verified already
-	int sink_allocated_bw; // The Actual Allocated BW that sink currently allocated
-	int sink_max_bw;       // The Max BW that sink can require/support
+	int remote_sink_req_bw[MAX_SINKS_PER_LINK]; // BW requested by remote sinks
+	int link_verified_bw;  // The Verified BW that link can allocated and use that has been verified already
+	int link_max_bw;       // The Max BW that link can require/support
+	int allocated_bw;      // The Actual Allocated BW for this DPIA
 	int estimated_bw;      // The estimated available BW for this DPIA
 	int bw_granularity;    // BW Granularity
+	int dp_overhead;       // DP overhead in dp tunneling
 	bool bw_alloc_enabled; // The BW Alloc Mode Support is turned ON for all 3:  DP-Tx & Dpia & CM
 	bool response_ready;   // Response ready from the CM side
 	uint8_t nrd_max_lane_count; // Non-reduced max lane count
 	uint8_t nrd_max_link_rate; // Non-reduced max link rate
 };
 
-#define MAX_SINKS_PER_LINK 4
-
 enum dc_hpd_enable_select {
 	HPD_EN_FOR_ALL_EDP = 0,
 	HPD_EN_FOR_PRIMARY_EDP_ONLY,
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 5fe8b4871c776..3de148004c066 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -2005,17 +2005,11 @@ static enum dc_status enable_link_dp(struct dc_state *state,
 		}
 	}
 
-	/*
-	 * If the link is DP-over-USB4 do the following:
-	 * - Train with fallback when enabling DPIA link. Conventional links are
+	/* Train with fallback when enabling DPIA link. Conventional links are
 	 * trained with fallback during sink detection.
-	 * - Allocate only what the stream needs for bw in Gbps. Inform the CM
-	 * in case stream needs more or less bw from what has been allocated
-	 * earlier at plug time.
 	 */
-	if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) {
+	if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
 		do_fallback = true;
-	}
 
 	/*
 	 * Temporary w/a to get DP2.0 link rates to work with SST.
@@ -2197,6 +2191,32 @@ static enum dc_status enable_link(
 	return status;
 }
 
+static bool allocate_usb4_bandwidth_for_stream(struct dc_stream_state *stream, int bw)
+{
+	return true;
+}
+
+static bool allocate_usb4_bandwidth(struct dc_stream_state *stream)
+{
+	bool ret;
+
+	int bw = dc_bandwidth_in_kbps_from_timing(&stream->timing,
+			dc_link_get_highest_encoding_format(stream->sink->link));
+
+	ret = allocate_usb4_bandwidth_for_stream(stream, bw);
+
+	return ret;
+}
+
+static bool deallocate_usb4_bandwidth(struct dc_stream_state *stream)
+{
+	bool ret;
+
+	ret = allocate_usb4_bandwidth_for_stream(stream, 0);
+
+	return ret;
+}
+
 void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
 {
 	struct dc  *dc = pipe_ctx->stream->ctx->dc;
@@ -2232,6 +2252,9 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
 	update_psp_stream_config(pipe_ctx, true);
 	dc->hwss.blank_stream(pipe_ctx);
 
+	if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
+		deallocate_usb4_bandwidth(pipe_ctx->stream);
+
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		deallocate_mst_payload(pipe_ctx);
 	else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT &&
@@ -2474,6 +2497,9 @@ void link_set_dpms_on(
 		}
 	}
 
+	if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
+		allocate_usb4_bandwidth(pipe_ctx->stream);
+
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		allocate_mst_payload(pipe_ctx);
 	else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT &&
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
index b45fda96eaf64..8fe66c3678508 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
@@ -346,23 +346,61 @@ enum dc_status link_validate_mode_timing(
 	return DC_OK;
 }
 
+/*
+ * This function calculates the bandwidth required for the stream timing
+ * and aggregates the stream bandwidth for the respective dpia link
+ *
+ * @stream: pointer to the dc_stream_state struct instance
+ * @num_streams: number of streams to be validated
+ *
+ * return: true if validation is succeeded
+ */
 bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const unsigned int num_streams)
 {
-	bool ret = true;
-	int bw_needed[MAX_DPIA_NUM];
-	struct dc_link *link[MAX_DPIA_NUM];
-
-	if (!num_streams || num_streams > MAX_DPIA_NUM)
-		return ret;
+	int bw_needed[MAX_DPIA_NUM] = {0};
+	struct dc_link *dpia_link[MAX_DPIA_NUM] = {0};
+	int num_dpias = 0;
 
 	for (uint8_t i = 0; i < num_streams; ++i) {
+		if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) {
+			/* new dpia sst stream, check whether it exceeds max dpia */
+			if (num_dpias >= MAX_DPIA_NUM)
+				return false;
 
-		link[i] = stream[i].link;
-		bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
-				dc_link_get_highest_encoding_format(link[i]));
+			dpia_link[num_dpias] = stream[i].link;
+			bw_needed[num_dpias] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
+					dc_link_get_highest_encoding_format(dpia_link[num_dpias]));
+			num_dpias++;
+		} else if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+			uint8_t j = 0;
+			/* check whether its a known dpia link */
+			for (; j < num_dpias; ++j) {
+				if (dpia_link[j] == stream[i].link)
+					break;
+			}
+
+			if (j == num_dpias) {
+				/* new dpia mst stream, check whether it exceeds max dpia */
+				if (num_dpias >= MAX_DPIA_NUM)
+					return false;
+				else {
+					dpia_link[j] = stream[i].link;
+					num_dpias++;
+				}
+			}
+
+			bw_needed[j] += dc_bandwidth_in_kbps_from_timing(&stream[i].timing,
+				dc_link_get_highest_encoding_format(dpia_link[j]));
+		}
 	}
 
-	ret = dpia_validate_usb4_bw(link, bw_needed, num_streams);
+	/* Include dp overheads */
+	for (uint8_t i = 0; i < num_dpias; ++i) {
+		int dp_overhead = 0;
+
+		dp_overhead = link_dp_dpia_get_dp_overhead_in_dp_tunneling(dpia_link[i]);
+		bw_needed[i] += dp_overhead;
+	}
 
-	return ret;
+	return dpia_validate_usb4_bw(dpia_link, bw_needed, num_dpias);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index a7aa8c9da868f..4ef1a6a1d1295 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -54,12 +54,18 @@ static bool get_bw_alloc_proceed_flag(struct dc_link *tmp)
 static void reset_bw_alloc_struct(struct dc_link *link)
 {
 	link->dpia_bw_alloc_config.bw_alloc_enabled = false;
-	link->dpia_bw_alloc_config.sink_verified_bw = 0;
-	link->dpia_bw_alloc_config.sink_max_bw = 0;
+	link->dpia_bw_alloc_config.link_verified_bw = 0;
+	link->dpia_bw_alloc_config.link_max_bw = 0;
+	link->dpia_bw_alloc_config.allocated_bw = 0;
 	link->dpia_bw_alloc_config.estimated_bw = 0;
 	link->dpia_bw_alloc_config.bw_granularity = 0;
+	link->dpia_bw_alloc_config.dp_overhead = 0;
 	link->dpia_bw_alloc_config.response_ready = false;
-	link->dpia_bw_alloc_config.sink_allocated_bw = 0;
+	link->dpia_bw_alloc_config.nrd_max_lane_count = 0;
+	link->dpia_bw_alloc_config.nrd_max_link_rate = 0;
+	for (int i = 0; i < MAX_SINKS_PER_LINK; i++)
+		link->dpia_bw_alloc_config.remote_sink_req_bw[i] = 0;
+	DC_LOG_DEBUG("reset usb4 bw alloc of link(%d)\n", link->link_index);
 }
 
 #define BW_GRANULARITY_0 4 // 0.25 Gbps
@@ -210,8 +216,8 @@ static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_in
 				link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) &&
 				(link_dpia_secondary->hpd_status &&
 				link_dpia_secondary->dpia_bw_alloc_config.bw_alloc_enabled)) {
-				total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw +
-					link_dpia_secondary->dpia_bw_alloc_config.sink_allocated_bw;
+					total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw +
+						link_dpia_secondary->dpia_bw_alloc_config.allocated_bw;
 			} else if (link_dpia_primary->hpd_status &&
 					link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) {
 				total_bw = link_dpia_primary->dpia_bw_alloc_config.estimated_bw;
@@ -264,7 +270,7 @@ static void set_usb4_req_bw_req(struct dc_link *link, int req_bw)
 
 	/* Error check whether requested and allocated are equal */
 	req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
-	if (req_bw == link->dpia_bw_alloc_config.sink_allocated_bw) {
+	if (req_bw == link->dpia_bw_alloc_config.allocated_bw) {
 		DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n",
 			__func__, link->link_index);
 	}
@@ -387,9 +393,9 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res
 		DC_LOG_DEBUG("%s: BW REQ SUCCESS for DP-TX Request for link(%d)\n",
 			__func__, link->link_index);
 		DC_LOG_DEBUG("%s: current allocated_bw(%d), new allocated_bw(%d)\n",
-			__func__, link->dpia_bw_alloc_config.sink_allocated_bw, bw_needed);
+			__func__, link->dpia_bw_alloc_config.allocated_bw, bw_needed);
 
-		link->dpia_bw_alloc_config.sink_allocated_bw = bw_needed;
+		link->dpia_bw_alloc_config.allocated_bw = bw_needed;
 
 		link->dpia_bw_alloc_config.response_ready = true;
 		break;
@@ -427,8 +433,8 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
 	if (link->hpd_status && peak_bw > 0) {
 
 		// If DP over USB4 then we need to check BW allocation
-		link->dpia_bw_alloc_config.sink_max_bw = peak_bw;
-		set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.sink_max_bw);
+		link->dpia_bw_alloc_config.link_max_bw = peak_bw;
+		set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.link_max_bw);
 
 		do {
 			if (timeout > 0)
@@ -440,8 +446,8 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
 
 		if (!timeout)
 			ret = 0;// ERROR TIMEOUT waiting for response for allocating bw
-		else if (link->dpia_bw_alloc_config.sink_allocated_bw > 0)
-			ret = link->dpia_bw_alloc_config.sink_allocated_bw;
+		else if (link->dpia_bw_alloc_config.allocated_bw > 0)
+			ret = link->dpia_bw_alloc_config.allocated_bw;
 	}
 	//2. Cold Unplug
 	else if (!link->hpd_status)
@@ -450,7 +456,6 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea
 out:
 	return ret;
 }
-
 bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw)
 {
 	bool ret = false;
@@ -458,7 +463,7 @@ bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int r
 
 	DC_LOG_DEBUG("%s: ENTER: link(%d), hpd_status(%d), current allocated_bw(%d), req_bw(%d)\n",
 		__func__, link->link_index, link->hpd_status,
-		link->dpia_bw_alloc_config.sink_allocated_bw, req_bw);
+		link->dpia_bw_alloc_config.allocated_bw, req_bw);
 
 	if (!get_bw_alloc_proceed_flag(link))
 		goto out;
@@ -523,3 +528,29 @@ bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed_per_dpia, const
 
 	return ret;
 }
+
+int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link)
+{
+	int dp_overhead = 0, link_mst_overhead = 0;
+
+	if (!get_bw_alloc_proceed_flag((link)))
+		return dp_overhead;
+
+	/* if its mst link, add MTPH overhead */
+	if ((link->type == dc_connection_mst_branch) &&
+		!link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED) {
+		/* For 8b/10b encoding: MTP is 64 time slots long, slot 0 is used for MTPH
+		 * MST overhead is 1/64 of link bandwidth (excluding any overhead)
+		 */
+		const struct dc_link_settings *link_cap =
+			dc_link_get_link_cap(link);
+		uint32_t link_bw_in_kbps =
+			link_cap->link_rate * link_cap->lane_count * LINK_RATE_REF_FREQ_IN_KHZ * 8;
+		link_mst_overhead = (link_bw_in_kbps / 64) + ((link_bw_in_kbps % 64) ? 1 : 0);
+	}
+
+	/* add all the overheads */
+	dp_overhead = link_mst_overhead;
+
+	return dp_overhead;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
index 981bc4eb6120e..3b6d8494f9d5d 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h
@@ -99,4 +99,13 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res
  */
 bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed, const unsigned int num_dpias);
 
+/*
+ * Obtain all the DP overheads in dp tunneling for the dpia link
+ *
+ * @link: pointer to the dc_link struct instance
+ *
+ * return: DP overheads in DP tunneling
+ */
+int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link);
+
 #endif /* DC_INC_LINK_DP_DPIA_BW_H_ */
-- 
GitLab


From bf282eb92b84709d99186ad5940b9997eb3c1ff2 Mon Sep 17 00:00:00 2001
From: Daniel Miess <daniel.miess@amd.com>
Date: Wed, 20 Dec 2023 10:34:32 -0500
Subject: [PATCH 2410/4076] Revert "drm/amd/display: Fix conversions between
 bytes and KB"

This reverts commit d0f639c5869399bf6dde4d694d5f8c0ab8c0ec46.

The previous commit causes failure to light up for 1080p
eDP + 8k HDMI panel combo.

Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Daniel Miess <daniel.miess@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/dml2/display_mode_core.c    | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index b95bf27f2fe2f..a6b938a12de13 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -6229,7 +6229,7 @@ static void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *m
 				CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable;
 				CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
 				CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
-				CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+				CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 				CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k];
 				CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
 				CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k];
@@ -6329,7 +6329,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 				mode_lib->ms.NoOfDPPThisState,
 				mode_lib->ms.dpte_group_bytes,
 				s->HostVMInefficiencyFactor,
-				mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+				mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 				mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
 
 		s->NextMaxVStartup = s->MaxVStartupAllPlanes[j];
@@ -6542,7 +6542,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 						mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
 						mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
 						mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
-						mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+						mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 						mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k],
 						mode_lib->ms.MetaRowBytes[j][k],
 						mode_lib->ms.DPTEBytesPerRow[j][k],
@@ -7687,7 +7687,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
 		CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 		CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 		CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
-		CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+		CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 		CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
 		CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
 		CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = mode_lib->ms.PTEBufferSizeNotExceededPerState;
@@ -7957,7 +7957,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
 		UseMinimumDCFCLK_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 		UseMinimumDCFCLK_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
 		UseMinimumDCFCLK_params->NumberOfActiveSurfaces = mode_lib->ms.num_active_planes;
-		UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+		UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 		UseMinimumDCFCLK_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 		UseMinimumDCFCLK_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
 		UseMinimumDCFCLK_params->ImmediateFlipRequirement = s->ImmediateFlipRequiredFinal;
@@ -8699,7 +8699,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 	CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 	CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 	CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
-	CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+	CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 	CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
 	CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
 	CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = s->dummy_boolean_array[0];
@@ -8805,7 +8805,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 			mode_lib->ms.cache_display_cfg.hw.DPPPerSurface,
 			locals->dpte_group_bytes,
 			s->HostVMInefficiencyFactor,
-			mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+			mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 			mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
 
 	locals->TCalc = 24.0 / locals->DCFCLKDeepSleep;
@@ -8995,7 +8995,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 			CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable;
 			CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
 			CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
-			CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+			CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 			CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k];
 			CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
 			CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k];
@@ -9240,7 +9240,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 						mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
 						mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
 						mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
-						mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+						mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 						locals->PDEAndMetaPTEBytesFrame[k],
 						locals->MetaRowByte[k],
 						locals->PixelPTEBytesPerRow[k],
-- 
GitLab


From 2476bf4328d1a55db709ce9ad2c274d26040311b Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Thu, 21 Dec 2023 09:42:28 -0500
Subject: [PATCH 2411/4076] drm/amd/display: Update z8 latency

Adjust z8 latency for performance.

Reviewed-by: Muhammad Ahmed <ahmed.ahmed@amd.com>
Acked-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 3d12dabd39e47..475c4ec43c013 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -166,9 +166,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 	.num_states = 5,
 	.sr_exit_time_us = 14.0,
 	.sr_enter_plus_exit_time_us = 16.0,
-	.sr_exit_z8_time_us = 525.0,
-	.sr_enter_plus_exit_z8_time_us = 715.0,
-	.fclk_change_latency_us = 20.0,
+	.sr_exit_z8_time_us = 210.0,
+	.sr_enter_plus_exit_z8_time_us = 320.0,
+	.fclk_change_latency_us = 24.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
 
-- 
GitLab


From ab76bd72ee12d9117c3a16d749ffce84f5b235bf Mon Sep 17 00:00:00 2001
From: Meenakshikumar Somasundaram <meenakshikumar.somasundaram@amd.com>
Date: Tue, 19 Dec 2023 15:51:24 -0500
Subject: [PATCH 2412/4076] drm/amd/display: Dpia hpd status not in sync after
 S4

[Why]
Dpia hpd status not in sync causing driver not enabling BW Alloc after
S4.

[How]
Update hpd_status of the link when querying hpd state from dmub in
dpia_query_hpd_status().

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Meenakshikumar Somasundaram <meenakshikumar.somasundaram@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/link/protocols/link_dp_dpia.c  | 36 +++++++++++--------
 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
index 982eda3c46f56..6af42ba9885c0 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c
@@ -82,25 +82,33 @@ bool dpia_query_hpd_status(struct dc_link *link)
 {
 	union dmub_rb_cmd cmd = {0};
 	struct dc_dmub_srv *dmub_srv = link->ctx->dmub_srv;
-	bool is_hpd_high = false;
 
 	/* prepare QUERY_HPD command */
 	cmd.query_hpd.header.type = DMUB_CMD__QUERY_HPD_STATE;
 	cmd.query_hpd.data.instance = link->link_id.enum_id - ENUM_ID_1;
 	cmd.query_hpd.data.ch_type = AUX_CHANNEL_DPIA;
 
-	/* Return HPD status reported by DMUB if query successfully executed. */
-	if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) &&
-	    cmd.query_hpd.data.status == AUX_RET_SUCCESS)
-		is_hpd_high = cmd.query_hpd.data.result;
-
-	DC_LOG_DEBUG("%s: link(%d) dpia(%d) cmd_status(%d) result(%d)\n",
-		__func__,
-		link->link_index,
-		link->link_id.enum_id - ENUM_ID_1,
-		cmd.query_hpd.data.status,
-		cmd.query_hpd.data.result);
-
-	return is_hpd_high;
+	/* Query dpia hpd status from dmub */
+	if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd,
+		DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) &&
+	    cmd.query_hpd.data.status == AUX_RET_SUCCESS) {
+		DC_LOG_DEBUG("%s: for link(%d) dpia(%d) success, current_hpd_status(%d) new_hpd_status(%d)\n",
+			__func__,
+			link->link_index,
+			link->link_id.enum_id - ENUM_ID_1,
+			link->hpd_status,
+			cmd.query_hpd.data.result);
+		link->hpd_status = cmd.query_hpd.data.result;
+	} else {
+		DC_LOG_ERROR("%s: for link(%d) dpia(%d) failed with status(%d), current_hpd_status(%d) new_hpd_status(0)\n",
+			__func__,
+			link->link_index,
+			link->link_id.enum_id - ENUM_ID_1,
+			cmd.query_hpd.data.status,
+			link->hpd_status);
+		link->hpd_status = false;
+	}
+
+	return link->hpd_status;
 }
 
-- 
GitLab


From d32156a07575d69916944ce0e2d4a71a4c95979d Mon Sep 17 00:00:00 2001
From: Aric Cyr <aric.cyr@amd.com>
Date: Sun, 17 Dec 2023 19:36:16 -0500
Subject: [PATCH 2413/4076] drm/amd/display: 3.2.266

This version brings along following fixes:

- Improve z8/z10 support.
- Revert some of the VRR optimization.
- Improve usb4 when using MST.

Acked-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 7222f63caf28a..5d7aa882416b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -51,7 +51,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.265"
+#define DC_VER "3.2.266"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
-- 
GitLab


From 90bd01471d1c7f2d2db3c69259e247357991fe50 Mon Sep 17 00:00:00 2001
From: Candice Li <candice.li@amd.com>
Date: Thu, 4 Jan 2024 09:34:25 +0800
Subject: [PATCH 2414/4076] drm/amdgpu: Drop unnecessary sentences about CE and
 deferred error.

Remove "no user action is needed" for correctable and deferred error
to avoid confusion.

Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 14 +++++---------
 drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c  |  3 +--
 drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c  |  3 +--
 drivers/gpu/drm/amd/amdgpu/umc_v6_7.c   |  2 +-
 4 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index fc42fb6ee1914..9a64584318e02 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1067,8 +1067,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
 			mcm_info = &err_info->mcm_info;
 			if (err_info->ce_count) {
 				dev_info(adev->dev, "socket: %d, die: %d, "
-					 "%lld new correctable hardware errors detected in %s block, "
-					 "no user action is needed\n",
+					 "%lld new correctable hardware errors detected in %s block\n",
 					 mcm_info->socket_id,
 					 mcm_info->die_id,
 					 err_info->ce_count,
@@ -1080,8 +1079,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
 			err_info = &err_node->err_info;
 			mcm_info = &err_info->mcm_info;
 			dev_info(adev->dev, "socket: %d, die: %d, "
-				 "%lld correctable hardware errors detected in total in %s block, "
-				 "no user action is needed\n",
+				 "%lld correctable hardware errors detected in total in %s block\n",
 				 mcm_info->socket_id, mcm_info->die_id, err_info->ce_count, blk_name);
 		}
 	}
@@ -1108,16 +1106,14 @@ static void amdgpu_ras_error_generate_report(struct amdgpu_device *adev,
 			   adev->smuio.funcs->get_die_id) {
 			dev_info(adev->dev, "socket: %d, die: %d "
 				 "%ld correctable hardware errors "
-				 "detected in %s block, no user "
-				 "action is needed.\n",
+				 "detected in %s block\n",
 				 adev->smuio.funcs->get_socket_id(adev),
 				 adev->smuio.funcs->get_die_id(adev),
 				 ras_mgr->err_data.ce_count,
 				 blk_name);
 		} else {
 			dev_info(adev->dev, "%ld correctable hardware errors "
-				 "detected in %s block, no user "
-				 "action is needed.\n",
+				 "detected in %s block\n",
 				 ras_mgr->err_data.ce_count,
 				 blk_name);
 		}
@@ -1920,7 +1916,7 @@ static void amdgpu_ras_interrupt_poison_creation_handler(struct ras_manager *obj
 				struct amdgpu_iv_entry *entry)
 {
 	dev_info(obj->adev->dev,
-		"Poison is created, no user action is needed.\n");
+		"Poison is created\n");
 }
 
 static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 6d24c84924cb5..19986ff6a48d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -401,8 +401,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 
 			if (err_data.ce_count)
 				dev_info(adev->dev, "%ld correctable hardware "
-						"errors detected in %s block, "
-						"no user action is needed.\n",
+						"errors detected in %s block\n",
 						obj->err_data.ce_count,
 						get_ras_block_str(adev->nbio.ras_if));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 25a3da83e0fb9..e90f337808034 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -597,8 +597,7 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 
 			if (err_data.ce_count)
 				dev_info(adev->dev, "%ld correctable hardware "
-						"errors detected in %s block, "
-						"no user action is needed.\n",
+						"errors detected in %s block\n",
 						obj->err_data.ce_count,
 						get_ras_block_str(adev->nbio.ras_if));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
index 530549314ce46..a3ee3c4c650fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
@@ -64,7 +64,7 @@ static void umc_v6_7_query_error_status_helper(struct amdgpu_device *adev,
 	uint64_t reg_value;
 
 	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1)
-		dev_info(adev->dev, "Deferred error, no user action is needed.\n");
+		dev_info(adev->dev, "Deferred error\n");
 
 	if (mc_umc_status)
 		dev_info(adev->dev, "MCA STATUS 0x%llx, umc_reg_offset 0x%x\n", mc_umc_status, umc_reg_offset);
-- 
GitLab


From f4a94dbb6dc0bed10a5fc63718d00f1de45b12c0 Mon Sep 17 00:00:00 2001
From: Likun Gao <Likun.Gao@amd.com>
Date: Fri, 5 Jan 2024 17:33:34 +0800
Subject: [PATCH 2415/4076] drm/amdgpu: correct the cu count for gfx v11

Correct the algorithm of active CU to skip disabled
sa for gfx v11.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 2fbcd9765980d..c7242877d5d31 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -6383,6 +6383,9 @@ static int gfx_v11_0_get_cu_info(struct amdgpu_device *adev,
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			bitmap = i * adev->gfx.config.max_sh_per_se + j;
+			if (!((gfx_v11_0_get_sa_active_bitmap(adev) >> bitmap) & 1))
+				continue;
 			mask = 1;
 			counter = 0;
 			gfx_v11_0_select_se_sh(adev, i, j, 0xffffffff, 0);
-- 
GitLab


From fb1e91719983c529f85602fdd08c0b7dbf384b1c Mon Sep 17 00:00:00 2001
From: Candice Li <candice.li@amd.com>
Date: Thu, 4 Jan 2024 10:27:10 +0800
Subject: [PATCH 2416/4076] drm/amdgpu: Support poison error injection via
 ras_ctrl debugfs

Support poison error injection.

Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 9a64584318e02..3f7f5c12961d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -305,11 +305,13 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 			return -EINVAL;
 
 		data->head.block = block_id;
-		/* only ue and ce errors are supported */
+		/* only ue, ce and poison errors are supported */
 		if (!memcmp("ue", err, 2))
 			data->head.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		else if (!memcmp("ce", err, 2))
 			data->head.type = AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE;
+		else if (!memcmp("poison", err, 6))
+			data->head.type = AMDGPU_RAS_ERROR__POISON;
 		else
 			return -EINVAL;
 
@@ -431,9 +433,10 @@ static void amdgpu_ras_instance_mask_check(struct amdgpu_device *adev,
  * The block is one of: umc, sdma, gfx, etc.
  *	see ras_block_string[] for details
  *
- * The error type is one of: ue, ce, where,
+ * The error type is one of: ue, ce and poison where,
  *	ue is multi-uncorrectable
  *	ce is single-correctable
+ *	poison is poison
  *
  * The sub-block is a the sub-block index, pass 0 if there is no sub-block.
  * The address and value are hexadecimal numbers, leading 0x is optional.
-- 
GitLab


From 73cb81dc548f154547d9205d5b9603ba10e2a402 Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Fri, 29 Dec 2023 14:54:35 +0800
Subject: [PATCH 2417/4076] drm/amdgpu: Packed socket_id to ras feature mask

Initialize RAS feature mask bit[31:29] with socket_id.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 3f7f5c12961d3..31823a30dea21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2919,6 +2919,11 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 
 	amdgpu_ras_query_poison_mode(adev);
 
+	/* Packed socket_id to ras feature mask bits[31:29] */
+	if (adev->smuio.funcs &&
+	    adev->smuio.funcs->get_socket_id)
+		con->features |= ((adev->smuio.funcs->get_socket_id(adev)) << 29);
+
 	/* Get RAS schema for particular SOC */
 	con->schema = amdgpu_get_ras_schema(adev);
 
-- 
GitLab


From 2a9de42e8d3c82c6990d226198602be44f43f340 Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Fri, 29 Dec 2023 15:19:25 -0500
Subject: [PATCH 2418/4076] drm/amdkfd: Fix lock dependency warning with srcu

======================================================
WARNING: possible circular locking dependency detected
6.5.0-kfd-yangp #2289 Not tainted
------------------------------------------------------
kworker/0:2/996 is trying to acquire lock:
        (srcu){.+.+}-{0:0}, at: __synchronize_srcu+0x5/0x1a0

but task is already holding lock:
        ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}, at:
	process_one_work+0x211/0x560

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #3 ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}:
        __flush_work+0x88/0x4f0
        svm_range_list_lock_and_flush_work+0x3d/0x110 [amdgpu]
        svm_range_set_attr+0xd6/0x14c0 [amdgpu]
        kfd_ioctl+0x1d1/0x630 [amdgpu]
        __x64_sys_ioctl+0x88/0xc0

-> #2 (&info->lock#2){+.+.}-{3:3}:
        __mutex_lock+0x99/0xc70
        amdgpu_amdkfd_gpuvm_restore_process_bos+0x54/0x740 [amdgpu]
        restore_process_helper+0x22/0x80 [amdgpu]
        restore_process_worker+0x2d/0xa0 [amdgpu]
        process_one_work+0x29b/0x560
        worker_thread+0x3d/0x3d0

-> #1 ((work_completion)(&(&process->restore_work)->work)){+.+.}-{0:0}:
        __flush_work+0x88/0x4f0
        __cancel_work_timer+0x12c/0x1c0
        kfd_process_notifier_release_internal+0x37/0x1f0 [amdgpu]
        __mmu_notifier_release+0xad/0x240
        exit_mmap+0x6a/0x3a0
        mmput+0x6a/0x120
        do_exit+0x322/0xb90
        do_group_exit+0x37/0xa0
        __x64_sys_exit_group+0x18/0x20
        do_syscall_64+0x38/0x80

-> #0 (srcu){.+.+}-{0:0}:
        __lock_acquire+0x1521/0x2510
        lock_sync+0x5f/0x90
        __synchronize_srcu+0x4f/0x1a0
        __mmu_notifier_release+0x128/0x240
        exit_mmap+0x6a/0x3a0
        mmput+0x6a/0x120
        svm_range_deferred_list_work+0x19f/0x350 [amdgpu]
        process_one_work+0x29b/0x560
        worker_thread+0x3d/0x3d0

other info that might help us debug this:
Chain exists of:
  srcu --> &info->lock#2 --> (work_completion)(&svms->deferred_list_work)

Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
        lock((work_completion)(&svms->deferred_list_work));
                        lock(&info->lock#2);
			lock((work_completion)(&svms->deferred_list_work));
        sync(srcu);

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index d46c145835e09..4e9f07c7a9376 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2340,8 +2340,10 @@ retry:
 		mutex_unlock(&svms->lock);
 		mmap_write_unlock(mm);
 
-		/* Pairs with mmget in svm_range_add_list_work */
-		mmput(mm);
+		/* Pairs with mmget in svm_range_add_list_work. If dropping the
+		 * last mm refcount, schedule release work to avoid circular locking
+		 */
+		mmput_async(mm);
 
 		spin_lock(&svms->deferred_list_lock);
 	}
-- 
GitLab


From c147ddc68e741aed78bba796effe049344d87ab8 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <felix.kuehling@amd.com>
Date: Wed, 3 Jan 2024 18:13:04 -0500
Subject: [PATCH 2419/4076] drm/amdkfd: Fix sparse __rcu annotation warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Properly mark kfd_process->ef as __rcu and consistently use the right
accessor functions.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312052245.yFpBSgNH-lkp@intel.com/
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h       | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 4 ++--
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h            | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_process.c         | 7 +++++--
 4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index cf6ed5fce291f..f262b9d89541a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -311,7 +311,7 @@ void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_mem *mem);
 int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo);
 
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
-					    struct dma_fence **ef);
+					    struct dma_fence __rcu **ef);
 int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct amdgpu_device *adev,
 					      struct kfd_vm_fault_info *info);
 int amdgpu_amdkfd_gpuvm_import_dmabuf_fd(struct amdgpu_device *adev, int fd,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index d17b2452cb1f6..f183d7faeeece 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2802,7 +2802,7 @@ unlock_out:
 	put_task_struct(usertask);
 }
 
-static void replace_eviction_fence(struct dma_fence **ef,
+static void replace_eviction_fence(struct dma_fence __rcu **ef,
 				   struct dma_fence *new_ef)
 {
 	struct dma_fence *old_ef = rcu_replace_pointer(*ef, new_ef, true
@@ -2837,7 +2837,7 @@ static void replace_eviction_fence(struct dma_fence **ef,
  * 7.  Add fence to all PD and PT BOs.
  * 8.  Unreserve all BOs
  */
-int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
+int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu **ef)
 {
 	struct amdkfd_process_info *process_info = info;
 	struct amdgpu_vm *peer_vm;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 745024b313401..17fbedbf36513 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -917,7 +917,7 @@ struct kfd_process {
 	 * fence will be triggered during eviction and new one will be created
 	 * during restore
 	 */
-	struct dma_fence *ef;
+	struct dma_fence __rcu *ef;
 
 	/* Work items for evicting and restoring BOs */
 	struct delayed_work eviction_work;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 71df51fcc1b0d..717a60d7a4ea9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1110,6 +1110,7 @@ static void kfd_process_wq_release(struct work_struct *work)
 {
 	struct kfd_process *p = container_of(work, struct kfd_process,
 					     release_work);
+	struct dma_fence *ef;
 
 	kfd_process_dequeue_from_all_devices(p);
 	pqm_uninit(&p->pqm);
@@ -1118,7 +1119,9 @@ static void kfd_process_wq_release(struct work_struct *work)
 	 * destroyed. This allows any BOs to be freed without
 	 * triggering pointless evictions or waiting for fences.
 	 */
-	dma_fence_signal(p->ef);
+	synchronize_rcu();
+	ef = rcu_access_pointer(p->ef);
+	dma_fence_signal(ef);
 
 	kfd_process_remove_sysfs(p);
 
@@ -1127,7 +1130,7 @@ static void kfd_process_wq_release(struct work_struct *work)
 	svm_range_list_fini(p);
 
 	kfd_process_destroy_pdds(p);
-	dma_fence_put(p->ef);
+	dma_fence_put(ef);
 
 	kfd_event_free_process(p);
 
-- 
GitLab


From c2ab9ce0ee7225fc05f58a6671c43b8a3684f530 Mon Sep 17 00:00:00 2001
From: Ivan Lipski <ivlipski@amd.com>
Date: Fri, 5 Jan 2024 19:40:50 -0500
Subject: [PATCH 2420/4076] Revert "drm/amd/display: fix bandwidth validation
 failure on DCN 2.1"

This commit causes dmesg-warn on several IGT tests on DCN 3.1.6: *ERROR*
link_enc_cfg_validate: Invalid link encoder assignments - 0x1c

Affected IGT tests include:
- amdgpu/[amd_assr|amd_plane|amd_hotplug]
- kms_atomic
- kms_color
- kms_flip
- kms_properties
- kms_universal_plane

and some other tests

This reverts commit 3a0fa3bc245ef92838a8296e0055569b8dff94c4.

Cc: Melissa Wen <mwen@igalia.com>
Cc: Hamza Mahfooz <hamza.mahfooz@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Ivan Lipski <ivlipski@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index f6575d7dee971..10b2a896c4982 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -10753,7 +10753,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			DRM_DEBUG_DRIVER("drm_dp_mst_atomic_check() failed\n");
 			goto fail;
 		}
-		status = dc_validate_global_state(dc, dm_state->context, false);
+		status = dc_validate_global_state(dc, dm_state->context, true);
 		if (status != DC_OK) {
 			DRM_DEBUG_DRIVER("DC global validation failure: %s (%d)",
 				       dc_status_to_str(status), status);
-- 
GitLab


From 50e60184bfe72400c49f7806af97edaf693ecd45 Mon Sep 17 00:00:00 2001
From: James Zhu <James.Zhu@amd.com>
Date: Tue, 2 Jan 2024 15:53:01 -0500
Subject: [PATCH 2421/4076] drm/amdgpu: make a correction on comment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use a generic comment for AMDGPU_VM_RESERVED_VRAM size.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index b6cd565562ad8..4740dd65b99d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -116,7 +116,7 @@ struct amdgpu_mem_stats;
 #define AMDGPU_VM_FAULT_STOP_FIRST	1
 #define AMDGPU_VM_FAULT_STOP_ALWAYS	2
 
-/* Reserve 4MB VRAM for page tables */
+/* How much VRAM be reserved for page tables */
 #define AMDGPU_VM_RESERVED_VRAM		(8ULL << 20)
 
 /*
-- 
GitLab


From 7075893d1d68b2b3517be250a02d86e76554ed22 Mon Sep 17 00:00:00 2001
From: Melissa Wen <mwen@igalia.com>
Date: Fri, 5 Jan 2024 21:02:09 -0100
Subject: [PATCH 2422/4076] drm/amd/display: cleanup inconsistent indenting in
 amdgpu_dm_color

smatch warnings:
amdgpu_dm_update_plane_color_mgmt() warn: inconsistent indenting

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401051643.PPdbmG1U-lkp@intel.com/
Signed-off-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index 9b527bffe11a1..c87b64e464ed5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -1239,7 +1239,7 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 	if (has_crtc_cm_degamma && ret != -EINVAL) {
 		drm_dbg_kms(crtc->base.crtc->dev,
 			    "doesn't support plane and CRTC degamma at the same time\n");
-			return -EINVAL;
+		return -EINVAL;
 	}
 
 	/* If we are here, it means we don't have plane degamma settings, check
-- 
GitLab


From 4e11c29873a8a296a20f99b3e03095e65ebf897d Mon Sep 17 00:00:00 2001
From: qizhong cheng <qizhong.cheng@mediatek.com>
Date: Mon, 11 Dec 2023 17:49:23 +0800
Subject: [PATCH 2423/4076] PCI: mediatek: Clear interrupt status before
 dispatching handler
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We found a failure when using the iperf tool during WiFi performance
testing, where some MSIs were received while clearing the interrupt
status, and these MSIs cannot be serviced.

The interrupt status can be cleared even if the MSI status remains pending.
As such, given the edge-triggered interrupt type, its status should be
cleared before being dispatched to the handler of the underling device.

[kwilczynski: commit log, code comment wording]
Link: https://lore.kernel.org/linux-pci/20231211094923.31967-1-jianjun.wang@mediatek.com
Fixes: 43e6409db64d ("PCI: mediatek: Add MSI support for MT2712 and MT7622")
Signed-off-by: qizhong cheng <qizhong.cheng@mediatek.com>
Signed-off-by: Jianjun Wang <jianjun.wang@mediatek.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
[bhelgaas: rewrap comment]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Cc:  <stable@vger.kernel.org>
---
 drivers/pci/controller/pcie-mediatek.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index 66a8f73296fc8..48372013f26d2 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -617,12 +617,18 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc)
 		if (status & MSI_STATUS){
 			unsigned long imsi_status;
 
+			/*
+			 * The interrupt status can be cleared even if the
+			 * MSI status remains pending. As such, given the
+			 * edge-triggered interrupt type, its status should
+			 * be cleared before being dispatched to the
+			 * handler of the underlying device.
+			 */
+			writel(MSI_STATUS, port->base + PCIE_INT_STATUS);
 			while ((imsi_status = readl(port->base + PCIE_IMSI_STATUS))) {
 				for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM)
 					generic_handle_domain_irq(port->inner_domain, bit);
 			}
-			/* Clear MSI interrupt status */
-			writel(MSI_STATUS, port->base + PCIE_INT_STATUS);
 		}
 	}
 
-- 
GitLab


From 9ccc1318cf4bd90601f221268e42c3374703d681 Mon Sep 17 00:00:00 2001
From: Jianjun Wang <jianjun.wang@mediatek.com>
Date: Mon, 23 Oct 2023 16:14:23 +0800
Subject: [PATCH 2424/4076] PCI: mediatek-gen3: Fix translation window size
 calculation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When using the fls() helper, the translation table should be a power of
two; otherwise, the resulting value will not be correct.

For example, given fls(0x3e00000) - 1 = 25, the PCIe translation window
size will be set to 0x2000000 instead of the expected size 0x3e00000.

Fix the translation window by splitting the MMIO space into multiple tables
if its size is not a power of two.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20231023081423.18559-1-jianjun.wang@mediatek.com
Fixes: d3bf75b579b9 ("PCI: mediatek-gen3: Add MediaTek Gen3 driver for MT8192")
Signed-off-by: Jianjun Wang <jianjun.wang@mediatek.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 drivers/pci/controller/pcie-mediatek-gen3.c | 85 ++++++++++++---------
 1 file changed, 50 insertions(+), 35 deletions(-)

diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index e0e27645fdf4c..975b3024fb08c 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -245,35 +245,60 @@ static int mtk_pcie_set_trans_table(struct mtk_gen3_pcie *pcie,
 				    resource_size_t cpu_addr,
 				    resource_size_t pci_addr,
 				    resource_size_t size,
-				    unsigned long type, int num)
+				    unsigned long type, int *num)
 {
+	resource_size_t remaining = size;
+	resource_size_t table_size;
+	resource_size_t addr_align;
+	const char *range_type;
 	void __iomem *table;
 	u32 val;
 
-	if (num >= PCIE_MAX_TRANS_TABLES) {
-		dev_err(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n",
-			(unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES);
-		return -ENODEV;
-	}
+	while (remaining && (*num < PCIE_MAX_TRANS_TABLES)) {
+		/* Table size needs to be a power of 2 */
+		table_size = BIT(fls(remaining) - 1);
+
+		if (cpu_addr > 0) {
+			addr_align = BIT(ffs(cpu_addr) - 1);
+			table_size = min(table_size, addr_align);
+		}
+
+		/* Minimum size of translate table is 4KiB */
+		if (table_size < 0x1000) {
+			dev_err(pcie->dev, "illegal table size %#llx\n",
+				(unsigned long long)table_size);
+			return -EINVAL;
+		}
 
-	table = pcie->base + PCIE_TRANS_TABLE_BASE_REG +
-		num * PCIE_ATR_TLB_SET_OFFSET;
+		table = pcie->base + PCIE_TRANS_TABLE_BASE_REG + *num * PCIE_ATR_TLB_SET_OFFSET;
+		writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(table_size) - 1), table);
+		writel_relaxed(upper_32_bits(cpu_addr), table + PCIE_ATR_SRC_ADDR_MSB_OFFSET);
+		writel_relaxed(lower_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET);
+		writel_relaxed(upper_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET);
 
-	writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(size) - 1),
-		       table);
-	writel_relaxed(upper_32_bits(cpu_addr),
-		       table + PCIE_ATR_SRC_ADDR_MSB_OFFSET);
-	writel_relaxed(lower_32_bits(pci_addr),
-		       table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET);
-	writel_relaxed(upper_32_bits(pci_addr),
-		       table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET);
+		if (type == IORESOURCE_IO) {
+			val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO;
+			range_type = "IO";
+		} else {
+			val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM;
+			range_type = "MEM";
+		}
 
-	if (type == IORESOURCE_IO)
-		val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO;
-	else
-		val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM;
+		writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET);
 
-	writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET);
+		dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n",
+			range_type, *num, (unsigned long long)cpu_addr,
+			(unsigned long long)pci_addr, (unsigned long long)table_size);
+
+		cpu_addr += table_size;
+		pci_addr += table_size;
+		remaining -= table_size;
+		(*num)++;
+	}
+
+	if (remaining)
+		dev_warn(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n",
+			 (unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES);
 
 	return 0;
 }
@@ -380,30 +405,20 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie)
 		resource_size_t cpu_addr;
 		resource_size_t pci_addr;
 		resource_size_t size;
-		const char *range_type;
 
-		if (type == IORESOURCE_IO) {
+		if (type == IORESOURCE_IO)
 			cpu_addr = pci_pio_to_address(res->start);
-			range_type = "IO";
-		} else if (type == IORESOURCE_MEM) {
+		else if (type == IORESOURCE_MEM)
 			cpu_addr = res->start;
-			range_type = "MEM";
-		} else {
+		else
 			continue;
-		}
 
 		pci_addr = res->start - entry->offset;
 		size = resource_size(res);
 		err = mtk_pcie_set_trans_table(pcie, cpu_addr, pci_addr, size,
-					       type, table_index);
+					       type, &table_index);
 		if (err)
 			return err;
-
-		dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n",
-			range_type, table_index, (unsigned long long)cpu_addr,
-			(unsigned long long)pci_addr, (unsigned long long)size);
-
-		table_index++;
 	}
 
 	return 0;
-- 
GitLab


From 7dab24554dedd4e6f408af8eb2d25c89997a6a1f Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Sun, 7 Jan 2024 16:12:23 -0800
Subject: [PATCH 2425/4076] md/raid1: Use blk_opf_t for read and write
 operations

Use the type blk_opf_t for read and write operations instead of int. This
patch does not affect the generated code but fixes the following sparse
warning:

drivers/md/raid1.c:1993:60: sparse: sparse: incorrect type in argument 5 (different base types)
     expected restricted blk_opf_t [usertype] opf
     got int rw

Cc: Song Liu <song@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Fixes: 3c5e514db58f ("md/raid1: Use the new blk_opf_t type")
Cc: stable@vger.kernel.org # v6.0+
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401080657.UjFnvQgX-lkp@intel.com/
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240108001223.23835-1-bvanassche@acm.org
---
 drivers/md/raid1.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index aaa434f0c1751..24f0d799fd98e 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1968,12 +1968,12 @@ static void end_sync_write(struct bio *bio)
 }
 
 static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
-			   int sectors, struct page *page, int rw)
+			   int sectors, struct page *page, blk_opf_t rw)
 {
 	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
 		/* success */
 		return 1;
-	if (rw == WRITE) {
+	if (rw == REQ_OP_WRITE) {
 		set_bit(WriteErrorSeen, &rdev->flags);
 		if (!test_and_set_bit(WantReplacement,
 				      &rdev->flags))
@@ -2090,7 +2090,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 			rdev = conf->mirrors[d].rdev;
 			if (r1_sync_page_io(rdev, sect, s,
 					    pages[idx],
-					    WRITE) == 0) {
+					    REQ_OP_WRITE) == 0) {
 				r1_bio->bios[d]->bi_end_io = NULL;
 				rdev_dec_pending(rdev, mddev);
 			}
@@ -2105,7 +2105,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 			rdev = conf->mirrors[d].rdev;
 			if (r1_sync_page_io(rdev, sect, s,
 					    pages[idx],
-					    READ) != 0)
+					    REQ_OP_READ) != 0)
 				atomic_add(s, &rdev->corrected_errors);
 		}
 		sectors -= s;
@@ -2321,7 +2321,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 			    !test_bit(Faulty, &rdev->flags)) {
 				atomic_inc(&rdev->nr_pending);
 				r1_sync_page_io(rdev, sect, s,
-						conf->tmppage, WRITE);
+						conf->tmppage, REQ_OP_WRITE);
 				rdev_dec_pending(rdev, mddev);
 			}
 		}
@@ -2335,7 +2335,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 			    !test_bit(Faulty, &rdev->flags)) {
 				atomic_inc(&rdev->nr_pending);
 				if (r1_sync_page_io(rdev, sect, s,
-						    conf->tmppage, READ)) {
+						conf->tmppage, REQ_OP_READ)) {
 					atomic_add(s, &rdev->corrected_errors);
 					pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %pg)\n",
 						mdname(mddev), s,
-- 
GitLab


From 4c115c9c1f81a6efe2bd68fcefec6836f7f3dc71 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:30 -0800
Subject: [PATCH 2426/4076] cxl/events: Create common event UUID defines

Dan points out in review that the cxl_test code could be made better
through the use of UUID's defines rather than being open coded.[1]

Create UUID defines and use them rather than open coding them.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: http://lore.kernel.org/r/65738d09e30e2_45e0129451@dwillia2-xfh.jf.intel.com.notmuch [1]
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-3-1bb8a4ca2c7a@intel.com
[djbw: clang-format uuid definitions]
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c      | 30 +++---------------------------
 drivers/cxl/cxlmem.h         | 24 ++++++++++++++++++++++++
 tools/testing/cxl/test/mem.c |  9 +++------
 3 files changed, 30 insertions(+), 33 deletions(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 00f429c440dfe..1ccc3a56e0af6 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -836,46 +836,22 @@ out:
 }
 EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL);
 
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-static const uuid_t gen_media_event_uuid =
-	UUID_INIT(0xfbcd0a77, 0xc260, 0x417f,
-		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6);
-
-/*
- * DRAM Event Record
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
- */
-static const uuid_t dram_event_uuid =
-	UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,
-		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24);
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-static const uuid_t mem_mod_event_uuid =
-	UUID_INIT(0xfe927475, 0xdd59, 0x4339,
-		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74);
-
 static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 				   enum cxl_event_log_type type,
 				   struct cxl_event_record_raw *record)
 {
 	uuid_t *id = &record->hdr.id;
 
-	if (uuid_equal(id, &gen_media_event_uuid)) {
+	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID)) {
 		struct cxl_event_gen_media *rec =
 				(struct cxl_event_gen_media *)record;
 
 		trace_cxl_general_media(cxlmd, type, id, rec);
-	} else if (uuid_equal(id, &dram_event_uuid)) {
+	} else if (uuid_equal(id, &CXL_EVENT_DRAM_UUID)) {
 		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
 
 		trace_cxl_dram(cxlmd, type, id, rec);
-	} else if (uuid_equal(id, &mem_mod_event_uuid)) {
+	} else if (uuid_equal(id, &CXL_EVENT_MEM_MODULE_UUID)) {
 		struct cxl_event_mem_module *rec =
 				(struct cxl_event_mem_module *)record;
 
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index f0e7ebb84f028..27575513ec689 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -580,6 +580,30 @@ struct cxl_mbox_identify {
 	u8 qos_telemetry_caps;
 } __packed;
 
+/*
+ * General Media Event Record UUID
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CXL_EVENT_GEN_MEDIA_UUID                                            \
+	UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, 0x85, 0xa9, 0x08, 0x8b, 0x16, \
+		  0x21, 0xeb, 0xa6)
+
+/*
+ * DRAM Event Record UUID
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CXL_EVENT_DRAM_UUID                                                 \
+	UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, \
+		  0x5c, 0x96, 0x24)
+
+/*
+ * Memory Module Event Record UUID
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CXL_EVENT_MEM_MODULE_UUID                                           \
+	UUID_INIT(0xfe927475, 0xdd59, 0x4339, 0xa5, 0x86, 0x79, 0xba, 0xb1, \
+		  0x13, 0xb7, 0x74)
+
 /*
  * Get Event Records output payload
  * CXL rev 3.0 section 8.2.9.2.2; Table 8-50
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index ee61fa3a2411f..5a95b04b329ae 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -362,8 +362,7 @@ struct cxl_event_record_raw hardware_replace = {
 
 struct cxl_event_gen_media gen_media = {
 	.hdr = {
-		.id = UUID_INIT(0xfbcd0a77, 0xc260, 0x417f,
-				0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6),
+		.id = CXL_EVENT_GEN_MEDIA_UUID,
 		.length = sizeof(struct cxl_event_gen_media),
 		.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
 		/* .handle = Set dynamically */
@@ -380,8 +379,7 @@ struct cxl_event_gen_media gen_media = {
 
 struct cxl_event_dram dram = {
 	.hdr = {
-		.id = UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,
-				0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24),
+		.id = CXL_EVENT_DRAM_UUID,
 		.length = sizeof(struct cxl_event_dram),
 		.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
 		/* .handle = Set dynamically */
@@ -400,8 +398,7 @@ struct cxl_event_dram dram = {
 
 struct cxl_event_mem_module mem_module = {
 	.hdr = {
-		.id = UUID_INIT(0xfe927475, 0xdd59, 0x4339,
-				0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74),
+		.id = CXL_EVENT_MEM_MODULE_UUID,
 		.length = sizeof(struct cxl_event_mem_module),
 		/* .handle = Set dynamically */
 		.related_handle = cpu_to_le16(0),
-- 
GitLab


From 207a1f82301de0b4123f00a8d26ea55bb2484757 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:31 -0800
Subject: [PATCH 2427/4076] cxl/events: Remove passing a UUID to known event
 traces

The UUID data is redundant in the known event trace types.  The addition
of static defines allows the trace macros to create the UUID data inside
the trace thus removing unnecessary code.

Have well known trace events use static data to set the uuid field based
on the event type.

Suggested-by: Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-4-1bb8a4ca2c7a@intel.com
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c  |  6 +++---
 drivers/cxl/core/trace.h | 28 ++++++++++++++++------------
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 1ccc3a56e0af6..5f3681de10dec 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -846,16 +846,16 @@ static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 		struct cxl_event_gen_media *rec =
 				(struct cxl_event_gen_media *)record;
 
-		trace_cxl_general_media(cxlmd, type, id, rec);
+		trace_cxl_general_media(cxlmd, type, rec);
 	} else if (uuid_equal(id, &CXL_EVENT_DRAM_UUID)) {
 		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
 
-		trace_cxl_dram(cxlmd, type, id, rec);
+		trace_cxl_dram(cxlmd, type, rec);
 	} else if (uuid_equal(id, &CXL_EVENT_MEM_MODULE_UUID)) {
 		struct cxl_event_mem_module *rec =
 				(struct cxl_event_mem_module *)record;
 
-		trace_cxl_memory_module(cxlmd, type, id, rec);
+		trace_cxl_memory_module(cxlmd, type, rec);
 	} else {
 		/* For unknown record types print just the header */
 		trace_cxl_generic_event(cxlmd, type, id, record);
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 3da16026b8dbf..312cfa9e00045 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -181,6 +181,7 @@ TRACE_EVENT(cxl_overflow,
  *	1) Add CXL_EVT_TP_entry to TP_STRUCT__entry
  *	2) Use CXL_EVT_TP_fast_assign within TP_fast_assign;
  *	   pass the dev, log, and CXL event header
+ *	   NOTE: The uuid must be assigned by the specific trace event
  *	3) Use CXL_EVT_TP_printk() instead of TP_printk()
  *
  * See the generic_event tracepoint as an example.
@@ -198,12 +199,11 @@ TRACE_EVENT(cxl_overflow,
 	__field(u8, hdr_length)					\
 	__field(u8, hdr_maint_op_class)
 
-#define CXL_EVT_TP_fast_assign(cxlmd, l, uuid, hdr)				\
+#define CXL_EVT_TP_fast_assign(cxlmd, l, hdr)					\
 	__assign_str(memdev, dev_name(&(cxlmd)->dev));				\
 	__assign_str(host, dev_name((cxlmd)->dev.parent));			\
 	__entry->log = (l);							\
 	__entry->serial = (cxlmd)->cxlds->serial;				\
-	memcpy(&__entry->hdr_uuid, (uuid), sizeof(uuid_t));			\
 	__entry->hdr_length = (hdr).length;					\
 	__entry->hdr_flags = get_unaligned_le24((hdr).flags);			\
 	__entry->hdr_handle = le16_to_cpu((hdr).handle);			\
@@ -235,7 +235,8 @@ TRACE_EVENT(cxl_generic_event,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, uuid, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		memcpy(&__entry->hdr_uuid, uuid, sizeof(uuid_t));
 		memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
 	),
 
@@ -315,9 +316,9 @@ TRACE_EVENT(cxl_generic_event,
 TRACE_EVENT(cxl_general_media,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 const uuid_t *uuid, struct cxl_event_gen_media *rec),
+		 struct cxl_event_gen_media *rec),
 
-	TP_ARGS(cxlmd, log, uuid, rec),
+	TP_ARGS(cxlmd, log, rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -336,7 +337,8 @@ TRACE_EVENT(cxl_general_media,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, uuid, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		memcpy(&__entry->hdr_uuid, &CXL_EVENT_GEN_MEDIA_UUID, sizeof(uuid_t));
 
 		/* General Media */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -398,9 +400,9 @@ TRACE_EVENT(cxl_general_media,
 TRACE_EVENT(cxl_dram,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 const uuid_t *uuid, struct cxl_event_dram *rec),
+		 struct cxl_event_dram *rec),
 
-	TP_ARGS(cxlmd, log, uuid, rec),
+	TP_ARGS(cxlmd, log, rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -422,7 +424,8 @@ TRACE_EVENT(cxl_dram,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, uuid, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		memcpy(&__entry->hdr_uuid, &CXL_EVENT_DRAM_UUID, sizeof(uuid_t));
 
 		/* DRAM */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -547,9 +550,9 @@ TRACE_EVENT(cxl_dram,
 TRACE_EVENT(cxl_memory_module,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 const uuid_t *uuid, struct cxl_event_mem_module *rec),
+		 struct cxl_event_mem_module *rec),
 
-	TP_ARGS(cxlmd, log, uuid, rec),
+	TP_ARGS(cxlmd, log, rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -569,7 +572,8 @@ TRACE_EVENT(cxl_memory_module,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, uuid, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		memcpy(&__entry->hdr_uuid, &CXL_EVENT_MEM_MODULE_UUID, sizeof(uuid_t));
 
 		/* Memory Module Event */
 		__entry->event_type = rec->event_type;
-- 
GitLab


From 6eade110754c085cee9e46f4d87d2c3ea4e59e8c Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:32 -0800
Subject: [PATCH 2428/4076] cxl/events: Separate UUID from event structures

The UEFI CXL CPER structure does not include the UUID.  Now that the
UUID is passed separately to the trace event there is no need to have
the UUID in those structures.

Move UUID from the event record header to the raw structures.  Adjust
cxl-test to Create dummy structures for creating test records.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-5-1bb8a4ca2c7a@intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c      |   2 +-
 include/linux/cxl-event.h    |   6 +-
 tools/testing/cxl/test/mem.c | 129 ++++++++++++++++++++---------------
 3 files changed, 81 insertions(+), 56 deletions(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 5f3681de10dec..4c51618968264 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -840,7 +840,7 @@ static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 				   enum cxl_event_log_type type,
 				   struct cxl_event_record_raw *record)
 {
-	uuid_t *id = &record->hdr.id;
+	uuid_t *id = &record->id;
 
 	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID)) {
 		struct cxl_event_gen_media *rec =
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 0fc068123f8ed..3d9b5954d0c11 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -8,7 +8,6 @@
  * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
  */
 struct cxl_event_record_hdr {
-	uuid_t id;
 	u8 length;
 	u8 flags[3];
 	__le16 handle;
@@ -18,8 +17,13 @@ struct cxl_event_record_hdr {
 	u8 reserved[15];
 } __packed;
 
+/*
+ * Common Event Record Format
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
 #define CXL_EVENT_RECORD_DATA_LENGTH 0x50
 struct cxl_event_record_raw {
+	uuid_t id;
 	struct cxl_event_record_hdr hdr;
 	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
 } __packed;
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 5a95b04b329ae..9cc2b8ce1efd0 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -337,9 +337,9 @@ static void cxl_mock_event_trigger(struct device *dev)
 }
 
 struct cxl_event_record_raw maint_needed = {
+	.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
+			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
 	.hdr = {
-		.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
-				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
 		.length = sizeof(struct cxl_event_record_raw),
 		.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
 		/* .handle = Set dynamically */
@@ -349,9 +349,9 @@ struct cxl_event_record_raw maint_needed = {
 };
 
 struct cxl_event_record_raw hardware_replace = {
+	.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
+			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
 	.hdr = {
-		.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
-				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
 		.length = sizeof(struct cxl_event_record_raw),
 		.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
 		/* .handle = Set dynamically */
@@ -360,61 +360,82 @@ struct cxl_event_record_raw hardware_replace = {
 	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 };
 
-struct cxl_event_gen_media gen_media = {
-	.hdr = {
-		.id = CXL_EVENT_GEN_MEDIA_UUID,
-		.length = sizeof(struct cxl_event_gen_media),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_gen_media {
+	uuid_t id;
+	struct cxl_event_gen_media rec;
+} __packed;
+
+struct cxl_test_gen_media gen_media = {
+	.id = CXL_EVENT_GEN_MEDIA_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_gen_media),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.phys_addr = cpu_to_le64(0x2000),
+		.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
+		.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
+		.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
+		/* .validity_flags = <set below> */
+		.channel = 1,
+		.rank = 30
 	},
-	.phys_addr = cpu_to_le64(0x2000),
-	.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
-	.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
-	.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
-	/* .validity_flags = <set below> */
-	.channel = 1,
-	.rank = 30
 };
 
-struct cxl_event_dram dram = {
-	.hdr = {
-		.id = CXL_EVENT_DRAM_UUID,
-		.length = sizeof(struct cxl_event_dram),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_dram {
+	uuid_t id;
+	struct cxl_event_dram rec;
+} __packed;
+
+struct cxl_test_dram dram = {
+	.id = CXL_EVENT_DRAM_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_dram),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.phys_addr = cpu_to_le64(0x8000),
+		.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
+		.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
+		.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
+		/* .validity_flags = <set below> */
+		.channel = 1,
+		.bank_group = 5,
+		.bank = 2,
+		.column = {0xDE, 0xAD},
 	},
-	.phys_addr = cpu_to_le64(0x8000),
-	.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
-	.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
-	.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
-	/* .validity_flags = <set below> */
-	.channel = 1,
-	.bank_group = 5,
-	.bank = 2,
-	.column = {0xDE, 0xAD},
 };
 
-struct cxl_event_mem_module mem_module = {
-	.hdr = {
-		.id = CXL_EVENT_MEM_MODULE_UUID,
-		.length = sizeof(struct cxl_event_mem_module),
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_mem_module {
+	uuid_t id;
+	struct cxl_event_mem_module rec;
+} __packed;
+
+struct cxl_test_mem_module mem_module = {
+	.id = CXL_EVENT_MEM_MODULE_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_mem_module),
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.event_type = CXL_MMER_TEMP_CHANGE,
+		.info = {
+			.health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED,
+			.media_status = CXL_DHI_MS_ALL_DATA_LOST,
+			.add_status = (CXL_DHI_AS_CRITICAL << 2) |
+				      (CXL_DHI_AS_WARNING << 4) |
+				      (CXL_DHI_AS_WARNING << 5),
+			.device_temp = { 0xDE, 0xAD},
+			.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
+			.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+			.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+		}
 	},
-	.event_type = CXL_MMER_TEMP_CHANGE,
-	.info = {
-		.health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED,
-		.media_status = CXL_DHI_MS_ALL_DATA_LOST,
-		.add_status = (CXL_DHI_AS_CRITICAL << 2) |
-			      (CXL_DHI_AS_WARNING << 4) |
-			      (CXL_DHI_AS_WARNING << 5),
-		.device_temp = { 0xDE, 0xAD},
-		.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
-		.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
-		.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
-	}
 };
 
 static int mock_set_timestamp(struct cxl_dev_state *cxlds,
@@ -436,11 +457,11 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds,
 static void cxl_mock_add_event_logs(struct mock_event_store *mes)
 {
 	put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK,
-			   &gen_media.validity_flags);
+			   &gen_media.rec.validity_flags);
 
 	put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP |
 			   CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN,
-			   &dram.validity_flags);
+			   &dram.rec.validity_flags);
 
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed);
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
-- 
GitLab


From f9c683386f5bc0364615138ce2b14be50848dbcf Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:33 -0800
Subject: [PATCH 2429/4076] cxl/events: Create a CXL event union

The CXL CPER and event log records share everything but a UUID/GUID in
their structures.

Define a cxl_event union without the UUID/GUID to be shared between the
CPER and event log record formats.  Adjust the code to use this union.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-6-1bb8a4ca2c7a@intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c      | 32 +++++++++++++-------------------
 drivers/cxl/core/trace.h     |  8 ++++----
 include/linux/cxl-event.h    | 23 +++++++++++++++++------
 tools/testing/cxl/test/mem.c | 31 ++++++++++++++++++-------------
 4 files changed, 52 insertions(+), 42 deletions(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 4c51618968264..06957696247bd 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -840,26 +840,17 @@ static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 				   enum cxl_event_log_type type,
 				   struct cxl_event_record_raw *record)
 {
+	union cxl_event *evt = &record->event;
 	uuid_t *id = &record->id;
 
-	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID)) {
-		struct cxl_event_gen_media *rec =
-				(struct cxl_event_gen_media *)record;
-
-		trace_cxl_general_media(cxlmd, type, rec);
-	} else if (uuid_equal(id, &CXL_EVENT_DRAM_UUID)) {
-		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
-
-		trace_cxl_dram(cxlmd, type, rec);
-	} else if (uuid_equal(id, &CXL_EVENT_MEM_MODULE_UUID)) {
-		struct cxl_event_mem_module *rec =
-				(struct cxl_event_mem_module *)record;
-
-		trace_cxl_memory_module(cxlmd, type, rec);
-	} else {
-		/* For unknown record types print just the header */
-		trace_cxl_generic_event(cxlmd, type, id, record);
-	}
+	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID))
+		trace_cxl_general_media(cxlmd, type, &evt->gen_media);
+	else if (uuid_equal(id, &CXL_EVENT_DRAM_UUID))
+		trace_cxl_dram(cxlmd, type, &evt->dram);
+	else if (uuid_equal(id, &CXL_EVENT_MEM_MODULE_UUID))
+		trace_cxl_memory_module(cxlmd, type, &evt->mem_module);
+	else
+		trace_cxl_generic_event(cxlmd, type, id, &evt->generic);
 }
 
 static int cxl_clear_event_record(struct cxl_memdev_state *mds,
@@ -902,7 +893,10 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds,
 	 */
 	i = 0;
 	for (cnt = 0; cnt < total; cnt++) {
-		payload->handles[i++] = get_pl->records[cnt].hdr.handle;
+		struct cxl_event_record_raw *raw = &get_pl->records[cnt];
+		struct cxl_event_generic *gen = &raw->event.generic;
+
+		payload->handles[i++] = gen->hdr.handle;
 		dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log,
 			le16_to_cpu(payload->handles[i]));
 
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 312cfa9e00045..89445435303aa 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -225,9 +225,9 @@ TRACE_EVENT(cxl_overflow,
 TRACE_EVENT(cxl_generic_event,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 const uuid_t *uuid, struct cxl_event_record_raw *rec),
+		 const uuid_t *uuid, struct cxl_event_generic *gen_rec),
 
-	TP_ARGS(cxlmd, log, uuid, rec),
+	TP_ARGS(cxlmd, log, uuid, gen_rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -235,9 +235,9 @@ TRACE_EVENT(cxl_generic_event,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, gen_rec->hdr);
 		memcpy(&__entry->hdr_uuid, uuid, sizeof(uuid_t));
-		memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
+		memcpy(__entry->data, gen_rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
 	),
 
 	CXL_EVT_TP_printk("%s",
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 3d9b5954d0c11..4d6c05f535f80 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -17,13 +17,8 @@ struct cxl_event_record_hdr {
 	u8 reserved[15];
 } __packed;
 
-/*
- * Common Event Record Format
- * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
- */
 #define CXL_EVENT_RECORD_DATA_LENGTH 0x50
-struct cxl_event_record_raw {
-	uuid_t id;
+struct cxl_event_generic {
 	struct cxl_event_record_hdr hdr;
 	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
 } __packed;
@@ -96,4 +91,20 @@ struct cxl_event_mem_module {
 	u8 reserved[0x3d];
 } __packed;
 
+union cxl_event {
+	struct cxl_event_generic generic;
+	struct cxl_event_gen_media gen_media;
+	struct cxl_event_dram dram;
+	struct cxl_event_mem_module mem_module;
+} __packed;
+
+/*
+ * Common Event Record Format; in event logs
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_raw {
+	uuid_t id;
+	union cxl_event event;
+} __packed;
+
 #endif /* _LINUX_CXL_EVENT_H */
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 9cc2b8ce1efd0..35ee41e435ab3 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -251,7 +251,8 @@ static int mock_get_event(struct device *dev, struct cxl_mbox_cmd *cmd)
 	for (i = 0; i < CXL_TEST_EVENT_CNT && !event_log_empty(log); i++) {
 		memcpy(&pl->records[i], event_get_current(log),
 		       sizeof(pl->records[i]));
-		pl->records[i].hdr.handle = event_get_cur_event_handle(log);
+		pl->records[i].event.generic.hdr.handle =
+				event_get_cur_event_handle(log);
 		log->cur_idx++;
 	}
 
@@ -339,25 +340,29 @@ static void cxl_mock_event_trigger(struct device *dev)
 struct cxl_event_record_raw maint_needed = {
 	.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
 			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
-	.hdr = {
-		.length = sizeof(struct cxl_event_record_raw),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0xa5b6),
+	.event.generic = {
+		.hdr = {
+			.length = sizeof(struct cxl_event_record_raw),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0xa5b6),
+		},
+		.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 	},
-	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 };
 
 struct cxl_event_record_raw hardware_replace = {
 	.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
 			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
-	.hdr = {
-		.length = sizeof(struct cxl_event_record_raw),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0xb6a5),
+	.event.generic = {
+		.hdr = {
+			.length = sizeof(struct cxl_event_record_raw),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0xb6a5),
+		},
+		.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 	},
-	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 };
 
 struct cxl_test_gen_media {
-- 
GitLab


From 671a794c33c6e048ca5cedd5ad6af44d52d5d7e5 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:34 -0800
Subject: [PATCH 2430/4076] acpi/ghes: Process CXL Component Events

BIOS can configure memory devices as firmware first.  This will send CXL
events to the firmware instead of the OS.  The firmware can then send
these events to the OS via UEFI.

UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER)
format for CXL Component Events.  The format is mostly the same as the
CXL Common Event Record Format.  The difference is the use of a GUID in
the Section Type rather than a UUID as part of the event itself.

Add GHES support to detect CXL CPER records and call a registered
callback with the event.

A notifier chain was considered for the callback but the complexity did
not justify the use case as only the CXL subsystem requires this event.
Enforce that only one callback can be registered at any time.

Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-7-1bb8a4ca2c7a@intel.com
[djbw: fixup checkpatch errors]
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/apei/ghes.c  | 89 +++++++++++++++++++++++++++++++++++++++
 include/linux/cxl-event.h | 50 ++++++++++++++++++++++
 2 files changed, 139 insertions(+)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 63ad0541db381..56a5d2ef9e0a0 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
+#include <linux/cxl-event.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -657,6 +658,78 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/*
+ * Only a single callback can be registered for CXL CPER events.
+ */
+static DECLARE_RWSEM(cxl_cper_rw_sem);
+static cxl_cper_callback cper_callback;
+
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
+	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID						\
+	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID					\
+	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
+
+static void cxl_cper_post_event(enum cxl_event_type event_type,
+				struct cxl_cper_event_rec *rec)
+{
+	if (rec->hdr.length <= sizeof(rec->hdr) ||
+	    rec->hdr.length > sizeof(*rec)) {
+		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
+		       rec->hdr.length);
+		return;
+	}
+
+	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
+		pr_err(FW_WARN "CXL CPER invalid event\n");
+		return;
+	}
+
+	guard(rwsem_read)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		cper_callback(event_type, rec);
+}
+
+int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		return -EINVAL;
+	cper_callback = callback;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_callback, CXL);
+
+int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (callback != cper_callback)
+		return -EINVAL;
+	cper_callback = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_callback, CXL);
+
 static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -690,6 +763,22 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
+		} else if (guid_equal(sec_type,
+				      &CPER_SEC_CXL_MEM_MODULE_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 4d6c05f535f80..95841750a383b 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -107,4 +107,54 @@ struct cxl_event_record_raw {
 	union cxl_event event;
 } __packed;
 
+enum cxl_event_type {
+	CXL_CPER_EVENT_GEN_MEDIA,
+	CXL_CPER_EVENT_DRAM,
+	CXL_CPER_EVENT_MEM_MODULE,
+};
+
+#define CPER_CXL_DEVICE_ID_VALID		BIT(0)
+#define CPER_CXL_DEVICE_SN_VALID		BIT(1)
+#define CPER_CXL_COMP_EVENT_LOG_VALID		BIT(2)
+struct cxl_cper_event_rec {
+	struct {
+		u32 length;
+		u64 validation_bits;
+		struct cper_cxl_event_devid {
+			u16 vendor_id;
+			u16 device_id;
+			u8 func_num;
+			u8 device_num;
+			u8 bus_num;
+			u16 segment_num;
+			u16 slot_num; /* bits 2:0 reserved */
+			u8 reserved;
+		} __packed device_id;
+		struct cper_cxl_event_sn {
+			u32 lower_dw;
+			u32 upper_dw;
+		} __packed dev_serial_num;
+	} __packed hdr;
+
+	union cxl_event event;
+} __packed;
+
+typedef void (*cxl_cper_callback)(enum cxl_event_type type,
+				  struct cxl_cper_event_rec *rec);
+
+#ifdef CONFIG_ACPI_APEI_GHES
+int cxl_cper_register_callback(cxl_cper_callback callback);
+int cxl_cper_unregister_callback(cxl_cper_callback callback);
+#else
+static inline int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	return 0;
+}
+
+static inline int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	return 0;
+}
+#endif
+
 #endif /* _LINUX_CXL_EVENT_H */
-- 
GitLab


From ced085ef369af7a2b6da962ec2fbd01339f60693 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:35 -0800
Subject: [PATCH 2431/4076] PCI: Introduce cleanup helpers for device reference
 counts and locks

The "goto error" pattern is notorious for introducing subtle resource
leaks. Use the new cleanup.h helpers for PCI device reference counts and
locks.

Similar to the new put_device() and device_lock() cleanup helpers,
__free(put_device) and guard(device), define the same for PCI devices,
__free(pci_dev_put) and guard(pci_dev).  These helpers eliminate the
need for "goto free;" and "goto unlock;" patterns. For example, A
'struct pci_dev *' instance declared as:

    struct pci_dev *pdev __free(pci_dev_put) = NULL;

...will automatically call pci_dev_put() if @pdev is non-NULL when @pdev
goes out of scope (automatic variable scope). If a function wants to
invoke pci_dev_put() on error, but return @pdev on success, it can do:

    return no_free_ptr(pdev);

...or:

    return_ptr(pdev);

For potential cleanup opportunity there are 587 open-coded calls to
pci_dev_put() in the kernel with 65 instances within 10 lines of a goto
statement with the CXL driver threatening to add another one.

The guard() helper holds the associated lock for the remainder of the
current scope in which it was invoked. So, for example:

    func(...)
    {
        if (...) {
            ...
            guard(pci_dev); /* pci_dev_lock() invoked here */
            ...
        } /* <- implied pci_dev_unlock() triggered here */
    }

There are 15 invocations of pci_dev_unlock() in the kernel with 5
instances within 10 lines of a goto statement. Again, the CXL driver is
threatening to add another.

Introduce these helpers to preclude the addition of new more error prone
goto put; / goto unlock; sequences. For now, these helpers are used in
drivers/cxl/pci.c to allow ACPI error reports to be fed back into the
CXL driver associated with the PCI device identified in the report.

Cc: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-8-1bb8a4ca2c7a@intel.com
[djbw: rewrite changelog]
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 include/linux/pci.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/pci.h b/include/linux/pci.h
index dea043bc1e383..0d23d2e0eb1a4 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1170,6 +1170,7 @@ int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge);
 u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp);
 struct pci_dev *pci_dev_get(struct pci_dev *dev);
 void pci_dev_put(struct pci_dev *dev);
+DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T))
 void pci_remove_bus(struct pci_bus *b);
 void pci_stop_and_remove_bus_device(struct pci_dev *dev);
 void pci_stop_and_remove_bus_device_locked(struct pci_dev *dev);
@@ -1874,6 +1875,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev);
 void pci_dev_lock(struct pci_dev *dev);
 int pci_dev_trylock(struct pci_dev *dev);
 void pci_dev_unlock(struct pci_dev *dev);
+DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T))
 
 /*
  * PCI domain support.  Sometimes called PCI segment (eg by ACPI),
-- 
GitLab


From dc97f6344f205b0dfa144e1b3e16d6dc05383d57 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:36 -0800
Subject: [PATCH 2432/4076] cxl/pci: Register for and process CPER events

If the firmware has configured CXL event support to be firmware first
the OS can process those events through CPER records.  The CXL layer has
unique DPA to HPA knowledge and standard event trace parsing in place.

CPER records contain Bus, Device, Function information which can be used
to identify the PCI device which is sending the event.

Change the PCI driver registration to include registration of a CXL
CPER callback to process events through the trace subsystem.

Use new scoped based management to simplify the handling of the PCI
device object.

Tested-by: Smita-Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Reviewed-by: Smita-Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-9-1bb8a4ca2c7a@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
[djbw: use new pci_dev guard, flip init order]
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c   | 40 +++++++++++++++++++--------
 drivers/cxl/cxlmem.h      |  4 +++
 drivers/cxl/pci.c         | 58 ++++++++++++++++++++++++++++++++++++++-
 include/linux/cxl-event.h |  1 +
 4 files changed, 90 insertions(+), 13 deletions(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 06957696247bd..23021920aacee 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -836,21 +836,37 @@ out:
 }
 EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL);
 
-static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
-				   enum cxl_event_log_type type,
-				   struct cxl_event_record_raw *record)
+void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt)
 {
-	union cxl_event *evt = &record->event;
-	uuid_t *id = &record->id;
-
-	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID))
+	if (event_type == CXL_CPER_EVENT_GEN_MEDIA)
 		trace_cxl_general_media(cxlmd, type, &evt->gen_media);
-	else if (uuid_equal(id, &CXL_EVENT_DRAM_UUID))
+	else if (event_type == CXL_CPER_EVENT_DRAM)
 		trace_cxl_dram(cxlmd, type, &evt->dram);
-	else if (uuid_equal(id, &CXL_EVENT_MEM_MODULE_UUID))
+	else if (event_type == CXL_CPER_EVENT_MEM_MODULE)
 		trace_cxl_memory_module(cxlmd, type, &evt->mem_module);
 	else
-		trace_cxl_generic_event(cxlmd, type, id, &evt->generic);
+		trace_cxl_generic_event(cxlmd, type, uuid, &evt->generic);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, CXL);
+
+static void __cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+				     enum cxl_event_log_type type,
+				     struct cxl_event_record_raw *record)
+{
+	enum cxl_event_type ev_type = CXL_CPER_EVENT_GENERIC;
+	const uuid_t *uuid = &record->id;
+
+	if (uuid_equal(uuid, &CXL_EVENT_GEN_MEDIA_UUID))
+		ev_type = CXL_CPER_EVENT_GEN_MEDIA;
+	else if (uuid_equal(uuid, &CXL_EVENT_DRAM_UUID))
+		ev_type = CXL_CPER_EVENT_DRAM;
+	else if (uuid_equal(uuid, &CXL_EVENT_MEM_MODULE_UUID))
+		ev_type = CXL_CPER_EVENT_MEM_MODULE;
+
+	cxl_event_trace_record(cxlmd, type, ev_type, uuid, &record->event);
 }
 
 static int cxl_clear_event_record(struct cxl_memdev_state *mds,
@@ -961,8 +977,8 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds,
 			break;
 
 		for (i = 0; i < nr_rec; i++)
-			cxl_event_trace_record(cxlmd, type,
-					       &payload->records[i]);
+			__cxl_event_trace_record(cxlmd, type,
+						 &payload->records[i]);
 
 		if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW)
 			trace_cxl_overflow(cxlmd, type, payload);
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 27575513ec689..3c201324a3b3e 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -802,6 +802,10 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 				  unsigned long *cmds);
 void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status);
+void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt);
 int cxl_set_timestamp(struct cxl_memdev_state *mds);
 int cxl_poison_state_init(struct cxl_memdev_state *mds);
 int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 0155fb66b580d..4fd1f207c84ee 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2020 Intel Corporation. All rights reserved. */
+#include <asm-generic/unaligned.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/moduleparam.h>
 #include <linux/module.h>
@@ -969,6 +970,61 @@ static struct pci_driver cxl_pci_driver = {
 	},
 };
 
+#define CXL_EVENT_HDR_FLAGS_REC_SEVERITY GENMASK(1, 0)
+static void cxl_cper_event_call(enum cxl_event_type ev_type,
+				struct cxl_cper_event_rec *rec)
+{
+	struct cper_cxl_event_devid *device_id = &rec->hdr.device_id;
+	struct pci_dev *pdev __free(pci_dev_put) = NULL;
+	enum cxl_event_log_type log_type;
+	struct cxl_dev_state *cxlds;
+	unsigned int devfn;
+	u32 hdr_flags;
+
+	devfn = PCI_DEVFN(device_id->device_num, device_id->func_num);
+	pdev = pci_get_domain_bus_and_slot(device_id->segment_num,
+					   device_id->bus_num, devfn);
+	if (!pdev)
+		return;
+
+	guard(pci_dev)(pdev);
+	if (pdev->driver != &cxl_pci_driver)
+		return;
+
+	cxlds = pci_get_drvdata(pdev);
+	if (!cxlds)
+		return;
+
+	/* Fabricate a log type */
+	hdr_flags = get_unaligned_le24(rec->event.generic.hdr.flags);
+	log_type = FIELD_GET(CXL_EVENT_HDR_FLAGS_REC_SEVERITY, hdr_flags);
+
+	cxl_event_trace_record(cxlds->cxlmd, log_type, ev_type,
+			       &uuid_null, &rec->event);
+}
+
+static int __init cxl_pci_driver_init(void)
+{
+	int rc;
+
+	rc = cxl_cper_register_callback(cxl_cper_event_call);
+	if (rc)
+		return rc;
+
+	rc = pci_register_driver(&cxl_pci_driver);
+	if (rc)
+		cxl_cper_unregister_callback(cxl_cper_event_call);
+
+	return rc;
+}
+
+static void __exit cxl_pci_driver_exit(void)
+{
+	pci_unregister_driver(&cxl_pci_driver);
+	cxl_cper_unregister_callback(cxl_cper_event_call);
+}
+
+module_init(cxl_pci_driver_init);
+module_exit(cxl_pci_driver_exit);
 MODULE_LICENSE("GPL v2");
-module_pci_driver(cxl_pci_driver);
 MODULE_IMPORT_NS(CXL);
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 95841750a383b..91125eca4c8ab 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -108,6 +108,7 @@ struct cxl_event_record_raw {
 } __packed;
 
 enum cxl_event_type {
+	CXL_CPER_EVENT_GENERIC,
 	CXL_CPER_EVENT_GEN_MEDIA,
 	CXL_CPER_EVENT_DRAM,
 	CXL_CPER_EVENT_MEM_MODULE,
-- 
GitLab


From 66f1e68093979816a23412a3fad066f5bcbc0360 Mon Sep 17 00:00:00 2001
From: Frederik Haxel <haxel@fzi.de>
Date: Tue, 12 Dec 2023 14:01:12 +0100
Subject: [PATCH 2433/4076] riscv: Make XIP bootable again

Currently, the XIP kernel seems to fail to boot due to missing
XIP_FIXUP and a wrong page_offset value. A superfluous XIP_FIXUP
has also been removed.

Signed-off-by: Frederik Haxel <haxel@fzi.de>
Link: https://lore.kernel.org/r/20231212130116.848530-2-haxel@fzi.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/head.S | 1 +
 arch/riscv/mm/init.c     | 8 ++++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index b77397432403d..a2e2f0dd3899a 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -89,6 +89,7 @@ relocate_enable_mmu:
 	/* Compute satp for kernel page tables, but don't load it yet */
 	srl a2, a0, PAGE_SHIFT
 	la a1, satp_mode
+	XIP_FIXUP_OFFSET a1
 	REG_L a1, 0(a1)
 	or a2, a2, a1
 
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 2e011cbddf3af..a65937336cdc8 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -174,6 +174,9 @@ void __init mem_init(void)
 
 /* Limit the memory size via mem. */
 static phys_addr_t memory_limit;
+#ifdef CONFIG_XIP_KERNEL
+#define memory_limit	(*(phys_addr_t *)XIP_FIXUP(&memory_limit))
+#endif /* CONFIG_XIP_KERNEL */
 
 static int __init early_mem(char *p)
 {
@@ -952,7 +955,7 @@ static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va,
 	 * setup_vm_final installs the linear mapping. For 32-bit kernel, as the
 	 * kernel is mapped in the linear mapping, that makes no difference.
 	 */
-	dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa));
+	dtb_early_va = kernel_mapping_pa_to_va(dtb_pa);
 #endif
 
 	dtb_early_pa = dtb_pa;
@@ -1055,9 +1058,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 #endif
 
 	kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset;
-	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 
 #ifdef CONFIG_XIP_KERNEL
+	kernel_map.page_offset = PAGE_OFFSET_L3;
 	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
 	kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
 
@@ -1067,6 +1070,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 
 	kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
 #else
+	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 	kernel_map.phys_addr = (uintptr_t)(&_start);
 	kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
 #endif
-- 
GitLab


From 5daa3726410288075ba73c336bb2e80d6b06aa4d Mon Sep 17 00:00:00 2001
From: Frederik Haxel <haxel@fzi.de>
Date: Tue, 12 Dec 2023 14:01:13 +0100
Subject: [PATCH 2434/4076] riscv: Fixed wrong register in
 XIP_FIXUP_FLASH_OFFSET macro

During the refactoring, a bug was introduced in the rarly used
XIP_FIXUP_FLASH_OFFSET macro.

Fixes: bee7fbc38579 ("RISC-V CPU Idle Support")
Fixes: e7681beba992 ("RISC-V: Split out the XIP fixups into their own file")

Signed-off-by: Frederik Haxel <haxel@fzi.de>
Link: https://lore.kernel.org/r/20231212130116.848530-3-haxel@fzi.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/xip_fixup.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h
index d4ffc3c37649f..b65bf6306f69c 100644
--- a/arch/riscv/include/asm/xip_fixup.h
+++ b/arch/riscv/include/asm/xip_fixup.h
@@ -13,7 +13,7 @@
         add \reg, \reg, t0
 .endm
 .macro XIP_FIXUP_FLASH_OFFSET reg
-	la t1, __data_loc
+	la t0, __data_loc
 	REG_L t1, _xip_phys_offset
 	sub \reg, \reg, t1
 	add \reg, \reg, t0
-- 
GitLab


From 6c4a2f6329f0925161a80d2fd90aa8438c1ca82f Mon Sep 17 00:00:00 2001
From: Frederik Haxel <haxel@fzi.de>
Date: Tue, 12 Dec 2023 14:01:14 +0100
Subject: [PATCH 2435/4076] riscv: Allow disabling of BUILTIN_DTB for XIP

This enables, among other things, testing with the QEMU virt machine.

To build an XIP kernel for the QEMU virt machine, configure the
the kernel as desired and apply the following configuration
```
CONFIG_NONPORTABLE=y
CONFIG_XIP_KERNEL=y
CONFIG_XIP_PHYS_ADDR=0x20000000
CONFIG_PHYS_RAM_BASE=0x80200000
CONFIG_BUILTIN_DTB=n
```

Since the QEMU virt flash memory expects a 32 MB file, the built image
must be padded. For example, with
`truncate -s 32M arch/riscv/boot/xipImage`

The kernel can be started using the following command in QEMU (v8+)
```
qemu-system-riscv64 -M virt,pflash0=pflash0 \
 -blockdev node-name=pflash0,driver=file,read-only=on,\
filename=arch/riscv/boot/xipImage <optional parameters>
```

Signed-off-by: Frederik Haxel <haxel@fzi.de>
Link: https://lore.kernel.org/r/20231212130116.848530-4-haxel@fzi.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig       | 6 +++---
 arch/riscv/kernel/head.S | 4 +++-
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a6..72bc31b6eeb95 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -904,13 +904,13 @@ config RISCV_ISA_FALLBACK
 	  on the replacement properties, "riscv,isa-base" and
 	  "riscv,isa-extensions".
 
-endmenu # "Boot options"
-
 config BUILTIN_DTB
-	bool
+	bool "Built-in device tree"
 	depends on OF && NONPORTABLE
 	default y if XIP_KERNEL
 
+endmenu # "Boot options"
+
 config PORTABLE
 	bool
 	default !NONPORTABLE
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index a2e2f0dd3899a..a8939558702cb 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -266,10 +266,12 @@ SYM_CODE_START(_start_kernel)
 	la sp, _end + THREAD_SIZE
 	XIP_FIXUP_OFFSET sp
 	mv s0, a0
+	mv s1, a1
 	call __copy_data
 
-	/* Restore a0 copy */
+	/* Restore a0 & a1 copy */
 	mv a0, s0
+	mv a1, s1
 #endif
 
 #ifndef CONFIG_XIP_KERNEL
-- 
GitLab


From 25742aeb135c4a44e92fb347e037adaa145b9484 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 20 Dec 2023 08:10:28 -0500
Subject: [PATCH 2436/4076] ring-buffer: Remove stale comment from
 ring_buffer_size()

It's been 11 years since the ring_buffer_size() function was updated to
use the nr_pages from the buffer->buffers[cpu] structure instead of using
the buffer->nr_pages that no longer exists.

The comment in the code is more of what a change log should have and is
pretty much useless for development. It's saying how things worked back in
2012 that bares no purpose on today's code. Remove it.

Link: https://lore.kernel.org/linux-trace-kernel/84d3b41a72bd43dbb9d44921ef535c92@AcuMS.aculab.com/
Link: https://lore.kernel.org/linux-trace-kernel/20231220081028.7cd7e8e2@gandalf.local.home

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reported-by: David Laight <David.Laight@ACULAB.COM>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/ring_buffer.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 173d2595ce2d9..7887d61d5b569 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5122,12 +5122,6 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_advance);
  */
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 {
-	/*
-	 * Earlier, this method returned
-	 *	buffer->subbuf_size * buffer->nr_pages
-	 * Since the nr_pages field is now removed, we have converted this to
-	 * return the per cpu buffer value.
-	 */
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
-- 
GitLab


From b7b4e4d79fc72e2b565cb3da38897b0e4c891e79 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Tue, 21 Nov 2023 14:53:18 -0800
Subject: [PATCH 2437/4076] riscv: Remove obsolete rv32_defconfig file

This file is not used since commit 72f045d19f25 ("riscv: Fixup
difference with defconfig"), where it was replaced by the
32-bit.config fragment. Delete the old file to avoid any confusion.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231121225320.3430550-1-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/configs/rv32_defconfig | 139 ------------------------------
 1 file changed, 139 deletions(-)
 delete mode 100644 arch/riscv/configs/rv32_defconfig

diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
deleted file mode 100644
index 89b601e253a68..0000000000000
--- a/arch/riscv/configs/rv32_defconfig
+++ /dev/null
@@ -1,139 +0,0 @@
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ_IDLE=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BPF_SYSCALL=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_CFS_BANDWIDTH=y
-CONFIG_CGROUP_BPF=y
-CONFIG_NAMESPACES=y
-CONFIG_USER_NS=y
-CONFIG_CHECKPOINT_RESTORE=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_PROFILING=y
-CONFIG_SOC_SIFIVE=y
-CONFIG_SOC_VIRT=y
-CONFIG_NONPORTABLE=y
-CONFIG_ARCH_RV32I=y
-CONFIG_SMP=y
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PM=y
-CONFIG_CPU_IDLE=y
-CONFIG_VIRTUALIZATION=y
-CONFIG_KVM=m
-CONFIG_JUMP_LABEL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_NETLINK_DIAG=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
-CONFIG_PCI=y
-CONFIG_PCIEPORTBUS=y
-CONFIG_PCI_HOST_GENERIC=y
-CONFIG_PCIE_XILINX=y
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_SCSI_VIRTIO=y
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-CONFIG_SATA_AHCI_PLATFORM=y
-CONFIG_NETDEVICES=y
-CONFIG_VIRTIO_NET=y
-CONFIG_MACB=y
-CONFIG_E1000E=y
-CONFIG_R8169=y
-CONFIG_MICROSEMI_PHY=y
-CONFIG_INPUT_MOUSEDEV=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_VIRTIO=y
-CONFIG_SPI=y
-CONFIG_SPI_SIFIVE=y
-# CONFIG_PTP_1588_CLOCK is not set
-CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
-CONFIG_DRM_VIRTIO_GPU=y
-CONFIG_FB=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_USB=y
-CONFIG_USB_XHCI_HCD=y
-CONFIG_USB_XHCI_PLATFORM=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_OHCI_HCD_PLATFORM=y
-CONFIG_USB_STORAGE=y
-CONFIG_USB_UAS=y
-CONFIG_MMC=y
-CONFIG_MMC_SPI=y
-CONFIG_RTC_CLASS=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_INPUT=y
-CONFIG_VIRTIO_MMIO=y
-CONFIG_RPMSG_CHAR=y
-CONFIG_RPMSG_CTRL=y
-CONFIG_RPMSG_VIRTIO=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_AUTOFS_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_HUGETLBFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
-CONFIG_NFS_V4_1=y
-CONFIG_NFS_V4_2=y
-CONFIG_ROOT_NFS=y
-CONFIG_9P_FS=y
-CONFIG_CRYPTO_USER_API_HASH=y
-CONFIG_CRYPTO_DEV_VIRTIO=y
-CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_PAGEALLOC=y
-CONFIG_SCHED_STACK_END_CHECK=y
-CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_VM_PGFLAGS=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_DEBUG_PER_CPU_MAPS=y
-CONFIG_SOFTLOCKUP_DETECTOR=y
-CONFIG_WQ_WATCHDOG=y
-CONFIG_DEBUG_TIMEKEEPING=y
-CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_DEBUG_SPINLOCK=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_DEBUG_RWSEMS=y
-CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_STACKTRACE=y
-CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_PLIST=y
-CONFIG_DEBUG_SG=y
-# CONFIG_RCU_TRACE is not set
-CONFIG_RCU_EQS_DEBUG=y
-# CONFIG_FTRACE is not set
-# CONFIG_RUNTIME_TESTING_MENU is not set
-CONFIG_MEMTEST=y
-- 
GitLab


From cfbc4f81c9d0ea7d6b6726d55a93e859f51ef196 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Thu, 23 Nov 2023 22:22:23 +0800
Subject: [PATCH 2438/4076] riscv: Select ARCH_WANTS_NO_INSTR

As said in the help of ARCH_WANTS_NO_INSTR entry in arch/Kconfig:
"An architecture should select this if the noinstr macro is being used on
functions to denote that the toolchain should avoid instrumenting such
functions and is required for correctness."

Select ARCH_WANTS_NO_INSTR for correctness.

PS: The reason we didn't find any issue so far is that the
CC_HAS_NO_PROFILE_FN_ATTR is true.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://lore.kernel.org/r/20231123142223.1787-1-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a6..5e12582f66d46 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -59,6 +59,7 @@ config RISCV
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
+	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
-- 
GitLab


From ca0e433b41a6aa5115f752644eb39470f9a12a99 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Thu, 23 Nov 2023 14:16:17 +0000
Subject: [PATCH 2439/4076] riscv: fix __user annotation in traps_misaligned.c

The instruction reading code can read from either user or kernel addresses
and thus the use of __user on pointers to instructions depends on which
context. Fix a few sparse warnings by using __user for user-accesses and
remove it when not.

Fixes:

arch/riscv/kernel/traps_misaligned.c:361:21: warning: dereference of noderef expression
arch/riscv/kernel/traps_misaligned.c:373:21: warning: dereference of noderef expression
arch/riscv/kernel/traps_misaligned.c:381:21: warning: dereference of noderef expression
arch/riscv/kernel/traps_misaligned.c:322:24: warning: incorrect type in initializer (different address spaces)
arch/riscv/kernel/traps_misaligned.c:322:24:    expected unsigned char const [noderef] __user *__gu_ptr
arch/riscv/kernel/traps_misaligned.c:322:24:    got unsigned char const [usertype] *addr
arch/riscv/kernel/traps_misaligned.c:361:21: warning: dereference of noderef expression
arch/riscv/kernel/traps_misaligned.c:373:21: warning: dereference of noderef expression
arch/riscv/kernel/traps_misaligned.c:381:21: warning: dereference of noderef expression
arch/riscv/kernel/traps_misaligned.c:332:24: warning: incorrect type in initializer (different address spaces)
arch/riscv/kernel/traps_misaligned.c:332:24:    expected unsigned char [noderef] __user *__gu_ptr
arch/riscv/kernel/traps_misaligned.c:332:24:    got unsigned char [usertype] *addr

Fixes: 7c83232161f60 ("riscv: add support for misaligned trap handling in S-mode")
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Link: https://lore.kernel.org/r/20231123141617.259591-1-ben.dooks@codethink.co.uk
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/traps_misaligned.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 5eba37147caa9..446e3d4eeea90 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -319,7 +319,7 @@ static inline int get_insn(struct pt_regs *regs, ulong mepc, ulong *r_insn)
 static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
 {
 	if (user_mode(regs)) {
-		return __get_user(*r_val, addr);
+		return __get_user(*r_val, (u8 __user *)addr);
 	} else {
 		*r_val = *addr;
 		return 0;
@@ -329,7 +329,7 @@ static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
 static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
 {
 	if (user_mode(regs)) {
-		return __put_user(val, addr);
+		return __put_user(val, (u8 __user *)addr);
 	} else {
 		*addr = val;
 		return 0;
@@ -343,7 +343,7 @@ static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
 	if (user_mode(regs)) {				\
 		__ret = __get_user(insn, insn_addr);	\
 	} else {					\
-		insn = *insn_addr;			\
+		insn = *(__force u16 *)insn_addr;	\
 		__ret = 0;				\
 	}						\
 							\
-- 
GitLab


From 869436dae72acf1629b41437e9d08d31a7360fdb Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Thu, 23 Nov 2023 14:27:08 +0000
Subject: [PATCH 2440/4076] riscv; fix __user annotation in save_v_state()

The save_v_state() is technically sending a __user pointer through
__put_user() and thus is generating a sparse warning so force the
value to be "void *" to fix:

arch/riscv/kernel/signal.c:94:16: warning: incorrect type in initializer (different address spaces)
arch/riscv/kernel/signal.c:94:16: expected void *__val
arch/riscv/kernel/signal.c:94:16: got void [noderef] __user *[assigned] datap

Fixes: 8ee0b41898fa26f66e32 ("riscv: signal: Add sigcontext save/restore for vector")
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Link: https://lore.kernel.org/r/20231123142708.261733-1-ben.dooks@codethink.co.uk
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/signal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 88b6220b26087..33dfb50783010 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -91,7 +91,7 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	err = __copy_to_user(&state->v_state, &current->thread.vstate,
 			     offsetof(struct __riscv_v_ext_state, datap));
 	/* Copy the pointer datap itself. */
-	err |= __put_user(datap, &state->v_state.datap);
+	err |= __put_user((__force void *)datap, &state->v_state.datap);
 	/* Copy the whole vector content to user space datap. */
 	err |= __copy_to_user(datap, current->thread.vstate.datap, riscv_v_vsize);
 	/* Copy magic to the user space after saving  all vector conetext */
-- 
GitLab


From a7565f4d068b2e60f95c3223c3167c40b8fe83ae Mon Sep 17 00:00:00 2001
From: Song Shuai <songshuaishuai@tinylab.org>
Date: Mon, 11 Dec 2023 19:03:31 +0800
Subject: [PATCH 2441/4076] riscv: Remove SHADOW_OVERFLOW_STACK_SIZE macro

The commit be97d0db5f44 ("riscv: VMAP_STACK overflow
detection thread-safe") got rid of `shadow_stack`,
so SHADOW_OVERFLOW_STACK_SIZE should be removed too.

Fixes: be97d0db5f44 ("riscv: VMAP_STACK overflow detection thread-safe")
Signed-off-by: Song Shuai <songshuaishuai@tinylab.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20231211110331.359534-1-songshuaishuai@tinylab.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/thread_info.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 574779900bfb3..4856697c5f25a 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -28,7 +28,6 @@
 
 #define THREAD_SHIFT            (PAGE_SHIFT + THREAD_SIZE_ORDER)
 #define OVERFLOW_STACK_SIZE     SZ_4K
-#define SHADOW_OVERFLOW_STACK_SIZE (1024)
 
 #define IRQ_STACK_SIZE		THREAD_SIZE
 
-- 
GitLab


From 62694797f56bf72e4c598bc0e319c7b828c1b187 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 14 Dec 2023 19:19:22 +0000
Subject: [PATCH 2442/4076] use linux/export.h rather than asm-generic/export.h

asm-generic/export.h is a wrapper for linux/export.h, with explicit request
to use linux/export.h directly.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/r/20231214191922.GQ1674809@ZenIV
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/mcount-dyn.S | 2 +-
 arch/riscv/kernel/mcount.S     | 2 +-
 arch/riscv/lib/clear_page.S    | 2 +-
 arch/riscv/lib/tishift.S       | 2 +-
 arch/riscv/lib/uaccess.S       | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 58dd96a2a1534..79dc812232382 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -3,12 +3,12 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm-generic/export.h>
 #include <asm/ftrace.h>
 
 	.text
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index b4dd9ed6849e3..d7ec69ac6910c 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -4,12 +4,12 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/cfi_types.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm-generic/export.h>
 #include <asm/ftrace.h>
 
 	.text
diff --git a/arch/riscv/lib/clear_page.S b/arch/riscv/lib/clear_page.S
index b22de1231144c..20ff03f5b0f23 100644
--- a/arch/riscv/lib/clear_page.S
+++ b/arch/riscv/lib/clear_page.S
@@ -4,9 +4,9 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/alternative-macros.h>
-#include <asm-generic/export.h>
 #include <asm/hwcap.h>
 #include <asm/insn-def.h>
 #include <asm/page.h>
diff --git a/arch/riscv/lib/tishift.S b/arch/riscv/lib/tishift.S
index ef90075c4b0a9..c8294bf72c064 100644
--- a/arch/riscv/lib/tishift.S
+++ b/arch/riscv/lib/tishift.S
@@ -4,7 +4,7 @@
  */
 
 #include <linux/linkage.h>
-#include <asm-generic/export.h>
+#include <linux/export.h>
 
 SYM_FUNC_START(__lshrti3)
 	beqz	a2, .L1
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 3ab438f30d132..a9d356d6c03cd 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -1,5 +1,5 @@
 #include <linux/linkage.h>
-#include <asm-generic/export.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/asm-extable.h>
 #include <asm/csr.h>
-- 
GitLab


From 1ec9f381e84877085ed4ce891e89172f8494ddb8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Wed, 20 Dec 2023 16:57:17 +0100
Subject: [PATCH 2443/4076] riscv: add ISA extension parsing for Ztso
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support to parse the Ztso string in the riscv,isa string. The
bindings already supports it but not the ISA parsing code.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231220155723.684081-2-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 1 +
 arch/riscv/kernel/cpufeature.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 2438d4685da67..3b31efe2f716d 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -84,6 +84,7 @@
 #define RISCV_ISA_EXT_ZVFH		69
 #define RISCV_ISA_EXT_ZVFHMIN		70
 #define RISCV_ISA_EXT_ZFA		71
+#define RISCV_ISA_EXT_ZTSO		72
 
 #define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index dc0ab3e97cd28..3eb48a0eecb3e 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -279,6 +279,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zkt, RISCV_ISA_EXT_ZKT),
 	__RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED),
 	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
+	__RISCV_ISA_EXT_DATA(ztso, RISCV_ISA_EXT_ZTSO),
 	__RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts),
 	__RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC),
 	__RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH),
-- 
GitLab


From 5b4d64a819c05e7e96e7ab3f00f4f0967246905f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Wed, 20 Dec 2023 16:57:18 +0100
Subject: [PATCH 2444/4076] riscv: hwprobe: export Ztso ISA extension
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export the Ztso extension to userspace.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231220155723.684081-3-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 4 ++++
 arch/riscv/include/uapi/asm/hwprobe.h | 1 +
 arch/riscv/kernel/sys_riscv.c         | 1 +
 3 files changed, 6 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 41463b9322689..10bd7b170118e 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -161,6 +161,10 @@ The following keys are defined:
        defined in the RISC-V ISA manual starting from commit 056b6ff467c7
        ("Zfa is ratified").
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZTSO`: The Ztso extension is supported as
+       defined in the RISC-V ISA manual starting from commit 5618fb5a216b
+       ("Ztso is now ratified.")
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 91fbe1a7f2e29..01ac3dc196e52 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -56,6 +56,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZVFH		(1 << 30)
 #define		RISCV_HWPROBE_EXT_ZVFHMIN	(1 << 31)
 #define		RISCV_HWPROBE_EXT_ZFA		(1ULL << 32)
+#define		RISCV_HWPROBE_EXT_ZTSO		(1ULL << 33)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index f0bd7b480b7f2..6564fa9e7a7ff 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -174,6 +174,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZKSH);
 		EXT_KEY(ZKT);
 		EXT_KEY(ZIHINTNTL);
+		EXT_KEY(ZTSO);
 
 		if (has_vector()) {
 			EXT_KEY(ZVBB);
-- 
GitLab


From cd7be4d02f418d5d62bcaf26e5c44ceb4ce00029 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Wed, 20 Dec 2023 16:57:19 +0100
Subject: [PATCH 2445/4076] dt-bindings: riscv: add Zacas ISA extension
 description
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add description for the Zacas ISA extension which was ratified recently.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231220155723.684081-4-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/extensions.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index 3574a0b70be45..27beedb981987 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -171,6 +171,12 @@ properties:
             memory types as ratified in the 20191213 version of the privileged
             ISA specification.
 
+        - const: zacas
+          description: |
+            The Zacas extension for Atomic Compare-and-Swap (CAS) instructions
+            is supported as ratified at commit 5059e0ca641c ("update to
+            ratified") of the riscv-zacas.
+
         - const: zba
           description: |
             The standard Zba bit-manipulation extension for address generation
-- 
GitLab


From 188a2122c8274b64a739544b1bcfd30e30aed5dd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Wed, 20 Dec 2023 16:57:20 +0100
Subject: [PATCH 2446/4076] riscv: add ISA extension parsing for Zacas
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add parsing for Zacas ISA extension which was ratified recently in the
riscv-zacas manual.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231220155723.684081-5-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hwcap.h | 1 +
 arch/riscv/kernel/cpufeature.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 3b31efe2f716d..34f86424d7439 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -85,6 +85,7 @@
 #define RISCV_ISA_EXT_ZVFHMIN		70
 #define RISCV_ISA_EXT_ZFA		71
 #define RISCV_ISA_EXT_ZTSO		72
+#define RISCV_ISA_EXT_ZACAS		73
 
 #define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 3eb48a0eecb3e..9a9d915b5bb2e 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -259,6 +259,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zihintntl, RISCV_ISA_EXT_ZIHINTNTL),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
 	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
 	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
 	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
-- 
GitLab


From 154a3706122978eeb34d8223d49285ed4f3c61fa Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Wed, 20 Dec 2023 16:57:21 +0100
Subject: [PATCH 2447/4076] riscv: hwprobe: export Zacas ISA extension
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export Zacas ISA extension through hwprobe.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231220155723.684081-6-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 4 ++++
 arch/riscv/include/uapi/asm/hwprobe.h | 1 +
 arch/riscv/kernel/sys_riscv.c         | 1 +
 3 files changed, 6 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 10bd7b170118e..bff68004ad43d 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -165,6 +165,10 @@ The following keys are defined:
        defined in the RISC-V ISA manual starting from commit 5618fb5a216b
        ("Ztso is now ratified.")
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZACAS`: The Zacas extension is supported as
+       defined in the Atomic Compare-and-Swap (CAS) instructions manual starting
+       from commit 5059e0ca641c ("update to ratified").
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 01ac3dc196e52..ac65bb43c8e72 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -57,6 +57,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZVFHMIN	(1 << 31)
 #define		RISCV_HWPROBE_EXT_ZFA		(1ULL << 32)
 #define		RISCV_HWPROBE_EXT_ZTSO		(1ULL << 33)
+#define		RISCV_HWPROBE_EXT_ZACAS		(1ULL << 34)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 6564fa9e7a7ff..6c680c75ac0d4 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -175,6 +175,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZKT);
 		EXT_KEY(ZIHINTNTL);
 		EXT_KEY(ZTSO);
+		EXT_KEY(ZACAS);
 
 		if (has_vector()) {
 			EXT_KEY(ZVBB);
-- 
GitLab


From 3359866b40a97038405c72e68097a92a4a9caa71 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Wed, 20 Dec 2023 16:57:22 +0100
Subject: [PATCH 2448/4076] riscv: hwprobe: export Zicond extension
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Export the zicond extension to userspace using hwprobe.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231220155723.684081-7-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/arch/riscv/hwprobe.rst  | 5 +++++
 arch/riscv/include/uapi/asm/hwprobe.h | 1 +
 arch/riscv/kernel/sys_riscv.c         | 1 +
 3 files changed, 7 insertions(+)

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index bff68004ad43d..ee320fe7581b2 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -169,6 +169,11 @@ The following keys are defined:
        defined in the Atomic Compare-and-Swap (CAS) instructions manual starting
        from commit 5059e0ca641c ("update to ratified").
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZICOND`: The Zicond extension is supported as
+       defined in the RISC-V Integer Conditional (Zicond) operations extension
+       manual starting from commit 95cf1f9 ("Add changes requested by Ved
+       during signoff")
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index ac65bb43c8e72..fd7af0dddb12b 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -58,6 +58,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZFA		(1ULL << 32)
 #define		RISCV_HWPROBE_EXT_ZTSO		(1ULL << 33)
 #define		RISCV_HWPROBE_EXT_ZACAS		(1ULL << 34)
+#define		RISCV_HWPROBE_EXT_ZICOND	(1ULL << 35)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 6c680c75ac0d4..cca9b1e356470 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -176,6 +176,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZIHINTNTL);
 		EXT_KEY(ZTSO);
 		EXT_KEY(ZACAS);
+		EXT_KEY(ZICOND);
 
 		if (has_vector()) {
 			EXT_KEY(ZVBB);
-- 
GitLab


From b6da6cbe13ebf24716438de71d50573b9f36f35d Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Mon, 25 Dec 2023 12:42:06 +0800
Subject: [PATCH 2449/4076] riscv: introduce RISCV_EFFICIENT_UNALIGNED_ACCESS

Some riscv implementations such as T-HEAD's C906, C908, C910 and C920
support efficient unaligned access, for performance reason we want
to enable HAVE_EFFICIENT_UNALIGNED_ACCESS on these platforms. To
avoid performance regressions on other non efficient unaligned access
platforms, HAVE_EFFICIENT_UNALIGNED_ACCESS can't be globally selected.

To solve this problem, runtime code patching based on the detected
speed is a good solution. But that's not easy, it involves lots of
work to modify vairous subsystems such as net, mm, lib and so on.
This can be done step by step.

So let's take an easier solution: add support to efficient unaligned
access and hide the support under NONPORTABLE.

Now let's introduce RISCV_EFFICIENT_UNALIGNED_ACCESS which depends on
NONPORTABLE, if users know during config time that the kernel will be
only run on those efficient unaligned access hw platforms, they can
enable it. Obviously, generic unified kernel Image shouldn't enable it.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20231225044207.3821-2-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig  | 13 +++++++++++++
 arch/riscv/Makefile |  2 ++
 2 files changed, 15 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a6..1ba03a2b509c3 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -651,6 +651,19 @@ config RISCV_MISALIGNED
 	  load/store for both kernel and userspace. When disable, misaligned
 	  accesses will generate SIGBUS in userspace and panic in kernel.
 
+config RISCV_EFFICIENT_UNALIGNED_ACCESS
+	bool "Assume the CPU supports fast unaligned memory accesses"
+	depends on NONPORTABLE
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	help
+	  Say Y here if you want the kernel to assume that the CPU supports
+	  efficient unaligned memory accesses.  When enabled, this option
+	  improves the performance of the kernel on such CPUs.  However, the
+	  kernel will run much more slowly, or will not be able to run at all,
+	  on CPUs that do not support efficient unaligned memory accesses.
+
+	  If unsure what to do here, say N.
+
 endmenu # "Platform type"
 
 menu "Kernel features"
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index a74be78678eb0..ebbe02628a276 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -108,7 +108,9 @@ KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
 # unaligned accesses.  While unaligned accesses are explicitly allowed in the
 # RISC-V ISA, they're emulated by machine mode traps on all extant
 # architectures.  It's faster to have GCC emit only aligned accesses.
+ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS),y)
 KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
+endif
 
 ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
 prepare: stack_protector_prepare
-- 
GitLab


From d0fdc20b0429150c9dd09111f9b1d9d48117b56f Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Mon, 25 Dec 2023 12:42:07 +0800
Subject: [PATCH 2450/4076] riscv: select DCACHE_WORD_ACCESS for efficient
 unaligned access HW

DCACHE_WORD_ACCESS uses the word-at-a-time API for optimised string
comparisons in the vfs layer.

This patch implements support for load_unaligned_zeropad in much the
same way as has been done for arm64.

Here is the test program and step:

 $ cat tt.c
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>

 #define ITERATIONS 1000000

 #define PATH "123456781234567812345678123456781"

 int main(void)
 {
         unsigned long i;
         struct stat buf;

         for (i = 0; i < ITERATIONS; i++)
                 stat(PATH, &buf);

         return 0;
 }

 $ gcc -O2 tt.c
 $ touch 123456781234567812345678123456781
 $ time ./a.out

Per my test on T-HEAD C910 platforms, the above test performance is
improved by about 7.5%.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://lore.kernel.org/r/20231225044207.3821-3-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                      |  1 +
 arch/riscv/include/asm/asm-extable.h    | 15 ++++++++++++
 arch/riscv/include/asm/word-at-a-time.h | 27 +++++++++++++++++++++
 arch/riscv/mm/extable.c                 | 31 +++++++++++++++++++++++++
 4 files changed, 74 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 1ba03a2b509c3..39b0c594cc4eb 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -654,6 +654,7 @@ config RISCV_MISALIGNED
 config RISCV_EFFICIENT_UNALIGNED_ACCESS
 	bool "Assume the CPU supports fast unaligned memory accesses"
 	depends on NONPORTABLE
+	select DCACHE_WORD_ACCESS if MMU
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	help
 	  Say Y here if you want the kernel to assume that the CPU supports
diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h
index 00a96e7a96644..0c8bfd54fc4e0 100644
--- a/arch/riscv/include/asm/asm-extable.h
+++ b/arch/riscv/include/asm/asm-extable.h
@@ -6,6 +6,7 @@
 #define EX_TYPE_FIXUP			1
 #define EX_TYPE_BPF			2
 #define EX_TYPE_UACCESS_ERR_ZERO	3
+#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD	4
 
 #ifdef CONFIG_MMU
 
@@ -47,6 +48,11 @@
 #define EX_DATA_REG_ZERO_SHIFT	5
 #define EX_DATA_REG_ZERO	GENMASK(9, 5)
 
+#define EX_DATA_REG_DATA_SHIFT	0
+#define EX_DATA_REG_DATA	GENMASK(4, 0)
+#define EX_DATA_REG_ADDR_SHIFT	5
+#define EX_DATA_REG_ADDR	GENMASK(9, 5)
+
 #define EX_DATA_REG(reg, gpr)						\
 	"((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
 
@@ -62,6 +68,15 @@
 #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)			\
 	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
 
+#define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr)		\
+	__DEFINE_ASM_GPR_NUMS							\
+	__ASM_EXTABLE_RAW(#insn, #fixup,					\
+			  __stringify(EX_TYPE_LOAD_UNALIGNED_ZEROPAD),		\
+			  "("							\
+			    EX_DATA_REG(DATA, data) " | "			\
+			    EX_DATA_REG(ADDR, addr)				\
+			  ")")
+
 #endif /* __ASSEMBLY__ */
 
 #else /* CONFIG_MMU */
diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h
index 7c086ac6ecd4a..f3f031e34191d 100644
--- a/arch/riscv/include/asm/word-at-a-time.h
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -9,6 +9,7 @@
 #define _ASM_RISCV_WORD_AT_A_TIME_H
 
 
+#include <asm/asm-extable.h>
 #include <linux/kernel.h>
 
 struct word_at_a_time {
@@ -45,4 +46,30 @@ static inline unsigned long find_zero(unsigned long mask)
 /* The mask we created is directly usable as a bytemask */
 #define zero_bytemask(mask) (mask)
 
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret;
+
+	/* Load word from unaligned pointer addr */
+	asm(
+	"1:	" REG_L " %0, %2\n"
+	"2:\n"
+	_ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1)
+	: "=&r" (ret)
+	: "r" (addr), "m" (*(unsigned long *)addr));
+
+	return ret;
+}
+
+#endif	/* CONFIG_DCACHE_WORD_ACCESS */
+
 #endif /* _ASM_RISCV_WORD_AT_A_TIME_H */
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
index 35484d830fd6d..dd1530af3ef15 100644
--- a/arch/riscv/mm/extable.c
+++ b/arch/riscv/mm/extable.c
@@ -27,6 +27,14 @@ static bool ex_handler_fixup(const struct exception_table_entry *ex,
 	return true;
 }
 
+static inline unsigned long regs_get_gpr(struct pt_regs *regs, unsigned int offset)
+{
+	if (unlikely(!offset || offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
 static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
 				unsigned long val)
 {
@@ -50,6 +58,27 @@ static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
 	return true;
 }
 
+static bool
+ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
+				  struct pt_regs *regs)
+{
+	int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data);
+	int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
+	unsigned long data, addr, offset;
+
+	addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long));
+
+	offset = addr & 0x7UL;
+	addr &= ~0x7UL;
+
+	data = *(unsigned long *)addr >> (offset * 8);
+
+	regs_set_gpr(regs, reg_data * sizeof(unsigned long), data);
+
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
 bool fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *ex;
@@ -65,6 +94,8 @@ bool fixup_exception(struct pt_regs *regs)
 		return ex_handler_bpf(ex, regs);
 	case EX_TYPE_UACCESS_ERR_ZERO:
 		return ex_handler_uaccess_err_zero(ex, regs);
+	case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
+		return ex_handler_load_unaligned_zeropad(ex, regs);
 	}
 
 	BUG();
-- 
GitLab


From 2d2db7d40254d5fb53b11ebd703cd1ed0c5de7a1 Mon Sep 17 00:00:00 2001
From: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Date: Sun, 7 Jan 2024 12:34:26 +0200
Subject: [PATCH 2451/4076] xen/gntdev: Fix the abuse of underlying struct page
 in DMA-buf import
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DO NOT access the underlying struct page of an sg table exported
by DMA-buf in dmabuf_imp_to_refs(), this is not allowed.
Please see drivers/dma-buf/dma-buf.c:mangle_sg_table() for details.

Fortunately, here (for special Xen device) we can avoid using
pages and calculate gfns directly from dma addresses provided by
the sg table.

Suggested-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
Link: https://lore.kernel.org/r/20240107103426.2038075-1-olekstysh@gmail.com
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 drivers/xen/gntdev-dmabuf.c | 50 ++++++++++++++++++-------------------
 1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
index 4440e626b7975..42adc2c1e06b3 100644
--- a/drivers/xen/gntdev-dmabuf.c
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/dma-buf.h>
+#include <linux/dma-direct.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
@@ -50,7 +51,7 @@ struct gntdev_dmabuf {
 
 	/* Number of pages this buffer has. */
 	int nr_pages;
-	/* Pages of this buffer. */
+	/* Pages of this buffer (only for dma-buf export). */
 	struct page **pages;
 };
 
@@ -484,7 +485,7 @@ out:
 /* DMA buffer import support. */
 
 static int
-dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs,
+dmabuf_imp_grant_foreign_access(unsigned long *gfns, u32 *refs,
 				int count, int domid)
 {
 	grant_ref_t priv_gref_head;
@@ -507,7 +508,7 @@ dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs,
 		}
 
 		gnttab_grant_foreign_access_ref(cur_ref, domid,
-						xen_page_to_gfn(pages[i]), 0);
+						gfns[i], 0);
 		refs[i] = cur_ref;
 	}
 
@@ -529,7 +530,6 @@ static void dmabuf_imp_end_foreign_access(u32 *refs, int count)
 
 static void dmabuf_imp_free_storage(struct gntdev_dmabuf *gntdev_dmabuf)
 {
-	kfree(gntdev_dmabuf->pages);
 	kfree(gntdev_dmabuf->u.imp.refs);
 	kfree(gntdev_dmabuf);
 }
@@ -549,12 +549,6 @@ static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count)
 	if (!gntdev_dmabuf->u.imp.refs)
 		goto fail;
 
-	gntdev_dmabuf->pages = kcalloc(count,
-				       sizeof(gntdev_dmabuf->pages[0]),
-				       GFP_KERNEL);
-	if (!gntdev_dmabuf->pages)
-		goto fail;
-
 	gntdev_dmabuf->nr_pages = count;
 
 	for (i = 0; i < count; i++)
@@ -576,7 +570,8 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
 	struct dma_buf *dma_buf;
 	struct dma_buf_attachment *attach;
 	struct sg_table *sgt;
-	struct sg_page_iter sg_iter;
+	struct sg_dma_page_iter sg_iter;
+	unsigned long *gfns;
 	int i;
 
 	dma_buf = dma_buf_get(fd);
@@ -624,26 +619,31 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
 
 	gntdev_dmabuf->u.imp.sgt = sgt;
 
-	/* Now convert sgt to array of pages and check for page validity. */
+	gfns = kcalloc(count, sizeof(*gfns), GFP_KERNEL);
+	if (!gfns) {
+		ret = ERR_PTR(-ENOMEM);
+		goto fail_unmap;
+	}
+
+	/*
+	 * Now convert sgt to array of gfns without accessing underlying pages.
+	 * It is not allowed to access the underlying struct page of an sg table
+	 * exported by DMA-buf, but since we deal with special Xen dma device here
+	 * (not a normal physical one) look at the dma addresses in the sg table
+	 * and then calculate gfns directly from them.
+	 */
 	i = 0;
-	for_each_sgtable_page(sgt, &sg_iter, 0) {
-		struct page *page = sg_page_iter_page(&sg_iter);
-		/*
-		 * Check if page is valid: this can happen if we are given
-		 * a page from VRAM or other resources which are not backed
-		 * by a struct page.
-		 */
-		if (!pfn_valid(page_to_pfn(page))) {
-			ret = ERR_PTR(-EINVAL);
-			goto fail_unmap;
-		}
+	for_each_sgtable_dma_page(sgt, &sg_iter, 0) {
+		dma_addr_t addr = sg_page_iter_dma_address(&sg_iter);
+		unsigned long pfn = bfn_to_pfn(XEN_PFN_DOWN(dma_to_phys(dev, addr)));
 
-		gntdev_dmabuf->pages[i++] = page;
+		gfns[i++] = pfn_to_gfn(pfn);
 	}
 
-	ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gntdev_dmabuf->pages,
+	ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gfns,
 						      gntdev_dmabuf->u.imp.refs,
 						      count, domid));
+	kfree(gfns);
 	if (IS_ERR(ret))
 		goto fail_end_access;
 
-- 
GitLab


From dc5b56241cf3e4084723c2e27758358e0feec84f Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Tue, 9 Jan 2024 14:38:57 -0800
Subject: [PATCH 2452/4076] dt-bindings: input: bindings for Adafruit Seesaw
 Gamepad

Adds bindings for the Adafruit Seesaw Gamepad.

The gamepad functions as an i2c device with the default address of 0x50
and has an IRQ pin that can be enabled in the driver to allow for a rising
edge trigger on each button press or joystick movement.

Product page:
  https://www.adafruit.com/product/5743
Arduino driver:
  https://github.com/adafruit/Adafruit_Seesaw

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20240106015111.882325-1-anshulusr@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../input/adafruit,seesaw-gamepad.yaml        | 63 +++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml

diff --git a/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml b/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml
new file mode 100644
index 0000000000000..5e86f6de69784
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml
@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/adafruit,seesaw-gamepad.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Adafruit Mini I2C Gamepad with seesaw
+
+maintainers:
+  - Anshul Dalal <anshulusr@gmail.com>
+
+description: |
+  Adafruit Mini I2C Gamepad
+
+    +-----------------------------+
+    |   ___                       |
+    |  /   \               (X)    |
+    | |  S  |  __   __  (Y)   (A) |
+    |  \___/  |ST| |SE|    (B)    |
+    |                             |
+    +-----------------------------+
+
+  S -> 10-bit precision bidirectional analog joystick
+  ST -> Start
+  SE -> Select
+  X, A, B, Y -> Digital action buttons
+
+  Datasheet: https://cdn-learn.adafruit.com/downloads/pdf/gamepad-qt.pdf
+  Product page: https://www.adafruit.com/product/5743
+  Arduino Driver: https://github.com/adafruit/Adafruit_Seesaw
+
+properties:
+  compatible:
+    const: adafruit,seesaw-gamepad
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+    description:
+      The gamepad's IRQ pin triggers a rising edge if interrupts are enabled.
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        joystick@50 {
+            compatible = "adafruit,seesaw-gamepad";
+            interrupts = <18 IRQ_TYPE_EDGE_RISING>;
+            reg = <0x50>;
+        };
+    };
-- 
GitLab


From 52c4e5985a730796a3fa555b83b404708b960f9d Mon Sep 17 00:00:00 2001
From: Anshul Dalal <anshulusr@gmail.com>
Date: Tue, 9 Jan 2024 14:39:26 -0800
Subject: [PATCH 2453/4076] Input: driver for Adafruit Seesaw Gamepad
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adds a driver for a mini gamepad that communicates over i2c, the gamepad
has bidirectional thumb stick input and six buttons.

The gamepad chip utilizes the open framework from Adafruit called 'Seesaw'
to transmit the ADC data for the joystick and digital pin state for the
buttons. I have only implemented the functionality required to receive the
thumb stick and button state.

Steps in reading the gamepad state over i2c:
  1. Reset the registers
  2. Set the pin mode of the pins specified by the `BUTTON_MASK` to input
      `BUTTON_MASK`: A bit-map for the six digital pins internally
       connected to the joystick buttons.
  3. Enable internal pullup resistors for the `BUTTON_MASK`
  4. Bulk set the pin state HIGH for `BUTTON_MASK`
  5. Poll the device for button and joystick state done by:
      `seesaw_read_data(struct i2c_client *client, struct seesaw_data *data)`

Product page:
  https://www.adafruit.com/product/5743
Arduino driver:
  https://github.com/adafruit/Adafruit_Seesaw

Driver tested on RPi Zero 2W

Reviewed-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Anshul Dalal <anshulusr@gmail.com>
Link: https://lore.kernel.org/r/20240106015111.882325-2-anshulusr@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 MAINTAINERS                              |   7 +
 drivers/input/joystick/Kconfig           |  10 +
 drivers/input/joystick/Makefile          |   1 +
 drivers/input/joystick/adafruit-seesaw.c | 315 +++++++++++++++++++++++
 4 files changed, 333 insertions(+)
 create mode 100644 drivers/input/joystick/adafruit-seesaw.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 4cc6bf79fdd83..0595c832c2489 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -441,6 +441,13 @@ W:	http://wiki.analog.com/AD7879
 W:	https://ez.analog.com/linux-software-drivers
 F:	drivers/input/touchscreen/ad7879.c
 
+ADAFRUIT MINI I2C GAMEPAD
+M:	Anshul Dalal <anshulusr@gmail.com>
+L:	linux-input@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/input/adafruit,seesaw-gamepad.yaml
+F:	drivers/input/joystick/adafruit-seesaw.c
+
 ADDRESS SPACE LAYOUT RANDOMIZATION (ASLR)
 M:	Jiri Kosina <jikos@kernel.org>
 S:	Maintained
diff --git a/drivers/input/joystick/Kconfig b/drivers/input/joystick/Kconfig
index ac6925ce83667..7755e5b454d2c 100644
--- a/drivers/input/joystick/Kconfig
+++ b/drivers/input/joystick/Kconfig
@@ -412,4 +412,14 @@ config JOYSTICK_SENSEHAT
 	  To compile this driver as a module, choose M here: the
 	  module will be called sensehat_joystick.
 
+config JOYSTICK_SEESAW
+	tristate "Adafruit Mini I2C Gamepad with Seesaw"
+	depends on I2C
+	select INPUT_SPARSEKMAP
+	help
+	  Say Y here if you want to use the Adafruit Mini I2C Gamepad.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called adafruit-seesaw.
+
 endif
diff --git a/drivers/input/joystick/Makefile b/drivers/input/joystick/Makefile
index 3937535f00981..9976f596a9208 100644
--- a/drivers/input/joystick/Makefile
+++ b/drivers/input/joystick/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_JOYSTICK_N64)		+= n64joy.o
 obj-$(CONFIG_JOYSTICK_PSXPAD_SPI)	+= psxpad-spi.o
 obj-$(CONFIG_JOYSTICK_PXRC)		+= pxrc.o
 obj-$(CONFIG_JOYSTICK_QWIIC)		+= qwiic-joystick.o
+obj-$(CONFIG_JOYSTICK_SEESAW)		+= adafruit-seesaw.o
 obj-$(CONFIG_JOYSTICK_SENSEHAT)	+= sensehat-joystick.o
 obj-$(CONFIG_JOYSTICK_SIDEWINDER)	+= sidewinder.o
 obj-$(CONFIG_JOYSTICK_SPACEBALL)	+= spaceball.o
diff --git a/drivers/input/joystick/adafruit-seesaw.c b/drivers/input/joystick/adafruit-seesaw.c
new file mode 100644
index 0000000000000..1b9279f024cc6
--- /dev/null
+++ b/drivers/input/joystick/adafruit-seesaw.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Anshul Dalal <anshulusr@gmail.com>
+ *
+ * Driver for Adafruit Mini I2C Gamepad
+ *
+ * Based on the work of:
+ *	Oleh Kravchenko (Sparkfun Qwiic Joystick driver)
+ *
+ * Datasheet: https://cdn-learn.adafruit.com/downloads/pdf/gamepad-qt.pdf
+ * Product page: https://www.adafruit.com/product/5743
+ * Firmware and hardware sources: https://github.com/adafruit/Adafruit_Seesaw
+ *
+ * TODO:
+ *	- Add interrupt support
+ */
+
+#include <asm/unaligned.h>
+#include <linux/bits.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/input/sparse-keymap.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#define SEESAW_DEVICE_NAME		"seesaw-gamepad"
+
+#define SEESAW_ADC_BASE			0x0900
+
+#define SEESAW_GPIO_DIRCLR_BULK		0x0103
+#define SEESAW_GPIO_BULK		0x0104
+#define SEESAW_GPIO_BULK_SET		0x0105
+#define SEESAW_GPIO_PULLENSET		0x010b
+
+#define SEESAW_STATUS_HW_ID		0x0001
+#define SEESAW_STATUS_SWRST		0x007f
+
+#define SEESAW_ADC_OFFSET		0x07
+
+#define SEESAW_BUTTON_A			0x05
+#define SEESAW_BUTTON_B			0x01
+#define SEESAW_BUTTON_X			0x06
+#define SEESAW_BUTTON_Y			0x02
+#define SEESAW_BUTTON_START		0x10
+#define SEESAW_BUTTON_SELECT		0x00
+
+#define SEESAW_ANALOG_X			0x0e
+#define SEESAW_ANALOG_Y			0x0f
+
+#define SEESAW_JOYSTICK_MAX_AXIS	1023
+#define SEESAW_JOYSTICK_FUZZ		2
+#define SEESAW_JOYSTICK_FLAT		4
+
+#define SEESAW_GAMEPAD_POLL_INTERVAL_MS	16
+#define SEESAW_GAMEPAD_POLL_MIN		8
+#define SEESAW_GAMEPAD_POLL_MAX		32
+
+static const unsigned long SEESAW_BUTTON_MASK =
+	BIT(SEESAW_BUTTON_A) | BIT(SEESAW_BUTTON_B) | BIT(SEESAW_BUTTON_X) |
+	BIT(SEESAW_BUTTON_Y) | BIT(SEESAW_BUTTON_START) |
+	BIT(SEESAW_BUTTON_SELECT);
+
+struct seesaw_gamepad {
+	struct input_dev *input_dev;
+	struct i2c_client *i2c_client;
+};
+
+struct seesaw_data {
+	u16 x;
+	u16 y;
+	u32 button_state;
+};
+
+static const struct key_entry seesaw_buttons_new[] = {
+	{ KE_KEY, SEESAW_BUTTON_A, .keycode = BTN_SOUTH },
+	{ KE_KEY, SEESAW_BUTTON_B, .keycode = BTN_EAST },
+	{ KE_KEY, SEESAW_BUTTON_X, .keycode = BTN_NORTH },
+	{ KE_KEY, SEESAW_BUTTON_Y, .keycode = BTN_WEST },
+	{ KE_KEY, SEESAW_BUTTON_START, .keycode = BTN_START },
+	{ KE_KEY, SEESAW_BUTTON_SELECT, .keycode = BTN_SELECT },
+	{ KE_END, 0 }
+};
+
+static int seesaw_register_read(struct i2c_client *client, u16 reg, void *buf,
+				int count)
+{
+	__be16 register_buf = cpu_to_be16(reg);
+	struct i2c_msg message_buf[2] = {
+		{
+			.addr = client->addr,
+			.flags = client->flags,
+			.len = sizeof(register_buf),
+			.buf = (u8 *)&register_buf,
+		},
+		{
+			.addr = client->addr,
+			.flags = client->flags | I2C_M_RD,
+			.len = count,
+			.buf = (u8 *)buf,
+		},
+	};
+	int ret;
+
+	ret = i2c_transfer(client->adapter, message_buf,
+			   ARRAY_SIZE(message_buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int seesaw_register_write_u8(struct i2c_client *client, u16 reg,
+				    u8 value)
+{
+	u8 write_buf[sizeof(reg) + sizeof(value)];
+	int ret;
+
+	put_unaligned_be16(reg, write_buf);
+	write_buf[sizeof(reg)] = value;
+
+	ret = i2c_master_send(client, write_buf, sizeof(write_buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int seesaw_register_write_u32(struct i2c_client *client, u16 reg,
+				     u32 value)
+{
+	u8 write_buf[sizeof(reg) + sizeof(value)];
+	int ret;
+
+	put_unaligned_be16(reg, write_buf);
+	put_unaligned_be32(value, write_buf + sizeof(reg));
+	ret = i2c_master_send(client, write_buf, sizeof(write_buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int seesaw_read_data(struct i2c_client *client, struct seesaw_data *data)
+{
+	__be16 adc_data;
+	__be32 read_buf;
+	int err;
+
+	err = seesaw_register_read(client, SEESAW_GPIO_BULK,
+				   &read_buf, sizeof(read_buf));
+	if (err)
+		return err;
+
+	data->button_state = ~be32_to_cpu(read_buf);
+
+	err = seesaw_register_read(client,
+				   SEESAW_ADC_BASE |
+					(SEESAW_ADC_OFFSET + SEESAW_ANALOG_X),
+				   &adc_data, sizeof(adc_data));
+	if (err)
+		return err;
+	/*
+	 * ADC reads left as max and right as 0, must be reversed since kernel
+	 * expects reports in opposite order.
+	 */
+	data->x = SEESAW_JOYSTICK_MAX_AXIS - be16_to_cpu(adc_data);
+
+	err = seesaw_register_read(client,
+				   SEESAW_ADC_BASE |
+					(SEESAW_ADC_OFFSET + SEESAW_ANALOG_Y),
+				   &adc_data, sizeof(adc_data));
+	if (err)
+		return err;
+
+	data->y = be16_to_cpu(adc_data);
+
+	return 0;
+}
+
+static void seesaw_poll(struct input_dev *input)
+{
+	struct seesaw_gamepad *private = input_get_drvdata(input);
+	struct seesaw_data data;
+	int err, i;
+
+	err = seesaw_read_data(private->i2c_client, &data);
+	if (err) {
+		dev_err_ratelimited(&input->dev,
+				    "failed to read joystick state: %d\n", err);
+		return;
+	}
+
+	input_report_abs(input, ABS_X, data.x);
+	input_report_abs(input, ABS_Y, data.y);
+
+	for_each_set_bit(i, &SEESAW_BUTTON_MASK,
+			 BITS_PER_TYPE(SEESAW_BUTTON_MASK)) {
+		if (!sparse_keymap_report_event(input, i,
+						data.button_state & BIT(i),
+						false))
+			dev_err_ratelimited(&input->dev,
+					    "failed to report keymap event");
+	}
+
+	input_sync(input);
+}
+
+static int seesaw_probe(struct i2c_client *client)
+{
+	struct seesaw_gamepad *seesaw;
+	u8 hardware_id;
+	int err;
+
+	err = seesaw_register_write_u8(client, SEESAW_STATUS_SWRST, 0xFF);
+	if (err)
+		return err;
+
+	/* Wait for the registers to reset before proceeding */
+	usleep_range(10000, 15000);
+
+	seesaw = devm_kzalloc(&client->dev, sizeof(*seesaw), GFP_KERNEL);
+	if (!seesaw)
+		return -ENOMEM;
+
+	err = seesaw_register_read(client, SEESAW_STATUS_HW_ID,
+				   &hardware_id, sizeof(hardware_id));
+	if (err)
+		return err;
+
+	dev_dbg(&client->dev, "Adafruit Seesaw Gamepad, Hardware ID: %02x\n",
+		hardware_id);
+
+	/* Set Pin Mode to input and enable pull-up resistors */
+	err = seesaw_register_write_u32(client, SEESAW_GPIO_DIRCLR_BULK,
+					SEESAW_BUTTON_MASK);
+	if (err)
+		return err;
+	err = seesaw_register_write_u32(client, SEESAW_GPIO_PULLENSET,
+					SEESAW_BUTTON_MASK);
+	if (err)
+		return err;
+	err = seesaw_register_write_u32(client, SEESAW_GPIO_BULK_SET,
+					SEESAW_BUTTON_MASK);
+	if (err)
+		return err;
+
+	seesaw->i2c_client = client;
+	seesaw->input_dev = devm_input_allocate_device(&client->dev);
+	if (!seesaw->input_dev)
+		return -ENOMEM;
+
+	seesaw->input_dev->id.bustype = BUS_I2C;
+	seesaw->input_dev->name = "Adafruit Seesaw Gamepad";
+	seesaw->input_dev->phys = "i2c/" SEESAW_DEVICE_NAME;
+	input_set_drvdata(seesaw->input_dev, seesaw);
+	input_set_abs_params(seesaw->input_dev, ABS_X,
+			     0, SEESAW_JOYSTICK_MAX_AXIS,
+			     SEESAW_JOYSTICK_FUZZ, SEESAW_JOYSTICK_FLAT);
+	input_set_abs_params(seesaw->input_dev, ABS_Y,
+			     0, SEESAW_JOYSTICK_MAX_AXIS,
+			     SEESAW_JOYSTICK_FUZZ, SEESAW_JOYSTICK_FLAT);
+
+	err = sparse_keymap_setup(seesaw->input_dev, seesaw_buttons_new, NULL);
+	if (err) {
+		dev_err(&client->dev,
+			"failed to set up input device keymap: %d\n", err);
+		return err;
+	}
+
+	err = input_setup_polling(seesaw->input_dev, seesaw_poll);
+	if (err) {
+		dev_err(&client->dev, "failed to set up polling: %d\n", err);
+		return err;
+	}
+
+	input_set_poll_interval(seesaw->input_dev,
+				SEESAW_GAMEPAD_POLL_INTERVAL_MS);
+	input_set_max_poll_interval(seesaw->input_dev, SEESAW_GAMEPAD_POLL_MAX);
+	input_set_min_poll_interval(seesaw->input_dev, SEESAW_GAMEPAD_POLL_MIN);
+
+	err = input_register_device(seesaw->input_dev);
+	if (err) {
+		dev_err(&client->dev, "failed to register joystick: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static const struct i2c_device_id seesaw_id_table[] = {
+	{ SEESAW_DEVICE_NAME },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, seesaw_id_table);
+
+static const struct of_device_id seesaw_of_table[] = {
+	{ .compatible = "adafruit,seesaw-gamepad"},
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, seesaw_of_table);
+
+static struct i2c_driver seesaw_driver = {
+	.driver = {
+		.name = SEESAW_DEVICE_NAME,
+		.of_match_table = seesaw_of_table,
+	},
+	.id_table = seesaw_id_table,
+	.probe = seesaw_probe,
+};
+module_i2c_driver(seesaw_driver);
+
+MODULE_AUTHOR("Anshul Dalal <anshulusr@gmail.com>");
+MODULE_DESCRIPTION("Adafruit Mini I2C Gamepad driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From a4a9779d7642111b4fb6e7415aae9da9783850bd Mon Sep 17 00:00:00 2001
From: Mika Kahola <mika.kahola@intel.com>
Date: Tue, 2 Jan 2024 13:57:39 +0200
Subject: [PATCH 2454/4076] drm/i915/display: Fix C20 pll selection for state
 verification

Add pll selection check for C20 as well as
clock state verification0. We have been relying
on sw state to select A or B pll's. This is incorrect
as the hw might see this selection differently. This
patch fixes this shortcoming by reading pll selection
for both sw and hw states and compares if these two
selections match.

Fixes: 59be90248b42 ("drm/i915/mtl: C20 state verification")

v2: reword commit message and include fix to a
    original commit (Imre)
    Compare pll selection (Jani)

Signed-off-by: Mika Kahola <mika.kahola@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240102115741.118525-2-mika.kahola@intel.com
(cherry picked from commit f4304beadd88d074333b23fdc7f35d00ee763e14)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_cx0_phy.c | 25 ++++++++++++--------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
index 884a1da360893..6b25e195232f1 100644
--- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
@@ -3067,24 +3067,29 @@ static void intel_c20pll_state_verify(const struct intel_crtc_state *state,
 {
 	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
 	const struct intel_c20pll_state *mpll_sw_state = &state->cx0pll_state.c20;
-	bool use_mplla;
+	bool sw_use_mpllb = mpll_sw_state->tx[0] & C20_PHY_USE_MPLLB;
+	bool hw_use_mpllb = mpll_hw_state->tx[0] & C20_PHY_USE_MPLLB;
 	int i;
 
-	use_mplla = intel_c20_use_mplla(mpll_hw_state->clock);
-	if (use_mplla) {
-		for (i = 0; i < ARRAY_SIZE(mpll_sw_state->mplla); i++) {
-			I915_STATE_WARN(i915, mpll_hw_state->mplla[i] != mpll_sw_state->mplla[i],
-					"[CRTC:%d:%s] mismatch in C20MPLLA: Register[%d] (expected 0x%04x, found 0x%04x)",
-					crtc->base.base.id, crtc->base.name, i,
-					mpll_sw_state->mplla[i], mpll_hw_state->mplla[i]);
-		}
-	} else {
+	I915_STATE_WARN(i915, sw_use_mpllb != hw_use_mpllb,
+			"[CRTC:%d:%s] mismatch in C20: Register MPLLB selection (expected %d, found %d)",
+			crtc->base.base.id, crtc->base.name,
+			sw_use_mpllb, hw_use_mpllb);
+
+	if (hw_use_mpllb) {
 		for (i = 0; i < ARRAY_SIZE(mpll_sw_state->mpllb); i++) {
 			I915_STATE_WARN(i915, mpll_hw_state->mpllb[i] != mpll_sw_state->mpllb[i],
 					"[CRTC:%d:%s] mismatch in C20MPLLB: Register[%d] (expected 0x%04x, found 0x%04x)",
 					crtc->base.base.id, crtc->base.name, i,
 					mpll_sw_state->mpllb[i], mpll_hw_state->mpllb[i]);
 		}
+	} else {
+		for (i = 0; i < ARRAY_SIZE(mpll_sw_state->mplla); i++) {
+			I915_STATE_WARN(i915, mpll_hw_state->mplla[i] != mpll_sw_state->mplla[i],
+					"[CRTC:%d:%s] mismatch in C20MPLLA: Register[%d] (expected 0x%04x, found 0x%04x)",
+					crtc->base.base.id, crtc->base.name, i,
+					mpll_sw_state->mplla[i], mpll_hw_state->mplla[i]);
+		}
 	}
 
 	for (i = 0; i < ARRAY_SIZE(mpll_sw_state->tx); i++) {
-- 
GitLab


From ae8986e681e9c26fb6c140ae1ed41e6d74d38fc4 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 3 Jan 2024 17:26:09 +0200
Subject: [PATCH 2455/4076] drm/i915/dp: Fix the PSR debugfs entries wrt. MST
 connectors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

MST connectors don't have a static attached encoder, as their encoder
can change depending on the pipe they use; so the encoder for an MST
connector can't be retrieved using intel_dp_attached_encoder() (which
may return NULL for MST). Most of the PSR debugfs entries depend on a
static connector -> encoder mapping which is only true for eDP and SST
DP connectors and not for MST. These debugfs entries were enabled for
MST connectors as well recently to provide PR information for them, but
handling MST connectors needs more changes.

Fix this by not adding for now the PSR entries on MST connectors. To
make things more uniform add the entries for SST connectors on all
platforms, not just on platforms supporting DP2.0.

v2:
- Keep adding the entries for SST connectors. (Jouni)
- Add a TODO: comment for MST support.

Fixes: ef75c25e8fed ("drm/i915/panelreplay: Debugfs support for panel replay")
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/9850
Cc: Animesh Manna <animesh.manna@intel.com>
Cc: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240103152609.2434100-1-imre.deak@intel.com
(cherry picked from commit 9b0b61c5bc08e1aa55a0c1e7cda28f952b2d02cc)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index b6e2e70e12904..8f702c3fc62d4 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -3319,11 +3319,11 @@ void intel_psr_connector_debugfs_add(struct intel_connector *connector)
 	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	struct dentry *root = connector->base.debugfs_entry;
 
-	if (connector->base.connector_type != DRM_MODE_CONNECTOR_eDP) {
-		if (!(HAS_DP20(i915) &&
-		      connector->base.connector_type == DRM_MODE_CONNECTOR_DisplayPort))
-			return;
-	}
+	/* TODO: Add support for MST connectors as well. */
+	if ((connector->base.connector_type != DRM_MODE_CONNECTOR_eDP &&
+	     connector->base.connector_type != DRM_MODE_CONNECTOR_DisplayPort) ||
+	    connector->mst_port)
+		return;
 
 	debugfs_create_file("i915_psr_sink_status", 0444, root,
 			    connector, &i915_psr_sink_status_fops);
-- 
GitLab


From 11809687954ab2a073ec5a4bafd8281a42ff407a Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 4 Jan 2024 18:46:00 +0200
Subject: [PATCH 2456/4076] drm/i915: don't make assumptions about
 intel_wakeref_t type

intel_wakeref_t is supposed to be a mostly opaque cookie to its
users. It should only be checked for being non-zero and set to
zero. Debug logging its actual value is meaningless. Switch to just
debug logging whether the async_put_wakeref is non-zero.

The issue dates back to much earlier than
commit b49e894c3fd8 ("drm/i915: Replace custom intel runtime_pm tracker
with ref_tracker library"), but this is the one that brought about a
build failure due to the printf format.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/r/20240102111222.2db11208@canb.auug.org.au
Fixes: b49e894c3fd8 ("drm/i915: Replace custom intel runtime_pm tracker with ref_tracker library")
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240104164600.783371-1-jani.nikula@intel.com
(cherry picked from commit de06b42edc5bf05aefbb7e2f59475d6022ed57e1)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 5f091502719b9..6fd4fa52253a3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -405,8 +405,8 @@ print_async_put_domains_state(struct i915_power_domains *power_domains)
 						     struct drm_i915_private,
 						     display.power.domains);
 
-	drm_dbg(&i915->drm, "async_put_wakeref %lu\n",
-		power_domains->async_put_wakeref);
+	drm_dbg(&i915->drm, "async_put_wakeref: %s\n",
+		str_yes_no(power_domains->async_put_wakeref));
 
 	print_power_domains(power_domains, "async_put_domains[0]",
 			    &power_domains->async_put_domains[0]);
-- 
GitLab


From 584ebbefd12296c6bad009c8a0c9e610eb8283c8 Mon Sep 17 00:00:00 2001
From: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Date: Wed, 13 Dec 2023 14:46:29 +0530
Subject: [PATCH 2457/4076] drm/i915/dp: Fix the max DSC bpc supported by
 source

Use correct helper for getting max DSC bpc supported by the source.

Fixes: 1c56e9a39833 ("drm/i915/dp: Get optimal link config to have best compressed bpp")
Cc: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>

Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Reviewed-by: Swati Sharma <swati2.sharma@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231213091632.431557-3-ankit.k.nautiyal@intel.com
(cherry picked from commit cd7b0b2dd3d9fecc6057c07b40e8087db2f9f71a)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 3b2482bf683ff..c3b906ebe542f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2101,7 +2101,7 @@ static int intel_dp_dsc_compute_pipe_bpp(struct intel_dp *intel_dp,
 		}
 	}
 
-	dsc_max_bpc = intel_dp_dsc_min_src_input_bpc(i915);
+	dsc_max_bpc = intel_dp_dsc_max_src_input_bpc(i915);
 	if (!dsc_max_bpc)
 		return -EINVAL;
 
-- 
GitLab


From 30e18a89fb1f84718a174bc02807bd9a590e2bd0 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 26 Dec 2023 11:54:29 -0800
Subject: [PATCH 2458/4076] drm/i915/gem: reconcile Excess struct member
 kernel-doc warnings

Document nested struct members with full names as described in
Documentation/doc-guide/kernel-doc.rst.

i915_gem_context_types.h:420: warning: Excess struct member 'lock' description in 'i915_gem_context'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231226195432.10891-1-rdunlap@infradead.org
(cherry picked from commit 7353c3d7c15017140a8b984e41f94be0bf535e73)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index c573c067779f5..03bc7f9d191b9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -412,9 +412,9 @@ struct i915_gem_context {
 
 	/** @stale: tracks stale engines to be destroyed */
 	struct {
-		/** @lock: guards engines */
+		/** @stale.lock: guards engines */
 		spinlock_t lock;
-		/** @engines: list of stale engines */
+		/** @stale.engines: list of stale engines */
 		struct list_head engines;
 	} stale;
 };
-- 
GitLab


From 53cd65a9c95109eef402db0ed7822b7c9a8ad732 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 28 Dec 2023 15:49:46 -0800
Subject: [PATCH 2459/4076] drm/i915/gt: reconcile Excess struct member
 kernel-doc warnings

Document nested struct members with full names as described in
Documentation/doc-guide/kernel-doc.rst.

intel_gsc.h:34: warning: Excess struct member 'gem_obj' description in 'intel_gsc'

Also add missing field member descriptions.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231228234946.12405-1-rdunlap@infradead.org
(cherry picked from commit cd1d91115ff1929ec346d85f512ef260ddf8131e)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gsc.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.h b/drivers/gpu/drm/i915/gt/intel_gsc.h
index 7ab3ca0f9f268..013c642514486 100644
--- a/drivers/gpu/drm/i915/gt/intel_gsc.h
+++ b/drivers/gpu/drm/i915/gt/intel_gsc.h
@@ -21,8 +21,11 @@ struct mei_aux_device;
 /**
  * struct intel_gsc - graphics security controller
  *
- * @gem_obj: scratch memory GSC operations
- * @intf : gsc interface
+ * @intf: gsc interface
+ * @intf.adev: MEI aux. device for this @intf
+ * @intf.gem_obj: scratch memory GSC operations
+ * @intf.irq: IRQ for this device (%-1 for no IRQ)
+ * @intf.id: this interface's id number/index
  */
 struct intel_gsc {
 	struct intel_gsc_intf {
-- 
GitLab


From af3cfcad492f2ffbef5de36c8ee1e8f8a701938f Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 26 Dec 2023 11:54:31 -0800
Subject: [PATCH 2460/4076] drm/i915/guc: reconcile Excess struct member
 kernel-doc warnings

Document nested struct members with full names as described in
Documentation/doc-guide/kernel-doc.rst.

intel_guc.h:305: warning: Excess struct member 'lock' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'guc_ids' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'num_guc_ids' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'guc_ids_bitmap' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'guc_id_list' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'guc_ids_in_use' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'destroyed_contexts' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'destroyed_worker' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'reset_fail_worker' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'reset_fail_mask' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'sched_disable_delay_ms' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'sched_disable_gucid_threshold' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'lock' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'gt_stamp' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'ping_delay' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'work' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'shift' description in 'intel_guc'
intel_guc.h:305: warning: Excess struct member 'last_stat_jiffies' description in 'intel_guc'
18 warnings as Errors

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231226195432.10891-3-rdunlap@infradead.org
(cherry picked from commit e4cf1a70fad3e2107503e99cfe9cc0c9cba19dad)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc.h | 75 ++++++++++++++------------
 1 file changed, 42 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index e22c12ce245ad..813cc888e6fae 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -105,61 +105,67 @@ struct intel_guc {
 	 */
 	struct {
 		/**
-		 * @lock: protects everything in submission_state,
-		 * ce->guc_id.id, and ce->guc_id.ref when transitioning in and
-		 * out of zero
+		 * @submission_state.lock: protects everything in
+		 * submission_state, ce->guc_id.id, and ce->guc_id.ref
+		 * when transitioning in and out of zero
 		 */
 		spinlock_t lock;
 		/**
-		 * @guc_ids: used to allocate new guc_ids, single-lrc
+		 * @submission_state.guc_ids: used to allocate new
+		 * guc_ids, single-lrc
 		 */
 		struct ida guc_ids;
 		/**
-		 * @num_guc_ids: Number of guc_ids, selftest feature to be able
-		 * to reduce this number while testing.
+		 * @submission_state.num_guc_ids: Number of guc_ids, selftest
+		 * feature to be able to reduce this number while testing.
 		 */
 		int num_guc_ids;
 		/**
-		 * @guc_ids_bitmap: used to allocate new guc_ids, multi-lrc
+		 * @submission_state.guc_ids_bitmap: used to allocate
+		 * new guc_ids, multi-lrc
 		 */
 		unsigned long *guc_ids_bitmap;
 		/**
-		 * @guc_id_list: list of intel_context with valid guc_ids but no
-		 * refs
+		 * @submission_state.guc_id_list: list of intel_context
+		 * with valid guc_ids but no refs
 		 */
 		struct list_head guc_id_list;
 		/**
-		 * @guc_ids_in_use: Number single-lrc guc_ids in use
+		 * @submission_state.guc_ids_in_use: Number single-lrc
+		 * guc_ids in use
 		 */
 		unsigned int guc_ids_in_use;
 		/**
-		 * @destroyed_contexts: list of contexts waiting to be destroyed
-		 * (deregistered with the GuC)
+		 * @submission_state.destroyed_contexts: list of contexts
+		 * waiting to be destroyed (deregistered with the GuC)
 		 */
 		struct list_head destroyed_contexts;
 		/**
-		 * @destroyed_worker: worker to deregister contexts, need as we
-		 * need to take a GT PM reference and can't from destroy
-		 * function as it might be in an atomic context (no sleeping)
+		 * @submission_state.destroyed_worker: worker to deregister
+		 * contexts, need as we need to take a GT PM reference and
+		 * can't from destroy function as it might be in an atomic
+		 * context (no sleeping)
 		 */
 		struct work_struct destroyed_worker;
 		/**
-		 * @reset_fail_worker: worker to trigger a GT reset after an
-		 * engine reset fails
+		 * @submission_state.reset_fail_worker: worker to trigger
+		 * a GT reset after an engine reset fails
 		 */
 		struct work_struct reset_fail_worker;
 		/**
-		 * @reset_fail_mask: mask of engines that failed to reset
+		 * @submission_state.reset_fail_mask: mask of engines that
+		 * failed to reset
 		 */
 		intel_engine_mask_t reset_fail_mask;
 		/**
-		 * @sched_disable_delay_ms: schedule disable delay, in ms, for
-		 * contexts
+		 * @submission_state.sched_disable_delay_ms: schedule
+		 * disable delay, in ms, for contexts
 		 */
 		unsigned int sched_disable_delay_ms;
 		/**
-		 * @sched_disable_gucid_threshold: threshold of min remaining available
-		 * guc_ids before we start bypassing the schedule disable delay
+		 * @submission_state.sched_disable_gucid_threshold:
+		 * threshold of min remaining available guc_ids before
+		 * we start bypassing the schedule disable delay
 		 */
 		unsigned int sched_disable_gucid_threshold;
 	} submission_state;
@@ -243,37 +249,40 @@ struct intel_guc {
 	 */
 	struct {
 		/**
-		 * @lock: Lock protecting the below fields and the engine stats.
+		 * @timestamp.lock: Lock protecting the below fields and
+		 * the engine stats.
 		 */
 		spinlock_t lock;
 
 		/**
-		 * @gt_stamp: 64 bit extended value of the GT timestamp.
+		 * @timestamp.gt_stamp: 64-bit extended value of the GT
+		 * timestamp.
 		 */
 		u64 gt_stamp;
 
 		/**
-		 * @ping_delay: Period for polling the GT timestamp for
-		 * overflow.
+		 * @timestamp.ping_delay: Period for polling the GT
+		 * timestamp for overflow.
 		 */
 		unsigned long ping_delay;
 
 		/**
-		 * @work: Periodic work to adjust GT timestamp, engine and
-		 * context usage for overflows.
+		 * @timestamp.work: Periodic work to adjust GT timestamp,
+		 * engine and context usage for overflows.
 		 */
 		struct delayed_work work;
 
 		/**
-		 * @shift: Right shift value for the gpm timestamp
+		 * @timestamp.shift: Right shift value for the gpm timestamp
 		 */
 		u32 shift;
 
 		/**
-		 * @last_stat_jiffies: jiffies at last actual stats collection time
-		 * We use this timestamp to ensure we don't oversample the
-		 * stats because runtime power management events can trigger
-		 * stats collection at much higher rates than required.
+		 * @timestamp.last_stat_jiffies: jiffies at last actual
+		 * stats collection time. We use this timestamp to ensure
+		 * we don't oversample the stats because runtime power
+		 * management events can trigger stats collection at much
+		 * higher rates than required.
 		 */
 		unsigned long last_stat_jiffies;
 	} timestamp;
-- 
GitLab


From d505a16e00c35919fd9fe5735894645e0f70a415 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 26 Dec 2023 11:54:32 -0800
Subject: [PATCH 2461/4076] drm/i915/perf: reconcile Excess struct member
 kernel-doc warnings

Document nested struct members with full names as described in
Documentation/doc-guide/kernel-doc.rst.

i915_perf_types.h:341: warning: Excess struct member 'ptr_lock' description in 'i915_perf_stream'
i915_perf_types.h:341: warning: Excess struct member 'head' description in 'i915_perf_stream'
i915_perf_types.h:341: warning: Excess struct member 'tail' description in 'i915_perf_stream'
3 warnings as Errors

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231226195432.10891-4-rdunlap@infradead.org
(cherry picked from commit aa253baca534357e033bd29b074ce1eade2a9362)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_perf_types.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 13b1ae9b96c7f..46445248d193e 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -291,7 +291,8 @@ struct i915_perf_stream {
 		int size_exponent;
 
 		/**
-		 * @ptr_lock: Locks reads and writes to all head/tail state
+		 * @oa_buffer.ptr_lock: Locks reads and writes to all
+		 * head/tail state
 		 *
 		 * Consider: the head and tail pointer state needs to be read
 		 * consistently from a hrtimer callback (atomic context) and
@@ -313,7 +314,8 @@ struct i915_perf_stream {
 		spinlock_t ptr_lock;
 
 		/**
-		 * @head: Although we can always read back the head pointer register,
+		 * @oa_buffer.head: Although we can always read back
+		 * the head pointer register,
 		 * we prefer to avoid trusting the HW state, just to avoid any
 		 * risk that some hardware condition could * somehow bump the
 		 * head pointer unpredictably and cause us to forward the wrong
@@ -322,7 +324,8 @@ struct i915_perf_stream {
 		u32 head;
 
 		/**
-		 * @tail: The last verified tail that can be read by userspace.
+		 * @oa_buffer.tail: The last verified tail that can be
+		 * read by userspace.
 		 */
 		u32 tail;
 	} oa_buffer;
-- 
GitLab


From 3208bcef366a1795f03abd93a0dfe7f1c364e4d7 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 14 Dec 2023 19:26:31 +0100
Subject: [PATCH 2462/4076] mfd: ab8500-sysctrl: Drop ancient charger

The sysctrl driver was looking for an instance of the PM2301
charger but this has been deleted from the kernel and is not
used with the U8500 systems any more. Drop the string.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231214-ab8500-sysctrl-oneliner-v1-1-fd78a15c0b2f@linaro.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/ab8500-sysctrl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
index ce81fcb785d03..8f3ebe651eeaa 100644
--- a/drivers/mfd/ab8500-sysctrl.c
+++ b/drivers/mfd/ab8500-sysctrl.c
@@ -30,7 +30,7 @@ static void ab8500_power_off(void)
 {
 	sigset_t old;
 	sigset_t all;
-	static const char * const pss[] = {"ab8500_ac", "pm2301", "ab8500_usb"};
+	static const char * const pss[] = {"ab8500_ac", "ab8500_usb"};
 	int i;
 	bool charger_present = false;
 	union power_supply_propval val;
-- 
GitLab


From 64fe64f920f0b478c0fb350b1682b70c21160c98 Mon Sep 17 00:00:00 2001
From: Chunyan Zhang <chunyan.zhang@unisoc.com>
Date: Fri, 15 Dec 2023 16:56:27 +0800
Subject: [PATCH 2463/4076] dt-bindings: mfd: sprd: Add support for UMS9620

Add bindings for Unisoc UMS9620 system global registers which provide
register maps for clocks.

Signed-off-by: Chunyan Zhang <chunyan.zhang@unisoc.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231215085630.984892-2-chunyan.zhang@unisoc.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml b/Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml
index 996bd4a17ca35..a750fa23d7e7c 100644
--- a/Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml
+++ b/Documentation/devicetree/bindings/mfd/sprd,ums512-glbreg.yaml
@@ -19,7 +19,9 @@ description:
 properties:
   compatible:
     items:
-      - const: sprd,ums512-glbregs
+      - enum:
+          - sprd,ums512-glbregs
+          - sprd,ums9620-glbregs
       - const: syscon
       - const: simple-mfd
 
-- 
GitLab


From 284d16c456e5d4b143f375b8ccc4038ab3f4ee0f Mon Sep 17 00:00:00 2001
From: Peter Robinson <pbrobinson@gmail.com>
Date: Wed, 20 Dec 2023 15:56:39 +0000
Subject: [PATCH 2464/4076] mfd: ti_am335x_tscadc: Fix TI SoC dependencies

The ti_am335x_tscadc is specific to some TI SoCs, update
the dependencies for those SoCs and compile testing.

Signed-off-by: Peter Robinson <pbrobinson@gmail.com>
Link: https://lore.kernel.org/r/20231220155643.445849-1-pbrobinson@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 90ce58fd629e5..68d71b4b55bd3 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1483,6 +1483,7 @@ config MFD_SYSCON
 
 config MFD_TI_AM335X_TSCADC
 	tristate "TI ADC / Touch Screen chip support"
+	depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST
 	select MFD_CORE
 	select REGMAP
 	select REGMAP_MMIO
-- 
GitLab


From 1b5e94657320c86fc660745e3fc64321948649be Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 30 Dec 2023 22:51:56 +0900
Subject: [PATCH 2465/4076] kbuild: deb-pkg: move 'make headers' to build-arch

Strictly speaking, 'make headers' should be a part of build-arch
instead of binary-arch.

'make headers' constructs ready-to-copy UAPI headers in the kernel
directory.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/builddeb     | 1 -
 scripts/package/debian/rules | 4 ++--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index cc8c7a807fcc2..842ee4b405285 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -155,7 +155,6 @@ install_libc_headers () {
 
 	rm -rf $pdir
 
-	$MAKE -f $srctree/Makefile headers
 	$MAKE -f $srctree/Makefile headers_install INSTALL_HDR_PATH=$pdir/usr
 
 	# move asm headers to /usr/include/<libc-machine>/asm to match the structure
diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules
index 7ab31419579f0..0983077800622 100755
--- a/scripts/package/debian/rules
+++ b/scripts/package/debian/rules
@@ -26,8 +26,8 @@ binary-arch: build-arch
 build: build-arch build-indep
 build-indep:
 build-arch:
-	$(MAKE) $(make-opts) \
-	olddefconfig all
+	$(MAKE) $(make-opts) olddefconfig
+	$(MAKE) $(make-opts) $(if $(filter um,$(ARCH)),,headers) all
 
 .PHONY: clean
 clean:
-- 
GitLab


From 6185d32170b683abadddf1e68be998e24f3cc5de Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 30 Dec 2023 22:51:58 +0900
Subject: [PATCH 2466/4076] kbuild: deb-pkg: use debian/<package> for tmpdir

Use debian/<package> for tmpdir, which is the default of debhelper.
This simplifies the code.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
---
 scripts/package/builddeb | 41 ++++++++++++----------------------------
 1 file changed, 12 insertions(+), 29 deletions(-)

diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 842ee4b405285..bf96a3c246081 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -25,9 +25,7 @@ if_enabled_echo() {
 }
 
 create_package() {
-	local pname="$1" pdir="$2"
-
-	export DH_OPTIONS="-p${pname} -P${pdir}"
+	export DH_OPTIONS="-p${1}"
 
 	dh_installdocs
 	dh_installchangelogs
@@ -39,8 +37,8 @@ create_package() {
 }
 
 install_linux_image () {
-	pdir=$1
-	pname=$2
+	pname=$1
+	pdir=debian/$1
 
 	rm -rf ${pdir}
 
@@ -109,7 +107,7 @@ install_linux_image () {
 }
 
 install_linux_image_dbg () {
-	pdir=$1
+	pdir=debian/$1
 
 	rm -rf ${pdir}
 
@@ -139,8 +137,8 @@ install_linux_image_dbg () {
 }
 
 install_kernel_headers () {
-	pdir=$1
-	version=$2
+	pdir=debian/$1
+	version=${1#linux-headers-}
 
 	rm -rf $pdir
 
@@ -151,7 +149,7 @@ install_kernel_headers () {
 }
 
 install_libc_headers () {
-	pdir=$1
+	pdir=debian/$1
 
 	rm -rf $pdir
 
@@ -171,28 +169,13 @@ for package in ${packages_enabled}
 do
 	case ${package} in
 	*-dbg)
-		install_linux_image_dbg debian/linux-image-dbg;;
-	linux-image-*|user-mode-linux-*)
-		install_linux_image debian/linux-image ${package};;
-	linux-libc-dev)
-		install_libc_headers debian/linux-libc-dev;;
-	linux-headers-*)
-		install_kernel_headers debian/linux-headers ${package#linux-headers-};;
-	esac
-done
-
-for package in ${packages_enabled}
-do
-	case ${package} in
-	*-dbg)
-		create_package ${package} debian/linux-image-dbg;;
+		install_linux_image_dbg "${package}";;
 	linux-image-*|user-mode-linux-*)
-		create_package ${package} debian/linux-image;;
+		install_linux_image "${package}";;
 	linux-libc-dev)
-		create_package ${package} debian/linux-libc-dev;;
+		install_libc_headers "${package}";;
 	linux-headers-*)
-		create_package ${package} debian/linux-headers;;
+		install_kernel_headers "${package}";;
 	esac
+	create_package "${package}"
 done
-
-exit 0
-- 
GitLab


From e70b8dd26711704b1ff1f1b4eb3d048ba69e29da Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Date: Wed, 10 Jan 2024 11:57:57 +0100
Subject: [PATCH 2467/4076] ASoC: mediatek: mt8195: Remove afe-dai component
 and rework codec link

Remove the extra 'mt8195-afe-pcm-dai' component, register the DAI
drivers to the main AFE component, and rework the DAI linking between
the headset codec (RT5682/RT5682S) and the TDM interface in the probe
function to stop assigning name, relying on the of_node of the codec.
Also replace the COMP_DUMMY codec entry with a COMP_EMPTY for the
ETDM2_IN and remove it entirely from ETDM1_OUT to fix the registration
flow for this sound card.

While at it, since we also need to swap the codec init function from
ETDM2_IN to ETDM1_OUT, remove the static assignment of both `ops` and
`init` for both, as we now assign these dynamically during probe.

Fixes: 13f58267cda3 ("ASoC: soc.h: don't create dummy Component via COMP_DUMMY()")
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://msgid.link/r/20240110105757.539089-1-angelogioacchino.delregno@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/mediatek/mt8195/mt8195-afe-pcm.c | 33 +----------------
 sound/soc/mediatek/mt8195/mt8195-mt6359.c  | 41 +++++++++++++++-------
 2 files changed, 29 insertions(+), 45 deletions(-)

diff --git a/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c b/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c
index 1e33863c85ca0..620d7ade1992e 100644
--- a/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c
+++ b/sound/soc/mediatek/mt8195/mt8195-afe-pcm.c
@@ -1795,10 +1795,6 @@ static const struct snd_kcontrol_new mt8195_memif_controls[] = {
 			    MT8195_AFE_IRQ_28),
 };
 
-static const struct snd_soc_component_driver mt8195_afe_pcm_dai_component = {
-	.name = "mt8195-afe-pcm-dai",
-};
-
 static const struct mtk_base_memif_data memif_data[MT8195_AFE_MEMIF_NUM] = {
 	[MT8195_AFE_MEMIF_DL2] = {
 		.name = "DL2",
@@ -3037,7 +3033,6 @@ static int mt8195_afe_pcm_dev_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct reset_control *rstc;
 	int i, irq_id, ret;
-	struct snd_soc_component *component;
 
 	ret = of_reserved_mem_device_init(dev);
 	if (ret)
@@ -3170,36 +3165,12 @@ static int mt8195_afe_pcm_dev_probe(struct platform_device *pdev)
 
 	/* register component */
 	ret = devm_snd_soc_register_component(dev, &mt8195_afe_component,
-					      NULL, 0);
+					      afe->dai_drivers, afe->num_dai_drivers);
 	if (ret) {
 		dev_warn(dev, "err_platform\n");
 		goto err_pm_put;
 	}
 
-	component = devm_kzalloc(dev, sizeof(*component), GFP_KERNEL);
-	if (!component) {
-		ret = -ENOMEM;
-		goto err_pm_put;
-	}
-
-	ret = snd_soc_component_initialize(component,
-					   &mt8195_afe_pcm_dai_component,
-					   dev);
-	if (ret)
-		goto err_pm_put;
-
-#ifdef CONFIG_DEBUG_FS
-	component->debugfs_prefix = "pcm";
-#endif
-
-	ret = snd_soc_add_component(component,
-				    afe->dai_drivers,
-				    afe->num_dai_drivers);
-	if (ret) {
-		dev_warn(dev, "err_dai_component\n");
-		goto err_pm_put;
-	}
-
 	ret = regmap_multi_reg_write(afe->regmap, mt8195_afe_reg_defaults,
 				     ARRAY_SIZE(mt8195_afe_reg_defaults));
 	if (ret)
@@ -3224,8 +3195,6 @@ err_pm_put:
 
 static void mt8195_afe_pcm_dev_remove(struct platform_device *pdev)
 {
-	snd_soc_unregister_component(&pdev->dev);
-
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		mt8195_afe_runtime_suspend(&pdev->dev);
diff --git a/sound/soc/mediatek/mt8195/mt8195-mt6359.c b/sound/soc/mediatek/mt8195/mt8195-mt6359.c
index 4feb9fb769679..53fd8a897b9d2 100644
--- a/sound/soc/mediatek/mt8195/mt8195-mt6359.c
+++ b/sound/soc/mediatek/mt8195/mt8195-mt6359.c
@@ -934,12 +934,11 @@ SND_SOC_DAILINK_DEFS(ETDM1_IN_BE,
 
 SND_SOC_DAILINK_DEFS(ETDM2_IN_BE,
 		     DAILINK_COMP_ARRAY(COMP_CPU("ETDM2_IN")),
-		     DAILINK_COMP_ARRAY(COMP_DUMMY()),
+		     DAILINK_COMP_ARRAY(COMP_EMPTY()),
 		     DAILINK_COMP_ARRAY(COMP_EMPTY()));
 
 SND_SOC_DAILINK_DEFS(ETDM1_OUT_BE,
 		     DAILINK_COMP_ARRAY(COMP_CPU("ETDM1_OUT")),
-		     DAILINK_COMP_ARRAY(COMP_DUMMY()),
 		     DAILINK_COMP_ARRAY(COMP_EMPTY()));
 
 SND_SOC_DAILINK_DEFS(ETDM2_OUT_BE,
@@ -1237,8 +1236,6 @@ static struct snd_soc_dai_link mt8195_mt6359_dai_links[] = {
 			SND_SOC_DAIFMT_NB_NF |
 			SND_SOC_DAIFMT_CBS_CFS,
 		.dpcm_capture = 1,
-		.init = mt8195_rt5682_init,
-		.ops = &mt8195_rt5682_etdm_ops,
 		.be_hw_params_fixup = mt8195_etdm_hw_params_fixup,
 		SND_SOC_DAILINK_REG(ETDM2_IN_BE),
 	},
@@ -1249,7 +1246,6 @@ static struct snd_soc_dai_link mt8195_mt6359_dai_links[] = {
 			SND_SOC_DAIFMT_NB_NF |
 			SND_SOC_DAIFMT_CBS_CFS,
 		.dpcm_playback = 1,
-		.ops = &mt8195_rt5682_etdm_ops,
 		.be_hw_params_fixup = mt8195_etdm_hw_params_fixup,
 		SND_SOC_DAILINK_REG(ETDM1_OUT_BE),
 	},
@@ -1381,7 +1377,7 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev)
 	struct snd_soc_dai_link *dai_link;
 	struct mtk_soc_card_data *soc_card_data;
 	struct mt8195_mt6359_priv *mach_priv;
-	struct device_node *platform_node, *adsp_node, *dp_node, *hdmi_node;
+	struct device_node *platform_node, *adsp_node, *codec_node, *dp_node, *hdmi_node;
 	struct mt8195_card_data *card_data;
 	int is5682s = 0;
 	int init6359 = 0;
@@ -1401,8 +1397,12 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev)
 	if (!card->name)
 		card->name = card_data->name;
 
-	if (strstr(card->name, "_5682s"))
+	if (strstr(card->name, "_5682s")) {
+		codec_node = of_find_compatible_node(NULL, NULL, "realtek,rt5682s");
 		is5682s = 1;
+	} else
+		codec_node = of_find_compatible_node(NULL, NULL, "realtek,rt5682i");
+
 	soc_card_data = devm_kzalloc(&pdev->dev, sizeof(*card_data), GFP_KERNEL);
 	if (!soc_card_data)
 		return -ENOMEM;
@@ -1488,12 +1488,27 @@ static int mt8195_mt6359_dev_probe(struct platform_device *pdev)
 				dai_link->codecs->dai_name = "i2s-hifi";
 				dai_link->init = mt8195_hdmi_codec_init;
 			}
-		} else if (strcmp(dai_link->name, "ETDM1_OUT_BE") == 0 ||
-			   strcmp(dai_link->name, "ETDM2_IN_BE") == 0) {
-			dai_link->codecs->name =
-				is5682s ? RT5682S_DEV0_NAME : RT5682_DEV0_NAME;
-			dai_link->codecs->dai_name =
-				is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI;
+		} else if (strcmp(dai_link->name, "ETDM1_OUT_BE") == 0) {
+			if (!codec_node) {
+				dev_err(&pdev->dev, "Codec not found!\n");
+			} else {
+				dai_link->codecs->of_node = codec_node;
+				dai_link->codecs->name = NULL;
+				dai_link->codecs->dai_name =
+					is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI;
+				dai_link->init = mt8195_rt5682_init;
+				dai_link->ops = &mt8195_rt5682_etdm_ops;
+			}
+		} else if (strcmp(dai_link->name, "ETDM2_IN_BE") == 0) {
+			if (!codec_node) {
+				dev_err(&pdev->dev, "Codec not found!\n");
+			} else {
+				dai_link->codecs->of_node = codec_node;
+				dai_link->codecs->name = NULL;
+				dai_link->codecs->dai_name =
+					is5682s ? RT5682S_CODEC_DAI : RT5682_CODEC_DAI;
+				dai_link->ops = &mt8195_rt5682_etdm_ops;
+			}
 		} else if (strcmp(dai_link->name, "DL_SRC_BE") == 0 ||
 			   strcmp(dai_link->name, "UL_SRC1_BE") == 0 ||
 			   strcmp(dai_link->name, "UL_SRC2_BE") == 0) {
-- 
GitLab


From bde4f5ff8295601554601f78a523d4d97e42433e Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Tue, 9 Jan 2024 09:48:48 -0800
Subject: [PATCH 2468/4076] cpufreq: intel_pstate: Update hybrid scaling factor
 for Meteor Lake

On some Meteor Lake platforms, maximum one core turbo frequency is not
observed. During hybrid performance to frequency conversion, the maximum
frequency is 100 MHz less. This results in requesting maximum frequency
100 MHz less.

For example when the max one core turbo is 4.9 GHz:
MSR HWP_CAPABILITIES shows highest performance ratio for P-core is 0x3E.
With the current scaling factor of 78741 (1.27x for converting frequency
to performance) results in max frequency of 4.8 GHz. This results in
capping the max scaling frequency as 4.8 GHz, which is 100 MHz less than
the desired.

Add capability to define per CPU model specific scaling factor and define
scaling factor of 80000 (1.25x for converting frequency to performance for
P-cores) for Meteor Lake.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
[ rjw: Debug message adjustment, subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 3c69040920b8f..2ca70b0b5fdc5 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -302,7 +302,10 @@ static bool hwp_forced __read_mostly;
 
 static struct cpufreq_driver *intel_pstate_driver __read_mostly;
 
-#define HYBRID_SCALING_FACTOR	78741
+#define HYBRID_SCALING_FACTOR		78741
+#define HYBRID_SCALING_FACTOR_MTL	80000
+
+static int hybrid_scaling_factor = HYBRID_SCALING_FACTOR;
 
 static inline int core_get_scaling(void)
 {
@@ -422,7 +425,7 @@ static int intel_pstate_cppc_get_scaling(int cpu)
 	 */
 	if (!ret && cppc_perf.nominal_perf && cppc_perf.nominal_freq &&
 	    cppc_perf.nominal_perf * 100 != cppc_perf.nominal_freq)
-		return HYBRID_SCALING_FACTOR;
+		return hybrid_scaling_factor;
 
 	return core_get_scaling();
 }
@@ -1968,7 +1971,7 @@ static int hwp_get_cpu_scaling(int cpu)
 	smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
 	/* P-cores have a smaller perf level-to-freqency scaling factor. */
 	if (cpu_type == 0x40)
-		return HYBRID_SCALING_FACTOR;
+		return hybrid_scaling_factor;
 
 	/* Use default core scaling for E-cores */
 	if (cpu_type == 0x20)
@@ -3399,6 +3402,11 @@ static const struct x86_cpu_id intel_epp_balance_perf[] = {
 	{}
 };
 
+static const struct x86_cpu_id intel_hybrid_scaling_factor[] = {
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL),
+	{}
+};
+
 static int __init intel_pstate_init(void)
 {
 	static struct cpudata **_all_cpu_data;
@@ -3489,9 +3497,16 @@ hwp_cpu_matched:
 
 	if (hwp_active) {
 		const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf);
+		const struct x86_cpu_id *hybrid_id = x86_match_cpu(intel_hybrid_scaling_factor);
 
 		if (id)
 			epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data;
+
+		if (hybrid_id) {
+			hybrid_scaling_factor = hybrid_id->driver_data;
+			pr_debug("hybrid scaling factor: %d\n", hybrid_scaling_factor);
+		}
+
 	}
 
 	mutex_lock(&intel_pstate_driver_lock);
-- 
GitLab


From 03c305861c70d6db898dd2379b882e7772a5c5d0 Mon Sep 17 00:00:00 2001
From: Erwan Velu <erwanaliasr1@gmail.com>
Date: Tue, 9 Jan 2024 18:57:53 +0100
Subject: [PATCH 2469/4076] Documentation: admin-guide: PM: Fix two typos

Fix two typos in the admin-guide:

 - a missing e in "reference_perf" in cppc_sysfs.rst.
 - the amd_pstate sysfs path uses a dash instead of an underscore.

Signed-off-by: Erwan Velu <e.velu@criteo.com>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/admin-guide/acpi/cppc_sysfs.rst | 2 +-
 Documentation/admin-guide/pm/amd-pstate.rst   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/acpi/cppc_sysfs.rst b/Documentation/admin-guide/acpi/cppc_sysfs.rst
index e53d76365aa70..36981c6678232 100644
--- a/Documentation/admin-guide/acpi/cppc_sysfs.rst
+++ b/Documentation/admin-guide/acpi/cppc_sysfs.rst
@@ -75,4 +75,4 @@ taking two different snapshots of feedback counters at time T1 and T2.
   delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
   reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
 
-  delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
+  delivered_perf = (reference_perf x delivered_counter_delta) / reference_counter_delta
diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index 1cf40f69278cd..9eb26014d34b6 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -361,7 +361,7 @@ Global Attributes
 
 ``amd-pstate`` exposes several global attributes (files) in ``sysfs`` to
 control its functionality at the system level.  They are located in the
-``/sys/devices/system/cpu/amd-pstate/`` directory and affect all CPUs.
+``/sys/devices/system/cpu/amd_pstate/`` directory and affect all CPUs.
 
 ``status``
 	Operation mode of the driver: "active", "passive" or "disable".
-- 
GitLab


From 78996eee79ebdfe8b6f0e54cb6dcc792d5129291 Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Thu, 4 Jan 2024 11:42:47 -0800
Subject: [PATCH 2470/4076] riscv: Fix module loading free order

Reverse order of kfree calls to resolve use-after-free error.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Fixes: d8792a5734b0 ("riscv: Safely remove entries from relocation list")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202312132019.iYGTwW0L-lkp@intel.com/
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Julia Lawall <julia.lawall@inria.fr>
Closes: https://lore.kernel.org/r/202312120044.wTI1Uyaa-lkp@intel.com/
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20240104-module_loading_fix-v3-1-a71f8de6ce0f@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/module.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index aac019ed63b1b..21c7a773a8efa 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -723,8 +723,8 @@ static int add_relocation_to_accumulate(struct module *me, int type,
 
 			if (!bucket) {
 				kfree(entry);
-				kfree(rel_head);
 				kfree(rel_head->rel_entry);
+				kfree(rel_head);
 				return -ENOMEM;
 			}
 
-- 
GitLab


From 4b38b36bfbd83b23e20c172d08dd85773791e3bd Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Thu, 4 Jan 2024 11:42:48 -0800
Subject: [PATCH 2471/4076] riscv: Correctly free relocation hashtable on error

When there is not enough allocatable memory for the relocation
hashtable, module loading should exit gracefully. Previously, this was
attempted to be accomplished by checking if an unsigned number is less
than zero which does not work. Instead have the caller check if the
hashtable was correctly allocated and add a comment explaining that
hashtable_bits that is 0 is valid.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Fixes: d8792a5734b0 ("riscv: Safely remove entries from relocation list")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202312132019.iYGTwW0L-lkp@intel.com/
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Julia Lawall <julia.lawall@inria.fr>
Closes: https://lore.kernel.org/r/202312120044.wTI1Uyaa-lkp@intel.com/
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20240104-module_loading_fix-v3-2-a71f8de6ce0f@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/module.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 21c7a773a8efa..32743180e8ef5 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -747,6 +747,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 {
 	/* Can safely assume that bits is not greater than sizeof(long) */
 	unsigned long hashtable_size = roundup_pow_of_two(num_relocations);
+	/*
+	 * When hashtable_size == 1, hashtable_bits == 0.
+	 * This is valid because the hashing algorithm returns 0 in this case.
+	 */
 	unsigned int hashtable_bits = ilog2(hashtable_size);
 
 	/*
@@ -763,7 +767,7 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 					      sizeof(*relocation_hashtable),
 					      GFP_KERNEL);
 	if (!*relocation_hashtable)
-		return -ENOMEM;
+		return 0;
 
 	__hash_init(*relocation_hashtable, hashtable_size);
 
@@ -789,8 +793,8 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	hashtable_bits = initialize_relocation_hashtable(num_relocations,
 							 &relocation_hashtable);
 
-	if (hashtable_bits < 0)
-		return hashtable_bits;
+	if (!relocation_hashtable)
+		return -ENOMEM;
 
 	INIT_LIST_HEAD(&used_buckets_list);
 
-- 
GitLab


From a35551c7244d9d061643a01eb96cc3ba04eaf45c Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Thu, 4 Jan 2024 11:42:49 -0800
Subject: [PATCH 2472/4076] riscv: Fix relocation_hashtable size

A second dereference is needed to get the accurate size of the
relocation_hashtable.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Fixes: d8792a5734b0 ("riscv: Safely remove entries from relocation list")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Julia Lawall <julia.lawall@inria.fr>
Closes: https://lore.kernel.org/r/202312120044.wTI1Uyaa-lkp@intel.com/
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20240104-module_loading_fix-v3-3-a71f8de6ce0f@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/module.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 32743180e8ef5..ceb0adb387158 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -764,7 +764,7 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 	hashtable_size <<= should_double_size;
 
 	*relocation_hashtable = kmalloc_array(hashtable_size,
-					      sizeof(*relocation_hashtable),
+					      sizeof(**relocation_hashtable),
 					      GFP_KERNEL);
 	if (!*relocation_hashtable)
 		return 0;
-- 
GitLab


From f503b167b66007fc6b4434cd07a044ce4a56b6a0 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Fri, 24 Nov 2023 12:39:01 +0530
Subject: [PATCH 2473/4076] RISC-V: Add stubs for sbi_console_putchar/getchar()

The functions sbi_console_putchar() and sbi_console_getchar() are
not defined when CONFIG_RISCV_SBI_V01 is disabled so let us add
stub of these functions to avoid "#ifdef" on user side.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231124070905.1043092-2-apatel@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/sbi.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 0892f4421bc4a..66f3933c14f63 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -271,8 +271,13 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
 			unsigned long arg3, unsigned long arg4,
 			unsigned long arg5);
 
+#ifdef CONFIG_RISCV_SBI_V01
 void sbi_console_putchar(int ch);
 int sbi_console_getchar(void);
+#else
+static inline void sbi_console_putchar(int ch) { }
+static inline int sbi_console_getchar(void) { return -ENOENT; }
+#endif
 long sbi_get_mvendorid(void);
 long sbi_get_marchid(void);
 long sbi_get_mimpid(void);
-- 
GitLab


From f43fabf444ca3c4c74bf5fa5211bb2d0548715c4 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Fri, 24 Nov 2023 12:39:02 +0530
Subject: [PATCH 2474/4076] RISC-V: Add SBI debug console helper routines

Let us provide SBI debug console helper routines which can be
shared by serial/earlycon-riscv-sbi.c and hvc/hvc_riscv_sbi.c.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231124070905.1043092-3-apatel@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/sbi.h |  5 +++
 arch/riscv/kernel/sbi.c      | 66 ++++++++++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+)

diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 66f3933c14f63..9eef25308d537 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -334,6 +334,11 @@ static inline unsigned long sbi_mk_version(unsigned long major,
 }
 
 int sbi_err_map_linux_errno(int err);
+
+extern bool sbi_debug_console_available;
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes);
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes);
+
 #else /* CONFIG_RISCV_SBI */
 static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; }
 static inline void sbi_init(void) {}
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index 5a62ed1da4533..e66e0999a8005 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -7,6 +7,7 @@
 
 #include <linux/bits.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/reboot.h>
 #include <asm/sbi.h>
@@ -571,6 +572,66 @@ long sbi_get_mimpid(void)
 }
 EXPORT_SYMBOL_GPL(sbi_get_mimpid);
 
+bool sbi_debug_console_available;
+
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes)
+{
+	phys_addr_t base_addr;
+	struct sbiret ret;
+
+	if (!sbi_debug_console_available)
+		return -EOPNOTSUPP;
+
+	if (is_vmalloc_addr(bytes))
+		base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+			    offset_in_page(bytes);
+	else
+		base_addr = __pa(bytes);
+	if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+		num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+				num_bytes, lower_32_bits(base_addr),
+				upper_32_bits(base_addr), 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+				num_bytes, base_addr, 0, 0, 0, 0);
+
+	if (ret.error == SBI_ERR_FAILURE)
+		return -EIO;
+	return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes)
+{
+	phys_addr_t base_addr;
+	struct sbiret ret;
+
+	if (!sbi_debug_console_available)
+		return -EOPNOTSUPP;
+
+	if (is_vmalloc_addr(bytes))
+		base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+			    offset_in_page(bytes);
+	else
+		base_addr = __pa(bytes);
+	if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+		num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+				num_bytes, lower_32_bits(base_addr),
+				upper_32_bits(base_addr), 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+				num_bytes, base_addr, 0, 0, 0, 0);
+
+	if (ret.error == SBI_ERR_FAILURE)
+		return -EIO;
+	return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
 void __init sbi_init(void)
 {
 	int ret;
@@ -612,6 +673,11 @@ void __init sbi_init(void)
 			sbi_srst_reboot_nb.priority = 192;
 			register_restart_handler(&sbi_srst_reboot_nb);
 		}
+		if ((sbi_spec_version >= sbi_mk_version(2, 0)) &&
+		    (sbi_probe_extension(SBI_EXT_DBCN) > 0)) {
+			pr_info("SBI DBCN extension detected\n");
+			sbi_debug_console_available = true;
+		}
 	} else {
 		__sbi_set_timer = __sbi_set_timer_v01;
 		__sbi_send_ipi	= __sbi_send_ipi_v01;
-- 
GitLab


From c77bf3607a0f0180aa674b58cfa76633215bb42f Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Fri, 24 Nov 2023 12:39:03 +0530
Subject: [PATCH 2475/4076] tty/serial: Add RISC-V SBI debug console based
 earlycon

We extend the existing RISC-V SBI earlycon support to use the new
RISC-V SBI debug console extension.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231124070905.1043092-4-apatel@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 drivers/tty/serial/Kconfig              |  2 +-
 drivers/tty/serial/earlycon-riscv-sbi.c | 27 ++++++++++++++++++++++---
 2 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 732c893c8d161..1f2594b8ab9d8 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -87,7 +87,7 @@ config SERIAL_EARLYCON_SEMIHOST
 
 config SERIAL_EARLYCON_RISCV_SBI
 	bool "Early console using RISC-V SBI"
-	depends on RISCV_SBI_V01
+	depends on RISCV_SBI
 	select SERIAL_CORE
 	select SERIAL_CORE_CONSOLE
 	select SERIAL_EARLYCON
diff --git a/drivers/tty/serial/earlycon-riscv-sbi.c b/drivers/tty/serial/earlycon-riscv-sbi.c
index 27afb0b74ea70..0162155f0c839 100644
--- a/drivers/tty/serial/earlycon-riscv-sbi.c
+++ b/drivers/tty/serial/earlycon-riscv-sbi.c
@@ -15,17 +15,38 @@ static void sbi_putc(struct uart_port *port, unsigned char c)
 	sbi_console_putchar(c);
 }
 
-static void sbi_console_write(struct console *con,
-			      const char *s, unsigned n)
+static void sbi_0_1_console_write(struct console *con,
+				  const char *s, unsigned int n)
 {
 	struct earlycon_device *dev = con->data;
 	uart_console_write(&dev->port, s, n, sbi_putc);
 }
 
+static void sbi_dbcn_console_write(struct console *con,
+				   const char *s, unsigned int n)
+{
+	int ret;
+
+	while (n) {
+		ret = sbi_debug_console_write(s, n);
+		if (ret < 0)
+			break;
+
+		s += ret;
+		n -= ret;
+	}
+}
+
 static int __init early_sbi_setup(struct earlycon_device *device,
 				  const char *opt)
 {
-	device->con->write = sbi_console_write;
+	if (sbi_debug_console_available)
+		device->con->write = sbi_dbcn_console_write;
+	else if (IS_ENABLED(CONFIG_RISCV_SBI_V01))
+		device->con->write = sbi_0_1_console_write;
+	else
+		return -ENODEV;
+
 	return 0;
 }
 EARLYCON_DECLARE(sbi, early_sbi_setup);
-- 
GitLab


From 88ead68e764cd164abb965e258c4e18841433ecf Mon Sep 17 00:00:00 2001
From: Atish Patra <atishp@rivosinc.com>
Date: Fri, 24 Nov 2023 12:39:04 +0530
Subject: [PATCH 2476/4076] tty: Add SBI debug console support to HVC SBI
 driver

RISC-V SBI specification supports advanced debug console
support via SBI DBCN extension.

Extend the HVC SBI driver to support it.

Signed-off-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231124070905.1043092-5-apatel@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 drivers/tty/hvc/Kconfig         |  2 +-
 drivers/tty/hvc/hvc_riscv_sbi.c | 37 ++++++++++++++++++++++++++-------
 2 files changed, 31 insertions(+), 8 deletions(-)

diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig
index 4f9264d005c06..6e05c5c7bca1a 100644
--- a/drivers/tty/hvc/Kconfig
+++ b/drivers/tty/hvc/Kconfig
@@ -108,7 +108,7 @@ config HVC_DCC_SERIALIZE_SMP
 
 config HVC_RISCV_SBI
 	bool "RISC-V SBI console support"
-	depends on RISCV_SBI_V01
+	depends on RISCV_SBI
 	select HVC_DRIVER
 	help
 	  This enables support for console output via RISC-V SBI calls, which
diff --git a/drivers/tty/hvc/hvc_riscv_sbi.c b/drivers/tty/hvc/hvc_riscv_sbi.c
index 31f53fa77e4af..2f3571f17ecd4 100644
--- a/drivers/tty/hvc/hvc_riscv_sbi.c
+++ b/drivers/tty/hvc/hvc_riscv_sbi.c
@@ -39,21 +39,44 @@ static int hvc_sbi_tty_get(uint32_t vtermno, char *buf, int count)
 	return i;
 }
 
-static const struct hv_ops hvc_sbi_ops = {
+static const struct hv_ops hvc_sbi_v01_ops = {
 	.get_chars = hvc_sbi_tty_get,
 	.put_chars = hvc_sbi_tty_put,
 };
 
-static int __init hvc_sbi_init(void)
+static int hvc_sbi_dbcn_tty_put(uint32_t vtermno, const char *buf, int count)
 {
-	return PTR_ERR_OR_ZERO(hvc_alloc(0, 0, &hvc_sbi_ops, 16));
+	return sbi_debug_console_write(buf, count);
 }
-device_initcall(hvc_sbi_init);
 
-static int __init hvc_sbi_console_init(void)
+static int hvc_sbi_dbcn_tty_get(uint32_t vtermno, char *buf, int count)
 {
-	hvc_instantiate(0, 0, &hvc_sbi_ops);
+	return sbi_debug_console_read(buf, count);
+}
+
+static const struct hv_ops hvc_sbi_dbcn_ops = {
+	.put_chars = hvc_sbi_dbcn_tty_put,
+	.get_chars = hvc_sbi_dbcn_tty_get,
+};
+
+static int __init hvc_sbi_init(void)
+{
+	int err;
+
+	if (sbi_debug_console_available) {
+		err = PTR_ERR_OR_ZERO(hvc_alloc(0, 0, &hvc_sbi_dbcn_ops, 256));
+		if (err)
+			return err;
+		hvc_instantiate(0, 0, &hvc_sbi_dbcn_ops);
+	} else if (IS_ENABLED(CONFIG_RISCV_SBI_V01)) {
+		err = PTR_ERR_OR_ZERO(hvc_alloc(0, 0, &hvc_sbi_v01_ops, 256));
+		if (err)
+			return err;
+		hvc_instantiate(0, 0, &hvc_sbi_v01_ops);
+	} else {
+		return -ENODEV;
+	}
 
 	return 0;
 }
-console_initcall(hvc_sbi_console_init);
+device_initcall(hvc_sbi_init);
-- 
GitLab


From 50942ad6ddb57d3cfe2e4fc1f08714d54b2565ef Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Fri, 24 Nov 2023 12:39:05 +0530
Subject: [PATCH 2477/4076] RISC-V: Enable SBI based earlycon support

Let us enable SBI based earlycon support in defconfig for both RV32
and RV64 so that "earlycon=sbi" can be used again.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231124070905.1043092-6-apatel@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/configs/defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 905881282a7cd..eaf34e871e308 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -149,6 +149,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
 CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_VIRTIO=y
-- 
GitLab


From 742e324a0679ce271f7475a40056bac6917a950c Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 10 Jan 2024 08:29:53 -0700
Subject: [PATCH 2478/4076] block/iocost: silence warning on 'last_period'
 potentially being unused

If CONFIG_TRACEPOINTS isn't enabled, we assign this variable but then
never use it. This can cause the compiler to complain about that:

block/blk-iocost.c:1264:6: warning: variable 'last_period' set but not used [-Wunused-but-set-variable]
 1264 |         u64 last_period, cur_period;
      |             ^

Rather than add ifdefs to guard this, just mark it __maybe_unused.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401102335.GiWdeIo9-lkp@intel.com/
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iocost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 089fcb9cfce37..c8beec6d7df08 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1261,7 +1261,7 @@ static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now)
 static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 {
 	struct ioc *ioc = iocg->ioc;
-	u64 last_period, cur_period;
+	u64 __maybe_unused last_period, cur_period;
 	u64 vtime, vtarget;
 	int i;
 
-- 
GitLab


From 748dc0b65ec2b4b7b3dbd7befcc4a54fdcac7988 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 10 Jan 2024 18:29:42 +0900
Subject: [PATCH 2479/4076] block: fix partial zone append completion handling
 in req_bio_endio()

Partial completions of zone append request is not allowed but if a zone
append completion indicates a number of completed bytes different from
the original BIO size, only the BIO status is set to error. This leads
to bio_advance() not setting the BIO size to 0 and thus to not call
bio_endio() at the end of req_bio_endio().

Make sure a partially completed zone append is failed and completed
immediately by forcing the completed number of bytes (nbytes) to be
equal to the BIO size, thus ensuring that bio_endio() is called.

Fixes: 297db731847e ("block: fix req_bio_endio append error handling")
Cc: stable@kernel.vger.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20240110092942.442334-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index fb29ff5cc281d..aa9a05fdd0237 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -772,11 +772,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		/*
 		 * Partial zone append completions cannot be supported as the
 		 * BIO fragments may end up not being written sequentially.
+		 * For such case, force the completed nbytes to be equal to
+		 * the BIO size so that bio_advance() sets the BIO remaining
+		 * size to 0 and we end up calling bio_endio() before returning.
 		 */
-		if (bio->bi_iter.bi_size != nbytes)
+		if (bio->bi_iter.bi_size != nbytes) {
 			bio->bi_status = BLK_STS_IOERR;
-		else
+			nbytes = bio->bi_iter.bi_size;
+		} else {
 			bio->bi_iter.bi_sector = rq->__sector;
+		}
 	}
 
 	bio_advance(bio, nbytes);
-- 
GitLab


From a4ff64edf9edc8f05e2183610dc8306d3279c6ac Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Tue, 14 Nov 2023 22:33:37 +0800
Subject: [PATCH 2480/4076] riscv: errata: thead: use riscv_nonstd_cache_ops
 for CMO

Previously, we use alternative mechanism to dynamically patch
the CMO operations for THEAD C906/C910 during boot for performance
reason. But as pointed out by Arnd, "there is already a significant
cost in accessing the invalidated cache lines afterwards, which is
likely going to be much higher than the cost of an indirect branch".
And indeed, there's no performance difference with GMAC and EMMC per
my test on Sipeed Lichee Pi 4A board.

Use riscv_nonstd_cache_ops for THEAD C906/C910 CMO to simplify
the alternative code, and to acchieve Arnd's goal -- "I think
moving the THEAD ops at the same level as all nonstandard operations
makes sense, but I'd still leave CMO as an explicit fast path that
avoids the indirect branch. This seems like the right thing to do both
for readability and for platforms on which the indirect branch has a
noticeable overhead."

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Tested-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114143338.2406-2-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig.errata            |  1 +
 arch/riscv/errata/thead/errata.c     | 75 +++++++++++++++++++++++++++-
 arch/riscv/include/asm/errata_list.h | 50 +++----------------
 3 files changed, 80 insertions(+), 46 deletions(-)

diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index e2c731cfed8cc..dedb8b238e73d 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -79,6 +79,7 @@ config ERRATA_THEAD_CMO
 	depends on ERRATA_THEAD && MMU
 	select DMA_DIRECT_REMAP
 	select RISCV_DMA_NONCOHERENT
+	select RISCV_NONSTANDARD_CACHE_OPS
 	default y
 	help
 	  This will apply the cache management errata to handle the
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index 0554ed4bf087c..c07d957b14680 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -12,8 +12,10 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
+#include <asm/dma-noncoherent.h>
 #include <asm/errata_list.h>
 #include <asm/hwprobe.h>
+#include <asm/io.h>
 #include <asm/patch.h>
 #include <asm/vendorid_list.h>
 
@@ -33,6 +35,75 @@ static bool errata_probe_pbmt(unsigned int stage,
 	return false;
 }
 
+/*
+ * th.dcache.ipa rs1 (invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01010      rs1       000      00000  0001011
+ * th.dcache.iva rs1 (invalidate, virtual address)
+ *   0000001    00110      rs1       000      00000  0001011
+ *
+ * th.dcache.cpa rs1 (clean, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01001      rs1       000      00000  0001011
+ * th.dcache.cva rs1 (clean, virtual address)
+ *   0000001    00101      rs1       000      00000  0001011
+ *
+ * th.dcache.cipa rs1 (clean then invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01011      rs1       000      00000  0001011
+ * th.dcache.civa rs1 (clean then invalidate, virtual address)
+ *   0000001    00111      rs1       000      00000  0001011
+ *
+ * th.sync.s (make sure all cache operations finished)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000000    11001     00000      000      00000  0001011
+ */
+#define THEAD_INVAL_A0	".long 0x0265000b"
+#define THEAD_CLEAN_A0	".long 0x0255000b"
+#define THEAD_FLUSH_A0	".long 0x0275000b"
+#define THEAD_SYNC_S	".long 0x0190000b"
+
+#define THEAD_CMO_OP(_op, _start, _size, _cachesize)			\
+asm volatile("mv a0, %1\n\t"						\
+	     "j 2f\n\t"							\
+	     "3:\n\t"							\
+	     THEAD_##_op##_A0 "\n\t"					\
+	     "add a0, a0, %0\n\t"					\
+	     "2:\n\t"							\
+	     "bltu a0, %2, 3b\n\t"					\
+	     THEAD_SYNC_S						\
+	     : : "r"(_cachesize),					\
+		 "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)),	\
+		 "r"((unsigned long)(_start) + (_size))			\
+	     : "a0")
+
+static void thead_errata_cache_inv(phys_addr_t paddr, size_t size)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	THEAD_CMO_OP(INVAL, vaddr, size, riscv_cbom_block_size);
+}
+
+static void thead_errata_cache_wback(phys_addr_t paddr, size_t size)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	THEAD_CMO_OP(CLEAN, vaddr, size, riscv_cbom_block_size);
+}
+
+static void thead_errata_cache_wback_inv(phys_addr_t paddr, size_t size)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	THEAD_CMO_OP(FLUSH, vaddr, size, riscv_cbom_block_size);
+}
+
+static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops = {
+	.wback = &thead_errata_cache_wback,
+	.inv = &thead_errata_cache_inv,
+	.wback_inv = &thead_errata_cache_wback_inv,
+};
+
 static bool errata_probe_cmo(unsigned int stage,
 			     unsigned long arch_id, unsigned long impid)
 {
@@ -48,6 +119,7 @@ static bool errata_probe_cmo(unsigned int stage,
 	if (stage == RISCV_ALTERNATIVES_BOOT) {
 		riscv_cbom_block_size = L1_CACHE_BYTES;
 		riscv_noncoherent_supported();
+		riscv_noncoherent_register_cache_ops(&thead_errata_cmo_ops);
 	}
 
 	return true;
@@ -77,8 +149,7 @@ static u32 thead_errata_probe(unsigned int stage,
 	if (errata_probe_pbmt(stage, archid, impid))
 		cpu_req_errata |= BIT(ERRATA_THEAD_PBMT);
 
-	if (errata_probe_cmo(stage, archid, impid))
-		cpu_req_errata |= BIT(ERRATA_THEAD_CMO);
+	errata_probe_cmo(stage, archid, impid);
 
 	if (errata_probe_pmu(stage, archid, impid))
 		cpu_req_errata |= BIT(ERRATA_THEAD_PMU);
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 83ed25e435534..ea33288f8a25b 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -24,9 +24,8 @@
 
 #ifdef CONFIG_ERRATA_THEAD
 #define	ERRATA_THEAD_PBMT 0
-#define	ERRATA_THEAD_CMO 1
-#define	ERRATA_THEAD_PMU 2
-#define	ERRATA_THEAD_NUMBER 3
+#define	ERRATA_THEAD_PMU 1
+#define	ERRATA_THEAD_NUMBER 2
 #endif
 
 #ifdef __ASSEMBLY__
@@ -94,54 +93,17 @@ asm volatile(ALTERNATIVE(						\
 #define ALT_THEAD_PMA(_val)
 #endif
 
-/*
- * th.dcache.ipa rs1 (invalidate, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01010      rs1       000      00000  0001011
- * th.dache.iva rs1 (invalida, virtual address)
- *   0000001    00110      rs1       000      00000  0001011
- *
- * th.dcache.cpa rs1 (clean, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01001      rs1       000      00000  0001011
- * th.dcache.cva rs1 (clean, virtual address)
- *   0000001    00101      rs1       000      00000  0001011
- *
- * th.dcache.cipa rs1 (clean then invalidate, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01011      rs1       000      00000  0001011
- * th.dcache.civa rs1 (... virtual address)
- *   0000001    00111      rs1       000      00000  0001011
- *
- * th.sync.s (make sure all cache operations finished)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000000    11001     00000      000      00000  0001011
- */
-#define THEAD_INVAL_A0	".long 0x0265000b"
-#define THEAD_CLEAN_A0	".long 0x0255000b"
-#define THEAD_FLUSH_A0	".long 0x0275000b"
-#define THEAD_SYNC_S	".long 0x0190000b"
-
 #define ALT_CMO_OP(_op, _start, _size, _cachesize)			\
-asm volatile(ALTERNATIVE_2(						\
-	__nops(6),							\
+asm volatile(ALTERNATIVE(						\
+	__nops(5),							\
 	"mv a0, %1\n\t"							\
 	"j 2f\n\t"							\
 	"3:\n\t"							\
 	CBO_##_op(a0)							\
 	"add a0, a0, %0\n\t"						\
 	"2:\n\t"							\
-	"bltu a0, %2, 3b\n\t"						\
-	"nop", 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM,	\
-	"mv a0, %1\n\t"							\
-	"j 2f\n\t"							\
-	"3:\n\t"							\
-	THEAD_##_op##_A0 "\n\t"						\
-	"add a0, a0, %0\n\t"						\
-	"2:\n\t"							\
-	"bltu a0, %2, 3b\n\t"						\
-	THEAD_SYNC_S, THEAD_VENDOR_ID,					\
-			ERRATA_THEAD_CMO, CONFIG_ERRATA_THEAD_CMO)	\
+	"bltu a0, %2, 3b\n\t",						\
+	0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM)		\
 	: : "r"(_cachesize),						\
 	    "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)),	\
 	    "r"((unsigned long)(_start) + (_size))			\
-- 
GitLab


From 3690492612ecd2b3fd69f39f3a56f6313ea8ef8b Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Tue, 14 Nov 2023 22:33:38 +0800
Subject: [PATCH 2481/4076] riscv: errata: thead: use pa based instructions for
 CMO

T-HEAD CPUs such as C906/C910/C920 support phy address based CMO, use
them so that we don't need to convert to virt address.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20231114143338.2406-3-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/errata/thead/errata.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index c07d957b14680..b1c410bbc1aec 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -58,9 +58,9 @@ static bool errata_probe_pbmt(unsigned int stage,
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000000    11001     00000      000      00000  0001011
  */
-#define THEAD_INVAL_A0	".long 0x0265000b"
-#define THEAD_CLEAN_A0	".long 0x0255000b"
-#define THEAD_FLUSH_A0	".long 0x0275000b"
+#define THEAD_INVAL_A0	".long 0x02a5000b"
+#define THEAD_CLEAN_A0	".long 0x0295000b"
+#define THEAD_FLUSH_A0	".long 0x02b5000b"
 #define THEAD_SYNC_S	".long 0x0190000b"
 
 #define THEAD_CMO_OP(_op, _start, _size, _cachesize)			\
@@ -79,23 +79,17 @@ asm volatile("mv a0, %1\n\t"						\
 
 static void thead_errata_cache_inv(phys_addr_t paddr, size_t size)
 {
-	void *vaddr = phys_to_virt(paddr);
-
-	THEAD_CMO_OP(INVAL, vaddr, size, riscv_cbom_block_size);
+	THEAD_CMO_OP(INVAL, paddr, size, riscv_cbom_block_size);
 }
 
 static void thead_errata_cache_wback(phys_addr_t paddr, size_t size)
 {
-	void *vaddr = phys_to_virt(paddr);
-
-	THEAD_CMO_OP(CLEAN, vaddr, size, riscv_cbom_block_size);
+	THEAD_CMO_OP(CLEAN, paddr, size, riscv_cbom_block_size);
 }
 
 static void thead_errata_cache_wback_inv(phys_addr_t paddr, size_t size)
 {
-	void *vaddr = phys_to_virt(paddr);
-
-	THEAD_CMO_OP(FLUSH, vaddr, size, riscv_cbom_block_size);
+	THEAD_CMO_OP(FLUSH, paddr, size, riscv_cbom_block_size);
 }
 
 static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops = {
-- 
GitLab


From b12fbc3f787e3d7e47af274a761fdee6e867bc7d Mon Sep 17 00:00:00 2001
From: David Stevens <stevensd@chromium.org>
Date: Wed, 10 Jan 2024 11:19:25 +0900
Subject: [PATCH 2482/4076] virtio_balloon: stay awake while adjusting balloon

A virtio_balloon's parent device may be configured so that a
configuration change interrupt is a wakeup event. Extend the processing
of such a wakeup event until the balloon finishes inflating or deflating
by calling pm_stay_awake/pm_relax in the virtio_balloon driver. Note
that these calls are no-ops if the parent device doesn't support wakeup
events or if the wakeup events are not enabled.

This change allows the guest to use system power states such as s2idle
without running the risk the virtio_balloon's cooperative memory
management becoming unresponsive to the host's requests.

Tested-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: David Stevens <stevensd@chromium.org>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Message-Id: <20240110021925.1137333-1-stevensd@google.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_balloon.c | 57 +++++++++++++++++++++++++++------
 1 file changed, 47 insertions(+), 10 deletions(-)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 1fe93e93f5bcc..fa710e6c505ad 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -119,6 +119,11 @@ struct virtio_balloon {
 	/* Free page reporting device */
 	struct virtqueue *reporting_vq;
 	struct page_reporting_dev_info pr_dev_info;
+
+	/* State for keeping the wakeup_source active while adjusting the balloon */
+	spinlock_t adjustment_lock;
+	bool adjustment_signal_pending;
+	bool adjustment_in_progress;
 };
 
 static const struct virtio_device_id id_table[] = {
@@ -437,6 +442,31 @@ static void virtio_balloon_queue_free_page_work(struct virtio_balloon *vb)
 	queue_work(vb->balloon_wq, &vb->report_free_page_work);
 }
 
+static void start_update_balloon_size(struct virtio_balloon *vb)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&vb->adjustment_lock, flags);
+	vb->adjustment_signal_pending = true;
+	if (!vb->adjustment_in_progress) {
+		vb->adjustment_in_progress = true;
+		pm_stay_awake(vb->vdev->dev.parent);
+	}
+	spin_unlock_irqrestore(&vb->adjustment_lock, flags);
+
+	queue_work(system_freezable_wq, &vb->update_balloon_size_work);
+}
+
+static void end_update_balloon_size(struct virtio_balloon *vb)
+{
+	spin_lock_irq(&vb->adjustment_lock);
+	if (!vb->adjustment_signal_pending && vb->adjustment_in_progress) {
+		vb->adjustment_in_progress = false;
+		pm_relax(vb->vdev->dev.parent);
+	}
+	spin_unlock_irq(&vb->adjustment_lock);
+}
+
 static void virtballoon_changed(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
@@ -444,8 +474,7 @@ static void virtballoon_changed(struct virtio_device *vdev)
 
 	spin_lock_irqsave(&vb->stop_update_lock, flags);
 	if (!vb->stop_update) {
-		queue_work(system_freezable_wq,
-			   &vb->update_balloon_size_work);
+		start_update_balloon_size(vb);
 		virtio_balloon_queue_free_page_work(vb);
 	}
 	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
@@ -476,19 +505,25 @@ static void update_balloon_size_func(struct work_struct *work)
 
 	vb = container_of(work, struct virtio_balloon,
 			  update_balloon_size_work);
-	diff = towards_target(vb);
 
-	if (!diff)
-		return;
+	spin_lock_irq(&vb->adjustment_lock);
+	vb->adjustment_signal_pending = false;
+	spin_unlock_irq(&vb->adjustment_lock);
 
-	if (diff > 0)
-		diff -= fill_balloon(vb, diff);
-	else
-		diff += leak_balloon(vb, -diff);
-	update_balloon_size(vb);
+	diff = towards_target(vb);
+
+	if (diff) {
+		if (diff > 0)
+			diff -= fill_balloon(vb, diff);
+		else
+			diff += leak_balloon(vb, -diff);
+		update_balloon_size(vb);
+	}
 
 	if (diff)
 		queue_work(system_freezable_wq, work);
+	else
+		end_update_balloon_size(vb);
 }
 
 static int init_vqs(struct virtio_balloon *vb)
@@ -992,6 +1027,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
 			goto out_unregister_oom;
 	}
 
+	spin_lock_init(&vb->adjustment_lock);
+
 	virtio_device_ready(vdev);
 
 	if (towards_target(vb))
-- 
GitLab


From 35967bdcff325f4572b21b0d0005318da7e03f53 Mon Sep 17 00:00:00 2001
From: Changyuan Lyu <changyuanl@google.com>
Date: Wed, 20 Dec 2023 12:49:06 -0800
Subject: [PATCH 2483/4076] virtio_pmem: support feature SHMEM_REGION

This patch adds the support for feature VIRTIO_PMEM_F_SHMEM_REGION
(virtio spec v1.2 section 5.19.5.2 [1]).

During feature negotiation, if VIRTIO_PMEM_F_SHMEM_REGION is offered
by the device, the driver looks for a shared memory region of id 0.
If it is found, this feature is understood. Otherwise, this feature
bit is cleared.

During probe, if VIRTIO_PMEM_F_SHMEM_REGION has been negotiated,
virtio pmem ignores the `start` and `size` fields in device config
and uses the physical address range of shared memory region 0.

[1] https://docs.oasis-open.org/virtio/virtio/v1.2/csd01/virtio-v1.2-csd01.html#x1-6480002

Signed-off-by: Changyuan Lyu <changyuanl@google.com>
Message-Id: <20231220204906.566922-1-changyuanl@google.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/nvdimm/virtio_pmem.c     | 36 ++++++++++++++++++++++++++++----
 include/uapi/linux/virtio_pmem.h |  7 +++++++
 2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index a92eb172f0e7e..4ceced5cefcf1 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -29,12 +29,27 @@ static int init_vq(struct virtio_pmem *vpmem)
 	return 0;
 };
 
+static int virtio_pmem_validate(struct virtio_device *vdev)
+{
+	struct virtio_shm_region shm_reg;
+
+	if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION) &&
+		!virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID)
+	) {
+		dev_notice(&vdev->dev, "failed to get shared memory region %d\n",
+				VIRTIO_PMEM_SHMEM_REGION_ID);
+		__virtio_clear_bit(vdev, VIRTIO_PMEM_F_SHMEM_REGION);
+	}
+	return 0;
+}
+
 static int virtio_pmem_probe(struct virtio_device *vdev)
 {
 	struct nd_region_desc ndr_desc = {};
 	struct nd_region *nd_region;
 	struct virtio_pmem *vpmem;
 	struct resource res;
+	struct virtio_shm_region shm_reg;
 	int err = 0;
 
 	if (!vdev->config->get) {
@@ -57,10 +72,16 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
 		goto out_err;
 	}
 
-	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
-			start, &vpmem->start);
-	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
-			size, &vpmem->size);
+	if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION)) {
+		virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID);
+		vpmem->start = shm_reg.addr;
+		vpmem->size = shm_reg.len;
+	} else {
+		virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
+				start, &vpmem->start);
+		virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
+				size, &vpmem->size);
+	}
 
 	res.start = vpmem->start;
 	res.end   = vpmem->start + vpmem->size - 1;
@@ -122,10 +143,17 @@ static void virtio_pmem_remove(struct virtio_device *vdev)
 	virtio_reset_device(vdev);
 }
 
+static unsigned int features[] = {
+	VIRTIO_PMEM_F_SHMEM_REGION,
+};
+
 static struct virtio_driver virtio_pmem_driver = {
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
 	.driver.name		= KBUILD_MODNAME,
 	.driver.owner		= THIS_MODULE,
 	.id_table		= id_table,
+	.validate		= virtio_pmem_validate,
 	.probe			= virtio_pmem_probe,
 	.remove			= virtio_pmem_remove,
 };
diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h
index d676b3620383c..ede4f3564977d 100644
--- a/include/uapi/linux/virtio_pmem.h
+++ b/include/uapi/linux/virtio_pmem.h
@@ -14,6 +14,13 @@
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 
+/* Feature bits */
+/* guest physical address range will be indicated as shared memory region 0 */
+#define VIRTIO_PMEM_F_SHMEM_REGION 0
+
+/* shmid of the shared memory region corresponding to the pmem */
+#define VIRTIO_PMEM_SHMEM_REGION_ID 0
+
 struct virtio_pmem_config {
 	__le64 start;
 	__le64 size;
-- 
GitLab


From 95e7249691f082a5178d4d6f60fcdee91da458ab Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Wed, 13 Dec 2023 23:26:49 -0600
Subject: [PATCH 2484/4076] scsi: virtio_scsi: Add mq_poll support

This adds polling support to virtio-scsi. It's based on and works similar
to virtblk support where we add a module param to specify the number of
poll queues then subtract to calculate the IO queues.

When using 8 poll queues and a vhost worker per queue we see 4K IOPs
with fio:

fio --filename=/dev/sda --direct=1 --rw=randread --bs=4k \
--ioengine=io_uring --hipri --iodepth=128  --numjobs=$NUM_JOBS

increase like:

jobs	base	poll
1	207K	296K
2	392K	552K
3	581K	860K
4	765K	1235K
5	936K	1598K
6	1104K	1880K
7	1253K	2095K
8	1311k	2187K

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Message-Id: <20231214052649.57743-1-michael.christie@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/scsi/virtio_scsi.c | 78 +++++++++++++++++++++++++++++++++++---
 1 file changed, 73 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 9d1bdcdc13312..4cf20be668a60 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -37,6 +37,11 @@
 #define VIRTIO_SCSI_EVENT_LEN 8
 #define VIRTIO_SCSI_VQ_BASE 2
 
+static unsigned int virtscsi_poll_queues;
+module_param(virtscsi_poll_queues, uint, 0644);
+MODULE_PARM_DESC(virtscsi_poll_queues,
+		 "The number of dedicated virtqueues for polling I/O");
+
 /* Command queue element */
 struct virtio_scsi_cmd {
 	struct scsi_cmnd *sc;
@@ -76,6 +81,7 @@ struct virtio_scsi {
 	struct virtio_scsi_event_node event_list[VIRTIO_SCSI_EVENT_LEN];
 
 	u32 num_queues;
+	int io_queues[HCTX_MAX_TYPES];
 
 	struct hlist_node node;
 
@@ -722,9 +728,49 @@ static int virtscsi_abort(struct scsi_cmnd *sc)
 static void virtscsi_map_queues(struct Scsi_Host *shost)
 {
 	struct virtio_scsi *vscsi = shost_priv(shost);
-	struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
+	int i, qoff;
+
+	for (i = 0, qoff = 0; i < shost->nr_maps; i++) {
+		struct blk_mq_queue_map *map = &shost->tag_set.map[i];
+
+		map->nr_queues = vscsi->io_queues[i];
+		map->queue_offset = qoff;
+		qoff += map->nr_queues;
+
+		if (map->nr_queues == 0)
+			continue;
+
+		/*
+		 * Regular queues have interrupts and hence CPU affinity is
+		 * defined by the core virtio code, but polling queues have
+		 * no interrupts so we let the block layer assign CPU affinity.
+		 */
+		if (i == HCTX_TYPE_POLL)
+			blk_mq_map_queues(map);
+		else
+			blk_mq_virtio_map_queues(map, vscsi->vdev, 2);
+	}
+}
+
+static int virtscsi_mq_poll(struct Scsi_Host *shost, unsigned int queue_num)
+{
+	struct virtio_scsi *vscsi = shost_priv(shost);
+	struct virtio_scsi_vq *virtscsi_vq = &vscsi->req_vqs[queue_num];
+	unsigned long flags;
+	unsigned int len;
+	int found = 0;
+	void *buf;
+
+	spin_lock_irqsave(&virtscsi_vq->vq_lock, flags);
+
+	while ((buf = virtqueue_get_buf(virtscsi_vq->vq, &len)) != NULL) {
+		virtscsi_complete_cmd(vscsi, buf);
+		found++;
+	}
+
+	spin_unlock_irqrestore(&virtscsi_vq->vq_lock, flags);
 
-	blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2);
+	return found;
 }
 
 static void virtscsi_commit_rqs(struct Scsi_Host *shost, u16 hwq)
@@ -751,6 +797,7 @@ static const struct scsi_host_template virtscsi_host_template = {
 	.this_id = -1,
 	.cmd_size = sizeof(struct virtio_scsi_cmd),
 	.queuecommand = virtscsi_queuecommand,
+	.mq_poll = virtscsi_mq_poll,
 	.commit_rqs = virtscsi_commit_rqs,
 	.change_queue_depth = virtscsi_change_queue_depth,
 	.eh_abort_handler = virtscsi_abort,
@@ -795,13 +842,14 @@ static int virtscsi_init(struct virtio_device *vdev,
 {
 	int err;
 	u32 i;
-	u32 num_vqs;
+	u32 num_vqs, num_poll_vqs, num_req_vqs;
 	vq_callback_t **callbacks;
 	const char **names;
 	struct virtqueue **vqs;
 	struct irq_affinity desc = { .pre_vectors = 2 };
 
-	num_vqs = vscsi->num_queues + VIRTIO_SCSI_VQ_BASE;
+	num_req_vqs = vscsi->num_queues;
+	num_vqs = num_req_vqs + VIRTIO_SCSI_VQ_BASE;
 	vqs = kmalloc_array(num_vqs, sizeof(struct virtqueue *), GFP_KERNEL);
 	callbacks = kmalloc_array(num_vqs, sizeof(vq_callback_t *),
 				  GFP_KERNEL);
@@ -812,15 +860,31 @@ static int virtscsi_init(struct virtio_device *vdev,
 		goto out;
 	}
 
+	num_poll_vqs = min_t(unsigned int, virtscsi_poll_queues,
+			     num_req_vqs - 1);
+	vscsi->io_queues[HCTX_TYPE_DEFAULT] = num_req_vqs - num_poll_vqs;
+	vscsi->io_queues[HCTX_TYPE_READ] = 0;
+	vscsi->io_queues[HCTX_TYPE_POLL] = num_poll_vqs;
+
+	dev_info(&vdev->dev, "%d/%d/%d default/read/poll queues\n",
+		 vscsi->io_queues[HCTX_TYPE_DEFAULT],
+		 vscsi->io_queues[HCTX_TYPE_READ],
+		 vscsi->io_queues[HCTX_TYPE_POLL]);
+
 	callbacks[0] = virtscsi_ctrl_done;
 	callbacks[1] = virtscsi_event_done;
 	names[0] = "control";
 	names[1] = "event";
-	for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs; i++) {
+	for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs - num_poll_vqs; i++) {
 		callbacks[i] = virtscsi_req_done;
 		names[i] = "request";
 	}
 
+	for (; i < num_vqs; i++) {
+		callbacks[i] = NULL;
+		names[i] = "request_poll";
+	}
+
 	/* Discover virtqueues and write information to configuration.  */
 	err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
 	if (err)
@@ -874,6 +938,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 
 	sg_elems = virtscsi_config_get(vdev, seg_max) ?: 1;
 	shost->sg_tablesize = sg_elems;
+	shost->nr_maps = 1;
 	vscsi = shost_priv(shost);
 	vscsi->vdev = vdev;
 	vscsi->num_queues = num_queues;
@@ -883,6 +948,9 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	if (err)
 		goto virtscsi_init_failed;
 
+	if (vscsi->io_queues[HCTX_TYPE_POLL])
+		shost->nr_maps = HCTX_TYPE_POLL + 1;
+
 	shost->can_queue = virtqueue_get_vring_size(vscsi->req_vqs[0].vq);
 
 	cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1;
-- 
GitLab


From c7e194402be3ed385dfaefaf1681bb731fd776e2 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 15:42:09 +0200
Subject: [PATCH 2485/4076] vdpa: Track device suspended state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set vdpa device suspended state on successful suspend. Clear it on
successful resume and reset.

The state will be locked by the vhost_vdpa mutex. The mutex is taken
during suspend, resume and reset in vhost_vdpa_unlocked_ioctl. The
exception is vhost_vdpa_open which does a device reset but that should
be safe because it can only happen before the other ops.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Suggested-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20231225134210.151540-2-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vdpa.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index a51c69c078d93..5f046770c0a43 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -59,6 +59,7 @@ struct vhost_vdpa {
 	int in_batch;
 	struct vdpa_iova_range range;
 	u32 batch_asid;
+	bool suspended;
 };
 
 static DEFINE_IDA(vhost_vdpa_ida);
@@ -232,6 +233,8 @@ static int _compat_vdpa_reset(struct vhost_vdpa *v)
 	struct vdpa_device *vdpa = v->vdpa;
 	u32 flags = 0;
 
+	v->suspended = false;
+
 	if (v->vdev.vqs) {
 		flags |= !vhost_backend_has_feature(v->vdev.vqs[0],
 						    VHOST_BACKEND_F_IOTLB_PERSIST) ?
@@ -590,11 +593,16 @@ static long vhost_vdpa_suspend(struct vhost_vdpa *v)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+	int ret;
 
 	if (!ops->suspend)
 		return -EOPNOTSUPP;
 
-	return ops->suspend(vdpa);
+	ret = ops->suspend(vdpa);
+	if (!ret)
+		v->suspended = true;
+
+	return ret;
 }
 
 /* After a successful return of this ioctl the device resumes processing
@@ -605,11 +613,16 @@ static long vhost_vdpa_resume(struct vhost_vdpa *v)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+	int ret;
 
 	if (!ops->resume)
 		return -EOPNOTSUPP;
 
-	return ops->resume(vdpa);
+	ret = ops->resume(vdpa);
+	if (!ret)
+		v->suspended = false;
+
+	return ret;
 }
 
 static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
-- 
GitLab


From a09483c4065fe1e14812f2371cee1cba78a13d60 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 15:42:10 +0200
Subject: [PATCH 2486/4076] vdpa: Block vq property changes in DRIVER_OK
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The virtio standard doesn't allow for virtqueue address and state
changes when the device is in DRIVER_OK. Return an error in such cases
unless the device is suspended.

The suspended device exception is needed because some devices support
virtqueue changes when the device is suspended.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Suggested-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20231225134210.151540-3-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vdpa.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 5f046770c0a43..5c3e019c01229 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -703,6 +703,9 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 
 	switch (cmd) {
 	case VHOST_SET_VRING_ADDR:
+		if ((ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) && !v->suspended)
+			return -EINVAL;
+
 		if (ops->set_vq_address(vdpa, idx,
 					(u64)(uintptr_t)vq->desc,
 					(u64)(uintptr_t)vq->avail,
@@ -711,6 +714,9 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 		break;
 
 	case VHOST_SET_VRING_BASE:
+		if ((ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) && !v->suspended)
+			return -EINVAL;
+
 		if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) {
 			vq_state.packed.last_avail_idx = vq->last_avail_idx & 0x7fff;
 			vq_state.packed.last_avail_counter = !!(vq->last_avail_idx & 0x8000);
-- 
GitLab


From ef067191f73cce3ee192e991ce486d95524655d5 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:11:56 +0200
Subject: [PATCH 2487/4076] vdpa/mlx5: Expose resumable vq capability
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Necessary for checking if resumable vqs are supported by the hardware.
Actual support will be added in a downstream patch.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-2-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/mlx5/mlx5_ifc.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f3631425f386..9eaceaf6bcb06 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1236,7 +1236,8 @@ struct mlx5_ifc_virtio_emulation_cap_bits {
 
 	u8	   reserved_at_c0[0x13];
 	u8         desc_group_mkey_supported[0x1];
-	u8         reserved_at_d4[0xc];
+	u8         freeze_to_rdy_supported[0x1];
+	u8         reserved_at_d5[0xb];
 
 	u8         reserved_at_e0[0x20];
 
-- 
GitLab


From 651cdaa9c028b1edf0897e10f560fed4f4fb1fb6 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:11:57 +0200
Subject: [PATCH 2488/4076] vdpa/mlx5: Allow modifying multiple vq fields in
 one modify command
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a bitmask variable that tracks hw vq field changes that
are supposed to be modified on next hw vq change command.

This will be useful to set multiple vq fields when resuming the vq.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-3-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c | 48 +++++++++++++++++++++++++------
 1 file changed, 40 insertions(+), 8 deletions(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 26ba7da6b4106..1e08a88056402 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -120,6 +120,9 @@ struct mlx5_vdpa_virtqueue {
 	u16 avail_idx;
 	u16 used_idx;
 	int fw_state;
+
+	u64 modified_fields;
+
 	struct msi_map map;
 
 	/* keep last in the struct */
@@ -1181,7 +1184,19 @@ static bool is_valid_state_change(int oldstate, int newstate)
 	}
 }
 
-static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int state)
+static bool modifiable_virtqueue_fields(struct mlx5_vdpa_virtqueue *mvq)
+{
+	/* Only state is always modifiable */
+	if (mvq->modified_fields & ~MLX5_VIRTQ_MODIFY_MASK_STATE)
+		return mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT ||
+		       mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND;
+
+	return true;
+}
+
+static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
+			    struct mlx5_vdpa_virtqueue *mvq,
+			    int state)
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in);
 	u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {};
@@ -1193,6 +1208,9 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	if (mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_NONE)
 		return 0;
 
+	if (!modifiable_virtqueue_fields(mvq))
+		return -EINVAL;
+
 	if (!is_valid_state_change(mvq->fw_state, state))
 		return -EINVAL;
 
@@ -1208,17 +1226,28 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
 
 	obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context);
-	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select,
-		   MLX5_VIRTQ_MODIFY_MASK_STATE);
-	MLX5_SET(virtio_net_q_object, obj_context, state, state);
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE)
+		MLX5_SET(virtio_net_q_object, obj_context, state, state);
+
+	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	kfree(in);
 	if (!err)
 		mvq->fw_state = state;
 
+	mvq->modified_fields = 0;
+
 	return err;
 }
 
+static int modify_virtqueue_state(struct mlx5_vdpa_net *ndev,
+				  struct mlx5_vdpa_virtqueue *mvq,
+				  unsigned int state)
+{
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_STATE;
+	return modify_virtqueue(ndev, mvq, state);
+}
+
 static int counter_set_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	u32 in[MLX5_ST_SZ_DW(create_virtio_q_counters_in)] = {};
@@ -1347,7 +1376,7 @@ static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 		goto err_vq;
 
 	if (mvq->ready) {
-		err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
+		err = modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
 		if (err) {
 			mlx5_vdpa_warn(&ndev->mvdev, "failed to modify to ready vq idx %d(%d)\n",
 				       idx, err);
@@ -1382,7 +1411,7 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
 	if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
 		return;
 
-	if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
+	if (modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
 		mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
 
 	if (query_virtqueue(ndev, mvq, &attr)) {
@@ -1407,6 +1436,7 @@ static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *
 		return;
 
 	suspend_vq(ndev, mvq);
+	mvq->modified_fields = 0;
 	destroy_virtqueue(ndev, mvq);
 	dealloc_vector(ndev, mvq);
 	counter_set_dealloc(ndev, mvq);
@@ -2207,7 +2237,7 @@ static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready
 	if (!ready) {
 		suspend_vq(ndev, mvq);
 	} else {
-		err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
+		err = modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
 		if (err) {
 			mlx5_vdpa_warn(mvdev, "modify VQ %d to ready failed (%d)\n", idx, err);
 			ready = false;
@@ -2804,8 +2834,10 @@ static void clear_vqs_ready(struct mlx5_vdpa_net *ndev)
 {
 	int i;
 
-	for (i = 0; i < ndev->mvdev.max_vqs; i++)
+	for (i = 0; i < ndev->mvdev.max_vqs; i++) {
 		ndev->vqs[i].ready = false;
+		ndev->vqs[i].modified_fields = 0;
+	}
 
 	ndev->mvdev.cvq.ready = false;
 }
-- 
GitLab


From 145096937b8a6a8d5889f5a1a6fb453c52cc48a1 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:11:58 +0200
Subject: [PATCH 2489/4076] vdpa/mlx5: Introduce per vq and device resume
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implement vdpa vq and device resume if capability detected. Add support
for suspend -> ready state change.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-4-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c | 69 +++++++++++++++++++++++++++----
 1 file changed, 62 insertions(+), 7 deletions(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 1e08a88056402..f8f088cced50a 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1170,7 +1170,12 @@ err_cmd:
 	return err;
 }
 
-static bool is_valid_state_change(int oldstate, int newstate)
+static bool is_resumable(struct mlx5_vdpa_net *ndev)
+{
+	return ndev->mvdev.vdev.config->resume;
+}
+
+static bool is_valid_state_change(int oldstate, int newstate, bool resumable)
 {
 	switch (oldstate) {
 	case MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT:
@@ -1178,6 +1183,7 @@ static bool is_valid_state_change(int oldstate, int newstate)
 	case MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY:
 		return newstate == MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND;
 	case MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND:
+		return resumable ? newstate == MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY : false;
 	case MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR:
 	default:
 		return false;
@@ -1200,6 +1206,7 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in);
 	u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {};
+	bool state_change = false;
 	void *obj_context;
 	void *cmd_hdr;
 	void *in;
@@ -1211,9 +1218,6 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	if (!modifiable_virtqueue_fields(mvq))
 		return -EINVAL;
 
-	if (!is_valid_state_change(mvq->fw_state, state))
-		return -EINVAL;
-
 	in = kzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1226,17 +1230,29 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
 
 	obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context);
-	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE)
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE) {
+		if (!is_valid_state_change(mvq->fw_state, state, is_resumable(ndev))) {
+			err = -EINVAL;
+			goto done;
+		}
+
 		MLX5_SET(virtio_net_q_object, obj_context, state, state);
+		state_change = true;
+	}
 
 	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
-	kfree(in);
-	if (!err)
+	if (err)
+		goto done;
+
+	if (state_change)
 		mvq->fw_state = state;
 
 	mvq->modified_fields = 0;
 
+done:
+	kfree(in);
 	return err;
 }
 
@@ -1430,6 +1446,24 @@ static void suspend_vqs(struct mlx5_vdpa_net *ndev)
 		suspend_vq(ndev, &ndev->vqs[i]);
 }
 
+static void resume_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+	if (!mvq->initialized || !is_resumable(ndev))
+		return;
+
+	if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND)
+		return;
+
+	if (modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY))
+		mlx5_vdpa_warn(&ndev->mvdev, "modify to resume failed for vq %u\n", mvq->index);
+}
+
+static void resume_vqs(struct mlx5_vdpa_net *ndev)
+{
+	for (int i = 0; i < ndev->mvdev.max_vqs; i++)
+		resume_vq(ndev, &ndev->vqs[i]);
+}
+
 static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	if (!mvq->initialized)
@@ -3261,6 +3295,23 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev)
 	return 0;
 }
 
+static int mlx5_vdpa_resume(struct vdpa_device *vdev)
+{
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev;
+
+	ndev = to_mlx5_vdpa_ndev(mvdev);
+
+	mlx5_vdpa_info(mvdev, "resuming device\n");
+
+	down_write(&ndev->reslock);
+	mvdev->suspended = false;
+	resume_vqs(ndev);
+	register_link_notifier(ndev);
+	up_write(&ndev->reslock);
+	return 0;
+}
+
 static int mlx5_set_group_asid(struct vdpa_device *vdev, u32 group,
 			       unsigned int asid)
 {
@@ -3317,6 +3368,7 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.get_vq_dma_dev = mlx5_get_vq_dma_dev,
 	.free = mlx5_vdpa_free,
 	.suspend = mlx5_vdpa_suspend,
+	.resume = mlx5_vdpa_resume, /* Op disabled if not supported. */
 };
 
 static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
@@ -3688,6 +3740,9 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, desc_group_mkey_supported))
 		mgtdev->vdpa_ops.get_vq_desc_group = NULL;
 
+	if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, freeze_to_rdy_supported))
+		mgtdev->vdpa_ops.resume = NULL;
+
 	err = vdpa_mgmtdev_register(&mgtdev->mgtdev);
 	if (err)
 		goto reg_err;
-- 
GitLab


From 9b23417825df470e4c9e98e7ed4b2c37465bfa1e Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:11:59 +0200
Subject: [PATCH 2490/4076] vdpa/mlx5: Mark vq addrs for modification in hw vq

Addresses get set by .set_vq_address. hw vq addresses will be updated on
next modify_virtqueue.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-5-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 9 +++++++++
 include/linux/mlx5/mlx5_ifc_vdpa.h | 1 +
 2 files changed, 10 insertions(+)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index f8f088cced50a..80e066de08661 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1209,6 +1209,7 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	bool state_change = false;
 	void *obj_context;
 	void *cmd_hdr;
+	void *vq_ctx;
 	void *in;
 	int err;
 
@@ -1230,6 +1231,7 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
 
 	obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context);
+	vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context);
 
 	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE) {
 		if (!is_valid_state_change(mvq->fw_state, state, is_resumable(ndev))) {
@@ -1241,6 +1243,12 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 		state_change = true;
 	}
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS) {
+		MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr);
+		MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr);
+		MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
+	}
+
 	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	if (err)
@@ -2202,6 +2210,7 @@ static int mlx5_vdpa_set_vq_address(struct vdpa_device *vdev, u16 idx, u64 desc_
 	mvq->desc_addr = desc_area;
 	mvq->device_addr = device_area;
 	mvq->driver_addr = driver_area;
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS;
 	return 0;
 }
 
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index b86d51a855f67..9594ac4057406 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -145,6 +145,7 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_STATE                    = (u64)1 << 0,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
 	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
-- 
GitLab


From 60c43b3f6b4eb5a3d672952a0d65991f414ea258 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:12:00 +0200
Subject: [PATCH 2491/4076] vdpa/mlx5: Mark vq state for modification in hw vq

.set_vq_state will set the indices and mark the fields to be modified in
the hw vq.

Advertise that the device supports changing the vq state when the device
is in DRIVER_OK state and suspended.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20231225151203.152687-6-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 8 ++++++++
 include/linux/mlx5/mlx5_ifc_vdpa.h | 2 ++
 2 files changed, 10 insertions(+)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 80e066de08661..d6c8506cec8f5 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1249,6 +1249,12 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 		MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
 	}
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX)
+		MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx);
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX)
+		MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx);
+
 	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	if (err)
@@ -2328,6 +2334,8 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
 
 	mvq->used_idx = state->split.avail_index;
 	mvq->avail_idx = state->split.avail_index;
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX |
+				MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX;
 	return 0;
 }
 
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 9594ac4057406..32e712106e684 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -146,6 +146,8 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX       = (u64)1 << 7,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX        = (u64)1 << 8,
 	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
-- 
GitLab


From f756dd3e2a4c704c0ab5ecb143ab71f1249af497 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:12:01 +0200
Subject: [PATCH 2492/4076] vdpa/mlx5: Use vq suspend/resume during .set_map
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of tearing down and setting up vq resources, use vq
suspend/resume during .set_map to speed things up a bit.

The vq mr is updated with the new mapping while the vqs are suspended.

If the device doesn't support resumable vqs, do the old teardown and
setup dance.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-7-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 46 ++++++++++++++++++++++++------
 include/linux/mlx5/mlx5_ifc_vdpa.h |  1 +
 2 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index d6c8506cec8f5..6a21223d97a8e 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1206,6 +1206,7 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in);
 	u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {};
+	struct mlx5_vdpa_dev *mvdev = &ndev->mvdev;
 	bool state_change = false;
 	void *obj_context;
 	void *cmd_hdr;
@@ -1255,6 +1256,24 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX)
 		MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx);
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY) {
+		struct mlx5_vdpa_mr *mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]];
+
+		if (mr)
+			MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, mr->mkey);
+		else
+			mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY;
+	}
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY) {
+		struct mlx5_vdpa_mr *mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_DESC_GROUP]];
+
+		if (mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported))
+			MLX5_SET(virtio_q, vq_ctx, desc_group_mkey, mr->mkey);
+		else
+			mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY;
+	}
+
 	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	if (err)
@@ -2784,24 +2803,35 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
 				unsigned int asid)
 {
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	bool teardown = !is_resumable(ndev);
 	int err;
 
 	suspend_vqs(ndev);
-	err = save_channels_info(ndev);
-	if (err)
-		return err;
+	if (teardown) {
+		err = save_channels_info(ndev);
+		if (err)
+			return err;
 
-	teardown_driver(ndev);
+		teardown_driver(ndev);
+	}
 
 	mlx5_vdpa_update_mr(mvdev, new_mr, asid);
 
+	for (int i = 0; i < ndev->cur_num_vqs; i++)
+		ndev->vqs[i].modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY |
+						MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY;
+
 	if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK) || mvdev->suspended)
 		return 0;
 
-	restore_channels_info(ndev);
-	err = setup_driver(mvdev);
-	if (err)
-		return err;
+	if (teardown) {
+		restore_channels_info(ndev);
+		err = setup_driver(mvdev);
+		if (err)
+			return err;
+	}
+
+	resume_vqs(ndev);
 
 	return 0;
 }
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 32e712106e684..40371c916cf94 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -148,6 +148,7 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX       = (u64)1 << 7,
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX        = (u64)1 << 8,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY            = (u64)1 << 11,
 	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
-- 
GitLab


From a06bd11b18fdf2d40e2b81d4318abc6cc38e70c9 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:12:02 +0200
Subject: [PATCH 2493/4076] vdpa/mlx5: Introduce reference counting to mrs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Deleting the old mr during mr update (.set_map) and then modifying the
vqs with the new mr is not a good flow for firmware. The firmware
expects that mkeys are deleted after there are no more vqs referencing
them.

Introduce reference counting for mrs to fix this. It is the only way to
make sure that mkeys are not in use by vqs.

An mr reference is taken when the mr is associated to the mr asid table
and when the mr is linked to the vq on create/modify. The reference is
released when the mkey is unlinked from the vq (trough modify/destroy)
and from the mr asid table.

To make things consistent, get rid of mlx5_vdpa_destroy_mr and use
get/put semantics everywhere.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-8-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/core/mlx5_vdpa.h |  8 +++--
 drivers/vdpa/mlx5/core/mr.c        | 50 ++++++++++++++++++++----------
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 45 ++++++++++++++++++++++-----
 3 files changed, 78 insertions(+), 25 deletions(-)

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 84547d998bcf3..1a0d27b6e09af 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -35,6 +35,8 @@ struct mlx5_vdpa_mr {
 	struct vhost_iotlb *iotlb;
 
 	bool user_mr;
+
+	refcount_t refcount;
 };
 
 struct mlx5_vdpa_resources {
@@ -118,8 +120,10 @@ int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey);
 struct mlx5_vdpa_mr *mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
 					 struct vhost_iotlb *iotlb);
 void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev);
-void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev,
-			  struct mlx5_vdpa_mr *mr);
+void mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev,
+		      struct mlx5_vdpa_mr *mr);
+void mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev,
+		      struct mlx5_vdpa_mr *mr);
 void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
 			 struct mlx5_vdpa_mr *mr,
 			 unsigned int asid);
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 2197c46e563a1..c7dc8914354aa 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -498,32 +498,52 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr
 
 static void _mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
 {
+	if (WARN_ON(!mr))
+		return;
+
 	if (mr->user_mr)
 		destroy_user_mr(mvdev, mr);
 	else
 		destroy_dma_mr(mvdev, mr);
 
 	vhost_iotlb_free(mr->iotlb);
+
+	kfree(mr);
 }
 
-void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev,
-			  struct mlx5_vdpa_mr *mr)
+static void _mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev,
+			      struct mlx5_vdpa_mr *mr)
 {
 	if (!mr)
 		return;
 
+	if (refcount_dec_and_test(&mr->refcount))
+		_mlx5_vdpa_destroy_mr(mvdev, mr);
+}
+
+void mlx5_vdpa_put_mr(struct mlx5_vdpa_dev *mvdev,
+		      struct mlx5_vdpa_mr *mr)
+{
 	mutex_lock(&mvdev->mr_mtx);
+	_mlx5_vdpa_put_mr(mvdev, mr);
+	mutex_unlock(&mvdev->mr_mtx);
+}
 
-	_mlx5_vdpa_destroy_mr(mvdev, mr);
+static void _mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev,
+			      struct mlx5_vdpa_mr *mr)
+{
+	if (!mr)
+		return;
 
-	for (int i = 0; i < MLX5_VDPA_NUM_AS; i++) {
-		if (mvdev->mr[i] == mr)
-			mvdev->mr[i] = NULL;
-	}
+	refcount_inc(&mr->refcount);
+}
 
+void mlx5_vdpa_get_mr(struct mlx5_vdpa_dev *mvdev,
+		      struct mlx5_vdpa_mr *mr)
+{
+	mutex_lock(&mvdev->mr_mtx);
+	_mlx5_vdpa_get_mr(mvdev, mr);
 	mutex_unlock(&mvdev->mr_mtx);
-
-	kfree(mr);
 }
 
 void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
@@ -534,20 +554,16 @@ void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
 
 	mutex_lock(&mvdev->mr_mtx);
 
+	_mlx5_vdpa_put_mr(mvdev, old_mr);
 	mvdev->mr[asid] = new_mr;
-	if (old_mr) {
-		_mlx5_vdpa_destroy_mr(mvdev, old_mr);
-		kfree(old_mr);
-	}
 
 	mutex_unlock(&mvdev->mr_mtx);
-
 }
 
 void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
 {
 	for (int i = 0; i < MLX5_VDPA_NUM_AS; i++)
-		mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[i]);
+		mlx5_vdpa_update_mr(mvdev, NULL, i);
 
 	prune_iotlb(mvdev->cvq.iotlb);
 }
@@ -607,6 +623,8 @@ struct mlx5_vdpa_mr *mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
 	if (err)
 		goto out_err;
 
+	refcount_set(&mr->refcount, 1);
+
 	return mr;
 
 out_err:
@@ -651,7 +669,7 @@ int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
 	if (asid >= MLX5_VDPA_NUM_AS)
 		return -EINVAL;
 
-	mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[asid]);
+	mlx5_vdpa_update_mr(mvdev, NULL, asid);
 
 	if (asid == 0 && MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
 		if (mlx5_vdpa_create_dma_mr(mvdev))
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 6a21223d97a8e..133cbb66dcfe4 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -123,6 +123,9 @@ struct mlx5_vdpa_virtqueue {
 
 	u64 modified_fields;
 
+	struct mlx5_vdpa_mr *vq_mr;
+	struct mlx5_vdpa_mr *desc_mr;
+
 	struct msi_map map;
 
 	/* keep last in the struct */
@@ -946,6 +949,14 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	kfree(in);
 	mvq->virtq_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
 
+	mlx5_vdpa_get_mr(mvdev, vq_mr);
+	mvq->vq_mr = vq_mr;
+
+	if (vq_desc_mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported)) {
+		mlx5_vdpa_get_mr(mvdev, vq_desc_mr);
+		mvq->desc_mr = vq_desc_mr;
+	}
+
 	return 0;
 
 err_cmd:
@@ -972,6 +983,12 @@ static void destroy_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtq
 	}
 	mvq->fw_state = MLX5_VIRTIO_NET_Q_OBJECT_NONE;
 	umems_destroy(ndev, mvq);
+
+	mlx5_vdpa_put_mr(&ndev->mvdev, mvq->vq_mr);
+	mvq->vq_mr = NULL;
+
+	mlx5_vdpa_put_mr(&ndev->mvdev, mvq->desc_mr);
+	mvq->desc_mr = NULL;
 }
 
 static u32 get_rqpn(struct mlx5_vdpa_virtqueue *mvq, bool fw)
@@ -1207,6 +1224,8 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in);
 	u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {};
 	struct mlx5_vdpa_dev *mvdev = &ndev->mvdev;
+	struct mlx5_vdpa_mr *desc_mr = NULL;
+	struct mlx5_vdpa_mr *vq_mr = NULL;
 	bool state_change = false;
 	void *obj_context;
 	void *cmd_hdr;
@@ -1257,19 +1276,19 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 		MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx);
 
 	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY) {
-		struct mlx5_vdpa_mr *mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]];
+		vq_mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]];
 
-		if (mr)
-			MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, mr->mkey);
+		if (vq_mr)
+			MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, vq_mr->mkey);
 		else
 			mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY;
 	}
 
 	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY) {
-		struct mlx5_vdpa_mr *mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_DESC_GROUP]];
+		desc_mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_DESC_GROUP]];
 
-		if (mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported))
-			MLX5_SET(virtio_q, vq_ctx, desc_group_mkey, mr->mkey);
+		if (desc_mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported))
+			MLX5_SET(virtio_q, vq_ctx, desc_group_mkey, desc_mr->mkey);
 		else
 			mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY;
 	}
@@ -1282,6 +1301,18 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	if (state_change)
 		mvq->fw_state = state;
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY) {
+		mlx5_vdpa_put_mr(mvdev, mvq->vq_mr);
+		mlx5_vdpa_get_mr(mvdev, vq_mr);
+		mvq->vq_mr = vq_mr;
+	}
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY) {
+		mlx5_vdpa_put_mr(mvdev, mvq->desc_mr);
+		mlx5_vdpa_get_mr(mvdev, desc_mr);
+		mvq->desc_mr = desc_mr;
+	}
+
 	mvq->modified_fields = 0;
 
 done:
@@ -3095,7 +3126,7 @@ static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
 	return mlx5_vdpa_update_cvq_iotlb(mvdev, iotlb, asid);
 
 out_err:
-	mlx5_vdpa_destroy_mr(mvdev, new_mr);
+	mlx5_vdpa_put_mr(mvdev, new_mr);
 	return err;
 }
 
-- 
GitLab


From f16d65124380ac6de8055c4a8e5373a1043bb09b Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:12:03 +0200
Subject: [PATCH 2494/4076] vdpa/mlx5: Add mkey leak detection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Track allocated mrs in a list and show warning when leaks are detected
on device free or reset.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-9-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/core/mlx5_vdpa.h |  2 ++
 drivers/vdpa/mlx5/core/mr.c        | 23 +++++++++++++++++++++++
 drivers/vdpa/mlx5/net/mlx5_vnet.c  |  2 ++
 3 files changed, 27 insertions(+)

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 1a0d27b6e09af..50aac8fe57ef5 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -37,6 +37,7 @@ struct mlx5_vdpa_mr {
 	bool user_mr;
 
 	refcount_t refcount;
+	struct list_head mr_list;
 };
 
 struct mlx5_vdpa_resources {
@@ -95,6 +96,7 @@ struct mlx5_vdpa_dev {
 	u32 generation;
 
 	struct mlx5_vdpa_mr *mr[MLX5_VDPA_NUM_AS];
+	struct list_head mr_list_head;
 	/* serialize mr access */
 	struct mutex mr_mtx;
 	struct mlx5_control_vq cvq;
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index c7dc8914354aa..4758914ccf860 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -508,6 +508,8 @@ static void _mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_
 
 	vhost_iotlb_free(mr->iotlb);
 
+	list_del(&mr->mr_list);
+
 	kfree(mr);
 }
 
@@ -560,12 +562,31 @@ void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
 	mutex_unlock(&mvdev->mr_mtx);
 }
 
+static void mlx5_vdpa_show_mr_leaks(struct mlx5_vdpa_dev *mvdev)
+{
+	struct mlx5_vdpa_mr *mr;
+
+	mutex_lock(&mvdev->mr_mtx);
+
+	list_for_each_entry(mr, &mvdev->mr_list_head, mr_list) {
+
+		mlx5_vdpa_warn(mvdev, "mkey still alive after resource delete: "
+				      "mr: %p, mkey: 0x%x, refcount: %u\n",
+				       mr, mr->mkey, refcount_read(&mr->refcount));
+	}
+
+	mutex_unlock(&mvdev->mr_mtx);
+
+}
+
 void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
 {
 	for (int i = 0; i < MLX5_VDPA_NUM_AS; i++)
 		mlx5_vdpa_update_mr(mvdev, NULL, i);
 
 	prune_iotlb(mvdev->cvq.iotlb);
+
+	mlx5_vdpa_show_mr_leaks(mvdev);
 }
 
 static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
@@ -592,6 +613,8 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
 	if (err)
 		goto err_iotlb;
 
+	list_add_tail(&mr->mr_list, &mvdev->mr_list_head);
+
 	return 0;
 
 err_iotlb:
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 133cbb66dcfe4..778821bab7d93 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -3722,6 +3722,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	if (err)
 		goto err_mpfs;
 
+	INIT_LIST_HEAD(&mvdev->mr_list_head);
+
 	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
 		err = mlx5_vdpa_create_dma_mr(mvdev);
 		if (err)
-- 
GitLab


From 06c59d427017fcde3107c236177fcc74c9db7909 Mon Sep 17 00:00:00 2001
From: William Butler <wab@google.com>
Date: Wed, 10 Jan 2024 18:28:55 +0000
Subject: [PATCH 2495/4076] nvme-pci: set doorbell config before unquiescing

During resets, if queues are unquiesced first, then the host can submit
IOs to the controller using shadow doorbell logic but the controller
won't be aware. This can lead to necessary MMIO doorbells from being
not issued, causing requests to be delayed and timed-out.

Signed-off-by: William Butler <wab@google.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 75e763ce09aa0..46d3897b8986a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2746,10 +2746,10 @@ static void nvme_reset_work(struct work_struct *work)
 	 * controller around but remove all namespaces.
 	 */
 	if (dev->online_queues > 1) {
+		nvme_dbbuf_set(dev);
 		nvme_unquiesce_io_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
 		nvme_pci_update_nr_queues(dev);
-		nvme_dbbuf_set(dev);
 		nvme_unfreeze(&dev->ctrl);
 	} else {
 		dev_warn(dev->ctrl.device, "IO queues lost\n");
-- 
GitLab


From fe80eb15dea5125ea64845c9de0dd7f8478dd267 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 10 Jan 2024 10:05:32 -0700
Subject: [PATCH 2496/4076] io_uring/rw: cleanup io_rw_done()

This originally came from the aio side, and it's laid out rather oddly.
The common case here is that we either get -EIOCBQUEUED from submitting
an async request, or that we complete the request correctly with the
given number of bytes. Handling the odd internal restart error codes
is not a common operation.

Lay it out a bit more optimally that better explains the normal flow,
and switch to avoiding the indirect call completely as this is our
kiocb and we know the completion handler can only be one of two
possible variants. While at it, move it to where it belongs in the
file, with fellow end IO helpers.

Outside of being easier to read, this also reduces the text size of the
function by 24 bytes for me on arm64.

Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 48 +++++++++++++++++++++++++++---------------------
 1 file changed, 27 insertions(+), 21 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 0c856726b15db..118cc9f1cf160 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -168,27 +168,6 @@ void io_readv_writev_cleanup(struct io_kiocb *req)
 	kfree(io->free_iovec);
 }
 
-static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
-{
-	switch (ret) {
-	case -EIOCBQUEUED:
-		break;
-	case -ERESTARTSYS:
-	case -ERESTARTNOINTR:
-	case -ERESTARTNOHAND:
-	case -ERESTART_RESTARTBLOCK:
-		/*
-		 * We can't just restart the syscall, since previously
-		 * submitted sqes may already be in progress. Just fail this
-		 * IO with EINTR.
-		 */
-		ret = -EINTR;
-		fallthrough;
-	default:
-		kiocb->ki_complete(kiocb, ret);
-	}
-}
-
 static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
 {
 	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
@@ -371,6 +350,33 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	smp_store_release(&req->iopoll_completed, 1);
 }
 
+static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+{
+	/* IO was queued async, completion will happen later */
+	if (ret == -EIOCBQUEUED)
+		return;
+
+	/* transform internal restart error codes */
+	if (unlikely(ret < 0)) {
+		switch (ret) {
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+		case -ERESTARTNOHAND:
+		case -ERESTART_RESTARTBLOCK:
+			/*
+			 * We can't just restart the syscall, since previously
+			 * submitted sqes may already be in progress. Just fail
+			 * this IO with EINTR.
+			 */
+			ret = -EINTR;
+			break;
+		}
+	}
+
+	INDIRECT_CALL_2(kiocb->ki_complete, io_complete_rw_iopoll,
+			io_complete_rw, kiocb, ret);
+}
+
 static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 		       unsigned int issue_flags)
 {
-- 
GitLab


From 3e999770ac1c7c31a70685dd5b88e89473509e9c Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 9 Jan 2024 17:59:22 +0100
Subject: [PATCH 2497/4076] PM: sleep: Restore asynchronous device resume
 optimization

Before commit 7839d0078e0d ("PM: sleep: Fix possible deadlocks in core
system-wide PM code"), the resume of devices that were allowed to resume
asynchronously was scheduled before starting the resume of the other
devices, so the former did not have to wait for the latter unless
functional dependencies were present.

Commit 7839d0078e0d removed that optimization in order to address a
correctness issue, but it can be restored with the help of a new device
power management flag, so do that now.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
 drivers/base/power/main.c | 117 +++++++++++++++++++++-----------------
 include/linux/pm.h        |   1 +
 2 files changed, 65 insertions(+), 53 deletions(-)

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 9c5a5f4dba5a6..fadcd0379dc2d 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -579,7 +579,7 @@ bool dev_pm_skip_resume(struct device *dev)
 }
 
 /**
- * __device_resume_noirq - Execute a "noirq resume" callback for given device.
+ * device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
@@ -587,7 +587,7 @@ bool dev_pm_skip_resume(struct device *dev)
  * The driver of @dev will not receive interrupts while this function is being
  * executed.
  */
-static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async)
+static void device_resume_noirq(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -674,16 +674,22 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 {
 	reinit_completion(&dev->power.completion);
 
-	if (!is_async(dev))
-		return false;
-
-	get_device(dev);
+	if (is_async(dev)) {
+		dev->power.async_in_progress = true;
 
-	if (async_schedule_dev_nocall(func, dev))
-		return true;
+		get_device(dev);
 
-	put_device(dev);
+		if (async_schedule_dev_nocall(func, dev))
+			return true;
 
+		put_device(dev);
+	}
+	/*
+	 * Because async_schedule_dev_nocall() above has returned false or it
+	 * has not been called at all, func() is not running and it is safe to
+	 * update the async_in_progress flag without extra synchronization.
+	 */
+	dev->power.async_in_progress = false;
 	return false;
 }
 
@@ -691,18 +697,10 @@ static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume_noirq(dev, pm_transition, true);
+	device_resume_noirq(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume_noirq(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume_noirq))
-		return;
-
-	__device_resume_noirq(dev, pm_transition, false);
-}
-
 static void dpm_noirq_resume_devices(pm_message_t state)
 {
 	struct device *dev;
@@ -712,18 +710,28 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_noirq_list, power.entry)
+		dpm_async_fn(dev, async_resume_noirq);
+
 	while (!list_empty(&dpm_noirq_list)) {
 		dev = to_device(dpm_noirq_list.next);
-		get_device(dev);
 		list_move_tail(&dev->power.entry, &dpm_late_early_list);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			get_device(dev);
 
-		device_resume_noirq(dev);
+			mutex_unlock(&dpm_list_mtx);
 
-		put_device(dev);
+			device_resume_noirq(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
@@ -747,14 +755,14 @@ void dpm_resume_noirq(pm_message_t state)
 }
 
 /**
- * __device_resume_early - Execute an "early resume" callback for given device.
+ * device_resume_early - Execute an "early resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  *
  * Runtime PM is disabled for @dev while this function is being executed.
  */
-static void __device_resume_early(struct device *dev, pm_message_t state, bool async)
+static void device_resume_early(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -820,18 +828,10 @@ static void async_resume_early(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume_early(dev, pm_transition, true);
+	device_resume_early(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume_early(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume_early))
-		return;
-
-	__device_resume_early(dev, pm_transition, false);
-}
-
 /**
  * dpm_resume_early - Execute "early resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
@@ -845,18 +845,28 @@ void dpm_resume_early(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_late_early_list, power.entry)
+		dpm_async_fn(dev, async_resume_early);
+
 	while (!list_empty(&dpm_late_early_list)) {
 		dev = to_device(dpm_late_early_list.next);
-		get_device(dev);
 		list_move_tail(&dev->power.entry, &dpm_suspended_list);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			get_device(dev);
 
-		device_resume_early(dev);
+			mutex_unlock(&dpm_list_mtx);
 
-		put_device(dev);
+			device_resume_early(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
@@ -876,12 +886,12 @@ void dpm_resume_start(pm_message_t state)
 EXPORT_SYMBOL_GPL(dpm_resume_start);
 
 /**
- * __device_resume - Execute "resume" callbacks for given device.
+ * device_resume - Execute "resume" callbacks for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  */
-static void __device_resume(struct device *dev, pm_message_t state, bool async)
+static void device_resume(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -975,18 +985,10 @@ static void async_resume(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume(dev, pm_transition, true);
+	device_resume(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume))
-		return;
-
-	__device_resume(dev, pm_transition, false);
-}
-
 /**
  * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
  * @state: PM transition of the system being carried out.
@@ -1006,16 +1008,25 @@ void dpm_resume(pm_message_t state)
 	pm_transition = state;
 	async_error = 0;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry)
+		dpm_async_fn(dev, async_resume);
+
 	while (!list_empty(&dpm_suspended_list)) {
 		dev = to_device(dpm_suspended_list.next);
 
 		get_device(dev);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			mutex_unlock(&dpm_list_mtx);
 
-		device_resume(dev);
+			device_resume(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			mutex_lock(&dpm_list_mtx);
+		}
 
 		if (!list_empty(&dev->power.entry))
 			list_move_tail(&dev->power.entry, &dpm_prepared_list);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 92a4f69de0e80..a2f3e53a8196d 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -681,6 +681,7 @@ struct dev_pm_info {
 	bool			wakeup_path:1;
 	bool			syscore:1;
 	bool			no_pm_callbacks:1;	/* Owned by the PM core */
+	bool			async_in_progress:1;	/* Owned by the PM core */
 	unsigned int		must_resume:1;	/* Owned by the PM core */
 	unsigned int		may_skip_resume:1;	/* Set by subsystems */
 #else
-- 
GitLab


From 07a29b134ce8e47aef15ea71eab8e6b3734a9720 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 8 Dec 2023 13:53:20 +0100
Subject: [PATCH 2498/4076] nvmet-tcp: avoid circular locking dependency on
 install_queue()

nvmet_tcp_install_queue() is driven from the ->io_work workqueue
function, but will call flush_workqueue() which might trigger
->release_work() which in itself calls flush_work on ->io_work.

To avoid that check for pending queue in disconnecting status,
and return 'controller busy' when we reached a certain threshold.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 4dc60cbcb205b..6a1e6bb80062d 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -25,6 +25,7 @@
 
 #define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
 #define NVMET_TCP_MAXH2CDATA		0x400000 /* 16M arbitrary limit */
+#define NVMET_TCP_BACKLOG 128
 
 static int param_store_val(const char *str, int *val, int min, int max)
 {
@@ -2067,7 +2068,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 		goto err_sock;
 	}
 
-	ret = kernel_listen(port->sock, 128);
+	ret = kernel_listen(port->sock, NVMET_TCP_BACKLOG);
 	if (ret) {
 		pr_err("failed to listen %d on port sock\n", ret);
 		goto err_sock;
@@ -2133,8 +2134,19 @@ static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq)
 		container_of(sq, struct nvmet_tcp_queue, nvme_sq);
 
 	if (sq->qid == 0) {
-		/* Let inflight controller teardown complete */
-		flush_workqueue(nvmet_wq);
+		struct nvmet_tcp_queue *q;
+		int pending = 0;
+
+		/* Check for pending controller teardown */
+		mutex_lock(&nvmet_tcp_queue_mutex);
+		list_for_each_entry(q, &nvmet_tcp_queue_list, queue_list) {
+			if (q->nvme_sq.ctrl == sq->ctrl &&
+			    q->state == NVMET_TCP_Q_DISCONNECTING)
+				pending++;
+		}
+		mutex_unlock(&nvmet_tcp_queue_mutex);
+		if (pending > NVMET_TCP_BACKLOG)
+			return NVME_SC_CONNECT_CTRL_BUSY;
 	}
 
 	queue->nr_cmds = sq->size * 2;
-- 
GitLab


From 31deaeb11ba7a885116c9c30892b9f763c04d59c Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 8 Dec 2023 13:53:21 +0100
Subject: [PATCH 2499/4076] nvmet-rdma: avoid circular locking dependency on
 install_queue()

nvmet_rdma_install_queue() is driven from the ->io_work workqueue
function, but will call flush_workqueue() which might trigger
->release_work() which in itself calls flush_work on ->io_work.

To avoid that check for pending queue in disconnecting status,
and return 'controller busy' when we reached a certain threshold.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/rdma.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 4597bca43a6d8..667f9c04f35d5 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -37,6 +37,8 @@
 #define NVMET_RDMA_MAX_MDTS			8
 #define NVMET_RDMA_MAX_METADATA_MDTS		5
 
+#define NVMET_RDMA_BACKLOG 128
+
 struct nvmet_rdma_srq;
 
 struct nvmet_rdma_cmd {
@@ -1583,8 +1585,19 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
 	}
 
 	if (queue->host_qid == 0) {
-		/* Let inflight controller teardown complete */
-		flush_workqueue(nvmet_wq);
+		struct nvmet_rdma_queue *q;
+		int pending = 0;
+
+		/* Check for pending controller teardown */
+		mutex_lock(&nvmet_rdma_queue_mutex);
+		list_for_each_entry(q, &nvmet_rdma_queue_list, queue_list) {
+			if (q->nvme_sq.ctrl == queue->nvme_sq.ctrl &&
+			    q->state == NVMET_RDMA_Q_DISCONNECTING)
+				pending++;
+		}
+		mutex_unlock(&nvmet_rdma_queue_mutex);
+		if (pending > NVMET_RDMA_BACKLOG)
+			return NVME_SC_CONNECT_CTRL_BUSY;
 	}
 
 	ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
@@ -1880,7 +1893,7 @@ static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port)
 		goto out_destroy_id;
 	}
 
-	ret = rdma_listen(cm_id, 128);
+	ret = rdma_listen(cm_id, NVMET_RDMA_BACKLOG);
 	if (ret) {
 		pr_err("listening to %pISpcs failed (%d)\n", addr, ret);
 		goto out_destroy_id;
-- 
GitLab


From 78f70c02bdbccb5e9b0b0c728185d4aeb7044ace Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 9 Jan 2024 08:57:19 +0100
Subject: [PATCH 2500/4076] vfio/virtio: fix virtio-pci dependency

The new vfio-virtio driver already has a dependency on VIRTIO_PCI_ADMIN_LEGACY,
but that is a bool symbol and allows vfio-virtio to be built-in even if
virtio-pci itself is a loadable module. This leads to a link failure:

aarch64-linux-ld: drivers/vfio/pci/virtio/main.o: in function `virtiovf_pci_probe':
main.c:(.text+0xec): undefined reference to `virtio_pci_admin_has_legacy_io'
aarch64-linux-ld: drivers/vfio/pci/virtio/main.o: in function `virtiovf_pci_init_device':
main.c:(.text+0x260): undefined reference to `virtio_pci_admin_legacy_io_notify_info'
aarch64-linux-ld: drivers/vfio/pci/virtio/main.o: in function `virtiovf_pci_bar0_rw':
main.c:(.text+0x6ec): undefined reference to `virtio_pci_admin_legacy_common_io_read'
aarch64-linux-ld: main.c:(.text+0x6f4): undefined reference to `virtio_pci_admin_legacy_device_io_read'
aarch64-linux-ld: main.c:(.text+0x7f0): undefined reference to `virtio_pci_admin_legacy_common_io_write'
aarch64-linux-ld: main.c:(.text+0x7f8): undefined reference to `virtio_pci_admin_legacy_device_io_write'

Add another explicit dependency on the tristate symbol.

Fixes: eb61eca0e8c3 ("vfio/virtio: Introduce a vfio driver over virtio devices")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20240109075731.2726731-1-arnd@kernel.org
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/virtio/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/virtio/Kconfig b/drivers/vfio/pci/virtio/Kconfig
index fc3a0be9d8d42..bd80eca4a196c 100644
--- a/drivers/vfio/pci/virtio/Kconfig
+++ b/drivers/vfio/pci/virtio/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config VIRTIO_VFIO_PCI
         tristate "VFIO support for VIRTIO NET PCI devices"
-        depends on VIRTIO_PCI_ADMIN_LEGACY
+        depends on VIRTIO_PCI && VIRTIO_PCI_ADMIN_LEGACY
         select VFIO_PCI_CORE
         help
           This provides support for exposing VIRTIO NET VF devices which support
-- 
GitLab


From 5b202c250acd8dd1df9fcc8e6319ecd83d69923a Mon Sep 17 00:00:00 2001
From: Mark Hasemeyer <markhas@chromium.org>
Date: Tue, 2 Jan 2024 14:07:28 -0700
Subject: [PATCH 2501/4076] dt-bindings: power: Clarify wording for
 wakeup-source property

The wording in the current documentation is a little strong. The
intention was not to fix any particular interrupt as wakeup capable but
leave those details to the device. It wasn't intended to enforce any
rules as what can be or can't be a wakeup interrupt.

Soften the wording to not mandate that the 'wakeup-source' property be
used, and clarify what it means when an interrupt is marked (or not
marked) for wakeup.

Link: https://lore.kernel.org/all/ZYAjxxHcCOgDVMTQ@bogus/
Link: https://lore.kernel.org/all/CAL_Jsq+MYwOG40X26cYmO9EkZ9xqWrXDi03MaRfxnV-+VGkXWQ@mail.gmail.com/
Signed-off-by: Mark Hasemeyer <markhas@chromium.org>
Link: https://lore.kernel.org/r/20240102140734.v4.4.I1016a45ac9e8daf8a9ebc9854ab90ec3542e7c30@changeid
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../bindings/power/wakeup-source.txt           | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/Documentation/devicetree/bindings/power/wakeup-source.txt b/Documentation/devicetree/bindings/power/wakeup-source.txt
index 697333a56d5e2..75bc20b95688f 100644
--- a/Documentation/devicetree/bindings/power/wakeup-source.txt
+++ b/Documentation/devicetree/bindings/power/wakeup-source.txt
@@ -3,16 +3,20 @@ Specifying wakeup capability for devices
 
 Any device nodes
 ----------------
-Nodes that describe devices which has wakeup capability must contain an
+Nodes that describe devices which have wakeup capability may contain a
 "wakeup-source" boolean property.
 
-Also, if device is marked as a wakeup source, then all the primary
-interrupt(s) can be used as wakeup interrupt(s).
+If the device is marked as a wakeup-source, interrupt wake capability depends
+on the device specific "interrupt-names" property. If no interrupts are labeled
+as wake capable, then it is up to the device to determine which interrupts can
+wake the system.
 
-However if the devices have dedicated interrupt as the wakeup source
-then they need to specify/identify the same using device specific
-interrupt name. In such cases only that interrupt can be used as wakeup
-interrupt.
+However if a device has a dedicated interrupt as the wakeup source, then it
+needs to specify/identify it using a device specific interrupt name. In such
+cases only that interrupt can be used as a wakeup interrupt.
+
+While various legacy interrupt names exist, new devices should use "wakeup" as
+the canonical interrupt name.
 
 List of legacy properties and respective binding document
 ---------------------------------------------------------
-- 
GitLab


From d61b40bf15ce453f3aa71f6b423938e239e7f8f8 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 8 Jan 2024 18:17:34 -0800
Subject: [PATCH 2502/4076] xfs: fix backwards logic in xfs_bmap_alloc_account

We're only allocating from the realtime device if the inode is marked
for realtime and we're /not/ allocating into the attr fork.

Fixes: 58643460546d ("xfs: also use xfs_bmap_btalloc_accounting for RT allocations")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 98aaca933bddb..f362345467fac 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3277,7 +3277,7 @@ xfs_bmap_alloc_account(
 	struct xfs_bmalloca	*ap)
 {
 	bool			isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
-					(ap->flags & XFS_BMAPI_ATTRFORK);
+					!(ap->flags & XFS_BMAPI_ATTRFORK);
 	uint			fld;
 
 	if (ap->flags & XFS_BMAPI_COWFORK) {
-- 
GitLab


From e3977e0609a07d86406029fceea0fd40d7849368 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 9 Jan 2024 11:48:02 -1000
Subject: [PATCH 2503/4076] Revert "kernfs: convert kernfs_idr_lock to an irq
 safe raw spinlock"

This reverts commit dad3fb67ca1cbef87ce700e83a55835e5921ce8a.

The commit converted kernfs_idr_lock to an IRQ-safe raw_spinlock because it
could be acquired while holding an rq lock through bpf_cgroup_from_id().
However, kernfs_idr_lock is held while doing GPF_NOWAIT allocations which
involves acquiring an non-IRQ-safe and non-raw lock leading to the following
lockdep warning:

  =============================
  [ BUG: Invalid wait context ]
  6.7.0-rc5-kzm9g-00251-g655022a45b1c #578 Not tainted
  -----------------------------
  swapper/0/0 is trying to lock:
  dfbcd488 (&c->lock){....}-{3:3}, at: local_lock_acquire+0x0/0xa4
  other info that might help us debug this:
  context-{5:5}
  2 locks held by swapper/0/0:
   #0: dfbc9c60 (lock){+.+.}-{3:3}, at: local_lock_acquire+0x0/0xa4
   #1: c0c012a8 (kernfs_idr_lock){....}-{2:2}, at: __kernfs_new_node.constprop.0+0x68/0x258
  stack backtrace:
  CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.7.0-rc5-kzm9g-00251-g655022a45b1c #578
  Hardware name: Generic SH73A0 (Flattened Device Tree)
   unwind_backtrace from show_stack+0x10/0x14
   show_stack from dump_stack_lvl+0x68/0x90
   dump_stack_lvl from __lock_acquire+0x3cc/0x168c
   __lock_acquire from lock_acquire+0x274/0x30c
   lock_acquire from local_lock_acquire+0x28/0xa4
   local_lock_acquire from ___slab_alloc+0x234/0x8a8
   ___slab_alloc from __slab_alloc.constprop.0+0x30/0x44
   __slab_alloc.constprop.0 from kmem_cache_alloc+0x7c/0x148
   kmem_cache_alloc from radix_tree_node_alloc.constprop.0+0x44/0xdc
   radix_tree_node_alloc.constprop.0 from idr_get_free+0x110/0x2b8
   idr_get_free from idr_alloc_u32+0x9c/0x108
   idr_alloc_u32 from idr_alloc_cyclic+0x50/0xb8
   idr_alloc_cyclic from __kernfs_new_node.constprop.0+0x88/0x258
   __kernfs_new_node.constprop.0 from kernfs_create_root+0xbc/0x154
   kernfs_create_root from sysfs_init+0x18/0x5c
   sysfs_init from mnt_init+0xc4/0x220
   mnt_init from vfs_caches_init+0x6c/0x88
   vfs_caches_init from start_kernel+0x474/0x528
   start_kernel from 0x0

Let's rever the commit. It's undesirable to spread out raw spinlock usage
anyway and the problem can be solved by protecting the lookup path with RCU
instead.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Andrea Righi <andrea.righi@canonical.com>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: http://lkml.kernel.org/r/CAMuHMdV=AKt+mwY7svEq5gFPx41LoSQZ_USME5_MEdWQze13ww@mail.gmail.com
Link: https://lore.kernel.org/r/20240109214828.252092-2-tj@kernel.org
Tested-by: Andrea Righi <andrea.righi@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index a62960fdf73f0..bce1d7ac95caa 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -27,7 +27,7 @@ static DEFINE_RWLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
  */
 static DEFINE_SPINLOCK(kernfs_pr_cont_lock);
 static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by pr_cont_lock */
-static DEFINE_RAW_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
+static DEFINE_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
 
@@ -539,7 +539,6 @@ void kernfs_put(struct kernfs_node *kn)
 {
 	struct kernfs_node *parent;
 	struct kernfs_root *root;
-	unsigned long flags;
 
 	if (!kn || !atomic_dec_and_test(&kn->count))
 		return;
@@ -564,9 +563,9 @@ void kernfs_put(struct kernfs_node *kn)
 		simple_xattrs_free(&kn->iattr->xattrs, NULL);
 		kmem_cache_free(kernfs_iattrs_cache, kn->iattr);
 	}
-	raw_spin_lock_irqsave(&kernfs_idr_lock, flags);
+	spin_lock(&kernfs_idr_lock);
 	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
-	raw_spin_unlock_irqrestore(&kernfs_idr_lock, flags);
+	spin_unlock(&kernfs_idr_lock);
 	kmem_cache_free(kernfs_node_cache, kn);
 
 	kn = parent;
@@ -608,7 +607,6 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	struct kernfs_node *kn;
 	u32 id_highbits;
 	int ret;
-	unsigned long irqflags;
 
 	name = kstrdup_const(name, GFP_KERNEL);
 	if (!name)
@@ -619,13 +617,13 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 		goto err_out1;
 
 	idr_preload(GFP_KERNEL);
-	raw_spin_lock_irqsave(&kernfs_idr_lock, irqflags);
+	spin_lock(&kernfs_idr_lock);
 	ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
 	if (ret >= 0 && ret < root->last_id_lowbits)
 		root->id_highbits++;
 	id_highbits = root->id_highbits;
 	root->last_id_lowbits = ret;
-	raw_spin_unlock_irqrestore(&kernfs_idr_lock, irqflags);
+	spin_unlock(&kernfs_idr_lock);
 	idr_preload_end();
 	if (ret < 0)
 		goto err_out2;
@@ -661,9 +659,9 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	return kn;
 
  err_out3:
-	raw_spin_lock_irqsave(&kernfs_idr_lock, irqflags);
+	spin_lock(&kernfs_idr_lock);
 	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
-	raw_spin_unlock_irqrestore(&kernfs_idr_lock, irqflags);
+	spin_unlock(&kernfs_idr_lock);
  err_out2:
 	kmem_cache_free(kernfs_node_cache, kn);
  err_out1:
@@ -716,9 +714,8 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
 	struct kernfs_node *kn;
 	ino_t ino = kernfs_id_ino(id);
 	u32 gen = kernfs_id_gen(id);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&kernfs_idr_lock, flags);
+	spin_lock(&kernfs_idr_lock);
 
 	kn = idr_find(&root->ino_idr, (u32)ino);
 	if (!kn)
@@ -742,10 +739,10 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
 	if (unlikely(!__kernfs_active(kn) || !atomic_inc_not_zero(&kn->count)))
 		goto err_unlock;
 
-	raw_spin_unlock_irqrestore(&kernfs_idr_lock, flags);
+	spin_unlock(&kernfs_idr_lock);
 	return kn;
 err_unlock:
-	raw_spin_unlock_irqrestore(&kernfs_idr_lock, flags);
+	spin_unlock(&kernfs_idr_lock);
 	return NULL;
 }
 
-- 
GitLab


From 989cd9fd1ffe1a964429325f9092ea8f0db3f953 Mon Sep 17 00:00:00 2001
From: Kalle Valo <kvalo@kernel.org>
Date: Tue, 19 Dec 2023 18:25:16 +0200
Subject: [PATCH 2504/4076] wifi: p54: fix GCC format truncation warning with
 wiphy->fw_version

GCC 13.2 warns:

drivers/net/wireless/intersil/p54/fwio.c:128:34: warning: '%s' directive output may be truncated writing up to 39 bytes into a region of size 32 [-Wformat-truncation=]
drivers/net/wireless/intersil/p54/fwio.c:128:33: note: directive argument in the range [0, 16777215]
drivers/net/wireless/intersil/p54/fwio.c:128:33: note: directive argument in the range [0, 255]
drivers/net/wireless/intersil/p54/fwio.c:127:17: note: 'snprintf' output between 7 and 52 bytes into a destination of size 32

The issue here is that wiphy->fw_version is 32 bytes and in theory the string
we try to place there can be 39 bytes. wiphy->fw_version is used for providing
the firmware version to user space via ethtool, so not really important.
fw_version in theory can be 24 bytes but in practise it's shorter, so even if
print only 19 bytes via ethtool there should not be any practical difference.

I did consider removing fw_var from the string altogether or making the maximum
length for fw_version 19 bytes, but chose this approach as it was the least
intrusive.

Compile tested only.

Signed-off-by: Kalle Valo <kvalo@kernel.org>
Acked-by: Christian Lamparter <chunkeey@gmail.com> # Tested with Dell 1450 USB
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20231219162516.898205-1-kvalo@kernel.org
---
 drivers/net/wireless/intersil/p54/fwio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intersil/p54/fwio.c b/drivers/net/wireless/intersil/p54/fwio.c
index b52cce38115d0..c4fe70e05b9b8 100644
--- a/drivers/net/wireless/intersil/p54/fwio.c
+++ b/drivers/net/wireless/intersil/p54/fwio.c
@@ -125,7 +125,7 @@ int p54_parse_firmware(struct ieee80211_hw *dev, const struct firmware *fw)
 			   "FW rev %s - Softmac protocol %x.%x\n",
 			   fw_version, priv->fw_var >> 8, priv->fw_var & 0xff);
 		snprintf(dev->wiphy->fw_version, sizeof(dev->wiphy->fw_version),
-				"%s - %x.%x", fw_version,
+				"%.19s - %x.%x", fw_version,
 				priv->fw_var >> 8, priv->fw_var & 0xff);
 	}
 
-- 
GitLab


From 89c4b588d11e9acf01d604de4b0c715884f59213 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 10 Jan 2024 19:07:36 +0100
Subject: [PATCH 2505/4076] MIPS: Alchemy: Fix an out-of-bound access in
 db1200_dev_setup()

When calling spi_register_board_info(), we should pass the number of
elements in 'db1200_spi_devs', not 'db1200_i2c_devs'.

Fixes: 63323ec54a7e ("MIPS: Alchemy: Extended DB1200 board support.")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/alchemy/devboards/db1200.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c
index f521874ebb07b..67f067706af27 100644
--- a/arch/mips/alchemy/devboards/db1200.c
+++ b/arch/mips/alchemy/devboards/db1200.c
@@ -847,7 +847,7 @@ int __init db1200_dev_setup(void)
 	i2c_register_board_info(0, db1200_i2c_devs,
 				ARRAY_SIZE(db1200_i2c_devs));
 	spi_register_board_info(db1200_spi_devs,
-				ARRAY_SIZE(db1200_i2c_devs));
+				ARRAY_SIZE(db1200_spi_devs));
 
 	/* SWITCHES:	S6.8 I2C/SPI selector  (OFF=I2C	 ON=SPI)
 	 *		S6.7 AC97/I2S selector (OFF=AC97 ON=I2S)
-- 
GitLab


From 3c1e5abcda64bed0c7bffa65af2316995f269a61 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 10 Jan 2024 19:09:46 +0100
Subject: [PATCH 2506/4076] MIPS: Alchemy: Fix an out-of-bound access in
 db1550_dev_setup()

When calling spi_register_board_info(),

Fixes: f869d42e580f ("MIPS: Alchemy: Improved DB1550 support, with audio and serial busses.")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/alchemy/devboards/db1550.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c
index fd91d9c9a2525..6c6837181f555 100644
--- a/arch/mips/alchemy/devboards/db1550.c
+++ b/arch/mips/alchemy/devboards/db1550.c
@@ -589,7 +589,7 @@ int __init db1550_dev_setup(void)
 	i2c_register_board_info(0, db1550_i2c_devs,
 				ARRAY_SIZE(db1550_i2c_devs));
 	spi_register_board_info(db1550_spi_devs,
-				ARRAY_SIZE(db1550_i2c_devs));
+				ARRAY_SIZE(db1550_spi_devs));
 
 	c = clk_get(NULL, "psc0_intclk");
 	if (!IS_ERR(c)) {
-- 
GitLab


From 14b15aeb3628fc2fd1fe7f6c94f6ea7b1557bc27 Mon Sep 17 00:00:00 2001
From: Jim Quinlan <james.quinlan@broadcom.com>
Date: Mon, 13 Nov 2023 13:56:05 -0500
Subject: [PATCH 2507/4076] dt-bindings: PCI: brcmstb: Add property
 "brcm,clkreq-mode"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Broadcom STB/CM PCIe HW -- a core that is also used by RPi SOCs --
requires the driver to deliberately place the RC HW one of three CLKREQ#
modes.  The "brcm,clkreq-mode" property allows the user to override the
default setting.  If this property is omitted, the default mode shall be
"default".

Link: https://lore.kernel.org/linux-pci/20231113185607.1756-2-james.quinlan@broadcom.com
Tested-by: Cyril Brulebois <cyril@debamax.com>
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
---
 .../devicetree/bindings/pci/brcm,stb-pcie.yaml | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml b/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
index 7e15aae7d69e9..22491f7f88521 100644
--- a/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
@@ -64,6 +64,24 @@ properties:
 
   aspm-no-l0s: true
 
+  brcm,clkreq-mode:
+    description: A string that determines the operating
+      clkreq mode of the PCIe RC HW with respect to controlling the refclk
+      signal.  There are three different modes -- "safe", which drives the
+      refclk signal unconditionally and will work for all devices but does
+      not provide any power savings; "no-l1ss" -- which provides Clock
+      Power Management, L0s, and L1, but cannot provide L1 substate (L1SS)
+      power savings. If the downstream device connected to the RC is L1SS
+      capable AND the OS enables L1SS, all PCIe traffic may abruptly halt,
+      potentially hanging the system; "default" -- which provides L0s, L1,
+      and L1SS, but not compliant to provide Clock Power Management;
+      specifically, may not be able to meet the T_CLRon max timing of 400ns
+      as specified in "Dynamic Clock Control", section 3.2.5.2.2 PCI
+      Express Mini CEM 2.1 specification.  This situation is atypical and
+      should happen only with older devices.
+    $ref: /schemas/types.yaml#/definitions/string
+    enum: [ safe, no-l1ss, default ]
+
   brcm,scb-sizes:
     description: u64 giving the 64bit PCIe memory
       viewport size of a memory controller.  There may be up to
-- 
GitLab


From e2596dcf1e9dfd5904d50f796c19b03c94a3b8b4 Mon Sep 17 00:00:00 2001
From: Jim Quinlan <james.quinlan@broadcom.com>
Date: Mon, 13 Nov 2023 13:56:06 -0500
Subject: [PATCH 2508/4076] PCI: brcmstb: Configure HW CLKREQ# mode appropriate
 for downstream device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Broadcom STB/CM PCIe HW core, which is also used in RPi SOCs, must be
deliberately set by the PCIe RC HW into one of three mutually exclusive
modes:

"safe" -- No CLKREQ# expected or required, refclk is always provided.  This
    mode should work for all devices but is not be capable of any refclk
    power savings.

"no-l1ss" -- CLKREQ# is expected to be driven by the downstream device for
    CPM and ASPM L0s and L1.  Provides Clock Power Management, L0s, and L1,
    but cannot provide L1 substate (L1SS) power savings. If the downstream
    device connected to the RC is L1SS capable AND the OS enables L1SS, all
    PCIe traffic may abruptly halt, potentially hanging the system.

"default" -- Bidirectional CLKREQ# between the RC and downstream device.
    Provides ASPM L0s, L1, and L1SS, but not compliant to provide Clock
    Power Management; specifically, may not be able to meet the T_CLRon max
    timing of 400ns as specified in "Dynamic Clock Control", section
    3.2.5.2.2 of the PCIe Express Mini CEM 2.1 specification.  This
    situation is atypical and should happen only with older devices.

Previously, this driver always set the mode to "no-l1ss", as almost all
STB/CM boards operate in this mode.  But now there is interest in
activating L1SS power savings from STB/CM customers, which requires "aspm"
mode.  In addition, a bug was filed for RPi4 CM platform because most
devices did not work in "no-l1ss" mode.

Note that the mode is specified by the DT property "brcm,clkreq-mode".  If
this property is omitted, then "default" mode is chosen.

Note: Since L1 substates are now possible, a modification was made
regarding an internal bus timeout: During long periods of the PCIe RC HW
being in an L1SS sleep state, there may be a timeout on an internal bus
access, even though there may not be any PCIe access involved.  Such a
timeout will cause a subsequent CPU abort.

Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217276
Link: https://lore.kernel.org/linux-pci/20231113185607.1756-3-james.quinlan@broadcom.com
Tested-by: Cyril Brulebois <cyril@debamax.com>
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/controller/pcie-brcmstb.c | 96 ++++++++++++++++++++++++---
 1 file changed, 86 insertions(+), 10 deletions(-)

diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index f9dd6622fe109..5b0730c3891b8 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -48,6 +48,9 @@
 #define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY			0x04dc
 #define  PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK	0xc00
 
+#define PCIE_RC_CFG_PRIV1_ROOT_CAP			0x4f8
+#define  PCIE_RC_CFG_PRIV1_ROOT_CAP_L1SS_MODE_MASK	0xf8
+
 #define PCIE_RC_DL_MDIO_ADDR				0x1100
 #define PCIE_RC_DL_MDIO_WR_DATA				0x1104
 #define PCIE_RC_DL_MDIO_RD_DATA				0x1108
@@ -121,9 +124,12 @@
 
 #define PCIE_MISC_HARD_PCIE_HARD_DEBUG					0x4204
 #define  PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK	0x2
+#define  PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK		0x200000
 #define  PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK		0x08000000
 #define  PCIE_BMIPS_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK		0x00800000
-
+#define  PCIE_CLKREQ_MASK \
+	  (PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK | \
+	   PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK)
 
 #define PCIE_INTR2_CPU_BASE		0x4300
 #define PCIE_MSI_INTR2_BASE		0x4500
@@ -1028,13 +1034,89 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie)
 	return 0;
 }
 
+/*
+ * This extends the timeout period for an access to an internal bus.  This
+ * access timeout may occur during L1SS sleep periods, even without the
+ * presence of a PCIe access.
+ */
+static void brcm_extend_rbus_timeout(struct brcm_pcie *pcie)
+{
+	/* TIMEOUT register is two registers before RGR1_SW_INIT_1 */
+	const unsigned int REG_OFFSET = PCIE_RGR1_SW_INIT_1(pcie) - 8;
+	u32 timeout_us = 4000000; /* 4 seconds, our setting for L1SS */
+
+	/* Each unit in timeout register is 1/216,000,000 seconds */
+	writel(216 * timeout_us, pcie->base + REG_OFFSET);
+}
+
+static void brcm_config_clkreq(struct brcm_pcie *pcie)
+{
+	static const char err_msg[] = "invalid 'brcm,clkreq-mode' DT string\n";
+	const char *mode = "default";
+	u32 clkreq_cntl;
+	int ret, tmp;
+
+	ret = of_property_read_string(pcie->np, "brcm,clkreq-mode", &mode);
+	if (ret && ret != -EINVAL) {
+		dev_err(pcie->dev, err_msg);
+		mode = "safe";
+	}
+
+	/* Start out assuming safe mode (both mode bits cleared) */
+	clkreq_cntl = readl(pcie->base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+	clkreq_cntl &= ~PCIE_CLKREQ_MASK;
+
+	if (strcmp(mode, "no-l1ss") == 0) {
+		/*
+		 * "no-l1ss" -- Provides Clock Power Management, L0s, and
+		 * L1, but cannot provide L1 substate (L1SS) power
+		 * savings. If the downstream device connected to the RC is
+		 * L1SS capable AND the OS enables L1SS, all PCIe traffic
+		 * may abruptly halt, potentially hanging the system.
+		 */
+		clkreq_cntl |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK;
+		/*
+		 * We want to un-advertise L1 substates because if the OS
+		 * tries to configure the controller into using L1 substate
+		 * power savings it may fail or hang when the RC HW is in
+		 * "no-l1ss" mode.
+		 */
+		tmp = readl(pcie->base + PCIE_RC_CFG_PRIV1_ROOT_CAP);
+		u32p_replace_bits(&tmp, 2, PCIE_RC_CFG_PRIV1_ROOT_CAP_L1SS_MODE_MASK);
+		writel(tmp, pcie->base + PCIE_RC_CFG_PRIV1_ROOT_CAP);
+
+	} else if (strcmp(mode, "default") == 0) {
+		/*
+		 * "default" -- Provides L0s, L1, and L1SS, but not
+		 * compliant to provide Clock Power Management;
+		 * specifically, may not be able to meet the Tclron max
+		 * timing of 400ns as specified in "Dynamic Clock Control",
+		 * section 3.2.5.2.2 of the PCIe spec.  This situation is
+		 * atypical and should happen only with older devices.
+		 */
+		clkreq_cntl |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK;
+		brcm_extend_rbus_timeout(pcie);
+
+	} else {
+		/*
+		 * "safe" -- No power savings; refclk is driven by RC
+		 * unconditionally.
+		 */
+		if (strcmp(mode, "safe") != 0)
+			dev_err(pcie->dev, err_msg);
+		mode = "safe";
+	}
+	writel(clkreq_cntl, pcie->base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+
+	dev_info(pcie->dev, "clkreq-mode set to %s\n", mode);
+}
+
 static int brcm_pcie_start_link(struct brcm_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
 	void __iomem *base = pcie->base;
 	u16 nlw, cls, lnksta;
 	bool ssc_good = false;
-	u32 tmp;
 	int ret, i;
 
 	/* Unassert the fundamental reset */
@@ -1059,6 +1141,8 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie)
 		return -ENODEV;
 	}
 
+	brcm_config_clkreq(pcie);
+
 	if (pcie->gen)
 		brcm_pcie_set_gen(pcie, pcie->gen);
 
@@ -1077,14 +1161,6 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie)
 		 pci_speed_string(pcie_link_speed[cls]), nlw,
 		 ssc_good ? "(SSC)" : "(!SSC)");
 
-	/*
-	 * Refclk from RC should be gated with CLKREQ# input when ASPM L0s,L1
-	 * is enabled => setting the CLKREQ_DEBUG_ENABLE field to 1.
-	 */
-	tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
-	tmp |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK;
-	writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
-
 	return 0;
 }
 
-- 
GitLab


From 2ad62d16cd24b5e2f18318e97e1f06bef9f1ce7d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ma=C3=ADra=20Canal?= <mcanal@igalia.com>
Date: Tue, 9 Jan 2024 11:28:24 -0300
Subject: [PATCH 2509/4076] drm/v3d: Free the job and assign it to NULL if
 initialization fails
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, if `v3d_job_init()` fails (e.g. in the IGT test "bad-in-sync",
where we submit an invalid in-sync to the IOCTL), then we end up with
the following NULL pointer dereference:

[   34.146279] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000078
[   34.146301] Mem abort info:
[   34.146306]   ESR = 0x0000000096000005
[   34.146315]   EC = 0x25: DABT (current EL), IL = 32 bits
[   34.146322]   SET = 0, FnV = 0
[   34.146328]   EA = 0, S1PTW = 0
[   34.146334]   FSC = 0x05: level 1 translation fault
[   34.146340] Data abort info:
[   34.146345]   ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
[   34.146351]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[   34.146357]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[   34.146366] user pgtable: 4k pages, 39-bit VAs, pgdp=00000001232e6000
[   34.146375] [0000000000000078] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000
[   34.146399] Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP
[   34.146406] Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device algif_hash aes_neon_bs aes_neon_blk algif_skcipher af_alg bnep hid_logitech_hidpp brcmfmac_wcc brcmfmac brcmutil hci_uart vc4 btbcm cfg80211 bluetooth bcm2835_v4l2(C) snd_soc_hdmi_codec binfmt_misc cec drm_display_helper hid_logitech_dj bcm2835_mmal_vchiq(C) drm_dma_helper drm_kms_helper videobuf2_v4l2 raspberrypi_hwmon ecdh_generic videobuf2_vmalloc videobuf2_memops ecc videobuf2_common rfkill videodev libaes snd_soc_core dwc2 i2c_brcmstb snd_pcm_dmaengine snd_bcm2835(C) i2c_bcm2835 pwm_bcm2835 snd_pcm mc v3d snd_timer snd gpu_sched drm_shmem_helper nvmem_rmem uio_pdrv_genirq uio i2c_dev drm fuse dm_mod drm_panel_orientation_quirks backlight configfs ip_tables x_tables ipv6
[   34.146556] CPU: 1 PID: 1890 Comm: v3d_submit_csd Tainted: G         C         6.7.0-rc3-g49ddab089611 #68
[   34.146563] Hardware name: Raspberry Pi 4 Model B Rev 1.5 (DT)
[   34.146569] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   34.146575] pc : drm_sched_job_cleanup+0x3c/0x190 [gpu_sched]
[   34.146611] lr : v3d_submit_csd_ioctl+0x1b4/0x460 [v3d]
[   34.146653] sp : ffffffc083cbbb80
[   34.146658] x29: ffffffc083cbbb90 x28: ffffff81035afc00 x27: ffffffe77a641168
[   34.146668] x26: ffffff81056a8000 x25: 0000000000000058 x24: 0000000000000000
[   34.146677] x23: ffffff81065e2000 x22: ffffff81035afe00 x21: ffffffc083cbbcf0
[   34.146686] x20: ffffff81035afe00 x19: 00000000ffffffea x18: 0000000000000000
[   34.146694] x17: 0000000000000000 x16: ffffffe7989e34b0 x15: 0000000000000000
[   34.146703] x14: 0000000004000004 x13: ffffff81035afe80 x12: ffffffc083cb8000
[   34.146711] x11: cc57e05dfbe5ef00 x10: cc57e05dfbe5ef00 x9 : ffffffe77a64131c
[   34.146719] x8 : 0000000000000000 x7 : 0000000000000000 x6 : 000000000000003f
[   34.146727] x5 : 0000000000000040 x4 : ffffff81fefb03f0 x3 : ffffffc083cbba40
[   34.146736] x2 : ffffff81056a8000 x1 : ffffffe7989e35e8 x0 : 0000000000000000
[   34.146745] Call trace:
[   34.146748]  drm_sched_job_cleanup+0x3c/0x190 [gpu_sched]
[   34.146768]  v3d_submit_csd_ioctl+0x1b4/0x460 [v3d]
[   34.146791]  drm_ioctl_kernel+0xe0/0x120 [drm]
[   34.147029]  drm_ioctl+0x264/0x408 [drm]
[   34.147135]  __arm64_sys_ioctl+0x9c/0xe0
[   34.147152]  invoke_syscall+0x4c/0x118
[   34.147162]  el0_svc_common+0xb8/0xf0
[   34.147168]  do_el0_svc+0x28/0x40
[   34.147174]  el0_svc+0x38/0x88
[   34.147184]  el0t_64_sync_handler+0x84/0x100
[   34.147191]  el0t_64_sync+0x190/0x198
[   34.147201] Code: aa0003f4 f90007e8 f9401008 aa0803e0 (b8478c09)
[   34.147210] ---[ end trace 0000000000000000 ]---

This happens because we are calling `drm_sched_job_cleanup()` twice:
once at `v3d_job_init()` and again when we call `v3d_job_cleanup()`.

To mitigate this issue, we can return to the same approach that we used
to use before 464c61e76de8: deallocate the job after `v3d_job_init()`
fails and assign it to NULL. Then, when we call `v3d_job_cleanup()`, job
is NULL and the function returns.

Fixes: 464c61e76de8 ("drm/v3d: Decouple job allocation from job initiation")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240109142857.1122704-1-mcanal@igalia.com
---
 drivers/gpu/drm/v3d/v3d_submit.c | 35 +++++++++++++++++++++++++-------
 1 file changed, 28 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
index fcff41dd2315b..88f63d526b223 100644
--- a/drivers/gpu/drm/v3d/v3d_submit.c
+++ b/drivers/gpu/drm/v3d/v3d_submit.c
@@ -147,6 +147,13 @@ v3d_job_allocate(void **container, size_t size)
 	return 0;
 }
 
+static void
+v3d_job_deallocate(void **container)
+{
+	kfree(*container);
+	*container = NULL;
+}
+
 static int
 v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
 	     struct v3d_job *job, void (*free)(struct kref *ref),
@@ -273,8 +280,10 @@ v3d_setup_csd_jobs_and_bos(struct drm_file *file_priv,
 
 	ret = v3d_job_init(v3d, file_priv, &(*job)->base,
 			   v3d_job_free, args->in_sync, se, V3D_CSD);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)job);
 		return ret;
+	}
 
 	ret = v3d_job_allocate((void *)clean_job, sizeof(**clean_job));
 	if (ret)
@@ -282,8 +291,10 @@ v3d_setup_csd_jobs_and_bos(struct drm_file *file_priv,
 
 	ret = v3d_job_init(v3d, file_priv, *clean_job,
 			   v3d_job_free, 0, NULL, V3D_CACHE_CLEAN);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)clean_job);
 		return ret;
+	}
 
 	(*job)->args = *args;
 
@@ -860,8 +871,10 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 	ret = v3d_job_init(v3d, file_priv, &render->base,
 			   v3d_render_job_free, args->in_sync_rcl, &se, V3D_RENDER);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)&render);
 		goto fail;
+	}
 
 	render->start = args->rcl_start;
 	render->end = args->rcl_end;
@@ -874,8 +887,10 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 		ret = v3d_job_init(v3d, file_priv, &bin->base,
 				   v3d_job_free, args->in_sync_bcl, &se, V3D_BIN);
-		if (ret)
+		if (ret) {
+			v3d_job_deallocate((void *)&bin);
 			goto fail;
+		}
 
 		bin->start = args->bcl_start;
 		bin->end = args->bcl_end;
@@ -892,8 +907,10 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 		ret = v3d_job_init(v3d, file_priv, clean_job,
 				   v3d_job_free, 0, NULL, V3D_CACHE_CLEAN);
-		if (ret)
+		if (ret) {
+			v3d_job_deallocate((void *)&clean_job);
 			goto fail;
+		}
 
 		last_job = clean_job;
 	} else {
@@ -1015,8 +1032,10 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
 
 	ret = v3d_job_init(v3d, file_priv, &job->base,
 			   v3d_job_free, args->in_sync, &se, V3D_TFU);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)&job);
 		goto fail;
+	}
 
 	job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles),
 			       sizeof(*job->base.bo), GFP_KERNEL);
@@ -1233,8 +1252,10 @@ v3d_submit_cpu_ioctl(struct drm_device *dev, void *data,
 
 	ret = v3d_job_init(v3d, file_priv, &cpu_job->base,
 			   v3d_job_free, 0, &se, V3D_CPU);
-	if (ret)
+	if (ret) {
+		v3d_job_deallocate((void *)&cpu_job);
 		goto fail;
+	}
 
 	clean_job = cpu_job->indirect_csd.clean_job;
 	csd_job = cpu_job->indirect_csd.job;
-- 
GitLab


From 4dc4af9ce32681fbd16aa0e757ccba341cc9d4ca Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 6 Dec 2023 12:08:09 +0100
Subject: [PATCH 2510/4076] riscv: sbi: Introduce system suspend support

When the SUSP SBI extension is present it implies that the standard
"suspend to RAM" type is available. Wire it up to the generic
platform suspend support, also applying the already present support
for non-retentive CPU suspend. When the kernel is built with
CONFIG_SUSPEND, one can do 'echo mem > /sys/power/state' to suspend.
Resumption will occur when a platform-specific wake-up event arrives.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231206110807.35882-4-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig           |  2 +-
 arch/riscv/include/asm/sbi.h |  9 ++++++++
 arch/riscv/kernel/suspend.c  | 44 ++++++++++++++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 3db3d0fa046ef..e0e7cb89ee349 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -66,7 +66,7 @@ config RISCV
 	select CLINT_TIMER if !MMU
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select CPU_PM if CPU_IDLE || HIBERNATION
+	select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
 	select EDAC_SUPPORT
 	select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
 	select GENERIC_ARCH_TOPOLOGY
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 0892f4421bc4a..f09356e187dfc 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -29,6 +29,7 @@ enum sbi_ext_id {
 	SBI_EXT_RFENCE = 0x52464E43,
 	SBI_EXT_HSM = 0x48534D,
 	SBI_EXT_SRST = 0x53525354,
+	SBI_EXT_SUSP = 0x53555350,
 	SBI_EXT_PMU = 0x504D55,
 	SBI_EXT_DBCN = 0x4442434E,
 
@@ -114,6 +115,14 @@ enum sbi_srst_reset_reason {
 	SBI_SRST_RESET_REASON_SYS_FAILURE,
 };
 
+enum sbi_ext_susp_fid {
+	SBI_EXT_SUSP_SYSTEM_SUSPEND = 0,
+};
+
+enum sbi_ext_susp_sleep_type {
+	SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM = 0,
+};
+
 enum sbi_ext_pmu_fid {
 	SBI_EXT_PMU_NUM_COUNTERS = 0,
 	SBI_EXT_PMU_COUNTER_GET_INFO,
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 3c89b8ec69c49..239509367e423 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -4,8 +4,12 @@
  * Copyright (c) 2022 Ventana Micro Systems Inc.
  */
 
+#define pr_fmt(fmt) "suspend: " fmt
+
 #include <linux/ftrace.h>
+#include <linux/suspend.h>
 #include <asm/csr.h>
+#include <asm/sbi.h>
 #include <asm/suspend.h>
 
 void suspend_save_csrs(struct suspend_context *context)
@@ -85,3 +89,43 @@ int cpu_suspend(unsigned long arg,
 
 	return rc;
 }
+
+#ifdef CONFIG_RISCV_SBI
+static int sbi_system_suspend(unsigned long sleep_type,
+			      unsigned long resume_addr,
+			      unsigned long opaque)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_SUSP, SBI_EXT_SUSP_SYSTEM_SUSPEND,
+			sleep_type, resume_addr, opaque, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+
+	return ret.value;
+}
+
+static int sbi_system_suspend_enter(suspend_state_t state)
+{
+	return cpu_suspend(SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM, sbi_system_suspend);
+}
+
+static const struct platform_suspend_ops sbi_system_suspend_ops = {
+	.valid = suspend_valid_only_mem,
+	.enter = sbi_system_suspend_enter,
+};
+
+static int __init sbi_system_suspend_init(void)
+{
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_SUSP) > 0) {
+		pr_info("SBI SUSP extension detected\n");
+		if (IS_ENABLED(CONFIG_SUSPEND))
+			suspend_set_ops(&sbi_system_suspend_ops);
+	}
+
+	return 0;
+}
+
+arch_initcall(sbi_system_suspend_init);
+#endif /* CONFIG_RISCV_SBI */
-- 
GitLab


From a452816132d699bbb2af6fab8530685306054bda Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Wed, 27 Dec 2023 09:57:38 -0800
Subject: [PATCH 2511/4076] dt-bindings: riscv: cpus: Clarify mmu-type
 interpretation

The current description implies that only a single address translation
mode is available to the operating system. However, some implementations
support multiple address translation modes, and the operating system is
free to choose between them.

Per the RISC-V privileged specification, Sv48 implementations must also
implement Sv39, and likewise Sv57 implies support for Sv48. This means
it is possible to describe all supported address translation modes using
a single value, by naming the largest supported mode. This appears to
have been the intended usage of the property, so note it explicitly.

Fixes: 4fd669a8c487 ("dt-bindings: riscv: convert cpu binding to json-schema")
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231227175739.1453782-1-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/cpus.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index 23646b684ea27..72f8af4828185 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -63,8 +63,8 @@ properties:
 
   mmu-type:
     description:
-      Identifies the MMU address translation mode used on this
-      hart.  These values originate from the RISC-V Privileged
+      Identifies the largest MMU address translation mode supported by
+      this hart.  These values originate from the RISC-V Privileged
       Specification document, available from
       https://riscv.org/specifications/
     $ref: /schemas/types.yaml#/definitions/string
-- 
GitLab


From 07df87c0f8815898cb994408c4b6dd542a1394b8 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Fri, 8 Dec 2023 16:06:51 +0000
Subject: [PATCH 2512/4076] dt-bindings: riscv: permit numbers in "riscv,isa"

There are some extensions that contain numbers, such as Zve32f, which
are enabled by the "max" cpu type in QEMU.

Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231208-uncolored-oxidant-5ab37dd3ab84@spud
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/extensions.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index 27beedb981987..63d81dc895e5c 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -48,7 +48,7 @@ properties:
       insensitive, letters in the riscv,isa string must be all
       lowercase.
     $ref: /schemas/types.yaml#/definitions/string
-    pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$
+    pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[0-9a-z])+)?(?:_[hsxz](?:[0-9a-z])+)*$
     deprecated: true
 
   riscv,isa-base:
-- 
GitLab


From d3e591a38c98d448ae84eba1f89388c55382cb0e Mon Sep 17 00:00:00 2001
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Date: Sun, 29 Oct 2023 09:35:00 -0300
Subject: [PATCH 2513/4076] dt-bindings: riscv: Document cbop-block-size

Following the examples of cbom-block-size and cboz-block-size,
cbop-block-size is the cache size of Zicbop (cbo.prefetch) operations.
The most common case is to have all cache block sizes to be the same
size (e.g. profiles such as rva22u64 mandates a 64 bytes size for all
cache operations), but there's no specification requirement for that,
and an implementation can have different cache sizes for each operation.

Cc: Rob Herring <robh@kernel.org>
Cc: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231029123500.739409-1-dbarboza@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 Documentation/devicetree/bindings/riscv/cpus.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index 72f8af4828185..9d8670c00e3b3 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -80,6 +80,11 @@ properties:
     description:
       The blocksize in bytes for the Zicbom cache operations.
 
+  riscv,cbop-block-size:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      The blocksize in bytes for the Zicbop cache operations.
+
   riscv,cboz-block-size:
     $ref: /schemas/types.yaml#/definitions/uint32
     description:
-- 
GitLab


From e3b3ec967a7d93b9010a5af9a2394c8b5c8f31ed Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Date: Thu, 11 Jan 2024 11:52:26 +0100
Subject: [PATCH 2514/4076] ASoC: mediatek: sof-common: Add NULL check for
 normal_link string

It's not granted that all entries of struct sof_conn_stream declare
a `normal_link` (a non-SOF, direct link) string, and this is the case
for SoCs that support only SOF paths (hence do not support both direct
and SOF usecases).

For example, in the case of MT8188 there is no normal_link string in
any of the sof_conn_stream entries and there will be more drivers
doing that in the future.

To avoid possible NULL pointer KPs, add a NULL check for `normal_link`.

Fixes: 0caf1120c583 ("ASoC: mediatek: mt8195: extract SOF common code")
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://msgid.link/r/20240111105226.117603-1-angelogioacchino.delregno@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/mediatek/common/mtk-dsp-sof-common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/mediatek/common/mtk-dsp-sof-common.c b/sound/soc/mediatek/common/mtk-dsp-sof-common.c
index f3894010f6563..7ec8965a70c06 100644
--- a/sound/soc/mediatek/common/mtk-dsp-sof-common.c
+++ b/sound/soc/mediatek/common/mtk-dsp-sof-common.c
@@ -24,7 +24,7 @@ int mtk_sof_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 		struct snd_soc_dai_link *sof_dai_link = NULL;
 		const struct sof_conn_stream *conn = &sof_priv->conn_streams[i];
 
-		if (strcmp(rtd->dai_link->name, conn->normal_link))
+		if (conn->normal_link && strcmp(rtd->dai_link->name, conn->normal_link))
 			continue;
 
 		for_each_card_rtds(card, runtime) {
-- 
GitLab


From ff172d4818ad32dba433dae189e36684e43c5c74 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Thu, 14 Dec 2023 14:29:35 +0100
Subject: [PATCH 2515/4076] riscv: Use hugepage mappings for vmemmap

This will allow better TLB utilization and then should be more performant.

Before:

---[ vmemmap start ]---
0xffff8d8002000000-0xffff8d8012000000    0x000000046ec00000       256M PTE .   ..     ..   D A G . . W R V
---[ vmemmap end ]---

After:

---[ vmemmap start ]---
0xffff8d8002000000-0xffff8d8012000000    0x000000046ec00000       256M PMD .   ..     ..   D A G . . W R V
---[ vmemmap end ]---

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20231214132935.212864-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/init.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index a65937336cdc8..f533dd667a83a 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1387,10 +1387,29 @@ void __init misc_mem_init(void)
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+			       unsigned long addr, unsigned long next)
+{
+	pmd_set_huge(pmd, virt_to_phys(p), PAGE_KERNEL);
+}
+
+int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
+				unsigned long addr, unsigned long next)
+{
+	vmemmap_verify((pte_t *)pmdp, node, addr, next);
+	return 1;
+}
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 			       struct vmem_altmap *altmap)
 {
-	return vmemmap_populate_basepages(start, end, node, NULL);
+	/*
+	 * Note that SPARSEMEM_VMEMMAP is only selected for rv64 and that we
+	 * can't use hugepage mappings for 2-level page table because in case of
+	 * memory hotplug, we are not able to update all the page tables with
+	 * the new PMDs.
+	 */
+	return vmemmap_populate_hugepages(start, end, node, NULL);
 }
 #endif
 
-- 
GitLab


From 54d7431af73e2fa53b73cfeb2bec559c6664a4e4 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Mon, 8 Jan 2024 20:36:40 +0100
Subject: [PATCH 2516/4076] riscv: Add support for BATCHED_UNMAP_TLB_FLUSH

Allow to defer the flushing of the TLB when unmapping pages, which allows
to reduce the numbers of IPI and the number of sfence.vma.

The ubenchmarch used in commit 43b3dfdd0455 ("arm64: support
batched/deferred tlb shootdown during page reclamation/migration") that
was multithreaded to force the usage of IPI shows good performance
improvement on all platforms:

* Unmatched: ~34%
* TH1520   : ~78%
* Qemu     : ~81%

In addition, perf on qemu reports an important decrease in time spent
dealing with IPIs:

Before:  68.17%  main     [kernel.kallsyms]            [k] __sbi_rfence_v02_call
After :   8.64%  main     [kernel.kallsyms]            [k] __sbi_rfence_v02_call

* Benchmark:

int stick_this_thread_to_core(int core_id) {
        int num_cores = sysconf(_SC_NPROCESSORS_ONLN);
        if (core_id < 0 || core_id >= num_cores)
           return EINVAL;

        cpu_set_t cpuset;
        CPU_ZERO(&cpuset);
        CPU_SET(core_id, &cpuset);

        pthread_t current_thread = pthread_self();
        return pthread_setaffinity_np(current_thread,
sizeof(cpu_set_t), &cpuset);
}

static void *fn_thread (void *p_data)
{
        int ret;
        pthread_t thread;

        stick_this_thread_to_core((int)p_data);

        while (1) {
                sleep(1);
        }

        return NULL;
}

int main()
{
        volatile unsigned char *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE,
                                         MAP_SHARED | MAP_ANONYMOUS, -1, 0);
        pthread_t threads[4];
        int ret;

        for (int i = 0; i < 4; ++i) {
                ret = pthread_create(&threads[i], NULL, fn_thread, (void *)i);
                if (ret)
                {
                        printf("%s", strerror (ret));
                }
        }

        memset(p, 0x88, SIZE);

        for (int k = 0; k < 10000; k++) {
                /* swap in */
                for (int i = 0; i < SIZE; i += 4096) {
                        (void)p[i];
                }

                /* swap out */
                madvise(p, SIZE, MADV_PAGEOUT);
        }

        for (int i = 0; i < 4; i++)
        {
                pthread_cancel(threads[i]);
        }

        for (int i = 0; i < 4; i++)
        {
                pthread_join(threads[i], NULL);
        }

        return 0;
}

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Jisheng Zhang <jszhang@kernel.org>
Tested-by: Jisheng Zhang <jszhang@kernel.org> # Tested on TH1520
Tested-by: Nam Cao <namcao@linutronix.de>
Link: https://lore.kernel.org/r/20240108193640.344929-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 .../features/vm/TLB/arch-support.txt          |  2 +-
 arch/riscv/Kconfig                            |  1 +
 arch/riscv/include/asm/tlbbatch.h             | 15 ++++
 arch/riscv/include/asm/tlbflush.h             |  8 +++
 arch/riscv/mm/tlbflush.c                      | 69 +++++++++++++------
 5 files changed, 74 insertions(+), 21 deletions(-)
 create mode 100644 arch/riscv/include/asm/tlbbatch.h

diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt
index 8fd22073a847e..d222bd3ee7495 100644
--- a/Documentation/features/vm/TLB/arch-support.txt
+++ b/Documentation/features/vm/TLB/arch-support.txt
@@ -20,7 +20,7 @@
     |    openrisc: |  ..  |
     |      parisc: | TODO |
     |     powerpc: | TODO |
-    |       riscv: | TODO |
+    |       riscv: |  ok  |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index e0e7cb89ee349..d42155c29a55b 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -53,6 +53,7 @@ config RISCV
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USES_CFI_TRAPS if CFI_CLANG
+	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP && MMU
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT
diff --git a/arch/riscv/include/asm/tlbbatch.h b/arch/riscv/include/asm/tlbbatch.h
new file mode 100644
index 0000000000000..46014f70b9daa
--- /dev/null
+++ b/arch/riscv/include/asm/tlbbatch.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+#ifndef _ASM_RISCV_TLBBATCH_H
+#define _ASM_RISCV_TLBBATCH_H
+
+#include <linux/cpumask.h>
+
+struct arch_tlbflush_unmap_batch {
+	struct cpumask cpumask;
+};
+
+#endif /* _ASM_RISCV_TLBBATCH_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 8f3418c5f1724..9c8a67b1285ec 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -46,6 +46,14 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end);
 #endif
+
+bool arch_tlbbatch_should_defer(struct mm_struct *mm);
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+			       struct mm_struct *mm,
+			       unsigned long uaddr);
+void arch_flush_tlb_batched_pending(struct mm_struct *mm);
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+
 #else /* CONFIG_SMP && CONFIG_MMU */
 
 #define flush_tlb_all() local_flush_tlb_all()
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index e6659d7368b35..f0190f5fdd050 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -93,29 +93,23 @@ static void __ipi_flush_tlb_range_asid(void *info)
 	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
 }
 
-static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
-			      unsigned long size, unsigned long stride)
+static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
+			      unsigned long start, unsigned long size,
+			      unsigned long stride)
 {
 	struct flush_tlb_range_data ftd;
-	const struct cpumask *cmask;
-	unsigned long asid = FLUSH_TLB_NO_ASID;
 	bool broadcast;
 
-	if (mm) {
-		unsigned int cpuid;
+	if (cpumask_empty(cmask))
+		return;
 
-		cmask = mm_cpumask(mm);
-		if (cpumask_empty(cmask))
-			return;
+	if (cmask != cpu_online_mask) {
+		unsigned int cpuid;
 
 		cpuid = get_cpu();
 		/* check if the tlbflush needs to be sent to other CPUs */
 		broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
-
-		if (static_branch_unlikely(&use_asid_allocator))
-			asid = atomic_long_read(&mm->context.id) & asid_mask;
 	} else {
-		cmask = cpu_online_mask;
 		broadcast = true;
 	}
 
@@ -135,25 +129,34 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 		local_flush_tlb_range_asid(start, size, stride, asid);
 	}
 
-	if (mm)
+	if (cmask != cpu_online_mask)
 		put_cpu();
 }
 
+static inline unsigned long get_mm_asid(struct mm_struct *mm)
+{
+	return static_branch_unlikely(&use_asid_allocator) ?
+			atomic_long_read(&mm->context.id) & asid_mask : FLUSH_TLB_NO_ASID;
+}
+
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
+			  0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_mm_range(struct mm_struct *mm,
 			unsigned long start, unsigned long end,
 			unsigned int page_size)
 {
-	__flush_tlb_range(mm, start, end - start, page_size);
+	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
+			  start, end - start, page_size);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
-	__flush_tlb_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  addr, PAGE_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -185,18 +188,44 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		}
 	}
 
-	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  start, end - start, stride_size);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	__flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
+	__flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID,
+			  start, end - start, PAGE_SIZE);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
 {
-	__flush_tlb_range(vma->vm_mm, start, end - start, PMD_SIZE);
+	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+			  start, end - start, PMD_SIZE);
 }
 #endif
+
+bool arch_tlbbatch_should_defer(struct mm_struct *mm)
+{
+	return true;
+}
+
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+			       struct mm_struct *mm,
+			       unsigned long uaddr)
+{
+	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+}
+
+void arch_flush_tlb_batched_pending(struct mm_struct *mm)
+{
+	flush_tlb_mm(mm);
+}
+
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+	__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
+			  FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+}
-- 
GitLab


From b91c26fdb0e8150cdb610cdaadea62bb5e43bee0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christoph=20M=C3=BCllner?= <christoph.muellner@vrull.eu>
Date: Thu, 23 Nov 2023 19:58:17 +0100
Subject: [PATCH 2517/4076] tools: selftests: riscv: Fix compile warnings in
 hwprobe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC prints a couple of format string warnings when compiling
the hwprobe test. Let's follow the recommendation in
Documentation/printk-formats.txt to fix these warnings.

Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231123185821.2272504-2-christoph.muellner@vrull.eu
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/riscv/hwprobe/hwprobe.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c
index c474891df3071..abb825811c70e 100644
--- a/tools/testing/selftests/riscv/hwprobe/hwprobe.c
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c
@@ -29,7 +29,7 @@ int main(int argc, char **argv)
 		/* Fail if the kernel claims not to recognize a base key. */
 		if ((i < 4) && (pairs[i].key != i))
 			ksft_exit_fail_msg("Failed to recognize base key: key != i, "
-					   "key=%ld, i=%ld\n", pairs[i].key, i);
+					   "key=%lld, i=%ld\n", pairs[i].key, i);
 
 		if (pairs[i].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR)
 			continue;
@@ -37,7 +37,7 @@ int main(int argc, char **argv)
 		if (pairs[i].value & RISCV_HWPROBE_BASE_BEHAVIOR_IMA)
 			continue;
 
-		ksft_exit_fail_msg("Unexpected pair: (%ld, %ld)\n", pairs[i].key, pairs[i].value);
+		ksft_exit_fail_msg("Unexpected pair: (%lld, %llu)\n", pairs[i].key, pairs[i].value);
 	}
 
 	out = riscv_hwprobe(pairs, 8, 0, 0, 0);
-- 
GitLab


From ac7b2a02d62faff8c6d45bacb5cb9ea565b47776 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christoph=20M=C3=BCllner?= <christoph.muellner@vrull.eu>
Date: Thu, 23 Nov 2023 19:58:18 +0100
Subject: [PATCH 2518/4076] tools: selftests: riscv: Fix compile warnings in
 cbo
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC prints a couple of format string warnings when compiling
the cbo test. Let's follow the recommendation in
Documentation/printk-formats.txt to fix these warnings.

Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231123185821.2272504-3-christoph.muellner@vrull.eu
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/riscv/hwprobe/cbo.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c
index 50a2cc8aef387..c6a83ab11e223 100644
--- a/tools/testing/selftests/riscv/hwprobe/cbo.c
+++ b/tools/testing/selftests/riscv/hwprobe/cbo.c
@@ -97,7 +97,7 @@ static void test_zicboz(void *arg)
 	block_size = pair.value;
 	ksft_test_result(rc == 0 && pair.key == RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE &&
 			 is_power_of_2(block_size), "Zicboz block size\n");
-	ksft_print_msg("Zicboz block size: %ld\n", block_size);
+	ksft_print_msg("Zicboz block size: %llu\n", block_size);
 
 	illegal_insn = false;
 	cbo_zero(&mem[block_size]);
@@ -121,7 +121,7 @@ static void test_zicboz(void *arg)
 		for (j = 0; j < block_size; ++j) {
 			if (mem[i * block_size + j] != expected) {
 				ksft_test_result_fail("cbo.zero check\n");
-				ksft_print_msg("cbo.zero check: mem[%d] != 0x%x\n",
+				ksft_print_msg("cbo.zero check: mem[%llu] != 0x%x\n",
 					       i * block_size + j, expected);
 				return;
 			}
@@ -201,7 +201,7 @@ int main(int argc, char **argv)
 	pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
 	rc = riscv_hwprobe(&pair, 1, sizeof(cpu_set_t), (unsigned long *)&cpus, 0);
 	if (rc < 0)
-		ksft_exit_fail_msg("hwprobe() failed with %d\n", rc);
+		ksft_exit_fail_msg("hwprobe() failed with %ld\n", rc);
 	assert(rc == 0 && pair.key == RISCV_HWPROBE_KEY_IMA_EXT_0);
 
 	if (pair.value & RISCV_HWPROBE_EXT_ZICBOZ) {
-- 
GitLab


From b250c90898412878fe56f069b1a6b1b94a7bbdfa Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christoph=20M=C3=BCllner?= <christoph.muellner@vrull.eu>
Date: Thu, 23 Nov 2023 19:58:19 +0100
Subject: [PATCH 2519/4076] tools: selftests: riscv: Add missing include for
 vector test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC raises the following warning:
  warning: 'status' may be used uninitialized
The warning comes from the fact, that the signature of waitpid() is
unknown and therefore the initialization of GCC cannot be guessed.
Let's add the relevant header to address this warning.

Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andy Chiu <andy.chiu@sifive.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231123185821.2272504-4-christoph.muellner@vrull.eu
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
index 2c0d2b1126c1e..1f9969bed2355 100644
--- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
+++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
@@ -1,4 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/wait.h>
+
 #define THIS_PROGRAM "./vstate_exec_nolibc"
 
 int main(int argc, char **argv)
-- 
GitLab


From e1baf5e68ed128c1e22ba43e5190526d85de323c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christoph=20M=C3=BCllner?= <christoph.muellner@vrull.eu>
Date: Thu, 23 Nov 2023 19:58:20 +0100
Subject: [PATCH 2520/4076] tools: selftests: riscv: Fix compile warnings in
 vector tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC prints a couple of format string warnings when compiling
the vector tests. Let's follow the recommendation in
Documentation/printk-formats.txt to fix these warnings.

Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231123185821.2272504-5-christoph.muellner@vrull.eu
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/riscv/vector/v_initval_nolibc.c | 2 +-
 tools/testing/selftests/riscv/vector/vstate_prctl.c     | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
index 66764edb0d526..1dd94197da30c 100644
--- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
+++ b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
@@ -27,7 +27,7 @@ int main(void)
 
 	datap = malloc(MAX_VSIZE);
 	if (!datap) {
-		ksft_test_result_fail("fail to allocate memory for size = %lu\n", MAX_VSIZE);
+		ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE);
 		exit(-1);
 	}
 
diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c
index b348b475be570..8ad94e08ff4d0 100644
--- a/tools/testing/selftests/riscv/vector/vstate_prctl.c
+++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c
@@ -68,7 +68,7 @@ int test_and_compare_child(long provided, long expected, int inherit)
 	}
 	rc = launch_test(inherit);
 	if (rc != expected) {
-		ksft_test_result_fail("Test failed, check %d != %d\n", rc,
+		ksft_test_result_fail("Test failed, check %d != %ld\n", rc,
 				      expected);
 		return -2;
 	}
@@ -87,7 +87,7 @@ int main(void)
 	pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
 	rc = riscv_hwprobe(&pair, 1, 0, NULL, 0);
 	if (rc < 0) {
-		ksft_test_result_fail("hwprobe() failed with %d\n", rc);
+		ksft_test_result_fail("hwprobe() failed with %ld\n", rc);
 		return -1;
 	}
 
-- 
GitLab


From 12c16919652b5873f524c8b361336ecfa5ce5e6b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christoph=20M=C3=BCllner?= <christoph.muellner@vrull.eu>
Date: Thu, 23 Nov 2023 19:58:21 +0100
Subject: [PATCH 2521/4076] tools: selftests: riscv: Fix compile warnings in mm
 tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building the mm tests with a riscv32 compiler, we see a range
of shift-count-overflow errors from shifting 1UL by more than 32 bits
in do_mmaps(). Since, the relevant code is only called from code that
is gated by `__riscv_xlen == 64`, we can just apply the same gating
to do_mmaps().

Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231123185821.2272504-6-christoph.muellner@vrull.eu
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/riscv/mm/mmap_test.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/riscv/mm/mmap_test.h b/tools/testing/selftests/riscv/mm/mmap_test.h
index 9b8434f62f570..2e0db9c5be6c3 100644
--- a/tools/testing/selftests/riscv/mm/mmap_test.h
+++ b/tools/testing/selftests/riscv/mm/mmap_test.h
@@ -18,6 +18,8 @@ struct addresses {
 	int *on_56_addr;
 };
 
+// Only works on 64 bit
+#if __riscv_xlen == 64
 static inline void do_mmaps(struct addresses *mmap_addresses)
 {
 	/*
@@ -50,6 +52,7 @@ static inline void do_mmaps(struct addresses *mmap_addresses)
 	mmap_addresses->on_56_addr =
 		mmap(on_56_bits, 5 * sizeof(int), prot, flags, 0, 0);
 }
+#endif /* __riscv_xlen == 64 */
 
 static inline int memory_layout(void)
 {
-- 
GitLab


From adb1f95d388a43c4c564ef3e436f18900dde978e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 29 Oct 2023 08:20:40 +0100
Subject: [PATCH 2522/4076] riscv: Fix an off-by-one in get_early_cmdline()

The ending NULL is not taken into account by strncat(), so switch to
strlcat() to correctly compute the size of the available memory when
appending CONFIG_CMDLINE to 'early_cmdline'.

Fixes: 26e7aacb83df ("riscv: Allow to downgrade paging mode from the command line")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/9f66d2b58c8052d4055e90b8477ee55d9a0914f9.1698564026.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/pi/cmdline_early.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c
index 68e786c84c949..f6d4dedffb842 100644
--- a/arch/riscv/kernel/pi/cmdline_early.c
+++ b/arch/riscv/kernel/pi/cmdline_early.c
@@ -38,8 +38,7 @@ static char *get_early_cmdline(uintptr_t dtb_pa)
 	if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
 	    IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
 	    fdt_cmdline_size == 0 /* CONFIG_CMDLINE_FALLBACK */) {
-		strncat(early_cmdline, CONFIG_CMDLINE,
-			COMMAND_LINE_SIZE - fdt_cmdline_size);
+		strlcat(early_cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
 	}
 
 	return early_cmdline;
-- 
GitLab


From 5f449e245e5b0d9d63eef6c8968fbdc3a8594407 Mon Sep 17 00:00:00 2001
From: Guo Ren <guoren@linux.alibaba.com>
Date: Fri, 22 Dec 2023 06:57:00 -0500
Subject: [PATCH 2523/4076] riscv: mm: Fixup compat mode boot failure

In COMPAT mode, the STACK_TOP is DEFAULT_MAP_WINDOW (0x80000000), but
the TASK_SIZE is 0x7fff000. When the user stack is upon 0x7fff000, it
will cause a user segment fault. Sometimes, it would cause boot
failure when the whole rootfs is rv32.

Freeing unused kernel image (initmem) memory: 2236K
Run /sbin/init as init process
Starting init: /sbin/init exists but couldn't execute it (error -14)
Run /etc/init as init process
...

Increase the TASK_SIZE to cover STACK_TOP.

Cc: stable@vger.kernel.org
Fixes: add2cc6b6515 ("RISC-V: mm: Restrict address space for sv39,sv48,sv57")
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231222115703.2404036-2-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/pgtable.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 294044429e8e1..4342e142eea98 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -881,7 +881,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 #define TASK_SIZE_MIN	(PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
 
 #ifdef CONFIG_COMPAT
-#define TASK_SIZE_32	(_AC(0x80000000, UL) - PAGE_SIZE)
+#define TASK_SIZE_32	(_AC(0x80000000, UL))
 #define TASK_SIZE	(test_thread_flag(TIF_32BIT) ? \
 			 TASK_SIZE_32 : TASK_SIZE_64)
 #else
-- 
GitLab


From 97b7ac69be2e5a683e898f5267f659fde52efdd5 Mon Sep 17 00:00:00 2001
From: Guo Ren <guoren@linux.alibaba.com>
Date: Fri, 22 Dec 2023 06:57:01 -0500
Subject: [PATCH 2524/4076] riscv: mm: Fixup compat arch_get_mmap_end

When the task is in COMPAT mode, the arch_get_mmap_end should be 2GB,
not TASK_SIZE_64. The TASK_SIZE has contained is_compat_mode()
detection, so change the definition of STACK_TOP_MAX to TASK_SIZE
directly.

Cc: stable@vger.kernel.org
Fixes: add2cc6b6515 ("RISC-V: mm: Restrict address space for sv39,sv48,sv57")
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231222115703.2404036-3-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/processor.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index f19f861cda549..e1944ff0757a8 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -16,7 +16,7 @@
 
 #ifdef CONFIG_64BIT
 #define DEFAULT_MAP_WINDOW	(UL(1) << (MMAP_VA_BITS - 1))
-#define STACK_TOP_MAX		TASK_SIZE_64
+#define STACK_TOP_MAX		TASK_SIZE
 
 #define arch_get_mmap_end(addr, len, flags)			\
 ({								\
-- 
GitLab


From 1f4cac0f7465830a17a266983acbd60a2ce7ee6f Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Wed, 10 Jan 2024 11:46:46 +0100
Subject: [PATCH 2525/4076] Documentation: constrain alabaster package to older
 versions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The 'alabaster' theme dropped support for Sphinx < v3.4:

    0.7.14 – 2024-01-08

    * Dropped support for Python 3.8 and earlier.
    * Dropped support for Sphinx 3.3 and earlier.
    [...]

(Source: https://alabaster.readthedocs.io/en/latest/changelog.html)

This manifests as an error when running 'make htmldocs' in a virtualenv
constructed from Documentation/sphinx/requirements.txt:

    Sphinx version error:
    The alabaster extension used by this project needs at least Sphinx v3.4; it therefore cannot be built with this version.

Raising the Sphinx version is not really a good option at this point,
since 3.x through 6.x have horrible performance regressions (7.x still
does, but not quite as bad).

Instead, constrain the 'alabaster' package to versions that still support
Sphinx 2.4.4.

Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Link: https://lore.kernel.org/r/20240110104646.3647600-1-vegard.nossum@oracle.com
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/sphinx/requirements.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/sphinx/requirements.txt b/Documentation/sphinx/requirements.txt
index 335b53df35e22..6b0a981dcb2cd 100644
--- a/Documentation/sphinx/requirements.txt
+++ b/Documentation/sphinx/requirements.txt
@@ -1,3 +1,5 @@
 # jinja2>=3.1 is not compatible with Sphinx<4.0
 jinja2<3.1
+# alabaster>=0.7.14 is not compatible with Sphinx<=3.3
+alabaster<0.7.14
 Sphinx==2.4.4
-- 
GitLab


From c48a7c44a1d02516309015b6134c9bb982e17008 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Wed, 10 Jan 2024 18:47:58 +0100
Subject: [PATCH 2526/4076] docs: kernel_feat.py: fix potential command
 injection

The kernel-feat directive passes its argument straight to the shell.
This is unfortunate and unnecessary.

Let's always use paths relative to $srctree/Documentation/ and use
subprocess.check_call() instead of subprocess.Popen(shell=True).

This also makes the code shorter.

This is analogous to commit 3231dd586277 ("docs: kernel_abi.py: fix
command injection") where we did exactly the same thing for
kernel_abi.py, somehow I completely missed this one.

Link: https://fosstodon.org/@jani/111676532203641247
Reported-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20240110174758.3680506-1-vegard.nossum@oracle.com
---
 Documentation/admin-guide/features.rst        |  2 +-
 Documentation/arch/arc/features.rst           |  2 +-
 Documentation/arch/arm/features.rst           |  2 +-
 Documentation/arch/arm64/features.rst         |  2 +-
 Documentation/arch/loongarch/features.rst     |  2 +-
 Documentation/arch/m68k/features.rst          |  2 +-
 Documentation/arch/mips/features.rst          |  2 +-
 Documentation/arch/nios2/features.rst         |  2 +-
 Documentation/arch/openrisc/features.rst      |  2 +-
 Documentation/arch/parisc/features.rst        |  2 +-
 Documentation/arch/powerpc/features.rst       |  2 +-
 Documentation/arch/riscv/features.rst         |  2 +-
 Documentation/arch/s390/features.rst          |  2 +-
 Documentation/arch/sh/features.rst            |  2 +-
 Documentation/arch/sparc/features.rst         |  2 +-
 Documentation/arch/x86/features.rst           |  2 +-
 Documentation/arch/xtensa/features.rst        |  2 +-
 Documentation/sphinx/kernel_feat.py           | 55 ++++---------------
 .../zh_CN/arch/loongarch/features.rst         |  2 +-
 .../translations/zh_CN/arch/mips/features.rst |  2 +-
 .../zh_TW/arch/loongarch/features.rst         |  2 +-
 .../translations/zh_TW/arch/mips/features.rst |  2 +-
 22 files changed, 32 insertions(+), 65 deletions(-)

diff --git a/Documentation/admin-guide/features.rst b/Documentation/admin-guide/features.rst
index 8c167082a84f9..7651eca38227d 100644
--- a/Documentation/admin-guide/features.rst
+++ b/Documentation/admin-guide/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features
+.. kernel-feat:: features
diff --git a/Documentation/arch/arc/features.rst b/Documentation/arch/arc/features.rst
index b793583d688a4..49ff446ff744c 100644
--- a/Documentation/arch/arc/features.rst
+++ b/Documentation/arch/arc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features arc
+.. kernel-feat:: features arc
diff --git a/Documentation/arch/arm/features.rst b/Documentation/arch/arm/features.rst
index 7414ec03dd157..0e76aaf68ecab 100644
--- a/Documentation/arch/arm/features.rst
+++ b/Documentation/arch/arm/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features arm
+.. kernel-feat:: features arm
diff --git a/Documentation/arch/arm64/features.rst b/Documentation/arch/arm64/features.rst
index dfa4cb3cd3efa..03321f4309d0b 100644
--- a/Documentation/arch/arm64/features.rst
+++ b/Documentation/arch/arm64/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features arm64
+.. kernel-feat:: features arm64
diff --git a/Documentation/arch/loongarch/features.rst b/Documentation/arch/loongarch/features.rst
index ebacade3ea454..009f44c7951f8 100644
--- a/Documentation/arch/loongarch/features.rst
+++ b/Documentation/arch/loongarch/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features loongarch
+.. kernel-feat:: features loongarch
diff --git a/Documentation/arch/m68k/features.rst b/Documentation/arch/m68k/features.rst
index 5107a21194724..de7f0ccf7fc8e 100644
--- a/Documentation/arch/m68k/features.rst
+++ b/Documentation/arch/m68k/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features m68k
+.. kernel-feat:: features m68k
diff --git a/Documentation/arch/mips/features.rst b/Documentation/arch/mips/features.rst
index 1973d729b29a9..6e0ffe3e73540 100644
--- a/Documentation/arch/mips/features.rst
+++ b/Documentation/arch/mips/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features mips
+.. kernel-feat:: features mips
diff --git a/Documentation/arch/nios2/features.rst b/Documentation/arch/nios2/features.rst
index 8449e63f69b2b..89913810ccb5a 100644
--- a/Documentation/arch/nios2/features.rst
+++ b/Documentation/arch/nios2/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features nios2
+.. kernel-feat:: features nios2
diff --git a/Documentation/arch/openrisc/features.rst b/Documentation/arch/openrisc/features.rst
index 3f7c40d219f2c..bae2e25adfd64 100644
--- a/Documentation/arch/openrisc/features.rst
+++ b/Documentation/arch/openrisc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features openrisc
+.. kernel-feat:: features openrisc
diff --git a/Documentation/arch/parisc/features.rst b/Documentation/arch/parisc/features.rst
index 501d7c4500379..b3aa4d243b936 100644
--- a/Documentation/arch/parisc/features.rst
+++ b/Documentation/arch/parisc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features parisc
+.. kernel-feat:: features parisc
diff --git a/Documentation/arch/powerpc/features.rst b/Documentation/arch/powerpc/features.rst
index aeae73df86b0c..ee4b95e04202d 100644
--- a/Documentation/arch/powerpc/features.rst
+++ b/Documentation/arch/powerpc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features powerpc
+.. kernel-feat:: features powerpc
diff --git a/Documentation/arch/riscv/features.rst b/Documentation/arch/riscv/features.rst
index c70ef6ac2368c..36e90144adabd 100644
--- a/Documentation/arch/riscv/features.rst
+++ b/Documentation/arch/riscv/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features riscv
+.. kernel-feat:: features riscv
diff --git a/Documentation/arch/s390/features.rst b/Documentation/arch/s390/features.rst
index 57c296a9d8f30..2883dc9506817 100644
--- a/Documentation/arch/s390/features.rst
+++ b/Documentation/arch/s390/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features s390
+.. kernel-feat:: features s390
diff --git a/Documentation/arch/sh/features.rst b/Documentation/arch/sh/features.rst
index f722af3b6c993..fae48fe81e9bd 100644
--- a/Documentation/arch/sh/features.rst
+++ b/Documentation/arch/sh/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features sh
+.. kernel-feat:: features sh
diff --git a/Documentation/arch/sparc/features.rst b/Documentation/arch/sparc/features.rst
index c0c92468b0fe9..96835b6d598a1 100644
--- a/Documentation/arch/sparc/features.rst
+++ b/Documentation/arch/sparc/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features sparc
+.. kernel-feat:: features sparc
diff --git a/Documentation/arch/x86/features.rst b/Documentation/arch/x86/features.rst
index b663f15053ce8..a33616346a388 100644
--- a/Documentation/arch/x86/features.rst
+++ b/Documentation/arch/x86/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features x86
+.. kernel-feat:: features x86
diff --git a/Documentation/arch/xtensa/features.rst b/Documentation/arch/xtensa/features.rst
index 6b92c7bfa19da..28dcce1759be4 100644
--- a/Documentation/arch/xtensa/features.rst
+++ b/Documentation/arch/xtensa/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-.. kernel-feat:: $srctree/Documentation/features xtensa
+.. kernel-feat:: features xtensa
diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py
index b5fa2f0542a5d..b9df61eb45013 100644
--- a/Documentation/sphinx/kernel_feat.py
+++ b/Documentation/sphinx/kernel_feat.py
@@ -37,8 +37,6 @@ import re
 import subprocess
 import sys
 
-from os import path
-
 from docutils import nodes, statemachine
 from docutils.statemachine import ViewList
 from docutils.parsers.rst import directives, Directive
@@ -76,33 +74,26 @@ class KernelFeat(Directive):
         self.state.document.settings.env.app.warn(message, prefix="")
 
     def run(self):
-
         doc = self.state.document
         if not doc.settings.file_insertion_enabled:
             raise self.warning("docutils: file insertion disabled")
 
         env = doc.settings.env
-        cwd = path.dirname(doc.current_source)
-        cmd = "get_feat.pl rest --enable-fname --dir "
-        cmd += self.arguments[0]
-
-        if len(self.arguments) > 1:
-            cmd += " --arch " + self.arguments[1]
 
-        srctree = path.abspath(os.environ["srctree"])
+        srctree = os.path.abspath(os.environ["srctree"])
 
-        fname = cmd
+        args = [
+            os.path.join(srctree, 'scripts/get_feat.pl'),
+            'rest',
+            '--enable-fname',
+            '--dir',
+            os.path.join(srctree, 'Documentation', self.arguments[0]),
+        ]
 
-        # extend PATH with $(srctree)/scripts
-        path_env = os.pathsep.join([
-            srctree + os.sep + "scripts",
-            os.environ["PATH"]
-        ])
-        shell_env = os.environ.copy()
-        shell_env["PATH"]    = path_env
-        shell_env["srctree"] = srctree
+        if len(self.arguments) > 1:
+            args.extend(['--arch', self.arguments[1]])
 
-        lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env)
+        lines = subprocess.check_output(args, cwd=os.path.dirname(doc.current_source)).decode('utf-8')
 
         line_regex = re.compile(r"^\.\. FILE (\S+)$")
 
@@ -121,30 +112,6 @@ class KernelFeat(Directive):
         nodeList = self.nestedParse(out_lines, fname)
         return nodeList
 
-    def runCmd(self, cmd, **kwargs):
-        u"""Run command ``cmd`` and return its stdout as unicode."""
-
-        try:
-            proc = subprocess.Popen(
-                cmd
-                , stdout = subprocess.PIPE
-                , stderr = subprocess.PIPE
-                , **kwargs
-            )
-            out, err = proc.communicate()
-
-            out, err = codecs.decode(out, 'utf-8'), codecs.decode(err, 'utf-8')
-
-            if proc.returncode != 0:
-                raise self.severe(
-                    u"command '%s' failed with return code %d"
-                    % (cmd, proc.returncode)
-                )
-        except OSError as exc:
-            raise self.severe(u"problems with '%s' directive: %s."
-                              % (self.name, ErrorString(exc)))
-        return out
-
     def nestedParse(self, lines, fname):
         content = ViewList()
         node    = nodes.section()
diff --git a/Documentation/translations/zh_CN/arch/loongarch/features.rst b/Documentation/translations/zh_CN/arch/loongarch/features.rst
index 82bfac180bdc0..cec38dda8298c 100644
--- a/Documentation/translations/zh_CN/arch/loongarch/features.rst
+++ b/Documentation/translations/zh_CN/arch/loongarch/features.rst
@@ -5,4 +5,4 @@
 :Original: Documentation/arch/loongarch/features.rst
 :Translator: Huacai Chen <chenhuacai@loongson.cn>
 
-.. kernel-feat:: $srctree/Documentation/features loongarch
+.. kernel-feat:: features loongarch
diff --git a/Documentation/translations/zh_CN/arch/mips/features.rst b/Documentation/translations/zh_CN/arch/mips/features.rst
index da1b956e4a40f..0d6df97db069b 100644
--- a/Documentation/translations/zh_CN/arch/mips/features.rst
+++ b/Documentation/translations/zh_CN/arch/mips/features.rst
@@ -10,4 +10,4 @@
 
 .. _cn_features:
 
-.. kernel-feat:: $srctree/Documentation/features mips
+.. kernel-feat:: features mips
diff --git a/Documentation/translations/zh_TW/arch/loongarch/features.rst b/Documentation/translations/zh_TW/arch/loongarch/features.rst
index b64e430f55aef..c2175fd32b54b 100644
--- a/Documentation/translations/zh_TW/arch/loongarch/features.rst
+++ b/Documentation/translations/zh_TW/arch/loongarch/features.rst
@@ -5,5 +5,5 @@
 :Original: Documentation/arch/loongarch/features.rst
 :Translator: Huacai Chen <chenhuacai@loongson.cn>
 
-.. kernel-feat:: $srctree/Documentation/features loongarch
+.. kernel-feat:: features loongarch
 
diff --git a/Documentation/translations/zh_TW/arch/mips/features.rst b/Documentation/translations/zh_TW/arch/mips/features.rst
index f694104200354..3d3906c4d08e2 100644
--- a/Documentation/translations/zh_TW/arch/mips/features.rst
+++ b/Documentation/translations/zh_TW/arch/mips/features.rst
@@ -10,5 +10,5 @@
 
 .. _tw_features:
 
-.. kernel-feat:: $srctree/Documentation/features mips
+.. kernel-feat:: features mips
 
-- 
GitLab


From 22160b08d88898898b2bb99282663cdf3caa5c1c Mon Sep 17 00:00:00 2001
From: attreyee-muk <tintinm2017@gmail.com>
Date: Thu, 11 Jan 2024 00:27:47 +0530
Subject: [PATCH 2527/4076] Documentation/core-api: fix spelling mistake in
 workqueue

Correct to "following" from "followings" in the sentence "The followings
are the read bandwidths and CPU utilizations depending on different affinity
scope settings on ``kcryptd`` measured over five runs."

Signed-off-by: Attreyee Mukherjee <tintinm2017@gmail.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20240110185746.24974-1-tintinm2017@gmail.com
---
 Documentation/core-api/workqueue.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index 33c4539155d94..3599cf9267b47 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -446,7 +446,7 @@ The command used: ::
 
 There are 24 issuers, each issuing 64 IOs concurrently. ``--verify=sha512``
 makes ``fio`` generate and read back the content each time which makes
-execution locality matter between the issuer and ``kcryptd``. The followings
+execution locality matter between the issuer and ``kcryptd``. The following
 are the read bandwidths and CPU utilizations depending on different affinity
 scope settings on ``kcryptd`` measured over five runs. Bandwidths are in
 MiBps, and CPU util in percents.
-- 
GitLab


From 54a2ffe9524f5aef34397bbd53366c6a95661491 Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Mon, 8 Jan 2024 15:21:45 +0200
Subject: [PATCH 2528/4076] docs: admin-guide: hw_random: update rng-tools
 website

rng-tools upstream moved to github. New upstream does not appear to
consider itself official website for hw_random. Drop that part.

Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/ef52ace5008fa934084442149f64f5f9ddbba465.1704720105.git.baruch@tkos.co.il
---
 Documentation/admin-guide/hw_random.rst | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/hw_random.rst b/Documentation/admin-guide/hw_random.rst
index d494601717f1f..bfc39f1cf470e 100644
--- a/Documentation/admin-guide/hw_random.rst
+++ b/Documentation/admin-guide/hw_random.rst
@@ -14,10 +14,9 @@ into that core.
 
 To make the most effective use of these mechanisms, you
 should download the support software as well.  Download the
-latest version of the "rng-tools" package from the
-hw_random driver's official Web site:
+latest version of the "rng-tools" package from:
 
-	http://sourceforge.net/projects/gkernel/
+	https://github.com/nhorman/rng-tools
 
 Those tools use /dev/hwrng to fill the kernel entropy pool,
 which is used internally and exported by the /dev/urandom and
-- 
GitLab


From b65a6b44f0eaab8f217335d821c9b79aed47d9d8 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 19 Dec 2023 14:23:29 +0800
Subject: [PATCH 2529/4076] docs, kprobes: Update email address of Masami
 Hiramatsu

According to the latest authorship and Signed-off-by:

  Masami Hiramatsu (Google) <mhiramat@kernel.org>

Masami Hiramatsu is working at Google, so the current email @redhat.com
is out of date, it is better to use the email @kernel.org.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Acked-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20231219062330.22813-2-yangtiezhu@loongson.cn
---
 Documentation/trace/kprobes.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/trace/kprobes.rst b/Documentation/trace/kprobes.rst
index f825970a14957..968ae080accd2 100644
--- a/Documentation/trace/kprobes.rst
+++ b/Documentation/trace/kprobes.rst
@@ -4,7 +4,7 @@ Kernel Probes (Kprobes)
 
 :Author: Jim Keniston <jkenisto@us.ibm.com>
 :Author: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
-:Author: Masami Hiramatsu <mhiramat@redhat.com>
+:Author: Masami Hiramatsu <mhiramat@kernel.org>
 
 .. CONTENTS
 
-- 
GitLab


From ead8467f96d6dc35bbf8c63ee9d244a357ede84a Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 19 Dec 2023 14:23:30 +0800
Subject: [PATCH 2530/4076] docs, kprobes: Add loongarch as supported
 architecture

After the following three changes at the beginning of the year:

  commit 6d4cc40fb5f5 ("LoongArch: Add kprobes support")
  commit 3f5536860086 ("LoongArch: Add kretprobes support")
  commit 09e679c28a4d ("LoongArch: Add kprobes on ftrace support")

it is appropriate to add loongarch as supported architecture in
kprobes documentation.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Acked-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20231219062330.22813-3-yangtiezhu@loongson.cn
---
 Documentation/trace/kprobes.rst | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/trace/kprobes.rst b/Documentation/trace/kprobes.rst
index 968ae080accd2..e1636e579c9cc 100644
--- a/Documentation/trace/kprobes.rst
+++ b/Documentation/trace/kprobes.rst
@@ -321,6 +321,7 @@ architectures:
 - mips
 - s390
 - parisc
+- loongarch
 
 Configuring Kprobes
 ===================
-- 
GitLab


From f35b88b66fbb5c90298ce3aa483b8a2cf1f39ad0 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Wed, 10 Jan 2024 20:10:08 -0800
Subject: [PATCH 2531/4076] iommu: Add cache_invalidate_user op

The updates of the PTEs in the nested page table will be propagated to the
hardware caches.

Add a new domain op cache_invalidate_user() for the userspace to flush the
hardware caches for a nested domain through iommufd. No wrapper for it, as
it's only supposed to be used by iommufd. Then, pass in invalidation
requests in form of a user data array containing a number of invalidation
data entries.

Link: https://lore.kernel.org/r/20240111041015.47920-2-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/iommu.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 6291aa7b079b0..93c0d12dd047c 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -284,6 +284,23 @@ struct iommu_user_data {
 	size_t len;
 };
 
+/**
+ * struct iommu_user_data_array - iommu driver specific user space data array
+ * @type: The data type of all the entries in the user buffer array
+ * @uptr: Pointer to the user buffer array
+ * @entry_len: The fixed-width length of an entry in the array, in bytes
+ * @entry_num: The number of total entries in the array
+ *
+ * The user buffer includes an array of requests with format defined in
+ * include/uapi/linux/iommufd.h
+ */
+struct iommu_user_data_array {
+	unsigned int type;
+	void __user *uptr;
+	size_t entry_len;
+	u32 entry_num;
+};
+
 /**
  * __iommu_copy_struct_from_user - Copy iommu driver specific user space data
  * @dst_data: Pointer to an iommu driver specific user data that is defined in
@@ -440,6 +457,13 @@ struct iommu_ops {
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
+ * @cache_invalidate_user: Flush hardware cache for user space IO page table.
+ *                         The @domain must be IOMMU_DOMAIN_NESTED. The @array
+ *                         passes in the cache invalidation requests, in form
+ *                         of a driver data structure. The driver must update
+ *                         array->entry_num to report the number of handled
+ *                         invalidation requests. The driver data structure
+ *                         must be defined in include/uapi/linux/iommufd.h
  * @iova_to_phys: translate iova to physical address
  * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE,
  *                           including no-snoop TLPs on PCIe or other platform
@@ -465,6 +489,8 @@ struct iommu_domain_ops {
 			      size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);
+	int (*cache_invalidate_user)(struct iommu_domain *domain,
+				     struct iommu_user_data_array *array);
 
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    dma_addr_t iova);
-- 
GitLab


From 8c6eabae3807e048b9f17733af5e20500fbf858c Mon Sep 17 00:00:00 2001
From: Yi Liu <yi.l.liu@intel.com>
Date: Wed, 10 Jan 2024 20:10:09 -0800
Subject: [PATCH 2532/4076] iommufd: Add IOMMU_HWPT_INVALIDATE

In nested translation, the stage-1 page table is user-managed but cached
by the IOMMU hardware, so an update on present page table entries in the
stage-1 page table should be followed with a cache invalidation.

Add an IOMMU_HWPT_INVALIDATE ioctl to support such a cache invalidation.
It takes hwpt_id to specify the iommu_domain, and a multi-entry array to
support multiple invalidation data in one ioctl.

enum iommu_hwpt_invalidate_data_type is defined to tag the data type of
the entries in the multi-entry array.

Link: https://lore.kernel.org/r/20240111041015.47920-3-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Co-developed-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/hw_pagetable.c    | 41 +++++++++++++++++++++++
 drivers/iommu/iommufd/iommufd_private.h | 10 ++++++
 drivers/iommu/iommufd/main.c            |  3 ++
 include/uapi/linux/iommufd.h            | 43 +++++++++++++++++++++++++
 4 files changed, 97 insertions(+)

diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index cbb5df0a6c32f..4e8711f19f721 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -371,3 +371,44 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
+
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hwpt_invalidate *cmd = ucmd->cmd;
+	struct iommu_user_data_array data_array = {
+		.type = cmd->data_type,
+		.uptr = u64_to_user_ptr(cmd->data_uptr),
+		.entry_len = cmd->entry_len,
+		.entry_num = cmd->entry_num,
+	};
+	struct iommufd_hw_pagetable *hwpt;
+	u32 done_num = 0;
+	int rc;
+
+	if (cmd->__reserved) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id);
+	if (IS_ERR(hwpt)) {
+		rc = PTR_ERR(hwpt);
+		goto out;
+	}
+
+	rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain,
+						      &data_array);
+	done_num = data_array.entry_num;
+
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+out:
+	cmd->entry_num = done_num;
+	if (iommufd_ucmd_respond(ucmd, sizeof(*cmd)))
+		return -EFAULT;
+	return rc;
+}
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index abae041e256f7..991f864d1f9bc 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -328,6 +328,15 @@ iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id)
 					       IOMMUFD_OBJ_HWPT_PAGING),
 			    struct iommufd_hwpt_paging, common.obj);
 }
+
+static inline struct iommufd_hw_pagetable *
+iommufd_get_hwpt_nested(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_HWPT_NESTED),
+			    struct iommufd_hw_pagetable, obj);
+}
+
 int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd);
 int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd);
 
@@ -345,6 +354,7 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj);
 void iommufd_hwpt_nested_destroy(struct iommufd_object *obj);
 void iommufd_hwpt_nested_abort(struct iommufd_object *obj);
 int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd);
 
 static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 					    struct iommufd_hw_pagetable *hwpt)
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index c9091e46d208a..39b32932c61ee 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -322,6 +322,7 @@ union ucmd_buffer {
 	struct iommu_hw_info info;
 	struct iommu_hwpt_alloc hwpt;
 	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
+	struct iommu_hwpt_invalidate cache;
 	struct iommu_hwpt_set_dirty_tracking set_dirty_tracking;
 	struct iommu_ioas_alloc alloc;
 	struct iommu_ioas_allow_iovas allow_iovas;
@@ -360,6 +361,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
 		 struct iommu_hwpt_get_dirty_bitmap, data),
+	IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate,
+		 struct iommu_hwpt_invalidate, __reserved),
 	IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking,
 		 struct iommu_hwpt_set_dirty_tracking, __reserved),
 	IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 0b2bc6252e2ca..824560c50ec6d 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -49,6 +49,7 @@ enum {
 	IOMMUFD_CMD_GET_HW_INFO,
 	IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING,
 	IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP,
+	IOMMUFD_CMD_HWPT_INVALIDATE,
 };
 
 /**
@@ -613,4 +614,46 @@ struct iommu_hwpt_get_dirty_bitmap {
 #define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \
 					IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP)
 
+/**
+ * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation
+ *                                        Data Type
+ * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1
+ */
+enum iommu_hwpt_invalidate_data_type {
+	IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+};
+
+/**
+ * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE)
+ * @size: sizeof(struct iommu_hwpt_invalidate)
+ * @hwpt_id: ID of a nested HWPT for cache invalidation
+ * @data_uptr: User pointer to an array of driver-specific cache invalidation
+ *             data.
+ * @data_type: One of enum iommu_hwpt_invalidate_data_type, defining the data
+ *             type of all the entries in the invalidation request array. It
+ *             should be a type supported by the hwpt pointed by @hwpt_id.
+ * @entry_len: Length (in bytes) of a request entry in the request array
+ * @entry_num: Input the number of cache invalidation requests in the array.
+ *             Output the number of requests successfully handled by kernel.
+ * @__reserved: Must be 0.
+ *
+ * Invalidate the iommu cache for user-managed page table. Modifications on a
+ * user-managed page table should be followed by this operation to sync cache.
+ * Each ioctl can support one or more cache invalidation requests in the array
+ * that has a total size of @entry_len * @entry_num.
+ *
+ * An empty invalidation request array by setting @entry_num==0 is allowed, and
+ * @entry_len and @data_uptr would be ignored in this case. This can be used to
+ * check if the given @data_type is supported or not by kernel.
+ */
+struct iommu_hwpt_invalidate {
+	__u32 size;
+	__u32 hwpt_id;
+	__aligned_u64 data_uptr;
+	__u32 data_type;
+	__u32 entry_len;
+	__u32 entry_num;
+	__u32 __reserved;
+};
+#define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE)
 #endif
-- 
GitLab


From 77785117f9c73fd71a440a5ac86dd80752967adc Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 10 Jan 2024 20:10:10 -0800
Subject: [PATCH 2533/4076] iommu: Add iommu_copy_struct_from_user_array helper

Wrap up the data pointer/num sanity and __iommu_copy_struct_from_user()
call for iommu drivers to copy driver specific data at a specific location
in the struct iommu_user_data_array.

And expect it to be used in cache_invalidate_user ops for example.

Link: https://lore.kernel.org/r/20240111041015.47920-4-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Co-developed-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/iommu.h | 51 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 93c0d12dd047c..9dbadf74a3a1e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -341,6 +341,57 @@ static inline int __iommu_copy_struct_from_user(
 				      sizeof(*kdst),                      \
 				      offsetofend(typeof(*kdst), min_last))
 
+/**
+ * __iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                       data from an iommu_user_data_array
+ * @dst_data: Pointer to an iommu driver specific user data that is defined in
+ *            include/uapi/linux/iommufd.h
+ * @src_array: Pointer to a struct iommu_user_data_array for a user space array
+ * @data_type: The data type of the @dst_data. Must match with @src_array.type
+ * @index: Index to the location in the array to copy user data from
+ * @data_len: Length of current user data structure, i.e. sizeof(struct _dst)
+ * @min_len: Initial length of user data structure for backward compatibility.
+ *           This should be offsetofend using the last member in the user data
+ *           struct that was initially added to include/uapi/linux/iommufd.h
+ */
+static inline int __iommu_copy_struct_from_user_array(
+	void *dst_data, const struct iommu_user_data_array *src_array,
+	unsigned int data_type, unsigned int index, size_t data_len,
+	size_t min_len)
+{
+	struct iommu_user_data src_data;
+
+	if (WARN_ON(!src_array || index >= src_array->entry_num))
+		return -EINVAL;
+	if (!src_array->entry_num)
+		return -EINVAL;
+	src_data.uptr = src_array->uptr + src_array->entry_len * index;
+	src_data.len = src_array->entry_len;
+	src_data.type = src_array->type;
+
+	return __iommu_copy_struct_from_user(dst_data, &src_data, data_type,
+					     data_len, min_len);
+}
+
+/**
+ * iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                     data from an iommu_user_data_array
+ * @kdst: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @user_array: Pointer to a struct iommu_user_data_array for a user space
+ *              array
+ * @data_type: The data type of the @kdst. Must match with @user_array->type
+ * @index: Index to the location in the array to copy user data from
+ * @min_last: The last member of the data structure @kdst points in the
+ *            initial version.
+ * Return 0 for success, otherwise -error.
+ */
+#define iommu_copy_struct_from_user_array(kdst, user_array, data_type, index, \
+					  min_last)                           \
+	__iommu_copy_struct_from_user_array(                                  \
+		kdst, user_array, data_type, index, sizeof(*(kdst)),          \
+		offsetofend(typeof(*(kdst)), min_last))
+
 /**
  * struct iommu_ops - iommu ops and capabilities
  * @capable: check capability
-- 
GitLab


From ac8691203c07bb1897681d5c66374174336392fe Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 10 Jan 2024 20:10:11 -0800
Subject: [PATCH 2534/4076] iommufd/selftest: Add
 mock_domain_cache_invalidate_user support

Add mock_domain_cache_invalidate_user() data structure to support user
space selftest program to cover user cache invalidation pathway.

Link: https://lore.kernel.org/r/20240111041015.47920-5-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Co-developed-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/iommufd_test.h | 18 ++++++++++
 drivers/iommu/iommufd/selftest.c     | 50 ++++++++++++++++++++++++++++
 2 files changed, 68 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index 7910fbe1962d7..09dfc8aa65c4f 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -148,4 +148,22 @@ struct iommu_hwpt_selftest {
 	__u32 iotlb;
 };
 
+/* Should not be equal to any defined value in enum iommu_hwpt_invalidate_data_type */
+#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST 0xdeadbeef
+#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID 0xdadbeef
+
+/**
+ * struct iommu_hwpt_invalidate_selftest - Invalidation data for Mock driver
+ *                                         (IOMMU_HWPT_INVALIDATE_DATA_SELFTEST)
+ * @flags: Invalidate flags
+ * @iotlb_id: Invalidate iotlb entry index
+ *
+ * If IOMMU_TEST_INVALIDATE_ALL is set in @flags, @iotlb_id will be ignored
+ */
+struct iommu_hwpt_invalidate_selftest {
+#define IOMMU_TEST_INVALIDATE_FLAG_ALL	(1 << 0)
+	__u32 flags;
+	__u32 iotlb_id;
+};
+
 #endif
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 022ef8f55088a..23879135d1c37 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -473,9 +473,59 @@ static void mock_domain_free_nested(struct iommu_domain *domain)
 	kfree(mock_nested);
 }
 
+static int
+mock_domain_cache_invalidate_user(struct iommu_domain *domain,
+				  struct iommu_user_data_array *array)
+{
+	struct mock_iommu_domain_nested *mock_nested =
+		container_of(domain, struct mock_iommu_domain_nested, domain);
+	struct iommu_hwpt_invalidate_selftest inv;
+	u32 processed = 0;
+	int i = 0, j;
+	int rc = 0;
+
+	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_SELFTEST) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	for ( ; i < array->entry_num; i++) {
+		rc = iommu_copy_struct_from_user_array(&inv, array,
+						       IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+						       i, iotlb_id);
+		if (rc)
+			break;
+
+		if (inv.flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) {
+			rc = -EOPNOTSUPP;
+			break;
+		}
+
+		if (inv.iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX) {
+			rc = -EINVAL;
+			break;
+		}
+
+		if (inv.flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) {
+			/* Invalidate all mock iotlb entries and ignore iotlb_id */
+			for (j = 0; j < MOCK_NESTED_DOMAIN_IOTLB_NUM; j++)
+				mock_nested->iotlb[j] = 0;
+		} else {
+			mock_nested->iotlb[inv.iotlb_id] = 0;
+		}
+
+		processed++;
+	}
+
+out:
+	array->entry_num = processed;
+	return rc;
+}
+
 static struct iommu_domain_ops domain_nested_ops = {
 	.free = mock_domain_free_nested,
 	.attach_dev = mock_domain_nop_attach,
+	.cache_invalidate_user = mock_domain_cache_invalidate_user,
 };
 
 static inline struct iommufd_hw_pagetable *
-- 
GitLab


From e1fa6640d58e3529bd5e392dd92371cde2b31283 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 10 Jan 2024 20:10:12 -0800
Subject: [PATCH 2535/4076] iommufd/selftest: Add IOMMU_TEST_OP_MD_CHECK_IOTLB
 test op

Allow to test whether IOTLB has been invalidated or not.

Link: https://lore.kernel.org/r/20240111041015.47920-6-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/iommufd_test.h          |  5 ++++
 drivers/iommu/iommufd/selftest.c              | 26 +++++++++++++++++++
 tools/testing/selftests/iommu/iommufd.c       |  4 +++
 tools/testing/selftests/iommu/iommufd_utils.h | 24 +++++++++++++++++
 4 files changed, 59 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index 09dfc8aa65c4f..482d4059f5db6 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -21,6 +21,7 @@ enum {
 	IOMMU_TEST_OP_ACCESS_REPLACE_IOAS,
 	IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS,
 	IOMMU_TEST_OP_DIRTY,
+	IOMMU_TEST_OP_MD_CHECK_IOTLB,
 };
 
 enum {
@@ -121,6 +122,10 @@ struct iommu_test_cmd {
 			__aligned_u64 uptr;
 			__aligned_u64 out_nr_dirty;
 		} dirty;
+		struct {
+			__u32 id;
+			__u32 iotlb;
+		} check_iotlb;
 	};
 	__u32 last;
 };
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 23879135d1c37..db648c81507fa 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -843,6 +843,28 @@ static int iommufd_test_md_check_refs(struct iommufd_ucmd *ucmd,
 	return 0;
 }
 
+static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd,
+				       u32 mockpt_id, unsigned int iotlb_id,
+				       u32 iotlb)
+{
+	struct mock_iommu_domain_nested *mock_nested;
+	struct iommufd_hw_pagetable *hwpt;
+	int rc = 0;
+
+	hwpt = get_md_pagetable_nested(ucmd, mockpt_id, &mock_nested);
+	if (IS_ERR(hwpt))
+		return PTR_ERR(hwpt);
+
+	mock_nested = container_of(hwpt->domain,
+				   struct mock_iommu_domain_nested, domain);
+
+	if (iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX ||
+	    mock_nested->iotlb[iotlb_id] != iotlb)
+		rc = -EINVAL;
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+	return rc;
+}
+
 struct selftest_access {
 	struct iommufd_access *access;
 	struct file *file;
@@ -1324,6 +1346,10 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
 		return iommufd_test_md_check_refs(
 			ucmd, u64_to_user_ptr(cmd->check_refs.uptr),
 			cmd->check_refs.length, cmd->check_refs.refs);
+	case IOMMU_TEST_OP_MD_CHECK_IOTLB:
+		return iommufd_test_md_check_iotlb(ucmd, cmd->id,
+						   cmd->check_iotlb.id,
+						   cmd->check_iotlb.iotlb);
 	case IOMMU_TEST_OP_CREATE_ACCESS:
 		return iommufd_test_create_access(ucmd, cmd->id,
 						  cmd->create_access.flags);
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 6ed328c863c4f..c8763b880a161 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -330,6 +330,10 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 					   &nested_hwpt_id[1],
 					   IOMMU_HWPT_DATA_SELFTEST, &data,
 					   sizeof(data));
+		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0],
+					      IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1],
+					      IOMMU_TEST_IOTLB_DEFAULT);
 
 		/* Negative test: a nested hwpt on top of a nested hwpt */
 		test_err_hwpt_alloc_nested(EINVAL, self->device_id,
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index ad9202335656c..fe0a0f566b678 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -195,6 +195,30 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id,
 		     _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, flags, \
 					  hwpt_id, data_type, data, data_len))
 
+#define test_cmd_hwpt_check_iotlb(hwpt_id, iotlb_id, expected)                 \
+	({                                                                     \
+		struct iommu_test_cmd test_cmd = {                             \
+			.size = sizeof(test_cmd),                              \
+			.op = IOMMU_TEST_OP_MD_CHECK_IOTLB,                    \
+			.id = hwpt_id,                                         \
+			.check_iotlb = {                                       \
+				.id = iotlb_id,                                \
+				.iotlb = expected,                             \
+			},                                                     \
+		};                                                             \
+		ASSERT_EQ(0,                                                   \
+			  ioctl(self->fd,                                      \
+				_IOMMU_TEST_CMD(IOMMU_TEST_OP_MD_CHECK_IOTLB), \
+				&test_cmd));                                   \
+	})
+
+#define test_cmd_hwpt_check_iotlb_all(hwpt_id, expected)                       \
+	({                                                                     \
+		int i;                                                         \
+		for (i = 0; i < MOCK_NESTED_DOMAIN_IOTLB_NUM; i++)             \
+			test_cmd_hwpt_check_iotlb(hwpt_id, i, expected);       \
+	})
+
 static int _test_cmd_access_replace_ioas(int fd, __u32 access_id,
 					 unsigned int ioas_id)
 {
-- 
GitLab


From bf26eb83fd3b6f392cf68285c8858db5bfd5e570 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 10 Jan 2024 20:10:13 -0800
Subject: [PATCH 2536/4076] iommufd/selftest: Add coverage for
 IOMMU_HWPT_INVALIDATE ioctl

Add test cases for the IOMMU_HWPT_INVALIDATE ioctl and verify it by using
the new IOMMU_TEST_OP_MD_CHECK_IOTLB.

Link: https://lore.kernel.org/r/20240111041015.47920-7-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Co-developed-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 tools/testing/selftests/iommu/iommufd.c       | 148 ++++++++++++++++++
 tools/testing/selftests/iommu/iommufd_utils.h |  31 ++++
 2 files changed, 179 insertions(+)

diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index c8763b880a161..1a881e7a21d1b 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -116,6 +116,7 @@ TEST_F(iommufd, cmd_length)
 	TEST_LENGTH(iommu_destroy, IOMMU_DESTROY, id);
 	TEST_LENGTH(iommu_hw_info, IOMMU_GET_HW_INFO, __reserved);
 	TEST_LENGTH(iommu_hwpt_alloc, IOMMU_HWPT_ALLOC, __reserved);
+	TEST_LENGTH(iommu_hwpt_invalidate, IOMMU_HWPT_INVALIDATE, __reserved);
 	TEST_LENGTH(iommu_ioas_alloc, IOMMU_IOAS_ALLOC, out_ioas_id);
 	TEST_LENGTH(iommu_ioas_iova_ranges, IOMMU_IOAS_IOVA_RANGES,
 		    out_iova_alignment);
@@ -271,7 +272,9 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 	struct iommu_hwpt_selftest data = {
 		.iotlb = IOMMU_TEST_IOTLB_DEFAULT,
 	};
+	struct iommu_hwpt_invalidate_selftest inv_reqs[2] = {};
 	uint32_t nested_hwpt_id[2] = {};
+	uint32_t num_inv;
 	uint32_t parent_hwpt_id = 0;
 	uint32_t parent_hwpt_id_not_work = 0;
 	uint32_t test_hwpt_id = 0;
@@ -344,6 +347,151 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 		EXPECT_ERRNO(EBUSY,
 			     _test_ioctl_destroy(self->fd, parent_hwpt_id));
 
+		/* hwpt_invalidate only supports a user-managed hwpt (nested) */
+		num_inv = 1;
+		test_err_hwpt_invalidate(ENOENT, parent_hwpt_id, inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Check data_type by passing zero-length array */
+		num_inv = 0;
+		test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: Invalid data_type */
+		num_inv = 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: structure size sanity */
+		num_inv = 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs) + 1, &num_inv);
+		assert(!num_inv);
+
+		num_inv = 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 1, &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: invalid flag is passed */
+		num_inv = 1;
+		inv_reqs[0].flags = 0xffffffff;
+		test_err_hwpt_invalidate(EOPNOTSUPP, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: invalid data_uptr when array is not empty */
+		num_inv = 1;
+		inv_reqs[0].flags = 0;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], NULL,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: invalid entry_len when array is not empty */
+		num_inv = 1;
+		inv_reqs[0].flags = 0;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 0, &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: invalid iotlb_id */
+		num_inv = 1;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = MOCK_NESTED_DOMAIN_IOTLB_ID_MAX + 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
+		/*
+		 * Invalidate the 1st iotlb entry but fail the 2nd request
+		 * due to invalid flags configuration in the 2nd request.
+		 */
+		num_inv = 2;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = 0;
+		inv_reqs[1].flags = 0xffffffff;
+		inv_reqs[1].iotlb_id = 1;
+		test_err_hwpt_invalidate(EOPNOTSUPP, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 1);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+
+		/*
+		 * Invalidate the 1st iotlb entry but fail the 2nd request
+		 * due to invalid iotlb_id configuration in the 2nd request.
+		 */
+		num_inv = 2;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = 0;
+		inv_reqs[1].flags = 0;
+		inv_reqs[1].iotlb_id = MOCK_NESTED_DOMAIN_IOTLB_ID_MAX + 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 1);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+
+		/* Invalidate the 2nd iotlb entry and verify */
+		num_inv = 1;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = 1;
+		test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 1);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1, 0);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+		test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3,
+					  IOMMU_TEST_IOTLB_DEFAULT);
+
+		/* Invalidate the 3rd and 4th iotlb entries and verify */
+		num_inv = 2;
+		inv_reqs[0].flags = 0;
+		inv_reqs[0].iotlb_id = 2;
+		inv_reqs[1].flags = 0;
+		inv_reqs[1].iotlb_id = 3;
+		test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 2);
+		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0], 0);
+
+		/* Invalidate all iotlb entries for nested_hwpt_id[1] and verify */
+		num_inv = 1;
+		inv_reqs[0].flags = IOMMU_TEST_INVALIDATE_FLAG_ALL;
+		test_cmd_hwpt_invalidate(nested_hwpt_id[1], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(num_inv == 1);
+		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1], 0);
+
 		/* Attach device to nested_hwpt_id[0] that then will be busy */
 		test_cmd_mock_domain_replace(self->stdev_id, nested_hwpt_id[0]);
 		EXPECT_ERRNO(EBUSY,
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index fe0a0f566b678..c646264aa41fd 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -219,6 +219,37 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id,
 			test_cmd_hwpt_check_iotlb(hwpt_id, i, expected);       \
 	})
 
+static int _test_cmd_hwpt_invalidate(int fd, __u32 hwpt_id, void *reqs,
+				     uint32_t data_type, uint32_t lreq,
+				     uint32_t *nreqs)
+{
+	struct iommu_hwpt_invalidate cmd = {
+		.size = sizeof(cmd),
+		.hwpt_id = hwpt_id,
+		.data_type = data_type,
+		.data_uptr = (uint64_t)reqs,
+		.entry_len = lreq,
+		.entry_num = *nreqs,
+	};
+	int rc = ioctl(fd, IOMMU_HWPT_INVALIDATE, &cmd);
+	*nreqs = cmd.entry_num;
+	return rc;
+}
+
+#define test_cmd_hwpt_invalidate(hwpt_id, reqs, data_type, lreq, nreqs)       \
+	({                                                                    \
+		ASSERT_EQ(0,                                                  \
+			  _test_cmd_hwpt_invalidate(self->fd, hwpt_id, reqs,  \
+						    data_type, lreq, nreqs)); \
+	})
+#define test_err_hwpt_invalidate(_errno, hwpt_id, reqs, data_type, lreq, \
+				 nreqs)                                  \
+	({                                                               \
+		EXPECT_ERRNO(_errno, _test_cmd_hwpt_invalidate(          \
+					     self->fd, hwpt_id, reqs,    \
+					     data_type, lreq, nreqs));   \
+	})
+
 static int _test_cmd_access_replace_ioas(int fd, __u32 access_id,
 					 unsigned int ioas_id)
 {
-- 
GitLab


From 393a5778b72a7b551493d0fd3fbe0282154058fe Mon Sep 17 00:00:00 2001
From: Yi Liu <yi.l.liu@intel.com>
Date: Wed, 10 Jan 2024 20:10:14 -0800
Subject: [PATCH 2537/4076] iommufd: Add data structure for Intel VT-d stage-1
 cache invalidation

This adds the data structure invalidating caches for the nested domain
allocated with IOMMU_HWPT_DATA_VTD_S1 type.

Link: https://lore.kernel.org/r/20240111041015.47920-8-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/uapi/linux/iommufd.h | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 824560c50ec6d..1dfeaa2e649ee 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -623,6 +623,42 @@ enum iommu_hwpt_invalidate_data_type {
 	IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
 };
 
+/**
+ * enum iommu_hwpt_vtd_s1_invalidate_flags - Flags for Intel VT-d
+ *                                           stage-1 cache invalidation
+ * @IOMMU_VTD_INV_FLAGS_LEAF: Indicates whether the invalidation applies
+ *                            to all-levels page structure cache or just
+ *                            the leaf PTE cache.
+ */
+enum iommu_hwpt_vtd_s1_invalidate_flags {
+	IOMMU_VTD_INV_FLAGS_LEAF = 1 << 0,
+};
+
+/**
+ * struct iommu_hwpt_vtd_s1_invalidate - Intel VT-d cache invalidation
+ *                                       (IOMMU_HWPT_INVALIDATE_DATA_VTD_S1)
+ * @addr: The start address of the range to be invalidated. It needs to
+ *        be 4KB aligned.
+ * @npages: Number of contiguous 4K pages to be invalidated.
+ * @flags: Combination of enum iommu_hwpt_vtd_s1_invalidate_flags
+ * @__reserved: Must be 0
+ *
+ * The Intel VT-d specific invalidation data for user-managed stage-1 cache
+ * invalidation in nested translation. Userspace uses this structure to
+ * tell the impacted cache scope after modifying the stage-1 page table.
+ *
+ * Invalidating all the caches related to the page table by setting @addr
+ * to be 0 and @npages to be U64_MAX.
+ *
+ * The device TLB will be invalidated automatically if ATS is enabled.
+ */
+struct iommu_hwpt_vtd_s1_invalidate {
+	__aligned_u64 addr;
+	__aligned_u64 npages;
+	__u32 flags;
+	__u32 __reserved;
+};
+
 /**
  * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE)
  * @size: sizeof(struct iommu_hwpt_invalidate)
-- 
GitLab


From 77ed045e88e5cba6d8dec3c5c7cd52105c46b50b Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 8 Dec 2023 13:50:35 +0100
Subject: [PATCH 2538/4076] s390/compat: change default for CONFIG_COMPAT to
 "n"

31 bit support has been removed from the kernel more than eight years
ago. The last 31 bit distribution is many years older. There shouldn't be
any 31 bit code around anymore.

Therefore avoid providing an unused and only partially tested user space
interface and change the default for CONFIG_COMPAT from "yes" to "no".

Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/Kconfig                    | 6 ++++--
 arch/s390/configs/zfcpdump_defconfig | 1 -
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8f39f04247966..3408b48423ad6 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -443,7 +443,7 @@ config COMMAND_LINE_SIZE
 	  line.
 
 config COMPAT
-	def_bool y
+	def_bool n
 	prompt "Kernel support for 31 bit emulation"
 	select ARCH_WANT_OLD_COMPAT_IPC
 	select COMPAT_OLD_SIGACTION
@@ -454,7 +454,9 @@ config COMPAT
 	  Select this option if you want to enable your system kernel to
 	  handle system-calls from ELF binaries for 31 bit ESA.  This option
 	  (and some other stuff like libraries and such) is needed for
-	  executing 31 bit applications.  It is safe to say "Y".
+	  executing 31 bit applications.
+
+	  If unsure say N.
 
 config SMP
 	def_bool y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 47028450eee15..30d2a16876650 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -10,7 +10,6 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_CRASH_DUMP=y
 CONFIG_MARCH_Z13=y
-# CONFIG_COMPAT is not set
 CONFIG_NR_CPUS=2
 CONFIG_HZ_100=y
 # CONFIG_CHSC_SCH is not set
-- 
GitLab


From 0130a0d3a61889060e912a533e996201c4d9a2e5 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Tue, 12 Dec 2023 13:59:42 +0100
Subject: [PATCH 2539/4076] s390/kexec: do not automatically select KEXEC
 option

Following commit dccf78d39f10 ("kernel/Kconfig.kexec: drop
select of KEXEC for CRASH_DUMP") also drop automatic KEXEC
selection for s390 while set CONFIG_KEXEC=y explicitly for
defconfig and debug_defconfig targets. zfcpdump_defconfig
target gets CONFIG_KEXEC unset as result, which is right
and consistent with CONFIG_KEXEC_FILE besides.

Acked-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/Kconfig                 | 1 -
 arch/s390/configs/debug_defconfig | 1 +
 arch/s390/configs/defconfig       | 1 +
 3 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3408b48423ad6..fe565f3a3a917 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -216,7 +216,6 @@ config S390
 	select HAVE_VIRT_CPU_ACCOUNTING_IDLE
 	select IOMMU_HELPER		if PCI
 	select IOMMU_SUPPORT		if PCI
-	select KEXEC
 	select MMU_GATHER_MERGE_VMAS
 	select MMU_GATHER_NO_GATHER
 	select MMU_GATHER_RCU_TABLE_FREE
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 6de44ede4e14d..689970baf7ac6 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -40,6 +40,7 @@ CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
+CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
 CONFIG_CRASH_DUMP=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index bcae47da6b7cd..229be2965e6a8 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -38,6 +38,7 @@ CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
+CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
 CONFIG_CRASH_DUMP=y
-- 
GitLab


From 80df7d6af7f6d229b34cf237b2cc9024c07111cd Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Tue, 28 Nov 2023 16:22:49 +0100
Subject: [PATCH 2540/4076] s390/pci: fix max size calculation in
 zpci_memcpy_toio()

The zpci_get_max_write_size() helper is used to determine the maximum
size a PCI store or load can use at a given __iomem address.

For the PCI block store the following restrictions apply:

1. The dst + len must not cross a 4K boundary in the (pseudo-)MMIO space
2. len must not exceed ZPCI_MAX_WRITE_SIZE
3. len must be a multiple of 8 bytes
4. The src address must be double word (8 byte) aligned
5. The dst address must be double word (8 byte) aligned

Otherwise only a normal PCI store which takes its src value from
a register can be used. For these PCI store restriction 1 still applies.
Similarly 1 also applies to PCI loads.

It turns out zpci_max_write_size() instead implements stricter
conditions which prevents PCI block stores from being used where they
can and should be used. In particular instead of conditions 4 and 5 it
wrongly enforces both dst and src to be size aligned. This indirectly
covers condition 1 but also prevents many legal PCI block stores.

On top of the functional shortcomings the zpci_get_max_write_size() is
misnamed as it is used for both read and write size calculations. Rename
it to zpci_get_max_io_size() and implement the listed conditions
explicitly.

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Fixes: cd24834130ac ("s390/pci: base support")
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
[agordeev@linux.ibm.com replaced spaces with tabs]
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/include/asm/pci_io.h | 32 ++++++++++++++++++--------------
 arch/s390/pci/pci_mmio.c       | 12 ++++++------
 2 files changed, 24 insertions(+), 20 deletions(-)

diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index 287bb88f76986..2686bee800e3d 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -11,6 +11,8 @@
 /* I/O size constraints */
 #define ZPCI_MAX_READ_SIZE	8
 #define ZPCI_MAX_WRITE_SIZE	128
+#define ZPCI_BOUNDARY_SIZE	(1 << 12)
+#define ZPCI_BOUNDARY_MASK	(ZPCI_BOUNDARY_SIZE - 1)
 
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
@@ -125,16 +127,18 @@ out:
 int zpci_write_block(volatile void __iomem *dst, const void *src,
 		     unsigned long len);
 
-static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
+static inline int zpci_get_max_io_size(u64 src, u64 dst, int len, int max)
 {
-	int count = len > max ? max : len, size = 1;
+	int offset = dst & ZPCI_BOUNDARY_MASK;
+	int size;
 
-	while (!(src & 0x1) && !(dst & 0x1) && ((size << 1) <= count)) {
-		dst = dst >> 1;
-		src = src >> 1;
-		size = size << 1;
-	}
-	return size;
+	size = min3(len, ZPCI_BOUNDARY_SIZE - offset, max);
+	if (IS_ALIGNED(src, 8) && IS_ALIGNED(dst, 8) && IS_ALIGNED(size, 8))
+		return size;
+
+	if (size >= 8)
+		return 8;
+	return rounddown_pow_of_two(size);
 }
 
 static inline int zpci_memcpy_fromio(void *dst,
@@ -144,9 +148,9 @@ static inline int zpci_memcpy_fromio(void *dst,
 	int size, rc = 0;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64) dst, n,
-					       ZPCI_MAX_READ_SIZE);
+		size = zpci_get_max_io_size((u64 __force) src,
+					    (u64) dst, n,
+					    ZPCI_MAX_READ_SIZE);
 		rc = zpci_read_single(dst, src, size);
 		if (rc)
 			break;
@@ -166,9 +170,9 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 		return -EINVAL;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64) src, n,
-					       ZPCI_MAX_WRITE_SIZE);
+		size = zpci_get_max_io_size((u64 __force) dst,
+					    (u64) src, n,
+					    ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = zpci_write_block(dst, src, size);
 		else
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 5880893329310..a90499c087f0c 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -97,9 +97,9 @@ static inline int __memcpy_toio_inuser(void __iomem *dst,
 		return -EINVAL;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64 __force) src, n,
-					       ZPCI_MAX_WRITE_SIZE);
+		size = zpci_get_max_io_size((u64 __force) dst,
+					    (u64 __force) src, n,
+					    ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = __pcistb_mio_inuser(dst, src, size, &status);
 		else
@@ -242,9 +242,9 @@ static inline int __memcpy_fromio_inuser(void __user *dst,
 	u8 status;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64 __force) dst, n,
-					       ZPCI_MAX_READ_SIZE);
+		size = zpci_get_max_io_size((u64 __force) src,
+					    (u64 __force) dst, n,
+					    ZPCI_MAX_READ_SIZE);
 		rc = __pcilg_mio_inuser(dst, src, size, &status);
 		if (rc)
 			break;
-- 
GitLab


From d124e484691a737e174474d230dc6a4b385ba3db Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 3 Jan 2024 13:15:13 +0100
Subject: [PATCH 2541/4076] s390/mm,fault: remove not needed tsk variable

tsk is only used as an intermediate variable for current. Remove tsk
and use current directly instead at the only place where it is used.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/mm/fault.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index ab4098886e562..ac4c78546d973 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -280,7 +280,6 @@ static void do_sigbus(struct pt_regs *regs)
 static void do_exception(struct pt_regs *regs, int access)
 {
 	struct vm_area_struct *vma;
-	struct task_struct *tsk;
 	unsigned long address;
 	struct mm_struct *mm;
 	enum fault_type type;
@@ -289,7 +288,6 @@ static void do_exception(struct pt_regs *regs, int access)
 	vm_fault_t fault;
 	bool is_write;
 
-	tsk = current;
 	/*
 	 * The instruction that caused the program check has
 	 * been nullified. Don't signal single step via SIGTRAP.
@@ -297,7 +295,7 @@ static void do_exception(struct pt_regs *regs, int access)
 	clear_thread_flag(TIF_PER_TRAP);
 	if (kprobe_page_fault(regs, 14))
 		return;
-	mm = tsk->mm;
+	mm = current->mm;
 	address = get_fault_address(regs);
 	is_write = fault_is_write(regs);
 	type = get_fault_type(regs);
-- 
GitLab


From 74ca896113531c4a3bba278fd7991da743b7e63b Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 5 Jan 2024 15:28:47 +0100
Subject: [PATCH 2542/4076] s390/fpu: remove __load_fpu_regs() export

__load_fpu_regs() is only called from core kernel code.
Therefore remove the not needed export.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/fpu.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index 9e7c15fccfea9..a4f3449cc8141 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -208,7 +208,6 @@ void __load_fpu_regs(void)
 	}
 	clear_cpu_flag(CIF_FPU);
 }
-EXPORT_SYMBOL(__load_fpu_regs);
 
 void load_fpu_regs(void)
 {
-- 
GitLab


From ba69655fffdb8ada391494cfb8ddfe6e96784b79 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Tue, 9 Jan 2024 11:59:47 +0100
Subject: [PATCH 2543/4076] s390/ptrace: remove leftover comment

The code which validates floating point control register contents was
reworked with commit 702644249d3e ("s390/fpu: get rid of test_fp_ctl()").

There is still a comment which refers to the old implementation - remove it
in order to avoid confusion.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/ptrace.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 2e6754b62b209..f1897a8bb2210 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -917,7 +917,6 @@ static int s390_fpregs_set(struct task_struct *target,
 	else
 		memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
 
-	/* If setting FPC, must validate it first. */
 	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
 		u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
 		rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc,
-- 
GitLab


From f6f3721244a8224fa97952b34fbb21e4ee40e8a8 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Wed, 10 Jan 2024 20:10:15 -0800
Subject: [PATCH 2544/4076] iommu/vt-d: Add iotlb flush for nested domain

This implements the .cache_invalidate_user() callback to support iotlb
flush for nested domain.

Link: https://lore.kernel.org/r/20240111041015.47920-9-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Co-developed-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/intel/nested.c | 88 ++++++++++++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)

diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index b5a5563ab32c6..f26c7f1c46cca 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -73,9 +73,97 @@ static void intel_nested_domain_free(struct iommu_domain *domain)
 	kfree(to_dmar_domain(domain));
 }
 
+static void nested_flush_dev_iotlb(struct dmar_domain *domain, u64 addr,
+				   unsigned int mask)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+	u16 sid, qdep;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!info->ats_enabled)
+			continue;
+		sid = info->bus << 8 | info->devfn;
+		qdep = info->ats_qdep;
+		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+				   qdep, addr, mask);
+		quirk_extra_dev_tlb_flush(info, addr, mask,
+					  IOMMU_NO_PASID, qdep);
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void intel_nested_flush_cache(struct dmar_domain *domain, u64 addr,
+				     unsigned long npages, bool ih)
+{
+	struct iommu_domain_info *info;
+	unsigned int mask;
+	unsigned long i;
+
+	xa_for_each(&domain->iommu_array, i, info)
+		qi_flush_piotlb(info->iommu,
+				domain_id_iommu(domain, info->iommu),
+				IOMMU_NO_PASID, addr, npages, ih);
+
+	if (!domain->has_iotlb_device)
+		return;
+
+	if (npages == U64_MAX)
+		mask = 64 - VTD_PAGE_SHIFT;
+	else
+		mask = ilog2(__roundup_pow_of_two(npages));
+
+	nested_flush_dev_iotlb(domain, addr, mask);
+}
+
+static int intel_nested_cache_invalidate_user(struct iommu_domain *domain,
+					      struct iommu_user_data_array *array)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct iommu_hwpt_vtd_s1_invalidate inv_entry;
+	u32 index, processed = 0;
+	int ret = 0;
+
+	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_VTD_S1) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (index = 0; index < array->entry_num; index++) {
+		ret = iommu_copy_struct_from_user_array(&inv_entry, array,
+							IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+							index, __reserved);
+		if (ret)
+			break;
+
+		if ((inv_entry.flags & ~IOMMU_VTD_INV_FLAGS_LEAF) ||
+		    inv_entry.__reserved) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		if (!IS_ALIGNED(inv_entry.addr, VTD_PAGE_SIZE) ||
+		    ((inv_entry.npages == U64_MAX) && inv_entry.addr)) {
+			ret = -EINVAL;
+			break;
+		}
+
+		intel_nested_flush_cache(dmar_domain, inv_entry.addr,
+					 inv_entry.npages,
+					 inv_entry.flags & IOMMU_VTD_INV_FLAGS_LEAF);
+		processed++;
+	}
+
+out:
+	array->entry_num = processed;
+	return ret;
+}
+
 static const struct iommu_domain_ops intel_nested_domain_ops = {
 	.attach_dev		= intel_nested_attach_dev,
 	.free			= intel_nested_domain_free,
+	.cache_invalidate_user	= intel_nested_cache_invalidate_user,
 };
 
 struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
-- 
GitLab


From 47f2bd2ff382e5fe766b1322e354558a8da4a470 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 3 Jan 2024 11:27:22 -0400
Subject: [PATCH 2545/4076] iommufd/selftest: Check the bus type during probe

This relied on the probe function only being invoked by the bus type mock
was registered on. The removal of the bus ops broke this assumption and
the probe could be called on non-mock bus types like PCI.

Check the bus type directly in probe.

Fixes: 17de3f5fdd35 ("iommu: Retire bus ops")
Link: https://lore.kernel.org/r/0-v1-82d59f7eab8c+40c-iommufd_mock_bus_jgg@nvidia.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/selftest.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index db648c81507fa..d9e9920c7eba4 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -25,6 +25,19 @@ static struct iommu_domain_ops domain_nested_ops;
 
 size_t iommufd_test_memory_limit = 65536;
 
+struct mock_bus_type {
+	struct bus_type bus;
+	struct notifier_block nb;
+};
+
+static struct mock_bus_type iommufd_mock_bus_type = {
+	.bus = {
+		.name = "iommufd_mock",
+	},
+};
+
+static atomic_t mock_dev_num;
+
 enum {
 	MOCK_DIRTY_TRACK = 1,
 	MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2,
@@ -437,6 +450,8 @@ static struct iommu_device mock_iommu_device = {
 
 static struct iommu_device *mock_probe_device(struct device *dev)
 {
+	if (dev->bus != &iommufd_mock_bus_type.bus)
+		return ERR_PTR(-ENODEV);
 	return &mock_iommu_device;
 }
 
@@ -576,19 +591,6 @@ get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id,
 	return hwpt;
 }
 
-struct mock_bus_type {
-	struct bus_type bus;
-	struct notifier_block nb;
-};
-
-static struct mock_bus_type iommufd_mock_bus_type = {
-	.bus = {
-		.name = "iommufd_mock",
-	},
-};
-
-static atomic_t mock_dev_num;
-
 static void mock_dev_release(struct device *dev)
 {
 	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
-- 
GitLab


From 3f302388d45855c0b24802e7b414e3fb29f172e3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 11 Jan 2024 13:34:33 -0700
Subject: [PATCH 2546/4076] io_uring/rsrc: improve code generation for fixed
 file assignment

For the normal read/write path, we have already locked the ring
submission side when assigning the file. This causes branch
mispredictions when we then check and try and lock again in
io_req_set_rsrc_node(). As this is a very hot path, this matters.

Add a basic helper that already assumes we already have it locked,
and use that in io_file_get_fixed().

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c |  5 +++--
 io_uring/rsrc.h     | 14 +++++++++-----
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 4afb911fc042b..50c9f04bc193c 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2000,9 +2000,10 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
 		goto out;
 	fd = array_index_nospec(fd, ctx->nr_user_files);
 	slot = io_fixed_file_slot(&ctx->file_table, fd);
-	file = io_slot_file(slot);
+	if (!req->rsrc_node)
+		__io_req_set_rsrc_node(req, ctx);
 	req->flags |= io_slot_flags(slot);
-	io_req_set_rsrc_node(req, ctx, 0);
+	file = io_slot_file(slot);
 out:
 	io_ring_submit_unlock(ctx, issue_flags);
 	return file;
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 7238b9cfe33b6..c6f199bbee284 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -102,17 +102,21 @@ static inline void io_charge_rsrc_node(struct io_ring_ctx *ctx,
 	node->refs++;
 }
 
+static inline void __io_req_set_rsrc_node(struct io_kiocb *req,
+					  struct io_ring_ctx *ctx)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+	req->rsrc_node = ctx->rsrc_node;
+	io_charge_rsrc_node(ctx, ctx->rsrc_node);
+}
+
 static inline void io_req_set_rsrc_node(struct io_kiocb *req,
 					struct io_ring_ctx *ctx,
 					unsigned int issue_flags)
 {
 	if (!req->rsrc_node) {
 		io_ring_submit_lock(ctx, issue_flags);
-
-		lockdep_assert_held(&ctx->uring_lock);
-
-		req->rsrc_node = ctx->rsrc_node;
-		io_charge_rsrc_node(ctx, ctx->rsrc_node);
+		__io_req_set_rsrc_node(req, ctx);
 		io_ring_submit_unlock(ctx, issue_flags);
 	}
 }
-- 
GitLab


From 9defbb1bcf973b43bef7e9960bc0006bdf38dfb2 Mon Sep 17 00:00:00 2001
From: Yoshinori Sato <ysato@users.sourceforge.jp>
Date: Tue, 9 Jan 2024 17:23:23 +0900
Subject: [PATCH 2547/4076] dt-bindings: vendor-prefixes: Add smi

Add Silicon Mortion Technology Corporation
https://www.siliconmotion.com/

Signed-off-by: Yoshinori Sato <ysato@users.sourceforge.jp>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/c8aaf67e3fcdb7e60632c53a784691aabfc7733e.1704788539.git.ysato@users.sourceforge.jp
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/vendor-prefixes.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 309b94c328c84..6f1b91d9d1114 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -1281,6 +1281,8 @@ patternProperties:
     description: Skyworks Solutions, Inc.
   "^smartlabs,.*":
     description: SmartLabs LLC
+  "^smi,.*":
+    description: Silicon Motion Technology Corporation
   "^smsc,.*":
     description: Standard Microsystems Corporation
   "^snps,.*":
-- 
GitLab


From 36a7c96b3f265fd2bc5f518ae2fc60bed578da30 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Tue, 9 Jan 2024 14:32:38 +0100
Subject: [PATCH 2548/4076] dt-bindings: fpga: Convert bridge binding to yaml

Convert the generic fpga bridge DT binding to json-schema.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Reviewed-by: Xu Yilun <yilun.xu@intel.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/14558a4dcfab5255c1683015287e9c7f48b1afc2.1704807147.git.michal.simek@amd.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/fpga/fpga-bridge.txt  | 13 --------
 .../devicetree/bindings/fpga/fpga-bridge.yaml | 30 +++++++++++++++++++
 .../bindings/fpga/xlnx,pr-decoupler.yaml      |  5 +++-
 3 files changed, 34 insertions(+), 14 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/fpga/fpga-bridge.txt
 create mode 100644 Documentation/devicetree/bindings/fpga/fpga-bridge.yaml

diff --git a/Documentation/devicetree/bindings/fpga/fpga-bridge.txt b/Documentation/devicetree/bindings/fpga/fpga-bridge.txt
deleted file mode 100644
index 72e06917288aa..0000000000000
--- a/Documentation/devicetree/bindings/fpga/fpga-bridge.txt
+++ /dev/null
@@ -1,13 +0,0 @@
-FPGA Bridge Device Tree Binding
-
-Optional properties:
-- bridge-enable		: 0 if driver should disable bridge at startup
-			  1 if driver should enable bridge at startup
-			  Default is to leave bridge in current state.
-
-Example:
-	fpga_bridge3: fpga-bridge@ffc25080 {
-		compatible = "altr,socfpga-fpga2sdram-bridge";
-		reg = <0xffc25080 0x4>;
-		bridge-enable = <0>;
-	};
diff --git a/Documentation/devicetree/bindings/fpga/fpga-bridge.yaml b/Documentation/devicetree/bindings/fpga/fpga-bridge.yaml
new file mode 100644
index 0000000000000..1ccb2aa187269
--- /dev/null
+++ b/Documentation/devicetree/bindings/fpga/fpga-bridge.yaml
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/fpga/fpga-bridge.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: FPGA Bridge
+
+maintainers:
+  - Michal Simek <michal.simek@amd.com>
+
+properties:
+  $nodename:
+    pattern: "^fpga-bridge(@.*|-([0-9]|[1-9][0-9]+))?$"
+
+  bridge-enable:
+    description: |
+      0 if driver should disable bridge at startup
+      1 if driver should enable bridge at startup
+      Default is to leave bridge in current state.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [ 0, 1 ]
+
+additionalProperties: true
+
+examples:
+  - |
+    fpga-bridge {
+        bridge-enable = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/fpga/xlnx,pr-decoupler.yaml b/Documentation/devicetree/bindings/fpga/xlnx,pr-decoupler.yaml
index a7d4b8e59e193..5bf731f9d99a3 100644
--- a/Documentation/devicetree/bindings/fpga/xlnx,pr-decoupler.yaml
+++ b/Documentation/devicetree/bindings/fpga/xlnx,pr-decoupler.yaml
@@ -9,6 +9,9 @@ title: Xilinx LogiCORE Partial Reconfig Decoupler/AXI shutdown manager Softcore
 maintainers:
   - Nava kishore Manne <nava.kishore.manne@amd.com>
 
+allOf:
+  - $ref: fpga-bridge.yaml#
+
 description: |
   The Xilinx LogiCORE Partial Reconfig(PR) Decoupler manages one or more
   decouplers/fpga bridges. The controller can decouple/disable the bridges
@@ -51,7 +54,7 @@ required:
   - clocks
   - clock-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
-- 
GitLab


From 22439cf4d1ca4861820b825f4f07958bdaed12d6 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Tue, 9 Jan 2024 14:32:39 +0100
Subject: [PATCH 2549/4076] dt-bindings: fpga: altera: Convert bridge bindings
 to yaml

Convert Altera's bridges to yaml with using fpga-bridge.yaml.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Reviewed-by: Xu Yilun <yilun.xu@intel.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/07d646a6d82cc21b100e45ced7cae3ef05faa2cc.1704807147.git.michal.simek@amd.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../fpga/altera-fpga2sdram-bridge.txt         | 13 -----
 .../bindings/fpga/altera-freeze-bridge.txt    | 20 --------
 .../bindings/fpga/altera-hps2fpga-bridge.txt  | 36 --------------
 .../fpga/altr,freeze-bridge-controller.yaml   | 41 ++++++++++++++++
 .../fpga/altr,socfpga-fpga2sdram-bridge.yaml  | 33 +++++++++++++
 .../fpga/altr,socfpga-hps2fpga-bridge.yaml    | 49 +++++++++++++++++++
 6 files changed, 123 insertions(+), 69 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/fpga/altera-fpga2sdram-bridge.txt
 delete mode 100644 Documentation/devicetree/bindings/fpga/altera-freeze-bridge.txt
 delete mode 100644 Documentation/devicetree/bindings/fpga/altera-hps2fpga-bridge.txt
 create mode 100644 Documentation/devicetree/bindings/fpga/altr,freeze-bridge-controller.yaml
 create mode 100644 Documentation/devicetree/bindings/fpga/altr,socfpga-fpga2sdram-bridge.yaml
 create mode 100644 Documentation/devicetree/bindings/fpga/altr,socfpga-hps2fpga-bridge.yaml

diff --git a/Documentation/devicetree/bindings/fpga/altera-fpga2sdram-bridge.txt b/Documentation/devicetree/bindings/fpga/altera-fpga2sdram-bridge.txt
deleted file mode 100644
index 5dd0ff0f7b4ef..0000000000000
--- a/Documentation/devicetree/bindings/fpga/altera-fpga2sdram-bridge.txt
+++ /dev/null
@@ -1,13 +0,0 @@
-Altera FPGA To SDRAM Bridge Driver
-
-Required properties:
-- compatible		: Should contain "altr,socfpga-fpga2sdram-bridge"
-
-See Documentation/devicetree/bindings/fpga/fpga-bridge.txt for generic bindings.
-
-Example:
-	fpga_bridge3: fpga-bridge@ffc25080 {
-		compatible = "altr,socfpga-fpga2sdram-bridge";
-		reg = <0xffc25080 0x4>;
-		bridge-enable = <0>;
-	};
diff --git a/Documentation/devicetree/bindings/fpga/altera-freeze-bridge.txt b/Documentation/devicetree/bindings/fpga/altera-freeze-bridge.txt
deleted file mode 100644
index 8b26fbcff3c62..0000000000000
--- a/Documentation/devicetree/bindings/fpga/altera-freeze-bridge.txt
+++ /dev/null
@@ -1,20 +0,0 @@
-Altera Freeze Bridge Controller Driver
-
-The Altera Freeze Bridge Controller manages one or more freeze bridges.
-The controller can freeze/disable the bridges which prevents signal
-changes from passing through the bridge.  The controller can also
-unfreeze/enable the bridges which allows traffic to pass through the
-bridge normally.
-
-Required properties:
-- compatible		: Should contain "altr,freeze-bridge-controller"
-- regs			: base address and size for freeze bridge module
-
-See Documentation/devicetree/bindings/fpga/fpga-bridge.txt for generic bindings.
-
-Example:
-	freeze-controller@100000450 {
-		compatible = "altr,freeze-bridge-controller";
-		regs = <0x1000 0x10>;
-		bridge-enable = <0>;
-	};
diff --git a/Documentation/devicetree/bindings/fpga/altera-hps2fpga-bridge.txt b/Documentation/devicetree/bindings/fpga/altera-hps2fpga-bridge.txt
deleted file mode 100644
index 68cce3945b103..0000000000000
--- a/Documentation/devicetree/bindings/fpga/altera-hps2fpga-bridge.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-Altera FPGA/HPS Bridge Driver
-
-Required properties:
-- regs		: base address and size for AXI bridge module
-- compatible	: Should contain one of:
-		  "altr,socfpga-lwhps2fpga-bridge",
-		  "altr,socfpga-hps2fpga-bridge", or
-		  "altr,socfpga-fpga2hps-bridge"
-- resets	: Phandle and reset specifier for this bridge's reset
-- clocks	: Clocks used by this module.
-
-See Documentation/devicetree/bindings/fpga/fpga-bridge.txt for generic bindings.
-
-Example:
-	fpga_bridge0: fpga-bridge@ff400000 {
-		compatible = "altr,socfpga-lwhps2fpga-bridge";
-		reg = <0xff400000 0x100000>;
-		resets = <&rst LWHPS2FPGA_RESET>;
-		clocks = <&l4_main_clk>;
-		bridge-enable = <0>;
-	};
-
-	fpga_bridge1: fpga-bridge@ff500000 {
-		compatible = "altr,socfpga-hps2fpga-bridge";
-		reg = <0xff500000 0x10000>;
-		resets = <&rst HPS2FPGA_RESET>;
-		clocks = <&l4_main_clk>;
-		bridge-enable = <1>;
-	};
-
-	fpga_bridge2: fpga-bridge@ff600000 {
-		compatible = "altr,socfpga-fpga2hps-bridge";
-		reg = <0xff600000 0x100000>;
-		resets = <&rst FPGA2HPS_RESET>;
-		clocks = <&l4_main_clk>;
-	};
diff --git a/Documentation/devicetree/bindings/fpga/altr,freeze-bridge-controller.yaml b/Documentation/devicetree/bindings/fpga/altr,freeze-bridge-controller.yaml
new file mode 100644
index 0000000000000..fccffeebb2560
--- /dev/null
+++ b/Documentation/devicetree/bindings/fpga/altr,freeze-bridge-controller.yaml
@@ -0,0 +1,41 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/fpga/altr,freeze-bridge-controller.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Altera Freeze Bridge Controller
+
+description:
+  The Altera Freeze Bridge Controller manages one or more freeze bridges.
+  The controller can freeze/disable the bridges which prevents signal
+  changes from passing through the bridge. The controller can also
+  unfreeze/enable the bridges which allows traffic to pass through the bridge
+  normally.
+
+maintainers:
+  - Xu Yilun <yilun.xu@intel.com>
+
+allOf:
+  - $ref: fpga-bridge.yaml#
+
+properties:
+  compatible:
+    const: altr,freeze-bridge-controller
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    fpga-bridge@100000450 {
+        compatible = "altr,freeze-bridge-controller";
+        reg = <0x1000 0x10>;
+        bridge-enable = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/fpga/altr,socfpga-fpga2sdram-bridge.yaml b/Documentation/devicetree/bindings/fpga/altr,socfpga-fpga2sdram-bridge.yaml
new file mode 100644
index 0000000000000..22b58453c5ff5
--- /dev/null
+++ b/Documentation/devicetree/bindings/fpga/altr,socfpga-fpga2sdram-bridge.yaml
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/fpga/altr,socfpga-fpga2sdram-bridge.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Altera FPGA To SDRAM Bridge
+
+maintainers:
+  - Xu Yilun <yilun.xu@intel.com>
+
+allOf:
+  - $ref: fpga-bridge.yaml#
+
+properties:
+  compatible:
+    const: altr,socfpga-fpga2sdram-bridge
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    fpga-bridge@ffc25080 {
+        compatible = "altr,socfpga-fpga2sdram-bridge";
+        reg = <0xffc25080 0x4>;
+        bridge-enable = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/fpga/altr,socfpga-hps2fpga-bridge.yaml b/Documentation/devicetree/bindings/fpga/altr,socfpga-hps2fpga-bridge.yaml
new file mode 100644
index 0000000000000..d19c6660d6c9a
--- /dev/null
+++ b/Documentation/devicetree/bindings/fpga/altr,socfpga-hps2fpga-bridge.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/fpga/altr,socfpga-hps2fpga-bridge.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Altera FPGA/HPS Bridge
+
+maintainers:
+  - Xu Yilun <yilun.xu@intel.com>
+
+allOf:
+  - $ref: fpga-bridge.yaml#
+
+properties:
+  compatible:
+    enum:
+      - altr,socfpga-lwhps2fpga-bridge
+      - altr,socfpga-hps2fpga-bridge
+      - altr,socfpga-fpga2hps-bridge
+
+  reg:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - resets
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/reset/altr,rst-mgr.h>
+
+    fpga-bridge@ff400000 {
+      compatible = "altr,socfpga-lwhps2fpga-bridge";
+      reg = <0xff400000 0x100000>;
+      bridge-enable = <0>;
+      clocks = <&l4_main_clk>;
+      resets = <&rst LWHPS2FPGA_RESET>;
+    };
-- 
GitLab


From 716089b417cf98d01f0dc1b39f9c47e1d7b4c965 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 11 Jan 2024 09:50:25 +0100
Subject: [PATCH 2550/4076] of: unittest: Fix of_count_phandle_with_args()
 expected value message

The expected result value for the call to of_count_phandle_with_args()
was updated from 7 to 8, but the accompanying error message was
forgotten.

Fixes: 4dde83569832f937 ("of: Fix double free in of_parse_phandle_with_args_map")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20240111085025.2073894-1-geert+renesas@glider.be
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/unittest.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 45bd0d28c7173..cfd60e35a8992 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -574,7 +574,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 	}
 
 	rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells");
-	unittest(rc == 8, "of_count_phandle_with_args() returned %i, expected 7\n", rc);
+	unittest(rc == 8, "of_count_phandle_with_args() returned %i, expected 8\n", rc);
 
 	for (i = 0; i < 9; i++) {
 		bool passed = true;
-- 
GitLab


From e1b1d282d5ccabbf17e5556191af248a35293e16 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 8 Jan 2024 10:16:02 -0800
Subject: [PATCH 2551/4076] net: fill in MODULE_DESCRIPTION()s for SLIP

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Serial Line (SLIP) protocol modules.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240108181610.2697017-3-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/slip/slhc.c | 1 +
 drivers/net/slip/slip.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index ba93bab948e09..18df7ca661981 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -752,4 +752,5 @@ EXPORT_SYMBOL(slhc_compress);
 EXPORT_SYMBOL(slhc_uncompress);
 EXPORT_SYMBOL(slhc_toss);
 
+MODULE_DESCRIPTION("Compression helpers for SLIP (serial line)");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index e4280e37fec97..0aba3569ccc0d 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -1437,5 +1437,6 @@ out:
 }
 
 #endif
+MODULE_DESCRIPTION("SLIP (serial line) protocol module");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_LDISC(N_SLIP);
-- 
GitLab


From 417d8c571cb49fcace83a6b6477da2970802bf26 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 8 Jan 2024 10:16:03 -0800
Subject: [PATCH 2552/4076] net: fill in MODULE_DESCRIPTION()s for HSR

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to High-availability Seamless Redundancy (HSR) driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240108181610.2697017-4-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/hsr/hsr_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index b099c31501509..cb83c8feb7465 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -167,4 +167,5 @@ static void __exit hsr_exit(void)
 
 module_init(hsr_init);
 module_exit(hsr_exit);
+MODULE_DESCRIPTION("High-availability Seamless Redundancy (HSR) driver");
 MODULE_LICENSE("GPL");
-- 
GitLab


From 95c236cc5fc9f09fc4cf58767fa7c01f2425ad6b Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 8 Jan 2024 10:16:04 -0800
Subject: [PATCH 2553/4076] net: fill in MODULE_DESCRIPTION()s for NFC

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to all NFC Controller Interface (NCI) modules.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240108181610.2697017-5-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/digital_core.c | 1 +
 net/nfc/nci/core.c     | 1 +
 net/nfc/nci/spi.c      | 1 +
 3 files changed, 3 insertions(+)

diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index d63d2e5dc60c9..dae378f1d52b6 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -858,4 +858,5 @@ void nfc_digital_unregister_device(struct nfc_digital_dev *ddev)
 }
 EXPORT_SYMBOL(nfc_digital_unregister_device);
 
+MODULE_DESCRIPTION("NFC Digital protocol stack");
 MODULE_LICENSE("GPL");
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6c9592d051206..97348cedb16b3 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1577,4 +1577,5 @@ static void nci_cmd_work(struct work_struct *work)
 	}
 }
 
+MODULE_DESCRIPTION("NFC Controller Interface");
 MODULE_LICENSE("GPL");
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index b68150c971d0b..6a93533c480e6 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -319,4 +319,5 @@ done:
 }
 EXPORT_SYMBOL_GPL(nci_spi_read);
 
+MODULE_DESCRIPTION("NFC Controller Interface (NCI) SPI link layer");
 MODULE_LICENSE("GPL");
-- 
GitLab


From d8610e431fe53ee3a1a11a7f25528b03f8a0b1c7 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 8 Jan 2024 10:16:05 -0800
Subject: [PATCH 2554/4076] net: fill in MODULE_DESCRIPTION()s for Sun RPC

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to Sun RPC modules.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20240108181610.2697017-6-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sunrpc/auth_gss/auth_gss.c      | 1 +
 net/sunrpc/auth_gss/gss_krb5_mech.c | 1 +
 net/sunrpc/sunrpc_syms.c            | 1 +
 3 files changed, 3 insertions(+)

diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 1af71fbb0d805..c7af0220f82f4 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -2280,6 +2280,7 @@ static void __exit exit_rpcsec_gss(void)
 }
 
 MODULE_ALIAS("rpc-auth-6");
+MODULE_DESCRIPTION("Sun RPC Kerberos RPCSEC_GSS client authentication");
 MODULE_LICENSE("GPL");
 module_param_named(expired_cred_retry_delay,
 		   gss_expired_cred_retry_delay,
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index e31cfdf7eadcb..64cff717c3d9b 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -650,6 +650,7 @@ static void __exit cleanup_kerberos_module(void)
 	gss_mech_unregister(&gss_kerberos_mech);
 }
 
+MODULE_DESCRIPTION("Sun RPC Kerberos 5 module");
 MODULE_LICENSE("GPL");
 module_init(init_kerberos_module);
 module_exit(cleanup_kerberos_module);
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index 691c0000e9eae..bab6cab294052 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -148,6 +148,7 @@ cleanup_sunrpc(void)
 #endif
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
+MODULE_DESCRIPTION("Sun RPC core");
 MODULE_LICENSE("GPL");
 fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */
 module_exit(cleanup_sunrpc);
-- 
GitLab


From ade98756128a63dbb801b9d3948c6954cc81b473 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 8 Jan 2024 10:16:08 -0800
Subject: [PATCH 2555/4076] net: fill in MODULE_DESCRIPTION()s for ds26522
 module

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to Slic Maxim ds26522 card driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240108181610.2697017-9-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/wan/slic_ds26522.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c
index 8a51cfcff99e5..cbb99fc5ea9fe 100644
--- a/drivers/net/wan/slic_ds26522.c
+++ b/drivers/net/wan/slic_ds26522.c
@@ -28,6 +28,7 @@
 
 static struct spi_device *g_spi;
 
+MODULE_DESCRIPTION("Slic Maxim DS26522 driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Zhao Qiang<B45475@freescale.com>");
 
-- 
GitLab


From c155eca07647bac84cbce690b4257605f5740dda Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 8 Jan 2024 10:16:09 -0800
Subject: [PATCH 2556/4076] net: fill in MODULE_DESCRIPTION()s for s2io

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Neterion 10GbE (s2io) driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240108181610.2697017-10-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/neterion/s2io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 61d8bfd12d5fd..55408f16fbbc4 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -414,6 +414,7 @@ static const u64 fix_mac[] = {
 	END_SIGN
 };
 
+MODULE_DESCRIPTION("Neterion 10GbE driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 
-- 
GitLab


From da14d1fed9c1e2f56a58dcd980d1395121c4665f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 9 Jan 2024 08:45:11 -0800
Subject: [PATCH 2557/4076] MAINTAINERS: eth: mtk: move John to CREDITS

John is still active in other bits of the kernel but not much
on the MediaTek ethernet switch side. Our scripts report:

Subsystem MEDIATEK ETHERNET DRIVER
  Changes 81 / 384 (21%)
  Last activity: 2023-12-21
  Felix Fietkau <nbd@nbd.name>:
    Author c6d96df9fa2c 2023-05-02 00:00:00 42
    Tags c6d96df9fa2c 2023-05-02 00:00:00 48
  John Crispin <john@phrozen.org>:
  Sean Wang <sean.wang@mediatek.com>:
    Author 880c2d4b2fdf 2019-06-03 00:00:00 5
    Tags a5d75538295b 2020-04-07 00:00:00 7
  Mark Lee <Mark-MC.Lee@mediatek.com>:
    Author 8d66a8183d0c 2019-11-14 00:00:00 4
    Tags 8d66a8183d0c 2019-11-14 00:00:00 4
  Lorenzo Bianconi <lorenzo@kernel.org>:
    Author 7cb8cd4daacf 2023-12-21 00:00:00 98
    Tags 7cb8cd4daacf 2023-12-21 00:00:00 112
  Top reviewers:
    [18]: horms@kernel.org
    [15]: leonro@nvidia.com
    [8]: rmk+kernel@armlinux.org.uk
  INACTIVE MAINTAINER John Crispin <john@phrozen.org>

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: John Crispin <john@phrozen.org>
Link: https://lore.kernel.org/r/20240109164517.3063131-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 1 -
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index d61ba9b5117f1..d174c65e10316 100644
--- a/CREDITS
+++ b/CREDITS
@@ -814,6 +814,10 @@ D: Support for Xircom PGSDB9 (firmware and host driver)
 S: Bucharest
 S: Romania
 
+N: John Crispin
+E: john@phrozen.org
+D: MediaTek MT7623 Gigabit ethernet support
+
 N: Laurence Culhane
 E: loz@holmes.demon.co.uk
 D: Wrote the initial alpha SLIP code
diff --git a/MAINTAINERS b/MAINTAINERS
index c36618d4659ec..f04fe483ecfbf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13509,7 +13509,6 @@ F:	drivers/dma/mediatek/
 
 MEDIATEK ETHERNET DRIVER
 M:	Felix Fietkau <nbd@nbd.name>
-M:	John Crispin <john@phrozen.org>
 M:	Sean Wang <sean.wang@mediatek.com>
 M:	Mark Lee <Mark-MC.Lee@mediatek.com>
 M:	Lorenzo Bianconi <lorenzo@kernel.org>
-- 
GitLab


From b59d8485fe7fda864e10800085ce1d19c321922a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 9 Jan 2024 08:45:12 -0800
Subject: [PATCH 2558/4076] MAINTAINERS: eth: mt7530: move Landen Chao to
 CREDITS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

mt7530 is a pretty active driver and last we have heard
from Landen Chao on the list was March. There were total
of 4 message from them in the last 2.5 years.
I think it's time to move to CREDITS.

Subsystem MEDIATEK SWITCH DRIVER
  Changes 94 / 169 (55%)
  Last activity: 2023-10-11
  Arınç ÜNAL <arinc.unal@arinc9.com>:
    Author e94b590abfff 2023-08-19 00:00:00 12
    Tags e94b590abfff 2023-08-19 00:00:00 16
  Daniel Golle <daniel@makrotopia.org>:
    Author 91daa4f62ce8 2023-04-19 00:00:00 17
    Tags ac49b992578d 2023-10-11 00:00:00 20
  Landen Chao <Landen.Chao@mediatek.com>:
  DENG Qingfang <dqfext@gmail.com>:
    Author 342afce10d6f 2021-10-18 00:00:00 24
    Tags 342afce10d6f 2021-10-18 00:00:00 25
  Sean Wang <sean.wang@mediatek.com>:
    Tags c288575f7810 2020-09-14 00:00:00 5
  Top reviewers:
    [46]: f.fainelli@gmail.com
    [29]: andrew@lunn.ch
    [19]: olteanv@gmail.com
  INACTIVE MAINTAINER Landen Chao <Landen.Chao@mediatek.com>

Acked-by: Arınç ÜNAL <arinc.unal@arinc9.com>
Link: https://lore.kernel.org/r/20240109164517.3063131-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 1 -
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index d174c65e10316..76bc0091f9cd4 100644
--- a/CREDITS
+++ b/CREDITS
@@ -677,6 +677,10 @@ D: Media subsystem (V4L/DVB) drivers and core
 D: EDAC drivers and EDAC 3.0 core rework
 S: Brazil
 
+N: Landen Chao
+E: Landen.Chao@mediatek.com
+D: MT7531 Ethernet switch support
+
 N: Raymond Chen
 E: raymondc@microsoft.com
 D: Author of Configure script
diff --git a/MAINTAINERS b/MAINTAINERS
index f04fe483ecfbf..b29c132f4754d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13664,7 +13664,6 @@ F:	include/soc/mediatek/smi.h
 MEDIATEK SWITCH DRIVER
 M:	Arınç ÜNAL <arinc.unal@arinc9.com>
 M:	Daniel Golle <daniel@makrotopia.org>
-M:	Landen Chao <Landen.Chao@mediatek.com>
 M:	DENG Qingfang <dqfext@gmail.com>
 M:	Sean Wang <sean.wang@mediatek.com>
 L:	netdev@vger.kernel.org
-- 
GitLab


From 009a98bca6347d0bd9cf0c31691331e68f0ee380 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 9 Jan 2024 08:45:13 -0800
Subject: [PATCH 2559/4076] MAINTAINERS: eth: mvneta: move Thomas to CREDITS

Thomas is still active in other bits of the kernel and beyond
but not as much on the Marvell Ethernet devices.
Our scripts report:

Subsystem MARVELL MVNETA ETHERNET DRIVER
  Changes 54 / 176 (30%)
  (No activity)
  Top reviewers:
    [12]: hawk@kernel.org
    [9]: toke@redhat.com
    [9]: john.fastabend@gmail.com
  INACTIVE MAINTAINER Thomas Petazzoni <thomas.petazzoni@bootlin.com>

Acked-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Link: https://lore.kernel.org/r/20240109164517.3063131-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 3 +--
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/CREDITS b/CREDITS
index 76bc0091f9cd4..4d6beeaaca3c4 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3049,6 +3049,10 @@ S: Demonstratsii 8-382
 S: Tula 300000
 S: Russia
 
+N: Thomas Petazzoni
+E: thomas.petazzoni@bootlin.com
+D: Driver for the Marvell Armada 370/XP network unit.
+
 N: Gordon Peters
 E: GordPeters@smarttech.com
 D: Isochronous receive for IEEE 1394 driver (OHCI module).
diff --git a/MAINTAINERS b/MAINTAINERS
index b29c132f4754d..ceb9b669dc6c5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12875,9 +12875,8 @@ S:	Maintained
 F:	drivers/thermal/armada_thermal.c
 
 MARVELL MVNETA ETHERNET DRIVER
-M:	Thomas Petazzoni <thomas.petazzoni@bootlin.com>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/net/ethernet/marvell/mvneta.*
 
 MARVELL MVPP2 ETHERNET DRIVER
-- 
GitLab


From 384a35866f3a2b75f0c12e09e1bc486ef96cb5f5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 9 Jan 2024 08:45:14 -0800
Subject: [PATCH 2560/4076] MAINTAINERS: eth: mark Cavium liquidio as an Orphan

We haven't seen much review activity from the liquidio
maintainers for years. Reflect that reality in MAINTAINERS.
Our scripts report:

Subsystem CAVIUM LIQUIDIO NETWORK DRIVER
  Changes 30 / 87 (34%)
  Last activity: 2019-01-28
  Derek Chickles <dchickles@marvell.com>:
    Tags ac93e2fa8550 2019-01-28 00:00:00 1
  Satanand Burla <sburla@marvell.com>:
  Felix Manlunas <fmanlunas@marvell.com>:
    Tags ac93e2fa8550 2019-01-28 00:00:00 1
  Top reviewers:
    [5]: simon.horman@corigine.com
    [4]: keescook@chromium.org
    [4]: jiri@nvidia.com
  INACTIVE MAINTAINER Satanand Burla <sburla@marvell.com>

Acked-by: Derek Chickles <dchickles@marvell.com>
Link: https://lore.kernel.org/r/20240109164517.3063131-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index ceb9b669dc6c5..1ef18977427ef 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4697,11 +4697,8 @@ F:	drivers/i2c/busses/i2c-octeon*
 F:	drivers/i2c/busses/i2c-thunderx*
 
 CAVIUM LIQUIDIO NETWORK DRIVER
-M:	Derek Chickles <dchickles@marvell.com>
-M:	Satanand Burla <sburla@marvell.com>
-M:	Felix Manlunas <fmanlunas@marvell.com>
 L:	netdev@vger.kernel.org
-S:	Supported
+S:	Orphan
 W:	http://www.marvell.com
 F:	drivers/net/ethernet/cavium/liquidio/
 
-- 
GitLab


From 0bfcdce867f70a8309fe120eb5a9fff2fc54e8b6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 9 Jan 2024 08:45:15 -0800
Subject: [PATCH 2561/4076] MAINTAINERS: Bluetooth: retire Johan (for now?)

Johan moved to maintaining the Zephyr Bluetooth stack,
and we haven't heard from him on the ML in 3 years
(according to lore), and seen any tags in git in 4 years.
Trade the MAINTAINER entry for CREDITS, we can revert
whenever Johan comes back to Linux hacking :)

Subsystem BLUETOOTH SUBSYSTEM
  Changes 173 / 986 (17%)
  Last activity: 2023-12-22
  Marcel Holtmann <marcel@holtmann.org>:
    Author 91cb4c19118a 2022-01-27 00:00:00 52
    Committer edcb185fa9c4 2022-05-23 00:00:00 446
    Tags 000c2fa2c144 2023-04-23 00:00:00 523
  Johan Hedberg <johan.hedberg@gmail.com>:
  Luiz Augusto von Dentz <luiz.dentz@gmail.com>:
    Author d03376c18592 2023-12-22 00:00:00 241
    Committer da9065caa594 2023-12-22 00:00:00 341
    Tags da9065caa594 2023-12-22 00:00:00 493
  Top reviewers:
    [33]: alainm@chromium.org
    [31]: mcchou@chromium.org
    [27]: abhishekpandit@chromium.org
  INACTIVE MAINTAINER Johan Hedberg <johan.hedberg@gmail.com>

Link: https://lore.kernel.org/r/20240109164517.3063131-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 1 -
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index 4d6beeaaca3c4..3c392f7ebc6ea 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1542,6 +1542,10 @@ N: Andrew Haylett
 E: ajh@primag.co.uk
 D: Selection mechanism
 
+N: Johan Hedberg
+E: johan.hedberg@gmail.com
+D: Bluetooth subsystem maintainer
+
 N: Andre Hedrick
 E: andre@linux-ide.org
 E: andre@linuxdiskcert.org
diff --git a/MAINTAINERS b/MAINTAINERS
index 1ef18977427ef..80422f6393522 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3609,7 +3609,6 @@ F:	drivers/mtd/devices/block2mtd.c
 
 BLUETOOTH DRIVERS
 M:	Marcel Holtmann <marcel@holtmann.org>
-M:	Johan Hedberg <johan.hedberg@gmail.com>
 M:	Luiz Augusto von Dentz <luiz.dentz@gmail.com>
 L:	linux-bluetooth@vger.kernel.org
 S:	Supported
-- 
GitLab


From bd93edbfd70cdea6e2313c87c3bae5b05bbb947e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 9 Jan 2024 08:45:16 -0800
Subject: [PATCH 2562/4076] MAINTAINERS: mark ax25 as Orphan

We haven't heard from Ralf for two years, according to lore.
We get a constant stream of "fixes" to ax25 from people using
code analysis tools. Nobody is reviewing those, let's reflect
this reality in MAINTAINERS.

Subsystem AX.25 NETWORK LAYER
  Changes 9 / 59 (15%)
  (No activity)
  Top reviewers:
    [2]: mkl@pengutronix.de
    [2]: edumazet@google.com
    [2]: stefan@datenfreihafen.org
  INACTIVE MAINTAINER Ralf Baechle <ralf@linux-mips.org>

Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240109164517.3063131-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 1 +
 MAINTAINERS | 3 +--
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/CREDITS b/CREDITS
index 3c392f7ebc6ea..f7888de50220a 100644
--- a/CREDITS
+++ b/CREDITS
@@ -179,6 +179,7 @@ E: ralf@gnu.org
 P: 1024/AF7B30C1 CF 97 C2 CC 6D AE A7 FE  C8 BA 9C FC 88 DE 32 C3
 D: Linux/MIPS port
 D: Linux/68k hacker
+D: AX25 maintainer
 S: Hauptstrasse 19
 S: 79837 St. Blasien
 S: Germany
diff --git a/MAINTAINERS b/MAINTAINERS
index 80422f6393522..b736b708b34bb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3376,9 +3376,8 @@ F:	Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml
 F:	drivers/iio/adc/hx711.c
 
 AX.25 NETWORK LAYER
-M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linux-ax25.in-berlin.de
 F:	include/net/ax25.h
 F:	include/uapi/linux/ax25.h
-- 
GitLab


From f9678f5825dd852b7201132e36691fefb17d49ce Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 9 Jan 2024 08:45:17 -0800
Subject: [PATCH 2563/4076] MAINTAINERS: ibmvnic: drop Dany from reviewers

I missed that Dany uses a different email address
when tagging patches (drt@linux.ibm.com)
and asked him if he's still actively working on ibmvnic.
He doesn't really fall under our removal criteria,
but he admitted that he already moved on to other projects.

Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240109164517.3063131-8-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index b736b708b34bb..4194f414dd2c5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10155,7 +10155,6 @@ IBM Power SRIOV Virtual NIC Device Driver
 M:	Haren Myneni <haren@linux.ibm.com>
 M:	Rick Lindsley <ricklind@linux.ibm.com>
 R:	Nick Child <nnac123@linux.ibm.com>
-R:	Dany Madden <danymadden@us.ibm.com>
 R:	Thomas Falcon <tlfalcon@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
-- 
GitLab


From b3739fb3a9e6633b233d829ee799323d75162775 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 11 Jan 2024 17:27:53 +0100
Subject: [PATCH 2564/4076] wangxunx: select CONFIG_PHYLINK where needed

The ngbe driver needs phylink:

arm-linux-gnueabi-ld: drivers/net/ethernet/wangxun/libwx/wx_ethtool.o: in function `wx_nway_reset':
wx_ethtool.c:(.text+0x458): undefined reference to `phylink_ethtool_nway_reset'
arm-linux-gnueabi-ld: drivers/net/ethernet/wangxun/ngbe/ngbe_main.o: in function `ngbe_remove':
ngbe_main.c:(.text+0x7c): undefined reference to `phylink_destroy'
arm-linux-gnueabi-ld: drivers/net/ethernet/wangxun/ngbe/ngbe_main.o: in function `ngbe_open':
ngbe_main.c:(.text+0xf90): undefined reference to `phylink_connect_phy'
arm-linux-gnueabi-ld: drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.o: in function `ngbe_mdio_init':
ngbe_mdio.c:(.text+0x314): undefined reference to `phylink_create'

Add the missing Kconfig description for this.

Fixes: bc2426d74aa3 ("net: ngbe: convert phylib to phylink")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20240111162828.68564-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig
index 23cd610bd3766..85cdbdd44fec7 100644
--- a/drivers/net/ethernet/wangxun/Kconfig
+++ b/drivers/net/ethernet/wangxun/Kconfig
@@ -26,7 +26,7 @@ config NGBE
 	tristate "Wangxun(R) GbE PCI Express adapters support"
 	depends on PCI
 	select LIBWX
-	select PHYLIB
+	select PHYLINK
 	help
 	  This driver supports Wangxun(R) GbE PCI Express family of
 	  adapters.
-- 
GitLab


From e689a876969833cb1317f8752cd064595e7b61e2 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Wed, 10 Jan 2024 21:34:10 +0000
Subject: [PATCH 2565/4076] selftests/net/tcp-ao: Use LDLIBS instead of LDFLAGS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The rules to link selftests are:

> $(OUTPUT)/%_ipv4: %.c
> 	$(LINK.c) $^ $(LDLIBS) -o $@
>
> $(OUTPUT)/%_ipv6: %.c
> 	$(LINK.c) -DIPV6_TEST $^ $(LDLIBS) -o $@

The intel test robot uses only selftest's Makefile, not the top linux
Makefile:

> make W=1 O=/tmp/kselftest -C tools/testing/selftests

So, $(LINK.c) is determined by environment, rather than by kernel
Makefiles. On my machine (as well as other people that ran tcp-ao
selftests) GNU/Make implicit definition does use $(LDFLAGS):

> [dima@Mindolluin ~]$ make -p -f/dev/null | grep '^LINK.c\>'
> make: *** No targets.  Stop.
> LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH)

But, according to build robot report, it's not the case for them.
While I could just avoid using pre-defined $(LINK.c), it's also used by
selftests/lib.mk by default.

Anyways, according to GNU/Make documentation [1], I should have used
$(LDLIBS) instead of $(LDFLAGS) in the first place, so let's just do it:

> LDFLAGS
>     Extra flags to give to compilers when they are supposed to invoke
>     the linker, ‘ld’, such as -L. Libraries (-lfoo) should be added
>     to the LDLIBS variable instead.
> LDLIBS
>     Library flags or names given to compilers when they are supposed
>     to invoke the linker, ‘ld’. LOADLIBES is a deprecated (but still
>     supported) alternative to LDLIBS. Non-library linker flags, such
>     as -L, should go in the LDFLAGS variable.

[1]: https://www.gnu.org/software/make/manual/html_node/Implicit-Variables.html

Fixes: cfbab37b3da0 ("selftests/net: Add TCP-AO library")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401011151.veyYTJzq-lkp@intel.com/
Signed-off-by: Dmitry Safonov <dima@arista.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240110-tcp_ao-selftests-makefile-v1-1-aa07d043f052@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile
index 8e60bae67aa9f..522d991e310eb 100644
--- a/tools/testing/selftests/net/tcp_ao/Makefile
+++ b/tools/testing/selftests/net/tcp_ao/Makefile
@@ -52,5 +52,5 @@ $(OUTPUT)/%_ipv6: %.c
 
 $(OUTPUT)/icmps-accept_ipv4: CFLAGS+= -DTEST_ICMPS_ACCEPT
 $(OUTPUT)/icmps-accept_ipv6: CFLAGS+= -DTEST_ICMPS_ACCEPT
-$(OUTPUT)/bench-lookups_ipv4: LDFLAGS+= -lm
-$(OUTPUT)/bench-lookups_ipv6: LDFLAGS+= -lm
+$(OUTPUT)/bench-lookups_ipv4: LDLIBS+= -lm
+$(OUTPUT)/bench-lookups_ipv6: LDLIBS+= -lm
-- 
GitLab


From b33fb5b801c6db408b774a68e7c8722796b59ecc Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Wed, 10 Jan 2024 14:14:00 +0800
Subject: [PATCH 2566/4076] net: qualcomm: rmnet: fix global oob in
 rmnet_policy

The variable rmnet_link_ops assign a *bigger* maxtype which leads to a
global out-of-bounds read when parsing the netlink attributes. See bug
trace below:

==================================================================
BUG: KASAN: global-out-of-bounds in validate_nla lib/nlattr.c:386 [inline]
BUG: KASAN: global-out-of-bounds in __nla_validate_parse+0x24af/0x2750 lib/nlattr.c:600
Read of size 1 at addr ffffffff92c438d0 by task syz-executor.6/84207

CPU: 0 PID: 84207 Comm: syz-executor.6 Tainted: G                 N 6.1.0 #3
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x8b/0xb3 lib/dump_stack.c:106
 print_address_description mm/kasan/report.c:284 [inline]
 print_report+0x172/0x475 mm/kasan/report.c:395
 kasan_report+0xbb/0x1c0 mm/kasan/report.c:495
 validate_nla lib/nlattr.c:386 [inline]
 __nla_validate_parse+0x24af/0x2750 lib/nlattr.c:600
 __nla_parse+0x3e/0x50 lib/nlattr.c:697
 nla_parse_nested_deprecated include/net/netlink.h:1248 [inline]
 __rtnl_newlink+0x50a/0x1880 net/core/rtnetlink.c:3485
 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3594
 rtnetlink_rcv_msg+0x43c/0xd70 net/core/rtnetlink.c:6091
 netlink_rcv_skb+0x14f/0x410 net/netlink/af_netlink.c:2540
 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
 netlink_unicast+0x54e/0x800 net/netlink/af_netlink.c:1345
 netlink_sendmsg+0x930/0xe50 net/netlink/af_netlink.c:1921
 sock_sendmsg_nosec net/socket.c:714 [inline]
 sock_sendmsg+0x154/0x190 net/socket.c:734
 ____sys_sendmsg+0x6df/0x840 net/socket.c:2482
 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536
 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7fdcf2072359
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fdcf13e3168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007fdcf219ff80 RCX: 00007fdcf2072359
RDX: 0000000000000000 RSI: 0000000020000200 RDI: 0000000000000003
RBP: 00007fdcf20bd493 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fffbb8d7bdf R14: 00007fdcf13e3300 R15: 0000000000022000
 </TASK>

The buggy address belongs to the variable:
 rmnet_policy+0x30/0xe0

The buggy address belongs to the physical page:
page:0000000065bdeb3c refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x155243
flags: 0x200000000001000(reserved|node=0|zone=2)
raw: 0200000000001000 ffffea00055490c8 ffffea00055490c8 0000000000000000
raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffffffff92c43780: f9 f9 f9 f9 00 00 00 02 f9 f9 f9 f9 00 00 00 07
 ffffffff92c43800: f9 f9 f9 f9 00 00 00 05 f9 f9 f9 f9 06 f9 f9 f9
>ffffffff92c43880: f9 f9 f9 f9 00 00 00 00 00 00 f9 f9 f9 f9 f9 f9
                                                 ^
 ffffffff92c43900: 00 00 00 00 00 00 00 00 07 f9 f9 f9 f9 f9 f9 f9
 ffffffff92c43980: 00 00 00 07 f9 f9 f9 f9 00 00 00 05 f9 f9 f9 f9

According to the comment of `nla_parse_nested_deprecated`, the maxtype
should be len(destination array) - 1. Hence use `IFLA_RMNET_MAX` here.

Fixes: 14452ca3b5ce ("net: qualcomm: rmnet: Export mux_id and flags to netlink")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Reviewed-by: Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240110061400.3356108-1-linma@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 39d24e07f3067..5b69b9268c757 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -396,7 +396,7 @@ nla_put_failure:
 
 struct rtnl_link_ops rmnet_link_ops __read_mostly = {
 	.kind		= "rmnet",
-	.maxtype	= __IFLA_RMNET_MAX,
+	.maxtype	= IFLA_RMNET_MAX,
 	.priv_size	= sizeof(struct rmnet_priv),
 	.setup		= rmnet_vnd_setup,
 	.validate	= rmnet_rtnl_validate,
-- 
GitLab


From 844f104790bd69c2e4dbb9ee3eba46fde1fcea7b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 10 Jan 2024 02:33:54 +0200
Subject: [PATCH 2567/4076] net: dsa: fix netdev_priv() dereference before
 check on non-DSA netdevice events

After the blamed commit, we started doing this dereference for every
NETDEV_CHANGEUPPER and NETDEV_PRECHANGEUPPER event in the system.

static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev)
{
	struct dsa_user_priv *p = netdev_priv(dev);

	return p->dp;
}

Which is obviously bogus, because not all net_devices have a netdev_priv()
of type struct dsa_user_priv. But struct dsa_user_priv is fairly small,
and p->dp means dereferencing 8 bytes starting with offset 16. Most
drivers allocate that much private memory anyway, making our access not
fault, and we discard the bogus data quickly afterwards, so this wasn't
caught.

But the dummy interface is somewhat special in that it calls
alloc_netdev() with a priv size of 0. So every netdev_priv() dereference
is invalid, and we get this when we emit a NETDEV_PRECHANGEUPPER event
with a VLAN as its new upper:

$ ip link add dummy1 type dummy
$ ip link add link dummy1 name dummy1.100 type vlan id 100
[   43.309174] ==================================================================
[   43.316456] BUG: KASAN: slab-out-of-bounds in dsa_user_prechangeupper+0x30/0xe8
[   43.323835] Read of size 8 at addr ffff3f86481d2990 by task ip/374
[   43.330058]
[   43.342436] Call trace:
[   43.366542]  dsa_user_prechangeupper+0x30/0xe8
[   43.371024]  dsa_user_netdevice_event+0xb38/0xee8
[   43.375768]  notifier_call_chain+0xa4/0x210
[   43.379985]  raw_notifier_call_chain+0x24/0x38
[   43.384464]  __netdev_upper_dev_link+0x3ec/0x5d8
[   43.389120]  netdev_upper_dev_link+0x70/0xa8
[   43.393424]  register_vlan_dev+0x1bc/0x310
[   43.397554]  vlan_newlink+0x210/0x248
[   43.401247]  rtnl_newlink+0x9fc/0xe30
[   43.404942]  rtnetlink_rcv_msg+0x378/0x580

Avoid the kernel oops by dereferencing after the type check, as customary.

Fixes: 4c3f80d22b2e ("net: dsa: walk through all changeupper notifier functions")
Reported-and-tested-by: syzbot+d81bcd883824180500c8@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/0000000000001d4255060e87545c@google.com/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240110003354.2796778-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dsa/user.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/dsa/user.c b/net/dsa/user.c
index b738a466e2dcc..b15e71cc342c7 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -2806,13 +2806,14 @@ EXPORT_SYMBOL_GPL(dsa_user_dev_check);
 static int dsa_user_changeupper(struct net_device *dev,
 				struct netdev_notifier_changeupper_info *info)
 {
-	struct dsa_port *dp = dsa_user_to_port(dev);
 	struct netlink_ext_ack *extack;
 	int err = NOTIFY_DONE;
+	struct dsa_port *dp;
 
 	if (!dsa_user_dev_check(dev))
 		return err;
 
+	dp = dsa_user_to_port(dev);
 	extack = netdev_notifier_info_to_extack(&info->info);
 
 	if (netif_is_bridge_master(info->upper_dev)) {
@@ -2865,11 +2866,13 @@ static int dsa_user_changeupper(struct net_device *dev,
 static int dsa_user_prechangeupper(struct net_device *dev,
 				   struct netdev_notifier_changeupper_info *info)
 {
-	struct dsa_port *dp = dsa_user_to_port(dev);
+	struct dsa_port *dp;
 
 	if (!dsa_user_dev_check(dev))
 		return NOTIFY_DONE;
 
+	dp = dsa_user_to_port(dev);
+
 	if (netif_is_bridge_master(info->upper_dev) && !info->linking)
 		dsa_port_pre_bridge_leave(dp, info->upper_dev);
 	else if (netif_is_lag_master(info->upper_dev) && !info->linking)
-- 
GitLab


From 8722014311e613244f33952354956a82fa4b0472 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 9 Jan 2024 15:10:48 +0000
Subject: [PATCH 2568/4076] rxrpc: Fix use of Don't Fragment flag

rxrpc normally has the Don't Fragment flag set on the UDP packets it
transmits, except when it has decided that DATA packets aren't getting
through - in which case it turns it off just for the DATA transmissions.
This can be a problem, however, for RESPONSE packets that convey
authentication and crypto data from the client to the server as ticket may
be larger than can fit in the MTU.

In such a case, rxrpc gets itself into an infinite loop as the sendmsg
returns an error (EMSGSIZE), which causes rxkad_send_response() to return
-EAGAIN - and the CHALLENGE packet is put back on the Rx queue to retry,
leading to the I/O thread endlessly attempting to perform the transmission.

Fix this by disabling DF on RESPONSE packets for now.  The use of DF and
best data MTU determination needs reconsidering at some point in the
future.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-afs@lists.infradead.org
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/1581852.1704813048@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/ar-internal.h  |  1 +
 net/rxrpc/local_object.c | 13 ++++++++++++-
 net/rxrpc/output.c       |  6 ++----
 net/rxrpc/rxkad.c        |  2 ++
 4 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 2f8b39a614c31..dbeb75c298573 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -1079,6 +1079,7 @@ void rxrpc_send_version_request(struct rxrpc_local *local,
 /*
  * local_object.c
  */
+void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set);
 struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *);
 struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace);
 struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace);
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index c553a30e9c838..34d3073681353 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -36,6 +36,17 @@ static void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, int err,
 		return ipv6_icmp_error(sk, skb, err, port, info, payload);
 }
 
+/*
+ * Set or clear the Don't Fragment flag on a socket.
+ */
+void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set)
+{
+	if (set)
+		ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DO);
+	else
+		ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DONT);
+}
+
 /*
  * Compare a local to an address.  Return -ve, 0 or +ve to indicate less than,
  * same or greater than.
@@ -203,7 +214,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		ip_sock_set_recverr(usk);
 
 		/* we want to set the don't fragment bit */
-		ip_sock_set_mtu_discover(usk, IP_PMTUDISC_DO);
+		rxrpc_local_dont_fragment(local, true);
 
 		/* We want receive timestamps. */
 		sock_enable_timestamps(usk);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 5e53429c69228..a0906145e8293 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -494,14 +494,12 @@ send_fragmentable:
 	switch (conn->local->srx.transport.family) {
 	case AF_INET6:
 	case AF_INET:
-		ip_sock_set_mtu_discover(conn->local->socket->sk,
-					 IP_PMTUDISC_DONT);
+		rxrpc_local_dont_fragment(conn->local, false);
 		rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag);
 		ret = do_udp_sendmsg(conn->local->socket, &msg, len);
 		conn->peer->last_tx_at = ktime_get_seconds();
 
-		ip_sock_set_mtu_discover(conn->local->socket->sk,
-					 IP_PMTUDISC_DO);
+		rxrpc_local_dont_fragment(conn->local, true);
 		break;
 
 	default:
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 1bf571a66e020..b52dedcebce0a 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -724,7 +724,9 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 	serial = atomic_inc_return(&conn->serial);
 	whdr.serial = htonl(serial);
 
+	rxrpc_local_dont_fragment(conn->local, false);
 	ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len);
+	rxrpc_local_dont_fragment(conn->local, true);
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
 				    rxrpc_tx_point_rxkad_response);
-- 
GitLab


From ec4ffd100ffb396eca13ebe7d18938ea80f399c3 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 8 Jan 2024 10:41:02 +0100
Subject: [PATCH 2569/4076] Revert "net: rtnetlink: Enslave device before
 bringing it up"

This reverts commit a4abfa627c3865c37e036bccb681619a50d3d93c.

The patch broke:
> ip link set dummy0 up
> ip link set dummy0 master bond0 down

This last command is useful to be able to enslave an interface with only
one netlink message.

After discussion, there is no good reason to support:
> ip link set dummy0 down
> ip link set dummy0 master bond0 up
because the bond interface already set the slave up when it is up.

Cc: stable@vger.kernel.org
Fixes: a4abfa627c38 ("net: rtnetlink: Enslave device before bringing it up")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20240108094103.2001224-2-nicolas.dichtel@6wind.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/rtnetlink.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5f6ed6da3cfc0..f6f29eb03ec27 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2899,13 +2899,6 @@ static int do_setlink(const struct sk_buff *skb,
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
 	}
 
-	if (tb[IFLA_MASTER]) {
-		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
-		if (err)
-			goto errout;
-		status |= DO_SETLINK_MODIFIED;
-	}
-
 	if (ifm->ifi_flags || ifm->ifi_change) {
 		err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
 				       extack);
@@ -2913,6 +2906,13 @@ static int do_setlink(const struct sk_buff *skb,
 			goto errout;
 	}
 
+	if (tb[IFLA_MASTER]) {
+		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
+		if (err)
+			goto errout;
+		status |= DO_SETLINK_MODIFIED;
+	}
+
 	if (tb[IFLA_CARRIER]) {
 		err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
 		if (err)
-- 
GitLab


From a159cbe81d3b88bf35cd4edb4e6040d015972fdd Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 8 Jan 2024 10:41:03 +0100
Subject: [PATCH 2570/4076] selftests: rtnetlink: check enslaving iface in a
 bond

The goal is to check the following two sequences:
> ip link set dummy0 up
> ip link set dummy0 master bond0 down

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240108094103.2001224-3-nicolas.dichtel@6wind.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/rtnetlink.sh | 28 ++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index a10a32952f216..a31be0eaaa50f 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -28,6 +28,7 @@ ALL_TESTS="
 	kci_test_neigh_get
 	kci_test_bridge_parent_id
 	kci_test_address_proto
+	kci_test_enslave_bonding
 "
 
 devdummy="test-dummy0"
@@ -1241,6 +1242,33 @@ kci_test_address_proto()
 	return $ret
 }
 
+kci_test_enslave_bonding()
+{
+	local testns="testns"
+	local bond="bond123"
+	local dummy="dummy123"
+	local ret=0
+
+	run_cmd ip netns add "$testns"
+	if [ $ret -ne 0 ]; then
+		end_test "SKIP bonding tests: cannot add net namespace $testns"
+		return $ksft_skip
+	fi
+
+	run_cmd ip -netns $testns link add dev $bond type bond mode balance-rr
+	run_cmd ip -netns $testns link add dev $dummy type dummy
+	run_cmd ip -netns $testns link set dev $dummy up
+	run_cmd ip -netns $testns link set dev $dummy master $bond down
+	if [ $ret -ne 0 ]; then
+		end_test "FAIL: initially up interface added to a bond and set down"
+		ip netns del "$testns"
+		return 1
+	fi
+
+	end_test "PASS: enslave interface in a bond"
+	ip netns del "$testns"
+}
+
 kci_test_rtnl()
 {
 	local current_test
-- 
GitLab


From a0cb76a770083a22167659e64ba69af6425b1d9b Mon Sep 17 00:00:00 2001
From: Nithin Dabilpuram <ndabilpuram@marvell.com>
Date: Mon, 8 Jan 2024 13:00:36 +0530
Subject: [PATCH 2571/4076] octeontx2-af: CN10KB: Fix FIFO length calculation
 for RPM2

RPM0 and RPM1 on the CN10KB SoC have 8 LMACs each, whereas RPM2
has only 4 LMACs. Similarly, the RPM0 and RPM1 have 256KB FIFO,
whereas RPM2 has 128KB FIFO. This patch fixes an issue with
improper TX credit programming for the RPM2 link.

Fixes: b9d0fedc6234 ("octeontx2-af: cn10kb: Add RPM_USX MAC support")
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Naveen Mamindlapalli <naveenm@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240108073036.8766-1-naveenm@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rpm.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index 4728ba34b0e34..76218f1cb4595 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -506,6 +506,7 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id)
 	rpm_t *rpm = rpmd;
 	u8 num_lmacs;
 	u32 fifo_len;
+	u16 max_lmac;
 
 	lmac_info = rpm_read(rpm, 0, RPM2_CMRX_RX_LMACS);
 	/* LMACs are divided into two groups and each group
@@ -513,7 +514,11 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id)
 	 * Group0 lmac_id range {0..3}
 	 * Group1 lmac_id range {4..7}
 	 */
-	fifo_len = rpm->mac_ops->fifo_len / 2;
+	max_lmac = (rpm_read(rpm, 0, CGX_CONST) >> 24) & 0xFF;
+	if (max_lmac > 4)
+		fifo_len = rpm->mac_ops->fifo_len / 2;
+	else
+		fifo_len = rpm->mac_ops->fifo_len;
 
 	if (lmac_id < 4) {
 		num_lmacs = hweight8(lmac_info & 0xF);
-- 
GitLab


From e3fe8d28c67bf6c291e920c6d04fa22afa14e6e4 Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@linux.dev>
Date: Thu, 4 Jan 2024 10:09:02 +0800
Subject: [PATCH 2572/4076] =?UTF-8?q?virtio=5Fnet:=20Fix=20"=E2=80=98%d?=
 =?UTF-8?q?=E2=80=99=20directive=20writing=20between=201=20and=2011=20byte?=
 =?UTF-8?q?s=20into=20a=20region=20of=20size=2010"=20warnings?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the warnings when building virtio_net driver.

"
drivers/net/virtio_net.c: In function ‘init_vqs’:
drivers/net/virtio_net.c:4551:48: warning: ‘%d’ directive writing between 1 and 11 bytes into a region of size 10 [-Wformat-overflow=]
 4551 |                 sprintf(vi->rq[i].name, "input.%d", i);
      |                                                ^~
In function ‘virtnet_find_vqs’,
    inlined from ‘init_vqs’ at drivers/net/virtio_net.c:4645:8:
drivers/net/virtio_net.c:4551:41: note: directive argument in the range [-2147483643, 65534]
 4551 |                 sprintf(vi->rq[i].name, "input.%d", i);
      |                                         ^~~~~~~~~~
drivers/net/virtio_net.c:4551:17: note: ‘sprintf’ output between 8 and 18 bytes into a destination of size 16
 4551 |                 sprintf(vi->rq[i].name, "input.%d", i);
      |                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/net/virtio_net.c: In function ‘init_vqs’:
drivers/net/virtio_net.c:4552:49: warning: ‘%d’ directive writing between 1 and 11 bytes into a region of size 9 [-Wformat-overflow=]
 4552 |                 sprintf(vi->sq[i].name, "output.%d", i);
      |                                                 ^~
In function ‘virtnet_find_vqs’,
    inlined from ‘init_vqs’ at drivers/net/virtio_net.c:4645:8:
drivers/net/virtio_net.c:4552:41: note: directive argument in the range [-2147483643, 65534]
 4552 |                 sprintf(vi->sq[i].name, "output.%d", i);
      |                                         ^~~~~~~~~~~
drivers/net/virtio_net.c:4552:17: note: ‘sprintf’ output between 9 and 19 bytes into a destination of size 16
 4552 |                 sprintf(vi->sq[i].name, "output.%d", i);

"

Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Link: https://lore.kernel.org/r/20240104020902.2753599-1-yanjun.zhu@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3cb8aa1938841..d7ce4a1011ea2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -4295,10 +4295,11 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 {
 	vq_callback_t **callbacks;
 	struct virtqueue **vqs;
-	int ret = -ENOMEM;
-	int i, total_vqs;
 	const char **names;
+	int ret = -ENOMEM;
+	int total_vqs;
 	bool *ctx;
+	u16 i;
 
 	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
 	 * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
@@ -4335,8 +4336,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		callbacks[rxq2vq(i)] = skb_recv_done;
 		callbacks[txq2vq(i)] = skb_xmit_done;
-		sprintf(vi->rq[i].name, "input.%d", i);
-		sprintf(vi->sq[i].name, "output.%d", i);
+		sprintf(vi->rq[i].name, "input.%u", i);
+		sprintf(vi->sq[i].name, "output.%u", i);
 		names[rxq2vq(i)] = vi->rq[i].name;
 		names[txq2vq(i)] = vi->sq[i].name;
 		if (ctx)
-- 
GitLab


From 64e47d8afb5ca533b27efc006405e5bcae2c4a7b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sanju=C3=A1n=20Garc=C3=ADa=2C=20Jorge?=
 <Jorge.SanjuanGarcia@duagon.com>
Date: Fri, 5 Jan 2024 08:55:43 +0000
Subject: [PATCH 2573/4076] net: ethernet: ti: am65-cpsw: Fix max mtu to fit
 ethernet frames

The value of AM65_CPSW_MAX_PACKET_SIZE represents the maximum length
of a received frame. This value is written to the register
AM65_CPSW_PORT_REG_RX_MAXLEN.

The maximum MTU configured on the network device should then leave
some room for the ethernet headers and frame check. Otherwise, if
the network interface is configured to its maximum mtu possible,
the frames will be larger than AM65_CPSW_MAX_PACKET_SIZE and will
get dropped as oversized.

The switch supports ethernet frame sizes between 64 and 2024 bytes
(including VLAN) as stated in the technical reference manual, so
define AM65_CPSW_MAX_PACKET_SIZE with that maximum size.

Fixes: 93a76530316a ("net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver")
Signed-off-by: Jorge Sanjuan Garcia <jorge.sanjuangarcia@duagon.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Link: https://lore.kernel.org/r/20240105085530.14070-2-jorge.sanjuangarcia@duagon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index faa0561e988ec..9d2f4ac783e43 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -56,7 +56,7 @@
 #define AM65_CPSW_MAX_PORTS	8
 
 #define AM65_CPSW_MIN_PACKET_SIZE	VLAN_ETH_ZLEN
-#define AM65_CPSW_MAX_PACKET_SIZE	(VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
+#define AM65_CPSW_MAX_PACKET_SIZE	2024
 
 #define AM65_CPSW_REG_CTL		0x004
 #define AM65_CPSW_REG_STAT_PORT_EN	0x014
@@ -2244,7 +2244,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	eth_hw_addr_set(port->ndev, port->slave.mac_addr);
 
 	port->ndev->min_mtu = AM65_CPSW_MIN_PACKET_SIZE;
-	port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE;
+	port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE -
+			      (VLAN_ETH_HLEN + ETH_FCS_LEN);
 	port->ndev->hw_features = NETIF_F_SG |
 				  NETIF_F_RXCSUM |
 				  NETIF_F_HW_CSUM |
-- 
GitLab


From bec161add35b478a7746bf58bcdea6faa19129ef Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 7 Jan 2024 14:42:41 +0000
Subject: [PATCH 2574/4076] amt: do not use overwrapped cb area

amt driver uses skb->cb for storing tunnel information.
This job is worked before TC layer and then amt driver load tunnel info
from skb->cb after TC layer.
So, its cb area should not be overwrapped with CB area used by TC.
In order to not use cb area used by TC, it skips the biggest cb
structure used by TC, which was qdisc_skb_cb.
But it's not anymore.
Currently, biggest structure of TC's CB is tc_skb_cb.
So, it should skip size of tc_skb_cb instead of qdisc_skb_cb.

Fixes: ec624fe740b4 ("net/sched: Extend qdisc control block with tc control block")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20240107144241.4169520-1-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/amt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 53415e83821ce..68e79b1272f6b 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -11,7 +11,7 @@
 #include <linux/net.h>
 #include <linux/igmp.h>
 #include <linux/workqueue.h>
-#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
 #include <net/net_namespace.h>
 #include <net/ip.h>
 #include <net/udp.h>
@@ -80,11 +80,11 @@ static struct mld2_grec mldv2_zero_grec;
 
 static struct amt_skb_cb *amt_skb_cb(struct sk_buff *skb)
 {
-	BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct qdisc_skb_cb) >
+	BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct tc_skb_cb) >
 		     sizeof_field(struct sk_buff, cb));
 
 	return (struct amt_skb_cb *)((void *)skb->cb +
-		sizeof(struct qdisc_skb_cb));
+		sizeof(struct tc_skb_cb));
 }
 
 static void __amt_source_gc_work(void)
-- 
GitLab


From b271fee9a41ca1474d30639fd6cc912c9901d0f8 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Tue, 19 Dec 2023 01:02:28 +0900
Subject: [PATCH 2575/4076] btrfs: zoned: factor out prepare_allocation_zoned()

Factor out prepare_allocation_zoned() for further extension. While at
it, optimize the if-branch a bit.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f396aba92c579..d260b970bec77 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4298,6 +4298,24 @@ static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info,
+				    struct find_free_extent_ctl *ffe_ctl)
+{
+	if (ffe_ctl->for_treelog) {
+		spin_lock(&fs_info->treelog_bg_lock);
+		if (fs_info->treelog_bg)
+			ffe_ctl->hint_byte = fs_info->treelog_bg;
+		spin_unlock(&fs_info->treelog_bg_lock);
+	} else if (ffe_ctl->for_data_reloc) {
+		spin_lock(&fs_info->relocation_bg_lock);
+		if (fs_info->data_reloc_bg)
+			ffe_ctl->hint_byte = fs_info->data_reloc_bg;
+		spin_unlock(&fs_info->relocation_bg_lock);
+	}
+
+	return 0;
+}
+
 static int prepare_allocation(struct btrfs_fs_info *fs_info,
 			      struct find_free_extent_ctl *ffe_ctl,
 			      struct btrfs_space_info *space_info,
@@ -4308,19 +4326,7 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
 		return prepare_allocation_clustered(fs_info, ffe_ctl,
 						    space_info, ins);
 	case BTRFS_EXTENT_ALLOC_ZONED:
-		if (ffe_ctl->for_treelog) {
-			spin_lock(&fs_info->treelog_bg_lock);
-			if (fs_info->treelog_bg)
-				ffe_ctl->hint_byte = fs_info->treelog_bg;
-			spin_unlock(&fs_info->treelog_bg_lock);
-		}
-		if (ffe_ctl->for_data_reloc) {
-			spin_lock(&fs_info->relocation_bg_lock);
-			if (fs_info->data_reloc_bg)
-				ffe_ctl->hint_byte = fs_info->data_reloc_bg;
-			spin_unlock(&fs_info->relocation_bg_lock);
-		}
-		return 0;
+		return prepare_allocation_zoned(fs_info, ffe_ctl);
 	default:
 		BUG();
 	}
-- 
GitLab


From 02444f2ac26eae6385a65fcd66915084d15dffba Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Tue, 19 Dec 2023 01:02:29 +0900
Subject: [PATCH 2576/4076] btrfs: zoned: optimize hint byte for zoned
 allocator

Writing sequentially to a huge file on btrfs on a SMR HDD revealed a
decline of the performance (220 MiB/s to 30 MiB/s after 500 minutes).

The performance goes down because of increased latency of the extent
allocation, which is induced by a traversing of a lot of full block groups.

So, this patch optimizes the ffe_ctl->hint_byte by choosing a block group
with sufficient size from the active block group list, which does not
contain full block groups.

After applying the patch, the performance is maintained well.

Fixes: 2eda57089ea3 ("btrfs: zoned: implement sequential extent allocation")
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d260b970bec77..6d680031211a1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4311,6 +4311,24 @@ static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info,
 		if (fs_info->data_reloc_bg)
 			ffe_ctl->hint_byte = fs_info->data_reloc_bg;
 		spin_unlock(&fs_info->relocation_bg_lock);
+	} else if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) {
+		struct btrfs_block_group *block_group;
+
+		spin_lock(&fs_info->zone_active_bgs_lock);
+		list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) {
+			/*
+			 * No lock is OK here because avail is monotinically
+			 * decreasing, and this is just a hint.
+			 */
+			u64 avail = block_group->zone_capacity - block_group->alloc_offset;
+
+			if (block_group_bits(block_group, ffe_ctl->flags) &&
+			    avail >= ffe_ctl->num_bytes) {
+				ffe_ctl->hint_byte = block_group->start;
+				break;
+			}
+		}
+		spin_unlock(&fs_info->zone_active_bgs_lock);
 	}
 
 	return 0;
-- 
GitLab


From 6ff09b6b8c2fb6b3edda4ffaa173153a40653067 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 21 Dec 2023 11:47:45 +0300
Subject: [PATCH 2577/4076] btrfs: fix kvcalloc() arguments order in
 btrfs_ioctl_send()

When compiling with gcc version 14.0.0 20231220 (experimental)
and W=1, I've noticed the following warning:

fs/btrfs/send.c: In function 'btrfs_ioctl_send':
fs/btrfs/send.c:8208:44: warning: 'kvcalloc' sizes specified with 'sizeof'
in the earlier argument and not in the later argument [-Wcalloc-transposed-args]
 8208 |         sctx->clone_roots = kvcalloc(sizeof(*sctx->clone_roots),
      |                                            ^

Since 'n' and 'size' arguments of 'kvcalloc()' are multiplied to
calculate the final size, their actual order doesn't affect the result
and so this is not a bug. But it's still worth to fix it.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/send.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4e36550618e58..2d7519a6ce72d 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -8205,8 +8205,8 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 		goto out;
 	}
 
-	sctx->clone_roots = kvcalloc(sizeof(*sctx->clone_roots),
-				     arg->clone_sources_count + 1,
+	sctx->clone_roots = kvcalloc(arg->clone_sources_count + 1,
+				     sizeof(*sctx->clone_roots),
 				     GFP_KERNEL);
 	if (!sctx->clone_roots) {
 		ret = -ENOMEM;
-- 
GitLab


From f03e274a8b29d1d1c1bbd7f764766cb5ca537ab7 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Wed, 3 Jan 2024 13:31:27 +0300
Subject: [PATCH 2578/4076] btrfs: ref-verify: free ref cache before clearing
 mount opt

As clearing REF_VERIFY mount option indicates there were some errors in a
ref-verify process, a ref cache is not relevant anymore and should be
freed.

btrfs_free_ref_cache() requires REF_VERIFY option being set so call
it just before clearing the mount option.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Reported-by: syzbot+be14ed7728594dc8bd42@syzkaller.appspotmail.com
Fixes: fd708b81d972 ("Btrfs: add a extent ref verify tool")
CC: stable@vger.kernel.org # 5.4+
Closes: https://lore.kernel.org/lkml/000000000000e5a65c05ee832054@google.com/
Reported-by: syzbot+c563a3c79927971f950f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/0000000000007fe09705fdc6086c@google.com/
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ref-verify.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 6486f0d7e9931..8c4fc98ca9ce7 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -889,8 +889,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 out_unlock:
 	spin_unlock(&fs_info->ref_verify_lock);
 out:
-	if (ret)
+	if (ret) {
+		btrfs_free_ref_cache(fs_info);
 		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
+	}
 	return ret;
 }
 
@@ -1021,8 +1023,8 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
 		}
 	}
 	if (ret) {
-		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
 		btrfs_free_ref_cache(fs_info);
+		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
 	}
 	btrfs_free_path(path);
 	return ret;
-- 
GitLab


From d967c914a633ee797255261808720f791b658f24 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Fri, 22 Dec 2023 01:46:16 +0900
Subject: [PATCH 2579/4076] btrfs: fix unbalanced unlock of mapping_tree_lock

The error path of btrfs_get_chunk_map() releases
fs_info->mapping_tree_lock. But, it is taken and released in
btrfs_find_chunk_map(). So, there is no need to do so.

Fixes: 7dc66abb5a47 ("btrfs: use a dedicated data structure for chunk maps")
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4c32497311d2f..d67785be2c778 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3087,7 +3087,6 @@ struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
 	map = btrfs_find_chunk_map(fs_info, logical, length);
 
 	if (unlikely(!map)) {
-		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
 			   "unable to find chunk map for logical %llu length %llu",
 			   logical, length);
@@ -3095,7 +3094,6 @@ struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
 	}
 
 	if (unlikely(map->start > logical || map->start + map->chunk_len <= logical)) {
-		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
 			   "found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
 			   logical, logical + length, map->start,
-- 
GitLab


From b18f3b60b35a8c01c9a2a0f0d6424c6d73971dc3 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Fri, 22 Dec 2023 13:56:34 +0900
Subject: [PATCH 2580/4076] btrfs: zoned: fix lock ordering in
 btrfs_zone_activate()

The btrfs CI reported a lockdep warning as follows by running generic
generic/129.

   WARNING: possible circular locking dependency detected
   6.7.0-rc5+ #1 Not tainted
   ------------------------------------------------------
   kworker/u5:5/793427 is trying to acquire lock:
   ffff88813256d028 (&cache->lock){+.+.}-{2:2}, at: btrfs_zone_finish_one_bg+0x5e/0x130
   but task is already holding lock:
   ffff88810a23a318 (&fs_info->zone_active_bgs_lock){+.+.}-{2:2}, at: btrfs_zone_finish_one_bg+0x34/0x130
   which lock already depends on the new lock.

   the existing dependency chain (in reverse order) is:
   -> #1 (&fs_info->zone_active_bgs_lock){+.+.}-{2:2}:
   ...
   -> #0 (&cache->lock){+.+.}-{2:2}:
   ...

This is because we take fs_info->zone_active_bgs_lock after a block_group's
lock in btrfs_zone_activate() while doing the opposite in other places.

Fix the issue by expanding the fs_info->zone_active_bgs_lock's critical
section and taking it before a block_group's lock.

Fixes: a7e1ac7bdc5a ("btrfs: zoned: reserve zones for an active metadata/system block group")
CC: stable@vger.kernel.org # 6.6
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 12066afc235c3..ac9bbe0c4ffe6 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2072,6 +2072,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 
 	map = block_group->physical_map;
 
+	spin_lock(&fs_info->zone_active_bgs_lock);
 	spin_lock(&block_group->lock);
 	if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) {
 		ret = true;
@@ -2084,7 +2085,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 		goto out_unlock;
 	}
 
-	spin_lock(&fs_info->zone_active_bgs_lock);
 	for (i = 0; i < map->num_stripes; i++) {
 		struct btrfs_zoned_device_info *zinfo;
 		int reserved = 0;
@@ -2104,20 +2104,17 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 		 */
 		if (atomic_read(&zinfo->active_zones_left) <= reserved) {
 			ret = false;
-			spin_unlock(&fs_info->zone_active_bgs_lock);
 			goto out_unlock;
 		}
 
 		if (!btrfs_dev_set_active_zone(device, physical)) {
 			/* Cannot activate the zone */
 			ret = false;
-			spin_unlock(&fs_info->zone_active_bgs_lock);
 			goto out_unlock;
 		}
 		if (!is_data)
 			zinfo->reserved_active_zones--;
 	}
-	spin_unlock(&fs_info->zone_active_bgs_lock);
 
 	/* Successfully activated all the zones */
 	set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags);
@@ -2125,8 +2122,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 
 	/* For the active block group list */
 	btrfs_get_block_group(block_group);
-
-	spin_lock(&fs_info->zone_active_bgs_lock);
 	list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs);
 	spin_unlock(&fs_info->zone_active_bgs_lock);
 
@@ -2134,6 +2129,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 
 out_unlock:
 	spin_unlock(&block_group->lock);
+	spin_unlock(&fs_info->zone_active_bgs_lock);
 	return ret;
 }
 
-- 
GitLab


From 7081929ab2572920e94d70be3d332e5c9f97095a Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Thu, 4 Jan 2024 11:48:46 -0800
Subject: [PATCH 2581/4076] btrfs: don't abort filesystem when attempting to
 snapshot deleted subvolume

If the source file descriptor to the snapshot ioctl refers to a deleted
subvolume, we get the following abort:

  BTRFS: Transaction aborted (error -2)
  WARNING: CPU: 0 PID: 833 at fs/btrfs/transaction.c:1875 create_pending_snapshot+0x1040/0x1190 [btrfs]
  Modules linked in: pata_acpi btrfs ata_piix libata scsi_mod virtio_net blake2b_generic xor net_failover virtio_rng failover scsi_common rng_core raid6_pq libcrc32c
  CPU: 0 PID: 833 Comm: t_snapshot_dele Not tainted 6.7.0-rc6 #2
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-1.fc39 04/01/2014
  RIP: 0010:create_pending_snapshot+0x1040/0x1190 [btrfs]
  RSP: 0018:ffffa09c01337af8 EFLAGS: 00010282
  RAX: 0000000000000000 RBX: ffff9982053e7c78 RCX: 0000000000000027
  RDX: ffff99827dc20848 RSI: 0000000000000001 RDI: ffff99827dc20840
  RBP: ffffa09c01337c00 R08: 0000000000000000 R09: ffffa09c01337998
  R10: 0000000000000003 R11: ffffffffb96da248 R12: fffffffffffffffe
  R13: ffff99820535bb28 R14: ffff99820b7bd000 R15: ffff99820381ea80
  FS:  00007fe20aadabc0(0000) GS:ffff99827dc00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000559a120b502f CR3: 00000000055b6000 CR4: 00000000000006f0
  Call Trace:
   <TASK>
   ? create_pending_snapshot+0x1040/0x1190 [btrfs]
   ? __warn+0x81/0x130
   ? create_pending_snapshot+0x1040/0x1190 [btrfs]
   ? report_bug+0x171/0x1a0
   ? handle_bug+0x3a/0x70
   ? exc_invalid_op+0x17/0x70
   ? asm_exc_invalid_op+0x1a/0x20
   ? create_pending_snapshot+0x1040/0x1190 [btrfs]
   ? create_pending_snapshot+0x1040/0x1190 [btrfs]
   create_pending_snapshots+0x92/0xc0 [btrfs]
   btrfs_commit_transaction+0x66b/0xf40 [btrfs]
   btrfs_mksubvol+0x301/0x4d0 [btrfs]
   btrfs_mksnapshot+0x80/0xb0 [btrfs]
   __btrfs_ioctl_snap_create+0x1c2/0x1d0 [btrfs]
   btrfs_ioctl_snap_create_v2+0xc4/0x150 [btrfs]
   btrfs_ioctl+0x8a6/0x2650 [btrfs]
   ? kmem_cache_free+0x22/0x340
   ? do_sys_openat2+0x97/0xe0
   __x64_sys_ioctl+0x97/0xd0
   do_syscall_64+0x46/0xf0
   entry_SYSCALL_64_after_hwframe+0x6e/0x76
  RIP: 0033:0x7fe20abe83af
  RSP: 002b:00007ffe6eff1360 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
  RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007fe20abe83af
  RDX: 00007ffe6eff23c0 RSI: 0000000050009417 RDI: 0000000000000003
  RBP: 0000000000000003 R08: 0000000000000000 R09: 00007fe20ad16cd0
  R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
  R13: 00007ffe6eff13c0 R14: 00007fe20ad45000 R15: 0000559a120b6d58
   </TASK>
  ---[ end trace 0000000000000000 ]---
  BTRFS: error (device vdc: state A) in create_pending_snapshot:1875: errno=-2 No such entry
  BTRFS info (device vdc: state EA): forced readonly
  BTRFS warning (device vdc: state EA): Skipping commit of aborted transaction.
  BTRFS: error (device vdc: state EA) in cleanup_transaction:2055: errno=-2 No such entry

This happens because create_pending_snapshot() initializes the new root
item as a copy of the source root item. This includes the refs field,
which is 0 for a deleted subvolume. The call to btrfs_insert_root()
therefore inserts a root with refs == 0. btrfs_get_new_fs_root() then
finds the root and returns -ENOENT if refs == 0, which causes
create_pending_snapshot() to abort.

Fix it by checking the source root's refs before attempting the
snapshot, but after locking subvol_sem to avoid racing with deletion.

CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4e50b62db2a8f..fea5d37528b80 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -790,6 +790,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		return -EOPNOTSUPP;
 	}
 
+	if (btrfs_root_refs(&root->root_item) == 0)
+		return -ENOENT;
+
 	if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
 		return -EINVAL;
 
-- 
GitLab


From 3324d0547861b16cf436d54abba7052e0c8aa9de Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Thu, 4 Jan 2024 11:48:47 -0800
Subject: [PATCH 2582/4076] btrfs: avoid copying BTRFS_ROOT_SUBVOL_DEAD flag to
 snapshot of subvolume being deleted

Sweet Tea spotted a race between subvolume deletion and snapshotting
that can result in the root item for the snapshot having the
BTRFS_ROOT_SUBVOL_DEAD flag set. The race is:

Thread 1                                      | Thread 2
----------------------------------------------|----------
btrfs_delete_subvolume                        |
  btrfs_set_root_flags(BTRFS_ROOT_SUBVOL_DEAD)|
                                              |btrfs_mksubvol
                                              |  down_read(subvol_sem)
                                              |  create_snapshot
                                              |    ...
                                              |    create_pending_snapshot
                                              |      copy root item from source
  down_write(subvol_sem)                      |

This flag is only checked in send and swap activate, which this would
cause to fail mysteriously.

create_snapshot() now checks the root refs to reject a deleted
subvolume, so we can fix this by locking subvol_sem earlier so that the
BTRFS_ROOT_SUBVOL_DEAD flag and the root refs are updated atomically.

CC: stable@vger.kernel.org # 4.14+
Reported-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me>
Reviewed-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b3e39610cc95a..7bcc1c03437a8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4458,6 +4458,8 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	u64 root_flags;
 	int ret;
 
+	down_write(&fs_info->subvol_sem);
+
 	/*
 	 * Don't allow to delete a subvolume with send in progress. This is
 	 * inside the inode lock so the error handling that has to drop the bit
@@ -4469,25 +4471,25 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu during send",
 			   dest->root_key.objectid);
-		return -EPERM;
+		ret = -EPERM;
+		goto out_up_write;
 	}
 	if (atomic_read(&dest->nr_swapfiles)) {
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu with active swapfile",
 			   root->root_key.objectid);
-		return -EPERM;
+		ret = -EPERM;
+		goto out_up_write;
 	}
 	root_flags = btrfs_root_flags(&dest->root_item);
 	btrfs_set_root_flags(&dest->root_item,
 			     root_flags | BTRFS_ROOT_SUBVOL_DEAD);
 	spin_unlock(&dest->root_item_lock);
 
-	down_write(&fs_info->subvol_sem);
-
 	ret = may_destroy_subvol(dest);
 	if (ret)
-		goto out_up_write;
+		goto out_undead;
 
 	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
 	/*
@@ -4497,7 +4499,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	 */
 	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
 	if (ret)
-		goto out_up_write;
+		goto out_undead;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
@@ -4563,15 +4565,17 @@ out_end_trans:
 	inode->i_flags |= S_DEAD;
 out_release:
 	btrfs_subvolume_release_metadata(root, &block_rsv);
-out_up_write:
-	up_write(&fs_info->subvol_sem);
+out_undead:
 	if (ret) {
 		spin_lock(&dest->root_item_lock);
 		root_flags = btrfs_root_flags(&dest->root_item);
 		btrfs_set_root_flags(&dest->root_item,
 				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
 		spin_unlock(&dest->root_item_lock);
-	} else {
+	}
+out_up_write:
+	up_write(&fs_info->subvol_sem);
+	if (!ret) {
 		d_invalidate(dentry);
 		btrfs_prune_dentries(dest);
 		ASSERT(dest->send_in_progress == 0);
-- 
GitLab


From 173431b274a9a54fc10b273b46e67f46bcf62d2e Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 10 Jan 2024 08:58:26 +1030
Subject: [PATCH 2583/4076] btrfs: defrag: reject unknown flags of
 btrfs_ioctl_defrag_range_args

Add extra sanity check for btrfs_ioctl_defrag_range_args::flags.

This is not really to enhance fuzzing tests, but as a preparation for
future expansion on btrfs_ioctl_defrag_range_args.

In the future we're going to add new members, allowing more fine tuning
for btrfs defrag.  Without the -ENONOTSUPP error, there would be no way
to detect if the kernel supports those new defrag features.

CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c           | 4 ++++
 include/uapi/linux/btrfs.h | 3 +++
 2 files changed, 7 insertions(+)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index fea5d37528b80..5d42319b43f2d 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2602,6 +2602,10 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 				ret = -EFAULT;
 				goto out;
 			}
+			if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) {
+				ret = -EOPNOTSUPP;
+				goto out;
+			}
 			/* compression requires us to start the IO */
 			if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
 				range.flags |= BTRFS_DEFRAG_RANGE_START_IO;
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 7c29d82db9ee0..f8bc34a6bcfa2 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -614,6 +614,9 @@ struct btrfs_ioctl_clone_range_args {
  */
 #define BTRFS_DEFRAG_RANGE_COMPRESS 1
 #define BTRFS_DEFRAG_RANGE_START_IO 2
+#define BTRFS_DEFRAG_RANGE_FLAGS_SUPP	(BTRFS_DEFRAG_RANGE_COMPRESS |		\
+					 BTRFS_DEFRAG_RANGE_START_IO)
+
 struct btrfs_ioctl_defrag_range_args {
 	/* start of the defrag operation */
 	__u64 start;
-- 
GitLab


From 567a1e852e872e702b18d271a3dbce2a75efbaff Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Tue, 2 Jan 2024 00:52:45 -0800
Subject: [PATCH 2584/4076] scsi: fcoe: Fix unsigned comparison with zero in
 store_ctlr_mode()

ctlr->mode is of unsigned type, it is never less than zero.

Fix this by using an extra variable called 'res', to store return value
from sysfs_match_string() and assign that to ctlr->mode on the success
path.

Fixes: edc22a7c8688 ("scsi: fcoe: Use sysfs_match_string() over fcoe_parse_mode()")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Link: https://lore.kernel.org/r/20240102085245.600570-1-harshit.m.mogalapalli@oracle.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fcoe/fcoe_sysfs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/fcoe/fcoe_sysfs.c b/drivers/scsi/fcoe/fcoe_sysfs.c
index 408a806bf4c2d..c64a085a7ee2f 100644
--- a/drivers/scsi/fcoe/fcoe_sysfs.c
+++ b/drivers/scsi/fcoe/fcoe_sysfs.c
@@ -263,6 +263,7 @@ static ssize_t store_ctlr_mode(struct device *dev,
 			       const char *buf, size_t count)
 {
 	struct fcoe_ctlr_device *ctlr = dev_to_ctlr(dev);
+	int res;
 
 	if (count > FCOE_MAX_MODENAME_LEN)
 		return -EINVAL;
@@ -279,12 +280,13 @@ static ssize_t store_ctlr_mode(struct device *dev,
 			return -ENOTSUPP;
 		}
 
-		ctlr->mode = sysfs_match_string(fip_conn_type_names, buf);
-		if (ctlr->mode < 0 || ctlr->mode == FIP_CONN_TYPE_UNKNOWN) {
+		res = sysfs_match_string(fip_conn_type_names, buf);
+		if (res < 0 || res == FIP_CONN_TYPE_UNKNOWN) {
 			LIBFCOE_SYSFS_DBG(ctlr, "Unknown mode %s provided.\n",
 					  buf);
 			return -EINVAL;
 		}
+		ctlr->mode = res;
 
 		ctlr->f->set_fcoe_ctlr_mode(ctlr);
 		LIBFCOE_SYSFS_DBG(ctlr, "Mode changed to %s.\n", buf);
-- 
GitLab


From 38945c2b006b23a1a7a0c88d76e3294c6199891c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 10 Jan 2024 21:41:55 +0300
Subject: [PATCH 2585/4076] scsi: fnic: unlock on error path in
 fnic_queuecommand()

Call spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags) before
returning.

Fixes: c81df08cd294 ("scsi: fnic: Add support for multiqueue (MQ) in fnic driver")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/5360fa20-74bc-4c22-a78e-ea8b18c5410d@moroto.mountain
Reviewed-by: Karan Tilak Kumar <kartilak@cisco.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fnic_scsi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 4d6db4509e755..8d7fc5284293b 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -546,6 +546,7 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc)
 	if (fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] != NULL) {
 		WARN(1, "fnic<%d>: %s: hwq: %d tag 0x%x already exists\n",
 				fnic->fnic_num, __func__, hwq, blk_mq_unique_tag_to_tag(mqtag));
+		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
-- 
GitLab


From 6df0e077d76bd144c533b61d6182676aae6b0a85 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Thu, 11 Jan 2024 13:05:32 +0100
Subject: [PATCH 2586/4076] scsi: core: Kick the requeue list after inserting
 when flushing

When libata calls ata_link_abort() to abort all ata queued commands, it
calls blk_abort_request() on the SCSI command representing each QC.

This causes scsi_timeout() to be called, which calls scsi_eh_scmd_add() for
each SCSI command.

scsi_eh_scmd_add() sets the SCSI host to state recovery, and then adds the
command to shost->eh_cmd_q.

This will wake up the SCSI EH, and eventually the libata EH strategy
handler will be called, which calls scsi_eh_flush_done_q() to either flush
retry or flush finish each failed command.

The commands that are flush retried by scsi_eh_flush_done_q() are done so
using scsi_queue_insert().

Before commit 8b566edbdbfb ("scsi: core: Only kick the requeue list if
necessary"), __scsi_queue_insert() called blk_mq_requeue_request() with the
second argument set to true, indicating that it should always kick/run the
requeue list after inserting.

After commit 8b566edbdbfb ("scsi: core: Only kick the requeue list if
necessary"), __scsi_queue_insert() does not kick/run the requeue list after
inserting, if the current SCSI host state is recovery (which is the case in
the libata example above).

This optimization is probably fine in most cases, as I can only assume that
most often someone will eventually kick/run the queues.

However, that is not the case for scsi_eh_flush_done_q(), where we can see
that the request gets inserted to the requeue list, but the queue is never
started after the request has been inserted, leading to the block layer
waiting for the completion of command that never gets to run.

Since scsi_eh_flush_done_q() is called by SCSI EH context, the SCSI host
state is most likely always in recovery when this function is called.

Thus, let scsi_eh_flush_done_q() explicitly kick the requeue list after
inserting a flush retry command, so that scsi_eh_flush_done_q() keeps the
same behavior as before commit 8b566edbdbfb ("scsi: core: Only kick the
requeue list if necessary").

Simple reproducer for the libata example above:
$ hdparm -Y /dev/sda
$ echo 1 > /sys/class/scsi_device/0\:0\:0\:0/device/delete

Fixes: 8b566edbdbfb ("scsi: core: Only kick the requeue list if necessary")
Reported-by: Kevin Locke <kevin@kevinlocke.name>
Closes: https://lore.kernel.org/linux-scsi/ZZw3Th70wUUvCiCY@kevinlocke.name/
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/20240111120533.3612509-1-cassel@kernel.org
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_error.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 1bac12ef238ef..44c1a89b717a9 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2196,15 +2196,18 @@ void scsi_eh_flush_done_q(struct list_head *done_q)
 	struct scsi_cmnd *scmd, *next;
 
 	list_for_each_entry_safe(scmd, next, done_q, eh_entry) {
+		struct scsi_device *sdev = scmd->device;
+
 		list_del_init(&scmd->eh_entry);
-		if (scsi_device_online(scmd->device) &&
-		    !scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd) &&
-			scsi_eh_should_retry_cmd(scmd)) {
+		if (scsi_device_online(sdev) && !scsi_noretry_cmd(scmd) &&
+		    scsi_cmd_retry_allowed(scmd) &&
+		    scsi_eh_should_retry_cmd(scmd)) {
 			SCSI_LOG_ERROR_RECOVERY(3,
 				scmd_printk(KERN_INFO, scmd,
 					     "%s: flush retry cmd\n",
 					     current->comm));
 				scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY);
+				blk_mq_kick_requeue_list(sdev->request_queue);
 		} else {
 			/*
 			 * If just we got sense for the device (called
-- 
GitLab


From 83ab68168a3d990d5ff39ab030ad5754cbbccb25 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <d.bogdanov@yadro.com>
Date: Thu, 11 Jan 2024 15:59:41 +0300
Subject: [PATCH 2587/4076] scsi: target: core: Add TMF to tmr_list handling

An abort that is responded to by iSCSI itself is added to tmr_list but does
not go to target core. A LUN_RESET that goes through tmr_list takes a
refcounter on the abort and waits for completion. However, the abort will
be never complete because it was not started in target core.

 Unable to locate ITT: 0x05000000 on CID: 0
 Unable to locate RefTaskTag: 0x05000000 on CID: 0.
 wait_for_tasks: Stopping tmf LUN_RESET with tag 0x0 ref_task_tag 0x0 i_state 34 t_state ISTATE_PROCESSING refcnt 2 transport_state active,stop,fabric_stop
 wait for tasks: tmf LUN_RESET with tag 0x0 ref_task_tag 0x0 i_state 34 t_state ISTATE_PROCESSING refcnt 2 transport_state active,stop,fabric_stop
...
 INFO: task kworker/0:2:49 blocked for more than 491 seconds.
 task:kworker/0:2     state:D stack:    0 pid:   49 ppid:     2 flags:0x00000800
 Workqueue: events target_tmr_work [target_core_mod]
Call Trace:
 __switch_to+0x2c4/0x470
 _schedule+0x314/0x1730
 schedule+0x64/0x130
 schedule_timeout+0x168/0x430
 wait_for_completion+0x140/0x270
 target_put_cmd_and_wait+0x64/0xb0 [target_core_mod]
 core_tmr_lun_reset+0x30/0xa0 [target_core_mod]
 target_tmr_work+0xc8/0x1b0 [target_core_mod]
 process_one_work+0x2d4/0x5d0
 worker_thread+0x78/0x6c0

To fix this, only add abort to tmr_list if it will be handled by target
core.

Signed-off-by: Dmitry Bogdanov <d.bogdanov@yadro.com>
Link: https://lore.kernel.org/r/20240111125941.8688-1-d.bogdanov@yadro.com
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_device.c    | 5 -----
 drivers/target/target_core_transport.c | 4 ++++
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 506193e870c49..7a85e6477e465 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -147,7 +147,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd)
 	struct se_session *se_sess = se_cmd->se_sess;
 	struct se_node_acl *nacl = se_sess->se_node_acl;
 	struct se_tmr_req *se_tmr = se_cmd->se_tmr_req;
-	unsigned long flags;
 
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, se_cmd->orig_fe_lun);
@@ -178,10 +177,6 @@ out_unlock:
 	se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 	se_tmr->tmr_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 
-	spin_lock_irqsave(&se_tmr->tmr_dev->se_tmr_lock, flags);
-	list_add_tail(&se_tmr->tmr_list, &se_tmr->tmr_dev->dev_tmr_list);
-	spin_unlock_irqrestore(&se_tmr->tmr_dev->se_tmr_lock, flags);
-
 	return 0;
 }
 EXPORT_SYMBOL(transport_lookup_tmr_lun);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 670cfb7bd426a..73d0d6133ac8f 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -3629,6 +3629,10 @@ int transport_generic_handle_tmr(
 	unsigned long flags;
 	bool aborted = false;
 
+	spin_lock_irqsave(&cmd->se_dev->se_tmr_lock, flags);
+	list_add_tail(&cmd->se_tmr_req->tmr_list, &cmd->se_dev->dev_tmr_list);
+	spin_unlock_irqrestore(&cmd->se_dev->se_tmr_lock, flags);
+
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
 	if (cmd->transport_state & CMD_T_ABORTED) {
 		aborted = true;
-- 
GitLab


From a03cd7602a090eae277d2b79d43925661e7fbe9a Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Wed, 10 Jan 2024 20:20:00 -0800
Subject: [PATCH 2588/4076] xtensa: don't produce FDPIC output with fdpic
 toolchain

The kernel doesn't use features of the FDPIC toolchain, disable FDPIC
code generation when using such toolchain and select ordinary ELF linker
emulation.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/Makefile | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index bfd8e433ed621..4c14a02179eba 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -35,15 +35,19 @@ KBUILD_CFLAGS += -ffreestanding -D__linux__
 KBUILD_CFLAGS += -pipe -mlongcalls -mtext-section-literals
 KBUILD_CFLAGS += $(call cc-option,-mforce-no-pic,)
 KBUILD_CFLAGS += $(call cc-option,-mno-serialize-volatile,)
+KBUILD_CFLAGS += $(call cc-option,-mno-fdpic,)
 ifneq ($(CONFIG_KERNEL_ABI_CALL0),)
 KBUILD_CFLAGS += -mabi=call0
 KBUILD_AFLAGS += -mabi=call0
 endif
 
 KBUILD_AFLAGS += -mlongcalls -mtext-section-literals
+KBUILD_AFLAGS += $(call cc-option,-mno-fdpic,)
+
+KBUILD_LDFLAGS += -m elf32xtensa
 
 ifneq ($(CONFIG_LD_NO_RELAX),)
-KBUILD_LDFLAGS := --no-relax
+KBUILD_LDFLAGS += --no-relax
 endif
 
 CHECKFLAGS += -D$(if $(CONFIG_CPU_BIG_ENDIAN),__XTENSA_EB__,__XTENSA_EL__)
-- 
GitLab


From cdac6e1f716419ce307ad3e44a718557a5469c17 Mon Sep 17 00:00:00 2001
From: Chancel Liu <chancel.liu@nxp.com>
Date: Thu, 11 Jan 2024 11:52:19 +0900
Subject: [PATCH 2589/4076] ALSA: aloop: Introduce a function to get if access
 is interleaved mode

There's a use case that playback stream of a loopback cable works on
RW_INTERLEAVED mode while capture stream works on MMAP_INTERLEAVED mode:

aplay -Dhw:Loopback,0,0 S32_48K_2ch.wav;
arecord -Dplughw:Loopback,1,0 -fS32_LE -r16000 -c2 cap.wav;

The plug plugin handles only slave PCM support MMAP mode. Not only plug
plugin but also other plugins like direct plugins(dmix/dsnoop/dshare)
work on MMAP access mode. In this case capture stream is the slave
PCM works on MMAP_INTERLEAVED mode. However loopback_check_format()
rejects this access setting and return:

arecord: pcm_read:2240: read error: Input/output error

To fix it a function called is_access_interleaved() is introduced to
get if access is interleaved mode. If both access of capture stream and
playback stream is interleaved mode loopback_check_format() will allow
this kind of access setting.

Fixes: 462494565c27 ("ALSA: aloop: Add support for the non-interleaved access mode")
Signed-off-by: Chancel Liu <chancel.liu@nxp.com>
Link: https://lore.kernel.org/r/20240111025219.2678764-1-chancel.liu@nxp.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/drivers/aloop.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index e87dc67f33c69..1c65e0a3b13ce 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -322,6 +322,17 @@ static int loopback_snd_timer_close_cable(struct loopback_pcm *dpcm)
 	return 0;
 }
 
+static bool is_access_interleaved(snd_pcm_access_t access)
+{
+	switch (access) {
+	case SNDRV_PCM_ACCESS_MMAP_INTERLEAVED:
+	case SNDRV_PCM_ACCESS_RW_INTERLEAVED:
+		return true;
+	default:
+		return false;
+	}
+};
+
 static int loopback_check_format(struct loopback_cable *cable, int stream)
 {
 	struct snd_pcm_runtime *runtime, *cruntime;
@@ -341,7 +352,8 @@ static int loopback_check_format(struct loopback_cable *cable, int stream)
 	check = runtime->format != cruntime->format ||
 		runtime->rate != cruntime->rate ||
 		runtime->channels != cruntime->channels ||
-		runtime->access != cruntime->access;
+		is_access_interleaved(runtime->access) !=
+		is_access_interleaved(cruntime->access);
 	if (!check)
 		return 0;
 	if (stream == SNDRV_PCM_STREAM_CAPTURE) {
@@ -369,7 +381,8 @@ static int loopback_check_format(struct loopback_cable *cable, int stream)
 							&setup->channels_id);
 			setup->channels = runtime->channels;
 		}
-		if (setup->access != runtime->access) {
+		if (is_access_interleaved(setup->access) !=
+		    is_access_interleaved(runtime->access)) {
 			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE,
 							&setup->access_id);
 			setup->access = runtime->access;
@@ -584,8 +597,7 @@ static void copy_play_buf(struct loopback_pcm *play,
 			size = play->pcm_buffer_size - src_off;
 		if (dst_off + size > capt->pcm_buffer_size)
 			size = capt->pcm_buffer_size - dst_off;
-		if (runtime->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED ||
-		    runtime->access == SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED)
+		if (!is_access_interleaved(runtime->access))
 			copy_play_buf_part_n(play, capt, size, src_off, dst_off);
 		else
 			memcpy(dst + dst_off, src + src_off, size);
@@ -1544,8 +1556,7 @@ static int loopback_access_get(struct snd_kcontrol *kcontrol,
 	mutex_lock(&loopback->cable_lock);
 	access = loopback->setup[kcontrol->id.subdevice][kcontrol->id.device].access;
 
-	ucontrol->value.enumerated.item[0] = access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED ||
-					     access == SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED;
+	ucontrol->value.enumerated.item[0] = !is_access_interleaved(access);
 
 	mutex_unlock(&loopback->cable_lock);
 	return 0;
-- 
GitLab


From 45dd7df26cee741b31c25ffdd44fb8794eb45ccd Mon Sep 17 00:00:00 2001
From: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Date: Thu, 12 Oct 2023 10:42:08 +0200
Subject: [PATCH 2590/4076] drm: panel-simple: add missing bus flags for Tianma
 tm070jvhg[30/33]

The DE signal is active high on this display, fill in the missing
bus_flags. This aligns panel_desc with its display_timing.

Fixes: 9a2654c0f62a ("drm/panel: Add and fill drm_panel type field")
Fixes: b3bfcdf8a3b6 ("drm/panel: simple: add Tianma TM070JVHG33")

Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Reviewed-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://lore.kernel.org/r/20231012084208.2731650-1-alexander.stein@ew.tq-group.com
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231012084208.2731650-1-alexander.stein@ew.tq-group.com
---
 drivers/gpu/drm/panel/panel-simple.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 9367a4572dcf6..1ba633fd56961 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -3861,6 +3861,7 @@ static const struct panel_desc tianma_tm070jdhg30 = {
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 };
 
 static const struct panel_desc tianma_tm070jvhg33 = {
@@ -3873,6 +3874,7 @@ static const struct panel_desc tianma_tm070jvhg33 = {
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 };
 
 static const struct display_timing tianma_tm070rvhg71_timing = {
-- 
GitLab


From 62b143b5ec4a14e1ae0dede5aabaf1832e3b0073 Mon Sep 17 00:00:00 2001
From: Artur Weber <aweber.kernel@gmail.com>
Date: Fri, 5 Jan 2024 07:53:02 +0100
Subject: [PATCH 2591/4076] drm/panel: samsung-s6d7aa0: drop
 DRM_BUS_FLAG_DE_HIGH for lsl080al02

It turns out that I had misconfigured the device I was using the panel
with; the bus data polarity is not high for this panel, I had to change
the config on the display controller's side.

Fix the panel config to properly reflect its accurate settings.

Fixes: 6810bb390282 ("drm/panel: Add Samsung S6D7AA0 panel controller driver")
Reviewed-by: Jessica Zhang <quic_jesszhan@quicinc.com>
Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Link: https://lore.kernel.org/r/20240105-tab3-display-fixes-v2-2-904d1207bf6f@gmail.com
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240105-tab3-display-fixes-v2-2-904d1207bf6f@gmail.com
---
 drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c
index ea5a857793827..f23d8832a1ad0 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c
@@ -309,7 +309,7 @@ static const struct s6d7aa0_panel_desc s6d7aa0_lsl080al02_desc = {
 	.off_func = s6d7aa0_lsl080al02_off,
 	.drm_mode = &s6d7aa0_lsl080al02_mode,
 	.mode_flags = MIPI_DSI_MODE_VSYNC_FLUSH | MIPI_DSI_MODE_VIDEO_NO_HFP,
-	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
+	.bus_flags = 0,
 
 	.has_backlight = false,
 	.use_passwd3 = false,
-- 
GitLab


From 589830b13ac21bddf99b9bc5a4ec17813d0869ef Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 23 Oct 2023 13:55:58 +0200
Subject: [PATCH 2592/4076] drm/panel/raydium-rm692e5: select
 CONFIG_DRM_DISPLAY_DP_HELPER

As with several other panel drivers, this fails to link without the DP
helper library:

ld: drivers/gpu/drm/panel/panel-raydium-rm692e5.o: in function `rm692e5_prepare':
panel-raydium-rm692e5.c:(.text+0x11f4): undefined reference to `drm_dsc_pps_payload_pack'

Select the same symbols that the others already use.

Fixes: 988d0ff29ecf7 ("drm/panel: Add driver for BOE RM692E5 AMOLED panel")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231023115619.3551348-1-arnd@kernel.org
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231023115619.3551348-1-arnd@kernel.org
---
 drivers/gpu/drm/panel/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index 99e14dc212ecb..a4ac4b47777fe 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -530,6 +530,8 @@ config DRM_PANEL_RAYDIUM_RM692E5
 	depends on OF
 	depends on DRM_MIPI_DSI
 	depends on BACKLIGHT_CLASS_DEVICE
+	select DRM_DISPLAY_DP_HELPER
+	select DRM_DISPLAY_HELPER
 	help
 	  Say Y here if you want to enable support for Raydium RM692E5-based
 	  display panels, such as the one found in the Fairphone 5 smartphone.
-- 
GitLab


From acd66c2126eb9b5da2d89ae07dbcd73b909c2111 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Wed, 10 Jan 2024 12:37:30 +0100
Subject: [PATCH 2593/4076] net: micrel: Fix PTP frame parsing for lan8841

The HW has the capability to check each frame if it is a PTP frame,
which domain it is, which ptp frame type it is, different ip address in
the frame. And if one of these checks fail then the frame is not
timestamp. Most of these checks were disabled except checking the field
minorVersionPTP inside the PTP header. Meaning that once a partner sends
a frame compliant to 8021AS which has minorVersionPTP set to 1, then the
frame was not timestamp because the HW expected by default a value of 0
in minorVersionPTP.
Fix this issue by removing this check so the userspace can decide on this.

Fixes: cafc3662ee3f ("net: micrel: Add PHC support for lan8841")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Divya Koppera <divya.koppera@microchip.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index d2aa3d0695e33..bf4053431dcb3 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -3338,8 +3338,10 @@ static int lan8814_probe(struct phy_device *phydev)
 #define LAN8841_ADC_CHANNEL_MASK		198
 #define LAN8841_PTP_RX_PARSE_L2_ADDR_EN		370
 #define LAN8841_PTP_RX_PARSE_IP_ADDR_EN		371
+#define LAN8841_PTP_RX_VERSION			374
 #define LAN8841_PTP_TX_PARSE_L2_ADDR_EN		434
 #define LAN8841_PTP_TX_PARSE_IP_ADDR_EN		435
+#define LAN8841_PTP_TX_VERSION			438
 #define LAN8841_PTP_CMD_CTL			256
 #define LAN8841_PTP_CMD_CTL_PTP_ENABLE		BIT(2)
 #define LAN8841_PTP_CMD_CTL_PTP_DISABLE		BIT(1)
@@ -3383,6 +3385,12 @@ static int lan8841_config_init(struct phy_device *phydev)
 	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
 		      LAN8841_PTP_RX_PARSE_IP_ADDR_EN, 0);
 
+	/* Disable checking for minorVersionPTP field */
+	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
+		      LAN8841_PTP_RX_VERSION, 0xff00);
+	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
+		      LAN8841_PTP_TX_VERSION, 0xff00);
+
 	/* 100BT Clause 40 improvenent errata */
 	phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG,
 		      LAN8841_ANALOG_CONTROL_1,
-- 
GitLab


From e398822c4751017fe401f57409488f5948d12fb5 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Fri, 5 Jan 2024 10:52:42 +0200
Subject: [PATCH 2594/4076] net: phy: micrel: populate .soft_reset for KSZ9131

The RZ/G3S SMARC Module has 2 KSZ9131 PHYs. In this setup, the KSZ9131 PHY
is used with the ravb Ethernet driver. It has been discovered that when
bringing the Ethernet interface down/up continuously, e.g., with the
following sh script:

$ while :; do ifconfig eth0 down; ifconfig eth0 up; done

the link speed and duplex are wrong after interrupting the bring down/up
operation even though the Ethernet interface is up. To recover from this
state the following configuration sequence is necessary (executed
manually):

$ ifconfig eth0 down
$ ifconfig eth0 up

The behavior has been identified also on the Microchip SAMA7G5-EK board
which runs the macb driver and uses the same PHY.

The order of PHY-related operations in ravb_open() is as follows:
ravb_open() ->
  ravb_phy_start() ->
    ravb_phy_init() ->
      of_phy_connect() ->
        phy_connect_direct() ->
	  phy_attach_direct() ->
	    phy_init_hw() ->
	      phydev->drv->soft_reset()
	      phydev->drv->config_init()
	      phydev->drv->config_intr()
	    phy_resume()
	      kszphy_resume()

The order of PHY-related operations in ravb_close is as follows:
ravb_close() ->
  phy_stop() ->
    phy_suspend() ->
      kszphy_suspend() ->
        genphy_suspend()
	  // set BMCR_PDOWN bit in MII_BMCR

In genphy_suspend() setting the BMCR_PDWN bit in MII_BMCR switches the PHY
to Software Power-Down (SPD) mode (according to the KSZ9131 datasheet).
Thus, when opening the interface after it has been  previously closed (via
ravb_close()), the phydev->drv->config_init() and
phydev->drv->config_intr() reach the KSZ9131 PHY driver via the
ksz9131_config_init() and kszphy_config_intr() functions.

KSZ9131 specifies that the MII management interface remains operational
during SPD (Software Power-Down), but (according to manual):
- Only access to the standard registers (0 through 31) is supported.
- Access to MMD address spaces other than MMD address space 1 is possible
  if the spd_clock_gate_override bit is set.
- Access to MMD address space 1 is not possible.

The spd_clock_gate_override bit is not used in the KSZ9131 driver.

ksz9131_config_init() configures RGMII delay, pad skews and LEDs by
accessesing MMD registers other than those in address space 1.

The datasheet for the KSZ9131 does not specify what happens if registers
from an unsupported address space are accessed while the PHY is in SPD.

To fix the issue the .soft_reset method has been instantiated for KSZ9131,
too. This resets the PHY to the default state before doing any
configurations to it, thus switching it out of SPD.

Fixes: bff5b4b37372 ("net: phy: micrel: add Microchip KSZ9131 initial driver")
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index bf4053431dcb3..81c20eb4b54b9 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -4847,6 +4847,7 @@ static struct phy_driver ksphy_driver[] = {
 	.flags		= PHY_POLL_CABLE_TEST,
 	.driver_data	= &ksz9131_type,
 	.probe		= kszphy_probe,
+	.soft_reset	= genphy_soft_reset,
 	.config_init	= ksz9131_config_init,
 	.config_intr	= kszphy_config_intr,
 	.config_aneg	= ksz9131_config_aneg,
-- 
GitLab


From a03cfad512ac24a35184d7d87ec0d5489e1cb763 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 12 Jan 2024 12:10:23 +0100
Subject: [PATCH 2595/4076] ALSA: oxygen: Fix right channel of capture volume
 mixer

There was a typo in oxygen mixer code that didn't update the right
channel value properly for the capture volume.  Let's fix it.

This trivial fix was originally reported on Bugzilla.

Fixes: a3601560496d ("[ALSA] oxygen: add front panel controls")
Cc: <stable@vger.kernel.org>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=156561
Link: https://lore.kernel.org/r/20240112111023.6208-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/oxygen/oxygen_mixer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c
index 46705ec77b481..eb3aca16359c5 100644
--- a/sound/pci/oxygen/oxygen_mixer.c
+++ b/sound/pci/oxygen/oxygen_mixer.c
@@ -718,7 +718,7 @@ static int ac97_fp_rec_volume_put(struct snd_kcontrol *ctl,
 	oldreg = oxygen_read_ac97(chip, 1, AC97_REC_GAIN);
 	newreg = oldreg & ~0x0707;
 	newreg = newreg | (value->value.integer.value[0] & 7);
-	newreg = newreg | ((value->value.integer.value[0] & 7) << 8);
+	newreg = newreg | ((value->value.integer.value[1] & 7) << 8);
 	change = newreg != oldreg;
 	if (change)
 		oxygen_write_ac97(chip, 1, AC97_REC_GAIN, newreg);
-- 
GitLab


From 907ee6681788556b9ade3ad0a1f6f4aea192399c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 11 Jan 2024 11:33:11 -0800
Subject: [PATCH 2596/4076] net: fill in MODULE_DESCRIPTION()s for wx_lib

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add a description to Wangxun's common code lib.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/wangxun/libwx/wx_lib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 23355cc408fd7..8706223a6e5aa 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -2769,4 +2769,5 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count,
 }
 EXPORT_SYMBOL(wx_set_ring);
 
+MODULE_DESCRIPTION("Common library for Wangxun(R) Ethernet drivers.");
 MODULE_LICENSE("GPL");
-- 
GitLab


From b95df3bd1ea31fadc9e1471a036b4c08199aa0f0 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Wed, 10 Jan 2024 07:40:07 +0000
Subject: [PATCH 2597/4076] arm64: irq: include <linux/cpumask.h>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Sorting include files in alphabetic order in
drivers/tty/serial/samsung.c revealed the following error:

In file included from drivers/tty/serial/samsung_tty.c:24:
./arch/arm64/include/asm/irq.h:9:43: error: unknown type name ‘cpumask_t’
    9 | void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu);
      |                                           ^~~~~~~~~

Include cpumask.h to avoid unknown type errors for parents of irq.h that
don't include cpumask.h.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Link: https://lore.kernel.org/r/20240110074007.4020016-1-tudor.ambarus@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/irq.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 50ce8b697ff36..e93548914c366 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -4,6 +4,8 @@
 
 #ifndef __ASSEMBLER__
 
+#include <linux/cpumask.h>
+
 #include <asm-generic/irq.h>
 
 void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu);
-- 
GitLab


From 8c5a19cb17a71e52303150335b459c7d2d28a155 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 10 Jan 2024 14:26:20 +0100
Subject: [PATCH 2598/4076] arm64: scs: Work around full LTO issue with dynamic
 SCS

Full LTO takes the '-mbranch-protection=none' passed to the compiler
when generating the dynamic shadow call stack patching code as a hint to
stop emitting PAC instructions altogether. (Thin LTO appears unaffected
by this)

Work around this by stripping unwind tables from the object in question,
which should be sufficient to prevent the patching code from attempting
to patch itself.

Fixes: 3b619e22c460 ("arm64: implement dynamic shadow call stack for Clang")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20240110132619.258809-2-ardb+git@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/Makefile | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index d95b3d6b471a7..e5d03a7039b4b 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -73,7 +73,13 @@ obj-$(CONFIG_ARM64_MTE)			+= mte.o
 obj-y					+= vdso-wrap.o
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32-wrap.o
 obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS)	+= patch-scs.o
-CFLAGS_patch-scs.o			+= -mbranch-protection=none
+
+# We need to prevent the SCS patching code from patching itself. Using
+# -mbranch-protection=none here to avoid the patchable PAC opcodes from being
+# generated triggers an issue with full LTO on Clang, which stops emitting PAC
+# instructions altogether. So instead, omit the unwind tables used by the
+# patching code, so it will not be able to locate its own PAC instructions.
+CFLAGS_patch-scs.o			+= -fno-asynchronous-unwind-tables -fno-unwind-tables
 
 # Force dependency (vdso*-wrap.S includes vdso.so through incbin)
 $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
-- 
GitLab


From 3931261ecf46151a5e779c96fb3da00677b6dc37 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 11 Jan 2024 12:24:48 +0100
Subject: [PATCH 2599/4076] arm64: fpsimd: Bring cond_yield asm macro in line
 with new rules

We no longer disable softirqs or preemption when doing kernel mode SIMD,
and so for fully preemptible kernels, there is no longer a need to do any
explicit yielding (and for non-preemptible kernels, yielding is not
needed either).

That leaves voluntary preemption, where only explicit yield calls may
result in a reschedule. To retain the existing behavior for such a
configuration, we should take the new situation into account, where the
preempt count will be zero rather than one, and yielding to pending
softirqs is unnecessary.

Fixes: aefbab8e77eb ("arm64: fpsimd: Preserve/restore kernel mode NEON at context switch")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20240111112447.577640-2-ardb+git@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/assembler.h | 25 +++++++++----------------
 arch/arm64/kernel/asm-offsets.c    |  2 --
 2 files changed, 9 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 7b1975bf4b90e..513787e433299 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -760,32 +760,25 @@ alternative_endif
 .endm
 
 	/*
-	 * Check whether preempt/bh-disabled asm code should yield as soon as
-	 * it is able. This is the case if we are currently running in task
-	 * context, and either a softirq is pending, or the TIF_NEED_RESCHED
-	 * flag is set and re-enabling preemption a single time would result in
-	 * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is
-	 * stored negated in the top word of the thread_info::preempt_count
+	 * Check whether asm code should yield as soon as it is able. This is
+	 * the case if we are currently running in task context, and the
+	 * TIF_NEED_RESCHED flag is set. (Note that the TIF_NEED_RESCHED flag
+	 * is stored negated in the top word of the thread_info::preempt_count
 	 * field)
 	 */
-	.macro		cond_yield, lbl:req, tmp:req, tmp2:req
+	.macro		cond_yield, lbl:req, tmp:req, tmp2
+#ifdef CONFIG_PREEMPT_VOLUNTARY
 	get_current_task \tmp
 	ldr		\tmp, [\tmp, #TSK_TI_PREEMPT]
 	/*
 	 * If we are serving a softirq, there is no point in yielding: the
 	 * softirq will not be preempted no matter what we do, so we should
-	 * run to completion as quickly as we can.
+	 * run to completion as quickly as we can. The preempt_count field will
+	 * have BIT(SOFTIRQ_SHIFT) set in this case, so the zero check will
+	 * catch this case too.
 	 */
-	tbnz		\tmp, #SOFTIRQ_SHIFT, .Lnoyield_\@
-#ifdef CONFIG_PREEMPTION
-	sub		\tmp, \tmp, #PREEMPT_DISABLE_OFFSET
 	cbz		\tmp, \lbl
 #endif
-	adr_l		\tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING
-	get_this_cpu_offset	\tmp2
-	ldr		w\tmp, [\tmp, \tmp2]
-	cbnz		w\tmp, \lbl	// yield on pending softirq in task context
-.Lnoyield_\@:
 	.endm
 
 /*
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 5ff1942b04fcf..5a7dbbe0ce639 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -117,8 +117,6 @@ int main(void)
   DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
   BLANK();
   DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET);
-  DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT);
-  DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
   BLANK();
   DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
   BLANK();
-- 
GitLab


From 546b7cde9b1dd36089649101b75266564600ffe5 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 10 Jan 2024 11:29:20 -0600
Subject: [PATCH 2600/4076] arm64: Rename ARM64_WORKAROUND_2966298

In preparation to apply ARM64_WORKAROUND_2966298 for multiple errata,
rename the kconfig and capability. No functional change.

Cc: stable@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20240110-arm-errata-a510-v1-1-d02bc51aeeee@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig             | 4 ++++
 arch/arm64/kernel/cpu_errata.c | 4 ++--
 arch/arm64/kernel/entry.S      | 2 +-
 arch/arm64/tools/cpucaps       | 2 +-
 4 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b67e6934316fd..96f31e235a1a0 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1037,8 +1037,12 @@ config ARM64_ERRATUM_2645198
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+	bool
+
 config ARM64_ERRATUM_2966298
 	bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load"
+	select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	default y
 	help
 	  This option adds the workaround for ARM Cortex-A520 erratum 2966298.
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index e29e0fea63fb6..cb5e0622168de 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -713,10 +713,10 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)),
 	},
 #endif
-#ifdef CONFIG_ARM64_ERRATUM_2966298
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	{
 		.desc = "ARM erratum 2966298",
-		.capability = ARM64_WORKAROUND_2966298,
+		.capability = ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD,
 		/* Cortex-A520 r0p0 - r0p1 */
 		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1),
 	},
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a6030913cd58c..544ab46649f3f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -428,7 +428,7 @@ alternative_else_nop_endif
 	ldp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
-alternative_if ARM64_WORKAROUND_2966298
+alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	tlbi	vale1, xzr
 	dsb	nsh
 alternative_else_nop_endif
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 1e07d74d7a6c9..b912b1409fc09 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -84,7 +84,6 @@ WORKAROUND_2077057
 WORKAROUND_2457168
 WORKAROUND_2645198
 WORKAROUND_2658417
-WORKAROUND_2966298
 WORKAROUND_AMPERE_AC03_CPU_38
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
@@ -100,3 +99,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP
 WORKAROUND_QCOM_FALKOR_E1003
 WORKAROUND_REPEAT_TLBI
 WORKAROUND_SPECULATIVE_AT
+WORKAROUND_SPECULATIVE_UNPRIV_LOAD
-- 
GitLab


From f827bcdafa2a2ac21c91e47f587e8d0c76195409 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 10 Jan 2024 11:29:21 -0600
Subject: [PATCH 2601/4076] arm64: errata: Add Cortex-A510 speculative
 unprivileged load workaround

Implement the workaround for ARM Cortex-A510 erratum 3117295. On an
affected Cortex-A510 core, a speculatively executed unprivileged load
might leak data from a privileged load via a cache side channel. The
issue only exists for loads within a translation regime with the same
translation (e.g. same ASID and VMID). Therefore, the issue only affects
the return to EL0.

The erratum and workaround are the same as ARM Cortex-A520 erratum
2966298, so reuse the existing workaround.

Cc: stable@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20240110-arm-errata-a510-v1-2-d02bc51aeeee@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/arch/arm64/silicon-errata.rst |  2 ++
 arch/arm64/Kconfig                          | 14 ++++++++++++++
 arch/arm64/kernel/cpu_errata.c              | 17 +++++++++++++++--
 3 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index f47f63bcf67c9..7acd64c61f50c 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -71,6 +71,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A510     | #2658417        | ARM64_ERRATUM_2658417       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A510     | #3117295        | ARM64_ERRATUM_3117295       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A520     | #2966298        | ARM64_ERRATUM_2966298       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319        |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 96f31e235a1a0..bfd2752493666 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1054,6 +1054,20 @@ config ARM64_ERRATUM_2966298
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_3117295
+	bool "Cortex-A510: 3117295: workaround for speculatively executed unprivileged load"
+	select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-A510 erratum 3117295.
+
+	  On an affected Cortex-A510 core, a speculatively executed unprivileged
+	  load might leak data from a privileged level via a cache side channel.
+
+	  Work around this problem by executing a TLBI before returning to EL0.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index cb5e0622168de..967c7c7a4e7db 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -416,6 +416,19 @@ static struct midr_range broken_aarch32_aes[] = {
 };
 #endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */
 
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+static const struct midr_range erratum_spec_unpriv_load_list[] = {
+#ifdef CONFIG_ARM64_ERRATUM_3117295
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A510),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_2966298
+	/* Cortex-A520 r0p0 to r0p1 */
+	MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1),
+#endif
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -715,10 +728,10 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	{
-		.desc = "ARM erratum 2966298",
+		.desc = "ARM errata 2966298, 3117295",
 		.capability = ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD,
 		/* Cortex-A520 r0p0 - r0p1 */
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1),
+		ERRATA_MIDR_RANGE_LIST(erratum_spec_unpriv_load_list),
 	},
 #endif
 #ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38
-- 
GitLab


From 8d0e8a8aa3a1e844b7a969e9fe80937667507c6c Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 14 Nov 2023 10:53:22 +0100
Subject: [PATCH 2602/4076] s390/pai: rework paixxxx_getctr interface

Simplify the interface for functions paicrypt_getctr() and
paiext_getctr(). Change the first parameter from a pointer to a
structure to a pointer to a structure member. The other members
of the structure are not needed.
No functional change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Mete Durlu <meted@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/perf_pai_crypto.c | 12 ++++++------
 arch/s390/kernel/perf_pai_ext.c    | 11 ++++++-----
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 39a91b00438a7..92156e14fc6f4 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -111,11 +111,11 @@ static void paicrypt_event_destroy(struct perf_event *event)
 	mutex_unlock(&pai_reserve_mutex);
 }
 
-static u64 paicrypt_getctr(struct paicrypt_map *cpump, int nr, bool kernel)
+static u64 paicrypt_getctr(unsigned long *page, int nr, bool kernel)
 {
 	if (kernel)
 		nr += PAI_CRYPTO_MAXCTR;
-	return cpump->page[nr];
+	return page[nr];
 }
 
 /* Read the counter values. Return value from location in CMP. For event
@@ -129,13 +129,13 @@ static u64 paicrypt_getdata(struct perf_event *event, bool kernel)
 	int i;
 
 	if (event->attr.config != PAI_CRYPTO_BASE) {
-		return paicrypt_getctr(cpump,
+		return paicrypt_getctr(cpump->page,
 				       event->attr.config - PAI_CRYPTO_BASE,
 				       kernel);
 	}
 
 	for (i = 1; i <= paicrypt_cnt; i++) {
-		u64 val = paicrypt_getctr(cpump, i, kernel);
+		u64 val = paicrypt_getctr(cpump->page, i, kernel);
 
 		if (!val)
 			continue;
@@ -383,9 +383,9 @@ static size_t paicrypt_copy(struct pai_userdata *userdata,
 		u64 val = 0;
 
 		if (!exclude_kernel)
-			val += paicrypt_getctr(cpump, i, true);
+			val += paicrypt_getctr(cpump->page, i, true);
 		if (!exclude_user)
-			val += paicrypt_getctr(cpump, i, false);
+			val += paicrypt_getctr(cpump->page, i, false);
 		if (val) {
 			userdata[outidx].num = i;
 			userdata[outidx].value = val;
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index e7013a2e89605..9452205e6febc 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -276,9 +276,9 @@ static int paiext_event_init(struct perf_event *event)
 	return 0;
 }
 
-static u64 paiext_getctr(struct paiext_map *cpump, int nr)
+static u64 paiext_getctr(unsigned long *area, int nr)
 {
-	return cpump->area[nr];
+	return area[nr];
 }
 
 /* Read the counter values. Return value from location in buffer. For event
@@ -292,10 +292,11 @@ static u64 paiext_getdata(struct perf_event *event)
 	int i;
 
 	if (event->attr.config != PAI_NNPA_BASE)
-		return paiext_getctr(cpump, event->attr.config - PAI_NNPA_BASE);
+		return paiext_getctr(cpump->area,
+				     event->attr.config - PAI_NNPA_BASE);
 
 	for (i = 1; i <= paiext_cnt; i++)
-		sum += paiext_getctr(cpump, i);
+		sum += paiext_getctr(cpump->area, i);
 
 	return sum;
 }
@@ -392,7 +393,7 @@ static size_t paiext_copy(struct paiext_map *cpump)
 	int i, outidx = 0;
 
 	for (i = 1; i <= paiext_cnt; i++) {
-		u64 val = paiext_getctr(cpump, i);
+		u64 val = paiext_getctr(cpump->area, i);
 
 		if (val) {
 			userdata[outidx].num = i;
-- 
GitLab


From 0578a54110ff28dc2b3830e90ad2dd9c1e065e90 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 14 Nov 2023 12:00:38 +0100
Subject: [PATCH 2603/4076] s390/pai_crypto: split function
 paicrypt_push_sample

Split function paicrypt_push_sample() into two parts. The first part
determines the number of bytes to store as raw data in the perf sample
record. The second part stores the raw data in the perf event's
ring buffer.
No functional change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Mete Durlu <meted@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/perf_pai_crypto.c | 43 +++++++++++++++++-------------
 1 file changed, 25 insertions(+), 18 deletions(-)

diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 92156e14fc6f4..ee8a011c46e97 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -373,8 +373,7 @@ static void paicrypt_del(struct perf_event *event, int flags)
  * 2 bytes: Number of counter
  * 8 bytes: Value of counter
  */
-static size_t paicrypt_copy(struct pai_userdata *userdata,
-			    struct paicrypt_map *cpump,
+static size_t paicrypt_copy(struct pai_userdata *userdata, unsigned long *page,
 			    bool exclude_user, bool exclude_kernel)
 {
 	int i, outidx = 0;
@@ -383,9 +382,9 @@ static size_t paicrypt_copy(struct pai_userdata *userdata,
 		u64 val = 0;
 
 		if (!exclude_kernel)
-			val += paicrypt_getctr(cpump->page, i, true);
+			val += paicrypt_getctr(page, i, true);
 		if (!exclude_user)
-			val += paicrypt_getctr(cpump->page, i, false);
+			val += paicrypt_getctr(page, i, false);
 		if (val) {
 			userdata[outidx].num = i;
 			userdata[outidx].value = val;
@@ -395,25 +394,14 @@ static size_t paicrypt_copy(struct pai_userdata *userdata,
 	return outidx * sizeof(struct pai_userdata);
 }
 
-static int paicrypt_push_sample(void)
+static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump,
+				struct perf_event *event)
 {
-	struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
-	struct paicrypt_map *cpump = mp->mapptr;
-	struct perf_event *event = cpump->event;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
-	size_t rawsize;
 	int overflow;
 
-	if (!cpump->event)		/* No event active */
-		return 0;
-	rawsize = paicrypt_copy(cpump->save, cpump,
-				cpump->event->attr.exclude_user,
-				cpump->event->attr.exclude_kernel);
-	if (!rawsize)			/* No incremented counters */
-		return 0;
-
 	/* Setup perf sample */
 	memset(&regs, 0, sizeof(regs));
 	memset(&raw, 0, sizeof(raw));
@@ -444,6 +432,25 @@ static int paicrypt_push_sample(void)
 	return overflow;
 }
 
+/* Check if there is data to be saved on schedule out of a task. */
+static int paicrypt_have_sample(void)
+{
+	struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
+	struct paicrypt_map *cpump = mp->mapptr;
+	struct perf_event *event = cpump->event;
+	size_t rawsize;
+	int rc = 0;
+
+	if (!event)		/* No event active */
+		return 0;
+	rawsize = paicrypt_copy(cpump->save, cpump->page,
+				cpump->event->attr.exclude_user,
+				cpump->event->attr.exclude_kernel);
+	if (rawsize)			/* No incremented counters */
+		rc = paicrypt_push_sample(rawsize, cpump, event);
+	return rc;
+}
+
 /* Called on schedule-in and schedule-out. No access to event structure,
  * but for sampling only event CRYPTO_ALL is allowed.
  */
@@ -453,7 +460,7 @@ static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sch
 	 * results on schedule_out and if page was dirty, clear values.
 	 */
 	if (!sched_in)
-		paicrypt_push_sample();
+		paicrypt_have_sample();
 }
 
 /* Attribute definitions for paicrypt interface. As with other CPU
-- 
GitLab


From cb1259b7b574bd90ef22dac2c6282327cdae31c6 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Wed, 15 Nov 2023 11:04:25 +0100
Subject: [PATCH 2604/4076] s390/pai: rework paiXXX_start and paiXXX_stop
 functions

The PAI crypto counter and PAI NNPA counters start and stop functions
are streamlined. Move the conditions to invoke start and stop functions
to its respective function body and call them unconditionally.
The start and stop functions now determine how to proceed.
No functional change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Mete Durlu <meted@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/perf_pai_crypto.c | 29 ++++++++++++-------------
 arch/s390/kernel/perf_pai_ext.c    | 35 ++++++++++++++----------------
 2 files changed, 30 insertions(+), 34 deletions(-)

diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index ee8a011c46e97..bf8a672b15a41 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -317,10 +317,14 @@ static void paicrypt_start(struct perf_event *event, int flags)
 	 * Events are added, deleted and re-added when 2 or more events
 	 * are active at the same time.
 	 */
-	if (!event->hw.last_tag) {
-		event->hw.last_tag = 1;
-		sum = paicrypt_getall(event);		/* Get current value */
-		local64_set(&event->hw.prev_count, sum);
+	if (!event->attr.sample_period) {	/* Counting */
+		if (!event->hw.last_tag) {
+			event->hw.last_tag = 1;
+			sum = paicrypt_getall(event);	/* Get current value */
+			local64_set(&event->hw.prev_count, sum);
+		}
+	} else {				/* Sampling */
+		perf_sched_cb_inc(event->pmu);
 	}
 }
 
@@ -336,19 +340,18 @@ static int paicrypt_add(struct perf_event *event, int flags)
 		local_ctl_set_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT);
 	}
 	cpump->event = event;
-	if (flags & PERF_EF_START && !event->attr.sample_period) {
-		/* Only counting needs initial counter value */
+	if (flags & PERF_EF_START)
 		paicrypt_start(event, PERF_EF_RELOAD);
-	}
 	event->hw.state = 0;
-	if (event->attr.sample_period)
-		perf_sched_cb_inc(event->pmu);
 	return 0;
 }
 
 static void paicrypt_stop(struct perf_event *event, int flags)
 {
-	paicrypt_read(event);
+	if (!event->attr.sample_period)	/* Counting */
+		paicrypt_read(event);
+	else				/* Sampling */
+		perf_sched_cb_dec(event->pmu);
 	event->hw.state = PERF_HES_STOPPED;
 }
 
@@ -357,11 +360,7 @@ static void paicrypt_del(struct perf_event *event, int flags)
 	struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
 	struct paicrypt_map *cpump = mp->mapptr;
 
-	if (event->attr.sample_period)
-		perf_sched_cb_dec(event->pmu);
-	if (!event->attr.sample_period)
-		/* Only counting needs to read counter */
-		paicrypt_stop(event, PERF_EF_UPDATE);
+	paicrypt_stop(event, PERF_EF_UPDATE);
 	if (--cpump->active_events == 0) {
 		local_ctl_clear_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT);
 		WRITE_ONCE(S390_lowcore.ccd, 0);
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 9452205e6febc..275d4fd3fe38b 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -321,11 +321,15 @@ static void paiext_start(struct perf_event *event, int flags)
 {
 	u64 sum;
 
-	if (event->hw.last_tag)
-		return;
-	event->hw.last_tag = 1;
-	sum = paiext_getall(event);		/* Get current value */
-	local64_set(&event->hw.prev_count, sum);
+	if (!event->attr.sample_period) {	/* Counting */
+		if (!event->hw.last_tag) {
+			event->hw.last_tag = 1;
+			sum = paiext_getall(event);	/* Get current value */
+			local64_set(&event->hw.prev_count, sum);
+		}
+	} else {				/* Sampling */
+		perf_sched_cb_inc(event->pmu);
+	}
 }
 
 static int paiext_add(struct perf_event *event, int flags)
@@ -342,21 +346,19 @@ static int paiext_add(struct perf_event *event, int flags)
 		debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n",
 				    __func__, S390_lowcore.aicd, pcb->acc);
 	}
-	if (flags & PERF_EF_START && !event->attr.sample_period) {
-		/* Only counting needs initial counter value */
+	cpump->event = event;
+	if (flags & PERF_EF_START)
 		paiext_start(event, PERF_EF_RELOAD);
-	}
 	event->hw.state = 0;
-	if (event->attr.sample_period) {
-		cpump->event = event;
-		perf_sched_cb_inc(event->pmu);
-	}
 	return 0;
 }
 
 static void paiext_stop(struct perf_event *event, int flags)
 {
-	paiext_read(event);
+	if (!event->attr.sample_period)	/* Counting */
+		paiext_read(event);
+	else				/* Sampling */
+		perf_sched_cb_dec(event->pmu);
 	event->hw.state = PERF_HES_STOPPED;
 }
 
@@ -366,12 +368,7 @@ static void paiext_del(struct perf_event *event, int flags)
 	struct paiext_map *cpump = mp->mapptr;
 	struct paiext_cb *pcb = cpump->paiext_cb;
 
-	if (event->attr.sample_period)
-		perf_sched_cb_dec(event->pmu);
-	if (!event->attr.sample_period) {
-		/* Only counting needs to read counter */
-		paiext_stop(event, PERF_EF_UPDATE);
-	}
+	paiext_stop(event, PERF_EF_UPDATE);
 	if (--cpump->active_events == 0) {
 		/* Disable CPU instruction lookup for PAIE1 control block */
 		local_ctl_clear_bit(0, CR0_PAI_EXTENSION_BIT);
-- 
GitLab


From 0dade41d16132ac11ac9e3ac0b0313d438037224 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 16 Nov 2023 10:43:14 +0100
Subject: [PATCH 2605/4076] s390/pai_ext: rework function paiext_copy argments

Change the function paiext_copy() parameter from a pointer to a
structure to two pointers to memory areas referenced. The other
members of that structure are not needed.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Mete Durlu <meted@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/perf_pai_ext.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 275d4fd3fe38b..e2e1ce2de695f 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -384,13 +384,12 @@ static void paiext_del(struct perf_event *event, int flags)
  * 2 bytes: Number of counter
  * 8 bytes: Value of counter
  */
-static size_t paiext_copy(struct paiext_map *cpump)
+static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area)
 {
-	struct pai_userdata *userdata = cpump->save;
 	int i, outidx = 0;
 
 	for (i = 1; i <= paiext_cnt; i++) {
-		u64 val = paiext_getctr(cpump->area, i);
+		u64 val = paiext_getctr(area, i);
 
 		if (val) {
 			userdata[outidx].num = i;
@@ -427,7 +426,7 @@ static int paiext_push_sample(void)
 	size_t rawsize;
 	int overflow;
 
-	rawsize = paiext_copy(cpump);
+	rawsize = paiext_copy(cpump->save, cpump->area);
 	if (!rawsize)			/* No incremented counters */
 		return 0;
 
-- 
GitLab


From 3046a1091137f55de473262b7f3a04c45f87873a Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 16 Nov 2023 12:12:12 +0100
Subject: [PATCH 2606/4076] s390/pai_ext: split function paiext_push_sample

Split function paiext_push_sample() into two parts. The first part
determines the number of bytes to store as raw data in the perf sample
record. This is now function paiext_have_sample().
The second part stores the raw data in the perf event's ring buffer.
No functional change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Mete Durlu <meted@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/perf_pai_ext.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index e2e1ce2de695f..af7f2b538c8fd 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -415,21 +415,14 @@ static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area)
  * sched_task() callback. That callback is not active after paiext_del()
  * returns and has deleted the event on that CPU.
  */
-static int paiext_push_sample(void)
+static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump,
+			      struct perf_event *event)
 {
-	struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr);
-	struct paiext_map *cpump = mp->mapptr;
-	struct perf_event *event = cpump->event;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
-	size_t rawsize;
 	int overflow;
 
-	rawsize = paiext_copy(cpump->save, cpump->area);
-	if (!rawsize)			/* No incremented counters */
-		return 0;
-
 	/* Setup perf sample */
 	memset(&regs, 0, sizeof(regs));
 	memset(&raw, 0, sizeof(raw));
@@ -458,6 +451,23 @@ static int paiext_push_sample(void)
 	return overflow;
 }
 
+/* Check if there is data to be saved on schedule out of a task. */
+static int paiext_have_sample(void)
+{
+	struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr);
+	struct paiext_map *cpump = mp->mapptr;
+	struct perf_event *event = cpump->event;
+	size_t rawsize;
+	int rc = 0;
+
+	if (!event)
+		return 0;
+	rawsize = paiext_copy(cpump->save, cpump->area);
+	if (rawsize)			/* Incremented counters */
+		rc = paiext_push_sample(rawsize, cpump, event);
+	return rc;
+}
+
 /* Called on schedule-in and schedule-out. No access to event structure,
  * but for sampling only event NNPA_ALL is allowed.
  */
@@ -467,7 +477,7 @@ static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched
 	 * results on schedule_out and if page was dirty, clear values.
 	 */
 	if (!sched_in)
-		paiext_push_sample();
+		paiext_have_sample();
 }
 
 /* Attribute definitions for pai extension1 interface. As with other CPU
-- 
GitLab


From 813c2f2925ee9c10dc4acd5aa7410cd3357e8da8 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Fri, 12 Jan 2024 15:27:49 +0200
Subject: [PATCH 2607/4076] ASoC: SOF: icp3-dtrace: Revert "Fix wrong kfree()
 usage"

The offending patch introduces memory leak when there is no error, the
memory allocated for the temporary storage is not freed up.

As I have commented, the original code was correct and cleaner to
follow but it was not obvious from the patch that it will introduce
regression.

Fixes: 8c91ca76f448 ("ASoC: SOF: icp3-dtrace: Fix wrong kfree() usage")
Link: https://lore.kernel.org/all/aec61f67-6b4f-49e6-b458-c332983a0ad6@linux.intel.com/
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://msgid.link/r/20240112132749.28970-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc3-dtrace.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/soc/sof/ipc3-dtrace.c b/sound/soc/sof/ipc3-dtrace.c
index 93b189c2d2ee2..0dca139322f3d 100644
--- a/sound/soc/sof/ipc3-dtrace.c
+++ b/sound/soc/sof/ipc3-dtrace.c
@@ -137,7 +137,6 @@ static int trace_filter_parse(struct snd_sof_dev *sdev, char *string,
 			dev_err(sdev->dev,
 				"Parsing filter entry '%s' failed with %d\n",
 				entry, entry_len);
-			kfree(*out);
 			return -EINVAL;
 		}
 	}
@@ -209,13 +208,13 @@ static ssize_t dfsentry_trace_filter_write(struct file *file, const char __user
 		ret = ipc3_trace_update_filter(sdev, num_elems, elems);
 		if (ret < 0) {
 			dev_err(sdev->dev, "Filter update failed: %d\n", ret);
-			kfree(elems);
 			goto error;
 		}
 	}
 	ret = count;
 error:
 	kfree(string);
+	kfree(elems);
 	return ret;
 }
 
-- 
GitLab


From 301bda18ac735eaaad5823dbdd067b3b2728c780 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Fri, 12 Jan 2024 06:10:15 +0000
Subject: [PATCH 2608/4076] ASoC: audio-graph-card2: fix index check on
 graph_parse_node_multi_nm()

commit d685aea5e0a8 ("ASoC: audio-graph-card2: fix off by one in
graph_parse_node_multi_nm()") uses ">=" instead of ">" for index check,
but it was wrong. The nm_idx will be increment at end of loop,
thus, ">" is correct.

	while (1) {
		...
=>		if (*nm_idx > nm_max)
			break;
		...
		(*nm_idx)++;
	}

Without this patch, "Multi-Codec-1" sample on
${LINUX}/sound/soc/generic/audio-graph-card2-custom-sample.dtsi
will be error.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://msgid.link/r/87o7drdqux.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/audio-graph-card2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c
index 9c94677f681a1..62606e20be9a3 100644
--- a/sound/soc/generic/audio-graph-card2.c
+++ b/sound/soc/generic/audio-graph-card2.c
@@ -556,7 +556,7 @@ static int graph_parse_node_multi_nm(struct snd_soc_dai_link *dai_link,
 		struct device_node *mcodec_port;
 		int codec_idx;
 
-		if (*nm_idx >= nm_max)
+		if (*nm_idx > nm_max)
 			break;
 
 		mcpu_ep_n = of_get_next_child(mcpu_port, mcpu_ep_n);
-- 
GitLab


From 7ea26f9460c6c76b1d6e36f39fce34b16cb88300 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 9 Jan 2024 20:22:45 +0200
Subject: [PATCH 2609/4076] fsnotify: compile out fsnotify permission hooks if
 !FANOTIFY_ACCESS_PERMISSIONS

The depency of FANOTIFY_ACCESS_PERMISSIONS on SECURITY made sure that
the fsnotify permission hooks were never called when SECURITY was
disabled.

Moving the fsnotify permission hook out of the secutiy hook broke that
optimisation.

Reported-and-tested-by: Jens Axboe <axboe@kernel.dk>
Closes: https://lore.kernel.org/linux-fsdevel/53682ece-f0e7-48de-9a1c-879ee34b0449@kernel.dk/
Fixes: d9e5d31084b0 ("fsnotify: optionally pass access range in file permission hooks")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20240109182245.38884-1-amir73il@gmail.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fsnotify.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 11e6434b8e714..8300a52869887 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -100,6 +100,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
 }
 
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 /*
  * fsnotify_file_area_perm - permission hook before access to file range
  */
@@ -145,6 +146,24 @@ static inline int fsnotify_open_perm(struct file *file)
 	return fsnotify_file(file, FS_OPEN_PERM);
 }
 
+#else
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
+{
+	return 0;
+}
+
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return 0;
+}
+
+static inline int fsnotify_open_perm(struct file *file)
+{
+	return 0;
+}
+#endif
+
 /*
  * fsnotify_link_count - inode's link count changed
  */
-- 
GitLab


From 755113d7678681a137c330f7997ceb680adb644e Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Tue, 9 Jan 2024 10:41:11 +0100
Subject: [PATCH 2610/4076] thermal/debugfs: Add thermal cooling device debugfs
 information

The thermal framework does not have any debug information except a
sysfs stat which is a bit controversial. This one allocates big chunks
of memory for every cooling devices with a high number of states and
could represent on some systems in production several megabytes of
memory for just a portion of it. As the sysfs is limited to a page
size, the output is not exploitable with large data array and gets
truncated.

The patch provides the same information than sysfs except the
transitions are dynamically allocated, thus they won't show more
events than the ones which actually occurred. There is no longer a
size limitation and it opens the field for more debugging information
where the debugfs is designed for, not sysfs.

The thermal debugfs directory structure tries to stay consistent with
the sysfs one but in a very simplified way:

thermal/
 -- cooling_devices
    |-- 0
    |   |-- clear
    |   |-- time_in_state_ms
    |   |-- total_trans
    |   `-- trans_table
    |-- 1
    |   |-- clear
    |   |-- time_in_state_ms
    |   |-- total_trans
    |   `-- trans_table
    |-- 2
    |   |-- clear
    |   |-- time_in_state_ms
    |   |-- total_trans
    |   `-- trans_table
    |-- 3
    |   |-- clear
    |   |-- time_in_state_ms
    |   |-- total_trans
    |   `-- trans_table
    `-- 4
        |-- clear
        |-- time_in_state_ms
        |-- total_trans
        `-- trans_table

The content of the files in the cooling devices directory is the same
as the sysfs one except for the trans_table which has the following
format:

Transition	Hits
1->0      	246
0->1      	246
2->1      	632
1->2      	632
3->2      	98
2->3      	98

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: White space fixups, rebase ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/Kconfig           |   7 +
 drivers/thermal/Makefile          |   2 +
 drivers/thermal/thermal_core.c    |   6 +
 drivers/thermal/thermal_core.h    |   1 +
 drivers/thermal/thermal_debugfs.c | 446 ++++++++++++++++++++++++++++++
 drivers/thermal/thermal_debugfs.h |  14 +
 drivers/thermal/thermal_helpers.c |  20 +-
 include/linux/thermal.h           |   7 +
 8 files changed, 497 insertions(+), 6 deletions(-)
 create mode 100644 drivers/thermal/thermal_debugfs.c
 create mode 100644 drivers/thermal/thermal_debugfs.h

diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index c81a00fbca7db..3ff7add3fb7cf 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -33,6 +33,13 @@ config THERMAL_STATISTICS
 
 	  If in doubt, say N.
 
+config THERMAL_DEBUGFS
+	bool "Thermal subsystem debug support"
+	depends on DEBUG_FS
+	help
+	  Say Y to allow the thermal subsystem to collect diagnostic
+	  information that can be accessed via debugfs.
+
 config THERMAL_EMERGENCY_POWEROFF_DELAY_MS
 	int "Emergency poweroff delay in milli-seconds"
 	default 0
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index c934cab309ae0..0f65ae86a9c65 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -10,6 +10,8 @@ thermal_sys-y			+= thermal_trip.o thermal_helpers.o
 # netlink interface to manage the thermal framework
 thermal_sys-$(CONFIG_THERMAL_NETLINK)		+= thermal_netlink.o
 
+thermal_sys-$(CONFIG_THERMAL_DEBUGFS)	+= thermal_debugfs.o
+
 # interface to/from other layers providing sensors
 thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
 thermal_sys-$(CONFIG_THERMAL_OF)		+= thermal_of.o
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index c0b012e075f34..5d9cc422d7baa 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -960,6 +960,8 @@ __thermal_cooling_device_register(struct device_node *np,
 
 	mutex_unlock(&thermal_list_lock);
 
+	thermal_debug_cdev_add(cdev);
+
 	return cdev;
 
 out_cooling_dev:
@@ -1166,6 +1168,8 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
 	if (!cdev)
 		return;
 
+	thermal_debug_cdev_remove(cdev);
+
 	mutex_lock(&thermal_list_lock);
 
 	if (!thermal_cooling_device_present(cdev)) {
@@ -1629,6 +1633,8 @@ static int __init thermal_init(void)
 {
 	int result;
 
+	thermal_debug_init();
+
 	result = thermal_netlink_init();
 	if (result)
 		goto error;
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 4e023d54fd27d..e9c099ecdd0fb 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -13,6 +13,7 @@
 #include <linux/thermal.h>
 
 #include "thermal_netlink.h"
+#include "thermal_debugfs.h"
 
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
new file mode 100644
index 0000000000000..b18bdde47847e
--- /dev/null
+++ b/drivers/thermal/thermal_debugfs.c
@@ -0,0 +1,446 @@
+
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * Thermal subsystem debug support
+ */
+#include <linux/debugfs.h>
+#include <linux/ktime.h>
+#include <linux/list.h>
+#include <linux/minmax.h>
+#include <linux/mutex.h>
+#include <linux/thermal.h>
+
+static struct dentry *d_root;
+static struct dentry *d_cdev;
+
+/*
+ * Length of the string containing the thermal zone id or the cooling
+ * device id, including the ending nul character. We can reasonably
+ * assume there won't be more than 256 thermal zones as the maximum
+ * observed today is around 32.
+ */
+#define IDSLENGTH 4
+
+/*
+ * The cooling device transition list is stored in a hash table where
+ * the size is CDEVSTATS_HASH_SIZE. The majority of cooling devices
+ * have dozen of states but some can have much more, so a hash table
+ * is more adequate in this case, because the cost of browsing the entire
+ * list when storing the transitions may not be negligible.
+ */
+#define CDEVSTATS_HASH_SIZE 16
+
+/**
+ * struct cdev_debugfs - per cooling device statistics structure
+ * A cooling device can have a high number of states. Showing the
+ * transitions on a matrix based representation can be overkill given
+ * most of the transitions won't happen and we end up with a matrix
+ * filled with zero. Instead, we show the transitions which actually
+ * happened.
+ *
+ * Every transition updates the current_state and the timestamp. The
+ * transitions and the durations are stored in lists.
+ *
+ * @total: the number of transitions for this cooling device
+ * @current_state: the current cooling device state
+ * @timestamp: the state change timestamp
+ * @transitions: an array of lists containing the state transitions
+ * @durations: an array of lists containing the residencies of each state
+ */
+struct cdev_debugfs {
+	u32 total;
+	int current_state;
+	ktime_t timestamp;
+	struct list_head transitions[CDEVSTATS_HASH_SIZE];
+	struct list_head durations[CDEVSTATS_HASH_SIZE];
+};
+
+/**
+ * struct cdev_value - Common structure for cooling device entry
+ *
+ * The following common structure allows to store the information
+ * related to the transitions and to the state residencies. They are
+ * identified with a id which is associated to a value. It is used as
+ * nodes for the "transitions" and "durations" above.
+ *
+ * @node: node to insert the structure in a list
+ * @id: identifier of the value which can be a state or a transition
+ * @residency: a ktime_t representing a state residency duration
+ * @count: a number of occurrences
+ */
+struct cdev_record {
+	struct list_head node;
+	int id;
+	union {
+                ktime_t residency;
+                u64 count;
+        };
+};
+
+/**
+ * struct thermal_debugfs - High level structure for a thermal object in debugfs
+ *
+ * The thermal_debugfs structure is the common structure used by the
+ * cooling device to compute the statistics.
+ *
+ * @d_top: top directory of the thermal object directory
+ * @lock: per object lock to protect the internals
+ *
+ * @cdev: a cooling device debug structure
+ */
+struct thermal_debugfs {
+	struct dentry *d_top;
+	struct mutex lock;
+	union {
+		struct cdev_debugfs cdev_dbg;
+	};
+};
+
+void thermal_debug_init(void)
+{
+	d_root = debugfs_create_dir("thermal", NULL);
+	if (!d_root)
+		return;
+
+	d_cdev = debugfs_create_dir("cooling_devices", d_root);
+}
+
+static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id)
+{
+	struct thermal_debugfs *thermal_dbg;
+	char ids[IDSLENGTH];
+
+	thermal_dbg = kzalloc(sizeof(*thermal_dbg), GFP_KERNEL);
+	if (!thermal_dbg)
+		return NULL;
+
+	mutex_init(&thermal_dbg->lock);
+
+	snprintf(ids, IDSLENGTH, "%d", id);
+
+	thermal_dbg->d_top = debugfs_create_dir(ids, d);
+	if (!thermal_dbg->d_top) {
+		kfree(thermal_dbg);
+		return NULL;
+	}
+
+	return thermal_dbg;
+}
+
+static void thermal_debugfs_remove_id(struct thermal_debugfs *thermal_dbg)
+{
+	if (!thermal_dbg)
+		return;
+
+	debugfs_remove(thermal_dbg->d_top);
+
+	kfree(thermal_dbg);
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_alloc(struct thermal_debugfs *thermal_dbg,
+				  struct list_head *lists, int id)
+{
+	struct cdev_record *cdev_record;
+
+	cdev_record = kzalloc(sizeof(*cdev_record), GFP_KERNEL);
+	if (!cdev_record)
+		return NULL;
+
+	cdev_record->id = id;
+	INIT_LIST_HEAD(&cdev_record->node);
+	list_add_tail(&cdev_record->node,
+		      &lists[cdev_record->id % CDEVSTATS_HASH_SIZE]);
+
+	return cdev_record;
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_find(struct thermal_debugfs *thermal_dbg,
+				 struct list_head *lists, int id)
+{
+	struct cdev_record *entry;
+
+	list_for_each_entry(entry, &lists[id % CDEVSTATS_HASH_SIZE], node)
+		if (entry->id == id)
+			return entry;
+
+	return NULL;
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_get(struct thermal_debugfs *thermal_dbg,
+				struct list_head *lists, int id)
+{
+	struct cdev_record *cdev_record;
+
+	cdev_record = thermal_debugfs_cdev_record_find(thermal_dbg, lists, id);
+	if (cdev_record)
+		return cdev_record;
+
+	return thermal_debugfs_cdev_record_alloc(thermal_dbg, lists, id);
+}
+
+static void thermal_debugfs_cdev_clear(struct cdev_debugfs *cdev_dbg)
+{
+	int i;
+	struct cdev_record *entry, *tmp;
+
+	for (i = 0; i < CDEVSTATS_HASH_SIZE; i++) {
+
+		list_for_each_entry_safe(entry, tmp,
+					 &cdev_dbg->transitions[i], node) {
+			list_del(&entry->node);
+			kfree(entry);
+		}
+
+		list_for_each_entry_safe(entry, tmp,
+					 &cdev_dbg->durations[i], node) {
+			list_del(&entry->node);
+			kfree(entry);
+		}
+	}
+
+	cdev_dbg->total = 0;
+}
+
+static void *cdev_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	return (*pos < CDEVSTATS_HASH_SIZE) ? pos : NULL;
+}
+
+static void *cdev_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	(*pos)++;
+
+	return (*pos < CDEVSTATS_HASH_SIZE) ? pos : NULL;
+}
+
+static void cdev_seq_stop(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+static int cdev_tt_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+	struct cdev_debugfs *cdev_dbg = &thermal_dbg->cdev_dbg;
+	struct list_head *transitions = cdev_dbg->transitions;
+	struct cdev_record *entry;
+	int i = *(loff_t *)v;
+
+	if (!i)
+		seq_puts(s, "Transition\tOccurences\n");
+
+	list_for_each_entry(entry, &transitions[i], node) {
+		/*
+		 * Assuming maximum cdev states is 1024, the longer
+		 * string for a transition would be "1024->1024\0"
+		 */
+		char buffer[11];
+
+		snprintf(buffer, ARRAY_SIZE(buffer), "%d->%d",
+			 entry->id >> 16, entry->id & 0xFFFF);
+
+		seq_printf(s, "%-10s\t%-10llu\n", buffer, entry->count);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations tt_sops = {
+	.start = cdev_seq_start,
+	.next = cdev_seq_next,
+	.stop = cdev_seq_stop,
+	.show = cdev_tt_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(tt);
+
+static int cdev_dt_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+	struct cdev_debugfs *cdev_dbg = &thermal_dbg->cdev_dbg;
+	struct list_head *durations = cdev_dbg->durations;
+	struct cdev_record *entry;
+	int i = *(loff_t *)v;
+
+	if (!i)
+		seq_puts(s, "State\tResidency\n");
+
+	list_for_each_entry(entry, &durations[i], node) {
+		s64 duration = ktime_to_ms(entry->residency);
+
+		if (entry->id == cdev_dbg->current_state)
+			duration += ktime_ms_delta(ktime_get(),
+						   cdev_dbg->timestamp);
+
+		seq_printf(s, "%-5d\t%-10llu\n", entry->id, duration);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations dt_sops = {
+	.start = cdev_seq_start,
+	.next = cdev_seq_next,
+	.stop = cdev_seq_stop,
+	.show = cdev_dt_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(dt);
+
+static int cdev_clear_set(void *data, u64 val)
+{
+	struct thermal_debugfs *thermal_dbg = data;
+
+	if (!val)
+		return -EINVAL;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg);
+
+	mutex_unlock(&thermal_dbg->lock);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(cdev_clear_fops, NULL, cdev_clear_set, "%llu\n");
+
+/**
+ * thermal_debug_cdev_state_update - Update a cooling device state change
+ *
+ * Computes a transition and the duration of the previous state residency.
+ *
+ * @cdev : a pointer to a cooling device
+ * @new_state: an integer corresponding to the new cooling device state
+ */
+void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
+				     int new_state)
+{
+	struct thermal_debugfs *thermal_dbg = cdev->debugfs;
+	struct cdev_debugfs *cdev_dbg;
+	struct cdev_record *cdev_record;
+	int transition, old_state;
+
+	if (!thermal_dbg || (thermal_dbg->cdev_dbg.current_state == new_state))
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	cdev_dbg = &thermal_dbg->cdev_dbg;
+
+	old_state = cdev_dbg->current_state;
+
+	/*
+	 * Get the old state information in the durations list. If
+	 * this one does not exist, a new allocated one will be
+	 * returned. Recompute the total duration in the old state and
+	 * get a new timestamp for the new state.
+	 */
+	cdev_record = thermal_debugfs_cdev_record_get(thermal_dbg,
+						      cdev_dbg->durations,
+						      old_state);
+	if (cdev_record) {
+		ktime_t now = ktime_get();
+		ktime_t delta = ktime_sub(now, cdev_dbg->timestamp);
+		cdev_record->residency = ktime_add(cdev_record->residency, delta);
+		cdev_dbg->timestamp = now;
+	}
+
+	cdev_dbg->current_state = new_state;
+	transition = (old_state << 16) | new_state;
+
+	/*
+	 * Get the transition in the transitions list. If this one
+	 * does not exist, a new allocated one will be returned.
+	 * Increment the occurrence of this transition which is stored
+	 * in the value field.
+	 */
+	cdev_record = thermal_debugfs_cdev_record_get(thermal_dbg,
+						      cdev_dbg->transitions,
+						      transition);
+	if (cdev_record)
+		cdev_record->count++;
+
+	cdev_dbg->total++;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+/**
+ * thermal_debug_cdev_add - Add a cooling device debugfs entry
+ *
+ * Allocates a cooling device object for debug, initializes the
+ * statistics and create the entries in sysfs.
+ * @cdev: a pointer to a cooling device
+ */
+void thermal_debug_cdev_add(struct thermal_cooling_device *cdev)
+{
+	struct thermal_debugfs *thermal_dbg;
+	struct cdev_debugfs *cdev_dbg;
+	int i;
+
+	thermal_dbg = thermal_debugfs_add_id(d_cdev, cdev->id);
+	if (!thermal_dbg)
+		return;
+
+	cdev_dbg = &thermal_dbg->cdev_dbg;
+
+	for (i = 0; i < CDEVSTATS_HASH_SIZE; i++) {
+		INIT_LIST_HEAD(&cdev_dbg->transitions[i]);
+		INIT_LIST_HEAD(&cdev_dbg->durations[i]);
+	}
+
+	cdev_dbg->current_state = 0;
+	cdev_dbg->timestamp = ktime_get();
+
+	debugfs_create_file("trans_table", 0400, thermal_dbg->d_top,
+			    thermal_dbg, &tt_fops);
+
+	debugfs_create_file("time_in_state_ms", 0400, thermal_dbg->d_top,
+			    thermal_dbg, &dt_fops);
+
+	debugfs_create_file("clear", 0200, thermal_dbg->d_top,
+			    thermal_dbg, &cdev_clear_fops);
+
+	debugfs_create_u32("total_trans", 0400, thermal_dbg->d_top,
+			   &cdev_dbg->total);
+
+	cdev->debugfs = thermal_dbg;
+}
+
+/**
+ * thermal_debug_cdev_remove - Remove a cooling device debugfs entry
+ *
+ * Frees the statistics memory data and remove the debugfs entry
+ *
+ * @cdev: a pointer to a cooling device
+ */
+void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev)
+{
+	struct thermal_debugfs *thermal_dbg = cdev->debugfs;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg);
+	cdev->debugfs = NULL;
+
+	mutex_unlock(&thermal_dbg->lock);
+
+	thermal_debugfs_remove_id(thermal_dbg);
+}
diff --git a/drivers/thermal/thermal_debugfs.h b/drivers/thermal/thermal_debugfs.h
new file mode 100644
index 0000000000000..3414993884484
--- /dev/null
+++ b/drivers/thermal/thermal_debugfs.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CONFIG_THERMAL_DEBUGFS
+void thermal_debug_init(void);
+void thermal_debug_cdev_add(struct thermal_cooling_device *cdev);
+void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev);
+void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, int state);
+#else
+static inline void thermal_debug_init(void) {}
+static inline void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) {}
+static inline void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev) {}
+static inline void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
+						   int state) {}
+#endif /* CONFIG_THERMAL_DEBUGFS */
diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index c3982e0f00750..8f85581693e75 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -146,14 +146,22 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(thermal_zone_get_temp);
 
-static void thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev,
-				       int target)
+static int thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev, int state)
 {
-	if (cdev->ops->set_cur_state(cdev, target))
-		return;
+	int ret;
+
+	/*
+	 * No check is needed for the ops->set_cur_state as the
+	 * registering function checked the ops are correctly set
+	 */
+	ret = cdev->ops->set_cur_state(cdev, state);
+	if (!ret) {
+		thermal_notify_cdev_state_update(cdev->id, state);
+		thermal_cooling_device_stats_update(cdev, state);
+		thermal_debug_cdev_state_update(cdev, state);
+	}
 
-	thermal_notify_cdev_state_update(cdev->id, target);
-	thermal_cooling_device_stats_update(cdev, target);
+	return ret;
 }
 
 void __thermal_cdev_update(struct thermal_cooling_device *cdev)
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 9d0427da32af5..7defea8fa2230 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -32,6 +32,7 @@
 struct thermal_zone_device;
 struct thermal_cooling_device;
 struct thermal_instance;
+struct thermal_debugfs;
 struct thermal_attr;
 
 enum thermal_trend {
@@ -113,6 +114,9 @@ struct thermal_cooling_device {
 	struct mutex lock; /* protect thermal_instances list */
 	struct list_head thermal_instances;
 	struct list_head node;
+#ifdef CONFIG_THERMAL_DEBUGFS
+	struct thermal_debugfs *debugfs;
+#endif
 };
 
 /**
@@ -189,6 +193,9 @@ struct thermal_zone_device {
 	struct list_head node;
 	struct delayed_work poll_queue;
 	enum thermal_notify_event notify_event;
+#ifdef CONFIG_THERMAL_DEBUGFS
+	struct thermal_debugfs *debugfs;
+#endif
 	bool suspended;
 };
 
-- 
GitLab


From 7ef01f228c9f54c6260319858be138a8a7e9e704 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Tue, 9 Jan 2024 10:41:12 +0100
Subject: [PATCH 2611/4076] thermal/debugfs: Add thermal debugfs information
 for mitigation episodes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The mitigation episodes are recorded. A mitigation episode happens
when the first trip point is crossed the way up and then the way
down. During this episode other trip points can be crossed also and
are accounted for this mitigation episode. The interesting information
is the average temperature at the trip point, the undershot and the
overshot. The standard deviation of the mitigated temperature will be
added later.

The thermal debugfs directory structure tries to stay consistent with
the sysfs one but in a very simplified way:

thermal/
 `-- thermal_zones
     |-- 0
     |   `-- mitigations
     `-- 1
         `-- mitigations

The content of the mitigations file has the following format:

,-Mitigation at 349988258us, duration=130136ms
| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |
|    0 |  passive |     65000 |      2000 |     130136 |     68227 |     62500 |     75625 |
|    1 |  passive |     75000 |      2000 |     104209 |     74857 |     71666 |     77500 |
,-Mitigation at 272451637us, duration=75000ms
| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |
|    0 |  passive |     65000 |      2000 |      75000 |     68561 |     62500 |     75000 |
|    1 |  passive |     75000 |      2000 |      60714 |     74820 |     70555 |     77500 |
,-Mitigation at 238184119us, duration=27316ms
| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |
|    0 |  passive |     65000 |      2000 |      27316 |     73377 |     62500 |     75000 |
|    1 |  passive |     75000 |      2000 |      19468 |     75284 |     69444 |     77500 |
,-Mitigation at 39863713us, duration=136196ms
| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |
|    0 |  passive |     65000 |      2000 |     136196 |     73922 |     62500 |     75000 |
|    1 |  passive |     75000 |      2000 |      91721 |     74386 |     69444 |     78125 |

More information for a better understanding of the thermal behavior
will be added after. The idea is to give detailed statistics
information about the undershots and overshots, the temperature speed,
etc... As all the information in a single file is too much, the idea
would be to create a directory named with the mitigation timestamp
where all data could be added.

Please note this code is immune against trip ordering but not against
a trip temperature change while a mitigation is happening. However,
this situation should be extremely rare, perhaps not happening and we
might question ourselves if something should be done in the core
framework for other components first.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: White space fixups, rebase ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c    |   7 +
 drivers/thermal/thermal_debugfs.c | 400 +++++++++++++++++++++++++++++-
 drivers/thermal/thermal_debugfs.h |  14 ++
 3 files changed, 417 insertions(+), 4 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 5d9cc422d7baa..abf4c2390b197 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -382,6 +382,7 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		 */
 		if (tz->temperature >= trip->temperature) {
 			thermal_notify_tz_trip_up(tz, trip);
+			thermal_debug_tz_trip_up(tz, trip);
 			trip->threshold = trip->temperature - trip->hysteresis;
 		} else {
 			trip->threshold = trip->temperature;
@@ -399,6 +400,7 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		 */
 		if (tz->temperature < trip->temperature - trip->hysteresis) {
 			thermal_notify_tz_trip_down(tz, trip);
+			thermal_debug_tz_trip_down(tz, trip);
 			trip->threshold = trip->temperature;
 		} else {
 			trip->threshold = trip->temperature - trip->hysteresis;
@@ -430,6 +432,7 @@ static void update_temperature(struct thermal_zone_device *tz)
 	trace_thermal_temperature(tz);
 
 	thermal_genl_sampling_temp(tz->id, temp);
+	thermal_debug_update_temp(tz);
 }
 
 static void thermal_zone_device_check(struct work_struct *work)
@@ -1413,6 +1416,8 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 
 	thermal_notify_tz_create(tz);
 
+	thermal_debug_tz_add(tz);
+
 	return tz;
 
 unregister:
@@ -1476,6 +1481,8 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	if (!tz)
 		return;
 
+	thermal_debug_tz_remove(tz);
+
 	mutex_lock(&thermal_list_lock);
 	list_for_each_entry(pos, &thermal_tz_list, node)
 		if (pos == tz)
diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
index b18bdde47847e..b53881e9e0b6e 100644
--- a/drivers/thermal/thermal_debugfs.c
+++ b/drivers/thermal/thermal_debugfs.c
@@ -1,4 +1,3 @@
-
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright 2023 Linaro Limited
@@ -14,8 +13,11 @@
 #include <linux/mutex.h>
 #include <linux/thermal.h>
 
+#include "thermal_core.h"
+
 static struct dentry *d_root;
 static struct dentry *d_cdev;
+static struct dentry *d_tz;
 
 /*
  * Length of the string containing the thermal zone id or the cooling
@@ -60,7 +62,7 @@ struct cdev_debugfs {
 };
 
 /**
- * struct cdev_value - Common structure for cooling device entry
+ * struct cdev_record - Common structure for cooling device entry
  *
  * The following common structure allows to store the information
  * related to the transitions and to the state residencies. They are
@@ -81,22 +83,89 @@ struct cdev_record {
         };
 };
 
+/**
+ * struct trip_stats - Thermal trip statistics
+ *
+ * The trip_stats structure has the relevant information to show the
+ * statistics related to temperature going above a trip point.
+ *
+ * @timestamp: the trip crossing timestamp
+ * @duration: total time when the zone temperature was above the trip point
+ * @count: the number of times the zone temperature was above the trip point
+ * @max: maximum recorded temperature above the trip point
+ * @min: minimum recorded temperature above the trip point
+ * @avg: average temperature above the trip point
+ */
+struct trip_stats {
+	ktime_t timestamp;
+	ktime_t duration;
+	int count;
+	int max;
+	int min;
+	int avg;
+};
+
+/**
+ * struct tz_episode - A mitigation episode information
+ *
+ * The tz_episode structure describes a mitigation episode. A
+ * mitigation episode begins the trip point with the lower temperature
+ * is crossed the way up and ends when it is crossed the way
+ * down. During this episode we can have multiple trip points crossed
+ * the way up and down if there are multiple trip described in the
+ * firmware after the lowest temperature trip point.
+ *
+ * @timestamp: first trip point crossed the way up
+ * @duration: total duration of the mitigation episode
+ * @node: a list element to be added to the list of tz events
+ * @trip_stats: per trip point statistics, flexible array
+ */
+struct tz_episode {
+	ktime_t timestamp;
+	ktime_t duration;
+	struct list_head node;
+	struct trip_stats trip_stats[];
+};
+
+/**
+ * struct tz_debugfs - Store all mitigation episodes for a thermal zone
+ *
+ * The tz_debugfs structure contains the list of the mitigation
+ * episodes and has to track which trip point has been crossed in
+ * order to handle correctly nested trip point mitigation episodes.
+ *
+ * We keep the history of the trip point crossed in an array and as we
+ * can go back and forth inside this history, eg. trip 0,1,2,1,2,1,0,
+ * we keep track of the current position in the history array.
+ *
+ * @tz_episodes: a list of thermal mitigation episodes
+ * @trips_crossed: an array of trip points crossed by id
+ * @nr_trips: the number of trip points currently being crossed
+ */
+struct tz_debugfs {
+	struct list_head tz_episodes;
+	int *trips_crossed;
+	int nr_trips;
+};
+
 /**
  * struct thermal_debugfs - High level structure for a thermal object in debugfs
  *
  * The thermal_debugfs structure is the common structure used by the
- * cooling device to compute the statistics.
+ * cooling device or the thermal zone to store the statistics.
  *
  * @d_top: top directory of the thermal object directory
  * @lock: per object lock to protect the internals
  *
- * @cdev: a cooling device debug structure
+ * @cdev_dbg: a cooling device debug structure
+ * @tz_dbg: a thermal zone debug structure
  */
 struct thermal_debugfs {
 	struct dentry *d_top;
 	struct mutex lock;
 	union {
 		struct cdev_debugfs cdev_dbg;
+		struct tz_debugfs tz_dbg;
 	};
 };
 
@@ -107,6 +176,10 @@ void thermal_debug_init(void)
 		return;
 
 	d_cdev = debugfs_create_dir("cooling_devices", d_root);
+	if (!d_cdev)
+		return;
+
+	d_tz = debugfs_create_dir("thermal_zones", d_root);
 }
 
 static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id)
@@ -444,3 +517,322 @@ void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev)
 
 	thermal_debugfs_remove_id(thermal_dbg);
 }
+
+static struct tz_episode *thermal_debugfs_tz_event_alloc(struct thermal_zone_device *tz,
+							ktime_t now)
+{
+	struct tz_episode *tze;
+	int i;
+
+	tze = kzalloc(struct_size(tze, trip_stats, tz->num_trips), GFP_KERNEL);
+	if (!tze)
+		return NULL;
+
+	INIT_LIST_HEAD(&tze->node);
+	tze->timestamp = now;
+
+	for (i = 0; i < tz->num_trips; i++) {
+		tze->trip_stats[i].min = INT_MAX;
+		tze->trip_stats[i].max = INT_MIN;
+	}
+
+	return tze;
+}
+
+void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip)
+{
+	struct tz_episode *tze;
+	struct tz_debugfs *tz_dbg;
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	int temperature = tz->temperature;
+	int trip_id = thermal_zone_trip_id(tz, trip);
+	ktime_t now = ktime_get();
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	tz_dbg = &thermal_dbg->tz_dbg;
+
+	/*
+	 * The mitigation is starting. A mitigation can contain
+	 * several episodes where each of them is related to a
+	 * temperature crossing a trip point. The episodes are
+	 * nested. That means when the temperature is crossing the
+	 * first trip point, the duration begins to be measured. If
+	 * the temperature continues to increase and reaches the
+	 * second trip point, the duration of the first trip must be
+	 * also accumulated.
+	 *
+	 * eg.
+	 *
+	 * temp
+	 *   ^
+	 *   |             --------
+	 * trip 2         /        \         ------
+	 *   |           /|        |\      /|      |\
+	 * trip 1       / |        | `----  |      | \
+	 *   |         /| |        |        |      | |\
+	 * trip 0     / | |        |        |      | | \
+	 *   |       /| | |        |        |      | | |\
+	 *   |      / | | |        |        |      | | | `--
+	 *   |     /  | | |        |        |      | | |
+	 *   |-----   | | |        |        |      | | |
+	 *   |        | | |        |        |      | | |
+	 *    --------|-|-|--------|--------|------|-|-|------------------> time
+	 *            | | |<--t2-->|        |<-t2'>| | |
+	 *            | |                            | |
+	 *            | |<------------t1------------>| |
+	 *            |                                |
+	 *            |<-------------t0--------------->|
+	 *
+	 */
+	if (!tz_dbg->nr_trips) {
+		tze = thermal_debugfs_tz_event_alloc(tz, now);
+		if (!tze)
+			return;
+
+		list_add(&tze->node, &tz_dbg->tz_episodes);
+	}
+
+	/*
+	 * Each time a trip point is crossed the way up, the trip_id
+	 * is stored in the trip_crossed array and the nr_trips is
+	 * incremented. A nr_trips equal to zero means we are entering
+	 * a mitigation episode.
+	 *
+	 * The trip ids may not be in the ascending order but the
+	 * result in the array trips_crossed will be in the ascending
+	 * temperature order. The function detecting when a trip point
+	 * is crossed the way down will handle the very rare case when
+	 * the trip points may have been reordered during this
+	 * mitigation episode.
+	 */
+	tz_dbg->trips_crossed[tz_dbg->nr_trips++] = trip_id;
+
+	tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
+	tze->trip_stats[trip_id].timestamp = now;
+	tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, temperature);
+	tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, temperature);
+	tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg +
+		(temperature - tze->trip_stats[trip_id].avg) /
+		tze->trip_stats[trip_id].count;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
+				const struct thermal_trip *trip)
+{
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	struct tz_episode *tze;
+	struct tz_debugfs *tz_dbg;
+	ktime_t delta, now = ktime_get();
+	int trip_id = thermal_zone_trip_id(tz, trip);
+	int i;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	tz_dbg = &thermal_dbg->tz_dbg;
+
+	/*
+	 * The temperature crosses the way down but there was not
+	 * mitigation detected before. That may happen when the
+	 * temperature is greater than a trip point when registering a
+	 * thermal zone, which is a common use case as the kernel has
+	 * no mitigation mechanism yet at boot time.
+	 */
+	if (!tz_dbg->nr_trips)
+		goto out;
+
+	for (i = tz_dbg->nr_trips - 1; i >= 0; i--) {
+		if (tz_dbg->trips_crossed[i] == trip_id)
+			break;
+	}
+
+	if (i < 0)
+		goto out;
+
+	tz_dbg->nr_trips--;
+
+	if (i < tz_dbg->nr_trips)
+		tz_dbg->trips_crossed[i] = tz_dbg->trips_crossed[tz_dbg->nr_trips];
+
+	tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
+
+	delta = ktime_sub(now, tze->trip_stats[trip_id].timestamp);
+
+	tze->trip_stats[trip_id].duration =
+		ktime_add(delta, tze->trip_stats[trip_id].duration);
+
+	/*
+	 * This event closes the mitigation as we are crossing the
+	 * last trip point the way down.
+	 */
+	if (!tz_dbg->nr_trips)
+		tze->duration = ktime_sub(now, tze->timestamp);
+
+out:
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+void thermal_debug_update_temp(struct thermal_zone_device *tz)
+{
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	struct tz_episode *tze;
+	struct tz_debugfs *tz_dbg;
+	int trip_id, i;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	tz_dbg = &thermal_dbg->tz_dbg;
+
+	if (!tz_dbg->nr_trips)
+		goto out;
+
+	for (i = 0; i < tz_dbg->nr_trips; i++) {
+		trip_id = tz_dbg->trips_crossed[i];
+		tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
+		tze->trip_stats[trip_id].count++;
+		tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, tz->temperature);
+		tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, tz->temperature);
+		tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg +
+			(tz->temperature - tze->trip_stats[trip_id].avg) /
+			tze->trip_stats[trip_id].count;
+	}
+out:
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+static void *tze_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	return seq_list_start(&tz_dbg->tz_episodes, *pos);
+}
+
+static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+	struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg;
+
+	return seq_list_next(v, &tz_dbg->tz_episodes, pos);
+}
+
+static void tze_seq_stop(struct seq_file *s, void *v)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+static int tze_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_trip *trip;
+	struct tz_episode *tze;
+	const char *type;
+	int trip_id;
+
+	tze = list_entry((struct list_head *)v, struct tz_episode, node);
+
+	seq_printf(s, ",-Mitigation at %lluus, duration=%llums\n",
+		   ktime_to_us(tze->timestamp),
+		   ktime_to_ms(tze->duration));
+
+	seq_printf(s, "| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |\n");
+
+	for_each_trip(tz, trip) {
+		/*
+		 * There is no possible mitigation happening at the
+		 * critical trip point, so the stats will be always
+		 * zero, skip this trip point
+		 */
+		if (trip->type == THERMAL_TRIP_CRITICAL)
+			continue;
+
+		if (trip->type == THERMAL_TRIP_PASSIVE)
+			type = "passive";
+		else if (trip->type == THERMAL_TRIP_ACTIVE)
+			type = "active";
+		else
+			type = "hot";
+
+		trip_id = thermal_zone_trip_id(tz, trip);
+
+		seq_printf(s, "| %*d | %*s | %*d | %*d | %*lld | %*d | %*d | %*d |\n",
+			   4 , trip_id,
+			   8, type,
+			   9, trip->temperature,
+			   9, trip->hysteresis,
+			   10, ktime_to_ms(tze->trip_stats[trip_id].duration),
+			   9, tze->trip_stats[trip_id].avg,
+			   9, tze->trip_stats[trip_id].min,
+			   9, tze->trip_stats[trip_id].max);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations tze_sops = {
+	.start = tze_seq_start,
+	.next = tze_seq_next,
+	.stop = tze_seq_stop,
+	.show = tze_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(tze);
+
+void thermal_debug_tz_add(struct thermal_zone_device *tz)
+{
+	struct thermal_debugfs *thermal_dbg;
+	struct tz_debugfs *tz_dbg;
+
+	thermal_dbg = thermal_debugfs_add_id(d_tz, tz->id);
+	if (!thermal_dbg)
+		return;
+
+	tz_dbg = &thermal_dbg->tz_dbg;
+
+	tz_dbg->trips_crossed = kzalloc(sizeof(int) * tz->num_trips, GFP_KERNEL);
+	if (!tz_dbg->trips_crossed) {
+		thermal_debugfs_remove_id(thermal_dbg);
+		return;
+	}
+
+	INIT_LIST_HEAD(&tz_dbg->tz_episodes);
+
+	debugfs_create_file("mitigations", 0400, thermal_dbg->d_top, tz, &tze_fops);
+
+	tz->debugfs = thermal_dbg;
+}
+
+void thermal_debug_tz_remove(struct thermal_zone_device *tz)
+{
+	struct thermal_debugfs *thermal_dbg = tz->debugfs;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	tz->debugfs = NULL;
+
+	mutex_unlock(&thermal_dbg->lock);
+
+	thermal_debugfs_remove_id(thermal_dbg);
+}
diff --git a/drivers/thermal/thermal_debugfs.h b/drivers/thermal/thermal_debugfs.h
index 3414993884484..155b9af5fe870 100644
--- a/drivers/thermal/thermal_debugfs.h
+++ b/drivers/thermal/thermal_debugfs.h
@@ -5,10 +5,24 @@ void thermal_debug_init(void);
 void thermal_debug_cdev_add(struct thermal_cooling_device *cdev);
 void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev);
 void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, int state);
+void thermal_debug_tz_add(struct thermal_zone_device *tz);
+void thermal_debug_tz_remove(struct thermal_zone_device *tz);
+void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip);
+void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
+				const struct thermal_trip *trip);
+void thermal_debug_update_temp(struct thermal_zone_device *tz);
 #else
 static inline void thermal_debug_init(void) {}
 static inline void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) {}
 static inline void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev) {}
 static inline void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
 						   int state) {}
+static inline void thermal_debug_tz_add(struct thermal_zone_device *tz) {}
+static inline void thermal_debug_tz_remove(struct thermal_zone_device *tz) {}
+static inline void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
+					    const struct thermal_trip *trip) {};
+static inline void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
+					      const struct thermal_trip *trip) {}
+static inline void thermal_debug_update_temp(struct thermal_zone_device *tz) {}
 #endif /* CONFIG_THERMAL_DEBUGFS */
-- 
GitLab


From 57a427c81c322c5f0cdfe7c46cdee553d18b1ec6 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 5 Jan 2024 14:45:11 +0100
Subject: [PATCH 2612/4076] thermal: core: Use kstrdup_const() during cooling
 device registration

Some *thermal_cooling_device_register() calls pass a string literal as
the 'type' parameter, so kstrdup_const() can be used instead of
kstrdup() to avoid a memory allocation in such cases.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c | 6 +++---
 include/linux/thermal.h        | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index abf4c2390b197..dfaa6341694a0 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -845,7 +845,7 @@ static void thermal_release(struct device *dev)
 			    sizeof("cooling_device") - 1)) {
 		cdev = to_cooling_device(dev);
 		thermal_cooling_device_destroy_sysfs(cdev);
-		kfree(cdev->type);
+		kfree_const(cdev->type);
 		ida_free(&thermal_cdev_ida, cdev->id);
 		kfree(cdev);
 	}
@@ -917,7 +917,7 @@ __thermal_cooling_device_register(struct device_node *np,
 	cdev->id = ret;
 	id = ret;
 
-	cdev->type = kstrdup(type ? type : "", GFP_KERNEL);
+	cdev->type = kstrdup_const(type ? type : "", GFP_KERNEL);
 	if (!cdev->type) {
 		ret = -ENOMEM;
 		goto out_ida_remove;
@@ -970,7 +970,7 @@ __thermal_cooling_device_register(struct device_node *np,
 out_cooling_dev:
 	thermal_cooling_device_destroy_sysfs(cdev);
 out_cdev_type:
-	kfree(cdev->type);
+	kfree_const(cdev->type);
 out_ida_remove:
 	ida_free(&thermal_cdev_ida, id);
 out_kfree_cdev:
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 7defea8fa2230..3227335fb4471 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -103,7 +103,7 @@ struct thermal_cooling_device_ops {
 
 struct thermal_cooling_device {
 	int id;
-	char *type;
+	const char *type;
 	unsigned long max_state;
 	struct device device;
 	struct device_node *np;
-- 
GitLab


From 11fde939314836c4375b567d60407d752d987069 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 9 Jan 2024 17:42:04 +0100
Subject: [PATCH 2613/4076] thermal: netlink: Rework notify API for cooling
 devices

In analogy with some previous thermal netlink API changes, redefine
thermal_notify_cdev_state_update(), thermal_notify_cdev_add() and
thermal_notify_cdev_delete() to take a const cdev pointer as their
first argument and let them extract the requisite information from
there by themselves.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_helpers.c |  2 +-
 drivers/thermal/thermal_netlink.c | 15 ++++++++-------
 drivers/thermal/thermal_netlink.h | 16 +++++++++-------
 3 files changed, 18 insertions(+), 15 deletions(-)

diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index 8f85581693e75..dd72eecfc7ca4 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -156,7 +156,7 @@ static int thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev, int s
 	 */
 	ret = cdev->ops->set_cur_state(cdev, state);
 	if (!ret) {
-		thermal_notify_cdev_state_update(cdev->id, state);
+		thermal_notify_cdev_state_update(cdev, state);
 		thermal_cooling_device_stats_update(cdev, state);
 		thermal_debug_cdev_state_update(cdev, state);
 	}
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 46b0156a63191..76a231a296545 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -364,24 +364,25 @@ int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_CHANGE, &p);
 }
 
-int thermal_notify_cdev_state_update(int cdev_id, int cdev_state)
+int thermal_notify_cdev_state_update(const struct thermal_cooling_device *cdev,
+				     int state)
 {
-	struct param p = { .cdev_id = cdev_id, .cdev_state = cdev_state };
+	struct param p = { .cdev_id = cdev->id, .cdev_state = state };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_STATE_UPDATE, &p);
 }
 
-int thermal_notify_cdev_add(int cdev_id, const char *name, int cdev_max_state)
+int thermal_notify_cdev_add(const struct thermal_cooling_device *cdev)
 {
-	struct param p = { .cdev_id = cdev_id, .name = name,
-			   .cdev_max_state = cdev_max_state };
+	struct param p = { .cdev_id = cdev->id, .name = cdev->type,
+			   .cdev_max_state = cdev->max_state };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_ADD, &p);
 }
 
-int thermal_notify_cdev_delete(int cdev_id)
+int thermal_notify_cdev_delete(const struct thermal_cooling_device *cdev)
 {
-	struct param p = { .cdev_id = cdev_id };
+	struct param p = { .cdev_id = cdev->id };
 
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_DELETE, &p);
 }
diff --git a/drivers/thermal/thermal_netlink.h b/drivers/thermal/thermal_netlink.h
index 13ea2ad23d3ab..93a927e144d55 100644
--- a/drivers/thermal/thermal_netlink.h
+++ b/drivers/thermal/thermal_netlink.h
@@ -12,6 +12,7 @@ struct thermal_genl_cpu_caps {
 
 struct thermal_zone_device;
 struct thermal_trip;
+struct thermal_cooling_device;
 
 /* Netlink notification function */
 #ifdef CONFIG_THERMAL_NETLINK
@@ -27,9 +28,10 @@ int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz,
 			      const struct thermal_trip *trip);
 int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz,
 				  const struct thermal_trip *trip);
-int thermal_notify_cdev_state_update(int cdev_id, int state);
-int thermal_notify_cdev_add(int cdev_id, const char *name, int max_state);
-int thermal_notify_cdev_delete(int cdev_id);
+int thermal_notify_cdev_state_update(const struct thermal_cooling_device *cdev,
+				     int state);
+int thermal_notify_cdev_add(const struct thermal_cooling_device *cdev);
+int thermal_notify_cdev_delete(const struct thermal_cooling_device *cdev);
 int thermal_notify_tz_gov_change(const struct thermal_zone_device *tz,
 				 const char *name);
 int thermal_genl_sampling_temp(int id, int temp);
@@ -79,18 +81,18 @@ static inline int thermal_notify_tz_trip_change(const struct thermal_zone_device
 	return 0;
 }
 
-static inline int thermal_notify_cdev_state_update(int cdev_id, int state)
+static inline int thermal_notify_cdev_state_update(const struct thermal_cooling_device *cdev,
+						   int state)
 {
 	return 0;
 }
 
-static inline int thermal_notify_cdev_add(int cdev_id, const char *name,
-					  int max_state)
+static inline int thermal_notify_cdev_add(const struct thermal_cooling_device *cdev)
 {
 	return 0;
 }
 
-static inline int thermal_notify_cdev_delete(int cdev_id)
+static inline int thermal_notify_cdev_delete(const struct thermal_cooling_device *cdev)
 {
 	return 0;
 }
-- 
GitLab


From fd881eac3af6c4e36b34ce92d69fb1d7e95f5920 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 9 Jan 2024 17:42:48 +0100
Subject: [PATCH 2614/4076] thermal: helpers: Rearrange
 thermal_cdev_set_cur_state()

Change the code layout in thermal_cdev_set_cur_state() so it returns
early on errors which is more consistent with what happens elsewhere.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_helpers.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index dd72eecfc7ca4..0329f4a71b020 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -155,13 +155,14 @@ static int thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev, int s
 	 * registering function checked the ops are correctly set
 	 */
 	ret = cdev->ops->set_cur_state(cdev, state);
-	if (!ret) {
-		thermal_notify_cdev_state_update(cdev, state);
-		thermal_cooling_device_stats_update(cdev, state);
-		thermal_debug_cdev_state_update(cdev, state);
-	}
+	if (ret)
+		return ret;
 
-	return ret;
+	thermal_notify_cdev_state_update(cdev, state);
+	thermal_cooling_device_stats_update(cdev, state);
+	thermal_debug_cdev_state_update(cdev, state);
+
+	return 0;
 }
 
 void __thermal_cdev_update(struct thermal_cooling_device *cdev)
-- 
GitLab


From e95fa7404716f6e25021e66067271a4ad8eb1486 Mon Sep 17 00:00:00 2001
From: Di Shen <di.shen@unisoc.com>
Date: Wed, 10 Jan 2024 19:55:26 +0800
Subject: [PATCH 2615/4076] thermal: gov_power_allocator: avoid inability to
 reset a cdev

Commit 0952177f2a1f ("thermal/core/power_allocator: Update once
cooling devices when temp is low") adds an update flag to avoid
triggering a thermal event when there is no need, and the thermal
cdev is updated once when the temperature is low.

But when the trips are writable, and switch_on_temp is set to be a
higher value, the cooling device state may not be reset to 0,
because last_temperature is smaller than switch_on_temp.

For example:
First:
switch_on_temp=70 control_temp=85;
Then userspace change the trip_temp:
switch_on_temp=45 control_temp=55 cur_temp=54

Then userspace reset the trip_temp:
switch_on_temp=70 control_temp=85 cur_temp=57 last_temp=54

At this time, the cooling device state should be reset to 0.
However, because cur_temp(57) < switch_on_temp(70)
last_temp(54) < switch_on_temp(70)  ---->  update = false,
update is false, the cooling device state can not be reset.

Using the observation that tz->passive can also be regarded as the
temperature status, set the update flag to the tz->passive value.

When the temperature drops below switch_on for the first time, the
states of cooling devices can be reset once, and tz->passive is updated
to 0. In the next round, because tz->passive is 0, cdev->state will not
be updated.

By using the tz->passive value as the "update" flag, the issue above
can be solved, and the cooling devices can be updated only once when the
temperature is low.

Fixes: 0952177f2a1f ("thermal/core/power_allocator: Update once cooling devices when temp is low")
Cc: 5.13+ <stable@vger.kernel.org> # 5.13+
Suggested-by: Wei Wang <wvw@google.com>
Signed-off-by: Di Shen <di.shen@unisoc.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/gov_power_allocator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 7b6aa265ff6a0..81e061f183ad1 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -762,7 +762,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz,
 
 	trip = params->trip_switch_on;
 	if (trip && tz->temperature < trip->temperature) {
-		update = tz->last_temperature >= trip->temperature;
+		update = tz->passive;
 		tz->passive = 0;
 		reset_pid_controller(params);
 		allow_maximum_power(tz, update);
-- 
GitLab


From 97566d09fd02d2ab329774bb89a2cdf2267e86d9 Mon Sep 17 00:00:00 2001
From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Date: Tue, 9 Jan 2024 19:07:04 -0800
Subject: [PATCH 2616/4076] thermal: intel: hfi: Add syscore callbacks for
 system-wide PM

The kernel allocates a memory buffer and provides its location to the
hardware, which uses it to update the HFI table. This allocation occurs
during boot and remains constant throughout runtime.

When resuming from hibernation, the restore kernel allocates a second
memory buffer and reprograms the HFI hardware with the new location as
part of a normal boot. The location of the second memory buffer may
differ from the one allocated by the image kernel.

When the restore kernel transfers control to the image kernel, its HFI
buffer becomes invalid, potentially leading to memory corruption if the
hardware writes to it (the hardware continues to use the buffer from the
restore kernel).

It is also possible that the hardware "forgets" the address of the memory
buffer when resuming from "deep" suspend. Memory corruption may also occur
in such a scenario.

To prevent the described memory corruption, disable HFI when preparing to
suspend or hibernate. Enable it when resuming.

Add syscore callbacks to handle the package of the boot CPU (packages of
non-boot CPUs are handled via CPU offline). Syscore ops always run on the
boot CPU. Additionally, HFI only needs to be disabled during "deep" suspend
and hibernation. Syscore ops only run in these cases.

Cc: 6.1+ <stable@vger.kernel.org> # 6.1+
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
[ rjw: Comment adjustment, subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/intel/intel_hfi.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
index 22445403b5200..3b04c6ec4fca0 100644
--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -35,7 +35,9 @@
 #include <linux/processor.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/suspend.h>
 #include <linux/string.h>
+#include <linux/syscore_ops.h>
 #include <linux/topology.h>
 #include <linux/workqueue.h>
 
@@ -571,6 +573,30 @@ static __init int hfi_parse_features(void)
 	return 0;
 }
 
+static void hfi_do_enable(void)
+{
+	/* This code runs only on the boot CPU. */
+	struct hfi_cpu_info *info = &per_cpu(hfi_cpu_info, 0);
+	struct hfi_instance *hfi_instance = info->hfi_instance;
+
+	/* No locking needed. There is no concurrency with CPU online. */
+	hfi_set_hw_table(hfi_instance);
+	hfi_enable();
+}
+
+static int hfi_do_disable(void)
+{
+	/* No locking needed. There is no concurrency with CPU offline. */
+	hfi_disable();
+
+	return 0;
+}
+
+static struct syscore_ops hfi_pm_ops = {
+	.resume = hfi_do_enable,
+	.suspend = hfi_do_disable,
+};
+
 void __init intel_hfi_init(void)
 {
 	struct hfi_instance *hfi_instance;
@@ -602,6 +628,8 @@ void __init intel_hfi_init(void)
 	if (!hfi_updates_wq)
 		goto err_nomem;
 
+	register_syscore_ops(&hfi_pm_ops);
+
 	return;
 
 err_nomem:
-- 
GitLab


From 6dcb35088e264306b948141971286257681ca412 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 12 Jan 2024 17:30:18 +0300
Subject: [PATCH 2617/4076] thermal/debugfs: Unlock on error path in
 thermal_debug_tz_trip_up()

Add a missing mutex_unlock(&thermal_dbg->lock) to this error path.

Fixes: 7ef01f228c9f ("thermal/debugfs: Add thermal debugfs information for mitigation episodes")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_debugfs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
index b53881e9e0b6e..c617e8b9f0ddf 100644
--- a/drivers/thermal/thermal_debugfs.c
+++ b/drivers/thermal/thermal_debugfs.c
@@ -592,7 +592,7 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
 	if (!tz_dbg->nr_trips) {
 		tze = thermal_debugfs_tz_event_alloc(tz, now);
 		if (!tze)
-			return;
+			goto unlock;
 
 		list_add(&tze->node, &tz_dbg->tz_episodes);
 	}
@@ -620,6 +620,7 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
 		(temperature - tze->trip_stats[trip_id].avg) /
 		tze->trip_stats[trip_id].count;
 
+unlock:
 	mutex_unlock(&thermal_dbg->lock);
 }
 
-- 
GitLab


From 7afc0e7f681e6efd6b826f003fc14c17b5093643 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 22 Dec 2023 06:56:39 +0100
Subject: [PATCH 2618/4076] MAINTAINERS: pwm: Thierry steps down, Uwe takes
 over
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It's not easy to let go responsibility for a subsystem that one cared
for for a long time, but Thierry realized that his heart isn't in the
pwm framework any more.

Thierry cared for the pwm subsystem (commit 200efedd8766 ("pwm: Take
over maintainership of the PWM subsystem")) as a maintainer during
nearly 12 years. A big thanks for the time, effort and dedication spend
during that time.

Uwe takes over maintenance.

Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 MAINTAINERS | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 5342cf32d73ff..c6c7b50e6ef60 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17561,12 +17561,11 @@ F:	Documentation/devicetree/bindings/leds/irled/pwm-ir-tx.yaml
 F:	drivers/media/rc/pwm-ir-tx.c
 
 PWM SUBSYSTEM
-M:	Thierry Reding <thierry.reding@gmail.com>
-R:	Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+M:	Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
 L:	linux-pwm@vger.kernel.org
 S:	Maintained
 Q:	https://patchwork.ozlabs.org/project/linux-pwm/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/thierry.reding/linux-pwm.git
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/ukleinek/linux.git
 F:	Documentation/devicetree/bindings/gpio/gpio-mvebu.yaml
 F:	Documentation/devicetree/bindings/pwm/
 F:	Documentation/driver-api/pwm.rst
-- 
GitLab


From 5266caaf5660529e3da53004b8b7174cab6374ed Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 12 Jan 2024 20:26:26 +0800
Subject: [PATCH 2619/4076] blk-mq: fix IO hang from sbitmap wakeup race

In blk_mq_mark_tag_wait(), __add_wait_queue() may be re-ordered
with the following blk_mq_get_driver_tag() in case of getting driver
tag failure.

Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observe
the added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantime
blk_mq_mark_tag_wait() can't get driver tag successfully.

This issue can be reproduced by running the following test in loop, and
fio hang can be observed in < 30min when running it on my test VM
in laptop.

	modprobe -r scsi_debug
	modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4
	dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`
	fio --filename=/dev/"$dev" --direct=1 --rw=randrw --bs=4k --iodepth=1 \
       		--runtime=100 --numjobs=40 --time_based --name=test \
        	--ioengine=libaio

Fix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), which
is just fine in case of running out of tag.

Cc: Jan Kara <jack@suse.cz>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Reported-by: Changhui Zhong <czhong@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240112122626.4181044-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index aa9a05fdd0237..a4c54c5895a13 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1852,6 +1852,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
 	__add_wait_queue(wq, wait);
 
+	/*
+	 * Add one explicit barrier since blk_mq_get_driver_tag() may
+	 * not imply barrier in case of failure.
+	 *
+	 * Order adding us to wait queue and allocating driver tag.
+	 *
+	 * The pair is the one implied in sbitmap_queue_wake_up() which
+	 * orders clearing sbitmap tag bits and waitqueue_active() in
+	 * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless
+	 *
+	 * Otherwise, re-order of adding wait queue and getting driver tag
+	 * may cause __sbitmap_queue_wake_up() to wake up nothing because
+	 * the waitqueue_active() may not observe us in wait queue.
+	 */
+	smp_mb();
+
 	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
-- 
GitLab


From 25c1772a0493463408489b1fae65cf77fe46cac1 Mon Sep 17 00:00:00 2001
From: Christian Heusel <christian@heusel.eu>
Date: Fri, 12 Jan 2024 00:15:18 +0100
Subject: [PATCH 2620/4076] block: print symbolic error name instead of error
 code

Utilize the %pe print specifier to get the symbolic error name as a
string (i.e "-ENOMEM") in the log message instead of the error code to
increase its readablility.

This change was suggested in
https://lore.kernel.org/all/92972476-0b1f-4d0a-9951-af3fc8bc6e65@suswa.mountain/

Signed-off-by: Christian Heusel <christian@heusel.eu>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20240111231521.1596838-1-christian@heusel.eu
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/block/partitions/core.c b/block/partitions/core.c
index e6ac73617f3e1..cab0d76a828e3 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -562,8 +562,8 @@ static bool blk_add_partition(struct gendisk *disk,
 	part = add_partition(disk, p, from, size, state->parts[p].flags,
 			     &state->parts[p].info);
 	if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) {
-		printk(KERN_ERR " %s: p%d could not be added: %ld\n",
-		       disk->disk_name, p, -PTR_ERR(part));
+		printk(KERN_ERR " %s: p%d could not be added: %pe\n",
+		       disk->disk_name, p, part);
 		return true;
 	}
 
-- 
GitLab


From 309ce6741430b5a7b5e85cd1a7569647f8d9dfa6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 11 Jan 2024 14:57:04 +0100
Subject: [PATCH 2621/4076] blk-mq: rename blk_mq_can_use_cached_rq

blk_mq_can_use_cached_rq doesn't just check if we can use the request,
but also performs the work to actually use it.  Remove the _can in the
naming, and improve the comment describing the function.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240111135705.2155518-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a4c54c5895a13..f57b86d6de6ac 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2900,8 +2900,11 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	return NULL;
 }
 
-/* return true if this @rq can be used for @bio */
-static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
+/*
+ * Check if we can use the passed on request for submitting the passed in bio,
+ * and remove it from the request list if it can be used.
+ */
+static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 		struct bio *bio)
 {
 	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
@@ -2979,7 +2982,7 @@ void blk_mq_submit_bio(struct bio *bio)
 			return;
 		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 			return;
-		if (blk_mq_can_use_cached_rq(rq, plug, bio))
+		if (blk_mq_use_cached_rq(rq, plug, bio))
 			goto done;
 		percpu_ref_get(&q->q_usage_counter);
 	} else {
-- 
GitLab


From 454abb80e26ab85323a30e52aa7b0ee9aae1d38a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?=
 <amadeuszx.slawinski@linux.intel.com>
Date: Fri, 12 Jan 2024 12:33:49 +0100
Subject: [PATCH 2622/4076] ALSA: hda: Properly setup HDMI stream
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit 4005d1ba0a7e ("ASoC: soc-dai: don't call PCM audio ops if
the stream is not supported") HDMI playback is broken with avs driver.
This happens because for HDMI stream (unlike generic HDA one)
channels_min for stream is not set when creating PCMs. Fix this by
setting the value based on first available converter.

Fixes: 4005d1ba0a7e ("ASoC: soc-dai: don't call PCM audio ops if the stream is not supported")
Signed-off-by: Amadeusz Sławiński <amadeuszx.slawinski@linux.intel.com>
Link: https://lore.kernel.org/r/20240112113349.2905328-1-amadeuszx.slawinski@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_hdmi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 200779296a1b8..495d63101186f 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2301,6 +2301,7 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec)
 	codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num);
 
 	for (idx = 0; idx < pcm_num; idx++) {
+		struct hdmi_spec_per_cvt *per_cvt;
 		struct hda_pcm *info;
 		struct hda_pcm_stream *pstr;
 
@@ -2316,6 +2317,11 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec)
 		pstr = &info->stream[SNDRV_PCM_STREAM_PLAYBACK];
 		pstr->substreams = 1;
 		pstr->ops = generic_ops;
+
+		per_cvt = get_cvt(spec, 0);
+		pstr->channels_min = per_cvt->channels_min;
+		pstr->channels_max = per_cvt->channels_max;
+
 		/* pcm number is less than pcm_rec array size */
 		if (spec->pcm_used >= ARRAY_SIZE(spec->pcm_rec))
 			break;
-- 
GitLab


From 678164a5f0ecd6e0134ce246d64ae7345f8de59c Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Fri, 22 Dec 2023 13:13:11 +0000
Subject: [PATCH 2623/4076] pwm: bcm2835: Remove duplicate call to
 clk_rate_exclusive_put()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

devm_add_action_or_reset() already calls the action in the error case.

Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Closes: https://lore.kernel.org/linux-pwm/fuku3b5ur6y4k4refd3vmeoenzjo6mwe3b3gtel34rhhhtvnsa@w4uktgbqsc3w/
Fixes: fcc760729359 ("pwm: bcm2835: Allow PWM driver to be used in atomic context")
Signed-off-by: Sean Young <sean@mess.org>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20231222131312.174491-1-sean@mess.org
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
---
 drivers/pwm/pwm-bcm2835.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c
index 307c0bd5f8855..283cf27f25bae 100644
--- a/drivers/pwm/pwm-bcm2835.c
+++ b/drivers/pwm/pwm-bcm2835.c
@@ -160,10 +160,8 @@ static int bcm2835_pwm_probe(struct platform_device *pdev)
 
 	ret = devm_add_action_or_reset(&pdev->dev, devm_clk_rate_exclusive_put,
 				       pc->clk);
-	if (ret) {
-		clk_rate_exclusive_put(pc->clk);
+	if (ret)
 		return ret;
-	}
 
 	pc->rate = clk_get_rate(pc->clk);
 	if (!pc->rate)
-- 
GitLab


From a297d07b9a1e4fb8cda25a4a2363a507d294b7c9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 9 Jan 2024 22:34:31 +0100
Subject: [PATCH 2624/4076] pwm: Fix out-of-bounds access in
 of_pwm_single_xlate()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With args->args_count == 2 args->args[2] is not defined. Actually the
flags are contained in args->args[1].

Fixes: 3ab7b6ac5d82 ("pwm: Introduce single-PWM of_xlate function")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/243908750d306e018a3d4bf2eb745d53ab50f663.1704835845.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
---
 drivers/pwm/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 9a4c720c88aad..f2728ee787d7a 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -152,7 +152,7 @@ of_pwm_single_xlate(struct pwm_chip *chip, const struct of_phandle_args *args)
 	pwm->args.period = args->args[0];
 	pwm->args.polarity = PWM_POLARITY_NORMAL;
 
-	if (args->args_count == 2 && args->args[2] & PWM_POLARITY_INVERTED)
+	if (args->args_count == 2 && args->args[1] & PWM_POLARITY_INVERTED)
 		pwm->args.polarity = PWM_POLARITY_INVERSED;
 
 	return pwm;
-- 
GitLab


From 9320fc509b87b4d795fb37112931e2f4f8b5c55f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 6 Jan 2024 15:13:03 +0100
Subject: [PATCH 2625/4076] pwm: jz4740: Don't use dev_err_probe() in
 .request()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dev_err_probe() is only supposed to be used in probe functions. While it
probably doesn't hurt, both the EPROBE_DEFER handling and calling
device_set_deferred_probe_reason() are conceptually wrong in the request
callback. So replace the call by dev_err() and a separate return
statement.

This effectively reverts commit c0bfe9606e03 ("pwm: jz4740: Simplify
with dev_err_probe()").

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240106141302.1253365-2-u.kleine-koenig@pengutronix.de
Fixes: c0bfe9606e03 ("pwm: jz4740: Simplify with dev_err_probe()")
Cc: stable@vger.kernel.org
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
---
 drivers/pwm/pwm-jz4740.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c
index 80dcff237a155..3933418e551b4 100644
--- a/drivers/pwm/pwm-jz4740.c
+++ b/drivers/pwm/pwm-jz4740.c
@@ -61,9 +61,10 @@ static int jz4740_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 	snprintf(name, sizeof(name), "timer%u", pwm->hwpwm);
 
 	clk = clk_get(chip->dev, name);
-	if (IS_ERR(clk))
-		return dev_err_probe(chip->dev, PTR_ERR(clk),
-				     "Failed to get clock\n");
+	if (IS_ERR(clk)) {
+		dev_err(chip->dev, "error %pe: Failed to get clock\n", clk);
+		return PTR_ERR(clk);
+	}
 
 	err = clk_prepare_enable(clk);
 	if (err < 0) {
-- 
GitLab


From 73bf93edeeea866b0b6efbc8d2595bdaaba7f1a5 Mon Sep 17 00:00:00 2001
From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Date: Fri, 12 Jan 2024 14:27:09 +0800
Subject: [PATCH 2626/4076] cxl/core: use sysfs_emit() for attr's _show()

sprintf() is deprecated for sysfs, use preferred sysfs_emit() instead.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Fan Ni <fan.ni@samsung.com>
Link: https://lore.kernel.org/r/20240112062709.2490947-1-ruansy.fnst@fujitsu.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/memdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index 2f43d368ba073..dae8802ecdb01 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -114,7 +114,7 @@ static DEVICE_ATTR_RO(serial);
 static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
 {
-	return sprintf(buf, "%d\n", dev_to_node(dev));
+	return sysfs_emit(buf, "%d\n", dev_to_node(dev));
 }
 static DEVICE_ATTR_RO(numa_node);
 
-- 
GitLab


From 4a693ce65b186fddc1a73621bd6f941e6e3eca21 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 29 Dec 2023 16:02:13 +0800
Subject: [PATCH 2627/4076] kdump: defer the insertion of crashkernel resources

In /proc/iomem, sub-regions should be inserted after their parent,
otherwise the insertion of parent resource fails.  But after generic
crashkernel reservation applied, in both RISC-V and ARM64 (LoongArch will
also use generic reservation later on), crashkernel resources are inserted
before their parent, which causes the parent disappear in /proc/iomem.  So
we defer the insertion of crashkernel resources to an early_initcall().

1, Without 'crashkernel' parameter:

 100d0100-100d01ff : LOON0001:00
   100d0100-100d01ff : LOON0001:00 LOON0001:00
 100e0000-100e0bff : LOON0002:00
   100e0000-100e0bff : LOON0002:00 LOON0002:00
 1fe001e0-1fe001e7 : serial
 90400000-fa17ffff : System RAM
   f6220000-f622ffff : Reserved
   f9ee0000-f9ee3fff : Reserved
   fa120000-fa17ffff : Reserved
 fa190000-fe0bffff : System RAM
   fa190000-fa1bffff : Reserved
 fe4e0000-47fffffff : System RAM
   43c000000-441ffffff : Reserved
   47ff98000-47ffa3fff : Reserved
   47ffa4000-47ffa7fff : Reserved
   47ffa8000-47ffabfff : Reserved
   47ffac000-47ffaffff : Reserved
   47ffb0000-47ffb3fff : Reserved

2, With 'crashkernel' parameter, before this patch:

 100d0100-100d01ff : LOON0001:00
   100d0100-100d01ff : LOON0001:00 LOON0001:00
 100e0000-100e0bff : LOON0002:00
   100e0000-100e0bff : LOON0002:00 LOON0002:00
 1fe001e0-1fe001e7 : serial
 e6200000-f61fffff : Crash kernel
 fa190000-fe0bffff : System RAM
   fa190000-fa1bffff : Reserved
 fe4e0000-47fffffff : System RAM
   43c000000-441ffffff : Reserved
   47ff98000-47ffa3fff : Reserved
   47ffa4000-47ffa7fff : Reserved
   47ffa8000-47ffabfff : Reserved
   47ffac000-47ffaffff : Reserved
   47ffb0000-47ffb3fff : Reserved

3, With 'crashkernel' parameter, after this patch:

 100d0100-100d01ff : LOON0001:00
   100d0100-100d01ff : LOON0001:00 LOON0001:00
 100e0000-100e0bff : LOON0002:00
   100e0000-100e0bff : LOON0002:00 LOON0002:00
 1fe001e0-1fe001e7 : serial
 90400000-fa17ffff : System RAM
   e6200000-f61fffff : Crash kernel
   f6220000-f622ffff : Reserved
   f9ee0000-f9ee3fff : Reserved
   fa120000-fa17ffff : Reserved
 fa190000-fe0bffff : System RAM
   fa190000-fa1bffff : Reserved
 fe4e0000-47fffffff : System RAM
   43c000000-441ffffff : Reserved
   47ff98000-47ffa3fff : Reserved
   47ffa4000-47ffa7fff : Reserved
   47ffa8000-47ffabfff : Reserved
   47ffac000-47ffaffff : Reserved
   47ffb0000-47ffb3fff : Reserved

Link: https://lkml.kernel.org/r/20231229080213.2622204-1-chenhuacai@loongson.cn
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Fixes: 0ab97169aa05 ("crash_core: add generic function to do reservation")
Cc: Baoquan He <bhe@redhat.com>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Cc: <stable@vger.kernel.org>	[6.6+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/crash_core.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index d483156677526..4e2cac71b84f1 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -376,7 +376,6 @@ static int __init reserve_crashkernel_low(unsigned long long low_size)
 
 	crashk_low_res.start = low_base;
 	crashk_low_res.end   = low_base + low_size - 1;
-	insert_resource(&iomem_resource, &crashk_low_res);
 #endif
 	return 0;
 }
@@ -458,8 +457,19 @@ retry:
 
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
-	insert_resource(&iomem_resource, &crashk_res);
 }
+
+static __init int insert_crashkernel_resources(void)
+{
+	if (crashk_res.start < crashk_res.end)
+		insert_resource(&iomem_resource, &crashk_res);
+
+	if (crashk_low_res.start < crashk_low_res.end)
+		insert_resource(&iomem_resource, &crashk_low_res);
+
+	return 0;
+}
+early_initcall(insert_crashkernel_resources);
 #endif
 
 int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
-- 
GitLab


From 65cc86800cf27d8e2da3439c834aef96d93fef63 Mon Sep 17 00:00:00 2001
From: Petr Vorel <pvorel@suse.cz>
Date: Thu, 4 Jan 2024 16:49:53 +0100
Subject: [PATCH 2628/4076] MAINTAINERS: update LTP maintainers

There are more people with git push permissions, but we keep only people
who actually did review and merge patches last year.

Link: https://lkml.kernel.org/r/20240104154953.1193634-1-pvorel@suse.cz
Signed-off-by: Petr Vorel <pvorel@suse.cz>
Reviewed-by: Li Wang <liwang@redhat.com>
Cc: Alexey Kodanev <aleksei.kodanev@bell-sw.com>
Cc: Jan Stancek <jstancek@redhat.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Wanlong Gao <wanlong.gao@gmail.com>
Cc: Yang Xu <xuyang2018.jy@fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 40c754b4c39c5..621751a8b8c77 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12627,12 +12627,11 @@ F:	Documentation/devicetree/bindings/i2c/i2c-mux-ltc4306.txt
 F:	drivers/i2c/muxes/i2c-mux-ltc4306.c
 
 LTP (Linux Test Project)
-M:	Mike Frysinger <vapier@gentoo.org>
 M:	Cyril Hrubis <chrubis@suse.cz>
-M:	Wanlong Gao <wanlong.gao@gmail.com>
 M:	Jan Stancek <jstancek@redhat.com>
-M:	Stanislav Kholmanskikh <stanislav.kholmanskikh@oracle.com>
-M:	Alexey Kodanev <alexey.kodanev@oracle.com>
+M:	Petr Vorel <pvorel@suse.cz>
+M:	Li Wang <liwang@redhat.com>
+M:	Yang Xu <xuyang2018.jy@fujitsu.com>
 L:	ltp@lists.linux.it (subscribers-only)
 S:	Maintained
 W:	http://linux-test-project.github.io/
-- 
GitLab


From aaa2c9a97c22af5bf011f6dd8e0538219b45af88 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 5 Jan 2024 12:13:04 -0700
Subject: [PATCH 2629/4076] lib/Kconfig.debug: disable CONFIG_DEBUG_INFO_BTF
 for Hexagon

pahole, which generates BTF, relies on elfutils to process DWARF debug
info.  Because kernel modules are relocatable files, elfutils needs to
resolve relocations when processing the DWARF .debug sections.

Hexagon is not supported in binutils or elfutils, so elfutils is unable to
process relocations in kernel modules, causing pahole to crash during BTF
generation.

Do not allow CONFIG_DEBUG_INFO_BTF to be selected for Hexagon until it is
supported in elfutils, so that there are no more cryptic build failures
during BTF generation.

Link: https://lkml.kernel.org/r/20240105-hexagon-disable-btf-v1-1-ddab073e7f74@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312192107.wMIKiZWw-lkp@intel.com/
Suggested-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Brian Cain <bcain@quicinc.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/Kconfig.debug | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 97ce28f4d1540..ba25129563ad7 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -378,6 +378,8 @@ config DEBUG_INFO_BTF
 	depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST
 	depends on BPF_SYSCALL
 	depends on !DEBUG_INFO_DWARF5 || PAHOLE_VERSION >= 121
+	# pahole uses elfutils, which does not have support for Hexagon relocations
+	depends on !HEXAGON
 	help
 	  Generate deduplicated BTF type information from DWARF debug info.
 	  Turning this on expects presence of pahole tool, which will convert
-- 
GitLab


From cc478e0b6bdffd20561e1a07941a65f6c8962cab Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@gmail.com>
Date: Tue, 9 Jan 2024 23:12:34 +0100
Subject: [PATCH 2630/4076] kasan: avoid resetting aux_lock

With commit 63b85ac56a64 ("kasan: stop leaking stack trace handles"),
KASAN zeroes out alloc meta when an object is freed.  The zeroed out data
purposefully includes alloc and auxiliary stack traces but also
accidentally includes aux_lock.

As aux_lock is only initialized for each object slot during slab creation,
when the freed slot is reallocated, saving auxiliary stack traces for the
new object leads to lockdep reports when taking the zeroed out aux_lock.

Arguably, we could reinitialize aux_lock when the object is reallocated,
but a simpler solution is to avoid zeroing out aux_lock when an object
gets freed.

Link: https://lkml.kernel.org/r/20240109221234.90929-1-andrey.konovalov@linux.dev
Fixes: 63b85ac56a64 ("kasan: stop leaking stack trace handles")
Signed-off-by: Andrey Konovalov <andreyknvl@gmail.com>
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Closes: https://lore.kernel.org/linux-next/5cc0f83c-e1d6-45c5-be89-9b86746fe731@paulmck-laptop/
Reviewed-by: Marco Elver <elver@google.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kasan/generic.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 24c13dfb1e947..df6627f62402c 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -487,6 +487,7 @@ void kasan_init_object_meta(struct kmem_cache *cache, const void *object)
 		__memset(alloc_meta, 0, sizeof(*alloc_meta));
 
 		/*
+		 * Prepare the lock for saving auxiliary stack traces.
 		 * Temporarily disable KASAN bug reporting to allow instrumented
 		 * raw_spin_lock_init to access aux_lock, which resides inside
 		 * of a redzone.
@@ -510,8 +511,13 @@ static void release_alloc_meta(struct kasan_alloc_meta *meta)
 	stack_depot_put(meta->aux_stack[0]);
 	stack_depot_put(meta->aux_stack[1]);
 
-	/* Zero out alloc meta to mark it as invalid. */
-	__memset(meta, 0, sizeof(*meta));
+	/*
+	 * Zero out alloc meta to mark it as invalid but keep aux_lock
+	 * initialized to avoid having to reinitialize it when another object
+	 * is allocated in the same slot.
+	 */
+	__memset(&meta->alloc_track, 0, sizeof(meta->alloc_track));
+	__memset(meta->aux_stack, 0, sizeof(meta->aux_stack));
 }
 
 static void release_free_meta(const void *object, struct kasan_free_meta *meta)
-- 
GitLab


From efbd6398353315b7018e6943e41fee9ec35e875f Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Fri, 29 Sep 2023 03:48:17 +0000
Subject: [PATCH 2631/4076] scripts/decode_stacktrace.sh: optionally use LLVM
 utilities

GNU's addr2line can have problems parsing a vmlinux built with LLVM,
particularly when LTO was used.  In order to decode the traces correctly
this patch adds the ability to switch to LLVM's utilities readelf and
addr2line.  The same approach is followed by Will in [1].

Before:
  $ scripts/decode_stacktrace.sh vmlinux < kernel.log
  [17716.240635] Call trace:
  [17716.240646] skb_cow_data (??:?)
  [17716.240654] esp6_input (ld-temp.o:?)
  [17716.240666] xfrm_input (ld-temp.o:?)
  [17716.240674] xfrm6_rcv (??:?)
  [...]

After:
  $ LLVM=1 scripts/decode_stacktrace.sh vmlinux < kernel.log
  [17716.240635] Call trace:
  [17716.240646] skb_cow_data (include/linux/skbuff.h:2172 net/core/skbuff.c:4503)
  [17716.240654] esp6_input (net/ipv6/esp6.c:977)
  [17716.240666] xfrm_input (net/xfrm/xfrm_input.c:659)
  [17716.240674] xfrm6_rcv (net/ipv6/xfrm6_input.c:172)
  [...]

Note that one could set CROSS_COMPILE=llvm- instead to hack around this
issue.  However, doing so can break the decodecode routine as it will
force the selection of other LLVM utilities down the line e.g.  llvm-as.

[1] https://lore.kernel.org/all/20230914131225.13415-3-will@kernel.org/

Link: https://lkml.kernel.org/r/20230929034836.403735-1-cmllamas@google.com
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Elliot Berman <quic_eberman@quicinc.com>
Tested-by: Justin Stitt <justinstitt@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: John Stultz <jstultz@google.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Tom Rix <trix@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/decode_stacktrace.sh | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index cb980b144ca14..fa5be6f57b009 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -16,6 +16,21 @@ elif type c++filt >/dev/null 2>&1 ; then
 	cppfilt_opts=-i
 fi
 
+UTIL_SUFFIX=
+if [[ -z ${LLVM:-} ]]; then
+	UTIL_PREFIX=${CROSS_COMPILE:-}
+else
+	UTIL_PREFIX=llvm-
+	if [[ ${LLVM} == */ ]]; then
+		UTIL_PREFIX=${LLVM}${UTIL_PREFIX}
+	elif [[ ${LLVM} == -* ]]; then
+		UTIL_SUFFIX=${LLVM}
+	fi
+fi
+
+READELF=${UTIL_PREFIX}readelf${UTIL_SUFFIX}
+ADDR2LINE=${UTIL_PREFIX}addr2line${UTIL_SUFFIX}
+
 if [[ $1 == "-r" ]] ; then
 	vmlinux=""
 	basepath="auto"
@@ -75,7 +90,7 @@ find_module() {
 
 	if [[ "$modpath" != "" ]] ; then
 		for fn in $(find "$modpath" -name "${module//_/[-_]}.ko*") ; do
-			if readelf -WS "$fn" | grep -qwF .debug_line ; then
+			if ${READELF} -WS "$fn" | grep -qwF .debug_line ; then
 				echo $fn
 				return
 			fi
@@ -169,7 +184,7 @@ parse_symbol() {
 	if [[ $aarray_support == true && "${cache[$module,$address]+isset}" == "isset" ]]; then
 		local code=${cache[$module,$address]}
 	else
-		local code=$(${CROSS_COMPILE}addr2line -i -e "$objfile" "$address" 2>/dev/null)
+		local code=$(${ADDR2LINE} -i -e "$objfile" "$address" 2>/dev/null)
 		if [[ $aarray_support == true ]]; then
 			cache[$module,$address]=$code
 		fi
-- 
GitLab


From ea52f71598f3d0cfaaf53b7d837bee9919041351 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Tue, 9 Jan 2024 14:02:00 -0500
Subject: [PATCH 2632/4076] mm: zswap: switch maintainers to recently active
 developers and reviewers

Yosry, Nhat and I have been doing most of the recent development and
reviewing of changes in this space.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Seth Jennings <sjenning@redhat.com>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 621751a8b8c77..5affd7ca3217a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24141,11 +24141,13 @@ N:	zstd
 K:	zstd
 
 ZSWAP COMPRESSED SWAP CACHING
-M:	Seth Jennings <sjenning@redhat.com>
-M:	Dan Streetman <ddstreet@ieee.org>
-M:	Vitaly Wool <vitaly.wool@konsulko.com>
+M:	Johannes Weiner <hannes@cmpxchg.org>
+M:	Yosry Ahmed <yosryahmed@google.com>
+M:	Nhat Pham <nphamcs@gmail.com>
 L:	linux-mm@kvack.org
 S:	Maintained
+F:	Documentation/admin-guide/mm/zswap.rst
+F:	include/linux/zswap.h
 F:	mm/zswap.c
 
 THE REST
-- 
GitLab


From 4cccb6221cae6d020270606b9e52b1678fc8b71a Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@collabora.com>
Date: Tue, 9 Jan 2024 16:24:42 +0500
Subject: [PATCH 2633/4076] fs/proc/task_mmu: move mmu notification mechanism
 inside mm lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move mmu notification mechanism inside mm lock to prevent race condition
in other components which depend on it.  The notifier will invalidate
memory range.  Depending upon the number of iterations, different memory
ranges would be invalidated.

The following warning would be removed by this patch:
WARNING: CPU: 0 PID: 5067 at arch/x86/kvm/../../../virt/kvm/kvm_main.c:734 kvm_mmu_notifier_change_pte+0x860/0x960 arch/x86/kvm/../../../virt/kvm/kvm_main.c:734

There is no behavioural and performance change with this patch when
there is no component registered with the mmu notifier.

[akpm@linux-foundation.org: narrow the scope of `range', per Sean]
Link: https://lkml.kernel.org/r/20240109112445.590736-1-usama.anjum@collabora.com
Fixes: 52526ca7fdb9 ("fs/proc/task_mmu: implement IOCTL to get and optionally clear info about PTEs")
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Reported-by: syzbot+81227d2bd69e9dedb802@syzkaller.appspotmail.com
Link: https://lore.kernel.org/all/000000000000f6d051060c6785bc@google.com/
Reviewed-by: Sean Christopherson <seanjc@google.com>
Cc: Andrei Vagin <avagin@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/task_mmu.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 62b16f42d5d25..3f78ebbb795fe 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -2432,7 +2432,6 @@ static long pagemap_scan_flush_buffer(struct pagemap_scan_private *p)
 
 static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
 {
-	struct mmu_notifier_range range;
 	struct pagemap_scan_private p = {0};
 	unsigned long walk_start;
 	size_t n_ranges_out = 0;
@@ -2448,15 +2447,9 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
 	if (ret)
 		return ret;
 
-	/* Protection change for the range is going to happen. */
-	if (p.arg.flags & PM_SCAN_WP_MATCHING) {
-		mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0,
-					mm, p.arg.start, p.arg.end);
-		mmu_notifier_invalidate_range_start(&range);
-	}
-
 	for (walk_start = p.arg.start; walk_start < p.arg.end;
 			walk_start = p.arg.walk_end) {
+		struct mmu_notifier_range range;
 		long n_out;
 
 		if (fatal_signal_pending(current)) {
@@ -2467,8 +2460,20 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
 		ret = mmap_read_lock_killable(mm);
 		if (ret)
 			break;
+
+		/* Protection change for the range is going to happen. */
+		if (p.arg.flags & PM_SCAN_WP_MATCHING) {
+			mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0,
+						mm, walk_start, p.arg.end);
+			mmu_notifier_invalidate_range_start(&range);
+		}
+
 		ret = walk_page_range(mm, walk_start, p.arg.end,
 				      &pagemap_scan_ops, &p);
+
+		if (p.arg.flags & PM_SCAN_WP_MATCHING)
+			mmu_notifier_invalidate_range_end(&range);
+
 		mmap_read_unlock(mm);
 
 		n_out = pagemap_scan_flush_buffer(&p);
@@ -2494,9 +2499,6 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
 	if (pagemap_scan_writeback_args(&p.arg, uarg))
 		ret = -EFAULT;
 
-	if (p.arg.flags & PM_SCAN_WP_MATCHING)
-		mmu_notifier_invalidate_range_end(&range);
-
 	kfree(p.vec_buf);
 	return ret;
 }
-- 
GitLab


From 327b4603c0b2469c2ef5f15b510d0e42d8e209de Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 9 Jan 2024 15:44:31 +0530
Subject: [PATCH 2634/4076] mailmap: update entry for Manivannan Sadhasivam

Remove the map for Linaro id as it is still in use and I want to use it
for submitting patches.  Otherwise, git uses kernel.org as the author id
for patches created using Linaro id.

Link: https://lkml.kernel.org/r/20240109-update-mailmap-v1-1-bf7a39f15fb7@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 1 -
 1 file changed, 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index 03587c4330979..23dbb22cfd7a4 100644
--- a/.mailmap
+++ b/.mailmap
@@ -363,7 +363,6 @@ Maheshwar Ajja <quic_majja@quicinc.com> <majja@codeaurora.org>
 Malathi Gottam <quic_mgottam@quicinc.com> <mgottam@codeaurora.org>
 Manikanta Pubbisetty <quic_mpubbise@quicinc.com> <mpubbise@codeaurora.org>
 Manivannan Sadhasivam <mani@kernel.org> <manivannanece23@gmail.com>
-Manivannan Sadhasivam <mani@kernel.org> <manivannan.sadhasivam@linaro.org>
 Manoj Basapathi <quic_manojbm@quicinc.com> <manojbm@codeaurora.org>
 Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
 Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com>
-- 
GitLab


From 7bb943806ff61e83ae4cceef8906b7fe52453e8a Mon Sep 17 00:00:00 2001
From: James Gowans <jgowans@amazon.com>
Date: Wed, 13 Dec 2023 08:40:04 +0200
Subject: [PATCH 2635/4076] kexec: do syscore_shutdown() in kernel_kexec

syscore_shutdown() runs driver and module callbacks to get the system into
a state where it can be correctly shut down.  In commit 6f389a8f1dd2 ("PM
/ reboot: call syscore_shutdown() after disable_nonboot_cpus()")
syscore_shutdown() was removed from kernel_restart_prepare() and hence got
(incorrectly?) removed from the kexec flow.  This was innocuous until
commit 6735150b6997 ("KVM: Use syscore_ops instead of reboot_notifier to
hook restart/shutdown") changed the way that KVM registered its shutdown
callbacks, switching from reboot notifiers to syscore_ops.shutdown.  As
syscore_shutdown() is missing from kexec, KVM's shutdown hook is not run
and virtualisation is left enabled on the boot CPU which results in triple
faults when switching to the new kernel on Intel x86 VT-x with VMXE
enabled.

Fix this by adding syscore_shutdown() to the kexec sequence.  In terms of
where to add it, it is being added after migrating the kexec task to the
boot CPU, but before APs are shut down.  It is not totally clear if this
is the best place: in commit 6f389a8f1dd2 ("PM / reboot: call
syscore_shutdown() after disable_nonboot_cpus()") it is stated that
"syscore_ops operations should be carried with one CPU on-line and
interrupts disabled." APs are only offlined later in machine_shutdown(),
so this syscore_shutdown() is being run while APs are still online.  This
seems to be the correct place as it matches where syscore_shutdown() is
run in the reboot and halt flows - they also run it before APs are shut
down.  The assumption is that the commit message in commit 6f389a8f1dd2
("PM / reboot: call syscore_shutdown() after disable_nonboot_cpus()") is
no longer valid.

KVM has been discussed here as it is what broke loudly by not having
syscore_shutdown() in kexec, but this change impacts more than just KVM;
all drivers/modules which register a syscore_ops.shutdown callback will
now be invoked in the kexec flow.  Looking at some of them like x86 MCE it
is probably more correct to also shut these down during kexec.
Maintainers of all drivers which use syscore_ops.shutdown are added on CC
for visibility.  They are:

arch/powerpc/platforms/cell/spu_base.c  .shutdown = spu_shutdown,
arch/x86/kernel/cpu/mce/core.c	        .shutdown = mce_syscore_shutdown,
arch/x86/kernel/i8259.c                 .shutdown = i8259A_shutdown,
drivers/irqchip/irq-i8259.c	        .shutdown = i8259A_shutdown,
drivers/irqchip/irq-sun6i-r.c	        .shutdown = sun6i_r_intc_shutdown,
drivers/leds/trigger/ledtrig-cpu.c	.shutdown = ledtrig_cpu_syscore_shutdown,
drivers/power/reset/sc27xx-poweroff.c	.shutdown = sc27xx_poweroff_shutdown,
kernel/irq/generic-chip.c	        .shutdown = irq_gc_shutdown,
virt/kvm/kvm_main.c	                .shutdown = kvm_shutdown,

This has been tested by doing a kexec on x86_64 and aarch64.

Link: https://lkml.kernel.org/r/20231213064004.2419447-1-jgowans@amazon.com
Fixes: 6735150b6997 ("KVM: Use syscore_ops instead of reboot_notifier to hook restart/shutdown")
Signed-off-by: James Gowans <jgowans@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: Jernej Skrabec <jernej.skrabec@gmail.com>
Cc: Samuel Holland <samuel@sholland.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Sebastian Reichel <sre@kernel.org>
Cc: Orson Zhai <orsonzhai@gmail.com>
Cc: Alexander Graf <graf@amazon.de>
Cc: Jan H. Schoenherr <jschoenh@amazon.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/kexec_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index a08031b57a61f..d08fc7b5db979 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1257,6 +1257,7 @@ int kernel_kexec(void)
 		kexec_in_progress = true;
 		kernel_restart_prepare("kexec reboot");
 		migrate_to_reboot_cpu();
+		syscore_shutdown();
 
 		/*
 		 * migrate_to_reboot_cpu() disables CPU hotplug assuming that
-- 
GitLab


From 7ea6ec4c25294e8bc8788148ef854df92ee8dc5e Mon Sep 17 00:00:00 2001
From: Ma Wupeng <mawupeng1@huawei.com>
Date: Tue, 9 Jan 2024 12:15:36 +0800
Subject: [PATCH 2636/4076] efi: disable mirror feature during crashkernel

If the system has no mirrored memory or uses crashkernel.high while
kernelcore=mirror is enabled on the command line then during crashkernel,
there will be limited mirrored memory and this usually leads to OOM.

To solve this problem, disable the mirror feature during crashkernel.

Link: https://lkml.kernel.org/r/20240109041536.3903042-1-mawupeng1@huawei.com
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/mm_init.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index 89dc29f1e6c6f..2c19f5515e36c 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -26,6 +26,7 @@
 #include <linux/pgtable.h>
 #include <linux/swap.h>
 #include <linux/cma.h>
+#include <linux/crash_dump.h>
 #include "internal.h"
 #include "slab.h"
 #include "shuffle.h"
@@ -381,6 +382,11 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 			goto out;
 		}
 
+		if (is_kdump_kernel()) {
+			pr_warn("The system is under kdump, ignore kernelcore=mirror.\n");
+			goto out;
+		}
+
 		for_each_mem_region(r) {
 			if (memblock_is_mirror(r))
 				continue;
-- 
GitLab


From 4e87ff59cebb53d3ce1333245e64ab7d51ebf118 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Tue, 9 Jan 2024 21:35:21 -0800
Subject: [PATCH 2637/4076] kernel/crash_core.c: make __crash_hotplug_lock
 static

sparse warnings:
kernel/crash_core.c:749:1: sparse: sparse: symbol '__crash_hotplug_lock' was not declared. Should it be static?

Fixes: e2a8f20dd8e9 ("Crash: add lock to serialize crash hotplug handling")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401080654.IjjU5oK7-lkp@intel.com/
Cc: Baoquan He <bhe@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/crash_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 4e2cac71b84f1..75cd6a736d030 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -877,7 +877,7 @@ subsys_initcall(crash_notes_memory_init);
  * regions are online. So mutex lock  __crash_hotplug_lock is used to
  * serialize the crash hotplug handling specifically.
  */
-DEFINE_MUTEX(__crash_hotplug_lock);
+static DEFINE_MUTEX(__crash_hotplug_lock);
 #define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock)
 #define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock)
 
-- 
GitLab


From 0b8f128da761c54c5b210fad581ef597d38e7f81 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 5 Jan 2024 22:30:44 -0800
Subject: [PATCH 2638/4076] mailmap: add old address mappings for Randy

Add my old email addresses so that git send-email will map them
to my current email address.

Link: https://lkml.kernel.org/r/20240106063051.13623-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/.mailmap b/.mailmap
index 23dbb22cfd7a4..3d2ca49c116a8 100644
--- a/.mailmap
+++ b/.mailmap
@@ -503,6 +503,9 @@ Ralf Baechle <ralf@linux-mips.org>
 Ralf Wildenhues <Ralf.Wildenhues@gmx.de>
 Ram Chandra Jangir <quic_rjangir@quicinc.com> <rjangir@codeaurora.org>
 Randy Dunlap <rdunlap@infradead.org> <rdunlap@xenotime.net>
+Randy Dunlap <rdunlap@infradead.org> <randy.dunlap@oracle.com>
+Randy Dunlap <rdunlap@infradead.org> <rddunlap@osdl.org>
+Randy Dunlap <rdunlap@infradead.org> <randy.dunlap@intel.com>
 Ravi Kumar Bokka <quic_rbokka@quicinc.com> <rbokka@codeaurora.org>
 Ravi Kumar Siddojigari <quic_rsiddoji@quicinc.com> <rsiddoji@codeaurora.org>
 Rémi Denis-Courmont <rdenis@simphalempin.com>
-- 
GitLab


From 55f958c55c2f381c4c9e121c0a5098b222bca75f Mon Sep 17 00:00:00 2001
From: Tanzir Hasan <tanzhasanwork@gmail.com>
Date: Fri, 5 Jan 2024 23:44:34 +0000
Subject: [PATCH 2639/4076] mailmap: switch email for Tanzir Hasan

Access to the tanzirh@google.com email will be revoked upon the end of the
internship.

Link: https://lkml.kernel.org/r/20240105-newemail-v3-1-3dc8ae035b54@google.com
Signed-off-by: Tanzir Hasan <tanzirh@google.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index 3d2ca49c116a8..aecdb52916808 100644
--- a/.mailmap
+++ b/.mailmap
@@ -584,6 +584,7 @@ Surabhi Vishnoi <quic_svishnoi@quicinc.com> <svishnoi@codeaurora.org>
 Takashi YOSHII <takashi.yoshii.zj@renesas.com>
 Tamizh Chelvam Raja <quic_tamizhr@quicinc.com> <tamizhr@codeaurora.org>
 Taniya Das <quic_tdas@quicinc.com> <tdas@codeaurora.org>
+Tanzir Hasan <tanzhasanwork@gmail.com> <tanzirh@google.com>
 Tejun Heo <htejun@gmail.com>
 Tomeu Vizoso <tomeu@tomeuvizoso.net> <tomeu.vizoso@collabora.com>
 Thomas Graf <tgraf@suug.ch>
-- 
GitLab


From 11684134140bb708b6e6de969a060535630b1b53 Mon Sep 17 00:00:00 2001
From: Sumanth Korikkar <sumanthk@linux.ibm.com>
Date: Wed, 10 Jan 2024 15:01:27 +0100
Subject: [PATCH 2640/4076] mm/memory_hotplug: fix memmap_on_memory sysfs value
 retrieval

set_memmap_mode() stores the kernel parameter memmap mode as an integer.
However, the get_memmap_mode() function utilizes param_get_bool() to fetch
the value as a boolean, leading to potential endianness issue.  On
Big-endian architectures, the memmap_on_memory is consistently displayed
as 'N' regardless of its actual status.

To address this endianness problem, the solution involves obtaining the
mode as an integer.  This adjustment ensures the proper display of the
memmap_on_memory parameter, presenting it as one of the following options:
Force, Y, or N.

Link: https://lkml.kernel.org/r/20240110140127.241451-1-sumanthk@linux.ibm.com
Fixes: 2d1f649c7c08 ("mm/memory_hotplug: support memmap_on_memory when memmap is not aligned to pageblocks")
Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Suggested-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: <stable@vger.kernel.org>	[6.6+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory_hotplug.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b3c0ff52bb72e..21890994c1d3c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -101,9 +101,11 @@ static int set_memmap_mode(const char *val, const struct kernel_param *kp)
 
 static int get_memmap_mode(char *buffer, const struct kernel_param *kp)
 {
-	if (*((int *)kp->arg) == MEMMAP_ON_MEMORY_FORCE)
-		return sprintf(buffer,  "force\n");
-	return param_get_bool(buffer, kp);
+	int mode = *((int *)kp->arg);
+
+	if (mode == MEMMAP_ON_MEMORY_FORCE)
+		return sprintf(buffer, "force\n");
+	return sprintf(buffer, "%c\n", mode ? 'Y' : 'N');
 }
 
 static const struct kernel_param_ops memmap_mode_ops = {
-- 
GitLab


From 00bcfcd47a52f50f07a2e88d730d7931384cb073 Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.vnet.ibm.com>
Date: Wed, 10 Jan 2024 14:03:35 +0530
Subject: [PATCH 2641/4076] selftests: mm: hugepage-vmemmap fails on 64K page
 size systems

The kernel sefltest mm/hugepage-vmemmap fails on architectures which has
different page size other than 4K.  In hugepage-vmemmap page size used is
4k so the pfn calculation will go wrong on systems which has different
page size .The length of MAP_HUGETLB memory must be hugepage aligned but
in hugepage-vmemmap map length is 2M so this will not get aligned if the
system has differnet hugepage size.

Added  psize() to get the page size and default_huge_page_size() to
get the default hugepage size at run time, hugepage-vmemmap test pass
on powerpc with 64K page size and x86 with 4K page size.

Result on powerpc without patch (page size 64K)
*# ./hugepage-vmemmap
Returned address is 0x7effff000000 whose pfn is 0
Head page flags (100000000) is invalid
check_page_flags: Invalid argument
*#

Result on powerpc with patch (page size 64K)
*# ./hugepage-vmemmap
Returned address is 0x7effff000000 whose pfn is 600
*#

Result on x86 with patch (page size 4K)
*# ./hugepage-vmemmap
Returned address is 0x7fc7c2c00000 whose pfn is 1dac00
*#

Link: https://lkml.kernel.org/r/3b3a3ae37ba21218481c482a872bbf7526031600.1704865754.git.donettom@linux.vnet.ibm.com
Fixes: b147c89cd429 ("selftests: vm: add a hugetlb test case")
Signed-off-by: Donet Tom <donettom@linux.vnet.ibm.com>
Reported-by: Geetika Moolchandani <geetika@linux.ibm.com>
Tested-by: Geetika Moolchandani <geetika@linux.ibm.com>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/hugepage-vmemmap.c | 29 ++++++++++++-------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/mm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c
index 5b354c209e936..894d28c3dd478 100644
--- a/tools/testing/selftests/mm/hugepage-vmemmap.c
+++ b/tools/testing/selftests/mm/hugepage-vmemmap.c
@@ -10,10 +10,7 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <fcntl.h>
-
-#define MAP_LENGTH		(2UL * 1024 * 1024)
-
-#define PAGE_SIZE		4096
+#include "vm_util.h"
 
 #define PAGE_COMPOUND_HEAD	(1UL << 15)
 #define PAGE_COMPOUND_TAIL	(1UL << 16)
@@ -39,6 +36,9 @@
 #define MAP_FLAGS		(MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
 #endif
 
+static size_t pagesize;
+static size_t maplength;
+
 static void write_bytes(char *addr, size_t length)
 {
 	unsigned long i;
@@ -56,7 +56,7 @@ static unsigned long virt_to_pfn(void *addr)
 	if (fd < 0)
 		return -1UL;
 
-	lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET);
+	lseek(fd, (unsigned long)addr / pagesize * sizeof(pagemap), SEEK_SET);
 	read(fd, &pagemap, sizeof(pagemap));
 	close(fd);
 
@@ -86,7 +86,7 @@ static int check_page_flags(unsigned long pfn)
 	 * this also verifies kernel has correctly set the fake page_head to tail
 	 * while hugetlb_free_vmemmap is enabled.
 	 */
-	for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) {
+	for (i = 1; i < maplength / pagesize; i++) {
 		read(fd, &pageflags, sizeof(pageflags));
 		if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS ||
 		    (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) {
@@ -106,18 +106,25 @@ int main(int argc, char **argv)
 	void *addr;
 	unsigned long pfn;
 
-	addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0);
+	pagesize  = psize();
+	maplength = default_huge_page_size();
+	if (!maplength) {
+		printf("Unable to determine huge page size\n");
+		exit(1);
+	}
+
+	addr = mmap(MAP_ADDR, maplength, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0);
 	if (addr == MAP_FAILED) {
 		perror("mmap");
 		exit(1);
 	}
 
 	/* Trigger allocation of HugeTLB page. */
-	write_bytes(addr, MAP_LENGTH);
+	write_bytes(addr, maplength);
 
 	pfn = virt_to_pfn(addr);
 	if (pfn == -1UL) {
-		munmap(addr, MAP_LENGTH);
+		munmap(addr, maplength);
 		perror("virt_to_pfn");
 		exit(1);
 	}
@@ -125,13 +132,13 @@ int main(int argc, char **argv)
 	printf("Returned address is %p whose pfn is %lx\n", addr, pfn);
 
 	if (check_page_flags(pfn) < 0) {
-		munmap(addr, MAP_LENGTH);
+		munmap(addr, maplength);
 		perror("check_page_flags");
 		exit(1);
 	}
 
 	/* munmap() length of MAP_HUGETLB memory must be hugepage aligned */
-	if (munmap(addr, MAP_LENGTH)) {
+	if (munmap(addr, maplength)) {
 		perror("munmap");
 		exit(1);
 	}
-- 
GitLab


From aa8f91910bf5fb11dcd176e6efac2dbe2cecebea Mon Sep 17 00:00:00 2001
From: Qi Zheng <zhengqi.arch@bytedance.com>
Date: Thu, 11 Jan 2024 15:52:19 +0800
Subject: [PATCH 2642/4076] MAINTAINERS: add entry for shrinker

Since the shrinker-related code has been moved to a separate shrinker.c
file, it's time to add a MAINTAINERS entry for it.

Dave, Roman, Muchun and I have all worked on shrinker (development,
review, etc) in the past period of time, and all of us are willing to
continue working on shrinker in the future, so I'd like to add all of us
as maintainer/reviewer.

Link: https://lkml.kernel.org/r/20240111075219.34221-1-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 5affd7ca3217a..a1b31c4c29697 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19635,6 +19635,19 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/i2c/rj54n1cb0c.c
 F:	include/media/i2c/rj54n1cb0c.h
 
+SHRINKER
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Dave Chinner <david@fromorbit.com>
+R:	Qi Zheng <zhengqi.arch@bytedance.com>
+R:	Roman Gushchin <roman.gushchin@linux.dev>
+R:	Muchun Song <muchun.song@linux.dev>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	Documentation/admin-guide/mm/shrinker_debugfs.rst
+F:	include/linux/shrinker.h
+F:	mm/shrinker.c
+F:	mm/shrinker_debug.c
+
 SH_VOU V4L2 OUTPUT DRIVER
 L:	linux-media@vger.kernel.org
 S:	Orphan
-- 
GitLab


From 5d4747a6cc8e78ce74742d557fc9b7697fcacc95 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Thu, 11 Jan 2024 17:39:35 -0800
Subject: [PATCH 2643/4076] userfaultfd: avoid huge_zero_page in UFFDIO_MOVE

While testing UFFDIO_MOVE ioctl, syzbot triggered VM_BUG_ON_PAGE caused by
a call to PageAnonExclusive() with a huge_zero_page as a parameter.
UFFDIO_MOVE does not yet handle zeropages and returns EBUSY when one is
encountered.  Add an early huge_zero_page check in the PMD move path to
avoid this situation.

Link: https://lkml.kernel.org/r/20240112013935.1474648-1-surenb@google.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Reported-by: syzbot+705209281e36404998f6@syzkaller.appspotmail.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 216ab4c8621f6..20e3b0d9cf7ed 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1393,6 +1393,12 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
 				err = -ENOENT;
 				break;
 			}
+			/* Avoid moving zeropages for now */
+			if (is_huge_zero_pmd(*src_pmd)) {
+				spin_unlock(ptl);
+				err = -EBUSY;
+				break;
+			}
 
 			/* Check if we can move the pmd without splitting it. */
 			if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) ||
-- 
GitLab


From cbdd50ec8b1daef6d71fb3325e436c8dec2d2e15 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 11 Jan 2024 19:24:29 +0300
Subject: [PATCH 2644/4076] net: liquidio: fix clang-specific W=1 build
 warnings

When compiling with clang-18 and W=1, I've noticed the following
warnings:

drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c:1493:16: warning: cast
from 'void (*)(struct octeon_device *, struct octeon_mbox_cmd *, void *)' to
'octeon_mbox_callback_t' (aka 'void (*)(void *, void *, void *)') converts to
incompatible function type [-Wcast-function-type-strict]
 1493 |         mbox_cmd.fn = (octeon_mbox_callback_t)cn23xx_get_vf_stats_callback;
      |                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

and:

drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c:432:16: warning: cast
from 'void (*)(struct octeon_device *, struct octeon_mbox_cmd *, void *)' to
'octeon_mbox_callback_t' (aka 'void (*)(void *, void *, void *)') converts to
incompatible function type [-Wcast-function-type-strict]
  432 |         mbox_cmd.fn = (octeon_mbox_callback_t)octeon_pfvf_hs_callback;
      |                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Fix both of the above by adjusting 'octeon_mbox_callback_t' to match actual
callback definitions (at the cost of adding an extra forward declaration).

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240111162432.124014-1-dmantipov@yandex.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c | 2 +-
 drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c | 2 +-
 drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h   | 5 ++++-
 3 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 068ed52b66c94..b3c81a2e9d464 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -1490,7 +1490,7 @@ int cn23xx_get_vf_stats(struct octeon_device *oct, int vfidx,
 	mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf;
 	mbox_cmd.recv_len = 0;
 	mbox_cmd.recv_status = 0;
-	mbox_cmd.fn = (octeon_mbox_callback_t)cn23xx_get_vf_stats_callback;
+	mbox_cmd.fn = cn23xx_get_vf_stats_callback;
 	ctx.stats = stats;
 	atomic_set(&ctx.status, 0);
 	mbox_cmd.fn_arg = (void *)&ctx;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
index dd5d80fee24f0..d2fcb3da484e3 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
@@ -429,7 +429,7 @@ int cn23xx_octeon_pfvf_handshake(struct octeon_device *oct)
 	mbox_cmd.q_no = 0;
 	mbox_cmd.recv_len = 0;
 	mbox_cmd.recv_status = 0;
-	mbox_cmd.fn = (octeon_mbox_callback_t)octeon_pfvf_hs_callback;
+	mbox_cmd.fn = octeon_pfvf_hs_callback;
 	mbox_cmd.fn_arg = &status;
 
 	octeon_mbox_write(oct, &mbox_cmd);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h
index d92bd7e164775..9ac85d22c6157 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h
@@ -57,7 +57,10 @@ union octeon_mbox_message {
 	} s;
 };
 
-typedef void (*octeon_mbox_callback_t)(void *, void *, void *);
+struct octeon_mbox_cmd;
+
+typedef void (*octeon_mbox_callback_t)(struct octeon_device *,
+				       struct octeon_mbox_cmd *, void *);
 
 struct octeon_mbox_cmd {
 	union octeon_mbox_message msg;
-- 
GitLab


From 89e23277f9c16df6f9f9c1a1a07f8f132339c15c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 Jan 2024 19:49:13 +0000
Subject: [PATCH 2645/4076] mptcp: mptcp_parse_option() fix for
 MPTCPOPT_MP_JOIN

mptcp_parse_option() currently sets OPTIONS_MPTCP_MPJ, for the three
possible cases handled for MPTCPOPT_MP_JOIN option.

OPTIONS_MPTCP_MPJ is the combination of three flags:
- OPTION_MPTCP_MPJ_SYN
- OPTION_MPTCP_MPJ_SYNACK
- OPTION_MPTCP_MPJ_ACK

This is a problem, because backup, join_id, token, nonce and/or hmac fields
could be left uninitialized in some cases.

Distinguish the three cases, as following patches will need this step.

Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Peter Krystad <peter.krystad@linux.intel.com>
Cc: Matthieu Baerts <matttbe@kernel.org>
Cc: Mat Martineau <martineau@kernel.org>
Cc: Geliang Tang <geliang.tang@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20240111194917.4044654-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/options.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c53914012d01d..d2527d189a799 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -123,8 +123,8 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_MP_JOIN:
-		mp_opt->suboptions |= OPTIONS_MPTCP_MPJ;
 		if (opsize == TCPOLEN_MPTCP_MPJ_SYN) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN;
 			mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
 			mp_opt->join_id = *ptr++;
 			mp_opt->token = get_unaligned_be32(ptr);
@@ -135,6 +135,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 				 mp_opt->backup, mp_opt->join_id,
 				 mp_opt->token, mp_opt->nonce);
 		} else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYNACK;
 			mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
 			mp_opt->join_id = *ptr++;
 			mp_opt->thmac = get_unaligned_be64(ptr);
@@ -145,11 +146,10 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 				 mp_opt->backup, mp_opt->join_id,
 				 mp_opt->thmac, mp_opt->nonce);
 		} else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK;
 			ptr += 2;
 			memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
 			pr_debug("MP_JOIN hmac");
-		} else {
-			mp_opt->suboptions &= ~OPTIONS_MPTCP_MPJ;
 		}
 		break;
 
-- 
GitLab


From c1665273bdc7c201766c65e561c06711f2e050dc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 Jan 2024 19:49:14 +0000
Subject: [PATCH 2646/4076] mptcp: strict validation before using mp_opt->hmac

mp_opt->hmac contains uninitialized data unless OPTION_MPTCP_MPJ_ACK
was set in mptcp_parse_option().

We must refine the condition before we call subflow_hmac_valid().

Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Peter Krystad <peter.krystad@linux.intel.com>
Cc: Matthieu Baerts <matttbe@kernel.org>
Cc: Mat Martineau <martineau@kernel.org>
Cc: Geliang Tang <geliang.tang@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20240111194917.4044654-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/subflow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 3eacd04e7099e..bb05477006a6e 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -788,7 +788,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 	} else if (subflow_req->mp_join) {
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) ||
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) ||
 		    !subflow_hmac_valid(req, &mp_opt) ||
 		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
-- 
GitLab


From be1d9d9d38da922bd4beeec5b6dd821ff5a1dfeb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 Jan 2024 19:49:15 +0000
Subject: [PATCH 2647/4076] mptcp: use OPTION_MPTCP_MPJ_SYNACK in
 subflow_finish_connect()

subflow_finish_connect() uses four fields (backup, join_id, thmac, none)
that may contain garbage unless OPTION_MPTCP_MPJ_SYNACK has been set
in mptcp_parse_option()

Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Peter Krystad <peter.krystad@linux.intel.com>
Cc: Matthieu Baerts <matttbe@kernel.org>
Cc: Mat Martineau <martineau@kernel.org>
Cc: Geliang Tang <geliang.tang@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20240111194917.4044654-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/subflow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index bb05477006a6e..103ff5471993a 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -506,7 +506,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) {
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYNACK)) {
 			subflow->reset_reason = MPTCP_RST_EMPTCP;
 			goto do_reset;
 		}
-- 
GitLab


From 66ff70df1a919a066942844bb095d6fcb748d78d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 Jan 2024 19:49:16 +0000
Subject: [PATCH 2648/4076] mptcp: use OPTION_MPTCP_MPJ_SYN in
 subflow_check_req()

syzbot reported that subflow_check_req() was using uninitialized data in
subflow_check_req() [1]

This is because mp_opt.token is only set when OPTION_MPTCP_MPJ_SYN is also set.

While we are are it, fix mptcp_subflow_init_cookie_req()
to test for OPTION_MPTCP_MPJ_ACK.

[1]

BUG: KMSAN: uninit-value in subflow_token_join_request net/mptcp/subflow.c:91 [inline]
 BUG: KMSAN: uninit-value in subflow_check_req+0x1028/0x15d0 net/mptcp/subflow.c:209
  subflow_token_join_request net/mptcp/subflow.c:91 [inline]
  subflow_check_req+0x1028/0x15d0 net/mptcp/subflow.c:209
  subflow_v6_route_req+0x269/0x410 net/mptcp/subflow.c:367
  tcp_conn_request+0x153a/0x4240 net/ipv4/tcp_input.c:7164
 subflow_v6_conn_request+0x3ee/0x510
  tcp_rcv_state_process+0x2e1/0x4ac0 net/ipv4/tcp_input.c:6659
  tcp_v6_do_rcv+0x11bf/0x1fe0 net/ipv6/tcp_ipv6.c:1669
  tcp_v6_rcv+0x480b/0x4fb0 net/ipv6/tcp_ipv6.c:1900
  ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438
  ip6_input_finish net/ipv6/ip6_input.c:483 [inline]
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492
  dst_input include/net/dst.h:461 [inline]
  ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310
  __netif_receive_skb_one_core net/core/dev.c:5532 [inline]
  __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5646
  netif_receive_skb_internal net/core/dev.c:5732 [inline]
  netif_receive_skb+0x58/0x660 net/core/dev.c:5791
  tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1555
  tun_get_user+0x53af/0x66d0 drivers/net/tun.c:2002
  tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048
  call_write_iter include/linux/fs.h:2020 [inline]
  new_sync_write fs/read_write.c:491 [inline]
  vfs_write+0x8ef/0x1490 fs/read_write.c:584
  ksys_write+0x20f/0x4c0 fs/read_write.c:637
  __do_sys_write fs/read_write.c:649 [inline]
  __se_sys_write fs/read_write.c:646 [inline]
  __x64_sys_write+0x93/0xd0 fs/read_write.c:646
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Local variable mp_opt created at:
  subflow_check_req+0x6d/0x15d0 net/mptcp/subflow.c:145
  subflow_v6_route_req+0x269/0x410 net/mptcp/subflow.c:367

CPU: 1 PID: 5924 Comm: syz-executor.3 Not tainted 6.7.0-rc8-syzkaller-00055-g5eff55d725a4 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023

Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Peter Krystad <peter.krystad@linux.intel.com>
Cc: Matthieu Baerts <matttbe@kernel.org>
Cc: Mat Martineau <martineau@kernel.org>
Cc: Geliang Tang <geliang.tang@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20240111194917.4044654-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/subflow.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 103ff5471993a..13039ac8d1ab6 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -158,7 +158,7 @@ static int subflow_check_req(struct request_sock *req,
 	mptcp_get_options(skb, &mp_opt);
 
 	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
-	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
+	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN);
 	if (opt_mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
@@ -255,7 +255,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 	mptcp_get_options(skb, &mp_opt);
 
 	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
-	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
+	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK);
 	if (opt_mp_capable && opt_mp_join)
 		return -EINVAL;
 
-- 
GitLab


From 724b00c12957973656d312dce2a110c75ae2c680 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 Jan 2024 19:49:17 +0000
Subject: [PATCH 2649/4076] mptcp: refine opt_mp_capable determination

OPTIONS_MPTCP_MPC is a combination of three flags.

It would be better to be strict about testing what
flag is expected, at least for code readability.

mptcp_parse_option() already makes the distinction.

- subflow_check_req() should use OPTION_MPTCP_MPC_SYN.

- mptcp_subflow_init_cookie_req() should use OPTION_MPTCP_MPC_ACK.

- subflow_finish_connect() should use OPTION_MPTCP_MPC_SYNACK

- subflow_syn_recv_sock should use OPTION_MPTCP_MPC_ACK

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Fixes: 74c7dfbee3e1 ("mptcp: consolidate in_opt sub-options fields in a bitmask")
Link: https://lore.kernel.org/r/20240111194917.4044654-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/subflow.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 13039ac8d1ab6..1117d1e84274a 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -157,7 +157,7 @@ static int subflow_check_req(struct request_sock *req,
 
 	mptcp_get_options(skb, &mp_opt);
 
-	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
+	opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYN);
 	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN);
 	if (opt_mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
@@ -254,7 +254,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 	subflow_init_req(req, sk_listener);
 	mptcp_get_options(skb, &mp_opt);
 
-	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
+	opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK);
 	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK);
 	if (opt_mp_capable && opt_mp_join)
 		return -EINVAL;
@@ -486,7 +486,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 	mptcp_get_options(skb, &mp_opt);
 	if (subflow->request_mptcp) {
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) {
 			MPTCP_INC_STATS(sock_net(sk),
 					MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
 			mptcp_do_fallback(sk);
@@ -783,7 +783,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * options.
 		 */
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC))
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK))
 			fallback = true;
 
 	} else if (subflow_req->mp_join) {
-- 
GitLab


From c919330dd57835970b37676d377de3eaaea2c1e9 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 12 Jan 2024 16:57:47 -0800
Subject: [PATCH 2650/4076] f2fs: fix double free of f2fs_sb_info

kill_f2fs_super() is called even if f2fs_fill_super() fails.
f2fs_fill_super() frees the struct f2fs_sb_info, so it must set
sb->s_fs_info to NULL to prevent it from being freed again.

Fixes: 275dca4630c1 ("f2fs: move release of block devices to after kill_block_super()")
Reported-by:  <syzbot+8f477ac014ff5b32d81f@syzkaller.appspotmail.com>
Closes: https://lore.kernel.org/lkml/0000000000006cb174060ec34502@google.com
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/linux-f2fs-devel/20240113005747.38887-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/f2fs/super.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index d00d21a8b53ad..d45ab0992ae59 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -4880,6 +4880,7 @@ free_sbi:
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi);
+	sb->s_fs_info = NULL;
 
 	/* give only one another chance */
 	if (retry_cnt > 0 && skip_recovery) {
-- 
GitLab


From 7b4f36cd22a65b750b4cb6ac14804fb7d6e6c67d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 12 Jan 2024 09:12:20 -0700
Subject: [PATCH 2651/4076] block: ensure we hold a queue reference when using
 queue limits

q_usage_counter is the only thing preventing us from the limits changing
under us in __bio_split_to_limits, but blk_mq_submit_bio doesn't hold
it while calling into it.

Move the splitting inside the region where we know we've got a queue
reference. Ideally this could still remain a shared section of code, but
let's keep the fix simple and defer any refactoring here to later.

Reported-by: Christoph Hellwig <hch@lst.de>
Fixes: 900e08075202 ("block: move queue enter logic into blk_mq_submit_bio()")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index f57b86d6de6ac..e02c4b1af8c55 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2964,12 +2964,6 @@ void blk_mq_submit_bio(struct bio *bio)
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	if (bio_may_exceed_limits(bio, &q->limits)) {
-		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-		if (!bio)
-			return;
-	}
-
 	bio_set_ioprio(bio);
 
 	if (plug) {
@@ -2978,6 +2972,11 @@ void blk_mq_submit_bio(struct bio *bio)
 			rq = NULL;
 	}
 	if (rq) {
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				return;
+		}
 		if (!bio_integrity_prep(bio))
 			return;
 		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
@@ -2988,6 +2987,11 @@ void blk_mq_submit_bio(struct bio *bio)
 	} else {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				goto fail;
+		}
 		if (!bio_integrity_prep(bio))
 			goto fail;
 	}
-- 
GitLab


From ba5afb9a84df2e6b26a1b6389b98849cd16ea757 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Fri, 12 Jan 2024 09:09:14 +0100
Subject: [PATCH 2652/4076] fs: rework listmount() implementation

Linus pointed out that there's error handling and naming issues in the
that we should rewrite:

* Perform the access checks for the buffer before actually doing any
  work instead of doing it during the iteration.
* Rename the arguments to listmount() and do_listmount() to clarify what
  the arguments are used for.
* Get rid of the pointless ctr variable and overflow checking.
* Get rid of the pointless speculation check.

Link: https://lore.kernel.org/r/CAHk-=wjh6Cypo8WC-McXgSzCaou3UXccxB+7PVeSuGR8AjCphg@mail.gmail.com
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c           | 50 ++++++++++++++++++++++------------------
 include/linux/syscalls.h |  2 +-
 2 files changed, 29 insertions(+), 23 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index ef1fd6829814c..437f60e96d405 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5042,13 +5042,12 @@ static struct mount *listmnt_next(struct mount *curr)
 	return node_to_mount(rb_next(&curr->mnt_node));
 }
 
-static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
-			    u64 __user *buf, size_t bufsize,
-			    const struct path *root)
+static ssize_t do_listmount(struct mount *first, struct path *orig,
+			    u64 mnt_parent_id, u64 __user *mnt_ids,
+			    size_t nr_mnt_ids, const struct path *root)
 {
 	struct mount *r;
-	ssize_t ctr;
-	int err;
+	ssize_t ret;
 
 	/*
 	 * Don't trigger audit denials. We just want to determine what
@@ -5058,50 +5057,57 @@ static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
 	    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	err = security_sb_statfs(orig->dentry);
-	if (err)
-		return err;
+	ret = security_sb_statfs(orig->dentry);
+	if (ret)
+		return ret;
 
-	for (ctr = 0, r = first; r && ctr < bufsize; r = listmnt_next(r)) {
-		if (r->mnt_id_unique == mnt_id)
+	for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r)) {
+		if (r->mnt_id_unique == mnt_parent_id)
 			continue;
 		if (!is_path_reachable(r, r->mnt.mnt_root, orig))
 			continue;
-		ctr = array_index_nospec(ctr, bufsize);
-		if (put_user(r->mnt_id_unique, buf + ctr))
+		if (put_user(r->mnt_id_unique, mnt_ids))
 			return -EFAULT;
-		if (check_add_overflow(ctr, 1, &ctr))
-			return -ERANGE;
+		mnt_ids++;
+		nr_mnt_ids--;
+		ret++;
 	}
-	return ctr;
+	return ret;
 }
 
-SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
-		u64 __user *, buf, size_t, bufsize, unsigned int, flags)
+SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *,
+		mnt_ids, size_t, nr_mnt_ids, unsigned int, flags)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
 	struct mnt_id_req kreq;
 	struct mount *first;
 	struct path root, orig;
-	u64 mnt_id, last_mnt_id;
+	u64 mnt_parent_id, last_mnt_id;
+	const size_t maxcount = (size_t)-1 >> 3;
 	ssize_t ret;
 
 	if (flags)
 		return -EINVAL;
 
+	if (unlikely(nr_mnt_ids > maxcount))
+		return -EFAULT;
+
+	if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids)))
+		return -EFAULT;
+
 	ret = copy_mnt_id_req(req, &kreq);
 	if (ret)
 		return ret;
-	mnt_id = kreq.mnt_id;
+	mnt_parent_id = kreq.mnt_id;
 	last_mnt_id = kreq.param;
 
 	down_read(&namespace_sem);
 	get_fs_root(current->fs, &root);
-	if (mnt_id == LSMT_ROOT) {
+	if (mnt_parent_id == LSMT_ROOT) {
 		orig = root;
 	} else {
 		ret = -ENOENT;
-		orig.mnt  = lookup_mnt_in_ns(mnt_id, ns);
+		orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns);
 		if (!orig.mnt)
 			goto err;
 		orig.dentry = orig.mnt->mnt_root;
@@ -5111,7 +5117,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 	else
 		first = mnt_find_id_at(ns, last_mnt_id + 1);
 
-	ret = do_listmount(first, &orig, mnt_id, buf, bufsize, &root);
+	ret = do_listmount(first, &orig, mnt_parent_id, mnt_ids, nr_mnt_ids, &root);
 err:
 	path_put(&root);
 	up_read(&namespace_sem);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5c0dbef55792f..cdba4d0c6d4a8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -414,7 +414,7 @@ asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
 			      struct statmount __user *buf, size_t bufsize,
 			      unsigned int flags);
 asmlinkage long sys_listmount(const struct mnt_id_req __user *req,
-			      u64 __user *buf, size_t bufsize,
+			      u64 __user *mnt_ids, size_t nr_mnt_ids,
 			      unsigned int flags);
 asmlinkage long sys_truncate(const char __user *path, long length);
 asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
-- 
GitLab


From 08300adac3b8dab9e2fd3be0155c7d3093c755f4 Mon Sep 17 00:00:00 2001
From: Sneh Shah <quic_snehshah@quicinc.com>
Date: Tue, 9 Jan 2024 20:17:29 +0530
Subject: [PATCH 2653/4076] net: stmmac: Fix ethool link settings ops for
 integrated PCS

Currently get/set_link_ksettings ethtool ops are dependent on PCS.
When PCS is integrated, it will not have separate link config.
Bypass configuring and checking PCS for integrated PCS.

Fixes: aa571b6275fb ("net: stmmac: add new switch to struct plat_stmmacenet_data")
Tested-by: Andrew Halaney <ahalaney@redhat.com> # sa8775p-ride
Signed-off-by: Sneh Shah <quic_snehshah@quicinc.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index dd05437b51f91..0f8bfba4443d1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -321,8 +321,9 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
-	    priv->hw->pcs & STMMAC_PCS_SGMII) {
+	if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) &&
+	    (priv->hw->pcs & STMMAC_PCS_RGMII ||
+	     priv->hw->pcs & STMMAC_PCS_SGMII)) {
 		struct rgmii_adv adv;
 		u32 supported, advertising, lp_advertising;
 
@@ -407,8 +408,9 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
-	    priv->hw->pcs & STMMAC_PCS_SGMII) {
+	if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) &&
+	    (priv->hw->pcs & STMMAC_PCS_RGMII ||
+	     priv->hw->pcs & STMMAC_PCS_SGMII)) {
 		/* Only support ANE */
 		if (cmd->base.autoneg != AUTONEG_ENABLE)
 			return -EINVAL;
-- 
GitLab


From 482521d8e0c6520429478aa6866cd44128b33d5d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 12 Jan 2024 10:44:27 +0000
Subject: [PATCH 2654/4076] udp: annotate data-races around up->pending

up->pending can be read without holding the socket lock,
as pointed out by syzbot [1]

Add READ_ONCE() in lockless contexts, and WRITE_ONCE()
on write side.

[1]
BUG: KCSAN: data-race in udpv6_sendmsg / udpv6_sendmsg

write to 0xffff88814e5eadf0 of 4 bytes by task 15547 on cpu 1:
 udpv6_sendmsg+0x1405/0x1530 net/ipv6/udp.c:1596
 inet6_sendmsg+0x63/0x80 net/ipv6/af_inet6.c:657
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 __sys_sendto+0x257/0x310 net/socket.c:2192
 __do_sys_sendto net/socket.c:2204 [inline]
 __se_sys_sendto net/socket.c:2200 [inline]
 __x64_sys_sendto+0x78/0x90 net/socket.c:2200
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

read to 0xffff88814e5eadf0 of 4 bytes by task 15551 on cpu 0:
 udpv6_sendmsg+0x22c/0x1530 net/ipv6/udp.c:1373
 inet6_sendmsg+0x63/0x80 net/ipv6/af_inet6.c:657
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x37c/0x4d0 net/socket.c:2586
 ___sys_sendmsg net/socket.c:2640 [inline]
 __sys_sendmmsg+0x269/0x500 net/socket.c:2726
 __do_sys_sendmmsg net/socket.c:2755 [inline]
 __se_sys_sendmmsg net/socket.c:2752 [inline]
 __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2752
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

value changed: 0x00000000 -> 0x0000000a

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 15551 Comm: syz-executor.1 Tainted: G        W          6.7.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+8d482d0e407f665d9d10@syzkaller.appspotmail.com
Link: https://lore.kernel.org/netdev/0000000000009e46c3060ebcdffd@google.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 12 ++++++------
 net/ipv6/udp.c | 16 ++++++++--------
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 89e5a806b82e9..5f742d0b9e079 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -805,7 +805,7 @@ void udp_flush_pending_frames(struct sock *sk)
 
 	if (up->pending) {
 		up->len = 0;
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 		ip_flush_pending_frames(sk);
 	}
 }
@@ -993,7 +993,7 @@ int udp_push_pending_frames(struct sock *sk)
 
 out:
 	up->len = 0;
-	up->pending = 0;
+	WRITE_ONCE(up->pending, 0);
 	return err;
 }
 EXPORT_SYMBOL(udp_push_pending_frames);
@@ -1070,7 +1070,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
 
 	fl4 = &inet->cork.fl.u.ip4;
-	if (up->pending) {
+	if (READ_ONCE(up->pending)) {
 		/*
 		 * There are pending frames.
 		 * The socket lock must be held while it's corked.
@@ -1269,7 +1269,7 @@ back_from_confirm:
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
 	fl4->fl4_sport = inet->inet_sport;
-	up->pending = AF_INET;
+	WRITE_ONCE(up->pending, AF_INET);
 
 do_append_data:
 	up->len += ulen;
@@ -1281,7 +1281,7 @@ do_append_data:
 	else if (!corkreq)
 		err = udp_push_pending_frames(sk);
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 	release_sock(sk);
 
 out:
@@ -1319,7 +1319,7 @@ void udp_splice_eof(struct socket *sock)
 	struct sock *sk = sock->sk;
 	struct udp_sock *up = udp_sk(sk);
 
-	if (!up->pending || udp_test_bit(CORK, sk))
+	if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk))
 		return;
 
 	lock_sock(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 594e3f23c1290..3f2249b4cd5f6 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1135,7 +1135,7 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
 		udp_flush_pending_frames(sk);
 	else if (up->pending) {
 		up->len = 0;
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 		ip6_flush_pending_frames(sk);
 	}
 }
@@ -1313,7 +1313,7 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 			      &inet_sk(sk)->cork.base);
 out:
 	up->len = 0;
-	up->pending = 0;
+	WRITE_ONCE(up->pending, 0);
 	return err;
 }
 
@@ -1370,7 +1370,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		default:
 			return -EINVAL;
 		}
-	} else if (!up->pending) {
+	} else if (!READ_ONCE(up->pending)) {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 		daddr = &sk->sk_v6_daddr;
@@ -1401,8 +1401,8 @@ do_udp_sendmsg:
 		return -EMSGSIZE;
 
 	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
-	if (up->pending) {
-		if (up->pending == AF_INET)
+	if (READ_ONCE(up->pending)) {
+		if (READ_ONCE(up->pending) == AF_INET)
 			return udp_sendmsg(sk, msg, len);
 		/*
 		 * There are pending frames.
@@ -1593,7 +1593,7 @@ back_from_confirm:
 		goto out;
 	}
 
-	up->pending = AF_INET6;
+	WRITE_ONCE(up->pending, AF_INET6);
 
 do_append_data:
 	if (ipc6.dontfrag < 0)
@@ -1607,7 +1607,7 @@ do_append_data:
 	else if (!corkreq)
 		err = udp_v6_push_pending_frames(sk);
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 
 	if (err > 0)
 		err = inet6_test_bit(RECVERR6, sk) ? net_xmit_errno(err) : 0;
@@ -1648,7 +1648,7 @@ static void udpv6_splice_eof(struct socket *sock)
 	struct sock *sk = sock->sk;
 	struct udp_sock *up = udp_sk(sk);
 
-	if (!up->pending || udp_test_bit(CORK, sk))
+	if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk))
 		return;
 
 	lock_sock(sk);
-- 
GitLab


From e18405d0be8001fa4c5f9e61471f6ffd59c7a1b3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 12 Jan 2024 12:39:30 +0100
Subject: [PATCH 2655/4076] net: sched: track device in tcf_block_get/put_ext()
 only for clsact binder types

Clsact/ingress qdisc is not the only one using shared block,
red is also using it. The device tracking was originally introduced
by commit 913b47d3424e ("net/sched: Introduce tc block netdev
tracking infra") for clsact/ingress only. Commit 94e2557d086a ("net:
sched: move block device tracking into tcf_block_get/put_ext()")
mistakenly enabled that for red as well.

Fix that by adding a check for the binder type being clsact when adding
device to the block->ports xarray.

Reported-by: Ido Schimmel <idosch@idosch.org>
Closes: https://lore.kernel.org/all/ZZ6JE0odnu1lLPtu@shredder/
Fixes: 94e2557d086a ("net: sched: move block device tracking into tcf_block_get/put_ext()")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Tested-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e3236a3169c32..92a12e3d0fe63 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1424,6 +1424,14 @@ static void tcf_block_owner_del(struct tcf_block *block,
 	WARN_ON(1);
 }
 
+static bool tcf_block_tracks_dev(struct tcf_block *block,
+				 struct tcf_block_ext_info *ei)
+{
+	return tcf_block_shared(block) &&
+	       (ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS ||
+		ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS);
+}
+
 int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 		      struct tcf_block_ext_info *ei,
 		      struct netlink_ext_ack *extack)
@@ -1462,7 +1470,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 	if (err)
 		goto err_block_offload_bind;
 
-	if (tcf_block_shared(block)) {
+	if (tcf_block_tracks_dev(block, ei)) {
 		err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL);
 		if (err) {
 			NL_SET_ERR_MSG(extack, "block dev insert failed");
@@ -1516,7 +1524,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
 	if (!block)
 		return;
-	if (tcf_block_shared(block))
+	if (tcf_block_tracks_dev(block, ei))
 		xa_erase(&block->ports, dev->ifindex);
 	tcf_chain0_head_change_cb_del(block, ei);
 	tcf_block_owner_del(block, q, ei->binder_type);
-- 
GitLab


From 118a8cf504d7dfa519562d000f423ee3ca75d2c4 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Sat, 13 Jan 2024 23:06:02 +0800
Subject: [PATCH 2656/4076] erofs: fix inconsistent per-file compression format

EROFS can select compression algorithms on a per-file basis, and each
per-file compression algorithm needs to be marked in the on-disk
superblock for initialization.

However, syzkaller can generate inconsistent crafted images that use
an unsupported algorithmtype for specific inodes, e.g. use MicroLZMA
algorithmtype even it's not set in `sbi->available_compr_algs`.  This
can lead to an unexpected "BUG: kernel NULL pointer dereference" if
the corresponding decompressor isn't built-in.

Fix this by checking against `sbi->available_compr_algs` for each
m_algorithmformat request.  Incorrect !erofs_sb_has_compr_cfgs preset
bitmap is now fixed together since it was harmless previously.

Reported-by: <bugreport@ubisectech.com>
Fixes: 8f89926290c4 ("erofs: get compression algorithms directly on mapping")
Fixes: 622ceaddb764 ("erofs: lzma compression support")
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Link: https://lore.kernel.org/r/20240113150602.1471050-1-hsiangkao@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/decompressor.c |  2 +-
 fs/erofs/zmap.c         | 23 +++++++++++++----------
 2 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 021be5feb1bcf..af98e88908eea 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -398,7 +398,7 @@ int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb)
 	int size, ret = 0;
 
 	if (!erofs_sb_has_compr_cfgs(sbi)) {
-		sbi->available_compr_algs = Z_EROFS_COMPRESSION_LZ4;
+		sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4;
 		return z_erofs_load_lz4_config(sb, dsb, NULL, 0);
 	}
 
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 7b55111fd5337..7a1a24ae4a2d8 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -458,7 +458,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 		.map = map,
 	};
 	int err = 0;
-	unsigned int lclusterbits, endoff;
+	unsigned int lclusterbits, endoff, afmt;
 	unsigned long initial_lcn;
 	unsigned long long ofs, end;
 
@@ -547,17 +547,20 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 			err = -EFSCORRUPTED;
 			goto unmap_out;
 		}
-		if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER)
-			map->m_algorithmformat =
-				Z_EROFS_COMPRESSION_INTERLACED;
-		else
-			map->m_algorithmformat =
-				Z_EROFS_COMPRESSION_SHIFTED;
-	} else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) {
-		map->m_algorithmformat = vi->z_algorithmtype[1];
+		afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ?
+			Z_EROFS_COMPRESSION_INTERLACED :
+			Z_EROFS_COMPRESSION_SHIFTED;
 	} else {
-		map->m_algorithmformat = vi->z_algorithmtype[0];
+		afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ?
+			vi->z_algorithmtype[1] : vi->z_algorithmtype[0];
+		if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) {
+			erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu",
+				  afmt, vi->nid);
+			err = -EFSCORRUPTED;
+			goto unmap_out;
+		}
 	}
+	map->m_algorithmformat = afmt;
 
 	if ((flags & EROFS_GET_BLOCKS_FIEMAP) ||
 	    ((flags & EROFS_GET_BLOCKS_READMORE) &&
-- 
GitLab


From 9181d6f8a2bb32d158de66a84164fac05e3ddd18 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 12 Jan 2024 12:28:16 +0000
Subject: [PATCH 2657/4076] net: add more sanity check in
 virtio_net_hdr_to_skb()

syzbot/KMSAN reports access to uninitialized data from gso_features_check() [1]

The repro use af_packet, injecting a gso packet and hdrlen == 0.

We could fix the issue making gso_features_check() more careful
while dealing with NETIF_F_TSO_MANGLEID in fast path.

Or we can make sure virtio_net_hdr_to_skb() pulls minimal network and
transport headers as intended.

Note that for GSO packets coming from untrusted sources, SKB_GSO_DODGY
bit forces a proper header validation (and pull) before the packet can
hit any device ndo_start_xmit(), thus we do not need a precise disection
at virtio_net_hdr_to_skb() stage.

[1]
BUG: KMSAN: uninit-value in skb_gso_segment include/net/gso.h:83 [inline]
BUG: KMSAN: uninit-value in validate_xmit_skb+0x10f2/0x1930 net/core/dev.c:3629
 skb_gso_segment include/net/gso.h:83 [inline]
 validate_xmit_skb+0x10f2/0x1930 net/core/dev.c:3629
 __dev_queue_xmit+0x1eac/0x5130 net/core/dev.c:4341
 dev_queue_xmit include/linux/netdevice.h:3134 [inline]
 packet_xmit+0x9c/0x6b0 net/packet/af_packet.c:276
 packet_snd net/packet/af_packet.c:3087 [inline]
 packet_sendmsg+0x8b1d/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x9c2/0xd60 net/socket.c:2584
 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
 __sys_sendmsg net/socket.c:2667 [inline]
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x307/0x490 net/socket.c:2674
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Uninit was created at:
 slab_post_alloc_hook+0x129/0xa70 mm/slab.h:768
 slab_alloc_node mm/slub.c:3478 [inline]
 kmem_cache_alloc_node+0x5e9/0xb10 mm/slub.c:3523
 kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:560
 __alloc_skb+0x318/0x740 net/core/skbuff.c:651
 alloc_skb include/linux/skbuff.h:1286 [inline]
 alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6334
 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2780
 packet_alloc_skb net/packet/af_packet.c:2936 [inline]
 packet_snd net/packet/af_packet.c:3030 [inline]
 packet_sendmsg+0x70e8/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x9c2/0xd60 net/socket.c:2584
 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
 __sys_sendmsg net/socket.c:2667 [inline]
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x307/0x490 net/socket.c:2674
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

CPU: 0 PID: 5025 Comm: syz-executor279 Not tainted 6.7.0-rc7-syzkaller-00003-gfbafc3e621c3 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023

Reported-by: syzbot+7f4d0ea3df4d4fa9a65f@syzkaller.appspotmail.com
Link: https://lore.kernel.org/netdev/0000000000005abd7b060eb160cd@google.com/
Fixes: 9274124f023b ("net: stricter validation of untrusted gso packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 27cc1d4643219..4dfa9b69ca8d9 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <linux/udp.h>
 #include <uapi/linux/tcp.h>
 #include <uapi/linux/virtio_net.h>
@@ -49,6 +51,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					const struct virtio_net_hdr *hdr,
 					bool little_endian)
 {
+	unsigned int nh_min_len = sizeof(struct iphdr);
 	unsigned int gso_type = 0;
 	unsigned int thlen = 0;
 	unsigned int p_off = 0;
@@ -65,6 +68,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			gso_type = SKB_GSO_TCPV6;
 			ip_proto = IPPROTO_TCP;
 			thlen = sizeof(struct tcphdr);
+			nh_min_len = sizeof(struct ipv6hdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
@@ -100,7 +104,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
-		p_off = skb_transport_offset(skb) + thlen;
+		nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb));
+		p_off = nh_min_len + thlen;
 		if (!pskb_may_pull(skb, p_off))
 			return -EINVAL;
 	} else {
@@ -140,7 +145,7 @@ retry:
 
 			skb_set_transport_header(skb, keys.control.thoff);
 		} else if (gso_type) {
-			p_off = thlen;
+			p_off = nh_min_len + thlen;
 			if (!pskb_may_pull(skb, p_off))
 				return -EINVAL;
 		}
-- 
GitLab


From 894d7508316e7ad722df597d68b4b1797a9eee11 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 12 Jan 2024 17:13:14 +0100
Subject: [PATCH 2658/4076] net: netdev_queue: netdev_txq_completed_mb(): fix
 wake condition

netif_txq_try_stop() uses "get_desc >= start_thrs" as the check for
the call to netif_tx_start_queue().

Use ">=" i netdev_txq_completed_mb(), too.

Fixes: c91c46de6bbc ("net: provide macros for commonly copied lockless queue stop/wake code")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netdev_queues.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index d68b0a4834315..8b8ed4e13d74d 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -128,7 +128,7 @@ netdev_txq_completed_mb(struct netdev_queue *dev_queue,
 		netdev_txq_completed_mb(txq, pkts, bytes);		\
 									\
 		_res = -1;						\
-		if (pkts && likely(get_desc > start_thrs)) {		\
+		if (pkts && likely(get_desc >= start_thrs)) {		\
 			_res = 1;					\
 			if (unlikely(netif_tx_queue_stopped(txq)) &&	\
 			    !(down_cond)) {				\
-- 
GitLab


From 19ca0823f6eaad01d18f664a00550abe912c034c Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Fri, 12 Jan 2024 11:05:28 -0800
Subject: [PATCH 2659/4076] bpf: iter_udp: Retry with a larger batch size
 without going back to the previous bucket

The current logic is to use a default size 16 to batch the whole bucket.
If it is too small, it will retry with a larger batch size.

The current code accidentally does a state->bucket-- before retrying.
This goes back to retry with the previous bucket which has already
been done. This patch fixed it.

It is hard to create a selftest. I added a WARN_ON(state->bucket < 0),
forced a particular port to be hashed to the first bucket,
created >16 sockets, and observed the for-loop went back
to the "-1" bucket.

Cc: Aditi Ghag <aditi.ghag@isovalent.com>
Fixes: c96dac8d369f ("bpf: udp: Implement batching for sockets iterator")
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Aditi Ghag <aditi.ghag@isovalent.com>
Link: https://lore.kernel.org/r/20240112190530.3751661-2-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/ipv4/udp.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5f742d0b9e079..79050d83e7366 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -3213,7 +3213,6 @@ again:
 		/* After allocating a larger batch, retry one more time to grab
 		 * the whole bucket.
 		 */
-		state->bucket--;
 		goto again;
 	}
 done:
-- 
GitLab


From 2242fd537fab52d5f4d2fbb1845f047c01fad0cf Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Fri, 12 Jan 2024 11:05:29 -0800
Subject: [PATCH 2660/4076] bpf: Avoid iter->offset making backward progress in
 bpf_iter_udp

There is a bug in the bpf_iter_udp_batch() function that stops
the userspace from making forward progress.

The case that triggers the bug is the userspace passed in
a very small read buffer. When the bpf prog does bpf_seq_printf,
the userspace read buffer is not enough to capture the whole bucket.

When the read buffer is not large enough, the kernel will remember
the offset of the bucket in iter->offset such that the next userspace
read() can continue from where it left off.

The kernel will skip the number (== "iter->offset") of sockets in
the next read(). However, the code directly decrements the
"--iter->offset". This is incorrect because the next read() may
not consume the whole bucket either and then the next-next read()
will start from offset 0. The net effect is the userspace will
keep reading from the beginning of a bucket and the process will
never finish. "iter->offset" must always go forward until the
whole bucket is consumed.

This patch fixes it by using a local variable "resume_offset"
and "resume_bucket". "iter->offset" is always reset to 0 before
it may be used. "iter->offset" will be advanced to the
"resume_offset" when it continues from the "resume_bucket" (i.e.
"state->bucket == resume_bucket"). This brings it closer to
the bpf_iter_tcp's offset handling which does not suffer
the same bug.

Cc: Aditi Ghag <aditi.ghag@isovalent.com>
Fixes: c96dac8d369f ("bpf: udp: Implement batching for sockets iterator")
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Aditi Ghag <aditi.ghag@isovalent.com>
Link: https://lore.kernel.org/r/20240112190530.3751661-3-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/ipv4/udp.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 79050d83e7366..148ffb007969f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -3137,16 +3137,18 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 	struct bpf_udp_iter_state *iter = seq->private;
 	struct udp_iter_state *state = &iter->state;
 	struct net *net = seq_file_net(seq);
+	int resume_bucket, resume_offset;
 	struct udp_table *udptable;
 	unsigned int batch_sks = 0;
 	bool resized = false;
 	struct sock *sk;
 
+	resume_bucket = state->bucket;
+	resume_offset = iter->offset;
+
 	/* The current batch is done, so advance the bucket. */
-	if (iter->st_bucket_done) {
+	if (iter->st_bucket_done)
 		state->bucket++;
-		iter->offset = 0;
-	}
 
 	udptable = udp_get_table_seq(seq, net);
 
@@ -3166,19 +3168,19 @@ again:
 	for (; state->bucket <= udptable->mask; state->bucket++) {
 		struct udp_hslot *hslot2 = &udptable->hash2[state->bucket];
 
-		if (hlist_empty(&hslot2->head)) {
-			iter->offset = 0;
+		if (hlist_empty(&hslot2->head))
 			continue;
-		}
 
+		iter->offset = 0;
 		spin_lock_bh(&hslot2->lock);
 		udp_portaddr_for_each_entry(sk, &hslot2->head) {
 			if (seq_sk_match(seq, sk)) {
 				/* Resume from the last iterated socket at the
 				 * offset in the bucket before iterator was stopped.
 				 */
-				if (iter->offset) {
-					--iter->offset;
+				if (state->bucket == resume_bucket &&
+				    iter->offset < resume_offset) {
+					++iter->offset;
 					continue;
 				}
 				if (iter->end_sk < iter->max_sk) {
@@ -3192,9 +3194,6 @@ again:
 
 		if (iter->end_sk)
 			break;
-
-		/* Reset the current bucket's offset before moving to the next bucket. */
-		iter->offset = 0;
 	}
 
 	/* All done: no batch made. */
-- 
GitLab


From dbd7db7787ba1743a505a495e479550932836fa4 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Fri, 12 Jan 2024 11:05:30 -0800
Subject: [PATCH 2661/4076] selftests/bpf: Test udp and tcp iter batching

The patch adds a test to exercise the bpf_iter_udp batching
logic. It specifically tests the case that there are multiple
so_reuseport udp_sk in a bucket of the udp_table.

The test creates two sets of so_reuseport sockets and
each set on a different port. Meaning there will be
two buckets in the udp_table.

The test does the following:
1. read() 3 out of 4 sockets in the first bucket.
2. close() all sockets in the first bucket. This
   will ensure the current bucket's offset in
   the kernel does not affect the read() of the
   following bucket.
3. read() all 4 sockets in the second bucket.

The test also reads one udp_sk at a time from
the bpf_iter_udp prog. The true case in
"do_test(..., bool onebyone)". This is the buggy case
that the previous patch fixed.

It also tests the "false" case in "do_test(..., bool onebyone)",
meaning the userspace reads the whole bucket. There is
no bug in this case but adding this test also while
at it.

Considering the way to have multiple tcp_sk in the same
bucket is similar (by using so_reuseport),
this patch also tests the bpf_iter_tcp even though the
bpf_iter_tcp batching logic works correctly.

Both IP v4 and v6 are exercising the same bpf_iter batching
code path, so only v6 is tested.

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20240112190530.3751661-4-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/sock_iter_batch.c          | 135 ++++++++++++++++++
 .../selftests/bpf/progs/bpf_tracing_net.h     |   3 +
 .../selftests/bpf/progs/sock_iter_batch.c     |  91 ++++++++++++
 .../testing/selftests/bpf/progs/test_jhash.h  |  31 ++++
 4 files changed, 260 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
 create mode 100644 tools/testing/selftests/bpf/progs/sock_iter_batch.c

diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
new file mode 100644
index 0000000000000..0c365f36c73b5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Meta
+
+#include <test_progs.h>
+#include "network_helpers.h"
+#include "sock_iter_batch.skel.h"
+
+#define TEST_NS "sock_iter_batch_netns"
+
+static const int nr_soreuse = 4;
+
+static void do_test(int sock_type, bool onebyone)
+{
+	int err, i, nread, to_read, total_read, iter_fd = -1;
+	int first_idx, second_idx, indices[nr_soreuse];
+	struct bpf_link *link = NULL;
+	struct sock_iter_batch *skel;
+	int *fds[2] = {};
+
+	skel = sock_iter_batch__open();
+	if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+		return;
+
+	/* Prepare 2 buckets of sockets in the kernel hashtable */
+	for (i = 0; i < ARRAY_SIZE(fds); i++) {
+		int local_port;
+
+		fds[i] = start_reuseport_server(AF_INET6, sock_type, "::1", 0, 0,
+						nr_soreuse);
+		if (!ASSERT_OK_PTR(fds[i], "start_reuseport_server"))
+			goto done;
+		local_port = get_socket_local_port(*fds[i]);
+		if (!ASSERT_GE(local_port, 0, "get_socket_local_port"))
+			goto done;
+		skel->rodata->ports[i] = ntohs(local_port);
+	}
+
+	err = sock_iter_batch__load(skel);
+	if (!ASSERT_OK(err, "sock_iter_batch__load"))
+		goto done;
+
+	link = bpf_program__attach_iter(sock_type == SOCK_STREAM ?
+					skel->progs.iter_tcp_soreuse :
+					skel->progs.iter_udp_soreuse,
+					NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto done;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create"))
+		goto done;
+
+	/* Test reading a bucket (either from fds[0] or fds[1]).
+	 * Only read "nr_soreuse - 1" number of sockets
+	 * from a bucket and leave one socket out from
+	 * that bucket on purpose.
+	 */
+	to_read = (nr_soreuse - 1) * sizeof(*indices);
+	total_read = 0;
+	first_idx = -1;
+	do {
+		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
+		if (nread <= 0 || nread % sizeof(*indices))
+			break;
+		total_read += nread;
+
+		if (first_idx == -1)
+			first_idx = indices[0];
+		for (i = 0; i < nread / sizeof(*indices); i++)
+			ASSERT_EQ(indices[i], first_idx, "first_idx");
+	} while (total_read < to_read);
+	ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread");
+	ASSERT_EQ(total_read, to_read, "total_read");
+
+	free_fds(fds[first_idx], nr_soreuse);
+	fds[first_idx] = NULL;
+
+	/* Read the "whole" second bucket */
+	to_read = nr_soreuse * sizeof(*indices);
+	total_read = 0;
+	second_idx = !first_idx;
+	do {
+		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
+		if (nread <= 0 || nread % sizeof(*indices))
+			break;
+		total_read += nread;
+
+		for (i = 0; i < nread / sizeof(*indices); i++)
+			ASSERT_EQ(indices[i], second_idx, "second_idx");
+	} while (total_read <= to_read);
+	ASSERT_EQ(nread, 0, "nread");
+	/* Both so_reuseport ports should be in different buckets, so
+	 * total_read must equal to the expected to_read.
+	 *
+	 * For a very unlikely case, both ports collide at the same bucket,
+	 * the bucket offset (i.e. 3) will be skipped and it cannot
+	 * expect the to_read number of bytes.
+	 */
+	if (skel->bss->bucket[0] != skel->bss->bucket[1])
+		ASSERT_EQ(total_read, to_read, "total_read");
+
+done:
+	for (i = 0; i < ARRAY_SIZE(fds); i++)
+		free_fds(fds[i], nr_soreuse);
+	if (iter_fd < 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	sock_iter_batch__destroy(skel);
+}
+
+void test_sock_iter_batch(void)
+{
+	struct nstoken *nstoken = NULL;
+
+	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+	SYS(done, "ip netns add %s", TEST_NS);
+	SYS(done, "ip -net %s link set dev lo up", TEST_NS);
+
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto done;
+
+	if (test__start_subtest("tcp")) {
+		do_test(SOCK_STREAM, true);
+		do_test(SOCK_STREAM, false);
+	}
+	if (test__start_subtest("udp")) {
+		do_test(SOCK_DGRAM, true);
+		do_test(SOCK_DGRAM, false);
+	}
+	close_netns(nstoken);
+
+done:
+	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 1bdc680b0e0e2..e8bd4b7b5ef76 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -72,6 +72,8 @@
 #define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
 #define inet_dport		sk.__sk_common.skc_dport
 
+#define udp_portaddr_hash	inet.sk.__sk_common.skc_u16hashes[1]
+
 #define ir_loc_addr		req.__req_common.skc_rcv_saddr
 #define ir_num			req.__req_common.skc_num
 #define ir_rmt_addr		req.__req_common.skc_daddr
@@ -85,6 +87,7 @@
 #define sk_rmem_alloc		sk_backlog.rmem_alloc
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_state		__sk_common.skc_state
+#define sk_net			__sk_common.skc_net
 #define sk_v6_daddr		__sk_common.skc_v6_daddr
 #define sk_v6_rcv_saddr		__sk_common.skc_v6_rcv_saddr
 #define sk_flags		__sk_common.skc_flags
diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
new file mode 100644
index 0000000000000..ffbbfe1fa1c1e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Meta
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+#include "bpf_kfuncs.h"
+
+#define ATTR __always_inline
+#include "test_jhash.h"
+
+static bool ipv6_addr_loopback(const struct in6_addr *a)
+{
+	return (a->s6_addr32[0] | a->s6_addr32[1] |
+		a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0;
+}
+
+volatile const __u16 ports[2];
+unsigned int bucket[2];
+
+SEC("iter/tcp")
+int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
+{
+	struct sock *sk = (struct sock *)ctx->sk_common;
+	struct inet_hashinfo *hinfo;
+	unsigned int hash;
+	struct net *net;
+	int idx;
+
+	if (!sk)
+		return 0;
+
+	sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock));
+	if (sk->sk_family != AF_INET6 ||
+	    sk->sk_state != TCP_LISTEN ||
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+		return 0;
+
+	if (sk->sk_num == ports[0])
+		idx = 0;
+	else if (sk->sk_num == ports[1])
+		idx = 1;
+	else
+		return 0;
+
+	/* bucket selection as in inet_lhash2_bucket_sk() */
+	net = sk->sk_net.net;
+	hash = jhash2(sk->sk_v6_rcv_saddr.s6_addr32, 4, net->hash_mix);
+	hash ^= sk->sk_num;
+	hinfo = net->ipv4.tcp_death_row.hashinfo;
+	bucket[idx] = hash & hinfo->lhash2_mask;
+	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+
+	return 0;
+}
+
+#define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk)
+
+SEC("iter/udp")
+int iter_udp_soreuse(struct bpf_iter__udp *ctx)
+{
+	struct sock *sk = (struct sock *)ctx->udp_sk;
+	struct udp_table *udptable;
+	int idx;
+
+	if (!sk)
+		return 0;
+
+	sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock));
+	if (sk->sk_family != AF_INET6 ||
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+		return 0;
+
+	if (sk->sk_num == ports[0])
+		idx = 0;
+	else if (sk->sk_num == ports[1])
+		idx = 1;
+	else
+		return 0;
+
+	/* bucket selection as in udp_hashslot2() */
+	udptable = sk->sk_net.net->ipv4.udp_table;
+	bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask;
+	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h
index c300734d26f63..ef53559bbbdf1 100644
--- a/tools/testing/selftests/bpf/progs/test_jhash.h
+++ b/tools/testing/selftests/bpf/progs/test_jhash.h
@@ -69,3 +69,34 @@ u32 jhash(const void *key, u32 length, u32 initval)
 
 	return c;
 }
+
+static __always_inline u32 jhash2(const u32 *k, u32 length, u32 initval)
+{
+	u32 a, b, c;
+
+	/* Set up the internal state */
+	a = b = c = JHASH_INITVAL + (length<<2) + initval;
+
+	/* Handle most of the key */
+	while (length > 3) {
+		a += k[0];
+		b += k[1];
+		c += k[2];
+		__jhash_mix(a, b, c);
+		length -= 3;
+		k += 3;
+	}
+
+	/* Handle the last 3 u32's */
+	switch (length) {
+	case 3: c += k[2];
+	case 2: b += k[1];
+	case 1: a += k[0];
+		__jhash_final(a, b, c);
+		break;
+	case 0:	/* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
-- 
GitLab


From 24583bd204d56d530d98431629d8a8cf021b9339 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 11 Nov 2023 21:49:14 +0100
Subject: [PATCH 2662/4076] dt-bindings: mailbox: qcom,apcs-kpss-global: drop
 duplicated qcom,ipq8074-apcs-apps-global

qcom,ipq8074-apcs-apps-global compatible is listed in two places: with
and without fallback.  Drop the second case to match DTS.

Fixes: 34d8775a0edc ("dt-bindings: mailbox: qcom,apcs-kpss-global: use fallbacks for few variants")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml       | 1 -
 1 file changed, 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
index a38413f8d1321..a22c8640dc0e4 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
+++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
@@ -41,7 +41,6 @@ properties:
           - const: syscon
       - enum:
           - qcom,ipq6018-apcs-apps-global
-          - qcom,ipq8074-apcs-apps-global
           - qcom,msm8996-apcs-hmss-global
           - qcom,msm8998-apcs-hmss-global
           - qcom,qcm2290-apcs-hmss-global
-- 
GitLab


From 1e9cb7e007dc3bfe12c1e1e8e9d4b0edca392fac Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 11 Nov 2023 21:49:15 +0100
Subject: [PATCH 2663/4076] dt-bindings: mailbox: qcom,apcs-kpss-global: use
 fallbacks

Rework the compatibles and group devices which have similar interface
(same from Linux driver point of view) as compatible.  This allows
smaller of_device_id table in the Linux driver and smaller
allOf:if:then: constraints.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../mailbox/qcom,apcs-kpss-global.yaml        | 61 +++++++++++++------
 1 file changed, 43 insertions(+), 18 deletions(-)

diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
index a22c8640dc0e4..79eb523b84364 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
+++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml
@@ -23,6 +23,24 @@ properties:
               - qcom,ipq8074-apcs-apps-global
               - qcom,ipq9574-apcs-apps-global
           - const: qcom,ipq6018-apcs-apps-global
+      - items:
+          - enum:
+              - qcom,qcs404-apcs-apps-global
+          - const: qcom,msm8916-apcs-kpss-global
+          - const: syscon
+      - items:
+          - enum:
+              - qcom,msm8976-apcs-kpss-global
+          - const: qcom,msm8994-apcs-kpss-global
+          - const: syscon
+      - items:
+          - enum:
+              - qcom,msm8998-apcs-hmss-global
+              - qcom,sdm660-apcs-hmss-global
+              - qcom,sm4250-apcs-hmss-global
+              - qcom,sm6115-apcs-hmss-global
+              - qcom,sm6125-apcs-hmss-global
+          - const: qcom,msm8994-apcs-kpss-global
       - items:
           - enum:
               - qcom,sc7180-apss-shared
@@ -34,21 +52,14 @@ properties:
               - qcom,msm8916-apcs-kpss-global
               - qcom,msm8939-apcs-kpss-global
               - qcom,msm8953-apcs-kpss-global
-              - qcom,msm8976-apcs-kpss-global
               - qcom,msm8994-apcs-kpss-global
-              - qcom,qcs404-apcs-apps-global
               - qcom,sdx55-apcs-gcc
           - const: syscon
       - enum:
           - qcom,ipq6018-apcs-apps-global
           - qcom,msm8996-apcs-hmss-global
-          - qcom,msm8998-apcs-hmss-global
           - qcom,qcm2290-apcs-hmss-global
-          - qcom,sdm660-apcs-hmss-global
           - qcom,sdm845-apss-shared
-          - qcom,sm4250-apcs-hmss-global
-          - qcom,sm6115-apcs-hmss-global
-          - qcom,sm6125-apcs-hmss-global
 
   reg:
     maxItems: 1
@@ -79,20 +90,38 @@ allOf:
   - if:
       properties:
         compatible:
-          enum:
-            - qcom,msm8916-apcs-kpss-global
-            - qcom,msm8939-apcs-kpss-global
-            - qcom,qcs404-apcs-apps-global
+          contains:
+            enum:
+              - qcom,msm8916-apcs-kpss-global
+    then:
+      properties:
+        clocks:
+          items:
+            - description: primary pll parent of the clock driver
+            - description: auxiliary parent
+        clock-names:
+          items:
+            - const: pll
+            - const: aux
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,msm8939-apcs-kpss-global
     then:
       properties:
         clocks:
           items:
             - description: primary pll parent of the clock driver
             - description: auxiliary parent
+            - description: reference clock
         clock-names:
           items:
             - const: pll
             - const: aux
+            - const: ref
 
   - if:
       properties:
@@ -112,6 +141,7 @@ allOf:
             - const: ref
             - const: pll
             - const: aux
+
   - if:
       properties:
         compatible:
@@ -136,16 +166,10 @@ allOf:
         compatible:
           enum:
             - qcom,msm8953-apcs-kpss-global
-            - qcom,msm8976-apcs-kpss-global
             - qcom,msm8994-apcs-kpss-global
             - qcom,msm8996-apcs-hmss-global
-            - qcom,msm8998-apcs-hmss-global
             - qcom,qcm2290-apcs-hmss-global
-            - qcom,sdm660-apcs-hmss-global
             - qcom,sdm845-apss-shared
-            - qcom,sm4250-apcs-hmss-global
-            - qcom,sm6115-apcs-hmss-global
-            - qcom,sm6125-apcs-hmss-global
     then:
       properties:
         clocks: false
@@ -191,7 +215,8 @@ examples:
     #define GCC_APSS_AHB_CLK_SRC  1
     #define GCC_GPLL0_AO_OUT_MAIN 123
     apcs: mailbox@b011000 {
-        compatible = "qcom,qcs404-apcs-apps-global", "syscon";
+        compatible = "qcom,qcs404-apcs-apps-global",
+                     "qcom,msm8916-apcs-kpss-global", "syscon";
         reg = <0x0b011000 0x1000>;
         #mbox-cells = <1>;
         clocks = <&apcs_hfpll>, <&gcc GCC_GPLL0_AO_OUT_MAIN>;
-- 
GitLab


From a71c8424e309c2b22fa357d0af23ac1cde4eecae Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 11 Nov 2023 21:49:16 +0100
Subject: [PATCH 2664/4076] mailbox: qcom-apcs-ipc: re-organize compatibles
 with fallbacks

Similarly to previous commit e17225887005 ("mailbox: qcom-apcs-ipc: do
not grow the of_device_id"), move compatibles with fallbacks in the
of_device_id table, to indicate these are not necessary.  This only
shuffles the code.  No functional impact.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/qcom-apcs-ipc-mailbox.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c
index 002a135ee8688..79136fb62f019 100644
--- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c
+++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c
@@ -145,19 +145,19 @@ static const struct of_device_id qcom_apcs_ipc_of_match[] = {
 	{ .compatible = "qcom,msm8916-apcs-kpss-global", .data = &msm8916_apcs_data },
 	{ .compatible = "qcom,msm8939-apcs-kpss-global", .data = &msm8916_apcs_data },
 	{ .compatible = "qcom,msm8953-apcs-kpss-global", .data = &msm8994_apcs_data },
-	{ .compatible = "qcom,msm8976-apcs-kpss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,msm8994-apcs-kpss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,msm8996-apcs-hmss-global", .data = &msm8996_apcs_data },
-	{ .compatible = "qcom,msm8998-apcs-hmss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,qcm2290-apcs-hmss-global", .data = &msm8994_apcs_data },
+	{ .compatible = "qcom,sdm845-apss-shared", .data = &apps_shared_apcs_data },
+	{ .compatible = "qcom,sdx55-apcs-gcc", .data = &sdx55_apcs_data },
+	/* Do not add any more entries using existing driver data */
+	{ .compatible = "qcom,msm8976-apcs-kpss-global", .data = &msm8994_apcs_data },
+	{ .compatible = "qcom,msm8998-apcs-hmss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,qcs404-apcs-apps-global", .data = &msm8916_apcs_data },
 	{ .compatible = "qcom,sdm660-apcs-hmss-global", .data = &msm8994_apcs_data },
-	{ .compatible = "qcom,sdm845-apss-shared", .data = &apps_shared_apcs_data },
 	{ .compatible = "qcom,sm4250-apcs-hmss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,sm6125-apcs-hmss-global", .data = &msm8994_apcs_data },
 	{ .compatible = "qcom,sm6115-apcs-hmss-global", .data = &msm8994_apcs_data },
-	{ .compatible = "qcom,sdx55-apcs-gcc", .data = &sdx55_apcs_data },
-	/* Do not add any more entries using existing driver data */
 	{ .compatible = "qcom,ipq5332-apcs-apps-global", .data = &ipq6018_apcs_data },
 	{ .compatible = "qcom,ipq8074-apcs-apps-global", .data = &ipq6018_apcs_data },
 	{ .compatible = "qcom,sc7180-apss-shared", .data = &apps_shared_apcs_data },
-- 
GitLab


From ee01c0b4384d19ecc5dfa7db3fd4303f965c3eba Mon Sep 17 00:00:00 2001
From: "Xiaowu.ding" <xiaowu.ding@jaguarmicro.com>
Date: Tue, 12 Dec 2023 19:37:22 +0800
Subject: [PATCH 2665/4076] mailbox: arm_mhuv2: Fix a bug for
 mhuv2_sender_interrupt

Message Handling Unit version is v2.1.

When arm_mhuv2 working with the data protocol transfer mode.
We have split one mhu into two channels, and every channel
include four channel windows, the two channels share
one gic spi interrupt.

There is a problem with the sending scenario.

The first channel will take up 0-3 channel windows, and the second
channel take up 4-7 channel windows. When the first channel send the
data, and the receiver will clear all the four channels status.
Although we only enabled the interrupt on the last channel window with
register CH_INT_EN,the register CHCOMB_INT_ST0 will be 0xf, not be 0x8.
Currently we just clear the last channel windows int status with the
data proctol mode.So after that,the CHCOMB_INT_ST0 status will be 0x7,
not be the 0x0.

Then the second channel send the data, the receiver read the
data, clear all the four channel windows status, trigger the sender
interrupt. But currently the CHCOMB_INT_ST0 register will be 0xf7,
get_irq_chan_comb function will always return the first channel.

So this patch clear all channel windows int status to avoid this interrupt
confusion.

Signed-off-by: Xiaowu.ding <xiaowu.ding@jaguarmicro.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/arm_mhuv2.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mailbox/arm_mhuv2.c b/drivers/mailbox/arm_mhuv2.c
index c6d4957c4da83..0ec21dcdbde72 100644
--- a/drivers/mailbox/arm_mhuv2.c
+++ b/drivers/mailbox/arm_mhuv2.c
@@ -553,7 +553,8 @@ static irqreturn_t mhuv2_sender_interrupt(int irq, void *data)
 	priv = chan->con_priv;
 
 	if (!IS_PROTOCOL_DOORBELL(priv)) {
-		writel_relaxed(1, &mhu->send->ch_wn[priv->ch_wn_idx + priv->windows - 1].int_clr);
+		for (i = 0; i < priv->windows; i++)
+			writel_relaxed(1, &mhu->send->ch_wn[priv->ch_wn_idx + i].int_clr);
 
 		if (chan->cl) {
 			mbox_chan_txdone(chan, 0);
-- 
GitLab


From 0a49b66c7413337445553da331aebfb26c95e6a2 Mon Sep 17 00:00:00 2001
From: Tanmay Shah <tanmay.shah@amd.com>
Date: Wed, 13 Dec 2023 21:42:25 -0800
Subject: [PATCH 2666/4076] dt-bindings: mailbox: zynqmp: extend required list

"xlnx,ipi-id" is handled as required property but is
missing from binding doc required list of mailbox child node.
Add that to required list. This does not break backward
compatibility but bug in bindings document.

Fixes: 4a855a957936 ("dt-bindings: mailbox: zynqmp_ipi: convert to yaml")
Signed-off-by: Tanmay Shah <tanmay.shah@amd.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml     | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
index 8b15a0532120f..73c1808716053 100644
--- a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
+++ b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
@@ -103,6 +103,7 @@ patternProperties:
       - reg
       - reg-names
       - "#mbox-cells"
+      - xlnx,ipi-id
 
 additionalProperties: false
 
-- 
GitLab


From 7f923ab20faa1d378ac3bca5bdb73a1a484fddd3 Mon Sep 17 00:00:00 2001
From: Tanmay Shah <tanmay.shah@amd.com>
Date: Wed, 13 Dec 2023 21:42:27 -0800
Subject: [PATCH 2667/4076] dt-bindings: mailbox: add Versal IPI bindings

Add documentation for AMD-Xilinx Versal platform Inter Processor Interrupt
controller. Versal IPI controller contains buffer-less IPI which do not
have buffers for message passing. For such IPI channels message buffers
are not expected and only notification to/from remote agent is expected.

Signed-off-by: Tanmay Shah <tanmay.shah@amd.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../mailbox/xlnx,zynqmp-ipi-mailbox.yaml      | 131 ++++++++++++++++--
 1 file changed, 118 insertions(+), 13 deletions(-)

diff --git a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
index 73c1808716053..fe83b5cb1278d 100644
--- a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
+++ b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.yaml
@@ -37,7 +37,9 @@ maintainers:
 
 properties:
   compatible:
-    const: xlnx,zynqmp-ipi-mailbox
+    enum:
+      - xlnx,zynqmp-ipi-mailbox
+      - xlnx,versal-ipi-mailbox
 
   method:
     description: |
@@ -58,6 +60,12 @@ properties:
   '#size-cells':
     const: 2
 
+  reg:
+    maxItems: 2
+
+  reg-names:
+    maxItems: 2
+
   xlnx,ipi-id:
     description: |
       Remote Xilinx IPI agent ID of which the mailbox is connected to.
@@ -76,7 +84,17 @@ patternProperties:
     properties:
 
       compatible:
-        const: xlnx,zynqmp-ipi-dest-mailbox
+        enum:
+          - xlnx,zynqmp-ipi-dest-mailbox
+          - xlnx,versal-ipi-dest-mailbox
+
+      reg:
+        minItems: 1
+        maxItems: 4
+
+      reg-names:
+        minItems: 1
+        maxItems: 4
 
       xlnx,ipi-id:
         description:
@@ -88,15 +106,37 @@ patternProperties:
         description:
           It contains tx(0) or rx(1) channel IPI id number.
 
-      reg:
-        maxItems: 4
-
-      reg-names:
-        items:
-          - const: local_request_region
-          - const: local_response_region
-          - const: remote_request_region
-          - const: remote_response_region
+    allOf:
+      - if:
+          properties:
+            compatible:
+              contains:
+                enum:
+                  - xlnx,zynqmp-ipi-dest-mailbox
+        then:
+          properties:
+            reg:
+              maxItems: 4
+
+            reg-names:
+              items:
+                - const: local_request_region
+                - const: local_response_region
+                - const: remote_request_region
+                - const: remote_response_region
+        else:
+          properties:
+            reg:
+              minItems: 1
+              items:
+                - description: Remote IPI agent control register region
+                - description: Remote IPI agent optional message buffers
+
+            reg-names:
+              minItems: 1
+              items:
+                - const: ctrl
+                - const: msg
 
     required:
       - compatible
@@ -105,8 +145,6 @@ patternProperties:
       - "#mbox-cells"
       - xlnx,ipi-id
 
-additionalProperties: false
-
 required:
   - compatible
   - interrupts
@@ -114,6 +152,36 @@ required:
   - '#size-cells'
   - xlnx,ipi-id
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - xlnx,zynqmp-ipi-mailbox
+    then:
+      properties:
+        reg: false
+        reg-names: false
+
+    else:
+      properties:
+        reg:
+          items:
+            - description: Host IPI agent control register region
+            - description: Host IPI agent optional message buffers
+
+        reg-names:
+          items:
+            - const: ctrl
+            - const: msg
+
+      required:
+        - reg
+        - reg-names
+
+additionalProperties: false
+
 examples:
   - |
     #include<dt-bindings/interrupt-controller/arm-gic.h>
@@ -145,4 +213,41 @@ examples:
       };
     };
 
+  - |
+    #include<dt-bindings/interrupt-controller/arm-gic.h>
+
+    bus {
+      #address-cells = <2>;
+      #size-cells = <2>;
+      mailbox@ff300000 {
+        compatible = "xlnx,versal-ipi-mailbox";
+        interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+        #address-cells = <2>;
+        #size-cells = <2>;
+        reg = <0x0 0xff300000 0x0 0x1000>,
+              <0x0 0xff990000 0x0 0x1ff>;
+        reg-names = "ctrl", "msg";
+        xlnx,ipi-id = <0>;
+        ranges;
+
+        /* buffered IPI */
+        mailbox@ff340000 {
+          compatible = "xlnx,versal-ipi-dest-mailbox";
+          reg = <0x0 0xff340000 0x0 0x1000>,
+                <0x0 0xff990400 0x0 0x1ff>;
+          reg-names = "ctrl", "msg";
+          #mbox-cells = <1>;
+          xlnx,ipi-id = <4>;
+        };
+
+        /* bufferless IPI */
+        mailbox@ff370000 {
+          compatible = "xlnx,versal-ipi-dest-mailbox";
+          reg = <0x0 0xff370000 0x0 0x1000>;
+          reg-names = "ctrl";
+          #mbox-cells = <1>;
+          xlnx,ipi-id = <7>;
+        };
+      };
+    };
 ...
-- 
GitLab


From b3734a8291ad7fd61e5a51cc540e414bcfbdc0cf Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 15 Dec 2023 16:41:56 -0800
Subject: [PATCH 2668/4076] mailbox: zynqmp-ipi: fix an Excess struct member
 kernel-doc warning

kernel test robot reports 2 Excess struct member warnings:

zynqmp-ipi-mailbox.c:92: warning: Excess struct member 'irq' description in 'zynqmp_ipi_mbox'
zynqmp-ipi-mailbox.c:112: warning: Excess struct member 'ipi_mboxes' description in 'zynqmp_ipi_pdata'

The second one is a false positive that is caused by the
__counted_by() attribute. Kees has posted a patch for that, so just
fix the first one.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312150705.glrQ4ypv-lkp@intel.com/
Cc: linux-arm-kernel@lists.infradead.org
Reviewed-by: Michal Simek <michal.simek@amd.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/zynqmp-ipi-mailbox.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c
index 7fa533e80dd97..a512e2405111d 100644
--- a/drivers/mailbox/zynqmp-ipi-mailbox.c
+++ b/drivers/mailbox/zynqmp-ipi-mailbox.c
@@ -81,7 +81,6 @@ struct zynqmp_ipi_mchan {
  * @remote_id:            remote IPI agent ID
  * @mbox:                 mailbox Controller
  * @mchans:               array for channels, tx channel and rx channel.
- * @irq:                  IPI agent interrupt ID
  */
 struct zynqmp_ipi_mbox {
 	struct zynqmp_ipi_pdata *pdata;
-- 
GitLab


From d0a724d419cccf301a62626f48bea4ed75dda1b9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:29 +0100
Subject: [PATCH 2669/4076] mailbox: bcm-flexrm: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/bcm-flexrm-mailbox.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c
index a2b8839d4e7c5..e3e28a4f7d017 100644
--- a/drivers/mailbox/bcm-flexrm-mailbox.c
+++ b/drivers/mailbox/bcm-flexrm-mailbox.c
@@ -1650,7 +1650,7 @@ fail:
 	return ret;
 }
 
-static int flexrm_mbox_remove(struct platform_device *pdev)
+static void flexrm_mbox_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct flexrm_mbox *mbox = platform_get_drvdata(pdev);
@@ -1661,8 +1661,6 @@ static int flexrm_mbox_remove(struct platform_device *pdev)
 
 	dma_pool_destroy(mbox->cmpl_pool);
 	dma_pool_destroy(mbox->bd_pool);
-
-	return 0;
 }
 
 static const struct of_device_id flexrm_mbox_of_match[] = {
@@ -1677,7 +1675,7 @@ static struct platform_driver flexrm_mbox_driver = {
 		.of_match_table = flexrm_mbox_of_match,
 	},
 	.probe		= flexrm_mbox_probe,
-	.remove		= flexrm_mbox_remove,
+	.remove_new	= flexrm_mbox_remove,
 };
 module_platform_driver(flexrm_mbox_driver);
 
-- 
GitLab


From 74701ffbf7db4352404034d9fac536a029d2fc3f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:30 +0100
Subject: [PATCH 2670/4076] mailbox: bcm-pdc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/bcm-pdc-mailbox.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c
index 778faeced81e1..1768d3d5aaa01 100644
--- a/drivers/mailbox/bcm-pdc-mailbox.c
+++ b/drivers/mailbox/bcm-pdc-mailbox.c
@@ -1605,7 +1605,7 @@ cleanup:
 	return err;
 }
 
-static int pdc_remove(struct platform_device *pdev)
+static void pdc_remove(struct platform_device *pdev)
 {
 	struct pdc_state *pdcs = platform_get_drvdata(pdev);
 
@@ -1617,12 +1617,11 @@ static int pdc_remove(struct platform_device *pdev)
 
 	dma_pool_destroy(pdcs->rx_buf_pool);
 	dma_pool_destroy(pdcs->ring_pool);
-	return 0;
 }
 
 static struct platform_driver pdc_mbox_driver = {
 	.probe = pdc_probe,
-	.remove = pdc_remove,
+	.remove_new = pdc_remove,
 	.driver = {
 		   .name = "brcm-iproc-pdc-mbox",
 		   .of_match_table = pdc_mbox_of_match,
-- 
GitLab


From a0c313d08d158e59262dd2bc89027d7de584950e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:31 +0100
Subject: [PATCH 2671/4076] mailbox: imx: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/imx-mailbox.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
index 0af739ab571cd..656171362fe9e 100644
--- a/drivers/mailbox/imx-mailbox.c
+++ b/drivers/mailbox/imx-mailbox.c
@@ -903,13 +903,11 @@ disable_runtime_pm:
 	return ret;
 }
 
-static int imx_mu_remove(struct platform_device *pdev)
+static void imx_mu_remove(struct platform_device *pdev)
 {
 	struct imx_mu_priv *priv = platform_get_drvdata(pdev);
 
 	pm_runtime_disable(priv->dev);
-
-	return 0;
 }
 
 static const struct imx_mu_dcfg imx_mu_cfg_imx6sx = {
@@ -1070,7 +1068,7 @@ static const struct dev_pm_ops imx_mu_pm_ops = {
 
 static struct platform_driver imx_mu_driver = {
 	.probe		= imx_mu_probe,
-	.remove		= imx_mu_remove,
+	.remove_new	= imx_mu_remove,
 	.driver = {
 		.name	= "imx_mu",
 		.of_match_table = imx_mu_dt_ids,
-- 
GitLab


From bf562bc5a86b2ab7b5cf9a85862a37bd4af06113 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:32 +0100
Subject: [PATCH 2672/4076] mailbox: mailbox-test: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mailbox-test.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c
index 22d6018ceec3c..3386b4e72551c 100644
--- a/drivers/mailbox/mailbox-test.c
+++ b/drivers/mailbox/mailbox-test.c
@@ -418,7 +418,7 @@ static int mbox_test_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mbox_test_remove(struct platform_device *pdev)
+static void mbox_test_remove(struct platform_device *pdev)
 {
 	struct mbox_test_device *tdev = platform_get_drvdata(pdev);
 
@@ -428,8 +428,6 @@ static int mbox_test_remove(struct platform_device *pdev)
 		mbox_free_channel(tdev->tx_channel);
 	if (tdev->rx_channel)
 		mbox_free_channel(tdev->rx_channel);
-
-	return 0;
 }
 
 static const struct of_device_id mbox_test_match[] = {
@@ -444,7 +442,7 @@ static struct platform_driver mbox_test_driver = {
 		.of_match_table = mbox_test_match,
 	},
 	.probe  = mbox_test_probe,
-	.remove = mbox_test_remove,
+	.remove_new = mbox_test_remove,
 };
 module_platform_driver(mbox_test_driver);
 
-- 
GitLab


From e89c7c3766dca2d38a1c7a695fd7d046e2a3fc4a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:33 +0100
Subject: [PATCH 2673/4076] mailbox: mtk-cmdq: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mtk-cmdq-mailbox.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index de862e9137d5f..c9009b729ab26 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -367,7 +367,7 @@ static int cmdq_resume(struct device *dev)
 	return 0;
 }
 
-static int cmdq_remove(struct platform_device *pdev)
+static void cmdq_remove(struct platform_device *pdev)
 {
 	struct cmdq *cmdq = platform_get_drvdata(pdev);
 
@@ -378,7 +378,6 @@ static int cmdq_remove(struct platform_device *pdev)
 		cmdq_runtime_suspend(&pdev->dev);
 
 	clk_bulk_unprepare(cmdq->pdata->gce_num, cmdq->clocks);
-	return 0;
 }
 
 static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
@@ -761,7 +760,7 @@ static const struct of_device_id cmdq_of_ids[] = {
 
 static struct platform_driver cmdq_drv = {
 	.probe = cmdq_probe,
-	.remove = cmdq_remove,
+	.remove_new = cmdq_remove,
 	.driver = {
 		.name = "mtk_cmdq",
 		.pm = &cmdq_pm_ops,
-- 
GitLab


From 67785923d3f5ee2cf6825f3f69fb6c2f9cc54c15 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:34 +0100
Subject: [PATCH 2674/4076] mailbox: omap: Convert to platform remove callback
 returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/omap-mailbox.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c
index 792bcaebbc9b8..c961706fe61d5 100644
--- a/drivers/mailbox/omap-mailbox.c
+++ b/drivers/mailbox/omap-mailbox.c
@@ -865,19 +865,17 @@ unregister:
 	return ret;
 }
 
-static int omap_mbox_remove(struct platform_device *pdev)
+static void omap_mbox_remove(struct platform_device *pdev)
 {
 	struct omap_mbox_device *mdev = platform_get_drvdata(pdev);
 
 	pm_runtime_disable(mdev->dev);
 	omap_mbox_unregister(mdev);
-
-	return 0;
 }
 
 static struct platform_driver omap_mbox_driver = {
 	.probe	= omap_mbox_probe,
-	.remove	= omap_mbox_remove,
+	.remove_new = omap_mbox_remove,
 	.driver	= {
 		.name = "omap-mailbox",
 		.pm = &omap_mbox_pm_ops,
-- 
GitLab


From ce42b93c6370020d3c3ba91d48f356227a059c17 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:35 +0100
Subject: [PATCH 2675/4076] mailbox: qcom-apcs-ipc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/qcom-apcs-ipc-mailbox.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c
index 79136fb62f019..7d91e7c016ba7 100644
--- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c
+++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c
@@ -129,14 +129,12 @@ static int qcom_apcs_ipc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qcom_apcs_ipc_remove(struct platform_device *pdev)
+static void qcom_apcs_ipc_remove(struct platform_device *pdev)
 {
 	struct qcom_apcs_ipc *apcs = platform_get_drvdata(pdev);
 	struct platform_device *clk = apcs->clk;
 
 	platform_device_unregister(clk);
-
-	return 0;
 }
 
 /* .data is the offset of the ipc register within the global block */
@@ -169,7 +167,7 @@ MODULE_DEVICE_TABLE(of, qcom_apcs_ipc_of_match);
 
 static struct platform_driver qcom_apcs_ipc_driver = {
 	.probe = qcom_apcs_ipc_probe,
-	.remove = qcom_apcs_ipc_remove,
+	.remove_new = qcom_apcs_ipc_remove,
 	.driver = {
 		.name = "qcom_apcs_ipc",
 		.of_match_table = qcom_apcs_ipc_of_match,
-- 
GitLab


From d3a0021c413262c011d7ffbce1de0b2cb1c7146b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:36 +0100
Subject: [PATCH 2676/4076] mailbox: qcom-ipcc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/qcom-ipcc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/qcom-ipcc.c b/drivers/mailbox/qcom-ipcc.c
index f597a1bd56847..d537cc9c4d4be 100644
--- a/drivers/mailbox/qcom-ipcc.c
+++ b/drivers/mailbox/qcom-ipcc.c
@@ -326,14 +326,12 @@ err_mbox:
 	return ret;
 }
 
-static int qcom_ipcc_remove(struct platform_device *pdev)
+static void qcom_ipcc_remove(struct platform_device *pdev)
 {
 	struct qcom_ipcc *ipcc = platform_get_drvdata(pdev);
 
 	disable_irq_wake(ipcc->irq);
 	irq_domain_remove(ipcc->irq_domain);
-
-	return 0;
 }
 
 static const struct of_device_id qcom_ipcc_of_match[] = {
@@ -348,7 +346,7 @@ static const struct dev_pm_ops qcom_ipcc_dev_pm_ops = {
 
 static struct platform_driver qcom_ipcc_driver = {
 	.probe = qcom_ipcc_probe,
-	.remove = qcom_ipcc_remove,
+	.remove_new = qcom_ipcc_remove,
 	.driver = {
 		.name = "qcom-ipcc",
 		.of_match_table = qcom_ipcc_of_match,
-- 
GitLab


From 0a902f502e392ffd689057af39e0cdadc6060362 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:37 +0100
Subject: [PATCH 2677/4076] mailbox: stm32-ipcc: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/stm32-ipcc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/stm32-ipcc.c b/drivers/mailbox/stm32-ipcc.c
index 4ad3653f38666..1442f275782bd 100644
--- a/drivers/mailbox/stm32-ipcc.c
+++ b/drivers/mailbox/stm32-ipcc.c
@@ -331,7 +331,7 @@ err_clk:
 	return ret;
 }
 
-static int stm32_ipcc_remove(struct platform_device *pdev)
+static void stm32_ipcc_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 
@@ -339,8 +339,6 @@ static int stm32_ipcc_remove(struct platform_device *pdev)
 		dev_pm_clear_wake_irq(&pdev->dev);
 
 	device_set_wakeup_capable(dev, false);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -381,7 +379,7 @@ static struct platform_driver stm32_ipcc_driver = {
 		.of_match_table = stm32_ipcc_of_match,
 	},
 	.probe		= stm32_ipcc_probe,
-	.remove		= stm32_ipcc_remove,
+	.remove_new	= stm32_ipcc_remove,
 };
 
 module_platform_driver(stm32_ipcc_driver);
-- 
GitLab


From b8e346bd8fb9bd1e310aa185219679c9412065b0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:38 +0100
Subject: [PATCH 2678/4076] mailbox: sun6i-msgbox: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/sun6i-msgbox.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/sun6i-msgbox.c b/drivers/mailbox/sun6i-msgbox.c
index 7f8d931042d38..3dcc54dc83b2d 100644
--- a/drivers/mailbox/sun6i-msgbox.c
+++ b/drivers/mailbox/sun6i-msgbox.c
@@ -287,15 +287,13 @@ err_disable_unprepare:
 	return ret;
 }
 
-static int sun6i_msgbox_remove(struct platform_device *pdev)
+static void sun6i_msgbox_remove(struct platform_device *pdev)
 {
 	struct sun6i_msgbox *mbox = platform_get_drvdata(pdev);
 
 	mbox_controller_unregister(&mbox->controller);
 	/* See the comment in sun6i_msgbox_probe about the reset line. */
 	clk_disable_unprepare(mbox->clk);
-
-	return 0;
 }
 
 static const struct of_device_id sun6i_msgbox_of_match[] = {
@@ -310,7 +308,7 @@ static struct platform_driver sun6i_msgbox_driver = {
 		.of_match_table = sun6i_msgbox_of_match,
 	},
 	.probe  = sun6i_msgbox_probe,
-	.remove = sun6i_msgbox_remove,
+	.remove_new = sun6i_msgbox_remove,
 };
 module_platform_driver(sun6i_msgbox_driver);
 
-- 
GitLab


From ab572ab44b042146dce1b38a5ad5c076e351833d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:39 +0100
Subject: [PATCH 2679/4076] mailbox: tegra-hsp: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/tegra-hsp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c
index fe29fc2ca5260..19ef56cbcfd39 100644
--- a/drivers/mailbox/tegra-hsp.c
+++ b/drivers/mailbox/tegra-hsp.c
@@ -868,13 +868,11 @@ static int tegra_hsp_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int tegra_hsp_remove(struct platform_device *pdev)
+static void tegra_hsp_remove(struct platform_device *pdev)
 {
 	struct tegra_hsp *hsp = platform_get_drvdata(pdev);
 
 	lockdep_unregister_key(&hsp->lock_key);
-
-	return 0;
 }
 
 static int __maybe_unused tegra_hsp_resume(struct device *dev)
@@ -953,7 +951,7 @@ static struct platform_driver tegra_hsp_driver = {
 		.pm = &tegra_hsp_pm_ops,
 	},
 	.probe = tegra_hsp_probe,
-	.remove = tegra_hsp_remove,
+	.remove_new = tegra_hsp_remove,
 };
 
 static int __init tegra_hsp_init(void)
-- 
GitLab


From cdf179a9d3e424e3634718ebd4208b5fd4ca480d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Dec 2023 22:02:40 +0100
Subject: [PATCH 2680/4076] mailbox: zynqmp-ipi: Convert to platform remove
 callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.

To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().

Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Michal Simek <michal.simek@amd.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/zynqmp-ipi-mailbox.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c
index a512e2405111d..25c65afc030a3 100644
--- a/drivers/mailbox/zynqmp-ipi-mailbox.c
+++ b/drivers/mailbox/zynqmp-ipi-mailbox.c
@@ -687,19 +687,17 @@ free_mbox_dev:
 	return ret;
 }
 
-static int zynqmp_ipi_remove(struct platform_device *pdev)
+static void zynqmp_ipi_remove(struct platform_device *pdev)
 {
 	struct zynqmp_ipi_pdata *pdata;
 
 	pdata = platform_get_drvdata(pdev);
 	zynqmp_ipi_free_mboxes(pdata);
-
-	return 0;
 }
 
 static struct platform_driver zynqmp_ipi_driver = {
 	.probe = zynqmp_ipi_probe,
-	.remove = zynqmp_ipi_remove,
+	.remove_new = zynqmp_ipi_remove,
 	.driver = {
 		   .name = "zynqmp-ipi",
 		   .of_match_table = of_match_ptr(zynqmp_ipi_of_match),
-- 
GitLab


From 171c8a20850fd29721c417af743a8e36aeb6e010 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 14 Dec 2023 19:16:04 +0200
Subject: [PATCH 2681/4076] dt-bindings: mailbox: qcom-ipcc: document the
 X1E80100 Inter-Processor Communication Controller

Document the Inter-Processor Communication Controller on the X1E80100 Platform.

Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
index a35f9483dc716..8f004868aad98 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
+++ b/Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
@@ -35,6 +35,7 @@ properties:
           - qcom,sm8450-ipcc
           - qcom,sm8550-ipcc
           - qcom,sm8650-ipcc
+          - qcom,x1e80100-ipcc
       - const: qcom,ipcc
 
   reg:
-- 
GitLab


From 060177644136bdefd887c61043220f7eb63c2fe6 Mon Sep 17 00:00:00 2001
From: "Jason-JH.Lin" <jason-jh.lin@mediatek.com>
Date: Fri, 15 Dec 2023 15:00:24 +0800
Subject: [PATCH 2682/4076] mailbox: mtk-cmdq: Rename gce_plat variable with
 SoC name postfix

Rename gce_plat variable postfix from 'v1~v7' to SoC names.

Signed-off-by: Jason-JH.Lin <jason-jh.lin@mediatek.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mtk-cmdq-mailbox.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index c9009b729ab26..6b1e8df8485e3 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -705,42 +705,42 @@ static const struct dev_pm_ops cmdq_pm_ops = {
 			   cmdq_runtime_resume, NULL)
 };
 
-static const struct gce_plat gce_plat_v2 = {
+static const struct gce_plat gce_plat_mt8173 = {
 	.thread_nr = 16,
 	.shift = 0,
 	.control_by_sw = false,
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_v3 = {
+static const struct gce_plat gce_plat_mt8183 = {
 	.thread_nr = 24,
 	.shift = 0,
 	.control_by_sw = false,
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_v4 = {
+static const struct gce_plat gce_plat_mt6779 = {
 	.thread_nr = 24,
 	.shift = 3,
 	.control_by_sw = false,
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_v5 = {
+static const struct gce_plat gce_plat_mt8192 = {
 	.thread_nr = 24,
 	.shift = 3,
 	.control_by_sw = true,
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_v6 = {
+static const struct gce_plat gce_plat_mt8195 = {
 	.thread_nr = 24,
 	.shift = 3,
 	.control_by_sw = true,
 	.gce_num = 2
 };
 
-static const struct gce_plat gce_plat_v7 = {
+static const struct gce_plat gce_plat_mt8186 = {
 	.thread_nr = 24,
 	.shift = 3,
 	.control_by_sw = true,
@@ -749,12 +749,12 @@ static const struct gce_plat gce_plat_v7 = {
 };
 
 static const struct of_device_id cmdq_of_ids[] = {
-	{.compatible = "mediatek,mt8173-gce", .data = (void *)&gce_plat_v2},
-	{.compatible = "mediatek,mt8183-gce", .data = (void *)&gce_plat_v3},
-	{.compatible = "mediatek,mt8186-gce", .data = (void *)&gce_plat_v7},
-	{.compatible = "mediatek,mt6779-gce", .data = (void *)&gce_plat_v4},
-	{.compatible = "mediatek,mt8192-gce", .data = (void *)&gce_plat_v5},
-	{.compatible = "mediatek,mt8195-gce", .data = (void *)&gce_plat_v6},
+	{.compatible = "mediatek,mt8173-gce", .data = (void *)&gce_plat_mt8173},
+	{.compatible = "mediatek,mt8183-gce", .data = (void *)&gce_plat_mt8183},
+	{.compatible = "mediatek,mt8186-gce", .data = (void *)&gce_plat_mt8186},
+	{.compatible = "mediatek,mt6779-gce", .data = (void *)&gce_plat_mt6779},
+	{.compatible = "mediatek,mt8192-gce", .data = (void *)&gce_plat_mt8192},
+	{.compatible = "mediatek,mt8195-gce", .data = (void *)&gce_plat_mt8195},
 	{}
 };
 
-- 
GitLab


From df71f7818fb20546e400379dcb2c6b9f2ebab8c5 Mon Sep 17 00:00:00 2001
From: "Jason-JH.Lin" <jason-jh.lin@mediatek.com>
Date: Fri, 15 Dec 2023 15:00:25 +0800
Subject: [PATCH 2683/4076] mailbox: mtk-cmdq: Sort cmdq platform data by
 compatible name

Sort cmdq platform data according to the number sequence of
compatible names.

Signed-off-by: Jason-JH.Lin <jason-jh.lin@mediatek.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mtk-cmdq-mailbox.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 6b1e8df8485e3..472144c0ef40e 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -705,6 +705,13 @@ static const struct dev_pm_ops cmdq_pm_ops = {
 			   cmdq_runtime_resume, NULL)
 };
 
+static const struct gce_plat gce_plat_mt6779 = {
+	.thread_nr = 24,
+	.shift = 3,
+	.control_by_sw = false,
+	.gce_num = 1
+};
+
 static const struct gce_plat gce_plat_mt8173 = {
 	.thread_nr = 16,
 	.shift = 0,
@@ -719,10 +726,11 @@ static const struct gce_plat gce_plat_mt8183 = {
 	.gce_num = 1
 };
 
-static const struct gce_plat gce_plat_mt6779 = {
+static const struct gce_plat gce_plat_mt8186 = {
 	.thread_nr = 24,
 	.shift = 3,
-	.control_by_sw = false,
+	.control_by_sw = true,
+	.sw_ddr_en = true,
 	.gce_num = 1
 };
 
@@ -740,19 +748,11 @@ static const struct gce_plat gce_plat_mt8195 = {
 	.gce_num = 2
 };
 
-static const struct gce_plat gce_plat_mt8186 = {
-	.thread_nr = 24,
-	.shift = 3,
-	.control_by_sw = true,
-	.sw_ddr_en = true,
-	.gce_num = 1
-};
-
 static const struct of_device_id cmdq_of_ids[] = {
+	{.compatible = "mediatek,mt6779-gce", .data = (void *)&gce_plat_mt6779},
 	{.compatible = "mediatek,mt8173-gce", .data = (void *)&gce_plat_mt8173},
 	{.compatible = "mediatek,mt8183-gce", .data = (void *)&gce_plat_mt8183},
 	{.compatible = "mediatek,mt8186-gce", .data = (void *)&gce_plat_mt8186},
-	{.compatible = "mediatek,mt6779-gce", .data = (void *)&gce_plat_mt6779},
 	{.compatible = "mediatek,mt8192-gce", .data = (void *)&gce_plat_mt8192},
 	{.compatible = "mediatek,mt8195-gce", .data = (void *)&gce_plat_mt8195},
 	{}
-- 
GitLab


From cd795fb0c352c1f70e5fa437b01572c8693e1b77 Mon Sep 17 00:00:00 2001
From: "Jason-JH.Lin" <jason-jh.lin@mediatek.com>
Date: Fri, 15 Dec 2023 15:00:26 +0800
Subject: [PATCH 2684/4076] mailbox: mtk-cmdq: Add CMDQ driver support for
 mt8188

Add CMDQ driver support for mt8188 by adding its compatible and
driver data in CMDQ driver.

Signed-off-by: Jason-JH.Lin <jason-jh.lin@mediatek.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mtk-cmdq-mailbox.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 472144c0ef40e..ead2200f39ba0 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -734,6 +734,13 @@ static const struct gce_plat gce_plat_mt8186 = {
 	.gce_num = 1
 };
 
+static const struct gce_plat gce_plat_mt8188 = {
+	.thread_nr = 32,
+	.shift = 3,
+	.control_by_sw = true,
+	.gce_num = 2
+};
+
 static const struct gce_plat gce_plat_mt8192 = {
 	.thread_nr = 24,
 	.shift = 3,
@@ -753,6 +760,7 @@ static const struct of_device_id cmdq_of_ids[] = {
 	{.compatible = "mediatek,mt8173-gce", .data = (void *)&gce_plat_mt8173},
 	{.compatible = "mediatek,mt8183-gce", .data = (void *)&gce_plat_mt8183},
 	{.compatible = "mediatek,mt8186-gce", .data = (void *)&gce_plat_mt8186},
+	{.compatible = "mediatek,mt8188-gce", .data = (void *)&gce_plat_mt8188},
 	{.compatible = "mediatek,mt8192-gce", .data = (void *)&gce_plat_mt8192},
 	{.compatible = "mediatek,mt8195-gce", .data = (void *)&gce_plat_mt8195},
 	{}
-- 
GitLab


From dc9dfc8dc629e42f2234e3327b75324ffc752bc9 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 12 Jan 2024 16:32:57 -0800
Subject: [PATCH 2685/4076] net: tls, fix WARNIING in __sk_msg_free

A splice with MSG_SPLICE_PAGES will cause tls code to use the
tls_sw_sendmsg_splice path in the TLS sendmsg code to move the user
provided pages from the msg into the msg_pl. This will loop over the
msg until msg_pl is full, checked by sk_msg_full(msg_pl). The user
can also set the MORE flag to hint stack to delay sending until receiving
more pages and ideally a full buffer.

If the user adds more pages to the msg than can fit in the msg_pl
scatterlist (MAX_MSG_FRAGS) we should ignore the MORE flag and send
the buffer anyways.

What actually happens though is we abort the msg to msg_pl scatterlist
setup and then because we forget to set 'full record' indicating we
can no longer consume data without a send we fallthrough to the 'continue'
path which will check if msg_data_left(msg) has more bytes to send and
then attempts to fit them in the already full msg_pl. Then next
iteration of sender doing send will encounter a full msg_pl and throw
the warning in the syzbot report.

To fix simply check if we have a full_record in splice code path and
if not send the msg regardless of MORE flag.

Reported-and-tested-by: syzbot+f2977222e0e95cec15c8@syzkaller.appspotmail.com
Reported-by: Edward Adam Davis <eadavis@qq.com>
Fixes: fe1e81d4f73b ("tls/sw: Support MSG_SPLICE_PAGES")
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index e37b4d2e2acde..31e8a94dfc111 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1052,7 +1052,11 @@ alloc_encrypted:
 			if (ret < 0)
 				goto send_end;
 			tls_ctx->pending_open_record_frags = true;
-			if (full_record || eor || sk_msg_full(msg_pl))
+
+			if (sk_msg_full(msg_pl))
+				full_record = true;
+
+			if (full_record || eor)
 				goto copied;
 			continue;
 		}
-- 
GitLab


From 034ea1305e659ddae44c19ba8449166fec318e2d Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 12 Jan 2024 16:32:58 -0800
Subject: [PATCH 2686/4076] net: tls, add test to capture error on large splice

syzbot found an error with how splice() is handled with a msg greater
than 32. This was fixed in previous patch, but lets add a test for
it to ensure it continues to work.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 464853a7f9829..7799e042a9719 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -707,6 +707,20 @@ TEST_F(tls, splice_from_pipe)
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
+TEST_F(tls, splice_more)
+{
+	unsigned int f = SPLICE_F_NONBLOCK | SPLICE_F_MORE | SPLICE_F_GIFT;
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	int i, send_pipe = 1;
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_GE(write(p[1], mem_send, send_len), 0);
+	for (i = 0; i < 32; i++)
+		EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, send_pipe, f), 1);
+}
+
 TEST_F(tls, splice_from_pipe2)
 {
 	int send_len = 16000;
-- 
GitLab


From c061be1bd5e74e9685630cc95b818e13dbff9713 Mon Sep 17 00:00:00 2001
From: Marcin Wojtas <marcin.s.wojtas@gmail.com>
Date: Fri, 12 Jan 2024 14:06:28 +0000
Subject: [PATCH 2687/4076] MAINTAINERS: eth: mvneta: update entry

Add myself as driver maintainer and restore the maintained status.
While at it, update the file field to cover mvneta_bm part of the driver.

Signed-off-by: Marcin Wojtas <marcin.s.wojtas@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4194f414dd2c5..39eb0a6a29277 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12869,9 +12869,10 @@ S:	Maintained
 F:	drivers/thermal/armada_thermal.c
 
 MARVELL MVNETA ETHERNET DRIVER
+M:	Marcin Wojtas <marcin.s.wojtas@gmail.com>
 L:	netdev@vger.kernel.org
-S:	Orphan
-F:	drivers/net/ethernet/marvell/mvneta.*
+S:	Maintained
+F:	drivers/net/ethernet/marvell/mvneta*
 
 MARVELL MVPP2 ETHERNET DRIVER
 M:	Marcin Wojtas <marcin.s.wojtas@gmail.com>
-- 
GitLab


From 95931a245b44ee04f3359ec432e73614d44d8b38 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 14 Jan 2024 10:00:59 +0100
Subject: [PATCH 2688/4076] null_blk: Remove usage of the deprecated
 ida_simple_xx() API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

This is less verbose.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/bf257b1078475a415cdc3344c6a750842946e367.1705222845.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 9f7695f00c2db..36755f263e8ec 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1840,7 +1840,7 @@ static void null_del_dev(struct nullb *nullb)
 
 	dev = nullb->dev;
 
-	ida_simple_remove(&nullb_indexes, nullb->index);
+	ida_free(&nullb_indexes, nullb->index);
 
 	list_del_init(&nullb->list);
 
@@ -2174,7 +2174,7 @@ static int null_add_dev(struct nullb_device *dev)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 
 	mutex_lock(&lock);
-	rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
+	rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
 	if (rv < 0) {
 		mutex_unlock(&lock);
 		goto out_cleanup_zone;
-- 
GitLab


From 2539b15d504c3f9fd8ca82032bf9c80c9864412c Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 12 Jan 2024 15:03:21 -0800
Subject: [PATCH 2689/4076] hwmon: (npcm750-pwm-fan) Fix crash observed when
 instantiating nuvoton,npcm750-pwm-fan

Commit 89fec128d5d1 ("hwmon: (npcm750-pwm-fan) Add NPCM8xx support")
introduced support for PWM fans on Nuvoton's npcm845 SoC. This chip
supports three PWM modules with four PWM channels each. The older npcm750
only supported two PWM modules. The commit did not take into account that
the older SoC only supported two PWM modules. This results in a crash if
npcm750 is instantiated when the code attempts to instantiate the
non-existing third PWM module.

Unable to handle kernel paging request at virtual address e0aa2000 when write
[e0aa2000] *pgd=04ab6811, *pte=00000000, *ppte=00000000
Internal error: Oops: 807 [#1] SMP ARM
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Tainted: G                 N 6.7.0-next-20240112-dirty #3
Hardware name: NPCM7XX Chip family
PC is at npcm7xx_pwm_fan_probe+0x204/0x890
LR is at arm_heavy_mb+0x1c/0x38

Fix the problem by detecting the number of supported PWM modules in the
probe function and only instantiating the supported modules.

Fixes: 89fec128d5d1 ("hwmon: (npcm750-pwm-fan) Add NPCM8xx support")
Cc: Tomer Maimon <tmaimon77@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/npcm750-pwm-fan.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c
index d9733da8ea34f..904816abb7c46 100644
--- a/drivers/hwmon/npcm750-pwm-fan.c
+++ b/drivers/hwmon/npcm750-pwm-fan.c
@@ -195,6 +195,7 @@ struct npcm7xx_cooling_device {
 struct npcm7xx_pwm_fan_data {
 	void __iomem *pwm_base;
 	void __iomem *fan_base;
+	int pwm_modules;
 	unsigned long pwm_clk_freq;
 	unsigned long fan_clk_freq;
 	struct clk *pwm_clk;
@@ -710,7 +711,7 @@ static u32 npcm7xx_pwm_init(struct npcm7xx_pwm_fan_data *data)
 	/* Setting PWM Prescale Register value register to both modules */
 	prescale_val |= (prescale_val << NPCM7XX_PWM_PRESCALE_SHIFT_CH01);
 
-	for (m = 0; m < NPCM7XX_PWM_MAX_MODULES  ; m++) {
+	for (m = 0; m < data->pwm_modules; m++) {
 		iowrite32(prescale_val, NPCM7XX_PWM_REG_PR(data->pwm_base, m));
 		iowrite32(NPCM7XX_PWM_PRESCALE2_DEFAULT,
 			  NPCM7XX_PWM_REG_CSR(data->pwm_base, m));
@@ -946,6 +947,8 @@ static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
 	if (!data->info)
 		return -EINVAL;
 
+	data->pwm_modules = data->info->pwm_max_channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE;
+
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm");
 	if (!res) {
 		dev_err(dev, "pwm resource not found\n");
@@ -983,7 +986,7 @@ static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
 	output_freq = npcm7xx_pwm_init(data);
 	npcm7xx_fan_init(data);
 
-	for (cnt = 0; cnt < NPCM7XX_PWM_MAX_MODULES  ; cnt++)
+	for (cnt = 0; cnt < data->pwm_modules; cnt++)
 		mutex_init(&data->pwm_lock[cnt]);
 
 	for (i = 0; i < NPCM7XX_FAN_MAX_MODULE; i++) {
-- 
GitLab


From e327b2372bc0f18c30433ac40be07741b59231c5 Mon Sep 17 00:00:00 2001
From: Nikita Yushchenko <nikita.yoush@cogentembedded.com>
Date: Sat, 13 Jan 2024 10:22:21 +0600
Subject: [PATCH 2690/4076] net: ravb: Fix dma_addr_t truncation in error case
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In ravb_start_xmit(), ravb driver uses u32 variable to store result of
dma_map_single() call. Since ravb hardware has 32-bit address fields in
descriptors, this works properly when mapping is successful - it is
platform's job to provide mapping addresses that fit into hardware
limitations.

However, in failure case dma_map_single() returns DMA_MAPPING_ERROR
constant that is 64-bit when dma_addr_t is 64-bit. Storing this constant
in u32 leads to truncation, and further call to dma_mapping_error()
fails to notice the error.

Fix that by storing result of dma_map_single() in a dma_addr_t
variable.

Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper")
Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 8649b3e90edb2..0e3731f50fc28 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1949,7 +1949,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct ravb_tstamp_skb *ts_skb;
 	struct ravb_tx_desc *desc;
 	unsigned long flags;
-	u32 dma_addr;
+	dma_addr_t dma_addr;
 	void *buffer;
 	u32 entry;
 	u32 len;
-- 
GitLab


From fdfd6dde4328635861db029f6fdb649e17350526 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sun, 14 Jan 2024 15:17:18 +0900
Subject: [PATCH 2691/4076] ksmbd: update feature status in documentation

Update ksmbd feature status in documentation file.
 - add support for v2 lease feature and SMB3 CCM/GCM256 encryption.
 - add planned compression, quic, gmac signing features.

Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 Documentation/filesystems/smb/ksmbd.rst | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/Documentation/filesystems/smb/ksmbd.rst b/Documentation/filesystems/smb/ksmbd.rst
index 7bed96d794fc2..6b30e43a0d11f 100644
--- a/Documentation/filesystems/smb/ksmbd.rst
+++ b/Documentation/filesystems/smb/ksmbd.rst
@@ -73,15 +73,14 @@ Auto Negotiation               Supported.
 Compound Request               Supported.
 Oplock Cache Mechanism         Supported.
 SMB2 leases(v1 lease)          Supported.
-Directory leases(v2 lease)     Planned for future.
+Directory leases(v2 lease)     Supported.
 Multi-credits                  Supported.
 NTLM/NTLMv2                    Supported.
 HMAC-SHA256 Signing            Supported.
 Secure negotiate               Supported.
 Signing Update                 Supported.
 Pre-authentication integrity   Supported.
-SMB3 encryption(CCM, GCM)      Supported. (CCM and GCM128 supported, GCM256 in
-                               progress)
+SMB3 encryption(CCM, GCM)      Supported. (CCM/GCM128 and CCM/GCM256 supported)
 SMB direct(RDMA)               Supported.
 SMB3 Multi-channel             Partially Supported. Planned to implement
                                replay/retry mechanisms for future.
@@ -112,6 +111,10 @@ DCE/RPC support                Partially Supported. a few calls(NetShareEnumAll,
                                for Witness protocol e.g.)
 ksmbd/nfsd interoperability    Planned for future. The features that ksmbd
                                support are Leases, Notify, ACLs and Share modes.
+SMB3.1.1 Compression           Planned for future.
+SMB3.1.1 over QUIC             Planned for future.
+Signing/Encryption over RDMA   Planned for future.
+SMB3.1.1 GMAC signing support  Planned for future.
 ============================== =================================================
 
 
-- 
GitLab


From 92e470163d96df8db6c4fa0f484e4a229edb903d Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 13 Jan 2024 15:11:41 +0900
Subject: [PATCH 2692/4076] ksmbd: validate mech token in session setup

If client send invalid mech token in session setup request, ksmbd
validate and make the error if it is invalid.

Cc: stable@vger.kernel.org
Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-22890
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/asn1.c       |  5 +++++
 fs/smb/server/connection.h |  1 +
 fs/smb/server/smb2pdu.c    | 22 +++++++++++++++++-----
 3 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/fs/smb/server/asn1.c b/fs/smb/server/asn1.c
index 4a4b2b03ff33d..b931a99ab9c85 100644
--- a/fs/smb/server/asn1.c
+++ b/fs/smb/server/asn1.c
@@ -214,10 +214,15 @@ static int ksmbd_neg_token_alloc(void *context, size_t hdrlen,
 {
 	struct ksmbd_conn *conn = context;
 
+	if (!vlen)
+		return -EINVAL;
+
 	conn->mechToken = kmemdup_nul(value, vlen, GFP_KERNEL);
 	if (!conn->mechToken)
 		return -ENOMEM;
 
+	conn->mechTokenLen = (unsigned int)vlen;
+
 	return 0;
 }
 
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 3c005246a32e8..342f935f57705 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -88,6 +88,7 @@ struct ksmbd_conn {
 	__u16				dialect;
 
 	char				*mechToken;
+	unsigned int			mechTokenLen;
 
 	struct ksmbd_conn_ops	*conn_ops;
 
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 3143819935dca..ba7a72a6a4f45 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -1414,7 +1414,10 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn,
 	char *name;
 	unsigned int name_off, name_len, secbuf_len;
 
-	secbuf_len = le16_to_cpu(req->SecurityBufferLength);
+	if (conn->use_spnego && conn->mechToken)
+		secbuf_len = conn->mechTokenLen;
+	else
+		secbuf_len = le16_to_cpu(req->SecurityBufferLength);
 	if (secbuf_len < sizeof(struct authenticate_message)) {
 		ksmbd_debug(SMB, "blob len %d too small\n", secbuf_len);
 		return NULL;
@@ -1505,7 +1508,10 @@ static int ntlm_authenticate(struct ksmbd_work *work,
 		struct authenticate_message *authblob;
 
 		authblob = user_authblob(conn, req);
-		sz = le16_to_cpu(req->SecurityBufferLength);
+		if (conn->use_spnego && conn->mechToken)
+			sz = conn->mechTokenLen;
+		else
+			sz = le16_to_cpu(req->SecurityBufferLength);
 		rc = ksmbd_decode_ntlmssp_auth_blob(authblob, sz, conn, sess);
 		if (rc) {
 			set_user_flag(sess->user, KSMBD_USER_FLAG_BAD_PASSWORD);
@@ -1778,8 +1784,7 @@ int smb2_sess_setup(struct ksmbd_work *work)
 
 	negblob_off = le16_to_cpu(req->SecurityBufferOffset);
 	negblob_len = le16_to_cpu(req->SecurityBufferLength);
-	if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) ||
-	    negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) {
+	if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer)) {
 		rc = -EINVAL;
 		goto out_err;
 	}
@@ -1788,8 +1793,15 @@ int smb2_sess_setup(struct ksmbd_work *work)
 			negblob_off);
 
 	if (decode_negotiation_token(conn, negblob, negblob_len) == 0) {
-		if (conn->mechToken)
+		if (conn->mechToken) {
 			negblob = (struct negotiate_message *)conn->mechToken;
+			negblob_len = conn->mechTokenLen;
+		}
+	}
+
+	if (negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) {
+		rc = -EINVAL;
+		goto out_err;
 	}
 
 	if (server_conf.auth_mechs & conn->auth_mechs) {
-- 
GitLab


From 38d20c62903d669693a1869aa68c4dd5674e2544 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 13 Jan 2024 15:30:07 +0900
Subject: [PATCH 2693/4076] ksmbd: fix UAF issue in ksmbd_tcp_new_connection()

The race is between the handling of a new TCP connection and
its disconnection. It leads to UAF on `struct tcp_transport` in
ksmbd_tcp_new_connection() function.

Cc: stable@vger.kernel.org
Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-22991
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/connection.c     |  6 ------
 fs/smb/server/connection.h     |  1 -
 fs/smb/server/transport_rdma.c | 11 ++++++-----
 fs/smb/server/transport_tcp.c  | 13 +++++++------
 4 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index d311c2ee10bd7..09e1e7771592f 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -416,13 +416,7 @@ static void stop_sessions(void)
 again:
 	down_read(&conn_list_lock);
 	list_for_each_entry(conn, &conn_list, conns_list) {
-		struct task_struct *task;
-
 		t = conn->transport;
-		task = t->handler;
-		if (task)
-			ksmbd_debug(CONN, "Stop session handler %s/%d\n",
-				    task->comm, task_pid_nr(task));
 		ksmbd_conn_set_exiting(conn);
 		if (t->ops->shutdown) {
 			up_read(&conn_list_lock);
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 342f935f57705..0e04cf8b1d896 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -135,7 +135,6 @@ struct ksmbd_transport_ops {
 struct ksmbd_transport {
 	struct ksmbd_conn		*conn;
 	struct ksmbd_transport_ops	*ops;
-	struct task_struct		*handler;
 };
 
 #define KSMBD_TCP_RECV_TIMEOUT	(7 * HZ)
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index c5629a68c8b73..8faa25c6e129b 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -2039,6 +2039,7 @@ static bool rdma_frwr_is_supported(struct ib_device_attr *attrs)
 static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id)
 {
 	struct smb_direct_transport *t;
+	struct task_struct *handler;
 	int ret;
 
 	if (!rdma_frwr_is_supported(&new_cm_id->device->attrs)) {
@@ -2056,11 +2057,11 @@ static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id)
 	if (ret)
 		goto out_err;
 
-	KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop,
-					      KSMBD_TRANS(t)->conn, "ksmbd:r%u",
-					      smb_direct_port);
-	if (IS_ERR(KSMBD_TRANS(t)->handler)) {
-		ret = PTR_ERR(KSMBD_TRANS(t)->handler);
+	handler = kthread_run(ksmbd_conn_handler_loop,
+			      KSMBD_TRANS(t)->conn, "ksmbd:r%u",
+			      smb_direct_port);
+	if (IS_ERR(handler)) {
+		ret = PTR_ERR(handler);
 		pr_err("Can't start thread\n");
 		goto out_err;
 	}
diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index eff7a1d793f00..9d4222154dcc0 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -185,6 +185,7 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk)
 	struct sockaddr *csin;
 	int rc = 0;
 	struct tcp_transport *t;
+	struct task_struct *handler;
 
 	t = alloc_transport(client_sk);
 	if (!t) {
@@ -199,13 +200,13 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk)
 		goto out_error;
 	}
 
-	KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop,
-					      KSMBD_TRANS(t)->conn,
-					      "ksmbd:%u",
-					      ksmbd_tcp_get_port(csin));
-	if (IS_ERR(KSMBD_TRANS(t)->handler)) {
+	handler = kthread_run(ksmbd_conn_handler_loop,
+			      KSMBD_TRANS(t)->conn,
+			      "ksmbd:%u",
+			      ksmbd_tcp_get_port(csin));
+	if (IS_ERR(handler)) {
 		pr_err("cannot start conn thread\n");
-		rc = PTR_ERR(KSMBD_TRANS(t)->handler);
+		rc = PTR_ERR(handler);
 		free_transport(t);
 	}
 	return rc;
-- 
GitLab


From 34d946b723b53488ab39d8ac540ddf9db255317a Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 9 Jan 2024 00:25:48 -0500
Subject: [PATCH 2694/4076] i3c: master: fix kernel-doc check warning

Fix warning found by
	'scripts/kernel-doc -v -none include/linux/i3c/master.h'

include/linux/i3c/master.h:457: warning: Function parameter or member 'enable_hotjoin' not described in 'i3c_master_controller_ops'
include/linux/i3c/master.h:457: warning: Function parameter or member 'disable_hotjoin' not described in 'i3c_master_controller_ops'
include/linux/i3c/master.h:499: warning: Function parameter or member 'hotjoin' not described in 'i3c_master_controller'

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20240109052548.2128133-1-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/master.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 1ecd73b17ff5d..0ca27dd869561 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -433,6 +433,8 @@ struct i3c_bus {
  *		      for a future IBI
  *		      This method is mandatory only if ->request_ibi is not
  *		      NULL.
+ * @enable_hotjoin: enable hot join event detect.
+ * @disable_hotjoin: disable hot join event detect.
  */
 struct i3c_master_controller_ops {
 	int (*bus_init)(struct i3c_master_controller *master);
@@ -474,6 +476,7 @@ struct i3c_master_controller_ops {
  * @ops: master operations. See &struct i3c_master_controller_ops
  * @secondary: true if the master is a secondary master
  * @init_done: true when the bus initialization is done
+ * @hotjoin: true if the master support hotjoin
  * @boardinfo.i3c: list of I3C  boardinfo objects
  * @boardinfo.i2c: list of I2C boardinfo objects
  * @boardinfo: board-level information attached to devices connected on the bus
-- 
GitLab


From 4fa0888f6f3e6a67cac5afafb23e33f8222cfdd0 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Sun, 14 Jan 2024 23:52:25 +0100
Subject: [PATCH 2695/4076] i3c: document hotjoin sysfs entry

The hotjoin syfs entry allows to enable or disable Hot-Join on the Current
Controller of the I3C Bus.

Link: https://lore.kernel.org/r/20240114225232.140860-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 Documentation/ABI/testing/sysfs-bus-i3c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-bus-i3c b/Documentation/ABI/testing/sysfs-bus-i3c
index e5248fd67a563..c812ab180ff40 100644
--- a/Documentation/ABI/testing/sysfs-bus-i3c
+++ b/Documentation/ABI/testing/sysfs-bus-i3c
@@ -88,6 +88,21 @@ Description:
 		This entry describes the HDRCAP of the master controller
 		driving the bus.
 
+What:		/sys/bus/i3c/devices/i3c-<bus-id>/hotjoin
+KernelVersion:  6.8
+Contact:	linux-i3c@vger.kernel.org
+Description:
+		I3C’s Hot-Join mechanism allows an I3C Device to inform the
+		Active Controller that a newly-joined Target is present on the
+		I3C Bus and is ready to receive a Dynamic Address, in order to
+		become fully functional on the Bus. Hot-Join is used when the
+		Target is mounted on the same I3C bus and remains depowered
+		until needed or until the Target is physically inserted into the
+		I3C bus
+
+		This entry allows to enable or disable Hot-join of the Current
+		Controller driving the bus.
+
 What:		/sys/bus/i3c/devices/i3c-<bus-id>/<bus-id>-<device-pid>
 KernelVersion:  5.0
 Contact:	linux-i3c@vger.kernel.org
-- 
GitLab


From 77bebd186442a7d703b796784db7495129cc3e70 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Mon, 15 Jan 2024 10:24:54 +0900
Subject: [PATCH 2696/4076] ksmbd: only v2 leases handle the directory

When smb2 leases is disable, ksmbd can send oplock break notification
and cause wait oplock break ack timeout. It may appear like hang when
accessing a directory. This patch make only v2 leases handle the
directory.

Cc: stable@vger.kernel.org
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/oplock.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 001926d3b348c..53dfaac425c68 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -1197,6 +1197,12 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid,
 	bool prev_op_has_lease;
 	__le32 prev_op_state = 0;
 
+	/* Only v2 leases handle the directory */
+	if (S_ISDIR(file_inode(fp->filp)->i_mode)) {
+		if (!lctx || lctx->version != 2)
+			return 0;
+	}
+
 	opinfo = alloc_opinfo(work, pid, tid);
 	if (!opinfo)
 		return -ENOMEM;
-- 
GitLab


From 205e18c13545ab43cc4fe4930732b4feef551198 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Wed, 10 Jan 2024 11:14:05 +1000
Subject: [PATCH 2697/4076] nouveau/gsp: handle engines in runl without
 nonstall interrupts.

It appears on TU106 GPUs (2070), that some of the nvdec engines
are in the runlist but have no valid nonstall interrupt, nouveau
didn't handle that too well.

This should let nouveau/gsp work on those.

Cc: stable@vger.kernel.org # v6.7+
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://lore.kernel.org/all/20240110011826.3996289-1-airlied@gmail.com/
---
 drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c | 4 ++++
 drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c  | 2 +-
 drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c   | 8 ++------
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
index c8ce7ff187135..e74493a4569ed 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
@@ -550,6 +550,10 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo)
 		struct nvkm_engn *engn = list_first_entry(&runl->engns, typeof(*engn), head);
 
 		runl->nonstall.vector = engn->func->nonstall(engn);
+
+		/* if no nonstall vector just keep going */
+		if (runl->nonstall.vector == -1)
+			continue;
 		if (runl->nonstall.vector < 0) {
 			RUNL_ERROR(runl, "nonstall %d", runl->nonstall.vector);
 			return runl->nonstall.vector;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
index d088e636edc31..de2ebe8f21348 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
@@ -350,7 +350,7 @@ r535_engn_nonstall(struct nvkm_engn *engn)
 	int ret;
 
 	ret = nvkm_gsp_intr_nonstall(subdev->device->gsp, subdev->type, subdev->inst);
-	WARN_ON(ret < 0);
+	WARN_ON(ret == -ENOENT);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
index 04bceaa28a197..da1bebb896f7f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
@@ -25,12 +25,8 @@ int
 nvkm_gsp_intr_nonstall(struct nvkm_gsp *gsp, enum nvkm_subdev_type type, int inst)
 {
 	for (int i = 0; i < gsp->intr_nr; i++) {
-		if (gsp->intr[i].type == type && gsp->intr[i].inst == inst) {
-			if (gsp->intr[i].nonstall != ~0)
-				return gsp->intr[i].nonstall;
-
-			return -EINVAL;
-		}
+		if (gsp->intr[i].type == type && gsp->intr[i].inst == inst)
+			return gsp->intr[i].nonstall;
 	}
 
 	return -ENOENT;
-- 
GitLab


From 7c65aa3cc072cee76f577262fbe381a111a98774 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 13 Jan 2024 20:46:42 -0800
Subject: [PATCH 2698/4076] dma-debug: fix kernel-doc warnings

Update the kernel-doc comments to catch up with the code changes and
fix the kernel-doc warnings:

debug.c:83: warning: Excess struct member 'stacktrace' description in 'dma_debug_entry'
debug.c:83: warning: Function parameter or struct member 'stack_len' not described in 'dma_debug_entry'
debug.c:83: warning: Function parameter or struct member 'stack_entries' not described in 'dma_debug_entry'

Fixes: 746017ed8d4d ("dma/debug: Simplify stracktrace retrieval")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: iommu@lists.linux.dev
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/debug.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 3de494375b7b3..08b7f84b76f9e 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -62,7 +62,8 @@ enum map_err_types {
  * @pfn: page frame of the start address
  * @offset: offset of mapping relative to pfn
  * @map_err_type: track whether dma_mapping_error() was checked
- * @stacktrace: support backtraces when a violation is detected
+ * @stack_len: number of backtrace entries in @stack_entries
+ * @stack_entries: stack of backtrace history
  */
 struct dma_debug_entry {
 	struct list_head list;
-- 
GitLab


From c8fb5a52b977ef91dc9342e556c63b9602065c8a Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 12 Jan 2024 09:55:25 +0300
Subject: [PATCH 2699/4076] gpio: rtd: Fix signedness bug in probe

The "data->irqs[]" array holds unsigned int so this error handling will
not work correctly.

Fixes: eee636bff0dc ("gpio: rtd: Add support for Realtek DHC(Digital Home Center) RTD SoCs")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-rtd.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpio/gpio-rtd.c b/drivers/gpio/gpio-rtd.c
index a7939bd0aa566..bf7f008f58d70 100644
--- a/drivers/gpio/gpio-rtd.c
+++ b/drivers/gpio/gpio-rtd.c
@@ -525,18 +525,21 @@ static int rtd_gpio_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct gpio_irq_chip *irq_chip;
 	struct rtd_gpio *data;
+	int ret;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	data->irqs[0] = platform_get_irq(pdev, 0);
-	if (data->irqs[0] < 0)
-		return data->irqs[0];
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		return ret;
+	data->irqs[0] = ret;
 
-	data->irqs[1] = platform_get_irq(pdev, 1);
-	if (data->irqs[1] < 0)
-		return data->irqs[1];
+	ret = platform_get_irq(pdev, 1);
+	if (ret < 0)
+		return ret;
+	data->irqs[1] = ret;
 
 	data->info = device_get_match_data(dev);
 	if (!data->info)
-- 
GitLab


From 314c020c4ed3de72b15603eb6892250bc4b51702 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Fri, 12 Jan 2024 12:32:58 +0100
Subject: [PATCH 2700/4076] dt-bindings: gpio: xilinx: Fix node address in gpio

Node address doesn't match reg property which is not correct.

Fixes: ba96b2e7974b ("dt-bindings: gpio: gpio-xilinx: Convert Xilinx axi gpio binding to YAML")
Signed-off-by: Michal Simek <michal.simek@amd.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml
index c1060e5fcef3a..d3d8a2e143ed2 100644
--- a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml
+++ b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml
@@ -126,7 +126,7 @@ examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
 
-        gpio@e000a000 {
+        gpio@a0020000 {
             compatible = "xlnx,xps-gpio-1.00.a";
             reg = <0xa0020000 0x10000>;
             #gpio-cells = <2>;
-- 
GitLab


From d460e9c2075164e9b1fa9c4c95f8c05517bd8752 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Fri, 12 Jan 2024 12:24:04 +0800
Subject: [PATCH 2701/4076] gpio: mlxbf3: add an error code check in
 mlxbf3_gpio_probe

Clang static checker warning: Value stored to 'ret' is never read.
bgpio_init() returns error code if failed, it's better to add this
check.

Fixes: cd33f216d241 ("gpio: mlxbf3: Add gpio driver support")
Signed-off-by: Su Hui <suhui@nfschina.com>
[Bartosz: add the Fixes: tag]
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-mlxbf3.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c
index 7a3e1760fc5b7..d5906d419b0ab 100644
--- a/drivers/gpio/gpio-mlxbf3.c
+++ b/drivers/gpio/gpio-mlxbf3.c
@@ -215,6 +215,8 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
 			gs->gpio_clr_io + MLXBF_GPIO_FW_DATA_OUT_CLEAR,
 			gs->gpio_set_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_SET,
 			gs->gpio_clr_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_CLEAR, 0);
+	if (ret)
+		return dev_err_probe(dev, ret, "%s: bgpio_init() failed", __func__);
 
 	gc->request = gpiochip_generic_request;
 	gc->free = gpiochip_generic_free;
-- 
GitLab


From 3787ffdd13de81ba406e5b42c6c24f823395ba5e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 12 Jan 2024 18:10:00 +0100
Subject: [PATCH 2702/4076] ALSA: scarlett2: Fix yet more -Wformat-truncation
 warnings

The recent code change introduced a few false-positive compile
warnings with -Wformat-trucation again.  Suppress them by replacing
snprintf() with scnprintf().

Fixes: 0a995e38dc44 ("ALSA: scarlett2: Add support for software-controllable input gain")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401062344.AzZCYlpa-lkp@intel.com/
Link: https://lore.kernel.org/r/20240112171000.31855-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_scarlett2.c | 42 ++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index 1de3ddc50eb6a..6de605a601e5f 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -5361,9 +5361,9 @@ static int scarlett2_add_line_out_ctls(struct usb_mixer_interface *mixer)
 			if (private->vol_sw_hw_switch[index])
 				scarlett2_vol_ctl_set_writable(mixer, i, 0);
 
-			snprintf(s, sizeof(s),
-				 "Line Out %02d Volume Control Playback Enum",
-				 i + 1);
+			scnprintf(s, sizeof(s),
+				  "Line Out %02d Volume Control Playback Enum",
+				  i + 1);
 			err = scarlett2_add_new_ctl(mixer,
 						    &scarlett2_sw_hw_enum_ctl,
 						    i, 1, s,
@@ -5406,8 +5406,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 
 	/* Add input level (line/inst) controls */
 	for (i = 0; i < info->level_input_count; i++) {
-		snprintf(s, sizeof(s), fmt, i + 1 + info->level_input_first,
-			 "Level", "Enum");
+		scnprintf(s, sizeof(s), fmt, i + 1 + info->level_input_first,
+			  "Level", "Enum");
 		err = scarlett2_add_new_ctl(mixer, &scarlett2_level_enum_ctl,
 					    i, 1, s, &private->level_ctls[i]);
 		if (err < 0)
@@ -5416,7 +5416,7 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 
 	/* Add input pad controls */
 	for (i = 0; i < info->pad_input_count; i++) {
-		snprintf(s, sizeof(s), fmt, i + 1, "Pad", "Switch");
+		scnprintf(s, sizeof(s), fmt, i + 1, "Pad", "Switch");
 		err = scarlett2_add_new_ctl(mixer, &scarlett2_pad_ctl,
 					    i, 1, s, &private->pad_ctls[i]);
 		if (err < 0)
@@ -5425,8 +5425,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 
 	/* Add input air controls */
 	for (i = 0; i < info->air_input_count; i++) {
-		snprintf(s, sizeof(s), fmt, i + 1 + info->air_input_first,
-			 "Air", info->air_option ? "Enum" : "Switch");
+		scnprintf(s, sizeof(s), fmt, i + 1 + info->air_input_first,
+			  "Air", info->air_option ? "Enum" : "Switch");
 		err = scarlett2_add_new_ctl(
 			mixer, &scarlett2_air_ctl[info->air_option],
 			i, 1, s, &private->air_ctls[i]);
@@ -5481,9 +5481,9 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 
 		for (i = 0; i < info->gain_input_count; i++) {
 			if (i % 2) {
-				snprintf(s, sizeof(s),
-					 "Line In %d-%d Link Capture Switch",
-					 i, i + 1);
+				scnprintf(s, sizeof(s),
+					  "Line In %d-%d Link Capture Switch",
+					  i, i + 1);
 				err = scarlett2_add_new_ctl(
 					mixer, &scarlett2_input_link_ctl,
 					i / 2, 1, s,
@@ -5492,30 +5492,30 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer)
 					return err;
 			}
 
-			snprintf(s, sizeof(s), fmt, i + 1,
-				 "Gain", "Volume");
+			scnprintf(s, sizeof(s), fmt, i + 1,
+				  "Gain", "Volume");
 			err = scarlett2_add_new_ctl(
 				mixer, &scarlett2_input_gain_ctl,
 				i, 1, s, &private->input_gain_ctls[i]);
 			if (err < 0)
 				return err;
 
-			snprintf(s, sizeof(s), fmt, i + 1,
-				 "Autogain", "Switch");
+			scnprintf(s, sizeof(s), fmt, i + 1,
+				  "Autogain", "Switch");
 			err = scarlett2_add_new_ctl(
 				mixer, &scarlett2_autogain_switch_ctl,
 				i, 1, s, &private->autogain_ctls[i]);
 			if (err < 0)
 				return err;
 
-			snprintf(s, sizeof(s), fmt, i + 1,
-				 "Autogain Status", "Enum");
+			scnprintf(s, sizeof(s), fmt, i + 1,
+				  "Autogain Status", "Enum");
 			err = scarlett2_add_new_ctl(
 				mixer, &scarlett2_autogain_status_ctl,
 				i, 1, s, &private->autogain_status_ctls[i]);
 
-			snprintf(s, sizeof(s), fmt, i + 1,
-				 "Safe", "Switch");
+			scnprintf(s, sizeof(s), fmt, i + 1,
+				  "Safe", "Switch");
 			err = scarlett2_add_new_ctl(
 				mixer, &scarlett2_safe_ctl,
 				i, 1, s, &private->safe_ctls[i]);
@@ -5902,8 +5902,8 @@ static int scarlett2_add_direct_monitor_ctls(struct usb_mixer_interface *mixer)
 			for (k = 0; k < private->num_mix_in; k++, index++) {
 				char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
 
-				snprintf(name, sizeof(name), format,
-					 mix_type, 'A' + j, k + 1);
+				scnprintf(name, sizeof(name), format,
+					  mix_type, 'A' + j, k + 1);
 
 				err = scarlett2_add_new_ctl(
 					mixer, &scarlett2_monitor_mix_ctl,
-- 
GitLab


From 19adbe96d3e3c2188ad5838b936550e073cba54d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 13 Jan 2024 17:08:54 +0100
Subject: [PATCH 2703/4076] ALSA: hda: generic: Remove obsolete call to
 ledtrig_audio_get

Since 64f67b5240db ("leds: trigger: audio: Add an activate callback to
ensure the initial brightness is set") the audio triggers have an
activate callback which sets the LED brightness as soon as the
(default) trigger is bound to the LED device. So we can remove the
call to ledtrig_audio_get.

Positive side effect: We have no code dependency to ledtrig-audio any
longer, therefore, if built as module, it's no longer loaded if not
needed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/3dc9167d-fb33-43a6-baa6-dbef8b5da7b9@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_generic.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index bf685d01259d3..de2a3d08c73c1 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -3946,7 +3946,6 @@ static int create_mute_led_cdev(struct hda_codec *codec,
 	cdev->max_brightness = 1;
 	cdev->default_trigger = micmute ? "audio-micmute" : "audio-mute";
 	cdev->brightness_set_blocking = callback;
-	cdev->brightness = ledtrig_audio_get(idx);
 	cdev->flags = LED_CORE_SUSPENDRESUME;
 
 	err = led_classdev_register(&codec->core.dev, cdev);
-- 
GitLab


From 1f1626ac0428820f998245478610f452650bcab5 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Sun, 14 Jan 2024 00:33:45 +0300
Subject: [PATCH 2704/4076] drm/ttm: fix ttm pool initialization for
 no-dma-device drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

QXL driver doesn't use any device for DMA mappings or allocations so
dev_to_node() will panic inside ttm_device_init() on NUMA systems:

general protection fault, probably for non-canonical address 0xdffffc000000007a: 0000 [#1] PREEMPT SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x00000000000003d0-0x00000000000003d7]
CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.7.0+ #9
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014
RIP: 0010:ttm_device_init+0x10e/0x340
Call Trace:
 <TASK>
 qxl_ttm_init+0xaa/0x310
 qxl_device_init+0x1071/0x2000
 qxl_pci_probe+0x167/0x3f0
 local_pci_probe+0xe1/0x1b0
 pci_device_probe+0x29d/0x790
 really_probe+0x251/0x910
 __driver_probe_device+0x1ea/0x390
 driver_probe_device+0x4e/0x2e0
 __driver_attach+0x1e3/0x600
 bus_for_each_dev+0x12d/0x1c0
 bus_add_driver+0x25a/0x590
 driver_register+0x15c/0x4b0
 qxl_pci_driver_init+0x67/0x80
 do_one_initcall+0xf5/0x5d0
 kernel_init_freeable+0x637/0xb10
 kernel_init+0x1c/0x2e0
 ret_from_fork+0x48/0x80
 ret_from_fork_asm+0x1b/0x30
 </TASK>
Modules linked in:
---[ end trace 0000000000000000 ]---
RIP: 0010:ttm_device_init+0x10e/0x340

Fall back to NUMA_NO_NODE if there is no device for DMA.

Found by Linux Verification Center (linuxtesting.org).

Fixes: b0a7ce53d494 ("drm/ttm: Schedule delayed_delete worker closer")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Link: https://patchwork.freedesktop.org/patch/msgid/20240113213347.9562-1-pchelkin@ispras.ru
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/ttm/ttm_device.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index f5187b384ae9a..4130945052ed2 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -195,7 +195,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 		    bool use_dma_alloc, bool use_dma32)
 {
 	struct ttm_global *glob = &ttm_glob;
-	int ret;
+	int ret, nid;
 
 	if (WARN_ON(vma_manager == NULL))
 		return -EINVAL;
@@ -215,7 +215,12 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 
 	ttm_sys_man_init(bdev);
 
-	ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32);
+	if (dev)
+		nid = dev_to_node(dev);
+	else
+		nid = NUMA_NO_NODE;
+
+	ttm_pool_init(&bdev->pool, dev, nid, use_dma_alloc, use_dma32);
 
 	bdev->vma_manager = vma_manager;
 	spin_lock_init(&bdev->lru_lock);
-- 
GitLab


From 848c8f563dadfdf01358b001ef7c9afe2a6ece8f Mon Sep 17 00:00:00 2001
From: Rander Wang <rander.wang@intel.com>
Date: Mon, 15 Jan 2024 11:22:08 +0200
Subject: [PATCH 2705/4076] ASoC: SOF: ipc4-pcm: remove log message for LLP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

LLP is supported by I2S and SDW platforms but not supported by HDA
platforms. This log is used to notify developer current LLP status
for current device. Since above case is known to developers, the log
is unnecessary and should be removed.

Fixes: 7cb19007baba ("ASoC: SOF: ipc4-pcm: add hw_params")
Signed-off-by: Rander Wang <rander.wang@intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://msgid.link/r/20240115092209.7184-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-pcm.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 39039a647cca3..85d3f390e4b29 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -768,10 +768,8 @@ static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pc
 	info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_evad_reading_slot) +
 					sdev->fw_info_box.offset;
 	sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot));
-	if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id) {
-		dev_info(sdev->dev, "no llp found, fall back to default HDA path");
+	if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id)
 		info->llp_offset = 0;
-	}
 }
 
 static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component,
-- 
GitLab


From ab09fb9c629ed3aaea6a82467f08595dbc549726 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Mon, 15 Jan 2024 11:22:09 +0200
Subject: [PATCH 2706/4076] ASoC: SOF: ipc4-loader: remove the CPC check
 warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Warnings related to missing data in firmware manifest have
proven to be too verbose. This relates to description of
DSP module cost expressed in cycles per chunk (CPC). If
a matching value is not found in the manifest, kernel will
pass a zero value and DSP firmware will use a conservative
value in its place.

Downgrade the warnings to dev_dbg().

Fixes: d8a2c9879349 ("ASoC: SOF: ipc4-loader/topology: Query the CPC value from manifest")
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://msgid.link/r/20240115092209.7184-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-loader.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/sound/soc/sof/ipc4-loader.c b/sound/soc/sof/ipc4-loader.c
index 3539b0a66e1be..c79479afa8d0d 100644
--- a/sound/soc/sof/ipc4-loader.c
+++ b/sound/soc/sof/ipc4-loader.c
@@ -482,13 +482,10 @@ void sof_ipc4_update_cpc_from_manifest(struct snd_sof_dev *sdev,
 		msg = "No CPC match in the firmware file's manifest";
 
 no_cpc:
-	dev_warn(sdev->dev, "%s (UUID: %pUL): %s (ibs/obs: %u/%u)\n",
-		 fw_module->man4_module_entry.name,
-		 &fw_module->man4_module_entry.uuid, msg, basecfg->ibs,
-		 basecfg->obs);
-	dev_warn_once(sdev->dev, "Please try to update the firmware.\n");
-	dev_warn_once(sdev->dev, "If the issue persists, file a bug at\n");
-	dev_warn_once(sdev->dev, "https://github.com/thesofproject/sof/issues/\n");
+	dev_dbg(sdev->dev, "%s (UUID: %pUL): %s (ibs/obs: %u/%u)\n",
+		fw_module->man4_module_entry.name,
+		&fw_module->man4_module_entry.uuid, msg, basecfg->ibs,
+		basecfg->obs);
 }
 
 const struct sof_ipc_fw_loader_ops ipc4_loader_ops = {
-- 
GitLab


From 521277d12b5a75982d4f642d2ee22db8d7f986dd Mon Sep 17 00:00:00 2001
From: Nicky Chorley <ndchorley@gmail.com>
Date: Sun, 14 Jan 2024 19:10:56 +0000
Subject: [PATCH 2707/4076] block: Correct a documentation comment in
 blk-cgroup.c

Commit 99e603874366
("blk-cgroup: pass a gendisk to the blkg allocation helpers") changed
blkg_alloc() to take a struct gendisk instead of a struct request_queue,
but the documentation comment still referred to q.

So, update that comment to refer to disk instead and fix a typo.

Signed-off-by: Nicky Chorley <ndchorley@gmail.com>
Link: https://lore.kernel.org/r/20240114191056.6992-1-ndchorley@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e303fd3173137..ff93c385ba5af 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -300,7 +300,7 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
  * @disk: gendisk the new blkg is associated with
  * @gfp_mask: allocation mask to use
  *
- * Allocate a new blkg assocating @blkcg and @q.
+ * Allocate a new blkg associating @blkcg and @disk.
  */
 static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 				   gfp_t gfp_mask)
-- 
GitLab


From 5c7fa5c8ad79a1d7cc9f59636e2f99e8b5471248 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Mon, 15 Jan 2024 22:56:26 +0800
Subject: [PATCH 2708/4076] sbitmap: remove stale comment in
 sbq_calc_wake_batch

After commit 106397376c036 ("sbitmap: fix batching wakeup"), we may wake
up more than one queue for each batch. Just remove stale comment that
we wake up only one queue for each batch.

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Link: https://lore.kernel.org/r/20240115145626.665562-1-shikemeng@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 lib/sbitmap.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index d0a5081dfd122..92c6b1fd89893 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -388,11 +388,6 @@ static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
 	unsigned int shallow_depth;
 
 	/*
-	 * For each batch, we wake up one queue. We need to make sure that our
-	 * batch size is small enough that the full depth of the bitmap,
-	 * potentially limited by a shallow depth, is enough to wake up all of
-	 * the queues.
-	 *
 	 * Each full word of the bitmap has bits_per_word bits, and there might
 	 * be a partial word. There are depth / bits_per_word full words and
 	 * depth % bits_per_word bits left over. In bitwise arithmetic:
-- 
GitLab


From 7b1a8a5fcee4a85be1f540ac0e09761d421e562d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Roberto=20de=20Souza?= <jose.souza@intel.com>
Date: Thu, 4 Jan 2024 08:18:32 -0800
Subject: [PATCH 2709/4076] drm/xe: Fix definition of intel_wakeref_t
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

i915 defines it as unsigned long so Xe should do the same to avoid
compilation warnings:

  CC [M]  drivers/gpu/drm/i915/i915_gem.o
  CC [M]  drivers/gpu/drm/xe/i915-display/intel_display_power_well.o
In file included from ./include/drm/drm_mm.h:51,
                 from drivers/gpu/drm/xe/xe_bo_types.h:11,
                 from drivers/gpu/drm/xe/xe_bo.h:11,
                 from ./drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h:11,
                 from ./drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h:15,
                 from drivers/gpu/drm/i915/display/intel_display_power.c:8:
drivers/gpu/drm/i915/display/intel_display_power.c: In function ‘print_async_put_domains_state’:
drivers/gpu/drm/i915/display/intel_display_power.c:408:29: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 5 has type ‘int’ [-Wformat=]
  408 |         drm_dbg(&i915->drm, "async_put_wakeref %lu\n",
      |                             ^~~~~~~~~~~~~~~~~~~~~~~~~
  409 |                 power_domains->async_put_wakeref);
      |                 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      |                              |
      |                              int
./include/drm/drm_print.h:410:39: note: in definition of macro ‘drm_dev_dbg’
  410 |         __drm_dev_dbg(NULL, dev, cat, fmt, ##__VA_ARGS__)
      |                                       ^~~
./include/drm/drm_print.h:510:33: note: in expansion of macro ‘drm_dbg_driver’
  510 | #define drm_dbg(drm, fmt, ...)  drm_dbg_driver(drm, fmt, ##__VA_ARGS__)
      |                                 ^~~~~~~~~~~~~~
drivers/gpu/drm/i915/display/intel_display_power.c:408:9: note: in expansion of macro ‘drm_dbg’
  408 |         drm_dbg(&i915->drm, "async_put_wakeref %lu\n",
      |         ^~~~~~~
drivers/gpu/drm/i915/display/intel_display_power.c:408:50: note: format string is defined here
  408 |         drm_dbg(&i915->drm, "async_put_wakeref %lu\n",
      |                                                ~~^
      |                                                  |
      |                                                  long unsigned int
      |                                                %u
  CC [M]  drivers/gpu/drm/i915/i915_gem_evict.o
  CC [M]  drivers/gpu/drm/i915/i915_gem_gtt.o
  CC [M]  drivers/gpu/drm/xe/i915-display/intel_display_trace.o
  CC [M]  drivers/gpu/drm/xe/i915-display/intel_display_wa.o
  CC [M]  drivers/gpu/drm/i915/i915_query.o

Fixes: 44e694958b95 ("drm/xe/display: Implement display support")
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
(cherry picked from commit fdbadf504375886a0320ac6f84c850322a6b32e1)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h b/drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h
index 1c5e30cf10caa..ecb1c07077069 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h
@@ -5,4 +5,4 @@
 
 #include <linux/types.h>
 
-typedef bool intel_wakeref_t;
+typedef unsigned long intel_wakeref_t;
-- 
GitLab


From 56c253daabc8bd9dfbae52c3d9e0dd34977347a6 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 4 Jan 2024 00:00:39 -0800
Subject: [PATCH 2710/4076] drm/xe: Fix exec IOCTL long running exec queue ring
 full condition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The intent is to return -EWOULDBLOCK to the user if a long running exec
queue is full during the exec IOCTL. -EWOULDBLOCK aliases to -EAGAIN
which results in the exec IOCTL doing a retry loop. Fix this by ensuring
the retry loop is broken when returning -EWOULDBLOCK.

Fixes: 8ae8a2e8dd21 ("drm/xe: Long running job update")
Reported-by: Sai Gowtham Ch <sai.gowtham.ch@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Brian Welty <brian.welty@intel.com>
(cherry picked from commit 97d0047cbb17318431eaf37dfe1a6855539340f9)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_exec.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index d30c0d0689bcc..b853feed9ccc1 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -115,7 +115,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct xe_sched_job *job;
 	struct dma_fence *rebind_fence;
 	struct xe_vm *vm;
-	bool write_locked;
+	bool write_locked, skip_retry = false;
 	ktime_t end = 0;
 	int err = 0;
 
@@ -227,7 +227,8 @@ retry:
 	}
 
 	if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
-		err = -EWOULDBLOCK;
+		err = -EWOULDBLOCK;	/* Aliased to -EAGAIN */
+		skip_retry = true;
 		goto err_exec;
 	}
 
@@ -337,7 +338,7 @@ err_unlock_list:
 		up_write(&vm->lock);
 	else
 		up_read(&vm->lock);
-	if (err == -EAGAIN)
+	if (err == -EAGAIN && !skip_retry)
 		goto retry;
 err_syncs:
 	for (i = 0; i < num_syncs; i++)
-- 
GitLab


From 457f4439833487acb18abdd55e95fbb17d43fdca Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 22 Dec 2023 18:59:04 +0100
Subject: [PATCH 2711/4076] drm/xe/vm: Fix an error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If using the VM_BIND_OP_UNMAP_ALL without any bound vmas for the
vm, we will end up dereferencing an uninitialized variable and leak a
bo lock. Fix this.

v2:
- Updated commit message (Lucas De Marchi)

Reported-by: Dafna Hirschfeld <dhirschfeld@habana.ai>
Closes: https://lore.kernel.org/intel-xe/jrwua7ckbiozfcaodx4gg2h4taiuxs53j5zlpf3qzvyhyiyl2d@pbs3plurokrj/
Suggested-by: Dafna Hirschfeld <dhirschfeld@habana.ai>
Fixes: b06d47be7c83 ("drm/xe: Port Xe to GPUVA")
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231222175904.16732-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 9d0c1c5618be02c5acda7e6bbb728007b0632984)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 0cfe7289b97ef..b0e3cab6a5845 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2063,9 +2063,11 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 		if (err)
 			return ERR_PTR(err);
 
-		vm_bo = drm_gpuvm_bo_find(&vm->gpuvm, obj);
-		if (!vm_bo)
-			break;
+		vm_bo = drm_gpuvm_bo_obtain(&vm->gpuvm, obj);
+		if (IS_ERR(vm_bo)) {
+			xe_bo_unlock(bo);
+			return ERR_CAST(vm_bo);
+		}
 
 		ops = drm_gpuvm_bo_unmap_ops_create(vm_bo);
 		drm_gpuvm_bo_put(vm_bo);
-- 
GitLab


From 3ec276d06698189506f508f87c0f4f17c11e0251 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 9 Jan 2024 12:24:02 +0100
Subject: [PATCH 2712/4076] drm/xe: Use __iomem for the regs pointer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The regs pointer points to IO memory. Annotate it properly and
fix the corresponding sparse warning.

Fixes: a4e2f3a299ea ("drm/xe: refactor xe_mmio_probe_tiles to support MMIO extension")
Cc: Koby Elbaz <kelbaz@habana.ai>
Cc: Ofir Bitton <obitton@habana.ai>
Cc: Moti Haimovski <mhaimovski@habana.ai>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240109112405.108136-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit 9d03bf30e78673d827484bbc17a6fd8f5e43a039)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_mmio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index f660cfb79f504..c8c5d74b6e904 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -303,7 +303,7 @@ void xe_mmio_probe_tiles(struct xe_device *xe)
 	u8 id, tile_count = xe->info.tile_count;
 	struct xe_gt *gt = xe_root_mmio_gt(xe);
 	struct xe_tile *tile;
-	void *regs;
+	void __iomem *regs;
 	u32 mtcfg;
 
 	if (tile_count == 1)
-- 
GitLab


From 77232e6a28447c2942558d05f1c3115bdf95a9e7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 9 Jan 2024 12:24:03 +0100
Subject: [PATCH 2713/4076] drm/xe: Annotate xe_mem_region::mapping with
 __iomem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pointer points to IO memory, but the __iomem annotation was
incorrectly placed. Annotate it correctly, update its usage accordingly
and fix the corresponding sparse error.

Fixes: 0887a2e7ab62 ("drm/xe: Make xe_mem_region struct")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: Michael J. Ruhl <michael.j.ruhl@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240109112405.108136-3-thomas.hellstrom@linux.intel.com
(cherry picked from commit 20855b62a30538361e587cfc7c5245f07d4f826a)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c           | 4 ++--
 drivers/gpu/drm/xe/xe_device_types.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 8e4a3b1f6b938..3cd29bd015a02 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -442,7 +442,7 @@ static int xe_ttm_io_mem_reserve(struct ttm_device *bdev,
 
 		if (vram->mapping &&
 		    mem->placement & TTM_PL_FLAG_CONTIGUOUS)
-			mem->bus.addr = (u8 *)vram->mapping +
+			mem->bus.addr = (u8 __force *)vram->mapping +
 				mem->bus.offset;
 
 		mem->bus.offset += vram->io_start;
@@ -734,7 +734,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 			/* Create a new VMAP once kernel BO back in VRAM */
 			if (!ret && resource_is_vram(new_mem)) {
 				struct xe_mem_region *vram = res_to_mem_region(new_mem);
-				void *new_addr = vram->mapping +
+				void __iomem *new_addr = vram->mapping +
 					(new_mem->start << PAGE_SHIFT);
 
 				if (XE_WARN_ON(new_mem->start == XE_BO_INVALID_OFFSET)) {
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index c45ef17b34732..4b38c6bc6c76c 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -97,7 +97,7 @@ struct xe_mem_region {
 	 */
 	resource_size_t actual_physical_size;
 	/** @mapping: pointer to VRAM mappable space */
-	void *__iomem mapping;
+	void __iomem *mapping;
 };
 
 /**
-- 
GitLab


From 5c63e7574739c034e072dea0e0a6fcbe8d538666 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 9 Jan 2024 12:24:04 +0100
Subject: [PATCH 2714/4076] drm/xe: Annotate multiple mmio pointers with
 __iomem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are a couple of pointers pointing to MMIO space. Annotate them
with __iomem and fix the corresponding sparse warnings.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Fixes: 3b0d4a557996 ("drm/xe: Move register MMIO into xe_tile")
Fixes: 399a13323f0d ("drm/xe: add 28-bit address support in struct xe_reg")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Koby Elbaz <kelbaz@habana.ai>
Cc: Ofir Bitton <obitton@habana.ai>
Cc: Moti Haimovski <mhaimovski@habana.ai>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240109112405.108136-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit 9d612ee52c6096bc70d43f54921ba2831ffbf1ad)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_device_types.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 4b38c6bc6c76c..5dc9127a20293 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -146,7 +146,7 @@ struct xe_tile {
 		size_t size;
 
 		/** @regs: pointer to tile's MMIO space (starting with registers) */
-		void *regs;
+		void __iomem *regs;
 	} mmio;
 
 	/**
@@ -159,7 +159,7 @@ struct xe_tile {
 		size_t size;
 
 		/** @regs: pointer to tile's additional MMIO-extension space */
-		void *regs;
+		void __iomem *regs;
 	} mmio_ext;
 
 	/** @mem: memory management info for tile */
@@ -301,7 +301,7 @@ struct xe_device {
 		/** @size: size of MMIO space for device */
 		size_t size;
 		/** @regs: pointer to MMIO space for device */
-		void *regs;
+		void __iomem *regs;
 	} mmio;
 
 	/** @mem: memory info for device */
-- 
GitLab


From 98949068eb559a31f162ab37f56a89bf6c3698ad Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 9 Jan 2024 12:24:05 +0100
Subject: [PATCH 2715/4076] drm/xe: Annotate xe_ttm_stolen_mgr::mapping with
 __iomem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pointer points to IO memory, but the __iomem annotation was
incorrectly placed. Annotate it correctly, update its usage accordingly
and fix the corresponding sparse error.

Fixes: d8b52a02cb40 ("drm/xe: Implement stolen memory.")
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240109112405.108136-5-thomas.hellstrom@linux.intel.com
(cherry picked from commit dcddb6f0b06d454c9a3b2b240a43f0e7310c7f7c)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
index d2b00d0bf1e20..e5d7d5e2bec12 100644
--- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
@@ -31,7 +31,7 @@ struct xe_ttm_stolen_mgr {
 	/* GPU base offset */
 	resource_size_t stolen_base;
 
-	void *__iomem mapping;
+	void __iomem *mapping;
 };
 
 static inline struct xe_ttm_stolen_mgr *
@@ -275,7 +275,7 @@ static int __xe_ttm_stolen_io_mem_reserve_bar2(struct xe_device *xe,
 	drm_WARN_ON(&xe->drm, !(mem->placement & TTM_PL_FLAG_CONTIGUOUS));
 
 	if (mem->placement & TTM_PL_FLAG_CONTIGUOUS && mgr->mapping)
-		mem->bus.addr = (u8 *)mgr->mapping + mem->bus.offset;
+		mem->bus.addr = (u8 __force *)mgr->mapping + mem->bus.offset;
 
 	mem->bus.offset += mgr->io_base;
 	mem->bus.is_iomem = true;
-- 
GitLab


From fef257eb6dcb9f39baee9ac44f064cd796ecfd0b Mon Sep 17 00:00:00 2001
From: Brian Welty <brian.welty@intel.com>
Date: Fri, 5 Jan 2024 11:04:39 -0800
Subject: [PATCH 2716/4076] drm/xe: Fix guc_exec_queue_set_priority
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We need to set q->priority prior to calling guc_exec_queue_add_msg() as
that will call init_policies() and sets the scheduling properties to those
stored in the exec_queue.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Brian Welty <brian.welty@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit b16483f9f8120b530327879fa3ea576e897946da)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 21ac68e3246f8..5de3ac47c4623 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1308,8 +1308,8 @@ static int guc_exec_queue_set_priority(struct xe_exec_queue *q,
 	if (!msg)
 		return -ENOMEM;
 
-	guc_exec_queue_add_msg(q, msg, SET_SCHED_PROPS);
 	q->priority = priority;
+	guc_exec_queue_add_msg(q, msg, SET_SCHED_PROPS);
 
 	return 0;
 }
-- 
GitLab


From 19c02225242498eea9267d444ee1276016368d49 Mon Sep 17 00:00:00 2001
From: Brian Welty <brian.welty@intel.com>
Date: Fri, 5 Jan 2024 11:04:40 -0800
Subject: [PATCH 2717/4076] drm/xe: Fix modifying exec_queue priority in
 xe_migrate_init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After exec_queue has been created, we cannot simply modify q->priority.
This needs to be done by the backend via q->ops.  However in this case,
it would be more efficient to simply pass a flag when creating the
exec_queue and set the desired priority upfront during queue creation.

To that end: new flag EXEC_QUEUE_FLAG_HIGH_PRIORITY is introduced.
The priority field is moved to be with other scheduling properties and
is now exec_queue.sched_props.priority. This is no longer set to initial
value by the backend, but is now set within __xe_exec_queue_create().

Fixes: b4eecedc75c1 ("drm/xe: Fix potential deadlock handling page faults")
Signed-off-by: Brian Welty <brian.welty@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit a8004af338f6b3319476ecbed63ea49bf393fc1f)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c       | 5 +++++
 drivers/gpu/drm/xe/xe_exec_queue_types.h | 6 ++++--
 drivers/gpu/drm/xe/xe_guc_submit.c       | 7 +++----
 drivers/gpu/drm/xe/xe_migrate.c          | 5 ++---
 4 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 44fe8097b7cda..bcfc4127c7c59 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -67,6 +67,11 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
 	q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us;
 	q->sched_props.preempt_timeout_us =
 				hwe->eclass->sched_props.preempt_timeout_us;
+	if (q->flags & EXEC_QUEUE_FLAG_KERNEL &&
+	    q->flags & EXEC_QUEUE_FLAG_HIGH_PRIORITY)
+		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
+	else
+		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
 
 	if (xe_exec_queue_is_parallel(q)) {
 		q->parallel.composite_fence_ctx = dma_fence_context_alloc(1);
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 3d7e704ec3d9f..8d4b7feb8c306 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -52,8 +52,6 @@ struct xe_exec_queue {
 	struct xe_vm *vm;
 	/** @class: class of this exec queue */
 	enum xe_engine_class class;
-	/** @priority: priority of this exec queue */
-	enum xe_exec_queue_priority priority;
 	/**
 	 * @logical_mask: logical mask of where job submitted to exec queue can run
 	 */
@@ -84,6 +82,8 @@ struct xe_exec_queue {
 #define EXEC_QUEUE_FLAG_VM			BIT(4)
 /* child of VM queue for multi-tile VM jobs */
 #define EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD	BIT(5)
+/* kernel exec_queue only, set priority to highest level */
+#define EXEC_QUEUE_FLAG_HIGH_PRIORITY		BIT(6)
 
 	/**
 	 * @flags: flags for this exec queue, should statically setup aside from ban
@@ -142,6 +142,8 @@ struct xe_exec_queue {
 		u32 timeslice_us;
 		/** @preempt_timeout_us: preemption timeout in micro-seconds */
 		u32 preempt_timeout_us;
+		/** @priority: priority of this exec queue */
+		enum xe_exec_queue_priority priority;
 	} sched_props;
 
 	/** @compute: compute exec queue state */
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 5de3ac47c4623..54ffcfcdd41f9 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -421,7 +421,7 @@ static void init_policies(struct xe_guc *guc, struct xe_exec_queue *q)
 {
 	struct exec_queue_policy policy;
 	struct xe_device *xe = guc_to_xe(guc);
-	enum xe_exec_queue_priority prio = q->priority;
+	enum xe_exec_queue_priority prio = q->sched_props.priority;
 	u32 timeslice_us = q->sched_props.timeslice_us;
 	u32 preempt_timeout_us = q->sched_props.preempt_timeout_us;
 
@@ -1231,7 +1231,6 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	err = xe_sched_entity_init(&ge->entity, sched);
 	if (err)
 		goto err_sched;
-	q->priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
 
 	if (xe_exec_queue_is_lr(q))
 		INIT_WORK(&q->guc->lr_tdr, xe_guc_exec_queue_lr_cleanup);
@@ -1301,14 +1300,14 @@ static int guc_exec_queue_set_priority(struct xe_exec_queue *q,
 {
 	struct xe_sched_msg *msg;
 
-	if (q->priority == priority || exec_queue_killed_or_banned(q))
+	if (q->sched_props.priority == priority || exec_queue_killed_or_banned(q))
 		return 0;
 
 	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
 
-	q->priority = priority;
+	q->sched_props.priority = priority;
 	guc_exec_queue_add_msg(q, msg, SET_SCHED_PROPS);
 
 	return 0;
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index adf1dab5eba25..02fca8f9adc28 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -344,7 +344,8 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 
 		m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe,
 					    EXEC_QUEUE_FLAG_KERNEL |
-					    EXEC_QUEUE_FLAG_PERMANENT);
+					    EXEC_QUEUE_FLAG_PERMANENT |
+					    EXEC_QUEUE_FLAG_HIGH_PRIORITY);
 	} else {
 		m->q = xe_exec_queue_create_class(xe, primary_gt, vm,
 						  XE_ENGINE_CLASS_COPY,
@@ -355,8 +356,6 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 		xe_vm_close_and_put(vm);
 		return ERR_CAST(m->q);
 	}
-	if (xe->info.has_usm)
-		m->q->priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
 
 	mutex_init(&m->job_mutex);
 
-- 
GitLab


From 23ca3d2fe367794d2816530fa6b141339fddc1c6 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Mon, 8 Jan 2024 14:58:42 -0800
Subject: [PATCH 2718/4076] drm/xe: Check skip_guc_pc before setting SLPC flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Don't set SLPC GuC feature ctl flag if skip_guc_pc is true.

v2: Skip the freq related sysfs creation as well (Badal)
v3: Remove unnecessary parenthesis (Lucas)

Fixes: 975e4a3795d4 ("drm/xe: Manually setup C6 when skip_guc_pc is set")
Fixes: bef52b5c7a19 ("drm/xe: Create a xe_gt_freq component for raw management and sysfs")
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://lore.kernel.org/r/20240108225842.966066-1-vinay.belgaumkar@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 69cac0a8f3ef8db4d62441c4a2686ec676c9facd)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_gt_freq.c | 3 +++
 drivers/gpu/drm/xe/xe_guc.c     | 7 ++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c
index 3adfa6686e7cf..e5b0f4ecdbe82 100644
--- a/drivers/gpu/drm/xe/xe_gt_freq.c
+++ b/drivers/gpu/drm/xe/xe_gt_freq.c
@@ -196,6 +196,9 @@ void xe_gt_freq_init(struct xe_gt *gt)
 	struct xe_device *xe = gt_to_xe(gt);
 	int err;
 
+	if (xe->info.skip_guc_pc)
+		return;
+
 	gt->freq = kobject_create_and_add("freq0", gt->sysfs);
 	if (!gt->freq) {
 		drm_warn(&xe->drm, "failed to add freq0 directory to %s\n",
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 482cb0df9f15b..0a61390c64a7b 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -60,7 +60,12 @@ static u32 guc_ctl_debug_flags(struct xe_guc *guc)
 
 static u32 guc_ctl_feature_flags(struct xe_guc *guc)
 {
-	return GUC_CTL_ENABLE_SLPC;
+	u32 flags = 0;
+
+	if (!guc_to_xe(guc)->info.skip_guc_pc)
+		flags |= GUC_CTL_ENABLE_SLPC;
+
+	return flags;
 }
 
 static u32 guc_ctl_log_params_flags(struct xe_guc *guc)
-- 
GitLab


From 190db3b1da8f40131d6153de7469abce16766302 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 10 Jan 2024 06:48:29 -0800
Subject: [PATCH 2719/4076] drm/xe: Fix build bug for GCC 11
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Building drivers/gpu/drm/xe/xe_gt_pagefault.c with GCC 11 results
in the following build errors:

./include/linux/fortify-string.h:57:33: error: writing 16 bytes into a region of size 0 [-Werror=stringop-overflow=]
   57 | #define __underlying_memcpy     __builtin_memcpy
      |                                 ^
./include/linux/fortify-string.h:644:9: note: in expansion of macro ‘__underlying_memcpy’
  644 |         __underlying_##op(p, q, __fortify_size);                        \
      |         ^~~~~~~~~~~~~
./include/linux/fortify-string.h:689:26: note: in expansion of macro ‘__fortify_memcpy_chk’
  689 | #define memcpy(p, q, s)  __fortify_memcpy_chk(p, q, s,                  \
      |                          ^~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/xe/xe_gt_pagefault.c:340:17: note: in expansion of macro ‘memcpy’
  340 |                 memcpy(pf_queue->data + pf_queue->tail, msg, len * sizeof(u32));
      |                 ^~~~~~
In file included from drivers/gpu/drm/xe/xe_device_types.h:17,
                 from drivers/gpu/drm/xe/xe_vm_types.h:16,
                 from drivers/gpu/drm/xe/xe_bo.h:13,
                 from drivers/gpu/drm/xe/xe_gt_pagefault.c:16:
drivers/gpu/drm/xe/xe_gt_types.h:102:25: note: at offset [1144, 265324] into destination object ‘tile’ of size 8
  102 |         struct xe_tile *tile;
      |                         ^~~~

Fix these by removing -Wstringop-overflow from drm/xe builds.

Closes: https://lore.kernel.org/all/45ad1d0f-a10f-483e-848a-76a30252edbe@paulmck-laptop/
Fixes: 7a8bc11782d3 ("drm/xe: Enable W=1 warnings by default")
Suggested-by: Stephen Rothwell <sfr@rothwell.id.au>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
[ This particular warning is broken on GCC11. In future changes it will
  be moved to the normal C flags in the top level Makefile (out of
  Makefile.extrawarn), but accounting for the compiler support. Just
  remove it out of xe's forced extra warnings for now ]
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit a109d19992294736abd4f4232ea639e03eb1f9e7)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/Makefile | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 53bd2a8ba1ae5..efcf0ab7a1a69 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -17,7 +17,6 @@ subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
 subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
 subdir-ccflags-y += $(call cc-option, -Wformat-overflow)
 subdir-ccflags-y += $(call cc-option, -Wformat-truncation)
-subdir-ccflags-y += $(call cc-option, -Wstringop-overflow)
 subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
 # The following turn off the warnings enabled by -Wextra
 ifeq ($(findstring 2, $(KBUILD_EXTRA_WARN)),)
-- 
GitLab


From ffd915e41a4a2277fd8041dc77603df59acf3e01 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 5 Jan 2024 15:22:23 +0300
Subject: [PATCH 2720/4076] drm/xe/device: clean up on error in probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This error path should clean up before returning.

Smatch detected this bug:
  drivers/gpu/drm/xe/xe_device.c:487 xe_device_probe() warn: missing unwind goto?

Fixes: 4cb12b71923b ("drm/xe/xe2: Determine bios enablement for flat ccs on igfx")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit c10da95afa68060e13c5f920d96671943a7e54d9)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index d9ae77fe7382d..b8d8da5466708 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -484,7 +484,7 @@ int xe_device_probe(struct xe_device *xe)
 
 	err = xe_device_set_has_flat_ccs(xe);
 	if (err)
-		return err;
+		goto err_irq_shutdown;
 
 	err = xe_mmio_probe_vram(xe);
 	if (err)
-- 
GitLab


From 616576df35193bbadac31dc42a32d5943e183f45 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 5 Jan 2024 15:20:35 +0300
Subject: [PATCH 2721/4076] drm/xe/selftests: Fix an error pointer dereference
 bug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Check if "bo" is an error pointer before calling xe_bo_lock() on it.

Fixes: d6abc18d6693 ("drm/xe/xe2: Modify xe_bo_test for system memory")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit 88ec23528b32ddb9ce2e8492f2629b0056353697)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/tests/xe_bo.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c
index 412b2e7ce40cb..3436fd9cf2b27 100644
--- a/drivers/gpu/drm/xe/tests/xe_bo.c
+++ b/drivers/gpu/drm/xe/tests/xe_bo.c
@@ -125,14 +125,13 @@ static void ccs_test_run_tile(struct xe_device *xe, struct xe_tile *tile,
 
 	bo = xe_bo_create_user(xe, NULL, NULL, SZ_1M, DRM_XE_GEM_CPU_CACHING_WC,
 			       ttm_bo_type_device, bo_flags);
-
-	xe_bo_lock(bo, false);
-
 	if (IS_ERR(bo)) {
 		KUNIT_FAIL(test, "Failed to create bo.\n");
 		return;
 	}
 
+	xe_bo_lock(bo, false);
+
 	kunit_info(test, "Verifying that CCS data is cleared on creation.\n");
 	ret = ccs_test_migrate(tile, bo, false, 0ULL, 0xdeadbeefdeadbeefULL,
 			       test);
-- 
GitLab


From ec32f4f1bed87f0b87b9b0091231c8685db1138c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 5 Jan 2024 15:20:22 +0300
Subject: [PATCH 2722/4076] drm/xe: unlock on error path in
 xe_vm_add_compute_exec_queue()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop the "&vm->lock" before returning.

Fixes: 24f947d58fe5 ("drm/xe: Use DRM GPUVM helpers for external- and evicted objects")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit cf46019e8550a810cc023af7aa020ba43103b44d)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index b0e3cab6a5845..10b6995fbf294 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -335,13 +335,13 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 	down_write(&vm->lock);
 	err = drm_gpuvm_exec_lock(&vm_exec);
 	if (err)
-		return err;
+		goto out_up_write;
 
 	pfence = xe_preempt_fence_create(q, q->compute.context,
 					 ++q->compute.seqno);
 	if (!pfence) {
 		err = -ENOMEM;
-		goto out_unlock;
+		goto out_fini;
 	}
 
 	list_add(&q->compute.link, &vm->preempt.exec_queues);
@@ -364,8 +364,9 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 
 	up_read(&vm->userptr.notifier_lock);
 
-out_unlock:
+out_fini:
 	drm_exec_fini(exec);
+out_up_write:
 	up_write(&vm->lock);
 
 	return err;
-- 
GitLab


From 7425c43c268f859426d02ccb3f043bdbae31cca9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Wed, 10 Jan 2024 17:34:15 +0100
Subject: [PATCH 2723/4076] drm/xe/migrate: Fix CCS copy for small VRAM copy
 chunks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the migrate code is using the identity map for addressing VRAM,
copy chunks may become as small as 64K if the VRAM resource is fragmented.

However, a chunk size smaller that 1MiB may lead to the *next* chunk's
offset into the CCS metadata backup memory may not be page-aligned, and
the XY_CTRL_SURF_COPY_BLT command can't handle that, and even if it could,
the current code doesn't handle the offset calculaton correctly.

To fix this, make sure we align the size of VRAM copy chunks to 1MiB. If
the remaining data to copy is smaller than that, that's not a problem,
so use the remaining size. If the VRAM copy cunk becomes fragmented due
to the size alignment restriction, don't use the identity map, but instead
emit PTEs into the page-table like we do for system memory.

v2:
- Rebase
v3:
- Future proof somewhat by taking into account the real data size to
  flat CCS metadata size ratio. (Matt Roper)
- Invert a couple of if-statements for better readability.
- Fix support for 4K-granularity VRAM sizes. (Tested on DG1).
v4:
- Fix up code comments
- Fix debug printout format typo.
v5:
- Add a Fixes: tag.

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Fixes: e89b384cde62 ("drm/xe/migrate: Update emit_pte to cope with a size level than 4k")
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240110163415.524165-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit ef51d7542d143f3fd9a48d4e2c307563661668aa)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/tests/xe_migrate.c |   2 +-
 drivers/gpu/drm/xe/xe_migrate.c       | 128 ++++++++++++++++----------
 2 files changed, 80 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c
index 7a32faa2f6888..a6523df0f1d39 100644
--- a/drivers/gpu/drm/xe/tests/xe_migrate.c
+++ b/drivers/gpu/drm/xe/tests/xe_migrate.c
@@ -331,7 +331,7 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test)
 		xe_res_first_sg(xe_bo_sg(pt), 0, pt->size, &src_it);
 
 	emit_pte(m, bb, NUM_KERNEL_PDE - 1, xe_bo_is_vram(pt), false,
-		 &src_it, XE_PAGE_SIZE, pt);
+		 &src_it, XE_PAGE_SIZE, pt->ttm.resource);
 
 	run_sanity_job(m, xe, bb, bb->len, "Writing PTE for our fake PT", test);
 
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 02fca8f9adc28..e05e9e7282b68 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -62,6 +62,8 @@ struct xe_migrate {
 	 * out of the pt_bo.
 	 */
 	struct drm_suballoc_manager vm_update_sa;
+	/** @min_chunk_size: For dgfx, Minimum chunk size */
+	u64 min_chunk_size;
 };
 
 #define MAX_PREEMPTDISABLE_TRANSFER SZ_8M /* Around 1ms. */
@@ -363,6 +365,19 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 	if (err)
 		return ERR_PTR(err);
 
+	if (IS_DGFX(xe)) {
+		if (xe_device_has_flat_ccs(xe))
+			/* min chunk size corresponds to 4K of CCS Metadata */
+			m->min_chunk_size = SZ_4K * SZ_64K /
+				xe_device_ccs_bytes(xe, SZ_64K);
+		else
+			/* Somewhat arbitrary to avoid a huge amount of blits */
+			m->min_chunk_size = SZ_64K;
+		m->min_chunk_size = roundup_pow_of_two(m->min_chunk_size);
+		drm_dbg(&xe->drm, "Migrate min chunk size is 0x%08llx\n",
+			(unsigned long long)m->min_chunk_size);
+	}
+
 	return m;
 }
 
@@ -374,16 +389,35 @@ static u64 max_mem_transfer_per_pass(struct xe_device *xe)
 	return MAX_PREEMPTDISABLE_TRANSFER;
 }
 
-static u64 xe_migrate_res_sizes(struct xe_device *xe, struct xe_res_cursor *cur)
+static u64 xe_migrate_res_sizes(struct xe_migrate *m, struct xe_res_cursor *cur)
 {
-	/*
-	 * For VRAM we use identity mapped pages so we are limited to current
-	 * cursor size. For system we program the pages ourselves so we have no
-	 * such limitation.
-	 */
-	return min_t(u64, max_mem_transfer_per_pass(xe),
-		     mem_type_is_vram(cur->mem_type) ? cur->size :
-		     cur->remaining);
+	struct xe_device *xe = tile_to_xe(m->tile);
+	u64 size = min_t(u64, max_mem_transfer_per_pass(xe), cur->remaining);
+
+	if (mem_type_is_vram(cur->mem_type)) {
+		/*
+		 * VRAM we want to blit in chunks with sizes aligned to
+		 * min_chunk_size in order for the offset to CCS metadata to be
+		 * page-aligned. If it's the last chunk it may be smaller.
+		 *
+		 * Another constraint is that we need to limit the blit to
+		 * the VRAM block size, unless size is smaller than
+		 * min_chunk_size.
+		 */
+		u64 chunk = max_t(u64, cur->size, m->min_chunk_size);
+
+		size = min_t(u64, size, chunk);
+		if (size > m->min_chunk_size)
+			size = round_down(size, m->min_chunk_size);
+	}
+
+	return size;
+}
+
+static bool xe_migrate_allow_identity(u64 size, const struct xe_res_cursor *cur)
+{
+	/* If the chunk is not fragmented, allow identity map. */
+	return cur->size >= size;
 }
 
 static u32 pte_update_size(struct xe_migrate *m,
@@ -396,7 +430,12 @@ static u32 pte_update_size(struct xe_migrate *m,
 	u32 cmds = 0;
 
 	*L0_pt = pt_ofs;
-	if (!is_vram) {
+	if (is_vram && xe_migrate_allow_identity(*L0, cur)) {
+		/* Offset into identity map. */
+		*L0_ofs = xe_migrate_vram_ofs(tile_to_xe(m->tile),
+					      cur->start + vram_region_gpu_offset(res));
+		cmds += cmd_size;
+	} else {
 		/* Clip L0 to available size */
 		u64 size = min(*L0, (u64)avail_pts * SZ_2M);
 		u64 num_4k_pages = DIV_ROUND_UP(size, XE_PAGE_SIZE);
@@ -412,11 +451,6 @@ static u32 pte_update_size(struct xe_migrate *m,
 
 		/* Each chunk has a single blit command */
 		cmds += cmd_size;
-	} else {
-		/* Offset into identity map. */
-		*L0_ofs = xe_migrate_vram_ofs(tile_to_xe(m->tile),
-					      cur->start + vram_region_gpu_offset(res));
-		cmds += cmd_size;
 	}
 
 	return cmds;
@@ -426,10 +460,10 @@ static void emit_pte(struct xe_migrate *m,
 		     struct xe_bb *bb, u32 at_pt,
 		     bool is_vram, bool is_comp_pte,
 		     struct xe_res_cursor *cur,
-		     u32 size, struct xe_bo *bo)
+		     u32 size, struct ttm_resource *res)
 {
 	struct xe_device *xe = tile_to_xe(m->tile);
-
+	struct xe_vm *vm = m->q->vm;
 	u16 pat_index;
 	u32 ptes;
 	u64 ofs = at_pt * XE_PAGE_SIZE;
@@ -442,13 +476,6 @@ static void emit_pte(struct xe_migrate *m,
 	else
 		pat_index = xe->pat.idx[XE_CACHE_WB];
 
-	/*
-	 * FIXME: Emitting VRAM PTEs to L0 PTs is forbidden. Currently
-	 * we're only emitting VRAM PTEs during sanity tests, so when
-	 * that's moved to a Kunit test, we should condition VRAM PTEs
-	 * on running tests.
-	 */
-
 	ptes = DIV_ROUND_UP(size, XE_PAGE_SIZE);
 
 	while (ptes) {
@@ -468,20 +495,22 @@ static void emit_pte(struct xe_migrate *m,
 
 			addr = xe_res_dma(cur) & PAGE_MASK;
 			if (is_vram) {
-				/* Is this a 64K PTE entry? */
-				if ((m->q->vm->flags & XE_VM_FLAG_64K) &&
-				    !(cur_ofs & (16 * 8 - 1))) {
-					xe_tile_assert(m->tile, IS_ALIGNED(addr, SZ_64K));
+				if (vm->flags & XE_VM_FLAG_64K) {
+					u64 va = cur_ofs * XE_PAGE_SIZE / 8;
+
+					xe_assert(xe, (va & (SZ_64K - 1)) ==
+						  (addr & (SZ_64K - 1)));
+
 					flags |= XE_PTE_PS64;
 				}
 
-				addr += vram_region_gpu_offset(bo->ttm.resource);
+				addr += vram_region_gpu_offset(res);
 				devmem = true;
 			}
 
-			addr = m->q->vm->pt_ops->pte_encode_addr(m->tile->xe,
-								 addr, pat_index,
-								 0, devmem, flags);
+			addr = vm->pt_ops->pte_encode_addr(m->tile->xe,
+							   addr, pat_index,
+							   0, devmem, flags);
 			bb->cs[bb->len++] = lower_32_bits(addr);
 			bb->cs[bb->len++] = upper_32_bits(addr);
 
@@ -693,8 +722,8 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		bool usm = xe->info.has_usm;
 		u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE;
 
-		src_L0 = xe_migrate_res_sizes(xe, &src_it);
-		dst_L0 = xe_migrate_res_sizes(xe, &dst_it);
+		src_L0 = xe_migrate_res_sizes(m, &src_it);
+		dst_L0 = xe_migrate_res_sizes(m, &dst_it);
 
 		drm_dbg(&xe->drm, "Pass %u, sizes: %llu & %llu\n",
 			pass++, src_L0, dst_L0);
@@ -715,6 +744,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 						      &ccs_ofs, &ccs_pt, 0,
 						      2 * avail_pts,
 						      avail_pts);
+			xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE));
 		}
 
 		/* Add copy commands size here */
@@ -727,20 +757,20 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 			goto err_sync;
 		}
 
-		if (!src_is_vram)
-			emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
-				 src_bo);
-		else
+		if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
 			xe_res_next(&src_it, src_L0);
-
-		if (!dst_is_vram)
-			emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
-				 dst_bo);
 		else
+			emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
+				 src);
+
+		if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
 			xe_res_next(&dst_it, src_L0);
+		else
+			emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
+				 dst);
 
 		if (copy_system_ccs)
-			emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src_bo);
+			emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src);
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
@@ -949,7 +979,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		bool usm = xe->info.has_usm;
 		u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE;
 
-		clear_L0 = xe_migrate_res_sizes(xe, &src_it);
+		clear_L0 = xe_migrate_res_sizes(m, &src_it);
 
 		drm_dbg(&xe->drm, "Pass %u, size: %llu\n", pass++, clear_L0);
 
@@ -976,12 +1006,12 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 
 		size -= clear_L0;
 		/* Preemption is enabled again by the ring ops. */
-		if (!clear_vram) {
-			emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0,
-				 bo);
-		} else {
+		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it))
 			xe_res_next(&src_it, clear_L0);
-		}
+		else
+			emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0,
+				 dst);
+
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
 
-- 
GitLab


From 8049e3954aeaaeb488cd4e371526721c7fca297e Mon Sep 17 00:00:00 2001
From: Brian Welty <brian.welty@intel.com>
Date: Wed, 10 Jan 2024 16:21:11 -0800
Subject: [PATCH 2724/4076] drm/xe: Fix bounds checking in
 __xe_bo_placement_for_flags()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Requesting all memory regions on PVC will fill bo->placements up to
XE_BO_MAX_PLACEMENTS. The subsequent call to try_add_stolen() will trip
over the bounds checking even though XE_PL_STOLEN is not expected to
be used in this case.

This is hit with igt@xe_exec_fault_mode@once-basic-prefetch:
    xe 0000:8c:00.0: [drm] Assertion `*c < (sizeof(bo->placements) / sizeof((bo->placements)[0]) + ((int)(sizeof(struct { int:(-!!(__builtin_types_compatible_p(typeof((bo->placements)), typeof(&(bo->placements)[0])))); }))))` failed!
    WARNING: CPU: 30 PID: 6161 at drivers/gpu/drm/xe/xe_bo.c:203 __xe_bo_placement_for_flags+0x218/0x240 [xe]

Is fixed here by moving the bounds checks closer to where we actually
write into the bo->placement array.

Fixes: 8c54ee8a8606 ("drm/xe: Ensure that we don't access the placements array out-of-bounds")
Link: https://patchwork.freedesktop.org/patch/msgid/20240111002111.10190-1-brian.welty@intel.com
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Brian Welty <brian.welty@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit 52e3fa3e3ea3ee05e32c1a8d72bb3ae306a4da64)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 3cd29bd015a02..0b0e262e2166d 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -125,9 +125,9 @@ static struct xe_mem_region *res_to_mem_region(struct ttm_resource *res)
 static void try_add_system(struct xe_device *xe, struct xe_bo *bo,
 			   u32 bo_flags, u32 *c)
 {
-	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
 	if (bo_flags & XE_BO_CREATE_SYSTEM_BIT) {
+		xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
 		bo->placements[*c] = (struct ttm_place) {
 			.mem_type = XE_PL_TT,
 		};
@@ -145,6 +145,8 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
 	struct xe_mem_region *vram;
 	u64 io_size;
 
+	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
 	vram = to_xe_ttm_vram_mgr(ttm_manager_type(&xe->ttm, mem_type))->vram;
 	xe_assert(xe, vram && vram->usable_size);
 	io_size = vram->io_size;
@@ -175,8 +177,6 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
 static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
 			 u32 bo_flags, u32 *c)
 {
-	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
 	if (bo->props.preferred_gt == XE_GT1) {
 		if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
 			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
@@ -193,9 +193,9 @@ static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
 static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo,
 			   u32 bo_flags, u32 *c)
 {
-	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
-
 	if (bo_flags & XE_BO_CREATE_STOLEN_BIT) {
+		xe_assert(xe, *c < ARRAY_SIZE(bo->placements));
+
 		bo->placements[*c] = (struct ttm_place) {
 			.mem_type = XE_PL_STOLEN,
 			.flags = bo_flags & (XE_BO_CREATE_PINNED_BIT |
-- 
GitLab


From cbcb358b744bf8d8c52b35d5efb1a960438c31cd Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 24 Aug 2023 17:55:51 +0800
Subject: [PATCH 2725/4076] ceph: skip reconnecting if MDS is not ready

When MDS closed the session the kclient will send to reconnect to
it immediately, but if the MDS just restarted and still not ready
yet, such as still in the up:replay state and the sessionmap journal
logs hasn't be replayed, the MDS will close the session.

And then the kclient could remove the session and later when the
mdsmap is in RECONNECT phrase it will skip reconnecting. But the MDS
will wait until timeout and then evict the kclient.

Just skip sending the reconnection request until the MDS is ready.

Link: https://tracker.ceph.com/issues/62489
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d95eb525519a6..be00c189ed460 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5870,7 +5870,8 @@ static void mds_peer_reset(struct ceph_connection *con)
 
 	pr_warn_client(mdsc->fsc->client, "mds%d closed our session\n",
 		       s->s_mds);
-	if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO)
+	if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO &&
+	    ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) >= CEPH_MDS_STATE_RECONNECT)
 		send_mds_reconnect(mdsc, s);
 }
 
-- 
GitLab


From f48e0342a74d7770cdf1d11894bdc3b6d989b29e Mon Sep 17 00:00:00 2001
From: Venky Shankar <vshankar@redhat.com>
Date: Mon, 6 Nov 2023 10:02:32 +0530
Subject: [PATCH 2726/4076] ceph: reinitialize mds feature bit even when
 session in open

Following along the same lines as per the user-space fix. Right
now this isn't really an issue with the ceph kernel driver because
of the feature bit laginess, however, that can change over time
(when the new snaprealm info type is ported to the kernel driver)
and depending on the MDS version that's being upgraded can cause
message decoding issues - so, fix that early on.

Link: http://tracker.ceph.com/issues/63188
Signed-off-by: Venky Shankar <vshankar@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index be00c189ed460..6781438f87829 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4128,12 +4128,12 @@ static void handle_session(struct ceph_mds_session *session,
 			pr_info_client(cl, "mds%d reconnect success\n",
 				       session->s_mds);
 
+		session->s_features = features;
 		if (session->s_state == CEPH_MDS_SESSION_OPEN) {
 			pr_notice_client(cl, "mds%d is already opened\n",
 					 session->s_mds);
 		} else {
 			session->s_state = CEPH_MDS_SESSION_OPEN;
-			session->s_features = features;
 			renewed_caps(mdsc, session, 0);
 			if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT,
 				     &session->s_features))
-- 
GitLab


From b79e4a0aa902322756ced7361a2c637d462c3c1c Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 7 Nov 2023 09:37:47 +0800
Subject: [PATCH 2727/4076] libceph: remove MAX_EXTENTS check for sparse reads

There is no any limit for the extent array size and it's possible
that when reading with a large size contents the total number of
extents will exceed 4096. Then the messager will fail by reseting
the connection and keeps resending the inflight IOs infinitely.

[ idryomov: adjust error message ]

Link: https://tracker.ceph.com/issues/62081
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/osd_client.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index d3a759e052c81..625622016f576 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5850,8 +5850,6 @@ static inline void convert_extent_map(struct ceph_sparse_read *sr)
 }
 #endif
 
-#define MAX_EXTENTS 4096
-
 static int osd_sparse_read(struct ceph_connection *con,
 			   struct ceph_msg_data_cursor *cursor,
 			   char **pbuf)
@@ -5882,23 +5880,16 @@ next_op:
 
 		if (count > 0) {
 			if (!sr->sr_extent || count > sr->sr_ext_len) {
-				/*
-				 * Apply a hard cap to the number of extents.
-				 * If we have more, assume something is wrong.
-				 */
-				if (count > MAX_EXTENTS) {
-					dout("%s: OSD returned 0x%x extents in a single reply!\n",
-					     __func__, count);
-					return -EREMOTEIO;
-				}
-
 				/* no extent array provided, or too short */
 				kfree(sr->sr_extent);
 				sr->sr_extent = kmalloc_array(count,
 							      sizeof(*sr->sr_extent),
 							      GFP_NOIO);
-				if (!sr->sr_extent)
+				if (!sr->sr_extent) {
+					pr_err("%s: failed to allocate %u extents\n",
+					       __func__, count);
 					return -ENOMEM;
+				}
 				sr->sr_ext_len = count;
 			}
 			ret = count * sizeof(*sr->sr_extent);
-- 
GitLab


From aaefabc4a5f7ae48682c4d2d5d10faaf95c08eb9 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 7 Nov 2023 10:44:41 +0800
Subject: [PATCH 2728/4076] ceph: try to allocate a smaller extent map for
 sparse read

In fscrypt case and for a smaller read length we can predict the
max count of the extent map. And for small read length use cases
this could save some memories.

[ idryomov: squash into a single patch to avoid build break, drop
  redundant variable in ceph_alloc_sparse_ext_map() ]

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c                  |  4 +++-
 fs/ceph/file.c                  |  8 ++++++--
 fs/ceph/super.h                 | 14 ++++++++++++++
 include/linux/ceph/osd_client.h |  7 +++++--
 4 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 85be3bf18cdf3..a5caafc1859ec 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -357,6 +357,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	u64 len = subreq->len;
 	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
 	u64 off = subreq->start;
+	int extent_cnt;
 
 	if (ceph_inode_is_shutdown(inode)) {
 		err = -EIO;
@@ -379,7 +380,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	}
 
 	if (sparse) {
-		err = ceph_alloc_sparse_ext_map(&req->r_ops[0]);
+		extent_cnt = __ceph_sparse_read_ext_count(inode, len);
+		err = ceph_alloc_sparse_ext_map(&req->r_ops[0], extent_cnt);
 		if (err)
 			goto out;
 	}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 3b5aae29e9447..4dde0da10079b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1028,6 +1028,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		struct ceph_osd_req_op *op;
 		u64 read_off = off;
 		u64 read_len = len;
+		int extent_cnt;
 
 		/* determine new offset/length if encrypted */
 		ceph_fscrypt_adjust_off_and_len(inode, &read_off, &read_len);
@@ -1067,7 +1068,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 
 		op = &req->r_ops[0];
 		if (sparse) {
-			ret = ceph_alloc_sparse_ext_map(op);
+			extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
+			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
 			if (ret) {
 				ceph_osdc_put_request(req);
 				break;
@@ -1464,6 +1466,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		ssize_t len;
 		struct ceph_osd_req_op *op;
 		int readop = sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ;
+		int extent_cnt;
 
 		if (write)
 			size = min_t(u64, size, fsc->mount_options->wsize);
@@ -1527,7 +1530,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
 		op = &req->r_ops[0];
 		if (sparse) {
-			ret = ceph_alloc_sparse_ext_map(op);
+			extent_cnt = __ceph_sparse_read_ext_count(inode, size);
+			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
 			if (ret) {
 				ceph_osdc_put_request(req);
 				break;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fe0f64a0acb27..b06e2bc86221b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -3,6 +3,7 @@
 #define _FS_CEPH_SUPER_H
 
 #include <linux/ceph/ceph_debug.h>
+#include <linux/ceph/osd_client.h>
 
 #include <asm/unaligned.h>
 #include <linux/backing-dev.h>
@@ -1407,6 +1408,19 @@ static inline void __ceph_update_quota(struct ceph_inode_info *ci,
 		ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota);
 }
 
+static inline int __ceph_sparse_read_ext_count(struct inode *inode, u64 len)
+{
+	int cnt = 0;
+
+	if (IS_ENCRYPTED(inode)) {
+		cnt = len >> CEPH_FSCRYPT_BLOCK_SHIFT;
+		if (cnt > CEPH_SPARSE_EXT_ARRAY_INITIAL)
+			cnt = 0;
+	}
+
+	return cnt;
+}
+
 extern void ceph_handle_quota(struct ceph_mds_client *mdsc,
 			      struct ceph_mds_session *session,
 			      struct ceph_msg *msg);
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index b8610e9d2471f..fa018d5864e74 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -572,9 +572,12 @@ int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt);
  */
 #define CEPH_SPARSE_EXT_ARRAY_INITIAL  16
 
-static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op)
+static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt)
 {
-	return __ceph_alloc_sparse_ext_map(op, CEPH_SPARSE_EXT_ARRAY_INITIAL);
+	if (!cnt)
+		cnt = CEPH_SPARSE_EXT_ARRAY_INITIAL;
+
+	return __ceph_alloc_sparse_ext_map(op, cnt);
 }
 
 extern void ceph_osdc_get_request(struct ceph_osd_request *req);
-- 
GitLab


From b493ad718b1f0357394d2cdecbf00a44a36fa085 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Fri, 17 Nov 2023 13:26:18 +0800
Subject: [PATCH 2729/4076] ceph: fix deadlock or deadcode of misusing dget()

The lock order is incorrect between denty and its parent, we should
always make sure that the parent get the lock first.

But since this deadcode is never used and the parent dir will always
be set from the callers, let's just remove it.

Link: https://lore.kernel.org/r/20231116081919.GZ1957730@ZenIV
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 2c0b8dc3dd0d8..9c02f328c966c 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -4887,13 +4887,15 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 			       struct inode *dir,
 			       int mds, int drop, int unless)
 {
-	struct dentry *parent = NULL;
 	struct ceph_mds_request_release *rel = *p;
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	struct ceph_client *cl;
 	int force = 0;
 	int ret;
 
+	/* This shouldn't happen */
+	BUG_ON(!dir);
+
 	/*
 	 * force an record for the directory caps if we have a dentry lease.
 	 * this is racy (can't take i_ceph_lock and d_lock together), but it
@@ -4903,14 +4905,9 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 	spin_lock(&dentry->d_lock);
 	if (di->lease_session && di->lease_session->s_mds == mds)
 		force = 1;
-	if (!dir) {
-		parent = dget(dentry->d_parent);
-		dir = d_inode(parent);
-	}
 	spin_unlock(&dentry->d_lock);
 
 	ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force);
-	dput(parent);
 
 	cl = ceph_inode_to_client(dir);
 	spin_lock(&dentry->d_lock);
-- 
GitLab


From 9c896d6bc3dfef86659a6a1fb25ccdea5dbef6a3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 22 Nov 2023 19:08:38 -0800
Subject: [PATCH 2730/4076] ceph: select FS_ENCRYPTION_ALGS if FS_ENCRYPTION

The kconfig options for filesystems that support FS_ENCRYPTION are
supposed to select FS_ENCRYPTION_ALGS.  This is needed to ensure that
required crypto algorithms get enabled as loadable modules or builtin as
is appropriate for the set of enabled filesystems.  Do this for CEPH_FS
so that there aren't any missing algorithms if someone happens to have
CEPH_FS as their only enabled filesystem that supports encryption.

Cc: stable@vger.kernel.org
Fixes: f061feda6c54 ("ceph: add fscrypt ioctls and ceph.fscrypt.auth vxattr")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 94df854147d35..7249d70e1a43f 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -7,6 +7,7 @@ config CEPH_FS
 	select CRYPTO_AES
 	select CRYPTO
 	select NETFS_SUPPORT
+	select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
 	default n
 	help
 	  Choose Y or M here to include support for mounting the
-- 
GitLab


From 66207de308df82242da0bf88035b24bcd4377562 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 16 Nov 2023 09:46:19 +0800
Subject: [PATCH 2731/4076] ceph: rename create_session_open_msg() to
 create_session_full_msg()

Makes the create session msg helper to be more general and could
be used by other ops.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 6781438f87829..a7eb722c1b48c 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1534,7 +1534,8 @@ static int encode_metric_spec(void **p, void *end)
  * session message, specialization for CEPH_SESSION_REQUEST_OPEN
  * to include additional client metadata fields.
  */
-static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u64 seq)
+static struct ceph_msg *
+create_session_full_msg(struct ceph_mds_client *mdsc, int op, u64 seq)
 {
 	struct ceph_msg *msg;
 	struct ceph_mds_session_head *h;
@@ -1589,7 +1590,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	end = p + msg->front.iov_len;
 
 	h = p;
-	h->op = cpu_to_le32(CEPH_SESSION_REQUEST_OPEN);
+	h->op = cpu_to_le32(op);
 	h->seq = cpu_to_le64(seq);
 
 	/*
@@ -1663,7 +1664,8 @@ static int __open_session(struct ceph_mds_client *mdsc,
 	session->s_renew_requested = jiffies;
 
 	/* send connect message */
-	msg = create_session_open_msg(mdsc, session->s_seq);
+	msg = create_session_full_msg(mdsc, CEPH_SESSION_REQUEST_OPEN,
+				      session->s_seq);
 	if (IS_ERR(msg))
 		return PTR_ERR(msg);
 	ceph_con_send(&session->s_con, msg);
-- 
GitLab


From 6df89bf220fdac9f40b0d35cd132eef54cf99d4b Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 16 Nov 2023 10:56:24 +0800
Subject: [PATCH 2732/4076] ceph: send oldest_client_tid when renewing caps

Update the oldest_client_tid via the session renew caps msg to
make sure that the MDSs won't pile up the completed request list
in a very large size.

[ idryomov: drop inapplicable comment ]

Link: https://tracker.ceph.com/issues/63364
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a7eb722c1b48c..6cfeba08a3600 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1579,6 +1579,9 @@ create_session_full_msg(struct ceph_mds_client *mdsc, int op, u64 seq)
 		size = METRIC_BYTES(count);
 	extra_bytes += 2 + 4 + 4 + size;
 
+	/* flags, mds auth caps and oldest_client_tid */
+	extra_bytes += 4 + 4 + 8;
+
 	/* Allocate the message */
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes,
 			   GFP_NOFS, false);
@@ -1597,9 +1600,9 @@ create_session_full_msg(struct ceph_mds_client *mdsc, int op, u64 seq)
 	 * Serialize client metadata into waiting buffer space, using
 	 * the format that userspace expects for map<string, string>
 	 *
-	 * ClientSession messages with metadata are v4
+	 * ClientSession messages with metadata are v7
 	 */
-	msg->hdr.version = cpu_to_le16(4);
+	msg->hdr.version = cpu_to_le16(7);
 	msg->hdr.compat_version = cpu_to_le16(1);
 
 	/* The write pointer, following the session_head structure */
@@ -1635,6 +1638,15 @@ create_session_full_msg(struct ceph_mds_client *mdsc, int op, u64 seq)
 		return ERR_PTR(ret);
 	}
 
+	/* version == 5, flags */
+	ceph_encode_32(&p, 0);
+
+	/* version == 6, mds auth caps */
+	ceph_encode_32(&p, 0);
+
+	/* version == 7, oldest_client_tid */
+	ceph_encode_64(&p, mdsc->oldest_tid);
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
@@ -2030,10 +2042,10 @@ static int send_renew_caps(struct ceph_mds_client *mdsc,
 
 	doutc(cl, "to mds%d (%s)\n", session->s_mds,
 	      ceph_mds_state_name(state));
-	msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_RENEWCAPS,
+	msg = create_session_full_msg(mdsc, CEPH_SESSION_REQUEST_RENEWCAPS,
 				      ++session->s_renew_seq);
-	if (!msg)
-		return -ENOMEM;
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
 	ceph_con_send(&session->s_con, msg);
 	return 0;
 }
-- 
GitLab


From b36b03344f5fccb81e5cf3b3ede68b7e7a7e930a Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Wed, 22 Nov 2023 15:55:14 +0800
Subject: [PATCH 2733/4076] ceph: remove duplicated code in
 ceph_netfs_issue_read()

When allocating an osd request the libceph.ko will add the
'read_from_replica' flag by default.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index a5caafc1859ec..792bbbf8de647 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -371,8 +371,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino,
 			off, &len, 0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
-			CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
-			NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
+			CEPH_OSD_FLAG_READ, NULL, ci->i_truncate_seq,
+			ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		req = NULL;
-- 
GitLab


From 0f4cf64eabc6e16cfc2704f1960e82dc79d91c8d Mon Sep 17 00:00:00 2001
From: Wenchao Hao <haowenchao2@huawei.com>
Date: Thu, 23 Nov 2023 09:53:40 +0800
Subject: [PATCH 2734/4076] ceph: fix invalid pointer access if get_quota_realm
 return ERR_PTR

This issue is reported by smatch that get_quota_realm() might return
ERR_PTR but we did not handle it. It's not a immediate bug, while we
still should address it to avoid potential bugs if get_quota_realm()
is changed to return other ERR_PTR in future.

Set ceph_snap_realm's pointer in get_quota_realm()'s to address this
issue, the pointer would be set to NULL if get_quota_realm() failed
to get struct ceph_snap_realm, so no ERR_PTR would happen any more.

[ xiubli: minor code style clean up ]

Signed-off-by: Wenchao Hao <haowenchao2@huawei.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/quota.c | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 9d36c3532de14..06ee397e0c3a6 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -197,10 +197,10 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc)
 }
 
 /*
- * This function walks through the snaprealm for an inode and returns the
- * ceph_snap_realm for the first snaprealm that has quotas set (max_files,
+ * This function walks through the snaprealm for an inode and set the
+ * realmp with the first snaprealm that has quotas set (max_files,
  * max_bytes, or any, depending on the 'which_quota' argument).  If the root is
- * reached, return the root ceph_snap_realm instead.
+ * reached, set the realmp with the root ceph_snap_realm instead.
  *
  * Note that the caller is responsible for calling ceph_put_snap_realm() on the
  * returned realm.
@@ -211,10 +211,9 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc)
  * this function will return -EAGAIN; otherwise, the snaprealms walk-through
  * will be restarted.
  */
-static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
-					       struct inode *inode,
-					       enum quota_get_realm which_quota,
-					       bool retry)
+static int get_quota_realm(struct ceph_mds_client *mdsc, struct inode *inode,
+			   enum quota_get_realm which_quota,
+			   struct ceph_snap_realm **realmp, bool retry)
 {
 	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci = NULL;
@@ -222,8 +221,10 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
 	struct inode *in;
 	bool has_quota;
 
+	if (realmp)
+		*realmp = NULL;
 	if (ceph_snap(inode) != CEPH_NOSNAP)
-		return NULL;
+		return 0;
 
 restart:
 	realm = ceph_inode(inode)->i_snap_realm;
@@ -250,7 +251,7 @@ restart:
 				break;
 			ceph_put_snap_realm(mdsc, realm);
 			if (!retry)
-				return ERR_PTR(-EAGAIN);
+				return -EAGAIN;
 			goto restart;
 		}
 
@@ -259,8 +260,11 @@ restart:
 		iput(in);
 
 		next = realm->parent;
-		if (has_quota || !next)
-		       return realm;
+		if (has_quota || !next) {
+			if (realmp)
+				*realmp = realm;
+			return 0;
+		}
 
 		ceph_get_snap_realm(mdsc, next);
 		ceph_put_snap_realm(mdsc, realm);
@@ -269,7 +273,7 @@ restart:
 	if (realm)
 		ceph_put_snap_realm(mdsc, realm);
 
-	return NULL;
+	return 0;
 }
 
 bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
@@ -277,6 +281,7 @@ bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old->i_sb);
 	struct ceph_snap_realm *old_realm, *new_realm;
 	bool is_same;
+	int ret;
 
 restart:
 	/*
@@ -286,9 +291,9 @@ restart:
 	 * dropped and we can then restart the whole operation.
 	 */
 	down_read(&mdsc->snap_rwsem);
-	old_realm = get_quota_realm(mdsc, old, QUOTA_GET_ANY, true);
-	new_realm = get_quota_realm(mdsc, new, QUOTA_GET_ANY, false);
-	if (PTR_ERR(new_realm) == -EAGAIN) {
+	get_quota_realm(mdsc, old, QUOTA_GET_ANY, &old_realm, true);
+	ret = get_quota_realm(mdsc, new, QUOTA_GET_ANY, &new_realm, false);
+	if (ret == -EAGAIN) {
 		up_read(&mdsc->snap_rwsem);
 		if (old_realm)
 			ceph_put_snap_realm(mdsc, old_realm);
@@ -492,8 +497,8 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf)
 	bool is_updated = false;
 
 	down_read(&mdsc->snap_rwsem);
-	realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root),
-				QUOTA_GET_MAX_BYTES, true);
+	get_quota_realm(mdsc, d_inode(fsc->sb->s_root), QUOTA_GET_MAX_BYTES,
+			&realm, true);
 	up_read(&mdsc->snap_rwsem);
 	if (!realm)
 		return false;
-- 
GitLab


From f6fb21b22fbe443f92b0d580391a7fb46d1840df Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 20 Dec 2023 05:20:54 +0000
Subject: [PATCH 2735/4076] ceph: d_obtain_{alias,root}(ERR_PTR(...)) will do
 the right thing

Clean up the code.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/export.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 726af69d4d62c..a79f163ae4ed2 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -286,8 +286,6 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
 		doutc(cl, "%llx.%llx parent %llx hash %x err=%d", vino.ino,
 		      vino.snap, sfh->parent_ino, sfh->hash, err);
 	}
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
 	/* see comments in ceph_get_parent() */
 	return unlinked ? d_obtain_root(inode) : d_obtain_alias(inode);
 }
-- 
GitLab


From 2a965d1b15d28065b35ab4ebd1e51558fcd91aa5 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 20 Dec 2023 05:29:25 +0000
Subject: [PATCH 2736/4076] ceph: get rid of passing callbacks in
 __dentry_leases_walk()

__dentry_leases_walk() gets a callback and calls it for
a bunch of denties; there are exactly two callers and
we already have a flag telling them apart - lwc->dir_lease.

Seeing that indirect calls are costly these days, let's
get rid of the callback and just call the right function
directly.  Has a side benefit of saner signatures...

[ xiubli: a minor fix in the commit title ]

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 91709934c8b14..7681587437504 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1593,10 +1593,12 @@ struct ceph_lease_walk_control {
 	unsigned long dir_lease_ttl;
 };
 
+static int __dir_lease_check(const struct dentry *, struct ceph_lease_walk_control *);
+static int __dentry_lease_check(const struct dentry *);
+
 static unsigned long
 __dentry_leases_walk(struct ceph_mds_client *mdsc,
-		     struct ceph_lease_walk_control *lwc,
-		     int (*check)(struct dentry*, void*))
+		     struct ceph_lease_walk_control *lwc)
 {
 	struct ceph_dentry_info *di, *tmp;
 	struct dentry *dentry, *last = NULL;
@@ -1624,7 +1626,10 @@ __dentry_leases_walk(struct ceph_mds_client *mdsc,
 			goto next;
 		}
 
-		ret = check(dentry, lwc);
+		if (lwc->dir_lease)
+			ret = __dir_lease_check(dentry, lwc);
+		else
+			ret = __dentry_lease_check(dentry);
 		if (ret & TOUCH) {
 			/* move it into tail of dir lease list */
 			__dentry_dir_lease_touch(mdsc, di);
@@ -1681,7 +1686,7 @@ next:
 	return freed;
 }
 
-static int __dentry_lease_check(struct dentry *dentry, void *arg)
+static int __dentry_lease_check(const struct dentry *dentry)
 {
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	int ret;
@@ -1696,9 +1701,9 @@ static int __dentry_lease_check(struct dentry *dentry, void *arg)
 	return DELETE;
 }
 
-static int __dir_lease_check(struct dentry *dentry, void *arg)
+static int __dir_lease_check(const struct dentry *dentry,
+			     struct ceph_lease_walk_control *lwc)
 {
-	struct ceph_lease_walk_control *lwc = arg;
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 
 	int ret = __dir_lease_try_check(dentry);
@@ -1737,7 +1742,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc)
 
 	lwc.dir_lease = false;
 	lwc.nr_to_scan  = CEPH_CAPS_PER_RELEASE * 2;
-	freed = __dentry_leases_walk(mdsc, &lwc, __dentry_lease_check);
+	freed = __dentry_leases_walk(mdsc, &lwc);
 	if (!lwc.nr_to_scan) /* more invalid leases */
 		return -EAGAIN;
 
@@ -1747,7 +1752,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc)
 	lwc.dir_lease = true;
 	lwc.expire_dir_lease = freed < count;
 	lwc.dir_lease_ttl = mdsc->fsc->mount_options->caps_wanted_delay_max * HZ;
-	freed +=__dentry_leases_walk(mdsc, &lwc, __dir_lease_check);
+	freed +=__dentry_leases_walk(mdsc, &lwc);
 	if (!lwc.nr_to_scan) /* more to check */
 		return -EAGAIN;
 
-- 
GitLab


From 2b872b0f466d2acb4491da845c66b49246d5cdf9 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 15 Jan 2024 22:46:35 +0800
Subject: [PATCH 2737/4076] erofs: Don't use certain unnecessary folio_*()
 functions

Filesystems should use folio->index and folio->mapping, instead of
folio_index(folio), folio_mapping() and folio_file_mapping() since
they know that it's in the pagecache.

Change this automagically with:

perl -p -i -e 's/folio_mapping[(]([^)]*)[)]/\1->mapping/g' fs/erofs/*.c
perl -p -i -e 's/folio_file_mapping[(]([^)]*)[)]/\1->mapping/g' fs/erofs/*.c
perl -p -i -e 's/folio_index[(]([^)]*)[)]/\1->index/g' fs/erofs/*.c

Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: Chao Yu <chao@kernel.org>
Cc: Yue Hu <huyue2@coolpad.com>
Cc: Jeffle Xu <jefflexu@linux.alibaba.com>
Cc: linux-erofs@lists.ozlabs.org
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240115144635.1931422-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/fscache.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 87ff35bff8d5b..bc12030393b24 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -165,10 +165,10 @@ static int erofs_fscache_read_folios_async(struct fscache_cookie *cookie,
 static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
 {
 	int ret;
-	struct erofs_fscache *ctx = folio_mapping(folio)->host->i_private;
+	struct erofs_fscache *ctx = folio->mapping->host->i_private;
 	struct erofs_fscache_request *req;
 
-	req = erofs_fscache_req_alloc(folio_mapping(folio),
+	req = erofs_fscache_req_alloc(folio->mapping,
 				folio_pos(folio), folio_size(folio));
 	if (IS_ERR(req)) {
 		folio_unlock(folio);
@@ -276,7 +276,7 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
 	struct erofs_fscache_request *req;
 	int ret;
 
-	req = erofs_fscache_req_alloc(folio_mapping(folio),
+	req = erofs_fscache_req_alloc(folio->mapping,
 			folio_pos(folio), folio_size(folio));
 	if (IS_ERR(req)) {
 		folio_unlock(folio);
-- 
GitLab


From 04036d49c44b1772d4158640f3ccd938a12a3cb8 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Sat, 13 Jan 2024 12:09:47 +0800
Subject: [PATCH 2738/4076] virtio_blk: remove duplicate check if queue is
 broken in virtblk_done

virtqueue_enable_cb() will call virtqueue_poll() which will check if
queue is broken at beginning, so remove the virtqueue_is_broken() call

Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/virtio_blk.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7d7a19b2b9a8e..24963f445cfe4 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -367,8 +367,6 @@ static void virtblk_done(struct virtqueue *vq)
 				blk_mq_complete_request(req);
 			req_done = true;
 		}
-		if (unlikely(virtqueue_is_broken(vq)))
-			break;
 	} while (!virtqueue_enable_cb(vq));
 
 	/* In case queue is stopped waiting for more buffers. */
-- 
GitLab


From 832b371097eb928d077c827b8f117bf5b99d35c0 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Mon, 15 Jan 2024 16:05:26 +0100
Subject: [PATCH 2739/4076] gpiolib: Fix scope-based gpio_device refcounting

Commit 9e4555d1e54a ("gpiolib: add support for scope-based management to
gpio_device") sought to add scope-based gpio_device refcounting, but
erroneously forgot a negation of IS_ERR_OR_NULL().

As a result, gpio_device_put() is not called if the gpio_device pointer
is valid (meaning the ref is leaked), but only called if the pointer is
NULL or an ERR_PTR().

While at it drop a superfluous trailing semicolon.

Fixes: 9e4555d1e54a ("gpiolib: add support for scope-based management to gpio_device")
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 include/linux/gpio/driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index e846bd4e7559b..9a5c6c76e6533 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -635,7 +635,7 @@ struct gpio_device *gpio_device_get(struct gpio_device *gdev);
 void gpio_device_put(struct gpio_device *gdev);
 
 DEFINE_FREE(gpio_device_put, struct gpio_device *,
-	    if (IS_ERR_OR_NULL(_T)) gpio_device_put(_T));
+	    if (!IS_ERR_OR_NULL(_T)) gpio_device_put(_T))
 
 struct device *gpio_device_to_device(struct gpio_device *gdev);
 
-- 
GitLab


From 2db6b72c989763e30fab83b186e9263fece26bc6 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 6 Dec 2023 12:17:51 -0600
Subject: [PATCH 2740/4076] PCI: Fix kernel-doc issues

Fix kernel-doc issues reported by
"find include -name \*pci\* | xargs scripts/kernel-doc -none":

  include/linux/pci.h:731: warning: Function parameter or member 'pdev' not described in 'pci_is_vga'
  include/linux/pci-epc.h:154: warning: Function parameter or member 'list_lock' not described in 'pci_epc'
  include/linux/pci-epf.h:83: warning: expecting prototype for struct pci_epf_event_ops. Prototype was for struct pci_epc_event_ops instead

Link: https://lore.kernel.org/r/20240111162850.2177655-1-helgaas@kernel.org
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Sui Jingfeng <suijingfeng@loongson.cn>
---
 include/linux/pci-epc.h | 2 +-
 include/linux/pci-epf.h | 2 +-
 include/linux/pci.h     | 1 +
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 5cb6940310729..bfe41b03b70ca 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -122,7 +122,7 @@ struct pci_epc_mem {
  * struct pci_epc - represents the PCI EPC device
  * @dev: PCI EPC device
  * @pci_epf: list of endpoint functions present in this EPC device
- * list_lock: Mutex for protecting pci_epf list
+ * @list_lock: Mutex for protecting pci_epf list
  * @ops: function pointers for performing endpoint operations
  * @windows: array of address space of the endpoint controller
  * @mem: first window of the endpoint controller, which corresponds to
diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 3f44b6aec4770..92d0b71d33d7f 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -68,7 +68,7 @@ struct pci_epf_ops {
 };
 
 /**
- * struct pci_epf_event_ops - Callbacks for capturing the EPC events
+ * struct pci_epc_event_ops - Callbacks for capturing the EPC events
  * @core_init: Callback for the EPC initialization complete event
  * @link_up: Callback for the EPC link up event
  * @link_down: Callback for the EPC link down event
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 1a89dc66f89ac..eb45087d7e001 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -715,6 +715,7 @@ static inline bool pci_is_bridge(struct pci_dev *dev)
 
 /**
  * pci_is_vga - check if the PCI device is a VGA device
+ * @pdev: PCI device
  *
  * The PCI Code and ID Assignment spec, r1.15, secs 1.4 and 1.1, define
  * VGA Base Class and Sub-Classes:
-- 
GitLab


From bf3ff145df184698a8a80b33265064638572366f Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 11 Jan 2024 12:47:16 +0200
Subject: [PATCH 2741/4076] drm/xe: display support should not depend on EXPERT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the DRM_XE_DISPLAY config dependency on EXPERT. I can only
presume the idea was only experts should be able to disable it, but the
effect is the opposite.

Reported-by: Eero Tamminen <eero.t.tamminen@intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240111104716.3548744-1-jani.nikula@intel.com
(cherry picked from commit 1c7531f50eaa425eca8ff726287b8df3a4a51e55)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
index 1cced50d8d8c9..e36ae1f0d8859 100644
--- a/drivers/gpu/drm/xe/Kconfig
+++ b/drivers/gpu/drm/xe/Kconfig
@@ -47,7 +47,7 @@ config DRM_XE
 
 config DRM_XE_DISPLAY
 	bool "Enable display support"
-	depends on DRM_XE && EXPERT && DRM_XE=m
+	depends on DRM_XE && DRM_XE=m
 	select FB_IOMEM_HELPERS
 	select I2C
 	select I2C_ALGOBIT
-- 
GitLab


From 5f4c01f1e3c7b0c8d1e5dd6f080531de7aa5e47b Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 15 Jan 2024 17:19:34 -0300
Subject: [PATCH 2742/4076] spinlock: Fix failing build for PREEMPT_RT

Since 1d71b30e1f85 ("sched.h: Move (spin|rwlock)_needbreak() to
spinlock.h") build fails for PREEMPT_RT, since there is no definition
available of either spin_needbreak() and rwlock_needbreak().

Since it was moved on the mentioned commit, it was placed inside a
!PREEMPT_RT part of the code, making it out of reach for an RT kernel.

Fix this by moving code it a few lines down so it can be reached by an
RT build, where it can also make use of the *_is_contended() definition
added by the spinlock_rt.h.

Fixes: d1d71b30e1f85 ("sched.h: Move (spin|rwlock)_needbreak() to
spinlock.h")
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Acked-by: Waiman Long <longman@redhat.com>
---
 include/linux/spinlock.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 0c71f06454d9e..b5c59fdad160f 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -449,6 +449,12 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
 	return raw_spin_is_contended(&lock->rlock);
 }
 
+#define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
+
+#else  /* !CONFIG_PREEMPT_RT */
+# include <linux/spinlock_rt.h>
+#endif /* CONFIG_PREEMPT_RT */
+
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
@@ -480,12 +486,6 @@ static inline int rwlock_needbreak(rwlock_t *lock)
 #endif
 }
 
-#define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
-
-#else  /* !CONFIG_PREEMPT_RT */
-# include <linux/spinlock_rt.h>
-#endif /* CONFIG_PREEMPT_RT */
-
 /*
  * Pull the atomic_t declaration:
  * (asm-mips/atomic.h needs above definitions)
-- 
GitLab


From eea7615b684fc98cd0403beaaa2194e6f029c812 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 14 Jan 2024 15:13:20 -0800
Subject: [PATCH 2743/4076] rtc: ac100: remove misuses of kernel-doc

Prevent kernel-doc warnings by changing "/**" to common comment
format "/*" in non-kernel-doc comments:

drivers/rtc/rtc-ac100.c:103: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * Clock controls for 3 clock output pins
drivers/rtc/rtc-ac100.c:382: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * RTC related bits

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc:  <linux-rtc@vger.kernel.org>
Link: https://lore.kernel.org/r/20240114231320.31437-1-rdunlap@infradead.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-ac100.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-ac100.c b/drivers/rtc/rtc-ac100.c
index eaf2c9ab96619..fa642bba3cee0 100644
--- a/drivers/rtc/rtc-ac100.c
+++ b/drivers/rtc/rtc-ac100.c
@@ -99,7 +99,7 @@ struct ac100_rtc_dev {
 	struct clk_hw_onecell_data *clk_data;
 };
 
-/**
+/*
  * Clock controls for 3 clock output pins
  */
 
@@ -378,7 +378,7 @@ static void ac100_rtc_unregister_clks(struct ac100_rtc_dev *chip)
 	clk_unregister_fixed_rate(chip->rtc_32k_clk->clk);
 }
 
-/**
+/*
  * RTC related bits
  */
 static int ac100_rtc_get_time(struct device *dev, struct rtc_time *rtc_tm)
-- 
GitLab


From 83c0711453e54dc696b13e9512fbbed6d9180ea2 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 8 Jan 2024 01:43:57 +0100
Subject: [PATCH 2744/4076] rtc: rv8803: add wakeup-source support

The RV8803 can be wired directly to a PMIC that can wake up an SoC without
the CPU getting interrupts.

Link: https://lore.kernel.org/r/20240108004357.602918-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 Documentation/devicetree/bindings/rtc/epson,rx8900.yaml | 2 ++
 drivers/rtc/rtc-rv8803.c                                | 7 +++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml b/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
index 1df7c45d95c18..b770149c5fd67 100644
--- a/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
+++ b/Documentation/devicetree/bindings/rtc/epson,rx8900.yaml
@@ -29,6 +29,8 @@ properties:
 
   trickle-diode-disable: true
 
+  wakeup-source: true
+
 required:
   - compatible
   - reg
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 11e6b0d31f5d7..1327251e527c2 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -712,9 +712,12 @@ static int rv8803_probe(struct i2c_client *client)
 			if (err)
 				dev_err(&client->dev, "failed to set wake IRQ\n");
 		}
+	} else {
+		if (device_property_read_bool(&client->dev, "wakeup-source"))
+			device_init_wakeup(&client->dev, true);
+		else
+			clear_bit(RTC_FEATURE_ALARM, rv8803->rtc->features);
 	}
-	if (!client->irq)
-		clear_bit(RTC_FEATURE_ALARM, rv8803->rtc->features);
 
 	if (of_property_read_bool(client->dev.of_node, "epson,vdet-disable"))
 		rv8803->backup |= RX8900_FLAG_VDETOFF;
-- 
GitLab


From 62b38f30a00ff47142e58d0a6d60dd296e0e8108 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 15 Jan 2024 10:56:47 -0800
Subject: [PATCH 2745/4076] gpio: EN7523: fix kernel-doc warnings

Add "struct" keyword and explain the @dir array differently to
prevent kernel-doc warnings:

gpio-en7523.c:22: warning: cannot understand function prototype: 'struct airoha_gpio_ctrl '
gpio-en7523.c:27: warning: Function parameter or struct member 'dir' not described in 'airoha_gpio_ctrl'
gpio-en7523.c:27: warning: Excess struct member 'dir0' description in 'airoha_gpio_ctrl'
gpio-en7523.c:27: warning: Excess struct member 'dir1' description in 'airoha_gpio_ctrl'

Fixes: 0868ad385aff ("gpio: Add support for Airoha EN7523 GPIO controller")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-en7523.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpio-en7523.c b/drivers/gpio/gpio-en7523.c
index f836a8db4c1d2..69834db2c1cf2 100644
--- a/drivers/gpio/gpio-en7523.c
+++ b/drivers/gpio/gpio-en7523.c
@@ -12,11 +12,11 @@
 #define AIROHA_GPIO_MAX		32
 
 /**
- * airoha_gpio_ctrl - Airoha GPIO driver data
+ * struct airoha_gpio_ctrl - Airoha GPIO driver data
  * @gc: Associated gpio_chip instance.
  * @data: The data register.
- * @dir0: The direction register for the lower 16 pins.
- * @dir1: The direction register for the higher 16 pins.
+ * @dir: [0] The direction register for the lower 16 pins.
+ * [1]: The direction register for the higher 16 pins.
  * @output: The output enable register.
  */
 struct airoha_gpio_ctrl {
-- 
GitLab


From 5905777847b5c3aa8aefe2aad5103f9f468fb990 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Mon, 20 Nov 2023 14:00:16 +0200
Subject: [PATCH 2746/4076] dt-bindings: rtc: max31335: add max31335 bindings

Document the Analog Devices MAX31335 device tree bindings.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Link: https://lore.kernel.org/r/20231120120114.48657-1-antoniu.miclaus@analog.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 .../devicetree/bindings/rtc/adi,max31335.yaml | 70 +++++++++++++++++++
 1 file changed, 70 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/rtc/adi,max31335.yaml

diff --git a/Documentation/devicetree/bindings/rtc/adi,max31335.yaml b/Documentation/devicetree/bindings/rtc/adi,max31335.yaml
new file mode 100644
index 0000000000000..0125cf6727cc3
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/adi,max31335.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/adi,max31335.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Analog Devices MAX31335 RTC
+
+maintainers:
+  - Antoniu Miclaus <antoniu.miclaus@analog.com>
+
+description:
+  Analog Devices MAX31335 I2C RTC ±2ppm Automotive Real-Time Clock with
+  Integrated MEMS Resonator.
+
+allOf:
+  - $ref: rtc.yaml#
+
+properties:
+  compatible:
+    const: adi,max31335
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  "#clock-cells":
+    description:
+      RTC can be used as a clock source through its clock output pin.
+    const: 0
+
+  adi,tc-diode:
+    description:
+      Select the diode configuration for the trickle charger.
+      schottky - Schottky diode in series.
+      standard+schottky - standard diode + Schottky diode in series.
+    enum: [schottky, standard+schottky]
+
+  trickle-resistor-ohms:
+    description:
+      Selected resistor for trickle charger. Should be specified if trickle
+      charger should be enabled.
+    enum: [3000, 6000, 11000]
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        rtc@68 {
+            compatible = "adi,max31335";
+            reg = <0x68>;
+            pinctrl-0 = <&rtc_nint_pins>;
+            interrupts-extended = <&gpio1 16 IRQ_TYPE_LEVEL_HIGH>;
+            aux-voltage-chargeable = <1>;
+            trickle-resistor-ohms = <6000>;
+            adi,tc-diode = "schottky";
+        };
+    };
+...
-- 
GitLab


From dedaf03b99d6561fae06457fd7fc2b0aa154d003 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Mon, 20 Nov 2023 14:00:17 +0200
Subject: [PATCH 2747/4076] rtc: max31335: add driver support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RTC driver for MAX31335 ±2ppm Automotive Real-Time Clock with
Integrated MEMS Resonator.

Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Link: https://lore.kernel.org/r/20231120120114.48657-2-antoniu.miclaus@analog.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 MAINTAINERS                |   8 +
 drivers/rtc/Kconfig        |  13 +
 drivers/rtc/Makefile       |   1 +
 drivers/rtc/rtc-max31335.c | 707 +++++++++++++++++++++++++++++++++++++
 4 files changed, 729 insertions(+)
 create mode 100644 drivers/rtc/rtc-max31335.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 2635f7b59e3ca..b4e368049fbff 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12986,6 +12986,14 @@ F:	Documentation/devicetree/bindings/hwmon/adi,max31827.yaml
 F:	Documentation/hwmon/max31827.rst
 F:	drivers/hwmon/max31827.c
 
+MAX31335 RTC DRIVER
+M:	Antoniu Miclaus <antoniu.miclaus@analog.com>
+L:	linux-rtc@vger.kernel.org
+S:	Supported
+W:	https://ez.analog.com/linux-software-drivers
+F:	Documentation/devicetree/bindings/rtc/adi,max31335.yaml
+F:	drivers/rtc/rtc-max31335.c
+
 MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 L:	linux-hwmon@vger.kernel.org
 S:	Orphan
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 1ea9c76001505..e37a4341f442d 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -373,6 +373,19 @@ config RTC_DRV_MAX8997
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-max8997.
 
+config RTC_DRV_MAX31335
+	tristate "Analog Devices MAX31335"
+	depends on I2C
+	depends on COMMON_CLK
+	depends on HWMON || HWMON=n
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the Analog Devices
+	  MAX31335.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-max31335.
+
 config RTC_DRV_MAX77686
 	tristate "Maxim MAX77686"
 	depends on MFD_MAX77686 || MFD_MAX77620 || MFD_MAX77714 || COMPILE_TEST
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 31c4606fd9bf0..6efff381c484d 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -89,6 +89,7 @@ obj-$(CONFIG_RTC_DRV_M48T35)	+= rtc-m48t35.o
 obj-$(CONFIG_RTC_DRV_M48T59)	+= rtc-m48t59.o
 obj-$(CONFIG_RTC_DRV_M48T86)	+= rtc-m48t86.o
 obj-$(CONFIG_RTC_DRV_MA35D1)	+= rtc-ma35d1.o
+obj-$(CONFIG_RTC_DRV_MAX31335)	+= rtc-max31335.o
 obj-$(CONFIG_RTC_DRV_MAX6900)	+= rtc-max6900.o
 obj-$(CONFIG_RTC_DRV_MAX6902)	+= rtc-max6902.o
 obj-$(CONFIG_RTC_DRV_MAX6916)	+= rtc-max6916.o
diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c
new file mode 100644
index 0000000000000..3ddfe71bbb560
--- /dev/null
+++ b/drivers/rtc/rtc-max31335.c
@@ -0,0 +1,707 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RTC driver for the MAX31335
+ *
+ * Copyright (C) 2023 Analog Devices
+ *
+ * Antoniu Miclaus <antoniu.miclaus@analog.com>
+ *
+ */
+
+#include <asm-generic/unaligned.h>
+#include <linux/bcd.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/hwmon.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+#include <linux/util_macros.h>
+
+/* MAX31335 Register Map */
+#define MAX31335_STATUS1			0x00
+#define MAX31335_INT_EN1			0x01
+#define MAX31335_STATUS2			0x02
+#define MAX31335_INT_EN2			0x03
+#define MAX31335_RTC_RESET			0x04
+#define MAX31335_RTC_CONFIG			0x05
+#define MAX31335_RTC_CONFIG2			0x06
+#define MAX31335_TIMESTAMP_CONFIG		0x07
+#define MAX31335_TIMER_CONFIG			0x08
+#define MAX31335_SECONDS_1_128			0x09
+#define MAX31335_SECONDS			0x0A
+#define MAX31335_MINUTES			0x0B
+#define MAX31335_HOURS				0x0C
+#define MAX31335_DAY				0x0D
+#define MAX31335_DATE				0x0E
+#define MAX31335_MONTH				0x0F
+#define MAX31335_YEAR				0x0F
+#define MAX31335_ALM1_SEC			0x11
+#define MAX31335_ALM1_MIN			0x12
+#define MAX31335_ALM1_HRS			0x13
+#define MAX31335_ALM1_DAY_DATE			0x14
+#define MAX31335_ALM1_MON			0x15
+#define MAX31335_ALM1_YEAR			0x16
+#define MAX31335_ALM2_MIN			0x17
+#define MAX31335_ALM2_HRS			0x18
+#define MAX31335_ALM2_DAY_DATE			0x19
+#define MAX31335_TIMER_COUNT			0x1A
+#define MAX31335_TIMER_INIT			0x1B
+#define MAX31335_PWR_MGMT			0x1C
+#define MAX31335_TRICKLE_REG			0x1D
+#define MAX31335_AGING_OFFSET			0x1E
+#define MAX31335_TS_CONFIG			0x30
+#define MAX31335_TEMP_ALARM_HIGH_MSB		0x31
+#define MAX31335_TEMP_ALARM_HIGH_LSB		0x32
+#define MAX31335_TEMP_ALARM_LOW_MSB		0x33
+#define MAX31335_TEMP_ALARM_LOW_LSB		0x34
+#define MAX31335_TEMP_DATA_MSB			0x35
+#define MAX31335_TEMP_DATA_LSB			0x36
+#define MAX31335_TS0_SEC_1_128			0x40
+#define MAX31335_TS0_SEC			0x41
+#define MAX31335_TS0_MIN			0x42
+#define MAX31335_TS0_HOUR			0x43
+#define MAX31335_TS0_DATE			0x44
+#define MAX31335_TS0_MONTH			0x45
+#define MAX31335_TS0_YEAR			0x46
+#define MAX31335_TS0_FLAGS			0x47
+#define MAX31335_TS1_SEC_1_128			0x48
+#define MAX31335_TS1_SEC			0x49
+#define MAX31335_TS1_MIN			0x4A
+#define MAX31335_TS1_HOUR			0x4B
+#define MAX31335_TS1_DATE			0x4C
+#define MAX31335_TS1_MONTH			0x4D
+#define MAX31335_TS1_YEAR			0x4E
+#define MAX31335_TS1_FLAGS			0x4F
+#define MAX31335_TS2_SEC_1_128			0x50
+#define MAX31335_TS2_SEC			0x51
+#define MAX31335_TS2_MIN			0x52
+#define MAX31335_TS2_HOUR			0x53
+#define MAX31335_TS2_DATE			0x54
+#define MAX31335_TS2_MONTH			0x55
+#define MAX31335_TS2_YEAR			0x56
+#define MAX31335_TS2_FLAGS			0x57
+#define MAX31335_TS3_SEC_1_128			0x58
+#define MAX31335_TS3_SEC			0x59
+#define MAX31335_TS3_MIN			0x5A
+#define MAX31335_TS3_HOUR			0x5B
+#define MAX31335_TS3_DATE			0x5C
+#define MAX31335_TS3_MONTH			0x5D
+#define MAX31335_TS3_YEAR			0x5E
+#define MAX31335_TS3_FLAGS			0x5F
+
+/* MAX31335_STATUS1 Bit Definitions */
+#define MAX31335_STATUS1_PSDECT			BIT(7)
+#define MAX31335_STATUS1_OSF			BIT(6)
+#define MAX31335_STATUS1_PFAIL			BIT(5)
+#define MAX31335_STATUS1_VBATLOW		BIT(4)
+#define MAX31335_STATUS1_DIF			BIT(3)
+#define MAX31335_STATUS1_TIF			BIT(2)
+#define MAX31335_STATUS1_A2F			BIT(1)
+#define MAX31335_STATUS1_A1F			BIT(0)
+
+/* MAX31335_INT_EN1 Bit Definitions */
+#define MAX31335_INT_EN1_DOSF			BIT(6)
+#define MAX31335_INT_EN1_PFAILE			BIT(5)
+#define MAX31335_INT_EN1_VBATLOWE		BIT(4)
+#define MAX31335_INT_EN1_DIE			BIT(3)
+#define MAX31335_INT_EN1_TIE			BIT(2)
+#define MAX31335_INT_EN1_A2IE			BIT(1)
+#define MAX31335_INT_EN1_A1IE			BIT(0)
+
+/* MAX31335_STATUS2 Bit Definitions */
+#define MAX31335_STATUS2_TEMP_RDY		BIT(2)
+#define MAX31335_STATUS2_OTF			BIT(1)
+#define MAX31335_STATUS2_UTF			BIT(0)
+
+/* MAX31335_INT_EN2 Bit Definitions */
+#define MAX31335_INT_EN2_TEMP_RDY_EN		BIT(2)
+#define MAX31335_INT_EN2_OTIE			BIT(1)
+#define MAX31335_INT_EN2_UTIE			BIT(0)
+
+/* MAX31335_RTC_RESET Bit Definitions */
+#define MAX31335_RTC_RESET_SWRST		BIT(0)
+
+/* MAX31335_RTC_CONFIG1 Bit Definitions */
+#define MAX31335_RTC_CONFIG1_EN_IO		BIT(6)
+#define MAX31335_RTC_CONFIG1_A1AC		GENMASK(5, 4)
+#define MAX31335_RTC_CONFIG1_DIP		BIT(3)
+#define MAX31335_RTC_CONFIG1_I2C_TIMEOUT	BIT(1)
+#define MAX31335_RTC_CONFIG1_EN_OSC		BIT(0)
+
+/* MAX31335_RTC_CONFIG2 Bit Definitions */
+#define MAX31335_RTC_CONFIG2_ENCLKO		BIT(2)
+#define MAX31335_RTC_CONFIG2_CLKO_HZ		GENMASK(1, 0)
+
+/* MAX31335_TIMESTAMP_CONFIG Bit Definitions */
+#define MAX31335_TIMESTAMP_CONFIG_TSVLOW	BIT(5)
+#define MAX31335_TIMESTAMP_CONFIG_TSPWM		BIT(4)
+#define MAX31335_TIMESTAMP_CONFIG_TSDIN		BIT(3)
+#define MAX31335_TIMESTAMP_CONFIG_TSOW		BIT(2)
+#define MAX31335_TIMESTAMP_CONFIG_TSR		BIT(1)
+#define MAX31335_TIMESTAMP_CONFIG_TSE		BIT(0)
+
+/* MAX31335_TIMER_CONFIG Bit Definitions */
+#define MAX31335_TIMER_CONFIG_TE		BIT(4)
+#define MAX31335_TIMER_CONFIG_TPAUSE		BIT(3)
+#define MAX31335_TIMER_CONFIG_TRPT		BIT(2)
+#define MAX31335_TIMER_CONFIG_TFS		GENMASK(1, 0)
+
+/* MAX31335_HOURS Bit Definitions */
+#define MAX31335_HOURS_F_24_12			BIT(6)
+#define MAX31335_HOURS_HR_20_AM_PM		BIT(5)
+
+/* MAX31335_MONTH Bit Definitions */
+#define MAX31335_MONTH_CENTURY			BIT(7)
+
+/* MAX31335_PWR_MGMT Bit Definitions */
+#define MAX31335_PWR_MGMT_PFVT			BIT(0)
+
+/* MAX31335_TRICKLE_REG Bit Definitions */
+#define MAX31335_TRICKLE_REG_TRICKLE		GENMASK(3, 1)
+#define MAX31335_TRICKLE_REG_EN_TRICKLE		BIT(0)
+
+/* MAX31335_TS_CONFIG Bit Definitions */
+#define MAX31335_TS_CONFIG_AUTO			BIT(4)
+#define MAX31335_TS_CONFIG_CONVERT_T		BIT(3)
+#define MAX31335_TS_CONFIG_TSINT		GENMASK(2, 0)
+
+/* MAX31335_TS_FLAGS Bit Definitions */
+#define MAX31335_TS_FLAGS_VLOWF			BIT(3)
+#define MAX31335_TS_FLAGS_VBATF			BIT(2)
+#define MAX31335_TS_FLAGS_VCCF			BIT(1)
+#define MAX31335_TS_FLAGS_DINF			BIT(0)
+
+/* MAX31335 Miscellaneous Definitions */
+#define MAX31335_TRICKLE_SCHOTTKY_DIODE		1
+#define MAX31335_TRICKLE_STANDARD_DIODE		4
+#define MAX31335_RAM_SIZE			32
+#define MAX31335_TIME_SIZE			0x07
+
+#define clk_hw_to_max31335(_hw) container_of(_hw, struct max31335_data, clkout)
+
+struct max31335_data {
+	struct regmap *regmap;
+	struct rtc_device *rtc;
+	struct clk_hw clkout;
+};
+
+static const int max31335_clkout_freq[] = { 1, 64, 1024, 32768 };
+
+static const u16 max31335_trickle_resistors[] = {3000, 6000, 11000};
+
+static bool max31335_volatile_reg(struct device *dev, unsigned int reg)
+{
+	/* time keeping registers */
+	if (reg >= MAX31335_SECONDS &&
+	    reg < MAX31335_SECONDS + MAX31335_TIME_SIZE)
+		return true;
+
+	/* interrupt status register */
+	if (reg == MAX31335_INT_EN1_A1IE)
+		return true;
+
+	/* temperature registers */
+	if (reg == MAX31335_TEMP_DATA_MSB || MAX31335_TEMP_DATA_LSB)
+		return true;
+
+	return false;
+}
+
+static const struct regmap_config regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = 0x5F,
+	.volatile_reg = max31335_volatile_reg,
+};
+
+static int max31335_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	u8 date[7];
+	int ret;
+
+	ret = regmap_bulk_read(max31335->regmap, MAX31335_SECONDS, date,
+			       sizeof(date));
+	if (ret)
+		return ret;
+
+	tm->tm_sec  = bcd2bin(date[0] & 0x7f);
+	tm->tm_min  = bcd2bin(date[1] & 0x7f);
+	tm->tm_hour = bcd2bin(date[2] & 0x3f);
+	tm->tm_wday = bcd2bin(date[3] & 0x7) - 1;
+	tm->tm_mday = bcd2bin(date[4] & 0x3f);
+	tm->tm_mon  = bcd2bin(date[5] & 0x1f) - 1;
+	tm->tm_year = bcd2bin(date[6]) + 100;
+
+	if (FIELD_GET(MAX31335_MONTH_CENTURY, date[5]))
+		tm->tm_year += 100;
+
+	return 0;
+}
+
+static int max31335_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	u8 date[7];
+
+	date[0] = bin2bcd(tm->tm_sec);
+	date[1] = bin2bcd(tm->tm_min);
+	date[2] = bin2bcd(tm->tm_hour);
+	date[3] = bin2bcd(tm->tm_wday + 1);
+	date[4] = bin2bcd(tm->tm_mday);
+	date[5] = bin2bcd(tm->tm_mon + 1);
+	date[6] = bin2bcd(tm->tm_year % 100);
+
+	if (tm->tm_year >= 200)
+		date[5] |= FIELD_PREP(MAX31335_MONTH_CENTURY, 1);
+
+	return regmap_bulk_write(max31335->regmap, MAX31335_SECONDS, date,
+				 sizeof(date));
+}
+
+static int max31335_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	int ret, ctrl, status;
+	struct rtc_time time;
+	u8 regs[6];
+
+	ret = regmap_bulk_read(max31335->regmap, MAX31335_ALM1_SEC, regs,
+			       sizeof(regs));
+	if (ret)
+		return ret;
+
+	alrm->time.tm_sec  = bcd2bin(regs[0] & 0x7f);
+	alrm->time.tm_min  = bcd2bin(regs[1] & 0x7f);
+	alrm->time.tm_hour = bcd2bin(regs[2] & 0x3f);
+	alrm->time.tm_mday = bcd2bin(regs[3] & 0x3f);
+	alrm->time.tm_mon  = bcd2bin(regs[4] & 0x1f) - 1;
+	alrm->time.tm_year = bcd2bin(regs[5]) + 100;
+
+	ret = max31335_read_time(dev, &time);
+	if (ret)
+		return ret;
+
+	if (time.tm_year >= 200)
+		alrm->time.tm_year += 100;
+
+	ret = regmap_read(max31335->regmap, MAX31335_INT_EN1, &ctrl);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(max31335->regmap, MAX31335_STATUS1, &status);
+	if (ret)
+		return ret;
+
+	alrm->enabled = FIELD_GET(MAX31335_INT_EN1_A1IE, ctrl);
+	alrm->pending = FIELD_GET(MAX31335_STATUS1_A1F, status);
+
+	return 0;
+}
+
+static int max31335_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	unsigned int reg;
+	u8 regs[6];
+	int ret;
+
+	regs[0] = bin2bcd(alrm->time.tm_sec);
+	regs[1] = bin2bcd(alrm->time.tm_min);
+	regs[2] = bin2bcd(alrm->time.tm_hour);
+	regs[3] = bin2bcd(alrm->time.tm_mday);
+	regs[4] = bin2bcd(alrm->time.tm_mon + 1);
+	regs[5] = bin2bcd(alrm->time.tm_year % 100);
+
+	ret = regmap_bulk_write(max31335->regmap, MAX31335_ALM1_SEC,
+				regs, sizeof(regs));
+	if (ret)
+		return ret;
+
+	reg = FIELD_PREP(MAX31335_INT_EN1_A1IE, alrm->enabled);
+	ret = regmap_update_bits(max31335->regmap, MAX31335_INT_EN1,
+				 MAX31335_INT_EN1_A1IE, reg);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(max31335->regmap, MAX31335_STATUS1,
+				 MAX31335_STATUS1_A1F, 0);
+
+	return 0;
+}
+
+static int max31335_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+
+	return regmap_update_bits(max31335->regmap, MAX31335_INT_EN1,
+				  MAX31335_INT_EN1_A1IE, enabled);
+}
+
+static irqreturn_t max31335_handle_irq(int irq, void *dev_id)
+{
+	struct max31335_data *max31335 = dev_id;
+	struct mutex *lock = &max31335->rtc->ops_lock;
+	int ret, status;
+
+	mutex_lock(lock);
+
+	ret = regmap_read(max31335->regmap, MAX31335_STATUS1, &status);
+	if (ret)
+		goto exit;
+
+	if (FIELD_GET(MAX31335_STATUS1_A1F, status)) {
+		ret = regmap_update_bits(max31335->regmap, MAX31335_STATUS1,
+					 MAX31335_STATUS1_A1F, 0);
+		if (ret)
+			goto exit;
+
+		rtc_update_irq(max31335->rtc, 1, RTC_AF | RTC_IRQF);
+	}
+
+exit:
+	mutex_unlock(lock);
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops max31335_rtc_ops = {
+	.read_time = max31335_read_time,
+	.set_time = max31335_set_time,
+	.read_alarm = max31335_read_alarm,
+	.set_alarm = max31335_set_alarm,
+	.alarm_irq_enable = max31335_alarm_irq_enable,
+};
+
+static int max31335_trickle_charger_setup(struct device *dev,
+					  struct max31335_data *max31335)
+{
+	u32 ohms, chargeable;
+	int i, trickle_cfg;
+	const char *diode;
+
+	if (device_property_read_u32(dev, "aux-voltage-chargeable",
+				     &chargeable))
+		return 0;
+
+	if (device_property_read_u32(dev, "trickle-resistor-ohms", &ohms))
+		return 0;
+
+	if (device_property_read_string(dev, "adi,tc-diode", &diode))
+		return 0;
+
+	if (!strcmp(diode, "schottky"))
+		trickle_cfg = MAX31335_TRICKLE_SCHOTTKY_DIODE;
+	else if (!strcmp(diode, "standard+schottky"))
+		trickle_cfg = MAX31335_TRICKLE_STANDARD_DIODE;
+	else
+		return dev_err_probe(dev, -EINVAL,
+				     "Invalid tc-diode value: %s\n", diode);
+
+	for (i = 0; i < ARRAY_SIZE(max31335_trickle_resistors); i++)
+		if (ohms == max31335_trickle_resistors[i])
+			break;
+
+	if (i >= ARRAY_SIZE(max31335_trickle_resistors))
+		return 0;
+
+	i = i + trickle_cfg;
+
+	return regmap_write(max31335->regmap, MAX31335_TRICKLE_REG,
+			    FIELD_PREP(MAX31335_TRICKLE_REG_TRICKLE, i) |
+			    FIELD_PREP(MAX31335_TRICKLE_REG_EN_TRICKLE,
+				       chargeable));
+}
+
+static unsigned long max31335_clkout_recalc_rate(struct clk_hw *hw,
+						 unsigned long parent_rate)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+	unsigned int freq_mask;
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(max31335->regmap, MAX31335_RTC_CONFIG2, &reg);
+	if (ret)
+		return 0;
+
+	freq_mask = __roundup_pow_of_two(ARRAY_SIZE(max31335_clkout_freq)) - 1;
+
+	return max31335_clkout_freq[reg & freq_mask];
+}
+
+static long max31335_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long *prate)
+{
+	int index;
+
+	index = find_closest(rate, max31335_clkout_freq,
+			     ARRAY_SIZE(max31335_clkout_freq));
+
+	return max31335_clkout_freq[index];
+}
+
+static int max31335_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+	unsigned int freq_mask;
+	int index;
+
+	index = find_closest(rate, max31335_clkout_freq,
+			     ARRAY_SIZE(max31335_clkout_freq));
+	freq_mask = __roundup_pow_of_two(ARRAY_SIZE(max31335_clkout_freq)) - 1;
+
+	return regmap_update_bits(max31335->regmap, MAX31335_RTC_CONFIG2,
+				  freq_mask, index);
+}
+
+static int max31335_clkout_enable(struct clk_hw *hw)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+
+	return regmap_set_bits(max31335->regmap, MAX31335_RTC_CONFIG2,
+			       MAX31335_RTC_CONFIG2_ENCLKO);
+}
+
+static void max31335_clkout_disable(struct clk_hw *hw)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+
+	regmap_clear_bits(max31335->regmap, MAX31335_RTC_CONFIG2,
+			  MAX31335_RTC_CONFIG2_ENCLKO);
+}
+
+static int max31335_clkout_is_enabled(struct clk_hw *hw)
+{
+	struct max31335_data *max31335 = clk_hw_to_max31335(hw);
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(max31335->regmap, MAX31335_RTC_CONFIG2, &reg);
+	if (ret)
+		return ret;
+
+	return !!(reg & MAX31335_RTC_CONFIG2_ENCLKO);
+}
+
+static const struct clk_ops max31335_clkout_ops = {
+	.recalc_rate = max31335_clkout_recalc_rate,
+	.round_rate = max31335_clkout_round_rate,
+	.set_rate = max31335_clkout_set_rate,
+	.enable = max31335_clkout_enable,
+	.disable = max31335_clkout_disable,
+	.is_enabled = max31335_clkout_is_enabled,
+};
+
+static struct clk_init_data max31335_clk_init = {
+	.name = "max31335-clkout",
+	.ops = &max31335_clkout_ops,
+};
+
+static int max31335_nvmem_reg_read(void *priv, unsigned int offset,
+				   void *val, size_t bytes)
+{
+	struct max31335_data *max31335 = priv;
+	unsigned int reg = MAX31335_TS0_SEC_1_128 + offset;
+
+	return regmap_bulk_read(max31335->regmap, reg, val, bytes);
+}
+
+static int max31335_nvmem_reg_write(void *priv, unsigned int offset,
+				    void *val, size_t bytes)
+{
+	struct max31335_data *max31335 = priv;
+	unsigned int reg = MAX31335_TS0_SEC_1_128 + offset;
+
+	return regmap_bulk_write(max31335->regmap, reg, val, bytes);
+}
+
+static struct nvmem_config max31335_nvmem_cfg = {
+	.reg_read = max31335_nvmem_reg_read,
+	.reg_write = max31335_nvmem_reg_write,
+	.word_size = 8,
+	.size = MAX31335_RAM_SIZE,
+};
+
+#if IS_REACHABLE(HWMON)
+static int max31335_read_temp(struct device *dev, enum hwmon_sensor_types type,
+			      u32 attr, int channel, long *val)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	u8 reg[2];
+	s16 temp;
+	int ret;
+
+	if (type != hwmon_temp || attr != hwmon_temp_input)
+		return -EOPNOTSUPP;
+
+	ret = regmap_bulk_read(max31335->regmap, MAX31335_TEMP_DATA_MSB,
+			       reg, 2);
+	if (ret)
+		return ret;
+
+	temp = get_unaligned_be16(reg);
+
+	*val = (temp / 64) * 250;
+
+	return 0;
+}
+
+static umode_t max31335_is_visible(const void *data,
+				   enum hwmon_sensor_types type,
+				   u32 attr, int channel)
+{
+	if (type == hwmon_temp && attr == hwmon_temp_input)
+		return 0444;
+
+	return 0;
+}
+
+static const struct hwmon_channel_info *max31335_info[] = {
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
+	NULL
+};
+
+static const struct hwmon_ops max31335_hwmon_ops = {
+	.is_visible = max31335_is_visible,
+	.read = max31335_read_temp,
+};
+
+static const struct hwmon_chip_info max31335_chip_info = {
+	.ops = &max31335_hwmon_ops,
+	.info = max31335_info,
+};
+#endif
+
+static int max31335_clkout_register(struct device *dev)
+{
+	struct max31335_data *max31335 = dev_get_drvdata(dev);
+	int ret;
+
+	if (!device_property_present(dev, "#clock-cells"))
+		return regmap_clear_bits(max31335->regmap, MAX31335_RTC_CONFIG2,
+					 MAX31335_RTC_CONFIG2_ENCLKO);
+
+	max31335->clkout.init = &max31335_clk_init;
+
+	ret = devm_clk_hw_register(dev, &max31335->clkout);
+	if (ret)
+		return dev_err_probe(dev, ret, "cannot register clock\n");
+
+	ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
+					  &max31335->clkout);
+	if (ret)
+		return dev_err_probe(dev, ret, "cannot add hw provider\n");
+
+	max31335->clkout.clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(max31335->clkout.clk))
+		return dev_err_probe(dev, PTR_ERR(max31335->clkout.clk),
+				     "cannot enable clkout\n");
+
+	return 0;
+}
+
+static int max31335_probe(struct i2c_client *client)
+{
+	struct max31335_data *max31335;
+#if IS_REACHABLE(HWMON)
+	struct device *hwmon;
+#endif
+	int ret;
+
+	max31335 = devm_kzalloc(&client->dev, sizeof(*max31335), GFP_KERNEL);
+	if (!max31335)
+		return -ENOMEM;
+
+	max31335->regmap = devm_regmap_init_i2c(client, &regmap_config);
+	if (IS_ERR(max31335->regmap))
+		return PTR_ERR(max31335->regmap);
+
+	i2c_set_clientdata(client, max31335);
+
+	max31335->rtc = devm_rtc_allocate_device(&client->dev);
+	if (IS_ERR(max31335->rtc))
+		return PTR_ERR(max31335->rtc);
+
+	max31335->rtc->ops = &max31335_rtc_ops;
+	max31335->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	max31335->rtc->range_max = RTC_TIMESTAMP_END_2199;
+	max31335->rtc->alarm_offset_max = 24 * 60 * 60;
+
+	ret = max31335_clkout_register(&client->dev);
+	if (ret)
+		return ret;
+
+	if (client->irq > 0) {
+		ret = devm_request_threaded_irq(&client->dev, client->irq,
+						NULL, max31335_handle_irq,
+						IRQF_ONESHOT,
+						"max31335", max31335);
+		if (ret) {
+			dev_warn(&client->dev,
+				 "unable to request IRQ, alarm max31335 disabled\n");
+			client->irq = 0;
+		}
+	}
+
+	if (!client->irq)
+		clear_bit(RTC_FEATURE_ALARM, max31335->rtc->features);
+
+	max31335_nvmem_cfg.priv = max31335;
+	ret = devm_rtc_nvmem_register(max31335->rtc, &max31335_nvmem_cfg);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				     "cannot register rtc nvmem\n");
+
+#if IS_REACHABLE(HWMON)
+	hwmon = devm_hwmon_device_register_with_info(&client->dev, client->name,
+						     max31335,
+						     &max31335_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon))
+		return dev_err_probe(&client->dev, PTR_ERR(hwmon),
+				     "cannot register hwmon device\n");
+#endif
+
+	ret = max31335_trickle_charger_setup(&client->dev, max31335);
+	if (ret)
+		return ret;
+
+	return devm_rtc_register_device(max31335->rtc);
+}
+
+static const struct i2c_device_id max31335_id[] = {
+	{ "max31335", 0 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(i2c, max31335_id);
+
+static const struct of_device_id max31335_of_match[] = {
+	{ .compatible = "adi,max31335" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, max31335_of_match);
+
+static struct i2c_driver max31335_driver = {
+	.driver = {
+		.name = "rtc-max31335",
+		.of_match_table = max31335_of_match,
+	},
+	.probe = max31335_probe,
+	.id_table = max31335_id,
+};
+module_i2c_driver(max31335_driver);
+
+MODULE_AUTHOR("Antoniu Miclaus <antoniu.miclaus@analog.com>");
+MODULE_DESCRIPTION("MAX31335 RTC driver");
+MODULE_LICENSE("GPL");
-- 
GitLab


From 02eed83abc1395a1207591aafad9bcfc5cb1abcb Mon Sep 17 00:00:00 2001
From: Dafna Hirschfeld <dhirschfeld@habana.ai>
Date: Sun, 7 Jan 2024 15:07:00 +0200
Subject: [PATCH 2748/4076] drm/amdkfd: fixes for HMM mem allocation

Fix err return value and reset pgmap->type after checking it.

Fixes: c83dee9b6394 ("drm/amdkfd: add SPM support for SVM")
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Dafna Hirschfeld <dhirschfeld@habana.ai>
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index d630100b9e91b..f856901055d34 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -1026,7 +1026,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	} else {
 		res = devm_request_free_mem_region(adev->dev, &iomem_resource, size);
 		if (IS_ERR(res))
-			return -ENOMEM;
+			return PTR_ERR(res);
 		pgmap->range.start = res->start;
 		pgmap->range.end = res->end;
 		pgmap->type = MEMORY_DEVICE_PRIVATE;
@@ -1042,10 +1042,10 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	r = devm_memremap_pages(adev->dev, pgmap);
 	if (IS_ERR(r)) {
 		pr_err("failed to register HMM device memory\n");
-		/* Disable SVM support capability */
-		pgmap->type = 0;
 		if (pgmap->type == MEMORY_DEVICE_PRIVATE)
 			devm_release_mem_region(adev->dev, res->start, resource_size(res));
+		/* Disable SVM support capability */
+		pgmap->type = 0;
 		return PTR_ERR(r);
 	}
 
-- 
GitLab


From 25852d4b97572ff62ffee574cb8bb4bc551af23a Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 2 Oct 2023 14:27:13 -0400
Subject: [PATCH 2749/4076] drm/amdgpu: fix avg vs input power reporting on
 smu7

Hawaii, Bonaire, Fiji, and Tonga support average power, the others
support current power.

Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index b1a8799e2dee3..aa91730e4eaff 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -3999,6 +3999,7 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 	uint32_t sclk, mclk, activity_percent;
 	uint32_t offset, val_vid;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	/* size must be at least 4 bytes for all sensors */
 	if (*size < 4)
@@ -4042,7 +4043,21 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		return 0;
 	case AMDGPU_PP_SENSOR_GPU_INPUT_POWER:
-		return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
+		if ((adev->asic_type != CHIP_HAWAII) &&
+		    (adev->asic_type != CHIP_BONAIRE) &&
+		    (adev->asic_type != CHIP_FIJI) &&
+		    (adev->asic_type != CHIP_TONGA))
+			return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
+		else
+			return -EOPNOTSUPP;
+	case AMDGPU_PP_SENSOR_GPU_AVG_POWER:
+		if ((adev->asic_type != CHIP_HAWAII) &&
+		    (adev->asic_type != CHIP_BONAIRE) &&
+		    (adev->asic_type != CHIP_FIJI) &&
+		    (adev->asic_type != CHIP_TONGA))
+			return -EOPNOTSUPP;
+		else
+			return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
 	case AMDGPU_PP_SENSOR_VDDGFX:
 		if ((data->vr_config & VRCONF_VDDGFX_MASK) ==
 		    (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT))
-- 
GitLab


From d02069850fc102b07ae923535d5e212f2c8a34e9 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 2 Oct 2023 14:43:06 -0400
Subject: [PATCH 2750/4076] drm/amdgpu: fall back to INPUT power for AVG power
 via INFO IOCTL

For backwards compatibility with userspace.

Fixes: 47f1724db4fe ("drm/amd: Introduce `AMDGPU_PP_SENSOR_GPU_INPUT_POWER`")
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2897
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index b5ebafd4a3adf..bf4f48fe438d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1105,7 +1105,12 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			if (amdgpu_dpm_read_sensor(adev,
 						   AMDGPU_PP_SENSOR_GPU_AVG_POWER,
 						   (void *)&ui32, &ui32_size)) {
-				return -EINVAL;
+				/* fall back to input power for backwards compat */
+				if (amdgpu_dpm_read_sensor(adev,
+							   AMDGPU_PP_SENSOR_GPU_INPUT_POWER,
+							   (void *)&ui32, &ui32_size)) {
+					return -EINVAL;
+				}
 			}
 			ui32 >>= 8;
 			break;
-- 
GitLab


From 6127d7df4a5b66783da5a55ff60b3920a9c315a2 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 7 Dec 2023 10:36:56 -0500
Subject: [PATCH 2751/4076] drm/amdgpu/pm: clarify debugfs pm output

On APUs power is SoC power, not just GPU.
Clarify that for UVD/VCE/VCN the IP is powered down,
not disabled which can confusing and lead to concerns
that the IP is actually not available.

Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/amdgpu_pm.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index f3cb490fe79b1..087d57850304c 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -4349,11 +4349,19 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDNB, (void *)&value, &size))
 		seq_printf(m, "\t%u mV (VDDNB)\n", value);
 	size = sizeof(uint32_t);
-	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size))
-		seq_printf(m, "\t%u.%02u W (average GPU)\n", query >> 8, query & 0xff);
+	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size)) {
+		if (adev->flags & AMD_IS_APU)
+			seq_printf(m, "\t%u.%02u W (average SoC including CPU)\n", query >> 8, query & 0xff);
+		else
+			seq_printf(m, "\t%u.%02u W (average SoC)\n", query >> 8, query & 0xff);
+	}
 	size = sizeof(uint32_t);
-	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size))
-		seq_printf(m, "\t%u.%02u W (current GPU)\n", query >> 8, query & 0xff);
+	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size)) {
+		if (adev->flags & AMD_IS_APU)
+			seq_printf(m, "\t%u.%02u W (current SoC including CPU)\n", query >> 8, query & 0xff);
+		else
+			seq_printf(m, "\t%u.%02u W (current SoC)\n", query >> 8, query & 0xff);
+	}
 	size = sizeof(value);
 	seq_printf(m, "\n");
 
@@ -4379,9 +4387,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 		/* VCN clocks */
 		if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCN_POWER_STATE, (void *)&value, &size)) {
 			if (!value) {
-				seq_printf(m, "VCN: Disabled\n");
+				seq_printf(m, "VCN: Powered down\n");
 			} else {
-				seq_printf(m, "VCN: Enabled\n");
+				seq_printf(m, "VCN: Powered up\n");
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
 					seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
@@ -4393,9 +4401,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 		/* UVD clocks */
 		if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) {
 			if (!value) {
-				seq_printf(m, "UVD: Disabled\n");
+				seq_printf(m, "UVD: Powered down\n");
 			} else {
-				seq_printf(m, "UVD: Enabled\n");
+				seq_printf(m, "UVD: Powered up\n");
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
 					seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
@@ -4407,9 +4415,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 		/* VCE clocks */
 		if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) {
 			if (!value) {
-				seq_printf(m, "VCE: Disabled\n");
+				seq_printf(m, "VCE: Powered down\n");
 			} else {
-				seq_printf(m, "VCE: Enabled\n");
+				seq_printf(m, "VCE: Powered up\n");
 				if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size))
 					seq_printf(m, "\t%u MHz (ECCLK)\n", value/100);
 			}
-- 
GitLab


From 8f8cb7124e86c68ab09aa446664192d3829a40be Mon Sep 17 00:00:00 2001
From: Yifan Zhang <yifan1.zhang@amd.com>
Date: Mon, 8 Jan 2024 15:46:12 +0800
Subject: [PATCH 2752/4076] drm/amdgpu: update headers for nbio v7.11

This patch is to update headers for nbio v7.11.

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Tim Huang <Tim.Huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h    | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
index 7ee3d291120d5..6f80bfa7e41ac 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
@@ -8707,10 +8707,10 @@
 #define regBIF_BX1_MM_CFGREGS_CNTL_BASE_IDX                                                             2
 #define regBIF_BX1_BX_RESET_CNTL                                                                        0x00f0
 #define regBIF_BX1_BX_RESET_CNTL_BASE_IDX                                                               2
-#define regBIF_BX1_INTERRUPT_CNTL                                                                       0x8e11
-#define regBIF_BX1_INTERRUPT_CNTL_BASE_IDX                                                              5
-#define regBIF_BX1_INTERRUPT_CNTL2                                                                      0x8e12
-#define regBIF_BX1_INTERRUPT_CNTL2_BASE_IDX                                                             5
+#define regBIF_BX1_INTERRUPT_CNTL                                                                       0x00f1
+#define regBIF_BX1_INTERRUPT_CNTL_BASE_IDX                                                              2
+#define regBIF_BX1_INTERRUPT_CNTL2                                                                      0x00f2
+#define regBIF_BX1_INTERRUPT_CNTL2_BASE_IDX                                                             2
 #define regBIF_BX1_CLKREQB_PAD_CNTL                                                                     0x00f8
 #define regBIF_BX1_CLKREQB_PAD_CNTL_BASE_IDX                                                            2
 #define regBIF_BX1_BIF_FEATURES_CONTROL_MISC                                                            0x00fb
-- 
GitLab


From c9edcc1864f8529fd24441da40a1275232b5efc4 Mon Sep 17 00:00:00 2001
From: Yifan Zhang <yifan1.zhang@amd.com>
Date: Mon, 8 Jan 2024 16:05:27 +0800
Subject: [PATCH 2753/4076] drm/amdgpu: update ATHUB_MISC_CNTL offset for athub
 v3.3

This patch to update ATHUB_MISC_CNTL offset for athub v3.3

v2: correct a typo (Tim)
v3: correct patch title (Lang)

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Tim Huang <Tim.Huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/athub_v3_0.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
index f0737fb3a999e..d1bba9c64e16d 100644
--- a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
@@ -30,6 +30,8 @@
 
 #define regATHUB_MISC_CNTL_V3_0_1			0x00d7
 #define regATHUB_MISC_CNTL_V3_0_1_BASE_IDX		0
+#define regATHUB_MISC_CNTL_V3_3_0			0x00d8
+#define regATHUB_MISC_CNTL_V3_3_0_BASE_IDX		0
 
 
 static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
@@ -40,6 +42,9 @@ static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
 	case IP_VERSION(3, 0, 1):
 		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1);
 		break;
+	case IP_VERSION(3, 3, 0):
+		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_3_0);
+		break;
 	default:
 		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
 		break;
@@ -53,6 +58,9 @@ static void athub_v3_0_set_cg_cntl(struct amdgpu_device *adev, uint32_t data)
 	case IP_VERSION(3, 0, 1):
 		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1, data);
 		break;
+	case IP_VERSION(3, 3, 0):
+		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_3_0, data);
+		break;
 	default:
 		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
 		break;
-- 
GitLab


From 6616b5e1999146b1304abe78232af810080c67e3 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Fri, 5 Jan 2024 12:05:09 +0530
Subject: [PATCH 2754/4076] drm/amd/powerplay: Fix kzalloc parameter
 'ATOM_Tonga_PPM_Table' in 'get_platform_power_management_table()'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In 'struct phm_ppm_table *ptr' allocation using kzalloc, an incorrect
structure type is passed to sizeof() in kzalloc, larger structure types
were used, thus using correct type 'struct phm_ppm_table' fixes the
below:

drivers/gpu/drm/amd/amdgpu/../pm/powerplay/hwmgr/process_pptables_v1_0.c:203 get_platform_power_management_table() warn: struct type mismatch 'phm_ppm_table vs _ATOM_Tonga_PPM_Table'

Cc: Eric Huang <JinHuiEric.Huang@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
index f2a55c1413f59..17882f8dfdd34 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c
@@ -200,7 +200,7 @@ static int get_platform_power_management_table(
 		struct pp_hwmgr *hwmgr,
 		ATOM_Tonga_PPM_Table *atom_ppm_table)
 {
-	struct phm_ppm_table *ptr = kzalloc(sizeof(ATOM_Tonga_PPM_Table), GFP_KERNEL);
+	struct phm_ppm_table *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
 	struct phm_ppt_v1_information *pp_table_information =
 		(struct phm_ppt_v1_information *)(hwmgr->pptable);
 
-- 
GitLab


From 30d8dffab7d00da7fd13ecdb7d41a1f25ed6a4af Mon Sep 17 00:00:00 2001
From: Victor Lu <victorchengchi.lu@amd.com>
Date: Tue, 19 Dec 2023 11:55:09 -0500
Subject: [PATCH 2755/4076] drm/amdgpu: Do not program VM_L2_CNTL under SRIOV

VM_L2_CNTL* should not be programmed on driver unload under SRIOV.
These regs are skipped during SRIOV driver init.

Signed-off-by: Victor Lu <victorchengchi.lu@amd.com>
Reviewed-by: Vignesh Chander <Vignesh.Chander@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
index 95d06da544e2a..49aecdcee0069 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
@@ -456,10 +456,12 @@ static void gfxhub_v1_2_xcc_gart_disable(struct amdgpu_device *adev,
 		WREG32_SOC15_RLC(GC, GET_INST(GC, j), regMC_VM_MX_L1_TLB_CNTL, tmp);
 
 		/* Setup L2 cache */
-		tmp = RREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL);
-		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0);
-		WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL, tmp);
-		WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL3, 0);
+		if (!amdgpu_sriov_vf(adev)) {
+			tmp = RREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL);
+			tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0);
+			WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL, tmp);
+			WREG32_SOC15(GC, GET_INST(GC, j), regVM_L2_CNTL3, 0);
+		}
 	}
 }
 
-- 
GitLab


From fac4ebd79fed60e79cccafdad45a2bb8d3795044 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Thu, 4 Jan 2024 15:26:42 +0530
Subject: [PATCH 2756/4076] drm/amdgpu: Fix with right return code '-EIO' in
 'amdgpu_gmc_vram_checking()'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The amdgpu_gmc_vram_checking() function in emulation checks whether
all of the memory range of shared system memory could be accessed by
GPU, from this aspect, -EIO is returned for error scenarios.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c:919 gmc_v6_0_hw_init() warn: missing error code? 'r'
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c:1103 gmc_v7_0_hw_init() warn: missing error code? 'r'
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c:1223 gmc_v8_0_hw_init() warn: missing error code? 'r'
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c:2344 gmc_v9_0_hw_init() warn: missing error code? 'r'

Cc: Xiaojian Du <Xiaojian.Du@amd.com>
Cc: Lijo Lazar <lijo.lazar@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index d2f273d77e595..55784a9f26c4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -1045,21 +1045,28 @@ int amdgpu_gmc_vram_checking(struct amdgpu_device *adev)
 	 * seconds, so here, we just pick up three parts for emulation.
 	 */
 	ret = memcmp(vram_ptr, cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
 	ret = memcmp(vram_ptr + (size / 2), cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
 	ret = memcmp(vram_ptr + size - 10, cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
+release_buffer:
 	amdgpu_bo_free_kernel(&vram_bo, &vram_gpu,
 			&vram_ptr);
 
-	return 0;
+	return ret;
 }
 
 static ssize_t current_memory_partition_show(
-- 
GitLab


From 8e8272f0dc22e11b2791dc778b07bd66c208d5a8 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Fri, 5 Jan 2024 10:08:58 +0530
Subject: [PATCH 2757/4076] drm/amdgpu: Fix unsigned comparison with less than
 zero in vpe_u1_8_from_fraction()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The variables 'numerator' and 'denominator', are unsigned 16-bit integer
types, that can never be less than 0.

Thus fixing the below:
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c:62 vpe_u1_8_from_fraction() warn: unsigned 'numerator' is never less than zero.
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c:63 vpe_u1_8_from_fraction() warn: unsigned 'denominator' is never less than zero.

Cc: Peyton Lee <peytolee@amd.com>
Cc: Lang Yu <lang.yu@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Peyton Lee <peyton.lee@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 6f149b54d4d39..b9a15d51eb5c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -59,11 +59,8 @@ static inline uint16_t complete_integer_division_u16(
 
 static uint16_t vpe_u1_8_from_fraction(uint16_t numerator, uint16_t denominator)
 {
-	bool arg1_negative = numerator < 0;
-	bool arg2_negative = denominator < 0;
-
-	uint16_t arg1_value = (uint16_t)(arg1_negative ? -numerator : numerator);
-	uint16_t arg2_value = (uint16_t)(arg2_negative ? -denominator : denominator);
+	u16 arg1_value = numerator;
+	u16 arg2_value = denominator;
 
 	uint16_t remainder;
 
@@ -100,9 +97,6 @@ static uint16_t vpe_u1_8_from_fraction(uint16_t numerator, uint16_t denominator)
 		res_value += summand;
 	}
 
-	if (arg1_negative ^ arg2_negative)
-		res_value = -res_value;
-
 	return res_value;
 }
 
-- 
GitLab


From 8a44fdd3cf91debbd09b43bd2519ad2b2486ccf4 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Thu, 21 Dec 2023 18:13:11 +0530
Subject: [PATCH 2758/4076] drm/amdgpu: Release 'adev->pm.fw' before return in
 'amdgpu_device_need_post()'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In function 'amdgpu_device_need_post(struct amdgpu_device *adev)' -
'adev->pm.fw' may not be released before return.

Using the function release_firmware() to release adev->pm.fw.

Thus fixing the below:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1571 amdgpu_device_need_post() warn: 'adev->pm.fw' from request_firmware() not released on lines: 1554.

Cc: Monk Liu <Monk.Liu@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5bb444bb36cec..ecbc58269951c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1544,6 +1544,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 				return true;
 
 			fw_ver = *((uint32_t *)adev->pm.fw->data + 69);
+			release_firmware(adev->pm.fw);
 			if (fw_ver < 0x00160e00)
 				return true;
 		}
-- 
GitLab


From 2b9a073b7304f4a9e130d04794c91a0c4f9a5c12 Mon Sep 17 00:00:00 2001
From: Yifan Zhang <yifan1.zhang@amd.com>
Date: Tue, 9 Jan 2024 09:19:22 +0800
Subject: [PATCH 2759/4076] drm/amdgpu: update regGL2C_CTRL4 value in golden
 setting

This patch to update regGL2C_CTRL4 in golden setting.

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Reviewed-by: Tim Huang <Tim.Huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.7.x
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index c7242877d5d31..0ea0866c261f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -115,7 +115,7 @@ static const struct soc15_reg_golden golden_settings_gc_11_5_0[] = {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL, 0xffffffff, 0xf37fff3f),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL3, 0xfffffffb, 0x00f40188),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x8000b007),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x80009007),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regPA_CL_ENHANCE, 0xf1ffffff, 0x00880007),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regPC_CONFIG_CNTL_1, 0xffffffff, 0x00010000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL_AUX, 0xf7f7ffff, 0x01030000),
-- 
GitLab


From 7073934f5d73f8b53308963cee36f0d389ea857c Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Mon, 8 Jan 2024 21:20:28 +0530
Subject: [PATCH 2760/4076] drm/amd/display: Fix variable deferencing before
 NULL check in edp_setup_replay()

In edp_setup_replay(), 'struct dc *dc' & 'struct dmub_replay *replay'
was dereferenced before the pointer 'link' & 'replay' NULL check.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_edp_panel_control.c:947 edp_setup_replay() warn: variable dereferenced before check 'link' (see line 933)

Cc: stable@vger.kernel.org
Cc: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../dc/link/protocols/link_edp_panel_control.c        | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index 7f11965282186..046d3e2054153 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -930,8 +930,8 @@ bool edp_get_replay_state(const struct dc_link *link, uint64_t *state)
 bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream)
 {
 	/* To-do: Setup Replay */
-	struct dc *dc = link->ctx->dc;
-	struct dmub_replay *replay = dc->res_pool->replay;
+	struct dc *dc;
+	struct dmub_replay *replay;
 	int i;
 	unsigned int panel_inst;
 	struct replay_context replay_context = { 0 };
@@ -947,6 +947,10 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
 	if (!link)
 		return false;
 
+	dc = link->ctx->dc;
+
+	replay = dc->res_pool->replay;
+
 	if (!replay)
 		return false;
 
@@ -975,8 +979,7 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
 
 	replay_context.line_time_in_ns = lineTimeInNs;
 
-	if (replay)
-		link->replay_settings.replay_feature_enabled =
+	link->replay_settings.replay_feature_enabled =
 			replay->funcs->replay_copy_settings(replay, link, &replay_context, panel_inst);
 	if (link->replay_settings.replay_feature_enabled) {
 
-- 
GitLab


From 6c5683bd9ecaa7f199c3122c1010ece5d59b1aef Mon Sep 17 00:00:00 2001
From: Le Ma <le.ma@amd.com>
Date: Tue, 9 Jan 2024 12:06:25 +0800
Subject: [PATCH 2761/4076] Revert "drm/amdgpu: add param to specify fw bo
 location for front-door loading"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit c572abffe9f50c8ba33060865449313b3f588c35.

Will use debug module param instead of independent module param.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h       | 2 --
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c   | 5 -----
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c   | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 3 +--
 4 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9da14436a3738..616b6c9117679 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -254,8 +254,6 @@ extern int amdgpu_agp;
 
 extern int amdgpu_wbrf;
 
-extern int fw_bo_location;
-
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 852cec98ff262..880137774b4eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -210,7 +210,6 @@ int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
 int amdgpu_agp = -1; /* auto */
 int amdgpu_wbrf = -1;
-int fw_bo_location = -1;
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -990,10 +989,6 @@ MODULE_PARM_DESC(wbrf,
 	"Enable Wifi RFI interference mitigation (0 = disabled, 1 = enabled, -1 = auto(default)");
 module_param_named(wbrf, amdgpu_wbrf, int, 0444);
 
-MODULE_PARM_DESC(fw_bo_location,
-	"location to put firmware bo for frontdoor loading (-1 = auto (default), 0 = on ram, 1 = on vram");
-module_param(fw_bo_location, int, 0644);
-
 /* These devices are not supported by amdgpu.
  * They are supported by the mach64, r128, radeon drivers
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 2addbdf88394b..1bf975b8d083e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -466,7 +466,7 @@ static int psp_sw_init(void *handle)
 	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-				      (amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
+				      amdgpu_sriov_vf(adev) ?
 				      AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 				      &psp->fw_pri_bo,
 				      &psp->fw_pri_mc_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index d334e42fe0ebe..0efb2568cb65f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -1062,8 +1062,7 @@ int amdgpu_ucode_create_bo(struct amdgpu_device *adev)
 {
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT) {
 		amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
-			(amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
-			AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
+			amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 			&adev->firmware.fw_buf,
 			&adev->firmware.fw_buf_mc,
 			&adev->firmware.fw_buf_ptr);
-- 
GitLab


From d20e1aec8862e48a352ca86969cee6f530dd41d5 Mon Sep 17 00:00:00 2001
From: Le Ma <le.ma@amd.com>
Date: Tue, 9 Jan 2024 17:44:39 +0800
Subject: [PATCH 2762/4076] drm/amdgpu: add debug flag to place fw bo on vram
 for frontdoor loading
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use debug_mask=0x8 param to help isolating data path issues
on new systems in early phase.

v2: rename the flag for explicitness (lijo)

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h       | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c   | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c   | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 3 ++-
 4 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 616b6c9117679..3d8a48f46b015 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1144,6 +1144,7 @@ struct amdgpu_device {
 	bool                            debug_vm;
 	bool                            debug_largebar;
 	bool                            debug_disable_soft_recovery;
+	bool                            debug_use_vram_fw_buf;
 };
 
 static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 880137774b4eb..0776b0c5e4e4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -128,6 +128,7 @@ enum AMDGPU_DEBUG_MASK {
 	AMDGPU_DEBUG_VM = BIT(0),
 	AMDGPU_DEBUG_LARGEBAR = BIT(1),
 	AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY = BIT(2),
+	AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3),
 };
 
 unsigned int amdgpu_vram_limit = UINT_MAX;
@@ -2117,6 +2118,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev)
 		pr_info("debug: soft reset for GPU recovery disabled\n");
 		adev->debug_disable_soft_recovery = true;
 	}
+
+	if (amdgpu_debug_mask & AMDGPU_DEBUG_USE_VRAM_FW_BUF) {
+		pr_info("debug: place fw in vram for frontdoor loading\n");
+		adev->debug_use_vram_fw_buf = true;
+	}
 }
 
 static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 1bf975b8d083e..0328616473f80 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -466,7 +466,7 @@ static int psp_sw_init(void *handle)
 	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-				      amdgpu_sriov_vf(adev) ?
+				      (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
 				      AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 				      &psp->fw_pri_bo,
 				      &psp->fw_pri_mc_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 0efb2568cb65f..3e12763e477aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -1062,7 +1062,8 @@ int amdgpu_ucode_create_bo(struct amdgpu_device *adev)
 {
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT) {
 		amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
-			amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
+			(amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
+			AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 			&adev->firmware.fw_buf,
 			&adev->firmware.fw_buf_mc,
 			&adev->firmware.fw_buf_ptr);
-- 
GitLab


From 51258acdc4758d43f03ec9cab6f3fa72a2838f0e Mon Sep 17 00:00:00 2001
From: Le Ma <le.ma@amd.com>
Date: Tue, 9 Jan 2024 18:06:35 +0800
Subject: [PATCH 2763/4076] drm/amdgpu: move debug options init prior to amdgpu
 device init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To bring debug options into effect in early initialization phase

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0776b0c5e4e4f..5c9caf5fa0758 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2234,6 +2234,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 
 	pci_set_drvdata(pdev, ddev);
 
+	amdgpu_init_debug_options(adev);
+
 	ret = amdgpu_driver_load_kms(adev, flags);
 	if (ret)
 		goto err_pci;
@@ -2314,8 +2316,6 @@ retry_init:
 			amdgpu_get_secondary_funcs(adev);
 	}
 
-	amdgpu_init_debug_options(adev);
-
 	return 0;
 
 err_pci:
-- 
GitLab


From c3d5e297dcae88274dc6924db337a2159279eced Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 9 Jan 2024 10:45:42 -0500
Subject: [PATCH 2764/4076] drm/amdgpu: drop exp hw support check for GC 9.4.3

No longer needed.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.7.x
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 0431eafa86b53..c7d60dd0fb975 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1963,8 +1963,6 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		break;
 	case IP_VERSION(9, 4, 3):
-		if (!amdgpu_exp_hw_support)
-			return -EINVAL;
 		amdgpu_device_ip_block_add(adev, &gfx_v9_4_3_ip_block);
 		break;
 	case IP_VERSION(10, 1, 10):
-- 
GitLab


From d7a254fad873775ce6c32b77796c81e81e6b7f2e Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Tue, 9 Jan 2024 16:57:26 +0530
Subject: [PATCH 2765/4076] drm/amdkfd: Fix 'node' NULL check in
 'svm_range_get_range_boundaries()'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Range interval [start, last] is ordered by rb_tree, rb_prev, rb_next
return value still needs NULL check, thus modified from "node" to "rb_node".

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_svm.c:2691 svm_range_get_range_boundaries() warn: can 'node' even be NULL?

Suggested-by: Philip Yang <Philip.Yang@amd.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 4e9f07c7a9376..c50a0dc9c9c07 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2654,6 +2654,7 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 {
 	struct vm_area_struct *vma;
 	struct interval_tree_node *node;
+	struct rb_node *rb_node;
 	unsigned long start_limit, end_limit;
 
 	vma = vma_lookup(p->mm, addr << PAGE_SHIFT);
@@ -2673,16 +2674,15 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 	if (node) {
 		end_limit = min(end_limit, node->start);
 		/* Last range that ends before the fault address */
-		node = container_of(rb_prev(&node->rb),
-				    struct interval_tree_node, rb);
+		rb_node = rb_prev(&node->rb);
 	} else {
 		/* Last range must end before addr because
 		 * there was no range after addr
 		 */
-		node = container_of(rb_last(&p->svms.objects.rb_root),
-				    struct interval_tree_node, rb);
+		rb_node = rb_last(&p->svms.objects.rb_root);
 	}
-	if (node) {
+	if (rb_node) {
+		node = container_of(rb_node, struct interval_tree_node, rb);
 		if (node->last >= addr) {
 			WARN(1, "Overlap with prev node and page fault addr\n");
 			return -EFAULT;
-- 
GitLab


From 91739a897c12dcec699e53f390be1b4abdeef3a0 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 11 Jan 2024 09:47:33 +0530
Subject: [PATCH 2766/4076] drm/amd/pm: Add error log for smu v13.0.6 reset

For all mode-2 reset fail cases, add error log.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.7.x
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 4ebc6b421c2cb..7513d1cfeebd7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2235,17 +2235,18 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu)
 			continue;
 		}
 
-		if (ret) {
-			dev_err(adev->dev,
-				"failed to send mode2 message \tparam: 0x%08x error code %d\n",
-				SMU_RESET_MODE_2, ret);
+		if (ret)
 			goto out;
-		}
+
 	} while (ret == -ETIME && timeout);
 
 out:
 	mutex_unlock(&smu->message_lock);
 
+	if (ret)
+		dev_err(adev->dev, "failed to send mode2 reset, error code %d",
+			ret);
+
 	return ret;
 }
 
-- 
GitLab


From a992c90d8ed3929b70ae815ce21ca5651cc0a692 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 11 Jan 2024 15:28:53 +0530
Subject: [PATCH 2767/4076] drm/amd/pm: Fix smuv13.0.6 current clock reporting

When current clock is equal to max dpm level clock, the level is not
indicated correctly with *. Fix by comparing current clock against dpm
level value.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.7.x
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 7513d1cfeebd7..a28649f210933 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -970,7 +970,9 @@ static int smu_v13_0_6_print_clks(struct smu_context *smu, char *buf, int size,
 			if (i < (clocks.num_levels - 1))
 				clk2 = clocks.data[i + 1].clocks_in_khz / 1000;
 
-			if (curr_clk >= clk1 && curr_clk < clk2) {
+			if (curr_clk == clk1) {
+				level = i;
+			} else if (curr_clk >= clk1 && curr_clk < clk2) {
 				level = (curr_clk - clk1) <= (clk2 - curr_clk) ?
 						i :
 						i + 1;
-- 
GitLab


From d7643fe6fb76edb1f2f1497bf5e8b8f4774b5129 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 10 Jan 2024 13:46:47 -0700
Subject: [PATCH 2768/4076] drm/amd/display: Avoid enum conversion warning

Clang warns (or errors with CONFIG_WERROR=y) when performing arithmetic
with different enumerated types, which is usually a bug:

    drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_dp_dpia_bw.c:548:24: error: arithmetic between different enumeration types ('const enum dc_link_rate' and 'const enum dc_lane_count') [-Werror,-Wenum-enum-conversion]
      548 |                         link_cap->link_rate * link_cap->lane_count * LINK_RATE_REF_FREQ_IN_KHZ * 8;
          |                         ~~~~~~~~~~~~~~~~~~~ ^ ~~~~~~~~~~~~~~~~~~~~
    1 error generated.

In this case, there is not a problem because the enumerated types are
basically treated as '#define' values. Add an explicit cast to an
integral type to silence the warning.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1976
Fixes: 5f3bce13266e ("drm/amd/display: Request usb4 bw for mst streams")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c  | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index 4ef1a6a1d1295..dd0d2b206462c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -544,8 +544,9 @@ int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link)
 		 */
 		const struct dc_link_settings *link_cap =
 			dc_link_get_link_cap(link);
-		uint32_t link_bw_in_kbps =
-			link_cap->link_rate * link_cap->lane_count * LINK_RATE_REF_FREQ_IN_KHZ * 8;
+		uint32_t link_bw_in_kbps = (uint32_t)link_cap->link_rate *
+					   (uint32_t)link_cap->lane_count *
+					   LINK_RATE_REF_FREQ_IN_KHZ * 8;
 		link_mst_overhead = (link_bw_in_kbps / 64) + ((link_bw_in_kbps % 64) ? 1 : 0);
 	}
 
-- 
GitLab


From c2518da8e6b0e248cfff1d4b6682e14020bd4d3f Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 10 Jan 2024 09:14:35 -0500
Subject: [PATCH 2769/4076] selftests: bonding: Change script interpreter

The tests changed by this patch, as well as the scripts they source, use
features which are not part of POSIX sh (ex. 'source' and 'local'). As a
result, these tests fail when /bin/sh is dash such as on Debian. Change the
interpreter to bash so that these tests can run successfully.

Fixes: d43eff0b85ae ("selftests: bonding: up/down delay w/ slave link flapping")
Tested-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/drivers/net/bonding/mode-1-recovery-updelay.sh    | 2 +-
 .../selftests/drivers/net/bonding/mode-2-recovery-updelay.sh    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
index ad4c845a4ac7c..b76bf50309524 100755
--- a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
+++ b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Regression Test:
diff --git a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
index 2330d37453f95..8c26190021479 100755
--- a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
+++ b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Regression Test:
-- 
GitLab


From 49078c1b80b6f7e214ff60cf6f44750b33019cad Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 10 Jan 2024 09:14:36 -0500
Subject: [PATCH 2770/4076] selftests: forwarding: Remove executable bits from
 lib.sh

The lib.sh script is meant to be sourced from other scripts, not executed
directly. Therefore, remove the executable bits from lib.sh's permissions.

Fixes: fe32dffdcd33 ("selftests: forwarding: add TCPDUMP_EXTRA_FLAGS to lib.sh")
Tested-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/forwarding/lib.sh | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 mode change 100755 => 100644 tools/testing/selftests/net/forwarding/lib.sh

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
old mode 100755
new mode 100644
-- 
GitLab


From ddb17dc880eeaac37b5a6e984de07b882de7d78d Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 16 Jan 2024 10:32:20 +0300
Subject: [PATCH 2771/4076] fs/ntfs3: Use kvfree to free memory allocated by
 kvmalloc

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/attrlist.c | 4 ++--
 fs/ntfs3/bitmap.c   | 4 ++--
 fs/ntfs3/frecord.c  | 4 ++--
 fs/ntfs3/super.c    | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index 48e7da47c6b71..9f4bd8d260901 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -29,7 +29,7 @@ static inline bool al_is_valid_le(const struct ntfs_inode *ni,
 void al_destroy(struct ntfs_inode *ni)
 {
 	run_close(&ni->attr_list.run);
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.size = 0;
 	ni->attr_list.dirty = false;
@@ -318,7 +318,7 @@ int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name,
 		memcpy(ptr, al->le, off);
 		memcpy(Add2Ptr(ptr, off + sz), le, old_size - off);
 		le = Add2Ptr(ptr, off);
-		kfree(al->le);
+		kvfree(al->le);
 		al->le = ptr;
 	} else {
 		memmove(Add2Ptr(le, sz), le, old_size - off);
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index 63f14a0232f6a..845f9b22deef0 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -124,7 +124,7 @@ void wnd_close(struct wnd_bitmap *wnd)
 {
 	struct rb_node *node, *next;
 
-	kfree(wnd->free_bits);
+	kvfree(wnd->free_bits);
 	wnd->free_bits = NULL;
 	run_close(&wnd->run);
 
@@ -1360,7 +1360,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 		memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short));
 		memset(new_free + wnd->nwnd, 0,
 		       (new_wnd - wnd->nwnd) * sizeof(short));
-		kfree(wnd->free_bits);
+		kvfree(wnd->free_bits);
 		wnd->free_bits = new_free;
 	}
 
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 6ff4f70ba0775..2636ab7640ace 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -778,7 +778,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 	run_deallocate(sbi, &ni->attr_list.run, true);
 	run_close(&ni->attr_list.run);
 	ni->attr_list.size = 0;
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.dirty = false;
 
@@ -927,7 +927,7 @@ int ni_create_attr_list(struct ntfs_inode *ni)
 	return 0;
 
 out:
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.size = 0;
 	return err;
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 65ef4b57411f0..c55a29793a8d8 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -625,7 +625,7 @@ static void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
 {
 	kfree(sbi->new_rec);
 	kvfree(ntfs_put_shared(sbi->upcase));
-	kfree(sbi->def_table);
+	kvfree(sbi->def_table);
 	kfree(sbi->compress.lznt);
 #ifdef CONFIG_NTFS3_LZX_XPRESS
 	xpress_free_decompressor(sbi->compress.xpress);
-- 
GitLab


From a23aa04042187cbde16f470b49d4ad60d32e9206 Mon Sep 17 00:00:00 2001
From: Qiang Ma <maqianga@uniontech.com>
Date: Fri, 12 Jan 2024 10:12:49 +0800
Subject: [PATCH 2772/4076] net: stmmac: ethtool: Fixed calltrace caused by
 unbalanced disable_irq_wake calls

We found the following dmesg calltrace when testing the GMAC NIC notebook:

[9.448656] ------------[ cut here ]------------
[9.448658] Unbalanced IRQ 43 wake disable
[9.448673] WARNING: CPU: 3 PID: 1083 at kernel/irq/manage.c:688 irq_set_irq_wake+0xe0/0x128
[9.448717] CPU: 3 PID: 1083 Comm: ethtool Tainted: G           O      4.19 #1
[9.448773]         ...
[9.448774] Call Trace:
[9.448781] [<9000000000209b5c>] show_stack+0x34/0x140
[9.448788] [<9000000000d52700>] dump_stack+0x98/0xd0
[9.448794] [<9000000000228610>] __warn+0xa8/0x120
[9.448797] [<9000000000d2fb60>] report_bug+0x98/0x130
[9.448800] [<900000000020a418>] do_bp+0x248/0x2f0
[9.448805] [<90000000002035f4>] handle_bp_int+0x4c/0x78
[9.448808] [<900000000029ea40>] irq_set_irq_wake+0xe0/0x128
[9.448813] [<9000000000a96a7c>] stmmac_set_wol+0x134/0x150
[9.448819] [<9000000000be6ed0>] dev_ethtool+0x1368/0x2440
[9.448824] [<9000000000c08350>] dev_ioctl+0x1f8/0x3e0
[9.448827] [<9000000000bb2a34>] sock_ioctl+0x2a4/0x450
[9.448832] [<900000000046f044>] do_vfs_ioctl+0xa4/0x738
[9.448834] [<900000000046f778>] ksys_ioctl+0xa0/0xe8
[9.448837] [<900000000046f7d8>] sys_ioctl+0x18/0x28
[9.448840] [<9000000000211ab4>] syscall_common+0x20/0x34
[9.448842] ---[ end trace 40c18d9aec863c3e ]---

Multiple disable_irq_wake() calls will keep decreasing the IRQ
wake_depth, When wake_depth is 0, calling disable_irq_wake() again,
will report the above calltrace.

Due to the need to appear in pairs, we cannot call disable_irq_wake()
without calling enable_irq_wake(). Fix this by making sure there are
no unbalanced disable_irq_wake() calls.

Fixes: 3172d3afa998 ("stmmac: support wake up irq from external sources (v3)")
Signed-off-by: Qiang Ma <maqianga@uniontech.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240112021249.24598-1-maqianga@uniontech.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h         |  1 +
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 10 ++++++++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c    |  1 +
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 9f89acf310502..f155e4841c62b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -267,6 +267,7 @@ struct stmmac_priv {
 	u32 msg_enable;
 	int wolopts;
 	int wol_irq;
+	bool wol_irq_disabled;
 	int clk_csr;
 	struct timer_list eee_ctrl_timer;
 	int lpi_irq;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 0f8bfba4443d1..42d27b97dd1d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -832,10 +832,16 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	if (wol->wolopts) {
 		pr_info("stmmac: wakeup enable\n");
 		device_set_wakeup_enable(priv->device, 1);
-		enable_irq_wake(priv->wol_irq);
+		/* Avoid unbalanced enable_irq_wake calls */
+		if (priv->wol_irq_disabled)
+			enable_irq_wake(priv->wol_irq);
+		priv->wol_irq_disabled = false;
 	} else {
 		device_set_wakeup_enable(priv->device, 0);
-		disable_irq_wake(priv->wol_irq);
+		/* Avoid unbalanced disable_irq_wake calls */
+		if (!priv->wol_irq_disabled)
+			disable_irq_wake(priv->wol_irq);
+		priv->wol_irq_disabled = true;
 	}
 
 	mutex_lock(&priv->lock);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 47de466e432c0..c78a96b8eb649 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3628,6 +3628,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 	/* Request the Wake IRQ in case of another line
 	 * is used for WoL
 	 */
+	priv->wol_irq_disabled = true;
 	if (priv->wol_irq > 0 && priv->wol_irq != dev->irq) {
 		int_name = priv->int_name_wol;
 		sprintf(int_name, "%s:%s", dev->name, "wol");
-- 
GitLab


From 08ac6f132dd77e40f786d8af51140c96c6d739c9 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Date: Wed, 3 Jan 2024 15:31:07 +0200
Subject: [PATCH 2773/4076] drm/bridge: sii902x: Fix probing race issue

A null pointer dereference crash has been observed rarely on TI
platforms using sii9022 bridge:

[   53.271356]  sii902x_get_edid+0x34/0x70 [sii902x]
[   53.276066]  sii902x_bridge_get_edid+0x14/0x20 [sii902x]
[   53.281381]  drm_bridge_get_edid+0x20/0x34 [drm]
[   53.286305]  drm_bridge_connector_get_modes+0x8c/0xcc [drm_kms_helper]
[   53.292955]  drm_helper_probe_single_connector_modes+0x190/0x538 [drm_kms_helper]
[   53.300510]  drm_client_modeset_probe+0x1f0/0xbd4 [drm]
[   53.305958]  __drm_fb_helper_initial_config_and_unlock+0x50/0x510 [drm_kms_helper]
[   53.313611]  drm_fb_helper_initial_config+0x48/0x58 [drm_kms_helper]
[   53.320039]  drm_fbdev_dma_client_hotplug+0x84/0xd4 [drm_dma_helper]
[   53.326401]  drm_client_register+0x5c/0xa0 [drm]
[   53.331216]  drm_fbdev_dma_setup+0xc8/0x13c [drm_dma_helper]
[   53.336881]  tidss_probe+0x128/0x264 [tidss]
[   53.341174]  platform_probe+0x68/0xc4
[   53.344841]  really_probe+0x188/0x3c4
[   53.348501]  __driver_probe_device+0x7c/0x16c
[   53.352854]  driver_probe_device+0x3c/0x10c
[   53.357033]  __device_attach_driver+0xbc/0x158
[   53.361472]  bus_for_each_drv+0x88/0xe8
[   53.365303]  __device_attach+0xa0/0x1b4
[   53.369135]  device_initial_probe+0x14/0x20
[   53.373314]  bus_probe_device+0xb0/0xb4
[   53.377145]  deferred_probe_work_func+0xcc/0x124
[   53.381757]  process_one_work+0x1f0/0x518
[   53.385770]  worker_thread+0x1e8/0x3dc
[   53.389519]  kthread+0x11c/0x120
[   53.392750]  ret_from_fork+0x10/0x20

The issue here is as follows:

- tidss probes, but is deferred as sii902x is still missing.
- sii902x starts probing and enters sii902x_init().
- sii902x calls drm_bridge_add(). Now the sii902x bridge is ready from
  DRM's perspective.
- sii902x calls sii902x_audio_codec_init() and
  platform_device_register_data()
- The registration of the audio platform device causes probing of the
  deferred devices.
- tidss probes, which eventually causes sii902x_bridge_get_edid() to be
  called.
- sii902x_bridge_get_edid() tries to use the i2c to read the edid.
  However, the sii902x driver has not set up the i2c part yet, leading
  to the crash.

Fix this by moving the drm_bridge_add() to the end of the
sii902x_init(), which is also at the very end of sii902x_probe().

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Fixes: 21d808405fe4 ("drm/bridge/sii902x: Fix EDID readback")
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20240103-si902x-fixes-v1-1-b9fd3e448411@ideasonboard.com
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240103-si902x-fixes-v1-1-b9fd3e448411@ideasonboard.com
---
 drivers/gpu/drm/bridge/sii902x.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index 2bdc5b439bebd..69da73e414a9a 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -1080,16 +1080,6 @@ static int sii902x_init(struct sii902x *sii902x)
 			return ret;
 	}
 
-	sii902x->bridge.funcs = &sii902x_bridge_funcs;
-	sii902x->bridge.of_node = dev->of_node;
-	sii902x->bridge.timings = &default_sii902x_timings;
-	sii902x->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID;
-
-	if (sii902x->i2c->irq > 0)
-		sii902x->bridge.ops |= DRM_BRIDGE_OP_HPD;
-
-	drm_bridge_add(&sii902x->bridge);
-
 	sii902x_audio_codec_init(sii902x, dev);
 
 	i2c_set_clientdata(sii902x->i2c, sii902x);
@@ -1102,7 +1092,21 @@ static int sii902x_init(struct sii902x *sii902x)
 		return -ENOMEM;
 
 	sii902x->i2cmux->priv = sii902x;
-	return i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0);
+	ret = i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0);
+	if (ret)
+		return ret;
+
+	sii902x->bridge.funcs = &sii902x_bridge_funcs;
+	sii902x->bridge.of_node = dev->of_node;
+	sii902x->bridge.timings = &default_sii902x_timings;
+	sii902x->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID;
+
+	if (sii902x->i2c->irq > 0)
+		sii902x->bridge.ops |= DRM_BRIDGE_OP_HPD;
+
+	drm_bridge_add(&sii902x->bridge);
+
+	return 0;
 }
 
 static int sii902x_probe(struct i2c_client *client)
@@ -1170,12 +1174,11 @@ static int sii902x_probe(struct i2c_client *client)
 }
 
 static void sii902x_remove(struct i2c_client *client)
-
 {
 	struct sii902x *sii902x = i2c_get_clientdata(client);
 
-	i2c_mux_del_adapters(sii902x->i2cmux);
 	drm_bridge_remove(&sii902x->bridge);
+	i2c_mux_del_adapters(sii902x->i2cmux);
 }
 
 static const struct of_device_id sii902x_dt_ids[] = {
-- 
GitLab


From 3fc6c76a8d208d3955c9e64b382d0ff370bc61fc Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Date: Wed, 3 Jan 2024 15:31:08 +0200
Subject: [PATCH 2774/4076] drm/bridge: sii902x: Fix audio codec unregistration

The driver never unregisters the audio codec platform device, which can
lead to a crash on module reloading, nor does it handle the return value
from sii902x_audio_codec_init().

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Fixes: ff5781634c41 ("drm/bridge: sii902x: Implement HDMI audio support")
Cc: Jyri Sarha <jsarha@ti.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20240103-si902x-fixes-v1-2-b9fd3e448411@ideasonboard.com
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240103-si902x-fixes-v1-2-b9fd3e448411@ideasonboard.com
---
 drivers/gpu/drm/bridge/sii902x.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index 69da73e414a9a..4560ae9cbce15 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -1080,7 +1080,9 @@ static int sii902x_init(struct sii902x *sii902x)
 			return ret;
 	}
 
-	sii902x_audio_codec_init(sii902x, dev);
+	ret = sii902x_audio_codec_init(sii902x, dev);
+	if (ret)
+		return ret;
 
 	i2c_set_clientdata(sii902x->i2c, sii902x);
 
@@ -1088,13 +1090,15 @@ static int sii902x_init(struct sii902x *sii902x)
 					1, 0, I2C_MUX_GATE,
 					sii902x_i2c_bypass_select,
 					sii902x_i2c_bypass_deselect);
-	if (!sii902x->i2cmux)
-		return -ENOMEM;
+	if (!sii902x->i2cmux) {
+		ret = -ENOMEM;
+		goto err_unreg_audio;
+	}
 
 	sii902x->i2cmux->priv = sii902x;
 	ret = i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0);
 	if (ret)
-		return ret;
+		goto err_unreg_audio;
 
 	sii902x->bridge.funcs = &sii902x_bridge_funcs;
 	sii902x->bridge.of_node = dev->of_node;
@@ -1107,6 +1111,12 @@ static int sii902x_init(struct sii902x *sii902x)
 	drm_bridge_add(&sii902x->bridge);
 
 	return 0;
+
+err_unreg_audio:
+	if (!PTR_ERR_OR_ZERO(sii902x->audio.pdev))
+		platform_device_unregister(sii902x->audio.pdev);
+
+	return ret;
 }
 
 static int sii902x_probe(struct i2c_client *client)
@@ -1179,6 +1189,9 @@ static void sii902x_remove(struct i2c_client *client)
 
 	drm_bridge_remove(&sii902x->bridge);
 	i2c_mux_del_adapters(sii902x->i2cmux);
+
+	if (!PTR_ERR_OR_ZERO(sii902x->audio.pdev))
+		platform_device_unregister(sii902x->audio.pdev);
 }
 
 static const struct of_device_id sii902x_dt_ids[] = {
-- 
GitLab


From bc7863d18677df66b2c7a0e172c91296ff380f11 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=C3=87a=C4=9Fhan=20Demir?= <caghandemir@marun.edu.tr>
Date: Mon, 15 Jan 2024 20:23:03 +0300
Subject: [PATCH 2775/4076] ALSA: hda/relatek: Enable Mute LED on HP Laptop
 15s-fq2xxx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This HP Laptop uses ALC236 codec with COEF 0x07 idx 1 controlling
the mute LED. This patch enables the already existing quirk for
this device.

Signed-off-by: Çağhan Demir <caghandemir@marun.edu.tr>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240115172303.4718-1-caghandemir@marun.edu.tr
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b68c947570510..0f0a03e890156 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9861,6 +9861,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f6, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
 	SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
+	SND_PCI_QUIRK(0x103c, 0x87fe, "HP Laptop 15s-fq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8811, "HP Spectre x360 15-eb1xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
-- 
GitLab


From b018cee7369896c7a15bfdbe88f168f3dbd8ba27 Mon Sep 17 00:00:00 2001
From: Yo-Jung Lin <leo.lin@canonical.com>
Date: Tue, 16 Jan 2024 10:07:19 +0800
Subject: [PATCH 2776/4076] ALSA: hda/realtek: Enable mute/micmute LEDs and
 limit mic boost on HP ZBook

On some HP ZBooks, the audio LEDs can be enabled by
ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF. So use it accordingly.

Signed-off-by: Yo-Jung Lin <leo.lin@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240116020722.27236-1-leo.lin@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 0f0a03e890156..dbf31fe901daa 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9956,6 +9956,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
-- 
GitLab


From e37617c8e53a1f7fcba6d5e1041f4fd8a2425c27 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Sun, 14 Jan 2024 19:36:00 +0100
Subject: [PATCH 2777/4076] sched/fair: Fix frequency selection for
 non-invariant case

Linus reported a ~50% performance regression on single-threaded
workloads on his AMD Ryzen system, and bisected it to:

  9c0b4bb7f630 ("sched/cpufreq: Rework schedutil governor performance estimation")

When frequency invariance is not enabled, get_capacity_ref_freq(policy)
is supposed to return the current frequency and the performance margin
applied by map_util_perf(), enabling the utilization to go above the
maximum compute capacity and to select a higher frequency than the current one.

After the changes in 9c0b4bb7f630, the performance margin was applied
earlier in the path to take into account utilization clampings and
we couldn't get a utilization higher than the maximum compute capacity,
and the CPU remained 'stuck' at lower frequencies.

To fix this, we must use a frequency above the current frequency to
get a chance to select a higher OPP when the current one becomes fully used.
Apply the same margin and return a frequency 25% higher than the current
one in order to switch to the next OPP before we fully use the CPU
at the current one.

[ mingo: Clarified the changelog. ]

Fixes: 9c0b4bb7f630 ("sched/cpufreq: Rework schedutil governor performance estimation")
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Bisected-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Wyes Karny <wkarny@gmail.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Wyes Karny <wkarny@gmail.com>
Link: https://lore.kernel.org/r/20240114183600.135316-1-vincent.guittot@linaro.org
---
 kernel/sched/cpufreq_schedutil.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 95c3c097083e5..eece6244f9d2f 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -133,7 +133,11 @@ unsigned long get_capacity_ref_freq(struct cpufreq_policy *policy)
 	if (arch_scale_freq_invariant())
 		return policy->cpuinfo.max_freq;
 
-	return policy->cur;
+	/*
+	 * Apply a 25% margin so that we select a higher frequency than
+	 * the current one before the CPU is fully busy:
+	 */
+	return policy->cur + (policy->cur >> 2);
 }
 
 /**
-- 
GitLab


From 2c4ca7977298c6a3d237d7d703df97e043b75c12 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 14 Jan 2024 14:47:26 -0800
Subject: [PATCH 2778/4076] selftests: netdevsim: sprinkle more udevadm settle

Number of tests are failing when netdev renaming is active
on the system. Add udevadm settle in logic determining
the names.

Fixes: 242aaf03dc9b ("selftests: add a test for ethtool pause stats")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240114224726.1210532-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh | 1 +
 tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh | 1 +
 2 files changed, 2 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
index 922744059aaa2..80160579e0cc1 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
@@ -51,6 +51,7 @@ function make_netdev {
     fi
 
     echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device
+    udevadm settle
     # get new device name
     ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/
 }
diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
index 1b08e042cf942..4855ef597a152 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
@@ -233,6 +233,7 @@ function print_tables {
 function get_netdev_name {
     local -n old=$1
 
+    udevadm settle
     new=$(ls /sys/class/net)
 
     for netdev in $new; do
-- 
GitLab


From 4697381bd076adfea4d67394189c8bf27b9cc95b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 14 Jan 2024 14:47:48 -0800
Subject: [PATCH 2779/4076] selftests: netdevsim: correct expected FEC strings

ethtool CLI has changed its output. Make the test compatible.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20240114224748.1210578-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../drivers/net/netdevsim/ethtool-fec.sh       | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
index 0c56746e9ce0e..7d7829f57550d 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
@@ -8,16 +8,20 @@ NSIM_NETDEV=$(make_netdev)
 
 set -o pipefail
 
+# Since commit 2b3ddcb35357 ("ethtool: fec: Change the prompt ...")
+# in ethtool CLI the Configured lines start with Supported/Configured.
+configured=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2 | head -1 | cut -d' ' -f1)
+
 # netdevsim starts out with None/None
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: None
+check $? "$s" "$configured FEC encodings: None
 Active FEC encoding: None"
 
 # Test Auto
 $ETHTOOL --set-fec $NSIM_NETDEV encoding auto
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: Auto
+check $? "$s" "$configured FEC encodings: Auto
 Active FEC encoding: Off"
 
 # Test case in-sensitivity
@@ -25,7 +29,7 @@ for o in off Off OFF; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: Off
+    check $? "$s" "$configured FEC encodings: Off
 Active FEC encoding: Off"
 done
 
@@ -33,7 +37,7 @@ for o in BaseR baser BAser; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: BaseR
+    check $? "$s" "$configured FEC encodings: BaseR
 Active FEC encoding: BaseR"
 done
 
@@ -41,7 +45,7 @@ for o in llrs rs; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: ${o^^}
+    check $? "$s" "$configured FEC encodings: ${o^^}
 Active FEC encoding: ${o^^}"
 done
 
@@ -49,13 +53,13 @@ done
 $ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: RS LLRS
+check $? "$s" "$configured FEC encodings: RS LLRS
 Active FEC encoding: LLRS"
 
 $ETHTOOL --set-fec $NSIM_NETDEV encoding rs off auto
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: Auto Off RS
+check $? "$s" "$configured FEC encodings: Auto Off RS
 Active FEC encoding: RS"
 
 # Make sure other link modes are rejected
-- 
GitLab


From 03fb8565c880d57952d9b4ba0b36468bae52b554 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 15 Jan 2024 18:02:01 -0800
Subject: [PATCH 2780/4076] selftests: bonding: add missing build configs

bonding tests also try to create bridge, veth and dummy
interfaces. These are not currently listed in config.

Fixes: bbb774d921e2 ("net: Add tests for bonding and team address list management")
Fixes: c078290a2b76 ("selftests: include bonding tests into the kselftest infra")
Acked-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Link: https://lore.kernel.org/r/20240116020201.1883023-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/bonding/config | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
index 70638fa50b2cc..f85b16fc5128c 100644
--- a/tools/testing/selftests/drivers/net/bonding/config
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -1,2 +1,5 @@
 CONFIG_BONDING=y
+CONFIG_BRIDGE=y
+CONFIG_DUMMY=y
 CONFIG_MACVLAN=y
+CONFIG_VETH=y
-- 
GitLab


From ecd2ada8a5e0b464dab54f71d4ba7bbf5708711f Mon Sep 17 00:00:00 2001
From: Greentime Hu <greentime.hu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:20 +0000
Subject: [PATCH 2781/4076] riscv: Add support for kernel mode vector
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add kernel_vector_begin() and kernel_vector_end() function declarations
and corresponding definitions in kernel_mode_vector.c

These are needed to wrap uses of vector in kernel mode.

Co-developed-by: Vincent Chen <vincent.chen@sifive.com>
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-2-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/processor.h     |  12 ++-
 arch/riscv/include/asm/simd.h          |  44 ++++++++++
 arch/riscv/include/asm/vector.h        |   9 ++
 arch/riscv/kernel/Makefile             |   1 +
 arch/riscv/kernel/kernel_mode_vector.c | 116 +++++++++++++++++++++++++
 arch/riscv/kernel/process.c            |   1 +
 6 files changed, 182 insertions(+), 1 deletion(-)
 create mode 100644 arch/riscv/include/asm/simd.h
 create mode 100644 arch/riscv/kernel/kernel_mode_vector.c

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index f19f861cda549..4809f20a20530 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -73,6 +73,15 @@
 struct task_struct;
 struct pt_regs;
 
+/*
+ * We use a flag to track in-kernel Vector context. Currently the flag has the
+ * following meaning:
+ *
+ *  - bit 0: indicates whether the in-kernel Vector context is active. The
+ *    activation of this state disables the preemption.
+ */
+#define RISCV_KERNEL_MODE_V	0x1
+
 /* CPU-specific state of a task */
 struct thread_struct {
 	/* Callee-saved registers */
@@ -81,7 +90,8 @@ struct thread_struct {
 	unsigned long s[12];	/* s[0]: frame pointer */
 	struct __riscv_d_ext_state fstate;
 	unsigned long bad_cause;
-	unsigned long vstate_ctrl;
+	u32 riscv_v_flags;
+	u32 vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
 	unsigned long align_ctl;
 };
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
new file mode 100644
index 0000000000000..ef8af413a9fc7
--- /dev/null
+++ b/arch/riscv/include/asm/simd.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef __ASM_SIMD_H
+#define __ASM_SIMD_H
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/vector.h>
+
+#ifdef CONFIG_RISCV_ISA_V
+/*
+ * may_use_simd - whether it is allowable at this time to issue vector
+ *                instructions or access the vector register file
+ *
+ * Callers must not assume that the result remains true beyond the next
+ * preempt_enable() or return from softirq context.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+	/*
+	 * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
+	 * and is clear whenever preemption is enabled.
+	 */
+	return !in_hardirq() && !in_nmi() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
+}
+
+#else /* ! CONFIG_RISCV_ISA_V */
+
+static __must_check inline bool may_use_simd(void)
+{
+	return false;
+}
+
+#endif /* ! CONFIG_RISCV_ISA_V */
+
+#endif
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 87aaef656257c..71af3404fda14 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -22,6 +22,15 @@
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
 bool riscv_v_first_use_handler(struct pt_regs *regs);
+void kernel_vector_begin(void);
+void kernel_vector_end(void);
+void get_cpu_vector_context(void);
+void put_cpu_vector_context(void);
+
+static inline u32 riscv_v_flags(void)
+{
+	return current->thread.riscv_v_flags;
+}
 
 static __always_inline bool has_vector(void)
 {
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index fee22a3d1b534..8c58595696b32 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
+obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
new file mode 100644
index 0000000000000..114cf4f0a0eb6
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/simd.h>
+
+static inline void riscv_v_flags_set(u32 flags)
+{
+	current->thread.riscv_v_flags = flags;
+}
+
+static inline void riscv_v_start(u32 flags)
+{
+	int orig;
+
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) != 0);
+	riscv_v_flags_set(orig | flags);
+}
+
+static inline void riscv_v_stop(u32 flags)
+{
+	int orig;
+
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) == 0);
+	riscv_v_flags_set(orig & ~flags);
+}
+
+/*
+ * Claim ownership of the CPU vector context for use by the calling context.
+ *
+ * The caller may freely manipulate the vector context metadata until
+ * put_cpu_vector_context() is called.
+ */
+void get_cpu_vector_context(void)
+{
+	preempt_disable();
+
+	riscv_v_start(RISCV_KERNEL_MODE_V);
+}
+
+/*
+ * Release the CPU vector context.
+ *
+ * Must be called from a context in which get_cpu_vector_context() was
+ * previously called, with no call to put_cpu_vector_context() in the
+ * meantime.
+ */
+void put_cpu_vector_context(void)
+{
+	riscv_v_stop(RISCV_KERNEL_MODE_V);
+
+	preempt_enable();
+}
+
+/*
+ * kernel_vector_begin(): obtain the CPU vector registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_simd() returns true.
+ * Task context in the vector registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_vector_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the vector registers until kernel_vector_end() is
+ * called.
+ */
+void kernel_vector_begin(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	BUG_ON(!may_use_simd());
+
+	get_cpu_vector_context();
+
+	riscv_v_vstate_save(current, task_pt_regs(current));
+
+	riscv_v_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_begin);
+
+/*
+ * kernel_vector_end(): give the CPU vector registers back to the current task
+ *
+ * Must be called from a context in which kernel_vector_begin() was previously
+ * called, with no call to kernel_vector_end() in the meantime.
+ *
+ * The caller must not use the vector registers after this function is called,
+ * unless kernel_vector_begin() is called again in the meantime.
+ */
+void kernel_vector_end(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	riscv_v_vstate_restore(current, task_pt_regs(current));
+
+	riscv_v_disable();
+
+	put_cpu_vector_context();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_end);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 4f21d970a1292..4a1275db11460 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -221,6 +221,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.s[0] = 0;
 	}
+	p->thread.riscv_v_flags = 0;
 	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
-- 
GitLab


From 956895b9d8f74df015636288a81872c07c4fded3 Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:21 +0000
Subject: [PATCH 2782/4076] riscv: vector: make Vector always available for
 softirq context
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The goal of this patch is to provide full support of Vector in kernel
softirq context. So that some of the crypto alogrithms won't need scalar
fallbacks.

By disabling bottom halves in active kernel-mode Vector, softirq will
not be able to nest on top of any kernel-mode Vector. So, softirq
context is able to use Vector whenever it runs.

After this patch, Vector context cannot start with irqs disabled.
Otherwise local_bh_enable() may run in a wrong context.

Disabling bh is not enough for RT-kernel to prevent preeemption. So
we must disable preemption, which also implies disabling bh on RT.

Related-to: commit 696207d4258b ("arm64/sve: Make kernel FPU protection RT friendly")
Related-to: commit 66c3ec5a7120 ("arm64: neon: Forbid when irqs are disabled")
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-3-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/processor.h     |  3 ++-
 arch/riscv/include/asm/simd.h          |  6 +++++-
 arch/riscv/kernel/kernel_mode_vector.c | 14 ++++++++++++--
 3 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 4809f20a20530..55ace554f2021 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -78,7 +78,8 @@ struct pt_regs;
  * following meaning:
  *
  *  - bit 0: indicates whether the in-kernel Vector context is active. The
- *    activation of this state disables the preemption.
+ *    activation of this state disables the preemption. On a non-RT kernel, it
+ *    also disable bh.
  */
 #define RISCV_KERNEL_MODE_V	0x1
 
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
index ef8af413a9fc7..4d699e16c9a96 100644
--- a/arch/riscv/include/asm/simd.h
+++ b/arch/riscv/include/asm/simd.h
@@ -28,8 +28,12 @@ static __must_check inline bool may_use_simd(void)
 	/*
 	 * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
 	 * and is clear whenever preemption is enabled.
+	 *
+	 * Kernel-mode Vector temporarily disables bh. So we must not return
+	 * true on irq_disabled(). Otherwise we would fail the lockdep check
+	 * calling local_bh_enable()
 	 */
-	return !in_hardirq() && !in_nmi() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
+	return !in_hardirq() && !in_nmi() && !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
 }
 
 #else /* ! CONFIG_RISCV_ISA_V */
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
index 114cf4f0a0eb6..2fc145edae3dd 100644
--- a/arch/riscv/kernel/kernel_mode_vector.c
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -46,7 +46,14 @@ static inline void riscv_v_stop(u32 flags)
  */
 void get_cpu_vector_context(void)
 {
-	preempt_disable();
+	/*
+	 * disable softirqs so it is impossible for softirqs to nest
+	 * get_cpu_vector_context() when kernel is actively using Vector.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_disable();
+	else
+		preempt_disable();
 
 	riscv_v_start(RISCV_KERNEL_MODE_V);
 }
@@ -62,7 +69,10 @@ void put_cpu_vector_context(void)
 {
 	riscv_v_stop(RISCV_KERNEL_MODE_V);
 
-	preempt_enable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_enable();
+	else
+		preempt_enable();
 }
 
 /*
-- 
GitLab


From c5674d00cacdb1c47c72e19a552fbae401bc3532 Mon Sep 17 00:00:00 2001
From: Greentime Hu <greentime.hu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:22 +0000
Subject: [PATCH 2783/4076] riscv: Add vector extension XOR implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds support for vector optimized XOR and it is tested in
qemu.

Co-developed-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-4-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/asm-prototypes.h | 18 ++++++
 arch/riscv/include/asm/xor.h            | 68 +++++++++++++++++++++
 arch/riscv/lib/Makefile                 |  1 +
 arch/riscv/lib/xor.S                    | 81 +++++++++++++++++++++++++
 4 files changed, 168 insertions(+)
 create mode 100644 arch/riscv/include/asm/xor.h
 create mode 100644 arch/riscv/lib/xor.S

diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 36b955c762ba0..6db1a9bbff4ce 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -9,6 +9,24 @@ long long __lshrti3(long long a, int b);
 long long __ashrti3(long long a, int b);
 long long __ashlti3(long long a, int b);
 
+#ifdef CONFIG_RISCV_ISA_V
+
+void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2);
+void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3);
+void xor_regs_4_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3,
+		 const unsigned long *__restrict p4);
+void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3,
+		 const unsigned long *__restrict p4,
+		 const unsigned long *__restrict p5);
+
+#endif /* CONFIG_RISCV_ISA_V */
 
 #define DECLARE_DO_ERROR_INFO(name)	asmlinkage void name(struct pt_regs *regs)
 
diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
new file mode 100644
index 0000000000000..96011861e46b4
--- /dev/null
+++ b/arch/riscv/include/asm/xor.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#ifdef CONFIG_RISCV_ISA_V
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/asm-prototypes.h>
+
+static void xor_vector_2(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2)
+{
+	kernel_vector_begin();
+	xor_regs_2_(bytes, p1, p2);
+	kernel_vector_end();
+}
+
+static void xor_vector_3(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2,
+			 const unsigned long *__restrict p3)
+{
+	kernel_vector_begin();
+	xor_regs_3_(bytes, p1, p2, p3);
+	kernel_vector_end();
+}
+
+static void xor_vector_4(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2,
+			 const unsigned long *__restrict p3,
+			 const unsigned long *__restrict p4)
+{
+	kernel_vector_begin();
+	xor_regs_4_(bytes, p1, p2, p3, p4);
+	kernel_vector_end();
+}
+
+static void xor_vector_5(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2,
+			 const unsigned long *__restrict p3,
+			 const unsigned long *__restrict p4,
+			 const unsigned long *__restrict p5)
+{
+	kernel_vector_begin();
+	xor_regs_5_(bytes, p1, p2, p3, p4, p5);
+	kernel_vector_end();
+}
+
+static struct xor_block_template xor_block_rvv = {
+	.name = "rvv",
+	.do_2 = xor_vector_2,
+	.do_3 = xor_vector_3,
+	.do_4 = xor_vector_4,
+	.do_5 = xor_vector_5
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES           \
+	do {        \
+		xor_speed(&xor_block_8regs);    \
+		xor_speed(&xor_block_32regs);    \
+		if (has_vector()) { \
+			xor_speed(&xor_block_rvv);\
+		} \
+	} while (0)
+#endif
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 26cb2502ecf89..494f9cd1a00c0 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -11,3 +11,4 @@ lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S
new file mode 100644
index 0000000000000..b28f2430e52fa
--- /dev/null
+++ b/arch/riscv/lib/xor.S
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/linkage.h>
+#include <linux/export.h>
+#include <asm/asm.h>
+
+SYM_FUNC_START(xor_regs_2_)
+	vsetvli a3, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a3
+	vxor.vv v16, v0, v8
+	add a2, a2, a3
+	vse8.v v16, (a1)
+	add a1, a1, a3
+	bnez a0, xor_regs_2_
+	ret
+SYM_FUNC_END(xor_regs_2_)
+EXPORT_SYMBOL(xor_regs_2_)
+
+SYM_FUNC_START(xor_regs_3_)
+	vsetvli a4, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a4
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a4
+	vxor.vv v16, v0, v16
+	add a3, a3, a4
+	vse8.v v16, (a1)
+	add a1, a1, a4
+	bnez a0, xor_regs_3_
+	ret
+SYM_FUNC_END(xor_regs_3_)
+EXPORT_SYMBOL(xor_regs_3_)
+
+SYM_FUNC_START(xor_regs_4_)
+	vsetvli a5, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a5
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a5
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a5
+	vxor.vv v16, v0, v24
+	add a4, a4, a5
+	vse8.v v16, (a1)
+	add a1, a1, a5
+	bnez a0, xor_regs_4_
+	ret
+SYM_FUNC_END(xor_regs_4_)
+EXPORT_SYMBOL(xor_regs_4_)
+
+SYM_FUNC_START(xor_regs_5_)
+	vsetvli a6, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a6
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a6
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a6
+	vxor.vv v0, v0, v24
+	vle8.v v8, (a5)
+	add a4, a4, a6
+	vxor.vv v16, v0, v8
+	add a5, a5, a6
+	vse8.v v16, (a1)
+	add a1, a1, a6
+	bnez a0, xor_regs_5_
+	ret
+SYM_FUNC_END(xor_regs_5_)
+EXPORT_SYMBOL(xor_regs_5_)
-- 
GitLab


From 7df56cbc27e4239807b5d8860f79a7350d63a741 Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:23 +0000
Subject: [PATCH 2784/4076] riscv: sched: defer restoring Vector context for
 user
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User will use its Vector registers only after the kernel really returns
to the userspace. So we can delay restoring Vector registers as long as
we are still running in kernel mode. So, add a thread flag to indicates
the need of restoring Vector and do the restore at the last
arch-specific exit-to-user hook. This save the context restoring cost
when we switch over multiple processes that run V in kernel mode. For
example, if the kernel performs a context swicth from A->B->C, and
returns to C's userspace, then there is no need to restore B's
V-register.

Besides, this also prevents us from repeatedly restoring V context when
executing kernel-mode Vector multiple times.

The cost of this is that we must disable preemption and mark vector as
busy during vstate_{save,restore}. Because then the V context will not
get restored back immediately when a trap-causing context switch happens
in the middle of vstate_{save,restore}.

Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-5-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/entry-common.h  | 17 +++++++++++++++++
 arch/riscv/include/asm/thread_info.h   |  2 ++
 arch/riscv/include/asm/vector.h        | 11 ++++++++++-
 arch/riscv/kernel/kernel_mode_vector.c |  2 +-
 arch/riscv/kernel/process.c            |  2 ++
 arch/riscv/kernel/ptrace.c             |  5 ++++-
 arch/riscv/kernel/signal.c             |  5 ++++-
 arch/riscv/kernel/vector.c             |  2 +-
 8 files changed, 41 insertions(+), 5 deletions(-)

diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 7ab5e34318c85..19023c430a9b5 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -4,6 +4,23 @@
 #define _ASM_RISCV_ENTRY_COMMON_H
 
 #include <asm/stacktrace.h>
+#include <asm/thread_info.h>
+#include <asm/vector.h>
+
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+	if (ti_work & _TIF_RISCV_V_DEFER_RESTORE) {
+		clear_thread_flag(TIF_RISCV_V_DEFER_RESTORE);
+		/*
+		 * We are already called with irq disabled, so go without
+		 * keeping track of riscv_v_flags.
+		 */
+		riscv_v_vstate_restore(current, regs);
+	}
+}
+
+#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
 
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 574779900bfb3..1047a97ddbc8a 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -103,12 +103,14 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define TIF_NOTIFY_SIGNAL	9	/* signal notifications exist */
 #define TIF_UPROBE		10	/* uprobe breakpoint or singlestep */
 #define TIF_32BIT		11	/* compat-mode 32bit process */
+#define TIF_RISCV_V_DEFER_RESTORE	12 /* restore Vector before returing to user */
 
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_RISCV_V_DEFER_RESTORE	(1 << TIF_RISCV_V_DEFER_RESTORE)
 
 #define _TIF_WORK_MASK \
 	(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 71af3404fda14..961c4e3d1b620 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -193,6 +193,15 @@ static inline void riscv_v_vstate_restore(struct task_struct *task,
 	}
 }
 
+static inline void riscv_v_vstate_set_restore(struct task_struct *task,
+					      struct pt_regs *regs)
+{
+	if ((regs->status & SR_VS) != SR_VS_OFF) {
+		set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
+		riscv_v_vstate_on(regs);
+	}
+}
+
 static inline void __switch_to_vector(struct task_struct *prev,
 				      struct task_struct *next)
 {
@@ -200,7 +209,7 @@ static inline void __switch_to_vector(struct task_struct *prev,
 
 	regs = task_pt_regs(prev);
 	riscv_v_vstate_save(prev, regs);
-	riscv_v_vstate_restore(next, task_pt_regs(next));
+	riscv_v_vstate_set_restore(next, task_pt_regs(next));
 }
 
 void riscv_v_vstate_ctrl_init(struct task_struct *tsk);
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
index 2fc145edae3dd..8422c881f4529 100644
--- a/arch/riscv/kernel/kernel_mode_vector.c
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -117,7 +117,7 @@ void kernel_vector_end(void)
 	if (WARN_ON(!has_vector()))
 		return;
 
-	riscv_v_vstate_restore(current, task_pt_regs(current));
+	riscv_v_vstate_set_restore(current, task_pt_regs(current));
 
 	riscv_v_disable();
 
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 4a1275db11460..36993f408de4a 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -171,6 +171,7 @@ void flush_thread(void)
 	riscv_v_vstate_off(task_pt_regs(current));
 	kfree(current->thread.vstate.datap);
 	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
 #endif
 }
 
@@ -187,6 +188,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	*dst = *src;
 	/* clear entire V context, including datap for a new task */
 	memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE);
 
 	return 0;
 }
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2afe460de16a6..7b93bcbdf9fab 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -99,8 +99,11 @@ static int riscv_vr_get(struct task_struct *target,
 	 * Ensure the vector registers have been saved to the memory before
 	 * copying them to membuf.
 	 */
-	if (target == current)
+	if (target == current) {
+		get_cpu_vector_context();
 		riscv_v_vstate_save(current, task_pt_regs(current));
+		put_cpu_vector_context();
+	}
 
 	ptrace_vstate.vstart = vstate->vstart;
 	ptrace_vstate.vl = vstate->vl;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 88b6220b26087..aca4a12c84162 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -86,7 +86,10 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	/* datap is designed to be 16 byte aligned for better performance */
 	WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
 
+	get_cpu_vector_context();
 	riscv_v_vstate_save(current, regs);
+	put_cpu_vector_context();
+
 	/* Copy everything of vstate but datap. */
 	err = __copy_to_user(&state->v_state, &current->thread.vstate,
 			     offsetof(struct __riscv_v_ext_state, datap));
@@ -134,7 +137,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	if (unlikely(err))
 		return err;
 
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 
 	return err;
 }
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 578b6292487e1..66e8c6ab09d25 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -167,7 +167,7 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 		return true;
 	}
 	riscv_v_vstate_on(regs);
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 	return true;
 }
 
-- 
GitLab


From c2a658d419246108c9bf065ec347355de5ba8a05 Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:24 +0000
Subject: [PATCH 2785/4076] riscv: lib: vectorize copy_to_user/copy_from_user
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch utilizes Vector to perform copy_to_user/copy_from_user. If
Vector is available and the size of copy is large enough for Vector to
perform better than scalar, then direct the kernel to do Vector copies
for userspace. Though the best programming practice for users is to
reduce the copy, this provides a faster variant when copies are
inevitable.

The optimal size for using Vector, copy_to_user_thres, is only a
heuristic for now. We can add DT parsing if people feel the need of
customizing it.

The exception fixup code of the __asm_vector_usercopy must fallback to
the scalar one because accessing user pages might fault, and must be
sleepable. Current kernel-mode Vector does not allow tasks to be
preemptible, so we must disactivate Vector and perform a scalar fallback
in such case.

The original implementation of Vector operations comes from
https://github.com/sifive/sifive-libc, which we agree to contribute to
Linux kernel.

Co-developed-by: Jerry Shih <jerry.shih@sifive.com>
Signed-off-by: Jerry Shih <jerry.shih@sifive.com>
Co-developed-by: Nick Knight <nick.knight@sifive.com>
Signed-off-by: Nick Knight <nick.knight@sifive.com>
Suggested-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-6-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                      |  8 ++++
 arch/riscv/include/asm/asm-prototypes.h |  4 ++
 arch/riscv/lib/Makefile                 |  6 ++-
 arch/riscv/lib/riscv_v_helpers.c        | 45 +++++++++++++++++++++
 arch/riscv/lib/uaccess.S                | 10 +++++
 arch/riscv/lib/uaccess_vector.S         | 53 +++++++++++++++++++++++++
 6 files changed, 125 insertions(+), 1 deletion(-)
 create mode 100644 arch/riscv/lib/riscv_v_helpers.c
 create mode 100644 arch/riscv/lib/uaccess_vector.S

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a6..3c5ba05e8a2da 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -525,6 +525,14 @@ config RISCV_ISA_V_DEFAULT_ENABLE
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_V_UCOPY_THRESHOLD
+	int "Threshold size for vectorized user copies"
+	depends on RISCV_ISA_V
+	default 768
+	help
+	  Prefer using vectorized copy_to_user()/copy_from_user() when the
+	  workload size exceeds this value.
+
 config TOOLCHAIN_HAS_ZBB
 	bool
 	default y
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 6db1a9bbff4ce..be438932f321f 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -11,6 +11,10 @@ long long __ashlti3(long long a, int b);
 
 #ifdef CONFIG_RISCV_ISA_V
 
+#ifdef CONFIG_MMU
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n);
+#endif /* CONFIG_MMU  */
+
 void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
 		 const unsigned long *__restrict p2);
 void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 494f9cd1a00c0..c8a6787d58273 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -6,9 +6,13 @@ lib-y			+= memmove.o
 lib-y			+= strcmp.o
 lib-y			+= strlen.o
 lib-y			+= strncmp.o
-lib-$(CONFIG_MMU)	+= uaccess.o
+ifeq ($(CONFIG_MMU), y)
+lib-y				+= uaccess.o
+lib-$(CONFIG_RISCV_ISA_V)	+= uaccess_vector.o
+endif
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
+lib-$(CONFIG_RISCV_ISA_V)	+= riscv_v_helpers.o
diff --git a/arch/riscv/lib/riscv_v_helpers.c b/arch/riscv/lib/riscv_v_helpers.c
new file mode 100644
index 0000000000000..be38a93cedaec
--- /dev/null
+++ b/arch/riscv/lib/riscv_v_helpers.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 SiFive
+ * Author: Andy Chiu <andy.chiu@sifive.com>
+ */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#include <asm/vector.h>
+#include <asm/simd.h>
+
+#ifdef CONFIG_MMU
+#include <asm/asm-prototypes.h>
+#endif
+
+#ifdef CONFIG_MMU
+size_t riscv_v_usercopy_threshold = CONFIG_RISCV_ISA_V_UCOPY_THRESHOLD;
+int __asm_vector_usercopy(void *dst, void *src, size_t n);
+int fallback_scalar_usercopy(void *dst, void *src, size_t n);
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n)
+{
+	size_t remain, copied;
+
+	/* skip has_vector() check because it has been done by the asm  */
+	if (!may_use_simd())
+		goto fallback;
+
+	kernel_vector_begin();
+	remain = __asm_vector_usercopy(dst, src, n);
+	kernel_vector_end();
+
+	if (remain) {
+		copied = n - remain;
+		dst += copied;
+		src += copied;
+		n = remain;
+		goto fallback;
+	}
+
+	return remain;
+
+fallback:
+	return fallback_scalar_usercopy(dst, src, n);
+}
+#endif
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 3ab438f30d132..a1e4a3c429254 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -3,6 +3,8 @@
 #include <asm/asm.h>
 #include <asm/asm-extable.h>
 #include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
 
 	.macro fixup op reg addr lbl
 100:
@@ -11,6 +13,13 @@
 	.endm
 
 SYM_FUNC_START(__asm_copy_to_user)
+#ifdef CONFIG_RISCV_ISA_V
+	ALTERNATIVE("j fallback_scalar_usercopy", "nop", 0, RISCV_ISA_EXT_v, CONFIG_RISCV_ISA_V)
+	REG_L	t0, riscv_v_usercopy_threshold
+	bltu	a2, t0, fallback_scalar_usercopy
+	tail enter_vector_usercopy
+#endif
+SYM_FUNC_START(fallback_scalar_usercopy)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -181,6 +190,7 @@ SYM_FUNC_START(__asm_copy_to_user)
 	sub a0, t5, a0
 	ret
 SYM_FUNC_END(__asm_copy_to_user)
+SYM_FUNC_END(fallback_scalar_usercopy)
 EXPORT_SYMBOL(__asm_copy_to_user)
 SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user)
 EXPORT_SYMBOL(__asm_copy_from_user)
diff --git a/arch/riscv/lib/uaccess_vector.S b/arch/riscv/lib/uaccess_vector.S
new file mode 100644
index 0000000000000..51ab5588e9ff3
--- /dev/null
+++ b/arch/riscv/lib/uaccess_vector.S
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+#include <asm/asm-extable.h>
+#include <asm/csr.h>
+
+#define pDst a0
+#define pSrc a1
+#define iNum a2
+
+#define iVL a3
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+	.macro fixup op reg addr lbl
+100:
+	\op \reg, \addr
+	_asm_extable	100b, \lbl
+	.endm
+
+SYM_FUNC_START(__asm_vector_usercopy)
+	/* Enable access to user memory */
+	li	t6, SR_SUM
+	csrs	CSR_STATUS, t6
+
+loop:
+	vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+	fixup vle8.v vData, (pSrc), 10f
+	sub iNum, iNum, iVL
+	add pSrc, pSrc, iVL
+	fixup vse8.v vData, (pDst), 11f
+	add pDst, pDst, iVL
+	bnez iNum, loop
+
+	/* Exception fixup for vector load is shared with normal exit */
+10:
+	/* Disable access to user memory */
+	csrc	CSR_STATUS, t6
+	mv	a0, iNum
+	ret
+
+	/* Exception fixup code for vector store. */
+11:
+	/* Undo the subtraction after vle8.v */
+	add	iNum, iNum, iVL
+	/* Make sure the scalar fallback skip already processed bytes */
+	csrr	t2, CSR_VSTART
+	sub	iNum, iNum, t2
+	j	10b
+SYM_FUNC_END(__asm_vector_usercopy)
-- 
GitLab


From a93fdaf183125fea81f66b9bd756ef5a0c30859e Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:25 +0000
Subject: [PATCH 2786/4076] riscv: fpu: drop SR_SD bit checking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SR_SD summarizes the dirty status of FS/VS/XS. However, the current code
structure does not fully utilize it because each extension specific code
is divided into an individual segment. So remove the SR_SD check for
now.

Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Reviewed-by: Song Shuai <songshuaishuai@tinylab.org>
Reviewed-by: Guo Ren <guoren@kernel.org>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-7-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/switch_to.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index f90d8e42f3c79..7efdb0584d47a 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -53,8 +53,7 @@ static inline void __switch_to_fpu(struct task_struct *prev,
 	struct pt_regs *regs;
 
 	regs = task_pt_regs(prev);
-	if (unlikely(regs->status & SR_SD))
-		fstate_save(prev, regs);
+	fstate_save(prev, regs);
 	fstate_restore(next, task_pt_regs(next));
 }
 
-- 
GitLab


From d6c78f1ca3e8ec3fd1afa1bc567cdf083e7af9fe Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:26 +0000
Subject: [PATCH 2787/4076] riscv: vector: do not pass task_struct into
 riscv_v_vstate_{save,restore}()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

riscv_v_vstate_{save,restore}() can operate only on the knowlege of
struct __riscv_v_ext_state, and struct pt_regs. Let the caller decides
which should be passed into the function. Meanwhile, the kernel-mode
Vector is going to introduce another vstate, so this also makes functions
potentially able to be reused.

Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-8-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/entry-common.h  |  2 +-
 arch/riscv/include/asm/vector.h        | 14 +++++---------
 arch/riscv/kernel/kernel_mode_vector.c |  2 +-
 arch/riscv/kernel/ptrace.c             |  2 +-
 arch/riscv/kernel/signal.c             |  2 +-
 5 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 19023c430a9b5..2293e535f8659 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -16,7 +16,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 		 * We are already called with irq disabled, so go without
 		 * keeping track of riscv_v_flags.
 		 */
-		riscv_v_vstate_restore(current, regs);
+		riscv_v_vstate_restore(&current->thread.vstate, regs);
 	}
 }
 
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 961c4e3d1b620..d750795206299 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -171,23 +171,19 @@ static inline void riscv_v_vstate_discard(struct pt_regs *regs)
 	__riscv_v_vstate_dirty(regs);
 }
 
-static inline void riscv_v_vstate_save(struct task_struct *task,
+static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
 				       struct pt_regs *regs)
 {
 	if ((regs->status & SR_VS) == SR_VS_DIRTY) {
-		struct __riscv_v_ext_state *vstate = &task->thread.vstate;
-
 		__riscv_v_vstate_save(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
 }
 
-static inline void riscv_v_vstate_restore(struct task_struct *task,
+static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
 					  struct pt_regs *regs)
 {
 	if ((regs->status & SR_VS) != SR_VS_OFF) {
-		struct __riscv_v_ext_state *vstate = &task->thread.vstate;
-
 		__riscv_v_vstate_restore(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
@@ -208,7 +204,7 @@ static inline void __switch_to_vector(struct task_struct *prev,
 	struct pt_regs *regs;
 
 	regs = task_pt_regs(prev);
-	riscv_v_vstate_save(prev, regs);
+	riscv_v_vstate_save(&prev->thread.vstate, regs);
 	riscv_v_vstate_set_restore(next, task_pt_regs(next));
 }
 
@@ -226,8 +222,8 @@ static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
 #define riscv_v_vsize (0)
 #define riscv_v_vstate_discard(regs)		do {} while (0)
-#define riscv_v_vstate_save(task, regs)		do {} while (0)
-#define riscv_v_vstate_restore(task, regs)	do {} while (0)
+#define riscv_v_vstate_save(vstate, regs)	do {} while (0)
+#define riscv_v_vstate_restore(vstate, regs)	do {} while (0)
 #define __switch_to_vector(__prev, __next)	do {} while (0)
 #define riscv_v_vstate_off(regs)		do {} while (0)
 #define riscv_v_vstate_on(regs)			do {} while (0)
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
index 8422c881f4529..241a8f834e1ce 100644
--- a/arch/riscv/kernel/kernel_mode_vector.c
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -97,7 +97,7 @@ void kernel_vector_begin(void)
 
 	get_cpu_vector_context();
 
-	riscv_v_vstate_save(current, task_pt_regs(current));
+	riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
 
 	riscv_v_enable();
 }
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 7b93bcbdf9fab..e8515aa9d80bf 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -101,7 +101,7 @@ static int riscv_vr_get(struct task_struct *target,
 	 */
 	if (target == current) {
 		get_cpu_vector_context();
-		riscv_v_vstate_save(current, task_pt_regs(current));
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
 		put_cpu_vector_context();
 	}
 
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index aca4a12c84162..5d69f4db9e8f3 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -87,7 +87,7 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
 
 	get_cpu_vector_context();
-	riscv_v_vstate_save(current, regs);
+	riscv_v_vstate_save(&current->thread.vstate, regs);
 	put_cpu_vector_context();
 
 	/* Copy everything of vstate but datap. */
-- 
GitLab


From 5b6048f2ff710196c85ce14373febe8be5115bbe Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:27 +0000
Subject: [PATCH 2788/4076] riscv: vector: use a mask to write vstate_ctrl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

riscv_v_ctrl_set() should only touch bits within
PR_RISCV_V_VSTATE_CTRL_MASK. So, use the mask when we really set task's
vstate_ctrl.

Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-9-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/vector.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 66e8c6ab09d25..c1f28bc89ec64 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -122,7 +122,8 @@ static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt,
 	ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt);
 	if (inherit)
 		ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
-	tsk->thread.vstate_ctrl = ctrl;
+	tsk->thread.vstate_ctrl &= ~PR_RISCV_V_VSTATE_CTRL_MASK;
+	tsk->thread.vstate_ctrl |= ctrl;
 }
 
 bool riscv_v_vstate_ctrl_user_allowed(void)
-- 
GitLab


From bd446f5df5afab212917f6732ba6442a5e8de85e Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:28 +0000
Subject: [PATCH 2789/4076] riscv: vector: use kmem_cache to manage vector
 context
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The allocation size of thread.vstate.datap is always riscv_v_vsize. So
it is possbile to use kmem_cache_* to manage the allocation. This gives
users more information regarding allocation of vector context via
/proc/slabinfo. And it potentially reduces the latency of the first-use
trap because of the allocation caches.

Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-10-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/vector.h |  4 ++++
 arch/riscv/kernel/process.c     |  7 ++++++-
 arch/riscv/kernel/vector.c      | 19 ++++++++++++++++++-
 3 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index d750795206299..7b316050f24f7 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -26,6 +26,8 @@ void kernel_vector_begin(void);
 void kernel_vector_end(void);
 void get_cpu_vector_context(void);
 void put_cpu_vector_context(void);
+void riscv_v_thread_free(struct task_struct *tsk);
+void __init riscv_v_setup_ctx_cache(void);
 
 static inline u32 riscv_v_flags(void)
 {
@@ -227,6 +229,8 @@ static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
 #define __switch_to_vector(__prev, __next)	do {} while (0)
 #define riscv_v_vstate_off(regs)		do {} while (0)
 #define riscv_v_vstate_on(regs)			do {} while (0)
+#define riscv_v_thread_free(tsk)		do {} while (0)
+#define  riscv_v_setup_ctx_cache()		do {} while (0)
 
 #endif /* CONFIG_RISCV_ISA_V */
 
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 36993f408de4a..862d59c3872e2 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -179,7 +179,7 @@ void arch_release_task_struct(struct task_struct *tsk)
 {
 	/* Free the vector context of datap. */
 	if (has_vector())
-		kfree(tsk->thread.vstate.datap);
+		riscv_v_thread_free(tsk);
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -228,3 +228,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }
+
+void __init arch_task_cache_init(void)
+{
+	riscv_v_setup_ctx_cache();
+}
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index c1f28bc89ec64..f7b4aeb9e4579 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -21,6 +21,7 @@
 #include <asm/bug.h>
 
 static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE);
+static struct kmem_cache *riscv_v_user_cachep;
 
 unsigned long riscv_v_vsize __read_mostly;
 EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -47,6 +48,16 @@ int riscv_v_setup_vsize(void)
 	return 0;
 }
 
+void __init riscv_v_setup_ctx_cache(void)
+{
+	if (!has_vector())
+		return;
+
+	riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
+							 riscv_v_vsize, 16, SLAB_PANIC,
+							 0, riscv_v_vsize, NULL);
+}
+
 static bool insn_is_vector(u32 insn_buf)
 {
 	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
@@ -84,7 +95,7 @@ static int riscv_v_thread_zalloc(void)
 {
 	void *datap;
 
-	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+	datap = kmem_cache_zalloc(riscv_v_user_cachep, GFP_KERNEL);
 	if (!datap)
 		return -ENOMEM;
 
@@ -94,6 +105,12 @@ static int riscv_v_thread_zalloc(void)
 	return 0;
 }
 
+void riscv_v_thread_free(struct task_struct *tsk)
+{
+	if (tsk->thread.vstate.datap)
+		kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap);
+}
+
 #define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)
 #define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2)
 #define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK)
-- 
GitLab


From 2080ff9493072a94e42b1856d59f5f1bffb761b7 Mon Sep 17 00:00:00 2001
From: Andy Chiu <andy.chiu@sifive.com>
Date: Mon, 15 Jan 2024 05:59:29 +0000
Subject: [PATCH 2790/4076] riscv: vector: allow kernel-mode Vector with
 preemption
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add kernel_vstate to keep track of kernel-mode Vector registers when
trap introduced context switch happens. Also, provide riscv_v_flags to
let context save/restore routine track context status. Context tracking
happens whenever the core starts its in-kernel Vector executions. An
active (dirty) kernel task's V contexts will be saved to memory whenever
a trap-introduced context switch happens. Or, when a softirq, which
happens to nest on top of it, uses Vector. Context retoring happens when
the execution transfer back to the original Kernel context where it
first enable preempt_v.

Also, provide a config CONFIG_RISCV_ISA_V_PREEMPTIVE to give users an
option to disable preemptible kernel-mode Vector at build time. Users
with constraint memory may want to disable this config as preemptible
kernel-mode Vector needs extra space for tracking of per thread's
kernel-mode V context. Or, users might as well want to disable it if all
kernel-mode Vector code is time sensitive and cannot tolerate context
switch overhead.

Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-11-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                      |  14 +++
 arch/riscv/include/asm/asm-prototypes.h |   5 +
 arch/riscv/include/asm/processor.h      |  30 +++++-
 arch/riscv/include/asm/simd.h           |  26 ++++-
 arch/riscv/include/asm/vector.h         |  58 ++++++++++-
 arch/riscv/kernel/entry.S               |   8 ++
 arch/riscv/kernel/kernel_mode_vector.c  | 133 ++++++++++++++++++++++--
 arch/riscv/kernel/process.c             |   3 +
 arch/riscv/kernel/vector.c              |  31 ++++--
 9 files changed, 286 insertions(+), 22 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 3c5ba05e8a2da..0a03d72706b54 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -533,6 +533,20 @@ config RISCV_ISA_V_UCOPY_THRESHOLD
 	  Prefer using vectorized copy_to_user()/copy_from_user() when the
 	  workload size exceeds this value.
 
+config RISCV_ISA_V_PREEMPTIVE
+	bool "Run kernel-mode Vector with kernel preemption"
+	depends on PREEMPTION
+	depends on RISCV_ISA_V
+	default y
+	help
+	  Usually, in-kernel SIMD routines are run with preemption disabled.
+	  Functions which envoke long running SIMD thus must yield core's
+	  vector unit to prevent blocking other tasks for too long.
+
+	  This config allows kernel to run SIMD without explicitly disable
+	  preemption. Enabling this config will result in higher memory
+	  consumption due to the allocation of per-task's kernel Vector context.
+
 config TOOLCHAIN_HAS_ZBB
 	bool
 	default y
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index be438932f321f..cd627ec289f16 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -30,6 +30,11 @@ void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
 		 const unsigned long *__restrict p4,
 		 const unsigned long *__restrict p5);
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs);
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs);
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
 #endif /* CONFIG_RISCV_ISA_V */
 
 #define DECLARE_DO_ERROR_INFO(name)	asmlinkage void name(struct pt_regs *regs)
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 55ace554f2021..b02119ff08fce 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -80,8 +80,35 @@ struct pt_regs;
  *  - bit 0: indicates whether the in-kernel Vector context is active. The
  *    activation of this state disables the preemption. On a non-RT kernel, it
  *    also disable bh.
+ *  - bits 8: is used for tracking preemptible kernel-mode Vector, when
+ *    RISCV_ISA_V_PREEMPTIVE is enabled. Calling kernel_vector_begin() does not
+ *    disable the preemption if the thread's kernel_vstate.datap is allocated.
+ *    Instead, the kernel set this bit field. Then the trap entry/exit code
+ *    knows if we are entering/exiting the context that owns preempt_v.
+ *     - 0: the task is not using preempt_v
+ *     - 1: the task is actively using preempt_v. But whether does the task own
+ *          the preempt_v context is decided by bits in RISCV_V_CTX_DEPTH_MASK.
+ *  - bit 16-23 are RISCV_V_CTX_DEPTH_MASK, used by context tracking routine
+ *     when preempt_v starts:
+ *     - 0: the task is actively using, and own preempt_v context.
+ *     - non-zero: the task was using preempt_v, but then took a trap within.
+ *       Thus, the task does not own preempt_v. Any use of Vector will have to
+ *       save preempt_v, if dirty, and fallback to non-preemptible kernel-mode
+ *       Vector.
+ *  - bit 30: The in-kernel preempt_v context is saved, and requries to be
+ *    restored when returning to the context that owns the preempt_v.
+ *  - bit 31: The in-kernel preempt_v context is dirty, as signaled by the
+ *    trap entry code. Any context switches out-of current task need to save
+ *    it to the task's in-kernel V context. Also, any traps nesting on-top-of
+ *    preempt_v requesting to use V needs a save.
  */
-#define RISCV_KERNEL_MODE_V	0x1
+#define RISCV_V_CTX_DEPTH_MASK		0x00ff0000
+
+#define RISCV_V_CTX_UNIT_DEPTH		0x00010000
+#define RISCV_KERNEL_MODE_V		0x00000001
+#define RISCV_PREEMPT_V			0x00000100
+#define RISCV_PREEMPT_V_DIRTY		0x80000000
+#define RISCV_PREEMPT_V_NEED_RESTORE	0x40000000
 
 /* CPU-specific state of a task */
 struct thread_struct {
@@ -95,6 +122,7 @@ struct thread_struct {
 	u32 vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
 	unsigned long align_ctl;
+	struct __riscv_v_ext_state kernel_vstate;
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
index 4d699e16c9a96..54efbf523d49c 100644
--- a/arch/riscv/include/asm/simd.h
+++ b/arch/riscv/include/asm/simd.h
@@ -12,6 +12,7 @@
 #include <linux/percpu.h>
 #include <linux/preempt.h>
 #include <linux/types.h>
+#include <linux/thread_info.h>
 
 #include <asm/vector.h>
 
@@ -28,12 +29,27 @@ static __must_check inline bool may_use_simd(void)
 	/*
 	 * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
 	 * and is clear whenever preemption is enabled.
-	 *
-	 * Kernel-mode Vector temporarily disables bh. So we must not return
-	 * true on irq_disabled(). Otherwise we would fail the lockdep check
-	 * calling local_bh_enable()
 	 */
-	return !in_hardirq() && !in_nmi() && !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
+	if (in_hardirq() || in_nmi())
+		return false;
+
+	/*
+	 * Nesting is acheived in preempt_v by spreading the control for
+	 * preemptible and non-preemptible kernel-mode Vector into two fields.
+	 * Always try to match with prempt_v if kernel V-context exists. Then,
+	 * fallback to check non preempt_v if nesting happens, or if the config
+	 * is not set.
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_V_PREEMPTIVE) && current->thread.kernel_vstate.datap) {
+		if (!riscv_preempt_v_started(current))
+			return true;
+	}
+	/*
+	 * Non-preemptible kernel-mode Vector temporarily disables bh. So we
+	 * must not return true on irq_disabled(). Otherwise we would fail the
+	 * lockdep check calling local_bh_enable()
+	 */
+	return !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
 }
 
 #else /* ! CONFIG_RISCV_ISA_V */
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 7b316050f24f7..0cd6f0a027d1f 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -28,10 +28,11 @@ void get_cpu_vector_context(void);
 void put_cpu_vector_context(void);
 void riscv_v_thread_free(struct task_struct *tsk);
 void __init riscv_v_setup_ctx_cache(void);
+void riscv_v_thread_alloc(struct task_struct *tsk);
 
 static inline u32 riscv_v_flags(void)
 {
-	return current->thread.riscv_v_flags;
+	return READ_ONCE(current->thread.riscv_v_flags);
 }
 
 static __always_inline bool has_vector(void)
@@ -200,14 +201,62 @@ static inline void riscv_v_vstate_set_restore(struct task_struct *task,
 	}
 }
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static inline bool riscv_preempt_v_dirty(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_DIRTY);
+}
+
+static inline bool riscv_preempt_v_restore(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_preempt_v_clear_dirty(struct task_struct *task)
+{
+	barrier();
+	task->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_set_restore(struct task_struct *task)
+{
+	barrier();
+	task->thread.riscv_v_flags |= RISCV_PREEMPT_V_NEED_RESTORE;
+}
+
+static inline bool riscv_preempt_v_started(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V);
+}
+
+#else /* !CONFIG_RISCV_ISA_V_PREEMPTIVE */
+static inline bool riscv_preempt_v_dirty(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_restore(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_started(struct task_struct *task) { return false; }
+#define riscv_preempt_v_clear_dirty(tsk)	do {} while (0)
+#define riscv_preempt_v_set_restore(tsk)	do {} while (0)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
 static inline void __switch_to_vector(struct task_struct *prev,
 				      struct task_struct *next)
 {
 	struct pt_regs *regs;
 
-	regs = task_pt_regs(prev);
-	riscv_v_vstate_save(&prev->thread.vstate, regs);
-	riscv_v_vstate_set_restore(next, task_pt_regs(next));
+	if (riscv_preempt_v_started(prev)) {
+		if (riscv_preempt_v_dirty(prev)) {
+			__riscv_v_vstate_save(&prev->thread.kernel_vstate,
+					      prev->thread.kernel_vstate.datap);
+			riscv_preempt_v_clear_dirty(prev);
+		}
+	} else {
+		regs = task_pt_regs(prev);
+		riscv_v_vstate_save(&prev->thread.vstate, regs);
+	}
+
+	if (riscv_preempt_v_started(next))
+		riscv_preempt_v_set_restore(next);
+	else
+		riscv_v_vstate_set_restore(next, task_pt_regs(next));
 }
 
 void riscv_v_vstate_ctrl_init(struct task_struct *tsk);
@@ -231,6 +280,7 @@ static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
 #define riscv_v_vstate_on(regs)			do {} while (0)
 #define riscv_v_thread_free(tsk)		do {} while (0)
 #define  riscv_v_setup_ctx_cache()		do {} while (0)
+#define riscv_v_thread_alloc(tsk)		do {} while (0)
 
 #endif /* CONFIG_RISCV_ISA_V */
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 54ca4564a9263..9d1a305d55087 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -83,6 +83,10 @@ SYM_CODE_START(handle_exception)
 	/* Load the kernel shadow call stack pointer if coming from userspace */
 	scs_load_current_if_task_changed s5
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_start
+#endif
 	move a0, sp /* pt_regs */
 	la ra, ret_from_exception
 
@@ -138,6 +142,10 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	 */
 	csrw CSR_SCRATCH, tp
 1:
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_end
+#endif
 	REG_L a0, PT_STATUS(sp)
 	/*
 	 * The current load reservation is effectively part of the processor's
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
index 241a8f834e1ce..6afe80c7f03ab 100644
--- a/arch/riscv/kernel/kernel_mode_vector.c
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -14,10 +14,13 @@
 #include <asm/vector.h>
 #include <asm/switch_to.h>
 #include <asm/simd.h>
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+#include <asm/asm-prototypes.h>
+#endif
 
 static inline void riscv_v_flags_set(u32 flags)
 {
-	current->thread.riscv_v_flags = flags;
+	WRITE_ONCE(current->thread.riscv_v_flags, flags);
 }
 
 static inline void riscv_v_start(u32 flags)
@@ -27,12 +30,14 @@ static inline void riscv_v_start(u32 flags)
 	orig = riscv_v_flags();
 	BUG_ON((orig & flags) != 0);
 	riscv_v_flags_set(orig | flags);
+	barrier();
 }
 
 static inline void riscv_v_stop(u32 flags)
 {
 	int orig;
 
+	barrier();
 	orig = riscv_v_flags();
 	BUG_ON((orig & flags) == 0);
 	riscv_v_flags_set(orig & ~flags);
@@ -75,6 +80,117 @@ void put_cpu_vector_context(void)
 		preempt_enable();
 }
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static __always_inline u32 *riscv_v_flags_ptr(void)
+{
+	return &current->thread.riscv_v_flags;
+}
+
+static inline void riscv_preempt_v_set_dirty(void)
+{
+	*riscv_v_flags_ptr() |= RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_reset_flags(void)
+{
+	*riscv_v_flags_ptr() &= ~(RISCV_PREEMPT_V_DIRTY | RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_v_ctx_depth_inc(void)
+{
+	*riscv_v_flags_ptr() += RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline void riscv_v_ctx_depth_dec(void)
+{
+	*riscv_v_flags_ptr() -= RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline u32 riscv_v_ctx_get_depth(void)
+{
+	return *riscv_v_flags_ptr() & RISCV_V_CTX_DEPTH_MASK;
+}
+
+static int riscv_v_stop_kernel_context(void)
+{
+	if (riscv_v_ctx_get_depth() != 0 || !riscv_preempt_v_started(current))
+		return 1;
+
+	riscv_preempt_v_clear_dirty(current);
+	riscv_v_stop(RISCV_PREEMPT_V);
+	return 0;
+}
+
+static int riscv_v_start_kernel_context(bool *is_nested)
+{
+	struct __riscv_v_ext_state *kvstate, *uvstate;
+
+	kvstate = &current->thread.kernel_vstate;
+	if (!kvstate->datap)
+		return -ENOENT;
+
+	if (riscv_preempt_v_started(current)) {
+		WARN_ON(riscv_v_ctx_get_depth() == 0);
+		*is_nested = true;
+		get_cpu_vector_context();
+		if (riscv_preempt_v_dirty(current)) {
+			__riscv_v_vstate_save(kvstate, kvstate->datap);
+			riscv_preempt_v_clear_dirty(current);
+		}
+		riscv_preempt_v_set_restore(current);
+		return 0;
+	}
+
+	/* Transfer the ownership of V from user to kernel, then save */
+	riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY);
+	if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) {
+		uvstate = &current->thread.vstate;
+		__riscv_v_vstate_save(uvstate, uvstate->datap);
+	}
+	riscv_preempt_v_clear_dirty(current);
+	return 0;
+}
+
+/* low-level V context handling code, called with irq disabled */
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs)
+{
+	int depth;
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY)
+		riscv_preempt_v_set_dirty();
+
+	riscv_v_ctx_depth_inc();
+}
+
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs)
+{
+	struct __riscv_v_ext_state *vstate = &current->thread.kernel_vstate;
+	u32 depth;
+
+	WARN_ON(!irqs_disabled());
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	riscv_v_ctx_depth_dec();
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0) {
+		if (riscv_preempt_v_restore(current)) {
+			__riscv_v_vstate_restore(vstate, vstate->datap);
+			__riscv_v_vstate_clean(regs);
+			riscv_preempt_v_reset_flags();
+		}
+	}
+}
+#else
+#define riscv_v_start_kernel_context(nested)	(-ENOENT)
+#define riscv_v_stop_kernel_context()		(-ENOENT)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
 /*
  * kernel_vector_begin(): obtain the CPU vector registers for use by the calling
  * context
@@ -90,14 +206,20 @@ void put_cpu_vector_context(void)
  */
 void kernel_vector_begin(void)
 {
+	bool nested = false;
+
 	if (WARN_ON(!has_vector()))
 		return;
 
 	BUG_ON(!may_use_simd());
 
-	get_cpu_vector_context();
+	if (riscv_v_start_kernel_context(&nested)) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+	}
 
-	riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+	if (!nested)
+		riscv_v_vstate_set_restore(current, task_pt_regs(current));
 
 	riscv_v_enable();
 }
@@ -117,10 +239,9 @@ void kernel_vector_end(void)
 	if (WARN_ON(!has_vector()))
 		return;
 
-	riscv_v_vstate_set_restore(current, task_pt_regs(current));
-
 	riscv_v_disable();
 
-	put_cpu_vector_context();
+	if (riscv_v_stop_kernel_context())
+		put_cpu_vector_context();
 }
 EXPORT_SYMBOL_GPL(kernel_vector_end);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 862d59c3872e2..92922dbd5b5c1 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -188,6 +188,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	*dst = *src;
 	/* clear entire V context, including datap for a new task */
 	memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	memset(&dst->thread.kernel_vstate, 0, sizeof(struct __riscv_v_ext_state));
 	clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE);
 
 	return 0;
@@ -224,6 +225,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		p->thread.s[0] = 0;
 	}
 	p->thread.riscv_v_flags = 0;
+	if (has_vector())
+		riscv_v_thread_alloc(p);
 	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index f7b4aeb9e4579..6727d1d3b8f28 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -22,6 +22,9 @@
 
 static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE);
 static struct kmem_cache *riscv_v_user_cachep;
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static struct kmem_cache *riscv_v_kernel_cachep;
+#endif
 
 unsigned long riscv_v_vsize __read_mostly;
 EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -56,6 +59,11 @@ void __init riscv_v_setup_ctx_cache(void)
 	riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
 							 riscv_v_vsize, 16, SLAB_PANIC,
 							 0, riscv_v_vsize, NULL);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_kernel_cachep = kmem_cache_create("riscv_vector_kctx",
+						  riscv_v_vsize, 16,
+						  SLAB_PANIC, NULL);
+#endif
 }
 
 static bool insn_is_vector(u32 insn_buf)
@@ -91,24 +99,35 @@ static bool insn_is_vector(u32 insn_buf)
 	return false;
 }
 
-static int riscv_v_thread_zalloc(void)
+static int riscv_v_thread_zalloc(struct kmem_cache *cache,
+				 struct __riscv_v_ext_state *ctx)
 {
 	void *datap;
 
-	datap = kmem_cache_zalloc(riscv_v_user_cachep, GFP_KERNEL);
+	datap = kmem_cache_zalloc(cache, GFP_KERNEL);
 	if (!datap)
 		return -ENOMEM;
 
-	current->thread.vstate.datap = datap;
-	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
-						    datap));
+	ctx->datap = datap;
+	memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap));
 	return 0;
 }
 
+void riscv_v_thread_alloc(struct task_struct *tsk)
+{
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_thread_zalloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate);
+#endif
+}
+
 void riscv_v_thread_free(struct task_struct *tsk)
 {
 	if (tsk->thread.vstate.datap)
 		kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	if (tsk->thread.kernel_vstate.datap)
+		kmem_cache_free(riscv_v_kernel_cachep, tsk->thread.kernel_vstate.datap);
+#endif
 }
 
 #define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)
@@ -180,7 +199,7 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 	 * context where VS has been off. So, try to allocate the user's V
 	 * context and resume execution.
 	 */
-	if (riscv_v_thread_zalloc()) {
+	if (riscv_v_thread_zalloc(riscv_v_user_cachep, &current->thread.vstate)) {
 		force_sig(SIGBUS);
 		return true;
 	}
-- 
GitLab


From 22c7fa171a02d310e3a3f6ed46a698ca8a0060ed Mon Sep 17 00:00:00 2001
From: Hao Sun <sunhao.th@gmail.com>
Date: Mon, 15 Jan 2024 09:20:27 +0100
Subject: [PATCH 2791/4076] bpf: Reject variable offset alu on PTR_TO_FLOW_KEYS

For PTR_TO_FLOW_KEYS, check_flow_keys_access() only uses fixed off
for validation. However, variable offset ptr alu is not prohibited
for this ptr kind. So the variable offset is not checked.

The following prog is accepted:

  func#0 @0
  0: R1=ctx() R10=fp0
  0: (bf) r6 = r1                       ; R1=ctx() R6_w=ctx()
  1: (79) r7 = *(u64 *)(r6 +144)        ; R6_w=ctx() R7_w=flow_keys()
  2: (b7) r8 = 1024                     ; R8_w=1024
  3: (37) r8 /= 1                       ; R8_w=scalar()
  4: (57) r8 &= 1024                    ; R8_w=scalar(smin=smin32=0,
  smax=umax=smax32=umax32=1024,var_off=(0x0; 0x400))
  5: (0f) r7 += r8
  mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1
  mark_precise: frame0: regs=r8 stack= before 4: (57) r8 &= 1024
  mark_precise: frame0: regs=r8 stack= before 3: (37) r8 /= 1
  mark_precise: frame0: regs=r8 stack= before 2: (b7) r8 = 1024
  6: R7_w=flow_keys(smin=smin32=0,smax=umax=smax32=umax32=1024,var_off
  =(0x0; 0x400)) R8_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=1024,
  var_off=(0x0; 0x400))
  6: (79) r0 = *(u64 *)(r7 +0)          ; R0_w=scalar()
  7: (95) exit

This prog loads flow_keys to r7, and adds the variable offset r8
to r7, and finally causes out-of-bounds access:

  BUG: unable to handle page fault for address: ffffc90014c80038
  [...]
  Call Trace:
   <TASK>
   bpf_dispatcher_nop_func include/linux/bpf.h:1231 [inline]
   __bpf_prog_run include/linux/filter.h:651 [inline]
   bpf_prog_run include/linux/filter.h:658 [inline]
   bpf_prog_run_pin_on_cpu include/linux/filter.h:675 [inline]
   bpf_flow_dissect+0x15f/0x350 net/core/flow_dissector.c:991
   bpf_prog_test_run_flow_dissector+0x39d/0x620 net/bpf/test_run.c:1359
   bpf_prog_test_run kernel/bpf/syscall.c:4107 [inline]
   __sys_bpf+0xf8f/0x4560 kernel/bpf/syscall.c:5475
   __do_sys_bpf kernel/bpf/syscall.c:5561 [inline]
   __se_sys_bpf kernel/bpf/syscall.c:5559 [inline]
   __x64_sys_bpf+0x73/0xb0 kernel/bpf/syscall.c:5559
   do_syscall_x64 arch/x86/entry/common.c:52 [inline]
   do_syscall_64+0x3f/0x110 arch/x86/entry/common.c:83
   entry_SYSCALL_64_after_hwframe+0x63/0x6b

Fix this by rejecting ptr alu with variable offset on flow_keys.
Applying the patch rejects the program with "R7 pointer arithmetic
on flow_keys prohibited".

Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook")
Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20240115082028.9992-1-sunhao.th@gmail.com
---
 kernel/bpf/verifier.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index adbf330d364bb..65f598694d550 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12826,6 +12826,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	}
 
 	switch (base_type(ptr_reg->type)) {
+	case PTR_TO_FLOW_KEYS:
+		if (known)
+			break;
+		fallthrough;
 	case CONST_PTR_TO_MAP:
 		/* smin_val represents the known value */
 		if (known && smin_val == 0 && opcode == BPF_ADD)
-- 
GitLab


From 33772ff3b887eb2f426ed66bcb1808837a40669c Mon Sep 17 00:00:00 2001
From: Hao Sun <sunhao.th@gmail.com>
Date: Mon, 15 Jan 2024 09:20:28 +0100
Subject: [PATCH 2792/4076] selftests/bpf: Add test for alu on PTR_TO_FLOW_KEYS

Add a test case for PTR_TO_FLOW_KEYS alu. Testing if alu with variable
offset on flow_keys is rejected. For the fixed offset success case, we
already have C code coverage to verify (e.g. via bpf_flow.c).

Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20240115082028.9992-2-sunhao.th@gmail.com
---
 .../bpf/progs/verifier_value_illegal_alu.c    | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
index 71814a7532160..a9ab37d3b9e2d 100644
--- a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
+++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
@@ -146,4 +146,23 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+SEC("flow_dissector")
+__description("flow_keys illegal alu op with variable offset")
+__failure __msg("R7 pointer arithmetic on flow_keys prohibited")
+__naked void flow_keys_illegal_variable_offset_alu(void)
+{
+	asm volatile("					\
+	r6 = r1;					\
+	r7 = *(u64*)(r6 + %[flow_keys_off]);		\
+	r8 = 8;						\
+	r8 /= 1;					\
+	r8 &= 8;					\
+	r7 += r8;					\
+	r0 = *(u64*)(r7 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys))
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
-- 
GitLab


From be50df31c4e2a69f961a3bb759346d299eaa2b23 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Tue, 16 Jan 2024 17:34:31 +0300
Subject: [PATCH 2793/4076] block: bio-integrity: fix kcalloc() arguments order

When compiling with gcc version 14.0.1 20240116 (experimental)
and W=1, I've noticed the following warning:

block/bio-integrity.c: In function 'bio_integrity_map_user':
block/bio-integrity.c:339:38: warning: 'kcalloc' sizes specified with 'sizeof'
in the earlier argument and not in the later argument [-Wcalloc-transposed-args]
  339 |                 bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
      |                                      ^
block/bio-integrity.c:339:38: note: earlier argument should specify number of
elements, later size of each element

Since 'n' and 'size' arguments of 'kcalloc()' are multiplied to
calculate the final size, their actual order doesn't affect the
result and so this is not a bug. But it's still worth to fix it.

Fixes: 492c5d455969 ("block: bio-integrity: directly map user buffers")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20240116143437.89060-1-dmantipov@yandex.ru
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio-integrity.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index feef615e2c9c8..c9a16fba58b9c 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -336,7 +336,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
 	if (nr_vecs > BIO_MAX_VECS)
 		return -E2BIG;
 	if (nr_vecs > UIO_FASTIOV) {
-		bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
+		bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL);
 		if (!bvec)
 			return -ENOMEM;
 		pages = NULL;
-- 
GitLab


From 58f65f9db7e0de366a5a115c2e2c0703858bba69 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 16 Jan 2024 21:43:25 +0100
Subject: [PATCH 2794/4076] Input: atkbd - use ab83 as id when skipping the
 getid command
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Barnabás reported that the change to skip the getid command
when the controller is in translated mode on laptops caused
the Version field of his "AT Translated Set 2 keyboard"
input device to change from ab83 to abba, breaking a custom
hwdb entry for this keyboard.

Use the standard ab83 id for keyboards when getid is skipped
(rather then that getid fails) to avoid reporting a different
Version to userspace then before skipping the getid.

Fixes: 936e4d49ecbc ("Input: atkbd - skip ATKBD_CMD_GETID in translated mode")
Reported-by: Barnabás Pőcze <pobrn@protonmail.com>
Closes: https://lore.kernel.org/linux-input/W1ydwoG2fYv85Z3C3yfDOJcVpilEvGge6UGa9kZh8zI2-qkHXp7WLnl2hSkFz63j-c7WupUWI5TLL6n7Lt8DjRuU-yJBwLYWrreb1hbnd6A=@protonmail.com/
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240116204325.7719-1-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/atkbd.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 786f00f6b7fd8..13ef6284223da 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -791,9 +791,9 @@ static bool atkbd_is_portable_device(void)
  * not work. So in this case simply assume a keyboard is connected to avoid
  * confusing some laptop keyboards.
  *
- * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using a fake id is
- * ok in translated mode, only atkbd_select_set() checks atkbd->id and in
- * translated mode that is a no-op.
+ * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using the standard
+ * 0xab83 id is ok in translated mode, only atkbd_select_set() checks atkbd->id
+ * and in translated mode that is a no-op.
  */
 static bool atkbd_skip_getid(struct atkbd *atkbd)
 {
@@ -811,6 +811,7 @@ static int atkbd_probe(struct atkbd *atkbd)
 {
 	struct ps2dev *ps2dev = &atkbd->ps2dev;
 	unsigned char param[2];
+	bool skip_getid;
 
 /*
  * Some systems, where the bit-twiddling when testing the io-lines of the
@@ -832,7 +833,8 @@ static int atkbd_probe(struct atkbd *atkbd)
  */
 
 	param[0] = param[1] = 0xa5;	/* initialize with invalid values */
-	if (atkbd_skip_getid(atkbd) || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
+	skip_getid = atkbd_skip_getid(atkbd);
+	if (skip_getid || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
 
 /*
  * If the get ID command was skipped or failed, we check if we can at least set
@@ -842,7 +844,7 @@ static int atkbd_probe(struct atkbd *atkbd)
 		param[0] = 0;
 		if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS))
 			return -1;
-		atkbd->id = 0xabba;
+		atkbd->id = skip_getid ? 0xab83 : 0xabba;
 		return 0;
 	}
 
-- 
GitLab


From 53c41052ba3121761e6f62a813961164532a214f Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 16 Jan 2024 16:12:18 -0500
Subject: [PATCH 2795/4076] eventfs: Have the inodes all for files and
 directories all be the same

The dentries and inodes are created in the readdir for the sole purpose of
getting a consistent inode number. Linus stated that is unnecessary, and
that all inodes can have the same inode number. For a virtual file system
they are pretty meaningless.

Instead use a single unique inode number for all files and one for all
directories.

Link: https://lore.kernel.org/all/20240116133753.2808d45e@gandalf.local.home/
Link: https://lore.kernel.org/linux-trace-kernel/20240116211353.412180363@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al  Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index fdff53d5a1f87..5edf0b96758ba 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -32,6 +32,10 @@
  */
 static DEFINE_MUTEX(eventfs_mutex);
 
+/* Choose something "unique" ;-) */
+#define EVENTFS_FILE_INODE_INO		0x12c4e37
+#define EVENTFS_DIR_INODE_INO		0x134b2f5
+
 /*
  * The eventfs_inode (ei) itself is protected by SRCU. It is released from
  * its parent's list and will have is_freed set (under eventfs_mutex).
@@ -352,6 +356,9 @@ static struct dentry *create_file(const char *name, umode_t mode,
 	inode->i_fop = fop;
 	inode->i_private = data;
 
+	/* All files will have the same inode number */
+	inode->i_ino = EVENTFS_FILE_INODE_INO;
+
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
 	d_instantiate(dentry, inode);
@@ -388,6 +395,9 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
+	/* All directories will have the same inode number */
+	inode->i_ino = EVENTFS_DIR_INODE_INO;
+
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
 
-- 
GitLab


From 7bed6f3d08b7af27b7015da8dc3acf2b9c1f21d7 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 16 Jan 2024 21:29:59 +0000
Subject: [PATCH 2796/4076] block: Fix iterating over an empty bio with
 bio_for_each_folio_all

If the bio contains no data, bio_first_folio() calls page_folio() on a
NULL pointer and oopses.  Move the test that we've reached the end of
the bio from bio_next_folio() to bio_first_folio().

Reported-by: syzbot+8b23309d5788a79d3eea@syzkaller.appspotmail.com
Reported-by: syzbot+004c1e0fced2b4bc3dcc@syzkaller.appspotmail.com
Fixes: 640d1930bef4 ("block: Add bio_for_each_folio_all()")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Link: https://lore.kernel.org/r/20240116212959.3413014-1-willy@infradead.org
[axboe: add unlikely() to error case]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bio.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/bio.h b/include/linux/bio.h
index ec4db73e5f4ec..875d792bffff8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -286,6 +286,11 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
 {
 	struct bio_vec *bvec = bio_first_bvec_all(bio) + i;
 
+	if (unlikely(i >= bio->bi_vcnt)) {
+		fi->folio = NULL;
+		return;
+	}
+
 	fi->folio = page_folio(bvec->bv_page);
 	fi->offset = bvec->bv_offset +
 			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
@@ -303,10 +308,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio)
 		fi->offset = 0;
 		fi->length = min(folio_size(fi->folio), fi->_seg_count);
 		fi->_next = folio_next(fi->folio);
-	} else if (fi->_i + 1 < bio->bi_vcnt) {
-		bio_first_folio(fi, bio, fi->_i + 1);
 	} else {
-		fi->folio = NULL;
+		bio_first_folio(fi, bio, fi->_i + 1);
 	}
 }
 
-- 
GitLab


From 852e46e239ee6db3cd220614cf8bce96e79227c2 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 16 Jan 2024 16:12:19 -0500
Subject: [PATCH 2797/4076] eventfs: Do not create dentries nor inodes in
 iterate_shared

The original eventfs code added a wrapper around the dcache_readdir open
callback and created all the dentries and inodes at open, and increment
their ref count. A wrapper was added around the dcache_readdir release
function to decrement all the ref counts of those created inodes and
dentries. But this proved to be buggy[1] for when a kprobe was created
during a dir read, it would create a dentry between the open and the
release, and because the release would decrement all ref counts of all
files and directories, that would include the kprobe directory that was
not there to have its ref count incremented in open. This would cause the
ref count to go to negative and later crash the kernel.

To solve this, the dentries and inodes that were created and had their ref
count upped in open needed to be saved. That list needed to be passed from
the open to the release, so that the release would only decrement the ref
counts of the entries that were incremented in the open.

Unfortunately, the dcache_readdir logic was already using the
file->private_data, which is the only field that can be used to pass
information from the open to the release. What was done was the eventfs
created another descriptor that had a void pointer to save the
dcache_readdir pointer, and it wrapped all the callbacks, so that it could
save the list of entries that had their ref counts incremented in the
open, and pass it to the release. The wrapped callbacks would just put
back the dcache_readdir pointer and call the functions it used so it could
still use its data[2].

But Linus had an issue with the "hijacking" of the file->private_data
(unfortunately this discussion was on a security list, so no public link).
Which we finally agreed on doing everything within the iterate_shared
callback and leave the dcache_readdir out of it[3]. All the information
needed for the getents() could be created then.

But this ended up being buggy too[4]. The iterate_shared callback was not
the right place to create the dentries and inodes. Even Christian Brauner
had issues with that[5].

An attempt was to go back to creating the inodes and dentries at
the open, create an array to store the information in the
file->private_data, and pass that information to the other callbacks.[6]

The difference between that and the original method, is that it does not
use dcache_readdir. It also does not up the ref counts of the dentries and
pass them. Instead, it creates an array of a structure that saves the
dentry's name and inode number. That information is used in the
iterate_shared callback, and the array is freed in the dir release. The
dentries and inodes created in the open are not used for the iterate_share
or release callbacks. Just their names and inode numbers.

Linus did not like that either[7] and just wanted to remove the dentries
being created in iterate_shared and use the hard coded inode numbers.

[ All this while Linus enjoyed an unexpected vacation during the merge
  window due to lack of power. ]

[1] https://lore.kernel.org/linux-trace-kernel/20230919211804.230edf1e@gandalf.local.home/
[2] https://lore.kernel.org/linux-trace-kernel/20230922163446.1431d4fa@gandalf.local.home/
[3] https://lore.kernel.org/linux-trace-kernel/20240104015435.682218477@goodmis.org/
[4] https://lore.kernel.org/all/202401152142.bfc28861-oliver.sang@intel.com/
[5] https://lore.kernel.org/all/20240111-unzahl-gefegt-433acb8a841d@brauner/
[6] https://lore.kernel.org/all/20240116114711.7e8637be@gandalf.local.home/
[7] https://lore.kernel.org/all/20240116170154.5bf0a250@gandalf.local.home/

Link: https://lore.kernel.org/linux-trace-kernel/20240116211353.573784051@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al  Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Fixes: 493ec81a8fb8 ("eventfs: Stop using dcache_readdir() for getdents()")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401152142.bfc28861-oliver.sang@intel.com
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 20 +++++---------------
 1 file changed, 5 insertions(+), 15 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 5edf0b96758ba..10580d6b50125 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -727,8 +727,6 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct dentry *ei_dentry = NULL;
-	struct dentry *dentry;
 	const char *name;
 	umode_t mode;
 	int idx;
@@ -749,11 +747,11 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 	mutex_lock(&eventfs_mutex);
 	ei = READ_ONCE(ti->private);
-	if (ei && !ei->is_freed)
-		ei_dentry = READ_ONCE(ei->dentry);
+	if (ei && ei->is_freed)
+		ei = NULL;
 	mutex_unlock(&eventfs_mutex);
 
-	if (!ei || !ei_dentry)
+	if (!ei)
 		goto out;
 
 	/*
@@ -780,11 +778,7 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 		if (r <= 0)
 			continue;
 
-		dentry = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
-		if (!dentry)
-			goto out;
-		ino = dentry->d_inode->i_ino;
-		dput(dentry);
+		ino = EVENTFS_FILE_INODE_INO;
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
 			goto out;
@@ -808,11 +802,7 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		name = ei_child->name;
 
-		dentry = create_dir_dentry(ei, ei_child, ei_dentry);
-		if (!dentry)
-			goto out_dec;
-		ino = dentry->d_inode->i_ino;
-		dput(dentry);
+		ino = EVENTFS_DIR_INODE_INO;
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
 			goto out_dec;
-- 
GitLab


From 1057066009c4325bb1d8430c9274894d0860e7c3 Mon Sep 17 00:00:00 2001
From: Erick Archer <erick.archer@gmx.com>
Date: Mon, 15 Jan 2024 19:16:58 +0100
Subject: [PATCH 2798/4076] eventfs: Use kcalloc() instead of kzalloc()

As noted in the "Deprecated Interfaces, Language Features, Attributes,
and Conventions" documentation [1], size calculations (especially
multiplication) should not be performed in memory allocator (or similar)
function arguments due to the risk of them overflowing. This could lead
to values wrapping around and a smaller allocation being made than the
caller was expecting. Using those allocations could lead to linear
overflows of heap memory and other misbehaviors.

So, use the purpose specific kcalloc() function instead of the argument
size * count in the kzalloc() function.

[1] https://www.kernel.org/doc/html/next/process/deprecated.html#open-coded-arithmetic-in-allocator-arguments

Link: https://lore.kernel.org/linux-trace-kernel/20240115181658.4562-1-erick.archer@gmx.com

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://github.com/KSPP/linux/issues/162
Signed-off-by: Erick Archer <erick.archer@gmx.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 10580d6b50125..6795fda2af191 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -97,7 +97,7 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	/* Preallocate the children mode array if necessary */
 	if (!(dentry->d_inode->i_mode & S_IFDIR)) {
 		if (!ei->entry_attrs) {
-			ei->entry_attrs = kzalloc(sizeof(*ei->entry_attrs) * ei->nr_entries,
+			ei->entry_attrs = kcalloc(ei->nr_entries, sizeof(*ei->entry_attrs),
 						  GFP_NOFS);
 			if (!ei->entry_attrs) {
 				ret = -ENOMEM;
@@ -874,7 +874,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 	}
 
 	if (size) {
-		ei->d_children = kzalloc(sizeof(*ei->d_children) * size, GFP_KERNEL);
+		ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL);
 		if (!ei->d_children) {
 			kfree_const(ei->name);
 			kfree(ei);
@@ -941,7 +941,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 		goto fail;
 
 	if (size) {
-		ei->d_children = kzalloc(sizeof(*ei->d_children) * size, GFP_KERNEL);
+		ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL);
 		if (!ei->d_children)
 			goto fail;
 	}
-- 
GitLab


From 8ca5d2641be217a78a891d4dbe2a46232d1d8eb9 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 16 Jan 2024 10:51:34 +0000
Subject: [PATCH 2799/4076] cifs: remove redundant variable tcon_exist

The variable tcon_exist is being assigned however it is never read, the
variable is redundant and can be removed.

Cleans up clang scan build warning:
warning: Although the value stored to 'tcon_exist' is used in
the enclosing expression, the value is never actually readfrom
'tcon_exist' [deadcode.DeadStores]

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index bd25c34dc398b..50f6bf16b6245 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3918,7 +3918,7 @@ void smb2_reconnect_server(struct work_struct *work)
 	struct cifs_ses *ses, *ses2;
 	struct cifs_tcon *tcon, *tcon2;
 	struct list_head tmp_list, tmp_ses_list;
-	bool tcon_exist = false, ses_exist = false;
+	bool ses_exist = false;
 	bool tcon_selected = false;
 	int rc;
 	bool resched = false;
@@ -3964,7 +3964,7 @@ void smb2_reconnect_server(struct work_struct *work)
 			if (tcon->need_reconnect || tcon->need_reopen_files) {
 				tcon->tc_count++;
 				list_add_tail(&tcon->rlist, &tmp_list);
-				tcon_selected = tcon_exist = true;
+				tcon_selected = true;
 			}
 		}
 		/*
@@ -3973,7 +3973,7 @@ void smb2_reconnect_server(struct work_struct *work)
 		 */
 		if (ses->tcon_ipc && ses->tcon_ipc->need_reconnect) {
 			list_add_tail(&ses->tcon_ipc->rlist, &tmp_list);
-			tcon_selected = tcon_exist = true;
+			tcon_selected = true;
 			cifs_smb_ses_inc_refcount(ses);
 		}
 		/*
-- 
GitLab


From 776dac5a662774f07a876b650ba578d0a62d20db Mon Sep 17 00:00:00 2001
From: Kunwu Chan <chentao@kylinos.cn>
Date: Thu, 11 Jan 2024 15:20:18 +0800
Subject: [PATCH 2800/4076] net: dsa: vsc73xx: Add null pointer check to
 vsc73xx_gpio_probe

devm_kasprintf() returns a pointer to dynamically allocated memory
which can be NULL upon failure.

Fixes: 05bd97fc559d ("net: dsa: Add Vitesse VSC73xx DSA router driver")
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240111072018.75971-1-chentao@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/vitesse-vsc73xx-core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index dd50502e21229..ae70eac3be28f 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -1135,6 +1135,8 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
 
 	vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x",
 				       vsc->chipid);
+	if (!vsc->gc.label)
+		return -ENOMEM;
 	vsc->gc.ngpio = 4;
 	vsc->gc.owner = THIS_MODULE;
 	vsc->gc.parent = vsc->dev;
-- 
GitLab


From 97eb5d51b4a584a60e5d096bdb6b33edc9f50d8d Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 15 Jan 2024 12:43:38 +0000
Subject: [PATCH 2801/4076] net: sfp-bus: fix SFP mode detect from bitrate

The referenced commit moved the setting of the Autoneg and pause bits
early in sfp_parse_support(). However, we check whether the modes are
empty before using the bitrate to set some modes. Setting these bits
so early causes that test to always be false, preventing this working,
and thus some modules that used to work no longer do.

Move them just before the call to the quirk.

Fixes: 8110633db49d ("net: sfp-bus: allow SFP quirks to override Autoneg and pause bits")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://lore.kernel.org/r/E1rPMJW-001Ahf-L0@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/sfp-bus.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 6fa679b36290e..db39dec7f2471 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -151,10 +151,6 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 	unsigned int br_min, br_nom, br_max;
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, };
 
-	phylink_set(modes, Autoneg);
-	phylink_set(modes, Pause);
-	phylink_set(modes, Asym_Pause);
-
 	/* Decode the bitrate information to MBd */
 	br_min = br_nom = br_max = 0;
 	if (id->base.br_nominal) {
@@ -339,6 +335,10 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 		}
 	}
 
+	phylink_set(modes, Autoneg);
+	phylink_set(modes, Pause);
+	phylink_set(modes, Asym_Pause);
+
 	if (bus->sfp_quirk && bus->sfp_quirk->modes)
 		bus->sfp_quirk->modes(id, modes, interfaces);
 
-- 
GitLab


From e9ce7ededf14af3396312f02d1622f4889d676ca Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 15 Jan 2024 14:59:22 +0100
Subject: [PATCH 2802/4076] selftests: rtnetlink: use setup_ns in bonding test

This is a follow-up of commit a159cbe81d3b ("selftests: rtnetlink: check
enslaving iface in a bond") after the merge of net-next into net.

The goal is to follow the new convention,
see commit d3b6b1116127 ("selftests/net: convert rtnetlink.sh to run it in
unique namespace") for more details.

Let's use also the generic dummy name instead of defining a new one.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20240115135922.3662648-1-nicolas.dichtel@6wind.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/rtnetlink.sh | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index a31be0eaaa50f..4667d74579d13 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -1244,21 +1244,19 @@ kci_test_address_proto()
 
 kci_test_enslave_bonding()
 {
-	local testns="testns"
 	local bond="bond123"
-	local dummy="dummy123"
 	local ret=0
 
-	run_cmd ip netns add "$testns"
-	if [ $ret -ne 0 ]; then
+	setup_ns testns
+	if [ $? -ne 0 ]; then
 		end_test "SKIP bonding tests: cannot add net namespace $testns"
 		return $ksft_skip
 	fi
 
 	run_cmd ip -netns $testns link add dev $bond type bond mode balance-rr
-	run_cmd ip -netns $testns link add dev $dummy type dummy
-	run_cmd ip -netns $testns link set dev $dummy up
-	run_cmd ip -netns $testns link set dev $dummy master $bond down
+	run_cmd ip -netns $testns link add dev $devdummy type dummy
+	run_cmd ip -netns $testns link set dev $devdummy up
+	run_cmd ip -netns $testns link set dev $devdummy master $bond down
 	if [ $ret -ne 0 ]; then
 		end_test "FAIL: initially up interface added to a bond and set down"
 		ip netns del "$testns"
-- 
GitLab


From 2772ae4d66d17c6a8b4c167ddb660fc8d7972da5 Mon Sep 17 00:00:00 2001
From: WANG Xuerui <git@xen0n.name>
Date: Wed, 17 Jan 2024 12:42:59 +0800
Subject: [PATCH 2803/4076] modpost: Ignore relaxation and alignment marker
 relocs on LoongArch

With recent trunk versions of binutils and gcc, alignment directives are
represented with R_LARCH_ALIGN relocs on LoongArch, which is necessary
for the linker to maintain alignment requirements during its relaxation
passes. And even though the kernel is built with relaxation disabled, so
far a small number of R_LARCH_RELAX marker relocs are still emitted as
part of la.* pseudo instructions in assembly. These two kinds of relocs
do not refer to symbols, which can trip up modpost's section mismatch
checks, because the r_offset of said relocs can be zero or any other
meaningless value, eventually leading to a `from == NULL` condition in
default_mismatch_handler and SIGSEGV.

As the two kinds of relocs are not concerned with symbols, just ignore
them for section mismatch check purposes.

Signed-off-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 scripts/mod/modpost.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index cb6406f485a96..68ab45273a22f 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1346,6 +1346,14 @@ static Elf_Addr addend_mips_rel(uint32_t *location, unsigned int r_type)
 #define R_LARCH_SUB32		55
 #endif
 
+#ifndef R_LARCH_RELAX
+#define R_LARCH_RELAX		100
+#endif
+
+#ifndef R_LARCH_ALIGN
+#define R_LARCH_ALIGN		102
+#endif
+
 static void get_rel_type_and_sym(struct elf_info *elf, uint64_t r_info,
 				 unsigned int *r_type, unsigned int *r_sym)
 {
@@ -1400,9 +1408,16 @@ static void section_rela(struct module *mod, struct elf_info *elf,
 				continue;
 			break;
 		case EM_LOONGARCH:
-			if (!strcmp("__ex_table", fromsec) &&
-			    r_type == R_LARCH_SUB32)
+			switch (r_type) {
+			case R_LARCH_SUB32:
+				if (!strcmp("__ex_table", fromsec))
+					continue;
+				break;
+			case R_LARCH_RELAX:
+			case R_LARCH_ALIGN:
+				/* These relocs do not refer to symbols */
 				continue;
+			}
 			break;
 		}
 
-- 
GitLab


From f58b0abae839f06be9d791d16196922a4b281777 Mon Sep 17 00:00:00 2001
From: WANG Rui <wangrui@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:00 +0800
Subject: [PATCH 2804/4076] scripts/min-tool-version.sh: Raise minimum clang
 version to 18.0.0 for loongarch

The existing mainline clang development version encounters difficulties
compiling the LoongArch kernel module. It is anticipated that this issue
will be resolved in the upcoming 18.0.0 release. To prevent user
confusion arising from broken builds, it is advisable to raise the
minimum required clang version for LoongArch to 18.0.0.

Suggested-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://github.com/ClangBuiltLinux/linux/issues/1941
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: WANG Rui <wangrui@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 scripts/min-tool-version.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index fd5ffdb81bab7..1c6ab10dc69ee 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -26,6 +26,8 @@ gcc)
 llvm)
 	if [ "$SRCARCH" = s390 ]; then
 		echo 15.0.0
+	elif [ "$SRCARCH" = loongarch ]; then
+		echo 18.0.0
 	else
 		echo 11.0.0
 	fi
-- 
GitLab


From 90868ff9cadecd46fa2a4f5501c66bfea8ade9b7 Mon Sep 17 00:00:00 2001
From: WANG Rui <wangrui@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:00 +0800
Subject: [PATCH 2805/4076] LoongArch: Enable initial Rust support

Enable initial Rust support for LoongArch.

Tested-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: WANG Rui <wangrui@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 Documentation/rust/arch-support.rst | 13 +++++++------
 arch/loongarch/Kconfig              |  1 +
 arch/loongarch/Makefile             |  3 +++
 scripts/generate_rust_target.rs     |  7 +++++++
 4 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst
index b91e9ef4d0c21..73203ba1e9011 100644
--- a/Documentation/rust/arch-support.rst
+++ b/Documentation/rust/arch-support.rst
@@ -12,10 +12,11 @@ which uses ``libclang``.
 Below is a general summary of architectures that currently work. Level of
 support corresponds to ``S`` values in the ``MAINTAINERS`` file.
 
-============  ================  ==============================================
-Architecture  Level of support  Constraints
-============  ================  ==============================================
-``um``        Maintained        ``x86_64`` only.
-``x86``       Maintained        ``x86_64`` only.
-============  ================  ==============================================
+=============  ================  ==============================================
+Architecture   Level of support  Constraints
+=============  ================  ==============================================
+``loongarch``  Maintained        -
+``um``         Maintained        ``x86_64`` only.
+``x86``        Maintained        ``x86_64`` only.
+=============  ================  ==============================================
 
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index ee123820a4760..6b9da3effdf8e 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -140,6 +140,7 @@ config LOONGARCH
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK
 	select HAVE_RSEQ
+	select HAVE_RUST
 	select HAVE_SAMPLE_FTRACE_DIRECT
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_SETUP_PER_CPU_AREA if NUMA
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 4ba8d67ddb097..ba45cb7b621cd 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -81,8 +81,11 @@ KBUILD_AFLAGS_MODULE		+= -Wa,-mla-global-with-abs
 KBUILD_CFLAGS_MODULE		+= -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs
 endif
 
+KBUILD_RUSTFLAGS_MODULE		+= -Crelocation-model=pic
+
 ifeq ($(CONFIG_RELOCATABLE),y)
 KBUILD_CFLAGS_KERNEL		+= -fPIE
+KBUILD_RUSTFLAGS_KERNEL		+= -Crelocation-model=pie
 LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs)
 endif
 
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 3c6cbe2b278d3..0da52b548ba50 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -161,6 +161,13 @@ fn main() {
         ts.push("features", features);
         ts.push("llvm-target", "x86_64-linux-gnu");
         ts.push("target-pointer-width", "64");
+    } else if cfg.has("LOONGARCH") {
+        ts.push("arch", "loongarch64");
+        ts.push("data-layout", "e-m:e-p:64:64-i64:64-i128:128-n64-S128");
+        ts.push("features", "-f,-d");
+        ts.push("llvm-target", "loongarch64-linux-gnusf");
+        ts.push("llvm-abiname", "lp64s");
+        ts.push("target-pointer-width", "64");
     } else {
         panic!("Unsupported architecture");
     }
-- 
GitLab


From 8e07e0e3964ca4e23ce7b68e2096fe660a888942 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:00 +0800
Subject: [PATCH 2806/4076] dt-bindings: loongarch: Add CPU bindings for
 LoongArch

Add the available CPUs in LoongArch binding with DT schema format using
json-schema.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../devicetree/bindings/loongarch/cpus.yaml   | 61 +++++++++++++++++++
 1 file changed, 61 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/loongarch/cpus.yaml

diff --git a/Documentation/devicetree/bindings/loongarch/cpus.yaml b/Documentation/devicetree/bindings/loongarch/cpus.yaml
new file mode 100644
index 0000000000000..f175872995e11
--- /dev/null
+++ b/Documentation/devicetree/bindings/loongarch/cpus.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/loongarch/cpus.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: LoongArch CPUs
+
+maintainers:
+  - Binbin Zhou <zhoubinbin@loongson.cn>
+
+description:
+  This document describes the list of LoongArch CPU cores that support FDT,
+  it describe the layout of CPUs in a system through the "cpus" node.
+
+allOf:
+  - $ref: /schemas/cpu.yaml#
+
+properties:
+  compatible:
+    enum:
+      - loongson,la264
+      - loongson,la364
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/loongson,ls2k-clk.h>
+
+    cpus {
+        #size-cells = <0>;
+        #address-cells = <1>;
+
+        cpu@0 {
+            compatible = "loongson,la264";
+            device_type = "cpu";
+            reg = <0>;
+            clocks = <&clk LOONGSON2_NODE_CLK>;
+        };
+
+        cpu@1 {
+            compatible = "loongson,la264";
+            device_type = "cpu";
+            reg = <1>;
+            clocks = <&clk LOONGSON2_NODE_CLK>;
+        };
+    };
+
+...
-- 
GitLab


From ec6b36edf0cea06d651ef14092921a339b4eea2f Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:00 +0800
Subject: [PATCH 2807/4076] dt-bindings: loongarch: Add Loongson SoC boards
 compatibles

Add Loongson SoC boards binding with DT schema format using json-schema.

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../bindings/loongarch/loongson.yaml          | 34 +++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/loongarch/loongson.yaml

diff --git a/Documentation/devicetree/bindings/loongarch/loongson.yaml b/Documentation/devicetree/bindings/loongarch/loongson.yaml
new file mode 100644
index 0000000000000..e1a4a97b7576c
--- /dev/null
+++ b/Documentation/devicetree/bindings/loongarch/loongson.yaml
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/loongarch/loongson.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Loongson SoC-based boards
+
+maintainers:
+  - Binbin Zhou <zhoubinbin@loongson.cn>
+
+properties:
+  $nodename:
+    const: '/'
+  compatible:
+    oneOf:
+      - description: Loongson-2K0500 processor based boards
+        items:
+          - const: loongson,ls2k0500-ref
+          - const: loongson,ls2k0500
+
+      - description: Loongson-2K1000 processor based boards
+        items:
+          - const: loongson,ls2k1000-ref
+          - const: loongson,ls2k1000
+
+      - description: Loongson-2K2000 processor based boards
+        items:
+          - const: loongson,ls2k2000-ref
+          - const: loongson,ls2k2000
+
+additionalProperties: true
+
+...
-- 
GitLab


From aaeebb3ea4f2d6674b0fbc8bd48bf8862309f191 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:00 +0800
Subject: [PATCH 2808/4076] dt-bindings: interrupt-controller:
 loongson,liointc: Fix dtbs_check warning for reg-names

As we know, the Loongson-2K0500 is a single-core CPU, and the core1-
related register (isr1) does not exist. So "reg" and "reg-names" should
be set to "minItems 2"(main nad isr0).

This fixes dtbs_check warning:

DTC_CHK arch/loongarch/boot/dts/loongson-2k0500-ref.dtb
arch/loongarch/boot/dts/loongson-2k0500-ref.dtb: interrupt-controller@1fe11400: reg-names: ['main', 'isr0'] is too short
        From schema: Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
arch/loongarch/boot/dts/loongson-2k0500-ref.dtb: interrupt-controller@1fe11400: Unevaluated properties are not allowed ('reg-names' was unexpected)
        From schema: Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
arch/loongarch/boot/dts/loongson-2k0500-ref.dtb: interrupt-controller@1fe11400: reg: [[0, 534844416, 0, 64], [0, 534843456, 0, 8]] is too short
        From schema: Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
arch/loongarch/boot/dts/loongson-2k0500-ref.dtb: interrupt-controller@1fe11440: reg-names: ['main', 'isr0'] is too short
        From schema: Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml

Acked-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../interrupt-controller/loongson,liointc.yaml        | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
index 00b570c829039..a3276c1d9b59f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
@@ -11,8 +11,13 @@ maintainers:
 
 description: |
   This interrupt controller is found in the Loongson-3 family of chips and
-  Loongson-2K1000 chip, as the primary package interrupt controller which
+  Loongson-2K series chips, as the primary package interrupt controller which
   can route local I/O interrupt to interrupt lines of cores.
+  Be aware of the following points.
+  1.The Loongson-2K0500 is a single core CPU;
+  2.The Loongson-2K0500/2K1000 has 64 device interrupt sources as inputs, so we
+    need to define two nodes in dts{i} to describe the "0-31" and "32-61" interrupt
+    sources respectively.
 
 allOf:
   - $ref: /schemas/interrupt-controller.yaml#
@@ -33,6 +38,7 @@ properties:
       - const: main
       - const: isr0
       - const: isr1
+    minItems: 2
 
   interrupt-controller: true
 
@@ -86,7 +92,8 @@ if:
 then:
   properties:
     reg:
-      minItems: 3
+      minItems: 2
+      maxItems: 3
 
   required:
     - reg-names
-- 
GitLab


From db8ce2407090f695339e3406a034377dcdc2c942 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:00 +0800
Subject: [PATCH 2809/4076] dt-bindings: interrupt-controller:
 loongson,liointc: Fix dtbs_check warning for interrupt-names

The Loongson-2K0500/2K1000 CPUs have 64 interrupt sources as inputs, and
a route-mapped node handles up to 32 interrupt sources, so two liointc
nodes are defined in dts{i}.

Of course, we have to make sure that the routing outputs ("intx") of the
two nodes do not conflict, i.e. "int0" can only be used as a routing
output for one of them. Therefore, "interrupt-names" should be defined
as "pattern".

In addition, since "interrupt-names" and "interrupts" are one-to-one
correspondence, we pass it to get the corresponding interrupt number in
the driver. Setting it to "required" does not break ABI, because it is
already logically represented as "required".

This fixes dtbs_check warning:

DTC_CHK arch/loongarch/boot/dts/loongson-2k0500-ref.dtb
arch/loongarch/boot/dts/loongson-2k0500-ref.dtb: interrupt-controller@1fe11440: interrupt-names:0: 'int0' was expected
        From schema: Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
arch/loongarch/boot/dts/loongson-2k0500-ref.dtb: interrupt-controller@1fe11440: Unevaluated properties are not allowed ('interrupt-names' was unexpected)
        From schema: Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
DTC_CHK arch/loongarch/boot/dts/loongson-2k1000-ref.dtb
arch/loongarch/boot/dts/loongson-2k1000-ref.dtb: interrupt-controller@1fe01440: interrupt-names:0: 'int0' was expected
        From schema: Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
arch/loongarch/boot/dts/loongson-2k1000-ref.dtb: interrupt-controller@1fe01440: Unevaluated properties are not allowed ('interrupt-names' was unexpected)
        From schema: Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml

Acked-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../bindings/interrupt-controller/loongson,liointc.yaml    | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
index a3276c1d9b59f..60441f0c5d721 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
@@ -51,11 +51,9 @@ properties:
   interrupt-names:
     description: List of names for the parent interrupts.
     items:
-      - const: int0
-      - const: int1
-      - const: int2
-      - const: int3
+      pattern: int[0-3]
     minItems: 1
+    maxItems: 4
 
   '#interrupt-cells':
     const: 2
@@ -75,6 +73,7 @@ required:
   - compatible
   - reg
   - interrupts
+  - interrupt-names
   - interrupt-controller
   - '#interrupt-cells'
   - loongson,parent_int_map
-- 
GitLab


From 5f346a6e5970229c19c059e8fa62c3dbdde56e7b Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:00 +0800
Subject: [PATCH 2810/4076] LoongArch: Allow device trees be built into the
 kernel

During the upstream progress of those DT-based drivers, DT properties
are changed a lot so very different from those in existing bootloaders.
It is inevitably that some existing systems do not provide a standard,
canonical device tree to the kernel at boot time. So let's provide a
device tree table in the kernel, keyed by the dts filename, containing
the relevant DTBs.

We can use the built-in dts files as references. Each SoC has only one
built-in dts file which describes all possible device information of
that SoC, so the dts files are good examples during development.

And as a reference, our built-in dts file only enables the most basic
bootable combinations (so it is generic enough), acts as an alternative
in case the dts in the bootloader is unexpected.

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kbuild            |  1 +
 arch/loongarch/Kconfig           | 18 ++++++++++++++++++
 arch/loongarch/Makefile          |  3 ++-
 arch/loongarch/boot/dts/Makefile |  3 +--
 arch/loongarch/kernel/setup.c    | 12 +++++++++---
 5 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild
index beb8499dd8ed8..bfa21465d83af 100644
--- a/arch/loongarch/Kbuild
+++ b/arch/loongarch/Kbuild
@@ -4,6 +4,7 @@ obj-y += net/
 obj-y += vdso/
 
 obj-$(CONFIG_KVM) += kvm/
+obj-$(CONFIG_BUILTIN_DTB) += boot/dts/
 
 # for cleaning
 subdir- += boot
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 6b9da3effdf8e..ede2ef26726a8 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -375,6 +375,24 @@ config CMDLINE_FORCE
 
 endchoice
 
+config BUILTIN_DTB
+	bool "Enable built-in dtb in kernel"
+	depends on OF
+	help
+	  Some existing systems do not provide a canonical device tree to
+	  the kernel at boot time. Let's provide a device tree table in the
+	  kernel, keyed by the dts filename, containing the relevant DTBs.
+
+	  Built-in DTBs are generic enough and can be used as references.
+
+config BUILTIN_DTB_NAME
+	string "Source file for built-in dtb"
+	depends on BUILTIN_DTB
+	help
+	  Base name (without suffix, relative to arch/loongarch/boot/dts/)
+	  for the DTS file that will be used to produce the DTB linked into
+	  the kernel.
+
 config DMI
 	bool "Enable DMI scanning"
 	select DMI_SCAN_MACHINE_NON_EFI_FALLBACK
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index ba45cb7b621cd..983aa2b1629a6 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -6,6 +6,7 @@
 boot	:= arch/loongarch/boot
 
 KBUILD_DEFCONFIG := loongson3_defconfig
+KBUILD_DTBS      := dtbs
 
 image-name-y			:= vmlinux
 image-name-$(CONFIG_EFI_ZBOOT)	:= vmlinuz
@@ -144,7 +145,7 @@ endif
 
 vdso-install-y += arch/loongarch/vdso/vdso.so.dbg
 
-all:	$(notdir $(KBUILD_IMAGE))
+all:	$(notdir $(KBUILD_IMAGE)) $(KBUILD_DTBS)
 
 vmlinuz.efi: vmlinux.efi
 
diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile
index 5f1f55e911adf..1e24cdb5180af 100644
--- a/arch/loongarch/boot/dts/Makefile
+++ b/arch/loongarch/boot/dts/Makefile
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
-dtstree	:= $(srctree)/$(src)
 
-dtb-y := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME))
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index d183a745fb85d..15d366b8407c3 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -295,8 +295,12 @@ static void __init fdt_setup(void)
 	if (acpi_os_get_root_pointer())
 		return;
 
-	/* Look for a device tree configuration table entry */
-	fdt_pointer = efi_fdt_pointer();
+	/* Prefer to use built-in dtb, checking its legality first. */
+	if (!fdt_check_header(__dtb_start))
+		fdt_pointer = __dtb_start;
+	else
+		fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */
+
 	if (!fdt_pointer || fdt_check_header(fdt_pointer))
 		return;
 
@@ -330,7 +334,9 @@ static void __init bootcmdline_init(char **cmdline_p)
 		if (boot_command_line[0])
 			strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
 
-		strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE);
+		if (!strstr(boot_command_line, init_command_line))
+			strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE);
+
 		goto out;
 	}
 #endif
-- 
GitLab


From 0f66569c85948c8b3c3edbe3e4ada6f98a4937ea Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:07 +0800
Subject: [PATCH 2811/4076] LoongArch: dts: DeviceTree for Loongson-2K0500

Add DeviceTree file for Loongson-2K0500 processor, which integrates one
64-bit 2-issue superscalar LA264 processor core.

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/boot/dts/Makefile              |   2 +
 .../boot/dts/loongson-2k0500-ref.dts          |  88 ++++++
 arch/loongarch/boot/dts/loongson-2k0500.dtsi  | 266 ++++++++++++++++++
 3 files changed, 356 insertions(+)
 create mode 100644 arch/loongarch/boot/dts/loongson-2k0500-ref.dts
 create mode 100644 arch/loongarch/boot/dts/loongson-2k0500.dtsi

diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile
index 1e24cdb5180af..89c9758bba7f1 100644
--- a/arch/loongarch/boot/dts/Makefile
+++ b/arch/loongarch/boot/dts/Makefile
@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+dtb-y = loongson-2k0500-ref.dtb
+
 obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME))
diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
new file mode 100644
index 0000000000000..b38071a4d0b02
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k0500.dtsi"
+
+/ {
+	compatible = "loongson,ls2k0500-ref", "loongson,ls2k0500";
+	model = "Loongson-2K0500 Reference Board";
+
+	aliases {
+		ethernet0 = &gmac0;
+		ethernet1 = &gmac1;
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@200000 {
+		device_type = "memory";
+		reg = <0x0 0x00200000 0x0 0x0ee00000>,
+		      <0x0 0x90000000 0x0 0x60000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0x0 0x2000000>;
+			linux,cma-default;
+		};
+	};
+};
+
+&gmac0 {
+	status = "okay";
+
+	phy-mode = "rgmii";
+	bus_id = <0x0>;
+};
+
+&gmac1 {
+	status = "okay";
+
+	phy-mode = "rgmii";
+	bus_id = <0x1>;
+};
+
+&i2c0 {
+	status = "okay";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+	eeprom@57{
+		compatible = "atmel,24c16";
+		reg = <0x57>;
+		pagesize = <16>;
+	};
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&sata {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&rtc0 {
+	status = "okay";
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi
new file mode 100644
index 0000000000000..444779c21034b
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "loongson,la264";
+			device_type = "cpu";
+			reg = <0x0>;
+			clocks = <&cpu_clk>;
+		};
+	};
+
+	cpu_clk: cpu-clk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <500000000>;
+	};
+
+	cpuintc: interrupt-controller {
+		compatible = "loongson,cpu-interrupt-controller";
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
+	bus@10000000 {
+		compatible = "simple-bus";
+		ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+			 <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+			 <0x0 0x20000000 0x0 0x20000000 0x0 0x10000000>,
+			 <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+			 <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		isa@16400000 {
+			compatible = "isa";
+			#size-cells = <1>;
+			#address-cells = <2>;
+			ranges = <1 0x0 0x0 0x16400000 0x4000>;
+		};
+
+		liointc0: interrupt-controller@1fe11400 {
+			compatible = "loongson,liointc-2.0";
+			reg = <0x0 0x1fe11400 0x0 0x40>,
+			      <0x0 0x1fe11040 0x0 0x8>;
+			reg-names = "main", "isr0";
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <2>;
+			interrupt-names = "int0";
+
+			loongson,parent_int_map = <0xffffffff>, /* int0 */
+						  <0x00000000>, /* int1 */
+						  <0x00000000>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		liointc1: interrupt-controller@1fe11440 {
+			compatible = "loongson,liointc-2.0";
+			reg = <0x0 0x1fe11440 0x0 0x40>,
+			      <0x0 0x1fe11048 0x0 0x8>;
+			reg-names = "main", "isr0";
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <4>;
+			interrupt-names = "int2";
+
+			loongson,parent_int_map = <0x00000000>, /* int0 */
+						  <0x00000000>, /* int1 */
+						  <0xffffffff>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		eiointc: interrupt-controller@1fe11600 {
+			compatible = "loongson,ls2k0500-eiointc";
+			reg = <0x0 0x1fe11600 0x0 0xea00>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <3>;
+		};
+
+		gmac0: ethernet@1f020000 {
+			compatible = "snps,dwmac-3.70a";
+			reg = <0x0 0x1f020000 0x0 0x10000>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq";
+			status = "disabled";
+		};
+
+		gmac1: ethernet@1f030000 {
+			compatible = "snps,dwmac-3.70a";
+			reg = <0x0 0x1f030000 0x0 0x10000>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq";
+			status = "disabled";
+		};
+
+		sata: sata@1f040000 {
+			compatible = "snps,spear-ahci";
+			reg = <0x0 0x1f040000 0x0 0x10000>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <75>;
+			status = "disabled";
+		};
+
+		ehci0: usb@1f050000 {
+			compatible = "generic-ehci";
+			reg = <0x0 0x1f050000 0x0 0x8000>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <71>;
+			status = "disabled";
+		};
+
+		ohci0: usb@1f058000 {
+			compatible = "generic-ohci";
+			reg = <0x0 0x1f058000 0x0 0x8000>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <72>;
+			status = "disabled";
+		};
+
+		uart0: serial@1ff40800 {
+			compatible = "ns16550a";
+			reg = <0x0 0x1ff40800 0x0 0x10>;
+			clock-frequency = <100000000>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <2>;
+			no-loopback-test;
+			status = "disabled";
+		};
+
+		i2c0: i2c@1ff48000 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff48000 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <14>;
+			status = "disabled";
+		};
+
+		i2c@1ff48800 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff48800 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <15>;
+			status = "disabled";
+		};
+
+		i2c@1ff49000 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff49000 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <16>;
+			status = "disabled";
+		};
+
+		i2c@1ff49800 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff49800 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <17>;
+			status = "disabled";
+		};
+
+		i2c@1ff4a000 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff4a000 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <18>;
+			status = "disabled";
+		};
+
+		i2c@1ff4a800 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1ff4a800 0x0 0x0800>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <19>;
+			status = "disabled";
+		};
+
+		pmc: power-management@1ff6c000 {
+			compatible = "loongson,ls2k0500-pmc", "syscon";
+			reg = <0x0 0x1ff6c000 0x0 0x58>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <56>;
+			loongson,suspend-address = <0x0 0x1c000500>;
+
+			syscon-reboot {
+				compatible = "syscon-reboot";
+				offset = <0x30>;
+				mask = <0x1>;
+			};
+
+			syscon-poweroff {
+				compatible = "syscon-poweroff";
+				regmap = <&pmc>;
+				offset = <0x14>;
+				mask = <0x3c00>;
+				value = <0x3c00>;
+			};
+		};
+
+		rtc0: rtc@1ff6c100 {
+			compatible = "loongson,ls2k0500-rtc", "loongson,ls7a-rtc";
+			reg = <0x0 0x1ff6c100 0x0 0x100>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <35>;
+			status = "disabled";
+		};
+
+		pcie@1a000000 {
+			compatible = "loongson,ls2k-pci";
+			reg = <0x0 0x1a000000 0x0 0x02000000>,
+			      <0xfe 0x0 0x0 0x20000000>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			device_type = "pci";
+			bus-range = <0x0 0x5>;
+			ranges = <0x01000000 0x0 0x00004000 0x0 0x16404000 0x0 0x00004000>,
+				 <0x02000000 0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>;
+
+			pcie@0,0 {
+				reg = <0x0000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&eiointc>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &eiointc 81>;
+				ranges;
+			};
+
+			pcie@1,0 {
+				reg = <0x0800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&eiointc>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &eiointc 82>;
+				ranges;
+			};
+		};
+	};
+};
-- 
GitLab


From 30a5532a32066233a2e9a4751989276e91c82210 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2812/4076] LoongArch: dts: DeviceTree for Loongson-2K1000

Add DeviceTree file for Loongson-2K1000 processor, which integrates two
64-bit 2-issue superscalar LA264 processor cores.

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/boot/dts/Makefile              |   2 +-
 .../boot/dts/loongson-2k1000-ref.dts          | 183 +++++++
 arch/loongarch/boot/dts/loongson-2k1000.dtsi  | 492 ++++++++++++++++++
 3 files changed, 676 insertions(+), 1 deletion(-)
 create mode 100644 arch/loongarch/boot/dts/loongson-2k1000-ref.dts
 create mode 100644 arch/loongarch/boot/dts/loongson-2k1000.dtsi

diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile
index 89c9758bba7f1..cfb0a122d91c1 100644
--- a/arch/loongarch/boot/dts/Makefile
+++ b/arch/loongarch/boot/dts/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-dtb-y = loongson-2k0500-ref.dtb
+dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb
 
 obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME))
diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
new file mode 100644
index 0000000000000..132a2d1ea8bce
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k1000.dtsi"
+
+/ {
+	compatible = "loongson,ls2k1000-ref", "loongson,ls2k1000";
+	model = "Loongson-2K1000 Reference Board";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@200000 {
+		device_type = "memory";
+		reg = <0x0 0x00200000 0x0 0x06e00000>,
+		      <0x0 0x08000000 0x0 0x07000000>,
+		      <0x0 0x90000000 0x1 0xe0000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0x0 0x2000000>;
+			linux,cma-default;
+		};
+	};
+};
+
+&gmac0 {
+	status = "okay";
+
+	phy-mode = "rgmii";
+	phy-handle = <&phy0>;
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy0: ethernet-phy@0 {
+			reg = <0>;
+		};
+	};
+};
+
+&gmac1 {
+	status = "okay";
+
+	phy-mode = "rgmii";
+	phy-handle = <&phy1>;
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy1: ethernet-phy@1 {
+			reg = <16>;
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	pinctrl-0 = <&i2c0_pins_default>;
+	pinctrl-names = "default";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+	eeprom@57{
+		compatible = "atmel,24c16";
+		reg = <0x57>;
+		pagesize = <16>;
+	};
+};
+
+&spi0 {
+	status = "okay";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+	spidev@0 {
+		compatible = "rohm,dh2228fv";
+		spi-max-frequency = <100000000>;
+		reg = <0>;
+	};
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&sata {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&clk {
+	status = "okay";
+};
+
+&rtc0 {
+	status = "okay";
+};
+
+&pctrl {
+	status = "okay";
+
+	sdio_pins_default: sdio-pins {
+		sdio-pinmux {
+			groups = "sdio";
+			function = "sdio";
+		};
+		sdio-det-pinmux {
+			groups = "pwm2";
+			function = "gpio";
+		};
+	};
+
+	pwm1_pins_default: pwm1-pins {
+		pinmux {
+			groups = "pwm1";
+			function = "pwm1";
+		};
+	};
+
+	pwm0_pins_default: pwm0-pins {
+		pinmux {
+			groups = "pwm0";
+			function = "pwm0";
+		};
+	};
+
+	i2c1_pins_default: i2c1-pins {
+		pinmux {
+			groups = "i2c1";
+			function = "i2c1";
+		};
+	};
+
+	i2c0_pins_default: i2c0-pins {
+		pinmux {
+			groups = "i2c0";
+			function = "i2c0";
+		};
+	};
+
+	nand_pins_default: nand-pins {
+		pinmux {
+			groups = "nand";
+			function = "nand";
+		};
+	};
+
+	hda_pins_default: hda-pins {
+		grp0-pinmux {
+			groups = "hda";
+			function = "hda";
+		};
+		grp1-pinmux {
+			groups = "i2s";
+			function = "gpio";
+		};
+	};
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
new file mode 100644
index 0000000000000..49a70f8c3cab2
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
@@ -0,0 +1,492 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/clock/loongson,ls2k-clk.h>
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "loongson,la264";
+			device_type = "cpu";
+			reg= <0x0>;
+			clocks = <&clk LOONGSON2_NODE_CLK>;
+		};
+
+		cpu1: cpu@1 {
+			compatible = "loongson,la264";
+			device_type = "cpu";
+			reg = <0x1>;
+			clocks = <&clk LOONGSON2_NODE_CLK>;
+		};
+	};
+
+	ref_100m: clock-ref-100m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+		clock-output-names = "ref_100m";
+	};
+
+	cpuintc: interrupt-controller {
+		compatible = "loongson,cpu-interrupt-controller";
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
+	/* i2c of the dvi eeprom edid */
+	i2c-gpio-0 {
+		compatible = "i2c-gpio";
+		scl-gpios = <&gpio0 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		sda-gpios = <&gpio0 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		i2c-gpio,delay-us = <5>;        /* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	/* i2c of the eeprom edid */
+	i2c-gpio-1 {
+		compatible = "i2c-gpio";
+		scl-gpios = <&gpio0 33 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		sda-gpios = <&gpio0 32 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		i2c-gpio,delay-us = <5>;        /* ~100 kHz */
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	thermal-zones {
+		cpu-thermal {
+			polling-delay-passive = <1000>;
+			polling-delay = <5000>;
+			thermal-sensors = <&tsensor 0>;
+
+			trips {
+				cpu_alert: cpu-alert {
+					temperature = <33000>;
+					hysteresis = <2000>;
+					type = "active";
+				};
+
+				cpu_crit: cpu-crit {
+					temperature = <85000>;
+					hysteresis = <5000>;
+					type = "critical";
+				};
+			};
+		};
+	};
+
+	bus@10000000 {
+		compatible = "simple-bus";
+		ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+			 <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+			 <0x0 0x20000000 0x0 0x20000000 0x0 0x10000000>,
+			 <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+			 <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dma-coherent;
+
+		liointc0: interrupt-controller@1fe01400 {
+			compatible = "loongson,liointc-2.0";
+			reg = <0x0 0x1fe01400 0x0 0x40>,
+			      <0x0 0x1fe01040 0x0 0x8>,
+			      <0x0 0x1fe01140 0x0 0x8>;
+			reg-names = "main", "isr0", "isr1";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <2>;
+			interrupt-names = "int0";
+			loongson,parent_int_map = <0xffffffff>, /* int0 */
+						  <0x00000000>, /* int1 */
+						  <0x00000000>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		liointc1: interrupt-controller@1fe01440 {
+			compatible = "loongson,liointc-2.0";
+			reg = <0x0 0x1fe01440 0x0 0x40>,
+			      <0x0 0x1fe01048 0x0 0x8>,
+			      <0x0 0x1fe01148 0x0 0x8>;
+			reg-names = "main", "isr0", "isr1";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <3>;
+			interrupt-names = "int1";
+			loongson,parent_int_map = <0x00000000>, /* int0 */
+						  <0xffffffff>, /* int1 */
+						  <0x00000000>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		chipid@1fe00000 {
+			compatible = "loongson,ls2k-chipid";
+			reg = <0x0 0x1fe00000 0x0 0x30>;
+			little-endian;
+		};
+
+		pctrl: pinctrl@1fe00420 {
+			compatible = "loongson,ls2k-pinctrl";
+			reg = <0x0 0x1fe00420 0x0 0x18>;
+			status = "disabled";
+		};
+
+		clk: clock-controller@1fe00480 {
+			compatible = "loongson,ls2k-clk";
+			reg = <0x0 0x1fe00480 0x0 0x58>;
+			#clock-cells = <1>;
+			clocks = <&ref_100m>;
+			clock-names = "ref_100m";
+			status = "disabled";
+		};
+
+		gpio0: gpio@1fe00500 {
+			compatible = "loongson,ls2k-gpio";
+			reg = <0x0 0x1fe00500 0x0 0x38>;
+			ngpios = <64>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pctrl 0x0 0x0 15>,
+				      <&pctrl 16 16 15>,
+				      <&pctrl 32 32 10>,
+				      <&pctrl 44 44 20>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <28 IRQ_TYPE_LEVEL_HIGH>,
+				     <29 IRQ_TYPE_LEVEL_HIGH>,
+				     <30 IRQ_TYPE_LEVEL_HIGH>,
+				     <30 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <26 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <>,
+				     <>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>,
+				     <27 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		tsensor: thermal-sensor@1fe01500 {
+			compatible = "loongson,ls2k1000-thermal";
+			reg = <0x0 0x1fe01500 0x0 0x30>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <7 IRQ_TYPE_LEVEL_HIGH>;
+			#thermal-sensor-cells = <1>;
+		};
+
+		dma-controller@1fe00c00 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c00 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		dma-controller@1fe00c10 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c10 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <13 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		dma-controller@1fe00c20 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c20 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		dma-controller@1fe00c30 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c30 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <15 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		dma-controller@1fe00c40 {
+			compatible = "loongson,ls2k1000-apbdma";
+			reg = <0x0 0x1fe00c40 0x0 0x8>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <16 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
+			#dma-cells = <1>;
+			status = "disabled";
+		};
+
+		uart0: serial@1fe20000 {
+			compatible = "ns16550a";
+			reg = <0x0 0x1fe20000 0x0 0x10>;
+			clock-frequency = <125000000>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <0x0 IRQ_TYPE_LEVEL_HIGH>;
+			no-loopback-test;
+			status = "disabled";
+		};
+
+		i2c2: i2c@1fe21000 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1fe21000 0x0 0x8>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		i2c3: i2c@1fe21800 {
+			compatible = "loongson,ls2k-i2c";
+			reg = <0x0 0x1fe21800 0x0 0x8>;
+			interrupt-parent = <&liointc0>;
+			interrupts = <23 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		pmc: power-management@1fe27000 {
+			compatible = "loongson,ls2k1000-pmc", "loongson,ls2k0500-pmc", "syscon";
+			reg = <0x0 0x1fe27000 0x0 0x58>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+			loongson,suspend-address = <0x0 0x1c000500>;
+
+			syscon-reboot {
+				compatible = "syscon-reboot";
+				offset = <0x30>;
+				mask = <0x1>;
+			};
+
+			syscon-poweroff {
+				compatible = "syscon-poweroff";
+				regmap = <&pmc>;
+				offset = <0x14>;
+				mask = <0x3c00>;
+				value = <0x3c00>;
+			};
+		};
+
+		rtc0: rtc@1fe27800 {
+			compatible = "loongson,ls2k1000-rtc";
+			reg = <0x0 0x1fe27800 0x0 0x100>;
+			interrupt-parent = <&liointc1>;
+			interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		spi0: spi@1fff0220 {
+			compatible = "loongson,ls2k1000-spi";
+			reg = <0x0 0x1fff0220 0x0 0x10>;
+			clocks = <&clk LOONGSON2_BOOT_CLK>;
+			status = "disabled";
+		};
+
+		pcie@1a000000 {
+			compatible = "loongson,ls2k-pci";
+			reg = <0x0 0x1a000000 0x0 0x02000000>,
+			      <0xfe 0x0 0x0 0x20000000>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			device_type = "pci";
+			bus-range = <0x0 0xff>;
+			ranges = <0x01000000 0x0 0x00008000 0x0 0x18008000 0x0 0x00008000>,
+				 <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>;
+
+			gmac0: ethernet@3,0 {
+				reg = <0x1800 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
+					     <13 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "macirq", "eth_lpi";
+				status = "disabled";
+			};
+
+			gmac1: ethernet@3,1 {
+				reg = <0x1900 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
+					     <15 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "macirq", "eth_lpi";
+				status = "disabled";
+			};
+
+			ehci0: usb@4,1 {
+				reg = <0x2100 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc1>;
+				interrupts = <18 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			ohci0: usb@4,2 {
+				reg = <0x2200 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc1>;
+				interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			display@6,0 {
+				reg = <0x3000 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <28 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			hda@7,0 {
+				reg = <0x3800 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <4 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			sata: sata@8,0 {
+				reg = <0x4000 0x0 0x0 0x0 0x0>;
+				interrupt-parent = <&liointc0>;
+				interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+			};
+
+			pcie@9,0 {
+				reg = <0x4800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 0x0 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@a,0 {
+				reg = <0x5000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 1 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@b,0 {
+				reg = <0x5800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 2 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@c,0 {
+				reg = <0x6000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 3 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@d,0 {
+				reg = <0x6800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 4 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@e,0 {
+				reg = <0x7000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&liointc1>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &liointc1 5 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+		};
+	};
+};
-- 
GitLab


From 2905844f682808275ea5daf6f5b668fbfe547363 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2813/4076] LoongArch: dts: DeviceTree for Loongson-2K2000

Add DeviceTree file for Loongson-2K2000 processor, which integrates two
64-bit 3-issue superscalar LA364 processor cores.

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/boot/dts/Makefile              |   2 +-
 .../boot/dts/loongson-2k2000-ref.dts          |  72 +++++
 arch/loongarch/boot/dts/loongson-2k2000.dtsi  | 300 ++++++++++++++++++
 3 files changed, 373 insertions(+), 1 deletion(-)
 create mode 100644 arch/loongarch/boot/dts/loongson-2k2000-ref.dts
 create mode 100644 arch/loongarch/boot/dts/loongson-2k2000.dtsi

diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile
index cfb0a122d91c1..747d0c3f63892 100644
--- a/arch/loongarch/boot/dts/Makefile
+++ b/arch/loongarch/boot/dts/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb
+dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb loongson-2k2000-ref.dtb
 
 obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME))
diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
new file mode 100644
index 0000000000000..dca91caf895e3
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include "loongson-2k2000.dtsi"
+
+/ {
+	compatible = "loongson,ls2k2000-ref", "loongson,ls2k2000";
+	model = "Loongson-2K2000 Reference Board";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@200000 {
+		device_type = "memory";
+		reg = <0x0 0x00200000 0x0 0x0ee00000>,
+		      <0x0 0x90000000 0x0 0x70000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0x0 0x2000000>;
+			linux,cma-default;
+		};
+	};
+};
+
+&sata {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&rtc0 {
+	status = "okay";
+};
+
+&xhci0 {
+	status = "okay";
+};
+
+&xhci1 {
+	status = "okay";
+};
+
+&gmac0 {
+	status = "okay";
+};
+
+&gmac1 {
+	status = "okay";
+};
+
+&gmac2 {
+	status = "okay";
+};
diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
new file mode 100644
index 0000000000000..a231949b5f553
--- /dev/null
+++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
@@ -0,0 +1,300 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@1 {
+			compatible = "loongson,la364";
+			device_type = "cpu";
+			reg = <0x0>;
+			clocks = <&cpu_clk>;
+		};
+
+		cpu1: cpu@2 {
+			compatible = "loongson,la364";
+			device_type = "cpu";
+			reg = <0x1>;
+			clocks = <&cpu_clk>;
+		};
+	};
+
+	cpu_clk: cpu-clk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <1400000000>;
+	};
+
+	cpuintc: interrupt-controller {
+		compatible = "loongson,cpu-interrupt-controller";
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
+	bus@10000000 {
+		compatible = "simple-bus";
+		ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>,
+			 <0x0 0x02000000 0x0 0x02000000 0x0 0x02000000>,
+			 <0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>,
+			 <0xfe 0x0 0xfe 0x0 0x0 0x40000000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		pmc: power-management@100d0000 {
+			compatible = "loongson,ls2k2000-pmc", "loongson,ls2k0500-pmc", "syscon";
+			reg = <0x0 0x100d0000 0x0 0x58>;
+			interrupt-parent = <&eiointc>;
+			interrupts = <47>;
+			loongson,suspend-address = <0x0 0x1c000500>;
+
+			syscon-reboot {
+				compatible = "syscon-reboot";
+				offset = <0x30>;
+				mask = <0x1>;
+			};
+
+			syscon-poweroff {
+				compatible = "syscon-poweroff";
+				regmap = <&pmc>;
+				offset = <0x14>;
+				mask = <0x3c00>;
+				value = <0x3c00>;
+			};
+		};
+
+		liointc: interrupt-controller@1fe01400 {
+			compatible = "loongson,liointc-1.0";
+			reg = <0x0 0x1fe01400 0x0 0x64>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <2>;
+			interrupt-names = "int0";
+			loongson,parent_int_map = <0xffffffff>, /* int0 */
+						  <0x00000000>, /* int1 */
+						  <0x00000000>, /* int2 */
+						  <0x00000000>; /* int3 */
+		};
+
+		eiointc: interrupt-controller@1fe01600 {
+			compatible = "loongson,ls2k2000-eiointc";
+			reg = <0x0 0x1fe01600 0x0 0xea00>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&cpuintc>;
+			interrupts = <3>;
+		};
+
+		pic: interrupt-controller@10000000 {
+			compatible = "loongson,pch-pic-1.0";
+			reg = <0x0 0x10000000 0x0 0x400>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			loongson,pic-base-vec = <0>;
+			interrupt-parent = <&eiointc>;
+		};
+
+		msi: msi-controller@1fe01140 {
+			compatible = "loongson,pch-msi-1.0";
+			reg = <0x0 0x1fe01140 0x0 0x8>;
+			msi-controller;
+			loongson,msi-base-vec = <64>;
+			loongson,msi-num-vecs = <192>;
+			interrupt-parent = <&eiointc>;
+		};
+
+		rtc0: rtc@100d0100 {
+			compatible = "loongson,ls2k2000-rtc", "loongson,ls7a-rtc";
+			reg = <0x0 0x100d0100 0x0 0x100>;
+			interrupt-parent = <&pic>;
+			interrupts = <52 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		uart0: serial@1fe001e0 {
+			compatible = "ns16550a";
+			reg = <0x0 0x1fe001e0 0x0 0x10>;
+			clock-frequency = <100000000>;
+			interrupt-parent = <&liointc>;
+			interrupts = <10 IRQ_TYPE_LEVEL_HIGH>;
+			no-loopback-test;
+			status = "disabled";
+		};
+
+		pcie@1a000000 {
+			compatible = "loongson,ls2k-pci";
+			reg = <0x0 0x1a000000 0x0 0x02000000>,
+			      <0xfe 0x0 0x0 0x20000000>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			device_type = "pci";
+			bus-range = <0x0 0xff>;
+			ranges = <0x01000000 0x0 0x00008000 0x0 0x18400000 0x0 0x00008000>,
+				 <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>;
+
+			gmac0: ethernet@3,0 {
+				reg = <0x1800 0x0 0x0 0x0 0x0>;
+				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			gmac1: ethernet@3,1 {
+				reg = <0x1900 0x0 0x0 0x0 0x0>;
+				interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			gmac2: ethernet@3,2 {
+				reg = <0x1a00 0x0 0x0 0x0 0x0>;
+				interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			xhci0: usb@4,0 {
+				reg = <0x2000 0x0 0x0 0x0 0x0>;
+				interrupts = <48 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			xhci1: usb@19,0 {
+				reg = <0xc800 0x0 0x0 0x0 0x0>;
+				interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			display@6,1 {
+				reg = <0x3100 0x0 0x0 0x0 0x0>;
+				interrupts = <28 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			hda@7,0 {
+				reg = <0x3800 0x0 0x0 0x0 0x0>;
+				interrupts = <58 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			sata: sata@8,0 {
+				reg = <0x4000 0x0 0x0 0x0 0x0>;
+				interrupts = <16 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-parent = <&pic>;
+				status = "disabled";
+			};
+
+			pcie@9,0 {
+				reg = <0x4800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 32 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@a,0 {
+				reg = <0x5000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 33 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@b,0 {
+				reg = <0x5800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 34 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@c,0 {
+				reg = <0x6000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 35 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@d,0 {
+				reg = <0x6800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 36 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@e,0 {
+				reg = <0x7000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 37 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@f,0 {
+				reg = <0x7800 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 40 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+
+			pcie@10,0 {
+				reg = <0x8000 0x0 0x0 0x0 0x0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				device_type = "pci";
+				interrupt-parent = <&pic>;
+				#interrupt-cells = <1>;
+				interrupt-map-mask = <0x0 0x0 0x0 0x0>;
+				interrupt-map = <0x0 0x0 0x0 0x0 &pic 30 IRQ_TYPE_LEVEL_HIGH>;
+				ranges;
+			};
+		};
+	};
+};
-- 
GitLab


From 44a01f1f726ab1d2050fb741eca4fabfa3cab799 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2814/4076] LoongArch: Parsing CPU-related information from DTS

Generally, we can get cpu-related information, such as model name, from
/proc/cpuinfo. For FDT-based systems, we need to parse the relevant
information from DTS.

BTW, set loongson_sysconf.cores_per_package to num_processors if SMBIOS
doesn't provide a valid number (usually FDT-based systems).

Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Hongliang Wang <wanghongliang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/env.c | 34 +++++++++++++++++++++++++++++++++-
 arch/loongarch/kernel/smp.c |  3 +++
 2 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 6b3bfb0092e60..2f1f5b08638f8 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -5,13 +5,16 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/acpi.h>
+#include <linux/clk.h>
 #include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/memblock.h>
+#include <linux/of_clk.h>
 #include <asm/early_ioremap.h>
 #include <asm/bootinfo.h>
 #include <asm/loongson.h>
 #include <asm/setup.h>
+#include <asm/time.h>
 
 u64 efi_system_table;
 struct loongson_system_configuration loongson_sysconf;
@@ -36,7 +39,16 @@ void __init init_environ(void)
 
 static int __init init_cpu_fullname(void)
 {
-	int cpu;
+	struct device_node *root;
+	int cpu, ret;
+	char *model;
+
+	/* Parsing cpuname from DTS model property */
+	root = of_find_node_by_path("/");
+	ret = of_property_read_string(root, "model", (const char **)&model);
+	of_node_put(root);
+	if (ret == 0)
+		loongson_sysconf.cpuname = strsep(&model, " ");
 
 	if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) {
 		for (cpu = 0; cpu < NR_CPUS; cpu++)
@@ -46,6 +58,26 @@ static int __init init_cpu_fullname(void)
 }
 arch_initcall(init_cpu_fullname);
 
+static int __init fdt_cpu_clk_init(void)
+{
+	struct clk *clk;
+	struct device_node *np;
+
+	np = of_get_cpu_node(0, NULL);
+	if (!np)
+		return -ENODEV;
+
+	clk = of_clk_get(np, 0);
+	if (IS_ERR(clk))
+		return -ENODEV;
+
+	cpu_clock_freq = clk_get_rate(clk);
+	clk_put(clk);
+
+	return 0;
+}
+late_initcall(fdt_cpu_clk_init);
+
 static ssize_t boardinfo_show(struct kobject *kobj,
 			      struct kobj_attribute *attr, char *buf)
 {
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 5bca12d16e069..9e33b5e361225 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -216,6 +216,9 @@ void __init loongson_smp_setup(void)
 {
 	fdt_smp_setup();
 
+	if (loongson_sysconf.cores_per_package == 0)
+		loongson_sysconf.cores_per_package = num_processors;
+
 	cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package;
 	cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package;
 
-- 
GitLab


From 9499daeade0edcbd3d5d20ffdd642a8e3a194b1f Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2815/4076] LoongArch: Add a missing call to efi_esrt_init()

ESRT (EFI System Resource Table) is needed for UEFI's "Capsule Update"
feature. But ESRT initialization is missing on LoongArch now, so add a
call to efi_esrt_init() at the end of efi_init().

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/efi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c
index acb5d3385675c..000825406c1f6 100644
--- a/arch/loongarch/kernel/efi.c
+++ b/arch/loongarch/kernel/efi.c
@@ -140,4 +140,6 @@ void __init efi_init(void)
 
 		early_memunmap(tbl, sizeof(*tbl));
 	}
+
+	efi_esrt_init();
 }
-- 
GitLab


From d23b77953f5a4fbf94c05157b186aac2a247ae32 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2816/4076] LoongArch: Change SHMLBA from SZ_64K to PAGE_SIZE

LoongArch has hardware page coloring for L1 Cache, so we don't have
cache aliases. But SFB (Store Fill Buffer) still has aliases. So we
define SHMLBA to SZ_64K previously. But there are losts of applications
use PAGE_SIZE rather than SHMLBA to mmap() file pages and shared pages.
Of course we can fix them one by one, but not easy.

On the other hand, we can simply disable SFB for 4KB page size to fix
cache alias (there will be performance decrease, but acceptable), and
in future we will fix SFB in hardware. So we can safely define SHMLBA to
PAGE_SIZE (use the generic shmparam.h) to make life easier.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/shmparam.h | 12 ------------
 arch/loongarch/kernel/head.S          | 10 ++++++++++
 2 files changed, 10 insertions(+), 12 deletions(-)
 delete mode 100644 arch/loongarch/include/asm/shmparam.h

diff --git a/arch/loongarch/include/asm/shmparam.h b/arch/loongarch/include/asm/shmparam.h
deleted file mode 100644
index c9554f48d2dfa..0000000000000
--- a/arch/loongarch/include/asm/shmparam.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#ifndef _ASM_SHMPARAM_H
-#define _ASM_SHMPARAM_H
-
-#define __ARCH_FORCE_SHMLBA	1
-
-#define	SHMLBA	SZ_64K		 /* attach addr a multiple of this */
-
-#endif /* _ASM_SHMPARAM_H */
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 53b883db07862..be187e99d3587 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -75,6 +75,11 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	la.pcrel	t0, fw_arg2
 	st.d		a2, t0, 0
 
+#ifdef CONFIG_PAGE_SIZE_4KB
+	li.d		t0, 0
+	li.d		t1, CSR_STFILL
+	csrxchg		t0, t1, LOONGARCH_CSR_IMPCTL1
+#endif
 	/* KSave3 used for percpu base, initialized as 0 */
 	csrwr		zero, PERCPU_BASE_KS
 	/* GPR21 used for percpu base (runtime), initialized as 0 */
@@ -127,6 +132,11 @@ SYM_CODE_START(smpboot_entry)
 
 	JUMP_VIRT_ADDR	t0, t1
 
+#ifdef CONFIG_PAGE_SIZE_4KB
+	li.d		t0, 0
+	li.d		t1, CSR_STFILL
+	csrxchg		t0, t1, LOONGARCH_CSR_IMPCTL1
+#endif
 	/* Enable PG */
 	li.w		t0, 0xb0		# PLV=0, IE=0, PG=1
 	csrwr		t0, LOONGARCH_CSR_CRMD
-- 
GitLab


From ce68ff3528e6eff4a1a4770600ec6c66779ba7b9 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2817/4076] LoongArch: Let cores_io_master cover the largest
 NR_CPUS

Now loongson_system_configuration::cores_io_master only covers 64 cpus,
if NR_CPUS > 64 there will be memory corruption. So let cores_io_master
cover the largest NR_CPUS (256).

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/bootinfo.h | 6 ++++--
 arch/loongarch/kernel/acpi.c          | 2 +-
 arch/loongarch/kernel/smp.c           | 2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h
index c60796869b2b8..6d5846dd075cb 100644
--- a/arch/loongarch/include/asm/bootinfo.h
+++ b/arch/loongarch/include/asm/bootinfo.h
@@ -24,13 +24,15 @@ struct loongson_board_info {
 	const char *board_vendor;
 };
 
+#define NR_WORDS DIV_ROUND_UP(NR_CPUS, BITS_PER_LONG)
+
 struct loongson_system_configuration {
 	int nr_cpus;
 	int nr_nodes;
 	int boot_cpu_id;
 	int cores_per_node;
 	int cores_per_package;
-	unsigned long cores_io_master;
+	unsigned long cores_io_master[NR_WORDS];
 	unsigned long suspend_addr;
 	const char *cpuname;
 };
@@ -42,7 +44,7 @@ extern struct loongson_system_configuration loongson_sysconf;
 
 static inline bool io_master(int cpu)
 {
-	return test_bit(cpu, &loongson_sysconf.cores_io_master);
+	return test_bit(cpu, loongson_sysconf.cores_io_master);
 }
 
 #endif /* _ASM_BOOTINFO_H */
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 8e00a754e5489..b6b097bbf8668 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -119,7 +119,7 @@ acpi_parse_eio_master(union acpi_subtable_headers *header, const unsigned long e
 		return -EINVAL;
 
 	core = eiointc->node * CORES_PER_EIO_NODE;
-	set_bit(core, &(loongson_sysconf.cores_io_master));
+	set_bit(core, loongson_sysconf.cores_io_master);
 
 	return 0;
 }
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 9e33b5e361225..a16e3dbe9f09e 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -208,7 +208,7 @@ static void __init fdt_smp_setup(void)
 	}
 
 	loongson_sysconf.nr_cpus = num_processors;
-	set_bit(0, &(loongson_sysconf.cores_io_master));
+	set_bit(0, loongson_sysconf.cores_io_master);
 #endif
 }
 
-- 
GitLab


From c2396651309eba291c15e32db8fbe44c738b5921 Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2818/4076] LoongArch: Fix and simplify fcsr initialization on
 execve()

There has been a lingering bug in LoongArch Linux systems causing some
GCC tests to intermittently fail (see Closes link).  I've made a minimal
reproducer:

    zsh% cat measure.s
    .align 4
    .globl _start
    _start:
        movfcsr2gr  $a0, $fcsr0
        bstrpick.w  $a0, $a0, 16, 16
        beqz        $a0, .ok
        break       0
    .ok:
        li.w        $a7, 93
        syscall     0
    zsh% cc mesaure.s -o measure -nostdlib
    zsh% echo $((1.0/3))
    0.33333333333333331
    zsh% while ./measure; do ; done

This while loop should not stop as POSIX is clear that execve must set
fenv to the default, where FCSR should be zero.  But in fact it will
just stop after running for a while (normally less than 30 seconds).
Note that "$((1.0/3))" is needed to reproduce this issue because it
raises FE_INVALID and makes fcsr0 non-zero.

The problem is we are currently relying on SET_PERSONALITY2() to reset
current->thread.fpu.fcsr.  But SET_PERSONALITY2() is executed before
start_thread which calls lose_fpu(0).  We can see if kernel preempt is
enabled, we may switch to another thread after SET_PERSONALITY2() but
before lose_fpu(0).  Then bad thing happens: during the thread switch
the value of the fcsr0 register is stored into current->thread.fpu.fcsr,
making it dirty again.

The issue can be fixed by setting current->thread.fpu.fcsr after
lose_fpu(0) because lose_fpu() clears TIF_USEDFPU, then the thread
switch won't touch current->thread.fpu.fcsr.

The only other architecture setting FCSR in SET_PERSONALITY2() is MIPS.
I've ran a similar test on MIPS with mainline kernel and it turns out
MIPS is buggy, too.  Anyway MIPS do this for supporting different FP
flavors (NaN encodings, etc.) which do not exist on LoongArch.  So for
LoongArch, we can simply remove the current->thread.fpu.fcsr setting
from SET_PERSONALITY2() and do it in start_thread(), after lose_fpu(0).

The while loop failing with the mainline kernel has survived one hour
after this change on LoongArch.

Fixes: 803b0fc5c3f2baa ("LoongArch: Add process management")
Closes: https://github.com/loongson-community/discussions/issues/7
Link: https://lore.kernel.org/linux-mips/7a6aa1bbdbbe2e63ae96ff163fab0349f58f1b9e.camel@xry111.site/
Cc: stable@vger.kernel.org
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/elf.h | 5 -----
 arch/loongarch/kernel/elf.c      | 5 -----
 arch/loongarch/kernel/process.c  | 1 +
 3 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index 9b16a3b8e7060..f16bd42456e4c 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -241,8 +241,6 @@ void loongarch_dump_regs64(u64 *uregs, const struct pt_regs *regs);
 do {									\
 	current->thread.vdso = &vdso_info;				\
 									\
-	loongarch_set_personality_fcsr(state);				\
-									\
 	if (personality(current->personality) != PER_LINUX)		\
 		set_personality(PER_LINUX);				\
 } while (0)
@@ -259,7 +257,6 @@ do {									\
 	clear_thread_flag(TIF_32BIT_ADDR);				\
 									\
 	current->thread.vdso = &vdso_info;				\
-	loongarch_set_personality_fcsr(state);				\
 									\
 	p = personality(current->personality);				\
 	if (p != PER_LINUX32 && p != PER_LINUX)				\
@@ -340,6 +337,4 @@ extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf,
 extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr,
 			  struct arch_elf_state *state);
 
-extern void loongarch_set_personality_fcsr(struct arch_elf_state *state);
-
 #endif /* _ASM_ELF_H */
diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c
index 183e94fc9c69c..0fa81ced28dcd 100644
--- a/arch/loongarch/kernel/elf.c
+++ b/arch/loongarch/kernel/elf.c
@@ -23,8 +23,3 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr,
 {
 	return 0;
 }
-
-void loongarch_set_personality_fcsr(struct arch_elf_state *state)
-{
-	current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0;
-}
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 767d94cce0de0..f2ff8b5d591e4 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -85,6 +85,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 	regs->csr_euen = euen;
 	lose_fpu(0);
 	lose_lbt(0);
+	current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0;
 
 	clear_thread_flag(TIF_LSX_CTX_LIVE);
 	clear_thread_flag(TIF_LASX_CTX_LIVE);
-- 
GitLab


From 78de91b45860da175bab73f4521d9ad875f3a7d4 Mon Sep 17 00:00:00 2001
From: Youling Tang <tangyouling@kylinos.cn>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2819/4076] LoongArch: Use generic interface to support
 crashkernel=X,[high,low]

LoongArch already supports two crashkernel regions in kexec-tools, so we
can directly use the common interface to support crashkernel=X,[high,low]
after commit 0ab97169aa0517079b ("crash_core: add generic function to do
reservation").

With the help of newly changed function parse_crashkernel() and generic
reserve_crashkernel_generic(), crashkernel reservation can be simplified
by steps:

1) Add a new header file <asm/crash_core.h>, then define CRASH_ALIGN,
   CRASH_ADDR_LOW_MAX and CRASH_ADDR_HIGH_MAX and in <asm/crash_core.h>;

2) Add arch_reserve_crashkernel() to call parse_crashkernel() and
   reserve_crashkernel_generic();

3) Add ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION Kconfig in
   arch/loongarch/Kconfig.

One can reserve the crash kernel from high memory above DMA zone range
by explicitly passing "crashkernel=X,high"; or reserve a memory range
below 4G with "crashkernel=X,low". Besides, there are few rules need to
take notice:

1) "crashkernel=X,[high,low]" will be ignored if "crashkernel=size" is
   specified.
2) "crashkernel=X,low" is valid only when "crashkernel=X,high" is passed
   and there is enough memory to be allocated under 4G.
3) When allocating crashkernel above 4G and no "crashkernel=X,low" is
   specified, a 128M low memory will be allocated automatically for
   swiotlb bounce buffer.
See Documentation/admin-guide/kernel-parameters.txt for more information.

Following test cases have been performed as expected:
1) crashkernel=256M                          //low=256M
2) crashkernel=1G                            //low=1G
3) crashkernel=4G                            //high=4G, low=128M(default)
4) crashkernel=4G crashkernel=256M,high      //high=4G, low=128M(default), high is ignored
5) crashkernel=4G crashkernel=256M,low       //high=4G, low=128M(default), low is ignored
6) crashkernel=4G,high                       //high=4G, low=128M(default)
7) crashkernel=256M,low                      //low=0M, invalid
8) crashkernel=4G,high crashkernel=256M,low  //high=4G, low=256M
9) crashkernel=4G,high crashkernel=4G,low    //high=0M, low=0M, invalid
10) crashkernel=512M@2560M                   //low=512M
11) crashkernel=1G,high crashkernel=0M,low   //high=1G, low=0M

Recommended usage in general:
1) In the case of small memory: crashkernel=512M
2) In the case of large memory: crashkernel=1024M,high crashkernel=128M,low

Signed-off-by: Youling Tang <tangyouling@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../admin-guide/kernel-parameters.txt         | 24 +++++-----
 arch/loongarch/Kconfig                        |  3 ++
 arch/loongarch/include/asm/crash_core.h       | 12 +++++
 arch/loongarch/kernel/setup.c                 | 44 +++++--------------
 4 files changed, 38 insertions(+), 45 deletions(-)
 create mode 100644 arch/loongarch/include/asm/crash_core.h

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 65731b060e3fe..f2633dd87a974 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -877,9 +877,9 @@
 			memory region [offset, offset + size] for that kernel
 			image. If '@offset' is omitted, then a suitable offset
 			is selected automatically.
-			[KNL, X86-64, ARM64, RISCV] Select a region under 4G first, and
-			fall back to reserve region above 4G when '@offset'
-			hasn't been specified.
+			[KNL, X86-64, ARM64, RISCV, LoongArch] Select a region
+			under 4G first, and fall back to reserve region above
+			4G when '@offset' hasn't been specified.
 			See Documentation/admin-guide/kdump/kdump.rst for further details.
 
 	crashkernel=range1:size1[,range2:size2,...][@offset]
@@ -890,25 +890,27 @@
 			Documentation/admin-guide/kdump/kdump.rst for an example.
 
 	crashkernel=size[KMG],high
-			[KNL, X86-64, ARM64, RISCV] range could be above 4G.
+			[KNL, X86-64, ARM64, RISCV, LoongArch] range could be
+			above 4G.
 			Allow kernel to allocate physical memory region from top,
 			so could be above 4G if system have more than 4G ram
 			installed. Otherwise memory region will be allocated
 			below 4G, if available.
 			It will be ignored if crashkernel=X is specified.
 	crashkernel=size[KMG],low
-			[KNL, X86-64, ARM64, RISCV] range under 4G. When crashkernel=X,high
-			is passed, kernel could allocate physical memory region
-			above 4G, that cause second kernel crash on system
-			that require some amount of low memory, e.g. swiotlb
-			requires at least 64M+32K low memory, also enough extra
-			low memory is needed to make sure DMA buffers for 32-bit
-			devices won't run out. Kernel would try to allocate
+			[KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G.
+			When crashkernel=X,high is passed, kernel could allocate
+			physical memory region above 4G, that cause second kernel
+			crash on system that require some amount of low memory,
+			e.g. swiotlb requires at least 64M+32K low memory, also
+			enough extra low memory is needed to make sure DMA buffers
+			for 32-bit devices won't run out. Kernel would try to allocate
 			default	size of memory below 4G automatically. The default
 			size is	platform dependent.
 			  --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
 			  --> arm64: 128MiB
 			  --> riscv: 128MiB
+			  --> loongarch: 128MiB
 			This one lets the user specify own low range under 4G
 			for second kernel instead.
 			0: to disable low allocation.
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index ede2ef26726a8..c997223beae00 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -594,6 +594,9 @@ config ARCH_SELECTS_CRASH_DUMP
 	depends on CRASH_DUMP
 	select RELOCATABLE
 
+config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+	def_bool CRASH_CORE
+
 config RELOCATABLE
 	bool "Relocatable kernel"
 	help
diff --git a/arch/loongarch/include/asm/crash_core.h b/arch/loongarch/include/asm/crash_core.h
new file mode 100644
index 0000000000000..218bdbfa527ba
--- /dev/null
+++ b/arch/loongarch/include/asm/crash_core.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _LOONGARCH_CRASH_CORE_H
+#define _LOONGARCH_CRASH_CORE_H
+
+#define CRASH_ALIGN			SZ_2M
+
+#define CRASH_ADDR_LOW_MAX		SZ_4G
+#define CRASH_ADDR_HIGH_MAX		memblock_end_of_DRAM()
+
+extern phys_addr_t memblock_end_of_DRAM(void);
+
+#endif
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 15d366b8407c3..edf2bba801306 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -252,38 +252,23 @@ static void __init arch_reserve_vmcore(void)
 #endif
 }
 
-/* 2MB alignment for crash kernel regions */
-#define CRASH_ALIGN	SZ_2M
-#define CRASH_ADDR_MAX	SZ_4G
-
-static void __init arch_parse_crashkernel(void)
+static void __init arch_reserve_crashkernel(void)
 {
-#ifdef CONFIG_KEXEC
 	int ret;
-	unsigned long long total_mem;
+	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
+	char *cmdline = boot_command_line;
+	bool high = false;
 
-	total_mem = memblock_phys_mem_size();
-	ret = parse_crashkernel(boot_command_line, total_mem,
-				&crash_size, &crash_base,
-				NULL, NULL);
-	if (ret < 0 || crash_size <= 0)
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
 		return;
 
-	if (crash_base <= 0) {
-		crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, CRASH_ALIGN, CRASH_ADDR_MAX);
-		if (!crash_base) {
-			pr_warn("crashkernel reservation failed - No suitable area found.\n");
-			return;
-		}
-	} else if (!memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_base + crash_size)) {
-		pr_warn("Invalid memory region reserved for crash kernel\n");
+	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+				&crash_size, &crash_base, &low_size, &high);
+	if (ret)
 		return;
-	}
 
-	crashk_res.start = crash_base;
-	crashk_res.end	 = crash_base + crash_size - 1;
-#endif
+	reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high);
 }
 
 static void __init fdt_setup(void)
@@ -363,7 +348,7 @@ out:
 void __init platform_init(void)
 {
 	arch_reserve_vmcore();
-	arch_parse_crashkernel();
+	arch_reserve_crashkernel();
 
 #ifdef CONFIG_ACPI_TABLE_UPGRADE
 	acpi_table_upgrade();
@@ -473,15 +458,6 @@ static void __init resource_init(void)
 		request_resource(res, &data_resource);
 		request_resource(res, &bss_resource);
 	}
-
-#ifdef CONFIG_KEXEC
-	if (crashk_res.start < crashk_res.end) {
-		insert_resource(&iomem_resource, &crashk_res);
-		pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
-			(unsigned long)((crashk_res.end - crashk_res.start + 1) >> 20),
-			(unsigned long)(crashk_res.start  >> 20));
-	}
-#endif
 }
 
 static int __init add_legacy_isa_io(struct fwnode_handle *fwnode,
-- 
GitLab


From 91af17cd7d03db8836554c91ba7c38b0817aa980 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:08 +0800
Subject: [PATCH 2820/4076] LoongArch: Fix definition of
 ftrace_regs_set_instruction_pointer()

The current definition of ftrace_regs_set_instruction_pointer() is not
correct. Obviously, this function is used to set instruction pointer but
not return value, so it should call instruction_pointer_set() instead of
regs_set_return_value().

There is no side effect by now because it is only used for kernel live-
patching which is not supported, so fix it to avoid failure when testing
livepatch in the future.

Fixes: 6fbff14a6382 ("LoongArch: ftrace: Abstract DYNAMIC_FTRACE_WITH_ARGS accesses")
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/ftrace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index a11996eb5892d..de891c2c83d4a 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/arch/loongarch/include/asm/ftrace.h
@@ -63,7 +63,7 @@ ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs)
 static __always_inline void
 ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip)
 {
-	regs_set_return_value(&fregs->regs, ip);
+	instruction_pointer_set(&fregs->regs, ip);
 }
 
 #define ftrace_regs_get_argument(fregs, n) \
-- 
GitLab


From 21c5ae5cc1eee70f7f3b09f1d6b237d9812d4b9c Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Wed, 17 Jan 2024 12:43:13 +0800
Subject: [PATCH 2821/4076] LoongArch: BPF: Support 64-bit pointers to kfuncs

Like commit 1cf3bfc60f9836f ("bpf: Support 64-bit pointers to kfuncs")
for s390x, add support for 64-bit pointers to kfuncs for LoongArch.
Since the infrastructure is already implemented in BPF core, the only
thing need to be done is to override bpf_jit_supports_far_kfunc_call().

Before this change, several test_verifier tests failed:

  # ./test_verifier | grep # | grep FAIL
  #119/p calls: invalid kfunc call: ptr_to_mem to struct with non-scalar FAIL
  #120/p calls: invalid kfunc call: ptr_to_mem to struct with nesting depth > 4 FAIL
  #121/p calls: invalid kfunc call: ptr_to_mem to struct with FAM FAIL
  #122/p calls: invalid kfunc call: reg->type != PTR_TO_CTX FAIL
  #123/p calls: invalid kfunc call: void * not allowed in func proto without mem size arg FAIL
  #124/p calls: trigger reg2btf_ids[reg->type] for reg->type > __BPF_REG_TYPE_MAX FAIL
  #125/p calls: invalid kfunc call: reg->off must be zero when passed to release kfunc FAIL
  #126/p calls: invalid kfunc call: don't match first member type when passed to release kfunc FAIL
  #127/p calls: invalid kfunc call: PTR_TO_BTF_ID with negative offset FAIL
  #128/p calls: invalid kfunc call: PTR_TO_BTF_ID with variable offset FAIL
  #129/p calls: invalid kfunc call: referenced arg needs refcounted PTR_TO_BTF_ID FAIL
  #130/p calls: valid kfunc call: referenced arg needs refcounted PTR_TO_BTF_ID FAIL
  #486/p map_kptr: ref: reference state created and released on xchg FAIL

This is because the kfuncs in the loaded module are far away from
__bpf_call_base:

  ffff800002009440 t bpf_kfunc_call_test_fail1    [bpf_testmod]
  9000000002e128d8 T __bpf_call_base

The offset relative to __bpf_call_base does NOT fit in s32, which breaks
the assumption in BPF core. Enable bpf_jit_supports_far_kfunc_call() lifts
this limit.

Note that to reproduce the above result, tools/testing/selftests/bpf/config
should be applied, and run the test with JIT enabled, unpriv BPF enabled.

With this change, the test_verifier tests now all passed:

  # ./test_verifier
  ...
  Summary: 777 PASSED, 0 SKIPPED, 0 FAILED

Tested-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/net/bpf_jit.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 4fcd6cd6da234..2f154c60ee007 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -201,6 +201,11 @@ bool bpf_jit_supports_kfunc_call(void)
 	return true;
 }
 
+bool bpf_jit_supports_far_kfunc_call(void)
+{
+	return true;
+}
+
 /* initialized on the first pass of build_body() */
 static int out_offset = -1;
 static int emit_bpf_tail_call(struct jit_ctx *ctx)
-- 
GitLab


From 36a87385e31c9343af9a4756598e704741250a67 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Wed, 17 Jan 2024 12:43:13 +0800
Subject: [PATCH 2822/4076] LoongArch: BPF: Prevent out-of-bounds memory access

The test_tag test triggers an unhandled page fault:

  # ./test_tag
  [  130.640218] CPU 0 Unable to handle kernel paging request at virtual address ffff80001b898004, era == 9000000003137f7c, ra == 9000000003139e70
  [  130.640501] Oops[#3]:
  [  130.640553] CPU: 0 PID: 1326 Comm: test_tag Tainted: G      D    O       6.7.0-rc4-loong-devel-gb62ab1a397cf #47 61985c1d94084daa2432f771daa45b56b10d8d2a
  [  130.640764] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022
  [  130.640874] pc 9000000003137f7c ra 9000000003139e70 tp 9000000104cb4000 sp 9000000104cb7a40
  [  130.641001] a0 ffff80001b894000 a1 ffff80001b897ff8 a2 000000006ba210be a3 0000000000000000
  [  130.641128] a4 000000006ba210be a5 00000000000000f1 a6 00000000000000b3 a7 0000000000000000
  [  130.641256] t0 0000000000000000 t1 00000000000007f6 t2 0000000000000000 t3 9000000004091b70
  [  130.641387] t4 000000006ba210be t5 0000000000000004 t6 fffffffffffffff0 t7 90000000040913e0
  [  130.641512] t8 0000000000000005 u0 0000000000000dc0 s9 0000000000000009 s0 9000000104cb7ae0
  [  130.641641] s1 00000000000007f6 s2 0000000000000009 s3 0000000000000095 s4 0000000000000000
  [  130.641771] s5 ffff80001b894000 s6 ffff80001b897fb0 s7 9000000004090c50 s8 0000000000000000
  [  130.641900]    ra: 9000000003139e70 build_body+0x1fcc/0x4988
  [  130.642007]   ERA: 9000000003137f7c build_body+0xd8/0x4988
  [  130.642112]  CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE)
  [  130.642261]  PRMD: 00000004 (PPLV0 +PIE -PWE)
  [  130.642353]  EUEN: 00000003 (+FPE +SXE -ASXE -BTE)
  [  130.642458]  ECFG: 00071c1c (LIE=2-4,10-12 VS=7)
  [  130.642554] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0)
  [  130.642658]  BADV: ffff80001b898004
  [  130.642719]  PRID: 0014c010 (Loongson-64bit, Loongson-3A5000)
  [  130.642815] Modules linked in: [last unloaded: bpf_testmod(O)]
  [  130.642924] Process test_tag (pid: 1326, threadinfo=00000000f7f4015f, task=000000006499f9fd)
  [  130.643062] Stack : 0000000000000000 9000000003380724 0000000000000000 0000000104cb7be8
  [  130.643213]         0000000000000000 25af8d9b6e600558 9000000106250ea0 9000000104cb7ae0
  [  130.643378]         0000000000000000 0000000000000000 9000000104cb7be8 90000000049f6000
  [  130.643538]         0000000000000090 9000000106250ea0 ffff80001b894000 ffff80001b894000
  [  130.643685]         00007ffffb917790 900000000313ca94 0000000000000000 0000000000000000
  [  130.643831]         ffff80001b894000 0000000000000ff7 0000000000000000 9000000100468000
  [  130.643983]         0000000000000000 0000000000000000 0000000000000040 25af8d9b6e600558
  [  130.644131]         0000000000000bb7 ffff80001b894048 0000000000000000 0000000000000000
  [  130.644276]         9000000104cb7be8 90000000049f6000 0000000000000090 9000000104cb7bdc
  [  130.644423]         ffff80001b894000 0000000000000000 00007ffffb917790 90000000032acfb0
  [  130.644572]         ...
  [  130.644629] Call Trace:
  [  130.644641] [<9000000003137f7c>] build_body+0xd8/0x4988
  [  130.644785] [<900000000313ca94>] bpf_int_jit_compile+0x228/0x4ec
  [  130.644891] [<90000000032acfb0>] bpf_prog_select_runtime+0x158/0x1b0
  [  130.645003] [<90000000032b3504>] bpf_prog_load+0x760/0xb44
  [  130.645089] [<90000000032b6744>] __sys_bpf+0xbb8/0x2588
  [  130.645175] [<90000000032b8388>] sys_bpf+0x20/0x2c
  [  130.645259] [<9000000003f6ab38>] do_syscall+0x7c/0x94
  [  130.645369] [<9000000003121c5c>] handle_syscall+0xbc/0x158
  [  130.645507]
  [  130.645539] Code: 380839f6  380831f9  28412bae <24000ca6> 004081ad  0014cb50  004083e8  02bff34c  58008e91
  [  130.645729]
  [  130.646418] ---[ end trace 0000000000000000 ]---

On my machine, which has CONFIG_PAGE_SIZE_16KB=y, the test failed at
loading a BPF prog with 2039 instructions:

  prog = (struct bpf_prog *)ffff80001b894000
  insn = (struct bpf_insn *)(prog->insnsi)ffff80001b894048
  insn + 2039 = (struct bpf_insn *)ffff80001b898000 <- end of the page

In the build_insn() function, we are trying to access next instruction
unconditionally, i.e. `(insn + 1)->imm`. The address lies in the next
page and can be not owned by the current process, thus an page fault is
inevitable and then segfault.

So, let's access next instruction only under `dst = imm64` context.

With this fix, we have:

  # ./test_tag
  test_tag: OK (40945 tests)

Fixes: bbfddb904df6f82 ("LoongArch: BPF: Avoid declare variables in switch-case")
Tested-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/net/bpf_jit.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 2f154c60ee007..e73323d759d0b 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -470,7 +470,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	const u8 dst = regmap[insn->dst_reg];
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
-	const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
 	const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32;
 
 	switch (code) {
@@ -928,8 +927,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* dst = imm64 */
 	case BPF_LD | BPF_IMM | BPF_DW:
+	{
+		const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
+
 		move_imm(ctx, dst, imm64, is32);
 		return 1;
+	}
 
 	/* dst = *(size *)(src + off) */
 	case BPF_LDX | BPF_MEM | BPF_B:
-- 
GitLab


From fc562925f51c0ce462c17b24a5c538db676af576 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:13 +0800
Subject: [PATCH 2823/4076] LoongArch: Update Loongson-3 default config file

1, Increase NR_CPUS to 256.
2, Enable some cgroup options.
3, Enable some PREEMPT_DYNAMIC/SCHED_CORE options.
4, Enable some CMA/DMA_CMA options.
5, Enable some F2FS options.
6, Enable some DMABUF/UDMABUF options.
7, Enable some USB4 and NTB options.
8, Enable some networking options (MPTCP).
9, Enable Loongson-specific drivers: APB DMA, ASoC.
10, Enable PCI_HOST_GENERIC and SND_VIRTIO for virtual machine.
11, Remove obsolete SECURITY_SELINUX_DISABLE.
12, Regenerate the whole file to keep the order of options be the same as
   the latest source code.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/configs/loongson3_defconfig | 55 ++++++++++++++++++----
 1 file changed, 47 insertions(+), 8 deletions(-)

diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 33795e4a5bd63..fd8d8a38cf5de 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -6,6 +6,8 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_PREEMPT=y
+CONFIG_PREEMPT_DYNAMIC=y
+CONFIG_SCHED_CORE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_TASKSTATS=y
@@ -19,6 +21,7 @@ CONFIG_BLK_CGROUP=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_HUGETLB=y
 CONFIG_CPUSETS=y
@@ -26,6 +29,7 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_PERF=y
 CONFIG_CGROUP_BPF=y
+CONFIG_CGROUP_MISC=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
@@ -35,6 +39,8 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_PERF_EVENTS=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
 CONFIG_LOONGARCH=y
 CONFIG_64BIT=y
 CONFIG_MACH_LOONGSON64=y
@@ -44,13 +50,11 @@ CONFIG_DMI=y
 CONFIG_EFI=y
 CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
-CONFIG_NR_CPUS=64
+CONFIG_NR_CPUS=256
 CONFIG_NUMA=y
 CONFIG_CPU_HAS_FPU=y
 CONFIG_CPU_HAS_LSX=y
 CONFIG_CPU_HAS_LASX=y
-CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
 CONFIG_RANDOMIZE_BASE=y
 CONFIG_SUSPEND=y
 CONFIG_HIBERNATION=y
@@ -62,10 +66,6 @@ CONFIG_ACPI_IPMI=m
 CONFIG_ACPI_HOTPLUG_CPU=y
 CONFIG_ACPI_PCI_SLOT=y
 CONFIG_ACPI_HOTPLUG_MEMORY=y
-CONFIG_EFI_ZBOOT=y
-CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER=y
-CONFIG_EFI_CAPSULE_LOADER=m
-CONFIG_EFI_TEST=m
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=m
 CONFIG_JUMP_LABEL=y
@@ -74,10 +74,18 @@ CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
+CONFIG_BLK_DEV_ZONED=y
 CONFIG_BLK_DEV_THROTTLING=y
+CONFIG_BLK_DEV_THROTTLING_LOW=y
+CONFIG_BLK_WBT=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_FC_APPID=y
+CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_CMDLINE_PARTITION=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BFQ_GROUP_IOSCHED=y
 CONFIG_BINFMT_MISC=m
@@ -93,6 +101,8 @@ CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_CMA=y
+CONFIG_CMA_SYSFS=y
 CONFIG_USERFAULTFD=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -128,6 +138,7 @@ CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
 CONFIG_INET6_ESP=m
 CONFIG_IPV6_MROUTE=y
+CONFIG_MPTCP=y
 CONFIG_NETWORK_PHY_TIMESTAMPING=y
 CONFIG_NETFILTER=y
 CONFIG_BRIDGE_NETFILTER=m
@@ -354,6 +365,7 @@ CONFIG_PCIEAER=y
 CONFIG_PCI_IOV=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_SHPC=y
+CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCCARD=m
 CONFIG_YENTA=m
 CONFIG_RAPIDIO=y
@@ -367,6 +379,10 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_FW_LOADER_COMPRESS=y
 CONFIG_FW_LOADER_COMPRESS_ZSTD=y
+CONFIG_EFI_ZBOOT=y
+CONFIG_EFI_BOOTLOADER_CONTROL=m
+CONFIG_EFI_CAPSULE_LOADER=m
+CONFIG_EFI_TEST=m
 CONFIG_MTD=m
 CONFIG_MTD_BLOCK=m
 CONFIG_MTD_CFI=m
@@ -588,6 +604,7 @@ CONFIG_RTW89_8852AE=m
 CONFIG_RTW89_8852CE=m
 CONFIG_ZD1211RW=m
 CONFIG_USB_NET_RNDIS_WLAN=m
+CONFIG_USB4_NET=m
 CONFIG_INPUT_MOUSEDEV=y
 CONFIG_INPUT_MOUSEDEV_PSAUX=y
 CONFIG_INPUT_EVDEV=y
@@ -693,6 +710,9 @@ CONFIG_SND_HDA_CODEC_SIGMATEL=y
 CONFIG_SND_HDA_CODEC_HDMI=y
 CONFIG_SND_HDA_CODEC_CONEXANT=y
 CONFIG_SND_USB_AUDIO=m
+CONFIG_SND_SOC=m
+CONFIG_SND_SOC_LOONGSON_CARD=m
+CONFIG_SND_VIRTIO=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 CONFIG_HID_A4TECH=m
@@ -740,6 +760,11 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
 CONFIG_RTC_DRV_LOONGSON=y
 CONFIG_DMADEVICES=y
+CONFIG_LS2X_APB_DMA=y
+CONFIG_UDMABUF=y
+CONFIG_DMABUF_HEAPS=y
+CONFIG_DMABUF_HEAPS_SYSTEM=y
+CONFIG_DMABUF_HEAPS_CMA=y
 CONFIG_UIO=m
 CONFIG_UIO_PDRV_GENIRQ=m
 CONFIG_UIO_DMEM_GENIRQ=m
@@ -780,7 +805,15 @@ CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
 CONFIG_DEVFREQ_GOV_PERFORMANCE=y
 CONFIG_DEVFREQ_GOV_POWERSAVE=y
 CONFIG_DEVFREQ_GOV_USERSPACE=y
+CONFIG_NTB=m
+CONFIG_NTB_MSI=y
+CONFIG_NTB_IDT=m
+CONFIG_NTB_EPF=m
+CONFIG_NTB_SWITCHTEC=m
+CONFIG_NTB_PERF=m
+CONFIG_NTB_TRANSPORT=m
 CONFIG_PWM=y
+CONFIG_USB4=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
@@ -799,6 +832,10 @@ CONFIG_GFS2_FS_LOCKING_DLM=y
 CONFIG_OCFS2_FS=m
 CONFIG_BTRFS_FS=y
 CONFIG_BTRFS_FS_POSIX_ACL=y
+CONFIG_F2FS_FS=m
+CONFIG_F2FS_FS_SECURITY=y
+CONFIG_F2FS_CHECK_FS=y
+CONFIG_F2FS_FS_COMPRESSION=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
@@ -885,7 +922,6 @@ CONFIG_KEY_DH_OPERATIONS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_DISABLE=y
 CONFIG_SECURITY_APPARMOR=y
 CONFIG_SECURITY_YAMA=y
 CONFIG_DEFAULT_SECURITY_DAC=y
@@ -916,6 +952,9 @@ CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_CRC32_LOONGARCH=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_DMA_CMA=y
+CONFIG_DMA_NUMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_PRINTK_TIME=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_MAGIC_SYSRQ=y
-- 
GitLab


From 6e441fa3ac475be73c03c9a85bd305d66ea476a6 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Wed, 17 Jan 2024 12:43:13 +0800
Subject: [PATCH 2824/4076] MAINTAINERS: Add BPF JIT for LOONGARCH entry

After commit 5dc615520c4d ("LoongArch: Add BPF JIT support"),
there is no BPF JIT for LOONGARCH entry, in order to maintain
the current code and the new features timely, just add it.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 MAINTAINERS | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index a7c4cf8201e01..afe2f311232fb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3651,6 +3651,13 @@ L:	bpf@vger.kernel.org
 S:	Supported
 F:	arch/arm64/net/
 
+BPF JIT for LOONGARCH
+M:	Tiezhu Yang <yangtiezhu@loongson.cn>
+R:	Hengqi Chen <hengqi.chen@gmail.com>
+L:	bpf@vger.kernel.org
+S:	Maintained
+F:	arch/loongarch/net/
+
 BPF JIT for MIPS (32-BIT AND 64-BIT)
 M:	Johan Almbladh <johan.almbladh@anyfinetworks.com>
 M:	Paul Burton <paulburton@kernel.org>
-- 
GitLab


From 0a8c1feed387f8460b8b65fc46fb3608afa7512e Mon Sep 17 00:00:00 2001
From: Yangyu Chen <cyy@cyyself.name>
Date: Wed, 17 Jan 2024 02:50:34 +0800
Subject: [PATCH 2825/4076] drm/ttm: allocate dummy_read_page without DMA32 on
 fail
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some platforms may not have any memory in ZONE_DMA32 and use IOMMU to allow
32-bit-DMA-only device to work. Forcing GFP_DMA32 on dummy_read_page will
fail on such platforms. Retry after fail will get this works on such
platforms.

Signed-off-by: Yangyu Chen <cyy@cyyself.name>
Link: https://patchwork.freedesktop.org/patch/msgid/tencent_8637383EE0A2C7CC870036AAF01909B26A0A@qq.com
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/ttm/ttm_device.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index d48b39132b324..c9fa8561f71fb 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -95,11 +95,17 @@ static int ttm_global_init(void)
 	ttm_pool_mgr_init(num_pages);
 	ttm_tt_mgr_init(num_pages, num_dma32);
 
-	glob->dummy_read_page = alloc_page(__GFP_ZERO | GFP_DMA32);
+	glob->dummy_read_page = alloc_page(__GFP_ZERO | GFP_DMA32 |
+					   __GFP_NOWARN);
 
+	/* Retry without GFP_DMA32 for platforms DMA32 is not available */
 	if (unlikely(glob->dummy_read_page == NULL)) {
-		ret = -ENOMEM;
-		goto out;
+		glob->dummy_read_page = alloc_page(__GFP_ZERO);
+		if (unlikely(glob->dummy_read_page == NULL)) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		pr_warn("Using GFP_DMA32 fallback for dummy_read_page\n");
 	}
 
 	INIT_LIST_HEAD(&glob->device_list);
-- 
GitLab


From 3d9e9020b92288871b02f194c3ec88e03a1afa88 Mon Sep 17 00:00:00 2001
From: Khaled Almahallawy <khaled.almahallawy@intel.com>
Date: Wed, 13 Dec 2023 13:15:42 -0800
Subject: [PATCH 2826/4076] drm/i915/dp: Fix passing the correct DPCD_REV for
 drm_dp_set_phy_test_pattern

Using link_status to get DPCD_REV fails when disabling/defaulting
phy pattern. Use intel_dp->dpcd to access DPCD_REV correctly.

Fixes: 8cdf72711928 ("drm/i915/dp: Program vswing, pre-emphasis, test-pattern")
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Lee Shawn C <shawn.c.lee@intel.com>
Signed-off-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231213211542.3585105-3-khaled.almahallawy@intel.com
(cherry picked from commit 3ee302ec22d6e1d7d1e6d381b0d507ee80f2135c)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index c3b906ebe542f..f5ef95da55346 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4764,7 +4764,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp,
 			  intel_dp->train_set, crtc_state->lane_count);
 
 	drm_dp_set_phy_test_pattern(&intel_dp->aux, data,
-				    link_status[DP_DPCD_REV]);
+				    intel_dp->dpcd[DP_DPCD_REV]);
 }
 
 static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp)
-- 
GitLab


From 0103b4496087c99c195800456bf6a4fcf24fd444 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Mon, 18 Dec 2023 16:05:43 -0800
Subject: [PATCH 2827/4076] drm/i915/perf: Update handling of MMIO triggered
 reports

On XEHP platforms user is not able to find MMIO triggered reports in the
OA buffer since i915 squashes the context ID fields. These context ID
fields hold the MMIO trigger markers.

Update logic to not squash the context ID fields of MMIO triggered
reports.

Fixes: cba94bbcff08 ("drm/i915/perf: Determine context valid in OA reports")
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231219000543.1087706-1-umesh.nerlige.ramappa@intel.com
(cherry picked from commit 0c68132df6e66244acec1bb5b9e19b0751414389)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_perf.c | 39 ++++++++++++++++++++++++++++----
 1 file changed, 34 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 7b1c8de2f9cb3..2d695818f0062 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -772,10 +772,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * The reason field includes flags identifying what
 		 * triggered this specific report (mostly timer
 		 * triggered or e.g. due to a context switch).
-		 *
-		 * In MMIO triggered reports, some platforms do not set the
-		 * reason bit in this field and it is valid to have a reason
-		 * field of zero.
 		 */
 		reason = oa_report_reason(stream, report);
 		ctx_id = oa_context_id(stream, report32);
@@ -787,8 +783,41 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 *
 		 * Note: that we don't clear the valid_ctx_bit so userspace can
 		 * understand that the ID has been squashed by the kernel.
+		 *
+		 * Update:
+		 *
+		 * On XEHP platforms the behavior of context id valid bit has
+		 * changed compared to prior platforms. To describe this, we
+		 * define a few terms:
+		 *
+		 * context-switch-report: This is a report with the reason type
+		 * being context-switch. It is generated when a context switches
+		 * out.
+		 *
+		 * context-valid-bit: A bit that is set in the report ID field
+		 * to indicate that a valid context has been loaded.
+		 *
+		 * gpu-idle: A condition characterized by a
+		 * context-switch-report with context-valid-bit set to 0.
+		 *
+		 * On prior platforms, context-id-valid bit is set to 0 only
+		 * when GPU goes idle. In all other reports, it is set to 1.
+		 *
+		 * On XEHP platforms, context-valid-bit is set to 1 in a context
+		 * switch report if a new context switched in. For all other
+		 * reports it is set to 0.
+		 *
+		 * This change in behavior causes an issue with MMIO triggered
+		 * reports. MMIO triggered reports have the markers in the
+		 * context ID field and the context-valid-bit is 0. The logic
+		 * below to squash the context ID would render the report
+		 * useless since the user will not be able to find it in the OA
+		 * buffer. Since MMIO triggered reports exist only on XEHP,
+		 * we should avoid squashing these for XEHP platforms.
 		 */
-		if (oa_report_ctx_invalid(stream, report)) {
+
+		if (oa_report_ctx_invalid(stream, report) &&
+		    GRAPHICS_VER_FULL(stream->engine->i915) < IP_VER(12, 50)) {
 			ctx_id = INVALID_CTX_ID;
 			oa_context_id_squash(stream, report32);
 		}
-- 
GitLab


From efb8235bfdbe661c460f803150b50840a73b5f03 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 15 Jan 2024 12:17:43 +0100
Subject: [PATCH 2828/4076] gpiolib: revert the attempt to protect the GPIO
 device list with an rwsem

This reverts commits 1979a2807547 ("gpiolib: replace the GPIO device
mutex with a read-write semaphore") and 65a828bab158 ("gpiolib: use
a mutex to protect the list of GPIO devices").

Unfortunately the legacy GPIO API that's still used in older code has to
translate numbers from the global GPIO numberspace to descriptors. This
results in a GPIO device lookup in every call to legacy functions. Some
of those functions - like gpio_set/get_value() - can be called from
atomic context so taking a sleeping lock that is an RW semaphore results
in an error.

We'll probably have to protect this list with SRCU.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-wireless/f7b5ff1e-8f34-4d98-a7be-b826cb897dc8@moroto.mountain/
Fixes: 1979a2807547 ("gpiolib: replace the GPIO device mutex with a read-write semaphore")
Fixes: 65a828bab158 ("gpiolib: use a mutex to protect the list of GPIO devices")
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib-sysfs.c |  45 ++++++------
 drivers/gpio/gpiolib-sysfs.h |   6 --
 drivers/gpio/gpiolib.c       | 133 +++++++++++++++++++----------------
 drivers/gpio/gpiolib.h       |   2 -
 4 files changed, 97 insertions(+), 89 deletions(-)

diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 4dbf298bb5dda..6bf5332136e5a 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -768,25 +768,6 @@ int gpiochip_sysfs_register(struct gpio_device *gdev)
 	return 0;
 }
 
-int gpiochip_sysfs_register_all(void)
-{
-	struct gpio_device *gdev;
-	int ret;
-
-	guard(rwsem_read)(&gpio_devices_sem);
-
-	list_for_each_entry(gdev, &gpio_devices, list) {
-		if (gdev->mockdev)
-			continue;
-
-		ret = gpiochip_sysfs_register(gdev);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
 void gpiochip_sysfs_unregister(struct gpio_device *gdev)
 {
 	struct gpio_desc *desc;
@@ -811,7 +792,9 @@ void gpiochip_sysfs_unregister(struct gpio_device *gdev)
 
 static int __init gpiolib_sysfs_init(void)
 {
-	int status;
+	int		status;
+	unsigned long	flags;
+	struct gpio_device *gdev;
 
 	status = class_register(&gpio_class);
 	if (status < 0)
@@ -823,6 +806,26 @@ static int __init gpiolib_sysfs_init(void)
 	 * We run before arch_initcall() so chip->dev nodes can have
 	 * registered, and so arch_initcall() can always gpiod_export().
 	 */
-	return gpiochip_sysfs_register_all();
+	spin_lock_irqsave(&gpio_lock, flags);
+	list_for_each_entry(gdev, &gpio_devices, list) {
+		if (gdev->mockdev)
+			continue;
+
+		/*
+		 * TODO we yield gpio_lock here because
+		 * gpiochip_sysfs_register() acquires a mutex. This is unsafe
+		 * and needs to be fixed.
+		 *
+		 * Also it would be nice to use gpio_device_find() here so we
+		 * can keep gpio_chips local to gpiolib.c, but the yield of
+		 * gpio_lock prevents us from doing this.
+		 */
+		spin_unlock_irqrestore(&gpio_lock, flags);
+		status = gpiochip_sysfs_register(gdev);
+		spin_lock_irqsave(&gpio_lock, flags);
+	}
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
+	return status;
 }
 postcore_initcall(gpiolib_sysfs_init);
diff --git a/drivers/gpio/gpiolib-sysfs.h b/drivers/gpio/gpiolib-sysfs.h
index ab157cec0b4be..b794b396d6a52 100644
--- a/drivers/gpio/gpiolib-sysfs.h
+++ b/drivers/gpio/gpiolib-sysfs.h
@@ -8,7 +8,6 @@ struct gpio_device;
 #ifdef CONFIG_GPIO_SYSFS
 
 int gpiochip_sysfs_register(struct gpio_device *gdev);
-int gpiochip_sysfs_register_all(void);
 void gpiochip_sysfs_unregister(struct gpio_device *gdev);
 
 #else
@@ -18,11 +17,6 @@ static inline int gpiochip_sysfs_register(struct gpio_device *gdev)
 	return 0;
 }
 
-static inline int gpiochip_sysfs_register_all(void)
-{
-	return 0;
-}
-
 static inline void gpiochip_sysfs_unregister(struct gpio_device *gdev)
 {
 }
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 4c93cf73a8260..44c8f5743a241 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2,7 +2,6 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
-#include <linux/cleanup.h>
 #include <linux/compat.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
@@ -16,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/seq_file.h>
@@ -83,9 +81,7 @@ DEFINE_SPINLOCK(gpio_lock);
 
 static DEFINE_MUTEX(gpio_lookup_lock);
 static LIST_HEAD(gpio_lookup_list);
-
 LIST_HEAD(gpio_devices);
-DECLARE_RWSEM(gpio_devices_sem);
 
 static DEFINE_MUTEX(gpio_machine_hogs_mutex);
 static LIST_HEAD(gpio_machine_hogs);
@@ -117,15 +113,20 @@ static inline void desc_set_label(struct gpio_desc *d, const char *label)
 struct gpio_desc *gpio_to_desc(unsigned gpio)
 {
 	struct gpio_device *gdev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gpio_lock, flags);
 
-	scoped_guard(rwsem_read, &gpio_devices_sem) {
-		list_for_each_entry(gdev, &gpio_devices, list) {
-			if (gdev->base <= gpio &&
-			    gdev->base + gdev->ngpio > gpio)
-				return &gdev->descs[gpio - gdev->base];
+	list_for_each_entry(gdev, &gpio_devices, list) {
+		if (gdev->base <= gpio &&
+		    gdev->base + gdev->ngpio > gpio) {
+			spin_unlock_irqrestore(&gpio_lock, flags);
+			return &gdev->descs[gpio - gdev->base];
 		}
 	}
 
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
 	if (!gpio_is_valid(gpio))
 		pr_warn("invalid GPIO %d\n", gpio);
 
@@ -398,21 +399,26 @@ static int gpiodev_add_to_list_unlocked(struct gpio_device *gdev)
 static struct gpio_desc *gpio_name_to_desc(const char * const name)
 {
 	struct gpio_device *gdev;
+	unsigned long flags;
 
 	if (!name)
 		return NULL;
 
-	guard(rwsem_read)(&gpio_devices_sem);
+	spin_lock_irqsave(&gpio_lock, flags);
 
 	list_for_each_entry(gdev, &gpio_devices, list) {
 		struct gpio_desc *desc;
 
 		for_each_gpio_desc(gdev->chip, desc) {
-			if (desc->name && !strcmp(desc->name, name))
+			if (desc->name && !strcmp(desc->name, name)) {
+				spin_unlock_irqrestore(&gpio_lock, flags);
 				return desc;
+			}
 		}
 	}
 
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
 	return NULL;
 }
 
@@ -807,6 +813,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 			       struct lock_class_key *request_key)
 {
 	struct gpio_device *gdev;
+	unsigned long flags;
 	unsigned int i;
 	int base = 0;
 	int ret = 0;
@@ -871,46 +878,49 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 
 	gdev->ngpio = gc->ngpio;
 
-	scoped_guard(rwsem_write, &gpio_devices_sem) {
-		/*
-		 * TODO: this allocates a Linux GPIO number base in the global
-		 * GPIO numberspace for this chip. In the long run we want to
-		 * get *rid* of this numberspace and use only descriptors, but
-		 * it may be a pipe dream. It will not happen before we get rid
-		 * of the sysfs interface anyways.
-		 */
-		base = gc->base;
+	spin_lock_irqsave(&gpio_lock, flags);
 
+	/*
+	 * TODO: this allocates a Linux GPIO number base in the global
+	 * GPIO numberspace for this chip. In the long run we want to
+	 * get *rid* of this numberspace and use only descriptors, but
+	 * it may be a pipe dream. It will not happen before we get rid
+	 * of the sysfs interface anyways.
+	 */
+	base = gc->base;
+	if (base < 0) {
+		base = gpiochip_find_base_unlocked(gc->ngpio);
 		if (base < 0) {
-			base = gpiochip_find_base_unlocked(gc->ngpio);
-			if (base < 0) {
-				ret = base;
-				base = 0;
-				goto err_free_label;
-			}
-			/*
-			 * TODO: it should not be necessary to reflect the assigned
-			 * base outside of the GPIO subsystem. Go over drivers and
-			 * see if anyone makes use of this, else drop this and assign
-			 * a poison instead.
-			 */
-			gc->base = base;
-		} else {
-			dev_warn(&gdev->dev,
-				 "Static allocation of GPIO base is deprecated, use dynamic allocation.\n");
-		}
-		gdev->base = base;
-
-		ret = gpiodev_add_to_list_unlocked(gdev);
-		if (ret) {
-			chip_err(gc, "GPIO integer space overlap, cannot add chip\n");
+			spin_unlock_irqrestore(&gpio_lock, flags);
+			ret = base;
+			base = 0;
 			goto err_free_label;
 		}
+		/*
+		 * TODO: it should not be necessary to reflect the assigned
+		 * base outside of the GPIO subsystem. Go over drivers and
+		 * see if anyone makes use of this, else drop this and assign
+		 * a poison instead.
+		 */
+		gc->base = base;
+	} else {
+		dev_warn(&gdev->dev,
+			 "Static allocation of GPIO base is deprecated, use dynamic allocation.\n");
+	}
+	gdev->base = base;
 
-		for (i = 0; i < gc->ngpio; i++)
-			gdev->descs[i].gdev = gdev;
+	ret = gpiodev_add_to_list_unlocked(gdev);
+	if (ret) {
+		spin_unlock_irqrestore(&gpio_lock, flags);
+		chip_err(gc, "GPIO integer space overlap, cannot add chip\n");
+		goto err_free_label;
 	}
 
+	for (i = 0; i < gc->ngpio; i++)
+		gdev->descs[i].gdev = gdev;
+
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
 	BLOCKING_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier);
 	BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier);
 	init_rwsem(&gdev->sem);
@@ -1001,8 +1011,9 @@ err_free_gpiochip_mask:
 		goto err_print_message;
 	}
 err_remove_from_list:
-	scoped_guard(rwsem_write, &gpio_devices_sem)
-		list_del(&gdev->list);
+	spin_lock_irqsave(&gpio_lock, flags);
+	list_del(&gdev->list);
+	spin_unlock_irqrestore(&gpio_lock, flags);
 err_free_label:
 	kfree_const(gdev->label);
 err_free_descs:
@@ -1065,7 +1076,7 @@ void gpiochip_remove(struct gpio_chip *gc)
 		dev_crit(&gdev->dev,
 			 "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
 
-	scoped_guard(rwsem_write, &gpio_devices_sem)
+	scoped_guard(spinlock_irqsave, &gpio_lock)
 		list_del(&gdev->list);
 
 	/*
@@ -1114,7 +1125,7 @@ struct gpio_device *gpio_device_find(void *data,
 	 */
 	might_sleep();
 
-	guard(rwsem_read)(&gpio_devices_sem);
+	guard(spinlock_irqsave)(&gpio_lock);
 
 	list_for_each_entry(gdev, &gpio_devices, list) {
 		if (gdev->chip && match(gdev->chip, data))
@@ -4725,33 +4736,35 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_device *gdev)
 
 static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos)
 {
+	unsigned long flags;
 	struct gpio_device *gdev = NULL;
 	loff_t index = *pos;
 
 	s->private = "";
 
-	guard(rwsem_read)(&gpio_devices_sem);
-
-	list_for_each_entry(gdev, &gpio_devices, list) {
-		if (index-- == 0)
+	spin_lock_irqsave(&gpio_lock, flags);
+	list_for_each_entry(gdev, &gpio_devices, list)
+		if (index-- == 0) {
+			spin_unlock_irqrestore(&gpio_lock, flags);
 			return gdev;
-	}
+		}
+	spin_unlock_irqrestore(&gpio_lock, flags);
 
 	return NULL;
 }
 
 static void *gpiolib_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
+	unsigned long flags;
 	struct gpio_device *gdev = v;
 	void *ret = NULL;
 
-	scoped_guard(rwsem_read, &gpio_devices_sem) {
-		if (list_is_last(&gdev->list, &gpio_devices))
-			ret = NULL;
-		else
-			ret = list_first_entry(&gdev->list, struct gpio_device,
-					       list);
-	}
+	spin_lock_irqsave(&gpio_lock, flags);
+	if (list_is_last(&gdev->list, &gpio_devices))
+		ret = NULL;
+	else
+		ret = list_first_entry(&gdev->list, struct gpio_device, list);
+	spin_unlock_irqrestore(&gpio_lock, flags);
 
 	s->private = "\n";
 	++*pos;
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 97df54abf57ac..a4a2520b5f31c 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -15,7 +15,6 @@
 #include <linux/gpio/consumer.h> /* for enum gpiod_flags */
 #include <linux/gpio/driver.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
 
@@ -137,7 +136,6 @@ int gpiod_set_transitory(struct gpio_desc *desc, bool transitory);
 
 extern spinlock_t gpio_lock;
 extern struct list_head gpio_devices;
-extern struct rw_semaphore gpio_devices_sem;
 
 void gpiod_line_state_notify(struct gpio_desc *desc, unsigned long action);
 
-- 
GitLab


From 3eb791c891aa91603a5fbbfea940f8acf5f17d45 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Winiarski?= <michal.winiarski@intel.com>
Date: Tue, 16 Jan 2024 18:46:02 +0100
Subject: [PATCH 2829/4076] drm/tests: mm: Call drm_mm_print in
 drm_test_mm_debug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The original intent behind the test was to sanity check whether calling
the debug iterator (drm_mm_print) doesn't cause any problems.
Unfortunately - this call got accidentally removed during KUnit
transition. Restore it.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240116174602.1019512-1-michal.winiarski@intel.com
---
 drivers/gpu/drm/tests/drm_mm_test.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c
index 05d5e7af6d250..6803cb2eb8fd6 100644
--- a/drivers/gpu/drm/tests/drm_mm_test.c
+++ b/drivers/gpu/drm/tests/drm_mm_test.c
@@ -247,13 +247,13 @@ out:
 
 static void drm_test_mm_debug(struct kunit *test)
 {
+	struct drm_printer p = drm_debug_printer(test->name);
 	struct drm_mm mm;
 	struct drm_mm_node nodes[2];
 
 	/* Create a small drm_mm with a couple of nodes and a few holes, and
 	 * check that the debug iterator doesn't explode over a trivial drm_mm.
 	 */
-
 	drm_mm_init(&mm, 0, 4096);
 
 	memset(nodes, 0, sizeof(nodes));
@@ -268,6 +268,9 @@ static void drm_test_mm_debug(struct kunit *test)
 	KUNIT_ASSERT_FALSE_MSG(test, drm_mm_reserve_node(&mm, &nodes[1]),
 			       "failed to reserve node[0] {start=%lld, size=%lld)\n",
 			       nodes[0].start, nodes[0].size);
+
+	drm_mm_print(&mm, &p);
+	KUNIT_SUCCEED(test);
 }
 
 static struct drm_mm_node *set_node(struct drm_mm_node *node,
-- 
GitLab


From c2945c435c999c63e47f337bc7c13c98c21d0bcc Mon Sep 17 00:00:00 2001
From: Romain Gantois <romain.gantois@bootlin.com>
Date: Tue, 16 Jan 2024 13:19:17 +0100
Subject: [PATCH 2830/4076] net: stmmac: Prevent DSA tags from breaking COE

Some DSA tagging protocols change the EtherType field in the MAC header
e.g.  DSA_TAG_PROTO_(DSA/EDSA/BRCM/MTK/RTL4C_A/SJA1105). On TX these tagged
frames are ignored by the checksum offload engine and IP header checker of
some stmmac cores.

On RX, the stmmac driver wrongly assumes that checksums have been computed
for these tagged packets, and sets CHECKSUM_UNNECESSARY.

Add an additional check in the stmmac TX and RX hotpaths so that COE is
deactivated for packets with ethertypes that will not trigger the COE and
IP header checks.

Fixes: 6b2c6e4a938f ("net: stmmac: propagate feature flags to vlan")
Cc:  <stable@vger.kernel.org>
Reported-by: Richard Tresidder <rtresidd@electromag.com.au>
Link: https://lore.kernel.org/netdev/e5c6c75f-2dfa-4e50-a1fb-6bf4cdb617c2@electromag.com.au/
Reported-by: Romain Gantois <romain.gantois@bootlin.com>
Link: https://lore.kernel.org/netdev/c57283ed-6b9b-b0e6-ee12-5655c1c54495@bootlin.com/
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Romain Gantois <romain.gantois@bootlin.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 32 +++++++++++++++++--
 1 file changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c78a96b8eb649..a0e46369ae158 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4435,6 +4435,28 @@ dma_map_err:
 	return NETDEV_TX_OK;
 }
 
+/**
+ * stmmac_has_ip_ethertype() - Check if packet has IP ethertype
+ * @skb: socket buffer to check
+ *
+ * Check if a packet has an ethertype that will trigger the IP header checks
+ * and IP/TCP checksum engine of the stmmac core.
+ *
+ * Return: true if the ethertype can trigger the checksum engine, false
+ * otherwise
+ */
+static bool stmmac_has_ip_ethertype(struct sk_buff *skb)
+{
+	int depth = 0;
+	__be16 proto;
+
+	proto = __vlan_get_protocol(skb, eth_header_parse_protocol(skb),
+				    &depth);
+
+	return (depth <= ETH_HLEN) &&
+		(proto == htons(ETH_P_IP) || proto == htons(ETH_P_IPV6));
+}
+
 /**
  *  stmmac_xmit - Tx entry point of the driver
  *  @skb : the socket buffer
@@ -4499,9 +4521,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* DWMAC IPs can be synthesized to support tx coe only for a few tx
 	 * queues. In that case, checksum offloading for those queues that don't
 	 * support tx coe needs to fallback to software checksum calculation.
+	 *
+	 * Packets that won't trigger the COE e.g. most DSA-tagged packets will
+	 * also have to be checksummed in software.
 	 */
 	if (csum_insertion &&
-	    priv->plat->tx_queues_cfg[queue].coe_unsupported) {
+	    (priv->plat->tx_queues_cfg[queue].coe_unsupported ||
+	     !stmmac_has_ip_ethertype(skb))) {
 		if (unlikely(skb_checksum_help(skb)))
 			goto dma_map_err;
 		csum_insertion = !csum_insertion;
@@ -5066,7 +5092,7 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 		stmmac_rx_vlan(priv->dev, skb);
 	skb->protocol = eth_type_trans(skb, priv->dev);
 
-	if (unlikely(!coe))
+	if (unlikely(!coe) || !stmmac_has_ip_ethertype(skb))
 		skb_checksum_none_assert(skb);
 	else
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -5589,7 +5615,7 @@ drain_data:
 
 		skb->protocol = eth_type_trans(skb, priv->dev);
 
-		if (unlikely(!coe))
+		if (unlikely(!coe) || !stmmac_has_ip_ethertype(skb))
 			skb_checksum_none_assert(skb);
 		else
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
-- 
GitLab


From c0f5aec28edf98906d28f08daace6522adf9ee7a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 16 Jan 2024 18:18:47 +0100
Subject: [PATCH 2831/4076] mptcp: relax check on MPC passive fallback

While testing the blamed commit below, I was able to miss (!)
packetdrill failures in the fastopen test-cases.

On passive fastopen the child socket is created by incoming TCP MPC syn,
allow for both MPC_SYN and MPC_ACK header.

Fixes: 724b00c12957 ("mptcp: refine opt_mp_capable determination")
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1117d1e84274a..0dcb721c89d19 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -783,7 +783,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * options.
 		 */
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK))
+		if (!(mp_opt.suboptions &
+		      (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_ACK)))
 			fallback = true;
 
 	} else if (subflow_req->mp_join) {
-- 
GitLab


From ea937f77208323d35ffe2f8d8fc81b00118bfcda Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 16 Jan 2024 11:14:00 -0800
Subject: [PATCH 2832/4076] net: netdevsim: don't try to destroy PHC on VFs

PHC gets initialized in nsim_init_netdevsim(), which
is only called if (nsim_dev_port_is_pf()).

Create a counterpart of nsim_init_netdevsim() and
move the mock_phc_destroy() there.

This fixes a crash trying to destroy netdevsim with
VFs instantiated, as caught by running the devlink.sh test:

    BUG: kernel NULL pointer dereference, address: 00000000000000b8
    RIP: 0010:mock_phc_destroy+0xd/0x30
    Call Trace:
     <TASK>
     nsim_destroy+0x4a/0x70 [netdevsim]
     __nsim_dev_port_del+0x47/0x70 [netdevsim]
     nsim_dev_reload_destroy+0x105/0x120 [netdevsim]
     nsim_drv_remove+0x2f/0xb0 [netdevsim]
     device_release_driver_internal+0x1a1/0x210
     bus_remove_device+0xd5/0x120
     device_del+0x159/0x490
     device_unregister+0x12/0x30
     del_device_store+0x11a/0x1a0 [netdevsim]
     kernfs_fop_write_iter+0x130/0x1d0
     vfs_write+0x30b/0x4b0
     ksys_write+0x69/0xf0
     do_syscall_64+0xcc/0x1e0
     entry_SYSCALL_64_after_hwframe+0x6f/0x77

Fixes: b63e78fca889 ("net: netdevsim: use mock PHC driver")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/netdev.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index aecaf5f44374f..77e8250282a51 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -369,6 +369,12 @@ static int nsim_init_netdevsim_vf(struct netdevsim *ns)
 	return err;
 }
 
+static void nsim_exit_netdevsim(struct netdevsim *ns)
+{
+	nsim_udp_tunnels_info_destroy(ns->netdev);
+	mock_phc_destroy(ns->phc);
+}
+
 struct netdevsim *
 nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 {
@@ -417,8 +423,7 @@ void nsim_destroy(struct netdevsim *ns)
 	}
 	rtnl_unlock();
 	if (nsim_dev_port_is_pf(ns->nsim_dev_port))
-		nsim_udp_tunnels_info_destroy(dev);
-	mock_phc_destroy(ns->phc);
+		nsim_exit_netdevsim(ns);
 	free_netdev(dev);
 }
 
-- 
GitLab


From 0617c3de9b4026b87be12b0cb5c35f42c7c66fcb Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 3 Jan 2024 23:34:58 +0100
Subject: [PATCH 2833/4076] netfilter: nf_tables: reject invalid set policy

Report -EINVAL in case userspace provides a unsupported set backend
policy.

Fixes: c50b960ccc59 ("netfilter: nf_tables: implement proper set selection")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 8438a8922e4ab..a90a364f5be5a 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5048,8 +5048,16 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 	}
 
 	desc.policy = NFT_SET_POL_PERFORMANCE;
-	if (nla[NFTA_SET_POLICY] != NULL)
+	if (nla[NFTA_SET_POLICY] != NULL) {
 		desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+		switch (desc.policy) {
+		case NFT_SET_POL_PERFORMANCE:
+		case NFT_SET_POL_MEMORY:
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
 
 	if (nla[NFTA_SET_DESC] != NULL) {
 		err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
-- 
GitLab


From 65b3bd600e15e00fb9e433bbc8aa55e42b202055 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sat, 6 Jan 2024 23:52:02 +0100
Subject: [PATCH 2834/4076] netfilter: nf_tables: validate .maxattr at
 expression registration

struct nft_expr_info allows to store up to NFT_EXPR_MAXATTR (16)
attributes when parsing netlink attributes.

Rise a warning in case there is ever a nft expression whose .maxattr
goes beyond this number of expressions, in such case, struct nft_expr_info
needs to be updated.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a90a364f5be5a..2548d7d56408c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2977,6 +2977,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info,
  */
 int nft_register_expr(struct nft_expr_type *type)
 {
+	if (WARN_ON_ONCE(type->maxattr > NFT_EXPR_MAXATTR))
+		return -ENOMEM;
+
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
 	if (type->family == NFPROTO_UNSPEC)
 		list_add_tail_rcu(&type->list, &nf_tables_expressions);
-- 
GitLab


From 3c13725f43dcf43ad8a9bcd6a9f12add19a8f93e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sun, 7 Jan 2024 23:00:15 +0100
Subject: [PATCH 2835/4076] netfilter: nf_tables: bail out if stateful
 expression provides no .clone

All existing NFT_EXPR_STATEFUL provide a .clone interface, remove
fallback to copy content of stateful expression since this is never
exercised and bail out if .clone interface is not defined.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 2548d7d56408c..b3db97440db15 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3274,14 +3274,13 @@ int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
 {
 	int err;
 
-	if (src->ops->clone) {
-		dst->ops = src->ops;
-		err = src->ops->clone(dst, src);
-		if (err < 0)
-			return err;
-	} else {
-		memcpy(dst, src, src->ops->size);
-	}
+	if (WARN_ON_ONCE(!src->ops->clone))
+		return -EINVAL;
+
+	dst->ops = src->ops;
+	err = src->ops->clone(dst, src);
+	if (err < 0)
+		return err;
 
 	__module_get(src->ops->type->owner);
 
-- 
GitLab


From 91a139cee1202a4599a380810d93c69b5bac6197 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 10 Jan 2024 00:42:37 +0100
Subject: [PATCH 2836/4076] netfilter: nft_limit: do not ignore unsupported
 flags

Bail out if userspace provides unsupported flags, otherwise future
extensions to the limit expression will be silently ignored by the
kernel.

Fixes: c7862a5f0de5 ("netfilter: nft_limit: allow to invert matching criteria")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_limit.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index 145dc62c62472..79039afde34ec 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -58,6 +58,7 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost)
 static int nft_limit_init(struct nft_limit_priv *priv,
 			  const struct nlattr * const tb[], bool pkts)
 {
+	bool invert = false;
 	u64 unit, tokens;
 
 	if (tb[NFTA_LIMIT_RATE] == NULL ||
@@ -90,19 +91,23 @@ static int nft_limit_init(struct nft_limit_priv *priv,
 				 priv->rate);
 	}
 
+	if (tb[NFTA_LIMIT_FLAGS]) {
+		u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS]));
+
+		if (flags & ~NFT_LIMIT_F_INV)
+			return -EOPNOTSUPP;
+
+		if (flags & NFT_LIMIT_F_INV)
+			invert = true;
+	}
+
 	priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT);
 	if (!priv->limit)
 		return -ENOMEM;
 
 	priv->limit->tokens = tokens;
 	priv->tokens_max = priv->limit->tokens;
-
-	if (tb[NFTA_LIMIT_FLAGS]) {
-		u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS]));
-
-		if (flags & NFT_LIMIT_F_INV)
-			priv->invert = true;
-	}
+	priv->invert = invert;
 	priv->limit->last = ktime_get_ns();
 	spin_lock_init(&priv->limit->lock);
 
-- 
GitLab


From c3f9fd54cd87233f53bdf0e191a86b3a5e960e02 Mon Sep 17 00:00:00 2001
From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Date: Thu, 11 Jan 2024 23:06:37 +0800
Subject: [PATCH 2837/4076] netfilter: nfnetlink_log: use proper helper for
 fetching physinif

We don't use physindev in __build_packet_message except for getting
physinif from it. So let's switch to nf_bridge_get_physinif to get what
we want directly.

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink_log.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index f03f4d4d7d889..134e05d31061e 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -508,7 +508,7 @@ __build_packet_message(struct nfnl_log_net *log,
 					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
 				goto nla_put_failure;
 		} else {
-			struct net_device *physindev;
+			int physinif;
 
 			/* Case 2: indev is bridge group, we need to look for
 			 * physical device (when called from ipv4) */
@@ -516,10 +516,10 @@ __build_packet_message(struct nfnl_log_net *log,
 					 htonl(indev->ifindex)))
 				goto nla_put_failure;
 
-			physindev = nf_bridge_get_physindev(skb);
-			if (physindev &&
+			physinif = nf_bridge_get_physinif(skb);
+			if (physinif &&
 			    nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV,
-					 htonl(physindev->ifindex)))
+					 htonl(physinif)))
 				goto nla_put_failure;
 		}
 #endif
-- 
GitLab


From aeaa44075f8e49e2e0ad4507d925e690b7950145 Mon Sep 17 00:00:00 2001
From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Date: Thu, 11 Jan 2024 23:06:38 +0800
Subject: [PATCH 2838/4076] netfilter: nf_queue: remove excess nf_bridge
 variable

We don't really need nf_bridge variable here. And nf_bridge_info_exists
is better replacement for nf_bridge_info_get in case we are only
checking for existence.

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_queue.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 63d1516816b1f..3dfcb3ac5cb44 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -82,10 +82,8 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	const struct sk_buff *skb = entry->skb;
-	struct nf_bridge_info *nf_bridge;
 
-	nf_bridge = nf_bridge_info_get(skb);
-	if (nf_bridge) {
+	if (nf_bridge_info_exists(skb)) {
 		entry->physin = nf_bridge_get_physindev(skb);
 		entry->physout = nf_bridge_get_physoutdev(skb);
 	} else {
-- 
GitLab


From a54e72197037d2c9bfcd70dddaac8c8ccb5b41ba Mon Sep 17 00:00:00 2001
From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Date: Thu, 11 Jan 2024 23:06:39 +0800
Subject: [PATCH 2839/4076] netfilter: propagate net to nf_bridge_get_physindev

This is a preparation patch for replacing physindev with physinif on
nf_bridge_info structure. We will use dev_get_by_index_rcu to resolve
device, when needed, and it requires net to be available.

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge.h           |  2 +-
 net/ipv4/netfilter/nf_reject_ipv4.c        |  2 +-
 net/ipv6/netfilter/nf_reject_ipv6.c        |  2 +-
 net/netfilter/ipset/ip_set_hash_netiface.c |  8 ++++----
 net/netfilter/nf_log_syslog.c              | 13 +++++++------
 net/netfilter/nf_queue.c                   |  2 +-
 net/netfilter/xt_physdev.c                 |  2 +-
 7 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index f980edfdd2783..e927b9a15a556 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -56,7 +56,7 @@ static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
 }
 
 static inline struct net_device *
-nf_bridge_get_physindev(const struct sk_buff *skb)
+nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net)
 {
 	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index f01b038fc1cda..86e7d390671af 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -289,7 +289,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb);
+	br_indev = nf_bridge_get_physindev(oldskb, net);
 	if (br_indev) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
 
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index d45bc54b7ea55..27b2164f4c439 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -354,7 +354,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb);
+	br_indev = nf_bridge_get_physindev(oldskb, net);
 	if (br_indev) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
 
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 95aeb31c60e0d..30a655e5c4fdc 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -138,9 +138,9 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next,
 #include "ip_set_hash_gen.h"
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-static const char *get_physindev_name(const struct sk_buff *skb)
+static const char *get_physindev_name(const struct sk_buff *skb, struct net *net)
 {
-	struct net_device *dev = nf_bridge_get_physindev(skb);
+	struct net_device *dev = nf_bridge_get_physindev(skb, net);
 
 	return dev ? dev->name : NULL;
 }
@@ -177,7 +177,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const char *eiface = SRCDIR ? get_physindev_name(skb) :
+		const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) :
 					      get_physoutdev_name(skb);
 
 		if (!eiface)
@@ -395,7 +395,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const char *eiface = SRCDIR ? get_physindev_name(skb) :
+		const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) :
 					      get_physoutdev_name(skb);
 
 		if (!eiface)
diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c
index c66689ad2b491..58402226045e8 100644
--- a/net/netfilter/nf_log_syslog.c
+++ b/net/netfilter/nf_log_syslog.c
@@ -111,7 +111,8 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf,
 			  unsigned int hooknum, const struct sk_buff *skb,
 			  const struct net_device *in,
 			  const struct net_device *out,
-			  const struct nf_loginfo *loginfo, const char *prefix)
+			  const struct nf_loginfo *loginfo, const char *prefix,
+			  struct net *net)
 {
 	const struct net_device *physoutdev __maybe_unused;
 	const struct net_device *physindev __maybe_unused;
@@ -121,7 +122,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf,
 			in ? in->name : "",
 			out ? out->name : "");
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	physindev = nf_bridge_get_physindev(skb);
+	physindev = nf_bridge_get_physindev(skb, net);
 	if (physindev && in != physindev)
 		nf_log_buf_add(m, "PHYSIN=%s ", physindev->name);
 	physoutdev = nf_bridge_get_physoutdev(skb);
@@ -148,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
-				  prefix);
+				  prefix, net);
 	dump_arp_packet(m, loginfo, skb, skb_network_offset(skb));
 
 	nf_log_buf_close(m);
@@ -845,7 +846,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in,
-				  out, loginfo, prefix);
+				  out, loginfo, prefix, net);
 
 	if (in)
 		dump_mac_header(m, loginfo, skb);
@@ -880,7 +881,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out,
-				  loginfo, prefix);
+				  loginfo, prefix, net);
 
 	if (in)
 		dump_mac_header(m, loginfo, skb);
@@ -916,7 +917,7 @@ static void nf_log_unknown_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
-				  prefix);
+				  prefix, net);
 
 	dump_mac_header(m, loginfo, skb);
 
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 3dfcb3ac5cb44..e2f334f70281f 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -84,7 +84,7 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 	const struct sk_buff *skb = entry->skb;
 
 	if (nf_bridge_info_exists(skb)) {
-		entry->physin = nf_bridge_get_physindev(skb);
+		entry->physin = nf_bridge_get_physindev(skb, entry->state.net);
 		entry->physout = nf_bridge_get_physoutdev(skb);
 	} else {
 		entry->physin = NULL;
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index ec6ed6fda96c5..343e65f377d44 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -59,7 +59,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	    (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
 		return false;
 
-	physdev = nf_bridge_get_physindev(skb);
+	physdev = nf_bridge_get_physindev(skb, xt_net(par));
 	indev = physdev ? physdev->name : NULL;
 
 	if ((info->bitmask & XT_PHYSDEV_OP_ISIN &&
-- 
GitLab


From 9874808878d9eed407e3977fd11fee49de1e1d86 Mon Sep 17 00:00:00 2001
From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Date: Thu, 11 Jan 2024 23:06:40 +0800
Subject: [PATCH 2840/4076] netfilter: bridge: replace physindev with physinif
 in nf_bridge_info

An skb can be added to a neigh->arp_queue while waiting for an arp
reply. Where original skb's skb->dev can be different to neigh's
neigh->dev. For instance in case of bridging dnated skb from one veth to
another, the skb would be added to a neigh->arp_queue of the bridge.

As skb->dev can be reset back to nf_bridge->physindev and used, and as
there is no explicit mechanism that prevents this physindev from been
freed under us (for instance neigh_flush_dev doesn't cleanup skbs from
different device's neigh queue) we can crash on e.g. this stack:

arp_process
  neigh_update
    skb = __skb_dequeue(&neigh->arp_queue)
      neigh_resolve_output(..., skb)
        ...
          br_nf_dev_xmit
            br_nf_pre_routing_finish_bridge_slow
              skb->dev = nf_bridge->physindev
              br_handle_frame_finish

Let's use plain ifindex instead of net_device link. To peek into the
original net_device we will use dev_get_by_index_rcu(). Thus either we
get device and are safe to use it or we don't get it and drop skb.

Fixes: c4e70a87d975 ("netfilter: bridge: rename br_netfilter.c to br_netfilter_hooks.c")
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge.h    |  4 +--
 include/linux/skbuff.h              |  2 +-
 net/bridge/br_netfilter_hooks.c     | 42 +++++++++++++++++++++++------
 net/bridge/br_netfilter_ipv6.c      | 14 +++++++---
 net/ipv4/netfilter/nf_reject_ipv4.c |  9 ++++---
 net/ipv6/netfilter/nf_reject_ipv6.c | 11 +++++---
 6 files changed, 61 insertions(+), 21 deletions(-)

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index e927b9a15a556..743475ca7e9d5 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -42,7 +42,7 @@ static inline int nf_bridge_get_physinif(const struct sk_buff *skb)
 	if (!nf_bridge)
 		return 0;
 
-	return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0;
+	return nf_bridge->physinif;
 }
 
 static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
@@ -60,7 +60,7 @@ nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net)
 {
 	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
-	return nf_bridge ? nf_bridge->physindev : NULL;
+	return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL;
 }
 
 static inline struct net_device *
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a5ae952454c89..2dde34c29203b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -295,7 +295,7 @@ struct nf_bridge_info {
 	u8			bridged_dnat:1;
 	u8			sabotage_in_done:1;
 	__u16			frag_max_size;
-	struct net_device	*physindev;
+	int			physinif;
 
 	/* always valid & non-NULL from FORWARD on, for physdev match */
 	struct net_device	*physoutdev;
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 6adcb45bca75d..ed17208907578 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -279,8 +279,17 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_
 
 		if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) &&
 		    READ_ONCE(neigh->hh.hh_len)) {
+			struct net_device *br_indev;
+
+			br_indev = nf_bridge_get_physindev(skb, net);
+			if (!br_indev) {
+				neigh_release(neigh);
+				goto free_skb;
+			}
+
 			neigh_hh_bridge(&neigh->hh, skb);
-			skb->dev = nf_bridge->physindev;
+			skb->dev = br_indev;
+
 			ret = br_handle_frame_finish(net, sk, skb);
 		} else {
 			/* the neighbour function below overwrites the complete
@@ -352,12 +361,18 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb,
  */
 static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev, *br_indev;
 	struct iphdr *iph = ip_hdr(skb);
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
 	int err;
 
+	br_indev = nf_bridge_get_physindev(skb, net);
+	if (!br_indev) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
 
 	if (nf_bridge->pkt_otherhost) {
@@ -397,7 +412,7 @@ free_skb:
 		} else {
 			if (skb_dst(skb)->dev == dev) {
 bridged_dnat:
-				skb->dev = nf_bridge->physindev;
+				skb->dev = br_indev;
 				nf_bridge_update_protocol(skb);
 				nf_bridge_push_encap_header(skb);
 				br_nf_hook_thresh(NF_BR_PRE_ROUTING,
@@ -410,7 +425,7 @@ bridged_dnat:
 			skb->pkt_type = PACKET_HOST;
 		}
 	} else {
-		rt = bridge_parent_rtable(nf_bridge->physindev);
+		rt = bridge_parent_rtable(br_indev);
 		if (!rt) {
 			kfree_skb(skb);
 			return 0;
@@ -419,7 +434,7 @@ bridged_dnat:
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
 	br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL,
@@ -456,7 +471,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net)
 	}
 
 	nf_bridge->in_prerouting = 1;
-	nf_bridge->physindev = skb->dev;
+	nf_bridge->physinif = skb->dev->ifindex;
 	skb->dev = brnf_get_logical_dev(skb, skb->dev, net);
 
 	if (skb->protocol == htons(ETH_P_8021Q))
@@ -553,7 +568,11 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff
 		if (skb->protocol == htons(ETH_P_IPV6))
 			nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
 
-		in = nf_bridge->physindev;
+		in = nf_bridge_get_physindev(skb, net);
+		if (!in) {
+			kfree_skb(skb);
+			return 0;
+		}
 		if (nf_bridge->pkt_otherhost) {
 			skb->pkt_type = PACKET_OTHERHOST;
 			nf_bridge->pkt_otherhost = false;
@@ -899,6 +918,13 @@ static unsigned int ip_sabotage_in(void *priv,
 static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+	struct net_device *br_indev;
+
+	br_indev = nf_bridge_get_physindev(skb, dev_net(skb->dev));
+	if (!br_indev) {
+		kfree_skb(skb);
+		return;
+	}
 
 	skb_pull(skb, ETH_HLEN);
 	nf_bridge->bridged_dnat = 0;
@@ -908,7 +934,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN),
 				       nf_bridge->neigh_header,
 				       ETH_HLEN - ETH_ALEN);
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 
 	nf_bridge->physoutdev = NULL;
 	br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 2e24a743f9173..e0421eaa3abc7 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -102,9 +102,15 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
-	struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev, *br_indev;
 	const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
 
+	br_indev = nf_bridge_get_physindev(skb, net);
+	if (!br_indev) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
 
 	if (nf_bridge->pkt_otherhost) {
@@ -122,7 +128,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		}
 
 		if (skb_dst(skb)->dev == dev) {
-			skb->dev = nf_bridge->physindev;
+			skb->dev = br_indev;
 			nf_bridge_update_protocol(skb);
 			nf_bridge_push_encap_header(skb);
 			br_nf_hook_thresh(NF_BR_PRE_ROUTING,
@@ -133,7 +139,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
 		skb->pkt_type = PACKET_HOST;
 	} else {
-		rt = bridge_parent_rtable(nf_bridge->physindev);
+		rt = bridge_parent_rtable(br_indev);
 		if (!rt) {
 			kfree_skb(skb);
 			return 0;
@@ -142,7 +148,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
 	br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb,
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 86e7d390671af..04504b2b51df5 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -239,7 +239,6 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in)
 void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		   int hook)
 {
-	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct iphdr *niph;
 	const struct tcphdr *oth;
@@ -289,9 +288,13 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb, net);
-	if (br_indev) {
+	if (nf_bridge_info_exists(oldskb)) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
+		struct net_device *br_indev;
+
+		br_indev = nf_bridge_get_physindev(oldskb, net);
+		if (!br_indev)
+			goto free_nskb;
 
 		nskb->dev = br_indev;
 		niph->tot_len = htons(nskb->len);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 27b2164f4c439..196dd4ecb5e21 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -278,7 +278,6 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
 void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		    int hook)
 {
-	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct tcphdr _otcph;
 	const struct tcphdr *otcph;
@@ -354,9 +353,15 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb, net);
-	if (br_indev) {
+	if (nf_bridge_info_exists(oldskb)) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
+		struct net_device *br_indev;
+
+		br_indev = nf_bridge_get_physindev(oldskb, net);
+		if (!br_indev) {
+			kfree_skb(nskb);
+			return;
+		}
 
 		nskb->dev = br_indev;
 		nskb->protocol = htons(ETH_P_IPV6);
-- 
GitLab


From b1db244ffd041a49ecc9618e8feb6b5c1afcdaa7 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 12 Jan 2024 23:28:45 +0100
Subject: [PATCH 2841/4076] netfilter: nf_tables: check if catch-all set
 element is active in next generation

When deactivating the catch-all set element, check the state in the next
generation that represents this transaction.

This bug uncovered after the recent removal of the element busy mark
a2dd0233cbc4 ("netfilter: nf_tables: remove busy mark and gc batch API").

Fixes: aaa31047a6d2 ("netfilter: nftables: add catch-all set element support")
Cc: stable@vger.kernel.org
Reported-by: lonial con <kongln9170@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b3db97440db15..50b595ef63892 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6578,7 +6578,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net,
 
 	list_for_each_entry(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
-		if (!nft_is_active(net, ext))
+		if (!nft_is_active_next(net, ext))
 			continue;
 
 		kfree(elem->priv);
-- 
GitLab


From 3ce67e3793f48c1b9635beb9bb71116ca1e51b58 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sun, 14 Jan 2024 23:53:39 +0100
Subject: [PATCH 2842/4076] netfilter: nf_tables: do not allow mismatch field
 size and set key length

The set description provides the size of each field in the set whose sum
should not mismatch the set key length, bail out otherwise.

I did not manage to crash nft_set_pipapo with mismatch fields and set key
length so far, but this is UB which must be disallowed.

Fixes: f3a2181e16f1 ("netfilter: nf_tables: Support for sets with multiple ranged fields")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 50b595ef63892..e9fa4a32c0939 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4813,8 +4813,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr,
 static int nft_set_desc_concat(struct nft_set_desc *desc,
 			       const struct nlattr *nla)
 {
+	u32 num_regs = 0, key_num_regs = 0;
 	struct nlattr *attr;
-	u32 num_regs = 0;
 	int rem, err, i;
 
 	nla_for_each_nested(attr, nla, rem) {
@@ -4829,6 +4829,10 @@ static int nft_set_desc_concat(struct nft_set_desc *desc,
 	for (i = 0; i < desc->field_count; i++)
 		num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32));
 
+	key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32));
+	if (key_num_regs != num_regs)
+		return -EINVAL;
+
 	if (num_regs > NFT_REG32_COUNT)
 		return -E2BIG;
 
-- 
GitLab


From 6b1ca88e4bb63673dc9f9c7f23c899f22c3cb17a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 15 Jan 2024 00:14:38 +0100
Subject: [PATCH 2843/4076] netfilter: nf_tables: skip dead set elements in
 netlink dump

Delete from packet path relies on the garbage collector to purge
elements with NFT_SET_ELEM_DEAD_BIT on.

Skip these dead elements from nf_tables_dump_setelem() path, I very
rarely see tests/shell/testcases/maps/typeof_maps_add_delete reports
[DUMP FAILED] showing a mismatch in the expected output with an element
that should not be there.

If the netlink dump happens before GC worker run, it might show dead
elements in the ruleset listing.

nft_rhash_get() already skips dead elements in nft_rhash_cmp(),
therefore, it already does not show the element when getting a single
element via netlink control plane.

Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index e9fa4a32c0939..88a6a858383b6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5718,7 +5718,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
 	struct nft_set_dump_args *args;
 
-	if (nft_set_elem_expired(ext))
+	if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext))
 		return 0;
 
 	args = container_of(iter, struct nft_set_dump_args, iter);
-- 
GitLab


From 113661e07460a6604aacc8ae1b23695a89e7d4b3 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 15 Jan 2024 12:50:29 +0100
Subject: [PATCH 2844/4076] netfilter: nf_tables: reject NFT_SET_CONCAT with
 not field length description

It is still possible to set on the NFT_SET_CONCAT flag by specifying a
set size and no field description, report EINVAL in such case.

Fixes: 1b6345d4160e ("netfilter: nf_tables: check NFT_SET_CONCAT flag if field_count is specified")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 88a6a858383b6..4b55533ce5ca2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5070,8 +5070,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 		if (err < 0)
 			return err;
 
-		if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT))
+		if (desc.field_count > 1) {
+			if (!(flags & NFT_SET_CONCAT))
+				return -EINVAL;
+		} else if (flags & NFT_SET_CONCAT) {
 			return -EINVAL;
+		}
 	} else if (flags & NFT_SET_CONCAT) {
 		return -EINVAL;
 	}
-- 
GitLab


From d6938c1c76c64f42363d0d1f051e1b4641c2ad40 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 15 Jan 2024 17:39:22 +0300
Subject: [PATCH 2845/4076] ipvs: avoid stat macros calls from preemptible
 context

Inside decrement_ttl() upon discovering that the packet ttl has exceeded,
__IP_INC_STATS and __IP6_INC_STATS macros can be called from preemptible
context having the following backtrace:

check_preemption_disabled: 48 callbacks suppressed
BUG: using __this_cpu_add() in preemptible [00000000] code: curl/1177
caller is decrement_ttl+0x217/0x830
CPU: 5 PID: 1177 Comm: curl Not tainted 6.7.0+ #34
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0xbd/0xe0
 check_preemption_disabled+0xd1/0xe0
 decrement_ttl+0x217/0x830
 __ip_vs_get_out_rt+0x4e0/0x1ef0
 ip_vs_nat_xmit+0x205/0xcd0
 ip_vs_in_hook+0x9b1/0x26a0
 nf_hook_slow+0xc2/0x210
 nf_hook+0x1fb/0x770
 __ip_local_out+0x33b/0x640
 ip_local_out+0x2a/0x490
 __ip_queue_xmit+0x990/0x1d10
 __tcp_transmit_skb+0x288b/0x3d10
 tcp_connect+0x3466/0x5180
 tcp_v4_connect+0x1535/0x1bb0
 __inet_stream_connect+0x40d/0x1040
 inet_stream_connect+0x57/0xa0
 __sys_connect_file+0x162/0x1a0
 __sys_connect+0x137/0x160
 __x64_sys_connect+0x72/0xb0
 do_syscall_64+0x6f/0x140
 entry_SYSCALL_64_after_hwframe+0x6e/0x76
RIP: 0033:0x7fe6dbbc34e0

Use the corresponding preemption-aware variants: IP_INC_STATS and
IP6_INC_STATS.

Found by Linux Verification Center (linuxtesting.org).

Fixes: 8d8e20e2d7bb ("ipvs: Decrement ttl")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Acked-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipvs/ip_vs_xmit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 9193e109e6b38..65e0259178da4 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -271,7 +271,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 			skb->dev = dst->dev;
 			icmpv6_send(skb, ICMPV6_TIME_EXCEED,
 				    ICMPV6_EXC_HOPLIMIT, 0);
-			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 
 			return false;
 		}
@@ -286,7 +286,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 	{
 		if (ip_hdr(skb)->ttl <= 1) {
 			/* Tell the sender its packet died... */
-			__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
+			IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
 			icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
 			return false;
 		}
-- 
GitLab


From 8f54fca3f8fce49c2d5f4ec4b7c325d1e50916df Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Thu, 4 Jan 2024 16:01:30 +0100
Subject: [PATCH 2846/4076] s390/net: add Thorsten Winkler as maintainer

Thank you Wenjia for your support, welcome Thorsten!

Acked-by: Wenjia Zhang <wenjia@linux.ibm.com>
Acked-by: Thorsten Winkler <twinkler@linux.ibm.com>
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index cc92b10a4cada..20396600f86a2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18962,7 +18962,7 @@ F:	drivers/iommu/s390-iommu.c
 
 S390 IUCV NETWORK LAYER
 M:	Alexandra Winter <wintera@linux.ibm.com>
-M:	Wenjia Zhang <wenjia@linux.ibm.com>
+M:	Thorsten Winkler <twinkler@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -18981,7 +18981,7 @@ F:	arch/s390/mm
 
 S390 NETWORK DRIVERS
 M:	Alexandra Winter <wintera@linux.ibm.com>
-M:	Wenjia Zhang <wenjia@linux.ibm.com>
+M:	Thorsten Winkler <twinkler@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
-- 
GitLab


From 850fb7fa8c684a4c6bf0e4b6978f4ddcc5d43d11 Mon Sep 17 00:00:00 2001
From: Tony Krowiak <akrowiak@linux.ibm.com>
Date: Mon, 15 Jan 2024 13:54:31 -0500
Subject: [PATCH 2847/4076] s390/vfio-ap: always filter entire AP matrix

The vfio_ap_mdev_filter_matrix function is called whenever a new adapter or
domain is assigned to the mdev. The purpose of the function is to update
the guest's AP configuration by filtering the matrix of adapters and
domains assigned to the mdev. When an adapter or domain is assigned, only
the APQNs associated with the APID of the new adapter or APQI of the new
domain are inspected. If an APQN does not reference a queue device bound to
the vfio_ap device driver, then it's APID will be filtered from the mdev's
matrix when updating the guest's AP configuration.

Inspecting only the APID of the new adapter or APQI of the new domain will
result in passing AP queues through to a guest that are not bound to the
vfio_ap device driver under certain circumstances. Consider the following:

guest's AP configuration (all also assigned to the mdev's matrix):
14.0004
14.0005
14.0006
16.0004
16.0005
16.0006

unassign domain 4
unbind queue 16.0005
assign domain 4

When domain 4 is re-assigned, since only domain 4 will be inspected, the
APQNs that will be examined will be:
14.0004
16.0004

Since both of those APQNs reference queue devices that are bound to the
vfio_ap device driver, nothing will get filtered from the mdev's matrix
when updating the guest's AP configuration. Consequently, queue 16.0005
will get passed through despite not being bound to the driver. This
violates the linux device model requirement that a guest shall only be
given access to devices bound to the device driver facilitating their
pass-through.

To resolve this problem, every adapter and domain assigned to the mdev will
be inspected when filtering the mdev's matrix.

Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Acked-by: Halil Pasic <pasic@linux.ibm.com>
Fixes: 48cae940c31d ("s390/vfio-ap: refresh guest's APCB by filtering AP resources assigned to mdev")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240115185441.31526-2-akrowiak@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 drivers/s390/crypto/vfio_ap_ops.c | 57 +++++++++----------------------
 1 file changed, 17 insertions(+), 40 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index acb710d3d7bcd..1f7a6c1067868 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -674,8 +674,7 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev)
  * Return: a boolean value indicating whether the KVM guest's APCB was changed
  *	   by the filtering or not.
  */
-static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
-				       struct ap_matrix_mdev *matrix_mdev)
+static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev)
 {
 	unsigned long apid, apqi, apqn;
 	DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES);
@@ -696,8 +695,8 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
 	bitmap_and(matrix_mdev->shadow_apcb.aqm, matrix_mdev->matrix.aqm,
 		   (unsigned long *)matrix_dev->info.aqm, AP_DOMAINS);
 
-	for_each_set_bit_inv(apid, apm, AP_DEVICES) {
-		for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) {
+	for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, AP_DEVICES) {
+		for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, AP_DOMAINS) {
 			/*
 			 * If the APQN is not bound to the vfio_ap device
 			 * driver, then we can't assign it to the guest's
@@ -962,7 +961,6 @@ static ssize_t assign_adapter_store(struct device *dev,
 {
 	int ret;
 	unsigned long apid;
-	DECLARE_BITMAP(apm_delta, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 
 	mutex_lock(&ap_perms_mutex);
@@ -991,11 +989,8 @@ static ssize_t assign_adapter_store(struct device *dev,
 	}
 
 	vfio_ap_mdev_link_adapter(matrix_mdev, apid);
-	memset(apm_delta, 0, sizeof(apm_delta));
-	set_bit_inv(apid, apm_delta);
 
-	if (vfio_ap_mdev_filter_matrix(apm_delta,
-				       matrix_mdev->matrix.aqm, matrix_mdev))
+	if (vfio_ap_mdev_filter_matrix(matrix_mdev))
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 
 	ret = count;
@@ -1171,7 +1166,6 @@ static ssize_t assign_domain_store(struct device *dev,
 {
 	int ret;
 	unsigned long apqi;
-	DECLARE_BITMAP(aqm_delta, AP_DOMAINS);
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 
 	mutex_lock(&ap_perms_mutex);
@@ -1200,11 +1194,8 @@ static ssize_t assign_domain_store(struct device *dev,
 	}
 
 	vfio_ap_mdev_link_domain(matrix_mdev, apqi);
-	memset(aqm_delta, 0, sizeof(aqm_delta));
-	set_bit_inv(apqi, aqm_delta);
 
-	if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, aqm_delta,
-				       matrix_mdev))
+	if (vfio_ap_mdev_filter_matrix(matrix_mdev))
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 
 	ret = count;
@@ -2109,9 +2100,7 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 	if (matrix_mdev) {
 		vfio_ap_mdev_link_queue(matrix_mdev, q);
 
-		if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm,
-					       matrix_mdev->matrix.aqm,
-					       matrix_mdev))
+		if (vfio_ap_mdev_filter_matrix(matrix_mdev))
 			vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 	dev_set_drvdata(&apdev->device, q);
@@ -2461,34 +2450,22 @@ void vfio_ap_on_cfg_changed(struct ap_config_info *cur_cfg_info,
 
 static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev)
 {
-	bool do_hotplug = false;
-	int filter_domains = 0;
-	int filter_adapters = 0;
-	DECLARE_BITMAP(apm, AP_DEVICES);
-	DECLARE_BITMAP(aqm, AP_DOMAINS);
+	bool filter_domains, filter_adapters, filter_cdoms, do_hotplug = false;
 
 	mutex_lock(&matrix_mdev->kvm->lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
 
-	filter_adapters = bitmap_and(apm, matrix_mdev->matrix.apm,
-				     matrix_mdev->apm_add, AP_DEVICES);
-	filter_domains = bitmap_and(aqm, matrix_mdev->matrix.aqm,
-				    matrix_mdev->aqm_add, AP_DOMAINS);
-
-	if (filter_adapters && filter_domains)
-		do_hotplug |= vfio_ap_mdev_filter_matrix(apm, aqm, matrix_mdev);
-	else if (filter_adapters)
-		do_hotplug |=
-			vfio_ap_mdev_filter_matrix(apm,
-						   matrix_mdev->shadow_apcb.aqm,
-						   matrix_mdev);
-	else
-		do_hotplug |=
-			vfio_ap_mdev_filter_matrix(matrix_mdev->shadow_apcb.apm,
-						   aqm, matrix_mdev);
+	filter_adapters = bitmap_intersects(matrix_mdev->matrix.apm,
+					    matrix_mdev->apm_add, AP_DEVICES);
+	filter_domains = bitmap_intersects(matrix_mdev->matrix.aqm,
+					   matrix_mdev->aqm_add, AP_DOMAINS);
+	filter_cdoms = bitmap_intersects(matrix_mdev->matrix.adm,
+					 matrix_mdev->adm_add, AP_DOMAINS);
+
+	if (filter_adapters || filter_domains)
+		do_hotplug = vfio_ap_mdev_filter_matrix(matrix_mdev);
 
-	if (bitmap_intersects(matrix_mdev->matrix.adm, matrix_mdev->adm_add,
-			      AP_DOMAINS))
+	if (filter_cdoms)
 		do_hotplug |= vfio_ap_mdev_filter_cdoms(matrix_mdev);
 
 	if (do_hotplug)
-- 
GitLab


From 16fb78cbf56e42b8efb2682a4444ab59e32e7959 Mon Sep 17 00:00:00 2001
From: Tony Krowiak <akrowiak@linux.ibm.com>
Date: Mon, 15 Jan 2024 13:54:32 -0500
Subject: [PATCH 2848/4076] s390/vfio-ap: loop over the shadow APCB when
 filtering guest's AP configuration

While filtering the mdev matrix, it doesn't make sense - and will have
unexpected results - to filter an APID from the matrix if the APID or one
of the associated APQIs is not in the host's AP configuration. There are
two reasons for this:

1. An adapter or domain that is not in the host's AP configuration can be
   assigned to the matrix; this is known as over-provisioning. Queue
   devices, however, are only created for adapters and domains in the
   host's AP configuration, so there will be no queues associated with an
   over-provisioned adapter or domain to filter.

2. The adapter or domain may have been externally removed from the host's
   configuration via an SE or HMC attached to a DPM enabled LPAR. In this
   case, the vfio_ap device driver would have been notified by the AP bus
   via the on_config_changed callback and the adapter or domain would
   have already been filtered.

Since the matrix_mdev->shadow_apcb.apm and matrix_mdev->shadow_apcb.aqm are
copied from the mdev matrix sans the APIDs and APQIs not in the host's AP
configuration, let's loop over those bitmaps instead of those assigned to
the matrix.

Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Fixes: 48cae940c31d ("s390/vfio-ap: refresh guest's APCB by filtering AP resources assigned to mdev")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240115185441.31526-3-akrowiak@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 drivers/s390/crypto/vfio_ap_ops.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 1f7a6c1067868..e825e13847fe0 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -695,8 +695,9 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev)
 	bitmap_and(matrix_mdev->shadow_apcb.aqm, matrix_mdev->matrix.aqm,
 		   (unsigned long *)matrix_dev->info.aqm, AP_DOMAINS);
 
-	for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, AP_DEVICES) {
-		for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, AP_DOMAINS) {
+	for_each_set_bit_inv(apid, matrix_mdev->shadow_apcb.apm, AP_DEVICES) {
+		for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm,
+				     AP_DOMAINS) {
 			/*
 			 * If the APQN is not bound to the vfio_ap device
 			 * driver, then we can't assign it to the guest's
-- 
GitLab


From 774d10196e648e2c0b78da817f631edfb3dfa557 Mon Sep 17 00:00:00 2001
From: Tony Krowiak <akrowiak@linux.ibm.com>
Date: Mon, 15 Jan 2024 13:54:33 -0500
Subject: [PATCH 2849/4076] s390/vfio-ap: let on_scan_complete() callback
 filter matrix and update guest's APCB

When adapters and/or domains are added to the host's AP configuration, this
may result in multiple queue devices getting created and probed by the
vfio_ap device driver. For each queue device probed, the matrix of adapters
and domains assigned to a matrix mdev will be filtered to update the
guest's APCB. If any adapters or domains get added to or removed from the
APCB, the guest's AP configuration will be dynamically updated (i.e., hot
plug/unplug). To dynamically update the guest's configuration, its VCPUs
must be taken out of SIE for the period of time it takes to make the
update. This is disruptive to the guest's operation and if there are many
queues probed due to a change in the host's AP configuration, this could be
troublesome. The problem is exacerbated by the fact that the
'on_scan_complete' callback also filters the mdev's matrix and updates
the guest's AP configuration.

In order to reduce the potential amount of disruption to the guest that may
result from a change to the host's AP configuration, let's bypass the
filtering of the matrix and updating of the guest's AP configuration in the
probe callback - if due to a host config change - and defer it until the
'on_scan_complete' callback is invoked after the AP bus finishes its device
scan operation. This way the filtering and updating will be performed only
once regardless of the number of queues added.

Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Fixes: 48cae940c31d ("s390/vfio-ap: refresh guest's APCB by filtering AP resources assigned to mdev")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240115185441.31526-4-akrowiak@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 drivers/s390/crypto/vfio_ap_ops.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index e825e13847fe0..e45d0bf7b126e 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -2101,9 +2101,22 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 	if (matrix_mdev) {
 		vfio_ap_mdev_link_queue(matrix_mdev, q);
 
+		/*
+		 * If we're in the process of handling the adding of adapters or
+		 * domains to the host's AP configuration, then let the
+		 * vfio_ap device driver's on_scan_complete callback filter the
+		 * matrix and update the guest's AP configuration after all of
+		 * the new queue devices are probed.
+		 */
+		if (!bitmap_empty(matrix_mdev->apm_add, AP_DEVICES) ||
+		    !bitmap_empty(matrix_mdev->aqm_add, AP_DOMAINS))
+			goto done;
+
 		if (vfio_ap_mdev_filter_matrix(matrix_mdev))
 			vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
+
+done:
 	dev_set_drvdata(&apdev->device, q);
 	release_update_locks_for_mdev(matrix_mdev);
 
-- 
GitLab


From f848cba767e59f8d5c54984b1d45451aae040d50 Mon Sep 17 00:00:00 2001
From: Tony Krowiak <akrowiak@linux.ibm.com>
Date: Mon, 15 Jan 2024 13:54:34 -0500
Subject: [PATCH 2850/4076] s390/vfio-ap: reset queues filtered from the
 guest's AP config

When filtering the adapters from the configuration profile for a guest to
create or update a guest's AP configuration, if the APID of an adapter and
the APQI of a domain identify a queue device that is not bound to the
vfio_ap device driver, the APID of the adapter will be filtered because an
individual APQN can not be filtered due to the fact the APQNs are assigned
to an AP configuration as a matrix of APIDs and APQIs. Consequently, a
guest will not have access to all of the queues associated with the
filtered adapter. If the queues are subsequently made available again to
the guest, they should re-appear in a reset state; so, let's make sure all
queues associated with an adapter unplugged from the guest are reset.

In order to identify the set of queues that need to be reset, let's allow a
vfio_ap_queue object to be simultaneously stored in both a hashtable and a
list: A hashtable used to store all of the queues assigned
to a matrix mdev; and/or, a list used to store a subset of the queues that
need to be reset. For example, when an adapter is hot unplugged from a
guest, all guest queues associated with that adapter must be reset. Since
that may be a subset of those assigned to the matrix mdev, they can be
stored in a list that can be passed to the vfio_ap_mdev_reset_queues
function.

Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Acked-by: Halil Pasic <pasic@linux.ibm.com>
Fixes: 48cae940c31d ("s390/vfio-ap: refresh guest's APCB by filtering AP resources assigned to mdev")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240115185441.31526-5-akrowiak@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 drivers/s390/crypto/vfio_ap_ops.c     | 171 +++++++++++++++++++-------
 drivers/s390/crypto/vfio_ap_private.h |   3 +
 2 files changed, 129 insertions(+), 45 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index e45d0bf7b126e..44cd29aace8ec 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -32,7 +32,8 @@
 
 #define AP_RESET_INTERVAL		20	/* Reset sleep interval (20ms)		*/
 
-static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable);
+static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev);
+static int vfio_ap_mdev_reset_qlist(struct list_head *qlist);
 static struct vfio_ap_queue *vfio_ap_find_queue(int apqn);
 static const struct vfio_device_ops vfio_ap_matrix_dev_ops;
 static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q);
@@ -665,16 +666,23 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev)
  *				device driver.
  *
  * @matrix_mdev: the matrix mdev whose matrix is to be filtered.
+ * @apm_filtered: a 256-bit bitmap for storing the APIDs filtered from the
+ *		  guest's AP configuration that are still in the host's AP
+ *		  configuration.
  *
  * Note: If an APQN referencing a queue device that is not bound to the vfio_ap
  *	 driver, its APID will be filtered from the guest's APCB. The matrix
  *	 structure precludes filtering an individual APQN, so its APID will be
- *	 filtered.
+ *	 filtered. Consequently, all queues associated with the adapter that
+ *	 are in the host's AP configuration must be reset. If queues are
+ *	 subsequently made available again to the guest, they should re-appear
+ *	 in a reset state
  *
  * Return: a boolean value indicating whether the KVM guest's APCB was changed
  *	   by the filtering or not.
  */
-static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev)
+static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev,
+				       unsigned long *apm_filtered)
 {
 	unsigned long apid, apqi, apqn;
 	DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES);
@@ -684,6 +692,7 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev)
 	bitmap_copy(prev_shadow_apm, matrix_mdev->shadow_apcb.apm, AP_DEVICES);
 	bitmap_copy(prev_shadow_aqm, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS);
 	vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->shadow_apcb);
+	bitmap_clear(apm_filtered, 0, AP_DEVICES);
 
 	/*
 	 * Copy the adapters, domains and control domains to the shadow_apcb
@@ -709,8 +718,16 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev)
 			apqn = AP_MKQID(apid, apqi);
 			q = vfio_ap_mdev_get_queue(matrix_mdev, apqn);
 			if (!q || q->reset_status.response_code) {
-				clear_bit_inv(apid,
-					      matrix_mdev->shadow_apcb.apm);
+				clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
+
+				/*
+				 * If the adapter was previously plugged into
+				 * the guest, let's let the caller know that
+				 * the APID was filtered.
+				 */
+				if (test_bit_inv(apid, prev_shadow_apm))
+					set_bit_inv(apid, apm_filtered);
+
 				break;
 			}
 		}
@@ -812,7 +829,7 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev)
 
 	mutex_lock(&matrix_dev->guests_lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
-	vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+	vfio_ap_mdev_reset_queues(matrix_mdev);
 	vfio_ap_mdev_unlink_fr_queues(matrix_mdev);
 	list_del(&matrix_mdev->node);
 	mutex_unlock(&matrix_dev->mdevs_lock);
@@ -922,6 +939,47 @@ static void vfio_ap_mdev_link_adapter(struct ap_matrix_mdev *matrix_mdev,
 				       AP_MKQID(apid, apqi));
 }
 
+static int reset_queues_for_apids(struct ap_matrix_mdev *matrix_mdev,
+				  unsigned long *apm_reset)
+{
+	struct vfio_ap_queue *q, *tmpq;
+	struct list_head qlist;
+	unsigned long apid, apqi;
+	int apqn, ret = 0;
+
+	if (bitmap_empty(apm_reset, AP_DEVICES))
+		return 0;
+
+	INIT_LIST_HEAD(&qlist);
+
+	for_each_set_bit_inv(apid, apm_reset, AP_DEVICES) {
+		for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm,
+				     AP_DOMAINS) {
+			/*
+			 * If the domain is not in the host's AP configuration,
+			 * then resetting it will fail with response code 01
+			 * (APQN not valid).
+			 */
+			if (!test_bit_inv(apqi,
+					  (unsigned long *)matrix_dev->info.aqm))
+				continue;
+
+			apqn = AP_MKQID(apid, apqi);
+			q = vfio_ap_mdev_get_queue(matrix_mdev, apqn);
+
+			if (q)
+				list_add_tail(&q->reset_qnode, &qlist);
+		}
+	}
+
+	ret = vfio_ap_mdev_reset_qlist(&qlist);
+
+	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode)
+		list_del(&q->reset_qnode);
+
+	return ret;
+}
+
 /**
  * assign_adapter_store - parses the APID from @buf and sets the
  * corresponding bit in the mediated matrix device's APM
@@ -962,6 +1020,7 @@ static ssize_t assign_adapter_store(struct device *dev,
 {
 	int ret;
 	unsigned long apid;
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 
 	mutex_lock(&ap_perms_mutex);
@@ -991,8 +1050,10 @@ static ssize_t assign_adapter_store(struct device *dev,
 
 	vfio_ap_mdev_link_adapter(matrix_mdev, apid);
 
-	if (vfio_ap_mdev_filter_matrix(matrix_mdev))
+	if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+		reset_queues_for_apids(matrix_mdev, apm_filtered);
+	}
 
 	ret = count;
 done:
@@ -1023,11 +1084,12 @@ static struct vfio_ap_queue
  *				 adapter was assigned.
  * @matrix_mdev: the matrix mediated device to which the adapter was assigned.
  * @apid: the APID of the unassigned adapter.
- * @qtable: table for storing queues associated with unassigned adapter.
+ * @qlist: list for storing queues associated with unassigned adapter that
+ *	   need to be reset.
  */
 static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 					unsigned long apid,
-					struct ap_queue_table *qtable)
+					struct list_head *qlist)
 {
 	unsigned long apqi;
 	struct vfio_ap_queue *q;
@@ -1035,11 +1097,10 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 	for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, AP_DOMAINS) {
 		q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi);
 
-		if (q && qtable) {
+		if (q && qlist) {
 			if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 			    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm))
-				hash_add(qtable->queues, &q->mdev_qnode,
-					 q->apqn);
+				list_add_tail(&q->reset_qnode, qlist);
 		}
 	}
 }
@@ -1047,26 +1108,23 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev,
 					    unsigned long apid)
 {
-	int loop_cursor;
-	struct vfio_ap_queue *q;
-	struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL);
+	struct vfio_ap_queue *q, *tmpq;
+	struct list_head qlist;
 
-	hash_init(qtable->queues);
-	vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, qtable);
+	INIT_LIST_HEAD(&qlist);
+	vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, &qlist);
 
 	if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm)) {
 		clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 
-	vfio_ap_mdev_reset_queues(qtable);
+	vfio_ap_mdev_reset_qlist(&qlist);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) {
 		vfio_ap_unlink_mdev_fr_queue(q);
-		hash_del(&q->mdev_qnode);
+		list_del(&q->reset_qnode);
 	}
-
-	kfree(qtable);
 }
 
 /**
@@ -1167,6 +1225,7 @@ static ssize_t assign_domain_store(struct device *dev,
 {
 	int ret;
 	unsigned long apqi;
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 
 	mutex_lock(&ap_perms_mutex);
@@ -1196,8 +1255,10 @@ static ssize_t assign_domain_store(struct device *dev,
 
 	vfio_ap_mdev_link_domain(matrix_mdev, apqi);
 
-	if (vfio_ap_mdev_filter_matrix(matrix_mdev))
+	if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+		reset_queues_for_apids(matrix_mdev, apm_filtered);
+	}
 
 	ret = count;
 done:
@@ -1210,7 +1271,7 @@ static DEVICE_ATTR_WO(assign_domain);
 
 static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 				       unsigned long apqi,
-				       struct ap_queue_table *qtable)
+				       struct list_head *qlist)
 {
 	unsigned long apid;
 	struct vfio_ap_queue *q;
@@ -1218,11 +1279,10 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 	for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, AP_DEVICES) {
 		q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi);
 
-		if (q && qtable) {
+		if (q && qlist) {
 			if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 			    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm))
-				hash_add(qtable->queues, &q->mdev_qnode,
-					 q->apqn);
+				list_add_tail(&q->reset_qnode, qlist);
 		}
 	}
 }
@@ -1230,26 +1290,23 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev,
 					   unsigned long apqi)
 {
-	int loop_cursor;
-	struct vfio_ap_queue *q;
-	struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL);
+	struct vfio_ap_queue *q, *tmpq;
+	struct list_head qlist;
 
-	hash_init(qtable->queues);
-	vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, qtable);
+	INIT_LIST_HEAD(&qlist);
+	vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, &qlist);
 
 	if (test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
 		clear_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm);
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 
-	vfio_ap_mdev_reset_queues(qtable);
+	vfio_ap_mdev_reset_qlist(&qlist);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) {
 		vfio_ap_unlink_mdev_fr_queue(q);
-		hash_del(&q->mdev_qnode);
+		list_del(&q->reset_qnode);
 	}
-
-	kfree(qtable);
 }
 
 /**
@@ -1604,7 +1661,7 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 		get_update_locks_for_kvm(kvm);
 
 		kvm_arch_crypto_clear_masks(kvm);
-		vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+		vfio_ap_mdev_reset_queues(matrix_mdev);
 		kvm_put_kvm(kvm);
 		matrix_mdev->kvm = NULL;
 
@@ -1740,15 +1797,33 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q)
 	}
 }
 
-static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable)
+static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev)
 {
 	int ret = 0, loop_cursor;
 	struct vfio_ap_queue *q;
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode)
+	hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode)
 		vfio_ap_mdev_reset_queue(q);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode) {
+		flush_work(&q->reset_work);
+
+		if (q->reset_status.response_code)
+			ret = -EIO;
+	}
+
+	return ret;
+}
+
+static int vfio_ap_mdev_reset_qlist(struct list_head *qlist)
+{
+	int ret = 0;
+	struct vfio_ap_queue *q;
+
+	list_for_each_entry(q, qlist, reset_qnode)
+		vfio_ap_mdev_reset_queue(q);
+
+	list_for_each_entry(q, qlist, reset_qnode) {
 		flush_work(&q->reset_work);
 
 		if (q->reset_status.response_code)
@@ -1934,7 +2009,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev,
 		ret = vfio_ap_mdev_get_device_info(arg);
 		break;
 	case VFIO_DEVICE_RESET:
-		ret = vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+		ret = vfio_ap_mdev_reset_queues(matrix_mdev);
 		break;
 	case VFIO_DEVICE_GET_IRQ_INFO:
 			ret = vfio_ap_get_irq_info(arg);
@@ -2080,6 +2155,7 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 {
 	int ret;
 	struct vfio_ap_queue *q;
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev;
 
 	ret = sysfs_create_group(&apdev->device.kobj, &vfio_queue_attr_group);
@@ -2112,15 +2188,17 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 		    !bitmap_empty(matrix_mdev->aqm_add, AP_DOMAINS))
 			goto done;
 
-		if (vfio_ap_mdev_filter_matrix(matrix_mdev))
+		if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 			vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+			reset_queues_for_apids(matrix_mdev, apm_filtered);
+		}
 	}
 
 done:
 	dev_set_drvdata(&apdev->device, q);
 	release_update_locks_for_mdev(matrix_mdev);
 
-	return 0;
+	return ret;
 
 err_remove_group:
 	sysfs_remove_group(&apdev->device.kobj, &vfio_queue_attr_group);
@@ -2464,6 +2542,7 @@ void vfio_ap_on_cfg_changed(struct ap_config_info *cur_cfg_info,
 
 static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev)
 {
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	bool filter_domains, filter_adapters, filter_cdoms, do_hotplug = false;
 
 	mutex_lock(&matrix_mdev->kvm->lock);
@@ -2477,7 +2556,7 @@ static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev)
 					 matrix_mdev->adm_add, AP_DOMAINS);
 
 	if (filter_adapters || filter_domains)
-		do_hotplug = vfio_ap_mdev_filter_matrix(matrix_mdev);
+		do_hotplug = vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered);
 
 	if (filter_cdoms)
 		do_hotplug |= vfio_ap_mdev_filter_cdoms(matrix_mdev);
@@ -2485,6 +2564,8 @@ static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev)
 	if (do_hotplug)
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 
+	reset_queues_for_apids(matrix_mdev, apm_filtered);
+
 	mutex_unlock(&matrix_dev->mdevs_lock);
 	mutex_unlock(&matrix_mdev->kvm->lock);
 }
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index 88aff8b81f2fc..98d37aa27044a 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -133,6 +133,8 @@ struct ap_matrix_mdev {
  * @apqn: the APQN of the AP queue device
  * @saved_isc: the guest ISC registered with the GIB interface
  * @mdev_qnode: allows the vfio_ap_queue struct to be added to a hashtable
+ * @reset_qnode: allows the vfio_ap_queue struct to be added to a list of queues
+ *		 that need to be reset
  * @reset_status: the status from the last reset of the queue
  * @reset_work: work to wait for queue reset to complete
  */
@@ -143,6 +145,7 @@ struct vfio_ap_queue {
 #define VFIO_AP_ISC_INVALID 0xff
 	unsigned char saved_isc;
 	struct hlist_node mdev_qnode;
+	struct list_head reset_qnode;
 	struct ap_queue_status reset_status;
 	struct work_struct reset_work;
 };
-- 
GitLab


From f009cfa466558b7dfe97f167ba1875d6f9ea4c07 Mon Sep 17 00:00:00 2001
From: Tony Krowiak <akrowiak@linux.ibm.com>
Date: Mon, 15 Jan 2024 13:54:35 -0500
Subject: [PATCH 2851/4076] s390/vfio-ap: reset queues associated with adapter
 for queue unbound from driver

When a queue is unbound from the vfio_ap device driver, if that queue is
assigned to a guest's AP configuration, its associated adapter is removed
because queues are defined to a guest via a matrix of adapters and
domains; so, it is not possible to remove a single queue.

If an adapter is removed from the guest's AP configuration, all associated
queues must be reset to prevent leaking crypto data should any of them be
assigned to a different guest or device driver. The one caveat is that if
the queue is being removed because the adapter or domain has been removed
from the host's AP configuration, then an attempt to reset the queue will
fail with response code 01, AP-queue number not valid; so resetting these
queues should be skipped.

Acked-by: Halil Pasic <pasic@linux.ibm.com>
Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Fixes: 09d31ff78793 ("s390/vfio-ap: hot plug/unplug of AP devices when probed/removed")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240115185441.31526-6-akrowiak@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 drivers/s390/crypto/vfio_ap_ops.c | 76 +++++++++++++++++--------------
 1 file changed, 41 insertions(+), 35 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 44cd29aace8ec..550c936c413db 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -939,45 +939,45 @@ static void vfio_ap_mdev_link_adapter(struct ap_matrix_mdev *matrix_mdev,
 				       AP_MKQID(apid, apqi));
 }
 
+static void collect_queues_to_reset(struct ap_matrix_mdev *matrix_mdev,
+				    unsigned long apid,
+				    struct list_head *qlist)
+{
+	struct vfio_ap_queue *q;
+	unsigned long  apqi;
+
+	for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS) {
+		q = vfio_ap_mdev_get_queue(matrix_mdev, AP_MKQID(apid, apqi));
+		if (q)
+			list_add_tail(&q->reset_qnode, qlist);
+	}
+}
+
+static void reset_queues_for_apid(struct ap_matrix_mdev *matrix_mdev,
+				  unsigned long apid)
+{
+	struct list_head qlist;
+
+	INIT_LIST_HEAD(&qlist);
+	collect_queues_to_reset(matrix_mdev, apid, &qlist);
+	vfio_ap_mdev_reset_qlist(&qlist);
+}
+
 static int reset_queues_for_apids(struct ap_matrix_mdev *matrix_mdev,
 				  unsigned long *apm_reset)
 {
-	struct vfio_ap_queue *q, *tmpq;
 	struct list_head qlist;
-	unsigned long apid, apqi;
-	int apqn, ret = 0;
+	unsigned long apid;
 
 	if (bitmap_empty(apm_reset, AP_DEVICES))
 		return 0;
 
 	INIT_LIST_HEAD(&qlist);
 
-	for_each_set_bit_inv(apid, apm_reset, AP_DEVICES) {
-		for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm,
-				     AP_DOMAINS) {
-			/*
-			 * If the domain is not in the host's AP configuration,
-			 * then resetting it will fail with response code 01
-			 * (APQN not valid).
-			 */
-			if (!test_bit_inv(apqi,
-					  (unsigned long *)matrix_dev->info.aqm))
-				continue;
-
-			apqn = AP_MKQID(apid, apqi);
-			q = vfio_ap_mdev_get_queue(matrix_mdev, apqn);
-
-			if (q)
-				list_add_tail(&q->reset_qnode, &qlist);
-		}
-	}
+	for_each_set_bit_inv(apid, apm_reset, AP_DEVICES)
+		collect_queues_to_reset(matrix_mdev, apid, &qlist);
 
-	ret = vfio_ap_mdev_reset_qlist(&qlist);
-
-	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode)
-		list_del(&q->reset_qnode);
-
-	return ret;
+	return vfio_ap_mdev_reset_qlist(&qlist);
 }
 
 /**
@@ -2217,24 +2217,30 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
 	matrix_mdev = q->matrix_mdev;
 
 	if (matrix_mdev) {
-		vfio_ap_unlink_queue_fr_mdev(q);
-
 		apid = AP_QID_CARD(q->apqn);
 		apqi = AP_QID_QUEUE(q->apqn);
-
-		/*
-		 * If the queue is assigned to the guest's APCB, then remove
-		 * the adapter's APID from the APCB and hot it into the guest.
-		 */
+		/* If the queue is assigned to the guest's AP configuration */
 		if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 		    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
+			/*
+			 * Since the queues are defined via a matrix of adapters
+			 * and domains, it is not possible to hot unplug a
+			 * single queue; so, let's unplug the adapter.
+			 */
 			clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
 			vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+			reset_queues_for_apid(matrix_mdev, apid);
+			goto done;
 		}
 	}
 
 	vfio_ap_mdev_reset_queue(q);
 	flush_work(&q->reset_work);
+
+done:
+	if (matrix_mdev)
+		vfio_ap_unlink_queue_fr_mdev(q);
+
 	dev_set_drvdata(&apdev->device, NULL);
 	kfree(q);
 	release_update_locks_for_mdev(matrix_mdev);
-- 
GitLab


From b9bd10c43456d16abd97b717446f51afb3b88411 Mon Sep 17 00:00:00 2001
From: Tony Krowiak <akrowiak@linux.ibm.com>
Date: Mon, 15 Jan 2024 13:54:36 -0500
Subject: [PATCH 2852/4076] s390/vfio-ap: do not reset queue removed from host
 config

When a queue is unbound from the vfio_ap device driver, it is reset to
ensure its crypto data is not leaked when it is bound to another device
driver. If the queue is unbound due to the fact that the adapter or domain
was removed from the host's AP configuration, then attempting to reset it
will fail with response code 01 (APID not valid) getting returned from the
reset command. Let's ensure that the queue is assigned to the host's
configuration before resetting it.

Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: "Jason J. Herne" <jjherne@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Fixes: eeb386aeb5b7 ("s390/vfio-ap: handle config changed and scan complete notification")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240115185441.31526-7-akrowiak@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 drivers/s390/crypto/vfio_ap_ops.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 550c936c413db..983b3b16196c6 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -2215,10 +2215,10 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
 	q = dev_get_drvdata(&apdev->device);
 	get_update_locks_for_queue(q);
 	matrix_mdev = q->matrix_mdev;
+	apid = AP_QID_CARD(q->apqn);
+	apqi = AP_QID_QUEUE(q->apqn);
 
 	if (matrix_mdev) {
-		apid = AP_QID_CARD(q->apqn);
-		apqi = AP_QID_QUEUE(q->apqn);
 		/* If the queue is assigned to the guest's AP configuration */
 		if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 		    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
@@ -2234,8 +2234,16 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
 		}
 	}
 
-	vfio_ap_mdev_reset_queue(q);
-	flush_work(&q->reset_work);
+	/*
+	 * If the queue is not in the host's AP configuration, then resetting
+	 * it will fail with response code 01, (APQN not valid); so, let's make
+	 * sure it is in the host's config.
+	 */
+	if (test_bit_inv(apid, (unsigned long *)matrix_dev->info.apm) &&
+	    test_bit_inv(apqi, (unsigned long *)matrix_dev->info.aqm)) {
+		vfio_ap_mdev_reset_queue(q);
+		flush_work(&q->reset_work);
+	}
 
 done:
 	if (matrix_mdev)
-- 
GitLab


From 78fbb92af27d0982634116c7a31065f24d092826 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 12 Jan 2024 13:26:57 +0000
Subject: [PATCH 2853/4076] nbd: always initialize struct msghdr completely

syzbot complains that msg->msg_get_inq value can be uninitialized [1]

struct msghdr got many new fields recently, we should always make
sure their values is zero by default.

[1]
 BUG: KMSAN: uninit-value in tcp_recvmsg+0x686/0xac0 net/ipv4/tcp.c:2571
  tcp_recvmsg+0x686/0xac0 net/ipv4/tcp.c:2571
  inet_recvmsg+0x131/0x580 net/ipv4/af_inet.c:879
  sock_recvmsg_nosec net/socket.c:1044 [inline]
  sock_recvmsg+0x12b/0x1e0 net/socket.c:1066
  __sock_xmit+0x236/0x5c0 drivers/block/nbd.c:538
  nbd_read_reply drivers/block/nbd.c:732 [inline]
  recv_work+0x262/0x3100 drivers/block/nbd.c:863
  process_one_work kernel/workqueue.c:2627 [inline]
  process_scheduled_works+0x104e/0x1e70 kernel/workqueue.c:2700
  worker_thread+0xf45/0x1490 kernel/workqueue.c:2781
  kthread+0x3ed/0x540 kernel/kthread.c:388
  ret_from_fork+0x66/0x80 arch/x86/kernel/process.c:147
  ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:242

Local variable msg created at:
  __sock_xmit+0x4c/0x5c0 drivers/block/nbd.c:513
  nbd_read_reply drivers/block/nbd.c:732 [inline]
  recv_work+0x262/0x3100 drivers/block/nbd.c:863

CPU: 1 PID: 7465 Comm: kworker/u5:1 Not tainted 6.7.0-rc7-syzkaller-00041-gf016f7547aee #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
Workqueue: nbd5-recv recv_work

Fixes: f94fd25cb0aa ("tcp: pass back data left in socket after receive")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: stable@vger.kernel.org
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: nbd@other.debian.org
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240112132657.647112-1-edumazet@google.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/nbd.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4e72ec4e25ac5..33a8f37bb6a1f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -508,7 +508,7 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send,
 		       struct iov_iter *iter, int msg_flags, int *sent)
 {
 	int result;
-	struct msghdr msg;
+	struct msghdr msg = {} ;
 	unsigned int noreclaim_flag;
 
 	if (unlikely(!sock)) {
@@ -524,10 +524,6 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send,
 	do {
 		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
 		sock->sk->sk_use_task_frag = false;
-		msg.msg_name = NULL;
-		msg.msg_namelen = 0;
-		msg.msg_control = NULL;
-		msg.msg_controllen = 0;
 		msg.msg_flags = msg_flags | MSG_NOSIGNAL;
 
 		if (send)
-- 
GitLab


From baf59771343dc0c2ef9ac3189bf9df2d6143654f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 16 Jan 2024 17:08:32 -0700
Subject: [PATCH 2854/4076] io_uring/register: guard compat syscall with
 CONFIG_COMPAT

Add compat.h include to avoid a potential build issue:

io_uring/register.c:281:6: error: call to undeclared function 'in_compat_syscall'; ISO C99 and later do not support implicit function declarations [-Werror,-Wimplicit-function-declaration]

if (in_compat_syscall()) {
    ^
1 warning generated.
io_uring/register.c:282:9: error: call to undeclared function 'compat_get_bitmap'; ISO C99 and later do not support implicit function declarations [-Werror,-Wimplicit-function-declaration]
ret = compat_get_bitmap(cpumask_bits(new_mask),
      ^

Fixes: c43203154d8a ("io_uring/register: move io_uring_register(2) related code to register.c")
Reported-by: Manu Bretelle <chantra@meta.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/register.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/io_uring/register.c b/io_uring/register.c
index 708dd1d89add4..5e62c12089965 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/nospec.h>
+#include <linux/compat.h>
 #include <linux/io_uring.h>
 #include <linux/io_uring_types.h>
 
@@ -278,13 +279,14 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
 	if (len > cpumask_size())
 		len = cpumask_size();
 
-	if (in_compat_syscall()) {
+#ifdef CONFIG_COMPAT
+	if (in_compat_syscall())
 		ret = compat_get_bitmap(cpumask_bits(new_mask),
 					(const compat_ulong_t __user *)arg,
 					len * 8 /* CHAR_BIT */);
-	} else {
+	else
+#endif
 		ret = copy_from_user(new_mask, arg, len);
-	}
 
 	if (ret) {
 		free_cpumask_var(new_mask);
-- 
GitLab


From dc12d1799ce710fd90abbe0ced71e7e1ae0894fc Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 17 Jan 2024 00:57:26 +0000
Subject: [PATCH 2855/4076] io_uring: adjust defer tw counting

The UINT_MAX work item counting bias in io_req_local_work_add() in case
of !IOU_F_TWQ_LAZY_WAKE works in a sense that we will not miss a wake up,
however it's still eerie. In particular, if we add a lazy work item
after a non-lazy one, we'll increment it and get nr_tw==0, and
subsequent adds may try to unnecessarily wake up the task, which is
though not so likely to happen in real workloads.

Half the bias, it's still large enough to be larger than any valid
->cq_wait_nr, which is limited by IORING_MAX_CQ_ENTRIES, but further
have a good enough of space before it overflows.

Fixes: 8751d15426a31 ("io_uring: reduce scheduling due to tw")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/108b971e958deaf7048342930c341ba90f75d806.1705438669.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 50c9f04bc193c..d40c767a62163 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1325,7 +1325,7 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 		nr_tw = nr_tw_prev + 1;
 		/* Large enough to fail the nr_wait comparison below */
 		if (!(flags & IOU_F_TWQ_LAZY_WAKE))
-			nr_tw = -1U;
+			nr_tw = INT_MAX;
 
 		req->nr_tw = nr_tw;
 		req->io_task_work.node.next = first;
-- 
GitLab


From d381099f980b5f6c3c7e150baf13b0aaefc66c29 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 17 Jan 2024 00:57:27 +0000
Subject: [PATCH 2856/4076] io_uring: clean up local tw add-wait sync

Kill a smp_mb__after_atomic() right before wake_up, it's useless, and
add a comment explaining implicit barriers from cmpxchg and
synchronsation around ->cq_wait_nr with the waiter.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/3007f3c2d53c72b61de56919ef56b53158b8276f.1705438669.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index d40c767a62163..3ab7e6a46149b 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1332,6 +1332,14 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	} while (!try_cmpxchg(&ctx->work_llist.first, &first,
 			      &req->io_task_work.node));
 
+	/*
+	 * cmpxchg implies a full barrier, which pairs with the barrier
+	 * in set_current_state() on the io_cqring_wait() side. It's used
+	 * to ensure that either we see updated ->cq_wait_nr, or waiters
+	 * going to sleep will observe the work added to the list, which
+	 * is similar to the wait/wawke task state sync.
+	 */
+
 	if (!first) {
 		if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 			atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
@@ -1346,8 +1354,6 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	/* either not enough or the previous add has already woken it up */
 	if (nr_wait > nr_tw || nr_tw_prev >= nr_wait)
 		return;
-	/* pairs with set_current_state() in io_cqring_wait() */
-	smp_mb__after_atomic();
 	wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE);
 }
 
-- 
GitLab


From e8c407717b4814dac5641d93cbbbb9fc394f7cf0 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 17 Jan 2024 00:57:28 +0000
Subject: [PATCH 2857/4076] io_uring: clean *local_work_add var naming

if (!first) { ... }

While it reads as do something if it's not the first entry, it does
exactly the opposite because "first" here is a pointer to the first
entry. Remove the confusion by renaming it into "head".

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/3b8be483b52f58a524185bb88694b8a268e7e85d.1705438669.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 3ab7e6a46149b..3508198d17ba9 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1304,16 +1304,16 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	unsigned nr_wait, nr_tw, nr_tw_prev;
-	struct llist_node *first;
+	struct llist_node *head;
 
 	if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
 		flags &= ~IOU_F_TWQ_LAZY_WAKE;
 
-	first = READ_ONCE(ctx->work_llist.first);
+	head = READ_ONCE(ctx->work_llist.first);
 	do {
 		nr_tw_prev = 0;
-		if (first) {
-			struct io_kiocb *first_req = container_of(first,
+		if (head) {
+			struct io_kiocb *first_req = container_of(head,
 							struct io_kiocb,
 							io_task_work.node);
 			/*
@@ -1328,8 +1328,8 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 			nr_tw = INT_MAX;
 
 		req->nr_tw = nr_tw;
-		req->io_task_work.node.next = first;
-	} while (!try_cmpxchg(&ctx->work_llist.first, &first,
+		req->io_task_work.node.next = head;
+	} while (!try_cmpxchg(&ctx->work_llist.first, &head,
 			      &req->io_task_work.node));
 
 	/*
@@ -1340,7 +1340,7 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	 * is similar to the wait/wawke task state sync.
 	 */
 
-	if (!first) {
+	if (!head) {
 		if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 			atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 		if (ctx->has_evfd)
-- 
GitLab


From b4bc35cf8704db86203c0739711dab1804265bf3 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 17 Jan 2024 00:57:29 +0000
Subject: [PATCH 2858/4076] io_uring: combine cq_wait_nr checks

Instead of explicitly checking ->cq_wait_nr for whether there are
waiting, which is currently represented by 0, we can store there a
large value and the nr_tw will automatically filter out those cases.
Add a named constant for that and for the wake up bias value.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/38def30282654d980673976cd42fde9bab19b297.1705438669.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 34 +++++++++++++++++++++++++++-------
 1 file changed, 27 insertions(+), 7 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 3508198d17ba9..b5fa3c7df1cf8 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -137,6 +137,14 @@ struct io_defer_entry {
 #define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)
 #define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
 
+/*
+ * No waiters. It's larger than any valid value of the tw counter
+ * so that tests against ->cq_wait_nr would fail and skip wake_up().
+ */
+#define IO_CQ_WAKE_INIT		(-1U)
+/* Forced wake up if there is a waiter regardless of ->cq_wait_nr */
+#define IO_CQ_WAKE_FORCE	(IO_CQ_WAKE_INIT >> 1)
+
 static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 					 struct task_struct *task,
 					 bool cancel_all);
@@ -303,6 +311,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 		goto err;
 
 	ctx->flags = p->flags;
+	atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
 	init_waitqueue_head(&ctx->sqo_sq_wait);
 	INIT_LIST_HEAD(&ctx->sqd_list);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
@@ -1306,6 +1315,13 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	unsigned nr_wait, nr_tw, nr_tw_prev;
 	struct llist_node *head;
 
+	/* See comment above IO_CQ_WAKE_INIT */
+	BUILD_BUG_ON(IO_CQ_WAKE_FORCE <= IORING_MAX_CQ_ENTRIES);
+
+	/*
+	 * We don't know how many reuqests is there in the link and whether
+	 * they can even be queued lazily, fall back to non-lazy.
+	 */
 	if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
 		flags &= ~IOU_F_TWQ_LAZY_WAKE;
 
@@ -1322,10 +1338,14 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 			 */
 			nr_tw_prev = READ_ONCE(first_req->nr_tw);
 		}
+
+		/*
+		 * Theoretically, it can overflow, but that's fine as one of
+		 * previous adds should've tried to wake the task.
+		 */
 		nr_tw = nr_tw_prev + 1;
-		/* Large enough to fail the nr_wait comparison below */
 		if (!(flags & IOU_F_TWQ_LAZY_WAKE))
-			nr_tw = INT_MAX;
+			nr_tw = IO_CQ_WAKE_FORCE;
 
 		req->nr_tw = nr_tw;
 		req->io_task_work.node.next = head;
@@ -1348,11 +1368,11 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	}
 
 	nr_wait = atomic_read(&ctx->cq_wait_nr);
-	/* no one is waiting */
-	if (!nr_wait)
+	/* not enough or no one is waiting */
+	if (nr_tw < nr_wait)
 		return;
-	/* either not enough or the previous add has already woken it up */
-	if (nr_wait > nr_tw || nr_tw_prev >= nr_wait)
+	/* the previous add has already woken it up */
+	if (nr_tw_prev >= nr_wait)
 		return;
 	wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE);
 }
@@ -2620,7 +2640,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 		ret = io_cqring_wait_schedule(ctx, &iowq);
 		__set_current_state(TASK_RUNNING);
-		atomic_set(&ctx->cq_wait_nr, 0);
+		atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
 
 		/*
 		 * Run task_work after scheduling and before io_should_wake().
-- 
GitLab


From fb3c007fde80d9d3b4207943e74c150c9116cead Mon Sep 17 00:00:00 2001
From: Bin Li <bin.li@canonical.com>
Date: Wed, 17 Jan 2024 23:41:23 +0800
Subject: [PATCH 2859/4076] ALSA: hda/realtek: Enable headset mic on Lenovo M70
 Gen5

Lenovo M70 Gen5 is equipped with ALC623, and it needs
ALC283_FIXUP_HEADSET_MIC quirk to make its headset mic work.

Signed-off-by: Bin Li <bin.li@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240117154123.21578-1-bin.li@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index dbf31fe901daa..f6f16622f9cc7 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10233,6 +10233,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340),
+	SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS),
-- 
GitLab


From 4f41d30cd6dc865c3cbc1a852372321eba6d4e4c Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 25 Nov 2023 13:05:04 +0100
Subject: [PATCH 2860/4076] kdb: Fix a potential buffer overflow in kdb_local()

When appending "[defcmd]" to 'kdb_prompt_str', the size of the string
already in the buffer should be taken into account.

An option could be to switch from strncat() to strlcat() which does the
correct test to avoid such an overflow.

However, this actually looks as dead code, because 'defcmd_in_progress'
can't be true here.
See a more detailed explanation at [1].

[1]: https://lore.kernel.org/all/CAD=FV=WSh7wKN7Yp-3wWiDgX4E3isQ8uh0LCzTmd1v9Cg9j+nQ@mail.gmail.com/

Fixes: 5d5314d6795f ("kdb: core for kgdb back end (1 of 2)")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
---
 kernel/debug/kdb/kdb_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 6b213c8252d62..d05066cb40b2e 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1348,8 +1348,6 @@ do_full_getstr:
 		/* PROMPT can only be set if we have MEM_READ permission. */
 		snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"),
 			 raw_smp_processor_id());
-		if (defcmd_in_progress)
-			strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN);
 
 		/*
 		 * Fetch command from keyboard
-- 
GitLab


From 26db46bc9c675e43230cc6accd110110a7654299 Mon Sep 17 00:00:00 2001
From: Pin-yen Lin <treapking@chromium.org>
Date: Tue, 9 Jan 2024 20:04:57 +0800
Subject: [PATCH 2861/4076] drm/bridge: parade-ps8640: Ensure bridge is
 suspended in .post_disable()

The ps8640 bridge seems to expect everything to be power cycled at the
disable process, but sometimes ps8640_aux_transfer() holds the runtime
PM reference and prevents the bridge from suspend.

Prevent that by introducing a mutex lock between ps8640_aux_transfer()
and .post_disable() to make sure the bridge is really powered off.

Fixes: 826cff3f7ebb ("drm/bridge: parade-ps8640: Enable runtime power management")
Signed-off-by: Pin-yen Lin <treapking@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240109120528.1292601-1-treapking@chromium.org
---
 drivers/gpu/drm/bridge/parade-ps8640.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c
index fb5e9ae9ad81d..166bfc725ef48 100644
--- a/drivers/gpu/drm/bridge/parade-ps8640.c
+++ b/drivers/gpu/drm/bridge/parade-ps8640.c
@@ -107,6 +107,7 @@ struct ps8640 {
 	struct device_link *link;
 	bool pre_enabled;
 	bool need_post_hpd_delay;
+	struct mutex aux_lock;
 };
 
 static const struct regmap_config ps8640_regmap_config[] = {
@@ -345,6 +346,7 @@ static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux,
 	struct device *dev = &ps_bridge->page[PAGE0_DP_CNTL]->dev;
 	int ret;
 
+	mutex_lock(&ps_bridge->aux_lock);
 	pm_runtime_get_sync(dev);
 	ret = _ps8640_wait_hpd_asserted(ps_bridge, 200 * 1000);
 	if (ret) {
@@ -354,6 +356,7 @@ static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux,
 	ret = ps8640_aux_transfer_msg(aux, msg);
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
+	mutex_unlock(&ps_bridge->aux_lock);
 
 	return ret;
 }
@@ -475,7 +478,18 @@ static void ps8640_atomic_post_disable(struct drm_bridge *bridge,
 	ps_bridge->pre_enabled = false;
 
 	ps8640_bridge_vdo_control(ps_bridge, DISABLE);
+
+	/*
+	 * The bridge seems to expect everything to be power cycled at the
+	 * disable process, so grab a lock here to make sure
+	 * ps8640_aux_transfer() is not holding a runtime PM reference and
+	 * preventing the bridge from suspend.
+	 */
+	mutex_lock(&ps_bridge->aux_lock);
+
 	pm_runtime_put_sync_suspend(&ps_bridge->page[PAGE0_DP_CNTL]->dev);
+
+	mutex_unlock(&ps_bridge->aux_lock);
 }
 
 static int ps8640_bridge_attach(struct drm_bridge *bridge,
@@ -624,6 +638,8 @@ static int ps8640_probe(struct i2c_client *client)
 	if (!ps_bridge)
 		return -ENOMEM;
 
+	mutex_init(&ps_bridge->aux_lock);
+
 	ps_bridge->supplies[0].supply = "vdd12";
 	ps_bridge->supplies[1].supply = "vdd33";
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(ps_bridge->supplies),
-- 
GitLab


From 658365c6b0857e6a306436e315a8633937e3af42 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Fri, 12 Jan 2024 12:19:27 +0800
Subject: [PATCH 2862/4076] scsi: isci: Fix an error code problem in
 isci_io_request_build()

Clang static complains that Value stored to 'status' is never read. Return
'status' rather than 'SCI_SUCCESS'.

Fixes: f1f52e75939b ("isci: uplevel request infrastructure")
Signed-off-by: Su Hui <suhui@nfschina.com>
Link: https://lore.kernel.org/r/20240112041926.3924315-1-suhui@nfschina.com
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/isci/request.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index 71f711cb0628a..355a0bc0828e7 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -3387,7 +3387,7 @@ static enum sci_status isci_io_request_build(struct isci_host *ihost,
 		return SCI_FAILURE;
 	}
 
-	return SCI_SUCCESS;
+	return status;
 }
 
 static struct isci_request *isci_request_from_tag(struct isci_host *ihost, u16 tag)
-- 
GitLab


From d6b75ba5218915be48542bcd7e2a09776b7c66c9 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 16 Jan 2024 12:58:36 +0800
Subject: [PATCH 2863/4076] scsi: virtio_scsi: Remove duplicate check if queue
 is broken

virtqueue_enable_cb() will call virtqueue_poll() which will check if queue
is broken at beginning, so remove the virtqueue_is_broken() call

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Link: https://lore.kernel.org/r/20240116045836.12475-1-lirongqing@baidu.com
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/virtio_scsi.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 9d1bdcdc13312..e15b3809d0595 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -182,8 +182,6 @@ static void virtscsi_vq_done(struct virtio_scsi *vscsi,
 		while ((buf = virtqueue_get_buf(vq, &len)) != NULL)
 			fn(vscsi, buf);
 
-		if (unlikely(virtqueue_is_broken(vq)))
-			break;
 	} while (!virtqueue_enable_cb(vq));
 	spin_unlock_irqrestore(&virtscsi_vq->vq_lock, flags);
 }
-- 
GitLab


From e6f3799de2f2b2cd23c3894a127921dfb6c6a512 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 16 Jan 2024 11:26:06 +0000
Subject: [PATCH 2864/4076] scsi: initio: Remove redundant variable 'rb'

The variable 'rb' is being assigned a value but it isn't being read
afterwards. The assignment is redundant and so 'rb' can be removed.

Cleans up clang scan build warning:

warning: Although the value stored to 'rb' is used in the enclosing
expression, the value is never actually read from 'rb'[deadcode.DeadStores]

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://lore.kernel.org/r/20240116112606.2263738-1-colin.i.king@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/initio.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c
index 2a50fda3a628c..625fd547ee60a 100644
--- a/drivers/scsi/initio.c
+++ b/drivers/scsi/initio.c
@@ -371,7 +371,6 @@ static u16 initio_se2_rd(unsigned long base, u8 addr)
  */
 static void initio_se2_wr(unsigned long base, u8 addr, u16 val)
 {
-	u8 rb;
 	u8 instr;
 	int i;
 
@@ -400,7 +399,7 @@ static void initio_se2_wr(unsigned long base, u8 addr, u16 val)
 		udelay(30);
 		outb(SE2CS, base + TUL_NVRAM);			/* -CLK */
 		udelay(30);
-		if ((rb = inb(base + TUL_NVRAM)) & SE2DI)
+		if (inb(base + TUL_NVRAM) & SE2DI)
 			break;	/* write complete */
 	}
 	outb(0, base + TUL_NVRAM);				/* -CS */
-- 
GitLab


From 7d1ae55ffed0ff78ed33b1465c1233e05024e135 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Tue, 16 Jan 2024 13:55:09 -0800
Subject: [PATCH 2865/4076] scsi: MAINTAINERS: Update ibmvscsi_tgt maintainer

Michael has not been responsible for this code as an IBMer for quite some
time. Seeing as the rest of the IBM Virtual SCSI related drivers already
fall under my purview replace Michael with myself as maintainer.

Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Link: https://lore.kernel.org/r/20240116215509.1155787-1-tyreld@linux.ibm.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index b5ac8c4ae4345..afbd909258dfe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10203,7 +10203,7 @@ F:	drivers/scsi/ibmvscsi/ibmvscsi*
 F:	include/scsi/viosrp.h
 
 IBM Power Virtual SCSI Device Target Driver
-M:	Michael Cyr <mikecyr@linux.ibm.com>
+M:	Tyrel Datwyler <tyreld@linux.ibm.com>
 L:	linux-scsi@vger.kernel.org
 L:	target-devel@vger.kernel.org
 S:	Supported
-- 
GitLab


From a20f1b02bafcbf5a32d96a1d4185d6981cf7d016 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Wed, 17 Jan 2024 10:35:03 -0800
Subject: [PATCH 2866/4076] drm/bridge: parade-ps8640: Make sure we drop the
 AUX mutex in the error case

After commit 26db46bc9c67 ("drm/bridge: parade-ps8640: Ensure bridge
is suspended in .post_disable()"), if we hit the error case in
ps8640_aux_transfer() then we return without dropping the mutex. Fix
this oversight.

Fixes: 26db46bc9c67 ("drm/bridge: parade-ps8640: Ensure bridge is suspended in .post_disable()")
Reviewed-by: Hsin-Yi Wang <hsinyi@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240117103502.1.Ib726a0184913925efc7e99c4d4fc801982e1bc24@changeid
---
 drivers/gpu/drm/bridge/parade-ps8640.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c
index 166bfc725ef48..14d4dcf239da8 100644
--- a/drivers/gpu/drm/bridge/parade-ps8640.c
+++ b/drivers/gpu/drm/bridge/parade-ps8640.c
@@ -351,11 +351,13 @@ static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux,
 	ret = _ps8640_wait_hpd_asserted(ps_bridge, 200 * 1000);
 	if (ret) {
 		pm_runtime_put_sync_suspend(dev);
-		return ret;
+		goto exit;
 	}
 	ret = ps8640_aux_transfer_msg(aux, msg);
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
+
+exit:
 	mutex_unlock(&ps_bridge->aux_lock);
 
 	return ret;
-- 
GitLab


From 49e60333d743ae32db3bdde2f93bc818482dd741 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 17 Jan 2024 12:36:09 -0800
Subject: [PATCH 2867/4076] blk-mq: Remove the hctx 'run' debugfs attribute

Nobody uses the debugfs hctx 'run' attribute. Hence remove this
attribute and also the code that updates the corresponding member
variable.

Suggested-by: Jens Axboe <axboe@kernel.dk>
Cc: Gabriel Ryan <gabe@cs.columbia.edu>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240117203609.4122520-1-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c | 18 ------------------
 block/blk-mq-sched.c   |  2 --
 include/linux/blk-mq.h |  3 ---
 3 files changed, 23 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 5cbeb9344f2f5..94668e72ab09b 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -479,23 +479,6 @@ out:
 	return res;
 }
 
-static int hctx_run_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	seq_printf(m, "%lu\n", hctx->run);
-	return 0;
-}
-
-static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
-			      loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	hctx->run = 0;
-	return count;
-}
-
 static int hctx_active_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
@@ -624,7 +607,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"tags_bitmap", 0400, hctx_tags_bitmap_show},
 	{"sched_tags", 0400, hctx_sched_tags_show},
 	{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
-	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
 	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
 	{"type", 0400, hctx_type_show},
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 67c95f31b15bb..451a2c1f1f321 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -324,8 +324,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
 		return;
 
-	hctx->run++;
-
 	/*
 	 * A return of -EAGAIN is an indication that hctx->dispatch is not
 	 * empty and we must run again in order to avoid starving flushes.
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a676e116085f3..7a8150a5f0513 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -391,9 +391,6 @@ struct blk_mq_hw_ctx {
 	 */
 	struct blk_mq_tags	*sched_tags;
 
-	/** @run: Number of dispatched requests. */
-	unsigned long		run;
-
 	/** @numa_node: NUMA node the storage adapter has been connected to. */
 	unsigned int		numa_node;
 	/** @queue_num: Index of this hardware queue. */
-- 
GitLab


From 1d9cabe2817edd215779dc9c2fe5e7ab9aac0704 Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Wed, 17 Jan 2024 22:06:28 +0100
Subject: [PATCH 2868/4076] SUNRPC: use request size to initialize bio_vec in
 svc_udp_sendto()

Use the proper size when setting up the bio_vec, as otherwise only
zero-length UDP packets will be sent.

Fixes: baabf59c2414 ("SUNRPC: Convert svc_udp_sendto() to use the per-socket bio_vec array")
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/svcsock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index bfb2f78523a82..545017a3daa4d 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -717,12 +717,12 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
 				ARRAY_SIZE(rqstp->rq_bvec), xdr);
 
 	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
-		      count, 0);
+		      count, rqstp->rq_res.len);
 	err = sock_sendmsg(svsk->sk_sock, &msg);
 	if (err == -ECONNREFUSED) {
 		/* ICMP error on earlier request. */
 		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
-			      count, 0);
+			      count, rqstp->rq_res.len);
 		err = sock_sendmsg(svsk->sk_sock, &msg);
 	}
 
-- 
GitLab


From 590b1d19d73914477cfd9faac7a0d7dcf5b4eb08 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 16 Jan 2024 00:22:13 +0100
Subject: [PATCH 2869/4076] rtc: max31335: remove unecessary locking

There is no race condition when accessing MAX31335_STATUS1 because it is
always about clearing the alarm interrupt bit.

Reviewed-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Link: https://lore.kernel.org/r/20240115232215.273374-1-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-max31335.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c
index 3ddfe71bbb560..2ce23f60a7f34 100644
--- a/drivers/rtc/rtc-max31335.c
+++ b/drivers/rtc/rtc-max31335.c
@@ -348,27 +348,19 @@ static int max31335_alarm_irq_enable(struct device *dev, unsigned int enabled)
 static irqreturn_t max31335_handle_irq(int irq, void *dev_id)
 {
 	struct max31335_data *max31335 = dev_id;
-	struct mutex *lock = &max31335->rtc->ops_lock;
 	int ret, status;
 
-	mutex_lock(lock);
-
 	ret = regmap_read(max31335->regmap, MAX31335_STATUS1, &status);
 	if (ret)
-		goto exit;
+		return IRQ_HANDLED;
 
 	if (FIELD_GET(MAX31335_STATUS1_A1F, status)) {
-		ret = regmap_update_bits(max31335->regmap, MAX31335_STATUS1,
-					 MAX31335_STATUS1_A1F, 0);
-		if (ret)
-			goto exit;
+		regmap_update_bits(max31335->regmap, MAX31335_STATUS1,
+				   MAX31335_STATUS1_A1F, 0);
 
 		rtc_update_irq(max31335->rtc, 1, RTC_AF | RTC_IRQF);
 	}
 
-exit:
-	mutex_unlock(lock);
-
 	return IRQ_HANDLED;
 }
 
-- 
GitLab


From b7d450d98b0f9917cac31b39ba459a4aee26c8b1 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 16 Jan 2024 00:22:14 +0100
Subject: [PATCH 2870/4076] rtc: max31335: use regmap_update_bits_check

Simplify the IRQ handler by using regmap_update_bits_check.

Reviewed-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Link: https://lore.kernel.org/r/20240115232215.273374-2-alexandre.belloni@bootlin.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-max31335.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c
index 2ce23f60a7f34..a38d303d9df4d 100644
--- a/drivers/rtc/rtc-max31335.c
+++ b/drivers/rtc/rtc-max31335.c
@@ -348,18 +348,16 @@ static int max31335_alarm_irq_enable(struct device *dev, unsigned int enabled)
 static irqreturn_t max31335_handle_irq(int irq, void *dev_id)
 {
 	struct max31335_data *max31335 = dev_id;
-	int ret, status;
+	bool status;
+	int ret;
 
-	ret = regmap_read(max31335->regmap, MAX31335_STATUS1, &status);
+	ret = regmap_update_bits_check(max31335->regmap, MAX31335_STATUS1,
+				       MAX31335_STATUS1_A1F, 0, &status);
 	if (ret)
 		return IRQ_HANDLED;
 
-	if (FIELD_GET(MAX31335_STATUS1_A1F, status)) {
-		regmap_update_bits(max31335->regmap, MAX31335_STATUS1,
-				   MAX31335_STATUS1_A1F, 0);
-
+	if (status)
 		rtc_update_irq(max31335->rtc, 1, RTC_AF | RTC_IRQF);
-	}
 
 	return IRQ_HANDLED;
 }
-- 
GitLab


From dd7fe5d9fd6a27531e985e3812ef4031bd316b01 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 17 Jan 2024 10:54:16 -0700
Subject: [PATCH 2871/4076] rtc: max31335: Fix comparison in
 max31335_volatile_reg()

Clang warns (or errors with CONFIG_WERROR=y):

    drivers/rtc/rtc-max31335.c:211:36: error: use of logical '||' with constant operand [-Werror,-Wconstant-logical-operand]
      211 |         if (reg == MAX31335_TEMP_DATA_MSB || MAX31335_TEMP_DATA_LSB)
          |                                           ^  ~~~~~~~~~~~~~~~~~~~~~~
    drivers/rtc/rtc-max31335.c:211:36: note: use '|' for a bitwise operation
      211 |         if (reg == MAX31335_TEMP_DATA_MSB || MAX31335_TEMP_DATA_LSB)
          |                                           ^~
          |                                           |
    1 error generated.

This clearly should be a comparison against reg. Fix the comparison so
that max31335_volatile_reg() does not always return true.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1980
Fixes: dedaf03b99d6 ("rtc: max31335: add driver support")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20240117-rtc-max3133-fix-comparison-v1-1-91e98b29d564@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-max31335.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c
index a38d303d9df4d..402fda8fd5488 100644
--- a/drivers/rtc/rtc-max31335.c
+++ b/drivers/rtc/rtc-max31335.c
@@ -208,7 +208,7 @@ static bool max31335_volatile_reg(struct device *dev, unsigned int reg)
 		return true;
 
 	/* temperature registers */
-	if (reg == MAX31335_TEMP_DATA_MSB || MAX31335_TEMP_DATA_LSB)
+	if (reg == MAX31335_TEMP_DATA_MSB || reg == MAX31335_TEMP_DATA_LSB)
 		return true;
 
 	return false;
-- 
GitLab


From 8681de6457aa071a5982e9b20682e56a7d87e3b6 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Fri, 5 Jan 2024 14:53:42 +0000
Subject: [PATCH 2872/4076] rtc: da9063: Make IRQ as optional

On some platforms (eg: RZ/{G2UL,Five} SMARC EVK), there is no IRQ
populated by default. Add irq optional support.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20240105145344.204453-2-biju.das.jz@bp.renesas.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-da9063.c | 40 ++++++++++++++++++++++------------------
 1 file changed, 22 insertions(+), 18 deletions(-)

diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index 2f5d60622564a..b3a1f852c318b 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -485,25 +485,29 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 		clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtc_dev->features);
 	}
 
-	irq_alarm = platform_get_irq_byname(pdev, "ALARM");
-	if (irq_alarm < 0)
+	irq_alarm = platform_get_irq_byname_optional(pdev, "ALARM");
+	if (irq_alarm >= 0) {
+		ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL,
+						da9063_alarm_event,
+						IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+						"ALARM", rtc);
+		if (ret)
+			dev_err(&pdev->dev,
+				"Failed to request ALARM IRQ %d: %d\n",
+				irq_alarm, ret);
+
+		ret = dev_pm_set_wake_irq(&pdev->dev, irq_alarm);
+		if (ret)
+			dev_warn(&pdev->dev,
+				 "Failed to set IRQ %d as a wake IRQ: %d\n",
+				 irq_alarm, ret);
+
+		device_init_wakeup(&pdev->dev, true);
+	}  else if (irq_alarm != -ENXIO) {
 		return irq_alarm;
-
-	ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL,
-					da9063_alarm_event,
-					IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-					"ALARM", rtc);
-	if (ret)
-		dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n",
-			irq_alarm, ret);
-
-	ret = dev_pm_set_wake_irq(&pdev->dev, irq_alarm);
-	if (ret)
-		dev_warn(&pdev->dev,
-			 "Failed to set IRQ %d as a wake IRQ: %d\n",
-			 irq_alarm, ret);
-
-	device_init_wakeup(&pdev->dev, true);
+	} else {
+		clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features);
+	}
 
 	return devm_rtc_register_device(rtc->rtc_dev);
 }
-- 
GitLab


From 4b60c32e979ac84a715c329161ddf42b0790be4e Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Fri, 5 Jan 2024 14:53:43 +0000
Subject: [PATCH 2873/4076] rtc: da9063: Use device_get_match_data()

Replace of_match_node()->device_get_match_data() for
the data associated with device match.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20240105145344.204453-3-biju.das.jz@bp.renesas.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-da9063.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index b3a1f852c318b..265abdd7e935f 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -377,7 +377,6 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 {
 	struct da9063_compatible_rtc *rtc;
 	const struct da9063_compatible_rtc_regmap *config;
-	const struct of_device_id *match;
 	int irq_alarm;
 	u8 data[RTC_DATA_LEN];
 	int ret;
@@ -385,14 +384,11 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 	if (!pdev->dev.of_node)
 		return -ENXIO;
 
-	match = of_match_node(da9063_compatible_reg_id_table,
-			      pdev->dev.of_node);
-
 	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
 	if (!rtc)
 		return -ENOMEM;
 
-	rtc->config = match->data;
+	rtc->config = device_get_match_data(&pdev->dev);
 	if (of_device_is_compatible(pdev->dev.of_node, "dlg,da9063-rtc")) {
 		struct da9063 *chip = dev_get_drvdata(pdev->dev.parent);
 
-- 
GitLab


From f5334aa88345874d54a406e86a886a54173e1ba8 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Fri, 5 Jan 2024 14:53:44 +0000
Subject: [PATCH 2874/4076] rtc: da9063: Use dev_err_probe()

Replace dev_err()->dev_err_probe() to simpilfy probe().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20240105145344.204453-4-biju.das.jz@bp.renesas.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-da9063.c | 42 ++++++++++++++++------------------------
 1 file changed, 17 insertions(+), 25 deletions(-)

diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index 265abdd7e935f..859397541f298 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -407,57 +407,49 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 				 config->rtc_enable_reg,
 				 config->rtc_enable_mask,
 				 config->rtc_enable_mask);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to enable RTC\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret, "Failed to enable RTC\n");
 
 	ret = regmap_update_bits(rtc->regmap,
 				 config->rtc_enable_32k_crystal_reg,
 				 config->rtc_crystal_mask,
 				 config->rtc_crystal_mask);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to run 32kHz oscillator\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to run 32kHz oscillator\n");
 
 	ret = regmap_update_bits(rtc->regmap,
 				 config->rtc_alarm_secs_reg,
 				 config->rtc_alarm_status_mask,
 				 0);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to access RTC alarm register\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to access RTC alarm register\n");
 
 	ret = regmap_update_bits(rtc->regmap,
 				 config->rtc_alarm_secs_reg,
 				 DA9063_ALARM_STATUS_ALARM,
 				 DA9063_ALARM_STATUS_ALARM);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to access RTC alarm register\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to access RTC alarm register\n");
 
 	ret = regmap_update_bits(rtc->regmap,
 				 config->rtc_alarm_year_reg,
 				 config->rtc_tick_on_mask,
 				 0);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to disable TICKs\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to disable TICKs\n");
 
 	data[RTC_SEC] = 0;
 	ret = regmap_bulk_read(rtc->regmap,
 			       config->rtc_alarm_secs_reg,
 			       &data[config->rtc_data_start],
 			       config->rtc_alarm_len);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to read initial alarm data: %d\n",
-			ret);
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Failed to read initial alarm data\n");
 
 	platform_set_drvdata(pdev, rtc);
 
-- 
GitLab


From 14688f1a91e1f37bc6bf50ff5241e857f24338e0 Mon Sep 17 00:00:00 2001
From: Mia Lin <mimi05633@gmail.com>
Date: Mon, 13 Nov 2023 18:38:07 +0800
Subject: [PATCH 2875/4076] rtc: nuvoton: Compatible with NCT3015Y-R and
 NCT3018Y-R

The NCT3015Y-R and NCT3018Y-R use the same datasheet
    but have different topologies as follows.
- Topology (Only 1st i2c can set TWO bit and HF bit)
  In NCT3015Y-R,
    rtc 1st i2c is connected to a host CPU
    rtc 2nd i2c is connected to a BMC
  In NCT3018Y-R,
    rtc 1st i2c is connected to a BMC
    rtc 2nd i2c is connected to a host CPU
In order to be compatible with NCT3015Y-R and NCT3018Y-R,
- In probe,
  If part number is NCT3018Y-R, only set HF bit to 24-Hour format.
  Else, do nothing
- In set_time,
  If part number is NCT3018Y-R && TWO bit is 0,
     change TWO bit to 1, and restore TWO bit after updating time.

Signed-off-by: Mia Lin <mimi05633@gmail.com>
Link: https://lore.kernel.org/r/20231113103807.1036978-2-mimi05633@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-nct3018y.c | 52 +++++++++++++++++++++++++++++++++-----
 1 file changed, 46 insertions(+), 6 deletions(-)

diff --git a/drivers/rtc/rtc-nct3018y.c b/drivers/rtc/rtc-nct3018y.c
index ed4e606be8e58..f488a189a4651 100644
--- a/drivers/rtc/rtc-nct3018y.c
+++ b/drivers/rtc/rtc-nct3018y.c
@@ -23,6 +23,7 @@
 #define NCT3018Y_REG_CTRL	0x0A /* timer control */
 #define NCT3018Y_REG_ST		0x0B /* status */
 #define NCT3018Y_REG_CLKO	0x0C /* clock out */
+#define NCT3018Y_REG_PART	0x21 /* part info */
 
 #define NCT3018Y_BIT_AF		BIT(7)
 #define NCT3018Y_BIT_ST		BIT(7)
@@ -37,10 +38,12 @@
 #define NCT3018Y_REG_BAT_MASK		0x07
 #define NCT3018Y_REG_CLKO_F_MASK	0x03 /* frequenc mask */
 #define NCT3018Y_REG_CLKO_CKE		0x80 /* clock out enabled */
+#define NCT3018Y_REG_PART_NCT3018Y	0x02
 
 struct nct3018y {
 	struct rtc_device *rtc;
 	struct i2c_client *client;
+	int part_num;
 #ifdef CONFIG_COMMON_CLK
 	struct clk_hw clkout_hw;
 #endif
@@ -177,8 +180,27 @@ static int nct3018y_rtc_read_time(struct device *dev, struct rtc_time *tm)
 static int nct3018y_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	struct i2c_client *client = to_i2c_client(dev);
+	struct nct3018y *nct3018y = dev_get_drvdata(dev);
 	unsigned char buf[4] = {0};
-	int err;
+	int err, flags;
+	int restore_flags = 0;
+
+	flags = i2c_smbus_read_byte_data(client, NCT3018Y_REG_CTRL);
+	if (flags < 0) {
+		dev_dbg(&client->dev, "Failed to read NCT3018Y_REG_CTRL.\n");
+		return flags;
+	}
+
+	/* Check and set TWO bit */
+	if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y && !(flags & NCT3018Y_BIT_TWO)) {
+		restore_flags = 1;
+		flags |= NCT3018Y_BIT_TWO;
+		err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n");
+			return err;
+		}
+	}
 
 	buf[0] = bin2bcd(tm->tm_sec);
 	err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_SC, buf[0]);
@@ -212,6 +234,18 @@ static int nct3018y_rtc_set_time(struct device *dev, struct rtc_time *tm)
 		return -EIO;
 	}
 
+	/* Restore TWO bit */
+	if (restore_flags) {
+		if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y)
+			flags &= ~NCT3018Y_BIT_TWO;
+
+		err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n");
+			return err;
+		}
+	}
+
 	return err;
 }
 
@@ -479,11 +513,17 @@ static int nct3018y_probe(struct i2c_client *client)
 		dev_dbg(&client->dev, "%s: NCT3018Y_BIT_TWO is set\n", __func__);
 	}
 
-	flags = NCT3018Y_BIT_TWO;
-	err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags);
-	if (err < 0) {
-		dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL\n");
-		return err;
+	nct3018y->part_num = i2c_smbus_read_byte_data(client, NCT3018Y_REG_PART);
+	if (nct3018y->part_num < 0) {
+		dev_dbg(&client->dev, "Failed to read NCT3018Y_REG_PART.\n");
+		return nct3018y->part_num;
+	} else if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y) {
+		flags = NCT3018Y_BIT_HF;
+		err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n");
+			return err;
+		}
 	}
 
 	flags = 0;
-- 
GitLab


From 0de65288d75ff96c30e216557d979fb9342c4323 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 17 Jan 2024 14:09:34 +0100
Subject: [PATCH 2876/4076] RISC-V: selftests: cbo: Ensure asm operands match
 constraints

The 'i' constraint expects a constant operand, which fn and its
constant derivative MK_CBO(fn) are, but passing fn through a function
as a parameter and using a local variable for MK_CBO(fn) allow the
compiler to lose sight of that when no optimization is done. Use
a macro instead of a function and skip the local variable to ensure
the compiler uses constants, matching the asm constraints.

Reported-by: Yunhui Cui <cuiyunhui@bytedance.com>
Closes: https://lore.kernel.org/all/20240117082514.42967-1-cuiyunhui@bytedance.com
Fixes: a29e2a48afe3 ("RISC-V: selftests: Add CBO tests")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20240117130933.57514-2-ajones@ventanamicro.com
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/riscv/hwprobe/cbo.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c
index c6a83ab11e223..c537d52fafc58 100644
--- a/tools/testing/selftests/riscv/hwprobe/cbo.c
+++ b/tools/testing/selftests/riscv/hwprobe/cbo.c
@@ -36,16 +36,14 @@ static void sigill_handler(int sig, siginfo_t *info, void *context)
 	regs[0] += 4;
 }
 
-static void cbo_insn(char *base, int fn)
-{
-	uint32_t insn = MK_CBO(fn);
-
-	asm volatile(
-	"mv	a0, %0\n"
-	"li	a1, %1\n"
-	".4byte	%2\n"
-	: : "r" (base), "i" (fn), "i" (insn) : "a0", "a1", "memory");
-}
+#define cbo_insn(base, fn)							\
+({										\
+	asm volatile(								\
+	"mv	a0, %0\n"							\
+	"li	a1, %1\n"							\
+	".4byte	%2\n"								\
+	: : "r" (base), "i" (fn), "i" (MK_CBO(fn)) : "a0", "a1", "memory");	\
+})
 
 static void cbo_inval(char *base) { cbo_insn(base, 0); }
 static void cbo_clean(char *base) { cbo_insn(base, 1); }
-- 
GitLab


From 1e7196fa5b0312a6a3e49e7c1300e145afcba96b Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Mon, 8 Jan 2024 15:57:02 -0800
Subject: [PATCH 2877/4076] asm-generic: Improve csum_fold

This csum_fold implementation introduced into arch/arc by Vineet Gupta
is better than the default implementation on at least arc, x86, and
riscv. Using GCC trunk and compiling non-inlined version, this
implementation has 41.6667%, 25% fewer instructions on riscv64, x86-64
respectively with -O3 optimization. Most implmentations override this
default in asm, but this should be more performant than all of those
other implementations except for arm which has barrel shifting and
sparc32 which has a carry flag.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: David Laight <david.laight@aculab.com>
Link: https://lore.kernel.org/r/20240108-optimize_checksum-v15-1-1c50de5f2167@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 include/asm-generic/checksum.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index 43e18db89c143..ad928cce268b4 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_GENERIC_CHECKSUM_H
 #define __ASM_GENERIC_CHECKSUM_H
 
+#include <linux/bitops.h>
+
 /*
  * computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
@@ -31,9 +33,7 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 static inline __sum16 csum_fold(__wsum csum)
 {
 	u32 sum = (__force u32)csum;
-	sum = (sum & 0xffff) + (sum >> 16);
-	sum = (sum & 0xffff) + (sum >> 16);
-	return (__force __sum16)~sum;
+	return (__force __sum16)((~sum - ror32(sum, 16)) >> 16);
 }
 #endif
 
-- 
GitLab


From 2ce5729fce8f62b5118f56110d16006c0e22c522 Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Mon, 8 Jan 2024 15:57:03 -0800
Subject: [PATCH 2878/4076] riscv: Add static key for misaligned accesses

Support static branches depending on the value of misaligned accesses.
This will be used by a later patch in the series. At any point in time,
this static branch will only be enabled if all online CPUs are
considered "fast".

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Evan Green <evan@rivosinc.com>
Link: https://lore.kernel.org/r/20240108-optimize_checksum-v15-2-1c50de5f2167@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cpufeature.h |  2 +
 arch/riscv/kernel/cpufeature.c      | 90 ++++++++++++++++++++++++++++-
 2 files changed, 89 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index a418c3112cd60..7b129e5e2f075 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -133,4 +133,6 @@ static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsi
 	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
 }
 
+DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
 #endif
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index b3785ffc15703..b62baeb504d80 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -8,8 +8,10 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
+#include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
 #include <linux/ctype.h>
+#include <linux/jump_label.h>
 #include <linux/log2.h>
 #include <linux/memory.h>
 #include <linux/module.h>
@@ -44,6 +46,8 @@ struct riscv_isainfo hart_isa[NR_CPUS];
 /* Performance information */
 DEFINE_PER_CPU(long, misaligned_access_speed);
 
+static cpumask_t fast_misaligned_access;
+
 /**
  * riscv_isa_extension_base() - Get base extension word
  *
@@ -643,6 +647,16 @@ static int check_unaligned_access(void *param)
 		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
 
 	per_cpu(misaligned_access_speed, cpu) = speed;
+
+	/*
+	 * Set the value of fast_misaligned_access of a CPU. These operations
+	 * are atomic to avoid race conditions.
+	 */
+	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+		cpumask_set_cpu(cpu, &fast_misaligned_access);
+	else
+		cpumask_clear_cpu(cpu, &fast_misaligned_access);
+
 	return 0;
 }
 
@@ -655,13 +669,69 @@ static void check_unaligned_access_nonboot_cpu(void *param)
 		check_unaligned_access(pages[cpu]);
 }
 
+DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
+static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
+{
+	if (cpumask_weight(mask) == weight)
+		static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
+	else
+		static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
+}
+
+static void set_unaligned_access_static_branches_except_cpu(int cpu)
+{
+	/*
+	 * Same as set_unaligned_access_static_branches, except excludes the
+	 * given CPU from the result. When a CPU is hotplugged into an offline
+	 * state, this function is called before the CPU is set to offline in
+	 * the cpumask, and thus the CPU needs to be explicitly excluded.
+	 */
+
+	cpumask_t fast_except_me;
+
+	cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
+	cpumask_clear_cpu(cpu, &fast_except_me);
+
+	modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
+}
+
+static void set_unaligned_access_static_branches(void)
+{
+	/*
+	 * This will be called after check_unaligned_access_all_cpus so the
+	 * result of unaligned access speed for all CPUs will be available.
+	 *
+	 * To avoid the number of online cpus changing between reading
+	 * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
+	 * held before calling this function.
+	 */
+
+	cpumask_t fast_and_online;
+
+	cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
+
+	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
+}
+
+static int lock_and_set_unaligned_access_static_branch(void)
+{
+	cpus_read_lock();
+	set_unaligned_access_static_branches();
+	cpus_read_unlock();
+
+	return 0;
+}
+
+arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
+
 static int riscv_online_cpu(unsigned int cpu)
 {
 	static struct page *buf;
 
 	/* We are already set since the last check */
 	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
-		return 0;
+		goto exit;
 
 	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
 	if (!buf) {
@@ -671,6 +741,17 @@ static int riscv_online_cpu(unsigned int cpu)
 
 	check_unaligned_access(buf);
 	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+
+exit:
+	set_unaligned_access_static_branches();
+
+	return 0;
+}
+
+static int riscv_offline_cpu(unsigned int cpu)
+{
+	set_unaligned_access_static_branches_except_cpu(cpu);
+
 	return 0;
 }
 
@@ -705,9 +786,12 @@ static int check_unaligned_access_all_cpus(void)
 	/* Check core 0. */
 	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
 
-	/* Setup hotplug callback for any new CPUs that come online. */
+	/*
+	 * Setup hotplug callbacks for any new CPUs that come online or go
+	 * offline.
+	 */
 	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
-				  riscv_online_cpu, NULL);
+				  riscv_online_cpu, riscv_offline_cpu);
 
 out:
 	unaligned_emulation_finish();
-- 
GitLab


From e11e367e9fe57164ea609807ed27184c85263355 Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Mon, 8 Jan 2024 15:57:04 -0800
Subject: [PATCH 2879/4076] riscv: Add checksum header

Provide checksum algorithms that have been designed to leverage riscv
instructions such as rotate. In 64-bit, can take advantage of the larger
register to avoid some overflow checking.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Xiao Wang <xiao.w.wang@intel.com>
Link: https://lore.kernel.org/r/20240108-optimize_checksum-v15-3-1c50de5f2167@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/checksum.h | 82 +++++++++++++++++++++++++++++++
 1 file changed, 82 insertions(+)
 create mode 100644 arch/riscv/include/asm/checksum.h

diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
new file mode 100644
index 0000000000000..5a810126aac71
--- /dev/null
+++ b/arch/riscv/include/asm/checksum.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Checksum routines
+ *
+ * Copyright (C) 2023 Rivos Inc.
+ */
+#ifndef __ASM_RISCV_CHECKSUM_H
+#define __ASM_RISCV_CHECKSUM_H
+
+#include <linux/in6.h>
+#include <linux/uaccess.h>
+
+#define ip_fast_csum ip_fast_csum
+
+/* Define riscv versions of functions before importing asm-generic/checksum.h */
+#include <asm-generic/checksum.h>
+
+/**
+ * Quickly compute an IP checksum with the assumption that IPv4 headers will
+ * always be in multiples of 32-bits, and have an ihl of at least 5.
+ *
+ * @ihl: the number of 32 bit segments and must be greater than or equal to 5.
+ * @iph: assumed to be word aligned given that NET_IP_ALIGN is set to 2 on
+ *  riscv, defining IP headers to be aligned.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	unsigned long csum = 0;
+	int pos = 0;
+
+	do {
+		csum += ((const unsigned int *)iph)[pos];
+		if (IS_ENABLED(CONFIG_32BIT))
+			csum += csum < ((const unsigned int *)iph)[pos];
+	} while (++pos < ihl);
+
+	/*
+	 * ZBB only saves three instructions on 32-bit and five on 64-bit so not
+	 * worth checking if supported without Alternatives.
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		unsigned long fold_temp;
+
+		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+		    :
+		    :
+		    :
+		    : no_zbb);
+
+		if (IS_ENABLED(CONFIG_32BIT)) {
+			asm(".option push				\n\
+			.option arch,+zbb				\n\
+				not	%[fold_temp], %[csum]		\n\
+				rori	%[csum], %[csum], 16		\n\
+				sub	%[csum], %[fold_temp], %[csum]	\n\
+			.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+		} else {
+			asm(".option push				\n\
+			.option arch,+zbb				\n\
+				rori	%[fold_temp], %[csum], 32	\n\
+				add	%[csum], %[fold_temp], %[csum]	\n\
+				srli	%[csum], %[csum], 32		\n\
+				not	%[fold_temp], %[csum]		\n\
+				roriw	%[csum], %[csum], 16		\n\
+				subw	%[csum], %[fold_temp], %[csum]	\n\
+			.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+		}
+		return (__force __sum16)(csum >> 16);
+	}
+no_zbb:
+#ifndef CONFIG_32BIT
+	csum += ror64(csum, 32);
+	csum >>= 32;
+#endif
+	return csum_fold((__force __wsum)csum);
+}
+
+#endif /* __ASM_RISCV_CHECKSUM_H */
-- 
GitLab


From a04c192eabfb76824d00f1b4cd0f25844a59d0f0 Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Mon, 8 Jan 2024 15:57:05 -0800
Subject: [PATCH 2880/4076] riscv: Add checksum library

Provide a 32 and 64 bit version of do_csum. When compiled for 32-bit
will load from the buffer in groups of 32 bits, and when compiled for
64-bit will load in groups of 64 bits.

Additionally provide riscv optimized implementation of csum_ipv6_magic.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Xiao Wang <xiao.w.wang@intel.com>
Link: https://lore.kernel.org/r/20240108-optimize_checksum-v15-4-1c50de5f2167@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/checksum.h |  11 +
 arch/riscv/lib/Makefile           |   1 +
 arch/riscv/lib/csum.c             | 326 ++++++++++++++++++++++++++++++
 3 files changed, 338 insertions(+)
 create mode 100644 arch/riscv/lib/csum.c

diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
index 5a810126aac71..a5b60b54b101c 100644
--- a/arch/riscv/include/asm/checksum.h
+++ b/arch/riscv/include/asm/checksum.h
@@ -12,6 +12,17 @@
 
 #define ip_fast_csum ip_fast_csum
 
+extern unsigned int do_csum(const unsigned char *buff, int len);
+#define do_csum do_csum
+
+/* Default version is sufficient for 32 bit */
+#ifndef CONFIG_32BIT
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum sum);
+#endif
+
 /* Define riscv versions of functions before importing asm-generic/checksum.h */
 #include <asm-generic/checksum.h>
 
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 26cb2502ecf89..2aa1a4ad361fb 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -6,6 +6,7 @@ lib-y			+= memmove.o
 lib-y			+= strcmp.o
 lib-y			+= strlen.o
 lib-y			+= strncmp.o
+lib-y			+= csum.o
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
new file mode 100644
index 0000000000000..06ce8e7250d98
--- /dev/null
+++ b/arch/riscv/lib/csum.c
@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Checksum library
+ *
+ * Influenced by arch/arm64/lib/csum.c
+ * Copyright (C) 2023 Rivos Inc.
+ */
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/jump_label.h>
+#include <linux/kasan-checks.h>
+#include <linux/kernel.h>
+
+#include <asm/cpufeature.h>
+
+#include <net/checksum.h>
+
+/* Default version is sufficient for 32 bit */
+#ifndef CONFIG_32BIT
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum csum)
+{
+	unsigned int ulen, uproto;
+	unsigned long sum = (__force unsigned long)csum;
+
+	sum += (__force unsigned long)saddr->s6_addr32[0];
+	sum += (__force unsigned long)saddr->s6_addr32[1];
+	sum += (__force unsigned long)saddr->s6_addr32[2];
+	sum += (__force unsigned long)saddr->s6_addr32[3];
+
+	sum += (__force unsigned long)daddr->s6_addr32[0];
+	sum += (__force unsigned long)daddr->s6_addr32[1];
+	sum += (__force unsigned long)daddr->s6_addr32[2];
+	sum += (__force unsigned long)daddr->s6_addr32[3];
+
+	ulen = (__force unsigned int)htonl((unsigned int)len);
+	sum += ulen;
+
+	uproto = (__force unsigned int)htonl(proto);
+	sum += uproto;
+
+	/*
+	 * Zbb support saves 4 instructions, so not worth checking without
+	 * alternatives if supported
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		unsigned long fold_temp;
+
+		/*
+		 * Zbb is likely available when the kernel is compiled with Zbb
+		 * support, so nop when Zbb is available and jump when Zbb is
+		 * not available.
+		 */
+		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+				  :
+				  :
+				  :
+				  : no_zbb);
+		asm(".option push					\n\
+		.option arch,+zbb					\n\
+			rori	%[fold_temp], %[sum], 32		\n\
+			add	%[sum], %[fold_temp], %[sum]		\n\
+			srli	%[sum], %[sum], 32			\n\
+			not	%[fold_temp], %[sum]			\n\
+			roriw	%[sum], %[sum], 16			\n\
+			subw	%[sum], %[fold_temp], %[sum]		\n\
+		.option pop"
+		: [sum] "+r" (sum), [fold_temp] "=&r" (fold_temp));
+		return (__force __sum16)(sum >> 16);
+	}
+no_zbb:
+	sum += ror64(sum, 32);
+	sum >>= 32;
+	return csum_fold((__force __wsum)sum);
+}
+EXPORT_SYMBOL(csum_ipv6_magic);
+#endif /* !CONFIG_32BIT */
+
+#ifdef CONFIG_32BIT
+#define OFFSET_MASK 3
+#elif CONFIG_64BIT
+#define OFFSET_MASK 7
+#endif
+
+static inline __no_sanitize_address unsigned long
+do_csum_common(const unsigned long *ptr, const unsigned long *end,
+	       unsigned long data)
+{
+	unsigned int shift;
+	unsigned long csum = 0, carry = 0;
+
+	/*
+	 * Do 32-bit reads on RV32 and 64-bit reads otherwise. This should be
+	 * faster than doing 32-bit reads on architectures that support larger
+	 * reads.
+	 */
+	while (ptr < end) {
+		csum += data;
+		carry += csum < data;
+		data = *(ptr++);
+	}
+
+	/*
+	 * Perform alignment (and over-read) bytes on the tail if any bytes
+	 * leftover.
+	 */
+	shift = ((long)ptr - (long)end) * 8;
+#ifdef __LITTLE_ENDIAN
+	data = (data << shift) >> shift;
+#else
+	data = (data >> shift) << shift;
+#endif
+	csum += data;
+	carry += csum < data;
+	csum += carry;
+	csum += csum < carry;
+
+	return csum;
+}
+
+/*
+ * Algorithm accounts for buff being misaligned.
+ * If buff is not aligned, will over-read bytes but not use the bytes that it
+ * shouldn't. The same thing will occur on the tail-end of the read.
+ */
+static inline __no_sanitize_address unsigned int
+do_csum_with_alignment(const unsigned char *buff, int len)
+{
+	unsigned int offset, shift;
+	unsigned long csum, data;
+	const unsigned long *ptr, *end;
+
+	/*
+	 * Align address to closest word (double word on rv64) that comes before
+	 * buff. This should always be in the same page and cache line.
+	 * Directly call KASAN with the alignment we will be using.
+	 */
+	offset = (unsigned long)buff & OFFSET_MASK;
+	kasan_check_read(buff, len);
+	ptr = (const unsigned long *)(buff - offset);
+
+	/*
+	 * Clear the most significant bytes that were over-read if buff was not
+	 * aligned.
+	 */
+	shift = offset * 8;
+	data = *(ptr++);
+#ifdef __LITTLE_ENDIAN
+	data = (data >> shift) << shift;
+#else
+	data = (data << shift) >> shift;
+#endif
+	end = (const unsigned long *)(buff + len);
+	csum = do_csum_common(ptr, end, data);
+
+	/*
+	 * Zbb support saves 6 instructions, so not worth checking without
+	 * alternatives if supported
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		unsigned long fold_temp;
+
+		/*
+		 * Zbb is likely available when the kernel is compiled with Zbb
+		 * support, so nop when Zbb is available and jump when Zbb is
+		 * not available.
+		 */
+		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+				  :
+				  :
+				  :
+				  : no_zbb);
+
+#ifdef CONFIG_32BIT
+		asm_volatile_goto(".option push			\n\
+		.option arch,+zbb				\n\
+			rori	%[fold_temp], %[csum], 16	\n\
+			andi	%[offset], %[offset], 1		\n\
+			add	%[csum], %[fold_temp], %[csum]	\n\
+			beq	%[offset], zero, %l[end]	\n\
+			rev8	%[csum], %[csum]		\n\
+		.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+			: [offset] "r" (offset)
+			:
+			: end);
+
+		return (unsigned short)csum;
+#else /* !CONFIG_32BIT */
+		asm_volatile_goto(".option push			\n\
+		.option arch,+zbb				\n\
+			rori	%[fold_temp], %[csum], 32	\n\
+			add	%[csum], %[fold_temp], %[csum]	\n\
+			srli	%[csum], %[csum], 32		\n\
+			roriw	%[fold_temp], %[csum], 16	\n\
+			addw	%[csum], %[fold_temp], %[csum]	\n\
+			andi	%[offset], %[offset], 1		\n\
+			beq	%[offset], zero, %l[end]	\n\
+			rev8	%[csum], %[csum]		\n\
+		.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+			: [offset] "r" (offset)
+			:
+			: end);
+
+		return (csum << 16) >> 48;
+#endif /* !CONFIG_32BIT */
+end:
+		return csum >> 16;
+	}
+no_zbb:
+#ifndef CONFIG_32BIT
+	csum += ror64(csum, 32);
+	csum >>= 32;
+#endif
+	csum = (u32)csum + ror32((u32)csum, 16);
+	if (offset & 1)
+		return (u16)swab32(csum);
+	return csum >> 16;
+}
+
+/*
+ * Does not perform alignment, should only be used if machine has fast
+ * misaligned accesses, or when buff is known to be aligned.
+ */
+static inline __no_sanitize_address unsigned int
+do_csum_no_alignment(const unsigned char *buff, int len)
+{
+	unsigned long csum, data;
+	const unsigned long *ptr, *end;
+
+	ptr = (const unsigned long *)(buff);
+	data = *(ptr++);
+
+	kasan_check_read(buff, len);
+
+	end = (const unsigned long *)(buff + len);
+	csum = do_csum_common(ptr, end, data);
+
+	/*
+	 * Zbb support saves 6 instructions, so not worth checking without
+	 * alternatives if supported
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		unsigned long fold_temp;
+
+		/*
+		 * Zbb is likely available when the kernel is compiled with Zbb
+		 * support, so nop when Zbb is available and jump when Zbb is
+		 * not available.
+		 */
+		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+				  :
+				  :
+				  :
+				  : no_zbb);
+
+#ifdef CONFIG_32BIT
+		asm (".option push				\n\
+		.option arch,+zbb				\n\
+			rori	%[fold_temp], %[csum], 16	\n\
+			add	%[csum], %[fold_temp], %[csum]	\n\
+		.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+			:
+			: );
+
+#else /* !CONFIG_32BIT */
+		asm (".option push				\n\
+		.option arch,+zbb				\n\
+			rori	%[fold_temp], %[csum], 32	\n\
+			add	%[csum], %[fold_temp], %[csum]	\n\
+			srli	%[csum], %[csum], 32		\n\
+			roriw	%[fold_temp], %[csum], 16	\n\
+			addw	%[csum], %[fold_temp], %[csum]	\n\
+		.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)
+			:
+			: );
+#endif /* !CONFIG_32BIT */
+		return csum >> 16;
+	}
+no_zbb:
+#ifndef CONFIG_32BIT
+	csum += ror64(csum, 32);
+	csum >>= 32;
+#endif
+	csum = (u32)csum + ror32((u32)csum, 16);
+	return csum >> 16;
+}
+
+/*
+ * Perform a checksum on an arbitrary memory address.
+ * Will do a light-weight address alignment if buff is misaligned, unless
+ * cpu supports fast misaligned accesses.
+ */
+unsigned int do_csum(const unsigned char *buff, int len)
+{
+	if (unlikely(len <= 0))
+		return 0;
+
+	/*
+	 * Significant performance gains can be seen by not doing alignment
+	 * on machines with fast misaligned accesses.
+	 *
+	 * There is some duplicate code between the "with_alignment" and
+	 * "no_alignment" implmentations, but the overlap is too awkward to be
+	 * able to fit in one function without introducing multiple static
+	 * branches. The largest chunk of overlap was delegated into the
+	 * do_csum_common function.
+	 */
+	if (static_branch_likely(&fast_misaligned_access_speed_key))
+		return do_csum_no_alignment(buff, len);
+
+	if (((unsigned long)buff & OFFSET_MASK) == 0)
+		return do_csum_no_alignment(buff, len);
+
+	return do_csum_with_alignment(buff, len);
+}
-- 
GitLab


From 6f4c45cbcb00d649475a3099235e5b4fce569b4b Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Mon, 8 Jan 2024 15:57:06 -0800
Subject: [PATCH 2881/4076] kunit: Add tests for csum_ipv6_magic and
 ip_fast_csum

Supplement existing checksum tests with tests for csum_ipv6_magic and
ip_fast_csum.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240108-optimize_checksum-v15-5-1c50de5f2167@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 lib/checksum_kunit.c | 284 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 283 insertions(+), 1 deletion(-)

diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c
index 0eed92b77ba37..af3e5ca4e1702 100644
--- a/lib/checksum_kunit.c
+++ b/lib/checksum_kunit.c
@@ -1,15 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * Test cases csum_partial and csum_fold
+ * Test cases csum_partial, csum_fold, ip_fast_csum, csum_ipv6_magic
  */
 
 #include <kunit/test.h>
 #include <asm/checksum.h>
+#include <net/ip6_checksum.h>
 
 #define MAX_LEN 512
 #define MAX_ALIGN 64
 #define TEST_BUFLEN (MAX_LEN + MAX_ALIGN)
 
+#define IPv4_MIN_WORDS 5
+#define IPv4_MAX_WORDS 15
+#define NUM_IPv6_TESTS 200
+#define NUM_IP_FAST_CSUM_TESTS 181
+
 /* Values for a little endian CPU. Byte swap each half on big endian CPU. */
 static const u32 random_init_sum = 0x2847aab;
 static const u8 random_buf[] = {
@@ -209,6 +215,237 @@ static const u32 init_sums_no_overflow[] = {
 	0xffff0000, 0xfffffffb,
 };
 
+static const __sum16 expected_csum_ipv6_magic[] = {
+	0x18d4, 0x3085, 0x2e4b, 0xd9f4, 0xbdc8, 0x78f,	0x1034, 0x8422, 0x6fc0,
+	0xd2f6, 0xbeb5, 0x9d3,	0x7e2a, 0x312e, 0x778e, 0xc1bb, 0x7cf2, 0x9d1e,
+	0xca21, 0xf3ff, 0x7569, 0xb02e, 0xca86, 0x7e76, 0x4539, 0x45e3, 0xf28d,
+	0xdf81, 0x8fd5, 0x3b5d, 0x8324, 0xf471, 0x83be, 0x1daf, 0x8c46, 0xe682,
+	0xd1fb, 0x6b2e, 0xe687, 0x2a33, 0x4833, 0x2d67, 0x660f, 0x2e79, 0xd65e,
+	0x6b62, 0x6672, 0x5dbd, 0x8680, 0xbaa5, 0x2229, 0x2125, 0x2d01, 0x1cc0,
+	0x6d36, 0x33c0, 0xee36, 0xd832, 0x9820, 0x8a31, 0x53c5, 0x2e2,	0xdb0e,
+	0x49ed, 0x17a7, 0x77a0, 0xd72e, 0x3d72, 0x7dc8, 0x5b17, 0xf55d, 0xa4d9,
+	0x1446, 0x5d56, 0x6b2e, 0x69a5, 0xadb6, 0xff2a, 0x92e,	0xe044, 0x3402,
+	0xbb60, 0xec7f, 0xe7e6, 0x1986, 0x32f4, 0x8f8,	0x5e00, 0x47c6, 0x3059,
+	0x3969, 0xe957, 0x4388, 0x2854, 0x3334, 0xea71, 0xa6de, 0x33f9, 0x83fc,
+	0x37b4, 0x5531, 0x3404, 0x1010, 0xed30, 0x610a, 0xc95,	0x9aed, 0x6ff,
+	0x5136, 0x2741, 0x660e, 0x8b80, 0xf71,	0xa263, 0x88af, 0x7a73, 0x3c37,
+	0x1908, 0x6db5, 0x2e92, 0x1cd2, 0x70c8, 0xee16, 0xe80,	0xcd55, 0x6e6,
+	0x6434, 0x127,	0x655d, 0x2ea0, 0xb4f4, 0xdc20, 0x5671, 0xe462, 0xe52b,
+	0xdb44, 0x3589, 0xc48f, 0xe60b, 0xd2d2, 0x66ad, 0x498,	0x436,	0xb917,
+	0xf0ca, 0x1a6e, 0x1cb7, 0xbf61, 0x2870, 0xc7e8, 0x5b30, 0xe4a5, 0x168,
+	0xadfc, 0xd035, 0xe690, 0xe283, 0xfb27, 0xe4ad, 0xb1a5, 0xf2d5, 0xc4b6,
+	0x8a30, 0xd7d5, 0x7df9, 0x91d5, 0x63ed, 0x2d21, 0x312b, 0xab19, 0xa632,
+	0x8d2e, 0xef06, 0x57b9, 0xc373, 0xbd1f, 0xa41f, 0x8444, 0x9975, 0x90cb,
+	0xc49c, 0xe965, 0x4eff, 0x5a,	0xef6d, 0xe81a, 0xe260, 0x853a, 0xff7a,
+	0x99aa, 0xb06b, 0xee19, 0xcc2c, 0xf34c, 0x7c49, 0xdac3, 0xa71e, 0xc988,
+	0x3845, 0x1014
+};
+
+static const __sum16 expected_fast_csum[] = {
+	0xda83, 0x45da, 0x4f46, 0x4e4f, 0x34e,	0xe902, 0xa5e9, 0x87a5, 0x7187,
+	0x5671, 0xf556, 0x6df5, 0x816d, 0x8f81, 0xbb8f, 0xfbba, 0x5afb, 0xbe5a,
+	0xedbe, 0xabee, 0x6aac, 0xe6b,	0xea0d, 0x67ea, 0x7e68, 0x8a7e, 0x6f8a,
+	0x3a70, 0x9f3a, 0xe89e, 0x75e8, 0x7976, 0xfa79, 0x2cfa, 0x3c2c, 0x463c,
+	0x7146, 0x7a71, 0x547a, 0xfd53, 0x99fc, 0xb699, 0x92b6, 0xdb91, 0xe8da,
+	0x5fe9, 0x1e60, 0xae1d, 0x39ae, 0xf439, 0xa1f4, 0xdda1, 0xede,	0x790f,
+	0x579,	0x1206, 0x9012, 0x2490, 0xd224, 0x5cd2, 0xa65d, 0xca7,	0x220d,
+	0xf922, 0xbf9,	0x920b, 0x1b92, 0x361c, 0x2e36, 0x4d2e, 0x24d,	0x2,
+	0xcfff, 0x90cf, 0xa591, 0x93a5, 0x7993, 0x9579, 0xc894, 0x50c8, 0x5f50,
+	0xd55e, 0xcad5, 0xf3c9, 0x8f4,	0x4409, 0x5043, 0x5b50, 0x55b,	0x2205,
+	0x1e22, 0x801e, 0x3780, 0xe137, 0x7ee0, 0xf67d, 0x3cf6, 0xa53c, 0x2ea5,
+	0x472e, 0x5147, 0xcf51, 0x1bcf, 0x951c, 0x1e95, 0xc71e, 0xe4c7, 0xc3e4,
+	0x3dc3, 0xee3d, 0xa4ed, 0xf9a4, 0xcbf8, 0x75cb, 0xb375, 0x50b4, 0x3551,
+	0xf835, 0x19f8, 0x8c1a, 0x538c, 0xad52, 0xa3ac, 0xb0a3, 0x5cb0, 0x6c5c,
+	0x5b6c, 0xc05a, 0x92c0, 0x4792, 0xbe47, 0x53be, 0x1554, 0x5715, 0x4b57,
+	0xe54a, 0x20e5, 0x21,	0xd500, 0xa1d4, 0xa8a1, 0x57a9, 0xca57, 0x5ca,
+	0x1c06, 0x4f1c, 0xe24e, 0xd9e2, 0xf0d9, 0x4af1, 0x474b, 0x8146, 0xe81,
+	0xfd0e, 0x84fd, 0x7c85, 0xba7c, 0x17ba, 0x4a17, 0x964a, 0xf595, 0xff5,
+	0x5310, 0x3253, 0x6432, 0x4263, 0x2242, 0xe121, 0x32e1, 0xf632, 0xc5f5,
+	0x21c6, 0x7d22, 0x8e7c, 0x418e, 0x5641, 0x3156, 0x7c31, 0x737c, 0x373,
+	0x2503, 0xc22a, 0x3c2,	0x4a04, 0x8549, 0x5285, 0xa352, 0xe8a3, 0x6fe8,
+	0x1a6f, 0x211a, 0xe021, 0x38e0, 0x7638, 0xf575, 0x9df5, 0x169e, 0xf116,
+	0x23f1, 0xcd23, 0xece,	0x660f, 0x4866, 0x6a48, 0x716a, 0xee71, 0xa2ee,
+	0xb8a2, 0x61b9, 0xa361, 0xf7a2, 0x26f7, 0x1127, 0x6611, 0xe065, 0x36e0,
+	0x1837, 0x3018, 0x1c30, 0x721b, 0x3e71, 0xe43d, 0x99e4, 0x9e9a, 0xb79d,
+	0xa9b7, 0xcaa,	0xeb0c, 0x4eb,	0x1305, 0x8813, 0xb687, 0xa9b6, 0xfba9,
+	0xd7fb, 0xccd8, 0x2ecd, 0x652f, 0xae65, 0x3fae, 0x3a40, 0x563a, 0x7556,
+	0x2776, 0x1228, 0xef12, 0xf9ee, 0xcef9, 0x56cf, 0xa956, 0x24a9, 0xba24,
+	0x5fba, 0x665f, 0xf465, 0x8ff4, 0x6d8f, 0x346d, 0x5f34, 0x385f, 0xd137,
+	0xb8d0, 0xacb8, 0x55ac, 0x7455, 0xe874, 0x89e8, 0xd189, 0xa0d1, 0xb2a0,
+	0xb8b2, 0x36b8, 0x5636, 0xd355, 0x8d3,	0x1908, 0x2118, 0xc21,	0x990c,
+	0x8b99, 0x158c, 0x7815, 0x9e78, 0x6f9e, 0x4470, 0x1d44, 0x341d, 0x2634,
+	0x3f26, 0x793e, 0xc79,	0xcc0b, 0x26cc, 0xd126, 0x1fd1, 0xb41f, 0xb6b4,
+	0x22b7, 0xa122, 0xa1,	0x7f01, 0x837e, 0x3b83, 0xaf3b, 0x6fae, 0x916f,
+	0xb490, 0xffb3, 0xceff, 0x50cf, 0x7550, 0x7275, 0x1272, 0x2613, 0xaa26,
+	0xd5aa, 0x7d5,	0x9607, 0x96,	0xb100, 0xf8b0, 0x4bf8, 0xdd4c, 0xeddd,
+	0x98ed, 0x2599, 0x9325, 0xeb92, 0x8feb, 0xcc8f, 0x2acd, 0x392b, 0x3b39,
+	0xcb3b, 0x6acb, 0xd46a, 0xb8d4, 0x6ab8, 0x106a, 0x2f10, 0x892f, 0x789,
+	0xc806, 0x45c8, 0x7445, 0x3c74, 0x3a3c, 0xcf39, 0xd7ce, 0x58d8, 0x6e58,
+	0x336e, 0x1034, 0xee10, 0xe9ed, 0xc2e9, 0x3fc2, 0xd53e, 0xd2d4, 0xead2,
+	0x8fea, 0x2190, 0x1162, 0xbe11, 0x8cbe, 0x6d8c, 0xfb6c, 0x6dfb, 0xd36e,
+	0x3ad3, 0xf3a,	0x870e, 0xc287, 0x53c3, 0xc54,	0x5b0c, 0x7d5a, 0x797d,
+	0xec79, 0x5dec, 0x4d5e, 0x184e, 0xd618, 0x60d6, 0xb360, 0x98b3, 0xf298,
+	0xb1f2, 0x69b1, 0xf969, 0xef9,	0xab0e, 0x21ab, 0xe321, 0x24e3, 0x8224,
+	0x5481, 0x5954, 0x7a59, 0xff7a, 0x7dff, 0x1a7d, 0xa51a, 0x46a5, 0x6b47,
+	0xe6b,	0x830e, 0xa083, 0xff9f, 0xd0ff, 0xffd0, 0xe6ff, 0x7de7, 0xc67d,
+	0xd0c6, 0x61d1, 0x3a62, 0xc3b,	0x150c, 0x1715, 0x4517, 0x5345, 0x3954,
+	0xdd39, 0xdadd, 0x32db, 0x6a33, 0xd169, 0x86d1, 0xb687, 0x3fb6, 0x883f,
+	0xa487, 0x39a4, 0x2139, 0xbe20, 0xffbe, 0xedfe, 0x8ded, 0x368e, 0xc335,
+	0x51c3, 0x9851, 0xf297, 0xd6f2, 0xb9d6, 0x95ba, 0x2096, 0xea1f, 0x76e9,
+	0x4e76, 0xe04d, 0xd0df, 0x80d0, 0xa280, 0xfca2, 0x75fc, 0xef75, 0x32ef,
+	0x6833, 0xdf68, 0xc4df, 0x76c4, 0xb77,	0xb10a, 0xbfb1, 0x58bf, 0x5258,
+	0x4d52, 0x6c4d, 0x7e6c, 0xb67e, 0xccb5, 0x8ccc, 0xbe8c, 0xc8bd, 0x9ac8,
+	0xa99b, 0x52a9, 0x2f53, 0xc30,	0x3e0c, 0xb83d, 0x83b7, 0x5383, 0x7e53,
+	0x4f7e, 0xe24e, 0xb3e1, 0x8db3, 0x618e, 0xc861, 0xfcc8, 0x34fc, 0x9b35,
+	0xaa9b, 0xb1aa, 0x5eb1, 0x395e, 0x8639, 0xd486, 0x8bd4, 0x558b, 0x2156,
+	0xf721, 0x4ef6, 0x14f,	0x7301, 0xdd72, 0x49de, 0x894a, 0x9889, 0x8898,
+	0x7788, 0x7b77, 0x637b, 0xb963, 0xabb9, 0x7cab, 0xc87b, 0x21c8, 0xcb21,
+	0xdfca, 0xbfdf, 0xf2bf, 0x6af2, 0x626b, 0xb261, 0x3cb2, 0xc63c, 0xc9c6,
+	0xc9c9, 0xb4c9, 0xf9b4, 0x91f9, 0x4091, 0x3a40, 0xcc39, 0xd1cb, 0x7ed1,
+	0x537f, 0x6753, 0xa167, 0xba49, 0x88ba, 0x7789, 0x3877, 0xf037, 0xd3ef,
+	0xb5d4, 0x55b6, 0xa555, 0xeca4, 0xa1ec, 0xb6a2, 0x7b7,	0x9507, 0xfd94,
+	0x82fd, 0x5c83, 0x765c, 0x9676, 0x3f97, 0xda3f, 0x6fda, 0x646f, 0x3064,
+	0x5e30, 0x655e, 0x6465, 0xcb64, 0xcdca, 0x4ccd, 0x3f4c, 0x243f, 0x6f24,
+	0x656f, 0x6065, 0x3560, 0x3b36, 0xac3b, 0x4aac, 0x714a, 0x7e71, 0xda7e,
+	0x7fda, 0xda7f, 0x6fda, 0xff6f, 0xc6ff, 0xedc6, 0xd4ed, 0x70d5, 0xeb70,
+	0xa3eb, 0x80a3, 0xca80, 0x3fcb, 0x2540, 0xf825, 0x7ef8, 0xf87e, 0x73f8,
+	0xb474, 0xb4b4, 0x92b5, 0x9293, 0x93,	0x3500, 0x7134, 0x9071, 0xfa8f,
+	0x51fa, 0x1452, 0xba13, 0x7ab9, 0x957a, 0x8a95, 0x6e8a, 0x6d6e, 0x7c6d,
+	0x447c, 0x9744, 0x4597, 0x8945, 0xef88, 0x8fee, 0x3190, 0x4831, 0x8447,
+	0xa183, 0x1da1, 0xd41d, 0x2dd4, 0x4f2e, 0xc94e, 0xcbc9, 0xc9cb, 0x9ec9,
+	0x319e, 0xd531, 0x20d5, 0x4021, 0xb23f, 0x29b2, 0xd828, 0xecd8, 0x5ded,
+	0xfc5d, 0x4dfc, 0xd24d, 0x6bd2, 0x5f6b, 0xb35e, 0x7fb3, 0xee7e, 0x56ee,
+	0xa657, 0x68a6, 0x8768, 0x7787, 0xb077, 0x4cb1, 0x764c, 0xb175, 0x7b1,
+	0x3d07, 0x603d, 0x3560, 0x3e35, 0xb03d, 0xd6b0, 0xc8d6, 0xd8c8, 0x8bd8,
+	0x3e8c, 0x303f, 0xd530, 0xf1d4, 0x42f1, 0xca42, 0xddca, 0x41dd, 0x3141,
+	0x132,	0xe901, 0x8e9,	0xbe09, 0xe0bd, 0x2ce0, 0x862d, 0x3986, 0x9139,
+	0x6d91, 0x6a6d, 0x8d6a, 0x1b8d, 0xac1b, 0xedab, 0x54ed, 0xc054, 0xcebf,
+	0xc1ce, 0x5c2,	0x3805, 0x6038, 0x5960, 0xd359, 0xdd3,	0xbe0d, 0xafbd,
+	0x6daf, 0x206d, 0x2c20, 0x862c, 0x8e86, 0xec8d, 0xa2ec, 0xa3a2, 0x51a3,
+	0x8051, 0xfd7f, 0x91fd, 0xa292, 0xaf14, 0xeeae, 0x59ef, 0x535a, 0x8653,
+	0x3986, 0x9539, 0xb895, 0xa0b8, 0x26a0, 0x2227, 0xc022, 0x77c0, 0xad77,
+	0x46ad, 0xaa46, 0x60aa, 0x8560, 0x4785, 0xd747, 0x45d7, 0x2346, 0x5f23,
+	0x25f,	0x1d02, 0x71d,	0x8206, 0xc82,	0x180c, 0x3018, 0x4b30, 0x4b,
+	0x3001, 0x1230, 0x2d12, 0x8c2d, 0x148d, 0x4015, 0x5f3f, 0x3d5f, 0x6b3d,
+	0x396b, 0x473a, 0xf746, 0x44f7, 0x8945, 0x3489, 0xcb34, 0x84ca, 0xd984,
+	0xf0d9, 0xbcf0, 0x63bd, 0x3264, 0xf332, 0x45f3, 0x7346, 0x5673, 0xb056,
+	0xd3b0, 0x4ad4, 0x184b, 0x7d18, 0x6c7d, 0xbb6c, 0xfeba, 0xe0fe, 0x10e1,
+	0x5410, 0x2954, 0x9f28, 0x3a9f, 0x5a3a, 0xdb59, 0xbdc,	0xb40b, 0x1ab4,
+	0x131b, 0x5d12, 0x6d5c, 0xe16c, 0xb0e0, 0x89b0, 0xba88, 0xbb,	0x3c01,
+	0xe13b, 0x6fe1, 0x446f, 0xa344, 0x81a3, 0xfe81, 0xc7fd, 0x38c8, 0xb38,
+	0x1a0b, 0x6d19, 0xf36c, 0x47f3, 0x6d48, 0xb76d, 0xd3b7, 0xd8d2, 0x52d9,
+	0x4b53, 0xa54a, 0x34a5, 0xc534, 0x9bc4, 0xed9b, 0xbeed, 0x3ebe, 0x233e,
+	0x9f22, 0x4a9f, 0x774b, 0x4577, 0xa545, 0x64a5, 0xb65,	0x870b, 0x487,
+	0x9204, 0x5f91, 0xd55f, 0x35d5, 0x1a35, 0x71a,	0x7a07, 0x4e7a, 0xfc4e,
+	0x1efc, 0x481f, 0x7448, 0xde74, 0xa7dd, 0x1ea7, 0xaa1e, 0xcfaa, 0xfbcf,
+	0xedfb, 0x6eee, 0x386f, 0x4538, 0x6e45, 0xd96d, 0x11d9, 0x7912, 0x4b79,
+	0x494b, 0x6049, 0xac5f, 0x65ac, 0x1366, 0x5913, 0xe458, 0x7ae4, 0x387a,
+	0x3c38, 0xb03c, 0x76b0, 0x9376, 0xe193, 0x42e1, 0x7742, 0x6476, 0x3564,
+	0x3c35, 0x6a3c, 0xcc69, 0x94cc, 0x5d95, 0xe5e,	0xee0d, 0x4ced, 0xce4c,
+	0x52ce, 0xaa52, 0xdaaa, 0xe4da, 0x1de5, 0x4530, 0x5445, 0x3954, 0xb639,
+	0x81b6, 0x7381, 0x1574, 0xc215, 0x10c2, 0x3f10, 0x6b3f, 0xe76b, 0x7be7,
+	0xbc7b, 0xf7bb, 0x41f7, 0xcc41, 0x38cc, 0x4239, 0xa942, 0x4a9,	0xc504,
+	0x7cc4, 0x437c, 0x6743, 0xea67, 0x8dea, 0xe88d, 0xd8e8, 0xdcd8, 0x17dd,
+	0x5718, 0x958,	0xa609, 0x41a5, 0x5842, 0x159,	0x9f01, 0x269f, 0x5a26,
+	0x405a, 0xc340, 0xb4c3, 0xd4b4, 0xf4d3, 0xf1f4, 0x39f2, 0xe439, 0x67e4,
+	0x4168, 0xa441, 0xdda3, 0xdedd, 0x9df,	0xab0a, 0xa5ab, 0x9a6,	0xba09,
+	0x9ab9, 0xad9a, 0x5ae,	0xe205, 0xece2, 0xecec, 0x14ed, 0xd614, 0x6bd5,
+	0x916c, 0x3391, 0x6f33, 0x206f, 0x8020, 0x780,	0x7207, 0x2472, 0x8a23,
+	0xb689, 0x3ab6, 0xf739, 0x97f6, 0xb097, 0xa4b0, 0xe6a4, 0x88e6, 0x2789,
+	0xb28,	0x350b, 0x1f35, 0x431e, 0x1043, 0xc30f, 0x79c3, 0x379,	0x5703,
+	0x3256, 0x4732, 0x7247, 0x9d72, 0x489d, 0xd348, 0xa4d3, 0x7ca4, 0xbf7b,
+	0x45c0, 0x7b45, 0x337b, 0x4034, 0x843f, 0xd083, 0x35d0, 0x6335, 0x4d63,
+	0xe14c, 0xcce0, 0xfecc, 0x35ff, 0x5636, 0xf856, 0xeef8, 0x2def, 0xfc2d,
+	0x4fc,	0x6e04, 0xb66d, 0x78b6, 0xbb78, 0x3dbb, 0x9a3d, 0x839a, 0x9283,
+	0x593,	0xd504, 0x23d5, 0x5424, 0xd054, 0x61d0, 0xdb61, 0x17db, 0x1f18,
+	0x381f, 0x9e37, 0x679e, 0x1d68, 0x381d, 0x8038, 0x917f, 0x491,	0xbb04,
+	0x23bb, 0x4124, 0xd41,	0xa30c, 0x8ba3, 0x8b8b, 0xc68b, 0xd2c6, 0xebd2,
+	0x93eb, 0xbd93, 0x99bd, 0x1a99, 0xea19, 0x58ea, 0xcf58, 0x73cf, 0x1073,
+	0x9e10, 0x139e, 0xea13, 0xcde9, 0x3ecd, 0x883f, 0xf89,	0x180f, 0x2a18,
+	0x212a, 0xce20, 0x73ce, 0xf373, 0x60f3, 0xad60, 0x4093, 0x8e40, 0xb98e,
+	0xbfb9, 0xf1bf, 0x8bf1, 0x5e8c, 0xe95e, 0x14e9, 0x4e14, 0x1c4e, 0x7f1c,
+	0xe77e, 0x6fe7, 0xf26f, 0x13f2, 0x8b13, 0xda8a, 0x5fda, 0xea5f, 0x4eea,
+	0xa84f, 0x88a8, 0x1f88, 0x2820, 0x9728, 0x5a97, 0x3f5b, 0xb23f, 0x70b2,
+	0x2c70, 0x232d, 0xf623, 0x4f6,	0x905,	0x7509, 0xd675, 0x28d7, 0x9428,
+	0x3794, 0xf036, 0x2bf0, 0xba2c, 0xedb9, 0xd7ed, 0x59d8, 0xed59, 0x4ed,
+	0xe304, 0x18e3, 0x5c19, 0x3d5c, 0x753d, 0x6d75, 0x956d, 0x7f95, 0xc47f,
+	0x83c4, 0xa84,	0x2e0a, 0x5f2e, 0xb95f, 0x77b9, 0x6d78, 0xf46d, 0x1bf4,
+	0xed1b, 0xd6ed, 0xe0d6, 0x5e1,	0x3905, 0x5638, 0xa355, 0x99a2, 0xbe99,
+	0xb4bd, 0x85b4, 0x2e86, 0x542e, 0x6654, 0xd765, 0x73d7, 0x3a74, 0x383a,
+	0x2638, 0x7826, 0x7677, 0x9a76, 0x7e99, 0x2e7e, 0xea2d, 0xa6ea, 0x8a7,
+	0x109,	0x3300, 0xad32, 0x5fad, 0x465f, 0x2f46, 0xc62f, 0xd4c5, 0xad5,
+	0xcb0a, 0x4cb,	0xb004, 0x7baf, 0xe47b, 0x92e4, 0x8e92, 0x638e, 0x1763,
+	0xc17,	0xf20b, 0x1ff2, 0x8920, 0x5889, 0xcb58, 0xf8cb, 0xcaf8, 0x84cb,
+	0x9f84, 0x8a9f, 0x918a, 0x4991, 0x8249, 0xff81, 0x46ff, 0x5046, 0x5f50,
+	0x725f, 0xf772, 0x8ef7, 0xe08f, 0xc1e0, 0x1fc2, 0x9e1f, 0x8b9d, 0x108b,
+	0x411,	0x2b04, 0xb02a, 0x1fb0, 0x1020, 0x7a0f, 0x587a, 0x8958, 0xb188,
+	0xb1b1, 0x49b2, 0xb949, 0x7ab9, 0x917a, 0xfc91, 0xe6fc, 0x47e7, 0xbc47,
+	0x8fbb, 0xea8e, 0x34ea, 0x2635, 0x1726, 0x9616, 0xc196, 0xa6c1, 0xf3a6,
+	0x11f3, 0x4811, 0x3e48, 0xeb3e, 0xf7ea, 0x1bf8, 0xdb1c, 0x8adb, 0xe18a,
+	0x42e1, 0x9d42, 0x5d9c, 0x6e5d, 0x286e, 0x4928, 0x9a49, 0xb09c, 0xa6b0,
+	0x2a7,	0xe702, 0xf5e6, 0x9af5, 0xf9b,	0x810f, 0x8080, 0x180,	0x1702,
+	0x5117, 0xa650, 0x11a6, 0x1011, 0x550f, 0xd554, 0xbdd5, 0x6bbe, 0xc66b,
+	0xfc7,	0x5510, 0x5555, 0x7655, 0x177,	0x2b02, 0x6f2a, 0xb70,	0x9f0b,
+	0xcf9e, 0xf3cf, 0x3ff4, 0xcb40, 0x8ecb, 0x768e, 0x5277, 0x8652, 0x9186,
+	0x9991, 0x5099, 0xd350, 0x93d3, 0x6d94, 0xe6d,	0x530e, 0x3153, 0xa531,
+	0x64a5, 0x7964, 0x7c79, 0x467c, 0x1746, 0x3017, 0x3730, 0x538,	0x5,
+	0x1e00, 0x5b1e, 0x955a, 0xae95, 0x3eaf, 0xff3e, 0xf8ff, 0xb2f9, 0xa1b3,
+	0xb2a1, 0x5b2,	0xad05, 0x7cac, 0x2d7c, 0xd32c, 0x80d2, 0x7280, 0x8d72,
+	0x1b8e, 0x831b, 0xac82, 0xfdac, 0xa7fd, 0x15a8, 0xd614, 0xe0d5, 0x7be0,
+	0xb37b, 0x61b3, 0x9661, 0x9d95, 0xc79d, 0x83c7, 0xd883, 0xead7, 0xceb,
+	0xf60c, 0xa9f5, 0x19a9, 0xa019, 0x8f9f, 0xd48f, 0x3ad5, 0x853a, 0x985,
+	0x5309, 0x6f52, 0x1370, 0x6e13, 0xa96d, 0x98a9, 0x5198, 0x9f51, 0xb69f,
+	0xa1b6, 0x2ea1, 0x672e, 0x2067, 0x6520, 0xaf65, 0x6eaf, 0x7e6f, 0xee7e,
+	0x17ef, 0xa917, 0xcea8, 0x9ace, 0xff99, 0x5dff, 0xdf5d, 0x38df, 0xa39,
+	0x1c0b, 0xe01b, 0x46e0, 0xcb46, 0x90cb, 0xba90, 0x4bb,	0x9104, 0x9d90,
+	0xc89c, 0xf6c8, 0x6cf6, 0x886c, 0x1789, 0xbd17, 0x70bc, 0x7e71, 0x17e,
+	0x1f01, 0xa01f, 0xbaa0, 0x14bb, 0xfc14, 0x7afb, 0xa07a, 0x3da0, 0xbf3d,
+	0x48bf, 0x8c48, 0x968b, 0x9d96, 0xfd9d, 0x96fd, 0x9796, 0x6b97, 0xd16b,
+	0xf4d1, 0x3bf4, 0x253c, 0x9125, 0x6691, 0xc166, 0x34c1, 0x5735, 0x1a57,
+	0xdc19, 0x77db, 0x8577, 0x4a85, 0x824a, 0x9182, 0x7f91, 0xfd7f, 0xb4c3,
+	0xb5b4, 0xb3b5, 0x7eb3, 0x617e, 0x4e61, 0xa4f,	0x530a, 0x3f52, 0xa33e,
+	0x34a3, 0x9234, 0xf091, 0xf4f0, 0x1bf5, 0x311b, 0x9631, 0x6a96, 0x386b,
+	0x1d39, 0xe91d, 0xe8e9, 0x69e8, 0x426a, 0xee42, 0x89ee, 0x368a, 0x2837,
+	0x7428, 0x5974, 0x6159, 0x1d62, 0x7b1d, 0xf77a, 0x7bf7, 0x6b7c, 0x696c,
+	0xf969, 0x4cf9, 0x714c, 0x4e71, 0x6b4e, 0x256c, 0x6e25, 0xe96d, 0x94e9,
+	0x8f94, 0x3e8f, 0x343e, 0x4634, 0xb646, 0x97b5, 0x8997, 0xe8a,	0x900e,
+	0x8090, 0xfd80, 0xa0fd, 0x16a1, 0xf416, 0xebf4, 0x95ec, 0x1196, 0x8911,
+	0x3d89, 0xda3c, 0x9fd9, 0xd79f, 0x4bd7, 0x214c, 0x3021, 0x4f30, 0x994e,
+	0x5c99, 0x6f5d, 0x326f, 0xab31, 0x6aab, 0xe969, 0x90e9, 0x1190, 0xff10,
+	0xa2fe, 0xe0a2, 0x66e1, 0x4067, 0x9e3f, 0x2d9e, 0x712d, 0x8170, 0xd180,
+	0xffd1, 0x25ff, 0x3826, 0x2538, 0x5f24, 0xc45e, 0x1cc4, 0xdf1c, 0x93df,
+	0xc793, 0x80c7, 0x2380, 0xd223, 0x7ed2, 0xfc7e, 0x22fd, 0x7422, 0x1474,
+	0xb714, 0x7db6, 0x857d, 0xa85,	0xa60a, 0x88a6, 0x4289, 0x7842, 0xc278,
+	0xf7c2, 0xcdf7, 0x84cd, 0xae84, 0x8cae, 0xb98c, 0x1aba, 0x4d1a, 0x884c,
+	0x4688, 0xcc46, 0xd8cb, 0x2bd9, 0xbe2b, 0xa2be, 0x72a2, 0xf772, 0xd2f6,
+	0x75d2, 0xc075, 0xa3c0, 0x63a3, 0xae63, 0x8fae, 0x2a90, 0x5f2a, 0xef5f,
+	0x5cef, 0xa05c, 0x89a0, 0x5e89, 0x6b5e, 0x736b, 0x773,	0x9d07, 0xe99c,
+	0x27ea, 0x2028, 0xc20,	0x980b, 0x4797, 0x2848, 0x9828, 0xc197, 0x48c2,
+	0x2449, 0x7024, 0x570,	0x3e05, 0xd3e,	0xf60c, 0xbbf5, 0x69bb, 0x3f6a,
+	0x740,	0xf006, 0xe0ef, 0xbbe0, 0xadbb, 0x56ad, 0xcf56, 0xbfce, 0xa9bf,
+	0x205b, 0x6920, 0xae69, 0x50ae, 0x2050, 0xf01f, 0x27f0, 0x9427, 0x8993,
+	0x8689, 0x4087, 0x6e40, 0xb16e, 0xa1b1, 0xe8a1, 0x87e8, 0x6f88, 0xfe6f,
+	0x4cfe, 0xe94d, 0xd5e9, 0x47d6, 0x3148, 0x5f31, 0xc35f, 0x13c4, 0xa413,
+	0x5a5,	0x2405, 0xc223, 0x66c2, 0x3667, 0x5e37, 0x5f5e, 0x2f5f, 0x8c2f,
+	0xe48c, 0xd0e4, 0x4d1,	0xd104, 0xe4d0, 0xcee4, 0xfcf,	0x480f, 0xa447,
+	0x5ea4, 0xff5e, 0xbefe, 0x8dbe, 0x1d8e, 0x411d, 0x1841, 0x6918, 0x5469,
+	0x1155, 0xc611, 0xaac6, 0x37ab, 0x2f37, 0xca2e, 0x87ca, 0xbd87, 0xabbd,
+	0xb3ab, 0xcb4,	0xce0c, 0xfccd, 0xa5fd, 0x72a5, 0xf072, 0x83f0, 0xfe83,
+	0x97fd, 0xc997, 0xb0c9, 0xadb0, 0xe6ac, 0x88e6, 0x1088, 0xbe10, 0x16be,
+	0xa916, 0xa3a8, 0x46a3, 0x5447, 0xe953, 0x84e8, 0x2085, 0xa11f, 0xfa1,
+	0xdd0f, 0xbedc, 0x5abe, 0x805a, 0xc97f, 0x6dc9, 0x826d, 0x4a82, 0x934a,
+	0x5293, 0xd852, 0xd3d8, 0xadd3, 0xf4ad, 0xf3f4, 0xfcf3, 0xfefc, 0xcafe,
+	0xb7ca, 0x3cb8, 0xa13c, 0x18a1, 0x1418, 0xea13, 0x91ea, 0xf891, 0x53f8,
+	0xa254, 0xe9a2, 0x87ea, 0x4188, 0x1c41, 0xdc1b, 0xf5db, 0xcaf5, 0x45ca,
+	0x6d45, 0x396d, 0xde39, 0x90dd, 0x1e91, 0x1e,	0x7b00, 0x6a7b, 0xa46a,
+	0xc9a3, 0x9bc9, 0x389b, 0x1139, 0x5211, 0x1f52, 0xeb1f, 0xabeb, 0x48ab,
+	0x9348, 0xb392, 0x17b3, 0x1618, 0x5b16, 0x175b, 0xdc17, 0xdedb, 0x1cdf,
+	0xeb1c, 0xd1ea, 0x4ad2, 0xd4b,	0xc20c, 0x24c2, 0x7b25, 0x137b, 0x8b13,
+	0x618b, 0xa061, 0xff9f, 0xfffe, 0x72ff, 0xf572, 0xe2f5, 0xcfe2, 0xd2cf,
+	0x75d3, 0x6a76, 0xc469, 0x1ec4, 0xfc1d, 0x59fb, 0x455a, 0x7a45, 0xa479,
+	0xb7a4
+};
+
 static u8 tmp_buf[TEST_BUFLEN];
 
 #define full_csum(buff, len, sum) csum_fold(csum_partial(buff, len, sum))
@@ -338,10 +575,55 @@ static void test_csum_no_carry_inputs(struct kunit *test)
 	}
 }
 
+static void test_ip_fast_csum(struct kunit *test)
+{
+	__sum16 csum_result, expected;
+
+	for (int len = IPv4_MIN_WORDS; len < IPv4_MAX_WORDS; len++) {
+		for (int index = 0; index < NUM_IP_FAST_CSUM_TESTS; index++) {
+			csum_result = ip_fast_csum(random_buf + index, len);
+			expected =
+				expected_fast_csum[(len - IPv4_MIN_WORDS) *
+						   NUM_IP_FAST_CSUM_TESTS +
+						   index];
+			CHECK_EQ(expected, csum_result);
+		}
+	}
+}
+
+static void test_csum_ipv6_magic(struct kunit *test)
+{
+	const struct in6_addr *saddr;
+	const struct in6_addr *daddr;
+	unsigned int len;
+	unsigned char proto;
+	unsigned int csum;
+
+	const int daddr_offset = sizeof(struct in6_addr);
+	const int len_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr);
+	const int proto_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr) +
+			     sizeof(int);
+	const int csum_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr) +
+			    sizeof(int) + sizeof(char);
+
+	for (int i = 0; i < NUM_IPv6_TESTS; i++) {
+		saddr = (const struct in6_addr *)(random_buf + i);
+		daddr = (const struct in6_addr *)(random_buf + i +
+						  daddr_offset);
+		len = *(unsigned int *)(random_buf + i + len_offset);
+		proto = *(random_buf + i + proto_offset);
+		csum = *(unsigned int *)(random_buf + i + csum_offset);
+		CHECK_EQ(expected_csum_ipv6_magic[i],
+			 csum_ipv6_magic(saddr, daddr, len, proto, csum));
+	}
+}
+
 static struct kunit_case __refdata checksum_test_cases[] = {
 	KUNIT_CASE(test_csum_fixed_random_inputs),
 	KUNIT_CASE(test_csum_all_carry_inputs),
 	KUNIT_CASE(test_csum_no_carry_inputs),
+	KUNIT_CASE(test_ip_fast_csum),
+	KUNIT_CASE(test_csum_ipv6_magic),
 	{}
 };
 
-- 
GitLab


From 55b71d2ce133da893ffb1ecd69a34e1fee509292 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 5 Dec 2023 16:53:50 -0700
Subject: [PATCH 2882/4076] riscv: Hoist linker relaxation disabling logic into
 Kconfig

Certain configurations may need to be disabled if linker relaxation is
in use, such as DWARF5 with ld.lld < 18. Hoist the logic of whether or
not linker relaxation is in use into Kconfig so decisions can be made at
configuration time.

Reviewed-by: Fangrui Song <maskray@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20231205-riscv-restrict-dwarf5-llvm-v2-1-aedf00a382ac@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig  | 5 +++++
 arch/riscv/Makefile | 4 +---
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a6..72be1d8122a3c 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -181,6 +181,11 @@ config HAVE_SHADOW_CALL_STACK
 	# https://github.com/riscv-non-isa/riscv-elf-psabi-doc/commit/a484e843e6eeb51f0cb7b8819e50da6d2444d769
 	depends on $(ld-option,--no-relax-gp)
 
+config RISCV_USE_LINKER_RELAXATION
+	def_bool y
+	# https://github.com/llvm/llvm-project/commit/6611d58f5bbcbec77262d392e2923e1d680f6985
+	depends on !LD_IS_LLD || LLD_VERSION >= 150000
+
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
 	default 8
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index a74be78678eb0..e383aa9e27578 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -43,8 +43,7 @@ else
 	KBUILD_LDFLAGS += -melf32lriscv
 endif
 
-ifeq ($(CONFIG_LD_IS_LLD),y)
-ifeq ($(call test-lt, $(CONFIG_LLD_VERSION), 150000),y)
+ifndef CONFIG_RISCV_USE_LINKER_RELAXATION
 	KBUILD_CFLAGS += -mno-relax
 	KBUILD_AFLAGS += -mno-relax
 ifndef CONFIG_AS_IS_LLVM
@@ -52,7 +51,6 @@ ifndef CONFIG_AS_IS_LLVM
 	KBUILD_AFLAGS += -Wa,-mno-relax
 endif
 endif
-endif
 
 ifeq ($(CONFIG_SHADOW_CALL_STACK),y)
 	KBUILD_LDFLAGS += --no-relax-gp
-- 
GitLab


From ae84ff9a14a5a8d36a329a30626800155782e617 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 5 Dec 2023 16:53:51 -0700
Subject: [PATCH 2883/4076] riscv: Restrict DWARF5 when building with LLVM to
 known working versions

LLVM prior to 18.0.0 would generate incorrect debug info for DWARF5 due
to linker relaxation, which was worked around in clang by defaulting
RISC-V to DWARF4 [1]. Unfortunately, this workaround does not work for
the kernel because the DWARF version can be independently changed from
the default in Kconfig.

Do not allow DWARF5 to be selected for RISC-V when using linker
relaxation (ld.lld >= 15.0.0) and a version of LLVM that does not have
the fixes (the integrated assembler [2] and ld.lld [3] < 18.0.0)
necessary to generate the correct debug info.

Link: https://github.com/llvm/llvm-project/commit/bbc0f99f3bc96f1db16f649fc21dd18e5b0918f6 [1]
Link: https://github.com/llvm/llvm-project/commit/1df5ea29b43690b6622db2cad7b745607ca4de6a [2]
Link: https://github.com/llvm/llvm-project/commit/7ffabb61a5569444b5ac9322e22e5471cc5e4a77 [3]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Fangrui Song <maskray@google.com>
Link: https://lore.kernel.org/r/20231205-riscv-restrict-dwarf5-llvm-v2-2-aedf00a382ac@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig | 9 +++++++++
 lib/Kconfig.debug  | 1 +
 2 files changed, 10 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 72be1d8122a3c..81b473cb47b05 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -186,6 +186,15 @@ config RISCV_USE_LINKER_RELAXATION
 	# https://github.com/llvm/llvm-project/commit/6611d58f5bbcbec77262d392e2923e1d680f6985
 	depends on !LD_IS_LLD || LLD_VERSION >= 150000
 
+# https://github.com/llvm/llvm-project/commit/bbc0f99f3bc96f1db16f649fc21dd18e5b0918f6
+config ARCH_HAS_BROKEN_DWARF5
+	def_bool y
+	depends on RISCV_USE_LINKER_RELAXATION
+	# https://github.com/llvm/llvm-project/commit/1df5ea29b43690b6622db2cad7b745607ca4de6a
+	depends on AS_IS_LLVM && AS_VERSION < 180000
+	# https://github.com/llvm/llvm-project/commit/7ffabb61a5569444b5ac9322e22e5471cc5e4a77
+	depends on LD_IS_LLD && LLD_VERSION < 180000
+
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
 	default 8
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index cc7d53d9dc019..a0ebce05a368f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -282,6 +282,7 @@ config DEBUG_INFO_DWARF4
 config DEBUG_INFO_DWARF5
 	bool "Generate DWARF Version 5 debuginfo"
 	select DEBUG_INFO
+	depends on !ARCH_HAS_BROKEN_DWARF5
 	depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128)
 	help
 	  Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc
-- 
GitLab


From a4426641f00cd2c293c91e881ab31faaf76b20fb Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 5 Dec 2023 16:53:52 -0700
Subject: [PATCH 2884/4076] lib/Kconfig.debug: Update AS_HAS_NON_CONST_LEB128
 comment and name

Fangrui noted that the comment around CONFIG_AS_HAS_NON_CONST_LEB128
could be made more accurate because explicit .sleb128 directives are not
emitted, only .uleb128 directives are. Rename the symbol to
CONFIG_AS_HAS_NON_CONST_ULEB128 as a result.

Further clarifications include replacing "symbol deltas" with the more
accurate "label differences", noting that this issue has been resolved
in newer binutils (2.41+), and it only occurs when a port uses RISC-V
style linker relaxation.

Suggested-by: Fangrui Song <maskray@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231205-riscv-restrict-dwarf5-llvm-v2-3-aedf00a382ac@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 lib/Kconfig.debug | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a0ebce05a368f..76c2cc6975731 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -231,9 +231,10 @@ config DEBUG_INFO
 	  in the "Debug information" choice below, indicating that debug
 	  information will be generated for build targets.
 
-# Clang is known to generate .{s,u}leb128 with symbol deltas with DWARF5, which
-# some targets may not support: https://sourceware.org/bugzilla/show_bug.cgi?id=27215
-config AS_HAS_NON_CONST_LEB128
+# Clang generates .uleb128 with label differences for DWARF v5, a feature that
+# older binutils ports do not support when utilizing RISC-V style linker
+# relaxation: https://sourceware.org/bugzilla/show_bug.cgi?id=27215
+config AS_HAS_NON_CONST_ULEB128
 	def_bool $(as-instr,.uleb128 .Lexpr_end4 - .Lexpr_start3\n.Lexpr_start3:\n.Lexpr_end4:)
 
 choice
@@ -258,7 +259,7 @@ config DEBUG_INFO_NONE
 config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT
 	bool "Rely on the toolchain's implicit default DWARF version"
 	select DEBUG_INFO
-	depends on !CC_IS_CLANG || AS_IS_LLVM || CLANG_VERSION < 140000 || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128)
+	depends on !CC_IS_CLANG || AS_IS_LLVM || CLANG_VERSION < 140000 || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_ULEB128)
 	help
 	  The implicit default version of DWARF debug info produced by a
 	  toolchain changes over time.
@@ -283,7 +284,7 @@ config DEBUG_INFO_DWARF5
 	bool "Generate DWARF Version 5 debuginfo"
 	select DEBUG_INFO
 	depends on !ARCH_HAS_BROKEN_DWARF5
-	depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128)
+	depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_ULEB128)
 	help
 	  Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc
 	  5.0+ accepts the -gdwarf-5 flag but only had partial support for some
-- 
GitLab


From b546d6363af4791567dcd145109837fe97cc8ba5 Mon Sep 17 00:00:00 2001
From: Song Shuai <suagrfillet@gmail.com>
Date: Thu, 30 Nov 2023 13:15:28 +0100
Subject: [PATCH 2885/4076] riscv: select
 FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In commit afc76b8b8011 ("riscv: Using PATCHABLE_FUNCTION_ENTRY instead
of MCOUNT") RISC-V added support for -fpatchable-function-entry, which
removes the need for recordmcount.

Select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY to tell the build
system not to run recordmcount.

Link: https://lore.kernel.org/linux-riscv/CAAYs2=j3Eak9vU6xbAw0zPuoh00rh8v5C2U3fePkokZFibWs2g@mail.gmail.com/T/#t
Link: https://lore.kernel.org/linux-riscv/Y4jtfrJt+%2FQ5nMOz@spud/
Signed-off-by: Song Shuai <suagrfillet@gmail.com>
Tested-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@kernel.org>
Acked-by: Björn Töpel <bjorn@rivosinc.com>
Link: https://lore.kernel.org/r/20231130121531.1178502-2-bjorn@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 95a2a06acc6a6..69c95e42be9f5 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -68,6 +68,7 @@ config RISCV
 	select CPU_PM if CPU_IDLE || HIBERNATION
 	select EDAC_SUPPORT
 	select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
+	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
 	select GENERIC_ARCH_TOPOLOGY
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
-- 
GitLab


From 35e61e8827ee8ea09e6093ab4d8ba45efd537e36 Mon Sep 17 00:00:00 2001
From: Song Shuai <suagrfillet@gmail.com>
Date: Thu, 30 Nov 2023 13:15:29 +0100
Subject: [PATCH 2886/4076] riscv: ftrace: Make function graph use ftrace
 directly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Similar to commit 0c0593b45c9b ("x86/ftrace: Make function graph use
ftrace directly") and commit c4a0ebf87ceb ("arm64/ftrace: Make
function graph use ftrace directly"), RISC-V has no need for a special
graph tracer hook. The graph_ops::func function can be used to install
the return_hooker.

This cleanup only changes the FTRACE_WITH_REGS implementation, leaving
the mcount-based implementation is unaffected.

Perform the simplification, and also cleanup the register save/restore
macros.

Signed-off-by: Song Shuai <suagrfillet@gmail.com>
Tested-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@kernel.org>
Acked-by: Björn Töpel <bjorn@rivosinc.com>
Link: https://lore.kernel.org/r/20231130121531.1178502-3-bjorn@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/ftrace.h |  11 +-
 arch/riscv/kernel/ftrace.c      |  30 +++--
 arch/riscv/kernel/mcount-dyn.S  | 190 +++++++++++++++++++++++++-------
 3 files changed, 175 insertions(+), 56 deletions(-)

diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 2b2f5df7ef2c7..b383926f73be1 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -128,7 +128,16 @@ do {									\
 struct dyn_ftrace;
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
-#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+struct ftrace_ops;
+struct ftrace_regs;
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#endif /* __ASSEMBLY__ */
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 03a6434a8cdd0..f5aa24d9e1c15 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -178,32 +178,28 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	struct pt_regs *regs = arch_ftrace_get_regs(fregs);
+	unsigned long *parent = (unsigned long *)&regs->ra;
+
+	prepare_ftrace_return(parent, ip, frame_pointer(regs));
+}
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 extern void ftrace_graph_call(void);
-extern void ftrace_graph_regs_call(void);
 int ftrace_enable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, true, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, true, true);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, false, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, false, true);
 }
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 58dd96a2a1534..c902a7ddb3106 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -57,31 +57,150 @@
 	.endm
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-	.macro SAVE_ALL
+
+/**
+* SAVE_ABI_REGS - save regs against the pt_regs struct
+*
+* @all: tell if saving all the regs
+*
+* If all is set, all the regs will be saved, otherwise only ABI
+* related regs (a0-a7,epc,ra and optional s0) will be saved.
+*
+* After the stack is established,
+*
+* 0(sp) stores the PC of the traced function which can be accessed
+* by &(fregs)->regs->epc in tracing function. Note that the real
+* function entry address should be computed with -FENTRY_RA_OFFSET.
+*
+* 8(sp) stores the function return address (i.e. parent IP) that
+* can be accessed by &(fregs)->regs->ra in tracing function.
+*
+* The other regs are saved at the respective localtion and accessed
+* by the respective pt_regs member.
+*
+* Here is the layout of stack for your reference.
+*
+* PT_SIZE_ON_STACK  ->  +++++++++
+*                       + ..... +
+*                       + t3-t6 +
+*                       + s2-s11+
+*                       + a0-a7 + --++++-> ftrace_caller saved
+*                       + s1    +   +
+*                       + s0    + --+
+*                       + t0-t2 +   +
+*                       + tp    +   +
+*                       + gp    +   +
+*                       + sp    +   +
+*                       + ra    + --+ // parent IP
+*               sp  ->  + epc   + --+ // PC
+*                       +++++++++
+**/
+	.macro SAVE_ABI_REGS, all=0
 	addi	sp, sp, -PT_SIZE_ON_STACK
 
-	REG_S t0,  PT_EPC(sp)
-	REG_S x1,  PT_RA(sp)
-	REG_S x2,  PT_SP(sp)
-	REG_S x3,  PT_GP(sp)
-	REG_S x4,  PT_TP(sp)
-	REG_S x5,  PT_T0(sp)
-	save_from_x6_to_x31
+	REG_S	t0,  PT_EPC(sp)
+	REG_S	x1,  PT_RA(sp)
+
+	// save the ABI regs
+
+	REG_S	x10, PT_A0(sp)
+	REG_S	x11, PT_A1(sp)
+	REG_S	x12, PT_A2(sp)
+	REG_S	x13, PT_A3(sp)
+	REG_S	x14, PT_A4(sp)
+	REG_S	x15, PT_A5(sp)
+	REG_S	x16, PT_A6(sp)
+	REG_S	x17, PT_A7(sp)
+
+	// save the leftover regs
+
+	.if \all == 1
+	REG_S	x2, PT_SP(sp)
+	REG_S	x3, PT_GP(sp)
+	REG_S	x4, PT_TP(sp)
+	REG_S	x5, PT_T0(sp)
+	REG_S	x6, PT_T1(sp)
+	REG_S	x7, PT_T2(sp)
+	REG_S	x8, PT_S0(sp)
+	REG_S	x9, PT_S1(sp)
+	REG_S	x18, PT_S2(sp)
+	REG_S	x19, PT_S3(sp)
+	REG_S	x20, PT_S4(sp)
+	REG_S	x21, PT_S5(sp)
+	REG_S	x22, PT_S6(sp)
+	REG_S	x23, PT_S7(sp)
+	REG_S	x24, PT_S8(sp)
+	REG_S	x25, PT_S9(sp)
+	REG_S	x26, PT_S10(sp)
+	REG_S	x27, PT_S11(sp)
+	REG_S	x28, PT_T3(sp)
+	REG_S	x29, PT_T4(sp)
+	REG_S	x30, PT_T5(sp)
+	REG_S	x31, PT_T6(sp)
+
+	// save s0 if FP_TEST defined
+
+	.else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_S	x8, PT_S0(sp)
+#endif
+	.endif
 	.endm
 
-	.macro RESTORE_ALL
-	REG_L x1,  PT_RA(sp)
-	REG_L x2,  PT_SP(sp)
-	REG_L x3,  PT_GP(sp)
-	REG_L x4,  PT_TP(sp)
-	/* Restore t0 with PT_EPC */
-	REG_L x5,  PT_EPC(sp)
-	restore_from_x6_to_x31
-
+	.macro RESTORE_ABI_REGS, all=0
+	REG_L	t0, PT_EPC(sp)
+	REG_L	x1, PT_RA(sp)
+	REG_L	x10, PT_A0(sp)
+	REG_L	x11, PT_A1(sp)
+	REG_L	x12, PT_A2(sp)
+	REG_L	x13, PT_A3(sp)
+	REG_L	x14, PT_A4(sp)
+	REG_L	x15, PT_A5(sp)
+	REG_L	x16, PT_A6(sp)
+	REG_L	x17, PT_A7(sp)
+
+	.if \all == 1
+	REG_L	x2, PT_SP(sp)
+	REG_L	x3, PT_GP(sp)
+	REG_L	x4, PT_TP(sp)
+	REG_L	x6, PT_T1(sp)
+	REG_L	x7, PT_T2(sp)
+	REG_L	x8, PT_S0(sp)
+	REG_L	x9, PT_S1(sp)
+	REG_L	x18, PT_S2(sp)
+	REG_L	x19, PT_S3(sp)
+	REG_L	x20, PT_S4(sp)
+	REG_L	x21, PT_S5(sp)
+	REG_L	x22, PT_S6(sp)
+	REG_L	x23, PT_S7(sp)
+	REG_L	x24, PT_S8(sp)
+	REG_L	x25, PT_S9(sp)
+	REG_L	x26, PT_S10(sp)
+	REG_L	x27, PT_S11(sp)
+	REG_L	x28, PT_T3(sp)
+	REG_L	x29, PT_T4(sp)
+	REG_L	x30, PT_T5(sp)
+	REG_L	x31, PT_T6(sp)
+
+	.else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_L	x8, PT_S0(sp)
+#endif
+	.endif
 	addi	sp, sp, PT_SIZE_ON_STACK
 	.endm
+
+	.macro PREPARE_ARGS
+	addi	a0, t0, -FENTRY_RA_OFFSET
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)
+	mv	a1, ra
+	mv	a3, sp
+	.endm
+
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 SYM_FUNC_START(ftrace_caller)
 	SAVE_ABI
 
@@ -105,34 +224,29 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 	RESTORE_ABI
-	jr t0
+	jr	t0
 SYM_FUNC_END(ftrace_caller)
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 SYM_FUNC_START(ftrace_regs_caller)
-	SAVE_ALL
-
-	addi	a0, t0, -FENTRY_RA_OFFSET
-	la	a1, function_trace_op
-	REG_L	a2, 0(a1)
-	mv	a1, ra
-	mv	a3, sp
+	SAVE_ABI_REGS 1
+	PREPARE_ARGS
 
 SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	addi	a0, sp, PT_RA
-	REG_L	a1, PT_EPC(sp)
-	addi	a1, a1, -FENTRY_RA_OFFSET
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	mv	a2, s0
-#endif
-SYM_INNER_LABEL(ftrace_graph_regs_call, SYM_L_GLOBAL)
+	RESTORE_ABI_REGS 1
+	jr	t0
+SYM_FUNC_END(ftrace_regs_caller)
+
+SYM_FUNC_START(ftrace_caller)
+	SAVE_ABI_REGS 0
+	PREPARE_ARGS
+
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call	ftrace_stub
-#endif
 
-	RESTORE_ALL
-	jr t0
-SYM_FUNC_END(ftrace_regs_caller)
+	RESTORE_ABI_REGS 0
+	jr	t0
+SYM_FUNC_END(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
-- 
GitLab


From 196c79f19a92764d45005599f35338cf0a9eafbb Mon Sep 17 00:00:00 2001
From: Song Shuai <suagrfillet@gmail.com>
Date: Thu, 30 Nov 2023 13:15:30 +0100
Subject: [PATCH 2887/4076] riscv: ftrace: Add DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Select the DYNAMIC_FTRACE_WITH_DIRECT_CALLS to provide the
register_ftrace_direct[_multi] interfaces allowing users to register
the customed trampoline (direct_caller) as the mcount for one or more
target functions. And modify_ftrace_direct[_multi] are also provided
for modifying direct_caller.

To make the direct_caller and the other ftrace hooks (e.g.
function/fgraph tracer, k[ret]probes) co-exist, a temporary register
is nominated to store the address of direct_caller in
ftrace_regs_caller. After the setting of the address direct_caller by
direct_ops->func and the RESTORE_REGS in ftrace_regs_caller,
direct_caller will be jumped to by the `jr` inst.

Add DYNAMIC_FTRACE_WITH_DIRECT_CALLS support for RISC-V.

Signed-off-by: Song Shuai <suagrfillet@gmail.com>
Tested-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@kernel.org>
Acked-by: Björn Töpel <bjorn@rivosinc.com>
Link: https://lore.kernel.org/r/20231130121531.1178502-4-bjorn@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig              |  1 +
 arch/riscv/include/asm/ftrace.h |  7 +++++++
 arch/riscv/kernel/mcount-dyn.S  | 10 ++++++++++
 3 files changed, 18 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 69c95e42be9f5..4684cdc754a09 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -114,6 +114,7 @@ config RISCV
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE)
+	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index b383926f73be1..3291721229523 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -135,6 +135,13 @@ struct ftrace_regs;
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #define ftrace_graph_func ftrace_graph_func
+
+static inline void __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
+{
+		regs->t1 = addr;
+}
+#define arch_ftrace_set_direct_caller(fregs, addr) \
+	__arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index c902a7ddb3106..b7ce001779c17 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -229,6 +229,7 @@ SYM_FUNC_END(ftrace_caller)
 
 #else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 SYM_FUNC_START(ftrace_regs_caller)
+	mv	t1, zero
 	SAVE_ABI_REGS 1
 	PREPARE_ARGS
 
@@ -236,7 +237,10 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
 	RESTORE_ABI_REGS 1
+	bnez	t1, .Ldirect
 	jr	t0
+.Ldirect:
+	jr	t1
 SYM_FUNC_END(ftrace_regs_caller)
 
 SYM_FUNC_START(ftrace_caller)
@@ -250,3 +254,9 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	jr	t0
 SYM_FUNC_END(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+SYM_CODE_START(ftrace_stub_direct_tramp)
+	jr	t0
+SYM_CODE_END(ftrace_stub_direct_tramp)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
-- 
GitLab


From 629291dd8499e4dc7dff6e9ab8c13b1a841059e8 Mon Sep 17 00:00:00 2001
From: Song Shuai <suagrfillet@gmail.com>
Date: Thu, 30 Nov 2023 13:15:31 +0100
Subject: [PATCH 2888/4076] samples: ftrace: Add RISC-V support for
 SAMPLE_FTRACE_DIRECT[_MULTI]
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add RISC-V variants of the ftrace-direct* samples.

Tested-by: Evgenii Shatokhin <e.shatokhin@yadro.com>
Signed-off-by: Song Shuai <suagrfillet@gmail.com>
Tested-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@kernel.org>
Acked-by: Björn Töpel <bjorn@rivosinc.com>
Link: https://lore.kernel.org/r/20231130121531.1178502-5-bjorn@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                          |  2 +
 samples/ftrace/ftrace-direct-modify.c       | 35 ++++++++++++++++++
 samples/ftrace/ftrace-direct-multi-modify.c | 41 +++++++++++++++++++++
 samples/ftrace/ftrace-direct-multi.c        | 25 +++++++++++++
 samples/ftrace/ftrace-direct-too.c          | 28 ++++++++++++++
 samples/ftrace/ftrace-direct.c              | 24 ++++++++++++
 6 files changed, 155 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 4684cdc754a09..0ee79a92918dd 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -142,6 +142,8 @@ config RISCV
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK if !XIP_KERNEL
 	select HAVE_RSEQ
+	select HAVE_SAMPLE_FTRACE_DIRECT
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c
index e2a6a69352dfb..81220390851a3 100644
--- a/samples/ftrace/ftrace-direct-modify.c
+++ b/samples/ftrace/ftrace-direct-modify.c
@@ -24,6 +24,41 @@ extern void my_tramp2(void *);
 
 static unsigned long my_ip = (unsigned long)schedule;
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:\n"
+"	addi	sp,sp,-2*"SZREG"\n"
+"	"REG_S"	t0,0*"SZREG"(sp)\n"
+"	"REG_S"	ra,1*"SZREG"(sp)\n"
+"	call	my_direct_func1\n"
+"	"REG_L"	t0,0*"SZREG"(sp)\n"
+"	"REG_L"	ra,1*"SZREG"(sp)\n"
+"	addi	sp,sp,2*"SZREG"\n"
+"	jr	t0\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+
+"   my_tramp2:\n"
+"	addi	sp,sp,-2*"SZREG"\n"
+"	"REG_S"	t0,0*"SZREG"(sp)\n"
+"	"REG_S"	ra,1*"SZREG"(sp)\n"
+"	call	my_direct_func2\n"
+"	"REG_L"	t0,0*"SZREG"(sp)\n"
+"	"REG_L"	ra,1*"SZREG"(sp)\n"
+"	addi	sp,sp,2*"SZREG"\n"
+"	jr	t0\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c
index 2e349834d63c3..f943e40d57fd3 100644
--- a/samples/ftrace/ftrace-direct-multi-modify.c
+++ b/samples/ftrace/ftrace-direct-multi-modify.c
@@ -22,6 +22,47 @@ void my_direct_func2(unsigned long ip)
 extern void my_tramp1(void *);
 extern void my_tramp2(void *);
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:\n"
+"       addi	sp,sp,-3*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	t0,1*"SZREG"(sp)\n"
+"       "REG_S"	ra,2*"SZREG"(sp)\n"
+"       mv	a0,t0\n"
+"       call	my_direct_func1\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	t0,1*"SZREG"(sp)\n"
+"       "REG_L"	ra,2*"SZREG"(sp)\n"
+"       addi	sp,sp,3*"SZREG"\n"
+"	jr	t0\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:\n"
+"       addi	sp,sp,-3*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	t0,1*"SZREG"(sp)\n"
+"       "REG_S"	ra,2*"SZREG"(sp)\n"
+"       mv	a0,t0\n"
+"       call	my_direct_func2\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	t0,1*"SZREG"(sp)\n"
+"       "REG_L"	ra,2*"SZREG"(sp)\n"
+"       addi	sp,sp,3*"SZREG"\n"
+"	jr	t0\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c
index 9243dbfe4d0c1..aed6df2927ce1 100644
--- a/samples/ftrace/ftrace-direct-multi.c
+++ b/samples/ftrace/ftrace-direct-multi.c
@@ -17,6 +17,31 @@ void my_direct_func(unsigned long ip)
 
 extern void my_tramp(void *);
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"       .pushsection    .text, \"ax\", @progbits\n"
+"       .type           my_tramp, @function\n"
+"       .globl          my_tramp\n"
+"   my_tramp:\n"
+"       addi	sp,sp,-3*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	t0,1*"SZREG"(sp)\n"
+"       "REG_S"	ra,2*"SZREG"(sp)\n"
+"       mv	a0,t0\n"
+"       call	my_direct_func\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	t0,1*"SZREG"(sp)\n"
+"       "REG_L"	ra,2*"SZREG"(sp)\n"
+"       addi	sp,sp,3*"SZREG"\n"
+"       jr	t0\n"
+"       .size           my_tramp, .-my_tramp\n"
+"       .popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c
index e39c3563ae4e4..6ff546a5d7eb0 100644
--- a/samples/ftrace/ftrace-direct-too.c
+++ b/samples/ftrace/ftrace-direct-too.c
@@ -19,6 +19,34 @@ void my_direct_func(struct vm_area_struct *vma, unsigned long address,
 
 extern void my_tramp(void *);
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"       .pushsection    .text, \"ax\", @progbits\n"
+"       .type           my_tramp, @function\n"
+"       .globl          my_tramp\n"
+"   my_tramp:\n"
+"       addi	sp,sp,-5*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	a1,1*"SZREG"(sp)\n"
+"       "REG_S"	a2,2*"SZREG"(sp)\n"
+"       "REG_S"	t0,3*"SZREG"(sp)\n"
+"       "REG_S"	ra,4*"SZREG"(sp)\n"
+"       call	my_direct_func\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	a1,1*"SZREG"(sp)\n"
+"       "REG_L"	a2,2*"SZREG"(sp)\n"
+"       "REG_L"	t0,3*"SZREG"(sp)\n"
+"       "REG_L"	ra,4*"SZREG"(sp)\n"
+"       addi	sp,sp,5*"SZREG"\n"
+"       jr	t0\n"
+"       .size           my_tramp, .-my_tramp\n"
+"       .popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c
index 32c477da1e9aa..ef0945670e1eb 100644
--- a/samples/ftrace/ftrace-direct.c
+++ b/samples/ftrace/ftrace-direct.c
@@ -16,6 +16,30 @@ void my_direct_func(struct task_struct *p)
 
 extern void my_tramp(void *);
 
+#ifdef CONFIG_RISCV
+#include <asm/asm.h>
+
+asm (
+"       .pushsection    .text, \"ax\", @progbits\n"
+"       .type           my_tramp, @function\n"
+"       .globl          my_tramp\n"
+"   my_tramp:\n"
+"       addi	sp,sp,-3*"SZREG"\n"
+"       "REG_S"	a0,0*"SZREG"(sp)\n"
+"       "REG_S"	t0,1*"SZREG"(sp)\n"
+"       "REG_S"	ra,2*"SZREG"(sp)\n"
+"       call	my_direct_func\n"
+"       "REG_L"	a0,0*"SZREG"(sp)\n"
+"       "REG_L"	t0,1*"SZREG"(sp)\n"
+"       "REG_L"	ra,2*"SZREG"(sp)\n"
+"       addi	sp,sp,3*"SZREG"\n"
+"       jr	t0\n"
+"       .size           my_tramp, .-my_tramp\n"
+"       .popsection\n"
+);
+
+#endif /* CONFIG_RISCV */
+
 #ifdef CONFIG_X86_64
 
 #include <asm/ibt.h>
-- 
GitLab


From c4db7ff7a9edf504752704f08aabb5554bd6c37f Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 19 Nov 2023 19:00:24 +0900
Subject: [PATCH 2889/4076] riscv: add dependency among Image(.gz),
 loader(.bin), and vmlinuz.efi

A common issue in Makefile is a race in parallel building.

You need to be careful to prevent multiple threads from writing to the
same file simultaneously.

Commit 3939f3345050 ("ARM: 8418/1: add boot image dependencies to not
generate invalid images") addressed such a bad scenario.

A similar symptom occurs with the following command:

  $ make -j$(nproc) ARCH=riscv Image Image.gz loader loader.bin vmlinuz.efi
    [ snip ]
    SORTTAB vmlinux
    OBJCOPY arch/riscv/boot/Image
    OBJCOPY arch/riscv/boot/Image
    OBJCOPY arch/riscv/boot/Image
    OBJCOPY arch/riscv/boot/Image
    OBJCOPY arch/riscv/boot/Image
    GZIP    arch/riscv/boot/Image.gz
    AS      arch/riscv/boot/loader.o
    AS      arch/riscv/boot/loader.o
    Kernel: arch/riscv/boot/Image is ready
    PAD     arch/riscv/boot/vmlinux.bin
    GZIP    arch/riscv/boot/vmlinuz
    Kernel: arch/riscv/boot/loader is ready
    OBJCOPY arch/riscv/boot/loader.bin
    Kernel: arch/riscv/boot/loader.bin is ready
    Kernel: arch/riscv/boot/Image.gz is ready
    OBJCOPY arch/riscv/boot/vmlinuz.o
    LD      arch/riscv/boot/vmlinuz.efi.elf
    OBJCOPY arch/riscv/boot/vmlinuz.efi
    Kernel: arch/riscv/boot/vmlinuz.efi is ready

The log "OBJCOPY arch/riscv/boot/Image" is displayed 5 times.
(also "AS      arch/riscv/boot/loader.o" twice.)

It indicates that 5 threads simultaneously enter arch/riscv/boot/
and write to arch/riscv/boot/Image.

It occasionally leads to a build failure:

  $ make -j$(nproc) ARCH=riscv Image Image.gz loader loader.bin vmlinuz.efi
    [ snip ]
    SORTTAB vmlinux
    OBJCOPY arch/riscv/boot/Image
    OBJCOPY arch/riscv/boot/Image
    OBJCOPY arch/riscv/boot/Image
    OBJCOPY arch/riscv/boot/Image
    PAD     arch/riscv/boot/vmlinux.bin
  truncate: Invalid number: 'arch/riscv/boot/vmlinux.bin'
  make[2]: *** [drivers/firmware/efi/libstub/Makefile.zboot:13: arch/riscv/boot/vmlinux.bin] Error 1
  make[2]: *** Deleting file 'arch/riscv/boot/vmlinux.bin'
  make[1]: *** [arch/riscv/Makefile:167: vmlinuz.efi] Error 2
  make[1]: *** Waiting for unfinished jobs....
    Kernel: arch/riscv/boot/Image is ready
    GZIP    arch/riscv/boot/Image.gz
    AS      arch/riscv/boot/loader.o
    AS      arch/riscv/boot/loader.o
    Kernel: arch/riscv/boot/loader is ready
    OBJCOPY arch/riscv/boot/loader.bin
    Kernel: arch/riscv/boot/loader.bin is ready
    Kernel: arch/riscv/boot/Image.gz is ready
  make: *** [Makefile:234: __sub-make] Error 2

Image.gz, loader, vmlinuz.efi depend on Image. loader.bin depends
on loader. Such dependencies are not specified in arch/riscv/Makefile.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20231119100024.2370992-1-masahiroy@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Makefile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 6539e43f82767..0b7d109258e7d 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -163,6 +163,8 @@ BOOT_TARGETS := Image Image.gz loader loader.bin xipImage vmlinuz.efi
 
 all:	$(notdir $(KBUILD_IMAGE))
 
+loader.bin: loader
+Image.gz loader vmlinuz.efi: Image
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 	@$(kecho) '  Kernel: $(boot)/$@ is ready'
-- 
GitLab


From 55ca8d7aa2af3ebdb6f85cccf1b0703d031c1678 Mon Sep 17 00:00:00 2001
From: Xiao Wang <xiao.w.wang@intel.com>
Date: Sun, 12 Nov 2023 17:52:44 +0800
Subject: [PATCH 2890/4076] riscv: Optimize hweight API with Zbb extension

The Hamming Weight of a number is the total number of bits set in it, so
the cpop/cpopw instruction from Zbb extension can be used to accelerate
hweight() API.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231112095244.4015351-1-xiao.w.wang@intel.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/arch_hweight.h | 78 +++++++++++++++++++++++++++
 arch/riscv/include/asm/bitops.h       |  4 +-
 2 files changed, 81 insertions(+), 1 deletion(-)
 create mode 100644 arch/riscv/include/asm/arch_hweight.h

diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
new file mode 100644
index 0000000000000..c20236a0725b9
--- /dev/null
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Based on arch/x86/include/asm/arch_hweight.h
+ */
+
+#ifndef _ASM_RISCV_HWEIGHT_H
+#define _ASM_RISCV_HWEIGHT_H
+
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+#if (BITS_PER_LONG == 64)
+#define CPOPW	"cpopw "
+#elif (BITS_PER_LONG == 32)
+#define CPOPW	"cpop "
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+static __always_inline unsigned int __arch_hweight32(unsigned int w)
+{
+#ifdef CONFIG_RISCV_ISA_ZBB
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm (".option push\n"
+	     ".option arch,+zbb\n"
+	     CPOPW "%0, %0\n"
+	     ".option pop\n"
+	     : "+r" (w) : :);
+
+	return w;
+
+legacy:
+#endif
+	return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+	return __arch_hweight32(w & 0xffff);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+	return __arch_hweight32(w & 0xff);
+}
+
+#if BITS_PER_LONG == 64
+static __always_inline unsigned long __arch_hweight64(__u64 w)
+{
+# ifdef CONFIG_RISCV_ISA_ZBB
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm (".option push\n"
+	     ".option arch,+zbb\n"
+	     "cpop %0, %0\n"
+	     ".option pop\n"
+	     : "+r" (w) : :);
+
+	return w;
+
+legacy:
+# endif
+	return __sw_hweight64(w);
+}
+#else /* BITS_PER_LONG == 64 */
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+	return  __arch_hweight32((u32)w) +
+		__arch_hweight32((u32)(w >> 32));
+}
+#endif /* !(BITS_PER_LONG == 64) */
+
+#endif /* _ASM_RISCV_HWEIGHT_H */
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 224b4dc02b50b..9ffc355370248 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -271,7 +271,9 @@ legacy:
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
 
-#include <asm-generic/bitops/hweight.h>
+#include <asm/arch_hweight.h>
+
+#include <asm-generic/bitops/const_hweight.h>
 
 #if (BITS_PER_LONG == 64)
 #define __AMO(op)	"amo" #op ".d"
-- 
GitLab


From 10243401059287868a5651f869a2494368872add Mon Sep 17 00:00:00 2001
From: Samuel Ortiz <sameo@rivosinc.com>
Date: Thu, 30 Nov 2023 12:17:02 +0100
Subject: [PATCH 2891/4076] RISC-V: Implement archrandom when Zkr is available
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Zkr extension is ratified and provides 16 bits of entropy seed when
reading the SEED CSR.

We can implement arch_get_random_seed_longs() by doing multiple csrrw to
that CSR and filling an unsigned long with valid entropy bits.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Samuel Ortiz <sameo@rivosinc.com>
Signed-off-by: Clément Léger <cleger@rivosinc.com>
Link: https://lore.kernel.org/r/20231130111704.1319081-1-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/archrandom.h | 72 +++++++++++++++++++++++++++++
 arch/riscv/include/asm/csr.h        |  9 ++++
 2 files changed, 81 insertions(+)
 create mode 100644 arch/riscv/include/asm/archrandom.h

diff --git a/arch/riscv/include/asm/archrandom.h b/arch/riscv/include/asm/archrandom.h
new file mode 100644
index 0000000000000..5345360adfb9c
--- /dev/null
+++ b/arch/riscv/include/asm/archrandom.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Kernel interface for the RISCV arch_random_* functions
+ *
+ * Copyright (c) 2023 Rivos Inc.
+ *
+ */
+
+#ifndef ASM_RISCV_ARCHRANDOM_H
+#define ASM_RISCV_ARCHRANDOM_H
+
+#include <asm/csr.h>
+#include <asm/processor.h>
+
+#define SEED_RETRY_LOOPS 100
+
+static inline bool __must_check csr_seed_long(unsigned long *v)
+{
+	unsigned int retry = SEED_RETRY_LOOPS, valid_seeds = 0;
+	const int needed_seeds = sizeof(long) / sizeof(u16);
+	u16 *entropy = (u16 *)v;
+
+	do {
+		/*
+		 * The SEED CSR must be accessed with a read-write instruction.
+		 */
+		unsigned long csr_seed = csr_swap(CSR_SEED, 0);
+		unsigned long opst = csr_seed & SEED_OPST_MASK;
+
+		switch (opst) {
+		case SEED_OPST_ES16:
+			entropy[valid_seeds++] = csr_seed & SEED_ENTROPY_MASK;
+			if (valid_seeds == needed_seeds)
+				return true;
+			break;
+
+		case SEED_OPST_DEAD:
+			pr_err_once("archrandom: Unrecoverable error\n");
+			return false;
+
+		case SEED_OPST_BIST:
+		case SEED_OPST_WAIT:
+		default:
+			cpu_relax();
+			continue;
+		}
+	} while (--retry);
+
+	return false;
+}
+
+static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
+{
+	return 0;
+}
+
+static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
+{
+	if (!max_longs)
+		return 0;
+
+	/*
+	 * If Zkr is supported and csr_seed_long succeeds, we return one long
+	 * worth of entropy.
+	 */
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZKR) && csr_seed_long(v))
+		return 1;
+
+	return 0;
+}
+
+#endif /* ASM_RISCV_ARCHRANDOM_H */
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 306a19a5509c1..510014051f5db 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -411,6 +411,15 @@
 #define CSR_VTYPE		0xc21
 #define CSR_VLENB		0xc22
 
+/* Scalar Crypto Extension - Entropy */
+#define CSR_SEED		0x015
+#define SEED_OPST_MASK		_AC(0xC0000000, UL)
+#define SEED_OPST_BIST		_AC(0x00000000, UL)
+#define SEED_OPST_WAIT		_AC(0x40000000, UL)
+#define SEED_OPST_ES16		_AC(0x80000000, UL)
+#define SEED_OPST_DEAD		_AC(0xC0000000, UL)
+#define SEED_ENTROPY_MASK	_AC(0xFFFF, UL)
+
 #ifdef CONFIG_RISCV_M_MODE
 # define CSR_STATUS	CSR_MSTATUS
 # define CSR_IE		CSR_MIE
-- 
GitLab


From 080c4324fa5e81ff3780206a138223abfb57a68e Mon Sep 17 00:00:00 2001
From: Maxim Kochetkov <fido_max@inbox.ru>
Date: Thu, 14 Dec 2023 09:39:06 +0300
Subject: [PATCH 2892/4076] riscv: optimize ELF relocation function in riscv

The patch can optimize the running times of insmod command by modify ELF
relocation function.
In the 5.10 and latest kernel, when install the riscv ELF drivers which
contains multiple symbol table items to be relocated, kernel takes a lot
of time to execute the relocation. For example, we install a 3+MB driver
need 180+s.
We focus on the riscv architecture handle R_RISCV_HI20 and R_RISCV_LO20
type items relocation function in the arch\riscv\kernel\module.c and
find that there are two-loops in the function. If we modify the begin
number in the second for-loops iteration, we could save significant time
for installation. We install the same 3+MB driver could just need 2s.

Signed-off-by: Amma Lee <lixiaoyun@binary-semi.com>
Signed-off-by: Maxim Kochetkov <fido_max@inbox.ru>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231214063906.13612-1-fido_max@inbox.ru
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/module.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index c9d59a5448b6c..5e5a82644451e 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -783,6 +783,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	Elf_Sym *sym;
 	void *location;
 	unsigned int i, type;
+	unsigned int j_idx = 0;
 	Elf_Addr v;
 	int res;
 	unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel);
@@ -833,9 +834,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		v = sym->st_value + rel[i].r_addend;
 
 		if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
-			unsigned int j;
+			unsigned int j = j_idx;
+			bool found = false;
 
-			for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+			do {
 				unsigned long hi20_loc =
 					sechdrs[sechdrs[relsec].sh_info].sh_addr
 					+ rel[j].r_offset;
@@ -864,16 +866,26 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 					hi20 = (offset + 0x800) & 0xfffff000;
 					lo12 = offset - hi20;
 					v = lo12;
+					found = true;
 
 					break;
 				}
-			}
-			if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+
+				j++;
+				if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+					j = 0;
+
+			} while (j_idx != j);
+
+			if (!found) {
 				pr_err(
 				  "%s: Can not find HI20 relocation information\n",
 				  me->name);
 				return -EINVAL;
 			}
+
+			/* Record the previous j-loop end index */
+			j_idx = j;
 		}
 
 		if (reloc_handlers[type].accumulate_handler)
-- 
GitLab


From 01b55f4f0cd6ad1a16eca6c43a3190005892ef91 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 17 Jan 2024 19:31:39 -0800
Subject: [PATCH 2893/4076] libbpf: feature-detect arg:ctx tag support in
 kernel

Add feature detector of kernel-side arg:ctx (__arg_ctx) tag support. If
this is detected, libbpf will avoid doing any __arg_ctx-related BTF
rewriting and checks in favor of letting kernel handle this completely.

test_global_funcs/ctx_arg_rewrite subtest is adjusted to do the same
feature detection (albeit in much simpler, though round-about and
inefficient, way), and skip the tests. This is done to still be able to
execute this test on older kernels (like in libbpf CI).

Note, BPF token series ([0]) does a major refactor and code moving of
libbpf-internal feature detection "framework", so to avoid unnecessary
conflicts we keep newly added feature detection stand-alone with ad-hoc
result caching. Once things settle, there will be a small follow up to
re-integrate everything back and move code into its final place in
newly-added (by BPF token series) features.c file.

  [0] https://patchwork.kernel.org/project/netdevbpf/list/?series=814209&state=*

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240118033143.3384355-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c                        | 67 +++++++++++++++++++
 .../bpf/prog_tests/test_global_funcs.c        | 13 ++++
 2 files changed, 80 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c5a42ac309fdb..61db92189517b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6757,6 +6757,69 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr
 	return fn_id;
 }
 
+static int probe_kern_arg_ctx_tag(void)
+{
+	/* To minimize merge conflicts with BPF token series that refactors
+	 * feature detection code a lot, we don't integrate
+	 * probe_kern_arg_ctx_tag() into kernel_supports() feature-detection
+	 * framework yet, doing our own caching internally.
+	 * This will be cleaned up a bit later when bpf/bpf-next trees settle.
+	 */
+	static int cached_result = -1;
+	static const char strs[] = "\0a\0b\0arg:ctx\0";
+	const __u32 types[] = {
+		/* [1] INT */
+		BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4),
+		/* [2] PTR -> VOID */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
+		/* [3] FUNC_PROTO `int(void *a)` */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
+		BTF_PARAM_ENC(1 /* "a" */, 2),
+		/* [4] FUNC 'a' -> FUNC_PROTO (main prog) */
+		BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3),
+		/* [5] FUNC_PROTO `int(void *b __arg_ctx)` */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
+		BTF_PARAM_ENC(3 /* "b" */, 2),
+		/* [6] FUNC 'b' -> FUNC_PROTO (subprog) */
+		BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5),
+		/* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */
+		BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0),
+	};
+	const struct bpf_insn insns[] = {
+		/* main prog */
+		BPF_CALL_REL(+1),
+		BPF_EXIT_INSN(),
+		/* global subprog */
+		BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */
+		BPF_EXIT_INSN(),
+	};
+	const struct bpf_func_info_min func_infos[] = {
+		{ 0, 4 }, /* main prog -> FUNC 'a' */
+		{ 2, 6 }, /* subprog -> FUNC 'b' */
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+	int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns);
+
+	if (cached_result >= 0)
+		return cached_result;
+
+	btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs));
+	if (btf_fd < 0)
+		return 0;
+
+	opts.prog_btf_fd = btf_fd;
+	opts.func_info = &func_infos;
+	opts.func_info_cnt = ARRAY_SIZE(func_infos);
+	opts.func_info_rec_size = sizeof(func_infos[0]);
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx",
+				"GPL", insns, insn_cnt, &opts);
+	close(btf_fd);
+
+	cached_result = probe_fd(prog_fd);
+	return cached_result;
+}
+
 /* Check if main program or global subprog's function prototype has `arg:ctx`
  * argument tags, and, if necessary, substitute correct type to match what BPF
  * verifier would expect, taking into account specific program type. This
@@ -6780,6 +6843,10 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra
 	if (!obj->btf_ext || !prog->func_info)
 		return 0;
 
+	/* don't do any fix ups if kernel natively supports __arg_ctx */
+	if (probe_kern_arg_ctx_tag() > 0)
+		return 0;
+
 	/* some BPF program types just don't have named context structs, so
 	 * this fallback mechanism doesn't work for them
 	 */
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index 67d4ef9e62b37..e905cbaf6b3d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -47,6 +47,19 @@ static void subtest_ctx_arg_rewrite(void)
 	struct btf *btf = NULL;
 	__u32 info_len = sizeof(info);
 	int err, fd, i;
+	struct btf *kern_btf = NULL;
+
+	kern_btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(kern_btf, "kern_btf_load"))
+		return;
+
+	/* simple detection of kernel native arg:ctx tag support */
+	if (btf__find_by_name_kind(kern_btf, "bpf_subprog_arg_info", BTF_KIND_STRUCT) > 0) {
+		test__skip();
+		btf__free(kern_btf);
+		return;
+	}
+	btf__free(kern_btf);
 
 	skel = test_global_func_ctx_args__open();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
-- 
GitLab


From 66967a32d3b16ed447e76fed4d946bab52e43d86 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 17 Jan 2024 19:31:40 -0800
Subject: [PATCH 2894/4076] bpf: extract bpf_ctx_convert_map logic and make it
 more reusable

Refactor btf_get_prog_ctx_type() a bit to allow reuse of
bpf_ctx_convert_map logic in more than one places. Simplify interface by
returning btf_type instead of btf_member (field reference in BTF).

To do the above we need to touch and start untangling
btf_translate_to_vmlinux() implementation. We do the bare minimum to
not regress anything for btf_translate_to_vmlinux(), but its
implementation is very questionable for what it claims to be doing.
Mapping kfunc argument types to kernel corresponding types conceptually
is quite different from recognizing program context types. Fixing this
is out of scope for this change though.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240118033143.3384355-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h |  2 +-
 kernel/bpf/btf.c    | 71 ++++++++++++++++++++++++++++-----------------
 2 files changed, 46 insertions(+), 27 deletions(-)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 59d404e22814e..cf5c6ff489812 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -512,7 +512,7 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner);
 struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id);
-const struct btf_member *
+const struct btf_type *
 btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 		      const struct btf_type *t, enum bpf_prog_type prog_type,
 		      int arg);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 51e8b4bee0c83..10ac9efc662d0 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5615,21 +5615,46 @@ static u8 bpf_ctx_convert_map[] = {
 #undef BPF_MAP_TYPE
 #undef BPF_LINK_TYPE
 
-const struct btf_member *
-btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
-		      const struct btf_type *t, enum bpf_prog_type prog_type,
-		      int arg)
+static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type)
 {
 	const struct btf_type *conv_struct;
-	const struct btf_type *ctx_struct;
 	const struct btf_member *ctx_type;
-	const char *tname, *ctx_tname;
 
 	conv_struct = bpf_ctx_convert.t;
-	if (!conv_struct) {
-		bpf_log(log, "btf_vmlinux is malformed\n");
+	if (!conv_struct)
 		return NULL;
-	}
+	/* prog_type is valid bpf program type. No need for bounds check. */
+	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
+	/* ctx_type is a pointer to prog_ctx_type in vmlinux.
+	 * Like 'struct __sk_buff'
+	 */
+	return btf_type_by_id(btf_vmlinux, ctx_type->type);
+}
+
+static int find_kern_ctx_type_id(enum bpf_prog_type prog_type)
+{
+	const struct btf_type *conv_struct;
+	const struct btf_member *ctx_type;
+
+	conv_struct = bpf_ctx_convert.t;
+	if (!conv_struct)
+		return -EFAULT;
+	/* prog_type is valid bpf program type. No need for bounds check. */
+	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1;
+	/* ctx_type is a pointer to prog_ctx_type in vmlinux.
+	 * Like 'struct sk_buff'
+	 */
+	return ctx_type->type;
+}
+
+const struct btf_type *
+btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+		      const struct btf_type *t, enum bpf_prog_type prog_type,
+		      int arg)
+{
+	const struct btf_type *ctx_type;
+	const char *tname, *ctx_tname;
+
 	t = btf_type_by_id(btf, t->type);
 	while (btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
@@ -5646,17 +5671,15 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 		bpf_log(log, "arg#%d struct doesn't have a name\n", arg);
 		return NULL;
 	}
-	/* prog_type is valid bpf program type. No need for bounds check. */
-	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
-	/* ctx_struct is a pointer to prog_ctx_type in vmlinux.
-	 * Like 'struct __sk_buff'
-	 */
-	ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type);
-	if (!ctx_struct)
+
+	ctx_type = find_canonical_prog_ctx_type(prog_type);
+	if (!ctx_type) {
+		bpf_log(log, "btf_vmlinux is malformed\n");
 		/* should not happen */
 		return NULL;
+	}
 again:
-	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off);
+	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off);
 	if (!ctx_tname) {
 		/* should not happen */
 		bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n");
@@ -5677,10 +5700,10 @@ again:
 		/* bpf_user_pt_regs_t is a typedef, so resolve it to
 		 * underlying struct and check name again
 		 */
-		if (!btf_type_is_modifier(ctx_struct))
+		if (!btf_type_is_modifier(ctx_type))
 			return NULL;
-		while (btf_type_is_modifier(ctx_struct))
-			ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type);
+		while (btf_type_is_modifier(ctx_type))
+			ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type);
 		goto again;
 	}
 	return ctx_type;
@@ -5692,13 +5715,9 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 				     enum bpf_prog_type prog_type,
 				     int arg)
 {
-	const struct btf_member *prog_ctx_type, *kern_ctx_type;
-
-	prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg);
-	if (!prog_ctx_type)
+	if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg))
 		return -ENOENT;
-	kern_ctx_type = prog_ctx_type + 1;
-	return kern_ctx_type->type;
+	return find_kern_ctx_type_id(prog_type);
 }
 
 int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type)
-- 
GitLab


From 0ba971511d16603599f947459e59b435cc465b0d Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 17 Jan 2024 19:31:41 -0800
Subject: [PATCH 2895/4076] bpf: enforce types for __arg_ctx-tagged arguments
 in global subprogs

Add enforcement of expected types for context arguments tagged with
arg:ctx (__arg_ctx) tag.

First, any program type will accept generic `void *` context type when
combined with __arg_ctx tag.

Besides accepting "canonical" struct names and `void *`, for a bunch of
program types for which program context is actually a named struct, we
allows a bunch of pragmatic exceptions to match real-world and expected
usage:

  - for both kprobes and perf_event we allow `bpf_user_pt_regs_t *` as
    canonical context argument type, where `bpf_user_pt_regs_t` is a
    *typedef*, not a struct;
  - for kprobes, we also always accept `struct pt_regs *`, as that's what
    actually is passed as a context to any kprobe program;
  - for perf_event, we resolve typedefs (unless it's `bpf_user_pt_regs_t`)
    down to actual struct type and accept `struct pt_regs *`, or
    `struct user_pt_regs *`, or `struct user_regs_struct *`, depending
    on the actual struct type kernel architecture points `bpf_user_pt_regs_t`
    typedef to; otherwise, canonical `struct bpf_perf_event_data *` is
    expected;
  - for raw_tp/raw_tp.w programs, `u64/long *` are accepted, as that's
    what's expected with BPF_PROG() usage; otherwise, canonical
    `struct bpf_raw_tracepoint_args *` is expected;
  - tp_btf supports both `struct bpf_raw_tracepoint_args *` and `u64 *`
    formats, both are coded as expections as tp_btf is actually a TRACING
    program type, which has no canonical context type;
  - iterator programs accept `struct bpf_iter__xxx *` structs, currently
    with no further iterator-type specific enforcement;
  - fentry/fexit/fmod_ret/lsm/struct_ops all accept `u64 *`;
  - classic tracepoint programs, as well as syscall and freplace
    programs allow any user-provided type.

In all other cases kernel will enforce exact match of struct name to
expected canonical type. And if user-provided type doesn't match that
expectation, verifier will emit helpful message with expected type name.

Note a bit unnatural way the check is done after processing all the
arguments. This is done to avoid conflict between bpf and bpf-next
trees. Once trees converge, a small follow up patch will place a simple
btf_validate_prog_ctx_type() check into a proper ARG_PTR_TO_CTX branch
(which bpf-next tree patch refactored already), removing duplicated
arg:ctx detection logic.

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240118033143.3384355-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 160 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 160 insertions(+)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 10ac9efc662d0..5964711891767 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5709,6 +5709,149 @@ again:
 	return ctx_type;
 }
 
+/* forward declarations for arch-specific underlying types of
+ * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef
+ * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still
+ * works correctly with __builtin_types_compatible_p() on respective
+ * architectures
+ */
+struct user_regs_struct;
+struct user_pt_regs;
+
+static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+				      const struct btf_type *t, int arg,
+				      enum bpf_prog_type prog_type,
+				      enum bpf_attach_type attach_type)
+{
+	const struct btf_type *ctx_type;
+	const char *tname, *ctx_tname;
+
+	if (!btf_is_ptr(t)) {
+		bpf_log(log, "arg#%d type isn't a pointer\n", arg);
+		return -EINVAL;
+	}
+	t = btf_type_by_id(btf, t->type);
+
+	/* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */
+	if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) {
+		while (btf_type_is_modifier(t) && !btf_type_is_typedef(t))
+			t = btf_type_by_id(btf, t->type);
+
+		if (btf_type_is_typedef(t)) {
+			tname = btf_name_by_offset(btf, t->name_off);
+			if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0)
+				return 0;
+		}
+	}
+
+	/* all other program types don't use typedefs for context type */
+	while (btf_type_is_modifier(t))
+		t = btf_type_by_id(btf, t->type);
+
+	/* `void *ctx __arg_ctx` is always valid */
+	if (btf_type_is_void(t))
+		return 0;
+
+	tname = btf_name_by_offset(btf, t->name_off);
+	if (str_is_empty(tname)) {
+		bpf_log(log, "arg#%d type doesn't have a name\n", arg);
+		return -EINVAL;
+	}
+
+	/* special cases */
+	switch (prog_type) {
+	case BPF_PROG_TYPE_KPROBE:
+		if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+			return 0;
+		break;
+	case BPF_PROG_TYPE_PERF_EVENT:
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) &&
+		    __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+			return 0;
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) &&
+		    __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0)
+			return 0;
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) &&
+		    __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0)
+			return 0;
+		break;
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+		/* allow u64* as ctx */
+		if (btf_is_int(t) && t->size == 8)
+			return 0;
+		break;
+	case BPF_PROG_TYPE_TRACING:
+		switch (attach_type) {
+		case BPF_TRACE_RAW_TP:
+			/* tp_btf program is TRACING, so need special case here */
+			if (__btf_type_is_struct(t) &&
+			    strcmp(tname, "bpf_raw_tracepoint_args") == 0)
+				return 0;
+			/* allow u64* as ctx */
+			if (btf_is_int(t) && t->size == 8)
+				return 0;
+			break;
+		case BPF_TRACE_ITER:
+			/* allow struct bpf_iter__xxx types only */
+			if (__btf_type_is_struct(t) &&
+			    strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0)
+				return 0;
+			break;
+		case BPF_TRACE_FENTRY:
+		case BPF_TRACE_FEXIT:
+		case BPF_MODIFY_RETURN:
+			/* allow u64* as ctx */
+			if (btf_is_int(t) && t->size == 8)
+				return 0;
+			break;
+		default:
+			break;
+		}
+		break;
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		/* allow u64* as ctx */
+		if (btf_is_int(t) && t->size == 8)
+			return 0;
+		break;
+	case BPF_PROG_TYPE_TRACEPOINT:
+	case BPF_PROG_TYPE_SYSCALL:
+	case BPF_PROG_TYPE_EXT:
+		return 0; /* anything goes */
+	default:
+		break;
+	}
+
+	ctx_type = find_canonical_prog_ctx_type(prog_type);
+	if (!ctx_type) {
+		/* should not happen */
+		bpf_log(log, "btf_vmlinux is malformed\n");
+		return -EINVAL;
+	}
+
+	/* resolve typedefs and check that underlying structs are matching as well */
+	while (btf_type_is_modifier(ctx_type))
+		ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type);
+
+	/* if program type doesn't have distinctly named struct type for
+	 * context, then __arg_ctx argument can only be `void *`, which we
+	 * already checked above
+	 */
+	if (!__btf_type_is_struct(ctx_type)) {
+		bpf_log(log, "arg#%d should be void pointer\n", arg);
+		return -EINVAL;
+	}
+
+	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off);
+	if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) {
+		bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 				     struct btf *btf,
 				     const struct btf_type *t,
@@ -6953,6 +7096,23 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 		return -EINVAL;
 	}
 
+	for (i = 0; i < nargs; i++) {
+		const char *tag;
+
+		if (sub->args[i].arg_type != ARG_PTR_TO_CTX)
+			continue;
+
+		/* check if arg has "arg:ctx" tag */
+		t = btf_type_by_id(btf, args[i].type);
+		tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:");
+		if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0)
+			continue;
+
+		if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type,
+					       prog->expected_attach_type))
+			return -EINVAL;
+	}
+
 	sub->arg_cnt = nargs;
 	sub->args_cached = true;
 
-- 
GitLab


From 989410cde81959c4033dc287d79b42b6eb04f04f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 17 Jan 2024 19:31:42 -0800
Subject: [PATCH 2896/4076] selftests/bpf: add tests confirming type logic in
 kernel for __arg_ctx

Add a bunch of global subprogs across variety of program types to
validate expected kernel type enforcement logic for __arg_ctx arguments.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240118033143.3384355-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/progs/verifier_global_subprogs.c      | 164 +++++++++++++++++-
 1 file changed, 161 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
index 9eeb2d89cda88..67dddd9418911 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -3,6 +3,7 @@
 
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
 #include "xdp_metadata.h"
 #include "bpf_kfuncs.h"
@@ -138,25 +139,182 @@ __weak int subprog_ctx_tag(void *ctx __arg_ctx)
 	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
 }
 
+__weak int raw_tp_canonical(struct bpf_raw_tracepoint_args *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int raw_tp_u64_array(u64 *ctx __arg_ctx)
+{
+	return 0;
+}
+
 SEC("?raw_tp")
 __success __log_level(2)
 int arg_tag_ctx_raw_tp(void *ctx)
 {
-	return subprog_ctx_tag(ctx);
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+SEC("?raw_tp.w")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp_writable(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+SEC("?tp_btf/sys_enter")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp_btf(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+struct whatever { };
+
+__weak int tp_whatever(struct whatever *ctx __arg_ctx)
+{
+	return 0;
 }
 
 SEC("?tp")
 __success __log_level(2)
 int arg_tag_ctx_tp(void *ctx)
 {
-	return subprog_ctx_tag(ctx);
+	return subprog_ctx_tag(ctx) + tp_whatever(ctx);
+}
+
+__weak int kprobe_subprog_pt_regs(struct pt_regs *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int kprobe_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx)
+{
+	return 0;
 }
 
 SEC("?kprobe")
 __success __log_level(2)
 int arg_tag_ctx_kprobe(void *ctx)
 {
-	return subprog_ctx_tag(ctx);
+	return subprog_ctx_tag(ctx) +
+	       kprobe_subprog_pt_regs(ctx) +
+	       kprobe_subprog_typedef(ctx);
+}
+
+__weak int perf_subprog_regs(
+#if defined(bpf_target_riscv)
+	struct user_regs_struct *ctx __arg_ctx
+#elif defined(bpf_target_s390)
+	/* user_pt_regs typedef is anonymous struct, so only `void *` works */
+	void *ctx __arg_ctx
+#elif defined(bpf_target_loongarch) || defined(bpf_target_arm64) || defined(bpf_target_powerpc)
+	struct user_pt_regs *ctx __arg_ctx
+#else
+	struct pt_regs *ctx __arg_ctx
+#endif
+)
+{
+	return 0;
+}
+
+__weak int perf_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int perf_subprog_canonical(struct bpf_perf_event_data *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?perf_event")
+__success __log_level(2)
+int arg_tag_ctx_perf(void *ctx)
+{
+	return subprog_ctx_tag(ctx) +
+	       perf_subprog_regs(ctx) +
+	       perf_subprog_typedef(ctx) +
+	       perf_subprog_canonical(ctx);
+}
+
+__weak int iter_subprog_void(void *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int iter_subprog_typed(struct bpf_iter__task *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?iter/task")
+__success __log_level(2)
+int arg_tag_ctx_iter_task(struct bpf_iter__task *ctx)
+{
+	return (iter_subprog_void(ctx) + iter_subprog_typed(ctx)) & 1;
+}
+
+__weak int tracing_subprog_void(void *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int tracing_subprog_u64(u64 *ctx __arg_ctx)
+{
+	return 0;
+}
+
+int acc;
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fentry)
+{
+	acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	return 0;
+}
+
+SEC("?fexit/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fexit)
+{
+	acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	return 0;
+}
+
+SEC("?fmod_ret/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fmod_ret)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC("?lsm/bpf")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_lsm)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC("?struct_ops/test_1")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_struct_ops)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC(".struct_ops")
+struct bpf_dummy_ops dummy_1 = {
+	.test_1 = (void *)arg_tag_ctx_struct_ops,
+};
+
+SEC("?syscall")
+__success __log_level(2)
+int arg_tag_ctx_syscall(void *ctx)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx) + tp_whatever(ctx);
 }
 
 __weak int subprog_dynptr(struct bpf_dynptr *dptr)
-- 
GitLab


From 76ec90a996e3c707eb6772510afa36faeba2ecff Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 17 Jan 2024 19:31:43 -0800
Subject: [PATCH 2897/4076] libbpf: warn on unexpected __arg_ctx type when
 rewriting BTF

On kernel that don't support arg:ctx tag, before adjusting global
subprog BTF information to match kernel's expected canonical type names,
make sure that types used by user are meaningful, and if not, warn and
don't do BTF adjustments.

This is similar to checks that kernel performs, but narrower in scope,
as only a small subset of BPF program types can be accommodated by
libbpf using canonical type names.

Libbpf unconditionally allows `struct pt_regs *` for perf_event program
types, unlike kernel, which supports that conditionally on architecture.
This is done to keep things simple and not cause unnecessary false
positives. This seems like a minor and harmless deviation, which in
real-world programs will be caught by kernels with arg:ctx tag support
anyways. So KISS principle.

This logic is hard to test (especially on latest kernels), so manual
testing was performed instead. Libbpf emitted the following warning for
perf_event program with wrong context argument type:

  libbpf: prog 'arg_tag_ctx_perf': subprog 'subprog_ctx_tag' arg#0 is expected to be of `struct bpf_perf_event_data *` type

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240118033143.3384355-6-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 75 +++++++++++++++++++++++++++++++++++++-----
 1 file changed, 66 insertions(+), 9 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 61db92189517b..afd09571c482b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6695,6 +6695,67 @@ static struct {
 	/* all other program types don't have "named" context structs */
 };
 
+static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_program *prog,
+				     const char *subprog_name, int arg_idx,
+				     int arg_type_id, const char *ctx_name)
+{
+	const struct btf_type *t;
+	const char *tname;
+
+	/* check if existing parameter already matches verifier expectations */
+	t = skip_mods_and_typedefs(btf, arg_type_id, NULL);
+	if (!btf_is_ptr(t))
+		goto out_warn;
+
+	/* typedef bpf_user_pt_regs_t is a special PITA case, valid for kprobe
+	 * and perf_event programs, so check this case early on and forget
+	 * about it for subsequent checks
+	 */
+	while (btf_is_mod(t))
+		t = btf__type_by_id(btf, t->type);
+	if (btf_is_typedef(t) &&
+	    (prog->type == BPF_PROG_TYPE_KPROBE || prog->type == BPF_PROG_TYPE_PERF_EVENT)) {
+		tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>";
+		if (strcmp(tname, "bpf_user_pt_regs_t") == 0)
+			return false; /* canonical type for kprobe/perf_event */
+	}
+
+	/* now we can ignore typedefs moving forward */
+	t = skip_mods_and_typedefs(btf, t->type, NULL);
+
+	/* if it's `void *`, definitely fix up BTF info */
+	if (btf_is_void(t))
+		return true;
+
+	/* if it's already proper canonical type, no need to fix up */
+	tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>";
+	if (btf_is_struct(t) && strcmp(tname, ctx_name) == 0)
+		return false;
+
+	/* special cases */
+	switch (prog->type) {
+	case BPF_PROG_TYPE_KPROBE:
+	case BPF_PROG_TYPE_PERF_EVENT:
+		/* `struct pt_regs *` is expected, but we need to fix up */
+		if (btf_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+			return true;
+		break;
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+		/* allow u64* as ctx */
+		if (btf_is_int(t) && t->size == 8)
+			return true;
+		break;
+	default:
+		break;
+	}
+
+out_warn:
+	pr_warn("prog '%s': subprog '%s' arg#%d is expected to be of `struct %s *` type\n",
+		prog->name, subprog_name, arg_idx, ctx_name);
+	return false;
+}
+
 static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog)
 {
 	int fn_id, fn_proto_id, ret_type_id, orig_proto_id;
@@ -6829,7 +6890,7 @@ static int probe_kern_arg_ctx_tag(void)
  */
 static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog)
 {
-	const char *ctx_name = NULL, *ctx_tag = "arg:ctx";
+	const char *ctx_name = NULL, *ctx_tag = "arg:ctx", *fn_name;
 	struct bpf_func_info_min *func_rec;
 	struct btf_type *fn_t, *fn_proto_t;
 	struct btf *btf = obj->btf;
@@ -6909,15 +6970,11 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra
 		if (arg_idx < 0 || arg_idx >= arg_cnt)
 			continue;
 
-		/* check if existing parameter already matches verifier expectations */
+		/* check if we should fix up argument type */
 		p = &btf_params(fn_proto_t)[arg_idx];
-		t = skip_mods_and_typedefs(btf, p->type, NULL);
-		if (btf_is_ptr(t) &&
-		    (t = skip_mods_and_typedefs(btf, t->type, NULL)) &&
-		    btf_is_struct(t) &&
-		    strcmp(btf__str_by_offset(btf, t->name_off), ctx_name) == 0) {
-			continue; /* no need for fix up */
-		}
+		fn_name = btf__str_by_offset(btf, fn_t->name_off) ?: "<anon>";
+		if (!need_func_arg_type_fixup(btf, prog, fn_name, arg_idx, p->type, ctx_name))
+			continue;
 
 		/* clone fn/fn_proto, unless we already did it for another arg */
 		if (func_rec->type_id == orig_fn_id) {
-- 
GitLab


From 556857aa1d0855aba02b1c63bc52b91ec63fc2cc Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Mon, 15 Jan 2024 11:18:05 +0100
Subject: [PATCH 2898/4076] wifi: ath11k: rely on mac80211 debugfs handling for
 vif

mac80211 started to delete debugfs entries in certain cases, causing a
ath11k to crash when it tried to delete the entries later. Fix this by
relying on mac80211 to delete the entries when appropriate and adding
them from the vif_add_debugfs handler.

Fixes: 0a3d898ee9a8 ("wifi: mac80211: add/remove driver debugfs entries as appropriate")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218364
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240115101805.1277949-1-benjamin@sipsolutions.net
---
 drivers/net/wireless/ath/ath11k/core.h    |  4 ----
 drivers/net/wireless/ath/ath11k/debugfs.c | 25 +++++++++--------------
 drivers/net/wireless/ath/ath11k/debugfs.h | 12 ++---------
 drivers/net/wireless/ath/ath11k/mac.c     | 12 +----------
 4 files changed, 13 insertions(+), 40 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index f12b606e2d2e5..667d55e261560 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -368,10 +368,6 @@ struct ath11k_vif {
 	struct ieee80211_chanctx_conf chanctx;
 	struct ath11k_arp_ns_offload arp_ns_offload;
 	struct ath11k_rekey_data rekey_data;
-
-#ifdef CONFIG_ATH11K_DEBUGFS
-	struct dentry *debugfs_twt;
-#endif /* CONFIG_ATH11K_DEBUGFS */
 };
 
 struct ath11k_vif_iter {
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index be76e7d1c4366..0796f4d92b477 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -1893,35 +1893,30 @@ static const struct file_operations ath11k_fops_twt_resume_dialog = {
 	.open = simple_open
 };
 
-void ath11k_debugfs_add_interface(struct ath11k_vif *arvif)
+void ath11k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif)
 {
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ath11k_base *ab = arvif->ar->ab;
+	struct dentry *debugfs_twt;
 
 	if (arvif->vif->type != NL80211_IFTYPE_AP &&
 	    !(arvif->vif->type == NL80211_IFTYPE_STATION &&
 	      test_bit(WMI_TLV_SERVICE_STA_TWT, ab->wmi_ab.svc_map)))
 		return;
 
-	arvif->debugfs_twt = debugfs_create_dir("twt",
-						arvif->vif->debugfs_dir);
-	debugfs_create_file("add_dialog", 0200, arvif->debugfs_twt,
+	debugfs_twt = debugfs_create_dir("twt",
+					 arvif->vif->debugfs_dir);
+	debugfs_create_file("add_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_add_dialog);
 
-	debugfs_create_file("del_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("del_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_del_dialog);
 
-	debugfs_create_file("pause_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("pause_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_pause_dialog);
 
-	debugfs_create_file("resume_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("resume_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_resume_dialog);
 }
 
-void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif)
-{
-	if (!arvif->debugfs_twt)
-		return;
-
-	debugfs_remove_recursive(arvif->debugfs_twt);
-	arvif->debugfs_twt = NULL;
-}
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.h b/drivers/net/wireless/ath/ath11k/debugfs.h
index 3af0169f6cf21..6f630b42e95c7 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs.h
@@ -306,8 +306,8 @@ static inline int ath11k_debugfs_rx_filter(struct ath11k *ar)
 	return ar->debug.rx_filter;
 }
 
-void ath11k_debugfs_add_interface(struct ath11k_vif *arvif);
-void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif);
+void ath11k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif);
 void ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 				     enum wmi_direct_buffer_module id,
 				     enum ath11k_dbg_dbr_event event,
@@ -386,14 +386,6 @@ static inline int ath11k_debugfs_get_fw_stats(struct ath11k *ar,
 	return 0;
 }
 
-static inline void ath11k_debugfs_add_interface(struct ath11k_vif *arvif)
-{
-}
-
-static inline void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif)
-{
-}
-
 static inline void
 ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 				enum wmi_direct_buffer_module id,
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 7f7b398177737..71c6dab1aedba 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -6750,13 +6750,6 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 		goto err;
 	}
 
-	/* In the case of hardware recovery, debugfs files are
-	 * not deleted since ieee80211_ops.remove_interface() is
-	 * not invoked. In such cases, try to delete the files.
-	 * These will be re-created later.
-	 */
-	ath11k_debugfs_remove_interface(arvif);
-
 	memset(arvif, 0, sizeof(*arvif));
 
 	arvif->ar = ar;
@@ -6933,8 +6926,6 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 
 	ath11k_dp_vdev_tx_attach(ar, arvif);
 
-	ath11k_debugfs_add_interface(arvif);
-
 	if (vif->type != NL80211_IFTYPE_MONITOR &&
 	    test_bit(ATH11K_FLAG_MONITOR_CONF_ENABLED, &ar->monitor_flags)) {
 		ret = ath11k_mac_monitor_vdev_create(ar);
@@ -7050,8 +7041,6 @@ err_vdev_del:
 	/* Recalc txpower for remaining vdev */
 	ath11k_mac_txpower_recalc(ar);
 
-	ath11k_debugfs_remove_interface(arvif);
-
 	/* TODO: recal traffic pause state based on the available vdevs */
 
 	mutex_unlock(&ar->conf_mutex);
@@ -9149,6 +9138,7 @@ static const struct ieee80211_ops ath11k_ops = {
 #endif
 
 #ifdef CONFIG_ATH11K_DEBUGFS
+	.vif_add_debugfs		= ath11k_debugfs_op_vif_add,
 	.sta_add_debugfs		= ath11k_debugfs_sta_op_add,
 #endif
 
-- 
GitLab


From 39369c9a6e090619a7b5eedb2212c99ac8a03890 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 16 Jan 2024 07:43:11 -0800
Subject: [PATCH 2899/4076] selftests: netdevsim: add a config file

netdevsim tests aren't very well integrated with kselftest,
which has its advantages and disadvantages. But regardless
of the intended integration - a config file to know what kernel
to build is very useful, add one.

Fixes: fc4c93f145d7 ("selftests: add basic netdevsim devlink flash testing")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20240116154311.1945801-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/netdevsim/config | 10 ++++++++++
 1 file changed, 10 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/netdevsim/config

diff --git a/tools/testing/selftests/drivers/net/netdevsim/config b/tools/testing/selftests/drivers/net/netdevsim/config
new file mode 100644
index 0000000000000..adf45a3a78b41
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/config
@@ -0,0 +1,10 @@
+CONFIG_DUMMY=y
+CONFIG_GENEVE=m
+CONFIG_IPV6=y
+CONFIG_NETDEVSIM=m
+CONFIG_NET_SCH_MQPRIO=y
+CONFIG_NET_SCH_MULTIQ=y
+CONFIG_NET_SCH_PRIO=y
+CONFIG_PSAMPLE=y
+CONFIG_PTP_1588_CLOCK_MOCK=y
+CONFIG_VXLAN=m
-- 
GitLab


From dd2d40acdbb2b9e6bcddd5424b0e00c1760ecf26 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Tue, 16 Jan 2024 10:49:26 -0500
Subject: [PATCH 2900/4076] selftests: bonding: Add more missing config options

As a followup to commit 03fb8565c880 ("selftests: bonding: add missing
build configs"), add more networking-specific config options which are
needed for bonding tests.

For testing, I used the minimal config generated by virtme-ng and I added
the options in the config file. All bonding tests passed.

Fixes: bbb774d921e2 ("net: Add tests for bonding and team address list management") # for ipv6
Fixes: 6cbe791c0f4e ("kselftest: bonding: add num_grat_arp test") # for tc options
Fixes: 222c94ec0ad4 ("selftests: bonding: add tests for ether type changes") # for nlmon
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Link: https://lore.kernel.org/r/20240116154926.202164-1-bpoirier@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/bonding/config | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
index f85b16fc5128c..899d7fb6ea8e9 100644
--- a/tools/testing/selftests/drivers/net/bonding/config
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -1,5 +1,10 @@
 CONFIG_BONDING=y
 CONFIG_BRIDGE=y
 CONFIG_DUMMY=y
+CONFIG_IPV6=y
 CONFIG_MACVLAN=y
+CONFIG_NET_ACT_GACT=y
+CONFIG_NET_CLS_FLOWER=y
+CONFIG_NET_SCH_INGRESS=y
+CONFIG_NLMON=y
 CONFIG_VETH=y
-- 
GitLab


From 832dd634bd1b4e3bbe9f10b9c9ba5db6f6f2b97f Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 16 Jan 2024 11:02:20 +0000
Subject: [PATCH 2901/4076] arm64: entry: fix
 ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD

Currently the ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD workaround isn't
quite right, as it is supposed to be applied after the last explicit
memory access, but is immediately followed by an LDR.

The ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD workaround is used to
handle Cortex-A520 erratum 2966298 and Cortex-A510 erratum 3117295,
which are described in:

* https://developer.arm.com/documentation/SDEN2444153/0600/?lang=en
* https://developer.arm.com/documentation/SDEN1873361/1600/?lang=en

In both cases the workaround is described as:

| If pagetable isolation is disabled, the context switch logic in the
| kernel can be updated to execute the following sequence on affected
| cores before exiting to EL0, and after all explicit memory accesses:
|
| 1. A non-shareable TLBI to any context and/or address, including
|    unused contexts or addresses, such as a `TLBI VALE1 Xzr`.
|
| 2. A DSB NSH to guarantee completion of the TLBI.

The important part being that the TLBI+DSB must be placed "after all
explicit memory accesses".

Unfortunately, as-implemented, the TLBI+DSB is immediately followed by
an LDR, as we have:

| alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
| 	tlbi	vale1, xzr
| 	dsb	nsh
| alternative_else_nop_endif
| alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
| 	ldr	lr, [sp, #S_LR]
| 	add	sp, sp, #PT_REGS_SIZE		// restore sp
| 	eret
| alternative_else_nop_endif
|
| [ ... KPTI exception return path ... ]

This patch fixes this by reworking the logic to place the TLBI+DSB
immediately before the ERET, after all explicit memory accesses.

The ERET is currently in a separate alternative block, and alternatives
cannot be nested. To account for this, the alternative block for
ARM64_UNMAP_KERNEL_AT_EL0 is replaced with a single alternative branch
to skip the KPTI logic, with the new shape of the logic being:

| alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0
| 	[ ... KPTI exception return path ... ]
| .L_skip_tramp_exit_\@:
|
| 	ldr	lr, [sp, #S_LR]
| 	add	sp, sp, #PT_REGS_SIZE		// restore sp
|
| alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
| 	tlbi	vale1, xzr
| 	dsb	nsh
| alternative_else_nop_endif
| 	eret

The new structure means that the workaround is only applied when KPTI is
not in use; this is fine as noted in the documented implications of the
erratum:

| Pagetable isolation between EL0 and higher level ELs prevents the
| issue from occurring.

... and as per the workaround description quoted above, the workaround
is only necessary "If pagetable isolation is disabled".

Fixes: 471470bc7052 ("arm64: errata: Add Cortex-A520 speculative unprivileged load workaround")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240116110221.420467-2-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/entry.S | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 544ab46649f3f..7fcbee0f6c0e4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -428,16 +428,9 @@ alternative_else_nop_endif
 	ldp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
-alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
-	tlbi	vale1, xzr
-	dsb	nsh
-alternative_else_nop_endif
-alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
-	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #PT_REGS_SIZE		// restore sp
-	eret
-alternative_else_nop_endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0
+
 	msr	far_el1, x29
 
 	ldr_this_cpu	x30, this_cpu_vector, x29
@@ -446,7 +439,18 @@ alternative_else_nop_endif
 	ldr		lr, [sp, #S_LR]		// restore x30
 	add		sp, sp, #PT_REGS_SIZE	// restore sp
 	br		x29
+
+.L_skip_tramp_exit_\@:
 #endif
+	ldr	lr, [sp, #S_LR]
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
+
+	/* This must be after the last explicit memory access */
+alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
+	tlbi	vale1, xzr
+	dsb	nsh
+alternative_else_nop_endif
+	eret
 	.else
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp
-- 
GitLab


From da59f1d051d57e85eca49401a3a36d5a622babde Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 16 Jan 2024 11:02:21 +0000
Subject: [PATCH 2902/4076] arm64: entry: simplify kernel_exit logic

For historical reasons, the non-KPTI exception return path is duplicated for
EL1 and EL0, with the structure:

	.if \el == 0
	[ KPTI handling ]
	ldr     lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp
	[ EL0 exception return workaround ]
	eret
	.else
	ldr     lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp
	[ EL1 exception return workaround ]
	eret
	.endif
	sb

This would be simpler and clearer with the common portions factored out,
e.g.

	.if \el == 0
	[ KPTI handling ]
	.endif

	ldr     lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp

	.if \el == 0
	[ EL0 exception return workaround ]
	.else
	[ EL1 exception return workaround ]
	.endif

	eret
	sb

This expands to the same code, but is simpler for a human to follow as
it avoids duplicates the restore of LR+SP, and makes it clear that the
ERET is associated with the SB.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20240116110221.420467-3-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/entry.S | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 7fcbee0f6c0e4..7ef0e127b149f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -442,24 +442,23 @@ alternative_else_nop_endif
 
 .L_skip_tramp_exit_\@:
 #endif
+	.endif
+
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
+	.if \el == 0
 	/* This must be after the last explicit memory access */
 alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	tlbi	vale1, xzr
 	dsb	nsh
 alternative_else_nop_endif
-	eret
 	.else
-	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #PT_REGS_SIZE		// restore sp
-
 	/* Ensure any device/NC reads complete */
 	alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
+	.endif
 
 	eret
-	.endif
 	sb
 	.endm
 
-- 
GitLab


From b7c510d049049409e8945b932f4b0b357fa17415 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Mon, 15 Jan 2024 18:42:38 +0000
Subject: [PATCH 2903/4076] arm64/ptrace: Don't flush ZA/ZT storage when
 writing ZA via ptrace

When writing ZA we currently unconditionally flush the buffer used to store
it as part of ensuring that it is allocated. Since this buffer is shared
with ZT0 this means that a write to ZA when PSTATE.ZA is already set will
corrupt the value of ZT0 on a SME2 system. Fix this by only flushing the
backing storage if PSTATE.ZA was not previously set.

This will mean that short or failed writes may leave stale data in the
buffer, this seems as correct as our current behaviour and unlikely to be
something that userspace will rely on.

Fixes: f90b529bcbe5 ("arm64/sme: Implement ZT0 ptrace support")
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20240115-arm64-fix-ptrace-za-zt-v1-1-48617517028a@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/ptrace.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 20d7ef82de90a..b3f64144b5cd9 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1107,12 +1107,13 @@ static int za_set(struct task_struct *target,
 		}
 	}
 
-	/* Allocate/reinit ZA storage */
-	sme_alloc(target, true);
-	if (!target->thread.sme_state) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	/*
+	 * Only flush the storage if PSTATE.ZA was not already set,
+	 * otherwise preserve any existing data.
+	 */
+	sme_alloc(target, !thread_za_enabled(&target->thread));
+	if (!target->thread.sme_state)
+		return -ENOMEM;
 
 	/* If there is no data then disable ZA */
 	if (!count) {
-- 
GitLab


From 6992eb815d087858f8d7e4020529c2fe800456b3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 16 Jan 2024 23:08:21 +0200
Subject: [PATCH 2904/4076] Revert "drm/i915/dsi: Do display on sequence later
 on icl+"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 88b065943cb583e890324d618e8d4b23460d51a3.

Lenovo 82TQ is unhappy if we do the display on sequence this
late. The display output shows severe corruption.

It's unclear if this is a failure on our part (perhaps
something to do with sending commands in LP mode after HS
/video mode transmission has been started? Though the backlight
on command at least seems to work) or simply that there are
some commands in the sequence that are needed to be done
earlier (eg. could be some DSC init stuff?). If the latter
then I don't think the current Windows code would work
either, but maybe this was originally tested with an older
driver, who knows.

Root causing this fully would likely require a lot of
experimentation which isn't really feasible without direct
access to the machine, so let's just accept failure and
go back to the original sequence.

Cc: stable@vger.kernel.org
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/10071
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240116210821.30194-1-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit dc524d05974f615b145404191fcf91b478950499)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/icl_dsi.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index ac456a2275dba..eda4a8b885904 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1155,6 +1155,7 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 	}
 
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP);
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
 
 	/* ensure all panel commands dispatched before enabling transcoder */
 	wait_for_cmds_dispatched_to_panel(encoder);
@@ -1255,8 +1256,6 @@ static void gen11_dsi_enable(struct intel_atomic_state *state,
 	/* step6d: enable dsi transcoder */
 	gen11_dsi_enable_transcoder(encoder);
 
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
-
 	/* step7: enable backlight */
 	intel_backlight_enable(crtc_state, conn_state);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON);
-- 
GitLab


From 84b5ece64477df4394d362d494a2496bf0878985 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Fri, 12 Jan 2024 07:49:12 -0800
Subject: [PATCH 2905/4076] drm/i915: Drop -Wstringop-overflow

-Wstringop-overflow is broken on GCC11. In future changes it will
be moved to the normal C flags in the top level Makefile (out of
Makefile.extrawarn), but accounting for the compiler support.

Just remove it out of i915's forced extra warnings, preparing for the
upcoming change and avoiding build warnings to show up.

Fixes: 2250c7ead8ad ("drm/i915: enable W=1 warnings by default")
References: https://lore.kernel.org/all/45ad1d0f-a10f-483e-848a-76a30252edbe@paulmck-laptop/
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240112154912.1775199-1-lucas.demarchi@intel.com
(cherry picked from commit 05ae67d95bade8b7facd5612baea21c12d243149)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/Makefile | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e777686190ca2..c13f14edb5088 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -17,7 +17,6 @@ subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
 subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
 subdir-ccflags-y += $(call cc-option, -Wformat-overflow)
 subdir-ccflags-y += $(call cc-option, -Wformat-truncation)
-subdir-ccflags-y += $(call cc-option, -Wstringop-overflow)
 subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
 # The following turn off the warnings enabled by -Wextra
 ifeq ($(findstring 2, $(KBUILD_EXTRA_WARN)),)
-- 
GitLab


From 8410186ca48002092818500b7c209e569b47a2ac Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Mon, 15 Jan 2024 19:53:01 +0000
Subject: [PATCH 2906/4076] arm64/fpsimd: Remove spurious check for SVE support

There is no need to check for SVE support when changing vector lengths,
even if the system is SME only we still need SVE storage for the streaming
SVE state.

Fixes: d4d5be94a878 ("arm64/fpsimd: Ensure SME storage is allocated after SVE VL changes")
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20240115-arm64-sve-enabled-check-v1-1-a26360b00f6d@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/fpsimd.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 505f389be3e0d..0983be2b1b614 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -898,10 +898,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	 * allocate SVE now in case it is needed for use in streaming
 	 * mode.
 	 */
-	if (system_supports_sve()) {
-		sve_free(task);
-		sve_alloc(task, true);
-	}
+	sve_free(task);
+	sve_alloc(task, true);
 
 	if (free_sme)
 		sme_free(task);
-- 
GitLab


From dc7eb8755797ed41a0d1b5c0c39df3c8f401b3d9 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Mon, 15 Jan 2024 20:15:46 +0000
Subject: [PATCH 2907/4076] arm64/sme: Always exit sme_alloc() early with
 existing storage

When sme_alloc() is called with existing storage and we are not flushing we
will always allocate new storage, both leaking the existing storage and
corrupting the state. Fix this by separating the checks for flushing and
for existing storage as we do for SVE.

Callers that reallocate (eg, due to changing the vector length) should
call sme_free() themselves.

Fixes: 5d0a8d2fba50 ("arm64/ptrace: Ensure that SME is set up for target when writing SSVE state")
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240115-arm64-sme-flush-v1-1-7472bd3459b7@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/fpsimd.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 0983be2b1b614..a5dc6f7641958 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1217,8 +1217,10 @@ void fpsimd_release_task(struct task_struct *dead_task)
  */
 void sme_alloc(struct task_struct *task, bool flush)
 {
-	if (task->thread.sme_state && flush) {
-		memset(task->thread.sme_state, 0, sme_state_size(task));
+	if (task->thread.sme_state) {
+		if (flush)
+			memset(task->thread.sme_state, 0,
+			       sme_state_size(task));
 		return;
 	}
 
-- 
GitLab


From 1b20d0486a602417defb5bf33320d31b2a7a47f8 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 17 Jan 2024 17:05:45 +0000
Subject: [PATCH 2908/4076] arm64: Fix silcon-errata.rst formatting

Remove the errant blank lines to make the desired empty row separators
around the Fujitsu and ASR entries in the main table, rather than them
being their own separate tables which then look odd in the HTML view.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/b6637654eda761e224f828a44a7bbc1eadf2ef88.1705511145.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/arch/arm64/silicon-errata.rst | 2 --
 1 file changed, 2 deletions(-)

diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index 7acd64c61f50c..b30bd6abffbe9 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -227,11 +227,9 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Rockchip       | RK3588          | #3588001        | ROCKCHIP_ERRATUM_3588001    |
 +----------------+-----------------+-----------------+-----------------------------+
-
 +----------------+-----------------+-----------------+-----------------------------+
 | Fujitsu        | A64FX           | E#010001        | FUJITSU_ERRATUM_010001      |
 +----------------+-----------------+-----------------+-----------------------------+
-
 +----------------+-----------------+-----------------+-----------------------------+
 | ASR            | ASR8601         | #8601001        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
-- 
GitLab


From f1172f3ee3a98754d95b968968920a7d03fdebcc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ludvig=20P=C3=A4rsson?= <ludvig.parsson@axis.com>
Date: Wed, 17 Jan 2024 13:03:14 +0100
Subject: [PATCH 2909/4076] ethtool: netlink: Add missing
 ethnl_ops_begin/complete
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Accessing an ethernet device that is powered off or clock gated might
cause the CPU to hang. Add ethnl_ops_begin/complete in
ethnl_set_features() to protect against this.

Fixes: 0980bfcd6954 ("ethtool: set netdev features with FEATURES_SET request")
Signed-off-by: Ludvig Pärsson <ludvig.parsson@axis.com>
Link: https://lore.kernel.org/r/20240117-etht2-v2-1-1a96b6e8c650@axis.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ethtool/features.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index a79af8c25a071..b6cb101d7f19e 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -234,17 +234,20 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		goto out_rtnl;
 	ethnl_features_to_bitmap(old_active, dev->features);
 	ethnl_features_to_bitmap(old_wanted, dev->wanted_features);
 	ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT,
 				 tb[ETHTOOL_A_FEATURES_WANTED],
 				 netdev_features_strings, info->extack);
 	if (ret < 0)
-		goto out_rtnl;
+		goto out_ops;
 	if (ethnl_bitmap_to_features(req_mask) & ~NETIF_F_ETHTOOL_BITS) {
 		GENL_SET_ERR_MSG(info, "attempt to change non-ethtool features");
 		ret = -EINVAL;
-		goto out_rtnl;
+		goto out_ops;
 	}
 
 	/* set req_wanted bits not in req_mask from old_wanted */
@@ -281,6 +284,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	if (mod)
 		netdev_features_change(dev);
 
+out_ops:
+	ethnl_ops_complete(dev);
 out_rtnl:
 	rtnl_unlock();
 	ethnl_parse_header_dev_put(&req_info);
-- 
GitLab


From a6e4f85d3820d00694ed10f581f4c650445dbcda Mon Sep 17 00:00:00 2001
From: Michal Kazior <michal@plume.com>
Date: Tue, 16 Jan 2024 14:22:57 +0000
Subject: [PATCH 2910/4076] wifi: cfg80211: fix missing interfaces when dumping

The nl80211_dump_interface() supports resumption
in case nl80211_send_iface() doesn't have the
resources to complete its work.

The logic would store the progress as iteration
offsets for rdev and wdev loops.

However the logic did not properly handle
resumption for non-last rdev. Assuming a system
with 2 rdevs, with 2 wdevs each, this could
happen:

 dump(cb=[0, 0]):
  if_start=cb[1] (=0)
  send rdev0.wdev0 -> ok
  send rdev0.wdev1 -> yield
  cb[1] = 1

 dump(cb=[0, 1]):
  if_start=cb[1] (=1)
  send rdev0.wdev1 -> ok
  // since if_start=1 the rdev0.wdev0 got skipped
  // through if_idx < if_start
  send rdev1.wdev1 -> ok

The if_start needs to be reset back to 0 upon wdev
loop end.

The problem is actually hard to hit on a desktop,
and even on most routers. The prerequisites for
this manifesting was:
 - more than 1 wiphy
 - a few handful of interfaces
 - dump without rdev or wdev filter

I was seeing this with 4 wiphys 9 interfaces each.
It'd miss 6 interfaces from the last wiphy
reported to userspace.

Signed-off-by: Michal Kazior <michal@plume.com>
Link: https://msgid.link/20240116142340.89678-1-kazikcz@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 1cbbb11ea5033..fbf95b7ff6b43 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4008,6 +4008,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 		}
 		wiphy_unlock(&rdev->wiphy);
 
+		if_start = 0;
 		wp_idx++;
 	}
  out:
-- 
GitLab


From 26490da5a71da9064e58f0d4ce82756c26ef9eb1 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Thu, 18 Jan 2024 09:25:45 +0100
Subject: [PATCH 2911/4076] wifi: cfg80211/mac80211: remove dependency on
 non-existing option

Commit ffbd0c8c1e7f ("wifi: mac80211: add an element parsing unit test")
and commit 730eeb17bbdd ("wifi: cfg80211: add first kunit tests, for
element defrag") add new configs that depend on !KERNEL_6_2, but the config
option KERNEL_6_2 does not exist in the tree. This dependency is used for
handling backporting to restrict the option to certain kernels but this
really should not be carried around the mainline kernel tree.

Clean up this needless dependency on the non-existing option KERNEL_6_2.

Link: https://lore.kernel.org/lkml/CAKXUXMyfrM6amOR7Ysim3WNQ-Ckf9HJDqRhAoYmLXujo1UV+yA@mail.gmail.com/
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/Kconfig | 1 -
 net/wireless/Kconfig | 1 -
 2 files changed, 2 deletions(-)

diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index cb0291decf2e5..13438cc0a6b13 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -62,7 +62,6 @@ config MAC80211_KUNIT_TEST
 	depends on KUNIT
 	depends on MAC80211
 	default KUNIT_ALL_TESTS
-	depends on !KERNEL_6_2
 	help
 	  Enable this option to test mac80211 internals with kunit.
 
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index a9ac85e09af37..10345388ad139 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -206,7 +206,6 @@ config CFG80211_KUNIT_TEST
 	depends on KUNIT
 	depends on CFG80211
 	default KUNIT_ALL_TESTS
-	depends on !KERNEL_6_2
 	help
 	  Enable this option to test cfg80211 functions with kunit.
 
-- 
GitLab


From b01a74b3ca6fd51b62c67733ba7c3280fa6c5d26 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 11 Jan 2024 18:17:44 +0200
Subject: [PATCH 2912/4076] wifi: mac80211: fix potential sta-link leak

When a station is allocated, links are added but not
set to valid yet (e.g. during connection to an AP MLD),
we might remove the station without ever marking links
valid, and leak them. Fix that.

Fixes: cb71f1d136a6 ("wifi: mac80211: add sta link addition/removal")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240111181514.6573998beaf8.I09ac2e1d41c80f82a5a616b8bd1d9d8dd709a6a6@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 0ba613dd1cc47..c33decbb97f2d 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -404,7 +404,10 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(sta->link); i++) {
-		if (!(sta->sta.valid_links & BIT(i)))
+		struct link_sta_info *link_sta;
+
+		link_sta = rcu_access_pointer(sta->link[i]);
+		if (!link_sta)
 			continue;
 
 		sta_remove_link(sta, i, false);
-- 
GitLab


From cf4a0d840ecc72fcf16198d5e9c505ab7d5a5e4d Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 11 Jan 2024 15:07:25 +0200
Subject: [PATCH 2913/4076] wifi: iwlwifi: fix a memory corruption

iwl_fw_ini_trigger_tlv::data is a pointer to a __le32, which means that
if we copy to iwl_fw_ini_trigger_tlv::data + offset while offset is in
bytes, we'll write past the buffer.

Cc: stable@vger.kernel.org
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218233
Fixes: cf29c5b66b9f ("iwlwifi: dbg_ini: implement time point handling")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240111150610.2d2b8b870194.I14ed76505a5cf87304e0c9cc05cc0ae85ed3bf91@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index b658cf228fbe2..9160d81a871ee 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 #include <linux/firmware.h>
 #include "iwl-drv.h"
@@ -1096,7 +1096,7 @@ static int iwl_dbg_tlv_override_trig_node(struct iwl_fw_runtime *fwrt,
 		node_trig = (void *)node_tlv->data;
 	}
 
-	memcpy(node_trig->data + offset, trig->data, trig_data_len);
+	memcpy((u8 *)node_trig->data + offset, trig->data, trig_data_len);
 	node_tlv->length = cpu_to_le32(size);
 
 	if (policy & IWL_FW_INI_APPLY_POLICY_OVERRIDE_CFG) {
-- 
GitLab


From bcbc84af1183c8cf3d1ca9b78540c2185cd85e7f Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 4 Jan 2024 19:10:59 +0100
Subject: [PATCH 2914/4076] wifi: mac80211: fix race condition on enabling
 fast-xmit

fast-xmit must only be enabled after the sta has been uploaded to the driver,
otherwise it could end up passing the not-yet-uploaded sta via drv_tx calls
to the driver, leading to potential crashes because of uninitialized drv_priv
data.
Add a missing sta->uploaded check and re-check fast xmit after inserting a sta.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://msgid.link/20240104181059.84032-1-nbd@nbd.name
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 2 ++
 net/mac80211/tx.c       | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index c33decbb97f2d..bcf3f727fc6da 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -913,6 +913,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 	if (ieee80211_vif_is_mesh(&sdata->vif))
 		mesh_accept_plinks_update(sdata);
 
+	ieee80211_check_fast_xmit(sta);
+
 	return 0;
  out_remove:
 	if (sta->sta.valid_links)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index ed4fdf655343f..4b2823e36a374 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3048,7 +3048,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
 	    sdata->vif.type == NL80211_IFTYPE_STATION)
 		goto out;
 
-	if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED))
+	if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded)
 		goto out;
 
 	if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
-- 
GitLab


From 0991abeddefa118479b0af32c28bcd662dec1561 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Thu, 18 Jan 2024 09:52:52 +0800
Subject: [PATCH 2915/4076] exfat: fix zero the unwritten part for dio read

For dio read, bio will be leave in flight when a successful partial
aio read have been setup, blockdev_direct_IO() will return
-EIOCBQUEUED. In the case, iter->iov_offset will be not advanced,
the oops reported by syzbot will occur if revert iter->iov_offset
with iov_iter_revert(). The unwritten part had been zeroed by aio
read, so there is no need to zero it in dio read.

Reported-by: syzbot+fd404f6b03a58e8bc403@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=fd404f6b03a58e8bc403
Fixes: 11a347fb6cef ("exfat: change to get file size from DataLength")
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/inode.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index 522edcbb2ce4d..0687f952956c3 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -501,7 +501,7 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = mapping->host;
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	loff_t pos = iocb->ki_pos;
-	loff_t size = iocb->ki_pos + iov_iter_count(iter);
+	loff_t size = pos + iov_iter_count(iter);
 	int rw = iov_iter_rw(iter);
 	ssize_t ret;
 
@@ -525,11 +525,10 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	 */
 	ret = blockdev_direct_IO(iocb, inode, iter, exfat_get_block);
 	if (ret < 0) {
-		if (rw == WRITE)
+		if (rw == WRITE && ret != -EIOCBQUEUED)
 			exfat_write_failed(mapping, size);
 
-		if (ret != -EIOCBQUEUED)
-			return ret;
+		return ret;
 	} else
 		size = pos + ret;
 
-- 
GitLab


From 7a8e9cdf9405819105ae7405cd91e482bf574b01 Mon Sep 17 00:00:00 2001
From: Nathan Lynch <nathanl@linux.ibm.com>
Date: Tue, 16 Jan 2024 08:09:25 -0600
Subject: [PATCH 2916/4076] seq_buf: Make DECLARE_SEQ_BUF() usable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using the address operator on the array doesn't work:

./include/linux/seq_buf.h:27:27: error: initialization of ‘char *’
  from incompatible pointer type ‘char (*)[128]’
  [-Werror=incompatible-pointer-types]
   27 |                 .buffer = &__ ## NAME ## _buffer,       \
      |                           ^

Apart from fixing that, we can improve DECLARE_SEQ_BUF() by using a
compound literal to define the buffer array without attaching a name
to it. This makes the macro a single statement, allowing constructs
such as:

  static DECLARE_SEQ_BUF(my_seq_buf, MYSB_SIZE);

to work as intended.

Link: https://lkml.kernel.org/r/20240116-declare-seq-buf-fix-v1-1-915db4692f32@linux.ibm.com

Cc: stable@vger.kernel.org
Acked-by: Kees Cook <keescook@chromium.org>
Fixes: dcc4e5728eea ("seq_buf: Introduce DECLARE_SEQ_BUF and seq_buf_str()")
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/seq_buf.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 5fb1f12c33f90..c44f4b47b9453 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -22,9 +22,8 @@ struct seq_buf {
 };
 
 #define DECLARE_SEQ_BUF(NAME, SIZE)			\
-	char __ ## NAME ## _buffer[SIZE] = "";		\
 	struct seq_buf NAME = {				\
-		.buffer = &__ ## NAME ## _buffer,	\
+		.buffer = (char[SIZE]) { 0 },		\
 		.size = SIZE,				\
 	}
 
-- 
GitLab


From baa7d536077dcdfe2b70c476a8873d1745d3de0f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 17 Jan 2024 18:59:01 +0100
Subject: [PATCH 2917/4076] loop: fix the the direct I/O support check when
 used on top of block devices

__loop_update_dio only checks the alignment requirement for block backed
file systems, but misses them for the case where the loop device is
created directly on top of another block device.  Due to this creating
a loop device with default option plus the direct I/O flag on a > 512 byte
sector size file system will lead to incorrect I/O being submitted to the
lower block device and a lot of error from the lock layer.  This can
be seen with xfstests generic/563.

Fix the code in __loop_update_dio by factoring the alignment check into
a helper, and calling that also for the struct block_device of a block
device inode.

Also remove the TODO comment talking about dynamically switching between
buffered and direct I/O, which is a would be a recipe for horrible
performance and occasional data loss.

Fixes: 2e5ab5f379f9 ("block: loop: prepare for supporing direct IO")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240117175901.871796-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 52 +++++++++++++++++++++-----------------------
 1 file changed, 25 insertions(+), 27 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 2bd10f3bfcb29..01bb943624048 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -165,39 +165,37 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
 	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
 }
 
+/*
+ * We support direct I/O only if lo_offset is aligned with the logical I/O size
+ * of backing device, and the logical block size of loop is bigger than that of
+ * the backing device.
+ */
+static bool lo_bdev_can_use_dio(struct loop_device *lo,
+		struct block_device *backing_bdev)
+{
+	unsigned short sb_bsize = bdev_logical_block_size(backing_bdev);
+
+	if (queue_logical_block_size(lo->lo_queue) < sb_bsize)
+		return false;
+	if (lo->lo_offset & (sb_bsize - 1))
+		return false;
+	return true;
+}
+
 static void __loop_update_dio(struct loop_device *lo, bool dio)
 {
 	struct file *file = lo->lo_backing_file;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	unsigned short sb_bsize = 0;
-	unsigned dio_align = 0;
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *backing_bdev = NULL;
 	bool use_dio;
 
-	if (inode->i_sb->s_bdev) {
-		sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
-		dio_align = sb_bsize - 1;
-	}
+	if (S_ISBLK(inode->i_mode))
+		backing_bdev = I_BDEV(inode);
+	else if (inode->i_sb->s_bdev)
+		backing_bdev = inode->i_sb->s_bdev;
 
-	/*
-	 * We support direct I/O only if lo_offset is aligned with the
-	 * logical I/O size of backing device, and the logical block
-	 * size of loop is bigger than the backing device's.
-	 *
-	 * TODO: the above condition may be loosed in the future, and
-	 * direct I/O may be switched runtime at that time because most
-	 * of requests in sane applications should be PAGE_SIZE aligned
-	 */
-	if (dio) {
-		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
-		    !(lo->lo_offset & dio_align) &&
-		    (file->f_mode & FMODE_CAN_ODIRECT))
-			use_dio = true;
-		else
-			use_dio = false;
-	} else {
-		use_dio = false;
-	}
+	use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) &&
+		(!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev));
 
 	if (lo->use_dio == use_dio)
 		return;
-- 
GitLab


From b2e792ae883a0aa976d4176dfa7dc933263440ea Mon Sep 17 00:00:00 2001
From: Christian Loehle <christian.loehle@arm.com>
Date: Thu, 18 Jan 2024 09:29:56 +0000
Subject: [PATCH 2918/4076] Documentation: block: ioprio: Update schedulers

This doc hasn't been touched in a while, in the meantime some
new io schedulers were added (e.g. all of mq), some with ioprio
support.

Also reword the introduction to remove reference to CFQ and the
limitation that io priorities only work on reads, which is no longer
true.

Signed-off-by: Christian Loehle <christian.loehle@arm.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/a86cfdc8-016f-40f1-8b58-0cb15d2a792c@arm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/ioprio.rst | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/Documentation/block/ioprio.rst b/Documentation/block/ioprio.rst
index a25c6d5df87b2..4662e1ff3d81f 100644
--- a/Documentation/block/ioprio.rst
+++ b/Documentation/block/ioprio.rst
@@ -6,17 +6,16 @@ Block io priorities
 Intro
 -----
 
-With the introduction of cfq v3 (aka cfq-ts or time sliced cfq), basic io
-priorities are supported for reads on files.  This enables users to io nice
-processes or process groups, similar to what has been possible with cpu
-scheduling for ages.  This document mainly details the current possibilities
-with cfq; other io schedulers do not support io priorities thus far.
+The io priority feature enables users to io nice processes or process groups,
+similar to what has been possible with cpu scheduling for ages. Support for io
+priorities is io scheduler dependent and currently supported by bfq and
+mq-deadline.
 
 Scheduling classes
 ------------------
 
-CFQ implements three generic scheduling classes that determine how io is
-served for a process.
+Three generic scheduling classes are implemented for io priorities that
+determine how io is served for a process.
 
 IOPRIO_CLASS_RT: This is the realtime io class. This scheduling class is given
 higher priority than any other in the system, processes from this class are
-- 
GitLab


From 55583e899a5357308274601364741a83e78d6ac4 Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 4 Jan 2024 22:20:33 +0800
Subject: [PATCH 2919/4076] ext4: fix double-free of blocks due to wrong
 extents moved_len

In ext4_move_extents(), moved_len is only updated when all moves are
successfully executed, and only discards orig_inode and donor_inode
preallocations when moved_len is not zero. When the loop fails to exit
after successfully moving some extents, moved_len is not updated and
remains at 0, so it does not discard the preallocations.

If the moved extents overlap with the preallocated extents, the
overlapped extents are freed twice in ext4_mb_release_inode_pa() and
ext4_process_freed_data() (as described in commit 94d7c16cbbbd ("ext4:
Fix double-free of blocks with EXT4_IOC_MOVE_EXT")), and bb_free is
incremented twice. Hence when trim is executed, a zero-division bug is
triggered in mb_update_avg_fragment_size() because bb_free is not zero
and bb_fragments is zero.

Therefore, update move_len after each extent move to avoid the issue.

Reported-by: Wei Chen <harperchen1110@gmail.com>
Reported-by: xingwei lee <xrivendell7@gmail.com>
Closes: https://lore.kernel.org/r/CAO4mrferzqBUnCag8R3m2zf897ts9UEuhjFQGPtODT92rYyR2Q@mail.gmail.com
Fixes: fcf6b1b729bc ("ext4: refactor ext4_move_extents code base")
CC:  <stable@vger.kernel.org> # 3.18
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240104142040.2835097-2-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/move_extent.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3aa57376d9c2e..391efa6d4c56f 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -618,6 +618,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		goto out;
 	o_end = o_start + len;
 
+	*moved_len = 0;
 	while (o_start < o_end) {
 		struct ext4_extent *ex;
 		ext4_lblk_t cur_blk, next_blk;
@@ -672,7 +673,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		 */
 		ext4_double_up_write_data_sem(orig_inode, donor_inode);
 		/* Swap original branches with new branches */
-		move_extent_per_page(o_filp, donor_inode,
+		*moved_len += move_extent_per_page(o_filp, donor_inode,
 				     orig_page_index, donor_page_index,
 				     offset_in_page, cur_len,
 				     unwritten, &ret);
@@ -682,9 +683,6 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		o_start += cur_len;
 		d_start += cur_len;
 	}
-	*moved_len = o_start - orig_blk;
-	if (*moved_len > len)
-		*moved_len = len;
 
 out:
 	if (*moved_len) {
-- 
GitLab


From 172202152a125955367393956acf5f4ffd092e0d Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 4 Jan 2024 22:20:34 +0800
Subject: [PATCH 2920/4076] ext4: do not trim the group with corrupted block
 bitmap

Otherwise operating on an incorrupted block bitmap can lead to all sorts
of unknown problems.

Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240104142040.2835097-3-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f44f668e407f2..c86c90b494de3 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -6761,6 +6761,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 	bool set_trimmed = false;
 	void *bitmap;
 
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		return 0;
+
 	last = ext4_last_grp_cluster(sb, e4b->bd_group);
 	bitmap = e4b->bd_bitmap;
 	if (start == 0 && max >= last)
-- 
GitLab


From c9b528c35795b711331ed36dc3dbee90d5812d4e Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 4 Jan 2024 22:20:35 +0800
Subject: [PATCH 2921/4076] ext4: regenerate buddy after block freeing failed
 if under fc replay

This mostly reverts commit 6bd97bf273bd ("ext4: remove redundant
mb_regenerate_buddy()") and reintroduces mb_regenerate_buddy(). Based on
code in mb_free_blocks(), fast commit replay can end up marking as free
blocks that are already marked as such. This causes corruption of the
buddy bitmap so we need to regenerate it in that case.

Reported-by: Jan Kara <jack@suse.cz>
Fixes: 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()")
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240104142040.2835097-4-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c86c90b494de3..c97ad0e778318 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1233,6 +1233,24 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 	atomic64_add(period, &sbi->s_mb_generation_time);
 }
 
+static void mb_regenerate_buddy(struct ext4_buddy *e4b)
+{
+	int count;
+	int order = 1;
+	void *buddy;
+
+	while ((buddy = mb_find_buddy(e4b, order++, &count)))
+		mb_set_bits(buddy, 0, count);
+
+	e4b->bd_info->bb_fragments = 0;
+	memset(e4b->bd_info->bb_counters, 0,
+		sizeof(*e4b->bd_info->bb_counters) *
+		(e4b->bd_sb->s_blocksize_bits + 2));
+
+	ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
+		e4b->bd_bitmap, e4b->bd_group, e4b->bd_info);
+}
+
 /* The buddy information is attached the buddy cache inode
  * for convenience. The information regarding each group
  * is loaded via ext4_mb_load_buddy. The information involve
@@ -1920,6 +1938,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 			ext4_mark_group_bitmap_corrupted(
 				sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
+		} else {
+			mb_regenerate_buddy(e4b);
 		}
 		goto done;
 	}
-- 
GitLab


From 2331fd4a49864e1571b4f50aa3aa1536ed6220d0 Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 4 Jan 2024 22:20:36 +0800
Subject: [PATCH 2922/4076] ext4: avoid bb_free and bb_fragments inconsistency
 in mb_free_blocks()

After updating bb_free in mb_free_blocks, it is possible to return without
updating bb_fragments because the block being freed is found to have
already been freed, which leads to inconsistency between bb_free and
bb_fragments.

Since the group may be unlocked in ext4_grp_locked_error(), this can lead
to problems such as dividing by zero when calculating the average fragment
length. Hence move the update of bb_free to after the block double-free
check guarantees that the corresponding statistics are updated only after
the core block bitmap is modified.

Fixes: eabe0444df90 ("ext4: speed-up releasing blocks on commit")
CC:  <stable@vger.kernel.org> # 3.10
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240104142040.2835097-5-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 39 +++++++++++++++++++++------------------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c97ad0e778318..fa351aa323dcf 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1909,11 +1909,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	mb_check_buddy(e4b);
 	mb_free_blocks_double(inode, e4b, first, count);
 
-	this_cpu_inc(discard_pa_seq);
-	e4b->bd_info->bb_free += count;
-	if (first < e4b->bd_info->bb_first_free)
-		e4b->bd_info->bb_first_free = first;
-
 	/* access memory sequentially: check left neighbour,
 	 * clear range and then check right neighbour
 	 */
@@ -1927,23 +1922,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 		struct ext4_sb_info *sbi = EXT4_SB(sb);
 		ext4_fsblk_t blocknr;
 
+		/*
+		 * Fastcommit replay can free already freed blocks which
+		 * corrupts allocation info. Regenerate it.
+		 */
+		if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+			mb_regenerate_buddy(e4b);
+			goto check;
+		}
+
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 		blocknr += EXT4_C2B(sbi, block);
-		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
-			ext4_grp_locked_error(sb, e4b->bd_group,
-					      inode ? inode->i_ino : 0,
-					      blocknr,
-					      "freeing already freed block (bit %u); block bitmap corrupt.",
-					      block);
-			ext4_mark_group_bitmap_corrupted(
-				sb, e4b->bd_group,
+		ext4_grp_locked_error(sb, e4b->bd_group,
+				      inode ? inode->i_ino : 0, blocknr,
+				      "freeing already freed block (bit %u); block bitmap corrupt.",
+				      block);
+		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
-		} else {
-			mb_regenerate_buddy(e4b);
-		}
-		goto done;
+		return;
 	}
 
+	this_cpu_inc(discard_pa_seq);
+	e4b->bd_info->bb_free += count;
+	if (first < e4b->bd_info->bb_first_free)
+		e4b->bd_info->bb_first_free = first;
+
 	/* let's maintain fragments counter */
 	if (left_is_free && right_is_free)
 		e4b->bd_info->bb_fragments--;
@@ -1968,9 +1971,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	if (first <= last)
 		mb_buddy_mark_free(e4b, first >> 1, last >> 1);
 
-done:
 	mb_set_largest_free_order(sb, e4b->bd_info);
 	mb_update_avg_fragment_size(sb, e4b->bd_info);
+check:
 	mb_check_buddy(e4b);
 }
 
-- 
GitLab


From 993bf0f4c393b3667830918f9247438a8f6fdb5b Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 4 Jan 2024 22:20:37 +0800
Subject: [PATCH 2923/4076] ext4: avoid dividing by 0 in
 mb_update_avg_fragment_size() when block bitmap corrupt

Determine if bb_fragments is 0 instead of determining bb_free to eliminate
the risk of dividing by zero when the block bitmap is corrupted.

Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240104142040.2835097-6-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index fa351aa323dcf..751e31df0f104 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -842,7 +842,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int new_order;
 
-	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
+	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0)
 		return;
 
 	new_order = mb_avg_fragment_size_order(sb,
-- 
GitLab


From 4530b3660d396a646aad91a787b6ab37cf604b53 Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 4 Jan 2024 22:20:38 +0800
Subject: [PATCH 2924/4076] ext4: avoid allocating blocks from corrupted group
 in ext4_mb_try_best_found()

Determine if the group block bitmap is corrupted before using ac_b_ex in
ext4_mb_try_best_found() to avoid allocating blocks from a group with a
corrupted block bitmap in the following concurrency and making the
situation worse.

ext4_mb_regular_allocator
  ext4_lock_group(sb, group)
  ext4_mb_good_group
   // check if the group bbitmap is corrupted
  ext4_mb_complex_scan_group
   // Scan group gets ac_b_ex but doesn't use it
  ext4_unlock_group(sb, group)
                           ext4_mark_group_bitmap_corrupted(group)
                           // The block bitmap was corrupted during
                           // the group unlock gap.
  ext4_mb_try_best_found
    ext4_lock_group(ac->ac_sb, group)
    ext4_mb_use_best_found
      mb_mark_used
      // Allocating blocks in block bitmap corrupted group

Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240104142040.2835097-7-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 751e31df0f104..82afe275e6c88 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2299,6 +2299,9 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		return;
 
 	ext4_lock_group(ac->ac_sb, group);
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		goto out;
+
 	max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
 
 	if (max > 0) {
@@ -2306,6 +2309,7 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		ext4_mb_use_best_found(ac, e4b);
 	}
 
+out:
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
 }
-- 
GitLab


From 832698373a25950942c04a512daa652c18a9b513 Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 4 Jan 2024 22:20:39 +0800
Subject: [PATCH 2925/4076] ext4: avoid allocating blocks from corrupted group
 in ext4_mb_find_by_goal()

Places the logic for checking if the group's block bitmap is corrupt under
the protection of the group lock to avoid allocating blocks from the group
with a corrupted block bitmap.

Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240104142040.2835097-8-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 82afe275e6c88..2069d768c6198 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2336,12 +2336,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 	if (err)
 		return err;
 
-	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
-		ext4_mb_unload_buddy(e4b);
-		return 0;
-	}
-
 	ext4_lock_group(ac->ac_sb, group);
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		goto out;
+
 	max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
 			     ac->ac_g_ex.fe_len, &ex);
 	ex.fe_logical = 0xDEADFA11; /* debug value */
@@ -2374,6 +2372,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 		ac->ac_b_ex = ex;
 		ext4_mb_use_best_found(ac, e4b);
 	}
+out:
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
 
-- 
GitLab


From c5f3a3821de42ede9bcaeb892d1539717cf590cb Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 4 Jan 2024 22:20:40 +0800
Subject: [PATCH 2926/4076] ext4: mark the group block bitmap as corrupted
 before reporting an error

Otherwise unlocking the group in ext4_grp_locked_error may allow other
processes to modify the core block bitmap that is known to be corrupt.

Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240104142040.2835097-9-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 2069d768c6198..c7f63dd7afccb 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -564,14 +564,14 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
 
 			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 			blocknr += EXT4_C2B(EXT4_SB(sb), first + i);
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group,
 					      inode ? inode->i_ino : 0,
 					      blocknr,
 					      "freeing block already freed "
 					      "(bit %u)",
 					      first + i);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		}
 		mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
 	}
@@ -1933,12 +1933,12 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 		blocknr += EXT4_C2B(sbi, block);
+		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		ext4_grp_locked_error(sb, e4b->bd_group,
 				      inode ? inode->i_ino : 0, blocknr,
 				      "freeing already freed block (bit %u); block bitmap corrupt.",
 				      block);
-		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		return;
 	}
 
@@ -2406,12 +2406,12 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
 
 		k = mb_find_next_zero_bit(buddy, max, 0);
 		if (k >= max) {
+			ext4_mark_group_bitmap_corrupted(ac->ac_sb,
+					e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0,
 				"%d free clusters of order %d. But found 0",
 				grp->bb_counters[i], i);
-			ext4_mark_group_bitmap_corrupted(ac->ac_sb,
-					 e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 		ac->ac_found++;
@@ -2462,12 +2462,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 			 * free blocks even though group info says we
 			 * have free blocks
 			 */
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
 					"group info. But bitmap says 0",
 					free);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 
@@ -2493,12 +2493,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 		if (WARN_ON(ex.fe_len <= 0))
 			break;
 		if (free < ex.fe_len) {
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
 					"group info. But got %d blocks",
 					free, ex.fe_len);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			/*
 			 * The number of free blocks differs. This mostly
 			 * indicate that the bitmap is corrupt. So exit
-- 
GitLab


From 133de5a0d8f8e32b34feaa8beae7a189482f1856 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:20:54 +0800
Subject: [PATCH 2927/4076] ext4: remove unused return value of
 __mb_check_buddy

Remove unused return value of __mb_check_buddy.

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240105092102.496631-2-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c7f63dd7afccb..0d0917cf2e8fc 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -677,7 +677,7 @@ do {									\
 	}								\
 } while (0)
 
-static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
+static void __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 				const char *function, int line)
 {
 	struct super_block *sb = e4b->bd_sb;
@@ -696,7 +696,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 	void *buddy2;
 
 	if (e4b->bd_info->bb_check_counter++ % 10)
-		return 0;
+		return;
 
 	while (order > 1) {
 		buddy = mb_find_buddy(e4b, order, &max);
@@ -758,7 +758,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 
 	grp = ext4_get_group_info(sb, e4b->bd_group);
 	if (!grp)
-		return NULL;
+		return;
 	list_for_each(cur, &grp->bb_prealloc_list) {
 		ext4_group_t groupnr;
 		struct ext4_prealloc_space *pa;
@@ -768,7 +768,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 		for (i = 0; i < pa->pa_len; i++)
 			MB_CHECK_ASSERT(mb_test_bit(k + i, buddy));
 	}
-	return 0;
 }
 #undef MB_CHECK_ASSERT
 #define mb_check_buddy(e4b) __mb_check_buddy(e4b,	\
-- 
GitLab


From 438a35e72d09c01da7ffb49570ecd11ca632270b Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:20:55 +0800
Subject: [PATCH 2928/4076] ext4: remove unused parameter ngroup in
 ext4_mb_choose_next_group_*()

Remove unused parameter ngroup in ext4_mb_choose_next_group_*().

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Link: https://lore.kernel.org/r/20240105092102.496631-3-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 0d0917cf2e8fc..9c867a13bf8db 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -870,7 +870,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
  * cr level needs an update.
  */
 static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context *ac,
-			enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+			enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *iter;
@@ -944,7 +944,7 @@ ext4_mb_find_good_group_avg_frag_lists(struct ext4_allocation_context *ac, int o
  * order. Updates *new_cr if cr level needs an update.
  */
 static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *ac,
-		enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+		enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *grp = NULL;
@@ -989,7 +989,7 @@ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *
  * much and fall to CR_GOAL_LEN_SLOW in that case.
  */
 static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context *ac,
-		enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+		enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *grp = NULL;
@@ -1124,11 +1124,11 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
 	}
 
 	if (*new_cr == CR_POWER2_ALIGNED) {
-		ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group);
 	} else if (*new_cr == CR_GOAL_LEN_FAST) {
-		ext4_mb_choose_next_group_goal_fast(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_goal_fast(ac, new_cr, group);
 	} else if (*new_cr == CR_BEST_AVAIL_LEN) {
-		ext4_mb_choose_next_group_best_avail(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_best_avail(ac, new_cr, group);
 	} else {
 		/*
 		 * TODO: For CR=2, we can arrange groups in an rb tree sorted by
-- 
GitLab


From 11fd1a5d642355a45f4008d308399c26a8b3d3f0 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:20:56 +0800
Subject: [PATCH 2929/4076] ext4: remove unneeded return value of
 ext4_mb_release_context

Function ext4_mb_release_context always return 0 and the return value is
never used. Just remove unneeded return value of ext4_mb_release_context.

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240105092102.496631-4-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 9c867a13bf8db..dfd2de7aa0cfc 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -5968,7 +5968,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 /*
  * release all resource we used in allocation
  */
-static int ext4_mb_release_context(struct ext4_allocation_context *ac)
+static void ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_prealloc_space *pa = ac->ac_pa;
@@ -6005,7 +6005,6 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
-	return 0;
 }
 
 static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
-- 
GitLab


From 97c32dbffce12136c06d9ceb6919850233d3a1c2 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:20:57 +0800
Subject: [PATCH 2930/4076] ext4: remove unused
 ext4_allocation_context::ac_groups_considered

Remove unused ext4_allocation_context::ac_groups_considered

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240105092102.496631-5-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index d7aeb5da7d867..56938532b4ce2 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -192,7 +192,6 @@ struct ext4_allocation_context {
 	 */
 	ext4_grpblk_t	ac_orig_goal_len;
 
-	__u32 ac_groups_considered;
 	__u32 ac_flags;		/* allocation hints */
 	__u16 ac_groups_scanned;
 	__u16 ac_groups_linear_remaining;
-- 
GitLab


From 908177175a2ac7280cac738f33ccbbbcff035c5c Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:20:58 +0800
Subject: [PATCH 2931/4076] ext4: remove unused return value of ext4_mb_release

Remove unused return value of ext4_mb_release.

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240105092102.496631-6-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h    | 2 +-
 fs/ext4/mballoc.c | 4 +---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a5d784872303d..cabce11778fc1 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2912,7 +2912,7 @@ extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
 extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
 extern int ext4_mb_init(struct super_block *);
-extern int ext4_mb_release(struct super_block *);
+extern void ext4_mb_release(struct super_block *);
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
 extern void ext4_discard_preallocations(struct inode *, unsigned int);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index dfd2de7aa0cfc..26b199d2c3300 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3750,7 +3750,7 @@ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp)
 	return count;
 }
 
-int ext4_mb_release(struct super_block *sb)
+void ext4_mb_release(struct super_block *sb)
 {
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
@@ -3826,8 +3826,6 @@ int ext4_mb_release(struct super_block *sb)
 	}
 
 	free_percpu(sbi->s_locality_groups);
-
-	return 0;
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
-- 
GitLab


From 820c280896eaf715b39ac1ad38976bcc749082b7 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:20:59 +0800
Subject: [PATCH 2932/4076] ext4: remove unused return value of
 ext4_mb_release_inode_pa

Remove unused return value of ext4_mb_release_inode_pa

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240105092102.496631-7-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 26b199d2c3300..3349723ff93fb 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -5307,7 +5307,7 @@ static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac)
  * the caller MUST hold group/inode locks.
  * TODO: optimize the case when there are no in-core structures yet
  */
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 			struct ext4_prealloc_space *pa)
 {
@@ -5357,8 +5357,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 		 */
 	}
 	atomic_add(free, &sbi->s_mb_discarded);
-
-	return 0;
 }
 
 static noinline_for_stack int
-- 
GitLab


From 20427949b9b584422c05bb31e48b1b68615dd794 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:21:00 +0800
Subject: [PATCH 2933/4076] ext4: remove unused return value of
 ext4_mb_release_group_pa

Remove unused return value of ext4_mb_release_group_pa.

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240105092102.496631-8-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 3349723ff93fb..a8e61bb181fa4 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -5359,7 +5359,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 	atomic_add(free, &sbi->s_mb_discarded);
 }
 
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 				struct ext4_prealloc_space *pa)
 {
@@ -5373,13 +5373,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) {
 		ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu",
 			     e4b->bd_group, group, pa->pa_pstart);
-		return 0;
+		return;
 	}
 	mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
 	atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
 	trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
-
-	return 0;
 }
 
 /*
-- 
GitLab


From 2ffd2a6ad1d3a8213bb5805f45f49098fe615db1 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:21:01 +0800
Subject: [PATCH 2934/4076] ext4: remove unnecessary parameter "needed" in
 ext4_discard_preallocations

The "needed" controls the number of ext4_prealloc_space to discard in
ext4_discard_preallocations. Function ext4_discard_preallocations is
supposed to discard all non-used preallocated blocks when "needed"
is 0 and now ext4_discard_preallocations is always called with "needed"
= 0. Remove unnecessary parameter "needed" and remove all non-used
preallocated spaces in ext4_discard_preallocations to simplify the
code.

Note: If count of non-used preallocated spaces could be more than
UINT_MAX, there was a memory leak as some non-used preallocated
spaces are left ununsed and this commit will fix it. Otherwise,
there is no behavior change.

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240105092102.496631-9-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h        |  2 +-
 fs/ext4/extents.c     | 10 +++++-----
 fs/ext4/file.c        |  2 +-
 fs/ext4/indirect.c    |  2 +-
 fs/ext4/inode.c       |  6 +++---
 fs/ext4/ioctl.c       |  2 +-
 fs/ext4/mballoc.c     | 10 +++-------
 fs/ext4/move_extent.c |  4 ++--
 fs/ext4/super.c       |  2 +-
 9 files changed, 18 insertions(+), 22 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index cabce11778fc1..786b6857ab474 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2915,7 +2915,7 @@ extern int ext4_mb_init(struct super_block *);
 extern void ext4_mb_release(struct super_block *);
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
-extern void ext4_discard_preallocations(struct inode *, unsigned int);
+extern void ext4_discard_preallocations(struct inode *);
 extern int __init ext4_init_mballoc(void);
 extern void ext4_exit_mballoc(void);
 extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 01299b55a567a..9106715254ac0 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
 	 * i_rwsem. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
@@ -4313,7 +4313,7 @@ got_allocated_blocks:
 			 * not a good idea to call discard here directly,
 			 * but otherwise we'd need to call it every free().
 			 */
-			ext4_discard_preallocations(inode, 0);
+			ext4_discard_preallocations(inode);
 			if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
 				fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE;
 			ext4_free_blocks(handle, inode, NULL, newblock,
@@ -5357,7 +5357,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 	ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start);
 
 	ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
@@ -5365,7 +5365,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 		up_write(&EXT4_I(inode)->i_data_sem);
 		goto out_stop;
 	}
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	ret = ext4_ext_shift_extents(inode, handle, punch_stop,
 				     punch_stop - punch_start, SHIFT_LEFT);
@@ -5497,7 +5497,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
 		goto out_stop;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	path = ext4_find_extent(inode, offset_lblk, NULL, 0);
 	if (IS_ERR(path)) {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6aa15dafc6778..54d6ff22585cf 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -174,7 +174,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 			(atomic_read(&inode->i_writecount) == 1) &&
 			!EXT4_I(inode)->i_reserved_data_blocks) {
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	if (is_dx(inode) && filp->private_data)
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index a9f3716119d37..d8ca7f64f9523 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -714,7 +714,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
 	 * i_rwsem. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5af1b0b8680e9..4cae8698f70cf 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -371,7 +371,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 	 */
 	if ((ei->i_reserved_data_blocks == 0) &&
 	    !inode_is_open_for_write(inode))
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 }
 
 static int __check_block_validity(struct inode *inode, const char *func,
@@ -4017,7 +4017,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 	if (stop_block > first_block) {
 
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 
 		ext4_es_remove_extent(inode, first_block,
 				      stop_block - first_block);
@@ -4170,7 +4170,7 @@ int ext4_truncate(struct inode *inode)
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		err = ext4_ext_truncate(handle, inode);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index aa6be510eb8f5..7160a71044c88 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -467,7 +467,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_reset_inode_seed(inode);
 	ext4_reset_inode_seed(inode_bl);
 
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err < 0) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a8e61bb181fa4..f3da7db2beee5 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -5498,7 +5498,7 @@ out_dbg:
  *
  * FIXME!! Make sure it is valid at all the call sites
  */
-void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
+void ext4_discard_preallocations(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -5520,15 +5520,12 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
 	trace_ext4_discard_preallocations(inode,
-			atomic_read(&ei->i_prealloc_active), needed);
-
-	if (needed == 0)
-		needed = UINT_MAX;
+			atomic_read(&ei->i_prealloc_active), 0);
 
 repeat:
 	/* first, collect all pa's in the inode */
 	write_lock(&ei->i_prealloc_lock);
-	for (iter = rb_first(&ei->i_prealloc_node); iter && needed;
+	for (iter = rb_first(&ei->i_prealloc_node); iter;
 	     iter = rb_next(iter)) {
 		pa = rb_entry(iter, struct ext4_prealloc_space,
 			      pa_node.inode_node);
@@ -5552,7 +5549,6 @@ repeat:
 			spin_unlock(&pa->pa_lock);
 			rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node);
 			list_add(&pa->u.pa_tmp_list, &list);
-			needed--;
 			continue;
 		}
 
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 391efa6d4c56f..7cd4afa4de1d3 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -686,8 +686,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 
 out:
 	if (*moved_len) {
-		ext4_discard_preallocations(orig_inode, 0);
-		ext4_discard_preallocations(donor_inode, 0);
+		ext4_discard_preallocations(orig_inode);
+		ext4_discard_preallocations(donor_inode);
 	}
 
 	ext4_free_ext_path(path);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dcba0f85dfe24..0f931d0c227da 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1525,7 +1525,7 @@ void ext4_clear_inode(struct inode *inode)
 	ext4_fc_del(inode);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
-- 
GitLab


From f0e54b6087de9571ec61c189d6c378b81edbe3b2 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Fri, 5 Jan 2024 17:21:02 +0800
Subject: [PATCH 2935/4076] ext4: remove 'needed' in
 trace_ext4_discard_preallocations

As 'needed' to trace_ext4_discard_preallocations is always 0 which
is meaningless. Just remove it.

Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240105092102.496631-10-shikemeng@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c           |  5 ++---
 include/trace/events/ext4.h | 11 ++++-------
 2 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f3da7db2beee5..e4f7cf9d89c45 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -5510,9 +5510,8 @@ void ext4_discard_preallocations(struct inode *inode)
 	struct rb_node *iter;
 	int err;
 
-	if (!S_ISREG(inode->i_mode)) {
+	if (!S_ISREG(inode->i_mode))
 		return;
-	}
 
 	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
@@ -5520,7 +5519,7 @@ void ext4_discard_preallocations(struct inode *inode)
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
 	trace_ext4_discard_preallocations(inode,
-			atomic_read(&ei->i_prealloc_active), 0);
+			atomic_read(&ei->i_prealloc_active));
 
 repeat:
 	/* first, collect all pa's in the inode */
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 65029dfb92fbc..a697f4b77162d 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -772,15 +772,14 @@ TRACE_EVENT(ext4_mb_release_group_pa,
 );
 
 TRACE_EVENT(ext4_discard_preallocations,
-	TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed),
+	TP_PROTO(struct inode *inode, unsigned int len),
 
-	TP_ARGS(inode, len, needed),
+	TP_ARGS(inode, len),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
 		__field(	ino_t,		ino		)
 		__field(	unsigned int,	len		)
-		__field(	unsigned int,	needed		)
 
 	),
 
@@ -788,13 +787,11 @@ TRACE_EVENT(ext4_discard_preallocations,
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->len	= len;
-		__entry->needed	= needed;
 	),
 
-	TP_printk("dev %d,%d ino %lu len: %u needed %u",
+	TP_printk("dev %d,%d ino %lu len: %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino, __entry->len,
-		  __entry->needed)
+		  (unsigned long) __entry->ino, __entry->len)
 );
 
 TRACE_EVENT(ext4_mb_discard_preallocations,
-- 
GitLab


From 6d6eeabcfaba2fcadf5443b575789ea606f9de83 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Wed, 17 Jan 2024 16:04:16 +0100
Subject: [PATCH 2936/4076] mlxsw: spectrum_acl_erp: Fix error flow of pool
 allocation failure

Lately, a bug was found when many TC filters are added - at some point,
several bugs are printed to dmesg [1] and the switch is crashed with
segmentation fault.

The issue starts when gen_pool_free() fails because of unexpected
behavior - a try to free memory which is already freed, this leads to BUG()
call which crashes the switch and makes many other bugs.

Trying to track down the unexpected behavior led to a bug in eRP code. The
function mlxsw_sp_acl_erp_table_alloc() gets a pointer to the allocated
index, sets the value and returns an error code. When gen_pool_alloc()
fails it returns address 0, we track it and return -ENOBUFS outside, BUT
the call for gen_pool_alloc() already override the index in erp_table
structure. This is a problem when such allocation is done as part of
table expansion. This is not a new table, which will not be used in case
of allocation failure. We try to expand eRP table and override the
current index (non-zero) with zero. Then, it leads to an unexpected
behavior when address 0 is freed twice. Note that address 0 is valid in
erp_table->base_index and indeed other tables use it.

gen_pool_alloc() fails in case that there is no space left in the
pre-allocated pool, in our case, the pool is limited to
ACL_MAX_ERPT_BANK_SIZE, which is read from hardware. When more than max
erp entries are required, we exceed the limit and return an error, this
error leads to "Failed to migrate vregion" print.

Fix this by changing erp_table->base_index only in case of a successful
allocation.

Add a test case for such a scenario. Without this fix it causes
segmentation fault:

$ TESTS="max_erp_entries_test" ./tc_flower.sh
./tc_flower.sh: line 988:  1560 Segmentation fault      tc filter del dev $h2 ingress chain $i protocol ip pref $i handle $j flower &>/dev/null

[1]:
kernel BUG at lib/genalloc.c:508!
invalid opcode: 0000 [#1] PREEMPT SMP
CPU: 6 PID: 3531 Comm: tc Not tainted 6.7.0-rc5-custom-ga6893f479f5e #1
Hardware name: Mellanox Technologies Ltd. MSN4700/VMOD0010, BIOS 5.11 07/12/2021
RIP: 0010:gen_pool_free_owner+0xc9/0xe0
...
Call Trace:
 <TASK>
 __mlxsw_sp_acl_erp_table_other_dec+0x70/0xa0 [mlxsw_spectrum]
 mlxsw_sp_acl_erp_mask_destroy+0xf5/0x110 [mlxsw_spectrum]
 objagg_obj_root_destroy+0x18/0x80 [objagg]
 objagg_obj_destroy+0x12c/0x130 [objagg]
 mlxsw_sp_acl_erp_mask_put+0x37/0x50 [mlxsw_spectrum]
 mlxsw_sp_acl_ctcam_region_entry_remove+0x74/0xa0 [mlxsw_spectrum]
 mlxsw_sp_acl_ctcam_entry_del+0x1e/0x40 [mlxsw_spectrum]
 mlxsw_sp_acl_tcam_ventry_del+0x78/0xd0 [mlxsw_spectrum]
 mlxsw_sp_flower_destroy+0x4d/0x70 [mlxsw_spectrum]
 mlxsw_sp_flow_block_cb+0x73/0xb0 [mlxsw_spectrum]
 tc_setup_cb_destroy+0xc1/0x180
 fl_hw_destroy_filter+0x94/0xc0 [cls_flower]
 __fl_delete+0x1ac/0x1c0 [cls_flower]
 fl_destroy+0xc2/0x150 [cls_flower]
 tcf_proto_destroy+0x1a/0xa0
...
mlxsw_spectrum3 0000:07:00.0: Failed to migrate vregion
mlxsw_spectrum3 0000:07:00.0: Failed to migrate vregion

Fixes: f465261aa105 ("mlxsw: spectrum_acl: Implement common eRP core")
Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/4cfca254dfc0e5d283974801a24371c7b6db5989.1705502064.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlxsw/spectrum_acl_erp.c         |  8 +--
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh | 52 ++++++++++++++++++-
 2 files changed, 56 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 4c98950380d53..d231f4d2888be 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -301,6 +301,7 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
 			     unsigned long *p_index)
 {
 	unsigned int num_rows, entry_size;
+	unsigned long index;
 
 	/* We only allow allocations of entire rows */
 	if (num_erps % erp_core->num_erp_banks != 0)
@@ -309,10 +310,11 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
 	entry_size = erp_core->erpt_entries_size[region_type];
 	num_rows = num_erps / erp_core->num_erp_banks;
 
-	*p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
-	if (*p_index == 0)
+	index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
+	if (!index)
 		return -ENOBUFS;
-	*p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
+
+	*p_index = index - MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
 
 	return 0;
 }
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index fb850e0ec8375..7bf56ea161e35 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -10,7 +10,8 @@ lib_dir=$(dirname $0)/../../../../net/forwarding
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
 	delta_two_masks_one_key_test delta_simple_rehash_test \
-	bloom_simple_test bloom_complex_test bloom_delta_test"
+	bloom_simple_test bloom_complex_test bloom_delta_test \
+	max_erp_entries_test"
 NUM_NETIFS=2
 source $lib_dir/lib.sh
 source $lib_dir/tc_common.sh
@@ -983,6 +984,55 @@ bloom_delta_test()
 	log_test "bloom delta test ($tcflags)"
 }
 
+max_erp_entries_test()
+{
+	# The number of eRP entries is limited. Once the maximum number of eRPs
+	# has been reached, filters cannot be added. This test verifies that
+	# when this limit is reached, inserstion fails without crashing.
+
+	RET=0
+
+	local num_masks=32
+	local num_regions=15
+	local chain_failed
+	local mask_failed
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	for ((i=1; i < $num_regions; i++)); do
+		for ((j=$num_masks; j >= 0; j--)); do
+			tc filter add dev $h2 ingress chain $i protocol ip \
+				pref $i	handle $j flower $tcflags \
+				dst_ip 192.1.0.0/$j &> /dev/null
+			ret=$?
+
+			if [ $ret -ne 0 ]; then
+				chain_failed=$i
+				mask_failed=$j
+				break 2
+			fi
+		done
+	done
+
+	# We expect to exceed the maximum number of eRP entries, so that
+	# insertion eventually fails. Otherwise, the test should be adjusted to
+	# add more filters.
+	check_fail $ret "expected to exceed number of eRP entries"
+
+	for ((; i >= 1; i--)); do
+		for ((j=0; j <= $num_masks; j++)); do
+			tc filter del dev $h2 ingress chain $i protocol ip \
+				pref $i handle $j flower &> /dev/null
+		done
+	done
+
+	log_test "max eRP entries test ($tcflags). " \
+		"max chain $chain_failed, mask $mask_failed"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
GitLab


From efeb7dfea8ee10cdec11b6b6ba4e405edbe75809 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 17 Jan 2024 16:04:17 +0100
Subject: [PATCH 2937/4076] mlxsw: spectrum_acl_tcam: Fix NULL pointer
 dereference in error path

When calling mlxsw_sp_acl_tcam_region_destroy() from an error path after
failing to attach the region to an ACL group, we hit a NULL pointer
dereference upon 'region->group->tcam' [1].

Fix by retrieving the 'tcam' pointer using mlxsw_sp_acl_to_tcam().

[1]
BUG: kernel NULL pointer dereference, address: 0000000000000000
[...]
RIP: 0010:mlxsw_sp_acl_tcam_region_destroy+0xa0/0xd0
[...]
Call Trace:
 mlxsw_sp_acl_tcam_vchunk_get+0x88b/0xa20
 mlxsw_sp_acl_tcam_ventry_add+0x25/0xe0
 mlxsw_sp_acl_rule_add+0x47/0x240
 mlxsw_sp_flower_replace+0x1a9/0x1d0
 tc_setup_cb_add+0xdc/0x1c0
 fl_hw_replace_filter+0x146/0x1f0
 fl_change+0xc17/0x1360
 tc_new_tfilter+0x472/0xb90
 rtnetlink_rcv_msg+0x313/0x3b0
 netlink_rcv_skb+0x58/0x100
 netlink_unicast+0x244/0x390
 netlink_sendmsg+0x1e4/0x440
 ____sys_sendmsg+0x164/0x260
 ___sys_sendmsg+0x9a/0xe0
 __sys_sendmsg+0x7a/0xc0
 do_syscall_64+0x40/0xe0
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Fixes: 22a677661f56 ("mlxsw: spectrum: Introduce ACL core with simple TCAM implementation")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/fb6a4542bbc9fcab5a523802d97059bffbca7126.1705502064.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index d50786b0a6ce4..7d1e91196e943 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -681,13 +681,13 @@ static void
 mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_tcam_region *region)
 {
+	struct mlxsw_sp_acl_tcam *tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl);
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
 	ops->region_fini(mlxsw_sp, region->priv);
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
-	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam,
-					region->id);
+	mlxsw_sp_acl_tcam_region_id_put(tcam, region->id);
 	kfree(region);
 }
 
-- 
GitLab


From 483ae90d8f976f8339cf81066312e1329f2d3706 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 17 Jan 2024 16:04:18 +0100
Subject: [PATCH 2938/4076] mlxsw: spectrum_acl_tcam: Fix stack corruption

When tc filters are first added to a net device, the corresponding local
port gets bound to an ACL group in the device. The group contains a list
of ACLs. In turn, each ACL points to a different TCAM region where the
filters are stored. During forwarding, the ACLs are sequentially
evaluated until a match is found.

One reason to place filters in different regions is when they are added
with decreasing priorities and in an alternating order so that two
consecutive filters can never fit in the same region because of their
key usage.

In Spectrum-2 and newer ASICs the firmware started to report that the
maximum number of ACLs in a group is more than 16, but the layout of the
register that configures ACL groups (PAGT) was not updated to account
for that. It is therefore possible to hit stack corruption [1] in the
rare case where more than 16 ACLs in a group are required.

Fix by limiting the maximum ACL group size to the minimum between what
the firmware reports and the maximum ACLs that fit in the PAGT register.

Add a test case to make sure the machine does not crash when this
condition is hit.

[1]
Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: mlxsw_sp_acl_tcam_group_update+0x116/0x120
[...]
 dump_stack_lvl+0x36/0x50
 panic+0x305/0x330
 __stack_chk_fail+0x15/0x20
 mlxsw_sp_acl_tcam_group_update+0x116/0x120
 mlxsw_sp_acl_tcam_group_region_attach+0x69/0x110
 mlxsw_sp_acl_tcam_vchunk_get+0x492/0xa20
 mlxsw_sp_acl_tcam_ventry_add+0x25/0xe0
 mlxsw_sp_acl_rule_add+0x47/0x240
 mlxsw_sp_flower_replace+0x1a9/0x1d0
 tc_setup_cb_add+0xdc/0x1c0
 fl_hw_replace_filter+0x146/0x1f0
 fl_change+0xc17/0x1360
 tc_new_tfilter+0x472/0xb90
 rtnetlink_rcv_msg+0x313/0x3b0
 netlink_rcv_skb+0x58/0x100
 netlink_unicast+0x244/0x390
 netlink_sendmsg+0x1e4/0x440
 ____sys_sendmsg+0x164/0x260
 ___sys_sendmsg+0x9a/0xe0
 __sys_sendmsg+0x7a/0xc0
 do_syscall_64+0x40/0xe0
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Reported-by: Orel Hagag <orelh@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/2d91c89afba59c22587b444994ae419dbea8d876.1705502064.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlxsw/spectrum_acl_tcam.c        |  2 +
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh | 56 ++++++++++++++++++-
 2 files changed, 57 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 7d1e91196e943..50ea1eff02b2f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -1564,6 +1564,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 	tcam->max_groups = max_groups;
 	tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						  ACL_MAX_GROUP_SIZE);
+	tcam->max_group_size = min_t(unsigned int, tcam->max_group_size,
+				     MLXSW_REG_PAGT_ACL_MAX_NUM);
 
 	err = ops->init(mlxsw_sp, tcam->priv, tcam);
 	if (err)
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index 7bf56ea161e35..616d3581419ca 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -11,7 +11,7 @@ ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
 	delta_two_masks_one_key_test delta_simple_rehash_test \
 	bloom_simple_test bloom_complex_test bloom_delta_test \
-	max_erp_entries_test"
+	max_erp_entries_test max_group_size_test"
 NUM_NETIFS=2
 source $lib_dir/lib.sh
 source $lib_dir/tc_common.sh
@@ -1033,6 +1033,60 @@ max_erp_entries_test()
 		"max chain $chain_failed, mask $mask_failed"
 }
 
+max_group_size_test()
+{
+	# The number of ACLs in an ACL group is limited. Once the maximum
+	# number of ACLs has been reached, filters cannot be added. This test
+	# verifies that when this limit is reached, insertion fails without
+	# crashing.
+
+	RET=0
+
+	local num_acls=32
+	local max_size
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	for ((i=1; i < $num_acls; i++)); do
+		if [[ $(( i % 2 )) == 1 ]]; then
+			tc filter add dev $h2 ingress pref $i proto ipv4 \
+				flower $tcflags dst_ip 198.51.100.1/32 \
+				ip_proto tcp tcp_flags 0x01/0x01 \
+				action drop &> /dev/null
+		else
+			tc filter add dev $h2 ingress pref $i proto ipv6 \
+				flower $tcflags dst_ip 2001:db8:1::1/128 \
+				action drop &> /dev/null
+		fi
+
+		ret=$?
+		[[ $ret -ne 0 ]] && max_size=$((i - 1)) && break
+	done
+
+	# We expect to exceed the maximum number of ACLs in a group, so that
+	# insertion eventually fails. Otherwise, the test should be adjusted to
+	# add more filters.
+	check_fail $ret "expected to exceed number of ACLs in a group"
+
+	for ((; i >= 1; i--)); do
+		if [[ $(( i % 2 )) == 1 ]]; then
+			tc filter del dev $h2 ingress pref $i proto ipv4 \
+				flower $tcflags dst_ip 198.51.100.1/32 \
+				ip_proto tcp tcp_flags 0x01/0x01 \
+				action drop &> /dev/null
+		else
+			tc filter del dev $h2 ingress pref $i proto ipv6 \
+				flower $tcflags dst_ip 2001:db8:1::1/128 \
+				action drop &> /dev/null
+		fi
+	done
+
+	log_test "max ACL group size test ($tcflags). max size $max_size"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
GitLab


From 62bef63646c194e0f82b40304a0f2d060b28687b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 17 Jan 2024 16:04:19 +0100
Subject: [PATCH 2939/4076] mlxsw: spectrum_router: Register netdevice notifier
 before nexthop

If there are IPIP nexthops at the time when the driver is loaded (or the
devlink instance reloaded), the driver looks up the corresponding IPIP
entry. But IPIP entries are only created as a result of netdevice
notifications. Since the netdevice notifier is registered after the nexthop
notifier, mlxsw_sp_nexthop_type_init() never finds the IPIP entry,
registers the nexthop MLXSW_SP_NEXTHOP_TYPE_ETH, and fails to assign a CRIF
to the nexthop. Later on when the CRIF is necessary, the WARN_ON in
mlxsw_sp_nexthop_rif() triggers, causing the splat [1].

In order to fix the issue, reorder the netdevice notifier to be registered
before the nexthop one.

[1] (edited for clarity):

    WARNING: CPU: 1 PID: 1364 at drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3245 mlxsw_sp_nexthop_rif (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3246 (discriminator 1)) mlxsw_spectrum
    Hardware name: Mellanox Technologies Ltd. MSN4410/VMOD0010, BIOS 5.11 01/06/2019
    Call Trace:
    ? mlxsw_sp_nexthop_rif (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3246 (discriminator 1)) mlxsw_spectrum
    __mlxsw_sp_nexthop_eth_update (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3637) mlxsw_spectrum
    mlxsw_sp_nexthop_update (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3679 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3727) mlxsw_spectrum
    mlxsw_sp_nexthop_group_update (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3757) mlxsw_spectrum
    mlxsw_sp_nexthop_group_refresh (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:4112) mlxsw_spectrum
    mlxsw_sp_nexthop_obj_event (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5118 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5191 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5315 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5500) mlxsw_spectrum
    nexthops_dump (net/ipv4/nexthop.c:217 net/ipv4/nexthop.c:440 net/ipv4/nexthop.c:3609)
    register_nexthop_notifier (net/ipv4/nexthop.c:3624)
    mlxsw_sp_router_init (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:11486) mlxsw_spectrum
    mlxsw_sp_init (drivers/net/ethernet/mellanox/mlxsw/spectrum.c:3267) mlxsw_spectrum
    __mlxsw_core_bus_device_register (drivers/net/ethernet/mellanox/mlxsw/core.c:2202) mlxsw_core
    mlxsw_devlink_core_bus_device_reload_up (drivers/net/ethernet/mellanox/mlxsw/core.c:2265 drivers/net/ethernet/mellanox/mlxsw/core.c:1603) mlxsw_core
    devlink_reload (net/devlink/dev.c:314 net/devlink/dev.c:475)
    [...]

Fixes: 9464a3d68ea9 ("mlxsw: spectrum_router: Track next hops at CRIFs")
Reported-by: Maksym Yaremchuk <maksymy@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/74edb8d45d004e8d8f5318eede6ccc3d786d8ba9.1705502064.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 24 +++++++++----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 2c255ed9b8a94..7164f9e6370fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -11472,6 +11472,13 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_register_netevent_notifier;
 
+	mlxsw_sp->router->netdevice_nb.notifier_call =
+		mlxsw_sp_router_netdevice_event;
+	err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					      &mlxsw_sp->router->netdevice_nb);
+	if (err)
+		goto err_register_netdev_notifier;
+
 	mlxsw_sp->router->nexthop_nb.notifier_call =
 		mlxsw_sp_nexthop_obj_event;
 	err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
@@ -11487,22 +11494,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_register_fib_notifier;
 
-	mlxsw_sp->router->netdevice_nb.notifier_call =
-		mlxsw_sp_router_netdevice_event;
-	err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
-					      &mlxsw_sp->router->netdevice_nb);
-	if (err)
-		goto err_register_netdev_notifier;
-
 	return 0;
 
-err_register_netdev_notifier:
-	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp),
-				&mlxsw_sp->router->fib_nb);
 err_register_fib_notifier:
 	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
 				    &mlxsw_sp->router->nexthop_nb);
 err_register_nexthop_notifier:
+	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					  &router->netdevice_nb);
+err_register_netdev_notifier:
 	unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);
 err_register_netevent_notifier:
 	unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb);
@@ -11550,11 +11550,11 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_router *router = mlxsw_sp->router;
 
-	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
-					  &router->netdevice_nb);
 	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &router->fib_nb);
 	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
 				    &router->nexthop_nb);
+	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					  &router->netdevice_nb);
 	unregister_netevent_notifier(&router->netevent_nb);
 	unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb);
 	unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb);
-- 
GitLab


From 40cc674bafd50fc728c4a73d7dc77728a0b86759 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Wed, 17 Jan 2024 16:04:20 +0100
Subject: [PATCH 2940/4076] selftests: mlxsw: qos_pfc: Remove wrong description

In the diagram of the topology, $swp3 and $swp4 are described as 1Gbps
ports. This is wrong information, the test does not configure such speed.

Cc: Shuah Khan <shuah@kernel.org>
Fixes: bfa804784e32 ("selftests: mlxsw: Add a PFC test")
Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/0087e2d416aff7e444d15f7c2958fc1d438dc27e.1705502064.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
index 42ce602d8d492..49bef76083b83 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
@@ -40,7 +40,6 @@
 # |   + $swp1          $swp3 +                    + $swp4                     |
 # |   | iPOOL1        iPOOL0 |                    | iPOOL2                    |
 # |   | ePOOL4        ePOOL5 |                    | ePOOL4                    |
-# |   |                1Gbps |                    | 1Gbps                     |
 # |   |        PFC:enabled=1 |                    | PFC:enabled=1             |
 # | +-|----------------------|-+                +-|------------------------+  |
 # | | + $swp1.111  $swp3.111 + |                | + $swp4.111              |  |
-- 
GitLab


From b34f4de6d30cbaa8fed905a5080b6eace8c84dc7 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Wed, 17 Jan 2024 16:04:21 +0100
Subject: [PATCH 2941/4076] selftests: mlxsw: qos_pfc: Adjust the test to
 support 8 lanes

'qos_pfc' test checks PFC behavior. The idea is to limit the traffic
using a shaper somewhere in the flow of the packets. In this area, the
buffer is smaller than the buffer at the beginning of the flow, so it fills
up until there is no more space left. The test configures there PFC
which is supposed to notice that the headroom is filling up and send PFC
Xoff to indicate the transmitter to stop sending traffic for the priorities
sharing this PG.

The Xon/Xoff threshold is auto-configured and always equal to
2*(MTU rounded up to cell size). Even after sending the PFC Xoff packet,
traffic will keep arriving until the transmitter receives and processes
the PFC packet. This amount of traffic is known as the PFC delay allowance.

Currently the buffer for the delay traffic is configured as 100KB. The
MTU in the test is 10KB, therefore the threshold for Xoff is about 20KB.
This allows 80KB extra to be stored in this buffer.

8-lane ports use two buffers among which the configured buffer is split,
the Xoff threshold then applies to each buffer in parallel.

The test does not take into account the behavior of 8-lane ports, when the
ports are configured to 400Gbps with 8 lanes or 800Gbps with 8 lanes,
packets are dropped and the test fails.

Check if the relevant ports use 8 lanes, in such case double the size of
the buffer, as the headroom is split half-half.

Cc: Shuah Khan <shuah@kernel.org>
Fixes: bfa804784e32 ("selftests: mlxsw: Add a PFC test")
Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/23ff11b7dff031eb04a41c0f5254a2b636cd8ebb.1705502064.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/mlxsw/qos_pfc.sh     | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
index 49bef76083b83..0f0f4f05807c9 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
@@ -119,6 +119,9 @@ h2_destroy()
 
 switch_create()
 {
+	local lanes_swp4
+	local pg1_size
+
 	# pools
 	# -----
 
@@ -228,7 +231,20 @@ switch_create()
 	dcb pfc set dev $swp4 prio-pfc all:off 1:on
 	# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
 	# is (-2*MTU) about 80K of delay provision.
-	dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB
+	pg1_size=$_100KB
+
+	setup_wait_dev_with_timeout $swp4
+
+	lanes_swp4=$(ethtool $swp4 | grep 'Lanes:')
+	lanes_swp4=${lanes_swp4#*"Lanes: "}
+
+	# 8-lane ports use two buffers among which the configured buffer
+	# is split, so double the size to get twice (20K + 80K).
+	if [[ $lanes_swp4 -eq 8 ]]; then
+		pg1_size=$((pg1_size * 2))
+	fi
+
+	dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size
 
 	# bridges
 	# -------
-- 
GitLab


From 2e7ef287f07c74985f1bf2858bedc62bd9ebf155 Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Wed, 17 Jan 2024 09:21:02 -0800
Subject: [PATCH 2942/4076] ipv6: mcast: fix data-race in ipv6_mc_down /
 mld_ifc_work

idev->mc_ifc_count can be written over without proper locking.

Originally found by syzbot [1], fix this issue by encapsulating calls
to mld_ifc_stop_work() (and mld_gq_stop_work() for good measure) with
mutex_lock() and mutex_unlock() accordingly as these functions
should only be called with mc_lock per their declarations.

[1]
BUG: KCSAN: data-race in ipv6_mc_down / mld_ifc_work

write to 0xffff88813a80c832 of 1 bytes by task 3771 on cpu 0:
 mld_ifc_stop_work net/ipv6/mcast.c:1080 [inline]
 ipv6_mc_down+0x10a/0x280 net/ipv6/mcast.c:2725
 addrconf_ifdown+0xe32/0xf10 net/ipv6/addrconf.c:3949
 addrconf_notify+0x310/0x980
 notifier_call_chain kernel/notifier.c:93 [inline]
 raw_notifier_call_chain+0x6b/0x1c0 kernel/notifier.c:461
 __dev_notify_flags+0x205/0x3d0
 dev_change_flags+0xab/0xd0 net/core/dev.c:8685
 do_setlink+0x9f6/0x2430 net/core/rtnetlink.c:2916
 rtnl_group_changelink net/core/rtnetlink.c:3458 [inline]
 __rtnl_newlink net/core/rtnetlink.c:3717 [inline]
 rtnl_newlink+0xbb3/0x1670 net/core/rtnetlink.c:3754
 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6558
 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2545
 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6576
 netlink_unicast_kernel net/netlink/af_netlink.c:1342 [inline]
 netlink_unicast+0x589/0x650 net/netlink/af_netlink.c:1368
 netlink_sendmsg+0x66e/0x770 net/netlink/af_netlink.c:1910
 ...

write to 0xffff88813a80c832 of 1 bytes by task 22 on cpu 1:
 mld_ifc_work+0x54c/0x7b0 net/ipv6/mcast.c:2653
 process_one_work kernel/workqueue.c:2627 [inline]
 process_scheduled_works+0x5b8/0xa30 kernel/workqueue.c:2700
 worker_thread+0x525/0x730 kernel/workqueue.c:2781
 ...

Fixes: 2d9a93b4902b ("mld: convert from timer to delayed work")
Reported-by: syzbot+a9400cabb1d784e49abf@syzkaller.appspotmail.com
Link: https://lore.kernel.org/all/000000000000994e09060ebcdffb@google.com/
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Acked-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20240117172102.12001-1-n.zhandarovich@fintech.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/mcast.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index b75d3c9d41bb5..bc6e0a0bad3c1 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2722,8 +2722,12 @@ void ipv6_mc_down(struct inet6_dev *idev)
 	synchronize_net();
 	mld_query_stop_work(idev);
 	mld_report_stop_work(idev);
+
+	mutex_lock(&idev->mc_lock);
 	mld_ifc_stop_work(idev);
 	mld_gq_stop_work(idev);
+	mutex_unlock(&idev->mc_lock);
+
 	mld_dad_stop_work(idev);
 }
 
-- 
GitLab


From 9cfd3b502153810b66ac0ce47f1fba682228f2d2 Mon Sep 17 00:00:00 2001
From: Tony Nguyen <anthony.l.nguyen@intel.com>
Date: Wed, 17 Jan 2024 09:25:32 -0800
Subject: [PATCH 2943/4076] i40e: Include types.h to some headers

Commit 56df345917c0 ("i40e: Remove circular header dependencies and fix
headers") redistributed a number of includes from one large header file
to the locations they were needed. In some environments, types.h is not
included and causing compile issues. The driver should not rely on
implicit inclusion from other locations; explicitly include it to these
files.

Snippet of issue. Entire log can be seen through the Closes: link.

In file included from drivers/net/ethernet/intel/i40e/i40e_diag.h:7,
                 from drivers/net/ethernet/intel/i40e/i40e_diag.c:4:
drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h:33:9: error: unknown type name '__le16'
   33 |         __le16 flags;
      |         ^~~~~~
drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h:34:9: error: unknown type name '__le16'
   34 |         __le16 opcode;
      |         ^~~~~~
...
drivers/net/ethernet/intel/i40e/i40e_diag.h:22:9: error: unknown type name 'u32'
   22 |         u32 elements;   /* number of elements if array */
      |         ^~~
drivers/net/ethernet/intel/i40e/i40e_diag.h:23:9: error: unknown type name 'u32'
   23 |         u32 stride;     /* bytes between each element */

Reported-by: Martin Zaharinov <micron10@gmail.com>
Closes: https://lore.kernel.org/netdev/21BBD62A-F874-4E42-B347-93087EEA8126@gmail.com/
Fixes: 56df345917c0 ("i40e: Remove circular header dependencies and fix headers")
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Arpana Arland <arpanax.arland@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20240117172534.3555162-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 1 +
 drivers/net/ethernet/intel/i40e/i40e_diag.h       | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 18a1c3b6d72c5..c8f35d4de271a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -5,6 +5,7 @@
 #define _I40E_ADMINQ_CMD_H_
 
 #include <linux/bits.h>
+#include <linux/types.h>
 
 /* This header file defines the i40e Admin Queue commands and is shared between
  * i40e Firmware and Software.
diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h
index ece3a6b9a5c61..ab20202a3da3c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_diag.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h
@@ -4,6 +4,7 @@
 #ifndef _I40E_DIAG_H_
 #define _I40E_DIAG_H_
 
+#include <linux/types.h>
 #include "i40e_adminq_cmd.h"
 
 /* forward-declare the HW struct for the compiler */
-- 
GitLab


From d8392c203e84ec7daa2afecdb8f4db69bc32416a Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 17 Jan 2024 16:15:18 -0600
Subject: [PATCH 2944/4076] smb3: show beginning time for per share stats

In analyzing problems, one missing piece of debug data is when the
mount occurred.  A related problem is when collecting stats we don't
know the  period of time the stats covered, ie when this set of stats
for the tcon started to be collected.  To make debugging easier track
the stats begin time. Set it when the mount occurred at mount time,
and reset it to current time whenever stats are reset. For example,

...
1) \\localhost\test
SMBs: 14 since 2024-01-17 22:17:30 UTC
Bytes read: 0  Bytes written: 0
Open files: 0 total (local), 0 open on server
TreeConnects: 1 total 0 failed
TreeDisconnects: 0 total 0 failed
...
2) \\localhost\scratch
SMBs: 24 since 2024-01-17 22:16:04 UTC
Bytes read: 0  Bytes written: 0
Open files: 0 total (local), 0 open on server
TreeConnects: 1 total 0 failed
TreeDisconnects: 0 total 0 failed
...

Note the time "since ... UTC" is now displayed in /proc/fs/cifs/Stats
for each share that is mounted.

Suggested-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_debug.c | 6 ++++--
 fs/smb/client/cifsglob.h   | 1 +
 fs/smb/client/misc.c       | 1 +
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index 60027f5aebe87..3e4209f41c18f 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -659,6 +659,7 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 					spin_lock(&tcon->stat_lock);
 					tcon->bytes_read = 0;
 					tcon->bytes_written = 0;
+					tcon->stats_from_time = ktime_get_real_seconds();
 					spin_unlock(&tcon->stat_lock);
 					if (server->ops->clear_stats)
 						server->ops->clear_stats(tcon);
@@ -737,8 +738,9 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 				seq_printf(m, "\n%d) %s", i, tcon->tree_name);
 				if (tcon->need_reconnect)
 					seq_puts(m, "\tDISCONNECTED ");
-				seq_printf(m, "\nSMBs: %d",
-					   atomic_read(&tcon->num_smbs_sent));
+				seq_printf(m, "\nSMBs: %d since %ptTs UTC",
+					   atomic_read(&tcon->num_smbs_sent),
+					   &tcon->stats_from_time);
 				if (server->ops->print_stats)
 					server->ops->print_stats(m, tcon);
 			}
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 879d5ef8a66ed..f576ceee6157a 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1207,6 +1207,7 @@ struct cifs_tcon {
 	__u64    bytes_read;
 	__u64    bytes_written;
 	spinlock_t stat_lock;  /* protects the two fields above */
+	time64_t stats_from_time;
 	FILE_SYSTEM_DEVICE_INFO fsDevInfo;
 	FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */
 	FILE_SYSTEM_UNIX_INFO fsUnixInfo;
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index c2137ea3c2538..0748d7b757b95 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -140,6 +140,7 @@ tcon_info_alloc(bool dir_leases_enabled)
 	spin_lock_init(&ret_buf->stat_lock);
 	atomic_set(&ret_buf->num_local_opens, 0);
 	atomic_set(&ret_buf->num_remote_opens, 0);
+	ret_buf->stats_from_time = ktime_get_real_seconds();
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	INIT_LIST_HEAD(&ret_buf->dfs_ses_list);
 #endif
-- 
GitLab


From 0b549c4f594167d7ef056393c6a06ac77f5690ff Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 17 Jan 2024 16:56:05 -0600
Subject: [PATCH 2945/4076] cifs: minor comment cleanup

minor comment cleanup and trivial camelCase removal

Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/readdir.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 056cae1ddccef..e24684112ab0a 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -645,10 +645,10 @@ static int cifs_entry_is_dot(struct cifs_dirent *de, bool is_unicode)
 static int is_dir_changed(struct file *file)
 {
 	struct inode *inode = file_inode(file);
-	struct cifsInodeInfo *cifsInfo = CIFS_I(inode);
+	struct cifsInodeInfo *cifs_inode_info = CIFS_I(inode);
 
-	if (cifsInfo->time == 0)
-		return 1; /* directory was changed, perhaps due to unlink */
+	if (cifs_inode_info->time == 0)
+		return 1; /* directory was changed, e.g. unlink or new file */
 	else
 		return 0;
 
-- 
GitLab


From c3365ced1375db779d2244695a7f936fd2f1bdb5 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 17 Jan 2024 17:12:57 -0600
Subject: [PATCH 2946/4076] Update MAINTAINERS email address

Ronnie is no longer at Redhat.  Update his email address.

Signed-off-by: Steve French <stfrench@microsoft.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4c0135b70caeb..75d5308f57774 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5205,7 +5205,7 @@ X:	drivers/clk/clkdev.c
 COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3)
 M:	Steve French <sfrench@samba.org>
 R:	Paulo Alcantara <pc@manguebit.com> (DFS, global name space)
-R:	Ronnie Sahlberg <lsahlber@redhat.com> (directory leases, sparse files)
+R:	Ronnie Sahlberg <ronniesahlberg@gmail.com> (directory leases, sparse files)
 R:	Shyam Prasad N <sprasad@microsoft.com> (multichannel)
 R:	Tom Talpey <tom@talpey.com> (RDMA, smbdirect)
 L:	linux-cifs@vger.kernel.org
-- 
GitLab


From 18f14afe281648e31ed35c9ad2fcb724c4838ad9 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 15 Dec 2023 23:44:49 +1100
Subject: [PATCH 2947/4076] powerpc/64s: Increase default stack size to 32KB

There are reports of kernels crashing due to stack overflow while
running OpenShift (Kubernetes). The primary contributor to the stack
usage seems to be openvswitch, which is used by OVN-Kubernetes (based on
OVN (Open Virtual Network)), but NFS also contributes in some stack
traces.

There may be some opportunities to reduce stack usage in the openvswitch
code, but doing so potentially require tradeoffs vs performance, and
also requires testing across architectures.

Looking at stack usage across the kernel (using -fstack-usage), shows
that ppc64le stack frames are on average 50-100% larger than the
equivalent function built for x86-64. Which is not surprising given the
minimum stack frame size is 32 bytes on ppc64le vs 16 bytes on x86-64.

So increase the default stack size to 32KB for the modern 64-bit Book3S
platforms, ie. pseries (virtualised) and powernv (bare metal). That
leaves the older systems like G5s, and the AmigaOne (pasemi) with a 16KB
stack which should be sufficient on those machines.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Aneesh Kumar K.V (IBM) <aneesh.kumar@kernel.org>
Link: https://msgid.link/20231215124449.317597-1-mpe@ellerman.id.au
---
 arch/powerpc/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6f105ee4f3cf5..2df545c1446ec 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -858,6 +858,7 @@ config THREAD_SHIFT
 	int "Thread shift" if EXPERT
 	range 13 15
 	default "15" if PPC_256K_PAGES
+	default "15" if PPC_PSERIES || PPC_POWERNV
 	default "14" if PPC64
 	default "13"
 	help
-- 
GitLab


From e965a707276760cc010eb77fba64b08ee9e8781f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 23 Nov 2023 10:40:21 +0100
Subject: [PATCH 2948/4076] drm: remove I2C_CLASS_DDC support

After removal of the legacy EEPROM driver and I2C_CLASS_DDC support in
olpc_dcon there's no i2c client driver left supporting I2C_CLASS_DDC.
Class-based device auto-detection is a legacy mechanism and shouldn't
be used in new code. So we can remove this class completely now.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c           | 1 -
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 -
 drivers/gpu/drm/ast/ast_i2c.c                     | 1 -
 drivers/gpu/drm/bridge/synopsys/dw-hdmi.c         | 1 -
 drivers/gpu/drm/display/drm_dp_helper.c           | 1 -
 drivers/gpu/drm/display/drm_dp_mst_topology.c     | 1 -
 drivers/gpu/drm/gma500/cdv_intel_dp.c             | 1 -
 drivers/gpu/drm/gma500/intel_gmbus.c              | 1 -
 drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c        | 1 -
 drivers/gpu/drm/gma500/psb_intel_sdvo.c           | 1 -
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c   | 1 -
 drivers/gpu/drm/i915/display/intel_gmbus.c        | 1 -
 drivers/gpu/drm/i915/display/intel_sdvo.c         | 1 -
 drivers/gpu/drm/loongson/lsdc_i2c.c               | 1 -
 drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c           | 1 -
 drivers/gpu/drm/mgag200/mgag200_i2c.c             | 1 -
 drivers/gpu/drm/msm/hdmi/hdmi_i2c.c               | 1 -
 drivers/gpu/drm/radeon/radeon_i2c.c               | 1 -
 drivers/gpu/drm/rockchip/inno_hdmi.c              | 1 -
 drivers/gpu/drm/rockchip/rk3066_hdmi.c            | 1 -
 drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c            | 1 -
 21 files changed, 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
index 82608df433964..d79cb13e1aa83 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
@@ -175,7 +175,6 @@ struct amdgpu_i2c_chan *amdgpu_i2c_create(struct drm_device *dev,
 
 	i2c->rec = *rec;
 	i2c->adapter.owner = THIS_MODULE;
-	i2c->adapter.class = I2C_CLASS_DDC;
 	i2c->adapter.dev.parent = dev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index ee97814ebd994..bbd511567a73a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7533,7 +7533,6 @@ create_i2c(struct ddc_service *ddc_service,
 	if (!i2c)
 		return NULL;
 	i2c->base.owner = THIS_MODULE;
-	i2c->base.class = I2C_CLASS_DDC;
 	i2c->base.dev.parent = &adev->pdev->dev;
 	i2c->base.algo = &amdgpu_dm_i2c_algo;
 	snprintf(i2c->base.name, sizeof(i2c->base.name), "AMDGPU DM i2c hw bus %d", link_index);
diff --git a/drivers/gpu/drm/ast/ast_i2c.c b/drivers/gpu/drm/ast/ast_i2c.c
index 0e845e7acd9b5..e5d3f7121de42 100644
--- a/drivers/gpu/drm/ast/ast_i2c.c
+++ b/drivers/gpu/drm/ast/ast_i2c.c
@@ -120,7 +120,6 @@ struct ast_i2c_chan *ast_i2c_create(struct drm_device *dev)
 		return NULL;
 
 	i2c->adapter.owner = THIS_MODULE;
-	i2c->adapter.class = I2C_CLASS_DDC;
 	i2c->adapter.dev.parent = dev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 52d91a0df85e9..aca5bb0866f88 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -515,7 +515,6 @@ static struct i2c_adapter *dw_hdmi_i2c_adapter(struct dw_hdmi *hdmi)
 	init_completion(&i2c->cmp);
 
 	adap = &i2c->adap;
-	adap->class = I2C_CLASS_DDC;
 	adap->owner = THIS_MODULE;
 	adap->dev.parent = hdmi->dev;
 	adap->algo = &dw_hdmi_algorithm;
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index f3680f4e69708..ac901f4b48f23 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -2102,7 +2102,6 @@ int drm_dp_aux_register(struct drm_dp_aux *aux)
 	if (!aux->ddc.algo)
 		drm_dp_aux_init(aux);
 
-	aux->ddc.class = I2C_CLASS_DDC;
 	aux->ddc.owner = THIS_MODULE;
 	aux->ddc.dev.parent = aux->dev;
 
diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
index 0e0d0e76de065..4376e2c1f2d43 100644
--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -5803,7 +5803,6 @@ static int drm_dp_mst_register_i2c_bus(struct drm_dp_mst_port *port)
 	aux->ddc.algo_data = aux;
 	aux->ddc.retries = 3;
 
-	aux->ddc.class = I2C_CLASS_DDC;
 	aux->ddc.owner = THIS_MODULE;
 	/* FIXME: set the kdev of the port's connector as parent */
 	aux->ddc.dev.parent = parent_dev;
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 8992a95076f29..dd1eb7e9877d4 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -855,7 +855,6 @@ cdv_intel_dp_i2c_init(struct gma_connector *connector,
 
 	memset(&intel_dp->adapter, '\0', sizeof (intel_dp->adapter));
 	intel_dp->adapter.owner = THIS_MODULE;
-	intel_dp->adapter.class = I2C_CLASS_DDC;
 	strncpy (intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1);
 	intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0';
 	intel_dp->adapter.algo_data = &intel_dp->algo;
diff --git a/drivers/gpu/drm/gma500/intel_gmbus.c b/drivers/gpu/drm/gma500/intel_gmbus.c
index 09cedabf4776d..aa45509859f21 100644
--- a/drivers/gpu/drm/gma500/intel_gmbus.c
+++ b/drivers/gpu/drm/gma500/intel_gmbus.c
@@ -411,7 +411,6 @@ int gma_intel_setup_gmbus(struct drm_device *dev)
 		struct intel_gmbus *bus = &dev_priv->gmbus[i];
 
 		bus->adapter.owner = THIS_MODULE;
-		bus->adapter.class = I2C_CLASS_DDC;
 		snprintf(bus->adapter.name,
 			 sizeof(bus->adapter.name),
 			 "gma500 gmbus %s",
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c b/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
index fc9a34ed58bd1..6daa6669ed237 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
@@ -168,7 +168,6 @@ static struct i2c_adapter oaktrail_hdmi_i2c_adapter = {
 	.name		= "oaktrail_hdmi_i2c",
 	.nr		= 3,
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_DDC,
 	.algo		= &oaktrail_hdmi_i2c_algorithm,
 };
 
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index d6fd5d7262160..e4f914decebae 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -2426,7 +2426,6 @@ psb_intel_sdvo_init_ddc_proxy(struct psb_intel_sdvo *sdvo,
 			  struct drm_device *dev)
 {
 	sdvo->ddc.owner = THIS_MODULE;
-	sdvo->ddc.class = I2C_CLASS_DDC;
 	snprintf(sdvo->ddc.name, I2C_NAME_SIZE, "SDVO DDC proxy");
 	sdvo->ddc.dev.parent = dev->dev;
 	sdvo->ddc.algo_data = sdvo;
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
index 410bd019bb357..e6e48651c15c6 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
@@ -81,7 +81,6 @@ int hibmc_ddc_create(struct drm_device *drm_dev,
 		     struct hibmc_connector *connector)
 {
 	connector->adapter.owner = THIS_MODULE;
-	connector->adapter.class = I2C_CLASS_DDC;
 	snprintf(connector->adapter.name, I2C_NAME_SIZE, "HIS i2c bit bus");
 	connector->adapter.dev.parent = drm_dev->dev;
 	i2c_set_adapdata(&connector->adapter, connector);
diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index 40d7b6f3f4891..e9e4dcf345f95 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -899,7 +899,6 @@ int intel_gmbus_setup(struct drm_i915_private *i915)
 		}
 
 		bus->adapter.owner = THIS_MODULE;
-		bus->adapter.class = I2C_CLASS_DDC;
 		snprintf(bus->adapter.name,
 			 sizeof(bus->adapter.name),
 			 "i915 gmbus %s", gmbus_pin->name);
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index a636f42ceae55..5e64d1baffe88 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -3311,7 +3311,6 @@ intel_sdvo_init_ddc_proxy(struct intel_sdvo_ddc *ddc,
 	ddc->ddc_bus = ddc_bus;
 
 	ddc->ddc.owner = THIS_MODULE;
-	ddc->ddc.class = I2C_CLASS_DDC;
 	snprintf(ddc->ddc.name, I2C_NAME_SIZE, "SDVO %c DDC%d",
 		 port_name(sdvo->base.port), ddc_bus);
 	ddc->ddc.dev.parent = &pdev->dev;
diff --git a/drivers/gpu/drm/loongson/lsdc_i2c.c b/drivers/gpu/drm/loongson/lsdc_i2c.c
index 9625d0b1d0b4d..ce90c25536d24 100644
--- a/drivers/gpu/drm/loongson/lsdc_i2c.c
+++ b/drivers/gpu/drm/loongson/lsdc_i2c.c
@@ -154,7 +154,6 @@ int lsdc_create_i2c_chan(struct drm_device *ddev,
 	adapter = &li2c->adapter;
 	adapter->algo_data = &li2c->bit;
 	adapter->owner = THIS_MODULE;
-	adapter->class = I2C_CLASS_DDC;
 	adapter->dev.parent = ddev->dev;
 	adapter->nr = -1;
 
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
index d675c954befe3..54e46e440e0f0 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
@@ -297,7 +297,6 @@ static int mtk_hdmi_ddc_probe(struct platform_device *pdev)
 
 	strscpy(ddc->adap.name, "mediatek-hdmi-ddc", sizeof(ddc->adap.name));
 	ddc->adap.owner = THIS_MODULE;
-	ddc->adap.class = I2C_CLASS_DDC;
 	ddc->adap.algo = &mtk_hdmi_ddc_algorithm;
 	ddc->adap.retries = 3;
 	ddc->adap.dev.of_node = dev->of_node;
diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c
index 0c48bdf3e7f80..423eb302be7eb 100644
--- a/drivers/gpu/drm/mgag200/mgag200_i2c.c
+++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c
@@ -106,7 +106,6 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c)
 	i2c->data = BIT(info->i2c.data_bit);
 	i2c->clock = BIT(info->i2c.clock_bit);
 	i2c->adapter.owner = THIS_MODULE;
-	i2c->adapter.class = I2C_CLASS_DDC;
 	i2c->adapter.dev.parent = dev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
index de182c0048434..7aa500d24240f 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
@@ -249,7 +249,6 @@ struct i2c_adapter *msm_hdmi_i2c_init(struct hdmi *hdmi)
 
 
 	i2c->owner = THIS_MODULE;
-	i2c->class = I2C_CLASS_DDC;
 	snprintf(i2c->name, sizeof(i2c->name), "msm hdmi i2c");
 	i2c->dev.parent = &hdmi->pdev->dev;
 	i2c->algo = &msm_hdmi_i2c_algorithm;
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index 314d066e68e9d..3d174390a8afe 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -918,7 +918,6 @@ struct radeon_i2c_chan *radeon_i2c_create(struct drm_device *dev,
 
 	i2c->rec = *rec;
 	i2c->adapter.owner = THIS_MODULE;
-	i2c->adapter.class = I2C_CLASS_DDC;
 	i2c->adapter.dev.parent = dev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index 6e5b922a121e2..a7739b27c42b5 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -793,7 +793,6 @@ static struct i2c_adapter *inno_hdmi_i2c_adapter(struct inno_hdmi *hdmi)
 	init_completion(&i2c->cmp);
 
 	adap = &i2c->adap;
-	adap->class = I2C_CLASS_DDC;
 	adap->owner = THIS_MODULE;
 	adap->dev.parent = hdmi->dev;
 	adap->dev.of_node = hdmi->dev->of_node;
diff --git a/drivers/gpu/drm/rockchip/rk3066_hdmi.c b/drivers/gpu/drm/rockchip/rk3066_hdmi.c
index fa6e592e0276c..7a3f71aa2ca9d 100644
--- a/drivers/gpu/drm/rockchip/rk3066_hdmi.c
+++ b/drivers/gpu/drm/rockchip/rk3066_hdmi.c
@@ -725,7 +725,6 @@ static struct i2c_adapter *rk3066_hdmi_i2c_adapter(struct rk3066_hdmi *hdmi)
 	init_completion(&i2c->cmpltn);
 
 	adap = &i2c->adap;
-	adap->class = I2C_CLASS_DDC;
 	adap->owner = THIS_MODULE;
 	adap->dev.parent = hdmi->dev;
 	adap->dev.of_node = hdmi->dev->of_node;
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c
index d1a65a921f5af..f5f62eb0eecaa 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_i2c.c
@@ -302,7 +302,6 @@ int sun4i_hdmi_i2c_create(struct device *dev, struct sun4i_hdmi *hdmi)
 		return -ENOMEM;
 
 	adap->owner = THIS_MODULE;
-	adap->class = I2C_CLASS_DDC;
 	adap->algo = &sun4i_hdmi_i2c_algorithm;
 	strscpy(adap->name, "sun4i_hdmi_i2c adapter", sizeof(adap->name));
 	i2c_set_adapdata(adap, hdmi);
-- 
GitLab


From 754bd2fffc913e523d1b9e686e8b1fd3a70d8f7e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 23 Nov 2023 10:40:25 +0100
Subject: [PATCH 2949/4076] fbdev: remove I2C_CLASS_DDC support

After removal of the legacy EEPROM driver and I2C_CLASS_DDC support in
olpc_dcon there's no i2c client driver left supporting I2C_CLASS_DDC.
Class-based device auto-detection is a legacy mechanism and shouldn't
be used in new code. So we can remove this class completely now.

Acked-by: Helge Deller <deller@gmx.de>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/video/fbdev/core/fb_ddc.c         |  1 -
 drivers/video/fbdev/cyber2000fb.c         |  1 -
 drivers/video/fbdev/i740fb.c              |  1 -
 drivers/video/fbdev/intelfb/intelfb_i2c.c | 15 +++++----------
 drivers/video/fbdev/matrox/i2c-matroxfb.c | 15 +++++----------
 drivers/video/fbdev/s3fb.c                |  1 -
 drivers/video/fbdev/tdfxfb.c              |  1 -
 drivers/video/fbdev/tridentfb.c           |  1 -
 drivers/video/fbdev/via/via_i2c.c         |  1 -
 9 files changed, 10 insertions(+), 27 deletions(-)

diff --git a/drivers/video/fbdev/core/fb_ddc.c b/drivers/video/fbdev/core/fb_ddc.c
index 8bf5f2f54be7b..e251432198629 100644
--- a/drivers/video/fbdev/core/fb_ddc.c
+++ b/drivers/video/fbdev/core/fb_ddc.c
@@ -116,7 +116,6 @@ unsigned char *fb_ddc_read(struct i2c_adapter *adapter)
 	algo_data->setsda(algo_data->data, 1);
 	algo_data->setscl(algo_data->data, 1);
 
-	adapter->class |= I2C_CLASS_DDC;
 	return edid;
 }
 
diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c
index 52105dc1a72f3..79775dedacebc 100644
--- a/drivers/video/fbdev/cyber2000fb.c
+++ b/drivers/video/fbdev/cyber2000fb.c
@@ -1234,7 +1234,6 @@ static int cyber2000fb_setup_ddc_bus(struct cfb_info *cfb)
 	strscpy(cfb->ddc_adapter.name, cfb->fb.fix.id,
 		sizeof(cfb->ddc_adapter.name));
 	cfb->ddc_adapter.owner		= THIS_MODULE;
-	cfb->ddc_adapter.class		= I2C_CLASS_DDC;
 	cfb->ddc_adapter.algo_data	= &cfb->ddc_algo;
 	cfb->ddc_adapter.dev.parent	= cfb->fb.device;
 	cfb->ddc_algo.setsda		= cyber2000fb_ddc_setsda;
diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c
index 1897e65ab7031..9b74dae71472c 100644
--- a/drivers/video/fbdev/i740fb.c
+++ b/drivers/video/fbdev/i740fb.c
@@ -163,7 +163,6 @@ static int i740fb_setup_ddc_bus(struct fb_info *info)
 	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
-	par->ddc_adapter.class		= I2C_CLASS_DDC;
 	par->ddc_adapter.algo_data	= &par->ddc_algo;
 	par->ddc_adapter.dev.parent	= info->device;
 	par->ddc_algo.setsda		= i740fb_ddc_setsda;
diff --git a/drivers/video/fbdev/intelfb/intelfb_i2c.c b/drivers/video/fbdev/intelfb/intelfb_i2c.c
index 3300bd31d9d7e..f24c7cb4c2ea6 100644
--- a/drivers/video/fbdev/intelfb/intelfb_i2c.c
+++ b/drivers/video/fbdev/intelfb/intelfb_i2c.c
@@ -99,8 +99,7 @@ static int intelfb_gpio_getsda(void *data)
 
 static int intelfb_setup_i2c_bus(struct intelfb_info *dinfo,
 				 struct intelfb_i2c_chan *chan,
-				 const u32 reg, const char *name,
-				 int class)
+				 const u32 reg, const char *name)
 {
 	int rc;
 
@@ -108,7 +107,6 @@ static int intelfb_setup_i2c_bus(struct intelfb_info *dinfo,
 	chan->reg			= reg;
 	snprintf(chan->adapter.name, sizeof(chan->adapter.name),
 		 "intelfb %s", name);
-	chan->adapter.class		= class;
 	chan->adapter.owner		= THIS_MODULE;
 	chan->adapter.algo_data		= &chan->algo;
 	chan->adapter.dev.parent	= &chan->dinfo->pdev->dev;
@@ -144,8 +142,7 @@ void intelfb_create_i2c_busses(struct intelfb_info *dinfo)
 	dinfo->output[i].type = INTELFB_OUTPUT_ANALOG;
 
 	/* setup the DDC bus for analog output */
-	intelfb_setup_i2c_bus(dinfo, &dinfo->output[i].ddc_bus, GPIOA,
-			      "CRTDDC_A", I2C_CLASS_DDC);
+	intelfb_setup_i2c_bus(dinfo, &dinfo->output[i].ddc_bus, GPIOA, "CRTDDC_A");
 	i++;
 
 	/* need to add the output busses for each device
@@ -159,10 +156,8 @@ void intelfb_create_i2c_busses(struct intelfb_info *dinfo)
 	case INTEL_855GM:
 	case INTEL_865G:
 		dinfo->output[i].type = INTELFB_OUTPUT_DVO;
-		intelfb_setup_i2c_bus(dinfo, &dinfo->output[i].ddc_bus,
-				      GPIOD, "DVODDC_D", I2C_CLASS_DDC);
-		intelfb_setup_i2c_bus(dinfo, &dinfo->output[i].i2c_bus,
-				      GPIOE, "DVOI2C_E", 0);
+		intelfb_setup_i2c_bus(dinfo, &dinfo->output[i].ddc_bus, GPIOD, "DVODDC_D");
+		intelfb_setup_i2c_bus(dinfo, &dinfo->output[i].i2c_bus, GPIOE, "DVOI2C_E");
 		i++;
 		break;
 	case INTEL_915G:
@@ -176,7 +171,7 @@ void intelfb_create_i2c_busses(struct intelfb_info *dinfo)
 		/* SDVO ports have a single control bus - 2 devices */
 		dinfo->output[i].type = INTELFB_OUTPUT_SDVO;
 		intelfb_setup_i2c_bus(dinfo, &dinfo->output[i].i2c_bus,
-				      GPIOE, "SDVOCTRL_E", 0);
+				      GPIOE, "SDVOCTRL_E");
 		/* TODO: initialize the SDVO */
 		/* I830SDVOInit(pScrn, i, DVOB); */
 		i++;
diff --git a/drivers/video/fbdev/matrox/i2c-matroxfb.c b/drivers/video/fbdev/matrox/i2c-matroxfb.c
index e2e4705e3fe0e..bb048e14b2cf1 100644
--- a/drivers/video/fbdev/matrox/i2c-matroxfb.c
+++ b/drivers/video/fbdev/matrox/i2c-matroxfb.c
@@ -100,8 +100,7 @@ static const struct i2c_algo_bit_data matrox_i2c_algo_template =
 };
 
 static int i2c_bus_reg(struct i2c_bit_adapter* b, struct matrox_fb_info* minfo, 
-		unsigned int data, unsigned int clock, const char *name,
-		int class)
+		unsigned int data, unsigned int clock, const char *name)
 {
 	int err;
 
@@ -112,7 +111,6 @@ static int i2c_bus_reg(struct i2c_bit_adapter* b, struct matrox_fb_info* minfo,
 	snprintf(b->adapter.name, sizeof(b->adapter.name), name,
 		minfo->fbcon.node);
 	i2c_set_adapdata(&b->adapter, b);
-	b->adapter.class = class;
 	b->adapter.algo_data = &b->bac;
 	b->adapter.dev.parent = &minfo->pcidev->dev;
 	b->bac = matrox_i2c_algo_template;
@@ -160,27 +158,24 @@ static void* i2c_matroxfb_probe(struct matrox_fb_info* minfo) {
 		case MGA_2164:
 			err = i2c_bus_reg(&m2info->ddc1, minfo,
 					  DDC1B_DATA, DDC1B_CLK,
-					  "DDC:fb%u #0", I2C_CLASS_DDC);
+					  "DDC:fb%u #0");
 			break;
 		default:
 			err = i2c_bus_reg(&m2info->ddc1, minfo,
 					  DDC1_DATA, DDC1_CLK,
-					  "DDC:fb%u #0", I2C_CLASS_DDC);
+					  "DDC:fb%u #0");
 			break;
 	}
 	if (err)
 		goto fail_ddc1;
 	if (minfo->devflags.dualhead) {
-		err = i2c_bus_reg(&m2info->ddc2, minfo,
-				  DDC2_DATA, DDC2_CLK,
-				  "DDC:fb%u #1", I2C_CLASS_DDC);
+		err = i2c_bus_reg(&m2info->ddc2, minfo, DDC2_DATA, DDC2_CLK, "DDC:fb%u #1");
 		if (err == -ENODEV) {
 			printk(KERN_INFO "i2c-matroxfb: VGA->TV plug detected, DDC unavailable.\n");
 		} else if (err)
 			printk(KERN_INFO "i2c-matroxfb: Could not register secondary output i2c bus. Continuing anyway.\n");
 		/* Register maven bus even on G450/G550 */
-		err = i2c_bus_reg(&m2info->maven, minfo,
-				  MAT_DATA, MAT_CLK, "MAVEN:fb%u", 0);
+		err = i2c_bus_reg(&m2info->maven, minfo, MAT_DATA, MAT_CLK, "MAVEN:fb%u");
 		if (err)
 			printk(KERN_INFO "i2c-matroxfb: Could not register Maven i2c bus. Continuing anyway.\n");
 		else {
diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index 589b349cb63e0..07722a5ea8eff 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -252,7 +252,6 @@ static int s3fb_setup_ddc_bus(struct fb_info *info)
 	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
-	par->ddc_adapter.class		= I2C_CLASS_DDC;
 	par->ddc_adapter.algo_data	= &par->ddc_algo;
 	par->ddc_adapter.dev.parent	= info->device;
 	par->ddc_algo.setsda		= s3fb_ddc_setsda;
diff --git a/drivers/video/fbdev/tdfxfb.c b/drivers/video/fbdev/tdfxfb.c
index 22aa953138b0f..51ebe78359ec3 100644
--- a/drivers/video/fbdev/tdfxfb.c
+++ b/drivers/video/fbdev/tdfxfb.c
@@ -1267,7 +1267,6 @@ static int tdfxfb_setup_ddc_bus(struct tdfxfb_i2c_chan *chan, const char *name,
 
 	strscpy(chan->adapter.name, name, sizeof(chan->adapter.name));
 	chan->adapter.owner		= THIS_MODULE;
-	chan->adapter.class		= I2C_CLASS_DDC;
 	chan->adapter.algo_data		= &chan->algo;
 	chan->adapter.dev.parent	= dev;
 	chan->algo.setsda		= tdfxfb_ddc_setsda;
diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c
index 816d40b6f689c..516cf2a187575 100644
--- a/drivers/video/fbdev/tridentfb.c
+++ b/drivers/video/fbdev/tridentfb.c
@@ -274,7 +274,6 @@ static int tridentfb_setup_ddc_bus(struct fb_info *info)
 	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
-	par->ddc_adapter.class		= I2C_CLASS_DDC;
 	par->ddc_adapter.algo_data	= &par->ddc_algo;
 	par->ddc_adapter.dev.parent	= info->device;
 	if (is_oldclock(par->chip_id)) { /* not sure if this check is OK */
diff --git a/drivers/video/fbdev/via/via_i2c.c b/drivers/video/fbdev/via/via_i2c.c
index c35e530e0ec9d..5825028105759 100644
--- a/drivers/video/fbdev/via/via_i2c.c
+++ b/drivers/video/fbdev/via/via_i2c.c
@@ -201,7 +201,6 @@ static int create_i2c_bus(struct i2c_adapter *adapter,
 	sprintf(adapter->name, "viafb i2c io_port idx 0x%02x",
 		adap_cfg->ioport_index);
 	adapter->owner = THIS_MODULE;
-	adapter->class = I2C_CLASS_DDC;
 	adapter->algo_data = algo;
 	if (pdev)
 		adapter->dev.parent = &pdev->dev;
-- 
GitLab


From b60db383e2ba64a18e49b6bef3be1ab18aa159f1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 23 Nov 2023 10:40:40 +0100
Subject: [PATCH 2950/4076] include/linux/i2c.h: remove I2C_CLASS_DDC support

After removal of the legacy EEPROM driver and I2C_CLASS_DDC support in
olpc_dcon there's no i2c client driver left supporting I2C_CLASS_DDC.
Class-based device auto-detection is a legacy mechanism and shouldn't
be used in new code. So we can remove this class completely now.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 include/linux/i2c.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 0dae9db275380..d029aade338fd 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -850,7 +850,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap)
 
 /* i2c adapter classes (bitmask) */
 #define I2C_CLASS_HWMON		(1<<0)	/* lm_sensors, ... */
-#define I2C_CLASS_DDC		(1<<3)	/* DDC bus on graphics adapters */
 #define I2C_CLASS_SPD		(1<<7)	/* Memory modules */
 /* Warn users that the adapter doesn't support classes anymore */
 #define I2C_CLASS_DEPRECATED	(1<<8)
-- 
GitLab


From f21682b362b67833e4f4f481c30abcb432861b0c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 13 Nov 2023 12:37:15 +0100
Subject: [PATCH 2951/4076] drm/amd/pm: Remove I2C_CLASS_SPD support

I2C_CLASS_SPD was used to expose the EEPROM content to user space,
via the legacy eeprom driver. Now that this driver has been removed,
we can remove I2C_CLASS_SPD support. at24 driver with explicit
instantiation should be used instead.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c   | 1 -
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 1 -
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 1 -
 3 files changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 1a6675d70a4bc..bc56a29e63fad 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1527,7 +1527,6 @@ static int aldebaran_i2c_control_init(struct smu_context *smu)
 	smu_i2c->port = 0;
 	mutex_init(&smu_i2c->mutex);
 	control->owner = THIS_MODULE;
-	control->class = I2C_CLASS_SPD;
 	control->dev.parent = &adev->pdev->dev;
 	control->algo = &aldebaran_i2c_algo;
 	snprintf(control->name, sizeof(control->name), "AMDGPU SMU 0");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 82c4e1f1c6f07..c0e62bab97a12 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2720,7 +2720,6 @@ static int smu_v13_0_0_i2c_control_init(struct smu_context *smu)
 		smu_i2c->port = i;
 		mutex_init(&smu_i2c->mutex);
 		control->owner = THIS_MODULE;
-		control->class = I2C_CLASS_SPD;
 		control->dev.parent = &adev->pdev->dev;
 		control->algo = &smu_v13_0_0_i2c_algo;
 		snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 0e5a77c3c2e21..8bedd8d2ab2f4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -1884,7 +1884,6 @@ static int smu_v13_0_6_i2c_control_init(struct smu_context *smu)
 		smu_i2c->port = i;
 		mutex_init(&smu_i2c->mutex);
 		control->owner = THIS_MODULE;
-		control->class = I2C_CLASS_SPD;
 		control->dev.parent = &adev->pdev->dev;
 		control->algo = &smu_v13_0_6_i2c_algo;
 		snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i);
-- 
GitLab


From 9fd12f385720a85b4ce9a3cb98e66d470a5efd20 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 24 Nov 2023 11:16:10 +0100
Subject: [PATCH 2952/4076] i2c: Don't let i2c adapters declare I2C_CLASS_SPD
 support if they support I2C_CLASS_HWMON

After removal of the legacy eeprom driver the only remaining I2C
client device driver supporting I2C_CLASS_SPD is jc42. Because this
driver also supports I2C_CLASS_HWMON, adapters don't have to
declare support for I2C_CLASS_SPD if they support I2C_CLASS_HWMON.
It's one step towards getting rid of I2C_CLASS_SPD mid-term.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Andi Shyti <andi.shyti@kernel.org>
Acked-by: Jim Cromie <jim.cromie@gmail.com> # for SCX
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-ali1535.c    | 2 +-
 drivers/i2c/busses/i2c-ali1563.c    | 2 +-
 drivers/i2c/busses/i2c-ali15x3.c    | 2 +-
 drivers/i2c/busses/i2c-amd756.c     | 2 +-
 drivers/i2c/busses/i2c-amd8111.c    | 2 +-
 drivers/i2c/busses/i2c-elektor.c    | 2 +-
 drivers/i2c/busses/i2c-gpio.c       | 2 +-
 drivers/i2c/busses/i2c-ibm_iic.c    | 2 +-
 drivers/i2c/busses/i2c-iop3xx.c     | 2 +-
 drivers/i2c/busses/i2c-isch.c       | 2 +-
 drivers/i2c/busses/i2c-kempld.c     | 3 +--
 drivers/i2c/busses/i2c-mlxcpld.c    | 2 +-
 drivers/i2c/busses/i2c-nforce2.c    | 2 +-
 drivers/i2c/busses/i2c-pasemi-pci.c | 2 +-
 drivers/i2c/busses/i2c-piix4.c      | 2 +-
 drivers/i2c/busses/i2c-scmi.c       | 2 +-
 drivers/i2c/busses/i2c-sh7760.c     | 2 +-
 drivers/i2c/busses/i2c-sibyte.c     | 4 ++--
 drivers/i2c/busses/i2c-sis5595.c    | 2 +-
 drivers/i2c/busses/i2c-sis630.c     | 2 +-
 drivers/i2c/busses/i2c-sis96x.c     | 2 +-
 drivers/i2c/busses/i2c-via.c        | 2 +-
 drivers/i2c/busses/i2c-viapro.c     | 2 +-
 drivers/i2c/busses/scx200_acb.c     | 2 +-
 24 files changed, 25 insertions(+), 26 deletions(-)

diff --git a/drivers/i2c/busses/i2c-ali1535.c b/drivers/i2c/busses/i2c-ali1535.c
index ee83c4581bce0..461eb23f9d476 100644
--- a/drivers/i2c/busses/i2c-ali1535.c
+++ b/drivers/i2c/busses/i2c-ali1535.c
@@ -477,7 +477,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter ali1535_adapter = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-ali1563.c b/drivers/i2c/busses/i2c-ali1563.c
index 55a9e93fbfeb5..307fb0666ecb2 100644
--- a/drivers/i2c/busses/i2c-ali1563.c
+++ b/drivers/i2c/busses/i2c-ali1563.c
@@ -390,7 +390,7 @@ static const struct i2c_algorithm ali1563_algorithm = {
 
 static struct i2c_adapter ali1563_adapter = {
 	.owner	= THIS_MODULE,
-	.class	= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class	= I2C_CLASS_HWMON,
 	.algo	= &ali1563_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-ali15x3.c b/drivers/i2c/busses/i2c-ali15x3.c
index 0231c5be6354f..d2fa30deb054c 100644
--- a/drivers/i2c/busses/i2c-ali15x3.c
+++ b/drivers/i2c/busses/i2c-ali15x3.c
@@ -461,7 +461,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter ali15x3_adapter = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-amd756.c b/drivers/i2c/busses/i2c-amd756.c
index ef1307a258e95..208310db906df 100644
--- a/drivers/i2c/busses/i2c-amd756.c
+++ b/drivers/i2c/busses/i2c-amd756.c
@@ -285,7 +285,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 struct i2c_adapter amd756_smbus = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-amd8111.c b/drivers/i2c/busses/i2c-amd8111.c
index 1ed7e945bb6d1..42a9b1221065f 100644
--- a/drivers/i2c/busses/i2c-amd8111.c
+++ b/drivers/i2c/busses/i2c-amd8111.c
@@ -449,7 +449,7 @@ static int amd8111_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	smbus->adapter.owner = THIS_MODULE;
 	snprintf(smbus->adapter.name, sizeof(smbus->adapter.name),
 		"SMBus2 AMD8111 adapter at %04x", smbus->base);
-	smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	smbus->adapter.class = I2C_CLASS_HWMON;
 	smbus->adapter.algo = &smbus_algorithm;
 	smbus->adapter.algo_data = smbus;
 
diff --git a/drivers/i2c/busses/i2c-elektor.c b/drivers/i2c/busses/i2c-elektor.c
index b0f50dce9d0fe..cfe8665cacd27 100644
--- a/drivers/i2c/busses/i2c-elektor.c
+++ b/drivers/i2c/busses/i2c-elektor.c
@@ -188,7 +188,7 @@ static struct i2c_algo_pcf_data pcf_isa_data = {
 
 static struct i2c_adapter pcf_isa_ops = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo_data	= &pcf_isa_data,
 	.name		= "i2c-elektor",
 };
diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c
index fb35a75fe0e32..df2b183caa23a 100644
--- a/drivers/i2c/busses/i2c-gpio.c
+++ b/drivers/i2c/busses/i2c-gpio.c
@@ -444,7 +444,7 @@ static int i2c_gpio_probe(struct platform_device *pdev)
 		snprintf(adap->name, sizeof(adap->name), "i2c-gpio%d", pdev->id);
 
 	adap->algo_data = bit_data;
-	adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adap->class = I2C_CLASS_HWMON;
 	adap->dev.parent = dev;
 	device_set_node(&adap->dev, fwnode);
 
diff --git a/drivers/i2c/busses/i2c-ibm_iic.c b/drivers/i2c/busses/i2c-ibm_iic.c
index 408820319ec48..7fb87b78923e4 100644
--- a/drivers/i2c/busses/i2c-ibm_iic.c
+++ b/drivers/i2c/busses/i2c-ibm_iic.c
@@ -739,7 +739,7 @@ static int iic_probe(struct platform_device *ofdev)
 	adap->dev.of_node = of_node_get(np);
 	strscpy(adap->name, "IBM IIC", sizeof(adap->name));
 	i2c_set_adapdata(adap, dev);
-	adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adap->class = I2C_CLASS_HWMON;
 	adap->algo = &iic_algo;
 	adap->timeout = HZ;
 
diff --git a/drivers/i2c/busses/i2c-iop3xx.c b/drivers/i2c/busses/i2c-iop3xx.c
index f2f7ebeeaecb0..2e5f0165c3d30 100644
--- a/drivers/i2c/busses/i2c-iop3xx.c
+++ b/drivers/i2c/busses/i2c-iop3xx.c
@@ -478,7 +478,7 @@ iop3xx_i2c_probe(struct platform_device *pdev)
 
 	memcpy(new_adapter->name, pdev->name, strlen(pdev->name));
 	new_adapter->owner = THIS_MODULE;
-	new_adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	new_adapter->class = I2C_CLASS_HWMON;
 	new_adapter->dev.parent = &pdev->dev;
 	new_adapter->dev.of_node = pdev->dev.of_node;
 	new_adapter->nr = pdev->id;
diff --git a/drivers/i2c/busses/i2c-isch.c b/drivers/i2c/busses/i2c-isch.c
index 1dc1ceaa44439..416a9968ed287 100644
--- a/drivers/i2c/busses/i2c-isch.c
+++ b/drivers/i2c/busses/i2c-isch.c
@@ -249,7 +249,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter sch_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-kempld.c b/drivers/i2c/busses/i2c-kempld.c
index e01d753082884..c3a529a73b5bc 100644
--- a/drivers/i2c/busses/i2c-kempld.c
+++ b/drivers/i2c/busses/i2c-kempld.c
@@ -283,8 +283,7 @@ static const struct i2c_algorithm kempld_i2c_algorithm = {
 static const struct i2c_adapter kempld_i2c_adapter = {
 	.owner		= THIS_MODULE,
 	.name		= "i2c-kempld",
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD |
-			  I2C_CLASS_DEPRECATED,
+	.class		= I2C_CLASS_HWMON | I2C_CLASS_DEPRECATED,
 	.algo		= &kempld_i2c_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c
index 6fec64ea67fbc..099291a0411de 100644
--- a/drivers/i2c/busses/i2c-mlxcpld.c
+++ b/drivers/i2c/busses/i2c-mlxcpld.c
@@ -477,7 +477,7 @@ static const struct i2c_adapter_quirks mlxcpld_i2c_quirks_ext2 = {
 static struct i2c_adapter mlxcpld_i2c_adapter = {
 	.owner          = THIS_MODULE,
 	.name           = "i2c-mlxcpld",
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo           = &mlxcpld_i2c_algo,
 	.quirks		= &mlxcpld_i2c_quirks,
 	.retries	= MLXCPLD_I2C_RETR_NUM,
diff --git a/drivers/i2c/busses/i2c-nforce2.c b/drivers/i2c/busses/i2c-nforce2.c
index 38d203d93eeec..fab662e6bc084 100644
--- a/drivers/i2c/busses/i2c-nforce2.c
+++ b/drivers/i2c/busses/i2c-nforce2.c
@@ -349,7 +349,7 @@ static int nforce2_probe_smb(struct pci_dev *dev, int bar, int alt_reg,
 		return -EBUSY;
 	}
 	smbus->adapter.owner = THIS_MODULE;
-	smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	smbus->adapter.class = I2C_CLASS_HWMON;
 	smbus->adapter.algo = &smbus_algorithm;
 	smbus->adapter.algo_data = smbus;
 	smbus->adapter.dev.parent = &dev->dev;
diff --git a/drivers/i2c/busses/i2c-pasemi-pci.c b/drivers/i2c/busses/i2c-pasemi-pci.c
index cfc89e04eb94c..77f90c7436eda 100644
--- a/drivers/i2c/busses/i2c-pasemi-pci.c
+++ b/drivers/i2c/busses/i2c-pasemi-pci.c
@@ -56,7 +56,7 @@ static int pasemi_smb_pci_probe(struct pci_dev *dev,
 	if (!smbus->ioaddr)
 		return -EBUSY;
 
-	smbus->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	smbus->adapter.class = I2C_CLASS_HWMON;
 	error = pasemi_i2c_common_probe(smbus);
 	if (error)
 		return error;
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 809fbd014cd68..6a0392172b2f2 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -943,7 +943,7 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba,
 	}
 
 	adap->owner = THIS_MODULE;
-	adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adap->class = I2C_CLASS_HWMON;
 	adap->algo = sb800_main ? &piix4_smbus_algorithm_sb800
 				: &smbus_algorithm;
 
diff --git a/drivers/i2c/busses/i2c-scmi.c b/drivers/i2c/busses/i2c-scmi.c
index 421735acfa141..d7af8e0d7599e 100644
--- a/drivers/i2c/busses/i2c-scmi.c
+++ b/drivers/i2c/busses/i2c-scmi.c
@@ -385,7 +385,7 @@ static int smbus_cmi_probe(struct platform_device *device)
 	smbus_cmi->adapter.owner = THIS_MODULE;
 	smbus_cmi->adapter.algo = &acpi_smbus_cmi_algorithm;
 	smbus_cmi->adapter.algo_data = smbus_cmi;
-	smbus_cmi->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	smbus_cmi->adapter.class = I2C_CLASS_HWMON;
 	smbus_cmi->adapter.dev.parent = &device->dev;
 
 	ret = i2c_add_adapter(&smbus_cmi->adapter);
diff --git a/drivers/i2c/busses/i2c-sh7760.c b/drivers/i2c/busses/i2c-sh7760.c
index 1ad2a26156d17..8a043f5fca1e0 100644
--- a/drivers/i2c/busses/i2c-sh7760.c
+++ b/drivers/i2c/busses/i2c-sh7760.c
@@ -477,7 +477,7 @@ static int sh7760_i2c_probe(struct platform_device *pdev)
 
 	id->adap.nr = pdev->id;
 	id->adap.algo = &sh7760_i2c_algo;
-	id->adap.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	id->adap.class = I2C_CLASS_HWMON;
 	id->adap.retries = 3;
 	id->adap.algo_data = id;
 	id->adap.dev.parent = &pdev->dev;
diff --git a/drivers/i2c/busses/i2c-sibyte.c b/drivers/i2c/busses/i2c-sibyte.c
index 8f71f01cb169b..49f8f4f1b0f0f 100644
--- a/drivers/i2c/busses/i2c-sibyte.c
+++ b/drivers/i2c/busses/i2c-sibyte.c
@@ -142,7 +142,7 @@ static struct i2c_algo_sibyte_data sibyte_board_data[2] = {
 static struct i2c_adapter sibyte_board_adapter[2] = {
 	{
 		.owner		= THIS_MODULE,
-		.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+		.class		= I2C_CLASS_HWMON,
 		.algo		= NULL,
 		.algo_data	= &sibyte_board_data[0],
 		.nr		= 0,
@@ -150,7 +150,7 @@ static struct i2c_adapter sibyte_board_adapter[2] = {
 	},
 	{
 		.owner		= THIS_MODULE,
-		.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+		.class		= I2C_CLASS_HWMON,
 		.algo		= NULL,
 		.algo_data	= &sibyte_board_data[1],
 		.nr		= 1,
diff --git a/drivers/i2c/busses/i2c-sis5595.c b/drivers/i2c/busses/i2c-sis5595.c
index 486f1e9dfb74a..32476dc10ad61 100644
--- a/drivers/i2c/busses/i2c-sis5595.c
+++ b/drivers/i2c/busses/i2c-sis5595.c
@@ -353,7 +353,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter sis5595_adapter = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-sis630.c b/drivers/i2c/busses/i2c-sis630.c
index 87d56250d78a3..3505cf29cedda 100644
--- a/drivers/i2c/busses/i2c-sis630.c
+++ b/drivers/i2c/busses/i2c-sis630.c
@@ -493,7 +493,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter sis630_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 	.retries	= 3
 };
diff --git a/drivers/i2c/busses/i2c-sis96x.c b/drivers/i2c/busses/i2c-sis96x.c
index cde8003985a58..77529dda6fcde 100644
--- a/drivers/i2c/busses/i2c-sis96x.c
+++ b/drivers/i2c/busses/i2c-sis96x.c
@@ -228,7 +228,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter sis96x_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/i2c-via.c b/drivers/i2c/busses/i2c-via.c
index ad4f09c7f0275..7ed29992a97ff 100644
--- a/drivers/i2c/busses/i2c-via.c
+++ b/drivers/i2c/busses/i2c-via.c
@@ -70,7 +70,7 @@ static struct i2c_algo_bit_data bit_data = {
 
 static struct i2c_adapter vt586b_adapter = {
 	.owner		= THIS_MODULE,
-	.class          = I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class          = I2C_CLASS_HWMON,
 	.name		= "VIA i2c",
 	.algo_data	= &bit_data,
 };
diff --git a/drivers/i2c/busses/i2c-viapro.c b/drivers/i2c/busses/i2c-viapro.c
index 970ccdcbb8896..2cc7bba3b8bf8 100644
--- a/drivers/i2c/busses/i2c-viapro.c
+++ b/drivers/i2c/busses/i2c-viapro.c
@@ -304,7 +304,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter vt596_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 };
 
diff --git a/drivers/i2c/busses/scx200_acb.c b/drivers/i2c/busses/scx200_acb.c
index 83c1db610f54b..3648382b885a4 100644
--- a/drivers/i2c/busses/scx200_acb.c
+++ b/drivers/i2c/busses/scx200_acb.c
@@ -427,7 +427,7 @@ static struct scx200_acb_iface *scx200_create_iface(const char *text,
 	snprintf(adapter->name, sizeof(adapter->name), "%s ACB%d", text, index);
 	adapter->owner = THIS_MODULE;
 	adapter->algo = &scx200_acb_algorithm;
-	adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adapter->class = I2C_CLASS_HWMON;
 	adapter->dev.parent = dev;
 
 	mutex_init(&iface->mutex);
-- 
GitLab


From c1cc7ccb0ff7596a7025a844d29487df0efd40b2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 24 Nov 2023 11:16:14 +0100
Subject: [PATCH 2953/4076] i2c: stub: Don't let i2c adapters declare
 I2C_CLASS_SPD support if they support I2C_CLASS_HWMON

After removal of the legacy eeprom driver the only remaining I2C
client device driver supporting I2C_CLASS_SPD is jc42. Because this
driver also supports I2C_CLASS_HWMON, adapters don't have to
declare support for I2C_CLASS_SPD if they support I2C_CLASS_HWMON.
It's one step towards getting rid of I2C_CLASS_SPD mid-term.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-stub.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/i2c-stub.c b/drivers/i2c/i2c-stub.c
index d642cad219d9e..09e7b7bf4c5f7 100644
--- a/drivers/i2c/i2c-stub.c
+++ b/drivers/i2c/i2c-stub.c
@@ -308,7 +308,7 @@ static const struct i2c_algorithm smbus_algorithm = {
 
 static struct i2c_adapter stub_adapter = {
 	.owner		= THIS_MODULE,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &smbus_algorithm,
 	.name		= "SMBus stub driver",
 };
-- 
GitLab


From 8cd210d200ad00b29a8e0476ceef585bdca1d2a7 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 24 Nov 2023 11:16:17 +0100
Subject: [PATCH 2954/4076] media: netup_unidvb: Don't let i2c adapters declare
 I2C_CLASS_SPD support if they support I2C_CLASS_HWMON

After removal of the legacy eeprom driver the only remaining I2C
client device driver supporting I2C_CLASS_SPD is jc42. Because this
driver also supports I2C_CLASS_HWMON, adapters don't have to
declare support for I2C_CLASS_SPD if they support I2C_CLASS_HWMON.
It's one step towards getting rid of I2C_CLASS_SPD mid-term.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
index bd38ce4442325..46676f2c89c72 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
@@ -289,7 +289,7 @@ static const struct i2c_algorithm netup_i2c_algorithm = {
 static const struct i2c_adapter netup_i2c_adapter = {
 	.owner		= THIS_MODULE,
 	.name		= NETUP_UNIDVB_NAME,
-	.class		= I2C_CLASS_HWMON | I2C_CLASS_SPD,
+	.class		= I2C_CLASS_HWMON,
 	.algo		= &netup_i2c_algorithm,
 };
 
-- 
GitLab


From f79ad78a25841fdde6cd589969966fb113cf1d10 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 24 Nov 2023 11:16:11 +0100
Subject: [PATCH 2955/4076] staging: greybus: Don't let i2c adapters declare
 I2C_CLASS_SPD support if they support I2C_CLASS_HWMON

After removal of the legacy eeprom driver the only remaining I2C
client device driver supporting I2C_CLASS_SPD is jc42. Because this
driver also supports I2C_CLASS_HWMON, adapters don't have to
declare support for I2C_CLASS_SPD if they support I2C_CLASS_HWMON.
It's one step towards getting rid of I2C_CLASS_SPD mid-term.

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/staging/greybus/i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/greybus/i2c.c b/drivers/staging/greybus/i2c.c
index de2f6516da095..22325ab9d6521 100644
--- a/drivers/staging/greybus/i2c.c
+++ b/drivers/staging/greybus/i2c.c
@@ -264,7 +264,7 @@ static int gb_i2c_probe(struct gbphy_device *gbphy_dev,
 	/* Looks good; up our i2c adapter */
 	adapter = &gb_i2c_dev->adapter;
 	adapter->owner = THIS_MODULE;
-	adapter->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
+	adapter->class = I2C_CLASS_HWMON;
 	adapter->algo = &gb_i2c_algorithm;
 
 	adapter->dev.parent = &gbphy_dev->dev;
-- 
GitLab


From 73febd775bdbdb98c81255ff85773ac410ded5c4 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sun, 12 Nov 2023 17:54:41 -0500
Subject: [PATCH 2956/4076] i2c: create debugfs entry per adapter

Two drivers already implement custom debugfs handling for their
i2c_adapter and more will come. So, let the core create a debugfs
directory per adapter and pass that to drivers for their debugfs files.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-core-base.c | 11 +++++++++++
 include/linux/i2c.h         |  2 ++
 2 files changed, 13 insertions(+)

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index eac90a3cf61a4..f6c828bbd166a 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -16,6 +16,7 @@
 #include <linux/acpi.h>
 #include <linux/clk/clk-conf.h>
 #include <linux/completion.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -67,6 +68,8 @@ static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver);
 static DEFINE_STATIC_KEY_FALSE(i2c_trace_msg_key);
 static bool is_registered;
 
+static struct dentry *i2c_debugfs_root;
+
 int i2c_transfer_trace_reg(void)
 {
 	static_branch_inc(&i2c_trace_msg_key);
@@ -1524,6 +1527,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 		goto out_list;
 	}
 
+	adap->debugfs = debugfs_create_dir(dev_name(&adap->dev), i2c_debugfs_root);
+
 	res = i2c_setup_smbus_alert(adap);
 	if (res)
 		goto out_reg;
@@ -1563,6 +1568,7 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 	return 0;
 
 out_reg:
+	debugfs_remove_recursive(adap->debugfs);
 	init_completion(&adap->dev_released);
 	device_unregister(&adap->dev);
 	wait_for_completion(&adap->dev_released);
@@ -1764,6 +1770,8 @@ void i2c_del_adapter(struct i2c_adapter *adap)
 
 	i2c_host_notify_irq_teardown(adap);
 
+	debugfs_remove_recursive(adap->debugfs);
+
 	/* wait until all references to the device are gone
 	 *
 	 * FIXME: This is old code and should ideally be replaced by an
@@ -2061,6 +2069,8 @@ static int __init i2c_init(void)
 
 	is_registered = true;
 
+	i2c_debugfs_root = debugfs_create_dir("i2c", NULL);
+
 #ifdef CONFIG_I2C_COMPAT
 	i2c_adapter_compat_class = class_compat_register("i2c-adapter");
 	if (!i2c_adapter_compat_class) {
@@ -2099,6 +2109,7 @@ static void __exit i2c_exit(void)
 #ifdef CONFIG_I2C_COMPAT
 	class_compat_unregister(i2c_adapter_compat_class);
 #endif
+	debugfs_remove_recursive(i2c_debugfs_root);
 	bus_unregister(&i2c_bus_type);
 	tracepoint_synchronize_unregister();
 }
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index d029aade338fd..e01fb1097868c 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -746,6 +746,8 @@ struct i2c_adapter {
 
 	struct irq_domain *host_notify_domain;
 	struct regulator *bus_regulator;
+
+	struct dentry *debugfs;
 };
 #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev)
 
-- 
GitLab


From c66520c02c2f5b75e4f06a83ece4382fe2f92cfc Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sun, 12 Nov 2023 17:59:10 -0500
Subject: [PATCH 2957/4076] i2c: gpio: move to per-adapter debugfs directory

The I2C core now provides a per-adapter debugfs directory. Use it
instead of creating a custom one.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-gpio.c | 34 ++++++----------------------------
 1 file changed, 6 insertions(+), 28 deletions(-)

diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c
index df2b183caa23a..4f1411b1a7754 100644
--- a/drivers/i2c/busses/i2c-gpio.c
+++ b/drivers/i2c/busses/i2c-gpio.c
@@ -25,7 +25,6 @@ struct i2c_gpio_private_data {
 	struct i2c_algo_bit_data bit_data;
 	struct i2c_gpio_platform_data pdata;
 #ifdef CONFIG_I2C_GPIO_FAULT_INJECTOR
-	struct dentry *debug_dir;
 	/* these must be protected by bus lock */
 	struct completion scl_irq_completion;
 	u64 scl_irq_data;
@@ -72,7 +71,6 @@ static int i2c_gpio_getscl(void *data)
 }
 
 #ifdef CONFIG_I2C_GPIO_FAULT_INJECTOR
-static struct dentry *i2c_gpio_debug_dir;
 
 #define setsda(bd, val)	((bd)->setsda((bd)->data, val))
 #define setscl(bd, val)	((bd)->setscl((bd)->data, val))
@@ -258,41 +256,23 @@ static void i2c_gpio_fault_injector_init(struct platform_device *pdev)
 {
 	struct i2c_gpio_private_data *priv = platform_get_drvdata(pdev);
 
-	/*
-	 * If there will be a debugfs-dir per i2c adapter somewhen, put the
-	 * 'fault-injector' dir there. Until then, we have a global dir with
-	 * all adapters as subdirs.
-	 */
-	if (!i2c_gpio_debug_dir)
-		i2c_gpio_debug_dir = debugfs_create_dir("i2c-fault-injector", NULL);
-
-	priv->debug_dir = debugfs_create_dir(pdev->name, i2c_gpio_debug_dir);
-
 	init_completion(&priv->scl_irq_completion);
 
-	debugfs_create_file_unsafe("incomplete_address_phase", 0200, priv->debug_dir,
+	debugfs_create_file_unsafe("incomplete_address_phase", 0200, priv->adap.debugfs,
 				   priv, &fops_incomplete_addr_phase);
-	debugfs_create_file_unsafe("incomplete_write_byte", 0200, priv->debug_dir,
+	debugfs_create_file_unsafe("incomplete_write_byte", 0200, priv->adap.debugfs,
 				   priv, &fops_incomplete_write_byte);
 	if (priv->bit_data.getscl) {
-		debugfs_create_file_unsafe("inject_panic", 0200, priv->debug_dir,
+		debugfs_create_file_unsafe("inject_panic", 0200, priv->adap.debugfs,
 					   priv, &fops_inject_panic);
-		debugfs_create_file_unsafe("lose_arbitration", 0200, priv->debug_dir,
+		debugfs_create_file_unsafe("lose_arbitration", 0200, priv->adap.debugfs,
 					   priv, &fops_lose_arbitration);
 	}
-	debugfs_create_file_unsafe("scl", 0600, priv->debug_dir, priv, &fops_scl);
-	debugfs_create_file_unsafe("sda", 0600, priv->debug_dir, priv, &fops_sda);
-}
-
-static void i2c_gpio_fault_injector_exit(struct platform_device *pdev)
-{
-	struct i2c_gpio_private_data *priv = platform_get_drvdata(pdev);
-
-	debugfs_remove_recursive(priv->debug_dir);
+	debugfs_create_file_unsafe("scl", 0600, priv->adap.debugfs, priv, &fops_scl);
+	debugfs_create_file_unsafe("sda", 0600, priv->adap.debugfs, priv, &fops_sda);
 }
 #else
 static inline void i2c_gpio_fault_injector_init(struct platform_device *pdev) {}
-static inline void i2c_gpio_fault_injector_exit(struct platform_device *pdev) {}
 #endif /* CONFIG_I2C_GPIO_FAULT_INJECTOR*/
 
 /* Get i2c-gpio properties from DT or ACPI table */
@@ -475,8 +455,6 @@ static void i2c_gpio_remove(struct platform_device *pdev)
 	struct i2c_gpio_private_data *priv;
 	struct i2c_adapter *adap;
 
-	i2c_gpio_fault_injector_exit(pdev);
-
 	priv = platform_get_drvdata(pdev);
 	adap = &priv->adap;
 
-- 
GitLab


From e19e1abc9ce45f4d4cad2f7eab1827e683be4e84 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sun, 12 Nov 2023 17:59:11 -0500
Subject: [PATCH 2958/4076] i2c: npcm7xx: move to per-adapter debugfs directory

The I2C core now provides a per-adapter debugfs directory. Use it
instead of creating a custom one.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Tali Perry <tali.perry1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-npcm7xx.c | 49 +++++---------------------------
 1 file changed, 7 insertions(+), 42 deletions(-)

diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index ae4bae63ad4f3..54181b3f19196 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -326,7 +326,6 @@ struct npcm_i2c {
 	u8 slv_rd_buf[MAX_I2C_HW_FIFO_SIZE];
 	u8 slv_wr_buf[MAX_I2C_HW_FIFO_SIZE];
 #endif
-	struct dentry *debugfs; /* debugfs device directory */
 	u64 ber_cnt;
 	u64 rec_succ_cnt;
 	u64 rec_fail_cnt;
@@ -2250,27 +2249,15 @@ static const struct i2c_algorithm npcm_i2c_algo = {
 #endif
 };
 
-/* i2c debugfs directory: used to keep health monitor of i2c devices */
-static struct dentry *npcm_i2c_debugfs_dir;
-
 static void npcm_i2c_init_debugfs(struct platform_device *pdev,
 				  struct npcm_i2c *bus)
 {
-	struct dentry *d;
-
-	if (!npcm_i2c_debugfs_dir)
-		return;
-	d = debugfs_create_dir(dev_name(&pdev->dev), npcm_i2c_debugfs_dir);
-	if (IS_ERR_OR_NULL(d))
-		return;
-	debugfs_create_u64("ber_cnt", 0444, d, &bus->ber_cnt);
-	debugfs_create_u64("nack_cnt", 0444, d, &bus->nack_cnt);
-	debugfs_create_u64("rec_succ_cnt", 0444, d, &bus->rec_succ_cnt);
-	debugfs_create_u64("rec_fail_cnt", 0444, d, &bus->rec_fail_cnt);
-	debugfs_create_u64("timeout_cnt", 0444, d, &bus->timeout_cnt);
-	debugfs_create_u64("tx_complete_cnt", 0444, d, &bus->tx_complete_cnt);
-
-	bus->debugfs = d;
+	debugfs_create_u64("ber_cnt", 0444, bus->adap.debugfs, &bus->ber_cnt);
+	debugfs_create_u64("nack_cnt", 0444, bus->adap.debugfs, &bus->nack_cnt);
+	debugfs_create_u64("rec_succ_cnt", 0444, bus->adap.debugfs, &bus->rec_succ_cnt);
+	debugfs_create_u64("rec_fail_cnt", 0444, bus->adap.debugfs, &bus->rec_fail_cnt);
+	debugfs_create_u64("timeout_cnt", 0444, bus->adap.debugfs, &bus->timeout_cnt);
+	debugfs_create_u64("tx_complete_cnt", 0444, bus->adap.debugfs, &bus->tx_complete_cnt);
 }
 
 static int npcm_i2c_probe_bus(struct platform_device *pdev)
@@ -2362,7 +2349,6 @@ static void npcm_i2c_remove_bus(struct platform_device *pdev)
 	unsigned long lock_flags;
 	struct npcm_i2c *bus = platform_get_drvdata(pdev);
 
-	debugfs_remove_recursive(bus->debugfs);
 	spin_lock_irqsave(&bus->lock, lock_flags);
 	npcm_i2c_disable(bus);
 	spin_unlock_irqrestore(&bus->lock, lock_flags);
@@ -2385,28 +2371,7 @@ static struct platform_driver npcm_i2c_bus_driver = {
 	}
 };
 
-static int __init npcm_i2c_init(void)
-{
-	int ret;
-
-	npcm_i2c_debugfs_dir = debugfs_create_dir("npcm_i2c", NULL);
-
-	ret = platform_driver_register(&npcm_i2c_bus_driver);
-	if (ret) {
-		debugfs_remove_recursive(npcm_i2c_debugfs_dir);
-		return ret;
-	}
-
-	return 0;
-}
-module_init(npcm_i2c_init);
-
-static void __exit npcm_i2c_exit(void)
-{
-	platform_driver_unregister(&npcm_i2c_bus_driver);
-	debugfs_remove_recursive(npcm_i2c_debugfs_dir);
-}
-module_exit(npcm_i2c_exit);
+module_platform_driver(npcm_i2c_bus_driver);
 
 MODULE_AUTHOR("Avi Fishman <avi.fishman@gmail.com>");
 MODULE_AUTHOR("Tali Perry <tali.perry@nuvoton.com>");
-- 
GitLab


From 2b523c46e81ebd621515ab47117f95de197dfcbf Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 14 Dec 2023 08:43:57 +0100
Subject: [PATCH 2959/4076] i2c: rcar: introduce Gen4 devices

So far, we treated Gen4 as Gen3. But we are soon adding FM+ as a Gen4
specific feature, so prepare the code for the new devtype.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-rcar.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 829ac053bbb7c..973811a6c27ba 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -132,6 +132,7 @@ enum rcar_i2c_type {
 	I2C_RCAR_GEN1,
 	I2C_RCAR_GEN2,
 	I2C_RCAR_GEN3,
+	I2C_RCAR_GEN4,
 };
 
 struct rcar_i2c_priv {
@@ -431,8 +432,8 @@ static void rcar_i2c_cleanup_dma(struct rcar_i2c_priv *priv, bool terminate)
 	dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg),
 			 sg_dma_len(&priv->sg), priv->dma_direction);
 
-	/* Gen3 can only do one RXDMA per transfer and we just completed it */
-	if (priv->devtype == I2C_RCAR_GEN3 &&
+	/* Gen3+ can only do one RXDMA per transfer and we just completed it */
+	if (priv->devtype >= I2C_RCAR_GEN3 &&
 	    priv->dma_direction == DMA_FROM_DEVICE)
 		priv->flags |= ID_P_NO_RXDMA;
 
@@ -886,8 +887,8 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 	if (ret < 0)
 		goto out;
 
-	/* Gen3 needs a reset before allowing RXDMA once */
-	if (priv->devtype == I2C_RCAR_GEN3) {
+	/* Gen3+ needs a reset. That also allows RXDMA once */
+	if (priv->devtype >= I2C_RCAR_GEN3) {
 		priv->flags &= ~ID_P_NO_RXDMA;
 		ret = rcar_i2c_do_reset(priv);
 		if (ret)
@@ -1075,7 +1076,7 @@ static const struct of_device_id rcar_i2c_dt_ids[] = {
 	{ .compatible = "renesas,rcar-gen1-i2c", .data = (void *)I2C_RCAR_GEN1 },
 	{ .compatible = "renesas,rcar-gen2-i2c", .data = (void *)I2C_RCAR_GEN2 },
 	{ .compatible = "renesas,rcar-gen3-i2c", .data = (void *)I2C_RCAR_GEN3 },
-	{ .compatible = "renesas,rcar-gen4-i2c", .data = (void *)I2C_RCAR_GEN3 },
+	{ .compatible = "renesas,rcar-gen4-i2c", .data = (void *)I2C_RCAR_GEN4 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, rcar_i2c_dt_ids);
@@ -1151,7 +1152,7 @@ static int rcar_i2c_probe(struct platform_device *pdev)
 	if (of_property_read_bool(dev->of_node, "smbus"))
 		priv->flags |= ID_P_HOST_NOTIFY;
 
-	if (priv->devtype == I2C_RCAR_GEN3) {
+	if (priv->devtype >= I2C_RCAR_GEN3) {
 		priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
 		if (IS_ERR(priv->rstc)) {
 			ret = PTR_ERR(priv->rstc);
-- 
GitLab


From d0520eb3ed54df89eb5961ec3b88634f313123f2 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 14 Dec 2023 08:43:58 +0100
Subject: [PATCH 2960/4076] i2c: rcar: add FastMode+ support for Gen4

To support FM+, we mainly need to turn the SMD constant into a parameter
and set it accordingly. That also means we can finally fix SMD to our
needs instead of bailing out. A sanity check for SMD then becomes a
sanity check for 'x == 0'. After all that, activating the enable bit for
FM+ is all we need to do. Tested with a Renesas Falcon board using R-Car
V3U.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-rcar.c | 38 +++++++++++++++++++++++++----------
 1 file changed, 27 insertions(+), 11 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 973811a6c27ba..828aa2ea0fe4c 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -89,6 +89,7 @@
 #define TMDMAE	BIT(0)	/* DMA Master Transmitted Enable */
 
 /* ICCCR2 */
+#define FMPE	BIT(7)	/* Fast Mode Plus Enable */
 #define CDFD	BIT(2)	/* CDF Disable */
 #define HLSE	BIT(1)	/* HIGH/LOW Separate Control Enable */
 #define SME	BIT(0)	/* SCL Mask Enable */
@@ -122,11 +123,12 @@
 #define ID_NACK			BIT(4)
 #define ID_EPROTO		BIT(5)
 /* persistent flags */
+#define ID_P_FMPLUS		BIT(27)
 #define ID_P_NOT_ATOMIC		BIT(28)
 #define ID_P_HOST_NOTIFY	BIT(29)
 #define ID_P_NO_RXDMA		BIT(30) /* HW forbids RXDMA sometimes */
 #define ID_P_PM_BLOCKED		BIT(31)
-#define ID_P_MASK		GENMASK(31, 28)
+#define ID_P_MASK		GENMASK(31, 27)
 
 enum rcar_i2c_type {
 	I2C_RCAR_GEN1,
@@ -149,6 +151,7 @@ struct rcar_i2c_priv {
 	u32 icccr;
 	u16 schd;
 	u16 scld;
+	u8 smd;
 	u8 recovery_icmcr;	/* protected by adapter lock */
 	enum rcar_i2c_type devtype;
 	struct i2c_client *slave;
@@ -240,9 +243,14 @@ static void rcar_i2c_init(struct rcar_i2c_priv *priv)
 	if (priv->devtype < I2C_RCAR_GEN3) {
 		rcar_i2c_write(priv, ICCCR, priv->icccr);
 	} else {
-		rcar_i2c_write(priv, ICCCR2, CDFD | HLSE | SME);
+		u32 icccr2 = CDFD | HLSE | SME;
+
+		if (priv->flags & ID_P_FMPLUS)
+			icccr2 |= FMPE;
+
+		rcar_i2c_write(priv, ICCCR2, icccr2);
 		rcar_i2c_write(priv, ICCCR, priv->icccr);
-		rcar_i2c_write(priv, ICMPR, RCAR_DEFAULT_SMD);
+		rcar_i2c_write(priv, ICMPR, priv->smd);
 		rcar_i2c_write(priv, ICHPR, priv->schd);
 		rcar_i2c_write(priv, ICLPR, priv->scld);
 		rcar_i2c_write(priv, ICFBSCR, TCYC17);
@@ -279,6 +287,7 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv)
 
 	/* Fall back to previously used values if not supplied */
 	i2c_parse_fw_timings(dev, &t, false);
+	priv->smd = RCAR_DEFAULT_SMD;
 
 	/*
 	 * calculate SCL clock
@@ -304,6 +313,11 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv)
 	if (cdf >= 1U << cdf_width)
 		goto err_no_val;
 
+	if (t.bus_freq_hz > I2C_MAX_FAST_MODE_FREQ && priv->devtype >= I2C_RCAR_GEN4)
+		priv->flags |= ID_P_FMPLUS;
+	else
+		priv->flags &= ~ID_P_FMPLUS;
+
 	/* On Gen3+, we use cdf only for the filters, not as a SCL divider */
 	ick = rate / (priv->devtype < I2C_RCAR_GEN3 ? (cdf + 1) : 1);
 
@@ -345,30 +359,30 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv)
 		 * x as a base value for the SCLD/SCHD ratio:
 		 *
 		 * SCL = clkp / (8 + 2 * SMD + SCLD + SCHD + F[(ticf + tr + intd) * clkp])
-		 * SCL = clkp / (8 + 2 * RCAR_DEFAULT_SMD + RCAR_SCLD_RATIO * x
+		 * SCL = clkp / (8 + 2 * SMD + RCAR_SCLD_RATIO * x
 		 *		 + RCAR_SCHD_RATIO * x + F[...])
 		 *
 		 * with: sum_ratio = RCAR_SCLD_RATIO + RCAR_SCHD_RATIO
-		 * and:  smd = RCAR_DEFAULT_SMD
 		 *
 		 * SCL = clkp / (8 + 2 * smd + sum_ratio * x + F[...])
 		 * 8 + 2 * smd + sum_ratio * x + F[...] = clkp / SCL
 		 * x = ((clkp / SCL) - 8 - 2 * smd - F[...]) / sum_ratio
 		 */
 		x = DIV_ROUND_UP(rate, t.bus_freq_hz ?: 1);
-		x = DIV_ROUND_UP(x - 8 - 2 * RCAR_DEFAULT_SMD - round, sum_ratio);
-		scl = rate / (8 + 2 * RCAR_DEFAULT_SMD + sum_ratio * x + round);
+		x = DIV_ROUND_UP(x - 8 - 2 * priv->smd - round, sum_ratio);
+		scl = rate / (8 + 2 * priv->smd + sum_ratio * x + round);
 
-		/* Bail out if values don't fit into 16 bit or SMD became too large */
-		if (x * RCAR_SCLD_RATIO > 0xffff || RCAR_DEFAULT_SMD > x * RCAR_SCHD_RATIO)
+		if (x == 0 || x * RCAR_SCLD_RATIO > 0xffff)
 			goto err_no_val;
 
 		priv->icccr = cdf;
 		priv->schd = RCAR_SCHD_RATIO * x;
 		priv->scld = RCAR_SCLD_RATIO * x;
+		if (priv->smd >= priv->schd)
+			priv->smd = priv->schd - 1;
 
-		dev_dbg(dev, "clk %u/%u(%lu), round %u, CDF: %u SCHD %u SCLD %u\n",
-			scl, t.bus_freq_hz, rate, round, cdf, priv->schd, priv->scld);
+		dev_dbg(dev, "clk %u/%u(%lu), round %u, CDF: %u SCHD %u SCLD %u SMD %u\n",
+			scl, t.bus_freq_hz, rate, round, cdf, priv->schd, priv->scld, priv->smd);
 	}
 
 	return 0;
@@ -1073,6 +1087,8 @@ static const struct of_device_id rcar_i2c_dt_ids[] = {
 	{ .compatible = "renesas,i2c-r8a7794", .data = (void *)I2C_RCAR_GEN2 },
 	{ .compatible = "renesas,i2c-r8a7795", .data = (void *)I2C_RCAR_GEN3 },
 	{ .compatible = "renesas,i2c-r8a7796", .data = (void *)I2C_RCAR_GEN3 },
+	/* S4 has no FM+ bit */
+	{ .compatible = "renesas,i2c-r8a779f0", .data = (void *)I2C_RCAR_GEN3 },
 	{ .compatible = "renesas,rcar-gen1-i2c", .data = (void *)I2C_RCAR_GEN1 },
 	{ .compatible = "renesas,rcar-gen2-i2c", .data = (void *)I2C_RCAR_GEN2 },
 	{ .compatible = "renesas,rcar-gen3-i2c", .data = (void *)I2C_RCAR_GEN3 },
-- 
GitLab


From 0d9cf23ed55d7ba3ab26d617a3ae507863674c8f Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Wed, 8 Nov 2023 17:43:52 +0100
Subject: [PATCH 2961/4076] i2c: s3c24xx: fix read transfers in polling mode

To properly handle read transfers in polling mode, no waiting for the ACK
state is needed as it will never come. Just wait a bit to ensure start
state is on the bus and continue processing next bytes.

Fixes: 117053f77a5a ("i2c: s3c2410: Add polling mode support")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Chanho Park <chanho61.park@samsung.com>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-s3c2410.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index c56886af724ea..bf9a5670ef337 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -216,8 +216,17 @@ static bool is_ack(struct s3c24xx_i2c *i2c)
 	int tries;
 
 	for (tries = 50; tries; --tries) {
-		if (readl(i2c->regs + S3C2410_IICCON)
-			& S3C2410_IICCON_IRQPEND) {
+		unsigned long tmp = readl(i2c->regs + S3C2410_IICCON);
+
+		if (!(tmp & S3C2410_IICCON_ACKEN)) {
+			/*
+			 * Wait a bit for the bus to stabilize,
+			 * delay estimated experimentally.
+			 */
+			usleep_range(100, 200);
+			return true;
+		}
+		if (tmp & S3C2410_IICCON_IRQPEND) {
 			if (!(readl(i2c->regs + S3C2410_IICSTAT)
 				& S3C2410_IICSTAT_LASTBIT))
 				return true;
-- 
GitLab


From 990489e1042c6c5d6bccf56deca68f8dbeed8180 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Wed, 8 Nov 2023 17:43:53 +0100
Subject: [PATCH 2962/4076] i2c: s3c24xx: fix transferring more than one
 message in polling mode

To properly handle ACK on the bus when transferring more than one
message in polling mode, move the polling handling loop from
s3c24xx_i2c_message_start() to s3c24xx_i2c_doxfer(). This way
i2c_s3c_irq_nextbyte() is always executed till the end, properly
acknowledging the IRQ bits and no recursive calls to
i2c_s3c_irq_nextbyte() are made.

While touching this, also fix finishing transfers in polling mode by
using common code path and always waiting for the bus to become idle
and disabled.

Fixes: 117053f77a5a ("i2c: s3c2410: Add polling mode support")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-s3c2410.c | 27 ++++++++++-----------------
 1 file changed, 10 insertions(+), 17 deletions(-)

diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index bf9a5670ef337..c0fe96a4f2c4f 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -279,16 +279,6 @@ static void s3c24xx_i2c_message_start(struct s3c24xx_i2c *i2c,
 
 	stat |= S3C2410_IICSTAT_START;
 	writel(stat, i2c->regs + S3C2410_IICSTAT);
-
-	if (i2c->quirks & QUIRK_POLL) {
-		while ((i2c->msg_num != 0) && is_ack(i2c)) {
-			i2c_s3c_irq_nextbyte(i2c, stat);
-			stat = readl(i2c->regs + S3C2410_IICSTAT);
-
-			if (stat & S3C2410_IICSTAT_ARBITR)
-				dev_err(i2c->dev, "deal with arbitration loss\n");
-		}
-	}
 }
 
 static inline void s3c24xx_i2c_stop(struct s3c24xx_i2c *i2c, int ret)
@@ -694,7 +684,7 @@ static void s3c24xx_i2c_wait_idle(struct s3c24xx_i2c *i2c)
 static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c,
 			      struct i2c_msg *msgs, int num)
 {
-	unsigned long timeout;
+	unsigned long timeout = 0;
 	int ret;
 
 	ret = s3c24xx_i2c_set_master(i2c);
@@ -714,16 +704,19 @@ static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c,
 	s3c24xx_i2c_message_start(i2c, msgs);
 
 	if (i2c->quirks & QUIRK_POLL) {
-		ret = i2c->msg_idx;
+		while ((i2c->msg_num != 0) && is_ack(i2c)) {
+			unsigned long stat = readl(i2c->regs + S3C2410_IICSTAT);
 
-		if (ret != num)
-			dev_dbg(i2c->dev, "incomplete xfer (%d)\n", ret);
+			i2c_s3c_irq_nextbyte(i2c, stat);
 
-		goto out;
+			stat = readl(i2c->regs + S3C2410_IICSTAT);
+			if (stat & S3C2410_IICSTAT_ARBITR)
+				dev_err(i2c->dev, "deal with arbitration loss\n");
+		}
+	} else {
+		timeout = wait_event_timeout(i2c->wait, i2c->msg_num == 0, HZ * 5);
 	}
 
-	timeout = wait_event_timeout(i2c->wait, i2c->msg_num == 0, HZ * 5);
-
 	ret = i2c->msg_idx;
 
 	/*
-- 
GitLab


From 187432b82173c86e0450d0e3d516b415ab2455f8 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Wed, 8 Nov 2023 17:43:54 +0100
Subject: [PATCH 2963/4076] i2c: s3c24xx: add support for atomic transfers

Add support for atomic transfers using polling mode with interrupts
intentionally disabled to get rid of the following warning introduced by
commit 63b96983a5dd ("i2c: core: introduce callbacks for atomic
transfers") during system reboot and power-off:

------------[ cut here ]------------
WARNING: CPU: 0 PID: 1518 at drivers/i2c/i2c-core.h:40 i2c_transfer+0xe8/0xf4
No atomic I2C transfer handler for 'i2c-0'
...
---[ end trace 0000000000000000 ]---

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Chanho Park <chanho61.park@samsung.com>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-s3c2410.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index c0fe96a4f2c4f..275f7c42165cd 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -76,6 +76,7 @@
 #define QUIRK_HDMIPHY		(1 << 1)
 #define QUIRK_NO_GPIO		(1 << 2)
 #define QUIRK_POLL		(1 << 3)
+#define QUIRK_ATOMIC		(1 << 4)
 
 /* Max time to wait for bus to become idle after a xfer (in us) */
 #define S3C2410_IDLE_TIMEOUT	5000
@@ -174,7 +175,7 @@ static inline void s3c24xx_i2c_master_complete(struct s3c24xx_i2c *i2c, int ret)
 	if (ret)
 		i2c->msg_idx = ret;
 
-	if (!(i2c->quirks & QUIRK_POLL))
+	if (!(i2c->quirks & (QUIRK_POLL | QUIRK_ATOMIC)))
 		wake_up(&i2c->wait);
 }
 
@@ -703,7 +704,7 @@ static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c,
 	s3c24xx_i2c_enable_irq(i2c);
 	s3c24xx_i2c_message_start(i2c, msgs);
 
-	if (i2c->quirks & QUIRK_POLL) {
+	if (i2c->quirks & (QUIRK_POLL | QUIRK_ATOMIC)) {
 		while ((i2c->msg_num != 0) && is_ack(i2c)) {
 			unsigned long stat = readl(i2c->regs + S3C2410_IICSTAT);
 
@@ -775,6 +776,21 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap,
 	return -EREMOTEIO;
 }
 
+static int s3c24xx_i2c_xfer_atomic(struct i2c_adapter *adap,
+				   struct i2c_msg *msgs, int num)
+{
+	struct s3c24xx_i2c *i2c = (struct s3c24xx_i2c *)adap->algo_data;
+	int ret;
+
+	disable_irq(i2c->irq);
+	i2c->quirks |= QUIRK_ATOMIC;
+	ret = s3c24xx_i2c_xfer(adap, msgs, num);
+	i2c->quirks &= ~QUIRK_ATOMIC;
+	enable_irq(i2c->irq);
+
+	return ret;
+}
+
 /* declare our i2c functionality */
 static u32 s3c24xx_i2c_func(struct i2c_adapter *adap)
 {
@@ -785,6 +801,7 @@ static u32 s3c24xx_i2c_func(struct i2c_adapter *adap)
 /* i2c bus registration info */
 static const struct i2c_algorithm s3c24xx_i2c_algorithm = {
 	.master_xfer		= s3c24xx_i2c_xfer,
+	.master_xfer_atomic     = s3c24xx_i2c_xfer_atomic,
 	.functionality		= s3c24xx_i2c_func,
 };
 
-- 
GitLab


From 92a85b7c6262f19c65a1c115cf15f411ba65a57c Mon Sep 17 00:00:00 2001
From: Tim Lunn <tim@feathertop.org>
Date: Sun, 3 Dec 2023 23:39:59 +1100
Subject: [PATCH 2964/4076] i2c: rk3x: Adjust mask/value offset for i2c2 on
 rv1126

Rockchip RV1126 is using old style i2c controller, the i2c2
bus uses a non-sequential offset in the grf register for the
mask/value bits for this bus.

This patch fixes i2c2 bus on rv1126 SoCs.

Signed-off-by: Tim Lunn <tim@feathertop.org>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-rk3x.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index a044ca0c35a19..06fec2344575d 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -1288,8 +1288,12 @@ static int rk3x_i2c_probe(struct platform_device *pdev)
 			return -EINVAL;
 		}
 
-		/* 27+i: write mask, 11+i: value */
-		value = BIT(27 + bus_nr) | BIT(11 + bus_nr);
+		/* rv1126 i2c2 uses non-sequential write mask 20, value 4 */
+		if (i2c->soc_data == &rv1126_soc_data && bus_nr == 2)
+			value = BIT(20) | BIT(4);
+		else
+			/* 27+i: write mask, 11+i: value */
+			value = BIT(27 + bus_nr) | BIT(11 + bus_nr);
 
 		ret = regmap_write(grf, i2c->soc_data->grf_offset, value);
 		if (ret != 0) {
-- 
GitLab


From 13e3a512a29001cab68fe9a0c12be94e6d42a10c Mon Sep 17 00:00:00 2001
From: Jean Delvare <jdelvare@suse.de>
Date: Tue, 14 Nov 2023 15:13:28 +0100
Subject: [PATCH 2965/4076] i2c: smbus: Support up to 8 SPD EEPROMs

I originally restricted i2c_register_spd() to only support systems
with up to 4 memory slots, so that we can experiment with it on
a limited numbers of systems. It's been more than 3 years and it
seems to work just fine, so the time has come to lift this arbitrary
limitation.

The maximum number of memory slots which can be connected to a single
I2C segment is 8, so support that many SPD EEPROMs. Any system with
more than 8 memory slots would have either multiple SMBus channels
or SMBus multiplexing, so it would need dedicated care. We'll get to
that later as needed.

Signed-off-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-smbus.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c
index 138c3f5e0093a..74807c6db596d 100644
--- a/drivers/i2c/i2c-smbus.c
+++ b/drivers/i2c/i2c-smbus.c
@@ -308,8 +308,8 @@ EXPORT_SYMBOL_GPL(i2c_free_slave_host_notify_device);
  * target systems are the same.
  * Restrictions to automatic SPD instantiation:
  *  - Only works if all filled slots have the same memory type
- *  - Only works for DDR2, DDR3 and DDR4 for now
- *  - Only works on systems with 1 to 4 memory slots
+ *  - Only works for DDR, DDR2, DDR3 and DDR4 for now
+ *  - Only works on systems with 1 to 8 memory slots
  */
 #if IS_ENABLED(CONFIG_DMI)
 void i2c_register_spd(struct i2c_adapter *adap)
@@ -354,9 +354,9 @@ void i2c_register_spd(struct i2c_adapter *adap)
 	dev_info(&adap->dev, "%d/%d memory slots populated (from DMI)\n",
 		 dimm_count, slot_count);
 
-	if (slot_count > 4) {
+	if (slot_count > 8) {
 		dev_warn(&adap->dev,
-			 "Systems with more than 4 memory slots not supported yet, not instantiating SPD\n");
+			 "Systems with more than 8 memory slots not supported yet, not instantiating SPD\n");
 		return;
 	}
 
-- 
GitLab


From db63eacdf61d6bbcde783f15aaafbd8e66476e9a Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Thu, 30 Nov 2023 10:57:51 +0100
Subject: [PATCH 2966/4076] i2c: imx: Make SDA actually optional for bus
 recovering

Both i2c_generic_scl_recovery() and the debug output indicate that SDA is
purely optional for bus recovery. But devm_gpiod_get() never returns NULL
making it mandatory. Fix this by calling devm_gpiod_get_optional instead.

Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-imx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 1775a79aeba2a..88a053987403c 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1401,7 +1401,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx,
 			PINCTRL_STATE_DEFAULT);
 	i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl,
 			"gpio");
-	rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN);
+	rinfo->sda_gpiod = devm_gpiod_get_optional(&pdev->dev, "sda", GPIOD_IN);
 	rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
 
 	if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER ||
-- 
GitLab


From e535af5c4225fe2715d12322b645853ab9724648 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Wed, 6 Dec 2023 23:24:03 +0100
Subject: [PATCH 2967/4076] i2c: cpm: Remove linux,i2c-index conversion from
 be32

sparse reports an error on some data that gets converted from be32.

That's because that data is typed u32 instead of __be32.

The type is correct, the be32_to_cpu() conversion is not.

Remove the conversion.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312042210.QL4DA8Av-lkp@intel.com/
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-By: Jochen Friedrich <jochen@scram.de>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-cpm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c
index 9a664abf734d6..4404b4aac6765 100644
--- a/drivers/i2c/busses/i2c-cpm.c
+++ b/drivers/i2c/busses/i2c-cpm.c
@@ -658,7 +658,7 @@ static int cpm_i2c_probe(struct platform_device *ofdev)
 	/* register new adapter to i2c module... */
 
 	data = of_get_property(ofdev->dev.of_node, "linux,i2c-index", &len);
-	cpm->adap.nr = (data && len == 4) ? be32_to_cpup(data) : -1;
+	cpm->adap.nr = (data && len == 4) ? *data : -1;
 	result = i2c_add_numbered_adapter(&cpm->adap);
 
 	if (result < 0)
-- 
GitLab


From 2b0eee4f6add17a74f696a6f40ad2a4fa173613e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Thu, 23 Nov 2023 11:30:32 +0100
Subject: [PATCH 2968/4076] eeprom: at24: use of_match_ptr()

This driver does not depend on CONFIG_OF so using of_match_ptr() makes
sense to reduce the size a bit.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/misc/eeprom/at24.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index f61a80597a22d..8279adade07e8 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/nvmem-provider.h>
+#include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
@@ -242,7 +243,7 @@ static const struct i2c_device_id at24_ids[] = {
 };
 MODULE_DEVICE_TABLE(i2c, at24_ids);
 
-static const struct of_device_id at24_of_match[] = {
+static const struct of_device_id __maybe_unused at24_of_match[] = {
 	{ .compatible = "atmel,24c00",		.data = &at24_data_24c00 },
 	{ .compatible = "atmel,24c01",		.data = &at24_data_24c01 },
 	{ .compatible = "atmel,24cs01",		.data = &at24_data_24cs01 },
@@ -812,7 +813,7 @@ static struct i2c_driver at24_driver = {
 	.driver = {
 		.name = "at24",
 		.pm = &at24_pm_ops,
-		.of_match_table = at24_of_match,
+		.of_match_table = of_match_ptr(at24_of_match),
 		.acpi_match_table = ACPI_PTR(at24_acpi_ids),
 	},
 	.probe = at24_probe,
-- 
GitLab


From 614ef4d30fe724ff8558a74a1926bd3051d39b67 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Mon, 27 Nov 2023 22:11:02 +0100
Subject: [PATCH 2969/4076] dt-bindings: at24: add ROHM BR24G04

Add compatible for ROHM Semiconductor BR24G04 EEPROMs.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Roland Hieber <rhi@pengutronix.de>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 Documentation/devicetree/bindings/eeprom/at24.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml
index b6864d0ee81e4..1812ef31d5f1e 100644
--- a/Documentation/devicetree/bindings/eeprom/at24.yaml
+++ b/Documentation/devicetree/bindings/eeprom/at24.yaml
@@ -123,6 +123,7 @@ properties:
           - enum:
               - onnn,cat24c04
               - onnn,cat24c05
+              - rohm,br24g04
           - const: atmel,24c04
       - items:
           - const: renesas,r1ex24016
-- 
GitLab


From 94959c0e796e41128483588d133b9a7003b409f9 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 16:22:43 +0100
Subject: [PATCH 2970/4076] i2c: make i2c_bus_type const

Now that the driver core can properly handle constant struct bus_type,
move the i2c_bus_type variable to be a constant structure as well, placing
it into read-only memory which can not be modified at runtime.

Note, the sound/soc/rockchip/rk3399_gru_sound.c also needed tweaking as
it decided to save off a pointer to a bus type for internal stuff, and
it was using the i2c_bus_type as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-core-base.c           | 2 +-
 include/linux/i2c.h                   | 2 +-
 sound/soc/rockchip/rk3399_gru_sound.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index f6c828bbd166a..3bd48d4b6318f 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -692,7 +692,7 @@ static struct attribute *i2c_dev_attrs[] = {
 };
 ATTRIBUTE_GROUPS(i2c_dev);
 
-struct bus_type i2c_bus_type = {
+const struct bus_type i2c_bus_type = {
 	.name		= "i2c",
 	.match		= i2c_device_match,
 	.probe		= i2c_device_probe,
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index e01fb1097868c..652ecb7abedae 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -23,7 +23,7 @@
 #include <linux/swab.h>		/* for swab16 */
 #include <uapi/linux/i2c.h>
 
-extern struct bus_type i2c_bus_type;
+extern const struct bus_type i2c_bus_type;
 extern struct device_type i2c_adapter_type;
 extern struct device_type i2c_client_type;
 
diff --git a/sound/soc/rockchip/rk3399_gru_sound.c b/sound/soc/rockchip/rk3399_gru_sound.c
index 1a504ebd3a0e9..6c89c7331229f 100644
--- a/sound/soc/rockchip/rk3399_gru_sound.c
+++ b/sound/soc/rockchip/rk3399_gru_sound.c
@@ -446,7 +446,7 @@ static const struct rockchip_sound_route rockchip_routes[] = {
 
 struct dailink_match_data {
 	const char *compatible;
-	struct bus_type *bus_type;
+	const struct bus_type *bus_type;
 };
 
 static const struct dailink_match_data dailink_match[] = {
-- 
GitLab


From a8355235dbd571b32c750ee756dd6dac216d18f2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 8 Nov 2023 07:38:07 +0100
Subject: [PATCH 2971/4076] i2c: mux: reg: Remove class-based device
 auto-detection support

Legacy class-based device auto-detection shouldn't be used in new code.
Therefore remove support in i2c-mux-reg as long as we don't have a
user of this feature yet.

Link: https://lore.kernel.org/linux-i2c/a22978a4-88e4-46f4-b71c-032b22321599@gmail.com/
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/muxes/i2c-mux-reg.c           | 4 +---
 include/linux/platform_data/i2c-mux-reg.h | 2 --
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c
index 9efc1ed01577b..8489971babd37 100644
--- a/drivers/i2c/muxes/i2c-mux-reg.c
+++ b/drivers/i2c/muxes/i2c-mux-reg.c
@@ -159,7 +159,6 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 	struct regmux *mux;
 	struct i2c_adapter *parent;
 	struct resource *res;
-	unsigned int class;
 	int i, ret, nr;
 
 	mux = devm_kzalloc(&pdev->dev, sizeof(*mux), GFP_KERNEL);
@@ -213,9 +212,8 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 
 	for (i = 0; i < mux->data.n_values; i++) {
 		nr = mux->data.base_nr ? (mux->data.base_nr + i) : 0;
-		class = mux->data.classes ? mux->data.classes[i] : 0;
 
-		ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], class);
+		ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], 0);
 		if (ret)
 			goto err_del_mux_adapters;
 	}
diff --git a/include/linux/platform_data/i2c-mux-reg.h b/include/linux/platform_data/i2c-mux-reg.h
index 2543c2a1c9aef..e2e8957683116 100644
--- a/include/linux/platform_data/i2c-mux-reg.h
+++ b/include/linux/platform_data/i2c-mux-reg.h
@@ -17,7 +17,6 @@
  * @n_values: Number of multiplexer channels
  * @little_endian: Indicating if the register is in little endian
  * @write_only: Reading the register is not allowed by hardware
- * @classes: Optional I2C auto-detection classes
  * @idle: Value to write to mux when idle
  * @idle_in_use: indicate if idle value is in use
  * @reg: Virtual address of the register to switch channel
@@ -30,7 +29,6 @@ struct i2c_mux_reg_platform_data {
 	int n_values;
 	bool little_endian;
 	bool write_only;
-	const unsigned int *classes;
 	u32 idle;
 	bool idle_in_use;
 	void __iomem *reg;
-- 
GitLab


From 462e9804d2c90bfffb494718b5aae5c374ff3b78 Mon Sep 17 00:00:00 2001
From: Hans Hu <hanshu-oc@zhaoxin.com>
Date: Thu, 2 Nov 2023 10:53:51 +0800
Subject: [PATCH 2972/4076] i2c: wmt: Reduce redundant: bus busy check

Put wmt_i2c_wait_bus_not_busy() in a more appropriate place
to reduce code redundancy

Signed-off-by: Hans Hu <hanshu-oc@zhaoxin.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-wmt.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c
index 76118abc6e104..d554c63775331 100644
--- a/drivers/i2c/busses/i2c-wmt.c
+++ b/drivers/i2c/busses/i2c-wmt.c
@@ -128,12 +128,6 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	unsigned long wait_result;
 	int xfer_len = 0;
 
-	if (!(pmsg->flags & I2C_M_NOSTART)) {
-		ret = wmt_i2c_wait_bus_not_busy(i2c_dev);
-		if (ret < 0)
-			return ret;
-	}
-
 	if (pmsg->len == 0) {
 		/*
 		 * We still need to run through the while (..) once, so
@@ -219,12 +213,6 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	unsigned long wait_result;
 	u32 xfer_len = 0;
 
-	if (!(pmsg->flags & I2C_M_NOSTART)) {
-		ret = wmt_i2c_wait_bus_not_busy(i2c_dev);
-		if (ret < 0)
-			return ret;
-	}
-
 	val = readw(i2c_dev->base + REG_CR);
 	val &= ~CR_TX_END;
 	writew(val, i2c_dev->base + REG_CR);
@@ -297,11 +285,18 @@ static int wmt_i2c_xfer(struct i2c_adapter *adap,
 	struct i2c_msg *pmsg;
 	int i, is_last;
 	int ret = 0;
+	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
 
 	for (i = 0; ret >= 0 && i < num; i++) {
 		is_last = ((i + 1) == num);
 
 		pmsg = &msgs[i];
+		if (!(pmsg->flags & I2C_M_NOSTART)) {
+			ret = wmt_i2c_wait_bus_not_busy(i2c_dev);
+			if (ret < 0)
+				return ret;
+		}
+
 		if (pmsg->flags & I2C_M_RD)
 			ret = wmt_i2c_read(adap, pmsg, is_last);
 		else
-- 
GitLab


From 8a22991a48f2602aaab79df1301483d50bc51b2c Mon Sep 17 00:00:00 2001
From: Hans Hu <hanshu-oc@zhaoxin.com>
Date: Thu, 2 Nov 2023 10:53:52 +0800
Subject: [PATCH 2973/4076] i2c: wmt: Reduce redundant: wait event complete

Put the handling of interrupt events in a function class
to reduce code redundancy.

Signed-off-by: Hans Hu <hanshu-oc@zhaoxin.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-wmt.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c
index d554c63775331..1b31330ba4ebc 100644
--- a/drivers/i2c/busses/i2c-wmt.c
+++ b/drivers/i2c/busses/i2c-wmt.c
@@ -109,6 +109,12 @@ static int wmt_i2c_wait_bus_not_busy(struct wmt_i2c_dev *i2c_dev)
 static int wmt_check_status(struct wmt_i2c_dev *i2c_dev)
 {
 	int ret = 0;
+	unsigned long wait_result;
+
+	wait_result = wait_for_completion_timeout(&i2c_dev->complete,
+						msecs_to_jiffies(500));
+	if (!wait_result)
+		return -ETIMEDOUT;
 
 	if (i2c_dev->cmd_status & ISR_NACK_ADDR)
 		ret = -EIO;
@@ -125,7 +131,6 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
 	u16 val, tcr_val;
 	int ret;
-	unsigned long wait_result;
 	int xfer_len = 0;
 
 	if (pmsg->len == 0) {
@@ -167,12 +172,6 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	}
 
 	while (xfer_len < pmsg->len) {
-		wait_result = wait_for_completion_timeout(&i2c_dev->complete,
-							msecs_to_jiffies(500));
-
-		if (wait_result == 0)
-			return -ETIMEDOUT;
-
 		ret = wmt_check_status(i2c_dev);
 		if (ret)
 			return ret;
@@ -210,7 +209,6 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
 	u16 val, tcr_val;
 	int ret;
-	unsigned long wait_result;
 	u32 xfer_len = 0;
 
 	val = readw(i2c_dev->base + REG_CR);
@@ -251,12 +249,6 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	}
 
 	while (xfer_len < pmsg->len) {
-		wait_result = wait_for_completion_timeout(&i2c_dev->complete,
-							msecs_to_jiffies(500));
-
-		if (!wait_result)
-			return -ETIMEDOUT;
-
 		ret = wmt_check_status(i2c_dev);
 		if (ret)
 			return ret;
-- 
GitLab


From 7108ecf3cbc728ec4a72ce29136cbcfedf4a9242 Mon Sep 17 00:00:00 2001
From: Hans Hu <hanshu-oc@zhaoxin.com>
Date: Thu, 2 Nov 2023 10:53:53 +0800
Subject: [PATCH 2974/4076] i2c: wmt: Reduce redundant: clock mode setting

The frequency setting mode is adjusted to reduce the code redundancy,
and it is also convenient to share with zhaoxin

Signed-off-by: Hans Hu <hanshu-oc@zhaoxin.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-wmt.c | 28 +++++++---------------------
 1 file changed, 7 insertions(+), 21 deletions(-)

diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c
index 1b31330ba4ebc..a44ce5fdde8a3 100644
--- a/drivers/i2c/busses/i2c-wmt.c
+++ b/drivers/i2c/busses/i2c-wmt.c
@@ -74,9 +74,6 @@
 #define MCR_APB_96M		7
 #define MCR_APB_166M		12
 
-#define I2C_MODE_STANDARD	0
-#define I2C_MODE_FAST		1
-
 #define WMT_I2C_TIMEOUT		(msecs_to_jiffies(1000))
 
 struct wmt_i2c_dev {
@@ -85,7 +82,7 @@ struct wmt_i2c_dev {
 	struct device		*dev;
 	void __iomem		*base;
 	struct clk		*clk;
-	int			mode;
+	u16			tcr;
 	int			irq;
 	u16			cmd_status;
 };
@@ -129,7 +126,7 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 			 int last)
 {
 	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
-	u16 val, tcr_val;
+	u16 val, tcr_val = i2c_dev->tcr;
 	int ret;
 	int xfer_len = 0;
 
@@ -156,11 +153,6 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 
 	reinit_completion(&i2c_dev->complete);
 
-	if (i2c_dev->mode == I2C_MODE_STANDARD)
-		tcr_val = TCR_STANDARD_MODE;
-	else
-		tcr_val = TCR_FAST_MODE;
-
 	tcr_val |= (TCR_MASTER_WRITE | (pmsg->addr & TCR_SLAVE_ADDR_MASK));
 
 	writew(tcr_val, i2c_dev->base + REG_TCR);
@@ -207,7 +199,7 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 			int last)
 {
 	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
-	u16 val, tcr_val;
+	u16 val, tcr_val = i2c_dev->tcr;
 	int ret;
 	u32 xfer_len = 0;
 
@@ -233,11 +225,6 @@ static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 
 	reinit_completion(&i2c_dev->complete);
 
-	if (i2c_dev->mode == I2C_MODE_STANDARD)
-		tcr_val = TCR_STANDARD_MODE;
-	else
-		tcr_val = TCR_FAST_MODE;
-
 	tcr_val |= TCR_MASTER_READ | (pmsg->addr & TCR_SLAVE_ADDR_MASK);
 
 	writew(tcr_val, i2c_dev->base + REG_TCR);
@@ -346,10 +333,10 @@ static int wmt_i2c_reset_hardware(struct wmt_i2c_dev *i2c_dev)
 	readw(i2c_dev->base + REG_CSR);		/* read clear */
 	writew(ISR_WRITE_ALL, i2c_dev->base + REG_ISR);
 
-	if (i2c_dev->mode == I2C_MODE_STANDARD)
-		writew(SCL_TIMEOUT(128) | TR_STD, i2c_dev->base + REG_TR);
-	else
+	if (i2c_dev->tcr == TCR_FAST_MODE)
 		writew(SCL_TIMEOUT(128) | TR_HS, i2c_dev->base + REG_TR);
+	else
+		writew(SCL_TIMEOUT(128) | TR_STD, i2c_dev->base + REG_TR);
 
 	return 0;
 }
@@ -382,10 +369,9 @@ static int wmt_i2c_probe(struct platform_device *pdev)
 		return PTR_ERR(i2c_dev->clk);
 	}
 
-	i2c_dev->mode = I2C_MODE_STANDARD;
 	err = of_property_read_u32(np, "clock-frequency", &clk_rate);
 	if (!err && (clk_rate == I2C_MAX_FAST_MODE_FREQ))
-		i2c_dev->mode = I2C_MODE_FAST;
+		i2c_dev->tcr = TCR_FAST_MODE;
 
 	i2c_dev->dev = &pdev->dev;
 
-- 
GitLab


From 4c541c6a66df396c35693a21c5bc40553cd4d2fa Mon Sep 17 00:00:00 2001
From: Hans Hu <hanshu-oc@zhaoxin.com>
Date: Thu, 2 Nov 2023 10:53:55 +0800
Subject: [PATCH 2975/4076] i2c: wmt: Reduce redundant: function parameter

Use more appropriate parameter passing to reduce the amount of code

Signed-off-by: Hans Hu <hanshu-oc@zhaoxin.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-wmt.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c
index a44ce5fdde8a3..7de67886e8ca3 100644
--- a/drivers/i2c/busses/i2c-wmt.c
+++ b/drivers/i2c/busses/i2c-wmt.c
@@ -122,10 +122,9 @@ static int wmt_check_status(struct wmt_i2c_dev *i2c_dev)
 	return ret;
 }
 
-static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
+static int wmt_i2c_write(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg,
 			 int last)
 {
-	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
 	u16 val, tcr_val = i2c_dev->tcr;
 	int ret;
 	int xfer_len = 0;
@@ -195,10 +194,8 @@ static int wmt_i2c_write(struct i2c_adapter *adap, struct i2c_msg *pmsg,
 	return 0;
 }
 
-static int wmt_i2c_read(struct i2c_adapter *adap, struct i2c_msg *pmsg,
-			int last)
+static int wmt_i2c_read(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg)
 {
-	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
 	u16 val, tcr_val = i2c_dev->tcr;
 	int ret;
 	u32 xfer_len = 0;
@@ -262,13 +259,11 @@ static int wmt_i2c_xfer(struct i2c_adapter *adap,
 			int num)
 {
 	struct i2c_msg *pmsg;
-	int i, is_last;
+	int i;
 	int ret = 0;
 	struct wmt_i2c_dev *i2c_dev = i2c_get_adapdata(adap);
 
 	for (i = 0; ret >= 0 && i < num; i++) {
-		is_last = ((i + 1) == num);
-
 		pmsg = &msgs[i];
 		if (!(pmsg->flags & I2C_M_NOSTART)) {
 			ret = wmt_i2c_wait_bus_not_busy(i2c_dev);
@@ -277,9 +272,9 @@ static int wmt_i2c_xfer(struct i2c_adapter *adap,
 		}
 
 		if (pmsg->flags & I2C_M_RD)
-			ret = wmt_i2c_read(adap, pmsg, is_last);
+			ret = wmt_i2c_read(i2c_dev, pmsg);
 		else
-			ret = wmt_i2c_write(adap, pmsg, is_last);
+			ret = wmt_i2c_write(i2c_dev, pmsg, (i + 1) == num);
 	}
 
 	return (ret < 0) ? ret : i;
-- 
GitLab


From bb7c0209c4fead37fbc9fd07f9617f40ba21189e Mon Sep 17 00:00:00 2001
From: Hans Hu <hanshu-oc@zhaoxin.com>
Date: Thu, 2 Nov 2023 10:53:54 +0800
Subject: [PATCH 2976/4076] i2c: wmt: Reduce redundant: REG_CR setting

These Settings for the same register, REG_CR,
can be put together to reduce code redundancy.

Signed-off-by: Hans Hu <hanshu-oc@zhaoxin.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-wmt.c | 35 +++++++++--------------------------
 1 file changed, 9 insertions(+), 26 deletions(-)

diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c
index 7de67886e8ca3..ec2a8da134e56 100644
--- a/drivers/i2c/busses/i2c-wmt.c
+++ b/drivers/i2c/busses/i2c-wmt.c
@@ -143,9 +143,6 @@ static int wmt_i2c_write(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg,
 	if (!(pmsg->flags & I2C_M_NOSTART)) {
 		val = readw(i2c_dev->base + REG_CR);
 		val &= ~CR_TX_END;
-		writew(val, i2c_dev->base + REG_CR);
-
-		val = readw(i2c_dev->base + REG_CR);
 		val |= CR_CPU_RDY;
 		writew(val, i2c_dev->base + REG_CR);
 	}
@@ -201,24 +198,15 @@ static int wmt_i2c_read(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg)
 	u32 xfer_len = 0;
 
 	val = readw(i2c_dev->base + REG_CR);
-	val &= ~CR_TX_END;
-	writew(val, i2c_dev->base + REG_CR);
+	val &= ~(CR_TX_END | CR_TX_NEXT_NO_ACK);
 
-	val = readw(i2c_dev->base + REG_CR);
-	val &= ~CR_TX_NEXT_NO_ACK;
-	writew(val, i2c_dev->base + REG_CR);
-
-	if (!(pmsg->flags & I2C_M_NOSTART)) {
-		val = readw(i2c_dev->base + REG_CR);
+	if (!(pmsg->flags & I2C_M_NOSTART))
 		val |= CR_CPU_RDY;
-		writew(val, i2c_dev->base + REG_CR);
-	}
 
-	if (pmsg->len == 1) {
-		val = readw(i2c_dev->base + REG_CR);
+	if (pmsg->len == 1)
 		val |= CR_TX_NEXT_NO_ACK;
-		writew(val, i2c_dev->base + REG_CR);
-	}
+
+	writew(val, i2c_dev->base + REG_CR);
 
 	reinit_completion(&i2c_dev->complete);
 
@@ -240,15 +228,10 @@ static int wmt_i2c_read(struct wmt_i2c_dev *i2c_dev, struct i2c_msg *pmsg)
 		pmsg->buf[xfer_len] = readw(i2c_dev->base + REG_CDR) >> 8;
 		xfer_len++;
 
-		if (xfer_len == pmsg->len - 1) {
-			val = readw(i2c_dev->base + REG_CR);
-			val |= (CR_TX_NEXT_NO_ACK | CR_CPU_RDY);
-			writew(val, i2c_dev->base + REG_CR);
-		} else {
-			val = readw(i2c_dev->base + REG_CR);
-			val |= CR_CPU_RDY;
-			writew(val, i2c_dev->base + REG_CR);
-		}
+		val = readw(i2c_dev->base + REG_CR) | CR_CPU_RDY;
+		if (xfer_len == pmsg->len - 1)
+			val |= CR_TX_NEXT_NO_ACK;
+		writew(val, i2c_dev->base + REG_CR);
 	}
 
 	return 0;
-- 
GitLab


From 6d9450464ce1825d7d0e7ef5d33a9d2701f41c76 Mon Sep 17 00:00:00 2001
From: Paul Menzel <pmenzel@molgen.mpg.de>
Date: Wed, 20 Dec 2023 17:10:01 +0100
Subject: [PATCH 2977/4076] i2c: i801: Add lis3lv02d for Dell Precision 3540
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On the Dell Precision 3540/0M14W7, BIOS 1.7.4 05/12/2020, Linux prints
the warning below.

    i801_smbus 0000:00:1f.4: Accelerometer lis3lv02d is present on SMBus but its address is unknown, skipping registration

With the help of Wolfram Sang, the test to probe it on I2C bus 6 at address
0x29 was successful.

    $ echo lis3lv02d 0x29 | sudo tee /sys/bus/i2c/devices/i2c-6/new_device
    [ 2110.787000] i2c i2c-6: new_device: Instantiated device lis3lv02d at 0x29
    [ 2110.791932] lis3lv02d_i2c 6-0029: supply Vdd not found, using dummy regulator
    [ 2110.791981] lis3lv02d_i2c 6-0029: supply Vdd_IO not found, using dummy regulator
    [ 2110.809233] lis3lv02d: 8 bits 3DC sensor found
    [ 2110.900668] input: ST LIS3LV02DL Accelerometer as /devices/platform/lis3lv02d/input/input23

So, the device has that accelerometer. Add the I2C address to the
mapping list.

Link: https://lore.kernel.org/linux-i2c/97708c11-ac85-fb62-2c8e-d37739ca826f@molgen.mpg.de/
Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de>
Acked-by: Pali Rohár <pali@kernel.org>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
[wsa: shortened commit message a little]
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-i801.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 070999139c6dc..cb9660f841171 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1230,6 +1230,7 @@ static const struct {
 	 * Additional individual entries were added after verification.
 	 */
 	{ "Latitude 5480",      0x29 },
+	{ "Precision 3540",     0x29 },
 	{ "Vostro V131",        0x1d },
 	{ "Vostro 5568",        0x29 },
 };
-- 
GitLab


From 2f189493ae32be9768b27072c9388e62b38d2dda Mon Sep 17 00:00:00 2001
From: Paul Menzel <pmenzel@molgen.mpg.de>
Date: Wed, 20 Dec 2023 17:10:02 +0100
Subject: [PATCH 2978/4076] i2c: i801: Add lis3lv02d for Dell XPS 15 7590
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On the Dell XPS 15 7590/0VYV0G, BIOS 1.24.0 09/11/2023, Linux prints the
warning below.

    i801_smbus 0000:00:1f.4: Accelerometer lis3lv02d is present on SMBus but its address is unknown, skipping registration

Following the same suggestions by Wolfram Sang as for the Dell Precision
3540 [1], the accelerometer can be successfully found on I2C bus 2 at
address 0x29.

    $ echo lis3lv02d 0x29 | sudo tee /sys/bus/i2c/devices/i2c-2/new_device
    lis3lv02d 0x29
    $ dmesg | tail -5
    [  549.522876] lis3lv02d_i2c 2-0029: supply Vdd not found, using dummy regulator
    [  549.522904] lis3lv02d_i2c 2-0029: supply Vdd_IO not found, using dummy regulator
    [  549.542486] lis3lv02d: 8 bits 3DC sensor found
    [  549.630022] input: ST LIS3LV02DL Accelerometer as /devices/platform/lis3lv02d/input/input35
    [  549.630586] i2c i2c-2: new_device: Instantiated device lis3lv02d at 0x29

So, the device has that accelerometer. Add the I2C address to the
mapping list, and test it successfully on the device.

[1]: https://lore.kernel.org/linux-i2c/97708c11-ac85-fb62-2c8e-d37739ca826f@molgen.mpg.de/

Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de>
Acked-by: Pali Rohár <pali@kernel.org>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-i801.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index cb9660f841171..3932e8d96a171 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1233,6 +1233,7 @@ static const struct {
 	{ "Precision 3540",     0x29 },
 	{ "Vostro V131",        0x1d },
 	{ "Vostro 5568",        0x29 },
+	{ "XPS 15 7590",        0x29 },
 };
 
 static void register_dell_lis3lv02d_i2c_device(struct i801_priv *priv)
-- 
GitLab


From a51e224c2f42417e95a3e1a672ade221bcd006ba Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@foss.st.com>
Date: Fri, 15 Dec 2023 18:06:05 +0100
Subject: [PATCH 2979/4076] i2c: stm32f7: use dev_err_probe upon calls of
 devm_request_irq

Convert error handling upon calls of devm_request_irq functions during
the probe of the driver.

Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-stm32f7.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 983509936727e..d99f152ac7275 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -2199,19 +2199,13 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 					stm32f7_i2c_isr_event_thread,
 					IRQF_ONESHOT,
 					pdev->name, i2c_dev);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to request irq event %i\n",
-			irq_event);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to request irq event\n");
 
 	ret = devm_request_irq(&pdev->dev, irq_error, stm32f7_i2c_isr_error, 0,
 			       pdev->name, i2c_dev);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to request irq error %i\n",
-			irq_error);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to request irq error\n");
 
 	setup = of_device_get_match_data(&pdev->dev);
 	if (!setup) {
-- 
GitLab


From e6103cd45ef0e14eb02f0666bc6b494902cfe821 Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@foss.st.com>
Date: Fri, 15 Dec 2023 18:06:06 +0100
Subject: [PATCH 2980/4076] i2c: stm32f7: perform most of irq job in threaded
 handler

The irq handling is currently split between the irq handler
and the threaded irq handler.  Some of the handling (such as
dma related stuffs) done within the irq handler might sleep or
take some time leading to issues if the kernel is built with
realtime constraints.  In order to fix that, perform an overall
rework to perform most of the job within the threaded handler
and only keep fifo access in the non threaded handler.

Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-stm32f7.c | 126 ++++++++++++++-----------------
 1 file changed, 56 insertions(+), 70 deletions(-)

diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index d99f152ac7275..dde70e7ec7226 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -1497,17 +1497,11 @@ static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev)
 static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
-	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
-	struct stm32_i2c_dma *dma = i2c_dev->dma;
-	void __iomem *base = i2c_dev->base;
-	u32 status, mask;
-	int ret = IRQ_HANDLED;
+	u32 status;
 
-	/* Check if the interrupt if for a slave device */
-	if (!i2c_dev->master_mode) {
-		ret = stm32f7_i2c_slave_isr_event(i2c_dev);
-		return ret;
-	}
+	/* Check if the interrupt is for a slave device */
+	if (!i2c_dev->master_mode)
+		return IRQ_WAKE_THREAD;
 
 	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
 
@@ -1519,6 +1513,29 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 	if (status & STM32F7_I2C_ISR_RXNE)
 		stm32f7_i2c_read_rx_data(i2c_dev);
 
+	/* Wake up the thread if other flags are raised */
+	if (status &
+	    (STM32F7_I2C_ISR_NACKF | STM32F7_I2C_ISR_STOPF |
+	     STM32F7_I2C_ISR_TC | STM32F7_I2C_ISR_TCR))
+		return IRQ_WAKE_THREAD;
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
+{
+	struct stm32f7_i2c_dev *i2c_dev = data;
+	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
+	struct stm32_i2c_dma *dma = i2c_dev->dma;
+	void __iomem *base = i2c_dev->base;
+	u32 status, mask;
+	int ret;
+
+	if (!i2c_dev->master_mode)
+		return stm32f7_i2c_slave_isr_event(i2c_dev);
+
+	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
+
 	/* NACK received */
 	if (status & STM32F7_I2C_ISR_NACKF) {
 		dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n",
@@ -1531,33 +1548,28 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		f7_msg->result = -ENXIO;
 	}
 
-	/* STOP detection flag */
-	if (status & STM32F7_I2C_ISR_STOPF) {
-		/* Disable interrupts */
-		if (stm32f7_i2c_is_slave_registered(i2c_dev))
-			mask = STM32F7_I2C_XFER_IRQ_MASK;
+	if (status & STM32F7_I2C_ISR_TCR) {
+		if (f7_msg->smbus)
+			stm32f7_i2c_smbus_reload(i2c_dev);
 		else
-			mask = STM32F7_I2C_ALL_IRQ_MASK;
-		stm32f7_i2c_disable_irq(i2c_dev, mask);
-
-		/* Clear STOP flag */
-		writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR);
-
-		if (i2c_dev->use_dma && !f7_msg->result) {
-			ret = IRQ_WAKE_THREAD;
-		} else {
-			i2c_dev->master_mode = false;
-			complete(&i2c_dev->complete);
-		}
+			stm32f7_i2c_reload(i2c_dev);
 	}
 
 	/* Transfer complete */
 	if (status & STM32F7_I2C_ISR_TC) {
+		/* Wait for dma transfer completion before sending next message */
+		if (i2c_dev->use_dma && !f7_msg->result) {
+			ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ);
+			if (!ret) {
+				dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__);
+				stm32f7_i2c_disable_dma_req(i2c_dev);
+				dmaengine_terminate_async(dma->chan_using);
+				f7_msg->result = -ETIMEDOUT;
+			}
+		}
 		if (f7_msg->stop) {
 			mask = STM32F7_I2C_CR2_STOP;
 			stm32f7_i2c_set_bits(base + STM32F7_I2C_CR2, mask);
-		} else if (i2c_dev->use_dma && !f7_msg->result) {
-			ret = IRQ_WAKE_THREAD;
 		} else if (f7_msg->smbus) {
 			stm32f7_i2c_smbus_rep_start(i2c_dev);
 		} else {
@@ -1567,47 +1579,18 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		}
 	}
 
-	if (status & STM32F7_I2C_ISR_TCR) {
-		if (f7_msg->smbus)
-			stm32f7_i2c_smbus_reload(i2c_dev);
+	/* STOP detection flag */
+	if (status & STM32F7_I2C_ISR_STOPF) {
+		/* Disable interrupts */
+		if (stm32f7_i2c_is_slave_registered(i2c_dev))
+			mask = STM32F7_I2C_XFER_IRQ_MASK;
 		else
-			stm32f7_i2c_reload(i2c_dev);
-	}
-
-	return ret;
-}
-
-static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
-{
-	struct stm32f7_i2c_dev *i2c_dev = data;
-	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
-	struct stm32_i2c_dma *dma = i2c_dev->dma;
-	u32 status;
-	int ret;
-
-	/*
-	 * Wait for dma transfer completion before sending next message or
-	 * notity the end of xfer to the client
-	 */
-	ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ);
-	if (!ret) {
-		dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__);
-		stm32f7_i2c_disable_dma_req(i2c_dev);
-		dmaengine_terminate_async(dma->chan_using);
-		f7_msg->result = -ETIMEDOUT;
-	}
+			mask = STM32F7_I2C_ALL_IRQ_MASK;
+		stm32f7_i2c_disable_irq(i2c_dev, mask);
 
-	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
+		/* Clear STOP flag */
+		writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR);
 
-	if (status & STM32F7_I2C_ISR_TC) {
-		if (f7_msg->smbus) {
-			stm32f7_i2c_smbus_rep_start(i2c_dev);
-		} else {
-			i2c_dev->msg_id++;
-			i2c_dev->msg++;
-			stm32f7_i2c_xfer_msg(i2c_dev, i2c_dev->msg);
-		}
-	} else {
 		i2c_dev->master_mode = false;
 		complete(&i2c_dev->complete);
 	}
@@ -1615,7 +1598,7 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data)
+static irqreturn_t stm32f7_i2c_isr_error_thread(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
 	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
@@ -2202,8 +2185,11 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret, "Failed to request irq event\n");
 
-	ret = devm_request_irq(&pdev->dev, irq_error, stm32f7_i2c_isr_error, 0,
-			       pdev->name, i2c_dev);
+	ret = devm_request_threaded_irq(&pdev->dev, irq_error,
+					NULL,
+					stm32f7_i2c_isr_error_thread,
+					IRQF_ONESHOT,
+					pdev->name, i2c_dev);
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret, "Failed to request irq error\n");
 
-- 
GitLab


From 33a00d919253022aabafecae6bc88a6fad446589 Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@foss.st.com>
Date: Fri, 15 Dec 2023 18:06:07 +0100
Subject: [PATCH 2981/4076] i2c: stm32f7: simplify status messages in case of
 errors

Avoid usage of __func__ when reporting an error message
since dev_err/dev_dbg are already providing enough details
to identify the source of the message.

Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-stm32f7.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index dde70e7ec7226..15100fed0a3f3 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -1602,6 +1602,7 @@ static irqreturn_t stm32f7_i2c_isr_error_thread(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
 	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
+	u16 addr = f7_msg->addr;
 	void __iomem *base = i2c_dev->base;
 	struct device *dev = i2c_dev->dev;
 	struct stm32_i2c_dma *dma = i2c_dev->dma;
@@ -1611,8 +1612,7 @@ static irqreturn_t stm32f7_i2c_isr_error_thread(int irq, void *data)
 
 	/* Bus error */
 	if (status & STM32F7_I2C_ISR_BERR) {
-		dev_err(dev, "<%s>: Bus error accessing addr 0x%x\n",
-			__func__, f7_msg->addr);
+		dev_err(dev, "Bus error accessing addr 0x%x\n", addr);
 		writel_relaxed(STM32F7_I2C_ICR_BERRCF, base + STM32F7_I2C_ICR);
 		stm32f7_i2c_release_bus(&i2c_dev->adap);
 		f7_msg->result = -EIO;
@@ -1620,21 +1620,19 @@ static irqreturn_t stm32f7_i2c_isr_error_thread(int irq, void *data)
 
 	/* Arbitration loss */
 	if (status & STM32F7_I2C_ISR_ARLO) {
-		dev_dbg(dev, "<%s>: Arbitration loss accessing addr 0x%x\n",
-			__func__, f7_msg->addr);
+		dev_dbg(dev, "Arbitration loss accessing addr 0x%x\n", addr);
 		writel_relaxed(STM32F7_I2C_ICR_ARLOCF, base + STM32F7_I2C_ICR);
 		f7_msg->result = -EAGAIN;
 	}
 
 	if (status & STM32F7_I2C_ISR_PECERR) {
-		dev_err(dev, "<%s>: PEC error in reception accessing addr 0x%x\n",
-			__func__, f7_msg->addr);
+		dev_err(dev, "PEC error in reception accessing addr 0x%x\n", addr);
 		writel_relaxed(STM32F7_I2C_ICR_PECCF, base + STM32F7_I2C_ICR);
 		f7_msg->result = -EINVAL;
 	}
 
 	if (status & STM32F7_I2C_ISR_ALERT) {
-		dev_dbg(dev, "<%s>: SMBus alert received\n", __func__);
+		dev_dbg(dev, "SMBus alert received\n");
 		writel_relaxed(STM32F7_I2C_ICR_ALERTCF, base + STM32F7_I2C_ICR);
 		i2c_handle_smbus_alert(i2c_dev->alert->ara);
 		return IRQ_HANDLED;
-- 
GitLab


From bf12998e1a68a82d596ea33b00b3ebc75ce52bb5 Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@foss.st.com>
Date: Fri, 15 Dec 2023 18:06:08 +0100
Subject: [PATCH 2982/4076] dt-bindings: i2c: document st,stm32mp25-i2c
 compatible

Add a new compatible st,stm32mp25-i2c for the STM32MP25 series which
has only one interrupt line for both events and errors and differs in
term of handling of FastModePlus.

Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 .../devicetree/bindings/i2c/st,stm32-i2c.yaml | 28 +++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
index 94b75d9f66cdb..1b31b87c1800a 100644
--- a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
@@ -19,6 +19,7 @@ allOf:
               - st,stm32f7-i2c
               - st,stm32mp13-i2c
               - st,stm32mp15-i2c
+              - st,stm32mp25-i2c
     then:
       properties:
         i2c-scl-rising-time-ns:
@@ -41,6 +42,30 @@ allOf:
         clock-frequency:
           enum: [100000, 400000]
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - st,stm32f4-i2c
+              - st,stm32f7-i2c
+              - st,stm32mp13-i2c
+              - st,stm32mp15-i2c
+    then:
+      properties:
+        interrupts:
+          minItems: 2
+
+        interrupt-names:
+          minItems: 2
+    else:
+      properties:
+        interrupts:
+          maxItems: 1
+
+        interrupt-names:
+          maxItems: 1
+
 properties:
   compatible:
     enum:
@@ -48,6 +73,7 @@ properties:
       - st,stm32f7-i2c
       - st,stm32mp13-i2c
       - st,stm32mp15-i2c
+      - st,stm32mp25-i2c
 
   reg:
     maxItems: 1
@@ -56,11 +82,13 @@ properties:
     items:
       - description: interrupt ID for I2C event
       - description: interrupt ID for I2C error
+    minItems: 1
 
   interrupt-names:
     items:
       - const: event
       - const: error
+    minItems: 1
 
   resets:
     maxItems: 1
-- 
GitLab


From a058b24c08023ea0ea0a7c38e6845f1d25139a22 Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@foss.st.com>
Date: Fri, 15 Dec 2023 18:06:09 +0100
Subject: [PATCH 2983/4076] i2c: stm32f7: perform I2C_ISR read once at
 beginning of event isr

Move readl_relaxed of I2C_ISR register at beginning of event isr
so that it done once for both master & slave handling.

Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-stm32f7.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 15100fed0a3f3..f7abf6d3a7b96 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -1419,15 +1419,13 @@ static bool stm32f7_i2c_is_slave_busy(struct stm32f7_i2c_dev *i2c_dev)
 	return i == busy;
 }
 
-static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev)
+static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev, u32 status)
 {
 	void __iomem *base = i2c_dev->base;
-	u32 cr2, status, mask;
+	u32 cr2, mask;
 	u8 val;
 	int ret;
 
-	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
-
 	/* Slave transmitter mode */
 	if (status & STM32F7_I2C_ISR_TXIS) {
 		i2c_slave_event(i2c_dev->slave_running,
@@ -1531,11 +1529,11 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 	u32 status, mask;
 	int ret;
 
-	if (!i2c_dev->master_mode)
-		return stm32f7_i2c_slave_isr_event(i2c_dev);
-
 	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
 
+	if (!i2c_dev->master_mode)
+		return stm32f7_i2c_slave_isr_event(i2c_dev, status);
+
 	/* NACK received */
 	if (status & STM32F7_I2C_ISR_NACKF) {
 		dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n",
-- 
GitLab


From 90f9b1406236853bd524ddde86cc5a945690c6b7 Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@foss.st.com>
Date: Fri, 15 Dec 2023 18:06:10 +0100
Subject: [PATCH 2984/4076] i2c: stm32f7: add support for stm32mp25 soc

The stm32mp25 has only a single interrupt line used for both
events and errors. In order to cope with that, reorganise the
error handling code so that it can be called either from the
common handler (used in case of SoC having only a single IT line)
and the error handler for others.
The CR1 register also embeds a new FMP bit, necessary when running
at Fast Mode Plus frequency. This bit should be used instead of
the SYSCFG bit used on other platforms.
Add a new compatible to distinguish between the SoCs and two
boolean within the setup structure in order to know if the
platform has a single/multiple IT lines and if the FMP bit
within CR1 is available or not.

Signed-off-by: Valentin Caron <valentin.caron@foss.st.com>
Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-stm32f7.c | 214 ++++++++++++++++++-------------
 1 file changed, 126 insertions(+), 88 deletions(-)

diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index f7abf6d3a7b96..01210452216b3 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -50,6 +50,7 @@
 #define STM32F7_I2C_TXDR			0x28
 
 /* STM32F7 I2C control 1 */
+#define STM32_I2C_CR1_FMP			BIT(24)
 #define STM32F7_I2C_CR1_PECEN			BIT(23)
 #define STM32F7_I2C_CR1_ALERTEN			BIT(22)
 #define STM32F7_I2C_CR1_SMBHEN			BIT(20)
@@ -226,6 +227,8 @@ struct stm32f7_i2c_spec {
  * @rise_time: Rise time (ns)
  * @fall_time: Fall time (ns)
  * @fmp_clr_offset: Fast Mode Plus clear register offset from set register
+ * @single_it_line: Only a single IT line is used for both events/errors
+ * @fmp_cr1_bit: Fast Mode Plus control is done via a bit in CR1
  */
 struct stm32f7_i2c_setup {
 	u32 speed_freq;
@@ -233,6 +236,8 @@ struct stm32f7_i2c_setup {
 	u32 rise_time;
 	u32 fall_time;
 	u32 fmp_clr_offset;
+	bool single_it_line;
+	bool fmp_cr1_bit;
 };
 
 /**
@@ -418,6 +423,13 @@ static const struct stm32f7_i2c_setup stm32mp13_setup = {
 	.fmp_clr_offset = 0x4,
 };
 
+static const struct stm32f7_i2c_setup stm32mp25_setup = {
+	.rise_time = STM32F7_I2C_RISE_TIME_DEFAULT,
+	.fall_time = STM32F7_I2C_FALL_TIME_DEFAULT,
+	.single_it_line = true,
+	.fmp_cr1_bit = true,
+};
+
 static inline void stm32f7_i2c_set_bits(void __iomem *reg, u32 mask)
 {
 	writel_relaxed(readl_relaxed(reg) | mask, reg);
@@ -1492,17 +1504,81 @@ static irqreturn_t stm32f7_i2c_slave_isr_event(struct stm32f7_i2c_dev *i2c_dev,
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev, u32 status)
+{
+	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
+	u16 addr = f7_msg->addr;
+	void __iomem *base = i2c_dev->base;
+	struct device *dev = i2c_dev->dev;
+	struct stm32_i2c_dma *dma = i2c_dev->dma;
+
+	/* Bus error */
+	if (status & STM32F7_I2C_ISR_BERR) {
+		dev_err(dev, "Bus error accessing addr 0x%x\n", addr);
+		writel_relaxed(STM32F7_I2C_ICR_BERRCF, base + STM32F7_I2C_ICR);
+		stm32f7_i2c_release_bus(&i2c_dev->adap);
+		f7_msg->result = -EIO;
+	}
+
+	/* Arbitration loss */
+	if (status & STM32F7_I2C_ISR_ARLO) {
+		dev_dbg(dev, "Arbitration loss accessing addr 0x%x\n", addr);
+		writel_relaxed(STM32F7_I2C_ICR_ARLOCF, base + STM32F7_I2C_ICR);
+		f7_msg->result = -EAGAIN;
+	}
+
+	if (status & STM32F7_I2C_ISR_PECERR) {
+		dev_err(dev, "PEC error in reception accessing addr 0x%x\n", addr);
+		writel_relaxed(STM32F7_I2C_ICR_PECCF, base + STM32F7_I2C_ICR);
+		f7_msg->result = -EINVAL;
+	}
+
+	if (status & STM32F7_I2C_ISR_ALERT) {
+		dev_dbg(dev, "SMBus alert received\n");
+		writel_relaxed(STM32F7_I2C_ICR_ALERTCF, base + STM32F7_I2C_ICR);
+		i2c_handle_smbus_alert(i2c_dev->alert->ara);
+		return IRQ_HANDLED;
+	}
+
+	if (!i2c_dev->slave_running) {
+		u32 mask;
+		/* Disable interrupts */
+		if (stm32f7_i2c_is_slave_registered(i2c_dev))
+			mask = STM32F7_I2C_XFER_IRQ_MASK;
+		else
+			mask = STM32F7_I2C_ALL_IRQ_MASK;
+		stm32f7_i2c_disable_irq(i2c_dev, mask);
+	}
+
+	/* Disable dma */
+	if (i2c_dev->use_dma) {
+		stm32f7_i2c_disable_dma_req(i2c_dev);
+		dmaengine_terminate_async(dma->chan_using);
+	}
+
+	i2c_dev->master_mode = false;
+	complete(&i2c_dev->complete);
+
+	return IRQ_HANDLED;
+}
+
+#define STM32F7_ERR_EVENTS (STM32F7_I2C_ISR_BERR | STM32F7_I2C_ISR_ARLO |\
+			    STM32F7_I2C_ISR_PECERR | STM32F7_I2C_ISR_ALERT)
 static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
 	u32 status;
 
-	/* Check if the interrupt is for a slave device */
-	if (!i2c_dev->master_mode)
-		return IRQ_WAKE_THREAD;
-
 	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
 
+	/*
+	 * Check if the interrupt is for a slave device or related
+	 * to errors flags (in case of single it line mode)
+	 */
+	if (!i2c_dev->master_mode ||
+	    (i2c_dev->setup.single_it_line && (status & STM32F7_ERR_EVENTS)))
+		return IRQ_WAKE_THREAD;
+
 	/* Tx empty */
 	if (status & STM32F7_I2C_ISR_TXIS)
 		stm32f7_i2c_write_tx_data(i2c_dev);
@@ -1534,6 +1610,10 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 	if (!i2c_dev->master_mode)
 		return stm32f7_i2c_slave_isr_event(i2c_dev, status);
 
+	/* Handle errors in case of this handler is used for events/errors */
+	if (i2c_dev->setup.single_it_line && (status & STM32F7_ERR_EVENTS))
+		return stm32f7_i2c_handle_isr_errs(i2c_dev, status);
+
 	/* NACK received */
 	if (status & STM32F7_I2C_ISR_NACKF) {
 		dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n",
@@ -1599,63 +1679,11 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 static irqreturn_t stm32f7_i2c_isr_error_thread(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
-	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
-	u16 addr = f7_msg->addr;
-	void __iomem *base = i2c_dev->base;
-	struct device *dev = i2c_dev->dev;
-	struct stm32_i2c_dma *dma = i2c_dev->dma;
 	u32 status;
 
 	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
 
-	/* Bus error */
-	if (status & STM32F7_I2C_ISR_BERR) {
-		dev_err(dev, "Bus error accessing addr 0x%x\n", addr);
-		writel_relaxed(STM32F7_I2C_ICR_BERRCF, base + STM32F7_I2C_ICR);
-		stm32f7_i2c_release_bus(&i2c_dev->adap);
-		f7_msg->result = -EIO;
-	}
-
-	/* Arbitration loss */
-	if (status & STM32F7_I2C_ISR_ARLO) {
-		dev_dbg(dev, "Arbitration loss accessing addr 0x%x\n", addr);
-		writel_relaxed(STM32F7_I2C_ICR_ARLOCF, base + STM32F7_I2C_ICR);
-		f7_msg->result = -EAGAIN;
-	}
-
-	if (status & STM32F7_I2C_ISR_PECERR) {
-		dev_err(dev, "PEC error in reception accessing addr 0x%x\n", addr);
-		writel_relaxed(STM32F7_I2C_ICR_PECCF, base + STM32F7_I2C_ICR);
-		f7_msg->result = -EINVAL;
-	}
-
-	if (status & STM32F7_I2C_ISR_ALERT) {
-		dev_dbg(dev, "SMBus alert received\n");
-		writel_relaxed(STM32F7_I2C_ICR_ALERTCF, base + STM32F7_I2C_ICR);
-		i2c_handle_smbus_alert(i2c_dev->alert->ara);
-		return IRQ_HANDLED;
-	}
-
-	if (!i2c_dev->slave_running) {
-		u32 mask;
-		/* Disable interrupts */
-		if (stm32f7_i2c_is_slave_registered(i2c_dev))
-			mask = STM32F7_I2C_XFER_IRQ_MASK;
-		else
-			mask = STM32F7_I2C_ALL_IRQ_MASK;
-		stm32f7_i2c_disable_irq(i2c_dev, mask);
-	}
-
-	/* Disable dma */
-	if (i2c_dev->use_dma) {
-		stm32f7_i2c_disable_dma_req(i2c_dev);
-		dmaengine_terminate_async(dma->chan_using);
-	}
-
-	i2c_dev->master_mode = false;
-	complete(&i2c_dev->complete);
-
-	return IRQ_HANDLED;
+	return stm32f7_i2c_handle_isr_errs(i2c_dev, status);
 }
 
 static int stm32f7_i2c_wait_polling(struct stm32f7_i2c_dev *i2c_dev)
@@ -1991,23 +2019,27 @@ static int stm32f7_i2c_unreg_slave(struct i2c_client *slave)
 static int stm32f7_i2c_write_fm_plus_bits(struct stm32f7_i2c_dev *i2c_dev,
 					  bool enable)
 {
-	int ret;
+	int ret = 0;
 
 	if (i2c_dev->bus_rate <= I2C_MAX_FAST_MODE_FREQ ||
-	    IS_ERR_OR_NULL(i2c_dev->regmap))
+	    (!i2c_dev->setup.fmp_cr1_bit && IS_ERR_OR_NULL(i2c_dev->regmap)))
 		/* Optional */
 		return 0;
 
-	if (i2c_dev->fmp_sreg == i2c_dev->fmp_creg)
-		ret = regmap_update_bits(i2c_dev->regmap,
-					 i2c_dev->fmp_sreg,
-					 i2c_dev->fmp_mask,
-					 enable ? i2c_dev->fmp_mask : 0);
-	else
-		ret = regmap_write(i2c_dev->regmap,
-				   enable ? i2c_dev->fmp_sreg :
-					    i2c_dev->fmp_creg,
-				   i2c_dev->fmp_mask);
+	if (i2c_dev->setup.fmp_cr1_bit) {
+		if (enable)
+			stm32f7_i2c_set_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32_I2C_CR1_FMP);
+		else
+			stm32f7_i2c_clr_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32_I2C_CR1_FMP);
+	} else {
+		if (i2c_dev->fmp_sreg == i2c_dev->fmp_creg)
+			ret = regmap_update_bits(i2c_dev->regmap, i2c_dev->fmp_sreg,
+						 i2c_dev->fmp_mask, enable ? i2c_dev->fmp_mask : 0);
+		else
+			ret = regmap_write(i2c_dev->regmap,
+					   enable ? i2c_dev->fmp_sreg : i2c_dev->fmp_creg,
+					   i2c_dev->fmp_mask);
+	}
 
 	return ret;
 }
@@ -2141,6 +2173,13 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 	if (!i2c_dev)
 		return -ENOMEM;
 
+	setup = of_device_get_match_data(&pdev->dev);
+	if (!setup) {
+		dev_err(&pdev->dev, "Can't get device data\n");
+		return -ENODEV;
+	}
+	i2c_dev->setup = *setup;
+
 	i2c_dev->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(i2c_dev->base))
 		return PTR_ERR(i2c_dev->base);
@@ -2150,10 +2189,6 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 	if (irq_event < 0)
 		return irq_event;
 
-	irq_error = platform_get_irq(pdev, 1);
-	if (irq_error < 0)
-		return irq_error;
-
 	i2c_dev->wakeup_src = of_property_read_bool(pdev->dev.of_node,
 						    "wakeup-source");
 
@@ -2181,20 +2216,19 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret, "Failed to request irq event\n");
 
-	ret = devm_request_threaded_irq(&pdev->dev, irq_error,
-					NULL,
-					stm32f7_i2c_isr_error_thread,
-					IRQF_ONESHOT,
-					pdev->name, i2c_dev);
-	if (ret)
-		return dev_err_probe(&pdev->dev, ret, "Failed to request irq error\n");
+	if (!i2c_dev->setup.single_it_line) {
+		irq_error = platform_get_irq(pdev, 1);
+		if (irq_error < 0)
+			return irq_error;
 
-	setup = of_device_get_match_data(&pdev->dev);
-	if (!setup) {
-		dev_err(&pdev->dev, "Can't get device data\n");
-		return -ENODEV;
+		ret = devm_request_threaded_irq(&pdev->dev, irq_error,
+						NULL,
+						stm32f7_i2c_isr_error_thread,
+						IRQF_ONESHOT,
+						pdev->name, i2c_dev);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret, "Failed to request irq error\n");
 	}
-	i2c_dev->setup = *setup;
 
 	ret = stm32f7_i2c_setup_timing(i2c_dev, &i2c_dev->setup);
 	if (ret)
@@ -2202,9 +2236,12 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 
 	/* Setup Fast mode plus if necessary */
 	if (i2c_dev->bus_rate > I2C_MAX_FAST_MODE_FREQ) {
-		ret = stm32f7_i2c_setup_fm_plus_bits(pdev, i2c_dev);
-		if (ret)
-			return ret;
+		if (!i2c_dev->setup.fmp_cr1_bit) {
+			ret = stm32f7_i2c_setup_fm_plus_bits(pdev, i2c_dev);
+			if (ret)
+				return ret;
+		}
+
 		ret = stm32f7_i2c_write_fm_plus_bits(i2c_dev, true);
 		if (ret)
 			return ret;
@@ -2483,6 +2520,7 @@ static const struct of_device_id stm32f7_i2c_match[] = {
 	{ .compatible = "st,stm32f7-i2c", .data = &stm32f7_setup},
 	{ .compatible = "st,stm32mp15-i2c", .data = &stm32mp15_setup},
 	{ .compatible = "st,stm32mp13-i2c", .data = &stm32mp13_setup},
+	{ .compatible = "st,stm32mp25-i2c", .data = &stm32mp25_setup},
 	{},
 };
 MODULE_DEVICE_TABLE(of, stm32f7_i2c_match);
-- 
GitLab


From 4503538d3066f6dd0a66ecc902b382912b97d8a1 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sat, 13 Jan 2024 20:35:54 +0100
Subject: [PATCH 2985/4076] MAINTAINERS: use proper email for my I2C work

Renesas is solely funding my I2C maintenance meanwhile, give them credit
for that by using this email address.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 012df8ccf34e9..1a1824790239e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9988,7 +9988,7 @@ F:	Documentation/i2c/busses/i2c-parport.rst
 F:	drivers/i2c/busses/i2c-parport.c
 
 I2C SUBSYSTEM
-M:	Wolfram Sang <wsa@kernel.org>
+M:	Wolfram Sang <wsa+renesas@sang-engineering.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 W:	https://i2c.wiki.kernel.org/
-- 
GitLab


From e28b0359587fe4055c838698172de0530b511702 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 10 Jan 2024 15:54:41 -0800
Subject: [PATCH 2986/4076] bcachefs: Replace strlcpy() with strscpy()

strlcpy() reads the entire source buffer first. This read may exceed
the destination size limit. This is both inefficient and can lead
to linear read overflows if a source string is not NUL-terminated[1].
Additionally, it returns the size of the source string, not the
resulting size of the destination string. In an effort to remove strlcpy()
completely[2], replace strlcpy() here with strscpy().

Nothing checks the return value here, so a direct replacement with
strspy() is possible.

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [1]
Link: https://github.com/KSPP/linux/issues/89 [2]
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Brian Foster <bfoster@redhat.com>
Cc:  <linux-bcachefs@vger.kernel.org>
Link: https://lore.kernel.org/r/20240110235438.work.385-kees@kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/bcachefs/super.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 9dbc35940197f..cefe52898e8eb 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1386,8 +1386,8 @@ static int bch2_dev_attach_bdev(struct bch_fs *c, struct bch_sb_handle *sb)
 	prt_bdevname(&name, ca->disk_sb.bdev);
 
 	if (c->sb.nr_devices == 1)
-		strlcpy(c->name, name.buf, sizeof(c->name));
-	strlcpy(ca->name, name.buf, sizeof(ca->name));
+		strscpy(c->name, name.buf, sizeof(c->name));
+	strscpy(ca->name, name.buf, sizeof(ca->name));
 
 	printbuf_exit(&name);
 
-- 
GitLab


From 3bb9b1f958c3d986ed90a3ff009f1e77e9553207 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 10 Jan 2024 20:58:35 +0530
Subject: [PATCH 2987/4076] drm/amd/display: Fix late derefrence 'dsc' check in
 'link_set_dsc_pps_packet()'

In link_set_dsc_pps_packet(), 'struct display_stream_compressor *dsc'
was dereferenced in a DC_LOGGER_INIT(dsc->ctx->logger); before the 'dsc'
NULL pointer check.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/link/link_dpms.c:905 link_set_dsc_pps_packet() warn: variable dereferenced before check 'dsc' (see line 903)

Cc: stable@vger.kernel.org
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Hamza Mahfooz <hamza.mahfooz@amd.com>
Cc: Wenjing Liu <wenjing.liu@amd.com>
Cc: Qingqing Zhuo <qingqing.zhuo@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/link/link_dpms.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 3de148004c066..3cbfbf8d107e9 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -900,11 +900,15 @@ bool link_set_dsc_pps_packet(struct pipe_ctx *pipe_ctx, bool enable, bool immedi
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
-	DC_LOGGER_INIT(dsc->ctx->logger);
 
-	if (!pipe_ctx->stream->timing.flags.DSC || !dsc)
+	if (!pipe_ctx->stream->timing.flags.DSC)
 		return false;
 
+	if (!dsc)
+		return false;
+
+	DC_LOGGER_INIT(dsc->ctx->logger);
+
 	if (enable) {
 		struct dsc_config dsc_cfg;
 		uint8_t dsc_packed_pps[128];
-- 
GitLab


From aa36d8971fccb55ef3241cbfff9d1799e31d8628 Mon Sep 17 00:00:00 2001
From: Dillon Varone <dillon.varone@amd.com>
Date: Thu, 28 Dec 2023 21:36:39 -0500
Subject: [PATCH 2988/4076] drm/amd/display: Init link enc resources in
 dc_state only if res_pool presents

[Why & How]
res_pool is not initialized in all situations such as virtual
environments, and therefore link encoder resources should not be
initialized if res_pool is NULL.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Martin Leung <martin.leung@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Dillon Varone <dillon.varone@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_state.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 460a8010c79fe..56feee0ff01b1 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -267,7 +267,8 @@ void dc_state_construct(struct dc *dc, struct dc_state *state)
 	state->clk_mgr = dc->clk_mgr;
 
 	/* Initialise DIG link encoder resource tracking variables. */
-	link_enc_cfg_init(dc, state);
+	if (dc->res_pool)
+		link_enc_cfg_init(dc, state);
 }
 
 void dc_state_destruct(struct dc_state *state)
-- 
GitLab


From 8a51cc097dd590a86e8eec5398934ef389ff9a7b Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Thu, 28 Dec 2023 13:19:33 -0500
Subject: [PATCH 2989/4076] drm/amd/display: Add logging resource checks

[Why]
When mapping resources, resources could be unavailable.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Sung joon Kim <sungjoon.kim@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c          | 4 +++-
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 4 ++++
 drivers/gpu/drm/amd/display/dc/core/dc_state.c    | 5 +++--
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 69e726630241d..aa7c02ba948e9 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3522,7 +3522,7 @@ static void commit_planes_for_stream(struct dc *dc,
 	top_pipe_to_program = resource_get_otg_master_for_stream(
 				&context->res_ctx,
 				stream);
-
+	ASSERT(top_pipe_to_program != NULL);
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 
@@ -4345,6 +4345,8 @@ static bool should_commit_minimal_transition_for_windowed_mpo_odm(struct dc *dc,
 
 	cur_pipe = resource_get_otg_master_for_stream(&dc->current_state->res_ctx, stream);
 	new_pipe = resource_get_otg_master_for_stream(&context->res_ctx, stream);
+	if (!cur_pipe || !new_pipe)
+		return false;
 	cur_is_odm_in_use = resource_get_odm_slice_count(cur_pipe) > 1;
 	new_is_odm_in_use = resource_get_odm_slice_count(new_pipe) > 1;
 	if (cur_is_odm_in_use == new_is_odm_in_use)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index f2abc1096ffb6..9fbdb09697fd5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -2194,6 +2194,10 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state)
 	for (stream_idx = 0; stream_idx < state->stream_count; stream_idx++) {
 		otg_master = resource_get_otg_master_for_stream(
 				&state->res_ctx, state->streams[stream_idx]);
+		if (!otg_master	|| otg_master->stream_res.tg == NULL) {
+			DC_LOG_DC("topology update: otg_master NULL stream_idx %d!\n", stream_idx);
+			return;
+		}
 		slice_count = resource_get_opp_heads_for_otg_master(otg_master,
 				&state->res_ctx, opp_heads);
 		for (slice_idx = 0; slice_idx < slice_count; slice_idx++) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 56feee0ff01b1..88c6436b28b69 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -434,8 +434,9 @@ bool dc_state_add_plane(
 
 	otg_master_pipe = resource_get_otg_master_for_stream(
 			&state->res_ctx, stream);
-	added = resource_append_dpp_pipes_for_plane_composition(state,
-			dc->current_state, pool, otg_master_pipe, plane_state);
+	if (otg_master_pipe)
+		added = resource_append_dpp_pipes_for_plane_composition(state,
+				dc->current_state, pool, otg_master_pipe, plane_state);
 
 	if (added) {
 		stream_status->plane_states[stream_status->plane_count] =
-- 
GitLab


From 4b56f7d47be87cde5f368b67bc7fac53a2c3e8d2 Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Fri, 15 Dec 2023 11:01:42 -0500
Subject: [PATCH 2990/4076] drm/amd/display: Port DENTIST hang and TDR fixes to
 OTG disable W/A

[Why]
We can experience DENTIST hangs during optimize_bandwidth or TDRs if
FIFO is toggled and hangs.

[How]
Port the DCN35 fixes to DCN314.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../dc/clk_mgr/dcn314/dcn314_clk_mgr.c        | 21 ++++++++-----------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 878c0e7b78abd..a84f1e376dee4 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -145,30 +145,27 @@ static int dcn314_get_active_display_cnt_wa(
 	return display_count;
 }
 
-static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
+static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context,
+				  bool safe_to_lower, bool disable)
 {
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int i;
 
 	for (i = 0; i < dc->res_pool->pipe_count; ++i) {
-		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe = safe_to_lower
+			? &context->res_ctx.pipe_ctx[i]
+			: &dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe->top_pipe || pipe->prev_odm_pipe)
 			continue;
 		if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) {
-			struct stream_encoder *stream_enc = pipe->stream_res.stream_enc;
-
 			if (disable) {
-				if (stream_enc && stream_enc->funcs->disable_fifo)
-					pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc);
+				if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc)
+					pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
 
-				pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
 				reset_sync_context_for_pipe(dc, context, i);
 			} else {
 				pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
-
-				if (stream_enc && stream_enc->funcs->enable_fifo)
-					pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc);
 			}
 		}
 	}
@@ -297,11 +294,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
-		dcn314_disable_otg_wa(clk_mgr_base, context, true);
+		dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
 
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
-		dcn314_disable_otg_wa(clk_mgr_base, context, false);
+		dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
 
 		update_dispclk = true;
 	}
-- 
GitLab


From 3ba2a0bfd8cf94eb225e1c60dff16e5c35bde1da Mon Sep 17 00:00:00 2001
From: Ilya Bakoulin <ilya.bakoulin@amd.com>
Date: Wed, 3 Jan 2024 09:42:04 -0500
Subject: [PATCH 2991/4076] drm/amd/display: Clear OPTC mem select on disable

[Why]
Not clearing the memory select bits prior to OPTC disable can cause DSC
corruption issues when attempting to reuse a memory instance for another
OPTC that enables ODM.

[How]
Clear the memory select bits prior to disabling an OPTC.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Ilya Bakoulin <ilya.bakoulin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c | 3 +++
 drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
index 1788eb29474b4..8234935433254 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
@@ -173,6 +173,9 @@ static bool optc32_disable_crtc(struct timing_generator *optc)
 			OPTC_SEG3_SRC_SEL, 0xf,
 			OPTC_NUM_OF_INPUT_SEGMENT, 0);
 
+	REG_UPDATE(OPTC_MEMORY_CONFIG,
+			OPTC_MEM_SEL, 0);
+
 	/* disable otg request until end of the first line
 	 * in the vertical blank region
 	 */
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
index 3d6c1b2c2b4d6..5b15475088503 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
@@ -145,6 +145,9 @@ static bool optc35_disable_crtc(struct timing_generator *optc)
 			OPTC_SEG3_SRC_SEL, 0xf,
 			OPTC_NUM_OF_INPUT_SEGMENT, 0);
 
+	REG_UPDATE(OPTC_MEMORY_CONFIG,
+			OPTC_MEM_SEL, 0);
+
 	/* disable otg request until end of the first line
 	 * in the vertical blank region
 	 */
-- 
GitLab


From d3579f5df0536c2f0fabaa3ea80bb2d179884195 Mon Sep 17 00:00:00 2001
From: Ovidiu Bunea <ovidiu.bunea@amd.com>
Date: Mon, 18 Dec 2023 21:40:45 -0500
Subject: [PATCH 2992/4076] drm/amd/display: Fix DML2 watermark calculation

[Why]
core_mode_programming in DML2 should output watermark calculations
to locals, but it incorrectly uses mode_lib

[How]
update code to match HW DML2

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dml2/display_mode_core.c    | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index a6b938a12de13..9be5ebf3a8c0b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -9446,13 +9446,13 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 		CalculateWatermarks_params->CompressedBufferSizeInkByte = locals->CompressedBufferSizeInkByte;
 
 		// Output
-		CalculateWatermarks_params->Watermark = &s->dummy_watermark; // Watermarks *Watermark
-		CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[0];
-		CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = &s->dummy_single_array[0][0]; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
-		CalculateWatermarks_params->SubViewportLinesNeededInMALL = &mode_lib->ms.SubViewportLinesNeededInMALL[j]; // dml_uint_t SubViewportLinesNeededInMALL[]
-		CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[0];
-		CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &s->dummy_single[0]; // dml_float_t *MaxActiveFCLKChangeLatencySupported
-		CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[0];
+		CalculateWatermarks_params->Watermark = &locals->Watermark; // Watermarks *Watermark
+		CalculateWatermarks_params->DRAMClockChangeSupport = &locals->DRAMClockChangeSupport;
+		CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = locals->MaxActiveDRAMClockChangeLatencySupported; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
+		CalculateWatermarks_params->SubViewportLinesNeededInMALL = locals->SubViewportLinesNeededInMALL; // dml_uint_t SubViewportLinesNeededInMALL[]
+		CalculateWatermarks_params->FCLKChangeSupport = &locals->FCLKChangeSupport;
+		CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &locals->MaxActiveFCLKChangeLatencySupported; // dml_float_t *MaxActiveFCLKChangeLatencySupported
+		CalculateWatermarks_params->USRRetrainingSupport = &locals->USRRetrainingSupport;
 
 		CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 			&mode_lib->scratch,
-- 
GitLab


From bfe79f5fff1300d96203383582b078c7b0aec80a Mon Sep 17 00:00:00 2001
From: Wayne Lin <Wayne.Lin@amd.com>
Date: Tue, 2 Jan 2024 14:20:37 +0800
Subject: [PATCH 2993/4076] drm/amd/display: Align the returned error code with
 legacy DP

[Why]
For usb4 connector, AUX transaction is handled by dmub utilizing a differnt
code path comparing to legacy DP connector. If the usb4 DP connector is
disconnected, AUX access will report EBUSY and cause igt@kms_dp_aux_dev
fail.

[How]
Align the error code with the one reported by legacy DP as EIO.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Wayne Lin <Wayne.Lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index eaf8d9f482446..85b7f58a7f35a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -979,6 +979,11 @@ int dm_helper_dmub_aux_transfer_sync(
 		struct aux_payload *payload,
 		enum aux_return_code_type *operation_result)
 {
+	if (!link->hpd_status) {
+		*operation_result = AUX_RET_ERROR_HPD_DISCON;
+		return -1;
+	}
+
 	return amdgpu_dm_process_dmub_aux_transfer_sync(ctx, link->link_index, payload,
 			operation_result);
 }
-- 
GitLab


From bc03c02cc1991a066b23e69bbcc0f66e8f1f7453 Mon Sep 17 00:00:00 2001
From: Ma Jun <Jun.Ma2@amd.com>
Date: Fri, 12 Jan 2024 13:33:24 +0800
Subject: [PATCH 2994/4076] drm/amdgpu: Fix the null pointer when load rlc
 firmware

If the RLC firmware is invalid because of wrong header size,
the pointer to the rlc firmware is released in function
amdgpu_ucode_request. There will be a null pointer error
in subsequent use. So skip validation to fix it.

Fixes: 3da9b71563cb ("drm/amd: Use `amdgpu_ucode_*` helpers for GFX10")
Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 73f6d7e72c737..d63cab294883b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3996,16 +3996,13 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 
 	if (!amdgpu_sriov_vf(adev)) {
 		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix);
-		err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name);
-		/* don't check this.  There are apparently firmwares in the wild with
-		 * incorrect size in the header
-		 */
-		if (err == -ENODEV)
-			goto out;
+		err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 		if (err)
-			dev_dbg(adev->dev,
-				"gfx10: amdgpu_ucode_request() failed \"%s\"\n",
-				fw_name);
+			goto out;
+
+		/* don't validate this firmware. There are apparently firmwares
+		 * in the wild with incorrect size in the header
+		 */
 		rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
 		version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
 		version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
-- 
GitLab


From 05638ff6dd6f0f38734b6b3ee2c7cf15520f5c00 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 13 Jan 2024 15:58:21 +0100
Subject: [PATCH 2995/4076] drm/amd/display: Fix a switch statement in
 populate_dml_output_cfg_from_stream_state()

It is likely that the statement related to 'dml_edp' is misplaced. So move
it in the correct "case SIGNAL_TYPE_EDP".

Fixes: 7966f319c66d ("drm/amd/display: Introduce DML2")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index fa6a93dd96295..64d01a9cd68c8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -626,8 +626,8 @@ static void populate_dml_output_cfg_from_stream_state(struct dml_output_cfg_st *
 		if (is_dp2p0_output_encoder(pipe))
 			out->OutputEncoder[location] = dml_dp2p0;
 		break;
-		out->OutputEncoder[location] = dml_edp;
 	case SIGNAL_TYPE_EDP:
+		out->OutputEncoder[location] = dml_edp;
 		break;
 	case SIGNAL_TYPE_HDMI_TYPE_A:
 	case SIGNAL_TYPE_DVI_SINGLE_LINK:
-- 
GitLab


From 3c4e4eb5d872118fef1708abe933a410c5e07e3a Mon Sep 17 00:00:00 2001
From: Flora Cui <flora.cui@amd.com>
Date: Wed, 10 Jan 2024 19:23:56 +0800
Subject: [PATCH 2996/4076] drm/amdkfd: init drm_client with funcs hook

otherwise drm_client_dev_unregister() would try to
kfree(&adev->kfd.client).

Fixes: 1819200166ce ("drm/amdkfd: Export DMABufs from KFD using GEM handles")
Signed-off-by: Flora Cui <flora.cui@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 067690ba7bffd..81af6bf2f0525 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -138,6 +138,9 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
 	amdgpu_device_gpu_recover(adev, NULL, &reset_context);
 }
 
+static const struct drm_client_funcs kfd_client_funcs = {
+	.unregister	= drm_client_release,
+};
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
 	int i;
@@ -161,7 +164,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.enable_mes = adev->enable_mes,
 		};
 
-		ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", NULL);
+		ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", &kfd_client_funcs);
 		if (ret) {
 			dev_err(adev->dev, "Failed to init DRM client: %d\n", ret);
 			return;
-- 
GitLab


From fb1c93c2e9604a884467a773790016199f78ca08 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Wed, 10 Jan 2024 15:19:29 +0100
Subject: [PATCH 2997/4076] drm/amdgpu: revert "Adjust removal control flow for
 smu v13_0_2"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Calling amdgpu_device_ip_resume_phase1() during shutdown leaves the
HW in an active state and is an unbalanced use of the IP callbacks.

Using the IP callbacks like this can lead to memory leaks, double
free and imbalanced reference counters.

Leaving the HW in an active state can lead to DMA accesses to memory now
freed by the driver.

Both is a complete no-go for driver unload so completely revert the
workaround for now.

This reverts commit f5c7e7797060255dbc8160734ccc5ad6183c5e04.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 32 +---------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    | 32 ----------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h  |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h   |  1 -
 4 files changed, 1 insertion(+), 65 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ecbc58269951c..b158d27d0a71c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5246,7 +5246,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	struct amdgpu_device *tmp_adev = NULL;
 	bool need_full_reset, skip_hw_reset, vram_lost = false;
 	int r = 0;
-	bool gpu_reset_for_dev_remove = 0;
 
 	/* Try reset handler method first */
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
@@ -5266,10 +5265,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 		test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
 	skip_hw_reset = test_bit(AMDGPU_SKIP_HW_RESET, &reset_context->flags);
 
-	gpu_reset_for_dev_remove =
-		test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) &&
-			test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
-
 	/*
 	 * ASIC reset has to be done on all XGMI hive nodes ASAP
 	 * to allow proper links negotiation in FW (within 1 sec)
@@ -5312,18 +5307,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 		amdgpu_ras_intr_cleared();
 	}
 
-	/* Since the mode1 reset affects base ip blocks, the
-	 * phase1 ip blocks need to be resumed. Otherwise there
-	 * will be a BIOS signature error and the psp bootloader
-	 * can't load kdb on the next amdgpu install.
-	 */
-	if (gpu_reset_for_dev_remove) {
-		list_for_each_entry(tmp_adev, device_list_handle, reset_list)
-			amdgpu_device_ip_resume_phase1(tmp_adev);
-
-		goto end;
-	}
-
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
 		if (need_full_reset) {
 			/* post card */
@@ -5560,11 +5543,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	int i, r = 0;
 	bool need_emergency_restart = false;
 	bool audio_suspended = false;
-	bool gpu_reset_for_dev_remove = false;
-
-	gpu_reset_for_dev_remove =
-			test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) &&
-				test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
 
 	/*
 	 * Special case: RAS triggered and full reset isn't supported
@@ -5602,7 +5580,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) {
 		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
 			list_add_tail(&tmp_adev->reset_list, &device_list);
-			if (gpu_reset_for_dev_remove && adev->shutdown)
+			if (adev->shutdown)
 				tmp_adev->shutdown = true;
 		}
 		if (!list_is_first(&adev->reset_list, &device_list))
@@ -5687,10 +5665,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
-		if (gpu_reset_for_dev_remove) {
-			/* Workaroud for ASICs need to disable SMC first */
-			amdgpu_device_smu_fini_early(tmp_adev);
-		}
 		r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context);
 		/*TODO Should we stop ?*/
 		if (r) {
@@ -5722,9 +5696,6 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 		r = amdgpu_do_asic_reset(device_list_handle, reset_context);
 		if (r && r == -EAGAIN)
 			goto retry;
-
-		if (!r && gpu_reset_for_dev_remove)
-			goto recover_end;
 	}
 
 skip_hw_reset:
@@ -5780,7 +5751,6 @@ skip_sched_resume:
 		amdgpu_ras_set_error_query_ready(tmp_adev, true);
 	}
 
-recover_end:
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
 					    reset_list);
 	amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 5c9caf5fa0758..cc69005f5b46e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2337,38 +2337,6 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 		pm_runtime_forbid(dev->dev);
 	}
 
-	if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 2) &&
-	    !amdgpu_sriov_vf(adev)) {
-		bool need_to_reset_gpu = false;
-
-		if (adev->gmc.xgmi.num_physical_nodes > 1) {
-			struct amdgpu_hive_info *hive;
-
-			hive = amdgpu_get_xgmi_hive(adev);
-			if (hive->device_remove_count == 0)
-				need_to_reset_gpu = true;
-			hive->device_remove_count++;
-			amdgpu_put_xgmi_hive(hive);
-		} else {
-			need_to_reset_gpu = true;
-		}
-
-		/* Workaround for ASICs need to reset SMU.
-		 * Called only when the first device is removed.
-		 */
-		if (need_to_reset_gpu) {
-			struct amdgpu_reset_context reset_context;
-
-			adev->shutdown = true;
-			memset(&reset_context, 0, sizeof(reset_context));
-			reset_context.method = AMD_RESET_METHOD_NONE;
-			reset_context.reset_req_dev = adev;
-			set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-			set_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context.flags);
-			amdgpu_device_gpu_recover(adev, NULL, &reset_context);
-		}
-	}
-
 	amdgpu_driver_unload_kms(dev);
 
 	/*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index b0335a1c5e90c..19899f6b9b2b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -32,7 +32,6 @@ enum AMDGPU_RESET_FLAGS {
 
 	AMDGPU_NEED_FULL_RESET = 0,
 	AMDGPU_SKIP_HW_RESET = 1,
-	AMDGPU_RESET_FOR_DEVICE_REMOVE = 2,
 };
 
 struct amdgpu_reset_context {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 6cab882e8061e..1592c63b3099b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -43,7 +43,6 @@ struct amdgpu_hive_info {
 	} pstate;
 
 	struct amdgpu_reset_domain *reset_domain;
-	uint32_t device_remove_count;
 	atomic_t ras_recovery;
 };
 
-- 
GitLab


From b2139c96dc954b58b81bc670fc4ea5f034ed062c Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Sat, 13 Jan 2024 14:32:27 +0530
Subject: [PATCH 2998/4076] drm/amd/display: Drop 'acrtc' and add
 'new_crtc_state' NULL check for writeback requests.

Return value of 'to_amdgpu_crtc' which is container_of(...) can't be
null, so it's null check 'acrtc' is dropped.

Fixing the below:
drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:9302 amdgpu_dm_atomic_commit_tail() error: we previously assumed 'acrtc' could be null (see line 9299)

Added 'new_crtc_state' NULL check for function
'drm_atomic_get_new_crtc_state' that retrieves the new state for a CRTC,
while enabling writeback requests.

Cc: stable@vger.kernel.org
Cc: Alex Hung <alex.hung@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 10b2a896c4982..d55eeb30ccb2c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9293,10 +9293,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		if (!new_con_state->writeback_job)
 			continue;
 
-		new_crtc_state = NULL;
+		new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
 
-		if (acrtc)
-			new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
+		if (!new_crtc_state)
+			continue;
 
 		if (acrtc->wb_enabled)
 			continue;
-- 
GitLab


From aa0901a9008eeb2710292aff94e615adf7884d5f Mon Sep 17 00:00:00 2001
From: Ori Messinger <Ori.Messinger@amd.com>
Date: Wed, 22 Nov 2023 00:12:13 -0500
Subject: [PATCH 2999/4076] drm/amdgpu: Enable GFXOFF for Compute on GFX11
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On GFX version 11, GFXOFF was disabled due to a MES KIQ firmware
issue, which has since been fixed after version 64.
This patch only re-enables GFXOFF for GFX version 11 if the GPU's
MES KIQ firmware version is newer than version 64.

V2: Keep GFXOFF disabled on GFX11 if MES KIQ is below version 64.
V3: Add parentheses to avoid GCC warning for parentheses:
"suggest parentheses around comparison in operand of ‘&’"
V4: Remove "V3" from commit title
V5: Change commit description and insert 'Acked-by'

Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 81af6bf2f0525..77e2636602887 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -698,10 +698,8 @@ err:
 void amdgpu_amdkfd_set_compute_idle(struct amdgpu_device *adev, bool idle)
 {
 	enum amd_powergating_state state = idle ? AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE;
-	/* Temporary workaround to fix issues observed in some
-	 * compute applications when GFXOFF is enabled on GFX11.
-	 */
-	if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11) {
+	if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11 &&
+	    ((adev->mes.kiq_version & AMDGPU_MES_VERSION_MASK) <= 64)) {
 		pr_debug("GFXOFF is %s\n", idle ? "enabled" : "disabled");
 		amdgpu_gfx_off_ctrl(adev, idle);
 	} else if ((IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 9) &&
-- 
GitLab


From 66f962d8939fd2ac74de901d30d30310c8ddca79 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Thu, 18 Jan 2024 22:21:20 +0100
Subject: [PATCH 3000/4076] riscv: Fix build error on rv32 + XIP

commit 66f1e6809397 ("riscv: Make XIP bootable again") restricted page
offset to the sv39 page offset instead of the default sv57, which makes
sense since probably the platforms that target XIP kernels do not
support anything else than sv39 and we do not try to find out the
largest address space supported on XIP kernels (ie set_satp_mode()).

But PAGE_OFFSET_L3 is not defined for rv32, so fix the build error by
restoring the previous behaviour which picks CONFIG_PAGE_OFFSET for rv32.

Fixes: 66f1e6809397 ("riscv: Make XIP bootable again")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Closes: https://lore.kernel.org/linux-riscv/344dca85-5c48-44e1-bc64-4fa7973edd12@infradead.org/T/#u
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Link: https://lore.kernel.org/r/20240118212120.2087803-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/init.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f533dd667a83a..32cad6a65ccd2 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1060,7 +1060,11 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset;
 
 #ifdef CONFIG_XIP_KERNEL
+#ifdef CONFIG_64BIT
 	kernel_map.page_offset = PAGE_OFFSET_L3;
+#else
+	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
+#endif
 	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
 	kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
 
-- 
GitLab


From 2c25716dcc25a0420c4ad49d6e6bf61e60a21434 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 8 Jan 2024 19:38:44 +1030
Subject: [PATCH 3001/4076] btrfs: zlib: fix and simplify the inline extent
 decompression

[BUG]

If we have a filesystem with 4k sectorsize, and an inlined compressed
extent created like this:

	item 4 key (257 INODE_ITEM 0) itemoff 15863 itemsize 160
		generation 8 transid 8 size 4096 nbytes 4096
		block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0
		sequence 1 flags 0x0(none)
	item 5 key (257 INODE_REF 256) itemoff 15839 itemsize 24
		index 2 namelen 14 name: source_inlined
	item 6 key (257 EXTENT_DATA 0) itemoff 15770 itemsize 69
		generation 8 type 0 (inline)
		inline extent data size 48 ram_bytes 4096 compression 1 (zlib)

Which has an inline compressed extent at file offset 0, and its
decompressed size is 4K, allowing us to reflink that 4K range to another
location (which will not be compressed).

If we do such reflink on a subpage system, it would fail like this:

  # xfs_io -f -c "reflink $mnt/source_inlined 0 60k 4k" $mnt/dest
  XFS_IOC_CLONE_RANGE: Input/output error

[CAUSE]
In zlib_decompress(), we didn't treat @start_byte as just a page offset,
but also use it as an indicator on whether we should switch our output
buffer.

In reality, for subpage cases, although @start_byte can be non-zero,
we should never switch input/output buffer, since the whole input/output
buffer should never exceed one sector.

Note: The above assumption is only not true if we're going to support
multi-page sectorsize.

Thus the current code using @start_byte as a condition to switch
input/output buffer or finish the decompression is completely incorrect.

[FIX]
The fix involves several modifications:

- Rename @start_byte to @dest_pgoff to properly express its meaning

- Add an extra ASSERT() inside btrfs_decompress() to make sure the
  input/output size never exceeds one sector.

- Use Z_FINISH flag to make sure the decompression happens in one go

- Remove the loop needed to switch input/output buffers

- Use correct destination offset inside the destination page

- Consider early end as an error

After the fix, even on 64K page sized aarch64, above reflink now
works as expected:

  # xfs_io -f -c "reflink $mnt/source_inlined 0 60k 4k" $mnt/dest
  linked 4096/4096 bytes at offset 61440

And resulted a correct file layout:

	item 9 key (258 INODE_ITEM 0) itemoff 15542 itemsize 160
		generation 10 transid 10 size 65536 nbytes 4096
		block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0
		sequence 1 flags 0x0(none)
	item 10 key (258 INODE_REF 256) itemoff 15528 itemsize 14
		index 3 namelen 4 name: dest
	item 11 key (258 XATTR_ITEM 3817753667) itemoff 15445 itemsize 83
		location key (0 UNKNOWN.0 0) type XATTR
		transid 10 data_len 37 name_len 16
		name: security.selinux
		data unconfined_u:object_r:unlabeled_t:s0
	item 12 key (258 EXTENT_DATA 61440) itemoff 15392 itemsize 53
		generation 10 type 1 (regular)
		extent data disk byte 13631488 nr 4096
		extent data offset 0 nr 4096 ram 4096
		extent compression 0 (none)

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c | 23 +++++++++----
 fs/btrfs/compression.h |  2 +-
 fs/btrfs/zlib.c        | 73 +++++++++++-------------------------------
 3 files changed, 36 insertions(+), 62 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 193168214eeb1..68345f73d429a 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -141,16 +141,16 @@ static int compression_decompress_bio(struct list_head *ws,
 }
 
 static int compression_decompress(int type, struct list_head *ws,
-               const u8 *data_in, struct page *dest_page,
-               unsigned long start_byte, size_t srclen, size_t destlen)
+		const u8 *data_in, struct page *dest_page,
+		unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
 	switch (type) {
 	case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_LZO:  return lzo_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_NONE:
 	default:
 		/*
@@ -1037,14 +1037,23 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
  * start_byte tells us the offset into the compressed data we're interested in
  */
 int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
-		     unsigned long start_byte, size_t srclen, size_t destlen)
+		     unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
 	struct list_head *workspace;
+	const u32 sectorsize = fs_info->sectorsize;
 	int ret;
 
+	/*
+	 * The full destination page range should not exceed the page size.
+	 * And the @destlen should not exceed sectorsize, as this is only called for
+	 * inline file extents, which should not exceed sectorsize.
+	 */
+	ASSERT(dest_pgoff + destlen <= PAGE_SIZE && destlen <= sectorsize);
+
 	workspace = get_workspace(type, 0);
 	ret = compression_decompress(type, workspace, data_in, dest_page,
-				     start_byte, srclen, destlen);
+				     dest_pgoff, srclen, destlen);
 	put_workspace(type, workspace);
 
 	return ret;
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 93cc92974deee..2b4dfb1b010cd 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -148,7 +148,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out);
 int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int zlib_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 struct list_head *zlib_alloc_workspace(unsigned int level);
 void zlib_free_workspace(struct list_head *ws);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 36cf1f0e338e2..8da66ea699e8f 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -354,18 +354,13 @@ done:
 }
 
 int zlib_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
 	int wbits = MAX_WBITS;
-	unsigned long bytes_left;
-	unsigned long total_out = 0;
-	unsigned long pg_offset = 0;
-
-	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
-	bytes_left = destlen;
+	unsigned long to_copy;
 
 	workspace->strm.next_in = data_in;
 	workspace->strm.avail_in = srclen;
@@ -390,60 +385,30 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in,
 		return -EIO;
 	}
 
-	while (bytes_left > 0) {
-		unsigned long buf_start;
-		unsigned long buf_offset;
-		unsigned long bytes;
-
-		ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
-		if (ret != Z_OK && ret != Z_STREAM_END)
-			break;
-
-		buf_start = total_out;
-		total_out = workspace->strm.total_out;
-
-		if (total_out == buf_start) {
-			ret = -EIO;
-			break;
-		}
-
-		if (total_out <= start_byte)
-			goto next;
-
-		if (total_out > start_byte && buf_start < start_byte)
-			buf_offset = start_byte - buf_start;
-		else
-			buf_offset = 0;
-
-		bytes = min(PAGE_SIZE - pg_offset,
-			    PAGE_SIZE - (buf_offset % PAGE_SIZE));
-		bytes = min(bytes, bytes_left);
+	/*
+	 * Everything (in/out buf) should be at most one sector, there should
+	 * be no need to switch any input/output buffer.
+	 */
+	ret = zlib_inflate(&workspace->strm, Z_FINISH);
+	to_copy = min(workspace->strm.total_out, destlen);
+	if (ret != Z_STREAM_END)
+		goto out;
 
-		memcpy_to_page(dest_page, pg_offset,
-			       workspace->buf + buf_offset, bytes);
+	memcpy_to_page(dest_page, dest_pgoff, workspace->buf, to_copy);
 
-		pg_offset += bytes;
-		bytes_left -= bytes;
-next:
-		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = workspace->buf_size;
-	}
-
-	if (ret != Z_STREAM_END && bytes_left != 0)
+out:
+	if (unlikely(to_copy != destlen)) {
+		pr_warn_ratelimited("BTRFS: infalte failed, decompressed=%lu expected=%zu\n",
+					to_copy, destlen);
 		ret = -EIO;
-	else
+	} else {
 		ret = 0;
+	}
 
 	zlib_inflateEnd(&workspace->strm);
 
-	/*
-	 * this should only happen if zlib returned fewer bytes than we
-	 * expected.  btrfs_get_block is responsible for zeroing from the
-	 * end of the inline extent (destlen) to the end of the page
-	 */
-	if (pg_offset < destlen) {
-		memzero_page(dest_page, pg_offset, destlen - pg_offset);
-	}
+	if (unlikely(to_copy < destlen))
+		memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
 	return ret;
 }
 
-- 
GitLab


From 6a69631ec9b1b23784c012a855bbb23012a6dbeb Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 8 Jan 2024 19:38:45 +1030
Subject: [PATCH 3002/4076] btrfs: lzo: fix and simplify the inline extent
 decompression

[BUG]
If we have a filesystem with 4k sectorsize, and an inlined compressed
extent created like this:

	item 4 key (257 INODE_ITEM 0) itemoff 15863 itemsize 160
		generation 8 transid 8 size 4096 nbytes 4096
		block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0
		sequence 1 flags 0x0(none)
	item 5 key (257 INODE_REF 256) itemoff 15839 itemsize 24
		index 2 namelen 14 name: source_inlined
	item 6 key (257 EXTENT_DATA 0) itemoff 15770 itemsize 69
		generation 8 type 0 (inline)
		inline extent data size 48 ram_bytes 4096 compression 2 (lzo)

Then trying to reflink that extent in an aarch64 system with 64K page
size, the reflink would just fail:

  # xfs_io -f -c "reflink $mnt/source_inlined 0 60k 4k" $mnt/dest
  XFS_IOC_CLONE_RANGE: Input/output error

[CAUSE]
In zlib_decompress(), we didn't treat @start_byte as just a page offset,
but also use it as an indicator on whether we should error out, without
any proper explanation (this is from the very beginning of btrfs).

In reality, for subpage cases, although @start_byte can be non-zero,
we should never switch input/output buffer nor error out, since the whole
input/output buffer should never exceed one sector.

Note: The above assumption is only not true if we're going to support
multi-page sectorsize.

Thus the current code using @start_byte as a condition to switch
input/output buffer or finish the decompression is completely incorrect.

[FIX]
The fix involves several modifications:

- Rename @start_byte to @dest_pgoff to properly express its meaning

- Use @sectorsize other than PAGE_SIZE to properly initialize the
  output buffer size

- Use correct destination offset inside the destination page

- Use memcpy_to_page() to copy the contents to the destination page

- Use memzero_page() to zero out the tailing part

- Consider early end as an error

After the fix, even on 64K page sized aarch64, above reflink now
works as expected:

  # xfs_io -f -c "reflink $mnt/source_inlined 0 60k 4k" $mnt/dest
  linked 4096/4096 bytes at offset 61440

And results the correct file layout:

	item 9 key (258 INODE_ITEM 0) itemoff 15542 itemsize 160
		generation 10 transid 10 size 65536 nbytes 4096
		block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0
		sequence 1 flags 0x0(none)
	item 10 key (258 INODE_REF 256) itemoff 15528 itemsize 14
		index 3 namelen 4 name: dest
	item 11 key (258 XATTR_ITEM 3817753667) itemoff 15445 itemsize 83
		location key (0 UNKNOWN.0 0) type XATTR
		transid 10 data_len 37 name_len 16
		name: security.selinux
		data unconfined_u:object_r:unlabeled_t:s0
	item 12 key (258 EXTENT_DATA 61440) itemoff 15392 itemsize 53
		generation 10 type 1 (regular)
		extent data disk byte 13631488 nr 4096
		extent data offset 0 nr 4096 ram 4096
		extent compression 0 (none)

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.h |  2 +-
 fs/btrfs/lzo.c         | 34 +++++++++-------------------------
 2 files changed, 10 insertions(+), 26 deletions(-)

diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 2b4dfb1b010cd..afd7e50d073d4 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -159,7 +159,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out);
 int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int lzo_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 struct list_head *lzo_alloc_workspace(unsigned int level);
 void lzo_free_workspace(struct list_head *ws);
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 1131d5a29d612..e43bc0fdc74ec 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -425,16 +425,16 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 }
 
 int lzo_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	const u32 sectorsize = fs_info->sectorsize;
 	size_t in_len;
 	size_t out_len;
 	size_t max_segment_len = WORKSPACE_BUF_LENGTH;
 	int ret = 0;
-	char *kaddr;
-	unsigned long bytes;
 
 	if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
 		return -EUCLEAN;
@@ -451,7 +451,7 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
 	}
 	data_in += LZO_LEN;
 
-	out_len = PAGE_SIZE;
+	out_len = sectorsize;
 	ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
 	if (ret != LZO_E_OK) {
 		pr_warn("BTRFS: decompress failed!\n");
@@ -459,29 +459,13 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
 		goto out;
 	}
 
-	if (out_len < start_byte) {
+	ASSERT(out_len <= sectorsize);
+	memcpy_to_page(dest_page, dest_pgoff, workspace->buf, out_len);
+	/* Early end, considered as an error. */
+	if (unlikely(out_len < destlen)) {
 		ret = -EIO;
-		goto out;
+		memzero_page(dest_page, dest_pgoff + out_len, destlen - out_len);
 	}
-
-	/*
-	 * the caller is already checking against PAGE_SIZE, but lets
-	 * move this check closer to the memcpy/memset
-	 */
-	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
-	bytes = min_t(unsigned long, destlen, out_len - start_byte);
-
-	kaddr = kmap_local_page(dest_page);
-	memcpy(kaddr, workspace->buf + start_byte, bytes);
-
-	/*
-	 * btrfs_getblock is doing a zero on the tail of the page too,
-	 * but this will cover anything missing from the decompressed
-	 * data.
-	 */
-	if (bytes < destlen)
-		memset(kaddr+bytes, 0, destlen-bytes);
-	kunmap_local(kaddr);
 out:
 	return ret;
 }
-- 
GitLab


From 1e7f6def8b2370ecefb54b3c8f390ff894b0c51b Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 8 Jan 2024 19:38:46 +1030
Subject: [PATCH 3003/4076] btrfs: zstd: fix and simplify the inline extent
 decompression

[BUG]
If we have a filesystem with 4k sectorsize, and an inlined compressed
extent created like this:

	item 4 key (257 INODE_ITEM 0) itemoff 15863 itemsize 160
		generation 8 transid 8 size 4096 nbytes 4096
		block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0
		sequence 1 flags 0x0(none)
	item 5 key (257 INODE_REF 256) itemoff 15839 itemsize 24
		index 2 namelen 14 name: source_inlined
	item 6 key (257 EXTENT_DATA 0) itemoff 15770 itemsize 69
		generation 8 type 0 (inline)
		inline extent data size 48 ram_bytes 4096 compression 3 (zstd)

Then trying to reflink that extent in an aarch64 system with 64K page
size, the reflink would just fail:

  # xfs_io -f -c "reflink $mnt/source_inlined 0 60k 4k" $mnt/dest
  XFS_IOC_CLONE_RANGE: Input/output error

[CAUSE]
In zstd_decompress(), we didn't treat @start_byte as just a page offset,
but also use it as an indicator on whether we should error out, without
any proper explanation (this is copied from other decompression code).

In reality, for subpage cases, although @start_byte can be non-zero,
we should never switch input/output buffer nor error out, since the whole
input/output buffer should never exceed one sector, thus we should not
need to do any buffer switch.

Thus the current code using @start_byte as a condition to switch
input/output buffer or finish the decompression is completely incorrect.

[FIX]
The fix involves several modification:

- Rename @start_byte to @dest_pgoff to properly express its meaning

- Use @sectorsize other than PAGE_SIZE to properly initialize the
  output buffer size

- Use correct destination offset inside the destination page

- Simplify the main loop
  Since the input/output buffer should never switch, we only need one
  zstd_decompress_stream() call.

- Consider early end as an error

After the fix, even on 64K page sized aarch64, above reflink now
works as expected:

  # xfs_io -f -c "reflink $mnt/source_inlined 0 60k 4k" $mnt/dest
  linked 4096/4096 bytes at offset 61440

And results the correct file layout:

	item 9 key (258 INODE_ITEM 0) itemoff 15542 itemsize 160
		generation 10 transid 10 size 65536 nbytes 4096
		block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0
		sequence 1 flags 0x0(none)
	item 10 key (258 INODE_REF 256) itemoff 15528 itemsize 14
		index 3 namelen 4 name: dest
	item 11 key (258 XATTR_ITEM 3817753667) itemoff 15445 itemsize 83
		location key (0 UNKNOWN.0 0) type XATTR
		transid 10 data_len 37 name_len 16
		name: security.selinux
		data unconfined_u:object_r:unlabeled_t:s0
	item 12 key (258 EXTENT_DATA 61440) itemoff 15392 itemsize 53
		generation 10 type 1 (regular)
		extent data disk byte 13631488 nr 4096
		extent data offset 0 nr 4096 ram 4096
		extent compression 0 (none)

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.h |  2 +-
 fs/btrfs/zstd.c        | 75 +++++++++++++-----------------------------
 2 files changed, 23 insertions(+), 54 deletions(-)

diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index afd7e50d073d4..97fe3ebf11a22 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -169,7 +169,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out);
 int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int zstd_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 void zstd_init_workspace_manager(void);
 void zstd_cleanup_workspace_manager(void);
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 0d66db8bc1d47..346c46d88d07f 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -20,6 +20,7 @@
 #include "misc.h"
 #include "compression.h"
 #include "ctree.h"
+#include "super.h"
 
 #define ZSTD_BTRFS_MAX_WINDOWLOG 17
 #define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG)
@@ -618,80 +619,48 @@ done:
 }
 
 int zstd_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	const u32 sectorsize = fs_info->sectorsize;
 	zstd_dstream *stream;
 	int ret = 0;
-	size_t ret2;
-	unsigned long total_out = 0;
-	unsigned long pg_offset = 0;
+	unsigned long to_copy = 0;
 
 	stream = zstd_init_dstream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
 	if (!stream) {
 		pr_warn("BTRFS: zstd_init_dstream failed\n");
-		ret = -EIO;
 		goto finish;
 	}
 
-	destlen = min_t(size_t, destlen, PAGE_SIZE);
-
 	workspace->in_buf.src = data_in;
 	workspace->in_buf.pos = 0;
 	workspace->in_buf.size = srclen;
 
 	workspace->out_buf.dst = workspace->buf;
 	workspace->out_buf.pos = 0;
-	workspace->out_buf.size = PAGE_SIZE;
-
-	ret2 = 1;
-	while (pg_offset < destlen
-	       && workspace->in_buf.pos < workspace->in_buf.size) {
-		unsigned long buf_start;
-		unsigned long buf_offset;
-		unsigned long bytes;
-
-		/* Check if the frame is over and we still need more input */
-		if (ret2 == 0) {
-			pr_debug("BTRFS: zstd_decompress_stream ended early\n");
-			ret = -EIO;
-			goto finish;
-		}
-		ret2 = zstd_decompress_stream(stream, &workspace->out_buf,
-				&workspace->in_buf);
-		if (zstd_is_error(ret2)) {
-			pr_debug("BTRFS: zstd_decompress_stream returned %d\n",
-					zstd_get_error_code(ret2));
-			ret = -EIO;
-			goto finish;
-		}
-
-		buf_start = total_out;
-		total_out += workspace->out_buf.pos;
-		workspace->out_buf.pos = 0;
-
-		if (total_out <= start_byte)
-			continue;
-
-		if (total_out > start_byte && buf_start < start_byte)
-			buf_offset = start_byte - buf_start;
-		else
-			buf_offset = 0;
-
-		bytes = min_t(unsigned long, destlen - pg_offset,
-				workspace->out_buf.size - buf_offset);
-
-		memcpy_to_page(dest_page, pg_offset,
-			       workspace->out_buf.dst + buf_offset, bytes);
-
-		pg_offset += bytes;
+	workspace->out_buf.size = sectorsize;
+
+	/*
+	 * Since both input and output buffers should not exceed one sector,
+	 * one call should end the decompression.
+	 */
+	ret = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf);
+	if (zstd_is_error(ret)) {
+		pr_warn_ratelimited("BTRFS: zstd_decompress_stream return %d\n",
+				    zstd_get_error_code(ret));
+		goto finish;
 	}
-	ret = 0;
+	to_copy = workspace->out_buf.pos;
+	memcpy_to_page(dest_page, dest_pgoff + to_copy, workspace->out_buf.dst, to_copy);
 finish:
-	if (pg_offset < destlen) {
-		memzero_page(dest_page, pg_offset, destlen - pg_offset);
+	/* Error or early end. */
+	if (unlikely(to_copy < destlen)) {
+		ret = -EIO;
+		memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
 	}
 	return ret;
 }
-- 
GitLab


From f398e70dd69e6ceea71463a5380e6118f219197e Mon Sep 17 00:00:00 2001
From: Chung-Chiang Cheng <cccheng@synology.com>
Date: Fri, 12 Jan 2024 15:41:05 +0800
Subject: [PATCH 3004/4076] btrfs: tree-checker: fix inline ref size in error
 messages

The error message should accurately reflect the size rather than the
type.

Fixes: f82d1c7ca8ae ("btrfs: tree-checker: Add EXTENT_ITEM and METADATA_ITEM check")
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Chung-Chiang Cheng <cccheng@synology.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 50fdc69fdddf9..6eccf8496486c 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1436,7 +1436,7 @@ static int check_extent_item(struct extent_buffer *leaf,
 		if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
 			extent_err(leaf, slot,
 "inline ref item overflows extent item, ptr %lu iref size %u end %lu",
-				   ptr, inline_type, end);
+				   ptr, btrfs_extent_inline_ref_size(inline_type), end);
 			return -EUCLEAN;
 		}
 
-- 
GitLab


From a208b3f132b48e1f94f620024e66fea635925877 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Mon, 15 Jan 2024 20:30:26 +0100
Subject: [PATCH 3005/4076] btrfs: don't warn if discard range is not aligned
 to sector

There's a warning in btrfs_issue_discard() when the range is not aligned
to 512 bytes, originally added in 4d89d377bbb0 ("btrfs:
btrfs_issue_discard ensure offset/length are aligned to sector
boundaries"). We can't do sub-sector writes anyway so the adjustment is
the only thing that we can do and the warning is unnecessary.

CC: stable@vger.kernel.org # 4.19+
Reported-by: syzbot+4a4f1eba14eb5c3417d1@syzkaller.appspotmail.com
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6d680031211a1..8e8cc11112772 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1260,7 +1260,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 	u64 bytes_left, end;
 	u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT);
 
-	if (WARN_ON(start != aligned_start)) {
+	/* Adjust the range to be aligned to 512B sectors if necessary. */
+	if (start != aligned_start) {
 		len -= aligned_start - start;
 		len = round_down(len, 1 << SECTOR_SHIFT);
 		start = aligned_start;
-- 
GitLab


From 2018ef1d9ac3e95448b9206adc3425b0431c2411 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 10 Jan 2024 12:54:41 -0500
Subject: [PATCH 3006/4076] btrfs: use the original mount's mount options for
 the legacy reconfigure

btrfs/330, which tests our old trick to allow

mount -o ro,subvol=/x /dev/sda1 /foo
mount -o rw,subvol=/y /dev/sda1 /bar

fails on the block group tree.  This is because we aren't preserving the
mount options for what is essentially a remount, and thus we're ending
up without the FREE_SPACE_TREE mount option, which triggers our free
space tree delete codepath.  This isn't possible with the block group
tree and thus it falls over.

Fix this by making sure we copy the existing mount options for the
existing fs mount over in this case.

Fixes: f044b318675f ("btrfs: handle the ro->rw transition for mounting different subvolumes")
Reviewed-by: Neal Gompa <neal@gompa.dev>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3a677b808f0f7..f192f8fe0ce62 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1451,6 +1451,14 @@ static int btrfs_reconfigure(struct fs_context *fc)
 
 	btrfs_info_to_ctx(fs_info, &old_ctx);
 
+	/*
+	 * This is our "bind mount" trick, we don't want to allow the user to do
+	 * anything other than mount a different ro/rw and a different subvol,
+	 * all of the mount options should be maintained.
+	 */
+	if (mount_reconfigure)
+		ctx->mount_opt = old_ctx.mount_opt;
+
 	sync_filesystem(sb);
 	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
 
-- 
GitLab


From 1e61b8c672ab2f59b282c8d48a29c14b52c0f5b4 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 10 Jan 2024 17:14:21 -0500
Subject: [PATCH 3007/4076] btrfs: don't unconditionally call
 folio_start_writeback in subpage

In the normal case we check if a page is under writeback and skip it
before we attempt to begin writeback.

The exception is subpage metadata writes, where we know we don't have an
eb under writeback and we're doing it one eb at a time.  Since
b5612c368648 ("mm: return void from folio_start_writeback() and related
functions") we now will BUG_ON() if we call folio_start_writeback()
on a folio that's already under writeback.  Previously
folio_start_writeback() would bail if writeback was already started.

Fix this in the subpage code by checking if we have writeback set and
skipping it if we do.  This fixes the panic we were seeing on subpage.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/subpage.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index d9a30b93d543b..277dd6d312ee3 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -475,7 +475,8 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
-	folio_start_writeback(folio);
+	if (!folio_test_writeback(folio))
+		folio_start_writeback(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
-- 
GitLab


From 4525462dd0db9e86bb67c10dedbbaa4f8d62697d Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Thu, 18 Jan 2024 14:36:45 -0800
Subject: [PATCH 3008/4076] riscv: lib: Check if output in asm goto supported

The output field of an asm goto statement is not supported by all
compilers. If it is not supported, fallback to the non-optimized code.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Fixes: a04c192eabfb ("riscv: Add checksum library")
Link: https://lore.kernel.org/r/20240118-csum_remove_output_operands_asm_goto-v2-1-5d1b73cf93d4@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/lib/csum.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
index 06ce8e7250d98..af3df5274ccba 100644
--- a/arch/riscv/lib/csum.c
+++ b/arch/riscv/lib/csum.c
@@ -156,6 +156,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 	end = (const unsigned long *)(buff + len);
 	csum = do_csum_common(ptr, end, data);
 
+#ifdef CC_HAS_ASM_GOTO_TIED_OUTPUT
 	/*
 	 * Zbb support saves 6 instructions, so not worth checking without
 	 * alternatives if supported
@@ -214,6 +215,7 @@ end:
 		return csum >> 16;
 	}
 no_zbb:
+#endif /* CC_HAS_ASM_GOTO_TIED_OUTPUT */
 #ifndef CONFIG_32BIT
 	csum += ror64(csum, 32);
 	csum >>= 32;
-- 
GitLab


From f546c4282673497a06ecb6190b50ae7f6c85b02f Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 17 Jan 2024 11:02:25 +1030
Subject: [PATCH 3009/4076] btrfs: scrub: avoid use-after-free when chunk
 length is not 64K aligned

[BUG]
There is a bug report that, on a ext4-converted btrfs, scrub leads to
various problems, including:

- "unable to find chunk map" errors
  BTRFS info (device vdb): scrub: started on devid 1
  BTRFS critical (device vdb): unable to find chunk map for logical 2214744064 length 4096
  BTRFS critical (device vdb): unable to find chunk map for logical 2214744064 length 45056

  This would lead to unrepariable errors.

- Use-after-free KASAN reports:
  ==================================================================
  BUG: KASAN: slab-use-after-free in __blk_rq_map_sg+0x18f/0x7c0
  Read of size 8 at addr ffff8881013c9040 by task btrfs/909
  CPU: 0 PID: 909 Comm: btrfs Not tainted 6.7.0-x64v3-dbg #11 c50636e9419a8354555555245df535e380563b2b
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 2023.11-2 12/24/2023
  Call Trace:
   <TASK>
   dump_stack_lvl+0x43/0x60
   print_report+0xcf/0x640
   kasan_report+0xa6/0xd0
   __blk_rq_map_sg+0x18f/0x7c0
   virtblk_prep_rq.isra.0+0x215/0x6a0 [virtio_blk 19a65eeee9ae6fcf02edfad39bb9ddee07dcdaff]
   virtio_queue_rqs+0xc4/0x310 [virtio_blk 19a65eeee9ae6fcf02edfad39bb9ddee07dcdaff]
   blk_mq_flush_plug_list.part.0+0x780/0x860
   __blk_flush_plug+0x1ba/0x220
   blk_finish_plug+0x3b/0x60
   submit_initial_group_read+0x10a/0x290 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965]
   flush_scrub_stripes+0x38e/0x430 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965]
   scrub_stripe+0x82a/0xae0 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965]
   scrub_chunk+0x178/0x200 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965]
   scrub_enumerate_chunks+0x4bc/0xa30 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965]
   btrfs_scrub_dev+0x398/0x810 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965]
   btrfs_ioctl+0x4b9/0x3020 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965]
   __x64_sys_ioctl+0xbd/0x100
   do_syscall_64+0x5d/0xe0
   entry_SYSCALL_64_after_hwframe+0x63/0x6b
  RIP: 0033:0x7f47e5e0952b

- Crash, mostly due to above use-after-free

[CAUSE]
The converted fs has the following data chunk layout:

    item 2 key (FIRST_CHUNK_TREE CHUNK_ITEM 2214658048) itemoff 16025 itemsize 80
        length 86016 owner 2 stripe_len 65536 type DATA|single

For above logical bytenr 2214744064, it's at the chunk end
(2214658048 + 86016 = 2214744064).

This means btrfs_submit_bio() would split the bio, and trigger endio
function for both of the two halves.

However scrub_submit_initial_read() would only expect the endio function
to be called once, not any more.
This means the first endio function would already free the bbio::bio,
leaving the bvec freed, thus the 2nd endio call would lead to
use-after-free.

[FIX]
- Make sure scrub_read_endio() only updates bits in its range
  Since we may read less than 64K at the end of the chunk, we should not
  touch the bits beyond chunk boundary.

- Make sure scrub_submit_initial_read() only to read the chunk range
  This is done by calculating the real number of sectors we need to
  read, and add sector-by-sector to the bio.

Thankfully the scrub read repair path won't need extra fixes:

- scrub_stripe_submit_repair_read()
  With above fixes, we won't update error bit for range beyond chunk,
  thus scrub_stripe_submit_repair_read() should never submit any read
  beyond the chunk.

Reported-by: Rongrong <i@rong.moe>
Fixes: e02ee89baa66 ("btrfs: scrub: switch scrub_simple_mirror() to scrub_stripe infrastructure")
Tested-by: Rongrong <i@rong.moe>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/scrub.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index a01807cbd4d44..2d81b1a18a046 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1098,12 +1098,22 @@ out:
 static void scrub_read_endio(struct btrfs_bio *bbio)
 {
 	struct scrub_stripe *stripe = bbio->private;
+	struct bio_vec *bvec;
+	int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio));
+	int num_sectors;
+	u32 bio_size = 0;
+	int i;
+
+	ASSERT(sector_nr < stripe->nr_sectors);
+	bio_for_each_bvec_all(bvec, &bbio->bio, i)
+		bio_size += bvec->bv_len;
+	num_sectors = bio_size >> stripe->bg->fs_info->sectorsize_bits;
 
 	if (bbio->bio.bi_status) {
-		bitmap_set(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
-		bitmap_set(&stripe->error_bitmap, 0, stripe->nr_sectors);
+		bitmap_set(&stripe->io_error_bitmap, sector_nr, num_sectors);
+		bitmap_set(&stripe->error_bitmap, sector_nr, num_sectors);
 	} else {
-		bitmap_clear(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
+		bitmap_clear(&stripe->io_error_bitmap, sector_nr, num_sectors);
 	}
 	bio_put(&bbio->bio);
 	if (atomic_dec_and_test(&stripe->pending_io)) {
@@ -1701,6 +1711,9 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct btrfs_bio *bbio;
+	unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+				      stripe->bg->length - stripe->logical) >>
+				  fs_info->sectorsize_bits;
 	int mirror = stripe->mirror_num;
 
 	ASSERT(stripe->bg);
@@ -1715,14 +1728,16 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 	bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info,
 			       scrub_read_endio, stripe);
 
-	/* Read the whole stripe. */
 	bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT;
-	for (int i = 0; i < BTRFS_STRIPE_LEN >> PAGE_SHIFT; i++) {
+	/* Read the whole range inside the chunk boundary. */
+	for (unsigned int cur = 0; cur < nr_sectors; cur++) {
+		struct page *page = scrub_stripe_get_page(stripe, cur);
+		unsigned int pgoff = scrub_stripe_get_page_offset(stripe, cur);
 		int ret;
 
-		ret = bio_add_page(&bbio->bio, stripe->pages[i], PAGE_SIZE, 0);
+		ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
 		/* We should have allocated enough bio vectors. */
-		ASSERT(ret == PAGE_SIZE);
+		ASSERT(ret == fs_info->sectorsize);
 	}
 	atomic_inc(&stripe->pending_io);
 
-- 
GitLab


From 7f2d219e78e95a137a9c76fddac7ff8228260439 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 17 Jan 2024 11:02:26 +1030
Subject: [PATCH 3010/4076] btrfs: scrub: limit RST scrub to chunk boundary

[BUG]
If there is an extent beyond chunk boundary, currently RST scrub would
error out.

[CAUSE]
In scrub_submit_extent_sector_read(), we completely rely on
extent_sector_bitmap, which is populated using extent tree.

The extent tree can be corrupted that there is an extent item beyond a
chunk.

In that case, RST scrub would fail and error out.

[FIX]
Despite the extent_sector_bitmap usage, also limit the read to chunk
boundary.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/scrub.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2d81b1a18a046..0123d27289237 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1646,6 +1646,9 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
 {
 	struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
 	struct btrfs_bio *bbio = NULL;
+	unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+				      stripe->bg->length - stripe->logical) >>
+				  fs_info->sectorsize_bits;
 	u64 stripe_len = BTRFS_STRIPE_LEN;
 	int mirror = stripe->mirror_num;
 	int i;
@@ -1656,6 +1659,10 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
 		struct page *page = scrub_stripe_get_page(stripe, i);
 		unsigned int pgoff = scrub_stripe_get_page_offset(stripe, i);
 
+		/* We're beyond the chunk boundary, no need to read anymore. */
+		if (i >= nr_sectors)
+			break;
+
 		/* The current sector cannot be merged, submit the bio. */
 		if (bbio &&
 		    ((i > 0 &&
-- 
GitLab


From 17d49b7e47a1001c8796f05f4a2bbdef0a998213 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 3 Jan 2024 09:57:07 -0700
Subject: [PATCH 3011/4076] power: supply: bq24190_charger: Fix "initializer
 element is not constant" error

When building with a version of GCC prior to 8.x, there is an error
around non-constant initializer elements:

  drivers/power/supply/bq24190_charger.c:1978:16: error: initializer element is not constant
     .vbus_desc = bq24190_vbus_desc,
                  ^~~~~~~~~~~~~~~~~
  drivers/power/supply/bq24190_charger.c:1978:16: note: (near initialization for 'bq24190_chip_info_tbl[0].vbus_desc')
  drivers/power/supply/bq24190_charger.c:1989:16: error: initializer element is not constant
     .vbus_desc = bq24190_vbus_desc,
                  ^~~~~~~~~~~~~~~~~
  drivers/power/supply/bq24190_charger.c:1989:16: note: (near initialization for 'bq24190_chip_info_tbl[1].vbus_desc')
  drivers/power/supply/bq24190_charger.c:2000:16: error: initializer element is not constant
     .vbus_desc = bq24190_vbus_desc,
                  ^~~~~~~~~~~~~~~~~
  drivers/power/supply/bq24190_charger.c:2000:16: note: (near initialization for 'bq24190_chip_info_tbl[2].vbus_desc')
  drivers/power/supply/bq24190_charger.c:2011:16: error: initializer element is not constant
     .vbus_desc = bq24190_vbus_desc,
                  ^~~~~~~~~~~~~~~~~
  drivers/power/supply/bq24190_charger.c:2011:16: note: (near initialization for 'bq24190_chip_info_tbl[3].vbus_desc')
  drivers/power/supply/bq24190_charger.c:2022:16: error: initializer element is not constant
     .vbus_desc = bq24296_vbus_desc,
                  ^~~~~~~~~~~~~~~~~
  drivers/power/supply/bq24190_charger.c:2022:16: note: (near initialization for 'bq24190_chip_info_tbl[4].vbus_desc')

Clang versions prior to 17.x show a similar error:

  drivers/power/supply/bq24190_charger.c:1978:16: error: initializer element is not a compile-time constant
                  .vbus_desc = bq24190_vbus_desc,
                               ^~~~~~~~~~~~~~~~~
  1 error generated.

Newer compilers have decided to accept these structures as compile time
constants as an extension. To resolve this issue for all supported
compilers, change the vbus_desc member in 'struct bq24190_chip_info' to
a pointer, as it is only ever passed by reference anyways, and adjust
the assignments accordingly.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1973
Fixes: b150a703b56f ("power: supply: bq24190_charger: Add support for BQ24296")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Link: https://lore.kernel.org/r/20240103-fix-bq24190_charger-vbus_desc-non-const-v1-1-115ddf798c70@kernel.org
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq24190_charger.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c
index a8995a21fadbf..2b393eb5c2820 100644
--- a/drivers/power/supply/bq24190_charger.c
+++ b/drivers/power/supply/bq24190_charger.c
@@ -246,7 +246,7 @@ struct bq24190_dev_info {
 struct bq24190_chip_info {
 	int ichg_array_size;
 #ifdef CONFIG_REGULATOR
-	const struct regulator_desc vbus_desc;
+	const struct regulator_desc *vbus_desc;
 #endif
 	int (*check_chip)(struct bq24190_dev_info *bdi);
 	int (*set_chg_config)(struct bq24190_dev_info *bdi, const u8 chg_config);
@@ -728,7 +728,7 @@ static int bq24190_register_vbus_regulator(struct bq24190_dev_info *bdi)
 	else
 		cfg.init_data = &bq24190_vbus_init_data;
 	cfg.driver_data = bdi;
-	reg = devm_regulator_register(bdi->dev, &bdi->info->vbus_desc, &cfg);
+	reg = devm_regulator_register(bdi->dev, bdi->info->vbus_desc, &cfg);
 	if (IS_ERR(reg)) {
 		ret = PTR_ERR(reg);
 		dev_err(bdi->dev, "Can't register regulator: %d\n", ret);
@@ -1975,7 +1975,7 @@ static const struct bq24190_chip_info bq24190_chip_info_tbl[] = {
 	[BQ24190] = {
 		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
 #ifdef CONFIG_REGULATOR
-		.vbus_desc = bq24190_vbus_desc,
+		.vbus_desc = &bq24190_vbus_desc,
 #endif
 		.check_chip = bq24190_check_chip,
 		.set_chg_config = bq24190_battery_set_chg_config,
@@ -1986,7 +1986,7 @@ static const struct bq24190_chip_info bq24190_chip_info_tbl[] = {
 	[BQ24192] = {
 		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
 #ifdef CONFIG_REGULATOR
-		.vbus_desc = bq24190_vbus_desc,
+		.vbus_desc = &bq24190_vbus_desc,
 #endif
 		.check_chip = bq24190_check_chip,
 		.set_chg_config = bq24190_battery_set_chg_config,
@@ -1997,7 +1997,7 @@ static const struct bq24190_chip_info bq24190_chip_info_tbl[] = {
 	[BQ24192i] = {
 		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
 #ifdef CONFIG_REGULATOR
-		.vbus_desc = bq24190_vbus_desc,
+		.vbus_desc = &bq24190_vbus_desc,
 #endif
 		.check_chip = bq24190_check_chip,
 		.set_chg_config = bq24190_battery_set_chg_config,
@@ -2008,7 +2008,7 @@ static const struct bq24190_chip_info bq24190_chip_info_tbl[] = {
 	[BQ24196] = {
 		.ichg_array_size = ARRAY_SIZE(bq24190_ccc_ichg_values),
 #ifdef CONFIG_REGULATOR
-		.vbus_desc = bq24190_vbus_desc,
+		.vbus_desc = &bq24190_vbus_desc,
 #endif
 		.check_chip = bq24190_check_chip,
 		.set_chg_config = bq24190_battery_set_chg_config,
@@ -2019,7 +2019,7 @@ static const struct bq24190_chip_info bq24190_chip_info_tbl[] = {
 	[BQ24296] = {
 		.ichg_array_size = BQ24296_CCC_ICHG_VALUES_LEN,
 #ifdef CONFIG_REGULATOR
-		.vbus_desc = bq24296_vbus_desc,
+		.vbus_desc = &bq24296_vbus_desc,
 #endif
 		.check_chip = bq24296_check_chip,
 		.set_chg_config = bq24296_battery_set_chg_config,
-- 
GitLab


From d7851dc13d87688e2c532f0e77c2bd29f902d6cf Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 17 Jan 2024 17:59:59 -0600
Subject: [PATCH 3012/4076] smb3: minor documentation updates

Update the usage documentation to include some missing
configuration options.  Update the todo list documentation
for cifs.ko

Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 Documentation/admin-guide/cifs/todo.rst  | 36 +++++++++++++-----------
 Documentation/admin-guide/cifs/usage.rst |  8 +++++-
 2 files changed, 27 insertions(+), 17 deletions(-)

diff --git a/Documentation/admin-guide/cifs/todo.rst b/Documentation/admin-guide/cifs/todo.rst
index 2646ed2e2d3e3..e46c360013947 100644
--- a/Documentation/admin-guide/cifs/todo.rst
+++ b/Documentation/admin-guide/cifs/todo.rst
@@ -2,7 +2,8 @@
 TODO
 ====
 
-Version 2.14 December 21, 2018
+As of 6.7 kernel. See https://wiki.samba.org/index.php/LinuxCIFSKernel
+for list of features added by release
 
 A Partial List of Missing Features
 ==================================
@@ -12,22 +13,22 @@ for visible, important contributions to this module.  Here
 is a partial list of the known problems and missing features:
 
 a) SMB3 (and SMB3.1.1) missing optional features:
+   multichannel performance optimizations, algorithmic channel selection,
+   directory leases optimizations,
+   support for faster packet signing (GMAC),
+   support for compression over the network,
+   T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
+   are currently the only two server side copy mechanisms supported)
 
-   - multichannel (partially integrated), integration of multichannel with RDMA
-   - directory leases (improved metadata caching). Currently only implemented for root dir
-   - T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
-     currently the only two server side copy mechanisms supported)
+b) Better optimized compounding and error handling for sparse file support,
+   perhaps addition of new optional SMB3.1.1 fsctls to make collapse range
+   and insert range more atomic
 
-b) improved sparse file support (fiemap and SEEK_HOLE are implemented
-   but additional features would be supportable by the protocol such
-   as FALLOC_FL_COLLAPSE_RANGE and FALLOC_FL_INSERT_RANGE)
-
-c) Directory entry caching relies on a 1 second timer, rather than
-   using Directory Leases, currently only the root file handle is cached longer
-   by leveraging Directory Leases
+c) Support for SMB3.1.1 over QUIC (and perhaps other socket based protocols
+   like SCTP)
 
 d) quota support (needs minor kernel change since quota calls otherwise
-    won't make it to network filesystems or deviceless filesystems).
+   won't make it to network filesystems or deviceless filesystems).
 
 e) Additional use cases can be optimized to use "compounding" (e.g.
    open/query/close and open/setinfo/close) to reduce the number of
@@ -92,10 +93,13 @@ t) split cifs and smb3 support into separate modules so legacy (and less
 
 v) Additional testing of POSIX Extensions for SMB3.1.1
 
-w) Add support for additional strong encryption types, and additional spnego
-   authentication mechanisms (see MS-SMB2).  GCM-256 is now partially implemented.
+w) Support for the Mac SMB3.1.1 extensions to improve interop with Apple servers
+
+x) Support for additional authentication options (e.g. IAKERB, peer-to-peer
+   Kerberos, SCRAM and others supported by existing servers)
 
-x) Finish support for SMB3.1.1 compression
+y) Improved tracing, more eBPF trace points, better scripts for performance
+   analysis
 
 Known Bugs
 ==========
diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst
index 5f936b4b60188..aa8290a29dc88 100644
--- a/Documentation/admin-guide/cifs/usage.rst
+++ b/Documentation/admin-guide/cifs/usage.rst
@@ -81,7 +81,7 @@ much older and less secure than the default dialect SMB3 which includes
 many advanced security features such as downgrade attack detection
 and encrypted shares and stronger signing and authentication algorithms.
 There are additional mount options that may be helpful for SMB3 to get
-improved POSIX behavior (NB: can use vers=3.0 to force only SMB3, never 2.1):
+improved POSIX behavior (NB: can use vers=3 to force SMB3 or later, never 2.1):
 
    ``mfsymlinks`` and either ``cifsacl`` or ``modefromsid`` (usually with ``idsfromsid``)
 
@@ -715,6 +715,7 @@ DebugData		Displays information about active CIFS sessions and
 Stats			Lists summary resource usage information as well as per
 			share statistics.
 open_files		List all the open file handles on all active SMB sessions.
+mount_params            List of all mount parameters available for the module
 ======================= =======================================================
 
 Configuration pseudo-files:
@@ -864,6 +865,11 @@ i.e.::
 
     echo "value" > /sys/module/cifs/parameters/<param>
 
+More detailed descriptions of the available module parameters and their values
+can be seen by doing:
+
+    modinfo cifs (or modinfo smb3)
+
 ================= ==========================================================
 1. enable_oplocks Enable or disable oplocks. Oplocks are enabled by default.
 		  [Y/y/1]. To disable use any of [N/n/0].
-- 
GitLab


From 936eba9cfb5cfbf6a2c762cd163605f2b784e03e Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 17 Jan 2024 05:55:39 +0000
Subject: [PATCH 3013/4076] cifs: open_cached_dir should not rely on primary
 channel

open_cached_dir today selects ses->server a.k.a primary channel
to send requests. When multichannel is used, the primary
channel maybe down. So it does not make sense to rely only
on that channel.

This fix makes this function pick a channel with the standard
helper function cifs_pick_channel.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index d64a306a414be..9718926205047 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -151,7 +151,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 		return -EOPNOTSUPP;
 
 	ses = tcon->ses;
-	server = ses->server;
+	server = cifs_pick_channel(ses);
 	cfids = tcon->cfids;
 
 	if (!server->ops->new_lease_key)
-- 
GitLab


From 268b8b5797becb242013fcd63173eb28c007c8ae Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 10 Jan 2024 10:48:36 +0000
Subject: [PATCH 3014/4076] cifs: pick channel for tcon and tdis

Today, the tree connect and disconnect requests are
sent on the primary channel only. However, the new
multichannel logic allows the session to remain active
even if one of the channels are alive. So a tree connect
can now be triggered during a reconnect on any of
its channels.

This change changes tcon and tdis calls to pick an
active channel instead of the first one.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 50f6bf16b6245..f8d70660ba292 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -1958,10 +1958,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	__le16 *unc_path = NULL;
 	int flags = 0;
 	unsigned int total_len;
-	struct TCP_Server_Info *server;
-
-	/* always use master channel */
-	server = ses->server;
+	struct TCP_Server_Info *server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "TCON\n");
 
@@ -2094,6 +2091,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 	struct smb2_tree_disconnect_req *req; /* response is trivial */
 	int rc = 0;
 	struct cifs_ses *ses = tcon->ses;
+	struct TCP_Server_Info *server = cifs_pick_channel(ses);
 	int flags = 0;
 	unsigned int total_len;
 	struct kvec iov[1];
@@ -2116,7 +2114,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 
 	invalidate_all_cached_dirs(tcon);
 
-	rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, ses->server,
+	rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, server,
 				 (void **) &req,
 				 &total_len);
 	if (rc)
@@ -2134,7 +2132,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
-	rc = cifs_send_recv(xid, ses, ses->server,
+	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buf_type, flags, &rsp_iov);
 	cifs_small_buf_release(req);
 	if (rc) {
-- 
GitLab


From 7f738527a7a03021c7e1b02e188f446845f05eb6 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 17 Jan 2024 06:21:33 +0000
Subject: [PATCH 3015/4076] cifs: new nt status codes from MS-SMB2

MS-SMB2 spec has introduced two new status codes,
STATUS_SERVER_UNAVAILABLE and STATUS_FILE_NOT_AVAILABLE
which are to be treated as retryable errors.

This change adds these to the available mappings and
maps them to Linux errno EAGAIN.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2maperror.c | 2 ++
 fs/smb/client/smb2status.h   | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c
index 1a90dd78b238f..ac1895358908a 100644
--- a/fs/smb/client/smb2maperror.c
+++ b/fs/smb/client/smb2maperror.c
@@ -1210,6 +1210,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_INVALID_TASK_INDEX, -EIO, "STATUS_INVALID_TASK_INDEX"},
 	{STATUS_THREAD_ALREADY_IN_TASK, -EIO, "STATUS_THREAD_ALREADY_IN_TASK"},
 	{STATUS_CALLBACK_BYPASS, -EIO, "STATUS_CALLBACK_BYPASS"},
+	{STATUS_SERVER_UNAVAILABLE, -EAGAIN, "STATUS_SERVER_UNAVAILABLE"},
+	{STATUS_FILE_NOT_AVAILABLE, -EAGAIN, "STATUS_FILE_NOT_AVAILABLE"},
 	{STATUS_PORT_CLOSED, -EIO, "STATUS_PORT_CLOSED"},
 	{STATUS_MESSAGE_LOST, -EIO, "STATUS_MESSAGE_LOST"},
 	{STATUS_INVALID_MESSAGE, -EIO, "STATUS_INVALID_MESSAGE"},
diff --git a/fs/smb/client/smb2status.h b/fs/smb/client/smb2status.h
index a9e958166fc53..9c6d79b0bd497 100644
--- a/fs/smb/client/smb2status.h
+++ b/fs/smb/client/smb2status.h
@@ -982,6 +982,8 @@ struct ntstatus {
 #define STATUS_INVALID_TASK_INDEX cpu_to_le32(0xC0000501)
 #define STATUS_THREAD_ALREADY_IN_TASK cpu_to_le32(0xC0000502)
 #define STATUS_CALLBACK_BYPASS cpu_to_le32(0xC0000503)
+#define STATUS_SERVER_UNAVAILABLE cpu_to_le32(0xC0000466)
+#define STATUS_FILE_NOT_AVAILABLE cpu_to_le32(0xC0000467)
 #define STATUS_PORT_CLOSED cpu_to_le32(0xC0000700)
 #define STATUS_MESSAGE_LOST cpu_to_le32(0xC0000701)
 #define STATUS_INVALID_MESSAGE cpu_to_le32(0xC0000702)
-- 
GitLab


From 367188297254e7f81e3c3c94e6d6a623f757c4cb Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 16:11:09 +0530
Subject: [PATCH 3016/4076] RISC-V: KVM: Allow Zbc extension for Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zbc extension for Guest/VM.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 1 +
 arch/riscv/kvm/vcpu_onereg.c      | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index d6b7a5b958742..bbff9c7e8f3f8 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -139,6 +139,7 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZIHPM,
 	KVM_RISCV_ISA_EXT_SMSTATEEN,
 	KVM_RISCV_ISA_EXT_ZICOND,
+	KVM_RISCV_ISA_EXT_ZBC,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index fc34557f5356e..4522fdfec94ef 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -42,6 +42,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(SVPBMT),
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
+	KVM_ISA_EXT_ARR(ZBC),
 	KVM_ISA_EXT_ARR(ZBS),
 	KVM_ISA_EXT_ARR(ZICBOM),
 	KVM_ISA_EXT_ARR(ZICBOZ),
@@ -92,6 +93,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
 	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_RISCV_ISA_EXT_ZBC:
 	case KVM_RISCV_ISA_EXT_ZBS:
 	case KVM_RISCV_ISA_EXT_ZICNTR:
 	case KVM_RISCV_ISA_EXT_ZICOND:
-- 
GitLab


From ac396141308d07a9534c5a7f1f7c80cb95e35b20 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 18:47:23 +0530
Subject: [PATCH 3017/4076] KVM: riscv: selftests: Add Zbc extension to
 get-reg-list test

The KVM RISC-V allows Zbc extension for Guest/VM so let us add
this extension to get-reg-list test.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/riscv/get-reg-list.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6652108816db4..2e8e1c52b9efb 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -49,6 +49,7 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
@@ -394,6 +395,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(SVPBMT),
 		KVM_ISA_EXT_ARR(ZBA),
 		KVM_ISA_EXT_ARR(ZBB),
+		KVM_ISA_EXT_ARR(ZBC),
 		KVM_ISA_EXT_ARR(ZBS),
 		KVM_ISA_EXT_ARR(ZICBOM),
 		KVM_ISA_EXT_ARR(ZICBOZ),
@@ -888,6 +890,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
 KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
 KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
@@ -914,6 +917,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_svpbmt,
 	&config_zba,
 	&config_zbb,
+	&config_zbc,
 	&config_zbs,
 	&config_zicbom,
 	&config_zicboz,
-- 
GitLab


From f370b4e668f017f523968f7490163fa922dcd92e Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 20:36:36 +0530
Subject: [PATCH 3018/4076] RISC-V: KVM: Allow scalar crypto extensions for
 Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable scalar crypto extensions for
Guest/VM. This includes extensions Zbkb, Zbkc, Zbkx, Zknd, Zkne,
Zknh, Zkr, Zksed, Zksh, and Zkt.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 10 ++++++++++
 arch/riscv/kvm/vcpu_onereg.c      | 20 ++++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index bbff9c7e8f3f8..453edf620b87b 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -140,6 +140,16 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_SMSTATEEN,
 	KVM_RISCV_ISA_EXT_ZICOND,
 	KVM_RISCV_ISA_EXT_ZBC,
+	KVM_RISCV_ISA_EXT_ZBKB,
+	KVM_RISCV_ISA_EXT_ZBKC,
+	KVM_RISCV_ISA_EXT_ZBKX,
+	KVM_RISCV_ISA_EXT_ZKND,
+	KVM_RISCV_ISA_EXT_ZKNE,
+	KVM_RISCV_ISA_EXT_ZKNH,
+	KVM_RISCV_ISA_EXT_ZKR,
+	KVM_RISCV_ISA_EXT_ZKSED,
+	KVM_RISCV_ISA_EXT_ZKSH,
+	KVM_RISCV_ISA_EXT_ZKT,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 4522fdfec94ef..680da2a55da25 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -43,6 +43,9 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
 	KVM_ISA_EXT_ARR(ZBC),
+	KVM_ISA_EXT_ARR(ZBKB),
+	KVM_ISA_EXT_ARR(ZBKC),
+	KVM_ISA_EXT_ARR(ZBKX),
 	KVM_ISA_EXT_ARR(ZBS),
 	KVM_ISA_EXT_ARR(ZICBOM),
 	KVM_ISA_EXT_ARR(ZICBOZ),
@@ -52,6 +55,13 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZIFENCEI),
 	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 	KVM_ISA_EXT_ARR(ZIHPM),
+	KVM_ISA_EXT_ARR(ZKND),
+	KVM_ISA_EXT_ARR(ZKNE),
+	KVM_ISA_EXT_ARR(ZKNH),
+	KVM_ISA_EXT_ARR(ZKR),
+	KVM_ISA_EXT_ARR(ZKSED),
+	KVM_ISA_EXT_ARR(ZKSH),
+	KVM_ISA_EXT_ARR(ZKT),
 };
 
 static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
@@ -94,6 +104,9 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
 	case KVM_RISCV_ISA_EXT_ZBC:
+	case KVM_RISCV_ISA_EXT_ZBKB:
+	case KVM_RISCV_ISA_EXT_ZBKC:
+	case KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_RISCV_ISA_EXT_ZBS:
 	case KVM_RISCV_ISA_EXT_ZICNTR:
 	case KVM_RISCV_ISA_EXT_ZICOND:
@@ -101,6 +114,13 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_ZIFENCEI:
 	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_RISCV_ISA_EXT_ZIHPM:
+	case KVM_RISCV_ISA_EXT_ZKND:
+	case KVM_RISCV_ISA_EXT_ZKNE:
+	case KVM_RISCV_ISA_EXT_ZKNH:
+	case KVM_RISCV_ISA_EXT_ZKR:
+	case KVM_RISCV_ISA_EXT_ZKSED:
+	case KVM_RISCV_ISA_EXT_ZKSH:
+	case KVM_RISCV_ISA_EXT_ZKT:
 		return false;
 	/* Extensions which can be disabled using Smstateen */
 	case KVM_RISCV_ISA_EXT_SSAIA:
-- 
GitLab


From 14d70de562dfd78be638fc59b0a323235acc67be Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 20:47:58 +0530
Subject: [PATCH 3019/4076] KVM: riscv: selftests: Add scaler crypto extensions
 to get-reg-list test

The KVM RISC-V allows scaler crypto extensions for Guest/VM so let us
add these extensions to get-reg-list test. This includes extensions
Zbkb, Zbkc, Zbkx, Zknd, Zkne, Zknh, Zkr, Zksed, Zksh, and Zkt.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/riscv/get-reg-list.c        | 40 +++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 2e8e1c52b9efb..3f5674fbd6806 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -50,6 +50,9 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
@@ -59,6 +62,13 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKND:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNE:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
 	/*
 	 * Like ISA_EXT registers, SBI_EXT registers are only visible when the
 	 * host supports them and disabling them does not affect the visibility
@@ -396,6 +406,9 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZBA),
 		KVM_ISA_EXT_ARR(ZBB),
 		KVM_ISA_EXT_ARR(ZBC),
+		KVM_ISA_EXT_ARR(ZBKB),
+		KVM_ISA_EXT_ARR(ZBKC),
+		KVM_ISA_EXT_ARR(ZBKX),
 		KVM_ISA_EXT_ARR(ZBS),
 		KVM_ISA_EXT_ARR(ZICBOM),
 		KVM_ISA_EXT_ARR(ZICBOZ),
@@ -405,6 +418,13 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZIFENCEI),
 		KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 		KVM_ISA_EXT_ARR(ZIHPM),
+		KVM_ISA_EXT_ARR(ZKND),
+		KVM_ISA_EXT_ARR(ZKNE),
+		KVM_ISA_EXT_ARR(ZKNH),
+		KVM_ISA_EXT_ARR(ZKR),
+		KVM_ISA_EXT_ARR(ZKSED),
+		KVM_ISA_EXT_ARR(ZKSH),
+		KVM_ISA_EXT_ARR(ZKT),
 	};
 
 	if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name))
@@ -891,6 +911,9 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
 KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
@@ -900,6 +923,13 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR);
 KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI);
 KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE);
 KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
+KVM_ISA_EXT_SIMPLE_CONFIG(zknd, ZKND);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkne, ZKNE);
+KVM_ISA_EXT_SIMPLE_CONFIG(zknh, ZKNH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR);
+KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
 
 struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_base,
@@ -918,6 +948,9 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zba,
 	&config_zbb,
 	&config_zbc,
+	&config_zbkb,
+	&config_zbkc,
+	&config_zbkx,
 	&config_zbs,
 	&config_zicbom,
 	&config_zicboz,
@@ -927,5 +960,12 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zifencei,
 	&config_zihintpause,
 	&config_zihpm,
+	&config_zknd,
+	&config_zkne,
+	&config_zknh,
+	&config_zkr,
+	&config_zksed,
+	&config_zksh,
+	&config_zkt,
 };
 int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
-- 
GitLab


From afd1ef3adfbc36e35fcf4f742fd90aea6480a276 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 21:38:43 +0530
Subject: [PATCH 3020/4076] RISC-V: KVM: Allow vector crypto extensions for
 Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable vector crypto extensions for
Guest/VM. This includes extensions Zvbb, Zvbc, Zvkb, Zvkg,
Zvkned, Zvknha, Zvknhb, Zvksed, Zvksh, and Zvkt.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 10 ++++++++++
 arch/riscv/kvm/vcpu_onereg.c      | 20 ++++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 453edf620b87b..e68ba0819ef75 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -150,6 +150,16 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZKSED,
 	KVM_RISCV_ISA_EXT_ZKSH,
 	KVM_RISCV_ISA_EXT_ZKT,
+	KVM_RISCV_ISA_EXT_ZVBB,
+	KVM_RISCV_ISA_EXT_ZVBC,
+	KVM_RISCV_ISA_EXT_ZVKB,
+	KVM_RISCV_ISA_EXT_ZVKG,
+	KVM_RISCV_ISA_EXT_ZVKNED,
+	KVM_RISCV_ISA_EXT_ZVKNHA,
+	KVM_RISCV_ISA_EXT_ZVKNHB,
+	KVM_RISCV_ISA_EXT_ZVKSED,
+	KVM_RISCV_ISA_EXT_ZVKSH,
+	KVM_RISCV_ISA_EXT_ZVKT,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 680da2a55da25..297acdcfed775 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -62,6 +62,16 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZKSED),
 	KVM_ISA_EXT_ARR(ZKSH),
 	KVM_ISA_EXT_ARR(ZKT),
+	KVM_ISA_EXT_ARR(ZVBB),
+	KVM_ISA_EXT_ARR(ZVBC),
+	KVM_ISA_EXT_ARR(ZVKB),
+	KVM_ISA_EXT_ARR(ZVKG),
+	KVM_ISA_EXT_ARR(ZVKNED),
+	KVM_ISA_EXT_ARR(ZVKNHA),
+	KVM_ISA_EXT_ARR(ZVKNHB),
+	KVM_ISA_EXT_ARR(ZVKSED),
+	KVM_ISA_EXT_ARR(ZVKSH),
+	KVM_ISA_EXT_ARR(ZVKT),
 };
 
 static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
@@ -121,6 +131,16 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_ZKSED:
 	case KVM_RISCV_ISA_EXT_ZKSH:
 	case KVM_RISCV_ISA_EXT_ZKT:
+	case KVM_RISCV_ISA_EXT_ZVBB:
+	case KVM_RISCV_ISA_EXT_ZVBC:
+	case KVM_RISCV_ISA_EXT_ZVKB:
+	case KVM_RISCV_ISA_EXT_ZVKG:
+	case KVM_RISCV_ISA_EXT_ZVKNED:
+	case KVM_RISCV_ISA_EXT_ZVKNHA:
+	case KVM_RISCV_ISA_EXT_ZVKNHB:
+	case KVM_RISCV_ISA_EXT_ZVKSED:
+	case KVM_RISCV_ISA_EXT_ZVKSH:
+	case KVM_RISCV_ISA_EXT_ZVKT:
 		return false;
 	/* Extensions which can be disabled using Smstateen */
 	case KVM_RISCV_ISA_EXT_SSAIA:
-- 
GitLab


From 2ddf79070f7edada19fecec57d8591d6b718fa53 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 21:54:33 +0530
Subject: [PATCH 3021/4076] KVM: riscv: selftests: Add vector crypto extensions
 to get-reg-list test

The KVM RISC-V allows vector crypto extensions for Guest/VM so let us
add these extensions to get-reg-list test. This includes extensions
Zvbb, Zvbc, Zvkb, Zvkg, Zvkned, Zvknha, Zvknhb, Zvksed, Zvksh, and Zvkt.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 .../selftests/kvm/riscv/get-reg-list.c        | 40 +++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 3f5674fbd6806..6b4ba06e26e57 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -69,6 +69,16 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKG:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKT:
 	/*
 	 * Like ISA_EXT registers, SBI_EXT registers are only visible when the
 	 * host supports them and disabling them does not affect the visibility
@@ -425,6 +435,16 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZKSED),
 		KVM_ISA_EXT_ARR(ZKSH),
 		KVM_ISA_EXT_ARR(ZKT),
+		KVM_ISA_EXT_ARR(ZVBB),
+		KVM_ISA_EXT_ARR(ZVBC),
+		KVM_ISA_EXT_ARR(ZVKB),
+		KVM_ISA_EXT_ARR(ZVKG),
+		KVM_ISA_EXT_ARR(ZVKNED),
+		KVM_ISA_EXT_ARR(ZVKNHA),
+		KVM_ISA_EXT_ARR(ZVKNHB),
+		KVM_ISA_EXT_ARR(ZVKSED),
+		KVM_ISA_EXT_ARR(ZVKSH),
+		KVM_ISA_EXT_ARR(ZVKT),
 	};
 
 	if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name))
@@ -930,6 +950,16 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR);
 KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED);
 KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
 KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkg, ZVKG);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkned, ZVKNED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvknha, ZVKNHA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvknhb, ZVKNHB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvksed, ZVKSED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvksh, ZVKSH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkt, ZVKT);
 
 struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_base,
@@ -967,5 +997,15 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zksed,
 	&config_zksh,
 	&config_zkt,
+	&config_zvbb,
+	&config_zvbc,
+	&config_zvkb,
+	&config_zvkg,
+	&config_zvkned,
+	&config_zvknha,
+	&config_zvknhb,
+	&config_zvksed,
+	&config_zvksh,
+	&config_zvkt,
 };
 int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
-- 
GitLab


From f3901ece5b3894177d1816208d0fb06b295617e0 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:01:55 +0530
Subject: [PATCH 3022/4076] RISC-V: KVM: Allow Zfh[min] extensions for Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zfh[min] extensions for Guest/VM.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 2 ++
 arch/riscv/kvm/vcpu_onereg.c      | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index e68ba0819ef75..a8411ae5cc85c 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -160,6 +160,8 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZVKSED,
 	KVM_RISCV_ISA_EXT_ZVKSH,
 	KVM_RISCV_ISA_EXT_ZVKT,
+	KVM_RISCV_ISA_EXT_ZFH,
+	KVM_RISCV_ISA_EXT_ZFHMIN,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 297acdcfed775..e00745bf05905 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -47,6 +47,8 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZBKC),
 	KVM_ISA_EXT_ARR(ZBKX),
 	KVM_ISA_EXT_ARR(ZBS),
+	KVM_ISA_EXT_ARR(ZFH),
+	KVM_ISA_EXT_ARR(ZFHMIN),
 	KVM_ISA_EXT_ARR(ZICBOM),
 	KVM_ISA_EXT_ARR(ZICBOZ),
 	KVM_ISA_EXT_ARR(ZICNTR),
@@ -118,6 +120,8 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_ZBKC:
 	case KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_RISCV_ISA_EXT_ZFH:
+	case KVM_RISCV_ISA_EXT_ZFHMIN:
 	case KVM_RISCV_ISA_EXT_ZICNTR:
 	case KVM_RISCV_ISA_EXT_ZICOND:
 	case KVM_RISCV_ISA_EXT_ZICSR:
-- 
GitLab


From 496ee21a17ce45e92483fdf1827ba91f4867f160 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:11:02 +0530
Subject: [PATCH 3023/4076] KVM: riscv: selftests: Add Zfh[min] extensions to
 get-reg-list test

The KVM RISC-V allows Zfh[min] extensions for Guest/VM so let us
add these extensions to get-reg-list test.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/riscv/get-reg-list.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6b4ba06e26e57..eeb9857feede1 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -54,6 +54,8 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR:
@@ -420,6 +422,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZBKC),
 		KVM_ISA_EXT_ARR(ZBKX),
 		KVM_ISA_EXT_ARR(ZBS),
+		KVM_ISA_EXT_ARR(ZFH),
+		KVM_ISA_EXT_ARR(ZFHMIN),
 		KVM_ISA_EXT_ARR(ZICBOM),
 		KVM_ISA_EXT_ARR(ZICBOZ),
 		KVM_ISA_EXT_ARR(ZICNTR),
@@ -935,6 +939,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR);
@@ -982,6 +988,8 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zbkc,
 	&config_zbkx,
 	&config_zbs,
+	&config_zfh,
+	&config_zfhmin,
 	&config_zicbom,
 	&config_zicboz,
 	&config_zicntr,
-- 
GitLab


From ab6da9cdc3f3d1d091d657219fb6e98f710ee098 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:15:10 +0530
Subject: [PATCH 3024/4076] RISC-V: KVM: Allow Zihintntl extension for Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zihintntl extension for Guest/VM.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 1 +
 arch/riscv/kvm/vcpu_onereg.c      | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index a8411ae5cc85c..95e4d5a1793e7 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -162,6 +162,7 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZVKT,
 	KVM_RISCV_ISA_EXT_ZFH,
 	KVM_RISCV_ISA_EXT_ZFHMIN,
+	KVM_RISCV_ISA_EXT_ZIHINTNTL,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index e00745bf05905..deceaa6f9cfa2 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -55,6 +55,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZICOND),
 	KVM_ISA_EXT_ARR(ZICSR),
 	KVM_ISA_EXT_ARR(ZIFENCEI),
+	KVM_ISA_EXT_ARR(ZIHINTNTL),
 	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 	KVM_ISA_EXT_ARR(ZIHPM),
 	KVM_ISA_EXT_ARR(ZKND),
@@ -126,6 +127,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_ZICOND:
 	case KVM_RISCV_ISA_EXT_ZICSR:
 	case KVM_RISCV_ISA_EXT_ZIFENCEI:
+	case KVM_RISCV_ISA_EXT_ZIHINTNTL:
 	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_RISCV_ISA_EXT_ZIHPM:
 	case KVM_RISCV_ISA_EXT_ZKND:
-- 
GitLab


From 1a3bc507821d24a80a6af8beb08af8032c33ebd7 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:22:06 +0530
Subject: [PATCH 3025/4076] KVM: riscv: selftests: Add Zihintntl extension to
 get-reg-list test

The KVM RISC-V allows Zihintntl extension for Guest/VM so let us
add this extension to get-reg-list test.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/riscv/get-reg-list.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index eeb9857feede1..c9a45e17267bf 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -62,6 +62,7 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTNTL:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKND:
@@ -430,6 +431,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZICOND),
 		KVM_ISA_EXT_ARR(ZICSR),
 		KVM_ISA_EXT_ARR(ZIFENCEI),
+		KVM_ISA_EXT_ARR(ZIHINTNTL),
 		KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 		KVM_ISA_EXT_ARR(ZIHPM),
 		KVM_ISA_EXT_ARR(ZKND),
@@ -947,6 +949,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR);
 KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI);
+KVM_ISA_EXT_SIMPLE_CONFIG(zihintntl, ZIHINTNTL);
 KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE);
 KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
 KVM_ISA_EXT_SIMPLE_CONFIG(zknd, ZKND);
@@ -996,6 +999,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zicond,
 	&config_zicsr,
 	&config_zifencei,
+	&config_zihintntl,
 	&config_zihintpause,
 	&config_zihpm,
 	&config_zknd,
-- 
GitLab


From f46300285926c2b0d0c79bf40c87d45e169cecb6 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:26:05 +0530
Subject: [PATCH 3026/4076] RISC-V: KVM: Allow Zvfh[min] extensions for
 Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zvfh[min] extensions for Guest/VM.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 2 ++
 arch/riscv/kvm/vcpu_onereg.c      | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 95e4d5a1793e7..7d07722aa1aaf 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -163,6 +163,8 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZFH,
 	KVM_RISCV_ISA_EXT_ZFHMIN,
 	KVM_RISCV_ISA_EXT_ZIHINTNTL,
+	KVM_RISCV_ISA_EXT_ZVFH,
+	KVM_RISCV_ISA_EXT_ZVFHMIN,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index deceaa6f9cfa2..707d9d9883c85 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -67,6 +67,8 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZKT),
 	KVM_ISA_EXT_ARR(ZVBB),
 	KVM_ISA_EXT_ARR(ZVBC),
+	KVM_ISA_EXT_ARR(ZVFH),
+	KVM_ISA_EXT_ARR(ZVFHMIN),
 	KVM_ISA_EXT_ARR(ZVKB),
 	KVM_ISA_EXT_ARR(ZVKG),
 	KVM_ISA_EXT_ARR(ZVKNED),
@@ -139,6 +141,8 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_ZKT:
 	case KVM_RISCV_ISA_EXT_ZVBB:
 	case KVM_RISCV_ISA_EXT_ZVBC:
+	case KVM_RISCV_ISA_EXT_ZVFH:
+	case KVM_RISCV_ISA_EXT_ZVFHMIN:
 	case KVM_RISCV_ISA_EXT_ZVKB:
 	case KVM_RISCV_ISA_EXT_ZVKG:
 	case KVM_RISCV_ISA_EXT_ZVKNED:
-- 
GitLab


From 1216fdd99be113fa75ccdd0497802bd0fe4369aa Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:35:06 +0530
Subject: [PATCH 3027/4076] KVM: riscv: selftests: Add Zvfh[min] extensions to
 get-reg-list test

The KVM RISC-V allows Zvfh[min] extensions for Guest/VM so let us
add these extensions to get-reg-list test.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/riscv/get-reg-list.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index c9a45e17267bf..02ec1a44624a8 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -74,6 +74,8 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFHMIN:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKG:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNED:
@@ -443,6 +445,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZKT),
 		KVM_ISA_EXT_ARR(ZVBB),
 		KVM_ISA_EXT_ARR(ZVBC),
+		KVM_ISA_EXT_ARR(ZVFH),
+		KVM_ISA_EXT_ARR(ZVFHMIN),
 		KVM_ISA_EXT_ARR(ZVKB),
 		KVM_ISA_EXT_ARR(ZVKG),
 		KVM_ISA_EXT_ARR(ZVKNED),
@@ -961,6 +965,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
 KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
 KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB);
 KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvfhmin, ZVFHMIN);
 KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB);
 KVM_ISA_EXT_SIMPLE_CONFIG(zvkg, ZVKG);
 KVM_ISA_EXT_SIMPLE_CONFIG(zvkned, ZVKNED);
@@ -1011,6 +1017,8 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zkt,
 	&config_zvbb,
 	&config_zvbc,
+	&config_zvfh,
+	&config_zvfhmin,
 	&config_zvkb,
 	&config_zvkg,
 	&config_zvkned,
-- 
GitLab


From 41182cc6f507011a2e6c82657779e451ed9942bb Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:43:12 +0530
Subject: [PATCH 3028/4076] RISC-V: KVM: Allow Zfa extension for Guest/VM

We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zfa extension for Guest/VM.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/uapi/asm/kvm.h | 1 +
 arch/riscv/kvm/vcpu_onereg.c      | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 7d07722aa1aaf..7499e88a947c0 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -165,6 +165,7 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZIHINTNTL,
 	KVM_RISCV_ISA_EXT_ZVFH,
 	KVM_RISCV_ISA_EXT_ZVFHMIN,
+	KVM_RISCV_ISA_EXT_ZFA,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 707d9d9883c85..5f7355e960084 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -47,6 +47,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZBKC),
 	KVM_ISA_EXT_ARR(ZBKX),
 	KVM_ISA_EXT_ARR(ZBS),
+	KVM_ISA_EXT_ARR(ZFA),
 	KVM_ISA_EXT_ARR(ZFH),
 	KVM_ISA_EXT_ARR(ZFHMIN),
 	KVM_ISA_EXT_ARR(ZICBOM),
@@ -123,6 +124,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_ZBKC:
 	case KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_RISCV_ISA_EXT_ZFA:
 	case KVM_RISCV_ISA_EXT_ZFH:
 	case KVM_RISCV_ISA_EXT_ZFHMIN:
 	case KVM_RISCV_ISA_EXT_ZICNTR:
-- 
GitLab


From 4d0e8f9a361b3a1f7b67418c536b258323de734f Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:45:35 +0530
Subject: [PATCH 3029/4076] KVM: riscv: selftests: Add Zfa extension to
 get-reg-list test

The KVM RISC-V allows Zfa extension for Guest/VM so let us
add this extension to get-reg-list test.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/riscv/get-reg-list.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 02ec1a44624a8..4fd0f89515744 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -54,6 +54,7 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFA:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
@@ -425,6 +426,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZBKC),
 		KVM_ISA_EXT_ARR(ZBKX),
 		KVM_ISA_EXT_ARR(ZBS),
+		KVM_ISA_EXT_ARR(ZFA),
 		KVM_ISA_EXT_ARR(ZFH),
 		KVM_ISA_EXT_ARR(ZFHMIN),
 		KVM_ISA_EXT_ARR(ZICBOM),
@@ -945,6 +947,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA);
 KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH);
 KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
@@ -997,6 +1000,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zbkc,
 	&config_zbkx,
 	&config_zbs,
+	&config_zfa,
 	&config_zfh,
 	&config_zfhmin,
 	&config_zicbom,
-- 
GitLab


From cacea81390fd8c8c85404e5eb2adeb83d87a912e Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 18 Jan 2024 06:19:57 +1000
Subject: [PATCH 3030/4076] nouveau/vmm: don't set addr on the fail path to
 avoid warning

nvif_vmm_put gets called if addr is set, but if the allocation
fails we don't need to call put, otherwise we get a warning like

[523232.435671] ------------[ cut here ]------------
[523232.435674] WARNING: CPU: 8 PID: 1505697 at drivers/gpu/drm/nouveau/nvif/vmm.c:68 nvif_vmm_put+0x72/0x80 [nouveau]
[523232.435795] Modules linked in: uinput rfcomm snd_seq_dummy snd_hrtimer nf_conntrack_netbios_ns nf_conntrack_broadcast nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables nfnetlink qrtr bnep sunrpc binfmt_misc intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common isst_if_common iwlmvm nfit libnvdimm vfat fat x86_pkg_temp_thermal intel_powerclamp mac80211 snd_soc_avs snd_soc_hda_codec coretemp snd_hda_ext_core snd_soc_core snd_hda_codec_realtek kvm_intel snd_hda_codec_hdmi snd_compress snd_hda_codec_generic ac97_bus snd_pcm_dmaengine snd_hda_intel libarc4 snd_intel_dspcfg snd_intel_sdw_acpi snd_hda_codec kvm iwlwifi snd_hda_core btusb snd_hwdep btrtl snd_seq btintel irqbypass btbcm rapl snd_seq_device eeepc_wmi btmtk intel_cstate iTCO_wdt cfg80211 snd_pcm asus_wmi bluetooth intel_pmc_bxt iTCO_vendor_support snd_timer ledtrig_audio pktcdvd snd mei_me
[523232.435828]  sparse_keymap intel_uncore i2c_i801 platform_profile wmi_bmof mei pcspkr ioatdma soundcore i2c_smbus rfkill idma64 dca joydev acpi_tad loop zram nouveau drm_ttm_helper ttm video drm_exec drm_gpuvm gpu_sched crct10dif_pclmul i2c_algo_bit nvme crc32_pclmul crc32c_intel drm_display_helper polyval_clmulni nvme_core polyval_generic e1000e mxm_wmi cec ghash_clmulni_intel r8169 sha512_ssse3 nvme_common wmi pinctrl_sunrisepoint uas usb_storage ip6_tables ip_tables fuse
[523232.435849] CPU: 8 PID: 1505697 Comm: gnome-shell Tainted: G        W          6.6.0-rc7-nvk-uapi+ #12
[523232.435851] Hardware name: System manufacturer System Product Name/ROG STRIX X299-E GAMING II, BIOS 1301 09/24/2021
[523232.435852] RIP: 0010:nvif_vmm_put+0x72/0x80 [nouveau]
[523232.435934] Code: 00 00 48 89 e2 be 02 00 00 00 48 c7 04 24 00 00 00 00 48 89 44 24 08 e8 fc bf ff ff 85
c0 75 0a 48 c7 43 08 00 00 00 00 eb b3 <0f> 0b eb f2 e8 f5 c9 b2 e6 0f 1f 44 00 00 90 90 90 90 90 90 90 90
[523232.435936] RSP: 0018:ffffc900077ffbd8 EFLAGS: 00010282
[523232.435937] RAX: 00000000fffffffe RBX: ffffc900077ffc00 RCX: 0000000000000010
[523232.435938] RDX: 0000000000000010 RSI: ffffc900077ffb38 RDI: ffffc900077ffbd8
[523232.435940] RBP: ffff888e1c4f2140 R08: 0000000000000000 R09: 0000000000000000
[523232.435940] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888503811800
[523232.435941] R13: ffffc900077ffca0 R14: ffff888e1c4f2140 R15: ffff88810317e1e0
[523232.435942] FS:  00007f933a769640(0000) GS:ffff88905fa00000(0000) knlGS:0000000000000000
[523232.435943] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[523232.435944] CR2: 00007f930bef7000 CR3: 00000005d0322001 CR4: 00000000003706e0
[523232.435945] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[523232.435946] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[523232.435964] Call Trace:
[523232.435965]  <TASK>
[523232.435966]  ? nvif_vmm_put+0x72/0x80 [nouveau]
[523232.436051]  ? __warn+0x81/0x130
[523232.436055]  ? nvif_vmm_put+0x72/0x80 [nouveau]
[523232.436138]  ? report_bug+0x171/0x1a0
[523232.436142]  ? handle_bug+0x3c/0x80
[523232.436144]  ? exc_invalid_op+0x17/0x70
[523232.436145]  ? asm_exc_invalid_op+0x1a/0x20
[523232.436149]  ? nvif_vmm_put+0x72/0x80 [nouveau]
[523232.436230]  ? nvif_vmm_put+0x64/0x80 [nouveau]
[523232.436342]  nouveau_vma_del+0x80/0xd0 [nouveau]
[523232.436506]  nouveau_vma_new+0x1a0/0x210 [nouveau]
[523232.436671]  nouveau_gem_object_open+0x1d0/0x1f0 [nouveau]
[523232.436835]  drm_gem_handle_create_tail+0xd1/0x180
[523232.436840]  drm_prime_fd_to_handle_ioctl+0x12e/0x200
[523232.436844]  ? __pfx_drm_prime_fd_to_handle_ioctl+0x10/0x10
[523232.436847]  drm_ioctl_kernel+0xd3/0x180
[523232.436849]  drm_ioctl+0x26d/0x4b0
[523232.436851]  ? __pfx_drm_prime_fd_to_handle_ioctl+0x10/0x10
[523232.436855]  nouveau_drm_ioctl+0x5a/0xb0 [nouveau]
[523232.437032]  __x64_sys_ioctl+0x94/0xd0
[523232.437036]  do_syscall_64+0x5d/0x90
[523232.437040]  ? syscall_exit_to_user_mode+0x2b/0x40
[523232.437044]  ? do_syscall_64+0x6c/0x90
[523232.437046]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Reported-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240117213852.295565-1-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/nouveau_vmm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c
index a6602c0126715..3dda885df5b22 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c
@@ -108,6 +108,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm,
 	} else {
 		ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0,
 				   mem->mem.size, &tmp);
+		if (ret)
+			goto done;
+
 		vma->addr = tmp.addr;
 	}
 
-- 
GitLab


From d87123aa9a7920e88633ffc5c5a0a22ab08bdc06 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 25 Sep 2023 13:10:22 +0200
Subject: [PATCH 3031/4076] sh: ecovec24: Rename missed backlight field from
 fbdev to dev
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

One instance of gpio_backlight_platform_data.fbdev was renamed, but the
second instance was forgotten, causing a build failure:

    arch/sh/boards/mach-ecovec24/setup.c: In function ‘arch_setup’:
    arch/sh/boards/mach-ecovec24/setup.c:1223:37: error: ‘struct gpio_backlight_platform_data’ has no member named ‘fbdev’; did you mean ‘dev’?
     1223 |                 gpio_backlight_data.fbdev = NULL;
	  |                                     ^~~~~
	  |                                     dev

Fix this by updating the second instance.

Fixes: ed369def91c1579a ("backlight/gpio_backlight: Rename field 'fbdev' to 'dev'")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202309231601.Uu6qcRnU-lkp@intel.com/
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Link: https://lore.kernel.org/r/20230925111022.3626362-1-geert+renesas@glider.be
Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
---
 arch/sh/boards/mach-ecovec24/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 0f279360838a4..30d117f9ad7ee 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -1220,7 +1220,7 @@ static int __init arch_setup(void)
 		lcdc_info.ch[0].num_modes		= ARRAY_SIZE(ecovec_dvi_modes);
 
 		/* No backlight */
-		gpio_backlight_data.fbdev = NULL;
+		gpio_backlight_data.dev = NULL;
 
 		gpio_set_value(GPIO_PTA2, 1);
 		gpio_set_value(GPIO_PTU1, 1);
-- 
GitLab


From 180a8f12c21f41740fee09ca7f7aa98ff5bb99f8 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 23 Dec 2023 15:16:50 +0100
Subject: [PATCH 3032/4076] Input: goodix - accept ACPI resources with
 gpio_count == 3 && gpio_int_idx == 0

Some devices list 3 Gpio resources in the ACPI resource list for
the touchscreen:

1. GpioInt resource pointing to the GPIO used for the interrupt
2. GpioIo resource pointing to the reset GPIO
3. GpioIo resource pointing to the GPIO used for the interrupt

Note how the third extra GpioIo resource really is a duplicate
of the GpioInt provided info.

Ignore this extra GPIO, treating this setup the same as gpio_count == 2 &&
gpio_int_idx == 0 fixes the touchscreen not working on the Thunderbook
Colossus W803 rugged tablet and likely also on the CyberBook_T116K.

Reported-by: Maarten van der Schrieck
Closes: https://gitlab.com/AdyaAdya/goodix-touchscreen-linux-driver/-/issues/22
Suggested-by: Maarten van der Schrieck
Tested-by: Maarten van der Schrieck
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20231223141650.10679-1-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/goodix.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index af32fbe57b630..b068ff8afbc9a 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -884,7 +884,8 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts)
 		}
 	}
 
-	if (ts->gpio_count == 2 && ts->gpio_int_idx == 0) {
+	/* Some devices with gpio_int_idx 0 list a third unused GPIO */
+	if ((ts->gpio_count == 2 || ts->gpio_count == 3) && ts->gpio_int_idx == 0) {
 		ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_GPIO;
 		gpio_mapping = acpi_goodix_int_first_gpios;
 	} else if (ts->gpio_count == 2 && ts->gpio_int_idx == 1) {
-- 
GitLab


From 6a9531c3a88096a26cf3ac582f7ec44f94a7dcb2 Mon Sep 17 00:00:00 2001
From: Yajun Deng <yajun.deng@linux.dev>
Date: Thu, 18 Jan 2024 14:18:53 +0800
Subject: [PATCH 3033/4076] memblock: fix crash when reserved memory is not
 added to memory

After commit 61167ad5fecd ("mm: pass nid to reserve_bootmem_region()")
nid of a reserved region is used by init_reserved_page() (with
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y) to access node strucure.
In many cases the nid of the reserved memory is not set and this causes
a crash.

When the nid of a reserved region is not set, fall back to
early_pfn_to_nid(), so that nid of the first_online_node will be passed
to init_reserved_page().

Fixes: 61167ad5fecd ("mm: pass nid to reserve_bootmem_region()")
Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
Link: https://lore.kernel.org/r/20240118061853.2652295-1-yajun.deng@linux.dev
[rppt: massaged the commit message]
Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
---
 mm/memblock.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/memblock.c b/mm/memblock.c
index 5a88d6d24d793..4823ad979b72f 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -2141,6 +2141,9 @@ static void __init memmap_init_reserved_pages(void)
 			start = region->base;
 			end = start + region->size;
 
+			if (nid == NUMA_NO_NODE || nid >= MAX_NUMNODES)
+				nid = early_pfn_to_nid(PFN_DOWN(start));
+
 			reserve_bootmem_region(start, end, nid);
 		}
 	}
-- 
GitLab


From 99fe83ab3bb0e8aac4d45a9361919794336b2ba8 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 21 Nov 2023 08:54:23 +0900
Subject: [PATCH 3034/4076] sh: vsyscall: Remove unnecessary $(foreach ...)

There is no need to use $(foreach ...) for iterating over just one parameter.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Link: https://lore.kernel.org/r/20231120235423.4103310-1-masahiroy@kernel.org
Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
---
 arch/sh/kernel/vsyscall/Makefile | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/sh/kernel/vsyscall/Makefile b/arch/sh/kernel/vsyscall/Makefile
index 6e86644480488..118744d349e21 100644
--- a/arch/sh/kernel/vsyscall/Makefile
+++ b/arch/sh/kernel/vsyscall/Makefile
@@ -1,11 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y += vsyscall.o vsyscall-syscall.o vsyscall-syms.o
 
-$(obj)/vsyscall-syscall.o: \
-	$(foreach F,trapa,$(obj)/vsyscall-$F.so)
+$(obj)/vsyscall-syscall.o: $(obj)/vsyscall-trapa.so
 
 # Teach kbuild about targets
-targets += $(foreach F,trapa,vsyscall-$F.o vsyscall-$F.so)
+targets += vsyscall-trapa.o vsyscall-traps.so
 targets += vsyscall-note.o vsyscall.lds vsyscall-dummy.o
 
 # The DSO images are built using a special linker script
-- 
GitLab


From fe0d495e759cee0dbfff4348b5791f21b6f56655 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 22 Dec 2023 11:06:44 -0700
Subject: [PATCH 3035/4076] dmaengine: xilinx: xdma: Fix operator precedence in
 xdma_prep_interleaved_dma()

Clang warns (or errors with CONFIG_WERROR=y):

  drivers/dma/xilinx/xdma.c:757:68: error: operator '?:' has lower precedence than '+'; '+' will be evaluated first [-Werror,-Wparentheses]
    757 |                 src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + xt->src_inc ?
        |                             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ^
  drivers/dma/xilinx/xdma.c:757:68: note: place parentheses around the '+' expression to silence this warning
    757 |                 src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + xt->src_inc ?
        |                                                                                  ^
        |                             (                                                   )
  drivers/dma/xilinx/xdma.c:757:68: note: place parentheses around the '?:' expression to evaluate it first
    757 |                 src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + xt->src_inc ?
        |                                                                                  ^
        |                                                                      (
    758 |                                                               xt->sgl[i].size : 0;
        |
        |                                                                                  )
  drivers/dma/xilinx/xdma.c:759:68: error: operator '?:' has lower precedence than '+'; '+' will be evaluated first [-Werror,-Wparentheses]
    759 |                 dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + xt->dst_inc ?
        |                             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ^
  drivers/dma/xilinx/xdma.c:759:68: note: place parentheses around the '+' expression to silence this warning
    759 |                 dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + xt->dst_inc ?
        |                                                                                  ^
        |                             (                                                   )
  drivers/dma/xilinx/xdma.c:759:68: note: place parentheses around the '?:' expression to evaluate it first
    759 |                 dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + xt->dst_inc ?
        |                                                                                  ^
        |                                                                      (
    760 |                                                               xt->sgl[i].size : 0;
        |
        |                                                                                  )

The src_inc and dst_inc members of 'struct dma_interleaved_template' are
booleans, so it does not make sense for the addition to happen first.
Wrap the conditional operator in parantheses so it is evaluated first.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1971
Fixes: 2f8f90cd2f8d ("dmaengine: xilinx: xdma: Implement interleaved DMA transfers")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20231222-dma-xilinx-xdma-clang-fixes-v1-1-84a18ff184d2@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 4ebc90b41bdb9..d5b9fc3fd955b 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -754,10 +754,10 @@ xdma_prep_interleaved_dma(struct dma_chan *chan,
 	dst_addr = xt->dst_start;
 	for (i = 0; i < xt->frame_size; ++i) {
 		desc_num += xdma_fill_descs(sw_desc, src_addr, dst_addr, xt->sgl[i].size, desc_num);
-		src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + xt->src_inc ?
-							      xt->sgl[i].size : 0;
-		dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + xt->dst_inc ?
-							      xt->sgl[i].size : 0;
+		src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + (xt->src_inc ?
+							      xt->sgl[i].size : 0);
+		dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + (xt->dst_inc ?
+							      xt->sgl[i].size : 0);
 		period_size += xt->sgl[i].size;
 	}
 	sw_desc->period_size = period_size;
-- 
GitLab


From 620a7e4c1f03a84e10c8c3fa0ae1aab03ef84294 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 22 Dec 2023 11:06:45 -0700
Subject: [PATCH 3036/4076] dmaengine: xilinx: xdma: Fix initialization
 location of desc in xdma_channel_isr()

Clang warns (or errors with CONFIG_WERROR=y):

  drivers/dma/xilinx/xdma.c:894:3: error: variable 'desc' is uninitialized when used here [-Werror,-Wuninitialized]
    894 |                 desc->error = true;
        |                 ^~~~

The initialization of desc was moved too far forward, move it back so
that this assignment does not result in a potential crash at runtime
while clearing up the warning.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1972
Fixes: 2f8f90cd2f8d ("dmaengine: xilinx: xdma: Implement interleaved DMA transfers")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20231222-dma-xilinx-xdma-clang-fixes-v1-2-84a18ff184d2@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index d5b9fc3fd955b..ee595d1ebc63e 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -888,6 +888,8 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	if (ret)
 		goto out;
 
+	desc = to_xdma_desc(vd);
+
 	st &= XDMA_CHAN_STATUS_MASK;
 	if ((st & XDMA_CHAN_ERROR_MASK) ||
 	    !(st & (CHAN_CTRL_IE_DESC_COMPLETED | CHAN_CTRL_IE_DESC_STOPPED))) {
@@ -901,7 +903,6 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	if (ret)
 		goto out;
 
-	desc = to_xdma_desc(vd);
 	if (desc->interleaved_dma) {
 		xchan->busy = false;
 		desc->completed_desc_num += complete_desc_num;
-- 
GitLab


From 98373a21159379341742dadd6c038fe8ff34d9a1 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 18 Jan 2024 19:28:32 -0800
Subject: [PATCH 3037/4076] dmaengine: imx-sdma: fix Excess kernel-doc warnings

Fix warnings of "Excess struct member" by removing those lines.
They are extraneous.

imx-sdma.c:467: warning: Excess struct member 'context_loaded' description in 'sdma_channel'
imx-sdma.c:467: warning: Excess struct member 'bd_pool' description in 'sdma_channel'
imx-sdma.c:500: warning: Excess struct member 'script_addrs' description in 'sdma_firmware_header'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Sascha Hauer <s.hauer@pengutronix.de>
Cc: Shawn Guo <shawnguo@kernel.org>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: dmaengine@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20240119032832.4051-1-rdunlap@infradead.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/imx-sdma.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index f81ecf5863e86..9b42f5e96b1e0 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -421,9 +421,7 @@ struct sdma_desc {
  * @shp_addr:		value for gReg[6]
  * @per_addr:		value for gReg[2]
  * @status:		status of dma channel
- * @context_loaded:	ensure context is only loaded once
  * @data:		specific sdma interface structure
- * @bd_pool:		dma_pool for bd
  * @terminate_worker:	used to call back into terminate work function
  * @terminated:		terminated list
  * @is_ram_script:	flag for script in ram
@@ -486,8 +484,6 @@ struct sdma_channel {
  * @num_script_addrs:	Number of script addresses in this image
  * @ram_code_start:	offset of SDMA ram image in this firmware image
  * @ram_code_size:	size of SDMA ram image
- * @script_addrs:	Stores the start address of the SDMA scripts
- *			(in SDMA memory space)
  */
 struct sdma_firmware_header {
 	u32	magic;
-- 
GitLab


From c4d6dcb3b6250ea546a952ad33382daf7cd32425 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Wed, 10 Jan 2024 22:27:17 +0000
Subject: [PATCH 3038/4076] dmaengine: sh: rz-dmac: Avoid format-overflow
 warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The max channel count for RZ DMAC is 16, hence use u8 instead of unsigned
int and make the pdev_irqname string long enough to avoid the warning.

This fixes the below issue:
drivers/dma/sh/rz-dmac.c: In function ‘rz_dmac_probe’:
drivers/dma/sh/rz-dmac.c:770:34: warning: ‘%u’ directive writing between 1 and 10 bytes into a region of size 3 [-Wformat-overflow=]
  770 |         sprintf(pdev_irqname, "ch%u", index);
      |                                  ^~
In function ‘rz_dmac_chan_probe’,
    inlined from ‘rz_dmac_probe’ at drivers/dma/sh/rz-dmac.c:910:9:
drivers/dma/sh/rz-dmac.c:770:31: note: directive argument in the range [0, 4294967294]
  770 |         sprintf(pdev_irqname, "ch%u", index);
      |                               ^~~~~~
drivers/dma/sh/rz-dmac.c:770:9: note: ‘sprintf’ output between 4 and 13 bytes into a destination of size 5
  770 |         sprintf(pdev_irqname, "ch%u", index);
      |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

While at it use scnprintf() instead of sprintf() to make the code
more robust.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20240110222717.193719-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/sh/rz-dmac.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index fea5bda34bc20..1f1e86ba5c66a 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -755,11 +755,11 @@ static struct dma_chan *rz_dmac_of_xlate(struct of_phandle_args *dma_spec,
 
 static int rz_dmac_chan_probe(struct rz_dmac *dmac,
 			      struct rz_dmac_chan *channel,
-			      unsigned int index)
+			      u8 index)
 {
 	struct platform_device *pdev = to_platform_device(dmac->dev);
 	struct rz_lmdesc *lmdesc;
-	char pdev_irqname[5];
+	char pdev_irqname[6];
 	char *irqname;
 	int ret;
 
@@ -767,7 +767,7 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac,
 	channel->mid_rid = -EINVAL;
 
 	/* Request the channel interrupt. */
-	sprintf(pdev_irqname, "ch%u", index);
+	scnprintf(pdev_irqname, sizeof(pdev_irqname), "ch%u", index);
 	channel->irq = platform_get_irq_byname(pdev, pdev_irqname);
 	if (channel->irq < 0)
 		return channel->irq;
@@ -845,9 +845,9 @@ static int rz_dmac_probe(struct platform_device *pdev)
 	struct dma_device *engine;
 	struct rz_dmac *dmac;
 	int channel_num;
-	unsigned int i;
 	int ret;
 	int irq;
+	u8 i;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
 	if (!dmac)
-- 
GitLab


From e626cb02ee8399fd42c415e542d031d185783903 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 18 Jan 2024 12:54:51 +0100
Subject: [PATCH 3039/4076] futex: Prevent the reuse of stale pi_state

Jiri Slaby reported a futex state inconsistency resulting in -EINVAL during
a lock operation for a PI futex. It requires that the a lock process is
interrupted by a timeout or signal:

  T1 Owns the futex in user space.

  T2 Tries to acquire the futex in kernel (futex_lock_pi()). Allocates a
     pi_state and attaches itself to it.

  T2 Times out and removes its rt_waiter from the rt_mutex. Drops the
     rtmutex lock and tries to acquire the hash bucket lock to remove
     the futex_q. The lock is contended and T2 schedules out.

  T1 Unlocks the futex (futex_unlock_pi()). Finds a futex_q but no
     rt_waiter. Unlocks the futex (do_uncontended) and makes it available
     to user space.

  T3 Acquires the futex in user space.

  T4 Tries to acquire the futex in kernel (futex_lock_pi()). Finds the
     existing futex_q of T2 and tries to attach itself to the existing
     pi_state.  This (attach_to_pi_state()) fails with -EINVAL because uval
     contains the TID of T3 but pi_state points to T1.

It's incorrect to unlock the futex and make it available for user space to
acquire as long as there is still an existing state attached to it in the
kernel.

T1 cannot hand over the futex to T2 because T2 already gave up and started
to clean up and is blocked on the hash bucket lock, so T2's futex_q with
the pi_state pointing to T1 is still queued.

T2 observes the futex_q, but ignores it as there is no waiter on the
corresponding rt_mutex and takes the uncontended path which allows the
subsequent caller of futex_lock_pi() (T4) to observe that stale state.

To prevent this the unlock path must dequeue all futex_q entries which
point to the same pi_state when there is no waiter on the rt mutex. This
requires obviously to make the dequeue conditional in the locking path to
prevent a double dequeue. With that it's guaranteed that user space cannot
observe an uncontended futex which has kernel state attached.

Fixes: fbeb558b0dd0d ("futex/pi: Fix recursive rt_mutex waiter state")
Reported-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20240118115451.0TkD_ZhB@linutronix.de
Closes: https://lore.kernel.org/all/4611bcf2-44d0-4c34-9b84-17406f881003@kernel.org
---
 kernel/futex/core.c | 15 ++++++++++++---
 kernel/futex/pi.c   | 11 ++++++++---
 2 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index e0e853412c158..1e78ef24321e8 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -627,12 +627,21 @@ retry:
 }
 
 /*
- * PI futexes can not be requeued and must remove themselves from the
- * hash bucket. The hash bucket lock (i.e. lock_ptr) is held.
+ * PI futexes can not be requeued and must remove themselves from the hash
+ * bucket. The hash bucket lock (i.e. lock_ptr) is held.
  */
 void futex_unqueue_pi(struct futex_q *q)
 {
-	__futex_unqueue(q);
+	/*
+	 * If the lock was not acquired (due to timeout or signal) then the
+	 * rt_waiter is removed before futex_q is. If this is observed by
+	 * an unlocker after dropping the rtmutex wait lock and before
+	 * acquiring the hash bucket lock, then the unlocker dequeues the
+	 * futex_q from the hash bucket list to guarantee consistent state
+	 * vs. userspace. Therefore the dequeue here must be conditional.
+	 */
+	if (!plist_node_empty(&q->list))
+		__futex_unqueue(q);
 
 	BUG_ON(!q->pi_state);
 	put_pi_state(q->pi_state);
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index 90e5197f4e569..5722467f27379 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -1135,6 +1135,7 @@ retry:
 
 	hb = futex_hash(&key);
 	spin_lock(&hb->lock);
+retry_hb:
 
 	/*
 	 * Check waiters first. We do not trust user space values at
@@ -1177,12 +1178,17 @@ retry:
 		/*
 		 * Futex vs rt_mutex waiter state -- if there are no rt_mutex
 		 * waiters even though futex thinks there are, then the waiter
-		 * is leaving and the uncontended path is safe to take.
+		 * is leaving. The entry needs to be removed from the list so a
+		 * new futex_lock_pi() is not using this stale PI-state while
+		 * the futex is available in user space again.
+		 * There can be more than one task on its way out so it needs
+		 * to retry.
 		 */
 		rt_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
 		if (!rt_waiter) {
+			__futex_unqueue(top_waiter);
 			raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-			goto do_uncontended;
+			goto retry_hb;
 		}
 
 		get_pi_state(pi_state);
@@ -1217,7 +1223,6 @@ retry:
 		return ret;
 	}
 
-do_uncontended:
 	/*
 	 * We have no kernel internal state, i.e. no waiters in the
 	 * kernel. Waiters which are about to queue themselves are stuck
-- 
GitLab


From dbc153fd3c142909e564bb256da087e13fbf239c Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Thu, 18 Jan 2024 12:32:10 +0800
Subject: [PATCH 3040/4076] net/smc: fix illegal rmb_desc access in SMC-D
 connection dump

A crash was found when dumping SMC-D connections. It can be reproduced
by following steps:

- run nginx/wrk test:
  smc_run nginx
  smc_run wrk -t 16 -c 1000 -d <duration> -H 'Connection: Close' <URL>

- continuously dump SMC-D connections in parallel:
  watch -n 1 'smcss -D'

 BUG: kernel NULL pointer dereference, address: 0000000000000030
 CPU: 2 PID: 7204 Comm: smcss Kdump: loaded Tainted: G	E      6.7.0+ #55
 RIP: 0010:__smc_diag_dump.constprop.0+0x5e5/0x620 [smc_diag]
 Call Trace:
  <TASK>
  ? __die+0x24/0x70
  ? page_fault_oops+0x66/0x150
  ? exc_page_fault+0x69/0x140
  ? asm_exc_page_fault+0x26/0x30
  ? __smc_diag_dump.constprop.0+0x5e5/0x620 [smc_diag]
  ? __kmalloc_node_track_caller+0x35d/0x430
  ? __alloc_skb+0x77/0x170
  smc_diag_dump_proto+0xd0/0xf0 [smc_diag]
  smc_diag_dump+0x26/0x60 [smc_diag]
  netlink_dump+0x19f/0x320
  __netlink_dump_start+0x1dc/0x300
  smc_diag_handler_dump+0x6a/0x80 [smc_diag]
  ? __pfx_smc_diag_dump+0x10/0x10 [smc_diag]
  sock_diag_rcv_msg+0x121/0x140
  ? __pfx_sock_diag_rcv_msg+0x10/0x10
  netlink_rcv_skb+0x5a/0x110
  sock_diag_rcv+0x28/0x40
  netlink_unicast+0x22a/0x330
  netlink_sendmsg+0x1f8/0x420
  __sock_sendmsg+0xb0/0xc0
  ____sys_sendmsg+0x24e/0x300
  ? copy_msghdr_from_user+0x62/0x80
  ___sys_sendmsg+0x7c/0xd0
  ? __do_fault+0x34/0x160
  ? do_read_fault+0x5f/0x100
  ? do_fault+0xb0/0x110
  ? __handle_mm_fault+0x2b0/0x6c0
  __sys_sendmsg+0x4d/0x80
  do_syscall_64+0x69/0x180
  entry_SYSCALL_64_after_hwframe+0x6e/0x76

It is possible that the connection is in process of being established
when we dump it. Assumed that the connection has been registered in a
link group by smc_conn_create() but the rmb_desc has not yet been
initialized by smc_buf_create(), thus causing the illegal access to
conn->rmb_desc. So fix it by checking before dump.

Fixes: 4b1b7d3b30a6 ("net/smc: add SMC-D diag support")
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_diag.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 52f7c4f1e7670..5a33908015f3e 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -164,7 +164,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	}
 	if (smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd &&
 	    (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
-	    !list_empty(&smc->conn.lgr->list)) {
+	    !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) {
 		struct smc_connection *conn = &smc->conn;
 		struct smcd_diag_dmbinfo dinfo;
 		struct smcd_dev *smcd = conn->lgr->smcd;
-- 
GitLab


From 62b68a88795942512936896b9fec1ee7d5fa9922 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Wed, 10 Jan 2024 22:22:10 +0000
Subject: [PATCH 3041/4076] dmaengine: usb-dmac: Avoid format-overflow warning

gcc points out that the fix-byte buffer might be too small:
drivers/dma/sh/usb-dmac.c: In function 'usb_dmac_probe':
drivers/dma/sh/usb-dmac.c:720:34: warning: '%u' directive writing between 1 and 10 bytes into a region of size 3 [-Wformat-overflow=]
  720 |         sprintf(pdev_irqname, "ch%u", index);
      |                                  ^~
In function 'usb_dmac_chan_probe',
    inlined from 'usb_dmac_probe' at drivers/dma/sh/usb-dmac.c:814:9:
drivers/dma/sh/usb-dmac.c:720:31: note: directive argument in the range [0, 4294967294]
  720 |         sprintf(pdev_irqname, "ch%u", index);
      |                               ^~~~~~
drivers/dma/sh/usb-dmac.c:720:9: note: 'sprintf' output between 4 and 13 bytes into a destination of size 5
  720 |         sprintf(pdev_irqname, "ch%u", index);
      |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Maximum number of channels for USB-DMAC as per the driver is 1-99 so use
u8 instead of unsigned int/int for DMAC channel indexing and make the
pdev_irqname string long enough to avoid the warning.

While at it use scnprintf() instead of sprintf() to make the code more
robust.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20240110222210.193479-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/sh/usb-dmac.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index a9b4302f60501..f7cd0cad056c1 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -706,10 +706,10 @@ static const struct dev_pm_ops usb_dmac_pm = {
 
 static int usb_dmac_chan_probe(struct usb_dmac *dmac,
 			       struct usb_dmac_chan *uchan,
-			       unsigned int index)
+			       u8 index)
 {
 	struct platform_device *pdev = to_platform_device(dmac->dev);
-	char pdev_irqname[5];
+	char pdev_irqname[6];
 	char *irqname;
 	int ret;
 
@@ -717,7 +717,7 @@ static int usb_dmac_chan_probe(struct usb_dmac *dmac,
 	uchan->iomem = dmac->iomem + USB_DMAC_CHAN_OFFSET(index);
 
 	/* Request the channel interrupt. */
-	sprintf(pdev_irqname, "ch%u", index);
+	scnprintf(pdev_irqname, sizeof(pdev_irqname), "ch%u", index);
 	uchan->irq = platform_get_irq_byname(pdev, pdev_irqname);
 	if (uchan->irq < 0)
 		return -ENODEV;
@@ -768,8 +768,8 @@ static int usb_dmac_probe(struct platform_device *pdev)
 	const enum dma_slave_buswidth widths = USB_DMAC_SLAVE_BUSWIDTH;
 	struct dma_device *engine;
 	struct usb_dmac *dmac;
-	unsigned int i;
 	int ret;
+	u8 i;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
 	if (!dmac)
@@ -869,7 +869,7 @@ static void usb_dmac_chan_remove(struct usb_dmac *dmac,
 static void usb_dmac_remove(struct platform_device *pdev)
 {
 	struct usb_dmac *dmac = platform_get_drvdata(pdev);
-	int i;
+	u8 i;
 
 	for (i = 0; i < dmac->n_channels; ++i)
 		usb_dmac_chan_remove(dmac, &dmac->channels[i]);
-- 
GitLab


From f829bca2e294bc2953bd2dadb93d72a9987b3110 Mon Sep 17 00:00:00 2001
From: Jan Kuliga <jankul@alatek.krakow.pl>
Date: Sat, 23 Dec 2023 00:17:28 +0100
Subject: [PATCH 3042/4076] dmaengine: xilinx: xdma: Fix kernel-doc warnings

Replace hyphens with colons where necessary.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312230634.3AIMQ3OP-lkp@intel.com/
Signed-off-by: Jan Kuliga <jankul@alatek.krakow.pl>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20231222231728.7156-1-jankul@alatek.krakow.pl
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index ee595d1ebc63e..170017ff2aad6 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -548,11 +548,11 @@ static void xdma_synchronize(struct dma_chan *chan)
 
 /**
  * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses
- * @sw_desc - tx descriptor state container
- * @src_addr - Value for a ->src_addr field of a first descriptor
- * @dst_addr - Value for a ->dst_addr field of a first descriptor
- * @size - Total size of a contiguous memory block
- * @filled_descs_num - Number of filled hardware descriptors for corresponding sw_desc
+ * @sw_desc: tx descriptor state container
+ * @src_addr: Value for a ->src_addr field of a first descriptor
+ * @dst_addr: Value for a ->dst_addr field of a first descriptor
+ * @size: Total size of a contiguous memory block
+ * @filled_descs_num: Number of filled hardware descriptors for corresponding sw_desc
  */
 static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr,
 				  u64 dst_addr, u32 size, u32 filled_descs_num)
-- 
GitLab


From 404290240827c3bb5c4e195174a8854eef2f89ac Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Fri, 19 Jan 2024 18:10:44 +0530
Subject: [PATCH 3043/4076] dmaengine: shdma: increase size of 'dev_id'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We seem to have hit warnings of 'output may be truncated' which is fixed
by increasing the size of 'dev_id'

drivers/dma/sh/shdmac.c: In function ‘sh_dmae_probe’:
drivers/dma/sh/shdmac.c:541:34: error: ‘%d’ directive output may be truncated writing between 1 and 10 bytes into a region of size 9 [-Werror=format-truncation=]
  541 |                          "sh-dmae%d.%d", pdev->id, id);
      |                                  ^~
In function ‘sh_dmae_chan_probe’,
    inlined from ‘sh_dmae_probe’ at drivers/dma/sh/shdmac.c:845:9:
drivers/dma/sh/shdmac.c:541:26: note: directive argument in the range [0, 2147483647]
  541 |                          "sh-dmae%d.%d", pdev->id, id);
      |                          ^~~~~~~~~~~~~~
drivers/dma/sh/shdmac.c:541:26: note: directive argument in the range [0, 19]
drivers/dma/sh/shdmac.c:540:17: note: ‘snprintf’ output between 11 and 21 bytes into a destination of size 16
  540 |                 snprintf(sh_chan->dev_id, sizeof(sh_chan->dev_id),
      |                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  541 |                          "sh-dmae%d.%d", pdev->id, id);
      |                          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/sh/shdma.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h
index 9c121a4b33ad8..f97d80343aea4 100644
--- a/drivers/dma/sh/shdma.h
+++ b/drivers/dma/sh/shdma.h
@@ -25,7 +25,7 @@ struct sh_dmae_chan {
 	const struct sh_dmae_slave_config *config; /* Slave DMA configuration */
 	int xmit_shift;			/* log_2(bytes_per_xfer) */
 	void __iomem *base;
-	char dev_id[16];		/* unique name per DMAC of channel */
+	char dev_id[32];		/* unique name per DMAC of channel */
 	int pm_error;
 	dma_addr_t slave_addr;
 };
-- 
GitLab


From 6386f6c995b3ab91c72cfb76e4465553c555a8da Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Fri, 19 Jan 2024 18:10:44 +0530
Subject: [PATCH 3044/4076] dmaengine: fsl-qdma: increase size of 'irq_name'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We seem to have hit warnings of 'output may be truncated' which is fixed
by increasing the size of 'irq_name'

drivers/dma/fsl-qdma.c: In function ‘fsl_qdma_irq_init’:
drivers/dma/fsl-qdma.c:824:46: error: ‘%d’ directive writing between 1 and 11 bytes into a region of size 10 [-Werror=format-overflow=]
  824 |                 sprintf(irq_name, "qdma-queue%d", i);
      |                                              ^~
drivers/dma/fsl-qdma.c:824:35: note: directive argument in the range [-2147483641, 2147483646]
  824 |                 sprintf(irq_name, "qdma-queue%d", i);
      |                                   ^~~~~~~~~~~~~~
drivers/dma/fsl-qdma.c:824:17: note: ‘sprintf’ output between 12 and 22 bytes into a destination of size 20
  824 |                 sprintf(irq_name, "qdma-queue%d", i);
      |                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/fsl-qdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 47cb284680494..a1d0aa63142a9 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -805,7 +805,7 @@ fsl_qdma_irq_init(struct platform_device *pdev,
 	int i;
 	int cpu;
 	int ret;
-	char irq_name[20];
+	char irq_name[32];
 
 	fsl_qdma->error_irq =
 		platform_get_irq_byname(pdev, "qdma-error");
-- 
GitLab


From cb95a4fa50bbc1262bfb7fea482388a50b12948f Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Fri, 19 Jan 2024 18:10:44 +0530
Subject: [PATCH 3045/4076] dmaengine: dw-edma: increase size of 'name' in
 debugfs code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We seem to have hit warnings of 'output may be truncated' which is fixed
by increasing the size of 'name'

drivers/dma/dw-edma/dw-hdma-v0-debugfs.c: In function ‘dw_hdma_v0_debugfs_on’:
drivers/dma/dw-edma/dw-hdma-v0-debugfs.c:125:50: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 8 [-Werror=format-truncation=]
  125 |                 snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
      |                                                  ^~

drivers/dma/dw-edma/dw-hdma-v0-debugfs.c: In function ‘dw_hdma_v0_debugfs_on’:
drivers/dma/dw-edma/dw-hdma-v0-debugfs.c:142:50: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 8 [-Werror=format-truncation=]
  142 |                 snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
      |                                                  ^~
drivers/dma/dw-edma/dw-edma-v0-debugfs.c: In function ‘dw_edma_debugfs_regs_wr’:
drivers/dma/dw-edma/dw-edma-v0-debugfs.c:193:50: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 8 [-Werror=format-truncation=]
  193 |                 snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
      |                                                  ^~

Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dw-edma/dw-edma-v0-debugfs.c | 4 ++--
 drivers/dma/dw-edma/dw-hdma-v0-debugfs.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
index 0745d9e7d259b..406f169b09a75 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
@@ -176,7 +176,7 @@ dw_edma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
 	};
 	struct dentry *regs_dent, *ch_dent;
 	int nr_entries, i;
-	char name[16];
+	char name[32];
 
 	regs_dent = debugfs_create_dir(WRITE_STR, dent);
 
@@ -239,7 +239,7 @@ static noinline_for_stack void dw_edma_debugfs_regs_rd(struct dw_edma *dw,
 	};
 	struct dentry *regs_dent, *ch_dent;
 	int nr_entries, i;
-	char name[16];
+	char name[32];
 
 	regs_dent = debugfs_create_dir(READ_STR, dent);
 
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
index 520c81978b085..dcdc57fe976c1 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
@@ -116,7 +116,7 @@ static void dw_hdma_debugfs_regs_ch(struct dw_edma *dw, enum dw_edma_dir dir,
 static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
 {
 	struct dentry *regs_dent, *ch_dent;
-	char name[16];
+	char name[32];
 	int i;
 
 	regs_dent = debugfs_create_dir(WRITE_STR, dent);
@@ -133,7 +133,7 @@ static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
 static void dw_hdma_debugfs_regs_rd(struct dw_edma *dw, struct dentry *dent)
 {
 	struct dentry *regs_dent, *ch_dent;
-	char name[16];
+	char name[32];
 	int i;
 
 	regs_dent = debugfs_create_dir(READ_STR, dent);
-- 
GitLab


From 61c2ef4b6cb019946479baf0aeded648081bfb5c Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 31 Aug 2023 16:40:08 -0500
Subject: [PATCH 3046/4076] sparc: Use device_get_match_data()

Use preferred device_get_match_data() instead of of_match_device() to
get the driver match data. With this, adjust the includes to explicitly
include the correct headers.

Signed-off-by: Rob Herring <robh@kernel.org>
---
 arch/sparc/kernel/pci_sabre.c  |  9 +++++----
 arch/sparc/kernel/pci_schizo.c | 13 +++++++------
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/sparc/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c
index 3c38ca40a22ba..a84598568300d 100644
--- a/arch/sparc/kernel/pci_sabre.c
+++ b/arch/sparc/kernel/pci_sabre.c
@@ -13,7 +13,10 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 
 #include <asm/apb.h>
 #include <asm/iommu.h>
@@ -456,7 +459,6 @@ static void sabre_pbm_init(struct pci_pbm_info *pbm,
 static const struct of_device_id sabre_match[];
 static int sabre_probe(struct platform_device *op)
 {
-	const struct of_device_id *match;
 	const struct linux_prom64_registers *pr_regs;
 	struct device_node *dp = op->dev.of_node;
 	struct pci_pbm_info *pbm;
@@ -466,8 +468,7 @@ static int sabre_probe(struct platform_device *op)
 	const u32 *vdma;
 	u64 clear_irq;
 
-	match = of_match_device(sabre_match, &op->dev);
-	hummingbird_p = match && (match->data != NULL);
+	hummingbird_p = (uintptr_t)device_get_match_data(&op->dev);
 	if (!hummingbird_p) {
 		struct device_node *cpu_dp;
 
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 23b47f7fdb1d5..5d8dd49495863 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -11,7 +11,10 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/interrupt.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/numa.h>
 
 #include <asm/iommu.h>
@@ -1459,15 +1462,13 @@ out_err:
 	return err;
 }
 
-static const struct of_device_id schizo_match[];
 static int schizo_probe(struct platform_device *op)
 {
-	const struct of_device_id *match;
+	unsigned long chip_type = (unsigned long)device_get_match_data(&op->dev);
 
-	match = of_match_device(schizo_match, &op->dev);
-	if (!match)
+	if (!chip_type)
 		return -EINVAL;
-	return __schizo_init(op, (unsigned long)match->data);
+	return __schizo_init(op, chip_type);
 }
 
 /* The ordering of this table is very important.  Some Tomatillo
-- 
GitLab


From 5e6c3454b40594c6f1d398254e7b4005494f9638 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 1 Sep 2023 14:36:49 -0500
Subject: [PATCH 3047/4076] net: can: Use device_get_match_data()

Use preferred device_get_match_data() instead of of_match_device() to
get the driver match data. With this, adjust the includes to explicitly
include the correct headers.

Error checking for matching and match data was not necessary as matching
is always successful if we're already in probe and the match tables always
have data pointers.

Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/net/can/c_can/c_can_platform.c | 13 ++-----------
 drivers/net/can/flexcan/flexcan-core.c | 12 ++----------
 drivers/net/can/mscan/mpc5xxx_can.c    |  8 ++++----
 drivers/net/can/xilinx_can.c           |  9 +++------
 4 files changed, 11 insertions(+), 31 deletions(-)

diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index f44ba2600415f..e2ec69aa46e53 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -30,9 +30,9 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/clk.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 
@@ -259,22 +259,13 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	void __iomem *addr;
 	struct net_device *dev;
 	struct c_can_priv *priv;
-	const struct of_device_id *match;
 	struct resource *mem;
 	int irq;
 	struct clk *clk;
 	const struct c_can_driver_data *drvdata;
 	struct device_node *np = pdev->dev.of_node;
 
-	match = of_match_device(c_can_of_table, &pdev->dev);
-	if (match) {
-		drvdata = match->data;
-	} else if (pdev->id_entry->driver_data) {
-		drvdata = (struct c_can_driver_data *)
-			platform_get_device_id(pdev)->driver_data;
-	} else {
-		return -ENODEV;
-	}
+	drvdata = device_get_match_data(&pdev->dev);
 
 	/* get the appropriate clk */
 	clk = devm_clk_get(&pdev->dev, NULL);
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index d15f85a40c1e5..8ea7f2795551b 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -23,11 +23,11 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/can/platform/flexcan.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 
@@ -2034,7 +2034,6 @@ MODULE_DEVICE_TABLE(platform, flexcan_id_table);
 
 static int flexcan_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id;
 	const struct flexcan_devtype_data *devtype_data;
 	struct net_device *dev;
 	struct flexcan_priv *priv;
@@ -2090,14 +2089,7 @@ static int flexcan_probe(struct platform_device *pdev)
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
 
-	of_id = of_match_device(flexcan_of_match, &pdev->dev);
-	if (of_id)
-		devtype_data = of_id->data;
-	else if (platform_get_device_id(pdev)->driver_data)
-		devtype_data = (struct flexcan_devtype_data *)
-			platform_get_device_id(pdev)->driver_data;
-	else
-		return -ENODEV;
+	devtype_data = device_get_match_data(&pdev->dev);
 
 	if ((devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_FD) &&
 	    !((devtype_data->quirks &
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index 4837df6efa926..5b3d69c3b6b66 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -12,8 +12,10 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/netdevice.h>
 #include <linux/can/dev.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
@@ -290,7 +292,7 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
 	int irq, mscan_clksrc = 0;
 	int err = -ENOMEM;
 
-	data = of_device_get_match_data(&ofdev->dev);
+	data = device_get_match_data(&ofdev->dev);
 	if (!data)
 		return -EINVAL;
 
@@ -351,13 +353,11 @@ exit_unmap_mem:
 
 static void mpc5xxx_can_remove(struct platform_device *ofdev)
 {
-	const struct of_device_id *match;
 	const struct mpc5xxx_can_data *data;
 	struct net_device *dev = platform_get_drvdata(ofdev);
 	struct mscan_priv *priv = netdev_priv(dev);
 
-	match = of_match_device(mpc5xxx_can_table, &ofdev->dev);
-	data = match ? match->data : NULL;
+	data = device_get_match_data(&ofdev->dev);
 
 	unregister_mscandev(dev);
 	if (data && data->put_clock)
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index abe58f1030433..3722eaa84234e 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -20,8 +20,8 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
@@ -1726,8 +1726,7 @@ static int xcan_probe(struct platform_device *pdev)
 	struct net_device *ndev;
 	struct xcan_priv *priv;
 	struct phy *transceiver;
-	const struct of_device_id *of_id;
-	const struct xcan_devtype_data *devtype = &xcan_axi_data;
+	const struct xcan_devtype_data *devtype;
 	void __iomem *addr;
 	int ret;
 	int rx_max, tx_max;
@@ -1741,9 +1740,7 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	of_id = of_match_device(xcan_of_match, &pdev->dev);
-	if (of_id && of_id->data)
-		devtype = of_id->data;
+	devtype = device_get_match_data(&pdev->dev);
 
 	hw_tx_max_property = devtype->flags & XCAN_FLAG_TX_MAILBOXES ?
 			     "tx-mailbox-count" : "tx-fifo-depth";
-- 
GitLab


From ed7dafcc5364d5ff1ac85d7b18bf9a00ff28b6f8 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 9 Oct 2023 14:45:08 -0500
Subject: [PATCH 3048/4076] thermal: loongson2: Replace of_device.h with
 explicit includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h.

of_device.h isn't needed, but mod_devicetable.h and property.h were
implicitly included.

Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/thermal/loongson2_thermal.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/loongson2_thermal.c b/drivers/thermal/loongson2_thermal.c
index 99ca0c7bc41c7..0f475fe46bc9d 100644
--- a/drivers/thermal/loongson2_thermal.c
+++ b/drivers/thermal/loongson2_thermal.c
@@ -8,9 +8,10 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/minmax.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/thermal.h>
 #include <linux/units.h>
 #include "thermal_hwmon.h"
-- 
GitLab


From 527eb67e0cfb3f398d780cf04fde28ee55618a4a Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Mon, 11 Dec 2023 16:05:10 +1100
Subject: [PATCH 3049/4076] clk: qcom: gcc-x1e80100: Replace of_device.h with
 explicit includes

The DT of_device.h and of_platform.h date back to the separate
of_platform_bus_type before it as merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. They also include platform_device.h
and of.h.

of_device.h isn't needed, but mod_devicetable.h and platform_device.h
were implicitly included.

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reviewed-by: Sibi Sankar <quic_sibis@quicinc.com>
Link: https://lore.kernel.org/r/20231211160510.0aef871b@canb.auug.org.au
[robh: Redo commit msg]
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/clk/qcom/gcc-x1e80100.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c
index 74db7fef237b4..d7182d6e97837 100644
--- a/drivers/clk/qcom/gcc-x1e80100.c
+++ b/drivers/clk/qcom/gcc-x1e80100.c
@@ -4,8 +4,9 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 
 #include <dt-bindings/clock/qcom,x1e80100-gcc.h>
-- 
GitLab


From ef175b29a242fea98f467f008237484b03c94834 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 15 Jan 2021 15:24:59 -0600
Subject: [PATCH 3050/4076] of: Stop circularly including of_device.h and
 of_platform.h

The DT of_device.h and of_platform.h headers date back to the separate
of_platform_bus_type before it was merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. The headers also include
platform_device.h and of.h. The result was lots of drivers relied on
these implicit includes.

Now the entire tree has been fixed over the last couple of cycles to
explicitly include the necessary headers instead of relying on
of_device.h and/or of_platform.h implicit includes, so the implicit and
circular includes can finally be removed.

Signed-off-by: Rob Herring <robh@kernel.org>
---
 include/linux/of_device.h   | 5 +----
 include/linux/of_platform.h | 4 ++--
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index a72661e47faa5..9042bca5bb848 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -2,10 +2,7 @@
 #ifndef _LINUX_OF_DEVICE_H
 #define _LINUX_OF_DEVICE_H
 
-#include <linux/platform_device.h>
-#include <linux/of_platform.h> /* temporary until merge */
-
-#include <linux/of.h>
+#include <linux/device/driver.h>
 
 struct device;
 struct of_device_id;
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index fadfea5754852..a2ff1ad48f7f0 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -7,11 +7,11 @@
  */
 
 #include <linux/mod_devicetable.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
 
 struct device;
+struct device_node;
 struct of_device_id;
+struct platform_device;
 
 /**
  * struct of_dev_auxdata - lookup table entry for device names & platform_data
-- 
GitLab


From 71fee48fb772ac4f6cfa63dbebc5629de8b4cc09 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 15 Jan 2024 17:35:55 +0100
Subject: [PATCH 3051/4076] tick-sched: Fix idle and iowait sleeptime
 accounting vs CPU hotplug

When offlining and onlining CPUs the overall reported idle and iowait
times as reported by /proc/stat jump backward and forward:

cpu  132 0 176 225249 47 6 6 21 0 0
cpu0 80 0 115 112575 33 3 4 18 0 0
cpu1 52 0 60 112673 13 3 1 2 0 0

cpu  133 0 177 226681 47 6 6 21 0 0
cpu0 80 0 116 113387 33 3 4 18 0 0

cpu  133 0 178 114431 33 6 6 21 0 0 <---- jump backward
cpu0 80 0 116 114247 33 3 4 18 0 0
cpu1 52 0 61 183 0 3 1 2 0 0        <---- idle + iowait start with 0

cpu  133 0 178 228956 47 6 6 21 0 0 <---- jump forward
cpu0 81 0 117 114929 33 3 4 18 0 0

Reason for this is that get_idle_time() in fs/proc/stat.c has different
sources for both values depending on if a CPU is online or offline:

- if a CPU is online the values may be taken from its per cpu
  tick_cpu_sched structure

- if a CPU is offline the values are taken from its per cpu cpustat
  structure

The problem is that the per cpu tick_cpu_sched structure is set to zero on
CPU offline. See tick_cancel_sched_timer() in kernel/time/tick-sched.c.

Therefore when a CPU is brought offline and online afterwards both its idle
and iowait sleeptime will be zero, causing a jump backward in total system
idle and iowait sleeptime. In a similar way if a CPU is then brought
offline again the total idle and iowait sleeptimes will jump forward.

It looks like this behavior was introduced with commit 4b0c0f294f60
("tick: Cleanup NOHZ per cpu data on cpu down").

This was only noticed now on s390, since we switched to generic idle time
reporting with commit be76ea614460 ("s390/idle: remove arch_cpu_idle_time()
and corresponding code").

Fix this by preserving the values of idle_sleeptime and iowait_sleeptime
members of the per-cpu tick_sched structure on CPU hotplug.

Fixes: 4b0c0f294f60 ("tick: Cleanup NOHZ per cpu data on cpu down")
Reported-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20240115163555.1004144-1-hca@linux.ibm.com
---
 kernel/time/tick-sched.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a17d260028310..d2501673028da 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1576,13 +1576,18 @@ void tick_setup_sched_timer(void)
 void tick_cancel_sched_timer(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	ktime_t idle_sleeptime, iowait_sleeptime;
 
 # ifdef CONFIG_HIGH_RES_TIMERS
 	if (ts->sched_timer.base)
 		hrtimer_cancel(&ts->sched_timer);
 # endif
 
+	idle_sleeptime = ts->idle_sleeptime;
+	iowait_sleeptime = ts->iowait_sleeptime;
 	memset(ts, 0, sizeof(*ts));
+	ts->idle_sleeptime = idle_sleeptime;
+	ts->iowait_sleeptime = iowait_sleeptime;
 }
 #endif
 
-- 
GitLab


From f24a70106dc1ad2a755b2d42f47cf1dcf24f0b27 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@rivosinc.com>
Date: Fri, 19 Jan 2024 06:56:01 -0800
Subject: [PATCH 3052/4076] lib: checksum: Fix build with CONFIG_NET=n

The generic ipv6 checksums are only defined with CONFIG_NET=y, so gate
the test as well.

Fixes: 6f4c45cbcb00 ("kunit: Add tests for csum_ipv6_magic and ip_fast_csum")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401192143.jLdjbIy3-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202401192357.WU4nPRdN-lkp@intel.com/
Reviewed-By: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240119145600.3093-2-palmer@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 lib/checksum_kunit.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c
index af3e5ca4e1702..225bb77014600 100644
--- a/lib/checksum_kunit.c
+++ b/lib/checksum_kunit.c
@@ -593,6 +593,7 @@ static void test_ip_fast_csum(struct kunit *test)
 
 static void test_csum_ipv6_magic(struct kunit *test)
 {
+#if defined(CONFIG_NET)
 	const struct in6_addr *saddr;
 	const struct in6_addr *daddr;
 	unsigned int len;
@@ -616,6 +617,7 @@ static void test_csum_ipv6_magic(struct kunit *test)
 		CHECK_EQ(expected_csum_ipv6_magic[i],
 			 csum_ipv6_magic(saddr, daddr, len, proto, csum));
 	}
+#endif /* !CONFIG_NET */
 }
 
 static struct kunit_case __refdata checksum_test_cases[] = {
-- 
GitLab


From cfb7a13399be2234052a5bc480d166cd33047b0c Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Thu, 18 Jan 2024 22:36:13 -0600
Subject: [PATCH 3053/4076] cifs: update known bugs mentioned in kernel docs
 for cifs

Remove bugs that have been addressed and add link to xfstest results
wiki.

Signed-off-by: Steve French <stfrench@microsoft.com>
---
 Documentation/admin-guide/cifs/todo.rst | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/Documentation/admin-guide/cifs/todo.rst b/Documentation/admin-guide/cifs/todo.rst
index e46c360013947..9a65c670774ee 100644
--- a/Documentation/admin-guide/cifs/todo.rst
+++ b/Documentation/admin-guide/cifs/todo.rst
@@ -106,13 +106,7 @@ Known Bugs
 
 See https://bugzilla.samba.org - search on product "CifsVFS" for
 current bug list.  Also check http://bugzilla.kernel.org (Product = File System, Component = CIFS)
-
-1) existing symbolic links (Windows reparse points) are recognized but
-   can not be created remotely. They are implemented for Samba and those that
-   support the CIFS Unix extensions, although earlier versions of Samba
-   overly restrict the pathnames.
-2) follow_link and readdir code does not follow dfs junctions
-   but recognizes them
+and xfstest results e.g. https://wiki.samba.org/index.php/Xfstest-results-smb3
 
 Misc testing to do
 ==================
-- 
GitLab


From 76025cc2285d9ede3d717fe4305d66f8be2d9346 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Fri, 19 Jan 2024 01:08:26 -0300
Subject: [PATCH 3054/4076] smb: client: fix parsing of SMB3.1.1 POSIX create
 context

The data offset for the SMB3.1.1 POSIX create context will always be
8-byte aligned so having the check 'noff + nlen >= doff' in
smb2_parse_contexts() is wrong as it will lead to -EINVAL because noff
+ nlen == doff.

Fix the sanity check to correctly handle aligned create context data.

Fixes: af1689a9b770 ("smb: client: fix potential OOBs in smb2_parse_contexts()")
Signed-off-by: Paulo Alcantara <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index f8d70660ba292..ec39dfbc31541 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -2277,7 +2277,7 @@ int smb2_parse_contexts(struct TCP_Server_Info *server,
 
 		noff = le16_to_cpu(cc->NameOffset);
 		nlen = le16_to_cpu(cc->NameLength);
-		if (noff + nlen >= doff)
+		if (noff + nlen > doff)
 			return -EINVAL;
 
 		name = (char *)cc + noff;
-- 
GitLab


From 858e74876c5cbff1dfd5bace99e32fbce2abd4b5 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Fri, 19 Jan 2024 01:08:27 -0300
Subject: [PATCH 3055/4076] smb: client: parse owner/group when creating
 reparse points

Parse owner/group when creating special files and symlinks under
SMB3.1.1 POSIX mounts.

Move the parsing of owner/group to smb2_compound_op() so we don't have
to duplicate it in both smb2_get_reparse_inode() and
smb311_posix_query_path_info().

Signed-off-by: Paulo Alcantara <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h  |   2 +
 fs/smb/client/inode.c     |  25 +++-----
 fs/smb/client/smb2inode.c | 129 ++++++++++++++++++--------------------
 fs/smb/client/smb2proto.h |   4 +-
 4 files changed, 71 insertions(+), 89 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index f576ceee6157a..49ec4d3713fe9 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -204,6 +204,8 @@ struct cifs_open_info_data {
 		};
 	} reparse;
 	char *symlink_target;
+	struct cifs_sid posix_owner;
+	struct cifs_sid posix_group;
 	union {
 		struct smb2_file_all_info fi;
 		struct smb311_posix_qinfo posix_fi;
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 9f37c1758f732..cedffaad86aea 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -665,8 +665,6 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
 /* Fill a cifs_fattr struct with info from POSIX info struct */
 static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr,
 				       struct cifs_open_info_data *data,
-				       struct cifs_sid *owner,
-				       struct cifs_sid *group,
 				       struct super_block *sb)
 {
 	struct smb311_posix_qinfo *info = &data->posix_fi;
@@ -722,8 +720,8 @@ out_reparse:
 		fattr->cf_symlink_target = data->symlink_target;
 		data->symlink_target = NULL;
 	}
-	sid_to_id(cifs_sb, owner, fattr, SIDOWNER);
-	sid_to_id(cifs_sb, group, fattr, SIDGROUP);
+	sid_to_id(cifs_sb, &data->posix_owner, fattr, SIDOWNER);
+	sid_to_id(cifs_sb, &data->posix_group, fattr, SIDGROUP);
 
 	cifs_dbg(FYI, "POSIX query info: mode 0x%x uniqueid 0x%llx nlink %d\n",
 		fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink);
@@ -1070,9 +1068,7 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 				 const unsigned int xid,
 				 struct cifs_tcon *tcon,
 				 const char *full_path,
-				 struct cifs_fattr *fattr,
-				 struct cifs_sid *owner,
-				 struct cifs_sid *group)
+				 struct cifs_fattr *fattr)
 {
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
@@ -1117,7 +1113,7 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 	}
 
 	if (tcon->posix_extensions)
-		smb311_posix_info_to_fattr(fattr, data, owner, group, sb);
+		smb311_posix_info_to_fattr(fattr, data, sb);
 	else
 		cifs_open_info_to_fattr(fattr, data, sb);
 out:
@@ -1171,8 +1167,7 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 		 */
 		if (cifs_open_data_reparse(data)) {
 			rc = reparse_info_to_fattr(data, sb, xid, tcon,
-						   full_path, fattr,
-						   NULL, NULL);
+						   full_path, fattr);
 		} else {
 			cifs_open_info_to_fattr(fattr, data, sb);
 		}
@@ -1320,7 +1315,6 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_tcon *tcon;
 	struct tcon_link *tlink;
-	struct cifs_sid owner, group;
 	int tmprc;
 	int rc = 0;
 
@@ -1334,8 +1328,7 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 	 */
 	if (!data) {
 		rc = smb311_posix_query_path_info(xid, tcon, cifs_sb,
-						  full_path, &tmp_data,
-						  &owner, &group);
+						  full_path, &tmp_data);
 		data = &tmp_data;
 	}
 
@@ -1347,11 +1340,9 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 	case 0:
 		if (cifs_open_data_reparse(data)) {
 			rc = reparse_info_to_fattr(data, sb, xid, tcon,
-						   full_path, fattr,
-						   &owner, &group);
+						   full_path, fattr);
 		} else {
-			smb311_posix_info_to_fattr(fattr, data,
-						   &owner, &group, sb);
+			smb311_posix_info_to_fattr(fattr, data, sb);
 		}
 		break;
 	case -EREMOTE:
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 5053a5550abed..f38cdc38f10cb 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -56,6 +56,35 @@ static inline __u32 file_create_options(struct dentry *dentry)
 	return 0;
 }
 
+/* Parse owner and group from SMB3.1.1 POSIX query info */
+static int parse_posix_sids(struct cifs_open_info_data *data,
+			    struct kvec *rsp_iov)
+{
+	struct smb2_query_info_rsp *qi = rsp_iov->iov_base;
+	unsigned int out_len = le32_to_cpu(qi->OutputBufferLength);
+	unsigned int qi_len = sizeof(data->posix_fi);
+	int owner_len, group_len;
+	u8 *sidsbuf, *sidsbuf_end;
+
+	if (out_len <= qi_len)
+		return -EINVAL;
+
+	sidsbuf = (u8 *)qi + le16_to_cpu(qi->OutputBufferOffset) + qi_len;
+	sidsbuf_end = sidsbuf + out_len - qi_len;
+
+	owner_len = posix_info_sid_size(sidsbuf, sidsbuf_end);
+	if (owner_len == -1)
+		return -EINVAL;
+
+	memcpy(&data->posix_owner, sidsbuf, owner_len);
+	group_len = posix_info_sid_size(sidsbuf + owner_len, sidsbuf_end);
+	if (group_len == -1)
+		return -EINVAL;
+
+	memcpy(&data->posix_group, sidsbuf + owner_len, group_len);
+	return 0;
+}
+
 /*
  * note: If cfile is passed, the reference to it is dropped here.
  * So make sure that you do not reuse cfile after return from this func.
@@ -69,7 +98,6 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 			    __u32 desired_access, __u32 create_disposition,
 			    __u32 create_options, umode_t mode, struct kvec *in_iov,
 			    int *cmds, int num_cmds, struct cifsFileInfo *cfile,
-			    __u8 **extbuf, size_t *extbuflen,
 			    struct kvec *out_iov, int *out_buftype)
 {
 
@@ -494,21 +522,9 @@ finished:
 					&rsp_iov[i + 1], sizeof(idata->posix_fi) /* add SIDs */,
 					(char *)&idata->posix_fi);
 			}
-			if (rc == 0) {
-				unsigned int length = le32_to_cpu(qi_rsp->OutputBufferLength);
-
-				if (length > sizeof(idata->posix_fi)) {
-					char *base = (char *)rsp_iov[i + 1].iov_base +
-						le16_to_cpu(qi_rsp->OutputBufferOffset) +
-						sizeof(idata->posix_fi);
-					*extbuflen = length - sizeof(idata->posix_fi);
-					*extbuf = kmemdup(base, *extbuflen, GFP_KERNEL);
-					if (!*extbuf)
-						rc = -ENOMEM;
-				} else {
-					rc = -EINVAL;
-				}
-			}
+			if (rc == 0)
+				rc = parse_posix_sids(idata, &rsp_iov[i + 1]);
+
 			SMB2_query_info_free(&rqst[num_rqst++]);
 			if (rc)
 				trace_smb3_posix_query_info_compound_err(xid,  ses->Suid,
@@ -693,9 +709,8 @@ int smb2_query_path_info(const unsigned int xid,
 	cifs_get_readable_path(tcon, full_path, &cfile);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_READ_ATTRIBUTES, FILE_OPEN,
-			      create_options, ACL_NO_MODE,
-			      in_iov, cmds, 1, cfile,
-			      NULL, NULL, out_iov, out_buftype);
+			      create_options, ACL_NO_MODE, in_iov,
+			      cmds, 1, cfile, out_iov, out_buftype);
 	hdr = out_iov[0].iov_base;
 	/*
 	 * If first iov is unset, then SMB session was dropped or we've got a
@@ -722,8 +737,8 @@ int smb2_query_path_info(const unsigned int xid,
 		cifs_get_readable_path(tcon, full_path, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      FILE_READ_ATTRIBUTES, FILE_OPEN,
-				      create_options, ACL_NO_MODE, in_iov, cmds,
-				      num_cmds, cfile, NULL, NULL, NULL, NULL);
+				      create_options, ACL_NO_MODE, in_iov,
+				      cmds, num_cmds, cfile, NULL, NULL);
 		break;
 	case -EREMOTE:
 		break;
@@ -750,19 +765,13 @@ int smb311_posix_query_path_info(const unsigned int xid,
 				 struct cifs_tcon *tcon,
 				 struct cifs_sb_info *cifs_sb,
 				 const char *full_path,
-				 struct cifs_open_info_data *data,
-				 struct cifs_sid *owner,
-				 struct cifs_sid *group)
+				 struct cifs_open_info_data *data)
 {
 	int rc;
 	__u32 create_options = 0;
 	struct cifsFileInfo *cfile;
 	struct kvec in_iov[2], out_iov[3] = {};
 	int out_buftype[3] = {};
-	__u8 *sidsbuf = NULL;
-	__u8 *sidsbuf_end = NULL;
-	size_t sidsbuflen = 0;
-	size_t owner_len, group_len;
 	int cmds[2] = { SMB2_OP_POSIX_QUERY_INFO,  };
 	int i, num_cmds;
 
@@ -782,8 +791,8 @@ int smb311_posix_query_path_info(const unsigned int xid,
 	cifs_get_readable_path(tcon, full_path, &cfile);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_READ_ATTRIBUTES, FILE_OPEN,
-			      create_options, ACL_NO_MODE, in_iov, cmds, 1,
-			      cfile, &sidsbuf, &sidsbuflen, out_iov, out_buftype);
+			      create_options, ACL_NO_MODE, in_iov,
+			      cmds, 1, cfile, out_iov, out_buftype);
 	/*
 	 * If first iov is unset, then SMB session was dropped or we've got a
 	 * cached open file (@cfile).
@@ -810,32 +819,12 @@ int smb311_posix_query_path_info(const unsigned int xid,
 		cifs_get_readable_path(tcon, full_path, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      FILE_READ_ATTRIBUTES, FILE_OPEN,
-				      create_options, ACL_NO_MODE, in_iov, cmds,
-				      num_cmds, cfile, &sidsbuf, &sidsbuflen, NULL, NULL);
+				      create_options, ACL_NO_MODE, in_iov,
+				      cmds, num_cmds, cfile, NULL, NULL);
 		break;
 	}
 
 out:
-	if (rc == 0) {
-		sidsbuf_end = sidsbuf + sidsbuflen;
-
-		owner_len = posix_info_sid_size(sidsbuf, sidsbuf_end);
-		if (owner_len == -1) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(owner, sidsbuf, owner_len);
-
-		group_len = posix_info_sid_size(
-			sidsbuf + owner_len, sidsbuf_end);
-		if (group_len == -1) {
-			rc = -EINVAL;
-			goto out;
-		}
-		memcpy(group, sidsbuf + owner_len, group_len);
-	}
-
-	kfree(sidsbuf);
 	for (i = 0; i < ARRAY_SIZE(out_buftype); i++)
 		free_rsp_buf(out_buftype[i], out_iov[i].iov_base);
 	return rc;
@@ -848,9 +837,9 @@ smb2_mkdir(const unsigned int xid, struct inode *parent_inode, umode_t mode,
 {
 	return smb2_compound_op(xid, tcon, cifs_sb, name,
 				FILE_WRITE_ATTRIBUTES, FILE_CREATE,
-				CREATE_NOT_FILE, mode, NULL,
-				&(int){SMB2_OP_MKDIR}, 1,
-				NULL, NULL, NULL, NULL, NULL);
+				CREATE_NOT_FILE, mode,
+				NULL, &(int){SMB2_OP_MKDIR}, 1,
+				NULL, NULL, NULL);
 }
 
 void
@@ -875,7 +864,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name,
 				 FILE_WRITE_ATTRIBUTES, FILE_CREATE,
 				 CREATE_NOT_FILE, ACL_NO_MODE, &in_iov,
 				 &(int){SMB2_OP_SET_INFO}, 1,
-				 cfile, NULL, NULL, NULL, NULL);
+				 cfile, NULL, NULL);
 	if (tmprc == 0)
 		cifs_i->cifsAttrs = dosattrs;
 }
@@ -887,8 +876,9 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	drop_cached_dir_by_name(xid, tcon, name, cifs_sb);
 	return smb2_compound_op(xid, tcon, cifs_sb, name,
 				DELETE, FILE_OPEN, CREATE_NOT_FILE,
-				ACL_NO_MODE, NULL, &(int){SMB2_OP_RMDIR}, 1,
-				NULL, NULL, NULL, NULL, NULL);
+				ACL_NO_MODE, NULL,
+				&(int){SMB2_OP_RMDIR}, 1,
+				NULL, NULL, NULL);
 }
 
 int
@@ -897,8 +887,9 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 {
 	return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN,
 				CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT,
-				ACL_NO_MODE, NULL, &(int){SMB2_OP_DELETE}, 1,
-				NULL, NULL, NULL, NULL, NULL);
+				ACL_NO_MODE, NULL,
+				&(int){SMB2_OP_DELETE}, 1,
+				NULL, NULL, NULL);
 }
 
 static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
@@ -919,8 +910,8 @@ static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	in_iov.iov_base = smb2_to_name;
 	in_iov.iov_len = 2 * UniStrnlen((wchar_t *)smb2_to_name, PATH_MAX);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, from_name, access,
-			      FILE_OPEN, create_options, ACL_NO_MODE, &in_iov,
-			      &command, 1, cfile, NULL, NULL, NULL, NULL);
+			      FILE_OPEN, create_options, ACL_NO_MODE,
+			      &in_iov, &command, 1, cfile, NULL, NULL);
 smb2_rename_path:
 	kfree(smb2_to_name);
 	return rc;
@@ -971,7 +962,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
 				FILE_WRITE_DATA, FILE_OPEN,
 				0, ACL_NO_MODE, &in_iov,
 				&(int){SMB2_OP_SET_EOF}, 1,
-				cfile, NULL, NULL, NULL, NULL);
+				cfile, NULL, NULL);
 }
 
 int
@@ -999,8 +990,8 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_WRITE_ATTRIBUTES, FILE_OPEN,
 			      0, ACL_NO_MODE, &in_iov,
-			      &(int){SMB2_OP_SET_INFO}, 1, cfile,
-			      NULL, NULL, NULL, NULL);
+			      &(int){SMB2_OP_SET_INFO}, 1,
+			      cfile, NULL, NULL);
 	cifs_put_tlink(tlink);
 	return rc;
 }
@@ -1035,7 +1026,7 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
 		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      da, cd, co, ACL_NO_MODE, in_iov,
-				      cmds, 2, cfile, NULL, NULL, NULL, NULL);
+				      cmds, 2, cfile, NULL, NULL);
 		if (!rc) {
 			rc = smb311_posix_get_inode_info(&new, full_path,
 							 data, sb, xid);
@@ -1045,7 +1036,7 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
 		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      da, cd, co, ACL_NO_MODE, in_iov,
-				      cmds, 2, cfile, NULL, NULL, NULL, NULL);
+				      cmds, 2, cfile, NULL, NULL);
 		if (!rc) {
 			rc = cifs_get_inode_info(&new, full_path,
 						 data, sb, xid, NULL);
@@ -1072,8 +1063,8 @@ int smb2_query_reparse_point(const unsigned int xid,
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_READ_ATTRIBUTES, FILE_OPEN,
 			      OPEN_REPARSE_POINT, ACL_NO_MODE, &in_iov,
-			      &(int){SMB2_OP_GET_REPARSE}, 1, cfile,
-			      NULL, NULL, NULL, NULL);
+			      &(int){SMB2_OP_GET_REPARSE}, 1,
+			      cfile, NULL, NULL);
 	if (rc)
 		goto out;
 
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 343ada691e763..0034b537b0b3f 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -299,9 +299,7 @@ int smb311_posix_query_path_info(const unsigned int xid,
 				 struct cifs_tcon *tcon,
 				 struct cifs_sb_info *cifs_sb,
 				 const char *full_path,
-				 struct cifs_open_info_data *data,
-				 struct cifs_sid *owner,
-				 struct cifs_sid *group);
+				 struct cifs_open_info_data *data);
 int posix_info_parse(const void *beg, const void *end,
 		     struct smb2_posix_info_parsed *out);
 int posix_info_sid_size(const void *beg, const void *end);
-- 
GitLab


From f83709b9e0eb7048d74ba4515f268c6eacbce9c9 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Fri, 19 Jan 2024 01:08:28 -0300
Subject: [PATCH 3056/4076] smb: client: get rid of
 smb311_posix_query_path_info()

Merge smb311_posix_query_path_info into ->query_path_info() to get rid
of duplicate code.

Signed-off-by: Paulo Alcantara <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/inode.c     |   4 +-
 fs/smb/client/smb2inode.c | 115 +++++++++++---------------------------
 2 files changed, 36 insertions(+), 83 deletions(-)

diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index cedffaad86aea..f0989484f2c64 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1312,6 +1312,7 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 				  const unsigned int xid)
 {
 	struct cifs_open_info_data tmp_data = {};
+	struct TCP_Server_Info *server;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_tcon *tcon;
 	struct tcon_link *tlink;
@@ -1322,12 +1323,13 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
 	tcon = tlink_tcon(tlink);
+	server = tcon->ses->server;
 
 	/*
 	 * 1. Fetch file metadata if not provided (data)
 	 */
 	if (!data) {
-		rc = smb311_posix_query_path_info(xid, tcon, cifs_sb,
+		rc = server->ops->query_path_info(xid, tcon, cifs_sb,
 						  full_path, &tmp_data);
 		data = &tmp_data;
 	}
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index f38cdc38f10cb..a652200540c8a 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -678,7 +678,7 @@ int smb2_query_path_info(const unsigned int xid,
 	struct smb2_hdr *hdr;
 	struct kvec in_iov[2], out_iov[3] = {};
 	int out_buftype[3] = {};
-	int cmds[2] = { SMB2_OP_QUERY_INFO,  };
+	int cmds[2];
 	bool islink;
 	int i, num_cmds;
 	int rc, rc2;
@@ -686,20 +686,36 @@ int smb2_query_path_info(const unsigned int xid,
 	data->adjust_tz = false;
 	data->reparse_point = false;
 
-	if (strcmp(full_path, ""))
-		rc = -ENOENT;
-	else
-		rc = open_cached_dir(xid, tcon, full_path, cifs_sb, false, &cfid);
-	/* If it is a root and its handle is cached then use it */
-	if (!rc) {
-		if (cfid->file_all_info_is_valid) {
-			memcpy(&data->fi, &cfid->file_all_info, sizeof(data->fi));
+	/*
+	 * BB TODO: Add support for using cached root handle in SMB3.1.1 POSIX.
+	 * Create SMB2_query_posix_info worker function to do non-compounded
+	 * query when we already have an open file handle for this. For now this
+	 * is fast enough (always using the compounded version).
+	 */
+	if (!tcon->posix_extensions) {
+		if (*full_path) {
+			rc = -ENOENT;
 		} else {
-			rc = SMB2_query_info(xid, tcon, cfid->fid.persistent_fid,
-					     cfid->fid.volatile_fid, &data->fi);
+			rc = open_cached_dir(xid, tcon, full_path,
+					     cifs_sb, false, &cfid);
 		}
-		close_cached_dir(cfid);
-		return rc;
+		/* If it is a root and its handle is cached then use it */
+		if (!rc) {
+			if (cfid->file_all_info_is_valid) {
+				memcpy(&data->fi, &cfid->file_all_info,
+				       sizeof(data->fi));
+			} else {
+				rc = SMB2_query_info(xid, tcon,
+						     cfid->fid.persistent_fid,
+						     cfid->fid.volatile_fid,
+						     &data->fi);
+			}
+			close_cached_dir(cfid);
+			return rc;
+		}
+		cmds[0] = SMB2_OP_QUERY_INFO;
+	} else {
+		cmds[0] = SMB2_OP_POSIX_QUERY_INFO;
 	}
 
 	in_iov[0].iov_base = data;
@@ -722,6 +738,10 @@ int smb2_query_path_info(const unsigned int xid,
 	switch (rc) {
 	case 0:
 	case -EOPNOTSUPP:
+		/*
+		 * BB TODO: When support for special files added to Samba
+		 * re-verify this path.
+		 */
 		rc = parse_create_response(data, cifs_sb, &out_iov[0]);
 		if (rc || !data->reparse_point)
 			goto out;
@@ -761,75 +781,6 @@ out:
 	return rc;
 }
 
-int smb311_posix_query_path_info(const unsigned int xid,
-				 struct cifs_tcon *tcon,
-				 struct cifs_sb_info *cifs_sb,
-				 const char *full_path,
-				 struct cifs_open_info_data *data)
-{
-	int rc;
-	__u32 create_options = 0;
-	struct cifsFileInfo *cfile;
-	struct kvec in_iov[2], out_iov[3] = {};
-	int out_buftype[3] = {};
-	int cmds[2] = { SMB2_OP_POSIX_QUERY_INFO,  };
-	int i, num_cmds;
-
-	data->adjust_tz = false;
-	data->reparse_point = false;
-
-	/*
-	 * BB TODO: Add support for using the cached root handle.
-	 * Create SMB2_query_posix_info worker function to do non-compounded query
-	 * when we already have an open file handle for this. For now this is fast enough
-	 * (always using the compounded version).
-	 */
-	in_iov[0].iov_base = data;
-	in_iov[0].iov_len = sizeof(*data);
-	in_iov[1] = in_iov[0];
-
-	cifs_get_readable_path(tcon, full_path, &cfile);
-	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
-			      FILE_READ_ATTRIBUTES, FILE_OPEN,
-			      create_options, ACL_NO_MODE, in_iov,
-			      cmds, 1, cfile, out_iov, out_buftype);
-	/*
-	 * If first iov is unset, then SMB session was dropped or we've got a
-	 * cached open file (@cfile).
-	 */
-	if (!out_iov[0].iov_base || out_buftype[0] == CIFS_NO_BUFFER)
-		goto out;
-
-	switch (rc) {
-	case 0:
-	case -EOPNOTSUPP:
-		/* BB TODO: When support for special files added to Samba re-verify this path */
-		rc = parse_create_response(data, cifs_sb, &out_iov[0]);
-		if (rc || !data->reparse_point)
-			goto out;
-
-		if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK) {
-			/* symlink already parsed in create response */
-			num_cmds = 1;
-		} else {
-			cmds[1] = SMB2_OP_GET_REPARSE;
-			num_cmds = 2;
-		}
-		create_options |= OPEN_REPARSE_POINT;
-		cifs_get_readable_path(tcon, full_path, &cfile);
-		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
-				      FILE_READ_ATTRIBUTES, FILE_OPEN,
-				      create_options, ACL_NO_MODE, in_iov,
-				      cmds, num_cmds, cfile, NULL, NULL);
-		break;
-	}
-
-out:
-	for (i = 0; i < ARRAY_SIZE(out_buftype); i++)
-		free_rsp_buf(out_buftype[i], out_iov[i].iov_base);
-	return rc;
-}
-
 int
 smb2_mkdir(const unsigned int xid, struct inode *parent_inode, umode_t mode,
 	   struct cifs_tcon *tcon, const char *name,
-- 
GitLab


From 66c9314b61ed5b7bfcff0d89359aa0f975c0ab53 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Fri, 19 Jan 2024 01:08:29 -0300
Subject: [PATCH 3057/4076] smb: client: don't clobber ->i_rdev from cached
 reparse points

Don't clobber ->i_rdev from valid reparse inodes over readdir(2) as it
can't be provided by query dir responses.

Signed-off-by: Paulo Alcantara <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/readdir.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index e24684112ab0a..94255401b38dc 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -133,14 +133,14 @@ retry:
 				 * Query dir responses don't provide enough
 				 * information about reparse points other than
 				 * their reparse tags.  Save an invalidation by
-				 * not clobbering the existing mode, size and
-				 * symlink target (if any) when reparse tag and
-				 * ctime haven't changed.
+				 * not clobbering some existing attributes when
+				 * reparse tag and ctime haven't changed.
 				 */
 				rc = 0;
 				if (fattr->cf_cifsattrs & ATTR_REPARSE) {
 					if (likely(reparse_inode_match(inode, fattr))) {
 						fattr->cf_mode = inode->i_mode;
+						fattr->cf_rdev = inode->i_rdev;
 						fattr->cf_eof = CIFS_I(inode)->server_eof;
 						fattr->cf_symlink_target = NULL;
 					} else {
-- 
GitLab


From 49fe25ce838183afac20f40457157ec009a86930 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 3 Jan 2024 08:36:22 +0000
Subject: [PATCH 3058/4076] cifs: reschedule periodic query for server
 interfaces

Today, we schedule periodic query for server interfaces
once every 10 minutes once a tree connection has been
established. Recent change to handle disabling of
multichannel disabled this delayed work.

This change reenables it following a reconnect, and
the server advertises multichannel.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index ec39dfbc31541..88c60187593f9 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -405,6 +405,8 @@ skip_sess_setup:
 				cifs_server_dbg(VFS, "supports multichannel now\n");
 
 			cifs_try_adding_channels(ses);
+			queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
+					   (SMB_INTERFACE_POLL_INTERVAL * HZ));
 		}
 	} else {
 		mutex_unlock(&ses->session_mutex);
-- 
GitLab


From ce09f8d8a7130e6edfdd6fcad8eb277824d5de95 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 17 Jan 2024 06:09:16 +0000
Subject: [PATCH 3059/4076] cifs: new mount option called retrans

We have several places in the code where we treat the
error -EAGAIN very differently. Some code retry for
arbitrary number of times.

Introducing this new mount option named "retrans", so
that all these handlers of -EAGAIN can retry a fixed
number of times. This applies only to soft mounts.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsfs.c     | 2 ++
 fs/smb/client/cifsglob.h   | 1 +
 fs/smb/client/connect.c    | 4 ++++
 fs/smb/client/fs_context.c | 6 ++++++
 fs/smb/client/fs_context.h | 2 ++
 5 files changed, 15 insertions(+)

diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 99b0ade833aa3..de46beb7fa4a9 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -681,6 +681,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_printf(s, ",rasize=%u", cifs_sb->ctx->rasize);
 	if (tcon->ses->server->min_offload)
 		seq_printf(s, ",esize=%u", tcon->ses->server->min_offload);
+	if (tcon->ses->server->retrans)
+		seq_printf(s, ",retrans=%u", tcon->ses->server->retrans);
 	seq_printf(s, ",echo_interval=%lu",
 			tcon->ses->server->echo_interval / HZ);
 
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 49ec4d3713fe9..20036fb16cece 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -753,6 +753,7 @@ struct TCP_Server_Info {
 	unsigned int	max_read;
 	unsigned int	max_write;
 	unsigned int	min_offload;
+	unsigned int	retrans;
 	__le16	compress_algorithm;
 	__u16	signing_algorithm;
 	__le16	cipher_type;
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 3052a208c6ca0..bfd568f897105 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -1574,6 +1574,9 @@ static int match_server(struct TCP_Server_Info *server,
 	if (server->min_offload != ctx->min_offload)
 		return 0;
 
+	if (server->retrans != ctx->retrans)
+		return 0;
+
 	return 1;
 }
 
@@ -1798,6 +1801,7 @@ smbd_connected:
 		goto out_err_crypto_release;
 	}
 	tcp_ses->min_offload = ctx->min_offload;
+	tcp_ses->retrans = ctx->retrans;
 	/*
 	 * at this point we are the only ones with the pointer
 	 * to the struct since the kernel thread not created yet
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index a3493da12ad1e..52cbef2eeb28f 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -139,6 +139,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
 	fsparam_u32("dir_mode", Opt_dirmode),
 	fsparam_u32("port", Opt_port),
 	fsparam_u32("min_enc_offload", Opt_min_enc_offload),
+	fsparam_u32("retrans", Opt_retrans),
 	fsparam_u32("esize", Opt_min_enc_offload),
 	fsparam_u32("bsize", Opt_blocksize),
 	fsparam_u32("rasize", Opt_rasize),
@@ -1064,6 +1065,9 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 	case Opt_min_enc_offload:
 		ctx->min_offload = result.uint_32;
 		break;
+	case Opt_retrans:
+		ctx->retrans = result.uint_32;
+		break;
 	case Opt_blocksize:
 		/*
 		 * inode blocksize realistically should never need to be
@@ -1619,6 +1623,8 @@ int smb3_init_fs_context(struct fs_context *fc)
 	ctx->backupuid_specified = false; /* no backup intent for a user */
 	ctx->backupgid_specified = false; /* no backup intent for a group */
 
+	ctx->retrans = 1;
+
 /*
  *	short int override_uid = -1;
  *	short int override_gid = -1;
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index cf46916286d02..182ce11cbe936 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -118,6 +118,7 @@ enum cifs_param {
 	Opt_file_mode,
 	Opt_dirmode,
 	Opt_min_enc_offload,
+	Opt_retrans,
 	Opt_blocksize,
 	Opt_rasize,
 	Opt_rsize,
@@ -245,6 +246,7 @@ struct smb3_fs_context {
 	unsigned int rsize;
 	unsigned int wsize;
 	unsigned int min_offload;
+	unsigned int retrans;
 	bool sockopt_tcp_nodelay:1;
 	/* attribute cache timemout for files and directories in jiffies */
 	unsigned long acregmax;
-- 
GitLab


From f591062bdbf4742b7f1622173017f19e927057b0 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Tue, 2 Jan 2024 13:14:46 +0000
Subject: [PATCH 3060/4076] cifs: handle servers that still advertise
 multichannel after disabling

Some servers like Azure SMB servers always advertise multichannel
capability in server capabilities list. Such servers return error
STATUS_NOT_IMPLEMENTED for ioctl calls to query server interfaces,
and expect clients to consider that as a sign that they do not support
multichannel.

We already handled this at mount time. Soon after the tree connect,
we query server interfaces. And when server returned STATUS_NOT_IMPLEMENTED,
we kept interface list as empty. When cifs_try_adding_channels gets
called, it would not find any interfaces, so will not add channels.

For the case where an active multichannel mount exists, and multichannel
is disabled by such a server, this change will now allow the client
to disable secondary channels on the mount. It will check the return
status of query server interfaces call soon after a tree reconnect.
If the return status is EOPNOTSUPP, then instead of the check to add
more channels, we'll disable the secondary channels instead.

For better code reuse, this change also moves the common code for
disabling multichannel to a helper function.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c |   8 +--
 fs/smb/client/smb2pdu.c | 107 +++++++++++++++++++++++++---------------
 2 files changed, 69 insertions(+), 46 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 01a5bd7e6a307..f080fac1b26ee 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -614,7 +614,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 				 "multichannel not available\n"
 				 "Empty network interface list returned by server %s\n",
 				 ses->server->hostname);
-		rc = -EINVAL;
+		rc = -EOPNOTSUPP;
 		goto out;
 	}
 
@@ -734,12 +734,6 @@ next_iface:
 	if ((bytes_left > 8) || p->Next)
 		cifs_dbg(VFS, "%s: incomplete interface info\n", __func__);
 
-
-	if (!ses->iface_count) {
-		rc = -EINVAL;
-		goto out;
-	}
-
 out:
 	/*
 	 * Go through the list again and put the inactive entries
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 88c60187593f9..288199f0b987d 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -156,6 +156,57 @@ out:
 	return;
 }
 
+/* helper function for code reuse */
+static int
+cifs_chan_skip_or_disable(struct cifs_ses *ses,
+			  struct TCP_Server_Info *server,
+			  bool from_reconnect)
+{
+	struct TCP_Server_Info *pserver;
+	unsigned int chan_index;
+
+	if (SERVER_IS_CHAN(server)) {
+		cifs_dbg(VFS,
+			"server %s does not support multichannel anymore. Skip secondary channel\n",
+			 ses->server->hostname);
+
+		spin_lock(&ses->chan_lock);
+		chan_index = cifs_ses_get_chan_index(ses, server);
+		if (chan_index == CIFS_INVAL_CHAN_INDEX) {
+			spin_unlock(&ses->chan_lock);
+			goto skip_terminate;
+		}
+
+		ses->chans[chan_index].server = NULL;
+		spin_unlock(&ses->chan_lock);
+
+		/*
+		 * the above reference of server by channel
+		 * needs to be dropped without holding chan_lock
+		 * as cifs_put_tcp_session takes a higher lock
+		 * i.e. cifs_tcp_ses_lock
+		 */
+		cifs_put_tcp_session(server, from_reconnect);
+
+		server->terminate = true;
+		cifs_signal_cifsd_for_reconnect(server, false);
+
+		/* mark primary server as needing reconnect */
+		pserver = server->primary_server;
+		cifs_signal_cifsd_for_reconnect(pserver, false);
+skip_terminate:
+		mutex_unlock(&ses->session_mutex);
+		return -EHOSTDOWN;
+	}
+
+	cifs_server_dbg(VFS,
+		"server does not support multichannel anymore. Disable all other channels\n");
+	cifs_disable_secondary_channels(ses);
+
+
+	return 0;
+}
+
 static int
 smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	       struct TCP_Server_Info *server, bool from_reconnect)
@@ -164,8 +215,6 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	struct nls_table *nls_codepage = NULL;
 	struct cifs_ses *ses;
 	int xid;
-	struct TCP_Server_Info *pserver;
-	unsigned int chan_index;
 
 	/*
 	 * SMB2s NegProt, SessSetup, Logoff do not have tcon yet so
@@ -310,44 +359,11 @@ again:
 		 */
 		if (ses->chan_count > 1 &&
 		    !(server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
-			if (SERVER_IS_CHAN(server)) {
-				cifs_dbg(VFS, "server %s does not support " \
-					 "multichannel anymore. skipping secondary channel\n",
-					 ses->server->hostname);
-
-				spin_lock(&ses->chan_lock);
-				chan_index = cifs_ses_get_chan_index(ses, server);
-				if (chan_index == CIFS_INVAL_CHAN_INDEX) {
-					spin_unlock(&ses->chan_lock);
-					goto skip_terminate;
-				}
-
-				ses->chans[chan_index].server = NULL;
-				spin_unlock(&ses->chan_lock);
-
-				/*
-				 * the above reference of server by channel
-				 * needs to be dropped without holding chan_lock
-				 * as cifs_put_tcp_session takes a higher lock
-				 * i.e. cifs_tcp_ses_lock
-				 */
-				cifs_put_tcp_session(server, from_reconnect);
-
-				server->terminate = true;
-				cifs_signal_cifsd_for_reconnect(server, false);
-
-				/* mark primary server as needing reconnect */
-				pserver = server->primary_server;
-				cifs_signal_cifsd_for_reconnect(pserver, false);
-
-skip_terminate:
+			rc = cifs_chan_skip_or_disable(ses, server,
+						       from_reconnect);
+			if (rc) {
 				mutex_unlock(&ses->session_mutex);
-				rc = -EHOSTDOWN;
 				goto out;
-			} else {
-				cifs_server_dbg(VFS, "does not support " \
-					 "multichannel anymore. disabling all other channels\n");
-				cifs_disable_secondary_channels(ses);
 			}
 		}
 
@@ -395,11 +411,23 @@ skip_sess_setup:
 		rc = SMB3_request_interfaces(xid, tcon, false);
 		free_xid(xid);
 
-		if (rc)
+		if (rc == -EOPNOTSUPP) {
+			/*
+			 * some servers like Azure SMB server do not advertise
+			 * that multichannel has been disabled with server
+			 * capabilities, rather return STATUS_NOT_IMPLEMENTED.
+			 * treat this as server not supporting multichannel
+			 */
+
+			rc = cifs_chan_skip_or_disable(ses, server,
+						       from_reconnect);
+			goto skip_add_channels;
+		} else if (rc)
 			cifs_dbg(FYI, "%s: failed to query server interfaces: %d\n",
 				 __func__, rc);
 
 		if (ses->chan_max > ses->chan_count &&
+		    ses->iface_count &&
 		    !SERVER_IS_CHAN(server)) {
 			if (ses->chan_count == 1)
 				cifs_server_dbg(VFS, "supports multichannel now\n");
@@ -411,6 +439,7 @@ skip_sess_setup:
 	} else {
 		mutex_unlock(&ses->session_mutex);
 	}
+skip_add_channels:
 
 	if (smb2_command != SMB2_INTERNAL_CMD)
 		mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
-- 
GitLab


From 78e727e58e54efca4c23863fbd9e16e9d2d83f81 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 3 Jan 2024 12:51:49 +0000
Subject: [PATCH 3061/4076] cifs: update iface_last_update on each
 query-and-update

iface_last_update was an unused field when it was introduced.
Later, when we had periodic update of server interface list,
this field was used regularly to decide when to update next.

However, with the new logic of updating the interfaces, it
becomes crucial that this field be updated whenever
parse_server_interfaces runs successfully.

This change updates this field when either the server does
not support query of interfaces; so that we do not query
the interfaces repeatedly. It also updates the field when
the function reaches the end.

Fixes: aa45dadd34e4 ("cifs: change iface_list from array to sorted linked list")
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index f080fac1b26ee..d9553c2556a29 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -615,6 +615,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 				 "Empty network interface list returned by server %s\n",
 				 ses->server->hostname);
 		rc = -EOPNOTSUPP;
+		ses->iface_last_update = jiffies;
 		goto out;
 	}
 
@@ -712,7 +713,6 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 
 		ses->iface_count++;
 		spin_unlock(&ses->iface_lock);
-		ses->iface_last_update = jiffies;
 next_iface:
 		nb_iface++;
 		next = le32_to_cpu(p->Next);
@@ -734,6 +734,8 @@ next_iface:
 	if ((bytes_left > 8) || p->Next)
 		cifs_dbg(VFS, "%s: incomplete interface info\n", __func__);
 
+	ses->iface_last_update = jiffies;
+
 out:
 	/*
 	 * Go through the list again and put the inactive entries
-- 
GitLab


From d26270061ae66b915138af7cd73ca6f8b85e6b44 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 18 Jan 2024 12:31:55 -0800
Subject: [PATCH 3062/4076] string: Remove strlcpy()

With all the users of strlcpy() removed[1] from the kernel, remove the
API, self-tests, and other references. Leave mentions in Documentation
(about its deprecation), and in checkpatch.pl (to help migrate host-only
tools/ usage). Long live strscpy().

Link: https://github.com/KSPP/linux/issues/89 [1]
Cc: Azeem Shaikh <azeemshaikh38@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Joe Perches <joe@perches.com>
Cc: Dwaipayan Ray <dwaipayanray1@gmail.com>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Cc: linux-hardening@vger.kernel.org
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/fortify-string.h                | 51 -------------------
 include/linux/string.h                        |  3 --
 lib/nlattr.c                                  |  2 +-
 lib/string.c                                  | 15 ------
 lib/test_fortify/write_overflow-strlcpy-src.c |  5 --
 lib/test_fortify/write_overflow-strlcpy.c     |  5 --
 6 files changed, 1 insertion(+), 80 deletions(-)
 delete mode 100644 lib/test_fortify/write_overflow-strlcpy-src.c
 delete mode 100644 lib/test_fortify/write_overflow-strlcpy.c

diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 79ef6ac4c0211..89a6888f2f9e5 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -214,51 +214,6 @@ __kernel_size_t __fortify_strlen(const char * const POS p)
 	return ret;
 }
 
-/* Defined after fortified strlen() to reuse it. */
-extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy);
-/**
- * strlcpy - Copy a string into another string buffer
- *
- * @p: pointer to destination of copy
- * @q: pointer to NUL-terminated source string to copy
- * @size: maximum number of bytes to write at @p
- *
- * If strlen(@q) >= @size, the copy of @q will be truncated at
- * @size - 1 bytes. @p will always be NUL-terminated.
- *
- * Do not use this function. While FORTIFY_SOURCE tries to avoid
- * over-reads when calculating strlen(@q), it is still possible.
- * Prefer strscpy(), though note its different return values for
- * detecting truncation.
- *
- * Returns total number of bytes written to @p, including terminating NUL.
- *
- */
-__FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size)
-{
-	const size_t p_size = __member_size(p);
-	const size_t q_size = __member_size(q);
-	size_t q_len;	/* Full count of source string length. */
-	size_t len;	/* Count of characters going into destination. */
-
-	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
-		return __real_strlcpy(p, q, size);
-	q_len = strlen(q);
-	len = (q_len >= size) ? size - 1 : q_len;
-	if (__builtin_constant_p(size) && __builtin_constant_p(q_len) && size) {
-		/* Write size is always larger than destination. */
-		if (len >= p_size)
-			__write_overflow();
-	}
-	if (size) {
-		if (len >= p_size)
-			fortify_panic(__func__);
-		__underlying_memcpy(p, q, len);
-		p[len] = '\0';
-	}
-	return q_len;
-}
-
 /* Defined after fortified strnlen() to reuse it. */
 extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
 /**
@@ -272,12 +227,6 @@ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
  * @p buffer. The behavior is undefined if the string buffers overlap. The
  * destination @p buffer is always NUL terminated, unless it's zero-sized.
  *
- * Preferred to strlcpy() since the API doesn't require reading memory
- * from the source @q string beyond the specified @size bytes, and since
- * the return value is easier to error-check than strlcpy()'s.
- * In addition, the implementation is robust to the string changing out
- * from underneath it, unlike the current strlcpy() implementation.
- *
  * Preferred to strncpy() since it always returns a valid string, and
  * doesn't unnecessarily force the tail of the destination buffer to be
  * zero padded. If padding is desired please use strscpy_pad().
diff --git a/include/linux/string.h b/include/linux/string.h
index ce137830a0b99..ab148d8dbfc14 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -66,9 +66,6 @@ extern char * strcpy(char *,const char *);
 #ifndef __HAVE_ARCH_STRNCPY
 extern char * strncpy(char *,const char *, __kernel_size_t);
 #endif
-#ifndef __HAVE_ARCH_STRLCPY
-size_t strlcpy(char *, const char *, size_t);
-#endif
 #ifndef __HAVE_ARCH_STRSCPY
 ssize_t strscpy(char *, const char *, size_t);
 #endif
diff --git a/lib/nlattr.c b/lib/nlattr.c
index dc15e7888fc1f..ed2ab43e1b22c 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -758,7 +758,7 @@ EXPORT_SYMBOL(nla_find);
  * @dstsize: Size of destination buffer.
  *
  * Copies at most dstsize - 1 bytes into the destination buffer.
- * Unlike strlcpy the destination buffer is always padded out.
+ * Unlike strscpy() the destination buffer is always padded out.
  *
  * Return:
  * * srclen - Returns @nla length (not including the trailing %NUL).
diff --git a/lib/string.c b/lib/string.c
index be26623953d2e..6891d15ce991c 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -103,21 +103,6 @@ char *strncpy(char *dest, const char *src, size_t count)
 EXPORT_SYMBOL(strncpy);
 #endif
 
-#ifndef __HAVE_ARCH_STRLCPY
-size_t strlcpy(char *dest, const char *src, size_t size)
-{
-	size_t ret = strlen(src);
-
-	if (size) {
-		size_t len = (ret >= size) ? size - 1 : ret;
-		__builtin_memcpy(dest, src, len);
-		dest[len] = '\0';
-	}
-	return ret;
-}
-EXPORT_SYMBOL(strlcpy);
-#endif
-
 #ifndef __HAVE_ARCH_STRSCPY
 ssize_t strscpy(char *dest, const char *src, size_t count)
 {
diff --git a/lib/test_fortify/write_overflow-strlcpy-src.c b/lib/test_fortify/write_overflow-strlcpy-src.c
deleted file mode 100644
index 91bf83ebd34a5..0000000000000
--- a/lib/test_fortify/write_overflow-strlcpy-src.c
+++ /dev/null
@@ -1,5 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define TEST	\
-	strlcpy(small, large_src, sizeof(small) + 1)
-
-#include "test_fortify.h"
diff --git a/lib/test_fortify/write_overflow-strlcpy.c b/lib/test_fortify/write_overflow-strlcpy.c
deleted file mode 100644
index 1883db7c0cd67..0000000000000
--- a/lib/test_fortify/write_overflow-strlcpy.c
+++ /dev/null
@@ -1,5 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define TEST	\
-	strlcpy(instance.buf, large_src, sizeof(instance.buf) + 1)
-
-#include "test_fortify.h"
-- 
GitLab


From 68ea60a7961ca6c7c38f856572a146f66949815d Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@fujitsu.com>
Date: Fri, 19 Jan 2024 14:20:57 +0800
Subject: [PATCH 3063/4076] coccinelle: device_attr_show: Adapt to the latest
 Documentation/filesystems/sysfs.rst

Adapt description, warning message and MODE=patch according to the latest
Documentation/filesystems/sysfs.rst:
> show() should only use sysfs_emit() or sysfs_emit_at() when formatting
> the value to be returned to user space.

After this patch:
When MODE=report,
 $ make coccicheck COCCI=scripts/coccinelle/api/device_attr_show.cocci M=drivers/hid/hid-picolcd_core.c MODE=report
 <...snip...>
 drivers/hid/hid-picolcd_core.c:304:8-16: WARNING: please use sysfs_emit or sysfs_emit_at
 drivers/hid/hid-picolcd_core.c:259:9-17: WARNING: please use sysfs_emit or sysfs_emit_at

When MODE=patch,
 $ make coccicheck COCCI=scripts/coccinelle/api/device_attr_show.cocci M=drivers/hid/hid-picolcd_core.c MODE=patch
 <...snip...>
 diff -u -p a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c
 --- a/drivers/hid/hid-picolcd_core.c
 +++ b/drivers/hid/hid-picolcd_core.c
 @@ -255,10 +255,12 @@ static ssize_t picolcd_operation_mode_sh
  {
         struct picolcd_data *data = dev_get_drvdata(dev);

 -       if (data->status & PICOLCD_BOOTLOADER)
 -               return snprintf(buf, PAGE_SIZE, "[bootloader] lcd\n");
 -       else
 -               return snprintf(buf, PAGE_SIZE, "bootloader [lcd]\n");
 +       if (data->status & PICOLCD_BOOTLOADER) {
 +               return sysfs_emit(buf, "[bootloader] lcd\n");
 +       }
 +       else {
 +               return sysfs_emit(buf, "bootloader [lcd]\n");
 +       }
  }

  static ssize_t picolcd_operation_mode_store(struct device *dev,
 @@ -301,7 +303,7 @@ static ssize_t picolcd_operation_mode_de
  {
         struct picolcd_data *data = dev_get_drvdata(dev);

 -       return snprintf(buf, PAGE_SIZE, "hello world\n");
 +       return sysfs_emit(buf, "hello world\n");
  }

  static ssize_t picolcd_operation_mode_delay_store(struct device *dev,

CC: Julia Lawall <Julia.Lawall@inria.fr>
CC: Nicolas Palix <nicolas.palix@imag.fr>
CC: cocci@inria.fr
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
---
 scripts/coccinelle/api/device_attr_show.cocci | 22 +++++++++++--------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/scripts/coccinelle/api/device_attr_show.cocci b/scripts/coccinelle/api/device_attr_show.cocci
index a28dc061653aa..634514937e634 100644
--- a/scripts/coccinelle/api/device_attr_show.cocci
+++ b/scripts/coccinelle/api/device_attr_show.cocci
@@ -1,10 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 ///
 /// From Documentation/filesystems/sysfs.rst:
-///  show() must not use snprintf() when formatting the value to be
-///  returned to user space. If you can guarantee that an overflow
-///  will never happen you can use sprintf() otherwise you must use
-///  scnprintf().
+///  show() should only use sysfs_emit() or sysfs_emit_at() when formatting
+///  the value to be returned to user space.
 ///
 // Confidence: High
 // Copyright: (C) 2020 Denis Efremov ISPRAS
@@ -30,15 +28,21 @@ ssize_t show(struct device *dev, struct device_attribute *attr, char *buf)
 
 @rp depends on patch@
 identifier show, dev, attr, buf;
+expression BUF, SZ, FORMAT, STR;
 @@
 
 ssize_t show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	<...
+(
 	return
--		snprintf
-+		scnprintf
-			(...);
+-		snprintf(BUF, SZ, FORMAT, STR);
++		sysfs_emit(BUF, FORMAT, STR);
+|
+	return
+-		snprintf(BUF, SZ, STR);
++		sysfs_emit(BUF, STR);
+)
 	...>
 }
 
@@ -46,10 +50,10 @@ ssize_t show(struct device *dev, struct device_attribute *attr, char *buf)
 p << r.p;
 @@
 
-coccilib.report.print_report(p[0], "WARNING: use scnprintf or sprintf")
+coccilib.report.print_report(p[0], "WARNING: please use sysfs_emit or sysfs_emit_at")
 
 @script: python depends on org@
 p << r.p;
 @@
 
-coccilib.org.print_todo(p[0], "WARNING: use scnprintf or sprintf")
+coccilib.org.print_todo(p[0], "WARNING: please use sysfs_emit or sysfs_emit_at")
-- 
GitLab


From 2bebc3cd48701607e38e8258ab9692de9b1a718b Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Fri, 19 Jan 2024 21:47:15 +0100
Subject: [PATCH 3064/4076] Revert "firmware/sysfb: Clear screen_info state
 after consuming it"

This reverts commit df67699c9cb0ceb70f6cc60630ca938c06773eda.

Jens Axboe reported a regression that his machine is failing to show a
console, or in fact anything, on current -git. There's no output and no
console after:

Loading Linux 6.7.0+ ...
Loading initial ramdisk ...

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Jens Axboe <axboe@kernel.dk>
---
 drivers/firmware/sysfb.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
index 19706bd2642ad..82fcfd29bc4d2 100644
--- a/drivers/firmware/sysfb.c
+++ b/drivers/firmware/sysfb.c
@@ -71,7 +71,7 @@ EXPORT_SYMBOL_GPL(sysfb_disable);
 
 static __init int sysfb_init(void)
 {
-	const struct screen_info *si = &screen_info;
+	struct screen_info *si = &screen_info;
 	struct simplefb_platform_data mode;
 	const char *name;
 	bool compatible;
@@ -119,18 +119,6 @@ static __init int sysfb_init(void)
 	if (ret)
 		goto err;
 
-	/*
-	 * The firmware framebuffer is now maintained by the created
-	 * device. Disable screen_info after we've consumed it. Prevents
-	 * invalid access during kexec reboots.
-	 *
-	 * TODO: Vgacon still relies on the global screen_info. Make
-	 *       vgacon work with the platform device, so we can clear
-	 *       the screen_info unconditionally.
-	 */
-	if (strcmp(name, "platform-framebuffer"))
-		screen_info.orig_video_isVGA = 0;
-
 	goto unlock_mutex;
 err:
 	platform_device_put(pd);
-- 
GitLab


From b01f15a7571b7aa222458bc9bf26ab59bd84e384 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 17 Jan 2024 19:12:32 -0500
Subject: [PATCH 3065/4076] selftests: bonding: Increase timeout to 1200s

When tests are run by runner.sh, bond_options.sh gets killed before
it can complete:

make -C tools/testing/selftests run_tests TARGETS="drivers/net/bonding"
	[...]
	# timeout set to 120
	# selftests: drivers/net/bonding: bond_options.sh
	# TEST: prio (active-backup miimon primary_reselect 0)                [ OK ]
	# TEST: prio (active-backup miimon primary_reselect 1)                [ OK ]
	# TEST: prio (active-backup miimon primary_reselect 2)                [ OK ]
	# TEST: prio (active-backup arp_ip_target primary_reselect 0)         [ OK ]
	# TEST: prio (active-backup arp_ip_target primary_reselect 1)         [ OK ]
	# TEST: prio (active-backup arp_ip_target primary_reselect 2)         [ OK ]
	#
	not ok 7 selftests: drivers/net/bonding: bond_options.sh # TIMEOUT 120 seconds

This test includes many sleep statements, at least some of which are
related to timers in the operation of the bonding driver itself. Increase
the test timeout to allow the test to complete.

I ran the test in slightly different VMs (including one without HW
virtualization support) and got runtimes of 13m39.760s, 13m31.238s, and
13m2.956s. Use a ~1.5x "safety factor" and set the timeout to 1200s.

Fixes: 42a8d4aaea84 ("selftests: bonding: add bonding prio option test")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20240116104402.1203850a@kernel.org/#t
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20240118001233.304759-1-bpoirier@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/bonding/settings | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings
index 6091b45d226ba..79b65bdf05db6 100644
--- a/tools/testing/selftests/drivers/net/bonding/settings
+++ b/tools/testing/selftests/drivers/net/bonding/settings
@@ -1 +1 @@
-timeout=120
+timeout=1200
-- 
GitLab


From 198bc90e0e734e5f98c3d2833e8390cac3df61b2 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Thu, 18 Jan 2024 09:20:19 +0800
Subject: [PATCH 3066/4076] tcp: make sure init the accept_queue's spinlocks
 once

When I run syz's reproduction C program locally, it causes the following
issue:
pvqspinlock: lock 0xffff9d181cd5c660 has corrupted value 0x0!
WARNING: CPU: 19 PID: 21160 at __pv_queued_spin_unlock_slowpath (kernel/locking/qspinlock_paravirt.h:508)
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
RIP: 0010:__pv_queued_spin_unlock_slowpath (kernel/locking/qspinlock_paravirt.h:508)
Code: 73 56 3a ff 90 c3 cc cc cc cc 8b 05 bb 1f 48 01 85 c0 74 05 c3 cc cc cc cc 8b 17 48 89 fe 48 c7 c7
30 20 ce 8f e8 ad 56 42 ff <0f> 0b c3 cc cc cc cc 0f 0b 0f 1f 40 00 90 90 90 90 90 90 90 90 90
RSP: 0018:ffffa8d200604cb8 EFLAGS: 00010282
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff9d1ef60e0908
RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff9d1ef60e0900
RBP: ffff9d181cd5c280 R08: 0000000000000000 R09: 00000000ffff7fff
R10: ffffa8d200604b68 R11: ffffffff907dcdc8 R12: 0000000000000000
R13: ffff9d181cd5c660 R14: ffff9d1813a3f330 R15: 0000000000001000
FS:  00007fa110184640(0000) GS:ffff9d1ef60c0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000000 CR3: 000000011f65e000 CR4: 00000000000006f0
Call Trace:
<IRQ>
  _raw_spin_unlock (kernel/locking/spinlock.c:186)
  inet_csk_reqsk_queue_add (net/ipv4/inet_connection_sock.c:1321)
  inet_csk_complete_hashdance (net/ipv4/inet_connection_sock.c:1358)
  tcp_check_req (net/ipv4/tcp_minisocks.c:868)
  tcp_v4_rcv (net/ipv4/tcp_ipv4.c:2260)
  ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205)
  ip_local_deliver_finish (net/ipv4/ip_input.c:234)
  __netif_receive_skb_one_core (net/core/dev.c:5529)
  process_backlog (./include/linux/rcupdate.h:779)
  __napi_poll (net/core/dev.c:6533)
  net_rx_action (net/core/dev.c:6604)
  __do_softirq (./arch/x86/include/asm/jump_label.h:27)
  do_softirq (kernel/softirq.c:454 kernel/softirq.c:441)
</IRQ>
<TASK>
  __local_bh_enable_ip (kernel/softirq.c:381)
  __dev_queue_xmit (net/core/dev.c:4374)
  ip_finish_output2 (./include/net/neighbour.h:540 net/ipv4/ip_output.c:235)
  __ip_queue_xmit (net/ipv4/ip_output.c:535)
  __tcp_transmit_skb (net/ipv4/tcp_output.c:1462)
  tcp_rcv_synsent_state_process (net/ipv4/tcp_input.c:6469)
  tcp_rcv_state_process (net/ipv4/tcp_input.c:6657)
  tcp_v4_do_rcv (net/ipv4/tcp_ipv4.c:1929)
  __release_sock (./include/net/sock.h:1121 net/core/sock.c:2968)
  release_sock (net/core/sock.c:3536)
  inet_wait_for_connect (net/ipv4/af_inet.c:609)
  __inet_stream_connect (net/ipv4/af_inet.c:702)
  inet_stream_connect (net/ipv4/af_inet.c:748)
  __sys_connect (./include/linux/file.h:45 net/socket.c:2064)
  __x64_sys_connect (net/socket.c:2073 net/socket.c:2070 net/socket.c:2070)
  do_syscall_64 (arch/x86/entry/common.c:51 arch/x86/entry/common.c:82)
  entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129)
  RIP: 0033:0x7fa10ff05a3d
  Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89
  c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ab a3 0e 00 f7 d8 64 89 01 48
  RSP: 002b:00007fa110183de8 EFLAGS: 00000202 ORIG_RAX: 000000000000002a
  RAX: ffffffffffffffda RBX: 0000000020000054 RCX: 00007fa10ff05a3d
  RDX: 000000000000001c RSI: 0000000020000040 RDI: 0000000000000003
  RBP: 00007fa110183e20 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000202 R12: 00007fa110184640
  R13: 0000000000000000 R14: 00007fa10fe8b060 R15: 00007fff73e23b20
</TASK>

The issue triggering process is analyzed as follows:
Thread A                                       Thread B
tcp_v4_rcv	//receive ack TCP packet       inet_shutdown
  tcp_check_req                                  tcp_disconnect //disconnect sock
  ...                                              tcp_set_state(sk, TCP_CLOSE)
    inet_csk_complete_hashdance                ...
      inet_csk_reqsk_queue_add                 inet_listen  //start listen
        spin_lock(&queue->rskq_lock)             inet_csk_listen_start
        ...                                        reqsk_queue_alloc
        ...                                          spin_lock_init
        spin_unlock(&queue->rskq_lock)	//warning

When the socket receives the ACK packet during the three-way handshake,
it will hold spinlock. And then the user actively shutdowns the socket
and listens to the socket immediately, the spinlock will be initialized.
When the socket is going to release the spinlock, a warning is generated.
Also the same issue to fastopenq.lock.

Move init spinlock to inet_create and inet_accept to make sure init the
accept_queue's spinlocks once.

Fixes: fff1f3001cc5 ("tcp: add a spinlock to protect struct request_sock_queue")
Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path")
Reported-by: Ming Shu <sming56@aliyun.com>
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240118012019.1751966-1-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_connection_sock.h | 8 ++++++++
 net/core/request_sock.c            | 3 ---
 net/ipv4/af_inet.c                 | 3 +++
 net/ipv4/inet_connection_sock.c    | 4 ++++
 4 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index d0a2f827d5f20..9ab4bf704e864 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -357,4 +357,12 @@ static inline bool inet_csk_has_ulp(const struct sock *sk)
 	return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops;
 }
 
+static inline void inet_init_csk_locks(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	spin_lock_init(&icsk->icsk_accept_queue.rskq_lock);
+	spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock);
+}
+
 #endif /* _INET_CONNECTION_SOCK_H */
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index f35c2e9984062..63de5c635842b 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -33,9 +33,6 @@
 
 void reqsk_queue_alloc(struct request_sock_queue *queue)
 {
-	spin_lock_init(&queue->rskq_lock);
-
-	spin_lock_init(&queue->fastopenq.lock);
 	queue->fastopenq.rskq_rst_head = NULL;
 	queue->fastopenq.rskq_rst_tail = NULL;
 	queue->fastopenq.qlen = 0;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 835f4f9d98d25..4e635dd3d3c8c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -330,6 +330,9 @@ lookup_protocol:
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
+	if (INET_PROTOSW_ICSK & answer_flags)
+		inet_init_csk_locks(sk);
+
 	inet = inet_sk(sk);
 	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8e2eb1793685e..459af1f897395 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -727,6 +727,10 @@ out:
 	}
 	if (req)
 		reqsk_put(req);
+
+	if (newsk)
+		inet_init_csk_locks(newsk);
+
 	return newsk;
 out_err:
 	newsk = NULL;
-- 
GitLab


From 3c1069fa42872f95cf3c6fedf80723d391e12d57 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 17 Jan 2024 15:45:11 -0800
Subject: [PATCH 3067/4076] bnxt_en: Wait for FLR to complete during probe

The first message to firmware may fail if the device is undergoing FLR.
The driver has some recovery logic for this failure scenario but we must
wait 100 msec for FLR to complete before proceeding.  Otherwise the
recovery will always fail.

Fixes: ba02629ff6cb ("bnxt_en: log firmware status on firmware init failure")
Reviewed-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20240117234515.226944-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0aacd3c6ed5c0..0866aba35d9b3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13232,6 +13232,11 @@ static int bnxt_fw_init_one_p1(struct bnxt *bp)
 
 	bp->fw_cap = 0;
 	rc = bnxt_hwrm_ver_get(bp);
+	/* FW may be unresponsive after FLR. FLR must complete within 100 msec
+	 * so wait before continuing with recovery.
+	 */
+	if (rc)
+		msleep(100);
 	bnxt_try_map_fw_health_reg(bp);
 	if (rc) {
 		rc = bnxt_try_recover_fw(bp);
-- 
GitLab


From 2ad8e57338ac7b1e149d458669a95132e2460096 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 17 Jan 2024 15:45:12 -0800
Subject: [PATCH 3068/4076] bnxt_en: Fix memory leak in bnxt_hwrm_get_rings()

bnxt_hwrm_get_rings() can abort and return error when there are not
enough ring resources.  It aborts without releasing the HWRM DMA buffer,
causing a dma_pool_destroy warning when the driver is unloaded:

bnxt_en 0000:99:00.0: dma_pool_destroy bnxt_hwrm, 000000005b089ba8 busy

Fixes: f1e50b276d37 ("bnxt_en: Fix trimming of P5 RX and TX rings")
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20240117234515.226944-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0866aba35d9b3..9fdc90bfce383 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6926,7 +6926,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 			if (cp < (rx + tx)) {
 				rc = __bnxt_trim_rings(bp, &rx, &tx, cp, false);
 				if (rc)
-					return rc;
+					goto get_rings_exit;
 				if (bp->flags & BNXT_FLAG_AGG_RINGS)
 					rx <<= 1;
 				hw_resc->resv_rx_rings = rx;
@@ -6938,8 +6938,9 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 		hw_resc->resv_cp_rings = cp;
 		hw_resc->resv_stat_ctxs = stats;
 	}
+get_rings_exit:
 	hwrm_req_drop(bp, req);
-	return 0;
+	return rc;
 }
 
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings)
-- 
GitLab


From 523384a6aa095d3f3d9ee8b1a4e289d4311cd2d9 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 17 Jan 2024 15:45:13 -0800
Subject: [PATCH 3069/4076] bnxt_en: Fix RSS table entries calculation for
 P5_PLUS chips

The existing formula used in the driver to calculate the number of RSS
table entries is to round up the number of RX rings to the next integer
multiples of 64 (e.g. 64, 128, 192, ..).  This is incorrect.  The valid
values supported by the chip are 64, 128, 256, 512 only (power of 2
starting from 64).  When the number of RX rings is greater than 128, the
entry size will likely be wrong.  Firmware will round down the invalid
value (e.g. 192 rounded down to 128) provided by the driver, causing some
RSS rings to not receive any packets.

We already have an existing function bnxt_calc_nr_ring_pages() to
do this calculation.  Use it in bnxt_get_nr_rss_ctxs() to calculate the
number of RSS contexts correctly for P5_PLUS chips.

Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Fixes: 7b3af4f75b81 ("bnxt_en: Add RSS support for 57500 chips.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20240117234515.226944-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       | 17 ++++++++++++-----
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c   |  3 ++-
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9fdc90bfce383..3d090d4403df7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5935,8 +5935,12 @@ static u16 bnxt_get_max_rss_ring(struct bnxt *bp)
 
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-		return DIV_ROUND_UP(rx_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		if (!rx_rings)
+			return 0;
+		return bnxt_calc_nr_ring_pages(rx_rings - 1,
+					       BNXT_RSS_TABLE_ENTRIES_P5);
+	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return 2;
 	return 1;
@@ -7001,10 +7005,11 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 
 		req->num_rx_rings = cpu_to_le16(rx_rings);
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+			u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
 			req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
 			req->num_msix = cpu_to_le16(cp_rings);
-			req->num_rsscos_ctxs =
-				cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+			req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
 		} else {
 			req->num_cmpl_rings = cpu_to_le16(cp_rings);
 			req->num_hw_ring_grps = cpu_to_le16(ring_grps);
@@ -7051,8 +7056,10 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	req->num_rx_rings = cpu_to_le16(rx_rings);
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
 		req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
-		req->num_rsscos_ctxs = cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+		req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
 	} else {
 		req->num_cmpl_rings = cpu_to_le16(cp_rings);
 		req->num_hw_ring_grps = cpu_to_le16(ring_grps);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 27b983c0a8a9c..1f6e0cd84f2e8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1574,7 +1574,8 @@ u32 bnxt_get_rxfh_indir_size(struct net_device *dev)
 	struct bnxt *bp = netdev_priv(dev);
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-		return ALIGN(bp->rx_nr_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+		return bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) *
+		       BNXT_RSS_TABLE_ENTRIES_P5;
 	return HW_HASH_INDEX_SIZE;
 }
 
-- 
GitLab


From c20f482129a582455f02eb9a6dcb2a4215274599 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 17 Jan 2024 15:45:14 -0800
Subject: [PATCH 3070/4076] bnxt_en: Prevent kernel warning when running
 offline self test

We call bnxt_half_open_nic() to setup the chip partially to run
loopback tests.  The rings and buffers are initialized normally
so that we can transmit and receive packets in loopback mode.
That means page pool buffers are allocated for the aggregation ring
just like the normal case.  NAPI is not needed because we are just
polling for the loopback packets.

When we're done with the loopback tests, we call bnxt_half_close_nic()
to clean up.  When freeing the page pools, we hit a WARN_ON()
in page_pool_unlink_napi() because the NAPI state linked to the
page pool is uninitialized.

The simplest way to avoid this warning is just to initialize the
NAPIs during half open and delete the NAPIs during half close.
Trying to skip the page pool initialization or skip linking of
NAPI during half open will be more complicated.

This fix avoids this warning:

WARNING: CPU: 4 PID: 46967 at net/core/page_pool.c:946 page_pool_unlink_napi+0x1f/0x30
CPU: 4 PID: 46967 Comm: ethtool Tainted: G S      W          6.7.0-rc5+ #22
Hardware name: Dell Inc. PowerEdge R750/06V45N, BIOS 1.3.8 08/31/2021
RIP: 0010:page_pool_unlink_napi+0x1f/0x30
Code: 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 48 8b 47 18 48 85 c0 74 1b 48 8b 50 10 83 e2 01 74 08 8b 40 34 83 f8 ff 74 02 <0f> 0b 48 c7 47 18 00 00 00 00 c3 cc cc cc cc 66 90 90 90 90 90 90
RSP: 0018:ffa000003d0dfbe8 EFLAGS: 00010246
RAX: ff110003607ce640 RBX: ff110010baf5d000 RCX: 0000000000000008
RDX: 0000000000000000 RSI: ff110001e5e522c0 RDI: ff110010baf5d000
RBP: ff11000145539b40 R08: 0000000000000001 R09: ffffffffc063f641
R10: ff110001361eddb8 R11: 000000000040000f R12: 0000000000000001
R13: 000000000000001c R14: ff1100014553a080 R15: 0000000000003fc0
FS:  00007f9301c4f740(0000) GS:ff1100103fd00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f91344fa8f0 CR3: 00000003527cc005 CR4: 0000000000771ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <TASK>
 ? __warn+0x81/0x140
 ? page_pool_unlink_napi+0x1f/0x30
 ? report_bug+0x102/0x200
 ? handle_bug+0x44/0x70
 ? exc_invalid_op+0x13/0x60
 ? asm_exc_invalid_op+0x16/0x20
 ? bnxt_free_ring.isra.123+0xb1/0xd0 [bnxt_en]
 ? page_pool_unlink_napi+0x1f/0x30
 page_pool_destroy+0x3e/0x150
 bnxt_free_mem+0x441/0x5e0 [bnxt_en]
 bnxt_half_close_nic+0x2a/0x40 [bnxt_en]
 bnxt_self_test+0x21d/0x450 [bnxt_en]
 __dev_ethtool+0xeda/0x2e30
 ? native_queued_spin_lock_slowpath+0x17f/0x2b0
 ? __link_object+0xa1/0x160
 ? _raw_spin_unlock_irqrestore+0x23/0x40
 ? __create_object+0x5f/0x90
 ? __kmem_cache_alloc_node+0x317/0x3c0
 ? dev_ethtool+0x59/0x170
 dev_ethtool+0xa7/0x170
 dev_ioctl+0xc3/0x530
 sock_do_ioctl+0xa8/0xf0
 sock_ioctl+0x270/0x310
 __x64_sys_ioctl+0x8c/0xc0
 do_syscall_64+0x3e/0xf0
 entry_SYSCALL_64_after_hwframe+0x6e/0x76

Fixes: 294e39e0d034 ("bnxt: hook NAPIs to page pools")
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20240117234515.226944-5-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 3d090d4403df7..0f5004872a468 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11572,10 +11572,12 @@ int bnxt_half_open_nic(struct bnxt *bp)
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
 		goto half_open_err;
 	}
+	bnxt_init_napi(bp);
 	set_bit(BNXT_STATE_HALF_OPEN, &bp->state);
 	rc = bnxt_init_nic(bp, true);
 	if (rc) {
 		clear_bit(BNXT_STATE_HALF_OPEN, &bp->state);
+		bnxt_del_napi(bp);
 		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
 		goto half_open_err;
 	}
@@ -11594,6 +11596,7 @@ half_open_err:
 void bnxt_half_close_nic(struct bnxt *bp)
 {
 	bnxt_hwrm_resource_free(bp, false, true);
+	bnxt_del_napi(bp);
 	bnxt_free_skbs(bp);
 	bnxt_free_mem(bp, true);
 	clear_bit(BNXT_STATE_HALF_OPEN, &bp->state);
-- 
GitLab


From 467739baf63646d4a5033f7f8a9306669ea55326 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 17 Jan 2024 15:45:15 -0800
Subject: [PATCH 3071/4076] bnxt_en: Fix possible crash after creating sw
 mqprio TCs

The driver relies on netdev_get_num_tc() to get the number of HW
offloaded mqprio TCs to allocate and free TX rings.  This won't
work and can potentially crash the system if software mqprio or
taprio TCs have been setup.  netdev_get_num_tc() will return the
number of software TCs and it may cause the driver to allocate or
free more TX rings that it should.  Fix it by adding a bp->num_tc
field to store the number of HW offload mqprio TCs for the device.
Use bp->num_tc instead of netdev_get_num_tc().

This fixes a crash like this:

BUG: kernel NULL pointer dereference, address: 0000000000000000
PGD 42b8404067 P4D 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 120 PID: 8661 Comm: ifconfig Kdump: loaded Tainted: G           OE     5.18.16 #1
Hardware name: Lenovo ThinkSystem SR650 V3/SB27A92818, BIOS ESE114N-2.12 04/25/2023
RIP: 0010:bnxt_hwrm_cp_ring_alloc_p5+0x10/0x90 [bnxt_en]
Code: 41 5c 41 5d 41 5e c3 cc cc cc cc 41 8b 44 24 08 66 89 03 eb c6 e8 b0 f1 7d db 0f 1f 44 00 00 41 56 41 55 41 54 55 48 89 fd 53 <48> 8b 06 48 89 f3 48 81 c6 28 01 00 00 0f b6 96 13 ff ff ff 44 8b
RSP: 0018:ff65907660d1fa88 EFLAGS: 00010202
RAX: 0000000000000010 RBX: ff4dde1d907e4980 RCX: f400000000000000
RDX: 0000000000000010 RSI: 0000000000000000 RDI: ff4dde1d907e4980
RBP: ff4dde1d907e4980 R08: 000000000000000f R09: 0000000000000000
R10: ff4dde5f02671800 R11: 0000000000000008 R12: 0000000088888889
R13: 0500000000000000 R14: 00f0000000000000 R15: ff4dde5f02671800
FS:  00007f4b126b5740(0000) GS:ff4dde9bff600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 000000416f9c6002 CR4: 0000000000771ee0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <TASK>
 bnxt_hwrm_ring_alloc+0x204/0x770 [bnxt_en]
 bnxt_init_chip+0x4d/0x680 [bnxt_en]
 ? bnxt_poll+0x1a0/0x1a0 [bnxt_en]
 __bnxt_open_nic+0xd2/0x740 [bnxt_en]
 bnxt_open+0x10b/0x220 [bnxt_en]
 ? raw_notifier_call_chain+0x41/0x60
 __dev_open+0xf3/0x1b0
 __dev_change_flags+0x1db/0x250
 dev_change_flags+0x21/0x60
 devinet_ioctl+0x590/0x720
 ? avc_has_extended_perms+0x1b7/0x420
 ? _copy_from_user+0x3a/0x60
 inet_ioctl+0x189/0x1c0
 ? wp_page_copy+0x45a/0x6e0
 sock_do_ioctl+0x42/0xf0
 ? ioctl_has_perm.constprop.0.isra.0+0xbd/0x120
 sock_ioctl+0x1ce/0x2e0
 __x64_sys_ioctl+0x87/0xc0
 do_syscall_64+0x59/0x90
 ? syscall_exit_work+0x103/0x130
 ? syscall_exit_to_user_mode+0x12/0x30
 ? do_syscall_64+0x69/0x90
 ? exc_page_fault+0x62/0x150

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Reviewed-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20240117234515.226944-6-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 19 ++++++++++++-------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c |  2 +-
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c |  4 ++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c |  2 +-
 5 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0f5004872a468..39845d556bafc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3817,7 +3817,7 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 {
 	bool sh = !!(bp->flags & BNXT_FLAG_SHARED_RINGS);
 	int i, j, rc, ulp_base_vec, ulp_msix;
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	if (!tcs)
 		tcs = 1;
@@ -9946,7 +9946,7 @@ static int __bnxt_num_tx_to_cp(struct bnxt *bp, int tx, int tx_sets, int tx_xdp)
 
 int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	if (!tcs)
 		tcs = 1;
@@ -9955,7 +9955,7 @@ int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
 
 static int bnxt_num_cp_to_tx(struct bnxt *bp, int tx_cp)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	return (tx_cp - bp->tx_nr_rings_xdp) * tcs +
 	       bp->tx_nr_rings_xdp;
@@ -9985,7 +9985,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
 	struct net_device *dev = bp->dev;
 	int tcs, i;
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 	if (tcs) {
 		int i, off, count;
 
@@ -10017,8 +10017,10 @@ static void bnxt_setup_inta(struct bnxt *bp)
 {
 	const int len = sizeof(bp->irq_tbl[0].name);
 
-	if (netdev_get_num_tc(bp->dev))
+	if (bp->num_tc) {
 		netdev_reset_tc(bp->dev);
+		bp->num_tc = 0;
+	}
 
 	snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx",
 		 0);
@@ -10244,8 +10246,8 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
 
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
 	bool irq_cleared = false;
+	int tcs = bp->num_tc;
 	int rc;
 
 	if (!bnxt_need_reserve_rings(bp))
@@ -10271,6 +10273,7 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 		    bp->tx_nr_rings - bp->tx_nr_rings_xdp)) {
 		netdev_err(bp->dev, "tx ring reservation failure\n");
 		netdev_reset_tc(bp->dev);
+		bp->num_tc = 0;
 		if (bp->tx_nr_rings_xdp)
 			bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp;
 		else
@@ -13800,7 +13803,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 		return -EINVAL;
 	}
 
-	if (netdev_get_num_tc(dev) == tc)
+	if (bp->num_tc == tc)
 		return 0;
 
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
@@ -13818,9 +13821,11 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	if (tc) {
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc;
 		netdev_set_num_tc(dev, tc);
+		bp->num_tc = tc;
 	} else {
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
 		netdev_reset_tc(dev);
+		bp->num_tc = 0;
 	}
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
 	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index b8ef1717cb65f..47338b48ca203 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2225,6 +2225,7 @@ struct bnxt {
 	u8			tc_to_qidx[BNXT_MAX_QUEUE];
 	u8			q_ids[BNXT_MAX_QUEUE];
 	u8			max_q;
+	u8			num_tc;
 
 	unsigned int		current_interval;
 #define BNXT_TIMER_INTERVAL	HZ
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 63e0670383852..0dbb880a7aa0e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -228,7 +228,7 @@ static int bnxt_queue_remap(struct bnxt *bp, unsigned int lltc_mask)
 		}
 	}
 	if (bp->ieee_ets) {
-		int tc = netdev_get_num_tc(bp->dev);
+		int tc = bp->num_tc;
 
 		if (!tc)
 			tc = 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1f6e0cd84f2e8..dc4ca706b0e29 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -884,7 +884,7 @@ static void bnxt_get_channels(struct net_device *dev,
 	if (max_tx_sch_inputs)
 		max_tx_rings = min_t(int, max_tx_rings, max_tx_sch_inputs);
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 	tx_grps = max(tcs, 1);
 	if (bp->tx_nr_rings_xdp)
 		tx_grps++;
@@ -944,7 +944,7 @@ static int bnxt_set_channels(struct net_device *dev,
 	if (channel->combined_count)
 		sh = true;
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 
 	req_tx_rings = sh ? channel->combined_count : channel->tx_count;
 	req_rx_rings = sh ? channel->combined_count : channel->rx_count;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index c2b25fc623ecc..4079538bc310e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -407,7 +407,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	if (prog)
 		tx_xdp = bp->rx_nr_rings;
 
-	tc = netdev_get_num_tc(dev);
+	tc = bp->num_tc;
 	if (!tc)
 		tc = 1;
 	rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
-- 
GitLab


From 6c21660fe221a15c789dee2bc2fd95516bc5aeaf Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Thu, 18 Jan 2024 21:03:06 +0800
Subject: [PATCH 3072/4076] vlan: skip nested type that is not
 IFLA_VLAN_QOS_MAPPING

In the vlan_changelink function, a loop is used to parse the nested
attributes IFLA_VLAN_EGRESS_QOS and IFLA_VLAN_INGRESS_QOS in order to
obtain the struct ifla_vlan_qos_mapping. These two nested attributes are
checked in the vlan_validate_qos_map function, which calls
nla_validate_nested_deprecated with the vlan_map_policy.

However, this deprecated validator applies a LIBERAL strictness, allowing
the presence of an attribute with the type IFLA_VLAN_QOS_UNSPEC.
Consequently, the loop in vlan_changelink may parse an attribute of type
IFLA_VLAN_QOS_UNSPEC and believe it carries a payload of
struct ifla_vlan_qos_mapping, which is not necessarily true.

To address this issue and ensure compatibility, this patch introduces two
type checks that skip attributes whose type is not IFLA_VLAN_QOS_MAPPING.

Fixes: 07b5b17e157b ("[VLAN]: Use rtnl_link API")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240118130306.1644001-1-linma@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/8021q/vlan_netlink.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 214532173536b..a3b68243fd4b1 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -118,12 +118,16 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	}
 	if (data[IFLA_VLAN_INGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) {
+			if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING)
+				continue;
 			m = nla_data(attr);
 			vlan_dev_set_ingress_priority(dev, m->to, m->from);
 		}
 	}
 	if (data[IFLA_VLAN_EGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) {
+			if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING)
+				continue;
 			m = nla_data(attr);
 			err = vlan_dev_set_egress_priority(dev, m->from, m->to);
 			if (err)
-- 
GitLab


From dad555c816a50c6a6a8a86be1f9177673918c647 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 18 Jan 2024 18:36:25 +0000
Subject: [PATCH 3073/4076] llc: make llc_ui_sendmsg() more robust against
 bonding changes

syzbot was able to trick llc_ui_sendmsg(), allocating an skb with no
headroom, but subsequently trying to push 14 bytes of Ethernet header [1]

Like some others, llc_ui_sendmsg() releases the socket lock before
calling sock_alloc_send_skb().
Then it acquires it again, but does not redo all the sanity checks
that were performed.

This fix:

- Uses LL_RESERVED_SPACE() to reserve space.
- Check all conditions again after socket lock is held again.
- Do not account Ethernet header for mtu limitation.

[1]

skbuff: skb_under_panic: text:ffff800088baa334 len:1514 put:14 head:ffff0000c9c37000 data:ffff0000c9c36ff2 tail:0x5dc end:0x6c0 dev:bond0

 kernel BUG at net/core/skbuff.c:193 !
Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
Modules linked in:
CPU: 0 PID: 6875 Comm: syz-executor.0 Not tainted 6.7.0-rc8-syzkaller-00101-g0802e17d9aca-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : skb_panic net/core/skbuff.c:189 [inline]
 pc : skb_under_panic+0x13c/0x140 net/core/skbuff.c:203
 lr : skb_panic net/core/skbuff.c:189 [inline]
 lr : skb_under_panic+0x13c/0x140 net/core/skbuff.c:203
sp : ffff800096f97000
x29: ffff800096f97010 x28: ffff80008cc8d668 x27: dfff800000000000
x26: ffff0000cb970c90 x25: 00000000000005dc x24: ffff0000c9c36ff2
x23: ffff0000c9c37000 x22: 00000000000005ea x21: 00000000000006c0
x20: 000000000000000e x19: ffff800088baa334 x18: 1fffe000368261ce
x17: ffff80008e4ed000 x16: ffff80008a8310f8 x15: 0000000000000001
x14: 1ffff00012df2d58 x13: 0000000000000000 x12: 0000000000000000
x11: 0000000000000001 x10: 0000000000ff0100 x9 : e28a51f1087e8400
x8 : e28a51f1087e8400 x7 : ffff80008028f8d0 x6 : 0000000000000000
x5 : 0000000000000001 x4 : 0000000000000001 x3 : ffff800082b78714
x2 : 0000000000000001 x1 : 0000000100000000 x0 : 0000000000000089
Call trace:
  skb_panic net/core/skbuff.c:189 [inline]
  skb_under_panic+0x13c/0x140 net/core/skbuff.c:203
  skb_push+0xf0/0x108 net/core/skbuff.c:2451
  eth_header+0x44/0x1f8 net/ethernet/eth.c:83
  dev_hard_header include/linux/netdevice.h:3188 [inline]
  llc_mac_hdr_init+0x110/0x17c net/llc/llc_output.c:33
  llc_sap_action_send_xid_c+0x170/0x344 net/llc/llc_s_ac.c:85
  llc_exec_sap_trans_actions net/llc/llc_sap.c:153 [inline]
  llc_sap_next_state net/llc/llc_sap.c:182 [inline]
  llc_sap_state_process+0x1ec/0x774 net/llc/llc_sap.c:209
  llc_build_and_send_xid_pkt+0x12c/0x1c0 net/llc/llc_sap.c:270
  llc_ui_sendmsg+0x7bc/0xb1c net/llc/af_llc.c:997
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg net/socket.c:745 [inline]
  sock_sendmsg+0x194/0x274 net/socket.c:767
  splice_to_socket+0x7cc/0xd58 fs/splice.c:881
  do_splice_from fs/splice.c:933 [inline]
  direct_splice_actor+0xe4/0x1c0 fs/splice.c:1142
  splice_direct_to_actor+0x2a0/0x7e4 fs/splice.c:1088
  do_splice_direct+0x20c/0x348 fs/splice.c:1194
  do_sendfile+0x4bc/0xc70 fs/read_write.c:1254
  __do_sys_sendfile64 fs/read_write.c:1322 [inline]
  __se_sys_sendfile64 fs/read_write.c:1308 [inline]
  __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1308
  __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline]
  invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51
  el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136
  do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155
  el0_svc+0x54/0x158 arch/arm64/kernel/entry-common.c:678
  el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:696
  el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:595
Code: aa1803e6 aa1903e7 a90023f5 94792f6a (d4210000)

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-and-tested-by: syzbot+2a7024e9502df538e8ef@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240118183625.4007013-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/llc/af_llc.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 9b06c380866b5..20551cfb7da6d 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -928,14 +928,15 @@ copy_uaddr:
  */
 static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
+	DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
-	DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
 	int flags = msg->msg_flags;
 	int noblock = flags & MSG_DONTWAIT;
+	int rc = -EINVAL, copied = 0, hdrlen, hh_len;
 	struct sk_buff *skb = NULL;
+	struct net_device *dev;
 	size_t size = 0;
-	int rc = -EINVAL, copied = 0, hdrlen;
 
 	dprintk("%s: sending from %02X to %02X\n", __func__,
 		llc->laddr.lsap, llc->daddr.lsap);
@@ -955,22 +956,29 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		if (rc)
 			goto out;
 	}
-	hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr);
+	dev = llc->dev;
+	hh_len = LL_RESERVED_SPACE(dev);
+	hdrlen = llc_ui_header_len(sk, addr);
 	size = hdrlen + len;
-	if (size > llc->dev->mtu)
-		size = llc->dev->mtu;
+	size = min_t(size_t, size, READ_ONCE(dev->mtu));
 	copied = size - hdrlen;
 	rc = -EINVAL;
 	if (copied < 0)
 		goto out;
 	release_sock(sk);
-	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
+	skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc);
 	lock_sock(sk);
 	if (!skb)
 		goto out;
-	skb->dev      = llc->dev;
+	if (sock_flag(sk, SOCK_ZAPPED) ||
+	    llc->dev != dev ||
+	    hdrlen != llc_ui_header_len(sk, addr) ||
+	    hh_len != LL_RESERVED_SPACE(dev) ||
+	    size > READ_ONCE(dev->mtu))
+		goto out;
+	skb->dev      = dev;
 	skb->protocol = llc_proto_type(addr->sllc_arphrd);
-	skb_reserve(skb, hdrlen);
+	skb_reserve(skb, hh_len + hdrlen);
 	rc = memcpy_from_msg(skb_put(skb, copied), msg, copied);
 	if (rc)
 		goto out;
-- 
GitLab


From e3f9bed9bee261e3347131764e42aeedf1ffea61 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 18 Jan 2024 17:55:15 -0800
Subject: [PATCH 3074/4076] llc: Drop support for ETH_P_TR_802_2.

syzbot reported an uninit-value bug below. [0]

llc supports ETH_P_802_2 (0x0004) and used to support ETH_P_TR_802_2
(0x0011), and syzbot abused the latter to trigger the bug.

  write$tun(r0, &(0x7f0000000040)={@val={0x0, 0x11}, @val, @mpls={[], @llc={@snap={0xaa, 0x1, ')', "90e5dd"}}}}, 0x16)

llc_conn_handler() initialises local variables {saddr,daddr}.mac
based on skb in llc_pdu_decode_sa()/llc_pdu_decode_da() and passes
them to __llc_lookup().

However, the initialisation is done only when skb->protocol is
htons(ETH_P_802_2), otherwise, __llc_lookup_established() and
__llc_lookup_listener() will read garbage.

The missing initialisation existed prior to commit 211ed865108e
("net: delete all instances of special processing for token ring").

It removed the part to kick out the token ring stuff but forgot to
close the door allowing ETH_P_TR_802_2 packets to sneak into llc_rcv().

Let's remove llc_tr_packet_type and complete the deprecation.

[0]:
BUG: KMSAN: uninit-value in __llc_lookup_established+0xe9d/0xf90
 __llc_lookup_established+0xe9d/0xf90
 __llc_lookup net/llc/llc_conn.c:611 [inline]
 llc_conn_handler+0x4bd/0x1360 net/llc/llc_conn.c:791
 llc_rcv+0xfbb/0x14a0 net/llc/llc_input.c:206
 __netif_receive_skb_one_core net/core/dev.c:5527 [inline]
 __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5641
 netif_receive_skb_internal net/core/dev.c:5727 [inline]
 netif_receive_skb+0x58/0x660 net/core/dev.c:5786
 tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1555
 tun_get_user+0x53af/0x66d0 drivers/net/tun.c:2002
 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048
 call_write_iter include/linux/fs.h:2020 [inline]
 new_sync_write fs/read_write.c:491 [inline]
 vfs_write+0x8ef/0x1490 fs/read_write.c:584
 ksys_write+0x20f/0x4c0 fs/read_write.c:637
 __do_sys_write fs/read_write.c:649 [inline]
 __se_sys_write fs/read_write.c:646 [inline]
 __x64_sys_write+0x93/0xd0 fs/read_write.c:646
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:82
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Local variable daddr created at:
 llc_conn_handler+0x53/0x1360 net/llc/llc_conn.c:783
 llc_rcv+0xfbb/0x14a0 net/llc/llc_input.c:206

CPU: 1 PID: 5004 Comm: syz-executor994 Not tainted 6.6.0-syzkaller-14500-g1c41041124bd #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/09/2023

Fixes: 211ed865108e ("net: delete all instances of special processing for token ring")
Reported-by: syzbot+b5ad66046b913bc04c6f@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=b5ad66046b913bc04c6f
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240119015515.61898-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/llc_pdu.h | 6 ++----
 net/llc/llc_core.c    | 7 -------
 2 files changed, 2 insertions(+), 11 deletions(-)

diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h
index 7e73f8e5e4970..1d55ba7c45be1 100644
--- a/include/net/llc_pdu.h
+++ b/include/net/llc_pdu.h
@@ -262,8 +262,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type,
  */
 static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa)
 {
-	if (skb->protocol == htons(ETH_P_802_2))
-		memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN);
+	memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN);
 }
 
 /**
@@ -275,8 +274,7 @@ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa)
  */
 static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da)
 {
-	if (skb->protocol == htons(ETH_P_802_2))
-		memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN);
+	memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN);
 }
 
 /**
diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c
index 6e387aadffcec..4f16d9c88350b 100644
--- a/net/llc/llc_core.c
+++ b/net/llc/llc_core.c
@@ -135,22 +135,15 @@ static struct packet_type llc_packet_type __read_mostly = {
 	.func = llc_rcv,
 };
 
-static struct packet_type llc_tr_packet_type __read_mostly = {
-	.type = cpu_to_be16(ETH_P_TR_802_2),
-	.func = llc_rcv,
-};
-
 static int __init llc_init(void)
 {
 	dev_add_pack(&llc_packet_type);
-	dev_add_pack(&llc_tr_packet_type);
 	return 0;
 }
 
 static void __exit llc_exit(void)
 {
 	dev_remove_pack(&llc_packet_type);
-	dev_remove_pack(&llc_tr_packet_type);
 }
 
 module_init(llc_init);
-- 
GitLab


From 978ffcbf00d82b03b79e64b5c8249589b50e7463 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 8 Jan 2024 16:43:04 -0800
Subject: [PATCH 3075/4076] execve: open the executable file before doing
 anything else

No point in allocating a new mm, counting arguments and environment
variables etc if we're just going to return ENOENT.

This patch does expose the fact that 'do_filp_open()' that execve() uses
is still unnecessarily expensive in the failure case, because it
allocates the 'struct file *' early, even if the path lookup (which is
heavily optimized) fails.

So that remains an unnecessary cost in the "no such executable" case,
but it's a separate issue.  Regardless, I do not want to do _both_ a
filename_lookup() and a later do_filp_open() like the origin patch by
Josh Triplett did in [1].

Reported-by: Josh Triplett <josh@joshtriplett.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/lkml/5c7333ea4bec2fad1b47a8fa2db7c31e4ffc4f14.1663334978.git.josh@joshtriplett.org/ [1]
Link: https://lore.kernel.org/lkml/202209161637.9EDAF6B18@keescook/
Link: https://lore.kernel.org/lkml/CAHk-=wgznerM-xs+x+krDfE7eVBiy_HOam35rbsFMMOwvYuEKQ@mail.gmail.com/
Link: https://lore.kernel.org/lkml/CAHk-=whf9qLO8ipps4QhmS0BkM8mtWJhvnuDSdtw5gFjhzvKNA@mail.gmail.com/
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/exec.c | 69 ++++++++++++++++++++++++++++---------------------------
 1 file changed, 35 insertions(+), 34 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 73e4045df271d..8cdd5b2dd09c2 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1508,12 +1508,24 @@ static void free_bprm(struct linux_binprm *bprm)
 	kfree(bprm);
 }
 
-static struct linux_binprm *alloc_bprm(int fd, struct filename *filename)
+static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags)
 {
-	struct linux_binprm *bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	struct linux_binprm *bprm;
+	struct file *file;
 	int retval = -ENOMEM;
-	if (!bprm)
-		goto out;
+
+	file = do_open_execat(fd, filename, flags);
+	if (IS_ERR(file))
+		return ERR_CAST(file);
+
+	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	if (!bprm) {
+		allow_write_access(file);
+		fput(file);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	bprm->file = file;
 
 	if (fd == AT_FDCWD || filename->name[0] == '/') {
 		bprm->filename = filename->name;
@@ -1526,18 +1538,28 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename)
 		if (!bprm->fdpath)
 			goto out_free;
 
+		/*
+		 * Record that a name derived from an O_CLOEXEC fd will be
+		 * inaccessible after exec.  This allows the code in exec to
+		 * choose to fail when the executable is not mmaped into the
+		 * interpreter and an open file descriptor is not passed to
+		 * the interpreter.  This makes for a better user experience
+		 * than having the interpreter start and then immediately fail
+		 * when it finds the executable is inaccessible.
+		 */
+		if (get_close_on_exec(fd))
+			bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
+
 		bprm->filename = bprm->fdpath;
 	}
 	bprm->interp = bprm->filename;
 
 	retval = bprm_mm_init(bprm);
-	if (retval)
-		goto out_free;
-	return bprm;
+	if (!retval)
+		return bprm;
 
 out_free:
 	free_bprm(bprm);
-out:
 	return ERR_PTR(retval);
 }
 
@@ -1807,10 +1829,8 @@ static int exec_binprm(struct linux_binprm *bprm)
 /*
  * sys_execve() executes a new program.
  */
-static int bprm_execve(struct linux_binprm *bprm,
-		       int fd, struct filename *filename, int flags)
+static int bprm_execve(struct linux_binprm *bprm)
 {
-	struct file *file;
 	int retval;
 
 	retval = prepare_bprm_creds(bprm);
@@ -1826,26 +1846,8 @@ static int bprm_execve(struct linux_binprm *bprm,
 	current->in_execve = 1;
 	sched_mm_cid_before_execve(current);
 
-	file = do_open_execat(fd, filename, flags);
-	retval = PTR_ERR(file);
-	if (IS_ERR(file))
-		goto out_unmark;
-
 	sched_exec();
 
-	bprm->file = file;
-	/*
-	 * Record that a name derived from an O_CLOEXEC fd will be
-	 * inaccessible after exec.  This allows the code in exec to
-	 * choose to fail when the executable is not mmaped into the
-	 * interpreter and an open file descriptor is not passed to
-	 * the interpreter.  This makes for a better user experience
-	 * than having the interpreter start and then immediately fail
-	 * when it finds the executable is inaccessible.
-	 */
-	if (bprm->fdpath && get_close_on_exec(fd))
-		bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
-
 	/* Set the unchanging part of bprm->cred */
 	retval = security_bprm_creds_for_exec(bprm);
 	if (retval)
@@ -1875,7 +1877,6 @@ out:
 	if (bprm->point_of_no_return && !fatal_signal_pending(current))
 		force_fatal_sig(SIGSEGV);
 
-out_unmark:
 	sched_mm_cid_after_execve(current);
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
@@ -1910,7 +1911,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 	 * further execve() calls fail. */
 	current->flags &= ~PF_NPROC_EXCEEDED;
 
-	bprm = alloc_bprm(fd, filename);
+	bprm = alloc_bprm(fd, filename, flags);
 	if (IS_ERR(bprm)) {
 		retval = PTR_ERR(bprm);
 		goto out_ret;
@@ -1959,7 +1960,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 		bprm->argc = 1;
 	}
 
-	retval = bprm_execve(bprm, fd, filename, flags);
+	retval = bprm_execve(bprm);
 out_free:
 	free_bprm(bprm);
 
@@ -1984,7 +1985,7 @@ int kernel_execve(const char *kernel_filename,
 	if (IS_ERR(filename))
 		return PTR_ERR(filename);
 
-	bprm = alloc_bprm(fd, filename);
+	bprm = alloc_bprm(fd, filename, 0);
 	if (IS_ERR(bprm)) {
 		retval = PTR_ERR(bprm);
 		goto out_ret;
@@ -2019,7 +2020,7 @@ int kernel_execve(const char *kernel_filename,
 	if (retval < 0)
 		goto out_free;
 
-	retval = bprm_execve(bprm, fd, filename, 0);
+	retval = bprm_execve(bprm);
 out_free:
 	free_bprm(bprm);
 out_ret:
-- 
GitLab


From ff82e84e80fc0c93095f5a36e0a3508ac121ab80 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Sat, 20 Jan 2024 21:56:11 +0100
Subject: [PATCH 3076/4076] coccinelle: device_attr_show: simplify patch case

Replacing the final expression argument by ... allows the format
string to have multiple arguments.

It also has the advantage of allowing the change to be recognized as
a change in a single statement, thus avoiding adding unneeded braces.

Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
---
 scripts/coccinelle/api/device_attr_show.cocci | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/scripts/coccinelle/api/device_attr_show.cocci b/scripts/coccinelle/api/device_attr_show.cocci
index 634514937e634..550d1d2fc02a9 100644
--- a/scripts/coccinelle/api/device_attr_show.cocci
+++ b/scripts/coccinelle/api/device_attr_show.cocci
@@ -34,15 +34,10 @@ expression BUF, SZ, FORMAT, STR;
 ssize_t show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	<...
-(
 	return
--		snprintf(BUF, SZ, FORMAT, STR);
-+		sysfs_emit(BUF, FORMAT, STR);
-|
-	return
--		snprintf(BUF, SZ, STR);
-+		sysfs_emit(BUF, STR);
-)
+-		snprintf(BUF, SZ, FORMAT
++		sysfs_emit(BUF, FORMAT
+				,...);
 	...>
 }
 
-- 
GitLab


From 31e97d7c9ae3de072d7b424b2cf706a03ec10720 Mon Sep 17 00:00:00 2001
From: Aurelien Jarno <aurelien@aurel32.net>
Date: Sat, 13 Jan 2024 19:33:31 +0100
Subject: [PATCH 3077/4076] media: solo6x10: replace max(a, min(b, c)) by
 clamp(b, a, c)

This patch replaces max(a, min(b, c)) by clamp(b, a, c) in the solo6x10
driver.  This improves the readability and more importantly, for the
solo6x10-p2m.c file, this reduces on my system (x86-64, gcc 13):

 - the preprocessed size from 121 MiB to 4.5 MiB;

 - the build CPU time from 46.8 s to 1.6 s;

 - the build memory from 2786 MiB to 98MiB.

In fine, this allows this relatively simple C file to be built on a
32-bit system.

Reported-by: Jiri Slaby <jirislaby@gmail.com>
Closes: https://lore.kernel.org/lkml/18c6df0d-45ed-450c-9eda-95160a2bbb8e@gmail.com/
Cc:  <stable@vger.kernel.org> # v6.7+
Suggested-by: David Laight <David.Laight@ACULAB.COM>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: David Laight <David.Laight@ACULAB.COM>
Reviewed-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/media/pci/solo6x10/solo6x10-offsets.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/media/pci/solo6x10/solo6x10-offsets.h b/drivers/media/pci/solo6x10/solo6x10-offsets.h
index f414ee1316f29..fdbb817e63601 100644
--- a/drivers/media/pci/solo6x10/solo6x10-offsets.h
+++ b/drivers/media/pci/solo6x10/solo6x10-offsets.h
@@ -57,16 +57,16 @@
 #define SOLO_MP4E_EXT_ADDR(__solo) \
 	(SOLO_EREF_EXT_ADDR(__solo) + SOLO_EREF_EXT_AREA(__solo))
 #define SOLO_MP4E_EXT_SIZE(__solo) \
-	max((__solo->nr_chans * 0x00080000),				\
-	    min(((__solo->sdram_size - SOLO_MP4E_EXT_ADDR(__solo)) -	\
-		 __SOLO_JPEG_MIN_SIZE(__solo)), 0x00ff0000))
+	clamp(__solo->sdram_size - SOLO_MP4E_EXT_ADDR(__solo) -	\
+	      __SOLO_JPEG_MIN_SIZE(__solo),			\
+	      __solo->nr_chans * 0x00080000, 0x00ff0000)
 
 #define __SOLO_JPEG_MIN_SIZE(__solo)		(__solo->nr_chans * 0x00080000)
 #define SOLO_JPEG_EXT_ADDR(__solo) \
 		(SOLO_MP4E_EXT_ADDR(__solo) + SOLO_MP4E_EXT_SIZE(__solo))
 #define SOLO_JPEG_EXT_SIZE(__solo) \
-	max(__SOLO_JPEG_MIN_SIZE(__solo),				\
-	    min((__solo->sdram_size - SOLO_JPEG_EXT_ADDR(__solo)), 0x00ff0000))
+	clamp(__solo->sdram_size - SOLO_JPEG_EXT_ADDR(__solo),	\
+	      __SOLO_JPEG_MIN_SIZE(__solo), 0x00ff0000)
 
 #define SOLO_SDRAM_END(__solo) \
 	(SOLO_JPEG_EXT_ADDR(__solo) + SOLO_JPEG_EXT_SIZE(__solo))
-- 
GitLab


From fead90507a37e73d41f6059b325b34412ed8d84b Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Fri, 5 Jan 2024 10:06:01 +0800
Subject: [PATCH 3078/4076] fbdev: vt8500lcdfb: Remove unnecessary print
 function dev_err()

The print function dev_err() is redundant because platform_get_irq()
already prints an error.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=7824
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/vt8500lcdfb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/video/fbdev/vt8500lcdfb.c b/drivers/video/fbdev/vt8500lcdfb.c
index 42c25dc851976..ac73937073a76 100644
--- a/drivers/video/fbdev/vt8500lcdfb.c
+++ b/drivers/video/fbdev/vt8500lcdfb.c
@@ -374,7 +374,6 @@ static int vt8500lcd_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(&pdev->dev, "no IRQ defined\n");
 		ret = -ENODEV;
 		goto failed_free_palette;
 	}
-- 
GitLab


From 04e5eac8f3ab2ff52fa191c187a46d4fdbc1e288 Mon Sep 17 00:00:00 2001
From: Fullway Wang <fullwaywang@outlook.com>
Date: Thu, 18 Jan 2024 11:49:40 +0800
Subject: [PATCH 3079/4076] fbdev: savage: Error out if pixclock equals zero

The userspace program could pass any values to the driver through
ioctl() interface. If the driver doesn't check the value of pixclock,
it may cause divide-by-zero error.

Although pixclock is checked in savagefb_decode_var(), but it is not
checked properly in savagefb_probe(). Fix this by checking whether
pixclock is zero in the function savagefb_check_var() before
info->var.pixclock is used as the divisor.

This is similar to CVE-2022-3061 in i740fb which was fixed by
commit 15cf0b8.

Signed-off-by: Fullway Wang <fullwaywang@outlook.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/savage/savagefb_driver.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c
index dddd6afcb972a..ebc9aeffdde7c 100644
--- a/drivers/video/fbdev/savage/savagefb_driver.c
+++ b/drivers/video/fbdev/savage/savagefb_driver.c
@@ -869,6 +869,9 @@ static int savagefb_check_var(struct fb_var_screeninfo   *var,
 
 	DBG("savagefb_check_var");
 
+	if (!var->pixclock)
+		return -EINVAL;
+
 	var->transp.offset = 0;
 	var->transp.length = 0;
 	switch (var->bits_per_pixel) {
-- 
GitLab


From e421946be7d9bf545147bea8419ef8239cb7ca52 Mon Sep 17 00:00:00 2001
From: Fullway Wang <fullwaywang@outlook.com>
Date: Thu, 18 Jan 2024 14:24:43 +0800
Subject: [PATCH 3080/4076] fbdev: sis: Error out if pixclock equals zero

The userspace program could pass any values to the driver through
ioctl() interface. If the driver doesn't check the value of pixclock,
it may cause divide-by-zero error.

In sisfb_check_var(), var->pixclock is used as a divisor to caculate
drate before it is checked against zero. Fix this by checking it
at the beginning.

This is similar to CVE-2022-3061 in i740fb which was fixed by
commit 15cf0b8.

Signed-off-by: Fullway Wang <fullwaywang@outlook.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/sis/sis_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c
index 803ccb6aa4797..009bf1d926448 100644
--- a/drivers/video/fbdev/sis/sis_main.c
+++ b/drivers/video/fbdev/sis/sis_main.c
@@ -1444,6 +1444,8 @@ sisfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 	vtotal = var->upper_margin + var->lower_margin + var->vsync_len;
 
+	if (!var->pixclock)
+		return -EINVAL;
 	pixclock = var->pixclock;
 
 	if((var->vmode & FB_VMODE_MASK) == FB_VMODE_NONINTERLACED) {
-- 
GitLab


From e240c1b3635e3fc7d3ba46c6fe12a0d8efb2941a Mon Sep 17 00:00:00 2001
From: Su Yue <glass.su@suse.com>
Date: Mon, 8 Jan 2024 23:11:08 +0800
Subject: [PATCH 3081/4076] bcachefs: fix memleak in bch2_split_devs

The pointer dev_name can be modified by strseq(),
then causes the memleak:

unreferenced object 0xffff9d08a2916c80 (size 32):
  comm "mount.bcachefs", pid 9090, jiffies 4295856224 (age 17.564s)
  hex dump (first 32 bytes):
    2f 64 65 76 2f 6d 61 70 70 65 72 2f 74 65 73 74  /dev/mapper/test
    2d 30 00 00 00 00 00 00 00 00 00 00 00 00 00 00  -0..............
  backtrace:
    [<00000000c5d3be7d>] __kmem_cache_alloc_node+0x1f3/0x2c0
    [<0000000052215d26>] __kmalloc_node_track_caller+0x51/0x150
    [<0000000069fea956>] kstrdup+0x32/0x60
    [<000000000877fcf1>] bch2_split_devs+0x3f/0x150 [bcachefs]
    [<000000007ee93204>] bch2_mount+0xcb/0x640 [bcachefs]
    [<000000002dd1e04b>] legacy_get_tree+0x30/0x60
    [<000000006afc31d3>] vfs_get_tree+0x28/0xf0
    [<000000007b0c538e>] path_mount+0x475/0xb60
    [<0000000092de5882>] __x64_sys_mount+0x105/0x140
    [<0000000054fc05d8>] do_syscall_64+0x42/0xf0
    [<00000000df584910>] entry_SYSCALL_64_after_hwframe+0x6e/0x76

Fix it by copy pointer dev_name at beginning and free the copied
pointer at end.

Signed-off-by: Su Yue <glass.su@suse.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/util.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index c2ef7cddaa4fc..f927c8a19e241 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -1186,7 +1186,9 @@ int bch2_split_devs(const char *_dev_name, darray_str *ret)
 {
 	darray_init(ret);
 
-	char *dev_name = kstrdup(_dev_name, GFP_KERNEL), *s = dev_name;
+	char *dev_name, *s, *orig;
+
+	dev_name = orig = kstrdup(_dev_name, GFP_KERNEL);
 	if (!dev_name)
 		return -ENOMEM;
 
@@ -1201,10 +1203,10 @@ int bch2_split_devs(const char *_dev_name, darray_str *ret)
 		}
 	}
 
-	kfree(dev_name);
+	kfree(orig);
 	return 0;
 err:
 	bch2_darray_str_exit(ret);
-	kfree(dev_name);
+	kfree(orig);
 	return -ENOMEM;
 }
-- 
GitLab


From 4ecad0da9de830681ffff973bc0d47b07612bbe6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 10 Jan 2024 23:08:30 -0500
Subject: [PATCH 3082/4076] bcachefs: Don't log errors if
 BCH_WRITE_ALLOC_NOWAIT

Previously, we added logging in the write path to ensure that any
unexpected errors getting reported to userspace have a log message; but
BCH_WRITE_ALLOC_NOWAIT is a special case, it's used for promotes where
errors are expected and not reported out to userspace - so we need to
silence those.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/io_write.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index 33c0e783d5469..e69c00fa32bdb 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -1447,10 +1447,11 @@ err:
 			op->flags |= BCH_WRITE_DONE;
 
 			if (ret < 0) {
-				bch_err_inum_offset_ratelimited(c,
-					op->pos.inode,
-					op->pos.offset << 9,
-					"%s(): error: %s", __func__, bch2_err_str(ret));
+				if (!(op->flags & BCH_WRITE_ALLOC_NOWAIT))
+					bch_err_inum_offset_ratelimited(c,
+						op->pos.inode,
+						op->pos.offset << 9,
+						"%s(): error: %s", __func__, bch2_err_str(ret));
 				op->error = ret;
 				break;
 			}
-- 
GitLab


From 3fe8a1864042f7793e8fd79e4e24678839207153 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 6 Jan 2024 19:29:14 -0500
Subject: [PATCH 3083/4076] bcachefs: eytzinger_for_each() declares loop iter

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bset.c      | 2 +-
 fs/bcachefs/eytzinger.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/bcachefs/bset.c b/fs/bcachefs/bset.c
index 74bf8eb90a4c4..044fff9b2cf6e 100644
--- a/fs/bcachefs/bset.c
+++ b/fs/bcachefs/bset.c
@@ -720,7 +720,7 @@ static noinline void __build_ro_aux_tree(struct btree *b, struct bset_tree *t)
 {
 	struct bkey_packed *prev = NULL, *k = btree_bkey_first(b, t);
 	struct bkey_i min_key, max_key;
-	unsigned j, cacheline = 1;
+	unsigned cacheline = 1;
 
 	t->size = min(bkey_to_cacheline(b, t, btree_bkey_last(b, t)),
 		      bset_ro_tree_capacity(b, t));
diff --git a/fs/bcachefs/eytzinger.h b/fs/bcachefs/eytzinger.h
index 9637f636e32d5..b04750dbf870b 100644
--- a/fs/bcachefs/eytzinger.h
+++ b/fs/bcachefs/eytzinger.h
@@ -156,7 +156,7 @@ static inline unsigned inorder_to_eytzinger1(unsigned i, unsigned size)
 }
 
 #define eytzinger1_for_each(_i, _size)			\
-	for ((_i) = eytzinger1_first((_size));		\
+	for (unsigned (_i) = eytzinger1_first((_size));	\
 	     (_i) != 0;					\
 	     (_i) = eytzinger1_next((_i), (_size)))
 
@@ -227,7 +227,7 @@ static inline unsigned inorder_to_eytzinger0(unsigned i, unsigned size)
 }
 
 #define eytzinger0_for_each(_i, _size)			\
-	for ((_i) = eytzinger0_first((_size));		\
+	for (unsigned (_i) = eytzinger0_first((_size));	\
 	     (_i) != -1;				\
 	     (_i) = eytzinger0_next((_i), (_size)))
 
-- 
GitLab


From 9d5dba2ba86de28f74497d9018889918d368d9fa Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 6 Jan 2024 19:47:09 -0500
Subject: [PATCH 3084/4076] bcachefs: drop to_text code for obsolete bps in
 alloc keys

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/alloc_background.c | 18 ------------------
 1 file changed, 18 deletions(-)

diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index a09b9d00226a4..f31541a95537a 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -321,7 +321,6 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
 {
 	struct bch_alloc_v4 _a;
 	const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a);
-	unsigned i;
 
 	prt_newline(out);
 	printbuf_indent_add(out, 2);
@@ -353,23 +352,6 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
 	prt_printf(out, "fragmentation     %llu",	a->fragmentation_lru);
 	prt_newline(out);
 	prt_printf(out, "bp_start          %llu", BCH_ALLOC_V4_BACKPOINTERS_START(a));
-	prt_newline(out);
-
-	if (BCH_ALLOC_V4_NR_BACKPOINTERS(a)) {
-		struct bkey_s_c_alloc_v4 a_raw = bkey_s_c_to_alloc_v4(k);
-		const struct bch_backpointer *bps = alloc_v4_backpointers_c(a_raw.v);
-
-		prt_printf(out, "backpointers:     %llu", BCH_ALLOC_V4_NR_BACKPOINTERS(a_raw.v));
-		printbuf_indent_add(out, 2);
-
-		for (i = 0; i < BCH_ALLOC_V4_NR_BACKPOINTERS(a_raw.v); i++) {
-			prt_newline(out);
-			bch2_backpointer_to_text(out, &bps[i]);
-		}
-
-		printbuf_indent_sub(out, 2);
-	}
-
 	printbuf_indent_sub(out, 2);
 }
 
-- 
GitLab


From 38c23fb809f60bda1adfc431b18200b8f68c2025 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 7 Jan 2024 17:14:46 -0500
Subject: [PATCH 3085/4076] bcachefs: BTREE_TRIGGER_ATOMIC

Add a new flag to be explicit about when we're running atomic triggers.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/alloc_background.c   |  2 +-
 fs/bcachefs/bkey_methods.h       | 10 ++++++----
 fs/bcachefs/btree_trans_commit.c | 19 +++++++------------
 fs/bcachefs/btree_types.h        |  4 ++--
 fs/bcachefs/ec.c                 |  2 +-
 fs/bcachefs/inode.c              |  2 +-
 fs/bcachefs/reflink.c            | 10 +++++-----
 fs/bcachefs/reflink.h            |  8 ++++----
 8 files changed, 27 insertions(+), 30 deletions(-)

diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index f31541a95537a..bebaaf8dbeea8 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -821,7 +821,7 @@ int bch2_trigger_alloc(struct btree_trans *trans,
 		}
 	}
 
-	if (!(flags & BTREE_TRIGGER_TRANSACTIONAL) && (flags & BTREE_TRIGGER_INSERT)) {
+	if ((flags & BTREE_TRIGGER_ATOMIC) && (flags & BTREE_TRIGGER_INSERT)) {
 		struct bch_alloc_v4 *new_a = bkey_s_to_alloc_v4(new).v;
 		u64 journal_seq = trans->journal_res.seq;
 		u64 bucket_journal_seq = new_a->journal_seq;
diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h
index ee82283722b75..03efe8ee565a9 100644
--- a/fs/bcachefs/bkey_methods.h
+++ b/fs/bcachefs/bkey_methods.h
@@ -83,9 +83,10 @@ enum btree_update_flags {
 
 	__BTREE_TRIGGER_NORUN,
 	__BTREE_TRIGGER_TRANSACTIONAL,
+	__BTREE_TRIGGER_ATOMIC,
+	__BTREE_TRIGGER_GC,
 	__BTREE_TRIGGER_INSERT,
 	__BTREE_TRIGGER_OVERWRITE,
-	__BTREE_TRIGGER_GC,
 	__BTREE_TRIGGER_BUCKET_INVALIDATE,
 };
 
@@ -107,6 +108,10 @@ enum btree_update_flags {
  * causing us to go emergency read-only)
  */
 #define BTREE_TRIGGER_TRANSACTIONAL	(1U << __BTREE_TRIGGER_TRANSACTIONAL)
+#define BTREE_TRIGGER_ATOMIC		(1U << __BTREE_TRIGGER_ATOMIC)
+
+/* We're in gc/fsck: running triggers to recalculate e.g. disk usage */
+#define BTREE_TRIGGER_GC		(1U << __BTREE_TRIGGER_GC)
 
 /* @new is entering the btree */
 #define BTREE_TRIGGER_INSERT		(1U << __BTREE_TRIGGER_INSERT)
@@ -114,9 +119,6 @@ enum btree_update_flags {
 /* @old is leaving the btree */
 #define BTREE_TRIGGER_OVERWRITE		(1U << __BTREE_TRIGGER_OVERWRITE)
 
-/* We're in gc/fsck: running triggers to recalculate e.g. disk usage */
-#define BTREE_TRIGGER_GC		(1U << __BTREE_TRIGGER_GC)
-
 /* signal from bucket invalidate path to alloc trigger */
 #define BTREE_TRIGGER_BUCKET_INVALIDATE	(1U << __BTREE_TRIGGER_BUCKET_INVALIDATE)
 
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 90eb8065ff2da..e3a82c33912b9 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -448,9 +448,6 @@ static int run_one_mem_trigger(struct btree_trans *trans,
 	if (unlikely(flags & BTREE_TRIGGER_NORUN))
 		return 0;
 
-	if (!btree_node_type_needs_gc(__btree_node_type(i->level, i->btree_id)))
-		return 0;
-
 	if (old_ops->trigger == new_ops->trigger) {
 		ret   = bch2_key_trigger(trans, i->btree_id, i->level,
 				old, bkey_i_to_s(new),
@@ -586,9 +583,6 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans)
 
 static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans)
 {
-	struct bch_fs *c = trans->c;
-	int ret = 0;
-
 	trans_for_each_update(trans, i) {
 		/*
 		 * XXX: synchronization of cached update triggers with gc
@@ -596,14 +590,15 @@ static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans)
 		 */
 		BUG_ON(i->cached || i->level);
 
-		if (gc_visited(c, gc_pos_btree_node(insert_l(trans, i)->b))) {
-			ret = run_one_mem_trigger(trans, i, i->flags|BTREE_TRIGGER_GC);
+		if (btree_node_type_needs_gc(__btree_node_type(i->level, i->btree_id)) &&
+		    gc_visited(trans->c, gc_pos_btree_node(insert_l(trans, i)->b))) {
+			int ret = run_one_mem_trigger(trans, i, i->flags|BTREE_TRIGGER_GC);
 			if (ret)
-				break;
+				return ret;
 		}
 	}
 
-	return ret;
+	return 0;
 }
 
 static inline int
@@ -689,8 +684,8 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 	}
 
 	trans_for_each_update(trans, i)
-		if (BTREE_NODE_TYPE_HAS_MEM_TRIGGERS & (1U << i->bkey_type)) {
-			ret = run_one_mem_trigger(trans, i, i->flags);
+		if (BTREE_NODE_TYPE_HAS_ATOMIC_TRIGGERS & (1U << i->bkey_type)) {
+			ret = run_one_mem_trigger(trans, i, BTREE_TRIGGER_ATOMIC|i->flags);
 			if (ret)
 				goto fatal_err;
 		}
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index d530307046f4c..e46867536fa6a 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -653,7 +653,7 @@ const char *bch2_btree_node_type_str(enum btree_node_type);
 	 BIT_ULL(BKEY_TYPE_reflink)|			\
 	 BIT_ULL(BKEY_TYPE_btree))
 
-#define BTREE_NODE_TYPE_HAS_MEM_TRIGGERS		\
+#define BTREE_NODE_TYPE_HAS_ATOMIC_TRIGGERS		\
 	(BIT_ULL(BKEY_TYPE_alloc)|			\
 	 BIT_ULL(BKEY_TYPE_inodes)|			\
 	 BIT_ULL(BKEY_TYPE_stripes)|			\
@@ -661,7 +661,7 @@ const char *bch2_btree_node_type_str(enum btree_node_type);
 
 #define BTREE_NODE_TYPE_HAS_TRIGGERS			\
 	(BTREE_NODE_TYPE_HAS_TRANS_TRIGGERS|		\
-	 BTREE_NODE_TYPE_HAS_MEM_TRIGGERS)
+	 BTREE_NODE_TYPE_HAS_ATOMIC_TRIGGERS)
 
 static inline bool btree_node_type_needs_gc(enum btree_node_type type)
 {
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index d802bc63c8d0b..b29b8a20bb8b4 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -367,7 +367,7 @@ int bch2_trigger_stripe(struct btree_trans *trans,
 		}
 	}
 
-	if (!(flags & (BTREE_TRIGGER_TRANSACTIONAL|BTREE_TRIGGER_GC))) {
+	if (flags & BTREE_TRIGGER_ATOMIC) {
 		struct stripe *m = genradix_ptr(&c->stripes, idx);
 
 		if (!m) {
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 37dce96f48ac4..51a06324b21d3 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -587,7 +587,7 @@ int bch2_trigger_inode(struct btree_trans *trans,
 		}
 	}
 
-	if (!(flags & BTREE_TRIGGER_TRANSACTIONAL) && (flags & BTREE_TRIGGER_INSERT)) {
+	if ((flags & BTREE_TRIGGER_ATOMIC) && (flags & BTREE_TRIGGER_INSERT)) {
 		BUG_ON(!trans->journal_res.seq);
 
 		bkey_s_to_inode_v3(new).v->bi_journal_seq = cpu_to_le64(trans->journal_res.seq);
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index faa5d36700587..6070109174210 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -292,10 +292,10 @@ static inline void check_indirect_extent_deleting(struct bkey_s new, unsigned *f
 	}
 }
 
-int bch2_trans_mark_reflink_v(struct btree_trans *trans,
-			      enum btree_id btree_id, unsigned level,
-			      struct bkey_s_c old, struct bkey_s new,
-			      unsigned flags)
+int bch2_trigger_reflink_v(struct btree_trans *trans,
+			   enum btree_id btree_id, unsigned level,
+			   struct bkey_s_c old, struct bkey_s new,
+			   unsigned flags)
 {
 	if ((flags & BTREE_TRIGGER_TRANSACTIONAL) &&
 	    (flags & BTREE_TRIGGER_INSERT))
@@ -324,7 +324,7 @@ void bch2_indirect_inline_data_to_text(struct printbuf *out,
 	       min(datalen, 32U), d.v->data);
 }
 
-int bch2_trans_mark_indirect_inline_data(struct btree_trans *trans,
+int bch2_trigger_indirect_inline_data(struct btree_trans *trans,
 			      enum btree_id btree_id, unsigned level,
 			      struct bkey_s_c old, struct bkey_s new,
 			      unsigned flags)
diff --git a/fs/bcachefs/reflink.h b/fs/bcachefs/reflink.h
index 8ee778ec0022a..4d8867289717b 100644
--- a/fs/bcachefs/reflink.h
+++ b/fs/bcachefs/reflink.h
@@ -24,14 +24,14 @@ int bch2_reflink_v_invalid(struct bch_fs *, struct bkey_s_c,
 			   enum bkey_invalid_flags, struct printbuf *);
 void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *,
 			    struct bkey_s_c);
-int bch2_trans_mark_reflink_v(struct btree_trans *, enum btree_id, unsigned,
+int bch2_trigger_reflink_v(struct btree_trans *, enum btree_id, unsigned,
 			      struct bkey_s_c, struct bkey_s, unsigned);
 
 #define bch2_bkey_ops_reflink_v ((struct bkey_ops) {		\
 	.key_invalid	= bch2_reflink_v_invalid,		\
 	.val_to_text	= bch2_reflink_v_to_text,		\
 	.swab		= bch2_ptr_swab,			\
-	.trigger	= bch2_trans_mark_reflink_v,		\
+	.trigger	= bch2_trigger_reflink_v,		\
 	.min_val_size	= 8,					\
 })
 
@@ -39,7 +39,7 @@ int bch2_indirect_inline_data_invalid(struct bch_fs *, struct bkey_s_c,
 				      enum bkey_invalid_flags, struct printbuf *);
 void bch2_indirect_inline_data_to_text(struct printbuf *,
 				struct bch_fs *, struct bkey_s_c);
-int bch2_trans_mark_indirect_inline_data(struct btree_trans *,
+int bch2_trigger_indirect_inline_data(struct btree_trans *,
 					 enum btree_id, unsigned,
 			      struct bkey_s_c, struct bkey_s,
 			      unsigned);
@@ -47,7 +47,7 @@ int bch2_trans_mark_indirect_inline_data(struct btree_trans *,
 #define bch2_bkey_ops_indirect_inline_data ((struct bkey_ops) {	\
 	.key_invalid	= bch2_indirect_inline_data_invalid,	\
 	.val_to_text	= bch2_indirect_inline_data_to_text,	\
-	.trigger	= bch2_trans_mark_indirect_inline_data,	\
+	.trigger	= bch2_trigger_indirect_inline_data,	\
 	.min_val_size	= 8,					\
 })
 
-- 
GitLab


From e58f963cecbdb08f28334122afba93a7840beabc Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 6 Jan 2024 20:57:43 -0500
Subject: [PATCH 3086/4076] bcachefs: helpers for printing data types

We need bounds checking since new versions may introduce new data types.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/alloc_background.c |  9 +++------
 fs/bcachefs/alloc_foreground.c |  7 ++++---
 fs/bcachefs/btree_gc.c         | 24 ++++++++++++------------
 fs/bcachefs/buckets.c          | 26 +++++++++++++-------------
 fs/bcachefs/buckets.h          | 15 +++++++++++++++
 fs/bcachefs/ec.c               |  4 ++--
 fs/bcachefs/journal_io.c       |  5 +----
 fs/bcachefs/move.c             |  6 +++---
 fs/bcachefs/opts.c             |  2 +-
 fs/bcachefs/opts.h             |  2 +-
 fs/bcachefs/replicas.c         | 18 ++++--------------
 fs/bcachefs/sb-members.c       |  4 ++--
 fs/bcachefs/super.c            |  2 +-
 fs/bcachefs/sysfs.c            |  4 ++--
 14 files changed, 64 insertions(+), 64 deletions(-)

diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index bebaaf8dbeea8..614da759226b5 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -273,7 +273,7 @@ int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k,
 		bkey_fsck_err_on(!bch2_bucket_sectors_dirty(*a.v),
 				 c, err, alloc_key_dirty_sectors_0,
 				 "data_type %s but dirty_sectors==0",
-				 bch2_data_types[a.v->data_type]);
+				 bch2_data_type_str(a.v->data_type));
 		break;
 	case BCH_DATA_cached:
 		bkey_fsck_err_on(!a.v->cached_sectors ||
@@ -325,11 +325,8 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
 	prt_newline(out);
 	printbuf_indent_add(out, 2);
 
-	prt_printf(out, "gen %u oldest_gen %u data_type %s",
-	       a->gen, a->oldest_gen,
-	       a->data_type < BCH_DATA_NR
-	       ? bch2_data_types[a->data_type]
-	       : "(invalid data type)");
+	prt_printf(out, "gen %u oldest_gen %u data_type ", a->gen, a->oldest_gen);
+	bch2_prt_data_type(out, a->data_type);
 	prt_newline(out);
 	prt_printf(out, "journal_seq       %llu",	a->journal_seq);
 	prt_newline(out);
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index b0ff47998a944..633d3223b353f 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -1525,10 +1525,11 @@ static void bch2_open_bucket_to_text(struct printbuf *out, struct bch_fs *c, str
 	unsigned data_type = ob->data_type;
 	barrier(); /* READ_ONCE() doesn't work on bitfields */
 
-	prt_printf(out, "%zu ref %u %s %u:%llu gen %u allocated %u/%u",
+	prt_printf(out, "%zu ref %u ",
 		   ob - c->open_buckets,
-		   atomic_read(&ob->pin),
-		   data_type < BCH_DATA_NR ? bch2_data_types[data_type] : "invalid data type",
+		   atomic_read(&ob->pin));
+	bch2_prt_data_type(out, data_type);
+	prt_printf(out, " %u:%llu gen %u allocated %u/%u",
 		   ob->dev, ob->bucket, ob->gen,
 		   ca->mi.bucket_size - ob->sectors_free, ca->mi.bucket_size);
 	if (ob->ec)
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 49b4ade758c36..523e9b1069cd2 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -597,7 +597,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 			      "bucket %u:%zu data type %s ptr gen %u missing in alloc btree\n"
 			      "while marking %s",
 			      p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr),
-			      bch2_data_types[ptr_data_type(k->k, &p.ptr)],
+			      bch2_data_type_str(ptr_data_type(k->k, &p.ptr)),
 			      p.ptr.gen,
 			      (printbuf_reset(&buf),
 			       bch2_bkey_val_to_text(&buf, c, *k), buf.buf)))) {
@@ -615,7 +615,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 			      "bucket %u:%zu data type %s ptr gen in the future: %u > %u\n"
 			      "while marking %s",
 			      p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr),
-			      bch2_data_types[ptr_data_type(k->k, &p.ptr)],
+			      bch2_data_type_str(ptr_data_type(k->k, &p.ptr)),
 			      p.ptr.gen, g->gen,
 			      (printbuf_reset(&buf),
 			       bch2_bkey_val_to_text(&buf, c, *k), buf.buf)))) {
@@ -637,7 +637,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 			      "bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n"
 			      "while marking %s",
 			      p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), g->gen,
-			      bch2_data_types[ptr_data_type(k->k, &p.ptr)],
+			      bch2_data_type_str(ptr_data_type(k->k, &p.ptr)),
 			      p.ptr.gen,
 			      (printbuf_reset(&buf),
 			       bch2_bkey_val_to_text(&buf, c, *k), buf.buf))))
@@ -649,7 +649,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 			      "bucket %u:%zu data type %s stale dirty ptr: %u < %u\n"
 			      "while marking %s",
 			      p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr),
-			      bch2_data_types[ptr_data_type(k->k, &p.ptr)],
+			      bch2_data_type_str(ptr_data_type(k->k, &p.ptr)),
 			      p.ptr.gen, g->gen,
 			      (printbuf_reset(&buf),
 			       bch2_bkey_val_to_text(&buf, c, *k), buf.buf))))
@@ -664,8 +664,8 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id
 				"bucket %u:%zu different types of data in same bucket: %s, %s\n"
 				"while marking %s",
 				p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr),
-				bch2_data_types[g->data_type],
-				bch2_data_types[data_type],
+				bch2_data_type_str(g->data_type),
+				bch2_data_type_str(data_type),
 				(printbuf_reset(&buf),
 				 bch2_bkey_val_to_text(&buf, c, *k), buf.buf))) {
 			if (data_type == BCH_DATA_btree) {
@@ -1238,11 +1238,11 @@ static int bch2_gc_done(struct bch_fs *c,
 
 		for (i = 0; i < BCH_DATA_NR; i++) {
 			copy_dev_field(dev_usage_buckets_wrong,
-				       d[i].buckets,	"%s buckets", bch2_data_types[i]);
+				       d[i].buckets,	"%s buckets", bch2_data_type_str(i));
 			copy_dev_field(dev_usage_sectors_wrong,
-				       d[i].sectors,	"%s sectors", bch2_data_types[i]);
+				       d[i].sectors,	"%s sectors", bch2_data_type_str(i));
 			copy_dev_field(dev_usage_fragmented_wrong,
-				       d[i].fragmented,	"%s fragmented", bch2_data_types[i]);
+				       d[i].fragmented,	"%s fragmented", bch2_data_type_str(i));
 		}
 	}
 
@@ -1417,8 +1417,8 @@ static int bch2_alloc_write_key(struct btree_trans *trans,
 			": got %s, should be %s",
 			iter->pos.inode, iter->pos.offset,
 			gc.gen,
-			bch2_data_types[new.data_type],
-			bch2_data_types[gc.data_type]))
+			bch2_data_type_str(new.data_type),
+			bch2_data_type_str(gc.data_type)))
 		new.data_type = gc.data_type;
 
 #define copy_bucket_field(_errtype, _f)					\
@@ -1428,7 +1428,7 @@ static int bch2_alloc_write_key(struct btree_trans *trans,
 			": got %u, should be %u",			\
 			iter->pos.inode, iter->pos.offset,		\
 			gc.gen,						\
-			bch2_data_types[gc.data_type],			\
+			bch2_data_type_str(gc.data_type),		\
 			new._f, gc._f))					\
 		new._f = gc._f;						\
 
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index d83ea0e53df3f..5dc19363bb9fe 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -284,7 +284,7 @@ void bch2_dev_usage_to_text(struct printbuf *out, struct bch_dev_usage *usage)
 	prt_newline(out);
 
 	for (unsigned i = 0; i < BCH_DATA_NR; i++) {
-		prt_str(out, bch2_data_types[i]);
+		bch2_prt_data_type(out, i);
 		prt_tab(out);
 		prt_u64(out, usage->d[i].buckets);
 		prt_tab_rjust(out);
@@ -523,8 +523,8 @@ int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca,
 	if (bch2_fs_inconsistent_on(g->data_type &&
 			g->data_type != data_type, c,
 			"different types of data in same bucket: %s, %s",
-			bch2_data_types[g->data_type],
-			bch2_data_types[data_type])) {
+			bch2_data_type_str(g->data_type),
+			bch2_data_type_str(data_type))) {
 		ret = -EIO;
 		goto err;
 	}
@@ -532,7 +532,7 @@ int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca,
 	if (bch2_fs_inconsistent_on((u64) g->dirty_sectors + sectors > ca->mi.bucket_size, c,
 			"bucket %u:%zu gen %u data type %s sector count overflow: %u + %u > bucket size",
 			ca->dev_idx, b, g->gen,
-			bch2_data_types[g->data_type ?: data_type],
+			bch2_data_type_str(g->data_type ?: data_type),
 			g->dirty_sectors, sectors)) {
 		ret = -EIO;
 		goto err;
@@ -575,7 +575,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"bucket %u:%zu gen %u data type %s: ptr gen %u newer than bucket gen\n"
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
-			bch2_data_types[bucket_data_type ?: ptr_data_type],
+			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
 			ptr->gen,
 			(bch2_bkey_val_to_text(&buf, c, k), buf.buf));
 		ret = -EIO;
@@ -588,7 +588,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n"
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
-			bch2_data_types[bucket_data_type ?: ptr_data_type],
+			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
 			ptr->gen,
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
@@ -603,7 +603,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
 			*bucket_gen(ca, bucket_nr),
-			bch2_data_types[bucket_data_type ?: ptr_data_type],
+			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
 			ptr->gen,
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
@@ -624,8 +624,8 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n"
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
-			bch2_data_types[bucket_data_type],
-			bch2_data_types[ptr_data_type],
+			bch2_data_type_str(bucket_data_type),
+			bch2_data_type_str(ptr_data_type),
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
 		ret = -EIO;
@@ -638,7 +638,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans,
 			"bucket %u:%zu gen %u data type %s sector count overflow: %u + %lli > U32_MAX\n"
 			"while marking %s",
 			ptr->dev, bucket_nr, b_gen,
-			bch2_data_types[bucket_data_type ?: ptr_data_type],
+			bch2_data_type_str(bucket_data_type ?: ptr_data_type),
 			bucket_sectors, sectors,
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf));
@@ -1130,9 +1130,9 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
 			"bucket %llu:%llu gen %u different types of data in same bucket: %s, %s\n"
 			"while marking %s",
 			iter.pos.inode, iter.pos.offset, a->v.gen,
-			bch2_data_types[a->v.data_type],
-			bch2_data_types[type],
-			bch2_data_types[type]);
+			bch2_data_type_str(a->v.data_type),
+			bch2_data_type_str(type),
+			bch2_data_type_str(type));
 		ret = -EIO;
 		goto err;
 	}
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 2c95cc5d86be6..2b1e907f2acad 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -385,6 +385,21 @@ static inline bool is_superblock_bucket(struct bch_dev *ca, u64 b)
 	return false;
 }
 
+static inline const char *bch2_data_type_str(enum bch_data_type type)
+{
+	return type < BCH_DATA_NR
+		? __bch2_data_types[type]
+		: "(invalid data type)";
+}
+
+static inline void bch2_prt_data_type(struct printbuf *out, enum bch_data_type type)
+{
+	if (type < BCH_DATA_NR)
+		prt_str(out, __bch2_data_types[type]);
+	else
+		prt_printf(out, "(invalid data type %u)", type);
+}
+
 /* disk reservations: */
 
 static inline void bch2_disk_reservation_put(struct bch_fs *c,
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index b29b8a20bb8b4..d503af2700247 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -190,7 +190,7 @@ static int bch2_trans_mark_stripe_bucket(struct btree_trans *trans,
 					       a->v.stripe_redundancy, trans,
 				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: multiple stripes using same bucket (%u, %llu)",
 				iter.pos.inode, iter.pos.offset, a->v.gen,
-				bch2_data_types[a->v.data_type],
+				bch2_data_type_str(a->v.data_type),
 				a->v.dirty_sectors,
 				a->v.stripe, s.k->p.offset)) {
 			ret = -EIO;
@@ -200,7 +200,7 @@ static int bch2_trans_mark_stripe_bucket(struct btree_trans *trans,
 		if (bch2_trans_inconsistent_on(data_type && a->v.dirty_sectors, trans,
 				"bucket %llu:%llu gen %u data type %s dirty_sectors %u: data already in stripe bucket %llu",
 				iter.pos.inode, iter.pos.offset, a->v.gen,
-				bch2_data_types[a->v.data_type],
+				bch2_data_type_str(a->v.data_type),
 				a->v.dirty_sectors,
 				s.k->p.offset)) {
 			ret = -EIO;
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index b0f4dd491e120..04a1e79a5ed39 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -683,10 +683,7 @@ static void journal_entry_dev_usage_to_text(struct printbuf *out, struct bch_fs
 	prt_printf(out, "dev=%u", le32_to_cpu(u->dev));
 
 	for (i = 0; i < nr_types; i++) {
-		if (i < BCH_DATA_NR)
-			prt_printf(out, " %s", bch2_data_types[i]);
-		else
-			prt_printf(out, " (unknown data type %u)", i);
+		bch2_prt_data_type(out, i);
 		prt_printf(out, ": buckets=%llu sectors=%llu fragmented=%llu",
 		       le64_to_cpu(u->d[i].buckets),
 		       le64_to_cpu(u->d[i].sectors),
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 7a33319dcd168..a9e0920b34f32 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -1083,9 +1083,9 @@ int bch2_data_job(struct bch_fs *c,
 
 void bch2_move_stats_to_text(struct printbuf *out, struct bch_move_stats *stats)
 {
-	prt_printf(out, "%s: data type=%s pos=",
-		   stats->name,
-		   bch2_data_types[stats->data_type]);
+	prt_printf(out, "%s: data type==", stats->name);
+	bch2_prt_data_type(out, stats->data_type);
+	prt_str(out, " pos=");
 	bch2_bbpos_to_text(out, stats->pos);
 	prt_newline(out);
 	printbuf_indent_add(out, 2);
diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c
index 8e6f230eac381..6aaf78de88457 100644
--- a/fs/bcachefs/opts.c
+++ b/fs/bcachefs/opts.c
@@ -72,7 +72,7 @@ const char * const bch2_str_hash_opts[] = {
 	NULL
 };
 
-const char * const bch2_data_types[] = {
+const char * const __bch2_data_types[] = {
 	BCH_DATA_TYPES()
 	NULL
 };
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 93a24fef42148..67e98e00e9372 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -22,7 +22,7 @@ extern const char * const bch2_compression_types[];
 extern const char * const bch2_compression_opts[];
 extern const char * const bch2_str_hash_types[];
 extern const char * const bch2_str_hash_opts[];
-extern const char * const bch2_data_types[];
+extern const char * const __bch2_data_types[];
 extern const char * const bch2_member_states[];
 extern const char * const bch2_jset_entry_types[];
 extern const char * const bch2_fs_usage_types[];
diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c
index 92ba56ef1fc89..1c3900da4c770 100644
--- a/fs/bcachefs/replicas.c
+++ b/fs/bcachefs/replicas.c
@@ -39,15 +39,10 @@ static void bch2_cpu_replicas_sort(struct bch_replicas_cpu *r)
 static void bch2_replicas_entry_v0_to_text(struct printbuf *out,
 					   struct bch_replicas_entry_v0 *e)
 {
-	unsigned i;
-
-	if (e->data_type < BCH_DATA_NR)
-		prt_printf(out, "%s", bch2_data_types[e->data_type]);
-	else
-		prt_printf(out, "(invalid data type %u)", e->data_type);
+	bch2_prt_data_type(out, e->data_type);
 
 	prt_printf(out, ": %u [", e->nr_devs);
-	for (i = 0; i < e->nr_devs; i++)
+	for (unsigned i = 0; i < e->nr_devs; i++)
 		prt_printf(out, i ? " %u" : "%u", e->devs[i]);
 	prt_printf(out, "]");
 }
@@ -55,15 +50,10 @@ static void bch2_replicas_entry_v0_to_text(struct printbuf *out,
 void bch2_replicas_entry_to_text(struct printbuf *out,
 				 struct bch_replicas_entry_v1 *e)
 {
-	unsigned i;
-
-	if (e->data_type < BCH_DATA_NR)
-		prt_printf(out, "%s", bch2_data_types[e->data_type]);
-	else
-		prt_printf(out, "(invalid data type %u)", e->data_type);
+	bch2_prt_data_type(out, e->data_type);
 
 	prt_printf(out, ": %u/%u [", e->nr_required, e->nr_devs);
-	for (i = 0; i < e->nr_devs; i++)
+	for (unsigned i = 0; i < e->nr_devs; i++)
 		prt_printf(out, i ? " %u" : "%u", e->devs[i]);
 	prt_printf(out, "]");
 }
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index a44a238bf8b55..a45354d2acde9 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -251,7 +251,7 @@ static void member_to_text(struct printbuf *out,
 	prt_printf(out, "Data allowed:");
 	prt_tab(out);
 	if (BCH_MEMBER_DATA_ALLOWED(&m))
-		prt_bitflags(out, bch2_data_types, BCH_MEMBER_DATA_ALLOWED(&m));
+		prt_bitflags(out, __bch2_data_types, BCH_MEMBER_DATA_ALLOWED(&m));
 	else
 		prt_printf(out, "(none)");
 	prt_newline(out);
@@ -259,7 +259,7 @@ static void member_to_text(struct printbuf *out,
 	prt_printf(out, "Has data:");
 	prt_tab(out);
 	if (data_have)
-		prt_bitflags(out, bch2_data_types, data_have);
+		prt_bitflags(out, __bch2_data_types, data_have);
 	else
 		prt_printf(out, "(none)");
 	prt_newline(out);
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 9dbc35940197f..a3ec21f229ed6 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1625,7 +1625,7 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
 	if (data) {
 		struct printbuf data_has = PRINTBUF;
 
-		prt_bitflags(&data_has, bch2_data_types, data);
+		prt_bitflags(&data_has, __bch2_data_types, data);
 		bch_err(ca, "Remove failed, still has data (%s)", data_has.buf);
 		printbuf_exit(&data_has);
 		ret = -EBUSY;
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index 8ed52319ff68d..434961e400e24 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -883,7 +883,7 @@ static void dev_io_done_to_text(struct printbuf *out, struct bch_dev *ca)
 
 		for (i = 1; i < BCH_DATA_NR; i++)
 			prt_printf(out, "%-12s:%12llu\n",
-			       bch2_data_types[i],
+			       bch2_data_type_str(i),
 			       percpu_u64_get(&ca->io_done->sectors[rw][i]) << 9);
 	}
 }
@@ -908,7 +908,7 @@ SHOW(bch2_dev)
 	}
 
 	if (attr == &sysfs_has_data) {
-		prt_bitflags(out, bch2_data_types, bch2_dev_has_data(c, ca));
+		prt_bitflags(out, __bch2_data_types, bch2_dev_has_data(c, ca));
 		prt_char(out, '\n');
 	}
 
-- 
GitLab


From 4f564f4f9fdd4d120ee04678b0c22e40cc8b6b47 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 6 Jan 2024 21:01:47 -0500
Subject: [PATCH 3087/4076] bcachefs: bch2_prt_compression_type()

bounds checking helper, since compression types are extensible

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/compress.h | 8 ++++++++
 fs/bcachefs/extents.c  | 6 +++---
 fs/bcachefs/opts.c     | 2 +-
 fs/bcachefs/opts.h     | 2 +-
 fs/bcachefs/sysfs.c    | 3 ++-
 5 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/compress.h b/fs/bcachefs/compress.h
index 607fd5e232c90..58c2eb45570ff 100644
--- a/fs/bcachefs/compress.h
+++ b/fs/bcachefs/compress.h
@@ -47,6 +47,14 @@ static inline enum bch_compression_type bch2_compression_opt_to_type(unsigned v)
 	return __bch2_compression_opt_to_type[bch2_compression_decode(v).type];
 }
 
+static inline void bch2_prt_compression_type(struct printbuf *out, enum bch_compression_type type)
+{
+	if (type < BCH_COMPRESSION_TYPE_NR)
+		prt_str(out, __bch2_compression_types[type]);
+	else
+		prt_printf(out, "(invalid compression type %u)", type);
+}
+
 int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *,
 				struct bch_extent_crc_unpacked *);
 int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *,
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 82ec056f4cdbb..edb1e32d77831 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -1018,12 +1018,12 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c,
 			struct bch_extent_crc_unpacked crc =
 				bch2_extent_crc_unpack(k.k, entry_to_crc(entry));
 
-			prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum %s compress %s",
+			prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum %s compress ",
 			       crc.compressed_size,
 			       crc.uncompressed_size,
 			       crc.offset, crc.nonce,
-			       bch2_csum_types[crc.csum_type],
-			       bch2_compression_types[crc.compression_type]);
+			       bch2_csum_types[crc.csum_type]);
+			bch2_prt_compression_type(out, crc.compression_type);
 			break;
 		}
 		case BCH_EXTENT_ENTRY_stripe_ptr: {
diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c
index 6aaf78de88457..b1ed0b9a20d35 100644
--- a/fs/bcachefs/opts.c
+++ b/fs/bcachefs/opts.c
@@ -52,7 +52,7 @@ const char * const bch2_csum_opts[] = {
 	NULL
 };
 
-const char * const bch2_compression_types[] = {
+const char * const __bch2_compression_types[] = {
 	BCH_COMPRESSION_TYPES()
 	NULL
 };
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 67e98e00e9372..7414c564b5d83 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -18,7 +18,7 @@ extern const char * const bch2_sb_compat[];
 extern const char * const __bch2_btree_ids[];
 extern const char * const bch2_csum_types[];
 extern const char * const bch2_csum_opts[];
-extern const char * const bch2_compression_types[];
+extern const char * const __bch2_compression_types[];
 extern const char * const bch2_compression_opts[];
 extern const char * const bch2_str_hash_types[];
 extern const char * const bch2_str_hash_opts[];
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index 434961e400e24..553190d719dfc 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -21,6 +21,7 @@
 #include "btree_gc.h"
 #include "buckets.h"
 #include "clock.h"
+#include "compress.h"
 #include "disk_groups.h"
 #include "ec.h"
 #include "inode.h"
@@ -330,7 +331,7 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c
 	prt_newline(out);
 
 	for (unsigned i = 0; i < ARRAY_SIZE(s); i++) {
-		prt_str(out, bch2_compression_types[i]);
+		bch2_prt_compression_type(out, i);
 		prt_tab(out);
 
 		prt_human_readable_u64(out, s[i].sectors_compressed << 9);
-- 
GitLab


From 8e7834a8831678d0825895d7f5a02ad0b29bbcde Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 17 Nov 2023 00:03:45 -0500
Subject: [PATCH 3088/4076] bcachefs: bch_fs_usage_base

Split out base filesystem usage into its own type; prep work for
breaking up bch2_trans_fs_usage_apply().

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_gc.c      | 12 ++++----
 fs/bcachefs/btree_types.h   |  3 ++
 fs/bcachefs/buckets.c       | 56 ++++++++++++++++++-------------------
 fs/bcachefs/buckets_types.h | 15 ++++------
 fs/bcachefs/inode.c         |  2 +-
 fs/bcachefs/recovery.c      |  2 +-
 fs/bcachefs/sb-clean.c      |  2 +-
 7 files changed, 45 insertions(+), 47 deletions(-)

diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 523e9b1069cd2..1102995643b13 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -1253,19 +1253,19 @@ static int bch2_gc_done(struct bch_fs *c,
 			bch2_acc_percpu_u64s((u64 __percpu *) c->usage_gc, nr);
 
 		copy_fs_field(fs_usage_hidden_wrong,
-			      hidden,		"hidden");
+			      b.hidden,		"hidden");
 		copy_fs_field(fs_usage_btree_wrong,
-			      btree,		"btree");
+			      b.btree,		"btree");
 
 		if (!metadata_only) {
 			copy_fs_field(fs_usage_data_wrong,
-				      data,	"data");
+				      b.data,	"data");
 			copy_fs_field(fs_usage_cached_wrong,
-				      cached,	"cached");
+				      b.cached,	"cached");
 			copy_fs_field(fs_usage_reserved_wrong,
-				      reserved,	"reserved");
+				      b.reserved,	"reserved");
 			copy_fs_field(fs_usage_nr_inodes_wrong,
-				      nr_inodes,"nr_inodes");
+				      b.nr_inodes,"nr_inodes");
 
 			for (i = 0; i < BCH_REPLICAS_MAX; i++)
 				copy_fs_field(fs_usage_persistent_reserved_wrong,
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index e46867536fa6a..e58e9a7f7b627 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -430,6 +430,9 @@ struct btree_trans {
 	struct journal_res	journal_res;
 	u64			*journal_seq;
 	struct disk_reservation *disk_res;
+
+	struct bch_fs_usage_base fs_usage_delta;
+
 	unsigned		journal_u64s;
 	unsigned		extra_disk_res; /* XXX kill */
 	struct replicas_delta_list *fs_usage_deltas;
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 5dc19363bb9fe..f8b9be9a84579 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -25,7 +25,7 @@
 
 #include <linux/preempt.h>
 
-static inline void fs_usage_data_type_to_base(struct bch_fs_usage *fs_usage,
+static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage,
 					      enum bch_data_type data_type,
 					      s64 sectors)
 {
@@ -54,20 +54,20 @@ void bch2_fs_usage_initialize(struct bch_fs *c)
 		bch2_fs_usage_acc_to_base(c, i);
 
 	for (unsigned i = 0; i < BCH_REPLICAS_MAX; i++)
-		usage->reserved += usage->persistent_reserved[i];
+		usage->b.reserved += usage->persistent_reserved[i];
 
 	for (unsigned i = 0; i < c->replicas.nr; i++) {
 		struct bch_replicas_entry_v1 *e =
 			cpu_replicas_entry(&c->replicas, i);
 
-		fs_usage_data_type_to_base(usage, e->data_type, usage->replicas[i]);
+		fs_usage_data_type_to_base(&usage->b, e->data_type, usage->replicas[i]);
 	}
 
 	for_each_member_device(c, ca) {
 		struct bch_dev_usage dev = bch2_dev_usage_read(ca);
 
-		usage->hidden += (dev.d[BCH_DATA_sb].buckets +
-				  dev.d[BCH_DATA_journal].buckets) *
+		usage->b.hidden += (dev.d[BCH_DATA_sb].buckets +
+				    dev.d[BCH_DATA_journal].buckets) *
 			ca->mi.bucket_size;
 	}
 
@@ -188,15 +188,15 @@ void bch2_fs_usage_to_text(struct printbuf *out,
 	prt_printf(out, "capacity:\t\t\t%llu\n", c->capacity);
 
 	prt_printf(out, "hidden:\t\t\t\t%llu\n",
-	       fs_usage->u.hidden);
+	       fs_usage->u.b.hidden);
 	prt_printf(out, "data:\t\t\t\t%llu\n",
-	       fs_usage->u.data);
+	       fs_usage->u.b.data);
 	prt_printf(out, "cached:\t\t\t\t%llu\n",
-	       fs_usage->u.cached);
+	       fs_usage->u.b.cached);
 	prt_printf(out, "reserved:\t\t\t%llu\n",
-	       fs_usage->u.reserved);
+	       fs_usage->u.b.reserved);
 	prt_printf(out, "nr_inodes:\t\t\t%llu\n",
-	       fs_usage->u.nr_inodes);
+	       fs_usage->u.b.nr_inodes);
 	prt_printf(out, "online reserved:\t\t%llu\n",
 	       fs_usage->online_reserved);
 
@@ -225,10 +225,10 @@ static u64 reserve_factor(u64 r)
 
 u64 bch2_fs_sectors_used(struct bch_fs *c, struct bch_fs_usage_online *fs_usage)
 {
-	return min(fs_usage->u.hidden +
-		   fs_usage->u.btree +
-		   fs_usage->u.data +
-		   reserve_factor(fs_usage->u.reserved +
+	return min(fs_usage->u.b.hidden +
+		   fs_usage->u.b.btree +
+		   fs_usage->u.b.data +
+		   reserve_factor(fs_usage->u.b.reserved +
 				  fs_usage->online_reserved),
 		   c->capacity);
 }
@@ -240,17 +240,17 @@ __bch2_fs_usage_read_short(struct bch_fs *c)
 	u64 data, reserved;
 
 	ret.capacity = c->capacity -
-		bch2_fs_usage_read_one(c, &c->usage_base->hidden);
+		bch2_fs_usage_read_one(c, &c->usage_base->b.hidden);
 
-	data		= bch2_fs_usage_read_one(c, &c->usage_base->data) +
-		bch2_fs_usage_read_one(c, &c->usage_base->btree);
-	reserved	= bch2_fs_usage_read_one(c, &c->usage_base->reserved) +
+	data		= bch2_fs_usage_read_one(c, &c->usage_base->b.data) +
+		bch2_fs_usage_read_one(c, &c->usage_base->b.btree);
+	reserved	= bch2_fs_usage_read_one(c, &c->usage_base->b.reserved) +
 		percpu_u64_get(c->online_reserved);
 
 	ret.used	= min(ret.capacity, data + reserve_factor(reserved));
 	ret.free	= ret.capacity - ret.used;
 
-	ret.nr_inodes	= bch2_fs_usage_read_one(c, &c->usage_base->nr_inodes);
+	ret.nr_inodes	= bch2_fs_usage_read_one(c, &c->usage_base->b.nr_inodes);
 
 	return ret;
 }
@@ -308,9 +308,9 @@ void bch2_dev_usage_update(struct bch_fs *c, struct bch_dev *ca,
 	fs_usage = fs_usage_ptr(c, journal_seq, gc);
 
 	if (data_type_is_hidden(old->data_type))
-		fs_usage->hidden -= ca->mi.bucket_size;
+		fs_usage->b.hidden -= ca->mi.bucket_size;
 	if (data_type_is_hidden(new->data_type))
-		fs_usage->hidden += ca->mi.bucket_size;
+		fs_usage->b.hidden += ca->mi.bucket_size;
 
 	u = dev_usage_ptr(ca, journal_seq, gc);
 
@@ -359,7 +359,7 @@ static inline int __update_replicas(struct bch_fs *c,
 	if (idx < 0)
 		return -1;
 
-	fs_usage_data_type_to_base(fs_usage, r->data_type, sectors);
+	fs_usage_data_type_to_base(&fs_usage->b, r->data_type, sectors);
 	fs_usage->replicas[idx]		+= sectors;
 	return 0;
 }
@@ -394,7 +394,7 @@ int bch2_update_replicas(struct bch_fs *c, struct bkey_s_c k,
 
 	preempt_disable();
 	fs_usage = fs_usage_ptr(c, journal_seq, gc);
-	fs_usage_data_type_to_base(fs_usage, r->data_type, sectors);
+	fs_usage_data_type_to_base(&fs_usage->b, r->data_type, sectors);
 	fs_usage->replicas[idx]		+= sectors;
 	preempt_enable();
 err:
@@ -677,11 +677,11 @@ void bch2_trans_fs_usage_revert(struct btree_trans *trans,
 		BUG_ON(__update_replicas(c, dst, &d->r, -d->delta));
 	}
 
-	dst->nr_inodes -= deltas->nr_inodes;
+	dst->b.nr_inodes -= deltas->nr_inodes;
 
 	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
 		added				-= deltas->persistent_reserved[i];
-		dst->reserved			-= deltas->persistent_reserved[i];
+		dst->b.reserved			-= deltas->persistent_reserved[i];
 		dst->persistent_reserved[i]	-= deltas->persistent_reserved[i];
 	}
 
@@ -723,11 +723,11 @@ int bch2_trans_fs_usage_apply(struct btree_trans *trans,
 			goto need_mark;
 	}
 
-	dst->nr_inodes += deltas->nr_inodes;
+	dst->b.nr_inodes += deltas->nr_inodes;
 
 	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
 		added				+= deltas->persistent_reserved[i];
-		dst->reserved			+= deltas->persistent_reserved[i];
+		dst->b.reserved			+= deltas->persistent_reserved[i];
 		dst->persistent_reserved[i]	+= deltas->persistent_reserved[i];
 	}
 
@@ -1084,7 +1084,7 @@ static int __trigger_reservation(struct btree_trans *trans,
 		struct bch_fs_usage *fs_usage = this_cpu_ptr(c->usage_gc);
 
 		replicas = min(replicas, ARRAY_SIZE(fs_usage->persistent_reserved));
-		fs_usage->reserved				+= sectors;
+		fs_usage->b.reserved				+= sectors;
 		fs_usage->persistent_reserved[replicas - 1]	+= sectors;
 
 		preempt_enable();
diff --git a/fs/bcachefs/buckets_types.h b/fs/bcachefs/buckets_types.h
index 783f71017204c..6a31740222a71 100644
--- a/fs/bcachefs/buckets_types.h
+++ b/fs/bcachefs/buckets_types.h
@@ -45,23 +45,18 @@ struct bch_dev_usage {
 	}			d[BCH_DATA_NR];
 };
 
-struct bch_fs_usage {
-	/* all fields are in units of 512 byte sectors: */
+struct bch_fs_usage_base {
 	u64			hidden;
 	u64			btree;
 	u64			data;
 	u64			cached;
 	u64			reserved;
 	u64			nr_inodes;
+};
 
-	/* XXX: add stats for compression ratio */
-#if 0
-	u64			uncompressed;
-	u64			compressed;
-#endif
-
-	/* broken out: */
-
+struct bch_fs_usage {
+	/* all fields are in units of 512 byte sectors: */
+	struct bch_fs_usage_base b;
 	u64			persistent_reserved[BCH_REPLICAS_MAX];
 	u64			replicas[];
 };
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 51a06324b21d3..18a8d141b4437 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -597,7 +597,7 @@ int bch2_trigger_inode(struct btree_trans *trans,
 		struct bch_fs *c = trans->c;
 
 		percpu_down_read(&c->mark_lock);
-		this_cpu_add(c->usage_gc->nr_inodes, nr);
+		this_cpu_add(c->usage_gc->b.nr_inodes, nr);
 		percpu_up_read(&c->mark_lock);
 	}
 
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 725214605a050..9127d0e3ca2f6 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -280,7 +280,7 @@ static int journal_replay_entry_early(struct bch_fs *c,
 					le64_to_cpu(u->v);
 			break;
 		case BCH_FS_USAGE_inodes:
-			c->usage_base->nr_inodes = le64_to_cpu(u->v);
+			c->usage_base->b.nr_inodes = le64_to_cpu(u->v);
 			break;
 		case BCH_FS_USAGE_key_version:
 			atomic64_set(&c->key_version,
diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c
index 9632f36f5f318..b6bf0ebe7e840 100644
--- a/fs/bcachefs/sb-clean.c
+++ b/fs/bcachefs/sb-clean.c
@@ -207,7 +207,7 @@ void bch2_journal_super_entries_add_common(struct bch_fs *c,
 
 		u->entry.type	= BCH_JSET_ENTRY_usage;
 		u->entry.btree_id = BCH_FS_USAGE_inodes;
-		u->v		= cpu_to_le64(c->usage_base->nr_inodes);
+		u->v		= cpu_to_le64(c->usage_base->b.nr_inodes);
 	}
 
 	{
-- 
GitLab


From 5b14ce35af901853e91e186f34e71f31b08b4e0a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 11 Nov 2023 15:08:36 -0500
Subject: [PATCH 3089/4076] bcachefs: bch2_trans_account_disk_usage_change()

The disk space accounting rewrite is splitting out accounting for each
replicas set - those are moving to btree keys, instead of percpu
counters.

This breaks bch2_trans_fs_usage_apply() up, splitting out the part we
will still need.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_trans_commit.c |  5 +++
 fs/bcachefs/buckets.c            | 70 +++++++++++++++++++-------------
 fs/bcachefs/buckets.h            |  2 +
 3 files changed, 48 insertions(+), 29 deletions(-)

diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index e3a82c33912b9..ab00d202361eb 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -675,6 +675,9 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 	    bch2_trans_fs_usage_apply(trans, trans->fs_usage_deltas))
 		return -BCH_ERR_btree_insert_need_mark_replicas;
 
+	/* XXX: we only want to run this if deltas are nonzero */
+	bch2_trans_account_disk_usage_change(trans);
+
 	h = trans->hooks;
 	while (h) {
 		ret = h->fn(trans, h);
@@ -989,6 +992,8 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 	    !trans->journal_entries_u64s)
 		goto out_reset;
 
+	memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta));
+
 	ret = bch2_trans_commit_run_triggers(trans);
 	if (ret)
 		goto out_reset;
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index f8b9be9a84579..54f7826ac4987 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -694,48 +694,25 @@ void bch2_trans_fs_usage_revert(struct btree_trans *trans,
 	percpu_up_read(&c->mark_lock);
 }
 
-int bch2_trans_fs_usage_apply(struct btree_trans *trans,
-			      struct replicas_delta_list *deltas)
+void bch2_trans_account_disk_usage_change(struct btree_trans *trans)
 {
 	struct bch_fs *c = trans->c;
+	u64 disk_res_sectors = trans->disk_res ? trans->disk_res->sectors : 0;
 	static int warned_disk_usage = 0;
 	bool warn = false;
-	u64 disk_res_sectors = trans->disk_res ? trans->disk_res->sectors : 0;
-	struct replicas_delta *d, *d2;
-	struct replicas_delta *top = (void *) deltas->d + deltas->used;
-	struct bch_fs_usage *dst;
-	s64 added = 0, should_not_have_added;
-	unsigned i;
 
 	percpu_down_read(&c->mark_lock);
 	preempt_disable();
-	dst = fs_usage_ptr(c, trans->journal_res.seq, false);
-
-	for (d = deltas->d; d != top; d = replicas_delta_next(d)) {
-		switch (d->r.data_type) {
-		case BCH_DATA_btree:
-		case BCH_DATA_user:
-		case BCH_DATA_parity:
-			added += d->delta;
-		}
-
-		if (__update_replicas(c, dst, &d->r, d->delta))
-			goto need_mark;
-	}
+	struct bch_fs_usage_base *dst = &fs_usage_ptr(c, trans->journal_res.seq, false)->b;
+	struct bch_fs_usage_base *src = &trans->fs_usage_delta;
 
-	dst->b.nr_inodes += deltas->nr_inodes;
-
-	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
-		added				+= deltas->persistent_reserved[i];
-		dst->b.reserved			+= deltas->persistent_reserved[i];
-		dst->persistent_reserved[i]	+= deltas->persistent_reserved[i];
-	}
+	s64 added = src->btree + src->data + src->reserved;
 
 	/*
 	 * Not allowed to reduce sectors_available except by getting a
 	 * reservation:
 	 */
-	should_not_have_added = added - (s64) disk_res_sectors;
+	s64 should_not_have_added = added - (s64) disk_res_sectors;
 	if (unlikely(should_not_have_added > 0)) {
 		u64 old, new, v = atomic64_read(&c->sectors_available);
 
@@ -754,6 +731,13 @@ int bch2_trans_fs_usage_apply(struct btree_trans *trans,
 		this_cpu_sub(*c->online_reserved, added);
 	}
 
+	dst->hidden	+= src->hidden;
+	dst->btree	+= src->btree;
+	dst->data	+= src->data;
+	dst->cached	+= src->cached;
+	dst->reserved	+= src->reserved;
+	dst->nr_inodes	+= src->nr_inodes;
+
 	preempt_enable();
 	percpu_up_read(&c->mark_lock);
 
@@ -761,6 +745,34 @@ int bch2_trans_fs_usage_apply(struct btree_trans *trans,
 		bch2_trans_inconsistent(trans,
 					"disk usage increased %lli more than %llu sectors reserved)",
 					should_not_have_added, disk_res_sectors);
+}
+
+int bch2_trans_fs_usage_apply(struct btree_trans *trans,
+			      struct replicas_delta_list *deltas)
+{
+	struct bch_fs *c = trans->c;
+	struct replicas_delta *d, *d2;
+	struct replicas_delta *top = (void *) deltas->d + deltas->used;
+	struct bch_fs_usage *dst;
+	unsigned i;
+
+	percpu_down_read(&c->mark_lock);
+	preempt_disable();
+	dst = fs_usage_ptr(c, trans->journal_res.seq, false);
+
+	for (d = deltas->d; d != top; d = replicas_delta_next(d))
+		if (__update_replicas(c, dst, &d->r, d->delta))
+			goto need_mark;
+
+	dst->b.nr_inodes += deltas->nr_inodes;
+
+	for (i = 0; i < BCH_REPLICAS_MAX; i++) {
+		dst->b.reserved			+= deltas->persistent_reserved[i];
+		dst->persistent_reserved[i]	+= deltas->persistent_reserved[i];
+	}
+
+	preempt_enable();
+	percpu_up_read(&c->mark_lock);
 	return 0;
 need_mark:
 	/* revert changes: */
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 2b1e907f2acad..6387e039f7897 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -356,6 +356,8 @@ int bch2_trigger_reservation(struct btree_trans *, enum btree_id, unsigned,
 	ret;											\
 })
 
+void bch2_trans_account_disk_usage_change(struct btree_trans *);
+
 void bch2_trans_fs_usage_revert(struct btree_trans *, struct replicas_delta_list *);
 int bch2_trans_fs_usage_apply(struct btree_trans *, struct replicas_delta_list *);
 
-- 
GitLab


From 57f2d2097603fea102330e8cfe6be4a8db24809e Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 10 Jan 2024 23:47:04 -0500
Subject: [PATCH 3090/4076] bcachefs: Reduce would_deadlock restarts

We don't have to take locks in any particular ordering - we'll make
forward progress just fine - but if we try to stick to an ordering, it
can help to avoid excessive would_deadlock transaction restarts.

This tweaks the reflink path to take extents btree locks in the right
order.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/reflink.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index 6070109174210..98255aa64e226 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -486,6 +486,13 @@ s64 bch2_remap_range(struct bch_fs *c,
 
 		bch2_btree_iter_set_snapshot(&dst_iter, dst_snapshot);
 
+		if (dst_inum.inum < src_inum.inum) {
+			/* Avoid some lock cycle transaction restarts */
+			ret = bch2_btree_iter_traverse(&dst_iter);
+			if (ret)
+				continue;
+		}
+
 		dst_done = dst_iter.pos.offset - dst_start.offset;
 		src_want = POS(src_start.inode, src_start.offset + dst_done);
 		bch2_btree_iter_set_pos(&src_iter, src_want);
-- 
GitLab


From a54d51fb2dfb846aedf3751af501e9688db447f5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 18 Jan 2024 20:17:49 +0000
Subject: [PATCH 3091/4076] udp: fix busy polling

Generic sk_busy_loop_end() only looks at sk->sk_receive_queue
for presence of packets.

Problem is that for UDP sockets after blamed commit, some packets
could be present in another queue: udp_sk(sk)->reader_queue

In some cases, a busy poller could spin until timeout expiration,
even if some packets are available in udp_sk(sk)->reader_queue.

v3: - make sk_busy_loop_end() nicer (Willem)

v2: - add a READ_ONCE(sk->sk_family) in sk_is_inet() to avoid KCSAN splats.
    - add a sk_is_inet() check in sk_is_udp() (Willem feedback)
    - add a sk_is_inet() check in sk_is_tcp().

Fixes: 2276f58ac589 ("udp: use a separate rx queue for packet reception")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skmsg.h   |  6 ------
 include/net/inet_sock.h |  5 -----
 include/net/sock.h      | 18 +++++++++++++++++-
 net/core/sock.c         | 11 +++++++++--
 4 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 888a4b217829f..e65ec3fd27998 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -505,12 +505,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
 	return !!psock->saved_data_ready;
 }
 
-static inline bool sk_is_udp(const struct sock *sk)
-{
-	return sk->sk_type == SOCK_DGRAM &&
-	       sk->sk_protocol == IPPROTO_UDP;
-}
-
 #if IS_ENABLED(CONFIG_NET_SOCK_MSG)
 
 #define BPF_F_STRPARSER	(1UL << 1)
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index aa86453f6b9ba..d94c242eb3ed2 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -307,11 +307,6 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet)
 #define inet_assign_bit(nr, sk, val)		\
 	assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val)
 
-static inline bool sk_is_inet(struct sock *sk)
-{
-	return sk->sk_family == AF_INET || sk->sk_family == AF_INET6;
-}
-
 /**
  * sk_to_full_sk - Access to a full socket
  * @sk: pointer to a socket
diff --git a/include/net/sock.h b/include/net/sock.h
index a7f815c7cfdfd..54ca8dcbfb433 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2765,9 +2765,25 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
 			   &skb_shinfo(skb)->tskey);
 }
 
+static inline bool sk_is_inet(const struct sock *sk)
+{
+	int family = READ_ONCE(sk->sk_family);
+
+	return family == AF_INET || family == AF_INET6;
+}
+
 static inline bool sk_is_tcp(const struct sock *sk)
 {
-	return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP;
+	return sk_is_inet(sk) &&
+	       sk->sk_type == SOCK_STREAM &&
+	       sk->sk_protocol == IPPROTO_TCP;
+}
+
+static inline bool sk_is_udp(const struct sock *sk)
+{
+	return sk_is_inet(sk) &&
+	       sk->sk_type == SOCK_DGRAM &&
+	       sk->sk_protocol == IPPROTO_UDP;
 }
 
 static inline bool sk_is_stream_unix(const struct sock *sk)
diff --git a/net/core/sock.c b/net/core/sock.c
index 158dbdebce6a3..0a7f46c37f0cf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -107,6 +107,7 @@
 #include <linux/interrupt.h>
 #include <linux/poll.h>
 #include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
@@ -4144,8 +4145,14 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
 {
 	struct sock *sk = p;
 
-	return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
-	       sk_busy_loop_timeout(sk, start_time);
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
+		return true;
+
+	if (sk_is_udp(sk) &&
+	    !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
+		return true;
+
+	return sk_busy_loop_timeout(sk, start_time);
 }
 EXPORT_SYMBOL(sk_busy_loop_end);
 #endif /* CONFIG_NET_RX_BUSY_POLL */
-- 
GitLab


From 359724fa3ab79fbe9f42c6263cddc2afae32eef3 Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Thu, 18 Jan 2024 21:50:40 +0100
Subject: [PATCH 3092/4076] idpf: distinguish vports by the dev_port attribute

idpf registers multiple netdevs (virtual ports) for one PCI function,
but it does not provide a way for userspace to distinguish them with
sysfs attributes. Per Documentation/ABI/testing/sysfs-class-net, it is
a bug not to set dev_port for independent ports on the same PCI bus,
device and function.

Without dev_port set, systemd-udevd's default naming policy attempts
to assign the same name ("ens2f0") to all four idpf netdevs on my test
system and obviously fails, leaving three of them with the initial
eth<N> name.

With this patch, systemd-udevd is able to assign unique names to the
netdevs (e.g. "ens2f0", "ens2f0d1", "ens2f0d2", "ens2f0d3").

The Intel-provided out-of-tree idpf driver already sets dev_port. In
this patch I chose to do it in the same place in the idpf_cfg_netdev
function.

Fixes: 0fe45467a104 ("idpf: add create vport and netdev configuration")
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 5fea2fd957eb3..58179bd733ff0 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -783,6 +783,8 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	/* setup watchdog timeout value to be 5 second */
 	netdev->watchdog_timeo = 5 * HZ;
 
+	netdev->dev_port = idx;
+
 	/* configure default MTU size */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = vport->max_mtu;
-- 
GitLab


From 0124f42da70c513dc371b73688663c54e5a9666f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 14:12:43 -0500
Subject: [PATCH 3093/4076] bcachefs: Don't pass memcmp() as a pointer

Some (buggy!) compilers have issues with this.

Fixes: https://github.com/koverstreet/bcachefs/issues/625
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/replicas.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c
index 1c3900da4c770..cc2672c120312 100644
--- a/fs/bcachefs/replicas.c
+++ b/fs/bcachefs/replicas.c
@@ -9,6 +9,12 @@
 static int bch2_cpu_replicas_to_sb_replicas(struct bch_fs *,
 					    struct bch_replicas_cpu *);
 
+/* Some (buggy!) compilers don't allow memcmp to be passed as a pointer */
+static int bch2_memcmp(const void *l, const void *r, size_t size)
+{
+	return memcmp(l, r, size);
+}
+
 /* Replicas tracking - in memory: */
 
 static void verify_replicas_entry(struct bch_replicas_entry_v1 *e)
@@ -33,7 +39,7 @@ void bch2_replicas_entry_sort(struct bch_replicas_entry_v1 *e)
 
 static void bch2_cpu_replicas_sort(struct bch_replicas_cpu *r)
 {
-	eytzinger0_sort(r->entries, r->nr, r->entry_size, memcmp, NULL);
+	eytzinger0_sort(r->entries, r->nr, r->entry_size, bch2_memcmp, NULL);
 }
 
 static void bch2_replicas_entry_v0_to_text(struct printbuf *out,
@@ -821,7 +827,7 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r,
 	sort_cmp_size(cpu_r->entries,
 		      cpu_r->nr,
 		      cpu_r->entry_size,
-		      memcmp, NULL);
+		      bch2_memcmp, NULL);
 
 	for (i = 0; i < cpu_r->nr; i++) {
 		struct bch_replicas_entry_v1 *e =
-- 
GitLab


From 741c1d3ec1a4a91d0bf18f200e2f0f8bed1ee7e9 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 14:15:03 -0500
Subject: [PATCH 3094/4076] bcachefs: Add .val_to_text() for KEY_TYPE_cookie

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bkey_methods.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c
index 761f5e33b1e69..5e52684764eb1 100644
--- a/fs/bcachefs/bkey_methods.c
+++ b/fs/bcachefs/bkey_methods.c
@@ -63,8 +63,17 @@ static int key_type_cookie_invalid(struct bch_fs *c, struct bkey_s_c k,
 	return 0;
 }
 
+static void key_type_cookie_to_text(struct printbuf *out, struct bch_fs *c,
+				    struct bkey_s_c k)
+{
+	struct bkey_s_c_cookie ck = bkey_s_c_to_cookie(k);
+
+	prt_printf(out, "%llu", le64_to_cpu(ck.v->cookie));
+}
+
 #define bch2_bkey_ops_cookie ((struct bkey_ops) {	\
 	.key_invalid	= key_type_cookie_invalid,	\
+	.val_to_text	= key_type_cookie_to_text,	\
 	.min_val_size	= 8,				\
 })
 
-- 
GitLab


From d92b83f592d810aded2e5f90db5f560cc8cf577b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 14:15:26 -0500
Subject: [PATCH 3095/4076] bcachefs: bch2_kthread_io_clock_wait() no longer
 sleeps until full amount

Drop t he loop in bch2_kthread_io_clock_wait(): this allows the code
that uses it to be woken up for other reasons, and fixes a bug where
rebalance wouldn't wake up when a scan was requested.

This raises the possibility of spurious wakeups, but callers should
always be able to handle that reasonably well.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/clock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/clock.c b/fs/bcachefs/clock.c
index f41889093a2c7..3636444511064 100644
--- a/fs/bcachefs/clock.c
+++ b/fs/bcachefs/clock.c
@@ -109,7 +109,7 @@ void bch2_kthread_io_clock_wait(struct io_clock *clock,
 	if (cpu_timeout != MAX_SCHEDULE_TIMEOUT)
 		mod_timer(&wait.cpu_timer, cpu_timeout + jiffies);
 
-	while (1) {
+	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (kthread && kthread_should_stop())
 			break;
@@ -119,7 +119,7 @@ void bch2_kthread_io_clock_wait(struct io_clock *clock,
 
 		schedule();
 		try_to_freeze();
-	}
+	} while (0);
 
 	__set_current_state(TASK_RUNNING);
 	del_timer_sync(&wait.cpu_timer);
-- 
GitLab


From fa3185af43dce43a23df78c122bef860bcd4bf40 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 15:04:40 -0500
Subject: [PATCH 3096/4076] bcachefs: Re-add move_extent_write tracepoint

It appears this was accidentally deleted at some point - also, do a bit
of cleanup.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/move.c  |  9 +++++++++
 fs/bcachefs/trace.h | 34 +++++++++++-----------------------
 2 files changed, 20 insertions(+), 23 deletions(-)

diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index a9e0920b34f32..7a66706e4dcef 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -111,6 +111,15 @@ static void move_write(struct moving_io *io)
 		return;
 	}
 
+	if (trace_move_extent_write_enabled()) {
+		struct bch_fs *c = io->write.op.c;
+		struct printbuf buf = PRINTBUF;
+
+		bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(io->write.k.k));
+		trace_move_extent_write(c, buf.buf);
+		printbuf_exit(&buf);
+	}
+
 	closure_get(&io->write.ctxt->cl);
 	atomic_add(io->write_sectors, &io->write.ctxt->write_sectors);
 	atomic_inc(&io->write.ctxt->write_ios);
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index c94876b3bb06e..8292efc3289ba 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -827,40 +827,28 @@ TRACE_EVENT(bucket_evacuate,
 );
 
 DEFINE_EVENT(fs_str, move_extent,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(fs_str, move_extent_read,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(fs_str, move_extent_write,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(fs_str, move_extent_finish,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
-TRACE_EVENT(move_extent_fail,
-	TP_PROTO(struct bch_fs *c, const char *msg),
-	TP_ARGS(c, msg),
-
-	TP_STRUCT__entry(
-		__field(dev_t,		dev			)
-		__string(msg,		msg			)
-	),
-
-	TP_fast_assign(
-		__entry->dev		= c->dev;
-		__assign_str(msg, msg);
-	),
-
-	TP_printk("%d:%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(msg))
+DEFINE_EVENT(fs_str, move_extent_fail,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(fs_str, move_extent_start_fail,
-- 
GitLab


From ef740a1e2939376ea4cc11cc8b923214dc1f4a41 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 15:06:43 -0500
Subject: [PATCH 3097/4076] bcachefs: Add missing bch2_moving_ctxt_flush_all()

This fixes a bug with rebalance IOs getting stuck with reads completed,
but writes never being issued.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/rebalance.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index 95f46cb3b5bdf..a729682d653d6 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -371,6 +371,7 @@ static int do_rebalance(struct moving_context *ctxt)
 	    !kthread_should_stop() &&
 	    !atomic64_read(&r->work_stats.sectors_seen) &&
 	    !atomic64_read(&r->scan_stats.sectors_seen)) {
+		bch2_moving_ctxt_flush_all(ctxt);
 		bch2_trans_unlock_long(trans);
 		rebalance_wait(c);
 	}
-- 
GitLab


From 189c176c5dd324531d4cb23f172b1761e65bb0ed Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 15:33:39 -0500
Subject: [PATCH 3098/4076] bcachefs: Improve move_extent tracepoint

Also print out the data_opts, so that we can see what specifically is
being done to an extent.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bkey.c      |  2 +-
 fs/bcachefs/move.c      | 40 ++++++++++++++++++++++++++++++++++++++--
 fs/bcachefs/rebalance.c |  3 +--
 fs/bcachefs/util.c      |  7 ++++++-
 fs/bcachefs/util.h      |  3 ++-
 5 files changed, 48 insertions(+), 7 deletions(-)

diff --git a/fs/bcachefs/bkey.c b/fs/bcachefs/bkey.c
index abdb05507d162..76e79a15ba08f 100644
--- a/fs/bcachefs/bkey.c
+++ b/fs/bcachefs/bkey.c
@@ -33,7 +33,7 @@ void bch2_bkey_packed_to_binary_text(struct printbuf *out,
 			next_key_bits -= 64;
 		}
 
-		bch2_prt_u64_binary(out, v, min(word_bits, nr_key_bits));
+		bch2_prt_u64_base2_nbits(out, v, min(word_bits, nr_key_bits));
 
 		if (!next_key_bits)
 			break;
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 7a66706e4dcef..2e083daedfb2b 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -9,6 +9,7 @@
 #include "btree_update.h"
 #include "btree_update_interior.h"
 #include "btree_write_buffer.h"
+#include "compress.h"
 #include "disk_groups.h"
 #include "ec.h"
 #include "errcode.h"
@@ -34,12 +35,46 @@ const char * const bch2_data_ops_strs[] = {
 	NULL
 };
 
-static void trace_move_extent2(struct bch_fs *c, struct bkey_s_c k)
+static void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c,
+					  struct bch_io_opts *io_opts,
+					  struct data_update_opts *data_opts)
+{
+	printbuf_tabstop_push(out, 20);
+	prt_str(out, "rewrite ptrs:");
+	prt_tab(out);
+	bch2_prt_u64_base2(out, data_opts->rewrite_ptrs);
+	prt_newline(out);
+
+	prt_str(out, "kill ptrs: ");
+	prt_tab(out);
+	bch2_prt_u64_base2(out, data_opts->kill_ptrs);
+	prt_newline(out);
+
+	prt_str(out, "target: ");
+	prt_tab(out);
+	bch2_target_to_text(out, c, data_opts->target);
+	prt_newline(out);
+
+	prt_str(out, "compression: ");
+	prt_tab(out);
+	bch2_compression_opt_to_text(out, io_opts->background_compression ?: io_opts->compression);
+	prt_newline(out);
+
+	prt_str(out, "extra replicas: ");
+	prt_tab(out);
+	prt_u64(out, data_opts->extra_replicas);
+}
+
+static void trace_move_extent2(struct bch_fs *c, struct bkey_s_c k,
+			       struct bch_io_opts *io_opts,
+			       struct data_update_opts *data_opts)
 {
 	if (trace_move_extent_enabled()) {
 		struct printbuf buf = PRINTBUF;
 
 		bch2_bkey_val_to_text(&buf, c, k);
+		prt_newline(&buf);
+		bch2_data_update_opts_to_text(&buf, c, io_opts, data_opts);
 		trace_move_extent(c, buf.buf);
 		printbuf_exit(&buf);
 	}
@@ -250,9 +285,10 @@ int bch2_move_extent(struct moving_context *ctxt,
 	unsigned sectors = k.k->size, pages;
 	int ret = -ENOMEM;
 
+	trace_move_extent2(c, k, &io_opts, &data_opts);
+
 	if (ctxt->stats)
 		ctxt->stats->pos = BBPOS(iter->btree_id, iter->pos);
-	trace_move_extent2(c, k);
 
 	bch2_data_update_opts_normalize(k, &data_opts);
 
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index a729682d653d6..f24106dee21d6 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -177,8 +177,7 @@ static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans,
 		prt_str(&buf, "target=");
 		bch2_target_to_text(&buf, c, r->target);
 		prt_str(&buf, " compression=");
-		struct bch_compression_opt opt = __bch2_compression_decode(r->compression);
-		prt_str(&buf, bch2_compression_opts[opt.type]);
+		bch2_compression_opt_to_text(&buf, r->compression);
 		prt_str(&buf, " ");
 		bch2_bkey_val_to_text(&buf, c, k);
 
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index f927c8a19e241..a135136adeee3 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -241,12 +241,17 @@ bool bch2_is_zero(const void *_p, size_t n)
 	return true;
 }
 
-void bch2_prt_u64_binary(struct printbuf *out, u64 v, unsigned nr_bits)
+void bch2_prt_u64_base2_nbits(struct printbuf *out, u64 v, unsigned nr_bits)
 {
 	while (nr_bits)
 		prt_char(out, '0' + ((v >> --nr_bits) & 1));
 }
 
+void bch2_prt_u64_base2(struct printbuf *out, u64 v)
+{
+	bch2_prt_u64_base2_nbits(out, v, fls64(v) ?: 1);
+}
+
 void bch2_print_string_as_lines(const char *prefix, const char *lines)
 {
 	const char *p;
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index c75fc31915d39..df67bf55fe2bc 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -342,7 +342,8 @@ bool bch2_is_zero(const void *, size_t);
 
 u64 bch2_read_flag_list(char *, const char * const[]);
 
-void bch2_prt_u64_binary(struct printbuf *, u64, unsigned);
+void bch2_prt_u64_base2_nbits(struct printbuf *, u64, unsigned);
+void bch2_prt_u64_base2(struct printbuf *, u64);
 
 void bch2_print_string_as_lines(const char *prefix, const char *lines);
 
-- 
GitLab


From a6548c8b5eb541e77ffcf497e8761f34172ff828 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 17:56:22 -0500
Subject: [PATCH 3099/4076] bcachefs: Avoid flushing the journal in the discard
 path

When issuing discards, we may need to flush the journal if there's too
many buckets that can't be discarded until a journal flush.

But the heuristic was bad; we should be comparing the number of buckets
that need to flushes against the number of free buckets, not the number
of buckets we saw.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/alloc_background.c | 60 +++++++++++++++++++++++-----------
 1 file changed, 41 insertions(+), 19 deletions(-)

diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index 614da759226b5..10704f2d3af53 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -1604,13 +1604,36 @@ int bch2_check_alloc_to_lru_refs(struct bch_fs *c)
 	return ret;
 }
 
+struct discard_buckets_state {
+	u64		seen;
+	u64		open;
+	u64		need_journal_commit;
+	u64		discarded;
+	struct bch_dev	*ca;
+	u64		need_journal_commit_this_dev;
+};
+
+static void discard_buckets_next_dev(struct bch_fs *c, struct discard_buckets_state *s, struct bch_dev *ca)
+{
+	if (s->ca == ca)
+		return;
+
+	if (s->ca && s->need_journal_commit_this_dev >
+	    bch2_dev_usage_read(s->ca).d[BCH_DATA_free].buckets)
+		bch2_journal_flush_async(&c->journal, NULL);
+
+	if (s->ca)
+		percpu_ref_put(&s->ca->ref);
+	if (ca)
+		percpu_ref_get(&ca->ref);
+	s->ca = ca;
+	s->need_journal_commit_this_dev = 0;
+}
+
 static int bch2_discard_one_bucket(struct btree_trans *trans,
 				   struct btree_iter *need_discard_iter,
 				   struct bpos *discard_pos_done,
-				   u64 *seen,
-				   u64 *open,
-				   u64 *need_journal_commit,
-				   u64 *discarded)
+				   struct discard_buckets_state *s)
 {
 	struct bch_fs *c = trans->c;
 	struct bpos pos = need_discard_iter->pos;
@@ -1622,20 +1645,24 @@ static int bch2_discard_one_bucket(struct btree_trans *trans,
 	int ret = 0;
 
 	ca = bch_dev_bkey_exists(c, pos.inode);
+
 	if (!percpu_ref_tryget(&ca->io_ref)) {
 		bch2_btree_iter_set_pos(need_discard_iter, POS(pos.inode + 1, 0));
 		return 0;
 	}
 
+	discard_buckets_next_dev(c, s, ca);
+
 	if (bch2_bucket_is_open_safe(c, pos.inode, pos.offset)) {
-		(*open)++;
+		s->open++;
 		goto out;
 	}
 
 	if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal,
 			c->journal.flushed_seq_ondisk,
 			pos.inode, pos.offset)) {
-		(*need_journal_commit)++;
+		s->need_journal_commit++;
+		s->need_journal_commit_this_dev++;
 		goto out;
 	}
 
@@ -1711,9 +1738,9 @@ write:
 		goto out;
 
 	count_event(c, bucket_discard);
-	(*discarded)++;
+	s->discarded++;
 out:
-	(*seen)++;
+	s->seen++;
 	bch2_trans_iter_exit(trans, &iter);
 	percpu_ref_put(&ca->io_ref);
 	printbuf_exit(&buf);
@@ -1723,7 +1750,7 @@ out:
 static void bch2_do_discards_work(struct work_struct *work)
 {
 	struct bch_fs *c = container_of(work, struct bch_fs, discard_work);
-	u64 seen = 0, open = 0, need_journal_commit = 0, discarded = 0;
+	struct discard_buckets_state s = {};
 	struct bpos discard_pos_done = POS_MAX;
 	int ret;
 
@@ -1735,19 +1762,14 @@ static void bch2_do_discards_work(struct work_struct *work)
 	ret = bch2_trans_run(c,
 		for_each_btree_key(trans, iter,
 				   BTREE_ID_need_discard, POS_MIN, 0, k,
-			bch2_discard_one_bucket(trans, &iter, &discard_pos_done,
-						&seen,
-						&open,
-						&need_journal_commit,
-						&discarded)));
-
-	if (need_journal_commit * 2 > seen)
-		bch2_journal_flush_async(&c->journal, NULL);
+			bch2_discard_one_bucket(trans, &iter, &discard_pos_done, &s)));
 
-	bch2_write_ref_put(c, BCH_WRITE_REF_discard);
+	discard_buckets_next_dev(c, &s, NULL);
 
-	trace_discard_buckets(c, seen, open, need_journal_commit, discarded,
+	trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded,
 			      bch2_err_str(ret));
+
+	bch2_write_ref_put(c, BCH_WRITE_REF_discard);
 }
 
 void bch2_do_discards(struct bch_fs *c)
-- 
GitLab


From 4ae016607b907e69ed817ce14158adffb9b47978 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 17:57:44 -0500
Subject: [PATCH 3100/4076] bcachefs: Print size of superblock with space
 allocated

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super-io.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index 55926b81eede6..9564d2d9ccaef 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -1320,7 +1320,9 @@ void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb,
 
 	prt_printf(out, "Superblock size:");
 	prt_tab(out);
-	prt_printf(out, "%zu", vstruct_bytes(sb));
+	prt_units_u64(out, vstruct_bytes(sb));
+	prt_str(out, "/");
+	prt_units_u64(out, 512ULL << sb->layout.sb_max_size_bits);
 	prt_newline(out);
 
 	prt_printf(out, "Clean:");
-- 
GitLab


From e6a2566f7a009b644fd84a43a6c1e3a53bb0bf00 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 17:59:51 -0500
Subject: [PATCH 3101/4076] bcachefs: Better journal tracepoints

Factor out bch2_journal_bufs_to_text(), and use it in the
journal_entry_full() tracepoint; when we can't get a journal reservation
we need to know the outstanding journal entry sizes to know if the
problem is due to excessive flushing.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/journal.c | 111 +++++++++++++++++++++++++++---------------
 fs/bcachefs/trace.h   |  28 +++--------
 2 files changed, 79 insertions(+), 60 deletions(-)

diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 8538ef34f62bc..d71d26e39521e 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -27,6 +27,47 @@ static const char * const bch2_journal_errors[] = {
 	NULL
 };
 
+static void bch2_journal_buf_to_text(struct printbuf *out, struct journal *j, u64 seq)
+{
+	union journal_res_state s = READ_ONCE(j->reservations);
+	unsigned i = seq & JOURNAL_BUF_MASK;
+	struct journal_buf *buf = j->buf + i;
+
+	prt_printf(out, "seq:");
+	prt_tab(out);
+	prt_printf(out, "%llu", seq);
+	prt_newline(out);
+	printbuf_indent_add(out, 2);
+
+	prt_printf(out, "refcount:");
+	prt_tab(out);
+	prt_printf(out, "%u", journal_state_count(s, i));
+	prt_newline(out);
+
+	prt_printf(out, "size:");
+	prt_tab(out);
+	prt_human_readable_u64(out, vstruct_bytes(buf->data));
+	prt_newline(out);
+
+	prt_printf(out, "expires");
+	prt_tab(out);
+	prt_printf(out, "%li jiffies", buf->expires - jiffies);
+	prt_newline(out);
+
+	printbuf_indent_sub(out, 2);
+}
+
+static void bch2_journal_bufs_to_text(struct printbuf *out, struct journal *j)
+{
+	if (!out->nr_tabstops)
+		printbuf_tabstop_push(out, 24);
+
+	for (u64 seq = journal_last_unwritten_seq(j);
+	     seq <= journal_cur_seq(j);
+	     seq++)
+		bch2_journal_buf_to_text(out, j, seq);
+}
+
 static inline bool journal_seq_unwritten(struct journal *j, u64 seq)
 {
 	return seq > j->seq_ondisk;
@@ -156,7 +197,7 @@ void bch2_journal_buf_put_final(struct journal *j, u64 seq, bool write)
  * We don't close a journal_buf until the next journal_buf is finished writing,
  * and can be opened again - this also initializes the next journal_buf:
  */
-static void __journal_entry_close(struct journal *j, unsigned closed_val)
+static void __journal_entry_close(struct journal *j, unsigned closed_val, bool trace)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_buf *buf = journal_cur_buf(j);
@@ -185,7 +226,17 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val)
 	/* Close out old buffer: */
 	buf->data->u64s		= cpu_to_le32(old.cur_entry_offset);
 
-	trace_journal_entry_close(c, vstruct_bytes(buf->data));
+	if (trace_journal_entry_close_enabled() && trace) {
+		struct printbuf pbuf = PRINTBUF;
+		pbuf.atomic++;
+
+		prt_str(&pbuf, "entry size: ");
+		prt_human_readable_u64(&pbuf, vstruct_bytes(buf->data));
+		prt_newline(&pbuf);
+		bch2_prt_task_backtrace(&pbuf, current, 1);
+		trace_journal_entry_close(c, pbuf.buf);
+		printbuf_exit(&pbuf);
+	}
 
 	sectors = vstruct_blocks_plus(buf->data, c->block_bits,
 				      buf->u64s_reserved) << c->block_bits;
@@ -225,7 +276,7 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val)
 void bch2_journal_halt(struct journal *j)
 {
 	spin_lock(&j->lock);
-	__journal_entry_close(j, JOURNAL_ENTRY_ERROR_VAL);
+	__journal_entry_close(j, JOURNAL_ENTRY_ERROR_VAL, true);
 	if (!j->err_seq)
 		j->err_seq = journal_cur_seq(j);
 	journal_wake(j);
@@ -239,7 +290,7 @@ static bool journal_entry_want_write(struct journal *j)
 
 	/* Don't close it yet if we already have a write in flight: */
 	if (ret)
-		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 	else if (nr_unwritten_journal_entries(j)) {
 		struct journal_buf *buf = journal_cur_buf(j);
 
@@ -406,7 +457,7 @@ static void journal_write_work(struct work_struct *work)
 	if (delta > 0)
 		mod_delayed_work(c->io_complete_wq, &j->write_work, delta);
 	else
-		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 unlock:
 	spin_unlock(&j->lock);
 }
@@ -463,13 +514,21 @@ retry:
 	    buf->buf_size < JOURNAL_ENTRY_SIZE_MAX)
 		j->buf_size_want = max(j->buf_size_want, buf->buf_size << 1);
 
-	__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+	__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, false);
 	ret = journal_entry_open(j);
 
 	if (ret == JOURNAL_ERR_max_in_flight) {
 		track_event_change(&c->times[BCH_TIME_blocked_journal_max_in_flight],
 				   &j->max_in_flight_start, true);
-		trace_and_count(c, journal_entry_full, c);
+		if (trace_journal_entry_full_enabled()) {
+			struct printbuf buf = PRINTBUF;
+			buf.atomic++;
+
+			bch2_journal_bufs_to_text(&buf, j);
+			trace_journal_entry_full(c, buf.buf);
+			printbuf_exit(&buf);
+		}
+		count_event(c, journal_entry_full);
 	}
 unlock:
 	can_discard = j->can_discard;
@@ -549,7 +608,7 @@ void bch2_journal_entry_res_resize(struct journal *j,
 		/*
 		 * Not enough room in current journal entry, have to flush it:
 		 */
-		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+		__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 	} else {
 		journal_cur_buf(j)->u64s_reserved += d;
 	}
@@ -606,7 +665,7 @@ recheck_need_open:
 		struct journal_res res = { 0 };
 
 		if (journal_entry_is_open(j))
-			__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+			__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 
 		spin_unlock(&j->lock);
 
@@ -786,7 +845,7 @@ static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct jou
 
 		if (buf->need_flush_to_write_buffer) {
 			if (seq == journal_cur_seq(j))
-				__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL);
+				__journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true);
 
 			union journal_res_state s;
 			s.v = atomic64_read_acquire(&j->reservations.counter);
@@ -1339,35 +1398,9 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 	}
 
 	prt_newline(out);
-
-	for (u64 seq = journal_cur_seq(j);
-	     seq >= journal_last_unwritten_seq(j);
-	     --seq) {
-		unsigned i = seq & JOURNAL_BUF_MASK;
-
-		prt_printf(out, "unwritten entry:");
-		prt_tab(out);
-		prt_printf(out, "%llu", seq);
-		prt_newline(out);
-		printbuf_indent_add(out, 2);
-
-		prt_printf(out, "refcount:");
-		prt_tab(out);
-		prt_printf(out, "%u", journal_state_count(s, i));
-		prt_newline(out);
-
-		prt_printf(out, "sectors:");
-		prt_tab(out);
-		prt_printf(out, "%u", j->buf[i].sectors);
-		prt_newline(out);
-
-		prt_printf(out, "expires");
-		prt_tab(out);
-		prt_printf(out, "%li jiffies", j->buf[i].expires - jiffies);
-		prt_newline(out);
-
-		printbuf_indent_sub(out, 2);
-	}
+	prt_printf(out, "unwritten entries:");
+	prt_newline(out);
+	bch2_journal_bufs_to_text(out, j);
 
 	prt_printf(out,
 	       "replay done:\t\t%i\n",
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index 8292efc3289ba..ea307ed49424e 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -46,7 +46,7 @@ DECLARE_EVENT_CLASS(fs_str,
 		__assign_str(str, str);
 	),
 
-	TP_printk("%d,%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(str))
+	TP_printk("%d,%d\n%s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(str))
 );
 
 DECLARE_EVENT_CLASS(trans_str,
@@ -273,28 +273,14 @@ DEFINE_EVENT(bch_fs, journal_full,
 	TP_ARGS(c)
 );
 
-DEFINE_EVENT(bch_fs, journal_entry_full,
-	TP_PROTO(struct bch_fs *c),
-	TP_ARGS(c)
+DEFINE_EVENT(fs_str, journal_entry_full,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
-TRACE_EVENT(journal_entry_close,
-	TP_PROTO(struct bch_fs *c, unsigned bytes),
-	TP_ARGS(c, bytes),
-
-	TP_STRUCT__entry(
-		__field(dev_t,		dev			)
-		__field(u32,		bytes			)
-	),
-
-	TP_fast_assign(
-		__entry->dev			= c->dev;
-		__entry->bytes			= bytes;
-	),
-
-	TP_printk("%d,%d entry bytes %u",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->bytes)
+DEFINE_EVENT(fs_str, journal_entry_close,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 DEFINE_EVENT(bio, journal_write,
-- 
GitLab


From ba96d36ca526f99b163927115abfec36ef5565e0 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 18:08:32 -0500
Subject: [PATCH 3102/4076] bcachefs: bkey_and_val_eq()

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/backpointers.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index e358a2ffffdea..56e5a0e213f9e 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -400,6 +400,13 @@ int bch2_check_btree_backpointers(struct bch_fs *c)
 	return ret;
 }
 
+static inline bool bkey_and_val_eq(struct bkey_s_c l, struct bkey_s_c r)
+{
+	return bpos_eq(l.k->p, r.k->p) &&
+		bkey_bytes(l.k) == bkey_bytes(r.k) &&
+		!memcmp(l.v, r.v, bkey_val_bytes(l.k));
+}
+
 static int check_bp_exists(struct btree_trans *trans,
 			   struct bpos bucket,
 			   struct bch_backpointer bp,
@@ -433,9 +440,7 @@ static int check_bp_exists(struct btree_trans *trans,
 
 	if (bp_k.k->type != KEY_TYPE_backpointer ||
 	    memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp, sizeof(bp))) {
-		if (!bpos_eq(orig_k.k->p, last_flushed->k->k.p) ||
-		    bkey_bytes(orig_k.k) != bkey_bytes(&last_flushed->k->k) ||
-		    memcmp(orig_k.v, &last_flushed->k->v, bkey_val_bytes(orig_k.k))) {
+		if (!bkey_and_val_eq(orig_k, bkey_i_to_s_c(last_flushed->k))) {
 			bch2_bkey_buf_reassemble(&tmp, c, orig_k);
 
 			if (bp.level) {
-- 
GitLab


From 1a5039041b376f545dfc11d89af77cc720217b44 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 18:19:52 -0500
Subject: [PATCH 3103/4076] bcachefs: extents_to_bp_state

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/backpointers.c | 89 ++++++++++++++++++--------------------
 1 file changed, 41 insertions(+), 48 deletions(-)

diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index 56e5a0e213f9e..bf828f1f28d2b 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -407,13 +407,17 @@ static inline bool bkey_and_val_eq(struct bkey_s_c l, struct bkey_s_c r)
 		!memcmp(l.v, r.v, bkey_val_bytes(l.k));
 }
 
+struct extents_to_bp_state {
+	struct bpos	bucket_start;
+	struct bpos	bucket_end;
+	struct bkey_buf last_flushed;
+};
+
 static int check_bp_exists(struct btree_trans *trans,
+			   struct extents_to_bp_state *s,
 			   struct bpos bucket,
 			   struct bch_backpointer bp,
-			   struct bkey_s_c orig_k,
-			   struct bpos bucket_start,
-			   struct bpos bucket_end,
-			   struct bkey_buf *last_flushed)
+			   struct bkey_s_c orig_k)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter bp_iter = { NULL };
@@ -424,8 +428,8 @@ static int check_bp_exists(struct btree_trans *trans,
 
 	bch2_bkey_buf_init(&tmp);
 
-	if (bpos_lt(bucket, bucket_start) ||
-	    bpos_gt(bucket, bucket_end))
+	if (bpos_lt(bucket, s->bucket_start) ||
+	    bpos_gt(bucket, s->bucket_end))
 		return 0;
 
 	if (!bch2_dev_bucket_exists(c, bucket))
@@ -440,9 +444,9 @@ static int check_bp_exists(struct btree_trans *trans,
 
 	if (bp_k.k->type != KEY_TYPE_backpointer ||
 	    memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp, sizeof(bp))) {
-		if (!bkey_and_val_eq(orig_k, bkey_i_to_s_c(last_flushed->k))) {
-			bch2_bkey_buf_reassemble(&tmp, c, orig_k);
+		bch2_bkey_buf_reassemble(&tmp, c, orig_k);
 
+		if (!bkey_and_val_eq(orig_k, bkey_i_to_s_c(s->last_flushed.k))) {
 			if (bp.level) {
 				bch2_trans_unlock(trans);
 				bch2_btree_interior_updates_flush(c);
@@ -452,7 +456,7 @@ static int check_bp_exists(struct btree_trans *trans,
 			if (ret)
 				goto err;
 
-			bch2_bkey_buf_copy(last_flushed, c, tmp.k);
+			bch2_bkey_buf_copy(&s->last_flushed, c, tmp.k);
 			ret = -BCH_ERR_transaction_restart_write_buffer_flush;
 			goto out;
 		}
@@ -480,10 +484,8 @@ missing:
 }
 
 static int check_extent_to_backpointers(struct btree_trans *trans,
+					struct extents_to_bp_state *s,
 					enum btree_id btree, unsigned level,
-					struct bpos bucket_start,
-					struct bpos bucket_end,
-					struct bkey_buf *last_flushed,
 					struct bkey_s_c k)
 {
 	struct bch_fs *c = trans->c;
@@ -503,9 +505,7 @@ static int check_extent_to_backpointers(struct btree_trans *trans,
 		bch2_extent_ptr_to_bp(c, btree, level,
 				      k, p, &bucket_pos, &bp);
 
-		ret = check_bp_exists(trans, bucket_pos, bp, k,
-				      bucket_start, bucket_end,
-				      last_flushed);
+		ret = check_bp_exists(trans, s, bucket_pos, bp, k);
 		if (ret)
 			return ret;
 	}
@@ -514,10 +514,8 @@ static int check_extent_to_backpointers(struct btree_trans *trans,
 }
 
 static int check_btree_root_to_backpointers(struct btree_trans *trans,
+					    struct extents_to_bp_state *s,
 					    enum btree_id btree_id,
-					    struct bpos bucket_start,
-					    struct bpos bucket_end,
-					    struct bkey_buf *last_flushed,
 					    int *level)
 {
 	struct bch_fs *c = trans->c;
@@ -541,9 +539,7 @@ retry:
 	*level = b->c.level;
 
 	k = bkey_i_to_s_c(&b->key);
-	ret = check_extent_to_backpointers(trans, btree_id, b->c.level + 1,
-				      bucket_start, bucket_end,
-				      last_flushed, k);
+	ret = check_extent_to_backpointers(trans, s, btree_id, b->c.level + 1, k);
 err:
 	bch2_trans_iter_exit(trans, &iter);
 	return ret;
@@ -615,43 +611,35 @@ static int bch2_get_btree_in_memory_pos(struct btree_trans *trans,
 }
 
 static int bch2_check_extents_to_backpointers_pass(struct btree_trans *trans,
-						   struct bpos bucket_start,
-						   struct bpos bucket_end)
+						   struct extents_to_bp_state *s)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_iter iter;
-	enum btree_id btree_id;
-	struct bkey_s_c k;
-	struct bkey_buf last_flushed;
 	int ret = 0;
 
-	bch2_bkey_buf_init(&last_flushed);
-	bkey_init(&last_flushed.k->k);
-
-	for (btree_id = 0; btree_id < btree_id_nr_alive(c); btree_id++) {
+	for (enum btree_id btree_id = 0;
+	     btree_id < btree_id_nr_alive(c);
+	     btree_id++) {
 		int level, depth = btree_type_has_ptrs(btree_id) ? 0 : 1;
 
 		ret = commit_do(trans, NULL, NULL,
 				BCH_TRANS_COMMIT_no_enospc,
-				check_btree_root_to_backpointers(trans, btree_id,
-							bucket_start, bucket_end,
-							&last_flushed, &level));
+				check_btree_root_to_backpointers(trans, s, btree_id, &level));
 		if (ret)
 			return ret;
 
 		while (level >= depth) {
+			struct btree_iter iter;
 			bch2_trans_node_iter_init(trans, &iter, btree_id, POS_MIN, 0,
 						  level,
 						  BTREE_ITER_PREFETCH);
 			while (1) {
 				bch2_trans_begin(trans);
-				k = bch2_btree_iter_peek(&iter);
+
+				struct bkey_s_c k = bch2_btree_iter_peek(&iter);
 				if (!k.k)
 					break;
 				ret = bkey_err(k) ?:
-					check_extent_to_backpointers(trans, btree_id, level,
-								     bucket_start, bucket_end,
-								     &last_flushed, k) ?:
+					check_extent_to_backpointers(trans, s, btree_id, level, k) ?:
 					bch2_trans_commit(trans, NULL, NULL,
 							  BCH_TRANS_COMMIT_no_enospc);
 				if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
@@ -673,7 +661,6 @@ static int bch2_check_extents_to_backpointers_pass(struct btree_trans *trans,
 		}
 	}
 
-	bch2_bkey_buf_exit(&last_flushed, c);
 	return 0;
 }
 
@@ -736,37 +723,43 @@ static int bch2_get_alloc_in_memory_pos(struct btree_trans *trans,
 int bch2_check_extents_to_backpointers(struct bch_fs *c)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
-	struct bpos start = POS_MIN, end;
+	struct extents_to_bp_state s = { .bucket_start = POS_MIN };
 	int ret;
 
+	bch2_bkey_buf_init(&s.last_flushed);
+	bkey_init(&s.last_flushed.k->k);
+
 	while (1) {
-		ret = bch2_get_alloc_in_memory_pos(trans, start, &end);
+		ret = bch2_get_alloc_in_memory_pos(trans, s.bucket_start, &s.bucket_end);
 		if (ret)
 			break;
 
-		if (bpos_eq(start, POS_MIN) && !bpos_eq(end, SPOS_MAX))
+		if ( bpos_eq(s.bucket_start, POS_MIN) &&
+		    !bpos_eq(s.bucket_end, SPOS_MAX))
 			bch_verbose(c, "%s(): alloc info does not fit in ram, running in multiple passes with %zu nodes per pass",
 				    __func__, btree_nodes_fit_in_ram(c));
 
-		if (!bpos_eq(start, POS_MIN) || !bpos_eq(end, SPOS_MAX)) {
+		if (!bpos_eq(s.bucket_start, POS_MIN) ||
+		    !bpos_eq(s.bucket_end, SPOS_MAX)) {
 			struct printbuf buf = PRINTBUF;
 
 			prt_str(&buf, "check_extents_to_backpointers(): ");
-			bch2_bpos_to_text(&buf, start);
+			bch2_bpos_to_text(&buf, s.bucket_start);
 			prt_str(&buf, "-");
-			bch2_bpos_to_text(&buf, end);
+			bch2_bpos_to_text(&buf, s.bucket_end);
 
 			bch_verbose(c, "%s", buf.buf);
 			printbuf_exit(&buf);
 		}
 
-		ret = bch2_check_extents_to_backpointers_pass(trans, start, end);
-		if (ret || bpos_eq(end, SPOS_MAX))
+		ret = bch2_check_extents_to_backpointers_pass(trans, &s);
+		if (ret || bpos_eq(s.bucket_end, SPOS_MAX))
 			break;
 
-		start = bpos_successor(end);
+		s.bucket_start = bpos_successor(s.bucket_end);
 	}
 	bch2_trans_put(trans);
+	bch2_bkey_buf_exit(&s.last_flushed, c);
 
 	bch_err_fn(c, ret);
 	return ret;
-- 
GitLab


From 46bf2e9cc745996ca56e56ed816e60d07811bd9a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 20:37:23 -0500
Subject: [PATCH 3104/4076] bcachefs: Fix excess transaction restarts in
 __bchfs_fallocate()

drop_locks_do() should not be used in a fastpath without first trying
the do in nonblocking mode - the unlock and relock will cause excessive
transaction restarts and potentially livelocking with other threads that
are contending for the same locks.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_iter.h      |  5 +++++
 fs/bcachefs/fs-io-pagecache.c | 37 +++++++++++++++++++++++------------
 fs/bcachefs/fs-io-pagecache.h |  2 +-
 fs/bcachefs/fs-io.c           |  7 +++++--
 4 files changed, 35 insertions(+), 16 deletions(-)

diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index da2b74fa63fce..24772538e4cc7 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -819,6 +819,11 @@ __bch2_btree_iter_peek_and_restart(struct btree_trans *trans,
 #define for_each_btree_key_continue_norestart(_iter, _flags, _k, _ret)	\
 	for_each_btree_key_upto_continue_norestart(_iter, SPOS_MAX, _flags, _k, _ret)
 
+/*
+ * This should not be used in a fastpath, without first trying _do in
+ * nonblocking mode - it will cause excessive transaction restarts and
+ * potentially livelocking:
+ */
 #define drop_locks_do(_trans, _do)					\
 ({									\
 	bch2_trans_unlock(_trans);					\
diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c
index ff664fd0d8ef8..d359aa9b33b82 100644
--- a/fs/bcachefs/fs-io-pagecache.c
+++ b/fs/bcachefs/fs-io-pagecache.c
@@ -309,39 +309,49 @@ void bch2_mark_pagecache_unallocated(struct bch_inode_info *inode,
 	}
 }
 
-void bch2_mark_pagecache_reserved(struct bch_inode_info *inode,
-				  u64 start, u64 end)
+int bch2_mark_pagecache_reserved(struct bch_inode_info *inode,
+				 u64 *start, u64 end,
+				 bool nonblocking)
 {
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
-	pgoff_t index = start >> PAGE_SECTORS_SHIFT;
+	pgoff_t index = *start >> PAGE_SECTORS_SHIFT;
 	pgoff_t end_index = (end - 1) >> PAGE_SECTORS_SHIFT;
 	struct folio_batch fbatch;
 	s64 i_sectors_delta = 0;
-	unsigned i, j;
+	int ret = 0;
 
-	if (end <= start)
-		return;
+	if (end <= *start)
+		return 0;
 
 	folio_batch_init(&fbatch);
 
 	while (filemap_get_folios(inode->v.i_mapping,
 				  &index, end_index, &fbatch)) {
-		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+		for (unsigned i = 0; i < folio_batch_count(&fbatch); i++) {
 			struct folio *folio = fbatch.folios[i];
+
+			if (!nonblocking)
+				folio_lock(folio);
+			else if (!folio_trylock(folio)) {
+				folio_batch_release(&fbatch);
+				ret = -EAGAIN;
+				break;
+			}
+
 			u64 folio_start = folio_sector(folio);
 			u64 folio_end = folio_end_sector(folio);
-			unsigned folio_offset = max(start, folio_start) - folio_start;
-			unsigned folio_len = min(end, folio_end) - folio_offset - folio_start;
-			struct bch_folio *s;
 
 			BUG_ON(end <= folio_start);
 
-			folio_lock(folio);
-			s = bch2_folio(folio);
+			*start = min(end, folio_end);
 
+			struct bch_folio *s = bch2_folio(folio);
 			if (s) {
+				unsigned folio_offset = max(*start, folio_start) - folio_start;
+				unsigned folio_len = min(end, folio_end) - folio_offset - folio_start;
+
 				spin_lock(&s->lock);
-				for (j = folio_offset; j < folio_offset + folio_len; j++) {
+				for (unsigned j = folio_offset; j < folio_offset + folio_len; j++) {
 					i_sectors_delta -= s->s[j].state == SECTOR_dirty;
 					bch2_folio_sector_set(folio, s, j,
 						folio_sector_reserve(s->s[j].state));
@@ -356,6 +366,7 @@ void bch2_mark_pagecache_reserved(struct bch_inode_info *inode,
 	}
 
 	bch2_i_sectors_acct(c, inode, NULL, i_sectors_delta);
+	return ret;
 }
 
 static inline unsigned sectors_to_reserve(struct bch_folio_sector *s,
diff --git a/fs/bcachefs/fs-io-pagecache.h b/fs/bcachefs/fs-io-pagecache.h
index 27f712ae37a68..8cbaba6565b44 100644
--- a/fs/bcachefs/fs-io-pagecache.h
+++ b/fs/bcachefs/fs-io-pagecache.h
@@ -143,7 +143,7 @@ int bch2_folio_set(struct bch_fs *, subvol_inum, struct folio **, unsigned);
 void bch2_bio_page_state_set(struct bio *, struct bkey_s_c);
 
 void bch2_mark_pagecache_unallocated(struct bch_inode_info *, u64, u64);
-void bch2_mark_pagecache_reserved(struct bch_inode_info *, u64, u64);
+int bch2_mark_pagecache_reserved(struct bch_inode_info *, u64 *, u64, bool);
 
 int bch2_get_folio_disk_reservation(struct bch_fs *,
 				struct bch_inode_info *,
diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 98bd5babab193..dc52918d06ef3 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -675,8 +675,11 @@ static int __bchfs_fallocate(struct bch_inode_info *inode, int mode,
 
 		bch2_i_sectors_acct(c, inode, &quota_res, i_sectors_delta);
 
-		drop_locks_do(trans,
-			(bch2_mark_pagecache_reserved(inode, hole_start, iter.pos.offset), 0));
+		if (bch2_mark_pagecache_reserved(inode, &hole_start,
+						 iter.pos.offset, true))
+			drop_locks_do(trans,
+				bch2_mark_pagecache_reserved(inode, &hole_start,
+							     iter.pos.offset, false));
 bkey_err:
 		bch2_quota_reservation_put(c, inode, &quota_res);
 		if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
-- 
GitLab


From b97de453651f06071afbf52a5614bd55b8cc4740 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 15 Jan 2024 20:40:06 -0500
Subject: [PATCH 3105/4076] bcachefs: Improve trace_trans_restart_relock

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_iter.c    |  2 +-
 fs/bcachefs/btree_locking.c | 40 ++++++++++++++++++++++++++++++-------
 fs/bcachefs/btree_locking.h |  9 +--------
 fs/bcachefs/btree_types.h   |  5 +++++
 fs/bcachefs/trace.h         | 12 ++++-------
 5 files changed, 44 insertions(+), 24 deletions(-)

diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index fa298289e0165..5467a8635be11 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -1337,7 +1337,7 @@ void bch2_path_put(struct btree_trans *trans, btree_path_idx_t path_idx, bool in
 
 	if (path->should_be_locked &&
 	    !trans->restarted &&
-	    (!dup || !bch2_btree_path_relock_norestart(trans, dup, _THIS_IP_)))
+	    (!dup || !bch2_btree_path_relock_norestart(trans, dup)))
 		return;
 
 	if (dup) {
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 2d1c95c42f240..bed75c93c0690 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -631,8 +631,7 @@ int bch2_btree_path_relock_intent(struct btree_trans *trans,
 }
 
 __flatten
-bool bch2_btree_path_relock_norestart(struct btree_trans *trans,
-			struct btree_path *path, unsigned long trace_ip)
+bool bch2_btree_path_relock_norestart(struct btree_trans *trans, struct btree_path *path)
 {
 	struct get_locks_fail f;
 
@@ -642,7 +641,7 @@ bool bch2_btree_path_relock_norestart(struct btree_trans *trans,
 int __bch2_btree_path_relock(struct btree_trans *trans,
 			struct btree_path *path, unsigned long trace_ip)
 {
-	if (!bch2_btree_path_relock_norestart(trans, path, trace_ip)) {
+	if (!bch2_btree_path_relock_norestart(trans, path)) {
 		trace_and_count(trans->c, trans_restart_relock_path, trans, trace_ip, path);
 		return btree_trans_restart(trans, BCH_ERR_transaction_restart_relock_path);
 	}
@@ -759,12 +758,39 @@ int bch2_trans_relock(struct btree_trans *trans)
 	if (unlikely(trans->restarted))
 		return -((int) trans->restarted);
 
-	trans_for_each_path(trans, path, i)
+	trans_for_each_path(trans, path, i) {
+		struct get_locks_fail f;
+
 		if (path->should_be_locked &&
-		    !bch2_btree_path_relock_norestart(trans, path, _RET_IP_)) {
-			trace_and_count(trans->c, trans_restart_relock, trans, _RET_IP_, path);
+		    !btree_path_get_locks(trans, path, false, &f)) {
+			if (trace_trans_restart_relock_enabled()) {
+				struct printbuf buf = PRINTBUF;
+
+				bch2_bpos_to_text(&buf, path->pos);
+				prt_printf(&buf, " l=%u seq=%u node seq=",
+					   f.l, path->l[f.l].lock_seq);
+				if (IS_ERR_OR_NULL(f.b)) {
+					prt_str(&buf, bch2_err_str(PTR_ERR(f.b)));
+				} else {
+					prt_printf(&buf, "%u", f.b->c.lock.seq);
+
+					struct six_lock_count c =
+						bch2_btree_node_lock_counts(trans, NULL, &f.b->c, f.l);
+					prt_printf(&buf, " self locked %u.%u.%u", c.n[0], c.n[1], c.n[2]);
+
+					c = six_lock_counts(&f.b->c.lock);
+					prt_printf(&buf, " total locked %u.%u.%u", c.n[0], c.n[1], c.n[2]);
+				}
+
+				trace_trans_restart_relock(trans, _RET_IP_, buf.buf);
+				printbuf_exit(&buf);
+			}
+
+			count_event(trans->c, trans_restart_relock);
 			return btree_trans_restart(trans, BCH_ERR_transaction_restart_relock);
 		}
+	}
+
 	return 0;
 }
 
@@ -778,7 +804,7 @@ int bch2_trans_relock_notrace(struct btree_trans *trans)
 
 	trans_for_each_path(trans, path, i)
 		if (path->should_be_locked &&
-		    !bch2_btree_path_relock_norestart(trans, path, _RET_IP_)) {
+		    !bch2_btree_path_relock_norestart(trans, path)) {
 			return btree_trans_restart(trans, BCH_ERR_transaction_restart_relock);
 		}
 	return 0;
diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h
index cc5500a957a1b..4bd72c855da1a 100644
--- a/fs/bcachefs/btree_locking.h
+++ b/fs/bcachefs/btree_locking.h
@@ -312,8 +312,7 @@ void bch2_btree_node_lock_write_nofail(struct btree_trans *,
 
 /* relock: */
 
-bool bch2_btree_path_relock_norestart(struct btree_trans *,
-				      struct btree_path *, unsigned long);
+bool bch2_btree_path_relock_norestart(struct btree_trans *, struct btree_path *);
 int __bch2_btree_path_relock(struct btree_trans *,
 			     struct btree_path *, unsigned long);
 
@@ -353,12 +352,6 @@ static inline bool bch2_btree_node_relock_notrace(struct btree_trans *trans,
 
 /* upgrade */
 
-
-struct get_locks_fail {
-	unsigned	l;
-	struct btree	*b;
-};
-
 bool bch2_btree_path_upgrade_noupgrade_sibs(struct btree_trans *,
 			       struct btree_path *, unsigned,
 			       struct get_locks_fail *);
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index e58e9a7f7b627..4a5a64499eb76 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -741,4 +741,9 @@ enum btree_node_sibling {
 	btree_next_sib,
 };
 
+struct get_locks_fail {
+	unsigned	l;
+	struct btree	*b;
+};
+
 #endif /* _BCACHEFS_BTREE_TYPES_H */
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index ea307ed49424e..6ac1dfeaa8f29 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -528,7 +528,7 @@ TRACE_EVENT(btree_path_relock_fail,
 		__entry->level			= path->level;
 		TRACE_BPOS_assign(pos, path->pos);
 
-		c = bch2_btree_node_lock_counts(trans, NULL, &path->l[level].b->c, level),
+		c = bch2_btree_node_lock_counts(trans, NULL, &path->l[level].b->c, level);
 		__entry->self_read_count	= c.n[SIX_LOCK_read];
 		__entry->self_intent_count	= c.n[SIX_LOCK_intent];
 
@@ -1120,8 +1120,6 @@ DEFINE_EVENT(transaction_restart_iter,	trans_restart_btree_node_split,
 	TP_ARGS(trans, caller_ip, path)
 );
 
-struct get_locks_fail;
-
 TRACE_EVENT(trans_restart_upgrade,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip,
@@ -1169,11 +1167,9 @@ TRACE_EVENT(trans_restart_upgrade,
 		  __entry->node_seq)
 );
 
-DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 struct btree_path *path),
-	TP_ARGS(trans, caller_ip, path)
+DEFINE_EVENT(trans_str,	trans_restart_relock,
+	TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, const char *str),
+	TP_ARGS(trans, caller_ip, str)
 );
 
 DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_next_node,
-- 
GitLab


From aead3428e8b7502942356a17f0882d28eb3ff0c3 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 16 Jan 2024 11:07:23 +0000
Subject: [PATCH 3106/4076] bcachefs: remove redundant variable tmp

The variable tmp is being assigned a value but it isn't being
read afterwards. The assignment is redundant and so tmp can be
removed.

Cleans up clang scan build warning:
warning: Although the value stored to 'ret' is used in the enclosing
expression, the value is never actually read from 'ret'
[deadcode.DeadStores]

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/rebalance.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index f24106dee21d6..2d22efed981a7 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -385,7 +385,6 @@ static int bch2_rebalance_thread(void *arg)
 	struct bch_fs *c = arg;
 	struct bch_fs_rebalance *r = &c->rebalance;
 	struct moving_context ctxt;
-	int ret;
 
 	set_freezable();
 
@@ -393,8 +392,7 @@ static int bch2_rebalance_thread(void *arg)
 			      writepoint_ptr(&c->rebalance_write_point),
 			      true);
 
-	while (!kthread_should_stop() &&
-	       !(ret = do_rebalance(&ctxt)))
+	while (!kthread_should_stop() && !do_rebalance(&ctxt))
 		;
 
 	bch2_moving_ctxt_exit(&ctxt);
-- 
GitLab


From 00fff4dd58661944af9cb4fe8fe61b4105931776 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 16 Jan 2024 11:38:04 -0500
Subject: [PATCH 3107/4076] bcachefs: bios must be 512 byte algined

Fixes: 023f9ac9f70f bcachefs: Delete dio read alignment check
Reported-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs-io-direct.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index fdd57c5785c9c..e3b219e19e100 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -77,6 +77,10 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter)
 
 	bch2_inode_opts_get(&opts, c, &inode->ei_inode);
 
+	/* bios must be 512 byte aligned: */
+	if ((offset|iter->count) & (SECTOR_SIZE - 1))
+		return -EINVAL;
+
 	ret = min_t(loff_t, iter->count,
 		    max_t(loff_t, 0, i_size_read(&inode->v) - offset));
 
-- 
GitLab


From 369acf97d6fd5da620d053d0f1878ffe32eff555 Mon Sep 17 00:00:00 2001
From: Su Yue <glass.su@suse.com>
Date: Tue, 16 Jan 2024 19:05:37 +0800
Subject: [PATCH 3108/4076] bcachefs: kvfree bch_fs::snapshots in
 bch2_fs_snapshots_exit

bch_fs::snapshots is allocated by kvzalloc in __snapshot_t_mut.
It should be freed by kvfree not kfree.
Or umount will triger:

[  406.829178 ] BUG: unable to handle page fault for address: ffffe7b487148008
[  406.830676 ] #PF: supervisor read access in kernel mode
[  406.831643 ] #PF: error_code(0x0000) - not-present page
[  406.832487 ] PGD 0 P4D 0
[  406.832898 ] Oops: 0000 [#1] PREEMPT SMP PTI
[  406.833512 ] CPU: 2 PID: 1754 Comm: umount Kdump: loaded Tainted: G           OE      6.7.0-rc7-custom+ #90
[  406.834746 ] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014
[  406.835796 ] RIP: 0010:kfree+0x62/0x140
[  406.836197 ] Code: 80 48 01 d8 0f 82 e9 00 00 00 48 c7 c2 00 00 00 80 48 2b 15 78 9f 1f 01 48 01 d0 48 c1 e8 0c 48 c1 e0 06 48 03 05 56 9f 1f 01 <48> 8b 50 08 48 89 c7 f6 c2 01 0f 85 b0 00 00 00 66 90 48 8b 07 f6
[  406.837810 ] RSP: 0018:ffffb9d641607e48 EFLAGS: 00010286
[  406.838213 ] RAX: ffffe7b487148000 RBX: ffffb9d645200000 RCX: ffffb9d641607dc4
[  406.838738 ] RDX: 000065bb00000000 RSI: ffffffffc0d88b84 RDI: ffffb9d645200000
[  406.839217 ] RBP: ffff9a4625d00068 R08: 0000000000000001 R09: 0000000000000001
[  406.839650 ] R10: 0000000000000001 R11: 000000000000001f R12: ffff9a4625d4da80
[  406.840055 ] R13: ffff9a4625d00000 R14: ffffffffc0e2eb20 R15: 0000000000000000
[  406.840451 ] FS:  00007f0a264ffb80(0000) GS:ffff9a4e2d500000(0000) knlGS:0000000000000000
[  406.840851 ] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  406.841125 ] CR2: ffffe7b487148008 CR3: 000000018c4d2000 CR4: 00000000000006f0
[  406.841464 ] Call Trace:
[  406.841583 ]  <TASK>
[  406.841682 ]  ? __die+0x1f/0x70
[  406.841828 ]  ? page_fault_oops+0x159/0x470
[  406.842014 ]  ? fixup_exception+0x22/0x310
[  406.842198 ]  ? exc_page_fault+0x1ed/0x200
[  406.842382 ]  ? asm_exc_page_fault+0x22/0x30
[  406.842574 ]  ? bch2_fs_release+0x54/0x280 [bcachefs]
[  406.842842 ]  ? kfree+0x62/0x140
[  406.842988 ]  ? kfree+0x104/0x140
[  406.843138 ]  bch2_fs_release+0x54/0x280 [bcachefs]
[  406.843390 ]  kobject_put+0xb7/0x170
[  406.843552 ]  deactivate_locked_super+0x2f/0xa0
[  406.843756 ]  cleanup_mnt+0xba/0x150
[  406.843917 ]  task_work_run+0x59/0xa0
[  406.844083 ]  exit_to_user_mode_prepare+0x197/0x1a0
[  406.844302 ]  syscall_exit_to_user_mode+0x16/0x40
[  406.844510 ]  do_syscall_64+0x4e/0xf0
[  406.844675 ]  entry_SYSCALL_64_after_hwframe+0x6e/0x76
[  406.844907 ] RIP: 0033:0x7f0a2664e4fb

Signed-off-by: Su Yue <glass.su@suse.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/snapshot.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 56af937523ff2..cdcff4e5ae5c3 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -1681,5 +1681,5 @@ int bch2_snapshots_read(struct bch_fs *c)
 
 void bch2_fs_snapshots_exit(struct bch_fs *c)
 {
-	kfree(rcu_dereference_protected(c->snapshots, true));
+	kvfree(rcu_dereference_protected(c->snapshots, true));
 }
-- 
GitLab


From 2acc59dd88d27ad69b66ded80df16c042b04eeec Mon Sep 17 00:00:00 2001
From: Su Yue <glass.su@suse.com>
Date: Mon, 15 Jan 2024 10:21:25 +0800
Subject: [PATCH 3109/4076] bcachefs: grab s_umount only if snapshotting

When I was testing mongodb over bcachefs with compression,
there is a lockdep warning when snapshotting mongodb data volume.

$ cat test.sh
prog=bcachefs

$prog subvolume create /mnt/data
$prog subvolume create /mnt/data/snapshots

while true;do
    $prog subvolume snapshot /mnt/data /mnt/data/snapshots/$(date +%s)
    sleep 1s
done

$ cat /etc/mongodb.conf
systemLog:
  destination: file
  logAppend: true
  path: /mnt/data/mongod.log

storage:
  dbPath: /mnt/data/

lockdep reports:
[ 3437.452330] ======================================================
[ 3437.452750] WARNING: possible circular locking dependency detected
[ 3437.453168] 6.7.0-rc7-custom+ #85 Tainted: G            E
[ 3437.453562] ------------------------------------------------------
[ 3437.453981] bcachefs/35533 is trying to acquire lock:
[ 3437.454325] ffffa0a02b2b1418 (sb_writers#10){.+.+}-{0:0}, at: filename_create+0x62/0x190
[ 3437.454875]
               but task is already holding lock:
[ 3437.455268] ffffa0a02b2b10e0 (&type->s_umount_key#48){.+.+}-{3:3}, at: bch2_fs_file_ioctl+0x232/0xc90 [bcachefs]
[ 3437.456009]
               which lock already depends on the new lock.

[ 3437.456553]
               the existing dependency chain (in reverse order) is:
[ 3437.457054]
               -> #3 (&type->s_umount_key#48){.+.+}-{3:3}:
[ 3437.457507]        down_read+0x3e/0x170
[ 3437.457772]        bch2_fs_file_ioctl+0x232/0xc90 [bcachefs]
[ 3437.458206]        __x64_sys_ioctl+0x93/0xd0
[ 3437.458498]        do_syscall_64+0x42/0xf0
[ 3437.458779]        entry_SYSCALL_64_after_hwframe+0x6e/0x76
[ 3437.459155]
               -> #2 (&c->snapshot_create_lock){++++}-{3:3}:
[ 3437.459615]        down_read+0x3e/0x170
[ 3437.459878]        bch2_truncate+0x82/0x110 [bcachefs]
[ 3437.460276]        bchfs_truncate+0x254/0x3c0 [bcachefs]
[ 3437.460686]        notify_change+0x1f1/0x4a0
[ 3437.461283]        do_truncate+0x7f/0xd0
[ 3437.461555]        path_openat+0xa57/0xce0
[ 3437.461836]        do_filp_open+0xb4/0x160
[ 3437.462116]        do_sys_openat2+0x91/0xc0
[ 3437.462402]        __x64_sys_openat+0x53/0xa0
[ 3437.462701]        do_syscall_64+0x42/0xf0
[ 3437.462982]        entry_SYSCALL_64_after_hwframe+0x6e/0x76
[ 3437.463359]
               -> #1 (&sb->s_type->i_mutex_key#15){+.+.}-{3:3}:
[ 3437.463843]        down_write+0x3b/0xc0
[ 3437.464223]        bch2_write_iter+0x5b/0xcc0 [bcachefs]
[ 3437.464493]        vfs_write+0x21b/0x4c0
[ 3437.464653]        ksys_write+0x69/0xf0
[ 3437.464839]        do_syscall_64+0x42/0xf0
[ 3437.465009]        entry_SYSCALL_64_after_hwframe+0x6e/0x76
[ 3437.465231]
               -> #0 (sb_writers#10){.+.+}-{0:0}:
[ 3437.465471]        __lock_acquire+0x1455/0x21b0
[ 3437.465656]        lock_acquire+0xc6/0x2b0
[ 3437.465822]        mnt_want_write+0x46/0x1a0
[ 3437.465996]        filename_create+0x62/0x190
[ 3437.466175]        user_path_create+0x2d/0x50
[ 3437.466352]        bch2_fs_file_ioctl+0x2ec/0xc90 [bcachefs]
[ 3437.466617]        __x64_sys_ioctl+0x93/0xd0
[ 3437.466791]        do_syscall_64+0x42/0xf0
[ 3437.466957]        entry_SYSCALL_64_after_hwframe+0x6e/0x76
[ 3437.467180]
               other info that might help us debug this:

[ 3437.469670] 2 locks held by bcachefs/35533:
               other info that might help us debug this:

[ 3437.467507] Chain exists of:
                 sb_writers#10 --> &c->snapshot_create_lock --> &type->s_umount_key#48

[ 3437.467979]  Possible unsafe locking scenario:

[ 3437.468223]        CPU0                    CPU1
[ 3437.468405]        ----                    ----
[ 3437.468585]   rlock(&type->s_umount_key#48);
[ 3437.468758]                                lock(&c->snapshot_create_lock);
[ 3437.469030]                                lock(&type->s_umount_key#48);
[ 3437.469291]   rlock(sb_writers#10);
[ 3437.469434]
                *** DEADLOCK ***

[ 3437.469670] 2 locks held by bcachefs/35533:
[ 3437.469838]  #0: ffffa0a02ce00a88 (&c->snapshot_create_lock){++++}-{3:3}, at: bch2_fs_file_ioctl+0x1e3/0xc90 [bcachefs]
[ 3437.470294]  #1: ffffa0a02b2b10e0 (&type->s_umount_key#48){.+.+}-{3:3}, at: bch2_fs_file_ioctl+0x232/0xc90 [bcachefs]
[ 3437.470744]
               stack backtrace:
[ 3437.470922] CPU: 7 PID: 35533 Comm: bcachefs Kdump: loaded Tainted: G            E      6.7.0-rc7-custom+ #85
[ 3437.471313] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014
[ 3437.471694] Call Trace:
[ 3437.471795]  <TASK>
[ 3437.471884]  dump_stack_lvl+0x57/0x90
[ 3437.472035]  check_noncircular+0x132/0x150
[ 3437.472202]  __lock_acquire+0x1455/0x21b0
[ 3437.472369]  lock_acquire+0xc6/0x2b0
[ 3437.472518]  ? filename_create+0x62/0x190
[ 3437.472683]  ? lock_is_held_type+0x97/0x110
[ 3437.472856]  mnt_want_write+0x46/0x1a0
[ 3437.473025]  ? filename_create+0x62/0x190
[ 3437.473204]  filename_create+0x62/0x190
[ 3437.473380]  user_path_create+0x2d/0x50
[ 3437.473555]  bch2_fs_file_ioctl+0x2ec/0xc90 [bcachefs]
[ 3437.473819]  ? lock_acquire+0xc6/0x2b0
[ 3437.474002]  ? __fget_files+0x2a/0x190
[ 3437.474195]  ? __fget_files+0xbc/0x190
[ 3437.474380]  ? lock_release+0xc5/0x270
[ 3437.474567]  ? __x64_sys_ioctl+0x93/0xd0
[ 3437.474764]  ? __pfx_bch2_fs_file_ioctl+0x10/0x10 [bcachefs]
[ 3437.475090]  __x64_sys_ioctl+0x93/0xd0
[ 3437.475277]  do_syscall_64+0x42/0xf0
[ 3437.475454]  entry_SYSCALL_64_after_hwframe+0x6e/0x76
[ 3437.475691] RIP: 0033:0x7f2743c313af
======================================================

In __bch2_ioctl_subvolume_create(), we grab s_umount unconditionally
and unlock it at the end of the function. There is a comment
"why do we need this lock?" about the lock coming from
commit 42d237320e98 ("bcachefs: Snapshot creation, deletion")
The reason is that __bch2_ioctl_subvolume_create() calls
sync_inodes_sb() which enforce locked s_umount to writeback all dirty
nodes before doing snapshot works.

Fix it by read locking s_umount for snapshotting only and unlocking
s_umount after sync_inodes_sb().

Signed-off-by: Su Yue <glass.su@suse.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs-ioctl.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index e0a19a73c8e1a..1346861ed9443 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -337,11 +337,12 @@ static long __bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp,
 	if (arg.flags & BCH_SUBVOL_SNAPSHOT_RO)
 		create_flags |= BCH_CREATE_SNAPSHOT_RO;
 
-	/* why do we need this lock? */
-	down_read(&c->vfs_sb->s_umount);
-
-	if (arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE)
+	if (arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE) {
+		/* sync_inodes_sb enforce s_umount is locked */
+		down_read(&c->vfs_sb->s_umount);
 		sync_inodes_sb(c->vfs_sb);
+		up_read(&c->vfs_sb->s_umount);
+	}
 retry:
 	if (arg.src_ptr) {
 		error = user_path_at(arg.dirfd,
@@ -425,8 +426,6 @@ err2:
 		goto retry;
 	}
 err1:
-	up_read(&c->vfs_sb->s_umount);
-
 	return error;
 }
 
-- 
GitLab


From ec4edd7b9d2038a97e0ba3fad8fc8492b0d12d35 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 16 Jan 2024 13:29:59 -0500
Subject: [PATCH 3110/4076] bcachefs: Prep work for variable size btree node
 buffers

bcachefs btree nodes are big - typically 256k - and btree roots are
pinned in memory. As we're now up to 18 btrees, we now have significant
memory overhead in mostly empty btree roots.

And in the future we're going to start enforcing that certain btree node
boundaries exist, to solve lock contention issues - analagous to XFS's
AGIs.

Thus, we need to start allocating smaller btree node buffers when we
can. This patch changes code that refers to the filesystem constant
c->opts.btree_node_size to refer to the btree node buffer size -
btree_buf_bytes() - where appropriate.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/backpointers.c          |  2 +-
 fs/bcachefs/backpointers.h          |  1 +
 fs/bcachefs/bcachefs.h              |  5 ----
 fs/bcachefs/bset.c                  |  5 ++--
 fs/bcachefs/bset.h                  |  3 +--
 fs/bcachefs/btree_cache.c           | 12 ++++-----
 fs/bcachefs/btree_cache.h           | 19 ++++++++-----
 fs/bcachefs/btree_io.c              | 38 +++++++++++++-------------
 fs/bcachefs/btree_trans_commit.c    |  9 +++----
 fs/bcachefs/btree_update_interior.c |  8 +++---
 fs/bcachefs/btree_update_interior.h | 42 ++++++++++++-----------------
 fs/bcachefs/btree_write_buffer.c    |  7 +++--
 fs/bcachefs/debug.c                 | 16 +++++------
 fs/bcachefs/extents.c               |  1 +
 fs/bcachefs/move.c                  | 10 ++++---
 fs/bcachefs/super.c                 |  2 +-
 fs/bcachefs/sysfs.c                 |  2 +-
 fs/bcachefs/trace.h                 |  2 +-
 18 files changed, 87 insertions(+), 97 deletions(-)

diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index bf828f1f28d2b..b4dc319bcb2bc 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -560,7 +560,7 @@ static size_t btree_nodes_fit_in_ram(struct bch_fs *c)
 
 	si_meminfo(&i);
 	mem_bytes = i.totalram * i.mem_unit;
-	return div_u64(mem_bytes >> 1, btree_bytes(c));
+	return div_u64(mem_bytes >> 1, c->opts.btree_node_size);
 }
 
 static int bch2_get_btree_in_memory_pos(struct btree_trans *trans,
diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h
index 737e2396ade7e..327365a9feac4 100644
--- a/fs/bcachefs/backpointers.h
+++ b/fs/bcachefs/backpointers.h
@@ -2,6 +2,7 @@
 #ifndef _BCACHEFS_BACKPOINTERS_BACKGROUND_H
 #define _BCACHEFS_BACKPOINTERS_BACKGROUND_H
 
+#include "btree_cache.h"
 #include "btree_iter.h"
 #include "btree_update.h"
 #include "buckets.h"
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index dac383e371816..b80c6c9efd8ce 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -1204,11 +1204,6 @@ static inline unsigned block_sectors(const struct bch_fs *c)
 	return c->opts.block_size >> 9;
 }
 
-static inline size_t btree_sectors(const struct bch_fs *c)
-{
-	return c->opts.btree_node_size >> 9;
-}
-
 static inline bool btree_id_cached(const struct bch_fs *c, enum btree_id btree)
 {
 	return c->btree_key_cache_btrees & (1U << btree);
diff --git a/fs/bcachefs/bset.c b/fs/bcachefs/bset.c
index 044fff9b2cf6e..3fd1085b6c61e 100644
--- a/fs/bcachefs/bset.c
+++ b/fs/bcachefs/bset.c
@@ -823,13 +823,12 @@ void bch2_bset_init_first(struct btree *b, struct bset *i)
 	set_btree_bset(b, t, i);
 }
 
-void bch2_bset_init_next(struct bch_fs *c, struct btree *b,
-			 struct btree_node_entry *bne)
+void bch2_bset_init_next(struct btree *b, struct btree_node_entry *bne)
 {
 	struct bset *i = &bne->keys;
 	struct bset_tree *t;
 
-	BUG_ON(bset_byte_offset(b, bne) >= btree_bytes(c));
+	BUG_ON(bset_byte_offset(b, bne) >= btree_buf_bytes(b));
 	BUG_ON((void *) bne < (void *) btree_bkey_last(b, bset_tree_last(b)));
 	BUG_ON(b->nsets >= MAX_BSETS);
 
diff --git a/fs/bcachefs/bset.h b/fs/bcachefs/bset.h
index 632c2b8c54609..79c77baaa3838 100644
--- a/fs/bcachefs/bset.h
+++ b/fs/bcachefs/bset.h
@@ -264,8 +264,7 @@ static inline struct bset *bset_next_set(struct btree *b,
 void bch2_btree_keys_init(struct btree *);
 
 void bch2_bset_init_first(struct btree *, struct bset *);
-void bch2_bset_init_next(struct bch_fs *, struct btree *,
-			 struct btree_node_entry *);
+void bch2_bset_init_next(struct btree *, struct btree_node_entry *);
 void bch2_bset_build_aux_tree(struct btree *, struct bset_tree *, bool);
 
 void bch2_bset_insert(struct btree *, struct btree_node_iter *,
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 8e2488a4b58d0..d7c81beac14af 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -60,7 +60,7 @@ static void btree_node_data_free(struct bch_fs *c, struct btree *b)
 
 	clear_btree_node_just_written(b);
 
-	kvpfree(b->data, btree_bytes(c));
+	kvpfree(b->data, btree_buf_bytes(b));
 	b->data = NULL;
 #ifdef __KERNEL__
 	kvfree(b->aux_data);
@@ -94,7 +94,7 @@ static int btree_node_data_alloc(struct bch_fs *c, struct btree *b, gfp_t gfp)
 {
 	BUG_ON(b->data || b->aux_data);
 
-	b->data = kvpmalloc(btree_bytes(c), gfp);
+	b->data = kvpmalloc(btree_buf_bytes(b), gfp);
 	if (!b->data)
 		return -BCH_ERR_ENOMEM_btree_node_mem_alloc;
 #ifdef __KERNEL__
@@ -107,7 +107,7 @@ static int btree_node_data_alloc(struct bch_fs *c, struct btree *b, gfp_t gfp)
 		b->aux_data = NULL;
 #endif
 	if (!b->aux_data) {
-		kvpfree(b->data, btree_bytes(c));
+		kvpfree(b->data, btree_buf_bytes(b));
 		b->data = NULL;
 		return -BCH_ERR_ENOMEM_btree_node_mem_alloc;
 	}
@@ -126,7 +126,7 @@ static struct btree *__btree_node_mem_alloc(struct bch_fs *c, gfp_t gfp)
 	bkey_btree_ptr_init(&b->key);
 	INIT_LIST_HEAD(&b->list);
 	INIT_LIST_HEAD(&b->write_blocked);
-	b->byte_order = ilog2(btree_bytes(c));
+	b->byte_order = ilog2(c->opts.btree_node_size);
 	return b;
 }
 
@@ -408,7 +408,7 @@ void bch2_fs_btree_cache_exit(struct bch_fs *c)
 	if (c->verify_data)
 		list_move(&c->verify_data->list, &bc->live);
 
-	kvpfree(c->verify_ondisk, btree_bytes(c));
+	kvpfree(c->verify_ondisk, c->opts.btree_node_size);
 
 	for (i = 0; i < btree_id_nr_alive(c); i++) {
 		struct btree_root *r = bch2_btree_id_root(c, i);
@@ -1192,7 +1192,7 @@ void bch2_btree_node_to_text(struct printbuf *out, struct bch_fs *c, const struc
 	       "    failed unpacked %zu\n",
 	       b->unpack_fn_len,
 	       b->nr.live_u64s * sizeof(u64),
-	       btree_bytes(c) - sizeof(struct btree_node),
+	       btree_buf_bytes(b) - sizeof(struct btree_node),
 	       b->nr.live_u64s * 100 / btree_max_u64s(c),
 	       b->sib_u64s[0],
 	       b->sib_u64s[1],
diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h
index 4e1af58820522..6d33885fdbde0 100644
--- a/fs/bcachefs/btree_cache.h
+++ b/fs/bcachefs/btree_cache.h
@@ -74,22 +74,27 @@ static inline bool btree_node_hashed(struct btree *b)
 	     _iter = 0;	_iter < (_tbl)->size; _iter++)			\
 		rht_for_each_entry_rcu((_b), (_pos), _tbl, _iter, hash)
 
-static inline size_t btree_bytes(struct bch_fs *c)
+static inline size_t btree_buf_bytes(const struct btree *b)
 {
-	return c->opts.btree_node_size;
+	return 1UL << b->byte_order;
 }
 
-static inline size_t btree_max_u64s(struct bch_fs *c)
+static inline size_t btree_buf_max_u64s(const struct btree *b)
 {
-	return (btree_bytes(c) - sizeof(struct btree_node)) / sizeof(u64);
+	return (btree_buf_bytes(b) - sizeof(struct btree_node)) / sizeof(u64);
 }
 
-static inline size_t btree_pages(struct bch_fs *c)
+static inline size_t btree_max_u64s(const struct bch_fs *c)
 {
-	return btree_bytes(c) / PAGE_SIZE;
+	return (c->opts.btree_node_size - sizeof(struct btree_node)) / sizeof(u64);
 }
 
-static inline unsigned btree_blocks(struct bch_fs *c)
+static inline size_t btree_sectors(const struct bch_fs *c)
+{
+	return c->opts.btree_node_size >> SECTOR_SHIFT;
+}
+
+static inline unsigned btree_blocks(const struct bch_fs *c)
 {
 	return btree_sectors(c) >> c->block_bits;
 }
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 33db48e2153fe..aa9b6cbe32269 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -112,7 +112,7 @@ static void *btree_bounce_alloc(struct bch_fs *c, size_t size,
 	unsigned flags = memalloc_nofs_save();
 	void *p;
 
-	BUG_ON(size > btree_bytes(c));
+	BUG_ON(size > c->opts.btree_node_size);
 
 	*used_mempool = false;
 	p = vpmalloc(size, __GFP_NOWARN|GFP_NOWAIT);
@@ -174,8 +174,8 @@ static void bch2_sort_whiteouts(struct bch_fs *c, struct btree *b)
 
 	ptrs = ptrs_end = ((void *) new_whiteouts + bytes);
 
-	for (k = unwritten_whiteouts_start(c, b);
-	     k != unwritten_whiteouts_end(c, b);
+	for (k = unwritten_whiteouts_start(b);
+	     k != unwritten_whiteouts_end(b);
 	     k = bkey_p_next(k))
 		*--ptrs = k;
 
@@ -192,7 +192,7 @@ static void bch2_sort_whiteouts(struct bch_fs *c, struct btree *b)
 	verify_no_dups(b, new_whiteouts,
 		       (void *) ((u64 *) new_whiteouts + b->whiteout_u64s));
 
-	memcpy_u64s(unwritten_whiteouts_start(c, b),
+	memcpy_u64s(unwritten_whiteouts_start(b),
 		    new_whiteouts, b->whiteout_u64s);
 
 	btree_bounce_free(c, bytes, used_mempool, new_whiteouts);
@@ -313,7 +313,7 @@ static void btree_node_sort(struct bch_fs *c, struct btree *b,
 	}
 
 	bytes = sorting_entire_node
-		? btree_bytes(c)
+		? btree_buf_bytes(b)
 		: __vstruct_bytes(struct btree_node, u64s);
 
 	out = btree_bounce_alloc(c, bytes, &used_mempool);
@@ -338,7 +338,7 @@ static void btree_node_sort(struct bch_fs *c, struct btree *b,
 	if (sorting_entire_node) {
 		u64s = le16_to_cpu(out->keys.u64s);
 
-		BUG_ON(bytes != btree_bytes(c));
+		BUG_ON(bytes != btree_buf_bytes(b));
 
 		/*
 		 * Our temporary buffer is the same size as the btree node's
@@ -502,7 +502,7 @@ void bch2_btree_init_next(struct btree_trans *trans, struct btree *b)
 
 	bne = want_new_bset(c, b);
 	if (bne)
-		bch2_bset_init_next(c, b, bne);
+		bch2_bset_init_next(b, bne);
 
 	bch2_btree_build_aux_trees(b);
 
@@ -1160,7 +1160,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 			     ptr_written, b->written);
 	} else {
 		for (bne = write_block(b);
-		     bset_byte_offset(b, bne) < btree_bytes(c);
+		     bset_byte_offset(b, bne) < btree_buf_bytes(b);
 		     bne = (void *) bne + block_bytes(c))
 			btree_err_on(bne->keys.seq == b->data->keys.seq &&
 				     !bch2_journal_seq_is_blacklisted(c,
@@ -1172,7 +1172,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 				     "found bset signature after last bset");
 	}
 
-	sorted = btree_bounce_alloc(c, btree_bytes(c), &used_mempool);
+	sorted = btree_bounce_alloc(c, btree_buf_bytes(b), &used_mempool);
 	sorted->keys.u64s = 0;
 
 	set_btree_bset(b, b->set, &b->data->keys);
@@ -1188,7 +1188,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 	BUG_ON(b->nr.live_u64s != u64s);
 
-	btree_bounce_free(c, btree_bytes(c), used_mempool, sorted);
+	btree_bounce_free(c, btree_buf_bytes(b), used_mempool, sorted);
 
 	if (updated_range)
 		bch2_btree_node_drop_keys_outside_node(b);
@@ -1284,7 +1284,7 @@ static void btree_node_read_work(struct work_struct *work)
 		rb->have_ioref		= bch2_dev_get_ioref(ca, READ);
 		bio_reset(bio, NULL, REQ_OP_READ|REQ_SYNC|REQ_META);
 		bio->bi_iter.bi_sector	= rb->pick.ptr.offset;
-		bio->bi_iter.bi_size	= btree_bytes(c);
+		bio->bi_iter.bi_size	= btree_buf_bytes(b);
 
 		if (rb->have_ioref) {
 			bio_set_dev(bio, ca->disk_sb.bdev);
@@ -1512,7 +1512,7 @@ fsck_err:
 	}
 
 	if (best >= 0) {
-		memcpy(b->data, ra->buf[best], btree_bytes(c));
+		memcpy(b->data, ra->buf[best], btree_buf_bytes(b));
 		ret = bch2_btree_node_read_done(c, NULL, b, false, saw_error);
 	} else {
 		ret = -1;
@@ -1578,7 +1578,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 	for (i = 0; i < ra->nr; i++) {
 		ra->buf[i] = mempool_alloc(&c->btree_bounce_pool, GFP_NOFS);
 		ra->bio[i] = bio_alloc_bioset(NULL,
-					      buf_pages(ra->buf[i], btree_bytes(c)),
+					      buf_pages(ra->buf[i], btree_buf_bytes(b)),
 					      REQ_OP_READ|REQ_SYNC|REQ_META,
 					      GFP_NOFS,
 					      &c->btree_bio);
@@ -1598,7 +1598,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 		rb->pick		= pick;
 		rb->bio.bi_iter.bi_sector = pick.ptr.offset;
 		rb->bio.bi_end_io	= btree_node_read_all_replicas_endio;
-		bch2_bio_map(&rb->bio, ra->buf[i], btree_bytes(c));
+		bch2_bio_map(&rb->bio, ra->buf[i], btree_buf_bytes(b));
 
 		if (rb->have_ioref) {
 			this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_btree],
@@ -1665,7 +1665,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 	ca = bch_dev_bkey_exists(c, pick.ptr.dev);
 
 	bio = bio_alloc_bioset(NULL,
-			       buf_pages(b->data, btree_bytes(c)),
+			       buf_pages(b->data, btree_buf_bytes(b)),
 			       REQ_OP_READ|REQ_SYNC|REQ_META,
 			       GFP_NOFS,
 			       &c->btree_bio);
@@ -1679,7 +1679,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 	INIT_WORK(&rb->work, btree_node_read_work);
 	bio->bi_iter.bi_sector	= pick.ptr.offset;
 	bio->bi_end_io		= btree_node_read_endio;
-	bch2_bio_map(bio, b->data, btree_bytes(c));
+	bch2_bio_map(bio, b->data, btree_buf_bytes(b));
 
 	if (rb->have_ioref) {
 		this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_btree],
@@ -2074,8 +2074,8 @@ do_write:
 	i->u64s		= 0;
 
 	sort_iter_add(&sort_iter.iter,
-		      unwritten_whiteouts_start(c, b),
-		      unwritten_whiteouts_end(c, b));
+		      unwritten_whiteouts_start(b),
+		      unwritten_whiteouts_end(b));
 	SET_BSET_SEPARATE_WHITEOUTS(i, false);
 
 	b->whiteout_u64s = 0;
@@ -2251,7 +2251,7 @@ bool bch2_btree_post_write_cleanup(struct bch_fs *c, struct btree *b)
 
 	bne = want_new_bset(c, b);
 	if (bne)
-		bch2_bset_init_next(c, b, bne);
+		bch2_bset_init_next(b, bne);
 
 	bch2_btree_build_aux_trees(b);
 
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index ab00d202361eb..10f2478e45d18 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -139,8 +139,7 @@ bool bch2_btree_bset_insert_key(struct btree_trans *trans,
 	EBUG_ON(bkey_deleted(&insert->k) && bkey_val_u64s(&insert->k));
 	EBUG_ON(bpos_lt(insert->k.p, b->data->min_key));
 	EBUG_ON(bpos_gt(insert->k.p, b->data->max_key));
-	EBUG_ON(insert->k.u64s >
-		bch_btree_keys_u64s_remaining(trans->c, b));
+	EBUG_ON(insert->k.u64s > bch2_btree_keys_u64s_remaining(b));
 	EBUG_ON(!b->c.level && !bpos_eq(insert->k.p, path->pos));
 
 	k = bch2_btree_node_iter_peek_all(node_iter, b);
@@ -160,7 +159,7 @@ bool bch2_btree_bset_insert_key(struct btree_trans *trans,
 		k->type = KEY_TYPE_deleted;
 
 		if (k->needs_whiteout)
-			push_whiteout(trans->c, b, insert->k.p);
+			push_whiteout(b, insert->k.p);
 		k->needs_whiteout = false;
 
 		if (k >= btree_bset_last(b)->start) {
@@ -348,9 +347,7 @@ static noinline void journal_transaction_name(struct btree_trans *trans)
 static inline int btree_key_can_insert(struct btree_trans *trans,
 				       struct btree *b, unsigned u64s)
 {
-	struct bch_fs *c = trans->c;
-
-	if (!bch2_btree_node_insert_fits(c, b, u64s))
+	if (!bch2_btree_node_insert_fits(b, u64s))
 		return -BCH_ERR_btree_insert_btree_node_full;
 
 	return 0;
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 44f9dfa28a09d..17a5938aa71a6 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -159,7 +159,7 @@ static bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b,
 {
 	size_t u64s = btree_node_u64s_with_format(nr, &b->format, new_f);
 
-	return __vstruct_bytes(struct btree_node, u64s) < btree_bytes(c);
+	return __vstruct_bytes(struct btree_node, u64s) < btree_buf_bytes(b);
 }
 
 /* Btree node freeing/allocation: */
@@ -1097,7 +1097,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 		 * Always check for space for two keys, even if we won't have to
 		 * split at prior level - it might have been a merge instead:
 		 */
-		if (bch2_btree_node_insert_fits(c, path->l[update_level].b,
+		if (bch2_btree_node_insert_fits(path->l[update_level].b,
 						BKEY_BTREE_PTR_U64s_MAX * 2))
 			break;
 
@@ -1401,7 +1401,7 @@ static void __btree_split_node(struct btree_update *as,
 
 		unsigned u64s = nr_keys[i].nr_keys * n[i]->data->format.key_u64s +
 			nr_keys[i].val_u64s;
-		if (__vstruct_bytes(struct btree_node, u64s) > btree_bytes(as->c))
+		if (__vstruct_bytes(struct btree_node, u64s) > btree_buf_bytes(b))
 			n[i]->data->format = b->format;
 
 		btree_node_set_format(n[i], n[i]->data->format);
@@ -1703,7 +1703,7 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t
 
 	bch2_btree_node_prep_for_write(trans, path, b);
 
-	if (!bch2_btree_node_insert_fits(c, b, bch2_keylist_u64s(keys))) {
+	if (!bch2_btree_node_insert_fits(b, bch2_keylist_u64s(keys))) {
 		bch2_btree_node_unlock_write(trans, path, b);
 		goto split;
 	}
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index adfc62083844c..c593c925d1e3b 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -184,21 +184,19 @@ static inline void btree_node_reset_sib_u64s(struct btree *b)
 	b->sib_u64s[1] = b->nr.live_u64s;
 }
 
-static inline void *btree_data_end(struct bch_fs *c, struct btree *b)
+static inline void *btree_data_end(struct btree *b)
 {
-	return (void *) b->data + btree_bytes(c);
+	return (void *) b->data + btree_buf_bytes(b);
 }
 
-static inline struct bkey_packed *unwritten_whiteouts_start(struct bch_fs *c,
-							    struct btree *b)
+static inline struct bkey_packed *unwritten_whiteouts_start(struct btree *b)
 {
-	return (void *) ((u64 *) btree_data_end(c, b) - b->whiteout_u64s);
+	return (void *) ((u64 *) btree_data_end(b) - b->whiteout_u64s);
 }
 
-static inline struct bkey_packed *unwritten_whiteouts_end(struct bch_fs *c,
-							  struct btree *b)
+static inline struct bkey_packed *unwritten_whiteouts_end(struct btree *b)
 {
-	return btree_data_end(c, b);
+	return btree_data_end(b);
 }
 
 static inline void *write_block(struct btree *b)
@@ -221,13 +219,11 @@ static inline bool bkey_written(struct btree *b, struct bkey_packed *k)
 	return __btree_addr_written(b, k);
 }
 
-static inline ssize_t __bch_btree_u64s_remaining(struct bch_fs *c,
-						 struct btree *b,
-						 void *end)
+static inline ssize_t __bch2_btree_u64s_remaining(struct btree *b, void *end)
 {
 	ssize_t used = bset_byte_offset(b, end) / sizeof(u64) +
 		b->whiteout_u64s;
-	ssize_t total = c->opts.btree_node_size >> 3;
+	ssize_t total = btree_buf_bytes(b) >> 3;
 
 	/* Always leave one extra u64 for bch2_varint_decode: */
 	used++;
@@ -235,10 +231,9 @@ static inline ssize_t __bch_btree_u64s_remaining(struct bch_fs *c,
 	return total - used;
 }
 
-static inline size_t bch_btree_keys_u64s_remaining(struct bch_fs *c,
-						   struct btree *b)
+static inline size_t bch2_btree_keys_u64s_remaining(struct btree *b)
 {
-	ssize_t remaining = __bch_btree_u64s_remaining(c, b,
+	ssize_t remaining = __bch2_btree_u64s_remaining(b,
 				btree_bkey_last(b, bset_tree_last(b)));
 
 	BUG_ON(remaining < 0);
@@ -260,14 +255,13 @@ static inline unsigned btree_write_set_buffer(struct btree *b)
 	return 8 << BTREE_WRITE_SET_U64s_BITS;
 }
 
-static inline struct btree_node_entry *want_new_bset(struct bch_fs *c,
-						     struct btree *b)
+static inline struct btree_node_entry *want_new_bset(struct bch_fs *c, struct btree *b)
 {
 	struct bset_tree *t = bset_tree_last(b);
 	struct btree_node_entry *bne = max(write_block(b),
 			(void *) btree_bkey_last(b, bset_tree_last(b)));
 	ssize_t remaining_space =
-		__bch_btree_u64s_remaining(c, b, bne->keys.start);
+		__bch2_btree_u64s_remaining(b, bne->keys.start);
 
 	if (unlikely(bset_written(b, bset(b, t)))) {
 		if (remaining_space > (ssize_t) (block_bytes(c) >> 3))
@@ -281,12 +275,11 @@ static inline struct btree_node_entry *want_new_bset(struct bch_fs *c,
 	return NULL;
 }
 
-static inline void push_whiteout(struct bch_fs *c, struct btree *b,
-				 struct bpos pos)
+static inline void push_whiteout(struct btree *b, struct bpos pos)
 {
 	struct bkey_packed k;
 
-	BUG_ON(bch_btree_keys_u64s_remaining(c, b) < BKEY_U64s);
+	BUG_ON(bch2_btree_keys_u64s_remaining(b) < BKEY_U64s);
 	EBUG_ON(btree_node_just_written(b));
 
 	if (!bkey_pack_pos(&k, pos, b)) {
@@ -299,20 +292,19 @@ static inline void push_whiteout(struct bch_fs *c, struct btree *b,
 	k.needs_whiteout = true;
 
 	b->whiteout_u64s += k.u64s;
-	bkey_p_copy(unwritten_whiteouts_start(c, b), &k);
+	bkey_p_copy(unwritten_whiteouts_start(b), &k);
 }
 
 /*
  * write lock must be held on @b (else the dirty bset that we were going to
  * insert into could be written out from under us)
  */
-static inline bool bch2_btree_node_insert_fits(struct bch_fs *c,
-					       struct btree *b, unsigned u64s)
+static inline bool bch2_btree_node_insert_fits(struct btree *b, unsigned u64s)
 {
 	if (unlikely(btree_node_need_rewrite(b)))
 		return false;
 
-	return u64s <= bch_btree_keys_u64s_remaining(c, b);
+	return u64s <= bch2_btree_keys_u64s_remaining(b);
 }
 
 void bch2_btree_updates_to_text(struct printbuf *, struct bch_fs *);
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index 5c1169c78dafe..ac78448619663 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -125,13 +125,12 @@ static inline int wb_flush_one(struct btree_trans *trans, struct btree_iter *ite
 			       struct btree_write_buffered_key *wb,
 			       bool *write_locked, size_t *fast)
 {
-	struct bch_fs *c = trans->c;
 	struct btree_path *path;
 	int ret;
 
 	EBUG_ON(!wb->journal_seq);
-	EBUG_ON(!c->btree_write_buffer.flushing.pin.seq);
-	EBUG_ON(c->btree_write_buffer.flushing.pin.seq > wb->journal_seq);
+	EBUG_ON(!trans->c->btree_write_buffer.flushing.pin.seq);
+	EBUG_ON(trans->c->btree_write_buffer.flushing.pin.seq > wb->journal_seq);
 
 	ret = bch2_btree_iter_traverse(iter);
 	if (ret)
@@ -155,7 +154,7 @@ static inline int wb_flush_one(struct btree_trans *trans, struct btree_iter *ite
 		*write_locked = true;
 	}
 
-	if (unlikely(!bch2_btree_node_insert_fits(c, path->l[0].b, wb->k.k.u64s))) {
+	if (unlikely(!bch2_btree_node_insert_fits(path->l[0].b, wb->k.k.u64s))) {
 		*write_locked = false;
 		return wb_flush_one_slowpath(trans, iter, wb);
 	}
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index d6418948495f8..cadda9bbe4a4c 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -44,19 +44,19 @@ static bool bch2_btree_verify_replica(struct bch_fs *c, struct btree *b,
 		return false;
 
 	bio = bio_alloc_bioset(ca->disk_sb.bdev,
-			       buf_pages(n_sorted, btree_bytes(c)),
+			       buf_pages(n_sorted, btree_buf_bytes(b)),
 			       REQ_OP_READ|REQ_META,
 			       GFP_NOFS,
 			       &c->btree_bio);
 	bio->bi_iter.bi_sector	= pick.ptr.offset;
-	bch2_bio_map(bio, n_sorted, btree_bytes(c));
+	bch2_bio_map(bio, n_sorted, btree_buf_bytes(b));
 
 	submit_bio_wait(bio);
 
 	bio_put(bio);
 	percpu_ref_put(&ca->io_ref);
 
-	memcpy(n_ondisk, n_sorted, btree_bytes(c));
+	memcpy(n_ondisk, n_sorted, btree_buf_bytes(b));
 
 	v->written = 0;
 	if (bch2_btree_node_read_done(c, ca, v, false, &saw_error) || saw_error)
@@ -137,7 +137,7 @@ void __bch2_btree_verify(struct bch_fs *c, struct btree *b)
 	mutex_lock(&c->verify_lock);
 
 	if (!c->verify_ondisk) {
-		c->verify_ondisk = kvpmalloc(btree_bytes(c), GFP_KERNEL);
+		c->verify_ondisk = kvpmalloc(btree_buf_bytes(b), GFP_KERNEL);
 		if (!c->verify_ondisk)
 			goto out;
 	}
@@ -199,19 +199,19 @@ void bch2_btree_node_ondisk_to_text(struct printbuf *out, struct bch_fs *c,
 		return;
 	}
 
-	n_ondisk = kvpmalloc(btree_bytes(c), GFP_KERNEL);
+	n_ondisk = kvpmalloc(btree_buf_bytes(b), GFP_KERNEL);
 	if (!n_ondisk) {
 		prt_printf(out, "memory allocation failure\n");
 		goto out;
 	}
 
 	bio = bio_alloc_bioset(ca->disk_sb.bdev,
-			       buf_pages(n_ondisk, btree_bytes(c)),
+			       buf_pages(n_ondisk, btree_buf_bytes(b)),
 			       REQ_OP_READ|REQ_META,
 			       GFP_NOFS,
 			       &c->btree_bio);
 	bio->bi_iter.bi_sector	= pick.ptr.offset;
-	bch2_bio_map(bio, n_ondisk, btree_bytes(c));
+	bch2_bio_map(bio, n_ondisk, btree_buf_bytes(b));
 
 	ret = submit_bio_wait(bio);
 	if (ret) {
@@ -293,7 +293,7 @@ void bch2_btree_node_ondisk_to_text(struct printbuf *out, struct bch_fs *c,
 out:
 	if (bio)
 		bio_put(bio);
-	kvpfree(n_ondisk, btree_bytes(c));
+	kvpfree(n_ondisk, btree_buf_bytes(b));
 	percpu_ref_put(&ca->io_ref);
 }
 
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index edb1e32d77831..3ae4aba4f151b 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -8,6 +8,7 @@
 
 #include "bcachefs.h"
 #include "bkey_methods.h"
+#include "btree_cache.h"
 #include "btree_gc.h"
 #include "btree_io.h"
 #include "btree_iter.h"
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 2e083daedfb2b..dc284a89bd2db 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -6,6 +6,7 @@
 #include "backpointers.h"
 #include "bkey_buf.h"
 #include "btree_gc.h"
+#include "btree_io.h"
 #include "btree_update.h"
 #include "btree_update_interior.h"
 #include "btree_write_buffer.h"
@@ -804,6 +805,8 @@ int bch2_evacuate_bucket(struct moving_context *ctxt,
 			if (!b)
 				goto next;
 
+			unsigned sectors = btree_ptr_sectors_written(&b->key);
+
 			ret = bch2_btree_node_rewrite(trans, &iter, b, 0);
 			bch2_trans_iter_exit(trans, &iter);
 
@@ -813,11 +816,10 @@ int bch2_evacuate_bucket(struct moving_context *ctxt,
 				goto err;
 
 			if (ctxt->rate)
-				bch2_ratelimit_increment(ctxt->rate,
-							 c->opts.btree_node_size >> 9);
+				bch2_ratelimit_increment(ctxt->rate, sectors);
 			if (ctxt->stats) {
-				atomic64_add(c->opts.btree_node_size >> 9, &ctxt->stats->sectors_seen);
-				atomic64_add(c->opts.btree_node_size >> 9, &ctxt->stats->sectors_moved);
+				atomic64_add(sectors, &ctxt->stats->sectors_seen);
+				atomic64_add(sectors, &ctxt->stats->sectors_moved);
 			}
 		}
 next:
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index a3ec21f229ed6..9262a9298fcd1 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -883,7 +883,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	    !(c->pcpu = alloc_percpu(struct bch_fs_pcpu)) ||
 	    !(c->online_reserved = alloc_percpu(u64)) ||
 	    mempool_init_kvpmalloc_pool(&c->btree_bounce_pool, 1,
-					btree_bytes(c)) ||
+					c->opts.btree_node_size) ||
 	    mempool_init_kmalloc_pool(&c->large_bkey_pool, 1, 2048) ||
 	    !(c->unused_inode_hints = kcalloc(1U << c->inode_shard_bits,
 					      sizeof(u64), GFP_KERNEL))) {
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index 553190d719dfc..46c4e98dc1004 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -248,7 +248,7 @@ static size_t bch2_btree_cache_size(struct bch_fs *c)
 
 	mutex_lock(&c->btree_cache.lock);
 	list_for_each_entry(b, &c->btree_cache.live, list)
-		ret += btree_bytes(c);
+		ret += btree_buf_bytes(b);
 
 	mutex_unlock(&c->btree_cache.lock);
 	return ret;
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index 6ac1dfeaa8f29..293b90d704fb5 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -1013,7 +1013,7 @@ TRACE_EVENT(trans_restart_split_race,
 		__entry->level		= b->c.level;
 		__entry->written	= b->written;
 		__entry->blocks		= btree_blocks(trans->c);
-		__entry->u64s_remaining	= bch_btree_keys_u64s_remaining(trans->c, b);
+		__entry->u64s_remaining	= bch2_btree_keys_u64s_remaining(b);
 	),
 
 	TP_printk("%s %pS l=%u written %u/%u u64s remaining %u",
-- 
GitLab


From d7e77f53e90e1eb87838eed7c651531427b9114a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 16 Jan 2024 16:20:21 -0500
Subject: [PATCH 3111/4076] bcachefs: opts->compression can now also be applied
 in the background

The "apply this compression method in the background" paths now use the
compression option if background_compression is not set; this means that
setting or changing the compression option will cause existing data to
be compressed accordingly in the background.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/data_update.c | 6 ++----
 fs/bcachefs/extents.c     | 4 +++-
 fs/bcachefs/extents.h     | 2 +-
 fs/bcachefs/io_misc.c     | 4 +---
 fs/bcachefs/io_write.c    | 4 +---
 fs/bcachefs/move.c        | 2 +-
 fs/bcachefs/opts.h        | 5 +++++
 fs/bcachefs/rebalance.c   | 5 ++---
 fs/bcachefs/reflink.c     | 4 +---
 fs/bcachefs/sysfs.c       | 6 ++++--
 fs/bcachefs/xattr.c       | 5 +++--
 11 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 6f13477ff652e..4150feca42a2e 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -285,9 +285,7 @@ restart_drop_extra_replicas:
 						k.k->p, bkey_start_pos(&insert->k)) ?:
 			bch2_insert_snapshot_whiteouts(trans, m->btree_id,
 						k.k->p, insert->k.p) ?:
-			bch2_bkey_set_needs_rebalance(c, insert,
-						      op->opts.background_target,
-						      op->opts.background_compression) ?:
+			bch2_bkey_set_needs_rebalance(c, insert, &op->opts) ?:
 			bch2_trans_update(trans, &iter, insert,
 				BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
 			bch2_trans_commit(trans, &op->res,
@@ -529,7 +527,7 @@ int bch2_data_update_init(struct btree_trans *trans,
 		BCH_WRITE_DATA_ENCODED|
 		BCH_WRITE_MOVE|
 		m->data_opts.write_flags;
-	m->op.compression_opt	= io_opts.background_compression ?: io_opts.compression;
+	m->op.compression_opt	= background_compression(io_opts);
 	m->op.watermark		= m->data_opts.btree_insert_flags & BCH_WATERMARK_MASK;
 
 	bkey_for_each_ptr(ptrs, ptr)
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 3ae4aba4f151b..61395b113df9b 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -1335,10 +1335,12 @@ bool bch2_bkey_needs_rebalance(struct bch_fs *c, struct bkey_s_c k)
 }
 
 int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bkey_i *_k,
-				  unsigned target, unsigned compression)
+				  struct bch_io_opts *opts)
 {
 	struct bkey_s k = bkey_i_to_s(_k);
 	struct bch_extent_rebalance *r;
+	unsigned target = opts->background_target;
+	unsigned compression = background_compression(*opts);
 	bool needs_rebalance;
 
 	if (!bkey_extent_is_direct_data(k.k))
diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h
index a855c94d43ddb..6bf839d69e84e 100644
--- a/fs/bcachefs/extents.h
+++ b/fs/bcachefs/extents.h
@@ -708,7 +708,7 @@ unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *, struct bkey_s_c,
 bool bch2_bkey_needs_rebalance(struct bch_fs *, struct bkey_s_c);
 
 int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bkey_i *,
-				  unsigned, unsigned);
+				  struct bch_io_opts *);
 
 /* Generic extent code: */
 
diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c
index ca6d5f516aa2b..1baf78594ccaf 100644
--- a/fs/bcachefs/io_misc.c
+++ b/fs/bcachefs/io_misc.c
@@ -442,9 +442,7 @@ case LOGGED_OP_FINSERT_shift_extents:
 
 		op->v.pos = cpu_to_le64(insert ? bkey_start_offset(&delete.k) : delete.k.p.offset);
 
-		ret =   bch2_bkey_set_needs_rebalance(c, copy,
-					opts.background_target,
-					opts.background_compression) ?:
+		ret =   bch2_bkey_set_needs_rebalance(c, copy, &opts) ?:
 			bch2_btree_insert_trans(trans, BTREE_ID_extents, &delete, 0) ?:
 			bch2_btree_insert_trans(trans, BTREE_ID_extents, copy, 0) ?:
 			bch2_logged_op_update(trans, &op->k_i) ?:
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index e69c00fa32bdb..ef3a53f9045af 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -362,9 +362,7 @@ static int bch2_write_index_default(struct bch_write_op *op)
 				     bkey_start_pos(&sk.k->k),
 				     BTREE_ITER_SLOTS|BTREE_ITER_INTENT);
 
-		ret =   bch2_bkey_set_needs_rebalance(c, sk.k,
-					op->opts.background_target,
-					op->opts.background_compression) ?:
+		ret =   bch2_bkey_set_needs_rebalance(c, sk.k, &op->opts) ?:
 			bch2_extent_update(trans, inum, &iter, sk.k,
 					&op->res,
 					op->new_i_size, &op->i_sectors_delta,
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index dc284a89bd2db..bf68ea49447b9 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -58,7 +58,7 @@ static void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c
 
 	prt_str(out, "compression: ");
 	prt_tab(out);
-	bch2_compression_opt_to_text(out, io_opts->background_compression ?: io_opts->compression);
+	bch2_compression_opt_to_text(out, background_compression(*io_opts));
 	prt_newline(out);
 
 	prt_str(out, "extra replicas: ");
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 7414c564b5d83..9a4b7faa37650 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -564,6 +564,11 @@ struct bch_io_opts {
 #undef x
 };
 
+static inline unsigned background_compression(struct bch_io_opts opts)
+{
+	return opts.background_compression ?: opts.compression;
+}
+
 struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts);
 bool bch2_opt_is_inode_opt(enum bch_opt_id);
 
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index 2d22efed981a7..22d1017aa49b9 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -253,13 +253,12 @@ static bool rebalance_pred(struct bch_fs *c, void *arg,
 
 	if (k.k->p.inode) {
 		target		= io_opts->background_target;
-		compression	= io_opts->background_compression ?: io_opts->compression;
+		compression	= background_compression(*io_opts);
 	} else {
 		const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k);
 
 		target		= r ? r->target : io_opts->background_target;
-		compression	= r ? r->compression :
-			(io_opts->background_compression ?: io_opts->compression);
+		compression	= r ? r->compression : background_compression(*io_opts);
 	}
 
 	data_opts->rewrite_ptrs		= bch2_bkey_ptrs_need_rebalance(c, k, target, compression);
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index 98255aa64e226..c47c66c2b394d 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -545,9 +545,7 @@ s64 bch2_remap_range(struct bch_fs *c,
 				min(src_k.k->p.offset - src_want.offset,
 				    dst_end.offset - dst_iter.pos.offset));
 
-		ret =   bch2_bkey_set_needs_rebalance(c, new_dst.k,
-					opts.background_target,
-					opts.background_compression) ?:
+		ret =   bch2_bkey_set_needs_rebalance(c, new_dst.k, &opts) ?:
 			bch2_extent_update(trans, dst_inum, &dst_iter,
 					new_dst.k, &disk_res,
 					new_i_size, i_sectors_delta,
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index 46c4e98dc1004..cee80c47feea2 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -726,8 +726,10 @@ STORE(bch2_fs_opts_dir)
 	bch2_opt_set_sb(c, opt, v);
 	bch2_opt_set_by_id(&c->opts, id, v);
 
-	if ((id == Opt_background_target ||
-	     id == Opt_background_compression) && v)
+	if (v &&
+	    (id == Opt_background_target ||
+	     id == Opt_background_compression ||
+	     (id == Opt_compression && !c->opts.background_compression)))
 		bch2_set_rebalance_needs_scan(c, 0);
 
 	ret = size;
diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c
index 5a1858fb9879a..9c0d2316031b1 100644
--- a/fs/bcachefs/xattr.c
+++ b/fs/bcachefs/xattr.c
@@ -590,8 +590,9 @@ err:
 	mutex_unlock(&inode->ei_update_lock);
 
 	if (value &&
-	    (opt_id == Opt_background_compression ||
-	     opt_id == Opt_background_target))
+	    (opt_id == Opt_background_target ||
+	     opt_id == Opt_background_compression ||
+	     (opt_id == Opt_compression && !inode_opt_get(c, &inode->ei_inode, background_compression))))
 		bch2_set_rebalance_needs_scan(c, inode->ei_inode.bi_inum);
 
 	return bch2_err_class(ret);
-- 
GitLab


From 7be0208fc99207e86974f40a3b57949dae67976c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 17 Jan 2024 17:16:07 -0500
Subject: [PATCH 3112/4076] bcachefs: add missing __GFP_NOWARN

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_trans_commit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 10f2478e45d18..30d69a6d133ee 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -415,7 +415,7 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags
 		return 0;
 
 	new_u64s	= roundup_pow_of_two(u64s);
-	new_k		= krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOWAIT);
+	new_k		= krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOWAIT|__GFP_NOWARN);
 	if (unlikely(!new_k))
 		return btree_key_can_insert_cached_slowpath(trans, flags, path, new_u64s);
 
-- 
GitLab


From d32088f2f2f0f361caeb87dfc71b632231fd6c7b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 20 Jan 2024 23:35:41 -0500
Subject: [PATCH 3113/4076] bcachefs: bch_snapshot::btime

Add a field to bch_snapshot for creation time; this will be important
when we start exposing the snapshot tree to userspace.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 1 +
 fs/bcachefs/snapshot.c        | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 0d5ac4184fbce..a76036179238e 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -1149,6 +1149,7 @@ struct bch_snapshot {
 	__le32			tree;
 	__le32			depth;
 	__le32			skip[3];
+	bch_le128		btime;
 };
 
 LE32_BITMASK(BCH_SNAPSHOT_DELETED,	struct bch_snapshot, flags,  0,  1)
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index cdcff4e5ae5c3..45f67e8b29eb6 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -1053,6 +1053,8 @@ static int create_snapids(struct btree_trans *trans, u32 parent, u32 tree,
 		n->v.subvol	= cpu_to_le32(snapshot_subvols[i]);
 		n->v.tree	= cpu_to_le32(tree);
 		n->v.depth	= cpu_to_le32(depth);
+		n->v.btime.lo	= cpu_to_le64(bch2_current_time(c));
+		n->v.btime.hi	= 0;
 
 		for (j = 0; j < ARRAY_SIZE(n->v.skip); j++)
 			n->v.skip[j] = cpu_to_le32(bch2_snapshot_skiplist_get(c, parent));
-- 
GitLab


From 12207f49ef41d5599fb313d103f2c7b485848c9d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 20 Jan 2024 23:44:17 -0500
Subject: [PATCH 3114/4076] bcachefs: comment bch_subvolume

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index a76036179238e..6abd19cdbfcfe 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -1123,6 +1123,9 @@ struct bch_subvolume {
 	 * Snapshot subvolumes form a tree, separate from the snapshot nodes
 	 * tree - if this subvolume is a snapshot, this is the ID of the
 	 * subvolume it was created from:
+	 *
+	 * This is _not_ necessarily the subvolume of the directory containing
+	 * this subvolume:
 	 */
 	__le32			parent;
 	__le32			pad;
-- 
GitLab


From 3a58dfbc46c277b090f1b72c949e15da7e1290bf Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 20 Jan 2024 23:46:35 -0500
Subject: [PATCH 3115/4076] bcachefs: counters.c -> sb-counters.c

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/Makefile                      | 2 +-
 fs/bcachefs/{counters.c => sb-counters.c} | 2 +-
 fs/bcachefs/{counters.h => sb-counters.h} | 7 +++----
 fs/bcachefs/super-io.c                    | 2 +-
 fs/bcachefs/super.c                       | 2 +-
 5 files changed, 7 insertions(+), 8 deletions(-)
 rename fs/bcachefs/{counters.c => sb-counters.c} (99%)
 rename fs/bcachefs/{counters.h => sb-counters.h} (77%)

diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile
index 7423a3557c680..1a05cecda7cc5 100644
--- a/fs/bcachefs/Makefile
+++ b/fs/bcachefs/Makefile
@@ -27,7 +27,6 @@ bcachefs-y		:=	\
 	checksum.o		\
 	clock.o			\
 	compress.o		\
-	counters.o		\
 	darray.o		\
 	debug.o			\
 	dirent.o		\
@@ -71,6 +70,7 @@ bcachefs-y		:=	\
 	reflink.o		\
 	replicas.o		\
 	sb-clean.o		\
+	sb-counters.o		\
 	sb-downgrade.o		\
 	sb-errors.o		\
 	sb-members.o		\
diff --git a/fs/bcachefs/counters.c b/fs/bcachefs/sb-counters.c
similarity index 99%
rename from fs/bcachefs/counters.c
rename to fs/bcachefs/sb-counters.c
index 02a996e06a64e..7dc898761bb31 100644
--- a/fs/bcachefs/counters.c
+++ b/fs/bcachefs/sb-counters.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "bcachefs.h"
 #include "super-io.h"
-#include "counters.h"
+#include "sb-counters.h"
 
 /* BCH_SB_FIELD_counters */
 
diff --git a/fs/bcachefs/counters.h b/fs/bcachefs/sb-counters.h
similarity index 77%
rename from fs/bcachefs/counters.h
rename to fs/bcachefs/sb-counters.h
index 4778aa19bf346..81f8aec9fcb1c 100644
--- a/fs/bcachefs/counters.h
+++ b/fs/bcachefs/sb-counters.h
@@ -1,11 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _BCACHEFS_COUNTERS_H
-#define _BCACHEFS_COUNTERS_H
+#ifndef _BCACHEFS_SB_COUNTERS_H
+#define _BCACHEFS_SB_COUNTERS_H
 
 #include "bcachefs.h"
 #include "super-io.h"
 
-
 int bch2_sb_counters_to_cpu(struct bch_fs *);
 int bch2_sb_counters_from_cpu(struct bch_fs *);
 
@@ -14,4 +13,4 @@ int bch2_fs_counters_init(struct bch_fs *);
 
 extern const struct bch_sb_field_ops bch_sb_field_ops_counters;
 
-#endif // _BCACHEFS_COUNTERS_H
+#endif // _BCACHEFS_SB_COUNTERS_H
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index 9564d2d9ccaef..4e4da1a5e5d78 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -2,7 +2,6 @@
 
 #include "bcachefs.h"
 #include "checksum.h"
-#include "counters.h"
 #include "disk_groups.h"
 #include "ec.h"
 #include "error.h"
@@ -13,6 +12,7 @@
 #include "replicas.h"
 #include "quota.h"
 #include "sb-clean.h"
+#include "sb-counters.h"
 #include "sb-downgrade.h"
 #include "sb-errors.h"
 #include "sb-members.h"
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 9262a9298fcd1..670fe1e6733ad 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -23,7 +23,6 @@
 #include "checksum.h"
 #include "clock.h"
 #include "compress.h"
-#include "counters.h"
 #include "debug.h"
 #include "disk_groups.h"
 #include "ec.h"
@@ -49,6 +48,7 @@
 #include "recovery.h"
 #include "replicas.h"
 #include "sb-clean.h"
+#include "sb-counters.h"
 #include "sb-errors.h"
 #include "sb-members.h"
 #include "snapshot.h"
-- 
GitLab


From 43314801a43985aa78cf475ccbdb3c520aa1e3d0 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 20 Jan 2024 23:50:56 -0500
Subject: [PATCH 3116/4076] bcachefs: sb-counters_format.h

bcachefs_format.h has gotten too big; let's do some organizing.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h    | 97 +------------------------------
 fs/bcachefs/sb-counters_format.h | 98 ++++++++++++++++++++++++++++++++
 2 files changed, 100 insertions(+), 95 deletions(-)
 create mode 100644 fs/bcachefs/sb-counters_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 6abd19cdbfcfe..a9d2086ea2be3 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -1234,6 +1234,8 @@ struct bch_sb_field {
 	x(ext,				13)	\
 	x(downgrade,			14)
 
+#include "sb-counters_format.h"
+
 enum bch_sb_field_type {
 #define x(f, nr)	BCH_SB_FIELD_##f = nr,
 	BCH_SB_FIELDS()
@@ -1504,101 +1506,6 @@ struct bch_sb_field_disk_groups {
 	struct bch_disk_group	entries[];
 } __packed __aligned(8);
 
-/* BCH_SB_FIELD_counters */
-
-#define BCH_PERSISTENT_COUNTERS()				\
-	x(io_read,					0)	\
-	x(io_write,					1)	\
-	x(io_move,					2)	\
-	x(bucket_invalidate,				3)	\
-	x(bucket_discard,				4)	\
-	x(bucket_alloc,					5)	\
-	x(bucket_alloc_fail,				6)	\
-	x(btree_cache_scan,				7)	\
-	x(btree_cache_reap,				8)	\
-	x(btree_cache_cannibalize,			9)	\
-	x(btree_cache_cannibalize_lock,			10)	\
-	x(btree_cache_cannibalize_lock_fail,		11)	\
-	x(btree_cache_cannibalize_unlock,		12)	\
-	x(btree_node_write,				13)	\
-	x(btree_node_read,				14)	\
-	x(btree_node_compact,				15)	\
-	x(btree_node_merge,				16)	\
-	x(btree_node_split,				17)	\
-	x(btree_node_rewrite,				18)	\
-	x(btree_node_alloc,				19)	\
-	x(btree_node_free,				20)	\
-	x(btree_node_set_root,				21)	\
-	x(btree_path_relock_fail,			22)	\
-	x(btree_path_upgrade_fail,			23)	\
-	x(btree_reserve_get_fail,			24)	\
-	x(journal_entry_full,				25)	\
-	x(journal_full,					26)	\
-	x(journal_reclaim_finish,			27)	\
-	x(journal_reclaim_start,			28)	\
-	x(journal_write,				29)	\
-	x(read_promote,					30)	\
-	x(read_bounce,					31)	\
-	x(read_split,					33)	\
-	x(read_retry,					32)	\
-	x(read_reuse_race,				34)	\
-	x(move_extent_read,				35)	\
-	x(move_extent_write,				36)	\
-	x(move_extent_finish,				37)	\
-	x(move_extent_fail,				38)	\
-	x(move_extent_start_fail,			39)	\
-	x(copygc,					40)	\
-	x(copygc_wait,					41)	\
-	x(gc_gens_end,					42)	\
-	x(gc_gens_start,				43)	\
-	x(trans_blocked_journal_reclaim,		44)	\
-	x(trans_restart_btree_node_reused,		45)	\
-	x(trans_restart_btree_node_split,		46)	\
-	x(trans_restart_fault_inject,			47)	\
-	x(trans_restart_iter_upgrade,			48)	\
-	x(trans_restart_journal_preres_get,		49)	\
-	x(trans_restart_journal_reclaim,		50)	\
-	x(trans_restart_journal_res_get,		51)	\
-	x(trans_restart_key_cache_key_realloced,	52)	\
-	x(trans_restart_key_cache_raced,		53)	\
-	x(trans_restart_mark_replicas,			54)	\
-	x(trans_restart_mem_realloced,			55)	\
-	x(trans_restart_memory_allocation_failure,	56)	\
-	x(trans_restart_relock,				57)	\
-	x(trans_restart_relock_after_fill,		58)	\
-	x(trans_restart_relock_key_cache_fill,		59)	\
-	x(trans_restart_relock_next_node,		60)	\
-	x(trans_restart_relock_parent_for_fill,		61)	\
-	x(trans_restart_relock_path,			62)	\
-	x(trans_restart_relock_path_intent,		63)	\
-	x(trans_restart_too_many_iters,			64)	\
-	x(trans_restart_traverse,			65)	\
-	x(trans_restart_upgrade,			66)	\
-	x(trans_restart_would_deadlock,			67)	\
-	x(trans_restart_would_deadlock_write,		68)	\
-	x(trans_restart_injected,			69)	\
-	x(trans_restart_key_cache_upgrade,		70)	\
-	x(trans_traverse_all,				71)	\
-	x(transaction_commit,				72)	\
-	x(write_super,					73)	\
-	x(trans_restart_would_deadlock_recursion_limit,	74)	\
-	x(trans_restart_write_buffer_flush,		75)	\
-	x(trans_restart_split_race,			76)	\
-	x(write_buffer_flush_slowpath,			77)	\
-	x(write_buffer_flush_sync,			78)
-
-enum bch_persistent_counters {
-#define x(t, n, ...) BCH_COUNTER_##t,
-	BCH_PERSISTENT_COUNTERS()
-#undef x
-	BCH_COUNTER_NR
-};
-
-struct bch_sb_field_counters {
-	struct bch_sb_field	field;
-	__le64			d[];
-};
-
 /*
  * On clean shutdown, store btree roots and current journal sequence number in
  * the superblock:
diff --git a/fs/bcachefs/sb-counters_format.h b/fs/bcachefs/sb-counters_format.h
new file mode 100644
index 0000000000000..62ea478215d08
--- /dev/null
+++ b/fs/bcachefs/sb-counters_format.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SB_COUNTERS_FORMAT_H
+#define _BCACHEFS_SB_COUNTERS_FORMAT_H
+
+#define BCH_PERSISTENT_COUNTERS()				\
+	x(io_read,					0)	\
+	x(io_write,					1)	\
+	x(io_move,					2)	\
+	x(bucket_invalidate,				3)	\
+	x(bucket_discard,				4)	\
+	x(bucket_alloc,					5)	\
+	x(bucket_alloc_fail,				6)	\
+	x(btree_cache_scan,				7)	\
+	x(btree_cache_reap,				8)	\
+	x(btree_cache_cannibalize,			9)	\
+	x(btree_cache_cannibalize_lock,			10)	\
+	x(btree_cache_cannibalize_lock_fail,		11)	\
+	x(btree_cache_cannibalize_unlock,		12)	\
+	x(btree_node_write,				13)	\
+	x(btree_node_read,				14)	\
+	x(btree_node_compact,				15)	\
+	x(btree_node_merge,				16)	\
+	x(btree_node_split,				17)	\
+	x(btree_node_rewrite,				18)	\
+	x(btree_node_alloc,				19)	\
+	x(btree_node_free,				20)	\
+	x(btree_node_set_root,				21)	\
+	x(btree_path_relock_fail,			22)	\
+	x(btree_path_upgrade_fail,			23)	\
+	x(btree_reserve_get_fail,			24)	\
+	x(journal_entry_full,				25)	\
+	x(journal_full,					26)	\
+	x(journal_reclaim_finish,			27)	\
+	x(journal_reclaim_start,			28)	\
+	x(journal_write,				29)	\
+	x(read_promote,					30)	\
+	x(read_bounce,					31)	\
+	x(read_split,					33)	\
+	x(read_retry,					32)	\
+	x(read_reuse_race,				34)	\
+	x(move_extent_read,				35)	\
+	x(move_extent_write,				36)	\
+	x(move_extent_finish,				37)	\
+	x(move_extent_fail,				38)	\
+	x(move_extent_start_fail,			39)	\
+	x(copygc,					40)	\
+	x(copygc_wait,					41)	\
+	x(gc_gens_end,					42)	\
+	x(gc_gens_start,				43)	\
+	x(trans_blocked_journal_reclaim,		44)	\
+	x(trans_restart_btree_node_reused,		45)	\
+	x(trans_restart_btree_node_split,		46)	\
+	x(trans_restart_fault_inject,			47)	\
+	x(trans_restart_iter_upgrade,			48)	\
+	x(trans_restart_journal_preres_get,		49)	\
+	x(trans_restart_journal_reclaim,		50)	\
+	x(trans_restart_journal_res_get,		51)	\
+	x(trans_restart_key_cache_key_realloced,	52)	\
+	x(trans_restart_key_cache_raced,		53)	\
+	x(trans_restart_mark_replicas,			54)	\
+	x(trans_restart_mem_realloced,			55)	\
+	x(trans_restart_memory_allocation_failure,	56)	\
+	x(trans_restart_relock,				57)	\
+	x(trans_restart_relock_after_fill,		58)	\
+	x(trans_restart_relock_key_cache_fill,		59)	\
+	x(trans_restart_relock_next_node,		60)	\
+	x(trans_restart_relock_parent_for_fill,		61)	\
+	x(trans_restart_relock_path,			62)	\
+	x(trans_restart_relock_path_intent,		63)	\
+	x(trans_restart_too_many_iters,			64)	\
+	x(trans_restart_traverse,			65)	\
+	x(trans_restart_upgrade,			66)	\
+	x(trans_restart_would_deadlock,			67)	\
+	x(trans_restart_would_deadlock_write,		68)	\
+	x(trans_restart_injected,			69)	\
+	x(trans_restart_key_cache_upgrade,		70)	\
+	x(trans_traverse_all,				71)	\
+	x(transaction_commit,				72)	\
+	x(write_super,					73)	\
+	x(trans_restart_would_deadlock_recursion_limit,	74)	\
+	x(trans_restart_write_buffer_flush,		75)	\
+	x(trans_restart_split_race,			76)	\
+	x(write_buffer_flush_slowpath,			77)	\
+	x(write_buffer_flush_sync,			78)
+
+enum bch_persistent_counters {
+#define x(t, n, ...) BCH_COUNTER_##t,
+	BCH_PERSISTENT_COUNTERS()
+#undef x
+	BCH_COUNTER_NR
+};
+
+struct bch_sb_field_counters {
+	struct bch_sb_field	field;
+	__le64			d[];
+};
+
+#endif /* _BCACHEFS_SB_COUNTERS_FORMAT_H */
-- 
GitLab


From 82de6207fb20ea9a467065f4c8ec382affc38405 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 20 Jan 2024 23:53:52 -0500
Subject: [PATCH 3117/4076] bcachefs; quota_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 43 +-------------------------------
 fs/bcachefs/quota_format.h    | 47 +++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+), 42 deletions(-)
 create mode 100644 fs/bcachefs/quota_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index a9d2086ea2be3..2e91403f82355 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -1030,31 +1030,6 @@ struct bch_bucket_gens {
 	u8			gens[KEY_TYPE_BUCKET_GENS_NR];
 } __packed __aligned(8);
 
-/* Quotas: */
-
-enum quota_types {
-	QTYP_USR		= 0,
-	QTYP_GRP		= 1,
-	QTYP_PRJ		= 2,
-	QTYP_NR			= 3,
-};
-
-enum quota_counters {
-	Q_SPC			= 0,
-	Q_INO			= 1,
-	Q_COUNTERS		= 2,
-};
-
-struct bch_quota_counter {
-	__le64			hardlimit;
-	__le64			softlimit;
-};
-
-struct bch_quota {
-	struct bch_val		v;
-	struct bch_quota_counter c[Q_COUNTERS];
-} __packed __aligned(8);
-
 /* Erasure coding */
 
 struct bch_stripe {
@@ -1234,6 +1209,7 @@ struct bch_sb_field {
 	x(ext,				13)	\
 	x(downgrade,			14)
 
+#include "quota_format.h"
 #include "sb-counters_format.h"
 
 enum bch_sb_field_type {
@@ -1471,23 +1447,6 @@ struct bch_sb_field_replicas {
 	struct bch_replicas_entry_v1 entries[];
 } __packed __aligned(8);
 
-/* BCH_SB_FIELD_quota: */
-
-struct bch_sb_quota_counter {
-	__le32				timelimit;
-	__le32				warnlimit;
-};
-
-struct bch_sb_quota_type {
-	__le64				flags;
-	struct bch_sb_quota_counter	c[Q_COUNTERS];
-};
-
-struct bch_sb_field_quota {
-	struct bch_sb_field		field;
-	struct bch_sb_quota_type	q[QTYP_NR];
-} __packed __aligned(8);
-
 /* BCH_SB_FIELD_disk_groups: */
 
 #define BCH_SB_LABEL_SIZE		32
diff --git a/fs/bcachefs/quota_format.h b/fs/bcachefs/quota_format.h
new file mode 100644
index 0000000000000..dc34347ef6c74
--- /dev/null
+++ b/fs/bcachefs/quota_format.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_QUOTA_FORMAT_H
+#define _BCACHEFS_QUOTA_FORMAT_H
+
+/* KEY_TYPE_quota: */
+
+enum quota_types {
+	QTYP_USR		= 0,
+	QTYP_GRP		= 1,
+	QTYP_PRJ		= 2,
+	QTYP_NR			= 3,
+};
+
+enum quota_counters {
+	Q_SPC			= 0,
+	Q_INO			= 1,
+	Q_COUNTERS		= 2,
+};
+
+struct bch_quota_counter {
+	__le64			hardlimit;
+	__le64			softlimit;
+};
+
+struct bch_quota {
+	struct bch_val		v;
+	struct bch_quota_counter c[Q_COUNTERS];
+} __packed __aligned(8);
+
+/* BCH_SB_FIELD_quota: */
+
+struct bch_sb_quota_counter {
+	__le32				timelimit;
+	__le32				warnlimit;
+};
+
+struct bch_sb_quota_type {
+	__le64				flags;
+	struct bch_sb_quota_counter	c[Q_COUNTERS];
+};
+
+struct bch_sb_field_quota {
+	struct bch_sb_field		field;
+	struct bch_sb_quota_type	q[QTYP_NR];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_QUOTA_FORMAT_H */
-- 
GitLab


From b36425da71fe25a51c7f28af0e92b37e535db4a2 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 20 Jan 2024 23:55:39 -0500
Subject: [PATCH 3118/4076] bcachefs: inode_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 165 +--------------------------------
 fs/bcachefs/inode_format.h    | 166 ++++++++++++++++++++++++++++++++++
 2 files changed, 167 insertions(+), 164 deletions(-)
 create mode 100644 fs/bcachefs/inode_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 2e91403f82355..691654f265529 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -710,170 +710,6 @@ struct bch_reservation {
 #define BKEY_BTREE_PTR_U64s_MAX					\
 	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
 
-/* Inodes */
-
-#define BLOCKDEV_INODE_MAX	4096
-
-#define BCACHEFS_ROOT_INO	4096
-
-struct bch_inode {
-	struct bch_val		v;
-
-	__le64			bi_hash_seed;
-	__le32			bi_flags;
-	__le16			bi_mode;
-	__u8			fields[];
-} __packed __aligned(8);
-
-struct bch_inode_v2 {
-	struct bch_val		v;
-
-	__le64			bi_journal_seq;
-	__le64			bi_hash_seed;
-	__le64			bi_flags;
-	__le16			bi_mode;
-	__u8			fields[];
-} __packed __aligned(8);
-
-struct bch_inode_v3 {
-	struct bch_val		v;
-
-	__le64			bi_journal_seq;
-	__le64			bi_hash_seed;
-	__le64			bi_flags;
-	__le64			bi_sectors;
-	__le64			bi_size;
-	__le64			bi_version;
-	__u8			fields[];
-} __packed __aligned(8);
-
-#define INODEv3_FIELDS_START_INITIAL	6
-#define INODEv3_FIELDS_START_CUR	(offsetof(struct bch_inode_v3, fields) / sizeof(__u64))
-
-struct bch_inode_generation {
-	struct bch_val		v;
-
-	__le32			bi_generation;
-	__le32			pad;
-} __packed __aligned(8);
-
-/*
- * bi_subvol and bi_parent_subvol are only set for subvolume roots:
- */
-
-#define BCH_INODE_FIELDS_v2()			\
-	x(bi_atime,			96)	\
-	x(bi_ctime,			96)	\
-	x(bi_mtime,			96)	\
-	x(bi_otime,			96)	\
-	x(bi_size,			64)	\
-	x(bi_sectors,			64)	\
-	x(bi_uid,			32)	\
-	x(bi_gid,			32)	\
-	x(bi_nlink,			32)	\
-	x(bi_generation,		32)	\
-	x(bi_dev,			32)	\
-	x(bi_data_checksum,		8)	\
-	x(bi_compression,		8)	\
-	x(bi_project,			32)	\
-	x(bi_background_compression,	8)	\
-	x(bi_data_replicas,		8)	\
-	x(bi_promote_target,		16)	\
-	x(bi_foreground_target,		16)	\
-	x(bi_background_target,		16)	\
-	x(bi_erasure_code,		16)	\
-	x(bi_fields_set,		16)	\
-	x(bi_dir,			64)	\
-	x(bi_dir_offset,		64)	\
-	x(bi_subvol,			32)	\
-	x(bi_parent_subvol,		32)
-
-#define BCH_INODE_FIELDS_v3()			\
-	x(bi_atime,			96)	\
-	x(bi_ctime,			96)	\
-	x(bi_mtime,			96)	\
-	x(bi_otime,			96)	\
-	x(bi_uid,			32)	\
-	x(bi_gid,			32)	\
-	x(bi_nlink,			32)	\
-	x(bi_generation,		32)	\
-	x(bi_dev,			32)	\
-	x(bi_data_checksum,		8)	\
-	x(bi_compression,		8)	\
-	x(bi_project,			32)	\
-	x(bi_background_compression,	8)	\
-	x(bi_data_replicas,		8)	\
-	x(bi_promote_target,		16)	\
-	x(bi_foreground_target,		16)	\
-	x(bi_background_target,		16)	\
-	x(bi_erasure_code,		16)	\
-	x(bi_fields_set,		16)	\
-	x(bi_dir,			64)	\
-	x(bi_dir_offset,		64)	\
-	x(bi_subvol,			32)	\
-	x(bi_parent_subvol,		32)	\
-	x(bi_nocow,			8)
-
-/* subset of BCH_INODE_FIELDS */
-#define BCH_INODE_OPTS()			\
-	x(data_checksum,		8)	\
-	x(compression,			8)	\
-	x(project,			32)	\
-	x(background_compression,	8)	\
-	x(data_replicas,		8)	\
-	x(promote_target,		16)	\
-	x(foreground_target,		16)	\
-	x(background_target,		16)	\
-	x(erasure_code,			16)	\
-	x(nocow,			8)
-
-enum inode_opt_id {
-#define x(name, ...)				\
-	Inode_opt_##name,
-	BCH_INODE_OPTS()
-#undef  x
-	Inode_opt_nr,
-};
-
-#define BCH_INODE_FLAGS()			\
-	x(sync,				0)	\
-	x(immutable,			1)	\
-	x(append,			2)	\
-	x(nodump,			3)	\
-	x(noatime,			4)	\
-	x(i_size_dirty,			5)	\
-	x(i_sectors_dirty,		6)	\
-	x(unlinked,			7)	\
-	x(backptr_untrusted,		8)
-
-/* bits 20+ reserved for packed fields below: */
-
-enum bch_inode_flags {
-#define x(t, n)	BCH_INODE_##t = 1U << n,
-	BCH_INODE_FLAGS()
-#undef x
-};
-
-enum __bch_inode_flags {
-#define x(t, n)	__BCH_INODE_##t = n,
-	BCH_INODE_FLAGS()
-#undef x
-};
-
-LE32_BITMASK(INODE_STR_HASH,	struct bch_inode, bi_flags, 20, 24);
-LE32_BITMASK(INODE_NR_FIELDS,	struct bch_inode, bi_flags, 24, 31);
-LE32_BITMASK(INODE_NEW_VARINT,	struct bch_inode, bi_flags, 31, 32);
-
-LE64_BITMASK(INODEv2_STR_HASH,	struct bch_inode_v2, bi_flags, 20, 24);
-LE64_BITMASK(INODEv2_NR_FIELDS,	struct bch_inode_v2, bi_flags, 24, 31);
-
-LE64_BITMASK(INODEv3_STR_HASH,	struct bch_inode_v3, bi_flags, 20, 24);
-LE64_BITMASK(INODEv3_NR_FIELDS,	struct bch_inode_v3, bi_flags, 24, 31);
-
-LE64_BITMASK(INODEv3_FIELDS_START,
-				struct bch_inode_v3, bi_flags, 31, 36);
-LE64_BITMASK(INODEv3_MODE,	struct bch_inode_v3, bi_flags, 36, 52);
-
 /* Dirents */
 
 /*
@@ -1209,6 +1045,7 @@ struct bch_sb_field {
 	x(ext,				13)	\
 	x(downgrade,			14)
 
+#include "inode_format.h"
 #include "quota_format.h"
 #include "sb-counters_format.h"
 
diff --git a/fs/bcachefs/inode_format.h b/fs/bcachefs/inode_format.h
new file mode 100644
index 0000000000000..83d107331edf4
--- /dev/null
+++ b/fs/bcachefs/inode_format.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_INODE_FORMAT_H
+#define _BCACHEFS_INODE_FORMAT_H
+
+#define BLOCKDEV_INODE_MAX	4096
+#define BCACHEFS_ROOT_INO	4096
+
+struct bch_inode {
+	struct bch_val		v;
+
+	__le64			bi_hash_seed;
+	__le32			bi_flags;
+	__le16			bi_mode;
+	__u8			fields[];
+} __packed __aligned(8);
+
+struct bch_inode_v2 {
+	struct bch_val		v;
+
+	__le64			bi_journal_seq;
+	__le64			bi_hash_seed;
+	__le64			bi_flags;
+	__le16			bi_mode;
+	__u8			fields[];
+} __packed __aligned(8);
+
+struct bch_inode_v3 {
+	struct bch_val		v;
+
+	__le64			bi_journal_seq;
+	__le64			bi_hash_seed;
+	__le64			bi_flags;
+	__le64			bi_sectors;
+	__le64			bi_size;
+	__le64			bi_version;
+	__u8			fields[];
+} __packed __aligned(8);
+
+#define INODEv3_FIELDS_START_INITIAL	6
+#define INODEv3_FIELDS_START_CUR	(offsetof(struct bch_inode_v3, fields) / sizeof(__u64))
+
+struct bch_inode_generation {
+	struct bch_val		v;
+
+	__le32			bi_generation;
+	__le32			pad;
+} __packed __aligned(8);
+
+/*
+ * bi_subvol and bi_parent_subvol are only set for subvolume roots:
+ */
+
+#define BCH_INODE_FIELDS_v2()			\
+	x(bi_atime,			96)	\
+	x(bi_ctime,			96)	\
+	x(bi_mtime,			96)	\
+	x(bi_otime,			96)	\
+	x(bi_size,			64)	\
+	x(bi_sectors,			64)	\
+	x(bi_uid,			32)	\
+	x(bi_gid,			32)	\
+	x(bi_nlink,			32)	\
+	x(bi_generation,		32)	\
+	x(bi_dev,			32)	\
+	x(bi_data_checksum,		8)	\
+	x(bi_compression,		8)	\
+	x(bi_project,			32)	\
+	x(bi_background_compression,	8)	\
+	x(bi_data_replicas,		8)	\
+	x(bi_promote_target,		16)	\
+	x(bi_foreground_target,		16)	\
+	x(bi_background_target,		16)	\
+	x(bi_erasure_code,		16)	\
+	x(bi_fields_set,		16)	\
+	x(bi_dir,			64)	\
+	x(bi_dir_offset,		64)	\
+	x(bi_subvol,			32)	\
+	x(bi_parent_subvol,		32)
+
+#define BCH_INODE_FIELDS_v3()			\
+	x(bi_atime,			96)	\
+	x(bi_ctime,			96)	\
+	x(bi_mtime,			96)	\
+	x(bi_otime,			96)	\
+	x(bi_uid,			32)	\
+	x(bi_gid,			32)	\
+	x(bi_nlink,			32)	\
+	x(bi_generation,		32)	\
+	x(bi_dev,			32)	\
+	x(bi_data_checksum,		8)	\
+	x(bi_compression,		8)	\
+	x(bi_project,			32)	\
+	x(bi_background_compression,	8)	\
+	x(bi_data_replicas,		8)	\
+	x(bi_promote_target,		16)	\
+	x(bi_foreground_target,		16)	\
+	x(bi_background_target,		16)	\
+	x(bi_erasure_code,		16)	\
+	x(bi_fields_set,		16)	\
+	x(bi_dir,			64)	\
+	x(bi_dir_offset,		64)	\
+	x(bi_subvol,			32)	\
+	x(bi_parent_subvol,		32)	\
+	x(bi_nocow,			8)
+
+/* subset of BCH_INODE_FIELDS */
+#define BCH_INODE_OPTS()			\
+	x(data_checksum,		8)	\
+	x(compression,			8)	\
+	x(project,			32)	\
+	x(background_compression,	8)	\
+	x(data_replicas,		8)	\
+	x(promote_target,		16)	\
+	x(foreground_target,		16)	\
+	x(background_target,		16)	\
+	x(erasure_code,			16)	\
+	x(nocow,			8)
+
+enum inode_opt_id {
+#define x(name, ...)				\
+	Inode_opt_##name,
+	BCH_INODE_OPTS()
+#undef  x
+	Inode_opt_nr,
+};
+
+#define BCH_INODE_FLAGS()			\
+	x(sync,				0)	\
+	x(immutable,			1)	\
+	x(append,			2)	\
+	x(nodump,			3)	\
+	x(noatime,			4)	\
+	x(i_size_dirty,			5)	\
+	x(i_sectors_dirty,		6)	\
+	x(unlinked,			7)	\
+	x(backptr_untrusted,		8)
+
+/* bits 20+ reserved for packed fields below: */
+
+enum bch_inode_flags {
+#define x(t, n)	BCH_INODE_##t = 1U << n,
+	BCH_INODE_FLAGS()
+#undef x
+};
+
+enum __bch_inode_flags {
+#define x(t, n)	__BCH_INODE_##t = n,
+	BCH_INODE_FLAGS()
+#undef x
+};
+
+LE32_BITMASK(INODE_STR_HASH,	struct bch_inode, bi_flags, 20, 24);
+LE32_BITMASK(INODE_NR_FIELDS,	struct bch_inode, bi_flags, 24, 31);
+LE32_BITMASK(INODE_NEW_VARINT,	struct bch_inode, bi_flags, 31, 32);
+
+LE64_BITMASK(INODEv2_STR_HASH,	struct bch_inode_v2, bi_flags, 20, 24);
+LE64_BITMASK(INODEv2_NR_FIELDS,	struct bch_inode_v2, bi_flags, 24, 31);
+
+LE64_BITMASK(INODEv3_STR_HASH,	struct bch_inode_v3, bi_flags, 20, 24);
+LE64_BITMASK(INODEv3_NR_FIELDS,	struct bch_inode_v3, bi_flags, 24, 31);
+
+LE64_BITMASK(INODEv3_FIELDS_START,
+				struct bch_inode_v3, bi_flags, 31, 36);
+LE64_BITMASK(INODEv3_MODE,	struct bch_inode_v3, bi_flags, 36, 52);
+
+#endif /* _BCACHEFS_INODE_FORMAT_H */
-- 
GitLab


From 7ffc4daa5f08b13f88c0ce743dadb18040926cbf Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 20 Jan 2024 23:57:10 -0500
Subject: [PATCH 3119/4076] bcachefs: dirent_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 40 +--------------------------------
 fs/bcachefs/dirent_format.h   | 42 +++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 39 deletions(-)
 create mode 100644 fs/bcachefs/dirent_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 691654f265529..2af3795b49177 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -710,45 +710,6 @@ struct bch_reservation {
 #define BKEY_BTREE_PTR_U64s_MAX					\
 	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
 
-/* Dirents */
-
-/*
- * Dirents (and xattrs) have to implement string lookups; since our b-tree
- * doesn't support arbitrary length strings for the key, we instead index by a
- * 64 bit hash (currently truncated sha1) of the string, stored in the offset
- * field of the key - using linear probing to resolve hash collisions. This also
- * provides us with the readdir cookie posix requires.
- *
- * Linear probing requires us to use whiteouts for deletions, in the event of a
- * collision:
- */
-
-struct bch_dirent {
-	struct bch_val		v;
-
-	/* Target inode number: */
-	union {
-	__le64			d_inum;
-	struct {		/* DT_SUBVOL */
-	__le32			d_child_subvol;
-	__le32			d_parent_subvol;
-	};
-	};
-
-	/*
-	 * Copy of mode bits 12-15 from the target inode - so userspace can get
-	 * the filetype without having to do a stat()
-	 */
-	__u8			d_type;
-
-	__u8			d_name[];
-} __packed __aligned(8);
-
-#define DT_SUBVOL	16
-#define BCH_DT_MAX	17
-
-#define BCH_NAME_MAX	512
-
 /* Xattrs */
 
 #define KEY_TYPE_XATTR_INDEX_USER			0
@@ -1045,6 +1006,7 @@ struct bch_sb_field {
 	x(ext,				13)	\
 	x(downgrade,			14)
 
+#include "dirent_format.h"
 #include "inode_format.h"
 #include "quota_format.h"
 #include "sb-counters_format.h"
diff --git a/fs/bcachefs/dirent_format.h b/fs/bcachefs/dirent_format.h
new file mode 100644
index 0000000000000..5e116b88e8146
--- /dev/null
+++ b/fs/bcachefs/dirent_format.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_DIRENT_FORMAT_H
+#define _BCACHEFS_DIRENT_FORMAT_H
+
+/*
+ * Dirents (and xattrs) have to implement string lookups; since our b-tree
+ * doesn't support arbitrary length strings for the key, we instead index by a
+ * 64 bit hash (currently truncated sha1) of the string, stored in the offset
+ * field of the key - using linear probing to resolve hash collisions. This also
+ * provides us with the readdir cookie posix requires.
+ *
+ * Linear probing requires us to use whiteouts for deletions, in the event of a
+ * collision:
+ */
+
+struct bch_dirent {
+	struct bch_val		v;
+
+	/* Target inode number: */
+	union {
+	__le64			d_inum;
+	struct {		/* DT_SUBVOL */
+	__le32			d_child_subvol;
+	__le32			d_parent_subvol;
+	};
+	};
+
+	/*
+	 * Copy of mode bits 12-15 from the target inode - so userspace can get
+	 * the filetype without having to do a stat()
+	 */
+	__u8			d_type;
+
+	__u8			d_name[];
+} __packed __aligned(8);
+
+#define DT_SUBVOL	16
+#define BCH_DT_MAX	17
+
+#define BCH_NAME_MAX	512
+
+#endif /* _BCACHEFS_DIRENT_FORMAT_H */
-- 
GitLab


From 72e0801049c9b10fe3cadacf57eb040dbe65ba52 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 20 Jan 2024 23:59:15 -0500
Subject: [PATCH 3120/4076] bcachefs: xattr_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 16 +---------------
 fs/bcachefs/xattr_format.h    | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+), 15 deletions(-)
 create mode 100644 fs/bcachefs/xattr_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 2af3795b49177..1dbc26a5945ea 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -710,21 +710,6 @@ struct bch_reservation {
 #define BKEY_BTREE_PTR_U64s_MAX					\
 	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
 
-/* Xattrs */
-
-#define KEY_TYPE_XATTR_INDEX_USER			0
-#define KEY_TYPE_XATTR_INDEX_POSIX_ACL_ACCESS	1
-#define KEY_TYPE_XATTR_INDEX_POSIX_ACL_DEFAULT	2
-#define KEY_TYPE_XATTR_INDEX_TRUSTED			3
-#define KEY_TYPE_XATTR_INDEX_SECURITY	        4
-
-struct bch_xattr {
-	struct bch_val		v;
-	__u8			x_type;
-	__u8			x_name_len;
-	__le16			x_val_len;
-	__u8			x_name[];
-} __packed __aligned(8);
 
 /* Bucket/allocation information: */
 
@@ -1008,6 +993,7 @@ struct bch_sb_field {
 
 #include "dirent_format.h"
 #include "inode_format.h"
+#include "xattr_format.h"
 #include "quota_format.h"
 #include "sb-counters_format.h"
 
diff --git a/fs/bcachefs/xattr_format.h b/fs/bcachefs/xattr_format.h
new file mode 100644
index 0000000000000..e9f810539552e
--- /dev/null
+++ b/fs/bcachefs/xattr_format.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_XATTR_FORMAT_H
+#define _BCACHEFS_XATTR_FORMAT_H
+
+#define KEY_TYPE_XATTR_INDEX_USER		0
+#define KEY_TYPE_XATTR_INDEX_POSIX_ACL_ACCESS	1
+#define KEY_TYPE_XATTR_INDEX_POSIX_ACL_DEFAULT	2
+#define KEY_TYPE_XATTR_INDEX_TRUSTED		3
+#define KEY_TYPE_XATTR_INDEX_SECURITY	        4
+
+struct bch_xattr {
+	struct bch_val		v;
+	__u8			x_type;
+	__u8			x_name_len;
+	__le16			x_val_len;
+	__u8			x_name[];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_XATTR_FORMAT_H */
-- 
GitLab


From d455179fce10f0a7a76b84d1c8327988a93e3216 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 21 Jan 2024 00:01:52 -0500
Subject: [PATCH 3121/4076] bcachefs: alloc_background_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/alloc_background_format.h | 92 ++++++++++++++++++++++++++
 fs/bcachefs/bcachefs_format.h         | 95 +--------------------------
 2 files changed, 94 insertions(+), 93 deletions(-)
 create mode 100644 fs/bcachefs/alloc_background_format.h

diff --git a/fs/bcachefs/alloc_background_format.h b/fs/bcachefs/alloc_background_format.h
new file mode 100644
index 0000000000000..b4ec20be93b86
--- /dev/null
+++ b/fs/bcachefs/alloc_background_format.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_ALLOC_BACKGROUND_FORMAT_H
+#define _BCACHEFS_ALLOC_BACKGROUND_FORMAT_H
+
+struct bch_alloc {
+	struct bch_val		v;
+	__u8			fields;
+	__u8			gen;
+	__u8			data[];
+} __packed __aligned(8);
+
+#define BCH_ALLOC_FIELDS_V1()			\
+	x(read_time,		16)		\
+	x(write_time,		16)		\
+	x(data_type,		8)		\
+	x(dirty_sectors,	16)		\
+	x(cached_sectors,	16)		\
+	x(oldest_gen,		8)		\
+	x(stripe,		32)		\
+	x(stripe_redundancy,	8)
+
+enum {
+#define x(name, _bits) BCH_ALLOC_FIELD_V1_##name,
+	BCH_ALLOC_FIELDS_V1()
+#undef x
+};
+
+struct bch_alloc_v2 {
+	struct bch_val		v;
+	__u8			nr_fields;
+	__u8			gen;
+	__u8			oldest_gen;
+	__u8			data_type;
+	__u8			data[];
+} __packed __aligned(8);
+
+#define BCH_ALLOC_FIELDS_V2()			\
+	x(read_time,		64)		\
+	x(write_time,		64)		\
+	x(dirty_sectors,	32)		\
+	x(cached_sectors,	32)		\
+	x(stripe,		32)		\
+	x(stripe_redundancy,	8)
+
+struct bch_alloc_v3 {
+	struct bch_val		v;
+	__le64			journal_seq;
+	__le32			flags;
+	__u8			nr_fields;
+	__u8			gen;
+	__u8			oldest_gen;
+	__u8			data_type;
+	__u8			data[];
+} __packed __aligned(8);
+
+LE32_BITMASK(BCH_ALLOC_V3_NEED_DISCARD,struct bch_alloc_v3, flags,  0,  1)
+LE32_BITMASK(BCH_ALLOC_V3_NEED_INC_GEN,struct bch_alloc_v3, flags,  1,  2)
+
+struct bch_alloc_v4 {
+	struct bch_val		v;
+	__u64			journal_seq;
+	__u32			flags;
+	__u8			gen;
+	__u8			oldest_gen;
+	__u8			data_type;
+	__u8			stripe_redundancy;
+	__u32			dirty_sectors;
+	__u32			cached_sectors;
+	__u64			io_time[2];
+	__u32			stripe;
+	__u32			nr_external_backpointers;
+	__u64			fragmentation_lru;
+} __packed __aligned(8);
+
+#define BCH_ALLOC_V4_U64s_V0	6
+#define BCH_ALLOC_V4_U64s	(sizeof(struct bch_alloc_v4) / sizeof(__u64))
+
+BITMASK(BCH_ALLOC_V4_NEED_DISCARD,	struct bch_alloc_v4, flags,  0,  1)
+BITMASK(BCH_ALLOC_V4_NEED_INC_GEN,	struct bch_alloc_v4, flags,  1,  2)
+BITMASK(BCH_ALLOC_V4_BACKPOINTERS_START,struct bch_alloc_v4, flags,  2,  8)
+BITMASK(BCH_ALLOC_V4_NR_BACKPOINTERS,	struct bch_alloc_v4, flags,  8,  14)
+
+#define KEY_TYPE_BUCKET_GENS_BITS	8
+#define KEY_TYPE_BUCKET_GENS_NR		(1U << KEY_TYPE_BUCKET_GENS_BITS)
+#define KEY_TYPE_BUCKET_GENS_MASK	(KEY_TYPE_BUCKET_GENS_NR - 1)
+
+struct bch_bucket_gens {
+	struct bch_val		v;
+	u8			gens[KEY_TYPE_BUCKET_GENS_NR];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_ALLOC_BACKGROUND_FORMAT_H */
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 1dbc26a5945ea..e26b8000c26bf 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -710,89 +710,6 @@ struct bch_reservation {
 #define BKEY_BTREE_PTR_U64s_MAX					\
 	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
 
-
-/* Bucket/allocation information: */
-
-struct bch_alloc {
-	struct bch_val		v;
-	__u8			fields;
-	__u8			gen;
-	__u8			data[];
-} __packed __aligned(8);
-
-#define BCH_ALLOC_FIELDS_V1()			\
-	x(read_time,		16)		\
-	x(write_time,		16)		\
-	x(data_type,		8)		\
-	x(dirty_sectors,	16)		\
-	x(cached_sectors,	16)		\
-	x(oldest_gen,		8)		\
-	x(stripe,		32)		\
-	x(stripe_redundancy,	8)
-
-enum {
-#define x(name, _bits) BCH_ALLOC_FIELD_V1_##name,
-	BCH_ALLOC_FIELDS_V1()
-#undef x
-};
-
-struct bch_alloc_v2 {
-	struct bch_val		v;
-	__u8			nr_fields;
-	__u8			gen;
-	__u8			oldest_gen;
-	__u8			data_type;
-	__u8			data[];
-} __packed __aligned(8);
-
-#define BCH_ALLOC_FIELDS_V2()			\
-	x(read_time,		64)		\
-	x(write_time,		64)		\
-	x(dirty_sectors,	32)		\
-	x(cached_sectors,	32)		\
-	x(stripe,		32)		\
-	x(stripe_redundancy,	8)
-
-struct bch_alloc_v3 {
-	struct bch_val		v;
-	__le64			journal_seq;
-	__le32			flags;
-	__u8			nr_fields;
-	__u8			gen;
-	__u8			oldest_gen;
-	__u8			data_type;
-	__u8			data[];
-} __packed __aligned(8);
-
-LE32_BITMASK(BCH_ALLOC_V3_NEED_DISCARD,struct bch_alloc_v3, flags,  0,  1)
-LE32_BITMASK(BCH_ALLOC_V3_NEED_INC_GEN,struct bch_alloc_v3, flags,  1,  2)
-
-struct bch_alloc_v4 {
-	struct bch_val		v;
-	__u64			journal_seq;
-	__u32			flags;
-	__u8			gen;
-	__u8			oldest_gen;
-	__u8			data_type;
-	__u8			stripe_redundancy;
-	__u32			dirty_sectors;
-	__u32			cached_sectors;
-	__u64			io_time[2];
-	__u32			stripe;
-	__u32			nr_external_backpointers;
-	__u64			fragmentation_lru;
-} __packed __aligned(8);
-
-#define BCH_ALLOC_V4_U64s_V0	6
-#define BCH_ALLOC_V4_U64s	(sizeof(struct bch_alloc_v4) / sizeof(__u64))
-
-BITMASK(BCH_ALLOC_V4_NEED_DISCARD,	struct bch_alloc_v4, flags,  0,  1)
-BITMASK(BCH_ALLOC_V4_NEED_INC_GEN,	struct bch_alloc_v4, flags,  1,  2)
-BITMASK(BCH_ALLOC_V4_BACKPOINTERS_START,struct bch_alloc_v4, flags,  2,  8)
-BITMASK(BCH_ALLOC_V4_NR_BACKPOINTERS,	struct bch_alloc_v4, flags,  8,  14)
-
-#define BCH_ALLOC_V4_NR_BACKPOINTERS_MAX	40
-
 struct bch_backpointer {
 	struct bch_val		v;
 	__u8			btree_id;
@@ -803,15 +720,6 @@ struct bch_backpointer {
 	struct bpos		pos;
 } __packed __aligned(8);
 
-#define KEY_TYPE_BUCKET_GENS_BITS	8
-#define KEY_TYPE_BUCKET_GENS_NR		(1U << KEY_TYPE_BUCKET_GENS_BITS)
-#define KEY_TYPE_BUCKET_GENS_MASK	(KEY_TYPE_BUCKET_GENS_NR - 1)
-
-struct bch_bucket_gens {
-	struct bch_val		v;
-	u8			gens[KEY_TYPE_BUCKET_GENS_NR];
-} __packed __aligned(8);
-
 /* Erasure coding */
 
 struct bch_stripe {
@@ -991,8 +899,9 @@ struct bch_sb_field {
 	x(ext,				13)	\
 	x(downgrade,			14)
 
-#include "dirent_format.h"
+#include "alloc_background_format.h"
 #include "inode_format.h"
+#include "dirent_format.h"
 #include "xattr_format.h"
 #include "quota_format.h"
 #include "sb-counters_format.h"
-- 
GitLab


From 8fed323b14040f42e5755bbb9bd778415634c4b6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 21 Jan 2024 02:41:06 -0500
Subject: [PATCH 3122/4076] bcachefs: snapshot_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 34 +--------------------------------
 fs/bcachefs/snapshot_format.h | 36 +++++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+), 33 deletions(-)
 create mode 100644 fs/bcachefs/snapshot_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index e26b8000c26bf..cfce8ca1f8359 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -805,39 +805,6 @@ LE32_BITMASK(BCH_SUBVOLUME_RO,		struct bch_subvolume, flags,  0,  1)
 LE32_BITMASK(BCH_SUBVOLUME_SNAP,	struct bch_subvolume, flags,  1,  2)
 LE32_BITMASK(BCH_SUBVOLUME_UNLINKED,	struct bch_subvolume, flags,  2,  3)
 
-/* Snapshots */
-
-struct bch_snapshot {
-	struct bch_val		v;
-	__le32			flags;
-	__le32			parent;
-	__le32			children[2];
-	__le32			subvol;
-	/* corresponds to a bch_snapshot_tree in BTREE_ID_snapshot_trees */
-	__le32			tree;
-	__le32			depth;
-	__le32			skip[3];
-	bch_le128		btime;
-};
-
-LE32_BITMASK(BCH_SNAPSHOT_DELETED,	struct bch_snapshot, flags,  0,  1)
-
-/* True if a subvolume points to this snapshot node: */
-LE32_BITMASK(BCH_SNAPSHOT_SUBVOL,	struct bch_snapshot, flags,  1,  2)
-
-/*
- * Snapshot trees:
- *
- * The snapshot_trees btree gives us persistent indentifier for each tree of
- * bch_snapshot nodes, and allow us to record and easily find the root/master
- * subvolume that other snapshots were created from:
- */
-struct bch_snapshot_tree {
-	struct bch_val		v;
-	__le32			master_subvol;
-	__le32			root_snapshot;
-};
-
 /* LRU btree: */
 
 struct bch_lru {
@@ -904,6 +871,7 @@ struct bch_sb_field {
 #include "dirent_format.h"
 #include "xattr_format.h"
 #include "quota_format.h"
+#include "snapshot_format.h"
 #include "sb-counters_format.h"
 
 enum bch_sb_field_type {
diff --git a/fs/bcachefs/snapshot_format.h b/fs/bcachefs/snapshot_format.h
new file mode 100644
index 0000000000000..aabcd3a74cd95
--- /dev/null
+++ b/fs/bcachefs/snapshot_format.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SNAPSHOT_FORMAT_H
+#define _BCACHEFS_SNAPSHOT_FORMAT_H
+
+struct bch_snapshot {
+	struct bch_val		v;
+	__le32			flags;
+	__le32			parent;
+	__le32			children[2];
+	__le32			subvol;
+	/* corresponds to a bch_snapshot_tree in BTREE_ID_snapshot_trees */
+	__le32			tree;
+	__le32			depth;
+	__le32			skip[3];
+	bch_le128		btime;
+};
+
+LE32_BITMASK(BCH_SNAPSHOT_DELETED,	struct bch_snapshot, flags,  0,  1)
+
+/* True if a subvolume points to this snapshot node: */
+LE32_BITMASK(BCH_SNAPSHOT_SUBVOL,	struct bch_snapshot, flags,  1,  2)
+
+/*
+ * Snapshot trees:
+ *
+ * The snapshot_trees btree gives us persistent indentifier for each tree of
+ * bch_snapshot nodes, and allow us to record and easily find the root/master
+ * subvolume that other snapshots were created from:
+ */
+struct bch_snapshot_tree {
+	struct bch_val		v;
+	__le32			master_subvol;
+	__le32			root_snapshot;
+};
+
+#endif /* _BCACHEFS_SNAPSHOT_FORMAT_H */
-- 
GitLab


From c6c4ff6507c4e1d32f9c2019795d4b7aa6eb559f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 21 Jan 2024 02:42:53 -0500
Subject: [PATCH 3123/4076] bcachefs: subvolume_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h  | 33 +-------------------------------
 fs/bcachefs/subvolume_format.h | 35 ++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 32 deletions(-)
 create mode 100644 fs/bcachefs/subvolume_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index cfce8ca1f8359..6e4fc27ffb3bd 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -773,38 +773,6 @@ struct bch_inline_data {
 	u8			data[];
 };
 
-/* Subvolumes: */
-
-#define SUBVOL_POS_MIN		POS(0, 1)
-#define SUBVOL_POS_MAX		POS(0, S32_MAX)
-#define BCACHEFS_ROOT_SUBVOL	1
-
-struct bch_subvolume {
-	struct bch_val		v;
-	__le32			flags;
-	__le32			snapshot;
-	__le64			inode;
-	/*
-	 * Snapshot subvolumes form a tree, separate from the snapshot nodes
-	 * tree - if this subvolume is a snapshot, this is the ID of the
-	 * subvolume it was created from:
-	 *
-	 * This is _not_ necessarily the subvolume of the directory containing
-	 * this subvolume:
-	 */
-	__le32			parent;
-	__le32			pad;
-	bch_le128		otime;
-};
-
-LE32_BITMASK(BCH_SUBVOLUME_RO,		struct bch_subvolume, flags,  0,  1)
-/*
- * We need to know whether a subvolume is a snapshot so we can know whether we
- * can delete it (or whether it should just be rm -rf'd)
- */
-LE32_BITMASK(BCH_SUBVOLUME_SNAP,	struct bch_subvolume, flags,  1,  2)
-LE32_BITMASK(BCH_SUBVOLUME_UNLINKED,	struct bch_subvolume, flags,  2,  3)
-
 /* LRU btree: */
 
 struct bch_lru {
@@ -872,6 +840,7 @@ struct bch_sb_field {
 #include "xattr_format.h"
 #include "quota_format.h"
 #include "snapshot_format.h"
+#include "subvolume_format.h"
 #include "sb-counters_format.h"
 
 enum bch_sb_field_type {
diff --git a/fs/bcachefs/subvolume_format.h b/fs/bcachefs/subvolume_format.h
new file mode 100644
index 0000000000000..af79134b07d6a
--- /dev/null
+++ b/fs/bcachefs/subvolume_format.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_SUBVOLUME_FORMAT_H
+#define _BCACHEFS_SUBVOLUME_FORMAT_H
+
+#define SUBVOL_POS_MIN		POS(0, 1)
+#define SUBVOL_POS_MAX		POS(0, S32_MAX)
+#define BCACHEFS_ROOT_SUBVOL	1
+
+struct bch_subvolume {
+	struct bch_val		v;
+	__le32			flags;
+	__le32			snapshot;
+	__le64			inode;
+	/*
+	 * Snapshot subvolumes form a tree, separate from the snapshot nodes
+	 * tree - if this subvolume is a snapshot, this is the ID of the
+	 * subvolume it was created from:
+	 *
+	 * This is _not_ necessarily the subvolume of the directory containing
+	 * this subvolume:
+	 */
+	__le32			parent;
+	__le32			pad;
+	bch_le128		otime;
+};
+
+LE32_BITMASK(BCH_SUBVOLUME_RO,		struct bch_subvolume, flags,  0,  1)
+/*
+ * We need to know whether a subvolume is a snapshot so we can know whether we
+ * can delete it (or whether it should just be rm -rf'd)
+ */
+LE32_BITMASK(BCH_SUBVOLUME_SNAP,	struct bch_subvolume, flags,  1,  2)
+LE32_BITMASK(BCH_SUBVOLUME_UNLINKED,	struct bch_subvolume, flags,  2,  3)
+
+#endif /* _BCACHEFS_SUBVOLUME_FORMAT_H */
-- 
GitLab


From 0560eb9abf7dee3c3517cb38246522ecaf1efc12 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 21 Jan 2024 02:47:14 -0500
Subject: [PATCH 3124/4076] bcachefs: ec_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 17 +----------------
 fs/bcachefs/ec_format.h       | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+), 16 deletions(-)
 create mode 100644 fs/bcachefs/ec_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 6e4fc27ffb3bd..5327514d96f9f 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -720,22 +720,6 @@ struct bch_backpointer {
 	struct bpos		pos;
 } __packed __aligned(8);
 
-/* Erasure coding */
-
-struct bch_stripe {
-	struct bch_val		v;
-	__le16			sectors;
-	__u8			algorithm;
-	__u8			nr_blocks;
-	__u8			nr_redundant;
-
-	__u8			csum_granularity_bits;
-	__u8			csum_type;
-	__u8			pad;
-
-	struct bch_extent_ptr	ptrs[];
-} __packed __aligned(8);
-
 /* Reflink: */
 
 struct bch_reflink_p {
@@ -835,6 +819,7 @@ struct bch_sb_field {
 	x(downgrade,			14)
 
 #include "alloc_background_format.h"
+#include "ec_format.h"
 #include "inode_format.h"
 #include "dirent_format.h"
 #include "xattr_format.h"
diff --git a/fs/bcachefs/ec_format.h b/fs/bcachefs/ec_format.h
new file mode 100644
index 0000000000000..44ce88ba08d71
--- /dev/null
+++ b/fs/bcachefs/ec_format.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_EC_FORMAT_H
+#define _BCACHEFS_EC_FORMAT_H
+
+struct bch_stripe {
+	struct bch_val		v;
+	__le16			sectors;
+	__u8			algorithm;
+	__u8			nr_blocks;
+	__u8			nr_redundant;
+
+	__u8			csum_granularity_bits;
+	__u8			csum_type;
+	__u8			pad;
+
+	struct bch_extent_ptr	ptrs[];
+} __packed __aligned(8);
+
+#endif /* _BCACHEFS_EC_FORMAT_H */
-- 
GitLab


From b2fa1b633bac0c3b2d04ae00e8801414d251aace Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 21 Jan 2024 02:51:56 -0500
Subject: [PATCH 3125/4076] bcachefs; extents_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 281 +--------------------------------
 fs/bcachefs/extents_format.h  | 282 ++++++++++++++++++++++++++++++++++
 2 files changed, 284 insertions(+), 279 deletions(-)
 create mode 100644 fs/bcachefs/extents_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 5327514d96f9f..2921ecd49c6ee 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -417,272 +417,12 @@ struct bch_set {
 	struct bch_val		v;
 };
 
-/* Extents */
-
-/*
- * In extent bkeys, the value is a list of pointers (bch_extent_ptr), optionally
- * preceded by checksum/compression information (bch_extent_crc32 or
- * bch_extent_crc64).
- *
- * One major determining factor in the format of extents is how we handle and
- * represent extents that have been partially overwritten and thus trimmed:
- *
- * If an extent is not checksummed or compressed, when the extent is trimmed we
- * don't have to remember the extent we originally allocated and wrote: we can
- * merely adjust ptr->offset to point to the start of the data that is currently
- * live. The size field in struct bkey records the current (live) size of the
- * extent, and is also used to mean "size of region on disk that we point to" in
- * this case.
- *
- * Thus an extent that is not checksummed or compressed will consist only of a
- * list of bch_extent_ptrs, with none of the fields in
- * bch_extent_crc32/bch_extent_crc64.
- *
- * When an extent is checksummed or compressed, it's not possible to read only
- * the data that is currently live: we have to read the entire extent that was
- * originally written, and then return only the part of the extent that is
- * currently live.
- *
- * Thus, in addition to the current size of the extent in struct bkey, we need
- * to store the size of the originally allocated space - this is the
- * compressed_size and uncompressed_size fields in bch_extent_crc32/64. Also,
- * when the extent is trimmed, instead of modifying the offset field of the
- * pointer, we keep a second smaller offset field - "offset into the original
- * extent of the currently live region".
- *
- * The other major determining factor is replication and data migration:
- *
- * Each pointer may have its own bch_extent_crc32/64. When doing a replicated
- * write, we will initially write all the replicas in the same format, with the
- * same checksum type and compression format - however, when copygc runs later (or
- * tiering/cache promotion, anything that moves data), it is not in general
- * going to rewrite all the pointers at once - one of the replicas may be in a
- * bucket on one device that has very little fragmentation while another lives
- * in a bucket that has become heavily fragmented, and thus is being rewritten
- * sooner than the rest.
- *
- * Thus it will only move a subset of the pointers (or in the case of
- * tiering/cache promotion perhaps add a single pointer without dropping any
- * current pointers), and if the extent has been partially overwritten it must
- * write only the currently live portion (or copygc would not be able to reduce
- * fragmentation!) - which necessitates a different bch_extent_crc format for
- * the new pointer.
- *
- * But in the interests of space efficiency, we don't want to store one
- * bch_extent_crc for each pointer if we don't have to.
- *
- * Thus, a bch_extent consists of bch_extent_crc32s, bch_extent_crc64s, and
- * bch_extent_ptrs appended arbitrarily one after the other. We determine the
- * type of a given entry with a scheme similar to utf8 (except we're encoding a
- * type, not a size), encoding the type in the position of the first set bit:
- *
- * bch_extent_crc32	- 0b1
- * bch_extent_ptr	- 0b10
- * bch_extent_crc64	- 0b100
- *
- * We do it this way because bch_extent_crc32 is _very_ constrained on bits (and
- * bch_extent_crc64 is the least constrained).
- *
- * Then, each bch_extent_crc32/64 applies to the pointers that follow after it,
- * until the next bch_extent_crc32/64.
- *
- * If there are no bch_extent_crcs preceding a bch_extent_ptr, then that pointer
- * is neither checksummed nor compressed.
- */
-
 /* 128 bits, sufficient for cryptographic MACs: */
 struct bch_csum {
 	__le64			lo;
 	__le64			hi;
 } __packed __aligned(8);
 
-#define BCH_EXTENT_ENTRY_TYPES()		\
-	x(ptr,			0)		\
-	x(crc32,		1)		\
-	x(crc64,		2)		\
-	x(crc128,		3)		\
-	x(stripe_ptr,		4)		\
-	x(rebalance,		5)
-#define BCH_EXTENT_ENTRY_MAX	6
-
-enum bch_extent_entry_type {
-#define x(f, n) BCH_EXTENT_ENTRY_##f = n,
-	BCH_EXTENT_ENTRY_TYPES()
-#undef x
-};
-
-/* Compressed/uncompressed size are stored biased by 1: */
-struct bch_extent_crc32 {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u32			type:2,
-				_compressed_size:7,
-				_uncompressed_size:7,
-				offset:7,
-				_unused:1,
-				csum_type:4,
-				compression_type:4;
-	__u32			csum;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u32			csum;
-	__u32			compression_type:4,
-				csum_type:4,
-				_unused:1,
-				offset:7,
-				_uncompressed_size:7,
-				_compressed_size:7,
-				type:2;
-#endif
-} __packed __aligned(8);
-
-#define CRC32_SIZE_MAX		(1U << 7)
-#define CRC32_NONCE_MAX		0
-
-struct bch_extent_crc64 {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:3,
-				_compressed_size:9,
-				_uncompressed_size:9,
-				offset:9,
-				nonce:10,
-				csum_type:4,
-				compression_type:4,
-				csum_hi:16;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			csum_hi:16,
-				compression_type:4,
-				csum_type:4,
-				nonce:10,
-				offset:9,
-				_uncompressed_size:9,
-				_compressed_size:9,
-				type:3;
-#endif
-	__u64			csum_lo;
-} __packed __aligned(8);
-
-#define CRC64_SIZE_MAX		(1U << 9)
-#define CRC64_NONCE_MAX		((1U << 10) - 1)
-
-struct bch_extent_crc128 {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:4,
-				_compressed_size:13,
-				_uncompressed_size:13,
-				offset:13,
-				nonce:13,
-				csum_type:4,
-				compression_type:4;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			compression_type:4,
-				csum_type:4,
-				nonce:13,
-				offset:13,
-				_uncompressed_size:13,
-				_compressed_size:13,
-				type:4;
-#endif
-	struct bch_csum		csum;
-} __packed __aligned(8);
-
-#define CRC128_SIZE_MAX		(1U << 13)
-#define CRC128_NONCE_MAX	((1U << 13) - 1)
-
-/*
- * @reservation - pointer hasn't been written to, just reserved
- */
-struct bch_extent_ptr {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:1,
-				cached:1,
-				unused:1,
-				unwritten:1,
-				offset:44, /* 8 petabytes */
-				dev:8,
-				gen:8;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			gen:8,
-				dev:8,
-				offset:44,
-				unwritten:1,
-				unused:1,
-				cached:1,
-				type:1;
-#endif
-} __packed __aligned(8);
-
-struct bch_extent_stripe_ptr {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:5,
-				block:8,
-				redundancy:4,
-				idx:47;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			idx:47,
-				redundancy:4,
-				block:8,
-				type:5;
-#endif
-};
-
-struct bch_extent_rebalance {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u64			type:6,
-				unused:34,
-				compression:8, /* enum bch_compression_opt */
-				target:16;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-	__u64			target:16,
-				compression:8,
-				unused:34,
-				type:6;
-#endif
-};
-
-union bch_extent_entry {
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ ||  __BITS_PER_LONG == 64
-	unsigned long			type;
-#elif __BITS_PER_LONG == 32
-	struct {
-		unsigned long		pad;
-		unsigned long		type;
-	};
-#else
-#error edit for your odd byteorder.
-#endif
-
-#define x(f, n) struct bch_extent_##f	f;
-	BCH_EXTENT_ENTRY_TYPES()
-#undef x
-};
-
-struct bch_btree_ptr {
-	struct bch_val		v;
-
-	__u64			_data[0];
-	struct bch_extent_ptr	start[];
-} __packed __aligned(8);
-
-struct bch_btree_ptr_v2 {
-	struct bch_val		v;
-
-	__u64			mem_ptr;
-	__le64			seq;
-	__le16			sectors_written;
-	__le16			flags;
-	struct bpos		min_key;
-	__u64			_data[0];
-	struct bch_extent_ptr	start[];
-} __packed __aligned(8);
-
-LE16_BITMASK(BTREE_PTR_RANGE_UPDATED,	struct bch_btree_ptr_v2, flags, 0, 1);
-
-struct bch_extent {
-	struct bch_val		v;
-
-	__u64			_data[0];
-	union bch_extent_entry	start[];
-} __packed __aligned(8);
-
 struct bch_reservation {
 	struct bch_val		v;
 
@@ -691,25 +431,6 @@ struct bch_reservation {
 	__u8			pad[3];
 } __packed __aligned(8);
 
-/* Maximum size (in u64s) a single pointer could be: */
-#define BKEY_EXTENT_PTR_U64s_MAX\
-	((sizeof(struct bch_extent_crc128) +			\
-	  sizeof(struct bch_extent_ptr)) / sizeof(__u64))
-
-/* Maximum possible size of an entire extent value: */
-#define BKEY_EXTENT_VAL_U64s_MAX				\
-	(1 + BKEY_EXTENT_PTR_U64s_MAX * (BCH_REPLICAS_MAX + 1))
-
-/* * Maximum possible size of an entire extent, key + value: */
-#define BKEY_EXTENT_U64s_MAX		(BKEY_U64s + BKEY_EXTENT_VAL_U64s_MAX)
-
-/* Btree pointers don't carry around checksums: */
-#define BKEY_BTREE_PTR_VAL_U64s_MAX				\
-	((sizeof(struct bch_btree_ptr_v2) +			\
-	  sizeof(struct bch_extent_ptr) * BCH_REPLICAS_MAX) / sizeof(__u64))
-#define BKEY_BTREE_PTR_U64s_MAX					\
-	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
-
 struct bch_backpointer {
 	struct bch_val		v;
 	__u8			btree_id;
@@ -720,6 +441,8 @@ struct bch_backpointer {
 	struct bpos		pos;
 } __packed __aligned(8);
 
+#include "extents_format.h"
+
 /* Reflink: */
 
 struct bch_reflink_p {
diff --git a/fs/bcachefs/extents_format.h b/fs/bcachefs/extents_format.h
new file mode 100644
index 0000000000000..939d09f9d3b84
--- /dev/null
+++ b/fs/bcachefs/extents_format.h
@@ -0,0 +1,282 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_EXTENTS_FORMAT_H
+#define _BCACHEFS_EXTENTS_FORMAT_H
+
+/*
+ * In extent bkeys, the value is a list of pointers (bch_extent_ptr), optionally
+ * preceded by checksum/compression information (bch_extent_crc32 or
+ * bch_extent_crc64).
+ *
+ * One major determining factor in the format of extents is how we handle and
+ * represent extents that have been partially overwritten and thus trimmed:
+ *
+ * If an extent is not checksummed or compressed, when the extent is trimmed we
+ * don't have to remember the extent we originally allocated and wrote: we can
+ * merely adjust ptr->offset to point to the start of the data that is currently
+ * live. The size field in struct bkey records the current (live) size of the
+ * extent, and is also used to mean "size of region on disk that we point to" in
+ * this case.
+ *
+ * Thus an extent that is not checksummed or compressed will consist only of a
+ * list of bch_extent_ptrs, with none of the fields in
+ * bch_extent_crc32/bch_extent_crc64.
+ *
+ * When an extent is checksummed or compressed, it's not possible to read only
+ * the data that is currently live: we have to read the entire extent that was
+ * originally written, and then return only the part of the extent that is
+ * currently live.
+ *
+ * Thus, in addition to the current size of the extent in struct bkey, we need
+ * to store the size of the originally allocated space - this is the
+ * compressed_size and uncompressed_size fields in bch_extent_crc32/64. Also,
+ * when the extent is trimmed, instead of modifying the offset field of the
+ * pointer, we keep a second smaller offset field - "offset into the original
+ * extent of the currently live region".
+ *
+ * The other major determining factor is replication and data migration:
+ *
+ * Each pointer may have its own bch_extent_crc32/64. When doing a replicated
+ * write, we will initially write all the replicas in the same format, with the
+ * same checksum type and compression format - however, when copygc runs later (or
+ * tiering/cache promotion, anything that moves data), it is not in general
+ * going to rewrite all the pointers at once - one of the replicas may be in a
+ * bucket on one device that has very little fragmentation while another lives
+ * in a bucket that has become heavily fragmented, and thus is being rewritten
+ * sooner than the rest.
+ *
+ * Thus it will only move a subset of the pointers (or in the case of
+ * tiering/cache promotion perhaps add a single pointer without dropping any
+ * current pointers), and if the extent has been partially overwritten it must
+ * write only the currently live portion (or copygc would not be able to reduce
+ * fragmentation!) - which necessitates a different bch_extent_crc format for
+ * the new pointer.
+ *
+ * But in the interests of space efficiency, we don't want to store one
+ * bch_extent_crc for each pointer if we don't have to.
+ *
+ * Thus, a bch_extent consists of bch_extent_crc32s, bch_extent_crc64s, and
+ * bch_extent_ptrs appended arbitrarily one after the other. We determine the
+ * type of a given entry with a scheme similar to utf8 (except we're encoding a
+ * type, not a size), encoding the type in the position of the first set bit:
+ *
+ * bch_extent_crc32	- 0b1
+ * bch_extent_ptr	- 0b10
+ * bch_extent_crc64	- 0b100
+ *
+ * We do it this way because bch_extent_crc32 is _very_ constrained on bits (and
+ * bch_extent_crc64 is the least constrained).
+ *
+ * Then, each bch_extent_crc32/64 applies to the pointers that follow after it,
+ * until the next bch_extent_crc32/64.
+ *
+ * If there are no bch_extent_crcs preceding a bch_extent_ptr, then that pointer
+ * is neither checksummed nor compressed.
+ */
+
+#define BCH_EXTENT_ENTRY_TYPES()		\
+	x(ptr,			0)		\
+	x(crc32,		1)		\
+	x(crc64,		2)		\
+	x(crc128,		3)		\
+	x(stripe_ptr,		4)		\
+	x(rebalance,		5)
+#define BCH_EXTENT_ENTRY_MAX	6
+
+enum bch_extent_entry_type {
+#define x(f, n) BCH_EXTENT_ENTRY_##f = n,
+	BCH_EXTENT_ENTRY_TYPES()
+#undef x
+};
+
+/* Compressed/uncompressed size are stored biased by 1: */
+struct bch_extent_crc32 {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u32			type:2,
+				_compressed_size:7,
+				_uncompressed_size:7,
+				offset:7,
+				_unused:1,
+				csum_type:4,
+				compression_type:4;
+	__u32			csum;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u32			csum;
+	__u32			compression_type:4,
+				csum_type:4,
+				_unused:1,
+				offset:7,
+				_uncompressed_size:7,
+				_compressed_size:7,
+				type:2;
+#endif
+} __packed __aligned(8);
+
+#define CRC32_SIZE_MAX		(1U << 7)
+#define CRC32_NONCE_MAX		0
+
+struct bch_extent_crc64 {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:3,
+				_compressed_size:9,
+				_uncompressed_size:9,
+				offset:9,
+				nonce:10,
+				csum_type:4,
+				compression_type:4,
+				csum_hi:16;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			csum_hi:16,
+				compression_type:4,
+				csum_type:4,
+				nonce:10,
+				offset:9,
+				_uncompressed_size:9,
+				_compressed_size:9,
+				type:3;
+#endif
+	__u64			csum_lo;
+} __packed __aligned(8);
+
+#define CRC64_SIZE_MAX		(1U << 9)
+#define CRC64_NONCE_MAX		((1U << 10) - 1)
+
+struct bch_extent_crc128 {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:4,
+				_compressed_size:13,
+				_uncompressed_size:13,
+				offset:13,
+				nonce:13,
+				csum_type:4,
+				compression_type:4;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			compression_type:4,
+				csum_type:4,
+				nonce:13,
+				offset:13,
+				_uncompressed_size:13,
+				_compressed_size:13,
+				type:4;
+#endif
+	struct bch_csum		csum;
+} __packed __aligned(8);
+
+#define CRC128_SIZE_MAX		(1U << 13)
+#define CRC128_NONCE_MAX	((1U << 13) - 1)
+
+/*
+ * @reservation - pointer hasn't been written to, just reserved
+ */
+struct bch_extent_ptr {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:1,
+				cached:1,
+				unused:1,
+				unwritten:1,
+				offset:44, /* 8 petabytes */
+				dev:8,
+				gen:8;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			gen:8,
+				dev:8,
+				offset:44,
+				unwritten:1,
+				unused:1,
+				cached:1,
+				type:1;
+#endif
+} __packed __aligned(8);
+
+struct bch_extent_stripe_ptr {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:5,
+				block:8,
+				redundancy:4,
+				idx:47;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			idx:47,
+				redundancy:4,
+				block:8,
+				type:5;
+#endif
+};
+
+struct bch_extent_rebalance {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u64			type:6,
+				unused:34,
+				compression:8, /* enum bch_compression_opt */
+				target:16;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+	__u64			target:16,
+				compression:8,
+				unused:34,
+				type:6;
+#endif
+};
+
+union bch_extent_entry {
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ ||  __BITS_PER_LONG == 64
+	unsigned long			type;
+#elif __BITS_PER_LONG == 32
+	struct {
+		unsigned long		pad;
+		unsigned long		type;
+	};
+#else
+#error edit for your odd byteorder.
+#endif
+
+#define x(f, n) struct bch_extent_##f	f;
+	BCH_EXTENT_ENTRY_TYPES()
+#undef x
+};
+
+struct bch_btree_ptr {
+	struct bch_val		v;
+
+	__u64			_data[0];
+	struct bch_extent_ptr	start[];
+} __packed __aligned(8);
+
+struct bch_btree_ptr_v2 {
+	struct bch_val		v;
+
+	__u64			mem_ptr;
+	__le64			seq;
+	__le16			sectors_written;
+	__le16			flags;
+	struct bpos		min_key;
+	__u64			_data[0];
+	struct bch_extent_ptr	start[];
+} __packed __aligned(8);
+
+LE16_BITMASK(BTREE_PTR_RANGE_UPDATED,	struct bch_btree_ptr_v2, flags, 0, 1);
+
+struct bch_extent {
+	struct bch_val		v;
+
+	__u64			_data[0];
+	union bch_extent_entry	start[];
+} __packed __aligned(8);
+
+/* Maximum size (in u64s) a single pointer could be: */
+#define BKEY_EXTENT_PTR_U64s_MAX\
+	((sizeof(struct bch_extent_crc128) +			\
+	  sizeof(struct bch_extent_ptr)) / sizeof(__u64))
+
+/* Maximum possible size of an entire extent value: */
+#define BKEY_EXTENT_VAL_U64s_MAX				\
+	(1 + BKEY_EXTENT_PTR_U64s_MAX * (BCH_REPLICAS_MAX + 1))
+
+/* * Maximum possible size of an entire extent, key + value: */
+#define BKEY_EXTENT_U64s_MAX		(BKEY_U64s + BKEY_EXTENT_VAL_U64s_MAX)
+
+/* Btree pointers don't carry around checksums: */
+#define BKEY_BTREE_PTR_VAL_U64s_MAX				\
+	((sizeof(struct bch_btree_ptr_v2) +			\
+	  sizeof(struct bch_extent_ptr) * BCH_REPLICAS_MAX) / sizeof(__u64))
+#define BKEY_BTREE_PTR_U64s_MAX					\
+	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
+
+#endif /* _BCACHEFS_EXTENTS_FORMAT_H */
-- 
GitLab


From 8d52ba60c4dccbf5d45db70f41b82b18c38059bd Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 21 Jan 2024 02:54:47 -0500
Subject: [PATCH 3126/4076] bcachefs: reflink_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h | 49 ++---------------------------------
 fs/bcachefs/extents_format.h  | 13 ++++++++++
 fs/bcachefs/reflink_format.h  | 33 +++++++++++++++++++++++
 3 files changed, 48 insertions(+), 47 deletions(-)
 create mode 100644 fs/bcachefs/reflink_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 2921ecd49c6ee..12b0ddedebd7a 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -423,14 +423,6 @@ struct bch_csum {
 	__le64			hi;
 } __packed __aligned(8);
 
-struct bch_reservation {
-	struct bch_val		v;
-
-	__le32			generation;
-	__u8			nr_replicas;
-	__u8			pad[3];
-} __packed __aligned(8);
-
 struct bch_backpointer {
 	struct bch_val		v;
 	__u8			btree_id;
@@ -441,45 +433,6 @@ struct bch_backpointer {
 	struct bpos		pos;
 } __packed __aligned(8);
 
-#include "extents_format.h"
-
-/* Reflink: */
-
-struct bch_reflink_p {
-	struct bch_val		v;
-	__le64			idx;
-	/*
-	 * A reflink pointer might point to an indirect extent which is then
-	 * later split (by copygc or rebalance). If we only pointed to part of
-	 * the original indirect extent, and then one of the fragments is
-	 * outside the range we point to, we'd leak a refcount: so when creating
-	 * reflink pointers, we need to store pad values to remember the full
-	 * range we were taking a reference on.
-	 */
-	__le32			front_pad;
-	__le32			back_pad;
-} __packed __aligned(8);
-
-struct bch_reflink_v {
-	struct bch_val		v;
-	__le64			refcount;
-	union bch_extent_entry	start[0];
-	__u64			_data[];
-} __packed __aligned(8);
-
-struct bch_indirect_inline_data {
-	struct bch_val		v;
-	__le64			refcount;
-	u8			data[];
-};
-
-/* Inline data */
-
-struct bch_inline_data {
-	struct bch_val		v;
-	u8			data[];
-};
-
 /* LRU btree: */
 
 struct bch_lru {
@@ -542,6 +495,8 @@ struct bch_sb_field {
 	x(downgrade,			14)
 
 #include "alloc_background_format.h"
+#include "extents_format.h"
+#include "reflink_format.h"
 #include "ec_format.h"
 #include "inode_format.h"
 #include "dirent_format.h"
diff --git a/fs/bcachefs/extents_format.h b/fs/bcachefs/extents_format.h
index 939d09f9d3b84..3bd2fdbb08174 100644
--- a/fs/bcachefs/extents_format.h
+++ b/fs/bcachefs/extents_format.h
@@ -279,4 +279,17 @@ struct bch_extent {
 #define BKEY_BTREE_PTR_U64s_MAX					\
 	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)
 
+struct bch_reservation {
+	struct bch_val		v;
+
+	__le32			generation;
+	__u8			nr_replicas;
+	__u8			pad[3];
+} __packed __aligned(8);
+
+struct bch_inline_data {
+	struct bch_val		v;
+	u8			data[];
+};
+
 #endif /* _BCACHEFS_EXTENTS_FORMAT_H */
diff --git a/fs/bcachefs/reflink_format.h b/fs/bcachefs/reflink_format.h
new file mode 100644
index 0000000000000..6772eebb1fc66
--- /dev/null
+++ b/fs/bcachefs/reflink_format.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_REFLINK_FORMAT_H
+#define _BCACHEFS_REFLINK_FORMAT_H
+
+struct bch_reflink_p {
+	struct bch_val		v;
+	__le64			idx;
+	/*
+	 * A reflink pointer might point to an indirect extent which is then
+	 * later split (by copygc or rebalance). If we only pointed to part of
+	 * the original indirect extent, and then one of the fragments is
+	 * outside the range we point to, we'd leak a refcount: so when creating
+	 * reflink pointers, we need to store pad values to remember the full
+	 * range we were taking a reference on.
+	 */
+	__le32			front_pad;
+	__le32			back_pad;
+} __packed __aligned(8);
+
+struct bch_reflink_v {
+	struct bch_val		v;
+	__le64			refcount;
+	union bch_extent_entry	start[0];
+	__u64			_data[];
+} __packed __aligned(8);
+
+struct bch_indirect_inline_data {
+	struct bch_val		v;
+	__le64			refcount;
+	u8			data[];
+};
+
+#endif /* _BCACHEFS_REFLINK_FORMAT_H */
-- 
GitLab


From d826cc57c53fa759cac019efc9e59e475cf41070 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 21 Jan 2024 02:57:45 -0500
Subject: [PATCH 3127/4076] bcachefs: logged_ops_format.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs_format.h   | 28 +---------------------------
 fs/bcachefs/logged_ops_format.h | 30 ++++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 27 deletions(-)
 create mode 100644 fs/bcachefs/logged_ops_format.h

diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 12b0ddedebd7a..0668b682a21ca 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -442,33 +442,6 @@ struct bch_lru {
 
 #define LRU_ID_STRIPES		(1U << 16)
 
-/* Logged operations btree: */
-
-struct bch_logged_op_truncate {
-	struct bch_val		v;
-	__le32			subvol;
-	__le32			pad;
-	__le64			inum;
-	__le64			new_i_size;
-};
-
-enum logged_op_finsert_state {
-	LOGGED_OP_FINSERT_start,
-	LOGGED_OP_FINSERT_shift_extents,
-	LOGGED_OP_FINSERT_finish,
-};
-
-struct bch_logged_op_finsert {
-	struct bch_val		v;
-	__u8			state;
-	__u8			pad[3];
-	__le32			subvol;
-	__le64			inum;
-	__le64			dst_offset;
-	__le64			src_offset;
-	__le64			pos;
-};
-
 /* Optional/variable size superblock sections: */
 
 struct bch_sb_field {
@@ -502,6 +475,7 @@ struct bch_sb_field {
 #include "dirent_format.h"
 #include "xattr_format.h"
 #include "quota_format.h"
+#include "logged_ops_format.h"
 #include "snapshot_format.h"
 #include "subvolume_format.h"
 #include "sb-counters_format.h"
diff --git a/fs/bcachefs/logged_ops_format.h b/fs/bcachefs/logged_ops_format.h
new file mode 100644
index 0000000000000..6a4bf7129dba2
--- /dev/null
+++ b/fs/bcachefs/logged_ops_format.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_LOGGED_OPS_FORMAT_H
+#define _BCACHEFS_LOGGED_OPS_FORMAT_H
+
+struct bch_logged_op_truncate {
+	struct bch_val		v;
+	__le32			subvol;
+	__le32			pad;
+	__le64			inum;
+	__le64			new_i_size;
+};
+
+enum logged_op_finsert_state {
+	LOGGED_OP_FINSERT_start,
+	LOGGED_OP_FINSERT_shift_extents,
+	LOGGED_OP_FINSERT_finish,
+};
+
+struct bch_logged_op_finsert {
+	struct bch_val		v;
+	__u8			state;
+	__u8			pad[3];
+	__le32			subvol;
+	__le64			inum;
+	__le64			dst_offset;
+	__le64			src_offset;
+	__le64			pos;
+};
+
+#endif /* _BCACHEFS_LOGGED_OPS_FORMAT_H */
-- 
GitLab


From 249f441f83c546281f1c175756c81fac332bb64c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 21 Jan 2024 12:19:01 -0500
Subject: [PATCH 3128/4076] bcachefs: Improve inode_to_text()

Add line breaks - inode_to_text() is now much easier to read.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/inode.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 18a8d141b4437..086f0090b03a4 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -506,22 +506,33 @@ fsck_err:
 static void __bch2_inode_unpacked_to_text(struct printbuf *out,
 					  struct bch_inode_unpacked *inode)
 {
-	prt_printf(out, "mode=%o ", inode->bi_mode);
+	printbuf_indent_add(out, 2);
+	prt_printf(out, "mode=%o", inode->bi_mode);
+	prt_newline(out);
 
 	prt_str(out, "flags=");
 	prt_bitflags(out, bch2_inode_flag_strs, inode->bi_flags & ((1U << 20) - 1));
 	prt_printf(out, " (%x)", inode->bi_flags);
+	prt_newline(out);
 
-	prt_printf(out, " journal_seq=%llu bi_size=%llu bi_sectors=%llu bi_version=%llu",
-	       inode->bi_journal_seq,
-	       inode->bi_size,
-	       inode->bi_sectors,
-	       inode->bi_version);
+	prt_printf(out, "journal_seq=%llu", inode->bi_journal_seq);
+	prt_newline(out);
+
+	prt_printf(out, "bi_size=%llu", inode->bi_size);
+	prt_newline(out);
+
+	prt_printf(out, "bi_sectors=%llu", inode->bi_sectors);
+	prt_newline(out);
+
+	prt_newline(out);
+	prt_printf(out, "bi_version=%llu", inode->bi_version);
 
 #define x(_name, _bits)						\
-	prt_printf(out, " "#_name "=%llu", (u64) inode->_name);
+	prt_printf(out, #_name "=%llu", (u64) inode->_name);	\
+	prt_newline(out);
 	BCH_INODE_FIELDS_v3()
 #undef  x
+	printbuf_indent_sub(out, 2);
 }
 
 void bch2_inode_unpacked_to_text(struct printbuf *out, struct bch_inode_unpacked *inode)
-- 
GitLab


From 6613476e225e090cc9aad49be7fa504e290dd33d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 21 Jan 2024 14:11:32 -0800
Subject: [PATCH 3129/4076] Linux 6.8-rc1

---
 Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index e5321e45e4e52..9869f57c3fb3e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
-PATCHLEVEL = 7
+PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
-- 
GitLab


From 72b0cbf6b81003c01d63c60180b335f7692d170e Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Fri, 19 Jan 2024 17:57:07 +0800
Subject: [PATCH 3130/4076] smb: Fix some kernel-doc comments

Fix some kernel-doc comments to silence the warnings:
fs/smb/server/transport_tcp.c:374: warning: Function parameter or struct member 'max_retries' not described in 'ksmbd_tcp_read'
fs/smb/server/transport_tcp.c:423: warning: Function parameter or struct member 'iface' not described in 'create_socket'

Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/transport_tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index 9d4222154dcc0..002a3f0dc7c58 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -365,6 +365,7 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig,
  * @t:		TCP transport instance
  * @buf:	buffer to store read data from socket
  * @to_read:	number of bytes to read from socket
+ * @max_retries: number of retries if reading from socket fails
  *
  * Return:	on success return number of bytes read from socket,
  *		otherwise return error number
@@ -416,6 +417,7 @@ static void tcp_destroy_socket(struct socket *ksmbd_socket)
 
 /**
  * create_socket - create socket for ksmbd/0
+ * @iface:      interface to bind the created socket to
  *
  * Return:	0 on success, error number otherwise
  */
-- 
GitLab


From cd30e8bde28ac361e15d67ee5c00e0125ed42548 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 15 Jan 2024 21:37:47 +0100
Subject: [PATCH 3131/4076] rbd: remove usage of the deprecated ida_simple_*()
 API

ida_alloc() and ida_free() should be preferred to the deprecated
ida_simple_get() and ida_simple_remove().

Note that the upper limit of ida_simple_get() is exclusive, while that
of ida_alloc_max() is inclusive, so 1 has been subtracted.

[ idryomov: tweak changelog ]

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 drivers/block/rbd.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index a999b698b131f..63897d0d66292 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -5326,7 +5326,7 @@ static void rbd_dev_release(struct device *dev)
 
 	if (need_put) {
 		destroy_workqueue(rbd_dev->task_wq);
-		ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+		ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
 	}
 
 	rbd_dev_free(rbd_dev);
@@ -5402,9 +5402,9 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 		return NULL;
 
 	/* get an id and fill in device name */
-	rbd_dev->dev_id = ida_simple_get(&rbd_dev_id_ida, 0,
-					 minor_to_rbd_dev_id(1 << MINORBITS),
-					 GFP_KERNEL);
+	rbd_dev->dev_id = ida_alloc_max(&rbd_dev_id_ida,
+					minor_to_rbd_dev_id(1 << MINORBITS) - 1,
+					GFP_KERNEL);
 	if (rbd_dev->dev_id < 0)
 		goto fail_rbd_dev;
 
@@ -5425,7 +5425,7 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 	return rbd_dev;
 
 fail_dev_id:
-	ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+	ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
 fail_rbd_dev:
 	rbd_dev_free(rbd_dev);
 	return NULL;
-- 
GitLab


From ded080c86b3f99683774af0441a58fc2e3d60cae Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Wed, 17 Jan 2024 18:59:44 +0100
Subject: [PATCH 3132/4076] rbd: don't move requests to the running list on
 errors

The running list is supposed to contain requests that are pinning the
exclusive lock, i.e. those that must be flushed before exclusive lock
is released.  When wake_lock_waiters() is called to handle an error,
requests on the acquiring list are failed with that error and no
flushing takes place.  Briefly moving them to the running list is not
only pointless but also harmful: if exclusive lock gets acquired
before all of their state machines are scheduled and go through
rbd_lock_del_request(), we trigger

    rbd_assert(list_empty(&rbd_dev->running_list));

in rbd_try_acquire_lock().

Cc: stable@vger.kernel.org
Fixes: 637cd060537d ("rbd: new exclusive lock wait/wake code")
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
---
 drivers/block/rbd.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 63897d0d66292..12b5d53ec8564 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3452,14 +3452,15 @@ static bool rbd_lock_add_request(struct rbd_img_request *img_req)
 static void rbd_lock_del_request(struct rbd_img_request *img_req)
 {
 	struct rbd_device *rbd_dev = img_req->rbd_dev;
-	bool need_wakeup;
+	bool need_wakeup = false;
 
 	lockdep_assert_held(&rbd_dev->lock_rwsem);
 	spin_lock(&rbd_dev->lock_lists_lock);
-	rbd_assert(!list_empty(&img_req->lock_item));
-	list_del_init(&img_req->lock_item);
-	need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
-		       list_empty(&rbd_dev->running_list));
+	if (!list_empty(&img_req->lock_item)) {
+		list_del_init(&img_req->lock_item);
+		need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+			       list_empty(&rbd_dev->running_list));
+	}
 	spin_unlock(&rbd_dev->lock_lists_lock);
 	if (need_wakeup)
 		complete(&rbd_dev->releasing_wait);
@@ -3842,14 +3843,19 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result)
 		return;
 	}
 
-	list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) {
+	while (!list_empty(&rbd_dev->acquiring_list)) {
+		img_req = list_first_entry(&rbd_dev->acquiring_list,
+					   struct rbd_img_request, lock_item);
 		mutex_lock(&img_req->state_mutex);
 		rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK);
+		if (!result)
+			list_move_tail(&img_req->lock_item,
+				       &rbd_dev->running_list);
+		else
+			list_del_init(&img_req->lock_item);
 		rbd_img_schedule(img_req, result);
 		mutex_unlock(&img_req->state_mutex);
 	}
-
-	list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list);
 }
 
 static bool locker_equal(const struct ceph_locker *lhs,
-- 
GitLab


From 113a61863ecbfb3c29f3eb18fd9813bccf1743c1 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 31 Oct 2023 17:50:11 -0600
Subject: [PATCH 3133/4076] Makefile: Enable -Wstringop-overflow globally

It seems that we have finished addressing all the remaining
issues regarding -Wstringop-overflow. So, we are now in good
shape to enable this compiler option globally.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 Makefile                   | 2 ++
 scripts/Makefile.extrawarn | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 9869f57c3fb3e..c01cbbb208cab 100644
--- a/Makefile
+++ b/Makefile
@@ -986,6 +986,8 @@ NOSTDINC_FLAGS += -nostdinc
 # perform bounds checking.
 KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
 
+KBUILD_CFLAGS += $(call cc-option, -Wstringop-overflow)
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow
 
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 9b7a37ae28a88..a9e552a1e9105 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -97,7 +97,6 @@ KBUILD_CFLAGS += $(call cc-option, -Wunused-const-variable)
 KBUILD_CFLAGS += $(call cc-option, -Wpacked-not-aligned)
 KBUILD_CFLAGS += $(call cc-option, -Wformat-overflow)
 KBUILD_CFLAGS += $(call cc-option, -Wformat-truncation)
-KBUILD_CFLAGS += $(call cc-option, -Wstringop-overflow)
 KBUILD_CFLAGS += $(call cc-option, -Wstringop-truncation)
 
 KBUILD_CPPFLAGS += -Wundef
@@ -113,7 +112,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, restrict)
 KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
-KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)
 KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
 
 ifdef CONFIG_CC_IS_CLANG
-- 
GitLab


From a5e0ace04fbf56c1794b1a2fa7a93672753b3fc7 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 30 Nov 2023 14:29:34 -0600
Subject: [PATCH 3134/4076] init: Kconfig: Disable -Wstringop-overflow for
 GCC-11

-Wstringop-overflow is buggy in GCC-11. Therefore, we should disable
this option specifically for that compiler version. To achieve this,
we introduce a new configuration option: GCC11_NO_STRINGOP_OVERFLOW.

The compiler option related to string operation overflow is now managed
under configuration CC_STRINGOP_OVERFLOW. This option is enabled by
default for all other versions of GCC that support it.

Link: https://lore.kernel.org/lkml/b3c99290-40bc-426f-b3d2-1aa903f95c4e@embeddedor.com/
Link: https://lore.kernel.org/lkml/20231128091351.2bfb38dd@canb.auug.org.au/
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/linux-hardening/ZWj1+jkweEDWbmAR@work/
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 Makefile     |  4 +++-
 init/Kconfig | 12 ++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index c01cbbb208cab..9f9b76d3a4b7d 100644
--- a/Makefile
+++ b/Makefile
@@ -986,7 +986,9 @@ NOSTDINC_FLAGS += -nostdinc
 # perform bounds checking.
 KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
 
-KBUILD_CFLAGS += $(call cc-option, -Wstringop-overflow)
+#Currently, disable -Wstringop-overflow for GCC 11, globally.
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
 
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow
diff --git a/init/Kconfig b/init/Kconfig
index 8df18f3a97484..8d4e836e1b6b1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -876,6 +876,18 @@ config CC_NO_ARRAY_BOUNDS
 	bool
 	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC11_NO_ARRAY_BOUNDS
 
+# Currently, disable -Wstringop-overflow for GCC 11, globally.
+config GCC11_NO_STRINGOP_OVERFLOW
+	def_bool y
+
+config CC_NO_STRINGOP_OVERFLOW
+	bool
+	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_STRINGOP_OVERFLOW
+
+config CC_STRINGOP_OVERFLOW
+	bool
+	default y if CC_IS_GCC && !CC_NO_STRINGOP_OVERFLOW
+
 #
 # For architectures that know their GCC __int128 support is sound
 #
-- 
GitLab


From 0086ffec768bec6f5d61fc7e406af640eb912a24 Mon Sep 17 00:00:00 2001
From: Stanley Chan <schan@cloudflare.com>
Date: Mon, 27 Nov 2023 15:20:48 -0600
Subject: [PATCH 3135/4076] tools cpupower bench: Override CFLAGS assignments

Allow user to specify outside CFLAGS values as make argument

Corrects an issue where CFLAGS is passed as a make argument for
cpupower, but bench's makefile does not inherit and append to them.

Signed-off-by: Stanley Chan <schan@cloudflare.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/bench/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile
index d9d9923af85c2..a4b902f9e1c48 100644
--- a/tools/power/cpupower/bench/Makefile
+++ b/tools/power/cpupower/bench/Makefile
@@ -15,7 +15,7 @@ LIBS = -L../ -L$(OUTPUT) -lm -lcpupower
 OBJS = $(OUTPUT)main.o $(OUTPUT)parse.o $(OUTPUT)system.o $(OUTPUT)benchmark.o
 endif
 
-CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\"
+override CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\"
 
 $(OUTPUT)%.o : %.c
 	$(ECHO) "  CC      " $@
-- 
GitLab


From d09486a04f5da0a812c26217213b89a3b1acf836 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 18 Jan 2024 16:58:59 -0800
Subject: [PATCH 3136/4076] net: fix removing a namespace with conflicting
 altnames
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Mark reports a BUG() when a net namespace is removed.

    kernel BUG at net/core/dev.c:11520!

Physical interfaces moved outside of init_net get "refunded"
to init_net when that namespace disappears. The main interface
name may get overwritten in the process if it would have
conflicted. We need to also discard all conflicting altnames.
Recent fixes addressed ensuring that altnames get moved
with the main interface, which surfaced this problem.

Reported-by: Марк Коренберг <socketpair@gmail.com>
Link: https://lore.kernel.org/all/CAEmTpZFZ4Sv3KwqFOY2WKDHeZYdi0O7N5H1nTvcGp=SAEavtDg@mail.gmail.com/
Fixes: 7663d522099e ("net: check for altname conflicts when changing netdev's netns")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 9 +++++++++
 net/core/dev.h | 3 +++
 2 files changed, 12 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index f01a9b858347b..cb2dab0feee0a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11551,6 +11551,7 @@ static struct pernet_operations __net_initdata netdev_net_ops = {
 
 static void __net_exit default_device_exit_net(struct net *net)
 {
+	struct netdev_name_node *name_node, *tmp;
 	struct net_device *dev, *aux;
 	/*
 	 * Push all migratable network devices back to the
@@ -11573,6 +11574,14 @@ static void __net_exit default_device_exit_net(struct net *net)
 		snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
 		if (netdev_name_in_use(&init_net, fb_name))
 			snprintf(fb_name, IFNAMSIZ, "dev%%d");
+
+		netdev_for_each_altname_safe(dev, name_node, tmp)
+			if (netdev_name_in_use(&init_net, name_node->name)) {
+				netdev_name_node_del(name_node);
+				synchronize_rcu();
+				__netdev_name_node_alt_destroy(name_node);
+			}
+
 		err = dev_change_net_namespace(dev, &init_net, fb_name);
 		if (err) {
 			pr_emerg("%s: failed to move %s to init_net: %d\n",
diff --git a/net/core/dev.h b/net/core/dev.h
index cf93e188785ba..7480b4c842980 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -63,6 +63,9 @@ int dev_change_name(struct net_device *dev, const char *newname);
 
 #define netdev_for_each_altname(dev, namenode)				\
 	list_for_each_entry((namenode), &(dev)->name_node->list, list)
+#define netdev_for_each_altname_safe(dev, namenode, next)		\
+	list_for_each_entry_safe((namenode), (next), &(dev)->name_node->list, \
+				 list)
 
 int netdev_name_node_alt_create(struct net_device *dev, const char *name);
 int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
-- 
GitLab


From 477552e1d339d9fa654a363c9c0f1e9c4f087d2b Mon Sep 17 00:00:00 2001
From: Inki Dae <inki.dae@samsung.com>
Date: Fri, 15 Dec 2023 09:38:19 +0900
Subject: [PATCH 3137/4076] drm/exynos: fix incorrect type issue

Fix incorrect type issue in fimd_commit() of exynos_drm_fimd.c module.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312140930.Me9yWf8F-lkp@intel.com/
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_fimd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 8dde7b1e9b35d..a090ff8370758 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -480,7 +480,7 @@ static void fimd_commit(struct exynos_drm_crtc *crtc)
 	struct fimd_context *ctx = crtc->ctx;
 	struct drm_display_mode *mode = &crtc->base.state->adjusted_mode;
 	const struct fimd_driver_data *driver_data = ctx->driver_data;
-	void *timing_base = ctx->regs + driver_data->timing_base;
+	void __iomem *timing_base = ctx->regs + driver_data->timing_base;
 	u32 val;
 
 	if (ctx->suspended)
-- 
GitLab


From 960b537e91725bcb17dd1b19e48950e62d134078 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 14 Dec 2023 13:32:15 +0100
Subject: [PATCH 3138/4076] drm/exynos: fix accidental on-stack copy of
 exynos_drm_plane

gcc rightfully complains about excessive stack usage in the fimd_win_set_pixfmt()
function:

drivers/gpu/drm/exynos/exynos_drm_fimd.c: In function 'fimd_win_set_pixfmt':
drivers/gpu/drm/exynos/exynos_drm_fimd.c:750:1: error: the frame size of 1032 bytes is larger than 1024 byte
drivers/gpu/drm/exynos/exynos5433_drm_decon.c: In function 'decon_win_set_pixfmt':
drivers/gpu/drm/exynos/exynos5433_drm_decon.c:381:1: error: the frame size of 1032 bytes is larger than 1024 bytes

There is really no reason to copy the large exynos_drm_plane
structure to the stack before using one of its members, so just
use a pointer instead.

Fixes: 6f8ee5c21722 ("drm/exynos: fimd: Make plane alpha configurable")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 4 ++--
 drivers/gpu/drm/exynos/exynos_drm_fimd.c      | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 4d986077738b9..bce027552474a 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -319,9 +319,9 @@ static void decon_win_set_bldmod(struct decon_context *ctx, unsigned int win,
 static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win,
 				 struct drm_framebuffer *fb)
 {
-	struct exynos_drm_plane plane = ctx->planes[win];
+	struct exynos_drm_plane *plane = &ctx->planes[win];
 	struct exynos_drm_plane_state *state =
-		to_exynos_plane_state(plane.base.state);
+		to_exynos_plane_state(plane->base.state);
 	unsigned int alpha = state->base.alpha;
 	unsigned int pixel_alpha;
 	unsigned long val;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index a090ff8370758..65489e18ab915 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -661,9 +661,9 @@ static void fimd_win_set_bldmod(struct fimd_context *ctx, unsigned int win,
 static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win,
 				struct drm_framebuffer *fb, int width)
 {
-	struct exynos_drm_plane plane = ctx->planes[win];
+	struct exynos_drm_plane *plane = &ctx->planes[win];
 	struct exynos_drm_plane_state *state =
-		to_exynos_plane_state(plane.base.state);
+		to_exynos_plane_state(plane->base.state);
 	uint32_t pixel_format = fb->format->format;
 	unsigned int alpha = state->base.alpha;
 	u32 val = WINCONx_ENWIN;
-- 
GitLab


From 4050957c7c2c14aa795dbf423b4180d5ac04e113 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Wed, 20 Dec 2023 12:53:15 +0300
Subject: [PATCH 3139/4076] drm/exynos: gsc: minor fix for loop iteration in
 gsc_runtime_resume

Do not forget to call clk_disable_unprepare() on the first element of
ctx->clocks array.

Found by Linux Verification Center (linuxtesting.org).

Fixes: 8b7d3ec83aba ("drm/exynos: gsc: Convert driver to IPP v2 core API")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Reviewed-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_gsc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 34cdabc30b4f5..5302bebbe38c9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1342,7 +1342,7 @@ static int __maybe_unused gsc_runtime_resume(struct device *dev)
 	for (i = 0; i < ctx->num_clocks; i++) {
 		ret = clk_prepare_enable(ctx->clocks[i]);
 		if (ret) {
-			while (--i > 0)
+			while (--i >= 0)
 				clk_disable_unprepare(ctx->clocks[i]);
 			return ret;
 		}
-- 
GitLab


From d8d222e09dab84a17bb65dda4b94d01c565f5327 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Tue, 16 Jan 2024 15:33:07 +1100
Subject: [PATCH 3140/4076] xfs: read only mounts with fsopen mount API are
 busted

Recently xfs/513 started failing on my test machines testing "-o
ro,norecovery" mount options. This was being emitted in dmesg:

[ 9906.932724] XFS (pmem0): no-recovery mounts must be read-only.

Turns out, readonly mounts with the fsopen()/fsconfig() mount API
have been busted since day zero. It's only taken 5 years for debian
unstable to start using this "new" mount API, and shortly after this
I noticed xfs/513 had started to fail as per above.

The syscall trace is:

fsopen("xfs", FSOPEN_CLOEXEC)           = 3
mount_setattr(-1, NULL, 0, NULL, 0)     = -1 EINVAL (Invalid argument)
.....
fsconfig(3, FSCONFIG_SET_STRING, "source", "/dev/pmem0", 0) = 0
fsconfig(3, FSCONFIG_SET_FLAG, "ro", NULL, 0) = 0
fsconfig(3, FSCONFIG_SET_FLAG, "norecovery", NULL, 0) = 0
fsconfig(3, FSCONFIG_CMD_CREATE, NULL, NULL, 0) = -1 EINVAL (Invalid argument)
close(3)                                = 0

Showing that the actual mount instantiation (FSCONFIG_CMD_CREATE) is
what threw out the error.

During mount instantiation, we call xfs_fs_validate_params() which
does:

        /* No recovery flag requires a read-only mount */
        if (xfs_has_norecovery(mp) && !xfs_is_readonly(mp)) {
                xfs_warn(mp, "no-recovery mounts must be read-only.");
                return -EINVAL;
        }

and xfs_is_readonly() checks internal mount flags for read only
state. This state is set in xfs_init_fs_context() from the
context superblock flag state:

        /*
         * Copy binary VFS mount flags we are interested in.
         */
        if (fc->sb_flags & SB_RDONLY)
                set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);

With the old mount API, all of the VFS specific superblock flags
had already been parsed and set before xfs_init_fs_context() is
called, so this all works fine.

However, in the brave new fsopen/fsconfig world,
xfs_init_fs_context() is called from fsopen() context, before any
VFS superblock have been set or parsed. Hence if we use fsopen(),
the internal XFS readonly state is *never set*. Hence anything that
depends on xfs_is_readonly() actually returning true for read only
mounts is broken if fsopen() has been used to mount the filesystem.

Fix this by moving this internal state initialisation to
xfs_fs_fill_super() before we attempt to validate the parameters
that have been set prior to the FSCONFIG_CMD_CREATE call being made.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Fixes: 73e5fff98b64 ("xfs: switch to use the new mount-api")
cc: stable@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/xfs_super.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index aff20ddd4a9f9..5a2512d20bd07 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1496,6 +1496,18 @@ xfs_fs_fill_super(
 
 	mp->m_super = sb;
 
+	/*
+	 * Copy VFS mount flags from the context now that all parameter parsing
+	 * is guaranteed to have been completed by either the old mount API or
+	 * the newer fsopen/fsconfig API.
+	 */
+	if (fc->sb_flags & SB_RDONLY)
+		set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
+	if (fc->sb_flags & SB_DIRSYNC)
+		mp->m_features |= XFS_FEAT_DIRSYNC;
+	if (fc->sb_flags & SB_SYNCHRONOUS)
+		mp->m_features |= XFS_FEAT_WSYNC;
+
 	error = xfs_fs_validate_params(mp);
 	if (error)
 		return error;
@@ -1965,6 +1977,11 @@ static const struct fs_context_operations xfs_context_ops = {
 	.free        = xfs_fs_free,
 };
 
+/*
+ * WARNING: do not initialise any parameters in this function that depend on
+ * mount option parsing having already been performed as this can be called from
+ * fsopen() before any parameters have been set.
+ */
 static int xfs_init_fs_context(
 	struct fs_context	*fc)
 {
@@ -1996,16 +2013,6 @@ static int xfs_init_fs_context(
 	mp->m_logbsize = -1;
 	mp->m_allocsize_log = 16; /* 64k */
 
-	/*
-	 * Copy binary VFS mount flags we are interested in.
-	 */
-	if (fc->sb_flags & SB_RDONLY)
-		set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
-	if (fc->sb_flags & SB_DIRSYNC)
-		mp->m_features |= XFS_FEAT_DIRSYNC;
-	if (fc->sb_flags & SB_SYNCHRONOUS)
-		mp->m_features |= XFS_FEAT_WSYNC;
-
 	fc->s_fs_info = mp;
 	fc->ops = &xfs_context_ops;
 
-- 
GitLab


From 805c74eac8cb306dc69b87b6b066ab4da77ceaf1 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 17 Jan 2024 08:29:42 -0600
Subject: [PATCH 3141/4076] gpiolib: acpi: Ignore touchpad wakeup on GPD
 G1619-04

Spurious wakeups are reported on the GPD G1619-04 which
can be absolved by programming the GPIO to ignore wakeups.

Cc: stable@vger.kernel.org
Reported-and-tested-by: George Melikov <mail@gmelikov.ru>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3073
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib-acpi.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 88066826d8e5b..cd3e9657cc36d 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1651,6 +1651,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = {
 			.ignore_interrupt = "INT33FC:00@3",
 		},
 	},
+	{
+		/*
+		 * Spurious wakeups from TP_ATTN# pin
+		 * Found in BIOS 0.35
+		 * https://gitlab.freedesktop.org/drm/amd/-/issues/3073
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GPD"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "G1619-04"),
+		},
+		.driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+			.ignore_wake = "PNP0C50:00@8",
+		},
+	},
 	{} /* Terminating entry */
 };
 
-- 
GitLab


From 30cf36bb0408a163eb3d58ea6b883c612c029286 Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Mon, 15 Jan 2024 14:44:26 +0100
Subject: [PATCH 3142/4076] accel/ivpu: Dump MMU events in case of VPU boot
 timeout

Add ivpu_mmu_evtq_dump() function that dumps existing MMU events from
MMU event queue. Call this function if VPU boot failed.

Previously MMU events were only checked in interrupt handler, but if VPU
failed to boot due to MMU faults, those faults were missed because of
interrupts not yet being enabled. This will allow checking potential
fault reason of VPU not booting.

Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-2-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 1 +
 drivers/accel/ivpu/ivpu_mmu.c | 8 ++++++++
 drivers/accel/ivpu/ivpu_mmu.h | 1 +
 3 files changed, 10 insertions(+)

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 64927682161b2..0c3180411b0e9 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -369,6 +369,7 @@ int ivpu_boot(struct ivpu_device *vdev)
 	ret = ivpu_wait_for_ready(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to boot the firmware: %d\n", ret);
+		ivpu_mmu_evtq_dump(vdev);
 		return ret;
 	}
 
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 2228c44b115fa..92ef651098d83 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -905,6 +905,14 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		ivpu_pm_schedule_recovery(vdev);
 }
 
+void ivpu_mmu_evtq_dump(struct ivpu_device *vdev)
+{
+	u32 *event;
+
+	while ((event = ivpu_mmu_get_event(vdev)) != NULL)
+		ivpu_mmu_dump_event(vdev, event);
+}
+
 void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev)
 {
 	u32 gerror_val, gerrorn_val, active;
diff --git a/drivers/accel/ivpu/ivpu_mmu.h b/drivers/accel/ivpu/ivpu_mmu.h
index cb551126806ba..6fa35c2407106 100644
--- a/drivers/accel/ivpu/ivpu_mmu.h
+++ b/drivers/accel/ivpu/ivpu_mmu.h
@@ -46,5 +46,6 @@ int ivpu_mmu_invalidate_tlb(struct ivpu_device *vdev, u16 ssid);
 
 void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev);
 void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev);
+void ivpu_mmu_evtq_dump(struct ivpu_device *vdev);
 
 #endif /* __IVPU_MMU_H__ */
-- 
GitLab


From 929acfb9c53986d5ba37cfb9e1172ad79735f8eb Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Mon, 15 Jan 2024 14:44:27 +0100
Subject: [PATCH 3143/4076] accel/ivpu: Call diagnose failure in
 ivpu_mmu_cmdq_sync()

Check for possible failure reasons in the buttress.
Some errors (like external abort) should have corresponding buttress errors
registers set indicating the real reason of failure.

Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-3-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_mmu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 92ef651098d83..1f813625aab39 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -7,6 +7,7 @@
 #include <linux/highmem.h>
 
 #include "ivpu_drv.h"
+#include "ivpu_hw.h"
 #include "ivpu_hw_reg_io.h"
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
@@ -518,6 +519,7 @@ static int ivpu_mmu_cmdq_sync(struct ivpu_device *vdev)
 
 		ivpu_err(vdev, "Timed out waiting for MMU consumer: %d, error: %s\n", ret,
 			 ivpu_mmu_cmdq_err_to_str(err));
+		ivpu_hw_diagnose_failure(vdev);
 	}
 
 	return ret;
-- 
GitLab


From 8047d36fe563bf7ee7b28a284a0892506a6000a9 Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Mon, 15 Jan 2024 14:44:28 +0100
Subject: [PATCH 3144/4076] accel/ivpu: Add debug prints for MMU map/unmap
 operations

It is common need to be able to see IOVA/physical to VPU addresses
mappings. Especially when debugging different kind of memory related
issues. Lack of such logs forces user to modify and recompile KMD manually.

This commit adds those logs under MMU debug mask which can be turned on
dynamically with module param during KMD load.

Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-4-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.h         | 1 +
 drivers/accel/ivpu/ivpu_mmu_context.c | 9 +++++++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index ebc4b84f27b20..9b6e336626e39 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -56,6 +56,7 @@
 #define IVPU_DBG_JSM	 BIT(10)
 #define IVPU_DBG_KREF	 BIT(11)
 #define IVPU_DBG_RPM	 BIT(12)
+#define IVPU_DBG_MMU_MAP BIT(13)
 
 #define ivpu_err(vdev, fmt, ...) \
 	drm_err(&(vdev)->drm, "%s(): " fmt, __func__, ##__VA_ARGS__)
diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c
index 12a8c09d4547d..fe61612992364 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -355,6 +355,9 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 		dma_addr_t dma_addr = sg_dma_address(sg) - sg->offset;
 		size_t size = sg_dma_len(sg) + sg->offset;
 
+		ivpu_dbg(vdev, MMU_MAP, "Map ctx: %u dma_addr: 0x%llx vpu_addr: 0x%llx size: %lu\n",
+			 ctx->id, dma_addr, vpu_addr, size);
+
 		ret = ivpu_mmu_context_map_pages(vdev, ctx, vpu_addr, dma_addr, size, prot);
 		if (ret) {
 			ivpu_err(vdev, "Failed to map context pages\n");
@@ -366,6 +369,7 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 
 	/* Ensure page table modifications are flushed from wc buffers to memory */
 	wmb();
+
 	mutex_unlock(&ctx->lock);
 
 	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
@@ -388,14 +392,19 @@ ivpu_mmu_context_unmap_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ct
 	mutex_lock(&ctx->lock);
 
 	for_each_sgtable_dma_sg(sgt, sg, i) {
+		dma_addr_t dma_addr = sg_dma_address(sg) - sg->offset;
 		size_t size = sg_dma_len(sg) + sg->offset;
 
+		ivpu_dbg(vdev, MMU_MAP, "Unmap ctx: %u dma_addr: 0x%llx vpu_addr: 0x%llx size: %lu\n",
+			 ctx->id, dma_addr, vpu_addr, size);
+
 		ivpu_mmu_context_unmap_pages(ctx, vpu_addr, size);
 		vpu_addr += size;
 	}
 
 	/* Ensure page table modifications are flushed from wc buffers to memory */
 	wmb();
+
 	mutex_unlock(&ctx->lock);
 
 	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
-- 
GitLab


From 2a20b857dd654595d332f2521d80bd67b03536a0 Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Mon, 15 Jan 2024 14:44:29 +0100
Subject: [PATCH 3145/4076] accel/ivpu: Add diagnostic messages when VPU fails
 to boot or suspend

Make boot/suspend failure debugging easier by dumping FW logs and error
registers.

Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-5-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 5 +++--
 drivers/accel/ivpu/ivpu_pm.c  | 4 +++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 0c3180411b0e9..ec66c2c39877d 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -17,6 +17,7 @@
 #include "ivpu_debugfs.h"
 #include "ivpu_drv.h"
 #include "ivpu_fw.h"
+#include "ivpu_fw_log.h"
 #include "ivpu_gem.h"
 #include "ivpu_hw.h"
 #include "ivpu_ipc.h"
@@ -340,8 +341,6 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
 
 	if (!ret)
 		ivpu_dbg(vdev, PM, "VPU ready message received successfully\n");
-	else
-		ivpu_hw_diagnose_failure(vdev);
 
 	return ret;
 }
@@ -369,7 +368,9 @@ int ivpu_boot(struct ivpu_device *vdev)
 	ret = ivpu_wait_for_ready(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to boot the firmware: %d\n", ret);
+		ivpu_hw_diagnose_failure(vdev);
 		ivpu_mmu_evtq_dump(vdev);
+		ivpu_fw_log_dump(vdev);
 		return ret;
 	}
 
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 0af8864cb3b55..8407f1d8c99cb 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -13,6 +13,7 @@
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
 #include "ivpu_fw.h"
+#include "ivpu_fw_log.h"
 #include "ivpu_ipc.h"
 #include "ivpu_job.h"
 #include "ivpu_jsm_msg.h"
@@ -247,7 +248,8 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 		ivpu_err(vdev, "Failed to set suspend VPU: %d\n", ret);
 
 	if (!hw_is_idle) {
-		ivpu_warn(vdev, "VPU failed to enter idle, force suspended.\n");
+		ivpu_err(vdev, "VPU failed to enter idle, force suspended.\n");
+		ivpu_fw_log_dump(vdev);
 		ivpu_pm_prepare_cold_boot(vdev);
 	} else {
 		ivpu_pm_prepare_warm_boot(vdev);
-- 
GitLab


From 7f66319927a8ced3be715eb7616a890b9bf0348b Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 15 Jan 2024 14:44:30 +0100
Subject: [PATCH 3146/4076] accel/ivpu: Fix for missing lock around
 drm_gem_shmem_vmap()

drm_gem_shmem_vmap/vunmap requires dma resv lock to be held.
This was missed during conversion to shmem helper.

Fixes: 8d88e4cdce4f ("accel/ivpu: Use GEM shmem helper for all buffers")
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-6-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_gem.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 1dda4f38ea25c..6890d33cf3528 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -361,7 +361,9 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla
 	if (ret)
 		goto err_put;
 
+	dma_resv_lock(bo->base.base.resv, NULL);
 	ret = drm_gem_shmem_vmap(&bo->base, &map);
+	dma_resv_unlock(bo->base.base.resv);
 	if (ret)
 		goto err_put;
 
@@ -376,7 +378,10 @@ void ivpu_bo_free_internal(struct ivpu_bo *bo)
 {
 	struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr);
 
+	dma_resv_lock(bo->base.base.resv, NULL);
 	drm_gem_shmem_vunmap(&bo->base, &map);
+	dma_resv_unlock(bo->base.base.resv);
+
 	drm_gem_object_put(&bo->base.base);
 }
 
-- 
GitLab


From a8c099d5d0e4b0400cfddfd95b881c8bd9349a88 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 15 Jan 2024 14:44:31 +0100
Subject: [PATCH 3147/4076] accel/ivpu: Free buffer sgt on unbind

Call dma_unmap() on all buffers before the VPU is unbinded to avoid
"device driver has pending DMA allocations while released from device"
warning when DMA-API debug is enabled.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-7-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_gem.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 6890d33cf3528..4de454bfbf917 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -112,8 +112,6 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 
 	ivpu_dbg_bo(vdev, bo, "unbind");
 
-	/* TODO: dma_unmap */
-
 	if (bo->mmu_mapped) {
 		drm_WARN_ON(&vdev->drm, !bo->ctx);
 		drm_WARN_ON(&vdev->drm, !bo->vpu_addr);
@@ -127,6 +125,18 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 		bo->vpu_addr = 0;
 		bo->ctx = NULL;
 	}
+
+	if (bo->base.base.import_attach)
+		return;
+
+	dma_resv_lock(bo->base.base.resv, NULL);
+	if (bo->base.sgt) {
+		dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0);
+		sg_free_table(bo->base.sgt);
+		kfree(bo->base.sgt);
+		bo->base.sgt = NULL;
+	}
+	dma_resv_unlock(bo->base.base.resv);
 }
 
 static void ivpu_bo_unbind(struct ivpu_bo *bo)
-- 
GitLab


From b7a0e75632eb6568c82de9108bd29e130dd082d9 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 15 Jan 2024 14:44:32 +0100
Subject: [PATCH 3148/4076] accel/ivpu: Disable buffer sharing among VPU
 contexts

This was not supported properly. A buffer was imported to another VPU
context as a separate buffer object with duplicated sgt.
Both exported and imported buffers could be DMA mapped causing a double
mapping on the same device.

Buffers imported from another VPU context will now just increase
reference count, leaving only a single sgt, fixing the problem above.
Buffers still can't be shared among VPU contexts because each has its
own MMU mapping and ivpu_bo only supports single MMU mappings.

The solution would be to use a mapping list as in panfrost or etnaviv
drivers and it will be implemented in future if required.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-8-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_gem.c | 44 +++++------------------------------
 1 file changed, 6 insertions(+), 38 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 4de454bfbf917..95e731e13941d 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -222,6 +222,12 @@ static int ivpu_bo_open(struct drm_gem_object *obj, struct drm_file *file)
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
 	struct ivpu_addr_range *range;
 
+	if (bo->ctx) {
+		ivpu_warn(vdev, "Can't add BO to ctx %u: already in ctx %u\n",
+			  file_priv->ctx.id, bo->ctx->id);
+		return -EALREADY;
+	}
+
 	if (bo->flags & DRM_IVPU_BO_SHAVE_MEM)
 		range = &vdev->hw->ranges.shave;
 	else if (bo->flags & DRM_IVPU_BO_DMA_MEM)
@@ -252,47 +258,9 @@ static void ivpu_bo_free(struct drm_gem_object *obj)
 	drm_gem_shmem_free(&bo->base);
 }
 
-static const struct dma_buf_ops ivpu_bo_dmabuf_ops =  {
-	.cache_sgt_mapping = true,
-	.attach = drm_gem_map_attach,
-	.detach = drm_gem_map_detach,
-	.map_dma_buf = drm_gem_map_dma_buf,
-	.unmap_dma_buf = drm_gem_unmap_dma_buf,
-	.release = drm_gem_dmabuf_release,
-	.mmap = drm_gem_dmabuf_mmap,
-	.vmap = drm_gem_dmabuf_vmap,
-	.vunmap = drm_gem_dmabuf_vunmap,
-};
-
-static struct dma_buf *ivpu_bo_export(struct drm_gem_object *obj, int flags)
-{
-	struct drm_device *dev = obj->dev;
-	struct dma_buf_export_info exp_info = {
-		.exp_name = KBUILD_MODNAME,
-		.owner = dev->driver->fops->owner,
-		.ops = &ivpu_bo_dmabuf_ops,
-		.size = obj->size,
-		.flags = flags,
-		.priv = obj,
-		.resv = obj->resv,
-	};
-	void *sgt;
-
-	/*
-	 * Make sure that pages are allocated and dma-mapped before exporting the bo.
-	 * DMA-mapping is required if the bo will be imported to the same device.
-	 */
-	sgt = drm_gem_shmem_get_pages_sgt(to_drm_gem_shmem_obj(obj));
-	if (IS_ERR(sgt))
-		return sgt;
-
-	return drm_gem_dmabuf_export(dev, &exp_info);
-}
-
 static const struct drm_gem_object_funcs ivpu_gem_funcs = {
 	.free = ivpu_bo_free,
 	.open = ivpu_bo_open,
-	.export = ivpu_bo_export,
 	.print_info = drm_gem_shmem_object_print_info,
 	.pin = drm_gem_shmem_object_pin,
 	.unpin = drm_gem_shmem_object_unpin,
-- 
GitLab


From 37dee2a2f4330a030abc5674bcec25ccc4addbcc Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 15 Jan 2024 14:44:33 +0100
Subject: [PATCH 3149/4076] accel/ivpu: Improve buffer object debug logs

Make debug logs more readable and consistent:
  - don't print handle as it is not always available for all buffers
  - use hashed ivpu_bo ptr as main buffer identifier
  - remove unused fields from ivpu_bo_print_info()

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Wachowski, Karol <karol.wachowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-9-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_gem.c | 63 ++++++++++++-----------------------
 drivers/accel/ivpu/ivpu_gem.h |  1 -
 2 files changed, 22 insertions(+), 42 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 95e731e13941d..16f3035b91c07 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -24,14 +24,11 @@ static const struct drm_gem_object_funcs ivpu_gem_funcs;
 
 static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, const char *action)
 {
-	if (bo->ctx)
-		ivpu_dbg(vdev, BO, "%6s: size %zu has_pages %d dma_mapped %d handle %u ctx %d vpu_addr 0x%llx mmu_mapped %d\n",
-			 action, ivpu_bo_size(bo), (bool)bo->base.pages, (bool)bo->base.sgt,
-			 bo->handle, bo->ctx->id, bo->vpu_addr, bo->mmu_mapped);
-	else
-		ivpu_dbg(vdev, BO, "%6s: size %zu has_pages %d dma_mapped %d handle %u (not added to context)\n",
-			 action, ivpu_bo_size(bo), (bool)bo->base.pages, (bool)bo->base.sgt,
-			 bo->handle);
+	ivpu_dbg(vdev, BO,
+		 "%6s: bo %8p vpu_addr %9llx size %8zu ctx %d has_pages %d dma_mapped %d mmu_mapped %d wc %d imported %d\n",
+		 action, bo, bo->vpu_addr, ivpu_bo_size(bo), bo->ctx ? bo->ctx->id : 0,
+		 (bool)bo->base.pages, (bool)bo->base.sgt, bo->mmu_mapped, bo->base.map_wc,
+		 (bool)bo->base.base.import_attach);
 }
 
 /*
@@ -49,12 +46,7 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 	mutex_lock(&bo->lock);
 
 	ivpu_dbg_bo(vdev, bo, "pin");
-
-	if (!bo->ctx) {
-		ivpu_err(vdev, "vpu_addr not allocated for BO %d\n", bo->handle);
-		ret = -EINVAL;
-		goto unlock;
-	}
+	drm_WARN_ON(&vdev->drm, !bo->ctx);
 
 	if (!bo->mmu_mapped) {
 		struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
@@ -108,9 +100,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
 
-	lockdep_assert_held(&bo->lock);
-
-	ivpu_dbg_bo(vdev, bo, "unbind");
+	lockdep_assert(lockdep_is_held(&bo->lock) || !kref_read(&bo->base.base.refcount));
 
 	if (bo->mmu_mapped) {
 		drm_WARN_ON(&vdev->drm, !bo->ctx);
@@ -122,7 +112,6 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 
 	if (bo->ctx) {
 		ivpu_mmu_context_remove_node(bo->ctx, &bo->mm_node);
-		bo->vpu_addr = 0;
 		bo->ctx = NULL;
 	}
 
@@ -156,8 +145,10 @@ void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_m
 	mutex_lock(&vdev->bo_list_lock);
 	list_for_each_entry(bo, &vdev->bo_list, bo_list_node) {
 		mutex_lock(&bo->lock);
-		if (bo->ctx == ctx)
+		if (bo->ctx == ctx) {
+			ivpu_dbg_bo(vdev, bo, "unbind");
 			ivpu_bo_unbind_locked(bo);
+		}
 		mutex_unlock(&bo->lock);
 	}
 	mutex_unlock(&vdev->bo_list_lock);
@@ -209,9 +200,6 @@ ivpu_bo_create(struct ivpu_device *vdev, u64 size, u32 flags)
 	list_add_tail(&bo->bo_list_node, &vdev->bo_list);
 	mutex_unlock(&vdev->bo_list_lock);
 
-	ivpu_dbg(vdev, BO, "create: vpu_addr 0x%llx size %zu flags 0x%x\n",
-		 bo->vpu_addr, bo->base.base.size, flags);
-
 	return bo;
 }
 
@@ -243,14 +231,14 @@ static void ivpu_bo_free(struct drm_gem_object *obj)
 	struct ivpu_device *vdev = to_ivpu_device(obj->dev);
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
 
+	ivpu_dbg_bo(vdev, bo, "free");
+
 	mutex_lock(&vdev->bo_list_lock);
 	list_del(&bo->bo_list_node);
 	mutex_unlock(&vdev->bo_list_lock);
 
 	drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
 
-	ivpu_dbg_bo(vdev, bo, "free");
-
 	ivpu_bo_unbind(bo);
 	mutex_destroy(&bo->lock);
 
@@ -293,11 +281,9 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 		return PTR_ERR(bo);
 	}
 
-	ret = drm_gem_handle_create(file, &bo->base.base, &bo->handle);
-	if (!ret) {
+	ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
+	if (!ret)
 		args->vpu_addr = bo->vpu_addr;
-		args->handle = bo->handle;
-	}
 
 	drm_gem_object_put(&bo->base.base);
 
@@ -415,19 +401,11 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 {
-	unsigned long dma_refcount = 0;
-
 	mutex_lock(&bo->lock);
 
-	if (bo->base.base.dma_buf && bo->base.base.dma_buf->file)
-		dma_refcount = atomic_long_read(&bo->base.base.dma_buf->file->f_count);
-
-	drm_printf(p, "%-3u %-6d 0x%-12llx %-10lu 0x%-8x %-4u %-8lu",
-		   bo->ctx->id, bo->handle, bo->vpu_addr, bo->base.base.size,
-		   bo->flags, kref_read(&bo->base.base.refcount), dma_refcount);
-
-	if (bo->base.base.import_attach)
-		drm_printf(p, " imported");
+	drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u",
+		   bo, bo->ctx->id, bo->vpu_addr, bo->base.base.size,
+		   bo->flags, kref_read(&bo->base.base.refcount));
 
 	if (bo->base.pages)
 		drm_printf(p, " has_pages");
@@ -435,6 +413,9 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 	if (bo->mmu_mapped)
 		drm_printf(p, " mmu_mapped");
 
+	if (bo->base.base.import_attach)
+		drm_printf(p, " imported");
+
 	drm_printf(p, "\n");
 
 	mutex_unlock(&bo->lock);
@@ -445,8 +426,8 @@ void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p)
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_bo *bo;
 
-	drm_printf(p, "%-3s %-6s %-14s %-10s %-10s %-4s %-8s %s\n",
-		   "ctx", "handle", "vpu_addr", "size", "flags", "refs", "dma_refs", "attribs");
+	drm_printf(p, "%-9s %-3s %-14s %-10s %-10s %-4s %s\n",
+		   "bo", "ctx", "vpu_addr", "size", "flags", "refs", "attribs");
 
 	mutex_lock(&vdev->bo_list_lock);
 	list_for_each_entry(bo, &vdev->bo_list, bo_list_node)
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index d75cad0d3c742..5cb1dda3e58ea 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -19,7 +19,6 @@ struct ivpu_bo {
 
 	struct mutex lock; /* Protects: ctx, mmu_mapped, vpu_addr */
 	u64 vpu_addr;
-	u32 handle;
 	u32 flags;
 	u32 job_status; /* Valid only for command buffer */
 	bool mmu_mapped;
-- 
GitLab


From b246271d257b4b0573e88f443ed8091f8b044895 Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Mon, 15 Jan 2024 14:44:34 +0100
Subject: [PATCH 3150/4076] accel/ivpu: Deprecate
 DRM_IVPU_PARAM_CONTEXT_PRIORITY param

DRM_IVPU_PARAM_CONTEXT_PRIORITY has been deprecated because it
has been replaced with DRM_IVPU_JOB_PRIORITY levels set with
submit IOCTL and was unused anyway.

Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240115134434.493839-10-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 11 -----------
 drivers/accel/ivpu/ivpu_drv.h |  1 -
 drivers/accel/ivpu/ivpu_job.c |  3 +++
 include/uapi/drm/ivpu_accel.h | 25 ++++++++++++++++++++-----
 4 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index ec66c2c39877d..546c0899bb9e1 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -177,9 +177,6 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 	case DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
 		args->value = vdev->hw->ranges.user.start;
 		break;
-	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-		args->value = file_priv->priority;
-		break;
 	case DRM_IVPU_PARAM_CONTEXT_ID:
 		args->value = file_priv->ctx.id;
 		break;
@@ -219,17 +216,10 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 
 static int ivpu_set_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
-	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct drm_ivpu_param *args = data;
 	int ret = 0;
 
 	switch (args->param) {
-	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-		if (args->value <= DRM_IVPU_CONTEXT_PRIORITY_REALTIME)
-			file_priv->priority = args->value;
-		else
-			ret = -EINVAL;
-		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -258,7 +248,6 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 	}
 
 	file_priv->vdev = vdev;
-	file_priv->priority = DRM_IVPU_CONTEXT_PRIORITY_NORMAL;
 	kref_init(&file_priv->ref);
 	mutex_init(&file_priv->lock);
 
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 9b6e336626e39..7a6bc1918780c 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -146,7 +146,6 @@ struct ivpu_file_priv {
 	struct mutex lock; /* Protects cmdq */
 	struct ivpu_cmdq *cmdq[IVPU_NUM_ENGINES];
 	struct ivpu_mmu_context ctx;
-	u32 priority;
 	bool has_mmu_faults;
 };
 
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 7206cf9cdb4a4..82e40bb4803c5 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -488,6 +488,9 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (params->engine > DRM_IVPU_ENGINE_COPY)
 		return -EINVAL;
 
+	if (params->priority > DRM_IVPU_JOB_PRIORITY_REALTIME)
+		return -EINVAL;
+
 	if (params->buffer_count == 0 || params->buffer_count > JOB_MAX_BUFFER_COUNT)
 		return -EINVAL;
 
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
index de1944e42c655..63c49318a8630 100644
--- a/include/uapi/drm/ivpu_accel.h
+++ b/include/uapi/drm/ivpu_accel.h
@@ -53,7 +53,7 @@ extern "C" {
 #define DRM_IVPU_PARAM_CORE_CLOCK_RATE	    3
 #define DRM_IVPU_PARAM_NUM_CONTEXTS	    4
 #define DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS 5
-#define DRM_IVPU_PARAM_CONTEXT_PRIORITY	    6
+#define DRM_IVPU_PARAM_CONTEXT_PRIORITY	    6 /* Deprecated */
 #define DRM_IVPU_PARAM_CONTEXT_ID	    7
 #define DRM_IVPU_PARAM_FW_API_VERSION	    8
 #define DRM_IVPU_PARAM_ENGINE_HEARTBEAT	    9
@@ -64,11 +64,18 @@ extern "C" {
 
 #define DRM_IVPU_PLATFORM_TYPE_SILICON	    0
 
+/* Deprecated, use DRM_IVPU_JOB_PRIORITY */
 #define DRM_IVPU_CONTEXT_PRIORITY_IDLE	    0
 #define DRM_IVPU_CONTEXT_PRIORITY_NORMAL    1
 #define DRM_IVPU_CONTEXT_PRIORITY_FOCUS	    2
 #define DRM_IVPU_CONTEXT_PRIORITY_REALTIME  3
 
+#define DRM_IVPU_JOB_PRIORITY_DEFAULT  0
+#define DRM_IVPU_JOB_PRIORITY_IDLE     1
+#define DRM_IVPU_JOB_PRIORITY_NORMAL   2
+#define DRM_IVPU_JOB_PRIORITY_FOCUS    3
+#define DRM_IVPU_JOB_PRIORITY_REALTIME 4
+
 /**
  * DRM_IVPU_CAP_METRIC_STREAMER
  *
@@ -112,10 +119,6 @@ struct drm_ivpu_param {
 	 * %DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
 	 * Lowest VPU virtual address available in the current context (read-only)
 	 *
-	 * %DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-	 * Value of current context scheduling priority (read-write).
-	 * See DRM_IVPU_CONTEXT_PRIORITY_* for possible values.
-	 *
 	 * %DRM_IVPU_PARAM_CONTEXT_ID:
 	 * Current context ID, always greater than 0 (read-only)
 	 *
@@ -286,6 +289,18 @@ struct drm_ivpu_submit {
 	 * to be executed. The offset has to be 8-byte aligned.
 	 */
 	__u32 commands_offset;
+
+	/**
+	 * @priority:
+	 *
+	 * Priority to be set for related job command queue, can be one of the following:
+	 * %DRM_IVPU_JOB_PRIORITY_DEFAULT
+	 * %DRM_IVPU_JOB_PRIORITY_IDLE
+	 * %DRM_IVPU_JOB_PRIORITY_NORMAL
+	 * %DRM_IVPU_JOB_PRIORITY_FOCUS
+	 * %DRM_IVPU_JOB_PRIORITY_REALTIME
+	 */
+	__u32 priority;
 };
 
 /* drm_ivpu_bo_wait job status codes */
-- 
GitLab


From 0dd20a48a541ea5485b8bfc0e0bdbc6ae29b389f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 16 Jan 2024 20:30:59 -0800
Subject: [PATCH 3151/4076] MIPS: Cobalt: Fix missing prototypes

Fix missing prototypes warnings for cobalt_machine_halt() and
cobalt_machine_restart() by moving their prototypes to cobalt.h which is
included by setup.c.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/cobalt/setup.c                   | 3 ---
 arch/mips/include/asm/mach-cobalt/cobalt.h | 3 +++
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/mips/cobalt/setup.c b/arch/mips/cobalt/setup.c
index 2e099d55a564a..9a266bf783399 100644
--- a/arch/mips/cobalt/setup.c
+++ b/arch/mips/cobalt/setup.c
@@ -23,9 +23,6 @@
 
 #include <cobalt.h>
 
-extern void cobalt_machine_restart(char *command);
-extern void cobalt_machine_halt(void);
-
 const char *get_system_type(void)
 {
 	switch (cobalt_board_id) {
diff --git a/arch/mips/include/asm/mach-cobalt/cobalt.h b/arch/mips/include/asm/mach-cobalt/cobalt.h
index 5b9fce73f11d1..97f9d5e9446d2 100644
--- a/arch/mips/include/asm/mach-cobalt/cobalt.h
+++ b/arch/mips/include/asm/mach-cobalt/cobalt.h
@@ -19,4 +19,7 @@ extern int cobalt_board_id;
 #define COBALT_BRD_ID_QUBE2    0x5
 #define COBALT_BRD_ID_RAQ2     0x6
 
+void cobalt_machine_halt(void);
+void cobalt_machine_restart(char *command);
+
 #endif /* __ASM_COBALT_H */
-- 
GitLab


From feab19143a1c8c5efdf1934dd0b1defb29bb5026 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 17 Jan 2024 15:49:44 -0800
Subject: [PATCH 3152/4076] MIPS: Alchemy: Fix missing prototypes

We have a number of missing prototypes warnings for board_setup(),
alchemy_set_lpj() and prom_init_cmdline(), prom_getenv() and
prom_get_ethernet_addr(). Fix those by providing definitions for the
first two functions in au1000.h which is included everywhere relevant,
and including prom.h for the last three.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/alchemy/common/prom.c            | 1 +
 arch/mips/alchemy/common/setup.c           | 4 +---
 arch/mips/include/asm/mach-au1x00/au1000.h | 3 +++
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/mips/alchemy/common/prom.c b/arch/mips/alchemy/common/prom.c
index b13d8adf3be47..20d30f6265cdc 100644
--- a/arch/mips/alchemy/common/prom.c
+++ b/arch/mips/alchemy/common/prom.c
@@ -40,6 +40,7 @@
 #include <linux/string.h>
 
 #include <asm/bootinfo.h>
+#include <prom.h>
 
 int prom_argc;
 char **prom_argv;
diff --git a/arch/mips/alchemy/common/setup.c b/arch/mips/alchemy/common/setup.c
index 2388d68786f4a..a7a6d31a7a414 100644
--- a/arch/mips/alchemy/common/setup.c
+++ b/arch/mips/alchemy/common/setup.c
@@ -30,13 +30,11 @@
 #include <linux/mm.h>
 #include <linux/dma-map-ops.h> /* for dma_default_coherent */
 
+#include <asm/bootinfo.h>
 #include <asm/mipsregs.h>
 
 #include <au1000.h>
 
-extern void __init board_setup(void);
-extern void __init alchemy_set_lpj(void);
-
 static bool alchemy_dma_coherent(void)
 {
 	switch (alchemy_get_cputype()) {
diff --git a/arch/mips/include/asm/mach-au1x00/au1000.h b/arch/mips/include/asm/mach-au1x00/au1000.h
index a7eec3364a64a..41546777902ba 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000.h
@@ -597,6 +597,9 @@
 
 #include <asm/cpu.h>
 
+void alchemy_set_lpj(void);
+void board_setup(void);
+
 /* helpers to access the SYS_* registers */
 static inline unsigned long alchemy_rdsys(int regofs)
 {
-- 
GitLab


From 437a310b22244d4e0b78665c3042e5d1c0f45306 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 20 Dec 2023 17:21:12 +0000
Subject: [PATCH 3153/4076] firmware: arm_scmi: Check mailbox/SMT channel for
 consistency

On reception of a completion interrupt the shared memory area is accessed
to retrieve the message header at first and then, if the message sequence
number identifies a transaction which is still pending, the related
payload is fetched too.

When an SCMI command times out the channel ownership remains with the
platform until eventually a late reply is received and, as a consequence,
any further transmission attempt remains pending, waiting for the channel
to be relinquished by the platform.

Once that late reply is received the channel ownership is given back
to the agent and any pending request is then allowed to proceed and
overwrite the SMT area of the just delivered late reply; then the wait
for the reply to the new request starts.

It has been observed that the spurious IRQ related to the late reply can
be wrongly associated with the freshly enqueued request: when that happens
the SCMI stack in-flight lookup procedure is fooled by the fact that the
message header now present in the SMT area is related to the new pending
transaction, even though the real reply has still to arrive.

This race-condition on the A2P channel can be detected by looking at the
channel status bits: a genuine reply from the platform will have set the
channel free bit before triggering the completion IRQ.

Add a consistency check to validate such condition in the A2P ISR.

Reported-by: Xinglong Yang <xinglong.yang@cixtech.com>
Closes: https://lore.kernel.org/all/PUZPR06MB54981E6FA00D82BFDBB864FBF08DA@PUZPR06MB5498.apcprd06.prod.outlook.com/
Fixes: 5c8a47a5a91d ("firmware: arm_scmi: Make scmi core independent of the transport type")
Cc: stable@vger.kernel.org # 5.15+
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Tested-by: Xinglong Yang <xinglong.yang@cixtech.com>
Link: https://lore.kernel.org/r/20231220172112.763539-1-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/common.h  |  1 +
 drivers/firmware/arm_scmi/mailbox.c | 14 ++++++++++++++
 drivers/firmware/arm_scmi/shmem.c   |  6 ++++++
 3 files changed, 21 insertions(+)

diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h
index c46dc5215af7a..00b165d1f502d 100644
--- a/drivers/firmware/arm_scmi/common.h
+++ b/drivers/firmware/arm_scmi/common.h
@@ -314,6 +314,7 @@ void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem,
 void shmem_clear_channel(struct scmi_shared_mem __iomem *shmem);
 bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem,
 		     struct scmi_xfer *xfer);
+bool shmem_channel_free(struct scmi_shared_mem __iomem *shmem);
 
 /* declarations for message passing transports */
 struct scmi_msg_payld;
diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c
index 19246ed1f01ff..b8d470417e8f9 100644
--- a/drivers/firmware/arm_scmi/mailbox.c
+++ b/drivers/firmware/arm_scmi/mailbox.c
@@ -45,6 +45,20 @@ static void rx_callback(struct mbox_client *cl, void *m)
 {
 	struct scmi_mailbox *smbox = client_to_scmi_mailbox(cl);
 
+	/*
+	 * An A2P IRQ is NOT valid when received while the platform still has
+	 * the ownership of the channel, because the platform at first releases
+	 * the SMT channel and then sends the completion interrupt.
+	 *
+	 * This addresses a possible race condition in which a spurious IRQ from
+	 * a previous timed-out reply which arrived late could be wrongly
+	 * associated with the next pending transaction.
+	 */
+	if (cl->knows_txdone && !shmem_channel_free(smbox->shmem)) {
+		dev_warn(smbox->cinfo->dev, "Ignoring spurious A2P IRQ !\n");
+		return;
+	}
+
 	scmi_rx_callback(smbox->cinfo, shmem_read_header(smbox->shmem), NULL);
 }
 
diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c
index 87b4f4d35f062..517d52fb3bcbb 100644
--- a/drivers/firmware/arm_scmi/shmem.c
+++ b/drivers/firmware/arm_scmi/shmem.c
@@ -122,3 +122,9 @@ bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem,
 		(SCMI_SHMEM_CHAN_STAT_CHANNEL_ERROR |
 		 SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE);
 }
+
+bool shmem_channel_free(struct scmi_shared_mem __iomem *shmem)
+{
+	return (ioread32(&shmem->channel_status) &
+			SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE);
+}
-- 
GitLab


From 0726fcc8d4af75441b38aaa082f820e63b3a8748 Mon Sep 17 00:00:00 2001
From: Tanzir Hasan <tanzirh@google.com>
Date: Tue, 26 Dec 2023 22:52:03 +0000
Subject: [PATCH 3154/4076] firmware: arm_scmi: Replace asm-generic/bug.h with
 linux/bug.h

linux/bug.h includes asm-generic/bug.h already and hence replacing
asm-generic/bug.h with linux/bug.h will not regress any build.
Also, it is always better to avoid header file inclusion from asm-generic
if possible.

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Tanzir Hasan <tanzirh@google.com>
Link: https://lore.kernel.org/r/20231226-shmem-v1-1-ea15ce81d8ba@google.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/shmem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c
index 517d52fb3bcbb..8bf495bcad09b 100644
--- a/drivers/firmware/arm_scmi/shmem.c
+++ b/drivers/firmware/arm_scmi/shmem.c
@@ -10,7 +10,7 @@
 #include <linux/processor.h>
 #include <linux/types.h>
 
-#include <asm-generic/bug.h>
+#include <linux/bug.h>
 
 #include "common.h"
 
-- 
GitLab


From e8ef4bbe39b9576a73f104f6af743fb9c7b624ba Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 8 Jan 2024 18:50:49 +0000
Subject: [PATCH 3155/4076] firmware: arm_scmi: Use xa_insert() to store opps

When storing opps by level or index use xa_insert() instead of xa_store()
and add error-checking to spot bad duplicates indexes possibly wrongly
provided by the platform firmware.

Fixes: 31c7c1397a33 ("firmware: arm_scmi: Add v3.2 perf level indexing mode support")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240108185050.1628687-1-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/perf.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index 8ea2a7b3d35d2..211e8e0aef2c2 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -350,8 +350,8 @@ process_response_opp(struct scmi_opp *opp, unsigned int loop_idx,
 }
 
 static inline void
-process_response_opp_v4(struct perf_dom_info *dom, struct scmi_opp *opp,
-			unsigned int loop_idx,
+process_response_opp_v4(struct device *dev, struct perf_dom_info *dom,
+			struct scmi_opp *opp, unsigned int loop_idx,
 			const struct scmi_msg_resp_perf_describe_levels_v4 *r)
 {
 	opp->perf = le32_to_cpu(r->opp[loop_idx].perf_val);
@@ -362,10 +362,23 @@ process_response_opp_v4(struct perf_dom_info *dom, struct scmi_opp *opp,
 	/* Note that PERF v4 reports always five 32-bit words */
 	opp->indicative_freq = le32_to_cpu(r->opp[loop_idx].indicative_freq);
 	if (dom->level_indexing_mode) {
+		int ret;
+
 		opp->level_index = le32_to_cpu(r->opp[loop_idx].level_index);
 
-		xa_store(&dom->opps_by_idx, opp->level_index, opp, GFP_KERNEL);
-		xa_store(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
+		ret = xa_insert(&dom->opps_by_idx, opp->level_index, opp,
+				GFP_KERNEL);
+		if (ret)
+			dev_warn(dev,
+				 "Failed to add opps_by_idx at %d - ret:%d\n",
+				 opp->level_index, ret);
+
+		ret = xa_insert(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
+		if (ret)
+			dev_warn(dev,
+				 "Failed to add opps_by_lvl at %d - ret:%d\n",
+				 opp->perf, ret);
+
 		hash_add(dom->opps_by_freq, &opp->hash, opp->indicative_freq);
 	}
 }
@@ -382,7 +395,7 @@ iter_perf_levels_process_response(const struct scmi_protocol_handle *ph,
 	if (PROTOCOL_REV_MAJOR(p->version) <= 0x3)
 		process_response_opp(opp, st->loop_idx, response);
 	else
-		process_response_opp_v4(p->perf_dom, opp, st->loop_idx,
+		process_response_opp_v4(ph->dev, p->perf_dom, opp, st->loop_idx,
 					response);
 	p->perf_dom->opp_count++;
 
-- 
GitLab


From b5dc0ffd36560dbadaed9a3d9fd7838055d62d74 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 8 Jan 2024 18:50:50 +0000
Subject: [PATCH 3156/4076] firmware: arm_scmi: Use xa_insert() when saving raw
 queues

Use xa_insert() when saving per-channel raw queues to better check for
duplicates.

Fixes: 7860701d1e6e ("firmware: arm_scmi: Add per-channel raw injection support")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240108185050.1628687-2-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/raw_mode.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c
index 0493aa3c12bf5..3505735185033 100644
--- a/drivers/firmware/arm_scmi/raw_mode.c
+++ b/drivers/firmware/arm_scmi/raw_mode.c
@@ -1111,7 +1111,6 @@ static int scmi_raw_mode_setup(struct scmi_raw_mode_info *raw,
 		int i;
 
 		for (i = 0; i < num_chans; i++) {
-			void *xret;
 			struct scmi_raw_queue *q;
 
 			q = scmi_raw_queue_init(raw);
@@ -1120,13 +1119,12 @@ static int scmi_raw_mode_setup(struct scmi_raw_mode_info *raw,
 				goto err_xa;
 			}
 
-			xret = xa_store(&raw->chans_q, channels[i], q,
+			ret = xa_insert(&raw->chans_q, channels[i], q,
 					GFP_KERNEL);
-			if (xa_err(xret)) {
+			if (ret) {
 				dev_err(dev,
 					"Fail to allocate Raw queue 0x%02X\n",
 					channels[i]);
-				ret = xa_err(xret);
 				goto err_xa;
 			}
 		}
@@ -1322,6 +1320,12 @@ void scmi_raw_message_report(void *r, struct scmi_xfer *xfer,
 	dev = raw->handle->dev;
 	q = scmi_raw_queue_select(raw, idx,
 				  SCMI_XFER_IS_CHAN_SET(xfer) ? chan_id : 0);
+	if (!q) {
+		dev_warn(dev,
+			 "RAW[%d] - NO queue for chan 0x%X. Dropping report.\n",
+			 idx, chan_id);
+		return;
+	}
 
 	/*
 	 * Grab the msg_q_lock upfront to avoid a possible race between
-- 
GitLab


From 27600c96e2ffa6c1b2cb378ddc75c6620c628d04 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Tue, 9 Jan 2024 15:01:06 +0000
Subject: [PATCH 3157/4076] firmware: arm_scmi: Fix the clock protocol version
 for v3.2

The clock protocol version as per the SCMI v3.2 specification is 0x30000.
Enable the v3.0 clock protocol features only when clock protocol version
equals 0x30000.

The previous beta version of the spec had this value set to 0x20001 and
th same value trickled down from the initial development. The version
update were missed in the driver.

Fixes: e49e314a2cf7 ("firmware: arm_scmi: Add clock v3.2 CONFIG_SET support")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240109150106.2066739-1-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/clock.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index c0644558042a0..d6357513163c8 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -954,8 +954,7 @@ static int scmi_clock_protocol_init(const struct scmi_protocol_handle *ph)
 			scmi_clock_describe_rates_get(ph, clkid, clk);
 	}
 
-	if (PROTOCOL_REV_MAJOR(version) >= 0x2 &&
-	    PROTOCOL_REV_MINOR(version) >= 0x1) {
+	if (PROTOCOL_REV_MAJOR(version) >= 0x3) {
 		cinfo->clock_config_set = scmi_clock_config_set_v2;
 		cinfo->clock_config_get = scmi_clock_config_get_v2;
 	} else {
-- 
GitLab


From 6bd1b3fede83d8ba5314886062a9bfdada5102a9 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Tue, 9 Jan 2024 18:17:16 +0000
Subject: [PATCH 3158/4076] firmware: arm_scmi: Fix the clock protocol
 supported version

Rollback currently supported SCMI clock protocol version to v2.0 since
some of the mandatory v3.0 features are indeed still not supported yet.

Fixes: b5efc28a754d ("firmware: arm_scmi: Add protocol versioning checks")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240109181716.2338636-1-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index d6357513163c8..e2050adbf85c6 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -13,7 +13,7 @@
 #include "notify.h"
 
 /* Updated only after ALL the mandatory features for that version are merged */
-#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20001
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20000
 
 enum scmi_clock_protocol_cmd {
 	CLOCK_ATTRIBUTES = 0x3,
-- 
GitLab


From 59b2e242b13192e50bf47df3780bf8a7e2260e98 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 8 Jan 2024 12:34:11 +0000
Subject: [PATCH 3159/4076] firmware: arm_ffa: Add missing rwlock_init() in
 ffa_setup_partitions()

Add the missing rwlock initialization for the individual FF-A partition
information in ffa_setup_partitions().

Fixes: 0184450b8b1e ("firmware: arm_ffa: Add schedule receiver callback mechanism")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240108-ffa_fixes_6-8-v1-1-75bf7035bc50@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 6146b2927d5c5..ed1d6a24934ec 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -1226,6 +1226,7 @@ static void ffa_setup_partitions(void)
 			ffa_device_unregister(ffa_dev);
 			continue;
 		}
+		rwlock_init(&info->rw_lock);
 		xa_store(&drv_info->partition_info, tpbuf->id, info, GFP_KERNEL);
 	}
 	drv_info->partition_count = count;
-- 
GitLab


From 5ff30ade16cd9efc2466d3ea22bbaf370772941a Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 8 Jan 2024 12:34:12 +0000
Subject: [PATCH 3160/4076] firmware: arm_ffa: Add missing rwlock_init() for
 the driver partition

Add the missing rwlock initialization for the FF-A partition associated
the driver in ffa_setup_partitions(). It will the primary scheduler
partition in the host or the VM partition in the virtualised environment.
IOW, it corresponds to the partition with VM ID == drv_info->vm_id.

Fixes: 1b6bf41b7a65 ("firmware: arm_ffa: Add notification handling mechanism")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240108-ffa_fixes_6-8-v1-2-75bf7035bc50@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index ed1d6a24934ec..8df92c9521f43 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -1237,6 +1237,7 @@ static void ffa_setup_partitions(void)
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return;
+	rwlock_init(&info->rw_lock);
 	xa_store(&drv_info->partition_info, drv_info->vm_id, info, GFP_KERNEL);
 	drv_info->partition_count++;
 }
-- 
GitLab


From c00d9738fd5fce15dc5494d05b7599dce23e8146 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 8 Jan 2024 12:34:13 +0000
Subject: [PATCH 3161/4076] firmware: arm_ffa: Check xa_load() return value

Add a check to verify the result of xa_load() during the partition
lookups done while registering/unregistering the scheduler receiver
interrupt callbacks and while executing the main scheduler receiver
interrupt callback handler.

Fixes: 0184450b8b1e ("firmware: arm_ffa: Add schedule receiver callback mechanism")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240108-ffa_fixes_6-8-v1-3-75bf7035bc50@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 8df92c9521f43..0ea1dd6e55c40 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -733,6 +733,11 @@ static void __do_sched_recv_cb(u16 part_id, u16 vcpu, bool is_per_vcpu)
 	void *cb_data;
 
 	partition = xa_load(&drv_info->partition_info, part_id);
+	if (!partition) {
+		pr_err("%s: Invalid partition ID 0x%x\n", __func__, part_id);
+		return;
+	}
+
 	read_lock(&partition->rw_lock);
 	callback = partition->callback;
 	cb_data = partition->cb_data;
@@ -915,6 +920,11 @@ static int ffa_sched_recv_cb_update(u16 part_id, ffa_sched_recv_cb callback,
 		return -EOPNOTSUPP;
 
 	partition = xa_load(&drv_info->partition_info, part_id);
+	if (!partition) {
+		pr_err("%s: Invalid partition ID 0x%x\n", __func__, part_id);
+		return -EINVAL;
+	}
+
 	write_lock(&partition->rw_lock);
 
 	cb_valid = !!partition->callback;
-- 
GitLab


From ad9d9a107a4308e75ec34890547447c7095b4781 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 8 Jan 2024 12:34:14 +0000
Subject: [PATCH 3162/4076] firmware: arm_ffa: Simplify
 ffa_partitions_cleanup()

On cleanup iterate the XArrays with xa_for_each() and remove the existent
entries with xa_erase(), finally destroy the XArray itself.

Remove partition_count field from drv_info since no more used anywhwere.

Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240108-ffa_fixes_6-8-v1-4-75bf7035bc50@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 26 ++++++--------------------
 1 file changed, 6 insertions(+), 20 deletions(-)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 0ea1dd6e55c40..2426021dbb58f 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -107,7 +107,6 @@ struct ffa_drv_info {
 	struct work_struct notif_pcpu_work;
 	struct work_struct irq_work;
 	struct xarray partition_info;
-	unsigned int partition_count;
 	DECLARE_HASHTABLE(notifier_hash, ilog2(FFA_MAX_NOTIFICATIONS));
 	struct mutex notify_lock; /* lock to protect notifier hashtable  */
 };
@@ -1239,7 +1238,6 @@ static void ffa_setup_partitions(void)
 		rwlock_init(&info->rw_lock);
 		xa_store(&drv_info->partition_info, tpbuf->id, info, GFP_KERNEL);
 	}
-	drv_info->partition_count = count;
 
 	kfree(pbuf);
 
@@ -1249,29 +1247,18 @@ static void ffa_setup_partitions(void)
 		return;
 	rwlock_init(&info->rw_lock);
 	xa_store(&drv_info->partition_info, drv_info->vm_id, info, GFP_KERNEL);
-	drv_info->partition_count++;
 }
 
 static void ffa_partitions_cleanup(void)
 {
-	struct ffa_dev_part_info **info;
-	int idx, count = drv_info->partition_count;
-
-	if (!count)
-		return;
-
-	info = kcalloc(count, sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return;
-
-	xa_extract(&drv_info->partition_info, (void **)info, 0, VM_ID_MASK,
-		   count, XA_PRESENT);
+	struct ffa_dev_part_info *info;
+	unsigned long idx;
 
-	for (idx = 0; idx < count; idx++)
-		kfree(info[idx]);
-	kfree(info);
+	xa_for_each(&drv_info->partition_info, idx, info) {
+		xa_erase(&drv_info->partition_info, idx);
+		kfree(info);
+	}
 
-	drv_info->partition_count = 0;
 	xa_destroy(&drv_info->partition_info);
 }
 
@@ -1547,7 +1534,6 @@ static void __exit ffa_exit(void)
 	ffa_rxtx_unmap(drv_info->vm_id);
 	free_pages_exact(drv_info->tx_buffer, RXTX_BUFFER_SIZE);
 	free_pages_exact(drv_info->rx_buffer, RXTX_BUFFER_SIZE);
-	xa_destroy(&drv_info->partition_info);
 	kfree(drv_info);
 	arm_ffa_bus_exit();
 }
-- 
GitLab


From ace760d9c0498fb226269ed34f0e86417d90f91b Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 8 Jan 2024 12:34:15 +0000
Subject: [PATCH 3163/4076] firmware: arm_ffa: Use xa_insert() and check for
 result

While adding new partitions descriptors to the XArray the outcome of the
stores should be checked and, in particular, it has also to be ensured
that an existing entry with the same index was not already present, since
partitions IDs are expected to be unique.

Use xa_insert() instead of xa_store() since it returns -EBUSY when the
index is already in use and log an error when that happens.

Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240108-ffa_fixes_6-8-v1-5-75bf7035bc50@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 2426021dbb58f..c613b57747cf6 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -1197,7 +1197,7 @@ void ffa_device_match_uuid(struct ffa_device *ffa_dev, const uuid_t *uuid)
 
 static void ffa_setup_partitions(void)
 {
-	int count, idx;
+	int count, idx, ret;
 	uuid_t uuid;
 	struct ffa_device *ffa_dev;
 	struct ffa_dev_part_info *info;
@@ -1236,7 +1236,14 @@ static void ffa_setup_partitions(void)
 			continue;
 		}
 		rwlock_init(&info->rw_lock);
-		xa_store(&drv_info->partition_info, tpbuf->id, info, GFP_KERNEL);
+		ret = xa_insert(&drv_info->partition_info, tpbuf->id,
+				info, GFP_KERNEL);
+		if (ret) {
+			pr_err("%s: failed to save partition ID 0x%x - ret:%d\n",
+			       __func__, tpbuf->id, ret);
+			ffa_device_unregister(ffa_dev);
+			kfree(info);
+		}
 	}
 
 	kfree(pbuf);
@@ -1246,7 +1253,13 @@ static void ffa_setup_partitions(void)
 	if (!info)
 		return;
 	rwlock_init(&info->rw_lock);
-	xa_store(&drv_info->partition_info, drv_info->vm_id, info, GFP_KERNEL);
+	ret = xa_insert(&drv_info->partition_info, drv_info->vm_id,
+			info, GFP_KERNEL);
+	if (ret) {
+		pr_err("%s: failed to save Host partition ID 0x%x - ret:%d. Abort.\n",
+		       __func__, drv_info->vm_id, ret);
+		kfree(info);
+	}
 }
 
 static void ffa_partitions_cleanup(void)
-- 
GitLab


From 0c565d16b80074e57e3e56240d13fc6cd6ed0334 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 8 Jan 2024 12:34:16 +0000
Subject: [PATCH 3164/4076] firmware: arm_ffa: Handle partitions setup failures

Make ffa_setup_partitions() fail, cleanup and return an error when the Host
partition setup fails: in such a case ffa_init() itself will fail.

Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20240108-ffa_fixes_6-8-v1-6-75bf7035bc50@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index c613b57747cf6..f2556a8e94015 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -112,6 +112,7 @@ struct ffa_drv_info {
 };
 
 static struct ffa_drv_info *drv_info;
+static void ffa_partitions_cleanup(void);
 
 /*
  * The driver must be able to support all the versions from the earliest
@@ -1195,7 +1196,7 @@ void ffa_device_match_uuid(struct ffa_device *ffa_dev, const uuid_t *uuid)
 	kfree(pbuf);
 }
 
-static void ffa_setup_partitions(void)
+static int ffa_setup_partitions(void)
 {
 	int count, idx, ret;
 	uuid_t uuid;
@@ -1206,7 +1207,7 @@ static void ffa_setup_partitions(void)
 	count = ffa_partition_probe(&uuid_null, &pbuf);
 	if (count <= 0) {
 		pr_info("%s: No partitions found, error %d\n", __func__, count);
-		return;
+		return -EINVAL;
 	}
 
 	xa_init(&drv_info->partition_info);
@@ -1250,8 +1251,14 @@ static void ffa_setup_partitions(void)
 
 	/* Allocate for the host */
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return;
+	if (!info) {
+		pr_err("%s: failed to alloc Host partition ID 0x%x. Abort.\n",
+		       __func__, drv_info->vm_id);
+		/* Already registered devices are freed on bus_exit */
+		ffa_partitions_cleanup();
+		return -ENOMEM;
+	}
+
 	rwlock_init(&info->rw_lock);
 	ret = xa_insert(&drv_info->partition_info, drv_info->vm_id,
 			info, GFP_KERNEL);
@@ -1259,7 +1266,11 @@ static void ffa_setup_partitions(void)
 		pr_err("%s: failed to save Host partition ID 0x%x - ret:%d. Abort.\n",
 		       __func__, drv_info->vm_id, ret);
 		kfree(info);
+		/* Already registered devices are freed on bus_exit */
+		ffa_partitions_cleanup();
 	}
+
+	return ret;
 }
 
 static void ffa_partitions_cleanup(void)
@@ -1520,7 +1531,11 @@ static int __init ffa_init(void)
 
 	ffa_notifications_setup();
 
-	ffa_setup_partitions();
+	ret = ffa_setup_partitions();
+	if (ret) {
+		pr_err("failed to setup partitions\n");
+		goto cleanup_notifs;
+	}
 
 	ret = ffa_sched_recv_cb_update(drv_info->vm_id, ffa_self_notif_handle,
 				       drv_info, true);
@@ -1528,6 +1543,9 @@ static int __init ffa_init(void)
 		pr_info("Failed to register driver sched callback %d\n", ret);
 
 	return 0;
+
+cleanup_notifs:
+	ffa_notifications_cleanup();
 free_pages:
 	if (drv_info->tx_buffer)
 		free_pages_exact(drv_info->tx_buffer, RXTX_BUFFER_SIZE);
-- 
GitLab


From f134bd1ebc28d40010328e5b314e10575e3550e0 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Fri, 19 Jan 2024 14:32:16 +0100
Subject: [PATCH 3165/4076] MIPS: sgi-ip27: Fix missing prototypes

Fix missing prototypes by making not shared functions static and
adding others to ip27-common.h. Also drop ip27-hubio.c as it's
not used for a long time.

Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
---
 arch/mips/sgi-ip27/Makefile      |   2 +-
 arch/mips/sgi-ip27/ip27-berr.c   |   4 +-
 arch/mips/sgi-ip27/ip27-common.h |   2 +
 arch/mips/sgi-ip27/ip27-hubio.c  | 185 -------------------------------
 arch/mips/sgi-ip27/ip27-irq.c    |   2 +
 arch/mips/sgi-ip27/ip27-memory.c |   1 +
 arch/mips/sgi-ip27/ip27-nmi.c    |  25 ++---
 7 files changed, 17 insertions(+), 204 deletions(-)
 delete mode 100644 arch/mips/sgi-ip27/ip27-hubio.c

diff --git a/arch/mips/sgi-ip27/Makefile b/arch/mips/sgi-ip27/Makefile
index 27c14ede191eb..9877fcc512b15 100644
--- a/arch/mips/sgi-ip27/Makefile
+++ b/arch/mips/sgi-ip27/Makefile
@@ -5,7 +5,7 @@
 
 obj-y	:= ip27-berr.o ip27-irq.o ip27-init.o ip27-klconfig.o \
 	   ip27-klnuma.o ip27-memory.o ip27-nmi.o ip27-reset.o ip27-timer.o \
-	   ip27-hubio.o ip27-xtalk.o
+	   ip27-xtalk.o
 
 obj-$(CONFIG_EARLY_PRINTK)	+= ip27-console.o
 obj-$(CONFIG_SMP)		+= ip27-smp.o
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index 923a63a51cda3..9eb497cb5d525 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -22,6 +22,8 @@
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 
+#include "ip27-common.h"
+
 static void dump_hub_information(unsigned long errst0, unsigned long errst1)
 {
 	static char *err_type[2][8] = {
@@ -57,7 +59,7 @@ static void dump_hub_information(unsigned long errst0, unsigned long errst1)
 	       [st0.pi_stat0_fmt.s0_err_type] ? : "invalid");
 }
 
-int ip27_be_handler(struct pt_regs *regs, int is_fixup)
+static int ip27_be_handler(struct pt_regs *regs, int is_fixup)
 {
 	unsigned long errst0, errst1;
 	int data = regs->cp0_cause & 4;
diff --git a/arch/mips/sgi-ip27/ip27-common.h b/arch/mips/sgi-ip27/ip27-common.h
index ed008a08464c2..a0059fa139345 100644
--- a/arch/mips/sgi-ip27/ip27-common.h
+++ b/arch/mips/sgi-ip27/ip27-common.h
@@ -10,6 +10,7 @@ extern void hub_rt_clock_event_init(void);
 extern void hub_rtc_init(nasid_t nasid);
 extern void install_cpu_nmi_handler(int slice);
 extern void install_ipi(void);
+extern void ip27_be_init(void);
 extern void ip27_reboot_setup(void);
 extern const struct plat_smp_ops ip27_smp_ops;
 extern unsigned long node_getfirstfree(nasid_t nasid);
@@ -17,4 +18,5 @@ extern void per_cpu_init(void);
 extern void replicate_kernel_text(void);
 extern void setup_replication_mask(void);
 
+
 #endif /* __IP27_COMMON_H */
diff --git a/arch/mips/sgi-ip27/ip27-hubio.c b/arch/mips/sgi-ip27/ip27-hubio.c
deleted file mode 100644
index c57f0d8f32186..0000000000000
--- a/arch/mips/sgi-ip27/ip27-hubio.c
+++ /dev/null
@@ -1,185 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 1992-1997, 2000-2003 Silicon Graphics, Inc.
- * Copyright (C) 2004 Christoph Hellwig.
- *
- * Support functions for the HUB ASIC - mostly PIO mapping related.
- */
-
-#include <linux/bitops.h>
-#include <linux/string.h>
-#include <linux/mmzone.h>
-#include <asm/sn/addrs.h>
-#include <asm/sn/arch.h>
-#include <asm/sn/agent.h>
-#include <asm/sn/io.h>
-#include <asm/xtalk/xtalk.h>
-
-
-static int force_fire_and_forget = 1;
-
-/**
- * hub_pio_map	-  establish a HUB PIO mapping
- *
- * @nasid:	nasid to perform PIO mapping on
- * @widget:	widget ID to perform PIO mapping for
- * @xtalk_addr: xtalk_address that needs to be mapped
- * @size:	size of the PIO mapping
- *
- **/
-unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget,
-			  unsigned long xtalk_addr, size_t size)
-{
-	unsigned i;
-
-	/* use small-window mapping if possible */
-	if ((xtalk_addr % SWIN_SIZE) + size <= SWIN_SIZE)
-		return NODE_SWIN_BASE(nasid, widget) + (xtalk_addr % SWIN_SIZE);
-
-	if ((xtalk_addr % BWIN_SIZE) + size > BWIN_SIZE) {
-		printk(KERN_WARNING "PIO mapping at hub %d widget %d addr 0x%lx"
-				" too big (%ld)\n",
-				nasid, widget, xtalk_addr, size);
-		return 0;
-	}
-
-	xtalk_addr &= ~(BWIN_SIZE-1);
-	for (i = 0; i < HUB_NUM_BIG_WINDOW; i++) {
-		if (test_and_set_bit(i, hub_data(nasid)->h_bigwin_used))
-			continue;
-
-		/*
-		 * The code below does a PIO write to setup an ITTE entry.
-		 *
-		 * We need to prevent other CPUs from seeing our updated
-		 * memory shadow of the ITTE (in the piomap) until the ITTE
-		 * entry is actually set up; otherwise, another CPU might
-		 * attempt a PIO prematurely.
-		 *
-		 * Also, the only way we can know that an entry has been
-		 * received  by the hub and can be used by future PIO reads/
-		 * writes is by reading back the ITTE entry after writing it.
-		 *
-		 * For these two reasons, we PIO read back the ITTE entry
-		 * after we write it.
-		 */
-		IIO_ITTE_PUT(nasid, i, HUB_PIO_MAP_TO_MEM, widget, xtalk_addr);
-		__raw_readq(IIO_ITTE_GET(nasid, i));
-
-		return NODE_BWIN_BASE(nasid, widget) + (xtalk_addr % BWIN_SIZE);
-	}
-
-	printk(KERN_WARNING "unable to establish PIO mapping for at"
-			" hub %d widget %d addr 0x%lx\n",
-			nasid, widget, xtalk_addr);
-	return 0;
-}
-
-
-/*
- * hub_setup_prb(nasid, prbnum, credits, conveyor)
- *
- *	Put a PRB into fire-and-forget mode if conveyor isn't set.  Otherwise,
- *	put it into conveyor belt mode with the specified number of credits.
- */
-static void hub_setup_prb(nasid_t nasid, int prbnum, int credits)
-{
-	union iprb_u prb;
-	int prb_offset;
-
-	/*
-	 * Get the current register value.
-	 */
-	prb_offset = IIO_IOPRB(prbnum);
-	prb.iprb_regval = REMOTE_HUB_L(nasid, prb_offset);
-
-	/*
-	 * Clear out some fields.
-	 */
-	prb.iprb_ovflow = 1;
-	prb.iprb_bnakctr = 0;
-	prb.iprb_anakctr = 0;
-
-	/*
-	 * Enable or disable fire-and-forget mode.
-	 */
-	prb.iprb_ff = force_fire_and_forget ? 1 : 0;
-
-	/*
-	 * Set the appropriate number of PIO credits for the widget.
-	 */
-	prb.iprb_xtalkctr = credits;
-
-	/*
-	 * Store the new value to the register.
-	 */
-	REMOTE_HUB_S(nasid, prb_offset, prb.iprb_regval);
-}
-
-/**
- * hub_set_piomode  -  set pio mode for a given hub
- *
- * @nasid:	physical node ID for the hub in question
- *
- * Put the hub into either "PIO conveyor belt" mode or "fire-and-forget" mode.
- * To do this, we have to make absolutely sure that no PIOs are in progress
- * so we turn off access to all widgets for the duration of the function.
- *
- * XXX - This code should really check what kind of widget we're talking
- * to.	Bridges can only handle three requests, but XG will do more.
- * How many can crossbow handle to widget 0?  We're assuming 1.
- *
- * XXX - There is a bug in the crossbow that link reset PIOs do not
- * return write responses.  The easiest solution to this problem is to
- * leave widget 0 (xbow) in fire-and-forget mode at all times.	This
- * only affects pio's to xbow registers, which should be rare.
- **/
-static void hub_set_piomode(nasid_t nasid)
-{
-	u64 ii_iowa;
-	union hubii_wcr_u ii_wcr;
-	unsigned i;
-
-	ii_iowa = REMOTE_HUB_L(nasid, IIO_OUTWIDGET_ACCESS);
-	REMOTE_HUB_S(nasid, IIO_OUTWIDGET_ACCESS, 0);
-
-	ii_wcr.wcr_reg_value = REMOTE_HUB_L(nasid, IIO_WCR);
-
-	if (ii_wcr.iwcr_dir_con) {
-		/*
-		 * Assume a bridge here.
-		 */
-		hub_setup_prb(nasid, 0, 3);
-	} else {
-		/*
-		 * Assume a crossbow here.
-		 */
-		hub_setup_prb(nasid, 0, 1);
-	}
-
-	/*
-	 * XXX - Here's where we should take the widget type into
-	 * when account assigning credits.
-	 */
-	for (i = HUB_WIDGET_ID_MIN; i <= HUB_WIDGET_ID_MAX; i++)
-		hub_setup_prb(nasid, i, 3);
-
-	REMOTE_HUB_S(nasid, IIO_OUTWIDGET_ACCESS, ii_iowa);
-}
-
-/*
- * hub_pio_init	 -  PIO-related hub initialization
- *
- * @hub:	hubinfo structure for our hub
- */
-void hub_pio_init(nasid_t nasid)
-{
-	unsigned i;
-
-	/* initialize big window piomaps for this hub */
-	bitmap_zero(hub_data(nasid)->h_bigwin_used, HUB_NUM_BIG_WINDOW);
-	for (i = 0; i < HUB_NUM_BIG_WINDOW; i++)
-		IIO_ITTE_DISABLE(nasid, i);
-
-	hub_set_piomode(nasid);
-}
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index a0dd3bd2b81b3..8f5299b269e7e 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -23,6 +23,8 @@
 #include <asm/sn/intr.h>
 #include <asm/sn/irq_alloc.h>
 
+#include "ip27-common.h"
+
 struct hub_irq_data {
 	u64	*irq_mask[2];
 	cpuid_t	cpu;
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index f79c483937166..b8ca94cfb4fef 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -23,6 +23,7 @@
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
+#include <asm/sgialib.h>
 
 #include <asm/sn/arch.h>
 #include <asm/sn/agent.h>
diff --git a/arch/mips/sgi-ip27/ip27-nmi.c b/arch/mips/sgi-ip27/ip27-nmi.c
index 84889b57d5ff6..fc2816398d0cf 100644
--- a/arch/mips/sgi-ip27/ip27-nmi.c
+++ b/arch/mips/sgi-ip27/ip27-nmi.c
@@ -11,6 +11,8 @@
 #include <asm/sn/arch.h>
 #include <asm/sn/agent.h>
 
+#include "ip27-common.h"
+
 #if 0
 #define NODE_NUM_CPUS(n)	CNODE_NUM_CPUS(n)
 #else
@@ -23,16 +25,7 @@
 typedef unsigned long machreg_t;
 
 static arch_spinlock_t nmi_lock = __ARCH_SPIN_LOCK_UNLOCKED;
-
-/*
- * Let's see what else we need to do here. Set up sp, gp?
- */
-void nmi_dump(void)
-{
-	void cont_nmi_dump(void);
-
-	cont_nmi_dump();
-}
+static void nmi_dump(void);
 
 void install_cpu_nmi_handler(int slice)
 {
@@ -53,7 +46,7 @@ void install_cpu_nmi_handler(int slice)
  * into the eframe format for the node under consideration.
  */
 
-void nmi_cpu_eframe_save(nasid_t nasid, int slice)
+static void nmi_cpu_eframe_save(nasid_t nasid, int slice)
 {
 	struct reg_struct *nr;
 	int		i;
@@ -129,7 +122,7 @@ void nmi_cpu_eframe_save(nasid_t nasid, int slice)
 	pr_emerg("\n");
 }
 
-void nmi_dump_hub_irq(nasid_t nasid, int slice)
+static void nmi_dump_hub_irq(nasid_t nasid, int slice)
 {
 	u64 mask0, mask1, pend0, pend1;
 
@@ -153,7 +146,7 @@ void nmi_dump_hub_irq(nasid_t nasid, int slice)
  * Copy the cpu registers which have been saved in the IP27prom format
  * into the eframe format for the node under consideration.
  */
-void nmi_node_eframe_save(nasid_t nasid)
+static void nmi_node_eframe_save(nasid_t nasid)
 {
 	int slice;
 
@@ -170,8 +163,7 @@ void nmi_node_eframe_save(nasid_t nasid)
 /*
  * Save the nmi cpu registers for all cpus in the system.
  */
-void
-nmi_eframes_save(void)
+static void nmi_eframes_save(void)
 {
 	nasid_t nasid;
 
@@ -179,8 +171,7 @@ nmi_eframes_save(void)
 		nmi_node_eframe_save(nasid);
 }
 
-void
-cont_nmi_dump(void)
+static void nmi_dump(void)
 {
 #ifndef REAL_NMI_SIGNAL
 	static atomic_t nmied_cpus = ATOMIC_INIT(0);
-- 
GitLab


From e3a4f1b7ada8360c1838ac3aad9837749a698c7a Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Fri, 19 Jan 2024 14:36:34 +0100
Subject: [PATCH 3166/4076] MIPS: fw arc: Fix missing prototypes

Make ArcGetMemoryDescriptor() static since it's only needed internally.

Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
---
 arch/mips/fw/arc/memory.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c
index 66188739f54d2..fb78e6fd5de48 100644
--- a/arch/mips/fw/arc/memory.c
+++ b/arch/mips/fw/arc/memory.c
@@ -37,7 +37,7 @@ static unsigned int nr_prom_mem __initdata;
  */
 #define ARC_PAGE_SHIFT	12
 
-struct linux_mdesc * __init ArcGetMemoryDescriptor(struct linux_mdesc *Current)
+static struct linux_mdesc * __init ArcGetMemoryDescriptor(struct linux_mdesc *Current)
 {
 	return (struct linux_mdesc *) ARC_CALL1(get_mdesc, Current);
 }
-- 
GitLab


From ab58a2f319de945f631150a190653a90e307df8e Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Fri, 19 Jan 2024 14:37:57 +0100
Subject: [PATCH 3167/4076] MIPS: sgi-ip30: Fix missing prototypes

Include needed header files.

Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
---
 arch/mips/sgi-ip30/ip30-console.c | 1 +
 arch/mips/sgi-ip30/ip30-setup.c   | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/mips/sgi-ip30/ip30-console.c b/arch/mips/sgi-ip30/ip30-console.c
index b91f8c4fdc786..7c6dcf6e73f70 100644
--- a/arch/mips/sgi-ip30/ip30-console.c
+++ b/arch/mips/sgi-ip30/ip30-console.c
@@ -3,6 +3,7 @@
 #include <linux/io.h>
 
 #include <asm/sn/ioc3.h>
+#include <asm/setup.h>
 
 static inline struct ioc3_uartregs *console_uart(void)
 {
diff --git a/arch/mips/sgi-ip30/ip30-setup.c b/arch/mips/sgi-ip30/ip30-setup.c
index 75a34684e7045..e8547636a7482 100644
--- a/arch/mips/sgi-ip30/ip30-setup.c
+++ b/arch/mips/sgi-ip30/ip30-setup.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/memblock.h>
 
+#include <asm/bootinfo.h>
 #include <asm/smp-ops.h>
 #include <asm/sgialib.h>
 #include <asm/time.h>
-- 
GitLab


From f64fdde9bc771d7d790e8bcc30a7e03bbe0b1a9f Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Fri, 19 Jan 2024 14:52:51 +0100
Subject: [PATCH 3168/4076] MIPS: sgi-ip32: Fix missing prototypes

Fix interrupt function prototypes, move all prototypes into a new
file ip32-common.h and include it where needed.

Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
---
 arch/mips/sgi-ip32/crime.c       |  6 ++++--
 arch/mips/sgi-ip32/ip32-berr.c   |  2 ++
 arch/mips/sgi-ip32/ip32-common.h | 15 +++++++++++++++
 arch/mips/sgi-ip32/ip32-irq.c    |  6 ++----
 arch/mips/sgi-ip32/ip32-memory.c |  1 +
 arch/mips/sgi-ip32/ip32-reset.c  |  2 ++
 arch/mips/sgi-ip32/ip32-setup.c  |  3 +--
 7 files changed, 27 insertions(+), 8 deletions(-)
 create mode 100644 arch/mips/sgi-ip32/ip32-common.h

diff --git a/arch/mips/sgi-ip32/crime.c b/arch/mips/sgi-ip32/crime.c
index a8e0c776ca6c6..b8a0e4cfa9ce8 100644
--- a/arch/mips/sgi-ip32/crime.c
+++ b/arch/mips/sgi-ip32/crime.c
@@ -18,6 +18,8 @@
 #include <asm/ip32/crime.h>
 #include <asm/ip32/mace.h>
 
+#include "ip32-common.h"
+
 struct sgi_crime __iomem *crime;
 struct sgi_mace __iomem *mace;
 
@@ -39,7 +41,7 @@ void __init crime_init(void)
 	       id, rev, field, (unsigned long) CRIME_BASE);
 }
 
-irqreturn_t crime_memerr_intr(unsigned int irq, void *dev_id)
+irqreturn_t crime_memerr_intr(int irq, void *dev_id)
 {
 	unsigned long stat, addr;
 	int fatal = 0;
@@ -90,7 +92,7 @@ irqreturn_t crime_memerr_intr(unsigned int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-irqreturn_t crime_cpuerr_intr(unsigned int irq, void *dev_id)
+irqreturn_t crime_cpuerr_intr(int irq, void *dev_id)
 {
 	unsigned long stat = crime->cpu_error_stat & CRIME_CPU_ERROR_MASK;
 	unsigned long addr = crime->cpu_error_addr & CRIME_CPU_ERROR_ADDR_MASK;
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index 478b63b4c808f..7cbc27941f928 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -18,6 +18,8 @@
 #include <asm/ptrace.h>
 #include <asm/tlbdebug.h>
 
+#include "ip32-common.h"
+
 static int ip32_be_handler(struct pt_regs *regs, int is_fixup)
 {
 	int data = regs->cp0_cause & 4;
diff --git a/arch/mips/sgi-ip32/ip32-common.h b/arch/mips/sgi-ip32/ip32-common.h
new file mode 100644
index 0000000000000..cfc0225b14193
--- /dev/null
+++ b/arch/mips/sgi-ip32/ip32-common.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __IP32_COMMON_H
+#define __IP32_COMMON_H
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+
+void __init crime_init(void);
+irqreturn_t crime_memerr_intr(int irq, void *dev_id);
+irqreturn_t crime_cpuerr_intr(int irq, void *dev_id);
+void __init ip32_be_init(void);
+void ip32_prepare_poweroff(void);
+
+#endif /* __IP32_COMMON_H */
diff --git a/arch/mips/sgi-ip32/ip32-irq.c b/arch/mips/sgi-ip32/ip32-irq.c
index e21ea1de05e31..29d04468a06b8 100644
--- a/arch/mips/sgi-ip32/ip32-irq.c
+++ b/arch/mips/sgi-ip32/ip32-irq.c
@@ -28,6 +28,8 @@
 #include <asm/ip32/mace.h>
 #include <asm/ip32/ip32_ints.h>
 
+#include "ip32-common.h"
+
 /* issue a PIO read to make sure no PIO writes are pending */
 static inline void flush_crime_bus(void)
 {
@@ -107,10 +109,6 @@ static inline void flush_mace_bus(void)
  * is quite different anyway.
  */
 
-/* Some initial interrupts to set up */
-extern irqreturn_t crime_memerr_intr(int irq, void *dev_id);
-extern irqreturn_t crime_cpuerr_intr(int irq, void *dev_id);
-
 /*
  * This is for pure CRIME interrupts - ie not MACE.  The advantage?
  * We get to split the register in half and do faster lookups.
diff --git a/arch/mips/sgi-ip32/ip32-memory.c b/arch/mips/sgi-ip32/ip32-memory.c
index 3fc8d0a0bdfa4..5fee33744f674 100644
--- a/arch/mips/sgi-ip32/ip32-memory.c
+++ b/arch/mips/sgi-ip32/ip32-memory.c
@@ -15,6 +15,7 @@
 #include <asm/ip32/crime.h>
 #include <asm/bootinfo.h>
 #include <asm/page.h>
+#include <asm/sgialib.h>
 
 extern void crime_init(void);
 
diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c
index 18d1c115cd534..6bdc1421cda46 100644
--- a/arch/mips/sgi-ip32/ip32-reset.c
+++ b/arch/mips/sgi-ip32/ip32-reset.c
@@ -29,6 +29,8 @@
 #include <asm/ip32/crime.h>
 #include <asm/ip32/ip32_ints.h>
 
+#include "ip32-common.h"
+
 #define POWERDOWN_TIMEOUT	120
 /*
  * Blink frequency during reboot grace period and when panicked.
diff --git a/arch/mips/sgi-ip32/ip32-setup.c b/arch/mips/sgi-ip32/ip32-setup.c
index 8019dae1721a8..aeb0805aae57b 100644
--- a/arch/mips/sgi-ip32/ip32-setup.c
+++ b/arch/mips/sgi-ip32/ip32-setup.c
@@ -26,8 +26,7 @@
 #include <asm/ip32/mace.h>
 #include <asm/ip32/ip32_ints.h>
 
-extern void ip32_be_init(void);
-extern void crime_init(void);
+#include "ip32-common.h"
 
 #ifdef CONFIG_SGI_O2MACE_ETH
 /*
-- 
GitLab


From e4cec073b7755a78030f30cf627141c759035b50 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 20 Jan 2024 23:00:21 -0800
Subject: [PATCH 3169/4076] dmaengine: at_hdmac: fix some kernel-doc warnings

Fix some kernel-doc format warnings:

at_hdmac.c:243: warning: Excess struct member 'sg_len' description in 'at_desc'
at_hdmac.c:252: warning: cannot understand function prototype: 'enum atc_status '
ez
at_hdmac.c:351: warning: Excess struct member 'atdma_devtype' description in 'at_dma'
at_hdmac.c:351: warning: Excess struct member 'ch_regs' description in 'at_dma'
at_hdmac.c:664: warning: contents before sections

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Ludovic Desroches <ludovic.desroches@microchip.com>
Cc: Tudor Ambarus <tudor.ambarus@linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Vinod Koul <vkoul@kernel.org>
Cc: dmaengine@vger.kernel.org
Link: https://lore.kernel.org/r/20240121070021.25365-1-rdunlap@infradead.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/at_hdmac.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index fb89ecbf0cc5b..6bad536e04924 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -222,7 +222,7 @@ struct atdma_sg {
  * @vd: pointer to the virtual dma descriptor.
  * @atchan: pointer to the atmel dma channel.
  * @total_len: total transaction byte count
- * @sg_len: number of sg entries.
+ * @sglen: number of sg entries.
  * @sg: array of sgs.
  */
 struct at_desc {
@@ -245,7 +245,7 @@ struct at_desc {
 /*--  Channels  --------------------------------------------------------*/
 
 /**
- * atc_status - information bits stored in channel status flag
+ * enum atc_status - information bits stored in channel status flag
  *
  * Manipulated with atomic operations.
  */
@@ -328,8 +328,7 @@ static inline u8 convert_buswidth(enum dma_slave_buswidth addr_width)
 /**
  * struct at_dma - internal representation of an Atmel HDMA Controller
  * @dma_device: dmaengine dma_device object members
- * @atdma_devtype: identifier of DMA controller compatibility
- * @ch_regs: memory mapped register base
+ * @regs: memory mapped register base
  * @clk: dma controller clock
  * @save_imr: interrupt mask register that is saved on suspend/resume cycle
  * @all_chan_mask: all channels availlable in a mask
@@ -626,6 +625,9 @@ static inline u32 atc_calc_bytes_left(u32 current_len, u32 ctrla)
 
 /**
  * atc_get_llis_residue - Get residue for a hardware linked list transfer
+ * @atchan: pointer to an atmel hdmac channel.
+ * @desc: pointer to the descriptor for which the residue is calculated.
+ * @residue: residue to be set to dma_tx_state.
  *
  * Calculate the residue by removing the length of the Linked List Item (LLI)
  * already transferred from the total length. To get the current LLI we can use
@@ -661,10 +663,8 @@ static inline u32 atc_calc_bytes_left(u32 current_len, u32 ctrla)
  * two DSCR values are different, we read again the CTRLA then the DSCR till two
  * consecutive read values from DSCR are equal or till the maximum trials is
  * reach. This algorithm is very unlikely not to find a stable value for DSCR.
- * @atchan: pointer to an atmel hdmac channel.
- * @desc: pointer to the descriptor for which the residue is calculated.
- * @residue: residue to be set to dma_tx_state.
- * Returns 0 on success, -errno otherwise.
+ *
+ * Returns: %0 on success, -errno otherwise.
  */
 static int atc_get_llis_residue(struct at_dma_chan *atchan,
 				struct at_desc *desc, u32 *residue)
@@ -731,7 +731,8 @@ static int atc_get_llis_residue(struct at_dma_chan *atchan,
  * @chan: DMA channel
  * @cookie: transaction identifier to check status of
  * @residue: residue to be updated.
- * Return 0 on success, -errono otherwise.
+ *
+ * Return: %0 on success, -errno otherwise.
  */
 static int atc_get_residue(struct dma_chan *chan, dma_cookie_t cookie,
 			   u32 *residue)
@@ -1710,7 +1711,7 @@ static void atc_issue_pending(struct dma_chan *chan)
  * atc_alloc_chan_resources - allocate resources for DMA channel
  * @chan: allocate descriptor resources for this channel
  *
- * return - the number of allocated descriptors
+ * Return: the number of allocated descriptors
  */
 static int atc_alloc_chan_resources(struct dma_chan *chan)
 {
-- 
GitLab


From 6ba7843b59b77360812617d071313c7f35f3757a Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 3 Jan 2024 20:27:04 +0100
Subject: [PATCH 3170/4076] platform/x86: wmi: Fix error handling in legacy WMI
 notify handler functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When wmi_install_notify_handler()/wmi_remove_notify_handler() are
unable to enable/disable the WMI device, they unconditionally return
an error to the caller.
When registering legacy WMI notify handlers, this means that the
callback remains registered despite wmi_install_notify_handler()
having returned an error.
When removing legacy WMI notify handlers, this means that the
callback is removed despite wmi_remove_notify_handler() having
returned an error.

Fix this by only warning when the WMI device could not be enabled.
This behaviour matches the bus-based WMI interface.

Tested on a Dell Inspiron 3505 and a Acer Aspire E1-731.

Fixes: 58f6425eb92f ("WMI: Cater for multiple events with same GUID")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240103192707.115512-2-W_Armin@gmx.de
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/wmi.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index bd271a5730aa5..23b4043c0fe77 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -593,9 +593,10 @@ acpi_status wmi_install_notify_handler(const char *guid,
 			block->handler_data = data;
 
 			wmi_status = wmi_method_enable(block, true);
-			if ((wmi_status != AE_OK) ||
-			    ((wmi_status == AE_OK) && (status == AE_NOT_EXIST)))
-				status = wmi_status;
+			if (ACPI_FAILURE(wmi_status))
+				dev_warn(&block->dev.dev, "Failed to enable device\n");
+
+			status = AE_OK;
 		}
 	}
 
@@ -631,10 +632,13 @@ acpi_status wmi_remove_notify_handler(const char *guid)
 				return AE_NULL_ENTRY;
 
 			wmi_status = wmi_method_enable(block, false);
+			if (ACPI_FAILURE(wmi_status))
+				dev_warn(&block->dev.dev, "Failed to disable device\n");
+
 			block->handler = NULL;
 			block->handler_data = NULL;
-			if (wmi_status != AE_OK || (wmi_status == AE_OK && status == AE_NOT_EXIST))
-				status = wmi_status;
+
+			status = AE_OK;
 		}
 	}
 
-- 
GitLab


From 3d8a29fec2cb96b3aa75a595f20c4b73ff294a97 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 3 Jan 2024 20:27:05 +0100
Subject: [PATCH 3171/4076] platform/x86: wmi: Return immediately if an
 suitable WMI event is found
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 58f6425eb92f ("WMI: Cater for multiple events with same GUID")
allowed legacy WMI notify handlers to be installed for multiple WMI
devices with the same GUID.
However this is useless since the legacy GUID-based interface is
blacklisted from seeing WMI devices with duplicated GUIDs.

Return immediately if a suitable WMI event is found in
wmi_install/remove_notify_handler() since searching for other suitable
events is pointless.

Tested on a Dell Inspiron 3505 and a Acer Aspire E1-731.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240103192707.115512-3-W_Armin@gmx.de
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/wmi.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 23b4043c0fe77..4e2d0e15b1559 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -573,7 +573,6 @@ acpi_status wmi_install_notify_handler(const char *guid,
 				       void *data)
 {
 	struct wmi_block *block;
-	acpi_status status = AE_NOT_EXIST;
 	guid_t guid_input;
 
 	if (!guid || !handler)
@@ -596,11 +595,11 @@ acpi_status wmi_install_notify_handler(const char *guid,
 			if (ACPI_FAILURE(wmi_status))
 				dev_warn(&block->dev.dev, "Failed to enable device\n");
 
-			status = AE_OK;
+			return AE_OK;
 		}
 	}
 
-	return status;
+	return AE_NOT_EXIST;
 }
 EXPORT_SYMBOL_GPL(wmi_install_notify_handler);
 
@@ -615,7 +614,6 @@ EXPORT_SYMBOL_GPL(wmi_install_notify_handler);
 acpi_status wmi_remove_notify_handler(const char *guid)
 {
 	struct wmi_block *block;
-	acpi_status status = AE_NOT_EXIST;
 	guid_t guid_input;
 
 	if (!guid)
@@ -638,11 +636,11 @@ acpi_status wmi_remove_notify_handler(const char *guid)
 			block->handler = NULL;
 			block->handler_data = NULL;
 
-			status = AE_OK;
+			return AE_OK;
 		}
 	}
 
-	return status;
+	return AE_NOT_EXIST;
 }
 EXPORT_SYMBOL_GPL(wmi_remove_notify_handler);
 
-- 
GitLab


From 3ea7f59af8ffa17ce5f5173d6f4bfbc73334187d Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 3 Jan 2024 20:27:06 +0100
Subject: [PATCH 3172/4076] platform/x86: wmi: Decouple legacy WMI notify
 handlers from wmi_block_list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Until now, legacy WMI notify handler functions where using the
wmi_block_list, which did no refcounting on the returned WMI device.
This meant that the WMI device could disappear at any moment,
potentially leading to various errors.
Fix this by using bus_find_device() which returns an actual
reference to the found WMI device.

Tested on a Dell Inspiron 3505 and a Acer Aspire E1-731.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240103192707.115512-4-W_Armin@gmx.de
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/wmi.c | 118 +++++++++++++++++++++----------------
 1 file changed, 68 insertions(+), 50 deletions(-)

diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 4e2d0e15b1559..699157ce347ce 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -219,6 +219,17 @@ static int wmidev_match_guid(struct device *dev, const void *data)
 	return 0;
 }
 
+static int wmidev_match_notify_id(struct device *dev, const void *data)
+{
+	struct wmi_block *wblock = dev_to_wblock(dev);
+	const u32 *notify_id = data;
+
+	if (wblock->gblock.flags & ACPI_WMI_EVENT && wblock->gblock.notify_id == *notify_id)
+		return 1;
+
+	return 0;
+}
+
 static struct bus_type wmi_bus_type;
 
 static struct wmi_device *wmi_find_device_by_guid(const char *guid_string)
@@ -238,6 +249,17 @@ static struct wmi_device *wmi_find_device_by_guid(const char *guid_string)
 	return dev_to_wdev(dev);
 }
 
+static struct wmi_device *wmi_find_event_by_notify_id(const u32 notify_id)
+{
+	struct device *dev;
+
+	dev = bus_find_device(&wmi_bus_type, NULL, &notify_id, wmidev_match_notify_id);
+	if (!dev)
+		return ERR_PTR(-ENODEV);
+
+	return to_wmi_device(dev);
+}
+
 static void wmi_device_put(struct wmi_device *wdev)
 {
 	put_device(&wdev->dev);
@@ -572,34 +594,30 @@ acpi_status wmi_install_notify_handler(const char *guid,
 				       wmi_notify_handler handler,
 				       void *data)
 {
-	struct wmi_block *block;
-	guid_t guid_input;
-
-	if (!guid || !handler)
-		return AE_BAD_PARAMETER;
-
-	if (guid_parse(guid, &guid_input))
-		return AE_BAD_PARAMETER;
-
-	list_for_each_entry(block, &wmi_block_list, list) {
-		acpi_status wmi_status;
+	struct wmi_block *wblock;
+	struct wmi_device *wdev;
+	acpi_status status;
 
-		if (guid_equal(&block->gblock.guid, &guid_input)) {
-			if (block->handler)
-				return AE_ALREADY_ACQUIRED;
+	wdev = wmi_find_device_by_guid(guid);
+	if (IS_ERR(wdev))
+		return AE_ERROR;
 
-			block->handler = handler;
-			block->handler_data = data;
+	wblock = container_of(wdev, struct wmi_block, dev);
+	if (wblock->handler) {
+		status = AE_ALREADY_ACQUIRED;
+	} else {
+		wblock->handler = handler;
+		wblock->handler_data = data;
 
-			wmi_status = wmi_method_enable(block, true);
-			if (ACPI_FAILURE(wmi_status))
-				dev_warn(&block->dev.dev, "Failed to enable device\n");
+		if (ACPI_FAILURE(wmi_method_enable(wblock, true)))
+			dev_warn(&wblock->dev.dev, "Failed to enable device\n");
 
-			return AE_OK;
-		}
+		status = AE_OK;
 	}
 
-	return AE_NOT_EXIST;
+	wmi_device_put(wdev);
+
+	return status;
 }
 EXPORT_SYMBOL_GPL(wmi_install_notify_handler);
 
@@ -613,34 +631,30 @@ EXPORT_SYMBOL_GPL(wmi_install_notify_handler);
  */
 acpi_status wmi_remove_notify_handler(const char *guid)
 {
-	struct wmi_block *block;
-	guid_t guid_input;
-
-	if (!guid)
-		return AE_BAD_PARAMETER;
-
-	if (guid_parse(guid, &guid_input))
-		return AE_BAD_PARAMETER;
-
-	list_for_each_entry(block, &wmi_block_list, list) {
-		acpi_status wmi_status;
+	struct wmi_block *wblock;
+	struct wmi_device *wdev;
+	acpi_status status;
 
-		if (guid_equal(&block->gblock.guid, &guid_input)) {
-			if (!block->handler)
-				return AE_NULL_ENTRY;
+	wdev = wmi_find_device_by_guid(guid);
+	if (IS_ERR(wdev))
+		return AE_ERROR;
 
-			wmi_status = wmi_method_enable(block, false);
-			if (ACPI_FAILURE(wmi_status))
-				dev_warn(&block->dev.dev, "Failed to disable device\n");
+	wblock = container_of(wdev, struct wmi_block, dev);
+	if (!wblock->handler) {
+		status = AE_NULL_ENTRY;
+	} else {
+		if (ACPI_FAILURE(wmi_method_enable(wblock, false)))
+			dev_warn(&wblock->dev.dev, "Failed to disable device\n");
 
-			block->handler = NULL;
-			block->handler_data = NULL;
+		wblock->handler = NULL;
+		wblock->handler_data = NULL;
 
-			return AE_OK;
-		}
+		status = AE_OK;
 	}
 
-	return AE_NOT_EXIST;
+	wmi_device_put(wdev);
+
+	return status;
 }
 EXPORT_SYMBOL_GPL(wmi_remove_notify_handler);
 
@@ -657,15 +671,19 @@ EXPORT_SYMBOL_GPL(wmi_remove_notify_handler);
 acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out)
 {
 	struct wmi_block *wblock;
+	struct wmi_device *wdev;
+	acpi_status status;
 
-	list_for_each_entry(wblock, &wmi_block_list, list) {
-		struct guid_block *gblock = &wblock->gblock;
+	wdev = wmi_find_event_by_notify_id(event);
+	if (IS_ERR(wdev))
+		return AE_NOT_FOUND;
 
-		if ((gblock->flags & ACPI_WMI_EVENT) && gblock->notify_id == event)
-			return get_event_data(wblock, out);
-	}
+	wblock = container_of(wdev, struct wmi_block, dev);
+	status = get_event_data(wblock, out);
 
-	return AE_NOT_FOUND;
+	wmi_device_put(wdev);
+
+	return status;
 }
 EXPORT_SYMBOL_GPL(wmi_get_event_data);
 
-- 
GitLab


From 29e473f4b51ee56b5808323e274a8369b4d181cb Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 3 Jan 2024 20:27:07 +0100
Subject: [PATCH 3173/4076] platform/x86: wmi: Fix notify callback locking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When an legacy WMI event handler is removed, an WMI event could
have called the handler just before it was removed, meaning the
handler could still be running after wmi_remove_notify_handler()
returns.
Something similar could also happens when using the WMI bus, as
the WMI core might still call the notify() callback from an WMI
driver even if its remove() callback was just called.

Fix this by introducing a rw semaphore which ensures that the
event state of a WMI device does not change while the WMI core
is handling an event for it.

Tested on a Dell Inspiron 3505 and a Acer Aspire E1-731.

Fixes: 1686f5444546 ("platform/x86: wmi: Incorporate acpi_install_notify_handler")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240103192707.115512-5-W_Armin@gmx.de
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/wmi.c | 71 +++++++++++++++++++++++++-------------
 1 file changed, 47 insertions(+), 24 deletions(-)

diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 699157ce347ce..d1df1a31de008 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -25,6 +25,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/rwsem.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
@@ -56,7 +57,6 @@ static_assert(__alignof__(struct guid_block) == 1);
 
 enum {	/* wmi_block flags */
 	WMI_READ_TAKES_NO_ARGS,
-	WMI_PROBED,
 };
 
 struct wmi_block {
@@ -64,8 +64,10 @@ struct wmi_block {
 	struct list_head list;
 	struct guid_block gblock;
 	struct acpi_device *acpi_device;
+	struct rw_semaphore notify_lock;	/* Protects notify callback add/remove */
 	wmi_notify_handler handler;
 	void *handler_data;
+	bool driver_ready;
 	unsigned long flags;
 };
 
@@ -603,6 +605,8 @@ acpi_status wmi_install_notify_handler(const char *guid,
 		return AE_ERROR;
 
 	wblock = container_of(wdev, struct wmi_block, dev);
+
+	down_write(&wblock->notify_lock);
 	if (wblock->handler) {
 		status = AE_ALREADY_ACQUIRED;
 	} else {
@@ -614,6 +618,7 @@ acpi_status wmi_install_notify_handler(const char *guid,
 
 		status = AE_OK;
 	}
+	up_write(&wblock->notify_lock);
 
 	wmi_device_put(wdev);
 
@@ -640,6 +645,8 @@ acpi_status wmi_remove_notify_handler(const char *guid)
 		return AE_ERROR;
 
 	wblock = container_of(wdev, struct wmi_block, dev);
+
+	down_write(&wblock->notify_lock);
 	if (!wblock->handler) {
 		status = AE_NULL_ENTRY;
 	} else {
@@ -651,6 +658,7 @@ acpi_status wmi_remove_notify_handler(const char *guid)
 
 		status = AE_OK;
 	}
+	up_write(&wblock->notify_lock);
 
 	wmi_device_put(wdev);
 
@@ -896,7 +904,9 @@ static int wmi_dev_probe(struct device *dev)
 		}
 	}
 
-	set_bit(WMI_PROBED, &wblock->flags);
+	down_write(&wblock->notify_lock);
+	wblock->driver_ready = true;
+	up_write(&wblock->notify_lock);
 
 	return 0;
 }
@@ -906,7 +916,9 @@ static void wmi_dev_remove(struct device *dev)
 	struct wmi_block *wblock = dev_to_wblock(dev);
 	struct wmi_driver *wdriver = drv_to_wdrv(dev->driver);
 
-	clear_bit(WMI_PROBED, &wblock->flags);
+	down_write(&wblock->notify_lock);
+	wblock->driver_ready = false;
+	up_write(&wblock->notify_lock);
 
 	if (wdriver->remove)
 		wdriver->remove(dev_to_wdev(dev));
@@ -1019,6 +1031,8 @@ static int wmi_create_device(struct device *wmi_bus_dev,
 		wblock->dev.setable = true;
 
  out_init:
+	init_rwsem(&wblock->notify_lock);
+	wblock->driver_ready = false;
 	wblock->dev.dev.bus = &wmi_bus_type;
 	wblock->dev.dev.parent = wmi_bus_dev;
 
@@ -1191,6 +1205,26 @@ acpi_wmi_ec_space_handler(u32 function, acpi_physical_address address,
 	}
 }
 
+static void wmi_notify_driver(struct wmi_block *wblock)
+{
+	struct wmi_driver *driver = drv_to_wdrv(wblock->dev.dev.driver);
+	struct acpi_buffer data = { ACPI_ALLOCATE_BUFFER, NULL };
+	acpi_status status;
+
+	if (!driver->no_notify_data) {
+		status = get_event_data(wblock, &data);
+		if (ACPI_FAILURE(status)) {
+			dev_warn(&wblock->dev.dev, "Failed to get event data\n");
+			return;
+		}
+	}
+
+	if (driver->notify)
+		driver->notify(&wblock->dev, data.pointer);
+
+	kfree(data.pointer);
+}
+
 static int wmi_notify_device(struct device *dev, void *data)
 {
 	struct wmi_block *wblock = dev_to_wblock(dev);
@@ -1199,28 +1233,17 @@ static int wmi_notify_device(struct device *dev, void *data)
 	if (!(wblock->gblock.flags & ACPI_WMI_EVENT && wblock->gblock.notify_id == *event))
 		return 0;
 
-	/* If a driver is bound, then notify the driver. */
-	if (test_bit(WMI_PROBED, &wblock->flags) && wblock->dev.dev.driver) {
-		struct wmi_driver *driver = drv_to_wdrv(wblock->dev.dev.driver);
-		struct acpi_buffer evdata = { ACPI_ALLOCATE_BUFFER, NULL };
-		acpi_status status;
-
-		if (!driver->no_notify_data) {
-			status = get_event_data(wblock, &evdata);
-			if (ACPI_FAILURE(status)) {
-				dev_warn(&wblock->dev.dev, "failed to get event data\n");
-				return -EIO;
-			}
-		}
-
-		if (driver->notify)
-			driver->notify(&wblock->dev, evdata.pointer);
-
-		kfree(evdata.pointer);
-	} else if (wblock->handler) {
-		/* Legacy handler */
-		wblock->handler(*event, wblock->handler_data);
+	down_read(&wblock->notify_lock);
+	/* The WMI driver notify handler conflicts with the legacy WMI handler.
+	 * Because of this the WMI driver notify handler takes precedence.
+	 */
+	if (wblock->dev.dev.driver && wblock->driver_ready) {
+		wmi_notify_driver(wblock);
+	} else {
+		if (wblock->handler)
+			wblock->handler(*event, wblock->handler_data);
 	}
+	up_read(&wblock->notify_lock);
 
 	acpi_bus_generate_netlink_event(wblock->acpi_device->pnp.device_class,
 					dev_name(&wblock->dev.dev), *event, 0);
-- 
GitLab


From b73e43dcd7a8be26880ef8ff336053b29e79dbc5 Mon Sep 17 00:00:00 2001
From: Guanhua Gao <guanhua.gao@nxp.com>
Date: Thu, 18 Jan 2024 11:29:16 -0500
Subject: [PATCH 3174/4076] dmaengine: fsl-dpaa2-qdma: Fix the size of dma
 pools

In case of long format of qDMA command descriptor, there are one frame
descriptor, three entries in the frame list and two data entries. So the
size of dma_pool_create for these three fields should be the same with
the total size of entries respectively, or the contents may be overwritten
by the next allocated descriptor.

Fixes: 7fdf9b05c73b ("dmaengine: fsl-dpaa2-qdma: Add NXP dpaa2 qDMA controller driver for Layerscape SoCs")
Signed-off-by: Guanhua Gao <guanhua.gao@nxp.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20240118162917.2951450-1-Frank.Li@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
index 7958ac33e36ce..5a8061a307cda 100644
--- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
+++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
@@ -38,15 +38,17 @@ static int dpaa2_qdma_alloc_chan_resources(struct dma_chan *chan)
 	if (!dpaa2_chan->fd_pool)
 		goto err;
 
-	dpaa2_chan->fl_pool = dma_pool_create("fl_pool", dev,
-					      sizeof(struct dpaa2_fl_entry),
-					      sizeof(struct dpaa2_fl_entry), 0);
+	dpaa2_chan->fl_pool =
+		dma_pool_create("fl_pool", dev,
+				 sizeof(struct dpaa2_fl_entry) * 3,
+				 sizeof(struct dpaa2_fl_entry), 0);
+
 	if (!dpaa2_chan->fl_pool)
 		goto err_fd;
 
 	dpaa2_chan->sdd_pool =
 		dma_pool_create("sdd_pool", dev,
-				sizeof(struct dpaa2_qdma_sd_d),
+				sizeof(struct dpaa2_qdma_sd_d) * 2,
 				sizeof(struct dpaa2_qdma_sd_d), 0);
 	if (!dpaa2_chan->sdd_pool)
 		goto err_fl;
-- 
GitLab


From 8446f9d11678bc268897882e86733d73204f83c4 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 5 Jan 2024 16:47:54 +0300
Subject: [PATCH 3175/4076] platform/x86: wmi: Fix wmi_dev_probe()

This has a reversed if statement so it accidentally disables the wmi
method before returning.

Fixes: 704af3a40747 ("platform/x86: wmi: Remove chardev interface")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/9c81251b-bc87-4ca3-bb86-843dc85e5145@moroto.mountain
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/wmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index d1df1a31de008..3c288e8f404be 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -896,7 +896,7 @@ static int wmi_dev_probe(struct device *dev)
 	if (wdriver->probe) {
 		ret = wdriver->probe(dev_to_wdev(dev),
 				find_guid_context(wblock, wdriver));
-		if (!ret) {
+		if (ret) {
 			if (ACPI_FAILURE(wmi_method_enable(wblock, false)))
 				dev_warn(dev, "Failed to disable device\n");
 
-- 
GitLab


From 416de0246f35f43d871a57939671fe814f4455ee Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Thu, 4 Jan 2024 15:59:03 -0700
Subject: [PATCH 3176/4076] platform/x86: intel-uncore-freq: Fix types in sysfs
 callbacks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When booting a kernel with CONFIG_CFI_CLANG, there is a CFI failure when
accessing any of the values under
/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00:

  $ cat /sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/max_freq_khz
  fish: Job 1, 'cat /sys/devices/system/cpu/int…' terminated by signal SIGSEGV (Address boundary error)

  $ sudo dmesg &| grep 'CFI failure'
  [  170.953925] CFI failure at kobj_attr_show+0x19/0x30 (target: show_max_freq_khz+0x0/0xc0 [intel_uncore_frequency_common]; expected type: 0xd34078c5

The sysfs callback functions such as show_domain_id() are written as if
they are going to be called by dev_attr_show() but as the above message
shows, they are instead called by kobj_attr_show(). kCFI checks that the
destination of an indirect jump has the exact same type as the prototype
of the function pointer it is called through and fails when they do not.

These callbacks are called through kobj_attr_show() because
uncore_root_kobj was initialized with kobject_create_and_add(), which
means uncore_root_kobj has a ->sysfs_ops of kobj_sysfs_ops from
kobject_create(), which uses kobj_attr_show() as its ->show() value.

The only reason there has not been a more noticeable problem until this
point is that 'struct kobj_attribute' and 'struct device_attribute' have
the same layout, so getting the callback from container_of() works the
same with either value.

Change all the callbacks and their uses to be compatible with
kobj_attr_show() and kobj_attr_store(), which resolves the kCFI failure
and allows the sysfs files to work properly.

Closes: https://github.com/ClangBuiltLinux/linux/issues/1974
Fixes: ae7b2ce57851 ("platform/x86/intel/uncore-freq: Use sysfs API to create attributes")
Cc: stable@vger.kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://lore.kernel.org/r/20240104-intel-uncore-freq-kcfi-fix-v1-1-bf1e8939af40@kernel.org
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 .../uncore-frequency-common.c                 | 82 +++++++++----------
 .../uncore-frequency-common.h                 | 32 ++++----
 2 files changed, 57 insertions(+), 57 deletions(-)

diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
index 33ab207493e3e..33bb58dc3f78c 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
@@ -23,23 +23,23 @@ static int (*uncore_read)(struct uncore_data *data, unsigned int *min, unsigned
 static int (*uncore_write)(struct uncore_data *data, unsigned int input, unsigned int min_max);
 static int (*uncore_read_freq)(struct uncore_data *data, unsigned int *freq);
 
-static ssize_t show_domain_id(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t show_domain_id(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	struct uncore_data *data = container_of(attr, struct uncore_data, domain_id_dev_attr);
+	struct uncore_data *data = container_of(attr, struct uncore_data, domain_id_kobj_attr);
 
 	return sprintf(buf, "%u\n", data->domain_id);
 }
 
-static ssize_t show_fabric_cluster_id(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t show_fabric_cluster_id(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	struct uncore_data *data = container_of(attr, struct uncore_data, fabric_cluster_id_dev_attr);
+	struct uncore_data *data = container_of(attr, struct uncore_data, fabric_cluster_id_kobj_attr);
 
 	return sprintf(buf, "%u\n", data->cluster_id);
 }
 
-static ssize_t show_package_id(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t show_package_id(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
-	struct uncore_data *data = container_of(attr, struct uncore_data, package_id_dev_attr);
+	struct uncore_data *data = container_of(attr, struct uncore_data, package_id_kobj_attr);
 
 	return sprintf(buf, "%u\n", data->package_id);
 }
@@ -97,30 +97,30 @@ static ssize_t show_perf_status_freq_khz(struct uncore_data *data, char *buf)
 }
 
 #define store_uncore_min_max(name, min_max)				\
-	static ssize_t store_##name(struct device *dev,		\
-				     struct device_attribute *attr,	\
+	static ssize_t store_##name(struct kobject *kobj,		\
+				     struct kobj_attribute *attr,	\
 				     const char *buf, size_t count)	\
 	{								\
-		struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\
+		struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\
 									\
 		return store_min_max_freq_khz(data, buf, count,	\
 					      min_max);		\
 	}
 
 #define show_uncore_min_max(name, min_max)				\
-	static ssize_t show_##name(struct device *dev,		\
-				    struct device_attribute *attr, char *buf)\
+	static ssize_t show_##name(struct kobject *kobj,		\
+				    struct kobj_attribute *attr, char *buf)\
 	{                                                               \
-		struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\
+		struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\
 									\
 		return show_min_max_freq_khz(data, buf, min_max);	\
 	}
 
 #define show_uncore_perf_status(name)					\
-	static ssize_t show_##name(struct device *dev,		\
-				   struct device_attribute *attr, char *buf)\
+	static ssize_t show_##name(struct kobject *kobj,		\
+				   struct kobj_attribute *attr, char *buf)\
 	{                                                               \
-		struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\
+		struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\
 									\
 		return show_perf_status_freq_khz(data, buf); \
 	}
@@ -134,11 +134,11 @@ show_uncore_min_max(max_freq_khz, 1);
 show_uncore_perf_status(current_freq_khz);
 
 #define show_uncore_data(member_name)					\
-	static ssize_t show_##member_name(struct device *dev,	\
-					   struct device_attribute *attr, char *buf)\
+	static ssize_t show_##member_name(struct kobject *kobj,	\
+					   struct kobj_attribute *attr, char *buf)\
 	{                                                               \
 		struct uncore_data *data = container_of(attr, struct uncore_data,\
-							  member_name##_dev_attr);\
+							  member_name##_kobj_attr);\
 									\
 		return sysfs_emit(buf, "%u\n",				\
 				 data->member_name);			\
@@ -149,29 +149,29 @@ show_uncore_data(initial_max_freq_khz);
 
 #define init_attribute_rw(_name)					\
 	do {								\
-		sysfs_attr_init(&data->_name##_dev_attr.attr);	\
-		data->_name##_dev_attr.show = show_##_name;		\
-		data->_name##_dev_attr.store = store_##_name;		\
-		data->_name##_dev_attr.attr.name = #_name;		\
-		data->_name##_dev_attr.attr.mode = 0644;		\
+		sysfs_attr_init(&data->_name##_kobj_attr.attr);	\
+		data->_name##_kobj_attr.show = show_##_name;		\
+		data->_name##_kobj_attr.store = store_##_name;		\
+		data->_name##_kobj_attr.attr.name = #_name;		\
+		data->_name##_kobj_attr.attr.mode = 0644;		\
 	} while (0)
 
 #define init_attribute_ro(_name)					\
 	do {								\
-		sysfs_attr_init(&data->_name##_dev_attr.attr);	\
-		data->_name##_dev_attr.show = show_##_name;		\
-		data->_name##_dev_attr.store = NULL;			\
-		data->_name##_dev_attr.attr.name = #_name;		\
-		data->_name##_dev_attr.attr.mode = 0444;		\
+		sysfs_attr_init(&data->_name##_kobj_attr.attr);	\
+		data->_name##_kobj_attr.show = show_##_name;		\
+		data->_name##_kobj_attr.store = NULL;			\
+		data->_name##_kobj_attr.attr.name = #_name;		\
+		data->_name##_kobj_attr.attr.mode = 0444;		\
 	} while (0)
 
 #define init_attribute_root_ro(_name)					\
 	do {								\
-		sysfs_attr_init(&data->_name##_dev_attr.attr);	\
-		data->_name##_dev_attr.show = show_##_name;		\
-		data->_name##_dev_attr.store = NULL;			\
-		data->_name##_dev_attr.attr.name = #_name;		\
-		data->_name##_dev_attr.attr.mode = 0400;		\
+		sysfs_attr_init(&data->_name##_kobj_attr.attr);	\
+		data->_name##_kobj_attr.show = show_##_name;		\
+		data->_name##_kobj_attr.store = NULL;			\
+		data->_name##_kobj_attr.attr.name = #_name;		\
+		data->_name##_kobj_attr.attr.mode = 0400;		\
 	} while (0)
 
 static int create_attr_group(struct uncore_data *data, char *name)
@@ -186,21 +186,21 @@ static int create_attr_group(struct uncore_data *data, char *name)
 
 	if (data->domain_id != UNCORE_DOMAIN_ID_INVALID) {
 		init_attribute_root_ro(domain_id);
-		data->uncore_attrs[index++] = &data->domain_id_dev_attr.attr;
+		data->uncore_attrs[index++] = &data->domain_id_kobj_attr.attr;
 		init_attribute_root_ro(fabric_cluster_id);
-		data->uncore_attrs[index++] = &data->fabric_cluster_id_dev_attr.attr;
+		data->uncore_attrs[index++] = &data->fabric_cluster_id_kobj_attr.attr;
 		init_attribute_root_ro(package_id);
-		data->uncore_attrs[index++] = &data->package_id_dev_attr.attr;
+		data->uncore_attrs[index++] = &data->package_id_kobj_attr.attr;
 	}
 
-	data->uncore_attrs[index++] = &data->max_freq_khz_dev_attr.attr;
-	data->uncore_attrs[index++] = &data->min_freq_khz_dev_attr.attr;
-	data->uncore_attrs[index++] = &data->initial_min_freq_khz_dev_attr.attr;
-	data->uncore_attrs[index++] = &data->initial_max_freq_khz_dev_attr.attr;
+	data->uncore_attrs[index++] = &data->max_freq_khz_kobj_attr.attr;
+	data->uncore_attrs[index++] = &data->min_freq_khz_kobj_attr.attr;
+	data->uncore_attrs[index++] = &data->initial_min_freq_khz_kobj_attr.attr;
+	data->uncore_attrs[index++] = &data->initial_max_freq_khz_kobj_attr.attr;
 
 	ret = uncore_read_freq(data, &freq);
 	if (!ret)
-		data->uncore_attrs[index++] = &data->current_freq_khz_dev_attr.attr;
+		data->uncore_attrs[index++] = &data->current_freq_khz_kobj_attr.attr;
 
 	data->uncore_attrs[index] = NULL;
 
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
index 7afb69977c7e8..0e5bf507e5552 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
@@ -26,14 +26,14 @@
  * @instance_id:	Unique instance id to append to directory name
  * @name:		Sysfs entry name for this instance
  * @uncore_attr_group:	Attribute group storage
- * @max_freq_khz_dev_attr: Storage for device attribute max_freq_khz
- * @mix_freq_khz_dev_attr: Storage for device attribute min_freq_khz
- * @initial_max_freq_khz_dev_attr: Storage for device attribute initial_max_freq_khz
- * @initial_min_freq_khz_dev_attr: Storage for device attribute initial_min_freq_khz
- * @current_freq_khz_dev_attr: Storage for device attribute current_freq_khz
- * @domain_id_dev_attr: Storage for device attribute domain_id
- * @fabric_cluster_id_dev_attr: Storage for device attribute fabric_cluster_id
- * @package_id_dev_attr: Storage for device attribute package_id
+ * @max_freq_khz_kobj_attr: Storage for kobject attribute max_freq_khz
+ * @mix_freq_khz_kobj_attr: Storage for kobject attribute min_freq_khz
+ * @initial_max_freq_khz_kobj_attr: Storage for kobject attribute initial_max_freq_khz
+ * @initial_min_freq_khz_kobj_attr: Storage for kobject attribute initial_min_freq_khz
+ * @current_freq_khz_kobj_attr: Storage for kobject attribute current_freq_khz
+ * @domain_id_kobj_attr: Storage for kobject attribute domain_id
+ * @fabric_cluster_id_kobj_attr: Storage for kobject attribute fabric_cluster_id
+ * @package_id_kobj_attr: Storage for kobject attribute package_id
  * @uncore_attrs:	Attribute storage for group creation
  *
  * This structure is used to encapsulate all data related to uncore sysfs
@@ -53,14 +53,14 @@ struct uncore_data {
 	char name[32];
 
 	struct attribute_group uncore_attr_group;
-	struct device_attribute max_freq_khz_dev_attr;
-	struct device_attribute min_freq_khz_dev_attr;
-	struct device_attribute initial_max_freq_khz_dev_attr;
-	struct device_attribute initial_min_freq_khz_dev_attr;
-	struct device_attribute current_freq_khz_dev_attr;
-	struct device_attribute domain_id_dev_attr;
-	struct device_attribute fabric_cluster_id_dev_attr;
-	struct device_attribute package_id_dev_attr;
+	struct kobj_attribute max_freq_khz_kobj_attr;
+	struct kobj_attribute min_freq_khz_kobj_attr;
+	struct kobj_attribute initial_max_freq_khz_kobj_attr;
+	struct kobj_attribute initial_min_freq_khz_kobj_attr;
+	struct kobj_attribute current_freq_khz_kobj_attr;
+	struct kobj_attribute domain_id_kobj_attr;
+	struct kobj_attribute fabric_cluster_id_kobj_attr;
+	struct kobj_attribute package_id_kobj_attr;
 	struct attribute *uncore_attrs[9];
 };
 
-- 
GitLab


From 5913320eb0b3ec88158cfcb0fa5e996bf4ef681b Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Mon, 8 Jan 2024 15:20:58 +0900
Subject: [PATCH 3177/4076] platform/x86: p2sb: Allow p2sb_bar() calls during
 PCI device probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

p2sb_bar() unhides P2SB device to get resources from the device. It
guards the operation by locking pci_rescan_remove_lock so that parallel
rescans do not find the P2SB device. However, this lock causes deadlock
when PCI bus rescan is triggered by /sys/bus/pci/rescan. The rescan
locks pci_rescan_remove_lock and probes PCI devices. When PCI devices
call p2sb_bar() during probe, it locks pci_rescan_remove_lock again.
Hence the deadlock.

To avoid the deadlock, do not lock pci_rescan_remove_lock in p2sb_bar().
Instead, do the lock at fs_initcall. Introduce p2sb_cache_resources()
for fs_initcall which gets and caches the P2SB resources. At p2sb_bar(),
refer the cache and return to the caller.

Before operating the device at P2SB DEVFN for resource cache, check
that its device class is PCI_CLASS_MEMORY_OTHER 0x0580 that PCH
specifications define. This avoids unexpected operation to other devices
at the same DEVFN.

Link: https://lore.kernel.org/linux-pci/6xb24fjmptxxn5js2fjrrddjae6twex5bjaftwqsuawuqqqydx@7cl3uik5ef6j/
Fixes: 9745fb07474f ("platform/x86/intel: Add Primary to Sideband (P2SB) bridge support")
Cc: stable@vger.kernel.org
Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Link: https://lore.kernel.org/r/20240108062059.3583028-2-shinichiro.kawasaki@wdc.com
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by Klara Modin <klarasmodin@gmail.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/p2sb.c | 180 ++++++++++++++++++++++++++++--------
 1 file changed, 139 insertions(+), 41 deletions(-)

diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c
index 1cf2471d54dde..17cc4b45e0239 100644
--- a/drivers/platform/x86/p2sb.c
+++ b/drivers/platform/x86/p2sb.c
@@ -26,6 +26,21 @@ static const struct x86_cpu_id p2sb_cpu_ids[] = {
 	{}
 };
 
+/*
+ * Cache BAR0 of P2SB device functions 0 to 7.
+ * TODO: The constant 8 is the number of functions that PCI specification
+ *       defines. Same definitions exist tree-wide. Unify this definition and
+ *       the other definitions then move to include/uapi/linux/pci.h.
+ */
+#define NR_P2SB_RES_CACHE 8
+
+struct p2sb_res_cache {
+	u32 bus_dev_id;
+	struct resource res;
+};
+
+static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE];
+
 static int p2sb_get_devfn(unsigned int *devfn)
 {
 	unsigned int fn = P2SB_DEVFN_DEFAULT;
@@ -39,8 +54,16 @@ static int p2sb_get_devfn(unsigned int *devfn)
 	return 0;
 }
 
+static bool p2sb_valid_resource(struct resource *res)
+{
+	if (res->flags)
+		return true;
+
+	return false;
+}
+
 /* Copy resource from the first BAR of the device in question */
-static int p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem)
+static void p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem)
 {
 	struct resource *bar0 = &pdev->resource[0];
 
@@ -56,49 +79,66 @@ static int p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem)
 	mem->end = bar0->end;
 	mem->flags = bar0->flags;
 	mem->desc = bar0->desc;
-
-	return 0;
 }
 
-static int p2sb_scan_and_read(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
+static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn)
 {
+	struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)];
 	struct pci_dev *pdev;
-	int ret;
 
 	pdev = pci_scan_single_device(bus, devfn);
 	if (!pdev)
-		return -ENODEV;
+		return;
 
-	ret = p2sb_read_bar0(pdev, mem);
+	p2sb_read_bar0(pdev, &cache->res);
+	cache->bus_dev_id = bus->dev.id;
 
 	pci_stop_and_remove_bus_device(pdev);
-	return ret;
 }
 
-/**
- * p2sb_bar - Get Primary to Sideband (P2SB) bridge device BAR
- * @bus: PCI bus to communicate with
- * @devfn: PCI slot and function to communicate with
- * @mem: memory resource to be filled in
- *
- * The BIOS prevents the P2SB device from being enumerated by the PCI
- * subsystem, so we need to unhide and hide it back to lookup the BAR.
- *
- * if @bus is NULL, the bus 0 in domain 0 will be used.
- * If @devfn is 0, it will be replaced by devfn of the P2SB device.
- *
- * Caller must provide a valid pointer to @mem.
- *
- * Locking is handled by pci_rescan_remove_lock mutex.
- *
- * Return:
- * 0 on success or appropriate errno value on error.
- */
-int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
+static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn)
+{
+	unsigned int slot, fn;
+
+	if (PCI_FUNC(devfn) == 0) {
+		/*
+		 * When function number of the P2SB device is zero, scan it and
+		 * other function numbers, and if devices are available, cache
+		 * their BAR0s.
+		 */
+		slot = PCI_SLOT(devfn);
+		for (fn = 0; fn < NR_P2SB_RES_CACHE; fn++)
+			p2sb_scan_and_cache_devfn(bus, PCI_DEVFN(slot, fn));
+	} else {
+		/* Scan the P2SB device and cache its BAR0 */
+		p2sb_scan_and_cache_devfn(bus, devfn);
+	}
+
+	if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res))
+		return -ENOENT;
+
+	return 0;
+}
+
+static struct pci_bus *p2sb_get_bus(struct pci_bus *bus)
+{
+	static struct pci_bus *p2sb_bus;
+
+	bus = bus ?: p2sb_bus;
+	if (bus)
+		return bus;
+
+	/* Assume P2SB is on the bus 0 in domain 0 */
+	p2sb_bus = pci_find_bus(0, 0);
+	return p2sb_bus;
+}
+
+static int p2sb_cache_resources(void)
 {
-	struct pci_dev *pdev_p2sb;
 	unsigned int devfn_p2sb;
 	u32 value = P2SBC_HIDE;
+	struct pci_bus *bus;
+	u16 class;
 	int ret;
 
 	/* Get devfn for P2SB device itself */
@@ -106,8 +146,17 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
 	if (ret)
 		return ret;
 
-	/* if @bus is NULL, use bus 0 in domain 0 */
-	bus = bus ?: pci_find_bus(0, 0);
+	bus = p2sb_get_bus(NULL);
+	if (!bus)
+		return -ENODEV;
+
+	/*
+	 * When a device with same devfn exists and its device class is not
+	 * PCI_CLASS_MEMORY_OTHER for P2SB, do not touch it.
+	 */
+	pci_bus_read_config_word(bus, devfn_p2sb, PCI_CLASS_DEVICE, &class);
+	if (!PCI_POSSIBLE_ERROR(class) && class != PCI_CLASS_MEMORY_OTHER)
+		return -ENODEV;
 
 	/*
 	 * Prevent concurrent PCI bus scan from seeing the P2SB device and
@@ -115,17 +164,16 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
 	 */
 	pci_lock_rescan_remove();
 
-	/* Unhide the P2SB device, if needed */
+	/*
+	 * The BIOS prevents the P2SB device from being enumerated by the PCI
+	 * subsystem, so we need to unhide and hide it back to lookup the BAR.
+	 * Unhide the P2SB device here, if needed.
+	 */
 	pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value);
 	if (value & P2SBC_HIDE)
 		pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0);
 
-	pdev_p2sb = pci_scan_single_device(bus, devfn_p2sb);
-	if (devfn)
-		ret = p2sb_scan_and_read(bus, devfn, mem);
-	else
-		ret = p2sb_read_bar0(pdev_p2sb, mem);
-	pci_stop_and_remove_bus_device(pdev_p2sb);
+	ret = p2sb_scan_and_cache(bus, devfn_p2sb);
 
 	/* Hide the P2SB device, if it was hidden */
 	if (value & P2SBC_HIDE)
@@ -133,12 +181,62 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
 
 	pci_unlock_rescan_remove();
 
-	if (ret)
-		return ret;
+	return ret;
+}
+
+/**
+ * p2sb_bar - Get Primary to Sideband (P2SB) bridge device BAR
+ * @bus: PCI bus to communicate with
+ * @devfn: PCI slot and function to communicate with
+ * @mem: memory resource to be filled in
+ *
+ * If @bus is NULL, the bus 0 in domain 0 will be used.
+ * If @devfn is 0, it will be replaced by devfn of the P2SB device.
+ *
+ * Caller must provide a valid pointer to @mem.
+ *
+ * Return:
+ * 0 on success or appropriate errno value on error.
+ */
+int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
+{
+	struct p2sb_res_cache *cache;
+	int ret;
+
+	bus = p2sb_get_bus(bus);
+	if (!bus)
+		return -ENODEV;
+
+	if (!devfn) {
+		ret = p2sb_get_devfn(&devfn);
+		if (ret)
+			return ret;
+	}
 
-	if (mem->flags == 0)
+	cache = &p2sb_resources[PCI_FUNC(devfn)];
+	if (cache->bus_dev_id != bus->dev.id)
 		return -ENODEV;
 
+	if (!p2sb_valid_resource(&cache->res))
+		return -ENOENT;
+
+	memcpy(mem, &cache->res, sizeof(*mem));
 	return 0;
 }
 EXPORT_SYMBOL_GPL(p2sb_bar);
+
+static int __init p2sb_fs_init(void)
+{
+	p2sb_cache_resources();
+	return 0;
+}
+
+/*
+ * pci_rescan_remove_lock to avoid access to unhidden P2SB devices can
+ * not be locked in sysfs pci bus rescan path because of deadlock. To
+ * avoid the deadlock, access to P2SB devices with the lock at an early
+ * step in kernel initialization and cache required resources. This
+ * should happen after subsys_initcall which initializes PCI subsystem
+ * and before device_initcall which requires P2SB resources.
+ */
+fs_initcall(p2sb_fs_init);
-- 
GitLab


From 9e054ed05ddae2c1b4b2bcb5dfcae49c5ac7637e Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Mon, 8 Jan 2024 15:20:59 +0900
Subject: [PATCH 3178/4076] platform/x86: p2sb: Use pci_resource_n() in
 p2sb_read_bar0()

Accesses to resource[] member of struct pci_dev shall be wrapped with
pci_resource_n() for future compatibility. Call the helper function in
p2sb_read_bar0().

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Link: https://lore.kernel.org/r/20240108062059.3583028-3-shinichiro.kawasaki@wdc.com
Tested-by Klara Modin <klarasmodin@gmail.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/p2sb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c
index 17cc4b45e0239..6bd14d0132dbd 100644
--- a/drivers/platform/x86/p2sb.c
+++ b/drivers/platform/x86/p2sb.c
@@ -65,7 +65,7 @@ static bool p2sb_valid_resource(struct resource *res)
 /* Copy resource from the first BAR of the device in question */
 static void p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem)
 {
-	struct resource *bar0 = &pdev->resource[0];
+	struct resource *bar0 = pci_resource_n(pdev, 0);
 
 	/* Make sure we have no dangling pointers in the output */
 	memset(mem, 0, sizeof(*mem));
-- 
GitLab


From 348d9cc7bde30852aa4f54aa70a22c3ad5dd081a Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Sat, 6 Jan 2024 23:41:26 +0100
Subject: [PATCH 3179/4076] platform/x86: intel-wmi-sbl-fw-update: Fix function
 name in error message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since when the driver was converted to use the bus-based WMI
interface, the old GUID-based WMI functions are not used anymore.
Update the error message to avoid confusing users.

Compile-tested only.

Fixes: 75c487fcb69c ("platform/x86: intel-wmi-sbl-fw-update: Use bus-based WMI interface")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20240106224126.13803-1-W_Armin@gmx.de
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel/wmi/sbl-fw-update.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/intel/wmi/sbl-fw-update.c b/drivers/platform/x86/intel/wmi/sbl-fw-update.c
index 9cf5ed0f8dc28..040153ad67c1c 100644
--- a/drivers/platform/x86/intel/wmi/sbl-fw-update.c
+++ b/drivers/platform/x86/intel/wmi/sbl-fw-update.c
@@ -32,7 +32,7 @@ static int get_fwu_request(struct device *dev, u32 *out)
 		return -ENODEV;
 
 	if (obj->type != ACPI_TYPE_INTEGER) {
-		dev_warn(dev, "wmi_query_block returned invalid value\n");
+		dev_warn(dev, "wmidev_block_query returned invalid value\n");
 		kfree(obj);
 		return -EINVAL;
 	}
@@ -55,7 +55,7 @@ static int set_fwu_request(struct device *dev, u32 in)
 
 	status = wmidev_block_set(to_wmi_device(dev), 0, &input);
 	if (ACPI_FAILURE(status)) {
-		dev_err(dev, "wmi_set_block failed\n");
+		dev_err(dev, "wmidev_block_set failed\n");
 		return -ENODEV;
 	}
 
-- 
GitLab


From 41237735ccde2cc3fe1d83ae0b776a085be6a22f Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 8 Jan 2024 15:06:55 +0100
Subject: [PATCH 3180/4076] platform/x86: silicom-platform: Add missing
 "Description:" for power_cycle sysfs attr

The Documentation/ABI/testing/sysfs-platform-silicom entry
for the power_cycle sysfs attr is missing the "Description:" keyword,
add this.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240108140655.547261-1-hdegoede@redhat.com
---
 Documentation/ABI/testing/sysfs-platform-silicom | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/ABI/testing/sysfs-platform-silicom b/Documentation/ABI/testing/sysfs-platform-silicom
index 2288b3665d160..4d1cc5bdbcc5f 100644
--- a/Documentation/ABI/testing/sysfs-platform-silicom
+++ b/Documentation/ABI/testing/sysfs-platform-silicom
@@ -10,6 +10,7 @@ What:		/sys/devices/platform/silicom-platform/power_cycle
 Date:		November 2023
 KernelVersion:	6.7
 Contact:	Henry Shi <henrys@silicom-usa.com>
+Description:
 		This file allow user to power cycle the platform.
 		Default value is 0; when set to 1, it powers down
 		the platform, waits 5 seconds, then powers on the
-- 
GitLab


From 452c314988dbccc491a32b674a3945d93a23c87c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 14 Jan 2024 17:53:16 +0100
Subject: [PATCH 3181/4076] MAINTAINERS: Remove Perry Yuan as DELL WMI HARDWARE
 PRIVACY SUPPORT maintainer

Recent mails to his Dell address bounced with "user unknown".
So remove him as maintainer.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/c9757d0a-2046-464b-93e1-a2d9ab0ce36b@gmail.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a692..30e231c8da372 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5958,7 +5958,6 @@ S:	Maintained
 F:	drivers/platform/x86/dell/dell-wmi-descriptor.c
 
 DELL WMI HARDWARE PRIVACY SUPPORT
-M:	Perry Yuan <Perry.Yuan@dell.com>
 L:	Dell.Client.Kernel@dell.com
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
-- 
GitLab


From 20fe5e9be47efc952c66374334f7bb94e4a51d90 Mon Sep 17 00:00:00 2001
From: "Luke D. Jones" <luke@ljones.dev>
Date: Tue, 16 Jan 2024 10:18:29 +1300
Subject: [PATCH 3182/4076] MAINTAINERS: add Luke Jones as maintainer for asus
 notebooks

Add myself as maintainer for "ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS
DRIVERS" as suggested by Hans de Goede based on my history of
contributions.

Signed-off-by: Luke D. Jones <luke@ljones.dev>
Link: https://lore.kernel.org/r/20240115211829.48251-1-luke@ljones.dev
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 30e231c8da372..8be1d172cc06f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3168,6 +3168,7 @@ F:	drivers/hwmon/asus-ec-sensors.c
 
 ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS DRIVERS
 M:	Corentin Chary <corentin.chary@gmail.com>
+M:	Luke D. Jones <luke@ljones.dev>
 L:	acpi4asus-user@lists.sourceforge.net
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
-- 
GitLab


From 8530ecaf35f23d02fdce49aded7227fc8f14ebcc Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 16 Jan 2024 11:39:21 +0100
Subject: [PATCH 3183/4076] MAINTAINERS: remove defunct acpi4asus project info
 from asus notebooks section

The acpi4asus project appears to be defunct, according to:
https://sourceforge.net/p/acpi4asus/mailman/acpi4asus-user/
the last posts to the list were done in May 2020 and even then
they were mostly spam.

And the http://acpi4asus.sf.net website still talks about 2.6.x kernels.

Drop the defunct mailing-list and update the W: entry to point to
the new up2date https://asus-linux.org/ site.

Cc: Corentin Chary <corentin.chary@gmail.com>
Cc: Luke D. Jones <luke@ljones.dev>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8be1d172cc06f..d9f66b5dec6b3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3169,10 +3169,9 @@ F:	drivers/hwmon/asus-ec-sensors.c
 ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS DRIVERS
 M:	Corentin Chary <corentin.chary@gmail.com>
 M:	Luke D. Jones <luke@ljones.dev>
-L:	acpi4asus-user@lists.sourceforge.net
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
-W:	http://acpi4asus.sf.net
+W:	https://asus-linux.org/
 F:	drivers/platform/x86/asus*.c
 F:	drivers/platform/x86/eeepc*.c
 
-- 
GitLab


From 84aef4ed59705585d629e81d633a83b7d416f5fb Mon Sep 17 00:00:00 2001
From: Wenhua Lin <Wenhua.Lin@unisoc.com>
Date: Tue, 9 Jan 2024 15:38:48 +0800
Subject: [PATCH 3184/4076] gpio: eic-sprd: Clear interrupt after set the
 interrupt type

The raw interrupt status of eic maybe set before the interrupt is enabled,
since the eic interrupt has a latch function, which would trigger the
interrupt event once enabled it from user side. To solve this problem,
interrupts generated before setting the interrupt trigger type are ignored.

Fixes: 25518e024e3a ("gpio: Add Spreadtrum EIC driver support")
Acked-by: Chunyan Zhang <zhang.lyra@gmail.com>
Signed-off-by: Wenhua Lin <Wenhua.Lin@unisoc.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-eic-sprd.c | 32 ++++++++++++++++++++++++++++----
 1 file changed, 28 insertions(+), 4 deletions(-)

diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index be7f2fa5aa7b6..806b88d8dfb7b 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -330,20 +330,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 		switch (flow_type) {
 		case IRQ_TYPE_LEVEL_HIGH:
 			sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1);
 			break;
 		case IRQ_TYPE_LEVEL_LOW:
 			sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1);
 			break;
 		case IRQ_TYPE_EDGE_RISING:
 		case IRQ_TYPE_EDGE_FALLING:
 		case IRQ_TYPE_EDGE_BOTH:
 			state = sprd_eic_get(chip, offset);
-			if (state)
+			if (state) {
 				sprd_eic_update(chip, offset,
 						SPRD_EIC_DBNC_IEV, 0);
-			else
+				sprd_eic_update(chip, offset,
+						SPRD_EIC_DBNC_IC, 1);
+			} else {
 				sprd_eic_update(chip, offset,
 						SPRD_EIC_DBNC_IEV, 1);
+				sprd_eic_update(chip, offset,
+						SPRD_EIC_DBNC_IC, 1);
+			}
 			break;
 		default:
 			return -ENOTSUPP;
@@ -355,20 +362,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 		switch (flow_type) {
 		case IRQ_TYPE_LEVEL_HIGH:
 			sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1);
 			break;
 		case IRQ_TYPE_LEVEL_LOW:
 			sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1);
 			break;
 		case IRQ_TYPE_EDGE_RISING:
 		case IRQ_TYPE_EDGE_FALLING:
 		case IRQ_TYPE_EDGE_BOTH:
 			state = sprd_eic_get(chip, offset);
-			if (state)
+			if (state) {
 				sprd_eic_update(chip, offset,
 						SPRD_EIC_LATCH_INTPOL, 0);
-			else
+				sprd_eic_update(chip, offset,
+						SPRD_EIC_LATCH_INTCLR, 1);
+			} else {
 				sprd_eic_update(chip, offset,
 						SPRD_EIC_LATCH_INTPOL, 1);
+				sprd_eic_update(chip, offset,
+						SPRD_EIC_LATCH_INTCLR, 1);
+			}
 			break;
 		default:
 			return -ENOTSUPP;
@@ -382,29 +396,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_FALLING:
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_BOTH:
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_LEVEL_HIGH:
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_level_irq);
 			break;
 		case IRQ_TYPE_LEVEL_LOW:
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1);
 			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_level_irq);
 			break;
 		default:
@@ -417,29 +436,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_FALLING:
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_BOTH:
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_LEVEL_HIGH:
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_level_irq);
 			break;
 		case IRQ_TYPE_LEVEL_LOW:
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0);
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1);
 			irq_set_handler_locked(data, handle_level_irq);
 			break;
 		default:
-- 
GitLab


From 80c86ff6800b857c8008cebe7b8d22a6e574e68d Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Tue, 9 Jan 2024 11:49:07 +0000
Subject: [PATCH 3185/4076] arm64: dts: exynos: gs101: comply with the new
 cmu_misc clock names

The cmu_misc clock-names were renamed to just "bus" and "sss" because
naming is local to the module, so cmu_misc is implied. As the bindings
and the device tree have not made a release yet, comply with the
renamed clocks.

Suggested-by: Rob Herring <robh@kernel.org>
Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Link: https://lore.kernel.org/r/20240109114908.3623645-3-tudor.ambarus@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 arch/arm64/boot/dts/exynos/google/gs101.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/exynos/google/gs101.dtsi b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
index 9747cb3fa03ac..d838e3a7af6e5 100644
--- a/arch/arm64/boot/dts/exynos/google/gs101.dtsi
+++ b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
@@ -289,7 +289,7 @@
 			#clock-cells = <1>;
 			clocks = <&cmu_top CLK_DOUT_CMU_MISC_BUS>,
 				 <&cmu_top CLK_DOUT_CMU_MISC_SSS>;
-			clock-names = "dout_cmu_misc_bus", "dout_cmu_misc_sss";
+			clock-names = "bus", "sss";
 		};
 
 		watchdog_cl0: watchdog@10060000 {
-- 
GitLab


From eab4f56d3e75dad697acf8dc2c8be3c341d6c63e Mon Sep 17 00:00:00 2001
From: Artur Weber <aweber.kernel@gmail.com>
Date: Fri, 5 Jan 2024 07:53:01 +0100
Subject: [PATCH 3186/4076] ARM: dts: exynos4212-tab3: add samsung,invert-vclk
 flag to fimd

After more investigation, I've found that it's not the panel driver
config that needs to be modified to invert the data polarity, but
the FIMD config.

Add the missing invert-vclk option that is required to get the display
to work correctly.

Fixes: ee37a457af1d ("ARM: dts: exynos: Add Samsung Galaxy Tab 3 8.0 boards")
Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Link: https://lore.kernel.org/r/20240105-tab3-display-fixes-v2-1-904d1207bf6f@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi b/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi
index d7954ff466b49..e5254e32aa8fc 100644
--- a/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi
+++ b/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi
@@ -434,6 +434,7 @@
 };
 
 &fimd {
+	samsung,invert-vclk;
 	status = "okay";
 };
 
-- 
GitLab


From 5744ba05e7c4bff8fec133dd0f9e51ddffba92f5 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Fri, 19 Jan 2024 18:22:35 +0800
Subject: [PATCH 3187/4076] tun: fix missing dropped counter in tun_xdp_act

The commit 8ae1aff0b331 ("tuntap: split out XDP logic") includes
dropped counter for XDP_DROP, XDP_ABORTED, and invalid XDP actions.
Unfortunately, that commit missed the dropped counter when error
occurs during XDP_TX and XDP_REDIRECT actions. This patch fixes
this issue.

Fixes: 8ae1aff0b331 ("tuntap: split out XDP logic")
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index afa5497f7c35c..237fef557ba58 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1630,13 +1630,17 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog,
 	switch (act) {
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(tun->dev, xdp, xdp_prog);
-		if (err)
+		if (err) {
+			dev_core_stats_rx_dropped_inc(tun->dev);
 			return err;
+		}
 		break;
 	case XDP_TX:
 		err = tun_xdp_tx(tun->dev, xdp);
-		if (err < 0)
+		if (err < 0) {
+			dev_core_stats_rx_dropped_inc(tun->dev);
 			return err;
+		}
 		break;
 	case XDP_PASS:
 		break;
-- 
GitLab


From f1084c427f55d573fcd5688d9ba7b31b78019716 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Fri, 19 Jan 2024 18:22:56 +0800
Subject: [PATCH 3188/4076] tun: add missing rx stats accounting in tun_xdp_act

The TUN can be used as vhost-net backend, and it is necessary to
count the packets transmitted from TUN to vhost-net/virtio-net.
However, there are some places in the receive path that were not
taken into account when using XDP. It would be beneficial to also
include new accounting for successfully received bytes using
dev_sw_netstats_rx_add.

Fixes: 761876c857cb ("tap: XDP support")
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 237fef557ba58..4a4f8c8e79fa1 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1634,6 +1634,7 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog,
 			dev_core_stats_rx_dropped_inc(tun->dev);
 			return err;
 		}
+		dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data);
 		break;
 	case XDP_TX:
 		err = tun_xdp_tx(tun->dev, xdp);
@@ -1641,6 +1642,7 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog,
 			dev_core_stats_rx_dropped_inc(tun->dev);
 			return err;
 		}
+		dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data);
 		break;
 	case XDP_PASS:
 		break;
-- 
GitLab


From c6a783be82c893c6f124a5853bef2edeaf26dadf Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Thu, 18 Jan 2024 04:23:40 -0800
Subject: [PATCH 3189/4076] thermal: intel: powerclamp: Remove dead code for
 target mwait value

After conversion of this driver to use powercap idle_inject core, this
driver doesn't use target_mwait value. So remove dead code.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/intel/intel_powerclamp.c | 32 ------------------------
 1 file changed, 32 deletions(-)

diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index 5ac5cb60bae67..bc6eb0dd66a49 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -49,7 +49,6 @@
  */
 #define DEFAULT_DURATION_JIFFIES (6)
 
-static unsigned int target_mwait;
 static struct dentry *debug_dir;
 static bool poll_pkg_cstate_enable;
 
@@ -312,34 +311,6 @@ MODULE_PARM_DESC(window_size, "sliding window in number of clamping cycles\n"
 	"\twindow size results in slower response time but more smooth\n"
 	"\tclamping results. default to 2.");
 
-static void find_target_mwait(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
-		return;
-
-	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
-
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
-	    !(ecx & CPUID5_ECX_INTERRUPT_BREAK))
-		return;
-
-	edx >>= MWAIT_SUBSTATE_SIZE;
-	for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-		if (edx & MWAIT_SUBSTATE_MASK) {
-			highest_cstate = i;
-			highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-		}
-	}
-	target_mwait = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-		(highest_subcstate - 1);
-
-}
-
 struct pkg_cstate_info {
 	bool skip;
 	int msr_index;
@@ -759,9 +730,6 @@ static int __init powerclamp_probe(void)
 		return -ENODEV;
 	}
 
-	/* find the deepest mwait value */
-	find_target_mwait();
-
 	return 0;
 }
 
-- 
GitLab


From b6a11a7fc4d6337f7ea720b9287d1b9749c4eae0 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 19 Jan 2024 14:43:01 +0100
Subject: [PATCH 3190/4076] dpll: fix broken error path in dpll_pin_alloc(..)

If pin type is not expected, or pin properities failed to allocate
memory, the unwind error path shall not destroy pin's xarrays, which
were not yet initialized.
Add new goto label and use it to fix broken error path.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/dpll/dpll_core.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 1eca8cc271f84..c08772ee9fd69 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -441,7 +441,7 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	if (WARN_ON(prop->type < DPLL_PIN_TYPE_MUX ||
 		    prop->type > DPLL_PIN_TYPE_MAX)) {
 		ret = -EINVAL;
-		goto err;
+		goto err_pin_prop;
 	}
 	pin->prop = prop;
 	refcount_set(&pin->refcount, 1);
@@ -450,11 +450,12 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b,
 			      &dpll_pin_xa_id, GFP_KERNEL);
 	if (ret)
-		goto err;
+		goto err_xa_alloc;
 	return pin;
-err:
+err_xa_alloc:
 	xa_destroy(&pin->dpll_refs);
 	xa_destroy(&pin->parent_refs);
+err_pin_prop:
 	kfree(pin);
 	return ERR_PTR(ret);
 }
-- 
GitLab


From 830ead5fb0c5855ce4d70ba2ed4a673b5f1e7d9b Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 19 Jan 2024 14:43:02 +0100
Subject: [PATCH 3191/4076] dpll: fix pin dump crash for rebound module

When a kernel module is unbound but the pin resources were not entirely
freed (other kernel module instance of the same PCI device have had kept
the reference to that pin), and kernel module is again bound, the pin
properties would not be updated (the properties are only assigned when
memory for the pin is allocated), prop pointer still points to the
kernel module memory of the kernel module which was deallocated on the
unbind.

If the pin dump is invoked in this state, the result is a kernel crash.
Prevent the crash by storing persistent pin properties in dpll subsystem,
copy the content from the kernel module when pin is allocated, instead of
using memory of the kernel module.

Fixes: 9431063ad323 ("dpll: core: Add DPLL framework base functions")
Fixes: 9d71b54b65b1 ("dpll: netlink: Add DPLL framework base functions")
Reviewed-by: Jan Glaza <jan.glaza@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/dpll/dpll_core.c    | 55 +++++++++++++++++++++++++++++++++++--
 drivers/dpll/dpll_core.h    |  4 +--
 drivers/dpll/dpll_netlink.c | 28 +++++++++----------
 3 files changed, 69 insertions(+), 18 deletions(-)

diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index c08772ee9fd69..cb62696467d12 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -425,6 +425,53 @@ void dpll_device_unregister(struct dpll_device *dpll,
 }
 EXPORT_SYMBOL_GPL(dpll_device_unregister);
 
+static void dpll_pin_prop_free(struct dpll_pin_properties *prop)
+{
+	kfree(prop->package_label);
+	kfree(prop->panel_label);
+	kfree(prop->board_label);
+	kfree(prop->freq_supported);
+}
+
+static int dpll_pin_prop_dup(const struct dpll_pin_properties *src,
+			     struct dpll_pin_properties *dst)
+{
+	memcpy(dst, src, sizeof(*dst));
+	if (src->freq_supported && src->freq_supported_num) {
+		size_t freq_size = src->freq_supported_num *
+				   sizeof(*src->freq_supported);
+		dst->freq_supported = kmemdup(src->freq_supported,
+					      freq_size, GFP_KERNEL);
+		if (!src->freq_supported)
+			return -ENOMEM;
+	}
+	if (src->board_label) {
+		dst->board_label = kstrdup(src->board_label, GFP_KERNEL);
+		if (!dst->board_label)
+			goto err_board_label;
+	}
+	if (src->panel_label) {
+		dst->panel_label = kstrdup(src->panel_label, GFP_KERNEL);
+		if (!dst->panel_label)
+			goto err_panel_label;
+	}
+	if (src->package_label) {
+		dst->package_label = kstrdup(src->package_label, GFP_KERNEL);
+		if (!dst->package_label)
+			goto err_package_label;
+	}
+
+	return 0;
+
+err_package_label:
+	kfree(dst->panel_label);
+err_panel_label:
+	kfree(dst->board_label);
+err_board_label:
+	kfree(dst->freq_supported);
+	return -ENOMEM;
+}
+
 static struct dpll_pin *
 dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	       const struct dpll_pin_properties *prop)
@@ -443,7 +490,9 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 		ret = -EINVAL;
 		goto err_pin_prop;
 	}
-	pin->prop = prop;
+	ret = dpll_pin_prop_dup(prop, &pin->prop);
+	if (ret)
+		goto err_pin_prop;
 	refcount_set(&pin->refcount, 1);
 	xa_init_flags(&pin->dpll_refs, XA_FLAGS_ALLOC);
 	xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC);
@@ -455,6 +504,7 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 err_xa_alloc:
 	xa_destroy(&pin->dpll_refs);
 	xa_destroy(&pin->parent_refs);
+	dpll_pin_prop_free(&pin->prop);
 err_pin_prop:
 	kfree(pin);
 	return ERR_PTR(ret);
@@ -515,6 +565,7 @@ void dpll_pin_put(struct dpll_pin *pin)
 		xa_destroy(&pin->dpll_refs);
 		xa_destroy(&pin->parent_refs);
 		xa_erase(&dpll_pin_xa, pin->id);
+		dpll_pin_prop_free(&pin->prop);
 		kfree(pin);
 	}
 	mutex_unlock(&dpll_lock);
@@ -637,7 +688,7 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin,
 	unsigned long i, stop;
 	int ret;
 
-	if (WARN_ON(parent->prop->type != DPLL_PIN_TYPE_MUX))
+	if (WARN_ON(parent->prop.type != DPLL_PIN_TYPE_MUX))
 		return -EINVAL;
 
 	if (WARN_ON(!ops) ||
diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h
index 5585873c5c1b0..717f715015c74 100644
--- a/drivers/dpll/dpll_core.h
+++ b/drivers/dpll/dpll_core.h
@@ -44,7 +44,7 @@ struct dpll_device {
  * @module:		module of creator
  * @dpll_refs:		hold referencees to dplls pin was registered with
  * @parent_refs:	hold references to parent pins pin was registered with
- * @prop:		pointer to pin properties given by registerer
+ * @prop:		pin properties copied from the registerer
  * @rclk_dev_name:	holds name of device when pin can recover clock from it
  * @refcount:		refcount
  **/
@@ -55,7 +55,7 @@ struct dpll_pin {
 	struct module *module;
 	struct xarray dpll_refs;
 	struct xarray parent_refs;
-	const struct dpll_pin_properties *prop;
+	struct dpll_pin_properties prop;
 	refcount_t refcount;
 };
 
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 3370dbddb86bd..30f5be020862d 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -303,17 +303,17 @@ dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin,
 	if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY, sizeof(freq), &freq,
 			  DPLL_A_PIN_PAD))
 		return -EMSGSIZE;
-	for (fs = 0; fs < pin->prop->freq_supported_num; fs++) {
+	for (fs = 0; fs < pin->prop.freq_supported_num; fs++) {
 		nest = nla_nest_start(msg, DPLL_A_PIN_FREQUENCY_SUPPORTED);
 		if (!nest)
 			return -EMSGSIZE;
-		freq = pin->prop->freq_supported[fs].min;
+		freq = pin->prop.freq_supported[fs].min;
 		if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN, sizeof(freq),
 				  &freq, DPLL_A_PIN_PAD)) {
 			nla_nest_cancel(msg, nest);
 			return -EMSGSIZE;
 		}
-		freq = pin->prop->freq_supported[fs].max;
+		freq = pin->prop.freq_supported[fs].max;
 		if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX, sizeof(freq),
 				  &freq, DPLL_A_PIN_PAD)) {
 			nla_nest_cancel(msg, nest);
@@ -329,9 +329,9 @@ static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq)
 {
 	int fs;
 
-	for (fs = 0; fs < pin->prop->freq_supported_num; fs++)
-		if (freq >= pin->prop->freq_supported[fs].min &&
-		    freq <= pin->prop->freq_supported[fs].max)
+	for (fs = 0; fs < pin->prop.freq_supported_num; fs++)
+		if (freq >= pin->prop.freq_supported[fs].min &&
+		    freq <= pin->prop.freq_supported[fs].max)
 			return true;
 	return false;
 }
@@ -421,7 +421,7 @@ static int
 dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin,
 		     struct netlink_ext_ack *extack)
 {
-	const struct dpll_pin_properties *prop = pin->prop;
+	const struct dpll_pin_properties *prop = &pin->prop;
 	struct dpll_pin_ref *ref;
 	int ret;
 
@@ -717,7 +717,7 @@ dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx,
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "state changing is not allowed");
 		return -EOPNOTSUPP;
 	}
@@ -753,7 +753,7 @@ dpll_pin_state_set(struct dpll_device *dpll, struct dpll_pin *pin,
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "state changing is not allowed");
 		return -EOPNOTSUPP;
 	}
@@ -780,7 +780,7 @@ dpll_pin_prio_set(struct dpll_device *dpll, struct dpll_pin *pin,
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "prio changing is not allowed");
 		return -EOPNOTSUPP;
 	}
@@ -808,7 +808,7 @@ dpll_pin_direction_set(struct dpll_pin *pin, struct dpll_device *dpll,
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "direction changing is not allowed");
 		return -EOPNOTSUPP;
 	}
@@ -838,8 +838,8 @@ dpll_pin_phase_adj_set(struct dpll_pin *pin, struct nlattr *phase_adj_attr,
 	int ret;
 
 	phase_adj = nla_get_s32(phase_adj_attr);
-	if (phase_adj > pin->prop->phase_range.max ||
-	    phase_adj < pin->prop->phase_range.min) {
+	if (phase_adj > pin->prop.phase_range.max ||
+	    phase_adj < pin->prop.phase_range.min) {
 		NL_SET_ERR_MSG_ATTR(extack, phase_adj_attr,
 				    "phase adjust value not supported");
 		return -EINVAL;
@@ -1023,7 +1023,7 @@ dpll_pin_find(u64 clock_id, struct nlattr *mod_name_attr,
 	unsigned long i;
 
 	xa_for_each_marked(&dpll_pin_xa, i, pin, DPLL_REGISTERED) {
-		prop = pin->prop;
+		prop = &pin->prop;
 		cid_match = clock_id ? pin->clock_id == clock_id : true;
 		mod_match = mod_name_attr && module_name(pin->module) ?
 			!nla_strcmp(mod_name_attr,
-- 
GitLab


From db2ec3c94667eaeecc6a74d96594fab6baf80fdc Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 19 Jan 2024 14:43:03 +0100
Subject: [PATCH 3192/4076] dpll: fix userspace availability of pins

If parent pin was unregistered but child pin was not, the userspace
would see the "zombie" pins - the ones that were registered with
a parent pin (dpll_pin_on_pin_register(..)).
Technically those are not available - as there is no dpll device in the
system. Do not dump those pins and prevent userspace from any
interaction with them. Provide a unified function to determine if the
pin is available and use it before acting/responding for user requests.

Fixes: 9d71b54b65b1 ("dpll: netlink: Add DPLL framework base functions")
Reviewed-by: Jan Glaza <jan.glaza@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/dpll/dpll_netlink.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 30f5be020862d..314bb37754651 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -553,6 +553,24 @@ __dpll_device_change_ntf(struct dpll_device *dpll)
 	return dpll_device_event_send(DPLL_CMD_DEVICE_CHANGE_NTF, dpll);
 }
 
+static bool dpll_pin_available(struct dpll_pin *pin)
+{
+	struct dpll_pin_ref *par_ref;
+	unsigned long i;
+
+	if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED))
+		return false;
+	xa_for_each(&pin->parent_refs, i, par_ref)
+		if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id,
+				DPLL_REGISTERED))
+			return true;
+	xa_for_each(&pin->dpll_refs, i, par_ref)
+		if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id,
+				DPLL_REGISTERED))
+			return true;
+	return false;
+}
+
 /**
  * dpll_device_change_ntf - notify that the dpll device has been changed
  * @dpll: registered dpll pointer
@@ -579,7 +597,7 @@ dpll_pin_event_send(enum dpll_cmd event, struct dpll_pin *pin)
 	int ret = -ENOMEM;
 	void *hdr;
 
-	if (WARN_ON(!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED)))
+	if (!dpll_pin_available(pin))
 		return -ENODEV;
 
 	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
@@ -1130,6 +1148,10 @@ int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info)
 	}
 	pin = dpll_pin_find_from_nlattr(info);
 	if (!IS_ERR(pin)) {
+		if (!dpll_pin_available(pin)) {
+			nlmsg_free(msg);
+			return -ENODEV;
+		}
 		ret = dpll_msg_add_pin_handle(msg, pin);
 		if (ret) {
 			nlmsg_free(msg);
@@ -1179,6 +1201,8 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 	xa_for_each_marked_start(&dpll_pin_xa, i, pin, DPLL_REGISTERED,
 				 ctx->idx) {
+		if (!dpll_pin_available(pin))
+			continue;
 		hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq,
 				  &dpll_nl_family, NLM_F_MULTI,
@@ -1441,7 +1465,8 @@ int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 	}
 	info->user_ptr[0] = xa_load(&dpll_pin_xa,
 				    nla_get_u32(info->attrs[DPLL_A_PIN_ID]));
-	if (!info->user_ptr[0]) {
+	if (!info->user_ptr[0] ||
+	    !dpll_pin_available(info->user_ptr[0])) {
 		NL_SET_ERR_MSG(info->extack, "pin not found");
 		ret = -ENODEV;
 		goto unlock_dev;
-- 
GitLab


From 7dc5b18ff71bd6f948810ab8a08b6a6ff8b315c5 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 19 Jan 2024 14:43:04 +0100
Subject: [PATCH 3193/4076] dpll: fix register pin with unregistered parent pin

In case of multiple kernel module instances using the same dpll device:
if only one registers dpll device, then only that one can register
directly connected pins with a dpll device. When unregistered parent is
responsible for determining if the muxed pin can be registered with it
or not, the drivers need to be loaded in serialized order to work
correctly - first the driver instance which registers the direct pins
needs to be loaded, then the other instances could register muxed type
pins.

Allow registration of a pin with a parent even if the parent was not
yet registered, thus allow ability for unserialized driver instance
load order.
Do not WARN_ON notification for unregistered pin, which can be invoked
for described case, instead just return error.

Fixes: 9431063ad323 ("dpll: core: Add DPLL framework base functions")
Fixes: 9d71b54b65b1 ("dpll: netlink: Add DPLL framework base functions")
Reviewed-by: Jan Glaza <jan.glaza@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/dpll/dpll_core.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index cb62696467d12..5152bd1b0daf5 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -29,8 +29,6 @@ static u32 dpll_pin_xa_id;
 	WARN_ON_ONCE(!xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
 #define ASSERT_DPLL_NOT_REGISTERED(d)	\
 	WARN_ON_ONCE(xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
-#define ASSERT_PIN_REGISTERED(p)	\
-	WARN_ON_ONCE(!xa_get_mark(&dpll_pin_xa, (p)->id, DPLL_REGISTERED))
 
 struct dpll_device_registration {
 	struct list_head list;
@@ -616,8 +614,6 @@ dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin,
 	    WARN_ON(!ops->state_on_dpll_get) ||
 	    WARN_ON(!ops->direction_get))
 		return -EINVAL;
-	if (ASSERT_DPLL_REGISTERED(dpll))
-		return -EINVAL;
 
 	mutex_lock(&dpll_lock);
 	if (WARN_ON(!(dpll->module == pin->module &&
@@ -695,8 +691,6 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin,
 	    WARN_ON(!ops->state_on_pin_get) ||
 	    WARN_ON(!ops->direction_get))
 		return -EINVAL;
-	if (ASSERT_PIN_REGISTERED(parent))
-		return -EINVAL;
 
 	mutex_lock(&dpll_lock);
 	ret = dpll_xa_ref_pin_add(&pin->parent_refs, parent, ops, priv);
-- 
GitLab


From aaf632f7ab6dec57bc9329a438f94504fe8034b9 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Fri, 19 Jan 2024 11:47:50 +0100
Subject: [PATCH 3194/4076] net: micrel: Fix PTP frame parsing for lan8814

The HW has the capability to check each frame if it is a PTP frame,
which domain it is, which ptp frame type it is, different ip address in
the frame. And if one of these checks fail then the frame is not
timestamp. Most of these checks were disabled except checking the field
minorVersionPTP inside the PTP header. Meaning that once a partner sends
a frame compliant to 8021AS which has minorVersionPTP set to 1, then the
frame was not timestamp because the HW expected by default a value of 0
in minorVersionPTP. This is exactly the same issue as on lan8841.
Fix this issue by removing this check so the userspace can decide on this.

Fixes: ece19502834d ("net: phy: micrel: 1588 support for LAN8814 phy")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Divya Koppera <divya.koppera@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 81c20eb4b54b9..dad720138baaf 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -120,6 +120,11 @@
  */
 #define LAN8814_1PPM_FORMAT			17179
 
+#define PTP_RX_VERSION				0x0248
+#define PTP_TX_VERSION				0x0288
+#define PTP_MAX_VERSION(x)			(((x) & GENMASK(7, 0)) << 8)
+#define PTP_MIN_VERSION(x)			((x) & GENMASK(7, 0))
+
 #define PTP_RX_MOD				0x024F
 #define PTP_RX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_ BIT(3)
 #define PTP_RX_TIMESTAMP_EN			0x024D
@@ -3150,6 +3155,12 @@ static void lan8814_ptp_init(struct phy_device *phydev)
 	lanphy_write_page_reg(phydev, 5, PTP_TX_PARSE_IP_ADDR_EN, 0);
 	lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_IP_ADDR_EN, 0);
 
+	/* Disable checking for minorVersionPTP field */
+	lanphy_write_page_reg(phydev, 5, PTP_RX_VERSION,
+			      PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0));
+	lanphy_write_page_reg(phydev, 5, PTP_TX_VERSION,
+			      PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0));
+
 	skb_queue_head_init(&ptp_priv->tx_queue);
 	skb_queue_head_init(&ptp_priv->rx_queue);
 	INIT_LIST_HEAD(&ptp_priv->rx_ts_list);
-- 
GitLab


From 8cbc756b802605dee3dd40019bd75960772bacf5 Mon Sep 17 00:00:00 2001
From: Liming Sun <limings@nvidia.com>
Date: Thu, 11 Jan 2024 12:31:06 -0500
Subject: [PATCH 3195/4076] platform/mellanox: mlxbf-tmfifo: Drop Tx network
 packet when Tx TmFIFO is full
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Starting from Linux 5.16 kernel, Tx timeout mechanism was added
in the virtio_net driver which prints the "Tx timeout" warning
message when a packet stays in Tx queue for too long. Below is an
example of the reported message:

"[494105.316739] virtio_net virtio1 tmfifo_net0: TX timeout on
queue: 0, sq: output.0, vq: 0×1, name: output.0, usecs since
last trans: 3079892256".

This issue could happen when external host driver which drains the
FIFO is restared, stopped or upgraded. To avoid such confusing
"Tx timeout" messages, this commit adds logic to drop the outstanding
Tx packet if it's not able to transmit in two seconds due to Tx FIFO
full, which can be considered as congestion or out-of-resource drop.

This commit also handles the special case that the packet is half-
transmitted into the Tx FIFO. In such case, the packet is discarded
with remaining length stored in vring->rem_padding. So paddings with
zeros can be sent out when Tx space is available to maintain the
integrity of the packet format. The padded packet will be dropped on
the receiving side.

Signed-off-by: Liming Sun <limings@nvidia.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20240111173106.96958-1-limings@nvidia.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/mellanox/mlxbf-tmfifo.c | 67 ++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index ed16ec422a7b3..b8d1e32e97eba 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -47,6 +47,9 @@
 /* Message with data needs at least two words (for header & data). */
 #define MLXBF_TMFIFO_DATA_MIN_WORDS		2
 
+/* Tx timeout in milliseconds. */
+#define TMFIFO_TX_TIMEOUT			2000
+
 /* ACPI UID for BlueField-3. */
 #define TMFIFO_BF3_UID				1
 
@@ -62,12 +65,14 @@ struct mlxbf_tmfifo;
  * @drop_desc: dummy desc for packet dropping
  * @cur_len: processed length of the current descriptor
  * @rem_len: remaining length of the pending packet
+ * @rem_padding: remaining bytes to send as paddings
  * @pkt_len: total length of the pending packet
  * @next_avail: next avail descriptor id
  * @num: vring size (number of descriptors)
  * @align: vring alignment size
  * @index: vring index
  * @vdev_id: vring virtio id (VIRTIO_ID_xxx)
+ * @tx_timeout: expire time of last tx packet
  * @fifo: pointer to the tmfifo structure
  */
 struct mlxbf_tmfifo_vring {
@@ -79,12 +84,14 @@ struct mlxbf_tmfifo_vring {
 	struct vring_desc drop_desc;
 	int cur_len;
 	int rem_len;
+	int rem_padding;
 	u32 pkt_len;
 	u16 next_avail;
 	int num;
 	int align;
 	int index;
 	int vdev_id;
+	unsigned long tx_timeout;
 	struct mlxbf_tmfifo *fifo;
 };
 
@@ -819,6 +826,50 @@ mlxbf_tmfifo_desc_done:
 	return true;
 }
 
+static void mlxbf_tmfifo_check_tx_timeout(struct mlxbf_tmfifo_vring *vring)
+{
+	unsigned long flags;
+
+	/* Only handle Tx timeout for network vdev. */
+	if (vring->vdev_id != VIRTIO_ID_NET)
+		return;
+
+	/* Initialize the timeout or return if not expired. */
+	if (!vring->tx_timeout) {
+		/* Initialize the timeout. */
+		vring->tx_timeout = jiffies +
+			msecs_to_jiffies(TMFIFO_TX_TIMEOUT);
+		return;
+	} else if (time_before(jiffies, vring->tx_timeout)) {
+		/* Return if not timeout yet. */
+		return;
+	}
+
+	/*
+	 * Drop the packet after timeout. The outstanding packet is
+	 * released and the remaining bytes will be sent with padding byte 0x00
+	 * as a recovery. On the peer(host) side, the padding bytes 0x00 will be
+	 * either dropped directly, or appended into existing outstanding packet
+	 * thus dropped as corrupted network packet.
+	 */
+	vring->rem_padding = round_up(vring->rem_len, sizeof(u64));
+	mlxbf_tmfifo_release_pkt(vring);
+	vring->cur_len = 0;
+	vring->rem_len = 0;
+	vring->fifo->vring[0] = NULL;
+
+	/*
+	 * Make sure the load/store are in order before
+	 * returning back to virtio.
+	 */
+	virtio_mb(false);
+
+	/* Notify upper layer. */
+	spin_lock_irqsave(&vring->fifo->spin_lock[0], flags);
+	vring_interrupt(0, vring->vq);
+	spin_unlock_irqrestore(&vring->fifo->spin_lock[0], flags);
+}
+
 /* Rx & Tx processing of a queue. */
 static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx)
 {
@@ -841,6 +892,7 @@ static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx)
 		return;
 
 	do {
+retry:
 		/* Get available FIFO space. */
 		if (avail == 0) {
 			if (is_rx)
@@ -851,6 +903,17 @@ static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx)
 				break;
 		}
 
+		/* Insert paddings for discarded Tx packet. */
+		if (!is_rx) {
+			vring->tx_timeout = 0;
+			while (vring->rem_padding >= sizeof(u64)) {
+				writeq(0, vring->fifo->tx.data);
+				vring->rem_padding -= sizeof(u64);
+				if (--avail == 0)
+					goto retry;
+			}
+		}
+
 		/* Console output always comes from the Tx buffer. */
 		if (!is_rx && devid == VIRTIO_ID_CONSOLE) {
 			mlxbf_tmfifo_console_tx(fifo, avail);
@@ -860,6 +923,10 @@ static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx)
 		/* Handle one descriptor. */
 		more = mlxbf_tmfifo_rxtx_one_desc(vring, is_rx, &avail);
 	} while (more);
+
+	/* Check Tx timeout. */
+	if (avail <= 0 && !is_rx)
+		mlxbf_tmfifo_check_tx_timeout(vring);
 }
 
 /* Handle Rx or Tx queues. */
-- 
GitLab


From 732c35ce6d4892f7b07cc9aca61a6ad0fd400a26 Mon Sep 17 00:00:00 2001
From: Shravan Kumar Ramani <shravankr@nvidia.com>
Date: Wed, 17 Jan 2024 05:01:34 -0500
Subject: [PATCH 3196/4076] platform/mellanox: mlxbf-pmc: Fix offset
 calculation for crspace events

The event selector fields for 2 counters are contained in one
32-bit register and the current logic does not account for this.

Fixes: 423c3361855c ("platform/mellanox: mlxbf-pmc: Add support for BlueField-3")
Signed-off-by: Shravan Kumar Ramani <shravankr@nvidia.com>
Reviewed-by: David Thompson <davthompson@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Link: https://lore.kernel.org/r/8834cfa496c97c7c2fcebcfca5a2aa007e20ae96.1705485095.git.shravankr@nvidia.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/mellanox/mlxbf-pmc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c
index 1dd84c7a79de9..b1995ac268d77 100644
--- a/drivers/platform/mellanox/mlxbf-pmc.c
+++ b/drivers/platform/mellanox/mlxbf-pmc.c
@@ -1170,7 +1170,7 @@ static int mlxbf_pmc_program_crspace_counter(int blk_num, uint32_t cnt_num,
 	int ret;
 
 	addr = pmc->block[blk_num].mmio_base +
-		(rounddown(cnt_num, 2) * MLXBF_PMC_CRSPACE_PERFSEL_SZ);
+		((cnt_num / 2) * MLXBF_PMC_CRSPACE_PERFSEL_SZ);
 	ret = mlxbf_pmc_readl(addr, &word);
 	if (ret)
 		return ret;
@@ -1413,7 +1413,7 @@ static int mlxbf_pmc_read_crspace_event(int blk_num, uint32_t cnt_num,
 	int ret;
 
 	addr = pmc->block[blk_num].mmio_base +
-		(rounddown(cnt_num, 2) * MLXBF_PMC_CRSPACE_PERFSEL_SZ);
+		((cnt_num / 2) * MLXBF_PMC_CRSPACE_PERFSEL_SZ);
 	ret = mlxbf_pmc_readl(addr, &word);
 	if (ret)
 		return ret;
-- 
GitLab


From 6e2276203ac9ff10fc76917ec9813c660f627369 Mon Sep 17 00:00:00 2001
From: Kunwu Chan <chentao@kylinos.cn>
Date: Thu, 18 Jan 2024 11:19:29 +0800
Subject: [PATCH 3197/4076] dmaengine: ti: edma: Add some null pointer checks
 to the edma_probe

devm_kasprintf() returns a pointer to dynamically allocated memory
which can be NULL upon failure. Ensure the allocation was successful
by checking the pointer validity.

Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Link: https://lore.kernel.org/r/20240118031929.192192-1-chentao@kylinos.cn
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/ti/edma.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index f1f920861fa9d..5f8d2e93ff3fb 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -2404,6 +2404,11 @@ static int edma_probe(struct platform_device *pdev)
 	if (irq > 0) {
 		irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccint",
 					  dev_name(dev));
+		if (!irq_name) {
+			ret = -ENOMEM;
+			goto err_disable_pm;
+		}
+
 		ret = devm_request_irq(dev, irq, dma_irq_handler, 0, irq_name,
 				       ecc);
 		if (ret) {
@@ -2420,6 +2425,11 @@ static int edma_probe(struct platform_device *pdev)
 	if (irq > 0) {
 		irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccerrint",
 					  dev_name(dev));
+		if (!irq_name) {
+			ret = -ENOMEM;
+			goto err_disable_pm;
+		}
+
 		ret = devm_request_irq(dev, irq, dma_ccerr_handler, 0, irq_name,
 				       ecc);
 		if (ret) {
-- 
GitLab


From 13e788deb7348cc88df34bed736c3b3b9927ea52 Mon Sep 17 00:00:00 2001
From: Sharath Srinivasan <sharath.srinivasan@oracle.com>
Date: Fri, 19 Jan 2024 17:48:39 -0800
Subject: [PATCH 3198/4076] net/rds: Fix UBSAN: array-index-out-of-bounds in
 rds_cmsg_recv

Syzcaller UBSAN crash occurs in rds_cmsg_recv(),
which reads inc->i_rx_lat_trace[j + 1] with index 4 (3 + 1),
but with array size of 4 (RDS_RX_MAX_TRACES).
Here 'j' is assigned from rs->rs_rx_trace[i] and in-turn from
trace.rx_trace_pos[i] in rds_recv_track_latency(),
with both arrays sized 3 (RDS_MSG_RX_DGRAM_TRACE_MAX). So fix the
off-by-one bounds check in rds_recv_track_latency() to prevent
a potential crash in rds_cmsg_recv().

Found by syzcaller:
=================================================================
UBSAN: array-index-out-of-bounds in net/rds/recv.c:585:39
index 4 is out of range for type 'u64 [4]'
CPU: 1 PID: 8058 Comm: syz-executor228 Not tainted 6.6.0-gd2f51b3516da #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.15.0-1 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x136/0x150 lib/dump_stack.c:106
 ubsan_epilogue lib/ubsan.c:217 [inline]
 __ubsan_handle_out_of_bounds+0xd5/0x130 lib/ubsan.c:348
 rds_cmsg_recv+0x60d/0x700 net/rds/recv.c:585
 rds_recvmsg+0x3fb/0x1610 net/rds/recv.c:716
 sock_recvmsg_nosec net/socket.c:1044 [inline]
 sock_recvmsg+0xe2/0x160 net/socket.c:1066
 __sys_recvfrom+0x1b6/0x2f0 net/socket.c:2246
 __do_sys_recvfrom net/socket.c:2264 [inline]
 __se_sys_recvfrom net/socket.c:2260 [inline]
 __x64_sys_recvfrom+0xe0/0x1b0 net/socket.c:2260
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x40/0x110 arch/x86/entry/common.c:82
 entry_SYSCALL_64_after_hwframe+0x63/0x6b
==================================================================

Fixes: 3289025aedc0 ("RDS: add receive message trace used by application")
Reported-by: Chenyuan Yang <chenyuan0y@gmail.com>
Closes: https://lore.kernel.org/linux-rdma/CALGdzuoVdq-wtQ4Az9iottBqC5cv9ZhcE5q8N7LfYFvkRsOVcw@mail.gmail.com/
Signed-off-by: Sharath Srinivasan <sharath.srinivasan@oracle.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/af_rds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 01c4cdfef45df..8435a20968ef5 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -419,7 +419,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval,
 
 	rs->rs_rx_traces = trace.rx_traces;
 	for (i = 0; i < rs->rs_rx_traces; i++) {
-		if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) {
+		if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) {
 			rs->rs_rx_traces = 0;
 			return -EFAULT;
 		}
-- 
GitLab


From bc9847c9ba134cfe3398011e343dcf6588c1c902 Mon Sep 17 00:00:00 2001
From: Jai Luthra <j-luthra@ti.com>
Date: Wed, 3 Jan 2024 14:37:55 +0530
Subject: [PATCH 3199/4076] dmaengine: ti: k3-udma: Report short packet errors

Propagate the TR response status to the device using BCDMA
split-channels. For example CSI-RX driver should be able to check if a
frame was not transferred completely (short packet) and needs to be
discarded.

Fixes: 25dcb5dd7b7c ("dmaengine: ti: New driver for K3 UDMA")
Signed-off-by: Jai Luthra <j-luthra@ti.com>
Acked-by: Peter Ujfalusi <peter.ujfalusi@gmail.com>
Link: https://lore.kernel.org/r/20240103-tr_resp_err-v1-1-2fdf6d48ab92@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/ti/k3-udma.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 2841a539c2648..6400d06588a24 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -3968,6 +3968,7 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 {
 	struct udma_chan *uc = to_udma_chan(&vc->chan);
 	struct udma_desc *d;
+	u8 status;
 
 	if (!vd)
 		return;
@@ -3977,12 +3978,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 	if (d->metadata_size)
 		udma_fetch_epib(uc, d);
 
-	/* Provide residue information for the client */
 	if (result) {
 		void *desc_vaddr = udma_curr_cppi5_desc_vaddr(d, d->desc_idx);
 
 		if (cppi5_desc_get_type(desc_vaddr) ==
 		    CPPI5_INFO0_DESC_TYPE_VAL_HOST) {
+			/* Provide residue information for the client */
 			result->residue = d->residue -
 					  cppi5_hdesc_get_pktlen(desc_vaddr);
 			if (result->residue)
@@ -3991,7 +3992,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 				result->result = DMA_TRANS_NOERROR;
 		} else {
 			result->residue = 0;
-			result->result = DMA_TRANS_NOERROR;
+			/* Propagate TR Response errors to the client */
+			status = d->hwdesc[0].tr_resp_base->status;
+			if (status)
+				result->result = DMA_TRANS_ABORTED;
+			else
+				result->result = DMA_TRANS_NOERROR;
 		}
 	}
 }
-- 
GitLab


From 968bc1d7203d384e72afe34124a1801b7af76514 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 7 Jan 2024 11:02:03 +0100
Subject: [PATCH 3200/4076] dmaengine: fsl-qdma: Fix a memory leak related to
 the status queue DMA

This dma_alloc_coherent() is undone in the remove function, but not in the
error handling path of fsl_qdma_probe().

Switch to the managed version to fix the issue in the probe and simplify
the remove function.

Fixes: b092529e0aa0 ("dmaengine: fsl-qdma: Add qDMA controller driver for Layerscape SoCs")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/a0ef5d0f5a47381617ef339df776ddc68ce48173.1704621515.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/fsl-qdma.c | 18 +++++-------------
 1 file changed, 5 insertions(+), 13 deletions(-)

diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index a1d0aa63142a9..28c4e86bbcd2e 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -563,11 +563,11 @@ static struct fsl_qdma_queue
 	/*
 	 * Buffer for queue command
 	 */
-	status_head->cq = dma_alloc_coherent(&pdev->dev,
-					     sizeof(struct fsl_qdma_format) *
-					     status_size,
-					     &status_head->bus_addr,
-					     GFP_KERNEL);
+	status_head->cq = dmam_alloc_coherent(&pdev->dev,
+					      sizeof(struct fsl_qdma_format) *
+					      status_size,
+					      &status_head->bus_addr,
+					      GFP_KERNEL);
 	if (!status_head->cq) {
 		devm_kfree(&pdev->dev, status_head);
 		return NULL;
@@ -1268,8 +1268,6 @@ static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev)
 
 static void fsl_qdma_remove(struct platform_device *pdev)
 {
-	int i;
-	struct fsl_qdma_queue *status;
 	struct device_node *np = pdev->dev.of_node;
 	struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev);
 
@@ -1277,12 +1275,6 @@ static void fsl_qdma_remove(struct platform_device *pdev)
 	fsl_qdma_cleanup_vchan(&fsl_qdma->dma_dev);
 	of_dma_controller_free(np);
 	dma_async_device_unregister(&fsl_qdma->dma_dev);
-
-	for (i = 0; i < fsl_qdma->block_number; i++) {
-		status = fsl_qdma->status[i];
-		dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) *
-				status->n_cq, status->cq, status->bus_addr);
-	}
 }
 
 static const struct of_device_id fsl_qdma_dt_ids[] = {
-- 
GitLab


From 3aa58cb51318e329d203857f7a191678e60bb714 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 7 Jan 2024 11:02:04 +0100
Subject: [PATCH 3201/4076] dmaengine: fsl-qdma: Fix a memory leak related to
 the queue command DMA

This dma_alloc_coherent() is undone neither in the remove function, nor in
the error handling path of fsl_qdma_probe().

Switch to the managed version to fix both issues.

Fixes: b092529e0aa0 ("dmaengine: fsl-qdma: Add qDMA controller driver for Layerscape SoCs")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/7f66aa14f59d32b13672dde28602b47deb294e1f.1704621515.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/fsl-qdma.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 28c4e86bbcd2e..9b141369bea5d 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -514,11 +514,11 @@ static struct fsl_qdma_queue
 			queue_temp = queue_head + i + (j * queue_num);
 
 			queue_temp->cq =
-			dma_alloc_coherent(&pdev->dev,
-					   sizeof(struct fsl_qdma_format) *
-					   queue_size[i],
-					   &queue_temp->bus_addr,
-					   GFP_KERNEL);
+			dmam_alloc_coherent(&pdev->dev,
+					    sizeof(struct fsl_qdma_format) *
+					    queue_size[i],
+					    &queue_temp->bus_addr,
+					    GFP_KERNEL);
 			if (!queue_temp->cq)
 				return NULL;
 			queue_temp->block_base = fsl_qdma->block_base +
-- 
GitLab


From 0650006a93a2ce3b57f86e7f000347d9ae7737ef Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 7 Jan 2024 11:02:05 +0100
Subject: [PATCH 3202/4076] dmaengine: fsl-qdma: Remove a useless devm_kfree()

'status_head' is a managed resource. It will be freed automatically if
fsl_qdma_prep_status_queue(), and so fsl_qdma_probe(), fails.

Remove the redundant (and harmless) devm_kfree() call.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/6b7f60aa2b92f73b35c586886daffc1a5ac58697.1704621515.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/fsl-qdma.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 9b141369bea5d..f405c77060ad8 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -568,10 +568,9 @@ static struct fsl_qdma_queue
 					      status_size,
 					      &status_head->bus_addr,
 					      GFP_KERNEL);
-	if (!status_head->cq) {
-		devm_kfree(&pdev->dev, status_head);
+	if (!status_head->cq)
 		return NULL;
-	}
+
 	status_head->n_cq = status_size;
 	status_head->virt_head = status_head->cq;
 	status_head->virt_tail = status_head->cq;
-- 
GitLab


From 1513664f340289cf10402753110f3cff12a738aa Mon Sep 17 00:00:00 2001
From: Andy Chi <andy.chi@canonical.com>
Date: Mon, 22 Jan 2024 15:48:24 +0800
Subject: [PATCH 3203/4076] ALSA: hda/realtek: fix mute/micmute LEDs for HP
 ZBook Power

The HP ZBook Power using ALC236 codec which using 0x02 to
control mute LED and 0x01 to control micmute LED.
Therefore, add a quirk to make it works.

Signed-off-by: Andy Chi <andy.chi@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240122074826.1020964-1-andy.chi@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f6f16622f9cc7..19f2eb26659d8 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9957,6 +9957,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8ca1, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
-- 
GitLab


From 4b5581f112075e46d73b34b9848be041e6c1e489 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Tue, 24 Oct 2023 18:53:53 +0200
Subject: [PATCH 3204/4076] accel/ivpu: Disable PLL after VPU IP reset during
 FLR

IP reset has to followed by ivpu_pll_disable() to properly enter
reset state.

Fixes: 828d63042aec ("accel/ivpu: Don't enter d0i3 during FLR")
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231024165353.761507-1-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_hw_40xx.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index eba2fdef2ace1..c02061f299e23 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -746,7 +746,7 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 	return 0;
 }
 
-static int ivpu_hw_40xx_reset(struct ivpu_device *vdev)
+static int ivpu_hw_40xx_ip_reset(struct ivpu_device *vdev)
 {
 	int ret;
 	u32 val;
@@ -768,6 +768,23 @@ static int ivpu_hw_40xx_reset(struct ivpu_device *vdev)
 	return ret;
 }
 
+static int ivpu_hw_40xx_reset(struct ivpu_device *vdev)
+{
+	int ret = 0;
+
+	if (ivpu_hw_40xx_ip_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset VPU IP\n");
+		ret = -EIO;
+	}
+
+	if (ivpu_pll_disable(vdev)) {
+		ivpu_err(vdev, "Failed to disable PLL\n");
+		ret = -EIO;
+	}
+
+	return ret;
+}
+
 static int ivpu_hw_40xx_d0i3_enable(struct ivpu_device *vdev)
 {
 	int ret;
@@ -913,7 +930,7 @@ static int ivpu_hw_40xx_power_down(struct ivpu_device *vdev)
 
 	ivpu_hw_40xx_save_d0i3_entry_timestamp(vdev);
 
-	if (!ivpu_hw_40xx_is_idle(vdev) && ivpu_hw_40xx_reset(vdev))
+	if (!ivpu_hw_40xx_is_idle(vdev) && ivpu_hw_40xx_ip_reset(vdev))
 		ivpu_warn(vdev, "Failed to reset the VPU\n");
 
 	if (ivpu_pll_disable(vdev)) {
-- 
GitLab


From 192cdb1c907fd8df2d764c5bb17496e415e59391 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 22 Jan 2024 15:18:11 +0100
Subject: [PATCH 3205/4076] cpufreq: intel_pstate: Refine computation of
 P-state for given frequency

On systems using HWP, if a given frequency is equal to the maximum turbo
frequency or the maximum non-turbo frequency, the HWP performance level
corresponding to it is already known and can be used directly without
any computation.

Accordingly, adjust the code to use the known HWP performance levels in
the cases mentioned above.

This also helps to avoid limiting CPU capacity artificially in some
cases when the BIOS produces the HWP_CAP numbers using a different
E-core-to-P-core performance scaling factor than expected by the kernel.

Fixes: f5c8cf2a4992 ("cpufreq: intel_pstate: hybrid: Use known scaling factor for P-cores")
Cc: 6.1+ <stable@vger.kernel.org> # 6.1+
Tested-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 55 +++++++++++++++++++++-------------
 1 file changed, 34 insertions(+), 21 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2ca70b0b5fdc5..ca94e60e705a1 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -529,6 +529,30 @@ static int intel_pstate_cppc_get_scaling(int cpu)
 }
 #endif /* CONFIG_ACPI_CPPC_LIB */
 
+static int intel_pstate_freq_to_hwp_rel(struct cpudata *cpu, int freq,
+					unsigned int relation)
+{
+	if (freq == cpu->pstate.turbo_freq)
+		return cpu->pstate.turbo_pstate;
+
+	if (freq == cpu->pstate.max_freq)
+		return cpu->pstate.max_pstate;
+
+	switch (relation) {
+	case CPUFREQ_RELATION_H:
+		return freq / cpu->pstate.scaling;
+	case CPUFREQ_RELATION_C:
+		return DIV_ROUND_CLOSEST(freq, cpu->pstate.scaling);
+	}
+
+	return DIV_ROUND_UP(freq, cpu->pstate.scaling);
+}
+
+static int intel_pstate_freq_to_hwp(struct cpudata *cpu, int freq)
+{
+	return intel_pstate_freq_to_hwp_rel(cpu, freq, CPUFREQ_RELATION_L);
+}
+
 /**
  * intel_pstate_hybrid_hwp_adjust - Calibrate HWP performance levels.
  * @cpu: Target CPU.
@@ -546,6 +570,7 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
 	int perf_ctl_turbo = pstate_funcs.get_turbo(cpu->cpu);
 	int scaling = cpu->pstate.scaling;
+	int freq;
 
 	pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys);
 	pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo);
@@ -559,16 +584,16 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 	cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling,
 					 perf_ctl_scaling);
 
-	cpu->pstate.max_pstate_physical =
-			DIV_ROUND_UP(perf_ctl_max_phys * perf_ctl_scaling,
-				     scaling);
+	freq = perf_ctl_max_phys * perf_ctl_scaling;
+	cpu->pstate.max_pstate_physical = intel_pstate_freq_to_hwp(cpu, freq);
 
-	cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling;
+	freq = cpu->pstate.min_pstate * perf_ctl_scaling;
+	cpu->pstate.min_freq = freq;
 	/*
 	 * Cast the min P-state value retrieved via pstate_funcs.get_min() to
 	 * the effective range of HWP performance levels.
 	 */
-	cpu->pstate.min_pstate = DIV_ROUND_UP(cpu->pstate.min_freq, scaling);
+	cpu->pstate.min_pstate = intel_pstate_freq_to_hwp(cpu, freq);
 }
 
 static inline void update_turbo_state(void)
@@ -2528,13 +2553,12 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu,
 	 * abstract values to represent performance rather than pure ratios.
 	 */
 	if (hwp_active && cpu->pstate.scaling != perf_ctl_scaling) {
-		int scaling = cpu->pstate.scaling;
 		int freq;
 
 		freq = max_policy_perf * perf_ctl_scaling;
-		max_policy_perf = DIV_ROUND_UP(freq, scaling);
+		max_policy_perf = intel_pstate_freq_to_hwp(cpu, freq);
 		freq = min_policy_perf * perf_ctl_scaling;
-		min_policy_perf = DIV_ROUND_UP(freq, scaling);
+		min_policy_perf = intel_pstate_freq_to_hwp(cpu, freq);
 	}
 
 	pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n",
@@ -2908,18 +2932,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 
 	cpufreq_freq_transition_begin(policy, &freqs);
 
-	switch (relation) {
-	case CPUFREQ_RELATION_L:
-		target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling);
-		break;
-	case CPUFREQ_RELATION_H:
-		target_pstate = freqs.new / cpu->pstate.scaling;
-		break;
-	default:
-		target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling);
-		break;
-	}
-
+	target_pstate = intel_pstate_freq_to_hwp_rel(cpu, freqs.new, relation);
 	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false);
 
 	freqs.new = target_pstate * cpu->pstate.scaling;
@@ -2937,7 +2950,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 
 	update_turbo_state();
 
-	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
+	target_pstate = intel_pstate_freq_to_hwp(cpu, target_freq);
 
 	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true);
 
-- 
GitLab


From 3c18703079b6c7149d037b71d685d6fcaf6c4cd0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 22 Jan 2024 11:50:00 +0000
Subject: [PATCH 3206/4076] netfs, cachefiles: Change mailing list

The publicly accessible archives for Red Hat mailing lists stop at Oct
2023; messages sent after that time are in internal-only archives.

Change the netfs and cachefiles mailing list to one that has publicly
accessible archives:

	netfs@lists.linux.dev

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20240122115007.3820330-2-dhowells@redhat.com
cc: Jeff Layton <jlayton@kernel.org>
cc: Matthew Wilcox <willy@infradead.org>
cc:  <netfs@lists.linux.dev>
cc:  <linux-cachefs@redhat.com>
cc:  <v9fs@lists.linux.dev>
cc:  <linux-afs@lists.infradead.org>
cc:  <ceph-devel@vger.kernel.org>
cc:  <linux-cifs@vger.kernel.org>
cc:  <linux-erofs@lists.ozlabs.org>
cc:  <linux-nfs@vger.kernel.org>
cc:  <linux-fsdevel@vger.kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a692..ab5858d24ffc0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4547,7 +4547,7 @@ F:	drivers/net/ieee802154/ca8210.c
 
 CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS
 M:	David Howells <dhowells@redhat.com>
-L:	linux-cachefs@redhat.com (moderated for non-subscribers)
+L:	netfs@lists.linux.dev
 S:	Supported
 F:	Documentation/filesystems/caching/cachefiles.rst
 F:	fs/cachefiles/
@@ -8223,7 +8223,7 @@ F:	include/linux/iomap.h
 
 FILESYSTEMS [NETFS LIBRARY]
 M:	David Howells <dhowells@redhat.com>
-L:	linux-cachefs@redhat.com (moderated for non-subscribers)
+L:	netfs@lists.linux.dev
 L:	linux-fsdevel@vger.kernel.org
 S:	Supported
 F:	Documentation/filesystems/caching/
-- 
GitLab


From d59da02d1ab690b81a3dd2493112fc6878198f60 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 22 Jan 2024 11:50:01 +0000
Subject: [PATCH 3207/4076] netfs: Add Jeff Layton as reviewer

Add Jeff Layton as a reviewer in the MAINTAINERS file.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20240122115007.3820330-3-dhowells@redhat.com
Acked-by: Jeff Layton <jlayton@kernel.org>
cc:  <netfs@lists.linux.dev>
cc:  <linux-fsdevel@vger.kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index ab5858d24ffc0..2f4f4bf2e7f8d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8223,6 +8223,7 @@ F:	include/linux/iomap.h
 
 FILESYSTEMS [NETFS LIBRARY]
 M:	David Howells <dhowells@redhat.com>
+R:	Jeff Layton <jlayton@kernel.org>
 L:	netfs@lists.linux.dev
 L:	linux-fsdevel@vger.kernel.org
 S:	Supported
-- 
GitLab


From 741ba0134fa7822fcf4e4a0a537a5c4cfd706b20 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 27 Dec 2023 16:21:24 +0100
Subject: [PATCH 3208/4076] pmdomain: core: Move the unused cleanup to a _sync
 initcall

The unused clock cleanup uses the _sync initcall to give all users at
earlier initcalls time to probe. Do the same to avoid leaving some PDs
dangling at "on" (which actually happened on qcom!).

Fixes: 2fe71dcdfd10 ("PM / domains: Add late_initcall to disable unused PM domains")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20231227-topic-pmdomain_sync_cleanup-v1-1-5f36769d538b@linaro.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index a1f6cba3ae6c8..18e232b5ed53d 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -1109,7 +1109,7 @@ static int __init genpd_power_off_unused(void)
 
 	return 0;
 }
-late_initcall(genpd_power_off_unused);
+late_initcall_sync(genpd_power_off_unused);
 
 #ifdef CONFIG_PM_SLEEP
 
-- 
GitLab


From f0e4a1356466ec1858ae8e5c70bea2ce5e55008b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 12 Jan 2024 17:33:55 +0100
Subject: [PATCH 3209/4076] pmdomain: renesas: r8a77980-sysc: CR7 must be
 always on
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The power domain containing the Cortex-R7 CPU core on the R-Car V3H SoC
must always be in power-on state, unlike on other SoCs in the R-Car Gen3
family.  See Table 9.4 "Power domains" in the R-Car Series, 3rd
Generation Hardware User’s Manual Rev.1.00 and later.

Fix this by marking the domain as a CPU domain without control
registers, so the driver will not touch it.

Fixes: 41d6d8bd8ae9 ("soc: renesas: rcar-sysc: add R8A77980 support")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/fdad9a86132d53ecddf72b734dac406915c4edc0.1705076735.git.geert+renesas@glider.be
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/renesas/r8a77980-sysc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pmdomain/renesas/r8a77980-sysc.c b/drivers/pmdomain/renesas/r8a77980-sysc.c
index 39ca84a67daad..621e411fc9991 100644
--- a/drivers/pmdomain/renesas/r8a77980-sysc.c
+++ b/drivers/pmdomain/renesas/r8a77980-sysc.c
@@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = {
 	  PD_CPU_NOCR },
 	{ "ca53-cpu3",	0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU,
 	  PD_CPU_NOCR },
-	{ "cr7",	0x240, 0, R8A77980_PD_CR7,	R8A77980_PD_ALWAYS_ON },
+	{ "cr7",	0x240, 0, R8A77980_PD_CR7,	R8A77980_PD_ALWAYS_ON,
+	  PD_CPU_NOCR },
 	{ "a3ir",	0x180, 0, R8A77980_PD_A3IR,	R8A77980_PD_ALWAYS_ON },
 	{ "a2ir0",	0x400, 0, R8A77980_PD_A2IR0,	R8A77980_PD_A3IR },
 	{ "a2ir1",	0x400, 1, R8A77980_PD_A2IR1,	R8A77980_PD_A3IR },
-- 
GitLab


From f7cfe7017b531e08c108ac6615b1ddedcc892428 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 9 Jan 2024 09:22:32 +0100
Subject: [PATCH 3210/4076] x86/paravirt: Make BUG_func() usable by non-GPL
 modules

Several inlined functions subject to paravirt patching are referencing
BUG_func() after the recent switch to the alternative patching
mechanism.

As those functions can legally be used by non-GPL modules, BUG_func()
must be usable by those modules, too. So use EXPORT_SYMBOL() when
exporting BUG_func().

Fixes: 9824b00c2b58 ("x86/paravirt: Move some functions and defines to alternative.c")
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240109082232.22657-1-jgross@suse.com
---
 arch/x86/kernel/alternative.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index cc130b57542ac..1d85cb7071cb2 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -403,7 +403,7 @@ noinstr void BUG_func(void)
 {
 	BUG();
 }
-EXPORT_SYMBOL_GPL(BUG_func);
+EXPORT_SYMBOL(BUG_func);
 
 #define CALL_RIP_REL_OPCODE	0xff
 #define CALL_RIP_REL_MODRM	0x15
-- 
GitLab


From ed1a72fb0d646c983c85b62144fb1d134a8edb71 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 10 Jan 2024 21:55:22 +0300
Subject: [PATCH 3211/4076] kunit: Fix a NULL vs IS_ERR() bug

The kunit_device_register() function doesn't return NULL, it returns
error pointers.  Change the KUNIT_ASSERT_NOT_NULL() to check for
ERR_OR_NULL().

Fixes: d03c720e03bd ("kunit: Add APIs for managing devices")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Rae Moar <rmoar@google.com>
Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 lib/kunit/kunit-test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index c4259d910356b..f7980ef236a38 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -720,7 +720,7 @@ static void kunit_device_cleanup_test(struct kunit *test)
 	long action_was_run = 0;
 
 	test_device = kunit_device_register(test, "my_device");
-	KUNIT_ASSERT_NOT_NULL(test, test_device);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
 
 	/* Add an action to verify cleanup. */
 	devm_add_action(test_device, test_dev_action, &action_was_run);
-- 
GitLab


From 083974ebb8fc65978d6cacd1bcfe9158d6234b98 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 10 Jan 2024 21:55:14 +0300
Subject: [PATCH 3212/4076] kunit: device: Fix a NULL vs IS_ERR() check in
 init()

The root_device_register() function does not return NULL, it returns
error pointers.  Fix the check to match.

Fixes: d03c720e03bd ("kunit: Add APIs for managing devices")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Rae Moar <rmoar@google.com>
Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 lib/kunit/device.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/kunit/device.c b/lib/kunit/device.c
index f5371287b3750..074c6dd2e36a7 100644
--- a/lib/kunit/device.c
+++ b/lib/kunit/device.c
@@ -45,8 +45,8 @@ int kunit_bus_init(void)
 	int error;
 
 	kunit_bus_device = root_device_register("kunit");
-	if (!kunit_bus_device)
-		return -ENOMEM;
+	if (IS_ERR(kunit_bus_device))
+		return PTR_ERR(kunit_bus_device);
 
 	error = bus_register(&kunit_bus_type);
 	if (error)
-- 
GitLab


From 57e39086fb868a84f772cf097004f4715d8aaccb Mon Sep 17 00:00:00 2001
From: David Gow <davidgow@google.com>
Date: Fri, 12 Jan 2024 07:49:47 +0800
Subject: [PATCH 3213/4076] MAINTAINERS: kunit: Add Rae Moar as a reviewer

Rae has been shouldering a lot of the KUnit review burden for the last
year, and will continue to do so in the future. Thanks!

Signed-off-by: David Gow <davidgow@google.com>
Reviewed-by: Rae Moar <rmoar@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a692..354d993bc2cf8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11724,6 +11724,7 @@ F:	fs/smb/server/
 KERNEL UNIT TESTING FRAMEWORK (KUnit)
 M:	Brendan Higgins <brendanhiggins@google.com>
 M:	David Gow <davidgow@google.com>
+R:	Rae Moar <rmoar@google.com>
 L:	linux-kselftest@vger.kernel.org
 L:	kunit-dev@googlegroups.com
 S:	Maintained
-- 
GitLab


From a1af6a2bfa0cb46d70b7df5352993e750da6c79b Mon Sep 17 00:00:00 2001
From: Marco Pagani <marpagan@redhat.com>
Date: Wed, 10 Jan 2024 16:59:47 +0100
Subject: [PATCH 3214/4076] kunit: run test suites only after module
 initialization completes

Commit 2810c1e99867 ("kunit: Fix wild-memory-access bug in
kunit_free_suite_set()") fixed a wild-memory-access bug that could have
happened during the loading phase of test suites built and executed as
loadable modules. However, it also introduced a problematic side effect
that causes test suites modules to crash when they attempt to register
fake devices.

When a module is loaded, it traverses the MODULE_STATE_UNFORMED and
MODULE_STATE_COMING states before reaching the normal operating state
MODULE_STATE_LIVE. Finally, when the module is removed, it moves to
MODULE_STATE_GOING before being released. However, if the loading
function load_module() fails between complete_formation() and
do_init_module(), the module goes directly from MODULE_STATE_COMING to
MODULE_STATE_GOING without passing through MODULE_STATE_LIVE.

This behavior was causing kunit_module_exit() to be called without
having first executed kunit_module_init(). Since kunit_module_exit() is
responsible for freeing the memory allocated by kunit_module_init()
through kunit_filter_suites(), this behavior was resulting in a
wild-memory-access bug.

Commit 2810c1e99867 ("kunit: Fix wild-memory-access bug in
kunit_free_suite_set()") fixed this issue by running the tests when the
module is still in MODULE_STATE_COMING. However, modules in that state
are not fully initialized, lacking sysfs kobjects. Therefore, if a test
module attempts to register a fake device, it will inevitably crash.

This patch proposes a different approach to fix the original
wild-memory-access bug while restoring the normal module execution flow
by making kunit_module_exit() able to detect if kunit_module_init() has
previously initialized the tests suite set. In this way, test modules
can once again register fake devices without crashing.

This behavior is achieved by checking whether mod->kunit_suites is a
virtual or direct mapping address. If it is a virtual address, then
kunit_module_init() has allocated the suite_set in kunit_filter_suites()
using kmalloc_array(). On the contrary, if mod->kunit_suites is still
pointing to the original address that was set when looking up the
.kunit_test_suites section of the module, then the loading phase has
failed and there's no memory to be freed.

v4:
- rebased on 6.8
- noted that kunit_filter_suites() must return a virtual address
v3:
- add a comment to clarify why the start address is checked
v2:
- add include <linux/mm.h>

Fixes: 2810c1e99867 ("kunit: Fix wild-memory-access bug in kunit_free_suite_set()")
Reviewed-by: David Gow <davidgow@google.com>
Tested-by: Rae Moar <rmoar@google.com>
Tested-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Signed-off-by: Marco Pagani <marpagan@redhat.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 lib/kunit/executor.c |  4 ++++
 lib/kunit/test.c     | 14 +++++++++++---
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c
index 717b9599036ba..689fff2b2b106 100644
--- a/lib/kunit/executor.c
+++ b/lib/kunit/executor.c
@@ -146,6 +146,10 @@ void kunit_free_suite_set(struct kunit_suite_set suite_set)
 	kfree(suite_set.start);
 }
 
+/*
+ * Filter and reallocate test suites. Must return the filtered test suites set
+ * allocated at a valid virtual address or NULL in case of error.
+ */
 struct kunit_suite_set
 kunit_filter_suites(const struct kunit_suite_set *suite_set,
 		    const char *filter_glob,
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index f95d2093a0aa3..31a5a992e6467 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -17,6 +17,7 @@
 #include <linux/panic.h>
 #include <linux/sched/debug.h>
 #include <linux/sched.h>
+#include <linux/mm.h>
 
 #include "debugfs.h"
 #include "device-impl.h"
@@ -801,12 +802,19 @@ static void kunit_module_exit(struct module *mod)
 	};
 	const char *action = kunit_action();
 
+	/*
+	 * Check if the start address is a valid virtual address to detect
+	 * if the module load sequence has failed and the suite set has not
+	 * been initialized and filtered.
+	 */
+	if (!suite_set.start || !virt_addr_valid(suite_set.start))
+		return;
+
 	if (!action)
 		__kunit_test_suites_exit(mod->kunit_suites,
 					 mod->num_kunit_suites);
 
-	if (suite_set.start)
-		kunit_free_suite_set(suite_set);
+	kunit_free_suite_set(suite_set);
 }
 
 static int kunit_module_notify(struct notifier_block *nb, unsigned long val,
@@ -816,12 +824,12 @@ static int kunit_module_notify(struct notifier_block *nb, unsigned long val,
 
 	switch (val) {
 	case MODULE_STATE_LIVE:
+		kunit_module_init(mod);
 		break;
 	case MODULE_STATE_GOING:
 		kunit_module_exit(mod);
 		break;
 	case MODULE_STATE_COMING:
-		kunit_module_init(mod);
 		break;
 	case MODULE_STATE_UNFORMED:
 		break;
-- 
GitLab


From 1a9f2c776d1416c4ea6cb0d0b9917778c41a1a7d Mon Sep 17 00:00:00 2001
From: Arthur Grillo <arthurgrillo@riseup.net>
Date: Wed, 10 Jan 2024 14:39:28 -0300
Subject: [PATCH 3215/4076] Documentation: KUnit: Update the instructions on
 how to test static functions

Now that we have the VISIBLE_IF_KUNIT and EXPORT_SYMBOL_IF_KUNIT macros,
update the instructions to recommend this way of testing static
functions.

Signed-off-by: Arthur Grillo <arthurgrillo@riseup.net>
Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 Documentation/dev-tools/kunit/usage.rst | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index a9efab50eed83..22955d56b3799 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -671,8 +671,23 @@ Testing Static Functions
 ------------------------
 
 If we do not want to expose functions or variables for testing, one option is to
-conditionally ``#include`` the test file at the end of your .c file. For
-example:
+conditionally export the used symbol. For example:
+
+.. code-block:: c
+
+	/* In my_file.c */
+
+	VISIBLE_IF_KUNIT int do_interesting_thing();
+	EXPORT_SYMBOL_IF_KUNIT(do_interesting_thing);
+
+	/* In my_file.h */
+
+	#if IS_ENABLED(CONFIG_KUNIT)
+		int do_interesting_thing(void);
+	#endif
+
+Alternatively, you could conditionally ``#include`` the test file at the end of
+your .c file. For example:
 
 .. code-block:: c
 
-- 
GitLab


From 523d242d4309797e6b27c708fbd1463f301c199a Mon Sep 17 00:00:00 2001
From: Zhu Ning <zhuning0077@gmail.com>
Date: Sat, 20 Jan 2024 18:12:36 +0800
Subject: [PATCH 3216/4076] ASoC: codecs: ES8326: improving crosstalk
 performance

We change the crosstalk parameter in es8326_resume function
to improve crosstalk performance.
Adding crosstalk kcontrol to enhance the flexibility of crosstalk
debugging in machine.
Adding ES8326_DAC_CROSSTALK macro to declare the crosstalk register.

Signed-off-by: Zhu Ning <zhuning0077@gmail.com>
Link: https://msgid.link/r/20240120101240.12496-2-zhuning0077@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8326.c | 82 +++++++++++++++++++++++++++++++++++++++
 sound/soc/codecs/es8326.h |  1 +
 2 files changed, 83 insertions(+)

diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index fa890f6205e2a..82d1c4f8324c8 100755
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -45,6 +45,82 @@ struct es8326_priv {
 	int jack_remove_retry;
 };
 
+static int es8326_crosstalk1_get(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	regmap_read(es8326->regmap, ES8326_DAC_RAMPRATE, &crosstalk_h);
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h &= 0x20;
+	crosstalk_l &= 0xf0;
+	crosstalk = crosstalk_h >> 1 | crosstalk_l >> 4;
+	ucontrol->value.integer.value[0] = crosstalk;
+
+	return 0;
+}
+
+static int es8326_crosstalk1_set(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	crosstalk = ucontrol->value.integer.value[0];
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h = (crosstalk & 0x10) << 1;
+	crosstalk_l &= 0x0f;
+	crosstalk_l |= (crosstalk & 0x0f) << 4;
+	regmap_update_bits(es8326->regmap, ES8326_DAC_RAMPRATE,
+			0x20, crosstalk_h);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, crosstalk_l);
+
+	return 0;
+}
+
+static int es8326_crosstalk2_get(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	regmap_read(es8326->regmap, ES8326_DAC_RAMPRATE, &crosstalk_h);
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h &= 0x10;
+	crosstalk_l &= 0x0f;
+	crosstalk = crosstalk_h  | crosstalk_l;
+	ucontrol->value.integer.value[0] = crosstalk;
+
+	return 0;
+}
+
+static int es8326_crosstalk2_set(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	crosstalk = ucontrol->value.integer.value[0];
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h = crosstalk & 0x10;
+	crosstalk_l &= 0xf0;
+	crosstalk_l |= crosstalk & 0x0f;
+	regmap_update_bits(es8326->regmap, ES8326_DAC_RAMPRATE,
+			0x10, crosstalk_h);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, crosstalk_l);
+
+	return 0;
+}
+
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(dac_vol_tlv, -9550, 50, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(adc_vol_tlv, -9550, 50, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(adc_analog_pga_tlv, 0, 300, 0);
@@ -102,6 +178,10 @@ static const struct snd_kcontrol_new es8326_snd_controls[] = {
 	SOC_SINGLE_TLV("ALC Capture Target Level", ES8326_ALC_LEVEL,
 			0, 0x0f, 0, drc_target_tlv),
 
+	SOC_SINGLE_EXT("CROSSTALK1", SND_SOC_NOPM, 0, 31, 0,
+			es8326_crosstalk1_get, es8326_crosstalk1_set),
+	SOC_SINGLE_EXT("CROSSTALK2", SND_SOC_NOPM, 0, 31, 0,
+			es8326_crosstalk2_get, es8326_crosstalk2_set),
 };
 
 static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
@@ -844,6 +924,8 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_write(es8326->regmap, ES8326_CLK_CAL_TIME, 0x00);
 	/* calibrate for B version */
 	es8326_calibrate(component);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, 0xaa);
+	regmap_write(es8326->regmap, ES8326_DAC_RAMPRATE, 0x00);
 	/* turn off headphone out */
 	regmap_write(es8326->regmap, ES8326_HP_CAL, 0x00);
 	/* set ADC and DAC in low power mode */
diff --git a/sound/soc/codecs/es8326.h b/sound/soc/codecs/es8326.h
index 90a08351d6acd..dfef808673f4a 100644
--- a/sound/soc/codecs/es8326.h
+++ b/sound/soc/codecs/es8326.h
@@ -72,6 +72,7 @@
 #define ES8326_DAC_VOL		0x50
 #define ES8326_DRC_RECOVERY	0x53
 #define ES8326_DRC_WINSIZE	0x54
+#define ES8326_DAC_CROSSTALK	0x55
 #define ES8326_HPJACK_TIMER	0x56
 #define ES8326_HPDET_TYPE	0x57
 #define ES8326_INT_SOURCE	0x58
-- 
GitLab


From 14a0a1ec3335ac3945a96437c35465e4a9616b88 Mon Sep 17 00:00:00 2001
From: Zhu Ning <zhuning0077@gmail.com>
Date: Sat, 20 Jan 2024 18:12:37 +0800
Subject: [PATCH 3217/4076] ASoC: codecs: ES8326: Improving the THD+N
 performance

We update the values of some registers in the initialization
sequence in es8326_resume function to improve THD+N performance.
THD+N performance decreases if the output level on headphone is
close to full scale. So we change the register setting in
es8326_jack_detect_handler function to improve THD+N performance
if headphone pulgged. Also, the register setting should be restored
when the headset is unplugged

Signed-off-by: Zhu Ning <zhuning0077@gmail.com>
Link: https://msgid.link/r/20240120101240.12496-3-zhuning0077@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8326.c | 21 +++++++++++++--------
 sound/soc/codecs/es8326.h |  2 +-
 2 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index 82d1c4f8324c8..10157a4bd500a 100755
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -752,6 +752,8 @@ static void es8326_jack_detect_handler(struct work_struct *work)
 			es8326->hp = 0;
 		}
 		regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
+		regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x0a);
+		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x03);
 		/*
 		 * Inverted HPJACK_POL bit to trigger one IRQ to double check HP Removal event
 		 */
@@ -777,6 +779,8 @@ static void es8326_jack_detect_handler(struct work_struct *work)
 			regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
 			usleep_range(50000, 70000);
 			regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
+			regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x1f);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x08);
 			queue_delayed_work(system_wq, &es8326->jack_detect_work,
 					msecs_to_jiffies(400));
 			es8326->hp = 1;
@@ -846,14 +850,14 @@ static int es8326_calibrate(struct snd_soc_component *component)
 	if ((es8326->version == ES8326_VERSION_B) && (es8326->calibrated == false)) {
 		dev_dbg(component->dev, "ES8326_VERSION_B, calibrating\n");
 		regmap_write(es8326->regmap, ES8326_CLK_INV, 0xc0);
-		regmap_write(es8326->regmap, ES8326_CLK_DIV1, 0x01);
+		regmap_write(es8326->regmap, ES8326_CLK_DIV1, 0x03);
 		regmap_write(es8326->regmap, ES8326_CLK_DLL, 0x30);
 		regmap_write(es8326->regmap, ES8326_CLK_MUX, 0xed);
 		regmap_write(es8326->regmap, ES8326_CLK_DAC_SEL, 0x08);
 		regmap_write(es8326->regmap, ES8326_CLK_TRI, 0xc1);
 		regmap_write(es8326->regmap, ES8326_DAC_MUTE, 0x03);
 		regmap_write(es8326->regmap, ES8326_ANA_VSEL, 0x7f);
-		regmap_write(es8326->regmap, ES8326_VMIDLOW, 0x03);
+		regmap_write(es8326->regmap, ES8326_VMIDLOW, 0x23);
 		regmap_write(es8326->regmap, ES8326_DAC2HPMIX, 0x88);
 		usleep_range(15000, 20000);
 		regmap_write(es8326->regmap, ES8326_HP_OFFSET_CAL, 0x8c);
@@ -894,13 +898,13 @@ static int es8326_resume(struct snd_soc_component *component)
 	/* reset internal clock state */
 	regmap_write(es8326->regmap, ES8326_RESET, 0x1f);
 	regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E);
+	regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0);
 	usleep_range(10000, 15000);
 	regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xe9);
-	regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0x4b);
+	regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0xcb);
 	/* set headphone default type and detect pin */
 	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x83);
 	regmap_write(es8326->regmap, ES8326_CLK_RESAMPLE, 0x05);
-	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x30);
 
 	/* set internal oscillator as clock source of headpone cp */
 	regmap_write(es8326->regmap, ES8326_CLK_DIV_CPC, 0x89);
@@ -908,14 +912,15 @@ static int es8326_resume(struct snd_soc_component *component)
 	/* clock manager reset release */
 	regmap_write(es8326->regmap, ES8326_RESET, 0x17);
 	/* set headphone detection as half scan mode */
-	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x30);
+	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x3d);
 	regmap_write(es8326->regmap, ES8326_PULLUP_CTL, 0x00);
 
 	/* enable headphone driver */
+	regmap_write(es8326->regmap, ES8326_HP_VOL, 0xc4);
 	regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa7);
 	usleep_range(2000, 5000);
-	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0xa3);
-	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0xb3);
+	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0x23);
+	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0x33);
 	regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
 
 	regmap_write(es8326->regmap, ES8326_CLK_INV, 0x00);
@@ -946,7 +951,7 @@ static int es8326_resume(struct snd_soc_component *component)
 		    (ES8326_IO_DMIC_CLK << ES8326_SDINOUT1_SHIFT));
 	regmap_write(es8326->regmap, ES8326_SDINOUT23_IO, ES8326_IO_INPUT);
 
-	regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b);
+	regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00);
 	regmap_write(es8326->regmap, ES8326_RESET, ES8326_CSM_ON);
 	regmap_update_bits(es8326->regmap, ES8326_PGAGAIN, ES8326_MIC_SEL_MASK,
 			   ES8326_MIC1_SEL);
diff --git a/sound/soc/codecs/es8326.h b/sound/soc/codecs/es8326.h
index dfef808673f4a..4234bbb900c45 100644
--- a/sound/soc/codecs/es8326.h
+++ b/sound/soc/codecs/es8326.h
@@ -101,7 +101,7 @@
 #define ES8326_MUTE (3 << 0)
 
 /* ES8326_CLK_CTL */
-#define ES8326_CLK_ON (0x7f << 0)
+#define ES8326_CLK_ON (0x7e << 0)
 #define ES8326_CLK_OFF (0 << 0)
 
 /* ES8326_CLK_INV */
-- 
GitLab


From a3aa9255d6ccb1bff13c7c98e5d3bf10ba67f92e Mon Sep 17 00:00:00 2001
From: Zhu Ning <zhuning0077@gmail.com>
Date: Sat, 20 Jan 2024 18:12:39 +0800
Subject: [PATCH 3218/4076] ASoC: codecs: ES8326: Minimize the pop noise on
 headphone

We modify the register settings to minimize headphone pop noise
during ES8326 power-up and music start/stop.

Signed-off-by: Zhu Ning <zhuning0077@gmail.com>
Link: https://msgid.link/r/20240120101240.12496-5-zhuning0077@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8326.c | 36 ++++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index 10157a4bd500a..1ed068c417d60 100755
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -523,7 +523,8 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction)
 		regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_OFF);
 		regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
 				ES8326_MUTE_MASK, ES8326_MUTE);
-		regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xf0);
+		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF,
+				0x30, 0x00);
 	} else {
 		if (!es8326->calibrated) {
 			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_FORCE_CAL);
@@ -536,8 +537,13 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction)
 			regmap_write(es8326->regmap, ES8326_HPR_OFFSET_INI, offset_r);
 			es8326->calibrated = true;
 		}
+		regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x01);
+		usleep_range(1000, 5000);
+		regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x00);
+		usleep_range(1000, 5000);
+		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x20);
+		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x30);
 		regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
-		regmap_write(es8326->regmap, ES8326_HP_VOL, 0x91);
 		regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_ON);
 		regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
 				ES8326_MUTE_MASK, ~(ES8326_MUTE));
@@ -557,23 +563,20 @@ static int es8326_set_bias_level(struct snd_soc_component *codec,
 		if (ret)
 			return ret;
 
-		regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x00);
+		regmap_update_bits(es8326->regmap, ES8326_RESET, 0x02, 0x02);
+		usleep_range(5000, 10000);
 		regmap_write(es8326->regmap, ES8326_INTOUT_IO, es8326->interrupt_clk);
 		regmap_write(es8326->regmap, ES8326_SDINOUT1_IO,
 			    (ES8326_IO_DMIC_CLK << ES8326_SDINOUT1_SHIFT));
-		regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E);
 		regmap_write(es8326->regmap, ES8326_PGA_PDN, 0x40);
 		regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00);
 		regmap_update_bits(es8326->regmap,  ES8326_CLK_CTL, 0x20, 0x20);
-
-		regmap_update_bits(es8326->regmap, ES8326_RESET,
-				ES8326_CSM_ON, ES8326_CSM_ON);
+		regmap_update_bits(es8326->regmap, ES8326_RESET, 0x02, 0x00);
 		break;
 	case SND_SOC_BIAS_PREPARE:
 		break;
 	case SND_SOC_BIAS_STANDBY:
 		regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b);
-		regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x00);
 		regmap_update_bits(es8326->regmap, ES8326_CLK_CTL, 0x20, 0x00);
 		regmap_write(es8326->regmap, ES8326_SDINOUT1_IO, ES8326_IO_INPUT);
 		break;
@@ -777,6 +780,7 @@ static void es8326_jack_detect_handler(struct work_struct *work)
 			 * Don't report jack status.
 			 */
 			regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
+			es8326_enable_micbias(es8326->component);
 			usleep_range(50000, 70000);
 			regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
 			regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x1f);
@@ -820,13 +824,10 @@ exit:
 static irqreturn_t es8326_irq(int irq, void *dev_id)
 {
 	struct es8326_priv *es8326 = dev_id;
-	struct snd_soc_component *comp = es8326->component;
 
 	if (!es8326->jack)
 		goto out;
 
-	es8326_enable_micbias(comp);
-
 	if (es8326->jack->status & SND_JACK_HEADSET)
 		queue_delayed_work(system_wq, &es8326->jack_detect_work,
 				   msecs_to_jiffies(10));
@@ -943,6 +944,14 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_write(es8326->regmap, ES8326_DAC_DSM, 0x08);
 	regmap_write(es8326->regmap, ES8326_DAC_VPPSCALE, 0x15);
 
+	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x80 |
+			((es8326->version == ES8326_VERSION_B) ?
+			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol) :
+			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol | 0x04)));
+	usleep_range(5000, 10000);
+	es8326_enable_micbias(es8326->component);
+	usleep_range(50000, 70000);
+	regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
 	regmap_write(es8326->regmap, ES8326_INT_SOURCE,
 		    (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON));
 	regmap_write(es8326->regmap, ES8326_INTOUT_IO,
@@ -959,11 +968,6 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE, ES8326_MUTE_MASK,
 			   ES8326_MUTE);
 
-	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x80 |
-			((es8326->version == ES8326_VERSION_B) ?
-			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol) :
-			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol | 0x04)));
-	regmap_write(es8326->regmap, ES8326_HP_VOL, 0x11);
 
 	es8326->jack_remove_retry = 0;
 	es8326->hp = 0;
-- 
GitLab


From 8c99a0a607b5e0cf6b79b283d7bb2c2b84e01da5 Mon Sep 17 00:00:00 2001
From: Zhu Ning <zhuning0077@gmail.com>
Date: Sat, 20 Jan 2024 18:12:40 +0800
Subject: [PATCH 3219/4076] ASoC: codecs: ES8326: fix the capture noise issue

We get a noise issue during the startup of recording. We update the
register setting and dapm widgets to fix this issue.
we change callback type of es8326_mute function to mute_stream.
ES8326_ADC_MUTE is moved to es8326_mute function so it can
be turned on at last and turned off at first.

Signed-off-by: Zhu Ning <zhuning0077@gmail.com>
Link: https://msgid.link/r/20240120101240.12496-6-zhuning0077@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8326.c | 63 ++++++++++++++++++++-------------------
 1 file changed, 32 insertions(+), 31 deletions(-)

diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index 1ed068c417d60..cbcd02ec6ba42 100755
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -197,12 +197,6 @@ static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
 	SND_SOC_DAPM_AIF_OUT("I2S OUT", "I2S1 Capture", 0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("I2S IN", "I2S1 Playback", 0, SND_SOC_NOPM, 0, 0),
 
-	/* ADC Digital Mute */
-	SND_SOC_DAPM_PGA("ADC L1", ES8326_ADC_MUTE, 0, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC R1", ES8326_ADC_MUTE, 1, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC L2", ES8326_ADC_MUTE, 2, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC R2", ES8326_ADC_MUTE, 3, 1, NULL, 0),
-
 	/* Analog Power Supply*/
 	SND_SOC_DAPM_DAC("Right DAC", NULL, ES8326_ANA_PDN, 0, 1),
 	SND_SOC_DAPM_DAC("Left DAC", NULL, ES8326_ANA_PDN, 1, 1),
@@ -222,15 +216,10 @@ static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
 };
 
 static const struct snd_soc_dapm_route es8326_dapm_routes[] = {
-	{"ADC L1", NULL, "MIC1"},
-	{"ADC R1", NULL, "MIC2"},
-	{"ADC L2", NULL, "MIC3"},
-	{"ADC R2", NULL, "MIC4"},
-
-	{"ADC L", NULL, "ADC L1"},
-	{"ADC R", NULL, "ADC R1"},
-	{"ADC L", NULL, "ADC L2"},
-	{"ADC R", NULL, "ADC R2"},
+	{"ADC L", NULL, "MIC1"},
+	{"ADC R", NULL, "MIC2"},
+	{"ADC L", NULL, "MIC3"},
+	{"ADC R", NULL, "MIC4"},
 
 	{"I2S OUT", NULL, "ADC L"},
 	{"I2S OUT", NULL, "ADC R"},
@@ -520,11 +509,16 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction)
 	unsigned int offset_l, offset_r;
 
 	if (mute) {
-		regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_OFF);
-		regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
-				ES8326_MUTE_MASK, ES8326_MUTE);
-		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF,
-				0x30, 0x00);
+		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
+			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_OFF);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
+					ES8326_MUTE_MASK, ES8326_MUTE);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF,
+					0x30, 0x00);
+		} else {
+			regmap_update_bits(es8326->regmap,  ES8326_ADC_MUTE,
+					0x0F, 0x0F);
+		}
 	} else {
 		if (!es8326->calibrated) {
 			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_FORCE_CAL);
@@ -537,16 +531,22 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction)
 			regmap_write(es8326->regmap, ES8326_HPR_OFFSET_INI, offset_r);
 			es8326->calibrated = true;
 		}
-		regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x01);
-		usleep_range(1000, 5000);
-		regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x00);
-		usleep_range(1000, 5000);
-		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x20);
-		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x30);
-		regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
-		regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_ON);
-		regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
-				ES8326_MUTE_MASK, ~(ES8326_MUTE));
+		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
+			regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x01);
+			usleep_range(1000, 5000);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x00);
+			usleep_range(1000, 5000);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x20);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x30);
+			regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
+			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_ON);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
+					ES8326_MUTE_MASK, ~(ES8326_MUTE));
+		} else {
+			msleep(300);
+			regmap_update_bits(es8326->regmap,  ES8326_ADC_MUTE,
+					0x0F, 0x00);
+		}
 	}
 	return 0;
 }
@@ -596,7 +596,7 @@ static const struct snd_soc_dai_ops es8326_ops = {
 	.set_fmt = es8326_set_dai_fmt,
 	.set_sysclk = es8326_set_dai_sysclk,
 	.mute_stream = es8326_mute,
-	.no_capture_mute = 1,
+	.no_capture_mute = 0,
 };
 
 static struct snd_soc_dai_driver es8326_dai = {
@@ -968,6 +968,7 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE, ES8326_MUTE_MASK,
 			   ES8326_MUTE);
 
+	regmap_write(es8326->regmap, ES8326_ADC_MUTE, 0x0f);
 
 	es8326->jack_remove_retry = 0;
 	es8326->hp = 0;
-- 
GitLab


From b53cc6144a3f6c8b56afcdec89d81195c9b0dc69 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Fri, 19 Jan 2024 12:24:17 +0100
Subject: [PATCH 3220/4076] ASoC: codecs: wsa883x: fix PA volume control

The PA gain can be set in steps of 1.5 dB from -3 dB to 18 dB, that is,
in 15 levels.

Fix the dB values for the PA volume control as experiments using wsa8835
show that the first 16 levels all map to the same lowest gain while the
last three map to the highest gain.

These values specifically need to be correct for the sound server to
provide proper volume control.

Note that level 0 (-3 dB) does not mute the PA so the mute flag should
also not be set.

Fixes: cdb09e623143 ("ASoC: codecs: wsa883x: add control, dapm widgets and map")
Cc: stable@vger.kernel.org      # 6.0
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://msgid.link/r/20240119112420.7446-2-johan+linaro@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wsa883x.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c
index cb83c569e18d6..a2e86ef7d18f5 100644
--- a/sound/soc/codecs/wsa883x.c
+++ b/sound/soc/codecs/wsa883x.c
@@ -1098,7 +1098,11 @@ static int wsa_dev_mode_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const DECLARE_TLV_DB_SCALE(pa_gain, -300, 150, -300);
+static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(pa_gain,
+	0, 14, TLV_DB_SCALE_ITEM(-300, 0, 0),
+	15, 29, TLV_DB_SCALE_ITEM(-300, 150, 0),
+	30, 31, TLV_DB_SCALE_ITEM(1800, 0, 0),
+);
 
 static int wsa883x_get_swr_port(struct snd_kcontrol *kcontrol,
 				struct snd_ctl_elem_value *ucontrol)
-- 
GitLab


From 46188db080bd1df7d2d28031b89e56f2fdbabd67 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Fri, 19 Jan 2024 12:24:19 +0100
Subject: [PATCH 3221/4076] ASoC: codecs: lpass-wsa-macro: fix compander volume
 hack

The LPASS WSA macro codec driver is updating the digital gain settings
behind the back of user space on DAPM events if companding has been
enabled.

As compander control is exported to user space, this can result in the
digital gain setting being incremented (or decremented) every time the
sound server is started and the codec suspended depending on what the
UCM configuration looks like.

Soon enough playback will become distorted (or too quiet).

This is specifically a problem on the Lenovo ThinkPad X13s as this
bypasses the limit for the digital gain setting that has been set by the
machine driver.

Fix this by simply dropping the compander gain offset hack. If someone
cares about modelling the impact of the compander setting this can
possibly be done by exporting it as a volume control later.

Note that the volume registers still need to be written after enabling
clocks in order for any prior updates to take effect.

Fixes: 2c4066e5d428 ("ASoC: codecs: lpass-wsa-macro: add dapm widgets and route")
Cc: stable@vger.kernel.org      # 5.11
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://msgid.link/r/20240119112420.7446-4-johan+linaro@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/lpass-wsa-macro.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c
index 7e21cec3c2fb9..6ce309980cd10 100644
--- a/sound/soc/codecs/lpass-wsa-macro.c
+++ b/sound/soc/codecs/lpass-wsa-macro.c
@@ -1584,7 +1584,6 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 	u16 gain_reg;
 	u16 reg;
 	int val;
-	int offset_val = 0;
 	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
 
 	if (w->shift == WSA_MACRO_COMP1) {
@@ -1623,10 +1622,8 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 					CDC_WSA_RX1_RX_PATH_MIX_SEC0,
 					CDC_WSA_RX_PGA_HALF_DB_MASK,
 					CDC_WSA_RX_PGA_HALF_DB_ENABLE);
-			offset_val = -2;
 		}
 		val = snd_soc_component_read(component, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(component, gain_reg, val);
 		wsa_macro_config_ear_spkr_gain(component, wsa,
 						event, gain_reg);
@@ -1654,10 +1651,6 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 					CDC_WSA_RX1_RX_PATH_MIX_SEC0,
 					CDC_WSA_RX_PGA_HALF_DB_MASK,
 					CDC_WSA_RX_PGA_HALF_DB_DISABLE);
-			offset_val = 2;
-			val = snd_soc_component_read(component, gain_reg);
-			val += offset_val;
-			snd_soc_component_write(component, gain_reg, val);
 		}
 		wsa_macro_config_ear_spkr_gain(component, wsa,
 						event, gain_reg);
-- 
GitLab


From aafa3acf62f1f63e620753fb9fd75095325617b2 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Fri, 19 Jan 2024 12:24:20 +0100
Subject: [PATCH 3222/4076] ASoC: codecs: wcd9335: drop unused gain hack
 remnant

The vendor driver appears to be modifying the gain settings behind the
back of user space but these hacks never made it upstream except for
some essentially dead code that adds a constant zero to the current gain
setting on DAPM events.

Note that the volume registers still need to be written after enabling
clocks in order for any prior updates to take effect.

Reviewed-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://msgid.link/r/20240119112420.7446-5-johan+linaro@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wcd9335.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index 43c648efd0d93..deb15b95992d5 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -3033,7 +3033,6 @@ static int wcd9335_codec_enable_mix_path(struct snd_soc_dapm_widget *w,
 {
 	struct snd_soc_component *comp = snd_soc_dapm_to_component(w->dapm);
 	u16 gain_reg;
-	int offset_val = 0;
 	int val = 0;
 
 	switch (w->reg) {
@@ -3073,7 +3072,6 @@ static int wcd9335_codec_enable_mix_path(struct snd_soc_dapm_widget *w,
 	switch (event) {
 	case SND_SOC_DAPM_POST_PMU:
 		val = snd_soc_component_read(comp, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(comp, gain_reg, val);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
@@ -3294,7 +3292,6 @@ static int wcd9335_codec_enable_interpolator(struct snd_soc_dapm_widget *w,
 	u16 gain_reg;
 	u16 reg;
 	int val;
-	int offset_val = 0;
 
 	if (!(snd_soc_dapm_widget_name_cmp(w, "RX INT0 INTERP"))) {
 		reg = WCD9335_CDC_RX0_RX_PATH_CTL;
@@ -3337,7 +3334,6 @@ static int wcd9335_codec_enable_interpolator(struct snd_soc_dapm_widget *w,
 	case SND_SOC_DAPM_POST_PMU:
 		wcd9335_config_compander(comp, w->shift, event);
 		val = snd_soc_component_read(comp, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(comp, gain_reg, val);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
-- 
GitLab


From 4d0e8bdfa4a57099dc7230952a460903f2e2f8de Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Mon, 22 Jan 2024 10:11:30 +0100
Subject: [PATCH 3223/4076] ASoC: codecs: wcd938x: fix headphones volume
 controls

The lowest headphones volume setting does not mute so the leave the TLV
mute flag unset.

This is specifically needed to let the sound server use the lowest gain
setting.

Fixes: c03226ba15fe ("ASoC: codecs: wcd938x: fix dB range for HPHL and HPHR")
Cc:  <stable@vger.kernel.org>      # 6.5
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://msgid.link/r/20240122091130.27463-1-johan+linaro@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wcd938x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index faf8d3f9b3c5d..98055dd39b782 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -210,7 +210,7 @@ struct wcd938x_priv {
 };
 
 static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(ear_pa_gain, 600, -1800);
-static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, -3000);
+static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(analog_gain, 0, 3000);
 
 struct wcd938x_mbhc_zdet_param {
-- 
GitLab


From 1d565de8d53cfa823576abac84e82ab1561f04eb Mon Sep 17 00:00:00 2001
From: Venkata Prasad Potturu <venkataprasad.potturu@amd.com>
Date: Thu, 18 Jan 2024 20:00:19 +0530
Subject: [PATCH 3224/4076] ASoC: amd: acp: Enable rt5682s clocks in acp slave
 mode

Set and enable rt5682s codec bclk and lrclk rates when
acp is in slave mode.

Signed-off-by: Venkata Prasad Potturu <venkataprasad.potturu@amd.com>
Link: https://msgid.link/r/20240118143023.1903984-1-venkataprasad.potturu@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp-mach-common.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c
index c90ec34192477..a224043ccd425 100644
--- a/sound/soc/amd/acp/acp-mach-common.c
+++ b/sound/soc/amd/acp/acp-mach-common.c
@@ -505,6 +505,13 @@ static int acp_card_rt5682s_hw_params(struct snd_pcm_substream *substream,
 
 	clk_set_rate(drvdata->wclk, srate);
 	clk_set_rate(drvdata->bclk, srate * ch * format);
+	if (!drvdata->soc_mclk) {
+		ret = acp_clk_enable(drvdata, srate, ch * format);
+		if (ret < 0) {
+			dev_err(rtd->card->dev, "Failed to enable HS clk: %d\n", ret);
+			return ret;
+		}
+	}
 
 	return 0;
 }
-- 
GitLab


From 4bae2029ffcccfbefb8f31563556494464e7bf2d Mon Sep 17 00:00:00 2001
From: Venkata Prasad Potturu <venkataprasad.potturu@amd.com>
Date: Thu, 18 Jan 2024 20:00:20 +0530
Subject: [PATCH 3225/4076] ASoC: amd: acp: Update platform name for different
 boards

Update platform name for various boards based on rembrandt
and renoir platforms.

Signed-off-by: Venkata Prasad Potturu <venkataprasad.potturu@amd.com>
Link: https://msgid.link/r/20240118143023.1903984-2-venkataprasad.potturu@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp-sof-mach.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c
index 2a9fd3275e42f..20b94814a0462 100644
--- a/sound/soc/amd/acp/acp-sof-mach.c
+++ b/sound/soc/amd/acp/acp-sof-mach.c
@@ -48,6 +48,7 @@ static struct acp_card_drvdata sof_rt5682s_rt1019_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = RT1019,
 	.dmic_codec_id = DMIC,
+	.platform = RENOIR,
 	.tdm_mode = false,
 };
 
@@ -58,6 +59,7 @@ static struct acp_card_drvdata sof_rt5682s_max_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = MAX98360A,
 	.dmic_codec_id = DMIC,
+	.platform = RENOIR,
 	.tdm_mode = false,
 };
 
@@ -68,6 +70,7 @@ static struct acp_card_drvdata sof_nau8825_data = {
 	.hs_codec_id = NAU8825,
 	.amp_codec_id = MAX98360A,
 	.dmic_codec_id = DMIC,
+	.platform = REMBRANDT,
 	.soc_mclk = true,
 	.tdm_mode = false,
 };
@@ -79,6 +82,7 @@ static struct acp_card_drvdata sof_rt5682s_hs_rt1019_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = RT1019,
 	.dmic_codec_id = DMIC,
+	.platform = REMBRANDT,
 	.soc_mclk = true,
 	.tdm_mode = false,
 };
-- 
GitLab


From 6cc2aa9a75f2397d42b78d4c159bc06722183c78 Mon Sep 17 00:00:00 2001
From: Venkata Prasad Potturu <venkataprasad.potturu@amd.com>
Date: Thu, 18 Jan 2024 20:00:21 +0530
Subject: [PATCH 3226/4076] ASoC: amd: acp: Add check for cpu dai link
 initialization

Add condition check for cpu dai link initialization for amplifier
codec path, as same pcm id uses for both headset and speaker path
for RENOIR platforms.

Signed-off-by: Venkata Prasad Potturu <venkataprasad.potturu@amd.com>
Link: https://msgid.link/r/20240118143023.1903984-3-venkataprasad.potturu@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp-mach-common.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c
index a224043ccd425..504d1b8c4cbb4 100644
--- a/sound/soc/amd/acp/acp-mach-common.c
+++ b/sound/soc/amd/acp/acp-mach-common.c
@@ -1471,8 +1471,13 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card)
 	if (drv_data->amp_cpu_id == I2S_SP) {
 		links[i].name = "acp-amp-codec";
 		links[i].id = AMP_BE_ID;
-		links[i].cpus = sof_sp_virtual;
-		links[i].num_cpus = ARRAY_SIZE(sof_sp_virtual);
+		if (drv_data->platform == RENOIR) {
+			links[i].cpus = sof_sp;
+			links[i].num_cpus = ARRAY_SIZE(sof_sp);
+		} else {
+			links[i].cpus = sof_sp_virtual;
+			links[i].num_cpus = ARRAY_SIZE(sof_sp_virtual);
+		}
 		links[i].platforms = sof_component;
 		links[i].num_platforms = ARRAY_SIZE(sof_component);
 		links[i].dpcm_playback = 1;
-- 
GitLab


From 086df711d9b886194481b4fbe525eb43e9ae7403 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 17 Jan 2024 16:12:06 +0100
Subject: [PATCH 3227/4076] ASoC: codecs: wcd938x: handle deferred probe

WCD938x sound codec driver ignores return status of getting regulators
and returns EINVAL instead of EPROBE_DEFER.  If regulator provider
probes after the codec, system is left without probed audio:

  wcd938x_codec audio-codec: wcd938x_probe: Fail to obtain platform data
  wcd938x_codec: probe of audio-codec failed with error -22

Fixes: 16572522aece ("ASoC: codecs: wcd938x-sdw: add SoundWire driver")
Cc:  <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://msgid.link/r/20240117151208.1219755-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wcd938x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index 98055dd39b782..75834ed0365d9 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -3589,7 +3589,7 @@ static int wcd938x_probe(struct platform_device *pdev)
 	ret = wcd938x_populate_dt_data(wcd938x, dev);
 	if (ret) {
 		dev_err(dev, "%s: Fail to obtain platform data\n", __func__);
-		return -EINVAL;
+		return ret;
 	}
 
 	ret = wcd938x_add_slave_components(wcd938x, dev, &match);
-- 
GitLab


From 22221b13d0c20a9791dec33121df73fe0b2ac226 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 17 Jan 2024 16:12:07 +0100
Subject: [PATCH 3228/4076] ASoC: codecs: wcd938x: skip printing deferred probe
 failuers

Probe calls wcd938x_populate_dt_data() which already prints all the
error cases with dev_err_probe(), so skip the additional dev_err().

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://msgid.link/r/20240117151208.1219755-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wcd938x.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index 75834ed0365d9..6021aa5a56891 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -3587,10 +3587,8 @@ static int wcd938x_probe(struct platform_device *pdev)
 	mutex_init(&wcd938x->micb_lock);
 
 	ret = wcd938x_populate_dt_data(wcd938x, dev);
-	if (ret) {
-		dev_err(dev, "%s: Fail to obtain platform data\n", __func__);
+	if (ret)
 		return ret;
-	}
 
 	ret = wcd938x_add_slave_components(wcd938x, dev, &match);
 	if (ret)
-- 
GitLab


From 35314e39dabcfb256832654ad0e856a9fba744bd Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 17 Jan 2024 16:12:08 +0100
Subject: [PATCH 3229/4076] ASoC: codecs: wcd934x: drop unneeded regulator
 include

Driver does not use any regulator code, so drop redundant include of
regulator/consumer.h header.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://msgid.link/r/20240117151208.1219755-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wcd934x.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c
index 1b6e376f3833c..6813268e6a19f 100644
--- a/sound/soc/codecs/wcd934x.c
+++ b/sound/soc/codecs/wcd934x.c
@@ -13,7 +13,6 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
-#include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 #include <linux/slimbus.h>
 #include <sound/pcm_params.h>
-- 
GitLab


From 70b4769956651e986591dd94b3ff9649122b1513 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 17 Jan 2024 17:01:44 +0100
Subject: [PATCH 3230/4076] ASoC: allow up to eight CPU/codec DAIs

Sound card on Qualcomm X1E80100 CRD board will use eight DAIs in one DAI
link, so increase the limit.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://msgid.link/r/20240117160144.1305127-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index f8524b5bfb330..516350533e73f 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1037,7 +1037,7 @@ component_dai_empty:
 	return -EINVAL;
 }
 
-#define MAX_DEFAULT_CH_MAP_SIZE 7
+#define MAX_DEFAULT_CH_MAP_SIZE 8
 static struct snd_soc_dai_link_ch_map default_ch_map_sync[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
 	{ .cpu = 1, .codec = 1 },
@@ -1046,6 +1046,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_sync[MAX_DEFAULT_CH_MAP_SIZ
 	{ .cpu = 4, .codec = 4 },
 	{ .cpu = 5, .codec = 5 },
 	{ .cpu = 6, .codec = 6 },
+	{ .cpu = 7, .codec = 7 },
 };
 static struct snd_soc_dai_link_ch_map default_ch_map_1cpu[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
@@ -1055,6 +1056,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_1cpu[MAX_DEFAULT_CH_MAP_SIZ
 	{ .cpu = 0, .codec = 4 },
 	{ .cpu = 0, .codec = 5 },
 	{ .cpu = 0, .codec = 6 },
+	{ .cpu = 0, .codec = 7 },
 };
 static struct snd_soc_dai_link_ch_map default_ch_map_1codec[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
@@ -1064,6 +1066,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_1codec[MAX_DEFAULT_CH_MAP_S
 	{ .cpu = 4, .codec = 0 },
 	{ .cpu = 5, .codec = 0 },
 	{ .cpu = 6, .codec = 0 },
+	{ .cpu = 7, .codec = 0 },
 };
 static int snd_soc_compensate_channel_connection_map(struct snd_soc_card *card,
 						     struct snd_soc_dai_link *dai_link)
-- 
GitLab


From c92688cac239794e4a1d976afa5203a4d3a2ac0e Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sat, 13 Jan 2024 23:46:26 +0100
Subject: [PATCH 3231/4076] regulator: pwm-regulator: Add validity checks in
 continuous .get_voltage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Continuous regulators can be configured to operate only in a certain
duty cycle range (for example from 0..91%). Add a check to error out if
the duty cycle translates to an unsupported (or out of range) voltage.

Suggested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Link: https://msgid.link/r/20240113224628.377993-2-martin.blumenstingl@googlemail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pwm-regulator.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 698c420e0869b..226ca4c62673f 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -158,6 +158,9 @@ static int pwm_regulator_get_voltage(struct regulator_dev *rdev)
 	pwm_get_state(drvdata->pwm, &pstate);
 
 	voltage = pwm_get_relative_duty_cycle(&pstate, duty_unit);
+	if (voltage < min(max_uV_duty, min_uV_duty) ||
+	    voltage > max(max_uV_duty, min_uV_duty))
+		return -ENOTRECOVERABLE;
 
 	/*
 	 * The dutycycle for min_uV might be greater than the one for max_uV.
-- 
GitLab


From 6a7d11efd6915d80a025f2a0be4ae09d797b91ec Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sat, 13 Jan 2024 23:46:27 +0100
Subject: [PATCH 3232/4076] regulator: pwm-regulator: Calculate the output
 voltage for disabled PWMs

If a PWM output is disabled then it's voltage has to be calculated
based on a zero duty cycle (for normal polarity) or duty cycle being
equal to the PWM period (for inverted polarity). Add support for this
to pwm_regulator_get_voltage().

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Link: https://msgid.link/r/20240113224628.377993-3-martin.blumenstingl@googlemail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pwm-regulator.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 226ca4c62673f..d27b9a7a30c9b 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -157,6 +157,13 @@ static int pwm_regulator_get_voltage(struct regulator_dev *rdev)
 
 	pwm_get_state(drvdata->pwm, &pstate);
 
+	if (!pstate.enabled) {
+		if (pstate.polarity == PWM_POLARITY_INVERSED)
+			pstate.duty_cycle = pstate.period;
+		else
+			pstate.duty_cycle = 0;
+	}
+
 	voltage = pwm_get_relative_duty_cycle(&pstate, duty_unit);
 	if (voltage < min(max_uV_duty, min_uV_duty) ||
 	    voltage > max(max_uV_duty, min_uV_duty))
-- 
GitLab


From b3cbdcc191819b75c04178142e2d0d4c668f68c0 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sat, 13 Jan 2024 23:46:28 +0100
Subject: [PATCH 3233/4076] regulator: pwm-regulator: Manage boot-on with
 disabled PWM channels

Odroid-C1 uses a Monolithic Power Systems MP2161 controlled via PWM for
the VDDEE voltage supply of the Meson8b SoC. Commit 6b9352f3f8a1 ("pwm:
meson: modify and simplify calculation in meson_pwm_get_state") results
in my Odroid-C1 crashing with memory corruption in many different places
(seemingly at random). It turns out that this is due to a currently not
supported corner case.

The VDDEE regulator can generate between 860mV (duty cycle of ~91%) and
1140mV (duty cycle of 0%). We consider it to be enabled by the bootloader
(which is why it has the regulator-boot-on flag in .dts) as well as
being always-on (which is why it has the regulator-always-on flag in
.dts) because the VDDEE voltage is generally required for the Meson8b
SoC to work. The public S805 datasheet [0] states on page 17 (where "A5"
refers to the Cortex-A5 CPU cores):
  [...] So if EE domains is shut off, A5 memory is also shut off. That
  does not matter. Before EE power domain is shut off, A5 should be shut
  off at first.

It turns out that at least some bootloader versions are keeping the PWM
output disabled. This is not a problem due to the specific design of the
regulator: when the PWM output is disabled the output pin is pulled LOW,
effectively achieving a 0% duty cycle (which in return means that VDDEE
voltage is at 1140mV).

The problem comes when the pwm-regulator driver tries to initialize the
PWM output. To do so it reads the current state from the hardware, which
is:
  period: 3666ns
  duty cycle: 3333ns (= ~91%)
  enabled: false
Then those values are translated using the continuous voltage range to
860mV.
Later, when the regulator is being enabled (either by the regulator core
due to the always-on flag or first consumer - in this case the lima
driver for the Mali-450 GPU) the pwm-regulator driver tries to keep the
voltage (at 860mV) and just enable the PWM output. This is when things
start to go wrong as the typical voltage used for VDDEE is 1100mV.

Commit 6b9352f3f8a1 ("pwm: meson: modify and simplify calculation in
meson_pwm_get_state") triggers above condition as before that change
period and duty cycle were both at 0. Since the change to the pwm-meson
driver is considered correct the solution is to be found in the
pwm-regulator driver. Update the duty cycle during driver probe if the
regulator is flagged as boot-on so that a call to pwm_regulator_enable()
(by the regulator core during initialization of a regulator flagged with
boot-on) without any preceding call to pwm_regulator_set_voltage() does
not change the output voltage.

[0] https://dn.odroid.com/S805/Datasheet/S805_Datasheet%20V0.8%2020150126.pdf

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Link: https://msgid.link/r/20240113224628.377993-4-martin.blumenstingl@googlemail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pwm-regulator.c | 33 +++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index d27b9a7a30c9b..60cfcd741c2af 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -323,6 +323,32 @@ static int pwm_regulator_init_continuous(struct platform_device *pdev,
 	return 0;
 }
 
+static int pwm_regulator_init_boot_on(struct platform_device *pdev,
+				      struct pwm_regulator_data *drvdata,
+				      const struct regulator_init_data *init_data)
+{
+	struct pwm_state pstate;
+
+	if (!init_data->constraints.boot_on || drvdata->enb_gpio)
+		return 0;
+
+	pwm_get_state(drvdata->pwm, &pstate);
+	if (pstate.enabled)
+		return 0;
+
+	/*
+	 * Update the duty cycle so the output does not change
+	 * when the regulator core enables the regulator (and
+	 * thus the PWM channel).
+	 */
+	if (pstate.polarity == PWM_POLARITY_INVERSED)
+		pstate.duty_cycle = pstate.period;
+	else
+		pstate.duty_cycle = 0;
+
+	return pwm_apply_might_sleep(drvdata->pwm, &pstate);
+}
+
 static int pwm_regulator_probe(struct platform_device *pdev)
 {
 	const struct regulator_init_data *init_data;
@@ -382,6 +408,13 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = pwm_regulator_init_boot_on(pdev, drvdata, init_data);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to apply boot_on settings: %d\n",
+			ret);
+		return ret;
+	}
+
 	regulator = devm_regulator_register(&pdev->dev,
 					    &drvdata->desc, &config);
 	if (IS_ERR(regulator)) {
-- 
GitLab


From 6c314425b9ef6b247cefd0903e287eb072580c3b Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 22 Jan 2024 14:00:33 +0200
Subject: [PATCH 3234/4076] spi: intel-pci: Remove Meteor Lake-S SoC PCI ID
 from the list

Turns out this "SoC" side controller does not support certain commands,
such as reading chip JEDEC ID, so the controller is pretty much unusable
in Linux. We should be using the "PCH" side controller instead. For this
reason remove this PCI ID from the list.

Fixes: c2912d42e86e ("spi: intel-pci: Add support for Meteor Lake-S SPI serial flash")
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://msgid.link/r/20240122120034.2664812-2-mika.westerberg@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-intel-pci.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c
index 57d767a68e7b2..b9918dcc38027 100644
--- a/drivers/spi/spi-intel-pci.c
+++ b/drivers/spi/spi-intel-pci.c
@@ -84,7 +84,6 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0xa2a4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info },
-	{ PCI_VDEVICE(INTEL, 0xae23), (unsigned long)&cnl_info },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids);
-- 
GitLab


From 8afe3c7fcaf72fca1e7d3dab16a5b7f4201ece17 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 22 Jan 2024 14:00:34 +0200
Subject: [PATCH 3235/4076] spi: intel-pci: Add support for Arrow Lake SPI
 serial flash

This adds the PCI ID of the Arrow Lake and Meteor Lake-S PCH SPI serial
flash controller. This one supports all the necessary commands Linux
SPI-NOR stack requires.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://msgid.link/r/20240122120034.2664812-3-mika.westerberg@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-intel-pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c
index b9918dcc38027..07d20ca1164c3 100644
--- a/drivers/spi/spi-intel-pci.c
+++ b/drivers/spi/spi-intel-pci.c
@@ -76,6 +76,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0x7e23), (unsigned long)&cnl_info },
+	{ PCI_VDEVICE(INTEL, 0x7f24), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0x9d24), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0x9da4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&cnl_info },
-- 
GitLab


From 7777f47f2ea64efd1016262e7b59fab34adfb869 Mon Sep 17 00:00:00 2001
From: Li Lingfeng <lilingfeng3@huawei.com>
Date: Thu, 18 Jan 2024 21:04:01 +0800
Subject: [PATCH 3236/4076] block: Move checking GENHD_FL_NO_PART to
 bdev_add_partition()

Commit 1a721de8489f ("block: don't add or resize partition on the disk
with GENHD_FL_NO_PART") prevented all operations about partitions on disks
with GENHD_FL_NO_PART in blkpg_do_ioctl() since they are meaningless.
However, it changed error code in some scenarios. So move checking
GENHD_FL_NO_PART to bdev_add_partition() to eliminate impact.

Fixes: 1a721de8489f ("block: don't add or resize partition on the disk with GENHD_FL_NO_PART")
Reported-by: Allison Karlitskaya <allison.karlitskaya@redhat.com>
Closes: https://lore.kernel.org/all/CAOYeF9VsmqKMcQjo1k6YkGNujwN-nzfxY17N3F-CMikE1tYp+w@mail.gmail.com/
Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240118130401.792757-1-lilingfeng@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioctl.c           | 2 --
 block/partitions/core.c | 5 +++++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/block/ioctl.c b/block/ioctl.c
index 9c73a763ef883..438f79c564cfc 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -20,8 +20,6 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	struct blkpg_partition p;
 	sector_t start, length;
 
-	if (disk->flags & GENHD_FL_NO_PART)
-		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
diff --git a/block/partitions/core.c b/block/partitions/core.c
index cab0d76a828e3..5f5ed5c75f04d 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -439,6 +439,11 @@ int bdev_add_partition(struct gendisk *disk, int partno, sector_t start,
 		goto out;
 	}
 
+	if (disk->flags & GENHD_FL_NO_PART) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (partition_overlaps(disk, start, length, -1)) {
 		ret = -EBUSY;
 		goto out;
-- 
GitLab


From 4d5b7daa3c610af3f322ad1e91fc0c752ff32f0e Mon Sep 17 00:00:00 2001
From: Hsin-Yi Wang <hsinyi@chromium.org>
Date: Wed, 17 Jan 2024 17:58:14 -0800
Subject: [PATCH 3237/4076] drm/bridge: anx7625: Ensure bridge is suspended in
 disable()

Similar to commit 26db46bc9c67 ("drm/bridge: parade-ps8640: Ensure bridge
is suspended in .post_disable()"). Add a mutex to ensure that aux transfer
won't race with atomic_disable by holding the PM reference and prevent
the bridge from suspend.

Also we need to use pm_runtime_put_sync_suspend() to suspend the bridge
instead of idle with pm_runtime_put_sync().

Fixes: 3203e497eb76 ("drm/bridge: anx7625: Synchronously run runtime suspend.")
Fixes: adca62ec370c ("drm/bridge: anx7625: Support reading edid through aux channel")
Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
Tested-by: Xuxin Xiong <xuxinxiong@huaqin.corp-partner.google.com>
Reviewed-by: Pin-yen Lin <treapking@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240118015916.2296741-1-hsinyi@chromium.org
---
 drivers/gpu/drm/bridge/analogix/anx7625.c | 7 ++++++-
 drivers/gpu/drm/bridge/analogix/anx7625.h | 2 ++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c
index ef31033439bc1..29d91493b101a 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.c
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.c
@@ -1762,6 +1762,7 @@ static ssize_t anx7625_aux_transfer(struct drm_dp_aux *aux,
 	u8 request = msg->request & ~DP_AUX_I2C_MOT;
 	int ret = 0;
 
+	mutex_lock(&ctx->aux_lock);
 	pm_runtime_get_sync(dev);
 	msg->reply = 0;
 	switch (request) {
@@ -1778,6 +1779,7 @@ static ssize_t anx7625_aux_transfer(struct drm_dp_aux *aux,
 					msg->size, msg->buffer);
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
+	mutex_unlock(&ctx->aux_lock);
 
 	return ret;
 }
@@ -2474,7 +2476,9 @@ static void anx7625_bridge_atomic_disable(struct drm_bridge *bridge,
 	ctx->connector = NULL;
 	anx7625_dp_stop(ctx);
 
-	pm_runtime_put_sync(dev);
+	mutex_lock(&ctx->aux_lock);
+	pm_runtime_put_sync_suspend(dev);
+	mutex_unlock(&ctx->aux_lock);
 }
 
 static enum drm_connector_status
@@ -2668,6 +2672,7 @@ static int anx7625_i2c_probe(struct i2c_client *client)
 
 	mutex_init(&platform->lock);
 	mutex_init(&platform->hdcp_wq_lock);
+	mutex_init(&platform->aux_lock);
 
 	INIT_DELAYED_WORK(&platform->hdcp_work, hdcp_check_work_func);
 	platform->hdcp_workqueue = create_workqueue("hdcp workqueue");
diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.h b/drivers/gpu/drm/bridge/analogix/anx7625.h
index 66ebee7f3d832..39ed35d338363 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.h
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.h
@@ -475,6 +475,8 @@ struct anx7625_data {
 	struct workqueue_struct *hdcp_workqueue;
 	/* Lock for hdcp work queue */
 	struct mutex hdcp_wq_lock;
+	/* Lock for aux transfer and disable */
+	struct mutex aux_lock;
 	char edid_block;
 	struct display_timing dt;
 	u8 display_timing_valid;
-- 
GitLab


From 1a84c213146a06aca1fd0e5b376ab7d36d15e1b3 Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Tue, 14 Nov 2023 15:10:33 +0700
Subject: [PATCH 3238/4076] drm/dp_mst: Separate @failing_port list in
 drm_dp_mst_atomic_check_mgr() comment

Stephen Rothwell reported htmldocs warnings when merging drm-intel
tree:

Documentation/gpu/drm-kms-helpers:296: drivers/gpu/drm/display/drm_dp_mst_topology.c:5484: ERROR: Unexpected indentation.
Documentation/gpu/drm-kms-helpers:296: drivers/gpu/drm/display/drm_dp_mst_topology.c:5488: WARNING: Block quote ends without a blank line; unexpected unindent.

Separate @failing_port return value list by surrounding it with a
blank line to fix above warnings.

Fixes: 1cd0a5ea427931 ("drm/dp_mst: Factor out a helper to check the atomic state of a topology manager")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/linux-next/20231114141715.6f435118@canb.auug.org.au/
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231114081033.27343-1-bagasdotme@gmail.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/display/drm_dp_mst_topology.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
index bd6c24d4213cd..f7c6b60629c2b 100644
--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -5491,6 +5491,7 @@ EXPORT_SYMBOL(drm_dp_mst_atomic_enable_dsc);
  *   - 0 if the new state is valid
  *   - %-ENOSPC, if the new state is invalid, because of BW limitation
  *         @failing_port is set to:
+ *
  *         - The non-root port where a BW limit check failed
  *           with all the ports downstream of @failing_port passing
  *           the BW limit check.
@@ -5499,6 +5500,7 @@ EXPORT_SYMBOL(drm_dp_mst_atomic_enable_dsc);
  *         - %NULL if the BW limit check failed at the root port
  *           with all the ports downstream of the root port passing
  *           the BW limit check.
+ *
  *   - %-EINVAL, if the new state is invalid, because the root port has
  *     too many payloads.
  */
-- 
GitLab


From 612e1110d689387aab81b2727895cd307d3cbbfd Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 22 Jan 2024 12:25:00 -0500
Subject: [PATCH 3239/4076] bcachefs: Add gfp flags param to
 bch2_prt_task_backtrace()

Fixes: e6a2566f7a00 ("bcachefs: Better journal tracepoints")
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Reported-by: smatch
---
 fs/bcachefs/btree_locking.c |  4 ++--
 fs/bcachefs/debug.c         |  2 +-
 fs/bcachefs/journal.c       |  2 +-
 fs/bcachefs/util.c          | 10 +++++-----
 fs/bcachefs/util.h          |  4 ++--
 5 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index bed75c93c0690..6843974423381 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -92,7 +92,7 @@ static noinline void print_cycle(struct printbuf *out, struct lock_graph *g)
 			continue;
 
 		bch2_btree_trans_to_text(out, i->trans);
-		bch2_prt_task_backtrace(out, task, i == g->g ? 5 : 1);
+		bch2_prt_task_backtrace(out, task, i == g->g ? 5 : 1, GFP_NOWAIT);
 	}
 }
 
@@ -227,7 +227,7 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle)
 			prt_printf(&buf, "backtrace:");
 			prt_newline(&buf);
 			printbuf_indent_add(&buf, 2);
-			bch2_prt_task_backtrace(&buf, trans->locking_wait.task, 2);
+			bch2_prt_task_backtrace(&buf, trans->locking_wait.task, 2, GFP_NOWAIT);
 			printbuf_indent_sub(&buf, 2);
 			prt_newline(&buf);
 		}
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index cadda9bbe4a4c..7bdba8507fc93 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -627,7 +627,7 @@ restart:
 		prt_printf(&i->buf, "backtrace:");
 		prt_newline(&i->buf);
 		printbuf_indent_add(&i->buf, 2);
-		bch2_prt_task_backtrace(&i->buf, task, 0);
+		bch2_prt_task_backtrace(&i->buf, task, 0, GFP_KERNEL);
 		printbuf_indent_sub(&i->buf, 2);
 		prt_newline(&i->buf);
 
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index d71d26e39521e..bc890776eb579 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -233,7 +233,7 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val, bool t
 		prt_str(&pbuf, "entry size: ");
 		prt_human_readable_u64(&pbuf, vstruct_bytes(buf->data));
 		prt_newline(&pbuf);
-		bch2_prt_task_backtrace(&pbuf, current, 1);
+		bch2_prt_task_backtrace(&pbuf, current, 1, GFP_NOWAIT);
 		trace_journal_entry_close(c, pbuf.buf);
 		printbuf_exit(&pbuf);
 	}
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index a135136adeee3..56b815fd9fc6e 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -272,14 +272,14 @@ void bch2_print_string_as_lines(const char *prefix, const char *lines)
 	console_unlock();
 }
 
-int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigned skipnr)
+int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigned skipnr,
+			gfp_t gfp)
 {
 #ifdef CONFIG_STACKTRACE
 	unsigned nr_entries = 0;
-	int ret = 0;
 
 	stack->nr = 0;
-	ret = darray_make_room(stack, 32);
+	int ret = darray_make_room_gfp(stack, 32, gfp);
 	if (ret)
 		return ret;
 
@@ -308,10 +308,10 @@ void bch2_prt_backtrace(struct printbuf *out, bch_stacktrace *stack)
 	}
 }
 
-int bch2_prt_task_backtrace(struct printbuf *out, struct task_struct *task, unsigned skipnr)
+int bch2_prt_task_backtrace(struct printbuf *out, struct task_struct *task, unsigned skipnr, gfp_t gfp)
 {
 	bch_stacktrace stack = { 0 };
-	int ret = bch2_save_backtrace(&stack, task, skipnr + 1);
+	int ret = bch2_save_backtrace(&stack, task, skipnr + 1, gfp);
 
 	bch2_prt_backtrace(out, &stack);
 	darray_exit(&stack);
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index df67bf55fe2bc..b414736d59a5b 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -348,9 +348,9 @@ void bch2_prt_u64_base2(struct printbuf *, u64);
 void bch2_print_string_as_lines(const char *prefix, const char *lines);
 
 typedef DARRAY(unsigned long) bch_stacktrace;
-int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned);
+int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned, gfp_t);
 void bch2_prt_backtrace(struct printbuf *, bch_stacktrace *);
-int bch2_prt_task_backtrace(struct printbuf *, struct task_struct *, unsigned);
+int bch2_prt_task_backtrace(struct printbuf *, struct task_struct *, unsigned, gfp_t);
 
 static inline void prt_bdevname(struct printbuf *out, struct block_device *bdev)
 {
-- 
GitLab


From 3e44f325f6f75078cdcd44cd337f517ba3650d05 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 11 Jan 2024 08:36:55 +0100
Subject: [PATCH 3240/4076] bcachefs: fix incorrect usage of REQ_OP_FLUSH

REQ_OP_FLUSH is only for internal use in the blk-mq and request based
drivers. File systems and other block layer consumers must use
REQ_OP_WRITE | REQ_PREFLUSH as documented in
Documentation/block/writeback_cache_control.rst.

While REQ_OP_FLUSH appears to work for blk-mq drivers it does not
get the proper flush state machine handling, and completely fails
for any bio based drivers, including all the stacking drivers.  The
block layer will also get a check in 6.8 to reject this use case
entirely.

[Note: completely untested, but as this never got fixed since the
original bug report in November:

   https://bugzilla.kernel.org/show_bug.cgi?id=218184

and the the discussion in December:

    https://lore.kernel.org/all/20231221053016.72cqcfg46vxwohcj@moria.home.lan/T/

this seems to be best way to force it]

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs-io.c      | 2 +-
 fs/bcachefs/journal_io.c | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index dc52918d06ef3..8c70123b6a0c8 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -79,7 +79,7 @@ void bch2_inode_flush_nocow_writes_async(struct bch_fs *c,
 			continue;
 
 		bio = container_of(bio_alloc_bioset(ca->disk_sb.bdev, 0,
-						    REQ_OP_FLUSH,
+						    REQ_OP_WRITE|REQ_PREFLUSH,
 						    GFP_KERNEL,
 						    &c->nocow_flush_bioset),
 				   struct nocow_flush, bio);
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 04a1e79a5ed39..bfd6585e746da 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -1988,7 +1988,8 @@ CLOSURE_CALLBACK(bch2_journal_write)
 			percpu_ref_get(&ca->io_ref);
 
 			bio = ca->journal.bio;
-			bio_reset(bio, ca->disk_sb.bdev, REQ_OP_FLUSH);
+			bio_reset(bio, ca->disk_sb.bdev,
+				  REQ_OP_WRITE|REQ_PREFLUSH);
 			bio->bi_end_io		= journal_write_endio;
 			bio->bi_private		= ca;
 			closure_bio_submit(bio, cl);
-- 
GitLab


From d53271c05965b4469c57a18c66585075df81c504 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Thu, 11 Jan 2024 10:49:22 -0500
Subject: [PATCH 3241/4076] selftests/rseq: Do not skip !allowed_cpus for
 mm_cid

Indexing with mm_cid is incompatible with skipping disallowed cpumask,
because concurrency IDs are based on a virtual ID allocation which is
unrelated to the physical CPU mask.

These issues can be reproduced by running the rseq selftests under a
taskset which excludes CPU 0, e.g.

  taskset -c 10-20 ./run_param_test.sh

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .../selftests/rseq/basic_percpu_ops_test.c    | 14 ++++++++++--
 tools/testing/selftests/rseq/param_test.c     | 22 ++++++++++++++-----
 2 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
index 8875429619687..2348d2c20d0a1 100644
--- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -24,6 +24,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_mm_cid_available();
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return false;	/* Use mm_cid */
+}
 #else
 # define RSEQ_PERCPU	RSEQ_PERCPU_CPU_ID
 static
@@ -36,6 +41,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_current_cpu_raw() >= 0;
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return true;	/* Use cpu_id as index. */
+}
 #endif
 
 struct percpu_lock_entry {
@@ -274,7 +284,7 @@ void test_percpu_list(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		for (j = 1; j <= 100; j++) {
 			struct percpu_list_node *node;
@@ -299,7 +309,7 @@ void test_percpu_list(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_list_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_list_pop(&list, i))) {
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 20403d58345cd..2f37961240caa 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -288,6 +288,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_mm_cid_available();
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return false;	/* Use mm_cid */
+}
 # ifdef TEST_MEMBARRIER
 /*
  * Membarrier does not currently support targeting a mm_cid, so
@@ -312,6 +317,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_current_cpu_raw() >= 0;
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return true;	/* Use cpu_id as index. */
+}
 # ifdef TEST_MEMBARRIER
 static
 int rseq_membarrier_expedited(int cpu)
@@ -715,7 +725,7 @@ void test_percpu_list(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		for (j = 1; j <= 100; j++) {
 			struct percpu_list_node *node;
@@ -752,7 +762,7 @@ void test_percpu_list(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_list_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_list_pop(&list, i))) {
@@ -902,7 +912,7 @@ void test_percpu_buffer(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		/* Worse-case is every item in same CPU. */
 		buffer.c[i].array =
@@ -952,7 +962,7 @@ void test_percpu_buffer(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_buffer_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_buffer_pop(&buffer, i))) {
@@ -1113,7 +1123,7 @@ void test_percpu_memcpy_buffer(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		/* Worse-case is every item in same CPU. */
 		buffer.c[i].array =
@@ -1160,7 +1170,7 @@ void test_percpu_memcpy_buffer(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_memcpy_buffer_node item;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while (__percpu_memcpy_buffer_pop(&buffer, &item, i)) {
-- 
GitLab


From 68deb9972079c9904fe714c049a7f08bd997a9ee Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 16 Jan 2024 13:17:17 -0800
Subject: [PATCH 3242/4076] tools/testing/cxl: Disable "missing prototypes /
 declarations" warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prevent warnings of the form:

tools/testing/cxl/test/mock.c:44:6: error: no previous prototype for
‘__wrap_is_acpi_device_node’ [-Werror=missing-prototypes]

tools/testing/cxl/test/mock.c:63:5: error: no previous prototype for
‘__wrap_acpi_table_parse_cedt’ [-Werror=missing-prototypes]

tools/testing/cxl/test/mock.c:81:13: error: no previous prototype for
‘__wrap_acpi_evaluate_integer’ [-Werror=missing-prototypes]

...by locally disabling some warnings.

It turns out that:

Commit 0fcb70851fbf ("Makefile.extrawarn: turn on missing-prototypes globally")

...in addition to expanding in-tree coverage, also impacts out-of-tree
module builds like those in tools/testing/cxl/.

Filter out the warning options on unit test code that does not effect
mainline builds.

Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Link: https://lore.kernel.org/r/170543983780.460832.10920261849128601697.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/cxl/Kbuild      | 2 ++
 tools/testing/cxl/test/Kbuild | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 0b12c36902d82..caff3834671f9 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -65,4 +65,6 @@ cxl_core-y += config_check.o
 cxl_core-y += cxl_core_test.o
 cxl_core-y += cxl_core_exports.o
 
+KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS))
+
 obj-m += test/
diff --git a/tools/testing/cxl/test/Kbuild b/tools/testing/cxl/test/Kbuild
index 61d5f7bcddf9a..6b19278978561 100644
--- a/tools/testing/cxl/test/Kbuild
+++ b/tools/testing/cxl/test/Kbuild
@@ -8,3 +8,5 @@ obj-m += cxl_mock_mem.o
 cxl_test-y := cxl.o
 cxl_mock-y := mock.o
 cxl_mock_mem-y := mem.o
+
+KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS))
-- 
GitLab


From c97dac57c804b53eab492ca0230d86356729d633 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 16 Jan 2024 13:17:23 -0800
Subject: [PATCH 3243/4076] tools/testing/nvdimm: Disable "missing prototypes /
 declarations" warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prevent warnings of the form:

tools/testing/nvdimm/config_check.c:4:6: error: no previous prototype
for ‘check’ [-Werror=missing-prototypes]

...by locally disabling some warnings.

It turns out that:

Commit 0fcb70851fbf ("Makefile.extrawarn: turn on missing-prototypes globally")

...in addition to expanding in-tree coverage, also impacts out-of-tree
module builds like those in tools/testing/nvdimm/.

Filter out the warning options on unit test code that does not effect
mainline builds.

Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Link: https://lore.kernel.org/r/170543984331.460832.1780246477583036191.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/Kbuild | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 8153251ea389a..91a3627f301a7 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -82,4 +82,6 @@ libnvdimm-$(CONFIG_NVDIMM_KEYS) += $(NVDIMM_SRC)/security.o
 libnvdimm-y += libnvdimm_test.o
 libnvdimm-y += config_check.o
 
+KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS))
+
 obj-m += test/
-- 
GitLab


From d72a4caf685989e353dff0a97d7376ee10edbf87 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 17 Jan 2024 17:24:01 -0800
Subject: [PATCH 3244/4076] cxl/pci: Skip irq features if MSI/MSI-X are not
 supported

CXL 3.1 Section 3.1.1 states:

	"A Function on a CXL device must not generate INTx messages if
	that Function participates in CXL.cache protocol or CXL.mem
	protocols."

The generic CXL memory driver only supports devices which use the
CXL.mem protocol.  The current driver attempts to allocate MSI/MSI-X
vectors in anticipation of their need for mailbox interrupts or event
processing.  However, the above requirement does not require a device to
support interrupts, only that they use MSI/MSI-X.  For example, a device
may disable mailbox interrupts and either be configured for firmware
first or skip event processing and function.

Dave Larsen reported that the following Intel / Agilex card does not
support interrupts on function 0.

	CXL: Intel Corporation Device 0ddb (rev 01) (prog-if 10 [CXL Memory Device (CXL 2.x)])

Rather than fail device probe if interrupts are not supported; flag that
irqs are not enabled and avoid features which require interrupts.
Emit messages appropriate for the situation to aid in debugging should
device behavior be unexpected due to a failure to allocate vectors.

Note that it is possible for a device to have host based event
processing through polling.  However, the driver does not support
polling and it is not anticipated to be generally required.  Leave that
functionality to a future patch if such a device comes along.

Reported-by: Dave Larsen <davelarsen58@gmail.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Fan Ni <fan.ni@samsung.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-and-tested-by: Davidlohr Bueso <dave@stgolabs.net>
Link: https://lore.kernel.org/r/20240117-dont-fail-irq-v2-1-f33f26b0e365@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/pci.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 4fd1f207c84ee..233e7c42c161d 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -382,7 +382,7 @@ static int cxl_pci_mbox_send(struct cxl_memdev_state *mds,
 	return rc;
 }
 
-static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds)
+static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail)
 {
 	struct cxl_dev_state *cxlds = &mds->cxlds;
 	const int cap = readl(cxlds->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET);
@@ -441,7 +441,7 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds)
 	INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work);
 
 	/* background command interrupts are optional */
-	if (!(cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ))
+	if (!(cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ) || !irq_avail)
 		return 0;
 
 	msgnum = FIELD_GET(CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK, cap);
@@ -588,7 +588,7 @@ static int cxl_mem_alloc_event_buf(struct cxl_memdev_state *mds)
 	return devm_add_action_or_reset(mds->cxlds.dev, free_event_buf, buf);
 }
 
-static int cxl_alloc_irq_vectors(struct pci_dev *pdev)
+static bool cxl_alloc_irq_vectors(struct pci_dev *pdev)
 {
 	int nvecs;
 
@@ -605,9 +605,9 @@ static int cxl_alloc_irq_vectors(struct pci_dev *pdev)
 				      PCI_IRQ_MSIX | PCI_IRQ_MSI);
 	if (nvecs < 1) {
 		dev_dbg(&pdev->dev, "Failed to alloc irq vectors: %d\n", nvecs);
-		return -ENXIO;
+		return false;
 	}
-	return 0;
+	return true;
 }
 
 static irqreturn_t cxl_event_thread(int irq, void *id)
@@ -743,7 +743,7 @@ static bool cxl_event_int_is_fw(u8 setting)
 }
 
 static int cxl_event_config(struct pci_host_bridge *host_bridge,
-			    struct cxl_memdev_state *mds)
+			    struct cxl_memdev_state *mds, bool irq_avail)
 {
 	struct cxl_event_interrupt_policy policy;
 	int rc;
@@ -755,6 +755,11 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge,
 	if (!host_bridge->native_cxl_error)
 		return 0;
 
+	if (!irq_avail) {
+		dev_info(mds->cxlds.dev, "No interrupt support, disable event processing.\n");
+		return 0;
+	}
+
 	rc = cxl_mem_alloc_event_buf(mds);
 	if (rc)
 		return rc;
@@ -789,6 +794,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct cxl_register_map map;
 	struct cxl_memdev *cxlmd;
 	int i, rc, pmu_count;
+	bool irq_avail;
 
 	/*
 	 * Double check the anonymous union trickery in struct cxl_regs
@@ -846,11 +852,9 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	else
 		dev_warn(&pdev->dev, "Media not active (%d)\n", rc);
 
-	rc = cxl_alloc_irq_vectors(pdev);
-	if (rc)
-		return rc;
+	irq_avail = cxl_alloc_irq_vectors(pdev);
 
-	rc = cxl_pci_setup_mailbox(mds);
+	rc = cxl_pci_setup_mailbox(mds, irq_avail);
 	if (rc)
 		return rc;
 
@@ -909,7 +913,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		}
 	}
 
-	rc = cxl_event_config(host_bridge, mds);
+	rc = cxl_event_config(host_bridge, mds, irq_avail);
 	if (rc)
 		return rc;
 
-- 
GitLab


From 27daa514c48d5796d564ea5410cb72f78a521891 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Wed, 6 Dec 2023 12:21:42 +0300
Subject: [PATCH 3245/4076] ELF, MAINTAINERS: specifically mention ELF

People complain when I miss people in Cc.

[ kees: Also add the ELF uapi doc link ]

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Link: https://lore.kernel.org/r/2cb0891e-d7c0-4939-bb5f-282812de6078@p183
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a692..39219b144c239 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7955,12 +7955,13 @@ L:	rust-for-linux@vger.kernel.org
 S:	Maintained
 F:	rust/kernel/net/phy.rs
 
-EXEC & BINFMT API
+EXEC & BINFMT API, ELF
 R:	Eric Biederman <ebiederm@xmission.com>
 R:	Kees Cook <keescook@chromium.org>
 L:	linux-mm@kvack.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
+F:	Documentation/userspace-api/ELF.rst
 F:	fs/*binfmt_*.c
 F:	fs/exec.c
 F:	include/linux/binfmts.h
-- 
GitLab


From 8788a17c2319f020ccdc3f2907179a5ae81b7ad6 Mon Sep 17 00:00:00 2001
From: Askar Safin <safinaskar@zohomail.com>
Date: Tue, 9 Jan 2024 06:04:34 +0300
Subject: [PATCH 3246/4076] exec: remove useless comment

Function name is wrong and the comment tells us nothing

Signed-off-by: Askar Safin <safinaskar@zohomail.com>
Link: https://lore.kernel.org/r/20240109030801.31827-1-safinaskar@zohomail.com
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/exec.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 8cdd5b2dd09c2..ba7d0548ac57f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1826,9 +1826,6 @@ static int exec_binprm(struct linux_binprm *bprm)
 	return 0;
 }
 
-/*
- * sys_execve() executes a new program.
- */
 static int bprm_execve(struct linux_binprm *bprm)
 {
 	int retval;
-- 
GitLab


From 22fb4f041999f5f16ecbda15a2859b4ef4cbf47e Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 19 Jan 2024 05:33:19 -0600
Subject: [PATCH 3247/4076] cpufreq/amd-pstate: Fix setting scaling max/min
 freq values

Scaling min/max freq values were being cached and lagging a setting
each time.  Fix the ordering of the clamp call to ensure they work.

Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217931
Fixes: febab20caeba ("cpufreq/amd-pstate: Fix scaling_min_freq and scaling_max_freq update")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Wyes Karny <wkarny@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/amd-pstate.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 1f6186475715e..1791d37fbc53c 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -1232,14 +1232,13 @@ static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
 	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
 
+	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
+
 	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
 			cpudata->max_limit_perf);
 	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
 			cpudata->max_limit_perf);
-
-	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
-	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
-
 	value = READ_ONCE(cpudata->cppc_req_cached);
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
-- 
GitLab


From 92c02d74ba7b7cdf3887ed56bc9af38c3ee17a8b Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Mon, 22 Jan 2024 14:20:27 +0800
Subject: [PATCH 3248/4076] ASoC: codecs: ES8326: Remove executable bit

Remove the executable bit that was unintentionally turned on.

Fixes: ee09084fbf9f ("ASoC: codecs: ES8326: Add chip version flag")
Signed-off-by: Fei Shao <fshao@chromium.org>
Link: https://msgid.link/r/20240122062055.1673597-1-fshao@chromium.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8326.c | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 mode change 100755 => 100644 sound/soc/codecs/es8326.c

diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
old mode 100755
new mode 100644
-- 
GitLab


From c481016bb4f8a9c059c39ac06e7b65e233a61f6a Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Mon, 22 Jan 2024 19:18:17 +0100
Subject: [PATCH 3249/4076] ASoC: qcom: sc8280xp: limit speaker volumes

The UCM configuration for the Lenovo ThinkPad X13s has up until now
been setting the speaker PA volume to the minimum -3 dB when enabling
the speakers, but this does not prevent the user from increasing the
volume further.

Limit the digital gain and PA volumes to a combined -3 dB in the machine
driver to reduce the risk of speaker damage until we have active speaker
protection in place (or higher safe levels have been established).

Note that the PA volume limit cannot be set lower than 0 dB or
PulseAudio gets confused when the first 16 levels all map to -3 dB.

Also note that this will probably need to be generalised using
machine-specific limits, but a common limit should do for now.

Cc:  <stable@vger.kernel.org>	# 6.5
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://msgid.link/r/20240122181819.4038-3-johan+linaro@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/sc8280xp.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c
index ed4bb551bfbb9..b7fd503a16666 100644
--- a/sound/soc/qcom/sc8280xp.c
+++ b/sound/soc/qcom/sc8280xp.c
@@ -32,12 +32,14 @@ static int sc8280xp_snd_init(struct snd_soc_pcm_runtime *rtd)
 	case WSA_CODEC_DMA_RX_0:
 	case WSA_CODEC_DMA_RX_1:
 		/*
-		 * set limit of 0dB on Digital Volume for Speakers,
-		 * this can prevent damage of speakers to some extent without
-		 * active speaker protection
+		 * Set limit of -3 dB on Digital Volume and 0 dB on PA Volume
+		 * to reduce the risk of speaker damage until we have active
+		 * speaker protection in place.
 		 */
-		snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 84);
-		snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 84);
+		snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 81);
+		snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 81);
+		snd_soc_limit_volume(card, "SpkrLeft PA Volume", 17);
+		snd_soc_limit_volume(card, "SpkrRight PA Volume", 17);
 		break;
 	default:
 		break;
-- 
GitLab


From bdd8f62431ebcf15902a5fce3336388e436405c6 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 16 Sep 2022 17:11:18 -0700
Subject: [PATCH 3250/4076] exec: Add do_close_execat() helper

Consolidate the calls to allow_write_access()/fput() into a single
place, since we repeat this code pattern. Add comments around the
callers for the details on it.

Link: https://lore.kernel.org/r/202209161637.9EDAF6B18@keescook
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/exec.c | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index ba7d0548ac57f..2037cc6360364 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -904,6 +904,10 @@ EXPORT_SYMBOL(transfer_args_to_stack);
 
 #endif /* CONFIG_MMU */
 
+/*
+ * On success, caller must call do_close_execat() on the returned
+ * struct file to close it.
+ */
 static struct file *do_open_execat(int fd, struct filename *name, int flags)
 {
 	struct file *file;
@@ -948,6 +952,17 @@ exit:
 	return ERR_PTR(err);
 }
 
+/**
+ * open_exec - Open a path name for execution
+ *
+ * @name: path name to open with the intent of executing it.
+ *
+ * Returns ERR_PTR on failure or allocated struct file on success.
+ *
+ * As this is a wrapper for the internal do_open_execat(), callers
+ * must call allow_write_access() before fput() on release. Also see
+ * do_close_execat().
+ */
 struct file *open_exec(const char *name)
 {
 	struct filename *filename = getname_kernel(name);
@@ -1484,6 +1499,15 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
 	return -ENOMEM;
 }
 
+/* Matches do_open_execat() */
+static void do_close_execat(struct file *file)
+{
+	if (!file)
+		return;
+	allow_write_access(file);
+	fput(file);
+}
+
 static void free_bprm(struct linux_binprm *bprm)
 {
 	if (bprm->mm) {
@@ -1495,10 +1519,7 @@ static void free_bprm(struct linux_binprm *bprm)
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
-	if (bprm->file) {
-		allow_write_access(bprm->file);
-		fput(bprm->file);
-	}
+	do_close_execat(bprm->file);
 	if (bprm->executable)
 		fput(bprm->executable);
 	/* If a binfmt changed the interp, free it. */
@@ -1520,8 +1541,7 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl
 
 	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
 	if (!bprm) {
-		allow_write_access(file);
-		fput(file);
+		do_close_execat(file);
 		return ERR_PTR(-ENOMEM);
 	}
 
-- 
GitLab


From 84c39ec57d409e803a9bb6e4e85daf1243e0e80b Mon Sep 17 00:00:00 2001
From: Bernd Edlinger <bernd.edlinger@hotmail.de>
Date: Mon, 22 Jan 2024 19:34:21 +0100
Subject: [PATCH 3251/4076] exec: Fix error handling in begin_new_exec()

If get_unused_fd_flags() fails, the error handling is incomplete because
bprm->cred is already set to NULL, and therefore free_bprm will not
unlock the cred_guard_mutex. Note there are two error conditions which
end up here, one before and one after bprm->cred is cleared.

Fixes: b8a61c9e7b4a ("exec: Generic execfd support")
Signed-off-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
Acked-by: Eric W. Biederman <ebiederm@xmission.com>
Link: https://lore.kernel.org/r/AS8P193MB128517ADB5EFF29E04389EDAE4752@AS8P193MB1285.EURP193.PROD.OUTLOOK.COM
Cc: stable@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/exec.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/exec.c b/fs/exec.c
index 2037cc6360364..39d773021fffd 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1424,6 +1424,9 @@ int begin_new_exec(struct linux_binprm * bprm)
 
 out_unlock:
 	up_write(&me->signal->exec_update_lock);
+	if (!bprm->cred)
+		mutex_unlock(&me->signal->cred_guard_mutex);
+
 out:
 	return retval;
 }
-- 
GitLab


From 73ae7e1c7644a8c33ba526302a10267cdbc249f8 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Thu, 11 Jan 2024 17:57:44 +0100
Subject: [PATCH 3252/4076] ata: libata-sata: improve sysfs description for
 ATA_LPM_UNKNOWN

Currently, both ATA_LPM_UNKNOWN (0) and ATA_LPM_MAX_POWER (1) displays
as "max_performance" in sysfs.

This is quite misleading as they are not the same.

For ATA_LPM_UNKNOWN, ata_eh_set_lpm() will not be called at all,
leaving the configuration in unknown state.
For ATA_LPM_MAX_POWER, ata_eh_set_lpm() is called, and setting the
policy to ATA_LPM_MAX_POWER.

This also matches the description of the SATA_MOBILE_LPM_POLICY Kconfig:
0 => Keep firmware settings
1 => Maximum performance

Thus, update the sysfs description for ATA_LPM_UNKNOWN to match reality.

While at it, update libata.h to mention that the ascii descriptions
are in libata-sata.c and not in libata-scsi.c.

Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-sata.c | 2 +-
 include/linux/libata.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index b6656c287175c..0fb1934875f20 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -784,7 +784,7 @@ bool sata_lpm_ignore_phy_events(struct ata_link *link)
 EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events);
 
 static const char *ata_lpm_policy_names[] = {
-	[ATA_LPM_UNKNOWN]		= "max_performance",
+	[ATA_LPM_UNKNOWN]		= "keep_firmware_settings",
 	[ATA_LPM_MAX_POWER]		= "max_performance",
 	[ATA_LPM_MED_POWER]		= "medium_power",
 	[ATA_LPM_MED_POWER_WITH_DIPM]	= "med_power_with_dipm",
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 1dbb14daccfaf..26d68115afb82 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -471,7 +471,7 @@ enum ata_completion_errors {
 
 /*
  * Link power management policy: If you alter this, you also need to
- * alter libata-scsi.c (for the ascii descriptions)
+ * alter libata-sata.c (for the ascii descriptions)
  */
 enum ata_lpm_policy {
 	ATA_LPM_UNKNOWN,
-- 
GitLab


From 018856c3f171517c66d5d7d3755ae0c517924fd7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 22 Jan 2024 16:04:58 +0100
Subject: [PATCH 3253/4076] fbcon: Fix incorrect printed function name in
 fbcon_prepare_logo()

If the boot logo does not fit, a message is printed, including a wrong
function name prefix.  Instead of correcting the function name (or using
__func__), just use "fbcon", like is done in several other messages.

While at it, modernize the call by switching to pr_info().

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/core/fbcon.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 63af6ab034b5f..1183e7a871f8b 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -631,8 +631,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info,
 
 	if (logo_lines > vc->vc_bottom) {
 		logo_shown = FBCON_LOGO_CANSHOW;
-		printk(KERN_INFO
-		       "fbcon_init: disable boot-logo (boot-logo bigger than screen).\n");
+		pr_info("fbcon: disable boot-logo (boot-logo bigger than screen).\n");
 	} else {
 		logo_shown = FBCON_LOGO_DRAW;
 		vc->vc_top = logo_lines;
-- 
GitLab


From 202bc57b675601bc07b5942369ecc16af64d1b95 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 9 Jan 2024 17:17:36 +0000
Subject: [PATCH 3254/4076] netfs: Don't use certain unnecessary folio_*()
 functions

Filesystems should use folio->index and folio->mapping, instead of
folio_index(folio), folio_mapping() and folio_file_mapping() since
they know that it's in the pagecache.

Change this automagically with:

perl -p -i -e 's/folio_mapping[(]([^)]*)[)]/\1->mapping/g' fs/netfs/*.c
perl -p -i -e 's/folio_file_mapping[(]([^)]*)[)]/\1->mapping/g' fs/netfs/*.c
perl -p -i -e 's/folio_index[(]([^)]*)[)]/\1->index/g' fs/netfs/*.c

Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-afs@lists.infradead.org
cc: linux-cachefs@redhat.com
cc: linux-cifs@vger.kernel.org
cc: linux-erofs@lists.ozlabs.org
cc: linux-fsdevel@vger.kernel.org
---
 fs/netfs/buffered_read.c  | 12 ++++++------
 fs/netfs/buffered_write.c | 10 +++++-----
 fs/netfs/io.c             |  2 +-
 fs/netfs/misc.c           |  2 +-
 4 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index a59e7b2edaacd..3298c29b55483 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -101,7 +101,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 		}
 
 		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
-			if (folio_index(folio) == rreq->no_unlock_folio &&
+			if (folio->index == rreq->no_unlock_folio &&
 			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
 				_debug("no unlock");
 			else
@@ -246,13 +246,13 @@ EXPORT_SYMBOL(netfs_readahead);
  */
 int netfs_read_folio(struct file *file, struct folio *folio)
 {
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 	struct netfs_io_request *rreq;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
 	struct folio *sink = NULL;
 	int ret;
 
-	_enter("%lx", folio_index(folio));
+	_enter("%lx", folio->index);
 
 	rreq = netfs_alloc_request(mapping, file,
 				   folio_file_pos(folio), folio_size(folio),
@@ -460,7 +460,7 @@ retry:
 		ret = PTR_ERR(rreq);
 		goto error;
 	}
-	rreq->no_unlock_folio	= folio_index(folio);
+	rreq->no_unlock_folio	= folio->index;
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 
 	ret = netfs_begin_cache_read(rreq, ctx);
@@ -518,7 +518,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len)
 {
 	struct netfs_io_request *rreq;
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
 	unsigned long long start = folio_pos(folio);
 	size_t flen = folio_size(folio);
@@ -535,7 +535,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 		goto error;
 	}
 
-	rreq->no_unlock_folio = folio_index(folio);
+	rreq->no_unlock_folio = folio->index;
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 	ret = netfs_begin_cache_read(rreq, ctx);
 	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 93dc76f34e39a..e7f9ba6fb16bb 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -343,7 +343,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			break;
 		default:
 			WARN(true, "Unexpected modify type %u ix=%lx\n",
-			     howto, folio_index(folio));
+			     howto, folio->index);
 			ret = -EIO;
 			goto error_folio_unlock;
 		}
@@ -648,7 +648,7 @@ static void netfs_pages_written_back(struct netfs_io_request *wreq)
 	xas_for_each(&xas, folio, last) {
 		WARN(!folio_test_writeback(folio),
 		     "bad %zx @%llx page %lx %lx\n",
-		     wreq->len, wreq->start, folio_index(folio), last);
+		     wreq->len, wreq->start, folio->index, last);
 
 		if ((finfo = netfs_folio_info(folio))) {
 			/* Streaming writes cannot be redirtied whilst under
@@ -795,7 +795,7 @@ static void netfs_extend_writeback(struct address_space *mapping,
 				continue;
 			if (xa_is_value(folio))
 				break;
-			if (folio_index(folio) != index) {
+			if (folio->index != index) {
 				xas_reset(xas);
 				break;
 			}
@@ -901,7 +901,7 @@ static ssize_t netfs_write_back_from_locked_folio(struct address_space *mapping,
 	long count = wbc->nr_to_write;
 	int ret;
 
-	_enter(",%lx,%llx-%llx,%u", folio_index(folio), start, end, caching);
+	_enter(",%lx,%llx-%llx,%u", folio->index, start, end, caching);
 
 	wreq = netfs_alloc_request(mapping, NULL, start, folio_size(folio),
 				   NETFS_WRITEBACK);
@@ -1047,7 +1047,7 @@ search_again:
 
 	start = folio_pos(folio); /* May regress with THPs */
 
-	_debug("wback %lx", folio_index(folio));
+	_debug("wback %lx", folio->index);
 
 	/* At this point we hold neither the i_pages lock nor the page lock:
 	 * the page may be truncated or invalidated (changing page->mapping to
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 4309edf338627..e8ff1e61ce79b 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -124,7 +124,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
 			/* We might have multiple writes from the same huge
 			 * folio, but we mustn't unlock a folio more than once.
 			 */
-			if (have_unlocked && folio_index(folio) <= unlocked)
+			if (have_unlocked && folio->index <= unlocked)
 				continue;
 			unlocked = folio_next_index(folio) - 1;
 			trace_netfs_folio(folio, netfs_folio_trace_end_copy);
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 0e3af37fc9243..90051ced8e2a8 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -180,7 +180,7 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 	struct netfs_folio *finfo = NULL;
 	size_t flen = folio_size(folio);
 
-	_enter("{%lx},%zx,%zx", folio_index(folio), offset, length);
+	_enter("{%lx},%zx,%zx", folio->index, offset, length);
 
 	folio_wait_fscache(folio);
 
-- 
GitLab


From fa7d614da3c556c7ef71023cb8c410a3e8571a42 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 9 Jan 2024 17:51:08 +0000
Subject: [PATCH 3255/4076] afs: Don't use certain unnecessary folio_*()
 functions

Filesystems should use folio->index and folio->mapping, instead of
folio_index(folio), folio_mapping() and folio_file_mapping() since
they know that it's in the pagecache.

Change this automagically with:

perl -p -i -e 's/folio_mapping[(]([^)]*)[)]/\1->mapping/g' fs/afs/*.c
perl -p -i -e 's/folio_file_mapping[(]([^)]*)[)]/\1->mapping/g' fs/afs/*.c
perl -p -i -e 's/folio_index[(]([^)]*)[)]/\1->index/g' fs/afs/*.c

Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: linux-fsdevel@vger.kernel.org
---
 fs/afs/dir.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index c14533ef108f1..3f73d61f7c8a3 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -124,7 +124,7 @@ static void afs_dir_read_cleanup(struct afs_read *req)
 		if (xas_retry(&xas, folio))
 			continue;
 		BUG_ON(xa_is_value(folio));
-		ASSERTCMP(folio_file_mapping(folio), ==, mapping);
+		ASSERTCMP(folio->mapping, ==, mapping);
 
 		folio_put(folio);
 	}
@@ -202,12 +202,12 @@ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
 		if (xas_retry(&xas, folio))
 			continue;
 
-		BUG_ON(folio_file_mapping(folio) != mapping);
+		BUG_ON(folio->mapping != mapping);
 
 		size = min_t(loff_t, folio_size(folio), req->actual_len - folio_pos(folio));
 		for (offset = 0; offset < size; offset += sizeof(*block)) {
 			block = kmap_local_folio(folio, offset);
-			pr_warn("[%02lx] %32phN\n", folio_index(folio) + offset, block);
+			pr_warn("[%02lx] %32phN\n", folio->index + offset, block);
 			kunmap_local(block);
 		}
 	}
@@ -233,7 +233,7 @@ static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req)
 		if (xas_retry(&xas, folio))
 			continue;
 
-		BUG_ON(folio_file_mapping(folio) != mapping);
+		BUG_ON(folio->mapping != mapping);
 
 		if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) {
 			afs_dir_dump(dvnode, req);
@@ -2022,7 +2022,7 @@ static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags)
 {
 	struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio));
 
-	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio_index(folio));
+	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio->index);
 
 	folio_detach_private(folio);
 
-- 
GitLab


From c40497d82387188f14d9adc4caa58ee1cb1999e1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 9 Jan 2024 17:54:35 +0000
Subject: [PATCH 3256/4076] cifs: Don't use certain unnecessary folio_*()
 functions

Filesystems should use folio->index and folio->mapping, instead of
folio_index(folio), folio_mapping() and folio_file_mapping() since
they know that it's in the pagecache.

Change this automagically with:

perl -p -i -e 's/folio_mapping[(]([^)]*)[)]/\1->mapping/g' fs/smb/client/*.c
perl -p -i -e 's/folio_file_mapping[(]([^)]*)[)]/\1->mapping/g' fs/smb/client/*.c
perl -p -i -e 's/folio_index[(]([^)]*)[)]/\1->index/g' fs/smb/client/*.c

Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: Steve French <sfrench@samba.org>
cc: Paulo Alcantara <pc@manguebit.com>
cc: Ronnie Sahlberg <lsahlber@redhat.com>
cc: Shyam Prasad N <sprasad@microsoft.com>
cc: Tom Talpey <tom@talpey.com>
cc: linux-cifs@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
---
 fs/smb/client/file.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 3a213432775b1..90da81d0372a0 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -87,7 +87,7 @@ void cifs_pages_written_back(struct inode *inode, loff_t start, unsigned int len
 			continue;
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
@@ -120,7 +120,7 @@ void cifs_pages_write_failed(struct inode *inode, loff_t start, unsigned int len
 			continue;
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
@@ -151,7 +151,7 @@ void cifs_pages_write_redirty(struct inode *inode, loff_t start, unsigned int le
 	xas_for_each(&xas, folio, end) {
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
@@ -2651,7 +2651,7 @@ static void cifs_extend_writeback(struct address_space *mapping,
 				continue;
 			if (xa_is_value(folio))
 				break;
-			if (folio_index(folio) != index)
+			if (folio->index != index)
 				break;
 			if (!folio_try_get_rcu(folio)) {
 				xas_reset(&xas);
@@ -2899,7 +2899,7 @@ redo_folio:
 					goto skip_write;
 			}
 
-			if (folio_mapping(folio) != mapping ||
+			if (folio->mapping != mapping ||
 			    !folio_test_dirty(folio)) {
 				start += folio_size(folio);
 				folio_unlock(folio);
-- 
GitLab


From 3be0b3ed1d76c6703b9ee482b55f7e01c369cc68 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 12 Jan 2024 09:59:41 +0300
Subject: [PATCH 3257/4076] netfs, fscache: Prevent Oops in fscache_put_cache()

This function dereferences "cache" and then checks if it's
IS_ERR_OR_NULL().  Check first, then dereference.

Fixes: 9549332df4ed ("fscache: Implement cache registration")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/e84bc740-3502-4f16-982a-a40d5676615c@moroto.mountain/ # v2
---
 fs/netfs/fscache_cache.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/netfs/fscache_cache.c b/fs/netfs/fscache_cache.c
index d645f8b302a27..9397ed39b0b4e 100644
--- a/fs/netfs/fscache_cache.c
+++ b/fs/netfs/fscache_cache.c
@@ -179,13 +179,14 @@ EXPORT_SYMBOL(fscache_acquire_cache);
 void fscache_put_cache(struct fscache_cache *cache,
 		       enum fscache_cache_trace where)
 {
-	unsigned int debug_id = cache->debug_id;
+	unsigned int debug_id;
 	bool zero;
 	int ref;
 
 	if (IS_ERR_OR_NULL(cache))
 		return;
 
+	debug_id = cache->debug_id;
 	zero = __refcount_dec_and_test(&cache->ref, &ref);
 	trace_fscache_cache(debug_id, ref - 1, where);
 
-- 
GitLab


From 843609df0be792991b3c4a720d6be4828d48dec4 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 10 Jan 2024 21:54:42 +0300
Subject: [PATCH 3258/4076] netfs: Fix a NULL vs IS_ERR() check in
 netfs_perform_write()

The netfs_grab_folio_for_write() function doesn't return NULL, it returns
error pointers.  Update the check accordingly.

Fixes: c38f4e96e605 ("netfs: Provide func to copy data to pagecache for buffered write")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/29fb1310-8e2d-47ba-b68d-40354eb7b896@moroto.mountain/
---
 fs/netfs/buffered_write.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index e7f9ba6fb16bb..a3059b3168fd9 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -221,10 +221,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		if (unlikely(fault_in_iov_iter_readable(iter, part) == part))
 			break;
 
-		ret = -ENOMEM;
 		folio = netfs_grab_folio_for_write(mapping, pos, part);
-		if (!folio)
+		if (IS_ERR(folio)) {
+			ret = PTR_ERR(folio);
 			break;
+		}
 
 		flen = folio_size(folio);
 		offset = pos & (flen - 1);
-- 
GitLab


From 2b44760609e9eaafc9d234a6883d042fc21132a7 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 22 Jan 2024 16:09:28 +0100
Subject: [PATCH 3259/4076] tracing: Ensure visibility when inserting an
 element into tracing_map

Running the following two commands in parallel on a multi-processor
AArch64 machine can sporadically produce an unexpected warning about
duplicate histogram entries:

 $ while true; do
     echo hist:key=id.syscall:val=hitcount > \
       /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
     cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
     sleep 0.001
   done
 $ stress-ng --sysbadaddr $(nproc)

The warning looks as follows:

[ 2911.172474] ------------[ cut here ]------------
[ 2911.173111] Duplicates detected: 1
[ 2911.173574] WARNING: CPU: 2 PID: 12247 at kernel/trace/tracing_map.c:983 tracing_map_sort_entries+0x3e0/0x408
[ 2911.174702] Modules linked in: iscsi_ibft(E) iscsi_boot_sysfs(E) rfkill(E) af_packet(E) nls_iso8859_1(E) nls_cp437(E) vfat(E) fat(E) ena(E) tiny_power_button(E) qemu_fw_cfg(E) button(E) fuse(E) efi_pstore(E) ip_tables(E) x_tables(E) xfs(E) libcrc32c(E) aes_ce_blk(E) aes_ce_cipher(E) crct10dif_ce(E) polyval_ce(E) polyval_generic(E) ghash_ce(E) gf128mul(E) sm4_ce_gcm(E) sm4_ce_ccm(E) sm4_ce(E) sm4_ce_cipher(E) sm4(E) sm3_ce(E) sm3(E) sha3_ce(E) sha512_ce(E) sha512_arm64(E) sha2_ce(E) sha256_arm64(E) nvme(E) sha1_ce(E) nvme_core(E) nvme_auth(E) t10_pi(E) sg(E) scsi_mod(E) scsi_common(E) efivarfs(E)
[ 2911.174738] Unloaded tainted modules: cppc_cpufreq(E):1
[ 2911.180985] CPU: 2 PID: 12247 Comm: cat Kdump: loaded Tainted: G            E      6.7.0-default #2 1b58bbb22c97e4399dc09f92d309344f69c44a01
[ 2911.182398] Hardware name: Amazon EC2 c7g.8xlarge/, BIOS 1.0 11/1/2018
[ 2911.183208] pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[ 2911.184038] pc : tracing_map_sort_entries+0x3e0/0x408
[ 2911.184667] lr : tracing_map_sort_entries+0x3e0/0x408
[ 2911.185310] sp : ffff8000a1513900
[ 2911.185750] x29: ffff8000a1513900 x28: ffff0003f272fe80 x27: 0000000000000001
[ 2911.186600] x26: ffff0003f272fe80 x25: 0000000000000030 x24: 0000000000000008
[ 2911.187458] x23: ffff0003c5788000 x22: ffff0003c16710c8 x21: ffff80008017f180
[ 2911.188310] x20: ffff80008017f000 x19: ffff80008017f180 x18: ffffffffffffffff
[ 2911.189160] x17: 0000000000000000 x16: 0000000000000000 x15: ffff8000a15134b8
[ 2911.190015] x14: 0000000000000000 x13: 205d373432323154 x12: 5b5d313131333731
[ 2911.190844] x11: 00000000fffeffff x10: 00000000fffeffff x9 : ffffd1b78274a13c
[ 2911.191716] x8 : 000000000017ffe8 x7 : c0000000fffeffff x6 : 000000000057ffa8
[ 2911.192554] x5 : ffff0012f6c24ec0 x4 : 0000000000000000 x3 : ffff2e5b72b5d000
[ 2911.193404] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0003ff254480
[ 2911.194259] Call trace:
[ 2911.194626]  tracing_map_sort_entries+0x3e0/0x408
[ 2911.195220]  hist_show+0x124/0x800
[ 2911.195692]  seq_read_iter+0x1d4/0x4e8
[ 2911.196193]  seq_read+0xe8/0x138
[ 2911.196638]  vfs_read+0xc8/0x300
[ 2911.197078]  ksys_read+0x70/0x108
[ 2911.197534]  __arm64_sys_read+0x24/0x38
[ 2911.198046]  invoke_syscall+0x78/0x108
[ 2911.198553]  el0_svc_common.constprop.0+0xd0/0xf8
[ 2911.199157]  do_el0_svc+0x28/0x40
[ 2911.199613]  el0_svc+0x40/0x178
[ 2911.200048]  el0t_64_sync_handler+0x13c/0x158
[ 2911.200621]  el0t_64_sync+0x1a8/0x1b0
[ 2911.201115] ---[ end trace 0000000000000000 ]---

The problem appears to be caused by CPU reordering of writes issued from
__tracing_map_insert().

The check for the presence of an element with a given key in this
function is:

 val = READ_ONCE(entry->val);
 if (val && keys_match(key, val->key, map->key_size)) ...

The write of a new entry is:

 elt = get_free_elt(map);
 memcpy(elt->key, key, map->key_size);
 entry->val = elt;

The "memcpy(elt->key, key, map->key_size);" and "entry->val = elt;"
stores may become visible in the reversed order on another CPU. This
second CPU might then incorrectly determine that a new key doesn't match
an already present val->key and subsequently insert a new element,
resulting in a duplicate.

Fix the problem by adding a write barrier between
"memcpy(elt->key, key, map->key_size);" and "entry->val = elt;", and for
good measure, also use WRITE_ONCE(entry->val, elt) for publishing the
element. The sequence pairs with the mentioned "READ_ONCE(entry->val);"
and the "val->key" check which has an address dependency.

The barrier is placed on a path executed when adding an element for
a new key. Subsequent updates targeting the same key remain unaffected.

From the user's perspective, the issue was introduced by commit
c193707dde77 ("tracing: Remove code which merges duplicates"), which
followed commit cbf4100efb8f ("tracing: Add support to detect and avoid
duplicates"). The previous code operated differently; it inherently
expected potential races which result in duplicates but merged them
later when they occurred.

Link: https://lore.kernel.org/linux-trace-kernel/20240122150928.27725-1-petr.pavlu@suse.com

Fixes: c193707dde77 ("tracing: Remove code which merges duplicates")
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Acked-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/tracing_map.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index c774e560f2f95..a4dcf0f243521 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -574,7 +574,12 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
 				}
 
 				memcpy(elt->key, key, map->key_size);
-				entry->val = elt;
+				/*
+				 * Ensure the initialization is visible and
+				 * publish the elt.
+				 */
+				smp_wmb();
+				WRITE_ONCE(entry->val, elt);
 				atomic64_inc(&map->hits);
 
 				return entry->val;
-- 
GitLab


From c3d6569a43322f371e7ba0ad386112723757ac8f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 19 Jan 2024 20:49:34 +0000
Subject: [PATCH 3260/4076] cachefiles, erofs: Fix NULL deref in when
 cachefiles is not doing ondemand-mode

cachefiles_ondemand_init_object() as called from cachefiles_open_file() and
cachefiles_create_tmpfile() does not check if object->ondemand is set
before dereferencing it, leading to an oops something like:

	RIP: 0010:cachefiles_ondemand_init_object+0x9/0x41
	...
	Call Trace:
	 <TASK>
	 cachefiles_open_file+0xc9/0x187
	 cachefiles_lookup_cookie+0x122/0x2be
	 fscache_cookie_state_machine+0xbe/0x32b
	 fscache_cookie_worker+0x1f/0x2d
	 process_one_work+0x136/0x208
	 process_scheduled_works+0x3a/0x41
	 worker_thread+0x1a2/0x1f6
	 kthread+0xca/0xd2
	 ret_from_fork+0x21/0x33

Fix this by making cachefiles_ondemand_init_object() return immediately if
cachefiles->ondemand is NULL.

Fixes: 3c5ecfe16e76 ("cachefiles: extract ondemand info field from cachefiles_object")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Gao Xiang <xiang@kernel.org>
cc: Chao Yu <chao@kernel.org>
cc: Yue Hu <huyue2@coolpad.com>
cc: Jeffle Xu <jefflexu@linux.alibaba.com>
cc: linux-erofs@lists.ozlabs.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
---
 fs/cachefiles/ondemand.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 5fd74ec60befc..4ba42f1fa3b40 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -539,6 +539,9 @@ int cachefiles_ondemand_init_object(struct cachefiles_object *object)
 	struct fscache_volume *volume = object->volume->vcookie;
 	size_t volume_key_size, cookie_key_size, data_len;
 
+	if (!object->ondemand)
+		return 0;
+
 	/*
 	 * CacheFiles will firstly check the cache file under the root cache
 	 * directory. If the coherency check failed, it will fallback to
-- 
GitLab


From 57e9d49c54528c49b8bffe6d99d782ea051ea534 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 8 Jan 2024 17:22:36 +0000
Subject: [PATCH 3261/4076] afs: Hide silly-rename files from userspace

There appears to be a race between silly-rename files being created/removed
and various userspace tools iterating over the contents of a directory,
leading to such errors as:

	find: './kernel/.tmp_cpio_dir/include/dt-bindings/reset/.__afs2080': No such file or directory
	tar: ./include/linux/greybus/.__afs3C95: File removed before we read it

when building a kernel.

Fix afs_readdir() so that it doesn't return .__afsXXXX silly-rename files
to userspace.  This doesn't stop them being looked up directly by name as
we need to be able to look them up from within the kernel as part of the
silly-rename algorithm.

Fixes: 79ddbfa500b3 ("afs: Implement sillyrename for unlink and rename")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/dir.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 3f73d61f7c8a3..eface67ccc060 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -474,6 +474,14 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 			continue;
 		}
 
+		/* Don't expose silly rename entries to userspace. */
+		if (nlen > 6 &&
+		    dire->u.name[0] == '.' &&
+		    ctx->actor != afs_lookup_filldir &&
+		    ctx->actor != afs_lookup_one_filldir &&
+		    memcmp(dire->u.name, ".__afs", 6) == 0)
+			continue;
+
 		/* found the next entry */
 		if (!dir_emit(ctx, dire->u.name, nlen,
 			      ntohl(dire->u.vnode),
-- 
GitLab


From 17ba6f0bd14fe3ac606aac6bebe5e69bdaad8ba1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 2 Jan 2024 14:02:37 +0000
Subject: [PATCH 3262/4076] afs: Fix error handling with lookup via
 FS.InlineBulkStatus

When afs does a lookup, it tries to use FS.InlineBulkStatus to preemptively
look up a bunch of files in the parent directory and cache this locally, on
the basis that we might want to look at them too (for example if someone
does an ls on a directory, they may want want to then stat every file
listed).

FS.InlineBulkStatus can be considered a compound op with the normal abort
code applying to the compound as a whole.  Each status fetch within the
compound is then given its own individual abort code - but assuming no
error that prevents the bulk fetch from returning the compound result will
be 0, even if all the constituent status fetches failed.

At the conclusion of afs_do_lookup(), we should use the abort code from the
appropriate status to determine the error to return, if any - but instead
it is assumed that we were successful if the op as a whole succeeded and we
return an incompletely initialised inode, resulting in ENOENT, no matter
the actual reason.  In the particular instance reported, a vnode with no
permission granted to be accessed is being given a UAEACCES abort code
which should be reported as EACCES, but is instead being reported as
ENOENT.

Fix this by abandoning the inode (which will be cleaned up with the op) if
file[1] has an abort code indicated and turn that abort code into an error
instead.

Whilst we're at it, add a tracepoint so that the abort codes of the
individual subrequests of FS.InlineBulkStatus can be logged.  At the moment
only the container abort code can be 0.

Fixes: e49c7b2f6de7 ("afs: Build an abstraction around an "operation" concept")
Reported-by: Jeffrey Altman <jaltman@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/dir.c               | 12 +++++++++---
 include/trace/events/afs.h | 25 +++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index eface67ccc060..b5b8de521f99b 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -716,6 +716,8 @@ static void afs_do_lookup_success(struct afs_operation *op)
 			break;
 		}
 
+		if (vp->scb.status.abort_code)
+			trace_afs_bulkstat_error(op, &vp->fid, i, vp->scb.status.abort_code);
 		if (!vp->scb.have_status && !vp->scb.have_error)
 			continue;
 
@@ -905,12 +907,16 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 		afs_begin_vnode_operation(op);
 		afs_wait_for_operation(op);
 	}
-	inode = ERR_PTR(afs_op_error(op));
 
 out_op:
 	if (!afs_op_error(op)) {
-		inode = &op->file[1].vnode->netfs.inode;
-		op->file[1].vnode = NULL;
+		if (op->file[1].scb.status.abort_code) {
+			afs_op_accumulate_error(op, -ECONNABORTED,
+						op->file[1].scb.status.abort_code);
+		} else {
+			inode = &op->file[1].vnode->netfs.inode;
+			op->file[1].vnode = NULL;
+		}
 	}
 
 	if (op->file[0].scb.have_status)
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 8d73171cb9f0d..08f2c93d6b160 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -1071,6 +1071,31 @@ TRACE_EVENT(afs_file_error,
 		      __print_symbolic(__entry->where, afs_file_errors))
 	    );
 
+TRACE_EVENT(afs_bulkstat_error,
+	    TP_PROTO(struct afs_operation *op, struct afs_fid *fid, unsigned int index, s32 abort),
+
+	    TP_ARGS(op, fid, index, abort),
+
+	    TP_STRUCT__entry(
+		    __field_struct(struct afs_fid,	fid)
+		    __field(unsigned int,		op)
+		    __field(unsigned int,		index)
+		    __field(s32,			abort)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->op = op->debug_id;
+		    __entry->fid = *fid;
+		    __entry->index = index;
+		    __entry->abort = abort;
+			   ),
+
+	    TP_printk("OP=%08x[%02x] %llx:%llx:%x a=%d",
+		      __entry->op, __entry->index,
+		      __entry->fid.vid, __entry->fid.vnode, __entry->fid.unique,
+		      __entry->abort)
+	    );
+
 TRACE_EVENT(afs_cm_no_server,
 	    TP_PROTO(struct afs_call *call, struct sockaddr_rxrpc *srx),
 
-- 
GitLab


From cfcc005dbcc79f1e6bddc6fd4b3e8a1163a6d181 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 12 Jan 2024 21:59:44 +0000
Subject: [PATCH 3263/4076] afs: Remove afs_dynroot_d_revalidate() as it is
 redundant

Remove afs_dynroot_d_revalidate() as it is redundant as all it does is
return 1 and the caller assumes that if the op is not given.

Suggested-by: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: linux-fsdevel@vger.kernel.org
---
 fs/afs/dynroot.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index d3bc4a2d70851..c4d2711e20ad4 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -258,16 +258,7 @@ const struct inode_operations afs_dynroot_inode_operations = {
 	.lookup		= afs_dynroot_lookup,
 };
 
-/*
- * Dirs in the dynamic root don't need revalidation.
- */
-static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags)
-{
-	return 1;
-}
-
 const struct dentry_operations afs_dynroot_dentry_operations = {
-	.d_revalidate	= afs_dynroot_d_revalidate,
 	.d_delete	= always_delete_dentry,
 	.d_release	= afs_d_release,
 	.d_automount	= afs_d_automount,
-- 
GitLab


From b90493505347a4ca4d900f317e2b330e0e43ae2f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 17 Jan 2024 15:49:26 +0000
Subject: [PATCH 3264/4076] afs: Fix missing/incorrect unlocking of RCU read
 lock

In afs_proc_addr_prefs_show(), we need to unlock the RCU read lock in both
places before returning (and not lock it again).

Fixes: f94f70d39cc2 ("afs: Provide a way to configure address priorities")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401172243.cd53d5f6-oliver.sang@intel.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-afs@lists.infradead.org
cc: linux-fsdevel@vger.kernel.org
---
 fs/afs/proc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 3bd02571f30de..15eab053af6dc 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -166,7 +166,7 @@ static int afs_proc_addr_prefs_show(struct seq_file *m, void *v)
 
 	if (!preflist) {
 		seq_puts(m, "NO PREFS\n");
-		return 0;
+		goto out;
 	}
 
 	seq_printf(m, "PROT SUBNET                                      PRIOR (v=%u n=%u/%u/%u)\n",
@@ -191,7 +191,8 @@ static int afs_proc_addr_prefs_show(struct seq_file *m, void *v)
 		}
 	}
 
-	rcu_read_lock();
+out:
+	rcu_read_unlock();
 	return 0;
 }
 
-- 
GitLab


From e01a83e12604aa2f8d4ab359ec44e341a2248b4a Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 22 Jan 2024 15:39:01 -0800
Subject: [PATCH 3265/4076] Revert "btrfs: zstd: fix and simplify the inline
 extent decompression"

This reverts commit 1e7f6def8b2370ecefb54b3c8f390ff894b0c51b.

It causes my machine to not even boot, and Klara Modin reports that the
cause is that small zstd-compressed files return garbage when read.

Reported-by: Klara Modin <klarasmodin@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/CABq1_vj4GpUeZpVG49OHCo-3sdbe2-2ROcu_xDvUG-6-5zPRXg@mail.gmail.com/
Reported-and-bisected-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: David Sterba <dsterba@suse.com>
Cc: Qu Wenruo <wqu@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/btrfs/compression.h |  2 +-
 fs/btrfs/zstd.c        | 75 +++++++++++++++++++++++++++++-------------
 2 files changed, 54 insertions(+), 23 deletions(-)

diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 97fe3ebf11a22..afd7e50d073d4 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -169,7 +169,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out);
 int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int zstd_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
 		size_t destlen);
 void zstd_init_workspace_manager(void);
 void zstd_cleanup_workspace_manager(void);
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 346c46d88d07f..0d66db8bc1d47 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -20,7 +20,6 @@
 #include "misc.h"
 #include "compression.h"
 #include "ctree.h"
-#include "super.h"
 
 #define ZSTD_BTRFS_MAX_WINDOWLOG 17
 #define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG)
@@ -619,48 +618,80 @@ done:
 }
 
 int zstd_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
-	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
-	const u32 sectorsize = fs_info->sectorsize;
 	zstd_dstream *stream;
 	int ret = 0;
-	unsigned long to_copy = 0;
+	size_t ret2;
+	unsigned long total_out = 0;
+	unsigned long pg_offset = 0;
 
 	stream = zstd_init_dstream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
 	if (!stream) {
 		pr_warn("BTRFS: zstd_init_dstream failed\n");
+		ret = -EIO;
 		goto finish;
 	}
 
+	destlen = min_t(size_t, destlen, PAGE_SIZE);
+
 	workspace->in_buf.src = data_in;
 	workspace->in_buf.pos = 0;
 	workspace->in_buf.size = srclen;
 
 	workspace->out_buf.dst = workspace->buf;
 	workspace->out_buf.pos = 0;
-	workspace->out_buf.size = sectorsize;
-
-	/*
-	 * Since both input and output buffers should not exceed one sector,
-	 * one call should end the decompression.
-	 */
-	ret = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf);
-	if (zstd_is_error(ret)) {
-		pr_warn_ratelimited("BTRFS: zstd_decompress_stream return %d\n",
-				    zstd_get_error_code(ret));
-		goto finish;
+	workspace->out_buf.size = PAGE_SIZE;
+
+	ret2 = 1;
+	while (pg_offset < destlen
+	       && workspace->in_buf.pos < workspace->in_buf.size) {
+		unsigned long buf_start;
+		unsigned long buf_offset;
+		unsigned long bytes;
+
+		/* Check if the frame is over and we still need more input */
+		if (ret2 == 0) {
+			pr_debug("BTRFS: zstd_decompress_stream ended early\n");
+			ret = -EIO;
+			goto finish;
+		}
+		ret2 = zstd_decompress_stream(stream, &workspace->out_buf,
+				&workspace->in_buf);
+		if (zstd_is_error(ret2)) {
+			pr_debug("BTRFS: zstd_decompress_stream returned %d\n",
+					zstd_get_error_code(ret2));
+			ret = -EIO;
+			goto finish;
+		}
+
+		buf_start = total_out;
+		total_out += workspace->out_buf.pos;
+		workspace->out_buf.pos = 0;
+
+		if (total_out <= start_byte)
+			continue;
+
+		if (total_out > start_byte && buf_start < start_byte)
+			buf_offset = start_byte - buf_start;
+		else
+			buf_offset = 0;
+
+		bytes = min_t(unsigned long, destlen - pg_offset,
+				workspace->out_buf.size - buf_offset);
+
+		memcpy_to_page(dest_page, pg_offset,
+			       workspace->out_buf.dst + buf_offset, bytes);
+
+		pg_offset += bytes;
 	}
-	to_copy = workspace->out_buf.pos;
-	memcpy_to_page(dest_page, dest_pgoff + to_copy, workspace->out_buf.dst, to_copy);
+	ret = 0;
 finish:
-	/* Error or early end. */
-	if (unlikely(to_copy < destlen)) {
-		ret = -EIO;
-		memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
+	if (pg_offset < destlen) {
+		memzero_page(dest_page, pg_offset, destlen - pg_offset);
 	}
 	return ret;
 }
-- 
GitLab


From 7ed2632ec7d72e926b9e8bcc9ad1bb0cd37274bf Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Sun, 14 Jan 2024 00:33:45 +0300
Subject: [PATCH 3266/4076] drm/ttm: fix ttm pool initialization for
 no-dma-device drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The QXL driver doesn't use any device for DMA mappings or allocations so
dev_to_node() will panic inside ttm_device_init() on NUMA systems:

  general protection fault, probably for non-canonical address 0xdffffc000000007a: 0000 [#1] PREEMPT SMP KASAN NOPTI
  KASAN: null-ptr-deref in range [0x00000000000003d0-0x00000000000003d7]
  CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.7.0+ #9
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014
  RIP: 0010:ttm_device_init+0x10e/0x340
  Call Trace:
    qxl_ttm_init+0xaa/0x310
    qxl_device_init+0x1071/0x2000
    qxl_pci_probe+0x167/0x3f0
    local_pci_probe+0xe1/0x1b0
    pci_device_probe+0x29d/0x790
    really_probe+0x251/0x910
    __driver_probe_device+0x1ea/0x390
    driver_probe_device+0x4e/0x2e0
    __driver_attach+0x1e3/0x600
    bus_for_each_dev+0x12d/0x1c0
    bus_add_driver+0x25a/0x590
    driver_register+0x15c/0x4b0
    qxl_pci_driver_init+0x67/0x80
    do_one_initcall+0xf5/0x5d0
    kernel_init_freeable+0x637/0xb10
    kernel_init+0x1c/0x2e0
    ret_from_fork+0x48/0x80
    ret_from_fork_asm+0x1b/0x30
  RIP: 0010:ttm_device_init+0x10e/0x340

Fall back to NUMA_NO_NODE if there is no device for DMA.

Found by Linux Verification Center (linuxtesting.org).

Fixes: b0a7ce53d494 ("drm/ttm: Schedule delayed_delete worker closer")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/gpu/drm/ttm/ttm_device.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index f5187b384ae9a..4130945052ed2 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -195,7 +195,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 		    bool use_dma_alloc, bool use_dma32)
 {
 	struct ttm_global *glob = &ttm_glob;
-	int ret;
+	int ret, nid;
 
 	if (WARN_ON(vma_manager == NULL))
 		return -EINVAL;
@@ -215,7 +215,12 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 
 	ttm_sys_man_init(bdev);
 
-	ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32);
+	if (dev)
+		nid = dev_to_node(dev);
+	else
+		nid = NUMA_NO_NODE;
+
+	ttm_pool_init(&bdev->pool, dev, nid, use_dma_alloc, use_dma32);
 
 	bdev->vma_manager = vma_manager;
 	spin_lock_init(&bdev->lru_lock);
-- 
GitLab


From 3526860f26febbe46960f9b37f5dbd5ccc109ea8 Mon Sep 17 00:00:00 2001
From: Rui Salvaterra <rsalvaterra@gmail.com>
Date: Mon, 22 Jan 2024 11:45:12 +0000
Subject: [PATCH 3267/4076] ALSA: hda: Replace numeric device IDs with constant
 values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have self-explanatory constants for Intel HDA devices, let's use them instead
of magic numbers and code comments.

Signed-off-by: Rui Salvaterra <rsalvaterra@gmail.com>
Reviewed-by: Amadeusz Sławiński <amadeuszx.slawinski@linux.intel.com>
Link: https://lore.kernel.org/r/20240122114512.55808-2-rsalvaterra@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 2276adc844784..66f013ee160d2 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1729,8 +1729,8 @@ static int default_bdl_pos_adj(struct azx *chip)
 	/* some exceptions: Atoms seem problematic with value 1 */
 	if (chip->pci->vendor == PCI_VENDOR_ID_INTEL) {
 		switch (chip->pci->device) {
-		case 0x0f04: /* Baytrail */
-		case 0x2284: /* Braswell */
+		case PCI_DEVICE_ID_INTEL_HDA_BYT:
+		case PCI_DEVICE_ID_INTEL_HDA_BSW:
 			return 32;
 		}
 	}
-- 
GitLab


From 56beedc88405fd8022edfd1c2e63d1bc6c95efcb Mon Sep 17 00:00:00 2001
From: Rui Salvaterra <rsalvaterra@gmail.com>
Date: Mon, 22 Jan 2024 11:45:13 +0000
Subject: [PATCH 3268/4076] ALSA: hda: Increase default bdl_pos_adj for Apollo
 Lake
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Apollo Lake seems to also suffer from IRQ timing issues. After being up for ~4
minutes, a Pentium N4200 system ends up falling back to workqueue-based IRQ
handling:

[  208.019906] snd_hda_intel 0000:00:0e.0: IRQ timing workaround is activated
for card #0. Suggest a bigger bdl_pos_adj.

Unfortunately, the Baytrail and Braswell workaround value of 32 samples isn't
enough to fix the issue here. Default to 64 samples.

Signed-off-by: Rui Salvaterra <rsalvaterra@gmail.com>
Reviewed-by: Amadeusz Sławiński <amadeuszx.slawinski@linux.intel.com>
Link: https://lore.kernel.org/r/20240122114512.55808-3-rsalvaterra@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 66f013ee160d2..1b550c42db092 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1732,6 +1732,8 @@ static int default_bdl_pos_adj(struct azx *chip)
 		case PCI_DEVICE_ID_INTEL_HDA_BYT:
 		case PCI_DEVICE_ID_INTEL_HDA_BSW:
 			return 32;
+		case PCI_DEVICE_ID_INTEL_HDA_APL:
+			return 64;
 		}
 	}
 
-- 
GitLab


From a2ed0a44d637ef9deca595054c206da7d6cbdcbc Mon Sep 17 00:00:00 2001
From: Vitaly Rodionov <vitalyr@opensource.cirrus.com>
Date: Mon, 22 Jan 2024 18:47:10 +0000
Subject: [PATCH 3269/4076] ALSA: hda/cs8409: Suppress vmaster control for
 Dolphin models

Customer has reported an issue with specific desktop platform
where two CS42L42 codecs are connected to CS8409 HDA bridge.
If "Master Volume Control" is created then on Ubuntu OS UCM
left/right balance slider in UI audio settings has no effect.
This patch will fix this issue for a target paltform.

Fixes: 20e507724113 ("ALSA: hda/cs8409: Add support for dolphin")
Signed-off-by: Vitaly Rodionov <vitalyr@opensource.cirrus.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240122184710.5802-1-vitalyr@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_cs8409.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c
index 627899959ffe8..e41316e2e9833 100644
--- a/sound/pci/hda/patch_cs8409.c
+++ b/sound/pci/hda/patch_cs8409.c
@@ -1371,6 +1371,7 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac
 		spec->scodecs[CS8409_CODEC1] = &dolphin_cs42l42_1;
 		spec->scodecs[CS8409_CODEC1]->codec = codec;
 		spec->num_scodecs = 2;
+		spec->gen.suppress_vmaster = 1;
 
 		codec->patch_ops = cs8409_dolphin_patch_ops;
 
-- 
GitLab


From 4b088005c897a62fe98f70ab69687706cb2fad3b Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Mon, 22 Jan 2024 21:26:33 +0100
Subject: [PATCH 3270/4076] fbdev: stifb: Fix crash in stifb_blank()

Avoid a kernel crash in stifb by providing the correct pointer to the fb_info
struct. Prior to commit e2e0b838a184 ("video/sticore: Remove info field from
STI struct") the fb_info struct was at the beginning of the fb struct.

Fixes: e2e0b838a184 ("video/sticore: Remove info field from STI struct")
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
---
 drivers/video/fbdev/stifb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 2de0e675fd150..8e5bac27542d9 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -1158,7 +1158,7 @@ stifb_init_display(struct stifb_info *fb)
 	    }
 	    break;
 	}
-	stifb_blank(0, (struct fb_info *)fb);	/* 0=enable screen */
+	stifb_blank(0, fb->info);	/* 0=enable screen */
 
 	SETUP_FB(fb);
 }
-- 
GitLab


From a969210066054ea109d8b7aff29a9b1c98776841 Mon Sep 17 00:00:00 2001
From: Julian Sikorski <belegdol+github@gmail.com>
Date: Tue, 23 Jan 2024 09:49:35 +0100
Subject: [PATCH 3271/4076] ALSA: usb-audio: Add a quirk for Yamaha YIT-W12TX
 transmitter

The device fails to initialize otherwise, giving the following error:
[ 3676.671641] usb 2-1.1: 1:1: cannot get freq at ep 0x1

Signed-off-by: Julian Sikorski <belegdol+github@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240123084935.2745-1-belegdol+github@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 07cc6a201579a..43c14a81a1e2f 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2031,6 +2031,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x0499, 0x3108, /* Yamaha YIT-W12TX */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x04d8, 0xfeea, /* Benchmark DAC1 Pre */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x04e8, 0xa051, /* Samsung USBC Headset (AKG) */
-- 
GitLab


From 7267e8dcad6b2f9fce05a6a06335d7040acbc2b6 Mon Sep 17 00:00:00 2001
From: Salvatore Dipietro <dipiets@amazon.com>
Date: Fri, 19 Jan 2024 11:01:33 -0800
Subject: [PATCH 3272/4076] tcp: Add memory barrier to tcp_push()

On CPUs with weak memory models, reads and updates performed by tcp_push
to the sk variables can get reordered leaving the socket throttled when
it should not. The tasklet running tcp_wfree() may also not observe the
memory updates in time and will skip flushing any packets throttled by
tcp_push(), delaying the sending. This can pathologically cause 40ms
extra latency due to bad interactions with delayed acks.

Adding a memory barrier in tcp_push removes the bug, similarly to the
previous commit bf06200e732d ("tcp: tsq: fix nonagle handling").
smp_mb__after_atomic() is used to not incur in unnecessary overhead
on x86 since not affected.

Patch has been tested using an AWS c7g.2xlarge instance with Ubuntu
22.04 and Apache Tomcat 9.0.83 running the basic servlet below:

import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

public class HelloWorldServlet extends HttpServlet {
    @Override
    protected void doGet(HttpServletRequest request, HttpServletResponse response)
      throws ServletException, IOException {
        response.setContentType("text/html;charset=utf-8");
        OutputStreamWriter osw = new OutputStreamWriter(response.getOutputStream(),"UTF-8");
        String s = "a".repeat(3096);
        osw.write(s,0,s.length());
        osw.flush();
    }
}

Load was applied using wrk2 (https://github.com/kinvolk/wrk2) from an AWS
c6i.8xlarge instance. Before the patch an additional 40ms latency from P99.99+
values is observed while, with the patch, the extra latency disappears.

No patch and tcp_autocorking=1
./wrk -t32 -c128 -d40s --latency -R10000  http://172.31.60.173:8080/hello/hello
  ...
 50.000%    0.91ms
 75.000%    1.13ms
 90.000%    1.46ms
 99.000%    1.74ms
 99.900%    1.89ms
 99.990%   41.95ms  <<< 40+ ms extra latency
 99.999%   48.32ms
100.000%   48.96ms

With patch and tcp_autocorking=1
./wrk -t32 -c128 -d40s --latency -R10000  http://172.31.60.173:8080/hello/hello
  ...
 50.000%    0.90ms
 75.000%    1.13ms
 90.000%    1.45ms
 99.000%    1.72ms
 99.900%    1.83ms
 99.990%    2.11ms  <<< no 40+ ms extra latency
 99.999%    2.53ms
100.000%    2.62ms

Patch has been also tested on x86 (m7i.2xlarge instance) which it is not
affected by this issue and the patch doesn't introduce any additional
delay.

Fixes: 7aa5470c2c09 ("tcp: tsq: move tsq_flags close to sk_wmem_alloc")
Signed-off-by: Salvatore Dipietro <dipiets@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240119190133.43698-1-dipiets@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1baa484d21902..a1c6de385ccef 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -722,6 +722,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now,
 		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
 			set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
+			smp_mb__after_atomic();
 		}
 		/* It is possible TX completion already happened
 		 * before we set TSQ_THROTTLED.
-- 
GitLab


From 97de5a15edf2d22184f5ff588656030bbb7fa358 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 19 Jan 2024 19:16:42 -0800
Subject: [PATCH 3273/4076] selftest: Don't reuse port for SO_INCOMING_CPU
 test.

Jakub reported that ASSERT_EQ(cpu, i) in so_incoming_cpu.c seems to
fire somewhat randomly.

  # #  RUN           so_incoming_cpu.before_reuseport.test3 ...
  # # so_incoming_cpu.c:191:test3:Expected cpu (32) == i (0)
  # # test3: Test terminated by assertion
  # #          FAIL  so_incoming_cpu.before_reuseport.test3
  # not ok 3 so_incoming_cpu.before_reuseport.test3

When the test failed, not-yet-accepted CLOSE_WAIT sockets received
SYN with a "challenging" SEQ number, which was sent from an unexpected
CPU that did not create the receiver.

The test basically does:

  1. for each cpu:
    1-1. create a server
    1-2. set SO_INCOMING_CPU

  2. for each cpu:
    2-1. set cpu affinity
    2-2. create some clients
    2-3. let clients connect() to the server on the same cpu
    2-4. close() clients

  3. for each server:
    3-1. accept() all child sockets
    3-2. check if all children have the same SO_INCOMING_CPU with the server

The root cause was the close() in 2-4. and net.ipv4.tcp_tw_reuse.

In a loop of 2., close() changed the client state to FIN_WAIT_2, and
the peer transitioned to CLOSE_WAIT.

In another loop of 2., connect() happened to select the same port of
the FIN_WAIT_2 socket, and it was reused as the default value of
net.ipv4.tcp_tw_reuse is 2.

As a result, the new client sent SYN to the CLOSE_WAIT socket from
a different CPU, and the receiver's sk_incoming_cpu was overwritten
with unexpected CPU ID.

Also, the SYN had a different SEQ number, so the CLOSE_WAIT socket
responded with Challenge ACK.  The new client properly returned RST
and effectively killed the CLOSE_WAIT socket.

This way, all clients were created successfully, but the error was
detected later by 3-2., ASSERT_EQ(cpu, i).

To avoid the failure, let's make sure that (i) the number of clients
is less than the number of available ports and (ii) such reuse never
happens.

Fixes: 6df96146b202 ("selftest: Add test for SO_INCOMING_CPU.")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Tested-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20240120031642.67014-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/so_incoming_cpu.c | 68 ++++++++++++++-----
 1 file changed, 50 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/net/so_incoming_cpu.c b/tools/testing/selftests/net/so_incoming_cpu.c
index a148181641026..e9fa14e107322 100644
--- a/tools/testing/selftests/net/so_incoming_cpu.c
+++ b/tools/testing/selftests/net/so_incoming_cpu.c
@@ -3,19 +3,16 @@
 #define _GNU_SOURCE
 #include <sched.h>
 
+#include <fcntl.h>
+
 #include <netinet/in.h>
 #include <sys/socket.h>
 #include <sys/sysinfo.h>
 
 #include "../kselftest_harness.h"
 
-#define CLIENT_PER_SERVER	32 /* More sockets, more reliable */
-#define NR_SERVER		self->nproc
-#define NR_CLIENT		(CLIENT_PER_SERVER * NR_SERVER)
-
 FIXTURE(so_incoming_cpu)
 {
-	int nproc;
 	int *servers;
 	union {
 		struct sockaddr addr;
@@ -56,12 +53,47 @@ FIXTURE_VARIANT_ADD(so_incoming_cpu, after_all_listen)
 	.when_to_set = AFTER_ALL_LISTEN,
 };
 
+static void write_sysctl(struct __test_metadata *_metadata,
+			 char *filename, char *string)
+{
+	int fd, len, ret;
+
+	fd = open(filename, O_WRONLY);
+	ASSERT_NE(fd, -1);
+
+	len = strlen(string);
+	ret = write(fd, string, len);
+	ASSERT_EQ(ret, len);
+}
+
+static void setup_netns(struct __test_metadata *_metadata)
+{
+	ASSERT_EQ(unshare(CLONE_NEWNET), 0);
+	ASSERT_EQ(system("ip link set lo up"), 0);
+
+	write_sysctl(_metadata, "/proc/sys/net/ipv4/ip_local_port_range", "10000 60001");
+	write_sysctl(_metadata, "/proc/sys/net/ipv4/tcp_tw_reuse", "0");
+}
+
+#define NR_PORT				(60001 - 10000 - 1)
+#define NR_CLIENT_PER_SERVER_DEFAULT	32
+static int nr_client_per_server, nr_server, nr_client;
+
 FIXTURE_SETUP(so_incoming_cpu)
 {
-	self->nproc = get_nprocs();
-	ASSERT_LE(2, self->nproc);
+	setup_netns(_metadata);
+
+	nr_server = get_nprocs();
+	ASSERT_LE(2, nr_server);
+
+	if (NR_CLIENT_PER_SERVER_DEFAULT * nr_server < NR_PORT)
+		nr_client_per_server = NR_CLIENT_PER_SERVER_DEFAULT;
+	else
+		nr_client_per_server = NR_PORT / nr_server;
+
+	nr_client = nr_client_per_server * nr_server;
 
-	self->servers = malloc(sizeof(int) * NR_SERVER);
+	self->servers = malloc(sizeof(int) * nr_server);
 	ASSERT_NE(self->servers, NULL);
 
 	self->in_addr.sin_family = AF_INET;
@@ -74,7 +106,7 @@ FIXTURE_TEARDOWN(so_incoming_cpu)
 {
 	int i;
 
-	for (i = 0; i < NR_SERVER; i++)
+	for (i = 0; i < nr_server; i++)
 		close(self->servers[i]);
 
 	free(self->servers);
@@ -110,10 +142,10 @@ int create_server(struct __test_metadata *_metadata,
 	if (variant->when_to_set == BEFORE_LISTEN)
 		set_so_incoming_cpu(_metadata, fd, cpu);
 
-	/* We don't use CLIENT_PER_SERVER here not to block
+	/* We don't use nr_client_per_server here not to block
 	 * this test at connect() if SO_INCOMING_CPU is broken.
 	 */
-	ret = listen(fd, NR_CLIENT);
+	ret = listen(fd, nr_client);
 	ASSERT_EQ(ret, 0);
 
 	if (variant->when_to_set == AFTER_LISTEN)
@@ -128,7 +160,7 @@ void create_servers(struct __test_metadata *_metadata,
 {
 	int i, ret;
 
-	for (i = 0; i < NR_SERVER; i++) {
+	for (i = 0; i < nr_server; i++) {
 		self->servers[i] = create_server(_metadata, self, variant, i);
 
 		if (i == 0) {
@@ -138,7 +170,7 @@ void create_servers(struct __test_metadata *_metadata,
 	}
 
 	if (variant->when_to_set == AFTER_ALL_LISTEN) {
-		for (i = 0; i < NR_SERVER; i++)
+		for (i = 0; i < nr_server; i++)
 			set_so_incoming_cpu(_metadata, self->servers[i], i);
 	}
 }
@@ -149,7 +181,7 @@ void create_clients(struct __test_metadata *_metadata,
 	cpu_set_t cpu_set;
 	int i, j, fd, ret;
 
-	for (i = 0; i < NR_SERVER; i++) {
+	for (i = 0; i < nr_server; i++) {
 		CPU_ZERO(&cpu_set);
 
 		CPU_SET(i, &cpu_set);
@@ -162,7 +194,7 @@ void create_clients(struct __test_metadata *_metadata,
 		ret = sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 		ASSERT_EQ(ret, 0);
 
-		for (j = 0; j < CLIENT_PER_SERVER; j++) {
+		for (j = 0; j < nr_client_per_server; j++) {
 			fd  = socket(AF_INET, SOCK_STREAM, 0);
 			ASSERT_NE(fd, -1);
 
@@ -180,8 +212,8 @@ void verify_incoming_cpu(struct __test_metadata *_metadata,
 	int i, j, fd, cpu, ret, total = 0;
 	socklen_t len = sizeof(int);
 
-	for (i = 0; i < NR_SERVER; i++) {
-		for (j = 0; j < CLIENT_PER_SERVER; j++) {
+	for (i = 0; i < nr_server; i++) {
+		for (j = 0; j < nr_client_per_server; j++) {
 			/* If we see -EAGAIN here, SO_INCOMING_CPU is broken */
 			fd = accept(self->servers[i], &self->addr, &self->addrlen);
 			ASSERT_NE(fd, -1);
@@ -195,7 +227,7 @@ void verify_incoming_cpu(struct __test_metadata *_metadata,
 		}
 	}
 
-	ASSERT_EQ(total, NR_CLIENT);
+	ASSERT_EQ(total, nr_client);
 	TH_LOG("SO_INCOMING_CPU is very likely to be "
 	       "working correctly with %d sockets.", total);
 }
-- 
GitLab


From 3e4147f33f8b647775357bae0248b9a2aeebfcd2 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 4 Jan 2024 21:11:37 +0100
Subject: [PATCH 3274/4076] x86/CPU/AMD: Add X86_FEATURE_ZEN5

Add a synthetic feature flag for Zen5.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240104201138.5072-1-bp@alien8.de
---
 arch/x86/include/asm/cpufeatures.h |  4 +---
 arch/x86/kernel/cpu/amd.c          | 25 +++++++++++++++++++++----
 2 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 29cb275a219d7..fdf723b6f6d0c 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -81,10 +81,8 @@
 #define X86_FEATURE_K6_MTRR		( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
 #define X86_FEATURE_CYRIX_ARR		( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
 #define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-
-/* CPU types for specific tunings: */
 #define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
-/* FREE, was #define X86_FEATURE_K7			( 3*32+ 5) "" Athlon */
+#define X86_FEATURE_ZEN5		( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */
 #define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
 #define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9f42d1c59e095..bc49e3b3aae02 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -538,7 +538,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 
 	/* Figure out Zen generations: */
 	switch (c->x86) {
-	case 0x17: {
+	case 0x17:
 		switch (c->x86_model) {
 		case 0x00 ... 0x2f:
 		case 0x50 ... 0x5f:
@@ -554,8 +554,8 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 			goto warn;
 		}
 		break;
-	}
-	case 0x19: {
+
+	case 0x19:
 		switch (c->x86_model) {
 		case 0x00 ... 0x0f:
 		case 0x20 ... 0x5f:
@@ -569,7 +569,17 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 			goto warn;
 		}
 		break;
-	}
+
+	case 0x1a:
+		switch (c->x86_model) {
+		case 0x00 ... 0x0f:
+			setup_force_cpu_cap(X86_FEATURE_ZEN5);
+			break;
+		default:
+			goto warn;
+		}
+		break;
+
 	default:
 		break;
 	}
@@ -1039,6 +1049,11 @@ static void init_amd_zen4(struct cpuinfo_x86 *c)
 		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
 }
 
+static void init_amd_zen5(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
 	u64 vm_cr;
@@ -1084,6 +1099,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 		init_amd_zen3(c);
 	else if (boot_cpu_has(X86_FEATURE_ZEN4))
 		init_amd_zen4(c);
+	else if (boot_cpu_has(X86_FEATURE_ZEN5))
+		init_amd_zen5(c);
 
 	/*
 	 * Enable workaround for FXSAVE leak on CPUs
-- 
GitLab


From 090e3bec01763e415bccae445f5bfe3d0c61b629 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Jan 2024 11:18:44 -0800
Subject: [PATCH 3275/4076] x86/cpu: Add model number for Intel Clearwater
 Forest processor

Server product based on the Atom Darkmont core.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240117191844.56180-1-tony.luck@intel.com
---
 arch/x86/include/asm/intel-family.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 197316121f04e..b65e9c46b9221 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -162,6 +162,8 @@
 #define INTEL_FAM6_ATOM_CRESTMONT_X	0xAF /* Sierra Forest */
 #define INTEL_FAM6_ATOM_CRESTMONT	0xB6 /* Grand Ridge */
 
+#define INTEL_FAM6_ATOM_DARKMONT_X	0xDD /* Clearwater Forest */
+
 /* Xeon Phi */
 
 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
-- 
GitLab


From 234ec0b6034b16869d45128b8cd2dc6ffe596f04 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 22 Jan 2024 09:18:07 +0800
Subject: [PATCH 3276/4076] netlink: fix potential sleeping issue in
 mqueue_flush_file

I analyze the potential sleeping issue of the following processes:
Thread A                                Thread B
...                                     netlink_create  //ref = 1
do_mq_notify                            ...
  sock = netlink_getsockbyfilp          ...     //ref = 2
  info->notify_sock = sock;             ...
...                                     netlink_sendmsg
...                                       skb = netlink_alloc_large_skb  //skb->head is vmalloced
...                                       netlink_unicast
...                                         sk = netlink_getsockbyportid //ref = 3
...                                         netlink_sendskb
...                                           __netlink_sendskb
...                                             skb_queue_tail //put skb to sk_receive_queue
...                                         sock_put //ref = 2
...                                     ...
...                                     netlink_release
...                                       deferred_put_nlk_sk //ref = 1
mqueue_flush_file
  spin_lock
  remove_notification
    netlink_sendskb
      sock_put  //ref = 0
        sk_free
          ...
          __sk_destruct
            netlink_sock_destruct
              skb_queue_purge  //get skb from sk_receive_queue
                ...
                __skb_queue_purge_reason
                  kfree_skb_reason
                    __kfree_skb
                    ...
                    skb_release_all
                      skb_release_head_state
                        netlink_skb_destructor
                          vfree(skb->head)  //sleeping while holding spinlock

In netlink_sendmsg, if the memory pointed to by skb->head is allocated by
vmalloc, and is put to sk_receive_queue queue, also the skb is not freed.
When the mqueue executes flush, the sleeping bug will occur. Use
vfree_atomic instead of vfree in netlink_skb_destructor to solve the issue.

Fixes: c05cdb1b864f ("netlink: allow large data transfers from user-space")
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Link: https://lore.kernel.org/r/20240122011807.2110357-1-shaozhengchao@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/netlink/af_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4ed8ffd58ff37..9c962347cf859 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -374,7 +374,7 @@ static void netlink_skb_destructor(struct sk_buff *skb)
 	if (is_vmalloc_addr(skb->head)) {
 		if (!skb->cloned ||
 		    !atomic_dec_return(&(skb_shinfo(skb)->dataref)))
-			vfree(skb->head);
+			vfree_atomic(skb->head);
 
 		skb->head = NULL;
 	}
-- 
GitLab


From 420332b94119cdc7db4477cc88484691cb92ae71 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Sat, 20 Jan 2024 12:18:39 +0200
Subject: [PATCH 3277/4076] ovl: mark xwhiteouts directory with
 overlay.opaque='x'

An opaque directory cannot have xwhiteouts, so instead of marking an
xwhiteouts directory with a new xattr, overload overlay.opaque xattr
for marking both opaque dir ('y') and xwhiteouts dir ('x').

This is more efficient as the overlay.opaque xattr is checked during
lookup of directory anyway.

This also prevents unnecessary checking the xattr when reading a
directory without xwhiteouts, i.e. most of the time.

Note that the xwhiteouts marker is not checked on the upper layer and
on the last layer in lowerstack, where xwhiteouts are not expected.

Fixes: bc8df7a3dc03 ("ovl: Add an alternative type of whiteout")
Cc: <stable@vger.kernel.org> # v6.7
Reviewed-by: Alexander Larsson <alexl@redhat.com>
Tested-by: Alexander Larsson <alexl@redhat.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 Documentation/filesystems/overlayfs.rst | 16 ++++++--
 fs/overlayfs/namei.c                    | 43 ++++++++++++--------
 fs/overlayfs/overlayfs.h                | 23 ++++++++---
 fs/overlayfs/ovl_entry.h                |  4 +-
 fs/overlayfs/readdir.c                  |  7 ++--
 fs/overlayfs/super.c                    | 15 +++++++
 fs/overlayfs/util.c                     | 53 +++++++++++++++----------
 7 files changed, 110 insertions(+), 51 deletions(-)

diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst
index 1c244866041a3..1655144014418 100644
--- a/Documentation/filesystems/overlayfs.rst
+++ b/Documentation/filesystems/overlayfs.rst
@@ -145,7 +145,9 @@ filesystem, an overlay filesystem needs to record in the upper filesystem
 that files have been removed.  This is done using whiteouts and opaque
 directories (non-directories are always opaque).
 
-A whiteout is created as a character device with 0/0 device number.
+A whiteout is created as a character device with 0/0 device number or
+as a zero-size regular file with the xattr "trusted.overlay.whiteout".
+
 When a whiteout is found in the upper level of a merged directory, any
 matching name in the lower level is ignored, and the whiteout itself
 is also hidden.
@@ -154,6 +156,13 @@ A directory is made opaque by setting the xattr "trusted.overlay.opaque"
 to "y".  Where the upper filesystem contains an opaque directory, any
 directory in the lower filesystem with the same name is ignored.
 
+An opaque directory should not conntain any whiteouts, because they do not
+serve any purpose.  A merge directory containing regular files with the xattr
+"trusted.overlay.whiteout", should be additionally marked by setting the xattr
+"trusted.overlay.opaque" to "x" on the merge directory itself.
+This is needed to avoid the overhead of checking the "trusted.overlay.whiteout"
+on all entries during readdir in the common case.
+
 readdir
 -------
 
@@ -534,8 +543,9 @@ A lower dir with a regular whiteout will always be handled by the overlayfs
 mount, so to support storing an effective whiteout file in an overlayfs mount an
 alternative form of whiteout is supported. This form is a regular, zero-size
 file with the "overlay.whiteout" xattr set, inside a directory with the
-"overlay.whiteouts" xattr set. Such whiteouts are never created by overlayfs,
-but can be used by userspace tools (like containers) that generate lower layers.
+"overlay.opaque" xattr set to "x" (see `whiteouts and opaque directories`_).
+These alternative whiteouts are never created by overlayfs, but can be used by
+userspace tools (like containers) that generate lower layers.
 These alternative whiteouts can be escaped using the standard xattr escape
 mechanism in order to properly nest to any depth.
 
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 984ffdaeed6ca..5764f91d283e7 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -18,10 +18,11 @@
 
 struct ovl_lookup_data {
 	struct super_block *sb;
-	struct vfsmount *mnt;
+	const struct ovl_layer *layer;
 	struct qstr name;
 	bool is_dir;
 	bool opaque;
+	bool xwhiteouts;
 	bool stop;
 	bool last;
 	char *redirect;
@@ -201,17 +202,13 @@ struct dentry *ovl_decode_real_fh(struct ovl_fs *ofs, struct ovl_fh *fh,
 	return real;
 }
 
-static bool ovl_is_opaquedir(struct ovl_fs *ofs, const struct path *path)
-{
-	return ovl_path_check_dir_xattr(ofs, path, OVL_XATTR_OPAQUE);
-}
-
 static struct dentry *ovl_lookup_positive_unlocked(struct ovl_lookup_data *d,
 						   const char *name,
 						   struct dentry *base, int len,
 						   bool drop_negative)
 {
-	struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->mnt), name, base, len);
+	struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->layer->mnt), name,
+						 base, len);
 
 	if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) {
 		if (drop_negative && ret->d_lockref.count == 1) {
@@ -232,10 +229,13 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
 			     size_t prelen, const char *post,
 			     struct dentry **ret, bool drop_negative)
 {
+	struct ovl_fs *ofs = OVL_FS(d->sb);
 	struct dentry *this;
 	struct path path;
 	int err;
 	bool last_element = !post[0];
+	bool is_upper = d->layer->idx == 0;
+	char val;
 
 	this = ovl_lookup_positive_unlocked(d, name, base, namelen, drop_negative);
 	if (IS_ERR(this)) {
@@ -253,8 +253,8 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
 	}
 
 	path.dentry = this;
-	path.mnt = d->mnt;
-	if (ovl_path_is_whiteout(OVL_FS(d->sb), &path)) {
+	path.mnt = d->layer->mnt;
+	if (ovl_path_is_whiteout(ofs, &path)) {
 		d->stop = d->opaque = true;
 		goto put_and_out;
 	}
@@ -272,7 +272,7 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
 			d->stop = true;
 			goto put_and_out;
 		}
-		err = ovl_check_metacopy_xattr(OVL_FS(d->sb), &path, NULL);
+		err = ovl_check_metacopy_xattr(ofs, &path, NULL);
 		if (err < 0)
 			goto out_err;
 
@@ -292,7 +292,12 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
 		if (d->last)
 			goto out;
 
-		if (ovl_is_opaquedir(OVL_FS(d->sb), &path)) {
+		/* overlay.opaque=x means xwhiteouts directory */
+		val = ovl_get_opaquedir_val(ofs, &path);
+		if (last_element && !is_upper && val == 'x') {
+			d->xwhiteouts = true;
+			ovl_layer_set_xwhiteouts(ofs, d->layer);
+		} else if (val == 'y') {
 			d->stop = true;
 			if (last_element)
 				d->opaque = true;
@@ -863,7 +868,8 @@ fail:
  * Returns next layer in stack starting from top.
  * Returns -1 if this is the last layer.
  */
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer)
 {
 	struct ovl_entry *oe = OVL_E(dentry);
 	struct ovl_path *lowerstack = ovl_lowerstack(oe);
@@ -871,13 +877,16 @@ int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
 	BUG_ON(idx < 0);
 	if (idx == 0) {
 		ovl_path_upper(dentry, path);
-		if (path->dentry)
+		if (path->dentry) {
+			*layer = &OVL_FS(dentry->d_sb)->layers[0];
 			return ovl_numlower(oe) ? 1 : -1;
+		}
 		idx++;
 	}
 	BUG_ON(idx > ovl_numlower(oe));
 	path->dentry = lowerstack[idx - 1].dentry;
-	path->mnt = lowerstack[idx - 1].layer->mnt;
+	*layer = lowerstack[idx - 1].layer;
+	path->mnt = (*layer)->mnt;
 
 	return (idx < ovl_numlower(oe)) ? idx + 1 : -1;
 }
@@ -1055,7 +1064,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 	old_cred = ovl_override_creds(dentry->d_sb);
 	upperdir = ovl_dentry_upper(dentry->d_parent);
 	if (upperdir) {
-		d.mnt = ovl_upper_mnt(ofs);
+		d.layer = &ofs->layers[0];
 		err = ovl_lookup_layer(upperdir, &d, &upperdentry, true);
 		if (err)
 			goto out;
@@ -1111,7 +1120,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		else if (d.is_dir || !ofs->numdatalayer)
 			d.last = lower.layer->idx == ovl_numlower(roe);
 
-		d.mnt = lower.layer->mnt;
+		d.layer = lower.layer;
 		err = ovl_lookup_layer(lower.dentry, &d, &this, false);
 		if (err)
 			goto out_put;
@@ -1278,6 +1287,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 
 	if (upperopaque)
 		ovl_dentry_set_opaque(dentry);
+	if (d.xwhiteouts)
+		ovl_dentry_set_xwhiteouts(dentry);
 
 	if (upperdentry)
 		ovl_dentry_set_upper_alias(dentry);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 5ba11eb437679..ee949f3e7c778 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -50,7 +50,6 @@ enum ovl_xattr {
 	OVL_XATTR_METACOPY,
 	OVL_XATTR_PROTATTR,
 	OVL_XATTR_XWHITEOUT,
-	OVL_XATTR_XWHITEOUTS,
 };
 
 enum ovl_inode_flag {
@@ -70,6 +69,8 @@ enum ovl_entry_flag {
 	OVL_E_UPPER_ALIAS,
 	OVL_E_OPAQUE,
 	OVL_E_CONNECTED,
+	/* Lower stack may contain xwhiteout entries */
+	OVL_E_XWHITEOUTS,
 };
 
 enum {
@@ -477,6 +478,10 @@ bool ovl_dentry_test_flag(unsigned long flag, struct dentry *dentry);
 bool ovl_dentry_is_opaque(struct dentry *dentry);
 bool ovl_dentry_is_whiteout(struct dentry *dentry);
 void ovl_dentry_set_opaque(struct dentry *dentry);
+bool ovl_dentry_has_xwhiteouts(struct dentry *dentry);
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry);
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer);
 bool ovl_dentry_has_upper_alias(struct dentry *dentry);
 void ovl_dentry_set_upper_alias(struct dentry *dentry);
 bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags);
@@ -494,11 +499,10 @@ struct file *ovl_path_open(const struct path *path, int flags);
 int ovl_copy_up_start(struct dentry *dentry, int flags);
 void ovl_copy_up_end(struct dentry *dentry);
 bool ovl_already_copied_up(struct dentry *dentry, int flags);
-bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
-			      enum ovl_xattr ox);
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox);
 bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path);
 bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path);
-bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path);
 bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
 			 const struct path *upperpath);
 
@@ -573,7 +577,13 @@ static inline bool ovl_is_impuredir(struct super_block *sb,
 		.mnt = ovl_upper_mnt(ofs),
 	};
 
-	return ovl_path_check_dir_xattr(ofs, &upperpath, OVL_XATTR_IMPURE);
+	return ovl_get_dir_xattr_val(ofs, &upperpath, OVL_XATTR_IMPURE) == 'y';
+}
+
+static inline char ovl_get_opaquedir_val(struct ovl_fs *ofs,
+					 const struct path *path)
+{
+	return ovl_get_dir_xattr_val(ofs, path, OVL_XATTR_OPAQUE);
 }
 
 static inline bool ovl_redirect_follow(struct ovl_fs *ofs)
@@ -680,7 +690,8 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin,
 struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh);
 struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
 				struct dentry *origin, bool verify);
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer);
 int ovl_verify_lowerdata(struct dentry *dentry);
 struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 5fa9c58af65f2..cb449ab310a7a 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -40,6 +40,8 @@ struct ovl_layer {
 	int idx;
 	/* One fsid per unique underlying sb (upper fsid == 0) */
 	int fsid;
+	/* xwhiteouts were found on this layer */
+	bool has_xwhiteouts;
 };
 
 struct ovl_path {
@@ -59,7 +61,7 @@ struct ovl_fs {
 	unsigned int numfs;
 	/* Number of data-only lower layers */
 	unsigned int numdatalayer;
-	const struct ovl_layer *layers;
+	struct ovl_layer *layers;
 	struct ovl_sb *fs;
 	/* workbasedir is the path at workdir= mount option */
 	struct dentry *workbasedir;
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index e71156baa7bcc..0ca8af060b0c1 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -305,8 +305,6 @@ static inline int ovl_dir_read(const struct path *realpath,
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 
-	rdd->in_xwhiteouts_dir = rdd->dentry &&
-		ovl_path_check_xwhiteouts_xattr(OVL_FS(rdd->dentry->d_sb), realpath);
 	rdd->first_maybe_whiteout = NULL;
 	rdd->ctx.pos = 0;
 	do {
@@ -359,10 +357,13 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list,
 		.is_lowest = false,
 	};
 	int idx, next;
+	const struct ovl_layer *layer;
 
 	for (idx = 0; idx != -1; idx = next) {
-		next = ovl_path_next(idx, dentry, &realpath);
+		next = ovl_path_next(idx, dentry, &realpath, &layer);
 		rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry;
+		rdd.in_xwhiteouts_dir = layer->has_xwhiteouts &&
+					ovl_dentry_has_xwhiteouts(dentry);
 
 		if (next != -1) {
 			err = ovl_dir_read(&realpath, &rdd);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 4ab66e3d4cff9..2eef6c70b2aed 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1249,6 +1249,7 @@ static struct dentry *ovl_get_root(struct super_block *sb,
 				   struct ovl_entry *oe)
 {
 	struct dentry *root;
+	struct ovl_fs *ofs = OVL_FS(sb);
 	struct ovl_path *lowerpath = ovl_lowerstack(oe);
 	unsigned long ino = d_inode(lowerpath->dentry)->i_ino;
 	int fsid = lowerpath->layer->fsid;
@@ -1270,6 +1271,20 @@ static struct dentry *ovl_get_root(struct super_block *sb,
 			ovl_set_flag(OVL_IMPURE, d_inode(root));
 	}
 
+	/* Look for xwhiteouts marker except in the lowermost layer */
+	for (int i = 0; i < ovl_numlower(oe) - 1; i++, lowerpath++) {
+		struct path path = {
+			.mnt = lowerpath->layer->mnt,
+			.dentry = lowerpath->dentry,
+		};
+
+		/* overlay.opaque=x means xwhiteouts directory */
+		if (ovl_get_opaquedir_val(ofs, &path) == 'x') {
+			ovl_layer_set_xwhiteouts(ofs, lowerpath->layer);
+			ovl_dentry_set_xwhiteouts(root);
+		}
+	}
+
 	/* Root is always merge -> can have whiteouts */
 	ovl_set_flag(OVL_WHITEOUTS, d_inode(root));
 	ovl_dentry_set_flag(OVL_E_CONNECTED, root);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 0217094c23ea6..a8e17f14d7a21 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -461,6 +461,33 @@ void ovl_dentry_set_opaque(struct dentry *dentry)
 	ovl_dentry_set_flag(OVL_E_OPAQUE, dentry);
 }
 
+bool ovl_dentry_has_xwhiteouts(struct dentry *dentry)
+{
+	return ovl_dentry_test_flag(OVL_E_XWHITEOUTS, dentry);
+}
+
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry)
+{
+	ovl_dentry_set_flag(OVL_E_XWHITEOUTS, dentry);
+}
+
+/*
+ * ovl_layer_set_xwhiteouts() is called before adding the overlay dir
+ * dentry to dcache, while readdir of that same directory happens after
+ * the overlay dir dentry is in dcache, so if some cpu observes that
+ * ovl_dentry_is_xwhiteouts(), it will also observe layer->has_xwhiteouts
+ * for the layers where xwhiteouts marker was found in that merge dir.
+ */
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer)
+{
+	if (layer->has_xwhiteouts)
+		return;
+
+	/* Write once to read-mostly layer properties */
+	ofs->layers[layer->idx].has_xwhiteouts = true;
+}
+
 /*
  * For hard links and decoded file handles, it's possible for ovl_dentry_upper()
  * to return positive, while there's no actual upper alias for the inode.
@@ -739,19 +766,6 @@ bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path)
 	return res >= 0;
 }
 
-bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path)
-{
-	struct dentry *dentry = path->dentry;
-	int res;
-
-	/* xattr.whiteouts must be a directory */
-	if (!d_is_dir(dentry))
-		return false;
-
-	res = ovl_path_getxattr(ofs, path, OVL_XATTR_XWHITEOUTS, NULL, 0);
-	return res >= 0;
-}
-
 /*
  * Load persistent uuid from xattr into s_uuid if found, or store a new
  * random generated value in s_uuid and in xattr.
@@ -811,20 +825,17 @@ fail:
 	return false;
 }
 
-bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
-			       enum ovl_xattr ox)
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox)
 {
 	int res;
 	char val;
 
 	if (!d_is_dir(path->dentry))
-		return false;
+		return 0;
 
 	res = ovl_path_getxattr(ofs, path, ox, &val, 1);
-	if (res == 1 && val == 'y')
-		return true;
-
-	return false;
+	return res == 1 ? val : 0;
 }
 
 #define OVL_XATTR_OPAQUE_POSTFIX	"opaque"
@@ -837,7 +848,6 @@ bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
 #define OVL_XATTR_METACOPY_POSTFIX	"metacopy"
 #define OVL_XATTR_PROTATTR_POSTFIX	"protattr"
 #define OVL_XATTR_XWHITEOUT_POSTFIX	"whiteout"
-#define OVL_XATTR_XWHITEOUTS_POSTFIX	"whiteouts"
 
 #define OVL_XATTR_TAB_ENTRY(x) \
 	[x] = { [false] = OVL_XATTR_TRUSTED_PREFIX x ## _POSTFIX, \
@@ -854,7 +864,6 @@ const char *const ovl_xattr_table[][2] = {
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_METACOPY),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_PROTATTR),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUT),
-	OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUTS),
 };
 
 int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry,
-- 
GitLab


From c41336f4d69057cbf88fed47951379b384540df5 Mon Sep 17 00:00:00 2001
From: Eugen Hristev <eugen.hristev@collabora.com>
Date: Mon, 25 Dec 2023 15:36:15 +0200
Subject: [PATCH 3278/4076] pmdomain: mediatek: fix race conditions with genpd

If the power domains are registered first with genpd and *after that*
the driver attempts to power them on in the probe sequence, then it is
possible that a race condition occurs if genpd tries to power them on
in the same time.
The same is valid for powering them off before unregistering them
from genpd.
Attempt to fix race conditions by first removing the domains from genpd
and *after that* powering down domains.
Also first power up the domains and *after that* register them
to genpd.

Fixes: 59b644b01cf4 ("soc: mediatek: Add MediaTek SCPSYS power domains")
Signed-off-by: Eugen Hristev <eugen.hristev@collabora.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20231225133615.78993-1-eugen.hristev@collabora.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/mediatek/mtk-pm-domains.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c
index e26dc17d07ad7..e274e3315fe7a 100644
--- a/drivers/pmdomain/mediatek/mtk-pm-domains.c
+++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c
@@ -561,6 +561,11 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren
 			goto err_put_node;
 		}
 
+		/* recursive call to add all subdomains */
+		ret = scpsys_add_subdomain(scpsys, child);
+		if (ret)
+			goto err_put_node;
+
 		ret = pm_genpd_add_subdomain(parent_pd, child_pd);
 		if (ret) {
 			dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n",
@@ -570,11 +575,6 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren
 			dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name,
 				child_pd->name);
 		}
-
-		/* recursive call to add all subdomains */
-		ret = scpsys_add_subdomain(scpsys, child);
-		if (ret)
-			goto err_put_node;
 	}
 
 	return 0;
@@ -588,9 +588,6 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd)
 {
 	int ret;
 
-	if (scpsys_domain_is_on(pd))
-		scpsys_power_off(&pd->genpd);
-
 	/*
 	 * We're in the error cleanup already, so we only complain,
 	 * but won't emit another error on top of the original one.
@@ -600,6 +597,8 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd)
 		dev_err(pd->scpsys->dev,
 			"failed to remove domain '%s' : %d - state may be inconsistent\n",
 			pd->genpd.name, ret);
+	if (scpsys_domain_is_on(pd))
+		scpsys_power_off(&pd->genpd);
 
 	clk_bulk_put(pd->num_clks, pd->clks);
 	clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks);
-- 
GitLab


From 435e202d645c197dcfd39d7372eb2a56529b6640 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 22 Jan 2024 18:20:01 +0800
Subject: [PATCH 3279/4076] ipv6: init the accept_queue's spinlocks in
 inet6_create

In commit 198bc90e0e73("tcp: make sure init the accept_queue's spinlocks
once"), the spinlocks of accept_queue are initialized only when socket is
created in the inet4 scenario. The locks are not initialized when socket
is created in the inet6 scenario. The kernel reports the following error:
INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe
you didn't initialize this object before use?
turning off the locking correctness validator.
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
Call Trace:
<TASK>
	dump_stack_lvl (lib/dump_stack.c:107)
	register_lock_class (kernel/locking/lockdep.c:1289)
	__lock_acquire (kernel/locking/lockdep.c:5015)
	lock_acquire.part.0 (kernel/locking/lockdep.c:5756)
	_raw_spin_lock_bh (kernel/locking/spinlock.c:178)
	inet_csk_listen_stop (net/ipv4/inet_connection_sock.c:1386)
	tcp_disconnect (net/ipv4/tcp.c:2981)
	inet_shutdown (net/ipv4/af_inet.c:935)
	__sys_shutdown (./include/linux/file.h:32 net/socket.c:2438)
	__x64_sys_shutdown (net/socket.c:2445)
	do_syscall_64 (arch/x86/entry/common.c:52)
	entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129)
RIP: 0033:0x7f52ecd05a3d
Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7
48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
ff 73 01 c3 48 8b 0d ab a3 0e 00 f7 d8 64 89 01 48
RSP: 002b:00007f52ecf5dde8 EFLAGS: 00000293 ORIG_RAX: 0000000000000030
RAX: ffffffffffffffda RBX: 00007f52ecf5e640 RCX: 00007f52ecd05a3d
RDX: 00007f52ecc8b188 RSI: 0000000000000000 RDI: 0000000000000004
RBP: 00007f52ecf5de20 R08: 00007ffdae45c69f R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000293 R12: 00007f52ecf5e640
R13: 0000000000000000 R14: 00007f52ecc8b060 R15: 00007ffdae45c6e0

Fixes: 198bc90e0e73 ("tcp: make sure init the accept_queue's spinlocks once")
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240122102001.2851701-1-shaozhengchao@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/af_inet6.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 13a1833a4df52..959bfd9f6344f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -199,6 +199,9 @@ lookup_protocol:
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
+	if (INET_PROTOSW_ICSK & answer_flags)
+		inet_init_csk_locks(sk);
+
 	inet = inet_sk(sk);
 	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 
-- 
GitLab


From 574bf7bbe83794a902679846770f75a9b7f28176 Mon Sep 17 00:00:00 2001
From: Kamal Dasu <kamal.dasu@broadcom.com>
Date: Tue, 9 Jan 2024 16:00:32 -0500
Subject: [PATCH 3280/4076] spi: bcm-qspi: fix SFDP BFPT read by usig mspi read

SFDP read shall use the mspi reads when using the bcm_qspi_exec_mem_op()
call. This fixes SFDP parameter page read failures seen with parts that
now use SFDP protocol to read the basic flash parameter table.

Fixes: 5f195ee7d830 ("spi: bcm-qspi: Implement the spi_mem interface")
Signed-off-by: Kamal Dasu <kamal.dasu@broadcom.com>
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://msgid.link/r/20240109210033.43249-1-kamal.dasu@broadcom.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-bcm-qspi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index d96222e6d7d2d..cfdaa5eaec76d 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -19,7 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
-#include <linux/spi/spi-mem.h>
+#include <linux/mtd/spi-nor.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
 #include "spi-bcm-qspi.h"
@@ -1221,7 +1221,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem,
 
 	/* non-aligned and very short transfers are handled by MSPI */
 	if (!IS_ALIGNED((uintptr_t)addr, 4) || !IS_ALIGNED((uintptr_t)buf, 4) ||
-	    len < 4)
+	    len < 4 || op->cmd.opcode == SPINOR_OP_RDSFDP)
 		mspi_read = true;
 
 	if (!has_bspi(qspi) || mspi_read)
-- 
GitLab


From e267a5b3ec59ce88d6be21078e2deb807ca3b436 Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Wed, 10 Jan 2024 09:54:03 +0100
Subject: [PATCH 3281/4076] spi: spi-imx: Use dev_err_probe for failed DMA
 channel requests

If dma_request_chan() fails, no error is shown nor any information is
shown in /sys/kernel/debug/devices_deferred if -EPROBE_DEFER is returned.
Use dev_err_probe to fix both problems.

Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://msgid.link/r/20240110085403.457089-1-alexander.stein@ew.tq-group.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-imx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 272bc871a848b..546cdce525fc5 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1344,7 +1344,7 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 	controller->dma_tx = dma_request_chan(dev, "tx");
 	if (IS_ERR(controller->dma_tx)) {
 		ret = PTR_ERR(controller->dma_tx);
-		dev_dbg(dev, "can't get the TX DMA channel, error %d!\n", ret);
+		dev_err_probe(dev, ret, "can't get the TX DMA channel!\n");
 		controller->dma_tx = NULL;
 		goto err;
 	}
@@ -1353,7 +1353,7 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 	controller->dma_rx = dma_request_chan(dev, "rx");
 	if (IS_ERR(controller->dma_rx)) {
 		ret = PTR_ERR(controller->dma_rx);
-		dev_dbg(dev, "can't get the RX DMA channel, error %d\n", ret);
+		dev_err_probe(dev, ret, "can't get the RX DMA channel!\n");
 		controller->dma_rx = NULL;
 		goto err;
 	}
-- 
GitLab


From 633cd6fe6e1993ba80e0954c2db127a0b1a3e66f Mon Sep 17 00:00:00 2001
From: Amit Kumar Mahapatra <amit.kumar-mahapatra@amd.com>
Date: Mon, 18 Dec 2023 14:36:52 +0530
Subject: [PATCH 3282/4076] spi: spi-cadence: Reverse the order of interleaved
 write and read operations

In the existing implementation, when executing interleaved write and read
operations in the ISR for a transfer length greater than the FIFO size,
the TXFIFO write precedes the RXFIFO read. Consequently, the initially
received data in the RXFIFO is pushed out and lost, leading to a failure
in data integrity. To address this issue, reverse the order of interleaved
operations and conduct the RXFIFO read followed by the TXFIFO write.

Fixes: 6afe2ae8dc48 ("spi: spi-cadence: Interleave write of TX and read of RX FIFO")
Signed-off-by: Amit Kumar Mahapatra <amit.kumar-mahapatra@amd.com>
Link: https://msgid.link/r/20231218090652.18403-1-amit.kumar-mahapatra@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cadence.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index a50eb4db79de8..e5140532071d2 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -317,6 +317,15 @@ static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx)
 	xspi->rx_bytes -= nrx;
 
 	while (ntx || nrx) {
+		if (nrx) {
+			u8 data = cdns_spi_read(xspi, CDNS_SPI_RXD);
+
+			if (xspi->rxbuf)
+				*xspi->rxbuf++ = data;
+
+			nrx--;
+		}
+
 		if (ntx) {
 			if (xspi->txbuf)
 				cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
@@ -326,14 +335,6 @@ static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx)
 			ntx--;
 		}
 
-		if (nrx) {
-			u8 data = cdns_spi_read(xspi, CDNS_SPI_RXD);
-
-			if (xspi->rxbuf)
-				*xspi->rxbuf++ = data;
-
-			nrx--;
-		}
 	}
 }
 
-- 
GitLab


From afb2a4fb84555ef9e61061f6ea63ed7087b295d5 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Fri, 12 Jan 2024 19:37:29 +0100
Subject: [PATCH 3283/4076] riscv/efistub: Ensure GP-relative addressing is not
 used

The cflags for the RISC-V efistub were missing -mno-relax, thus were
under the risk that the compiler could use GP-relative addressing. That
happened for _edata with binutils-2.41 and kernel 6.1, causing the
relocation to fail due to an invalid kernel_size in handle_kernel_image.
It was not yet observed with newer versions, but that may just be luck.

Cc: <stable@vger.kernel.org>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 06964a3c130f6..d561d7de46a99 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -28,7 +28,7 @@ cflags-$(CONFIG_ARM)		+= -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \
 				   -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \
 				   -DEFI_HAVE_STRCMP -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
-cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE
+cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE -mno-relax
 cflags-$(CONFIG_LOONGARCH)	+= -fpie
 
 cflags-$(CONFIG_EFI_PARAMS_FROM_FDT)	+= -I$(srctree)/scripts/dtc/libfdt
-- 
GitLab


From d2baf8cc82c17459fca019a12348efcf86bfec29 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 16 Jan 2024 14:52:27 +0100
Subject: [PATCH 3284/4076] riscv/efistub: Tighten ELF relocation check

The EFI stub makefile contains logic to ensure that the objects that
make up the stub do not contain relocations that require runtime fixups
(typically to account for the runtime load address of the executable)

On RISC-V, we also avoid GP based relocations, as they require that GP
is assigned the correct base in the startup code, which is not
implemented in the EFI stub.

So add these relocation types to the grep expression that is used to
carry out this check.

Link: https://lkml.kernel.org/r/42c63cb9-87d0-49db-9af8-95771b186684%40siemens.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index d561d7de46a99..73f4810f6db38 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -143,7 +143,7 @@ STUBCOPY_RELOC-$(CONFIG_ARM64)	:= R_AARCH64_ABS
 # exist.
 STUBCOPY_FLAGS-$(CONFIG_RISCV)	+= --prefix-alloc-sections=.init \
 				   --prefix-symbols=__efistub_
-STUBCOPY_RELOC-$(CONFIG_RISCV)	:= R_RISCV_HI20
+STUBCOPY_RELOC-$(CONFIG_RISCV)	:= -E R_RISCV_HI20\|R_RISCV_$(BITS)\|R_RISCV_RELAX
 
 # For LoongArch, keep all the symbols in .init section and make sure that no
 # absolute symbols references exist.
-- 
GitLab


From 67794f882adca00d043899ac248bc002751da9f6 Mon Sep 17 00:00:00 2001
From: Alexander Tsoy <alexander@tsoy.me>
Date: Tue, 23 Jan 2024 16:46:35 +0300
Subject: [PATCH 3285/4076] ALSA: usb-audio: Skip setting clock selector for
 single connections

Since commit 086b957cc17f5 ("ALSA: usb-audio: Skip the clock selector
inquiry for single connections") we are already skipping clock selector
inquiry if only one clock source is connected, but we are still sending
a set request. Lets skip that too.

This should fix errors when setting a sample rate on devices that don't
have any controls present within the clock selector. An example of such
device is the new revision of MOTU M Series (07fd:000b):

      AudioControl Interface Descriptor:
        bLength                 8
        bDescriptorType        36
        bDescriptorSubtype     11 (CLOCK_SELECTOR)
        bClockID                1
        bNrInPins               1
        baCSourceID(0)          2
        bmControls           0x00
        iClockSelector          0

Perhaps we also should check if clock selectors are readable and writeable
like we already do for clock sources, but this is out of scope of this
patch.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=217601
Signed-off-by: Alexander Tsoy <alexander@tsoy.me>
Link: https://lore.kernel.org/r/20240123134635.54026-1-alexander@tsoy.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/clock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 33db334e65566..94e4aaeafe588 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -325,7 +325,8 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 					      visited, validate);
 		if (ret > 0) {
 			/* Skip setting clock selector again for some devices */
-			if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR)
+			if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR ||
+			    pins == 1)
 				return ret;
 			err = uac_clock_selector_set_val(chip, entity_id, cur);
 			if (err < 0)
-- 
GitLab


From 834bf76add3e6168038150f162cbccf1fd492a67 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Mon, 22 Jan 2024 15:27:48 -0500
Subject: [PATCH 3286/4076] eventfs: Save directory inodes in the eventfs_inode
 structure

The eventfs inodes and directories are allocated when referenced. But this
leaves the issue of keeping consistent inode numbers and the number is
only saved in the inode structure itself. When the inode is no longer
referenced, it can be freed. When the file that the inode was representing
is referenced again, the inode is once again created, but the inode number
needs to be the same as it was before.

Just making the inode numbers the same for all files is fine, but that
does not work with directories. The find command will check for loops via
the inode number and having the same inode number for directories triggers:

  # find /sys/kernel/tracing
find: File system loop detected;
'/sys/kernel/debug/tracing/events/initcall/initcall_finish' is part of the same file system loop as
'/sys/kernel/debug/tracing/events/initcall'.
[..]

Linus pointed out that the eventfs_inode structure ends with a single
32bit int, and on 64 bit machines, there's likely a 4 byte hole due to
alignment. We can use this hole to store the inode number for the
eventfs_inode. All directories in eventfs are represented by an
eventfs_inode and that data structure can hold its inode number.

That last int was also purposely placed at the end of the structure to
prevent holes from within. Now that there's a 4 byte number to hold the
inode, both the inode number and the last integer can be moved up in the
structure for better cache locality, where the llist and rcu fields can be
moved to the end as they are only used when the eventfs_inode is being
deleted.

Link: https://lore.kernel.org/all/CAMuHMdXKiorg-jiuKoZpfZyDJ3Ynrfb8=X+c7x0Eewxn-YRdCA@mail.gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240122152748.46897388@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Fixes: 53c41052ba31 ("eventfs: Have the inodes all for files and directories all be the same")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
 fs/tracefs/event_inode.c | 14 +++++++++++---
 fs/tracefs/internal.h    |  7 ++++---
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 6795fda2af191..6b211522a13ec 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -34,7 +34,15 @@ static DEFINE_MUTEX(eventfs_mutex);
 
 /* Choose something "unique" ;-) */
 #define EVENTFS_FILE_INODE_INO		0x12c4e37
-#define EVENTFS_DIR_INODE_INO		0x134b2f5
+
+/* Just try to make something consistent and unique */
+static int eventfs_dir_ino(struct eventfs_inode *ei)
+{
+	if (!ei->ino)
+		ei->ino = get_next_ino();
+
+	return ei->ino;
+}
 
 /*
  * The eventfs_inode (ei) itself is protected by SRCU. It is released from
@@ -396,7 +404,7 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
 	inode->i_fop = &eventfs_file_operations;
 
 	/* All directories will have the same inode number */
-	inode->i_ino = EVENTFS_DIR_INODE_INO;
+	inode->i_ino = eventfs_dir_ino(ei);
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
@@ -802,7 +810,7 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 
 		name = ei_child->name;
 
-		ino = EVENTFS_DIR_INODE_INO;
+		ino = eventfs_dir_ino(ei_child);
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
 			goto out_dec;
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 12b7d0150ae9e..45397df9bb65b 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -55,6 +55,10 @@ struct eventfs_inode {
 	struct eventfs_attr		*entry_attrs;
 	struct eventfs_attr		attr;
 	void				*data;
+	unsigned int			is_freed:1;
+	unsigned int			is_events:1;
+	unsigned int			nr_entries:30;
+	unsigned int			ino;
 	/*
 	 * Union - used for deletion
 	 * @llist:	for calling dput() if needed after RCU
@@ -64,9 +68,6 @@ struct eventfs_inode {
 		struct llist_node	llist;
 		struct rcu_head		rcu;
 	};
-	unsigned int			is_freed:1;
-	unsigned int			is_events:1;
-	unsigned int			nr_entries:30;
 };
 
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
-- 
GitLab


From a67e1f0bd4564b485e0f0c3ed7f6bf17688be268 Mon Sep 17 00:00:00 2001
From: Romain Naour <romain.naour@skf.com>
Date: Tue, 23 Jan 2024 12:14:56 +0100
Subject: [PATCH 3287/4076] regulator: ti-abb: don't use
 devm_platform_ioremap_resource_byname for shared interrupt register

We can't use devm_platform_ioremap_resource_byname() to remap the
interrupt register that can be shared between
regulator-abb-{ivahd,dspeve,gpu} drivers instances.

The combined helper introduce a call to devm_request_mem_region() that
creates a new busy resource region on PRM_IRQSTATUS_MPU register
(0x4ae06010). The first devm_request_mem_region() call succeeds for
regulator-abb-ivahd but fails for the two other regulator-abb-dspeve
and regulator-abb-gpu.

  # cat /proc/iomem | grep -i 4ae06
  4ae06010-4ae06013 : 4ae07e34.regulator-abb-ivahd int-address
  4ae06014-4ae06017 : 4ae07ddc.regulator-abb-mpu int-address

regulator-abb-dspeve and regulator-abb-gpu are missing due to
devm_request_mem_region() failure (EBUSY):

  [    1.326660] ti_abb 4ae07e30.regulator-abb-dspeve: can't request region for resource [mem 0x4ae06010-0x4ae06013]
  [    1.326660] ti_abb: probe of 4ae07e30.regulator-abb-dspeve failed with error -16
  [    1.327239] ti_abb 4ae07de4.regulator-abb-gpu: can't request region for resource [mem 0x4ae06010-0x4ae06013]
  [    1.327270] ti_abb: probe of 4ae07de4.regulator-abb-gpu failed with error -16

>From arm/boot/dts/dra7.dtsi:

The abb_mpu is the only instance using its own interrupt register:
  (0x4ae06014) PRM_IRQSTATUS_MPU_2, ABB_MPU_DONE_ST (bit 7)

The other tree instances (abb_ivahd, abb_dspeve, abb_gpu) share
PRM_IRQSTATUS_MPU register (0x4ae06010) but use different bits
ABB_IVA_DONE_ST (bit 30), ABB_DSPEVE_DONE_ST( bit 29) and
ABB_GPU_DONE_ST (but 28).

The commit b36c6b1887ff ("regulator: ti-abb: Make use of the helper
function devm_ioremap related") overlooked the following comment
implicitly explaining why devm_ioremap() is used in this case:

  /*
   * We may have shared interrupt register offsets which are
   * write-1-to-clear between domains ensuring exclusivity.
   */

Fixes and partially reverts commit b36c6b1887ff ("regulator: ti-abb:
Make use of the helper function devm_ioremap related").

Improve the existing comment to avoid further conversion to
devm_platform_ioremap_resource_byname().

Fixes: b36c6b1887ff ("regulator: ti-abb: Make use of the helper function devm_ioremap related")
Signed-off-by: Romain Naour <romain.naour@skf.com>
Reviewed-by: Yoann Congal <yoann.congal@smile.fr>
Link: https://msgid.link/r/20240123111456.739381-1-romain.naour@smile.fr
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/ti-abb-regulator.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c
index f48214e2c3b46..04133510e5af7 100644
--- a/drivers/regulator/ti-abb-regulator.c
+++ b/drivers/regulator/ti-abb-regulator.c
@@ -726,9 +726,25 @@ static int ti_abb_probe(struct platform_device *pdev)
 			return PTR_ERR(abb->setup_reg);
 	}
 
-	abb->int_base = devm_platform_ioremap_resource_byname(pdev, "int-address");
-	if (IS_ERR(abb->int_base))
-		return PTR_ERR(abb->int_base);
+	pname = "int-address";
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, pname);
+	if (!res) {
+		dev_err(dev, "Missing '%s' IO resource\n", pname);
+		return -ENODEV;
+	}
+	/*
+	 * The MPU interrupt status register (PRM_IRQSTATUS_MPU) is
+	 * shared between regulator-abb-{ivahd,dspeve,gpu} driver
+	 * instances. Therefore use devm_ioremap() rather than
+	 * devm_platform_ioremap_resource_byname() to avoid busy
+	 * resource region conflicts.
+	 */
+	abb->int_base = devm_ioremap(dev, res->start,
+					     resource_size(res));
+	if (!abb->int_base) {
+		dev_err(dev, "Unable to map '%s'\n", pname);
+		return -ENOMEM;
+	}
 
 	/* Map Optional resources */
 	pname = "efuse-address";
-- 
GitLab


From de8b6e1c231a95abf95ad097b993d34b31458ec9 Mon Sep 17 00:00:00 2001
From: Devyn Liu <liudingyuan@huawei.com>
Date: Tue, 23 Jan 2024 15:11:49 +0800
Subject: [PATCH 3288/4076] spi: hisi-sfc-v3xx: Return IRQ_NONE if no
 interrupts were detected

Return IRQ_NONE from the interrupt handler when no interrupt was
detected. Because an empty interrupt will cause a null pointer error:

    Unable to handle kernel NULL pointer dereference at virtual
  address 0000000000000008
    Call trace:
        complete+0x54/0x100
        hisi_sfc_v3xx_isr+0x2c/0x40 [spi_hisi_sfc_v3xx]
        __handle_irq_event_percpu+0x64/0x1e0
        handle_irq_event+0x7c/0x1cc

Signed-off-by: Devyn Liu <liudingyuan@huawei.com>
Link: https://msgid.link/r/20240123071149.917678-1-liudingyuan@huawei.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-hisi-sfc-v3xx.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/spi/spi-hisi-sfc-v3xx.c b/drivers/spi/spi-hisi-sfc-v3xx.c
index 9d22018f7985f..1301d14483d48 100644
--- a/drivers/spi/spi-hisi-sfc-v3xx.c
+++ b/drivers/spi/spi-hisi-sfc-v3xx.c
@@ -377,6 +377,11 @@ static const struct spi_controller_mem_ops hisi_sfc_v3xx_mem_ops = {
 static irqreturn_t hisi_sfc_v3xx_isr(int irq, void *data)
 {
 	struct hisi_sfc_v3xx_host *host = data;
+	u32 reg;
+
+	reg = readl(host->regbase + HISI_SFC_V3XX_INT_STAT);
+	if (!reg)
+		return IRQ_NONE;
 
 	hisi_sfc_v3xx_disable_int(host);
 
-- 
GitLab


From 13f3956eb5681a4045a8dfdef48df5dc4d9f58a6 Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Sun, 21 Jan 2024 21:26:34 +0100
Subject: [PATCH 3289/4076] block: Fix WARNING in _copy_from_iter

Syzkaller reports a warning in _copy_from_iter because an
iov_iter is supposedly used in the wrong direction. The reason
is that syzcaller managed to generate a request with
a transfer direction of SG_DXFER_TO_FROM_DEV. This instructs
the kernel to copy user buffers into the kernel, read into
the copied buffers and then copy the data back to user space.

Thus the iovec is used in both directions.

Detect this situation in the block layer and construct a new
iterator with the correct direction for the copy-in.

Reported-by: syzbot+a532b03fdfee2c137666@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/0000000000009b92c10604d7a5e9@google.com/t/
Reported-by: syzbot+63dec323ac56c28e644f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/0000000000003faaa105f6e7c658@google.com/T/
Signed-off-by: Christian A. Ehrhardt <lk@c--e.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240121202634.275068-1-lk@c--e.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/block/blk-map.c b/block/blk-map.c
index 8584babf3ea0c..71210cdb34426 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -205,12 +205,19 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 	/*
 	 * success
 	 */
-	if ((iov_iter_rw(iter) == WRITE &&
-	     (!map_data || !map_data->null_mapped)) ||
-	    (map_data && map_data->from_user)) {
+	if (iov_iter_rw(iter) == WRITE &&
+	     (!map_data || !map_data->null_mapped)) {
 		ret = bio_copy_from_iter(bio, iter);
 		if (ret)
 			goto cleanup;
+	} else if (map_data && map_data->from_user) {
+		struct iov_iter iter2 = *iter;
+
+		/* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */
+		iter2.data_source = ITER_SOURCE;
+		ret = bio_copy_from_iter(bio, &iter2);
+		if (ret)
+			goto cleanup;
 	} else {
 		if (bmd->is_our_pages)
 			zero_fill_bio(bio);
-- 
GitLab


From 41353fbad4f551e82c2792f7e82ac225c79cc710 Mon Sep 17 00:00:00 2001
From: Guixin Liu <kanie@linux.alibaba.com>
Date: Thu, 18 Jan 2024 20:51:45 +0800
Subject: [PATCH 3290/4076] nvmet: unify aer type enum

The host and target use two definition of aer type, unify
them into a single one.

Signed-off-by: Guixin Liu <kanie@linux.alibaba.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/core.c      | 4 ++--
 drivers/nvme/target/discovery.c | 2 +-
 include/linux/nvme.h            | 6 ------
 3 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index d26aa30f87026..fa35e65915f0c 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -248,7 +248,7 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 		nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
 		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_NS_ATTR))
 			continue;
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+		nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 				NVME_AER_NOTICE_NS_CHANGED,
 				NVME_LOG_CHANGED_NS);
 	}
@@ -265,7 +265,7 @@ void nvmet_send_ana_event(struct nvmet_subsys *subsys,
 			continue;
 		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_ANA_CHANGE))
 			continue;
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+		nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
 	}
 	mutex_unlock(&subsys->lock);
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 668d257fa9863..68e82ccc0e4e3 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -21,7 +21,7 @@ static void __nvmet_disc_changed(struct nvmet_port *port,
 	if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_DISC_CHANGE))
 		return;
 
-	nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+	nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 			      NVME_AER_NOTICE_DISC_CHANGED, NVME_LOG_DISC);
 }
 
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 462c21e0e4176..68eff8c86ce34 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -816,12 +816,6 @@ struct nvme_reservation_status_ext {
 	struct nvme_registered_ctrl_ext regctl_eds[];
 };
 
-enum nvme_async_event_type {
-	NVME_AER_TYPE_ERROR	= 0,
-	NVME_AER_TYPE_SMART	= 1,
-	NVME_AER_TYPE_NOTICE	= 2,
-};
-
 /* I/O commands */
 
 enum nvme_opcode {
-- 
GitLab


From 5d390df3bdd13d178eb2e02e60e9a480f7103f7b Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Tue, 23 Jan 2024 13:40:00 +0300
Subject: [PATCH 3291/4076] smb: client: delete "true", "false" defines

Kernel has its own official true/false definitions.

The defines aren't even used in this file.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smbencrypt.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/fs/smb/client/smbencrypt.c b/fs/smb/client/smbencrypt.c
index f0ce26414f173..1d1ee9f18f373 100644
--- a/fs/smb/client/smbencrypt.c
+++ b/fs/smb/client/smbencrypt.c
@@ -26,13 +26,6 @@
 #include "cifsproto.h"
 #include "../common/md4.h"
 
-#ifndef false
-#define false 0
-#endif
-#ifndef true
-#define true 1
-#endif
-
 /* following came from the other byteorder.h to avoid include conflicts */
 #define CVAL(buf,pos) (((unsigned char *)(buf))[pos])
 #define SSVALX(buf,pos,val) (CVAL(buf,pos)=(val)&0xFF,CVAL(buf,pos+1)=(val)>>8)
-- 
GitLab


From d2d0223441d3caad65f6978c07869321bce968e0 Mon Sep 17 00:00:00 2001
From: Gustavo Sousa <gustavo.sousa@intel.com>
Date: Tue, 23 Jan 2024 13:21:58 -0300
Subject: [PATCH 3292/4076] docs/sphinx: Fix TOC scroll hack for the home page

When on the documentation home page, there won't be any ".current"
element since no entry from the TOC was selected yet. That results in a
javascript error. Fix that by only trying to set the scrollTop if we
have matches for current entries.

Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20240123162157.61819-2-gustavo.sousa@intel.com
---
 Documentation/sphinx/templates/kernel-toc.html | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/sphinx/templates/kernel-toc.html b/Documentation/sphinx/templates/kernel-toc.html
index b58efa99df527..41f1efbe64bb2 100644
--- a/Documentation/sphinx/templates/kernel-toc.html
+++ b/Documentation/sphinx/templates/kernel-toc.html
@@ -12,5 +12,7 @@
 <script type="text/javascript"> <!--
   var sbar = document.getElementsByClassName("sphinxsidebar")[0];
   let currents = document.getElementsByClassName("current")
-  sbar.scrollTop = currents[currents.length - 1].offsetTop;
+  if (currents.length) {
+    sbar.scrollTop = currents[currents.length - 1].offsetTop;
+  }
   --> </script>
-- 
GitLab


From 3f0e4df37a1b505307f61fbfa7b1f9a2fa2c40bc Mon Sep 17 00:00:00 2001
From: Hu Haowen <2023002089@link.tyut.edu.cn>
Date: Thu, 18 Jan 2024 17:01:40 +0800
Subject: [PATCH 3293/4076] docs/accel: correct links to mailing list archives

Since the mailing archive list lkml.org is obsolete, change the links into
lore.kernel.org's ones.

Signed-off-by: Hu Haowen <2023002089@link.tyut.edu.cn>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20240118090140.4868-1-2023002089@link.tyut.edu.cn
---
 Documentation/accel/introduction.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/accel/introduction.rst b/Documentation/accel/introduction.rst
index 89984dfececf0..ae30301366379 100644
--- a/Documentation/accel/introduction.rst
+++ b/Documentation/accel/introduction.rst
@@ -101,8 +101,8 @@ External References
 email threads
 -------------
 
-* `Initial discussion on the New subsystem for acceleration devices <https://lkml.org/lkml/2022/7/31/83>`_ - Oded Gabbay (2022)
-* `patch-set to add the new subsystem <https://lkml.org/lkml/2022/10/22/544>`_ - Oded Gabbay (2022)
+* `Initial discussion on the New subsystem for acceleration devices <https://lore.kernel.org/lkml/CAFCwf11=9qpNAepL7NL+YAV_QO=Wv6pnWPhKHKAepK3fNn+2Dg@mail.gmail.com/>`_ - Oded Gabbay (2022)
+* `patch-set to add the new subsystem <https://lore.kernel.org/lkml/20221022214622.18042-1-ogabbay@kernel.org/>`_ - Oded Gabbay (2022)
 
 Conference talks
 ----------------
-- 
GitLab


From ea7dcd8a48ea3b440a7070b1a0f70f757f8ed9a8 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Thu, 11 Jan 2024 09:52:20 +0100
Subject: [PATCH 3294/4076] doc: admin-guide/kernel-parameters: remove useless
 comment

This comment about DRM drivers has been there since the first git
commit. It simply doesn't belong in kernel-parameters; remove it.

Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20240111085220.3693059-1-vegard.nossum@oracle.com
---
 Documentation/admin-guide/kernel-parameters.rst | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index 102937bc8443a..4410384596a90 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -218,8 +218,3 @@ bytes respectively. Such letter suffixes can also be entirely omitted:
 
 .. include:: kernel-parameters.txt
    :literal:
-
-Todo
-----
-
-	Add more DRM drivers.
-- 
GitLab


From d546978e0c07b6333fdbcbd81b2f2e058d4560b5 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Thu, 30 Nov 2023 10:55:15 +0100
Subject: [PATCH 3295/4076] docs: admin-guide: remove obsolete advice related
 to SLAB allocator

Commit 1db9d06aaa55 ("mm/slab: remove CONFIG_SLAB from all Kconfig and
Makefile") removes the config SLAB and makes the SLUB allocator the only
default allocator in the kernel. Hence, the advice on reducing OS jitter
due to kworker kernel threads to build with CONFIG_SLUB instead of
CONFIG_SLAB is obsolete.

Remove the obsolete advice to build with SLUB instead of SLAB.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20231130095515.21586-1-lukas.bulwahn@gmail.com
---
 .../admin-guide/kernel-per-CPU-kthreads.rst      | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/Documentation/admin-guide/kernel-per-CPU-kthreads.rst b/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
index 993c2a05f5eea..b6aeae3327ceb 100644
--- a/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
+++ b/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
@@ -243,13 +243,9 @@ To reduce its OS jitter, do any of the following:
 3.	Do any of the following needed to avoid jitter that your
 	application cannot tolerate:
 
-	a.	Build your kernel with CONFIG_SLUB=y rather than
-		CONFIG_SLAB=y, thus avoiding the slab allocator's periodic
-		use of each CPU's workqueues to run its cache_reap()
-		function.
-	b.	Avoid using oprofile, thus avoiding OS jitter from
+	a.	Avoid using oprofile, thus avoiding OS jitter from
 		wq_sync_buffer().
-	c.	Limit your CPU frequency so that a CPU-frequency
+	b.	Limit your CPU frequency so that a CPU-frequency
 		governor is not required, possibly enlisting the aid of
 		special heatsinks or other cooling technologies.  If done
 		correctly, and if you CPU architecture permits, you should
@@ -259,7 +255,7 @@ To reduce its OS jitter, do any of the following:
 
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	d.	As of v3.18, Christoph Lameter's on-demand vmstat workers
+	c.	As of v3.18, Christoph Lameter's on-demand vmstat workers
 		commit prevents OS jitter due to vmstat_update() on
 		CONFIG_SMP=y systems.  Before v3.18, is not possible
 		to entirely get rid of the OS jitter, but you can
@@ -274,7 +270,7 @@ To reduce its OS jitter, do any of the following:
 		(based on an earlier one from Gilad Ben-Yossef) that
 		reduces or even eliminates vmstat overhead for some
 		workloads at https://lore.kernel.org/r/00000140e9dfd6bd-40db3d4f-c1be-434f-8132-7820f81bb586-000000@email.amazonses.com.
-	e.	If running on high-end powerpc servers, build with
+	d.	If running on high-end powerpc servers, build with
 		CONFIG_PPC_RTAS_DAEMON=n.  This prevents the RTAS
 		daemon from running on each CPU every second or so.
 		(This will require editing Kconfig files and will defeat
@@ -282,12 +278,12 @@ To reduce its OS jitter, do any of the following:
 		due to the rtas_event_scan() function.
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	f.	If running on Cell Processor, build your kernel with
+	e.	If running on Cell Processor, build your kernel with
 		CBE_CPUFREQ_SPU_GOVERNOR=n to avoid OS jitter from
 		spu_gov_work().
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	g.	If running on PowerMAC, build your kernel with
+	f.	If running on PowerMAC, build your kernel with
 		CONFIG_PMAC_RACKMETER=n to disable the CPU-meter,
 		avoiding OS jitter from rackmeter_do_timer().
 
-- 
GitLab


From 1732ebc4a26181c8f116c7639db99754b313edc8 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Tue, 23 Jan 2024 02:32:07 +0000
Subject: [PATCH 3296/4076] riscv, bpf: Fix unpredictable kernel crash about
 RV64 struct_ops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We encountered a kernel crash triggered by the bpf_tcp_ca testcase as
show below:

Unable to handle kernel paging request at virtual address ff60000088554500
Oops [#1]
...
CPU: 3 PID: 458 Comm: test_progs Tainted: G           OE      6.8.0-rc1-kselftest_plain #1
Hardware name: riscv-virtio,qemu (DT)
epc : 0xff60000088554500
 ra : tcp_ack+0x288/0x1232
epc : ff60000088554500 ra : ffffffff80cc7166 sp : ff2000000117ba50
 gp : ffffffff82587b60 tp : ff60000087be0040 t0 : ff60000088554500
 t1 : ffffffff801ed24e t2 : 0000000000000000 s0 : ff2000000117bbc0
 s1 : 0000000000000500 a0 : ff20000000691000 a1 : 0000000000000018
 a2 : 0000000000000001 a3 : ff60000087be03a0 a4 : 0000000000000000
 a5 : 0000000000000000 a6 : 0000000000000021 a7 : ffffffff8263f880
 s2 : 000000004ac3c13b s3 : 000000004ac3c13a s4 : 0000000000008200
 s5 : 0000000000000001 s6 : 0000000000000104 s7 : ff2000000117bb00
 s8 : ff600000885544c0 s9 : 0000000000000000 s10: ff60000086ff0b80
 s11: 000055557983a9c0 t3 : 0000000000000000 t4 : 000000000000ffc4
 t5 : ffffffff8154f170 t6 : 0000000000000030
status: 0000000200000120 badaddr: ff60000088554500 cause: 000000000000000c
Code: c796 67d7 0000 0000 0052 0002 c13b 4ac3 0000 0000 (0001) 0000
---[ end trace 0000000000000000 ]---

The reason is that commit 2cd3e3772e41 ("x86/cfi,bpf: Fix bpf_struct_ops
CFI") changes the func_addr of arch_prepare_bpf_trampoline in struct_ops
from NULL to non-NULL, while we use func_addr on RV64 to differentiate
between struct_ops and regular trampoline. When the struct_ops testcase
is triggered, it emits wrong prologue and epilogue, and lead to
unpredictable issues. After commit 2cd3e3772e41, we can use
BPF_TRAMP_F_INDIRECT to distinguish them as it always be set in
struct_ops.

Fixes: 2cd3e3772e41 ("x86/cfi,bpf: Fix bpf_struct_ops CFI")
Signed-off-by: Pu Lehui <pulehui@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/bpf/20240123023207.1917284-1-pulehui@huaweicloud.com
---
 arch/riscv/net/bpf_jit_comp64.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 58dc64dd94a82..719a97e7edb2c 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -795,6 +795,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+	bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT;
 	void *orig_call = func_addr;
 	bool save_ret;
 	u32 insn;
@@ -878,7 +879,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 
 	stack_size = round_up(stack_size, 16);
 
-	if (func_addr) {
+	if (!is_struct_ops) {
 		/* For the trampoline called from function entry,
 		 * the frame of traced function and the frame of
 		 * trampoline need to be considered.
@@ -998,7 +999,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 
 	emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx);
 
-	if (func_addr) {
+	if (!is_struct_ops) {
 		/* trampoline called from function entry */
 		emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx);
 		emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx);
-- 
GitLab


From 16bae3e1377846734ec6b87eee459c0f3551692c Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Tue, 23 Jan 2024 16:55:02 -0500
Subject: [PATCH 3297/4076] io_uring: enable audit and restrict cred override
 for IORING_OP_FIXED_FD_INSTALL

We need to correct some aspects of the IORING_OP_FIXED_FD_INSTALL
command to take into account the security implications of making an
io_uring-private file descriptor generally accessible to a userspace
task.

The first change in this patch is to enable auditing of the FD_INSTALL
operation as installing a file descriptor into a task's file descriptor
table is a security relevant operation and something that admins/users
may want to audit.

The second change is to disable the io_uring credential override
functionality, also known as io_uring "personalities", in the
FD_INSTALL command.  The credential override in FD_INSTALL is
particularly problematic as it affects the credentials used in the
security_file_receive() LSM hook.  If a task were to request a
credential override via REQ_F_CREDS on a FD_INSTALL operation, the LSM
would incorrectly check to see if the overridden credentials of the
io_uring were able to "receive" the file as opposed to the task's
credentials.  After discussions upstream, it's difficult to imagine a
use case where we would want to allow a credential override on a
FD_INSTALL operation so we are simply going to block REQ_F_CREDS on
IORING_OP_FIXED_FD_INSTALL operations.

Fixes: dc18b89ab113 ("io_uring/openclose: add support for IORING_OP_FIXED_FD_INSTALL")
Signed-off-by: Paul Moore <paul@paul-moore.com>
Link: https://lore.kernel.org/r/20240123215501.289566-2-paul@paul-moore.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/opdef.c     | 1 -
 io_uring/openclose.c | 4 ++++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 6705634e5f52a..b1ee3a9c38072 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -471,7 +471,6 @@ const struct io_issue_def io_issue_defs[] = {
 	},
 	[IORING_OP_FIXED_FD_INSTALL] = {
 		.needs_file		= 1,
-		.audit_skip		= 1,
 		.prep			= io_install_fixed_fd_prep,
 		.issue			= io_install_fixed_fd,
 	},
diff --git a/io_uring/openclose.c b/io_uring/openclose.c
index 0fe0dd3055462..e3357dfa14ca4 100644
--- a/io_uring/openclose.c
+++ b/io_uring/openclose.c
@@ -277,6 +277,10 @@ int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sq
 	if (flags & ~IORING_FIXED_FD_NO_CLOEXEC)
 		return -EINVAL;
 
+	/* ensure the task's creds are used when installing/receiving fds */
+	if (req->flags & REQ_F_CREDS)
+		return -EPERM;
+
 	/* default to O_CLOEXEC, disable if IORING_FIXED_FD_NO_CLOEXEC is set */
 	ifi = io_kiocb_to_cmd(req, struct io_fixed_install);
 	ifi->o_flags = O_CLOEXEC;
-- 
GitLab


From 8deb05c84b63b4fdb8549e08942867a68924a5b8 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 23 Jan 2024 15:47:34 -0800
Subject: [PATCH 3298/4076] smb: Work around Clang __bdos() type confusion

Recent versions of Clang gets confused about the possible size of the
"user" allocation, and CONFIG_FORTIFY_SOURCE ends up emitting a
warning[1]:

repro.c:126:4: warning: call to '__write_overflow_field' declared with 'warning' attribute: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Wattribute-warning]
  126 |                         __write_overflow_field(p_size_field, size);
      |                         ^

for this memset():

        int len;
        __le16 *user;
	...
        len = ses->user_name ? strlen(ses->user_name) : 0;
        user = kmalloc(2 + (len * 2), GFP_KERNEL);
	...
	if (len) {
		...
	} else {
		memset(user, '\0', 2);
	}

While Clang works on this bug[2], switch to using a direct assignment,
which avoids memset() entirely which both simplifies the code and silences
the false positive warning. (Making "len" size_t also silences the
warning, but the direct assignment seems better.)

Reported-by: Nathan Chancellor <nathan@kernel.org>
Closes: https://github.com/ClangBuiltLinux/linux/issues/1966 [1]
Link: https://github.com/llvm/llvm-project/issues/77813 [2]
Cc: Steve French <sfrench@samba.org>
Cc: Paulo Alcantara <pc@manguebit.com>
Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Cc: Shyam Prasad N <sprasad@microsoft.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: linux-cifs@vger.kernel.org
Cc: llvm@lists.linux.dev
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsencrypt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c
index ef4c2e3c9fa61..6322f0f68a176 100644
--- a/fs/smb/client/cifsencrypt.c
+++ b/fs/smb/client/cifsencrypt.c
@@ -572,7 +572,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 		len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp);
 		UniStrupr(user);
 	} else {
-		memset(user, '\0', 2);
+		*(u16 *)user = 0;
 	}
 
 	rc = crypto_shash_update(ses->server->secmech.hmacmd5,
-- 
GitLab


From 966cc171c8be4fbeae1bf166d264e0bfb09e141c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 15 Feb 2022 19:22:18 +0000
Subject: [PATCH 3299/4076] cifs: Share server EOF pos with netfslib

Use cifsi->netfs_ctx.remote_i_size instead of cifsi->server_eof so that
netfslib can refer to it to.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Shyam Prasad N <nspmangalore@gmail.com>
cc: Rohith Surabattula <rohiths.msft@gmail.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsfs.c   | 17 ++++++++++++++---
 fs/smb/client/cifsglob.h |  1 -
 fs/smb/client/file.c     |  8 ++++----
 fs/smb/client/inode.c    |  8 +++++---
 fs/smb/client/readdir.c  |  2 +-
 fs/smb/client/smb2ops.c  | 18 +++++++++++++-----
 6 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index e902de4e475af..2a4a4e3a8751f 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -396,7 +396,7 @@ cifs_alloc_inode(struct super_block *sb)
 	spin_lock_init(&cifs_inode->writers_lock);
 	cifs_inode->writers = 0;
 	cifs_inode->netfs.inode.i_blkbits = 14;  /* 2**14 = CIFS_MAX_MSGSIZE */
-	cifs_inode->server_eof = 0;
+	cifs_inode->netfs.remote_i_size = 0;
 	cifs_inode->uniqueid = 0;
 	cifs_inode->createtime = 0;
 	cifs_inode->epoch = 0;
@@ -1380,6 +1380,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
 	struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode);
+	struct cifsInodeInfo *target_cifsi = CIFS_I(target_inode);
 	struct cifsFileInfo *smb_file_src;
 	struct cifsFileInfo *smb_file_target;
 	struct cifs_tcon *src_tcon;
@@ -1428,7 +1429,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	 * Advance the EOF marker after the flush above to the end of the range
 	 * if it's short of that.
 	 */
-	if (src_cifsi->server_eof < off + len) {
+	if (src_cifsi->netfs.remote_i_size < off + len) {
 		rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len);
 		if (rc < 0)
 			goto unlock;
@@ -1452,12 +1453,22 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	/* Discard all the folios that overlap the destination region. */
 	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
 
+	fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
+			   i_size_read(target_inode), 0);
+
 	rc = file_modified(dst_file);
 	if (!rc) {
 		rc = target_tcon->ses->server->ops->copychunk_range(xid,
 			smb_file_src, smb_file_target, off, len, destoff);
-		if (rc > 0 && destoff + rc > i_size_read(target_inode))
+		if (rc > 0 && destoff + rc > i_size_read(target_inode)) {
 			truncate_setsize(target_inode, destoff + rc);
+			netfs_resize_file(&target_cifsi->netfs,
+					  i_size_read(target_inode), true);
+			fscache_resize_cookie(cifs_inode_cookie(target_inode),
+					      i_size_read(target_inode));
+		}
+		if (rc > 0 && destoff + rc > target_cifsi->netfs.zero_point)
+			target_cifsi->netfs.zero_point = destoff + rc;
 	}
 
 	file_accessed(src_file);
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 20036fb16cece..dd12364ef3723 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1561,7 +1561,6 @@ struct cifsInodeInfo {
 	spinlock_t writers_lock;
 	unsigned int writers;		/* Number of writers on this inode */
 	unsigned long time;		/* jiffies of last update of inode */
-	u64  server_eof;		/* current file size on server -- protected by i_lock */
 	u64  uniqueid;			/* server inode number */
 	u64  createtime;		/* creation time on server */
 	__u8 lease_key[SMB2_LEASE_KEY_SIZE];	/* lease key for this inode */
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 3a213432775b1..70f9e3f12a5c5 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -2120,8 +2120,8 @@ cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
 {
 	loff_t end_of_write = offset + bytes_written;
 
-	if (end_of_write > cifsi->server_eof)
-		cifsi->server_eof = end_of_write;
+	if (end_of_write > cifsi->netfs.remote_i_size)
+		netfs_resize_file(&cifsi->netfs, end_of_write, true);
 }
 
 static ssize_t
@@ -3247,8 +3247,8 @@ cifs_uncached_writev_complete(struct work_struct *work)
 
 	spin_lock(&inode->i_lock);
 	cifs_update_eof(cifsi, wdata->offset, wdata->bytes);
-	if (cifsi->server_eof > inode->i_size)
-		i_size_write(inode, cifsi->server_eof);
+	if (cifsi->netfs.remote_i_size > inode->i_size)
+		i_size_write(inode, cifsi->netfs.remote_i_size);
 	spin_unlock(&inode->i_lock);
 
 	complete(&wdata->done);
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index f0989484f2c64..d02f8ba29cb5b 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -104,7 +104,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 	fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode);
 	mtime = inode_get_mtime(inode);
 	if (timespec64_equal(&mtime, &fattr->cf_mtime) &&
-	    cifs_i->server_eof == fattr->cf_eof) {
+	    cifs_i->netfs.remote_i_size == fattr->cf_eof) {
 		cifs_dbg(FYI, "%s: inode %llu is unchanged\n",
 			 __func__, cifs_i->uniqueid);
 		return;
@@ -194,7 +194,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	else
 		clear_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags);
 
-	cifs_i->server_eof = fattr->cf_eof;
+	cifs_i->netfs.remote_i_size = fattr->cf_eof;
 	/*
 	 * Can't safely change the file size here if the client is writing to
 	 * it due to potential races.
@@ -2858,7 +2858,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 
 set_size_out:
 	if (rc == 0) {
-		cifsInode->server_eof = attrs->ia_size;
+		netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true);
 		cifs_setsize(inode, attrs->ia_size);
 		/*
 		 * i_blocks is not related to (i_size / i_blksize), but instead
@@ -3011,6 +3011,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	if ((attrs->ia_valid & ATTR_SIZE) &&
 	    attrs->ia_size != i_size_read(inode)) {
 		truncate_setsize(inode, attrs->ia_size);
+		netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true);
 		fscache_resize_cookie(cifs_inode_cookie(inode), attrs->ia_size);
 	}
 
@@ -3210,6 +3211,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 	if ((attrs->ia_valid & ATTR_SIZE) &&
 	    attrs->ia_size != i_size_read(inode)) {
 		truncate_setsize(inode, attrs->ia_size);
+		netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true);
 		fscache_resize_cookie(cifs_inode_cookie(inode), attrs->ia_size);
 	}
 
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 94255401b38dc..3b1b01d10f7d7 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -141,7 +141,7 @@ retry:
 					if (likely(reparse_inode_match(inode, fattr))) {
 						fattr->cf_mode = inode->i_mode;
 						fattr->cf_rdev = inode->i_rdev;
-						fattr->cf_eof = CIFS_I(inode)->server_eof;
+						fattr->cf_eof = CIFS_I(inode)->netfs.remote_i_size;
 						fattr->cf_symlink_target = NULL;
 					} else {
 						CIFS_I(inode)->time = 0;
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index d9553c2556a29..27f8caccff7fc 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -3213,6 +3213,9 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 				  cfile->fid.volatile_fid, cfile->pid, new_size);
 		if (rc >= 0) {
 			truncate_setsize(inode, new_size);
+			netfs_resize_file(&cifsi->netfs, new_size, true);
+			if (offset < cifsi->netfs.zero_point)
+				cifsi->netfs.zero_point = offset;
 			fscache_resize_cookie(cifs_inode_cookie(inode), new_size);
 		}
 	}
@@ -3436,7 +3439,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 		rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 				  cfile->fid.volatile_fid, cfile->pid, new_eof);
 		if (rc == 0) {
-			cifsi->server_eof = new_eof;
+			netfs_resize_file(&cifsi->netfs, new_eof, true);
 			cifs_setsize(inode, new_eof);
 			cifs_truncate_page(inode->i_mapping, inode->i_size);
 			truncate_setsize(inode, new_eof);
@@ -3528,8 +3531,9 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 	int rc;
 	unsigned int xid;
 	struct inode *inode = file_inode(file);
-	struct cifsFileInfo *cfile = file->private_data;
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
+	struct cifsFileInfo *cfile = file->private_data;
+	struct netfs_inode *ictx = &cifsi->netfs;
 	loff_t old_eof, new_eof;
 
 	xid = get_xid();
@@ -3549,6 +3553,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 		goto out_2;
 
 	truncate_pagecache_range(inode, off, old_eof);
+	ictx->zero_point = old_eof;
 
 	rc = smb2_copychunk_range(xid, cfile, cfile, off + len,
 				  old_eof - off - len, off);
@@ -3563,9 +3568,10 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 
 	rc = 0;
 
-	cifsi->server_eof = i_size_read(inode) - len;
-	truncate_setsize(inode, cifsi->server_eof);
-	fscache_resize_cookie(cifs_inode_cookie(inode), cifsi->server_eof);
+	truncate_setsize(inode, new_eof);
+	netfs_resize_file(&cifsi->netfs, new_eof, true);
+	ictx->zero_point = new_eof;
+	fscache_resize_cookie(cifs_inode_cookie(inode), new_eof);
 out_2:
 	filemap_invalidate_unlock(inode->i_mapping);
  out:
@@ -3581,6 +3587,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	unsigned int xid;
 	struct cifsFileInfo *cfile = file->private_data;
 	struct inode *inode = file_inode(file);
+	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	__u64 count, old_eof, new_eof;
 
 	xid = get_xid();
@@ -3608,6 +3615,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 		goto out_2;
 
 	truncate_setsize(inode, new_eof);
+	netfs_resize_file(&cifsi->netfs, i_size_read(inode), true);
 	fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode));
 
 	rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len);
-- 
GitLab


From fc43a8ac396d302ced1e991e4913827cf72c8eb9 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Sun, 21 Jan 2024 03:32:43 +0000
Subject: [PATCH 3300/4076] cifs: cifs_pick_channel should try selecting active
 channels

cifs_pick_channel today just selects a channel based
on the policy of least loaded channel. However, it
does not take into account if the channel needs
reconnect. As a result, we can have failures in send
that can be completely avoided.

This change doesn't make a channel a candidate for
this selection if it needs reconnect.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/transport.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index 4f717ad7c21b4..8695c9961f5aa 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -1026,6 +1026,9 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 		if (!server || server->terminate)
 			continue;
 
+		if (CIFS_CHAN_NEEDS_RECONNECT(ses, i))
+			continue;
+
 		/*
 		 * strictly speaking, we should pick up req_lock to read
 		 * server->in_flight. But it shouldn't matter much here if we
-- 
GitLab


From 3222bc997a24821ea4f96d1a9108dafeadc00cfb Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Thu, 18 Jan 2024 11:18:06 -0800
Subject: [PATCH 3301/4076] Revert "net: macsec: use
 skb_ensure_writable_head_tail to expand the skb"

This reverts commit b34ab3527b9622ca4910df24ff5beed5aa66c6b5.

Using skb_ensure_writable_head_tail without a call to skb_unshare causes
the MACsec stack to operate on the original skb rather than a copy in the
macsec_encrypt path. This causes the buffer to be exceeded in space, and
leads to warnings generated by skb_put operations. Opting to revert this
change since skb_copy_expand is more efficient than
skb_ensure_writable_head_tail followed by a call to skb_unshare.

Log:
  ------------[ cut here ]------------
  kernel BUG at net/core/skbuff.c:2464!
  invalid opcode: 0000 [#1] SMP KASAN
  CPU: 21 PID: 61997 Comm: iperf3 Not tainted 6.7.0-rc8_for_upstream_debug_2024_01_07_17_05 #1
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
  RIP: 0010:skb_put+0x113/0x190
  Code: 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 70 3b 9d bc 00 00 00 77 0e 48 83 c4 08 4c 89 e8 5b 5d 41 5d c3 <0f> 0b 4c 8b 6c 24 20 89 74 24 04 e8 6d b7 f0 fe 8b 74 24 04 48 c7
  RSP: 0018:ffff8882694e7278 EFLAGS: 00010202
  RAX: 0000000000000025 RBX: 0000000000000100 RCX: 0000000000000001
  RDX: 0000000000000000 RSI: 0000000000000010 RDI: ffff88816ae0bad4
  RBP: ffff88816ae0ba60 R08: 0000000000000004 R09: 0000000000000004
  R10: 0000000000000001 R11: 0000000000000001 R12: ffff88811ba5abfa
  R13: ffff8882bdecc100 R14: ffff88816ae0ba60 R15: ffff8882bdecc0ae
  FS:  00007fe54df02740(0000) GS:ffff88881f080000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007fe54d92e320 CR3: 000000010a345003 CR4: 0000000000370eb0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   ? die+0x33/0x90
   ? skb_put+0x113/0x190
   ? do_trap+0x1b4/0x3b0
   ? skb_put+0x113/0x190
   ? do_error_trap+0xb6/0x180
   ? skb_put+0x113/0x190
   ? handle_invalid_op+0x2c/0x30
   ? skb_put+0x113/0x190
   ? exc_invalid_op+0x2b/0x40
   ? asm_exc_invalid_op+0x16/0x20
   ? skb_put+0x113/0x190
   ? macsec_start_xmit+0x4e9/0x21d0
   macsec_start_xmit+0x830/0x21d0
   ? get_txsa_from_nl+0x400/0x400
   ? lock_downgrade+0x690/0x690
   ? dev_queue_xmit_nit+0x78b/0xae0
   dev_hard_start_xmit+0x151/0x560
   __dev_queue_xmit+0x1580/0x28f0
   ? check_chain_key+0x1c5/0x490
   ? netdev_core_pick_tx+0x2d0/0x2d0
   ? __ip_queue_xmit+0x798/0x1e00
   ? lock_downgrade+0x690/0x690
   ? mark_held_locks+0x9f/0xe0
   ip_finish_output2+0x11e4/0x2050
   ? ip_mc_finish_output+0x520/0x520
   ? ip_fragment.constprop.0+0x230/0x230
   ? __ip_queue_xmit+0x798/0x1e00
   __ip_queue_xmit+0x798/0x1e00
   ? __skb_clone+0x57a/0x760
   __tcp_transmit_skb+0x169d/0x3490
   ? lock_downgrade+0x690/0x690
   ? __tcp_select_window+0x1320/0x1320
   ? mark_held_locks+0x9f/0xe0
   ? lockdep_hardirqs_on_prepare+0x286/0x400
   ? tcp_small_queue_check.isra.0+0x120/0x3d0
   tcp_write_xmit+0x12b6/0x7100
   ? skb_page_frag_refill+0x1e8/0x460
   __tcp_push_pending_frames+0x92/0x320
   tcp_sendmsg_locked+0x1ed4/0x3190
   ? tcp_sendmsg_fastopen+0x650/0x650
   ? tcp_sendmsg+0x1a/0x40
   ? mark_held_locks+0x9f/0xe0
   ? lockdep_hardirqs_on_prepare+0x286/0x400
   tcp_sendmsg+0x28/0x40
   ? inet_send_prepare+0x1b0/0x1b0
   __sock_sendmsg+0xc5/0x190
   sock_write_iter+0x222/0x380
   ? __sock_sendmsg+0x190/0x190
   ? kfree+0x96/0x130
   vfs_write+0x842/0xbd0
   ? kernel_write+0x530/0x530
   ? __fget_light+0x51/0x220
   ? __fget_light+0x51/0x220
   ksys_write+0x172/0x1d0
   ? update_socket_protocol+0x10/0x10
   ? __x64_sys_read+0xb0/0xb0
   ? lockdep_hardirqs_on_prepare+0x286/0x400
   do_syscall_64+0x40/0xe0
   entry_SYSCALL_64_after_hwframe+0x46/0x4e
  RIP: 0033:0x7fe54d9018b7
  Code: 0f 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
  RSP: 002b:00007ffdbd4191d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
  RAX: ffffffffffffffda RBX: 0000000000000025 RCX: 00007fe54d9018b7
  RDX: 0000000000000025 RSI: 0000000000d9859c RDI: 0000000000000004
  RBP: 0000000000d9859c R08: 0000000000000004 R09: 0000000000000000
  R10: 00007fe54d80afe0 R11: 0000000000000246 R12: 0000000000000004
  R13: 0000000000000025 R14: 00007fe54e00ec00 R15: 0000000000d982a0
   </TASK>
  Modules linked in: 8021q garp mrp iptable_raw bonding vfio_pci rdma_ucm ib_umad mlx5_vfio_pci mlx5_ib vfio_pci_core vfio_iommu_type1 ib_uverbs vfio mlx5_core ip_gre nf_tables ipip tunnel4 ib_ipoib ip6_gre gre ip6_tunnel tunnel6 geneve openvswitch nsh xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay rpcrdma ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm ib_core zram zsmalloc fuse [last unloaded: ib_uverbs]
  ---[ end trace 0000000000000000 ]---

Cc: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Cc: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Link: https://lore.kernel.org/r/20240118191811.50271-1-rrameshbabu@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/macsec.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index e34816638569e..7f5426285c61b 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -607,11 +607,26 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 		return ERR_PTR(-EINVAL);
 	}
 
-	ret = skb_ensure_writable_head_tail(skb, dev);
-	if (unlikely(ret < 0)) {
-		macsec_txsa_put(tx_sa);
-		kfree_skb(skb);
-		return ERR_PTR(ret);
+	if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM ||
+		     skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) {
+		struct sk_buff *nskb = skb_copy_expand(skb,
+						       MACSEC_NEEDED_HEADROOM,
+						       MACSEC_NEEDED_TAILROOM,
+						       GFP_ATOMIC);
+		if (likely(nskb)) {
+			consume_skb(skb);
+			skb = nskb;
+		} else {
+			macsec_txsa_put(tx_sa);
+			kfree_skb(skb);
+			return ERR_PTR(-ENOMEM);
+		}
+	} else {
+		skb = skb_unshare(skb, GFP_ATOMIC);
+		if (!skb) {
+			macsec_txsa_put(tx_sa);
+			return ERR_PTR(-ENOMEM);
+		}
 	}
 
 	unprotected_len = skb->len;
-- 
GitLab


From 6941f67ad37d5465b75b9ffc498fcf6897a3c00e Mon Sep 17 00:00:00 2001
From: Michael Kelley <mhklinux@outlook.com>
Date: Mon, 22 Jan 2024 08:20:28 -0800
Subject: [PATCH 3302/4076] hv_netvsc: Calculate correct ring size when
 PAGE_SIZE is not 4 Kbytes

Current code in netvsc_drv_init() incorrectly assumes that PAGE_SIZE
is 4 Kbytes, which is wrong on ARM64 with 16K or 64K page size. As a
result, the default VMBus ring buffer size on ARM64 with 64K page size
is 8 Mbytes instead of the expected 512 Kbytes. While this doesn't break
anything, a typical VM with 8 vCPUs and 8 netvsc channels wastes 120
Mbytes (8 channels * 2 ring buffers/channel * 7.5 Mbytes/ring buffer).

Unfortunately, the module parameter specifying the ring buffer size
is in units of 4 Kbyte pages. Ideally, it should be in units that
are independent of PAGE_SIZE, but backwards compatibility prevents
changing that now.

Fix this by having netvsc_drv_init() hardcode 4096 instead of using
PAGE_SIZE when calculating the ring buffer size in bytes. Also
use the VMBUS_RING_SIZE macro to ensure proper alignment when running
with page size larger than 4K.

Cc: <stable@vger.kernel.org> # 5.15.x
Fixes: 7aff79e297ee ("Drivers: hv: Enable Hyper-V code to be built on ARM64")
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/20240122162028.348885-1-mhklinux@outlook.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/hyperv/netvsc_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 4406427d4617d..273bd8a20122c 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -44,7 +44,7 @@
 
 static unsigned int ring_size __ro_after_init = 128;
 module_param(ring_size, uint, 0444);
-MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
+MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
 unsigned int netvsc_ring_bytes __ro_after_init;
 
 static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
@@ -2807,7 +2807,7 @@ static int __init netvsc_drv_init(void)
 		pr_info("Increased ring_size to %u (min allowed)\n",
 			ring_size);
 	}
-	netvsc_ring_bytes = ring_size * PAGE_SIZE;
+	netvsc_ring_bytes = VMBUS_RING_SIZE(ring_size * 4096);
 
 	register_netdevice_notifier(&netvsc_netdev_notifier);
 
-- 
GitLab


From 04fe7c5029cbdbcdb28917f09a958d939a8f19f7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 22 Jan 2024 12:35:28 -0800
Subject: [PATCH 3303/4076] selftests: fill in some missing configs for net

We are missing a lot of config options from net selftests,
it seems:

tun/tap:     CONFIG_TUN, CONFIG_MACVLAN, CONFIG_MACVTAP
fib_tests:   CONFIG_NET_SCH_FQ_CODEL
l2tp:        CONFIG_L2TP, CONFIG_L2TP_V3, CONFIG_L2TP_IP, CONFIG_L2TP_ETH
sctp-vrf:    CONFIG_INET_DIAG
txtimestamp: CONFIG_NET_CLS_U32
vxlan_mdb:   CONFIG_BRIDGE_VLAN_FILTERING
gre_gso:     CONFIG_NET_IPGRE_DEMUX, CONFIG_IP_GRE, CONFIG_IPV6_GRE
srv6_end_dt*_l3vpn:   CONFIG_IPV6_SEG6_LWTUNNEL
ip_local_port_range:  CONFIG_MPTCP
fib_test:    CONFIG_NET_CLS_BASIC
rtnetlink:   CONFIG_MACSEC, CONFIG_NET_SCH_HTB, CONFIG_XFRM_INTERFACE
             CONFIG_NET_IPGRE, CONFIG_BONDING
fib_nexthops: CONFIG_MPLS, CONFIG_MPLS_ROUTING
vxlan_mdb:   CONFIG_NET_ACT_GACT
tls:         CONFIG_TLS, CONFIG_CRYPTO_CHACHA20POLY1305
psample:     CONFIG_PSAMPLE
fcnal:       CONFIG_TCP_MD5SIG

Try to add them in a semi-alphabetical order.

Fixes: 62199e3f1658 ("selftests: net: Add VXLAN MDB test")
Fixes: c12e0d5f267d ("self-tests: introduce self-tests for RPS default mask")
Fixes: 122db5e3634b ("selftests/net: add MPTCP coverage for IP_LOCAL_PORT_RANGE")
Link: https://lore.kernel.org/r/20240122203528.672004-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 8da562a9ae87e..19ff750516609 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -1,5 +1,6 @@
 CONFIG_USER_NS=y
 CONFIG_NET_NS=y
+CONFIG_BONDING=m
 CONFIG_BPF_SYSCALL=y
 CONFIG_TEST_BPF=m
 CONFIG_NUMA=y
@@ -14,9 +15,13 @@ CONFIG_VETH=y
 CONFIG_NET_IPVTI=y
 CONFIG_IPV6_VTI=y
 CONFIG_DUMMY=y
+CONFIG_BRIDGE_VLAN_FILTERING=y
 CONFIG_BRIDGE=y
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_VLAN_8021Q=y
 CONFIG_IFB=y
+CONFIG_INET_DIAG=y
+CONFIG_IP_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NF_CONNTRACK=m
@@ -25,15 +30,36 @@ CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP_NF_NAT=m
+CONFIG_IPV6_GRE=m
+CONFIG_IPV6_SEG6_LWTUNNEL=y
+CONFIG_L2TP_ETH=m
+CONFIG_L2TP_IP=m
+CONFIG_L2TP=m
+CONFIG_L2TP_V3=y
+CONFIG_MACSEC=m
+CONFIG_MACVLAN=y
+CONFIG_MACVTAP=y
+CONFIG_MPLS=y
+CONFIG_MPTCP=y
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_IPV6=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_NAT=m
+CONFIG_NET_ACT_GACT=m
+CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_U32=m
+CONFIG_NET_IPGRE_DEMUX=m
+CONFIG_NET_IPGRE=m
+CONFIG_NET_SCH_FQ_CODEL=m
+CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
+CONFIG_PSAMPLE=m
+CONFIG_TCP_MD5SIG=y
 CONFIG_TEST_BLACKHOLE_DEV=m
 CONFIG_KALLSYMS=y
+CONFIG_TLS=m
 CONFIG_TRACEPOINTS=y
 CONFIG_NET_DROP_MONITOR=m
 CONFIG_NETDEVSIM=m
@@ -48,7 +74,9 @@ CONFIG_BAREUDP=m
 CONFIG_IPV6_IOAM6_LWTUNNEL=y
 CONFIG_CRYPTO_SM4_GENERIC=y
 CONFIG_AMT=m
+CONFIG_TUN=y
 CONFIG_VXLAN=m
 CONFIG_IP_SCTP=m
 CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_CRYPTO_ARIA=y
+CONFIG_XFRM_INTERFACE=m
-- 
GitLab


From 32f2a0afa95fae0d1ceec2ff06e0e816939964b8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 22 Jan 2024 15:28:43 +0200
Subject: [PATCH 3304/4076] net/sched: flower: Fix chain template offload

When a qdisc is deleted from a net device the stack instructs the
underlying driver to remove its flow offload callback from the
associated filter block using the 'FLOW_BLOCK_UNBIND' command. The stack
then continues to replay the removal of the filters in the block for
this driver by iterating over the chains in the block and invoking the
'reoffload' operation of the classifier being used. In turn, the
classifier in its 'reoffload' operation prepares and emits a
'FLOW_CLS_DESTROY' command for each filter.

However, the stack does not do the same for chain templates and the
underlying driver never receives a 'FLOW_CLS_TMPLT_DESTROY' command when
a qdisc is deleted. This results in a memory leak [1] which can be
reproduced using [2].

Fix by introducing a 'tmplt_reoffload' operation and have the stack
invoke it with the appropriate arguments as part of the replay.
Implement the operation in the sole classifier that supports chain
templates (flower) by emitting the 'FLOW_CLS_TMPLT_{CREATE,DESTROY}'
command based on whether a flow offload callback is being bound to a
filter block or being unbound from one.

As far as I can tell, the issue happens since cited commit which
reordered tcf_block_offload_unbind() before tcf_block_flush_all_chains()
in __tcf_block_put(). The order cannot be reversed as the filter block
is expected to be freed after flushing all the chains.

[1]
unreferenced object 0xffff888107e28800 (size 2048):
  comm "tc", pid 1079, jiffies 4294958525 (age 3074.287s)
  hex dump (first 32 bytes):
    b1 a6 7c 11 81 88 ff ff e0 5b b3 10 81 88 ff ff  ..|......[......
    01 00 00 00 00 00 00 00 e0 aa b0 84 ff ff ff ff  ................
  backtrace:
    [<ffffffff81c06a68>] __kmem_cache_alloc_node+0x1e8/0x320
    [<ffffffff81ab374e>] __kmalloc+0x4e/0x90
    [<ffffffff832aec6d>] mlxsw_sp_acl_ruleset_get+0x34d/0x7a0
    [<ffffffff832bc195>] mlxsw_sp_flower_tmplt_create+0x145/0x180
    [<ffffffff832b2e1a>] mlxsw_sp_flow_block_cb+0x1ea/0x280
    [<ffffffff83a10613>] tc_setup_cb_call+0x183/0x340
    [<ffffffff83a9f85a>] fl_tmplt_create+0x3da/0x4c0
    [<ffffffff83a22435>] tc_ctl_chain+0xa15/0x1170
    [<ffffffff838a863c>] rtnetlink_rcv_msg+0x3cc/0xed0
    [<ffffffff83ac87f0>] netlink_rcv_skb+0x170/0x440
    [<ffffffff83ac6270>] netlink_unicast+0x540/0x820
    [<ffffffff83ac6e28>] netlink_sendmsg+0x8d8/0xda0
    [<ffffffff83793def>] ____sys_sendmsg+0x30f/0xa80
    [<ffffffff8379d29a>] ___sys_sendmsg+0x13a/0x1e0
    [<ffffffff8379d50c>] __sys_sendmsg+0x11c/0x1f0
    [<ffffffff843b9ce0>] do_syscall_64+0x40/0xe0
unreferenced object 0xffff88816d2c0400 (size 1024):
  comm "tc", pid 1079, jiffies 4294958525 (age 3074.287s)
  hex dump (first 32 bytes):
    40 00 00 00 00 00 00 00 57 f6 38 be 00 00 00 00  @.......W.8.....
    10 04 2c 6d 81 88 ff ff 10 04 2c 6d 81 88 ff ff  ..,m......,m....
  backtrace:
    [<ffffffff81c06a68>] __kmem_cache_alloc_node+0x1e8/0x320
    [<ffffffff81ab36c1>] __kmalloc_node+0x51/0x90
    [<ffffffff81a8ed96>] kvmalloc_node+0xa6/0x1f0
    [<ffffffff82827d03>] bucket_table_alloc.isra.0+0x83/0x460
    [<ffffffff82828d2b>] rhashtable_init+0x43b/0x7c0
    [<ffffffff832aed48>] mlxsw_sp_acl_ruleset_get+0x428/0x7a0
    [<ffffffff832bc195>] mlxsw_sp_flower_tmplt_create+0x145/0x180
    [<ffffffff832b2e1a>] mlxsw_sp_flow_block_cb+0x1ea/0x280
    [<ffffffff83a10613>] tc_setup_cb_call+0x183/0x340
    [<ffffffff83a9f85a>] fl_tmplt_create+0x3da/0x4c0
    [<ffffffff83a22435>] tc_ctl_chain+0xa15/0x1170
    [<ffffffff838a863c>] rtnetlink_rcv_msg+0x3cc/0xed0
    [<ffffffff83ac87f0>] netlink_rcv_skb+0x170/0x440
    [<ffffffff83ac6270>] netlink_unicast+0x540/0x820
    [<ffffffff83ac6e28>] netlink_sendmsg+0x8d8/0xda0
    [<ffffffff83793def>] ____sys_sendmsg+0x30f/0xa80

[2]
 # tc qdisc add dev swp1 clsact
 # tc chain add dev swp1 ingress proto ip chain 1 flower dst_ip 0.0.0.0/32
 # tc qdisc del dev swp1 clsact
 # devlink dev reload pci/0000:06:00.0

Fixes: bbf73830cd48 ("net: sched: traverse chains in block with tcf_get_next_chain()")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  4 ++++
 net/sched/cls_api.c       |  9 ++++++++-
 net/sched/cls_flower.c    | 23 +++++++++++++++++++++++
 3 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index ba3e1b315de83..934fdb9775519 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -375,6 +375,10 @@ struct tcf_proto_ops {
 						struct nlattr **tca,
 						struct netlink_ext_ack *extack);
 	void			(*tmplt_destroy)(void *tmplt_priv);
+	void			(*tmplt_reoffload)(struct tcf_chain *chain,
+						   bool add,
+						   flow_setup_cb_t *cb,
+						   void *cb_priv);
 	struct tcf_exts *	(*get_exts)(const struct tcf_proto *tp,
 					    u32 handle);
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 92a12e3d0fe63..ff3d396a65aac 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1560,6 +1560,9 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb,
 	     chain_prev = chain,
 		     chain = __tcf_get_next_chain(block, chain),
 		     tcf_chain_put(chain_prev)) {
+		if (chain->tmplt_ops && add)
+			chain->tmplt_ops->tmplt_reoffload(chain, true, cb,
+							  cb_priv);
 		for (tp = __tcf_get_next_proto(chain, NULL); tp;
 		     tp_prev = tp,
 			     tp = __tcf_get_next_proto(chain, tp),
@@ -1575,6 +1578,9 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb,
 				goto err_playback_remove;
 			}
 		}
+		if (chain->tmplt_ops && !add)
+			chain->tmplt_ops->tmplt_reoffload(chain, false, cb,
+							  cb_priv);
 	}
 
 	return 0;
@@ -3000,7 +3006,8 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
 	ops = tcf_proto_lookup_ops(name, true, extack);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
-	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
+	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump ||
+	    !ops->tmplt_reoffload) {
 		NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier");
 		module_put(ops->owner);
 		return -EOPNOTSUPP;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index e5314a31f75ae..efb9d2811b73d 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -2721,6 +2721,28 @@ static void fl_tmplt_destroy(void *tmplt_priv)
 	kfree(tmplt);
 }
 
+static void fl_tmplt_reoffload(struct tcf_chain *chain, bool add,
+			       flow_setup_cb_t *cb, void *cb_priv)
+{
+	struct fl_flow_tmplt *tmplt = chain->tmplt_priv;
+	struct flow_cls_offload cls_flower = {};
+
+	cls_flower.rule = flow_rule_alloc(0);
+	if (!cls_flower.rule)
+		return;
+
+	cls_flower.common.chain_index = chain->index;
+	cls_flower.command = add ? FLOW_CLS_TMPLT_CREATE :
+				   FLOW_CLS_TMPLT_DESTROY;
+	cls_flower.cookie = (unsigned long) tmplt;
+	cls_flower.rule->match.dissector = &tmplt->dissector;
+	cls_flower.rule->match.mask = &tmplt->mask;
+	cls_flower.rule->match.key = &tmplt->dummy_key;
+
+	cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv);
+	kfree(cls_flower.rule);
+}
+
 static int fl_dump_key_val(struct sk_buff *skb,
 			   void *val, int val_type,
 			   void *mask, int mask_type, int len)
@@ -3628,6 +3650,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = {
 	.bind_class	= fl_bind_class,
 	.tmplt_create	= fl_tmplt_create,
 	.tmplt_destroy	= fl_tmplt_destroy,
+	.tmplt_reoffload = fl_tmplt_reoffload,
 	.tmplt_dump	= fl_tmplt_dump,
 	.get_exts	= fl_get_exts,
 	.owner		= THIS_MODULE,
-- 
GitLab


From 4373534a9850627a2695317944898eb1283a2db0 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 12 Jan 2024 15:00:00 +0800
Subject: [PATCH 3305/4076] scsi: core: Move scsi_host_busy() out of host lock
 for waking up EH handler

Inside scsi_eh_wakeup(), scsi_host_busy() is called & checked with host
lock every time for deciding if error handler kthread needs to be waken up.

This can be too heavy in case of recovery, such as:

 - N hardware queues

 - queue depth is M for each hardware queue

 - each scsi_host_busy() iterates over (N * M) tag/requests

If recovery is triggered in case that all requests are in-flight, each
scsi_eh_wakeup() is strictly serialized, when scsi_eh_wakeup() is called
for the last in-flight request, scsi_host_busy() has been run for (N * M -
1) times, and request has been iterated for (N*M - 1) * (N * M) times.

If both N and M are big enough, hard lockup can be triggered on acquiring
host lock, and it is observed on mpi3mr(128 hw queues, queue depth 8169).

Fix the issue by calling scsi_host_busy() outside the host lock. We don't
need the host lock for getting busy count because host the lock never
covers that.

[mkp: Drop unnecessary 'busy' variables pointed out by Bart]

Cc: Ewan Milne <emilne@redhat.com>
Fixes: 6eb045e092ef ("scsi: core: avoid host-wide host_busy counter for scsi_mq")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240112070000.4161982-1-ming.lei@redhat.com
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Reviewed-by: Sathya Prakash Veerichetty <safhya.prakash@broadcom.com>
Tested-by: Sathya Prakash Veerichetty <safhya.prakash@broadcom.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_error.c | 8 ++++----
 drivers/scsi/scsi_lib.c   | 2 +-
 drivers/scsi/scsi_priv.h  | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 79da4b1c1df0a..4f455884fdc44 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -61,11 +61,11 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd);
 static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *,
 						   struct scsi_cmnd *);
 
-void scsi_eh_wakeup(struct Scsi_Host *shost)
+void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy)
 {
 	lockdep_assert_held(shost->host_lock);
 
-	if (scsi_host_busy(shost) == shost->host_failed) {
+	if (busy == shost->host_failed) {
 		trace_scsi_eh_wakeup(shost);
 		wake_up_process(shost->ehandler);
 		SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost,
@@ -88,7 +88,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost)
 	if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 ||
 	    scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) {
 		shost->host_eh_scheduled++;
-		scsi_eh_wakeup(shost);
+		scsi_eh_wakeup(shost, scsi_host_busy(shost));
 	}
 
 	spin_unlock_irqrestore(shost->host_lock, flags);
@@ -286,7 +286,7 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head)
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	shost->host_failed++;
-	scsi_eh_wakeup(shost);
+	scsi_eh_wakeup(shost, scsi_host_busy(shost));
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index cf3864f720930..1fb80eae9a63a 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -280,7 +280,7 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 	if (unlikely(scsi_host_in_recovery(shost))) {
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (shost->host_failed || shost->host_eh_scheduled)
-			scsi_eh_wakeup(shost);
+			scsi_eh_wakeup(shost, scsi_host_busy(shost));
 		spin_unlock_irqrestore(shost->host_lock, flags);
 	}
 	rcu_read_unlock();
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 3f0dfb97db6bd..1fbfe1b52c9f1 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -92,7 +92,7 @@ extern void scmd_eh_abort_handler(struct work_struct *work);
 extern enum blk_eh_timer_return scsi_timeout(struct request *req);
 extern int scsi_error_handler(void *host);
 extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd);
-extern void scsi_eh_wakeup(struct Scsi_Host *shost);
+extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy);
 extern void scsi_eh_scmd_add(struct scsi_cmnd *);
 void scsi_eh_ready_devs(struct Scsi_Host *shost,
 			struct list_head *work_q,
-- 
GitLab


From a68106a6928e0a6680f12bcc7338c0dddcfe4d11 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Sun, 21 Jan 2024 03:32:45 +0000
Subject: [PATCH 3306/4076] cifs: translate network errors on send to
 -ECONNABORTED

When the network stack returns various errors, we today bubble
up the error to the user (in case of soft mounts).

This change translates all network errors except -EINTR and
-EAGAIN to -ECONNABORTED. A similar approach is taken when
we receive network errors when reading from the socket.

The change also forces the cifsd thread to reconnect during
it's next activity.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/transport.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index 8695c9961f5aa..e00278fcfa4fa 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -400,10 +400,17 @@ unmask:
 						  server->conn_id, server->hostname);
 	}
 smbd_done:
-	if (rc < 0 && rc != -EINTR)
+	/*
+	 * there's hardly any use for the layers above to know the
+	 * actual error code here. All they should do at this point is
+	 * to retry the connection and hope it goes away.
+	 */
+	if (rc < 0 && rc != -EINTR && rc != -EAGAIN) {
 		cifs_server_dbg(VFS, "Error %d sending data on socket to server\n",
 			 rc);
-	else if (rc > 0)
+		rc = -ECONNABORTED;
+		cifs_signal_cifsd_for_reconnect(server, false);
+	} else if (rc > 0)
 		rc = 0;
 out:
 	cifs_in_send_dec(server);
-- 
GitLab


From 64cc377b7628b81ffdbdb1c6bacfba895dcac3f8 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Sun, 21 Jan 2024 03:32:46 +0000
Subject: [PATCH 3307/4076] cifs: helper function to check replayable error
 codes

The code to check for replay is not just -EAGAIN. In some
cases, the send request or receive response may result in
network errors, which we're now mapping to -ECONNABORTED.

This change introduces a helper function which checks
if the error returned in one of the above two errors.
And all checks for replays will now use this helper.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c | 1 +
 fs/smb/client/cifsglob.h   | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 9718926205047..5730c65ffb40d 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -367,6 +367,7 @@ out:
 		atomic_inc(&tcon->num_remote_opens);
 	}
 	kfree(utf16_path);
+
 	return rc;
 }
 
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index dd12364ef3723..4eb706e27c825 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1830,6 +1830,13 @@ static inline bool is_retryable_error(int error)
 	return false;
 }
 
+static inline bool is_replayable_error(int error)
+{
+	if (error == -EAGAIN || error == -ECONNABORTED)
+		return true;
+	return false;
+}
+
 
 /* cifs_get_writable_file() flags */
 #define FIND_WR_ANY         0
-- 
GitLab


From 4f1fffa2376922f3d1d506e49c0fd445b023a28e Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Sun, 21 Jan 2024 03:32:47 +0000
Subject: [PATCH 3308/4076] cifs: commands that are retried should have replay
 flag set

MS-SMB2 states that the header flag SMB2_FLAGS_REPLAY_OPERATION
needs to be set when a command needs to be retried, so that
the server is aware that this is a replay for an operation that
appeared before.

This can be very important, for example, for state changing
operations and opens which get retried following a reconnect;
since the client maybe unaware of the status of the previous
open.

This is particularly important for multichannel scenario, since
disconnection of one connection does not mean that the session
is lost. The requests can be replayed on another channel.

This change also makes use of exponential back-off before replays
and also limits the number of retries to "retrans" mount option
value.

Also, this change does not modify the read/write codepath.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c |  23 +++-
 fs/smb/client/cifsglob.h   |   5 +
 fs/smb/client/smb2inode.c  |  33 ++++-
 fs/smb/client/smb2ops.c    | 123 ++++++++++++++++--
 fs/smb/client/smb2pdu.c    | 260 +++++++++++++++++++++++++++++++++----
 fs/smb/client/smb2proto.h  |   5 +
 6 files changed, 404 insertions(+), 45 deletions(-)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 5730c65ffb40d..1daeb5714faad 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -145,21 +145,27 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	struct cached_fid *cfid;
 	struct cached_fids *cfids;
 	const char *npath;
+	int retries = 0, cur_sleep = 1;
 
 	if (tcon == NULL || tcon->cfids == NULL || tcon->nohandlecache ||
 	    is_smb1_server(tcon->ses->server) || (dir_cache_timeout == 0))
 		return -EOPNOTSUPP;
 
 	ses = tcon->ses;
-	server = cifs_pick_channel(ses);
 	cfids = tcon->cfids;
 
-	if (!server->ops->new_lease_key)
-		return -EIO;
-
 	if (cifs_sb->root == NULL)
 		return -ENOENT;
 
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	oplock = SMB2_OPLOCK_LEVEL_II;
+	server = cifs_pick_channel(ses);
+
+	if (!server->ops->new_lease_key)
+		return -EIO;
+
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
 	if (!utf16_path)
 		return -ENOMEM;
@@ -268,6 +274,11 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	 */
 	cfid->has_lease = true;
 
+	if (retries) {
+		smb2_set_replay(server, &rqst[0]);
+		smb2_set_replay(server, &rqst[1]);
+	}
+
 	rc = compound_send_recv(xid, ses, server,
 				flags, 2, rqst,
 				resp_buftype, rsp_iov);
@@ -368,6 +379,10 @@ out:
 	}
 	kfree(utf16_path);
 
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 4eb706e27c825..ceaf9857885de 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -49,6 +49,11 @@
  */
 #define CIFS_DEF_ACTIMEO (1 * HZ)
 
+/*
+ * max sleep time before retry to server
+ */
+#define CIFS_MAX_SLEEP 2000
+
 /*
  * max attribute cache timeout (jiffies) - 2^30
  */
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index a652200540c8a..05818cd6d932e 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -120,6 +120,14 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	unsigned int size[2];
 	void *data[2];
 	int len;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	num_rqst = 0;
+	server = cifs_pick_channel(ses);
 
 	vars = kzalloc(sizeof(*vars), GFP_ATOMIC);
 	if (vars == NULL)
@@ -127,8 +135,6 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst = &vars->rqst[0];
 	rsp_iov = &vars->rsp_iov[0];
 
-	server = cifs_pick_channel(ses);
-
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
@@ -463,15 +469,24 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	num_rqst++;
 
 	if (cfile) {
+		if (retries)
+			for (i = 1; i < num_rqst - 2; i++)
+				smb2_set_replay(server, &rqst[i]);
+
 		rc = compound_send_recv(xid, ses, server,
 					flags, num_rqst - 2,
 					&rqst[1], &resp_buftype[1],
 					&rsp_iov[1]);
-	} else
+	} else {
+		if (retries)
+			for (i = 0; i < num_rqst; i++)
+				smb2_set_replay(server, &rqst[i]);
+
 		rc = compound_send_recv(xid, ses, server,
 					flags, num_rqst,
 					rqst, resp_buftype,
 					rsp_iov);
+	}
 
 finished:
 	num_rqst = 0;
@@ -620,9 +635,6 @@ finished:
 	}
 	SMB2_close_free(&rqst[num_rqst]);
 
-	if (cfile)
-		cifsFileInfo_put(cfile);
-
 	num_cmds += 2;
 	if (out_iov && out_buftype) {
 		memcpy(out_iov, rsp_iov, num_cmds * sizeof(*out_iov));
@@ -632,7 +644,16 @@ finished:
 		for (i = 0; i < num_cmds; i++)
 			free_rsp_buf(resp_buftype[i], rsp_iov[i].iov_base);
 	}
+	num_cmds -= 2; /* correct num_cmds as there could be a retry */
 	kfree(vars);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
+	if (cfile)
+		cifsFileInfo_put(cfile);
+
 	return rc;
 }
 
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 27f8caccff7fc..83c898afc8354 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1108,7 +1108,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_compound_vars *vars;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct smb_rqst *rqst;
 	struct kvec *rsp_iov;
 	__le16 *utf16_path = NULL;
@@ -1124,6 +1124,13 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 	struct smb2_file_full_ea_info *ea = NULL;
 	struct smb2_query_info_rsp *rsp;
 	int rc, used_len = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_CP_CREATE_CLOSE_OP;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	server = cifs_pick_channel(ses);
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
@@ -1244,6 +1251,12 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 		goto sea_exit;
 	smb2_set_related(&rqst[2]);
 
+	if (retries) {
+		smb2_set_replay(server, &rqst[0]);
+		smb2_set_replay(server, &rqst[1]);
+		smb2_set_replay(server, &rqst[2]);
+	}
+
 	rc = compound_send_recv(xid, ses, server,
 				flags, 3, rqst,
 				resp_buftype, rsp_iov);
@@ -1260,6 +1273,11 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 	kfree(vars);
 out_free_path:
 	kfree(utf16_path);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 #endif
@@ -1484,7 +1502,7 @@ smb2_ioctl_query_info(const unsigned int xid,
 	struct smb_rqst *rqst;
 	struct kvec *rsp_iov;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	char __user *arg = (char __user *)p;
 	struct smb_query_info qi;
 	struct smb_query_info __user *pqi;
@@ -1501,6 +1519,13 @@ smb2_ioctl_query_info(const unsigned int xid,
 	void *data[2];
 	int create_options = is_dir ? CREATE_NOT_FILE : CREATE_NOT_DIR;
 	void (*free_req1_func)(struct smb_rqst *r);
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_CP_CREATE_CLOSE_OP;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	server = cifs_pick_channel(ses);
 
 	vars = kzalloc(sizeof(*vars), GFP_ATOMIC);
 	if (vars == NULL)
@@ -1641,6 +1666,12 @@ smb2_ioctl_query_info(const unsigned int xid,
 		goto free_req_1;
 	smb2_set_related(&rqst[2]);
 
+	if (retries) {
+		smb2_set_replay(server, &rqst[0]);
+		smb2_set_replay(server, &rqst[1]);
+		smb2_set_replay(server, &rqst[2]);
+	}
+
 	rc = compound_send_recv(xid, ses, server,
 				flags, 3, rqst,
 				resp_buftype, rsp_iov);
@@ -1701,6 +1732,11 @@ free_output_buffer:
 	kfree(buffer);
 free_vars:
 	kfree(vars);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -2227,8 +2263,14 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_open_parms oparms;
 	struct smb2_query_directory_rsp *qd_rsp = NULL;
 	struct smb2_create_rsp *op_rsp = NULL;
-	struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses);
-	int retry_count = 0;
+	struct TCP_Server_Info *server;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	server = cifs_pick_channel(tcon->ses);
 
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
 	if (!utf16_path)
@@ -2278,14 +2320,15 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 
 	smb2_set_related(&rqst[1]);
 
-again:
+	if (retries) {
+		smb2_set_replay(server, &rqst[0]);
+		smb2_set_replay(server, &rqst[1]);
+	}
+
 	rc = compound_send_recv(xid, tcon->ses, server,
 				flags, 2, rqst,
 				resp_buftype, rsp_iov);
 
-	if (rc == -EAGAIN && retry_count++ < 10)
-		goto again;
-
 	/* If the open failed there is nothing to do */
 	op_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base;
 	if (op_rsp == NULL || op_rsp->hdr.Status != STATUS_SUCCESS) {
@@ -2333,6 +2376,11 @@ again:
 	SMB2_query_directory_free(&rqst[1]);
 	free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
 	free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -2457,6 +2505,22 @@ smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid,
 				 CIFS_CACHE_READ(cinode) ? 1 : 0);
 }
 
+void
+smb2_set_replay(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+{
+	struct smb2_hdr *shdr;
+
+	if (server->dialect < SMB30_PROT_ID)
+		return;
+
+	shdr = (struct smb2_hdr *)(rqst->rq_iov[0].iov_base);
+	if (shdr == NULL) {
+		cifs_dbg(FYI, "shdr NULL in smb2_set_related\n");
+		return;
+	}
+	shdr->Flags |= SMB2_FLAGS_REPLAY_OPERATION;
+}
+
 void
 smb2_set_related(struct smb_rqst *rqst)
 {
@@ -2529,6 +2593,27 @@ smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst)
 	shdr->NextCommand = cpu_to_le32(len);
 }
 
+/*
+ * helper function for exponential backoff and check if replayable
+ */
+bool smb2_should_replay(struct cifs_tcon *tcon,
+				int *pretries,
+				int *pcur_sleep)
+{
+	if (!pretries || !pcur_sleep)
+		return false;
+
+	if (tcon->retry || (*pretries)++ < tcon->ses->server->retrans) {
+		msleep(*pcur_sleep);
+		(*pcur_sleep) = ((*pcur_sleep) << 1);
+		if ((*pcur_sleep) > CIFS_MAX_SLEEP)
+			(*pcur_sleep) = CIFS_MAX_SLEEP;
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Passes the query info response back to the caller on success.
  * Caller need to free this with free_rsp_buf().
@@ -2542,7 +2627,7 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_compound_vars *vars;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int flags = CIFS_CP_CREATE_CLOSE_OP;
 	struct smb_rqst *rqst;
 	int resp_buftype[3];
@@ -2553,6 +2638,13 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc;
 	__le16 *utf16_path;
 	struct cached_fid *cfid = NULL;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_CP_CREATE_CLOSE_OP;
+	oplock = SMB2_OPLOCK_LEVEL_NONE;
+	server = cifs_pick_channel(ses);
 
 	if (!path)
 		path = "";
@@ -2633,6 +2725,14 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 		goto qic_exit;
 	smb2_set_related(&rqst[2]);
 
+	if (retries) {
+		if (!cfid) {
+			smb2_set_replay(server, &rqst[0]);
+			smb2_set_replay(server, &rqst[2]);
+		}
+		smb2_set_replay(server, &rqst[1]);
+	}
+
 	if (cfid) {
 		rc = compound_send_recv(xid, ses, server,
 					flags, 1, &rqst[1],
@@ -2665,6 +2765,11 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 	kfree(vars);
 out_free_path:
 	kfree(utf16_path);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 288199f0b987d..f92d77099ab41 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -2765,7 +2765,14 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	int flags = 0;
 	unsigned int total_len;
 	__le16 *utf16_path = NULL;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	n_iov = 2;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "mkdir\n");
 
@@ -2869,6 +2876,10 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	/* no need to inc num_remote_opens because we close it just below */
 	trace_smb3_posix_mkdir_enter(xid, tcon->tid, ses->Suid, full_path, CREATE_NOT_FILE,
 				    FILE_WRITE_ATTRIBUTES);
+
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	/* resource #4: response buffer */
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
@@ -2906,6 +2917,11 @@ err_free_req:
 	cifs_small_buf_release(req);
 err_free_path:
 	kfree(utf16_path);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3101,12 +3117,18 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	struct smb2_create_rsp *rsp = NULL;
 	struct cifs_tcon *tcon = oparms->tcon;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct kvec iov[SMB2_CREATE_IOV_SIZE];
 	struct kvec rsp_iov = {NULL, 0};
 	int resp_buftype = CIFS_NO_BUFFER;
 	int rc = 0;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "create/open\n");
 	if (!ses || !server)
@@ -3128,6 +3150,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	trace_smb3_open_enter(xid, tcon->tid, tcon->ses->Suid, oparms->path,
 		oparms->create_options, oparms->desired_access);
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags,
 			    &rsp_iov);
@@ -3181,6 +3206,11 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 creat_exit:
 	SMB2_open_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3305,15 +3335,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	int resp_buftype = CIFS_NO_BUFFER;
 	int rc = 0;
 	int flags = 0;
-
-	cifs_dbg(FYI, "SMB2 IOCTL\n");
-
-	if (out_data != NULL)
-		*out_data = NULL;
-
-	/* zero out returned data len, in case of error */
-	if (plen)
-		*plen = 0;
+	int retries = 0, cur_sleep = 1;
 
 	if (!tcon)
 		return -EIO;
@@ -3322,10 +3344,23 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (!ses)
 		return -EIO;
 
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
 	server = cifs_pick_channel(ses);
+
 	if (!server)
 		return -EIO;
 
+	cifs_dbg(FYI, "SMB2 IOCTL\n");
+
+	if (out_data != NULL)
+		*out_data = NULL;
+
+	/* zero out returned data len, in case of error */
+	if (plen)
+		*plen = 0;
+
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
@@ -3340,6 +3375,9 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (rc)
 		goto ioctl_exit;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags,
 			    &rsp_iov);
@@ -3409,6 +3447,11 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 ioctl_exit:
 	SMB2_ioctl_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3480,13 +3523,20 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	struct smb_rqst rqst;
 	struct smb2_close_rsp *rsp = NULL;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct kvec iov[1];
 	struct kvec rsp_iov;
 	int resp_buftype = CIFS_NO_BUFFER;
 	int rc = 0;
 	int flags = 0;
 	bool query_attrs = false;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	query_attrs = false;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "Close\n");
 
@@ -3512,6 +3562,9 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		goto close_exit;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
@@ -3545,6 +3598,11 @@ close_exit:
 			cifs_dbg(VFS, "handle cancelled close fid 0x%llx returned error %d\n",
 				 persistent_fid, tmp_rc);
 	}
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3675,12 +3733,19 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	struct TCP_Server_Info *server;
 	int flags = 0;
 	bool allocated = false;
+	int retries = 0, cur_sleep = 1;
 
 	cifs_dbg(FYI, "Query Info\n");
 
 	if (!ses)
 		return -EIO;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	allocated = false;
 	server = cifs_pick_channel(ses);
+
 	if (!server)
 		return -EIO;
 
@@ -3702,6 +3767,9 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	trace_smb3_query_info_enter(xid, persistent_fid, tcon->tid,
 				    ses->Suid, info_class, (__u32)info_type);
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
@@ -3744,6 +3812,11 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 qinf_exit:
 	SMB2_query_info_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -3844,7 +3917,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 		u32 *plen /* returned data len */)
 {
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct smb_rqst rqst;
 	struct smb2_change_notify_rsp *smb_rsp;
 	struct kvec iov[1];
@@ -3852,6 +3925,12 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 	int resp_buftype = CIFS_NO_BUFFER;
 	int flags = 0;
 	int rc = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "change notify\n");
 	if (!ses || !server)
@@ -3876,6 +3955,10 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 
 	trace_smb3_notify_enter(xid, persistent_fid, tcon->tid, ses->Suid,
 				(u8)watch_tree, completion_filter);
+
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 
@@ -3910,6 +3993,11 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rqst.rq_iov)
 		cifs_small_buf_release(rqst.rq_iov[0].iov_base); /* request */
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -4152,10 +4240,16 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	struct smb_rqst rqst;
 	struct kvec iov[1];
 	struct kvec rsp_iov = {NULL, 0};
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int resp_buftype = CIFS_NO_BUFFER;
 	int flags = 0;
 	int rc = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "flush\n");
 	if (!ses || !(ses->server))
@@ -4175,6 +4269,10 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		goto flush_exit;
 
 	trace_smb3_flush_enter(xid, persistent_fid, tcon->tid, ses->Suid);
+
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 
@@ -4189,6 +4287,11 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
  flush_exit:
 	SMB2_flush_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -4826,18 +4929,21 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	int flags = 0;
 	unsigned int total_len;
 	struct TCP_Server_Info *server;
+	int retries = 0, cur_sleep = 1;
 
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
 	*nbytes = 0;
-
-	if (n_vec < 1)
-		return rc;
-
 	if (!io_parms->server)
 		io_parms->server = cifs_pick_channel(io_parms->tcon->ses);
 	server = io_parms->server;
 	if (server == NULL)
 		return -ECONNABORTED;
 
+	if (n_vec < 1)
+		return rc;
+
 	rc = smb2_plain_req_init(SMB2_WRITE, io_parms->tcon, server,
 				 (void **) &req, &total_len);
 	if (rc)
@@ -4871,6 +4977,9 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = n_vec + 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, io_parms->tcon->ses, server,
 			    &rqst,
 			    &resp_buftype, flags, &rsp_iov);
@@ -4895,6 +5004,11 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 
 	cifs_small_buf_release(req);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(io_parms->tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5206,8 +5320,14 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	struct kvec rsp_iov;
 	int rc = 0;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	if (!ses || !(ses->server))
 		return -EIO;
@@ -5227,6 +5347,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		goto qdir_exit;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	rsp = (struct smb2_query_directory_rsp *)rsp_iov.iov_base;
@@ -5261,6 +5384,11 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 qdir_exit:
 	SMB2_query_directory_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5327,8 +5455,14 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	if (!ses || !server)
 		return -EIO;
@@ -5356,6 +5490,8 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 		return rc;
 	}
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
 
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags,
@@ -5371,6 +5507,11 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	free_rsp_buf(resp_buftype, rsp);
 	kfree(iov);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5423,12 +5564,18 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc;
 	struct smb2_oplock_break *req = NULL;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	int flags = CIFS_OBREAK_OP;
 	unsigned int total_len;
 	struct kvec iov[1];
 	struct kvec rsp_iov;
 	int resp_buf_type;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_OBREAK_OP;
+	server = cifs_pick_channel(ses);
 
 	cifs_dbg(FYI, "SMB2_oplock_break\n");
 	rc = smb2_plain_req_init(SMB2_OPLOCK_BREAK, tcon, server,
@@ -5453,15 +5600,21 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buf_type, flags, &rsp_iov);
 	cifs_small_buf_release(req);
-
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
 		cifs_dbg(FYI, "Send error in Oplock Break = %d\n", rc);
 	}
 
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5547,9 +5700,15 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	FILE_SYSTEM_POSIX_INFO *info = NULL;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	rc = build_qfs_info_req(&iov, tcon, server,
 				FS_POSIX_INFORMATION,
@@ -5565,6 +5724,9 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = &iov;
 	rqst.rq_nvec = 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	free_qfs_info_req(&iov);
@@ -5584,6 +5746,11 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 posix_qfsinf_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5598,9 +5765,15 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	struct smb2_fs_full_size_info *info = NULL;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	rc = build_qfs_info_req(&iov, tcon, server,
 				FS_FULL_SIZE_INFORMATION,
@@ -5616,6 +5789,9 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = &iov;
 	rqst.rq_nvec = 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	free_qfs_info_req(&iov);
@@ -5635,6 +5811,11 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 qfsinf_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5649,9 +5830,15 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype, max_len, min_len;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = cifs_pick_channel(ses);
+	struct TCP_Server_Info *server;
 	unsigned int rsp_len, offset;
 	int flags = 0;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = 0;
+	server = cifs_pick_channel(ses);
 
 	if (level == FS_DEVICE_INFORMATION) {
 		max_len = sizeof(FILE_SYSTEM_DEVICE_INFO);
@@ -5683,6 +5870,9 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = &iov;
 	rqst.rq_nvec = 1;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
 	free_qfs_info_req(&iov);
@@ -5720,6 +5910,11 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 
 qfsattr_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
@@ -5737,7 +5932,13 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	unsigned int count;
 	int flags = CIFS_NO_RSP_BUF;
 	unsigned int total_len;
-	struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses);
+	struct TCP_Server_Info *server;
+	int retries = 0, cur_sleep = 1;
+
+replay_again:
+	/* reinitialize for possible replay */
+	flags = CIFS_NO_RSP_BUF;
+	server = cifs_pick_channel(tcon->ses);
 
 	cifs_dbg(FYI, "smb2_lockv num lock %d\n", num_lock);
 
@@ -5768,6 +5969,9 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 2;
 
+	if (retries)
+		smb2_set_replay(server, &rqst);
+
 	rc = cifs_send_recv(xid, tcon->ses, server,
 			    &rqst, &resp_buf_type, flags,
 			    &rsp_iov);
@@ -5779,6 +5983,10 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 				    tcon->ses->Suid, rc);
 	}
 
+	if (is_replayable_error(rc) &&
+	    smb2_should_replay(tcon, &retries, &cur_sleep))
+		goto replay_again;
+
 	return rc;
 }
 
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 0034b537b0b3f..b3069911e9dd8 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -122,6 +122,11 @@ extern unsigned long smb_rqst_len(struct TCP_Server_Info *server,
 extern void smb2_set_next_command(struct cifs_tcon *tcon,
 				  struct smb_rqst *rqst);
 extern void smb2_set_related(struct smb_rqst *rqst);
+extern void smb2_set_replay(struct TCP_Server_Info *server,
+			    struct smb_rqst *rqst);
+extern bool smb2_should_replay(struct cifs_tcon *tcon,
+			  int *pretries,
+			  int *pcur_sleep);
 
 /*
  * SMB2 Worker functions - most of protocol specific implementation details
-- 
GitLab


From 4cdad80261862c8cdcbb5fd232aa713d0bdefe24 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Thu, 18 Jan 2024 09:14:10 +0000
Subject: [PATCH 3309/4076] cifs: set replay flag for retries of write command

Similar to the rest of the commands, this is a change
to add replay flags on retry. This one does not add a
back-off, considering that we may want to flush a write
ASAP to the server. Considering that this will be a
flush of cached pages, the retrans value is also not
honoured.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h | 1 +
 fs/smb/client/file.c     | 1 +
 fs/smb/client/smb2pdu.c  | 4 +++-
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index ceaf9857885de..16befff4cbb47 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1506,6 +1506,7 @@ struct cifs_writedata {
 	struct smbd_mr			*mr;
 #endif
 	struct cifs_credits		credits;
+	bool				replay;
 };
 
 /*
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 70f9e3f12a5c5..6f079976f9e77 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -3300,6 +3300,7 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
 			if (wdata->cfile->invalidHandle)
 				rc = -EAGAIN;
 			else {
+				wdata->replay = true;
 #ifdef CONFIG_CIFS_SMB_DIRECT
 				if (wdata->mr) {
 					wdata->mr->need_invalidate = true;
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index f92d77099ab41..4f2cc8373b675 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4771,7 +4771,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	struct cifs_io_parms *io_parms = NULL;
 	int credit_request;
 
-	if (!wdata->server)
+	if (!wdata->server || wdata->replay)
 		server = wdata->server = cifs_pick_channel(tcon->ses);
 
 	/*
@@ -4856,6 +4856,8 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	rqst.rq_nvec = 1;
 	rqst.rq_iter = wdata->iter;
 	rqst.rq_iter_size = iov_iter_count(&rqst.rq_iter);
+	if (wdata->replay)
+		smb2_set_replay(server, &rqst);
 #ifdef CONFIG_CIFS_SMB_DIRECT
 	if (wdata->mr)
 		iov[0].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
-- 
GitLab


From 993d1c346b1a51ac41b2193609a0d4e51e9748f4 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Tue, 23 Jan 2024 05:07:57 +0000
Subject: [PATCH 3310/4076] cifs: fix stray unlock in cifs_chan_skip_or_disable

A recent change moved the code that decides to skip
a channel or disable multichannel entirely, into a
helper function.

During this, a mutex_unlock of the session_mutex
should have been removed. Doing that here.

Fixes: f591062bdbf4 ("cifs: handle servers that still advertise multichannel after disabling")
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 4f2cc8373b675..86f6f35b7f32e 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -195,7 +195,6 @@ cifs_chan_skip_or_disable(struct cifs_ses *ses,
 		pserver = server->primary_server;
 		cifs_signal_cifsd_for_reconnect(pserver, false);
 skip_terminate:
-		mutex_unlock(&ses->session_mutex);
 		return -EHOSTDOWN;
 	}
 
-- 
GitLab


From f4469f3858352ad1197434557150b1f7086762a0 Mon Sep 17 00:00:00 2001
From: Michael Kelley <mhklinux@outlook.com>
Date: Mon, 22 Jan 2024 09:09:56 -0800
Subject: [PATCH 3311/4076] scsi: storvsc: Fix ring buffer size calculation

Current code uses the specified ring buffer size (either the default of 128
Kbytes or a module parameter specified value) to encompass the one page
ring buffer header plus the actual ring itself.  When the page size is 4K,
carving off one page for the header isn't significant.  But when the page
size is 64K on ARM64, only half of the default 128 Kbytes is left for the
actual ring.  While this doesn't break anything, the smaller ring size
could be a performance bottleneck.

Fix this by applying the VMBUS_RING_SIZE macro to the specified ring buffer
size.  This macro adds a page for the header, and rounds up the size to a
page boundary, using the page size for which the kernel is built.  Use this
new size for subsequent ring buffer calculations.  For example, on ARM64
with 64K page size and the default ring size, this results in the actual
ring being 128 Kbytes, which is intended.

Cc: stable@vger.kernel.org # 5.15.x
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/20240122170956.496436-1-mhklinux@outlook.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/storvsc_drv.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index a95936b18f695..7ceb982040a5d 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -330,6 +330,7 @@ enum storvsc_request_type {
  */
 
 static int storvsc_ringbuffer_size = (128 * 1024);
+static int aligned_ringbuffer_size;
 static u32 max_outstanding_req_per_channel;
 static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth);
 
@@ -687,8 +688,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc)
 	new_sc->next_request_id_callback = storvsc_next_request_id;
 
 	ret = vmbus_open(new_sc,
-			 storvsc_ringbuffer_size,
-			 storvsc_ringbuffer_size,
+			 aligned_ringbuffer_size,
+			 aligned_ringbuffer_size,
 			 (void *)&props,
 			 sizeof(struct vmstorage_channel_properties),
 			 storvsc_on_channel_callback, new_sc);
@@ -1973,7 +1974,7 @@ static int storvsc_probe(struct hv_device *device,
 	dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1);
 
 	stor_device->port_number = host->host_no;
-	ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc);
+	ret = storvsc_connect_to_vsp(device, aligned_ringbuffer_size, is_fc);
 	if (ret)
 		goto err_out1;
 
@@ -2164,7 +2165,7 @@ static int storvsc_resume(struct hv_device *hv_dev)
 {
 	int ret;
 
-	ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size,
+	ret = storvsc_connect_to_vsp(hv_dev, aligned_ringbuffer_size,
 				     hv_dev_is_fc(hv_dev));
 	return ret;
 }
@@ -2198,8 +2199,9 @@ static int __init storvsc_drv_init(void)
 	 * the ring buffer indices) by the max request size (which is
 	 * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64)
 	 */
+	aligned_ringbuffer_size = VMBUS_RING_SIZE(storvsc_ringbuffer_size);
 	max_outstanding_req_per_channel =
-		((storvsc_ringbuffer_size - PAGE_SIZE) /
+		((aligned_ringbuffer_size - PAGE_SIZE) /
 		ALIGN(MAX_MULTIPAGE_BUFFER_PACKET +
 		sizeof(struct vstor_packet) + sizeof(u64),
 		sizeof(u64)));
-- 
GitLab


From f74c35b630d40d414ca6b53f7b1b468dd4abf478 Mon Sep 17 00:00:00 2001
From: Mantas Pucka <mantas@8devices.com>
Date: Tue, 23 Jan 2024 18:09:19 +0200
Subject: [PATCH 3312/4076] phy: qcom-qmp-usb: fix register offsets for
 ipq8074/ipq6018

Commit 2be22aae6b18 ("phy: qcom-qmp-usb: populate offsets configuration")
introduced register offsets to the driver but for ipq8074/ipq6018 they do
not match what was in the old style device tree. Example from old
ipq6018.dtsi:

<0x00078200 0x130>,     /* Tx */
<0x00078400 0x200>,     /* Rx */
<0x00078800 0x1f8>,     /* PCS */
<0x00078600 0x044>;     /* PCS misc */

which would translate to:
{.., .pcs = 0x800, .pcs_misc = 0x600, .tx = 0x200, .rx = 0x400 }

but was translated to:
{.., .pcs = 0x600, .tx = 0x200, .rx = 0x400 }

So split usb_offsets and fix USB initialization for IPQ8074 and IPQ6018.
Tested only on IPQ6018

Fixes: 2be22aae6b18 ("phy: qcom-qmp-usb: populate offsets configuration")
Signed-off-by: Mantas Pucka <mantas@8devices.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/1706026160-17520-2-git-send-email-mantas@8devices.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-usb.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 243cc2b9a0fb6..05b4c0e678962 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -1556,6 +1556,14 @@ static const char * const qmp_phy_vreg_l[] = {
 	"vdda-phy", "vdda-pll",
 };
 
+static const struct qmp_usb_offsets qmp_usb_offsets_ipq8074 = {
+	.serdes		= 0,
+	.pcs		= 0x800,
+	.pcs_misc	= 0x600,
+	.tx		= 0x200,
+	.rx		= 0x400,
+};
+
 static const struct qmp_usb_offsets qmp_usb_offsets_ipq9574 = {
 	.serdes		= 0,
 	.pcs		= 0x800,
@@ -1616,7 +1624,7 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v7 = {
 static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = {
 	.lanes			= 1,
 
-	.offsets		= &qmp_usb_offsets_v3,
+	.offsets		= &qmp_usb_offsets_ipq8074,
 
 	.serdes_tbl		= ipq8074_usb3_serdes_tbl,
 	.serdes_tbl_num		= ARRAY_SIZE(ipq8074_usb3_serdes_tbl),
-- 
GitLab


From 62a5df451ab911421da96655fcc4d1e269ff6e2f Mon Sep 17 00:00:00 2001
From: Mantas Pucka <mantas@8devices.com>
Date: Tue, 23 Jan 2024 18:09:20 +0200
Subject: [PATCH 3313/4076] phy: qcom-qmp-usb: fix serdes init sequence for
 IPQ6018

Commit 23fd679249df ("phy: qcom-qmp: add USB3 PHY support for IPQ6018")
noted that IPQ6018 init is identical to IPQ8074. Yet downstream uses
separate serdes init sequence for IPQ6018. Since already existing IPQ9574
serdes init sequence is identical, just reuse it and fix failing USB3 mode
in IPQ6018.

Fixes: 23fd679249df ("phy: qcom-qmp: add USB3 PHY support for IPQ6018")
Signed-off-by: Mantas Pucka <mantas@8devices.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/1706026160-17520-3-git-send-email-mantas@8devices.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-usb.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 05b4c0e678962..6621246e4ddf0 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -1621,6 +1621,24 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v7 = {
 	.rx		= 0x1000,
 };
 
+static const struct qmp_phy_cfg ipq6018_usb3phy_cfg = {
+	.lanes			= 1,
+
+	.offsets		= &qmp_usb_offsets_ipq8074,
+
+	.serdes_tbl		= ipq9574_usb3_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(ipq9574_usb3_serdes_tbl),
+	.tx_tbl			= msm8996_usb3_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(msm8996_usb3_tx_tbl),
+	.rx_tbl			= ipq8074_usb3_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(ipq8074_usb3_rx_tbl),
+	.pcs_tbl		= ipq8074_usb3_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(ipq8074_usb3_pcs_tbl),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v3_usb3phy_regs_layout,
+};
+
 static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = {
 	.lanes			= 1,
 
@@ -2571,7 +2589,7 @@ err_node_put:
 static const struct of_device_id qmp_usb_of_match_table[] = {
 	{
 		.compatible = "qcom,ipq6018-qmp-usb3-phy",
-		.data = &ipq8074_usb3phy_cfg,
+		.data = &ipq6018_usb3phy_cfg,
 	}, {
 		.compatible = "qcom,ipq8074-qmp-usb3-phy",
 		.data = &ipq8074_usb3phy_cfg,
-- 
GitLab


From 249abaf3bf0dd07f5ddebbb2fe2e8f4d675f074e Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Fri, 5 Jan 2024 18:37:03 +0900
Subject: [PATCH 3314/4076] phy: renesas: rcar-gen3-usb2: Fix returning wrong
 error code

Even if device_create_file() returns error code,
rcar_gen3_phy_usb2_probe() will return zero because the "ret" is
variable shadowing.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202312161021.gOLDl48K-lkp@intel.com/
Fixes: 441a681b8843 ("phy: rcar-gen3-usb2: fix implementation for runtime PM")
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20240105093703.3359949-1-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/renesas/phy-rcar-gen3-usb2.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index e53eace7c91e3..6387c0d34c551 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -673,8 +673,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	channel->irq = platform_get_irq_optional(pdev, 0);
 	channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node);
 	if (channel->dr_mode != USB_DR_MODE_UNKNOWN) {
-		int ret;
-
 		channel->is_otg_channel = true;
 		channel->uses_otg_pins = !of_property_read_bool(dev->of_node,
 							"renesas,no-otg-pins");
@@ -738,8 +736,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 		ret = PTR_ERR(provider);
 		goto error;
 	} else if (channel->is_otg_channel) {
-		int ret;
-
 		ret = device_create_file(dev, &dev_attr_role);
 		if (ret < 0)
 			goto error;
-- 
GitLab


From 4e4a1183f281d95fbb6caf28d670775d13264beb Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Mon, 8 Jan 2024 21:51:40 +0100
Subject: [PATCH 3315/4076] phy: lan966x: Add missing serdes mux entry

According to the datasheet(Table 3-2: Port configuration) the serdes 2
(SD2) can be configured to run QSGMII or SGMII mode. Already the QSGMII
mode is supported in the serdes_muxes list  but was missing the SGMII mode.
In this mode the serdes is connected to the port 4.
Therefore add this entry in the list.

Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Link: https://lore.kernel.org/r/20240108205140.1701770-1-horatiu.vultur@microchip.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/microchip/lan966x_serdes.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/phy/microchip/lan966x_serdes.c b/drivers/phy/microchip/lan966x_serdes.c
index c1a41b6cd29b1..b5ac2b7995e71 100644
--- a/drivers/phy/microchip/lan966x_serdes.c
+++ b/drivers/phy/microchip/lan966x_serdes.c
@@ -96,6 +96,8 @@ static const struct serdes_mux lan966x_serdes_muxes[] = {
 	SERDES_MUX_SGMII(SERDES6G(1), 3, HSIO_HW_CFG_SD6G_1_CFG,
 			 HSIO_HW_CFG_SD6G_1_CFG_SET(1)),
 
+	SERDES_MUX_SGMII(SERDES6G(2), 4, 0, 0),
+
 	SERDES_MUX_RGMII(RGMII(0), 2, HSIO_HW_CFG_RGMII_0_CFG |
 			 HSIO_HW_CFG_RGMII_ENA |
 			 HSIO_HW_CFG_GMII_ENA,
-- 
GitLab


From 0077a504e1a4468669fd2e011108db49133db56e Mon Sep 17 00:00:00 2001
From: Conrad Kostecki <conikost@gentoo.org>
Date: Tue, 23 Jan 2024 19:30:02 +0100
Subject: [PATCH 3316/4076] ahci: asm1166: correct count of reported ports

The ASM1166 SATA host controller always reports wrongly,
that it has 32 ports. But in reality, it only has six ports.

This seems to be a hardware issue, as all tested ASM1166
SATA host controllers reports such high count of ports.

Example output: ahci 0000:09:00.0: AHCI 0001.0301
32 slots 32 ports 6 Gbps 0xffffff3f impl SATA mode.

By adjusting the port_map, the count is limited to six ports.

New output: ahci 0000:09:00.0: AHCI 0001.0301
32 slots 32 ports 6 Gbps 0x3f impl SATA mode.

Closes: https://bugzilla.kernel.org/show_bug.cgi?id=211873
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218346
Signed-off-by: Conrad Kostecki <conikost@gentoo.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 3a5f3255f51b3..762c5d8b7c1a1 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -663,6 +663,11 @@ MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets");
 static void ahci_pci_save_initial_config(struct pci_dev *pdev,
 					 struct ahci_host_priv *hpriv)
 {
+	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == 0x1166) {
+		dev_info(&pdev->dev, "ASM1166 has only six ports\n");
+		hpriv->saved_port_map = 0x3f;
+	}
+
 	if (pdev->vendor == PCI_VENDOR_ID_JMICRON && pdev->device == 0x2361) {
 		dev_info(&pdev->dev, "JMB361 has only one port\n");
 		hpriv->saved_port_map = 1;
-- 
GitLab


From 25461ce8b3d28528f2c55f5e737e99d2906eda83 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Fri, 15 Dec 2023 19:31:14 -0800
Subject: [PATCH 3317/4076] net/mlx5e: Use the correct lag ports number when
 creating TISes

The cited commit moved the code of mlx5e_create_tises() and changed the
loop to create TISes over MLX5_MAX_PORTS constant value, instead of
getting the correct lag ports supported by the device, which can cause
FW errors on devices with less than MLX5_MAX_PORTS ports.

Change that back to mlx5e_get_num_lag_ports(mdev).

Also IPoIB interfaces create there own TISes, they don't use the eth
TISes, pass a flag to indicate that.

This fixes the following errors that might appear in kernel log:
mlx5_cmd_out_err:808:(pid 650): CREATE_TIS(0x912) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x595b5d), err(-22)
mlx5e_create_mdev_resources:174:(pid 650): alloc tises failed, -22

Fixes: b25bd37c859f ("net/mlx5: Move TISes from priv to mdev HW resources")
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  2 +-
 .../ethernet/mellanox/mlx5/core/en_common.c   | 21 ++++++++++++-------
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  2 +-
 .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c |  2 +-
 include/linux/mlx5/driver.h                   |  1 +
 5 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0bfe1ca8a3642..55c6ace0acd55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1124,7 +1124,7 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 extern const struct ethtool_ops mlx5e_ethtool_ops;
 
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 		       bool enable_mc_lb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 67f546683e85a..6ed3a32b7e226 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -95,7 +95,7 @@ static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PO
 {
 	int tc, i;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++)
+	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++)
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++)
 			mlx5e_destroy_tis(mdev, tisn[i][tc]);
 }
@@ -110,7 +110,7 @@ static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORT
 	int tc, i;
 	int err;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) {
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) {
 			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
 			void *tisc;
@@ -140,7 +140,7 @@ err_close_tises:
 	return err;
 }
 
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
 	int err;
@@ -169,11 +169,15 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 		goto err_destroy_mkey;
 	}
 
-	err = mlx5e_create_tises(mdev, res->tisn);
-	if (err) {
-		mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
-		goto err_destroy_bfreg;
+	if (create_tises) {
+		err = mlx5e_create_tises(mdev, res->tisn);
+		if (err) {
+			mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
+			goto err_destroy_bfreg;
+		}
+		res->tisn_valid = true;
 	}
+
 	INIT_LIST_HEAD(&res->td.tirs_list);
 	mutex_init(&res->td.list_lock);
 
@@ -203,7 +207,8 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 
 	mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv);
 	mdev->mlx5e_res.dek_priv = NULL;
-	mlx5e_destroy_tises(mdev, res->tisn);
+	if (res->tisn_valid)
+		mlx5e_destroy_tises(mdev, res->tisn);
 	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b5f1c4ca38bac..c8e8f512803ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5992,7 +5992,7 @@ static int mlx5e_resume(struct auxiliary_device *adev)
 	if (netif_device_present(netdev))
 		return 0;
 
-	err = mlx5e_create_mdev_resources(mdev);
+	err = mlx5e_create_mdev_resources(mdev, true);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 58845121954c1..d77be1b4dd9c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -783,7 +783,7 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u32 port_num,
 		}
 
 		/* This should only be called once per mdev */
-		err = mlx5e_create_mdev_resources(mdev);
+		err = mlx5e_create_mdev_resources(mdev, false);
 		if (err)
 			goto destroy_ht;
 	}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 8c55ff351e5f2..41f03b352401e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -681,6 +681,7 @@ struct mlx5e_resources {
 		struct mlx5_sq_bfreg       bfreg;
 #define MLX5_MAX_NUM_TC 8
 		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
+		bool			   tisn_valid;
 	} hw_objs;
 	struct net_device *uplink_netdev;
 	struct mutex uplink_netdev_lock;
-- 
GitLab


From cfbc3608a8c69b48bf238bd68f768192f0238e0d Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 19 Dec 2023 14:46:20 +0200
Subject: [PATCH 3318/4076] net/mlx5: Fix query of sd_group field

The sd_group field moved in the HW spec from the MPIR register
to the vport context.
Align the query accordingly.

Fixes: f5e956329960 ("net/mlx5: Expose Management PCIe Index Register (MPIR)")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/vport.c   | 21 +++++++++++++++++++
 include/linux/mlx5/mlx5_ifc.h                 | 10 ++++++---
 include/linux/mlx5/vport.h                    |  1 +
 3 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 21753f3278685..1005bb6935b65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -440,6 +440,27 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid);
 
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 *out;
+	int err;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	if (err)
+		goto out;
+
+	*sd_group = MLX5_GET(query_nic_vport_context_out, out,
+			     nic_vport_context.sd_group);
+out:
+	kvfree(out);
+	return err;
+}
+
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 {
 	u32 *out;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index bf5320b28b8bf..37230253f9f17 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -4036,8 +4036,13 @@ struct mlx5_ifc_nic_vport_context_bits {
 	u8	   affiliation_criteria[0x4];
 	u8	   affiliated_vhca_id[0x10];
 
-	u8	   reserved_at_60[0xd0];
+	u8	   reserved_at_60[0xa0];
 
+	u8	   reserved_at_100[0x1];
+	u8         sd_group[0x3];
+	u8	   reserved_at_104[0x1c];
+
+	u8	   reserved_at_120[0x10];
 	u8         mtu[0x10];
 
 	u8         system_image_guid[0x40];
@@ -10122,8 +10127,7 @@ struct mlx5_ifc_mpir_reg_bits {
 	u8         reserved_at_20[0x20];
 
 	u8         local_port[0x8];
-	u8         reserved_at_28[0x15];
-	u8         sd_group[0x3];
+	u8         reserved_at_28[0x18];
 
 	u8         reserved_at_60[0x20];
 };
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index fbb9bf4478894..c36cc6d829267 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -72,6 +72,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu);
 int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 				    u16 vport, u64 node_guid);
-- 
GitLab


From 3876638b2c7ebb2c9d181de1191db0de8cac143a Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Wed, 22 Nov 2023 18:32:11 -0800
Subject: [PATCH 3319/4076] net/mlx5e: Fix operation precedence bug in port
 timestamping napi_poll context

Indirection (*) is of lower precedence than postfix increment (++). Logic
in napi_poll context would cause an out-of-bound read by first increment
the pointer address by byte address space and then dereference the value.
Rather, the intended logic was to dereference first and then increment the
underlying value.

Fixes: 92214be5979c ("net/mlx5e: Update doorbell for port timestamping CQ before the software counter")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index c206cc0a84832..078f56a3cbb2b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -213,7 +213,7 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 	mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp);
 out:
 	napi_consume_skb(skb, budget);
-	md_buff[*md_buff_sz++] = metadata_id;
+	md_buff[(*md_buff_sz)++] = metadata_id;
 	if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) &&
 	    !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
 		queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work);
-- 
GitLab


From c20767fd45e82d64352db82d4fc8d281a43e4783 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Sun, 5 Nov 2023 17:09:46 +0200
Subject: [PATCH 3320/4076] net/mlx5e: Fix inconsistent hairpin RQT sizes

The processing of traffic in hairpin queues occurs in HW/FW and does not
involve the cpus, hence the upper bound on max num channels does not
apply to them.  Using this bound for the hairpin RQT max_table_size is
wrong.  It could be too small, and cause the error below [1].  As the
RQT size provided on init does not get modified later, use the same
value for both actual and max table sizes.

[1]
mlx5_core 0000:08:00.1: mlx5_cmd_out_err:805:(pid 1200): CREATE_RQT(0x916) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x538faf), err(-22)

Fixes: 74a8dadac17e ("net/mlx5e: Preparations for supporting larger number of channels")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 30932c9c9a8f0..047b465fc6a53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -761,7 +761,7 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp)
 
 	err = mlx5e_rss_params_indir_init(&indir, mdev,
 					  mlx5e_rqt_size(mdev, hp->num_channels),
-					  mlx5e_rqt_size(mdev, priv->max_nch));
+					  mlx5e_rqt_size(mdev, hp->num_channels));
 	if (err)
 		return err;
 
-- 
GitLab


From d76fdd31f953ac5046555171620f2562715e9b71 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Fri, 10 Nov 2023 11:10:22 +0100
Subject: [PATCH 3321/4076] net/mlx5e: Fix peer flow lists handling

The cited change refactored mlx5e_tc_del_fdb_peer_flow() to only clear DUP
flag when list of peer flows has become empty. However, if any concurrent
user holds a reference to a peer flow (for example, the neighbor update
workqueue task is updating peer flow's parent encap entry concurrently),
then the flow will not be removed from the peer list and, consecutively,
DUP flag will remain set. Since mlx5e_tc_del_fdb_peers_flow() calls
mlx5e_tc_del_fdb_peer_flow() for every possible peer index the algorithm
will try to remove the flow from eswitch instances that it has never peered
with causing either NULL pointer dereference when trying to remove the flow
peer list head of peer_index that was never initialized or a warning if the
list debug config is enabled[0].

Fix the issue by always removing the peer flow from the list even when not
releasing the last reference to it.

[0]:

[ 3102.985806] ------------[ cut here ]------------
[ 3102.986223] list_del corruption, ffff888139110698->next is NULL
[ 3102.986757] WARNING: CPU: 2 PID: 22109 at lib/list_debug.c:53 __list_del_entry_valid_or_report+0x4f/0xc0
[ 3102.987561] Modules linked in: act_ct nf_flow_table bonding act_tunnel_key act_mirred act_skbedit vxlan cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress mlx5_vdpa vringh vhost_iotlb vdpa openvswitch nsh xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat xt_addrtype xt_conntrack nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcg
ss oid_registry overlay rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core mlx5_core [last unloaded: bonding]
[ 3102.991113] CPU: 2 PID: 22109 Comm: revalidator28 Not tainted 6.6.0-rc6+ #3
[ 3102.991695] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[ 3102.992605] RIP: 0010:__list_del_entry_valid_or_report+0x4f/0xc0
[ 3102.993122] Code: 39 c2 74 56 48 8b 32 48 39 fe 75 62 48 8b 51 08 48 39 f2 75 73 b8 01 00 00 00 c3 48 89 fe 48 c7 c7 48 fd 0a 82 e8 41 0b ad ff <0f> 0b 31 c0 c3 48 89 fe 48 c7 c7 70 fd 0a 82 e8 2d 0b ad ff 0f 0b
[ 3102.994615] RSP: 0018:ffff8881383e7710 EFLAGS: 00010286
[ 3102.995078] RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000000
[ 3102.995670] RDX: 0000000000000001 RSI: ffff88885f89b640 RDI: ffff88885f89b640
[ 3102.997188] DEL flow 00000000be367878 on port 0
[ 3102.998594] RBP: dead000000000122 R08: 0000000000000000 R09: c0000000ffffdfff
[ 3102.999604] R10: 0000000000000008 R11: ffff8881383e7598 R12: dead000000000100
[ 3103.000198] R13: 0000000000000002 R14: ffff888139110000 R15: ffff888101901240
[ 3103.000790] FS:  00007f424cde4700(0000) GS:ffff88885f880000(0000) knlGS:0000000000000000
[ 3103.001486] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 3103.001986] CR2: 00007fd42e8dcb70 CR3: 000000011e68a003 CR4: 0000000000370ea0
[ 3103.002596] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 3103.003190] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 3103.003787] Call Trace:
[ 3103.004055]  <TASK>
[ 3103.004297]  ? __warn+0x7d/0x130
[ 3103.004623]  ? __list_del_entry_valid_or_report+0x4f/0xc0
[ 3103.005094]  ? report_bug+0xf1/0x1c0
[ 3103.005439]  ? console_unlock+0x4a/0xd0
[ 3103.005806]  ? handle_bug+0x3f/0x70
[ 3103.006149]  ? exc_invalid_op+0x13/0x60
[ 3103.006531]  ? asm_exc_invalid_op+0x16/0x20
[ 3103.007430]  ? __list_del_entry_valid_or_report+0x4f/0xc0
[ 3103.007910]  mlx5e_tc_del_fdb_peers_flow+0xcf/0x240 [mlx5_core]
[ 3103.008463]  mlx5e_tc_del_flow+0x46/0x270 [mlx5_core]
[ 3103.008944]  mlx5e_flow_put+0x26/0x50 [mlx5_core]
[ 3103.009401]  mlx5e_delete_flower+0x25f/0x380 [mlx5_core]
[ 3103.009901]  tc_setup_cb_destroy+0xab/0x180
[ 3103.010292]  fl_hw_destroy_filter+0x99/0xc0 [cls_flower]
[ 3103.010779]  __fl_delete+0x2d4/0x2f0 [cls_flower]
[ 3103.011207]  fl_delete+0x36/0x80 [cls_flower]
[ 3103.011614]  tc_del_tfilter+0x56f/0x750
[ 3103.011982]  rtnetlink_rcv_msg+0xff/0x3a0
[ 3103.012362]  ? netlink_ack+0x1c7/0x4e0
[ 3103.012719]  ? rtnl_calcit.isra.44+0x130/0x130
[ 3103.013134]  netlink_rcv_skb+0x54/0x100
[ 3103.013533]  netlink_unicast+0x1ca/0x2b0
[ 3103.013902]  netlink_sendmsg+0x361/0x4d0
[ 3103.014269]  __sock_sendmsg+0x38/0x60
[ 3103.014643]  ____sys_sendmsg+0x1f2/0x200
[ 3103.015018]  ? copy_msghdr_from_user+0x72/0xa0
[ 3103.015265]  ___sys_sendmsg+0x87/0xd0
[ 3103.016608]  ? copy_msghdr_from_user+0x72/0xa0
[ 3103.017014]  ? ___sys_recvmsg+0x9b/0xd0
[ 3103.017381]  ? ttwu_do_activate.isra.137+0x58/0x180
[ 3103.017821]  ? wake_up_q+0x49/0x90
[ 3103.018157]  ? futex_wake+0x137/0x160
[ 3103.018521]  ? __sys_sendmsg+0x51/0x90
[ 3103.018882]  __sys_sendmsg+0x51/0x90
[ 3103.019230]  ? exit_to_user_mode_prepare+0x56/0x130
[ 3103.019670]  do_syscall_64+0x3c/0x80
[ 3103.020017]  entry_SYSCALL_64_after_hwframe+0x46/0xb0
[ 3103.020469] RIP: 0033:0x7f4254811ef4
[ 3103.020816] Code: 89 f3 48 83 ec 10 48 89 7c 24 08 48 89 14 24 e8 42 eb ff ff 48 8b 14 24 41 89 c0 48 89 de 48 8b 7c 24 08 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 30 44 89 c7 48 89 04 24 e8 78 eb ff ff 48 8b
[ 3103.022290] RSP: 002b:00007f424cdd9480 EFLAGS: 00000293 ORIG_RAX: 000000000000002e
[ 3103.022970] RAX: ffffffffffffffda RBX: 00007f424cdd9510 RCX: 00007f4254811ef4
[ 3103.023564] RDX: 0000000000000000 RSI: 00007f424cdd9510 RDI: 0000000000000012
[ 3103.024158] RBP: 00007f424cdda238 R08: 0000000000000000 R09: 00007f41d801a4b0
[ 3103.024748] R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000001
[ 3103.025341] R13: 00007f424cdd9510 R14: 00007f424cdda240 R15: 00007f424cdd99a0
[ 3103.025931]  </TASK>
[ 3103.026182] ---[ end trace 0000000000000000 ]---
[ 3103.027033] ------------[ cut here ]------------

Fixes: 9be6c21fdcf8 ("net/mlx5e: Handle offloads flows per peer")
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 047b465fc6a53..9fb2c057bd787 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2014,9 +2014,10 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow,
 	list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) {
 		if (peer_index != mlx5_get_dev_index(peer_flow->priv->mdev))
 			continue;
+
+		list_del(&peer_flow->peer_flows);
 		if (refcount_dec_and_test(&peer_flow->refcnt)) {
 			mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow);
-			list_del(&peer_flow->peer_flows);
 			kfree(peer_flow);
 		}
 	}
-- 
GitLab


From cc8091587779cfaddb6b29c9e9edb9079a282cad Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Sun, 31 Dec 2023 15:19:50 +0200
Subject: [PATCH 3322/4076] net/mlx5: Fix a WARN upon a callback command
 failure

The below WARN [1] is reported once a callback command failed.

As a callback runs under an interrupt context, needs to use the IRQ
save/restore variant.

[1]
DEBUG_LOCKS_WARN_ON(lockdep_hardirq_context())
WARNING: CPU: 15 PID: 0 at kernel/locking/lockdep.c:4353
              lockdep_hardirqs_on_prepare+0x11b/0x180
Modules linked in: vhost_net vhost tap mlx5_vfio_pci
vfio_pci vfio_pci_core vfio_iommu_type1 vfio mlx5_vdpa vringh
vhost_iotlb vdpa nfnetlink_cttimeout openvswitch nsh ip6table_mangle
ip6table_nat ip6table_filter ip6_tables iptable_mangle
xt_conntrackxt_MASQUERADE nf_conntrack_netlink nfnetlink
xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5
auth_rpcgss oid_registry overlay rpcrdma rdma_ucm ib_iser libiscsi
scsi_transport_iscsi rdma_cm iw_cm ib_umad ib_ipoib ib_cm
mlx5_ib ib_uverbs ib_core fuse mlx5_core
CPU: 15 PID: 0 Comm: swapper/15 Tainted: G        W 6.7.0-rc4+ #1587
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
RIP: 0010:lockdep_hardirqs_on_prepare+0x11b/0x180
Code: 00 5b c3 c3 e8 e6 0d 58 00 85 c0 74 d6 8b 15 f0 c3
      76 01 85 d2 75 cc 48 c7 c6 04 a5 3b 82 48 c7 c7 f1
      e9 39 82 e8 95 12 f9 ff <0f> 0b 5b c3 e8 bc 0d 58 00
      85 c0 74 ac 8b 3d c6 c3 76 01 85 ff 75
RSP: 0018:ffffc900003ecd18 EFLAGS: 00010086
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000027
RDX: 0000000000000000 RSI: ffff88885fbdb880 RDI: ffff88885fbdb888
RBP: 00000000ffffff87 R08: 0000000000000000 R09: 0000000000000001
R10: 0000000000000000 R11: 284e4f5f4e524157 R12: 00000000002c9aa1
R13: ffff88810aace980 R14: ffff88810aace9b8 R15: 0000000000000003
FS:  0000000000000000(0000) GS:ffff88885fbc0000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f731436f4c8 CR3: 000000010aae6001 CR4: 0000000000372eb0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <IRQ>
? __warn+0x81/0x170
? lockdep_hardirqs_on_prepare+0x11b/0x180
? report_bug+0xf8/0x1c0
? handle_bug+0x3f/0x70
? exc_invalid_op+0x13/0x60
? asm_exc_invalid_op+0x16/0x20
? lockdep_hardirqs_on_prepare+0x11b/0x180
? lockdep_hardirqs_on_prepare+0x11b/0x180
trace_hardirqs_on+0x4a/0xa0
raw_spin_unlock_irq+0x24/0x30
cmd_status_err+0xc0/0x1a0 [mlx5_core]
cmd_status_err+0x1a0/0x1a0 [mlx5_core]
mlx5_cmd_exec_cb_handler+0x24/0x40 [mlx5_core]
mlx5_cmd_comp_handler+0x129/0x4b0 [mlx5_core]
cmd_comp_notifier+0x1a/0x20 [mlx5_core]
notifier_call_chain+0x3e/0xe0
atomic_notifier_call_chain+0x5f/0x130
mlx5_eq_async_int+0xe7/0x200 [mlx5_core]
notifier_call_chain+0x3e/0xe0
atomic_notifier_call_chain+0x5f/0x130
irq_int_handler+0x11/0x20 [mlx5_core]
__handle_irq_event_percpu+0x99/0x220
? tick_irq_enter+0x5d/0x80
handle_irq_event_percpu+0xf/0x40
handle_irq_event+0x3a/0x60
handle_edge_irq+0xa2/0x1c0
__common_interrupt+0x55/0x140
common_interrupt+0x7d/0xa0
</IRQ>
<TASK>
asm_common_interrupt+0x22/0x40
RIP: 0010:default_idle+0x13/0x20
Code: c0 08 00 00 00 4d 29 c8 4c 01 c7 4c 29 c2 e9 72 ff
ff ff cc cc cc cc 8b 05 ea 08 25 01 85 c0 7e 07 0f 00 2d 7f b0 26 00 fb
f4 <fa> c3 90 66 2e 0f 1f 84 00 00 00 00 00 65 48 8b 04 25 80 d0 02 00
RSP: 0018:ffffc9000010fec8 EFLAGS: 00000242
RAX: 0000000000000001 RBX: 000000000000000f RCX: 4000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff811c410c
RBP: ffffffff829478c0 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
? do_idle+0x1ec/0x210
default_idle_call+0x6c/0x90
do_idle+0x1ec/0x210
cpu_startup_entry+0x26/0x30
start_secondary+0x11b/0x150
secondary_startup_64_no_verify+0x165/0x16b
</TASK>
irq event stamp: 833284
hardirqs last  enabled at (833283): [<ffffffff811c410c>]
do_idle+0x1ec/0x210
hardirqs last disabled at (833284): [<ffffffff81daf9ef>]
common_interrupt+0xf/0xa0
softirqs last  enabled at (833224): [<ffffffff81dc199f>]
__do_softirq+0x2bf/0x40e
softirqs last disabled at (833177): [<ffffffff81178ddf>]
irq_exit_rcu+0x7f/0xa0

Fixes: 34f46ae0d4b3 ("net/mlx5: Add command failures data to debugfs")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index a7b1f9686c09a..4957412ff1f65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1923,6 +1923,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
 {
 	const char *namep = mlx5_command_str(opcode);
 	struct mlx5_cmd_stats *stats;
+	unsigned long flags;
 
 	if (!err || !(strcmp(namep, "unknown command opcode")))
 		return;
@@ -1930,7 +1931,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
 	stats = xa_load(&dev->cmd.stats, opcode);
 	if (!stats)
 		return;
-	spin_lock_irq(&stats->lock);
+	spin_lock_irqsave(&stats->lock, flags);
 	stats->failed++;
 	if (err < 0)
 		stats->last_failed_errno = -err;
@@ -1939,7 +1940,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
 		stats->last_failed_mbox_status = status;
 		stats->last_failed_syndrome = syndrome;
 	}
-	spin_unlock_irq(&stats->lock);
+	spin_unlock_irqrestore(&stats->lock, flags);
 }
 
 /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */
-- 
GitLab


From ec7cc38ef9f83553102e84c82536971a81630739 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Sat, 30 Dec 2023 22:40:37 +0200
Subject: [PATCH 3323/4076] net/mlx5: Bridge, fix multicast packets sent to
 uplink

To enable multicast packets which are offloaded in bridge multicast
offload mode to be sent also to uplink, FTE bit uplink_hairpin_en should
be set. Add this bit to FTE for the bridge multicast offload rules.

Fixes: 18c2916cee12 ("net/mlx5: Bridge, snoop igmp/mld packets")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c           | 2 ++
 include/linux/mlx5/fs.h                                    | 1 +
 include/linux/mlx5/mlx5_ifc.h                              | 2 +-
 4 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
index a7ed87e9d8426..22dd30cf8033f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c
@@ -83,6 +83,7 @@ mlx5_esw_bridge_mdb_flow_create(u16 esw_owner_vhca_id, struct mlx5_esw_bridge_md
 		i++;
 	}
 
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 	dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, outer_headers.dmac_47_16);
 	ether_addr_copy(dmac_v, entry->key.addr);
@@ -587,6 +588,7 @@ mlx5_esw_bridge_mcast_vlan_flow_create(u16 vlan_proto, struct mlx5_esw_bridge_po
 	if (!rule_spec)
 		return ERR_PTR(-ENOMEM);
 
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 
 	flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
@@ -662,6 +664,7 @@ mlx5_esw_bridge_mcast_fwd_flow_create(struct mlx5_esw_bridge_port *port)
 		dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
 		dest.vport.vhca_id = port->esw_owner_vhca_id;
 	}
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	handle = mlx5_add_flow_rules(port->mcast.ft, rule_spec, &flow_act, &dest, 1);
 
 	kvfree(rule_spec);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 1616a6144f7b4..9b8599c200e2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -566,6 +566,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 		 fte->flow_context.flow_tag);
 	MLX5_SET(flow_context, in_flow_context, flow_source,
 		 fte->flow_context.flow_source);
+	MLX5_SET(flow_context, in_flow_context, uplink_hairpin_en,
+		 !!(fte->flow_context.flags & FLOW_CONTEXT_UPLINK_HAIRPIN_EN));
 
 	MLX5_SET(flow_context, in_flow_context, extended_destination,
 		 extended_dest);
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 6f7725238abc2..3fb428ce7d1c7 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -132,6 +132,7 @@ struct mlx5_flow_handle;
 
 enum {
 	FLOW_CONTEXT_HAS_TAG = BIT(0),
+	FLOW_CONTEXT_UPLINK_HAIRPIN_EN = BIT(1),
 };
 
 struct mlx5_flow_context {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 37230253f9f17..c726f90ab7524 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -3576,7 +3576,7 @@ struct mlx5_ifc_flow_context_bits {
 	u8         action[0x10];
 
 	u8         extended_destination[0x1];
-	u8         reserved_at_81[0x1];
+	u8         uplink_hairpin_en[0x1];
 	u8         flow_source[0x2];
 	u8         encrypt_decrypt_type[0x4];
 	u8         destination_list_size[0x18];
-- 
GitLab


From 5665954293f13642f9c052ead83c1e9d8cff186f Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sun, 17 Dec 2023 11:24:08 +0200
Subject: [PATCH 3324/4076] net/mlx5: DR, Use the right GVMI number for drop
 action

When FW provides ICM addresses for drop RX/TX, the provided capability
is 64 bits that contain its GVMI as well as the ICM address itself.
In case of TX DROP this GVMI is different from the GVMI that the
domain is operating on.

This patch fixes the action to use these GVMI IDs, as provided by FW.

Fixes: 9db810ed2d37 ("net/mlx5: DR, Expose steering action functionality")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 6f9790e97fed2..95517c4aca0fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -788,6 +788,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 		switch (action_type) {
 		case DR_ACTION_TYP_DROP:
 			attr.final_icm_addr = nic_dmn->drop_icm_addr;
+			attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48;
 			break;
 		case DR_ACTION_TYP_FT:
 			dest_action = action;
-- 
GitLab


From 5b2a2523eeea5f03d39a9d1ff1bad2e9f8eb98d2 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sun, 17 Dec 2023 13:20:36 +0200
Subject: [PATCH 3325/4076] net/mlx5: DR, Can't go to uplink vport on RX rule

Go-To-Vport action on RX is not allowed when the vport is uplink.
In such case, the packet should be dropped.

Fixes: 9db810ed2d37 ("net/mlx5: DR, Expose steering action functionality")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/steering/dr_action.c      | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 95517c4aca0fa..2ebb61ef3ea9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -874,11 +874,17 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 							action->sampler->tx_icm_addr;
 			break;
 		case DR_ACTION_TYP_VPORT:
-			attr.hit_gvmi = action->vport->caps->vhca_gvmi;
-			dest_action = action;
-			attr.final_icm_addr = rx_rule ?
-				action->vport->caps->icm_address_rx :
-				action->vport->caps->icm_address_tx;
+			if (unlikely(rx_rule && action->vport->caps->num == MLX5_VPORT_UPLINK)) {
+				/* can't go to uplink on RX rule - dropping instead */
+				attr.final_icm_addr = nic_dmn->drop_icm_addr;
+				attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48;
+			} else {
+				attr.hit_gvmi = action->vport->caps->vhca_gvmi;
+				dest_action = action;
+				attr.final_icm_addr = rx_rule ?
+						      action->vport->caps->icm_address_rx :
+						      action->vport->caps->icm_address_tx;
+			}
 			break;
 		case DR_ACTION_TYP_POP_VLAN:
 			if (!rx_rule && !(dmn->ste_ctx->actions_caps &
-- 
GitLab


From 20cbf8cbb827094197f3b17db60d71449415db1e Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Tue, 28 Nov 2023 14:01:54 -0800
Subject: [PATCH 3326/4076] net/mlx5: Use mlx5 device constant for selecting CQ
 period mode for ASO

mlx5 devices have specific constants for choosing the CQ period mode. These
constants do not have to match the constants used by the kernel software
API for DIM period mode selection.

Fixes: cdd04f4d4d71 ("net/mlx5: Add support to create SQ and CQ for ASO")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
index 40c7be1240416..58bd749b5e4de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
@@ -98,7 +98,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data)
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
-	MLX5_SET(cqc,   cqc, cq_period_mode, DIM_CQ_PERIOD_MODE_START_FROM_EQE);
+	MLX5_SET(cqc,   cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 	MLX5_SET(cqc,   cqc, c_eqn_or_apu_element, eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
-- 
GitLab


From 20f5468a7988dedd94a57ba8acd65ebda6a59723 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 12 Dec 2023 13:52:55 +0200
Subject: [PATCH 3327/4076] net/mlx5e: Allow software parsing when IPsec crypto
 is enabled

All ConnectX devices have software parsing capability enabled, but it is
more correct to set allow_swp only if capability exists, which for IPsec
means that crypto offload is supported.

Fixes: 2451da081a34 ("net/mlx5: Unify device IPsec capabilities check")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 284253b79266b..5d213a9886f11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -1064,8 +1064,8 @@ void mlx5e_build_sq_param(struct mlx5_core_dev *mdev,
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 	bool allow_swp;
 
-	allow_swp =
-		mlx5_geneve_tx_allowed(mdev) || !!mlx5_ipsec_device_caps(mdev);
+	allow_swp = mlx5_geneve_tx_allowed(mdev) ||
+		    (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO);
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	MLX5_SET(sqc, sqc, allow_swp, allow_swp);
-- 
GitLab


From 315a597f9bcfe7fe9980985031413457bee95510 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 26 Nov 2023 11:08:10 +0200
Subject: [PATCH 3328/4076] net/mlx5e: Ignore IPsec replay window values on
 sender side

XFRM stack doesn't prevent from users to configure replay window
in TX side and strongswan sets replay_window to be 1. It causes
to failures in validation logic when trying to offload the SA.

Replay window is not relevant in TX side and should be ignored.

Fixes: cded6d80129b ("net/mlx5e: Store replay window in XFRM attributes")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c   | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 161c5190c236a..05612d9c6080c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -336,12 +336,17 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	/* iv len */
 	aes_gcm->icv_len = x->aead->alg_icv_len;
 
+	attrs->dir = x->xso.dir;
+
 	/* esn */
 	if (x->props.flags & XFRM_STATE_ESN) {
 		attrs->replay_esn.trigger = true;
 		attrs->replay_esn.esn = sa_entry->esn_state.esn;
 		attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb;
 		attrs->replay_esn.overlap = sa_entry->esn_state.overlap;
+		if (attrs->dir == XFRM_DEV_OFFLOAD_OUT)
+			goto skip_replay_window;
+
 		switch (x->replay_esn->replay_window) {
 		case 32:
 			attrs->replay_esn.replay_window =
@@ -365,7 +370,7 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 		}
 	}
 
-	attrs->dir = x->xso.dir;
+skip_replay_window:
 	/* spi */
 	attrs->spi = be32_to_cpu(x->id.spi);
 
@@ -501,7 +506,8 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
 			return -EINVAL;
 		}
 
-		if (x->replay_esn && x->replay_esn->replay_window != 32 &&
+		if (x->replay_esn && x->xso.dir == XFRM_DEV_OFFLOAD_IN &&
+		    x->replay_esn->replay_window != 32 &&
 		    x->replay_esn->replay_window != 64 &&
 		    x->replay_esn->replay_window != 128 &&
 		    x->replay_esn->replay_window != 256) {
-- 
GitLab


From 3c6d5189246f590e4e1f167991558bdb72a4738b Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Wed, 17 Jan 2024 15:17:36 +0800
Subject: [PATCH 3329/4076] net/mlx5e: fix a double-free in arfs_create_groups

When `in` allocated by kvzalloc fails, arfs_create_groups will free
ft->g and return an error. However, arfs_create_table, the only caller of
arfs_create_groups, will hold this error and call to
mlx5e_destroy_flow_table, in which the ft->g will be freed again.

Fixes: 1cabe6b0965e ("net/mlx5e: Create aRFS flow tables")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_arfs.c | 26 +++++++++++--------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index bb7f86c993e55..e66f486faafe1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -254,11 +254,13 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 
 	ft->g = kcalloc(MLX5E_ARFS_NUM_GROUPS,
 			sizeof(*ft->g), GFP_KERNEL);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if  (!in || !ft->g) {
-		kfree(ft->g);
-		kvfree(in);
+	if (!ft->g)
 		return -ENOMEM;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto err_free_g;
 	}
 
 	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
@@ -278,7 +280,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 		break;
 	default:
 		err = -EINVAL;
-		goto out;
+		goto err_free_in;
 	}
 
 	switch (type) {
@@ -300,7 +302,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 		break;
 	default:
 		err = -EINVAL;
-		goto out;
+		goto err_free_in;
 	}
 
 	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
@@ -309,7 +311,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
 	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
+		goto err_clean_group;
 	ft->num_groups++;
 
 	memset(in, 0, inlen);
@@ -318,18 +320,20 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft,
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
 	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
+		goto err_clean_group;
 	ft->num_groups++;
 
 	kvfree(in);
 	return 0;
 
-err:
+err_clean_group:
 	err = PTR_ERR(ft->g[ft->num_groups]);
 	ft->g[ft->num_groups] = NULL;
-out:
+err_free_in:
 	kvfree(in);
-
+err_free_g:
+	kfree(ft->g);
+	ft->g = NULL;
 	return err;
 }
 
-- 
GitLab


From aef855df7e1bbd5aa4484851561211500b22707e Mon Sep 17 00:00:00 2001
From: Dinghao Liu <dinghao.liu@zju.edu.cn>
Date: Tue, 28 Nov 2023 17:29:01 +0800
Subject: [PATCH 3330/4076] net/mlx5e: fix a potential double-free in
 fs_any_create_groups

When kcalloc() for ft->g succeeds but kvzalloc() for in fails,
fs_any_create_groups() will free ft->g. However, its caller
fs_any_create_table() will free ft->g again through calling
mlx5e_destroy_flow_table(), which will lead to a double-free.
Fix this by setting ft->g to NULL in fs_any_create_groups().

Fixes: 0f575c20bf06 ("net/mlx5e: Introduce Flow Steering ANY API")
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
index e1283531e0b81..671adbad0a40f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
@@ -436,6 +436,7 @@ static int fs_any_create_groups(struct mlx5e_flow_table *ft)
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if  (!in || !ft->g) {
 		kfree(ft->g);
+		ft->g = NULL;
 		kvfree(in);
 		return -ENOMEM;
 	}
-- 
GitLab


From 3213b8070ac69b32f05fa2328cbebe0eca75c1bd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Wed, 17 Jan 2024 14:40:44 +0100
Subject: [PATCH 3331/4076] drm/xe/dmabuf: Make xe_dmabuf_ops static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is not referenced outside of the xe_dma_buf.c source file.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240117134048.165425-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit e2dc52f849f8694bdabb75127164c9df622af459)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_dma_buf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c
index 64ed303728fda..da2627ed6ae7a 100644
--- a/drivers/gpu/drm/xe/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/xe_dma_buf.c
@@ -175,7 +175,7 @@ static int xe_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 	return 0;
 }
 
-const struct dma_buf_ops xe_dmabuf_ops = {
+static const struct dma_buf_ops xe_dmabuf_ops = {
 	.attach = xe_dma_buf_attach,
 	.detach = xe_dma_buf_detach,
 	.pin = xe_dma_buf_pin,
-- 
GitLab


From 03b72dbbd4e96d0197aa8cf894a24a4db8623031 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Wed, 17 Jan 2024 14:40:48 +0100
Subject: [PATCH 3332/4076] drm/xe: Use a NULL pointer instead of 0.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The last argument of xe_pcode_read() is a pointer. Use NULL instead of 0.

Fixes: 92d44a422d0d ("drm/xe/hwmon: Expose card reactive critical power")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240117134048.165425-6-thomas.hellstrom@linux.intel.com
(cherry picked from commit 79f8eacbdf9dad7ead39b3319e31e12d4dc6529e)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_hwmon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index 6ef2aa1eae8b0..174ed2185481e 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -419,7 +419,7 @@ static int xe_hwmon_pcode_read_i1(struct xe_gt *gt, u32 *uval)
 
 	return xe_pcode_read(gt, PCODE_MBOX(PCODE_POWER_SETUP,
 			     POWER_SETUP_SUBCOMMAND_READ_I1, 0),
-			     uval, 0);
+			     uval, NULL);
 }
 
 static int xe_hwmon_pcode_write_i1(struct xe_gt *gt, u32 uval)
-- 
GitLab


From 32f6c3325703c98edee8f1005ad47b4d8431b758 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 18 Jan 2024 16:16:08 -0800
Subject: [PATCH 3333/4076] drm/xe: Use _ULL for u64 division
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use DIV_ROUND_UP_ULL() so it also works on 32bit build.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240119001612.2991381-2-lucas.demarchi@intel.com
(cherry picked from commit 7b5bdb447b14930b9ef3e39bd301937889c60c96)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index b8d8da5466708..1f0b4b9ce84f5 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -613,7 +613,7 @@ void xe_device_wmb(struct xe_device *xe)
 u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
 {
 	return xe_device_has_flat_ccs(xe) ?
-		DIV_ROUND_UP(size, NUM_BYTES_PER_CCS_BYTE(xe)) : 0;
+		DIV_ROUND_UP_ULL(size, NUM_BYTES_PER_CCS_BYTE(xe)) : 0;
 }
 
 bool xe_device_mem_access_ongoing(struct xe_device *xe)
-- 
GitLab


From 52e8948c6b6a41603371996b9bc0e43e17d690b4 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 18 Jan 2024 16:16:09 -0800
Subject: [PATCH 3334/4076] drm/xe/mmio: Cast to u64 when printing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

resource_size_t uses %pa format in printk since the size varies
depending on build options. However to keep the io_size/physical_size
addition in the same call we can't pass the address without adding yet
another variable in these function. Simply cast it to u64 and keep using
%llx.

Fixes: 286089ce6929 ("drm/xe: Improve vram info debug printing")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: Michael J. Ruhl <michael.j.ruhl@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240119001612.2991381-3-lucas.demarchi@intel.com
(cherry picked from commit 6d8d038364d8ec573e9dc0872e17bee1e5f12490)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_mmio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index c8c5d74b6e904..5f6b53ea5528b 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -272,8 +272,8 @@ int xe_mmio_probe_vram(struct xe_device *xe)
 		drm_info(&xe->drm, "VRAM[%u, %u]: Actual physical size %pa, usable size exclude stolen %pa, CPU accessible size %pa\n", id,
 			 tile->id, &tile->mem.vram.actual_physical_size, &tile->mem.vram.usable_size, &tile->mem.vram.io_size);
 		drm_info(&xe->drm, "VRAM[%u, %u]: DPA range: [%pa-%llx], io range: [%pa-%llx]\n", id, tile->id,
-			 &tile->mem.vram.dpa_base, tile->mem.vram.dpa_base + tile->mem.vram.actual_physical_size,
-			 &tile->mem.vram.io_start, tile->mem.vram.io_start + tile->mem.vram.io_size);
+			 &tile->mem.vram.dpa_base, tile->mem.vram.dpa_base + (u64)tile->mem.vram.actual_physical_size,
+			 &tile->mem.vram.io_start, tile->mem.vram.io_start + (u64)tile->mem.vram.io_size);
 
 		/* calculate total size using tile size to get the correct HW sizing */
 		total_size += tile_size;
-- 
GitLab


From 981460d8ee6042b14149fd8931ae27b91f2146b1 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 18 Jan 2024 16:16:10 -0800
Subject: [PATCH 3335/4076] drm/xe/display: Avoid calling readq()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

readq() is not available in 32bits and i915_gem_object_read_from_page()
is supposed to allow reading arbitrary sizes determined by the `size`
argument. Currently the only caller only passes a size == 8 so the
second problem is not that big. Migrate to calling
memcpy()/memcpy_fromio() to allow possible changes in the display side
and to fix the build on 32b architectures.

v2: Use memcpy/memcpy_fromio directly rather than using iosys-map with
    the same size == 8 bytes restriction (Matt Roper)

Fixes: 44e694958b95 ("drm/xe/display: Implement display support")
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240119001612.2991381-4-lucas.demarchi@intel.com
(cherry picked from commit 406663f777bee53e9ad93dc080c333d4655ab7de)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 .../drm/xe/compat-i915-headers/gem/i915_gem_object.h  | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
index 5f19550cc8453..68d9f6116bdfc 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
@@ -35,12 +35,10 @@ static inline int i915_gem_object_read_from_page(struct xe_bo *bo,
 					  u32 ofs, u64 *ptr, u32 size)
 {
 	struct ttm_bo_kmap_obj map;
-	void *virtual;
+	void *src;
 	bool is_iomem;
 	int ret;
 
-	XE_WARN_ON(size != 8);
-
 	ret = xe_bo_lock(bo, true);
 	if (ret)
 		return ret;
@@ -50,11 +48,12 @@ static inline int i915_gem_object_read_from_page(struct xe_bo *bo,
 		goto out_unlock;
 
 	ofs &= ~PAGE_MASK;
-	virtual = ttm_kmap_obj_virtual(&map, &is_iomem);
+	src = ttm_kmap_obj_virtual(&map, &is_iomem);
+	src += ofs;
 	if (is_iomem)
-		*ptr = readq((void __iomem *)(virtual + ofs));
+		memcpy_fromio(ptr, (void __iomem *)src, size);
 	else
-		*ptr = *(u64 *)(virtual + ofs);
+		memcpy(ptr, src, size);
 
 	ttm_bo_kunmap(&map);
 out_unlock:
-- 
GitLab


From c0e2508cb1004fdb153fbbcf0101404abfefdddd Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Fri, 19 Jan 2024 09:48:26 +0530
Subject: [PATCH 3336/4076] drm/xe/xe2: Use XE_CACHE_WB pat index
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pat table entry associated with XE_CACHE_WB is coherent whereas
XE_CACHE_NONE is non coherent. Migration expects the coherency
with cpu therefore use the coherent entry XE_CACHE_WB for
buffers not supporting compression. For read/write to flat ccs region
the issue is not related to coherency with cpu. The hardware expects
the pat index associated with GPUVA for indirect access to be
compression enabled hence use XE_CACHE_NONE_COMPRESSION.

v2
- Fix the argument to emit_pte, pass the bool directly. (Thomas)

v3
- Rebase
- Update commit message (Matt)

v4
- Add a Fixes: tag. (Thomas)

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: 65ef8dbad1db ("drm/xe/xe2: Update emit_pte to use compression enabled PAT index")
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240119041826.1670496-1-himal.prasad.ghimiray@intel.com
(cherry picked from commit 6a02867560f77328ae5637b70b06704b140aafa6)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index e05e9e7282b68..5c6c546242521 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -472,7 +472,7 @@ static void emit_pte(struct xe_migrate *m,
 	/* Indirect access needs compression enabled uncached PAT index */
 	if (GRAPHICS_VERx100(xe) >= 2000)
 		pat_index = is_comp_pte ? xe->pat.idx[XE_CACHE_NONE_COMPRESSION] :
-					  xe->pat.idx[XE_CACHE_NONE];
+					  xe->pat.idx[XE_CACHE_WB];
 	else
 		pat_index = xe->pat.idx[XE_CACHE_WB];
 
@@ -760,14 +760,14 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
 			xe_res_next(&src_it, src_L0);
 		else
-			emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
-				 src);
+			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs,
+				 &src_it, src_L0, src);
 
 		if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
 			xe_res_next(&dst_it, src_L0);
 		else
-			emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
-				 dst);
+			emit_pte(m, bb, dst_L0_pt, dst_is_vram, copy_system_ccs,
+				 &dst_it, src_L0, dst);
 
 		if (copy_system_ccs)
 			emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src);
@@ -1009,8 +1009,8 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it))
 			xe_res_next(&src_it, clear_L0);
 		else
-			emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0,
-				 dst);
+			emit_pte(m, bb, clear_L0_pt, clear_vram, clear_system_ccs,
+				 &src_it, clear_L0, dst);
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
-- 
GitLab


From d186e51b0ed05a0cd94c7c9756740a855325c557 Mon Sep 17 00:00:00 2001
From: Moti Haimovski <mhaimovski@habana.ai>
Date: Mon, 22 Jan 2024 12:24:24 +0200
Subject: [PATCH 3337/4076] drm/xe/vm: bugfix in xe_vm_create_ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix xe_vm_create_ioctl routine not freeing the vm-id allocated to it
when the function fails.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Moti Haimovski <mhaimovski@habana.ai>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240122102424.4008095-1-mhaimovski@habana.ai
(cherry picked from commit f6bf0424cadc27d7cf6a049d2db960e4b52fa513)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 10b6995fbf294..53833ab81424c 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1855,10 +1855,8 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&xef->vm.lock);
 	err = xa_alloc(&xef->vm.xa, &id, vm, xa_limit_32b, GFP_KERNEL);
 	mutex_unlock(&xef->vm.lock);
-	if (err) {
-		xe_vm_close_and_put(vm);
-		return err;
-	}
+	if (err)
+		goto err_close_and_put;
 
 	if (xe->info.has_asid) {
 		mutex_lock(&xe->usm.lock);
@@ -1866,11 +1864,9 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 				      XA_LIMIT(1, XE_MAX_ASID - 1),
 				      &xe->usm.next_asid, GFP_KERNEL);
 		mutex_unlock(&xe->usm.lock);
-		if (err < 0) {
-			xe_vm_close_and_put(vm);
-			return err;
-		}
-		err = 0;
+		if (err < 0)
+			goto err_free_id;
+
 		vm->usm.asid = asid;
 	}
 
@@ -1888,6 +1884,15 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 #endif
 
 	return 0;
+
+err_free_id:
+	mutex_lock(&xef->vm.lock);
+	xa_erase(&xef->vm.xa, id);
+	mutex_unlock(&xef->vm.lock);
+err_close_and_put:
+	xe_vm_close_and_put(vm);
+
+	return err;
 }
 
 int xe_vm_destroy_ioctl(struct drm_device *dev, void *data,
-- 
GitLab


From 9e3a13f3eef6b14a26cc2660ca2f43f0e46b4318 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Mon, 22 Jan 2024 19:12:42 -0800
Subject: [PATCH 3338/4076] drm/xe: Remove PVC from xe_wa kunit tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the PCI IDs for PVC weren't added to the xe driver, the xe_wa
tests should not try to create a fake PVC device since they can't find
the right PCI ID. Fix bugs when running kunit:

	# xe_wa_gt: ASSERTION FAILED at drivers/gpu/drm/xe/tests/xe_wa_test.c:111
	Expected ret == 0, but
	    ret == -19 (0xffffffffffffffed)
	[FAILED] PVC (B0)
	# xe_wa_gt: ASSERTION FAILED at drivers/gpu/drm/xe/tests/xe_wa_test.c:111
	Expected ret == 0, but
	    ret == -19 (0xffffffffffffffed)
	[FAILED] PVC (B1)
	# xe_wa_gt: ASSERTION FAILED at drivers/gpu/drm/xe/tests/xe_wa_test.c:111
	Expected ret == 0, but
	    ret == -19 (0xffffffffffffffed)
	[FAILED] PVC (C0)

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240123031242.3548724-1-lucas.demarchi@intel.com
(cherry picked from commit ab5ae65fb25d06c38a6617a628b964828adb4786)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/tests/xe_wa_test.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_wa_test.c b/drivers/gpu/drm/xe/tests/xe_wa_test.c
index a53c22a195824..b4715b78ef3bf 100644
--- a/drivers/gpu/drm/xe/tests/xe_wa_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_wa_test.c
@@ -74,9 +74,6 @@ static const struct platform_test_case cases[] = {
 	SUBPLATFORM_CASE(DG2, G11, B1),
 	SUBPLATFORM_CASE(DG2, G12, A0),
 	SUBPLATFORM_CASE(DG2, G12, A1),
-	PLATFORM_CASE(PVC, B0),
-	PLATFORM_CASE(PVC, B1),
-	PLATFORM_CASE(PVC, C0),
 	GMDID_CASE(METEORLAKE, 1270, A0, 1300, A0),
 	GMDID_CASE(METEORLAKE, 1271, A0, 1300, A0),
 	GMDID_CASE(LUNARLAKE, 2004, A0, 2000, A0),
-- 
GitLab


From 56062d60f117dccfb5281869e0ab61e090baf864 Mon Sep 17 00:00:00 2001
From: Richard Palethorpe <rpalethorpe@suse.com>
Date: Wed, 10 Jan 2024 15:01:22 +0200
Subject: [PATCH 3339/4076] x86/entry/ia32: Ensure s32 is sign extended to s64

Presently ia32 registers stored in ptregs are unconditionally cast to
unsigned int by the ia32 stub. They are then cast to long when passed to
__se_sys*, but will not be sign extended.

This takes the sign of the syscall argument into account in the ia32
stub. It still casts to unsigned int to avoid implementation specific
behavior. However then casts to int or unsigned int as necessary. So that
the following cast to long sign extends the value.

This fixes the io_pgetevents02 LTP test when compiled with -m32. Presently
the systemcall io_pgetevents_time64() unexpectedly accepts -1 for the
maximum number of events.

It doesn't appear other systemcalls with signed arguments are effected
because they all have compat variants defined and wired up.

Fixes: ebeb8c82ffaf ("syscalls/x86: Use 'struct pt_regs' based syscall calling for IA32_EMULATION and x32")
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Richard Palethorpe <rpalethorpe@suse.com>
Signed-off-by: Nikolay Borisov <nik.borisov@suse.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240110130122.3836513-1-nik.borisov@suse.com
Link: https://lore.kernel.org/ltp/20210921130127.24131-1-rpalethorpe@suse.com/
---
 arch/x86/include/asm/syscall_wrapper.h | 25 +++++++++++++++++++++----
 include/linux/syscalls.h               |  1 +
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index 21f9407be5d35..7e88705e907f4 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 		,,regs->di,,regs->si,,regs->dx				\
 		,,regs->r10,,regs->r8,,regs->r9)			\
 
+
+/* SYSCALL_PT_ARGS is Adapted from s390x */
+#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6)			\
+	SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp))
+#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5)				\
+	SYSCALL_PT_ARG4(m, t1, t2, t3, t4),  m(t5, (regs->di))
+#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4)				\
+	SYSCALL_PT_ARG3(m, t1, t2, t3),  m(t4, (regs->si))
+#define SYSCALL_PT_ARG3(m, t1, t2, t3)					\
+	SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx))
+#define SYSCALL_PT_ARG2(m, t1, t2)					\
+	SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx))
+#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx))
+#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__)
+
+#define __SC_COMPAT_CAST(t, a)						\
+	(__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U)))	\
+	(unsigned int)a
+
 /* Mapping of registers to parameters for syscalls on i386 */
 #define SC_IA32_REGS_TO_ARGS(x, ...)					\
-	__MAP(x,__SC_ARGS						\
-	      ,,(unsigned int)regs->bx,,(unsigned int)regs->cx		\
-	      ,,(unsigned int)regs->dx,,(unsigned int)regs->si		\
-	      ,,(unsigned int)regs->di,,(unsigned int)regs->bp)
+	SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST,				\
+			__MAP(x, __SC_TYPE, __VA_ARGS__))		\
 
 #define __SYS_STUB0(abi, name)						\
 	long __##abi##_##name(const struct pt_regs *regs);		\
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index cdba4d0c6d4a8..77eb9b0e76850 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -128,6 +128,7 @@ struct mnt_id_req;
 #define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL))
 #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a
 #define __SC_CAST(t, a)	(__force t) a
+#define __SC_TYPE(t, a)	t
 #define __SC_ARGS(t, a)	a
 #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long))
 
-- 
GitLab


From b184c8c2889ceef0a137c7d0567ef9fe3d92276e Mon Sep 17 00:00:00 2001
From: Dawei Li <dawei.li@shingroup.cn>
Date: Mon, 22 Jan 2024 16:57:15 +0800
Subject: [PATCH 3340/4076] genirq: Initialize resend_node hlist for all
 interrupt descriptors

For a CONFIG_SPARSE_IRQ=n kernel, early_irq_init() is supposed to
initialize all interrupt descriptors.

It does except for irq_desc::resend_node, which ia only initialized for the
first descriptor.

Use the indexed decriptor and not the base pointer to address that.

Fixes: bc06a9e08742 ("genirq: Use hlist for managing resend handlers")
Signed-off-by: Dawei Li <dawei.li@shingroup.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240122085716.2999875-5-dawei.li@shingroup.cn
---
 kernel/irq/irqdesc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 27ca1c866f298..371eb1711d346 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -600,7 +600,7 @@ int __init early_irq_init(void)
 		mutex_init(&desc[i].request_mutex);
 		init_waitqueue_head(&desc[i].wait_for_threads);
 		desc_set_defaults(i, &desc[i], node, NULL, NULL);
-		irq_resend_init(desc);
+		irq_resend_init(&desc[i]);
 	}
 	return arch_early_irq_init();
 }
-- 
GitLab


From fcfc9f711d1e2fc7876ac12b1b16c509404b9625 Mon Sep 17 00:00:00 2001
From: Kailang Yang <kailang@realtek.com>
Date: Wed, 24 Jan 2024 14:21:47 +0800
Subject: [PATCH 3341/4076] ALSA: hda/realtek - Add speaker pin verbtable for
 Dell dual speaker platform

SSID 0x0c0d platform. It can't mute speaker when HP plugged.
This patch add quirk to fill speaker pin verbtable.
And disable speaker passthrough.

Signed-off-by: Kailang Yang <kailang@realtek.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/38b82976a875451d833d514cee34ff6a@realtek.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 19f2eb26659d8..bfefe9ccbc6be 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -439,6 +439,10 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 		alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
 		fallthrough;
 	case 0x10ec0215:
+	case 0x10ec0285:
+	case 0x10ec0289:
+		alc_update_coef_idx(codec, 0x36, 1<<13, 0);
+		fallthrough;
 	case 0x10ec0230:
 	case 0x10ec0233:
 	case 0x10ec0235:
@@ -452,9 +456,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0283:
 	case 0x10ec0286:
 	case 0x10ec0288:
-	case 0x10ec0285:
 	case 0x10ec0298:
-	case 0x10ec0289:
 	case 0x10ec0300:
 		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
 		break;
@@ -9732,6 +9734,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0beb, "Dell XPS 15 9530 (2023)", ALC289_FIXUP_DELL_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0c0d, "Dell Oasis", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
-- 
GitLab


From 7c4298534ce3c4b85099aba53442ec82ef17578b Mon Sep 17 00:00:00 2001
From: Jacob Siverskog <jacob@teenage.engineering>
Date: Wed, 24 Jan 2024 11:18:24 +0100
Subject: [PATCH 3342/4076] ALSA: usb-audio: fix typo

fix typo in midi fallback log.

Signed-off-by: Jacob Siverskog <jacob@teenage.engineering>
Fixes: ff49d1df79ae ("ALSA: usb-audio: USB MIDI 2.0 UMP support")
Link: https://lore.kernel.org/r/20240124101827.35433-1-jacob@teenage.engineering
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/midi2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c
index 1ec177fe284ed..820d3e4b672ab 100644
--- a/sound/usb/midi2.c
+++ b/sound/usb/midi2.c
@@ -1085,7 +1085,7 @@ int snd_usb_midi_v2_create(struct snd_usb_audio *chip,
 	}
 	if ((quirk && quirk->type != QUIRK_MIDI_STANDARD_INTERFACE) ||
 	    iface->num_altsetting < 2) {
-		usb_audio_info(chip, "Quirk or no altest; falling back to MIDI 1.0\n");
+		usb_audio_info(chip, "Quirk or no altset; falling back to MIDI 1.0\n");
 		goto fallback_to_midi1;
 	}
 	hostif = &iface->altsetting[1];
-- 
GitLab


From d62ccb59afcd94e8d301433974672b156392289d Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 24 Jan 2024 20:08:34 +0800
Subject: [PATCH 3343/4076] ALSA: virtio: remove duplicate check if queue is
 broken

virtqueue_enable_cb() will call virtqueue_poll() which will check if
queue is broken at beginning, so remove the virtqueue_is_broken() call

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://lore.kernel.org/r/20240124120834.49410-1-lirongqing@baidu.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/virtio/virtio_card.c    | 2 --
 sound/virtio/virtio_ctl_msg.c | 2 --
 sound/virtio/virtio_pcm_msg.c | 2 --
 3 files changed, 6 deletions(-)

diff --git a/sound/virtio/virtio_card.c b/sound/virtio/virtio_card.c
index e2847c040f750..b158c3cb8e5f5 100644
--- a/sound/virtio/virtio_card.c
+++ b/sound/virtio/virtio_card.c
@@ -91,8 +91,6 @@ static void virtsnd_event_notify_cb(struct virtqueue *vqueue)
 			virtsnd_event_dispatch(snd, event);
 			virtsnd_event_send(vqueue, event, true, GFP_ATOMIC);
 		}
-		if (unlikely(virtqueue_is_broken(vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/sound/virtio/virtio_ctl_msg.c b/sound/virtio/virtio_ctl_msg.c
index 18dc5aca2e0c5..9dabea01277f8 100644
--- a/sound/virtio/virtio_ctl_msg.c
+++ b/sound/virtio/virtio_ctl_msg.c
@@ -303,8 +303,6 @@ void virtsnd_ctl_notify_cb(struct virtqueue *vqueue)
 		virtqueue_disable_cb(vqueue);
 		while ((msg = virtqueue_get_buf(vqueue, &length)))
 			virtsnd_ctl_msg_complete(msg);
-		if (unlikely(virtqueue_is_broken(vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/sound/virtio/virtio_pcm_msg.c b/sound/virtio/virtio_pcm_msg.c
index 542446c4c7ba8..8c32efaf4c529 100644
--- a/sound/virtio/virtio_pcm_msg.c
+++ b/sound/virtio/virtio_pcm_msg.c
@@ -358,8 +358,6 @@ static inline void virtsnd_pcm_notify_cb(struct virtio_snd_queue *queue)
 		virtqueue_disable_cb(queue->vqueue);
 		while ((msg = virtqueue_get_buf(queue->vqueue, &written_bytes)))
 			virtsnd_pcm_msg_complete(msg, written_bytes);
-		if (unlikely(virtqueue_is_broken(queue->vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(queue->vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
-- 
GitLab


From d915a6850e27efb383cd4400caadfe47792623df Mon Sep 17 00:00:00 2001
From: Alexander Tsoy <alexander@tsoy.me>
Date: Wed, 24 Jan 2024 16:02:39 +0300
Subject: [PATCH 3344/4076] ALSA: usb-audio: Add delay quirk for MOTU M Series
 2nd revision

Audio control requests that sets sampling frequency sometimes fail on
this card. Adding delay between control messages eliminates that problem.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=217601
Cc: <stable@vger.kernel.org>
Signed-off-by: Alexander Tsoy <alexander@tsoy.me>
Link: https://lore.kernel.org/r/20240124130239.358298-1-alexander@tsoy.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 43c14a81a1e2f..be0ce1fc4f26c 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2075,6 +2075,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x0763, 0x2031, /* M-Audio Fast Track C600 */
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x07fd, 0x000b, /* MOTU M Series 2nd hardware revision */
+		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x0951, 0x16ad, /* Kingston HyperX */
-- 
GitLab


From edcf9725150e42beeca42d085149f4c88fa97afd Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 22 Jan 2024 14:58:16 +1100
Subject: [PATCH 3345/4076] nfsd: fix RELEASE_LOCKOWNER

The test on so_count in nfsd4_release_lockowner() is nonsense and
harmful.  Revert to using check_for_locks(), changing that to not sleep.

First: harmful.
As is documented in the kdoc comment for nfsd4_release_lockowner(), the
test on so_count can transiently return a false positive resulting in a
return of NFS4ERR_LOCKS_HELD when in fact no locks are held.  This is
clearly a protocol violation and with the Linux NFS client it can cause
incorrect behaviour.

If RELEASE_LOCKOWNER is sent while some other thread is still
processing a LOCK request which failed because, at the time that request
was received, the given owner held a conflicting lock, then the nfsd
thread processing that LOCK request can hold a reference (conflock) to
the lock owner that causes nfsd4_release_lockowner() to return an
incorrect error.

The Linux NFS client ignores that NFS4ERR_LOCKS_HELD error because it
never sends NFS4_RELEASE_LOCKOWNER without first releasing any locks, so
it knows that the error is impossible.  It assumes the lock owner was in
fact released so it feels free to use the same lock owner identifier in
some later locking request.

When it does reuse a lock owner identifier for which a previous RELEASE
failed, it will naturally use a lock_seqid of zero.  However the server,
which didn't release the lock owner, will expect a larger lock_seqid and
so will respond with NFS4ERR_BAD_SEQID.

So clearly it is harmful to allow a false positive, which testing
so_count allows.

The test is nonsense because ... well... it doesn't mean anything.

so_count is the sum of three different counts.
1/ the set of states listed on so_stateids
2/ the set of active vfs locks owned by any of those states
3/ various transient counts such as for conflicting locks.

When it is tested against '2' it is clear that one of these is the
transient reference obtained by find_lockowner_str_locked().  It is not
clear what the other one is expected to be.

In practice, the count is often 2 because there is precisely one state
on so_stateids.  If there were more, this would fail.

In my testing I see two circumstances when RELEASE_LOCKOWNER is called.
In one case, CLOSE is called before RELEASE_LOCKOWNER.  That results in
all the lock states being removed, and so the lockowner being discarded
(it is removed when there are no more references which usually happens
when the lock state is discarded).  When nfsd4_release_lockowner() finds
that the lock owner doesn't exist, it returns success.

The other case shows an so_count of '2' and precisely one state listed
in so_stateid.  It appears that the Linux client uses a separate lock
owner for each file resulting in one lock state per lock owner, so this
test on '2' is safe.  For another client it might not be safe.

So this patch changes check_for_locks() to use the (newish)
find_any_file_locked() so that it doesn't take a reference on the
nfs4_file and so never calls nfsd_file_put(), and so never sleeps.  With
this check is it safe to restore the use of check_for_locks() rather
than testing so_count against the mysterious '2'.

Fixes: ce3c4ad7f4ce ("NFSD: Fix possible sleep during nfsd4_release_lockowner()")
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@vger.kernel.org # v6.2+
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2fa54cfd48823..6dc6340e28529 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -7911,14 +7911,16 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 {
 	struct file_lock *fl;
 	int status = false;
-	struct nfsd_file *nf = find_any_file(fp);
+	struct nfsd_file *nf;
 	struct inode *inode;
 	struct file_lock_context *flctx;
 
+	spin_lock(&fp->fi_lock);
+	nf = find_any_file_locked(fp);
 	if (!nf) {
 		/* Any valid lock stateid should have some sort of access */
 		WARN_ON_ONCE(1);
-		return status;
+		goto out;
 	}
 
 	inode = file_inode(nf->nf_file);
@@ -7934,7 +7936,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 		}
 		spin_unlock(&flctx->flc_lock);
 	}
-	nfsd_file_put(nf);
+out:
+	spin_unlock(&fp->fi_lock);
 	return status;
 }
 
@@ -7944,10 +7947,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
  * @cstate: NFSv4 COMPOUND state
  * @u: RELEASE_LOCKOWNER arguments
  *
- * The lockowner's so_count is bumped when a lock record is added
- * or when copying a conflicting lock. The latter case is brief,
- * but can lead to fleeting false positives when looking for
- * locks-in-use.
+ * Check if theree are any locks still held and if not - free the lockowner
+ * and any lock state that is owned.
  *
  * Return values:
  *   %nfs_ok: lockowner released or not found
@@ -7983,10 +7984,13 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		spin_unlock(&clp->cl_lock);
 		return nfs_ok;
 	}
-	if (atomic_read(&lo->lo_owner.so_count) != 2) {
-		spin_unlock(&clp->cl_lock);
-		nfs4_put_stateowner(&lo->lo_owner);
-		return nfserr_locks_held;
+
+	list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) {
+		if (check_for_locks(stp->st_stid.sc_file, lo)) {
+			spin_unlock(&clp->cl_lock);
+			nfs4_put_stateowner(&lo->lo_owner);
+			return nfserr_locks_held;
+		}
 	}
 	unhash_lockowner_locked(lo);
 	while (!list_empty(&lo->lo_owner.so_stateids)) {
-- 
GitLab


From 2f8c7c3715f2c6fb51a4ecc0905c04dd78a3da29 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Wed, 24 Jan 2024 13:24:24 +0000
Subject: [PATCH 3346/4076] spi: Raise limit on number of chip selects

As reported by Guenter the limit we've got on the number of chip selects is
set too low for some systems, raise the limit. We should really remove the
hard coded limit but this is needed as a fix so let's do the simple thing
and raise the limit for now.

Fixes: 4d8ff6b0991d ("spi: Add multi-cs memories support in SPI core")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Suggested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/r/20240124-spi-multi-cs-max-v2-1-df6fc5ab1abc@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 471fe2ff9066b..600fbd5daf683 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -21,7 +21,7 @@
 #include <uapi/linux/spi/spi.h>
 
 /* Max no. of CS supported per spi device */
-#define SPI_CS_CNT_MAX 4
+#define SPI_CS_CNT_MAX 16
 
 struct dma_chan;
 struct software_node;
-- 
GitLab


From 92b0b0ff0ba32e7b3f1e789cc96df1359db712ef Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Tue, 23 Jan 2024 14:13:40 -0800
Subject: [PATCH 3347/4076] nvme: add module description to stop warnings

Add MODULE_DESCRIPTION() in order to remove warnings & get clean build:-

WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/host/nvme-core.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/host/nvme.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/host/nvme-fabrics.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/host/nvme-rdma.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/host/nvme-fc.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/host/nvme-tcp.o

Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c    | 1 +
 drivers/nvme/host/fabrics.c | 1 +
 drivers/nvme/host/fc.c      | 1 +
 drivers/nvme/host/pci.c     | 1 +
 drivers/nvme/host/rdma.c    | 1 +
 drivers/nvme/host/tcp.c     | 1 +
 6 files changed, 6 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 85ab0fcf9e886..0810be0d1154c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4851,5 +4851,6 @@ static void __exit nvme_core_exit(void)
 
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0");
+MODULE_DESCRIPTION("NVMe host core framework");
 module_init(nvme_core_init);
 module_exit(nvme_core_exit);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index b5752a77ad989..373ed08e6b920 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -1488,6 +1488,7 @@ static void __exit nvmf_exit(void)
 }
 
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("NVMe host fabrics library");
 
 module_init(nvmf_init);
 module_exit(nvmf_exit);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 16847a316421f..e2308119f8f0b 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -4004,4 +4004,5 @@ static void __exit nvme_fc_exit_module(void)
 module_init(nvme_fc_init_module);
 module_exit(nvme_fc_exit_module);
 
+MODULE_DESCRIPTION("NVMe host FC transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c1d6357ec98a0..25eb727795417 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3543,5 +3543,6 @@ static void __exit nvme_exit(void)
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0");
+MODULE_DESCRIPTION("NVMe host PCIe transport driver");
 module_init(nvme_init);
 module_exit(nvme_exit);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 11dde0d830442..0f48ead986ec5 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -2400,4 +2400,5 @@ static void __exit nvme_rdma_cleanup_module(void)
 module_init(nvme_rdma_init_module);
 module_exit(nvme_rdma_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe host RDMA transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d058d990532bf..4393cf244025e 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2826,4 +2826,5 @@ static void __exit nvme_tcp_cleanup_module(void)
 module_init(nvme_tcp_init_module);
 module_exit(nvme_tcp_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe host TCP transport driver");
 MODULE_LICENSE("GPL v2");
-- 
GitLab


From 41951f83ef9044e906e11f5ea7db35a30dc9f581 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Tue, 23 Jan 2024 14:13:41 -0800
Subject: [PATCH 3348/4076] nvmet: add module description to stop warnings

Add MODULE_DESCRIPTION() in order to remove warnings & get clean build:-

WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/target/nvmet.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/target/nvme-loop.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/target/nvmet-rdma.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/target/nvmet-fc.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/target/nvme-fcloop.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/target/nvmet-tcp.o

Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/core.c   | 1 +
 drivers/nvme/target/fc.c     | 1 +
 drivers/nvme/target/fcloop.c | 1 +
 drivers/nvme/target/loop.c   | 1 +
 drivers/nvme/target/rdma.c   | 1 +
 drivers/nvme/target/tcp.c    | 1 +
 6 files changed, 6 insertions(+)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index fa35e65915f0c..8658e9c08534d 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1705,4 +1705,5 @@ static void __exit nvmet_exit(void)
 module_init(nvmet_init);
 module_exit(nvmet_exit);
 
+MODULE_DESCRIPTION("NVMe target core framework");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index bda7a3009e851..05e6a755b3306 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -2945,4 +2945,5 @@ static void __exit nvmet_fc_exit_module(void)
 module_init(nvmet_fc_init_module);
 module_exit(nvmet_fc_exit_module);
 
+MODULE_DESCRIPTION("NVMe target FC transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index ead349af30f1e..c1faeb1e9e556 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -1650,4 +1650,5 @@ static void __exit fcloop_exit(void)
 module_init(fcloop_init);
 module_exit(fcloop_exit);
 
+MODULE_DESCRIPTION("NVMe target FC loop transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 9cb434c580751..2b2e0d00af85e 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -688,5 +688,6 @@ static void __exit nvme_loop_cleanup_module(void)
 module_init(nvme_loop_init_module);
 module_exit(nvme_loop_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe target loop transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-254"); /* 254 == NVMF_TRTYPE_LOOP */
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 667f9c04f35d5..3a0f2c170f4c1 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -2104,5 +2104,6 @@ static void __exit nvmet_rdma_exit(void)
 module_init(nvmet_rdma_init);
 module_exit(nvmet_rdma_exit);
 
+MODULE_DESCRIPTION("NVMe target RDMA transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-1"); /* 1 == NVMF_TRTYPE_RDMA */
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 6a1e6bb80062d..da0469978d6f4 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -2221,5 +2221,6 @@ static void __exit nvmet_tcp_exit(void)
 module_init(nvmet_tcp_init);
 module_exit(nvmet_tcp_exit);
 
+MODULE_DESCRIPTION("NVMe target TCP transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-3"); /* 3 == NVMF_TRTYPE_TCP */
-- 
GitLab


From 7822baa844a87cbb93308c1032c3d47d4079bb8a Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Wed, 24 Jan 2024 15:15:24 +0000
Subject: [PATCH 3349/4076] ALSA: usb-audio: add quirk for RODE NT-USB+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The RODE NT-USB+ is marketed as a professional usb microphone, however the
usb audio interface is a mess:

[    1.130977] usb 1-5: new full-speed USB device number 2 using xhci_hcd
[    1.503906] usb 1-5: config 1 has an invalid interface number: 5 but max is 4
[    1.503912] usb 1-5: config 1 has no interface number 4
[    1.519689] usb 1-5: New USB device found, idVendor=19f7, idProduct=0035, bcdDevice= 1.09
[    1.519695] usb 1-5: New USB device strings: Mfr=1, Product=2, SerialNumber=3
[    1.519697] usb 1-5: Product: RØDE NT-USB+
[    1.519699] usb 1-5: Manufacturer: RØDE
[    1.519700] usb 1-5: SerialNumber: 1D773A1A
[    8.327495] usb 1-5: 1:1: cannot get freq at ep 0x82
[    8.344500] usb 1-5: 1:2: cannot get freq at ep 0x82
[    8.365499] usb 1-5: 2:1: cannot get freq at ep 0x2

Add QUIRK_FLAG_GET_SAMPLE_RATE to work around the broken sample rate get.
I have asked Rode support to fix it, but they show no interest.

Signed-off-by: Sean Young <sean@mess.org>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240124151524.23314-1-sean@mess.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index be0ce1fc4f26c..591c3a3546962 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2183,6 +2183,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_FIXED_RATE),
 	DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 
 	/* Vendor matches */
 	VENDOR_FLG(0x045e, /* MS Lifecam */
-- 
GitLab


From 15ade5bfa5abf0e02249239db91d5438fa796d18 Mon Sep 17 00:00:00 2001
From: Israel Rukshin <israelr@nvidia.com>
Date: Wed, 24 Jan 2024 12:16:27 +0000
Subject: [PATCH 3350/4076] nvme-rdma: Fix transfer length when
 write_generate/read_verify are 0

When the block layer doesn't generate/verify metadata, the SG length is
smaller than the transfer length. This is because the SG length doesn't
include the metadata length that is added by the HW on the wire. The
target failes those commands with "Data SGL Length Invalid" by comparing
the transfer length and the SG length. Fix it by adding the metadata
length to the transfer length when there is no metadata SGL. The bug
reproduces when setting read_verify/write_generate configs to 0 at the
child multipath device or at the primary device when NVMe multipath is
disabled.

Note that setting those configs to 0 on the multipath device (ns_head)
doesn't have any impact on the I/Os.

Fixes: 5ec5d3bddc6b ("nvme-rdma: add metadata/T10-PI support")
Signed-off-by: Israel Rukshin <israelr@nvidia.com>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/rdma.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 0f48ead986ec5..3f393ee202811 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1410,6 +1410,8 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	struct nvme_ns *ns = rq->q->queuedata;
 	struct bio *bio = rq->bio;
 	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	u32 xfer_len;
 	int nr;
 
 	req->mr = ib_mr_pool_get(queue->qp, &queue->qp->sig_mrs);
@@ -1422,8 +1424,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	if (unlikely(nr))
 		goto mr_put;
 
-	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c,
-				req->mr->sig_attrs, ns->head->pi_type);
+	nvme_rdma_set_sig_attrs(bi, c, req->mr->sig_attrs, ns->head->pi_type);
 	nvme_rdma_set_prot_checks(c, &req->mr->sig_attrs->check_mask);
 
 	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
@@ -1441,7 +1442,11 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 		     IB_ACCESS_REMOTE_WRITE;
 
 	sg->addr = cpu_to_le64(req->mr->iova);
-	put_unaligned_le24(req->mr->length, sg->length);
+	xfer_len = req->mr->length;
+	/* Check if PI is added by the HW */
+	if (!pi_count)
+		xfer_len += (xfer_len >> bi->interval_exp) * ns->head->pi_size;
+	put_unaligned_le24(xfer_len, sg->length);
 	put_unaligned_le32(req->mr->rkey, sg->key);
 	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
 
-- 
GitLab


From e169bd4fb2b36c4b2bee63c35c740c85daeb2e86 Mon Sep 17 00:00:00 2001
From: Maksim Kiselev <bigunclemax@gmail.com>
Date: Wed, 24 Jan 2024 10:24:36 +0300
Subject: [PATCH 3351/4076] aoe: avoid potential deadlock at set_capacity

Move set_capacity() outside of the section procected by (&d->lock).
To avoid possible interrupt unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
[1] lock(&bdev->bd_size_lock);
                                local_irq_disable();
                            [2] lock(&d->lock);
                            [3] lock(&bdev->bd_size_lock);
   <Interrupt>
[4]  lock(&d->lock);

  *** DEADLOCK ***

Where [1](&bdev->bd_size_lock) hold by zram_add()->set_capacity().
[2]lock(&d->lock) hold by aoeblk_gdalloc(). And aoeblk_gdalloc()
is trying to acquire [3](&bdev->bd_size_lock) at set_capacity() call.
In this situation an attempt to acquire [4]lock(&d->lock) from
aoecmd_cfg_rsp() will lead to deadlock.

So the simplest solution is breaking lock dependency
[2](&d->lock) -> [3](&bdev->bd_size_lock) by moving set_capacity()
outside.

Signed-off-by: Maksim Kiselev <bigunclemax@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240124072436.3745720-2-bigunclemax@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/aoe/aoeblk.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index d2dbf8aaccb5b..b1b47d88f5db4 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -333,6 +333,7 @@ aoeblk_gdalloc(void *vp)
 	struct gendisk *gd;
 	mempool_t *mp;
 	struct blk_mq_tag_set *set;
+	sector_t ssize;
 	ulong flags;
 	int late = 0;
 	int err;
@@ -396,7 +397,7 @@ aoeblk_gdalloc(void *vp)
 	gd->minors = AOE_PARTITIONS;
 	gd->fops = &aoe_bdops;
 	gd->private_data = d;
-	set_capacity(gd, d->ssize);
+	ssize = d->ssize;
 	snprintf(gd->disk_name, sizeof gd->disk_name, "etherd/e%ld.%d",
 		d->aoemajor, d->aoeminor);
 
@@ -405,6 +406,8 @@ aoeblk_gdalloc(void *vp)
 
 	spin_unlock_irqrestore(&d->lock, flags);
 
+	set_capacity(gd, ssize);
+
 	err = device_add_disk(NULL, gd, aoe_attr_groups);
 	if (err)
 		goto out_disk_cleanup;
-- 
GitLab


From 668abe6dc7b61941fa5c724c06797efb0b87f070 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 24 Jan 2024 16:53:07 +0100
Subject: [PATCH 3352/4076] ALSA: usb-audio: Sort quirk table entries

The quirk table entries should be put in the USB ID order, but some
entries have been put in random places.  Re-sort them.

Fixes: bf990c102319 ("ALSA: usb-audio: add quirk to fix Hamedal C20 disconnect issue")
Fixes: fd28941cff1c ("ALSA: usb-audio: Add new quirk FIXED_RATE for JBL Quantum810 Wireless")
Fixes: dfd5fe19db7d ("ALSA: usb-audio: Add FIXED_RATE quirk for JBL Quantum610 Wireless")
Fixes: 4a63e68a2951 ("ALSA: usb-audio: Fix microphone sound on Nexigo webcam.")
Fixes: 7822baa844a8 ("ALSA: usb-audio: add quirk for RODE NT-USB+")
Fixes: 4fb7c24f69c4 ("ALSA: usb-audio: Add quirk for Fiero SC-01")
Fixes: 2307a0e1ca0b ("ALSA: usb-audio: Add quirk for Fiero SC-01 (fw v1.0.0)")
Link: https://lore.kernel.org/r/20240124155307.16996-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 591c3a3546962..09712e61c606e 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2037,6 +2037,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x04e8, 0xa051, /* Samsung USBC Headset (AKG) */
 		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR | QUIRK_FLAG_CTL_MSG_DELAY_5M),
+	DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */
+		   QUIRK_FLAG_IFACE_SKIP_CLOSE),
 	DEVICE_FLG(0x054c, 0x0b8c, /* Sony WALKMAN NW-A45 DAC */
 		   QUIRK_FLAG_SET_IFACE_FIRST),
 	DEVICE_FLG(0x0556, 0x0014, /* Phoenix Audio TMX320VC */
@@ -2083,8 +2085,14 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x0b0e, 0x0349, /* Jabra 550a */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
+	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
+		   QUIRK_FLAG_FIXED_RATE),
+	DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
+		   QUIRK_FLAG_FIXED_RATE),
 	DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1397, 0x0507, /* Behringer UMC202HD */
@@ -2117,6 +2125,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY),
 	DEVICE_FLG(0x1901, 0x0191, /* GE B850V3 CP2114 audio interface */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x2040, 0x7200, /* Hauppauge HVR-950Q */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x2040, 0x7201, /* Hauppauge HVR-950Q-MXL */
@@ -2159,6 +2171,12 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
@@ -2167,24 +2185,6 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x534d, 0x2109, /* MacroSilicon MS2109 */
 		   QUIRK_FLAG_ALIGN_TRANSFER),
-	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
-		   QUIRK_FLAG_GET_SAMPLE_RATE),
-	DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */
-		   QUIRK_FLAG_IFACE_SKIP_CLOSE),
-	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
-		   QUIRK_FLAG_FIXED_RATE),
-	DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
-		   QUIRK_FLAG_FIXED_RATE),
-	DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
-		   QUIRK_FLAG_GET_SAMPLE_RATE),
-	DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */
-		   QUIRK_FLAG_GET_SAMPLE_RATE),
 
 	/* Vendor matches */
 	VENDOR_FLG(0x045e, /* MS Lifecam */
-- 
GitLab


From d1b163aa0749706379055e40a52cf7a851abf9dc Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 23 Jan 2024 13:09:26 +0100
Subject: [PATCH 3353/4076] Revert "drivers/firmware: Move sysfb_init() from
 device_initcall to subsys_initcall_sync"

This reverts commit 60aebc9559492cea6a9625f514a8041717e3a2e4.

Commit 60aebc9559492cea ("drivers/firmware: Move sysfb_init() from
device_initcall to subsys_initcall_sync") messes up initialization order
of the graphics drivers and leads to blank displays on some systems. So
revert the commit.

To make the display drivers fully independent from initialization
order requires to track framebuffer memory by device and independently
from the loaded drivers. The kernel currently lacks the infrastructure
to do so.

Reported-by: Jaak Ristioja <jaak@ristioja.ee>
Closes: https://lore.kernel.org/dri-devel/ZUnNi3q3yB3zZfTl@P70.localdomain/T/#t
Reported-by: Huacai Chen <chenhuacai@loongson.cn>
Closes: https://lore.kernel.org/dri-devel/20231108024613.2898921-1-chenhuacai@loongson.cn/
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/10133
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Thorsten Leemhuis <regressions@leemhuis.info>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: stable@vger.kernel.org # v6.5+
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240123120937.27736-1-tzimmermann@suse.de
---
 drivers/firmware/sysfb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
index 82fcfd29bc4d2..3c197db42c9d9 100644
--- a/drivers/firmware/sysfb.c
+++ b/drivers/firmware/sysfb.c
@@ -128,4 +128,4 @@ unlock_mutex:
 }
 
 /* must execute after PCI subsystem for EFI quirks */
-subsys_initcall_sync(sysfb_init);
+device_initcall(sysfb_init);
-- 
GitLab


From 520d9708979349dcf6e044eac51efc43788b5cec Mon Sep 17 00:00:00 2001
From: Brandon Brnich <b-brnich@ti.com>
Date: Mon, 11 Dec 2023 14:59:19 -0600
Subject: [PATCH 3354/4076] dt-bindings: media: Remove K3 Family Prefix from
 Compatible

K3 family prefix is not included in other TI compatible strings. Remove
this prefix to keep naming convention consistent.

Fixes: de4b9f7e371a ("dt-bindings: media: wave5: add yaml devicetree bindings")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Closes: https://lore.kernel.org/all/CAMuHMdUYOq=q1j=d+Eac28hthOUAaNUkuvxmRu-mUN1pLKq69g@mail.gmail.com/
Signed-off-by: Brandon Brnich <b-brnich@ti.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 Documentation/devicetree/bindings/media/cnm,wave521c.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/cnm,wave521c.yaml b/Documentation/devicetree/bindings/media/cnm,wave521c.yaml
index 6d5569e77b7a1..6a11c1d11fb5f 100644
--- a/Documentation/devicetree/bindings/media/cnm,wave521c.yaml
+++ b/Documentation/devicetree/bindings/media/cnm,wave521c.yaml
@@ -17,7 +17,7 @@ properties:
   compatible:
     items:
       - enum:
-          - ti,k3-j721s2-wave521c
+          - ti,j721s2-wave521c
       - const: cnm,wave521c
 
   reg:
@@ -53,7 +53,7 @@ additionalProperties: false
 examples:
   - |
     vpu: video-codec@12345678 {
-        compatible = "ti,k3-j721s2-wave521c", "cnm,wave521c";
+        compatible = "ti,j721s2-wave521c", "cnm,wave521c";
         reg = <0x12345678 0x1000>;
         clocks = <&clks 42>;
         interrupts = <42>;
-- 
GitLab


From c14d17a32568679385d32fe7a23994560c12772c Mon Sep 17 00:00:00 2001
From: Brandon Brnich <b-brnich@ti.com>
Date: Mon, 11 Dec 2023 14:59:20 -0600
Subject: [PATCH 3355/4076] media: chips-media: wave5: Remove K3 References

Change compatible string to match dt bindings for TI devices. K3 family
prefix should not be included as it deviates from naming convention.

Fixes: 9707a6254a8a ("media: chips-media: wave5: Add the v4l2 layer")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Closes: https://lore.kernel.org/all/CAMuHMdUYOq=q1j=d+Eac28hthOUAaNUkuvxmRu-mUN1pLKq69g@mail.gmail.com/
Signed-off-by: Brandon Brnich <b-brnich@ti.com>
Reviewed-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 drivers/media/platform/chips-media/wave5/wave5-vpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu.c b/drivers/media/platform/chips-media/wave5/wave5-vpu.c
index bfe4caa79cc98..0d90b5820bef7 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu.c
@@ -272,7 +272,7 @@ static const struct wave5_match_data ti_wave521c_data = {
 };
 
 static const struct of_device_id wave5_dt_ids[] = {
-	{ .compatible = "ti,k3-j721s2-wave521c", .data = &ti_wave521c_data },
+	{ .compatible = "ti,j721s2-wave521c", .data = &ti_wave521c_data },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, wave5_dt_ids);
-- 
GitLab


From 78e23c3e914a5e678a20286fb09bc218017af89a Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Date: Thu, 18 Jan 2024 13:14:52 +0100
Subject: [PATCH 3356/4076] media: media videobuf2: Stop direct calls to queue
 num_buffers field

Use vb2_get_num_buffers() to avoid using queue num_buffers field directly.
This allows us to change how the number of buffers is computed in the
future.

Fixes: d055a76c0065 ("media: core: Report the maximum possible number of buffers for the queue")
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Acked-by: Tomasz Figa <tfiga@chromium.org>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 drivers/media/common/videobuf2/videobuf2-core.c | 2 +-
 drivers/media/common/videobuf2/videobuf2-v4l2.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index 41a832dd1426b..b6bf8f232f488 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -989,7 +989,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 	bool no_previous_buffers = !q_num_bufs;
 	int ret = 0;
 
-	if (q->num_buffers == q->max_num_buffers) {
+	if (q_num_bufs == q->max_num_buffers) {
 		dprintk(q, 1, "maximum number of buffers already allocated\n");
 		return -ENOBUFS;
 	}
diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index 54d572c3b515d..6380155d8575f 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -1029,7 +1029,7 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv,
 	int res = vb2_verify_memory_type(vdev->queue, p->memory,
 			p->format.type);
 
-	p->index = vdev->queue->num_buffers;
+	p->index = vb2_get_num_buffers(vdev->queue);
 	fill_buf_caps(vdev->queue, &p->capabilities);
 	validate_memory_flags(vdev->queue, p->memory, &p->flags);
 	/*
-- 
GitLab


From b32431b753217d8d45b018443b1a7aac215921fb Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Date: Fri, 19 Jan 2024 10:03:23 +0100
Subject: [PATCH 3357/4076] media: vb2: refactor setting flags and caps, fix
 missing cap

Several functions implementing VIDIOC_REQBUFS and _CREATE_BUFS all use
almost the same code to fill in the flags and capability fields. Refactor
this into a new vb2_set_flags_and_caps() function that replaces the old
fill_buf_caps() and validate_memory_flags() functions.

This also fixes a bug where vb2_ioctl_create_bufs() would not set the
V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS cap and also not fill in the
max_num_buffers field.

Fixes: d055a76c0065 ("media: core: Report the maximum possible number of buffers for the queue")
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Reviewed-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Acked-by: Tomasz Figa <tfiga@chromium.org>
---
 .../media/common/videobuf2/videobuf2-v4l2.c   | 53 +++++++++----------
 1 file changed, 25 insertions(+), 28 deletions(-)

diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index 6380155d8575f..c575198e83547 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -671,8 +671,20 @@ int vb2_querybuf(struct vb2_queue *q, struct v4l2_buffer *b)
 }
 EXPORT_SYMBOL(vb2_querybuf);
 
-static void fill_buf_caps(struct vb2_queue *q, u32 *caps)
+static void vb2_set_flags_and_caps(struct vb2_queue *q, u32 memory,
+				   u32 *flags, u32 *caps, u32 *max_num_bufs)
 {
+	if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP) {
+		/*
+		 * This needs to clear V4L2_MEMORY_FLAG_NON_COHERENT only,
+		 * but in order to avoid bugs we zero out all bits.
+		 */
+		*flags = 0;
+	} else {
+		/* Clear all unknown flags. */
+		*flags &= V4L2_MEMORY_FLAG_NON_COHERENT;
+	}
+
 	*caps = V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS;
 	if (q->io_modes & VB2_MMAP)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_MMAP;
@@ -686,21 +698,9 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS;
 	if (q->supports_requests)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_REQUESTS;
-}
-
-static void validate_memory_flags(struct vb2_queue *q,
-				  int memory,
-				  u32 *flags)
-{
-	if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP) {
-		/*
-		 * This needs to clear V4L2_MEMORY_FLAG_NON_COHERENT only,
-		 * but in order to avoid bugs we zero out all bits.
-		 */
-		*flags = 0;
-	} else {
-		/* Clear all unknown flags. */
-		*flags &= V4L2_MEMORY_FLAG_NON_COHERENT;
+	if (max_num_bufs) {
+		*max_num_bufs = q->max_num_buffers;
+		*caps |= V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS;
 	}
 }
 
@@ -709,8 +709,8 @@ int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 	int ret = vb2_verify_memory_type(q, req->memory, req->type);
 	u32 flags = req->flags;
 
-	fill_buf_caps(q, &req->capabilities);
-	validate_memory_flags(q, req->memory, &flags);
+	vb2_set_flags_and_caps(q, req->memory, &flags,
+			       &req->capabilities, NULL);
 	req->flags = flags;
 	return ret ? ret : vb2_core_reqbufs(q, req->memory,
 					    req->flags, &req->count);
@@ -751,11 +751,9 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create)
 	int ret = vb2_verify_memory_type(q, create->memory, f->type);
 	unsigned i;
 
-	fill_buf_caps(q, &create->capabilities);
-	validate_memory_flags(q, create->memory, &create->flags);
 	create->index = vb2_get_num_buffers(q);
-	create->max_num_buffers = q->max_num_buffers;
-	create->capabilities |= V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS;
+	vb2_set_flags_and_caps(q, create->memory, &create->flags,
+			       &create->capabilities, &create->max_num_buffers);
 	if (create->count == 0)
 		return ret != -EBUSY ? ret : 0;
 
@@ -1006,8 +1004,8 @@ int vb2_ioctl_reqbufs(struct file *file, void *priv,
 	int res = vb2_verify_memory_type(vdev->queue, p->memory, p->type);
 	u32 flags = p->flags;
 
-	fill_buf_caps(vdev->queue, &p->capabilities);
-	validate_memory_flags(vdev->queue, p->memory, &flags);
+	vb2_set_flags_and_caps(vdev->queue, p->memory, &flags,
+			       &p->capabilities, NULL);
 	p->flags = flags;
 	if (res)
 		return res;
@@ -1026,12 +1024,11 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv,
 			  struct v4l2_create_buffers *p)
 {
 	struct video_device *vdev = video_devdata(file);
-	int res = vb2_verify_memory_type(vdev->queue, p->memory,
-			p->format.type);
+	int res = vb2_verify_memory_type(vdev->queue, p->memory, p->format.type);
 
 	p->index = vb2_get_num_buffers(vdev->queue);
-	fill_buf_caps(vdev->queue, &p->capabilities);
-	validate_memory_flags(vdev->queue, p->memory, &p->flags);
+	vb2_set_flags_and_caps(vdev->queue, p->memory, &p->flags,
+			       &p->capabilities, &p->max_num_buffers);
 	/*
 	 * If count == 0, then just check if memory and type are valid.
 	 * Any -EBUSY result from vb2_verify_memory_type can be mapped to 0.
-- 
GitLab


From e787644caf7628ad3269c1fbd321c3255cf51710 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 19 Dec 2023 00:19:15 +0100
Subject: [PATCH 3358/4076] rcu: Defer RCU kthreads wakeup when CPU is dying

When the CPU goes idle for the last time during the CPU down hotplug
process, RCU reports a final quiescent state for the current CPU. If
this quiescent state propagates up to the top, some tasks may then be
woken up to complete the grace period: the main grace period kthread
and/or the expedited main workqueue (or kworker).

If those kthreads have a SCHED_FIFO policy, the wake up can indirectly
arm the RT bandwith timer to the local offline CPU. Since this happens
after hrtimers have been migrated at CPUHP_AP_HRTIMERS_DYING stage, the
timer gets ignored. Therefore if the RCU kthreads are waiting for RT
bandwidth to be available, they may never be actually scheduled.

This triggers TREE03 rcutorture hangs:

	 rcu: INFO: rcu_preempt self-detected stall on CPU
	 rcu:     4-...!: (1 GPs behind) idle=9874/1/0x4000000000000000 softirq=0/0 fqs=20 rcuc=21071 jiffies(starved)
	 rcu:     (t=21035 jiffies g=938281 q=40787 ncpus=6)
	 rcu: rcu_preempt kthread starved for 20964 jiffies! g938281 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x0 ->cpu=0
	 rcu:     Unless rcu_preempt kthread gets sufficient CPU time, OOM is now expected behavior.
	 rcu: RCU grace-period kthread stack dump:
	 task:rcu_preempt     state:R  running task     stack:14896 pid:14    tgid:14    ppid:2      flags:0x00004000
	 Call Trace:
	  <TASK>
	  __schedule+0x2eb/0xa80
	  schedule+0x1f/0x90
	  schedule_timeout+0x163/0x270
	  ? __pfx_process_timeout+0x10/0x10
	  rcu_gp_fqs_loop+0x37c/0x5b0
	  ? __pfx_rcu_gp_kthread+0x10/0x10
	  rcu_gp_kthread+0x17c/0x200
	  kthread+0xde/0x110
	  ? __pfx_kthread+0x10/0x10
	  ret_from_fork+0x2b/0x40
	  ? __pfx_kthread+0x10/0x10
	  ret_from_fork_asm+0x1b/0x30
	  </TASK>

The situation can't be solved with just unpinning the timer. The hrtimer
infrastructure and the nohz heuristics involved in finding the best
remote target for an unpinned timer would then also need to handle
enqueues from an offline CPU in the most horrendous way.

So fix this on the RCU side instead and defer the wake up to an online
CPU if it's too late for the local one.

Reported-by: Paul E. McKenney <paulmck@kernel.org>
Fixes: 5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier")
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 kernel/rcu/tree.c     | 34 +++++++++++++++++++++++++++++++++-
 kernel/rcu/tree_exp.h |  3 +--
 2 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1ae8517778066..b2bccfd37c383 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1013,6 +1013,38 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
 	return needmore;
 }
 
+static void swake_up_one_online_ipi(void *arg)
+{
+	struct swait_queue_head *wqh = arg;
+
+	swake_up_one(wqh);
+}
+
+static void swake_up_one_online(struct swait_queue_head *wqh)
+{
+	int cpu = get_cpu();
+
+	/*
+	 * If called from rcutree_report_cpu_starting(), wake up
+	 * is dangerous that late in the CPU-down hotplug process. The
+	 * scheduler might queue an ignored hrtimer. Defer the wake up
+	 * to an online CPU instead.
+	 */
+	if (unlikely(cpu_is_offline(cpu))) {
+		int target;
+
+		target = cpumask_any_and(housekeeping_cpumask(HK_TYPE_RCU),
+					 cpu_online_mask);
+
+		smp_call_function_single(target, swake_up_one_online_ipi,
+					 wqh, 0);
+		put_cpu();
+	} else {
+		put_cpu();
+		swake_up_one(wqh);
+	}
+}
+
 /*
  * Awaken the grace-period kthread.  Don't do a self-awaken (unless in an
  * interrupt or softirq handler, in which case we just might immediately
@@ -1037,7 +1069,7 @@ static void rcu_gp_kthread_wake(void)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
 	WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
-	swake_up_one(&rcu_state.gp_wq);
+	swake_up_one_online(&rcu_state.gp_wq);
 }
 
 /*
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 6d7cea5d591f9..2ac440bc7e10b 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -173,7 +173,6 @@ static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp)
 	return ret;
 }
 
-
 /*
  * Report the exit from RCU read-side critical section for the last task
  * that queued itself during or before the current expedited preemptible-RCU
@@ -201,7 +200,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				swake_up_one(&rcu_state.expedited_wq);
+				swake_up_one_online(&rcu_state.expedited_wq);
 			}
 			break;
 		}
-- 
GitLab


From f9f4b0c6425eb9ffd9bf62b8b8143e786b6ba695 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Wed, 24 Jan 2024 17:41:01 +0000
Subject: [PATCH 3359/4076] spi: cs42l43: Handle error from
 devm_pm_runtime_enable

As it devm_pm_runtime_enable can fail due to memory allocations, it is
best to handle the error.

Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://msgid.link/r/20240124174101.2270249-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cs42l43.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c
index f13073e125936..b24190526ce96 100644
--- a/drivers/spi/spi-cs42l43.c
+++ b/drivers/spi/spi-cs42l43.c
@@ -244,7 +244,10 @@ static int cs42l43_spi_probe(struct platform_device *pdev)
 	priv->ctlr->use_gpio_descriptors = true;
 	priv->ctlr->auto_runtime_pm = true;
 
-	devm_pm_runtime_enable(priv->dev);
+	ret = devm_pm_runtime_enable(priv->dev);
+	if (ret)
+		return ret;
+
 	pm_runtime_idle(priv->dev);
 
 	regmap_write(priv->regmap, CS42L43_TRAN_CONFIG6, CS42L43_FIFO_SIZE - 1);
-- 
GitLab


From b253d87fd78bf8d3e7efc5d149147765f044e89d Mon Sep 17 00:00:00 2001
From: George Guo <guodongtai@kylinos.cn>
Date: Tue, 26 Dec 2023 17:42:42 +0800
Subject: [PATCH 3360/4076] netfilter: nf_tables: cleanup documentation

- Correct comments for nlpid, family, udlen and udata in struct nft_table,
  and afinfo is no longer a member of enum nft_set_class.

- Add comment for data in struct nft_set_elem.

- Add comment for flags in struct nft_ctx.

- Add comments for timeout in struct nft_set_iter, and flags is not a
  member of struct nft_set_iter, remove the comment for it.

- Add comments for commit, abort, estimate and gc_init in struct
  nft_set_ops.

- Add comments for pending_update, num_exprs, exprs and catchall_list
  in struct nft_set.

- Add comment for ext_len in struct nft_set_ext_tmpl.

- Add comment for inner_ops in struct nft_expr_type.

- Add comments for clone, destroy_clone, reduce, gc, offload,
  offload_action, offload_stats in struct nft_expr_ops.

- Add comments for blob_gen_0, blob_gen_1, bound, genmask, udlen, udata,
  blob_next in struct nft_chain.

- Add comment for flags in struct nft_base_chain.

- Add comments for udlen, udata in struct nft_object.

- Add comment for type in struct nft_object_ops.

- Add comment for hook_list in struct nft_flowtable, and remove comments
  for dev_name and ops which are not members of struct nft_flowtable.

Signed-off-by: George Guo <guodongtai@kylinos.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 49 ++++++++++++++++++++++++-------
 1 file changed, 39 insertions(+), 10 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index b157c5cafd14c..4e1ea18eb5f05 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -205,6 +205,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
  *	@nla: netlink attributes
  *	@portid: netlink portID of the original message
  *	@seq: netlink sequence number
+ *	@flags: modifiers to new request
  *	@family: protocol family
  *	@level: depth of the chains
  *	@report: notify via unicast netlink message
@@ -282,6 +283,7 @@ struct nft_elem_priv { };
  *
  *	@key: element key
  *	@key_end: closing element key
+ *	@data: element data
  *	@priv: element private data and extensions
  */
 struct nft_set_elem {
@@ -325,10 +327,10 @@ struct nft_set_iter {
  *	@dtype: data type
  *	@dlen: data length
  *	@objtype: object type
- *	@flags: flags
  *	@size: number of set elements
  *	@policy: set policy
  *	@gc_int: garbage collector interval
+ *	@timeout: element timeout
  *	@field_len: length of each field in concatenation, bytes
  *	@field_count: number of concatenated fields in element
  *	@expr: set must support for expressions
@@ -351,9 +353,9 @@ struct nft_set_desc {
 /**
  *	enum nft_set_class - performance class
  *
- *	@NFT_LOOKUP_O_1: constant, O(1)
- *	@NFT_LOOKUP_O_LOG_N: logarithmic, O(log N)
- *	@NFT_LOOKUP_O_N: linear, O(N)
+ *	@NFT_SET_CLASS_O_1: constant, O(1)
+ *	@NFT_SET_CLASS_O_LOG_N: logarithmic, O(log N)
+ *	@NFT_SET_CLASS_O_N: linear, O(N)
  */
 enum nft_set_class {
 	NFT_SET_CLASS_O_1,
@@ -422,9 +424,13 @@ struct nft_set_ext;
  *	@remove: remove element from set
  *	@walk: iterate over all set elements
  *	@get: get set elements
+ *	@commit: commit set elements
+ *	@abort: abort set elements
  *	@privsize: function to return size of set private data
+ *	@estimate: estimate the required memory size and the lookup complexity class
  *	@init: initialize private data of new set instance
  *	@destroy: destroy private data of set instance
+ *	@gc_init: initialize garbage collection
  *	@elemsize: element private size
  *
  *	Operations lookup, update and delete have simpler interfaces, are faster
@@ -540,13 +546,16 @@ struct nft_set_elem_expr {
  *	@policy: set parameterization (see enum nft_set_policies)
  *	@udlen: user data length
  *	@udata: user data
- *	@expr: stateful expression
+ *	@pending_update: list of pending update set element
  * 	@ops: set ops
  * 	@flags: set flags
  *	@dead: set will be freed, never cleared
  *	@genmask: generation mask
  * 	@klen: key length
  * 	@dlen: data length
+ *	@num_exprs: numbers of exprs
+ *	@exprs: stateful expression
+ *	@catchall_list: list of catch-all set element
  * 	@data: private set data
  */
 struct nft_set {
@@ -692,6 +701,7 @@ extern const struct nft_set_ext_type nft_set_ext_types[];
  *
  *	@len: length of extension area
  *	@offset: offsets of individual extension types
+ *	@ext_len: length of the expected extension(used to sanity check)
  */
 struct nft_set_ext_tmpl {
 	u16	len;
@@ -840,6 +850,7 @@ struct nft_expr_ops;
  *	@select_ops: function to select nft_expr_ops
  *	@release_ops: release nft_expr_ops
  *	@ops: default ops, used when no select_ops functions is present
+ *	@inner_ops: inner ops, used for inner packet operation
  *	@list: used internally
  *	@name: Identifier
  *	@owner: module reference
@@ -881,14 +892,22 @@ struct nft_offload_ctx;
  *	struct nft_expr_ops - nf_tables expression operations
  *
  *	@eval: Expression evaluation function
+ *	@clone: Expression clone function
  *	@size: full expression size, including private data size
  *	@init: initialization function
  *	@activate: activate expression in the next generation
  *	@deactivate: deactivate expression in next generation
  *	@destroy: destruction function, called after synchronize_rcu
+ *	@destroy_clone: destruction clone function
  *	@dump: function to dump parameters
- *	@type: expression type
  *	@validate: validate expression, called during loop detection
+ *	@reduce: reduce expression
+ *	@gc: garbage collection expression
+ *	@offload: hardware offload expression
+ *	@offload_action: function to report true/false to allocate one slot or not in the flow
+ *			 offload array
+ *	@offload_stats: function to synchronize hardware stats via updating the counter expression
+ *	@type: expression type
  *	@data: extra data to attach to this expression operation
  */
 struct nft_expr_ops {
@@ -1041,14 +1060,21 @@ struct nft_rule_blob {
 /**
  *	struct nft_chain - nf_tables chain
  *
+ *	@blob_gen_0: rule blob pointer to the current generation
+ *	@blob_gen_1: rule blob pointer to the future generation
  *	@rules: list of rules in the chain
  *	@list: used internally
  *	@rhlhead: used internally
  *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@use: number of jump references to this chain
- *	@flags: bitmask of enum nft_chain_flags
+ *	@flags: bitmask of enum NFTA_CHAIN_FLAGS
+ *	@bound: bind or not
+ *	@genmask: generation mask
  *	@name: name of the chain
+ *	@udlen: user data length
+ *	@udata: user data in the chain
+ *	@blob_next: rule blob pointer to the next in the chain
  */
 struct nft_chain {
 	struct nft_rule_blob		__rcu *blob_gen_0;
@@ -1146,6 +1172,7 @@ struct nft_hook {
  *	@hook_list: list of netfilter hooks (for NFPROTO_NETDEV family)
  *	@type: chain type
  *	@policy: default policy
+ *	@flags: indicate the base chain disabled or not
  *	@stats: per-cpu chain stats
  *	@chain: the chain
  *	@flow_block: flow block (for hardware offload)
@@ -1274,11 +1301,13 @@ struct nft_object_hash_key {
  *	struct nft_object - nf_tables stateful object
  *
  *	@list: table stateful object list node
- *	@key:  keys that identify this object
  *	@rhlhead: nft_objname_ht node
+ *	@key: keys that identify this object
  *	@genmask: generation mask
  *	@use: number of references to this stateful object
  *	@handle: unique object handle
+ *	@udlen: length of user data
+ *	@udata: user data
  *	@ops: object operations
  *	@data: object data, layout depends on type
  */
@@ -1344,6 +1373,7 @@ struct nft_object_type {
  *	@destroy: release existing stateful object
  *	@dump: netlink dump stateful object
  *	@update: update stateful object
+ *	@type: pointer to object type
  */
 struct nft_object_ops {
 	void				(*eval)(struct nft_object *obj,
@@ -1379,9 +1409,8 @@ void nft_unregister_obj(struct nft_object_type *obj_type);
  *	@genmask: generation mask
  *	@use: number of references to this flow table
  * 	@handle: unique object handle
- *	@dev_name: array of device names
+ *	@hook_list: hook list for hooks per net_device in flowtables
  *	@data: rhashtable and garbage collector
- * 	@ops: array of hooks
  */
 struct nft_flowtable {
 	struct list_head		list;
-- 
GitLab


From 01acb2e8666a6529697141a6017edbf206921913 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 18 Jan 2024 10:56:26 +0100
Subject: [PATCH 3361/4076] netfilter: nft_chain_filter: handle
 NETDEV_UNREGISTER for inet/ingress basechain

Remove netdevice from inet/ingress basechain in case NETDEV_UNREGISTER
event is reported, otherwise a stale reference to netdevice remains in
the hook list.

Fixes: 60a3815da702 ("netfilter: add inet ingress support")
Cc: stable@vger.kernel.org
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_chain_filter.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 680fe557686e4..274b6f7e6bb57 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -357,9 +357,10 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 				  unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct nft_base_chain *basechain;
 	struct nftables_pernet *nft_net;
-	struct nft_table *table;
 	struct nft_chain *chain, *nr;
+	struct nft_table *table;
 	struct nft_ctx ctx = {
 		.net	= dev_net(dev),
 	};
@@ -371,7 +372,8 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 	nft_net = nft_pernet(ctx.net);
 	mutex_lock(&nft_net->commit_mutex);
 	list_for_each_entry(table, &nft_net->tables, list) {
-		if (table->family != NFPROTO_NETDEV)
+		if (table->family != NFPROTO_NETDEV &&
+		    table->family != NFPROTO_INET)
 			continue;
 
 		ctx.family = table->family;
@@ -380,6 +382,11 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 			if (!nft_is_base_chain(chain))
 				continue;
 
+			basechain = nft_base_chain(chain);
+			if (table->family == NFPROTO_INET &&
+			    basechain->ops.hooknum != NF_INET_INGRESS)
+				continue;
+
 			ctx.chain = chain;
 			nft_netdev_event(event, dev, &ctx);
 		}
-- 
GitLab


From c9d9eb9c53d37cdebbad56b91e40baf42d5a97aa Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 19 Jan 2024 13:11:32 +0100
Subject: [PATCH 3362/4076] netfilter: nft_limit: reject configurations that
 cause integer overflow

Reject bogus configs where internal token counter wraps around.
This only occurs with very very large requests, such as 17gbyte/s.

Its better to reject this rather than having incorrect ratelimit.

Fixes: d2168e849ebf ("netfilter: nft_limit: add per-byte limiting")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_limit.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index 79039afde34ec..cefa25e0dbb0a 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -58,17 +58,19 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost)
 static int nft_limit_init(struct nft_limit_priv *priv,
 			  const struct nlattr * const tb[], bool pkts)
 {
+	u64 unit, tokens, rate_with_burst;
 	bool invert = false;
-	u64 unit, tokens;
 
 	if (tb[NFTA_LIMIT_RATE] == NULL ||
 	    tb[NFTA_LIMIT_UNIT] == NULL)
 		return -EINVAL;
 
 	priv->rate = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE]));
+	if (priv->rate == 0)
+		return -EINVAL;
+
 	unit = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT]));
-	priv->nsecs = unit * NSEC_PER_SEC;
-	if (priv->rate == 0 || priv->nsecs < unit)
+	if (check_mul_overflow(unit, NSEC_PER_SEC, &priv->nsecs))
 		return -EOVERFLOW;
 
 	if (tb[NFTA_LIMIT_BURST])
@@ -77,18 +79,25 @@ static int nft_limit_init(struct nft_limit_priv *priv,
 	if (pkts && priv->burst == 0)
 		priv->burst = NFT_LIMIT_PKT_BURST_DEFAULT;
 
-	if (priv->rate + priv->burst < priv->rate)
+	if (check_add_overflow(priv->rate, priv->burst, &rate_with_burst))
 		return -EOVERFLOW;
 
 	if (pkts) {
-		tokens = div64_u64(priv->nsecs, priv->rate) * priv->burst;
+		u64 tmp = div64_u64(priv->nsecs, priv->rate);
+
+		if (check_mul_overflow(tmp, priv->burst, &tokens))
+			return -EOVERFLOW;
 	} else {
+		u64 tmp;
+
 		/* The token bucket size limits the number of tokens can be
 		 * accumulated. tokens_max specifies the bucket size.
 		 * tokens_max = unit * (rate + burst) / rate.
 		 */
-		tokens = div64_u64(priv->nsecs * (priv->rate + priv->burst),
-				 priv->rate);
+		if (check_mul_overflow(priv->nsecs, rate_with_burst, &tmp))
+			return -EOVERFLOW;
+
+		tokens = div64_u64(tmp, priv->rate);
 	}
 
 	if (tb[NFTA_LIMIT_FLAGS]) {
-- 
GitLab


From b462579b2b86a8f5230543cadd3a4836be27baf7 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 19 Jan 2024 13:34:32 +0100
Subject: [PATCH 3363/4076] netfilter: nf_tables: restrict anonymous set and
 map names to 16 bytes

nftables has two types of sets/maps, one where userspace defines the
name, and anonymous sets/maps, where userspace defines a template name.

For the latter, kernel requires presence of exactly one "%d".
nftables uses "__set%d" and "__map%d" for this.  The kernel will
expand the format specifier and replaces it with the smallest unused
number.

As-is, userspace could define a template name that allows to move
the set name past the 256 bytes upperlimit (post-expansion).

I don't see how this could be a problem, but I would prefer if userspace
cannot do this, so add a limit of 16 bytes for the '%d' template name.

16 bytes is the old total upper limit for set names that existed when
nf_tables was merged initially.

Fixes: 387454901bd6 ("netfilter: nf_tables: Allow set names of up to 255 chars")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4b55533ce5ca2..02f45424644b4 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -24,6 +24,7 @@
 #include <net/sock.h>
 
 #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-"))
+#define NFT_SET_MAX_ANONLEN 16
 
 unsigned int nf_tables_net_id __read_mostly;
 
@@ -4413,6 +4414,9 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 		if (p[1] != 'd' || strchr(p + 2, '%'))
 			return -EINVAL;
 
+		if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN)
+			return -EINVAL;
+
 		inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL);
 		if (inuse == NULL)
 			return -ENOMEM;
-- 
GitLab


From f342de4e2f33e0e39165d8639387aa6c19dff660 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sat, 20 Jan 2024 22:50:04 +0100
Subject: [PATCH 3364/4076] netfilter: nf_tables: reject QUEUE/DROP verdict
 parameters

This reverts commit e0abdadcc6e1.

core.c:nf_hook_slow assumes that the upper 16 bits of NF_DROP
verdicts contain a valid errno, i.e. -EPERM, -EHOSTUNREACH or similar,
or 0.

Due to the reverted commit, its possible to provide a positive
value, e.g. NF_ACCEPT (1), which results in use-after-free.

Its not clear to me why this commit was made.

NF_QUEUE is not used by nftables; "queue" rules in nftables
will result in use of "nft_queue" expression.

If we later need to allow specifiying errno values from userspace
(do not know why), this has to call NF_DROP_GETERR and check that
"err <= 0" holds true.

Fixes: e0abdadcc6e1 ("netfilter: nf_tables: accept QUEUE/DROP verdict parameters")
Cc: stable@vger.kernel.org
Reported-by: Notselwyn <notselwyn@pwning.tech>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 02f45424644b4..c537104411e7d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -10992,16 +10992,10 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
 
 	switch (data->verdict.code) {
-	default:
-		switch (data->verdict.code & NF_VERDICT_MASK) {
-		case NF_ACCEPT:
-		case NF_DROP:
-		case NF_QUEUE:
-			break;
-		default:
-			return -EINVAL;
-		}
-		fallthrough;
+	case NF_ACCEPT:
+	case NF_DROP:
+	case NF_QUEUE:
+		break;
 	case NFT_CONTINUE:
 	case NFT_BREAK:
 	case NFT_RETURN:
@@ -11036,6 +11030,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 
 		data->verdict.chain = chain;
 		break;
+	default:
+		return -EINVAL;
 	}
 
 	desc->len = sizeof(data->verdict);
-- 
GitLab


From d0009effa8862c20a13af4cb7475d9771b905693 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 23 Jan 2024 16:38:25 +0100
Subject: [PATCH 3365/4076] netfilter: nf_tables: validate NFPROTO_* family

Several expressions explicitly refer to NF_INET_* hook definitions
from expr->ops->validate, however, family is not validated.

Bail out with EOPNOTSUPP in case they are used from unsupported
families.

Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
Fixes: a3c90f7a2323 ("netfilter: nf_tables: flow offload expression")
Fixes: 2fa841938c64 ("netfilter: nf_tables: introduce routing expression")
Fixes: 554ced0a6e29 ("netfilter: nf_tables: add support for native socket matching")
Fixes: ad49d86e07a4 ("netfilter: nf_tables: Add synproxy support")
Fixes: 4ed8eb6570a4 ("netfilter: nf_tables: Add native tproxy support")
Fixes: 6c47260250fc ("netfilter: nf_tables: add xfrm expression")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_compat.c       | 12 ++++++++++++
 net/netfilter/nft_flow_offload.c |  5 +++++
 net/netfilter/nft_nat.c          |  5 +++++
 net/netfilter/nft_rt.c           |  5 +++++
 net/netfilter/nft_socket.c       |  5 +++++
 net/netfilter/nft_synproxy.c     |  7 +++++--
 net/netfilter/nft_tproxy.c       |  5 +++++
 net/netfilter/nft_xfrm.c         |  5 +++++
 8 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 5284cd2ad5327..f0eeda97bfcd9 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -350,6 +350,12 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 	unsigned int hook_mask = 0;
 	int ret;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_BRIDGE &&
+	    ctx->family != NFPROTO_ARP)
+		return -EOPNOTSUPP;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
@@ -595,6 +601,12 @@ static int nft_match_validate(const struct nft_ctx *ctx,
 	unsigned int hook_mask = 0;
 	int ret;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_BRIDGE &&
+	    ctx->family != NFPROTO_ARP)
+		return -EOPNOTSUPP;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index ab3362c483b4a..397351fa4d5f8 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -384,6 +384,11 @@ static int nft_flow_offload_validate(const struct nft_ctx *ctx,
 {
 	unsigned int hook_mask = (1 << NF_INET_FORWARD);
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, hook_mask);
 }
 
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 583885ce72328..808f5802c2704 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -143,6 +143,11 @@ static int nft_nat_validate(const struct nft_ctx *ctx,
 	struct nft_nat *priv = nft_expr_priv(expr);
 	int err;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c
index 35a2c28caa60b..24d9771385729 100644
--- a/net/netfilter/nft_rt.c
+++ b/net/netfilter/nft_rt.c
@@ -166,6 +166,11 @@ static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *exp
 	const struct nft_rt *priv = nft_expr_priv(expr);
 	unsigned int hooks;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	switch (priv->key) {
 	case NFT_RT_NEXTHOP4:
 	case NFT_RT_NEXTHOP6:
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 9ed85be79452d..f30163e2ca620 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -242,6 +242,11 @@ static int nft_socket_validate(const struct nft_ctx *ctx,
 			       const struct nft_expr *expr,
 			       const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain,
 					(1 << NF_INET_PRE_ROUTING) |
 					(1 << NF_INET_LOCAL_IN) |
diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c
index 13da882669a4e..1d737f89dfc18 100644
--- a/net/netfilter/nft_synproxy.c
+++ b/net/netfilter/nft_synproxy.c
@@ -186,7 +186,6 @@ static int nft_synproxy_do_init(const struct nft_ctx *ctx,
 		break;
 #endif
 	case NFPROTO_INET:
-	case NFPROTO_BRIDGE:
 		err = nf_synproxy_ipv4_init(snet, ctx->net);
 		if (err)
 			goto nf_ct_failure;
@@ -219,7 +218,6 @@ static void nft_synproxy_do_destroy(const struct nft_ctx *ctx)
 		break;
 #endif
 	case NFPROTO_INET:
-	case NFPROTO_BRIDGE:
 		nf_synproxy_ipv4_fini(snet, ctx->net);
 		nf_synproxy_ipv6_fini(snet, ctx->net);
 		break;
@@ -253,6 +251,11 @@ static int nft_synproxy_validate(const struct nft_ctx *ctx,
 				 const struct nft_expr *expr,
 				 const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) |
 						    (1 << NF_INET_FORWARD));
 }
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index ae15cd693f0ec..71412adb73d41 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -316,6 +316,11 @@ static int nft_tproxy_validate(const struct nft_ctx *ctx,
 			       const struct nft_expr *expr,
 			       const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING);
 }
 
diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c
index 452f8587addad..1c866757db552 100644
--- a/net/netfilter/nft_xfrm.c
+++ b/net/netfilter/nft_xfrm.c
@@ -235,6 +235,11 @@ static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *e
 	const struct nft_xfrm *priv = nft_expr_priv(expr);
 	unsigned int hooks;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	switch (priv->dir) {
 	case XFRM_POLICY_IN:
 		hooks = (1 << NF_INET_FORWARD) |
-- 
GitLab


From 4759ff71f23e1a9cba001009abab68cde6dc327a Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 24 Jan 2024 11:22:32 -0800
Subject: [PATCH 3366/4076] exec: Check __FMODE_EXEC instead of in_execve for
 LSMs

After commit 978ffcbf00d8 ("execve: open the executable file before
doing anything else"), current->in_execve was no longer in sync with the
open(). This broke AppArmor and TOMOYO which depend on this flag to
distinguish "open" operations from being "exec" operations.

Instead of moving around in_execve, switch to using __FMODE_EXEC, which
is where the "is this an exec?" intent is stored. Note that TOMOYO still
uses in_execve around cred handling.

Reported-by: Kevin Locke <kevin@kevinlocke.name>
Closes: https://lore.kernel.org/all/ZbE4qn9_h14OqADK@kevinlocke.name
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Fixes: 978ffcbf00d8 ("execve: open the executable file before doing anything else")
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: John Johansen <john.johansen@canonical.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: James Morris <jmorris@namei.org>
Cc: Serge E. Hallyn <serge@hallyn.com>
Cc: Kentaro Takeda <takedakn@nttdata.co.jp>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc:  <linux-fsdevel@vger.kernel.org>
Cc:  <linux-mm@kvack.org>
Cc:  <apparmor@lists.ubuntu.com>
Cc:  <linux-security-module@vger.kernel.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 security/apparmor/lsm.c  | 4 +++-
 security/tomoyo/tomoyo.c | 3 ++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 7717354ce0950..98e1150bee9d0 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -469,8 +469,10 @@ static int apparmor_file_open(struct file *file)
 	 * Cache permissions granted by the previous exec check, with
 	 * implicit read and executable mmap which are required to
 	 * actually execute the image.
+	 *
+	 * Illogically, FMODE_EXEC is in f_flags, not f_mode.
 	 */
-	if (current->in_execve) {
+	if (file->f_flags & __FMODE_EXEC) {
 		fctx->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP;
 		return 0;
 	}
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index 3c3af149bf1c1..04a92c3d65d44 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -328,7 +328,8 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
 static int tomoyo_file_open(struct file *f)
 {
 	/* Don't check read permission here if called from execve(). */
-	if (current->in_execve)
+	/* Illogically, FMODE_EXEC is in f_flags, not f_mode. */
+	if (f->f_flags & __FMODE_EXEC)
 		return 0;
 	return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path,
 					    f->f_flags);
-- 
GitLab


From 90383cc07895183c75a0db2460301c2ffd912359 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 24 Jan 2024 11:15:33 -0800
Subject: [PATCH 3367/4076] exec: Distinguish in_execve from in_exec

Just to help distinguish the fs->in_exec flag from the current->in_execve
flag, add comments in check_unsafe_exec() and copy_fs() for more
context. Also note that in_execve is only used by TOMOYO now.

Cc: Kentaro Takeda <takedakn@nttdata.co.jp>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-mm@kvack.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/exec.c             | 1 +
 include/linux/sched.h | 2 +-
 kernel/fork.c         | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/exec.c b/fs/exec.c
index 39d773021fffd..d179abb78a1c8 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1633,6 +1633,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	}
 	rcu_read_unlock();
 
+	/* "users" and "in_exec" locked for copy_fs() */
 	if (p->fs->users > n_fs)
 		bprm->unsafe |= LSM_UNSAFE_SHARE;
 	else
diff --git a/include/linux/sched.h b/include/linux/sched.h
index cdb8ea53c365b..ffe8f618ab869 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -920,7 +920,7 @@ struct task_struct {
 	unsigned			sched_rt_mutex:1;
 #endif
 
-	/* Bit to tell LSMs we're in execve(): */
+	/* Bit to tell TOMOYO we're in execve(): */
 	unsigned			in_execve:1;
 	unsigned			in_iowait:1;
 #ifndef TIF_RESTORE_SIGMASK
diff --git a/kernel/fork.c b/kernel/fork.c
index 47ff3b35352e0..0d944e92a43ff 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1748,6 +1748,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
 		spin_lock(&fs->lock);
+		/* "users" and "in_exec" locked for check_unsafe_exec() */
 		if (fs->in_exec) {
 			spin_unlock(&fs->lock);
 			return -EAGAIN;
-- 
GitLab


From 443b349019f2d9461b23213a4308f9cf72e41c5e Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 24 Jan 2024 11:52:40 -0800
Subject: [PATCH 3368/4076] samples/cgroup: add .gitignore file for generated
 samples

Make 'git status' quietly happy again after a full allmodconfig build.

Fixes: 60433a9d038d ("samples: introduce new samples subdir for cgroup")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 samples/cgroup/.gitignore | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 samples/cgroup/.gitignore

diff --git a/samples/cgroup/.gitignore b/samples/cgroup/.gitignore
new file mode 100644
index 0000000000000..3a0161194ccec
--- /dev/null
+++ b/samples/cgroup/.gitignore
@@ -0,0 +1,3 @@
+/cgroup_event_listener
+/memcg_event_listener
+
-- 
GitLab


From a5f5eee282a0aae80227697e1d9c811b1726d31d Mon Sep 17 00:00:00 2001
From: Bernd Edlinger <bernd.edlinger@hotmail.de>
Date: Mon, 22 Jan 2024 19:19:09 +0100
Subject: [PATCH 3369/4076] net: stmmac: Wait a bit for the reset to take
 effect

otherwise the synopsys_id value may be read out wrong,
because the GMAC_VERSION register might still be in reset
state, for at least 1 us after the reset is de-asserted.

Add a wait for 10 us before continuing to be on the safe side.

> From what have you got that delay value?

Just try and error, with very old linux versions and old gcc versions
the synopsys_id was read out correctly most of the time (but not always),
with recent linux versions and recnet gcc versions it was read out
wrongly most of the time, but again not always.
I don't have access to the VHDL code in question, so I cannot
tell why it takes so long to get the correct values, I also do not
have more than a few hardware samples, so I cannot tell how long
this timeout must be in worst case.
Experimentally I can tell that the register is read several times
as zero immediately after the reset is de-asserted, also adding several
no-ops is not enough, adding a printk is enough, also udelay(1) seems to
be enough but I tried that not very often, and I have not access to many
hardware samples to be 100% sure about the necessary delay.
And since the udelay here is only executed once per device instance,
it seems acceptable to delay the boot for 10 us.

BTW: my hardware's synopsys id is 0x37.

Fixes: c5e4ddbdfa11 ("net: stmmac: Add support for optional reset control")
Signed-off-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/AS8P193MB1285A810BD78C111E7F6AA34E4752@AS8P193MB1285.EURP193.PROD.OUTLOOK.COM
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a0e46369ae158..b334eb16da23a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7542,6 +7542,9 @@ int stmmac_dvr_probe(struct device *device,
 		dev_err(priv->device, "unable to bring out of ahb reset: %pe\n",
 			ERR_PTR(ret));
 
+	/* Wait a bit for the reset to take effect */
+	udelay(10);
+
 	/* Init MAC and get the capabilities */
 	ret = stmmac_hw_init(priv);
 	if (ret)
-- 
GitLab


From 9f538b415db862e74b8c5d3abbccfc1b2b6caa38 Mon Sep 17 00:00:00 2001
From: Jenishkumar Maheshbhai Patel <jpatel2@marvell.com>
Date: Thu, 18 Jan 2024 19:59:14 -0800
Subject: [PATCH 3370/4076] net: mvpp2: clear BM pool before initialization

Register value persist after booting the kernel using
kexec which results in kernel panic. Thus clear the
BM pool registers before initialisation to fix the issue.

Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: Jenishkumar Maheshbhai Patel <jpatel2@marvell.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://lore.kernel.org/r/20240119035914.2595665-1-jpatel2@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c   | 27 ++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 820b1fabe297a..23adf53c2aa1c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -614,12 +614,38 @@ static void mvpp23_bm_set_8pool_mode(struct mvpp2 *priv)
 	mvpp2_write(priv, MVPP22_BM_POOL_BASE_ADDR_HIGH_REG, val);
 }
 
+/* Cleanup pool before actual initialization in the OS */
+static void mvpp2_bm_pool_cleanup(struct mvpp2 *priv, int pool_id)
+{
+	unsigned int thread = mvpp2_cpu_to_thread(priv, get_cpu());
+	u32 val;
+	int i;
+
+	/* Drain the BM from all possible residues left by firmware */
+	for (i = 0; i < MVPP2_BM_POOL_SIZE_MAX; i++)
+		mvpp2_thread_read(priv, thread, MVPP2_BM_PHY_ALLOC_REG(pool_id));
+
+	put_cpu();
+
+	/* Stop the BM pool */
+	val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(pool_id));
+	val |= MVPP2_BM_STOP_MASK;
+	mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(pool_id), val);
+}
+
 static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv)
 {
 	enum dma_data_direction dma_dir = DMA_FROM_DEVICE;
 	int i, err, poolnum = MVPP2_BM_POOLS_NUM;
 	struct mvpp2_port *port;
 
+	if (priv->percpu_pools)
+		poolnum = mvpp2_get_nrxqs(priv) * 2;
+
+	/* Clean up the pool state in case it contains stale state */
+	for (i = 0; i < poolnum; i++)
+		mvpp2_bm_pool_cleanup(priv, i);
+
 	if (priv->percpu_pools) {
 		for (i = 0; i < priv->port_count; i++) {
 			port = priv->port_list[i];
@@ -629,7 +655,6 @@ static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv)
 			}
 		}
 
-		poolnum = mvpp2_get_nrxqs(priv) * 2;
 		for (i = 0; i < poolnum; i++) {
 			/* the pool in use */
 			int pn = i / (poolnum / 2);
-- 
GitLab


From 1ed4b563100230ea68821a2b25a3d9f25388a3e6 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.ibm.com>
Date: Wed, 24 Jan 2024 14:21:44 -0500
Subject: [PATCH 3371/4076] Revert "KEYS: encrypted: Add check for strsep"

This reverts commit b4af096b5df5dd131ab796c79cedc7069d8f4882.

New encrypted keys are created either from kernel-generated random
numbers or user-provided decrypted data.  Revert the change requiring
user-provided decrypted data.

Reported-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 security/keys/encrypted-keys/encrypted.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 76f55dd13cb80..8af2136069d23 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -237,10 +237,6 @@ static int datablob_parse(char *datablob, const char **format,
 			break;
 		}
 		*decrypted_data = strsep(&datablob, " \t");
-		if (!*decrypted_data) {
-			pr_info("encrypted_key: decrypted_data is missing\n");
-			break;
-		}
 		ret = 0;
 		break;
 	case Opt_load:
-- 
GitLab


From 3eab830189d94f0f80f34cbff609b5bb54002679 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 24 Jan 2024 13:12:20 -0800
Subject: [PATCH 3372/4076] uselib: remove use of __FMODE_EXEC

Jann Horn points out that uselib() really shouldn't trigger the new
FMODE_EXEC logic introduced by commit 4759ff71f23e ("exec: __FMODE_EXEC
instead of in_execve for LSMs").

In fact, it shouldn't even have ever triggered the old pre-existing
logic for __FMODE_EXEC (like the NFS code that makes executables not
need read permissions).  Unlike a real execve(), that can work even with
files that are purely executable by the user (not readable), uselib()
has that MAY_READ requirement becasue it's really just a convenience
wrapper around mmap() for legacy shared libraries.

The whole FMODE_EXEC bit was originally introduced by commit
b500531e6f5f ("[PATCH] Introduce FMODE_EXEC file flag"), primarily to
give ETXTBUSY error returns for distributed filesystems.

It has since grown a few other warts (like that NFS thing), but there
really isn't any reason to use it for uselib(), and now that we are
trying to use it to replace the horrid 'tsk->in_execve' flag, it's
actively wrong.

Of course, as Jann Horn also points out, nobody should be enabling
CONFIG_USELIB in the first place in this day and age, but that's a
different discussion entirely.

Reported-by: Jann Horn <jannh@google.com>
Fixes: 4759ff71f23e ("exec: __FMODE_EXEC instead of in_execve for LSMs")
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/exec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/exec.c b/fs/exec.c
index 8cdd5b2dd09c2..1a097c1c2f774 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -128,7 +128,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	struct filename *tmp = getname(library);
 	int error = PTR_ERR(tmp);
 	static const struct open_flags uselib_flags = {
-		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.open_flag = O_LARGEFILE | O_RDONLY,
 		.acc_mode = MAY_READ | MAY_EXEC,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
-- 
GitLab


From 1793ce9f205efe07ca2992ef129b86dab2c329f5 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 30 Dec 2023 22:08:23 -0800
Subject: [PATCH 3373/4076] drm/msm/dpu: fix kernel-doc warnings

Correct all kernel-doc warnings in dpu_encoder.c and dpu_rm.c:

dpu_encoder.c:212: warning: Excess struct member 'crtc_kickoff_cb' description in 'dpu_encoder_virt'
dpu_encoder.c:212: warning: Excess struct member 'crtc_kickoff_cb_data' description in 'dpu_encoder_virt'
dpu_encoder.c:212: warning: Excess struct member 'debugfs_root' description in 'dpu_encoder_virt'

dpu_rm.c:35: warning: Excess struct member 'hw_res' description in 'dpu_rm_requirements'
dpu_rm.c:208: warning: No description found for return value of '_dpu_rm_get_lm_peer'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Abhinav Kumar <quic_abhinavk@quicinc.com>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Sean Paul <sean@poorly.run>
Cc: Marijn Suijten <marijn.suijten@somainline.org>
Cc: linux-arm-msm@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: freedreno@lists.freedesktop.org
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Reviewed-by: Paloma Arellano <quic_parellan@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312170641.5exlvQQx-lkp@intel.com/
Fixes: 62d35629da80 ("drm/msm/dpu: move encoder status to standard encoder debugfs dir")
Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support")
Patchwork: https://patchwork.freedesktop.org/patch/572962/
Link: https://lore.kernel.org/r/20231231060823.1934-1-rdunlap@infradead.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 4 ----
 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c      | 3 ++-
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 83380bc92a00a..f2b82ca5efb39 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -144,10 +144,6 @@ enum dpu_enc_rc_states {
  *			to track crtc in the disable() hook which is called
  *			_after_ encoder_mask is cleared.
  * @connector:		If a mode is set, cached pointer to the active connector
- * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
- *				all CTL paths
- * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
- * @debugfs_root:		Debug file system root file node
  * @enc_lock:			Lock around physical encoder
  *				create/destroy/enable/disable
  * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index b58a9c2ae326c..724537ab776df 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -29,7 +29,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx,
 /**
  * struct dpu_rm_requirements - Reservation requirements parameter bundle
  * @topology:  selected topology for the display
- * @hw_res:	   Hardware resources required as reported by the encoders
  */
 struct dpu_rm_requirements {
 	struct msm_display_topology topology;
@@ -204,6 +203,8 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
  * _dpu_rm_get_lm_peer - get the id of a mixer which is a peer of the primary
  * @rm: dpu resource manager handle
  * @primary_idx: index of primary mixer in rm->mixer_blks[]
+ *
+ * Returns: lm peer mixed id on success or %-EINVAL on error
  */
 static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx)
 {
-- 
GitLab


From 0719b5338a0cbe80d1637a5fb03d8141b5bfc7a1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 22 Jan 2024 11:58:15 -0800
Subject: [PATCH 3374/4076] selftests: net: fix rps_default_mask with >32 CPUs

If there is more than 32 cpus the bitmask will start to contain
commas, leading to:

./rps_default_mask.sh: line 36: [: 00000000,00000000: integer expression expected

Remove the commas, bash doesn't interpret leading zeroes as oct
so that should be good enough. Switch to bash, Simon reports that
not all shells support this type of substitution.

Fixes: c12e0d5f267d ("self-tests: introduce self-tests for RPS default mask")
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240122195815.638997-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/rps_default_mask.sh | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh
index a26c5624429fb..4287a85298907 100755
--- a/tools/testing/selftests/net/rps_default_mask.sh
+++ b/tools/testing/selftests/net/rps_default_mask.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 readonly ksft_skip=4
@@ -33,6 +33,10 @@ chk_rps() {
 
 	rps_mask=$($cmd /sys/class/net/$dev_name/queues/rx-0/rps_cpus)
 	printf "%-60s" "$msg"
+
+	# In case there is more than 32 CPUs we need to remove commas from masks
+	rps_mask=${rps_mask//,}
+	expected_rps_mask=${expected_rps_mask//,}
 	if [ $rps_mask -eq $expected_rps_mask ]; then
 		echo "[ ok ]"
 	else
-- 
GitLab


From 77e8aad5519e04f6c1e132aaec1c5f8faf41844f Mon Sep 17 00:00:00 2001
From: Kuogee Hsieh <quic_khsieh@quicinc.com>
Date: Wed, 10 Jan 2024 12:18:51 -0800
Subject: [PATCH 3375/4076] drm/msms/dp: fixed link clock divider bits be over
 written in BPC unknown case

Since the value of DP_TEST_BIT_DEPTH_8 is already left shifted, in the
BPC unknown case, the additional shift causes spill over to the other
bits of the [DP_CONFIGURATION_CTRL] register.
Fix this by changing the return value of dp_link_get_test_bits_depth()
in the BPC unknown case to (DP_TEST_BIT_DEPTH_8 >> DP_TEST_BIT_DEPTH_SHIFT).

Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support")
Signed-off-by: Kuogee Hsieh <quic_khsieh@quicinc.com>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/573989/
Link: https://lore.kernel.org/r/1704917931-30133-1-git-send-email-quic_khsieh@quicinc.com
[quic_abhinavk@quicinc.com: fix minor checkpatch warning to align with opening braces]
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dp/dp_ctrl.c |  5 -----
 drivers/gpu/drm/msm/dp/dp_link.c | 10 +++++++---
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 77a8d9366ed7b..fb588fde298a2 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
 	tbd = dp_link_get_test_bits_depth(ctrl->link,
 			ctrl->panel->dp_mode.bpp);
 
-	if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) {
-		pr_debug("BIT_DEPTH not set. Configure default\n");
-		tbd = DP_TEST_BIT_DEPTH_8;
-	}
-
 	config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT;
 
 	/* Num of Lanes */
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 98427d45e9a7e..a0015b9e79eb7 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -1179,6 +1179,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link)
 u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 {
 	u32 tbd;
+	struct dp_link_private *link;
+
+	link = container_of(dp_link, struct dp_link_private, dp_link);
 
 	/*
 	 * Few simplistic rules and assumptions made here:
@@ -1196,12 +1199,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 		tbd = DP_TEST_BIT_DEPTH_10;
 		break;
 	default:
-		tbd = DP_TEST_BIT_DEPTH_UNKNOWN;
+		drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n",
+			   bpp);
+		tbd = DP_TEST_BIT_DEPTH_8;
 		break;
 	}
 
-	if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN)
-		tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
+	tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
 
 	return tbd;
 }
-- 
GitLab


From fcccdafd91f8bdde568b86ff70848cf83f029add Mon Sep 17 00:00:00 2001
From: Kuogee Hsieh <quic_khsieh@quicinc.com>
Date: Wed, 17 Jan 2024 13:13:30 -0800
Subject: [PATCH 3376/4076] drm/msm/dp: return correct Colorimetry for
 DP_TEST_DYNAMIC_RANGE_CEA case

MSA MISC0 bit 1 to 7 contains Colorimetry Indicator Field.
dp_link_get_colorimetry_config() returns wrong colorimetry value
in the DP_TEST_DYNAMIC_RANGE_CEA case in the current implementation.
Hence fix this problem by having dp_link_get_colorimetry_config()
return defined CEA RGB colorimetry value in the case of
DP_TEST_DYNAMIC_RANGE_CEA.

Changes in V2:
-- drop retrieving colorimetry from colorspace
-- drop dr = link->dp_link.test_video.test_dyn_range assignment

Changes in V3:
-- move defined MISCr0a Colorimetry vale to dp_reg.h
-- rewording commit title
-- rewording commit text to more precise describe this patch

Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support")
Signed-off-by: Kuogee Hsieh <quic_khsieh@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/574888/
Link: https://lore.kernel.org/r/1705526010-597-1-git-send-email-quic_khsieh@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dp/dp_link.c | 12 +++++++-----
 drivers/gpu/drm/msm/dp/dp_reg.h  |  3 +++
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index a0015b9e79eb7..49dfac1fd1ef2 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -7,6 +7,7 @@
 
 #include <drm/drm_print.h>
 
+#include "dp_reg.h"
 #include "dp_link.h"
 #include "dp_panel.h"
 
@@ -1082,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link)
 
 int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 {
-	u32 cc;
+	u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB;
 	struct dp_link_private *link;
 
 	if (!dp_link) {
@@ -1096,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 	 * Unless a video pattern CTS test is ongoing, use RGB_VESA
 	 * Only RGB_VESA and RGB_CEA supported for now
 	 */
-	if (dp_link_is_video_pattern_requested(link))
-		cc = link->dp_link.test_video.test_dyn_range;
-	else
-		cc = DP_TEST_DYNAMIC_RANGE_VESA;
+	if (dp_link_is_video_pattern_requested(link)) {
+		if (link->dp_link.test_video.test_dyn_range &
+					DP_TEST_DYNAMIC_RANGE_CEA)
+			cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB;
+	}
 
 	return cc;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h
index ea85a691e72b5..78785ed4b40c4 100644
--- a/drivers/gpu/drm/msm/dp/dp_reg.h
+++ b/drivers/gpu/drm/msm/dp/dp_reg.h
@@ -143,6 +143,9 @@
 #define DP_MISC0_COLORIMETRY_CFG_SHIFT		(0x00000001)
 #define DP_MISC0_TEST_BITS_DEPTH_SHIFT		(0x00000005)
 
+#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB	(0)
+#define DP_MISC0_COLORIMERY_CFG_CEA_RGB		(0x04)
+
 #define REG_DP_VALID_BOUNDARY			(0x00000030)
 #define REG_DP_VALID_BOUNDARY_2			(0x00000034)
 
-- 
GitLab


From 096386a5bcf02e4053dc8b6cacb09a8493eeee4f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 22 Jan 2024 18:08:51 -0500
Subject: [PATCH 3377/4076] bcachefs: discard path uses unlock_long()

Some (bad) devices can have really terrible discard latency; we don't
want them blocking memory reclaim and causing warnings.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/alloc_background.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index 10704f2d3af53..fd3e175d83423 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -1715,7 +1715,7 @@ static int bch2_discard_one_bucket(struct btree_trans *trans,
 		 * This works without any other locks because this is the only
 		 * thread that removes items from the need_discard tree
 		 */
-		bch2_trans_unlock(trans);
+		bch2_trans_unlock_long(trans);
 		blkdev_issue_discard(ca->disk_sb.bdev,
 				     k.k->p.offset * ca->mi.bucket_size,
 				     ca->mi.bucket_size,
-- 
GitLab


From 0879020a7817e7ce636372c016b4528f541c9f4d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 22 Jan 2024 22:05:29 -0800
Subject: [PATCH 3378/4076] selftests: netdevsim: fix the udp_tunnel_nic test

This test is missing a whole bunch of checks for interface
renaming and one ifup. Presumably it was only used on a system
with renaming disabled and NetworkManager running.

Fixes: 91f430b2c49d ("selftests: net: add a test for UDP tunnel info infra")
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240123060529.1033912-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/netdevsim/udp_tunnel_nic.sh    | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
index 4855ef597a152..f98435c502f61 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
@@ -270,6 +270,7 @@ for port in 0 1; do
 	echo 1 > $NSIM_DEV_SYS/new_port
     fi
     NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ifconfig $NSIM_NETDEV up
 
     msg="new NIC device created"
     exp0=( 0 0 0 0 )
@@ -431,6 +432,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "overflow NIC table"
@@ -488,6 +490,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "overflow NIC table"
@@ -544,6 +547,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "destroy NIC"
@@ -573,6 +577,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
@@ -633,6 +638,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
@@ -688,6 +694,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
@@ -747,6 +754,7 @@ for port in 0 1; do
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
@@ -877,6 +885,7 @@ msg="re-add a port"
 
 echo 2 > $NSIM_DEV_SYS/del_port
 echo 2 > $NSIM_DEV_SYS/new_port
+NSIM_NETDEV=`get_netdev_name old_netdevs`
 check_tables
 
 msg="replace VxLAN in overflow table"
-- 
GitLab


From f5e414167be768b0373891d301478351f757ec65 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:22 -0800
Subject: [PATCH 3379/4076] net: fill in MODULE_DESCRIPTION()s for 8390

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to all the good old 8390 modules and drivers.

Signed-off-by: Breno Leitao <leitao@debian.org>
CC: geert@linux-m68k.org
Link: https://lore.kernel.org/r/20240123190332.677489-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/8390/8390.c      | 1 +
 drivers/net/ethernet/8390/8390p.c     | 1 +
 drivers/net/ethernet/8390/apne.c      | 1 +
 drivers/net/ethernet/8390/hydra.c     | 1 +
 drivers/net/ethernet/8390/stnic.c     | 1 +
 drivers/net/ethernet/8390/zorro8390.c | 1 +
 6 files changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/8390/8390.c b/drivers/net/ethernet/8390/8390.c
index 0e0aa40168588..c5636245f1cad 100644
--- a/drivers/net/ethernet/8390/8390.c
+++ b/drivers/net/ethernet/8390/8390.c
@@ -100,4 +100,5 @@ static void __exit ns8390_module_exit(void)
 module_init(ns8390_module_init);
 module_exit(ns8390_module_exit);
 #endif /* MODULE */
+MODULE_DESCRIPTION("National Semiconductor 8390 core driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/8390p.c b/drivers/net/ethernet/8390/8390p.c
index 6834742057b3e..6d429b11e9c6a 100644
--- a/drivers/net/ethernet/8390/8390p.c
+++ b/drivers/net/ethernet/8390/8390p.c
@@ -102,4 +102,5 @@ static void __exit NS8390p_cleanup_module(void)
 
 module_init(NS8390p_init_module);
 module_exit(NS8390p_cleanup_module);
+MODULE_DESCRIPTION("National Semiconductor 8390 core for ISA driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c
index a09f383dd249f..828edca8d30c5 100644
--- a/drivers/net/ethernet/8390/apne.c
+++ b/drivers/net/ethernet/8390/apne.c
@@ -610,4 +610,5 @@ static int init_pcmcia(void)
 	return 1;
 }
 
+MODULE_DESCRIPTION("National Semiconductor 8390 Amiga PCMCIA ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c
index 24f49a8ff903f..fd9dcdc356e68 100644
--- a/drivers/net/ethernet/8390/hydra.c
+++ b/drivers/net/ethernet/8390/hydra.c
@@ -270,4 +270,5 @@ static void __exit hydra_cleanup_module(void)
 module_init(hydra_init_module);
 module_exit(hydra_cleanup_module);
 
+MODULE_DESCRIPTION("Zorro-II Hydra 8390 ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c
index 265976e3b64ab..6cc0e190aa79c 100644
--- a/drivers/net/ethernet/8390/stnic.c
+++ b/drivers/net/ethernet/8390/stnic.c
@@ -296,4 +296,5 @@ static void __exit stnic_cleanup(void)
 
 module_init(stnic_probe);
 module_exit(stnic_cleanup);
+MODULE_DESCRIPTION("National Semiconductor DP83902AV ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c
index d70390e9d03d9..c24dd4fe7a106 100644
--- a/drivers/net/ethernet/8390/zorro8390.c
+++ b/drivers/net/ethernet/8390/zorro8390.c
@@ -443,4 +443,5 @@ static void __exit zorro8390_cleanup_module(void)
 module_init(zorro8390_init_module);
 module_exit(zorro8390_cleanup_module);
 
+MODULE_DESCRIPTION("Zorro NS8390-based ethernet driver");
 MODULE_LICENSE("GPL");
-- 
GitLab


From 39535d7ff6c1e5bda0a3f3c87250bab63e910969 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:23 -0800
Subject: [PATCH 3380/4076] net: fill in MODULE_DESCRIPTION()s for Broadcom
 bgmac

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Broadcom iProc GBit driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20240123190332.677489-3-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bcm4908_enet.c    | 1 +
 drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c | 1 +
 drivers/net/ethernet/broadcom/bgmac-bcma.c      | 1 +
 drivers/net/ethernet/broadcom/bgmac-platform.c  | 1 +
 drivers/net/ethernet/broadcom/bgmac.c           | 1 +
 5 files changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
index 3e7c8671cd116..72df1bb101728 100644
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -793,5 +793,6 @@ static struct platform_driver bcm4908_enet_driver = {
 };
 module_platform_driver(bcm4908_enet_driver);
 
+MODULE_DESCRIPTION("Broadcom BCM4908 Gigabit Ethernet driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, bcm4908_enet_of_match);
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
index 9b83d53616994..50b8e97a811d2 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
@@ -260,4 +260,5 @@ void bcma_mdio_mii_unregister(struct mii_bus *mii_bus)
 EXPORT_SYMBOL_GPL(bcma_mdio_mii_unregister);
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA MDIO helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 6e4f36aaf5db6..36f9bad28e6a9 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -362,4 +362,5 @@ module_init(bgmac_init)
 module_exit(bgmac_exit)
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA interface driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 0b21fd5bd4575..77425c7a32dbf 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -298,4 +298,5 @@ static struct platform_driver bgmac_enet_driver = {
 };
 
 module_platform_driver(bgmac_enet_driver);
+MODULE_DESCRIPTION("Broadcom iProc GBit platform interface driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 448a1b90de5eb..6ffdc42294074 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1626,4 +1626,5 @@ int bgmac_enet_resume(struct bgmac *bgmac)
 EXPORT_SYMBOL_GPL(bgmac_enet_resume);
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit driver");
 MODULE_LICENSE("GPL");
-- 
GitLab


From bb567fbbbbb41d61b685e224098806a90df8cef2 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:24 -0800
Subject: [PATCH 3381/4076] net: fill in MODULE_DESCRIPTION()s for liquidio

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Cavium Liquidio.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240123190332.677489-4-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/liquidio/lio_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 9cc6303c82ffb..f38d31bfab1bb 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -27,6 +27,7 @@
 #include "octeon_network.h"
 
 MODULE_AUTHOR("Cavium Networks, <support@cavium.com>");
+MODULE_DESCRIPTION("Cavium LiquidIO Intelligent Server Adapter Core");
 MODULE_LICENSE("GPL");
 
 /* OOM task polling interval */
-- 
GitLab


From 53c83e2d36484f8df87792bb5368653bdb441014 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:25 -0800
Subject: [PATCH 3382/4076] net: fill in MODULE_DESCRIPTION()s for ep93xxx_eth

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Cirrus EP93xx ethernet driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240123190332.677489-5-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cirrus/ep93xx_eth.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c
index 1c2a540db13d8..1f495cfd7959b 100644
--- a/drivers/net/ethernet/cirrus/ep93xx_eth.c
+++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c
@@ -868,5 +868,6 @@ static struct platform_driver ep93xx_eth_driver = {
 
 module_platform_driver(ep93xx_eth_driver);
 
+MODULE_DESCRIPTION("Cirrus EP93xx Ethernet driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:ep93xx-eth");
-- 
GitLab


From 27881ca8c8e1b6179ac41dc787cbfc3cb4362ff8 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:26 -0800
Subject: [PATCH 3383/4076] net: fill in MODULE_DESCRIPTION()s for nps_enet

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the EZchip NPS ethernet driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240123190332.677489-6-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ezchip/nps_enet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 07c2b701b5fa9..9ebe751c1df07 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -661,4 +661,5 @@ static struct platform_driver nps_enet_driver = {
 module_platform_driver(nps_enet_driver);
 
 MODULE_AUTHOR("EZchip Semiconductor");
+MODULE_DESCRIPTION("EZchip NPS Ethernet driver");
 MODULE_LICENSE("GPL v2");
-- 
GitLab


From 07c42d237567d47225499d0586b9b90a432a7b58 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:27 -0800
Subject: [PATCH 3384/4076] net: fill in MODULE_DESCRIPTION()s for enetc

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the NXP ENETC Ethernet driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240123190332.677489-7-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index cffbf27c4656b..bfdbdab443ae0 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -3216,4 +3216,5 @@ void enetc_pci_remove(struct pci_dev *pdev)
 }
 EXPORT_SYMBOL_GPL(enetc_pci_remove);
 
+MODULE_DESCRIPTION("NXP ENETC Ethernet driver");
 MODULE_LICENSE("Dual BSD/GPL");
-- 
GitLab


From 2e87576488552aab742391b6c442beedffd31abe Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:28 -0800
Subject: [PATCH 3385/4076] net: fill in MODULE_DESCRIPTION()s for fec

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the FEC (MPC8xx) Ethernet controller.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://lore.kernel.org/r/20240123190332.677489-8-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d42594f322750..4b0259e9269ae 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -4769,4 +4769,5 @@ static struct platform_driver fec_driver = {
 
 module_platform_driver(fec_driver);
 
+MODULE_DESCRIPTION("NXP Fast Ethernet Controller (FEC) driver");
 MODULE_LICENSE("GPL");
-- 
GitLab


From 8183c470c17602275ec1e3525d010f6c9cd383e9 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:29 -0800
Subject: [PATCH 3386/4076] net: fill in MODULE_DESCRIPTION()s for fsl_pq_mdio

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Freescale PQ MDIO driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240123190332.677489-9-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fsl_pq_mdio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 70dd982a5edce..026f7270a54de 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -531,4 +531,5 @@ static struct platform_driver fsl_pq_mdio_driver = {
 
 module_platform_driver(fsl_pq_mdio_driver);
 
+MODULE_DESCRIPTION("Freescale PQ MDIO helpers");
 MODULE_LICENSE("GPL");
-- 
GitLab


From 07d1e0ce874377a88c13bb56a336d6c544367837 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:30 -0800
Subject: [PATCH 3387/4076] net: fill in MODULE_DESCRIPTION()s for litex

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the LiteX Liteeth Ethernet device.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Gabriel Somlo <gsomlo@gmail.com>
Link: https://lore.kernel.org/r/20240123190332.677489-10-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/litex/litex_liteeth.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/litex/litex_liteeth.c b/drivers/net/ethernet/litex/litex_liteeth.c
index 5182fe737c372..ff54fbe41bccc 100644
--- a/drivers/net/ethernet/litex/litex_liteeth.c
+++ b/drivers/net/ethernet/litex/litex_liteeth.c
@@ -318,4 +318,5 @@ static struct platform_driver liteeth_driver = {
 module_platform_driver(liteeth_driver);
 
 MODULE_AUTHOR("Joel Stanley <joel@jms.id.au>");
+MODULE_DESCRIPTION("LiteX Liteeth Ethernet driver");
 MODULE_LICENSE("GPL");
-- 
GitLab


From bdc6734115d7f66d8bea155454d4ce9259821660 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 23 Jan 2024 11:03:31 -0800
Subject: [PATCH 3388/4076] net: fill in MODULE_DESCRIPTION()s for rvu_mbox

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Marvel RVU mbox driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240123190332.677489-11-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 9690ac01f02c8..b92264d0a77e7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -413,4 +413,5 @@ const char *otx2_mbox_id2name(u16 id)
 EXPORT_SYMBOL(otx2_mbox_id2name);
 
 MODULE_AUTHOR("Marvell.");
+MODULE_DESCRIPTION("Marvell RVU NIC Mbox helpers");
 MODULE_LICENSE("GPL v2");
-- 
GitLab


From 7f3d03c48b1eb6bc45ab20ca98b8b11be25f9f52 Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <quic_abhinavk@quicinc.com>
Date: Wed, 17 Jan 2024 11:41:09 -0800
Subject: [PATCH 3389/4076] drm/msm/dpu: check for valid hw_pp in
 dpu_encoder_helper_phys_cleanup

The commit 8b45a26f2ba9 ("drm/msm/dpu: reserve cdm blocks for writeback
in case of YUV output") introduced a smatch warning about another
conditional block in dpu_encoder_helper_phys_cleanup() which had assumed
hw_pp will always be valid which may not necessarily be true.

Lets fix the other conditional block by making sure hw_pp is valid
before dereferencing it.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Fixes: ae4d721ce100 ("drm/msm/dpu: add an API to reset the encoder related hw blocks")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/574878/
Link: https://lore.kernel.org/r/20240117194109.21609-1-quic_abhinavk@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index f2b82ca5efb39..6a4b489d44e51 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -2068,7 +2068,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	}
 
 	/* reset the merge 3D HW block */
-	if (phys_enc->hw_pp->merge_3d) {
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
 				BLEND_3D_NONE);
 		if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
@@ -2099,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	if (phys_enc->hw_wb)
 		intf_cfg.wb = phys_enc->hw_wb->idx;
 
-	if (phys_enc->hw_pp->merge_3d)
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
 	if (ctl->ops.reset_intf_cfg)
-- 
GitLab


From 269009893146c495f41e9572dd9319e787c2eba9 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:15:52 +0100
Subject: [PATCH 3390/4076] xsk: recycle buffer in case Rx queue was full

Add missing xsk_buff_free() call when __xsk_rcv_zc() failed to produce
descriptor to XSK Rx queue.

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-2-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9f13aa3353e31..1eadfac03cc41 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -167,8 +167,10 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		contd = XDP_PKT_CONTD;
 
 	err = __xsk_rcv_zc(xs, xskb, len, contd);
-	if (err || likely(!frags))
-		goto out;
+	if (err)
+		goto err;
+	if (likely(!frags))
+		return 0;
 
 	xskb_list = &xskb->pool->xskb_list;
 	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
@@ -177,11 +179,13 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		len = pos->xdp.data_end - pos->xdp.data;
 		err = __xsk_rcv_zc(xs, pos, len, contd);
 		if (err)
-			return err;
+			goto err;
 		list_del(&pos->xskb_list_node);
 	}
 
-out:
+	return 0;
+err:
+	xsk_buff_free(xdp);
 	return err;
 }
 
-- 
GitLab


From f7f6aa8e24383fbb11ac55942e66da9660110f80 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:15:53 +0100
Subject: [PATCH 3391/4076] xsk: make xsk_buff_pool responsible for clearing
 xdp_buff::flags

XDP multi-buffer support introduced XDP_FLAGS_HAS_FRAGS flag that is
used by drivers to notify data path whether xdp_buff contains fragments
or not. Data path looks up mentioned flag on first buffer that occupies
the linear part of xdp_buff, so drivers only modify it there. This is
sufficient for SKB and XDP_DRV modes as usually xdp_buff is allocated on
stack or it resides within struct representing driver's queue and
fragments are carried via skb_frag_t structs. IOW, we are dealing with
only one xdp_buff.

ZC mode though relies on list of xdp_buff structs that is carried via
xsk_buff_pool::xskb_list, so ZC data path has to make sure that
fragments do *not* have XDP_FLAGS_HAS_FRAGS set. Otherwise,
xsk_buff_free() could misbehave if it would be executed against xdp_buff
that carries a frag with XDP_FLAGS_HAS_FRAGS flag set. Such scenario can
take place when within supplied XDP program bpf_xdp_adjust_tail() is
used with negative offset that would in turn release the tail fragment
from multi-buffer frame.

Calling xsk_buff_free() on tail fragment with XDP_FLAGS_HAS_FRAGS would
result in releasing all the nodes from xskb_list that were produced by
driver before XDP program execution, which is not what is intended -
only tail fragment should be deleted from xskb_list and then it should
be put onto xsk_buff_pool::free_list. Such multi-buffer frame will never
make it up to user space, so from AF_XDP application POV there would be
no traffic running, however due to free_list getting constantly new
nodes, driver will be able to feed HW Rx queue with recycled buffers.
Bottom line is that instead of traffic being redirected to user space,
it would be continuously dropped.

To fix this, let us clear the mentioned flag on xsk_buff_pool side
during xdp_buff initialization, which is what should have been done
right from the start of XSK multi-buffer support.

Fixes: 1bbc04de607b ("ice: xsk: add RX multi-buffer support")
Fixes: 1c9ba9c14658 ("i40e: xsk: add RX multi-buffer support")
Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-3-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_xsk.c | 1 -
 drivers/net/ethernet/intel/ice/ice_xsk.c   | 1 -
 include/net/xdp_sock_drv.h                 | 1 +
 net/xdp/xsk_buff_pool.c                    | 1 +
 4 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index af7d5fa6cdc15..82aca0d16a3e1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -498,7 +498,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		xdp_res = i40e_run_xdp_zc(rx_ring, first, xdp_prog);
 		i40e_handle_xdp_result_zc(rx_ring, first, rx_desc, &rx_packets,
 					  &rx_bytes, xdp_res, &failure);
-		first->flags = 0;
 		next_to_clean = next_to_process;
 		if (failure)
 			break;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 5d1ae8e4058a4..d9073a618ad62 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -895,7 +895,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 
 		if (!first) {
 			first = xdp;
-			xdp_buff_clear_frags_flag(first);
 		} else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) {
 			break;
 		}
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 526c1e7f505e4..9819e2af0378c 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -164,6 +164,7 @@ static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
 	xdp->data_meta = xdp->data;
 	xdp->data_end = xdp->data + size;
+	xdp->flags = 0;
 }
 
 static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 28711cc44ced2..ce60ecd48a4dc 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -555,6 +555,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 
 	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
 	xskb->xdp.data_meta = xskb->xdp.data;
+	xskb->xdp.flags = 0;
 
 	if (pool->dma_need_sync) {
 		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,
-- 
GitLab


From c5114710c8ce86b8317e9b448f4fd15c711c2a82 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:15:54 +0100
Subject: [PATCH 3392/4076] xsk: fix usage of multi-buffer BPF helpers for ZC
 XDP

Currently when packet is shrunk via bpf_xdp_adjust_tail() and memory
type is set to MEM_TYPE_XSK_BUFF_POOL, null ptr dereference happens:

[1136314.192256] BUG: kernel NULL pointer dereference, address:
0000000000000034
[1136314.203943] #PF: supervisor read access in kernel mode
[1136314.213768] #PF: error_code(0x0000) - not-present page
[1136314.223550] PGD 0 P4D 0
[1136314.230684] Oops: 0000 [#1] PREEMPT SMP NOPTI
[1136314.239621] CPU: 8 PID: 54203 Comm: xdpsock Not tainted 6.6.0+ #257
[1136314.250469] Hardware name: Intel Corporation S2600WFT/S2600WFT,
BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019
[1136314.265615] RIP: 0010:__xdp_return+0x6c/0x210
[1136314.274653] Code: ad 00 48 8b 47 08 49 89 f8 a8 01 0f 85 9b 01 00 00 0f 1f 44 00 00 f0 41 ff 48 34 75 32 4c 89 c7 e9 79 cd 80 ff 83 fe 03 75 17 <f6> 41 34 01 0f 85 02 01 00 00 48 89 cf e9 22 cc 1e 00 e9 3d d2 86
[1136314.302907] RSP: 0018:ffffc900089f8db0 EFLAGS: 00010246
[1136314.312967] RAX: ffffc9003168aed0 RBX: ffff8881c3300000 RCX:
0000000000000000
[1136314.324953] RDX: 0000000000000000 RSI: 0000000000000003 RDI:
ffffc9003168c000
[1136314.336929] RBP: 0000000000000ae0 R08: 0000000000000002 R09:
0000000000010000
[1136314.348844] R10: ffffc9000e495000 R11: 0000000000000040 R12:
0000000000000001
[1136314.360706] R13: 0000000000000524 R14: ffffc9003168aec0 R15:
0000000000000001
[1136314.373298] FS:  00007f8df8bbcb80(0000) GS:ffff8897e0e00000(0000)
knlGS:0000000000000000
[1136314.386105] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1136314.396532] CR2: 0000000000000034 CR3: 00000001aa912002 CR4:
00000000007706f0
[1136314.408377] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[1136314.420173] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
0000000000000400
[1136314.431890] PKRU: 55555554
[1136314.439143] Call Trace:
[1136314.446058]  <IRQ>
[1136314.452465]  ? __die+0x20/0x70
[1136314.459881]  ? page_fault_oops+0x15b/0x440
[1136314.468305]  ? exc_page_fault+0x6a/0x150
[1136314.476491]  ? asm_exc_page_fault+0x22/0x30
[1136314.484927]  ? __xdp_return+0x6c/0x210
[1136314.492863]  bpf_xdp_adjust_tail+0x155/0x1d0
[1136314.501269]  bpf_prog_ccc47ae29d3b6570_xdp_sock_prog+0x15/0x60
[1136314.511263]  ice_clean_rx_irq_zc+0x206/0xc60 [ice]
[1136314.520222]  ? ice_xmit_zc+0x6e/0x150 [ice]
[1136314.528506]  ice_napi_poll+0x467/0x670 [ice]
[1136314.536858]  ? ttwu_do_activate.constprop.0+0x8f/0x1a0
[1136314.546010]  __napi_poll+0x29/0x1b0
[1136314.553462]  net_rx_action+0x133/0x270
[1136314.561619]  __do_softirq+0xbe/0x28e
[1136314.569303]  do_softirq+0x3f/0x60

This comes from __xdp_return() call with xdp_buff argument passed as
NULL which is supposed to be consumed by xsk_buff_free() call.

To address this properly, in ZC case, a node that represents the frag
being removed has to be pulled out of xskb_list. Introduce
appropriate xsk helpers to do such node operation and use them
accordingly within bpf_xdp_adjust_tail().

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com> # For the xsk header part
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-4-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock_drv.h | 26 +++++++++++++++++++++++
 net/core/filter.c          | 42 ++++++++++++++++++++++++++++++++------
 2 files changed, 62 insertions(+), 6 deletions(-)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 9819e2af0378c..c9aec9ab61912 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -159,6 +159,23 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
 	return ret;
 }
 
+static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+{
+	struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp);
+
+	list_del(&xskb->xskb_list_node);
+}
+
+static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
+{
+	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+	struct xdp_buff_xsk *frag;
+
+	frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
+			       xskb_list_node);
+	return &frag->xdp;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
@@ -351,6 +368,15 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
 	return NULL;
 }
 
+static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
+{
+	return NULL;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index 24061f29c9dd2..36fb5ae8af699 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -83,6 +83,7 @@
 #include <net/netfilter/nf_conntrack_bpf.h>
 #include <net/netkit.h>
 #include <linux/un.h>
+#include <net/xdp_sock_drv.h>
 
 #include "dev.h"
 
@@ -4096,6 +4097,40 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	return 0;
 }
 
+static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink,
+				   struct xdp_mem_info *mem_info, bool release)
+{
+	struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp);
+
+	if (release) {
+		xsk_buff_del_tail(zc_frag);
+		__xdp_return(NULL, mem_info, false, zc_frag);
+	} else {
+		zc_frag->data_end -= shrink;
+	}
+}
+
+static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
+				int shrink)
+{
+	struct xdp_mem_info *mem_info = &xdp->rxq->mem;
+	bool release = skb_frag_size(frag) == shrink;
+
+	if (mem_info->type == MEM_TYPE_XSK_BUFF_POOL) {
+		bpf_xdp_shrink_data_zc(xdp, shrink, mem_info, release);
+		goto out;
+	}
+
+	if (release) {
+		struct page *page = skb_frag_page(frag);
+
+		__xdp_return(page_address(page), mem_info, false, NULL);
+	}
+
+out:
+	return release;
+}
+
 static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
@@ -4110,12 +4145,7 @@ static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
 
 		len_free += shrink;
 		offset -= shrink;
-
-		if (skb_frag_size(frag) == shrink) {
-			struct page *page = skb_frag_page(frag);
-
-			__xdp_return(page_address(page), &xdp->rxq->mem,
-				     false, NULL);
+		if (bpf_xdp_shrink_data(xdp, frag, shrink)) {
 			n_frags_free++;
 		} else {
 			skb_frag_size_sub(frag, shrink);
-- 
GitLab


From ad2047cf5d9313200e308612aed516548873d124 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:15:55 +0100
Subject: [PATCH 3393/4076] ice: work on pre-XDP prog frag count

Fix an OOM panic in XDP_DRV mode when a XDP program shrinks a
multi-buffer packet by 4k bytes and then redirects it to an AF_XDP
socket.

Since support for handling multi-buffer frames was added to XDP, usage
of bpf_xdp_adjust_tail() helper within XDP program can free the page
that given fragment occupies and in turn decrease the fragment count
within skb_shared_info that is embedded in xdp_buff struct. In current
ice driver codebase, it can become problematic when page recycling logic
decides not to reuse the page. In such case, __page_frag_cache_drain()
is used with ice_rx_buf::pagecnt_bias that was not adjusted after
refcount of page was changed by XDP prog which in turn does not drain
the refcount to 0 and page is never freed.

To address this, let us store the count of frags before the XDP program
was executed on Rx ring struct. This will be used to compare with
current frag count from skb_shared_info embedded in xdp_buff. A smaller
value in the latter indicates that XDP prog freed frag(s). Then, for
given delta decrement pagecnt_bias for XDP_DROP verdict.

While at it, let us also handle the EOP frag within
ice_set_rx_bufs_act() to make our life easier, so all of the adjustments
needed to be applied against freed frags are performed in the single
place.

Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-5-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c     | 14 ++++++---
 drivers/net/ethernet/intel/ice/ice_txrx.h     |  1 +
 drivers/net/ethernet/intel/ice/ice_txrx_lib.h | 31 +++++++++++++------
 3 files changed, 32 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 74d13cc5a3a7f..0c9b4aa8a049c 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -603,9 +603,7 @@ out_failure:
 		ret = ICE_XDP_CONSUMED;
 	}
 exit:
-	rx_buf->act = ret;
-	if (unlikely(xdp_buff_has_frags(xdp)))
-		ice_set_rx_bufs_act(xdp, rx_ring, ret);
+	ice_set_rx_bufs_act(xdp, rx_ring, ret);
 }
 
 /**
@@ -893,14 +891,17 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	}
 
 	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		if (unlikely(xdp_buff_has_frags(xdp)))
-			ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
+		ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
 		return -ENOMEM;
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
 	sinfo->xdp_frags_size += size;
+	/* remember frag count before XDP prog execution; bpf_xdp_adjust_tail()
+	 * can pop off frags but driver has to handle it on its own
+	 */
+	rx_ring->nr_frags = sinfo->nr_frags;
 
 	if (page_is_pfmemalloc(rx_buf->page))
 		xdp_buff_set_frag_pfmemalloc(xdp);
@@ -1251,6 +1252,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 
 		xdp->data = NULL;
 		rx_ring->first_desc = ntc;
+		rx_ring->nr_frags = 0;
 		continue;
 construct_skb:
 		if (likely(ice_ring_uses_build_skb(rx_ring)))
@@ -1266,10 +1268,12 @@ construct_skb:
 						    ICE_XDP_CONSUMED);
 			xdp->data = NULL;
 			rx_ring->first_desc = ntc;
+			rx_ring->nr_frags = 0;
 			break;
 		}
 		xdp->data = NULL;
 		rx_ring->first_desc = ntc;
+		rx_ring->nr_frags = 0;
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
 		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index b3379ff736747..af955b0e5dc5c 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -358,6 +358,7 @@ struct ice_rx_ring {
 	struct ice_tx_ring *xdp_ring;
 	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	struct xsk_buff_pool *xsk_pool;
+	u32 nr_frags;
 	dma_addr_t dma;			/* physical address of ring */
 	u16 rx_buf_len;
 	u8 dcb_tc;			/* Traffic class of ring */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 7620475086196..afcead4baef4b 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -12,26 +12,39 @@
  * act: action to store onto Rx buffers related to XDP buffer parts
  *
  * Set action that should be taken before putting Rx buffer from first frag
- * to one before last. Last one is handled by caller of this function as it
- * is the EOP frag that is currently being processed. This function is
- * supposed to be called only when XDP buffer contains frags.
+ * to the last.
  */
 static inline void
 ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
 		    const unsigned int act)
 {
-	const struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
-	u32 first = rx_ring->first_desc;
-	u32 nr_frags = sinfo->nr_frags;
+	u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
 	u32 cnt = rx_ring->count;
 	struct ice_rx_buf *buf;
 
 	for (int i = 0; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[first];
+		buf = &rx_ring->rx_buf[idx];
 		buf->act = act;
 
-		if (++first == cnt)
-			first = 0;
+		if (++idx == cnt)
+			idx = 0;
+	}
+
+	/* adjust pagecnt_bias on frags freed by XDP prog */
+	if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) {
+		u32 delta = rx_ring->nr_frags - sinfo_frags;
+
+		while (delta) {
+			if (idx == 0)
+				idx = cnt - 1;
+			else
+				idx--;
+			buf = &rx_ring->rx_buf[idx];
+			buf->pagecnt_bias--;
+			delta--;
+		}
 	}
 }
 
-- 
GitLab


From 83014323c642b8faa2d64a5f303b41c019322478 Mon Sep 17 00:00:00 2001
From: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Date: Wed, 24 Jan 2024 20:15:56 +0100
Subject: [PATCH 3394/4076] i40e: handle multi-buffer packets that are shrunk
 by xdp prog

XDP programs can shrink packets by calling the bpf_xdp_adjust_tail()
helper function. For multi-buffer packets this may lead to reduction of
frag count stored in skb_shared_info area of the xdp_buff struct. This
results in issues with the current handling of XDP_PASS and XDP_DROP
cases.

For XDP_PASS, currently skb is being built using frag count of
xdp_buffer before it was processed by XDP prog and thus will result in
an inconsistent skb when frag count gets reduced by XDP prog. To fix
this, get correct frag count while building the skb instead of using
pre-obtained frag count.

For XDP_DROP, current page recycling logic will not reuse the page but
instead will adjust the pagecnt_bias so that the page can be freed. This
again results in inconsistent behavior as the page refcnt has already
been changed by the helper while freeing the frag(s) as part of
shrinking the packet. To fix this, only adjust pagecnt_bias for buffers
that are stillpart of the packet post-xdp prog run.

Fixes: e213ced19bef ("i40e: add support for XDP multi-buffer Rx")
Reported-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-6-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 40 ++++++++++++---------
 1 file changed, 23 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 971ba33220381..1f0a0f13a334a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2087,7 +2087,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
 static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res,
 				  struct xdp_buff *xdp)
 {
-	u32 next = rx_ring->next_to_clean;
+	u32 nr_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
+	u32 next = rx_ring->next_to_clean, i = 0;
 	struct i40e_rx_buffer *rx_buffer;
 
 	xdp->flags = 0;
@@ -2100,10 +2101,10 @@ static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res,
 		if (!rx_buffer->page)
 			continue;
 
-		if (xdp_res == I40E_XDP_CONSUMED)
-			rx_buffer->pagecnt_bias++;
-		else
+		if (xdp_res != I40E_XDP_CONSUMED)
 			i40e_rx_buffer_flip(rx_buffer, xdp->frame_sz);
+		else if (i++ <= nr_frags)
+			rx_buffer->pagecnt_bias++;
 
 		/* EOP buffer will be put in i40e_clean_rx_irq() */
 		if (next == rx_ring->next_to_process)
@@ -2117,20 +2118,20 @@ static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res,
  * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
- * @nr_frags: number of buffers for the packet
  *
  * This function allocates an skb.  It then populates it with the page
  * data from the current receive descriptor, taking care to set up the
  * skb correctly.
  */
 static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
-					  struct xdp_buff *xdp,
-					  u32 nr_frags)
+					  struct xdp_buff *xdp)
 {
 	unsigned int size = xdp->data_end - xdp->data;
 	struct i40e_rx_buffer *rx_buffer;
+	struct skb_shared_info *sinfo;
 	unsigned int headlen;
 	struct sk_buff *skb;
+	u32 nr_frags = 0;
 
 	/* prefetch first cache line of first page */
 	net_prefetch(xdp->data);
@@ -2168,6 +2169,10 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	memcpy(__skb_put(skb, headlen), xdp->data,
 	       ALIGN(headlen, sizeof(long)));
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
 	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
 	/* update all of the pointers */
 	size -= headlen;
@@ -2187,9 +2192,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	}
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
-		struct skb_shared_info *sinfo, *skinfo = skb_shinfo(skb);
+		struct skb_shared_info *skinfo = skb_shinfo(skb);
 
-		sinfo = xdp_get_shared_info_from_buff(xdp);
 		memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0],
 		       sizeof(skb_frag_t) * nr_frags);
 
@@ -2212,17 +2216,17 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
  * i40e_build_skb - Build skb around an existing buffer
  * @rx_ring: Rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
- * @nr_frags: number of buffers for the packet
  *
  * This function builds an skb around an existing Rx buffer, taking care
  * to set up the skb correctly and avoid any memcpy overhead.
  */
 static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
-				      struct xdp_buff *xdp,
-				      u32 nr_frags)
+				      struct xdp_buff *xdp)
 {
 	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct skb_shared_info *sinfo;
 	struct sk_buff *skb;
+	u32 nr_frags;
 
 	/* Prefetch first cache line of first page. If xdp->data_meta
 	 * is unused, this points exactly as xdp->data, otherwise we
@@ -2231,6 +2235,11 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 	 */
 	net_prefetch(xdp->data_meta);
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
+
 	/* build an skb around the page buffer */
 	skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz);
 	if (unlikely(!skb))
@@ -2243,9 +2252,6 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 		skb_metadata_set(skb, metasize);
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
-		struct skb_shared_info *sinfo;
-
-		sinfo = xdp_get_shared_info_from_buff(xdp);
 		xdp_update_skb_shared_info(skb, nr_frags,
 					   sinfo->xdp_frags_size,
 					   nr_frags * xdp->frame_sz,
@@ -2589,9 +2595,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 			total_rx_bytes += size;
 		} else {
 			if (ring_uses_build_skb(rx_ring))
-				skb = i40e_build_skb(rx_ring, xdp, nfrags);
+				skb = i40e_build_skb(rx_ring, xdp);
 			else
-				skb = i40e_construct_skb(rx_ring, xdp, nfrags);
+				skb = i40e_construct_skb(rx_ring, xdp);
 
 			/* drop if we failed to retrieve a buffer */
 			if (!skb) {
-- 
GitLab


From 2ee788c06493d02ee85855414cca39825e768aaf Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:15:57 +0100
Subject: [PATCH 3395/4076] ice: remove redundant xdp_rxq_info registration

xdp_rxq_info struct can be registered by drivers via two functions -
xdp_rxq_info_reg() and __xdp_rxq_info_reg(). The latter one allows
drivers that support XDP multi-buffer to set up xdp_rxq_info::frag_size
which in turn will make it possible to grow the packet via
bpf_xdp_adjust_tail() BPF helper.

Currently, ice registers xdp_rxq_info in two spots:
1) ice_setup_rx_ring() // via xdp_rxq_info_reg(), BUG
2) ice_vsi_cfg_rxq()   // via __xdp_rxq_info_reg(), OK

Cited commit under fixes tag took care of setting up frag_size and
updated registration scheme in 2) but it did not help as
1) is called before 2) and as shown above it uses old registration
function. This means that 2) sees that xdp_rxq_info is already
registered and never calls __xdp_rxq_info_reg() which leaves us with
xdp_rxq_info::frag_size being set to 0.

To fix this misbehavior, simply remove xdp_rxq_info_reg() call from
ice_setup_rx_ring().

Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-7-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 0c9b4aa8a049c..97d41d6ebf1fb 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -513,11 +513,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
 		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
 
-	if (rx_ring->vsi->type == ICE_VSI_PF &&
-	    !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
-		if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				     rx_ring->q_index, rx_ring->q_vector->napi.napi_id))
-			goto err;
 	return 0;
 
 err:
-- 
GitLab


From 290779905d09d5fdf6caa4f58ddefc3f4db0c0a9 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:15:58 +0100
Subject: [PATCH 3396/4076] intel: xsk: initialize skb_frag_t::bv_offset in ZC
 drivers

Ice and i40e ZC drivers currently set offset of a frag within
skb_shared_info to 0, which is incorrect. xdp_buffs that come from
xsk_buff_pool always have 256 bytes of a headroom, so they need to be
taken into account to retrieve xdp_buff::data via skb_frag_address().
Otherwise, bpf_xdp_frags_increase_tail() would be starting its job from
xdp_buff::data_hard_start which would result in overwriting existing
payload.

Fixes: 1c9ba9c14658 ("i40e: xsk: add RX multi-buffer support")
Fixes: 1bbc04de607b ("ice: xsk: add RX multi-buffer support")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-8-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_xsk.c | 3 ++-
 drivers/net/ethernet/intel/ice/ice_xsk.c   | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 82aca0d16a3e1..11500003af0d4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -414,7 +414,8 @@ i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first,
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start), 0, size);
+				   virt_to_page(xdp->data_hard_start),
+				   XDP_PACKET_HEADROOM, size);
 	sinfo->xdp_frags_size += size;
 	xsk_buff_add_frag(xdp);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index d9073a618ad62..8b81a16770459 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -825,7 +825,8 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start), 0, size);
+				   virt_to_page(xdp->data_hard_start),
+				   XDP_PACKET_HEADROOM, size);
 	sinfo->xdp_frags_size += size;
 	xsk_buff_add_frag(xdp);
 
-- 
GitLab


From 3de38c87174225487fc93befeea7d380db80aef6 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:15:59 +0100
Subject: [PATCH 3397/4076] ice: update xdp_rxq_info::frag_size for ZC enabled
 Rx queue

Now that ice driver correctly sets up frag_size in xdp_rxq_info, let us
make it work for ZC multi-buffer as well. ice_rx_ring::rx_buf_len for ZC
is being set via xsk_pool_get_rx_frame_size() and this needs to be
propagated up to xdp_rxq_info.

Use a bigger hammer and instead of unregistering only xdp_rxq_info's
memory model, unregister it altogether and register it again and have
xdp_rxq_info with correct frag_size value.

Fixes: 1bbc04de607b ("ice: xsk: add RX multi-buffer support")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-9-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 37 ++++++++++++++---------
 1 file changed, 23 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 533b923cae2d0..7ac847718882e 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -547,19 +547,27 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 	ring->rx_buf_len = ring->vsi->rx_buf_len;
 
 	if (ring->vsi->type == ICE_VSI_PF) {
-		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-			/* coverity[check_return] */
-			__xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					   ring->q_index,
-					   ring->q_vector->napi.napi_id,
-					   ring->vsi->rx_buf_len);
+		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+						 ring->q_index,
+						 ring->q_vector->napi.napi_id,
+						 ring->rx_buf_len);
+			if (err)
+				return err;
+		}
 
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
-			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
 				xsk_pool_get_rx_frame_size(ring->xsk_pool);
+			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+						 ring->q_index,
+						 ring->q_vector->napi.napi_id,
+						 ring->rx_buf_len);
+			if (err)
+				return err;
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 							 MEM_TYPE_XSK_BUFF_POOL,
 							 NULL);
@@ -571,13 +579,14 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
-			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-				/* coverity[check_return] */
-				__xdp_rxq_info_reg(&ring->xdp_rxq,
-						   ring->netdev,
-						   ring->q_index,
-						   ring->q_vector->napi.napi_id,
-						   ring->vsi->rx_buf_len);
+			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+				err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+							 ring->q_index,
+							 ring->q_vector->napi.napi_id,
+							 ring->rx_buf_len);
+				if (err)
+					return err;
+			}
 
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 							 MEM_TYPE_PAGE_SHARED,
-- 
GitLab


From fbadd83a612c3b7aad2987893faca6bd24aaebb3 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:16:00 +0100
Subject: [PATCH 3398/4076] xdp: reflect tail increase for
 MEM_TYPE_XSK_BUFF_POOL

XSK ZC Rx path calculates the size of data that will be posted to XSK Rx
queue via subtracting xdp_buff::data_end from xdp_buff::data.

In bpf_xdp_frags_increase_tail(), when underlying memory type of
xdp_rxq_info is MEM_TYPE_XSK_BUFF_POOL, add offset to data_end in tail
fragment, so that later on user space will be able to take into account
the amount of bytes added by XDP program.

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-10-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/filter.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 36fb5ae8af699..ef3e78b6a39c4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4093,6 +4093,8 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset);
 	skb_frag_size_add(frag, offset);
 	sinfo->xdp_frags_size += offset;
+	if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+		xsk_buff_get_tail(xdp)->data_end += offset;
 
 	return 0;
 }
-- 
GitLab


From a045d2f2d03d23e7db6772dd83e0ba2705dfad93 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:16:01 +0100
Subject: [PATCH 3399/4076] i40e: set xdp_rxq_info::frag_size

i40e support XDP multi-buffer so it is supposed to use
__xdp_rxq_info_reg() instead of xdp_rxq_info_reg() and set the
frag_size. It can not be simply converted at existing callsite because
rx_buf_len could be un-initialized, so let us register xdp_rxq_info
within i40e_configure_rx_ring(), which happen to be called with already
initialized rx_buf_len value.

Commit 5180ff1364bc ("i40e: use int for i40e_status") converted 'err' to
int, so two variables to deal with return codes are not needed within
i40e_configure_rx_ring(). Remove 'ret' and use 'err' to handle status
from xdp_rxq_info registration.

Fixes: e213ced19bef ("i40e: add support for XDP multi-buffer Rx")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-11-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 40 ++++++++++++---------
 drivers/net/ethernet/intel/i40e/i40e_txrx.c |  9 -----
 2 files changed, 24 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ae8f9f135725b..d3b00d8ed39ae 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3588,40 +3588,48 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	struct i40e_hmc_obj_rxq rx_ctx;
 	int err = 0;
 	bool ok;
-	int ret;
 
 	bitmap_zero(ring->state, __I40E_RING_STATE_NBITS);
 
 	/* clear the context structure first */
 	memset(&rx_ctx, 0, sizeof(rx_ctx));
 
-	if (ring->vsi->type == I40E_VSI_MAIN)
-		xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+	ring->rx_buf_len = vsi->rx_buf_len;
+
+	/* XDP RX-queue info only needed for RX rings exposed to XDP */
+	if (ring->vsi->type != I40E_VSI_MAIN)
+		goto skip;
+
+	if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->queue_index,
+					 ring->q_vector->napi.napi_id,
+					 ring->rx_buf_len);
+		if (err)
+			return err;
+	}
 
 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
-		ring->rx_buf_len =
-		  xsk_pool_get_rx_frame_size(ring->xsk_pool);
-		ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL,
 						 NULL);
-		if (ret)
-			return ret;
+		if (err)
+			return err;
 		dev_info(&vsi->back->pdev->dev,
 			 "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 			 ring->queue_index);
 
 	} else {
-		ring->rx_buf_len = vsi->rx_buf_len;
-		if (ring->vsi->type == I40E_VSI_MAIN) {
-			ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_PAGE_SHARED,
-							 NULL);
-			if (ret)
-				return ret;
-		}
+		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						 MEM_TYPE_PAGE_SHARED,
+						 NULL);
+		if (err)
+			return err;
 	}
 
+skip:
 	xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq);
 
 	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1f0a0f13a334a..0d7177083708f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1548,7 +1548,6 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring)
 int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	int err;
 
 	u64_stats_init(&rx_ring->syncp);
 
@@ -1569,14 +1568,6 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	rx_ring->next_to_process = 0;
 	rx_ring->next_to_use = 0;
 
-	/* XDP RX-queue info only needed for RX rings exposed to XDP */
-	if (rx_ring->vsi->type == I40E_VSI_MAIN) {
-		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				       rx_ring->queue_index, rx_ring->q_vector->napi.napi_id);
-		if (err < 0)
-			return err;
-	}
-
 	rx_ring->xdp_prog = rx_ring->vsi->xdp_prog;
 
 	rx_ring->rx_bi =
-- 
GitLab


From 0cbb08707c932b3f004bc1a8ec6200ef572c1f5f Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 24 Jan 2024 20:16:02 +0100
Subject: [PATCH 3400/4076] i40e: update xdp_rxq_info::frag_size for ZC enabled
 Rx queue

Now that i40e driver correctly sets up frag_size in xdp_rxq_info, let us
make it work for ZC multi-buffer as well. i40e_ring::rx_buf_len for ZC
is being set via xsk_pool_get_rx_frame_size() and this needs to be
propagated up to xdp_rxq_info.

Fixes: 1c9ba9c14658 ("i40e: xsk: add RX multi-buffer support")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-12-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index d3b00d8ed39ae..6e7fd473abfd0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3611,7 +3611,14 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 
 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
+		xdp_rxq_info_unreg(&ring->xdp_rxq);
 		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->queue_index,
+					 ring->q_vector->napi.napi_id,
+					 ring->rx_buf_len);
+		if (err)
+			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL,
 						 NULL);
-- 
GitLab


From f6cc4b6a3ae53df425771000e9c9540cce9b7bb1 Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Tue, 23 Jan 2024 01:24:42 +0800
Subject: [PATCH 3401/4076] fjes: fix memleaks in fjes_hw_setup

In fjes_hw_setup, it allocates several memory and delay the deallocation
to the fjes_hw_exit in fjes_probe through the following call chain:

fjes_probe
  |-> fjes_hw_init
        |-> fjes_hw_setup
  |-> fjes_hw_exit

However, when fjes_hw_setup fails, fjes_hw_exit won't be called and thus
all the resources allocated in fjes_hw_setup will be leaked. In this
patch, we free those resources in fjes_hw_setup and prevents such leaks.

Fixes: 2fcbca687702 ("fjes: platform_driver's .probe and .remove routine")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240122172445.3841883-1-alexious@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/fjes/fjes_hw.c | 37 ++++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c
index 704e949484d0c..b9b5554ea8620 100644
--- a/drivers/net/fjes/fjes_hw.c
+++ b/drivers/net/fjes/fjes_hw.c
@@ -221,21 +221,25 @@ static int fjes_hw_setup(struct fjes_hw *hw)
 
 	mem_size = FJES_DEV_REQ_BUF_SIZE(hw->max_epid);
 	hw->hw_info.req_buf = kzalloc(mem_size, GFP_KERNEL);
-	if (!(hw->hw_info.req_buf))
-		return -ENOMEM;
+	if (!(hw->hw_info.req_buf)) {
+		result = -ENOMEM;
+		goto free_ep_info;
+	}
 
 	hw->hw_info.req_buf_size = mem_size;
 
 	mem_size = FJES_DEV_RES_BUF_SIZE(hw->max_epid);
 	hw->hw_info.res_buf = kzalloc(mem_size, GFP_KERNEL);
-	if (!(hw->hw_info.res_buf))
-		return -ENOMEM;
+	if (!(hw->hw_info.res_buf)) {
+		result = -ENOMEM;
+		goto free_req_buf;
+	}
 
 	hw->hw_info.res_buf_size = mem_size;
 
 	result = fjes_hw_alloc_shared_status_region(hw);
 	if (result)
-		return result;
+		goto free_res_buf;
 
 	hw->hw_info.buffer_share_bit = 0;
 	hw->hw_info.buffer_unshare_reserve_bit = 0;
@@ -246,11 +250,11 @@ static int fjes_hw_setup(struct fjes_hw *hw)
 
 			result = fjes_hw_alloc_epbuf(&buf_pair->tx);
 			if (result)
-				return result;
+				goto free_epbuf;
 
 			result = fjes_hw_alloc_epbuf(&buf_pair->rx);
 			if (result)
-				return result;
+				goto free_epbuf;
 
 			spin_lock_irqsave(&hw->rx_status_lock, flags);
 			fjes_hw_setup_epbuf(&buf_pair->tx, mac,
@@ -273,6 +277,25 @@ static int fjes_hw_setup(struct fjes_hw *hw)
 	fjes_hw_init_command_registers(hw, &param);
 
 	return 0;
+
+free_epbuf:
+	for (epidx = 0; epidx < hw->max_epid ; epidx++) {
+		if (epidx == hw->my_epid)
+			continue;
+		fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].tx);
+		fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].rx);
+	}
+	fjes_hw_free_shared_status_region(hw);
+free_res_buf:
+	kfree(hw->hw_info.res_buf);
+	hw->hw_info.res_buf = NULL;
+free_req_buf:
+	kfree(hw->hw_info.req_buf);
+	hw->hw_info.req_buf = NULL;
+free_ep_info:
+	kfree(hw->ep_shm_info);
+	hw->ep_shm_info = NULL;
+	return result;
 }
 
 static void fjes_hw_cleanup(struct fjes_hw *hw)
-- 
GitLab


From 97cf5d53b4812dcb52c13fda700dad5aa8d3446c Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Wed, 24 Jan 2024 11:19:45 +0800
Subject: [PATCH 3402/4076] erofs: get rid of unneeded GFP_NOFS

Clean up some leftovers since there is no way for EROFS to be called
again from a reclaim context.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240124031945.130782-1-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/fscache.c | 2 +-
 fs/erofs/inode.c   | 2 +-
 fs/erofs/utils.c   | 2 +-
 fs/erofs/zdata.c   | 8 ++++----
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index bc12030393b24..5ff90026fd43f 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -459,7 +459,7 @@ static struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb
 
 	inode->i_size = OFFSET_MAX;
 	inode->i_mapping->a_ops = &erofs_fscache_meta_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
 	inode->i_blkbits = EROFS_SB(sb)->blkszbits;
 	inode->i_private = ctx;
 
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 3d616dea55dc3..36e638e8b53a3 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -60,7 +60,7 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		} else {
 			const unsigned int gotten = sb->s_blocksize - *ofs;
 
-			copied = kmalloc(vi->inode_isize, GFP_NOFS);
+			copied = kmalloc(vi->inode_isize, GFP_KERNEL);
 			if (!copied) {
 				err = -ENOMEM;
 				goto err_out;
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index 5dea308764b45..e146d09151af4 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -81,7 +81,7 @@ struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb,
 repeat:
 	xa_lock(&sbi->managed_pslots);
 	pre = __xa_cmpxchg(&sbi->managed_pslots, grp->index,
-			   NULL, grp, GFP_NOFS);
+			   NULL, grp, GFP_KERNEL);
 	if (pre) {
 		if (xa_is_err(pre)) {
 			pre = ERR_PTR(xa_err(pre));
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 692c0c39be638..583c062cd0e42 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -230,7 +230,7 @@ static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter,
 		struct page *nextpage = *candidate_bvpage;
 
 		if (!nextpage) {
-			nextpage = erofs_allocpage(pagepool, GFP_NOFS);
+			nextpage = erofs_allocpage(pagepool, GFP_KERNEL);
 			if (!nextpage)
 				return -ENOMEM;
 			set_page_private(nextpage, Z_EROFS_SHORTLIVED_PAGE);
@@ -302,7 +302,7 @@ static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int size)
 		if (nrpages > pcs->maxpages)
 			continue;
 
-		pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
+		pcl = kmem_cache_zalloc(pcs->slab, GFP_KERNEL);
 		if (!pcl)
 			return ERR_PTR(-ENOMEM);
 		pcl->pclustersize = size;
@@ -694,7 +694,7 @@ static void z_erofs_cache_invalidate_folio(struct folio *folio,
 	DBG_BUGON(stop > folio_size(folio) || stop < length);
 
 	if (offset == 0 && stop == folio_size(folio))
-		while (!z_erofs_cache_release_folio(folio, GFP_NOFS))
+		while (!z_erofs_cache_release_folio(folio, 0))
 			cond_resched();
 }
 
@@ -713,7 +713,7 @@ int erofs_init_managed_cache(struct super_block *sb)
 	set_nlink(inode, 1);
 	inode->i_size = OFFSET_MAX;
 	inode->i_mapping->a_ops = &z_erofs_cache_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
 	EROFS_SB(sb)->managed_cache = inode;
 	return 0;
 }
-- 
GitLab


From d76779dd3681c01a4c6c3cae4d0627c9083e0ee6 Mon Sep 17 00:00:00 2001
From: Quanquan Cao <caoqq@fujitsu.com>
Date: Wed, 24 Jan 2024 17:15:26 +0800
Subject: [PATCH 3403/4076] =?UTF-8?q?cxl/region=EF=BC=9AFix=20overflow=20i?=
 =?UTF-8?q?ssue=20in=20alloc=5Fhpa()?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Creating a region with 16 memory devices caused a problem. The div_u64_rem
function, used for dividing an unsigned 64-bit number by a 32-bit one,
faced an issue when SZ_256M * p->interleave_ways. The result surpassed
the maximum limit of the 32-bit divisor (4G), leading to an overflow
and a remainder of 0.
note: At this point, p->interleave_ways is 16, meaning 16 * 256M = 4G

To fix this issue, I replaced the div_u64_rem function with div64_u64_rem
and adjusted the type of the remainder.

Signed-off-by: Quanquan Cao <caoqq@fujitsu.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Fixes: 23a22cd1c98b ("cxl/region: Allocate HPA capacity to regions")
Cc: <stable@vger.kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/region.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 0f05692bfec39..ce0e2d82bb2b4 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -525,7 +525,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
 	struct cxl_region_params *p = &cxlr->params;
 	struct resource *res;
-	u32 remainder = 0;
+	u64 remainder = 0;
 
 	lockdep_assert_held_write(&cxl_region_rwsem);
 
@@ -545,7 +545,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	    (cxlr->mode == CXL_DECODER_PMEM && uuid_is_null(&p->uuid)))
 		return -ENXIO;
 
-	div_u64_rem(size, SZ_256M * p->interleave_ways, &remainder);
+	div64_u64_rem(size, (u64)SZ_256M * p->interleave_ways, &remainder);
 	if (remainder)
 		return -EINVAL;
 
-- 
GitLab


From ebeae8adf89d9a82359f6659b1663d09beec2faa Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Sun, 21 Jan 2024 15:35:06 +0800
Subject: [PATCH 3404/4076] ksmbd: fix global oob in ksmbd_nl_policy

Similar to a reported issue (check the commit b33fb5b801c6 ("net:
qualcomm: rmnet: fix global oob in rmnet_policy"), my local fuzzer finds
another global out-of-bounds read for policy ksmbd_nl_policy. See bug
trace below:

==================================================================
BUG: KASAN: global-out-of-bounds in validate_nla lib/nlattr.c:386 [inline]
BUG: KASAN: global-out-of-bounds in __nla_validate_parse+0x24af/0x2750 lib/nlattr.c:600
Read of size 1 at addr ffffffff8f24b100 by task syz-executor.1/62810

CPU: 0 PID: 62810 Comm: syz-executor.1 Tainted: G                 N 6.1.0 #3
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x8b/0xb3 lib/dump_stack.c:106
 print_address_description mm/kasan/report.c:284 [inline]
 print_report+0x172/0x475 mm/kasan/report.c:395
 kasan_report+0xbb/0x1c0 mm/kasan/report.c:495
 validate_nla lib/nlattr.c:386 [inline]
 __nla_validate_parse+0x24af/0x2750 lib/nlattr.c:600
 __nla_parse+0x3e/0x50 lib/nlattr.c:697
 __nlmsg_parse include/net/netlink.h:748 [inline]
 genl_family_rcv_msg_attrs_parse.constprop.0+0x1b0/0x290 net/netlink/genetlink.c:565
 genl_family_rcv_msg_doit+0xda/0x330 net/netlink/genetlink.c:734
 genl_family_rcv_msg net/netlink/genetlink.c:833 [inline]
 genl_rcv_msg+0x441/0x780 net/netlink/genetlink.c:850
 netlink_rcv_skb+0x14f/0x410 net/netlink/af_netlink.c:2540
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:861
 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
 netlink_unicast+0x54e/0x800 net/netlink/af_netlink.c:1345
 netlink_sendmsg+0x930/0xe50 net/netlink/af_netlink.c:1921
 sock_sendmsg_nosec net/socket.c:714 [inline]
 sock_sendmsg+0x154/0x190 net/socket.c:734
 ____sys_sendmsg+0x6df/0x840 net/socket.c:2482
 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536
 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7fdd66a8f359
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fdd65e00168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007fdd66bbcf80 RCX: 00007fdd66a8f359
RDX: 0000000000000000 RSI: 0000000020000500 RDI: 0000000000000003
RBP: 00007fdd66ada493 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007ffc84b81aff R14: 00007fdd65e00300 R15: 0000000000022000
 </TASK>

The buggy address belongs to the variable:
 ksmbd_nl_policy+0x100/0xa80

The buggy address belongs to the physical page:
page:0000000034f47940 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1ccc4b
flags: 0x200000000001000(reserved|node=0|zone=2)
raw: 0200000000001000 ffffea00073312c8 ffffea00073312c8 0000000000000000
raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffffffff8f24b000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffffffff8f24b080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>ffffffff8f24b100: f9 f9 f9 f9 00 00 f9 f9 f9 f9 f9 f9 00 00 07 f9
                   ^
 ffffffff8f24b180: f9 f9 f9 f9 00 05 f9 f9 f9 f9 f9 f9 00 00 00 05
 ffffffff8f24b200: f9 f9 f9 f9 00 00 03 f9 f9 f9 f9 f9 00 00 04 f9
==================================================================

To fix it, add a placeholder named __KSMBD_EVENT_MAX and let
KSMBD_EVENT_MAX to be its original value - 1 according to what other
netlink families do. Also change two sites that refer the
KSMBD_EVENT_MAX to correct value.

Cc: stable@vger.kernel.org
Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/ksmbd_netlink.h | 3 ++-
 fs/smb/server/transport_ipc.c | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h
index b7521e41402e0..0ebf91ffa2361 100644
--- a/fs/smb/server/ksmbd_netlink.h
+++ b/fs/smb/server/ksmbd_netlink.h
@@ -304,7 +304,8 @@ enum ksmbd_event {
 	KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST,
 	KSMBD_EVENT_SPNEGO_AUTHEN_RESPONSE	= 15,
 
-	KSMBD_EVENT_MAX
+	__KSMBD_EVENT_MAX,
+	KSMBD_EVENT_MAX = __KSMBD_EVENT_MAX - 1
 };
 
 /*
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index b49d47bdafc94..f29bb03f0dc47 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -74,7 +74,7 @@ static int handle_unsupported_event(struct sk_buff *skb, struct genl_info *info)
 static int handle_generic_event(struct sk_buff *skb, struct genl_info *info);
 static int ksmbd_ipc_heartbeat_request(void);
 
-static const struct nla_policy ksmbd_nl_policy[KSMBD_EVENT_MAX] = {
+static const struct nla_policy ksmbd_nl_policy[KSMBD_EVENT_MAX + 1] = {
 	[KSMBD_EVENT_UNSPEC] = {
 		.len = 0,
 	},
@@ -403,7 +403,7 @@ static int handle_generic_event(struct sk_buff *skb, struct genl_info *info)
 		return -EPERM;
 #endif
 
-	if (type >= KSMBD_EVENT_MAX) {
+	if (type > KSMBD_EVENT_MAX) {
 		WARN_ON(1);
 		return -EINVAL;
 	}
-- 
GitLab


From 9f3fe29d77ef4e7f7cb5c4c8c59f6dc373e57e78 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Wed, 17 Jan 2024 19:22:36 +0100
Subject: [PATCH 3405/4076] md: fix a suspicious RCU usage warning

RCU protection was removed in the commit 2d32777d60de ("raid1: remove rcu
protection to access rdev from conf").

However, the code in fix_read_error does rcu_dereference outside
rcu_read_lock - this triggers the following warning. The warning is
triggered by a LVM2 test shell/integrity-caching.sh.

This commit removes rcu_dereference.

=============================
WARNING: suspicious RCU usage
6.7.0 #2 Not tainted
-----------------------------
drivers/md/raid1.c:2265 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
no locks held by mdX_raid1/1859.

stack backtrace:
CPU: 2 PID: 1859 Comm: mdX_raid1 Not tainted 6.7.0 #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x60/0x70
 lockdep_rcu_suspicious+0x153/0x1b0
 raid1d+0x1732/0x1750 [raid1]
 ? lock_acquire+0x9f/0x270
 ? finish_wait+0x3d/0x80
 ? md_thread+0xf7/0x130 [md_mod]
 ? lock_release+0xaa/0x230
 ? md_register_thread+0xd0/0xd0 [md_mod]
 md_thread+0xa0/0x130 [md_mod]
 ? housekeeping_test_cpu+0x30/0x30
 kthread+0xdc/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x28/0x40
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork_asm+0x11/0x20
 </TASK>

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Fixes: ca294b34aaf3 ("md/raid1: support read error check")
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/51539879-e1ca-fde3-b8b4-8934ddedcbc@redhat.com
---
 drivers/md/raid1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 24f0d799fd98e..286f8b16c7bde 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2262,7 +2262,7 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	int sectors = r1_bio->sectors;
 	int read_disk = r1_bio->read_disk;
 	struct mddev *mddev = conf->mddev;
-	struct md_rdev *rdev = rcu_dereference(conf->mirrors[read_disk].rdev);
+	struct md_rdev *rdev = conf->mirrors[read_disk].rdev;
 
 	if (exceed_read_errors(mddev, rdev)) {
 		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
-- 
GitLab


From 644649553508b9bacf0fc7a5bdc4f9e0165576a5 Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.de>
Date: Mon, 22 Jan 2024 18:23:50 +0100
Subject: [PATCH 3406/4076] clocksource: Skip watchdog check for large watchdog
 intervals

There have been reports of the watchdog marking clocksources unstable on
machines with 8 NUMA nodes:

  clocksource: timekeeping watchdog on CPU373:
  Marking clocksource 'tsc' as unstable because the skew is too large:
  clocksource:   'hpet' wd_nsec: 14523447520
  clocksource:   'tsc'  cs_nsec: 14524115132

The measured clocksource skew - the absolute difference between cs_nsec
and wd_nsec - was 668 microseconds:

  cs_nsec - wd_nsec = 14524115132 - 14523447520 = 667612

The kernel used 200 microseconds for the uncertainty_margin of both the
clocksource and watchdog, resulting in a threshold of 400 microseconds (the
md variable). Both the cs_nsec and the wd_nsec value indicate that the
readout interval was circa 14.5 seconds.  The observed behaviour is that
watchdog checks failed for large readout intervals on 8 NUMA node
machines. This indicates that the size of the skew was directly proportinal
to the length of the readout interval on those machines. The measured
clocksource skew, 668 microseconds, was evaluated against a threshold (the
md variable) that is suited for readout intervals of roughly
WATCHDOG_INTERVAL, i.e. HZ >> 1, which is 0.5 second.

The intention of 2e27e793e280 ("clocksource: Reduce clocksource-skew
threshold") was to tighten the threshold for evaluating skew and set the
lower bound for the uncertainty_margin of clocksources to twice
WATCHDOG_MAX_SKEW. Later in c37e85c135ce ("clocksource: Loosen clocksource
watchdog constraints"), the WATCHDOG_MAX_SKEW constant was increased to
125 microseconds to fit the limit of NTP, which is able to use a
clocksource that suffers from up to 500 microseconds of skew per second.
Both the TSC and the HPET use default uncertainty_margin. When the
readout interval gets stretched the default uncertainty_margin is no
longer a suitable lower bound for evaluating skew - it imposes a limit
that is far stricter than the skew with which NTP can deal.

The root causes of the skew being directly proportinal to the length of
the readout interval are:

  * the inaccuracy of the shift/mult pairs of clocksources and the watchdog
  * the conversion to nanoseconds is imprecise for large readout intervals

Prevent this by skipping the current watchdog check if the readout
interval exceeds 2 * WATCHDOG_INTERVAL. Considering the maximum readout
interval of 2 * WATCHDOG_INTERVAL, the current default uncertainty margin
(of the TSC and HPET) corresponds to a limit on clocksource skew of 250
ppm (microseconds of skew per second).  To keep the limit imposed by NTP
(500 microseconds of skew per second) for all possible readout intervals,
the margins would have to be scaled so that the threshold value is
proportional to the length of the actual readout interval.

As for why the readout interval may get stretched: Since the watchdog is
executed in softirq context the expiration of the watchdog timer can get
severely delayed on account of a ksoftirqd thread not getting to run in a
timely manner. Surely, a system with such belated softirq execution is not
working well and the scheduling issue should be looked into but the
clocksource watchdog should be able to deal with it accordingly.

Fixes: 2e27e793e280 ("clocksource: Reduce clocksource-skew threshold")
Suggested-by: Feng Tang <feng.tang@intel.com>
Signed-off-by: Jiri Wiesner <jwiesner@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240122172350.GA740@incl
---
 kernel/time/clocksource.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index c108ed8a9804a..3052b1f1168e2 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -99,6 +99,7 @@ static u64 suspend_start;
  * Interval: 0.5sec.
  */
 #define WATCHDOG_INTERVAL (HZ >> 1)
+#define WATCHDOG_INTERVAL_MAX_NS ((2 * WATCHDOG_INTERVAL) * (NSEC_PER_SEC / HZ))
 
 /*
  * Threshold: 0.0312s, when doubled: 0.0625s.
@@ -134,6 +135,7 @@ static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
 static int watchdog_running;
 static atomic_t watchdog_reset_pending;
+static int64_t watchdog_max_interval;
 
 static inline void clocksource_watchdog_lock(unsigned long *flags)
 {
@@ -399,8 +401,8 @@ static inline void clocksource_reset_watchdog(void)
 static void clocksource_watchdog(struct timer_list *unused)
 {
 	u64 csnow, wdnow, cslast, wdlast, delta;
+	int64_t wd_nsec, cs_nsec, interval;
 	int next_cpu, reset_pending;
-	int64_t wd_nsec, cs_nsec;
 	struct clocksource *cs;
 	enum wd_read_status read_ret;
 	unsigned long extra_wait = 0;
@@ -470,6 +472,27 @@ static void clocksource_watchdog(struct timer_list *unused)
 		if (atomic_read(&watchdog_reset_pending))
 			continue;
 
+		/*
+		 * The processing of timer softirqs can get delayed (usually
+		 * on account of ksoftirqd not getting to run in a timely
+		 * manner), which causes the watchdog interval to stretch.
+		 * Skew detection may fail for longer watchdog intervals
+		 * on account of fixed margins being used.
+		 * Some clocksources, e.g. acpi_pm, cannot tolerate
+		 * watchdog intervals longer than a few seconds.
+		 */
+		interval = max(cs_nsec, wd_nsec);
+		if (unlikely(interval > WATCHDOG_INTERVAL_MAX_NS)) {
+			if (system_state > SYSTEM_SCHEDULING &&
+			    interval > 2 * watchdog_max_interval) {
+				watchdog_max_interval = interval;
+				pr_warn("Long readout interval, skipping watchdog check: cs_nsec: %lld wd_nsec: %lld\n",
+					cs_nsec, wd_nsec);
+			}
+			watchdog_timer.expires = jiffies;
+			continue;
+		}
+
 		/* Check the deviation from the watchdog clocksource. */
 		md = cs->uncertainty_margin + watchdog->uncertainty_margin;
 		if (abs(cs_nsec - wd_nsec) > md) {
-- 
GitLab


From f9f031dd21a7ce13a13862fa5281d32e1029c70f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jan 2024 23:21:31 +0200
Subject: [PATCH 3407/4076] drm/i915/psr: Only allow PSR in LPSP mode on HSW
 non-ULT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On HSW non-ULT (or at least on Dell Latitude E6540) external displays
start to flicker when we enable PSR on the eDP. We observe a much higher
SR and PC6 residency than should be possible with an external display,
and indeen much higher than what we observe with eDP disabled and
only the external display enabled. Looks like the hardware is somehow
ignoring the fact that the external display is active during PSR.

I wasn't able to redproduce this on my HSW ULT machine, or BDW.
So either there's something specific about this particular laptop
(eg. some unknown firmware thing) or the issue is limited to just
non-ULT HSW systems. All known registers that could affect this
look perfectly reasonable on the affected machine.

As a workaround let's unmask the LPSP event to prevent PSR entry
except while in LPSP mode (only pipe A + eDP active). This
will prevent PSR entry entirely when multiple pipes are active.
The one slight downside is that we now also prevent PSR entry
when driving eDP with pipe B or C, but I think that's a reasonable
tradeoff to avoid having to implement a more complex workaround.

Cc: stable@vger.kernel.org
Fixes: 783d8b80871f ("drm/i915/psr: Re-enable PSR1 on hsw/bdw")
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/10092
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240118212131.31868-1-ville.syrjala@linux.intel.com
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
(cherry picked from commit 94501c3ca6400e463ff6cc0c9cf4a2feb6a9205d)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 8f702c3fc62d4..57bbf3e3af92f 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1525,8 +1525,18 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 	 * can rely on frontbuffer tracking.
 	 */
 	mask = EDP_PSR_DEBUG_MASK_MEMUP |
-	       EDP_PSR_DEBUG_MASK_HPD |
-	       EDP_PSR_DEBUG_MASK_LPSP;
+	       EDP_PSR_DEBUG_MASK_HPD;
+
+	/*
+	 * For some unknown reason on HSW non-ULT (or at least on
+	 * Dell Latitude E6540) external displays start to flicker
+	 * when PSR is enabled on the eDP. SR/PC6 residency is much
+	 * higher than should be possible with an external display.
+	 * As a workaround leave LPSP unmasked to prevent PSR entry
+	 * when external displays are active.
+	 */
+	if (DISPLAY_VER(dev_priv) >= 8 || IS_HASWELL_ULT(dev_priv))
+		mask |= EDP_PSR_DEBUG_MASK_LPSP;
 
 	if (DISPLAY_VER(dev_priv) < 20)
 		mask |= EDP_PSR_DEBUG_MASK_MAX_SLEEP;
-- 
GitLab


From a2933a8759a62269754e54733d993b19de870e84 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 23 Jan 2024 15:59:17 +0800
Subject: [PATCH 3408/4076] selftests: bonding: do not test arp/ns target with
 mode balance-alb/tlb

The prio_arp/ns tests hard code the mode to active-backup. At the same
time, The balance-alb/tlb modes do not support arp/ns target. So remove
the prio_arp/ns tests from the loop and only test active-backup mode.

Fixes: 481b56e0391e ("selftests: bonding: re-format bond option tests")
Reported-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Closes: https://lore.kernel.org/netdev/17415.1705965957@famine/
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Link: https://lore.kernel.org/r/20240123075917.1576360-1-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../testing/selftests/drivers/net/bonding/bond_options.sh | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
index c54d1697f439a..d508486cc0bdc 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
@@ -162,7 +162,7 @@ prio_arp()
 	local mode=$1
 
 	for primary_reselect in 0 1 2; do
-		prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect"
+		prio_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect"
 		log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect"
 	done
 }
@@ -178,7 +178,7 @@ prio_ns()
 	fi
 
 	for primary_reselect in 0 1 2; do
-		prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect"
+		prio_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect"
 		log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect"
 	done
 }
@@ -194,9 +194,9 @@ prio()
 
 	for mode in $modes; do
 		prio_miimon $mode
-		prio_arp $mode
-		prio_ns $mode
 	done
+	prio_arp "active-backup"
+	prio_ns "active-backup"
 }
 
 arp_validate_test()
-- 
GitLab


From 9a574ea9069be30b835a3da772c039993c43369b Mon Sep 17 00:00:00 2001
From: Tim Chen <tim.c.chen@linux.intel.com>
Date: Mon, 22 Jan 2024 15:35:34 -0800
Subject: [PATCH 3409/4076] tick/sched: Preserve number of idle sleeps across
 CPU hotplug events

Commit 71fee48f ("tick-sched: Fix idle and iowait sleeptime accounting vs
CPU hotplug") preserved total idle sleep time and iowait sleeptime across
CPU hotplug events.

Similar reasoning applies to the number of idle calls and idle sleeps to
get the proper average of sleep time per idle invocation.

Preserve those fields too.

Fixes: 71fee48f ("tick-sched: Fix idle and iowait sleeptime accounting vs CPU hotplug")
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240122233534.3094238-1-tim.c.chen@linux.intel.com
---
 kernel/time/tick-sched.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index d2501673028da..01fb50c1b17e4 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1577,6 +1577,7 @@ void tick_cancel_sched_timer(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t idle_sleeptime, iowait_sleeptime;
+	unsigned long idle_calls, idle_sleeps;
 
 # ifdef CONFIG_HIGH_RES_TIMERS
 	if (ts->sched_timer.base)
@@ -1585,9 +1586,13 @@ void tick_cancel_sched_timer(int cpu)
 
 	idle_sleeptime = ts->idle_sleeptime;
 	iowait_sleeptime = ts->iowait_sleeptime;
+	idle_calls = ts->idle_calls;
+	idle_sleeps = ts->idle_sleeps;
 	memset(ts, 0, sizeof(*ts));
 	ts->idle_sleeptime = idle_sleeptime;
 	ts->iowait_sleeptime = iowait_sleeptime;
+	ts->idle_calls = idle_calls;
+	ts->idle_sleeps = idle_sleeps;
 }
 #endif
 
-- 
GitLab


From f1cc6aceecd04964304786530eaa4ad87d90b972 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 22 Jan 2024 13:09:43 +0100
Subject: [PATCH 3410/4076] accel/ivpu: Fix dev open/close races with unbind

  - Add context_list_lock to synchronize user context addition/removal
  - Use drm_dev_enter() to prevent unbinding the device during ivpu_open()
    and vpu address allocation

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Wachowski, Karol <karol.wachowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240122120945.1150728-2-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 109 +++++++++++++++++++++-------------
 drivers/accel/ivpu/ivpu_drv.h |   3 +-
 drivers/accel/ivpu/ivpu_gem.c |  18 +++---
 drivers/accel/ivpu/ivpu_gem.h |   2 +-
 drivers/accel/ivpu/ivpu_job.c |  16 ++---
 drivers/accel/ivpu/ivpu_job.h |   2 +-
 6 files changed, 85 insertions(+), 65 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 546c0899bb9e1..9418c73ee8ef8 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -6,6 +6,7 @@
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
 
 #include <drm/drm_accel.h>
 #include <drm/drm_file.h>
@@ -66,22 +67,20 @@ struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
 	return file_priv;
 }
 
-struct ivpu_file_priv *ivpu_file_priv_get_by_ctx_id(struct ivpu_device *vdev, unsigned long id)
+static void file_priv_unbind(struct ivpu_device *vdev, struct ivpu_file_priv *file_priv)
 {
-	struct ivpu_file_priv *file_priv;
-
-	xa_lock_irq(&vdev->context_xa);
-	file_priv = xa_load(&vdev->context_xa, id);
-	/* file_priv may still be in context_xa during file_priv_release() */
-	if (file_priv && !kref_get_unless_zero(&file_priv->ref))
-		file_priv = NULL;
-	xa_unlock_irq(&vdev->context_xa);
-
-	if (file_priv)
-		ivpu_dbg(vdev, KREF, "file_priv get by id: ctx %u refcount %u\n",
-			 file_priv->ctx.id, kref_read(&file_priv->ref));
-
-	return file_priv;
+	mutex_lock(&file_priv->lock);
+	if (file_priv->bound) {
+		ivpu_dbg(vdev, FILE, "file_priv unbind: ctx %u\n", file_priv->ctx.id);
+
+		ivpu_cmdq_release_all_locked(file_priv);
+		ivpu_jsm_context_release(vdev, file_priv->ctx.id);
+		ivpu_bo_unbind_all_bos_from_context(vdev, &file_priv->ctx);
+		ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
+		file_priv->bound = false;
+		drm_WARN_ON(&vdev->drm, !xa_erase_irq(&vdev->context_xa, file_priv->ctx.id));
+	}
+	mutex_unlock(&file_priv->lock);
 }
 
 static void file_priv_release(struct kref *ref)
@@ -89,13 +88,15 @@ static void file_priv_release(struct kref *ref)
 	struct ivpu_file_priv *file_priv = container_of(ref, struct ivpu_file_priv, ref);
 	struct ivpu_device *vdev = file_priv->vdev;
 
-	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u\n", file_priv->ctx.id);
+	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u bound %d\n",
+		 file_priv->ctx.id, (bool)file_priv->bound);
+
+	pm_runtime_get_sync(vdev->drm.dev);
+	mutex_lock(&vdev->context_list_lock);
+	file_priv_unbind(vdev, file_priv);
+	mutex_unlock(&vdev->context_list_lock);
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 
-	ivpu_cmdq_release_all(file_priv);
-	ivpu_jsm_context_release(vdev, file_priv->ctx.id);
-	ivpu_bo_remove_all_bos_from_context(vdev, &file_priv->ctx);
-	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
-	drm_WARN_ON(&vdev->drm, xa_erase_irq(&vdev->context_xa, file_priv->ctx.id) != file_priv);
 	mutex_destroy(&file_priv->lock);
 	kfree(file_priv);
 }
@@ -232,49 +233,53 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_file_priv *file_priv;
 	u32 ctx_id;
-	void *old;
-	int ret;
+	int idx, ret;
 
-	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, NULL, vdev->context_xa_limit, GFP_KERNEL);
-	if (ret) {
-		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
-		return ret;
-	}
+	if (!drm_dev_enter(dev, &idx))
+		return -ENODEV;
 
 	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
 	if (!file_priv) {
 		ret = -ENOMEM;
-		goto err_xa_erase;
+		goto err_dev_exit;
 	}
 
 	file_priv->vdev = vdev;
+	file_priv->bound = true;
 	kref_init(&file_priv->ref);
 	mutex_init(&file_priv->lock);
 
+	mutex_lock(&vdev->context_list_lock);
+
+	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, file_priv,
+			   vdev->context_xa_limit, GFP_KERNEL);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
+		goto err_unlock;
+	}
+
 	ret = ivpu_mmu_user_context_init(vdev, &file_priv->ctx, ctx_id);
 	if (ret)
-		goto err_mutex_destroy;
+		goto err_xa_erase;
 
-	old = xa_store_irq(&vdev->context_xa, ctx_id, file_priv, GFP_KERNEL);
-	if (xa_is_err(old)) {
-		ret = xa_err(old);
-		ivpu_err(vdev, "Failed to store context %u: %d\n", ctx_id, ret);
-		goto err_ctx_fini;
-	}
+	mutex_unlock(&vdev->context_list_lock);
+	drm_dev_exit(idx);
+
+	file->driver_priv = file_priv;
 
 	ivpu_dbg(vdev, FILE, "file_priv create: ctx %u process %s pid %d\n",
 		 ctx_id, current->comm, task_pid_nr(current));
 
-	file->driver_priv = file_priv;
 	return 0;
 
-err_ctx_fini:
-	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
-err_mutex_destroy:
-	mutex_destroy(&file_priv->lock);
-	kfree(file_priv);
 err_xa_erase:
 	xa_erase_irq(&vdev->context_xa, ctx_id);
+err_unlock:
+	mutex_unlock(&vdev->context_list_lock);
+	mutex_destroy(&file_priv->lock);
+	kfree(file_priv);
+err_dev_exit:
+	drm_dev_exit(idx);
 	return ret;
 }
 
@@ -531,6 +536,10 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
 	INIT_LIST_HEAD(&vdev->bo_list);
 
+	ret = drmm_mutex_init(&vdev->drm, &vdev->context_list_lock);
+	if (ret)
+		goto err_xa_destroy;
+
 	ret = drmm_mutex_init(&vdev->drm, &vdev->bo_list_lock);
 	if (ret)
 		goto err_xa_destroy;
@@ -602,14 +611,30 @@ err_xa_destroy:
 	return ret;
 }
 
+static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev)
+{
+	struct ivpu_file_priv *file_priv;
+	unsigned long ctx_id;
+
+	mutex_lock(&vdev->context_list_lock);
+
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv)
+		file_priv_unbind(vdev, file_priv);
+
+	mutex_unlock(&vdev->context_list_lock);
+}
+
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_pm_disable(vdev);
 	ivpu_shutdown(vdev);
 	if (IVPU_WA(d3hot_after_power_off))
 		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+
+	ivpu_jobs_abort_all(vdev);
 	ivpu_job_done_consumer_fini(vdev);
 	ivpu_pm_cancel_recovery(vdev);
+	ivpu_bo_unbind_all_user_contexts(vdev);
 
 	ivpu_ipc_fini(vdev);
 	ivpu_fw_fini(vdev);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 7a6bc1918780c..069ace4adb2d1 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -115,6 +115,7 @@ struct ivpu_device {
 
 	struct ivpu_mmu_context gctx;
 	struct ivpu_mmu_context rctx;
+	struct mutex context_list_lock; /* Protects user context addition/removal */
 	struct xarray context_xa;
 	struct xa_limit context_xa_limit;
 
@@ -147,6 +148,7 @@ struct ivpu_file_priv {
 	struct ivpu_cmdq *cmdq[IVPU_NUM_ENGINES];
 	struct ivpu_mmu_context ctx;
 	bool has_mmu_faults;
+	bool bound;
 };
 
 extern int ivpu_dbg_mask;
@@ -162,7 +164,6 @@ extern bool ivpu_disable_mmu_cont_pages;
 extern int ivpu_test_mode;
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
-struct ivpu_file_priv *ivpu_file_priv_get_by_ctx_id(struct ivpu_device *vdev, unsigned long id);
 void ivpu_file_priv_put(struct ivpu_file_priv **link);
 
 int ivpu_boot(struct ivpu_device *vdev);
diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 16f3035b91c07..e9ddbe9f50ebe 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -77,7 +77,10 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 		       const struct ivpu_addr_range *range)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	int ret;
+	int idx, ret;
+
+	if (!drm_dev_enter(&vdev->drm, &idx))
+		return -ENODEV;
 
 	mutex_lock(&bo->lock);
 
@@ -93,6 +96,8 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 
 	mutex_unlock(&bo->lock);
 
+	drm_dev_exit(idx);
+
 	return ret;
 }
 
@@ -128,14 +133,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 	dma_resv_unlock(bo->base.base.resv);
 }
 
-static void ivpu_bo_unbind(struct ivpu_bo *bo)
-{
-	mutex_lock(&bo->lock);
-	ivpu_bo_unbind_locked(bo);
-	mutex_unlock(&bo->lock);
-}
-
-void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
+void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
 {
 	struct ivpu_bo *bo;
 
@@ -239,7 +237,7 @@ static void ivpu_bo_free(struct drm_gem_object *obj)
 
 	drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
 
-	ivpu_bo_unbind(bo);
+	ivpu_bo_unbind_locked(bo);
 	mutex_destroy(&bo->lock);
 
 	drm_WARN_ON(obj->dev, bo->base.pages_use_count > 1);
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index 5cb1dda3e58ea..a8559211c70d4 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -25,7 +25,7 @@ struct ivpu_bo {
 };
 
 int ivpu_bo_pin(struct ivpu_bo *bo);
-void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
+void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
 
 struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t size);
 struct ivpu_bo *ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 flags);
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 82e40bb4803c5..4fed0c05e0515 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -112,16 +112,14 @@ static void ivpu_cmdq_release_locked(struct ivpu_file_priv *file_priv, u16 engin
 	}
 }
 
-void ivpu_cmdq_release_all(struct ivpu_file_priv *file_priv)
+void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
 {
 	int i;
 
-	mutex_lock(&file_priv->lock);
+	lockdep_assert_held(&file_priv->lock);
 
 	for (i = 0; i < IVPU_NUM_ENGINES; i++)
 		ivpu_cmdq_release_locked(file_priv, i);
-
-	mutex_unlock(&file_priv->lock);
 }
 
 /*
@@ -161,15 +159,13 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev)
 	struct ivpu_file_priv *file_priv;
 	unsigned long ctx_id;
 
-	xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
-		file_priv = ivpu_file_priv_get_by_ctx_id(vdev, ctx_id);
-		if (!file_priv)
-			continue;
+	mutex_lock(&vdev->context_list_lock);
 
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv)
 		ivpu_cmdq_reset_all(file_priv);
 
-		ivpu_file_priv_put(&file_priv);
-	}
+	mutex_unlock(&vdev->context_list_lock);
+
 }
 
 static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h
index 45a2f2ec82e5b..bd22cf8e39e75 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -56,7 +56,7 @@ struct ivpu_job {
 
 int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 
-void ivpu_cmdq_release_all(struct ivpu_file_priv *file_priv);
+void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv);
 void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev);
 
 void ivpu_job_done_consumer_init(struct ivpu_device *vdev);
-- 
GitLab


From 264b271d12d0af794f3d1dc3793e6589fae8c66c Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 22 Jan 2024 13:09:44 +0100
Subject: [PATCH 3411/4076] accel/ivpu: Improve stability of
 ivpu_submit_ioctl()

- Wake up the device as late as possible
- Remove job reference counting in order to simplify the code
- Don't put jobs that are not fully submitted on submitted_jobs_xa in
  order to avoid potential races with reset/recovery

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Wachowski, Karol <karol.wachowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240122120945.1150728-3-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_job.c | 139 +++++++++++++++-------------------
 drivers/accel/ivpu/ivpu_job.h |   1 -
 2 files changed, 62 insertions(+), 78 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 4fed0c05e0515..d9b47a04b35fe 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -125,7 +125,7 @@ void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
 /*
  * Mark the doorbell as unregistered and reset job queue pointers.
  * This function needs to be called when the VPU hardware is restarted
- * and FW looses job queue state. The next time job queue is used it
+ * and FW loses job queue state. The next time job queue is used it
  * will be registered again.
  */
 static void ivpu_cmdq_reset_locked(struct ivpu_file_priv *file_priv, u16 engine)
@@ -239,60 +239,32 @@ static struct dma_fence *ivpu_fence_create(struct ivpu_device *vdev)
 	return &fence->base;
 }
 
-static void job_get(struct ivpu_job *job, struct ivpu_job **link)
+static void ivpu_job_destroy(struct ivpu_job *job)
 {
 	struct ivpu_device *vdev = job->vdev;
-
-	kref_get(&job->ref);
-	*link = job;
-
-	ivpu_dbg(vdev, KREF, "Job get: id %u refcount %u\n", job->job_id, kref_read(&job->ref));
-}
-
-static void job_release(struct kref *ref)
-{
-	struct ivpu_job *job = container_of(ref, struct ivpu_job, ref);
-	struct ivpu_device *vdev = job->vdev;
 	u32 i;
 
+	ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d engine %d",
+		 job->job_id, job->file_priv->ctx.id, job->engine_idx);
+
 	for (i = 0; i < job->bo_count; i++)
 		if (job->bos[i])
 			drm_gem_object_put(&job->bos[i]->base.base);
 
 	dma_fence_put(job->done_fence);
 	ivpu_file_priv_put(&job->file_priv);
-
-	ivpu_dbg(vdev, KREF, "Job released: id %u\n", job->job_id);
 	kfree(job);
-
-	/* Allow the VPU to get suspended, must be called after ivpu_file_priv_put() */
-	ivpu_rpm_put(vdev);
-}
-
-static void job_put(struct ivpu_job *job)
-{
-	struct ivpu_device *vdev = job->vdev;
-
-	ivpu_dbg(vdev, KREF, "Job put: id %u refcount %u\n", job->job_id, kref_read(&job->ref));
-	kref_put(&job->ref, job_release);
 }
 
 static struct ivpu_job *
-ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
+ivpu_job_create(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 {
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_job *job;
-	int ret;
-
-	ret = ivpu_rpm_get(vdev);
-	if (ret < 0)
-		return NULL;
 
 	job = kzalloc(struct_size(job, bos, bo_count), GFP_KERNEL);
 	if (!job)
-		goto err_rpm_put;
-
-	kref_init(&job->ref);
+		return NULL;
 
 	job->vdev = vdev;
 	job->engine_idx = engine_idx;
@@ -306,17 +278,14 @@ ivpu_create_job(struct ivpu_file_priv *file_priv, u32 engine_idx, u32 bo_count)
 	job->file_priv = ivpu_file_priv_get(file_priv);
 
 	ivpu_dbg(vdev, JOB, "Job created: ctx %2d engine %d", file_priv->ctx.id, job->engine_idx);
-
 	return job;
 
 err_free_job:
 	kfree(job);
-err_rpm_put:
-	ivpu_rpm_put(vdev);
 	return NULL;
 }
 
-static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
+static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 job_status)
 {
 	struct ivpu_job *job;
 
@@ -333,9 +302,10 @@ static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
 	ivpu_dbg(vdev, JOB, "Job complete:  id %3u ctx %2d engine %d status 0x%x\n",
 		 job->job_id, job->file_priv->ctx.id, job->engine_idx, job_status);
 
+	ivpu_job_destroy(job);
 	ivpu_stop_job_timeout_detection(vdev);
 
-	job_put(job);
+	ivpu_rpm_put(vdev);
 	return 0;
 }
 
@@ -345,10 +315,10 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 	unsigned long id;
 
 	xa_for_each(&vdev->submitted_jobs_xa, id, job)
-		ivpu_job_done(vdev, id, VPU_JSM_STATUS_ABORTED);
+		ivpu_job_signal_and_destroy(vdev, id, VPU_JSM_STATUS_ABORTED);
 }
 
-static int ivpu_direct_job_submission(struct ivpu_job *job)
+static int ivpu_job_submit(struct ivpu_job *job)
 {
 	struct ivpu_file_priv *file_priv = job->file_priv;
 	struct ivpu_device *vdev = job->vdev;
@@ -356,53 +326,65 @@ static int ivpu_direct_job_submission(struct ivpu_job *job)
 	struct ivpu_cmdq *cmdq;
 	int ret;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->lock);
 
 	cmdq = ivpu_cmdq_acquire(job->file_priv, job->engine_idx);
 	if (!cmdq) {
-		ivpu_warn(vdev, "Failed get job queue, ctx %d engine %d\n",
-			  file_priv->ctx.id, job->engine_idx);
+		ivpu_warn_ratelimited(vdev, "Failed get job queue, ctx %d engine %d\n",
+				      file_priv->ctx.id, job->engine_idx);
 		ret = -EINVAL;
-		goto err_unlock;
+		goto err_unlock_file_priv;
 	}
 
 	job_id_range.min = FIELD_PREP(JOB_ID_CONTEXT_MASK, (file_priv->ctx.id - 1));
 	job_id_range.max = job_id_range.min | JOB_ID_JOB_MASK;
 
-	job_get(job, &job);
-	ret = xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL);
+	xa_lock(&vdev->submitted_jobs_xa);
+	ret = __xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL);
 	if (ret) {
-		ivpu_warn_ratelimited(vdev, "Failed to allocate job id: %d\n", ret);
-		goto err_job_put;
+		ivpu_dbg(vdev, JOB, "Too many active jobs in ctx %d\n",
+			 file_priv->ctx.id);
+		ret = -EBUSY;
+		goto err_unlock_submitted_jobs_xa;
 	}
 
 	ret = ivpu_cmdq_push_job(cmdq, job);
 	if (ret)
-		goto err_xa_erase;
+		goto err_erase_xa;
 
 	ivpu_start_job_timeout_detection(vdev);
 
-	ivpu_dbg(vdev, JOB, "Job submitted: id %3u addr 0x%llx ctx %2d engine %d next %d\n",
-		 job->job_id, job->cmd_buf_vpu_addr, file_priv->ctx.id,
-		 job->engine_idx, cmdq->jobq->header.tail);
-
-	if (ivpu_test_mode & IVPU_TEST_MODE_NULL_HW) {
-		ivpu_job_done(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW)) {
 		cmdq->jobq->header.head = cmdq->jobq->header.tail;
 		wmb(); /* Flush WC buffer for jobq header */
 	} else {
 		ivpu_cmdq_ring_db(vdev, cmdq);
 	}
 
+	ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d engine %d addr 0x%llx next %d\n",
+		 job->job_id, file_priv->ctx.id, job->engine_idx,
+		 job->cmd_buf_vpu_addr, cmdq->jobq->header.tail);
+
+	xa_unlock(&vdev->submitted_jobs_xa);
+
 	mutex_unlock(&file_priv->lock);
+
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW))
+		ivpu_job_signal_and_destroy(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
+
 	return 0;
 
-err_xa_erase:
-	xa_erase(&vdev->submitted_jobs_xa, job->job_id);
-err_job_put:
-	job_put(job);
-err_unlock:
+err_erase_xa:
+	__xa_erase(&vdev->submitted_jobs_xa, job->job_id);
+err_unlock_submitted_jobs_xa:
+	xa_unlock(&vdev->submitted_jobs_xa);
+err_unlock_file_priv:
 	mutex_unlock(&file_priv->lock);
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -508,44 +490,47 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 			     params->buffer_count * sizeof(u32));
 	if (ret) {
 		ret = -EFAULT;
-		goto free_handles;
+		goto err_free_handles;
 	}
 
 	if (!drm_dev_enter(&vdev->drm, &idx)) {
 		ret = -ENODEV;
-		goto free_handles;
+		goto err_free_handles;
 	}
 
 	ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u buf_count %u\n",
 		 file_priv->ctx.id, params->buffer_count);
 
-	job = ivpu_create_job(file_priv, params->engine, params->buffer_count);
+	job = ivpu_job_create(file_priv, params->engine, params->buffer_count);
 	if (!job) {
 		ivpu_err(vdev, "Failed to create job\n");
 		ret = -ENOMEM;
-		goto dev_exit;
+		goto err_exit_dev;
 	}
 
 	ret = ivpu_job_prepare_bos_for_submit(file, job, buf_handles, params->buffer_count,
 					      params->commands_offset);
 	if (ret) {
-		ivpu_err(vdev, "Failed to prepare job, ret %d\n", ret);
-		goto job_put;
+		ivpu_err(vdev, "Failed to prepare job: %d\n", ret);
+		goto err_destroy_job;
 	}
 
-	ret = ivpu_direct_job_submission(job);
-	if (ret) {
-		dma_fence_signal(job->done_fence);
-		ivpu_err(vdev, "Failed to submit job to the HW, ret %d\n", ret);
-	}
+	ret = ivpu_job_submit(job);
+	if (ret)
+		goto err_signal_fence;
 
-job_put:
-	job_put(job);
-dev_exit:
 	drm_dev_exit(idx);
-free_handles:
 	kfree(buf_handles);
+	return ret;
 
+err_signal_fence:
+	dma_fence_signal(job->done_fence);
+err_destroy_job:
+	ivpu_job_destroy(job);
+err_exit_dev:
+	drm_dev_exit(idx);
+err_free_handles:
+	kfree(buf_handles);
 	return ret;
 }
 
@@ -567,7 +552,7 @@ ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr,
 	}
 
 	payload = (struct vpu_ipc_msg_payload_job_done *)&jsm_msg->payload;
-	ret = ivpu_job_done(vdev, payload->job_id, payload->job_status);
+	ret = ivpu_job_signal_and_destroy(vdev, payload->job_id, payload->job_status);
 	if (!ret && !xa_empty(&vdev->submitted_jobs_xa))
 		ivpu_start_job_timeout_detection(vdev);
 }
diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h
index bd22cf8e39e75..ca4984071cc76 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -43,7 +43,6 @@ struct ivpu_cmdq {
 			  will update the job status
  */
 struct ivpu_job {
-	struct kref ref;
 	struct ivpu_device *vdev;
 	struct ivpu_file_priv *file_priv;
 	struct dma_fence *done_fence;
-- 
GitLab


From 27d19268cf394f2c78db732be0cb31852eeadb0a Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 22 Jan 2024 13:09:45 +0100
Subject: [PATCH 3412/4076] accel/ivpu: Improve recovery and reset support

  - Synchronize job submission with reset/recovery using reset_lock
  - Always print recovery reason and call diagnose_failure()
  - Don't allow for autosupend during recovery
  - Prevent immediate autosuspend after reset/recovery
  - Prevent force_recovery for issuing TDR when device is suspended
  - Reset VPU instead triggering recovery after changing debugfs params

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Wachowski, Karol <karol.wachowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240122120945.1150728-4-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_debugfs.c | 20 ++++++++++---
 drivers/accel/ivpu/ivpu_hw_37xx.c | 14 +++------
 drivers/accel/ivpu/ivpu_hw_40xx.c |  8 +++---
 drivers/accel/ivpu/ivpu_ipc.c     |  6 ++--
 drivers/accel/ivpu/ivpu_job.c     |  2 ++
 drivers/accel/ivpu/ivpu_mmu.c     | 14 ++++-----
 drivers/accel/ivpu/ivpu_pm.c      | 48 ++++++++++++++++++++-----------
 drivers/accel/ivpu/ivpu_pm.h      |  6 ++--
 8 files changed, 70 insertions(+), 48 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index 19035230563d7..7cb962e214534 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -102,7 +102,7 @@ static int reset_pending_show(struct seq_file *s, void *v)
 {
 	struct ivpu_device *vdev = seq_to_ivpu(s);
 
-	seq_printf(s, "%d\n", atomic_read(&vdev->pm->in_reset));
+	seq_printf(s, "%d\n", atomic_read(&vdev->pm->reset_pending));
 	return 0;
 }
 
@@ -130,7 +130,9 @@ dvfs_mode_fops_write(struct file *file, const char __user *user_buf, size_t size
 
 	fw->dvfs_mode = dvfs_mode;
 
-	ivpu_pm_schedule_recovery(vdev);
+	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+	if (ret)
+		return ret;
 
 	return size;
 }
@@ -190,7 +192,10 @@ fw_profiling_freq_fops_write(struct file *file, const char __user *user_buf,
 		return ret;
 
 	ivpu_hw_profiling_freq_drive(vdev, enable);
-	ivpu_pm_schedule_recovery(vdev);
+
+	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+	if (ret)
+		return ret;
 
 	return size;
 }
@@ -301,11 +306,18 @@ static ssize_t
 ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
 {
 	struct ivpu_device *vdev = file->private_data;
+	int ret;
 
 	if (!size)
 		return -EINVAL;
 
-	ivpu_pm_schedule_recovery(vdev);
+	ret = ivpu_rpm_get(vdev);
+	if (ret)
+		return ret;
+
+	ivpu_pm_trigger_recovery(vdev, "debugfs");
+	flush_work(&vdev->pm->recovery_work);
+	ivpu_rpm_put(vdev);
 	return size;
 }
 
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 574cdeefb66b3..f15a93d830578 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -875,24 +875,18 @@ static void ivpu_hw_37xx_irq_disable(struct ivpu_device *vdev)
 
 static void ivpu_hw_37xx_irq_wdt_nce_handler(struct ivpu_device *vdev)
 {
-	ivpu_err_ratelimited(vdev, "WDT NCE irq\n");
-
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT NCE IRQ");
 }
 
 static void ivpu_hw_37xx_irq_wdt_mss_handler(struct ivpu_device *vdev)
 {
-	ivpu_err_ratelimited(vdev, "WDT MSS irq\n");
-
 	ivpu_hw_wdt_disable(vdev);
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT MSS IRQ");
 }
 
 static void ivpu_hw_37xx_irq_noc_firewall_handler(struct ivpu_device *vdev)
 {
-	ivpu_err_ratelimited(vdev, "NOC Firewall irq\n");
-
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "NOC Firewall IRQ");
 }
 
 /* Handler for IRQs from VPU core (irqV) */
@@ -970,7 +964,7 @@ static bool ivpu_hw_37xx_irqb_handler(struct ivpu_device *vdev, int irq)
 		REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, status);
 
 	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
+		ivpu_pm_trigger_recovery(vdev, "Buttress IRQ");
 
 	return true;
 }
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index c02061f299e23..704288084f373 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -1049,18 +1049,18 @@ static void ivpu_hw_40xx_irq_disable(struct ivpu_device *vdev)
 static void ivpu_hw_40xx_irq_wdt_nce_handler(struct ivpu_device *vdev)
 {
 	/* TODO: For LNN hang consider engine reset instead of full recovery */
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT NCE IRQ");
 }
 
 static void ivpu_hw_40xx_irq_wdt_mss_handler(struct ivpu_device *vdev)
 {
 	ivpu_hw_wdt_disable(vdev);
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "WDT MSS IRQ");
 }
 
 static void ivpu_hw_40xx_irq_noc_firewall_handler(struct ivpu_device *vdev)
 {
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "NOC Firewall IRQ");
 }
 
 /* Handler for IRQs from VPU core (irqV) */
@@ -1154,7 +1154,7 @@ static bool ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq)
 	REGB_WR32(VPU_40XX_BUTTRESS_INTERRUPT_STAT, status);
 
 	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
+		ivpu_pm_trigger_recovery(vdev, "Buttress IRQ");
 
 	return true;
 }
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index e86621f16f85a..fa66c39b57eca 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -343,10 +343,8 @@ int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *r
 	hb_ret = ivpu_ipc_send_receive_internal(vdev, &hb_req, VPU_JSM_MSG_QUERY_ENGINE_HB_DONE,
 						&hb_resp, VPU_IPC_CHAN_ASYNC_CMD,
 						vdev->timeout.jsm);
-	if (hb_ret == -ETIMEDOUT) {
-		ivpu_hw_diagnose_failure(vdev);
-		ivpu_pm_schedule_recovery(vdev);
-	}
+	if (hb_ret == -ETIMEDOUT)
+		ivpu_pm_trigger_recovery(vdev, "IPC timeout");
 
 	return ret;
 }
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index d9b47a04b35fe..0440bee3ecafd 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -515,7 +515,9 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		goto err_destroy_job;
 	}
 
+	down_read(&vdev->pm->reset_lock);
 	ret = ivpu_job_submit(job);
+	up_read(&vdev->pm->reset_lock);
 	if (ret)
 		goto err_signal_fence;
 
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 1f813625aab39..9a3122ffce03c 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -887,7 +887,6 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 
 void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 {
-	bool schedule_recovery = false;
 	u32 *event;
 	u32 ssid;
 
@@ -897,14 +896,13 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		ivpu_mmu_dump_event(vdev, event);
 
 		ssid = FIELD_GET(IVPU_MMU_EVT_SSID_MASK, event[0]);
-		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID)
-			schedule_recovery = true;
-		else
-			ivpu_mmu_user_context_mark_invalid(vdev, ssid);
-	}
+		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID) {
+			ivpu_pm_trigger_recovery(vdev, "MMU event");
+			return;
+		}
 
-	if (schedule_recovery)
-		ivpu_pm_schedule_recovery(vdev);
+		ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+	}
 }
 
 void ivpu_mmu_evtq_dump(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 8407f1d8c99cb..f501f27ebafdf 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -112,6 +112,14 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
 	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
 	int ret;
 
+	ivpu_err(vdev, "Recovering the VPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
+
+	ret = pm_runtime_resume_and_get(vdev->drm.dev);
+	if (ret)
+		ivpu_err(vdev, "Failed to resume VPU: %d\n", ret);
+
+	ivpu_fw_log_dump(vdev);
+
 retry:
 	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
 	if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
@@ -123,11 +131,13 @@ retry:
 		ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
 
 	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
+	pm_runtime_mark_last_busy(vdev->drm.dev);
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 }
 
-void ivpu_pm_schedule_recovery(struct ivpu_device *vdev)
+void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason)
 {
-	struct ivpu_pm_info *pm = vdev->pm;
+	ivpu_err(vdev, "Recovery triggered by %s\n", reason);
 
 	if (ivpu_disable_recovery) {
 		ivpu_err(vdev, "Recovery not available when disable_recovery param is set\n");
@@ -139,10 +149,11 @@ void ivpu_pm_schedule_recovery(struct ivpu_device *vdev)
 		return;
 	}
 
-	/* Schedule recovery if it's not in progress */
-	if (atomic_cmpxchg(&pm->in_reset, 0, 1) == 0) {
-		ivpu_hw_irq_disable(vdev);
-		queue_work(system_long_wq, &pm->recovery_work);
+	/* Trigger recovery if it's not in progress */
+	if (atomic_cmpxchg(&vdev->pm->reset_pending, 0, 1) == 0) {
+		ivpu_hw_diagnose_failure(vdev);
+		ivpu_hw_irq_disable(vdev); /* Disable IRQ early to protect from IRQ storm */
+		queue_work(system_long_wq, &vdev->pm->recovery_work);
 	}
 }
 
@@ -150,12 +161,8 @@ static void ivpu_job_timeout_work(struct work_struct *work)
 {
 	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, job_timeout_work.work);
 	struct ivpu_device *vdev = pm->vdev;
-	unsigned long timeout_ms = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
 
-	ivpu_err(vdev, "TDR detected, timeout %lu ms", timeout_ms);
-	ivpu_hw_diagnose_failure(vdev);
-
-	ivpu_pm_schedule_recovery(vdev);
+	ivpu_pm_trigger_recovery(vdev, "TDR");
 }
 
 void ivpu_start_job_timeout_detection(struct ivpu_device *vdev)
@@ -228,6 +235,9 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 	bool hw_is_idle = true;
 	int ret;
 
+	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->submitted_jobs_xa));
+	drm_WARN_ON(&vdev->drm, work_pending(&vdev->pm->recovery_work));
+
 	ivpu_dbg(vdev, PM, "Runtime suspend..\n");
 
 	if (!ivpu_hw_is_idle(vdev) && vdev->pm->suspend_reschedule_counter) {
@@ -310,11 +320,12 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 {
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
 
-	pm_runtime_get_sync(vdev->drm.dev);
-
 	ivpu_dbg(vdev, PM, "Pre-reset..\n");
 	atomic_inc(&vdev->pm->reset_counter);
-	atomic_set(&vdev->pm->in_reset, 1);
+	atomic_set(&vdev->pm->reset_pending, 1);
+
+	pm_runtime_get_sync(vdev->drm.dev);
+	down_write(&vdev->pm->reset_lock);
 	ivpu_prepare_for_reset(vdev);
 	ivpu_hw_reset(vdev);
 	ivpu_pm_prepare_cold_boot(vdev);
@@ -331,9 +342,11 @@ void ivpu_pm_reset_done_cb(struct pci_dev *pdev)
 	ret = ivpu_resume(vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret);
-	atomic_set(&vdev->pm->in_reset, 0);
+	up_write(&vdev->pm->reset_lock);
+	atomic_set(&vdev->pm->reset_pending, 0);
 	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 
+	pm_runtime_mark_last_busy(vdev->drm.dev);
 	pm_runtime_put_autosuspend(vdev->drm.dev);
 }
 
@@ -346,7 +359,10 @@ void ivpu_pm_init(struct ivpu_device *vdev)
 	pm->vdev = vdev;
 	pm->suspend_reschedule_counter = PM_RESCHEDULE_LIMIT;
 
-	atomic_set(&pm->in_reset, 0);
+	init_rwsem(&pm->reset_lock);
+	atomic_set(&pm->reset_pending, 0);
+	atomic_set(&pm->reset_counter, 0);
+
 	INIT_WORK(&pm->recovery_work, ivpu_pm_recovery_work);
 	INIT_DELAYED_WORK(&pm->job_timeout_work, ivpu_job_timeout_work);
 
diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h
index 97c6e0b0aa42d..ec60fbeefefc6 100644
--- a/drivers/accel/ivpu/ivpu_pm.h
+++ b/drivers/accel/ivpu/ivpu_pm.h
@@ -6,6 +6,7 @@
 #ifndef __IVPU_PM_H__
 #define __IVPU_PM_H__
 
+#include <linux/rwsem.h>
 #include <linux/types.h>
 
 struct ivpu_device;
@@ -14,8 +15,9 @@ struct ivpu_pm_info {
 	struct ivpu_device *vdev;
 	struct delayed_work job_timeout_work;
 	struct work_struct recovery_work;
-	atomic_t in_reset;
+	struct rw_semaphore reset_lock;
 	atomic_t reset_counter;
+	atomic_t reset_pending;
 	bool is_warmboot;
 	u32 suspend_reschedule_counter;
 };
@@ -37,7 +39,7 @@ int __must_check ivpu_rpm_get(struct ivpu_device *vdev);
 int __must_check ivpu_rpm_get_if_active(struct ivpu_device *vdev);
 void ivpu_rpm_put(struct ivpu_device *vdev);
 
-void ivpu_pm_schedule_recovery(struct ivpu_device *vdev);
+void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason);
 void ivpu_start_job_timeout_detection(struct ivpu_device *vdev);
 void ivpu_stop_job_timeout_detection(struct ivpu_device *vdev);
 
-- 
GitLab


From 5e344807735023cd3a67c37a1852b849caa42620 Mon Sep 17 00:00:00 2001
From: Shenwei Wang <shenwei.wang@nxp.com>
Date: Tue, 23 Jan 2024 10:51:41 -0600
Subject: [PATCH 3413/4076] net: fec: fix the unhandled context fault from smmu

When repeatedly changing the interface link speed using the command below:

ethtool -s eth0 speed 100 duplex full
ethtool -s eth0 speed 1000 duplex full

The following errors may sometimes be reported by the ARM SMMU driver:

[ 5395.035364] fec 5b040000.ethernet eth0: Link is Down
[ 5395.039255] arm-smmu 51400000.iommu: Unhandled context fault:
fsr=0x402, iova=0x00000000, fsynr=0x100001, cbfrsynra=0x852, cb=2
[ 5398.108460] fec 5b040000.ethernet eth0: Link is Up - 100Mbps/Full -
flow control off

It is identified that the FEC driver does not properly stop the TX queue
during the link speed transitions, and this results in the invalid virtual
I/O address translations from the SMMU and causes the context faults.

Fixes: dbc64a8ea231 ("net: fec: move calls to quiesce/resume packet processing out of fec_restart()")
Signed-off-by: Shenwei Wang <shenwei.wang@nxp.com>
Link: https://lore.kernel.org/r/20240123165141.2008104-1-shenwei.wang@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/freescale/fec_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 4b0259e9269ae..432523b2c7892 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2036,6 +2036,7 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 
 		/* if any of the above changed restart the FEC */
 		if (status_change) {
+			netif_stop_queue(ndev);
 			napi_disable(&fep->napi);
 			netif_tx_lock_bh(ndev);
 			fec_restart(ndev);
@@ -2045,6 +2046,7 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 		}
 	} else {
 		if (fep->link) {
+			netif_stop_queue(ndev);
 			napi_disable(&fep->napi);
 			netif_tx_lock_bh(ndev);
 			fec_stop(ndev);
-- 
GitLab


From 50bad6f797d4d501c5ef416a6f92e1912ab5aa8b Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Tue, 23 Jan 2024 21:09:17 +0100
Subject: [PATCH 3414/4076] tsnep: Remove FCS for XDP data path

The RX data buffer includes the FCS. The FCS is already stripped for the
normal data path. But for the XDP data path the FCS is included and
acts like additional/useless data.

Remove the FCS from the RX data buffer also for XDP.

Fixes: 65b28c810035 ("tsnep: Add XDP RX support")
Fixes: 3fc2333933fd ("tsnep: Add XDP socket zero-copy RX support")
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/engleder/tsnep_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index df40c720e7b23..456e0336f3f66 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -1485,7 +1485,7 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi,
 
 			xdp_prepare_buff(&xdp, page_address(entry->page),
 					 XDP_PACKET_HEADROOM + TSNEP_RX_INLINE_METADATA_SIZE,
-					 length, false);
+					 length - ETH_FCS_LEN, false);
 
 			consume = tsnep_xdp_run_prog(rx, prog, &xdp,
 						     &xdp_status, tx_nq, tx);
@@ -1568,7 +1568,7 @@ static int tsnep_rx_poll_zc(struct tsnep_rx *rx, struct napi_struct *napi,
 		prefetch(entry->xdp->data);
 		length = __le32_to_cpu(entry->desc_wb->properties) &
 			 TSNEP_DESC_LENGTH_MASK;
-		xsk_buff_set_size(entry->xdp, length);
+		xsk_buff_set_size(entry->xdp, length - ETH_FCS_LEN);
 		xsk_buff_dma_sync_for_cpu(entry->xdp, rx->xsk_pool);
 
 		/* RX metadata with timestamps is in front of actual data,
-- 
GitLab


From 9a91c05f4bd6f6bdd6b8f90445e0da92e3ac956c Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Tue, 23 Jan 2024 21:09:18 +0100
Subject: [PATCH 3415/4076] tsnep: Fix XDP_RING_NEED_WAKEUP for empty fill ring

The fill ring of the XDP socket may contain not enough buffers to
completey fill the RX queue during socket creation. In this case the
flag XDP_RING_NEED_WAKEUP is not set as this flag is only set if the RX
queue is not completely filled during polling.

Set XDP_RING_NEED_WAKEUP flag also if RX queue is not completely filled
during XDP socket creation.

Fixes: 3fc2333933fd ("tsnep: Add XDP socket zero-copy RX support")
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/engleder/tsnep_main.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 456e0336f3f66..9aeff2b37a612 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -1762,6 +1762,19 @@ static void tsnep_rx_reopen_xsk(struct tsnep_rx *rx)
 			allocated--;
 		}
 	}
+
+	/* set need wakeup flag immediately if ring is not filled completely,
+	 * first polling would be too late as need wakeup signalisation would
+	 * be delayed for an indefinite time
+	 */
+	if (xsk_uses_need_wakeup(rx->xsk_pool)) {
+		int desc_available = tsnep_rx_desc_available(rx);
+
+		if (desc_available)
+			xsk_set_rx_need_wakeup(rx->xsk_pool);
+		else
+			xsk_clear_rx_need_wakeup(rx->xsk_pool);
+	}
 }
 
 static bool tsnep_pending(struct tsnep_queue *queue)
-- 
GitLab


From b9328fd636bd50da89e792e135b234ba8e6fe59f Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 24 Jan 2024 16:07:49 -0600
Subject: [PATCH 3416/4076] x86/CPU/AMD: Add more models to X86_FEATURE_ZEN5

Add model ranges starting at 0x20, 0x40 and 0x70 to the synthetic
feature flag X86_FEATURE_ZEN5.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240124220749.2983-1-mario.limonciello@amd.com
---
 arch/x86/kernel/cpu/amd.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index bc49e3b3aae02..f3abca334199d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -573,6 +573,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 	case 0x1a:
 		switch (c->x86_model) {
 		case 0x00 ... 0x0f:
+		case 0x20 ... 0x2f:
+		case 0x40 ... 0x4f:
+		case 0x70 ... 0x7f:
 			setup_force_cpu_cap(X86_FEATURE_ZEN5);
 			break;
 		default:
-- 
GitLab


From 116099ed345c932a8ae4a0d884a8f6cc54fd5fed Mon Sep 17 00:00:00 2001
From: Hu Yadi <hu.yadi@h3c.com>
Date: Tue, 23 Jan 2024 14:26:21 +0800
Subject: [PATCH 3417/4076] selftests/landlock: Fix net_test build with old
 libc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

One issue comes up while building selftest/landlock/net_test on my side
(gcc 7.3/glibc-2.28/kernel-4.19).

net_test.c: In function ‘set_service’:
net_test.c:91:45: warning: implicit declaration of function ‘gettid’; [-Wimplicit-function-declaration]
    "_selftests-landlock-net-tid%d-index%d", gettid(),
                                             ^~~~~~
                                             getgid
net_test.c:(.text+0x4e0): undefined reference to `gettid'

Signed-off-by: Hu Yadi <hu.yadi@h3c.com>
Suggested-by: Jiao <jiaoxupo@h3c.com>
Reviewed-by: Berlin <berlin@h3c.com>
Fixes: a549d055a22e ("selftests/landlock: Add network tests")
Link: https://lore.kernel.org/r/20240123062621.25082-1-hu.yadi@h3c.com
[mic: Cosmetic fixes]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/net_test.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index ea5f727dd2577..efcde123af1f2 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <sys/prctl.h>
 #include <sys/socket.h>
+#include <sys/syscall.h>
 #include <sys/un.h>
 
 #include "common.h"
@@ -54,6 +55,11 @@ struct service_fixture {
 	};
 };
 
+static pid_t sys_gettid(void)
+{
+	return syscall(__NR_gettid);
+}
+
 static int set_service(struct service_fixture *const srv,
 		       const struct protocol_variant prot,
 		       const unsigned short index)
@@ -88,7 +94,7 @@ static int set_service(struct service_fixture *const srv,
 	case AF_UNIX:
 		srv->unix_addr.sun_family = prot.domain;
 		sprintf(srv->unix_addr.sun_path,
-			"_selftests-landlock-net-tid%d-index%d", gettid(),
+			"_selftests-landlock-net-tid%d-index%d", sys_gettid(),
 			index);
 		srv->unix_addr_len = SUN_LEN(&srv->unix_addr);
 		srv->unix_addr.sun_path[0] = '\0';
-- 
GitLab


From 40b7835e74e0383be308d528c5e0e41b3bf72ade Mon Sep 17 00:00:00 2001
From: Hu Yadi <hu.yadi@h3c.com>
Date: Wed, 24 Jan 2024 10:29:08 +0800
Subject: [PATCH 3418/4076] selftests/landlock: Fix fs_test build with old libc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

One issue comes up while building selftest/landlock/fs_test on my side
(gcc 7.3/glibc-2.28/kernel-4.19).

gcc -Wall -O2 -isystem   fs_test.c -lcap -o selftests/landlock/fs_test
fs_test.c:4575:9: error: initializer element is not constant
  .mnt = mnt_tmp,
         ^~~~~~~

Signed-off-by: Hu Yadi <hu.yadi@h3c.com>
Suggested-by: Jiao <jiaoxupo@h3c.com>
Reviewed-by: Berlin <berlin@h3c.com>
Link: https://lore.kernel.org/r/20240124022908.42100-1-hu.yadi@h3c.com
Fixes: 04f9070e99a4 ("selftests/landlock: Add tests for pseudo filesystems")
[mic: Factor out mount's data string and make mnt_tmp static]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/fs_test.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 50818904397c5..2d6d9b43d958c 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -241,9 +241,11 @@ struct mnt_opt {
 	const char *const data;
 };
 
-const struct mnt_opt mnt_tmp = {
+#define MNT_TMP_DATA "size=4m,mode=700"
+
+static const struct mnt_opt mnt_tmp = {
 	.type = "tmpfs",
-	.data = "size=4m,mode=700",
+	.data = MNT_TMP_DATA,
 };
 
 static int mount_opt(const struct mnt_opt *const mnt, const char *const target)
@@ -4632,7 +4634,10 @@ FIXTURE_VARIANT(layout3_fs)
 /* clang-format off */
 FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) {
 	/* clang-format on */
-	.mnt = mnt_tmp,
+	.mnt = {
+		.type = "tmpfs",
+		.data = MNT_TMP_DATA,
+	},
 	.file_path = file1_s1d1,
 };
 
-- 
GitLab


From 20730e9b277873deeb6637339edcba64468f3da3 Mon Sep 17 00:00:00 2001
From: Lennert Buytenhek <kernel@wantstofly.org>
Date: Thu, 25 Jan 2024 17:04:01 +0200
Subject: [PATCH 3419/4076] ahci: add 43-bit DMA address quirk for ASMedia
 ASM1061 controllers

With one of the on-board ASM1061 AHCI controllers (1b21:0612) on an
ASUSTeK Pro WS WRX80E-SAGE SE WIFI mainboard, a controller hang was
observed that was immediately preceded by the following kernel
messages:

ahci 0000:28:00.0: Using 64-bit DMA addresses
ahci 0000:28:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0035 address=0x7fffff00000 flags=0x0000]
ahci 0000:28:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0035 address=0x7fffff00300 flags=0x0000]
ahci 0000:28:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0035 address=0x7fffff00380 flags=0x0000]
ahci 0000:28:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0035 address=0x7fffff00400 flags=0x0000]
ahci 0000:28:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0035 address=0x7fffff00680 flags=0x0000]
ahci 0000:28:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0035 address=0x7fffff00700 flags=0x0000]

The first message is produced by code in drivers/iommu/dma-iommu.c
which is accompanied by the following comment that seems to apply:

        /*
         * Try to use all the 32-bit PCI addresses first. The original SAC vs.
         * DAC reasoning loses relevance with PCIe, but enough hardware and
         * firmware bugs are still lurking out there that it's safest not to
         * venture into the 64-bit space until necessary.
         *
         * If your device goes wrong after seeing the notice then likely either
         * its driver is not setting DMA masks accurately, the hardware has
         * some inherent bug in handling >32-bit addresses, or not all the
         * expected address bits are wired up between the device and the IOMMU.
         */

Asking the ASM1061 on a discrete PCIe card to DMA from I/O virtual
address 0xffffffff00000000 produces the following I/O page faults:

vfio-pci 0000:07:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0021 address=0x7ff00000000 flags=0x0010]
vfio-pci 0000:07:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0021 address=0x7ff00000500 flags=0x0010]

Note that the upper 21 bits of the logged DMA address are zero.  (When
asking a different PCIe device in the same PCIe slot to DMA to the
same I/O virtual address, we do see all the upper 32 bits of the DMA
address as 1, so this is not an issue with the chipset or IOMMU
configuration on the test system.)

Also, hacking libahci to always set the upper 21 bits of all DMA
addresses to 1 produces no discernible effect on the behavior of the
ASM1061, and mkfs/mount/scrub/etc work as without this hack.

This all strongly suggests that the ASM1061 has a 43 bit DMA address
limit, and this commit therefore adds a quirk to deal with this limit.

This issue probably applies to (some of) the other supported ASMedia
parts as well, but we limit it to the PCI IDs known to refer to
ASM1061 parts, as that's the only part we know for sure to be affected
by this issue at this point.

Link: https://lore.kernel.org/linux-ide/ZaZ2PIpEId-rl6jv@wantstofly.org/
Signed-off-by: Lennert Buytenhek <kernel@wantstofly.org>
[cassel: drop date from error messages in commit log]
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 29 +++++++++++++++++++++++------
 drivers/ata/ahci.h |  1 +
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 762c5d8b7c1a1..d2460fa985b7e 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -48,6 +48,7 @@ enum {
 enum board_ids {
 	/* board IDs by feature in alphabetical order */
 	board_ahci,
+	board_ahci_43bit_dma,
 	board_ahci_ign_iferr,
 	board_ahci_low_power,
 	board_ahci_no_debounce_delay,
@@ -128,6 +129,13 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	[board_ahci_43bit_dma] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_43BIT_ONLY),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_ign_iferr] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_IGN_IRQ_IF_ERR),
 		.flags		= AHCI_FLAG_COMMON,
@@ -597,11 +605,11 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
 	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
-	/* Asmedia */
+	/* ASMedia */
 	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
 	{ PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci },	/* ASM1060 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci },	/* ASM1061 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci },	/* ASM1062 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci_43bit_dma },	/* ASM1061 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci_43bit_dma },	/* ASM1061/1062 */
 	{ PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci },   /* ASM1061R */
 	{ PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci },   /* ASM1062R */
 	{ PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci },   /* ASM1062+JMB575 */
@@ -954,11 +962,20 @@ static int ahci_pci_device_resume(struct device *dev)
 
 #endif /* CONFIG_PM */
 
-static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac)
+static int ahci_configure_dma_masks(struct pci_dev *pdev,
+				    struct ahci_host_priv *hpriv)
 {
-	const int dma_bits = using_dac ? 64 : 32;
+	int dma_bits;
 	int rc;
 
+	if (hpriv->cap & HOST_CAP_64) {
+		dma_bits = 64;
+		if (hpriv->flags & AHCI_HFLAG_43BIT_ONLY)
+			dma_bits = 43;
+	} else {
+		dma_bits = 32;
+	}
+
 	/*
 	 * If the device fixup already set the dma_mask to some non-standard
 	 * value, don't extend it here. This happens on STA2X11, for example.
@@ -1931,7 +1948,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ahci_gtf_filter_workaround(host);
 
 	/* initialize adapter */
-	rc = ahci_configure_dma_masks(pdev, hpriv->cap & HOST_CAP_64);
+	rc = ahci_configure_dma_masks(pdev, hpriv);
 	if (rc)
 		return rc;
 
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 4bae95b06ae3c..df8f8a1a3a34c 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -247,6 +247,7 @@ enum {
 	AHCI_HFLAG_SUSPEND_PHYS		= BIT(26), /* handle PHYs during
 						      suspend/resume */
 	AHCI_HFLAG_NO_SXS		= BIT(28), /* SXS not supported */
+	AHCI_HFLAG_43BIT_ONLY		= BIT(29), /* 43bit DMA addr limit */
 
 	/* ap->flags bits */
 
-- 
GitLab


From 8412c47d68436b9f9a260039a4a773daa6824925 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sat, 13 Jan 2024 10:03:51 +0100
Subject: [PATCH 3420/4076] ARM: dts: Fix TPM schema violations

Since commit 26c9d152ebf3 ("dt-bindings: tpm: Consolidate TCG TIS
bindings"), several issues are reported by "make dtbs_check" for ARM
devicetrees:

The nodename needs to be "tpm@0" rather than "tpmdev@0" and the
compatible property needs to contain the chip's name in addition to the
generic "tcg,tpm_tis-spi" or "tcg,tpm-tis-i2c":

  tpmdev@0: $nodename:0: 'tpmdev@0' does not match '^tpm(@[0-9a-f]+)?$'
        from schema $id: http://devicetree.org/schemas/tpm/tcg,tpm_tis-spi.yaml#

  tpm@2e: compatible: 'oneOf' conditional failed, one must be fixed:
        ['tcg,tpm-tis-i2c'] is too short
        from schema $id: http://devicetree.org/schemas/tpm/tcg,tpm-tis-i2c.yaml#

Fix these schema violations.

Aspeed Facebook BMCs use an Infineon SLB9670:
https://lore.kernel.org/all/ZZSmMJ%2F%2Fl972Qbxu@fedora/
https://lore.kernel.org/all/ZZT4%2Fw2eVzMhtsPx@fedora/
https://lore.kernel.org/all/ZZTS0p1hdAchIbKp@heinlein.vulture-banana.ts.net/

Aspeed Tacoma uses a Nuvoton NPCT75X per commit 39d8a73c53a2 ("ARM: dts:
aspeed: tacoma: Add TPM").

phyGATE-Tauri uses an Infineon SLB9670:
https://lore.kernel.org/all/ab45c82485fa272f74adf560cbb58ee60cc42689.camel@phytec.de/

A single schema violation remains in am335x-moxa-uc-2100-common.dtsi
because it is unknown which chip is used on the board.  The devicetree's
author has been asked for clarification but has not responded so far:
https://lore.kernel.org/all/20231220090910.GA32182@wunner.de/

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Patrick Williams <patrick@stwcx.xyz>
Reviewed-by: Tao Ren <rentao.bupt@gmail.com>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
---
 arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts   | 4 ++--
 arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts    | 4 ++--
 arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts           | 2 +-
 arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi | 4 ++--
 arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi          | 2 +-
 arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts        | 2 +-
 arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi    | 2 +-
 7 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts
index e899de681f475..5be0e8fd2633c 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts
+++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts
@@ -45,8 +45,8 @@
 		num-chipselects = <1>;
 		cs-gpios = <&gpio0 ASPEED_GPIO(Z, 0) GPIO_ACTIVE_LOW>;
 
-		tpmdev@0 {
-			compatible = "tcg,tpm_tis-spi";
+		tpm@0 {
+			compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 			spi-max-frequency = <33000000>;
 			reg = <0>;
 		};
diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts
index a677c827e758f..5a8169bbda879 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts
+++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts
@@ -80,8 +80,8 @@
 		gpio-miso = <&gpio ASPEED_GPIO(R, 5) GPIO_ACTIVE_HIGH>;
 		num-chipselects = <1>;
 
-		tpmdev@0 {
-			compatible = "tcg,tpm_tis-spi";
+		tpm@0 {
+			compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 			spi-max-frequency = <33000000>;
 			reg = <0>;
 		};
diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts
index 3f6010ef2b86f..213023bc5aec4 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts
+++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts
@@ -456,7 +456,7 @@
 	status = "okay";
 
 	tpm: tpm@2e {
-		compatible = "tcg,tpm-tis-i2c";
+		compatible = "nuvoton,npct75x", "tcg,tpm-tis-i2c";
 		reg = <0x2e>;
 	};
 };
diff --git a/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi b/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi
index 31590d3186a2e..00e5887c926f1 100644
--- a/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi
+++ b/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi
@@ -35,8 +35,8 @@
 		gpio-mosi = <&gpio0 ASPEED_GPIO(X, 4) GPIO_ACTIVE_HIGH>;
 		gpio-miso = <&gpio0 ASPEED_GPIO(X, 5) GPIO_ACTIVE_HIGH>;
 
-		tpmdev@0 {
-			compatible = "tcg,tpm_tis-spi";
+		tpm@0 {
+			compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 			spi-max-frequency = <33000000>;
 			reg = <0>;
 		};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi
index 44cc4ff1d0df3..d12fb44aeb140 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi
@@ -116,7 +116,7 @@
 	tpm_tis: tpm@1 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_tpm>;
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 		reg = <1>;
 		spi-max-frequency = <20000000>;
 		interrupt-parent = <&gpio5>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts b/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts
index 3a723843d5626..9984b343cdf0c 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts
@@ -130,7 +130,7 @@
 	 * TCG specification - Section 6.4.1 Clocking:
 	 * TPM shall support a SPI clock frequency range of 10-24 MHz.
 	 */
-	st33htph: tpm-tis@0 {
+	st33htph: tpm@0 {
 		compatible = "st,st33htpm-spi", "tcg,tpm_tis-spi";
 		reg = <0>;
 		spi-max-frequency = <24000000>;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi b/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi
index b8730aa52ce6f..a59331aa58e55 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi
@@ -217,7 +217,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&spi1_pins>;
 
-	tpm_spi_tis@0 {
+	tpm@0 {
 		compatible = "tcg,tpm_tis-spi";
 		reg = <0>;
 		spi-max-frequency = <500000>;
-- 
GitLab


From 5e2400f11d4deec444ac00b73e96267e057fbb37 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sat, 13 Jan 2024 19:06:56 +0100
Subject: [PATCH 3421/4076] arm64: dts: Fix TPM schema violations

Since commit 26c9d152ebf3 ("dt-bindings: tpm: Consolidate TCG TIS
bindings"), several issues are reported by "make dtbs_check" for arm64
devicetrees:

The compatible property needs to contain the chip's name in addition to
the generic "tcg,tpm_tis-spi" and the nodename needs to be "tpm@0"
rather than "cr50@0":

  tpm@1: compatible: ['tcg,tpm_tis-spi'] is too short
        from schema $id: http://devicetree.org/schemas/tpm/tcg,tpm_tis-spi.yaml#

  cr50@0: $nodename:0: 'cr50@0' does not match '^tpm(@[0-9a-f]+)?$'
        from schema $id: http://devicetree.org/schemas/tpm/google,cr50.yaml#

Fix these schema violations.

phyGATE-Tauri uses an Infineon SLB9670:
https://lore.kernel.org/all/ab45c82485fa272f74adf560cbb58ee60cc42689.camel@phytec.de/

Gateworks Venice uses an Atmel ATTPM20P:
https://trac.gateworks.com/wiki/tpm

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts    | 2 +-
 arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi     | 2 +-
 arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi     | 2 +-
 arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts         | 2 +-
 arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi     | 2 +-
 arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi     | 2 +-
 arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts      | 2 +-
 arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts | 2 +-
 arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi              | 2 +-
 arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi            | 2 +-
 arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts             | 2 +-
 arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi        | 2 +-
 12 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
index 968f475b9a96c..27a902569e2a2 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
@@ -120,7 +120,7 @@
 	};
 
 	tpm: tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&gpio2>;
 		pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
index 3f3f2a2c89cd5..752caa38eb03b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi
@@ -89,7 +89,7 @@
 	status = "okay";
 
 	tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
index 06fed93769966..2aa6c1090fc7d 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi
@@ -109,7 +109,7 @@
 	status = "okay";
 
 	tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
index feae77e038354..a08057410bdef 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
@@ -234,7 +234,7 @@
 	status = "okay";
 
 	tpm: tpm@0 {
-		compatible = "infineon,slb9670";
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 		reg = <0>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_tpm>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
index c24587c895e1f..41c79d2ebdd62 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
@@ -103,7 +103,7 @@
 	status = "okay";
 
 	tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
index 628ffba69862a..d5c400b355af5 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
@@ -115,7 +115,7 @@
 	status = "okay";
 
 	tpm@1 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
index 9caf7ca254446..cae586cd45bdd 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
@@ -196,7 +196,7 @@
 	status = "okay";
 
 	tpm@0 {
-		compatible = "tcg,tpm_tis-spi";
+		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x0>;
 		spi-max-frequency = <36000000>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts b/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts
index 6376417e918c2..d8cf1f27c3ec8 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts
@@ -65,7 +65,7 @@
 	status = "okay";
 
 	tpm@0 {
-		compatible = "infineon,slb9670";
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
 		reg = <0>;
 		spi-max-frequency = <43000000>;
 	};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
index 5506de83f61d4..1b3396b1cee39 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
@@ -888,7 +888,7 @@
 	status = "okay";
 	cs-gpios = <&pio 86 GPIO_ACTIVE_LOW>;
 
-	cr50@0 {
+	tpm@0 {
 		compatible = "google,cr50";
 		reg = <0>;
 		spi-max-frequency = <1000000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
index f2281250ac35d..d87aab8d7a79e 100644
--- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
@@ -1402,7 +1402,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&spi5_pins>;
 
-	cr50@0 {
+	tpm@0 {
 		compatible = "google,cr50";
 		reg = <0>;
 		interrupts-extended = <&pio 171 IRQ_TYPE_EDGE_RISING>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
index 0f9cc042d9bf0..1cba1d857c96b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
@@ -70,7 +70,7 @@
 &spi0 {
 	status = "okay";
 
-	cr50@0 {
+	tpm@0 {
 		compatible = "google,cr50";
 		reg = <0>;
 		interrupt-parent = <&gpio0>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
index c5e7de60c1214..5846a11f0e848 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
@@ -706,7 +706,7 @@ camera: &i2c7 {
 &spi2 {
 	status = "okay";
 
-	cr50@0 {
+	tpm@0 {
 		compatible = "google,cr50";
 		reg = <0>;
 		interrupt-parent = <&gpio1>;
-- 
GitLab


From fdaca31a7668cb17f70df5c32b6a9b90e82fc9b5 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Fri, 19 Jan 2024 11:32:41 +0800
Subject: [PATCH 3422/4076] drm/amd/pm: udpate smu v13.0.6 message permission

update smu v13.0.6 message to allow guest driver set gfx clock.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 3c98a8a0386a2..7e1941cf17964 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -160,8 +160,8 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(GfxDriverResetRecovery,		     PPSMC_MSG_GfxDriverResetRecovery,		0),
 	MSG_MAP(GetMinGfxclkFrequency,               PPSMC_MSG_GetMinGfxDpmFreq,                1),
 	MSG_MAP(GetMaxGfxclkFrequency,               PPSMC_MSG_GetMaxGfxDpmFreq,                1),
-	MSG_MAP(SetSoftMinGfxclk,                    PPSMC_MSG_SetSoftMinGfxClk,                0),
-	MSG_MAP(SetSoftMaxGfxClk,                    PPSMC_MSG_SetSoftMaxGfxClk,                0),
+	MSG_MAP(SetSoftMinGfxclk,                    PPSMC_MSG_SetSoftMinGfxClk,                1),
+	MSG_MAP(SetSoftMaxGfxClk,                    PPSMC_MSG_SetSoftMaxGfxClk,                1),
 	MSG_MAP(PrepareMp1ForUnload,                 PPSMC_MSG_PrepareForDriverUnload,          0),
 	MSG_MAP(GetCTFLimit,                         PPSMC_MSG_GetCTFLimit,                     0),
 	MSG_MAP(GetThermalLimit,                     PPSMC_MSG_ReadThrottlerLimit,              0),
-- 
GitLab


From a58371d632ebab9ea63f10893a6b6731196b6f8d Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 17 Jan 2024 08:41:52 +0530
Subject: [PATCH 3423/4076] drm/amd/display: Fix uninitialized variable usage
 in core_link_ 'read_dpcd() & write_dpcd()' functions

The 'status' variable in 'core_link_read_dpcd()' &
'core_link_write_dpcd()' was uninitialized.

Thus, initializing 'status' variable to 'DC_ERROR_UNEXPECTED' by default.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_dpcd.c:226 core_link_read_dpcd() error: uninitialized symbol 'status'.
drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_dpcd.c:248 core_link_write_dpcd() error: uninitialized symbol 'status'.

Cc: stable@vger.kernel.org
Cc: Jerry Zuo <jerry.zuo@amd.com>
Cc: Jun Lei <Jun.Lei@amd.com>
Cc: Wayne Lin <Wayne.Lin@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
index 5c9a30211c109..fc50931c2aecb 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
@@ -205,7 +205,7 @@ enum dc_status core_link_read_dpcd(
 	uint32_t extended_size;
 	/* size of the remaining partitioned address space */
 	uint32_t size_left_to_read;
-	enum dc_status status;
+	enum dc_status status = DC_ERROR_UNEXPECTED;
 	/* size of the next partition to be read from */
 	uint32_t partition_size;
 	uint32_t data_index = 0;
@@ -234,7 +234,7 @@ enum dc_status core_link_write_dpcd(
 {
 	uint32_t partition_size;
 	uint32_t data_index = 0;
-	enum dc_status status;
+	enum dc_status status = DC_ERROR_UNEXPECTED;
 
 	while (size) {
 		partition_size = dpcd_get_next_partition_size(address, size);
-- 
GitLab


From ca1ffb174f16b699c536734fc12a4162097c49f4 Mon Sep 17 00:00:00 2001
From: Ma Jun <Jun.Ma2@amd.com>
Date: Wed, 17 Jan 2024 14:35:29 +0800
Subject: [PATCH 3424/4076] drm/amdgpu/pm: Fix the power source flag error

The power source flag should be updated when
[1] System receives an interrupt indicating that the power source
has changed.
[2] System resumes from suspend or runtime suspend

Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c      | 13 +++----------
 drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c |  2 ++
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c |  2 ++
 3 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index c16703868e5ca..a54663f2e2ab9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -24,6 +24,7 @@
 
 #include <linux/firmware.h>
 #include <linux/pci.h>
+#include <linux/power_supply.h>
 #include <linux/reboot.h>
 
 #include "amdgpu.h"
@@ -817,16 +818,8 @@ static int smu_late_init(void *handle)
 	 * handle the switch automatically. Driver involvement
 	 * is unnecessary.
 	 */
-	if (!smu->dc_controlled_by_gpio) {
-		ret = smu_set_power_source(smu,
-					   adev->pm.ac_power ? SMU_POWER_SOURCE_AC :
-					   SMU_POWER_SOURCE_DC);
-		if (ret) {
-			dev_err(adev->dev, "Failed to switch to %s mode!\n",
-				adev->pm.ac_power ? "AC" : "DC");
-			return ret;
-		}
-	}
+	adev->pm.ac_power = power_supply_is_system_supplied() > 0;
+	smu_set_ac_dc(smu);
 
 	if ((amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 1)) ||
 	    (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 3)))
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 5a314d0316c1c..c7bfa68bf00f4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1442,10 +1442,12 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 			case 0x3:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
 				schedule_work(&smu->interrupt_work);
+				adev->pm.ac_power = true;
 				break;
 			case 0x4:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
 				schedule_work(&smu->interrupt_work);
+				adev->pm.ac_power = false;
 				break;
 			case 0x7:
 				/*
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 771a3d457c335..c486182ff2752 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1379,10 +1379,12 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 			case 0x3:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
 				smu_v13_0_ack_ac_dc_interrupt(smu);
+				adev->pm.ac_power = true;
 				break;
 			case 0x4:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
 				smu_v13_0_ack_ac_dc_interrupt(smu);
+				adev->pm.ac_power = false;
 				break;
 			case 0x7:
 				/*
-- 
GitLab


From 90751bdeee4e3ac87ebf814bf282b0fa97edfeab Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Sat, 20 Jan 2024 13:32:51 +0530
Subject: [PATCH 3425/4076] drm/amdgpu: Avoid fetching vram vendor information

For GFX 9.4.3 APUs, the current method of fetching vram vendor
information is not reliable. Avoid fetching the information.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.7.x
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index f9039d64ff2d7..17b7a25121b00 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1950,7 +1950,8 @@ static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
 	static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
 	u32 vram_info;
 
-	if (!amdgpu_sriov_vf(adev)) {
+	/* Only for dGPU, vendor informaton is reliable */
+	if (!amdgpu_sriov_vf(adev) && !(adev->flags & AMD_IS_APU)) {
 		vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
 		adev->gmc.vram_vendor = vram_info & 0xF;
 	}
-- 
GitLab


From 30269954745c6cac730352829ac9850918457440 Mon Sep 17 00:00:00 2001
From: Kenneth Feng <kenneth.feng@amd.com>
Date: Fri, 19 Jan 2024 16:12:00 +0800
Subject: [PATCH 3426/4076] drm/amd/pm: update the power cap setting

update the power cap setting for smu_v13.0.0/smu_v13.0.7

Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2356
Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c  | 54 ++++++++++++++++++-
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c  | 54 ++++++++++++++++++-
 2 files changed, 104 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index a9b25faa63e46..4fdf34fffa9a5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2357,6 +2357,7 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 	PPTable_t *pptable = table_context->driver_pptable;
 	SkuTable_t *skutable = &pptable->SkuTable;
 	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v13_0_get_current_power_limit(smu, &power_limit))
 		power_limit = smu->adev->pm.ac_power ?
@@ -2380,7 +2381,7 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 					od_percent_upper, od_percent_lower, power_limit);
 
 	if (max_power_limit) {
-		*max_power_limit = power_limit * (100 + od_percent_upper);
+		*max_power_limit = msg_limit * (100 + od_percent_upper);
 		*max_power_limit /= 100;
 	}
 
@@ -2959,6 +2960,55 @@ static bool smu_v13_0_0_wbrf_support_check(struct smu_context *smu)
 	}
 }
 
+static int smu_v13_0_0_set_power_limit(struct smu_context *smu,
+				       enum smu_ppt_limit_type limit_type,
+				       uint32_t limit)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	SkuTable_t *skutable = &pptable->SkuTable;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
+	struct smu_table_context *table_context = &smu->smu_table;
+	OverDriveTableExternal_t *od_table =
+		(OverDriveTableExternal_t *)table_context->overdrive_table;
+	int ret = 0;
+
+	if (limit_type != SMU_DEFAULT_PPT_LIMIT)
+		return -EINVAL;
+
+	if (limit <= msg_limit) {
+		if (smu->current_power_limit > msg_limit) {
+			od_table->OverDriveTable.Ppt = 0;
+			od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+			ret = smu_v13_0_0_upload_overdrive_table(smu, od_table);
+			if (ret) {
+				dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+				return ret;
+			}
+		}
+		return smu_v13_0_set_power_limit(smu, limit_type, limit);
+	} else if (smu->od_enabled) {
+		ret = smu_v13_0_set_power_limit(smu, limit_type, msg_limit);
+		if (ret)
+			return ret;
+
+		od_table->OverDriveTable.Ppt = (limit * 100) / msg_limit - 100;
+		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+		ret = smu_v13_0_0_upload_overdrive_table(smu, od_table);
+		if (ret) {
+		  dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+		  return ret;
+		}
+
+		smu->current_power_limit = limit;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_0_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_0_set_default_dpm_table,
@@ -3013,7 +3063,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.set_fan_control_mode = smu_v13_0_set_fan_control_mode,
 	.enable_mgpu_fan_boost = smu_v13_0_0_enable_mgpu_fan_boost,
 	.get_power_limit = smu_v13_0_0_get_power_limit,
-	.set_power_limit = smu_v13_0_set_power_limit,
+	.set_power_limit = smu_v13_0_0_set_power_limit,
 	.set_power_source = smu_v13_0_set_power_source,
 	.get_power_profile_mode = smu_v13_0_0_get_power_profile_mode,
 	.set_power_profile_mode = smu_v13_0_0_set_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 59606a19e3d2b..7c3e162e2d818 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2321,6 +2321,7 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 	PPTable_t *pptable = table_context->driver_pptable;
 	SkuTable_t *skutable = &pptable->SkuTable;
 	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v13_0_get_current_power_limit(smu, &power_limit))
 		power_limit = smu->adev->pm.ac_power ?
@@ -2344,7 +2345,7 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 					od_percent_upper, od_percent_lower, power_limit);
 
 	if (max_power_limit) {
-		*max_power_limit = power_limit * (100 + od_percent_upper);
+		*max_power_limit = msg_limit * (100 + od_percent_upper);
 		*max_power_limit /= 100;
 	}
 
@@ -2545,6 +2546,55 @@ static bool smu_v13_0_7_wbrf_support_check(struct smu_context *smu)
 	return smu->smc_fw_version > 0x00524600;
 }
 
+static int smu_v13_0_7_set_power_limit(struct smu_context *smu,
+				       enum smu_ppt_limit_type limit_type,
+				       uint32_t limit)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	SkuTable_t *skutable = &pptable->SkuTable;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
+	struct smu_table_context *table_context = &smu->smu_table;
+	OverDriveTableExternal_t *od_table =
+		(OverDriveTableExternal_t *)table_context->overdrive_table;
+	int ret = 0;
+
+	if (limit_type != SMU_DEFAULT_PPT_LIMIT)
+		return -EINVAL;
+
+	if (limit <= msg_limit) {
+		if (smu->current_power_limit > msg_limit) {
+			od_table->OverDriveTable.Ppt = 0;
+			od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+			ret = smu_v13_0_7_upload_overdrive_table(smu, od_table);
+			if (ret) {
+				dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+				return ret;
+			}
+		}
+		return smu_v13_0_set_power_limit(smu, limit_type, limit);
+	} else if (smu->od_enabled) {
+		ret = smu_v13_0_set_power_limit(smu, limit_type, msg_limit);
+		if (ret)
+			return ret;
+
+		od_table->OverDriveTable.Ppt = (limit * 100) / msg_limit - 100;
+		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+		ret = smu_v13_0_7_upload_overdrive_table(smu, od_table);
+		if (ret) {
+		  dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+		  return ret;
+		}
+
+		smu->current_power_limit = limit;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_7_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_7_set_default_dpm_table,
@@ -2596,7 +2646,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.set_fan_control_mode = smu_v13_0_set_fan_control_mode,
 	.enable_mgpu_fan_boost = smu_v13_0_7_enable_mgpu_fan_boost,
 	.get_power_limit = smu_v13_0_7_get_power_limit,
-	.set_power_limit = smu_v13_0_set_power_limit,
+	.set_power_limit = smu_v13_0_7_set_power_limit,
 	.set_power_source = smu_v13_0_set_power_source,
 	.get_power_profile_mode = smu_v13_0_7_get_power_profile_mode,
 	.set_power_profile_mode = smu_v13_0_7_set_power_profile_mode,
-- 
GitLab


From 89a7c0bd74918f723c94c10452265e25063cba9b Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Sat, 20 Jan 2024 13:48:09 +0530
Subject: [PATCH 3427/4076] drm/amdgpu: Show vram vendor only if available

Ony if vram vendor info is available, show in sysfs.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.7.x
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 08916538a615f..8db880244324f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -221,8 +221,23 @@ static struct attribute *amdgpu_vram_mgr_attributes[] = {
 	NULL
 };
 
+static umode_t amdgpu_vram_attrs_is_visible(struct kobject *kobj,
+					    struct attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (attr == &dev_attr_mem_info_vram_vendor.attr &&
+	    !adev->gmc.vram_vendor)
+		return 0;
+
+	return attr->mode;
+}
+
 const struct attribute_group amdgpu_vram_mgr_attr_group = {
-	.attrs = amdgpu_vram_mgr_attributes
+	.attrs = amdgpu_vram_mgr_attributes,
+	.is_visible = amdgpu_vram_attrs_is_visible
 };
 
 /**
-- 
GitLab


From bc8f6d42b1334f486980d57c8d12f3128d30c2e3 Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Mon, 22 Jan 2024 17:38:23 +0800
Subject: [PATCH 3428/4076] drm/amdgpu: Fix null pointer dereference

amdgpu_reg_state_sysfs_fini could be invoked at the
time when asic_func is even not initialized, i.e.,
amdgpu_discovery_init fails for some reason.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/include/amdgpu_reg_state.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/include/amdgpu_reg_state.h b/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
index be519c8edf496..335980e2afbfb 100644
--- a/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
+++ b/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
@@ -138,7 +138,7 @@ static inline size_t amdgpu_reginst_size(uint16_t num_inst, size_t inst_size,
 }
 
 #define amdgpu_asic_get_reg_state_supported(adev) \
-	((adev)->asic_funcs->get_reg_state ? 1 : 0)
+	(((adev)->asic_funcs && (adev)->asic_funcs->get_reg_state) ? 1 : 0)
 
 #define amdgpu_asic_get_reg_state(adev, state, buf, size)                  \
 	((adev)->asic_funcs->get_reg_state ?                               \
-- 
GitLab


From f1807682de0edbff6c1e46b19642a517d2e15c57 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 18 Jan 2024 14:25:35 +0530
Subject: [PATCH 3429/4076] drm/amd/pm: Fetch current power limit from FW

Power limit of SMUv13.0.6 SOCs can be updated by out-of-band ways. Fetch
the limit from firmware instead of using cached values.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.7.x
---
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index a54663f2e2ab9..7ffad3eb0a015 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2703,6 +2703,7 @@ int smu_get_power_limit(void *handle,
 		case SMU_PPT_LIMIT_CURRENT:
 			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 			case IP_VERSION(13, 0, 2):
+			case IP_VERSION(13, 0, 6):
 			case IP_VERSION(11, 0, 7):
 			case IP_VERSION(11, 0, 11):
 			case IP_VERSION(11, 0, 12):
-- 
GitLab


From e7a8594cc2af920a905db15653c19c362d4ebd3f Mon Sep 17 00:00:00 2001
From: Tom St Denis <tom.stdenis@amd.com>
Date: Wed, 17 Jan 2024 12:47:37 -0500
Subject: [PATCH 3430/4076] drm/amd/amdgpu: Assign GART pages to AMD device
 mapping
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows kernel mapped pages like the PDB and PTB to be
read via the iomem debugfs when there is no vram in the system.

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.7.x
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 73b8cca35bab8..c623e23049d1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -121,6 +121,7 @@ int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev)
 	struct amdgpu_bo_param bp;
 	dma_addr_t dma_addr;
 	struct page *p;
+	unsigned long x;
 	int ret;
 
 	if (adev->gart.bo != NULL)
@@ -130,6 +131,10 @@ int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev)
 	if (!p)
 		return -ENOMEM;
 
+	/* assign pages to this device */
+	for (x = 0; x < (1UL << order); x++)
+		p[x].mapping = adev->mman.bdev.dev_mapping;
+
 	/* If the hardware does not support UTCL2 snooping of the CPU caches
 	 * then set_memory_wc() could be used as a workaround to mark the pages
 	 * as write combine memory.
@@ -223,6 +228,7 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev)
 	unsigned int order = get_order(adev->gart.table_size);
 	struct sg_table *sg = adev->gart.bo->tbo.sg;
 	struct page *p;
+	unsigned long x;
 	int ret;
 
 	ret = amdgpu_bo_reserve(adev->gart.bo, false);
@@ -234,6 +240,8 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev)
 	sg_free_table(sg);
 	kfree(sg);
 	p = virt_to_page(adev->gart.ptr);
+	for (x = 0; x < (1UL << order); x++)
+		p[x].mapping = NULL;
 	__free_pages(p, order);
 
 	adev->gart.ptr = NULL;
-- 
GitLab


From 03ff6d7238b77e5fb2b85dc5fe01d2db9eb893bd Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 19 Jan 2024 12:23:55 -0500
Subject: [PATCH 3431/4076] drm/amdgpu/gfx10: set UNORD_DISPATCH in compute
 MQDs

This needs to be set to 1 to avoid a potential deadlock in
the GC 10.x and newer.  On GC 9.x and older, this needs
to be set to 0.  This can lead to hangs in some mixed
graphics and compute workloads.  Updated firmware is also
required for AQL.

Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c           | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index d63cab294883b..ecb622b7f9709 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6589,7 +6589,7 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 #ifdef __BIG_ENDIAN
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, ENDIAN_SWAP, 1);
 #endif
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 8b7fed9135269..22cbfa1bdaddb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -170,6 +170,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
-- 
GitLab


From 3380fcad2c906872110d31ddf7aa1fdea57f9df6 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 19 Jan 2024 12:32:59 -0500
Subject: [PATCH 3432/4076] drm/amdgpu/gfx11: set UNORD_DISPATCH in compute
 MQDs

This needs to be set to 1 to avoid a potential deadlock in
the GC 10.x and newer.  On GC 9.x and older, this needs
to be set to 0. This can lead to hangs in some mixed
graphics and compute workloads. Updated firmware is also
required for AQL.

Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c           | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 0ea0866c261f8..d9cf9fd03d300 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -3846,7 +3846,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 			    (order_base_2(prop->queue_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
 			    (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 15277f1d5cf0a..d722cbd317834 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -224,6 +224,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
-- 
GitLab


From ff8caade7429f28217c293672ab64323031f350e Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Thu, 7 Dec 2023 14:12:03 -0500
Subject: [PATCH 3433/4076] drm/amd/display: Allow IPS2 during Replay

[Why & How]
Add regkey to block video playback in IPS2 by default

Allow idle optimizations in the same spot we allow Replay for
video playback usecases.

Avoid sending it when there's an external display connected by
modifying the allow idle checks to check for active non-eDP screens.

Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c       | 2 ++
 drivers/gpu/drm/amd/display/dc/dc.h                     | 1 +
 drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c | 9 ++++++++-
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d4f525b66a090..5552d30a6d971 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1717,6 +1717,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.flags.disable_ips = DMUB_IPS_DISABLE_ALL;
 
+	init_data.flags.disable_ips_in_vpb = 1;
+
 	/* Enable DWB for tested platforms only */
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
 		init_data.num_virtual_links = 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 5d7aa882416b3..c9317ea0258ea 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -434,6 +434,7 @@ struct dc_config {
 	bool EnableMinDispClkODM;
 	bool enable_auto_dpm_test_logs;
 	unsigned int disable_ips;
+	unsigned int disable_ips_in_vpb;
 };
 
 enum visual_confirm {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 9c806385ecbdc..8b6c49622f3b6 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -680,7 +680,7 @@ void dcn35_power_down_on_boot(struct dc *dc)
 bool dcn35_apply_idle_power_optimizations(struct dc *dc, bool enable)
 {
 	struct dc_link *edp_links[MAX_NUM_EDP];
-	int edp_num;
+	int i, edp_num;
 	if (dc->debug.dmcub_emulation)
 		return true;
 
@@ -688,6 +688,13 @@ bool dcn35_apply_idle_power_optimizations(struct dc *dc, bool enable)
 		dc_get_edp_links(dc, edp_links, &edp_num);
 		if (edp_num == 0 || edp_num > 1)
 			return false;
+
+		for (i = 0; i < dc->current_state->stream_count; ++i) {
+			struct dc_stream_state *stream = dc->current_state->streams[i];
+
+			if (!stream->dpms_off && !dc_is_embedded_signal(stream->signal))
+				return false;
+		}
 	}
 
 	// TODO: review other cases when idle optimization is allowed
-- 
GitLab


From 955406e6fd241b2936e7f033a03b2956922c8f32 Mon Sep 17 00:00:00 2001
From: Alvin Lee <alvin.lee2@amd.com>
Date: Tue, 2 Jan 2024 12:02:39 -0500
Subject: [PATCH 3434/4076] drm/amd/display: Add Replay IPS register for DMUB
 command table

- Introduce a new Replay mode for DMUB version 0.0.199.0

Reviewed-by: Martin Leung <martin.leung@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index c64b6c848ef72..bcd3c361cca5e 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -2832,6 +2832,7 @@ struct dmub_rb_cmd_psr_set_power_opt {
 #define REPLAY_RESIDENCY_MODE_MASK             (0x1 << REPLAY_RESIDENCY_MODE_SHIFT)
 # define REPLAY_RESIDENCY_MODE_PHY             (0x0 << REPLAY_RESIDENCY_MODE_SHIFT)
 # define REPLAY_RESIDENCY_MODE_ALPM            (0x1 << REPLAY_RESIDENCY_MODE_SHIFT)
+# define REPLAY_RESIDENCY_MODE_IPS             0x10
 
 #define REPLAY_RESIDENCY_ENABLE_MASK           (0x1 << REPLAY_RESIDENCY_ENABLE_SHIFT)
 # define REPLAY_RESIDENCY_DISABLE              (0x0 << REPLAY_RESIDENCY_ENABLE_SHIFT)
-- 
GitLab


From 196107eb1e1557df25e1425bbfb53e0f7588b80a Mon Sep 17 00:00:00 2001
From: Roman Li <roman.li@amd.com>
Date: Tue, 9 Jan 2024 17:31:33 -0500
Subject: [PATCH 3435/4076] drm/amd/display: Add IPS checks before dcn register
 access

[Why]
With IPS enabled a system hangs once PSR is active.
PSR active triggers transition to IPS2 state.
While in IPS2 an access to dcn registers results in hard hang.
Existing check doesn't cover for PSR sequence.

[How]
Safeguard register access by disabling idle optimization in atomic commit
and crtc scanout. It will be re-enabled on next vblank.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Roman Li <roman.li@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c    | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 5552d30a6d971..d8f85df2bc660 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -272,6 +272,7 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 {
 	u32 v_blank_start, v_blank_end, h_position, v_position;
 	struct amdgpu_crtc *acrtc = NULL;
+	struct dc *dc = adev->dm.dc;
 
 	if ((crtc < 0) || (crtc >= adev->mode_info.num_crtc))
 		return -EINVAL;
@@ -284,6 +285,9 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 		return 0;
 	}
 
+	if (dc && dc->caps.ips_support && dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dc, false);
+
 	/*
 	 * TODO rework base driver to use values directly.
 	 * for now parse it back into reg-format
@@ -8978,16 +8982,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	trace_amdgpu_dm_atomic_commit_tail_begin(state);
 
-	if (dm->dc->caps.ips_support) {
-		for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
-			if (new_con_state->crtc &&
-				new_con_state->crtc->state->active &&
-				drm_atomic_crtc_needs_modeset(new_con_state->crtc->state)) {
-				dc_dmub_srv_apply_idle_power_optimizations(dm->dc, false);
-				break;
-			}
-		}
-	}
+	if (dm->dc->caps.ips_support && dm->dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dm->dc, false);
 
 	drm_atomic_helper_update_legacy_modeset_state(dev, state);
 	drm_dp_mst_atomic_wait_for_dependencies(state);
-- 
GitLab


From f37f7979202d45489d84469838f5352cda3557bc Mon Sep 17 00:00:00 2001
From: ChunTao Tso <chuntao.tso@amd.com>
Date: Mon, 8 Jan 2024 13:46:59 +0800
Subject: [PATCH 3436/4076] drm/amd/display: Replay + IPS + ABM in Full Screen
 VPB

[Why]
Because ABM will wait VStart to start getting histogram data,
 it will cause we can't enter IPS while full screnn video playing.

[How]
Modify the panel refresh rate to the maximun multiple of current
 refresh rate.

Reviewed-by: Dennis Chan <dennis.chan@amd.com>
Acked-by: Roman Li <roman.li@amd.com>
Signed-off-by: ChunTao Tso <chuntao.tso@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_types.h     |  5 ++
 .../gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 46 +++++++++++++++++++
 .../amd/display/modules/power/power_helpers.c |  5 ++
 .../amd/display/modules/power/power_helpers.h |  1 +
 4 files changed, 57 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index b08ccb8c68bc3..9900dda2eef5c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1034,6 +1034,7 @@ enum replay_FW_Message_type {
 	Replay_Msg_Not_Support = -1,
 	Replay_Set_Timing_Sync_Supported,
 	Replay_Set_Residency_Frameupdate_Timer,
+	Replay_Set_Pseudo_VTotal,
 };
 
 union replay_error_status {
@@ -1089,6 +1090,10 @@ struct replay_settings {
 	uint16_t coasting_vtotal_table[PR_COASTING_TYPE_NUM];
 	/* Maximum link off frame count */
 	enum replay_link_off_frame_count_level link_off_frame_count_level;
+	/* Replay pseudo vtotal for abm + ips on full screen video which can improve ips residency */
+	uint16_t abm_with_ips_on_full_screen_video_pseudo_vtotal;
+	/* Replay last pseudo vtotal set to DMUB */
+	uint16_t last_pseudo_vtotal;
 };
 
 /* To split out "global" and "per-panel" config settings.
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index bcd3c361cca5e..e699731ee68e9 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -2895,6 +2895,10 @@ enum dmub_cmd_replay_type {
 	 * Set Residency Frameupdate Timer.
 	 */
 	DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER = 6,
+	/**
+	 * Set pseudo vtotal
+	 */
+	DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL = 7,
 };
 
 /**
@@ -3077,6 +3081,26 @@ struct dmub_cmd_replay_set_timing_sync_data {
 	uint8_t pad[2];
 };
 
+/**
+ * Data passed from driver to FW in a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+ */
+struct dmub_cmd_replay_set_pseudo_vtotal {
+	/**
+	 * Panel Instance.
+	 * Panel isntance to identify which replay_state to use
+	 * Currently the support is only for 0 or 1
+	 */
+	uint8_t panel_inst;
+	/**
+	 * Source Vtotal that Replay + IPS + ABM full screen video src vtotal
+	 */
+	uint16_t vtotal;
+	/**
+	 * Explicit padding to 4 byte boundary.
+	 */
+	uint8_t pad;
+};
+
 /**
  * Definition of a DMUB_CMD__SET_REPLAY_POWER_OPT command.
  */
@@ -3157,6 +3181,20 @@ struct dmub_rb_cmd_replay_set_timing_sync {
 	struct dmub_cmd_replay_set_timing_sync_data replay_set_timing_sync_data;
 };
 
+/**
+ * Definition of a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+ */
+struct dmub_rb_cmd_replay_set_pseudo_vtotal {
+	/**
+	 * Command header.
+	 */
+	struct dmub_cmd_header header;
+	/**
+	 * Definition of DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+	 */
+	struct dmub_cmd_replay_set_pseudo_vtotal data;
+};
+
 /**
  * Data passed from driver to FW in  DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command.
  */
@@ -3208,6 +3246,10 @@ union dmub_replay_cmd_set {
 	 * Definition of DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command data.
 	 */
 	struct dmub_cmd_replay_frameupdate_timer_data timer_data;
+	/**
+	 * Definition of DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command data.
+	 */
+	struct dmub_cmd_replay_set_pseudo_vtotal pseudo_vtotal_data;
 };
 
 /**
@@ -4359,6 +4401,10 @@ union dmub_rb_cmd {
 	 * Definition of a DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command.
 	 */
 	struct dmub_rb_cmd_replay_set_frameupdate_timer replay_set_frameupdate_timer;
+	/**
+	 * Definition of a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+	 */
+	struct dmub_rb_cmd_replay_set_pseudo_vtotal replay_set_pseudo_vtotal;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index ad98e504c00de..e304e8435fb8f 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -980,6 +980,11 @@ void set_replay_coasting_vtotal(struct dc_link *link,
 	link->replay_settings.coasting_vtotal_table[type] = vtotal;
 }
 
+void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal)
+{
+	link->replay_settings.abm_with_ips_on_full_screen_video_pseudo_vtotal = vtotal;
+}
+
 void calculate_replay_link_off_frame_count(struct dc_link *link,
 	uint16_t vtotal, uint16_t htotal)
 {
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
index c17bbc6fb38ca..bef4815e1703d 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
@@ -57,6 +57,7 @@ void init_replay_config(struct dc_link *link, struct replay_config *pr_config);
 void set_replay_coasting_vtotal(struct dc_link *link,
 	enum replay_coasting_vtotal_type type,
 	uint16_t vtotal);
+void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal);
 void calculate_replay_link_off_frame_count(struct dc_link *link,
 	uint16_t vtotal, uint16_t htotal);
 
-- 
GitLab


From 8894b9283afd35b8d22ae07a0c118eb5f7d2e78b Mon Sep 17 00:00:00 2001
From: Roman Li <Roman.Li@amd.com>
Date: Mon, 22 Jan 2024 17:45:41 -0500
Subject: [PATCH 3437/4076] drm/amd/display: Disable ips before dc interrupt
 setting

[Why]
While in IPS2 an access to dcn registers is not allowed.
If interrupt results in dc call, we should disable IPS.

[How]
Safeguard register access in IPS2 by disabling idle optimization
before calling dc interrupt setting api.

Signed-off-by: Roman Li <Roman.Li@amd.com>
Tested-by: Mark Broadworth <mark.broadworth@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 58b880acb087a..3390f0d8420a0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -711,7 +711,7 @@ static inline int dm_irq_state(struct amdgpu_device *adev,
 {
 	bool st;
 	enum dc_irq_source irq_source;
-
+	struct dc *dc = adev->dm.dc;
 	struct amdgpu_crtc *acrtc = adev->mode_info.crtcs[crtc_id];
 
 	if (!acrtc) {
@@ -729,6 +729,9 @@ static inline int dm_irq_state(struct amdgpu_device *adev,
 
 	st = (state == AMDGPU_IRQ_STATE_ENABLE);
 
+	if (dc && dc->caps.ips_support && dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dc, false);
+
 	dc_interrupt_set(adev->dm.dc, irq_source, st);
 	return 0;
 }
-- 
GitLab


From d45669eb5e68c052d0d890cd88c33a65c115d9f3 Mon Sep 17 00:00:00 2001
From: Roman Li <Roman.Li@amd.com>
Date: Tue, 23 Jan 2024 15:14:28 -0500
Subject: [PATCH 3438/4076] drm/amd: Add a DC debug mask for IPS

For debugging IPS-related issues, expose a new debug mask
that allows to disable IPS.
Usage:
amdgpu.dcdebugmask=0x800

Signed-off-by: Roman Li <Roman.Li@amd.com>
Tested-by: Mark Broadworth <mark.broadworth@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/amd_shared.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 1dc5dd9b7bf70..df2c7ffe190f4 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -258,6 +258,7 @@ enum DC_DEBUG_MASK {
 	DC_ENABLE_DML2 = 0x100,
 	DC_DISABLE_PSR_SU = 0x200,
 	DC_DISABLE_REPLAY = 0x400,
+	DC_DISABLE_IPS = 0x800,
 };
 
 enum amd_dpm_forced_level;
-- 
GitLab


From c82eb25c5f005b33aebb1415a8472fc2eeea0deb Mon Sep 17 00:00:00 2001
From: Roman Li <Roman.Li@amd.com>
Date: Tue, 23 Jan 2024 15:18:24 -0500
Subject: [PATCH 3439/4076] drm/amd/display: "Enable IPS by default"

[Why]
IPS was temporary disabled due to instability.
It was fixed in dmub firmware and with:
- "drm/amd/display: Add IPS checks before dcn register access"
- "drm/amd/display: Disable ips before dc interrupt setting"

[How]
Enable IPS by default.
Disable IPS if 0x800 bit set in amdgpu.dcdebugmask module params

Signed-off-by: Roman Li <Roman.Li@amd.com>
Tested-by: Mark Broadworth <mark.broadworth@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d8f85df2bc660..6cda5b5363626 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1719,7 +1719,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	init_data.nbio_reg_offsets = adev->reg_offset[NBIO_HWIP][0];
 	init_data.clk_reg_offsets = adev->reg_offset[CLK_HWIP][0];
 
-	init_data.flags.disable_ips = DMUB_IPS_DISABLE_ALL;
+	if (amdgpu_dc_debug_mask & DC_DISABLE_IPS)
+		init_data.flags.disable_ips = DMUB_IPS_DISABLE_ALL;
 
 	init_data.flags.disable_ips_in_vpb = 1;
 
-- 
GitLab


From 8c2ae772fe08e33f3d7a83849e85539320701abd Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Thu, 25 Jan 2024 14:53:09 -0600
Subject: [PATCH 3440/4076] spi: fix finalize message on error return

In __spi_pump_transfer_message(), the message was not finalized in the
first error return as it is in the other error return paths. Not
finalizing the message could cause anything waiting on the message to
complete to hang forever.

This adds the missing call to spi_finalize_current_message().

Fixes: ae7d2346dc89 ("spi: Don't use the message queue if possible in spi_sync")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Link: https://msgid.link/r/20240125205312.3458541-2-dlechner@baylibre.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 7477a11e12be0..f2170f4b50775 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1717,6 +1717,10 @@ static int __spi_pump_transfer_message(struct spi_controller *ctlr,
 			pm_runtime_put_noidle(ctlr->dev.parent);
 			dev_err(&ctlr->dev, "Failed to power device: %d\n",
 				ret);
+
+			msg->status = ret;
+			spi_finalize_current_message(ctlr);
+
 			return ret;
 		}
 	}
-- 
GitLab


From 8d35217149daa33358c284aca6a56d5ab92cfc6c Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 15 Dec 2023 03:32:22 +0200
Subject: [PATCH 3441/4076] drm/msm/mdss: specify cfg bandwidth for SDM670

Lower the requested CFG bus bandwidth for the SDM670 platform. The
default value is 153600 kBps, which is twice as big as required by the
platform according to the vendor kernel.

Fixes: a55c8ff252d3 ("drm/msm/mdss: Handle the reg bus ICC path")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Tested-by: Richard Acayan <mailingradian@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/572182/
Link: https://lore.kernel.org/r/20231215013222.827975-1-dmitry.baryshkov@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/msm_mdss.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 455b2e3a0cdd4..35423d10aafa9 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -562,6 +562,7 @@ static const struct msm_mdss_data sdm670_data = {
 	.ubwc_enc_version = UBWC_2_0,
 	.ubwc_dec_version = UBWC_2_0,
 	.highest_bank_bit = 1,
+	.reg_bus_bw = 76800,
 };
 
 static const struct msm_mdss_data sdm845_data = {
-- 
GitLab


From b64787840080bdbd048bb9c68222ad17236cbd7e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 24 Jan 2024 11:25:50 -0800
Subject: [PATCH 3442/4076] selftests: tcp_ao: add a config file

Still a bit unclear whether each directory should have its own
config file, but assuming they should lets add one for tcp_ao.

The following tests still fail with this config in place:
 - rst_ipv4,
 - rst_ipv6,
 - bench-lookups_ipv6.
other 21 pass.

Fixes: d11301f65977 ("selftests/net: Add TCP-AO ICMPs accept test")
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://lore.kernel.org/r/20240124192550.1865743-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/config | 10 ++++++++++
 1 file changed, 10 insertions(+)
 create mode 100644 tools/testing/selftests/net/tcp_ao/config

diff --git a/tools/testing/selftests/net/tcp_ao/config b/tools/testing/selftests/net/tcp_ao/config
new file mode 100644
index 0000000000000..d3277a9de987c
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/config
@@ -0,0 +1,10 @@
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_RMD160=y
+CONFIG_CRYPTO_SHA1=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=y
+CONFIG_TCP_AO=y
+CONFIG_TCP_MD5SIG=y
+CONFIG_VETH=m
-- 
GitLab


From 98cb12eb52a780e682bea8372fdb2912c08132dd Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 24 Jan 2024 22:33:20 +0100
Subject: [PATCH 3443/4076] selftests: net: remove dependency on ebpf tests

Several net tests requires an XDP program build under the ebpf
directory, and error out if such program is not available.

That makes running successful net test hard, let's duplicate into the
net dir the [very small] program, re-using the existing rules to build
it, and finally dropping the bogus dependency.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/28e7af7c031557f691dc8045ee41dd549dd5e74c.1706131762.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile          |  5 +++--
 tools/testing/selftests/net/udpgro.sh         |  4 ++--
 tools/testing/selftests/net/udpgro_bench.sh   |  4 ++--
 tools/testing/selftests/net/udpgro_frglist.sh |  6 +++---
 tools/testing/selftests/net/udpgro_fwd.sh     |  2 +-
 tools/testing/selftests/net/veth.sh           |  4 ++--
 tools/testing/selftests/net/xdp_dummy.c       | 13 +++++++++++++
 7 files changed, 26 insertions(+), 12 deletions(-)
 create mode 100644 tools/testing/selftests/net/xdp_dummy.c

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 50818075e566e..304d8b852ef05 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -84,6 +84,7 @@ TEST_PROGS += sctp_vrf.sh
 TEST_GEN_FILES += sctp_hello
 TEST_GEN_FILES += csum
 TEST_GEN_FILES += nat6to4.o
+TEST_GEN_FILES += xdp_dummy.o
 TEST_GEN_FILES += ip_local_port_range
 TEST_GEN_FILES += bind_wildcard
 TEST_PROGS += test_vxlan_mdb.sh
@@ -104,7 +105,7 @@ $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
 $(OUTPUT)/bind_bhash: LDLIBS += -lpthread
 $(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/
 
-# Rules to generate bpf obj nat6to4.o
+# Rules to generate bpf objs
 CLANG ?= clang
 SCRATCH_DIR := $(OUTPUT)/tools
 BUILD_DIR := $(SCRATCH_DIR)/build
@@ -139,7 +140,7 @@ endif
 
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 
-$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS)
+$(OUTPUT)/nat6to4.o $(OUTPUT)/xdp_dummy.o: $(OUTPUT)/%.o : %.c $(BPFOBJ) | $(MAKE_DIRS)
 	$(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index af5dc57c8ce93..8802604148dda 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 # set global exit status, but never reset nonzero one.
 check_err()
@@ -197,7 +197,7 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index cb664679b4342..7080eae5312b2 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 cleanup() {
 	local -r jobs="$(jobs -p)"
@@ -84,7 +84,7 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index dd47fa96f6b3e..e1ff645bd3d1c 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 cleanup() {
 	local -r jobs="$(jobs -p)"
@@ -85,12 +85,12 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
 if [ ! -f nat6to4.o ]; then
-	echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first"
+	echo "Missing nat6to4 helper. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index c079565add392..5fa8659ab13d6 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 readonly BASE="ns-$(mktemp -u XXXXXX)"
 readonly SRC=2
 readonly DST=1
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 2d073595c6202..27574bbf2d638 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
 readonly BASE=`basename $STATS`
 readonly SRC=2
@@ -218,7 +218,7 @@ while getopts "hs:" option; do
 done
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit 1
 fi
 
diff --git a/tools/testing/selftests/net/xdp_dummy.c b/tools/testing/selftests/net/xdp_dummy.c
new file mode 100644
index 0000000000000..d988b2e0cee84
--- /dev/null
+++ b/tools/testing/selftests/net/xdp_dummy.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
GitLab


From f5173fe3e13b2cbd25d0d73f40acd923d75add55 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 24 Jan 2024 22:33:21 +0100
Subject: [PATCH 3444/4076] selftests: net: included needed helper in the
 install targets

The blamed commit below introduce a dependency in some net self-tests
towards a newly introduce helper script.

Such script is currently not included into the TEST_PROGS_EXTENDED list
and thus is not installed, causing failure for the relevant tests when
executed from the install dir.

Fix the issue updating the install targets.

Fixes: 3bdd9fd29cb0 ("selftests/net: synchronize udpgro tests' tx and rx connection")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/076e8758e21ff2061cc9f81640e7858df775f0a9.1706131762.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 304d8b852ef05..48c6f93b81498 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -55,6 +55,7 @@ TEST_PROGS += rps_default_mask.sh
 TEST_PROGS += big_tcp.sh
 TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
 TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh lib.sh
+TEST_PROGS_EXTENDED += net_helper.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
-- 
GitLab


From 4acffb66630a0e4800880baa61a54ef18047ccd3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 24 Jan 2024 22:33:22 +0100
Subject: [PATCH 3445/4076] selftests: net: explicitly wait for listener ready

The UDP GRO forwarding test still hard-code an arbitrary pause
to wait for the UDP listener becoming ready in background.

That causes sporadic failures depending on the host load.

Replace the sleep with the existing helper waiting for the desired
port being exposed.

Fixes: a062260a9d5f ("selftests: net: add UDP GRO forwarding self-tests")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/4d58900fb09cef42749cfcf2ad7f4b91a97d225c.1706131762.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/udpgro_fwd.sh | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 5fa8659ab13d6..d6b9c759043ca 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,6 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+source net_helper.sh
+
 BPF_FILE="xdp_dummy.o"
 readonly BASE="ns-$(mktemp -u XXXXXX)"
 readonly SRC=2
@@ -119,7 +121,7 @@ run_test() {
 	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
 	ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
 	local spid=$!
-	sleep 0.1
+	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
 	local retc=$?
 	wait $spid
@@ -168,7 +170,7 @@ run_bench() {
 	ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
 	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10  &
 	local spid=$!
-	sleep 0.1
+	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
 	local retc=$?
 	wait $spid
-- 
GitLab


From 39b383d77961a544d896242051168b8129cf5be7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 24 Jan 2024 15:36:30 -0800
Subject: [PATCH 3446/4076] selftests: tcp_ao: set the timeout to 2 minutes

The default timeout for tests is 45sec, bench-lookups_ipv6
seems to take around 50sec when running in a VM without
HW acceleration. Give it a 2x margin and set the timeout
to 120sec.

Fixes: d1066c9c58d4 ("selftests/net: Add test/benchmark for removing MKTs")
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://lore.kernel.org/r/20240124233630.1977708-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/settings | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 tools/testing/selftests/net/tcp_ao/settings

diff --git a/tools/testing/selftests/net/tcp_ao/settings b/tools/testing/selftests/net/tcp_ao/settings
new file mode 100644
index 0000000000000..6091b45d226ba
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/settings
@@ -0,0 +1 @@
+timeout=120
-- 
GitLab


From d2fda304bb739b97c1a3e46e39700eb49f07a62c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 24 Jan 2024 17:26:33 -0500
Subject: [PATCH 3447/4076] bcachefs: __lookup_dirent() works in snapshot, not
 subvol

Add a new helper, bch2_hash_lookup_in_snapshot(), for when we're not
operating in a subvolume and already have a snapshot ID, and then use it
in lookup_lostfound() -> __lookup_dirent().

This is a bugfix - lookup_lostfound() doesn't take a subvolume ID, we
were passing a nonsense subvolume ID before, and don't have one to pass
since we may be operating in an interior snapshot node that doesn't have
a subvolume ID.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c     | 23 ++++++++++++-----------
 fs/bcachefs/str_hash.h | 22 +++++++++++++++-------
 2 files changed, 27 insertions(+), 18 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 4f0ecd6056757..6a760777bafb0 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -119,22 +119,19 @@ static int lookup_inode(struct btree_trans *trans, u64 inode_nr,
 	if (!ret)
 		*snapshot = iter.pos.snapshot;
 err:
-	bch_err_msg(trans->c, ret, "fetching inode %llu:%u", inode_nr, *snapshot);
 	bch2_trans_iter_exit(trans, &iter);
 	return ret;
 }
 
-static int __lookup_dirent(struct btree_trans *trans,
+static int lookup_dirent_in_snapshot(struct btree_trans *trans,
 			   struct bch_hash_info hash_info,
 			   subvol_inum dir, struct qstr *name,
-			   u64 *target, unsigned *type)
+			   u64 *target, unsigned *type, u32 snapshot)
 {
 	struct btree_iter iter;
 	struct bkey_s_c_dirent d;
-	int ret;
-
-	ret = bch2_hash_lookup(trans, &iter, bch2_dirent_hash_desc,
-			       &hash_info, dir, name, 0);
+	int ret = bch2_hash_lookup_in_snapshot(trans, &iter, bch2_dirent_hash_desc,
+			       &hash_info, dir, name, 0, snapshot);
 	if (ret)
 		return ret;
 
@@ -225,15 +222,16 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
 
 	struct bch_inode_unpacked root_inode;
 	struct bch_hash_info root_hash_info;
-	ret = lookup_inode(trans, root_inum.inum, &root_inode, &snapshot);
+	u32 root_inode_snapshot = snapshot;
+	ret = lookup_inode(trans, root_inum.inum, &root_inode, &root_inode_snapshot);
 	bch_err_msg(c, ret, "looking up root inode");
 	if (ret)
 		return ret;
 
 	root_hash_info = bch2_hash_info_init(c, &root_inode);
 
-	ret = __lookup_dirent(trans, root_hash_info, root_inum,
-			      &lostfound_str, &inum, &d_type);
+	ret = lookup_dirent_in_snapshot(trans, root_hash_info, root_inum,
+			      &lostfound_str, &inum, &d_type, snapshot);
 	if (bch2_err_matches(ret, ENOENT))
 		goto create_lostfound;
 
@@ -250,7 +248,10 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
 	 * The bch2_check_dirents pass has already run, dangling dirents
 	 * shouldn't exist here:
 	 */
-	return lookup_inode(trans, inum, lostfound, &snapshot);
+	ret = lookup_inode(trans, inum, lostfound, &snapshot);
+	bch_err_msg(c, ret, "looking up lost+found %llu:%u in (root inode %llu, snapshot root %u)",
+		    inum, snapshot, root_inum.inum, bch2_snapshot_root(c, snapshot));
+	return ret;
 
 create_lostfound:
 	/*
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index 89fdb7c21134e..fcaa5a8887448 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -160,21 +160,16 @@ static inline bool is_visible_key(struct bch_hash_desc desc, subvol_inum inum, s
 }
 
 static __always_inline int
-bch2_hash_lookup(struct btree_trans *trans,
+bch2_hash_lookup_in_snapshot(struct btree_trans *trans,
 		 struct btree_iter *iter,
 		 const struct bch_hash_desc desc,
 		 const struct bch_hash_info *info,
 		 subvol_inum inum, const void *key,
-		 unsigned flags)
+		 unsigned flags, u32 snapshot)
 {
 	struct bkey_s_c k;
-	u32 snapshot;
 	int ret;
 
-	ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot);
-	if (ret)
-		return ret;
-
 	for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id,
 			   SPOS(inum.inum, desc.hash_key(info, key), snapshot),
 			   POS(inum.inum, U64_MAX),
@@ -194,6 +189,19 @@ bch2_hash_lookup(struct btree_trans *trans,
 	return ret ?: -BCH_ERR_ENOENT_str_hash_lookup;
 }
 
+static __always_inline int
+bch2_hash_lookup(struct btree_trans *trans,
+		 struct btree_iter *iter,
+		 const struct bch_hash_desc desc,
+		 const struct bch_hash_info *info,
+		 subvol_inum inum, const void *key,
+		 unsigned flags)
+{
+	u32 snapshot;
+	return  bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot) ?:
+		bch2_hash_lookup_in_snapshot(trans, iter, desc, info, inum, key, flags, snapshot);
+}
+
 static __always_inline int
 bch2_hash_hole(struct btree_trans *trans,
 	       struct btree_iter *iter,
-- 
GitLab


From fc836129f708407502632107e58d48f54b1caf75 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 24 Jan 2024 14:13:44 +0800
Subject: [PATCH 3448/4076] selftests/net/lib: update busywait timeout value

The busywait timeout value is a millisecond, not a second. So the
current setting 2 is too small. On slow/busy host (or VMs) the
current timeout can expire even on "correct" execution, causing random
failures. Let's copy the WAIT_TIMEOUT from forwarding/lib.sh and set
BUSYWAIT_TIMEOUT here.

Fixes: 25ae948b4478 ("selftests/net: add lib.sh")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240124061344.1864484-1-liuhangbin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index dca5494438011..f9fe182dfbd44 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -4,6 +4,9 @@
 ##############################################################################
 # Defines
 
+WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
+BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms
+
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 # namespace list created by setup_ns
@@ -48,7 +51,7 @@ cleanup_ns()
 
 	for ns in "$@"; do
 		ip netns delete "${ns}" &> /dev/null
-		if ! busywait 2 ip netns list \| grep -vq "^$ns$" &> /dev/null; then
+		if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
 			echo "Warn: Failed to remove namespace $ns"
 			ret=1
 		fi
-- 
GitLab


From 534326711000c318fe1523c77308450522baa499 Mon Sep 17 00:00:00 2001
From: Praveen Kaligineedi <pkaligineedi@google.com>
Date: Wed, 24 Jan 2024 08:10:25 -0800
Subject: [PATCH 3449/4076] gve: Fix skb truesize underestimation

For a skb frag with a newly allocated copy page, the true size is
incorrectly set to packet buffer size. It should be set to PAGE_SIZE
instead.

Fixes: 82fd151d38d9 ("gve: Reduce alloc and copy costs in the GQ rx path")
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Link: https://lore.kernel.org/r/20240124161025.1819836-1-pkaligineedi@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve_rx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 7a8dc5386ffff..76615d47e055a 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -356,7 +356,7 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags)
 
 static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 					struct gve_rx_slot_page_info *page_info,
-					u16 packet_buffer_size, u16 len,
+					unsigned int truesize, u16 len,
 					struct gve_rx_ctx *ctx)
 {
 	u32 offset = page_info->page_offset + page_info->pad;
@@ -389,10 +389,10 @@ static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 	if (skb != ctx->skb_head) {
 		ctx->skb_head->len += len;
 		ctx->skb_head->data_len += len;
-		ctx->skb_head->truesize += packet_buffer_size;
+		ctx->skb_head->truesize += truesize;
 	}
 	skb_add_rx_frag(skb, num_frags, page_info->page,
-			offset, len, packet_buffer_size);
+			offset, len, truesize);
 
 	return ctx->skb_head;
 }
@@ -486,7 +486,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx,
 
 		memcpy(alloc_page_info.page_address, src, page_info->pad + len);
 		skb = gve_rx_add_frags(napi, &alloc_page_info,
-				       rx->packet_buffer_size,
+				       PAGE_SIZE,
 				       len, ctx);
 
 		u64_stats_update_begin(&rx->statss);
-- 
GitLab


From cefa98e806fd4e2a5e2047457a11ae5f17b8f621 Mon Sep 17 00:00:00 2001
From: Hui Zhou <hui.zhou@corigine.com>
Date: Wed, 24 Jan 2024 17:19:08 +0200
Subject: [PATCH 3450/4076] nfp: flower: add hardware offload check for post ct
 entry

The nfp offload flow pay will not allocate a mask id when the out port
is openvswitch internal port. This is because these flows are used to
configure the pre_tun table and are never actually send to the firmware
as an add-flow message. When a tc rule which action contains ct and
the post ct entry's out port is openvswitch internal port, the merge
offload flow pay with the wrong mask id of 0 will be send to the
firmware. Actually, the nfp can not support hardware offload for this
situation, so return EOPNOTSUPP.

Fixes: bd0fe7f96a3c ("nfp: flower-ct: add zone table entry when handling pre/post_ct flows")
CC: stable@vger.kernel.org # 5.14+
Signed-off-by: Hui Zhou <hui.zhou@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Link: https://lore.kernel.org/r/20240124151909.31603-2-louis.peens@corigine.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/netronome/nfp/flower/conntrack.c | 22 ++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
index 2967bab725056..726d8cdf0b9cf 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
@@ -1864,10 +1864,30 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	struct nfp_fl_ct_flow_entry *ct_entry;
+	struct flow_action_entry *ct_goto;
 	struct nfp_fl_ct_zone_entry *zt;
+	struct flow_action_entry *act;
 	bool wildcarded = false;
 	struct flow_match_ct ct;
-	struct flow_action_entry *ct_goto;
+	int i;
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_REDIRECT:
+		case FLOW_ACTION_REDIRECT_INGRESS:
+		case FLOW_ACTION_MIRRED:
+		case FLOW_ACTION_MIRRED_INGRESS:
+			if (act->dev->rtnl_link_ops &&
+			    !strcmp(act->dev->rtnl_link_ops->kind, "openvswitch")) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "unsupported offload: out port is openvswitch internal port");
+				return -EOPNOTSUPP;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	flow_rule_match_ct(rule, &ct);
 	if (!ct.mask->ct_zone) {
-- 
GitLab


From 3a007b8009b5f8af021021b7a590a6da0dc4c6e0 Mon Sep 17 00:00:00 2001
From: Hui Zhou <hui.zhou@corigine.com>
Date: Wed, 24 Jan 2024 17:19:09 +0200
Subject: [PATCH 3451/4076] nfp: flower: fix hardware offload for the transfer
 layer port

The nfp driver will merge the tp source port and tp destination port
into one dword which the offset must be zero to do hardware offload.
However, the mangle action for the tp source port and tp destination
port is separated for tc ct action. Modify the mangle action for the
FLOW_ACT_MANGLE_HDR_TYPE_TCP and FLOW_ACT_MANGLE_HDR_TYPE_UDP to
satisfy the nfp driver offload check for the tp port.

The mangle action provides a 4B value for source, and a 4B value for
the destination, but only 2B of each contains the useful information.
For offload the 2B of each is combined into a single 4B word. Since the
incoming mask for the source is '0xFFFF<mask>' the shift-left will
throw away the 0xFFFF part. When this gets combined together in the
offload it will clear the destination field. Fix this by setting the
lower bits back to 0xFFFF, effectively doing a rotate-left operation on
the mask.

Fixes: 5cee92c6f57a ("nfp: flower: support hw offload for ct nat action")
CC: stable@vger.kernel.org # 6.1+
Signed-off-by: Hui Zhou <hui.zhou@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Link: https://lore.kernel.org/r/20240124151909.31603-3-louis.peens@corigine.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/netronome/nfp/flower/conntrack.c | 24 +++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
index 726d8cdf0b9cf..15180538b80a1 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
@@ -1424,10 +1424,30 @@ static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_
 		mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask);
 		return;
 
+	/* Both struct tcphdr and struct udphdr start with
+	 *	__be16 source;
+	 *	__be16 dest;
+	 * so we can use the same code for both.
+	 */
 	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
 	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
-		mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val);
-		mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask);
+		if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) {
+			mangle_action->mangle.val =
+				(__force u32)cpu_to_be32(mangle_action->mangle.val << 16);
+			/* The mask of mangle action is inverse mask,
+			 * so clear the dest tp port with 0xFFFF to
+			 * instead of rotate-left operation.
+			 */
+			mangle_action->mangle.mask =
+				(__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF);
+		}
+		if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) {
+			mangle_action->mangle.offset = 0;
+			mangle_action->mangle.val =
+				(__force u32)cpu_to_be32(mangle_action->mangle.val);
+			mangle_action->mangle.mask =
+				(__force u32)cpu_to_be32(mangle_action->mangle.mask);
+		}
 		return;
 
 	default:
-- 
GitLab


From cae1f1c36661f28c92a1db9113961a9ebd61dbaa Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Wed, 24 Jan 2024 16:22:09 +0000
Subject: [PATCH 3452/4076] net: ethernet: mtk_eth_soc: set DMA coherent mask
 to get PPE working

Set DMA coherent mask to 32-bit which makes PPE offloading engine start
working on BPi-R4 which got 4 GiB of RAM.

Fixes: 2d75891ebc09 ("net: ethernet: mtk_eth_soc: support 36-bit DMA addressing on MT7988")
Suggested-by: Elad Yifee <eladwf@users.github.com>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/97e90925368b405f0974b9b15f1b7377c4a329ad.1706113251.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index a6e91573f8dae..de123350bd46b 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4761,7 +4761,10 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
-		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36));
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(36));
+		if (!err)
+			err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+
 		if (err) {
 			dev_err(&pdev->dev, "Wrong DMA config\n");
 			return -EINVAL;
-- 
GitLab


From ff63cc2e95065bea978d2db01f7e7356cca3d021 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Wed, 24 Jan 2024 05:18:23 +0000
Subject: [PATCH 3453/4076] net: phy: mediatek-ge-soc: sync driver with
 MediaTek SDK

Sync initialization and calibration routines with MediaTek's reference
driver. Improves compliance and resolves link stability issues with
CH340 IoT devices connected to MT798x built-in PHYs.

Fixes: 98c485eaf509 ("net: phy: add driver for MediaTek SoC built-in GE PHYs")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/f2195279c234c0f618946424b8236026126bc595.1706071311.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mediatek-ge-soc.c | 147 ++++++++++++++++--------------
 1 file changed, 81 insertions(+), 66 deletions(-)

diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c
index 8a20d9889f105..0f3a1538a8b8e 100644
--- a/drivers/net/phy/mediatek-ge-soc.c
+++ b/drivers/net/phy/mediatek-ge-soc.c
@@ -489,7 +489,7 @@ static int tx_r50_fill_result(struct phy_device *phydev, u16 tx_r50_cal_val,
 	u16 reg, val;
 
 	if (phydev->drv->phy_id == MTK_GPHY_ID_MT7988)
-		bias = -2;
+		bias = -1;
 
 	val = clamp_val(bias + tx_r50_cal_val, 0, 63);
 
@@ -705,6 +705,11 @@ restore:
 static void mt798x_phy_common_finetune(struct phy_device *phydev)
 {
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
+	__phy_write(phydev, 0x11, 0xc71);
+	__phy_write(phydev, 0x12, 0xc);
+	__phy_write(phydev, 0x10, 0x8fae);
+
 	/* EnabRandUpdTrig = 1 */
 	__phy_write(phydev, 0x11, 0x2f00);
 	__phy_write(phydev, 0x12, 0xe);
@@ -715,15 +720,56 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x83aa);
 
-	/* TrFreeze = 0 */
+	/* FfeUpdGainForce = 1(Enable), FfeUpdGainForceVal = 4 */
+	__phy_write(phydev, 0x11, 0x240);
+	__phy_write(phydev, 0x12, 0x0);
+	__phy_write(phydev, 0x10, 0x9680);
+
+	/* TrFreeze = 0 (mt7988 default) */
 	__phy_write(phydev, 0x11, 0x0);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9686);
 
+	/* SSTrKp100 = 5 */
+	/* SSTrKf100 = 6 */
+	/* SSTrKp1000Mas = 5 */
+	/* SSTrKf1000Mas = 6 */
 	/* SSTrKp1000Slv = 5 */
+	/* SSTrKf1000Slv = 6 */
 	__phy_write(phydev, 0x11, 0xbaef);
 	__phy_write(phydev, 0x12, 0x2e);
 	__phy_write(phydev, 0x10, 0x968c);
+	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+}
+
+static void mt7981_phy_finetune(struct phy_device *phydev)
+{
+	u16 val[8] = { 0x01ce, 0x01c1,
+		       0x020f, 0x0202,
+		       0x03d0, 0x03c0,
+		       0x0013, 0x0005 };
+	int i, k;
+
+	/* 100M eye finetune:
+	 * Keep middle level of TX MLT3 shapper as default.
+	 * Only change TX MLT3 overshoot level here.
+	 */
+	for (k = 0, i = 1; i < 12; i++) {
+		if (i % 3 == 0)
+			continue;
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]);
+	}
+
+	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	/* ResetSyncOffset = 6 */
+	__phy_write(phydev, 0x11, 0x600);
+	__phy_write(phydev, 0x12, 0x0);
+	__phy_write(phydev, 0x10, 0x8fc0);
+
+	/* VgaDecRate = 1 */
+	__phy_write(phydev, 0x11, 0x4c2a);
+	__phy_write(phydev, 0x12, 0x3e);
+	__phy_write(phydev, 0x10, 0x8fa4);
 
 	/* MrvlTrFix100Kp = 3, MrvlTrFix100Kf = 2,
 	 * MrvlTrFix1000Kp = 3, MrvlTrFix1000Kf = 2
@@ -738,7 +784,7 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	__phy_write(phydev, 0x10, 0x8ec0);
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
-	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9*/
+	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9 */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234,
 		       MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK,
 		       BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0x9));
@@ -771,48 +817,6 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_LDO_OUTPUT_V, 0x2222);
 }
 
-static void mt7981_phy_finetune(struct phy_device *phydev)
-{
-	u16 val[8] = { 0x01ce, 0x01c1,
-		       0x020f, 0x0202,
-		       0x03d0, 0x03c0,
-		       0x0013, 0x0005 };
-	int i, k;
-
-	/* 100M eye finetune:
-	 * Keep middle level of TX MLT3 shapper as default.
-	 * Only change TX MLT3 overshoot level here.
-	 */
-	for (k = 0, i = 1; i < 12; i++) {
-		if (i % 3 == 0)
-			continue;
-		phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]);
-	}
-
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
-	__phy_write(phydev, 0x11, 0xc71);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
-
-	/* ResetSyncOffset = 6 */
-	__phy_write(phydev, 0x11, 0x600);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x8fc0);
-
-	/* VgaDecRate = 1 */
-	__phy_write(phydev, 0x11, 0x4c2a);
-	__phy_write(phydev, 0x12, 0x3e);
-	__phy_write(phydev, 0x10, 0x8fa4);
-
-	/* FfeUpdGainForce = 4 */
-	__phy_write(phydev, 0x11, 0x240);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x9680);
-
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
-}
-
 static void mt7988_phy_finetune(struct phy_device *phydev)
 {
 	u16 val[12] = { 0x0187, 0x01cd, 0x01c8, 0x0182,
@@ -827,17 +831,7 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 	/* TCT finetune */
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_TX_FILTER, 0x5);
 
-	/* Disable TX power saving */
-	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
-		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8);
-
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 12 */
-	__phy_write(phydev, 0x11, 0x671);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
-
 	/* ResetSyncOffset = 5 */
 	__phy_write(phydev, 0x11, 0x500);
 	__phy_write(phydev, 0x12, 0x0);
@@ -845,13 +839,27 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 
 	/* VgaDecRate is 1 at default on mt7988 */
 
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+	/* MrvlTrFix100Kp = 6, MrvlTrFix100Kf = 7,
+	 * MrvlTrFix1000Kp = 6, MrvlTrFix1000Kf = 7
+	 */
+	__phy_write(phydev, 0x11, 0xb90a);
+	__phy_write(phydev, 0x12, 0x6f);
+	__phy_write(phydev, 0x10, 0x8f82);
+
+	/* RemAckCntLimitCtrl = 1 */
+	__phy_write(phydev, 0x11, 0xfbba);
+	__phy_write(phydev, 0x12, 0xc3);
+	__phy_write(phydev, 0x10, 0x87f8);
 
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_2A30);
-	/* TxClkOffset = 2 */
-	__phy_modify(phydev, MTK_PHY_ANARG_RG, MTK_PHY_TCLKOFFSET_MASK,
-		     FIELD_PREP(MTK_PHY_TCLKOFFSET_MASK, 0x2));
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+
+	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 10 */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234,
+		       MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK,
+		       BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0xa));
+
+	/* rg_tr_lpf_cnt_val = 1023 */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_LPF_CNT_VAL, 0x3ff);
 }
 
 static void mt798x_phy_eee(struct phy_device *phydev)
@@ -884,11 +892,11 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 		       MTK_PHY_LPI_SLV_SEND_TX_EN,
 		       FIELD_PREP(MTK_PHY_LPI_SLV_SEND_TX_TIMER_MASK, 0x120));
 
-	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239,
-		       MTK_PHY_LPI_SEND_LOC_TIMER_MASK |
-		       MTK_PHY_LPI_TXPCS_LOC_RCV,
-		       FIELD_PREP(MTK_PHY_LPI_SEND_LOC_TIMER_MASK, 0x117));
+	/* Keep MTK_PHY_LPI_SEND_LOC_TIMER as 375 */
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239,
+			   MTK_PHY_LPI_TXPCS_LOC_RCV);
 
+	/* This also fixes some IoT issues, such as CH340 */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG2C7,
 		       MTK_PHY_MAX_GAIN_MASK | MTK_PHY_MIN_GAIN_MASK,
 		       FIELD_PREP(MTK_PHY_MAX_GAIN_MASK, 0x8) |
@@ -922,7 +930,7 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9690);
 
-	/* REG_EEE_st2TrKf1000 = 3 */
+	/* REG_EEE_st2TrKf1000 = 2 */
 	__phy_write(phydev, 0x11, 0x114f);
 	__phy_write(phydev, 0x12, 0x2);
 	__phy_write(phydev, 0x10, 0x969a);
@@ -947,7 +955,7 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96b8);
 
-	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 1 */
+	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */
 	__phy_write(phydev, 0x11, 0x1463);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96ca);
@@ -1459,6 +1467,13 @@ static int mt7988_phy_probe(struct phy_device *phydev)
 	if (err)
 		return err;
 
+	/* Disable TX power saving at probing to:
+	 * 1. Meet common mode compliance test criteria
+	 * 2. Make sure that TX-VCM calibration works fine
+	 */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
+		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8);
+
 	return mt798x_phy_calibration(phydev);
 }
 
-- 
GitLab


From 66dbd9004a55073c5931f5f65f5fe2bbd414bdaa Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 24 Jan 2024 13:08:11 -0800
Subject: [PATCH 3454/4076] drm/sched: Drain all entities in DRM sched run job
 worker

All entities must be drained in the DRM scheduler run job worker to
avoid the following case. An entity found that is ready, no job found
ready on entity, and run job worker goes idle with other entities + jobs
ready. Draining all ready entities (i.e. loop over all ready entities)
in the run job worker ensures all job that are ready will be scheduled.

Cc: Thorsten Leemhuis <regressions@leemhuis.info>
Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Closes: https://lore.kernel.org/all/CABXGCsM2VLs489CH-vF-1539-s3in37=bwuOWtoeeE+q26zE+Q@mail.gmail.com/
Reported-and-tested-by: Mario Limonciello <mario.limonciello@amd.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3124
Link: https://lore.kernel.org/all/20240123021155.2775-1-mario.limonciello@amd.com/
Reported-and-tested-by: Vlastimil Babka <vbabka@suse.cz>
Closes: https://lore.kernel.org/dri-devel/05ddb2da-b182-4791-8ef7-82179fd159a8@amd.com/T/#m0c31d4d1b9ae9995bb880974c4f1dbaddc33a48a
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240124210811.1639040-1-matthew.brost@intel.com
---
 drivers/gpu/drm/scheduler/sched_main.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 550492a7a031d..85f082396d42d 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1178,21 +1178,20 @@ static void drm_sched_run_job_work(struct work_struct *w)
 	struct drm_sched_entity *entity;
 	struct dma_fence *fence;
 	struct drm_sched_fence *s_fence;
-	struct drm_sched_job *sched_job;
+	struct drm_sched_job *sched_job = NULL;
 	int r;
 
 	if (READ_ONCE(sched->pause_submit))
 		return;
 
-	entity = drm_sched_select_entity(sched);
+	/* Find entity with a ready job */
+	while (!sched_job && (entity = drm_sched_select_entity(sched))) {
+		sched_job = drm_sched_entity_pop_job(entity);
+		if (!sched_job)
+			complete_all(&entity->entity_idle);
+	}
 	if (!entity)
-		return;
-
-	sched_job = drm_sched_entity_pop_job(entity);
-	if (!sched_job) {
-		complete_all(&entity->entity_idle);
 		return;	/* No more work */
-	}
 
 	s_fence = sched_job->s_fence;
 
-- 
GitLab


From ab4443fe3ca6298663a55c4a70efc6c3ce913ca6 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 4 Jan 2024 09:58:39 +0100
Subject: [PATCH 3455/4076] readahead: avoid multiple marked readahead pages

ra_alloc_folio() marks a page that should trigger next round of async
readahead.  However it rounds up computed index to the order of page being
allocated.  This can however lead to multiple consecutive pages being
marked with readahead flag.  Consider situation with index == 1, mark ==
1, order == 0.  We insert order 0 page at index 1 and mark it.  Then we
bump order to 1, index to 2, mark (still == 1) is rounded up to 2 so page
at index 2 is marked as well.  Then we bump order to 2, index is
incremented to 4, mark gets rounded to 4 so page at index 4 is marked as
well.  The fact that multiple pages get marked within a single readahead
window confuses the readahead logic and results in readahead window being
trimmed back to 1.  This situation is triggered in particular when maximum
readahead window size is not a power of two (in the observed case it was
768 KB) and as a result sequential read throughput suffers.

Fix the problem by rounding 'mark' down instead of up.  Because the index
is naturally aligned to 'order', we are guaranteed 'rounded mark' == index
iff 'mark' is within the page we are allocating at 'index' and thus
exactly one page is marked with readahead flag as required by the
readahead code and sequential read performance is restored.

This effectively reverts part of commit b9ff43dd2743 ("mm/readahead: Fix
readahead with large folios").  The commit changed the rounding with the
rationale:

"...  we were setting the readahead flag on the folio which contains the
last byte read from the block.  This is wrong because we will trigger
readahead at the end of the read without waiting to see if a subsequent
read is going to use the pages we just read."

Although this is true, the fact is this was always the case with read
sizes not aligned to folio boundaries and large folios in the page cache
just make the situation more obvious (and frequent).  Also for sequential
read workloads it is better to trigger the readahead earlier rather than
later.  It is true that the difference in the rounding and thus earlier
triggering of the readahead can result in reading more for semi-random
workloads.  However workloads really suffering from this seem to be rare.
In particular I have verified that the workload described in commit
b9ff43dd2743 ("mm/readahead: Fix readahead with large folios") of reading
random 100k blocks from a file like:

[reader]
bs=100k
rw=randread
numjobs=1
size=64g
runtime=60s

is not impacted by the rounding change and achieves ~70MB/s in both cases.

[jack@suse.cz: fix one more place where mark rounding was done as well]
  Link: https://lkml.kernel.org/r/20240123153254.5206-1-jack@suse.cz
Link: https://lkml.kernel.org/r/20240104085839.21029-1-jack@suse.cz
Fixes: b9ff43dd2743 ("mm/readahead: Fix readahead with large folios")
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Guo Xuenan <guoxuenan@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/readahead.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/readahead.c b/mm/readahead.c
index 23620c57c1225..2648ec4f04947 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -469,7 +469,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 
 	if (!folio)
 		return -ENOMEM;
-	mark = round_up(mark, 1UL << order);
+	mark = round_down(mark, 1UL << order);
 	if (index == mark)
 		folio_set_readahead(folio);
 	err = filemap_add_folio(ractl->mapping, folio, index, gfp);
@@ -575,7 +575,7 @@ static void ondemand_readahead(struct readahead_control *ractl,
 	 * It's the expected callback index, assume sequential access.
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
-	expected = round_up(ra->start + ra->size - ra->async_size,
+	expected = round_down(ra->start + ra->size - ra->async_size,
 			1UL << order);
 	if (index == expected || index == (ra->start + ra->size)) {
 		ra->start += ra->size;
-- 
GitLab


From 19d3e221807772f8443e565234a6fdc5a2b09d26 Mon Sep 17 00:00:00 2001
From: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Date: Fri, 12 Jan 2024 10:08:40 -0800
Subject: [PATCH 3456/4076] fs/hugetlbfs/inode.c: mm/memory-failure.c: fix
 hugetlbfs hwpoison handling

has_extra_refcount() makes the assumption that the page cache adds a ref
count of 1 and subtracts this in the extra_pins case.  Commit a08c7193e4f1
(mm/filemap: remove hugetlb special casing in filemap.c) modifies
__filemap_add_folio() by calling folio_ref_add(folio, nr); for all cases
(including hugtetlb) where nr is the number of pages in the folio.  We
should adjust the number of references coming from the page cache by
subtracing the number of pages rather than 1.

In hugetlbfs_read_iter(), folio_test_has_hwpoisoned() is testing the wrong
flag as, in the hugetlb case, memory-failure code calls
folio_test_set_hwpoison() to indicate poison.  folio_test_hwpoison() is
the correct function to test for that flag.

After these fixes, the hugetlb hwpoison read selftest passes all cases.

Link: https://lkml.kernel.org/r/20240112180840.367006-1-sidhartha.kumar@oracle.com
Fixes: a08c7193e4f1 ("mm/filemap: remove hugetlb special casing in filemap.c")
Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Closes: https://lore.kernel.org/linux-mm/20230713001833.3778937-1-jiaqiyan@google.com/T/#m8e1469119e5b831bbd05d495f96b842e4a1c5519
Reported-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Tested-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: James Houghton <jthoughton@google.com>
Cc: Jiaqi Yan <jiaqiyan@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: <stable@vger.kernel.org>	[6.7+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/hugetlbfs/inode.c | 2 +-
 mm/memory-failure.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ea5b8e57d904e..671664fed3077 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -340,7 +340,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		} else {
 			folio_unlock(folio);
 
-			if (!folio_test_has_hwpoisoned(folio))
+			if (!folio_test_hwpoison(folio))
 				want = nr;
 			else {
 				/*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f9b61f4a6682..636280d04008d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -982,7 +982,7 @@ static bool has_extra_refcount(struct page_state *ps, struct page *p,
 	int count = page_count(p) - 1;
 
 	if (extra_pins)
-		count -= 1;
+		count -= folio_nr_pages(page_folio(p));
 
 	if (count > 0) {
 		pr_err("%#lx: %s still referenced by %d users\n",
-- 
GitLab


From f8ee4361b7be3f0c5bd21ee47561473ddf3aa17b Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@collabora.com>
Date: Fri, 12 Jan 2024 12:18:50 +0500
Subject: [PATCH 3457/4076] selftests/mm: mremap_test: fix build warning

Use 2 separate variables of types int and unsigned long long instead of
confusing them.  This corrects the correct print format for each of them
and removes the build warning:

warning: format `%d' expects argument of type `int', but argument 2 has type `long long unsigned int'

Link: https://lkml.kernel.org/r/20240112071851.612930-1-usama.anjum@collabora.com
Fixes: a4cb3b243343 ("selftests: mm: add a test for remapping to area immediately after existing mapping")
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/mremap_test.c | 27 ++++++++++++------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index 1d4c1589c3055..2f8b991f78cb4 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -360,7 +360,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 			      char pattern_seed)
 {
 	void *addr, *src_addr, *dest_addr, *dest_preamble_addr;
-	unsigned long long i;
+	int d;
+	unsigned long long t;
 	struct timespec t_start = {0, 0}, t_end = {0, 0};
 	long long  start_ns, end_ns, align_mask, ret, offset;
 	unsigned long long threshold;
@@ -378,8 +379,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 	/* Set byte pattern for source block. */
 	srand(pattern_seed);
-	for (i = 0; i < threshold; i++)
-		memset((char *) src_addr + i, (char) rand(), 1);
+	for (t = 0; t < threshold; t++)
+		memset((char *) src_addr + t, (char) rand(), 1);
 
 	/* Mask to zero out lower bits of address for alignment */
 	align_mask = ~(c.dest_alignment - 1);
@@ -420,8 +421,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 		/* Set byte pattern for the dest preamble block. */
 		srand(pattern_seed);
-		for (i = 0; i < c.dest_preamble_size; i++)
-			memset((char *) dest_preamble_addr + i, (char) rand(), 1);
+		for (d = 0; d < c.dest_preamble_size; d++)
+			memset((char *) dest_preamble_addr + d, (char) rand(), 1);
 	}
 
 	clock_gettime(CLOCK_MONOTONIC, &t_start);
@@ -437,14 +438,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 	/* Verify byte pattern after remapping */
 	srand(pattern_seed);
-	for (i = 0; i < threshold; i++) {
+	for (t = 0; t < threshold; t++) {
 		char c = (char) rand();
 
-		if (((char *) dest_addr)[i] != c) {
+		if (((char *) dest_addr)[t] != c) {
 			ksft_print_msg("Data after remap doesn't match at offset %llu\n",
-				       i);
+				       t);
 			ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff,
-					((char *) dest_addr)[i] & 0xff);
+					((char *) dest_addr)[t] & 0xff);
 			ret = -1;
 			goto clean_up_dest;
 		}
@@ -453,14 +454,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 	/* Verify the dest preamble byte pattern after remapping */
 	if (c.dest_preamble_size) {
 		srand(pattern_seed);
-		for (i = 0; i < c.dest_preamble_size; i++) {
+		for (d = 0; d < c.dest_preamble_size; d++) {
 			char c = (char) rand();
 
-			if (((char *) dest_preamble_addr)[i] != c) {
+			if (((char *) dest_preamble_addr)[d] != c) {
 				ksft_print_msg("Preamble data after remap doesn't match at offset %d\n",
-					       i);
+					       d);
 				ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff,
-					       ((char *) dest_preamble_addr)[i] & 0xff);
+					       ((char *) dest_preamble_addr)[d] & 0xff);
 				ret = -1;
 				goto clean_up_dest;
 			}
-- 
GitLab


From 4dca82d14174fe53f656a6bc32398db1bdd8f481 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 15 Jan 2024 11:07:31 +0100
Subject: [PATCH 3458/4076] uprobes: use pagesize-aligned virtual address when
 replacing pages

uprobes passes an unaligned page mapping address to
folio_add_new_anon_rmap(), which ends up triggering a VM_BUG_ON() we
recently extended in commit 372cbd4d5a066 ("mm: non-pmd-mappable, large
folios for folio_add_new_anon_rmap()").

Arguably, this is uprobes code doing something wrong; however, for the
time being it would have likely worked in rmap code because
__folio_set_anon() would set folio->index to the same value.

Looking at __replace_page(), we'd also pass slightly wrong values to
mmu_notifier_range_init(), page_vma_mapped_walk(), flush_cache_page(),
ptep_clear_flush() and set_pte_at_notify().  I suspect most of them are
fine, but let's just mark the introducing commit as the one needed fixing.
I don't think CC stable is warranted.

We'll add more sanity checks in rmap code separately, to make sure that we
always get properly aligned addresses.

Link: https://lkml.kernel.org/r/20240115100731.91007-1-david@redhat.com
Fixes: c517ee744b96 ("uprobes: __replace_page() should not use page_address_in_vma()")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: Jiri Olsa <jolsa@kernel.org>
Closes: https://lkml.kernel.org/r/ZaMR2EWN-HvlCfUl@krava
Tested-by: Jiri Olsa <jolsa@kernel.org>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/events/uprobes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 485bb0389b488..929e98c629652 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -537,7 +537,7 @@ retry:
 		}
 	}
 
-	ret = __replace_page(vma, vaddr, old_page, new_page);
+	ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
 	if (new_page)
 		put_page(new_page);
 put_old:
-- 
GitLab


From c4608d1bf7c6536d1a3d233eb21e50678681564e Mon Sep 17 00:00:00 2001
From: Yang Shi <yang@os.amperecomputing.com>
Date: Wed, 20 Dec 2023 22:59:43 -0800
Subject: [PATCH 3459/4076] mm: mmap: map MAP_STACK to VM_NOHUGEPAGE

commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP
boundaries") incured regression for stress-ng pthread benchmark [1].  It
is because THP get allocated to pthread's stack area much more possible
than before.  Pthread's stack area is allocated by mmap without
VM_GROWSDOWN or VM_GROWSUP flag, so kernel can't tell whether it is a
stack area or not.

The MAP_STACK flag is used to mark the stack area, but it is a no-op on
Linux.  Mapping MAP_STACK to VM_NOHUGEPAGE to prevent from allocating THP
for such stack area.

With this change the stack area looks like:

fffd18e10000-fffd19610000 rw-p 00000000 00:00 0
Size:               8192 kB
KernelPageSize:        4 kB
MMUPageSize:           4 kB
Rss:                  12 kB
Pss:                  12 kB
Pss_Dirty:            12 kB
Shared_Clean:          0 kB
Shared_Dirty:          0 kB
Private_Clean:         0 kB
Private_Dirty:        12 kB
Referenced:           12 kB
Anonymous:            12 kB
KSM:                   0 kB
LazyFree:              0 kB
AnonHugePages:         0 kB
ShmemPmdMapped:        0 kB
FilePmdMapped:         0 kB
Shared_Hugetlb:        0 kB
Private_Hugetlb:       0 kB
Swap:                  0 kB
SwapPss:               0 kB
Locked:                0 kB
THPeligible:           0
VmFlags: rd wr mr mw me ac nh

The "nh" flag is set.

[1] https://lore.kernel.org/linux-mm/202312192310.56367035-oliver.sang@intel.com/

Link: https://lkml.kernel.org/r/20231221065943.2803551-2-shy828301@gmail.com
Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries")
Signed-off-by: Yang Shi <yang@os.amperecomputing.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Tested-by: Oliver Sang <oliver.sang@intel.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christopher Lameter <cl@linux.com>
Cc: Huang, Ying <ying.huang@intel.com>
Cc: <stable@vger.kerenl.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mman.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/mman.h b/include/linux/mman.h
index 40d94411d4920..dc7048824be81 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -156,6 +156,7 @@ calc_vm_flag_bits(unsigned long flags)
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
 	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
+	       _calc_vm_trans(flags, MAP_STACK,	     VM_NOHUGEPAGE) |
 	       arch_calc_vm_flag_bits(flags);
 }
 
-- 
GitLab


From 63fd327016fdfca6f2fa27eba3496bd079eb8ed3 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 11 Jan 2024 08:29:02 -0500
Subject: [PATCH 3460/4076] mm: memcontrol: don't throttle dying tasks on
 memory.high

While investigating hosts with high cgroup memory pressures, Tejun
found culprit zombie tasks that had were holding on to a lot of
memory, had SIGKILL pending, but were stuck in memory.high reclaim.

In the past, we used to always force-charge allocations from tasks
that were exiting in order to accelerate them dying and freeing up
their rss. This changed for memory.max in a4ebf1b6ca1e ("memcg:
prohibit unconditional exceeding the limit of dying tasks"); it noted
that this can cause (userspace inducable) containment failures, so it
added a mandatory reclaim and OOM kill cycle before forcing charges.
At the time, memory.high enforcement was handled in the userspace
return path, which isn't reached by dying tasks, and so memory.high
was still never enforced by dying tasks.

When c9afe31ec443 ("memcg: synchronously enforce memory.high for large
overcharges") added synchronous reclaim for memory.high, it added
unconditional memory.high enforcement for dying tasks as well. The
callstack shows that this path is where the zombie is stuck in.

We need to accelerate dying tasks getting past memory.high, but we
cannot do it quite the same way as we do for memory.max: memory.max is
enforced strictly, and tasks aren't allowed to move past it without
FIRST reclaiming and OOM killing if necessary. This ensures very small
levels of excess. With memory.high, though, enforcement happens lazily
after the charge, and OOM killing is never triggered. A lot of
concurrent threads could have pushed, or could actively be pushing,
the cgroup into excess. The dying task will enter reclaim on every
allocation attempt, with little hope of restoring balance.

To fix this, skip synchronous memory.high enforcement on dying tasks
altogether again. Update memory.high path documentation while at it.

[hannes@cmpxchg.org: also handle tasks are being killed during the reclaim]
  Link: https://lkml.kernel.org/r/20240111192807.GA424308@cmpxchg.org
Link: https://lkml.kernel.org/r/20240111132902.389862-1-hannes@cmpxchg.org
Fixes: c9afe31ec443 ("memcg: synchronously enforce memory.high for large overcharges")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Dan Schatzberg <schatzberg.dan@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memcontrol.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e4c8735e7c85c..46d8d02114cfe 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2623,8 +2623,9 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
 }
 
 /*
- * Scheduled by try_charge() to be executed from the userland return path
- * and reclaims memory over the high limit.
+ * Reclaims memory over the high limit. Called directly from
+ * try_charge() (context permitting), as well as from the userland
+ * return path where reclaim is always able to block.
  */
 void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 {
@@ -2643,6 +2644,17 @@ void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 	current->memcg_nr_pages_over_high = 0;
 
 retry_reclaim:
+	/*
+	 * Bail if the task is already exiting. Unlike memory.max,
+	 * memory.high enforcement isn't as strict, and there is no
+	 * OOM killer involved, which means the excess could already
+	 * be much bigger (and still growing) than it could for
+	 * memory.max; the dying task could get stuck in fruitless
+	 * reclaim for a long time, which isn't desirable.
+	 */
+	if (task_is_dying())
+		goto out;
+
 	/*
 	 * The allocating task should reclaim at least the batch size, but for
 	 * subsequent retries we only want to do what's necessary to prevent oom
@@ -2693,6 +2705,9 @@ retry_reclaim:
 	}
 
 	/*
+	 * Reclaim didn't manage to push usage below the limit, slow
+	 * this allocating task down.
+	 *
 	 * If we exit early, we're guaranteed to die (since
 	 * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
 	 * need to account for any ill-begotten jiffies to pay them off later.
@@ -2887,11 +2902,17 @@ done_restock:
 		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
 
+	/*
+	 * Reclaim is set up above to be called from the userland
+	 * return path. But also attempt synchronous reclaim to avoid
+	 * excessive overrun while the task is still inside the
+	 * kernel. If this is successful, the return path will see it
+	 * when it rechecks the overage and simply bail out.
+	 */
 	if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
 	    !(current->flags & PF_MEMALLOC) &&
-	    gfpflags_allow_blocking(gfp_mask)) {
+	    gfpflags_allow_blocking(gfp_mask))
 		mem_cgroup_handle_over_high(gfp_mask);
-	}
 	return 0;
 }
 
-- 
GitLab


From 0d7e68c0271853c30655b05934d66cec81dc6afc Mon Sep 17 00:00:00 2001
From: Petr Vorel <pvorel@suse.cz>
Date: Wed, 17 Jan 2024 13:22:57 +0100
Subject: [PATCH 3461/4076] MAINTAINERS: add man-pages git trees

The maintainer uses both.

Link: https://lkml.kernel.org/r/20240117122257.2707637-1-pvorel@suse.cz
Signed-off-by: Petr Vorel <pvorel@suse.cz>
Reviewed-by: Alejandro Colomar <alx@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a692..8c756737491ec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12902,6 +12902,8 @@ M:	Alejandro Colomar <alx@kernel.org>
 L:	linux-man@vger.kernel.org
 S:	Maintained
 W:	http://www.kernel.org/doc/man-pages
+T:	git git://git.kernel.org/pub/scm/docs/man-pages/man-pages.git
+T:	git git://www.alejandro-colomar.es/src/alx/linux/man-pages/man-pages.git
 
 MANAGEMENT COMPONENT TRANSPORT PROTOCOL (MCTP)
 M:	Jeremy Kerr <jk@codeconstruct.com.au>
-- 
GitLab


From bc29036e1da1cf66e5f8312649aeec2d51ea3d86 Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@collabora.com>
Date: Tue, 16 Jan 2024 14:04:54 +0500
Subject: [PATCH 3462/4076] selftests/mm: switch to bash from sh

Running charge_reserved_hugetlb.sh generates errors if sh is set to
dash:

./charge_reserved_hugetlb.sh: 9: [[: not found
./charge_reserved_hugetlb.sh: 19: [[: not found
./charge_reserved_hugetlb.sh: 27: [[: not found
./charge_reserved_hugetlb.sh: 37: [[: not found
./charge_reserved_hugetlb.sh: 45: Syntax error: "(" unexpected

Switch to using /bin/bash instead of /bin/sh.  Make the switch for
write_hugetlb_memory.sh as well which is called from
charge_reserved_hugetlb.sh.

Link: https://lkml.kernel.org/r/20240116090455.3407378-1-usama.anjum@collabora.com
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/charge_reserved_hugetlb.sh | 2 +-
 tools/testing/selftests/mm/write_hugetlb_memory.sh    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index 0899019a7fcb4..e14bdd4455f2d 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Kselftest framework requirement - SKIP code is 4.
diff --git a/tools/testing/selftests/mm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh
index 70a02301f4c27..3d2d2eb9d6fff 100755
--- a/tools/testing/selftests/mm/write_hugetlb_memory.sh
+++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
-- 
GitLab


From 9319b647902cbd5cc884ac08a8a6d54ce111fc78 Mon Sep 17 00:00:00 2001
From: Zach O'Keefe <zokeefe@google.com>
Date: Thu, 18 Jan 2024 10:19:53 -0800
Subject: [PATCH 3463/4076] mm/writeback: fix possible divide-by-zero in
 wb_dirty_limits(), again

(struct dirty_throttle_control *)->thresh is an unsigned long, but is
passed as the u32 divisor argument to div_u64().  On architectures where
unsigned long is 64 bytes, the argument will be implicitly truncated.

Use div64_u64() instead of div_u64() so that the value used in the "is
this a safe division" check is the same as the divisor.

Also, remove redundant cast of the numerator to u64, as that should happen
implicitly.

This would be difficult to exploit in memcg domain, given the ratio-based
arithmetic domain_drity_limits() uses, but is much easier in global
writeback domain with a BDI_CAP_STRICTLIMIT-backing device, using e.g.
vm.dirty_bytes=(1<<32)*PAGE_SIZE so that dtc->thresh == (1<<32)

Link: https://lkml.kernel.org/r/20240118181954.1415197-1-zokeefe@google.com
Fixes: f6789593d5ce ("mm/page-writeback.c: fix divide by zero in bdi_dirty_limits()")
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Cc: Maxim Patlasov <MPatlasov@parallels.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/page-writeback.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index cd4e4ae77c40a..02147b61712bc 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1638,7 +1638,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
 	 */
 	dtc->wb_thresh = __wb_calc_thresh(dtc);
 	dtc->wb_bg_thresh = dtc->thresh ?
-		div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
+		div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
-- 
GitLab


From f6564fce256a3944aa1bc76cb3c40e792d97c1eb Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Thu, 18 Jan 2024 11:59:14 +0100
Subject: [PATCH 3464/4076] mm, kmsan: fix infinite recursion due to RCU
 critical section

Alexander Potapenko writes in [1]: "For every memory access in the code
instrumented by KMSAN we call kmsan_get_metadata() to obtain the metadata
for the memory being accessed.  For virtual memory the metadata pointers
are stored in the corresponding `struct page`, therefore we need to call
virt_to_page() to get them.

According to the comment in arch/x86/include/asm/page.h,
virt_to_page(kaddr) returns a valid pointer iff virt_addr_valid(kaddr) is
true, so KMSAN needs to call virt_addr_valid() as well.

To avoid recursion, kmsan_get_metadata() must not call instrumented code,
therefore ./arch/x86/include/asm/kmsan.h forks parts of
arch/x86/mm/physaddr.c to check whether a virtual address is valid or not.

But the introduction of rcu_read_lock() to pfn_valid() added instrumented
RCU API calls to virt_to_page_or_null(), which is called by
kmsan_get_metadata(), so there is an infinite recursion now.  I do not
think it is correct to stop that recursion by doing
kmsan_enter_runtime()/kmsan_exit_runtime() in kmsan_get_metadata(): that
would prevent instrumented functions called from within the runtime from
tracking the shadow values, which might introduce false positives."

Fix the issue by switching pfn_valid() to the _sched() variant of
rcu_read_lock/unlock(), which does not require calling into RCU.  Given
the critical section in pfn_valid() is very small, this is a reasonable
trade-off (with preemptible RCU).

KMSAN further needs to be careful to suppress calls into the scheduler,
which would be another source of recursion.  This can be done by wrapping
the call to pfn_valid() into preempt_disable/enable_no_resched().  The
downside is that this sacrifices breaking scheduling guarantees; however,
a kernel compiled with KMSAN has already given up any performance
guarantees due to being heavily instrumented.

Note, KMSAN code already disables tracing via Makefile, and since mmzone.h
is included, it is not necessary to use the notrace variant, which is
generally preferred in all other cases.

Link: https://lkml.kernel.org/r/20240115184430.2710652-1-glider@google.com [1]
Link: https://lkml.kernel.org/r/20240118110022.2538350-1-elver@google.com
Fixes: 5ec8e8ea8b77 ("mm/sparsemem: fix race in accessing memory_section->usage")
Signed-off-by: Marco Elver <elver@google.com>
Reported-by: Alexander Potapenko <glider@google.com>
Reported-by: syzbot+93a9e8a3dea8d6085e12@syzkaller.appspotmail.com
Reviewed-by: Alexander Potapenko <glider@google.com>
Tested-by: Alexander Potapenko <glider@google.com>
Cc: Charan Teja Kalla <quic_charante@quicinc.com>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/include/asm/kmsan.h | 17 ++++++++++++++++-
 include/linux/mmzone.h       |  6 +++---
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h
index 8fa6ac0e2d766..d91b37f5b4bb4 100644
--- a/arch/x86/include/asm/kmsan.h
+++ b/arch/x86/include/asm/kmsan.h
@@ -64,6 +64,7 @@ static inline bool kmsan_virt_addr_valid(void *addr)
 {
 	unsigned long x = (unsigned long)addr;
 	unsigned long y = x - __START_KERNEL_map;
+	bool ret;
 
 	/* use the carry flag to determine if x was < __START_KERNEL_map */
 	if (unlikely(x > y)) {
@@ -79,7 +80,21 @@ static inline bool kmsan_virt_addr_valid(void *addr)
 			return false;
 	}
 
-	return pfn_valid(x >> PAGE_SHIFT);
+	/*
+	 * pfn_valid() relies on RCU, and may call into the scheduler on exiting
+	 * the critical section. However, this would result in recursion with
+	 * KMSAN. Therefore, disable preemption here, and re-enable preemption
+	 * below while suppressing reschedules to avoid recursion.
+	 *
+	 * Note, this sacrifices occasionally breaking scheduling guarantees.
+	 * Although, a kernel compiled with KMSAN has already given up on any
+	 * performance guarantees due to being heavily instrumented.
+	 */
+	preempt_disable();
+	ret = pfn_valid(x >> PAGE_SHIFT);
+	preempt_enable_no_resched();
+
+	return ret;
 }
 
 #endif /* !MODULE */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4ed33b1278215..a497f189d9881 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -2013,9 +2013,9 @@ static inline int pfn_valid(unsigned long pfn)
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 	ms = __pfn_to_section(pfn);
-	rcu_read_lock();
+	rcu_read_lock_sched();
 	if (!valid_section(ms)) {
-		rcu_read_unlock();
+		rcu_read_unlock_sched();
 		return 0;
 	}
 	/*
@@ -2023,7 +2023,7 @@ static inline int pfn_valid(unsigned long pfn)
 	 * the entire section-sized span.
 	 */
 	ret = early_section(ms) || pfn_section_valid(ms, pfn);
-	rcu_read_unlock();
+	rcu_read_unlock_sched();
 
 	return ret;
 }
-- 
GitLab


From c2a292545cd43dcab86d5290ed95b006f1cefe90 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Thu, 18 Jan 2024 12:01:29 +0100
Subject: [PATCH 3465/4076] stackdepot: add stats counters exported via debugfs

Add a few basic stats counters for stack depot that can be used to derive
if stack depot is working as intended.  This is a snapshot of the new
stats after booting a system with a KASAN-enabled kernel:

 $ cat /sys/kernel/debug/stackdepot/stats
 pools: 838
 allocations: 29861
 frees: 6561
 in_use: 23300
 freelist_size: 1840

Generally, "pools" should be well below the max; once the system is
booted, "in_use" should remain relatively steady.

Link: https://lkml.kernel.org/r/20240118110216.2539519-1-elver@google.com
Signed-off-by: Marco Elver <elver@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexander Potapenko <glider@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/stackdepot.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index a0be5d05c7f08..80a8ca24ccc88 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -14,6 +14,7 @@
 
 #define pr_fmt(fmt) "stackdepot: " fmt
 
+#include <linux/debugfs.h>
 #include <linux/gfp.h>
 #include <linux/jhash.h>
 #include <linux/kernel.h>
@@ -115,6 +116,23 @@ static bool new_pool_required = true;
 /* Lock that protects the variables above. */
 static DEFINE_RWLOCK(pool_rwlock);
 
+/* Statistics counters for debugfs. */
+enum depot_counter_id {
+	DEPOT_COUNTER_ALLOCS,
+	DEPOT_COUNTER_FREES,
+	DEPOT_COUNTER_INUSE,
+	DEPOT_COUNTER_FREELIST_SIZE,
+	DEPOT_COUNTER_COUNT,
+};
+static long counters[DEPOT_COUNTER_COUNT];
+static const char *const counter_names[] = {
+	[DEPOT_COUNTER_ALLOCS]		= "allocations",
+	[DEPOT_COUNTER_FREES]		= "frees",
+	[DEPOT_COUNTER_INUSE]		= "in_use",
+	[DEPOT_COUNTER_FREELIST_SIZE]	= "freelist_size",
+};
+static_assert(ARRAY_SIZE(counter_names) == DEPOT_COUNTER_COUNT);
+
 static int __init disable_stack_depot(char *str)
 {
 	return kstrtobool(str, &stack_depot_disabled);
@@ -277,6 +295,7 @@ static void depot_init_pool(void *pool)
 		stack->handle.extra = 0;
 
 		list_add(&stack->list, &free_stacks);
+		counters[DEPOT_COUNTER_FREELIST_SIZE]++;
 	}
 
 	/* Save reference to the pool to be used by depot_fetch_stack(). */
@@ -376,6 +395,7 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
 	/* Get and unlink the first entry from the freelist. */
 	stack = list_first_entry(&free_stacks, struct stack_record, list);
 	list_del(&stack->list);
+	counters[DEPOT_COUNTER_FREELIST_SIZE]--;
 
 	/* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */
 	if (size > CONFIG_STACKDEPOT_MAX_FRAMES)
@@ -394,6 +414,8 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
 	 */
 	kmsan_unpoison_memory(stack, DEPOT_STACK_RECORD_SIZE);
 
+	counters[DEPOT_COUNTER_ALLOCS]++;
+	counters[DEPOT_COUNTER_INUSE]++;
 	return stack;
 }
 
@@ -426,6 +448,10 @@ static void depot_free_stack(struct stack_record *stack)
 	lockdep_assert_held_write(&pool_rwlock);
 
 	list_add(&stack->list, &free_stacks);
+
+	counters[DEPOT_COUNTER_FREELIST_SIZE]++;
+	counters[DEPOT_COUNTER_FREES]++;
+	counters[DEPOT_COUNTER_INUSE]--;
 }
 
 /* Calculates the hash for a stack. */
@@ -690,3 +716,30 @@ unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle)
 	return parts.extra;
 }
 EXPORT_SYMBOL(stack_depot_get_extra_bits);
+
+static int stats_show(struct seq_file *seq, void *v)
+{
+	/*
+	 * data race ok: These are just statistics counters, and approximate
+	 * statistics are ok for debugging.
+	 */
+	seq_printf(seq, "pools: %d\n", data_race(pools_num));
+	for (int i = 0; i < DEPOT_COUNTER_COUNT; i++)
+		seq_printf(seq, "%s: %ld\n", counter_names[i], data_race(counters[i]));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(stats);
+
+static int depot_debugfs_init(void)
+{
+	struct dentry *dir;
+
+	if (stack_depot_disabled)
+		return 0;
+
+	dir = debugfs_create_dir("stackdepot", NULL);
+	debugfs_create_file("stats", 0444, dir, NULL, &stats_fops);
+	return 0;
+}
+late_initcall(depot_debugfs_init);
-- 
GitLab


From 4434a56ec20925333d6cf4d4093641d063abd35b Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Thu, 18 Jan 2024 12:01:30 +0100
Subject: [PATCH 3466/4076] stackdepot: make fast paths lock-less again

With the introduction of the pool_rwlock (reader-writer lock), several
fast paths end up taking the pool_rwlock as readers.  Furthermore,
stack_depot_put() unconditionally takes the pool_rwlock as a writer.

Despite allowing readers to make forward-progress concurrently,
reader-writer locks have inherent cache contention issues, which does not
scale well on systems with large CPU counts.

Rework the synchronization story of stack depot to again avoid taking any
locks in the fast paths.  This is done by relying on RCU-protected list
traversal, and the NMI-safe subset of RCU to delay reuse of freed stack
records.  See code comments for more details.

Along with the performance issues, this also fixes incorrect nesting of
rwlock within a raw_spinlock, given that stack depot should still be
usable from anywhere:

 | [ BUG: Invalid wait context ]
 | -----------------------------
 | swapper/0/1 is trying to lock:
 | ffffffff89869be8 (pool_rwlock){..--}-{3:3}, at: stack_depot_save_flags
 | other info that might help us debug this:
 | context-{5:5}
 | 2 locks held by swapper/0/1:
 |  #0: ffffffff89632440 (rcu_read_lock){....}-{1:3}, at: __queue_work
 |  #1: ffff888100092018 (&pool->lock){-.-.}-{2:2}, at: __queue_work  <-- raw_spin_lock

Stack depot usage stats are similar to the previous version after a KASAN
kernel boot:

 $ cat /sys/kernel/debug/stackdepot/stats
 pools: 838
 allocations: 29865
 frees: 6604
 in_use: 23261
 freelist_size: 1879

The number of pools is the same as previously.  The freelist size is
minimally larger, but this may also be due to variance across system
boots.  This shows that even though we do not eagerly wait for the next
RCU grace period (such as with synchronize_rcu() or call_rcu()) after
freeing a stack record - requiring depot_pop_free() to "poll" if an entry
may be used - new allocations are very likely to happen in later RCU grace
periods.

Link: https://lkml.kernel.org/r/20240118110216.2539519-2-elver@google.com
Fixes: 108be8def46e ("lib/stackdepot: allow users to evict stack traces")
Reported-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Marco Elver <elver@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/stackdepot.c | 322 +++++++++++++++++++++++++++++++----------------
 1 file changed, 211 insertions(+), 111 deletions(-)

diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 80a8ca24ccc88..5caa1f5665538 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -22,8 +22,9 @@
 #include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
-#include <linux/percpu.h>
 #include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
 #include <linux/refcount.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -68,12 +69,28 @@ union handle_parts {
 };
 
 struct stack_record {
-	struct list_head list;		/* Links in hash table or freelist */
+	struct list_head hash_list;	/* Links in the hash table */
 	u32 hash;			/* Hash in hash table */
 	u32 size;			/* Number of stored frames */
-	union handle_parts handle;
+	union handle_parts handle;	/* Constant after initialization */
 	refcount_t count;
-	unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
+	union {
+		unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
+		struct {
+			/*
+			 * An important invariant of the implementation is to
+			 * only place a stack record onto the freelist iff its
+			 * refcount is zero. Because stack records with a zero
+			 * refcount are never considered as valid, it is safe to
+			 * union @entries and freelist management state below.
+			 * Conversely, as soon as an entry is off the freelist
+			 * and its refcount becomes non-zero, the below must not
+			 * be accessed until being placed back on the freelist.
+			 */
+			struct list_head free_list;	/* Links in the freelist */
+			unsigned long rcu_state;	/* RCU cookie */
+		};
+	};
 };
 
 #define DEPOT_STACK_RECORD_SIZE \
@@ -113,8 +130,8 @@ static LIST_HEAD(free_stacks);
  * yet allocated or if the limit on the number of pools is reached.
  */
 static bool new_pool_required = true;
-/* Lock that protects the variables above. */
-static DEFINE_RWLOCK(pool_rwlock);
+/* The lock must be held when performing pool or freelist modifications. */
+static DEFINE_RAW_SPINLOCK(pool_lock);
 
 /* Statistics counters for debugfs. */
 enum depot_counter_id {
@@ -276,14 +293,15 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(stack_depot_init);
 
-/* Initializes a stack depol pool. */
+/*
+ * Initializes new stack depot @pool, release all its entries to the freelist,
+ * and update the list of pools.
+ */
 static void depot_init_pool(void *pool)
 {
 	int offset;
 
-	lockdep_assert_held_write(&pool_rwlock);
-
-	WARN_ON(!list_empty(&free_stacks));
+	lockdep_assert_held(&pool_lock);
 
 	/* Initialize handles and link stack records into the freelist. */
 	for (offset = 0; offset <= DEPOT_POOL_SIZE - DEPOT_STACK_RECORD_SIZE;
@@ -294,19 +312,36 @@ static void depot_init_pool(void *pool)
 		stack->handle.offset = offset >> DEPOT_STACK_ALIGN;
 		stack->handle.extra = 0;
 
-		list_add(&stack->list, &free_stacks);
+		/*
+		 * Stack traces of size 0 are never saved, and we can simply use
+		 * the size field as an indicator if this is a new unused stack
+		 * record in the freelist.
+		 */
+		stack->size = 0;
+
+		INIT_LIST_HEAD(&stack->hash_list);
+		/*
+		 * Add to the freelist front to prioritize never-used entries:
+		 * required in case there are entries in the freelist, but their
+		 * RCU cookie still belongs to the current RCU grace period
+		 * (there can still be concurrent readers).
+		 */
+		list_add(&stack->free_list, &free_stacks);
 		counters[DEPOT_COUNTER_FREELIST_SIZE]++;
 	}
 
 	/* Save reference to the pool to be used by depot_fetch_stack(). */
 	stack_pools[pools_num] = pool;
-	pools_num++;
+
+	/* Pairs with concurrent READ_ONCE() in depot_fetch_stack(). */
+	WRITE_ONCE(pools_num, pools_num + 1);
+	ASSERT_EXCLUSIVE_WRITER(pools_num);
 }
 
 /* Keeps the preallocated memory to be used for a new stack depot pool. */
 static void depot_keep_new_pool(void **prealloc)
 {
-	lockdep_assert_held_write(&pool_rwlock);
+	lockdep_assert_held(&pool_lock);
 
 	/*
 	 * If a new pool is already saved or the maximum number of
@@ -329,17 +364,16 @@ static void depot_keep_new_pool(void **prealloc)
 	 * number of pools is reached. In either case, take note that
 	 * keeping another pool is not required.
 	 */
-	new_pool_required = false;
+	WRITE_ONCE(new_pool_required, false);
 }
 
-/* Updates references to the current and the next stack depot pools. */
-static bool depot_update_pools(void **prealloc)
+/*
+ * Try to initialize a new stack depot pool from either a previous or the
+ * current pre-allocation, and release all its entries to the freelist.
+ */
+static bool depot_try_init_pool(void **prealloc)
 {
-	lockdep_assert_held_write(&pool_rwlock);
-
-	/* Check if we still have objects in the freelist. */
-	if (!list_empty(&free_stacks))
-		goto out_keep_prealloc;
+	lockdep_assert_held(&pool_lock);
 
 	/* Check if we have a new pool saved and use it. */
 	if (new_pool) {
@@ -348,10 +382,9 @@ static bool depot_update_pools(void **prealloc)
 
 		/* Take note that we might need a new new_pool. */
 		if (pools_num < DEPOT_MAX_POOLS)
-			new_pool_required = true;
+			WRITE_ONCE(new_pool_required, true);
 
-		/* Try keeping the preallocated memory for new_pool. */
-		goto out_keep_prealloc;
+		return true;
 	}
 
 	/* Bail out if we reached the pool limit. */
@@ -368,12 +401,32 @@ static bool depot_update_pools(void **prealloc)
 	}
 
 	return false;
+}
+
+/* Try to find next free usable entry. */
+static struct stack_record *depot_pop_free(void)
+{
+	struct stack_record *stack;
 
-out_keep_prealloc:
-	/* Keep the preallocated memory for a new pool if required. */
-	if (*prealloc)
-		depot_keep_new_pool(prealloc);
-	return true;
+	lockdep_assert_held(&pool_lock);
+
+	if (list_empty(&free_stacks))
+		return NULL;
+
+	/*
+	 * We maintain the invariant that the elements in front are least
+	 * recently used, and are therefore more likely to be associated with an
+	 * RCU grace period in the past. Consequently it is sufficient to only
+	 * check the first entry.
+	 */
+	stack = list_first_entry(&free_stacks, struct stack_record, free_list);
+	if (stack->size && !poll_state_synchronize_rcu(stack->rcu_state))
+		return NULL;
+
+	list_del(&stack->free_list);
+	counters[DEPOT_COUNTER_FREELIST_SIZE]--;
+
+	return stack;
 }
 
 /* Allocates a new stack in a stack depot pool. */
@@ -382,20 +435,22 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
 {
 	struct stack_record *stack;
 
-	lockdep_assert_held_write(&pool_rwlock);
+	lockdep_assert_held(&pool_lock);
 
-	/* Update current and new pools if required and possible. */
-	if (!depot_update_pools(prealloc))
+	/* This should already be checked by public API entry points. */
+	if (WARN_ON_ONCE(!size))
 		return NULL;
 
 	/* Check if we have a stack record to save the stack trace. */
-	if (list_empty(&free_stacks))
-		return NULL;
-
-	/* Get and unlink the first entry from the freelist. */
-	stack = list_first_entry(&free_stacks, struct stack_record, list);
-	list_del(&stack->list);
-	counters[DEPOT_COUNTER_FREELIST_SIZE]--;
+	stack = depot_pop_free();
+	if (!stack) {
+		/* No usable entries on the freelist - try to refill the freelist. */
+		if (!depot_try_init_pool(prealloc))
+			return NULL;
+		stack = depot_pop_free();
+		if (WARN_ON(!stack))
+			return NULL;
+	}
 
 	/* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */
 	if (size > CONFIG_STACKDEPOT_MAX_FRAMES)
@@ -421,37 +476,73 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
 
 static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
 {
+	const int pools_num_cached = READ_ONCE(pools_num);
 	union handle_parts parts = { .handle = handle };
 	void *pool;
 	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
 	struct stack_record *stack;
 
-	lockdep_assert_held(&pool_rwlock);
+	lockdep_assert_not_held(&pool_lock);
 
-	if (parts.pool_index > pools_num) {
+	if (parts.pool_index > pools_num_cached) {
 		WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
-		     parts.pool_index, pools_num, handle);
+		     parts.pool_index, pools_num_cached, handle);
 		return NULL;
 	}
 
 	pool = stack_pools[parts.pool_index];
-	if (!pool)
+	if (WARN_ON(!pool))
 		return NULL;
 
 	stack = pool + offset;
+	if (WARN_ON(!refcount_read(&stack->count)))
+		return NULL;
+
 	return stack;
 }
 
 /* Links stack into the freelist. */
 static void depot_free_stack(struct stack_record *stack)
 {
-	lockdep_assert_held_write(&pool_rwlock);
+	unsigned long flags;
+
+	lockdep_assert_not_held(&pool_lock);
+
+	raw_spin_lock_irqsave(&pool_lock, flags);
+	printk_deferred_enter();
 
-	list_add(&stack->list, &free_stacks);
+	/*
+	 * Remove the entry from the hash list. Concurrent list traversal may
+	 * still observe the entry, but since the refcount is zero, this entry
+	 * will no longer be considered as valid.
+	 */
+	list_del_rcu(&stack->hash_list);
+
+	/*
+	 * Due to being used from constrained contexts such as the allocators,
+	 * NMI, or even RCU itself, stack depot cannot rely on primitives that
+	 * would sleep (such as synchronize_rcu()) or recursively call into
+	 * stack depot again (such as call_rcu()).
+	 *
+	 * Instead, get an RCU cookie, so that we can ensure this entry isn't
+	 * moved onto another list until the next grace period, and concurrent
+	 * RCU list traversal remains safe.
+	 */
+	stack->rcu_state = get_state_synchronize_rcu();
+
+	/*
+	 * Add the entry to the freelist tail, so that older entries are
+	 * considered first - their RCU cookie is more likely to no longer be
+	 * associated with the current grace period.
+	 */
+	list_add_tail(&stack->free_list, &free_stacks);
 
 	counters[DEPOT_COUNTER_FREELIST_SIZE]++;
 	counters[DEPOT_COUNTER_FREES]++;
 	counters[DEPOT_COUNTER_INUSE]--;
+
+	printk_deferred_exit();
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 }
 
 /* Calculates the hash for a stack. */
@@ -479,22 +570,52 @@ int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2,
 
 /* Finds a stack in a bucket of the hash table. */
 static inline struct stack_record *find_stack(struct list_head *bucket,
-					     unsigned long *entries, int size,
-					     u32 hash)
+					      unsigned long *entries, int size,
+					      u32 hash, depot_flags_t flags)
 {
-	struct list_head *pos;
-	struct stack_record *found;
+	struct stack_record *stack, *ret = NULL;
+
+	/*
+	 * Stack depot may be used from instrumentation that instruments RCU or
+	 * tracing itself; use variant that does not call into RCU and cannot be
+	 * traced.
+	 *
+	 * Note: Such use cases must take care when using refcounting to evict
+	 * unused entries, because the stack record free-then-reuse code paths
+	 * do call into RCU.
+	 */
+	rcu_read_lock_sched_notrace();
+
+	list_for_each_entry_rcu(stack, bucket, hash_list) {
+		if (stack->hash != hash || stack->size != size)
+			continue;
 
-	lockdep_assert_held(&pool_rwlock);
+		/*
+		 * This may race with depot_free_stack() accessing the freelist
+		 * management state unioned with @entries. The refcount is zero
+		 * in that case and the below refcount_inc_not_zero() will fail.
+		 */
+		if (data_race(stackdepot_memcmp(entries, stack->entries, size)))
+			continue;
 
-	list_for_each(pos, bucket) {
-		found = list_entry(pos, struct stack_record, list);
-		if (found->hash == hash &&
-		    found->size == size &&
-		    !stackdepot_memcmp(entries, found->entries, size))
-			return found;
+		/*
+		 * Try to increment refcount. If this succeeds, the stack record
+		 * is valid and has not yet been freed.
+		 *
+		 * If STACK_DEPOT_FLAG_GET is not used, it is undefined behavior
+		 * to then call stack_depot_put() later, and we can assume that
+		 * a stack record is never placed back on the freelist.
+		 */
+		if ((flags & STACK_DEPOT_FLAG_GET) && !refcount_inc_not_zero(&stack->count))
+			continue;
+
+		ret = stack;
+		break;
 	}
-	return NULL;
+
+	rcu_read_unlock_sched_notrace();
+
+	return ret;
 }
 
 depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
@@ -508,7 +629,6 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	struct page *page = NULL;
 	void *prealloc = NULL;
 	bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC;
-	bool need_alloc = false;
 	unsigned long flags;
 	u32 hash;
 
@@ -531,31 +651,16 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	hash = hash_stack(entries, nr_entries);
 	bucket = &stack_table[hash & stack_hash_mask];
 
-	read_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
-	/* Fast path: look the stack trace up without full locking. */
-	found = find_stack(bucket, entries, nr_entries, hash);
-	if (found) {
-		if (depot_flags & STACK_DEPOT_FLAG_GET)
-			refcount_inc(&found->count);
-		printk_deferred_exit();
-		read_unlock_irqrestore(&pool_rwlock, flags);
+	/* Fast path: look the stack trace up without locking. */
+	found = find_stack(bucket, entries, nr_entries, hash, depot_flags);
+	if (found)
 		goto exit;
-	}
-
-	/* Take note if another stack pool needs to be allocated. */
-	if (new_pool_required)
-		need_alloc = true;
-
-	printk_deferred_exit();
-	read_unlock_irqrestore(&pool_rwlock, flags);
 
 	/*
 	 * Allocate memory for a new pool if required now:
 	 * we won't be able to do that under the lock.
 	 */
-	if (unlikely(can_alloc && need_alloc)) {
+	if (unlikely(can_alloc && READ_ONCE(new_pool_required))) {
 		/*
 		 * Zero out zone modifiers, as we don't have specific zone
 		 * requirements. Keep the flags related to allocation in atomic
@@ -569,31 +674,36 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 			prealloc = page_address(page);
 	}
 
-	write_lock_irqsave(&pool_rwlock, flags);
+	raw_spin_lock_irqsave(&pool_lock, flags);
 	printk_deferred_enter();
 
-	found = find_stack(bucket, entries, nr_entries, hash);
+	/* Try to find again, to avoid concurrently inserting duplicates. */
+	found = find_stack(bucket, entries, nr_entries, hash, depot_flags);
 	if (!found) {
 		struct stack_record *new =
 			depot_alloc_stack(entries, nr_entries, hash, &prealloc);
 
 		if (new) {
-			list_add(&new->list, bucket);
+			/*
+			 * This releases the stack record into the bucket and
+			 * makes it visible to readers in find_stack().
+			 */
+			list_add_rcu(&new->hash_list, bucket);
 			found = new;
 		}
-	} else {
-		if (depot_flags & STACK_DEPOT_FLAG_GET)
-			refcount_inc(&found->count);
+	}
+
+	if (prealloc) {
 		/*
-		 * Stack depot already contains this stack trace, but let's
-		 * keep the preallocated memory for future.
+		 * Either stack depot already contains this stack trace, or
+		 * depot_alloc_stack() did not consume the preallocated memory.
+		 * Try to keep the preallocated memory for future.
 		 */
-		if (prealloc)
-			depot_keep_new_pool(&prealloc);
+		depot_keep_new_pool(&prealloc);
 	}
 
 	printk_deferred_exit();
-	write_unlock_irqrestore(&pool_rwlock, flags);
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 exit:
 	if (prealloc) {
 		/* Stack depot didn't use this memory, free it. */
@@ -618,7 +728,6 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 			       unsigned long **entries)
 {
 	struct stack_record *stack;
-	unsigned long flags;
 
 	*entries = NULL;
 	/*
@@ -630,13 +739,13 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 	if (!handle || stack_depot_disabled)
 		return 0;
 
-	read_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
 	stack = depot_fetch_stack(handle);
-
-	printk_deferred_exit();
-	read_unlock_irqrestore(&pool_rwlock, flags);
+	/*
+	 * Should never be NULL, otherwise this is a use-after-put (or just a
+	 * corrupt handle).
+	 */
+	if (WARN(!stack, "corrupt handle or use after stack_depot_put()"))
+		return 0;
 
 	*entries = stack->entries;
 	return stack->size;
@@ -646,29 +755,20 @@ EXPORT_SYMBOL_GPL(stack_depot_fetch);
 void stack_depot_put(depot_stack_handle_t handle)
 {
 	struct stack_record *stack;
-	unsigned long flags;
 
 	if (!handle || stack_depot_disabled)
 		return;
 
-	write_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
 	stack = depot_fetch_stack(handle);
-	if (WARN_ON(!stack))
-		goto out;
-
-	if (refcount_dec_and_test(&stack->count)) {
-		/* Unlink stack from the hash table. */
-		list_del(&stack->list);
+	/*
+	 * Should always be able to find the stack record, otherwise this is an
+	 * unbalanced put attempt (or corrupt handle).
+	 */
+	if (WARN(!stack, "corrupt handle or unbalanced stack_depot_put()"))
+		return;
 
-		/* Free stack. */
+	if (refcount_dec_and_test(&stack->count))
 		depot_free_stack(stack);
-	}
-
-out:
-	printk_deferred_exit();
-	write_unlock_irqrestore(&pool_rwlock, flags);
 }
 EXPORT_SYMBOL_GPL(stack_depot_put);
 
-- 
GitLab


From 0fe8ff51efb3fe5cb25da13229f95aa709613cb3 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosryahmed@google.com>
Date: Wed, 17 Jan 2024 18:21:52 +0000
Subject: [PATCH 3467/4076] MAINTAINERS: supplement of zswap maintainers update

As discussed on the mailing list [1], merge the zpool maintainers entry
into the zswap one.  Also, add CREDITS entries for previous zswap/zpool
maintainers.

[1] https://lore.kernel.org/linux-mm/CAJD7tkYx4YWhGoVwnSeGc8dY_1aRRxxg8PzWBV==A6iqG_OgFw@mail.gmail.com/

Link: https://lkml.kernel.org/r/20240117182152.1439822-1-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Seth Jennings <sjenning@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 CREDITS     | 13 +++++++++++++
 MAINTAINERS |  9 ++-------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/CREDITS b/CREDITS
index 5797e8f7e92b0..df8d6946739f6 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2161,6 +2161,19 @@ N: Mike Kravetz
 E: mike.kravetz@oracle.com
 D: Maintenance and development of the hugetlb subsystem
 
+N: Seth Jennings
+E: sjenning@redhat.com
+D: Creation and maintenance of zswap
+
+N: Dan Streetman
+E: ddstreet@ieee.org
+D: Maintenance and development of zswap
+D: Creation and maintenance of the zpool API
+
+N: Vitaly Wool
+E: vitaly.wool@konsulko.com
+D: Maintenance and development of zswap
+
 N: Andreas S. Krebs
 E: akrebs@altavista.net
 D: CYPRESS CY82C693 chipset IDE, Digital's PC-Alpha 164SX boards
diff --git a/MAINTAINERS b/MAINTAINERS
index 8c756737491ec..fecebfc4c0dc6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24341,13 +24341,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs.git
 F:	Documentation/filesystems/zonefs.rst
 F:	fs/zonefs/
 
-ZPOOL COMPRESSED PAGE STORAGE API
-M:	Dan Streetman <ddstreet@ieee.org>
-L:	linux-mm@kvack.org
-S:	Maintained
-F:	include/linux/zpool.h
-F:	mm/zpool.c
-
 ZR36067 VIDEO FOR LINUX DRIVER
 M:	Corentin Labbe <clabbe@baylibre.com>
 L:	mjpeg-users@lists.sourceforge.net
@@ -24399,7 +24392,9 @@ M:	Nhat Pham <nphamcs@gmail.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/admin-guide/mm/zswap.rst
+F:	include/linux/zpool.h
 F:	include/linux/zswap.h
+F:	mm/zpool.c
 F:	mm/zswap.c
 
 THE REST
-- 
GitLab


From 91b80cc5b39f00399e8e2d17527cad2c7fa535e2 Mon Sep 17 00:00:00 2001
From: Nico Pache <npache@redhat.com>
Date: Fri, 19 Jan 2024 06:14:29 -0700
Subject: [PATCH 3468/4076] selftests: mm: fix map_hugetlb failure on 64K page
 size systems

On systems with 64k page size and 512M huge page sizes, the allocation and
test succeeds but errors out at the munmap.  As the comment states, munmap
will failure if its not HUGEPAGE aligned.  This is due to the length of
the mapping being 1/2 the size of the hugepage causing the munmap to not
be hugepage aligned.  Fix this by making the mapping length the full
hugepage if the hugepage is larger than the length of the mapping.

Link: https://lkml.kernel.org/r/20240119131429.172448-1-npache@redhat.com
Signed-off-by: Nico Pache <npache@redhat.com>
Cc: Donet Tom <donettom@linux.vnet.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/map_hugetlb.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c
index 193281560b61b..86e8f2048a409 100644
--- a/tools/testing/selftests/mm/map_hugetlb.c
+++ b/tools/testing/selftests/mm/map_hugetlb.c
@@ -15,6 +15,7 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <fcntl.h>
+#include "vm_util.h"
 
 #define LENGTH (256UL*1024*1024)
 #define PROTECTION (PROT_READ | PROT_WRITE)
@@ -58,10 +59,16 @@ int main(int argc, char **argv)
 {
 	void *addr;
 	int ret;
+	size_t hugepage_size;
 	size_t length = LENGTH;
 	int flags = FLAGS;
 	int shift = 0;
 
+	hugepage_size = default_huge_page_size();
+	/* munmap with fail if the length is not page aligned */
+	if (hugepage_size > length)
+		length = hugepage_size;
+
 	if (argc > 1)
 		length = atol(argv[1]) << 20;
 	if (argc > 2) {
-- 
GitLab


From 52e63d67b5bb423b33d7a262ac7f8bd375a90145 Mon Sep 17 00:00:00 2001
From: Audra Mitchell <audra@redhat.com>
Date: Fri, 19 Jan 2024 15:58:01 -0500
Subject: [PATCH 3469/4076] selftests/mm: Update va_high_addr_switch.sh to
 check CPU for la57 flag

In order for the page table level 5 to be in use, the CPU must have the
setting enabled in addition to the CONFIG option. Check for the flag to be
set to avoid false test failures on systems that do not have this cpu flag
set.

The test does a series of mmap calls including three using the
MAP_FIXED flag and specifying an address that is 1<<47 or 1<<48.  These
addresses are only available if you are using level 5 page tables,
which requires both the CPU to have the capabiltiy (la57 flag) and the
kernel to be configured.  Currently the test only checks for the kernel
configuration option, so this test can still report a false positive.
Here are the three failing lines:

$ ./va_high_addr_switch | grep FAILED
mmap(ADDR_SWITCH_HINT, 2 * PAGE_SIZE, MAP_FIXED): 0xffffffffffffffff - FAILED
mmap(HIGH_ADDR, MAP_FIXED): 0xffffffffffffffff - FAILED
mmap(ADDR_SWITCH_HINT, 2 * PAGE_SIZE, MAP_FIXED): 0xffffffffffffffff - FAILED

I thought (for about a second) refactoring the test so that these three
mmap calls will only be run on systems with the level 5 page tables
available, but the whole point of the test is to check the level 5
feature...

Link: https://lkml.kernel.org/r/20240119205801.62769-1-audra@redhat.com
Fixes: 4f2930c6718a ("selftests/vm: only run 128TBswitch with 5-level paging")
Signed-off-by: Audra Mitchell <audra@redhat.com>
Cc: Rafael Aquini <raquini@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Adam Sindelar <adam@wowsignal.io>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/va_high_addr_switch.sh | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh
index 45cae7cab27e1..a0a75f3029043 100755
--- a/tools/testing/selftests/mm/va_high_addr_switch.sh
+++ b/tools/testing/selftests/mm/va_high_addr_switch.sh
@@ -29,9 +29,15 @@ check_supported_x86_64()
 	# See man 1 gzip under '-f'.
 	local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2)
 
+	local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;}
+		else {print 1}; exit}' /proc/cpuinfo 2>/dev/null)
+
 	if [[ "${pg_table_levels}" -lt 5 ]]; then
 		echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
 		exit $ksft_skip
+	elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then
+		echo "$0: CPU does not have the necessary la57 flag to support page table level 5"
+		exit $ksft_skip
 	fi
 }
 
-- 
GitLab


From db44c658f798ad907219f15e033229b8d1aadb93 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 22 Jan 2024 18:54:07 +0100
Subject: [PATCH 3470/4076] mm/huge_memory: fix folio_set_dirty() vs.
 folio_mark_dirty()

The correct folio replacement for "set_page_dirty()" is
"folio_mark_dirty()", not "folio_set_dirty()".  Using the latter won't
properly inform the FS using the dirty_folio() callback.

This has been found by code inspection, but likely this can result in some
real trouble.

Link: https://lkml.kernel.org/r/20240122175407.307992-1-david@redhat.com
Fixes: a8e61d584eda0 ("mm/huge_memory: page_remove_rmap() -> folio_remove_rmap_pmd()")
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 94ef5c02b4596..5f31e51f22356 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2437,7 +2437,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			page = pmd_page(old_pmd);
 			folio = page_folio(page);
 			if (!folio_test_dirty(folio) && pmd_dirty(old_pmd))
-				folio_set_dirty(folio);
+				folio_mark_dirty(folio);
 			if (!folio_test_referenced(folio) && pmd_young(old_pmd))
 				folio_set_referenced(folio);
 			folio_remove_rmap_pmd(folio, page, vma);
@@ -3563,7 +3563,7 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	}
 
 	if (pmd_dirty(pmdval))
-		folio_set_dirty(folio);
+		folio_mark_dirty(folio);
 	if (pmd_write(pmdval))
 		entry = make_writable_migration_entry(page_to_pfn(page));
 	else if (anon_exclusive)
-- 
GitLab


From e4e3df290f65da6cb27dac1309389c916f27db1a Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 22 Jan 2024 18:17:51 +0100
Subject: [PATCH 3471/4076] mm/memory: fix folio_set_dirty() vs.
 folio_mark_dirty() in zap_pte_range()

The correct folio replacement for "set_page_dirty()" is
"folio_mark_dirty()", not "folio_set_dirty()".  Using the latter won't
properly inform the FS using the dirty_folio() callback.

This has been found by code inspection, but likely this can result in some
real trouble when zapping dirty PTEs that point at clean pagecache folios.

Yuezhang Mo said: "Without this fix, testing the latest exfat with
xfstests, test cases generic/029 and generic/030 will fail."

Link: https://lkml.kernel.org/r/20240122171751.272074-1-david@redhat.com
Fixes: c46265030b0f ("mm/memory: page_remove_rmap() -> folio_remove_rmap_pte()")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: Ryan Roberts <ryan.roberts@arm.com>
Closes: https://lkml.kernel.org/r/2445cedb-61fb-422c-8bfb-caf0a2beed62@arm.com
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/memory.c b/mm/memory.c
index 7e1f4849463aa..89bcae0b224d6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1464,7 +1464,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			delay_rmap = 0;
 			if (!folio_test_anon(folio)) {
 				if (pte_dirty(ptent)) {
-					folio_set_dirty(folio);
+					folio_mark_dirty(folio);
 					if (tlb_delay_rmap(tlb)) {
 						delay_rmap = 1;
 						force_flush = 1;
-- 
GitLab


From 6f9dc684cae638dda0570154509884ee78d0f75c Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel.holland@sifive.com>
Date: Mon, 22 Jan 2024 09:52:01 -0800
Subject: [PATCH 3472/4076] scs: add CONFIG_MMU dependency for vfree_atomic()

The shadow call stack implementation fails to build without CONFIG_MMU:

  ld.lld: error: undefined symbol: vfree_atomic
  >>> referenced by scs.c
  >>>               kernel/scs.o:(scs_free) in archive vmlinux.a

Link: https://lkml.kernel.org/r/20240122175204.2371009-1-samuel.holland@sifive.com
Fixes: a2abe7cbd8fe ("scs: switch to vmapped shadow stacks")
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/Kconfig b/arch/Kconfig
index c91917b508736..a5af0edd3eb8f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -673,6 +673,7 @@ config SHADOW_CALL_STACK
 	bool "Shadow Call Stack"
 	depends on ARCH_SUPPORTS_SHADOW_CALL_STACK
 	depends on DYNAMIC_FTRACE_WITH_ARGS || DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER
+	depends on MMU
 	help
 	  This option enables the compiler's Shadow Call Stack, which
 	  uses a shadow stack to protect function return addresses from
-- 
GitLab


From d021b442cf312664811783e92b3d5e4548e92a53 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 22 Jan 2024 12:05:54 +0000
Subject: [PATCH 3473/4076] selftests/mm: ksm_tests should only MADV_HUGEPAGE
 valid memory

ksm_tests was previously mmapping a region of memory, aligning the
returned pointer to a PMD boundary, then setting MADV_HUGEPAGE, but was
setting it past the end of the mmapped area due to not taking the pointer
alignment into consideration.  Fix this behaviour.

Up until commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP
boundaries"), this buggy behavior was (usually) masked because the
alignment difference was always less than PMD-size.  But since the
mentioned commit, `ksm_tests -H -s 100` started failing.

Link: https://lkml.kernel.org/r/20240122120554.3108022-1-ryan.roberts@arm.com
Fixes: 325254899684 ("selftests: vm: add KSM huge pages merging time test")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/ksm_tests.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c
index 380b691d3eb9f..b748c48908d9d 100644
--- a/tools/testing/selftests/mm/ksm_tests.c
+++ b/tools/testing/selftests/mm/ksm_tests.c
@@ -566,7 +566,7 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot,
 	if (map_ptr_orig == MAP_FAILED)
 		err(2, "initial mmap");
 
-	if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE))
+	if (madvise(map_ptr, len, MADV_HUGEPAGE))
 		err(2, "MADV_HUGEPAGE");
 
 	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
-- 
GitLab


From 67695f18d55924b2013534ef3bdc363bc9e14605 Mon Sep 17 00:00:00 2001
From: Lokesh Gidra <lokeshgidra@google.com>
Date: Wed, 17 Jan 2024 14:37:29 -0800
Subject: [PATCH 3474/4076] userfaultfd: fix mmap_changing checking in
 mfill_atomic_hugetlb

In mfill_atomic_hugetlb(), mmap_changing isn't being checked
again if we drop mmap_lock and reacquire it. When the lock is not held,
mmap_changing could have been incremented. This is also inconsistent
with the behavior in mfill_atomic().

Link: https://lkml.kernel.org/r/20240117223729.1444522-1-lokeshgidra@google.com
Fixes: df2cc96e77011 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races")
Signed-off-by: Lokesh Gidra <lokeshgidra@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 20e3b0d9cf7ed..75fcf1f783bc5 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
 					      unsigned long dst_start,
 					      unsigned long src_start,
 					      unsigned long len,
+					      atomic_t *mmap_changing,
 					      uffd_flags_t flags)
 {
 	struct mm_struct *dst_mm = dst_vma->vm_mm;
@@ -472,6 +473,15 @@ retry:
 				goto out;
 			}
 			mmap_read_lock(dst_mm);
+			/*
+			 * If memory mappings are changing because of non-cooperative
+			 * operation (e.g. mremap) running in parallel, bail out and
+			 * request the user to retry later
+			 */
+			if (mmap_changing && atomic_read(mmap_changing)) {
+				err = -EAGAIN;
+				break;
+			}
 
 			dst_vma = NULL;
 			goto retry;
@@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma,
 				    unsigned long dst_start,
 				    unsigned long src_start,
 				    unsigned long len,
+				    atomic_t *mmap_changing,
 				    uffd_flags_t flags);
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -622,8 +633,8 @@ retry:
 	 * If this is a HUGETLB vma, pass off to appropriate routine
 	 */
 	if (is_vm_hugetlb_page(dst_vma))
-		return  mfill_atomic_hugetlb(dst_vma, dst_start,
-					     src_start, len, flags);
+		return  mfill_atomic_hugetlb(dst_vma, dst_start, src_start,
+					     len, mmap_changing, flags);
 
 	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;
-- 
GitLab


From 4ef9ad19e17676b9ef071309bc62020e2373705d Mon Sep 17 00:00:00 2001
From: Yang Shi <yang@os.amperecomputing.com>
Date: Thu, 18 Jan 2024 10:05:05 -0800
Subject: [PATCH 3475/4076] mm: huge_memory: don't force huge page alignment on
 32 bit

commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP
boundaries") caused two issues [1] [2] reported on 32 bit system or compat
userspace.

It doesn't make too much sense to force huge page alignment on 32 bit
system due to the constrained virtual address space.

[1] https://lore.kernel.org/linux-mm/d0a136a0-4a31-46bc-adf4-2db109a61672@kernel.org/
[2] https://lore.kernel.org/linux-mm/CAJuCfpHXLdQy1a2B6xN2d7quTYwg2OoZseYPZTRpU0eHHKD-sQ@mail.gmail.com/

Link: https://lkml.kernel.org/r/20240118180505.2914778-1-shy828301@gmail.com
Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries")
Signed-off-by: Yang Shi <yang@os.amperecomputing.com>
Reported-by: Jiri Slaby <jirislaby@kernel.org>
Reported-by: Suren Baghdasaryan <surenb@google.com>
Tested-by: Jiri Slaby <jirislaby@kernel.org>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Christopher Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5f31e51f22356..172b85208276e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -37,6 +37,7 @@
 #include <linux/page_owner.h>
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
+#include <linux/compat.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -811,6 +812,9 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	loff_t off_align = round_up(off, size);
 	unsigned long len_pad, ret;
 
+	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
+		return 0;
+
 	if (off_end <= off_align || (off_end - off_align) < size)
 		return 0;
 
-- 
GitLab


From 5056c596c3d1848021a4eaa76ee42f4c05c50346 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 26 Jan 2024 16:22:07 +0800
Subject: [PATCH 3476/4076] LoongArch/smp: Call rcutree_report_cpu_starting()
 at tlb_init()

Machines which have more than 8 nodes fail to boot SMP after commit
a2ccf46333d7b2cf96 ("LoongArch/smp: Call rcutree_report_cpu_starting()
earlier"). Because such machines use tlb-based per-cpu base address
rather than dmw-based per-cpu base address, resulting per-cpu variables
can only be accessed after tlb_init(). But rcutree_report_cpu_starting()
is now called before tlb_init() and accesses per-cpu variables indeed.

Since the original patch want to avoid the lockdep warning caused by
page allocation in tlb_init(), we can move rcutree_report_cpu_starting()
to tlb_init() where after tlb exception configuration but before page
allocation.

Fixes: a2ccf46333d7b2cf96 ("LoongArch/smp: Call rcutree_report_cpu_starting() earlier")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/smp.c |  1 -
 arch/loongarch/mm/tlb.c     | 16 ++++++++++------
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index a16e3dbe9f09e..2b49d30eb7c01 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -509,7 +509,6 @@ asmlinkage void start_secondary(void)
 	sync_counter();
 	cpu = raw_smp_processor_id();
 	set_my_cpu_offset(per_cpu_offset(cpu));
-	rcutree_report_cpu_starting(cpu);
 
 	cpu_probe();
 	constant_clockevent_init();
diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c
index 2c0a411f23aa7..0b95d32b30c94 100644
--- a/arch/loongarch/mm/tlb.c
+++ b/arch/loongarch/mm/tlb.c
@@ -284,12 +284,16 @@ static void setup_tlb_handler(int cpu)
 		set_handler(EXCCODE_TLBNR * VECSIZE, handle_tlb_protect, VECSIZE);
 		set_handler(EXCCODE_TLBNX * VECSIZE, handle_tlb_protect, VECSIZE);
 		set_handler(EXCCODE_TLBPE * VECSIZE, handle_tlb_protect, VECSIZE);
-	}
+	} else {
+		int vec_sz __maybe_unused;
+		void *addr __maybe_unused;
+		struct page *page __maybe_unused;
+
+		/* Avoid lockdep warning */
+		rcutree_report_cpu_starting(cpu);
+
 #ifdef CONFIG_NUMA
-	else {
-		void *addr;
-		struct page *page;
-		const int vec_sz = sizeof(exception_handlers);
+		vec_sz = sizeof(exception_handlers);
 
 		if (pcpu_handlers[cpu])
 			return;
@@ -305,8 +309,8 @@ static void setup_tlb_handler(int cpu)
 		csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_EENTRY);
 		csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_MERRENTRY);
 		csr_write64(pcpu_handlers[cpu] + 80*VECSIZE, LOONGARCH_CSR_TLBRENTRY);
-	}
 #endif
+	}
 }
 
 void tlb_init(int cpu)
-- 
GitLab


From 614f362918c782d1cfa4ee50f96072a95eac264e Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Fri, 26 Jan 2024 16:22:07 +0800
Subject: [PATCH 3477/4076] LoongArch: KVM: Fix build due to API changes

Commit 8569992d64b8f750e34b7858eac ("KVM: Use gfn instead of hva for
mmu_notifier_retry") replaces mmu_invalidate_retry_hva() usage with
mmu_invalidate_retry_gfn() for X86, LoongArch also need similar changes
to fix build.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/mmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c
index 915f175278931..50a6acd7ffe4c 100644
--- a/arch/loongarch/kvm/mmu.c
+++ b/arch/loongarch/kvm/mmu.c
@@ -675,7 +675,7 @@ static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot,
  *
  * There are several ways to safely use this helper:
  *
- * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before
  *   consuming it.  In this case, mmu_lock doesn't need to be held during the
  *   lookup, but it does need to be held while checking the MMU notifier.
  *
@@ -855,7 +855,7 @@ retry:
 
 	/* Check if an invalidation has taken place since we got pfn */
 	spin_lock(&kvm->mmu_lock);
-	if (mmu_invalidate_retry_hva(kvm, mmu_seq, hva)) {
+	if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) {
 		/*
 		 * This can happen when mappings are changed asynchronously, but
 		 * also synchronously if a COW is triggered by
-- 
GitLab


From 48ef9e87b407f89f230f804815af7ac2031ec17a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 26 Jan 2024 16:22:07 +0800
Subject: [PATCH 3478/4076] LoongArch: KVM: Add returns to SIMD stubs

The stubs for kvm_own/lsx()/kvm_own_lasx() when CONFIG_CPU_HAS_LSX or
CONFIG_CPU_HAS_LASX is not defined should have a return value since they
return an int, so add "return -EINVAL;" to the stubs.
Fixes the build error:

In file included from ../arch/loongarch/include/asm/kvm_csr.h:12,
                 from ../arch/loongarch/kvm/interrupt.c:8:
../arch/loongarch/include/asm/kvm_vcpu.h: In function 'kvm_own_lasx':
../arch/loongarch/include/asm/kvm_vcpu.h:73:39: error: no return statement in function returning non-void [-Werror=return-type]
   73 | static inline int kvm_own_lasx(struct kvm_vcpu *vcpu) { }

Fixes: db1ecca22edf ("LoongArch: KVM: Add LSX (128bit SIMD) support")
Fixes: 118e10cd893d ("LoongArch: KVM: Add LASX (256bit SIMD) support")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/kvm_vcpu.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
index e71ceb88f29ee..0cb4fdb8a9b59 100644
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -60,7 +60,7 @@ int kvm_own_lsx(struct kvm_vcpu *vcpu);
 void kvm_save_lsx(struct loongarch_fpu *fpu);
 void kvm_restore_lsx(struct loongarch_fpu *fpu);
 #else
-static inline int kvm_own_lsx(struct kvm_vcpu *vcpu) { }
+static inline int kvm_own_lsx(struct kvm_vcpu *vcpu) { return -EINVAL; }
 static inline void kvm_save_lsx(struct loongarch_fpu *fpu) { }
 static inline void kvm_restore_lsx(struct loongarch_fpu *fpu) { }
 #endif
@@ -70,7 +70,7 @@ int kvm_own_lasx(struct kvm_vcpu *vcpu);
 void kvm_save_lasx(struct loongarch_fpu *fpu);
 void kvm_restore_lasx(struct loongarch_fpu *fpu);
 #else
-static inline int kvm_own_lasx(struct kvm_vcpu *vcpu) { }
+static inline int kvm_own_lasx(struct kvm_vcpu *vcpu) { return -EINVAL; }
 static inline void kvm_save_lasx(struct loongarch_fpu *fpu) { }
 static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { }
 #endif
-- 
GitLab


From 9b3058d1f456464a02e202cc7fc660508709097c Mon Sep 17 00:00:00 2001
From: Gregory Greenman <gregory.greenman@intel.com>
Date: Tue, 2 Jan 2024 14:20:19 +0200
Subject: [PATCH 3479/4076] MAINTAINERS: remove myself as iwlwifi driver
 maintainer

As I'm resigning from Intel, it's time to remove myself as a maintainer
of iwlwifi. Good luck to Miri!

Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://msgid.link/20240102122019.1689602-1-gregory.greenman@intel.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 92152ac346c8d..d8ca0e10c8d10 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11128,7 +11128,6 @@ S:	Supported
 F:	drivers/net/wireless/intel/iwlegacy/
 
 INTEL WIRELESS WIFI LINK (iwlwifi)
-M:	Gregory Greenman <gregory.greenman@intel.com>
 M:	Miri Korenblit <miriam.rachel.korenblit@intel.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
-- 
GitLab


From e1d54d153fc3e697b841999df7cbad51492def8e Mon Sep 17 00:00:00 2001
From: Damian Muszynski <damian.muszynski@intel.com>
Date: Fri, 19 Jan 2024 17:12:38 +0100
Subject: [PATCH 3480/4076] crypto: qat - fix arbiter mapping generation
 algorithm for QAT 402xx

The commit "crypto: qat - generate dynamically arbiter mappings"
introduced a regression on qat_402xx devices.
This is reported when the driver probes the device, as indicated by
the following error messages:

  4xxx 0000:0b:00.0: enabling device (0140 -> 0142)
  4xxx 0000:0b:00.0: Generate of the thread to arbiter map failed
  4xxx 0000:0b:00.0: Direct firmware load for qat_402xx_mmp.bin failed with error -2

The root cause of this issue was the omission of a necessary function
pointer required by the mapping algorithm during the implementation.
Fix it by adding the missing function pointer.

Fixes: 5da6a2d5353e ("crypto: qat - generate dynamically arbiter mappings")
Signed-off-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
index 479062aa5e6b6..94a0ebb03d8c9 100644
--- a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
@@ -463,6 +463,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 		hw_data->fw_name = ADF_402XX_FW;
 		hw_data->fw_mmp_name = ADF_402XX_MMP;
 		hw_data->uof_get_name = uof_get_name_402xx;
+		hw_data->get_ena_thd_mask = get_ena_thd_mask;
 		break;
 	case ADF_401XX_PCI_DEVICE_ID:
 		hw_data->fw_name = ADF_4XXX_FW;
-- 
GitLab


From c5a2f74db71a849f3a60bc153d684d6d28a0c665 Mon Sep 17 00:00:00 2001
From: Gaurav Jain <gaurav.jain@nxp.com>
Date: Thu, 18 Jan 2024 14:55:57 +0530
Subject: [PATCH 3481/4076] crypto: caam - fix asynchronous hash

ahash_alg->setkey is updated to ahash_nosetkey in ahash.c
so checking setkey() function to determine hmac algorithm is not valid.

to fix this added is_hmac variable in structure caam_hash_alg to determine
whether the algorithm is hmac or not.

Fixes: 2f1f34c1bf7b ("crypto: ahash - optimize performance when wrapping shash")
Signed-off-by: Gaurav Jain <gaurav.jain@nxp.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/caam/caamalg_qi2.c | 7 +++++--
 drivers/crypto/caam/caamhash.c    | 7 +++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c
index a148ff1f0872c..a4f6884416a04 100644
--- a/drivers/crypto/caam/caamalg_qi2.c
+++ b/drivers/crypto/caam/caamalg_qi2.c
@@ -4545,6 +4545,7 @@ struct caam_hash_alg {
 	struct list_head entry;
 	struct device *dev;
 	int alg_type;
+	bool is_hmac;
 	struct ahash_alg ahash_alg;
 };
 
@@ -4571,7 +4572,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 
 	ctx->dev = caam_hash->dev;
 
-	if (alg->setkey) {
+	if (caam_hash->is_hmac) {
 		ctx->adata.key_dma = dma_map_single_attrs(ctx->dev, ctx->key,
 							  ARRAY_SIZE(ctx->key),
 							  DMA_TO_DEVICE,
@@ -4611,7 +4612,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	 * For keyed hash algorithms shared descriptors
 	 * will be created later in setkey() callback
 	 */
-	return alg->setkey ? 0 : ahash_set_sh_desc(ahash);
+	return caam_hash->is_hmac ? 0 : ahash_set_sh_desc(ahash);
 }
 
 static void caam_hash_cra_exit(struct crypto_tfm *tfm)
@@ -4646,12 +4647,14 @@ static struct caam_hash_alg *caam_hash_alloc(struct device *dev,
 			 template->hmac_name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->hmac_driver_name);
+		t_alg->is_hmac = true;
 	} else {
 		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->driver_name);
 		t_alg->ahash_alg.setkey = NULL;
+		t_alg->is_hmac = false;
 	}
 	alg->cra_module = THIS_MODULE;
 	alg->cra_init = caam_hash_cra_init;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 290c8500c247f..fdd724228c2fa 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -1753,6 +1753,7 @@ static struct caam_hash_template driver_hash[] = {
 struct caam_hash_alg {
 	struct list_head entry;
 	int alg_type;
+	bool is_hmac;
 	struct ahash_engine_alg ahash_alg;
 };
 
@@ -1804,7 +1805,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	} else {
 		if (priv->era >= 6) {
 			ctx->dir = DMA_BIDIRECTIONAL;
-			ctx->key_dir = alg->setkey ? DMA_TO_DEVICE : DMA_NONE;
+			ctx->key_dir = caam_hash->is_hmac ? DMA_TO_DEVICE : DMA_NONE;
 		} else {
 			ctx->dir = DMA_TO_DEVICE;
 			ctx->key_dir = DMA_NONE;
@@ -1862,7 +1863,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	 * For keyed hash algorithms shared descriptors
 	 * will be created later in setkey() callback
 	 */
-	return alg->setkey ? 0 : ahash_set_sh_desc(ahash);
+	return caam_hash->is_hmac ? 0 : ahash_set_sh_desc(ahash);
 }
 
 static void caam_hash_cra_exit(struct crypto_tfm *tfm)
@@ -1915,12 +1916,14 @@ caam_hash_alloc(struct caam_hash_template *template,
 			 template->hmac_name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->hmac_driver_name);
+		t_alg->is_hmac = true;
 	} else {
 		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->driver_name);
 		halg->setkey = NULL;
+		t_alg->is_hmac = false;
 	}
 	alg->cra_module = THIS_MODULE;
 	alg->cra_init = caam_hash_cra_init;
-- 
GitLab


From 96204e15310c218fd9355bdcacd02fed1d18070e Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Tue, 23 Jan 2024 17:14:20 +0000
Subject: [PATCH 3482/4076] mm: thp_get_unmapped_area must honour topdown
 preference

The addition of commit efa7df3e3bb5 ("mm: align larger anonymous mappings
on THP boundaries") caused the "virtual_address_range" mm selftest to
start failing on arm64.  Let's fix that regression.

There were 2 visible problems when running the test; 1) it takes much
longer to execute, and 2) the test fails.  Both are related:

The (first part of the) test allocates as many 1GB anonymous blocks as it
can in the low 256TB of address space, passing NULL as the addr hint to
mmap.  Before the faulty patch, all allocations were abutted and contained
in a single, merged VMA.  However, after this patch, each allocation is in
its own VMA, and there is a 2M gap between each VMA.  This causes the 2
problems in the test: 1) mmap becomes MUCH slower because there are so
many VMAs to check to find a new 1G gap.  2) mmap fails once it hits the
VMA limit (/proc/sys/vm/max_map_count).  Hitting this limit then causes a
subsequent calloc() to fail, which causes the test to fail.

The problem is that arm64 (unlike x86) selects
ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT.  But __thp_get_unmapped_area()
allocates len+2M then always aligns to the bottom of the discovered gap.
That causes the 2M hole.

Fix this by detecting cases where we can still achive the alignment goal
when moved to the top of the allocated area, if configured to prefer
top-down allocation.

While we are at it, fix thp_get_unmapped_area's use of pgoff, which should
always be zero for anonymous mappings.  Prior to the faulty change, while
it was possible for user space to pass in pgoff!=0, the old
mm->get_unmapped_area() handler would not use it.  thp_get_unmapped_area()
does use it, so let's explicitly zero it before calling the handler.  This
should also be the correct behavior for arches that define their own
get_unmapped_area() handler.

Link: https://lkml.kernel.org/r/20240123171420.3970220-1-ryan.roberts@arm.com
Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries")
Closes: https://lore.kernel.org/linux-mm/1e8f5ac7-54ce-433a-ae53-81522b2320e1@arm.com/
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 10 ++++++++--
 mm/mmap.c        |  6 ++++--
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 172b85208276e..94c958f7ebb50 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -810,7 +810,7 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 {
 	loff_t off_end = off + len;
 	loff_t off_align = round_up(off, size);
-	unsigned long len_pad, ret;
+	unsigned long len_pad, ret, off_sub;
 
 	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
 		return 0;
@@ -839,7 +839,13 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	if (ret == addr)
 		return addr;
 
-	ret += (off - ret) & (size - 1);
+	off_sub = (off - ret) & (size - 1);
+
+	if (current->mm->get_unmapped_area == arch_get_unmapped_area_topdown &&
+	    !off_sub)
+		return ret + size;
+
+	ret += off_sub;
 	return ret;
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index b78e83d351d28..d89770eaab6b6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1825,15 +1825,17 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		/*
 		 * mmap_region() will call shmem_zero_setup() to create a file,
 		 * so use shmem's get_unmapped_area in case it can be huge.
-		 * do_mmap() will clear pgoff, so match alignment.
 		 */
-		pgoff = 0;
 		get_area = shmem_get_unmapped_area;
 	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 		/* Ensures that larger anonymous mappings are THP aligned. */
 		get_area = thp_get_unmapped_area;
 	}
 
+	/* Always treat pgoff as zero for anonymous memory. */
+	if (!file)
+		pgoff = 0;
+
 	addr = get_area(file, addr, len, pgoff, flags);
 	if (IS_ERR_VALUE(addr))
 		return addr;
-- 
GitLab


From dd3c33ccbb8f0dc6a256dc55e7607569aea69721 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 23 Jan 2024 09:46:54 -0800
Subject: [PATCH 3483/4076] MIPS: BCM63XX: Fix missing prototypes

Most of the symbols for which we do not have a prototype can actually be
made static and for the few that cannot, there is already a declaration
in a header for it.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/bcm63xx/boards/board_bcm963xx.c | 2 +-
 arch/mips/bcm63xx/dev-rng.c               | 2 +-
 arch/mips/bcm63xx/dev-uart.c              | 1 +
 arch/mips/bcm63xx/dev-wdt.c               | 2 +-
 arch/mips/bcm63xx/irq.c                   | 2 +-
 arch/mips/bcm63xx/setup.c                 | 2 +-
 arch/mips/bcm63xx/timer.c                 | 2 +-
 7 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c
index 01aff80a59672..99f321b6e417b 100644
--- a/arch/mips/bcm63xx/boards/board_bcm963xx.c
+++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c
@@ -702,7 +702,7 @@ static struct ssb_sprom bcm63xx_sprom = {
 	.boardflags_hi		= 0x0000,
 };
 
-int bcm63xx_get_fallback_sprom(struct ssb_bus *bus, struct ssb_sprom *out)
+static int bcm63xx_get_fallback_sprom(struct ssb_bus *bus, struct ssb_sprom *out)
 {
 	if (bus->bustype == SSB_BUSTYPE_PCI) {
 		memcpy(out, &bcm63xx_sprom, sizeof(struct ssb_sprom));
diff --git a/arch/mips/bcm63xx/dev-rng.c b/arch/mips/bcm63xx/dev-rng.c
index d277b4dc6c688..f94151f7c96fe 100644
--- a/arch/mips/bcm63xx/dev-rng.c
+++ b/arch/mips/bcm63xx/dev-rng.c
@@ -26,7 +26,7 @@ static struct platform_device bcm63xx_rng_device = {
 	.resource	= rng_resources,
 };
 
-int __init bcm63xx_rng_register(void)
+static int __init bcm63xx_rng_register(void)
 {
 	if (!BCMCPU_IS_6368())
 		return -ENODEV;
diff --git a/arch/mips/bcm63xx/dev-uart.c b/arch/mips/bcm63xx/dev-uart.c
index 3bc7f3bfc9ad5..5d6bf0445b299 100644
--- a/arch/mips/bcm63xx/dev-uart.c
+++ b/arch/mips/bcm63xx/dev-uart.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <bcm63xx_cpu.h>
+#include <bcm63xx_dev_uart.h>
 
 static struct resource uart0_resources[] = {
 	{
diff --git a/arch/mips/bcm63xx/dev-wdt.c b/arch/mips/bcm63xx/dev-wdt.c
index 42130914a3c21..302bf7ed5ad5a 100644
--- a/arch/mips/bcm63xx/dev-wdt.c
+++ b/arch/mips/bcm63xx/dev-wdt.c
@@ -34,7 +34,7 @@ static struct platform_device bcm63xx_wdt_device = {
 	},
 };
 
-int __init bcm63xx_wdt_register(void)
+static int __init bcm63xx_wdt_register(void)
 {
 	wdt_resources[0].start = bcm63xx_regset_address(RSET_WDT);
 	wdt_resources[0].end = wdt_resources[0].start;
diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c
index 2548013442f6d..6240a8f88ea36 100644
--- a/arch/mips/bcm63xx/irq.c
+++ b/arch/mips/bcm63xx/irq.c
@@ -72,7 +72,7 @@ static inline int enable_irq_for_cpu(int cpu, struct irq_data *d,
  */
 
 #define BUILD_IPIC_INTERNAL(width)					\
-void __dispatch_internal_##width(int cpu)				\
+static void __dispatch_internal_##width(int cpu)			\
 {									\
 	u32 pending[width / 32];					\
 	unsigned int src, tgt;						\
diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c
index d811e3e03f819..c13ddb544a23b 100644
--- a/arch/mips/bcm63xx/setup.c
+++ b/arch/mips/bcm63xx/setup.c
@@ -159,7 +159,7 @@ void __init plat_mem_setup(void)
 	board_setup();
 }
 
-int __init bcm63xx_register_devices(void)
+static int __init bcm63xx_register_devices(void)
 {
 	/* register gpiochip */
 	bcm63xx_gpio_init();
diff --git a/arch/mips/bcm63xx/timer.c b/arch/mips/bcm63xx/timer.c
index a86065854c0c8..74b83807df30a 100644
--- a/arch/mips/bcm63xx/timer.c
+++ b/arch/mips/bcm63xx/timer.c
@@ -178,7 +178,7 @@ int bcm63xx_timer_set(int id, int monotonic, unsigned int countdown_us)
 
 EXPORT_SYMBOL(bcm63xx_timer_set);
 
-int bcm63xx_timer_init(void)
+static int bcm63xx_timer_init(void)
 {
 	int ret, irq;
 	u32 reg;
-- 
GitLab


From abcabb9e30a1f9a69c76776f8abffc31c377b542 Mon Sep 17 00:00:00 2001
From: Huang Pei <huangpei@loongson.cn>
Date: Tue, 23 Jan 2024 09:47:57 +0800
Subject: [PATCH 3484/4076] MIPS: reserve exception vector space ONLY ONCE

"cpu_probe" is called both by BP and APs, but reserving exception vector
(like 0x0-0x1000) called by "cpu_probe" need once and calling on APs is
too late since memblock is unavailable at that time.

So, reserve exception vector ONLY by BP.

Suggested-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Huang Pei <huangpei@loongson.cn>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/traps.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index dec6878b35f62..a1c1cb5de9132 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2007,7 +2007,13 @@ unsigned long vi_handlers[64];
 
 void reserve_exception_space(phys_addr_t addr, unsigned long size)
 {
-	memblock_reserve(addr, size);
+	/*
+	 * reserve exception space on CPUs other than CPU0
+	 * is too late, since memblock is unavailable when APs
+	 * up
+	 */
+	if (smp_processor_id() == 0)
+		memblock_reserve(addr, size);
 }
 
 void __init *set_except_vector(int n, void *addr)
-- 
GitLab


From ce7b1b97776ec0b068c4dd6b6dbb48ae09a23519 Mon Sep 17 00:00:00 2001
From: Huang Pei <huangpei@loongson.cn>
Date: Tue, 23 Jan 2024 09:47:58 +0800
Subject: [PATCH 3485/4076] MIPS: loongson64: set nid for reserved memblock
 region

Commit 61167ad5fecd("mm: pass nid to reserve_bootmem_region()") reveals
that reserved memblock regions have no valid node id set, just set it
right since loongson64 firmware makes it clear in memory layout info.

This works around booting failure on 3A1000+ since commit 61167ad5fecd
("mm: pass nid to reserve_bootmem_region()") under
CONFIG_DEFERRED_STRUCT_PAGE_INIT.

Signed-off-by: Huang Pei <huangpei@loongson.cn>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/loongson64/init.c | 2 ++
 arch/mips/loongson64/numa.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index f25caa6aa9d30..000ba91c0886e 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -103,6 +103,8 @@ void __init szmem(unsigned int node)
 	if (loongson_sysconf.vgabios_addr)
 		memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr),
 				SZ_256K);
+	/* set nid for reserved memory */
+	memblock_set_node((u64)node << 44, (u64)(node+1) << 44, &memblock.reserved, node);
 }
 
 #ifndef CONFIG_NUMA
diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index 8f61e93c0c5bc..6345e096c5326 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -132,6 +132,8 @@ static void __init node_mem_init(unsigned int node)
 
 		/* Reserve pfn range 0~node[0]->node_start_pfn */
 		memblock_reserve(0, PAGE_SIZE * start_pfn);
+		/* set nid for reserved memory on node 0 */
+		memblock_set_node(0, (u64)1 << 44, &memblock.reserved, 1);
 	}
 }
 
-- 
GitLab


From 4bf2a626dc4bb46f0754d8ac02ec8584ff114ad5 Mon Sep 17 00:00:00 2001
From: Aleksander Jan Bajkowski <olek2@wp.pl>
Date: Mon, 22 Jan 2024 19:47:09 +0100
Subject: [PATCH 3486/4076] MIPS: lantiq: register smp_ops on non-smp platforms

Lantiq uses a common kernel config for devices with 24Kc and 34Kc cores.
The changes made previously to add support for interrupts on all cores
work on 24Kc platforms with SMP disabled and 34Kc platforms with SMP
enabled. This patch fixes boot issues on Danube (single core 24Kc) with
SMP enabled.

Fixes: 730320fd770d ("MIPS: lantiq: enable all hardware interrupts on second VPE")
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/lantiq/prom.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
index a3cf293658581..0c45767eacf67 100644
--- a/arch/mips/lantiq/prom.c
+++ b/arch/mips/lantiq/prom.c
@@ -108,10 +108,9 @@ void __init prom_init(void)
 	prom_init_cmdline();
 
 #if defined(CONFIG_MIPS_MT_SMP)
-	if (cpu_has_mipsmt) {
-		lantiq_smp_ops = vsmp_smp_ops;
+	lantiq_smp_ops = vsmp_smp_ops;
+	if (cpu_has_mipsmt)
 		lantiq_smp_ops.init_secondary = lantiq_init_secondary;
-		register_smp_ops(&lantiq_smp_ops);
-	}
+	register_smp_ops(&lantiq_smp_ops);
 #endif
 }
-- 
GitLab


From 353d321f63f7dbfc9ef58498cc732c9fe886a596 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 23 Jan 2024 20:08:11 +0200
Subject: [PATCH 3487/4076] wifi: iwlwifi: fix double-free bug

The storage for the TLV PC register data wasn't done like all
the other storage in the drv->fw area, which is cleared at the
end of deallocation. Therefore, the freeing must also be done
differently, explicitly NULL'ing it out after the free, since
otherwise there's a nasty double-free bug here if a file fails
to load after this has been parsed, and we get another free
later (e.g. because no other file exists.) Fix that by adding
the missing NULL assignment.

Cc: stable@vger.kernel.org
Fixes: 5e31b3df86ec ("wifi: iwlwifi: dbg: print pc register data once fw dump occurred")
Reported-by: Guy Kaplan <guy.kaplan@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240123200528.675f3c24ec0d.I6ab4015cd78d82dd95471f840629972ef0331de3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index ffe2670720c92..abf8001bdac17 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -128,6 +128,7 @@ static void iwl_dealloc_ucode(struct iwl_drv *drv)
 	kfree(drv->fw.ucode_capa.cmd_versions);
 	kfree(drv->fw.phy_integration_ver);
 	kfree(drv->trans->dbg.pc_data);
+	drv->trans->dbg.pc_data = NULL;
 
 	for (i = 0; i < IWL_UCODE_TYPE_MAX; i++)
 		iwl_free_fw_img(drv, drv->fw.img + i);
-- 
GitLab


From b743287d7a0007493f5cada34ed2085d475050b4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 25 Jan 2024 09:51:09 +0100
Subject: [PATCH 3488/4076] wifi: cfg80211: fix wiphy delayed work queueing

When a wiphy work is queued with timer, and then again
without a delay, it's started immediately but *also*
started again after the timer expires. This can lead,
for example, to warnings in mac80211's offchannel code
as reported by Jouni. Running the same work twice isn't
expected, of course. Fix this by deleting the timer at
this point, when queuing immediately due to delay=0.

Cc: stable@vger.kernel.org
Reported-by: Jouni Malinen <j@w1.fi>
Fixes: a3ee4dc84c4e ("wifi: cfg80211: add a work abstraction with special semantics")
Link: https://msgid.link/20240125095108.2feb0eaaa446.I4617f3210ed0e7f252290d5970dac6a876aa595b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 409d74c57ca0d..3fb1b637352a9 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010		Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -1661,6 +1661,7 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy,
 			      unsigned long delay)
 {
 	if (!delay) {
+		del_timer(&dwork->timer);
 		wiphy_work_queue(wiphy, &dwork->work);
 		return;
 	}
-- 
GitLab


From 3a3ef3940798e85121066a859127e72a528dc32a Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Tue, 23 Jan 2024 20:08:19 +0200
Subject: [PATCH 3489/4076] wifi: iwlwifi: mvm: skip adding debugfs symlink for
 reconfig

The function to add an interface may be called without a previous
removal if the HW is being reconfigured. As such, only add the symlink
if the hardware is not being reconfigured due to a HW_RESTART.

Fixes: c36235acb34f ("wifi: iwlwifi: mvm: rework debugfs handling")
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240123200528.314395eacda4.I5823e962c3c3674b942383733debd10b3fe903e2@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c     | 6 ++++--
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 3 ++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 7f13dff04b265..3447d67a8b311 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1600,7 +1600,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 	 */
 	if (vif->type == NL80211_IFTYPE_AP ||
 	    vif->type == NL80211_IFTYPE_ADHOC) {
-		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+		if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+			iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 		ret = 0;
 		goto out;
 	}
@@ -1640,7 +1641,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 			iwl_mvm_chandef_get_primary_80(&vif->bss_conf.chandef);
 	}
 
-	iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 
 	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
 	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 61170173f917a..1f36e934ef69e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -81,7 +81,8 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
 		ieee80211_hw_set(mvm->hw, RX_INCLUDES_FCS);
 	}
 
-	iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 
 	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
 	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
-- 
GitLab


From 1b023d475ae928f3036cefee9ea0a499af1d8900 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 16 Jan 2024 21:05:25 -0600
Subject: [PATCH 3490/4076] wifi: mac80211: Drop WBRF debugging statements

Due to the way that debugging is used in the mac80211 subsystem
this message ends up being noisier than it needs to be.

As the statement is only useful at a first stage of triage for
BIOS bugs, just drop it.

Cc: Jun Ma <Jun.Ma2@amd.com>
Suggested-by: Kalle Valo <kvalo@kernel.org>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240117030525.539-1-mario.limonciello@amd.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/wbrf.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/mac80211/wbrf.c b/net/mac80211/wbrf.c
index a05c5b971789c..3a86123091373 100644
--- a/net/mac80211/wbrf.c
+++ b/net/mac80211/wbrf.c
@@ -23,8 +23,6 @@ void ieee80211_check_wbrf_support(struct ieee80211_local *local)
 		return;
 
 	local->wbrf_supported = acpi_amd_wbrf_supported_producer(dev);
-	dev_dbg(dev, "WBRF is %s supported\n",
-		local->wbrf_supported ? "" : "not");
 }
 
 static void get_chan_freq_boundary(u32 center_freq, u32 bandwidth, u64 *start, u64 *end)
-- 
GitLab


From cc4b2dd95f0d1eba8c691b36e8f4d1795582f1ff Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Thu, 25 Jan 2024 20:00:39 +0800
Subject: [PATCH 3491/4076] erofs: fix infinite loop due to a race of filling
 compressed_bvecs

I encountered a race issue after lengthy (~594647 secs) stress tests on
a 64k-page arm64 VM with several 4k-block EROFS images.  The timing
is like below:

z_erofs_try_inplace_io                  z_erofs_fill_bio_vec
  cmpxchg(&compressed_bvecs[].page,
          NULL, ..)
                                        [access bufvec]
  compressed_bvecs[] = *bvec;

Previously, z_erofs_submit_queue() just accessed bufvec->page only, so
other fields in bufvec didn't matter.  After the subpage block support
is landed, .offset and .end can be used too, but filling bufvec isn't
an atomic operation which can cause inconsistency.

Let's use a spinlock to keep the atomicity of each bufvec.  More
specifically, just reuse the existing spinlock `pcl->obj.lockref.lock`
since it's rarely used (also it takes a short time if even used) as long
as the pcluster has a reference.

Fixes: 192351616a9d ("erofs: support I/O submission for sub-page compressed blocks")
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Sandeep Dhavale <dhavale@google.com>
Link: https://lore.kernel.org/r/20240125120039.3228103-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/zdata.c | 74 +++++++++++++++++++++++++-----------------------
 1 file changed, 38 insertions(+), 36 deletions(-)

diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 583c062cd0e42..c1c77166b30ff 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -563,21 +563,19 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 			__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
 	unsigned int i;
 
-	if (i_blocksize(fe->inode) != PAGE_SIZE)
-		return;
-	if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
+	if (i_blocksize(fe->inode) != PAGE_SIZE ||
+	    fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
 		return;
 
 	for (i = 0; i < pclusterpages; ++i) {
 		struct page *page, *newpage;
 		void *t;	/* mark pages just found for debugging */
 
-		/* the compressed page was loaded before */
+		/* Inaccurate check w/o locking to avoid unneeded lookups */
 		if (READ_ONCE(pcl->compressed_bvecs[i].page))
 			continue;
 
 		page = find_get_page(mc, pcl->obj.index + i);
-
 		if (page) {
 			t = (void *)((unsigned long)page | 1);
 			newpage = NULL;
@@ -597,9 +595,13 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 			set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE);
 			t = (void *)((unsigned long)newpage | 1);
 		}
-
-		if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL, t))
+		spin_lock(&pcl->obj.lockref.lock);
+		if (!pcl->compressed_bvecs[i].page) {
+			pcl->compressed_bvecs[i].page = t;
+			spin_unlock(&pcl->obj.lockref.lock);
 			continue;
+		}
+		spin_unlock(&pcl->obj.lockref.lock);
 
 		if (page)
 			put_page(page);
@@ -718,31 +720,25 @@ int erofs_init_managed_cache(struct super_block *sb)
 	return 0;
 }
 
-static bool z_erofs_try_inplace_io(struct z_erofs_decompress_frontend *fe,
-				   struct z_erofs_bvec *bvec)
-{
-	struct z_erofs_pcluster *const pcl = fe->pcl;
-
-	while (fe->icur > 0) {
-		if (!cmpxchg(&pcl->compressed_bvecs[--fe->icur].page,
-			     NULL, bvec->page)) {
-			pcl->compressed_bvecs[fe->icur] = *bvec;
-			return true;
-		}
-	}
-	return false;
-}
-
 /* callers must be with pcluster lock held */
 static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe,
 			       struct z_erofs_bvec *bvec, bool exclusive)
 {
+	struct z_erofs_pcluster *pcl = fe->pcl;
 	int ret;
 
 	if (exclusive) {
 		/* give priority for inplaceio to use file pages first */
-		if (z_erofs_try_inplace_io(fe, bvec))
+		spin_lock(&pcl->obj.lockref.lock);
+		while (fe->icur > 0) {
+			if (pcl->compressed_bvecs[--fe->icur].page)
+				continue;
+			pcl->compressed_bvecs[fe->icur] = *bvec;
+			spin_unlock(&pcl->obj.lockref.lock);
 			return 0;
+		}
+		spin_unlock(&pcl->obj.lockref.lock);
+
 		/* otherwise, check if it can be used as a bvpage */
 		if (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED &&
 		    !fe->candidate_bvpage)
@@ -1423,23 +1419,26 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
 {
 	gfp_t gfp = mapping_gfp_mask(mc);
 	bool tocache = false;
-	struct z_erofs_bvec *zbv = pcl->compressed_bvecs + nr;
+	struct z_erofs_bvec zbv;
 	struct address_space *mapping;
-	struct page *page, *oldpage;
+	struct page *page;
 	int justfound, bs = i_blocksize(f->inode);
 
 	/* Except for inplace pages, the entire page can be used for I/Os */
 	bvec->bv_offset = 0;
 	bvec->bv_len = PAGE_SIZE;
 repeat:
-	oldpage = READ_ONCE(zbv->page);
-	if (!oldpage)
+	spin_lock(&pcl->obj.lockref.lock);
+	zbv = pcl->compressed_bvecs[nr];
+	page = zbv.page;
+	justfound = (unsigned long)page & 1UL;
+	page = (struct page *)((unsigned long)page & ~1UL);
+	pcl->compressed_bvecs[nr].page = page;
+	spin_unlock(&pcl->obj.lockref.lock);
+	if (!page)
 		goto out_allocpage;
 
-	justfound = (unsigned long)oldpage & 1UL;
-	page = (struct page *)((unsigned long)oldpage & ~1UL);
 	bvec->bv_page = page;
-
 	DBG_BUGON(z_erofs_is_shortlived_page(page));
 	/*
 	 * Handle preallocated cached pages.  We tried to allocate such pages
@@ -1448,7 +1447,6 @@ repeat:
 	 */
 	if (page->private == Z_EROFS_PREALLOCATED_PAGE) {
 		set_page_private(page, 0);
-		WRITE_ONCE(zbv->page, page);
 		tocache = true;
 		goto out_tocache;
 	}
@@ -1459,9 +1457,9 @@ repeat:
 	 * therefore it is impossible for `mapping` to be NULL.
 	 */
 	if (mapping && mapping != mc) {
-		if (zbv->offset < 0)
-			bvec->bv_offset = round_up(-zbv->offset, bs);
-		bvec->bv_len = round_up(zbv->end, bs) - bvec->bv_offset;
+		if (zbv.offset < 0)
+			bvec->bv_offset = round_up(-zbv.offset, bs);
+		bvec->bv_len = round_up(zbv.end, bs) - bvec->bv_offset;
 		return;
 	}
 
@@ -1471,7 +1469,6 @@ repeat:
 
 	/* the cached page is still in managed cache */
 	if (page->mapping == mc) {
-		WRITE_ONCE(zbv->page, page);
 		/*
 		 * The cached page is still available but without a valid
 		 * `->private` pcluster hint.  Let's reconnect them.
@@ -1503,11 +1500,15 @@ repeat:
 	put_page(page);
 out_allocpage:
 	page = erofs_allocpage(&f->pagepool, gfp | __GFP_NOFAIL);
-	if (oldpage != cmpxchg(&zbv->page, oldpage, page)) {
+	spin_lock(&pcl->obj.lockref.lock);
+	if (pcl->compressed_bvecs[nr].page) {
 		erofs_pagepool_add(&f->pagepool, page);
+		spin_unlock(&pcl->obj.lockref.lock);
 		cond_resched();
 		goto repeat;
 	}
+	pcl->compressed_bvecs[nr].page = page;
+	spin_unlock(&pcl->obj.lockref.lock);
 	bvec->bv_page = page;
 out_tocache:
 	if (!tocache || bs != PAGE_SIZE ||
@@ -1685,6 +1686,7 @@ submit_bio_retry:
 
 			if (cur + bvec.bv_len > end)
 				bvec.bv_len = end - cur;
+			DBG_BUGON(bvec.bv_len < sb->s_blocksize);
 			if (!bio_add_page(bio, bvec.bv_page, bvec.bv_len,
 					  bvec.bv_offset))
 				goto submit_bio_retry;
-- 
GitLab


From 1f4a994be2c3d13852fd5c1054f292bd303352cc Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@outlook.com>
Date: Fri, 26 Jan 2024 17:20:00 +0800
Subject: [PATCH 3492/4076] riscv: dts: sophgo: separate sg2042 mtime and
 mtimecmp to fit aclint format

Change the timer layout in the dtb to fit the format that needed by
the SBI.

Fixes: 967a94a92aaa ("riscv: dts: add initial Sophgo SG2042 SoC device tree")
Reviewed-by: Chen Wang <unicorn_wang@outlook.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Inochi Amaoto <inochiama@outlook.com>
Signed-off-by: Chen Wang <unicorn_wang@outlook.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/riscv/boot/dts/sophgo/sg2042.dtsi | 80 +++++++++++++++-----------
 1 file changed, 48 insertions(+), 32 deletions(-)

diff --git a/arch/riscv/boot/dts/sophgo/sg2042.dtsi b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
index 93256540d0788..ead1cc35d88b2 100644
--- a/arch/riscv/boot/dts/sophgo/sg2042.dtsi
+++ b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
@@ -93,144 +93,160 @@
 					      <&cpu63_intc 3>;
 		};
 
-		clint_mtimer0: timer@70ac000000 {
+		clint_mtimer0: timer@70ac004000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac000000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac004000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu0_intc 7>,
 					      <&cpu1_intc 7>,
 					      <&cpu2_intc 7>,
 					      <&cpu3_intc 7>;
 		};
 
-		clint_mtimer1: timer@70ac010000 {
+		clint_mtimer1: timer@70ac014000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac010000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac014000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu4_intc 7>,
 					      <&cpu5_intc 7>,
 					      <&cpu6_intc 7>,
 					      <&cpu7_intc 7>;
 		};
 
-		clint_mtimer2: timer@70ac020000 {
+		clint_mtimer2: timer@70ac024000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac020000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac024000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu8_intc 7>,
 					      <&cpu9_intc 7>,
 					      <&cpu10_intc 7>,
 					      <&cpu11_intc 7>;
 		};
 
-		clint_mtimer3: timer@70ac030000 {
+		clint_mtimer3: timer@70ac034000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac030000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac034000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu12_intc 7>,
 					      <&cpu13_intc 7>,
 					      <&cpu14_intc 7>,
 					      <&cpu15_intc 7>;
 		};
 
-		clint_mtimer4: timer@70ac040000 {
+		clint_mtimer4: timer@70ac044000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac040000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac044000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu16_intc 7>,
 					      <&cpu17_intc 7>,
 					      <&cpu18_intc 7>,
 					      <&cpu19_intc 7>;
 		};
 
-		clint_mtimer5: timer@70ac050000 {
+		clint_mtimer5: timer@70ac054000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac050000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac054000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu20_intc 7>,
 					      <&cpu21_intc 7>,
 					      <&cpu22_intc 7>,
 					      <&cpu23_intc 7>;
 		};
 
-		clint_mtimer6: timer@70ac060000 {
+		clint_mtimer6: timer@70ac064000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac060000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac064000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu24_intc 7>,
 					      <&cpu25_intc 7>,
 					      <&cpu26_intc 7>,
 					      <&cpu27_intc 7>;
 		};
 
-		clint_mtimer7: timer@70ac070000 {
+		clint_mtimer7: timer@70ac074000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac070000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac074000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu28_intc 7>,
 					      <&cpu29_intc 7>,
 					      <&cpu30_intc 7>,
 					      <&cpu31_intc 7>;
 		};
 
-		clint_mtimer8: timer@70ac080000 {
+		clint_mtimer8: timer@70ac084000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac080000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac084000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu32_intc 7>,
 					      <&cpu33_intc 7>,
 					      <&cpu34_intc 7>,
 					      <&cpu35_intc 7>;
 		};
 
-		clint_mtimer9: timer@70ac090000 {
+		clint_mtimer9: timer@70ac094000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac090000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac094000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu36_intc 7>,
 					      <&cpu37_intc 7>,
 					      <&cpu38_intc 7>,
 					      <&cpu39_intc 7>;
 		};
 
-		clint_mtimer10: timer@70ac0a0000 {
+		clint_mtimer10: timer@70ac0a4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0a0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0a4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu40_intc 7>,
 					      <&cpu41_intc 7>,
 					      <&cpu42_intc 7>,
 					      <&cpu43_intc 7>;
 		};
 
-		clint_mtimer11: timer@70ac0b0000 {
+		clint_mtimer11: timer@70ac0b4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0b0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0b4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu44_intc 7>,
 					      <&cpu45_intc 7>,
 					      <&cpu46_intc 7>,
 					      <&cpu47_intc 7>;
 		};
 
-		clint_mtimer12: timer@70ac0c0000 {
+		clint_mtimer12: timer@70ac0c4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0c0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0c4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu48_intc 7>,
 					      <&cpu49_intc 7>,
 					      <&cpu50_intc 7>,
 					      <&cpu51_intc 7>;
 		};
 
-		clint_mtimer13: timer@70ac0d0000 {
+		clint_mtimer13: timer@70ac0d4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0d0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0d4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu52_intc 7>,
 					      <&cpu53_intc 7>,
 					      <&cpu54_intc 7>,
 					      <&cpu55_intc 7>;
 		};
 
-		clint_mtimer14: timer@70ac0e0000 {
+		clint_mtimer14: timer@70ac0e4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0e0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0e4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu56_intc 7>,
 					      <&cpu57_intc 7>,
 					      <&cpu58_intc 7>,
 					      <&cpu59_intc 7>;
 		};
 
-		clint_mtimer15: timer@70ac0f0000 {
+		clint_mtimer15: timer@70ac0f4000 {
 			compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer";
-			reg = <0x00000070 0xac0f0000 0x00000000 0x00007ff8>;
+			reg = <0x00000070 0xac0f4000 0x00000000 0x0000c000>;
+			reg-names = "mtimecmp";
 			interrupts-extended = <&cpu60_intc 7>,
 					      <&cpu61_intc 7>,
 					      <&cpu62_intc 7>,
-- 
GitLab


From ff3d5d04db07e5374758baa7e877fde8d683ebab Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Mon, 13 Nov 2023 17:43:44 +0100
Subject: [PATCH 3493/4076] drm: bridge: samsung-dsim: Don't use
 FORCE_STOP_STATE

The FORCE_STOP_STATE bit is unsuitable to force the DSI link into LP-11
mode. It seems the bridge internally queues DSI packets and when the
FORCE_STOP_STATE bit is cleared, they are sent in close succession
without any useful timing (this also means that the DSI lanes won't go
into LP-11 mode). The length of this gibberish varies between 1ms and
5ms. This sometimes breaks an attached bridge (TI SN65DSI84 in this
case). In our case, the bridge will fail in about 1 per 500 reboots.

The FORCE_STOP_STATE handling was introduced to have the DSI lanes in
LP-11 state during the .pre_enable phase. But as it turns out, none of
this is needed at all. Between samsung_dsim_init() and
samsung_dsim_set_display_enable() the lanes are already in LP-11 mode.
The code as it was before commit 20c827683de0 ("drm: bridge:
samsung-dsim: Fix init during host transfer") and 0c14d3130654 ("drm:
bridge: samsung-dsim: Fix i.MX8M enable flow to meet spec") was correct
in this regard.

This patch basically reverts both commits. It was tested on an i.MX8M
SoC with an SN65DSI84 bridge. The signals were probed and the DSI
packets were decoded during initialization and link start-up. After this
patch the first DSI packet on the link is a VSYNC packet and the timing
is correct.

Command mode between .pre_enable and .enable was also briefly tested by
a quick hack. There was no DSI link partner which would have responded,
but it was made sure the DSI packet was send on the link. As a side
note, the command mode seems to just work in HS mode. I couldn't find
that the bridge will handle commands in LP mode.

Fixes: 20c827683de0 ("drm: bridge: samsung-dsim: Fix init during host transfer")
Fixes: 0c14d3130654 ("drm: bridge: samsung-dsim: Fix i.MX8M enable flow to meet spec")
Signed-off-by: Michael Walle <mwalle@kernel.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231113164344.1612602-1-mwalle@kernel.org
---
 drivers/gpu/drm/bridge/samsung-dsim.c | 32 ++-------------------------
 1 file changed, 2 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c
index be5914caa17d5..63a1a0c88be4d 100644
--- a/drivers/gpu/drm/bridge/samsung-dsim.c
+++ b/drivers/gpu/drm/bridge/samsung-dsim.c
@@ -969,10 +969,6 @@ static int samsung_dsim_init_link(struct samsung_dsim *dsi)
 	reg = samsung_dsim_read(dsi, DSIM_ESCMODE_REG);
 	reg &= ~DSIM_STOP_STATE_CNT_MASK;
 	reg |= DSIM_STOP_STATE_CNT(driver_data->reg_values[STOP_STATE_CNT]);
-
-	if (!samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type))
-		reg |= DSIM_FORCE_STOP_STATE;
-
 	samsung_dsim_write(dsi, DSIM_ESCMODE_REG, reg);
 
 	reg = DSIM_BTA_TIMEOUT(0xff) | DSIM_LPDR_TIMEOUT(0xffff);
@@ -1431,18 +1427,6 @@ static void samsung_dsim_disable_irq(struct samsung_dsim *dsi)
 	disable_irq(dsi->irq);
 }
 
-static void samsung_dsim_set_stop_state(struct samsung_dsim *dsi, bool enable)
-{
-	u32 reg = samsung_dsim_read(dsi, DSIM_ESCMODE_REG);
-
-	if (enable)
-		reg |= DSIM_FORCE_STOP_STATE;
-	else
-		reg &= ~DSIM_FORCE_STOP_STATE;
-
-	samsung_dsim_write(dsi, DSIM_ESCMODE_REG, reg);
-}
-
 static int samsung_dsim_init(struct samsung_dsim *dsi)
 {
 	const struct samsung_dsim_driver_data *driver_data = dsi->driver_data;
@@ -1492,9 +1476,6 @@ static void samsung_dsim_atomic_pre_enable(struct drm_bridge *bridge,
 		ret = samsung_dsim_init(dsi);
 		if (ret)
 			return;
-
-		samsung_dsim_set_display_mode(dsi);
-		samsung_dsim_set_display_enable(dsi, true);
 	}
 }
 
@@ -1503,12 +1484,8 @@ static void samsung_dsim_atomic_enable(struct drm_bridge *bridge,
 {
 	struct samsung_dsim *dsi = bridge_to_dsi(bridge);
 
-	if (samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type)) {
-		samsung_dsim_set_display_mode(dsi);
-		samsung_dsim_set_display_enable(dsi, true);
-	} else {
-		samsung_dsim_set_stop_state(dsi, false);
-	}
+	samsung_dsim_set_display_mode(dsi);
+	samsung_dsim_set_display_enable(dsi, true);
 
 	dsi->state |= DSIM_STATE_VIDOUT_AVAILABLE;
 }
@@ -1521,9 +1498,6 @@ static void samsung_dsim_atomic_disable(struct drm_bridge *bridge,
 	if (!(dsi->state & DSIM_STATE_ENABLED))
 		return;
 
-	if (!samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type))
-		samsung_dsim_set_stop_state(dsi, true);
-
 	dsi->state &= ~DSIM_STATE_VIDOUT_AVAILABLE;
 }
 
@@ -1828,8 +1802,6 @@ static ssize_t samsung_dsim_host_transfer(struct mipi_dsi_host *host,
 	if (ret)
 		return ret;
 
-	samsung_dsim_set_stop_state(dsi, false);
-
 	ret = mipi_dsi_create_packet(&xfer.packet, msg);
 	if (ret < 0)
 		return ret;
-- 
GitLab


From 690811f0128eb6034e5fd011c3c54878839b4014 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Jan 2024 11:00:14 -0300
Subject: [PATCH 3494/4076] tools headers uapi: Sync linux/stat.h with the
 kernel sources to pick STATX_MNT_ID_UNIQUE

To pick the changes from:

  98d2b43081972abe ("add unique mount ID")

That add STATX_MNT_ID_UNIQUE that was manually added to
tools/perf/trace/beauty/statx.c, at some point this should move to the
shell based automated way.

This silences this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/stat.h include/uapi/linux/stat.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZbJq08s19890WDo-@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/stat.h | 1 +
 tools/perf/trace/beauty/statx.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 7cab2c65d3d7f..2f2ee82d55175 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -154,6 +154,7 @@ struct statx {
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index 5f5320f7c6e27..dc5943a6352d9 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -67,6 +67,7 @@ size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_a
 	P_FLAG(BTIME);
 	P_FLAG(MNT_ID);
 	P_FLAG(DIOALIGN);
+	P_FLAG(MNT_ID_UNIQUE);
 
 #undef P_FLAG
 
-- 
GitLab


From 174372668933ede569b9e56eab26971669a6a0a9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Jan 2024 11:08:44 -0300
Subject: [PATCH 3495/4076] tools arch x86: Sync the msr-index.h copy with the
 kernel sources to pick IA32_MKTME_KEYID_PARTITIONING

To pick up the changes in:

  765a0542fdc7aad7 ("x86/virt/tdx: Detect TDX during kernel boot")

Addressing this tools/perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h

That makes the beautification scripts to pick some new entries:

  $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before
  $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h
  $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after
  $ diff -u before after
  --- before	2024-01-25 11:08:12.363223880 -0300
  +++ after	2024-01-25 11:08:24.839307699 -0300
  @@ -21,6 +21,7 @@
   	[0x0000004f] = "PPIN",
   	[0x00000060] = "LBR_CORE_TO",
   	[0x00000079] = "IA32_UCODE_WRITE",
  +	[0x00000087] = "IA32_MKTME_KEYID_PARTITIONING",
   	[0x0000008b] = "AMD64_PATCH_LEVEL",
   	[0x0000008C] = "IA32_SGXLEPUBKEYHASH0",
   	[0x0000008D] = "IA32_SGXLEPUBKEYHASH1",
  $

Now one can trace systemwide asking to see backtraces to where that MSR
is being read/written, see this example with a previous update:

  # perf trace -e msr:*_msr/max-stack=32/ --filter="msr==IA32_MKTME_KEYID_PARTITIONING"
  ^C#

If we use -v (verbose mode) we can see what it does behind the scenes:

  # perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr==IA32_MKTME_KEYID_PARTITIONING"
  Using CPUID GenuineIntel-6-8E-A
  0x87
  New filter for msr:read_msr: (msr==0x87) && (common_pid != 58627 && common_pid != 3792)
  0x87
  New filter for msr:write_msr: (msr==0x87) && (common_pid != 58627 && common_pid != 3792)
  mmap size 528384B
  ^C#

Example with a frequent msr:

  # perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr==IA32_SPEC_CTRL" --max-events 2
  Using CPUID AuthenticAMD-25-21-0
  0x48
  New filter for msr:read_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841)
  0x48
  New filter for msr:write_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841)
  mmap size 528384B
  Looking at the vmlinux_path (8 entries long)
  symsrc__init: build id mismatch for vmlinux.
  Using /proc/kcore for kernel data
  Using /proc/kallsyms for symbols
   0.000 Timer/2525383 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
  				   do_trace_write_msr ([kernel.kallsyms])
  				   do_trace_write_msr ([kernel.kallsyms])
  				   __switch_to_xtra ([kernel.kallsyms])
  				   __switch_to ([kernel.kallsyms])
  				   __schedule ([kernel.kallsyms])
  				   schedule ([kernel.kallsyms])
  				   futex_wait_queue_me ([kernel.kallsyms])
  				   futex_wait ([kernel.kallsyms])
  				   do_futex ([kernel.kallsyms])
  				   __x64_sys_futex ([kernel.kallsyms])
  				   do_syscall_64 ([kernel.kallsyms])
  				   entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
  				   __futex_abstimed_wait_common64 (/usr/lib64/libpthread-2.33.so)
   0.030 :0/0 msr:write_msr(msr: IA32_SPEC_CTRL, val: 2)
  				   do_trace_write_msr ([kernel.kallsyms])
  				   do_trace_write_msr ([kernel.kallsyms])
  				   __switch_to_xtra ([kernel.kallsyms])
  				   __switch_to ([kernel.kallsyms])
  				   __schedule ([kernel.kallsyms])
  				   schedule_idle ([kernel.kallsyms])
  				   do_idle ([kernel.kallsyms])
  				   cpu_startup_entry ([kernel.kallsyms])
  				   secondary_startup_64_no_verify ([kernel.kallsyms])
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kai Huang <kai.huang@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZbJt27rjkQVU1YoP@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/msr-index.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 1d51e1850ed03..f1bd7b91b3c63 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -237,6 +237,11 @@
 #define LBR_INFO_CYCLES			0xffff
 #define LBR_INFO_BR_TYPE_OFFSET		56
 #define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
+#define LBR_INFO_BR_CNTR_OFFSET		32
+#define LBR_INFO_BR_CNTR_NUM		4
+#define LBR_INFO_BR_CNTR_BITS		2
+#define LBR_INFO_BR_CNTR_MASK		GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0)
+#define LBR_INFO_BR_CNTR_FULL_MASK	GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0)
 
 #define MSR_ARCH_LBR_CTL		0x000014ce
 #define ARCH_LBR_CTL_LBREN		BIT(0)
@@ -536,6 +541,9 @@
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
 
+/* KeyID partitioning between MKTME and TDX */
+#define MSR_IA32_MKTME_KEYID_PARTITIONING	0x00000087
+
 /*
  * AMD64 MSRs. Not complete. See the architecture manual for a more
  * complete list.
-- 
GitLab


From b0dc99215598d7fc7c6903437d49f0b33d1ef899 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Jan 2024 11:23:56 -0300
Subject: [PATCH 3496/4076] tools headers UAPI: Sync linux/fcntl.h with the
 kernel sources

To get the changes in:

  8a924db2d7b5eb69 ("fs: Pass AT_GETATTR_NOSEC flag to getattr interface function")

That don't add anything that is handled by existing hard coded tables or
table generation scripts.

This silences this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/fcntl.h include/uapi/linux/fcntl.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stefan Berger <stefanb@linux.ibm.com>
Link: https://lore.kernel.org/lkml/ZbJv9fGF_k2xXEdr@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fcntl.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 6c80f96049bd0..282e90aeb163c 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -116,5 +116,8 @@
 #define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
 					compare object identity and may not
 					be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC	0x80000000
+#endif
 
 #endif /* _UAPI_LINUX_FCNTL_H */
-- 
GitLab


From 2dac1f089add90a45d93fe8217938281532b86c7 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 25 Jan 2024 11:03:51 +0100
Subject: [PATCH 3497/4076] perf test: Fix 'perf script' tests on s390

In linux next repo, test case 'perf script tests' fails on s390.

The root case is a command line invocation of 'perf record' with
call-graph information. On s390 only DWARF formatted call-graphs are
supported and only on software events.

Change the command line parameters for s390.

Output before:

  # perf test 89
  89: perf script tests              : FAILED!
  #

Output after:

  # perf test 89
  89: perf script tests              : Ok
  #

Fixes: 0dd5041c9a0eaf8c ("perf addr_location: Add init/exit/copy functions")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20240125100351.936262-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/script.sh | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
index 5ae7bd0031a82..2973adab445d2 100755
--- a/tools/perf/tests/shell/script.sh
+++ b/tools/perf/tests/shell/script.sh
@@ -54,7 +54,14 @@ def sample_table(*args):
 def call_path_table(*args):
     print(f'call_path_table({args}')
 _end_of_file_
-	perf record -g -o "${perfdatafile}" true
+	case $(uname -m)
+	in s390x)
+		cmd_flags="--call-graph dwarf -e cpu-clock";;
+	*)
+		cmd_flags="-g";;
+	esac
+
+	perf record $cmd_flags -o "${perfdatafile}" true
 	perf script -i "${perfdatafile}" -s "${db_test}"
 	echo "DB test [Success]"
 }
-- 
GitLab


From 9d95c6be48fc8d3d622658da8fbd6d6787d5c2e7 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 23 Jan 2024 20:30:11 -0800
Subject: [PATCH 3498/4076] perf list: Switch error message to pr_err() to
 respect debug settings (-v)

Using printf() can interrupt 'perf list output', use pr_err() which can
respect debug settings and the debug file.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Ross Zwisler <zwisler@chromium.org>
Cc: Shirisha G <shirisha@linux.ibm.com>
Link: https://lore.kernel.org/r/20240124043015.1388867-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/print-events.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index b0fc48be623f3..9e47712507cc2 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -66,7 +66,7 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus
 
 	put_tracing_file(events_path);
 	if (events_fd < 0) {
-		printf("Error: failed to open tracing events directory\n");
+		pr_err("Error: failed to open tracing events directory\n");
 		return;
 	}
 
-- 
GitLab


From 79bacb6ad73ce63faba3564671c2028e6c3fa1e2 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 23 Jan 2024 20:30:12 -0800
Subject: [PATCH 3499/4076] perf list: Add output file option

Add an option to write the 'perf list' output to a specific file. This
can avoid issues with debug output being written into the output stream.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Ross Zwisler <zwisler@chromium.org>
Cc: Shirisha G <shirisha@linux.ibm.com>
Link: https://lore.kernel.org/r/20240124043015.1388867-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-list.txt |   4 +
 tools/perf/builtin-list.c              | 211 +++++++++++++++----------
 2 files changed, 133 insertions(+), 82 deletions(-)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 1b90575ee3c84..3b12595193c9f 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -47,6 +47,10 @@ Print PMU events and metrics limited to the specific PMU name.
 --json::
 Output in JSON format.
 
+-o::
+--output=::
+	Output file name. By default output is written to stdout.
+
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 61c2c96cc0701..e27a1b1288c29 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -30,6 +30,8 @@
  * functions.
  */
 struct print_state {
+	/** @fp: File to write output to. */
+	FILE *fp;
 	/**
 	 * @pmu_glob: Optionally restrict PMU and metric matching to PMU or
 	 * debugfs subsystem name.
@@ -66,13 +68,15 @@ static void default_print_start(void *ps)
 {
 	struct print_state *print_state = ps;
 
-	if (!print_state->name_only && pager_in_use())
-		printf("\nList of pre-defined events (to be used in -e or -M):\n\n");
+	if (!print_state->name_only && pager_in_use()) {
+		fprintf(print_state->fp,
+			"\nList of pre-defined events (to be used in -e or -M):\n\n");
+	}
 }
 
 static void default_print_end(void *print_state __maybe_unused) {}
 
-static void wordwrap(const char *s, int start, int max, int corr)
+static void wordwrap(FILE *fp, const char *s, int start, int max, int corr)
 {
 	int column = start;
 	int n;
@@ -82,10 +86,10 @@ static void wordwrap(const char *s, int start, int max, int corr)
 		int wlen = strcspn(s, " \t\n");
 
 		if ((column + wlen >= max && column > start) || saw_newline) {
-			printf("\n%*s", start, "");
+			fprintf(fp, "\n%*s", start, "");
 			column = start + corr;
 		}
-		n = printf("%s%.*s", column > start ? " " : "", wlen, s);
+		n = fprintf(fp, "%s%.*s", column > start ? " " : "", wlen, s);
 		if (n <= 0)
 			break;
 		saw_newline = s[wlen] == '\n';
@@ -104,6 +108,7 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 {
 	struct print_state *print_state = ps;
 	int pos;
+	FILE *fp = print_state->fp;
 
 	if (deprecated && !print_state->deprecated)
 		return;
@@ -119,30 +124,30 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 
 	if (print_state->name_only) {
 		if (event_alias && strlen(event_alias))
-			printf("%s ", event_alias);
+			fprintf(fp, "%s ", event_alias);
 		else
-			printf("%s ", event_name);
+			fprintf(fp, "%s ", event_name);
 		return;
 	}
 
 	if (strcmp(print_state->last_topic, topic ?: "")) {
 		if (topic)
-			printf("\n%s:\n", topic);
+			fprintf(fp, "\n%s:\n", topic);
 		zfree(&print_state->last_topic);
 		print_state->last_topic = strdup(topic ?: "");
 	}
 
 	if (event_alias && strlen(event_alias))
-		pos = printf("  %s OR %s", event_name, event_alias);
+		pos = fprintf(fp, "  %s OR %s", event_name, event_alias);
 	else
-		pos = printf("  %s", event_name);
+		pos = fprintf(fp, "  %s", event_name);
 
 	if (!topic && event_type_desc) {
 		for (; pos < 53; pos++)
-			putchar(' ');
-		printf("[%s]\n", event_type_desc);
+			fputc(' ', fp);
+		fprintf(fp, "[%s]\n", event_type_desc);
 	} else
-		putchar('\n');
+		fputc('\n', fp);
 
 	if (desc && print_state->desc) {
 		char *desc_with_unit = NULL;
@@ -155,22 +160,22 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 					      ? "%s. Unit: %s" : "%s Unit: %s",
 					    desc, pmu_name);
 		}
-		printf("%*s", 8, "[");
-		wordwrap(desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 		free(desc_with_unit);
 	}
 	long_desc = long_desc ?: desc;
 	if (long_desc && print_state->long_desc) {
-		printf("%*s", 8, "[");
-		wordwrap(long_desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, long_desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 
 	if (print_state->detailed && encoding_desc) {
-		printf("%*s", 8, "");
-		wordwrap(encoding_desc, 8, pager_get_columns(), 0);
-		putchar('\n');
+		fprintf(fp, "%*s", 8, "");
+		wordwrap(fp, encoding_desc, 8, pager_get_columns(), 0);
+		fputc('\n', fp);
 	}
 }
 
@@ -184,6 +189,7 @@ static void default_print_metric(void *ps,
 				const char *unit __maybe_unused)
 {
 	struct print_state *print_state = ps;
+	FILE *fp = print_state->fp;
 
 	if (print_state->event_glob &&
 	    (!print_state->metrics || !name || !strglobmatch(name, print_state->event_glob)) &&
@@ -192,27 +198,27 @@ static void default_print_metric(void *ps,
 
 	if (!print_state->name_only && !print_state->last_metricgroups) {
 		if (print_state->metricgroups) {
-			printf("\nMetric Groups:\n");
+			fprintf(fp, "\nMetric Groups:\n");
 			if (!print_state->metrics)
-				putchar('\n');
+				fputc('\n', fp);
 		} else {
-			printf("\nMetrics:\n\n");
+			fprintf(fp, "\nMetrics:\n\n");
 		}
 	}
 	if (!print_state->last_metricgroups ||
 	    strcmp(print_state->last_metricgroups, group ?: "")) {
 		if (group && print_state->metricgroups) {
 			if (print_state->name_only)
-				printf("%s ", group);
+				fprintf(fp, "%s ", group);
 			else if (print_state->metrics) {
 				const char *gdesc = describe_metricgroup(group);
 
 				if (gdesc)
-					printf("\n%s: [%s]\n", group, gdesc);
+					fprintf(fp, "\n%s: [%s]\n", group, gdesc);
 				else
-					printf("\n%s:\n", group);
+					fprintf(fp, "\n%s:\n", group);
 			} else
-				printf("%s\n", group);
+				fprintf(fp, "%s\n", group);
 		}
 		zfree(&print_state->last_metricgroups);
 		print_state->last_metricgroups = strdup(group ?: "");
@@ -223,53 +229,59 @@ static void default_print_metric(void *ps,
 	if (print_state->name_only) {
 		if (print_state->metrics &&
 		    !strlist__has_entry(print_state->visited_metrics, name)) {
-			printf("%s ", name);
+			fprintf(fp, "%s ", name);
 			strlist__add(print_state->visited_metrics, name);
 		}
 		return;
 	}
-	printf("  %s\n", name);
+	fprintf(fp, "  %s\n", name);
 
 	if (desc && print_state->desc) {
-		printf("%*s", 8, "[");
-		wordwrap(desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (long_desc && print_state->long_desc) {
-		printf("%*s", 8, "[");
-		wordwrap(long_desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, long_desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (expr && print_state->detailed) {
-		printf("%*s", 8, "[");
-		wordwrap(expr, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, expr, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (threshold && print_state->detailed) {
-		printf("%*s", 8, "[");
-		wordwrap(threshold, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, threshold, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 }
 
 struct json_print_state {
+	/** @fp: File to write output to. */
+	FILE *fp;
 	/** Should a separator be printed prior to the next item? */
 	bool need_sep;
 };
 
-static void json_print_start(void *print_state __maybe_unused)
+static void json_print_start(void *ps)
 {
-	printf("[\n");
+	struct json_print_state *print_state = ps;
+	FILE *fp = print_state->fp;
+
+	fprintf(fp, "[\n");
 }
 
 static void json_print_end(void *ps)
 {
 	struct json_print_state *print_state = ps;
+	FILE *fp = print_state->fp;
 
-	printf("%s]\n", print_state->need_sep ? "\n" : "");
+	fprintf(fp, "%s]\n", print_state->need_sep ? "\n" : "");
 }
 
-static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...)
+static void fix_escape_fprintf(FILE *fp, struct strbuf *buf, const char *fmt, ...)
 {
 	va_list args;
 
@@ -318,7 +330,7 @@ static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...)
 		}
 	}
 	va_end(args);
-	fputs(buf->buf, stdout);
+	fputs(buf->buf, fp);
 }
 
 static void json_print_event(void *ps, const char *pmu_name, const char *topic,
@@ -330,60 +342,71 @@ static void json_print_event(void *ps, const char *pmu_name, const char *topic,
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
+	FILE *fp = print_state->fp;
 	struct strbuf buf;
 
 	strbuf_init(&buf, 0);
-	printf("%s{\n", print_state->need_sep ? ",\n" : "");
+	fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : "");
 	print_state->need_sep = true;
 	if (pmu_name) {
-		fix_escape_printf(&buf, "\t\"Unit\": \"%S\"", pmu_name);
+		fix_escape_fprintf(fp, &buf, "\t\"Unit\": \"%S\"", pmu_name);
 		need_sep = true;
 	}
 	if (topic) {
-		fix_escape_printf(&buf, "%s\t\"Topic\": \"%S\"", need_sep ? ",\n" : "", topic);
+		fix_escape_fprintf(fp, &buf, "%s\t\"Topic\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   topic);
 		need_sep = true;
 	}
 	if (event_name) {
-		fix_escape_printf(&buf, "%s\t\"EventName\": \"%S\"", need_sep ? ",\n" : "",
-				  event_name);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventName\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_name);
 		need_sep = true;
 	}
 	if (event_alias && strlen(event_alias)) {
-		fix_escape_printf(&buf, "%s\t\"EventAlias\": \"%S\"", need_sep ? ",\n" : "",
-				  event_alias);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventAlias\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_alias);
 		need_sep = true;
 	}
 	if (scale_unit && strlen(scale_unit)) {
-		fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "",
-				  scale_unit);
+		fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   scale_unit);
 		need_sep = true;
 	}
 	if (event_type_desc) {
-		fix_escape_printf(&buf, "%s\t\"EventType\": \"%S\"", need_sep ? ",\n" : "",
-				  event_type_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventType\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_type_desc);
 		need_sep = true;
 	}
 	if (deprecated) {
-		fix_escape_printf(&buf, "%s\t\"Deprecated\": \"%S\"", need_sep ? ",\n" : "",
-				  deprecated ? "1" : "0");
+		fix_escape_fprintf(fp, &buf, "%s\t\"Deprecated\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   deprecated ? "1" : "0");
 		need_sep = true;
 	}
 	if (desc) {
-		fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   desc);
 		need_sep = true;
 	}
 	if (long_desc) {
-		fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  long_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   long_desc);
 		need_sep = true;
 	}
 	if (encoding_desc) {
-		fix_escape_printf(&buf, "%s\t\"Encoding\": \"%S\"", need_sep ? ",\n" : "",
-				  encoding_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"Encoding\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   encoding_desc);
 		need_sep = true;
 	}
-	printf("%s}", need_sep ? "\n" : "");
+	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
 
@@ -394,43 +417,53 @@ static void json_print_metric(void *ps __maybe_unused, const char *group,
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
+	FILE *fp = print_state->fp;
 	struct strbuf buf;
 
 	strbuf_init(&buf, 0);
-	printf("%s{\n", print_state->need_sep ? ",\n" : "");
+	fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : "");
 	print_state->need_sep = true;
 	if (group) {
-		fix_escape_printf(&buf, "\t\"MetricGroup\": \"%S\"", group);
+		fix_escape_fprintf(fp, &buf, "\t\"MetricGroup\": \"%S\"", group);
 		need_sep = true;
 	}
 	if (name) {
-		fix_escape_printf(&buf, "%s\t\"MetricName\": \"%S\"", need_sep ? ",\n" : "", name);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricName\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   name);
 		need_sep = true;
 	}
 	if (expr) {
-		fix_escape_printf(&buf, "%s\t\"MetricExpr\": \"%S\"", need_sep ? ",\n" : "", expr);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricExpr\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   expr);
 		need_sep = true;
 	}
 	if (threshold) {
-		fix_escape_printf(&buf, "%s\t\"MetricThreshold\": \"%S\"", need_sep ? ",\n" : "",
-				  threshold);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricThreshold\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   threshold);
 		need_sep = true;
 	}
 	if (unit) {
-		fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "", unit);
+		fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   unit);
 		need_sep = true;
 	}
 	if (desc) {
-		fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   desc);
 		need_sep = true;
 	}
 	if (long_desc) {
-		fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  long_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   long_desc);
 		need_sep = true;
 	}
-	printf("%s}", need_sep ? "\n" : "");
+	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
 
@@ -449,8 +482,12 @@ static bool default_skip_duplicate_pmus(void *ps)
 int cmd_list(int argc, const char **argv)
 {
 	int i, ret = 0;
-	struct print_state default_ps = {};
-	struct print_state json_ps = {};
+	struct print_state default_ps = {
+		.fp = stdout,
+	};
+	struct print_state json_ps = {
+		.fp = stdout,
+	};
 	void *ps = &default_ps;
 	struct print_callbacks print_cb = {
 		.print_start = default_print_start,
@@ -461,6 +498,7 @@ int cmd_list(int argc, const char **argv)
 	};
 	const char *cputype = NULL;
 	const char *unit_name = NULL;
+	const char *output_path = NULL;
 	bool json = false;
 	struct option list_options[] = {
 		OPT_BOOLEAN(0, "raw-dump", &default_ps.name_only, "Dump raw events"),
@@ -471,6 +509,7 @@ int cmd_list(int argc, const char **argv)
 			    "Print longer event descriptions."),
 		OPT_BOOLEAN(0, "details", &default_ps.detailed,
 			    "Print information on the perf event names and expressions used internally by events."),
+		OPT_STRING('o', "output", &output_path, "file", "output file name"),
 		OPT_BOOLEAN(0, "deprecated", &default_ps.deprecated,
 			    "Print deprecated events."),
 		OPT_STRING(0, "cputype", &cputype, "cpu type",
@@ -497,6 +536,11 @@ int cmd_list(int argc, const char **argv)
 	argc = parse_options(argc, argv, list_options, list_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (output_path) {
+		default_ps.fp = fopen(output_path, "w");
+		json_ps.fp = default_ps.fp;
+	}
+
 	setup_pager();
 
 	if (!default_ps.name_only)
@@ -618,5 +662,8 @@ out:
 	free(default_ps.last_topic);
 	free(default_ps.last_metricgroups);
 	strlist__delete(default_ps.visited_metrics);
+	if (output_path)
+		fclose(default_ps.fp);
+
 	return ret;
 }
-- 
GitLab


From a734c7f969750302b1150ef20468704498f74e64 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 23 Jan 2024 20:30:13 -0800
Subject: [PATCH 3500/4076] perf test: Workaround debug output in list test

Write the JSON output to a specific file to avoid debug output
breaking it.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Ross Zwisler <zwisler@chromium.org>
Cc: Shirisha G <shirisha@linux.ibm.com>
Link: https://lore.kernel.org/r/20240124043015.1388867-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/list.sh | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh
index 22b004f2b23ec..8a868ae64560e 100755
--- a/tools/perf/tests/shell/list.sh
+++ b/tools/perf/tests/shell/list.sh
@@ -3,17 +3,32 @@
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
-err=0
 
 shelldir=$(dirname "$0")
 # shellcheck source=lib/setup_python.sh
 . "${shelldir}"/lib/setup_python.sh
 
+list_output=$(mktemp /tmp/__perf_test.list_output.json.XXXXX)
+
+cleanup() {
+  rm -f "${list_output}"
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
 test_list_json() {
   echo "Json output test"
-  perf list -j | $PYTHON -m json.tool
+  perf list -j -o "${list_output}"
+  $PYTHON -m json.tool "${list_output}"
   echo "Json output test [Success]"
 }
 
 test_list_json
-exit $err
+cleanup
+exit 0
-- 
GitLab


From 1c2124ec8431f88f5c122be73cb4b784b558d600 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 23 Jan 2024 20:30:14 -0800
Subject: [PATCH 3501/4076] perf test shell script: Fix test for python being
 disabled

"grep -cv" can exit with an error code that causes the "set -e" to abort
the script. Switch to using the grep exit code in the if condition to
avoid this.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Ross Zwisler <zwisler@chromium.org>
Cc: Shirisha G <shirisha@linux.ibm.com>
Link: https://lore.kernel.org/r/20240124043015.1388867-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/script.sh | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
index 2973adab445d2..fa4d71e2e72a6 100755
--- a/tools/perf/tests/shell/script.sh
+++ b/tools/perf/tests/shell/script.sh
@@ -36,8 +36,7 @@ test_db()
 	echo "DB test"
 
 	# Check if python script is supported
-	libpython=$(perf version --build-options | grep python | grep -cv OFF)
-	if [ "${libpython}" != "1" ] ; then
+        if perf version --build-options | grep python | grep -q OFF ; then
 		echo "SKIP: python scripting is not supported"
 		err=2
 		return
-- 
GitLab


From 9a8dd2f24d1cb8e8df2c5d18b4973298db1006e1 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 23 Jan 2024 20:30:15 -0800
Subject: [PATCH 3502/4076] perf test shell daemon: Make signal test less racy

The daemon signal test sends signals and then expects files to be
written. It was observed on an Intel Alderlake that the signals were
sent too quickly leading to the 3 expected files not appearing.

To avoid this send the next signal only after the expected previous file
has appeared. To avoid an infinite loop the number of retries is
limited.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Ross Zwisler <zwisler@chromium.org>
Cc: Shirisha G <shirisha@linux.ibm.com>
Link: https://lore.kernel.org/r/20240124043015.1388867-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/daemon.sh | 34 ++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index 4c598cfc5afa1..e5fa8d6f9eb1f 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -414,16 +414,30 @@ EOF
 	# start daemon
 	daemon_start ${config} test
 
-	# send 2 signals
-	perf daemon signal --config ${config} --session test
-	perf daemon signal --config ${config}
-
-	# stop daemon
-	daemon_exit ${config}
-
-	# count is 2 perf.data for signals and 1 for perf record finished
-	count=`ls ${base}/session-test/*perf.data* | wc -l`
-	if [ ${count} -ne 3 ]; then
+        # send 2 signals then exit. Do this in a loop watching the number of
+        # files to avoid races. If the loop retries more than 600 times then
+        # give up.
+	local retries=0
+	local signals=0
+	local success=0
+	while [ ${retries} -lt 600 ] && [ ${success} -eq 0 ]; do
+		local files
+		files=`ls ${base}/session-test/*perf.data* 2> /dev/null | wc -l`
+		if [ ${signals} -eq 0 ]; then
+			perf daemon signal --config ${config} --session test
+			signals=1
+		elif [ ${signals} -eq 1 ] && [ $files -ge 1 ]; then
+			perf daemon signal --config ${config}
+			signals=2
+		elif [ ${signals} -eq 2 ] && [ $files -ge 2 ]; then
+			daemon_exit ${config}
+			signals=3
+		elif [ ${signals} -eq 3 ] && [ $files -ge 3 ]; then
+			success=1
+		fi
+		retries=$((${retries} +1))
+	done
+	if [ ${success} -eq 0 ]; then
 		error=1
 		echo "FAILED: perf data no generated"
 	fi
-- 
GitLab


From 61f61c89fa5d9925e0b874854fb62e51948a6de1 Mon Sep 17 00:00:00 2001
From: Andreas Larsson <andreas@gaisler.com>
Date: Mon, 15 Jan 2024 16:02:00 +0100
Subject: [PATCH 3503/4076] MAINTAINERS: Add Andreas Larsson as co-maintainer
 for arch/sparc

Dave has not been very active on arch/sparc for the past two years.
I have been contributing to the SPARC32 port as well as maintaining
out-of-tree SPARC32 patches for LEON3/4/5 (SPARCv8 with CAS support)
since 2012. I am willing to step up as an arch/sparc (co-)maintainer.

For recent discussions on the matter, see [1] and [2].

[1] https://lore.kernel.org/r/20230713075235.2164609-1-u.kleine-koenig@pengutronix.de
[2] https://lore.kernel.org/r/20231209105816.GA1085691@ravnborg.org/

Signed-off-by: Andreas Larsson <andreas@gaisler.com>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Acked-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Acked-by: Jose E. Marchesi <jose.marchesi@oracle.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a692..542ab762be7de 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20549,6 +20549,7 @@ F:	Documentation/translations/sp_SP/
 
 SPARC + UltraSPARC (sparc/sparc64)
 M:	"David S. Miller" <davem@davemloft.net>
+M:	Andreas Larsson <andreas@gaisler.com>
 L:	sparclinux@vger.kernel.org
 S:	Maintained
 Q:	http://patchwork.ozlabs.org/project/sparclinux/list/
-- 
GitLab


From 1233d1d54b7f66813cfa748aaaeca8c4f9c36c6b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 26 Jan 2024 11:00:01 -0300
Subject: [PATCH 3504/4076] tools headers UAPI: Update tools's copy of drm.h
 headers to pick DRM_IOCTL_MODE_CLOSEFB

Picking the changes from:

  8570c27932e132d2 ("drm/syncobj: Add deadline support for syncobj waits")
  9724ed6c1b1212d1 ("drm: Introduce DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT")
  e4d983acffff270c ("drm: introduce DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP")
  d208d875667e2a29 ("drm: introduce CLOSEFB IOCTL")
  afa5cf3175a22b71 ("drm/i915/uapi: fix typos/spellos and punctuation")

Addressing these perf build warnings:

  Warning: Kernel ABI header differences:

Now 'perf trace' and other code that might use the
tools/perf/trace/beauty autogenerated tables will be able to translate
this new ioctl command into a string:

  $ tools/perf/trace/beauty/drm_ioctl.sh > before
  $ cp include/uapi/drm/drm.h tools/include/uapi/drm/drm.h
  $ tools/perf/trace/beauty/drm_ioctl.sh > after
  $ diff -u before after
  --- before	2024-01-26 10:54:23.486381862 -0300
  +++ after	2024-01-26 10:54:35.767902442 -0300
  @@ -109,6 +109,7 @@
   	[0xCD] = "SYNCOBJ_TIMELINE_SIGNAL",
   	[0xCE] = "MODE_GETFB2",
   	[0xCF] = "SYNCOBJ_EVENTFD",
  +	[0xD0] = "MODE_CLOSEFB",
   	[DRM_COMMAND_BASE + 0x00] = "I915_INIT",
   	[DRM_COMMAND_BASE + 0x01] = "I915_FLUSH",
   	[DRM_COMMAND_BASE + 0x02] = "I915_FLIP",
  $

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Rob Clark <robdclark@chromium.org>
Cc: Simon Ser <contact@emersion.fr>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Zack Rusin <zack.rusin@broadcom.com>
Link: https://lore.kernel.org/lkml/ZbPIN9Dcc5AM0uxo@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/drm/drm.h      | 72 ++++++++++++++++++++++++++++++-
 tools/include/uapi/drm/i915_drm.h | 12 +++---
 2 files changed, 77 insertions(+), 7 deletions(-)

diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index de723566c5ae8..16122819edfef 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -713,7 +713,8 @@ struct drm_gem_open {
 /**
  * DRM_CAP_ASYNC_PAGE_FLIP
  *
- * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC.
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for legacy
+ * page-flips.
  */
 #define DRM_CAP_ASYNC_PAGE_FLIP		0x7
 /**
@@ -773,6 +774,13 @@ struct drm_gem_open {
  * :ref:`drm_sync_objects`.
  */
 #define DRM_CAP_SYNCOBJ_TIMELINE	0x14
+/**
+ * DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP
+ *
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for atomic
+ * commits.
+ */
+#define DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP	0x15
 
 /* DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
@@ -842,6 +850,31 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
 
+/**
+ * DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT
+ *
+ * Drivers for para-virtualized hardware (e.g. vmwgfx, qxl, virtio and
+ * virtualbox) have additional restrictions for cursor planes (thus
+ * making cursor planes on those drivers not truly universal,) e.g.
+ * they need cursor planes to act like one would expect from a mouse
+ * cursor and have correctly set hotspot properties.
+ * If this client cap is not set the DRM core will hide cursor plane on
+ * those virtualized drivers because not setting it implies that the
+ * client is not capable of dealing with those extra restictions.
+ * Clients which do set cursor hotspot and treat the cursor plane
+ * like a mouse cursor should set this property.
+ * The client must enable &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * Setting this property on drivers which do not special case
+ * cursor planes (i.e. non-virtualized drivers) will return
+ * EOPNOTSUPP, which can be used by userspace to gauge
+ * requirements of the hardware/drivers they're running on.
+ *
+ * This capability is always supported for atomic-capable virtualized
+ * drivers starting from kernel version 6.6.
+ */
+#define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT	6
+
 /* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
@@ -893,6 +926,7 @@ struct drm_syncobj_transfer {
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline to deadline_nsec */
 struct drm_syncobj_wait {
 	__u64 handles;
 	/* absolute timeout */
@@ -901,6 +935,14 @@ struct drm_syncobj_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 struct drm_syncobj_timeline_wait {
@@ -913,6 +955,14 @@ struct drm_syncobj_timeline_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 /**
@@ -1218,6 +1268,26 @@ extern "C" {
 
 #define DRM_IOCTL_SYNCOBJ_EVENTFD	DRM_IOWR(0xCF, struct drm_syncobj_eventfd)
 
+/**
+ * DRM_IOCTL_MODE_CLOSEFB - Close a framebuffer.
+ *
+ * This closes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL
+ * argument is a framebuffer object ID.
+ *
+ * This IOCTL is similar to &DRM_IOCTL_MODE_RMFB, except it doesn't disable
+ * planes and CRTCs. As long as the framebuffer is used by a plane, it's kept
+ * alive. When the plane no longer uses the framebuffer (because the
+ * framebuffer is replaced with another one, or the plane is disabled), the
+ * framebuffer is cleaned up.
+ *
+ * This is useful to implement flicker-free transitions between two processes.
+ *
+ * Depending on the threat model, user-space may want to ensure that the
+ * framebuffer doesn't expose any sensitive user information: closed
+ * framebuffers attached to a plane can be read back by the next DRM master.
+ */
+#define DRM_IOCTL_MODE_CLOSEFB		DRM_IOWR(0xD0, struct drm_mode_closefb)
+
 /*
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 218edb0a96f8c..fd4f9574d177a 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -693,7 +693,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_EXEC_FENCE	 44
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
- * user specified bufffers for post-mortem debugging of GPU hangs. See
+ * user-specified buffers for post-mortem debugging of GPU hangs. See
  * EXEC_OBJECT_CAPTURE.
  */
 #define I915_PARAM_HAS_EXEC_CAPTURE	 45
@@ -1606,7 +1606,7 @@ struct drm_i915_gem_busy {
 	 * is accurate.
 	 *
 	 * The returned dword is split into two fields to indicate both
-	 * the engine classess on which the object is being read, and the
+	 * the engine classes on which the object is being read, and the
 	 * engine class on which it is currently being written (if any).
 	 *
 	 * The low word (bits 0:15) indicate if the object is being written
@@ -1815,7 +1815,7 @@ struct drm_i915_gem_madvise {
 	__u32 handle;
 
 	/* Advice: either the buffer will be needed again in the near future,
-	 *         or wont be and could be discarded under memory pressure.
+	 *         or won't be and could be discarded under memory pressure.
 	 */
 	__u32 madv;
 
@@ -3246,7 +3246,7 @@ struct drm_i915_query_topology_info {
  * 	// enough to hold our array of engines. The kernel will fill out the
  * 	// item.length for us, which is the number of bytes we need.
  * 	//
- * 	// Alternatively a large buffer can be allocated straight away enabling
+ *	// Alternatively a large buffer can be allocated straightaway enabling
  * 	// querying in one pass, in which case item.length should contain the
  * 	// length of the provided buffer.
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
@@ -3256,7 +3256,7 @@ struct drm_i915_query_topology_info {
  * 	// Now that we allocated the required number of bytes, we call the ioctl
  * 	// again, this time with the data_ptr pointing to our newly allocated
  * 	// blob, which the kernel can then populate with info on all engines.
- * 	item.data_ptr = (uintptr_t)&info,
+ *	item.data_ptr = (uintptr_t)&info;
  *
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
  * 	if (err) ...
@@ -3286,7 +3286,7 @@ struct drm_i915_query_topology_info {
 /**
  * struct drm_i915_engine_info
  *
- * Describes one engine and it's capabilities as known to the driver.
+ * Describes one engine and its capabilities as known to the driver.
  */
 struct drm_i915_engine_info {
 	/** @engine: Engine class and instance. */
-- 
GitLab


From 39af67413997a350fa02a88e15eaacf202c94884 Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Mon, 22 Jan 2024 16:04:06 +0800
Subject: [PATCH 3505/4076] perf build: Make minimal shellcheck version to
 v0.6.0

The perf build failed due to the shellcheck on my machine (v0.4.6 on Ubuntu
18.04.1 LTS) doesn't support -a/--check-sourced and -S/--severity option.

These two options are introduced in shellcheck v0.4.7 and v0.6.0
respectively. So restrict the minimal version of shellcheck to v0.6.0.

Fixes: b809fc656e763296 ("perf build: Shellcheck support for OUTPUT directory")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Junhao He <hejunhao3@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linuxarm@huawei.com
Link: https://lore.kernel.org/r/20240122080406.28678-1-yangyicong@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 27e7c478880fd..f8774a9b1377a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -236,6 +236,16 @@ else
   SHELLCHECK := $(shell which shellcheck 2> /dev/null)
 endif
 
+# shellcheck is using in tools/perf/tests/Build with option -a/--check-sourced (
+# introduced in v0.4.7) and -S/--severity (introduced in v0.6.0). So make the
+# minimal shellcheck version as v0.6.0.
+ifneq ($(SHELLCHECK),)
+  ifeq ($(shell expr $(shell $(SHELLCHECK) --version | grep version: | \
+        sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 060), 1)
+    SHELLCHECK :=
+  endif
+endif
+
 export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
 export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK
 
-- 
GitLab


From 79baac8acfc60a7a5114f6d60731e28c242ef8ce Mon Sep 17 00:00:00 2001
From: Sun Haiyong <sunhaiyong@loongson.cn>
Date: Mon, 4 Dec 2023 16:20:55 +0800
Subject: [PATCH 3506/4076] perf top: Remove needless malloc(0) call that
 triggers -Walloc-size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC 14 introduces a new -Walloc-size included in -Wextra which errors out
like:

  builtin-top.c: In function ‘prompt_integer’:
  builtin-top.c:360:21: error: allocation of insufficient size ‘0’ for
  type ‘char’ with size ‘1’ [-Werror=alloc-size]
    360 |         char *buf = malloc(0), *p;
        |                     ^~~~~~

Just set it to NULL, getline() will do the allocation.

Signed-off-by: Sun Haiyong <sunhaiyong@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231204082055.91877-1-siyanteng@loongson.cn
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index baf1ab083436e..5301d1badd435 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -357,7 +357,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
 static void prompt_integer(int *target, const char *msg)
 {
-	char *buf = malloc(0), *p;
+	char *buf = NULL, *p;
 	size_t dummy = 0;
 	int tmp;
 
-- 
GitLab


From eeca59a6e8e610e593d17e12f67324c615ec5ef2 Mon Sep 17 00:00:00 2001
From: Alexander Tsoy <alexander@tsoy.me>
Date: Thu, 25 Jan 2024 23:54:57 +0300
Subject: [PATCH 3507/4076] ALSA: usb-audio: Support read-only clock selector
 control

Clock selector control might be read-only. Add corresponding checks
to prevent sending control requests that would fail.

Signed-off-by: Alexander Tsoy <alexander@tsoy.me>
Link: https://lore.kernel.org/r/20240125205457.28258-1-alexander@tsoy.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/clock.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 94e4aaeafe588..7b259641adb51 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -261,6 +261,8 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 	int ret, i, cur, err, pins, clock_id;
 	const u8 *sources;
 	int proto = fmt->protocol;
+	bool readable, writeable;
+	u32 bmControls;
 
 	entity_id &= 0xff;
 
@@ -292,11 +294,27 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 		sources = GET_VAL(selector, proto, baCSourceID);
 		cur = 0;
 
+		if (proto == UAC_VERSION_3)
+			bmControls = le32_to_cpu(*(__le32 *)(&selector->v3.baCSourceID[0] + pins));
+		else
+			bmControls = *(__u8 *)(&selector->v2.baCSourceID[0] + pins);
+
+		readable = uac_v2v3_control_is_readable(bmControls,
+							UAC2_CX_CLOCK_SELECTOR);
+		writeable = uac_v2v3_control_is_writeable(bmControls,
+							  UAC2_CX_CLOCK_SELECTOR);
+
 		if (pins == 1) {
 			ret = 1;
 			goto find_source;
 		}
 
+		/* for now just warn about buggy device */
+		if (!readable)
+			usb_audio_warn(chip,
+				"%s(): clock selector control is not readable, id %d\n",
+				__func__, clock_id);
+
 		/* the entity ID we are looking at is a selector.
 		 * find out what it currently selects */
 		ret = uac_clock_selector_get_val(chip, clock_id);
@@ -326,7 +344,7 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 		if (ret > 0) {
 			/* Skip setting clock selector again for some devices */
 			if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR ||
-			    pins == 1)
+			    pins == 1 || !writeable)
 				return ret;
 			err = uac_clock_selector_set_val(chip, entity_id, cur);
 			if (err < 0)
@@ -337,6 +355,9 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 			return ret;
 
 	find_others:
+		if (!writeable)
+			return -ENXIO;
+
 		/* The current clock source is invalid, try others. */
 		for (i = 1; i <= pins; i++) {
 			if (i == cur)
-- 
GitLab


From 7bbe8f0071dfa23fcc3b2864ec9f3b1aeb7ab2df Mon Sep 17 00:00:00 2001
From: Sun Haiyong <sunhaiyong@loongson.cn>
Date: Sat, 6 Jan 2024 17:41:29 +0800
Subject: [PATCH 3508/4076] perf tools: Fix calloc() arguments to address error
 introduced in gcc-14

the definition of calloc is as follows:

    void *calloc(size_t nmemb, size_t size);

number of members is in the first parameter and the size is in the
second parameter.

Fix error messages on gcc 14 20240102:

  error: 'calloc' sizes specified with 'sizeof' in the earlier argument and
  not in the later argument [-Werror=calloc-transposed-args]

Committer notes:

I noticed this on fedora 40 and rawhide.

Signed-off-by: Sun Haiyong <sunhaiyong@loongson.cn>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240106094129.3337057-1-siyanteng@loongson.cn
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c        | 4 ++--
 tools/perf/util/hist.c             | 4 ++--
 tools/perf/util/metricgroup.c      | 2 +-
 tools/perf/util/synthetic-events.c | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 91e6828c38cc2..86c9101251726 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -4080,8 +4080,8 @@ int cmd_record(int argc, const char **argv)
 	}
 
 	if (rec->switch_output.num_files) {
-		rec->switch_output.filenames = calloc(sizeof(char *),
-						      rec->switch_output.num_files);
+		rec->switch_output.filenames = calloc(rec->switch_output.num_files,
+						      sizeof(char *));
 		if (!rec->switch_output.filenames) {
 			err = -EINVAL;
 			goto out_opts;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 0888b7163b7cc..fa359180ebf8f 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -491,8 +491,8 @@ static int hist_entry__init(struct hist_entry *he,
 	}
 
 	if (symbol_conf.res_sample) {
-		he->res_samples = calloc(sizeof(struct res_sample),
-					symbol_conf.res_sample);
+		he->res_samples = calloc(symbol_conf.res_sample,
+					sizeof(struct res_sample));
 		if (!he->res_samples)
 			goto err_srcline;
 	}
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index ca3e0404f1872..966cca5a3e88c 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -286,7 +286,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 	*out_metric_events = NULL;
 	ids_size = hashmap__size(ids);
 
-	metric_events = calloc(sizeof(void *), ids_size + 1);
+	metric_events = calloc(ids_size + 1, sizeof(void *));
 	if (!metric_events)
 		return -ENOMEM;
 
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 3712186353fb9..2a0289c149599 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1055,11 +1055,11 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (thread_nr > n)
 		thread_nr = n;
 
-	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+	synthesize_threads = calloc(thread_nr, sizeof(pthread_t));
 	if (synthesize_threads == NULL)
 		goto free_dirent;
 
-	args = calloc(sizeof(*args), thread_nr);
+	args = calloc(thread_nr, sizeof(*args));
 	if (args == NULL)
 		goto free_threads;
 
-- 
GitLab


From a7a6a01f88e87dec4bf2365571dd2dc7403d52d0 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 26 Jan 2024 12:14:30 +0100
Subject: [PATCH 3509/4076] x86/efistub: Give up if memory attribute protocol
 returns an error

The recently introduced EFI memory attributes protocol should be used
if it exists to ensure that the memory allocation created for the kernel
permits execution. This is needed for compatibility with tightened
requirements related to Windows logo certification for x86 PCs.

Currently, we simply strip the execute protect (XP) attribute from the
entire range, but this might be rejected under some firmware security
policies, and so in a subsequent patch, this will be changed to only
strip XP from the executable region that runs early, and make it
read-only (RO) as well.

In order to catch any issues early, ensure that the memory attribute
protocol works as intended, and give up if it produces spurious errors.

Note that the DXE services based fallback was always based on best
effort, so don't propagate any errors returned by that API.

Fixes: a1b87d54f4e4 ("x86/efistub: Avoid legacy decompressor when doing EFI boot")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/x86-stub.c | 24 ++++++++++++++----------
 drivers/firmware/efi/libstub/x86-stub.h |  4 ++--
 2 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 0d510c9a06a45..cb0be88c81317 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -223,8 +223,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 	}
 }
 
-void efi_adjust_memory_range_protection(unsigned long start,
-					unsigned long size)
+efi_status_t efi_adjust_memory_range_protection(unsigned long start,
+						unsigned long size)
 {
 	efi_status_t status;
 	efi_gcd_memory_space_desc_t desc;
@@ -236,13 +236,17 @@ void efi_adjust_memory_range_protection(unsigned long start,
 	rounded_end = roundup(start + size, EFI_PAGE_SIZE);
 
 	if (memattr != NULL) {
-		efi_call_proto(memattr, clear_memory_attributes, rounded_start,
-			       rounded_end - rounded_start, EFI_MEMORY_XP);
-		return;
+		status = efi_call_proto(memattr, clear_memory_attributes,
+					rounded_start,
+					rounded_end - rounded_start,
+					EFI_MEMORY_XP);
+		if (status != EFI_SUCCESS)
+			efi_warn("Failed to clear EFI_MEMORY_XP attribute\n");
+		return status;
 	}
 
 	if (efi_dxe_table == NULL)
-		return;
+		return EFI_SUCCESS;
 
 	/*
 	 * Don't modify memory region attributes, they are
@@ -255,7 +259,7 @@ void efi_adjust_memory_range_protection(unsigned long start,
 		status = efi_dxe_call(get_memory_space_descriptor, start, &desc);
 
 		if (status != EFI_SUCCESS)
-			return;
+			break;
 
 		next = desc.base_address + desc.length;
 
@@ -280,8 +284,10 @@ void efi_adjust_memory_range_protection(unsigned long start,
 				 unprotect_start,
 				 unprotect_start + unprotect_size,
 				 status);
+			break;
 		}
 	}
+	return EFI_SUCCESS;
 }
 
 static void setup_unaccepted_memory(void)
@@ -805,9 +811,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
 
 	*kernel_entry = addr + entry;
 
-	efi_adjust_memory_range_protection(addr, kernel_total_size);
-
-	return EFI_SUCCESS;
+	return efi_adjust_memory_range_protection(addr, kernel_total_size);
 }
 
 static void __noreturn enter_kernel(unsigned long kernel_addr,
diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h
index 37c5a36b9d8cf..1c20e99a64944 100644
--- a/drivers/firmware/efi/libstub/x86-stub.h
+++ b/drivers/firmware/efi/libstub/x86-stub.h
@@ -5,8 +5,8 @@
 extern void trampoline_32bit_src(void *, bool);
 extern const u16 trampoline_ljmp_imm_offset;
 
-void efi_adjust_memory_range_protection(unsigned long start,
-					unsigned long size);
+efi_status_t efi_adjust_memory_range_protection(unsigned long start,
+						unsigned long size);
 
 #ifdef CONFIG_X86_64
 efi_status_t efi_setup_5level_paging(void);
-- 
GitLab


From 47c5dd66c1840524572dcdd956f4af2bdb6fbdff Mon Sep 17 00:00:00 2001
From: Guixin Liu <kanie@linux.alibaba.com>
Date: Fri, 26 Jan 2024 16:26:43 +0800
Subject: [PATCH 3510/4076] nvmet-tcp: fix nvme tcp ida memory leak

The nvmet_tcp_queue_ida should be destroy when the nvmet-tcp module
exit.

Signed-off-by: Guixin Liu <kanie@linux.alibaba.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index da0469978d6f4..c8655fc5aa5b8 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -2216,6 +2216,7 @@ static void __exit nvmet_tcp_exit(void)
 	flush_workqueue(nvmet_wq);
 
 	destroy_workqueue(nvmet_tcp_wq);
+	ida_destroy(&nvmet_tcp_queue_ida);
 }
 
 module_init(nvmet_tcp_init);
-- 
GitLab


From 4d7acc8f48bcf27d0dc068f02e55c77e840b9110 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Sat, 27 Jan 2024 04:04:34 +1000
Subject: [PATCH 3511/4076] Revert "nouveau: push event block/allowing out of
 the fence context"

This reverts commit eacabb5462717a52fccbbbba458365a4f5e61f35.

This commit causes some regressions in desktop usage, this will
reintroduce the original deadlock in DRI_PRIME situations, I've
got an idea to fix it by offloading to a workqueue in a different
spot, however this code has a race condition where we sometimes
miss interrupts so I'd like to fix that as well.

Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/nouveau/nouveau_fence.c | 28 +++++--------------------
 drivers/gpu/drm/nouveau/nouveau_fence.h |  5 +----
 2 files changed, 6 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 5057d976fa578..ca762ea554136 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -62,7 +62,7 @@ nouveau_fence_signal(struct nouveau_fence *fence)
 	if (test_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags)) {
 		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 
-		if (atomic_dec_and_test(&fctx->notify_ref))
+		if (!--fctx->notify_ref)
 			drop = 1;
 	}
 
@@ -103,7 +103,6 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 void
 nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 {
-	cancel_work_sync(&fctx->allow_block_work);
 	nouveau_fence_context_kill(fctx, 0);
 	nvif_event_dtor(&fctx->event);
 	fctx->dead = 1;
@@ -168,18 +167,6 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc
 	return ret;
 }
 
-static void
-nouveau_fence_work_allow_block(struct work_struct *work)
-{
-	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
-						       allow_block_work);
-
-	if (atomic_read(&fctx->notify_ref) == 0)
-		nvif_event_block(&fctx->event);
-	else
-		nvif_event_allow(&fctx->event);
-}
-
 void
 nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx)
 {
@@ -191,7 +178,6 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 	} args;
 	int ret;
 
-	INIT_WORK(&fctx->allow_block_work, nouveau_fence_work_allow_block);
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
@@ -535,19 +521,15 @@ static bool nouveau_fence_enable_signaling(struct dma_fence *f)
 	struct nouveau_fence *fence = from_fence(f);
 	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 	bool ret;
-	bool do_work;
 
-	if (atomic_inc_return(&fctx->notify_ref) == 0)
-		do_work = true;
+	if (!fctx->notify_ref++)
+		nvif_event_allow(&fctx->event);
 
 	ret = nouveau_fence_no_signaling(f);
 	if (ret)
 		set_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags);
-	else if (atomic_dec_and_test(&fctx->notify_ref))
-		do_work = true;
-
-	if (do_work)
-		schedule_work(&fctx->allow_block_work);
+	else if (!--fctx->notify_ref)
+		nvif_event_block(&fctx->event);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 28f5cf013b898..64d33ae7f3561 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -3,7 +3,6 @@
 #define __NOUVEAU_FENCE_H__
 
 #include <linux/dma-fence.h>
-#include <linux/workqueue.h>
 #include <nvif/event.h>
 
 struct nouveau_drm;
@@ -46,9 +45,7 @@ struct nouveau_fence_chan {
 	char name[32];
 
 	struct nvif_event event;
-	struct work_struct allow_block_work;
-	atomic_t notify_ref;
-	int dead, killed;
+	int notify_ref, dead, killed;
 };
 
 struct nouveau_fence_priv {
-- 
GitLab


From 97aab852c4b9e1b378de48a55f8c9b8d76c36ccc Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Mon, 22 Jan 2024 07:49:52 -0800
Subject: [PATCH 3512/4076] hwmon: gigabyte_waterforce: Fix locking bug in
 waterforce_get_status()

Goto 'unlock_and_return' for unlocking before returning on the error
path.

Fixes: d5939a793693 ("hwmon: Add driver for Gigabyte AORUS Waterforce AIO coolers")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Reviewed-by: Aleksa Savic <savicaleksa83@gmail.com>
Link: https://lore.kernel.org/r/20240122154952.2851934-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/gigabyte_waterforce.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/gigabyte_waterforce.c b/drivers/hwmon/gigabyte_waterforce.c
index 85e5237757142..8129d7b3ceaf9 100644
--- a/drivers/hwmon/gigabyte_waterforce.c
+++ b/drivers/hwmon/gigabyte_waterforce.c
@@ -146,7 +146,7 @@ static int waterforce_get_status(struct waterforce_data *priv)
 	/* Send command for getting status */
 	ret = waterforce_write_expanded(priv, get_status_cmd, GET_STATUS_CMD_LENGTH);
 	if (ret < 0)
-		return ret;
+		goto unlock_and_return;
 
 	ret = wait_for_completion_interruptible_timeout(&priv->status_report_received,
 							msecs_to_jiffies(STATUS_VALIDITY));
-- 
GitLab


From 118063f3803324411be0e601d560ed7d1c9824b0 Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Tue, 23 Jan 2024 19:44:57 +0530
Subject: [PATCH 3513/4076] platform/x86/amd/pmf: Get Human presence
 information from AMD SFH driver

AMD SFH driver has APIs defined to export the human presence information;
use this within the PMF driver to send inputs to the PMF TA, so that PMF
driver can enact to the actions coming from the TA.

Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20240123141458.3715211-1-Shyam-sundar.S-k@amd.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/amd/pmf/Kconfig |  1 +
 drivers/platform/x86/amd/pmf/spc.c   | 28 ++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/Kconfig b/drivers/platform/x86/amd/pmf/Kconfig
index f246252bddd85..f4fa8bd8bda83 100644
--- a/drivers/platform/x86/amd/pmf/Kconfig
+++ b/drivers/platform/x86/amd/pmf/Kconfig
@@ -10,6 +10,7 @@ config AMD_PMF
 	depends on AMD_NB
 	select ACPI_PLATFORM_PROFILE
 	depends on TEE && AMDTEE
+	depends on AMD_SFH_HID
 	help
 	  This driver provides support for the AMD Platform Management Framework.
 	  The goal is to enhance end user experience by making AMD PCs smarter,
diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c
index a0423942f771e..87ae7c41c9f8a 100644
--- a/drivers/platform/x86/amd/pmf/spc.c
+++ b/drivers/platform/x86/amd/pmf/spc.c
@@ -10,6 +10,7 @@
  */
 
 #include <acpi/button.h>
+#include <linux/amd-pmf-io.h>
 #include <linux/power_supply.h>
 #include <linux/units.h>
 #include "pmf.h"
@@ -44,6 +45,7 @@ void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *
 	dev_dbg(dev->dev, "Max C0 Residency: %u\n", in->ev_info.max_c0residency);
 	dev_dbg(dev->dev, "GFX Busy: %u\n", in->ev_info.gfx_busy);
 	dev_dbg(dev->dev, "LID State: %s\n", in->ev_info.lid_state ? "close" : "open");
+	dev_dbg(dev->dev, "User Presence: %s\n", in->ev_info.user_present ? "Present" : "Away");
 	dev_dbg(dev->dev, "==== TA inputs END ====\n");
 }
 #else
@@ -147,6 +149,31 @@ static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_
 	return 0;
 }
 
+static int amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+{
+	struct amd_sfh_info sfh_info;
+	int ret;
+
+	/* get HPD data */
+	ret = amd_get_sfh_info(&sfh_info, MT_HPD);
+	if (ret)
+		return ret;
+
+	switch (sfh_info.user_present) {
+	case SFH_NOT_DETECTED:
+		in->ev_info.user_present = 0xff; /* assume no sensors connected */
+		break;
+	case SFH_USER_PRESENT:
+		in->ev_info.user_present = 1;
+		break;
+	case SFH_USER_AWAY:
+		in->ev_info.user_present = 0;
+		break;
+	}
+
+	return 0;
+}
+
 void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
 {
 	/* TA side lid open is 1 and close is 0, hence the ! here */
@@ -155,4 +182,5 @@ void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_tab
 	amd_pmf_get_smu_info(dev, in);
 	amd_pmf_get_battery_info(dev, in);
 	amd_pmf_get_slider_info(dev, in);
+	amd_pmf_get_sensor_info(dev, in);
 }
-- 
GitLab


From cedecdba60f4a42a8562574119f317ed0c674b5a Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Tue, 23 Jan 2024 19:44:58 +0530
Subject: [PATCH 3514/4076] platform/x86/amd/pmf: Get ambient light information
 from AMD SFH driver

AMD SFH driver has APIs defined to export the ambient light information;
use this within the PMF driver to send inputs to the PMF TA, so that PMF
driver can enact to the actions coming from the TA.

Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20240123141458.3715211-2-Shyam-sundar.S-k@amd.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/amd/pmf/spc.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c
index 87ae7c41c9f8a..a3dec14c30043 100644
--- a/drivers/platform/x86/amd/pmf/spc.c
+++ b/drivers/platform/x86/amd/pmf/spc.c
@@ -46,6 +46,7 @@ void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *
 	dev_dbg(dev->dev, "GFX Busy: %u\n", in->ev_info.gfx_busy);
 	dev_dbg(dev->dev, "LID State: %s\n", in->ev_info.lid_state ? "close" : "open");
 	dev_dbg(dev->dev, "User Presence: %s\n", in->ev_info.user_present ? "Present" : "Away");
+	dev_dbg(dev->dev, "Ambient Light: %d\n", in->ev_info.ambient_light);
 	dev_dbg(dev->dev, "==== TA inputs END ====\n");
 }
 #else
@@ -154,6 +155,13 @@ static int amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_
 	struct amd_sfh_info sfh_info;
 	int ret;
 
+	/* Get ALS data */
+	ret = amd_get_sfh_info(&sfh_info, MT_ALS);
+	if (!ret)
+		in->ev_info.ambient_light = sfh_info.ambient_light;
+	else
+		return ret;
+
 	/* get HPD data */
 	ret = amd_get_sfh_info(&sfh_info, MT_HPD);
 	if (ret)
-- 
GitLab


From a692a86efe97fe0aba7cb15f38cbce866c080689 Mon Sep 17 00:00:00 2001
From: Cong Liu <liucong2@kylinos.cn>
Date: Wed, 24 Jan 2024 09:29:38 +0800
Subject: [PATCH 3515/4076] platform/x86/amd/pmf: Fix memory leak in
 amd_pmf_get_pb_data()

amd_pmf_get_pb_data() will allocate memory for the policy buffer,
but does not free it if copy_from_user() fails. This leads to a memory
leak.

Fixes: 10817f28e533 ("platform/x86/amd/pmf: Add capability to sideload of policy binary")
Reviewed-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: Cong Liu <liucong2@kylinos.cn>
Link: https://lore.kernel.org/r/20240124012939.6550-1-liucong2@kylinos.cn
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/amd/pmf/tee-if.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index 502ce93d5cdda..f8c0177afb0da 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -298,8 +298,10 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf,
 	if (!new_policy_buf)
 		return -ENOMEM;
 
-	if (copy_from_user(new_policy_buf, buf, length))
+	if (copy_from_user(new_policy_buf, buf, length)) {
+		kfree(new_policy_buf);
 		return -EFAULT;
+	}
 
 	kfree(dev->policy_buf);
 	dev->policy_buf = new_policy_buf;
-- 
GitLab


From 8c898ec07a2fc1d4694e81097a48e94a3816308d Mon Sep 17 00:00:00 2001
From: Jithu Joseph <jithu.joseph@intel.com>
Date: Thu, 25 Jan 2024 00:22:50 -0800
Subject: [PATCH 3516/4076] platform/x86/intel/ifs: Call release_firmware()
 when handling errors.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Missing release_firmware() due to error handling blocked any future image
loading.

Fix the return code and release_fiwmare() to release the bad image.

Fixes: 25a76dbb36dd ("platform/x86/intel/ifs: Validate image size")
Reported-by: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Jithu Joseph <jithu.joseph@intel.com>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Tested-by: Pengfei Xu <pengfei.xu@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20240125082254.424859-2-ashok.raj@intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel/ifs/load.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/ifs/load.c b/drivers/platform/x86/intel/ifs/load.c
index a1ee1a74fc3c4..2cf3b4a8813f9 100644
--- a/drivers/platform/x86/intel/ifs/load.c
+++ b/drivers/platform/x86/intel/ifs/load.c
@@ -399,7 +399,8 @@ int ifs_load_firmware(struct device *dev)
 	if (fw->size != expected_size) {
 		dev_err(dev, "File size mismatch (expected %u, actual %zu). Corrupted IFS image.\n",
 			expected_size, fw->size);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto release;
 	}
 
 	ret = image_sanity_check(dev, (struct microcode_header_intel *)fw->data);
-- 
GitLab


From 1abdf288b0ef5606f76b6e191fa6df05330e3d7e Mon Sep 17 00:00:00 2001
From: Phoenix Chen <asbeltogf@gmail.com>
Date: Fri, 26 Jan 2024 17:53:08 +0800
Subject: [PATCH 3517/4076] platform/x86: touchscreen_dmi: Add info for the
 TECLAST X16 Plus tablet

Add touch screen info for TECLAST X16 Plus tablet.

Signed-off-by: Phoenix Chen <asbeltogf@gmail.com>
Link: https://lore.kernel.org/r/20240126095308.5042-1-asbeltogf@gmail.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/touchscreen_dmi.c | 35 ++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index 0c67337726984..7aee5e9ff2b8d 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -944,6 +944,32 @@ static const struct ts_dmi_data teclast_tbook11_data = {
 	.properties	= teclast_tbook11_props,
 };
 
+static const struct property_entry teclast_x16_plus_props[] = {
+	PROPERTY_ENTRY_U32("touchscreen-min-x", 8),
+	PROPERTY_ENTRY_U32("touchscreen-min-y", 14),
+	PROPERTY_ENTRY_U32("touchscreen-size-x", 1916),
+	PROPERTY_ENTRY_U32("touchscreen-size-y", 1264),
+	PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+	PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-teclast-x16-plus.fw"),
+	PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+	PROPERTY_ENTRY_BOOL("silead,home-button"),
+	{ }
+};
+
+static const struct ts_dmi_data teclast_x16_plus_data = {
+	.embedded_fw = {
+		.name	= "silead/gsl3692-teclast-x16-plus.fw",
+		.prefix = { 0xf0, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00 },
+		.length	= 43560,
+		.sha256	= { 0x9d, 0xb0, 0x3d, 0xf1, 0x00, 0x3c, 0xb5, 0x25,
+			    0x62, 0x8a, 0xa0, 0x93, 0x4b, 0xe0, 0x4e, 0x75,
+			    0xd1, 0x27, 0xb1, 0x65, 0x3c, 0xba, 0xa5, 0x0f,
+			    0xcd, 0xb4, 0xbe, 0x00, 0xbb, 0xf6, 0x43, 0x29 },
+	},
+	.acpi_name	= "MSSL1680:00",
+	.properties	= teclast_x16_plus_props,
+};
+
 static const struct property_entry teclast_x3_plus_props[] = {
 	PROPERTY_ENTRY_U32("touchscreen-size-x", 1980),
 	PROPERTY_ENTRY_U32("touchscreen-size-y", 1500),
@@ -1612,6 +1638,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_SKU, "E5A6_A1"),
 		},
 	},
+	{
+		/* Teclast X16 Plus */
+		.driver_data = (void *)&teclast_x16_plus_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TECLAST"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
+			DMI_MATCH(DMI_PRODUCT_SKU, "D3A5_A1"),
+		},
+	},
 	{
 		/* Teclast X3 Plus */
 		.driver_data = (void *)&teclast_x3_plus_data,
-- 
GitLab


From fcf67d82b8b878bdd95145382be43927bce07ec6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 26 Jan 2024 16:32:36 +0100
Subject: [PATCH 3518/4076] selftests: net: add missing config for big tcp
 tests

The big_tcp test-case requires a few kernel knobs currently
not specified in the net selftests config, causing the
following failure:

  # selftests: net: big_tcp.sh
  # Error: Failed to load TC action module.
  # We have an error talking to the kernel
...
  # Testing for BIG TCP:
  # CLI GSO | GW GRO | GW GSO | SER GRO
  # ./big_tcp.sh: line 107: test: !=: unary operator expected
...
  # on        on       on       on      : [FAIL_on_link1]

Add the missing configs

Fixes: 6bb382bcf742 ("selftests: add a selftest for big tcp")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Aaron Conole <aconole@redhat.com>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://lore.kernel.org/all/21630ecea872fea13f071342ac64ef52a991a9b5.1706282943.git.pabeni@redhat.com/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 19ff750516609..413ab9abcf1bf 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -29,7 +29,9 @@ CONFIG_NF_NAT=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP6_NF_NAT=m
+CONFIG_IP6_NF_RAW=m
 CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_RAW=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_SEG6_LWTUNNEL=y
 CONFIG_L2TP_ETH=m
@@ -45,6 +47,8 @@ CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_IPV6=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_NAT=m
+CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_U32=m
@@ -55,6 +59,7 @@ CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
+CONFIG_NF_FLOW_TABLE=m
 CONFIG_PSAMPLE=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_TEST_BLACKHOLE_DEV=m
-- 
GitLab


From 0958b33ef5a04ed91f61cef4760ac412080c4e08 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 26 Jan 2024 09:42:58 +0900
Subject: [PATCH 3519/4076] tracing/trigger: Fix to return error if failed to
 alloc snapshot

Fix register_snapshot_trigger() to return error code if it failed to
allocate a snapshot instead of 0 (success). Unless that, it will register
snapshot trigger without an error.

Link: https://lore.kernel.org/linux-trace-kernel/170622977792.270660.2789298642759362200.stgit@devnote2

Fixes: 0bbe7f719985 ("tracing: Fix the race between registering 'snapshot' event trigger and triggering 'snapshot' operation")
Cc: stable@vger.kernel.org
Cc: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_trigger.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 46439e3bcec4d..b33c3861fbbbf 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1470,8 +1470,10 @@ register_snapshot_trigger(char *glob,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
-	if (tracing_alloc_snapshot_instance(file->tr) != 0)
-		return 0;
+	int ret = tracing_alloc_snapshot_instance(file->tr);
+
+	if (ret < 0)
+		return ret;
 
 	return register_trigger(glob, data, file);
 }
-- 
GitLab


From c60fe56c169eb552113a4711db3a5f99e3acd4c1 Mon Sep 17 00:00:00 2001
From: Konstantin Aladyshev <aladyshev22@gmail.com>
Date: Fri, 26 Jan 2024 23:57:14 +0300
Subject: [PATCH 3520/4076] hwmon: (pmbus/mp2975) Fix driver initialization for
 MP2975 device

The commit 1feb31e810b0 ("hwmon: (pmbus/mp2975) Simplify VOUT code")
has introduced a bug that makes it impossible to initialize MP2975
device:
"""
mp2975 5-0020: Failed to identify chip capabilities
i2c i2c-5: new_device: Instantiated device mp2975 at 0x20
i2c i2c-5: delete_device: Deleting device mp2975 at 0x20
"""
Since the 'read_byte_data' function was removed from the
'pmbus_driver_info ' structure the driver no longer reports correctly
that VOUT mode is direct. Therefore 'pmbus_identify_common' fails
with error, making it impossible to initialize the device.

Restore 'read_byte_data' function to fix the issue.

Tested:
- before: it is not possible to initialize MP2975 device with the
'mp2975' driver,
- after: 'mp2975' correctly initializes MP2975 device and all sensor
data is correct.

Fixes: 1feb31e810b0 ("hwmon: (pmbus/mp2975) Simplify VOUT code")
Signed-off-by: Konstantin Aladyshev <aladyshev22@gmail.com>
Link: https://lore.kernel.org/r/20240126205714.2363-1-aladyshev22@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/mp2975.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/hwmon/pmbus/mp2975.c b/drivers/hwmon/pmbus/mp2975.c
index b9bb469e2d8fe..5bbfdacb61a76 100644
--- a/drivers/hwmon/pmbus/mp2975.c
+++ b/drivers/hwmon/pmbus/mp2975.c
@@ -126,6 +126,22 @@ static const struct regulator_desc __maybe_unused mp2975_reg_desc[] = {
 
 #define to_mp2975_data(x)  container_of(x, struct mp2975_data, info)
 
+static int mp2975_read_byte_data(struct i2c_client *client, int page, int reg)
+{
+	switch (reg) {
+	case PMBUS_VOUT_MODE:
+		/*
+		 * Enforce VOUT direct format, since device allows to set the
+		 * different formats for the different rails. Conversion from
+		 * VID to direct provided by driver internally, in case it is
+		 * necessary.
+		 */
+		return PB_VOUT_MODE_DIRECT;
+	default:
+		return -ENODATA;
+	}
+}
+
 static int
 mp2975_read_word_helper(struct i2c_client *client, int page, int phase, u8 reg,
 			u16 mask)
@@ -869,6 +885,7 @@ static struct pmbus_driver_info mp2975_info = {
 		PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT |
 		PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP | PMBUS_HAVE_POUT |
 		PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT | PMBUS_PHASE_VIRTUAL,
+	.read_byte_data = mp2975_read_byte_data,
 	.read_word_data = mp2975_read_word_data,
 #if IS_ENABLED(CONFIG_SENSORS_MP2975_REGULATOR)
 	.num_regulators = 1,
-- 
GitLab


From d0266d7ab1618482d58015d67a5220e590333298 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Tue, 23 Jan 2024 17:00:53 +0100
Subject: [PATCH 3521/4076] Revert "power: supply: qcom_battmgr: Register the
 power supplies after PDR is up"

This reverts commit b43f7ddc2b7a5a90447d96cb4d3c6d142dd4a810.

The offending commit deferred power-supply class device registration
until the service-started notification is received.

This triggers a NULL pointer dereference during boot of the Lenovo
ThinkPad X13s and SC8280XP CRD as battery status notifications can be
received before the service-start notification:

	Unable to handle kernel NULL pointer dereference at virtual address 00000000000005c0
	...
	Call trace:
	 _acquire+0x338/0x2064
	 acquire+0x1e8/0x318
	 spin_lock_irqsave+0x60/0x88
	 _supply_changed+0x2c/0xa4
	 battmgr_callback+0x1d4/0x60c [qcom_battmgr]
	 pmic_glink_rpmsg_callback+0x5c/0xa4 [pmic_glink]
	 qcom_glink_native_rx+0x58c/0x7e8
	 qcom_glink_smem_intr+0x14/0x24 [qcom_glink_smem]
	 __handle_irq_event_percpu+0xb0/0x2d4
	 handle_irq_event+0x4c/0xb8

As trying to serialise this is non-trivial and risks missing
notifications, let's revert to registration during probe so that the
driver data is all set up once the service goes live.

The warning message during resume in case the aDSP firmware is not
running that motivated the change can be considered a feature and should
not be suppressed.

Fixes: b43f7ddc2b7a ("power: supply: qcom_battmgr: Register the power supplies after PDR is up")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20240123160053.18331-1-johan+linaro@kernel.org
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/qcom_battmgr.c | 109 +++++++++++++---------------
 1 file changed, 49 insertions(+), 60 deletions(-)

diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c
index a12e2a66d516f..ec163d1bcd189 100644
--- a/drivers/power/supply/qcom_battmgr.c
+++ b/drivers/power/supply/qcom_battmgr.c
@@ -282,7 +282,6 @@ struct qcom_battmgr_wireless {
 
 struct qcom_battmgr {
 	struct device *dev;
-	struct auxiliary_device *adev;
 	struct pmic_glink_client *client;
 
 	enum qcom_battmgr_variant variant;
@@ -1294,69 +1293,11 @@ static void qcom_battmgr_enable_worker(struct work_struct *work)
 		dev_err(battmgr->dev, "failed to request power notifications\n");
 }
 
-static char *qcom_battmgr_battery[] = { "battery" };
-
-static void qcom_battmgr_register_psy(struct qcom_battmgr *battmgr)
-{
-	struct power_supply_config psy_cfg_supply = {};
-	struct auxiliary_device *adev = battmgr->adev;
-	struct power_supply_config psy_cfg = {};
-	struct device *dev = &adev->dev;
-
-	psy_cfg.drv_data = battmgr;
-	psy_cfg.of_node = adev->dev.of_node;
-
-	psy_cfg_supply.drv_data = battmgr;
-	psy_cfg_supply.of_node = adev->dev.of_node;
-	psy_cfg_supply.supplied_to = qcom_battmgr_battery;
-	psy_cfg_supply.num_supplicants = 1;
-
-	if (battmgr->variant == QCOM_BATTMGR_SC8280XP) {
-		battmgr->bat_psy = devm_power_supply_register(dev, &sc8280xp_bat_psy_desc, &psy_cfg);
-		if (IS_ERR(battmgr->bat_psy))
-			dev_err(dev, "failed to register battery power supply (%ld)\n",
-				PTR_ERR(battmgr->bat_psy));
-
-		battmgr->ac_psy = devm_power_supply_register(dev, &sc8280xp_ac_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->ac_psy))
-			dev_err(dev, "failed to register AC power supply (%ld)\n",
-				PTR_ERR(battmgr->ac_psy));
-
-		battmgr->usb_psy = devm_power_supply_register(dev, &sc8280xp_usb_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->usb_psy))
-			dev_err(dev, "failed to register USB power supply (%ld)\n",
-				PTR_ERR(battmgr->usb_psy));
-
-		battmgr->wls_psy = devm_power_supply_register(dev, &sc8280xp_wls_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->wls_psy))
-			dev_err(dev, "failed to register wireless charing power supply (%ld)\n",
-				PTR_ERR(battmgr->wls_psy));
-	} else {
-		battmgr->bat_psy = devm_power_supply_register(dev, &sm8350_bat_psy_desc, &psy_cfg);
-		if (IS_ERR(battmgr->bat_psy))
-			dev_err(dev, "failed to register battery power supply (%ld)\n",
-				PTR_ERR(battmgr->bat_psy));
-
-		battmgr->usb_psy = devm_power_supply_register(dev, &sm8350_usb_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->usb_psy))
-			dev_err(dev, "failed to register USB power supply (%ld)\n",
-				PTR_ERR(battmgr->usb_psy));
-
-		battmgr->wls_psy = devm_power_supply_register(dev, &sm8350_wls_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->wls_psy))
-			dev_err(dev, "failed to register wireless charing power supply (%ld)\n",
-				PTR_ERR(battmgr->wls_psy));
-	}
-}
-
 static void qcom_battmgr_pdr_notify(void *priv, int state)
 {
 	struct qcom_battmgr *battmgr = priv;
 
 	if (state == SERVREG_SERVICE_STATE_UP) {
-		if (!battmgr->bat_psy)
-			qcom_battmgr_register_psy(battmgr);
-
 		battmgr->service_up = true;
 		schedule_work(&battmgr->enable_work);
 	} else {
@@ -1371,9 +1312,13 @@ static const struct of_device_id qcom_battmgr_of_variants[] = {
 	{}
 };
 
+static char *qcom_battmgr_battery[] = { "battery" };
+
 static int qcom_battmgr_probe(struct auxiliary_device *adev,
 			      const struct auxiliary_device_id *id)
 {
+	struct power_supply_config psy_cfg_supply = {};
+	struct power_supply_config psy_cfg = {};
 	const struct of_device_id *match;
 	struct qcom_battmgr *battmgr;
 	struct device *dev = &adev->dev;
@@ -1383,7 +1328,14 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev,
 		return -ENOMEM;
 
 	battmgr->dev = dev;
-	battmgr->adev = adev;
+
+	psy_cfg.drv_data = battmgr;
+	psy_cfg.of_node = adev->dev.of_node;
+
+	psy_cfg_supply.drv_data = battmgr;
+	psy_cfg_supply.of_node = adev->dev.of_node;
+	psy_cfg_supply.supplied_to = qcom_battmgr_battery;
+	psy_cfg_supply.num_supplicants = 1;
 
 	INIT_WORK(&battmgr->enable_work, qcom_battmgr_enable_worker);
 	mutex_init(&battmgr->lock);
@@ -1395,6 +1347,43 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev,
 	else
 		battmgr->variant = QCOM_BATTMGR_SM8350;
 
+	if (battmgr->variant == QCOM_BATTMGR_SC8280XP) {
+		battmgr->bat_psy = devm_power_supply_register(dev, &sc8280xp_bat_psy_desc, &psy_cfg);
+		if (IS_ERR(battmgr->bat_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->bat_psy),
+					     "failed to register battery power supply\n");
+
+		battmgr->ac_psy = devm_power_supply_register(dev, &sc8280xp_ac_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->ac_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->ac_psy),
+					     "failed to register AC power supply\n");
+
+		battmgr->usb_psy = devm_power_supply_register(dev, &sc8280xp_usb_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->usb_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->usb_psy),
+					     "failed to register USB power supply\n");
+
+		battmgr->wls_psy = devm_power_supply_register(dev, &sc8280xp_wls_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->wls_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->wls_psy),
+					     "failed to register wireless charing power supply\n");
+	} else {
+		battmgr->bat_psy = devm_power_supply_register(dev, &sm8350_bat_psy_desc, &psy_cfg);
+		if (IS_ERR(battmgr->bat_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->bat_psy),
+					     "failed to register battery power supply\n");
+
+		battmgr->usb_psy = devm_power_supply_register(dev, &sm8350_usb_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->usb_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->usb_psy),
+					     "failed to register USB power supply\n");
+
+		battmgr->wls_psy = devm_power_supply_register(dev, &sm8350_wls_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->wls_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->wls_psy),
+					     "failed to register wireless charing power supply\n");
+	}
+
 	battmgr->client = devm_pmic_glink_register_client(dev,
 							  PMIC_GLINK_OWNER_BATTMGR,
 							  qcom_battmgr_callback,
-- 
GitLab


From c3dfcdb65ec1a4813ec1e0871c52c671ba9c71ac Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Thu, 25 Jan 2024 20:39:16 +0800
Subject: [PATCH 3522/4076] net/smc: fix incorrect SMC-D link group matching
 logic

The logic to determine if SMC-D link group matches is incorrect. The
correct logic should be that it only returns true when the GID is the
same, and the SMC-D device is the same and the extended GID is the same
(in the case of virtual ISM).

It can be fixed by adding brackets around the conditional (or ternary)
operator expression. But for better readability and maintainability, it
has been changed to an if-else statement.

Reported-by: Matthew Rosato <mjrosato@linux.ibm.com>
Closes: https://lore.kernel.org/r/13579588-eb9d-4626-a063-c0b77ed80f11@linux.ibm.com
Fixes: b40584d14570 ("net/smc: compatible with 128-bits extended GID of virtual ISM device")
Link: https://lore.kernel.org/r/13579588-eb9d-4626-a063-c0b77ed80f11@linux.ibm.com
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Link: https://lore.kernel.org/r/20240125123916.77928-1-guwen@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/smc/smc_core.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 95cc95458e2d8..e4c858411207a 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1877,9 +1877,15 @@ static bool smcd_lgr_match(struct smc_link_group *lgr,
 			   struct smcd_dev *smcismdev,
 			   struct smcd_gid *peer_gid)
 {
-	return lgr->peer_gid.gid == peer_gid->gid && lgr->smcd == smcismdev &&
-		smc_ism_is_virtual(smcismdev) ?
-		(lgr->peer_gid.gid_ext == peer_gid->gid_ext) : 1;
+	if (lgr->peer_gid.gid != peer_gid->gid ||
+	    lgr->smcd != smcismdev)
+		return false;
+
+	if (smc_ism_is_virtual(smcismdev) &&
+	    lgr->peer_gid.gid_ext != peer_gid->gid_ext)
+		return false;
+
+	return true;
 }
 
 /* create a new SMC connection (and a new link group if necessary) */
-- 
GitLab


From 281cb9d65a95c00bb844f332cd187491d2d55496 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 25 Jan 2024 05:41:03 -0800
Subject: [PATCH 3523/4076] bnxt_en: Make PTP timestamp HWRM more silent

commit 056bce63c469 ("bnxt_en: Make PTP TX timestamp HWRM query silent")
changed a netdev_err() to netdev_WARN_ONCE().

netdev_WARN_ONCE() is it generates a kernel WARNING, which is bad, for
the following reasons:

 * You do not a kernel warning if the firmware queries are late
 * In busy networks, timestamp query failures fairly regularly
 * A WARNING message doesn't bring much value, since the code path
is clear.
(This was discussed in-depth in [1])

Transform the netdev_WARN_ONCE() into a netdev_warn_once(), and print a
more well-behaved message, instead of a full WARN().

	bnxt_en 0000:67:00.0 eth0: TS query for TX timer failed rc = fffffff5

[1] Link: https://lore.kernel.org/all/ZbDj%2FFI4EJezcfd1@gmail.com/
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Fixes: 056bce63c469 ("bnxt_en: Make PTP TX timestamp HWRM query silent")
Link: https://lore.kernel.org/r/20240125134104.2045573-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index adad188e38b82..cc07660330f53 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -684,7 +684,7 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(ptp->tx_skb, &timestamp);
 	} else {
-		netdev_WARN_ONCE(bp->dev,
+		netdev_warn_once(bp->dev,
 				 "TS query for TX timer failed rc = %x\n", rc);
 	}
 
-- 
GitLab


From d3cb3b0088ca92082e2bebc40cc6894a632173e2 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 25 Jan 2024 09:22:50 +0100
Subject: [PATCH 3524/4076] selftests: net: add missing required classifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

the udpgro_fraglist self-test uses the BPF classifiers, but the
current net self-test configuration does not include it, causing
CI failures:

 # selftests: net: udpgro_frglist.sh
 # ipv6
 # tcp - over veth touching data
 # -l 4 -6 -D 2001:db8::1 -t rx -4 -t
 # Error: TC classifier not found.
 # We have an error talking to the kernel
 # Error: TC classifier not found.
 # We have an error talking to the kernel

Add the missing knob.

Fixes: edae34a3ed92 ("selftests net: add UDP GRO fraglist + bpf self-tests")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/7c3643763b331e9a400e1874fe089193c99a1c3f.1706170897.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 413ab9abcf1bf..56da5d52674cf 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -51,6 +51,7 @@ CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_BPF=m
 CONFIG_NET_CLS_U32=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-- 
GitLab


From 89abe628375301fedb68770644df845d49018d8b Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 25 Jan 2024 19:09:06 +0100
Subject: [PATCH 3525/4076] selftests: net: give more time for GRO aggregation

The gro.sh test-case relay on the gro_flush_timeout to ensure
that all the segments belonging to any given batch are properly
aggregated.

The other end, the sender is a user-space program transmitting
each packet with a separate write syscall. A busy host and/or
stracing the sender program can make the relevant segments reach
the GRO engine after the flush timeout triggers.

Give the GRO flush timeout more slack, to avoid sporadic self-tests
failures.

Fixes: 9af771d2ec04 ("selftests/net: allow GRO coalesce test on veth")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Tested-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/bffec2beab3a5672dd13ecabe4fad81d2155b367.1706206101.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/setup_veth.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh
index a9a1759e035ca..1f78a87f6f37e 100644
--- a/tools/testing/selftests/net/setup_veth.sh
+++ b/tools/testing/selftests/net/setup_veth.sh
@@ -11,7 +11,7 @@ setup_veth_ns() {
 	local -r ns_mac="$4"
 
 	[[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}"
-	echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+	echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
 	ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535
 	ip -netns "${ns_name}" link set dev "${ns_dev}" up
 
-- 
GitLab


From 8d975c15c0cd744000ca386247432d57b21f9df0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 25 Jan 2024 17:05:57 +0000
Subject: [PATCH 3526/4076] ip6_tunnel: make sure to pull inner header in
 __ip6_tnl_rcv()

syzbot found __ip6_tnl_rcv() could access unitiliazed data [1].

Call pskb_inet_may_pull() to fix this, and initialize ipv6h
variable after this call as it can change skb->head.

[1]
 BUG: KMSAN: uninit-value in __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline]
 BUG: KMSAN: uninit-value in INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline]
 BUG: KMSAN: uninit-value in IP6_ECN_decapsulate+0x7df/0x1e50 include/net/inet_ecn.h:321
  __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline]
  INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline]
  IP6_ECN_decapsulate+0x7df/0x1e50 include/net/inet_ecn.h:321
  ip6ip6_dscp_ecn_decapsulate+0x178/0x1b0 net/ipv6/ip6_tunnel.c:727
  __ip6_tnl_rcv+0xd4e/0x1590 net/ipv6/ip6_tunnel.c:845
  ip6_tnl_rcv+0xce/0x100 net/ipv6/ip6_tunnel.c:888
 gre_rcv+0x143f/0x1870
  ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438
  ip6_input_finish net/ipv6/ip6_input.c:483 [inline]
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492
  ip6_mc_input+0xa7e/0xc80 net/ipv6/ip6_input.c:586
  dst_input include/net/dst.h:461 [inline]
  ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310
  __netif_receive_skb_one_core net/core/dev.c:5532 [inline]
  __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5646
  netif_receive_skb_internal net/core/dev.c:5732 [inline]
  netif_receive_skb+0x58/0x660 net/core/dev.c:5791
  tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1555
  tun_get_user+0x53af/0x66d0 drivers/net/tun.c:2002
  tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048
  call_write_iter include/linux/fs.h:2084 [inline]
  new_sync_write fs/read_write.c:497 [inline]
  vfs_write+0x786/0x1200 fs/read_write.c:590
  ksys_write+0x20f/0x4c0 fs/read_write.c:643
  __do_sys_write fs/read_write.c:655 [inline]
  __se_sys_write fs/read_write.c:652 [inline]
  __x64_sys_write+0x93/0xd0 fs/read_write.c:652
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0x6d/0x140 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Uninit was created at:
  slab_post_alloc_hook+0x129/0xa70 mm/slab.h:768
  slab_alloc_node mm/slub.c:3478 [inline]
  kmem_cache_alloc_node+0x5e9/0xb10 mm/slub.c:3523
  kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:560
  __alloc_skb+0x318/0x740 net/core/skbuff.c:651
  alloc_skb include/linux/skbuff.h:1286 [inline]
  alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6334
  sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2787
  tun_alloc_skb drivers/net/tun.c:1531 [inline]
  tun_get_user+0x1e8a/0x66d0 drivers/net/tun.c:1846
  tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048
  call_write_iter include/linux/fs.h:2084 [inline]
  new_sync_write fs/read_write.c:497 [inline]
  vfs_write+0x786/0x1200 fs/read_write.c:590
  ksys_write+0x20f/0x4c0 fs/read_write.c:643
  __do_sys_write fs/read_write.c:655 [inline]
  __se_sys_write fs/read_write.c:652 [inline]
  __x64_sys_write+0x93/0xd0 fs/read_write.c:652
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0x6d/0x140 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

CPU: 0 PID: 5034 Comm: syz-executor331 Not tainted 6.7.0-syzkaller-00562-g9f8413c4a66f #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023

Fixes: 0d3c703a9d17 ("ipv6: Cleanup IPv6 tunnel receive path")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240125170557.2663942-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_tunnel.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 46c19bd489901..9bbabf750a21e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 						struct sk_buff *skb),
 			 bool log_ecn_err)
 {
-	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-	int err;
+	const struct ipv6hdr *ipv6h;
+	int nh, err;
 
 	if ((!(tpi->flags & TUNNEL_CSUM) &&
 	     (tunnel->parms.i_flags & TUNNEL_CSUM)) ||
@@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 			goto drop;
 		}
 
-		ipv6h = ipv6_hdr(skb);
 		skb->protocol = eth_type_trans(skb, tunnel->dev);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 	} else {
@@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 		skb_reset_mac_header(skb);
 	}
 
+	/* Save offset of outer header relative to skb->head,
+	 * because we are going to reset the network header to the inner header
+	 * and might change skb->head.
+	 */
+	nh = skb_network_header(skb) - skb->head;
+
 	skb_reset_network_header(skb);
+
+	if (!pskb_inet_may_pull(skb)) {
+		DEV_STATS_INC(tunnel->dev, rx_length_errors);
+		DEV_STATS_INC(tunnel->dev, rx_errors);
+		goto drop;
+	}
+
+	/* Get the outer header. */
+	ipv6h = (struct ipv6hdr *)(skb->head + nh);
+
 	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 
 	__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
-- 
GitLab


From dfa988b4c7c3a48bde7c2713308920c7741fff29 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Wed, 24 Jan 2024 05:17:25 +0000
Subject: [PATCH 3527/4076] net: dsa: mt7530: fix 10M/100M speed on MT7988
 switch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Setup PMCR port register for actual speed and duplex on internally
connected PHYs of the MT7988 built-in switch. This fixes links with
speeds other than 1000M.

Fixes: 110c18bfed41 ("net: dsa: mt7530: introduce driver for MT7988 built-in switch")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Arınç ÜNAL <arinc.unal@arinc9.com>
Link: https://lore.kernel.org/r/a5b04dfa8256d8302f402545a51ac4c626fdba25.1706071272.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mt7530.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 391c4dbdff428..3c1f657593a8f 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2838,8 +2838,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port,
 	/* MT753x MAC works in 1G full duplex mode for all up-clocked
 	 * variants.
 	 */
-	if (interface == PHY_INTERFACE_MODE_INTERNAL ||
-	    interface == PHY_INTERFACE_MODE_TRGMII ||
+	if (interface == PHY_INTERFACE_MODE_TRGMII ||
 	    (phy_interface_mode_is_8023z(interface))) {
 		speed = SPEED_1000;
 		duplex = DUPLEX_FULL;
-- 
GitLab


From 99b817c173cd213671daecd25ca27f56b0c7c4ec Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Fri, 26 Jan 2024 11:44:03 +0100
Subject: [PATCH 3528/4076] lsm: fix the logic in security_inode_getsecctx()

The inode_getsecctx LSM hook has previously been corrected to have
-EOPNOTSUPP instead of 0 as the default return value to fix BPF LSM
behavior. However, the call_int_hook()-generated loop in
security_inode_getsecctx() was left treating 0 as the neutral value, so
after an LSM returns 0, the loop continues to try other LSMs, and if one
of them returns a non-zero value, the function immediately returns with
said value. So in a situation where SELinux and the BPF LSMs registered
this hook, -EOPNOTSUPP would be incorrectly returned whenever SELinux
returned 0.

Fix this by open-coding the call_int_hook() loop and making it use the
correct LSM_RET_DEFAULT() value as the neutral one, similar to what
other hooks do.

Cc: stable@vger.kernel.org
Reported-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Link: https://lore.kernel.org/selinux/CAEjxPJ4ev-pasUwGx48fDhnmjBnq_Wh90jYPwRQRAqXxmOKD4Q@mail.gmail.com/
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2257983
Fixes: b36995b8609a ("lsm: fix default return value for inode_getsecctx")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Reviewed-by: Casey Schaufler <casey@schaufler-ca.com>
[PM: subject line tweak]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/security.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/security/security.c b/security/security.c
index 0144a98d3712e..6196ccaba433a 100644
--- a/security/security.c
+++ b/security/security.c
@@ -4255,7 +4255,19 @@ EXPORT_SYMBOL(security_inode_setsecctx);
  */
 int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
 {
-	return call_int_hook(inode_getsecctx, -EOPNOTSUPP, inode, ctx, ctxlen);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) {
+		rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen);
+		if (rc != LSM_RET_DEFAULT(inode_getsecctx))
+			return rc;
+	}
+
+	return LSM_RET_DEFAULT(inode_getsecctx);
 }
 EXPORT_SYMBOL(security_inode_getsecctx);
 
-- 
GitLab


From d9281660ff3ffb4a05302b485cc59a87e709aefc Mon Sep 17 00:00:00 2001
From: Chunhai Guo <guochunhai@vivo.com>
Date: Fri, 26 Jan 2024 22:01:42 +0800
Subject: [PATCH 3529/4076] erofs: relaxed temporary buffers allocation on
 readahead

Even with inplace decompression, sometimes very few temporary buffers
may be still needed for a single decompression shot (e.g. 16 pages for
64k sliding window or 4 pages for 16k sliding window).  In low-memory
scenarios, it would be better to try to allocate with GFP_NOWAIT on
readahead first.  That can help reduce the time spent on page allocation
under durative memory pressure.

Here are detailed performance numbers under multi-app launch benchmark
workload [1] on ARM64 Android devices (8-core CPU and 8GB of memory)
running a 5.15 LTS kernel with EROFS of 4k pclusters:

+----------------------------------------------+
|      LZ4       | vanilla | patched |  diff   |
|----------------+---------+---------+---------|
|  Average (ms)  |  3364   |  2684   | -20.21% | [64k sliding window]
|----------------+---------+---------+---------|
|  Average (ms)  |  2079   |  1610   | -22.56% | [16k sliding window]
+----------------------------------------------+

The total size of system images for 4k pclusters is almost unchanged:
(64k sliding window)  9,117,044 KB
(16k sliding window)  9,113,096 KB

Therefore, in addition to switch the sliding window from 64k to 16k,
after applying this patch, it can eventually save 52.14% (3364 -> 1610)
on average with no memory reservation.  That is particularly useful for
embedded devices with limited resources.

[1] https://lore.kernel.org/r/20240109074143.4138783-1-guochunhai@vivo.com

Suggested-by: Gao Xiang <xiang@kernel.org>
Signed-off-by: Chunhai Guo <guochunhai@vivo.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Link: https://lore.kernel.org/r/20240126140142.201718-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/compress.h             |  5 ++---
 fs/erofs/decompressor.c         |  5 +++--
 fs/erofs/decompressor_deflate.c | 19 +++++++++++++------
 fs/erofs/decompressor_lzma.c    | 17 ++++++++++++-----
 fs/erofs/zdata.c                | 16 ++++++++++++----
 5 files changed, 42 insertions(+), 20 deletions(-)

diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h
index 279933e007d21..7cc5841577b24 100644
--- a/fs/erofs/compress.h
+++ b/fs/erofs/compress.h
@@ -11,13 +11,12 @@
 struct z_erofs_decompress_req {
 	struct super_block *sb;
 	struct page **in, **out;
-
 	unsigned short pageofs_in, pageofs_out;
 	unsigned int inputsize, outputsize;
 
-	/* indicate the algorithm will be used for decompression */
-	unsigned int alg;
+	unsigned int alg;       /* the algorithm for decompression */
 	bool inplace_io, partial_decoding, fillgaps;
+	gfp_t gfp;      /* allocation flags for extra temporary buffers */
 };
 
 struct z_erofs_decompressor {
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 072ef6a66823e..d4cee95af14c7 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -111,8 +111,9 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx,
 			victim = availables[--top];
 			get_page(victim);
 		} else {
-			victim = erofs_allocpage(pagepool,
-						 GFP_KERNEL | __GFP_NOFAIL);
+			victim = erofs_allocpage(pagepool, rq->gfp);
+			if (!victim)
+				return -ENOMEM;
 			set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE);
 		}
 		rq->out[i] = victim;
diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c
index 4a64a9c91dd32..b98872058abe8 100644
--- a/fs/erofs/decompressor_deflate.c
+++ b/fs/erofs/decompressor_deflate.c
@@ -95,7 +95,7 @@ int z_erofs_load_deflate_config(struct super_block *sb,
 }
 
 int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
-			       struct page **pagepool)
+			       struct page **pgpl)
 {
 	const unsigned int nrpages_out =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
@@ -158,8 +158,12 @@ again:
 			strm->z.avail_out = min_t(u32, outsz, PAGE_SIZE - pofs);
 			outsz -= strm->z.avail_out;
 			if (!rq->out[no]) {
-				rq->out[no] = erofs_allocpage(pagepool,
-						GFP_KERNEL | __GFP_NOFAIL);
+				rq->out[no] = erofs_allocpage(pgpl, rq->gfp);
+				if (!rq->out[no]) {
+					kout = NULL;
+					err = -ENOMEM;
+					break;
+				}
 				set_page_private(rq->out[no],
 						 Z_EROFS_SHORTLIVED_PAGE);
 			}
@@ -211,8 +215,11 @@ again:
 
 			DBG_BUGON(erofs_page_is_managed(EROFS_SB(sb),
 							rq->in[j]));
-			tmppage = erofs_allocpage(pagepool,
-						  GFP_KERNEL | __GFP_NOFAIL);
+			tmppage = erofs_allocpage(pgpl, rq->gfp);
+			if (!tmppage) {
+				err = -ENOMEM;
+				goto failed;
+			}
 			set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE);
 			copy_highpage(tmppage, rq->in[j]);
 			rq->in[j] = tmppage;
@@ -230,7 +237,7 @@ again:
 			break;
 		}
 	}
-
+failed:
 	if (zlib_inflateEnd(&strm->z) != Z_OK && !err)
 		err = -EIO;
 	if (kout)
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index 2dd14f99c1dc1..6ca357d83cfa4 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -148,7 +148,7 @@ again:
 }
 
 int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
-			    struct page **pagepool)
+			    struct page **pgpl)
 {
 	const unsigned int nrpages_out =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
@@ -215,8 +215,11 @@ again:
 						   PAGE_SIZE - pageofs);
 			outlen -= strm->buf.out_size;
 			if (!rq->out[no] && rq->fillgaps) {	/* deduped */
-				rq->out[no] = erofs_allocpage(pagepool,
-						GFP_KERNEL | __GFP_NOFAIL);
+				rq->out[no] = erofs_allocpage(pgpl, rq->gfp);
+				if (!rq->out[no]) {
+					err = -ENOMEM;
+					break;
+				}
 				set_page_private(rq->out[no],
 						 Z_EROFS_SHORTLIVED_PAGE);
 			}
@@ -258,8 +261,11 @@ again:
 
 			DBG_BUGON(erofs_page_is_managed(EROFS_SB(rq->sb),
 							rq->in[j]));
-			tmppage = erofs_allocpage(pagepool,
-						  GFP_KERNEL | __GFP_NOFAIL);
+			tmppage = erofs_allocpage(pgpl, rq->gfp);
+			if (!tmppage) {
+				err = -ENOMEM;
+				goto failed;
+			}
 			set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE);
 			copy_highpage(tmppage, rq->in[j]);
 			rq->in[j] = tmppage;
@@ -277,6 +283,7 @@ again:
 			break;
 		}
 	}
+failed:
 	if (no < nrpages_out && strm->buf.out)
 		kunmap(rq->out[no]);
 	if (ni < nrpages_in)
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index c1c77166b30ff..ff0aa72b0db34 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -82,6 +82,9 @@ struct z_erofs_pcluster {
 	/* L: indicate several pageofs_outs or not */
 	bool multibases;
 
+	/* L: whether extra buffer allocations are best-effort */
+	bool besteffort;
+
 	/* A: compressed bvecs (can be cached or inplaced pages) */
 	struct z_erofs_bvec compressed_bvecs[];
 };
@@ -960,7 +963,7 @@ static int z_erofs_read_fragment(struct super_block *sb, struct page *page,
 }
 
 static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
-				struct page *page)
+				struct page *page, bool ra)
 {
 	struct inode *const inode = fe->inode;
 	struct erofs_map_blocks *const map = &fe->map;
@@ -1010,6 +1013,7 @@ repeat:
 		err = z_erofs_pcluster_begin(fe);
 		if (err)
 			goto out;
+		fe->pcl->besteffort |= !ra;
 	}
 
 	/*
@@ -1276,6 +1280,9 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 					.inplace_io = overlapped,
 					.partial_decoding = pcl->partial,
 					.fillgaps = pcl->multibases,
+					.gfp = pcl->besteffort ?
+						GFP_KERNEL | __GFP_NOFAIL :
+						GFP_NOWAIT | __GFP_NORETRY
 				 }, be->pagepool);
 
 	/* must handle all compressed pages before actual file pages */
@@ -1318,6 +1325,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	pcl->length = 0;
 	pcl->partial = true;
 	pcl->multibases = false;
+	pcl->besteffort = false;
 	pcl->bvset.nextpage = NULL;
 	pcl->vcnt = 0;
 
@@ -1787,7 +1795,7 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f,
 			if (PageUptodate(page))
 				unlock_page(page);
 			else
-				(void)z_erofs_do_read_page(f, page);
+				(void)z_erofs_do_read_page(f, page, !!rac);
 			put_page(page);
 		}
 
@@ -1808,7 +1816,7 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio)
 	f.headoffset = (erofs_off_t)folio->index << PAGE_SHIFT;
 
 	z_erofs_pcluster_readmore(&f, NULL, true);
-	err = z_erofs_do_read_page(&f, &folio->page);
+	err = z_erofs_do_read_page(&f, &folio->page, false);
 	z_erofs_pcluster_readmore(&f, NULL, false);
 	z_erofs_pcluster_end(&f);
 
@@ -1849,7 +1857,7 @@ static void z_erofs_readahead(struct readahead_control *rac)
 		folio = head;
 		head = folio_get_private(folio);
 
-		err = z_erofs_do_read_page(&f, &folio->page);
+		err = z_erofs_do_read_page(&f, &folio->page, true);
 		if (err && err != -EINTR)
 			erofs_err(inode->i_sb, "readahead error at folio %lu @ nid %llu",
 				  folio->index, EROFS_I(inode)->nid);
-- 
GitLab


From e622502c310f1069fd9f41cd38210553115f610a Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 25 Jan 2024 15:18:47 +0100
Subject: [PATCH 3530/4076] ipmr: fix kernel panic when forwarding mcast
 packets

The stacktrace was:
[   86.305548] BUG: kernel NULL pointer dereference, address: 0000000000000092
[   86.306815] #PF: supervisor read access in kernel mode
[   86.307717] #PF: error_code(0x0000) - not-present page
[   86.308624] PGD 0 P4D 0
[   86.309091] Oops: 0000 [#1] PREEMPT SMP NOPTI
[   86.309883] CPU: 2 PID: 3139 Comm: pimd Tainted: G     U             6.8.0-6wind-knet #1
[   86.311027] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.1-0-g0551a4be2c-prebuilt.qemu-project.org 04/01/2014
[   86.312728] RIP: 0010:ip_mr_forward (/build/work/knet/net/ipv4/ipmr.c:1985)
[ 86.313399] Code: f9 1f 0f 87 85 03 00 00 48 8d 04 5b 48 8d 04 83 49 8d 44 c5 00 48 8b 40 70 48 39 c2 0f 84 d9 00 00 00 49 8b 46 58 48 83 e0 fe <80> b8 92 00 00 00 00 0f 84 55 ff ff ff 49 83 47 38 01 45 85 e4 0f
[   86.316565] RSP: 0018:ffffad21c0583ae0 EFLAGS: 00010246
[   86.317497] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[   86.318596] RDX: ffff9559cb46c000 RSI: 0000000000000000 RDI: 0000000000000000
[   86.319627] RBP: ffffad21c0583b30 R08: 0000000000000000 R09: 0000000000000000
[   86.320650] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001
[   86.321672] R13: ffff9559c093a000 R14: ffff9559cc00b800 R15: ffff9559c09c1d80
[   86.322873] FS:  00007f85db661980(0000) GS:ffff955a79d00000(0000) knlGS:0000000000000000
[   86.324291] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   86.325314] CR2: 0000000000000092 CR3: 000000002f13a000 CR4: 0000000000350ef0
[   86.326589] Call Trace:
[   86.327036]  <TASK>
[   86.327434] ? show_regs (/build/work/knet/arch/x86/kernel/dumpstack.c:479)
[   86.328049] ? __die (/build/work/knet/arch/x86/kernel/dumpstack.c:421 /build/work/knet/arch/x86/kernel/dumpstack.c:434)
[   86.328508] ? page_fault_oops (/build/work/knet/arch/x86/mm/fault.c:707)
[   86.329107] ? do_user_addr_fault (/build/work/knet/arch/x86/mm/fault.c:1264)
[   86.329756] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223)
[   86.330350] ? __irq_work_queue_local (/build/work/knet/kernel/irq_work.c:111 (discriminator 1))
[   86.331013] ? exc_page_fault (/build/work/knet/./arch/x86/include/asm/paravirt.h:693 /build/work/knet/arch/x86/mm/fault.c:1515 /build/work/knet/arch/x86/mm/fault.c:1563)
[   86.331702] ? asm_exc_page_fault (/build/work/knet/./arch/x86/include/asm/idtentry.h:570)
[   86.332468] ? ip_mr_forward (/build/work/knet/net/ipv4/ipmr.c:1985)
[   86.333183] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223)
[   86.333920] ipmr_mfc_add (/build/work/knet/./include/linux/rcupdate.h:782 /build/work/knet/net/ipv4/ipmr.c:1009 /build/work/knet/net/ipv4/ipmr.c:1273)
[   86.334583] ? __pfx_ipmr_hash_cmp (/build/work/knet/net/ipv4/ipmr.c:363)
[   86.335357] ip_mroute_setsockopt (/build/work/knet/net/ipv4/ipmr.c:1470)
[   86.336135] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223)
[   86.336854] ? ip_mroute_setsockopt (/build/work/knet/net/ipv4/ipmr.c:1470)
[   86.337679] do_ip_setsockopt (/build/work/knet/net/ipv4/ip_sockglue.c:944)
[   86.338408] ? __pfx_unix_stream_read_actor (/build/work/knet/net/unix/af_unix.c:2862)
[   86.339232] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223)
[   86.339809] ? aa_sk_perm (/build/work/knet/security/apparmor/include/cred.h:153 /build/work/knet/security/apparmor/net.c:181)
[   86.340342] ip_setsockopt (/build/work/knet/net/ipv4/ip_sockglue.c:1415)
[   86.340859] raw_setsockopt (/build/work/knet/net/ipv4/raw.c:836)
[   86.341408] ? security_socket_setsockopt (/build/work/knet/security/security.c:4561 (discriminator 13))
[   86.342116] sock_common_setsockopt (/build/work/knet/net/core/sock.c:3716)
[   86.342747] do_sock_setsockopt (/build/work/knet/net/socket.c:2313)
[   86.343363] __sys_setsockopt (/build/work/knet/./include/linux/file.h:32 /build/work/knet/net/socket.c:2336)
[   86.344020] __x64_sys_setsockopt (/build/work/knet/net/socket.c:2340)
[   86.344766] do_syscall_64 (/build/work/knet/arch/x86/entry/common.c:52 /build/work/knet/arch/x86/entry/common.c:83)
[   86.345433] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223)
[   86.346161] ? syscall_exit_work (/build/work/knet/./include/linux/audit.h:357 /build/work/knet/kernel/entry/common.c:160)
[   86.346938] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223)
[   86.347657] ? syscall_exit_to_user_mode (/build/work/knet/kernel/entry/common.c:215)
[   86.348538] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223)
[   86.349262] ? do_syscall_64 (/build/work/knet/./arch/x86/include/asm/cpufeature.h:171 /build/work/knet/arch/x86/entry/common.c:98)
[   86.349971] entry_SYSCALL_64_after_hwframe (/build/work/knet/arch/x86/entry/entry_64.S:129)

The original packet in ipmr_cache_report() may be queued and then forwarded
with ip_mr_forward(). This last function has the assumption that the skb
dst is set.

After the below commit, the skb dst is dropped by ipv4_pktinfo_prepare(),
which causes the oops.

Fixes: bb7403655b3c ("ipmr: support IP_PKTINFO on cache report IGMP msg")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240125141847.1931933-1-nicolas.dichtel@6wind.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip.h       | 2 +-
 net/ipv4/ip_sockglue.c | 6 ++++--
 net/ipv4/ipmr.c        | 2 +-
 net/ipv4/raw.c         | 2 +-
 net/ipv4/udp.c         | 2 +-
 5 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index de0c69c57e3cb..25cb688bdc623 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -767,7 +767,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
  *	Functions provided by ip_sockglue.c
  */
 
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst);
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			 struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 7aa9dc0e6760d..21d2ffa919e98 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1363,12 +1363,13 @@ e_inval:
  * ipv4_pktinfo_prepare - transfer some info from rtable to skb
  * @sk: socket
  * @skb: buffer
+ * @drop_dst: if true, drops skb dst
  *
  * To support IP_CMSG_PKTINFO option, we store rt_iif and specific
  * destination in skb->cb[] before dst drop.
  * This way, receiver doesn't make cache line misses to read rtable.
  */
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
 	bool prepare = inet_test_bit(PKTINFO, sk) ||
@@ -1397,7 +1398,8 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	skb_dst_drop(skb);
+	if (drop_dst)
+		skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d6f59531b3a0..3622298365105 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1073,7 +1073,7 @@ static int ipmr_cache_report(const struct mr_table *mrt,
 		msg = (struct igmpmsg *)skb_network_header(skb);
 		msg->im_vif = vifi;
 		msg->im_vif_hi = vifi >> 8;
-		ipv4_pktinfo_prepare(mroute_sk, pkt);
+		ipv4_pktinfo_prepare(mroute_sk, pkt, false);
 		memcpy(skb->cb, pkt->cb, sizeof(skb->cb));
 		/* Add our header */
 		igmp = skb_put(skb, sizeof(struct igmphdr));
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 27da9d7294c0b..aea89326c6979 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -292,7 +292,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	/* Charge it to the socket. */
 
-	ipv4_pktinfo_prepare(sk, skb);
+	ipv4_pktinfo_prepare(sk, skb, true);
 	if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) {
 		kfree_skb_reason(skb, reason);
 		return NET_RX_DROP;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 148ffb007969f..f631b0a21af4c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2169,7 +2169,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 
 	udp_csum_pull_header(skb);
 
-	ipv4_pktinfo_prepare(sk, skb);
+	ipv4_pktinfo_prepare(sk, skb, true);
 	return __udp_queue_rcv_skb(sk, skb);
 
 csum_error:
-- 
GitLab


From 59f7ea703c38abc3f239068d49cc8897740e4c54 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Tue, 9 Jan 2024 22:58:59 +0100
Subject: [PATCH 3531/4076] batman-adv: mcast: fix mcast packet type counter on
 timeouted nodes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When a node which does not have the new batman-adv multicast packet type
capability vanishes then the according, global counter erroneously would
not be reduced in response on other nodes. Which in turn leads to the mesh
never switching back to sending with the new multicast packet type.

Fix this by reducing the according counter when such a node times out.

Fixes: 90039133221e ("batman-adv: mcast: implement multicast packet generation")
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/multicast.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index d982daea83292..b4f8b4af17226 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -2198,6 +2198,8 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
 				      BATADV_MCAST_WANT_NO_RTR4);
 	batadv_mcast_want_rtr6_update(bat_priv, orig,
 				      BATADV_MCAST_WANT_NO_RTR6);
+	batadv_mcast_have_mc_ptype_update(bat_priv, orig,
+					  BATADV_MCAST_HAVE_MC_PTYPE_CAPA);
 
 	spin_unlock_bh(&orig->mcast_handler_lock);
 }
-- 
GitLab


From 0a186b49bba596b81de5a686ce5bfc9cd48ab3ef Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Wed, 17 Jan 2024 06:22:20 +0100
Subject: [PATCH 3532/4076] batman-adv: mcast: fix memory leak on deleting a
 batman-adv interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The batman-adv multicast tracker TVLV handler is registered for the
new batman-adv multicast packet type upon creating a batman-adv interface,
but not unregistered again upon the interface's deletion, leading to a
memory leak.

Fix this memory leak by calling the according TVLV handler unregister
routine for the multicast tracker TVLV upon batman-adv interface
deletion.

Fixes: 07afe1ba288c ("batman-adv: mcast: implement multicast packet reception and forwarding")
Reported-and-tested-by: syzbot+ebe64cc5950868e77358@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/000000000000beadc4060f0cbc23@google.com/
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/multicast.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index b4f8b4af17226..14088c4ff2f66 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -2175,6 +2175,7 @@ void batadv_mcast_free(struct batadv_priv *bat_priv)
 	cancel_delayed_work_sync(&bat_priv->mcast.work);
 
 	batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
+	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST_TRACKER, 1);
 	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
 
 	/* safely calling outside of worker, as worker was canceled above */
-- 
GitLab


From 586e40aa883cab255ab8ddfe332c4092a5349cb7 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 24 Jan 2024 09:16:22 +0000
Subject: [PATCH 3533/4076] MAINTAINERS: Add connector headers to NETWORKING
 DRIVERS

Commit 46cf789b68b2 ("connector: Move maintainence under networking
drivers umbrella.") moved the connector maintenance but did not include
the connector header files.

It seems that it has always been implied that these headers were
maintained along with the rest of the connector code, both before and
after the cited commit. Make this explicit.

Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 92152ac346c8d..9435ea0f8cda0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15179,6 +15179,7 @@ F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
 F:	include/dt-bindings/net/
+F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
 F:	include/linux/fcdevice.h
 F:	include/linux/fddidevice.h
@@ -15186,6 +15187,7 @@ F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
 F:	include/linux/netdevice.h
+F:	include/uapi/linux/cn_proc.h
 F:	include/uapi/linux/if_*
 F:	include/uapi/linux/netdevice.h
 X:	drivers/net/wireless/
-- 
GitLab


From 62b4248105353e7d1debd30ca5c57ec5e5f28e35 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Wed, 24 Jan 2024 11:17:58 +0100
Subject: [PATCH 3534/4076] net: lan966x: Fix port configuration when using
 SGMII interface

In case the interface between the MAC and the PHY is SGMII, then the bit
GIGA_MODE on the MAC side needs to be set regardless of the speed at
which it is running.

Fixes: d28d6d2e37d1 ("net: lan966x: add port module support")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_port.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
index 92108d354051c..2e83bbb9477e0 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
@@ -168,9 +168,10 @@ static void lan966x_port_link_up(struct lan966x_port *port)
 	lan966x_taprio_speed_set(port, config->speed);
 
 	/* Also the GIGA_MODE_ENA(1) needs to be set regardless of the
-	 * port speed for QSGMII ports.
+	 * port speed for QSGMII or SGMII ports.
 	 */
-	if (phy_interface_num_ports(config->portmode) == 4)
+	if (phy_interface_num_ports(config->portmode) == 4 ||
+	    config->portmode == PHY_INTERFACE_MODE_SGMII)
 		mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA_SET(1);
 
 	lan_wr(config->duplex | mode,
-- 
GitLab


From c91c6b2f08afb7be111678ceade563158c9a31ba Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Sat, 27 Jan 2024 11:07:49 +0100
Subject: [PATCH 3535/4076] Revert "MIPS: loongson64: set nid for reserved
 memblock region"

This reverts commit ce7b1b97776ec0b068c4dd6b6dbb48ae09a23519.

Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/loongson64/init.c | 2 --
 arch/mips/loongson64/numa.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index 000ba91c0886e..f25caa6aa9d30 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -103,8 +103,6 @@ void __init szmem(unsigned int node)
 	if (loongson_sysconf.vgabios_addr)
 		memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr),
 				SZ_256K);
-	/* set nid for reserved memory */
-	memblock_set_node((u64)node << 44, (u64)(node+1) << 44, &memblock.reserved, node);
 }
 
 #ifndef CONFIG_NUMA
diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index 6345e096c5326..8f61e93c0c5bc 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -132,8 +132,6 @@ static void __init node_mem_init(unsigned int node)
 
 		/* Reserve pfn range 0~node[0]->node_start_pfn */
 		memblock_reserve(0, PAGE_SIZE * start_pfn);
-		/* set nid for reserved memory on node 0 */
-		memblock_set_node(0, (u64)1 << 44, &memblock.reserved, 1);
 	}
 }
 
-- 
GitLab


From 822df315cc7c85c3c10afcc6408b254a6fa0f166 Mon Sep 17 00:00:00 2001
From: Huang Pei <huangpei@loongson.cn>
Date: Sat, 27 Jan 2024 17:12:21 +0800
Subject: [PATCH 3536/4076] MIPS: loongson64: set nid for reserved memblock
 region

Commit 61167ad5fecd("mm: pass nid to reserve_bootmem_region()") reveals
that reserved memblock regions have no valid node id set, just set it
right since loongson64 firmware makes it clear in memory layout info.

This works around booting failure on 3A1000+ since commit 61167ad5fecd
("mm: pass nid to reserve_bootmem_region()") under
CONFIG_DEFERRED_STRUCT_PAGE_INIT.

Signed-off-by: Huang Pei <huangpei@loongson.cn>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/loongson64/init.c | 3 +++
 arch/mips/loongson64/numa.c | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index f25caa6aa9d30..553142c1f14fe 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -103,6 +103,9 @@ void __init szmem(unsigned int node)
 	if (loongson_sysconf.vgabios_addr)
 		memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr),
 				SZ_256K);
+	/* set nid for reserved memory */
+	memblock_set_node((u64)node << 44, (u64)(node + 1) << 44,
+			&memblock.reserved, node);
 }
 
 #ifndef CONFIG_NUMA
diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index 8f61e93c0c5bc..68dafd6d3e257 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -132,6 +132,8 @@ static void __init node_mem_init(unsigned int node)
 
 		/* Reserve pfn range 0~node[0]->node_start_pfn */
 		memblock_reserve(0, PAGE_SIZE * start_pfn);
+		/* set nid for reserved memory on node 0 */
+		memblock_set_node(0, 1ULL << 44, &memblock.reserved, 0);
 	}
 }
 
-- 
GitLab


From 59be5c35850171e307ca5d3d703ee9ff4096b948 Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Sat, 27 Jan 2024 05:05:57 +0800
Subject: [PATCH 3537/4076] mips: Call lose_fpu(0) before initializing fcr31 in
 mips_set_personality_nan

If we still own the FPU after initializing fcr31, when we are preempted
the dirty value in the FPU will be read out and stored into fcr31,
clobbering our setting.  This can cause an improper floating-point
environment after execve().  For example:

    zsh% cat measure.c
    #include <fenv.h>
    int main() { return fetestexcept(FE_INEXACT); }
    zsh% cc measure.c -o measure -lm
    zsh% echo $((1.0/3)) # raising FE_INEXACT
    0.33333333333333331
    zsh% while ./measure; do ; done
    (stopped in seconds)

Call lose_fpu(0) before setting fcr31 to prevent this.

Closes: https://lore.kernel.org/linux-mips/7a6aa1bbdbbe2e63ae96ff163fab0349f58f1b9e.camel@xry111.site/
Fixes: 9b26616c8d9d ("MIPS: Respect the ISA level in FCSR handling")
Cc: stable@vger.kernel.org
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/elf.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index 5582a4ca1e9e3..7aa2c2360ff60 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -11,6 +11,7 @@
 
 #include <asm/cpu-features.h>
 #include <asm/cpu-info.h>
+#include <asm/fpu.h>
 
 #ifdef CONFIG_MIPS_FP_SUPPORT
 
@@ -309,6 +310,11 @@ void mips_set_personality_nan(struct arch_elf_state *state)
 	struct cpuinfo_mips *c = &boot_cpu_data;
 	struct task_struct *t = current;
 
+	/* Do this early so t->thread.fpu.fcr31 won't be clobbered in case
+	 * we are preempted before the lose_fpu(0) in start_thread.
+	 */
+	lose_fpu(0);
+
 	t->thread.fpu.fcr31 = c->fpu_csr31;
 	switch (state->nan_2008) {
 	case 0:
-- 
GitLab


From 915644189c22d9c93e9fee7c7c993b58e745bef7 Mon Sep 17 00:00:00 2001
From: Konstantin Aladyshev <aladyshev22@gmail.com>
Date: Sat, 27 Jan 2024 18:48:44 +0300
Subject: [PATCH 3538/4076] hwmon: (pmbus/mp2975) Correct comment inside
 'mp2975_read_byte_data'

The current driver code no longer perfrom internal conversion from
VID to direct. Instead it configures READ_VOUT using MFR_DC_LOOP_CTRL.
Correct the comment message inside the 'mp2975_read_byte_data'
function to match the driver logic.

Signed-off-by: Konstantin Aladyshev <aladyshev22@gmail.com>
Fixes: c60fe56c169e ("hwmon: (pmbus/mp2975) Fix driver initialization for MP2975 device")
Link: https://lore.kernel.org/r/20240127154844.989-1-aladyshev22@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/mp2975.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/hwmon/pmbus/mp2975.c b/drivers/hwmon/pmbus/mp2975.c
index 5bbfdacb61a76..e5fa10b3b8bc7 100644
--- a/drivers/hwmon/pmbus/mp2975.c
+++ b/drivers/hwmon/pmbus/mp2975.c
@@ -131,10 +131,9 @@ static int mp2975_read_byte_data(struct i2c_client *client, int page, int reg)
 	switch (reg) {
 	case PMBUS_VOUT_MODE:
 		/*
-		 * Enforce VOUT direct format, since device allows to set the
-		 * different formats for the different rails. Conversion from
-		 * VID to direct provided by driver internally, in case it is
-		 * necessary.
+		 * Report direct format as configured by MFR_DC_LOOP_CTRL.
+		 * Unlike on MP2971/MP2973 the reported VOUT_MODE isn't automatically
+		 * internally updated, but always reads as PB_VOUT_MODE_VID.
 		 */
 		return PB_VOUT_MODE_DIRECT;
 	default:
-- 
GitLab


From 6c20faec8ffc97af21acb43382adda011eb39359 Mon Sep 17 00:00:00 2001
From: Zhang Bingwu <xtexchooser@duck.com>
Date: Sun, 14 Jan 2024 16:13:59 +0800
Subject: [PATCH 3539/4076] kbuild: defconf: use SRCARCH to find merged configs

For some ARCH values, SRCARCH, which should be used for finding arch/
subdirectory, is different from ARCH.

Signed-off-by: Zhang Bingwu <xtexchooser@duck.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/Makefile.defconf | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/scripts/Makefile.defconf b/scripts/Makefile.defconf
index ab271b2051a24..226ea3df3b4b4 100644
--- a/scripts/Makefile.defconf
+++ b/scripts/Makefile.defconf
@@ -9,8 +9,8 @@
 # Input config fragments without '.config' suffix
 define merge_into_defconfig
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
+		-m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \
+		$(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
 	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 endef
 
@@ -23,7 +23,7 @@ endef
 # Input config fragments without '.config' suffix
 define merge_into_defconfig_override
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-Q -m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
+		-Q -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \
+		$(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
 	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 endef
-- 
GitLab


From 846cfbeed09b45d985079a9173cf390cc053715b Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 23 Jan 2024 15:59:54 -0700
Subject: [PATCH 3540/4076] um: Fix adding '-no-pie' for clang

The kernel builds with -fno-PIE, so commit 883354afbc10 ("um: link
vmlinux with -no-pie") added the compiler linker flag '-no-pie' via
cc-option because '-no-pie' was only supported in GCC 6.1.0 and newer.

While this works for GCC, this does not work for clang because cc-option
uses '-c', which stops the pipeline right before linking, so '-no-pie'
is unconsumed and clang warns, causing cc-option to fail just as it
would if the option was entirely unsupported:

  $ clang -Werror -no-pie -c -o /dev/null -x c /dev/null
  clang-16: error: argument unused during compilation: '-no-pie' [-Werror,-Wunused-command-line-argument]

A recent version of clang exposes this because it generates a relocation
under '-mcmodel=large' that is not supported in PIE mode:

  /usr/sbin/ld: init/main.o: relocation R_X86_64_32 against symbol `saved_command_line' can not be used when making a PIE object; recompile with -fPIE
  /usr/sbin/ld: failed to set dynamic section sizes: bad value
  clang: error: linker command failed with exit code 1 (use -v to see invocation)

Remove the cc-option check altogether. It is wasteful to invoke the
compiler to check for '-no-pie' because only one supported compiler
version does not support it, GCC 5.x (as it is supported with the
minimum version of clang and GCC 6.1.0+). Use a combination of the
gcc-min-version macro and CONFIG_CC_IS_CLANG to unconditionally add
'-no-pie' with CONFIG_LD_SCRIPT_DYN=y, so that it is enabled with all
compilers that support this. Furthermore, using gcc-min-version can help
turn this back into

  LINK-$(CONFIG_LD_SCRIPT_DYN) += -no-pie

when the minimum version of GCC is bumped past 6.1.0.

Cc: stable@vger.kernel.org
Closes: https://github.com/ClangBuiltLinux/linux/issues/1982
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 arch/um/Makefile | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/um/Makefile b/arch/um/Makefile
index 82f05f2506348..34957dcb88b9c 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -115,7 +115,9 @@ archprepare:
 	$(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h
 
 LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
-LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie)
+ifdef CONFIG_LD_SCRIPT_DYN
+LINK-$(call gcc-min-version, 60100)$(CONFIG_CC_IS_CLANG) += -no-pie
+endif
 LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib
 
 CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \
-- 
GitLab


From 397586506c3da005b9333ce5947ad01e8018a3be Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 23 Jan 2024 15:59:55 -0700
Subject: [PATCH 3541/4076] modpost: Add '.ltext' and '.ltext.*' to
 TEXT_SECTIONS

After the linked LLVM change, building ARCH=um defconfig results in a
segmentation fault in modpost. Prior to commit a23e7584ecf3 ("modpost:
unify 'sym' and 'to' in default_mismatch_handler()"), there was a
warning:

  WARNING: modpost: vmlinux.o(__ex_table+0x88): Section mismatch in reference to the .ltext:(unknown)
  WARNING: modpost: The relocation at __ex_table+0x88 references
  section ".ltext" which is not in the list of
  authorized sections.  If you're adding a new section
  and/or if this reference is valid, add ".ltext" to the
  list of authorized sections to jump to on fault.
  This can be achieved by adding ".ltext" to
  OTHER_TEXT_SECTIONS in scripts/mod/modpost.c.

The linked LLVM change moves global objects to the '.ltext' (and
'.ltext.*' with '-ffunction-sections') sections with '-mcmodel=large',
which ARCH=um uses. These sections should be handled just as '.text'
and '.text.*' are, so add them to TEXT_SECTIONS.

Cc: stable@vger.kernel.org
Closes: https://github.com/ClangBuiltLinux/linux/issues/1981
Link: https://github.com/llvm/llvm-project/commit/4bf8a688956a759b7b6b8d94f42d25c13c7af130
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/mod/modpost.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 795b21154446d..acf72112acd8b 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -806,7 +806,8 @@ static void check_section(const char *modname, struct elf_info *elf,
 
 #define DATA_SECTIONS ".data", ".data.rel"
 #define TEXT_SECTIONS ".text", ".text.*", ".sched.text", \
-		".kprobes.text", ".cpuidle.text", ".noinstr.text"
+		".kprobes.text", ".cpuidle.text", ".noinstr.text", \
+		".ltext", ".ltext.*"
 #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
 		".fixup", ".entry.text", ".exception.text", \
 		".coldtext", ".softirqentry.text"
-- 
GitLab


From e30dca91e5667568a6be54886020c43f1f6f95d3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 27 Jan 2024 14:52:23 -0300
Subject: [PATCH 3542/4076] tools headers UAPI: Sync kvm headers with the
 kernel sources

To pick the changes in:

  a5d3df8ae13fada7 ("KVM: remove deprecated UAPIs")
  6d72283526090850 ("KVM x86/xen: add an override for PVCLOCK_TSC_STABLE_BIT")
  89ea60c2c7b5838b ("KVM: x86: Add support for "protected VMs" that can utilize private memory")
  8dd2eee9d526c30f ("KVM: x86/mmu: Handle page fault for private memory")
  a7800aa80ea4d535 ("KVM: Add KVM_CREATE_GUEST_MEMFD ioctl() for guest-specific backing memory")
  5a475554db1e476a ("KVM: Introduce per-page memory attributes")
  16f95f3b95caded2 ("KVM: Add KVM_EXIT_MEMORY_FAULT exit to report faults to userspace")
  bb58b90b1a8f753b ("KVM: Introduce KVM_SET_USER_MEMORY_REGION2")
  3f9cd0ca848413fd ("KVM: arm64: Allow userspace to get the writable masks for feature ID registers")

That automatically adds support for some new ioctls and remove a bunch
of deprecated ones.

This ends up making the new binary to forget about the deprecated one,
so when used in an older system it will not be able to resolve those
codes to strings.

  $ tools/perf/trace/beauty/kvm_ioctl.sh > before
  $ cp include/uapi/linux/kvm.h tools/include/uapi/linux/kvm.h
  $ tools/perf/trace/beauty/kvm_ioctl.sh > after
  $ diff -u before after
  --- before	2024-01-27 14:48:16.523014020 -0300
  +++ after	2024-01-27 14:48:24.183932866 -0300
  @@ -14,6 +14,7 @@
   	[0x46] = "SET_USER_MEMORY_REGION",
   	[0x47] = "SET_TSS_ADDR",
   	[0x48] = "SET_IDENTITY_MAP_ADDR",
  +	[0x49] = "SET_USER_MEMORY_REGION2",
   	[0x60] = "CREATE_IRQCHIP",
   	[0x61] = "IRQ_LINE",
   	[0x62] = "GET_IRQCHIP",
  @@ -22,14 +23,8 @@
   	[0x65] = "GET_PIT",
   	[0x66] = "SET_PIT",
   	[0x67] = "IRQ_LINE_STATUS",
  -	[0x69] = "ASSIGN_PCI_DEVICE",
   	[0x6a] = "SET_GSI_ROUTING",
  -	[0x70] = "ASSIGN_DEV_IRQ",
   	[0x71] = "REINJECT_CONTROL",
  -	[0x72] = "DEASSIGN_PCI_DEVICE",
  -	[0x73] = "ASSIGN_SET_MSIX_NR",
  -	[0x74] = "ASSIGN_SET_MSIX_ENTRY",
  -	[0x75] = "DEASSIGN_DEV_IRQ",
   	[0x76] = "IRQFD",
   	[0x77] = "CREATE_PIT2",
   	[0x78] = "SET_BOOT_CPU_ID",
  @@ -66,7 +61,6 @@
   	[0x9f] = "GET_VCPU_EVENTS",
   	[0xa0] = "SET_VCPU_EVENTS",
   	[0xa3] = "ENABLE_CAP",
  -	[0xa4] = "ASSIGN_SET_INTX_MASK",
   	[0xa5] = "SIGNAL_MSI",
   	[0xa6] = "GET_XCRS",
   	[0xa7] = "SET_XCRS",
  @@ -97,6 +91,8 @@
   	[0xcd] = "SET_SREGS2",
   	[0xce] = "GET_STATS_FD",
   	[0xd0] = "XEN_HVM_EVTCHN_SEND",
  +	[0xd2] = "SET_MEMORY_ATTRIBUTES",
  +	[0xd4] = "CREATE_GUEST_MEMFD",
   	[0xe0] = "CREATE_DEVICE",
   	[0xe1] = "SET_DEVICE_ATTR",
   	[0xe2] = "GET_DEVICE_ATTR",
  $

This silences these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
    diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Chao Peng <chao.p.peng@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jing Zhang <jingzhangos@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paul Durrant <pdurrant@amazon.com>
Cc: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/lkml/ZbVLbkngp4oq13qN@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h |   3 +
 tools/include/uapi/linux/kvm.h        | 140 +++++++++-----------------
 2 files changed, 53 insertions(+), 90 deletions(-)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 1a6a1f9879496..a448d0964fc06 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -562,4 +562,7 @@ struct kvm_pmu_event_filter {
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
 #define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
 
+#define KVM_X86_DEFAULT_VM	0
+#define KVM_X86_SW_PROTECTED_VM	1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 211b86de35ac5..c3308536482bd 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -16,76 +16,6 @@
 
 #define KVM_API_VERSION 12
 
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT           16
-
-#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE       12
-#define KVM_TRC_CYCLE_SIZE      8
-#define KVM_TRC_EXTRA_MAX       7
-
-#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
-	__u32 buf_size;
-	__u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
-	_IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-struct kvm_debug_guest {
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
@@ -95,6 +25,19 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
+};
+
 /*
  * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
  * userspace, other bits are reserved for kvm internal use which are defined
@@ -102,6 +45,7 @@ struct kvm_userspace_memory_region {
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
+#define KVM_MEM_GUEST_MEMFD	(1UL << 2)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -265,6 +209,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
+#define KVM_EXIT_MEMORY_FAULT     39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -518,6 +463,13 @@ struct kvm_run {
 #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
 			__u32 flags;
 		} notify;
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -945,9 +897,6 @@ struct kvm_ppc_resize_hpt {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 #define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
@@ -1201,6 +1150,11 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1291,6 +1245,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1483,6 +1438,8 @@ struct kvm_vfio_spapr_tce {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {
@@ -1507,20 +1464,8 @@ struct kvm_s390_ucas_mapping {
 			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
 #define KVM_UNREGISTER_COALESCED_MMIO \
 			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
-				       struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
-#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
-				       struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
-				       struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
-				       struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
 #define KVM_CREATE_PIT2		  _IOW(KVMIO,  0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
@@ -1537,9 +1482,6 @@ struct kvm_s390_ucas_mapping {
 *  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
-				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 /* Available with KVM_CAP_PPC_GET_SMMU_INFO */
@@ -1592,8 +1534,6 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
@@ -2267,4 +2207,24 @@ struct kvm_s390_zpci_op {
 /* flags for kvm_s390_zpci_op->u.reg_aen.flags */
 #define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
 
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES              _IOW(KVMIO,  0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+#define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+};
+
 #endif /* __LINUX_KVM_H */
-- 
GitLab


From becc24e96ad4b9bc5c5bba800dc184661b6702bc Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 4 Jan 2024 15:19:03 -0800
Subject: [PATCH 3543/4076] perf vendor events intel: Alderlake/sapphirerapids
 metric fixes

As events are deduplicated by name, ensure PMU prefixes are always
used in metrics. Previously they may be missed on the first event in a
formula.

Update metric constraints for architectures with topdown l2 events.

Conversion script updated in:
https://github.com/intel/perfmon/pull/128

Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Closes: https://lore.kernel.org/lkml/ZZam-EG-UepcXtWw@kernel.org/
Link: https://lore.kernel.org/r/20240104231903.775717-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/x86/alderlake/adl-metrics.json       | 254 ++++++++----------
 .../arch/x86/alderlaken/adln-metrics.json     |   4 -
 .../arch/x86/sapphirerapids/spr-metrics.json  |  25 +-
 3 files changed, 123 insertions(+), 160 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 35124a4ddcb2b..bbfa3883e5338 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -114,7 +114,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to certain allocation restrictions.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_alloc_restriction",
         "MetricThreshold": "tma_alloc_restriction > 0.1",
@@ -124,7 +124,7 @@
     {
         "BriefDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.1",
@@ -169,7 +169,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_detect",
         "MetricThreshold": "tma_branch_detect > 0.05",
@@ -179,7 +179,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to branch mispredicts.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.05",
@@ -189,7 +189,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteer",
         "MetricThreshold": "tma_branch_resteer > 0.05",
@@ -198,7 +198,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to the microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_cisc",
         "MetricThreshold": "tma_cisc > 0.05",
@@ -217,7 +217,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to decode stalls.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_decode",
         "MetricThreshold": "tma_decode > 0.05",
@@ -235,7 +235,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -245,7 +244,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
         "MetricThreshold": "tma_fast_nuke > 0.05",
@@ -254,7 +253,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1",
@@ -264,7 +263,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.15",
@@ -283,7 +282,7 @@
     },
     {
         "BriefDescription": "Counts the number of floating point divide operations per uop.",
-        "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.FPDIV@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_fpdiv_uops",
         "MetricThreshold": "tma_fpdiv_uops > 0.2",
@@ -293,7 +292,7 @@
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to frontend stalls.",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.2",
@@ -303,7 +302,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to instruction cache misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05",
@@ -330,7 +329,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / tma_info_core_clks",
         "MetricName": "tma_info_core_ipc",
         "Unit": "cpu_atom"
     },
@@ -342,7 +341,7 @@
     },
     {
         "BriefDescription": "Uops Per Instruction",
-        "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.ALL@ / INST_RETIRED.ANY",
         "MetricName": "tma_info_core_upi",
         "Unit": "cpu_atom"
     },
@@ -366,13 +365,13 @@
     },
     {
         "BriefDescription": "Ratio of all branches which mispredict",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_branch_mispredict_ratio",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
+        "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BACLEARS.ANY",
         "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio",
         "Unit": "cpu_atom"
     },
@@ -390,61 +389,61 @@
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_ipbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.CALL",
         "MetricName": "tma_info_inst_mix_ipcall",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Far Branch",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
         "MetricName": "tma_info_inst_mix_ipfarbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Load",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricName": "tma_info_inst_mix_ipload",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
         "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN",
         "MetricName": "tma_info_inst_mix_ipmisp_cond_taken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.INDIRECT",
         "MetricName": "tma_info_inst_mix_ipmisp_indirect",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired return Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RETURN",
         "MetricName": "tma_info_inst_mix_ipmisp_ret",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_ipmispredict",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Store",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_STORES",
         "MetricName": "tma_info_inst_mix_ipstore",
         "Unit": "cpu_atom"
     },
@@ -480,19 +479,19 @@
     },
     {
         "BriefDescription": "Cycle cost per DRAM hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycle cost per L2 hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycle cost per LLC hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit",
         "Unit": "cpu_atom"
     },
@@ -504,7 +503,7 @@
     },
     {
         "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC",
         "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_atom"
     },
@@ -524,7 +523,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05",
@@ -533,7 +532,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.",
-        "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1",
@@ -542,7 +541,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -552,7 +550,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -571,7 +568,7 @@
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.05",
@@ -581,7 +578,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
         "MetricThreshold": "tma_mem_scheduler > 0.1",
@@ -590,7 +587,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.",
-        "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
+        "MetricExpr": "min(tma_backend_bound, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
@@ -609,7 +606,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.MS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
@@ -620,7 +617,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
         "MetricThreshold": "tma_non_mem_scheduler > 0.1",
@@ -629,7 +626,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear (slow nuke).",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
         "MetricThreshold": "tma_nuke > 0.05",
@@ -638,7 +635,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to other common frontend stalls not categorized.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_other_fb",
         "MetricThreshold": "tma_other_fb > 0.05",
@@ -647,7 +644,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.",
-        "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.OTHER_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_other_l1",
         "MetricThreshold": "tma_other_l1 > 0.05",
@@ -683,7 +680,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to wrong predecodes.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_predecode",
         "MetricThreshold": "tma_predecode > 0.05",
@@ -692,7 +689,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
         "MetricThreshold": "tma_register > 0.1",
@@ -701,7 +698,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the reorder buffer being full (ROB stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
         "MetricThreshold": "tma_reorder_buffer > 0.1",
@@ -722,7 +719,7 @@
     {
         "BriefDescription": "Counts the number of issue slots  that result in retirement slots.",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.75",
@@ -741,7 +738,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
         "MetricThreshold": "tma_serialization > 0.1",
@@ -768,7 +765,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.",
-        "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_hit",
         "MetricThreshold": "tma_stlb_hit > 0.05",
@@ -777,7 +774,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.",
-        "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.PGWALK_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_miss",
         "MetricThreshold": "tma_stlb_miss > 0.05",
@@ -795,8 +792,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.ST_ADDR_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
         "MetricThreshold": "tma_store_fwd_blk > 0.05",
@@ -875,7 +871,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
-        "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
+        "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
         "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -905,7 +901,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(25 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_average_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
@@ -927,7 +922,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "24 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
@@ -948,7 +942,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
-        "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
@@ -958,7 +952,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -979,7 +972,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
         "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1019,7 +1012,7 @@
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
-        "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.FB_FULL@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
@@ -1154,7 +1147,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1164,7 +1157,6 @@
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
@@ -1173,7 +1165,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200",
@@ -1181,7 +1173,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200",
@@ -1197,7 +1189,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500",
@@ -1205,7 +1197,7 @@
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BadSpec;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmispredict",
         "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200",
@@ -1213,7 +1205,6 @@
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
         "MetricGroup": "Cor;SMT",
         "MetricName": "tma_info_botlnk_l0_core_bound_likely",
@@ -1222,7 +1213,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
@@ -1232,7 +1222,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -1242,7 +1231,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
         "MetricName": "tma_info_bottleneck_big_code",
@@ -1261,7 +1249,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
         "MetricGroup": "Fed;FetchBW;Frontend",
         "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
@@ -1270,7 +1257,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -1280,7 +1266,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_info_bottleneck_memory_data_tlbs",
@@ -1290,7 +1275,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))",
         "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_info_bottleneck_memory_latency",
@@ -1300,7 +1284,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bottleneck_mispredictions",
@@ -1317,14 +1300,14 @@
     },
     {
         "BriefDescription": "Fraction of branches that are non-taken conditionals",
-        "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_NTAKEN@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
         "MetricName": "tma_info_branches_cond_nt",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of branches that are taken conditionals",
-        "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
         "MetricName": "tma_info_branches_cond_tk",
         "Unit": "cpu_core"
@@ -1352,7 +1335,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_core_core_clks",
         "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_core_coreipc",
         "Unit": "cpu_core"
@@ -1374,14 +1357,14 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_frontend_dsb_coverage",
         "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35",
@@ -1390,28 +1373,28 @@
     },
     {
         "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FRONTEND_RETIRED.ANY_DSB_MISS",
         "MetricGroup": "DSBmiss;Fed",
         "MetricName": "tma_info_frontend_ipdsb_miss_ret",
         "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50",
@@ -1440,14 +1423,14 @@
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Fed;LSD",
         "MetricName": "tma_info_frontend_lsd_coverage",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Branch instructions per taken branch.",
-        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
         "Unit": "cpu_core"
@@ -1462,7 +1445,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
@@ -1471,7 +1454,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
@@ -1480,7 +1463,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
@@ -1489,7 +1472,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
@@ -1498,7 +1481,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
@@ -1507,7 +1490,7 @@
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Branches;Fed;InsType",
         "MetricName": "tma_info_inst_mix_ipbranch",
         "MetricThreshold": "tma_info_inst_mix_ipbranch < 8",
@@ -1515,7 +1498,7 @@
     },
     {
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_CALL",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_ipcall",
         "MetricThreshold": "tma_info_inst_mix_ipcall < 200",
@@ -1523,7 +1506,7 @@
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_ipflop",
         "MetricThreshold": "tma_info_inst_mix_ipflop < 10",
@@ -1531,7 +1514,7 @@
     },
     {
         "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_LOADS",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipload",
         "MetricThreshold": "tma_info_inst_mix_ipload < 3",
@@ -1539,7 +1522,7 @@
     },
     {
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipstore",
         "MetricThreshold": "tma_info_inst_mix_ipstore < 8",
@@ -1547,7 +1530,7 @@
     },
     {
         "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
         "MetricGroup": "Prefetches",
         "MetricName": "tma_info_inst_mix_ipswpf",
         "MetricThreshold": "tma_info_inst_mix_ipswpf < 100",
@@ -1555,7 +1538,7 @@
     },
     {
         "BriefDescription": "Instruction per taken branch",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
         "MetricThreshold": "tma_info_inst_mix_iptb < 13",
@@ -1655,14 +1638,14 @@
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / MEM_LOAD_COMPLETED.L1_MISS_ANY",
         "MetricGroup": "Mem;MemoryBound;MemoryLat",
         "MetricName": "tma_info_memory_load_miss_real_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / L1D_PEND_MISS.PENDING_CYCLES",
         "MetricGroup": "Mem;MemoryBW;MemoryBound",
         "MetricName": "tma_info_memory_mlp",
         "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
@@ -1670,28 +1653,28 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD@ / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_oro_data_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / OFFCORE_REQUESTS.DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_oro_load_l2_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_oro_load_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L3 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_oro_load_l3_miss_latency",
         "Unit": "cpu_core"
@@ -1755,14 +1738,14 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per a microcode Assist invocation",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@",
         "MetricGroup": "Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
         "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
@@ -1778,7 +1761,7 @@
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1793,7 +1776,7 @@
     },
     {
         "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC",
         "MetricGroup": "HPC;Summary",
         "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_core"
@@ -1816,7 +1799,7 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
         "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
@@ -1847,6 +1830,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
@@ -1855,6 +1839,7 @@
     },
     {
         "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL",
         "MetricGroup": "Mem;SoC",
         "MetricName": "tma_info_system_mem_request_latency",
@@ -1897,7 +1882,7 @@
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
         "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
@@ -1905,7 +1890,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_thread_clks",
         "MetricGroup": "Ret;Summary",
         "MetricName": "tma_info_thread_ipc",
         "Unit": "cpu_core"
@@ -1972,7 +1957,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1992,7 +1977,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -2003,7 +1987,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -2024,7 +2007,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
-        "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
         "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -2045,7 +2028,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_2_3_10@ / (3 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
         "MetricThreshold": "tma_load_op_utilization > 0.6",
@@ -2064,7 +2047,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
         "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
@@ -2073,7 +2056,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
@@ -2136,6 +2118,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
@@ -2145,7 +2128,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2155,7 +2137,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@UOPS_RETIRED.MS@ / tma_info_thread_slots",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
@@ -2225,7 +2207,6 @@
     },
     {
         "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_other_light_ops",
@@ -2246,7 +2227,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_0@ / tma_info_core_core_clks",
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
@@ -2256,7 +2237,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_1@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
@@ -2266,7 +2247,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_6@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
@@ -2296,7 +2277,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
         "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2306,7 +2287,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
         "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2316,7 +2298,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
         "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2338,7 +2321,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations",
-        "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group",
         "MetricName": "tma_serializing_operation",
         "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))",
@@ -2348,7 +2331,7 @@
     },
     {
         "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.",
-        "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
+        "MetricExpr": "cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group",
         "MetricName": "tma_shuffles",
         "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
@@ -2357,7 +2340,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
-        "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
         "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))",
@@ -2377,8 +2361,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
         "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2398,7 +2381,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write",
-        "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
         "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -2408,7 +2391,6 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
@@ -2448,7 +2430,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
         "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
@@ -2467,7 +2449,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
         "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index c150c14ac6ed9..a35edf7d86a97 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -195,7 +195,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -457,7 +456,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -466,7 +464,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -683,7 +680,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index e31a4aac9f205..56e54babcc26f 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -400,7 +400,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(76 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 75.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
@@ -421,7 +420,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "75.5 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
@@ -449,7 +447,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -656,7 +653,6 @@
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
@@ -699,7 +695,6 @@
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
         "MetricGroup": "Cor;SMT",
         "MetricName": "tma_info_botlnk_l0_core_bound_likely",
@@ -707,7 +702,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
@@ -716,7 +710,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -725,7 +718,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
         "MetricName": "tma_info_bottleneck_big_code",
@@ -742,7 +734,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
         "MetricGroup": "Fed;FetchBW;Frontend",
         "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
@@ -750,7 +741,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -759,7 +749,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_info_bottleneck_memory_data_tlbs",
@@ -768,7 +757,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))",
         "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_info_bottleneck_memory_latency",
@@ -777,7 +765,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bottleneck_mispredictions",
@@ -1301,6 +1288,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
@@ -1455,7 +1443,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -1465,7 +1452,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1538,7 +1524,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
@@ -1596,6 +1581,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
@@ -1604,7 +1590,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1676,7 +1661,6 @@
     },
     {
         "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_other_light_ops",
@@ -1758,6 +1742,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
@@ -1767,6 +1752,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
@@ -1822,6 +1808,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
@@ -1840,7 +1827,6 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1868,7 +1854,6 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-- 
GitLab


From 20d03ae36ec010aa97a97495d9dd9202cb93cb87 Mon Sep 17 00:00:00 2001
From: Udipto Goswami <quic_ugoswami@quicinc.com>
Date: Mon, 8 Jan 2024 18:57:20 +0530
Subject: [PATCH 3544/4076] usb: gadget: ncm: Fix indentations in documentation
 of NCM section

Currently, the section of NCM which describes attributes are having wrong
indentation.

Fix this by following the correct format recommended.

Fixes: 1900daeefd3e ("usb: gadget: ncm: Add support to update wMaxSegmentSize via configfs")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/all/20240108160221.743649b5@canb.auug.org.au/
Signed-off-by: Udipto Goswami <quic_ugoswami@quicinc.com>
Link: https://lore.kernel.org/r/20240108132720.7786-1-quic_ugoswami@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/usb/gadget-testing.rst | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/Documentation/usb/gadget-testing.rst b/Documentation/usb/gadget-testing.rst
index 8cd62c466d20a..077dfac7ed98f 100644
--- a/Documentation/usb/gadget-testing.rst
+++ b/Documentation/usb/gadget-testing.rst
@@ -448,17 +448,17 @@ Function-specific configfs interface
 The function name to use when creating the function directory is "ncm".
 The NCM function provides these attributes in its function directory:
 
-	===============   ==================================================
-	ifname		  network device interface name associated with this
-			  function instance
-	qmult		  queue length multiplier for high and super speed
-	host_addr	  MAC address of host's end of this
-			  Ethernet over USB link
-	dev_addr	  MAC address of device's end of this
-			  Ethernet over USB link
-	max_segment_size  Segment size required for P2P connections. This
-			  will set MTU to (max_segment_size - 14 bytes)
-	===============   ==================================================
+	======================= ==================================================
+	ifname			network device interface name associated with this
+				function instance
+	qmult			queue length multiplier for high and super speed
+	host_addr		MAC address of host's end of this
+				Ethernet over USB link
+	dev_addr		MAC address of device's end of this
+				Ethernet over USB link
+	max_segment_size	Segment size required for P2P connections. This
+				will set MTU to 14 bytes
+	======================= ==================================================
 
 and after creating the functions/ncm.<instance name> they contain default
 values: qmult is 5, dev_addr and host_addr are randomly selected.
-- 
GitLab


From 817349b6d26aadd8b38283a05ce0bab106b4c765 Mon Sep 17 00:00:00 2001
From: Prashanth K <quic_prashk@quicinc.com>
Date: Tue, 16 Jan 2024 11:28:15 +0530
Subject: [PATCH 3545/4076] usb: dwc3: host: Set XHCI_SG_TRB_CACHE_SIZE_QUIRK

Upstream commit bac1ec551434 ("usb: xhci: Set quirk for
XHCI_SG_TRB_CACHE_SIZE_QUIRK") introduced a new quirk in XHCI
which fixes XHC timeout, which was seen on synopsys XHCs while
using SG buffers. But the support for this quirk isn't present
in the DWC3 layer.

We will encounter this XHCI timeout/hung issue if we run iperf
loopback tests using RTL8156 ethernet adaptor on DWC3 targets
with scatter-gather enabled. This gets resolved after enabling
the XHCI_SG_TRB_CACHE_SIZE_QUIRK. This patch enables it using
the xhci device property since its needed for DWC3 controller.

In Synopsys DWC3 databook,
Table 9-3: xHCI Debug Capability Limitations
Chained TRBs greater than TRB cache size: The debug capability
driver must not create a multi-TRB TD that describes smaller
than a 1K packet that spreads across 8 or more TRBs on either
the IN TR or the OUT TR.

Cc: stable@vger.kernel.org #5.11
Signed-off-by: Prashanth K <quic_prashk@quicinc.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/20240116055816.1169821-2-quic_prashk@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/host.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index 61f57fe5bb783..43230915323c7 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -61,7 +61,7 @@ out:
 
 int dwc3_host_init(struct dwc3 *dwc)
 {
-	struct property_entry	props[4];
+	struct property_entry	props[5];
 	struct platform_device	*xhci;
 	int			ret, irq;
 	int			prop_idx = 0;
@@ -89,6 +89,8 @@ int dwc3_host_init(struct dwc3 *dwc)
 
 	memset(props, 0, sizeof(struct property_entry) * ARRAY_SIZE(props));
 
+	props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-sg-trb-cache-size-quirk");
+
 	if (dwc->usb3_lpm_capable)
 		props[prop_idx++] = PROPERTY_ENTRY_BOOL("usb3-lpm-capable");
 
-- 
GitLab


From 520b391e3e813c1dd142d1eebb3ccfa6d08c3995 Mon Sep 17 00:00:00 2001
From: Prashanth K <quic_prashk@quicinc.com>
Date: Tue, 16 Jan 2024 11:28:16 +0530
Subject: [PATCH 3546/4076] usb: host: xhci-plat: Add support for
 XHCI_SG_TRB_CACHE_SIZE_QUIRK

Upstream commit bac1ec551434 ("usb: xhci: Set quirk for
XHCI_SG_TRB_CACHE_SIZE_QUIRK") introduced a new quirk in XHCI
which fixes XHC timeout, which was seen on synopsys XHCs while
using SG buffers. Currently this quirk can only be set using
xhci private data. But there are some drivers like dwc3/host.c
which adds adds quirks using software node for xhci device.
Hence set this xhci quirk by iterating over device properties.

Cc: stable@vger.kernel.org # 5.11
Fixes: bac1ec551434 ("usb: xhci: Set quirk for XHCI_SG_TRB_CACHE_SIZE_QUIRK")
Signed-off-by: Prashanth K <quic_prashk@quicinc.com>
Link: https://lore.kernel.org/r/20240116055816.1169821-3-quic_prashk@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-plat.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index f04fde19f5514..3d071b8753088 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -253,6 +253,9 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 		if (device_property_read_bool(tmpdev, "quirk-broken-port-ped"))
 			xhci->quirks |= XHCI_BROKEN_PORT_PED;
 
+		if (device_property_read_bool(tmpdev, "xhci-sg-trb-cache-size-quirk"))
+			xhci->quirks |= XHCI_SG_TRB_CACHE_SIZE_QUIRK;
+
 		device_property_read_u32(tmpdev, "imod-interval-ns",
 					 &xhci->imod_interval);
 	}
-- 
GitLab


From 9dc292413c56a2d01e34787d3fc4a76635e4a498 Mon Sep 17 00:00:00 2001
From: Krishna Kurapati <quic_kriskura@quicinc.com>
Date: Thu, 18 Jan 2024 21:18:53 +0530
Subject: [PATCH 3547/4076] usb: gadget: ncm: Fix endianness of wMaxSegmentSize
 variable in ecm_desc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Recent commit [1] added support for changing max segment size of the NCM
interface via configfs. But the value of segment size value stored in
ncm_opts need to be converted to little endian before saving it in
ecm_desc. Also while initialising the value of segment size in opts during
instance allocation, the value ETH_FRAME_LEN needs to be assigned directly
without any conversion as ETH_FRAME_LEN and the variable max_segment_size
are native endian. The current implementaion modifies it into little endian
thus breaking things for big endian targets.

Fix endianness while assigning these variables.
While at it, fix up some stray spaces in comments added in code.

[1]: https://lore.kernel.org/all/20231221153216.18657-1-quic_kriskura@quicinc.com/

Fixes: 1900daeefd3e ("usb: gadget: ncm: Add support to update wMaxSegmentSize via configfs")
Signed-off-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Link: https://lore.kernel.org/r/20240118154910.8765-1-quic_kriskura@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index a1575a0ca568d..ca5d5f5649982 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -105,8 +105,8 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f)
 
 /*
  * Although max mtu as dictated by u_ether is 15412 bytes, setting
- * max_segment_sizeto 15426 would not be efficient. If user chooses segment
- * size to be (>= 8192), then we can't aggregate more than one  buffer in each
+ * max_segment_size to 15426 would not be efficient. If user chooses segment
+ * size to be (>= 8192), then we can't aggregate more than one buffer in each
  * NTB (assuming each packet coming from network layer is >= 8192 bytes) as ep
  * maxpacket limit is 16384. So let max_segment_size be limited to 8000 to allow
  * at least 2 packets to be aggregated reducing wastage of NTB buffer space
@@ -1489,7 +1489,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	ncm_data_intf.bInterfaceNumber = status;
 	ncm_union_desc.bSlaveInterface0 = status;
 
-	ecm_desc.wMaxSegmentSize = ncm_opts->max_segment_size;
+	ecm_desc.wMaxSegmentSize = cpu_to_le16(ncm_opts->max_segment_size);
 
 	status = -ENODEV;
 
@@ -1685,7 +1685,7 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 		kfree(opts);
 		return ERR_CAST(net);
 	}
-	opts->max_segment_size = cpu_to_le16(ETH_FRAME_LEN);
+	opts->max_segment_size = ETH_FRAME_LEN;
 	INIT_LIST_HEAD(&opts->ncm_os_desc.ext_prop);
 
 	descs[0] = &opts->ncm_os_desc;
-- 
GitLab


From a54a594d72f25b08f39d743880a76721fba9ae77 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Thu, 25 Jan 2024 17:27:34 +0200
Subject: [PATCH 3548/4076] xhci: fix possible null pointer dereference at
 secondary interrupter removal

Don't try to remove a secondary interrupter that is known to be invalid.
Also check if the interrupter is valid inside the spinlock that protects
the array of interrupters.

Found by smatch static checker

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-usb/ffaa0a1b-5984-4a1f-bfd3-9184630a97b9@moroto.mountain/
Fixes: c99b38c41234 ("xhci: add support to allocate several interrupters")
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20240125152737.2983959-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mem.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 4460fa7e9fab9..d00d4d9372366 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1861,14 +1861,14 @@ void xhci_remove_secondary_interrupter(struct usb_hcd *hcd, struct xhci_interrup
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 	unsigned int intr_num;
 
+	spin_lock_irq(&xhci->lock);
+
 	/* interrupter 0 is primary interrupter, don't touch it */
-	if (!ir || !ir->intr_num || ir->intr_num >= xhci->max_interrupters)
+	if (!ir || !ir->intr_num || ir->intr_num >= xhci->max_interrupters) {
 		xhci_dbg(xhci, "Invalid secondary interrupter, can't remove\n");
-
-	/* fixme, should we check xhci->interrupter[intr_num] == ir */
-	/* fixme locking */
-
-	spin_lock_irq(&xhci->lock);
+		spin_unlock_irq(&xhci->lock);
+		return;
+	}
 
 	intr_num = ir->intr_num;
 
-- 
GitLab


From 09f197225cbc35db8ac135659cdd21bc1e29bda0 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Thu, 25 Jan 2024 17:27:35 +0200
Subject: [PATCH 3549/4076] xhci: fix off by one check when adding a secondary
 interrupter.

The sanity check of interrupter index when adding a new interrupter is
off by one. intr_num needs to be smaller than xhci->max_interrupter to
fit the array of interrupters.

Luckily this doesn't cause any real word harm as xhci_add_interrupter()
is always called with a intr_num value smaller than xhci->max_interrupters
in any current kernel.

Should not be needed for stable as 6.7 kernel and older only supports
one interrupter, with intr_num always being zero.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-usb/e9771296-586d-456a-ac24-a82de79bb2e6@moroto.mountain/
Fixes: 4bf398e15aa4 ("xhci: split allocate interrupter into separate alloacte and add parts")
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20240125152737.2983959-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index d00d4d9372366..a7716202a8dd5 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -2322,7 +2322,7 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir,
 	u64 erst_base;
 	u32 erst_size;
 
-	if (intr_num > xhci->max_interrupters) {
+	if (intr_num >= xhci->max_interrupters) {
 		xhci_warn(xhci, "Can't add interrupter %d, max interrupters %d\n",
 			  intr_num, xhci->max_interrupters);
 		return -EINVAL;
-- 
GitLab


From 5372c65e1311a16351ef03dd096ff576e6477674 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Thu, 25 Jan 2024 17:27:36 +0200
Subject: [PATCH 3550/4076] xhci: process isoc TD properly when there was a
 transaction error mid TD.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The last TRB of a isoc TD might not trigger an event if there was
an error event for a TRB mid TD. This is seen on a NEC Corporation
uPD720200 USB 3.0 Host

After an error mid a multi-TRB TD the xHC should according to xhci 4.9.1
generate events for passed TRBs with IOC flag set if it proceeds to the
next TD. This event is either a copy of the original error, or a
"success" transfer event.

If that event is missing then the driver and xHC host get out of sync as
the driver is still expecting a transfer event for that first TD, while
xHC host is already sending events for the next TD in the list.
This leads to
"Transfer event TRB DMA ptr not part of current TD" messages.

As a solution we tag the isoc TDs that get error events mid TD.
If an event doesn't match the first TD, then check if the tag is
set, and event points to the next TD.
In that case give back the fist TD and process the next TD normally

Make sure TD status and transferred length stay valid in both cases
with and without final TD completion event.

Reported-by: Michał Pecio <michal.pecio@gmail.com>
Closes: https://lore.kernel.org/linux-usb/20240112235205.1259f60c@foxbook/
Tested-by: Michał Pecio <michal.pecio@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20240125152737.2983959-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-ring.c | 74 +++++++++++++++++++++++++++++-------
 drivers/usb/host/xhci.h      |  1 +
 2 files changed, 61 insertions(+), 14 deletions(-)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 33806ae966f90..41be7d31a36ea 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -2376,6 +2376,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 	/* handle completion code */
 	switch (trb_comp_code) {
 	case COMP_SUCCESS:
+		/* Don't overwrite status if TD had an error, see xHCI 4.9.1 */
+		if (td->error_mid_td)
+			break;
 		if (remaining) {
 			frame->status = short_framestatus;
 			if (xhci->quirks & XHCI_TRUST_TX_LENGTH)
@@ -2401,8 +2404,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 		break;
 	case COMP_USB_TRANSACTION_ERROR:
 		frame->status = -EPROTO;
+		sum_trbs_for_length = true;
 		if (ep_trb != td->last_trb)
-			return 0;
+			td->error_mid_td = true;
 		break;
 	case COMP_STOPPED:
 		sum_trbs_for_length = true;
@@ -2422,6 +2426,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 		break;
 	}
 
+	if (td->urb_length_set)
+		goto finish_td;
+
 	if (sum_trbs_for_length)
 		frame->actual_length = sum_trb_lengths(xhci, ep->ring, ep_trb) +
 			ep_trb_len - remaining;
@@ -2430,6 +2437,14 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 
 	td->urb->actual_length += frame->actual_length;
 
+finish_td:
+	/* Don't give back TD yet if we encountered an error mid TD */
+	if (td->error_mid_td && ep_trb != td->last_trb) {
+		xhci_dbg(xhci, "Error mid isoc TD, wait for final completion event\n");
+		td->urb_length_set = true;
+		return 0;
+	}
+
 	return finish_td(xhci, ep, ep_ring, td, trb_comp_code);
 }
 
@@ -2808,17 +2823,51 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		}
 
 		if (!ep_seg) {
-			if (!ep->skip ||
-			    !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
-				/* Some host controllers give a spurious
-				 * successful event after a short transfer.
-				 * Ignore it.
-				 */
-				if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
-						ep_ring->last_td_was_short) {
-					ep_ring->last_td_was_short = false;
-					goto cleanup;
+
+			if (ep->skip && usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
+				skip_isoc_td(xhci, td, ep, status);
+				goto cleanup;
+			}
+
+			/*
+			 * Some hosts give a spurious success event after a short
+			 * transfer. Ignore it.
+			 */
+			if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
+			    ep_ring->last_td_was_short) {
+				ep_ring->last_td_was_short = false;
+				goto cleanup;
+			}
+
+			/*
+			 * xhci 4.10.2 states isoc endpoints should continue
+			 * processing the next TD if there was an error mid TD.
+			 * So host like NEC don't generate an event for the last
+			 * isoc TRB even if the IOC flag is set.
+			 * xhci 4.9.1 states that if there are errors in mult-TRB
+			 * TDs xHC should generate an error for that TRB, and if xHC
+			 * proceeds to the next TD it should genete an event for
+			 * any TRB with IOC flag on the way. Other host follow this.
+			 * So this event might be for the next TD.
+			 */
+			if (td->error_mid_td &&
+			    !list_is_last(&td->td_list, &ep_ring->td_list)) {
+				struct xhci_td *td_next = list_next_entry(td, td_list);
+
+				ep_seg = trb_in_td(xhci, td_next->start_seg, td_next->first_trb,
+						   td_next->last_trb, ep_trb_dma, false);
+				if (ep_seg) {
+					/* give back previous TD, start handling new */
+					xhci_dbg(xhci, "Missing TD completion event after mid TD error\n");
+					ep_ring->dequeue = td->last_trb;
+					ep_ring->deq_seg = td->last_trb_seg;
+					inc_deq(xhci, ep_ring);
+					xhci_td_cleanup(xhci, td, ep_ring, td->status);
+					td = td_next;
 				}
+			}
+
+			if (!ep_seg) {
 				/* HC is busted, give up! */
 				xhci_err(xhci,
 					"ERROR Transfer event TRB DMA ptr not "
@@ -2830,9 +2879,6 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 					  ep_trb_dma, true);
 				return -ESHUTDOWN;
 			}
-
-			skip_isoc_td(xhci, td, ep, status);
-			goto cleanup;
 		}
 		if (trb_comp_code == COMP_SHORT_PACKET)
 			ep_ring->last_td_was_short = true;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index a5c72a634e6a9..6f82d404883f9 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1549,6 +1549,7 @@ struct xhci_td {
 	struct xhci_segment	*bounce_seg;
 	/* actual_length of the URB has already been set */
 	bool			urb_length_set;
+	bool			error_mid_td;
 	unsigned int		num_trbs;
 };
 
-- 
GitLab


From 7c4650ded49e5b88929ecbbb631efb8b0838e811 Mon Sep 17 00:00:00 2001
From: Michal Pecio <michal.pecio@gmail.com>
Date: Thu, 25 Jan 2024 17:27:37 +0200
Subject: [PATCH 3551/4076] xhci: handle isoc Babble and Buffer Overrun events
 properly

xHCI 4.9 explicitly forbids assuming that the xHC has released its
ownership of a multi-TRB TD when it reports an error on one of the
early TRBs. Yet the driver makes such assumption and releases the TD,
allowing the remaining TRBs to be freed or overwritten by new TDs.

The xHC should also report completion of the final TRB due to its IOC
flag being set by us, regardless of prior errors. This event cannot
be recognized if the TD has already been freed earlier, resulting in
"Transfer event TRB DMA ptr not part of current TD" error message.

Fix this by reusing the logic for processing isoc Transaction Errors.
This also handles hosts which fail to report the final completion.

Fix transfer length reporting on Babble errors. They may be caused by
device malfunction, no guarantee that the buffer has been filled.

Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20240125152737.2983959-5-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-ring.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 41be7d31a36ea..f0d8a607ff214 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -2394,9 +2394,13 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 	case COMP_BANDWIDTH_OVERRUN_ERROR:
 		frame->status = -ECOMM;
 		break;
-	case COMP_ISOCH_BUFFER_OVERRUN:
 	case COMP_BABBLE_DETECTED_ERROR:
+		sum_trbs_for_length = true;
+		fallthrough;
+	case COMP_ISOCH_BUFFER_OVERRUN:
 		frame->status = -EOVERFLOW;
+		if (ep_trb != td->last_trb)
+			td->error_mid_td = true;
 		break;
 	case COMP_INCOMPATIBLE_DEVICE_ERROR:
 	case COMP_STALL_ERROR:
-- 
GitLab


From 12783c0b9e2c7915a50d5ec829630ff2da50472c Mon Sep 17 00:00:00 2001
From: Udipto Goswami <quic_ugoswami@quicinc.com>
Date: Wed, 10 Jan 2024 15:28:14 +0530
Subject: [PATCH 3552/4076] usb: core: Prevent null pointer dereference in
 update_port_device_state

Currently, the function update_port_device_state gets the usb_hub from
udev->parent by calling usb_hub_to_struct_hub.
However, in case the actconfig or the maxchild is 0, the usb_hub would
be NULL and upon further accessing to get port_dev would result in null
pointer dereference.

Fix this by introducing an if check after the usb_hub is populated.

Fixes: 83cb2604f641 ("usb: core: add sysfs entry for usb device state")
Cc: stable@vger.kernel.org
Signed-off-by: Udipto Goswami <quic_ugoswami@quicinc.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20240110095814.7626-1-quic_ugoswami@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index ffd7c99e24a36..48409d51ea438 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2053,9 +2053,19 @@ static void update_port_device_state(struct usb_device *udev)
 
 	if (udev->parent) {
 		hub = usb_hub_to_struct_hub(udev->parent);
-		port_dev = hub->ports[udev->portnum - 1];
-		WRITE_ONCE(port_dev->state, udev->state);
-		sysfs_notify_dirent(port_dev->state_kn);
+
+		/*
+		 * The Link Layer Validation System Driver (lvstest)
+		 * has a test step to unbind the hub before running the
+		 * rest of the procedure. This triggers hub_disconnect
+		 * which will set the hub's maxchild to 0, further
+		 * resulting in usb_hub_to_struct_hub returning NULL.
+		 */
+		if (hub) {
+			port_dev = hub->ports[udev->portnum - 1];
+			WRITE_ONCE(port_dev->state, udev->state);
+			sysfs_notify_dirent(port_dev->state_kn);
+		}
 	}
 }
 
-- 
GitLab


From de4b5b28c87ccae4da268a53c5df135437f5cfde Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Mon, 15 Jan 2024 11:28:20 +0200
Subject: [PATCH 3553/4076] usb: dwc3: pci: add support for the Intel Arrow
 Lake-H

This patch adds the necessary PCI ID for Intel Arrow Lake-H
devices.

Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240115092820.1454492-1-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-pci.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 6604845c397cd..39564e17f3b07 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -51,6 +51,8 @@
 #define PCI_DEVICE_ID_INTEL_MTLP		0x7ec1
 #define PCI_DEVICE_ID_INTEL_MTLS		0x7f6f
 #define PCI_DEVICE_ID_INTEL_MTL			0x7e7e
+#define PCI_DEVICE_ID_INTEL_ARLH		0x7ec1
+#define PCI_DEVICE_ID_INTEL_ARLH_PCH		0x777e
 #define PCI_DEVICE_ID_INTEL_TGL			0x9a15
 #define PCI_DEVICE_ID_AMD_MR			0x163a
 
@@ -421,6 +423,8 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, MTLP, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, MTL, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, MTLS, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, ARLH, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, ARLH_PCH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, TGL, &dwc3_pci_intel_swnode) },
 
 	{ PCI_DEVICE_DATA(AMD, NL_USB, &dwc3_pci_amd_swnode) },
-- 
GitLab


From 61a348857e869432e6a920ad8ea9132e8d44c316 Mon Sep 17 00:00:00 2001
From: Uttkarsh Aggarwal <quic_uaggarwa@quicinc.com>
Date: Fri, 19 Jan 2024 15:18:25 +0530
Subject: [PATCH 3554/4076] usb: dwc3: gadget: Fix NULL pointer dereference in
 dwc3_gadget_suspend

In current scenario if Plug-out and Plug-In performed continuously
there could be a chance while checking for dwc->gadget_driver in
dwc3_gadget_suspend, a NULL pointer dereference may occur.

Call Stack:

	CPU1:                           CPU2:
	gadget_unbind_driver            dwc3_suspend_common
	dwc3_gadget_stop                dwc3_gadget_suspend
                                        dwc3_disconnect_gadget

CPU1 basically clears the variable and CPU2 checks the variable.
Consider CPU1 is running and right before gadget_driver is cleared
and in parallel CPU2 executes dwc3_gadget_suspend where it finds
dwc->gadget_driver which is not NULL and resumes execution and then
CPU1 completes execution. CPU2 executes dwc3_disconnect_gadget where
it checks dwc->gadget_driver is already NULL because of which the
NULL pointer deference occur.

Cc: stable@vger.kernel.org
Fixes: 9772b47a4c29 ("usb: dwc3: gadget: Fix suspend/resume during device mode")
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Signed-off-by: Uttkarsh Aggarwal <quic_uaggarwa@quicinc.com>
Link: https://lore.kernel.org/r/20240119094825.26530-1-quic_uaggarwa@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 019368f8e9c4c..564976b3e2b91 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -4709,15 +4709,13 @@ int dwc3_gadget_suspend(struct dwc3 *dwc)
 	unsigned long flags;
 	int ret;
 
-	if (!dwc->gadget_driver)
-		return 0;
-
 	ret = dwc3_gadget_soft_disconnect(dwc);
 	if (ret)
 		goto err;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	dwc3_disconnect_gadget(dwc);
+	if (dwc->gadget_driver)
+		dwc3_disconnect_gadget(dwc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
-- 
GitLab


From cc509b6a47e7c8998d9e41c273191299d5d9d631 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Fri, 19 Jan 2024 20:35:37 +0800
Subject: [PATCH 3555/4076] usb: chipidea: core: handle power lost in workqueue

When power is recycled in usb controller during system power management,
the controller will recognize it and switch role if role has been changed
during power lost. In current design, it will be completed in resume()
function. However, this may bring issues since usb class devices have
their pm operations too and these device's resume() functions are still
not being called at this point. When usb controller recognized host role
should be stopped, these usb class devices will be removed at this point.
But these usb class devices can't be removed in some cases, such as scsi
devices. Since scsi driver may sync data to U-disk, however it will block
there because scsi drvier can only handle pm request when is in suspended
state. Therefore, there may exist a dependency between ci_resume() and usb
class device's resume(). To break this potential dependency, we need to
handle power lost work in a workqueue.

Fixes: 74494b33211d ("usb: chipidea: core: add controller resume support when controller is powered off")
cc: stable@vger.kernel.org
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20240119123537.3614838-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/ci.h   |  2 ++
 drivers/usb/chipidea/core.c | 44 ++++++++++++++++++++-----------------
 2 files changed, 26 insertions(+), 20 deletions(-)

diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index d9bb3d3f026e6..2a38e1eb65466 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -176,6 +176,7 @@ struct hw_bank {
  * @enabled_otg_timer_bits: bits of enabled otg timers
  * @next_otg_timer: next nearest enabled timer to be expired
  * @work: work for role changing
+ * @power_lost_work: work for power lost handling
  * @wq: workqueue thread
  * @qh_pool: allocation pool for queue heads
  * @td_pool: allocation pool for transfer descriptors
@@ -226,6 +227,7 @@ struct ci_hdrc {
 	enum otg_fsm_timer		next_otg_timer;
 	struct usb_role_switch		*role_switch;
 	struct work_struct		work;
+	struct work_struct		power_lost_work;
 	struct workqueue_struct		*wq;
 
 	struct dma_pool			*qh_pool;
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 41014f93cfdf3..835bf2428dc6e 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -856,6 +856,27 @@ static int ci_extcon_register(struct ci_hdrc *ci)
 	return 0;
 }
 
+static void ci_power_lost_work(struct work_struct *work)
+{
+	struct ci_hdrc *ci = container_of(work, struct ci_hdrc, power_lost_work);
+	enum ci_role role;
+
+	disable_irq_nosync(ci->irq);
+	pm_runtime_get_sync(ci->dev);
+	if (!ci_otg_is_fsm_mode(ci)) {
+		role = ci_get_role(ci);
+
+		if (ci->role != role) {
+			ci_handle_id_switch(ci);
+		} else if (role == CI_ROLE_GADGET) {
+			if (ci->is_otg && hw_read_otgsc(ci, OTGSC_BSV))
+				usb_gadget_vbus_connect(&ci->gadget);
+		}
+	}
+	pm_runtime_put_sync(ci->dev);
+	enable_irq(ci->irq);
+}
+
 static DEFINE_IDA(ci_ida);
 
 struct platform_device *ci_hdrc_add_device(struct device *dev,
@@ -1045,6 +1066,8 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 
 	spin_lock_init(&ci->lock);
 	mutex_init(&ci->mutex);
+	INIT_WORK(&ci->power_lost_work, ci_power_lost_work);
+
 	ci->dev = dev;
 	ci->platdata = dev_get_platdata(dev);
 	ci->imx28_write_fix = !!(ci->platdata->flags &
@@ -1396,25 +1419,6 @@ static int ci_suspend(struct device *dev)
 	return 0;
 }
 
-static void ci_handle_power_lost(struct ci_hdrc *ci)
-{
-	enum ci_role role;
-
-	disable_irq_nosync(ci->irq);
-	if (!ci_otg_is_fsm_mode(ci)) {
-		role = ci_get_role(ci);
-
-		if (ci->role != role) {
-			ci_handle_id_switch(ci);
-		} else if (role == CI_ROLE_GADGET) {
-			if (ci->is_otg && hw_read_otgsc(ci, OTGSC_BSV))
-				usb_gadget_vbus_connect(&ci->gadget);
-		}
-	}
-
-	enable_irq(ci->irq);
-}
-
 static int ci_resume(struct device *dev)
 {
 	struct ci_hdrc *ci = dev_get_drvdata(dev);
@@ -1446,7 +1450,7 @@ static int ci_resume(struct device *dev)
 		ci_role(ci)->resume(ci, power_lost);
 
 	if (power_lost)
-		ci_handle_power_lost(ci);
+		queue_work(system_freezable_wq, &ci->power_lost_work);
 
 	if (ci->supports_runtime_pm) {
 		pm_runtime_disable(dev);
-- 
GitLab


From f17c34ffc792bbb520e4b61baa16b6cfc7d44b13 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Mon, 22 Jan 2024 16:35:32 +0100
Subject: [PATCH 3556/4076] USB: hub: check for alternate port before enabling
 A_ALT_HNP_SUPPORT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The OTG 1.3 spec has the feature A_ALT_HNP_SUPPORT, which tells
a device that it is connected to the wrong port. Some devices
refuse to operate if you enable that feature, because it indicates
to them that they ought to request to be connected to another port.

According to the spec this feature may be used based only the following
three conditions:

6.5.3 a_alt_hnp_support
Setting this feature indicates to the B-device that it is connected to
an A-device port that is not capable of HNP, but that the A-device does
have an alternate port that is capable of HNP.
The A-device is required to set this feature under the following conditions:
• the A-device has multiple receptacles
• the A-device port that connects to the B-device does not support HNP
• the A-device has another port that does support HNP

A check for the third and first condition is missing. Add it.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Cc: stable <stable@kernel.org>
Fixes: 7d2d641c44269 ("usb: otg: don't set a_alt_hnp_support feature for OTG 2.0 device")
Link: https://lore.kernel.org/r/20240122153545.12284-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 48409d51ea438..e38a4124f6102 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2398,17 +2398,25 @@ static int usb_enumerate_device_otg(struct usb_device *udev)
 			}
 		} else if (desc->bLength == sizeof
 				(struct usb_otg_descriptor)) {
-			/* Set a_alt_hnp_support for legacy otg device */
-			err = usb_control_msg(udev,
-				usb_sndctrlpipe(udev, 0),
-				USB_REQ_SET_FEATURE, 0,
-				USB_DEVICE_A_ALT_HNP_SUPPORT,
-				0, NULL, 0,
-				USB_CTRL_SET_TIMEOUT);
-			if (err < 0)
-				dev_err(&udev->dev,
-					"set a_alt_hnp_support failed: %d\n",
-					err);
+			/*
+			 * We are operating on a legacy OTP device
+			 * These should be told that they are operating
+			 * on the wrong port if we have another port that does
+			 * support HNP
+			 */
+			if (bus->otg_port != 0) {
+				/* Set a_alt_hnp_support for legacy otg device */
+				err = usb_control_msg(udev,
+					usb_sndctrlpipe(udev, 0),
+					USB_REQ_SET_FEATURE, 0,
+					USB_DEVICE_A_ALT_HNP_SUPPORT,
+					0, NULL, 0,
+					USB_CTRL_SET_TIMEOUT);
+				if (err < 0)
+					dev_err(&udev->dev,
+						"set a_alt_hnp_support failed: %d\n",
+						err);
+			}
 		}
 	}
 #endif
-- 
GitLab


From b2d2d7ea0dd09802cf5a0545bf54d8ad8987d20c Mon Sep 17 00:00:00 2001
From: yuan linyu <yuanlinyu@hihonor.com>
Date: Tue, 23 Jan 2024 11:48:29 +0800
Subject: [PATCH 3557/4076] usb: f_mass_storage: forbid async queue when
 shutdown happen

When write UDC to empty and unbind gadget driver from gadget device, it is
possible that there are many queue failures for mass storage function.

The root cause is mass storage main thread alaways try to queue request to
receive a command from host if running flag is on, on platform like dwc3,
if pull down called, it will not queue request again and return
-ESHUTDOWN, but it not affect running flag of mass storage function.

Check return code from mass storage function and clear running flag if it
is -ESHUTDOWN, also indicate start in/out transfer failure to break loops.

Cc: stable <stable@kernel.org>
Signed-off-by: yuan linyu <yuanlinyu@hihonor.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20240123034829.3848409-1-yuanlinyu@hihonor.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_mass_storage.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 722a3ab2b3379..c265a1f62fc14 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -545,21 +545,37 @@ static int start_transfer(struct fsg_dev *fsg, struct usb_ep *ep,
 
 static bool start_in_transfer(struct fsg_common *common, struct fsg_buffhd *bh)
 {
+	int rc;
+
 	if (!fsg_is_set(common))
 		return false;
 	bh->state = BUF_STATE_SENDING;
-	if (start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq))
+	rc = start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq);
+	if (rc) {
 		bh->state = BUF_STATE_EMPTY;
+		if (rc == -ESHUTDOWN) {
+			common->running = 0;
+			return false;
+		}
+	}
 	return true;
 }
 
 static bool start_out_transfer(struct fsg_common *common, struct fsg_buffhd *bh)
 {
+	int rc;
+
 	if (!fsg_is_set(common))
 		return false;
 	bh->state = BUF_STATE_RECEIVING;
-	if (start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq))
+	rc = start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq);
+	if (rc) {
 		bh->state = BUF_STATE_FULL;
+		if (rc == -ESHUTDOWN) {
+			common->running = 0;
+			return false;
+		}
+	}
 	return true;
 }
 
-- 
GitLab


From 032178972f8e992b90f9794a13265fec8c8314b0 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 14 Jan 2024 16:30:08 -0800
Subject: [PATCH 3558/4076] usb: gadget: pch_udc: fix an Excess kernel-doc
 warning

Delete one extraneous line of kernel-doc to prevent a kernel-doc
warning:

pch_udc.c:297: warning: Excess struct member 'desc' description in 'pch_udc_ep'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Cc: tomoya-linux@dsn.lapis-semi.com
Link: https://lore.kernel.org/r/20240115003008.5763-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/pch_udc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c
index 4f8617210d852..169f72665739f 100644
--- a/drivers/usb/gadget/udc/pch_udc.c
+++ b/drivers/usb/gadget/udc/pch_udc.c
@@ -274,7 +274,6 @@ struct pch_udc_cfg_data {
  * @td_data:		for data request
  * @dev:		reference to device struct
  * @offset_addr:	offset address of ep register
- * @desc:		for this ep
  * @queue:		queue for requests
  * @num:		endpoint number
  * @in:			endpoint is IN
-- 
GitLab


From b717dfbf73e842d15174699fe2c6ee4fdde8aa1f Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 17 Jan 2024 11:47:42 +0000
Subject: [PATCH 3559/4076] Revert "usb: typec: tcpm: fix cc role at port
 reset"

This reverts commit 1e35f074399dece73d5df11847d4a0d7a6f49434.

Given that ERROR_RECOVERY calls into PORT_RESET for Hi-Zing
the CC pins, setting CC pins to default state during PORT_RESET
breaks error recovery.

4.5.2.2.2.1 ErrorRecovery State Requirements
The port shall not drive VBUS or VCONN, and shall present a
high-impedance to ground (above zOPEN) on its CC1 and CC2 pins.

Hi-Zing the CC pins is the inteded behavior for PORT_RESET.
CC pins are set to default state after tErrorRecovery in
PORT_RESET_WAIT_OFF.

4.5.2.2.2.2 Exiting From ErrorRecovery State
A Sink shall transition to Unattached.SNK after tErrorRecovery.
A Source shall transition to Unattached.SRC after tErrorRecovery.

Cc: stable@vger.kernel.org
Cc: Frank Wang <frank.wang@rock-chips.com>
Fixes: 1e35f074399d ("usb: typec: tcpm: fix cc role at port reset")
Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20240117114742.2587779-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 5945e3a2b0f78..9d410718eaf47 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4876,8 +4876,7 @@ static void run_state_machine(struct tcpm_port *port)
 		break;
 	case PORT_RESET:
 		tcpm_reset_port(port);
-		tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ?
-			    TYPEC_CC_RD : tcpm_rp_cc(port));
+		tcpm_set_cc(port, TYPEC_CC_OPEN);
 		tcpm_set_state(port, PORT_RESET_WAIT_OFF,
 			       PD_T_ERROR_RECOVERY);
 		break;
-- 
GitLab


From 3caf2b2ad7334ef35f55b95f3e1b138c6f77b368 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@seco.com>
Date: Fri, 26 Jan 2024 17:38:00 -0500
Subject: [PATCH 3560/4076] usb: ulpi: Fix debugfs directory leak

The ULPI per-device debugfs root is named after the ulpi device's
parent, but ulpi_unregister_interface tries to remove a debugfs
directory named after the ulpi device itself. This results in the
directory sticking around and preventing subsequent (deferred) probes
from succeeding. Change the directory name to match the ulpi device.

Fixes: bd0a0a024f2a ("usb: ulpi: Add debugfs support")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Anderson <sean.anderson@seco.com>
Link: https://lore.kernel.org/r/20240126223800.2864613-1-sean.anderson@seco.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/common/ulpi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c
index 84d91b1c1eed5..0886b19d2e1c8 100644
--- a/drivers/usb/common/ulpi.c
+++ b/drivers/usb/common/ulpi.c
@@ -301,7 +301,7 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi)
 		return ret;
 	}
 
-	root = debugfs_create_dir(dev_name(dev), ulpi_root);
+	root = debugfs_create_dir(dev_name(&ulpi->dev), ulpi_root);
 	debugfs_create_file("regs", 0444, root, ulpi, &ulpi_regs_fops);
 
 	dev_dbg(&ulpi->dev, "registered ULPI PHY: vendor %04x, product %04x\n",
-- 
GitLab


From c9aed03a0a683fd1600ea92f2ad32232d4736272 Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Sun, 21 Jan 2024 21:41:21 +0100
Subject: [PATCH 3561/4076] usb: ucsi: Add missing ppm_lock

Calling ->sync_write must be done while holding the PPM lock as
the mailbox logic does not support concurrent commands.

At least since the addition of partner task this means that
ucsi_acknowledge_connector_change should be called with the
PPM lock held as it calls ->sync_write.

Thus protect the only call to ucsi_acknowledge_connector_change
with the PPM. All other calls to ->sync_write already happen
under the PPM lock.

Fixes: b9aa02ca39a4 ("usb: typec: ucsi: Add polling mechanism for partner tasks like alt mode checking")
Cc: stable@vger.kernel.org
Signed-off-by: "Christian A. Ehrhardt" <lk@c--e.de>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20240121204123.275441-2-lk@c--e.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 5392ec6989592..14f5a7bfae2e9 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -938,7 +938,9 @@ static void ucsi_handle_connector_change(struct work_struct *work)
 
 	clear_bit(EVENT_PENDING, &con->ucsi->flags);
 
+	mutex_lock(&ucsi->ppm_lock);
 	ret = ucsi_acknowledge_connector_change(ucsi);
+	mutex_unlock(&ucsi->ppm_lock);
 	if (ret)
 		dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret);
 
-- 
GitLab


From 2840143e393a4ddc1caab4372969ea337371168c Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Sun, 21 Jan 2024 21:41:22 +0100
Subject: [PATCH 3562/4076] usb: ucsi_acpi: Fix command completion handling

In case of a spurious or otherwise delayed notification it is
possible that CCI still reports the previous completion. The
UCSI spec is aware of this and provides two completion bits in
CCI, one for normal commands and one for acks. As acks and commands
alternate the notification handler can determine if the completion
bit is from the current command.

The initial UCSI code correctly handled this but the distinction
between the two completion bits was lost with the introduction of
the new API.

To fix this revive the ACK_PENDING bit for ucsi_acpi and only complete
commands if the completion bit matches.

Fixes: f56de278e8ec ("usb: typec: ucsi: acpi: Move to the new API")
Cc: stable@vger.kernel.org
Signed-off-by: "Christian A. Ehrhardt" <lk@c--e.de>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20240121204123.275441-3-lk@c--e.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi_acpi.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 6bbf490ac4010..fa222080887d5 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -73,9 +73,13 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset,
 				const void *val, size_t val_len)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	bool ack = UCSI_COMMAND(*(u64 *)val) == UCSI_ACK_CC_CI;
 	int ret;
 
-	set_bit(COMMAND_PENDING, &ua->flags);
+	if (ack)
+		set_bit(ACK_PENDING, &ua->flags);
+	else
+		set_bit(COMMAND_PENDING, &ua->flags);
 
 	ret = ucsi_acpi_async_write(ucsi, offset, val, val_len);
 	if (ret)
@@ -85,7 +89,10 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset,
 		ret = -ETIMEDOUT;
 
 out_clear_bit:
-	clear_bit(COMMAND_PENDING, &ua->flags);
+	if (ack)
+		clear_bit(ACK_PENDING, &ua->flags);
+	else
+		clear_bit(COMMAND_PENDING, &ua->flags);
 
 	return ret;
 }
@@ -142,8 +149,10 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data)
 	if (UCSI_CCI_CONNECTOR(cci))
 		ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci));
 
-	if (test_bit(COMMAND_PENDING, &ua->flags) &&
-	    cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE))
+	if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags))
+		complete(&ua->complete);
+	if (cci & UCSI_CCI_COMMAND_COMPLETE &&
+	    test_bit(COMMAND_PENDING, &ua->flags))
 		complete(&ua->complete);
 }
 
-- 
GitLab


From f3be347ea42dbb0358cd8b2d8dc543a23b70a976 Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Sun, 21 Jan 2024 21:41:23 +0100
Subject: [PATCH 3563/4076] usb: ucsi_acpi: Quirk to ack a connector change ack
 cmd

The PPM on some Dell laptops seems to expect that the ACK_CC_CI
command to clear the connector change notification is in turn
followed by another ACK_CC_CI to acknowledge the ACK_CC_CI command
itself. This is in violation of the UCSI spec that states:

    "The only notification that is not acknowledged by the OPM is
     the command completion notification for the ACK_CC_CI or the
     PPM_RESET command."

Add a quirk to send this ack anyway.
Apply the quirk to all Dell systems.

On the first command that acks a connector change send a dummy
command to determine if it runs into a timeout. Only activate
the quirk if it does. This ensure that we do not break Dell
systems that do not need the quirk.

Signed-off-by: "Christian A. Ehrhardt" <lk@c--e.de>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20240121204123.275441-4-lk@c--e.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi_acpi.c | 71 ++++++++++++++++++++++++++++--
 1 file changed, 68 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index fa222080887d5..928eacbeb21ac 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -25,6 +25,8 @@ struct ucsi_acpi {
 	unsigned long flags;
 	guid_t guid;
 	u64 cmd;
+	bool dell_quirk_probed;
+	bool dell_quirk_active;
 };
 
 static int ucsi_acpi_dsm(struct ucsi_acpi *ua, int func)
@@ -126,12 +128,73 @@ static const struct ucsi_operations ucsi_zenbook_ops = {
 	.async_write = ucsi_acpi_async_write
 };
 
-static const struct dmi_system_id zenbook_dmi_id[] = {
+/*
+ * Some Dell laptops expect that an ACK command with the
+ * UCSI_ACK_CONNECTOR_CHANGE bit set is followed by a (separate)
+ * ACK command that only has the UCSI_ACK_COMMAND_COMPLETE bit set.
+ * If this is not done events are not delivered to OSPM and
+ * subsequent commands will timeout.
+ */
+static int
+ucsi_dell_sync_write(struct ucsi *ucsi, unsigned int offset,
+		     const void *val, size_t val_len)
+{
+	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	u64 cmd = *(u64 *)val, ack = 0;
+	int ret;
+
+	if (UCSI_COMMAND(cmd) == UCSI_ACK_CC_CI &&
+	    cmd & UCSI_ACK_CONNECTOR_CHANGE)
+		ack = UCSI_ACK_CC_CI | UCSI_ACK_COMMAND_COMPLETE;
+
+	ret = ucsi_acpi_sync_write(ucsi, offset, val, val_len);
+	if (ret != 0)
+		return ret;
+	if (ack == 0)
+		return ret;
+
+	if (!ua->dell_quirk_probed) {
+		ua->dell_quirk_probed = true;
+
+		cmd = UCSI_GET_CAPABILITY;
+		ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd,
+					   sizeof(cmd));
+		if (ret == 0)
+			return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL,
+						    &ack, sizeof(ack));
+		if (ret != -ETIMEDOUT)
+			return ret;
+
+		ua->dell_quirk_active = true;
+		dev_err(ua->dev, "Firmware bug: Additional ACK required after ACKing a connector change.\n");
+		dev_err(ua->dev, "Firmware bug: Enabling workaround\n");
+	}
+
+	if (!ua->dell_quirk_active)
+		return ret;
+
+	return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &ack, sizeof(ack));
+}
+
+static const struct ucsi_operations ucsi_dell_ops = {
+	.read = ucsi_acpi_read,
+	.sync_write = ucsi_dell_sync_write,
+	.async_write = ucsi_acpi_async_write
+};
+
+static const struct dmi_system_id ucsi_acpi_quirks[] = {
 	{
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"),
 		},
+		.driver_data = (void *)&ucsi_zenbook_ops,
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		},
+		.driver_data = (void *)&ucsi_dell_ops,
 	},
 	{ }
 };
@@ -160,6 +223,7 @@ static int ucsi_acpi_probe(struct platform_device *pdev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
 	const struct ucsi_operations *ops = &ucsi_acpi_ops;
+	const struct dmi_system_id *id;
 	struct ucsi_acpi *ua;
 	struct resource *res;
 	acpi_status status;
@@ -189,8 +253,9 @@ static int ucsi_acpi_probe(struct platform_device *pdev)
 	init_completion(&ua->complete);
 	ua->dev = &pdev->dev;
 
-	if (dmi_check_system(zenbook_dmi_id))
-		ops = &ucsi_zenbook_ops;
+	id = dmi_first_match(ucsi_acpi_quirks);
+	if (id)
+		ops = id->driver_data;
 
 	ua->ucsi = ucsi_create(&pdev->dev, ops);
 	if (IS_ERR(ua->ucsi))
-- 
GitLab


From f2e5d3de7e1fbf24483e7f996e519b3ebc3935a1 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sat, 13 Jan 2024 22:55:48 +0200
Subject: [PATCH 3564/4076] usb: typec: tcpm: fix the PD disabled case

If the PD is disabled for the port, port->pds will be left as NULL,
which causes the following crash during caps intilisation. Fix the
crash.

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
Call trace:
 tcpm_register_port+0xaec/0xc44
 qcom_pmic_typec_probe+0x1a4/0x254
 platform_probe+0x68/0xc0
 really_probe+0x148/0x2ac
 __driver_probe_device+0x78/0x12c
 driver_probe_device+0xd8/0x160
Bluetooth: hci0: QCA Product ID   :0x0000000a
 __device_attach_driver+0xb8/0x138
 bus_for_each_drv+0x80/0xdc
Bluetooth: hci0: QCA SOC Version  :0x40020150
 __device_attach+0x9c/0x188
 device_initial_probe+0x14/0x20
 bus_probe_device+0xac/0xb0
 deferred_probe_work_func+0x8c/0xc8
 process_one_work+0x1ec/0x51c
 worker_thread+0x1ec/0x3e4
 kthread+0x120/0x124
 ret_from_fork+0x10/0x20

Fixes: cd099cde4ed2 ("usb: typec: tcpm: Support multiple capabilities")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20240113-pmi632-typec-v2-5-182d9aa0a5b3@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 9d410718eaf47..f7d7daa60c8dc 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -6847,7 +6847,8 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	if (err)
 		goto out_role_sw_put;
 
-	port->typec_caps.pd = port->pds[0];
+	if (port->pds)
+		port->typec_caps.pd = port->pds[0];
 
 	port->typec_port = typec_register_port(port->dev, &port->typec_caps);
 	if (IS_ERR(port->typec_port)) {
-- 
GitLab


From e15c99be0c915bbe70dfe55450d268d7bd5bdac8 Mon Sep 17 00:00:00 2001
From: Christoph Niedermaier <cniedermaier@dh-electronics.com>
Date: Fri, 19 Jan 2024 12:35:16 +0100
Subject: [PATCH 3565/4076] tty: serial: Fix bit order in RS485 flag
 definitions

Since the commit 93f3350c46fa ("RS485: fix inconsistencies in the
meaning of some variables"), the definition for bit 3 has been removed.
But with the switch to bit shift macros in commit 76ac8e29855b ("tty:
serial: Cleanup the bit shift with macro"), this gap wasn't preserved.
To avoid a break in user/kernel api of the system skip bit 3 again and
add a placeholder comment.

Signed-off-by: Christoph Niedermaier <cniedermaier@dh-electronics.com>
Fixes: 76ac8e29855b ("tty: serial: Cleanup the bit shift with macro")
Fixes: 6056f20f27e9 ("tty: serial: Add RS422 flag to struct serial_rs485")
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Cc: Hugo Villeneuve <hugo@hugovil.com>
Link: https://lore.kernel.org/r/20240119113516.2944-1-cniedermaier@dh-electronics.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/serial.h | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h
index 9086367db0435..de9b4733607e6 100644
--- a/include/uapi/linux/serial.h
+++ b/include/uapi/linux/serial.h
@@ -145,12 +145,13 @@ struct serial_rs485 {
 #define SER_RS485_ENABLED		_BITUL(0)
 #define SER_RS485_RTS_ON_SEND		_BITUL(1)
 #define SER_RS485_RTS_AFTER_SEND	_BITUL(2)
-#define SER_RS485_RX_DURING_TX		_BITUL(3)
-#define SER_RS485_TERMINATE_BUS		_BITUL(4)
-#define SER_RS485_ADDRB			_BITUL(5)
-#define SER_RS485_ADDR_RECV		_BITUL(6)
-#define SER_RS485_ADDR_DEST		_BITUL(7)
-#define SER_RS485_MODE_RS422		_BITUL(8)
+/* Placeholder for bit 3: SER_RS485_RTS_BEFORE_SEND, which isn't used anymore */
+#define SER_RS485_RX_DURING_TX		_BITUL(4)
+#define SER_RS485_TERMINATE_BUS		_BITUL(5)
+#define SER_RS485_ADDRB			_BITUL(6)
+#define SER_RS485_ADDR_RECV		_BITUL(7)
+#define SER_RS485_ADDR_DEST		_BITUL(8)
+#define SER_RS485_MODE_RS422		_BITUL(9)
 
 	__u32	delay_rts_before_send;
 	__u32	delay_rts_after_send;
-- 
GitLab


From 86ee55e9bc7ff7308eda67e5bcb3f8c834c7c113 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 10 Jan 2024 22:25:21 +0300
Subject: [PATCH 3566/4076] serial: 8250_pci1xxxx: fix off by one in
 pci1xxxx_process_read_data()

These > comparisons should be >= to prevent writing one element beyond
the end of the rx_buff[] array.  The rx_buff[] buffer has RX_BUF_SIZE
elements.  Fix the buffer overflow.

Fixes: aba8290f368d ("8250: microchip: pci1xxxx: Add Burst mode reception support in uart driver for writing into FIFO")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/ZZ7vIfj7Jgh-pJn8@moroto
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci1xxxx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index 558c4c7f3104e..cd258922bd780 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -302,7 +302,7 @@ static void pci1xxxx_process_read_data(struct uart_port *port,
 	 * to read, the data is received one byte at a time.
 	 */
 	while (valid_burst_count--) {
-		if (*buff_index > (RX_BUF_SIZE - UART_BURST_SIZE))
+		if (*buff_index >= (RX_BUF_SIZE - UART_BURST_SIZE))
 			break;
 		burst_buf = (u32 *)&rx_buff[*buff_index];
 		*burst_buf = readl(port->membase + UART_RX_BURST_FIFO);
@@ -311,7 +311,7 @@ static void pci1xxxx_process_read_data(struct uart_port *port,
 	}
 
 	while (*valid_byte_count) {
-		if (*buff_index > RX_BUF_SIZE)
+		if (*buff_index >= RX_BUF_SIZE)
 			break;
 		rx_buff[*buff_index] = readb(port->membase +
 					     UART_RX_BYTE_FIFO);
-- 
GitLab


From 30926783a46841c2d1bbf3f74067ba85d304fd0d Mon Sep 17 00:00:00 2001
From: Gui-Dong Han <2045gemini@gmail.com>
Date: Fri, 12 Jan 2024 19:36:24 +0800
Subject: [PATCH 3567/4076] serial: core: Fix atomicity violation in
 uart_tiocmget

In uart_tiocmget():
    result = uport->mctrl;
    uart_port_lock_irq(uport);
    result |= uport->ops->get_mctrl(uport);
    uart_port_unlock_irq(uport);
    ...
    return result;

In uart_update_mctrl():
    uart_port_lock_irqsave(port, &flags);
    ...
    port->mctrl = (old & ~clear) | set;
    ...
    port->ops->set_mctrl(port, port->mctrl);
    ...
    uart_port_unlock_irqrestore(port, flags);

An atomicity violation is identified due to the concurrent execution of
uart_tiocmget() and uart_update_mctrl(). After assigning
result = uport->mctrl, the mctrl value may change in uart_update_mctrl(),
leading to a mismatch between the value returned by
uport->ops->get_mctrl(uport) and the mctrl value previously read.
This can result in uart_tiocmget() returning an incorrect value.

This possible bug is found by an experimental static analysis tool
developed by our team, BassCheck[1]. This tool analyzes the locking APIs
to extract function pairs that can be concurrently executed, and then
analyzes the instructions in the paired functions to identify possible
concurrency bugs including data races and atomicity violations. The above
possible bug is reported when our tool analyzes the source code of
Linux 5.17.

To address this issue, it is suggested to move the line
result = uport->mctrl inside the uart_port_lock block to ensure atomicity
and prevent the mctrl value from being altered during the execution of
uart_tiocmget(). With this patch applied, our tool no longer reports the
bug, with the kernel configuration allyesconfig for x86_64. Due to the
absence of the requisite hardware, we are unable to conduct runtime
testing of the patch. Therefore, our verification is solely based on code
logic analysis.

[1] https://sites.google.com/view/basscheck/

Fixes: c5f4644e6c8b ("[PATCH] Serial: Adjust serial locking")
Cc: stable@vger.kernel.org
Signed-off-by: Gui-Dong Han <2045gemini@gmail.com>
Link: https://lore.kernel.org/r/20240112113624.17048-1-2045gemini@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index b56ed8c376b22..d6a58a9e072a1 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1084,8 +1084,8 @@ static int uart_tiocmget(struct tty_struct *tty)
 		goto out;
 
 	if (!tty_io_error(tty)) {
-		result = uport->mctrl;
 		uart_port_lock_irq(uport);
+		result = uport->mctrl;
 		result |= uport->ops->get_mctrl(uport);
 		uart_port_unlock_irq(uport);
 	}
-- 
GitLab


From 0419373333c2f2024966d36261fd82a453281e80 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Tue, 16 Jan 2024 16:29:58 -0500
Subject: [PATCH 3568/4076] serial: max310x: set default value when reading
 clock ready bit

If regmap_read() returns a non-zero value, the 'val' variable can be left
uninitialized.

Clear it before calling regmap_read() to make sure we properly detect
the clock ready bit.

Fixes: 4cf9a888fd3c ("serial: max310x: Check the clock readiness")
Cc: stable@vger.kernel.org
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20240116213001.3691629-2-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index f3a99daebdaa0..b2c753ba9cbfd 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -641,7 +641,7 @@ static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
 
 	/* Wait for crystal */
 	if (xtal) {
-		unsigned int val;
+		unsigned int val = 0;
 		msleep(10);
 		regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val);
 		if (!(val & MAX310X_STS_CLKREADY_BIT)) {
-- 
GitLab


From 93cd256ab224c2519e7c4e5f58bb4f1ac2bf0965 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Tue, 16 Jan 2024 16:29:59 -0500
Subject: [PATCH 3569/4076] serial: max310x: improve crystal stable clock
 detection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some people are seeing a warning similar to this when using a crystal:

    max310x 11-006c: clock is not stable yet

The datasheet doesn't mention the maximum time to wait for the clock to be
stable when using a crystal, and it seems that the 10ms delay in the driver
is not always sufficient.

Jan Kundrát reported that it took three tries (each separated by 10ms) to
get a stable clock.

Modify behavior to check stable clock ready bit multiple times (20), and
waiting 10ms between each try.

Note: the first draft of the driver originally used a 50ms delay, without
checking the clock stable bit.
Then a loop with 1000 retries was implemented, each time reading the clock
stable bit.

Fixes: 4cf9a888fd3c ("serial: max310x: Check the clock readiness")
Cc: stable@vger.kernel.org
Suggested-by: Jan Kundrát <jan.kundrat@cesnet.cz>
Link: https://www.spinics.net/lists/linux-serial/msg35773.html
Link: https://lore.kernel.org/all/20240110174015.6f20195fde08e5c9e64e5675@hugovil.com/raw
Link: https://github.com/boundarydevices/linux/commit/e5dfe3e4a751392515d78051973190301a37ca9a
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20240116213001.3691629-3-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index b2c753ba9cbfd..c0eb0615d945b 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -237,6 +237,10 @@
 #define MAX310x_REV_MASK		(0xf8)
 #define MAX310X_WRITE_BIT		0x80
 
+/* Crystal-related definitions */
+#define MAX310X_XTAL_WAIT_RETRIES	20 /* Number of retries */
+#define MAX310X_XTAL_WAIT_DELAY_MS	10 /* Delay between retries */
+
 /* MAX3107 specific */
 #define MAX3107_REV_ID			(0xa0)
 
@@ -641,12 +645,19 @@ static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
 
 	/* Wait for crystal */
 	if (xtal) {
-		unsigned int val = 0;
-		msleep(10);
-		regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val);
-		if (!(val & MAX310X_STS_CLKREADY_BIT)) {
+		bool stable = false;
+		unsigned int try = 0, val = 0;
+
+		do {
+			msleep(MAX310X_XTAL_WAIT_DELAY_MS);
+			regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val);
+
+			if (val & MAX310X_STS_CLKREADY_BIT)
+				stable = true;
+		} while (!stable && (++try < MAX310X_XTAL_WAIT_RETRIES));
+
+		if (!stable)
 			dev_warn(dev, "clock is not stable yet\n");
-		}
 	}
 
 	return bestfreq;
-- 
GitLab


From 8afa6c6decea37e7cb473d2c60473f37f46cea35 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Tue, 16 Jan 2024 16:30:00 -0500
Subject: [PATCH 3570/4076] serial: max310x: fail probe if clock crystal is
 unstable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A stable clock is really required in order to use this UART, so log an
error message and bail out if the chip reports that the clock is not
stable.

Fixes: 4cf9a888fd3c ("serial: max310x: Check the clock readiness")
Cc: stable@vger.kernel.org
Suggested-by: Jan Kundrát <jan.kundrat@cesnet.cz>
Link: https://www.spinics.net/lists/linux-serial/msg35773.html
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20240116213001.3691629-4-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index c0eb0615d945b..552e153a24e05 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -587,7 +587,7 @@ static int max310x_update_best_err(unsigned long f, long *besterr)
 	return 1;
 }
 
-static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
+static s32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
 			       unsigned long freq, bool xtal)
 {
 	unsigned int div, clksrc, pllcfg = 0;
@@ -657,7 +657,8 @@ static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
 		} while (!stable && (++try < MAX310X_XTAL_WAIT_RETRIES));
 
 		if (!stable)
-			dev_warn(dev, "clock is not stable yet\n");
+			return dev_err_probe(dev, -EAGAIN,
+					     "clock is not stable\n");
 	}
 
 	return bestfreq;
@@ -1282,7 +1283,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 {
 	int i, ret, fmin, fmax, freq;
 	struct max310x_port *s;
-	u32 uartclk = 0;
+	s32 uartclk = 0;
 	bool xtal;
 
 	for (i = 0; i < devtype->nr; i++)
@@ -1360,6 +1361,11 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 	}
 
 	uartclk = max310x_set_ref_clk(dev, s, freq, xtal);
+	if (uartclk < 0) {
+		ret = uartclk;
+		goto out_uart;
+	}
+
 	dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk);
 
 	for (i = 0; i < devtype->nr; i++) {
-- 
GitLab


From b35f8dbbce818b02c730dc85133dc7754266e084 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Tue, 16 Jan 2024 16:30:01 -0500
Subject: [PATCH 3571/4076] serial: max310x: prevent infinite while() loop in
 port startup

If there is a problem after resetting a port, the do/while() loop that
checks the default value of DIVLSB register may run forever and spam the
I2C bus.

Add a delay before each read of DIVLSB, and a maximum number of tries to
prevent that situation from happening.

Also fail probe if port reset is unsuccessful.

Fixes: 10d8b34a4217 ("serial: max310x: Driver rework")
Cc: stable@vger.kernel.org
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20240116213001.3691629-5-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 552e153a24e05..10bf6d75bf9ee 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -237,6 +237,10 @@
 #define MAX310x_REV_MASK		(0xf8)
 #define MAX310X_WRITE_BIT		0x80
 
+/* Port startup definitions */
+#define MAX310X_PORT_STARTUP_WAIT_RETRIES	20 /* Number of retries */
+#define MAX310X_PORT_STARTUP_WAIT_DELAY_MS	10 /* Delay between retries */
+
 /* Crystal-related definitions */
 #define MAX310X_XTAL_WAIT_RETRIES	20 /* Number of retries */
 #define MAX310X_XTAL_WAIT_DELAY_MS	10 /* Delay between retries */
@@ -1346,6 +1350,9 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 		goto out_clk;
 
 	for (i = 0; i < devtype->nr; i++) {
+		bool started = false;
+		unsigned int try = 0, val = 0;
+
 		/* Reset port */
 		regmap_write(regmaps[i], MAX310X_MODE2_REG,
 			     MAX310X_MODE2_RST_BIT);
@@ -1354,8 +1361,17 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 
 		/* Wait for port startup */
 		do {
-			regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &ret);
-		} while (ret != 0x01);
+			msleep(MAX310X_PORT_STARTUP_WAIT_DELAY_MS);
+			regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &val);
+
+			if (val == 0x01)
+				started = true;
+		} while (!started && (++try < MAX310X_PORT_STARTUP_WAIT_RETRIES));
+
+		if (!started) {
+			ret = dev_err_probe(dev, -EAGAIN, "port reset failed\n");
+			goto out_uart;
+		}
 
 		regmap_write(regmaps[i], MAX310X_MODE1_REG, devtype->mode1);
 	}
-- 
GitLab


From 2751153b9945c31eb905deb9fbe2d7f127b4b34c Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Fri, 1 Dec 2023 21:20:50 +0100
Subject: [PATCH 3572/4076] parisc: Make RO_DATA page aligned in vmlinux.lds.S

The rodata_test program for CONFIG_DEBUG_RODATA_TEST=y complains if
read-only data does not start at page boundary.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/vmlinux.lds.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 548051b0b4aff..b445e47903cfd 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -127,7 +127,7 @@ SECTIONS
 	}
 #endif
 
-	RO_DATA(8)
+	RO_DATA(PAGE_SIZE)
 
 	/* unwind info */
 	. = ALIGN(4);
-- 
GitLab


From b9402e3b97289ca9e0f0f79f4df64bd6c9176a86 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 17 Jan 2024 17:46:43 +0100
Subject: [PATCH 3573/4076] parisc: Check for valid stride size for cache
 flushes

Report if the calculated cache stride size is zero, otherwise the cache
flushing routine will never finish and hang the machine.
This can be reproduced with a testcase in qemu, where the firmware reports
wrong cache values.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/cache.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 268d90a9325b4..0c015487e5db6 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -264,6 +264,10 @@ parisc_cache_init(void)
 	icache_stride = CAFL_STRIDE(cache_info.ic_conf);
 #undef CAFL_STRIDE
 
+	/* stride needs to be non-zero, otherwise cache flushes will not work */
+	WARN_ON(cache_info.dc_size && dcache_stride == 0);
+	WARN_ON(cache_info.ic_size && icache_stride == 0);
+
 	if ((boot_cpu_data.pdc.capabilities & PDC_MODEL_NVA_MASK) ==
 						PDC_MODEL_NVA_UNSUPPORTED) {
 		printk(KERN_WARNING "parisc_cache_init: Only equivalent aliasing supported!\n");
-- 
GitLab


From c8708d758e715c3824a73bf0cda97292b52be44d Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Fri, 19 Jan 2024 21:16:39 +0100
Subject: [PATCH 3574/4076] parisc: Prevent hung tasks when printing inventory
 on serial console

Printing the inventory on a serial console can be quite slow and thus may
trigger the hung task detector (CONFIG_DETECT_HUNG_TASK=y) and possibly
reboot the machine. Adding a cond_resched() prevents this.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.0+
---
 arch/parisc/kernel/drivers.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 25f9b9e9d6dfb..404ea37705ce6 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -1004,6 +1004,9 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data)
 
 	pr_info("\n");
 
+	/* Prevent hung task messages when printing on serial console */
+	cond_resched();
+
 	pr_info("#define HPA_%08lx_DESCRIPTION \"%s\"\n",
 		hpa, parisc_hardware_description(&dev->id));
 
-- 
GitLab


From 20e08a720cc526dacc0678067ffc81613aa738ca Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Mon, 22 Jan 2024 17:51:15 +0100
Subject: [PATCH 3575/4076] parisc: Drop unneeded semicolon in
 parse_tree_node()

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Helge Deller <deller@gmx.de>
Closes: https://lore.kernel.org/oe-kbuild-all/202401222059.Wli6OGT0-lkp@intel.com/
---
 arch/parisc/kernel/drivers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 404ea37705ce6..c7ff339732ba5 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -742,7 +742,7 @@ parse_tree_node(struct device *parent, int index, struct hardware_path *modpath)
 	};
 
 	if (device_for_each_child(parent, &recurse_data, descend_children))
-		{ /* nothing */ };
+		{ /* nothing */ }
 
 	return d.dev;
 }
-- 
GitLab


From 29142dc92c37d3259a33aef15b03e6ee25b0d188 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 27 Jan 2024 13:21:14 -0800
Subject: [PATCH 3576/4076] tracefs: remove stale 'update_gid' code

The 'eventfs_update_gid()' function is no longer called, so remove it
(and the helper function it uses).

Link: https://lore.kernel.org/all/CAHk-=wj+DsZZ=2iTUkJ-Nojs9fjYMvPs1NuoM3yK7aTDtJfPYQ@mail.gmail.com/

Fixes: 8186fff7ab64 ("tracefs/eventfs: Use root and instance inodes as default ownership")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 38 --------------------------------------
 fs/tracefs/internal.h    |  1 -
 2 files changed, 39 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 6b211522a13ec..1c3dd0ad4660e 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -281,44 +281,6 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
 		inode->i_gid = attr->gid;
 }
 
-static void update_gid(struct eventfs_inode *ei, kgid_t gid, int level)
-{
-	struct eventfs_inode *ei_child;
-
-	/* at most we have events/system/event */
-	if (WARN_ON_ONCE(level > 3))
-		return;
-
-	ei->attr.gid = gid;
-
-	if (ei->entry_attrs) {
-		for (int i = 0; i < ei->nr_entries; i++) {
-			ei->entry_attrs[i].gid = gid;
-		}
-	}
-
-	/*
-	 * Only eventfs_inode with dentries are updated, make sure
-	 * all eventfs_inodes are updated. If one of the children
-	 * do not have a dentry, this function must traverse it.
-	 */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		if (!ei_child->dentry)
-			update_gid(ei_child, gid, level + 1);
-	}
-}
-
-void eventfs_update_gid(struct dentry *dentry, kgid_t gid)
-{
-	struct eventfs_inode *ei = dentry->d_fsdata;
-	int idx;
-
-	idx = srcu_read_lock(&eventfs_srcu);
-	update_gid(ei, gid, 0);
-	srcu_read_unlock(&eventfs_srcu, idx);
-}
-
 /**
  * create_file - create a file in the tracefs filesystem
  * @name: the name of the file to create.
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 45397df9bb65b..91c2bf0b91d9c 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -82,7 +82,6 @@ struct inode *tracefs_get_inode(struct super_block *sb);
 struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
 struct dentry *eventfs_failed_creating(struct dentry *dentry);
 struct dentry *eventfs_end_creating(struct dentry *dentry);
-void eventfs_update_gid(struct dentry *dentry, kgid_t gid);
 void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */
-- 
GitLab


From 41bccc98fb7931d63d03f326a746ac4d429c1dd3 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 28 Jan 2024 17:01:12 -0800
Subject: [PATCH 3577/4076] Linux 6.8-rc2

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 9f9b76d3a4b7d..6c0a4d294444c 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
-- 
GitLab


From eba38cc7578bef94865341c73608bdf49193a51d Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@kernel.org>
Date: Sun, 28 Jan 2024 09:53:55 +0100
Subject: [PATCH 3578/4076] bcachefs: Fix build on parisc by avoiding
 __multi3()

The gcc compiler on paric does support the __int128 type, although the
architecture does not have native 128-bit support.

The effect is, that the bcachefs u128_square() function will pull in the
libgcc __multi3() helper, which breaks the kernel build when bcachefs is
built as module since this function isn't currently exported in
arch/parisc/kernel/parisc_ksyms.c.
The build failure can be seen in the latest debian kernel build at:
https://buildd.debian.org/status/fetch.php?pkg=linux&arch=hppa&ver=6.7.1-1%7Eexp1&stamp=1706132569&raw=0

We prefer to not export that symbol, so fall back to the optional 64-bit
implementation provided by bcachefs and thus avoid usage of __multi3().

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/mean_and_variance.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/mean_and_variance.h b/fs/bcachefs/mean_and_variance.h
index b2be565bb8f21..64df11ab422bf 100644
--- a/fs/bcachefs/mean_and_variance.h
+++ b/fs/bcachefs/mean_and_variance.h
@@ -17,7 +17,7 @@
  * Rust and rustc has issues with u128.
  */
 
-#if defined(__SIZEOF_INT128__) && defined(__KERNEL__)
+#if defined(__SIZEOF_INT128__) && defined(__KERNEL__) && !defined(CONFIG_PARISC)
 
 typedef struct {
 	unsigned __int128 v;
-- 
GitLab


From 6bb3f7f4c3f4da8e09de188f2f63e8f741bba3bd Mon Sep 17 00:00:00 2001
From: Guoyu Ou <benogy@gmail.com>
Date: Sun, 28 Jan 2024 16:46:17 +0800
Subject: [PATCH 3579/4076] bcachefs: unlock parent dir if entry is not found
 in subvolume deletion

Parent dir is locked by user_path_locked_at() before validating the
required dentry. It should be unlocked if we can not perform the
deletion.

This fixes the problem:

$ bcachefs subvolume delete not-exist-entry
BCH_IOCTL_SUBVOLUME_DESTROY ioctl error: No such file or directory
$ bcachefs subvolume delete not-exist-entry

the second will stuck because the parent dir is locked in the previous
deletion.

Signed-off-by: Guoyu Ou <benogy@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs-ioctl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 3a4c24c28e7fa..3dc8630ff9fe1 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -455,6 +455,7 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
 	if (IS_ERR(victim))
 		return PTR_ERR(victim);
 
+	dir = d_inode(path.dentry);
 	if (victim->d_sb->s_fs_info != c) {
 		ret = -EXDEV;
 		goto err;
@@ -463,14 +464,13 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
 		ret = -ENOENT;
 		goto err;
 	}
-	dir = d_inode(path.dentry);
 	ret = __bch2_unlink(dir, victim, true);
 	if (!ret) {
 		fsnotify_rmdir(dir, victim);
 		d_delete(victim);
 	}
-	inode_unlock(dir);
 err:
+	inode_unlock(dir);
 	dput(victim);
 	path_put(&path);
 	return ret;
-- 
GitLab


From c79f52f0656eeb3e4a12f7f358f760077ae111b6 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 27 Jan 2024 13:44:58 -0700
Subject: [PATCH 3580/4076] io_uring/rw: ensure poll based multishot read
 retries appropriately

io_read_mshot() always relies on poll triggering retries, and this works
fine as long as we do a retry per size of the buffer being read. The
buffer size is given by the size of the buffer(s) in the given buffer
group ID.

But if we're reading less than what is available, then we don't always
get to read everything that is available. For example, if the buffers
available are 32 bytes and we have 64 bytes to read, then we'll
correctly read the first 32 bytes and then wait for another poll trigger
before we attempt the next read. This next poll trigger may never
happen, in which case we just sit forever and never make progress, or it
may trigger at some point in the future, and now we're just delivering
the available data much later than we should have.

io_read_mshot() could do retries itself, but that is wasteful as we'll
be going through all of __io_read() again, and most likely in vain.
Rather than do that, bump our poll reference count and have
io_poll_check_events() do one more loop and check with vfs_poll() if we
have more data to read. If we do, io_read_mshot() will get invoked again
directly and we'll read the next chunk.

io_poll_multishot_retry() must only get called from inside
io_poll_issue(), which is our multishot retry handler, as we know we
already "own" the request at this point.

Cc: stable@vger.kernel.org
Link: https://github.com/axboe/liburing/issues/1041
Fixes: fc68fcda0491 ("io_uring/rw: add support for IORING_OP_READ_MULTISHOT")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/poll.h |  9 +++++++++
 io_uring/rw.c   | 10 +++++++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/io_uring/poll.h b/io_uring/poll.h
index ff4d5d753387e..1dacae9e816c9 100644
--- a/io_uring/poll.h
+++ b/io_uring/poll.h
@@ -24,6 +24,15 @@ struct async_poll {
 	struct io_poll		*double_poll;
 };
 
+/*
+ * Must only be called inside issue_flags & IO_URING_F_MULTISHOT, or
+ * potentially other cases where we already "own" this poll request.
+ */
+static inline void io_poll_multishot_retry(struct io_kiocb *req)
+{
+	atomic_inc(&req->poll_refs);
+}
+
 int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_poll_add(struct io_kiocb *req, unsigned int issue_flags);
 
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 118cc9f1cf160..d5e79d9bdc717 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -18,6 +18,7 @@
 #include "opdef.h"
 #include "kbuf.h"
 #include "rsrc.h"
+#include "poll.h"
 #include "rw.h"
 
 struct io_rw {
@@ -962,8 +963,15 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 		if (io_fill_cqe_req_aux(req,
 					issue_flags & IO_URING_F_COMPLETE_DEFER,
 					ret, cflags | IORING_CQE_F_MORE)) {
-			if (issue_flags & IO_URING_F_MULTISHOT)
+			if (issue_flags & IO_URING_F_MULTISHOT) {
+				/*
+				 * Force retry, as we might have more data to
+				 * be read and otherwise it won't get retried
+				 * until (if ever) another poll is triggered.
+				 */
+				io_poll_multishot_retry(req);
 				return IOU_ISSUE_SKIP_COMPLETE;
+			}
 			return -EAGAIN;
 		}
 	}
-- 
GitLab


From d6d33f03baa43d763fe094ca926eeae7d3421d07 Mon Sep 17 00:00:00 2001
From: Ism Hong <ism.hong@gmail.com>
Date: Tue, 26 Dec 2023 16:51:41 +0800
Subject: [PATCH 3581/4076] fs/ntfs3: use non-movable memory for ntfs3 MFT
 buffer cache

Since the buffer cache for ntfs3 metadata is not released until the file
system is unmounted, allocating from the movable zone may result in cma
allocation failures. This is due to the page still being used by ntfs3,
leading to migration failures.

To address this, this commit use sb_bread_umovable() instead of
sb_bread(). This change prevents allocation from the movable zone,
ensuring compatibility with scenarios where the buffer head is not
released until unmount. This patch is inspired by commit
a8ac900b8163("ext4: use non-movable memory for the ext4 superblock").

The issue is found when playing video files stored in NTFS on the
Android TV platform. During this process, the media parser reads the
video file, causing ntfs3 to allocate buffer cache from the CMA area.
Subsequently, the hardware decoder attempts to allocate memory from the
same CMA area. However, the page is still in use by ntfs3, resulting in
a migrate failure in alloc_contig_range().

The pinned page and allocating stacktrace reported by page owner shows
below:

page:ffffffff00b68880 refcount:3 mapcount:0 mapping:ffffff80046aa828
        index:0xc0040 pfn:0x20fa4
    aops:def_blk_aops ino:0
    flags: 0x2020(active|private)
    page dumped because: migration failure
    page last allocated via order 0, migratetype Movable,
        gfp_mask 0x108c48
        (GFP_NOFS|__GFP_NOFAIL|__GFP_HARDWALL|__GFP_MOVABLE),
    page_owner tracks the page as allocated
     prep_new_page
     get_page_from_freelist
     __alloc_pages_nodemask
     pagecache_get_page
     __getblk_gfp
     __bread_gfp
     ntfs_read_run_nb
     ntfs_read_bh
     mi_read
     ntfs_iget5
     dir_search_u
     ntfs_lookup
     __lookup_slow
     lookup_slow
     walk_component
     path_lookupat

Signed-off-by: Ism Hong <ism.hong@gmail.com>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/ntfs_fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index abbc7182554aa..2b54ae94440fb 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -1035,7 +1035,7 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size)
 static inline struct buffer_head *ntfs_bread(struct super_block *sb,
 					     sector_t block)
 {
-	struct buffer_head *bh = sb_bread(sb, block);
+	struct buffer_head *bh = sb_bread_unmovable(sb, block);
 
 	if (bh)
 		return bh;
-- 
GitLab


From 5ca87d01eba7bdfe9536a157ca33c1455bb8d16c Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 26 Jan 2024 11:03:21 +0300
Subject: [PATCH 3582/4076] fs/ntfs3: Prevent generic message "attempt to
 access beyond end of device"

It used in test environment.

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/fsntfs.c  | 24 ++++++++++++++++++++++++
 fs/ntfs3/ntfs_fs.h | 14 +-------------
 2 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 321978019407f..ae2ef5c11868c 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -1007,6 +1007,30 @@ static inline __le32 security_hash(const void *sd, size_t bytes)
 	return cpu_to_le32(hash);
 }
 
+/*
+ * simple wrapper for sb_bread_unmovable.
+ */
+struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block)
+{
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+	struct buffer_head *bh;
+
+	if (unlikely(block >= sbi->volume.blocks)) {
+		/* prevent generic message "attempt to access beyond end of device" */
+		ntfs_err(sb, "try to read out of volume at offset 0x%llx",
+			 (u64)block << sb->s_blocksize_bits);
+		return NULL;
+	}
+
+	bh = sb_bread_unmovable(sb, block);
+	if (bh)
+		return bh;
+
+	ntfs_err(sb, "failed to read volume at offset 0x%llx",
+		 (u64)block << sb->s_blocksize_bits);
+	return NULL;
+}
+
 int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer)
 {
 	struct block_device *bdev = sb->s_bdev;
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 2b54ae94440fb..81f7563428ee0 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -586,6 +586,7 @@ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes);
 int log_replay(struct ntfs_inode *ni, bool *initialized);
 
 /* Globals from fsntfs.c */
+struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block);
 bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes);
 int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes,
 		       bool simple);
@@ -1032,19 +1033,6 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size)
 	return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
 }
 
-static inline struct buffer_head *ntfs_bread(struct super_block *sb,
-					     sector_t block)
-{
-	struct buffer_head *bh = sb_bread_unmovable(sb, block);
-
-	if (bh)
-		return bh;
-
-	ntfs_err(sb, "failed to read volume at offset 0x%llx",
-		 (u64)block << sb->s_blocksize_bits);
-	return NULL;
-}
-
 static inline struct ntfs_inode *ntfs_i(struct inode *inode)
 {
 	return container_of(inode, struct ntfs_inode, vfs_inode);
-- 
GitLab


From 4fd6c08a16d7f1ba10212c9ef7bc73218144b463 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 26 Jan 2024 11:12:38 +0300
Subject: [PATCH 3583/4076] fs/ntfs3: Use i_size_read and i_size_write

Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/attrib.c  |  4 ++--
 fs/ntfs3/dir.c     |  2 +-
 fs/ntfs3/file.c    | 11 ++++++-----
 fs/ntfs3/frecord.c | 10 +++++-----
 fs/ntfs3/index.c   |  8 ++++----
 fs/ntfs3/inode.c   |  2 +-
 6 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 646e2dad1b757..7aadf50109994 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -2084,7 +2084,7 @@ next_attr:
 
 	/* Update inode size. */
 	ni->i_valid = valid_size;
-	ni->vfs_inode.i_size = data_size;
+	i_size_write(&ni->vfs_inode, data_size);
 	inode_set_bytes(&ni->vfs_inode, total_size);
 	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
 	mark_inode_dirty(&ni->vfs_inode);
@@ -2499,7 +2499,7 @@ int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	mi_b->dirty = true;
 
 done:
-	ni->vfs_inode.i_size += bytes;
+	i_size_write(&ni->vfs_inode, ni->vfs_inode.i_size + bytes);
 	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
 	mark_inode_dirty(&ni->vfs_inode);
 
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 9f6dd445eb04d..effa6accf8a85 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -517,7 +517,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 	u32 e_size, off, end;
 	size_t drs = 0, fles = 0, bit = 0;
 	struct indx_node *node = NULL;
-	size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits;
+	size_t max_indx = i_size_read(&ni->vfs_inode) >> ni->dir.index_bits;
 
 	if (is_empty)
 		*is_empty = true;
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 07ed3d946e7c5..b702543a87953 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -646,7 +646,7 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 			if (err)
 				goto out;
 		} else if (new_size > i_size) {
-			inode->i_size = new_size;
+			i_size_write(inode, new_size);
 		}
 	}
 
@@ -696,7 +696,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			goto out;
 		}
 		inode_dio_wait(inode);
-		oldsize = inode->i_size;
+		oldsize = i_size_read(inode);
 		newsize = attr->ia_size;
 
 		if (newsize <= oldsize)
@@ -708,7 +708,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			goto out;
 
 		ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
-		inode->i_size = newsize;
+		i_size_write(inode, newsize);
 	}
 
 	setattr_copy(idmap, inode, attr);
@@ -847,7 +847,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 	size_t count = iov_iter_count(from);
 	loff_t pos = iocb->ki_pos;
 	struct inode *inode = file_inode(file);
-	loff_t i_size = inode->i_size;
+	loff_t i_size = i_size_read(inode);
 	struct address_space *mapping = inode->i_mapping;
 	struct ntfs_inode *ni = ntfs_i(inode);
 	u64 valid = ni->i_valid;
@@ -1177,7 +1177,8 @@ static int ntfs_file_release(struct inode *inode, struct file *file)
 		down_write(&ni->file.run_lock);
 
 		err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run,
-				    inode->i_size, &ni->i_valid, false, NULL);
+				    i_size_read(inode), &ni->i_valid, false,
+				    NULL);
 
 		up_write(&ni->file.run_lock);
 		ni_unlock(ni);
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 2636ab7640ace..3b42938a9d3b2 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -2099,7 +2099,7 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page)
 	gfp_t gfp_mask;
 	struct page *pg;
 
-	if (vbo >= ni->vfs_inode.i_size) {
+	if (vbo >= i_size_read(&ni->vfs_inode)) {
 		SetPageUptodate(page);
 		err = 0;
 		goto out;
@@ -2173,7 +2173,7 @@ int ni_decompress_file(struct ntfs_inode *ni)
 {
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 	struct inode *inode = &ni->vfs_inode;
-	loff_t i_size = inode->i_size;
+	loff_t i_size = i_size_read(inode);
 	struct address_space *mapping = inode->i_mapping;
 	gfp_t gfp_mask = mapping_gfp_mask(mapping);
 	struct page **pages = NULL;
@@ -2457,6 +2457,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 	struct ATTR_LIST_ENTRY *le = NULL;
 	struct runs_tree *run = &ni->file.run;
 	u64 valid_size = ni->i_valid;
+	loff_t i_size = i_size_read(&ni->vfs_inode);
 	u64 vbo_disk;
 	size_t unc_size;
 	u32 frame_size, i, npages_disk, ondisk_size;
@@ -2548,7 +2549,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 			}
 		}
 
-		frames = (ni->vfs_inode.i_size - 1) >> frame_bits;
+		frames = (i_size - 1) >> frame_bits;
 
 		err = attr_wof_frame_info(ni, attr, run, frame64, frames,
 					  frame_bits, &ondisk_size, &vbo_data);
@@ -2556,8 +2557,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 			goto out2;
 
 		if (frame64 == frames) {
-			unc_size = 1 + ((ni->vfs_inode.i_size - 1) &
-					(frame_size - 1));
+			unc_size = 1 + ((i_size - 1) & (frame_size - 1));
 			ondisk_size = attr_size(attr) - vbo_data;
 		} else {
 			unc_size = frame_size;
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index cf92b2433f7a7..daabaad63aaf6 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -1462,7 +1462,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
 		goto out2;
 
 	if (in->name == I30_NAME) {
-		ni->vfs_inode.i_size = data_size;
+		i_size_write(&ni->vfs_inode, data_size);
 		inode_set_bytes(&ni->vfs_inode, alloc_size);
 	}
 
@@ -1544,7 +1544,7 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
 	}
 
 	if (in->name == I30_NAME)
-		ni->vfs_inode.i_size = data_size;
+		i_size_write(&ni->vfs_inode, data_size);
 
 	*vbn = bit << indx->idx2vbn_bits;
 
@@ -2090,7 +2090,7 @@ static int indx_shrink(struct ntfs_index *indx, struct ntfs_inode *ni,
 		return err;
 
 	if (in->name == I30_NAME)
-		ni->vfs_inode.i_size = new_data;
+		i_size_write(&ni->vfs_inode, new_data);
 
 	bpb = bitmap_size(bit);
 	if (bpb * 8 == nbits)
@@ -2576,7 +2576,7 @@ int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni,
 		err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len,
 				    &indx->alloc_run, 0, NULL, false, NULL);
 		if (in->name == I30_NAME)
-			ni->vfs_inode.i_size = 0;
+			i_size_write(&ni->vfs_inode, 0);
 
 		err = ni_remove_attr(ni, ATTR_ALLOC, in->name, in->name_len,
 				     false, NULL);
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 85452a6b1d40a..eb7a8c9fba018 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -985,7 +985,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
 		}
 
 		if (pos + err > inode->i_size) {
-			inode->i_size = pos + err;
+			i_size_write(inode, pos + err);
 			dirty = true;
 		}
 
-- 
GitLab


From 1b7dd28e14c4728ae1a815605ca33ffb4ce1b309 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 26 Jan 2024 11:13:59 +0300
Subject: [PATCH 3584/4076] fs/ntfs3: Correct function is_rst_area_valid

Reported-by: Robert Morris <rtm@csail.mit.edu>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/fslog.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 7dbb000fc6911..855519713bf79 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -465,7 +465,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
 {
 	const struct RESTART_AREA *ra;
 	u16 cl, fl, ul;
-	u32 off, l_size, file_dat_bits, file_size_round;
+	u32 off, l_size, seq_bits;
 	u16 ro = le16_to_cpu(rhdr->ra_off);
 	u32 sys_page = le32_to_cpu(rhdr->sys_page_size);
 
@@ -511,13 +511,15 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
 	/* Make sure the sequence number bits match the log file size. */
 	l_size = le64_to_cpu(ra->l_size);
 
-	file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits);
-	file_size_round = 1u << (file_dat_bits + 3);
-	if (file_size_round != l_size &&
-	    (file_size_round < l_size || (file_size_round / 2) > l_size)) {
-		return false;
+	seq_bits = sizeof(u64) * 8 + 3;
+	while (l_size) {
+		l_size >>= 1;
+		seq_bits -= 1;
 	}
 
+	if (seq_bits != ra->seq_num_bits)
+		return false;
+
 	/* The log page data offset and record header length must be quad-aligned. */
 	if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) ||
 	    !IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8))
-- 
GitLab


From 652cfeb43d6b9aba5c7c4902bed7a7340df131fb Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 26 Jan 2024 11:14:31 +0300
Subject: [PATCH 3585/4076] fs/ntfs3: Fixed overflow check in mi_enum_attr()

Reported-by: Robert Morris <rtm@csail.mit.edu>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/record.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index 7b6423584eaee..6aa3a9d44df1b 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -279,7 +279,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 		if (t16 > asize)
 			return NULL;
 
-		if (t16 + le32_to_cpu(attr->res.data_size) > asize)
+		if (le32_to_cpu(attr->res.data_size) > asize - t16)
 			return NULL;
 
 		t32 = sizeof(short) * attr->name_len;
-- 
GitLab


From d68968440b1a75dee05cfac7f368f1aa139e1911 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Mon, 29 Jan 2024 10:30:09 +0300
Subject: [PATCH 3586/4076] fs/ntfs3: Update inode->i_size after success write
 into compressed file

Reported-by: Giovanni Santini <giovannisantini93@yahoo.it>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/file.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index b702543a87953..691b0c9b95ae7 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -1054,6 +1054,8 @@ out:
 	iocb->ki_pos += written;
 	if (iocb->ki_pos > ni->i_valid)
 		ni->i_valid = iocb->ki_pos;
+	if (iocb->ki_pos > i_size)
+		i_size_write(inode, iocb->ki_pos);
 
 	return written;
 }
-- 
GitLab


From efb56d84dd9c3de3c99fc396abb57c6d330038b5 Mon Sep 17 00:00:00 2001
From: David Senoner <seda18@rolmail.net>
Date: Fri, 26 Jan 2024 16:56:26 +0100
Subject: [PATCH 3587/4076] ALSA: hda/realtek: Fix the external mic not being
 recognised for Acer Swift 1 SF114-32

If you connect an external headset/microphone to the 3.5mm jack on the
Acer Swift 1 SF114-32 it does not recognize the microphone. This fixes
that and gives the user the ability to choose between internal and
headset mic.

Signed-off-by: David Senoner <seda18@rolmail.net>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240126155626.2304465-1-seda18@rolmail.net
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index bfefe9ccbc6be..ef51e51fb6a51 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9655,6 +9655,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
 	SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1269, "Acer SWIFT SF314-54", ALC256_FIXUP_ACER_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x126a, "Acer Swift SF114-32", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
-- 
GitLab


From f0d78972f27dc1d1d51fbace2713ad3cdc60a877 Mon Sep 17 00:00:00 2001
From: Luka Guzenko <l.guzenko@web.de>
Date: Sun, 28 Jan 2024 16:57:04 +0100
Subject: [PATCH 3588/4076] ALSA: hda/realtek: Enable Mute LED on HP Laptop
 14-fq0xxx

This HP Laptop uses ALC236 codec with COEF 0x07 controlling the
mute LED. Enable existing quirk for this device.

Signed-off-by: Luka Guzenko <l.guzenko@web.de>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240128155704.2333812-1-l.guzenko@web.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index ef51e51fb6a51..bfa244028b994 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9856,6 +9856,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8786, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8787, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87e7, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
-- 
GitLab


From c0787fcff88bce36d21e5b726bdeab694baba6a5 Mon Sep 17 00:00:00 2001
From: Alexander Tsoy <alexander@tsoy.me>
Date: Sun, 28 Jan 2024 16:23:38 +0300
Subject: [PATCH 3589/4076] Revert "ALSA: usb-audio: Skip setting clock
 selector for single connections"

This reverts commit 67794f882adca00d043899ac248bc002751da9f6.

We need to explicitly set up the clock selector to workaround a problem
with the Behringer mixers. This was originally done in d2e8f641257d
("ALSA: usb-audio: Explicitly set up the clock selector")

The problem with MOTU M Series mentioned in commit message was fixed in
a different way by checking control capabilities of clock selectors.

Signed-off-by: Alexander Tsoy <alexander@tsoy.me>
Link: https://lore.kernel.org/r/20240128132338.819273-1-alexander@tsoy.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 7b259641adb51..a8204c6d6fac1 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -344,7 +344,7 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 		if (ret > 0) {
 			/* Skip setting clock selector again for some devices */
 			if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR ||
-			    pins == 1 || !writeable)
+			    !writeable)
 				return ret;
 			err = uac_clock_selector_set_val(chip, entity_id, cur);
 			if (err < 0)
-- 
GitLab


From 82ef1a5356572219f41f9123ca047259a77bd67b Mon Sep 17 00:00:00 2001
From: Andrey Albershteyn <aalbersh@redhat.com>
Date: Wed, 24 Jan 2024 11:26:44 +0100
Subject: [PATCH 3590/4076] xfs: reset XFS_ATTR_INCOMPLETE filter on node
 removal

In XFS_DAS_NODE_REMOVE_ATTR case, xfs_attr_mode_remove_attr() sets
filter to XFS_ATTR_INCOMPLETE. The filter is then reset in
xfs_attr_complete_op() if XFS_DA_OP_REPLACE operation is performed.

The filter is not reset though if XFS just removes the attribute
(args->value == NULL) with xfs_attr_defer_remove(). attr code goes
to XFS_DAS_DONE state.

Fix this by always resetting XFS_ATTR_INCOMPLETE filter. The replace
operation already resets this filter in anyway and others are
completed at this step hence don't need it.

Fixes: fdaf1bb3cafc ("xfs: ATTR_REPLACE algorithm with LARP enabled needs rework")
Signed-off-by: Andrey Albershteyn <aalbersh@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/libxfs/xfs_attr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 9976a00a73f99..e965a48e7db96 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -421,10 +421,10 @@ xfs_attr_complete_op(
 	bool			do_replace = args->op_flags & XFS_DA_OP_REPLACE;
 
 	args->op_flags &= ~XFS_DA_OP_REPLACE;
-	if (do_replace) {
-		args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+	args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+	if (do_replace)
 		return replace_state;
-	}
+
 	return XFS_DAS_DONE;
 }
 
-- 
GitLab


From 9c64e749cebd9c2d3d55261530a98bcccb83b950 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Tue, 23 Jan 2024 19:14:14 +0100
Subject: [PATCH 3591/4076] drm/virtio: Set segment size for virtio_gpu device

Set the segment size of the virtio_gpu device to the value
used by the drm helpers when allocating sg lists to fix the
following complaint from DMA_API debug code:

DMA-API: virtio-pci 0000:07:00.0: mapping sg segment longer than
device claims to support [len=262144] [max=65536]

Cc: stable@vger.kernel.org
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Acked-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
Signed-off-by: Sebastian Ott <sebott@redhat.com>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/7258a4cc-da16-5c34-a042-2a23ee396d56@redhat.com
---
 drivers/gpu/drm/virtio/virtgpu_drv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index f8e9abe647b92..9539aa28937fa 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -94,6 +94,7 @@ static int virtio_gpu_probe(struct virtio_device *vdev)
 			goto err_free;
 	}
 
+	dma_set_max_seg_size(dev->dev, dma_max_mapping_size(dev->dev) ?: UINT_MAX);
 	ret = virtio_gpu_init(vdev, dev);
 	if (ret)
 		goto err_free;
-- 
GitLab


From ebd4acc0cbeae9efea15993b11b05bd32942f3f0 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 23 Jan 2024 14:27:30 +0100
Subject: [PATCH 3592/4076] riscv: Fix wrong size passed to
 local_flush_tlb_range_asid()

local_flush_tlb_range_asid() takes the size as argument, not the end of
the range to flush, so fix this by computing the size from the end and
the start of the range.

Fixes: 7a92fc8b4d20 ("mm: Introduce flush_cache_vmap_early()")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
---
 arch/riscv/mm/tlbflush.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 8d12b26f5ac37..9619965f65018 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -68,7 +68,7 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 
 void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
 }
 
 static void __ipi_flush_tlb_all(void *info)
-- 
GitLab


From b2dd7b953c25ffd5912dda17e980e7168bebcf6c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 17 Oct 2023 17:04:39 +0300
Subject: [PATCH 3593/4076] fs/ntfs3: Fix an NULL dereference bug

The issue here is when this is called from ntfs_load_attr_list().  The
"size" comes from le32_to_cpu(attr->res.data_size) so it can't overflow
on a 64bit systems but on 32bit systems the "+ 1023" can overflow and
the result is zero.  This means that the kmalloc will succeed by
returning the ZERO_SIZE_PTR and then the memcpy() will crash with an
Oops on the next line.

Fixes: be71b5cba2e6 ("fs/ntfs3: Add attrib operations")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/ntfs_fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 81f7563428ee0..627419bd6f778 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -475,7 +475,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
 int al_update(struct ntfs_inode *ni, int sync);
 static inline size_t al_aligned(size_t size)
 {
-	return (size + 1023) & ~(size_t)1023;
+	return size_add(size, 1023) & ~(size_t)1023;
 }
 
 /* Globals from bitfunc.c */
-- 
GitLab


From 731ab1f9828800df871c5a7ab9ffe965317d3f15 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Sat, 30 Dec 2023 17:00:03 +0800
Subject: [PATCH 3594/4076] fs/ntfs3: Fix oob in ntfs_listxattr

The length of name cannot exceed the space occupied by ea.

Reported-and-tested-by: syzbot+65e940cfb8f99a97aca7@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/xattr.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 071356d096d83..53e7d1fa036aa 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -219,6 +219,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
 		if (!ea->name_len)
 			break;
 
+		if (ea->name_len > ea_size)
+			break;
+
 		if (buffer) {
 			/* Check if we can use field ea->name */
 			if (off + ea_size > size)
-- 
GitLab


From 1f5fa4b3b85ceb43f1053290f0ade037b50e6297 Mon Sep 17 00:00:00 2001
From: Nekun <nekokun@firemail.cc>
Date: Mon, 30 Oct 2023 08:33:54 +0000
Subject: [PATCH 3595/4076] fs/ntfs3: Add ioctl operation for directories
 (FITRIM)

While ntfs3 supports discards, FITRIM ioctl() command has defined
only for regular files. This may confuse users trying to invoke
`fstrim` utility with the directory argument (for example, call
`fstrim <mountpoint>` which is the common practice). In this case,
ioctl() returns -ENOTTY without any error messages in kernel ring
buffer, this may be easily interpreted as no support for discards
in ntfs3 driver.

Currently only FITRIM command implemented in ntfs_ioctl() and
passed inode used only for dereferencing NTFS superblock, so
no need for separate ioctl() handler for directories, just add
existing ntfs_ioctl() handler to ntfs_dir_operations.

Signed-off-by: Nekun <nekokun@firemail.cc>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/dir.c     | 4 ++++
 fs/ntfs3/file.c    | 4 ++--
 fs/ntfs3/ntfs_fs.h | 2 ++
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index effa6accf8a85..5cf3d9decf646 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -611,5 +611,9 @@ const struct file_operations ntfs_dir_operations = {
 	.iterate_shared	= ntfs_readdir,
 	.fsync		= generic_file_fsync,
 	.open		= ntfs_file_open,
+	.unlocked_ioctl = ntfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = ntfs_compat_ioctl,
+#endif
 };
 // clang-format on
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 691b0c9b95ae7..5418662c80d88 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -48,7 +48,7 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg)
 	return 0;
 }
 
-static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
@@ -61,7 +61,7 @@ static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 }
 
 #ifdef CONFIG_COMPAT
-static long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 
 {
 	return ntfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 627419bd6f778..79356fd29a141 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -502,6 +502,8 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 int ntfs_file_open(struct inode *inode, struct file *file);
 int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len);
+long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg);
+long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg);
 extern const struct inode_operations ntfs_special_inode_operations;
 extern const struct inode_operations ntfs_file_inode_operations;
 extern const struct file_operations ntfs_file_operations;
-- 
GitLab


From 622cd3daa8eae37359a6fd3c07c36d19f66606b5 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 10 Nov 2023 20:59:22 +0100
Subject: [PATCH 3596/4076] fs/ntfs3: Slightly simplify ntfs_inode_printk()

The size passed to snprintf() includes the space for the trailing space.
So there is no reason here not to use all the available space.

So remove the -1 when computing 'name_len'.
While at it, use the size of the array directly instead of the intermediate
'name_len' variable.

snprintf() also guaranties that the buffer if NULL terminated, so there is
no need to write an additional trailing NULL "To be sure".

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
 fs/ntfs3/super.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index c55a29793a8d8..cef5467fd9283 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -122,13 +122,12 @@ void ntfs_inode_printk(struct inode *inode, const char *fmt, ...)
 
 	if (name) {
 		struct dentry *de = d_find_alias(inode);
-		const u32 name_len = ARRAY_SIZE(s_name_buf) - 1;
 
 		if (de) {
 			spin_lock(&de->d_lock);
-			snprintf(name, name_len, " \"%s\"", de->d_name.name);
+			snprintf(name, sizeof(s_name_buf), " \"%s\"",
+				 de->d_name.name);
 			spin_unlock(&de->d_lock);
-			name[name_len] = 0; /* To be sure. */
 		} else {
 			name[0] = 0;
 		}
-- 
GitLab


From 8eed4e00a370b37b4e5985ed983dccedd555ea9d Mon Sep 17 00:00:00 2001
From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Date: Mon, 29 Jan 2024 14:38:42 +0800
Subject: [PATCH 3597/4076] x86/lib: Revert to _ASM_EXTABLE_UA() for
 {get,put}_user() fixups

During memory error injection test on kernels >= v6.4, the kernel panics
like below. However, this issue couldn't be reproduced on kernels <= v6.3.

  mce: [Hardware Error]: CPU 296: Machine Check Exception: f Bank 1: bd80000000100134
  mce: [Hardware Error]: RIP 10:<ffffffff821b9776> {__get_user_nocheck_4+0x6/0x20}
  mce: [Hardware Error]: TSC 411a93533ed ADDR 346a8730040 MISC 86
  mce: [Hardware Error]: PROCESSOR 0:a06d0 TIME 1706000767 SOCKET 1 APIC 211 microcode 80001490
  mce: [Hardware Error]: Run the above through 'mcelog --ascii'
  mce: [Hardware Error]: Machine check: Data load in unrecoverable area of kernel
  Kernel panic - not syncing: Fatal local machine check

The MCA code can recover from an in-kernel #MC if the fixup type is
EX_TYPE_UACCESS, explicitly indicating that the kernel is attempting to
access userspace memory. However, if the fixup type is EX_TYPE_DEFAULT
the only thing that is raised for an in-kernel #MC is a panic.

ex_handler_uaccess() would warn if users gave a non-canonical addresses
(with bit 63 clear) to {get, put}_user(), which was unexpected.

Therefore, commit

  b19b74bc99b1 ("x86/mm: Rework address range check in get_user() and put_user()")

replaced _ASM_EXTABLE_UA() with _ASM_EXTABLE() for {get, put}_user()
fixups. However, the new fixup type EX_TYPE_DEFAULT results in a panic.

Commit

  6014bc27561f ("x86-64: make access_ok() independent of LAM")

added the check gp_fault_address_ok() right before the WARN_ONCE() in
ex_handler_uaccess() to not warn about non-canonical user addresses due
to LAM.

With that in place, revert back to _ASM_EXTABLE_UA() for {get,put}_user()
exception fixups in order to be able to handle in-kernel MCEs correctly
again.

  [ bp: Massage commit message. ]

Fixes: b19b74bc99b1 ("x86/mm: Rework address range check in get_user() and put_user()")
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20240129063842.61584-1-qiuxu.zhuo@intel.com
---
 arch/x86/lib/getuser.S | 24 ++++++++++++------------
 arch/x86/lib/putuser.S | 20 ++++++++++----------
 2 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 20ef350a60fbb..10d5ed8b5990f 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -163,23 +163,23 @@ SYM_CODE_END(__get_user_8_handle_exception)
 #endif
 
 /* get_user */
-	_ASM_EXTABLE(1b, __get_user_handle_exception)
-	_ASM_EXTABLE(2b, __get_user_handle_exception)
-	_ASM_EXTABLE(3b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(1b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(4b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(4b, __get_user_8_handle_exception)
-	_ASM_EXTABLE(5b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(4b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(5b, __get_user_8_handle_exception)
 #endif
 
 /* __get_user */
-	_ASM_EXTABLE(6b, __get_user_handle_exception)
-	_ASM_EXTABLE(7b, __get_user_handle_exception)
-	_ASM_EXTABLE(8b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(8b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(9b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(9b, __get_user_8_handle_exception)
-	_ASM_EXTABLE(10b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(9b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(10b, __get_user_8_handle_exception)
 #endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 2877f59341775..975c9c18263d2 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -133,15 +133,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception)
 	RET
 SYM_CODE_END(__put_user_handle_exception)
 
-	_ASM_EXTABLE(1b, __put_user_handle_exception)
-	_ASM_EXTABLE(2b, __put_user_handle_exception)
-	_ASM_EXTABLE(3b, __put_user_handle_exception)
-	_ASM_EXTABLE(4b, __put_user_handle_exception)
-	_ASM_EXTABLE(5b, __put_user_handle_exception)
-	_ASM_EXTABLE(6b, __put_user_handle_exception)
-	_ASM_EXTABLE(7b, __put_user_handle_exception)
-	_ASM_EXTABLE(9b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(1b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(5b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __put_user_handle_exception)
 #ifdef CONFIG_X86_32
-	_ASM_EXTABLE(8b, __put_user_handle_exception)
-	_ASM_EXTABLE(10b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(8b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(10b, __put_user_handle_exception)
 #endif
-- 
GitLab


From 37e8c97e539015637cb920d3e6f1e404f707a06e Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Wed, 24 Jan 2024 02:21:47 -0800
Subject: [PATCH 3598/4076] net: hsr: remove WARN_ONCE() in
 send_hsr_supervision_frame()

Syzkaller reported [1] hitting a warning after failing to allocate
resources for skb in hsr_init_skb(). Since a WARN_ONCE() call will
not help much in this case, it might be prudent to switch to
netdev_warn_once(). At the very least it will suppress syzkaller
reports such as [1].

Just in case, use netdev_warn_once() in send_prp_supervision_frame()
for similar reasons.

[1]
HSR: Could not send supervision frame
WARNING: CPU: 1 PID: 85 at net/hsr/hsr_device.c:294 send_hsr_supervision_frame+0x60a/0x810 net/hsr/hsr_device.c:294
RIP: 0010:send_hsr_supervision_frame+0x60a/0x810 net/hsr/hsr_device.c:294
...
Call Trace:
 <IRQ>
 hsr_announce+0x114/0x370 net/hsr/hsr_device.c:382
 call_timer_fn+0x193/0x590 kernel/time/timer.c:1700
 expire_timers kernel/time/timer.c:1751 [inline]
 __run_timers+0x764/0xb20 kernel/time/timer.c:2022
 run_timer_softirq+0x58/0xd0 kernel/time/timer.c:2035
 __do_softirq+0x21a/0x8de kernel/softirq.c:553
 invoke_softirq kernel/softirq.c:427 [inline]
 __irq_exit_rcu kernel/softirq.c:632 [inline]
 irq_exit_rcu+0xb7/0x120 kernel/softirq.c:644
 sysvec_apic_timer_interrupt+0x95/0xb0 arch/x86/kernel/apic/apic.c:1076
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:649
...

This issue is also found in older kernels (at least up to 5.10).

Cc: stable@vger.kernel.org
Reported-by: syzbot+3ae0a3f42c84074b7c8e@syzkaller.appspotmail.com
Fixes: 121c33b07b31 ("net: hsr: introduce common code for skb initialization")
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 7ceb9ac6e7309..9d71b66183daf 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -308,7 +308,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
 
 	skb = hsr_init_skb(master);
 	if (!skb) {
-		WARN_ONCE(1, "HSR: Could not send supervision frame\n");
+		netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n");
 		return;
 	}
 
@@ -355,7 +355,7 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 
 	skb = hsr_init_skb(master);
 	if (!skb) {
-		WARN_ONCE(1, "PRP: Could not send supervision frame\n");
+		netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n");
 		return;
 	}
 
-- 
GitLab


From bfb007aebe6bff451f7f3a4be19f4f286d0d5d9c Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Thu, 25 Jan 2024 12:53:09 +0300
Subject: [PATCH 3599/4076] nfc: nci: free rx_data_reassembly skb on NCI device
 cleanup

rx_data_reassembly skb is stored during NCI data exchange for processing
fragmented packets. It is dropped only when the last fragment is processed
or when an NTF packet with NCI_OP_RF_DEACTIVATE_NTF opcode is received.
However, the NCI device may be deallocated before that which leads to skb
leak.

As by design the rx_data_reassembly skb is bound to the NCI device and
nothing prevents the device to be freed before the skb is processed in
some way and cleaned, free it on the NCI device cleanup.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 6a2968aaf50c ("NFC: basic NCI protocol implementation")
Cc: stable@vger.kernel.org
Reported-by: syzbot+6b7c68d9c21e4ee4251b@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/000000000000f43987060043da7b@google.com/
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/nci/core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 97348cedb16b3..cdad47b140fa4 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1208,6 +1208,10 @@ void nci_free_device(struct nci_dev *ndev)
 {
 	nfc_free_device(ndev->nfc_dev);
 	nci_hci_deallocate(ndev);
+
+	/* drop partial rx data packet if present */
+	if (ndev->rx_data_reassembly)
+		kfree_skb(ndev->rx_data_reassembly);
 	kfree(ndev);
 }
 EXPORT_SYMBOL(nci_free_device);
-- 
GitLab


From 577e4432f3ac810049cb7e6b71f4d96ec7c6e894 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 25 Jan 2024 10:33:17 +0000
Subject: [PATCH 3600/4076] tcp: add sanity checks to rx zerocopy

TCP rx zerocopy intent is to map pages initially allocated
from NIC drivers, not pages owned by a fs.

This patch adds to can_map_frag() these additional checks:

- Page must not be a compound one.
- page->mapping must be NULL.

This fixes the panic reported by ZhangPeng.

syzbot was able to loopback packets built with sendfile(),
mapping pages owned by an ext4 file to TCP rx zerocopy.

r3 = socket$inet_tcp(0x2, 0x1, 0x0)
mmap(&(0x7f0000ff9000/0x4000)=nil, 0x4000, 0x0, 0x12, r3, 0x0)
r4 = socket$inet_tcp(0x2, 0x1, 0x0)
bind$inet(r4, &(0x7f0000000000)={0x2, 0x4e24, @multicast1}, 0x10)
connect$inet(r4, &(0x7f00000006c0)={0x2, 0x4e24, @empty}, 0x10)
r5 = openat$dir(0xffffffffffffff9c, &(0x7f00000000c0)='./file0\x00',
    0x181e42, 0x0)
fallocate(r5, 0x0, 0x0, 0x85b8)
sendfile(r4, r5, 0x0, 0x8ba0)
getsockopt$inet_tcp_TCP_ZEROCOPY_RECEIVE(r4, 0x6, 0x23,
    &(0x7f00000001c0)={&(0x7f0000ffb000/0x3000)=nil, 0x3000, 0x0, 0x0, 0x0,
    0x0, 0x0, 0x0, 0x0}, &(0x7f0000000440)=0x40)
r6 = openat$dir(0xffffffffffffff9c, &(0x7f00000000c0)='./file0\x00',
    0x181e42, 0x0)

Fixes: 93ab6cc69162 ("tcp: implement mmap() for zero copy receive")
Link: https://lore.kernel.org/netdev/5106a58e-04da-372a-b836-9d3d0bd2507b@huawei.com/T/
Reported-and-bisected-by: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Arjun Roy <arjunroy@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: linux-mm@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a1c6de385ccef..7e2481b9eae1b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1786,7 +1786,17 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
 
 static bool can_map_frag(const skb_frag_t *frag)
 {
-	return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag);
+	struct page *page;
+
+	if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag))
+		return false;
+
+	page = skb_frag_page(frag);
+
+	if (PageCompound(page) || page->mapping)
+		return false;
+
+	return true;
 }
 
 static int find_next_mappable_frag(const skb_frag_t *frag,
-- 
GitLab


From c92c108403b09f75f3393588c2326ecad49ee2e2 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 19 Jan 2024 03:08:37 -0600
Subject: [PATCH 3601/4076] Revert "drm/amd/pm: fix the high voltage and
 temperature issue"

This reverts commit 5f38ac54e60562323ea4abb1bfb37d043ee23357.
This causes issues with rebooting and the 7800XT.

Cc: Kenneth Feng <kenneth.feng@amd.com>
Cc: stable@vger.kernel.org
Fixes: 5f38ac54e605 ("drm/amd/pm: fix the high voltage and temperature issue")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3062
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    | 24 ++++----------
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c     | 33 ++-----------------
 drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h |  1 -
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c  |  8 +----
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c  |  8 +----
 5 files changed, 11 insertions(+), 63 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b158d27d0a71c..31b28e6f35b26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4121,23 +4121,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 				}
 			}
 		} else {
-			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-			case IP_VERSION(13, 0, 0):
-			case IP_VERSION(13, 0, 7):
-			case IP_VERSION(13, 0, 10):
-				r = psp_gpu_reset(adev);
-				break;
-			default:
-				tmp = amdgpu_reset_method;
-				/* It should do a default reset when loading or reloading the driver,
-				 * regardless of the module parameter reset_method.
-				 */
-				amdgpu_reset_method = AMD_RESET_METHOD_NONE;
-				r = amdgpu_asic_reset(adev);
-				amdgpu_reset_method = tmp;
-				break;
-			}
-
+			tmp = amdgpu_reset_method;
+			/* It should do a default reset when loading or reloading the driver,
+			 * regardless of the module parameter reset_method.
+			 */
+			amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+			r = amdgpu_asic_reset(adev);
+			amdgpu_reset_method = tmp;
 			if (r) {
 				dev_err(adev->dev, "asic reset on init failed\n");
 				goto failed;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 7ffad3eb0a015..0ad947df777ab 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -734,7 +734,7 @@ static int smu_early_init(void *handle)
 	smu->adev = adev;
 	smu->pm_enabled = !!amdgpu_dpm;
 	smu->is_apu = false;
-	smu->smu_baco.state = SMU_BACO_STATE_NONE;
+	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
 	smu->smu_baco.platform_support = false;
 	smu->user_dpm_profile.fan_mode = -1;
 
@@ -1954,31 +1954,10 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_reset_mp1_state(struct smu_context *smu)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0;
-
-	if ((!adev->in_runpm) && (!adev->in_suspend) &&
-		(!amdgpu_in_reset(adev)))
-		switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-		case IP_VERSION(13, 0, 0):
-		case IP_VERSION(13, 0, 7):
-		case IP_VERSION(13, 0, 10):
-			ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD);
-			break;
-		default:
-			break;
-		}
-
-	return ret;
-}
-
 static int smu_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = adev->powerplay.pp_handle;
-	int ret;
 
 	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return 0;
@@ -1996,15 +1975,7 @@ static int smu_hw_fini(void *handle)
 
 	adev->pm.dpm_enabled = false;
 
-	ret = smu_smc_hw_cleanup(smu);
-	if (ret)
-		return ret;
-
-	ret = smu_reset_mp1_state(smu);
-	if (ret)
-		return ret;
-
-	return 0;
+	return smu_smc_hw_cleanup(smu);
 }
 
 static void smu_late_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 2aa4fea873147..66e84defd0b6e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -424,7 +424,6 @@ enum smu_reset_mode {
 enum smu_baco_state {
 	SMU_BACO_STATE_ENTER = 0,
 	SMU_BACO_STATE_EXIT,
-	SMU_BACO_STATE_NONE,
 };
 
 struct smu_baco_context {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 4fdf34fffa9a5..3230701d0d381 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2748,13 +2748,7 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		ret = smu_cmn_send_smc_msg_with_param(smu,
-											  SMU_MSG_PrepareMp1ForUnload,
-											  0x55, NULL);
-
-		if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
-			ret = smu_v13_0_disable_pmfw_state(smu);
-
+		ret = smu_cmn_set_mp1_state(smu, mp1_state);
 		break;
 	default:
 		/* Ignore others */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 7c3e162e2d818..0ffdb58af74e6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2505,13 +2505,7 @@ static int smu_v13_0_7_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		ret = smu_cmn_send_smc_msg_with_param(smu,
-											  SMU_MSG_PrepareMp1ForUnload,
-											  0x55, NULL);
-
-		if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
-			ret = smu_v13_0_disable_pmfw_state(smu);
-
+		ret = smu_cmn_set_mp1_state(smu, mp1_state);
 		break;
 	default:
 		/* Ignore others */
-- 
GitLab


From e42e29cc442395d62f1a8963ec2dfb700ba6a5d7 Mon Sep 17 00:00:00 2001
From: Dave Kleikamp <dave.kleikamp@oracle.com>
Date: Mon, 29 Jan 2024 08:40:23 -0600
Subject: [PATCH 3602/4076] Revert "jfs: fix shift-out-of-bounds in dbJoin"

This reverts commit cca974daeb6c43ea971f8ceff5a7080d7d49ee30.

The added sanity check is incorrect. BUDMIN is not the wrong value and
is too small.

Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
---
 fs/jfs/jfs_dmap.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index 8eec84c651bfb..cb3cda1390adb 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -2763,9 +2763,7 @@ static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl)
  *	leafno	- the number of the leaf to be updated.
  *	newval	- the new value for the leaf.
  *
- * RETURN VALUES:
- *  0		- success
- *	-EIO	- i/o error
+ * RETURN VALUES: none
  */
 static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 {
@@ -2792,10 +2790,6 @@ static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 		 * get the buddy size (number of words covered) of
 		 * the new value.
 		 */
-
-		if ((newval - tp->dmt_budmin) > BUDMIN)
-			return -EIO;
-
 		budsz = BUDSIZE(newval, tp->dmt_budmin);
 
 		/* try to join.
-- 
GitLab


From 6d3c7fb17b4c047ccd0b42cf1308da693ab45acb Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 24 Jan 2024 09:27:27 -0800
Subject: [PATCH 3603/4076] nvme: use ctrl state accessor

The ctrl->state value is updated in another thread using WRITE_ONCE, so
ensure all the readers use the appropriate accessor.

Reviewed-by: Sagi Grimberg <sagi@grmberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/apple.c     | 13 +++++++------
 drivers/nvme/host/auth.c      |  2 +-
 drivers/nvme/host/core.c      |  4 ++--
 drivers/nvme/host/fabrics.h   |  8 +++++---
 drivers/nvme/host/multipath.c | 15 ++++++++-------
 drivers/nvme/host/nvme.h      | 11 ++++++-----
 drivers/nvme/host/sysfs.c     |  6 +++---
 drivers/nvme/target/loop.c    |  8 +++++---
 8 files changed, 37 insertions(+), 30 deletions(-)

diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 596bb11eeba5a..c727cd1f264bf 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -797,6 +797,7 @@ static int apple_nvme_init_request(struct blk_mq_tag_set *set,
 
 static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl);
 	u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS);
 	bool dead = false, freeze = false;
 	unsigned long flags;
@@ -808,8 +809,8 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 	if (csts & NVME_CSTS_CFS)
 		dead = true;
 
-	if (anv->ctrl.state == NVME_CTRL_LIVE ||
-	    anv->ctrl.state == NVME_CTRL_RESETTING) {
+	if (state == NVME_CTRL_LIVE ||
+	    state == NVME_CTRL_RESETTING) {
 		freeze = true;
 		nvme_start_freeze(&anv->ctrl);
 	}
@@ -881,7 +882,7 @@ static enum blk_eh_timer_return apple_nvme_timeout(struct request *req)
 	unsigned long flags;
 	u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS);
 
-	if (anv->ctrl.state != NVME_CTRL_LIVE) {
+	if (nvme_ctrl_state(&anv->ctrl) != NVME_CTRL_LIVE) {
 		/*
 		 * From rdma.c:
 		 * If we are resetting, connecting or deleting we should
@@ -985,10 +986,10 @@ static void apple_nvme_reset_work(struct work_struct *work)
 	u32 boot_status, aqa;
 	struct apple_nvme *anv =
 		container_of(work, struct apple_nvme, ctrl.reset_work);
+	enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl);
 
-	if (anv->ctrl.state != NVME_CTRL_RESETTING) {
-		dev_warn(anv->dev, "ctrl state %d is not RESETTING\n",
-			 anv->ctrl.state);
+	if (state != NVME_CTRL_RESETTING) {
+		dev_warn(anv->dev, "ctrl state %d is not RESETTING\n", state);
 		ret = -ENODEV;
 		goto out;
 	}
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index 72c0525c75f50..2a12ee878783f 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -897,7 +897,7 @@ static void nvme_ctrl_auth_work(struct work_struct *work)
 	 * If the ctrl is no connected, bail as reconnect will handle
 	 * authentication.
 	 */
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	/* Authenticate admin queue first */
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0810be0d1154c..a42c347d08e87 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -721,7 +721,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
 
 bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live)
+		bool queue_live, enum nvme_ctrl_state state)
 {
 	struct nvme_request *req = nvme_req(rq);
 
@@ -742,7 +742,7 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		 * command, which is require to set the queue live in the
 		 * appropinquate states.
 		 */
-		switch (nvme_ctrl_state(ctrl)) {
+		switch (state) {
 		case NVME_CTRL_CONNECTING:
 			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 			    (req->cmd->fabrics.fctype == nvme_fabrics_type_connect ||
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index fbaee5a7be196..06cc54851b1be 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -185,9 +185,11 @@ static inline bool
 nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
 			struct nvmf_ctrl_options *opts)
 {
-	if (ctrl->state == NVME_CTRL_DELETING ||
-	    ctrl->state == NVME_CTRL_DELETING_NOIO ||
-	    ctrl->state == NVME_CTRL_DEAD ||
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (state == NVME_CTRL_DELETING ||
+	    state == NVME_CTRL_DELETING_NOIO ||
+	    state == NVME_CTRL_DEAD ||
 	    strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
 	    strcmp(opts->host->nqn, ctrl->opts->host->nqn) ||
 	    !uuid_equal(&opts->host->id, &ctrl->opts->host->id))
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 2dd4137a08b28..74de1e64aeead 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -156,7 +156,7 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 		if (!ns->head->disk)
 			continue;
 		kblockd_schedule_work(&ns->head->requeue_work);
-		if (ctrl->state == NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 			disk_uevent(ns->head->disk, KOBJ_CHANGE);
 	}
 	up_read(&ctrl->namespaces_rwsem);
@@ -223,13 +223,14 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(ns->ctrl);
+
 	/*
 	 * We don't treat NVME_CTRL_DELETING as a disabled path as I/O should
 	 * still be able to complete assuming that the controller is connected.
 	 * Otherwise it will fail immediately and return to the requeue list.
 	 */
-	if (ns->ctrl->state != NVME_CTRL_LIVE &&
-	    ns->ctrl->state != NVME_CTRL_DELETING)
+	if (state != NVME_CTRL_LIVE && state != NVME_CTRL_DELETING)
 		return true;
 	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
 	    !test_bit(NVME_NS_READY, &ns->flags))
@@ -331,7 +332,7 @@ out:
 
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
-	return ns->ctrl->state == NVME_CTRL_LIVE &&
+	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
 		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
@@ -358,7 +359,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
 		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
 			continue;
-		switch (ns->ctrl->state) {
+		switch (nvme_ctrl_state(ns->ctrl)) {
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
@@ -667,7 +668,7 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	 * controller is ready.
 	 */
 	if (nvme_state_is_live(ns->ana_state) &&
-	    ns->ctrl->state == NVME_CTRL_LIVE)
+	    nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
 }
 
@@ -748,7 +749,7 @@ static void nvme_ana_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	nvme_read_ana_log(ctrl);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 030c808182406..1700063bc24de 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -805,17 +805,18 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req);
 blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *req);
 bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live);
+		bool queue_live, enum nvme_ctrl_state state);
 
 static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live)
 {
-	if (likely(ctrl->state == NVME_CTRL_LIVE))
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (likely(state == NVME_CTRL_LIVE))
 		return true;
-	if (ctrl->ops->flags & NVME_F_FABRICS &&
-	    ctrl->state == NVME_CTRL_DELETING)
+	if (ctrl->ops->flags & NVME_F_FABRICS && state == NVME_CTRL_DELETING)
 		return queue_live;
-	return __nvme_check_ready(ctrl, rq, queue_live);
+	return __nvme_check_ready(ctrl, rq, queue_live, state);
 }
 
 /*
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 754e911110420..6b2f06f190de3 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -311,6 +311,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 				     char *buf)
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned state = (unsigned)nvme_ctrl_state(ctrl);
 	static const char *const state_name[] = {
 		[NVME_CTRL_NEW]		= "new",
 		[NVME_CTRL_LIVE]	= "live",
@@ -321,9 +322,8 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 		[NVME_CTRL_DEAD]	= "dead",
 	};
 
-	if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
-	    state_name[ctrl->state])
-		return sysfs_emit(buf, "%s\n", state_name[ctrl->state]);
+	if (state < ARRAY_SIZE(state_name) && state_name[state])
+		return sysfs_emit(buf, "%s\n", state_name[state]);
 
 	return sysfs_emit(buf, "unknown state\n");
 }
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 2b2e0d00af85e..e589915ddef85 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -400,7 +400,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 	}
 
 	nvme_quiesce_admin_queue(&ctrl->ctrl);
-	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE)
 		nvme_disable_ctrl(&ctrl->ctrl, true);
 
 	nvme_cancel_admin_tagset(&ctrl->ctrl);
@@ -434,8 +434,10 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 	nvme_loop_shutdown_ctrl(ctrl);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
-		if (ctrl->ctrl.state != NVME_CTRL_DELETING &&
-		    ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO)
+		enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
+		if (state != NVME_CTRL_DELETING &&
+		    state != NVME_CTRL_DELETING_NOIO)
 			/* state change failure for non-deleted ctrl? */
 			WARN_ON_ONCE(1);
 		return;
-- 
GitLab


From 346f59d1e8ed0eed41c80e1acb657e484c308e6a Mon Sep 17 00:00:00 2001
From: Alexander Tsoy <alexander@tsoy.me>
Date: Mon, 29 Jan 2024 15:12:54 +0300
Subject: [PATCH 3604/4076] ALSA: usb-audio: Check presence of valid altsetting
 control

Many devices with a single alternate setting do not have a Valid
Alternate Setting Control and validation performed by
validate_sample_rate_table_v2v3() doesn't work on them and is not
really needed. So check the presense of control before sending
altsetting validation requests.

MOTU Microbook IIc is suffering the most without this check. It
takes up to 40 seconds to bootup due to how slow it switches
sampling rates:

[ 2659.164824] usb 3-2: New USB device found, idVendor=07fd, idProduct=0004, bcdDevice= 0.60
[ 2659.164827] usb 3-2: New USB device strings: Mfr=1, Product=2, SerialNumber=0
[ 2659.164829] usb 3-2: Product: MicroBook IIc
[ 2659.164830] usb 3-2: Manufacturer: MOTU
[ 2659.166204] usb 3-2: Found last interface = 3
[ 2679.322298] usb 3-2: No valid sample rate available for 1:1, assuming a firmware bug
[ 2679.322306] usb 3-2: 1:1: add audio endpoint 0x3
[ 2679.322321] usb 3-2: Creating new data endpoint #3
[ 2679.322552] usb 3-2: 1:1 Set sample rate 96000, clock 1
[ 2684.362250] usb 3-2: 2:1: cannot get freq (v2/v3): err -110
[ 2694.444700] usb 3-2: No valid sample rate available for 2:1, assuming a firmware bug
[ 2694.444707] usb 3-2: 2:1: add audio endpoint 0x84
[ 2694.444721] usb 3-2: Creating new data endpoint #84
[ 2699.482103] usb 3-2: 2:1 Set sample rate 96000, clock 1

Signed-off-by: Alexander Tsoy <alexander@tsoy.me>
Link: https://lore.kernel.org/r/20240129121254.3454481-1-alexander@tsoy.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/format.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/sound/usb/format.c b/sound/usb/format.c
index ab5fed9f55b60..3b45d0ee76938 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -470,9 +470,11 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip,
 					   int clock)
 {
 	struct usb_device *dev = chip->dev;
+	struct usb_host_interface *alts;
 	unsigned int *table;
 	unsigned int nr_rates;
 	int i, err;
+	u32 bmControls;
 
 	/* performing the rate verification may lead to unexpected USB bus
 	 * behavior afterwards by some unknown reason.  Do this only for the
@@ -481,6 +483,24 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip,
 	if (!(chip->quirk_flags & QUIRK_FLAG_VALIDATE_RATES))
 		return 0; /* don't perform the validation as default */
 
+	alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting);
+	if (!alts)
+		return 0;
+
+	if (fp->protocol == UAC_VERSION_3) {
+		struct uac3_as_header_descriptor *as = snd_usb_find_csint_desc(
+				alts->extra, alts->extralen, NULL, UAC_AS_GENERAL);
+		bmControls = le32_to_cpu(as->bmControls);
+	} else {
+		struct uac2_as_header_descriptor *as = snd_usb_find_csint_desc(
+				alts->extra, alts->extralen, NULL, UAC_AS_GENERAL);
+		bmControls = as->bmControls;
+	}
+
+	if (!uac_v2v3_control_is_readable(bmControls,
+				UAC2_AS_VAL_ALT_SETTINGS))
+		return 0;
+
 	table = kcalloc(fp->nr_rates, sizeof(*table), GFP_KERNEL);
 	if (!table)
 		return -ENOMEM;
-- 
GitLab


From 21fdd8dd3726199451fc495f20104356e071a997 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 29 Jan 2024 13:00:07 -0300
Subject: [PATCH 3605/4076] tools headers UAPI: Sync unistd.h to pick
 {list,stat}mount, lsm_{[gs]et_self_attr,list_modules} syscall numbers

To pick the changes in these csets:

  d8b0f5465012538c ("wire up syscalls for statmount/listmount")
  5f42375904b08890 ("LSM: wireup Linux Security Module syscalls")

Used in some architectures to create syscall tables.

This addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h

Cc: Casey Schaufler <casey@schaufler-ca.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZbfMuAlUMRO9Hqa6@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/asm-generic/unistd.h | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 756b013fb8324..75f00965ab158 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -829,8 +829,21 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
+#define __NR_statmount   457
+__SYSCALL(__NR_statmount, sys_statmount)
+
+#define __NR_listmount   458
+__SYSCALL(__NR_listmount, sys_listmount)
+
+#define __NR_lsm_get_self_attr 459
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 460
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 461
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 462
 
 /*
  * 32 bit systems traditionally used different
-- 
GitLab


From c6dce23ec993f7da7790a9eadb36864ceb60e942 Mon Sep 17 00:00:00 2001
From: Techno Mooney <techno.mooney@gmail.com>
Date: Mon, 29 Jan 2024 15:11:47 +0700
Subject: [PATCH 3606/4076] ASoC: amd: yc: Add DMI quirk for MSI Bravo 15 C7VF

The laptop requires a quirk ID to enable its internal microphone. Add
it to the DMI quirk table.

Reported-by: Techno Mooney <techno.mooney@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218402
Cc: stable@vger.kernel.org
Signed-off-by: Techno Mooney <techno.mooney@gmail.com>
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://msgid.link/r/20240129081148.1044891-1-bagasdotme@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index d83cb6e4c62ae..23d44a50d8157 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -297,6 +297,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 B7ED"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VF"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
-- 
GitLab


From e4ad71e2367f3f7b7409c30df9cdbb34da15e012 Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Fri, 26 Jan 2024 11:57:24 +0100
Subject: [PATCH 3607/4076] MAINTAINERS: wifi: brcm80211: cleanup entry

There has been some discussion about what is expected from
a maintainer and so a cleanup seems to be in order. A dedicated
mailing list has been created to discuss brcm80211 specific
development issues. Keeping the status as Supported although
help in maintaining this driver is welcomed.

Cc: brcm80211@lists.linux.dev
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240126105724.384063-1-arend.vanspriel@broadcom.com
---
 MAINTAINERS | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d8ca0e10c8d10..25d530ab90d7b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4169,14 +4169,14 @@ F:	drivers/firmware/broadcom/tee_bnxt_fw.c
 F:	drivers/net/ethernet/broadcom/bnxt/
 F:	include/linux/firmware/broadcom/tee_bnxt_fw.h
 
-BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER
-M:	Arend van Spriel <aspriel@gmail.com>
-M:	Franky Lin <franky.lin@broadcom.com>
-M:	Hante Meuleman <hante.meuleman@broadcom.com>
+BROADCOM BRCM80211 IEEE802.11 WIRELESS DRIVERS
+M:	Arend van Spriel <arend.vanspriel@broadcom.com>
 L:	linux-wireless@vger.kernel.org
+L:	brcm80211@lists.linux.dev
 L:	brcm80211-dev-list.pdl@broadcom.com
 S:	Supported
 F:	drivers/net/wireless/broadcom/brcm80211/
+F:	include/linux/platform_data/brcmfmac.h
 
 BROADCOM BRCMSTB GPIO DRIVER
 M:	Doug Berger <opendmb@gmail.com>
-- 
GitLab


From 0adf963b8463faa44653e22e56ce55f747e68868 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Sun, 28 Jan 2024 00:32:43 +0800
Subject: [PATCH 3608/4076] ASoC: sunxi: sun4i-spdif: Add support for Allwinner
 H616

The SPDIF hardware block found in the H616 SoC has the same layout as
the one found in the H6 SoC, except that it is missing the receiver
side.

Since the driver currently only supports the transmit function, support
for the H616 is identical to what is currently done for the H6.

Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Link: https://msgid.link/r/20240127163247.384439-4-wens@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sunxi/sun4i-spdif.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c
index 702386823d172..f41c309558579 100644
--- a/sound/soc/sunxi/sun4i-spdif.c
+++ b/sound/soc/sunxi/sun4i-spdif.c
@@ -577,6 +577,11 @@ static const struct of_device_id sun4i_spdif_of_match[] = {
 		.compatible = "allwinner,sun50i-h6-spdif",
 		.data = &sun50i_h6_spdif_quirks,
 	},
+	{
+		.compatible = "allwinner,sun50i-h616-spdif",
+		/* Essentially the same as the H6, but without RX */
+		.data = &sun50i_h6_spdif_quirks,
+	},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sun4i_spdif_of_match);
-- 
GitLab


From 57b3c130d97e45b8a07586e0ae113e43776c5ea8 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Sun, 28 Jan 2024 00:32:41 +0800
Subject: [PATCH 3609/4076] ASoC: sun4i-spdif: Fix requirements for H6

When the H6 was added to the bindings, only the TX DMA channel was
added. As the hardware supports both transmit and receive functions,
the binding is missing the RX DMA channel and is thus incorrect.
Also, the reset control was not made mandatory.

Add the RX DMA channel for SPDIF on H6 by removing the compatible from
the list of compatibles that should only have a TX DMA channel. And add
the H6 compatible to the list of compatibles that require the reset
control to be present.

Fixes: b20453031472 ("dt-bindings: sound: sun4i-spdif: Add Allwinner H6 compatible")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Link: https://msgid.link/r/20240127163247.384439-2-wens@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
index 8108c564dd78a..98e2e053fa191 100644
--- a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
+++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
@@ -62,6 +62,7 @@ allOf:
             enum:
               - allwinner,sun6i-a31-spdif
               - allwinner,sun8i-h3-spdif
+              - allwinner,sun50i-h6-spdif
 
     then:
       required:
@@ -73,7 +74,6 @@ allOf:
           contains:
             enum:
               - allwinner,sun8i-h3-spdif
-              - allwinner,sun50i-h6-spdif
 
     then:
       properties:
-- 
GitLab


From 7a9dc944f129bb56ef855d9c0b0647bc3e98a56f Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Sun, 28 Jan 2024 00:32:42 +0800
Subject: [PATCH 3610/4076] ASoC: sun4i-spdif: Add Allwinner H616 compatible

The SPDIF hardware block found in the H616 SoC has the same layout as
the one found in the H6 SoC, except that it is missing the receiver
side.

Add a new compatible string for it.

Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Link: https://msgid.link/r/20240127163247.384439-3-wens@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml   | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
index 98e2e053fa191..aa32dc950e72c 100644
--- a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
+++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
@@ -22,6 +22,7 @@ properties:
       - const: allwinner,sun6i-a31-spdif
       - const: allwinner,sun8i-h3-spdif
       - const: allwinner,sun50i-h6-spdif
+      - const: allwinner,sun50i-h616-spdif
       - items:
           - const: allwinner,sun8i-a83t-spdif
           - const: allwinner,sun8i-h3-spdif
@@ -63,6 +64,7 @@ allOf:
               - allwinner,sun6i-a31-spdif
               - allwinner,sun8i-h3-spdif
               - allwinner,sun50i-h6-spdif
+              - allwinner,sun50i-h616-spdif
 
     then:
       required:
@@ -74,6 +76,7 @@ allOf:
           contains:
             enum:
               - allwinner,sun8i-h3-spdif
+              - allwinner,sun50i-h616-spdif
 
     then:
       properties:
-- 
GitLab


From f1f6a6b1830a8f1dc92ee26fae76333f446b0663 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Mon, 11 Dec 2023 18:05:52 -0800
Subject: [PATCH 3611/4076] e1000e: correct maximum frequency adjustment values

The e1000e driver supports hardware with a variety of different clock
speeds, and thus a variety of different increment values used for
programming its PTP hardware clock.

The values currently programmed in e1000e_ptp_init are incorrect. In
particular, only two maximum adjustments are used: 24000000 - 1, and
600000000 - 1. These were originally intended to be used with the 96 MHz
clock and the 25 MHz clock.

Both of these values are actually slightly too high. For the 96 MHz clock,
the actual maximum value that can safely be programmed is 23,999,938. For
the 25 MHz clock, the maximum value is 599,999,904.

Worse, several devices use a 24 MHz clock or a 38.4 MHz clock. These parts
are incorrectly assigned one of either the 24million or 600million values.
For the 24 MHz clock, this is not a significant issue: its current
increment value can support an adjustment up to 7billion in the positive
direction. However, the 38.4 KHz clock uses an increment value which can
only support up to 230,769,157 before it starts overflowing.

To understand where these values come from, consider that frequency
adjustments have the form of:

new_incval = base_incval + (base_incval * adjustment) / (unit of adjustment)

The maximum adjustment is reported in terms of parts per billion:
new_incval = base_incval + (base_incval * adjustment) / 1 billion

The largest possible adjustment is thus given by the following:
max_incval = base_incval + (base_incval * max_adj) / 1 billion

Re-arranging to solve for max_adj:
max_adj = (max_incval - base_incval) * 1 billion / base_incval

We also need to ensure that negative adjustments cannot underflow. This can
be achieved simply by ensuring max_adj is always less than 1 billion.

Introduce new macros in e1000.h codifying the maximum adjustment in PPB for
each frequency given its associated increment values. Also clarify where
these values come from by commenting about the above equations.

Replace the switch statement in e1000e_ptp_init with one which mirrors the
increment value switch statement from e1000e_get_base_timinica. For each
device, assign the appropriate maximum adjustment based on its frequency.
Some parts can have one of two frequency modes as determined by
E1000_TSYNCRXCTL_SYSCFI.

Since the new flow directly matches the assignments in
e1000e_get_base_timinca, and uses well defined macro names, it is much
easier to verify that the resulting maximum adjustments are correct. It
also avoids difficult to parse construction such as the "hw->mac.type <
e1000_phc_lpt", and the use of fallthrough which was especially confusing
when combined with a conditional block.

Note that I believe the current increment value configuration used for
24MHz clocks is sub-par, as it leaves at least 3 extra bits available in
the INCVALUE register. However, fixing that requires more careful review of
the clock rate and associated values.

Reported-by: Trey Harrison <harrisondigitalmedia@gmail.com>
Fixes: 68fe1d5da548 ("e1000e: Add Support for 38.4MHZ frequency")
Fixes: d89777bf0e42 ("e1000e: add support for IEEE-1588 PTP")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/e1000.h | 20 ++++++++++++++++++++
 drivers/net/ethernet/intel/e1000e/ptp.c   | 22 +++++++++++++++-------
 2 files changed, 35 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index a187582d22994..ba9c19e6994c9 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -360,23 +360,43 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
  * As a result, a shift of INCVALUE_SHIFT_n is used to fit a value of
  * INCVALUE_n into the TIMINCA register allowing 32+8+(24-INCVALUE_SHIFT_n)
  * bits to count nanoseconds leaving the rest for fractional nonseconds.
+ *
+ * Any given INCVALUE also has an associated maximum adjustment value. This
+ * maximum adjustment value is the largest increase (or decrease) which can be
+ * safely applied without overflowing the INCVALUE. Since INCVALUE has
+ * a maximum range of 24 bits, its largest value is 0xFFFFFF.
+ *
+ * To understand where the maximum value comes from, consider the following
+ * equation:
+ *
+ *   new_incval = base_incval + (base_incval * adjustment) / 1billion
+ *
+ * To avoid overflow that means:
+ *   max_incval = base_incval + (base_incval * max_adj) / billion
+ *
+ * Re-arranging:
+ *   max_adj = floor(((max_incval - base_incval) * 1billion) / 1billion)
  */
 #define INCVALUE_96MHZ		125
 #define INCVALUE_SHIFT_96MHZ	17
 #define INCPERIOD_SHIFT_96MHZ	2
 #define INCPERIOD_96MHZ		(12 >> INCPERIOD_SHIFT_96MHZ)
+#define MAX_PPB_96MHZ		23999900 /* 23,999,900 ppb */
 
 #define INCVALUE_25MHZ		40
 #define INCVALUE_SHIFT_25MHZ	18
 #define INCPERIOD_25MHZ		1
+#define MAX_PPB_25MHZ		599999900 /* 599,999,900 ppb */
 
 #define INCVALUE_24MHZ		125
 #define INCVALUE_SHIFT_24MHZ	14
 #define INCPERIOD_24MHZ		3
+#define MAX_PPB_24MHZ		999999999 /* 999,999,999 ppb */
 
 #define INCVALUE_38400KHZ	26
 #define INCVALUE_SHIFT_38400KHZ	19
 #define INCPERIOD_38400KHZ	1
+#define MAX_PPB_38400KHZ	230769100 /* 230,769,100 ppb */
 
 /* Another drawback of scaling the incvalue by a large factor is the
  * 64-bit SYSTIM register overflows more quickly.  This is dealt with
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 02d871bc112a7..bbcfd529399b0 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -280,8 +280,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 
 	switch (hw->mac.type) {
 	case e1000_pch2lan:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ;
+		break;
 	case e1000_pch_lpt:
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
+			adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ;
+		else
+			adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
+		break;
 	case e1000_pch_spt:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
+		break;
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
@@ -289,15 +298,14 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
 	case e1000_pch_nvp:
-		if ((hw->mac.type < e1000_pch_lpt) ||
-		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
-			adapter->ptp_clock_info.max_adj = 24000000 - 1;
-			break;
-		}
-		fallthrough;
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
+			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
+		else
+			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+		break;
 	case e1000_82574:
 	case e1000_82583:
-		adapter->ptp_clock_info.max_adj = 600000000 - 1;
+		adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
 		break;
 	default:
 		break;
-- 
GitLab


From bbc404d20d1b46d89b461918bc44587620eda200 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 20 Jan 2024 18:25:36 +0100
Subject: [PATCH 3612/4076] ixgbe: Fix an error handling path in
 ixgbe_read_iosf_sb_reg_x550()

All error handling paths, except this one, go to 'out' where
release_swfw_sync() is called.
This call balances the acquire_swfw_sync() call done at the beginning of
the function.

Branch to the error handling path in order to correctly release some
resources in case of error.

Fixes: ae14a1d8e104 ("ixgbe: Fix IOSF SB access issues")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 6208923e29a2b..c1adc94a5a657 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -716,7 +716,8 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
 		error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command);
 		hw_dbg(hw, "Failed to read, error %x\n", error);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	if (!ret)
-- 
GitLab


From ccbca118ef1a71d5faa012b9bb1ecd784e9e2b42 Mon Sep 17 00:00:00 2001
From: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Date: Mon, 22 Jan 2024 21:35:09 -0800
Subject: [PATCH 3613/4076] NFSv4.1: Assign the right value for initval and
 retries for rpc timeout

Make sure the rpc timeout was assigned with the correct value for
initial timeout and max number of retries.

Fixes: 57331a59ac0d ("NFSv4.1: Use the nfs_client's rpc timeouts for backchannel")
Signed-off-by: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/svc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index f60c93e5a25d6..b969e505c7b77 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1598,10 +1598,10 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 	/* Finally, send the reply synchronously */
 	if (rqstp->bc_to_initval > 0) {
 		timeout.to_initval = rqstp->bc_to_initval;
-		timeout.to_retries = rqstp->bc_to_initval;
+		timeout.to_retries = rqstp->bc_to_retries;
 	} else {
 		timeout.to_initval = req->rq_xprt->timeout->to_initval;
-		timeout.to_initval = req->rq_xprt->timeout->to_retries;
+		timeout.to_retries = req->rq_xprt->timeout->to_retries;
 	}
 	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
 	task = rpc_run_bc_task(req, &timeout);
-- 
GitLab


From 5513c5d0fb3d509cdd0a11afc18441c57eb7c94c Mon Sep 17 00:00:00 2001
From: Marian Postevca <posteuca@mutex.one>
Date: Sun, 28 Jan 2024 19:22:29 +0200
Subject: [PATCH 3614/4076] ASoC: amd: acp: Fix support for a Huawei Matebook
 laptop

Previous commit that added support for Huawei MateBook D16 2021
with Ryzen 4600H (HVY-WXX9 M1010) was incomplete.

To activate support for this laptop, the DMI table in
acp3x-es83xx machine driver must also be updated.

Fixes: b5338b1b901e ("ASoC: amd: acp: Add support for a new Huawei Matebook laptop")
Signed-off-by: Marian Postevca <posteuca@mutex.one>
Link: https://msgid.link/r/20240128172229.657142-1-posteuca@mutex.one
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c b/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
index f85b85ea4be9c..2b0aa270a3e9d 100644
--- a/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
+++ b/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
@@ -354,6 +354,14 @@ static const struct dmi_system_id acp3x_es83xx_dmi_table[] = {
 		},
 		.driver_data = (void *)(ES83XX_ENABLE_DMIC|ES83XX_48_MHZ_MCLK),
 	},
+	{
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1010"),
+		},
+		.driver_data = (void *)(ES83XX_ENABLE_DMIC),
+	},
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
-- 
GitLab


From e84b01a880f635e3084a361afba41f95ff500d12 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 29 Jan 2024 11:52:54 -0700
Subject: [PATCH 3615/4076] io_uring/poll: move poll execution helpers higher
 up

In preparation for calling __io_poll_execute() higher up, move the
functions to avoid forward declarations.

No functional changes in this patch.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/poll.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/io_uring/poll.c b/io_uring/poll.c
index d59b74a99d4e4..785a5b1910038 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -228,6 +228,26 @@ enum {
 	IOU_POLL_REISSUE = 3,
 };
 
+static void __io_poll_execute(struct io_kiocb *req, int mask)
+{
+	unsigned flags = 0;
+
+	io_req_set_res(req, mask, 0);
+	req->io_task_work.func = io_poll_task_func;
+
+	trace_io_uring_task_add(req, mask);
+
+	if (!(req->flags & REQ_F_POLL_NO_LAZY))
+		flags = IOU_F_TWQ_LAZY_WAKE;
+	__io_req_task_work_add(req, flags);
+}
+
+static inline void io_poll_execute(struct io_kiocb *req, int res)
+{
+	if (io_poll_get_ownership(req))
+		__io_poll_execute(req, res);
+}
+
 /*
  * All poll tw should go through this. Checks for poll events, manages
  * references, does rewait, etc.
@@ -364,26 +384,6 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 	}
 }
 
-static void __io_poll_execute(struct io_kiocb *req, int mask)
-{
-	unsigned flags = 0;
-
-	io_req_set_res(req, mask, 0);
-	req->io_task_work.func = io_poll_task_func;
-
-	trace_io_uring_task_add(req, mask);
-
-	if (!(req->flags & REQ_F_POLL_NO_LAZY))
-		flags = IOU_F_TWQ_LAZY_WAKE;
-	__io_req_task_work_add(req, flags);
-}
-
-static inline void io_poll_execute(struct io_kiocb *req, int res)
-{
-	if (io_poll_get_ownership(req))
-		__io_poll_execute(req, res);
-}
-
 static void io_poll_cancel_req(struct io_kiocb *req)
 {
 	io_poll_mark_cancelled(req);
-- 
GitLab


From 91e5d765a82fb2c9d0b7ad930d8953208081ddf1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 29 Jan 2024 11:54:18 -0700
Subject: [PATCH 3616/4076] io_uring/net: un-indent mshot retry path in
 io_recv_finish()

In preparation for putting some retry logic in there, have the done
path just skip straight to the end rather than have too much nesting
in here.

No functional changes in this patch.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 36 ++++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 75d494dad7e2c..740c6bfa5b590 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -645,23 +645,27 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 		return true;
 	}
 
-	if (!mshot_finished) {
-		if (io_fill_cqe_req_aux(req, issue_flags & IO_URING_F_COMPLETE_DEFER,
-					*ret, cflags | IORING_CQE_F_MORE)) {
-			io_recv_prep_retry(req);
-			/* Known not-empty or unknown state, retry */
-			if (cflags & IORING_CQE_F_SOCK_NONEMPTY ||
-			    msg->msg_inq == -1)
-				return false;
-			if (issue_flags & IO_URING_F_MULTISHOT)
-				*ret = IOU_ISSUE_SKIP_COMPLETE;
-			else
-				*ret = -EAGAIN;
-			return true;
-		}
-		/* Otherwise stop multishot but use the current result. */
-	}
+	if (mshot_finished)
+		goto finish;
 
+	/*
+	 * Fill CQE for this receive and see if we should keep trying to
+	 * receive from this socket.
+	 */
+	if (io_fill_cqe_req_aux(req, issue_flags & IO_URING_F_COMPLETE_DEFER,
+				*ret, cflags | IORING_CQE_F_MORE)) {
+		io_recv_prep_retry(req);
+		/* Known not-empty or unknown state, retry */
+		if (cflags & IORING_CQE_F_SOCK_NONEMPTY || msg->msg_inq == -1)
+			return false;
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			*ret = IOU_ISSUE_SKIP_COMPLETE;
+		else
+			*ret = -EAGAIN;
+		return true;
+	}
+	/* Otherwise stop multishot but use the current result. */
+finish:
 	io_req_set_res(req, *ret, cflags);
 
 	if (issue_flags & IO_URING_F_MULTISHOT)
-- 
GitLab


From 704ea888d646cb9d715662944cf389c823252ee0 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 29 Jan 2024 11:57:11 -0700
Subject: [PATCH 3617/4076] io_uring/poll: add requeue return code from poll
 multishot handling

Since our poll handling is edge triggered, multishot handlers retry
internally until they know that no more data is available. In
preparation for limiting these retries, add an internal return code,
IOU_REQUEUE, which can be used to inform the poll backend about the
handler wanting to retry, but that this should happen through a normal
task_work requeue rather than keep hammering on the issue side for this
one request.

No functional changes in this patch, nobody is using this return code
just yet.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.h | 8 +++++++-
 io_uring/poll.c     | 9 ++++++++-
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 04e33f25919ca..d5495710c1787 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -15,11 +15,17 @@
 #include <trace/events/io_uring.h>
 #endif
 
-
 enum {
 	IOU_OK			= 0,
 	IOU_ISSUE_SKIP_COMPLETE	= -EIOCBQUEUED,
 
+	/*
+	 * Requeue the task_work to restart operations on this request. The
+	 * actual value isn't important, should just be not an otherwise
+	 * valid error code, yet less than -MAX_ERRNO and valid internally.
+	 */
+	IOU_REQUEUE		= -3072,
+
 	/*
 	 * Intended only when both IO_URING_F_MULTISHOT is passed
 	 * to indicate to the poll runner that multishot should be
diff --git a/io_uring/poll.c b/io_uring/poll.c
index 785a5b1910038..7513afc7b702e 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -226,6 +226,7 @@ enum {
 	IOU_POLL_NO_ACTION = 1,
 	IOU_POLL_REMOVE_POLL_USE_RES = 2,
 	IOU_POLL_REISSUE = 3,
+	IOU_POLL_REQUEUE = 4,
 };
 
 static void __io_poll_execute(struct io_kiocb *req, int mask)
@@ -329,6 +330,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
 			int ret = io_poll_issue(req, ts);
 			if (ret == IOU_STOP_MULTISHOT)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
+			else if (ret == IOU_REQUEUE)
+				return IOU_POLL_REQUEUE;
 			if (ret < 0)
 				return ret;
 		}
@@ -351,8 +354,12 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 	int ret;
 
 	ret = io_poll_check_events(req, ts);
-	if (ret == IOU_POLL_NO_ACTION)
+	if (ret == IOU_POLL_NO_ACTION) {
 		return;
+	} else if (ret == IOU_POLL_REQUEUE) {
+		__io_poll_execute(req, 0);
+		return;
+	}
 	io_poll_remove_entries(req);
 	io_poll_tw_hash_eject(req, ts);
 
-- 
GitLab


From 76b367a2d83163cf19173d5cb0b562acbabc8eac Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 29 Jan 2024 12:00:58 -0700
Subject: [PATCH 3618/4076] io_uring/net: limit inline multishot retries

If we have multiple clients and some/all are flooding the receives to
such an extent that we can retry a LOT handling multishot receives, then
we can be starving some clients and hence serving traffic in an
imbalanced fashion.

Limit multishot retry attempts to some arbitrary value, whose only
purpose serves to ensure that we don't keep serving a single connection
for way too long. We default to 32 retries, which should be more than
enough to provide fairness, yet not so small that we'll spend too much
time requeuing rather than handling traffic.

Cc: stable@vger.kernel.org
Depends-on: 704ea888d646 ("io_uring/poll: add requeue return code from poll multishot handling")
Depends-on: 1e5d765a82f ("io_uring/net: un-indent mshot retry path in io_recv_finish()")
Depends-on: e84b01a880f6 ("io_uring/poll: move poll execution helpers higher up")
Fixes: b3fdea6ecb55 ("io_uring: multishot recv")
Fixes: 9bb66906f23e ("io_uring: support multishot in recvmsg")
Link: https://github.com/axboe/liburing/issues/1043
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 740c6bfa5b590..a12ff69e68434 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -60,6 +60,7 @@ struct io_sr_msg {
 	unsigned			len;
 	unsigned			done_io;
 	unsigned			msg_flags;
+	unsigned			nr_multishot_loops;
 	u16				flags;
 	/* initialised and used only by !msg send variants */
 	u16				addr_len;
@@ -70,6 +71,13 @@ struct io_sr_msg {
 	struct io_kiocb 		*notif;
 };
 
+/*
+ * Number of times we'll try and do receives if there's more data. If we
+ * exceed this limit, then add us to the back of the queue and retry from
+ * there. This helps fairness between flooding clients.
+ */
+#define MULTISHOT_MAX_RETRY	32
+
 static inline bool io_check_multishot(struct io_kiocb *req,
 				      unsigned int issue_flags)
 {
@@ -611,6 +619,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		sr->msg_flags |= MSG_CMSG_COMPAT;
 #endif
 	sr->done_io = 0;
+	sr->nr_multishot_loops = 0;
 	return 0;
 }
 
@@ -654,12 +663,20 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 	 */
 	if (io_fill_cqe_req_aux(req, issue_flags & IO_URING_F_COMPLETE_DEFER,
 				*ret, cflags | IORING_CQE_F_MORE)) {
+		struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+		int mshot_retry_ret = IOU_ISSUE_SKIP_COMPLETE;
+
 		io_recv_prep_retry(req);
 		/* Known not-empty or unknown state, retry */
-		if (cflags & IORING_CQE_F_SOCK_NONEMPTY || msg->msg_inq == -1)
-			return false;
+		if (cflags & IORING_CQE_F_SOCK_NONEMPTY || msg->msg_inq == -1) {
+			if (sr->nr_multishot_loops++ < MULTISHOT_MAX_RETRY)
+				return false;
+			/* mshot retries exceeded, force a requeue */
+			sr->nr_multishot_loops = 0;
+			mshot_retry_ret = IOU_REQUEUE;
+		}
 		if (issue_flags & IO_URING_F_MULTISHOT)
-			*ret = IOU_ISSUE_SKIP_COMPLETE;
+			*ret = mshot_retry_ret;
 		else
 			*ret = -EAGAIN;
 		return true;
-- 
GitLab


From c44fc98f0a8ffd94fa0bd291928e7e312ffc7ca4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Vok=C3=A1=C4=8D?= <michal.vokac@ysoft.com>
Date: Fri, 26 Jan 2024 11:49:35 +0100
Subject: [PATCH 3619/4076] net: dsa: qca8k: fix illegal usage of GPIO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When working with GPIO, its direction must be set either when the GPIO is
requested by gpiod_get*() or later on by one of the gpiod_direction_*()
functions. Neither of this is done here which results in undefined
behavior on some systems.

As the reset GPIO is used right after it is requested here, it makes sense
to configure it as GPIOD_OUT_HIGH right away. With that, the following
gpiod_set_value_cansleep(1) becomes redundant and can be safely
removed.

Fixes: a653f2f538f9 ("net: dsa: qca8k: introduce reset via gpio feature")
Signed-off-by: Michal Vokáč <michal.vokac@ysoft.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/1706266175-3408-1-git-send-email-michal.vokac@ysoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/qca/qca8k-8xxx.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index c51f40960961f..7a864329cb726 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -2051,12 +2051,11 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 	priv->info = of_device_get_match_data(priv->dev);
 
 	priv->reset_gpio = devm_gpiod_get_optional(priv->dev, "reset",
-						   GPIOD_ASIS);
+						   GPIOD_OUT_HIGH);
 	if (IS_ERR(priv->reset_gpio))
 		return PTR_ERR(priv->reset_gpio);
 
 	if (priv->reset_gpio) {
-		gpiod_set_value_cansleep(priv->reset_gpio, 1);
 		/* The active low duration must be greater than 10 ms
 		 * and checkpatch.pl wants 20 ms.
 		 */
-- 
GitLab


From 59c93583491ab15db109f9902524d241c4fa4c0b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 26 Jan 2024 12:13:08 -0800
Subject: [PATCH 3620/4076] selftests: net: add missing config for
 nftables-backed iptables

Modern OSes use iptables implementation with nf_tables as a backend,
e.g.:

$ iptables -V
iptables v1.8.8 (nf_tables)

Pablo points out that we need CONFIG_NFT_COMPAT to make that work,
otherwise we see a lot of:

  Warning: Extension DNAT revision 0 not supported, missing kernel module?

with DNAT being just an example here, other modules we need
include udp, TTL, length etc.

Link: https://lore.kernel.org/r/20240126201308.2903602-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 56da5d52674cf..d4b38177ed04a 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -60,6 +60,7 @@ CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
+CONFIG_NFT_COMPAT=m
 CONFIG_NF_FLOW_TABLE=m
 CONFIG_PSAMPLE=m
 CONFIG_TCP_MD5SIG=y
-- 
GitLab


From 881f78f472556ed05588172d5b5676b48dc48240 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 29 Jan 2024 20:27:23 -0800
Subject: [PATCH 3621/4076] xfs: remove conditional building of rt geometry
 validator functions

I mistakenly turned off CONFIG_XFS_RT in the Kconfig file for arm64
variant of the djwong-wtf git branch.  Unfortunately, it took me a good
hour to figure out that RT wasn't built because this is what got printed
to dmesg:

XFS (sda2): realtime geometry sanity check failed
XFS (sda2): Metadata corruption detected at xfs_sb_read_verify+0x170/0x190 [xfs], xfs_sb block 0x0

Whereas I would have expected:

XFS (sda2): Not built with CONFIG_XFS_RT
XFS (sda2): RT mount failed

The root cause of these problems is the conditional compilation of the
new functions xfs_validate_rtextents and xfs_compute_rextslog that I
introduced in the two commits listed below.  The !RT versions of these
functions return false and 0, respectively, which causes primary
superblock validation to fail, which explains the first message.

Move the two functions to other parts of libxfs that are not
conditionally defined by CONFIG_XFS_RT and remove the broken stubs so
that validation works again.

Fixes: e14293803f4e ("xfs: don't allow overly small or large realtime volumes")
Fixes: a6a38f309afc ("xfs: make rextslog computation consistent with mkfs")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 fs/xfs/libxfs/xfs_rtbitmap.c | 14 --------------
 fs/xfs/libxfs/xfs_rtbitmap.h | 16 ----------------
 fs/xfs/libxfs/xfs_sb.c       | 14 ++++++++++++++
 fs/xfs/libxfs/xfs_sb.h       |  2 ++
 fs/xfs/libxfs/xfs_types.h    | 12 ++++++++++++
 fs/xfs/scrub/rtbitmap.c      |  1 +
 fs/xfs/scrub/rtsummary.c     |  1 +
 7 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 31100120b2c58..e31663cb7b434 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1118,20 +1118,6 @@ xfs_rtbitmap_blockcount(
 	return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
 }
 
-/*
- * Compute the maximum level number of the realtime summary file, as defined by
- * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
- * use of rt volumes with more than 2^32 extents.
- */
-uint8_t
-xfs_compute_rextslog(
-	xfs_rtbxlen_t		rtextents)
-{
-	if (!rtextents)
-		return 0;
-	return xfs_highbit64(rtextents);
-}
-
 /*
  * Compute the number of rtbitmap words needed to populate every block of a
  * bitmap that is large enough to track the given number of rt extents.
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 274dc7dae1faf..152a66750af55 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -351,20 +351,6 @@ xfs_rtfree_extent(
 int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
 		xfs_filblks_t rtlen);
 
-uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
-
-/* Do we support an rt volume having this number of rtextents? */
-static inline bool
-xfs_validate_rtextents(
-	xfs_rtbxlen_t		rtextents)
-{
-	/* No runt rt volumes */
-	if (rtextents == 0)
-		return false;
-
-	return true;
-}
-
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
 		rtextents);
 unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp,
@@ -383,8 +369,6 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
 # define xfs_rtsummary_read_buf(a,b)			(-ENOSYS)
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
-# define xfs_compute_rextslog(rtx)			(0)
-# define xfs_validate_rtextents(rtx)			(false)
 static inline xfs_filblks_t
 xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 4a9e8588f4c98..5bb6e2bd6deee 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1377,3 +1377,17 @@ xfs_validate_stripe_geometry(
 	}
 	return true;
 }
+
+/*
+ * Compute the maximum level number of the realtime summary file, as defined by
+ * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
+ * use of rt volumes with more than 2^32 extents.
+ */
+uint8_t
+xfs_compute_rextslog(
+	xfs_rtbxlen_t		rtextents)
+{
+	if (!rtextents)
+		return 0;
+	return xfs_highbit64(rtextents);
+}
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 19134b23c10be..2e8e8d63d4eb2 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -38,4 +38,6 @@ extern int	xfs_sb_get_secondary(struct xfs_mount *mp,
 extern bool	xfs_validate_stripe_geometry(struct xfs_mount *mp,
 		__s64 sunit, __s64 swidth, int sectorsize, bool silent);
 
+uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+
 #endif	/* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 20b5375f2d9c9..62e02d5380ad3 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -251,4 +251,16 @@ bool xfs_verify_fileoff(struct xfs_mount *mp, xfs_fileoff_t off);
 bool xfs_verify_fileext(struct xfs_mount *mp, xfs_fileoff_t off,
 		xfs_fileoff_t len);
 
+/* Do we support an rt volume having this number of rtextents? */
+static inline bool
+xfs_validate_rtextents(
+	xfs_rtbxlen_t		rtextents)
+{
+	/* No runt rt volumes */
+	if (rtextents == 0)
+		return false;
+
+	return true;
+}
+
 #endif	/* __XFS_TYPES_H__ */
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 441ca99776527..46583517377ff 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -15,6 +15,7 @@
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
 #include "xfs_bit.h"
+#include "xfs_sb.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index fabd0ed9dfa67..b1ff4f33324a7 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -16,6 +16,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_bit.h"
 #include "xfs_bmap.h"
+#include "xfs_sb.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
-- 
GitLab


From 60365049ccbacd101654a66ddcb299abfabd4fc5 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@kernel.org>
Date: Fri, 26 Jan 2024 09:32:20 +0100
Subject: [PATCH 3622/4076] ipv6: Ensure natural alignment of const ipv6
 loopback and router addresses

On a parisc64 kernel I sometimes notice this kernel warning:
Kernel unaligned access to 0x40ff8814 at ndisc_send_skb+0xc0/0x4d8

The address 0x40ff8814 points to the in6addr_linklocal_allrouters
variable and the warning simply means that some ipv6 function tries to
read a 64-bit word directly from the not-64-bit aligned
in6addr_linklocal_allrouters variable.

Unaligned accesses are non-critical as the architecture or exception
handlers usually will fix it up at runtime. Nevertheless it may trigger
a performance penality for some architectures. For details read the
"unaligned-memory-access" kernel documentation.

The patch below ensures that the ipv6 loopback and router addresses will
always be naturally aligned. This prevents the unaligned accesses for
all architectures.

Signed-off-by: Helge Deller <deller@gmx.de>
Fixes: 034dfc5df99eb ("ipv6: export in6addr_loopback to modules")
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/ZbNuFM1bFqoH-UoY@p100
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/addrconf_core.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 507a8353a6bdb..c008d21925d7f 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
 /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
-const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT;
+const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LOOPBACK_INIT;
 EXPORT_SYMBOL(in6addr_loopback);
-const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT;
+const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_ANY_INIT;
 EXPORT_SYMBOL(in6addr_any);
-const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT;
+const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LINKLOCAL_ALLNODES_INIT;
 EXPORT_SYMBOL(in6addr_linklocal_allnodes);
-const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_linklocal_allrouters);
-const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
+const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
 EXPORT_SYMBOL(in6addr_interfacelocal_allnodes);
-const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_interfacelocal_allrouters);
-const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_sitelocal_allrouters);
 
 static void snmp6_free_dev(struct inet6_dev *idev)
-- 
GitLab


From 2fa28abd1090562b4d9bc4aedd70abcca26561af Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 23 Jan 2024 14:30:54 +0100
Subject: [PATCH 3623/4076] arm64: Revert "scs: Work around full LTO issue with
 dynamic SCS"

This reverts commit 8c5a19cb17a71e ("arm64: scs: Work around full LTO
issue with dynamic SCS"), which did not quite fix the issue as intended.
Apparently, -fno-unwind-tables is ignored for the final full LTO link
when it is set on any of the objects, resulting in an early boot crash
due to the SCS patching code patching itself, and attempting to pop the
return address from the shadow stack while the associated push was still
a PACIASP instruction when it executed.

Reported-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20240123133052.1417449-5-ardb+git@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/Makefile | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index e5d03a7039b4b..d95b3d6b471a7 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -73,13 +73,7 @@ obj-$(CONFIG_ARM64_MTE)			+= mte.o
 obj-y					+= vdso-wrap.o
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32-wrap.o
 obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS)	+= patch-scs.o
-
-# We need to prevent the SCS patching code from patching itself. Using
-# -mbranch-protection=none here to avoid the patchable PAC opcodes from being
-# generated triggers an issue with full LTO on Clang, which stops emitting PAC
-# instructions altogether. So instead, omit the unwind tables used by the
-# patching code, so it will not be able to locate its own PAC instructions.
-CFLAGS_patch-scs.o			+= -fno-asynchronous-unwind-tables -fno-unwind-tables
+CFLAGS_patch-scs.o			+= -mbranch-protection=none
 
 # Force dependency (vdso*-wrap.S includes vdso.so through incbin)
 $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
-- 
GitLab


From d104a6fef3fec137d8d44961224ab76edbd6cbc7 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 23 Jan 2024 14:30:55 +0100
Subject: [PATCH 3624/4076] arm64: scs: Disable LTO for SCS patching code

Full LTO takes the '-mbranch-protection=none' passed to the compiler
when generating the dynamic shadow call stack patching code as a hint to
stop emitting PAC instructions altogether. (Thin LTO appears unaffected
by this)

Work around this by disabling LTO for the compilation unit, which
appears to convince the linker that it should still use PAC in the rest
of the kernel..

Fixes: 3b619e22c460 ("arm64: implement dynamic shadow call stack for Clang")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20240123133052.1417449-6-ardb+git@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/Makefile | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index d95b3d6b471a7..467cb71172730 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -73,7 +73,13 @@ obj-$(CONFIG_ARM64_MTE)			+= mte.o
 obj-y					+= vdso-wrap.o
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32-wrap.o
 obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS)	+= patch-scs.o
+
+# We need to prevent the SCS patching code from patching itself. Using
+# -mbranch-protection=none here to avoid the patchable PAC opcodes from being
+# generated triggers an issue with full LTO on Clang, which stops emitting PAC
+# instructions altogether. So disable LTO as well for the compilation unit.
 CFLAGS_patch-scs.o			+= -mbranch-protection=none
+CFLAGS_REMOVE_patch-scs.o		+= $(CC_FLAGS_LTO)
 
 # Force dependency (vdso*-wrap.S includes vdso.so through incbin)
 $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
-- 
GitLab


From 4896bb7c0b31a0a3379b290ea7729900c59e0c69 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Fri, 26 Jan 2024 10:10:41 +0100
Subject: [PATCH 3625/4076] net: stmmac: do not clear TBS enable bit on link
 up/down

With the dma conf being reallocated on each call to stmmac_open(), any
information in there is lost, unless we specifically handle it.

The STMMAC_TBS_EN bit is set when adding an etf qdisc, and the etf qdisc
therefore would stop working when link was set down and then back up.

Fixes: ba39b344e924 ("net: ethernet: stmicro: stmmac: generate stmmac dma conf before open")
Cc: stable@vger.kernel.org
Signed-off-by: Esben Haabendal <esben@geanix.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b334eb16da23a..25519952f754c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3932,6 +3932,9 @@ static int __stmmac_open(struct net_device *dev,
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
 
 	buf_sz = dma_conf->dma_buf_sz;
+	for (int i = 0; i < MTL_MAX_TX_QUEUES; i++)
+		if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN)
+			dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs;
 	memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf));
 
 	stmmac_reset_queues_param(priv);
-- 
GitLab


From 3b12ec8f618ebaccfe43ea4621a6f5fb586edef8 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Fri, 26 Jan 2024 10:10:42 +0100
Subject: [PATCH 3626/4076] net: stmmac: dwmac-imx: set TSO/TBS TX queues
 default settings

TSO and TBS cannot coexist. For now we set i.MX Ethernet QOS controller to
use the first TX queue with TSO and the rest for TBS.

TX queues with TBS can support etf qdisc hw offload.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 8f730ada71f91..6b65420e11b5c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -353,6 +353,10 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	if (data->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
 		plat_dat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY;
 
+	/* Default TX Q0 to use TSO and rest TXQ for TBS */
+	for (int i = 1; i < plat_dat->tx_queues_to_use; i++)
+		plat_dat->tx_queues_cfg[i].tbs_en = 1;
+
 	plat_dat->host_dma_width = dwmac->ops->addr_width;
 	plat_dat->init = imx_dwmac_init;
 	plat_dat->exit = imx_dwmac_exit;
-- 
GitLab


From c7767f5c43df2c453af4651d1f58f489e3eb4ac1 Mon Sep 17 00:00:00 2001
From: Kevin Brodsky <kevin.brodsky@arm.com>
Date: Mon, 29 Jan 2024 15:47:48 +0000
Subject: [PATCH 3627/4076] arm64: vdso32: Remove unused vdso32-offsets.h

Commit 2d071968a405 ("arm64: compat: Remove 32-bit sigreturn code
from the vDSO") removed all VDSO_* symbols in the compat vDSO. As a
result, vdso32-offsets.h is now empty and therefore unused. Time to
remove it.

Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Link: https://lore.kernel.org/r/20240129154748.1727759-1-kevin.brodsky@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Makefile               | 2 +-
 arch/arm64/include/asm/vdso.h     | 3 ---
 arch/arm64/kernel/vdso32/Makefile | 9 ---------
 3 files changed, 1 insertion(+), 13 deletions(-)

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 47ecc4cff9d25..a88cdf9106871 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -195,7 +195,7 @@ vdso_prepare: prepare0
 	include/generated/vdso-offsets.h arch/arm64/kernel/vdso/vdso.so
 ifdef CONFIG_COMPAT_VDSO
 	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 \
-	include/generated/vdso32-offsets.h arch/arm64/kernel/vdso32/vdso.so
+	arch/arm64/kernel/vdso32/vdso.so
 endif
 endif
 
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index b4ae321099327..4305995c8f82f 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -17,9 +17,6 @@
 #ifndef __ASSEMBLY__
 
 #include <generated/vdso-offsets.h>
-#ifdef CONFIG_COMPAT_VDSO
-#include <generated/vdso32-offsets.h>
-#endif
 
 #define VDSO_SYMBOL(base, name)						   \
 ({									   \
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 2266fcdff78a0..f5f80fdce0fe7 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -127,9 +127,6 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
 targets += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 
-include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE
-	$(call if_changed,vdsosym)
-
 # Strip rule for vdso.so
 $(obj)/vdso.so: OBJCOPYFLAGS := -S
 $(obj)/vdso.so: $(obj)/vdso32.so.dbg FORCE
@@ -166,9 +163,3 @@ quiet_cmd_vdsoas = AS32    $@
 
 quiet_cmd_vdsomunge = MUNGE   $@
       cmd_vdsomunge = $(obj)/$(munge) $< $@
-
-# Generate vDSO offsets using helper script (borrowed from the 64-bit vDSO)
-gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh
-quiet_cmd_vdsosym = VDSOSYM $@
-# The AArch64 nm should be able to read an AArch32 binary
-      cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
-- 
GitLab


From aa2b2eb3934859904c287bf5434647ba72e14c1c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 26 Jan 2024 16:55:32 +0000
Subject: [PATCH 3628/4076] llc: call sock_orphan() at release time

syzbot reported an interesting trace [1] caused by a stale sk->sk_wq
pointer in a closed llc socket.

In commit ff7b11aa481f ("net: socket: set sock->sk to NULL after
calling proto_ops::release()") Eric Biggers hinted that some protocols
are missing a sock_orphan(), we need to perform a full audit.

In net-next, I plan to clear sock->sk from sock_orphan() and
amend Eric patch to add a warning.

[1]
 BUG: KASAN: slab-use-after-free in list_empty include/linux/list.h:373 [inline]
 BUG: KASAN: slab-use-after-free in waitqueue_active include/linux/wait.h:127 [inline]
 BUG: KASAN: slab-use-after-free in sock_def_write_space_wfree net/core/sock.c:3384 [inline]
 BUG: KASAN: slab-use-after-free in sock_wfree+0x9a8/0x9d0 net/core/sock.c:2468
Read of size 8 at addr ffff88802f4fc880 by task ksoftirqd/1/27

CPU: 1 PID: 27 Comm: ksoftirqd/1 Not tainted 6.8.0-rc1-syzkaller-00049-g6098d87eaf31 #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:88 [inline]
  dump_stack_lvl+0xd9/0x1b0 lib/dump_stack.c:106
  print_address_description mm/kasan/report.c:377 [inline]
  print_report+0xc4/0x620 mm/kasan/report.c:488
  kasan_report+0xda/0x110 mm/kasan/report.c:601
  list_empty include/linux/list.h:373 [inline]
  waitqueue_active include/linux/wait.h:127 [inline]
  sock_def_write_space_wfree net/core/sock.c:3384 [inline]
  sock_wfree+0x9a8/0x9d0 net/core/sock.c:2468
  skb_release_head_state+0xa3/0x2b0 net/core/skbuff.c:1080
  skb_release_all net/core/skbuff.c:1092 [inline]
  napi_consume_skb+0x119/0x2b0 net/core/skbuff.c:1404
  e1000_unmap_and_free_tx_resource+0x144/0x200 drivers/net/ethernet/intel/e1000/e1000_main.c:1970
  e1000_clean_tx_irq drivers/net/ethernet/intel/e1000/e1000_main.c:3860 [inline]
  e1000_clean+0x4a1/0x26e0 drivers/net/ethernet/intel/e1000/e1000_main.c:3801
  __napi_poll.constprop.0+0xb4/0x540 net/core/dev.c:6576
  napi_poll net/core/dev.c:6645 [inline]
  net_rx_action+0x956/0xe90 net/core/dev.c:6778
  __do_softirq+0x21a/0x8de kernel/softirq.c:553
  run_ksoftirqd kernel/softirq.c:921 [inline]
  run_ksoftirqd+0x31/0x60 kernel/softirq.c:913
  smpboot_thread_fn+0x660/0xa10 kernel/smpboot.c:164
  kthread+0x2c6/0x3a0 kernel/kthread.c:388
  ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
  ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:242
 </TASK>

Allocated by task 5167:
  kasan_save_stack+0x33/0x50 mm/kasan/common.c:47
  kasan_save_track+0x14/0x30 mm/kasan/common.c:68
  unpoison_slab_object mm/kasan/common.c:314 [inline]
  __kasan_slab_alloc+0x81/0x90 mm/kasan/common.c:340
  kasan_slab_alloc include/linux/kasan.h:201 [inline]
  slab_post_alloc_hook mm/slub.c:3813 [inline]
  slab_alloc_node mm/slub.c:3860 [inline]
  kmem_cache_alloc_lru+0x142/0x6f0 mm/slub.c:3879
  alloc_inode_sb include/linux/fs.h:3019 [inline]
  sock_alloc_inode+0x25/0x1c0 net/socket.c:308
  alloc_inode+0x5d/0x220 fs/inode.c:260
  new_inode_pseudo+0x16/0x80 fs/inode.c:1005
  sock_alloc+0x40/0x270 net/socket.c:634
  __sock_create+0xbc/0x800 net/socket.c:1535
  sock_create net/socket.c:1622 [inline]
  __sys_socket_create net/socket.c:1659 [inline]
  __sys_socket+0x14c/0x260 net/socket.c:1706
  __do_sys_socket net/socket.c:1720 [inline]
  __se_sys_socket net/socket.c:1718 [inline]
  __x64_sys_socket+0x72/0xb0 net/socket.c:1718
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xd3/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Freed by task 0:
  kasan_save_stack+0x33/0x50 mm/kasan/common.c:47
  kasan_save_track+0x14/0x30 mm/kasan/common.c:68
  kasan_save_free_info+0x3f/0x60 mm/kasan/generic.c:640
  poison_slab_object mm/kasan/common.c:241 [inline]
  __kasan_slab_free+0x121/0x1b0 mm/kasan/common.c:257
  kasan_slab_free include/linux/kasan.h:184 [inline]
  slab_free_hook mm/slub.c:2121 [inline]
  slab_free mm/slub.c:4299 [inline]
  kmem_cache_free+0x129/0x350 mm/slub.c:4363
  i_callback+0x43/0x70 fs/inode.c:249
  rcu_do_batch kernel/rcu/tree.c:2158 [inline]
  rcu_core+0x819/0x1680 kernel/rcu/tree.c:2433
  __do_softirq+0x21a/0x8de kernel/softirq.c:553

Last potentially related work creation:
  kasan_save_stack+0x33/0x50 mm/kasan/common.c:47
  __kasan_record_aux_stack+0xba/0x100 mm/kasan/generic.c:586
  __call_rcu_common.constprop.0+0x9a/0x7b0 kernel/rcu/tree.c:2683
  destroy_inode+0x129/0x1b0 fs/inode.c:315
  iput_final fs/inode.c:1739 [inline]
  iput.part.0+0x560/0x7b0 fs/inode.c:1765
  iput+0x5c/0x80 fs/inode.c:1755
  dentry_unlink_inode+0x292/0x430 fs/dcache.c:400
  __dentry_kill+0x1ca/0x5f0 fs/dcache.c:603
  dput.part.0+0x4ac/0x9a0 fs/dcache.c:845
  dput+0x1f/0x30 fs/dcache.c:835
  __fput+0x3b9/0xb70 fs/file_table.c:384
  task_work_run+0x14d/0x240 kernel/task_work.c:180
  exit_task_work include/linux/task_work.h:38 [inline]
  do_exit+0xa8a/0x2ad0 kernel/exit.c:871
  do_group_exit+0xd4/0x2a0 kernel/exit.c:1020
  __do_sys_exit_group kernel/exit.c:1031 [inline]
  __se_sys_exit_group kernel/exit.c:1029 [inline]
  __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:1029
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xd3/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

The buggy address belongs to the object at ffff88802f4fc800
 which belongs to the cache sock_inode_cache of size 1408
The buggy address is located 128 bytes inside of
 freed 1408-byte region [ffff88802f4fc800, ffff88802f4fcd80)

The buggy address belongs to the physical page:
page:ffffea0000bd3e00 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2f4f8
head:ffffea0000bd3e00 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0
anon flags: 0xfff00000000840(slab|head|node=0|zone=1|lastcpupid=0x7ff)
page_type: 0xffffffff()
raw: 00fff00000000840 ffff888013b06b40 0000000000000000 0000000000000001
raw: 0000000000000000 0000000080150015 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 3, migratetype Reclaimable, gfp_mask 0xd20d0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_RECLAIMABLE), pid 4956, tgid 4956 (sshd), ts 31423924727, free_ts 0
  set_page_owner include/linux/page_owner.h:31 [inline]
  post_alloc_hook+0x2d0/0x350 mm/page_alloc.c:1533
  prep_new_page mm/page_alloc.c:1540 [inline]
  get_page_from_freelist+0xa28/0x3780 mm/page_alloc.c:3311
  __alloc_pages+0x22f/0x2440 mm/page_alloc.c:4567
  __alloc_pages_node include/linux/gfp.h:238 [inline]
  alloc_pages_node include/linux/gfp.h:261 [inline]
  alloc_slab_page mm/slub.c:2190 [inline]
  allocate_slab mm/slub.c:2354 [inline]
  new_slab+0xcc/0x3a0 mm/slub.c:2407
  ___slab_alloc+0x4af/0x19a0 mm/slub.c:3540
  __slab_alloc.constprop.0+0x56/0xa0 mm/slub.c:3625
  __slab_alloc_node mm/slub.c:3678 [inline]
  slab_alloc_node mm/slub.c:3850 [inline]
  kmem_cache_alloc_lru+0x379/0x6f0 mm/slub.c:3879
  alloc_inode_sb include/linux/fs.h:3019 [inline]
  sock_alloc_inode+0x25/0x1c0 net/socket.c:308
  alloc_inode+0x5d/0x220 fs/inode.c:260
  new_inode_pseudo+0x16/0x80 fs/inode.c:1005
  sock_alloc+0x40/0x270 net/socket.c:634
  __sock_create+0xbc/0x800 net/socket.c:1535
  sock_create net/socket.c:1622 [inline]
  __sys_socket_create net/socket.c:1659 [inline]
  __sys_socket+0x14c/0x260 net/socket.c:1706
  __do_sys_socket net/socket.c:1720 [inline]
  __se_sys_socket net/socket.c:1718 [inline]
  __x64_sys_socket+0x72/0xb0 net/socket.c:1718
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xd3/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b
page_owner free stack trace missing

Memory state around the buggy address:
 ffff88802f4fc780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88802f4fc800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff88802f4fc880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff88802f4fc900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88802f4fc980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 43815482370c ("net: sock_def_readable() and friends RCU conversion")
Reported-and-tested-by: syzbot+32b89eaa102b372ff76d@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240126165532.3396702-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/llc/af_llc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 20551cfb7da6d..fde1140d899ef 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -226,6 +226,8 @@ static int llc_ui_release(struct socket *sock)
 	}
 	netdev_put(llc->dev, &llc->dev_tracker);
 	sock_put(sk);
+	sock_orphan(sk);
+	sock->sk = NULL;
 	llc_sk_free(sk);
 out:
 	return 0;
-- 
GitLab


From c16dfab33f99fc3ff43d48253bc2784ccb84c1de Mon Sep 17 00:00:00 2001
From: Kenzo Gomez <kenzo.sgomez@gmail.com>
Date: Sat, 27 Jan 2024 17:46:21 +0100
Subject: [PATCH 3629/4076] ALSA: hda: cs35l41: Support additional ASUS Zenbook
 UX3402VA

Add new model entry into configuration table.

Signed-off-by: Kenzo Gomez <kenzo.sgomez@gmail.com>
Link: https://lore.kernel.org/r/20240127164621.26431-1-kenzo.sgomez@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/cs35l41_hda_property.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index 35277ce890a46..59504852adc69 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -76,6 +76,7 @@ static const struct cs35l41_config cs35l41_config_table[] = {
 	{ "10431533", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431573", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "10431663", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "104316A3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104316D3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104316F3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104317F3", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
@@ -410,6 +411,7 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
 	{ "CSC3551", "10431533", generic_dsd_config },
 	{ "CSC3551", "10431573", generic_dsd_config },
 	{ "CSC3551", "10431663", generic_dsd_config },
+	{ "CSC3551", "104316A3", generic_dsd_config },
 	{ "CSC3551", "104316D3", generic_dsd_config },
 	{ "CSC3551", "104316F3", generic_dsd_config },
 	{ "CSC3551", "104317F3", generic_dsd_config },
-- 
GitLab


From 15d6daad8f8add8ef99b6e4e2b5bf0db48e1a8db Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Jan 2024 10:09:18 -0300
Subject: [PATCH 3630/4076] tools headers x86 cpufeatures: Sync with the kernel
 sources to pick TDX, Zen, APIC MSR fence changes

To pick the changes from:

  1e536e10689700e0 ("x86/cpu: Detect TDX partial write machine check erratum")
  765a0542fdc7aad7 ("x86/virt/tdx: Detect TDX during kernel boot")
  30fa92832f405d5a ("x86/CPU/AMD: Add ZenX generations flags")
  04c3024560d3a14a ("x86/barrier: Do not serialize MSR accesses on AMD")

This causes these perf files to be rebuilt and brings some X86_FEATURE
that will be used when updating the copies of
tools/arch/x86/lib/mem{cpy,set}_64.S with the kernel sources:

      CC       /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o
      CC       /tmp/build/perf/bench/mem-memset-x86-64-asm.o

And addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kai Huang <kai.huang@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/cpufeatures.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index f4542d2718f4f..29cb275a219d7 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,6 +198,7 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM	( 7*32+ 7) /* Platform supports being a TDX host */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
@@ -308,10 +309,14 @@
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 #define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
-
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
 #define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE	(11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
+#define X86_FEATURE_ZEN2		(11*32+28) /* "" CPU based on Zen2 microarchitecture */
+#define X86_FEATURE_ZEN3		(11*32+29) /* "" CPU based on Zen3 microarchitecture */
+#define X86_FEATURE_ZEN4		(11*32+30) /* "" CPU based on Zen4 microarchitecture */
+#define X86_FEATURE_ZEN1		(11*32+31) /* "" CPU based on Zen1 microarchitecture */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -495,6 +500,7 @@
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 #define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */
 
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
-- 
GitLab


From be220d2e5544ff094142d263db5cf94d034b5e39 Mon Sep 17 00:00:00 2001
From: Chhayly Leang <clw.leang@gmail.com>
Date: Fri, 26 Jan 2024 15:09:12 +0700
Subject: [PATCH 3631/4076] ALSA: hda: cs35l41: Support ASUS Zenbook UM3402YAR

Adds sound support for ASUS Zenbook UM3402YAR with missing DSD

Signed-off-by: Chhayly Leang <clw.leang@gmail.com>
Link: https://lore.kernel.org/r/20240126080912.87422-1-clw.leang@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/cs35l41_hda_property.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index 59504852adc69..d74cf11eef1ea 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -76,6 +76,7 @@ static const struct cs35l41_config cs35l41_config_table[] = {
 	{ "10431533", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431573", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "10431663", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "10431683", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
 	{ "104316A3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104316D3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104316F3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
@@ -411,6 +412,7 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
 	{ "CSC3551", "10431533", generic_dsd_config },
 	{ "CSC3551", "10431573", generic_dsd_config },
 	{ "CSC3551", "10431663", generic_dsd_config },
+	{ "CSC3551", "10431683", generic_dsd_config },
 	{ "CSC3551", "104316A3", generic_dsd_config },
 	{ "CSC3551", "104316D3", generic_dsd_config },
 	{ "CSC3551", "104316F3", generic_dsd_config },
-- 
GitLab


From f7c4cb4a3f77867612b45c6327f80eac58a8ce65 Mon Sep 17 00:00:00 2001
From: Ivan Orlov <ivan.orlov0322@gmail.com>
Date: Thu, 25 Jan 2024 22:35:19 +0000
Subject: [PATCH 3632/4076] ALSA: pcm: Add missing formats to formats list

Add 4 missing formats to 'snd_pcm_format_names' array in order to be
able to get their names with 'snd_pcm_format_name' function.

Signed-off-by: Ivan Orlov <ivan.orlov0322@gmail.com>
Link: https://lore.kernel.org/r/20240125223522.1122765-1-ivan.orlov0322@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/pcm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index a09f0154e6a70..d0788126cbab1 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -211,6 +211,10 @@ static const char * const snd_pcm_format_names[] = {
 	FORMAT(DSD_U32_LE),
 	FORMAT(DSD_U16_BE),
 	FORMAT(DSD_U32_BE),
+	FORMAT(S20_LE),
+	FORMAT(S20_BE),
+	FORMAT(U20_LE),
+	FORMAT(U20_BE),
 };
 
 /**
-- 
GitLab


From efe80f9c9063228136bc3824f7ac6b4ff2e273b4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Jan 2024 10:45:24 -0300
Subject: [PATCH 3633/4076] tools headers: Update the copy of x86's
 mem{cpy,set}_64.S used in 'perf bench'

This is to get the changes from:

  94ea9c05219518ef ("x86/headers: Replace #include <asm/export.h> with #include <linux/export.h>")
  10f4c9b9a33b7df0 ("x86/asm: Fix build of UML with KASAN")

That addresses these perf tools build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S
    diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Link: https://lore.kernel.org/lkml/ZbkIKpKdNqOFdMwJ@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/lib/memcpy_64.S          | 4 ++--
 tools/arch/x86/lib/memset_64.S          | 4 ++--
 tools/perf/util/include/linux/linkage.h | 4 ++++
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index d055b82d22ccd..59cf6f9065aa8 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -1,11 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright 2002 Andi Kleen */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
@@ -39,7 +39,7 @@ SYM_TYPED_FUNC_START(__memcpy)
 SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
-SYM_FUNC_ALIAS(memcpy, __memcpy)
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 7c59a704c4584..0199d56cb479d 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -1,10 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
 SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
-SYM_FUNC_ALIAS(memset, __memset)
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index 75e2248416f55..178b00205fe6a 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -115,6 +115,10 @@
 	SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK)
 #endif
 
+#ifndef SYM_FUNC_ALIAS_MEMFUNC
+#define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
+#endif
+
 // In the kernel sources (include/linux/cfi_types.h), this has a different
 // definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang
 // definition:
-- 
GitLab


From 7814fe24a6211a610db0b408d87420403b5b7a36 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Wed, 24 Jan 2024 09:43:57 +0000
Subject: [PATCH 3634/4076] perf evlist: Fix evlist__new_default() for > 1 core
 PMU

The 'Session topology' test currently fails with this message when
evlist__new_default() opens more than one event:

  32: Session topology                                                :
  --- start ---
  templ file: /tmp/perf-test-vv5YzZ
  Using CPUID 0x00000000410fd070
  Opening: unknown-hardware:HG
  ------------------------------------------------------------
  perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    config                           0xb00000000
    disabled                         1
  ------------------------------------------------------------
  sys_perf_event_open: pid 0  cpu -1  group_fd -1  flags 0x8 = 4
  Opening: unknown-hardware:HG
  ------------------------------------------------------------
  perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    config                           0xa00000000
    disabled                         1
  ------------------------------------------------------------
  sys_perf_event_open: pid 0  cpu -1  group_fd -1  flags 0x8 = 5
  non matching sample_type
  FAILED tests/topology.c:73 can't get session
  ---- end ----
  Session topology: FAILED!

This is because when re-opening the file and parsing the header, Perf
expects that any file that has more than one event has the sample ID
flag set. Perf record already sets the flag in a similar way when there
is more than one event, so add the same logic to evlist__new_default().

evlist__new_default() is only currently used in tests, so I don't
expect this change to have any other side effects. The other tests that
use it don't save and re-open the file so don't hit this issue.

The session topology test has been failing on Arm big.LITTLE platforms
since commit 251aa040244a3b17 ("perf parse-events: Wildcard most
"numeric" events") when evlist__new_default() started opening multiple
events for 'cycles'.

Fixes: 251aa040244a3b17 ("perf parse-events: Wildcard most "numeric" events")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: James Clark <james.clark@arm.com>
[ This was failing as well on a Rocket Lake Refresh/14700k Intel hybrid system - Arnaldo ]
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Closes: https://lore.kernel.org/lkml/CAP-5=fWVQ-7ijjK3-w1q+k2WYVNHbAcejb-xY0ptbjRw476VKA@mail.gmail.com/
Link: https://lore.kernel.org/r/20240124094358.489372-1-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 95f25e9fb994a..55a300a0977b4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -103,7 +103,14 @@ struct evlist *evlist__new_default(void)
 	err = parse_event(evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu");
 	if (err) {
 		evlist__delete(evlist);
-		evlist = NULL;
+		return NULL;
+	}
+
+	if (evlist->core.nr_entries > 1) {
+		struct evsel *evsel;
+
+		evlist__for_each_entry(evlist, evsel)
+			evsel__set_sample_id(evsel, /*can_sample_identifier=*/false);
 	}
 
 	return evlist;
-- 
GitLab


From 1f8c43b09ec6906079ac1f02e2b0a381c6f48c6c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Jan 2024 11:44:00 -0300
Subject: [PATCH 3635/4076] tools include UAPI: Sync linux/mount.h copy with
 the kernel sources

To pick the changes from:

  35e27a5744131996 ("fs: keep struct mnt_id_req extensible")
  b4c2bea8ceaa50cd ("add listmount(2) syscall")
  46eae99ef73302f9 ("add statmount(2) syscall")

That doesn't change anything in tools this time as nothing that is
harvested by the beauty scripts got changed:

  $ ls -1 tools/perf/trace/beauty/*mount*sh
  tools/perf/trace/beauty/fsmount.sh
  tools/perf/trace/beauty/mount_flags.sh
  tools/perf/trace/beauty/move_mount_flags.sh
  $

This addresses this perf build warning.

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/mount.h include/uapi/linux/mount.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZbkMiB7ZcOsLP2V5@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/mount.h | 70 ++++++++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)

diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index bb242fdcfe6b2..ad5478dbad007 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -138,4 +138,74 @@ struct mount_attr {
 /* List of all mount_attr versions. */
 #define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 __spare1;
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__u64 propagate_from;	/* Propagation from in current namespace */
+	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
+	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
+	__u64 __spare2[50];
+	char str[];		/* Variable size part containing strings */
+};
+
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+};
+
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
+#define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
+#define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+
 #endif /* _UAPI_LINUX_MOUNT_H */
-- 
GitLab


From 12b17b4eb82a41977eb848048137b5908d52845c Mon Sep 17 00:00:00 2001
From: Leonard Dallmayr <leonard.dallmayr@mailbox.org>
Date: Fri, 5 Jan 2024 13:35:51 +0100
Subject: [PATCH 3636/4076] USB: serial: cp210x: add ID for IMST iM871A-USB

The device IMST USB-Stick for Smart Meter is a rebranded IMST iM871A-USB
Wireless M-Bus USB-adapter. It is used to read wireless water, gas and
electricity meters.

Signed-off-by: Leonard Dallmayr <leonard.dallmayr@mailbox.org>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/cp210x.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 1e61fe0431715..923e0ed85444b 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -146,6 +146,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
 	{ USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */
 	{ USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */
+	{ USB_DEVICE(0x10C4, 0x87ED) }, /* IMST USB-Stick for Smart Meter */
 	{ USB_DEVICE(0x10C4, 0x8856) },	/* CEL EM357 ZigBee USB Stick - LR */
 	{ USB_DEVICE(0x10C4, 0x8857) },	/* CEL EM357 ZigBee USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
-- 
GitLab


From 129690fb229a20b6e563a77a2c85266acecf20bc Mon Sep 17 00:00:00 2001
From: JackBB Wu <wojackbb@gmail.com>
Date: Tue, 23 Jan 2024 17:39:48 +0800
Subject: [PATCH 3637/4076] USB: serial: qcserial: add new usb-id for Dell
 Wireless DW5826e

Add support for Dell DW5826e with USB-id 0x413c:0x8217 & 0x413c:0x8218.

It is 0x413c:0x8217
T:  Bus=02 Lev=01 Prnt=01 Port=05 Cnt=01 Dev#=  4 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=413c ProdID=8217 Rev= 5.04
S:  Manufacturer=DELL
S:  Product=COMPAL Electronics EXM-G1A
S:  SerialNumber=359302940050401
C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=qcserial
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=usbfs
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=qcserial
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=qcserial
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E:  Ad=87(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:* If#= 8 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=88(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

It is 0x413c:0x8218
T:  Bus=02 Lev=01 Prnt=01 Port=05 Cnt=01 Dev#=  3 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=413c ProdID=8218 Rev= 0.00
S:  Manufacturer=DELL
S:  Product=COMPAL Electronics EXM-G1A
S:  SerialNumber=359302940050401
C:* #Ifs= 1 Cfg#= 1 Atr=a0 MxPwr=  2mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=qcserial
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: JackBB Wu <wojackbb@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/qcserial.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index b1e844bf31f81..703a9c5635573 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -184,6 +184,8 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81d0)},   /* Dell Wireless 5819 */
 	{DEVICE_SWI(0x413c, 0x81d1)},   /* Dell Wireless 5818 */
 	{DEVICE_SWI(0x413c, 0x81d2)},   /* Dell Wireless 5818 */
+	{DEVICE_SWI(0x413c, 0x8217)},	/* Dell Wireless DW5826e */
+	{DEVICE_SWI(0x413c, 0x8218)},	/* Dell Wireless DW5826e QDL */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
-- 
GitLab


From d877550eaf2dc9090d782864c96939397a3c6835 Mon Sep 17 00:00:00 2001
From: Andrei Vagin <avagin@google.com>
Date: Mon, 29 Jan 2024 22:36:03 -0800
Subject: [PATCH 3638/4076] x86/fpu: Stop relying on userspace for info to
 fault in xsave buffer

Before this change, the expected size of the user space buffer was
taken from fx_sw->xstate_size. fx_sw->xstate_size can be changed
from user-space, so it is possible construct a sigreturn frame where:

 * fx_sw->xstate_size is smaller than the size required by valid bits in
   fx_sw->xfeatures.
 * user-space unmaps parts of the sigrame fpu buffer so that not all of
   the buffer required by xrstor is accessible.

In this case, xrstor tries to restore and accesses the unmapped area
which results in a fault. But fault_in_readable succeeds because buf +
fx_sw->xstate_size is within the still mapped area, so it goes back and
tries xrstor again. It will spin in this loop forever.

Instead, fault in the maximum size which can be touched by XRSTOR (taken
from fpstate->user_size).

[ dhansen: tweak subject / changelog ]

Fixes: fcb3635f5018 ("x86/fpu/signal: Handle #PF in the direct restore path")
Reported-by: Konstantin Bogomolov <bogomolov@google.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrei Vagin <avagin@google.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20240130063603.3392627-1-avagin%40google.com
---
 arch/x86/kernel/fpu/signal.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 558076dbde5bf..247f2225aa9f3 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
  * Attempt to restore the FPU registers directly from user memory.
  * Pagefaults are handled and any errors returned are fatal.
  */
-static bool restore_fpregs_from_user(void __user *buf, u64 xrestore,
-				     bool fx_only, unsigned int size)
+static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
 {
 	struct fpu *fpu = &current->thread.fpu;
 	int ret;
 
+	/* Restore enabled features only. */
+	xrestore &= fpu->fpstate->user_xfeatures;
 retry:
 	fpregs_lock();
 	/* Ensure that XFD is up to date */
@@ -309,7 +310,7 @@ retry:
 		if (ret != X86_TRAP_PF)
 			return false;
 
-		if (!fault_in_readable(buf, size))
+		if (!fault_in_readable(buf, fpu->fpstate->user_size))
 			goto retry;
 		return false;
 	}
@@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 	struct user_i387_ia32_struct env;
 	bool success, fx_only = false;
 	union fpregs_state *fpregs;
-	unsigned int state_size;
 	u64 user_xfeatures = 0;
 
 	if (use_xsave()) {
@@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 			return false;
 
 		fx_only = !fx_sw_user.magic1;
-		state_size = fx_sw_user.xstate_size;
 		user_xfeatures = fx_sw_user.xfeatures;
 	} else {
 		user_xfeatures = XFEATURE_MASK_FPSSE;
-		state_size = fpu->fpstate->user_size;
 	}
 
 	if (likely(!ia32_fxstate)) {
 		/* Restore the FPU registers directly from user memory. */
-		return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only,
-						state_size);
+		return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only);
 	}
 
 	/*
-- 
GitLab


From a3fa9838e8140584a6f338e8516f2b05d3bea812 Mon Sep 17 00:00:00 2001
From: Patrick Rudolph <patrick.rudolph@9elements.com>
Date: Tue, 30 Jan 2024 20:32:56 +0530
Subject: [PATCH 3639/4076] regulator (max5970): Fix IRQ handler

The max5970 datasheet gives the impression that IRQ status bits must
be cleared by writing a one to set bits, as those are marked with 'R/C',
however tests showed that a zero must be written.

Fixes an IRQ storm as the interrupt handler actually clears the IRQ
status bits.

Signed-off-by: Patrick Rudolph <patrick.rudolph@9elements.com>
Signed-off-by: Naresh Solanki <naresh.solanki@9elements.com>
Link: https://msgid.link/r/20240130150257.3643657-1-naresh.solanki@9elements.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/max5970-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/max5970-regulator.c b/drivers/regulator/max5970-regulator.c
index bc88a40a88d4c..830a1c4cd7057 100644
--- a/drivers/regulator/max5970-regulator.c
+++ b/drivers/regulator/max5970-regulator.c
@@ -392,7 +392,7 @@ static int max597x_regmap_read_clear(struct regmap *map, unsigned int reg,
 		return ret;
 
 	if (*val)
-		return regmap_write(map, reg, *val);
+		return regmap_write(map, reg, 0);
 
 	return 0;
 }
-- 
GitLab


From 6500ad28fd5d67d5ca0fee9da73c463090842440 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Tue, 30 Jan 2024 10:40:53 +0100
Subject: [PATCH 3640/4076] spi: sh-msiof: avoid integer overflow in constants

cppcheck rightfully warned:

 drivers/spi/spi-sh-msiof.c:792:28: warning: Signed integer overflow for expression '7<<29'. [integerOverflow]
 sh_msiof_write(p, SIFCTR, SIFCTR_TFWM_1 | SIFCTR_RFWM_1);

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://msgid.link/r/20240130094053.10672-1-wsa+renesas@sang-engineering.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-sh-msiof.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index cfc3b1ddbd229..6f12e4fb2e2e1 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -136,14 +136,14 @@ struct sh_msiof_spi_priv {
 
 /* SIFCTR */
 #define SIFCTR_TFWM_MASK	GENMASK(31, 29)	/* Transmit FIFO Watermark */
-#define SIFCTR_TFWM_64		(0 << 29)	/*  Transfer Request when 64 empty stages */
-#define SIFCTR_TFWM_32		(1 << 29)	/*  Transfer Request when 32 empty stages */
-#define SIFCTR_TFWM_24		(2 << 29)	/*  Transfer Request when 24 empty stages */
-#define SIFCTR_TFWM_16		(3 << 29)	/*  Transfer Request when 16 empty stages */
-#define SIFCTR_TFWM_12		(4 << 29)	/*  Transfer Request when 12 empty stages */
-#define SIFCTR_TFWM_8		(5 << 29)	/*  Transfer Request when 8 empty stages */
-#define SIFCTR_TFWM_4		(6 << 29)	/*  Transfer Request when 4 empty stages */
-#define SIFCTR_TFWM_1		(7 << 29)	/*  Transfer Request when 1 empty stage */
+#define SIFCTR_TFWM_64		(0UL << 29)	/*  Transfer Request when 64 empty stages */
+#define SIFCTR_TFWM_32		(1UL << 29)	/*  Transfer Request when 32 empty stages */
+#define SIFCTR_TFWM_24		(2UL << 29)	/*  Transfer Request when 24 empty stages */
+#define SIFCTR_TFWM_16		(3UL << 29)	/*  Transfer Request when 16 empty stages */
+#define SIFCTR_TFWM_12		(4UL << 29)	/*  Transfer Request when 12 empty stages */
+#define SIFCTR_TFWM_8		(5UL << 29)	/*  Transfer Request when 8 empty stages */
+#define SIFCTR_TFWM_4		(6UL << 29)	/*  Transfer Request when 4 empty stages */
+#define SIFCTR_TFWM_1		(7UL << 29)	/*  Transfer Request when 1 empty stage */
 #define SIFCTR_TFUA_MASK	GENMASK(26, 20) /* Transmit FIFO Usable Area */
 #define SIFCTR_TFUA_SHIFT	20
 #define SIFCTR_TFUA(i)		((i) << SIFCTR_TFUA_SHIFT)
-- 
GitLab


From f1fea725cc93fcc3c5af9a2af63ffdc40dd2259e Mon Sep 17 00:00:00 2001
From: Joe Lawrence <joe.lawrence@redhat.com>
Date: Wed, 20 Dec 2023 10:11:51 -0500
Subject: [PATCH 3641/4076] selftests/livepatch: fix and refactor new dmesg
 message code

The livepatching kselftests rely on comparing expected vs. observed
dmesg output.  After each test, new dmesg entries are determined by the
'comm' utility comparing a saved, pre-test copy of dmesg to post-test
dmesg output.

Alexander reports that the 'comm --nocheck-order -13' invocation used by
the tests can be confused when dmesg entry timestamps vary in magnitude
(ie, "[   98.820331]" vs. "[  100.031067]"), in which case, additional
messages are reported as new.  The unexpected entries then spoil the
test results.

Instead of relying on 'comm' or 'diff' to determine new testing dmesg
entries, refactor the code:

  - pre-test  : log a unique canary dmesg entry
  - test      : run tests, log messages
  - post-test : filter dmesg starting from pre-test message

Reported-by: Alexander Gordeev <agordeev@linux.ibm.com>
Closes: https://lore.kernel.org/live-patching/ZYAimyPYhxVA9wKg@li-008a6a4c-3549-11b2-a85c-c5cc2836eea2.ibm.com/
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Tested-by: Marcos Paulo de Souza <mpdesouza@suse.com>
Reviewed-by: Marcos Paulo de Souza <mpdesouza@suse.com>
Acked-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .../testing/selftests/livepatch/functions.sh  | 37 +++++++++----------
 1 file changed, 17 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh
index c8416c54b4637..b1fd7362c2fee 100644
--- a/tools/testing/selftests/livepatch/functions.sh
+++ b/tools/testing/selftests/livepatch/functions.sh
@@ -42,17 +42,6 @@ function die() {
 	exit 1
 }
 
-# save existing dmesg so we can detect new content
-function save_dmesg() {
-	SAVED_DMESG=$(mktemp --tmpdir -t klp-dmesg-XXXXXX)
-	dmesg > "$SAVED_DMESG"
-}
-
-# cleanup temporary dmesg file from save_dmesg()
-function cleanup_dmesg_file() {
-	rm -f "$SAVED_DMESG"
-}
-
 function push_config() {
 	DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \
 			awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}')
@@ -99,7 +88,6 @@ function set_ftrace_enabled() {
 
 function cleanup() {
 	pop_config
-	cleanup_dmesg_file
 }
 
 # setup_config - save the current config and set a script exit trap that
@@ -280,7 +268,15 @@ function set_pre_patch_ret {
 function start_test {
 	local test="$1"
 
-	save_dmesg
+	# Dump something unique into the dmesg log, then stash the entry
+	# in LAST_DMESG.  The check_result() function will use it to
+	# find new kernel messages since the test started.
+	local last_dmesg_msg="livepatch kselftest timestamp: $(date --rfc-3339=ns)"
+	log "$last_dmesg_msg"
+	loop_until 'dmesg | grep -q "$last_dmesg_msg"' ||
+		die "buffer busy? can't find canary dmesg message: $last_dmesg_msg"
+	LAST_DMESG=$(dmesg | grep "$last_dmesg_msg")
+
 	echo -n "TEST: $test ... "
 	log "===== TEST: $test ====="
 }
@@ -291,23 +287,24 @@ function check_result {
 	local expect="$*"
 	local result
 
-	# Note: when comparing dmesg output, the kernel log timestamps
-	# help differentiate repeated testing runs.  Remove them with a
-	# post-comparison sed filter.
-
-	result=$(dmesg | comm --nocheck-order -13 "$SAVED_DMESG" - | \
+	# Test results include any new dmesg entry since LAST_DMESG, then:
+	# - include lines matching keywords
+	# - exclude lines matching keywords
+	# - filter out dmesg timestamp prefixes
+	result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \
 		 grep -e 'livepatch:' -e 'test_klp' | \
 		 grep -v '\(tainting\|taints\) kernel' | \
 		 sed 's/^\[[ 0-9.]*\] //')
 
 	if [[ "$expect" == "$result" ]] ; then
 		echo "ok"
+	elif [[ "$result" == "" ]] ; then
+		echo -e "not ok\n\nbuffer overrun? can't find canary dmesg entry: $LAST_DMESG\n"
+		die "livepatch kselftest(s) failed"
 	else
 		echo -e "not ok\n\n$(diff -upr --label expected --label result <(echo "$expect") <(echo "$result"))\n"
 		die "livepatch kselftest(s) failed"
 	fi
-
-	cleanup_dmesg_file
 }
 
 # check_sysfs_rights(modname, rel_path, expected_rights) - check sysfs
-- 
GitLab


From 5820cfee443f8a90ea3eb9f99f57f2049a4a93c3 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Wed, 24 Jan 2024 13:00:18 +0000
Subject: [PATCH 3642/4076] kselftest/seccomp: Use kselftest output functions
 for benchmark

In preparation for trying to output the test results themselves in TAP
format rework all the prints in the benchmark to use the kselftest output
functions. The uses of system() all produce single line output so we can
avoid having to deal with fully managing the child process and continue to
use system() by simply printing an empty message before we invoke system().
We also leave one printf() used to complete a line of output in place.

Tested-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .../selftests/seccomp/seccomp_benchmark.c     | 45 ++++++++++---------
 1 file changed, 24 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
index 5b5c9d558dee0..93168dd2c1e30 100644
--- a/tools/testing/selftests/seccomp/seccomp_benchmark.c
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -38,10 +38,10 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples)
 	i *= 1000000000ULL;
 	i += finish.tv_nsec - start.tv_nsec;
 
-	printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n",
-		finish.tv_sec, finish.tv_nsec,
-		start.tv_sec, start.tv_nsec,
-		i, (double)i / 1000000000.0);
+	ksft_print_msg("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n",
+		       finish.tv_sec, finish.tv_nsec,
+		       start.tv_sec, start.tv_nsec,
+		       i, (double)i / 1000000000.0);
 
 	return i;
 }
@@ -53,7 +53,7 @@ unsigned long long calibrate(void)
 	pid_t pid, ret;
 	int seconds = 15;
 
-	printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds);
+	ksft_print_msg("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds);
 
 	samples = 0;
 	pid = getpid();
@@ -102,14 +102,14 @@ long compare(const char *name_one, const char *name_eval, const char *name_two,
 {
 	bool good;
 
-	printf("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
-	       (long long)one, name_eval, (long long)two);
+	ksft_print_msg("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
+		       (long long)one, name_eval, (long long)two);
 	if (one > INT_MAX) {
-		printf("Miscalculation! Measurement went negative: %lld\n", (long long)one);
+		ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)one);
 		return 1;
 	}
 	if (two > INT_MAX) {
-		printf("Miscalculation! Measurement went negative: %lld\n", (long long)two);
+		ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)two);
 		return 1;
 	}
 
@@ -145,12 +145,15 @@ int main(int argc, char *argv[])
 
 	setbuf(stdout, NULL);
 
-	printf("Running on:\n");
+	ksft_print_msg("Running on:\n");
+	ksft_print_msg("");
 	system("uname -a");
 
-	printf("Current BPF sysctl settings:\n");
+	ksft_print_msg("Current BPF sysctl settings:\n");
 	/* Avoid using "sysctl" which may not be installed. */
+	ksft_print_msg("");
 	system("grep -H . /proc/sys/net/core/bpf_jit_enable");
+	ksft_print_msg("");
 	system("grep -H . /proc/sys/net/core/bpf_jit_harden");
 
 	if (argc > 1)
@@ -158,11 +161,11 @@ int main(int argc, char *argv[])
 	else
 		samples = calibrate();
 
-	printf("Benchmarking %llu syscalls...\n", samples);
+	ksft_print_msg("Benchmarking %llu syscalls...\n", samples);
 
 	/* Native call */
 	native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid native: %llu ns\n", native);
+	ksft_print_msg("getpid native: %llu ns\n", native);
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	assert(ret == 0);
@@ -172,33 +175,33 @@ int main(int argc, char *argv[])
 	assert(ret == 0);
 
 	bitmap1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1);
+	ksft_print_msg("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1);
 
 	/* Second filter resulting in a bitmap */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
 	assert(ret == 0);
 
 	bitmap2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2);
+	ksft_print_msg("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2);
 
 	/* Third filter, can no longer be converted to bitmap */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
 	assert(ret == 0);
 
 	filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1);
+	ksft_print_msg("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1);
 
 	/* Fourth filter, can not be converted to bitmap because of filter 3 */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
 	assert(ret == 0);
 
 	filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2);
+	ksft_print_msg("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2);
 
 	/* Estimations */
 #define ESTIMATE(fmt, var, what)	do {			\
 		var = (what);					\
-		printf("Estimated " fmt ": %llu ns\n", var);	\
+		ksft_print_msg("Estimated " fmt ": %llu ns\n", var);	\
 		if (var > INT_MAX)				\
 			goto more_samples;			\
 	} while (0)
@@ -218,7 +221,7 @@ int main(int argc, char *argv[])
 	ESTIMATE("seccomp per-filter overhead (filters / 4)", per_filter2,
 		 (filter2 - native - entry) / 4);
 
-	printf("Expectations:\n");
+	ksft_print_msg("Expectations:\n");
 	ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1);
 	bits = compare("native", "≤", "1 filter", native, le, filter1);
 	if (bits)
@@ -230,7 +233,7 @@ int main(int argc, char *argv[])
 	bits = compare("1 bitmapped", "≈", "2 bitmapped",
 			bitmap1 - native, approx, bitmap2 - native);
 	if (bits) {
-		printf("Skipping constant action bitmap expectations: they appear unsupported.\n");
+		ksft_print_msg("Skipping constant action bitmap expectations: they appear unsupported.\n");
 		goto out;
 	}
 
@@ -242,7 +245,7 @@ int main(int argc, char *argv[])
 		goto out;
 
 more_samples:
-	printf("Saw unexpected benchmark result. Try running again with more samples?\n");
+	ksft_print_msg("Saw unexpected benchmark result. Try running again with more samples?\n");
 out:
 	return 0;
 }
-- 
GitLab


From b54761f6e9773350c0d1fb8e1e5aacaba7769d0f Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Wed, 24 Jan 2024 13:00:19 +0000
Subject: [PATCH 3643/4076] kselftest/seccomp: Report each expectation we
 assert as a KTAP test

The seccomp benchmark test makes a number of checks on the performance it
measures and logs them to the output but does so in a custom format which
none of the automated test runners understand meaning that the chances that
anyone is paying attention are slim. Let's additionally log each result in
KTAP format so that automated systems parsing the test output will see each
comparison as a test case. The original logs are left in place since they
provide the actual numbers for analysis.

As part of this rework the flow for the main program so that when we skip
tests we still log all the tests we skip, this is because the standard KTAP
headers and footers include counts of the number of expected and run tests.

Tested-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .../selftests/seccomp/seccomp_benchmark.c     | 61 +++++++++++++------
 1 file changed, 41 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
index 93168dd2c1e30..97b86980b768f 100644
--- a/tools/testing/selftests/seccomp/seccomp_benchmark.c
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -98,24 +98,36 @@ bool le(int i_one, int i_two)
 }
 
 long compare(const char *name_one, const char *name_eval, const char *name_two,
-	     unsigned long long one, bool (*eval)(int, int), unsigned long long two)
+	     unsigned long long one, bool (*eval)(int, int), unsigned long long two,
+	     bool skip)
 {
 	bool good;
 
+	if (skip) {
+		ksft_test_result_skip("%s %s %s\n", name_one, name_eval,
+				      name_two);
+		return 0;
+	}
+
 	ksft_print_msg("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
 		       (long long)one, name_eval, (long long)two);
 	if (one > INT_MAX) {
 		ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)one);
-		return 1;
+		good = false;
+		goto out;
 	}
 	if (two > INT_MAX) {
 		ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)two);
-		return 1;
+		good = false;
+		goto out;
 	}
 
 	good = eval(one, two);
 	printf("%s\n", good ? "✔️" : "❌");
 
+out:
+	ksft_test_result(good, "%s %s %s\n", name_one, name_eval, name_two);
+
 	return good ? 0 : 1;
 }
 
@@ -142,9 +154,13 @@ int main(int argc, char *argv[])
 	unsigned long long samples, calc;
 	unsigned long long native, filter1, filter2, bitmap1, bitmap2;
 	unsigned long long entry, per_filter1, per_filter2;
+	bool skip = false;
 
 	setbuf(stdout, NULL);
 
+	ksft_print_header();
+	ksft_set_plan(7);
+
 	ksft_print_msg("Running on:\n");
 	ksft_print_msg("");
 	system("uname -a");
@@ -202,8 +218,10 @@ int main(int argc, char *argv[])
 #define ESTIMATE(fmt, var, what)	do {			\
 		var = (what);					\
 		ksft_print_msg("Estimated " fmt ": %llu ns\n", var);	\
-		if (var > INT_MAX)				\
-			goto more_samples;			\
+		if (var > INT_MAX) {				\
+			skip = true;				\
+			ret |= 1;				\
+		}						\
 	} while (0)
 
 	ESTIMATE("total seccomp overhead for 1 bitmapped filter", calc,
@@ -222,30 +240,33 @@ int main(int argc, char *argv[])
 		 (filter2 - native - entry) / 4);
 
 	ksft_print_msg("Expectations:\n");
-	ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1);
-	bits = compare("native", "≤", "1 filter", native, le, filter1);
+	ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1,
+		       skip);
+	bits = compare("native", "≤", "1 filter", native, le, filter1,
+		       skip);
 	if (bits)
-		goto more_samples;
+		skip = true;
 
 	ret |= compare("per-filter (last 2 diff)", "≈", "per-filter (filters / 4)",
-			per_filter1, approx, per_filter2);
+		       per_filter1, approx, per_filter2, skip);
 
 	bits = compare("1 bitmapped", "≈", "2 bitmapped",
-			bitmap1 - native, approx, bitmap2 - native);
+		       bitmap1 - native, approx, bitmap2 - native, skip);
 	if (bits) {
 		ksft_print_msg("Skipping constant action bitmap expectations: they appear unsupported.\n");
-		goto out;
+		skip = true;
 	}
 
-	ret |= compare("entry", "≈", "1 bitmapped", entry, approx, bitmap1 - native);
-	ret |= compare("entry", "≈", "2 bitmapped", entry, approx, bitmap2 - native);
+	ret |= compare("entry", "≈", "1 bitmapped", entry, approx,
+		       bitmap1 - native, skip);
+	ret |= compare("entry", "≈", "2 bitmapped", entry, approx,
+		       bitmap2 - native, skip);
 	ret |= compare("native + entry + (per filter * 4)", "≈", "4 filters total",
-			entry + (per_filter1 * 4) + native, approx, filter2);
-	if (ret == 0)
-		goto out;
+		       entry + (per_filter1 * 4) + native, approx, filter2,
+		       skip);
 
-more_samples:
-	ksft_print_msg("Saw unexpected benchmark result. Try running again with more samples?\n");
-out:
-	return 0;
+	if (ret)
+		ksft_print_msg("Saw unexpected benchmark result. Try running again with more samples?\n");
+
+	ksft_finished();
 }
-- 
GitLab


From 8b1d72395635af45410b66cc4c4ab37a12c4a831 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Sat, 20 Jan 2024 15:29:27 +0100
Subject: [PATCH 3644/4076] parisc: Fix random data corruption from exception
 handler

The current exception handler implementation, which assists when accessing
user space memory, may exhibit random data corruption if the compiler decides
to use a different register than the specified register %r29 (defined in
ASM_EXCEPTIONTABLE_REG) for the error code. If the compiler choose another
register, the fault handler will nevertheless store -EFAULT into %r29 and thus
trash whatever this register is used for.
Looking at the assembly I found that this happens sometimes in emulate_ldd().

To solve the issue, the easiest solution would be if it somehow is
possible to tell the fault handler which register is used to hold the error
code. Using %0 or %1 in the inline assembly is not posssible as it will show
up as e.g. %r29 (with the "%r" prefix), which the GNU assembler can not
convert to an integer.

This patch takes another, better and more flexible approach:
We extend the __ex_table (which is out of the execution path) by one 32-word.
In this word we tell the compiler to insert the assembler instruction
"or %r0,%r0,%reg", where %reg references the register which the compiler
choosed for the error return code.
In case of an access failure, the fault handler finds the __ex_table entry and
can examine the opcode. The used register is encoded in the lowest 5 bits, and
the fault handler can then store -EFAULT into this register.

Since we extend the __ex_table to 3 words we can't use the BUILDTIME_TABLE_SORT
config option any longer.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.0+
---
 arch/parisc/Kconfig                     |  1 -
 arch/parisc/include/asm/assembly.h      |  1 +
 arch/parisc/include/asm/extable.h       | 64 +++++++++++++++++++++++++
 arch/parisc/include/asm/special_insns.h |  6 ++-
 arch/parisc/include/asm/uaccess.h       | 48 +++----------------
 arch/parisc/kernel/cache.c              |  4 +-
 arch/parisc/kernel/unaligned.c          | 44 ++++++++---------
 arch/parisc/mm/fault.c                  | 11 +++--
 8 files changed, 108 insertions(+), 71 deletions(-)
 create mode 100644 arch/parisc/include/asm/extable.h

diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index d14ccc948a29b..5c845e8d59d92 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -25,7 +25,6 @@ config PARISC
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
 	select BUG
-	select BUILDTIME_TABLE_SORT
 	select HAVE_KERNEL_UNCOMPRESSED
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 74d17d7e759da..5937d5edaba1e 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -576,6 +576,7 @@
 	.section __ex_table,"aw"			!	\
 	.align 4					!	\
 	.word (fault_addr - .), (except_addr - .)	!	\
+	or %r0,%r0,%r0					!	\
 	.previous
 
 
diff --git a/arch/parisc/include/asm/extable.h b/arch/parisc/include/asm/extable.h
new file mode 100644
index 0000000000000..4ea23e3d79dc9
--- /dev/null
+++ b/arch/parisc/include/asm/extable.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PARISC_EXTABLE_H
+#define __PARISC_EXTABLE_H
+
+#include <asm/ptrace.h>
+#include <linux/compiler.h>
+
+/*
+ * The exception table consists of three addresses:
+ *
+ * - A relative address to the instruction that is allowed to fault.
+ * - A relative address at which the program should continue (fixup routine)
+ * - An asm statement which specifies which CPU register will
+ *   receive -EFAULT when an exception happens if the lowest bit in
+ *   the fixup address is set.
+ *
+ * Note: The register specified in the err_opcode instruction will be
+ * modified at runtime if a fault happens. Register %r0 will be ignored.
+ *
+ * Since relative addresses are used, 32bit values are sufficient even on
+ * 64bit kernel.
+ */
+
+struct pt_regs;
+int fixup_exception(struct pt_regs *regs);
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+struct exception_table_entry {
+	int insn;	/* relative address of insn that is allowed to fault. */
+	int fixup;	/* relative address of fixup routine */
+	int err_opcode; /* sample opcode with register which holds error code */
+};
+
+#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr, opcode )\
+	".section __ex_table,\"aw\"\n"			   \
+	".align 4\n"					   \
+	".word (" #fault_addr " - .), (" #except_addr " - .)\n" \
+	opcode "\n"					   \
+	".previous\n"
+
+/*
+ * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
+ * (with lowest bit set) for which the fault handler in fixup_exception() will
+ * load -EFAULT on fault into the register specified by the err_opcode instruction,
+ * and zeroes the target register in case of a read fault in get_user().
+ */
+#define ASM_EXCEPTIONTABLE_VAR(__err_var)		\
+	int __err_var = 0
+#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr, register )\
+	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1, "or %%r0,%%r0," register)
+
+static inline void swap_ex_entry_fixup(struct exception_table_entry *a,
+				       struct exception_table_entry *b,
+				       struct exception_table_entry tmp,
+				       int delta)
+{
+	a->fixup = b->fixup + delta;
+	b->fixup = tmp.fixup - delta;
+	a->err_opcode = b->err_opcode;
+	b->err_opcode = tmp.err_opcode;
+}
+#define swap_ex_entry_fixup swap_ex_entry_fixup
+
+#endif
diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h
index c822bd0c0e3c6..51f40eaf77806 100644
--- a/arch/parisc/include/asm/special_insns.h
+++ b/arch/parisc/include/asm/special_insns.h
@@ -8,7 +8,8 @@
 		"copy %%r0,%0\n"			\
 		"8:\tlpa %%r0(%1),%0\n"			\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b,	\
+				"or %%r0,%%r0,%%r0")	\
 		: "=&r" (pa)				\
 		: "r" (va)				\
 		: "memory"				\
@@ -22,7 +23,8 @@
 		"copy %%r0,%0\n"			\
 		"8:\tlpa %%r0(%%sr3,%1),%0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b,	\
+				"or %%r0,%%r0,%%r0")	\
 		: "=&r" (pa)				\
 		: "r" (va)				\
 		: "memory"				\
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 4165079898d9e..88d0ae5769dde 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -7,6 +7,7 @@
  */
 #include <asm/page.h>
 #include <asm/cache.h>
+#include <asm/extable.h>
 
 #include <linux/bug.h>
 #include <linux/string.h>
@@ -26,37 +27,6 @@
 #define STD_USER(sr, x, ptr)	__put_user_asm(sr, "std", x, ptr)
 #endif
 
-/*
- * The exception table contains two values: the first is the relative offset to
- * the address of the instruction that is allowed to fault, and the second is
- * the relative offset to the address of the fixup routine. Since relative
- * addresses are used, 32bit values are sufficient even on 64bit kernel.
- */
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-struct exception_table_entry {
-	int insn;	/* relative address of insn that is allowed to fault. */
-	int fixup;	/* relative address of fixup routine */
-};
-
-#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\
-	".section __ex_table,\"aw\"\n"			   \
-	".align 4\n"					   \
-	".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \
-	".previous\n"
-
-/*
- * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
- * (with lowest bit set) for which the fault handler in fixup_exception() will
- * load -EFAULT into %r29 for a read or write fault, and zeroes the target
- * register in case of a read fault in get_user().
- */
-#define ASM_EXCEPTIONTABLE_REG	29
-#define ASM_EXCEPTIONTABLE_VAR(__variable)		\
-	register long __variable __asm__ ("r29") = 0
-#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\
-	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1)
-
 #define __get_user_internal(sr, val, ptr)		\
 ({							\
 	ASM_EXCEPTIONTABLE_VAR(__gu_err);		\
@@ -83,7 +53,7 @@ struct exception_table_entry {
 							\
 	__asm__("1: " ldx " 0(%%sr%2,%3),%0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1")	\
 		: "=r"(__gu_val), "+r"(__gu_err)        \
 		: "i"(sr), "r"(ptr));			\
 							\
@@ -115,8 +85,8 @@ struct exception_table_entry {
 		"1: ldw 0(%%sr%2,%3),%0\n"		\
 		"2: ldw 4(%%sr%2,%3),%R0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1")	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%1")	\
 		: "=&r"(__gu_tmp.l), "+r"(__gu_err)	\
 		: "i"(sr), "r"(ptr));			\
 							\
@@ -174,7 +144,7 @@ struct exception_table_entry {
 	__asm__ __volatile__ (					\
 		"1: " stx " %1,0(%%sr%2,%3)\n"			\
 		"9:\n"						\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0")	\
 		: "+r"(__pu_err)				\
 		: "r"(x), "i"(sr), "r"(ptr))
 
@@ -186,15 +156,14 @@ struct exception_table_entry {
 		"1: stw %1,0(%%sr%2,%3)\n"			\
 		"2: stw %R1,4(%%sr%2,%3)\n"			\
 		"9:\n"						\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0")	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%0")	\
 		: "+r"(__pu_err)				\
 		: "r"(__val), "i"(sr), "r"(ptr));		\
 } while (0)
 
 #endif /* !defined(CONFIG_64BIT) */
 
-
 /*
  * Complex access routines -- external declarations
  */
@@ -216,7 +185,4 @@ unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src,
 #define INLINE_COPY_TO_USER
 #define INLINE_COPY_FROM_USER
 
-struct pt_regs;
-int fixup_exception(struct pt_regs *regs);
-
 #endif /* __PARISC_UACCESS_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 0c015487e5db6..5552602fcaef1 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -854,7 +854,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #endif
 			"   fic,m	%3(%4,%0)\n"
 			"2: sync\n"
-			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b)
+			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
 			: "r" (end), "r" (dcache_stride), "i" (SR_USER));
 	}
@@ -869,7 +869,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #endif
 			"   fdc,m	%3(%4,%0)\n"
 			"2: sync\n"
-			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b)
+			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
 			: "r" (end), "r" (icache_stride), "i" (SR_USER));
 	}
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index ce25acfe4889d..c520e551a1652 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -120,8 +120,8 @@ static int emulate_ldh(struct pt_regs *regs, int toreg)
 "2:	ldbs	1(%%sr1,%3), %0\n"
 "	depw	%2, 23, 24, %0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "+r" (val), "+r" (ret), "=&r" (temp1)
 	: "r" (saddr), "r" (regs->isr) );
 
@@ -152,8 +152,8 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop)
 "	mtctl	%2,11\n"
 "	vshd	%0,%3,%0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "+r" (val), "+r" (ret), "=&r" (temp1), "=&r" (temp2)
 	: "r" (saddr), "r" (regs->isr) );
 
@@ -189,8 +189,8 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop)
 "	mtsar	%%r19\n"
 "	shrpd	%0,%%r20,%%sar,%0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "=r" (val), "+r" (ret)
 	: "0" (val), "r" (saddr), "r" (regs->isr)
 	: "r19", "r20" );
@@ -209,9 +209,9 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop)
 "	vshd	%0,%R0,%0\n"
 "	vshd	%R0,%4,%R0\n"
 "4:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1")
 	: "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1)
 	: "r" (regs->isr) );
     }
@@ -244,8 +244,8 @@ static int emulate_sth(struct pt_regs *regs, int frreg)
 "1:	stb %1, 0(%%sr1, %3)\n"
 "2:	stb %2, 1(%%sr1, %3)\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0")
 	: "+r" (ret), "=&r" (temp1)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr) );
 
@@ -285,8 +285,8 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop)
 "	stw	%%r20,0(%%sr1,%2)\n"
 "	stw	%%r21,4(%%sr1,%2)\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r22", "r1" );
@@ -329,10 +329,10 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop)
 "3:	std	%%r20,0(%%sr1,%2)\n"
 "4:	std	%%r21,8(%%sr1,%2)\n"
 "5:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r22", "r1" );
@@ -357,11 +357,11 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop)
 "4:	stw	%%r1,4(%%sr1,%2)\n"
 "5:	stw	%R1,8(%%sr1,%2)\n"
 "6:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r1" );
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 2fe5b44986e09..c39de84e98b05 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -150,11 +150,16 @@ int fixup_exception(struct pt_regs *regs)
 		 * Fix up get_user() and put_user().
 		 * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant
 		 * bit in the relative address of the fixup routine to indicate
-		 * that gr[ASM_EXCEPTIONTABLE_REG] should be loaded with
-		 * -EFAULT to report a userspace access error.
+		 * that the register encoded in the "or %r0,%r0,register"
+		 * opcode should be loaded with -EFAULT to report a userspace
+		 * access error.
 		 */
 		if (fix->fixup & 1) {
-			regs->gr[ASM_EXCEPTIONTABLE_REG] = -EFAULT;
+			int fault_error_reg = fix->err_opcode & 0x1f;
+			if (!WARN_ON(!fault_error_reg))
+				regs->gr[fault_error_reg] = -EFAULT;
+			pr_debug("Unalignment fixup of register %d at %pS\n",
+				fault_error_reg, (void*)regs->iaoq[0]);
 
 			/* zero target register for get_user() */
 			if (parisc_acctyp(0, regs->iir) == VM_READ) {
-- 
GitLab


From a22fe1d6dec7e98535b97249fdc95c2be79120bb Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 23 Jan 2024 12:28:41 -0500
Subject: [PATCH 3645/4076] dmaengine: fix is_slave_direction() return false
 when DMA_DEV_TO_DEV

is_slave_direction() should return true when direction is DMA_DEV_TO_DEV.

Fixes: 49920bc66984 ("dmaengine: add new enum dma_transfer_direction")
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20240123172842.3764529-1-Frank.Li@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dmaengine.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 3df70d6131c8f..752dbde4cec1f 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -953,7 +953,8 @@ static inline int dmaengine_slave_config(struct dma_chan *chan,
 
 static inline bool is_slave_direction(enum dma_transfer_direction direction)
 {
-	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM);
+	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM) ||
+	       (direction == DMA_DEV_TO_DEV);
 }
 
 static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
-- 
GitLab


From 7104ba0f1958adb250319e68a15eff89ec4fd36d Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Sun, 28 Jan 2024 14:05:54 +0200
Subject: [PATCH 3646/4076] phy: ti: phy-omap-usb2: Fix NULL pointer
 dereference for SRP

If the external phy working together with phy-omap-usb2 does not implement
send_srp(), we may still attempt to call it. This can happen on an idle
Ethernet gadget triggering a wakeup for example:

configfs-gadget.g1 gadget.0: ECM Suspend
configfs-gadget.g1 gadget.0: Port suspended. Triggering wakeup
...
Unable to handle kernel NULL pointer dereference at virtual address
00000000 when execute
...
PC is at 0x0
LR is at musb_gadget_wakeup+0x1d4/0x254 [musb_hdrc]
...
musb_gadget_wakeup [musb_hdrc] from usb_gadget_wakeup+0x1c/0x3c [udc_core]
usb_gadget_wakeup [udc_core] from eth_start_xmit+0x3b0/0x3d4 [u_ether]
eth_start_xmit [u_ether] from dev_hard_start_xmit+0x94/0x24c
dev_hard_start_xmit from sch_direct_xmit+0x104/0x2e4
sch_direct_xmit from __dev_queue_xmit+0x334/0xd88
__dev_queue_xmit from arp_solicit+0xf0/0x268
arp_solicit from neigh_probe+0x54/0x7c
neigh_probe from __neigh_event_send+0x22c/0x47c
__neigh_event_send from neigh_resolve_output+0x14c/0x1c0
neigh_resolve_output from ip_finish_output2+0x1c8/0x628
ip_finish_output2 from ip_send_skb+0x40/0xd8
ip_send_skb from udp_send_skb+0x124/0x340
udp_send_skb from udp_sendmsg+0x780/0x984
udp_sendmsg from __sys_sendto+0xd8/0x158
__sys_sendto from ret_fast_syscall+0x0/0x58

Let's fix the issue by checking for send_srp() and set_vbus() before
calling them. For USB peripheral only cases these both could be NULL.

Fixes: 657b306a7bdf ("usb: phy: add a new driver for omap usb2 phy")
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20240128120556.8848-1-tony@atomide.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-omap-usb2.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c
index dd2913ac0fa28..78e19b128962a 100644
--- a/drivers/phy/ti/phy-omap-usb2.c
+++ b/drivers/phy/ti/phy-omap-usb2.c
@@ -117,7 +117,7 @@ static int omap_usb_set_vbus(struct usb_otg *otg, bool enabled)
 {
 	struct omap_usb *phy = phy_to_omapusb(otg->usb_phy);
 
-	if (!phy->comparator)
+	if (!phy->comparator || !phy->comparator->set_vbus)
 		return -ENODEV;
 
 	return phy->comparator->set_vbus(phy->comparator, enabled);
@@ -127,7 +127,7 @@ static int omap_usb_start_srp(struct usb_otg *otg)
 {
 	struct omap_usb *phy = phy_to_omapusb(otg->usb_phy);
 
-	if (!phy->comparator)
+	if (!phy->comparator || !phy->comparator->start_srp)
 		return -ENODEV;
 
 	return phy->comparator->start_srp(phy->comparator);
-- 
GitLab


From bd504bcfec41a503b32054da5472904b404341a4 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 9 Jan 2024 15:57:56 +0100
Subject: [PATCH 3647/4076] dm: limit the number of targets and parameter size
 area

The kvmalloc function fails with a warning if the size is larger than
INT_MAX. The warning was triggered by a syscall testing robot.

In order to avoid the warning, this commit limits the number of targets to
1048576 and the size of the parameter area to 1073741824.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
 drivers/md/dm-core.h  | 2 ++
 drivers/md/dm-ioctl.c | 3 ++-
 drivers/md/dm-table.c | 9 +++++++--
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 095b9b49aa825..e6757a30dccad 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -22,6 +22,8 @@
 #include "dm-ima.h"
 
 #define DM_RESERVED_MAX_IOS		1024
+#define DM_MAX_TARGETS			1048576
+#define DM_MAX_TARGET_PARAMS		1024
 
 struct dm_io;
 
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index e65058e0ed06a..3b1ad7127cb84 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1941,7 +1941,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 			   minimum_data_size - sizeof(param_kernel->version)))
 		return -EFAULT;
 
-	if (param_kernel->data_size < minimum_data_size) {
+	if (unlikely(param_kernel->data_size < minimum_data_size) ||
+	    unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) {
 		DMERR("Invalid data size in the ioctl structure: %u",
 		      param_kernel->data_size);
 		return -EINVAL;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 260b5b8f2b0d7..41f1d731ae5ac 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -129,7 +129,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 int dm_table_create(struct dm_table **result, blk_mode_t mode,
 		    unsigned int num_targets, struct mapped_device *md)
 {
-	struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
+	struct dm_table *t;
+
+	if (num_targets > DM_MAX_TARGETS)
+		return -EOVERFLOW;
+
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
 
 	if (!t)
 		return -ENOMEM;
@@ -144,7 +149,7 @@ int dm_table_create(struct dm_table **result, blk_mode_t mode,
 
 	if (!num_targets) {
 		kfree(t);
-		return -ENOMEM;
+		return -EOVERFLOW;
 	}
 
 	if (alloc_targets(t, num_targets)) {
-- 
GitLab


From 9cf11ce06ea52911245578032761e40a6409cf35 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 9 Jan 2024 15:59:15 +0100
Subject: [PATCH 3648/4076] dm stats: limit the number of entries

The kvmalloc function fails with a warning if the size is larger than
INT_MAX. Linus said that there should be limits that prevent this warning
from being hit. This commit adds the limits to the dm-stats subsystem
in DM core.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
 drivers/md/dm-stats.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index bdc14ec998141..1e5d988f44da6 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -66,6 +66,9 @@ struct dm_stats_last_position {
 	unsigned int last_rw;
 };
 
+#define DM_STAT_MAX_ENTRIES		8388608
+#define DM_STAT_MAX_HISTOGRAM_ENTRIES	134217728
+
 /*
  * A typo on the command line could possibly make the kernel run out of memory
  * and crash. To prevent the crash we account all used memory. We fail if we
@@ -285,6 +288,9 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 	if (n_entries != (size_t)n_entries || !(size_t)(n_entries + 1))
 		return -EOVERFLOW;
 
+	if (n_entries > DM_STAT_MAX_ENTRIES)
+		return -EOVERFLOW;
+
 	shared_alloc_size = struct_size(s, stat_shared, n_entries);
 	if ((shared_alloc_size - sizeof(struct dm_stat)) / sizeof(struct dm_stat_shared) != n_entries)
 		return -EOVERFLOW;
@@ -297,6 +303,9 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 	if (histogram_alloc_size / (n_histogram_entries + 1) != (size_t)n_entries * sizeof(unsigned long long))
 		return -EOVERFLOW;
 
+	if ((n_histogram_entries + 1) * (size_t)n_entries > DM_STAT_MAX_HISTOGRAM_ENTRIES)
+		return -EOVERFLOW;
+
 	if (!check_shared_memory(shared_alloc_size + histogram_alloc_size +
 				 num_possible_cpus() * (percpu_alloc_size + histogram_alloc_size)))
 		return -ENOMEM;
-- 
GitLab


From 40ef8756fbdd9faec4da5d70352b28f1196132ed Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 9 Jan 2024 16:00:57 +0100
Subject: [PATCH 3649/4076] dm writecache: allow allocations larger than 2GiB

The function kvmalloc_node limits the allocation size to INT_MAX. This
limit will be overflowed if dm-writecache attempts to map a device with
1TiB or larger length. This commit changes kvmalloc_array to vmalloc_array
to avoid the limit.

The commit also changes vmalloc(array_size()) to vmalloc_array().

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
 drivers/md/dm-writecache.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 074cb785eafc1..b463c28c39ad3 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -299,7 +299,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		long i;
 
 		wc->memory_map = NULL;
-		pages = kvmalloc_array(p, sizeof(struct page *), GFP_KERNEL);
+		pages = vmalloc_array(p, sizeof(struct page *));
 		if (!pages) {
 			r = -ENOMEM;
 			goto err2;
@@ -330,7 +330,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 			r = -ENOMEM;
 			goto err3;
 		}
-		kvfree(pages);
+		vfree(pages);
 		wc->memory_vmapped = true;
 	}
 
@@ -341,7 +341,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 
 	return 0;
 err3:
-	kvfree(pages);
+	vfree(pages);
 err2:
 	dax_read_unlock(id);
 err1:
@@ -962,7 +962,7 @@ static int writecache_alloc_entries(struct dm_writecache *wc)
 
 	if (wc->entries)
 		return 0;
-	wc->entries = vmalloc(array_size(sizeof(struct wc_entry), wc->n_blocks));
+	wc->entries = vmalloc_array(wc->n_blocks, sizeof(struct wc_entry));
 	if (!wc->entries)
 		return -ENOMEM;
 	for (b = 0; b < wc->n_blocks; b++) {
-- 
GitLab


From 53ed2ac8fc1de6658aadae5714627ac99b9dddb0 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 30 Jan 2024 11:34:49 -0800
Subject: [PATCH 3650/4076] soc: apple: mailbox: error pointers are negative
 integers

In an entirely unrelated discussion where I pointed out a stupid thinko
of mine, Rasmus piped up and noted that that obvious mistake already
existed elsewhere in the kernel tree.

An "error pointer" is the negative error value encoded as a pointer,
making the whole "return error or valid pointer" use-case simple and
straightforward.  We use it all over the kernel.

But the key here is that errors are _negative_ error numbers, not the
horrid UNIX user-level model of "-1 and the value of 'errno'".

The Apple mailbox driver used the positive error values, and thus just
returned invalid normal pointers instead of actual errors.

Of course, the reason nobody ever noticed is that the errors presumably
never actually happen, so this is fixing a conceptual bug rather than an
actual one.

Reported-by: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Link: https://lore.kernel.org/all/5c30afe0-f9fb-45d5-9333-dd914a1ea93a@prevas.dk/
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/soc/apple/mailbox.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/soc/apple/mailbox.c b/drivers/soc/apple/mailbox.c
index 780199bf351ef..49a0955e82d6c 100644
--- a/drivers/soc/apple/mailbox.c
+++ b/drivers/soc/apple/mailbox.c
@@ -296,14 +296,14 @@ struct apple_mbox *apple_mbox_get(struct device *dev, int index)
 	of_node_put(args.np);
 
 	if (!pdev)
-		return ERR_PTR(EPROBE_DEFER);
+		return ERR_PTR(-EPROBE_DEFER);
 
 	mbox = platform_get_drvdata(pdev);
 	if (!mbox)
-		return ERR_PTR(EPROBE_DEFER);
+		return ERR_PTR(-EPROBE_DEFER);
 
 	if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_CONSUMER))
-		return ERR_PTR(ENODEV);
+		return ERR_PTR(-ENODEV);
 
 	return mbox;
 }
-- 
GitLab


From 2f77465b05b1270c832b5e2ee27037672ad2a10a Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 30 Jan 2024 19:01:35 +0100
Subject: [PATCH 3651/4076] x86/efistub: Avoid placing the kernel below
 LOAD_PHYSICAL_ADDR

The EFI stub's kernel placement logic randomizes the physical placement
of the kernel by taking all available memory into account, and picking a
region at random, based on a random seed.

When KASLR is disabled, this seed is set to 0x0, and this results in the
lowest available region of memory to be selected for loading the kernel,
even if this is below LOAD_PHYSICAL_ADDR. Some of this memory is
typically reserved for the GFP_DMA region, to accommodate masters that
can only access the first 16 MiB of system memory.

Even if such devices are rare these days, we may still end up with a
warning in the kernel log, as reported by Tom:

 swapper/0: page allocation failure: order:10, mode:0xcc1(GFP_KERNEL|GFP_DMA), nodemask=(null),cpuset=/,mems_allowed=0

Fix this by tweaking the random allocation logic to accept a low bound
on the placement, and set it to LOAD_PHYSICAL_ADDR.

Fixes: a1b87d54f4e4 ("x86/efistub: Avoid legacy decompressor when doing EFI boot")
Reported-by: Tom Englund <tomenglund26@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218404
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/efistub.h     |  3 ++-
 drivers/firmware/efi/libstub/kaslr.c       |  2 +-
 drivers/firmware/efi/libstub/randomalloc.c | 12 +++++++-----
 drivers/firmware/efi/libstub/x86-stub.c    |  1 +
 drivers/firmware/efi/libstub/zboot.c       |  2 +-
 5 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 212687c30d79c..c04b82ea40f21 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -956,7 +956,8 @@ efi_status_t efi_get_random_bytes(unsigned long size, u8 *out);
 
 efi_status_t efi_random_alloc(unsigned long size, unsigned long align,
 			      unsigned long *addr, unsigned long random_seed,
-			      int memory_type, unsigned long alloc_limit);
+			      int memory_type, unsigned long alloc_min,
+			      unsigned long alloc_max);
 
 efi_status_t efi_random_get_seed(void);
 
diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c
index 62d63f7a2645b..1a9808012abd3 100644
--- a/drivers/firmware/efi/libstub/kaslr.c
+++ b/drivers/firmware/efi/libstub/kaslr.c
@@ -119,7 +119,7 @@ efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr,
 		 */
 		status = efi_random_alloc(*reserve_size, min_kimg_align,
 					  reserve_addr, phys_seed,
-					  EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
+					  EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT);
 		if (status != EFI_SUCCESS)
 			efi_warn("efi_random_alloc() failed: 0x%lx\n", status);
 	} else {
diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index 674a064b8f7ad..4e96a855fdf47 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -17,7 +17,7 @@
 static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 					 unsigned long size,
 					 unsigned long align_shift,
-					 u64 alloc_limit)
+					 u64 alloc_min, u64 alloc_max)
 {
 	unsigned long align = 1UL << align_shift;
 	u64 first_slot, last_slot, region_end;
@@ -30,11 +30,11 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 		return 0;
 
 	region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1,
-			 alloc_limit);
+			 alloc_max);
 	if (region_end < size)
 		return 0;
 
-	first_slot = round_up(md->phys_addr, align);
+	first_slot = round_up(max(md->phys_addr, alloc_min), align);
 	last_slot = round_down(region_end - size + 1, align);
 
 	if (first_slot > last_slot)
@@ -56,7 +56,8 @@ efi_status_t efi_random_alloc(unsigned long size,
 			      unsigned long *addr,
 			      unsigned long random_seed,
 			      int memory_type,
-			      unsigned long alloc_limit)
+			      unsigned long alloc_min,
+			      unsigned long alloc_max)
 {
 	unsigned long total_slots = 0, target_slot;
 	unsigned long total_mirrored_slots = 0;
@@ -78,7 +79,8 @@ efi_status_t efi_random_alloc(unsigned long size,
 		efi_memory_desc_t *md = (void *)map->map + map_offset;
 		unsigned long slots;
 
-		slots = get_entry_num_slots(md, size, ilog2(align), alloc_limit);
+		slots = get_entry_num_slots(md, size, ilog2(align), alloc_min,
+					    alloc_max);
 		MD_NUM_SLOTS(md) = slots;
 		total_slots += slots;
 		if (md->attribute & EFI_MEMORY_MORE_RELIABLE)
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index cb0be88c81317..99429bc4b0c7e 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -799,6 +799,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
 
 	status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
 				  seed[0], EFI_LOADER_CODE,
+				  LOAD_PHYSICAL_ADDR,
 				  EFI_X86_KERNEL_ALLOC_LIMIT);
 	if (status != EFI_SUCCESS)
 		return status;
diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c
index bdb17eac0cb40..1ceace9567586 100644
--- a/drivers/firmware/efi/libstub/zboot.c
+++ b/drivers/firmware/efi/libstub/zboot.c
@@ -119,7 +119,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab)
 		}
 
 		status = efi_random_alloc(alloc_size, min_kimg_align, &image_base,
-					  seed, EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
+					  seed, EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT);
 		if (status != EFI_SUCCESS) {
 			efi_err("Failed to allocate memory\n");
 			goto free_cmdline;
-- 
GitLab


From aa0e784dea7c1a026aabff9db1cb5d2bd92b3e92 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Fri, 19 Jan 2024 18:06:35 +0800
Subject: [PATCH 3652/4076] efi/libstub: Add one kernel-doc comment

Add the description of @memory_type to silence the warning:
drivers/firmware/efi/libstub/alignedmem.c:27: warning: Function parameter or struct member 'memory_type' not described in 'efi_allocate_pages_aligned'

Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
[ardb: tweak comment]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/alignedmem.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c
index 6b83c492c3b82..31928bd87e0ff 100644
--- a/drivers/firmware/efi/libstub/alignedmem.c
+++ b/drivers/firmware/efi/libstub/alignedmem.c
@@ -14,6 +14,7 @@
  * @max:	the address that the last allocated memory page shall not
  *		exceed
  * @align:	minimum alignment of the base of the allocation
+ * @memory_type: the type of memory to allocate
  *
  * Allocate pages as EFI_LOADER_DATA. The allocated pages are aligned according
  * to @align, which should be >= EFI_ALLOC_ALIGN. The last allocated page will
-- 
GitLab


From 5a287d3d2b9de2b3e747132c615599907ba5c3c1 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Fri, 26 Jan 2024 19:45:31 +0100
Subject: [PATCH 3653/4076] lsm: fix default return value of the
 socket_getpeersec_*() hooks

For these hooks the true "neutral" value is -EOPNOTSUPP, which is
currently what is returned when no LSM provides this hook and what LSMs
return when there is no security context set on the socket. Correct the
value in <linux/lsm_hooks.h> and adjust the dispatch functions in
security/security.c to avoid issues when the BPF LSM is enabled.

Cc: stable@vger.kernel.org
Fixes: 98e828a0650f ("security: Refactor declaration of LSM hooks")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
[PM: subject line tweak]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/lsm_hook_defs.h |  4 ++--
 security/security.c           | 31 +++++++++++++++++++++++++++----
 2 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 185924c563787..76458b6d53da7 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -315,9 +315,9 @@ LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname)
 LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname)
 LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how)
 LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb)
-LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock,
+LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock,
 	 sockptr_t optval, sockptr_t optlen, unsigned int len)
-LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock,
+LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock,
 	 struct sk_buff *skb, u32 *secid)
 LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority)
 LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk)
diff --git a/security/security.c b/security/security.c
index 6196ccaba433a..3aaad75c9ce85 100644
--- a/security/security.c
+++ b/security/security.c
@@ -4624,8 +4624,20 @@ EXPORT_SYMBOL(security_sock_rcv_skb);
 int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval,
 				      sockptr_t optlen, unsigned int len)
 {
-	return call_int_hook(socket_getpeersec_stream, -ENOPROTOOPT, sock,
-			     optval, optlen, len);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_stream,
+			     list) {
+		rc = hp->hook.socket_getpeersec_stream(sock, optval, optlen,
+						       len);
+		if (rc != LSM_RET_DEFAULT(socket_getpeersec_stream))
+			return rc;
+	}
+	return LSM_RET_DEFAULT(socket_getpeersec_stream);
 }
 
 /**
@@ -4645,8 +4657,19 @@ int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval,
 int security_socket_getpeersec_dgram(struct socket *sock,
 				     struct sk_buff *skb, u32 *secid)
 {
-	return call_int_hook(socket_getpeersec_dgram, -ENOPROTOOPT, sock,
-			     skb, secid);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_dgram,
+			     list) {
+		rc = hp->hook.socket_getpeersec_dgram(sock, skb, secid);
+		if (rc != LSM_RET_DEFAULT(socket_getpeersec_dgram))
+			return rc;
+	}
+	return LSM_RET_DEFAULT(socket_getpeersec_dgram);
 }
 EXPORT_SYMBOL(security_socket_getpeersec_dgram);
 
-- 
GitLab


From 80441f76ee67002437db61f3b317ed80cce085d2 Mon Sep 17 00:00:00 2001
From: Brenton Simpson <appsforartists@google.com>
Date: Tue, 30 Jan 2024 13:34:16 -0800
Subject: [PATCH 3654/4076] Input: xpad - add Lenovo Legion Go controllers

The Lenovo Legion Go is a handheld gaming system, similar to a Steam Deck.
It has a gamepad (including rear paddles), 3 gyroscopes, a trackpad,
volume buttons, a power button, and 2 LED ring lights.

The Legion Go firmware presents these controls as a USB hub with various
devices attached.  In its default state, the gamepad is presented as an
Xbox controller connected to this hub.  (By holding a combination of
buttons, it can be changed to use the older DirectInput API.)

This patch teaches the existing Xbox controller module `xpad` to bind to
the controller in the Legion Go, which enables support for the:

- directional pad,
- analog sticks (including clicks),
- X, Y, A, B,
- start and select (or menu and capture),
- shoulder buttons, and
- rumble.

The trackpad, touchscreen, volume controls, and power button are already
supported via existing kernel modules.  Two of the face buttons, the
gyroscopes, rear paddles, and LEDs are not.

After this patch lands, the Legion Go will be mostly functional in Linux,
out-of-the-box.  The various components of the USB hub can be synthesized
into a single logical controller (including the additional buttons) in
userspace with [Handheld Daemon](https://github.com/hhd-dev/hhd), which
makes the Go fully functional.

Signed-off-by: Brenton Simpson <appsforartists@google.com>
Link: https://lore.kernel.org/r/20240118183546.418064-1-appsforartists@google.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index b1244d7df6cc9..7c4b2a5cc1b54 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -294,6 +294,7 @@ static const struct xpad_device {
 	{ 0x1689, 0xfd00, "Razer Onza Tournament Edition", 0, XTYPE_XBOX360 },
 	{ 0x1689, 0xfd01, "Razer Onza Classic Edition", 0, XTYPE_XBOX360 },
 	{ 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 },
+	{ 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 },
 	{ 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
@@ -491,6 +492,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x15e4),		/* Numark Xbox 360 controllers */
 	XPAD_XBOX360_VENDOR(0x162e),		/* Joytech Xbox 360 controllers */
 	XPAD_XBOX360_VENDOR(0x1689),		/* Razer Onza */
+	XPAD_XBOX360_VENDOR(0x17ef),		/* Lenovo */
 	XPAD_XBOX360_VENDOR(0x1949),		/* Amazon controllers */
 	XPAD_XBOX360_VENDOR(0x1bad),		/* Harmonix Rock Band guitar and drums */
 	XPAD_XBOX360_VENDOR(0x20d6),		/* PowerA controllers */
-- 
GitLab


From a4e61de63e34860c36a71d1a364edba16fb6203b Mon Sep 17 00:00:00 2001
From: Ekansh Gupta <quic_ekangupt@quicinc.com>
Date: Mon, 8 Jan 2024 17:18:33 +0530
Subject: [PATCH 3655/4076] misc: fastrpc: Mark all sessions as invalid in
 cb_remove

In remoteproc shutdown sequence, rpmsg_remove will get called which
would depopulate all the child nodes that have been created during
rpmsg_probe. This would result in cb_remove call for all the context
banks for the remoteproc. In cb_remove function, session 0 is
getting skipped which is not correct as session 0 will never become
available again. Add changes to mark session 0 also as invalid.

Fixes: f6f9279f2bf0 ("misc: fastrpc: Add Qualcomm fastrpc basic driver model")
Cc: stable <stable@kernel.org>
Signed-off-by: Ekansh Gupta <quic_ekangupt@quicinc.com>
Link: https://lore.kernel.org/r/20240108114833.20480-1-quic_ekangupt@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/fastrpc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 1c6c62a7f7f55..03319a1fa97fd 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -2191,7 +2191,7 @@ static int fastrpc_cb_remove(struct platform_device *pdev)
 	int i;
 
 	spin_lock_irqsave(&cctx->lock, flags);
-	for (i = 1; i < FASTRPC_MAX_SESSIONS; i++) {
+	for (i = 0; i < FASTRPC_MAX_SESSIONS; i++) {
 		if (cctx->session[i].sid == sess->sid) {
 			cctx->session[i].valid = false;
 			cctx->sesscount--;
-- 
GitLab


From ac9762a74c7ca7cbfcb4c65f5871373653a046ac Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 26 Jan 2024 15:24:10 +0000
Subject: [PATCH 3656/4076] misc: open-dice: Fix spurious lockdep warning

When probing the open-dice driver with PROVE_LOCKING=y, lockdep
complains that the mutex in 'drvdata->lock' has a non-static key:

 | INFO: trying to register non-static key.
 | The code is fine but needs lockdep annotation, or maybe
 | you didn't initialize this object before use?
 | turning off the locking correctness validator.

Fix the problem by initialising the mutex memory with mutex_init()
instead of __MUTEX_INITIALIZER().

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Brazdil <dbrazdil@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20240126152410.10148-1-will@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/open-dice.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c
index 8aea2d070a40c..d279a4f195e2a 100644
--- a/drivers/misc/open-dice.c
+++ b/drivers/misc/open-dice.c
@@ -140,7 +140,6 @@ static int __init open_dice_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	*drvdata = (struct open_dice_drvdata){
-		.lock = __MUTEX_INITIALIZER(drvdata->lock),
 		.rmem = rmem,
 		.misc = (struct miscdevice){
 			.parent	= dev,
@@ -150,6 +149,7 @@ static int __init open_dice_probe(struct platform_device *pdev)
 			.mode	= 0600,
 		},
 	};
+	mutex_init(&drvdata->lock);
 
 	/* Index overflow check not needed, misc_register() will fail. */
 	snprintf(drvdata->name, sizeof(drvdata->name), DRIVER_NAME"%u", dev_idx++);
-- 
GitLab


From b40f873a7c80dbafbb6f4a7a569f2dcaf969d283 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 29 Jan 2024 14:37:03 +0200
Subject: [PATCH 3657/4076] selftests: net: Add missing matchall classifier

One of the test cases in the test_bridge_backup_port.sh selftest relies
on a matchall classifier to drop unrelated traffic so that the Tx drop
counter on the VXLAN device will only be incremented as a result of
traffic generated by the test.

However, the configuration option for the matchall classifier is
missing from the configuration file which might explain the failures we
see in the netdev CI [1].

Fix by adding CONFIG_NET_CLS_MATCHALL to the configuration file.

[1]
 # Backup nexthop ID - invalid IDs
 # -------------------------------
 [...]
 # TEST: Forwarding out of vx0                                         [ OK ]
 # TEST: No forwarding using backup nexthop ID                         [ OK ]
 # TEST: Tx drop increased                                             [FAIL]
 # TEST: IPv6 address family nexthop as backup nexthop                 [ OK ]
 # TEST: No forwarding out of swp1                                     [ OK ]
 # TEST: Forwarding out of vx0                                         [ OK ]
 # TEST: No forwarding using backup nexthop ID                         [ OK ]
 # TEST: Tx drop increased                                             [FAIL]
 [...]

Fixes: b408453053fb ("selftests: net: Add bridge backup port and backup nexthop ID test")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20240129123703.1857843-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index d4b38177ed04a..3d908b52f22f3 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -52,6 +52,7 @@ CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_MATCHALL=m
 CONFIG_NET_CLS_U32=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-- 
GitLab


From f5c3eb4b7251baba5cd72c9e93920e710ac8194a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Sat, 27 Jan 2024 18:50:32 +0100
Subject: [PATCH 3658/4076] bridge: mcast: fix disabled snooping after long
 uptime
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The original idea of the delay_time check was to not apply multicast
snooping too early when an MLD querier appears. And to instead wait at
least for MLD reports to arrive before switching from flooding to group
based, MLD snooped forwarding, to avoid temporary packet loss.

However in a batman-adv mesh network it was noticed that after 248 days of
uptime 32bit MIPS based devices would start to signal that they had
stopped applying multicast snooping due to missing queriers - even though
they were the elected querier and still sending MLD queries themselves.

While time_is_before_jiffies() generally is safe against jiffies
wrap-arounds, like the code comments in jiffies.h explain, it won't
be able to track a difference larger than ULONG_MAX/2. With a 32bit
large jiffies and one jiffies tick every 10ms (CONFIG_HZ=100) on these MIPS
devices running OpenWrt this would result in a difference larger than
ULONG_MAX/2 after 248 (= 2^32/100/60/60/24/2) days and
time_is_before_jiffies() would then start to return false instead of
true. Leading to multicast snooping not being applied to multicast
packets anymore.

Fix this issue by using a proper timer_list object which won't have this
ULONG_MAX/2 difference limitation.

Fixes: b00589af3b04 ("bridge: disable snooping if there is no querier")
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20240127175033.9640-1-linus.luessing@c0d3.blue
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_multicast.c | 20 +++++++++++++++-----
 net/bridge/br_private.h   |  4 ++--
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index d7d021af10298..2d7b732429588 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1762,6 +1762,10 @@ static void br_ip6_multicast_querier_expired(struct timer_list *t)
 }
 #endif
 
+static void br_multicast_query_delay_expired(struct timer_list *t)
+{
+}
+
 static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx,
 					    struct br_ip *ip,
 					    struct sk_buff *skb)
@@ -3198,7 +3202,7 @@ br_multicast_update_query_timer(struct net_bridge_mcast *brmctx,
 				unsigned long max_delay)
 {
 	if (!timer_pending(&query->timer))
-		query->delay_time = jiffies + max_delay;
+		mod_timer(&query->delay_timer, jiffies + max_delay);
 
 	mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval);
 }
@@ -4041,13 +4045,11 @@ void br_multicast_ctx_init(struct net_bridge *br,
 	brmctx->multicast_querier_interval = 255 * HZ;
 	brmctx->multicast_membership_interval = 260 * HZ;
 
-	brmctx->ip4_other_query.delay_time = 0;
 	brmctx->ip4_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock);
 	brmctx->multicast_igmp_version = 2;
 #if IS_ENABLED(CONFIG_IPV6)
 	brmctx->multicast_mld_version = 1;
-	brmctx->ip6_other_query.delay_time = 0;
 	brmctx->ip6_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock);
 #endif
@@ -4056,6 +4058,8 @@ void br_multicast_ctx_init(struct net_bridge *br,
 		    br_ip4_multicast_local_router_expired, 0);
 	timer_setup(&brmctx->ip4_other_query.timer,
 		    br_ip4_multicast_querier_expired, 0);
+	timer_setup(&brmctx->ip4_other_query.delay_timer,
+		    br_multicast_query_delay_expired, 0);
 	timer_setup(&brmctx->ip4_own_query.timer,
 		    br_ip4_multicast_query_expired, 0);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -4063,6 +4067,8 @@ void br_multicast_ctx_init(struct net_bridge *br,
 		    br_ip6_multicast_local_router_expired, 0);
 	timer_setup(&brmctx->ip6_other_query.timer,
 		    br_ip6_multicast_querier_expired, 0);
+	timer_setup(&brmctx->ip6_other_query.delay_timer,
+		    br_multicast_query_delay_expired, 0);
 	timer_setup(&brmctx->ip6_own_query.timer,
 		    br_ip6_multicast_query_expired, 0);
 #endif
@@ -4197,10 +4203,12 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx)
 {
 	del_timer_sync(&brmctx->ip4_mc_router_timer);
 	del_timer_sync(&brmctx->ip4_other_query.timer);
+	del_timer_sync(&brmctx->ip4_other_query.delay_timer);
 	del_timer_sync(&brmctx->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
 	del_timer_sync(&brmctx->ip6_mc_router_timer);
 	del_timer_sync(&brmctx->ip6_other_query.timer);
+	del_timer_sync(&brmctx->ip6_other_query.delay_timer);
 	del_timer_sync(&brmctx->ip6_own_query.timer);
 #endif
 }
@@ -4643,13 +4651,15 @@ int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val)
 	max_delay = brmctx->multicast_query_response_interval;
 
 	if (!timer_pending(&brmctx->ip4_other_query.timer))
-		brmctx->ip4_other_query.delay_time = jiffies + max_delay;
+		mod_timer(&brmctx->ip4_other_query.delay_timer,
+			  jiffies + max_delay);
 
 	br_multicast_start_querier(brmctx, &brmctx->ip4_own_query);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (!timer_pending(&brmctx->ip6_other_query.timer))
-		brmctx->ip6_other_query.delay_time = jiffies + max_delay;
+		mod_timer(&brmctx->ip6_other_query.delay_timer,
+			  jiffies + max_delay);
 
 	br_multicast_start_querier(brmctx, &brmctx->ip6_own_query);
 #endif
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index b0a92c344722b..86ea5e6689b5c 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -78,7 +78,7 @@ struct bridge_mcast_own_query {
 /* other querier */
 struct bridge_mcast_other_query {
 	struct timer_list		timer;
-	unsigned long			delay_time;
+	struct timer_list		delay_timer;
 };
 
 /* selected querier */
@@ -1159,7 +1159,7 @@ __br_multicast_querier_exists(struct net_bridge_mcast *brmctx,
 		own_querier_enabled = false;
 	}
 
-	return time_is_before_jiffies(querier->delay_time) &&
+	return !timer_pending(&querier->delay_timer) &&
 	       (own_querier_enabled || timer_pending(&querier->timer));
 }
 
-- 
GitLab


From 1a89e24f8bfd3e3562d69709c9d9cd185ded869b Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Mon, 29 Jan 2024 21:10:59 +0200
Subject: [PATCH 3659/4076] devlink: Fix referring to hw_addr attribute during
 state validation

When port function state change is requested, and when the driver
does not support it, it refers to the hw address attribute instead
of state attribute. Seems like a copy paste error.

Fix it by referring to the port function state attribute.

Fixes: c0bea69d1ca7 ("devlink: Validate port function request")
Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240129191059.129030-1-parav@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/port.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/devlink/port.c b/net/devlink/port.c
index 62e54e152ecf1..78592912f657c 100644
--- a/net/devlink/port.c
+++ b/net/devlink/port.c
@@ -674,7 +674,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port,
 		return -EOPNOTSUPP;
 	}
 	if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) {
-		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
+		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE],
 				    "Function does not support state setting");
 		return -EOPNOTSUPP;
 	}
-- 
GitLab


From f884a9f9e59206a2d41f265e7e403f080d10b493 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 10 Jan 2024 17:48:44 +0100
Subject: [PATCH 3660/4076] btrfs: send: return EOPNOTSUPP on unknown flags

When some ioctl flags are checked we return EOPNOTSUPP, like for
BTRFS_SCRUB_SUPPORTED_FLAGS, BTRFS_SUBVOL_CREATE_ARGS_MASK or fallocate
modes. The EINVAL is supposed to be for a supported but invalid
values or combination of options. Fix that when checking send flags so
it's consistent with the rest.

CC: stable@vger.kernel.org # 4.14+
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5rryOLzp3EKq8RTbjMHMHeaJubfpsVLF6H4qJnKCUR1w@mail.gmail.com/
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/send.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 2d7519a6ce72d..7902298c1f25b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -8111,7 +8111,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 	}
 
 	if (arg->flags & ~BTRFS_SEND_FLAG_MASK) {
-		ret = -EINVAL;
+		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
-- 
GitLab


From 0c309d66dacddf8ce939b891d9ead4a8e21ad6f0 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Wed, 10 Jan 2024 17:51:26 -0800
Subject: [PATCH 3661/4076] btrfs: forbid creating subvol qgroups

Creating a qgroup 0/subvolid leads to various races and it isn't
helpful, because you can't specify a subvol id when creating a subvol,
so you can't be sure it will be the right one. Any requirements on the
automatic subvol can be gratified by using a higher level qgroup and the
inheritance parameters of subvol creation.

Fixes: cecbb533b5fc ("btrfs: record simple quota deltas in delayed refs")
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5d42319b43f2d..fb2323b323bf9 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3806,6 +3806,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 		goto out;
 	}
 
+	if (sa->create && is_fstree(sa->qgroupid)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-- 
GitLab


From a8df35619948bd8363d330c20a90c9a7fbff28c0 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Wed, 10 Jan 2024 17:30:00 -0800
Subject: [PATCH 3662/4076] btrfs: forbid deleting live subvol qgroup

If a subvolume still exists, forbid deleting its qgroup 0/subvolid.
This behavior generally leads to incorrect behavior in squotas and
doesn't have a legitimate purpose.

Fixes: cecbb533b5fc ("btrfs: record simple quota deltas in delayed refs")
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 63b426cc77989..5470e1cdf10c5 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1736,6 +1736,15 @@ out:
 	return ret;
 }
 
+static bool qgroup_has_usage(struct btrfs_qgroup *qgroup)
+{
+	return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 ||
+		qgroup->excl > 0 || qgroup->excl_cmpr > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0);
+}
+
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -1755,6 +1764,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 		goto out;
 	}
 
+	if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	/* Check if there are no children of this qgroup */
 	if (!list_empty(&qgroup->members)) {
 		ret = -EBUSY;
-- 
GitLab


From e03ee2fe873eb68c1f9ba5112fee70303ebf9dfb Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Sat, 20 Jan 2024 19:41:28 +1030
Subject: [PATCH 3663/4076] btrfs: do not ASSERT() if the newly created
 subvolume already got read

[BUG]
There is a syzbot crash, triggered by the ASSERT() during subvolume
creation:

 assertion failed: !anon_dev, in fs/btrfs/disk-io.c:1319
 ------------[ cut here ]------------
 kernel BUG at fs/btrfs/disk-io.c:1319!
 invalid opcode: 0000 [#1] PREEMPT SMP KASAN
 RIP: 0010:btrfs_get_root_ref.part.0+0x9aa/0xa60
  <TASK>
  btrfs_get_new_fs_root+0xd3/0xf0
  create_subvol+0xd02/0x1650
  btrfs_mksubvol+0xe95/0x12b0
  __btrfs_ioctl_snap_create+0x2f9/0x4f0
  btrfs_ioctl_snap_create+0x16b/0x200
  btrfs_ioctl+0x35f0/0x5cf0
  __x64_sys_ioctl+0x19d/0x210
  do_syscall_64+0x3f/0xe0
  entry_SYSCALL_64_after_hwframe+0x63/0x6b
 ---[ end trace 0000000000000000 ]---

[CAUSE]
During create_subvol(), after inserting root item for the newly created
subvolume, we would trigger btrfs_get_new_fs_root() to get the
btrfs_root of that subvolume.

The idea here is, we have preallocated an anonymous device number for
the subvolume, thus we can assign it to the new subvolume.

But there is really nothing preventing things like backref walk to read
the new subvolume.
If that happens before we call btrfs_get_new_fs_root(), the subvolume
would be read out, with a new anonymous device number assigned already.

In that case, we would trigger ASSERT(), as we really expect no one to
read out that subvolume (which is not yet accessible from the fs).
But things like backref walk is still possible to trigger the read on
the subvolume.

Thus our assumption on the ASSERT() is not correct in the first place.

[FIX]
Fix it by removing the ASSERT(), and just free the @anon_dev, reset it
to 0, and continue.

If the subvolume tree is read out by something else, it should have
already get a new anon_dev assigned thus we only need to free the
preallocated one.

Reported-by: Chenyuan Yang <chenyuan0y@gmail.com>
Fixes: 2dfb1e43f57d ("btrfs: preallocate anon block device at first phase of snapshot creation")
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c6907d533fe83..e71ef97d0a7ca 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1336,8 +1336,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
 again:
 	root = btrfs_lookup_fs_root(fs_info, objectid);
 	if (root) {
-		/* Shouldn't get preallocated anon_dev for cached roots */
-		ASSERT(!anon_dev);
+		/*
+		 * Some other caller may have read out the newly inserted
+		 * subvolume already (for things like backref walk etc).  Not
+		 * that common but still possible.  In that case, we just need
+		 * to free the anon_dev.
+		 */
+		if (unlikely(anon_dev)) {
+			free_anon_bdev(anon_dev);
+			anon_dev = 0;
+		}
+
 		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
 			btrfs_put_root(root);
 			return ERR_PTR(-ENOENT);
-- 
GitLab


From 4451e8e8415e4ef48cdc763d66855f8c25fda94c Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 23 Jan 2024 12:08:18 -0600
Subject: [PATCH 3664/4076] pinctrl: amd: Add IRQF_ONESHOT to the interrupt
 request

On some systems the interrupt is shared between GPIO controller
and ACPI SCI. When the interrupt is shared with the ACPI SCI the
flags need to be identical.

This should fix the GPIO controller failing to work after commit
7a36b901a6eb ("ACPI: OSL: Use a threaded interrupt handler for SCI").
```
[    0.417335] genirq: Flags mismatch irq 9. 00000088 (pinctrl_amd) vs. 00002080 (acpi)
[    0.420073] amd_gpio: probe of AMDI0030:00 failed with error -16
```

Cc: Rafael J. Wysocki <rafael@kernel.org>
Reported-by: Christian Heusel <christian@heusel.eu>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218407
Fixes: 7a36b901a6eb ("ACPI: OSL: Use a threaded interrupt handler for SCI")
Link: https://lore.kernel.org/linux-acpi/CAJZ5v0iRqUXeuKmC_+dAJtDBLWQ3x15n4gRH48y7MEaLoXF+UA@mail.gmail.com/T/#mc5506014141b61e472b24e095889535a04458083
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Tested-by: Christian Heusel <christian@heusel.eu>
Link: https://lore.kernel.org/r/20240123180818.3994-1-mario.limonciello@amd.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-amd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 03ecb3d1aaf60..49f89b70dcecb 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -1159,7 +1159,7 @@ static int amd_gpio_probe(struct platform_device *pdev)
 	}
 
 	ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler,
-			       IRQF_SHARED, KBUILD_MODNAME, gpio_dev);
+			       IRQF_SHARED | IRQF_ONESHOT, KBUILD_MODNAME, gpio_dev);
 	if (ret)
 		goto out2;
 
-- 
GitLab


From b4a1f4eaf1d798066affc6ad040f76eb1a16e1c9 Mon Sep 17 00:00:00 2001
From: Puliang Lu <puliang.lu@fibocom.com>
Date: Wed, 31 Jan 2024 17:12:24 +0800
Subject: [PATCH 3665/4076] USB: serial: option: add Fibocom FM101-GL variant

Update the USB serial option driver support for the Fibocom
FM101-GL
LTE modules as there are actually several different variants.
- VID:PID 2cb7:01a3, FM101-GL are laptop M.2 cards (with
MBIM interfaces for /Linux/Chrome OS)

0x01a3:mbim,gnss

Here are the outputs of usb-devices:

T:  Bus=04 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  3 Spd=5000 MxCh= 0
D:  Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs=  1
P:  Vendor=2cb7 ProdID=01a3 Rev=05.04
S:  Manufacturer=Fibocom Wireless Inc.
S:  Product=Fibocom FM101-GL Module
S:  SerialNumber=5ccd5cd4
C:  #Ifs= 3 Cfg#= 1 Atr=a0 MxPwr=896mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=0f(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

Signed-off-by: Puliang Lu <puliang.lu@fibocom.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 72390dbf07692..2ae124c49d448 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -2269,6 +2269,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) },			/* Fibocom FM160 (MBIM mode) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) },			/* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff),			/* Fibocom FM101-GL (laptop MBIM) */
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
-- 
GitLab


From 51af8f255bdaca6d501afc0d085b808f67b44d91 Mon Sep 17 00:00:00 2001
From: Lennert Buytenhek <kernel@wantstofly.org>
Date: Tue, 30 Jan 2024 15:21:51 +0200
Subject: [PATCH 3666/4076] ahci: Extend ASM1061 43-bit DMA address quirk to
 other ASM106x parts

ASMedia have confirmed that all ASM106x parts currently listed in
ahci_pci_tbl[] suffer from the 43-bit DMA address limitation that we ran
into on the ASM1061, and therefore, we need to apply the quirk added by
commit 20730e9b2778 ("ahci: add 43-bit DMA address quirk for ASMedia
ASM1061 controllers") to the other supported ASM106x parts as well.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/linux-ide/ZbopwKZJAKQRA4Xv@x1-carbon/
Signed-off-by: Lennert Buytenhek <kernel@wantstofly.org>
[cassel: add link to ASMedia confirmation email]
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index d2460fa985b7e..da2e74fce2d99 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -606,13 +606,13 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
 	/* ASMedia */
-	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci },	/* ASM1060 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci_43bit_dma },	/* ASM1060 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci_43bit_dma },	/* ASM1060 */
 	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci_43bit_dma },	/* ASM1061 */
 	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci_43bit_dma },	/* ASM1061/1062 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci },   /* ASM1061R */
-	{ PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci },   /* ASM1062R */
-	{ PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci },   /* ASM1062+JMB575 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci_43bit_dma },	/* ASM1061R */
+	{ PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci_43bit_dma },	/* ASM1062R */
+	{ PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci_43bit_dma },	/* ASM1062+JMB575 */
 	{ PCI_VDEVICE(ASMEDIA, 0x1062), board_ahci },	/* ASM1062A */
 	{ PCI_VDEVICE(ASMEDIA, 0x1064), board_ahci },	/* ASM1064 */
 	{ PCI_VDEVICE(ASMEDIA, 0x1164), board_ahci },   /* ASM1164 */
-- 
GitLab


From 913b9d443a0180cf0de3548f1ab3149378998486 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 31 Jan 2024 13:37:25 +0100
Subject: [PATCH 3667/4076] parisc: BTLB: Fix crash when setting up BTLB at CPU
 bringup

When using hotplug and bringing up a 32-bit CPU, ask the firmware about the
BTLB information to set up the static (block) TLB entries.

For that write access to the static btlb_info struct is needed, but
since it is marked __ro_after_init the kernel segfaults with missing
write permissions.

Fix the crash by dropping the __ro_after_init annotation.

Fixes: e5ef93d02d6c ("parisc: BTLB: Initialize BTLB tables at CPU startup")
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.6+
---
 arch/parisc/kernel/cache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 5552602fcaef1..422f3e1e6d9ca 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -58,7 +58,7 @@ int pa_serialize_tlb_flushes __ro_after_init;
 
 struct pdc_cache_info cache_info __ro_after_init;
 #ifndef CONFIG_PA20
-struct pdc_btlb_info btlb_info __ro_after_init;
+struct pdc_btlb_info btlb_info;
 #endif
 
 DEFINE_STATIC_KEY_TRUE(parisc_has_cache);
-- 
GitLab


From 2468e8922d2f6da81a6192b73023eff67e3fefdd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Relvas?= <josemonsantorelvas@gmail.com>
Date: Wed, 31 Jan 2024 11:34:09 +0000
Subject: [PATCH 3668/4076] ALSA: hda/realtek: Apply headset jack quirk for
 non-bass alc287 thinkpads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There currently exists two thinkpad headset jack fixups:
ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK
ALC285_FIXUP_THINKPAD_HEADSET_JACK

The latter is applied to alc285 and alc287 thinkpads which contain
bass speakers.
However, the former was only being applied to alc285 thinkpads,
leaving non-bass alc287 thinkpads with no headset button controls.
This patch fixes that by adding ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK
to the alc287 chains, allowing the detection of headset buttons.

Signed-off-by: José Relvas <josemonsantorelvas@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240131113407.34698-3-josemonsantorelvas@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index bfa244028b994..f98520c0bed9f 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9579,7 +9579,7 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cs35l41_fixup_i2c_two,
 		.chained = true,
-		.chain_id = ALC269_FIXUP_THINKPAD_ACPI,
+		.chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK,
 	},
 	[ALC287_FIXUP_TAS2781_I2C] = {
 		.type = HDA_FIXUP_FUNC,
@@ -9606,6 +9606,8 @@ static const struct hda_fixup alc269_fixups[] = {
 	[ALC287_FIXUP_THINKPAD_I2S_SPK] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc287_fixup_bind_dacs,
+		.chained = true,
+		.chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK,
 	},
 	[ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD] = {
 		.type = HDA_FIXUP_FUNC,
-- 
GitLab


From 89876175c8c83c35cf0cc8e21b7460dfed7b118a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 20 Jan 2024 17:32:55 +0900
Subject: [PATCH 3669/4076] kbuild: fix W= flags in the help message

W=c and W=e are supported.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 9869f57c3fb3e..02e3500c2c178 100644
--- a/Makefile
+++ b/Makefile
@@ -1662,7 +1662,7 @@ help:
 	@echo  '                       (sparse by default)'
 	@echo  '  make C=2   [targets] Force check of all c source with $$CHECK'
 	@echo  '  make RECORDMCOUNT_WARN=1 [targets] Warn about ignored mcount sections'
-	@echo  '  make W=n   [targets] Enable extra build checks, n=1,2,3 where'
+	@echo  '  make W=n   [targets] Enable extra build checks, n=1,2,3,c,e where'
 	@echo  '		1: warnings which may be relevant and do not occur too often'
 	@echo  '		2: warnings which occur quite often but may still be relevant'
 	@echo  '		3: more obscure warnings, can most likely be ignored'
-- 
GitLab


From cda5f94e88b45c9209599bac15fc44add5a59f60 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 27 Jan 2024 22:28:11 +0900
Subject: [PATCH 3670/4076] modpost: avoid using the alias attribute

Aiden Leong reported modpost fails to build on macOS since commit
16a473f60edc ("modpost: inform compilers that fatal() never returns"):

  scripts/mod/modpost.c:93:21: error: aliases are not supported on darwin

Nathan's research indicates that Darwin seems to support weak aliases
at least [1]. Although the situation might be improved in future Clang
versions, we can achieve a similar outcome without relying on it.

This commit makes fatal() a macro of error() + exit(1) in modpost.h, as
compilers recognize that exit() never returns.

[1]: https://github.com/llvm/llvm-project/issues/71001

Fixes: 16a473f60edc ("modpost: inform compilers that fatal() never returns")
Reported-by: Aiden Leong <aiden.leong@aibsd.com>
Closes: https://lore.kernel.org/all/d9ac2960-6644-4a87-b5e4-4bfb6e0364a8@aibsd.com/
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/mod/modpost.c | 12 +-----------
 scripts/mod/modpost.h |  6 +-----
 2 files changed, 2 insertions(+), 16 deletions(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index acf72112acd8b..267b9a0a3abcd 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -70,9 +70,7 @@ void modpost_log(enum loglevel loglevel, const char *fmt, ...)
 		break;
 	case LOG_ERROR:
 		fprintf(stderr, "ERROR: ");
-		break;
-	case LOG_FATAL:
-		fprintf(stderr, "FATAL: ");
+		error_occurred = true;
 		break;
 	default: /* invalid loglevel, ignore */
 		break;
@@ -83,16 +81,8 @@ void modpost_log(enum loglevel loglevel, const char *fmt, ...)
 	va_start(arglist, fmt);
 	vfprintf(stderr, fmt, arglist);
 	va_end(arglist);
-
-	if (loglevel == LOG_FATAL)
-		exit(1);
-	if (loglevel == LOG_ERROR)
-		error_occurred = true;
 }
 
-void __attribute__((alias("modpost_log")))
-modpost_log_noret(enum loglevel loglevel, const char *fmt, ...);
-
 static inline bool strends(const char *str, const char *postfix)
 {
 	if (strlen(str) < strlen(postfix))
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 835cababf1b09..ee43c79506368 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -194,15 +194,11 @@ void *sym_get_data(const struct elf_info *info, const Elf_Sym *sym);
 enum loglevel {
 	LOG_WARN,
 	LOG_ERROR,
-	LOG_FATAL
 };
 
 void __attribute__((format(printf, 2, 3)))
 modpost_log(enum loglevel loglevel, const char *fmt, ...);
 
-void __attribute__((format(printf, 2, 3), noreturn))
-modpost_log_noret(enum loglevel loglevel, const char *fmt, ...);
-
 /*
  * warn - show the given message, then let modpost continue running, still
  *        allowing modpost to exit successfully. This should be used when
@@ -218,4 +214,4 @@ modpost_log_noret(enum loglevel loglevel, const char *fmt, ...);
  */
 #define warn(fmt, args...)	modpost_log(LOG_WARN, fmt, ##args)
 #define error(fmt, args...)	modpost_log(LOG_ERROR, fmt, ##args)
-#define fatal(fmt, args...)	modpost_log_noret(LOG_FATAL, fmt, ##args)
+#define fatal(fmt, args...)	do { error(fmt, ##args); exit(1); } while (1)
-- 
GitLab


From 82175d1f9430d5a026e2231782d13da0bf57155c Mon Sep 17 00:00:00 2001
From: Dmitry Goncharov <dgoncharov@users.sf.net>
Date: Sun, 28 Jan 2024 10:10:39 -0500
Subject: [PATCH 3671/4076] kbuild: Replace tabs with spaces when followed by
 conditionals

This is needed for the future (post make-4.4.1) versions of gnu make.

Starting from https://git.savannah.gnu.org/cgit/make.git/commit/?id=07fcee35f058a876447c8a021f9eb1943f902534
gnu make won't allow conditionals to follow recipe prefix.

For example there is a tab followed by ifeq on line 324 in the root Makefile.
With the new make this conditional causes the following

$ make cpu.o
/home/dgoncharov/src/linux-kbuild/Makefile:2063: *** missing 'endif'.  Stop.
make: *** [Makefile:240: __sub-make] Error 2

This patch replaces tabs followed by conditionals with 8 spaces.

See https://savannah.gnu.org/bugs/?64185 and
https://savannah.gnu.org/bugs/?64259 for details.

Signed-off-by: Dmitry Goncharov <dgoncharov@users.sf.net>
Reported-by: Martin Dorey <martin.dorey@hitachivantara.com>
Reviewed-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 Makefile             | 12 ++++++------
 arch/m68k/Makefile   |  4 ++--
 arch/parisc/Makefile |  4 ++--
 arch/x86/Makefile    | 10 +++++-----
 4 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/Makefile b/Makefile
index 02e3500c2c178..087c9c64f611a 100644
--- a/Makefile
+++ b/Makefile
@@ -294,15 +294,15 @@ may-sync-config	:= 1
 single-build	:=
 
 ifneq ($(filter $(no-dot-config-targets), $(MAKECMDGOALS)),)
-	ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
+        ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
 		need-config :=
-	endif
+        endif
 endif
 
 ifneq ($(filter $(no-sync-config-targets), $(MAKECMDGOALS)),)
-	ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
+        ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
 		may-sync-config :=
-	endif
+        endif
 endif
 
 need-compiler := $(may-sync-config)
@@ -323,9 +323,9 @@ endif
 # We cannot build single targets and the others at the same time
 ifneq ($(filter $(single-targets), $(MAKECMDGOALS)),)
 	single-build := 1
-	ifneq ($(filter-out $(single-targets), $(MAKECMDGOALS)),)
+        ifneq ($(filter-out $(single-targets), $(MAKECMDGOALS)),)
 		mixed-build := 1
-	endif
+        endif
 endif
 
 # For "make -j clean all", "make -j mrproper defconfig all", etc.
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 43e39040d3ac6..76ef1a67c3611 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -15,10 +15,10 @@
 KBUILD_DEFCONFIG := multi_defconfig
 
 ifdef cross_compiling
-	ifeq ($(CROSS_COMPILE),)
+        ifeq ($(CROSS_COMPILE),)
 		CROSS_COMPILE := $(call cc-cross-prefix, \
 			m68k-linux-gnu- m68k-linux- m68k-unknown-linux-gnu-)
-	endif
+        endif
 endif
 
 #
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 920db57b6b4cc..7486b3b305949 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -50,12 +50,12 @@ export CROSS32CC
 
 # Set default cross compiler for kernel build
 ifdef cross_compiling
-	ifeq ($(CROSS_COMPILE),)
+        ifeq ($(CROSS_COMPILE),)
 		CC_SUFFIXES = linux linux-gnu unknown-linux-gnu suse-linux
 		CROSS_COMPILE := $(call cc-cross-prefix, \
 			$(foreach a,$(CC_ARCHES), \
 			$(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
-	endif
+        endif
 endif
 
 ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1a068de12a564..2264db14a25d3 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -112,13 +112,13 @@ ifeq ($(CONFIG_X86_32),y)
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
 
-	ifeq ($(CONFIG_STACKPROTECTOR),y)
-		ifeq ($(CONFIG_SMP),y)
+        ifeq ($(CONFIG_STACKPROTECTOR),y)
+                ifeq ($(CONFIG_SMP),y)
 			KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
-		else
+                else
 			KBUILD_CFLAGS += -mstack-protector-guard=global
-		endif
-	endif
+                endif
+        endif
 else
         BITS := 64
         UTS_MACHINE := x86_64
-- 
GitLab


From 358de8b4f201bc05712484b15f0109b1ae3516a8 Mon Sep 17 00:00:00 2001
From: Jose Ignacio Tornos Martinez <jtornosm@redhat.com>
Date: Mon, 29 Jan 2024 10:28:19 +0100
Subject: [PATCH 3672/4076] kbuild: rpm-pkg: simplify installkernel %post

The new installkernel application that is now included in systemd-udev
package allows installation although destination files are already present
in the boot directory of the kernel package, but is failing with the
implemented workaround for the old installkernel application from grubby
package.

For the new installkernel application, as Davide says:
<<The %post currently does a shuffling dance before calling installkernel.
This isn't actually necessary afaict, and the current implementation
ends up triggering downstream issues such as
https://github.com/systemd/systemd/issues/29568
This commit simplifies the logic to remove the shuffling. For reference,
the original logic was added in commit 3c9c7a14b627("rpm-pkg: add %post
section to create initramfs and grub hooks").>>

But we need to keep the old behavior as well, because the old installkernel
application from grubby package, does not allow this simplification and
we need to be backward compatible to avoid issues with the different
packages.

Mimic Fedora shipping process and store vmlinuz, config amd System.map
in the module directory instead of the boot directory. In this way, we will
avoid the commented problem for all the cases, because the new destination
files are not going to exist in the boot directory of the kernel package.

Replace installkernel tool with kernel-install tool, because the latter is
more complete.

Besides, after installkernel tool execution, check to complete if the
correct package files vmlinuz, System.map and config files are present
in /boot directory, and if necessary, copy manually for install operation.
In this way, take into account if  files were not previously copied from
/usr/lib/kernel/install.d/* scripts and if the suitable files for the
requested package are present (it could be others if the rpm files were
replace with a new pacakge with the same release and a different build).

Tested with Fedora 38, Fedora 39, RHEL 9, Oracle Linux 9.3,
openSUSE Tumbleweed and openMandrive ROME, using dnf/zypper and rpm tools.

cc: stable@vger.kernel.org
Co-Developed-by: Davide Cavalca <dcavalca@meta.com>
Signed-off-by: Jose Ignacio Tornos Martinez <jtornosm@redhat.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/package/kernel.spec | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
index 89298983a1694..f58726671fb37 100644
--- a/scripts/package/kernel.spec
+++ b/scripts/package/kernel.spec
@@ -55,12 +55,12 @@ patch -p1 < %{SOURCE2}
 %{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release}
 
 %install
-mkdir -p %{buildroot}/boot
-cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/vmlinuz-%{KERNELRELEASE}
+mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE}
+cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz
 %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} modules_install
 %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
-cp System.map %{buildroot}/boot/System.map-%{KERNELRELEASE}
-cp .config %{buildroot}/boot/config-%{KERNELRELEASE}
+cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE}
+cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config
 ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEASE}/build
 %if %{with_devel}
 %{make} %{makeflags} run-command KBUILD_RUN_COMMAND='${srctree}/scripts/package/install-extmod-build %{buildroot}/usr/src/kernels/%{KERNELRELEASE}'
@@ -70,13 +70,14 @@ ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEA
 rm -rf %{buildroot}
 
 %post
-if [ -x /sbin/installkernel -a -r /boot/vmlinuz-%{KERNELRELEASE} -a -r /boot/System.map-%{KERNELRELEASE} ]; then
-cp /boot/vmlinuz-%{KERNELRELEASE} /boot/.vmlinuz-%{KERNELRELEASE}-rpm
-cp /boot/System.map-%{KERNELRELEASE} /boot/.System.map-%{KERNELRELEASE}-rpm
-rm -f /boot/vmlinuz-%{KERNELRELEASE} /boot/System.map-%{KERNELRELEASE}
-/sbin/installkernel %{KERNELRELEASE} /boot/.vmlinuz-%{KERNELRELEASE}-rpm /boot/.System.map-%{KERNELRELEASE}-rpm
-rm -f /boot/.vmlinuz-%{KERNELRELEASE}-rpm /boot/.System.map-%{KERNELRELEASE}-rpm
+if [ -x /usr/bin/kernel-install ]; then
+	/usr/bin/kernel-install add %{KERNELRELEASE} /lib/modules/%{KERNELRELEASE}/vmlinuz
 fi
+for file in vmlinuz System.map config; do
+	if ! cmp --silent "/lib/modules/%{KERNELRELEASE}/${file}" "/boot/${file}-%{KERNELRELEASE}"; then
+		cp "/lib/modules/%{KERNELRELEASE}/${file}" "/boot/${file}-%{KERNELRELEASE}"
+	fi
+done
 
 %preun
 if [ -x /sbin/new-kernel-pkg ]; then
@@ -94,7 +95,6 @@ fi
 %defattr (-, root, root)
 /lib/modules/%{KERNELRELEASE}
 %exclude /lib/modules/%{KERNELRELEASE}/build
-/boot/*
 
 %files headers
 %defattr (-, root, root)
-- 
GitLab


From 1c1914d6e8c6edbf5b45047419ff51abdb1dce96 Mon Sep 17 00:00:00 2001
From: "T.J. Mercier" <tjmercier@google.com>
Date: Wed, 17 Jan 2024 18:11:40 +0000
Subject: [PATCH 3673/4076] dma-buf: heaps: Don't track CMA dma-buf pages under
 RssFile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DMA buffers allocated from the CMA dma-buf heap get counted under
RssFile for processes that map them and trigger page faults. In
addition to the incorrect accounting reported to userspace, reclaim
behavior was influenced by the MM_FILEPAGES counter until linux 6.8, but
this memory is not reclaimable. [1] Change the CMA dma-buf heap to set
VM_PFNMAP on the VMA so MM does not poke at the memory managed by this
dma-buf heap, and use vmf_insert_pfn to correct the RSS accounting.

The system dma-buf heap does not suffer from this issue since
remap_pfn_range is used during the mmap of the buffer, which also sets
VM_PFNMAP on the VMA.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/mm/vmscan.c?id=fb46e22a9e3863e08aef8815df9f17d0f4b9aede

Fixes: b61614ec318a ("dma-buf: heaps: Add CMA heap to dmabuf heaps")
Signed-off-by: T.J. Mercier <tjmercier@google.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240117181141.286383-1-tjmercier@google.com
---
 drivers/dma-buf/heaps/cma_heap.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index ee899f8e67215..4a63567e93bae 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -168,10 +168,7 @@ static vm_fault_t cma_heap_vm_fault(struct vm_fault *vmf)
 	if (vmf->pgoff > buffer->pagecount)
 		return VM_FAULT_SIGBUS;
 
-	vmf->page = buffer->pages[vmf->pgoff];
-	get_page(vmf->page);
-
-	return 0;
+	return vmf_insert_pfn(vma, vmf->address, page_to_pfn(buffer->pages[vmf->pgoff]));
 }
 
 static const struct vm_operations_struct dma_heap_vm_ops = {
@@ -185,6 +182,8 @@ static int cma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
 	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
 		return -EINVAL;
 
+	vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+
 	vma->vm_ops = &dma_heap_vm_ops;
 	vma->vm_private_data = buffer;
 
-- 
GitLab


From bfef491df67022c56aab3b831044f8d259f9441f Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Fri, 26 Jan 2024 22:30:10 +0900
Subject: [PATCH 3674/4076] kconfig: initialize sym->curr.tri to 'no' for all
 symbol types again

Geert Uytterhoeven reported that commit 4e244c10eab3 ("kconfig: remove
unneeded symbol_empty variable") changed the default value of
CONFIG_LOG_CPU_MAX_BUF_SHIFT from 12 to 0.

As it turned out, this is an undefined behavior because sym_calc_value()
stopped setting the sym->curr.tri field for 'int', 'hex', and 'string'
symbols.

This commit restores the original behavior, where 'int', 'hex', 'string'
symbols are interpreted as false if used in boolean contexts.

CONFIG_LOG_CPU_MAX_BUF_SHIFT will default to 12 again, irrespective
of CONFIG_BASE_SMALL. Presumably, this is not the intended behavior,
as already reported [1], but this is another issue that should be
addressed by a separate patch.

[1]: https://lore.kernel.org/all/f6856be8-54b7-0fa0-1d17-39632bf29ada@oracle.com/

Fixes: 4e244c10eab3 ("kconfig: remove unneeded symbol_empty variable")
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Closes: https://lore.kernel.org/all/CAMuHMdWm6u1wX7efZQf=2XUAHascps76YQac6rdnQGhc8nop_Q@mail.gmail.com/
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/kconfig/symbol.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 3e808528aaeab..e9e9fb8d86746 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -345,6 +345,8 @@ void sym_calc_value(struct symbol *sym)
 
 	oldval = sym->curr;
 
+	newval.tri = no;
+
 	switch (sym->type) {
 	case S_INT:
 		newval.val = "0";
@@ -357,7 +359,7 @@ void sym_calc_value(struct symbol *sym)
 		break;
 	case S_BOOLEAN:
 	case S_TRISTATE:
-		newval = symbol_no.curr;
+		newval.val = "n";
 		break;
 	default:
 		sym->curr.val = sym->name;
-- 
GitLab


From 1e560864159d002b453da42bd2c13a1805515a20 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Tue, 30 Jan 2024 11:02:43 +0100
Subject: [PATCH 3675/4076] PCI/ASPM: Fix deadlock when enabling ASPM

A last minute revert in 6.7-final introduced a potential deadlock when
enabling ASPM during probe of Qualcomm PCIe controllers as reported by
lockdep:

  ============================================
  WARNING: possible recursive locking detected
  6.7.0 #40 Not tainted
  --------------------------------------------
  kworker/u16:5/90 is trying to acquire lock:
  ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pcie_aspm_pm_state_change+0x58/0xdc

              but task is already holding lock:
  ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pci_walk_bus+0x34/0xbc

              other info that might help us debug this:
   Possible unsafe locking scenario:

         CPU0
         ----
    lock(pci_bus_sem);
    lock(pci_bus_sem);

               *** DEADLOCK ***

  Call trace:
   print_deadlock_bug+0x25c/0x348
   __lock_acquire+0x10a4/0x2064
   lock_acquire+0x1e8/0x318
   down_read+0x60/0x184
   pcie_aspm_pm_state_change+0x58/0xdc
   pci_set_full_power_state+0xa8/0x114
   pci_set_power_state+0xc4/0x120
   qcom_pcie_enable_aspm+0x1c/0x3c [pcie_qcom]
   pci_walk_bus+0x64/0xbc
   qcom_pcie_host_post_init_2_7_0+0x28/0x34 [pcie_qcom]

The deadlock can easily be reproduced on machines like the Lenovo ThinkPad
X13s by adding a delay to increase the race window during asynchronous
probe where another thread can take a write lock.

Add a new pci_set_power_state_locked() and associated helper functions that
can be called with the PCI bus semaphore held to avoid taking the read lock
twice.

Link: https://lore.kernel.org/r/ZZu0qx2cmn7IwTyQ@hovoldconsulting.com
Link: https://lore.kernel.org/r/20240130100243.11011-1-johan+linaro@kernel.org
Fixes: f93e71aea6c6 ("Revert "PCI/ASPM: Remove pcie_aspm_pm_state_change()"")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: <stable@vger.kernel.org>	# 6.7
---
 drivers/pci/bus.c                      | 49 ++++++++++------
 drivers/pci/controller/dwc/pcie-qcom.c |  2 +-
 drivers/pci/pci.c                      | 78 +++++++++++++++++---------
 drivers/pci/pci.h                      |  4 +-
 drivers/pci/pcie/aspm.c                | 13 +++--
 include/linux/pci.h                    |  5 ++
 6 files changed, 101 insertions(+), 50 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 9c2137dae429a..826b5016a1010 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -386,21 +386,8 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_bus_add_devices);
 
-/** pci_walk_bus - walk devices on/under bus, calling callback.
- *  @top      bus whose devices should be walked
- *  @cb       callback to be called for each device found
- *  @userdata arbitrary pointer to be passed to callback.
- *
- *  Walk the given bus, including any bridged devices
- *  on buses under this bus.  Call the provided callback
- *  on each device found.
- *
- *  We check the return of @cb each time. If it returns anything
- *  other than 0, we break out.
- *
- */
-void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
-		  void *userdata)
+static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+			   void *userdata, bool locked)
 {
 	struct pci_dev *dev;
 	struct pci_bus *bus;
@@ -408,7 +395,8 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 	int retval;
 
 	bus = top;
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	next = top->devices.next;
 	for (;;) {
 		if (next == &bus->devices) {
@@ -431,10 +419,37 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		if (retval)
 			break;
 	}
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
+}
+
+/**
+ *  pci_walk_bus - walk devices on/under bus, calling callback.
+ *  @top: bus whose devices should be walked
+ *  @cb: callback to be called for each device found
+ *  @userdata: arbitrary pointer to be passed to callback
+ *
+ *  Walk the given bus, including any bridged devices
+ *  on buses under this bus.  Call the provided callback
+ *  on each device found.
+ *
+ *  We check the return of @cb each time. If it returns anything
+ *  other than 0, we break out.
+ */
+void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
+{
+	__pci_walk_bus(top, cb, userdata, false);
 }
 EXPORT_SYMBOL_GPL(pci_walk_bus);
 
+void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
+{
+	lockdep_assert_held(&pci_bus_sem);
+
+	__pci_walk_bus(top, cb, userdata, true);
+}
+EXPORT_SYMBOL_GPL(pci_walk_bus_locked);
+
 struct pci_bus *pci_bus_get(struct pci_bus *bus)
 {
 	if (bus)
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 10f2d0bb86bec..2ce2a3bd932bd 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -972,7 +972,7 @@ static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata)
 	 * Downstream devices need to be in D0 state before enabling PCI PM
 	 * substates.
 	 */
-	pci_set_power_state(pdev, PCI_D0);
+	pci_set_power_state_locked(pdev, PCI_D0);
 	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
 
 	return 0;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d8f11a078924c..9ab9b1008d8b9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1354,6 +1354,7 @@ end:
 /**
  * pci_set_full_power_state - Put a PCI device into D0 and update its state
  * @dev: PCI device to power up
+ * @locked: whether pci_bus_sem is held
  *
  * Call pci_power_up() to put @dev into D0, read from its PCI_PM_CTRL register
  * to confirm the state change, restore its BARs if they might be lost and
@@ -1363,7 +1364,7 @@ end:
  * to D0, it is more efficient to use pci_power_up() directly instead of this
  * function.
  */
-static int pci_set_full_power_state(struct pci_dev *dev)
+static int pci_set_full_power_state(struct pci_dev *dev, bool locked)
 {
 	u16 pmcsr;
 	int ret;
@@ -1399,7 +1400,7 @@ static int pci_set_full_power_state(struct pci_dev *dev)
 	}
 
 	if (dev->bus->self)
-		pcie_aspm_pm_state_change(dev->bus->self);
+		pcie_aspm_pm_state_change(dev->bus->self, locked);
 
 	return 0;
 }
@@ -1428,10 +1429,22 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state)
 		pci_walk_bus(bus, __pci_dev_set_current_state, &state);
 }
 
+static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state, bool locked)
+{
+	if (!bus)
+		return;
+
+	if (locked)
+		pci_walk_bus_locked(bus, __pci_dev_set_current_state, &state);
+	else
+		pci_walk_bus(bus, __pci_dev_set_current_state, &state);
+}
+
 /**
  * pci_set_low_power_state - Put a PCI device into a low-power state.
  * @dev: PCI device to handle.
  * @state: PCI power state (D1, D2, D3hot) to put the device into.
+ * @locked: whether pci_bus_sem is held
  *
  * Use the device's PCI_PM_CTRL register to put it into a low-power state.
  *
@@ -1442,7 +1455,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state)
  * 0 if device already is in the requested state.
  * 0 if device's power state has been successfully changed.
  */
-static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state)
+static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool locked)
 {
 	u16 pmcsr;
 
@@ -1496,29 +1509,12 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state)
 				     pci_power_name(state));
 
 	if (dev->bus->self)
-		pcie_aspm_pm_state_change(dev->bus->self);
+		pcie_aspm_pm_state_change(dev->bus->self, locked);
 
 	return 0;
 }
 
-/**
- * pci_set_power_state - Set the power state of a PCI device
- * @dev: PCI device to handle.
- * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
- *
- * Transition a device to a new power state, using the platform firmware and/or
- * the device's PCI PM registers.
- *
- * RETURN VALUE:
- * -EINVAL if the requested state is invalid.
- * -EIO if device does not support PCI PM or its PM capabilities register has a
- * wrong version, or device doesn't support the requested state.
- * 0 if the transition is to D1 or D2 but D1 and D2 are not supported.
- * 0 if device already is in the requested state.
- * 0 if the transition is to D3 but D3 is not supported.
- * 0 if device's power state has been successfully changed.
- */
-int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
+static int __pci_set_power_state(struct pci_dev *dev, pci_power_t state, bool locked)
 {
 	int error;
 
@@ -1542,7 +1538,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		return 0;
 
 	if (state == PCI_D0)
-		return pci_set_full_power_state(dev);
+		return pci_set_full_power_state(dev, locked);
 
 	/*
 	 * This device is quirked not to be put into D3, so don't put it in
@@ -1556,16 +1552,16 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		 * To put the device in D3cold, put it into D3hot in the native
 		 * way, then put it into D3cold using platform ops.
 		 */
-		error = pci_set_low_power_state(dev, PCI_D3hot);
+		error = pci_set_low_power_state(dev, PCI_D3hot, locked);
 
 		if (pci_platform_power_transition(dev, PCI_D3cold))
 			return error;
 
 		/* Powering off a bridge may power off the whole hierarchy */
 		if (dev->current_state == PCI_D3cold)
-			pci_bus_set_current_state(dev->subordinate, PCI_D3cold);
+			__pci_bus_set_current_state(dev->subordinate, PCI_D3cold, locked);
 	} else {
-		error = pci_set_low_power_state(dev, state);
+		error = pci_set_low_power_state(dev, state, locked);
 
 		if (pci_platform_power_transition(dev, state))
 			return error;
@@ -1573,8 +1569,38 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 
 	return 0;
 }
+
+/**
+ * pci_set_power_state - Set the power state of a PCI device
+ * @dev: PCI device to handle.
+ * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
+ *
+ * Transition a device to a new power state, using the platform firmware and/or
+ * the device's PCI PM registers.
+ *
+ * RETURN VALUE:
+ * -EINVAL if the requested state is invalid.
+ * -EIO if device does not support PCI PM or its PM capabilities register has a
+ * wrong version, or device doesn't support the requested state.
+ * 0 if the transition is to D1 or D2 but D1 and D2 are not supported.
+ * 0 if device already is in the requested state.
+ * 0 if the transition is to D3 but D3 is not supported.
+ * 0 if device's power state has been successfully changed.
+ */
+int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
+{
+	return __pci_set_power_state(dev, state, false);
+}
 EXPORT_SYMBOL(pci_set_power_state);
 
+int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state)
+{
+	lockdep_assert_held(&pci_bus_sem);
+
+	return __pci_set_power_state(dev, state, true);
+}
+EXPORT_SYMBOL(pci_set_power_state_locked);
+
 #define PCI_EXP_SAVE_REGS	7
 
 static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev,
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 2336a8d1edab2..e9750b1b19bad 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -571,12 +571,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt);
 #ifdef CONFIG_PCIEASPM
 void pcie_aspm_init_link_state(struct pci_dev *pdev);
 void pcie_aspm_exit_link_state(struct pci_dev *pdev);
-void pcie_aspm_pm_state_change(struct pci_dev *pdev);
+void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked);
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev);
 #else
 static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { }
 static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { }
-static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { }
+static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { }
 static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { }
 #endif
 
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 5a0066ecc3c5a..bc0bd86695ec6 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1003,8 +1003,11 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 	up_read(&pci_bus_sem);
 }
 
-/* @pdev: the root port or switch downstream port */
-void pcie_aspm_pm_state_change(struct pci_dev *pdev)
+/*
+ * @pdev: the root port or switch downstream port
+ * @locked: whether pci_bus_sem is held
+ */
+void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked)
 {
 	struct pcie_link_state *link = pdev->link_state;
 
@@ -1014,12 +1017,14 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev)
 	 * Devices changed PM state, we should recheck if latency
 	 * meets all functions' requirement
 	 */
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	pcie_update_aspm_capable(link->root);
 	pcie_config_aspm_path(link);
 	mutex_unlock(&aspm_lock);
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
 }
 
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index add9368e6314b..7ab0d13672daf 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1422,6 +1422,7 @@ int pci_load_and_free_saved_state(struct pci_dev *dev,
 				  struct pci_saved_state **state);
 int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state);
 int pci_set_power_state(struct pci_dev *dev, pci_power_t state);
+int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state);
 pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state);
 bool pci_pme_capable(struct pci_dev *dev, pci_power_t state);
 void pci_pme_active(struct pci_dev *dev, bool enable);
@@ -1625,6 +1626,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
 
 void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		  void *userdata);
+void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+			 void *userdata);
 int pci_cfg_space_size(struct pci_dev *dev);
 unsigned char pci_bus_max_busnr(struct pci_bus *bus);
 void pci_setup_bridge(struct pci_bus *bus);
@@ -2025,6 +2028,8 @@ static inline int pci_save_state(struct pci_dev *dev) { return 0; }
 static inline void pci_restore_state(struct pci_dev *dev) { }
 static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 { return 0; }
+static inline int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state)
+{ return 0; }
 static inline int pci_wake_from_d3(struct pci_dev *dev, bool enable)
 { return 0; }
 static inline pci_power_t pci_choose_state(struct pci_dev *dev,
-- 
GitLab


From 925bd5e08106bd5bfbd1cb8e124c89a0b4003569 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Mon, 29 Jan 2024 17:59:33 +0100
Subject: [PATCH 3676/4076] MAINTAINERS: Add Manivannan Sadhasivam as PCI
 Endpoint maintainer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PCI endpoint subsystem is evolving at a rate I cannot keep up with,
therefore I am standing down as a maintainer handing over to Manivannan
(currently reviewer for this code) and Krzysztof who are doing an excellent
job on the matter - they don't need my help any longer.

Link: https://lore.kernel.org/r/20240129165933.33428-1-lpieralisi@kernel.org
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: Krzysztof Wilczyński <kw@linux.com>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a692..a40cfcd1c65e7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16856,9 +16856,8 @@ F:	Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml
 F:	drivers/pci/controller/pcie-xilinx-cpm.c
 
 PCI ENDPOINT SUBSYSTEM
-M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
+M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 M:	Krzysztof Wilczyński <kw@linux.com>
-R:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 R:	Kishon Vijay Abraham I <kishon@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
-- 
GitLab


From 9189526c46f2ad14df25dbdc30443f79d03dc7bd Mon Sep 17 00:00:00 2001
From: Andi Shyti <andi.shyti@kernel.org>
Date: Wed, 24 Jan 2024 23:50:31 +0100
Subject: [PATCH 3677/4076] MAINTAINERS: Update i2c host drivers repository

The i2c host patches are now set to be merged into the following
repository:

git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux.git

Cc: Wolfram Sang <wsa@kernel.org>
Acked-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8999497011a26..179929cce68c5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10091,7 +10091,7 @@ L:	linux-i2c@vger.kernel.org
 S:	Maintained
 W:	https://i2c.wiki.kernel.org/
 Q:	https://patchwork.ozlabs.org/project/linux-i2c/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux.git
 F:	Documentation/devicetree/bindings/i2c/
 F:	drivers/i2c/algos/
 F:	drivers/i2c/busses/
-- 
GitLab


From 5b778e1c2e9760ffe99482de26e70cd74683ba5c Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:35 -0800
Subject: [PATCH 3678/4076] wifi: fill in MODULE_DESCRIPTION()s for wlcore

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the TI WLAN wlcore drivers.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-2-leitao@debian.org
---
 drivers/net/wireless/ti/wlcore/main.c | 1 +
 drivers/net/wireless/ti/wlcore/sdio.c | 1 +
 drivers/net/wireless/ti/wlcore/spi.c  | 1 +
 3 files changed, 3 insertions(+)

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index fb9ed97774c7a..5736acb4d2063 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -6793,6 +6793,7 @@ MODULE_PARM_DESC(bug_on_recovery, "BUG() on fw recovery");
 module_param(no_recovery, int, 0600);
 MODULE_PARM_DESC(no_recovery, "Prevent HW recovery. FW will remain stuck.");
 
+MODULE_DESCRIPTION("TI WLAN core driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index f0686635db46e..eb5482ed76ae4 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -447,6 +447,7 @@ module_sdio_driver(wl1271_sdio_driver);
 module_param(dump, bool, 0600);
 MODULE_PARM_DESC(dump, "Enable sdio read/write dumps.");
 
+MODULE_DESCRIPTION("TI WLAN SDIO helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index 7d9a139db59e1..0aa2b2f3c5c91 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -562,6 +562,7 @@ static struct spi_driver wl1271_spi_driver = {
 };
 
 module_spi_driver(wl1271_spi_driver);
+MODULE_DESCRIPTION("TI WLAN SPI helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
-- 
GitLab


From 2f2b503ea770cf817044851a583e8880d1de4ae2 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:36 -0800
Subject: [PATCH 3679/4076] wifi: fill in MODULE_DESCRIPTION()s for wl1251 and
 wl12xx

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the TI wireless drivers wl12xx and wl1251.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-3-leitao@debian.org
---
 drivers/net/wireless/ti/wl1251/sdio.c | 1 +
 drivers/net/wireless/ti/wl1251/spi.c  | 1 +
 drivers/net/wireless/ti/wl12xx/main.c | 1 +
 3 files changed, 3 insertions(+)

diff --git a/drivers/net/wireless/ti/wl1251/sdio.c b/drivers/net/wireless/ti/wl1251/sdio.c
index 301bd0043a435..4e5b351f80f09 100644
--- a/drivers/net/wireless/ti/wl1251/sdio.c
+++ b/drivers/net/wireless/ti/wl1251/sdio.c
@@ -343,5 +343,6 @@ static void __exit wl1251_sdio_exit(void)
 module_init(wl1251_sdio_init);
 module_exit(wl1251_sdio_exit);
 
+MODULE_DESCRIPTION("TI WL1251 SDIO helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kalle Valo <kvalo@adurom.com>");
diff --git a/drivers/net/wireless/ti/wl1251/spi.c b/drivers/net/wireless/ti/wl1251/spi.c
index 29292f06bd3dc..1936bb3af54ab 100644
--- a/drivers/net/wireless/ti/wl1251/spi.c
+++ b/drivers/net/wireless/ti/wl1251/spi.c
@@ -342,6 +342,7 @@ static struct spi_driver wl1251_spi_driver = {
 
 module_spi_driver(wl1251_spi_driver);
 
+MODULE_DESCRIPTION("TI WL1251 SPI helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kalle Valo <kvalo@adurom.com>");
 MODULE_ALIAS("spi:wl1251");
diff --git a/drivers/net/wireless/ti/wl12xx/main.c b/drivers/net/wireless/ti/wl12xx/main.c
index de045fe4ca1eb..b26d42b4e3cc0 100644
--- a/drivers/net/wireless/ti/wl12xx/main.c
+++ b/drivers/net/wireless/ti/wl12xx/main.c
@@ -1955,6 +1955,7 @@ module_param_named(tcxo, tcxo_param, charp, 0);
 MODULE_PARM_DESC(tcxo,
 		 "TCXO clock: 19.2, 26, 38.4, 52, 16.368, 32.736, 16.8, 33.6");
 
+MODULE_DESCRIPTION("TI WL12xx wireless driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_FIRMWARE(WL127X_FW_NAME_SINGLE);
-- 
GitLab


From 257ca10c7317d4a424e48bb95d14ca53a1f1dd6f Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:37 -0800
Subject: [PATCH 3680/4076] wifi: fill in MODULE_DESCRIPTION()s for Broadcom
 WLAN

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Broadcom FullMac WLAN drivers.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-4-leitao@debian.org
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c | 1 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c | 1 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c | 1 +
 3 files changed, 3 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
index d55f3271d6190..4f0c1e1a8e605 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_bca_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_BCA, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Broadcom AP chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
index f82fbbe3ecefb..90d06cda03a2f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_cyw_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_CYW, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Cypress/Infineon chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
index 02918d434556b..b66135e3cff47 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_wcc_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_WCC, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Broadcom mobility chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
-- 
GitLab


From f8782ea450ad83df5f3dfdb1fca093f46238febe Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:38 -0800
Subject: [PATCH 3681/4076] wifi: fill in MODULE_DESCRIPTION()s for ar5523

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Atheros AR5523 wireless driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-5-leitao@debian.org
---
 drivers/net/wireless/ath/ar5523/ar5523.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 43e0db78d42be..a742cec44e3db 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1803,5 +1803,6 @@ static struct usb_driver ar5523_driver = {
 
 module_usb_driver(ar5523_driver);
 
+MODULE_DESCRIPTION("Atheros AR5523 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_FIRMWARE(AR5523_FIRMWARE_FILE);
-- 
GitLab


From e063d2a05d713d396044124867704b08e5c30860 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:39 -0800
Subject: [PATCH 3682/4076] wifi: fill in MODULE_DESCRIPTION()s for wcn36xx

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Qualcomm Atheros WCN3660/3680 wireless driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-6-leitao@debian.org
---
 drivers/net/wireless/ath/wcn36xx/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 41119fb177e30..4e6b4df8562f6 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1685,6 +1685,7 @@ static struct platform_driver wcn36xx_driver = {
 
 module_platform_driver(wcn36xx_driver);
 
+MODULE_DESCRIPTION("Qualcomm Atheros WCN3660/3680 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Eugene Krasnikov k.eugene.e@gmail.com");
 MODULE_FIRMWARE(WLAN_NV_FILE);
-- 
GitLab


From 714ea2f109d9d561789078fd8a1beeffa9af36d6 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:40 -0800
Subject: [PATCH 3683/4076] wifi: fill in MODULE_DESCRIPTION()s for p54spi

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Prism54 SPI wireless driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-7-leitao@debian.org
---
 drivers/net/wireless/intersil/p54/p54spi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intersil/p54/p54spi.c b/drivers/net/wireless/intersil/p54/p54spi.c
index ce0179b8ab368..0073b5e0f9c90 100644
--- a/drivers/net/wireless/intersil/p54/p54spi.c
+++ b/drivers/net/wireless/intersil/p54/p54spi.c
@@ -700,6 +700,7 @@ static struct spi_driver p54spi_driver = {
 
 module_spi_driver(p54spi_driver);
 
+MODULE_DESCRIPTION("Prism54 SPI wireless driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Lamparter <chunkeey@web.de>");
 MODULE_ALIAS("spi:cx3110x");
-- 
GitLab


From 35337ac472605da9db051827fa2d39e6c02c6d81 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:41 -0800
Subject: [PATCH 3684/4076] wifi: fill in MODULE_DESCRIPTION()s for wl18xx

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the TI WiLink 8 wireless driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-8-leitao@debian.org
---
 drivers/net/wireless/ti/wl18xx/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ti/wl18xx/main.c b/drivers/net/wireless/ti/wl18xx/main.c
index 20d9181b3410c..2ccac1cdec012 100644
--- a/drivers/net/wireless/ti/wl18xx/main.c
+++ b/drivers/net/wireless/ti/wl18xx/main.c
@@ -2086,6 +2086,7 @@ module_param_named(num_rx_desc, num_rx_desc_param, int, 0400);
 MODULE_PARM_DESC(num_rx_desc_param,
 		 "Number of Rx descriptors: u8 (default is 32)");
 
+MODULE_DESCRIPTION("TI WiLink 8 wireless driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_FIRMWARE(WL18XX_FW_NAME);
-- 
GitLab


From c9013880284d78bac6498d9c0b0b7043cf0f5639 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:42 -0800
Subject: [PATCH 3685/4076] wifi: fill in MODULE_DESCRIPTION()s for wilc1000

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Atmel WILC1000 SPI driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-9-leitao@debian.org
---
 drivers/net/wireless/microchip/wilc1000/netdev.c | 1 +
 drivers/net/wireless/microchip/wilc1000/sdio.c   | 1 +
 drivers/net/wireless/microchip/wilc1000/spi.c    | 1 +
 3 files changed, 3 insertions(+)

diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index 91d71e0f7ef23..81e8f25863f5b 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -1018,5 +1018,6 @@ unregister_netdev:
 	return ERR_PTR(ret);
 }
 
+MODULE_DESCRIPTION("Atmel WILC1000 core wireless driver");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(WILC1000_FW(WILC1000_API_VER));
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 0d13e3e46e98e..d6d3946930905 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -984,4 +984,5 @@ static struct sdio_driver wilc_sdio_driver = {
 module_driver(wilc_sdio_driver,
 	      sdio_register_driver,
 	      sdio_unregister_driver);
+MODULE_DESCRIPTION("Atmel WILC1000 SDIO wireless driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index 77b4cdff73c37..1d8b241ce43ca 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -273,6 +273,7 @@ static struct spi_driver wilc_spi_driver = {
 	.remove = wilc_bus_remove,
 };
 module_spi_driver(wilc_spi_driver);
+MODULE_DESCRIPTION("Atmel WILC1000 SPI wireless driver");
 MODULE_LICENSE("GPL");
 
 static int wilc_spi_tx(struct wilc *wilc, u8 *b, u32 len)
-- 
GitLab


From f3f8f050316893fe2da523458ff7f5f6d61fb1a6 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:43 -0800
Subject: [PATCH 3686/4076] wifi: fill in MODULE_DESCRIPTION()s for mt76
 drivers

W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the MediaTek mt76 drivers.

Here is a sorted list of descriptions. It might make the reviewing
process easier.

	MODULE_DESCRIPTION("MediaTek MT7603E and MT76x8 wireless driver");
	MODULE_DESCRIPTION("MediaTek MT7615E and MT7663E wireless driver");
	MODULE_DESCRIPTION("MediaTek MT7615E MMIO helpers");
	MODULE_DESCRIPTION("MediaTek MT7663 SDIO/USB helpers");
	MODULE_DESCRIPTION("MediaTek MT7663S (SDIO) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT7663U (USB) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT76x02 helpers");
	MODULE_DESCRIPTION("MediaTek MT76x02 MCU helpers");
	MODULE_DESCRIPTION("MediaTek MT76x0E (PCIe) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT76x0U (USB) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT76x2 EEPROM helpers");
	MODULE_DESCRIPTION("MediaTek MT76x2E (PCIe) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT76x2U (USB) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT76x connac layer helpers");
	MODULE_DESCRIPTION("MediaTek MT76x EEPROM helpers");
	MODULE_DESCRIPTION("MediaTek MT76x helpers");
	MODULE_DESCRIPTION("MediaTek MT76x SDIO helpers");
	MODULE_DESCRIPTION("MediaTek MT76x USB helpers");
	MODULE_DESCRIPTION("MediaTek MT7915E MMIO helpers");
	MODULE_DESCRIPTION("MediaTek MT7921 core driver");
	MODULE_DESCRIPTION("MediaTek MT7921E (PCIe) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT7921S (SDIO) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT7921U (USB) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT7925 core driver");
	MODULE_DESCRIPTION("MediaTek MT7925E (PCIe) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT7925U (USB) wireless driver");
	MODULE_DESCRIPTION("MediaTek MT792x core driver");
	MODULE_DESCRIPTION("MediaTek MT792x USB helpers");
	MODULE_DESCRIPTION("MediaTek MT7996 MMIO helpers");

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-10-leitao@debian.org
---
 drivers/net/wireless/mediatek/mt76/mt7603/main.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt7615/main.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt7615/mmio.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt7615/sdio.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt7615/usb.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c | 1 +
 drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c   | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c    | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c   | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x2/pci.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x2/usb.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt7915/mmio.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt7921/main.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt7921/pci.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt7921/sdio.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt7921/usb.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt7925/main.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt7925/pci.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt7925/usb.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt792x_core.c     | 1 +
 drivers/net/wireless/mediatek/mt76/mt792x_usb.c      | 1 +
 drivers/net/wireless/mediatek/mt76/mt7996/mmio.c     | 1 +
 drivers/net/wireless/mediatek/mt76/sdio.c            | 1 +
 drivers/net/wireless/mediatek/mt76/usb.c             | 1 +
 drivers/net/wireless/mediatek/mt76/util.c            | 1 +
 29 files changed, 29 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 89d738deea62e..e2146d30e5536 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -728,6 +728,7 @@ const struct ieee80211_ops mt7603_ops = {
 	.set_sar_specs = mt7603_set_sar_specs,
 };
 
+MODULE_DESCRIPTION("MediaTek MT7603E and MT76x8 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static int __init mt7603_init(void)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index dab16b5fc3861..0971c164b57e9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -1375,4 +1375,5 @@ const struct ieee80211_ops mt7615_ops = {
 };
 EXPORT_SYMBOL_GPL(mt7615_ops);
 
+MODULE_DESCRIPTION("MediaTek MT7615E and MT7663E wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
index ac036a072439d..87a956ea3ad74 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
@@ -270,4 +270,5 @@ static void __exit mt7615_exit(void)
 
 module_init(mt7615_init);
 module_exit(mt7615_exit);
+MODULE_DESCRIPTION("MediaTek MT7615E MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
index 67cedd2555f97..9692890ba51b7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
@@ -253,4 +253,5 @@ module_sdio_driver(mt7663s_driver);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7663S (SDIO) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
index 04963b9f74983..df737e1ff27b7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
@@ -281,4 +281,5 @@ module_usb_driver(mt7663u_driver);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7663U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
index 0052d103e276a..820b395900275 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
@@ -349,4 +349,5 @@ EXPORT_SYMBOL_GPL(mt7663_usb_sdio_register_device);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT7663 SDIO/USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index 96494ba2fdf76..3a20ba0d24928 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -3160,4 +3160,5 @@ exit:
 EXPORT_SYMBOL_GPL(mt76_connac2_mcu_fill_message);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT76x connac layer helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
index c3a392a1a659e..bcd24c9072ec9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -342,4 +342,5 @@ int mt76x0_eeprom_init(struct mt76x02_dev *dev)
 	return 0;
 }
 
+MODULE_DESCRIPTION("MediaTek MT76x EEPROM helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 9277ff38b7a22..293e66fa83d5d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -302,6 +302,7 @@ static const struct pci_device_id mt76x0e_device_table[] = {
 MODULE_DEVICE_TABLE(pci, mt76x0e_device_table);
 MODULE_FIRMWARE(MT7610E_FIRMWARE);
 MODULE_FIRMWARE(MT7650E_FIRMWARE);
+MODULE_DESCRIPTION("MediaTek MT76x0E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static struct pci_driver mt76x0e_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 0422c332354a1..dd042949cf82b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -336,6 +336,7 @@ err:
 MODULE_DEVICE_TABLE(usb, mt76x0_device_table);
 MODULE_FIRMWARE(MT7610E_FIRMWARE);
 MODULE_FIRMWARE(MT7610U_FIRMWARE);
+MODULE_DESCRIPTION("MediaTek MT76x0U (USB) wireless driver");
 MODULE_LICENSE("GPL");
 
 static struct usb_driver mt76x0_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
index 02da543dfc5cf..b2cc449142945 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
@@ -293,4 +293,5 @@ void mt76x02u_init_mcu(struct mt76_dev *dev)
 EXPORT_SYMBOL_GPL(mt76x02u_init_mcu);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x02 MCU helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 8a0e8124b8940..8020446be37bd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -696,4 +696,5 @@ void mt76x02_config_mac_addr_list(struct mt76x02_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76x02_config_mac_addr_list);
 
+MODULE_DESCRIPTION("MediaTek MT76x02 helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
index 8c01855885ce3..1fe5f5a02f937 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
@@ -506,4 +506,5 @@ int mt76x2_eeprom_init(struct mt76x02_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76x2_eeprom_init);
 
+MODULE_DESCRIPTION("MediaTek MT76x2 EEPROM helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index df85ebc6e1df0..30959746e9242 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -165,6 +165,7 @@ mt76x2e_resume(struct pci_dev *pdev)
 MODULE_DEVICE_TABLE(pci, mt76x2e_device_table);
 MODULE_FIRMWARE(MT7662_FIRMWARE);
 MODULE_FIRMWARE(MT7662_ROM_PATCH);
+MODULE_DESCRIPTION("MediaTek MT76x2E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static struct pci_driver mt76pci_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 55068f3252ef3..ca78e14251c2f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -147,4 +147,5 @@ static struct usb_driver mt76x2u_driver = {
 module_usb_driver(mt76x2u_driver);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x2U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index aff4f21e843d2..3039f53e22454 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -958,4 +958,5 @@ static void __exit mt7915_exit(void)
 
 module_init(mt7915_init);
 module_exit(mt7915_exit);
+MODULE_DESCRIPTION("MediaTek MT7915E MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 0645417e05825..0d5adc5ddae38 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1418,5 +1418,6 @@ const struct ieee80211_ops mt7921_ops = {
 };
 EXPORT_SYMBOL_GPL(mt7921_ops);
 
+MODULE_DESCRIPTION("MediaTek MT7921 core driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 57903c6e4f11f..dde26f3274783 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -544,4 +544,5 @@ MODULE_FIRMWARE(MT7922_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7922_ROM_PATCH);
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7921E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index 7591e54d28973..a9ce1e746b954 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -323,5 +323,6 @@ static struct sdio_driver mt7921s_driver = {
 	.drv.pm		= pm_sleep_ptr(&mt7921s_pm_ops),
 };
 module_sdio_driver(mt7921s_driver);
+MODULE_DESCRIPTION("MediaTek MT7921S (SDIO) wireless driver");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index e5258c74fc077..8b7c03c47598d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -336,5 +336,6 @@ static struct usb_driver mt7921u_driver = {
 };
 module_usb_driver(mt7921u_driver);
 
+MODULE_DESCRIPTION("MediaTek MT7921U (USB) wireless driver");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 8f1075da49039..125a1be3cb64c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1450,4 +1450,5 @@ const struct ieee80211_ops mt7925_ops = {
 EXPORT_SYMBOL_GPL(mt7925_ops);
 
 MODULE_AUTHOR("Deren Wu <deren.wu@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT7925 core driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index 734f31ee40d3f..1fd99a8565415 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -583,4 +583,5 @@ MODULE_FIRMWARE(MT7925_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7925_ROM_PATCH);
 MODULE_AUTHOR("Deren Wu <deren.wu@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7925E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
index 9b885c5b3ed59..1e0f094fc9059 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
@@ -329,4 +329,5 @@ static struct usb_driver mt7925u_driver = {
 module_usb_driver(mt7925u_driver);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7925U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index 502be22dbe367..c42101aa9e45e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -862,5 +862,6 @@ int mt792x_load_firmware(struct mt792x_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt792x_load_firmware);
 
+MODULE_DESCRIPTION("MediaTek MT792x core driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
index 2dd283caed36b..589a3efb9f8c3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
@@ -314,5 +314,6 @@ void mt792xu_disconnect(struct usb_interface *usb_intf)
 }
 EXPORT_SYMBOL_GPL(mt792xu_disconnect);
 
+MODULE_DESCRIPTION("MediaTek MT792x USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index c50d89a445e95..9f2abfa273c9b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -650,4 +650,5 @@ static void __exit mt7996_exit(void)
 
 module_init(mt7996_init);
 module_exit(mt7996_exit);
+MODULE_DESCRIPTION("MediaTek MT7996 MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c
index c52d550f0c32a..3e88798df0178 100644
--- a/drivers/net/wireless/mediatek/mt76/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/sdio.c
@@ -672,4 +672,5 @@ EXPORT_SYMBOL_GPL(mt76s_init);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT76x SDIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 1584665fe3cb6..5a0bcb5071bd7 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -1128,4 +1128,5 @@ int mt76u_init(struct mt76_dev *dev, struct usb_interface *intf)
 EXPORT_SYMBOL_GPL(mt76u_init);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c
index fc76c66ff1a5a..d6c01a2dd1988 100644
--- a/drivers/net/wireless/mediatek/mt76/util.c
+++ b/drivers/net/wireless/mediatek/mt76/util.c
@@ -138,4 +138,5 @@ int __mt76_worker_fn(void *ptr)
 }
 EXPORT_SYMBOL_GPL(__mt76_worker_fn);
 
+MODULE_DESCRIPTION("MediaTek MT76x helpers");
 MODULE_LICENSE("Dual BSD/GPL");
-- 
GitLab


From c9ec85153fea6873c52ed4f5055c87263f1b54f9 Mon Sep 17 00:00:00 2001
From: Matthias May <Matthias.May@westermo.com>
Date: Tue, 30 Jan 2024 10:12:18 +0000
Subject: [PATCH 3687/4076] selftests: net: add missing config for GENEVE

l2_tos_ttl_inherit.sh verifies the inheritance of tos and ttl
for GRETAP, VXLAN and GENEVE.
Before testing it checks if the required module is available
and if not skips the tests accordingly.
Currently only GRETAP and VXLAN are tested because the GENEVE
module is missing.

Fixes: b690842d12fd ("selftests/net: test l2 tunnel TOS/TTL inheriting")
Signed-off-by: Matthias May <matthias.may@westermo.com>
Link: https://lore.kernel.org/r/20240130101157.196006-1-matthias.may@westermo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 3d908b52f22f3..77a173635a29b 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -19,6 +19,7 @@ CONFIG_BRIDGE_VLAN_FILTERING=y
 CONFIG_BRIDGE=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_VLAN_8021Q=y
+CONFIG_GENEVE=m
 CONFIG_IFB=y
 CONFIG_INET_DIAG=y
 CONFIG_IP_GRE=m
-- 
GitLab


From fdd0ae72b34e56eb5e896d067c49a78ecb451032 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 31 Jan 2024 11:24:40 -0300
Subject: [PATCH 3688/4076] perf tools headers: update the
 asm-generic/unaligned.h copy with the kernel sources

To pick up the changes in:

  1ab33c03145d0f6c ("asm-generic: make sparse happy with odd-sized put_unaligned_*()")

Addressing this perf tools build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/asm-generic/unaligned.h include/asm-generic/unaligned.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/Zbp9I7rmFj1Owhug@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/asm-generic/unaligned.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h
index 2fd551915c202..cdd2fd078027a 100644
--- a/tools/include/asm-generic/unaligned.h
+++ b/tools/include/asm-generic/unaligned.h
@@ -105,9 +105,9 @@ static inline u32 get_unaligned_le24(const void *p)
 
 static inline void __put_unaligned_be24(const u32 val, u8 *p)
 {
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be24(const u32 val, void *p)
@@ -117,9 +117,9 @@ static inline void put_unaligned_be24(const u32 val, void *p)
 
 static inline void __put_unaligned_le24(const u32 val, u8 *p)
 {
-	*p++ = val;
-	*p++ = val >> 8;
-	*p++ = val >> 16;
+	*p++ = val & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = (val >> 16) & 0xff;
 }
 
 static inline void put_unaligned_le24(const u32 val, void *p)
@@ -129,12 +129,12 @@ static inline void put_unaligned_le24(const u32 val, void *p)
 
 static inline void __put_unaligned_be48(const u64 val, u8 *p)
 {
-	*p++ = val >> 40;
-	*p++ = val >> 32;
-	*p++ = val >> 24;
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 40) & 0xff;
+	*p++ = (val >> 32) & 0xff;
+	*p++ = (val >> 24) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be48(const u64 val, void *p)
-- 
GitLab


From 2b9c3eb32a699acdd4784d6b93743271b4970899 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 14 Oct 2023 12:20:15 +0200
Subject: [PATCH 3689/4076] Input: bcm5974 - check endpoint type before
 starting traffic

syzbot has found a type mismatch between a USB pipe and the transfer
endpoint, which is triggered by the bcm5974 driver[1].

This driver expects the device to provide input interrupt endpoints and
if that is not the case, the driver registration should terminate.

Repros are available to reproduce this issue with a certain setup for
the dummy_hcd, leading to an interrupt/bulk mismatch which is caught in
the USB core after calling usb_submit_urb() with the following message:
"BOGUS urb xfer, pipe 1 != type 3"

Some other device drivers (like the appletouch driver bcm5974 is mainly
based on) provide some checking mechanism to make sure that an IN
interrupt endpoint is available. In this particular case the endpoint
addresses are provided by a config table, so the checking can be
targeted to the provided endpoints.

Add some basic checking to guarantee that the endpoints available match
the expected type for both the trackpad and button endpoints.

This issue was only found for the trackpad endpoint, but the checking
has been added to the button endpoint as well for the same reasons.

Given that there was never a check for the endpoint type, this bug has
been there since the first implementation of the driver (f89bd95c5c94).

[1] https://syzkaller.appspot.com/bug?extid=348331f63b034f89b622

Fixes: f89bd95c5c94 ("Input: bcm5974 - add driver for Macbook Air and Pro Penryn touchpads")
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Reported-and-tested-by: syzbot+348331f63b034f89b622@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/20231007-topic-bcm5974_bulk-v3-1-d0f38b9d2935@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/bcm5974.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c
index ca150618d32f1..953992b458e9f 100644
--- a/drivers/input/mouse/bcm5974.c
+++ b/drivers/input/mouse/bcm5974.c
@@ -19,6 +19,7 @@
  * Copyright (C) 2006	   Nicolas Boichat (nicolas@boichat.ch)
  */
 
+#include "linux/usb.h"
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
@@ -193,6 +194,8 @@ enum tp_type {
 
 /* list of device capability bits */
 #define HAS_INTEGRATED_BUTTON	1
+/* maximum number of supported endpoints (currently trackpad and button) */
+#define MAX_ENDPOINTS	2
 
 /* trackpad finger data block size */
 #define FSIZE_TYPE1		(14 * sizeof(__le16))
@@ -891,6 +894,18 @@ static int bcm5974_resume(struct usb_interface *iface)
 	return error;
 }
 
+static bool bcm5974_check_endpoints(struct usb_interface *iface,
+				    const struct bcm5974_config *cfg)
+{
+	u8 ep_addr[MAX_ENDPOINTS + 1] = {0};
+
+	ep_addr[0] = cfg->tp_ep;
+	if (cfg->tp_type == TYPE1)
+		ep_addr[1] = cfg->bt_ep;
+
+	return usb_check_int_endpoints(iface, ep_addr);
+}
+
 static int bcm5974_probe(struct usb_interface *iface,
 			 const struct usb_device_id *id)
 {
@@ -903,6 +918,11 @@ static int bcm5974_probe(struct usb_interface *iface,
 	/* find the product index */
 	cfg = bcm5974_get_config(udev);
 
+	if (!bcm5974_check_endpoints(iface, cfg)) {
+		dev_err(&iface->dev, "Unexpected non-int endpoint\n");
+		return -ENODEV;
+	}
+
 	/* allocate memory for our device state and initialize it */
 	dev = kzalloc(sizeof(struct bcm5974), GFP_KERNEL);
 	input_dev = input_allocate_device();
-- 
GitLab


From 66bbea9ed6446b8471d365a22734dc00556c4785 Mon Sep 17 00:00:00 2001
From: Vincent Donnefort <vdonnefort@google.com>
Date: Wed, 31 Jan 2024 14:09:55 +0000
Subject: [PATCH 3690/4076] ring-buffer: Clean ring_buffer_poll_wait() error
 return

The return type for ring_buffer_poll_wait() is __poll_t. This is behind
the scenes an unsigned where we can set event bits. In case of a
non-allocated CPU, we do return instead -EINVAL (0xffffffea). Lucky us,
this ends up setting few error bits (EPOLLERR | EPOLLHUP | EPOLLNVAL), so
user-space at least is aware something went wrong.

Nonetheless, this is an incorrect code. Replace that -EINVAL with a
proper EPOLLERR to clean that output. As this doesn't change the
behaviour, there's no need to treat this change as a bug fix.

Link: https://lore.kernel.org/linux-trace-kernel/20240131140955.3322792-1-vdonnefort@google.com

Cc: stable@vger.kernel.org
Fixes: 6721cb6002262 ("ring-buffer: Do not poll non allocated cpu buffers")
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 13aaf5e85b811..fd4bfe3ecf014 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -944,7 +944,7 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
-			return -EINVAL;
+			return EPOLLERR;
 
 		cpu_buffer = buffer->buffers[cpu];
 		work = &cpu_buffer->irq_work;
-- 
GitLab


From d81786f53aec14fd4d56263145a0635afbc64617 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 31 Jan 2024 13:49:19 -0500
Subject: [PATCH 3691/4076] tracefs: Zero out the tracefs_inode when allocating
 it

eventfs uses the tracefs_inode and assumes that it's already initialized
to zero. That is, it doesn't set fields to zero (like ti->private) after
getting its tracefs_inode. This causes bugs due to stale values.

Just initialize the entire structure to zero on allocation so there isn't
any more surprises.

This is a partial fix to access to ti->private. The assignment still needs
to be made before the dentry is instantiated.

Link: https://lore.kernel.org/linux-trace-kernel/20240131185512.315825944@goodmis.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: 5790b1fb3d672 ("eventfs: Remove eventfs_file and just use eventfs_inode")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401291043.e62e89dc-oliver.sang@intel.com
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/inode.c    | 6 ++++--
 fs/tracefs/internal.h | 3 ++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index e1b172c0e091a..888e420878477 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -38,8 +38,6 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
 	if (!ti)
 		return NULL;
 
-	ti->flags = 0;
-
 	return &ti->vfs_inode;
 }
 
@@ -779,7 +777,11 @@ static void init_once(void *foo)
 {
 	struct tracefs_inode *ti = (struct tracefs_inode *) foo;
 
+	/* inode_init_once() calls memset() on the vfs_inode portion */
 	inode_init_once(&ti->vfs_inode);
+
+	/* Zero out the rest */
+	memset_after(ti, 0, vfs_inode);
 }
 
 static int __init tracefs_init(void)
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 91c2bf0b91d9c..7d84349ade872 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -11,9 +11,10 @@ enum {
 };
 
 struct tracefs_inode {
+	struct inode            vfs_inode;
+	/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
 	unsigned long           flags;
 	void                    *private;
-	struct inode            vfs_inode;
 };
 
 /*
-- 
GitLab


From 4fa4b010b83fb2f837b5ef79e38072a79e96e4f1 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 31 Jan 2024 13:49:20 -0500
Subject: [PATCH 3692/4076] eventfs: Initialize the tracefs inode properly

The tracefs-specific fields in the inode were not initialized before the
inode was exposed to others through the dentry with 'd_instantiate()'.

Move the field initializations up to before the d_instantiate.

Link: https://lore.kernel.org/linux-trace-kernel/20240131185512.478449628@goodmis.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: 5790b1fb3d672 ("eventfs: Remove eventfs_file and just use eventfs_inode")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401291043.e62e89dc-oliver.sang@intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 1c3dd0ad4660e..824b1811e342f 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -370,6 +370,8 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
+	/* Only directories have ti->private set to an ei, not files */
+	ti->private = ei;
 
 	inc_nlink(inode);
 	d_instantiate(dentry, inode);
@@ -515,7 +517,6 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 static void eventfs_post_create_dir(struct eventfs_inode *ei)
 {
 	struct eventfs_inode *ei_child;
-	struct tracefs_inode *ti;
 
 	lockdep_assert_held(&eventfs_mutex);
 
@@ -525,9 +526,6 @@ static void eventfs_post_create_dir(struct eventfs_inode *ei)
 				 srcu_read_lock_held(&eventfs_srcu)) {
 		ei_child->d_parent = ei->dentry;
 	}
-
-	ti = get_tracefs(ei->dentry->d_inode);
-	ti->private = ei;
 }
 
 /**
-- 
GitLab


From 99c001cb617df409dac275a059d6c3f187a2da7a Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 31 Jan 2024 13:49:21 -0500
Subject: [PATCH 3693/4076] tracefs: Avoid using the ei->dentry pointer
 unnecessarily

The eventfs_find_events() code tries to walk up the tree to find the
event directory that a dentry belongs to, in order to then find the
eventfs inode that is associated with that event directory.

However, it uses an odd combination of walking the dentry parent,
looking up the eventfs inode associated with that, and then looking up
the dentry from there.  Repeat.

But the code shouldn't have back-pointers to dentries in the first
place, and it should just walk the dentry parenthood chain directly.

Similarly, 'set_top_events_ownership()' looks up the dentry from the
eventfs inode, but the only reason it wants a dentry is to look up the
superblock in order to look up the root dentry.

But it already has the real filesystem inode, which has that same
superblock pointer.  So just pass in the superblock pointer using the
information that's already there, instead of looking up extraneous data
that is irrelevant.

Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240131185512.638645365@goodmis.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 824b1811e342f..e9819d719d2ac 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -156,33 +156,30 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	return ret;
 }
 
-static void update_top_events_attr(struct eventfs_inode *ei, struct dentry *dentry)
+static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb)
 {
-	struct inode *inode;
+	struct inode *root;
 
 	/* Only update if the "events" was on the top level */
 	if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL))
 		return;
 
 	/* Get the tracefs root inode. */
-	inode = d_inode(dentry->d_sb->s_root);
-	ei->attr.uid = inode->i_uid;
-	ei->attr.gid = inode->i_gid;
+	root = d_inode(sb->s_root);
+	ei->attr.uid = root->i_uid;
+	ei->attr.gid = root->i_gid;
 }
 
 static void set_top_events_ownership(struct inode *inode)
 {
 	struct tracefs_inode *ti = get_tracefs(inode);
 	struct eventfs_inode *ei = ti->private;
-	struct dentry *dentry;
 
 	/* The top events directory doesn't get automatically updated */
 	if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL))
 		return;
 
-	dentry = ei->dentry;
-
-	update_top_events_attr(ei, dentry);
+	update_top_events_attr(ei, inode->i_sb);
 
 	if (!(ei->attr.mode & EVENTFS_SAVE_UID))
 		inode->i_uid = ei->attr.uid;
@@ -235,8 +232,10 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 
 	mutex_lock(&eventfs_mutex);
 	do {
-		/* The parent always has an ei, except for events itself */
-		ei = dentry->d_parent->d_fsdata;
+		// The parent is stable because we do not do renames
+		dentry = dentry->d_parent;
+		// ... and directories always have d_fsdata
+		ei = dentry->d_fsdata;
 
 		/*
 		 * If the ei is being freed, the ownership of the children
@@ -246,12 +245,11 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 			ei = NULL;
 			break;
 		}
-
-		dentry = ei->dentry;
+		// Walk upwards until you find the events inode
 	} while (!ei->is_events);
 	mutex_unlock(&eventfs_mutex);
 
-	update_top_events_attr(ei, dentry);
+	update_top_events_attr(ei, dentry->d_sb);
 
 	return ei;
 }
-- 
GitLab


From db2aad036e77100e04a96c67f65ae7d49fb538fb Mon Sep 17 00:00:00 2001
From: Le Ma <le.ma@amd.com>
Date: Thu, 25 Jan 2024 12:00:34 +0800
Subject: [PATCH 3694/4076] drm/amdgpu: move the drm client creation behind drm
 device registration

This patch is to eliminate interrupt warning below:

  "[drm] Fence fallback timer expired on ring sdma0.0".

An early vm pt clearing job is sent to SDMA ahead of interrupt enabled.
And re-locating the drm client creation following after drm_dev_register
looks like a more proper flow.

v2: wrap the drm client creation

Fixes: 1819200166ce ("drm/amdkfd: Export DMABufs from KFD using GEM handles")
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 32 ++++++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    |  4 +++
 3 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 77e2636602887..41db030ddc4ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -141,11 +141,31 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
 static const struct drm_client_funcs kfd_client_funcs = {
 	.unregister	= drm_client_release,
 };
+
+int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev)
+{
+	int ret;
+
+	if (!adev->kfd.init_complete)
+		return 0;
+
+	ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd",
+			      &kfd_client_funcs);
+	if (ret) {
+		dev_err(adev->dev, "Failed to init DRM client: %d\n",
+			ret);
+		return ret;
+	}
+
+	drm_client_register(&adev->kfd.client);
+
+	return 0;
+}
+
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
 	int i;
 	int last_valid_bit;
-	int ret;
 
 	amdgpu_amdkfd_gpuvm_init_mem_limits();
 
@@ -164,12 +184,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.enable_mes = adev->enable_mes,
 		};
 
-		ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", &kfd_client_funcs);
-		if (ret) {
-			dev_err(adev->dev, "Failed to init DRM client: %d\n", ret);
-			return;
-		}
-
 		/* this is going to have a few of the MSBs set that we need to
 		 * clear
 		 */
@@ -208,10 +222,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 
 		adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev,
 							&gpu_resources);
-		if (adev->kfd.init_complete)
-			drm_client_register(&adev->kfd.client);
-		else
-			drm_client_release(&adev->kfd.client);
 
 		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index f262b9d89541a..937d0f0b21dfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -182,6 +182,8 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
 struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
 				struct mm_struct *mm,
 				struct svm_range_bo *svm_bo);
+
+int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev);
 #if defined(CONFIG_DEBUG_FS)
 int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index cc69005f5b46e..971acf01bea60 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2255,6 +2255,10 @@ retry_init:
 	if (ret)
 		goto err_pci;
 
+	ret = amdgpu_amdkfd_drm_client_create(adev);
+	if (ret)
+		goto err_pci;
+
 	/*
 	 * 1. don't init fbdev on hw without DCE
 	 * 2. don't init fbdev if there are no connectors
-- 
GitLab


From d9807d60c145836043ffa602328ea1d66dc458b1 Mon Sep 17 00:00:00 2001
From: Vincent Chen <vincent.chen@sifive.com>
Date: Wed, 17 Jan 2024 22:03:33 +0800
Subject: [PATCH 3695/4076] riscv: mm: execute local TLB flush after populating
 vmemmap

The spare_init() calls memmap_populate() many times to create VA to PA
mapping for the VMEMMAP area, where all "struct page" are located once
CONFIG_SPARSEMEM_VMEMMAP is defined. These "struct page" are later
initialized in the zone_sizes_init() function. However, during this
process, no sfence.vma instruction is executed for this VMEMMAP area.
This omission may cause the hart to fail to perform page table walk
because some data related to the address translation is invisible to the
hart. To solve this issue, the local_flush_tlb_kernel_range() is called
right after the sparse_init() to execute a sfence.vma instruction for this
VMEMMAP area, ensuring that all data related to the address translation
is visible to the hart.

Fixes: d95f1a542c3d ("RISC-V: Implement sparsemem")
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240117140333.2479667-1-vincent.chen@sifive.com
Fixes: 7a92fc8b4d20 ("mm: Introduce flush_cache_vmap_early()")
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/tlbflush.h | 1 +
 arch/riscv/mm/init.c              | 4 ++++
 arch/riscv/mm/tlbflush.c          | 3 ++-
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 928f096dca21b..4112cc8d1d69f 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -75,6 +75,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 
 #define flush_tlb_mm(mm) flush_tlb_all()
 #define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#define local_flush_tlb_kernel_range(start, end) flush_tlb_all()
 #endif /* !CONFIG_SMP || !CONFIG_MMU */
 
 #endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 32cad6a65ccd2..fa34cf55037bd 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1385,6 +1385,10 @@ void __init misc_mem_init(void)
 	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
 	arch_numa_init();
 	sparse_init();
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	/* The entire VMEMMAP region has been populated. Flush TLB for this region */
+	local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END);
+#endif
 	zone_sizes_init();
 	arch_reserve_crashkernel();
 	memblock_dump_all();
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 8d12b26f5ac37..dffb0e5bd9425 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -66,9 +66,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
+/* Flush a range of kernel pages without broadcasting */
 void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
 }
 
 static void __ipi_flush_tlb_all(void *info)
-- 
GitLab


From 9e05d9b06757732477cca428e87f3d72163d01cf Mon Sep 17 00:00:00 2001
From: Tengfei Yu <moehanabichan@gmail.com>
Date: Thu, 25 Jan 2024 13:08:23 +0800
Subject: [PATCH 3696/4076] KVM: x86: Check irqchip mode before create PIT

As the kvm api(https://docs.kernel.org/virt/kvm/api.html) reads,
KVM_CREATE_PIT2 call is only valid after enabling in-kernel irqchip
support via KVM_CREATE_IRQCHIP.

Without this check, I can create PIT first and enable irqchip-split
then, which may cause the PIT invalid because of lacking of in-kernel
PIC to inject the interrupt.

Signed-off-by: Tengfei Yu <moehanabichan@gmail.com>
Message-Id: <20240125050823.4893-1-moehanabichan@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 363b1c0802057..9a89471a613cd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7016,6 +7016,9 @@ set_identity_unlock:
 		r = -EEXIST;
 		if (kvm->arch.vpit)
 			goto create_pit_unlock;
+		r = -ENOENT;
+		if (!pic_in_kernel(kvm))
+			goto create_pit_unlock;
 		r = -ENOMEM;
 		kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags);
 		if (kvm->arch.vpit)
-- 
GitLab


From d52734d00b8e86604a66b4cdfa9e8bb541daca2d Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
Date: Wed, 24 Jan 2024 21:18:21 +0100
Subject: [PATCH 3697/4076] KVM: x86: Give a hint when Win2016 might fail to
 boot due to XSAVES erratum

Since commit b0563468eeac ("x86/CPU/AMD: Disable XSAVES on AMD family 0x17")
kernel unconditionally clears the XSAVES CPU feature bit on Zen1/2 CPUs.

Because KVM CPU caps are initialized from the kernel boot CPU features this
makes the XSAVES feature also unavailable for KVM guests in this case.
At the same time the XSAVEC feature is left enabled.

Unfortunately, having XSAVEC but no XSAVES in CPUID breaks Hyper-V enabled
Windows Server 2016 VMs that have more than one vCPU.

Let's at least give users hint in the kernel log what could be wrong since
these VMs currently simply hang at boot with a black screen - giving no
clue what suddenly broke them and how to make them work again.

Trigger the kernel message hint based on the particular guest ID written to
the Guest OS Identity Hyper-V MSR implemented by KVM.

Defer this check to when the L1 Hyper-V hypervisor enables SVM in EFER
since we want to limit this message to Hyper-V enabled Windows guests only
(Windows session running nested as L2) but the actual Guest OS Identity MSR
write is done by L1 and happens before it enables SVM.

Fixes: b0563468eeac ("x86/CPU/AMD: Disable XSAVES on AMD family 0x17")
Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Message-Id: <b83ab45c5e239e5d148b0ae7750133a67ac9575c.1706127425.git.maciej.szmigiero@oracle.com>
[Move some checks before mutex_lock(), rename function. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/hyperv.c           | 50 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/hyperv.h           |  3 ++
 arch/x86/kvm/x86.c              |  4 +++
 4 files changed, 59 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b5b2d0fde5796..d271ba20a0b21 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1145,6 +1145,8 @@ struct kvm_hv {
 	unsigned int synic_auto_eoi_used;
 
 	struct kvm_hv_syndbg hv_syndbg;
+
+	bool xsaves_xsavec_checked;
 };
 #endif
 
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4943f6b2bbee4..8a47f8541eab7 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1322,6 +1322,56 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr)
 	return false;
 }
 
+#define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839
+#define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */
+
+/*
+ * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC
+ * configuration.
+ * Such configuration can result from, for example, AMD Erratum 1386 workaround.
+ *
+ * Print a notice so users aren't left wondering what's suddenly gone wrong.
+ */
+static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = to_kvm_hv(kvm);
+
+	/* Check again under the hv_lock.  */
+	if (hv->xsaves_xsavec_checked)
+		return;
+
+	if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) !=
+	    KVM_HV_WIN2016_GUEST_ID)
+		return;
+
+	hv->xsaves_xsavec_checked = true;
+
+	/* UP configurations aren't affected */
+	if (atomic_read(&kvm->online_vcpus) < 2)
+		return;
+
+	if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) ||
+	    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC))
+		return;
+
+	pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. "
+			      "If it fails to boot try disabling XSAVEC in the VM config.\n");
+}
+
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+	struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+	if (!vcpu->arch.hyperv_enabled ||
+	    hv->xsaves_xsavec_checked)
+		return;
+
+	mutex_lock(&hv->hv_lock);
+	__kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+	mutex_unlock(&hv->hv_lock);
+}
+
 static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 			     bool host)
 {
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 1dc0b6604526a..923e64903da9a 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -182,6 +182,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock);
 void kvm_hv_request_tsc_page_update(struct kvm *kvm);
 
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu);
+
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
 int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
@@ -267,6 +269,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
 static inline void kvm_hv_setup_tsc_page(struct kvm *kvm,
 					 struct pvclock_vcpu_time_info *hv_clock) {}
 static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {}
+static inline void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) {}
 static inline void kvm_hv_init_vm(struct kvm *kvm) {}
 static inline void kvm_hv_destroy_vm(struct kvm *kvm) {}
 static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a89471a613cd..bf10a9073a092 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1782,6 +1782,10 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS)
 		kvm_mmu_reset_context(vcpu);
 
+	if (!static_cpu_has(X86_FEATURE_XSAVES) &&
+	    (efer & EFER_SVME))
+		kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+
 	return 0;
 }
 
-- 
GitLab


From a9ef277488cfc1b7da88235dc11c338a14f34835 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 24 Jan 2024 15:03:17 +0200
Subject: [PATCH 3698/4076] x86/kvm: Fix SEV check in sev_map_percpu_data()

The function sev_map_percpu_data() checks if it is running on an SEV
platform by checking the CC_ATTR_GUEST_MEM_ENCRYPT attribute. However,
this attribute is also defined for TDX.

To avoid false positives, add a cc_vendor check.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Fixes: 4d96f9109109 ("x86/sev: Replace occurrences of sev_active() with cc_platform_has()")
Suggested-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: David Rientjes <rientjes@google.com>
Message-Id: <20240124130317.495519-1-kirill.shutemov@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kernel/kvm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index dfe9945b9bece..428ee74002e1e 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -434,7 +434,8 @@ static void __init sev_map_percpu_data(void)
 {
 	int cpu;
 
-	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+	if (cc_vendor != CC_VENDOR_AMD ||
+	    !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
 		return;
 
 	for_each_possible_cpu(cpu) {
-- 
GitLab


From fb366fc7541a1de521ab3df58471746aa793b833 Mon Sep 17 00:00:00 2001
From: Ryan Schaefer <ryanschf@amazon.com>
Date: Sun, 21 Jan 2024 21:51:44 +0000
Subject: [PATCH 3699/4076] netfilter: conntrack: correct window scaling with
 retransmitted SYN

commit c7aab4f17021 ("netfilter: nf_conntrack_tcp: re-init for syn packets
only") introduces a bug where SYNs in ORIGINAL direction on reused 5-tuple
result in incorrect window scale negotiation. This commit merged the SYN
re-initialization and simultaneous open or SYN retransmits cases. Merging
this block added the logic in tcp_init_sender() that performed window scale
negotiation to the retransmitted syn case. Previously. this would only
result in updating the sender's scale and flags. After the merge the
additional logic results in improperly clearing the scale in ORIGINAL
direction before any packets in the REPLY direction are received. This
results in packets incorrectly being marked invalid for being
out-of-window.

This can be reproduced with the following trace:

Packet Sequence:
> Flags [S], seq 1687765604, win 62727, options [.. wscale 7], length 0
> Flags [S], seq 1944817196, win 62727, options [.. wscale 7], length 0

In order to fix the issue, only evaluate window negotiation for packets
in the REPLY direction. This was tested with simultaneous open, fast
open, and the above reproduction.

Fixes: c7aab4f17021 ("netfilter: nf_conntrack_tcp: re-init for syn packets only")
Signed-off-by: Ryan Schaefer <ryanschf@amazon.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_proto_tcp.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index e573be5afde7a..ae493599a3ef0 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -457,7 +457,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
 			    const struct sk_buff *skb,
 			    unsigned int dataoff,
 			    const struct tcphdr *tcph,
-			    u32 end, u32 win)
+			    u32 end, u32 win,
+			    enum ip_conntrack_dir dir)
 {
 	/* SYN-ACK in reply to a SYN
 	 * or SYN from reply direction in simultaneous open.
@@ -471,7 +472,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
 	 * Both sides must send the Window Scale option
 	 * to enable window scaling in either direction.
 	 */
-	if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
+	if (dir == IP_CT_DIR_REPLY &&
+	    !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
 	      receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) {
 		sender->td_scale = 0;
 		receiver->td_scale = 0;
@@ -542,7 +544,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
 		if (tcph->syn) {
 			tcp_init_sender(sender, receiver,
 					skb, dataoff, tcph,
-					end, win);
+					end, win, dir);
 			if (!tcph->ack)
 				/* Simultaneous open */
 				return NFCT_TCP_ACCEPT;
@@ -585,7 +587,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
 		 */
 		tcp_init_sender(sender, receiver,
 				skb, dataoff, tcph,
-				end, win);
+				end, win, dir);
 
 		if (dir == IP_CT_DIR_REPLY && !tcph->ack)
 			return NFCT_TCP_ACCEPT;
-- 
GitLab


From 776d451648443f9884be4a1b4e38e8faf1c621f9 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 23 Jan 2024 23:45:32 +0100
Subject: [PATCH 3700/4076] netfilter: nf_tables: restrict tunnel object to
 NFPROTO_NETDEV

Bail out on using the tunnel dst template from other than netdev family.
Add the infrastructure to check for the family in objects.

Fixes: af308b94a2a4 ("netfilter: nf_tables: add tunnel support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c     | 14 +++++++++-----
 net/netfilter/nft_tunnel.c        |  1 +
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 4e1ea18eb5f05..001226c346215 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1351,6 +1351,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
  *	@type: stateful object numeric type
  *	@owner: module owner
  *	@maxattr: maximum netlink attribute
+ *	@family: address family for AF-specific object types
  *	@policy: netlink attribute policy
  */
 struct nft_object_type {
@@ -1360,6 +1361,7 @@ struct nft_object_type {
 	struct list_head		list;
 	u32				type;
 	unsigned int                    maxattr;
+	u8				family;
 	struct module			*owner;
 	const struct nla_policy		*policy;
 };
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c537104411e7d..fc016befb46ff 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7551,11 +7551,15 @@ nla_put_failure:
 	return -1;
 }
 
-static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
+static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
 	list_for_each_entry(type, &nf_tables_objects, list) {
+		if (type->family != NFPROTO_UNSPEC &&
+		    type->family != family)
+			continue;
+
 		if (objtype == type->type)
 			return type;
 	}
@@ -7563,11 +7567,11 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
 }
 
 static const struct nft_object_type *
-nft_obj_type_get(struct net *net, u32 objtype)
+nft_obj_type_get(struct net *net, u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
-	type = __nft_obj_type_get(objtype);
+	type = __nft_obj_type_get(objtype, family);
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
@@ -7660,7 +7664,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 		if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
-		type = __nft_obj_type_get(objtype);
+		type = __nft_obj_type_get(objtype, family);
 		if (WARN_ON_ONCE(!type))
 			return -ENOENT;
 
@@ -7674,7 +7678,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 	if (!nft_use_inc(&table->use))
 		return -EMFILE;
 
-	type = nft_obj_type_get(net, objtype);
+	type = nft_obj_type_get(net, objtype, family);
 	if (IS_ERR(type)) {
 		err = PTR_ERR(type);
 		goto err_type;
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 9f21953c7433f..f735d79d8be57 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -713,6 +713,7 @@ static const struct nft_object_ops nft_tunnel_obj_ops = {
 
 static struct nft_object_type nft_tunnel_obj_type __read_mostly = {
 	.type		= NFT_OBJECT_TUNNEL,
+	.family		= NFPROTO_NETDEV,
 	.ops		= &nft_tunnel_obj_ops,
 	.maxattr	= NFTA_TUNNEL_KEY_MAX,
 	.policy		= nft_tunnel_key_policy,
-- 
GitLab


From 97830f3c3088638ff90b20dfba2eb4d487bf14d7 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Wed, 31 Jan 2024 21:53:46 +0000
Subject: [PATCH 3701/4076] binder: signal epoll threads of self-work
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In (e)poll mode, threads often depend on I/O events to determine when
data is ready for consumption. Within binder, a thread may initiate a
command via BINDER_WRITE_READ without a read buffer and then make use
of epoll_wait() or similar to consume any responses afterwards.

It is then crucial that epoll threads are signaled via wakeup when they
queue their own work. Otherwise, they risk waiting indefinitely for an
event leaving their work unhandled. What is worse, subsequent commands
won't trigger a wakeup either as the thread has pending work.

Fixes: 457b9a6f09f0 ("Staging: android: add binder driver")
Cc: Arve Hjønnevåg <arve@android.com>
Cc: Martijn Coenen <maco@android.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Steven Moreland <smoreland@google.com>
Cc: stable@vger.kernel.org # v4.19+
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20240131215347.1808751-1-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 8dd23b19e9973..eca24f41556df 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -478,6 +478,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread,
 {
 	WARN_ON(!list_empty(&thread->waiting_thread_node));
 	binder_enqueue_work_ilocked(work, &thread->todo);
+
+	/* (e)poll-based threads require an explicit wakeup signal when
+	 * queuing their own work; they rely on these events to consume
+	 * messages without I/O block. Without it, threads risk waiting
+	 * indefinitely without handling the work.
+	 */
+	if (thread->looper & BINDER_LOOPER_STATE_POLL &&
+	    thread->pid == current->pid && !thread->process_todo)
+		wake_up_interruptible_sync(&thread->wait);
+
 	thread->process_todo = true;
 }
 
-- 
GitLab


From 6e348067ee4bc5905e35faa3a8fafa91c9124bc7 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 25 Jan 2024 17:29:46 -0500
Subject: [PATCH 3702/4076] netfilter: conntrack: check SCTP_CID_SHUTDOWN_ACK
 for vtag setting in sctp_new

The annotation says in sctp_new(): "If it is a shutdown ack OOTB packet, we
expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8)".
However, it does not check SCTP_CID_SHUTDOWN_ACK before setting vtag[REPLY]
in the conntrack entry(ct).

Because of that, if the ct in Router disappears for some reason in [1]
with the packet sequence like below:

   Client > Server: sctp (1) [INIT] [init tag: 3201533963]
   Server > Client: sctp (1) [INIT ACK] [init tag: 972498433]
   Client > Server: sctp (1) [COOKIE ECHO]
   Server > Client: sctp (1) [COOKIE ACK]
   Client > Server: sctp (1) [DATA] (B)(E) [TSN: 3075057809]
   Server > Client: sctp (1) [SACK] [cum ack 3075057809]
   Server > Client: sctp (1) [HB REQ]
   (the ct in Router disappears somehow)  <-------- [1]
   Client > Server: sctp (1) [HB ACK]
   Client > Server: sctp (1) [DATA] (B)(E) [TSN: 3075057810]
   Client > Server: sctp (1) [DATA] (B)(E) [TSN: 3075057810]
   Client > Server: sctp (1) [HB REQ]
   Client > Server: sctp (1) [DATA] (B)(E) [TSN: 3075057810]
   Client > Server: sctp (1) [HB REQ]
   Client > Server: sctp (1) [ABORT]

when processing HB ACK packet in Router it calls sctp_new() to initialize
the new ct with vtag[REPLY] set to HB_ACK packet's vtag.

Later when sending DATA from Client, all the SACKs from Server will get
dropped in Router, as the SACK packet's vtag does not match vtag[REPLY]
in the ct. The worst thing is the vtag in this ct will never get fixed
by the upcoming packets from Server.

This patch fixes it by checking SCTP_CID_SHUTDOWN_ACK before setting
vtag[REPLY] in the ct in sctp_new() as the annotation says. With this
fix, it will leave vtag[REPLY] in ct to 0 in the case above, and the
next HB REQ/ACK from Server is able to fix the vtag as its value is 0
in nf_conntrack_sctp_packet().

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_proto_sctp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index c6bd533983c1f..4cc97f971264e 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -283,7 +283,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 			pr_debug("Setting vtag %x for secondary conntrack\n",
 				 sh->vtag);
 			ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag;
-		} else {
+		} else if (sch->type == SCTP_CID_SHUTDOWN_ACK) {
 		/* If it is a shutdown ack OOTB packet, we expect a return
 		   shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */
 			pr_debug("Setting vtag %x for new conn OOTB\n",
-- 
GitLab


From 97f7cf1cd80eeed3b7c808b7c12463295c751001 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@netfilter.org>
Date: Mon, 29 Jan 2024 10:57:01 +0100
Subject: [PATCH 3703/4076] netfilter: ipset: fix performance regression in
 swap operation

The patch "netfilter: ipset: fix race condition between swap/destroy
and kernel side add/del/test", commit 28628fa9 fixes a race condition.
But the synchronize_rcu() added to the swap function unnecessarily slows
it down: it can safely be moved to destroy and use call_rcu() instead.

Eric Dumazet pointed out that simply calling the destroy functions as
rcu callback does not work: sets with timeout use garbage collectors
which need cancelling at destroy which can wait. Therefore the destroy
functions are split into two: cancelling garbage collectors safely at
executing the command received by netlink and moving the remaining
part only into the rcu callback.

Link: https://lore.kernel.org/lkml/C0829B10-EAA6-4809-874E-E1E9C05A8D84@automattic.com/
Fixes: 28628fa952fe ("netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test")
Reported-by: Ale Crismani <ale.crismani@automattic.com>
Reported-by: David Wang <00107082@163.com>
Tested-by: David Wang <00107082@163.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/ipset/ip_set.h  |  4 +++
 net/netfilter/ipset/ip_set_bitmap_gen.h | 14 ++++++++--
 net/netfilter/ipset/ip_set_core.c       | 37 +++++++++++++++++++------
 net/netfilter/ipset/ip_set_hash_gen.h   | 15 ++++++++--
 net/netfilter/ipset/ip_set_list_set.c   | 13 +++++++--
 5 files changed, 65 insertions(+), 18 deletions(-)

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index e8c350a3ade15..e9f4f845d760a 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -186,6 +186,8 @@ struct ip_set_type_variant {
 	/* Return true if "b" set is the same as "a"
 	 * according to the create set parameters */
 	bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
+	/* Cancel ongoing garbage collectors before destroying the set*/
+	void (*cancel_gc)(struct ip_set *set);
 	/* Region-locking is used */
 	bool region_lock;
 };
@@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type);
 
 /* A generic IP set */
 struct ip_set {
+	/* For call_cru in destroy */
+	struct rcu_head rcu;
 	/* The name of the set */
 	char name[IPSET_MAXNAMELEN];
 	/* Lock protecting the set data */
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 21f7860e8fa1f..cb48a2b9cb9fd 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -30,6 +30,7 @@
 #define mtype_del		IPSET_TOKEN(MTYPE, _del)
 #define mtype_list		IPSET_TOKEN(MTYPE, _list)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
+#define mtype_cancel_gc		IPSET_TOKEN(MTYPE, _cancel_gc)
 #define mtype			MTYPE
 
 #define get_ext(set, map, id)	((map)->extensions + ((set)->dsize * (id)))
@@ -59,9 +60,6 @@ mtype_destroy(struct ip_set *set)
 {
 	struct mtype *map = set->data;
 
-	if (SET_WITH_TIMEOUT(set))
-		del_timer_sync(&map->gc);
-
 	if (set->dsize && set->extensions & IPSET_EXT_DESTROY)
 		mtype_ext_cleanup(set);
 	ip_set_free(map->members);
@@ -290,6 +288,15 @@ mtype_gc(struct timer_list *t)
 	add_timer(&map->gc);
 }
 
+static void
+mtype_cancel_gc(struct ip_set *set)
+{
+	struct mtype *map = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		del_timer_sync(&map->gc);
+}
+
 static const struct ip_set_type_variant mtype = {
 	.kadt	= mtype_kadt,
 	.uadt	= mtype_uadt,
@@ -303,6 +310,7 @@ static const struct ip_set_type_variant mtype = {
 	.head	= mtype_head,
 	.list	= mtype_list,
 	.same_set = mtype_same_set,
+	.cancel_gc = mtype_cancel_gc,
 };
 
 #endif /* __IP_SET_BITMAP_IP_GEN_H */
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 4c133e06be1de..bcaad9c009fe0 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1182,6 +1182,14 @@ ip_set_destroy_set(struct ip_set *set)
 	kfree(set);
 }
 
+static void
+ip_set_destroy_set_rcu(struct rcu_head *head)
+{
+	struct ip_set *set = container_of(head, struct ip_set, rcu);
+
+	ip_set_destroy_set(set);
+}
+
 static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			  const struct nlattr * const attr[])
 {
@@ -1193,8 +1201,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
-	/* Must wait for flush to be really finished in list:set */
-	rcu_barrier();
 
 	/* Commands are serialized and references are
 	 * protected by the ip_set_ref_lock.
@@ -1206,8 +1212,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	 * counter, so if it's already zero, we can proceed
 	 * without holding the lock.
 	 */
-	read_lock_bh(&ip_set_ref_lock);
 	if (!attr[IPSET_ATTR_SETNAME]) {
+		/* Must wait for flush to be really finished in list:set */
+		rcu_barrier();
+		read_lock_bh(&ip_set_ref_lock);
 		for (i = 0; i < inst->ip_set_max; i++) {
 			s = ip_set(inst, i);
 			if (s && (s->ref || s->ref_netlink)) {
@@ -1221,6 +1229,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			s = ip_set(inst, i);
 			if (s) {
 				ip_set(inst, i) = NULL;
+				/* Must cancel garbage collectors */
+				s->variant->cancel_gc(s);
 				ip_set_destroy_set(s);
 			}
 		}
@@ -1228,6 +1238,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 		inst->is_destroyed = false;
 	} else {
 		u32 flags = flag_exist(info->nlh);
+		u16 features = 0;
+
+		read_lock_bh(&ip_set_ref_lock);
 		s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
 				    &i);
 		if (!s) {
@@ -1238,10 +1251,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			ret = -IPSET_ERR_BUSY;
 			goto out;
 		}
+		features = s->type->features;
 		ip_set(inst, i) = NULL;
 		read_unlock_bh(&ip_set_ref_lock);
-
-		ip_set_destroy_set(s);
+		if (features & IPSET_TYPE_NAME) {
+			/* Must wait for flush to be really finished  */
+			rcu_barrier();
+		}
+		/* Must cancel garbage collectors */
+		s->variant->cancel_gc(s);
+		call_rcu(&s->rcu, ip_set_destroy_set_rcu);
 	}
 	return 0;
 out:
@@ -1394,9 +1413,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
-	/* Make sure all readers of the old set pointers are completed. */
-	synchronize_rcu();
-
 	return 0;
 }
 
@@ -2409,8 +2425,11 @@ ip_set_fini(void)
 {
 	nf_unregister_sockopt(&so_set);
 	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-
 	unregister_pernet_subsys(&ip_set_net_ops);
+
+	/* Wait for call_rcu() in destroy */
+	rcu_barrier();
+
 	pr_debug("these are the famous last words\n");
 }
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index cbf80da9a01ca..1136510521a80 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -222,6 +222,7 @@ static const union nf_inet_addr zeromask = {};
 #undef mtype_gc_do
 #undef mtype_gc
 #undef mtype_gc_init
+#undef mtype_cancel_gc
 #undef mtype_variant
 #undef mtype_data_match
 
@@ -266,6 +267,7 @@ static const union nf_inet_addr zeromask = {};
 #define mtype_gc_do		IPSET_TOKEN(MTYPE, _gc_do)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
 #define mtype_gc_init		IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_cancel_gc		IPSET_TOKEN(MTYPE, _cancel_gc)
 #define mtype_variant		IPSET_TOKEN(MTYPE, _variant)
 #define mtype_data_match	IPSET_TOKEN(MTYPE, _data_match)
 
@@ -450,9 +452,6 @@ mtype_destroy(struct ip_set *set)
 	struct htype *h = set->data;
 	struct list_head *l, *lt;
 
-	if (SET_WITH_TIMEOUT(set))
-		cancel_delayed_work_sync(&h->gc.dwork);
-
 	mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
 	list_for_each_safe(l, lt, &h->ad) {
 		list_del(l);
@@ -599,6 +598,15 @@ mtype_gc_init(struct htable_gc *gc)
 	queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ);
 }
 
+static void
+mtype_cancel_gc(struct ip_set *set)
+{
+	struct htype *h = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		cancel_delayed_work_sync(&h->gc.dwork);
+}
+
 static int
 mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	  struct ip_set_ext *mext, u32 flags);
@@ -1441,6 +1449,7 @@ static const struct ip_set_type_variant mtype_variant = {
 	.uref	= mtype_uref,
 	.resize	= mtype_resize,
 	.same_set = mtype_same_set,
+	.cancel_gc = mtype_cancel_gc,
 	.region_lock = true,
 };
 
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index e162636525cfb..6c3f28bc59b32 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set)
 	struct list_set *map = set->data;
 	struct set_elem *e, *n;
 
-	if (SET_WITH_TIMEOUT(set))
-		timer_shutdown_sync(&map->gc);
-
 	list_for_each_entry_safe(e, n, &map->members, list) {
 		list_del(&e->list);
 		ip_set_put_byindex(map->net, e->id);
@@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b)
 	       a->extensions == b->extensions;
 }
 
+static void
+list_set_cancel_gc(struct ip_set *set)
+{
+	struct list_set *map = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		timer_shutdown_sync(&map->gc);
+}
+
 static const struct ip_set_type_variant set_variant = {
 	.kadt	= list_set_kadt,
 	.uadt	= list_set_uadt,
@@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = {
 	.head	= list_set_head,
 	.list	= list_set_list,
 	.same_set = list_set_same_set,
+	.cancel_gc = list_set_cancel_gc,
 };
 
 static void
-- 
GitLab


From 259eb32971e9eb24d1777a28d82730659f50fdcb Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 29 Jan 2024 11:09:43 +0100
Subject: [PATCH 3704/4076] netfilter: nf_log: replace BUG_ON by WARN_ON_ONCE
 when putting logger

Module reference is bumped for each user, this should not ever happen.

But BUG_ON check should use rcu_access_pointer() instead.

If this ever happens, do WARN_ON_ONCE() instead of BUG_ON() and
consolidate pointer check under the rcu read side lock section.

Fixes: fab4085f4e24 ("netfilter: log: nf_log_packet() as real unified interface")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_log.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 8cc52d2bd31be..e16f158388bbe 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -193,11 +193,12 @@ void nf_logger_put(int pf, enum nf_log_type type)
 		return;
 	}
 
-	BUG_ON(loggers[pf][type] == NULL);
-
 	rcu_read_lock();
 	logger = rcu_dereference(loggers[pf][type]);
-	module_put(logger->me);
+	if (!logger)
+		WARN_ON_ONCE(1);
+	else
+		module_put(logger->me);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(nf_logger_put);
-- 
GitLab


From 8059918a1377f2f1fff06af4f5a4ed3d5acd6bc4 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 29 Jan 2024 13:12:33 +0100
Subject: [PATCH 3705/4076] netfilter: nft_ct: sanitize layer 3 and 4 protocol
 number in custom expectations

- Disallow families other than NFPROTO_{IPV4,IPV6,INET}.
- Disallow layer 4 protocol with no ports, since destination port is a
  mandatory attribute for this object.

Fixes: 857b46027d6f ("netfilter: nft_ct: add ct expectations support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_ct.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 86bb9d7797d9e..aac98a3c966e9 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1250,7 +1250,31 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_CT_EXPECT_L3PROTO])
 		priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO]));
 
+	switch (priv->l3num) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+		if (priv->l3num != ctx->family)
+			return -EINVAL;
+
+		fallthrough;
+	case NFPROTO_INET:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]);
+	switch (priv->l4proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
+	case IPPROTO_DCCP:
+	case IPPROTO_SCTP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]);
 	priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]);
 	priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]);
-- 
GitLab


From 961df3085416ffabea192989941c89ffbf2af2d5 Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Mon, 15 Jan 2024 13:37:47 -0500
Subject: [PATCH 3706/4076] drm/amdkfd: Correct partial migration virtual addr

Partial migration to system memory should use migrate.addr, not
prange->start as virtual address to allocate system memory page.

Fixes: a546a2768440 ("drm/amdkfd: Use partial migrations/mapping for GPU/CPU page faults in SVM")
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index f856901055d34..bdc01ca9609a7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -574,7 +574,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start,
 		 prange->last);
 
-	addr = prange->start << PAGE_SHIFT;
+	addr = migrate->start;
 
 	src = (uint64_t *)(scratch + npages);
 	dst = scratch;
-- 
GitLab


From c49bf4fcfc2f5516f76a706b06fcad5886cc25e1 Mon Sep 17 00:00:00 2001
From: Jay Cornwall <jay.cornwall@amd.com>
Date: Fri, 5 Jan 2024 08:49:06 -0600
Subject: [PATCH 3707/4076] drm/amdkfd: Use S_ENDPGM_SAVED in trap handler

This instruction has no functional difference to S_ENDPGM
but allows performance counters to track save events correctly.

Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Laurent Morichetti <laurent.morichetti@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h     | 14 +++++++-------
 .../gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm |  2 +-
 .../gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm  |  2 +-
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index df75863393fcb..d1caaf0e6a7c4 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -674,7 +674,7 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_nv1x_hex[] = {
@@ -1091,7 +1091,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = {
 	0xb9eef807, 0x876dff6d,
 	0x0000ffff, 0x87fe7e7e,
 	0x87ea6a6a, 0xb9faf802,
-	0xbe80226c, 0xbf810000,
+	0xbe80226c, 0xbf9b0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0x00000000,
@@ -1574,7 +1574,7 @@ static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_aldebaran_hex[] = {
@@ -2065,7 +2065,7 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_gfx10_hex[] = {
@@ -2500,7 +2500,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x876dff6d, 0x0000ffff,
 	0x87fe7e7e, 0x87ea6a6a,
 	0xb9faf802, 0xbe80226c,
-	0xbf810000, 0xbf9f0000,
+	0xbf9b0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 };
@@ -2944,7 +2944,7 @@ static const uint32_t cwsr_trap_gfx11_hex[] = {
 	0xb8eef802, 0xbf0d866e,
 	0xbfa20002, 0xb97af802,
 	0xbe80486c, 0xb97af802,
-	0xbe804a6c, 0xbfb00000,
+	0xbe804a6c, 0xbfb10000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0x00000000,
@@ -3436,5 +3436,5 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index e0140df0b0ec8..71b3dc0c73634 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -1104,7 +1104,7 @@ L_RETURN_WITHOUT_PRIV:
 	s_rfe_b64	s_restore_pc_lo						//Return to the main shader program and resume execution
 
 L_END_PGM:
-	s_endpgm
+	s_endpgm_saved
 end
 
 function write_hwreg_to_mem(s, s_rsrc, s_mem_offset)
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index e506411ad28ab..bb26338204f4b 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -921,7 +921,7 @@ L_RESTORE:
 /*			the END						  */
 /**************************************************************************/
 L_END_PGM:
-    s_endpgm
+    s_endpgm_saved
 
 end
 
-- 
GitLab


From 4119734e06a7f30e7e8eb666692a58b85dca0269 Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Fri, 26 Jan 2024 15:14:50 -0500
Subject: [PATCH 3708/4076] drm/amdkfd: Use correct drm device for cgroup
 permission check

On GFX 9.4.3, for a given KFD node, fetch the correct drm device from
XCP manager when checking for cgroup permissions.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 17fbedbf36513..677281c0793e2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1488,10 +1488,15 @@ void kfd_dec_compute_active(struct kfd_node *dev);
 
 /* Cgroup Support */
 /* Check with device cgroup if @kfd device is accessible */
-static inline int kfd_devcgroup_check_permission(struct kfd_node *kfd)
+static inline int kfd_devcgroup_check_permission(struct kfd_node *node)
 {
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
-	struct drm_device *ddev = adev_to_drm(kfd->adev);
+	struct drm_device *ddev;
+
+	if (node->xcp)
+		ddev = node->xcp->ddev;
+	else
+		ddev = adev_to_drm(node->adev);
 
 	return devcgroup_check_permission(DEVCG_DEV_CHAR, DRM_MAJOR,
 					  ddev->render->index,
-- 
GitLab


From 514312c07f6cd2f1ffe5a90d42b6080868a03a26 Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Tue, 9 Jan 2024 11:31:20 -0500
Subject: [PATCH 3709/4076] Revert "drm/amd/display: initialize all the dpm
 level's stutter latency"

Revert commit 885c71ad791c
("drm/amd/display: initialize all the dpm level's stutter latency")

Because it causes some regression

Reviewed-by: Muhammad Ahmed <ahmed.ahmed@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 64d01a9cd68c8..8b0f930be5ae1 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -341,9 +341,6 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		break;
 	}
 
-	if (dml2->config.bbox_overrides.clks_table.num_states)
-			p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
-
 	/* Override from passed values, if available */
 	for (i = 0; i < p->in_states->num_states; i++) {
 		if (dml2->config.bbox_overrides.sr_exit_latency_us) {
@@ -400,6 +397,7 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 	}
 	/* Copy clocks tables entries, if available */
 	if (dml2->config.bbox_overrides.clks_table.num_states) {
+		p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
 
 		for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels; i++) {
 			p->in_states->state_array[i].dcfclk_mhz = dml2->config.bbox_overrides.clks_table.clk_entries[i].dcfclk_mhz;
-- 
GitLab


From 2ff33c759a4247c84ec0b7815f1f223e155ba82a Mon Sep 17 00:00:00 2001
From: Sohaib Nadeem <sohaib.nadeem@amd.com>
Date: Tue, 16 Jan 2024 11:00:00 -0500
Subject: [PATCH 3710/4076] drm/amd/display: increased min_dcfclk_mhz and
 min_fclk_mhz

[why]
Originally, PMFW said min FCLK is 300Mhz, but min DCFCLK can be increased
to 400Mhz because min FCLK is now 600Mhz so FCLK >= 1.5 * DCFCLK hardware
requirement will still be satisfied. Increasing min DCFCLK addresses
underflow issues (underflow occurs when phantom pipe is turned on for some
Sub-Viewport configs).

[how]
Increasing DCFCLK by raising the min_dcfclk_mhz

Reviewed-by: Chaitanya Dhere <chaitanya.dhere@amd.com>
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Sohaib Nadeem <sohaib.nadeem@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 9f37f717a1f86..b13a6fd7cc832 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -2753,7 +2753,7 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 	struct _vcs_dpi_voltage_scaling_st entry = {0};
 	struct clk_limit_table_entry max_clk_data = {0};
 
-	unsigned int min_dcfclk_mhz = 199, min_fclk_mhz = 299;
+	unsigned int min_dcfclk_mhz = 399, min_fclk_mhz = 599;
 
 	static const unsigned int num_dcfclk_stas = 5;
 	unsigned int dcfclk_sta_targets[DC__VOLTAGE_STATES] = {199, 615, 906, 1324, 1564};
-- 
GitLab


From b5abd7f983e14054593dc91d6df2aa5f8cc67652 Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Tue, 16 Jan 2024 19:54:15 -0500
Subject: [PATCH 3711/4076] drm/amd/display: fix USB-C flag update after enc10
 feature init

[why]
BIOS's integration info table not following the original order
which is phy instance is ext_displaypath's array index.

[how]
Move them to follow the original order.

Reviewed-by: Muhammad Ahmed <ahmed.ahmed@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c | 4 ++--
 drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
index 501388014855c..d761b0df28784 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
@@ -203,12 +203,12 @@ void dcn32_link_encoder_construct(
 	enc10->base.hpd_source = init_data->hpd_source;
 	enc10->base.connector = init_data->connector;
 
-	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
-		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
 
 	enc10->base.features = *enc_features;
+	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.transmitter = init_data->transmitter;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
index da94e5309fbaf..81e349d5835bb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
@@ -184,8 +184,6 @@ void dcn35_link_encoder_construct(
 	enc10->base.hpd_source = init_data->hpd_source;
 	enc10->base.connector = init_data->connector;
 
-	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
-		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
 
@@ -240,6 +238,8 @@ void dcn35_link_encoder_construct(
 	}
 
 	enc10->base.features.flags.bits.HDMI_6GB_EN = 1;
+	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	if (bp_funcs->get_connector_speed_cap_info)
 		result = bp_funcs->get_connector_speed_cap_info(enc10->base.ctx->dc_bios,
-- 
GitLab


From 31c2bf25eaf51c2d45f092284a28e97f43b54c15 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <dmytro.laktyushkin@amd.com>
Date: Wed, 17 Jan 2024 16:46:02 -0500
Subject: [PATCH 3712/4076] drm/amd/display: Fix DPSTREAM CLK on and off
 sequence

[Why]
Secondary DP2 display fails to light up in some instances

[How]
Clock needs to be on when DPSTREAMCLK*_EN =1. This change
moves dtbclk_p enable/disable point to make sure this is
the case

Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <dmytro.laktyushkin@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Daniel Miess <daniel.miess@amd.com>
Signed-off-by: Dmytro Laktyushkin <dmytro.laktyushkin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c |  2 +-
 .../gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c   | 11 +++++------
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 5660f15da291e..2352428bcea3c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1183,9 +1183,9 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 		dto_params.timing = &pipe_ctx->stream->timing;
 		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
 		if (dccg) {
-			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 			dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst);
 			dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst);
+			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 		}
 	} else if (dccg && dccg->funcs->disable_symclk_se) {
 		dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index e931342fcf4cf..4853ecac53f91 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -2790,18 +2790,17 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	}
 
 	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
-		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
-		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
-
-		phyd32clk = get_phyd32clk_src(link);
-		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
-
 		dto_params.otg_inst = tg->inst;
 		dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10;
 		dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx);
 		dto_params.timing = &pipe_ctx->stream->timing;
 		dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
 		dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
+		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
+		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
+
+		phyd32clk = get_phyd32clk_src(link);
+		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
 	} else {
 		if (dccg->funcs->enable_symclk_se)
 			dccg->funcs->enable_symclk_se(dccg, stream_enc->stream_enc_inst,
-- 
GitLab


From 39079fe8e660851abbafa90cd55cbf029210661f Mon Sep 17 00:00:00 2001
From: Wenjing Liu <wenjing.liu@amd.com>
Date: Thu, 18 Jan 2024 15:14:15 -0500
Subject: [PATCH 3713/4076] drm/amd/display: fix incorrect mpc_combine array
 size

[why]
MAX_SURFACES is per stream, while MAX_PLANES is per asic. The
mpc_combine is an array that records all the planes per asic. Therefore
MAX_PLANES should be used as the array size. Using MAX_SURFACES causes
array overflow when there are more than 3 planes.

[how]
Use the MAX_PLANES for the mpc_combine array size.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Reviewed-by: Nevenko Stupar <nevenko.stupar@amd.com>
Reviewed-by: Chaitanya Dhere <chaitanya.dhere@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index b13a6fd7cc832..dd781a20692ee 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1112,7 +1112,7 @@ struct pipe_slice_table {
 		struct pipe_ctx *pri_pipe;
 		struct dc_plane_state *plane;
 		int slice_count;
-	} mpc_combines[MAX_SURFACES];
+	} mpc_combines[MAX_PLANES];
 	int mpc_combine_count;
 };
 
-- 
GitLab


From 191cb4ed33a61c90feed8bda0f0df3a419604fc8 Mon Sep 17 00:00:00 2001
From: Nicholas Susanto <nicholas.susanto@amd.com>
Date: Thu, 18 Jan 2024 13:34:40 -0500
Subject: [PATCH 3714/4076] drm/amd/display: Underflow workaround by increasing
 SR exit latency

[Why]
On 14us for exit latency time causes underflow for 8K monitor with HDR on.
Increasing the latency to 28us fixes the underflow.

[How]
Increase the latency to 28us. This workaround should be sufficient
before we figure out why SR exit so long.

Reviewed-by: Chaitanya Dhere <chaitanya.dhere@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Nicholas Susanto <nicholas.susanto@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c  | 32 +++++++++----------
 .../drm/amd/display/dc/dml/dcn35/dcn35_fpu.c  |  4 +--
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 9c660d1facc76..14cec1c7b718c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -437,32 +437,32 @@ static struct wm_table ddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 	}
@@ -474,32 +474,32 @@ static struct wm_table lpddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 475c4ec43c013..7ea2bd5374d51 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -164,8 +164,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 		},
 	},
 	.num_states = 5,
-	.sr_exit_time_us = 14.0,
-	.sr_enter_plus_exit_time_us = 16.0,
+	.sr_exit_time_us = 28.0,
+	.sr_enter_plus_exit_time_us = 30.0,
 	.sr_exit_z8_time_us = 210.0,
 	.sr_enter_plus_exit_z8_time_us = 320.0,
 	.fclk_change_latency_us = 24.0,
-- 
GitLab


From faf51b201bc42adf500945732abb6220c707d6f3 Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <jerry.zuo@amd.com>
Date: Thu, 11 Jan 2024 14:46:01 -0500
Subject: [PATCH 3715/4076] drm/amd/display: Fix dcn35 8k30
 Underflow/Corruption Issue

[why]
odm calculation is missing for pipe split policy determination
and cause Underflow/Corruption issue.

[how]
Add the odm calculation.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Fangzhi Zuo <jerry.zuo@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/dml2/dml2_translation_helper.c | 29 +++++++------------
 .../gpu/drm/amd/display/dc/inc/core_types.h   |  2 ++
 2 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 8b0f930be5ae1..23a608274096f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -791,35 +791,28 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 	}
 }
 
-/*TODO no support for mpc combine, need rework - should calculate scaling params based on plane+stream*/
-static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, const struct dc_state *context)
+static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context)
 {
 	int i;
-	struct scaler_data data = { 0 };
+	struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
+
+	memset(temp_pipe, 0, sizeof(struct pipe_ctx));
 
 	for (i = 0; i < MAX_PIPES; i++)	{
 		const struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (pipe->plane_state == in && !pipe->prev_odm_pipe) {
-			const struct pipe_ctx *next_pipe = pipe->next_odm_pipe;
-
-			data = context->res_ctx.pipe_ctx[i].plane_res.scl_data;
-			while (next_pipe) {
-				data.h_active += next_pipe->plane_res.scl_data.h_active;
-				data.recout.width += next_pipe->plane_res.scl_data.recout.width;
-				if (in->rotation == ROTATION_ANGLE_0 || in->rotation == ROTATION_ANGLE_180) {
-					data.viewport.width += next_pipe->plane_res.scl_data.viewport.width;
-				} else {
-					data.viewport.height += next_pipe->plane_res.scl_data.viewport.height;
-				}
-				next_pipe = next_pipe->next_odm_pipe;
-			}
+			temp_pipe->stream = pipe->stream;
+			temp_pipe->plane_state = pipe->plane_state;
+			temp_pipe->plane_res.scl_data.taps = pipe->plane_res.scl_data.taps;
+
+			resource_build_scaling_params(temp_pipe);
 			break;
 		}
 	}
 
 	ASSERT(i < MAX_PIPES);
-	return data;
+	return temp_pipe->plane_res.scl_data;
 }
 
 static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_stream_state *in)
@@ -864,7 +857,7 @@ static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned
 	out->ScalerEnabled[location] = false;
 }
 
-static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, const struct dc_state *context)
+static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, struct dc_state *context)
 {
 	const struct scaler_data scaler_data = get_scaler_data_for_plane(in, context);
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index f74ae0d41d3c4..3a6bf77a68732 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -469,6 +469,8 @@ struct resource_context {
 	unsigned int hpo_dp_link_enc_to_link_idx[MAX_HPO_DP2_LINK_ENCODERS];
 	int hpo_dp_link_enc_ref_cnts[MAX_HPO_DP2_LINK_ENCODERS];
 	bool is_mpc_3dlut_acquired[MAX_PIPES];
+	/* solely used for build scalar data in dml2 */
+	struct pipe_ctx temp_pipe;
 };
 
 struct dce_bw_output {
-- 
GitLab


From bb34bc2cd3ee284d7992df24a3f7d24f61a59268 Mon Sep 17 00:00:00 2001
From: Ma Jun <Jun.Ma2@amd.com>
Date: Fri, 5 Jan 2024 14:05:25 +0800
Subject: [PATCH 3716/4076] drm/amdgpu: Fix the warning info in mode1 reset

Fix the warning info below during mode1 reset.
[  +0.000004] Call Trace:
[  +0.000004]  <TASK>
[  +0.000006]  ? show_regs+0x6e/0x80
[  +0.000011]  ? __flush_work.isra.0+0x2e8/0x390
[  +0.000005]  ? __warn+0x91/0x150
[  +0.000009]  ? __flush_work.isra.0+0x2e8/0x390
[  +0.000006]  ? report_bug+0x19d/0x1b0
[  +0.000013]  ? handle_bug+0x46/0x80
[  +0.000012]  ? exc_invalid_op+0x1d/0x80
[  +0.000011]  ? asm_exc_invalid_op+0x1f/0x30
[  +0.000014]  ? __flush_work.isra.0+0x2e8/0x390
[  +0.000007]  ? __flush_work.isra.0+0x208/0x390
[  +0.000007]  ? _prb_read_valid+0x216/0x290
[  +0.000008]  __cancel_work_timer+0x11d/0x1a0
[  +0.000007]  ? try_to_grab_pending+0xe8/0x190
[  +0.000012]  cancel_work_sync+0x14/0x20
[  +0.000008]  amddrm_sched_stop+0x3c/0x1d0 [amd_sched]
[  +0.000032]  amdgpu_device_gpu_recover+0x29a/0xe90 [amdgpu]

This warning info was printed after applying the patch
"drm/sched: Convert drm scheduler to use a work queue rather than kthread".
The root cause is that amdgpu driver tries to use the uninitialized
work_struct in the struct drm_gpu_scheduler

v2:
 - Rename the function to amdgpu_ring_sched_ready and move it to
amdgpu_ring.c (Alex)
v3:
- Fix a few more checks based on Vitaly's patch (Alex)
v4:
- squash in fix noticed by Bert in
https://gitlab.freedesktop.org/drm/amd/-/issues/3139

Fixes: 11b3b9f461c5 ("drm/sched: Check scheduler ready before calling timeout handling")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c         |  8 ++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c          | 12 ++++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c            | 12 ++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h            |  2 +-
 5 files changed, 24 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index 899e31e3a5e81..3a3f3ce09f00d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -290,7 +290,7 @@ static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool sus
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 
-		if (!(ring && drm_sched_wqueue_ready(&ring->sched)))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		/* stop secheduler and drain ring. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index e485dd3357c63..1afbb2e932c6b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1678,7 +1678,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 		drm_sched_wqueue_stop(&ring->sched);
 	}
@@ -1694,7 +1694,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 		drm_sched_wqueue_start(&ring->sched);
 	}
@@ -1916,8 +1916,8 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
 
 	ring = adev->rings[val];
 
-	if (!ring || !ring->funcs->preempt_ib ||
-	    !drm_sched_wqueue_ready(&ring->sched))
+	if (!amdgpu_ring_sched_ready(ring) ||
+	    !ring->funcs->preempt_ib)
 		return -EINVAL;
 
 	/* the last preemption failed */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 31b28e6f35b26..fdde7488d0ed9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5021,7 +5021,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		spin_lock(&ring->sched.job_list_lock);
@@ -5160,7 +5160,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		/* Clear job fence from fence drv to avoid force_completion
@@ -5627,7 +5627,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_stop(&ring->sched, job ? &job->base : NULL);
@@ -5696,7 +5696,7 @@ skip_hw_reset:
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_start(&ring->sched, true);
@@ -6051,7 +6051,7 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_stop(&ring->sched, NULL);
@@ -6179,7 +6179,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		drm_sched_start(&ring->sched, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 45424ebf96814..5505d646f43aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -635,6 +635,7 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
 			      ring->name);
 
 	ring->sched.ready = !r;
+
 	return r;
 }
 
@@ -717,3 +718,14 @@ void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring)
 	if (ring->is_sw_ring)
 		amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_DE);
 }
+
+bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring)
+{
+	if (!ring)
+		return false;
+
+	if (ring->no_scheduler || !drm_sched_wqueue_ready(&ring->sched))
+		return false;
+
+	return true;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index bbb53720a0181..fe1a61eb6e4c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -450,5 +450,5 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 int amdgpu_ib_pool_init(struct amdgpu_device *adev);
 void amdgpu_ib_pool_fini(struct amdgpu_device *adev);
 int amdgpu_ib_ring_tests(struct amdgpu_device *adev);
-
+bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring);
 #endif
-- 
GitLab


From 8ef85a0ce24a6d9322dfa2a67477e473c3619b4f Mon Sep 17 00:00:00 2001
From: David McFarland <corngood@gmail.com>
Date: Mon, 29 Jan 2024 18:18:22 -0400
Subject: [PATCH 3717/4076] drm/amd: Don't init MEC2 firmware when it fails to
 load

The same calls are made directly above, but conditional on the firmware
loading and validating successfully.

Cc: stable@vger.kernel.org
Fixes: 9931b67690cf ("drm/amd: Load GFX10 microcode during early_init")
Signed-off-by: David McFarland <corngood@gmail.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ecb622b7f9709..dcdecb18b2306 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4027,8 +4027,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		err = 0;
 		adev->gfx.mec2_fw = NULL;
 	}
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2);
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT);
 
 	gfx_v10_0_check_fw_write_wait(adev);
 out:
-- 
GitLab


From 492a1e67ee59312b27c85c275298080fde392190 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Tue, 30 Jan 2024 14:06:43 +0530
Subject: [PATCH 3718/4076] drm/amd/display: Add NULL check for kzalloc in
 'amdgpu_dm_atomic_commit_tail()'

Add a NULL check for the kzalloc call that allocates memory for
dummy_updates in the amdgpu_dm_atomic_commit_tail function. Previously,
if kzalloc failed to allocate memory and returned NULL, the code would
attempt to use the NULL pointer.

The fix is to check if kzalloc returns NULL, and if so, log an error
message and skip the rest of the current loop iteration with the
continue statement.  This prevents the code from attempting to use the
NULL pointer.

Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Cc: Alex Hung <alex.hung@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reported-by: Julia Lawall <julia.lawall@inria.fr>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/r/202401300629.ICnCt983-lkp@intel.com/
Fixes: 135fd1b35690 ("drm/amd/display: Reduce stack size")
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 6cda5b5363626..d292f290cd6eb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9187,6 +9187,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		 * To fix this, DC should permit updating only stream properties.
 		 */
 		dummy_updates = kzalloc(sizeof(struct dc_surface_update) * MAX_SURFACES, GFP_ATOMIC);
+		if (!dummy_updates) {
+			DRM_ERROR("Failed to allocate memory for dummy_updates.\n");
+			continue;
+		}
 		for (j = 0; j < status->plane_count; j++)
 			dummy_updates[j].surface = status->plane_states[0];
 
-- 
GitLab


From 97cba232549b9fe7e491fb60a69cf93075015f29 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Mon, 29 Jan 2024 21:17:09 +0530
Subject: [PATCH 3719/4076] drm/amd/display: Fix buffer overflow in
 'get_host_router_total_dp_tunnel_bw()'

The error message buffer overflow 'dc->links' 12 <= 12 suggests that the
code is trying to access an element of the dc->links array that is
beyond its bounds. In C, arrays are zero-indexed, so an array with 12
elements has valid indices from 0 to 11. Trying to access dc->links[12]
would be an attempt to access the 13th element of a 12-element array,
which is a buffer overflow.

To fix this, ensure that the loop does not go beyond the last valid
index when accessing dc->links[i + 1] by subtracting 1 from the loop
condition.

This would ensure that i + 1 is always a valid index in the array.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_dp_dpia_bw.c:208 get_host_router_total_dp_tunnel_bw() error: buffer overflow 'dc->links' 12 <= 12

Fixes: 59f1622a5f05 ("drm/amd/display: Add dpia display mode validation logic")
Cc: PeiChen Huang <peichen.huang@amd.com>
Cc: Aric Cyr <aric.cyr@amd.com>
Cc: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Meenakshikumar Somasundaram <meenakshikumar.somasundaram@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index dd0d2b206462c..5491b707cec88 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -196,7 +196,7 @@ static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_in
 	struct dc_link *link_dpia_primary, *link_dpia_secondary;
 	int total_bw = 0;
 
-	for (uint8_t i = 0; i < MAX_PIPES * 2; ++i) {
+	for (uint8_t i = 0; i < (MAX_PIPES * 2) - 1; ++i) {
 
 		if (!dc->links[i] || dc->links[i]->ep_type != DISPLAY_ENDPOINT_USB4_DPIA)
 			continue;
-- 
GitLab


From 16da399091dca3d1e48109086403587af37cc196 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Tue, 30 Jan 2024 12:10:38 +0530
Subject: [PATCH 3720/4076] drm/amdgpu: Fix missing error code in
 'gmc_v6/7/8/9_0_hw_init()'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Return 0 for success scenairos in 'gmc_v6/7/8/9_0_hw_init()'

Fixes the below:
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c:920 gmc_v6_0_hw_init() warn: missing error code? 'r'
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c:1104 gmc_v7_0_hw_init() warn: missing error code? 'r'
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c:1224 gmc_v8_0_hw_init() warn: missing error code? 'r'
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c:2347 gmc_v9_0_hw_init() warn: missing error code? 'r'

Fixes: fac4ebd79fed ("drm/amdgpu: Fix with right return code '-EIO' in 'amdgpu_gmc_vram_checking()'")
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 4 ++--
 drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 4 ++--
 drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 4 ++--
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 4 ++--
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 42e103d7077d5..59d9215e55562 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -915,8 +915,8 @@ static int gmc_v6_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v6_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index efc16e580f1e2..45a2f8e031a2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1099,8 +1099,8 @@ static int gmc_v7_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v7_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index ff4ae73d27ecd..4422b27a3cc2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1219,8 +1219,8 @@ static int gmc_v8_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v8_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 17b7a25121b00..40a00ea0009f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -2341,8 +2341,8 @@ static int gmc_v9_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 /**
-- 
GitLab


From 9c29282ecbeeb1b43fced3055c6a5bb244b9390b Mon Sep 17 00:00:00 2001
From: Lang Yu <Lang.Yu@amd.com>
Date: Thu, 11 Jan 2024 12:27:07 +0800
Subject: [PATCH 3721/4076] drm/amdkfd: reserve the BO before validating it

Fix a warning.

v2: Avoid unmapping attachment repeatedly when ERESTARTSYS.

v3: Lock the BO before accessing ttm->sg to avoid race conditions.(Felix)

[   41.708711] WARNING: CPU: 0 PID: 1463 at drivers/gpu/drm/ttm/ttm_bo.c:846 ttm_bo_validate+0x146/0x1b0 [ttm]
[   41.708989] Call Trace:
[   41.708992]  <TASK>
[   41.708996]  ? show_regs+0x6c/0x80
[   41.709000]  ? ttm_bo_validate+0x146/0x1b0 [ttm]
[   41.709008]  ? __warn+0x93/0x190
[   41.709014]  ? ttm_bo_validate+0x146/0x1b0 [ttm]
[   41.709024]  ? report_bug+0x1f9/0x210
[   41.709035]  ? handle_bug+0x46/0x80
[   41.709041]  ? exc_invalid_op+0x1d/0x80
[   41.709048]  ? asm_exc_invalid_op+0x1f/0x30
[   41.709057]  ? amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x2c/0x80 [amdgpu]
[   41.709185]  ? ttm_bo_validate+0x146/0x1b0 [ttm]
[   41.709197]  ? amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x2c/0x80 [amdgpu]
[   41.709337]  ? srso_alias_return_thunk+0x5/0x7f
[   41.709346]  kfd_mem_dmaunmap_attachment+0x9e/0x1e0 [amdgpu]
[   41.709467]  amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x56/0x80 [amdgpu]
[   41.709586]  kfd_ioctl_unmap_memory_from_gpu+0x1b7/0x300 [amdgpu]
[   41.709710]  kfd_ioctl+0x1ec/0x650 [amdgpu]
[   41.709822]  ? __pfx_kfd_ioctl_unmap_memory_from_gpu+0x10/0x10 [amdgpu]
[   41.709945]  ? srso_alias_return_thunk+0x5/0x7f
[   41.709949]  ? tomoyo_file_ioctl+0x20/0x30
[   41.709959]  __x64_sys_ioctl+0x9c/0xd0
[   41.709967]  do_syscall_64+0x3f/0x90
[   41.709973]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Fixes: 101b8104307e ("drm/amdkfd: Move dma unmapping after TLB flush")
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h    |  2 +-
 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  | 20 ++++++++++++++++---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c      |  4 +++-
 3 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 937d0f0b21dfb..27c61c535e297 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -303,7 +303,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev,
 					  struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv);
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
 		struct amdgpu_device *adev, struct kgd_mem *mem, bool intr);
 int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index f183d7faeeece..231fd927dcfbe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2085,21 +2085,35 @@ out:
 	return ret;
 }
 
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
 {
 	struct kfd_mem_attachment *entry;
 	struct amdgpu_vm *vm;
+	int ret;
 
 	vm = drm_priv_to_vm(drm_priv);
 
 	mutex_lock(&mem->lock);
 
+	ret = amdgpu_bo_reserve(mem->bo, true);
+	if (ret)
+		goto out;
+
 	list_for_each_entry(entry, &mem->attachments, list) {
-		if (entry->bo_va->base.vm == vm)
-			kfd_mem_dmaunmap_attachment(mem, entry);
+		if (entry->bo_va->base.vm != vm)
+			continue;
+		if (entry->bo_va->base.bo->tbo.ttm &&
+		    !entry->bo_va->base.bo->tbo.ttm->sg)
+			continue;
+
+		kfd_mem_dmaunmap_attachment(mem, entry);
 	}
 
+	amdgpu_bo_unreserve(mem->bo);
+out:
 	mutex_unlock(&mem->lock);
+
+	return ret;
 }
 
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index ce4c52ec34d80..80e90fdef291d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1442,7 +1442,9 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 			kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
 
 		/* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
-		amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+		err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+		if (err)
+			goto sync_memory_failed;
 	}
 
 	mutex_unlock(&p->mutex);
-- 
GitLab


From de4a733868df3a1b899fd4b05c32e92474cc8f73 Mon Sep 17 00:00:00 2001
From: Yifan Zhang <yifan1.zhang@amd.com>
Date: Tue, 30 Jan 2024 13:14:39 +0800
Subject: [PATCH 3722/4076] drm/amdgpu: drm/amdgpu: remove golden setting for
 gfx 11.5.0

No need to set GC golden settings in driver from gfx 11.5.0 onwards.

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lang Yu <lang.yu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 22 ----------------------
 1 file changed, 22 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index d9cf9fd03d300..4f3bfdc75b37d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -107,23 +107,6 @@ static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL2, 0xfcffffff, 0x0000000a)
 };
 
-static const struct soc15_reg_golden golden_settings_gc_11_5_0[] = {
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regDB_DEBUG5, 0xffffffff, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL, 0xffffffff, 0xf37fff3f),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL3, 0xfffffffb, 0x00f40188),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x80009007),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regPA_CL_ENHANCE, 0xf1ffffff, 0x00880007),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regPC_CONFIG_CNTL_1, 0xffffffff, 0x00010000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL_AUX, 0xf7f7ffff, 0x01030000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL2, 0x007f0000, 0x00000000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL2, 0xffcfffff, 0x0000200a),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regUTCL1_CTRL_2, 0xffffffff, 0x0000048f)
-};
-
 #define DEFAULT_SH_MEM_CONFIG \
 	((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \
 	 (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
@@ -304,11 +287,6 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_gc_11_0_1,
 						(const u32)ARRAY_SIZE(golden_settings_gc_11_0_1));
 		break;
-	case IP_VERSION(11, 5, 0):
-		soc15_program_register_sequence(adev,
-						golden_settings_gc_11_5_0,
-						(const u32)ARRAY_SIZE(golden_settings_gc_11_5_0));
-		break;
 	default:
 		break;
 	}
-- 
GitLab


From 4f56acdee4c69224afde328bb6402a48b93f8221 Mon Sep 17 00:00:00 2001
From: Yifan Zhang <yifan1.zhang@amd.com>
Date: Tue, 30 Jan 2024 21:01:42 +0800
Subject: [PATCH 3723/4076] drm/amdgpu: remove asymmetrical irq disabling in
 vcn 4.0.5 suspend

There is no irq enabled in vcn 4.0.5 resume, causing wrong amdgpu_irq_src status.
Beside, current set function callbacks are empty with no real effect.

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Acked-by: Saleemkhan Jamadar <saleemkhan.jamadar@amd.com>
Reviewed-by: Veerabadhran Gopalakrishnan <Veerabadhran.Gopalakrishnan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c   | 17 -----------------
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 19 -------------------
 2 files changed, 36 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 169ed400ee7b7..8ab01ae919d2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -2017,22 +2017,6 @@ static int vcn_v4_0_set_powergating_state(void *handle, enum amd_powergating_sta
 	return ret;
 }
 
-/**
- * vcn_v4_0_set_interrupt_state - set VCN block interrupt state
- *
- * @adev: amdgpu_device pointer
- * @source: interrupt sources
- * @type: interrupt types
- * @state: interrupt states
- *
- * Set VCN block interrupt state
- */
-static int vcn_v4_0_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
-      unsigned type, enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 /**
  * vcn_v4_0_set_ras_interrupt_state - set VCN block RAS interrupt state
  *
@@ -2097,7 +2081,6 @@ static int vcn_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_
 }
 
 static const struct amdgpu_irq_src_funcs vcn_v4_0_irq_funcs = {
-	.set = vcn_v4_0_set_interrupt_state,
 	.process = vcn_v4_0_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 2eda30e78f61d..49e4c3c09acab 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -269,8 +269,6 @@ static int vcn_v4_0_5_hw_fini(void *handle)
 				vcn_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 			}
 		}
-
-		amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0);
 	}
 
 	return 0;
@@ -1668,22 +1666,6 @@ static int vcn_v4_0_5_set_powergating_state(void *handle, enum amd_powergating_s
 	return ret;
 }
 
-/**
- * vcn_v4_0_5_set_interrupt_state - set VCN block interrupt state
- *
- * @adev: amdgpu_device pointer
- * @source: interrupt sources
- * @type: interrupt types
- * @state: interrupt states
- *
- * Set VCN block interrupt state
- */
-static int vcn_v4_0_5_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
-		unsigned type, enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 /**
  * vcn_v4_0_5_process_interrupt - process VCN block interrupt
  *
@@ -1726,7 +1708,6 @@ static int vcn_v4_0_5_process_interrupt(struct amdgpu_device *adev, struct amdgp
 }
 
 static const struct amdgpu_irq_src_funcs vcn_v4_0_5_irq_funcs = {
-	.set = vcn_v4_0_5_set_interrupt_state,
 	.process = vcn_v4_0_5_process_interrupt,
 };
 
-- 
GitLab


From 7330256268664ea0a7dd5b07a3fed363093477dd Mon Sep 17 00:00:00 2001
From: Friedrich Vock <friedrich.vock@gmx.de>
Date: Tue, 23 Jan 2024 12:52:03 +0100
Subject: [PATCH 3724/4076] drm/amdgpu: Reset IH OVERFLOW_CLEAR bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allows us to detect subsequent IH ring buffer overflows as well.

Cc: Joshua Ashton <joshua@froggi.es>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Friedrich Vock <friedrich.vock@gmx.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/cik_ih.c     | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/cz_ih.c      | 5 +++++
 drivers/gpu/drm/amd/amdgpu/iceland_ih.c | 5 +++++
 drivers/gpu/drm/amd/amdgpu/ih_v6_0.c    | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/ih_v6_1.c    | 7 +++++++
 drivers/gpu/drm/amd/amdgpu/navi10_ih.c  | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/si_ih.c      | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/tonga_ih.c   | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/vega10_ih.c  | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/vega20_ih.c  | 6 ++++++
 10 files changed, 59 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index 6f7c031dd197a..f24e34dc33d1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -204,6 +204,12 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(mmIH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(mmIH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(mmIH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index b8c47e0cf37ad..c19681492efa7 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -216,6 +216,11 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
 
 out:
 	return (wptr & ih->ptr_mask);
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index aecad530b10a6..2c02ae69883d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -215,6 +215,11 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
 
 out:
 	return (wptr & ih->ptr_mask);
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index d9ed7332d805d..ad4ad39f128f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -418,6 +418,12 @@ static u32 ih_v6_0_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
index 8fb05eae340ad..b8da0fc29378c 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
@@ -418,6 +418,13 @@ static u32 ih_v6_1_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index e64b33115848d..de93614726c9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -442,6 +442,12 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index 9a24f17a57502..cada9f300a7f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -119,6 +119,12 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(IH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(IH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 917707bba7f36..450b6e8315091 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -219,6 +219,12 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index d364c6dd152c3..bf68e18e3824b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -373,6 +373,12 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index ddfc6941f9d55..db66e6cccaf2a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -421,6 +421,12 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
-- 
GitLab


From ee36a3b345c433a846effcdcfba437c2298eeda5 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Mon, 29 Jan 2024 13:58:13 +0000
Subject: [PATCH 3725/4076] cifs: make sure that channel scaling is done only
 once

Following a successful cifs_tree_connect, we have the code
to scale up/down the number of channels in the session.
However, it is not protected by a lock today.

As a result, this code can be executed by several processes
that select the same channel. The core functions handle this
well, as they pick chan_lock. However, we've seen cases where
smb2_reconnect throws some warnings.

To fix that, this change introduces a flags bitmap inside the
cifs_ses structure. A new flag type is used to ensure that
only one process enters this section at any time.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h |  3 +++
 fs/smb/client/smb2pdu.c  | 20 +++++++++++++++++---
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 16befff4cbb47..9093c507042fa 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1032,6 +1032,8 @@ struct cifs_chan {
 	__u8 signkey[SMB3_SIGN_KEY_SIZE];
 };
 
+#define CIFS_SES_FLAG_SCALE_CHANNELS (0x1)
+
 /*
  * Session structure.  One of these for each uid session with a particular host
  */
@@ -1064,6 +1066,7 @@ struct cifs_ses {
 	enum securityEnum sectype; /* what security flavor was specified? */
 	bool sign;		/* is signing required? */
 	bool domainAuto:1;
+	unsigned int flags;
 	__u16 session_flags;
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE];
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 86f6f35b7f32e..6db54c6ef5719 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -399,6 +399,15 @@ skip_sess_setup:
 		goto out;
 	}
 
+	spin_lock(&ses->ses_lock);
+	if (ses->flags & CIFS_SES_FLAG_SCALE_CHANNELS) {
+		spin_unlock(&ses->ses_lock);
+		mutex_unlock(&ses->session_mutex);
+		goto skip_add_channels;
+	}
+	ses->flags |= CIFS_SES_FLAG_SCALE_CHANNELS;
+	spin_unlock(&ses->ses_lock);
+
 	if (!rc &&
 	    (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
 		mutex_unlock(&ses->session_mutex);
@@ -428,17 +437,22 @@ skip_sess_setup:
 		if (ses->chan_max > ses->chan_count &&
 		    ses->iface_count &&
 		    !SERVER_IS_CHAN(server)) {
-			if (ses->chan_count == 1)
+			if (ses->chan_count == 1) {
 				cifs_server_dbg(VFS, "supports multichannel now\n");
+				queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
+						 (SMB_INTERFACE_POLL_INTERVAL * HZ));
+			}
 
 			cifs_try_adding_channels(ses);
-			queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
-					   (SMB_INTERFACE_POLL_INTERVAL * HZ));
 		}
 	} else {
 		mutex_unlock(&ses->session_mutex);
 	}
+
 skip_add_channels:
+	spin_lock(&ses->ses_lock);
+	ses->flags &= ~CIFS_SES_FLAG_SCALE_CHANNELS;
+	spin_unlock(&ses->ses_lock);
 
 	if (smb2_command != SMB2_INTERNAL_CMD)
 		mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
-- 
GitLab


From e028243003ad6e1417cc8ac19af9ded672b9ec59 Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Mon, 29 Jan 2024 11:12:11 -0600
Subject: [PATCH 3726/4076] MAINTAINERS: Drop unreachable reviewer for Qualcomm
 ETHQOS ethernet driver

Bhupesh's email responds indicating they've changed employers and with
no new contact information. Let's drop the line from MAINTAINERS to
avoid getting the same response over and over.

Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Link: https://lore.kernel.org/r/20240129-remove-dwmac-qcom-ethqos-reviewer-v1-1-2645eab61451@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9435ea0f8cda0..6ae30c50e79fc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18085,7 +18085,6 @@ F:	drivers/net/ethernet/qualcomm/emac/
 
 QUALCOMM ETHQOS ETHERNET DRIVER
 M:	Vinod Koul <vkoul@kernel.org>
-R:	Bhupesh Sharma <bhupesh.sharma@linaro.org>
 L:	netdev@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
-- 
GitLab


From 5dee6d6923458e26966717f2a3eae7d09fc10bf6 Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Mon, 29 Jan 2024 17:10:17 +0800
Subject: [PATCH 3727/4076] net: ipv4: fix a memleak in ip_setup_cork

When inetdev_valid_mtu fails, cork->opt should be freed if it is
allocated in ip_setup_cork. Otherwise there could be a memleak.

Fixes: 501a90c94510 ("inet: protect against too small mtu values.")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240129091017.2938835-1-alexious@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_output.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b06f678b03a19..41537d18eecfd 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1287,6 +1287,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	if (unlikely(!rt))
 		return -EFAULT;
 
+	cork->fragsize = ip_sk_use_pmtu(sk) ?
+			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+
+	if (!inetdev_valid_mtu(cork->fragsize))
+		return -ENETUNREACH;
+
 	/*
 	 * setup for corking.
 	 */
@@ -1303,12 +1309,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		cork->addr = ipc->addr;
 	}
 
-	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
-
-	if (!inetdev_valid_mtu(cork->fragsize))
-		return -ENETUNREACH;
-
 	cork->gso_size = ipc->gso_size;
 
 	cork->dst = &rt->dst;
-- 
GitLab


From 585b40e25dc9ff3d2b03d1495150540849009e5b Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Mon, 29 Jan 2024 23:49:48 +0100
Subject: [PATCH 3728/4076] net: dsa: mv88e6xxx: Fix failed probe due to
 unsupported C45 reads

Not all mv88e6xxx device support C45 read/write operations. Those
which do not return -EOPNOTSUPP. However, when phylib scans the bus,
it considers this fatal, and the probe of the MDIO bus fails, which in
term causes the mv88e6xxx probe as a whole to fail.

When there is no device on the bus for a given address, the pull up
resistor on the data line results in the read returning 0xffff. The
phylib core code understands this when scanning for devices on the
bus. C45 allows multiple devices to be supported at one address, so
phylib will perform a few reads at each address, so although thought
not the most efficient solution, it is a way to avoid fatal
errors. Make use of this as a minimal fix for stable to fix the
probing problems.

Follow up patches will rework how C45 operates to make it similar to
C22 which considers -ENODEV as a none-fatal, and swap mv88e6xxx to
using this.

Cc: stable@vger.kernel.org
Fixes: 743a19e38d02 ("net: dsa: mv88e6xxx: Separate C22 and C45 transactions")
Reported-by: Tim Menninger <tmenninger@purestorage.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20240129224948.1531452-1-andrew@lunn.ch
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 383b3c4d6f599..614cabb5c1b03 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3659,7 +3659,7 @@ static int mv88e6xxx_mdio_read_c45(struct mii_bus *bus, int phy, int devad,
 	int err;
 
 	if (!chip->info->ops->phy_read_c45)
-		return -EOPNOTSUPP;
+		return 0xffff;
 
 	mv88e6xxx_reg_lock(chip);
 	err = chip->info->ops->phy_read_c45(chip, bus, phy, devad, reg, &val);
-- 
GitLab


From f9ddefb6c0de771038b041eaad5cc15e61fe283f Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Mon, 29 Jan 2024 07:39:45 +0100
Subject: [PATCH 3729/4076] nvme-auth: open-code single-use macros

No point in having macros just for a single function nvme_auth_submit().
Open-code them into the caller.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/auth.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index 2a12ee878783f..3dce480d932e3 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -48,11 +48,6 @@ struct nvme_dhchap_queue_context {
 
 static struct workqueue_struct *nvme_auth_wq;
 
-#define nvme_auth_flags_from_qid(qid) \
-	(qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED
-#define nvme_auth_queue_from_qid(ctrl, qid) \
-	(qid == 0) ? (ctrl)->fabrics_q : (ctrl)->connect_q
-
 static inline int ctrl_max_dhchaps(struct nvme_ctrl *ctrl)
 {
 	return ctrl->opts->nr_io_queues + ctrl->opts->nr_write_queues +
@@ -63,10 +58,15 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 			    void *data, size_t data_len, bool auth_send)
 {
 	struct nvme_command cmd = {};
-	blk_mq_req_flags_t flags = nvme_auth_flags_from_qid(qid);
-	struct request_queue *q = nvme_auth_queue_from_qid(ctrl, qid);
+	blk_mq_req_flags_t flags = 0;
+	struct request_queue *q = ctrl->fabrics_q;
 	int ret;
 
+	if (qid != 0) {
+		flags |= BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED;
+		q = ctrl->connect_q;
+	}
+
 	cmd.auth_common.opcode = nvme_fabrics_command;
 	cmd.auth_common.secp = NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER;
 	cmd.auth_common.spsp0 = 0x01;
-- 
GitLab


From bd2687f2e5940f6ee14bfae787b3c1f5f0574907 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Mon, 29 Jan 2024 07:39:46 +0100
Subject: [PATCH 3730/4076] nvme: change __nvme_submit_sync_cmd() calling
 conventions

Combine the two arguments 'flags' and 'at_head' from __nvme_submit_sync_cmd()
into a single 'flags' argument and use function-specific values to indicate
what should be set within the function.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/auth.c    |  7 +++----
 drivers/nvme/host/core.c    | 19 ++++++++++++-------
 drivers/nvme/host/fabrics.c | 18 +++++++++++-------
 drivers/nvme/host/nvme.h    | 17 +++++++++++++++--
 4 files changed, 41 insertions(+), 20 deletions(-)

diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index 3dce480d932e3..bf69be8966f44 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -58,12 +58,12 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 			    void *data, size_t data_len, bool auth_send)
 {
 	struct nvme_command cmd = {};
-	blk_mq_req_flags_t flags = 0;
+	nvme_submit_flags_t flags = 0;
 	struct request_queue *q = ctrl->fabrics_q;
 	int ret;
 
 	if (qid != 0) {
-		flags |= BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED;
+		flags |= NVME_SUBMIT_NOWAIT | NVME_SUBMIT_RESERVED;
 		q = ctrl->connect_q;
 	}
 
@@ -80,8 +80,7 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 	}
 
 	ret = __nvme_submit_sync_cmd(q, &cmd, NULL, data, data_len,
-				     qid == 0 ? NVME_QID_ANY : qid,
-				     0, flags);
+				     qid == 0 ? NVME_QID_ANY : qid, flags);
 	if (ret > 0)
 		dev_warn(ctrl->device,
 			"qid %d auth_send failed with status %d\n", qid, ret);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index a42c347d08e87..aed099a457911 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1051,15 +1051,20 @@ EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, NVME_TARGET_PASSTHRU);
  */
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		int qid, int at_head, blk_mq_req_flags_t flags)
+		int qid, nvme_submit_flags_t flags)
 {
 	struct request *req;
 	int ret;
+	blk_mq_req_flags_t blk_flags = 0;
 
+	if (flags & NVME_SUBMIT_NOWAIT)
+		blk_flags |= BLK_MQ_REQ_NOWAIT;
+	if (flags & NVME_SUBMIT_RESERVED)
+		blk_flags |= BLK_MQ_REQ_RESERVED;
 	if (qid == NVME_QID_ANY)
-		req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
+		req = blk_mq_alloc_request(q, nvme_req_op(cmd), blk_flags);
 	else
-		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
+		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), blk_flags,
 						qid - 1);
 
 	if (IS_ERR(req))
@@ -1072,7 +1077,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	ret = nvme_execute_rq(req, at_head);
+	ret = nvme_execute_rq(req, flags & NVME_SUBMIT_AT_HEAD);
 	if (result && ret >= 0)
 		*result = nvme_req(req)->result;
  out:
@@ -1085,7 +1090,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buffer, unsigned bufflen)
 {
 	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 
@@ -1560,7 +1565,7 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
 	c.features.dword11 = cpu_to_le32(dword11);
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res,
-			buffer, buflen, NVME_QID_ANY, 0, 0);
+			buffer, buflen, NVME_QID_ANY, 0);
 	if (ret >= 0 && result)
 		*result = le32_to_cpu(res.u32);
 	return ret;
@@ -2172,7 +2177,7 @@ static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t l
 	cmd.common.cdw11 = cpu_to_le32(len);
 
 	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
-			NVME_QID_ANY, 1, 0);
+			NVME_QID_ANY, NVME_SUBMIT_AT_HEAD);
 }
 
 static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended)
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 373ed08e6b920..3499acbf6a822 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -180,7 +180,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -226,7 +226,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -271,7 +271,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 	cmd.prop_set.value = cpu_to_le64(val);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 	if (unlikely(ret))
 		dev_err(ctrl->device,
 			"Property Set error: %d, offset %#x\n",
@@ -450,8 +450,10 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 		return -ENOMEM;
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res,
-			data, sizeof(*data), NVME_QID_ANY, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+			data, sizeof(*data), NVME_QID_ANY,
+			NVME_SUBMIT_AT_HEAD |
+			NVME_SUBMIT_NOWAIT |
+			NVME_SUBMIT_RESERVED);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);
@@ -525,8 +527,10 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 		return -ENOMEM;
 
 	ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res,
-			data, sizeof(*data), qid, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+			data, sizeof(*data), qid,
+			NVME_SUBMIT_AT_HEAD |
+			NVME_SUBMIT_RESERVED |
+			NVME_SUBMIT_NOWAIT);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 1700063bc24de..7d315b670e537 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -837,12 +837,25 @@ static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl,
 		(ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS);
 }
 
+/*
+ * Flags for __nvme_submit_sync_cmd()
+ */
+typedef __u32 __bitwise nvme_submit_flags_t;
+
+enum {
+	/* Insert request at the head of the queue */
+	NVME_SUBMIT_AT_HEAD  = (__force nvme_submit_flags_t)(1 << 0),
+	/* Set BLK_MQ_REQ_NOWAIT when allocating request */
+	NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1),
+	/* Set BLK_MQ_REQ_RESERVED when allocating request */
+	NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2),
+};
+
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		int qid, int at_head,
-		blk_mq_req_flags_t flags);
+		int qid, nvme_submit_flags_t flags);
 int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
 		      unsigned int dword11, void *buffer, size_t buflen,
 		      u32 *result);
-- 
GitLab


From 48dae46676d1acb632a3e1e14d02879d57618b5d Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Mon, 29 Jan 2024 07:39:48 +0100
Subject: [PATCH 3731/4076] nvme: enable retries for authentication commands

Authentication commands might trigger a lengthy computation on the
controller or even a callout to an external entity.
In these cases the controller might return a status without the DNR
bit set, indicating that the command should be retried.
This patch enables retries for authentication commands  by setting
NVME_SUBMIT_RETRY for __nvme_submit_sync_cmd().

Reported-by: Martin George <marting@netapp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/auth.c | 2 +-
 drivers/nvme/host/core.c | 2 ++
 drivers/nvme/host/nvme.h | 2 ++
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index bf69be8966f44..a264b3ae078b8 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -58,7 +58,7 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 			    void *data, size_t data_len, bool auth_send)
 {
 	struct nvme_command cmd = {};
-	nvme_submit_flags_t flags = 0;
+	nvme_submit_flags_t flags = NVME_SUBMIT_RETRY;
 	struct request_queue *q = ctrl->fabrics_q;
 	int ret;
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index aed099a457911..8b48b7f7871ad 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1070,6 +1070,8 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 	nvme_init_request(req, cmd);
+	if (flags & NVME_SUBMIT_RETRY)
+		req->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
 	if (buffer && bufflen) {
 		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 7d315b670e537..945bf15dccec6 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -849,6 +849,8 @@ enum {
 	NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1),
 	/* Set BLK_MQ_REQ_RESERVED when allocating request */
 	NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2),
+	/* Retry command when NVME_SC_DNR is not set in the result */
+	NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3),
 };
 
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
-- 
GitLab


From 0945b43b4ef8833d73daf5d057d07b64a23b4220 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Wed, 31 Jan 2024 15:01:38 -0800
Subject: [PATCH 3732/4076] nvme-common: add module description

Add MODULE_DESCRIPTION() in order to remove warnings & get clean build:-

WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/common/nvme-auth.o
WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/nvme/common/nvme-keyring.o

Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/common/auth.c    | 1 +
 drivers/nvme/common/keyring.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c
index a23ab5c968b94..a3455f1d67fae 100644
--- a/drivers/nvme/common/auth.c
+++ b/drivers/nvme/common/auth.c
@@ -471,4 +471,5 @@ int nvme_auth_generate_key(u8 *secret, struct nvme_dhchap_key **ret_key)
 }
 EXPORT_SYMBOL_GPL(nvme_auth_generate_key);
 
+MODULE_DESCRIPTION("NVMe Authentication framework");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c
index a5c0431c101cf..6f7e7a8fa5ae4 100644
--- a/drivers/nvme/common/keyring.c
+++ b/drivers/nvme/common/keyring.c
@@ -181,5 +181,6 @@ static void __exit nvme_keyring_exit(void)
 
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Hannes Reinecke <hare@suse.de>");
+MODULE_DESCRIPTION("NVMe Keyring implementation");
 module_init(nvme_keyring_init);
 module_exit(nvme_keyring_exit);
-- 
GitLab


From 4b6821940eeb238a0cc9af322e9ebe8e12613f6a Mon Sep 17 00:00:00 2001
From: Caleb Sander <csander@purestorage.com>
Date: Wed, 31 Jan 2024 09:43:11 -0700
Subject: [PATCH 3733/4076] nvme: return string as char *, not unsigned char *

The functions in drivers/nvme/host/constants.c returning human-readable
status and opcode strings currently use type "const unsigned char *".
Typically string constants use type "const char *",
so remove "unsigned" from the return types.
This is a purely cosmetic change to clarify that the functions
return text strings instead of an array of bytes, for example.

Signed-off-by: Caleb Sander <csander@purestorage.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/constants.c |  8 ++++----
 drivers/nvme/host/nvme.h      | 18 +++++++++---------
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 20f46c230885c..8791283ec6ad2 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -171,7 +171,7 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_HOST_ABORTED_CMD] = "Host Aborted Command",
 };
 
-const unsigned char *nvme_get_error_status_str(u16 status)
+const char *nvme_get_error_status_str(u16 status)
 {
 	status &= 0x7ff;
 	if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
@@ -179,7 +179,7 @@ const unsigned char *nvme_get_error_status_str(u16 status)
 	return "Unknown";
 }
 
-const unsigned char *nvme_get_opcode_str(u8 opcode)
+const char *nvme_get_opcode_str(u8 opcode)
 {
 	if (opcode < ARRAY_SIZE(nvme_ops) && nvme_ops[opcode])
 		return nvme_ops[opcode];
@@ -187,7 +187,7 @@ const unsigned char *nvme_get_opcode_str(u8 opcode)
 }
 EXPORT_SYMBOL_GPL(nvme_get_opcode_str);
 
-const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+const char *nvme_get_admin_opcode_str(u8 opcode)
 {
 	if (opcode < ARRAY_SIZE(nvme_admin_ops) && nvme_admin_ops[opcode])
 		return nvme_admin_ops[opcode];
@@ -195,7 +195,7 @@ const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
 }
 EXPORT_SYMBOL_GPL(nvme_get_admin_opcode_str);
 
-const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode) {
+const char *nvme_get_fabrics_opcode_str(u8 opcode) {
 	if (opcode < ARRAY_SIZE(nvme_fabrics_ops) && nvme_fabrics_ops[opcode])
 		return nvme_fabrics_ops[opcode];
 	return "Unknown";
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 945bf15dccec6..acdf0e5e7e9aa 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -1140,31 +1140,31 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
 }
 
 #ifdef CONFIG_NVME_VERBOSE_ERRORS
-const unsigned char *nvme_get_error_status_str(u16 status);
-const unsigned char *nvme_get_opcode_str(u8 opcode);
-const unsigned char *nvme_get_admin_opcode_str(u8 opcode);
-const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode);
+const char *nvme_get_error_status_str(u16 status);
+const char *nvme_get_opcode_str(u8 opcode);
+const char *nvme_get_admin_opcode_str(u8 opcode);
+const char *nvme_get_fabrics_opcode_str(u8 opcode);
 #else /* CONFIG_NVME_VERBOSE_ERRORS */
-static inline const unsigned char *nvme_get_error_status_str(u16 status)
+static inline const char *nvme_get_error_status_str(u16 status)
 {
 	return "I/O Error";
 }
-static inline const unsigned char *nvme_get_opcode_str(u8 opcode)
+static inline const char *nvme_get_opcode_str(u8 opcode)
 {
 	return "I/O Cmd";
 }
-static inline const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+static inline const char *nvme_get_admin_opcode_str(u8 opcode)
 {
 	return "Admin Cmd";
 }
 
-static inline const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode)
+static inline const char *nvme_get_fabrics_opcode_str(u8 opcode)
 {
 	return "Fabrics Cmd";
 }
 #endif /* CONFIG_NVME_VERBOSE_ERRORS */
 
-static inline const unsigned char *nvme_opcode_str(int qid, u8 opcode, u8 fctype)
+static inline const char *nvme_opcode_str(int qid, u8 opcode, u8 fctype)
 {
 	if (opcode == nvme_fabrics_command)
 		return nvme_get_fabrics_opcode_str(fctype);
-- 
GitLab


From 6f9a71c61183d6849d5aeab085b210c10398af9a Mon Sep 17 00:00:00 2001
From: Caleb Sander <csander@purestorage.com>
Date: Wed, 31 Jan 2024 09:43:12 -0700
Subject: [PATCH 3734/4076] nvme: remove redundant status mask

In nvme_get_error_status_str(), the status code is already masked
with 0x7ff at the beginning of the function.
Don't bother masking it again when indexing nvme_statuses.

Signed-off-by: Caleb Sander <csander@purestorage.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/constants.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 8791283ec6ad2..6f2ebb5fcdb05 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -175,7 +175,7 @@ const char *nvme_get_error_status_str(u16 status)
 {
 	status &= 0x7ff;
 	if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
-		return nvme_statuses[status & 0x7ff];
+		return nvme_statuses[status];
 	return "Unknown";
 }
 
-- 
GitLab


From f9e9115d0c014dec3278d68823eaff159f98f4d6 Mon Sep 17 00:00:00 2001
From: Caleb Sander <csander@purestorage.com>
Date: Wed, 31 Jan 2024 09:43:13 -0700
Subject: [PATCH 3735/4076] nvme: take const cmd pointer in read-only helpers

nvme_is_fabrics() and nvme_is_write() only read struct nvme_command,
so take it by const pointer. This allows callers to pass a const pointer
and communicates that these functions don't modify the command.

Signed-off-by: Caleb Sander <csander@purestorage.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/nvme.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 68eff8c86ce34..bc605ec4a3fd0 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1812,7 +1812,7 @@ struct nvme_command {
 	};
 };
 
-static inline bool nvme_is_fabrics(struct nvme_command *cmd)
+static inline bool nvme_is_fabrics(const struct nvme_command *cmd)
 {
 	return cmd->common.opcode == nvme_fabrics_command;
 }
@@ -1831,7 +1831,7 @@ struct nvme_error_slot {
 	__u8		resv2[24];
 };
 
-static inline bool nvme_is_write(struct nvme_command *cmd)
+static inline bool nvme_is_write(const struct nvme_command *cmd)
 {
 	/*
 	 * What a mess...
-- 
GitLab


From d8f5df1fcea54923b74558035b8de8fb2da3e816 Mon Sep 17 00:00:00 2001
From: Mohammad Nassiri <mnassiri@ciena.com>
Date: Tue, 30 Jan 2024 03:51:52 +0000
Subject: [PATCH 3736/4076] selftests/net: Argument value mismatch when calling
 verify_counters()

The end_server() function only operates in the server thread
and always takes an accept socket instead of a listen socket as
its input argument. To align with this, invert the boolean values
used when calling verify_counters() within the end_server() function.

As a result of this typo, the test didn't correctly check for
the non-symmetrical scenario, where i.e. peer-A uses a key <100:200>
to send data, but peer-B uses another key <105:205> to send its data.
So, in simple words, different keys for TX and RX.

Fixes: 3c3ead555648 ("selftests/net: Add TCP-AO key-management test")
Signed-off-by: Mohammad Nassiri <mnassiri@ciena.com>
Link: https://lore.kernel.org/all/934627c5-eebb-4626-be23-cfb134c01d1a@arista.com/
[amended 'Fixes' tag, added the issue description and carried-over to lkml]
Signed-off-by: Dmitry Safonov <dima@arista.com>
Link: https://lore.kernel.org/r/20240130-tcp-ao-test-key-mgmt-v2-1-d190430a6c60@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/key-management.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index c48b4970ca17e..f6a9395e3cd7d 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -843,7 +843,7 @@ static void end_server(const char *tst_name, int sk,
 	synchronize_threads(); /* 4: verified => closed */
 	close(sk);
 
-	verify_counters(tst_name, true, false, begin, &end);
+	verify_counters(tst_name, false, true, begin, &end);
 	synchronize_threads(); /* 5: counters */
 }
 
-- 
GitLab


From 384aa16d3776a9ca5c0c1f1e7af4030fe176a993 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Tue, 30 Jan 2024 03:51:53 +0000
Subject: [PATCH 3737/4076] selftests/net: Rectify key counters checks

As the names of (struct test_key) members didn't reflect whether the key
was used for TX or RX, the verification for the counters was done
incorrectly for asymmetrical selftests.

Rename these with _tx appendix and fix checks in verify_counters().
While at it, as the checks are now correct, introduce skip_counters_checks,
which is intended for tests where it's expected that a key that was set
with setsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, ...) might had no chance
of getting used on the wire.

Fixes the following failures, exposed by the previous commit:
> not ok 51 server: Check current != rnext keys set before connect(): Counter pkt_good was expected to increase 0 => 0 for key 132:5
> not ok 52 server: Check current != rnext keys set before connect(): Counter pkt_good was not expected to increase 0 => 21 for key 137:10
>
> not ok 63 server: Check current flapping back on peer's RnextKey request: Counter pkt_good was expected to increase 0 => 0 for key 132:5
> not ok 64 server: Check current flapping back on peer's RnextKey request: Counter pkt_good was not expected to increase 0 => 40 for key 137:10

Cc: Mohammad Nassiri <mnassiri@ciena.com>
Fixes: 3c3ead555648 ("selftests/net: Add TCP-AO key-management test")
Signed-off-by: Dmitry Safonov <dima@arista.com>
Link: https://lore.kernel.org/r/20240130-tcp-ao-test-key-mgmt-v2-2-d190430a6c60@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/net/tcp_ao/key-management.c     | 44 +++++++++++--------
 1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index f6a9395e3cd7d..24e62120b7924 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -417,9 +417,9 @@ struct test_key {
 		matches_vrf		: 1,
 		is_current		: 1,
 		is_rnext		: 1,
-		used_on_handshake	: 1,
-		used_after_accept	: 1,
-		used_on_client		: 1;
+		used_on_server_tx	: 1,
+		used_on_client_tx	: 1,
+		skip_counters_checks	: 1;
 };
 
 struct key_collection {
@@ -609,16 +609,14 @@ static int key_collection_socket(bool server, unsigned int port)
 				addr = &this_ip_dest;
 			sndid = key->client_keyid;
 			rcvid = key->server_keyid;
-			set_current = key->is_current;
-			set_rnext = key->is_rnext;
+			key->used_on_client_tx = set_current = key->is_current;
+			key->used_on_server_tx = set_rnext = key->is_rnext;
 		}
 
 		if (test_add_key_cr(sk, key->password, key->len,
 				    *addr, vrf, sndid, rcvid, key->maclen,
 				    key->alg, set_current, set_rnext))
 			test_key_error("setsockopt(TCP_AO_ADD_KEY)", key);
-		if (set_current || set_rnext)
-			key->used_on_handshake = 1;
 #ifdef DEBUG
 		test_print("%s [%u/%u] key: { %s, %u:%u, %u, %u:%u:%u:%u (%u)}",
 			   server ? "server" : "client", i, collection.nr_keys,
@@ -640,22 +638,22 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server
 	for (i = 0; i < collection.nr_keys; i++) {
 		struct test_key *key = &collection.keys[i];
 		uint8_t sndid, rcvid;
-		bool was_used;
+		bool rx_cnt_expected;
 
+		if (key->skip_counters_checks)
+			continue;
 		if (server) {
 			sndid = key->server_keyid;
 			rcvid = key->client_keyid;
-			if (is_listen_sk)
-				was_used = key->used_on_handshake;
-			else
-				was_used = key->used_after_accept;
+			rx_cnt_expected = key->used_on_client_tx;
 		} else {
 			sndid = key->client_keyid;
 			rcvid = key->server_keyid;
-			was_used = key->used_on_client;
+			rx_cnt_expected = key->used_on_server_tx;
 		}
 
-		test_tcp_ao_key_counters_cmp(tst_name, a, b, was_used,
+		test_tcp_ao_key_counters_cmp(tst_name, a, b,
+					     rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
 					     sndid, rcvid);
 	}
 	test_tcp_ao_counters_free(a);
@@ -916,9 +914,8 @@ static int run_client(const char *tst_name, unsigned int port,
 		current_index = nr_keys - 1;
 	if (rnext_index < 0)
 		rnext_index = nr_keys - 1;
-	collection.keys[current_index].used_on_handshake = 1;
-	collection.keys[rnext_index].used_after_accept = 1;
-	collection.keys[rnext_index].used_on_client = 1;
+	collection.keys[current_index].used_on_client_tx = 1;
+	collection.keys[rnext_index].used_on_server_tx = 1;
 
 	synchronize_threads(); /* 3: accepted => send data */
 	if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) {
@@ -1059,7 +1056,16 @@ static void check_current_back(const char *tst_name, unsigned int port,
 		test_error("Can't change the current key");
 	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
 		test_fail("verify failed");
-	collection.keys[rotate_to_index].used_after_accept = 1;
+	/* There is a race here: between setting the current_key with
+	 * setsockopt(TCP_AO_INFO) and starting to send some data - there
+	 * might have been a segment received with the desired
+	 * RNext_key set. In turn that would mean that the first outgoing
+	 * segment will have the desired current_key (flipped back).
+	 * Which is what the user/test wants. As it's racy, skip checking
+	 * the counters, yet check what are the resulting current/rnext
+	 * keys on both sides.
+	 */
+	collection.keys[rotate_to_index].skip_counters_checks = 1;
 
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
 }
@@ -1089,7 +1095,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 		}
 		verify_current_rnext(tst_name, sk, -1,
 				     collection.keys[i].server_keyid);
-		collection.keys[i].used_on_client = 1;
+		collection.keys[i].used_on_server_tx = 1;
 		synchronize_threads(); /* verify current/rnext */
 	}
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
-- 
GitLab


From 6caf3adcc877b3470e98133d52b360ebe5f7a6a3 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Tue, 30 Jan 2024 03:51:54 +0000
Subject: [PATCH 3738/4076] selftests/net: Repair RST passive reset selftest

Currently, the test is racy and seems to not pass anymore.

In order to rectify it, aim on TCP_TW_RST.
Doesn't seem way too good with this sleep() part, but it seems as
a reasonable compromise for the test. There is a plan in-line comment on
how-to improve it, going to do it on the top, at this moment I want it
to run on netdev/patchwork selftests dashboard.

It also slightly changes tcp_ao-lib in order to get SO_ERROR propagated
to test_client_verify() return value.

Fixes: c6df7b2361d7 ("selftests/net: Add TCP-AO RST test")
Signed-off-by: Dmitry Safonov <dima@arista.com>
Link: https://lore.kernel.org/r/20240130-tcp-ao-test-key-mgmt-v2-3-d190430a6c60@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/lib/sock.c |  12 +-
 tools/testing/selftests/net/tcp_ao/rst.c      | 138 ++++++++++++------
 2 files changed, 98 insertions(+), 52 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index c75d82885a2e1..15aeb0963058f 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -62,7 +62,9 @@ int test_wait_fd(int sk, time_t sec, bool write)
 		return -ETIMEDOUT;
 	}
 
-	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen) || ret)
+	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen))
+		return -errno;
+	if (ret)
 		return -ret;
 	return 0;
 }
@@ -584,9 +586,11 @@ int test_client_verify(int sk, const size_t msg_len, const size_t nr,
 {
 	size_t buf_sz = msg_len * nr;
 	char *buf = alloca(buf_sz);
+	ssize_t ret;
 
 	randomize_buffer(buf, buf_sz);
-	if (test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec) != buf_sz)
-		return -1;
-	return 0;
+	ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec);
+	if (ret < 0)
+		return (int)ret;
+	return ret != buf_sz ? -1 : 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index ac06009a7f5f6..7df8b8700e39e 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -1,10 +1,33 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Author: Dmitry Safonov <dima@arista.com> */
+/*
+ * The test checks that both active and passive reset have correct TCP-AO
+ * signature. An "active" reset (abort) here is procured from closing
+ * listen() socket with non-accepted connections in the queue:
+ * inet_csk_listen_stop() => inet_child_forget() =>
+ *                        => tcp_disconnect() => tcp_send_active_reset()
+ *
+ * The passive reset is quite hard to get on established TCP connections.
+ * It could be procured from non-established states, but the synchronization
+ * part from userspace in order to reliably get RST seems uneasy.
+ * So, instead it's procured by corrupting SEQ number on TIMED-WAIT state.
+ *
+ * It's important to test both passive and active RST as they go through
+ * different code-paths:
+ * - tcp_send_active_reset() makes no-data skb, sends it with tcp_transmit_skb()
+ * - tcp_v*_send_reset() create their reply skbs and send them with
+ *   ip_send_unicast_reply()
+ *
+ * In both cases TCP-AO signatures have to be correct, which is verified by
+ * (1) checking that the TCP-AO connection was reset and (2) TCP-AO counters.
+ *
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
 #include <inttypes.h>
 #include "../../../../include/linux/kernel.h"
 #include "aolib.h"
 
 const size_t quota = 1000;
+const size_t packet_sz = 100;
 /*
  * Backlog == 0 means 1 connection in queue, see:
  * commit 64a146513f8f ("[NET]: Revert incorrect accept queue...")
@@ -59,26 +82,6 @@ static void close_forced(int sk)
 	close(sk);
 }
 
-static int test_wait_for_exception(int sk, time_t sec)
-{
-	struct timeval tv = { .tv_sec = sec };
-	struct timeval *ptv = NULL;
-	fd_set efds;
-	int ret;
-
-	FD_ZERO(&efds);
-	FD_SET(sk, &efds);
-
-	if (sec)
-		ptv = &tv;
-
-	errno = 0;
-	ret = select(sk + 1, NULL, NULL, &efds, ptv);
-	if (ret < 0)
-		return -errno;
-	return ret ? sk : 0;
-}
-
 static void test_server_active_rst(unsigned int port)
 {
 	struct tcp_ao_counters cnt1, cnt2;
@@ -155,17 +158,16 @@ static void test_server_passive_rst(unsigned int port)
 			test_fail("server returned %zd", bytes);
 	}
 
-	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	synchronize_threads(); /* 3: checkpoint the client */
+	synchronize_threads(); /* 4: close the server, creating twsk */
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
-
-	synchronize_threads(); /* 4: terminate server + send more on client */
-	bytes = test_server_run(sk, quota, TEST_RETRANSMIT_SEC);
 	close(sk);
+
+	synchronize_threads(); /* 5: restore the socket, send more data */
 	test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
 
-	synchronize_threads(); /* 5: verified => closed */
-	close(sk);
+	synchronize_threads(); /* 6: server exits */
 }
 
 static void *server_fn(void *arg)
@@ -284,7 +286,7 @@ static void test_client_active_rst(unsigned int port)
 		test_error("test_wait_fds(): %d", err);
 
 	synchronize_threads(); /* 3: close listen socket */
-	if (test_client_verify(sk[0], 100, quota / 100, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
@@ -323,7 +325,6 @@ static void test_client_passive_rst(unsigned int port)
 	struct tcp_sock_state img;
 	sockaddr_af saddr;
 	int sk, err;
-	socklen_t slen = sizeof(err);
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
 	if (sk < 0)
@@ -337,18 +338,51 @@ static void test_client_passive_rst(unsigned int port)
 		test_error("failed to connect()");
 
 	synchronize_threads(); /* 2: accepted => send data */
-	if (test_client_verify(sk, 100, quota / 100, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
 
-	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	synchronize_threads(); /* 3: checkpoint the client */
 	test_enable_repair(sk);
 	test_sock_checkpoint(sk, &img, &saddr);
 	test_ao_checkpoint(sk, &ao_img);
-	test_kill_sk(sk);
+	test_disable_repair(sk);
 
-	img.out.seq += quota;
+	synchronize_threads(); /* 4: close the server, creating twsk */
+
+	/*
+	 * The "corruption" in SEQ has to be small enough to fit into TCP
+	 * window, see tcp_timewait_state_process() for out-of-window
+	 * segments.
+	 */
+	img.out.seq += 5; /* 5 is more noticeable in tcpdump than 1 */
+
+	/*
+	 * FIXME: This is kind-of ugly and dirty, but it works.
+	 *
+	 * At this moment, the server has close'ed(sk).
+	 * The passive RST that is being targeted here is new data after
+	 * half-duplex close, see tcp_timewait_state_process() => TCP_TW_RST
+	 *
+	 * What is needed here is:
+	 * (1) wait for FIN from the server
+	 * (2) make sure that the ACK from the client went out
+	 * (3) make sure that the ACK was received and processed by the server
+	 *
+	 * Otherwise, the data that will be sent from "repaired" socket
+	 * post SEQ corruption may get to the server before it's in
+	 * TCP_FIN_WAIT2.
+	 *
+	 * (1) is easy with select()/poll()
+	 * (2) is possible by polling tcpi_state from TCP_INFO
+	 * (3) is quite complex: as server's socket was already closed,
+	 *     probably the way to do it would be tcp-diag.
+	 */
+	sleep(TEST_RETRANSMIT_SEC);
+
+	synchronize_threads(); /* 5: restore the socket, send more data */
+	test_kill_sk(sk);
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
 	if (sk < 0)
@@ -366,25 +400,33 @@ static void test_client_passive_rst(unsigned int port)
 	test_disable_repair(sk);
 	test_sock_state_free(&img);
 
-	synchronize_threads(); /* 4: terminate server + send more on client */
-	if (test_client_verify(sk, 100, quota / 100, 2 * TEST_TIMEOUT_SEC))
-		test_ok("client connection broken post-seq-adjust");
-	else
-		test_fail("client connection still works post-seq-adjust");
-
-	test_wait_for_exception(sk, TEST_TIMEOUT_SEC);
-
-	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &err, &slen))
-		test_error("getsockopt()");
-	if (err != ECONNRESET && err != EPIPE)
-		test_fail("client connection was not reset: %d", err);
+	/*
+	 * This is how "passive reset" is acquired in this test from TCP_TW_RST:
+	 *
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [P.], seq 901:1001, ack 1001, win 249,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x10217d6c36a22379086ef3b1], length 100
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [F.], seq 1001, ack 1001, win 249,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x104ffc99b98c10a5298cc268], length 0
+	 * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [.], ack 1002, win 251,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0xe496dd4f7f5a8a66873c6f93,nop,nop,sack 1 {1001:1002}], length 0
+	 * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [P.], seq 1006:1106, ack 1001, win 251,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x1b5f3330fb23fbcd0c77d0ca], length 100
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0
+	 */
+	err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC);
+	/* Make sure that the connection was reset, not timeouted */
+	if (err && err == -ECONNRESET)
+		test_ok("client sock was passively reset post-seq-adjust");
+	else if (err)
+		test_fail("client sock was not reset post-seq-adjust: %d", err);
 	else
-		test_ok("client connection was reset");
+		test_fail("client sock is yet connected post-seq-adjust");
 
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
 
-	synchronize_threads(); /* 5: verified => closed */
+	synchronize_threads(); /* 6: server exits */
 	close(sk);
 	test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
 }
@@ -410,6 +452,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(15, server_fn, client_fn);
+	test_init(14, server_fn, client_fn);
 	return 0;
 }
-- 
GitLab


From 7d23e836b00eec96610141549f59e5902dc55fe8 Mon Sep 17 00:00:00 2001
From: Caleb Sander <csander@purestorage.com>
Date: Wed, 31 Jan 2024 09:43:14 -0700
Subject: [PATCH 3739/4076] nvme: split out fabrics version of
 nvme_opcode_str()

nvme_opcode_str() currently supports admin, IO, and fabrics commands.
However, fabrics commands aren't allowed for the pci transport.
Currently the pci caller passes 0 as the fctype,
which means any fabrics command would be displayed as "Property Set".

Move fabrics command support into a function nvme_fabrics_opcode_str()
and remove the fctype argument to nvme_opcode_str().
This way, a fabrics command will display as "Unknown" for pci.
Convert the rdma and tcp transports to use nvme_fabrics_opcode_str().

Signed-off-by: Caleb Sander <csander@purestorage.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/nvme.h | 13 ++++++++++---
 drivers/nvme/host/pci.c  |  2 +-
 drivers/nvme/host/rdma.c |  7 +++----
 drivers/nvme/host/tcp.c  |  6 +++---
 4 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index acdf0e5e7e9aa..b70b333a0874f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -1164,11 +1164,18 @@ static inline const char *nvme_get_fabrics_opcode_str(u8 opcode)
 }
 #endif /* CONFIG_NVME_VERBOSE_ERRORS */
 
-static inline const char *nvme_opcode_str(int qid, u8 opcode, u8 fctype)
+static inline const char *nvme_opcode_str(int qid, u8 opcode)
 {
-	if (opcode == nvme_fabrics_command)
-		return nvme_get_fabrics_opcode_str(fctype);
 	return qid ? nvme_get_opcode_str(opcode) :
 		nvme_get_admin_opcode_str(opcode);
 }
+
+static inline const char *nvme_fabrics_opcode_str(
+		int qid, const struct nvme_command *cmd)
+{
+	if (nvme_is_fabrics(cmd))
+		return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype);
+
+	return nvme_opcode_str(qid, cmd->common.opcode);
+}
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 25eb727795417..e6267a6aa3801 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1349,7 +1349,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 		dev_warn(dev->ctrl.device,
 			 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n",
 			 req->tag, nvme_cid(req), opcode,
-			 nvme_opcode_str(nvmeq->qid, opcode, 0), nvmeq->qid);
+			 nvme_opcode_str(nvmeq->qid, opcode), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		goto disable;
 	}
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 3f393ee202811..6adf2c19a7120 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1951,14 +1951,13 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
-	u8 opcode = req->req.cmd->common.opcode;
-	u8 fctype = req->req.cmd->fabrics.fctype;
+	struct nvme_command *cmd = req->req.cmd;
 	int qid = nvme_rdma_queue_idx(queue);
 
 	dev_warn(ctrl->ctrl.device,
 		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n",
-		 rq->tag, nvme_cid(rq), opcode,
-		 nvme_opcode_str(qid, opcode, fctype), qid);
+		 rq->tag, nvme_cid(rq), cmd->common.opcode,
+		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
 	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
 		/*
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 4393cf244025e..9f8dea2e2c7d5 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2428,13 +2428,13 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req);
-	u8 opc = pdu->cmd.common.opcode, fctype = pdu->cmd.fabrics.fctype;
+	struct nvme_command *cmd = &pdu->cmd;
 	int qid = nvme_tcp_queue_id(req->queue);
 
 	dev_warn(ctrl->device,
 		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
-		 rq->tag, nvme_cid(rq), pdu->hdr.type, opc,
-		 nvme_opcode_str(qid, opc, fctype), qid);
+		 rq->tag, nvme_cid(rq), pdu->hdr.type, cmd->common.opcode,
+		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
 	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
 		/*
-- 
GitLab


From 0d150beff26e636aa07ab889133a0015eaee4227 Mon Sep 17 00:00:00 2001
From: Caleb Sander <csander@purestorage.com>
Date: Wed, 31 Jan 2024 09:43:15 -0700
Subject: [PATCH 3740/4076] nvme-fc: log human-readable opcode on timeout

The fc transport logs the opcode and fctype on command timeout.
This is sufficient information to identify the command issued,
but not very human-readable. Use the nvme_fabrics_opcode_str()
helper to also log the name of the command, as rdma and tcp already do.

Signed-off-by: Caleb Sander <csander@purestorage.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/fc.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index e2308119f8f0b..63a2e2839a789 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2574,6 +2574,7 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
+	u16 qnum = op->queue->qnum;
 	struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
 	struct nvme_command *sqe = &cmdiu->sqe;
 
@@ -2582,10 +2583,11 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 	 * will detect the aborted io and will fail the connection.
 	 */
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d w10/11: "
+		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d (%s) w10/11: "
 		"x%08x/x%08x\n",
-		ctrl->cnum, op->queue->qnum, sqe->common.opcode,
-		sqe->connect.fctype, sqe->common.cdw10, sqe->common.cdw11);
+		ctrl->cnum, qnum, sqe->common.opcode, sqe->fabrics.fctype,
+		nvme_fabrics_opcode_str(qnum, sqe),
+		sqe->common.cdw10, sqe->common.cdw11);
 	if (__nvme_fc_abort_op(ctrl, op))
 		nvme_fc_error_recovery(ctrl, "io timeout abort failed");
 
-- 
GitLab


From 4d322dce82a1d44f8c83f0f54f95dd1b8dcf46c9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Jan 2024 18:42:35 +0000
Subject: [PATCH 3741/4076] af_unix: fix lockdep positive in
 sk_diag_dump_icons()

syzbot reported a lockdep splat [1].

Blamed commit hinted about the possible lockdep
violation, and code used unix_state_lock_nested()
in an attempt to silence lockdep.

It is not sufficient, because unix_state_lock_nested()
is already used from unix_state_double_lock().

We need to use a separate subclass.

This patch adds a distinct enumeration to make things
more explicit.

Also use swap() in unix_state_double_lock() as a clean up.

v2: add a missing inline keyword to unix_state_lock_nested()

[1]
WARNING: possible circular locking dependency detected
6.8.0-rc1-syzkaller-00356-g8a696a29c690 #0 Not tainted

syz-executor.1/2542 is trying to acquire lock:
 ffff88808b5df9e8 (rlock-AF_UNIX){+.+.}-{2:2}, at: skb_queue_tail+0x36/0x120 net/core/skbuff.c:3863

but task is already holding lock:
 ffff88808b5dfe70 (&u->lock/1){+.+.}-{2:2}, at: unix_dgram_sendmsg+0xfc7/0x2200 net/unix/af_unix.c:2089

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&u->lock/1){+.+.}-{2:2}:
        lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754
        _raw_spin_lock_nested+0x31/0x40 kernel/locking/spinlock.c:378
        sk_diag_dump_icons net/unix/diag.c:87 [inline]
        sk_diag_fill+0x6ea/0xfe0 net/unix/diag.c:157
        sk_diag_dump net/unix/diag.c:196 [inline]
        unix_diag_dump+0x3e9/0x630 net/unix/diag.c:220
        netlink_dump+0x5c1/0xcd0 net/netlink/af_netlink.c:2264
        __netlink_dump_start+0x5d7/0x780 net/netlink/af_netlink.c:2370
        netlink_dump_start include/linux/netlink.h:338 [inline]
        unix_diag_handler_dump+0x1c3/0x8f0 net/unix/diag.c:319
       sock_diag_rcv_msg+0xe3/0x400
        netlink_rcv_skb+0x1df/0x430 net/netlink/af_netlink.c:2543
        sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280
        netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline]
        netlink_unicast+0x7e6/0x980 net/netlink/af_netlink.c:1367
        netlink_sendmsg+0xa37/0xd70 net/netlink/af_netlink.c:1908
        sock_sendmsg_nosec net/socket.c:730 [inline]
        __sock_sendmsg net/socket.c:745 [inline]
        sock_write_iter+0x39a/0x520 net/socket.c:1160
        call_write_iter include/linux/fs.h:2085 [inline]
        new_sync_write fs/read_write.c:497 [inline]
        vfs_write+0xa74/0xca0 fs/read_write.c:590
        ksys_write+0x1a0/0x2c0 fs/read_write.c:643
        do_syscall_x64 arch/x86/entry/common.c:52 [inline]
        do_syscall_64+0xf5/0x230 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x63/0x6b

-> #0 (rlock-AF_UNIX){+.+.}-{2:2}:
        check_prev_add kernel/locking/lockdep.c:3134 [inline]
        check_prevs_add kernel/locking/lockdep.c:3253 [inline]
        validate_chain+0x1909/0x5ab0 kernel/locking/lockdep.c:3869
        __lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137
        lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754
        __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
        _raw_spin_lock_irqsave+0xd5/0x120 kernel/locking/spinlock.c:162
        skb_queue_tail+0x36/0x120 net/core/skbuff.c:3863
        unix_dgram_sendmsg+0x15d9/0x2200 net/unix/af_unix.c:2112
        sock_sendmsg_nosec net/socket.c:730 [inline]
        __sock_sendmsg net/socket.c:745 [inline]
        ____sys_sendmsg+0x592/0x890 net/socket.c:2584
        ___sys_sendmsg net/socket.c:2638 [inline]
        __sys_sendmmsg+0x3b2/0x730 net/socket.c:2724
        __do_sys_sendmmsg net/socket.c:2753 [inline]
        __se_sys_sendmmsg net/socket.c:2750 [inline]
        __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2750
        do_syscall_x64 arch/x86/entry/common.c:52 [inline]
        do_syscall_64+0xf5/0x230 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x63/0x6b

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&u->lock/1);
                               lock(rlock-AF_UNIX);
                               lock(&u->lock/1);
  lock(rlock-AF_UNIX);

 *** DEADLOCK ***

1 lock held by syz-executor.1/2542:
  #0: ffff88808b5dfe70 (&u->lock/1){+.+.}-{2:2}, at: unix_dgram_sendmsg+0xfc7/0x2200 net/unix/af_unix.c:2089

stack backtrace:
CPU: 1 PID: 2542 Comm: syz-executor.1 Not tainted 6.8.0-rc1-syzkaller-00356-g8a696a29c690 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:88 [inline]
  dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106
  check_noncircular+0x366/0x490 kernel/locking/lockdep.c:2187
  check_prev_add kernel/locking/lockdep.c:3134 [inline]
  check_prevs_add kernel/locking/lockdep.c:3253 [inline]
  validate_chain+0x1909/0x5ab0 kernel/locking/lockdep.c:3869
  __lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137
  lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754
  __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
  _raw_spin_lock_irqsave+0xd5/0x120 kernel/locking/spinlock.c:162
  skb_queue_tail+0x36/0x120 net/core/skbuff.c:3863
  unix_dgram_sendmsg+0x15d9/0x2200 net/unix/af_unix.c:2112
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg net/socket.c:745 [inline]
  ____sys_sendmsg+0x592/0x890 net/socket.c:2584
  ___sys_sendmsg net/socket.c:2638 [inline]
  __sys_sendmmsg+0x3b2/0x730 net/socket.c:2724
  __do_sys_sendmmsg net/socket.c:2753 [inline]
  __se_sys_sendmmsg net/socket.c:2750 [inline]
  __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2750
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xf5/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b
RIP: 0033:0x7f26d887cda9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f26d95a60c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00007f26d89abf80 RCX: 00007f26d887cda9
RDX: 000000000000003e RSI: 00000000200bd000 RDI: 0000000000000004
RBP: 00007f26d88c947a R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000008c0 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007f26d89abf80 R15: 00007ffcfe081a68

Fixes: 2aac7a2cb0d9 ("unix_diag: Pending connections IDs NLA")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240130184235.1620738-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/af_unix.h | 20 ++++++++++++++------
 net/unix/af_unix.c    | 14 ++++++--------
 net/unix/diag.c       |  2 +-
 3 files changed, 21 insertions(+), 15 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 49c4640027d8a..afd40dce40f3d 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -46,12 +46,6 @@ struct scm_stat {
 
 #define UNIXCB(skb)	(*(struct unix_skb_parms *)&((skb)->cb))
 
-#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
-#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
-#define unix_state_lock_nested(s) \
-				spin_lock_nested(&unix_sk(s)->lock, \
-				SINGLE_DEPTH_NESTING)
-
 /* The AF_UNIX socket */
 struct unix_sock {
 	/* WARNING: sk has to be the first member */
@@ -77,6 +71,20 @@ struct unix_sock {
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
 #define unix_peer(sk) (unix_sk(sk)->peer)
 
+#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
+#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
+enum unix_socket_lock_class {
+	U_LOCK_NORMAL,
+	U_LOCK_SECOND,	/* for double locking, see unix_state_double_lock(). */
+	U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
+};
+
+static inline void unix_state_lock_nested(struct sock *sk,
+				   enum unix_socket_lock_class subclass)
+{
+	spin_lock_nested(&unix_sk(sk)->lock, subclass);
+}
+
 #define peer_wait peer_wq.wait
 
 long unix_inq_len(struct sock *sk);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ac1f2bc18fc96..30b178ebba60a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1344,13 +1344,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
 		unix_state_lock(sk1);
 		return;
 	}
-	if (sk1 < sk2) {
-		unix_state_lock(sk1);
-		unix_state_lock_nested(sk2);
-	} else {
-		unix_state_lock(sk2);
-		unix_state_lock_nested(sk1);
-	}
+	if (sk1 > sk2)
+		swap(sk1, sk2);
+
+	unix_state_lock(sk1);
+	unix_state_lock_nested(sk2, U_LOCK_SECOND);
 }
 
 static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
@@ -1591,7 +1589,7 @@ restart:
 		goto out_unlock;
 	}
 
-	unix_state_lock_nested(sk);
+	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
 	if (sk->sk_state != st) {
 		unix_state_unlock(sk);
diff --git a/net/unix/diag.c b/net/unix/diag.c
index bec09a3a1d44c..be19827eca36d 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -84,7 +84,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 			 * queue lock. With the other's queue locked it's
 			 * OK to lock the state.
 			 */
-			unix_state_lock_nested(req);
+			unix_state_lock_nested(req, U_LOCK_DIAG);
 			peer = unix_sk(req)->peer;
 			buf[i++] = (peer ? sock_i_ino(peer) : 0);
 			unix_state_unlock(req);
-- 
GitLab


From d9407ff11809c6812bb84fe7be9c1367d758e5c8 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Mon, 29 Jan 2024 15:40:30 -0800
Subject: [PATCH 3742/4076] pds_core: Prevent health thread from running during
 reset/remove

The PCIe reset handlers can run at the same time as the
health thread. This can cause the health thread to
stomp on the PCIe reset. Fix this by preventing the
health thread from running while a PCIe reset is happening.

As part of this use timer_shutdown_sync() during reset and
remove to make sure the timer doesn't ever get rearmed.

Fixes: ffa55858330f ("pds_core: implement pci reset handlers")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/20240129234035.69802-2-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/main.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 3080898d7b95b..5172a5ad8ec6d 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -293,7 +293,7 @@ err_out_stop:
 err_out_teardown:
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING);
 err_out_unmap_bars:
-	del_timer_sync(&pdsc->wdtimer);
+	timer_shutdown_sync(&pdsc->wdtimer);
 	if (pdsc->wq)
 		destroy_workqueue(pdsc->wq);
 	mutex_destroy(&pdsc->config_lock);
@@ -420,7 +420,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 		 */
 		pdsc_sriov_configure(pdev, 0);
 
-		del_timer_sync(&pdsc->wdtimer);
+		timer_shutdown_sync(&pdsc->wdtimer);
 		if (pdsc->wq)
 			destroy_workqueue(pdsc->wq);
 
@@ -445,10 +445,24 @@ static void pdsc_remove(struct pci_dev *pdev)
 	devlink_free(dl);
 }
 
+static void pdsc_stop_health_thread(struct pdsc *pdsc)
+{
+	timer_shutdown_sync(&pdsc->wdtimer);
+	if (pdsc->health_work.func)
+		cancel_work_sync(&pdsc->health_work);
+}
+
+static void pdsc_restart_health_thread(struct pdsc *pdsc)
+{
+	timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
+	mod_timer(&pdsc->wdtimer, jiffies + 1);
+}
+
 void pdsc_reset_prepare(struct pci_dev *pdev)
 {
 	struct pdsc *pdsc = pci_get_drvdata(pdev);
 
+	pdsc_stop_health_thread(pdsc);
 	pdsc_fw_down(pdsc);
 
 	pci_free_irq_vectors(pdev);
@@ -486,6 +500,7 @@ void pdsc_reset_done(struct pci_dev *pdev)
 	}
 
 	pdsc_fw_up(pdsc);
+	pdsc_restart_health_thread(pdsc);
 }
 
 static const struct pci_error_handlers pdsc_err_handler = {
-- 
GitLab


From d321067e2cfa4d5e45401a00912ca9da8d1af631 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Mon, 29 Jan 2024 15:40:31 -0800
Subject: [PATCH 3743/4076] pds_core: Cancel AQ work on teardown

There is a small window where pdsc_work_thread()
calls pdsc_process_adminq() and pdsc_process_adminq()
passes the PDSC_S_STOPPING_DRIVER check and starts
to process adminq/notifyq work and then the driver
starts a fw_down cycle. This could cause some
undefined behavior if the notifyqcq/adminqcq are
free'd while pdsc_process_adminq() is running. Use
cancel_work_sync() on the adminqcq's work struct
to make sure any pending work items are cancelled
and any in progress work items are completed.

Also, make sure to not call cancel_work_sync() if
the work item has not be initialized. Without this,
traces will happen in cases where a reset fails and
teardown is called again or if reset fails and the
driver is removed.

Fixes: 01ba61b55b20 ("pds_core: Add adminq processing and commands")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/20240129234035.69802-3-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 0d2091e9eb283..b582729331ebf 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -464,6 +464,8 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 
 	if (!pdsc->pdev->is_virtfn)
 		pdsc_devcmd_reset(pdsc);
+	if (pdsc->adminqcq.work.func)
+		cancel_work_sync(&pdsc->adminqcq.work);
 	pdsc_qcq_free(pdsc, &pdsc->notifyqcq);
 	pdsc_qcq_free(pdsc, &pdsc->adminqcq);
 
-- 
GitLab


From 951705151e50f9022bc96ec8b3fd5697380b1df6 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Mon, 29 Jan 2024 15:40:32 -0800
Subject: [PATCH 3744/4076] pds_core: Use struct pdsc for the pdsc_adminq_isr
 private data

The initial design for the adminq interrupt was done based
on client drivers having their own adminq and adminq
interrupt. So, each client driver's adminq isr would use
their specific adminqcq for the private data struct. For the
time being the design has changed to only use a single
adminq for all clients. So, instead use the struct pdsc for
the private data to simplify things a bit.

This also has the benefit of not dereferencing the adminqcq
to access the pdsc struct when the PDSC_S_STOPPING_DRIVER bit
is set and the adminqcq has actually been cleared/freed.

Fixes: 01ba61b55b20 ("pds_core: Add adminq processing and commands")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/20240129234035.69802-4-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/adminq.c | 5 +++--
 drivers/net/ethernet/amd/pds_core/core.c   | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index 5beadabc21361..68be5ea251fc1 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -135,8 +135,8 @@ void pdsc_work_thread(struct work_struct *work)
 
 irqreturn_t pdsc_adminq_isr(int irq, void *data)
 {
-	struct pdsc_qcq *qcq = data;
-	struct pdsc *pdsc = qcq->pdsc;
+	struct pdsc *pdsc = data;
+	struct pdsc_qcq *qcq;
 
 	/* Don't process AdminQ when shutting down */
 	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
@@ -145,6 +145,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 		return IRQ_HANDLED;
 	}
 
+	qcq = &pdsc->adminqcq;
 	queue_work(pdsc->wq, &qcq->work);
 	pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
 
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index b582729331ebf..0356e56a6e99e 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -125,7 +125,7 @@ static int pdsc_qcq_intr_alloc(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 
 	snprintf(name, sizeof(name), "%s-%d-%s",
 		 PDS_CORE_DRV_NAME, pdsc->pdev->bus->number, qcq->q.name);
-	index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, qcq);
+	index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, pdsc);
 	if (index < 0)
 		return index;
 	qcq->intx = index;
-- 
GitLab


From 7e82a8745b951b1e794cc780d46f3fbee5e93447 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Mon, 29 Jan 2024 15:40:33 -0800
Subject: [PATCH 3745/4076] pds_core: Prevent race issues involving the adminq

There are multiple paths that can result in using the pdsc's
adminq.

[1] pdsc_adminq_isr and the resulting work from queue_work(),
    i.e. pdsc_work_thread()->pdsc_process_adminq()

[2] pdsc_adminq_post()

When the device goes through reset via PCIe reset and/or
a fw_down/fw_up cycle due to bad PCIe state or bad device
state the adminq is destroyed and recreated.

A NULL pointer dereference can happen if [1] or [2] happens
after the adminq is already destroyed.

In order to fix this, add some further state checks and
implement reference counting for adminq uses. Reference
counting was used because multiple threads can attempt to
access the adminq at the same time via [1] or [2]. Additionally,
multiple clients (i.e. pds-vfio-pci) can be using [2]
at the same time.

The adminq_refcnt is initialized to 1 when the adminq has been
allocated and is ready to use. Users/clients of the adminq
(i.e. [1] and [2]) will increment the refcnt when they are using
the adminq. When the driver goes into a fw_down cycle it will
set the PDSC_S_FW_DEAD bit and then wait for the adminq_refcnt
to hit 1. Setting the PDSC_S_FW_DEAD before waiting will prevent
any further adminq_refcnt increments. Waiting for the
adminq_refcnt to hit 1 allows for any current users of the adminq
to finish before the driver frees the adminq. Once the
adminq_refcnt hits 1 the driver clears the refcnt to signify that
the adminq is deleted and cannot be used. On the fw_up cycle the
driver will once again initialize the adminq_refcnt to 1 allowing
the adminq to be used again.

Fixes: 01ba61b55b20 ("pds_core: Add adminq processing and commands")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/20240129234035.69802-5-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/adminq.c | 31 +++++++++++++++++-----
 drivers/net/ethernet/amd/pds_core/core.c   | 21 +++++++++++++++
 drivers/net/ethernet/amd/pds_core/core.h   |  1 +
 3 files changed, 47 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index 68be5ea251fc1..5edff33d56f36 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -63,6 +63,15 @@ static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 	return nq_work;
 }
 
+static bool pdsc_adminq_inc_if_up(struct pdsc *pdsc)
+{
+	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER) ||
+	    pdsc->state & BIT_ULL(PDSC_S_FW_DEAD))
+		return false;
+
+	return refcount_inc_not_zero(&pdsc->adminq_refcnt);
+}
+
 void pdsc_process_adminq(struct pdsc_qcq *qcq)
 {
 	union pds_core_adminq_comp *comp;
@@ -75,9 +84,9 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 	int aq_work = 0;
 	int credits;
 
-	/* Don't process AdminQ when shutting down */
-	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
-		dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n",
+	/* Don't process AdminQ when it's not up */
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_err(pdsc->dev, "%s: called while adminq is unavailable\n",
 			__func__);
 		return;
 	}
@@ -124,6 +133,7 @@ credits:
 		pds_core_intr_credits(&pdsc->intr_ctrl[qcq->intx],
 				      credits,
 				      PDS_CORE_INTR_CRED_REARM);
+	refcount_dec(&pdsc->adminq_refcnt);
 }
 
 void pdsc_work_thread(struct work_struct *work)
@@ -138,9 +148,9 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 	struct pdsc *pdsc = data;
 	struct pdsc_qcq *qcq;
 
-	/* Don't process AdminQ when shutting down */
-	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
-		dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n",
+	/* Don't process AdminQ when it's not up */
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_err(pdsc->dev, "%s: called while adminq is unavailable\n",
 			__func__);
 		return IRQ_HANDLED;
 	}
@@ -148,6 +158,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 	qcq = &pdsc->adminqcq;
 	queue_work(pdsc->wq, &qcq->work);
 	pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
+	refcount_dec(&pdsc->adminq_refcnt);
 
 	return IRQ_HANDLED;
 }
@@ -231,6 +242,12 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	int err = 0;
 	int index;
 
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_dbg(pdsc->dev, "%s: preventing adminq cmd %u\n",
+			__func__, cmd->opcode);
+		return -ENXIO;
+	}
+
 	wc.qcq = &pdsc->adminqcq;
 	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
 	if (index < 0) {
@@ -286,6 +303,8 @@ err_out:
 			queue_work(pdsc->wq, &pdsc->health_work);
 	}
 
+	refcount_dec(&pdsc->adminq_refcnt);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(pdsc_adminq_post);
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 0356e56a6e99e..f44333bd1256e 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -450,6 +450,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 		pdsc_debugfs_add_viftype(pdsc);
 	}
 
+	refcount_set(&pdsc->adminq_refcnt, 1);
 	clear_bit(PDSC_S_FW_DEAD, &pdsc->state);
 	return 0;
 
@@ -514,6 +515,24 @@ void pdsc_stop(struct pdsc *pdsc)
 					   PDS_CORE_INTR_MASK_SET);
 }
 
+static void pdsc_adminq_wait_and_dec_once_unused(struct pdsc *pdsc)
+{
+	/* The driver initializes the adminq_refcnt to 1 when the adminq is
+	 * allocated and ready for use. Other users/requesters will increment
+	 * the refcnt while in use. If the refcnt is down to 1 then the adminq
+	 * is not in use and the refcnt can be cleared and adminq freed. Before
+	 * calling this function the driver will set PDSC_S_FW_DEAD, which
+	 * prevent subsequent attempts to use the adminq and increment the
+	 * refcnt to fail. This guarantees that this function will eventually
+	 * exit.
+	 */
+	while (!refcount_dec_if_one(&pdsc->adminq_refcnt)) {
+		dev_dbg_ratelimited(pdsc->dev, "%s: adminq in use\n",
+				    __func__);
+		cpu_relax();
+	}
+}
+
 void pdsc_fw_down(struct pdsc *pdsc)
 {
 	union pds_core_notifyq_comp reset_event = {
@@ -529,6 +548,8 @@ void pdsc_fw_down(struct pdsc *pdsc)
 	if (pdsc->pdev->is_virtfn)
 		return;
 
+	pdsc_adminq_wait_and_dec_once_unused(pdsc);
+
 	/* Notify clients of fw_down */
 	if (pdsc->fw_reporter)
 		devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index e35d3e7006bfc..cbd5716f46e69 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -184,6 +184,7 @@ struct pdsc {
 	struct mutex devcmd_lock;	/* lock for dev_cmd operations */
 	struct mutex config_lock;	/* lock for configuration operations */
 	spinlock_t adminq_lock;		/* lock for adminq operations */
+	refcount_t adminq_refcnt;
 	struct pds_core_dev_info_regs __iomem *info_regs;
 	struct pds_core_dev_cmd_regs __iomem *cmd_regs;
 	struct pds_core_intr __iomem *intr_ctrl;
-- 
GitLab


From e96094c1d11cce4deb5da3c0500d49041ab845b8 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Mon, 29 Jan 2024 15:40:34 -0800
Subject: [PATCH 3746/4076] pds_core: Clear BARs on reset

During reset the BARs might be accessed when they are
unmapped. This can cause unexpected issues, so fix it by
clearing the cached BAR values so they are not accessed
until they are re-mapped.

Also, make sure any places that can access the BARs
when they are NULL are prevented.

Fixes: 49ce92fbee0b ("pds_core: add FW update feature to devlink")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://lore.kernel.org/r/20240129234035.69802-6-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/adminq.c  | 28 +++++++++++++++------
 drivers/net/ethernet/amd/pds_core/core.c    |  8 +++++-
 drivers/net/ethernet/amd/pds_core/dev.c     |  9 ++++++-
 drivers/net/ethernet/amd/pds_core/devlink.c |  3 ++-
 drivers/net/ethernet/amd/pds_core/fw.c      |  3 +++
 drivers/net/ethernet/amd/pds_core/main.c    |  5 ++++
 6 files changed, 45 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index 5edff33d56f36..ea773cfa0af67 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -191,10 +191,16 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 
 	/* Check that the FW is running */
 	if (!pdsc_is_fw_running(pdsc)) {
-		u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
-
-		dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n",
-			 __func__, fw_status);
+		if (pdsc->info_regs) {
+			u8 fw_status =
+				ioread8(&pdsc->info_regs->fw_status);
+
+			dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n",
+				 __func__, fw_status);
+		} else {
+			dev_info(pdsc->dev, "%s: post failed - BARs not setup\n",
+				 __func__);
+		}
 		ret = -ENXIO;
 
 		goto err_out_unlock;
@@ -266,10 +272,16 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 			break;
 
 		if (!pdsc_is_fw_running(pdsc)) {
-			u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
-
-			dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n",
-				__func__, fw_status);
+			if (pdsc->info_regs) {
+				u8 fw_status =
+					ioread8(&pdsc->info_regs->fw_status);
+
+				dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n",
+					__func__, fw_status);
+			} else {
+				dev_dbg(pdsc->dev, "%s: post wait failed - BARs not setup\n",
+					__func__);
+			}
 			err = -ENXIO;
 			break;
 		}
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index f44333bd1256e..65c8a7072e354 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -600,7 +600,13 @@ err_out:
 
 static void pdsc_check_pci_health(struct pdsc *pdsc)
 {
-	u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
+	u8 fw_status;
+
+	/* some sort of teardown already in progress */
+	if (!pdsc->info_regs)
+		return;
+
+	fw_status = ioread8(&pdsc->info_regs->fw_status);
 
 	/* is PCI broken? */
 	if (fw_status != PDS_RC_BAD_PCI)
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index 31940b857e0e5..62a38e0a84546 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -57,6 +57,9 @@ int pdsc_err_to_errno(enum pds_core_status_code code)
 
 bool pdsc_is_fw_running(struct pdsc *pdsc)
 {
+	if (!pdsc->info_regs)
+		return false;
+
 	pdsc->fw_status = ioread8(&pdsc->info_regs->fw_status);
 	pdsc->last_fw_time = jiffies;
 	pdsc->last_hb = ioread32(&pdsc->info_regs->fw_heartbeat);
@@ -182,13 +185,17 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 {
 	int err;
 
+	if (!pdsc->cmd_regs)
+		return -ENXIO;
+
 	memcpy_toio(&pdsc->cmd_regs->cmd, cmd, sizeof(*cmd));
 	pdsc_devcmd_dbell(pdsc);
 	err = pdsc_devcmd_wait(pdsc, cmd->opcode, max_seconds);
-	memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	if ((err == -ENXIO || err == -ETIMEDOUT) && pdsc->wq)
 		queue_work(pdsc->wq, &pdsc->health_work);
+	else
+		memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	return err;
 }
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index e9948ea5bbcdb..54864f27c87a9 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -111,7 +111,8 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 
 	mutex_lock(&pdsc->devcmd_lock);
 	err = pdsc_devcmd_locked(pdsc, &cmd, &comp, pdsc->devcmd_timeout * 2);
-	memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
+	if (!err)
+		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
 	if (err && err != -EIO)
 		return err;
diff --git a/drivers/net/ethernet/amd/pds_core/fw.c b/drivers/net/ethernet/amd/pds_core/fw.c
index 90a811f3878ae..fa626719e68d1 100644
--- a/drivers/net/ethernet/amd/pds_core/fw.c
+++ b/drivers/net/ethernet/amd/pds_core/fw.c
@@ -107,6 +107,9 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw,
 
 	dev_info(pdsc->dev, "Installing firmware\n");
 
+	if (!pdsc->cmd_regs)
+		return -ENXIO;
+
 	dl = priv_to_devlink(pdsc);
 	devlink_flash_update_status_notify(dl, "Preparing to flash",
 					   NULL, 0, 0);
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 5172a5ad8ec6d..05fdeb235e5f1 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -37,6 +37,11 @@ static void pdsc_unmap_bars(struct pdsc *pdsc)
 	struct pdsc_dev_bar *bars = pdsc->bars;
 	unsigned int i;
 
+	pdsc->info_regs = NULL;
+	pdsc->cmd_regs = NULL;
+	pdsc->intr_status = NULL;
+	pdsc->intr_ctrl = NULL;
+
 	for (i = 0; i < PDS_CORE_BARS_MAX; i++) {
 		if (bars[i].vaddr)
 			pci_iounmap(pdsc->pdev, bars[i].vaddr);
-- 
GitLab


From bc90fbe0c3182157d2be100a2f6c2edbb1820677 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Mon, 29 Jan 2024 15:40:35 -0800
Subject: [PATCH 3747/4076] pds_core: Rework teardown/setup flow to be more
 common

Currently the teardown/setup flow for driver probe/remove is quite
a bit different from the reset flows in pdsc_fw_down()/pdsc_fw_up().
One key piece that's missing are the calls to pci_alloc_irq_vectors()
and pci_free_irq_vectors(). The pcie reset case is calling
pci_free_irq_vectors() on reset_prepare, but not calling the
corresponding pci_alloc_irq_vectors() on reset_done. This is causing
unexpected/unwanted interrupt behavior due to the adminq interrupt
being accidentally put into legacy interrupt mode. Also, the
pci_alloc_irq_vectors()/pci_free_irq_vectors() functions are being
called directly in probe/remove respectively.

Fix this inconsistency by making the following changes:
  1. Always call pdsc_dev_init() in pdsc_setup(), which calls
     pci_alloc_irq_vectors() and get rid of the now unused
     pds_dev_reinit().
  2. Always free/clear the pdsc->intr_info in pdsc_teardown()
     since this structure will get re-alloced in pdsc_setup().
  3. Move the calls of pci_free_irq_vectors() to pdsc_teardown()
     since pci_alloc_irq_vectors() will always be called in
     pdsc_setup()->pdsc_dev_init() for both the probe/remove and
     reset flows.
  4. Make sure to only create the debugfs "identity" entry when it
     doesn't already exist, which it will in the reset case because
     it's already been created in the initial call to pdsc_dev_init().

Fixes: ffa55858330f ("pds_core: implement pci reset handlers")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240129234035.69802-7-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/core.c    | 13 +++++--------
 drivers/net/ethernet/amd/pds_core/core.h    |  1 -
 drivers/net/ethernet/amd/pds_core/debugfs.c |  4 ++++
 drivers/net/ethernet/amd/pds_core/dev.c     |  7 -------
 drivers/net/ethernet/amd/pds_core/main.c    |  2 --
 5 files changed, 9 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 65c8a7072e354..7658a72867675 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -404,10 +404,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 	int numdescs;
 	int err;
 
-	if (init)
-		err = pdsc_dev_init(pdsc);
-	else
-		err = pdsc_dev_reinit(pdsc);
+	err = pdsc_dev_init(pdsc);
 	if (err)
 		return err;
 
@@ -479,10 +476,9 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 		for (i = 0; i < pdsc->nintrs; i++)
 			pdsc_intr_free(pdsc, i);
 
-		if (removing) {
-			kfree(pdsc->intr_info);
-			pdsc->intr_info = NULL;
-		}
+		kfree(pdsc->intr_info);
+		pdsc->intr_info = NULL;
+		pdsc->nintrs = 0;
 	}
 
 	if (pdsc->kern_dbpage) {
@@ -490,6 +486,7 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 		pdsc->kern_dbpage = NULL;
 	}
 
+	pci_free_irq_vectors(pdsc->pdev);
 	set_bit(PDSC_S_FW_DEAD, &pdsc->state);
 }
 
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index cbd5716f46e69..110c4b826b22d 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -281,7 +281,6 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 		       union pds_core_dev_comp *comp, int max_seconds);
 int pdsc_devcmd_init(struct pdsc *pdsc);
 int pdsc_devcmd_reset(struct pdsc *pdsc);
-int pdsc_dev_reinit(struct pdsc *pdsc);
 int pdsc_dev_init(struct pdsc *pdsc);
 
 void pdsc_reset_prepare(struct pci_dev *pdev);
diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index 8ec392299b7dc..4e8579ca1c8c7 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -64,6 +64,10 @@ DEFINE_SHOW_ATTRIBUTE(identity);
 
 void pdsc_debugfs_add_ident(struct pdsc *pdsc)
 {
+	/* This file will already exist in the reset flow */
+	if (debugfs_lookup("identity", pdsc->dentry))
+		return;
+
 	debugfs_create_file("identity", 0400, pdsc->dentry,
 			    pdsc, &identity_fops);
 }
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index 62a38e0a84546..e65a1632df505 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -316,13 +316,6 @@ static int pdsc_identify(struct pdsc *pdsc)
 	return 0;
 }
 
-int pdsc_dev_reinit(struct pdsc *pdsc)
-{
-	pdsc_init_devinfo(pdsc);
-
-	return pdsc_identify(pdsc);
-}
-
 int pdsc_dev_init(struct pdsc *pdsc)
 {
 	unsigned int nintrs;
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 05fdeb235e5f1..cdbf053b5376c 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -438,7 +438,6 @@ static void pdsc_remove(struct pci_dev *pdev)
 		mutex_destroy(&pdsc->config_lock);
 		mutex_destroy(&pdsc->devcmd_lock);
 
-		pci_free_irq_vectors(pdev);
 		pdsc_unmap_bars(pdsc);
 		pci_release_regions(pdev);
 	}
@@ -470,7 +469,6 @@ void pdsc_reset_prepare(struct pci_dev *pdev)
 	pdsc_stop_health_thread(pdsc);
 	pdsc_fw_down(pdsc);
 
-	pci_free_irq_vectors(pdev);
 	pdsc_unmap_bars(pdsc);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
-- 
GitLab


From f7c25d8e17dd759d97ca093faf92eeb7da7b3890 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 30 Jan 2024 18:47:16 +0100
Subject: [PATCH 3748/4076] selftests: net: add missing config for pmtu.sh
 tests

The mentioned test uses a few Kconfig still missing the
net config, add them.

Before:
  # Error: Specified qdisc kind is unknown.
  # Error: Specified qdisc kind is unknown.
  # Error: Qdisc not classful.
  # We have an error talking to the kernel
  # Error: Qdisc not classful.
  # We have an error talking to the kernel
  #   policy_routing not supported
  # TEST: ICMPv4 with DSCP and ECN: PMTU exceptions                     [SKIP]

After:
  # TEST: ICMPv4 with DSCP and ECN: PMTU exceptions                     [ OK ]

Fixes: ec730c3e1f0e ("selftest: net: Test IPv4 PMTU exceptions with DSCP and ECN")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/8d27bf6762a5c7b3acc457d6e6872c533040f9c1.1706635101.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 77a173635a29b..98c6bd2228c69 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -49,8 +49,10 @@ CONFIG_NF_TABLES_IPV6=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_NAT=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NET_ACT_CSUM=m
 CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GACT=m
+CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_BPF=m
 CONFIG_NET_CLS_MATCHALL=m
@@ -62,6 +64,7 @@ CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_PRIO=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NF_FLOW_TABLE=m
 CONFIG_PSAMPLE=m
-- 
GitLab


From e4e4b6d568d2549583cbda3f8ce567e586cb05da Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 30 Jan 2024 18:47:17 +0100
Subject: [PATCH 3749/4076] selftests: net: fix available tunnels detection

The pmtu.sh test tries to detect the tunnel protocols available
in the running kernel and properly skip the unsupported cases.

In a few more complex setup, such detection is unsuccessful, as
the script currently ignores some intermediate error code at
setup time.

Before:
  # which: no nettest in (/bin:/sbin:/usr/bin:/usr/sbin:/usr/local/bin)
  # TEST: vti6: PMTU exceptions (ESP-in-UDP)                            [FAIL]
  #   PMTU exception wasn't created after creating tunnel exceeding link layer MTU
  # ./pmtu.sh: line 931: kill: (7543) - No such process
  # ./pmtu.sh: line 931: kill: (7544) - No such process

After:
  #   xfrm4 not supported
  # TEST: vti4: PMTU exceptions                                         [SKIP]

Fixes: ece1278a9b81 ("selftests: net: add ESP-in-UDP PMTU test")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/cab10e75fda618e6fff8c595b632f47db58b9309.1706635101.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/pmtu.sh | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f10879788f61b..31892b366913c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -707,23 +707,23 @@ setup_xfrm6() {
 }
 
 setup_xfrm4udp() {
-	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 4 4500
+	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 4 4500
 }
 
 setup_xfrm6udp() {
-	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 6 4500
+	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 6 4500
 }
 
 setup_xfrm4udprouted() {
-	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 4 4500
+	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 4 4500
 }
 
 setup_xfrm6udprouted() {
-	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 6 4500
+	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 6 4500
 }
 
 setup_routing_old() {
-- 
GitLab


From bc0970d5ac1d1317e212bdf55533935ecb6ae95c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 30 Jan 2024 18:47:18 +0100
Subject: [PATCH 3750/4076] selftests: net: don't access /dev/stdout in pmtu.sh

When running the pmtu.sh via the kselftest infra, accessing
/dev/stdout gives unexpected results:
  # dd: failed to open '/dev/stdout': Device or resource busy
  # TEST: IPv4, bridged vxlan4: PMTU exceptions                         [FAIL]

Let dd use directly the standard output to fix the above:
  # TEST: IPv4, bridged vxlan4: PMTU exceptions - nexthop objects       [ OK ]

Fixes: 136a1b434bbb ("selftests: net: test vxlan pmtu exceptions with tcp")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/23d7592c5d77d75cff9b34f15c227f92e911c2ae.1706635101.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/pmtu.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 31892b366913c..3f118e3f1c66d 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1339,7 +1339,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
 
 		sleep 1
 
-		dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
+		dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
 
 		size=$(du -sb $tmpoutfile)
 		size=${size%%/tmp/*}
-- 
GitLab


From aa125f229076a8230a171d519dbdb2a862145d33 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 28 Jan 2024 10:23:09 +0200
Subject: [PATCH 3751/4076] wifi: iwlwifi: remove extra kernel-doc

This no longer exists, remove the kernel-doc.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240128102209.d2192d79bc09.Id9551728d618248dd471382a5283503a8976237a@changeid
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index e27774e7ed74d..80fda056e46a6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -19,7 +19,6 @@
  * @fwrt_ptr: pointer to the buffer coming from fwrt
  * @trans_ptr: pointer to struct %iwl_trans_dump_data which contains the
  *	transport's data.
- * @trans_len: length of the valid data in trans_ptr
  * @fwrt_len: length of the valid data in fwrt_ptr
  */
 struct iwl_fw_dump_ptrs {
-- 
GitLab


From f9c15a678db3acbe769635e3c49f979e2f88a514 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Roberto=20de=20Souza?= <jose.souza@intel.com>
Date: Wed, 24 Jan 2024 09:18:30 -0800
Subject: [PATCH 3752/4076] drm/xe: Fix crash in trace_dma_fence_init()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

trace_dma_fence_init() uses dma_fence_ops functions
like get_driver_name() and get_timeline_name() to generate trace
information but the Xe KMD implementation of those functions makes
use of xe_hw_fence_ctx that was being set after dma_fence_init().

So here just inverting the order to fix the crash.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240124171830.95774-1-jose.souza@intel.com
(cherry picked from commit c6878e47431c72168da08dfbc1496c09b2d3c246)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_hw_fence.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c
index a6094c81f2ad0..a5de3e7b0bd6a 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence.c
+++ b/drivers/gpu/drm/xe/xe_hw_fence.c
@@ -217,13 +217,13 @@ struct xe_hw_fence *xe_hw_fence_create(struct xe_hw_fence_ctx *ctx,
 	if (!fence)
 		return ERR_PTR(-ENOMEM);
 
-	dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
-		       ctx->dma_fence_ctx, ctx->next_seqno++);
-
 	fence->ctx = ctx;
 	fence->seqno_map = seqno_map;
 	INIT_LIST_HEAD(&fence->irq_link);
 
+	dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
+		       ctx->dma_fence_ctx, ctx->next_seqno++);
+
 	trace_xe_hw_fence_create(fence);
 
 	return fence;
-- 
GitLab


From 6d2096239af11f1c9fa03e8fc74400ce048078b0 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 26 Jan 2024 14:06:14 -0800
Subject: [PATCH 3753/4076] drm/xe: Grab mem_access when disabling C6 on
 skip_guc_pc platforms
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If skip_guc_pc is set for a platform, C6 is disabled directly without
acquiring a mem_access reference, triggering an assertion inside
xe_gt_idle_disable_c6.

Fixes: 975e4a3795d4 ("drm/xe: Manually setup C6 when skip_guc_pc is set")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126220613.865939-2-matthew.d.roper@intel.com
(cherry picked from commit 9f5971bdf78e0937206556534247243ad56cd735)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc_pc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index f71085228cb33..d91702592520a 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -963,7 +963,9 @@ void xe_guc_pc_fini(struct xe_guc_pc *pc)
 	struct xe_device *xe = pc_to_xe(pc);
 
 	if (xe->info.skip_guc_pc) {
+		xe_device_mem_access_get(xe);
 		xe_gt_idle_disable_c6(pc_to_gt(pc));
+		xe_device_mem_access_put(xe);
 		return;
 	}
 
-- 
GitLab


From efeff7b38ef62fc65069bd2200d151a9d5d38907 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 24 Jan 2024 15:44:13 -0800
Subject: [PATCH 3754/4076] drm/xe: Only allow 1 ufence per exec / bind IOCTL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The way exec ufences are coded only 1 ufence per IOCTL will be signaled.
It is possible to fix this but for current use cases 1 ufence per IOCTL
is sufficient. Enforce a limit of 1 ufence per IOCTL (both exec and bind
to be uniform).

v2:
- Add fixes tag (Thomas)

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Mika Kahola <mika.kahola@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Brian Welty <brian.welty@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240124234413.1640825-1-matthew.brost@intel.com
(cherry picked from commit d1df9bfbf68c65418f30917f406b6d5bd597714e)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_exec.c | 10 +++++++++-
 drivers/gpu/drm/xe/xe_sync.h |  5 +++++
 drivers/gpu/drm/xe/xe_vm.c   | 10 +++++++++-
 3 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index b853feed9ccc1..17f26952e6656 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -111,7 +111,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	u64 addresses[XE_HW_ENGINE_MAX_INSTANCE];
 	struct drm_gpuvm_exec vm_exec = {.extra.fn = xe_exec_fn};
 	struct drm_exec *exec = &vm_exec.exec;
-	u32 i, num_syncs = 0;
+	u32 i, num_syncs = 0, num_ufence = 0;
 	struct xe_sched_job *job;
 	struct dma_fence *rebind_fence;
 	struct xe_vm *vm;
@@ -157,6 +157,14 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 					   SYNC_PARSE_FLAG_LR_MODE : 0));
 		if (err)
 			goto err_syncs;
+
+		if (xe_sync_is_ufence(&syncs[i]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(xe, num_ufence > 1)) {
+		err = -EINVAL;
+		goto err_syncs;
 	}
 
 	if (xe_exec_queue_is_parallel(q)) {
diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h
index d284afbe917c1..f43cdcaca6c57 100644
--- a/drivers/gpu/drm/xe/xe_sync.h
+++ b/drivers/gpu/drm/xe/xe_sync.h
@@ -33,4 +33,9 @@ struct dma_fence *
 xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		     struct xe_exec_queue *q, struct xe_vm *vm);
 
+static inline bool xe_sync_is_ufence(struct xe_sync_entry *sync)
+{
+	return !!sync->ufence;
+}
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 53833ab81424c..32ae51945439a 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2851,7 +2851,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct drm_gpuva_ops **ops = NULL;
 	struct xe_vm *vm;
 	struct xe_exec_queue *q = NULL;
-	u32 num_syncs;
+	u32 num_syncs, num_ufence = 0;
 	struct xe_sync_entry *syncs = NULL;
 	struct drm_xe_vm_bind_op *bind_ops;
 	LIST_HEAD(ops_list);
@@ -2988,6 +2988,14 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 					   SYNC_PARSE_FLAG_DISALLOW_USER_FENCE : 0));
 		if (err)
 			goto free_syncs;
+
+		if (xe_sync_is_ufence(&syncs[num_syncs]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(xe, num_ufence > 1)) {
+		err = -EINVAL;
+		goto free_syncs;
 	}
 
 	if (!args->num_binds) {
-- 
GitLab


From 3ecf036b04b9dc72ca5bd62359748e14568fcf3f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Wed, 17 Jan 2024 14:40:46 +0100
Subject: [PATCH 3755/4076] drm/xe: Annotate mcr_[un]lock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These functions acquire and release the gt::mcr_lock. Annotate
accordingly.
Fix the corresponding sparse warning.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Fixes: fb1d55efdfcb ("drm/xe: Cleanup OPEN_BRACE style issues")
Cc: Francois Dugast <francois.dugast@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240117134048.165425-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit 97fd7a7e4e877676a2ab1a687ba958b70931abcc)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_gt_mcr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
index 77925b35cf8dc..8546cd3cc50d1 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.c
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
@@ -480,7 +480,7 @@ static bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt,
  * to synchronize with external clients (e.g., firmware), so a semaphore
  * register will also need to be taken.
  */
-static void mcr_lock(struct xe_gt *gt)
+static void mcr_lock(struct xe_gt *gt) __acquires(&gt->mcr_lock)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	int ret = 0;
@@ -500,7 +500,7 @@ static void mcr_lock(struct xe_gt *gt)
 	drm_WARN_ON_ONCE(&xe->drm, ret == -ETIMEDOUT);
 }
 
-static void mcr_unlock(struct xe_gt *gt)
+static void mcr_unlock(struct xe_gt *gt) __releases(&gt->mcr_lock)
 {
 	/* Release hardware semaphore - this is done by writing 1 to the register */
 	if (GRAPHICS_VERx100(gt_to_xe(gt)) >= 1270)
-- 
GitLab


From ef87557928d1ab3a1487520962f55cd7163e621b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Wed, 17 Jan 2024 14:40:47 +0100
Subject: [PATCH 3756/4076] drm/xe: Don't use __user error pointers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The error pointer macros are not aware of __user pointers and as a
consequence sparse warns.

Have the copy_mask() function return an integer instead of a __user
pointer.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240117134048.165425-5-thomas.hellstrom@linux.intel.com
(cherry picked from commit 78366eed6853aa6a5deccb2eb182f9334d2bd208)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_query.c | 50 +++++++++++++++++------------------
 1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 9b35673b286c8..7e924faeeea0b 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -459,21 +459,21 @@ static size_t calc_topo_query_size(struct xe_device *xe)
 		 sizeof_field(struct xe_gt, fuse_topo.eu_mask_per_dss));
 }
 
-static void __user *copy_mask(void __user *ptr,
-			      struct drm_xe_query_topology_mask *topo,
-			      void *mask, size_t mask_size)
+static int copy_mask(void __user **ptr,
+		     struct drm_xe_query_topology_mask *topo,
+		     void *mask, size_t mask_size)
 {
 	topo->num_bytes = mask_size;
 
-	if (copy_to_user(ptr, topo, sizeof(*topo)))
-		return ERR_PTR(-EFAULT);
-	ptr += sizeof(topo);
+	if (copy_to_user(*ptr, topo, sizeof(*topo)))
+		return -EFAULT;
+	*ptr += sizeof(topo);
 
-	if (copy_to_user(ptr, mask, mask_size))
-		return ERR_PTR(-EFAULT);
-	ptr += mask_size;
+	if (copy_to_user(*ptr, mask, mask_size))
+		return -EFAULT;
+	*ptr += mask_size;
 
-	return ptr;
+	return 0;
 }
 
 static int query_gt_topology(struct xe_device *xe,
@@ -493,28 +493,28 @@ static int query_gt_topology(struct xe_device *xe,
 	}
 
 	for_each_gt(gt, xe, id) {
+		int err;
+
 		topo.gt_id = id;
 
 		topo.type = DRM_XE_TOPO_DSS_GEOMETRY;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.g_dss_mask,
-				      sizeof(gt->fuse_topo.g_dss_mask));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.g_dss_mask,
+				sizeof(gt->fuse_topo.g_dss_mask));
+		if (err)
+			return err;
 
 		topo.type = DRM_XE_TOPO_DSS_COMPUTE;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.c_dss_mask,
-				      sizeof(gt->fuse_topo.c_dss_mask));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.c_dss_mask,
+				sizeof(gt->fuse_topo.c_dss_mask));
+		if (err)
+			return err;
 
 		topo.type = DRM_XE_TOPO_EU_PER_DSS;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.eu_mask_per_dss,
-				      sizeof(gt->fuse_topo.eu_mask_per_dss));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo,
+				gt->fuse_topo.eu_mask_per_dss,
+				sizeof(gt->fuse_topo.eu_mask_per_dss));
+		if (err)
+			return err;
 	}
 
 	return 0;
-- 
GitLab


From 89642db3b28849c23f42baadc88b40435ba6c5c6 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 23 Jan 2024 13:26:38 -0800
Subject: [PATCH 3757/4076] drm/xe: Use LRC prefix rather than CTX prefix in
 lrc desc defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sparc build fails [1] due to CTX_VALID being redefined. Fix this by
using a better naming convention of LRC_VALID as this define is used in
setting bits in the lrc descriptor. To be uniform, change other define
with LRC prefix too.

[1] https://lore.kernel.org/all/20240123111235.3097079-1-geert@linux-m68k.org/

v2:
- s/LEGACY_64B_CONTEXT/LRC_LEGACY_64B_CONTEXT (Lucas)

Fixes: 0bc519d20ffa ("drm/xe: Remove GEN[0-9]*_ prefixes")
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240123212638.1605626-1-matthew.brost@intel.com
(cherry picked from commit 152ca51d8db03f08a71c25e999812e263839fdce)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index b7fa3831b6845..0ec5ad2539f1b 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -21,10 +21,10 @@
 #include "xe_map.h"
 #include "xe_vm.h"
 
-#define CTX_VALID				(1 << 0)
-#define CTX_PRIVILEGE				(1 << 8)
-#define CTX_ADDRESSING_MODE_SHIFT		3
-#define LEGACY_64B_CONTEXT			3
+#define LRC_VALID				(1 << 0)
+#define LRC_PRIVILEGE				(1 << 8)
+#define LRC_ADDRESSING_MODE_SHIFT		3
+#define LRC_LEGACY_64B_CONTEXT			3
 
 #define ENGINE_CLASS_SHIFT			61
 #define ENGINE_INSTANCE_SHIFT			48
@@ -762,15 +762,15 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 				     (q->usm.acc_notify << ACC_NOTIFY_S) |
 				     q->usm.acc_trigger);
 
-	lrc->desc = CTX_VALID;
-	lrc->desc |= LEGACY_64B_CONTEXT << CTX_ADDRESSING_MODE_SHIFT;
+	lrc->desc = LRC_VALID;
+	lrc->desc |= LRC_LEGACY_64B_CONTEXT << LRC_ADDRESSING_MODE_SHIFT;
 	/* TODO: Priority */
 
 	/* While this appears to have something about privileged batches or
 	 * some such, it really just means PPGTT mode.
 	 */
 	if (vm)
-		lrc->desc |= CTX_PRIVILEGE;
+		lrc->desc |= LRC_PRIVILEGE;
 
 	if (GRAPHICS_VERx100(xe) < 1250) {
 		lrc->desc |= (u64)hwe->instance << ENGINE_INSTANCE_SHIFT;
-- 
GitLab


From ed2bdf3b264d627e1c2f26272660e1d7c2115000 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Wed, 31 Jan 2024 10:16:28 +0100
Subject: [PATCH 3758/4076] drm/xe/vm: Subclass userptr vmas
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The construct allocating only parts of the vma structure when
the userptr part is not needed is very fragile. A developer could
add additional fields below the userptr part, and the code could
easily attempt to access the userptr part even if its not persent.

So introduce xe_userptr_vma which subclasses struct xe_vma the
proper way, and accordingly modify a couple of interfaces.
This should also help if adding userptr helpers to drm_gpuvm.

v2:
- Fix documentation of to_userptr_vma() (Matthew Brost)
- Fix allocation and freeing of vmas to clearer distinguish
  between the types.

Closes: https://lore.kernel.org/intel-xe/0c4cc1a7-f409-4597-b110-81f9e45d1ffe@embeddedor.com/T/#u
Fixes: a4cc60a55fd9 ("drm/xe: Only alloc userptr part of xe_vma for userptrs")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240131091628.12318-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 5bd24e78829ad569fa1c3ce9a05b59bb97b91f3d)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_gt_pagefault.c |  11 +-
 drivers/gpu/drm/xe/xe_pt.c           |  32 +++---
 drivers/gpu/drm/xe/xe_vm.c           | 155 ++++++++++++++++-----------
 drivers/gpu/drm/xe/xe_vm.h           |  16 ++-
 drivers/gpu/drm/xe/xe_vm_types.h     |  16 +--
 5 files changed, 137 insertions(+), 93 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 59a70d2e0a7a3..9c2fe1697d6ee 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -165,7 +165,8 @@ retry_userptr:
 		goto unlock_vm;
 	}
 
-	if (!xe_vma_is_userptr(vma) || !xe_vma_userptr_check_repin(vma)) {
+	if (!xe_vma_is_userptr(vma) ||
+	    !xe_vma_userptr_check_repin(to_userptr_vma(vma))) {
 		downgrade_write(&vm->lock);
 		write_locked = false;
 	}
@@ -181,11 +182,13 @@ retry_userptr:
 	/* TODO: Validate fault */
 
 	if (xe_vma_is_userptr(vma) && write_locked) {
+		struct xe_userptr_vma *uvma = to_userptr_vma(vma);
+
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_del_init(&vma->userptr.invalidate_link);
+		list_del_init(&uvma->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 
-		ret = xe_vma_userptr_pin_pages(vma);
+		ret = xe_vma_userptr_pin_pages(uvma);
 		if (ret)
 			goto unlock_vm;
 
@@ -220,7 +223,7 @@ retry_userptr:
 	dma_fence_put(fence);
 
 	if (xe_vma_is_userptr(vma))
-		ret = xe_vma_userptr_check_repin(vma);
+		ret = xe_vma_userptr_check_repin(to_userptr_vma(vma));
 	vma->usm.tile_invalidated &= ~BIT(tile->id);
 
 unlock_dma_resv:
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index de1030a475883..e45b37c3f0c26 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -618,8 +618,8 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
 
 	if (!xe_vma_is_null(vma)) {
 		if (xe_vma_is_userptr(vma))
-			xe_res_first_sg(vma->userptr.sg, 0, xe_vma_size(vma),
-					&curs);
+			xe_res_first_sg(to_userptr_vma(vma)->userptr.sg, 0,
+					xe_vma_size(vma), &curs);
 		else if (xe_bo_is_vram(bo) || xe_bo_is_stolen(bo))
 			xe_res_first(bo->ttm.resource, xe_vma_bo_offset(vma),
 				     xe_vma_size(vma), &curs);
@@ -906,17 +906,17 @@ static void xe_vm_dbg_print_entries(struct xe_device *xe,
 
 #ifdef CONFIG_DRM_XE_USERPTR_INVAL_INJECT
 
-static int xe_pt_userptr_inject_eagain(struct xe_vma *vma)
+static int xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma)
 {
-	u32 divisor = vma->userptr.divisor ? vma->userptr.divisor : 2;
+	u32 divisor = uvma->userptr.divisor ? uvma->userptr.divisor : 2;
 	static u32 count;
 
 	if (count++ % divisor == divisor - 1) {
-		struct xe_vm *vm = xe_vma_vm(vma);
+		struct xe_vm *vm = xe_vma_vm(&uvma->vma);
 
-		vma->userptr.divisor = divisor << 1;
+		uvma->userptr.divisor = divisor << 1;
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&vma->userptr.invalidate_link,
+		list_move_tail(&uvma->userptr.invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 		return true;
@@ -927,7 +927,7 @@ static int xe_pt_userptr_inject_eagain(struct xe_vma *vma)
 
 #else
 
-static bool xe_pt_userptr_inject_eagain(struct xe_vma *vma)
+static bool xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma)
 {
 	return false;
 }
@@ -1000,9 +1000,9 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 {
 	struct xe_pt_migrate_pt_update *userptr_update =
 		container_of(pt_update, typeof(*userptr_update), base);
-	struct xe_vma *vma = pt_update->vma;
-	unsigned long notifier_seq = vma->userptr.notifier_seq;
-	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_userptr_vma *uvma = to_userptr_vma(pt_update->vma);
+	unsigned long notifier_seq = uvma->userptr.notifier_seq;
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
 	int err = xe_pt_vm_dependencies(pt_update->job,
 					&vm->rftree[pt_update->tile_id],
 					pt_update->start,
@@ -1023,7 +1023,7 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 	 */
 	do {
 		down_read(&vm->userptr.notifier_lock);
-		if (!mmu_interval_read_retry(&vma->userptr.notifier,
+		if (!mmu_interval_read_retry(&uvma->userptr.notifier,
 					     notifier_seq))
 			break;
 
@@ -1032,11 +1032,11 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 		if (userptr_update->bind)
 			return -EAGAIN;
 
-		notifier_seq = mmu_interval_read_begin(&vma->userptr.notifier);
+		notifier_seq = mmu_interval_read_begin(&uvma->userptr.notifier);
 	} while (true);
 
 	/* Inject errors to test_whether they are handled correctly */
-	if (userptr_update->bind && xe_pt_userptr_inject_eagain(vma)) {
+	if (userptr_update->bind && xe_pt_userptr_inject_eagain(uvma)) {
 		up_read(&vm->userptr.notifier_lock);
 		return -EAGAIN;
 	}
@@ -1297,7 +1297,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
 		vma->tile_present |= BIT(tile->id);
 
 		if (bind_pt_update.locked) {
-			vma->userptr.initial_bind = true;
+			to_userptr_vma(vma)->userptr.initial_bind = true;
 			up_read(&vm->userptr.notifier_lock);
 			xe_bo_put_commit(&deferred);
 		}
@@ -1642,7 +1642,7 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
 
 		if (!vma->tile_present) {
 			spin_lock(&vm->userptr.invalidated_lock);
-			list_del_init(&vma->userptr.invalidate_link);
+			list_del_init(&to_userptr_vma(vma)->userptr.invalidate_link);
 			spin_unlock(&vm->userptr.invalidated_lock);
 		}
 		up_read(&vm->userptr.notifier_lock);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 32ae51945439a..30db264d34a32 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -46,7 +46,7 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 
 /**
  * xe_vma_userptr_check_repin() - Advisory check for repin needed
- * @vma: The userptr vma
+ * @uvma: The userptr vma
  *
  * Check if the userptr vma has been invalidated since last successful
  * repin. The check is advisory only and can the function can be called
@@ -56,15 +56,17 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
  *
  * Return: 0 if userptr vma is valid, -EAGAIN otherwise; repin recommended.
  */
-int xe_vma_userptr_check_repin(struct xe_vma *vma)
+int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma)
 {
-	return mmu_interval_check_retry(&vma->userptr.notifier,
-					vma->userptr.notifier_seq) ?
+	return mmu_interval_check_retry(&uvma->userptr.notifier,
+					uvma->userptr.notifier_seq) ?
 		-EAGAIN : 0;
 }
 
-int xe_vma_userptr_pin_pages(struct xe_vma *vma)
+int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma)
 {
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vma *vma = &uvma->vma;
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct xe_device *xe = vm->xe;
 	const unsigned long num_pages = xe_vma_size(vma) >> PAGE_SHIFT;
@@ -80,30 +82,30 @@ retry:
 	if (vma->gpuva.flags & XE_VMA_DESTROYED)
 		return 0;
 
-	notifier_seq = mmu_interval_read_begin(&vma->userptr.notifier);
-	if (notifier_seq == vma->userptr.notifier_seq)
+	notifier_seq = mmu_interval_read_begin(&userptr->notifier);
+	if (notifier_seq == userptr->notifier_seq)
 		return 0;
 
 	pages = kvmalloc_array(num_pages, sizeof(*pages), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
 
-	if (vma->userptr.sg) {
+	if (userptr->sg) {
 		dma_unmap_sgtable(xe->drm.dev,
-				  vma->userptr.sg,
+				  userptr->sg,
 				  read_only ? DMA_TO_DEVICE :
 				  DMA_BIDIRECTIONAL, 0);
-		sg_free_table(vma->userptr.sg);
-		vma->userptr.sg = NULL;
+		sg_free_table(userptr->sg);
+		userptr->sg = NULL;
 	}
 
 	pinned = ret = 0;
 	if (in_kthread) {
-		if (!mmget_not_zero(vma->userptr.notifier.mm)) {
+		if (!mmget_not_zero(userptr->notifier.mm)) {
 			ret = -EFAULT;
 			goto mm_closed;
 		}
-		kthread_use_mm(vma->userptr.notifier.mm);
+		kthread_use_mm(userptr->notifier.mm);
 	}
 
 	while (pinned < num_pages) {
@@ -123,32 +125,32 @@ retry:
 	}
 
 	if (in_kthread) {
-		kthread_unuse_mm(vma->userptr.notifier.mm);
-		mmput(vma->userptr.notifier.mm);
+		kthread_unuse_mm(userptr->notifier.mm);
+		mmput(userptr->notifier.mm);
 	}
 mm_closed:
 	if (ret)
 		goto out;
 
-	ret = sg_alloc_table_from_pages_segment(&vma->userptr.sgt, pages,
+	ret = sg_alloc_table_from_pages_segment(&userptr->sgt, pages,
 						pinned, 0,
 						(u64)pinned << PAGE_SHIFT,
 						xe_sg_segment_size(xe->drm.dev),
 						GFP_KERNEL);
 	if (ret) {
-		vma->userptr.sg = NULL;
+		userptr->sg = NULL;
 		goto out;
 	}
-	vma->userptr.sg = &vma->userptr.sgt;
+	userptr->sg = &userptr->sgt;
 
-	ret = dma_map_sgtable(xe->drm.dev, vma->userptr.sg,
+	ret = dma_map_sgtable(xe->drm.dev, userptr->sg,
 			      read_only ? DMA_TO_DEVICE :
 			      DMA_BIDIRECTIONAL,
 			      DMA_ATTR_SKIP_CPU_SYNC |
 			      DMA_ATTR_NO_KERNEL_MAPPING);
 	if (ret) {
-		sg_free_table(vma->userptr.sg);
-		vma->userptr.sg = NULL;
+		sg_free_table(userptr->sg);
+		userptr->sg = NULL;
 		goto out;
 	}
 
@@ -167,8 +169,8 @@ out:
 	kvfree(pages);
 
 	if (!(ret < 0)) {
-		vma->userptr.notifier_seq = notifier_seq;
-		if (xe_vma_userptr_check_repin(vma) == -EAGAIN)
+		userptr->notifier_seq = notifier_seq;
+		if (xe_vma_userptr_check_repin(uvma) == -EAGAIN)
 			goto retry;
 	}
 
@@ -635,7 +637,9 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 				   const struct mmu_notifier_range *range,
 				   unsigned long cur_seq)
 {
-	struct xe_vma *vma = container_of(mni, struct xe_vma, userptr.notifier);
+	struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier);
+	struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr);
+	struct xe_vma *vma = &uvma->vma;
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
@@ -651,7 +655,7 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 	mmu_interval_set_seq(mni, cur_seq);
 
 	/* No need to stop gpu access if the userptr is not yet bound. */
-	if (!vma->userptr.initial_bind) {
+	if (!userptr->initial_bind) {
 		up_write(&vm->userptr.notifier_lock);
 		return true;
 	}
@@ -663,7 +667,7 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 	if (!xe_vm_in_fault_mode(vm) &&
 	    !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) {
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&vma->userptr.invalidate_link,
+		list_move_tail(&userptr->invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	}
@@ -703,7 +707,7 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = {
 
 int xe_vm_userptr_pin(struct xe_vm *vm)
 {
-	struct xe_vma *vma, *next;
+	struct xe_userptr_vma *uvma, *next;
 	int err = 0;
 	LIST_HEAD(tmp_evict);
 
@@ -711,22 +715,23 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 
 	/* Collect invalidated userptrs */
 	spin_lock(&vm->userptr.invalidated_lock);
-	list_for_each_entry_safe(vma, next, &vm->userptr.invalidated,
+	list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
 				 userptr.invalidate_link) {
-		list_del_init(&vma->userptr.invalidate_link);
-		list_move_tail(&vma->combined_links.userptr,
+		list_del_init(&uvma->userptr.invalidate_link);
+		list_move_tail(&uvma->userptr.repin_link,
 			       &vm->userptr.repin_list);
 	}
 	spin_unlock(&vm->userptr.invalidated_lock);
 
 	/* Pin and move to temporary list */
-	list_for_each_entry_safe(vma, next, &vm->userptr.repin_list,
-				 combined_links.userptr) {
-		err = xe_vma_userptr_pin_pages(vma);
+	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
+				 userptr.repin_link) {
+		err = xe_vma_userptr_pin_pages(uvma);
 		if (err < 0)
 			return err;
 
-		list_move_tail(&vma->combined_links.userptr, &vm->rebind_list);
+		list_del_init(&uvma->userptr.repin_link);
+		list_move_tail(&uvma->vma.combined_links.rebind, &vm->rebind_list);
 	}
 
 	return 0;
@@ -782,6 +787,14 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
 	return fence;
 }
 
+static void xe_vma_free(struct xe_vma *vma)
+{
+	if (xe_vma_is_userptr(vma))
+		kfree(to_userptr_vma(vma));
+	else
+		kfree(vma);
+}
+
 #define VMA_CREATE_FLAG_READ_ONLY	BIT(0)
 #define VMA_CREATE_FLAG_IS_NULL		BIT(1)
 
@@ -800,14 +813,26 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	xe_assert(vm->xe, start < end);
 	xe_assert(vm->xe, end < vm->size);
 
-	if (!bo && !is_null)	/* userptr */
+	/*
+	 * Allocate and ensure that the xe_vma_is_userptr() return
+	 * matches what was allocated.
+	 */
+	if (!bo && !is_null) {
+		struct xe_userptr_vma *uvma = kzalloc(sizeof(*uvma), GFP_KERNEL);
+
+		if (!uvma)
+			return ERR_PTR(-ENOMEM);
+
+		vma = &uvma->vma;
+	} else {
 		vma = kzalloc(sizeof(*vma), GFP_KERNEL);
-	else
-		vma = kzalloc(sizeof(*vma) - sizeof(struct xe_userptr),
-			      GFP_KERNEL);
-	if (!vma) {
-		vma = ERR_PTR(-ENOMEM);
-		return vma;
+		if (!vma)
+			return ERR_PTR(-ENOMEM);
+
+		if (is_null)
+			vma->gpuva.flags |= DRM_GPUVA_SPARSE;
+		if (bo)
+			vma->gpuva.gem.obj = &bo->ttm.base;
 	}
 
 	INIT_LIST_HEAD(&vma->combined_links.rebind);
@@ -818,8 +843,6 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	vma->gpuva.va.range = end - start + 1;
 	if (read_only)
 		vma->gpuva.flags |= XE_VMA_READ_ONLY;
-	if (is_null)
-		vma->gpuva.flags |= DRM_GPUVA_SPARSE;
 
 	for_each_tile(tile, vm->xe, id)
 		vma->tile_mask |= 0x1 << id;
@@ -836,35 +859,35 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 
 		vm_bo = drm_gpuvm_bo_obtain(vma->gpuva.vm, &bo->ttm.base);
 		if (IS_ERR(vm_bo)) {
-			kfree(vma);
+			xe_vma_free(vma);
 			return ERR_CAST(vm_bo);
 		}
 
 		drm_gpuvm_bo_extobj_add(vm_bo);
 		drm_gem_object_get(&bo->ttm.base);
-		vma->gpuva.gem.obj = &bo->ttm.base;
 		vma->gpuva.gem.offset = bo_offset_or_userptr;
 		drm_gpuva_link(&vma->gpuva, vm_bo);
 		drm_gpuvm_bo_put(vm_bo);
 	} else /* userptr or null */ {
 		if (!is_null) {
+			struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
 			u64 size = end - start + 1;
 			int err;
 
-			INIT_LIST_HEAD(&vma->userptr.invalidate_link);
+			INIT_LIST_HEAD(&userptr->invalidate_link);
+			INIT_LIST_HEAD(&userptr->repin_link);
 			vma->gpuva.gem.offset = bo_offset_or_userptr;
 
-			err = mmu_interval_notifier_insert(&vma->userptr.notifier,
+			err = mmu_interval_notifier_insert(&userptr->notifier,
 							   current->mm,
 							   xe_vma_userptr(vma), size,
 							   &vma_userptr_notifier_ops);
 			if (err) {
-				kfree(vma);
-				vma = ERR_PTR(err);
-				return vma;
+				xe_vma_free(vma);
+				return ERR_PTR(err);
 			}
 
-			vma->userptr.notifier_seq = LONG_MAX;
+			userptr->notifier_seq = LONG_MAX;
 		}
 
 		xe_vm_get(vm);
@@ -880,13 +903,15 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 	bool read_only = xe_vma_read_only(vma);
 
 	if (xe_vma_is_userptr(vma)) {
-		if (vma->userptr.sg) {
+		struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
+
+		if (userptr->sg) {
 			dma_unmap_sgtable(xe->drm.dev,
-					  vma->userptr.sg,
+					  userptr->sg,
 					  read_only ? DMA_TO_DEVICE :
 					  DMA_BIDIRECTIONAL, 0);
-			sg_free_table(vma->userptr.sg);
-			vma->userptr.sg = NULL;
+			sg_free_table(userptr->sg);
+			userptr->sg = NULL;
 		}
 
 		/*
@@ -894,7 +919,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		 * the notifer until we're sure the GPU is not accessing
 		 * them anymore
 		 */
-		mmu_interval_notifier_remove(&vma->userptr.notifier);
+		mmu_interval_notifier_remove(&userptr->notifier);
 		xe_vm_put(vm);
 	} else if (xe_vma_is_null(vma)) {
 		xe_vm_put(vm);
@@ -902,7 +927,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		xe_bo_put(xe_vma_bo(vma));
 	}
 
-	kfree(vma);
+	xe_vma_free(vma);
 }
 
 static void vma_destroy_work_func(struct work_struct *w)
@@ -933,7 +958,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 		xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
 
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_del(&vma->userptr.invalidate_link);
+		list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	} else if (!xe_vma_is_null(vma)) {
 		xe_bo_assert_held(xe_vma_bo(vma));
@@ -2150,7 +2175,7 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op,
 		drm_exec_fini(&exec);
 
 	if (xe_vma_is_userptr(vma)) {
-		err = xe_vma_userptr_pin_pages(vma);
+		err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
 		if (err) {
 			prep_vma_destroy(vm, vma, false);
 			xe_vma_destroy_unlocked(vma);
@@ -2507,7 +2532,7 @@ retry_userptr:
 
 	if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
 		lockdep_assert_held_write(&vm->lock);
-		err = xe_vma_userptr_pin_pages(vma);
+		err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
 		if (!err)
 			goto retry_userptr;
 
@@ -3138,8 +3163,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
 		if (xe_vma_is_userptr(vma)) {
 			WARN_ON_ONCE(!mmu_interval_check_retry
-				     (&vma->userptr.notifier,
-				      vma->userptr.notifier_seq));
+				     (&to_userptr_vma(vma)->userptr.notifier,
+				      to_userptr_vma(vma)->userptr.notifier_seq));
 			WARN_ON_ONCE(!dma_resv_test_signaled(xe_vm_resv(xe_vma_vm(vma)),
 							     DMA_RESV_USAGE_BOOKKEEP));
 
@@ -3200,11 +3225,11 @@ int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id)
 		if (is_null) {
 			addr = 0;
 		} else if (is_userptr) {
+			struct sg_table *sg = to_userptr_vma(vma)->userptr.sg;
 			struct xe_res_cursor cur;
 
-			if (vma->userptr.sg) {
-				xe_res_first_sg(vma->userptr.sg, 0, XE_PAGE_SIZE,
-						&cur);
+			if (sg) {
+				xe_res_first_sg(sg, 0, XE_PAGE_SIZE, &cur);
 				addr = xe_res_dma(&cur);
 			} else {
 				addr = 0;
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index cf2f96e8c1ab9..9654a0612fc25 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -160,6 +160,18 @@ static inline bool xe_vma_is_userptr(struct xe_vma *vma)
 	return xe_vma_has_no_bo(vma) && !xe_vma_is_null(vma);
 }
 
+/**
+ * to_userptr_vma() - Return a pointer to an embedding userptr vma
+ * @vma: Pointer to the embedded struct xe_vma
+ *
+ * Return: Pointer to the embedding userptr vma
+ */
+static inline struct xe_userptr_vma *to_userptr_vma(struct xe_vma *vma)
+{
+	xe_assert(xe_vma_vm(vma)->xe, xe_vma_is_userptr(vma));
+	return container_of(vma, struct xe_userptr_vma, vma);
+}
+
 u64 xe_vm_pdp4_descriptor(struct xe_vm *vm, struct xe_tile *tile);
 
 int xe_vm_create_ioctl(struct drm_device *dev, void *data,
@@ -224,9 +236,9 @@ static inline void xe_vm_reactivate_rebind(struct xe_vm *vm)
 	}
 }
 
-int xe_vma_userptr_pin_pages(struct xe_vma *vma);
+int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma);
 
-int xe_vma_userptr_check_repin(struct xe_vma *vma);
+int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma);
 
 bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end);
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 63e8a50b88e94..1fec66ae2eb2d 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -37,6 +37,8 @@ struct xe_vm;
 struct xe_userptr {
 	/** @invalidate_link: Link for the vm::userptr.invalidated list */
 	struct list_head invalidate_link;
+	/** @userptr: link into VM repin list if userptr. */
+	struct list_head repin_link;
 	/**
 	 * @notifier: MMU notifier for user pointer (invalidation call back)
 	 */
@@ -68,8 +70,6 @@ struct xe_vma {
 	 * resv.
 	 */
 	union {
-		/** @userptr: link into VM repin list if userptr. */
-		struct list_head userptr;
 		/** @rebind: link into VM if this VMA needs rebinding. */
 		struct list_head rebind;
 		/** @destroy: link to contested list when VM is being closed. */
@@ -105,11 +105,15 @@ struct xe_vma {
 	 * @pat_index: The pat index to use when encoding the PTEs for this vma.
 	 */
 	u16 pat_index;
+};
 
-	/**
-	 * @userptr: user pointer state, only allocated for VMAs that are
-	 * user pointers
-	 */
+/**
+ * struct xe_userptr_vma - A userptr vma subclass
+ * @vma: The vma.
+ * @userptr: Additional userptr information.
+ */
+struct xe_userptr_vma {
+	struct xe_vma vma;
 	struct xe_userptr userptr;
 };
 
-- 
GitLab


From c9cfed29f5fe13f97e46c3879517d8c41ae251d6 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 30 Jan 2024 18:54:24 -0800
Subject: [PATCH 3759/4076] drm/xe: Make all GuC ABI shift values unsigned
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All GuC ABI definitions are unsigned and not defining as unsigned is
causing build errors [1].

[1] https://lore.kernel.org/all/20240123111235.3097079-1-geert@linux-m68k.org/

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240131025424.2087936-1-matthew.brost@intel.com
(cherry picked from commit d83d8ae275c6bf87506b71b8a1acd98452137dc5)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/abi/guc_actions_abi.h      |  4 ++--
 drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h |  4 ++--
 .../drm/xe/abi/guc_communication_ctb_abi.h    |  8 ++++----
 drivers/gpu/drm/xe/abi/guc_klvs_abi.h         |  6 +++---
 drivers/gpu/drm/xe/abi/guc_messages_abi.h     | 20 +++++++++----------
 5 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
index 3062e0e0d467e..79ba98a169f90 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
@@ -50,8 +50,8 @@
 
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 3u)
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffff << 16)
-#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffff << 0)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffffu << 16)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffffu << 0)
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32		GUC_HXG_REQUEST_MSG_n_DATAn
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64		GUC_HXG_REQUEST_MSG_n_DATAn
 
diff --git a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
index 811add10c30dc..c165e26c09766 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
@@ -242,8 +242,8 @@ struct slpc_shared_data {
 		(HOST2GUC_PC_SLPC_REQUEST_REQUEST_MSG_MIN_LEN + \
 			HOST2GUC_PC_SLPC_EVENT_MAX_INPUT_ARGS)
 #define HOST2GUC_PC_SLPC_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xff << 8)
-#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xff << 0)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xffu << 8)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xffu << 0)
 #define HOST2GUC_PC_SLPC_REQUEST_MSG_N_EVENT_DATA_N	GUC_HXG_REQUEST_MSG_n_DATAn
 
 #endif
diff --git a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
index 3b83f907ece46..0b1146d0c997a 100644
--- a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
@@ -82,11 +82,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64);
 #define GUC_CTB_HDR_LEN				1u
 #define GUC_CTB_MSG_MIN_LEN			GUC_CTB_HDR_LEN
 #define GUC_CTB_MSG_MAX_LEN			256u
-#define GUC_CTB_MSG_0_FENCE			(0xffff << 16)
-#define GUC_CTB_MSG_0_FORMAT			(0xf << 12)
+#define GUC_CTB_MSG_0_FENCE			(0xffffu << 16)
+#define GUC_CTB_MSG_0_FORMAT			(0xfu << 12)
 #define   GUC_CTB_FORMAT_HXG			0u
-#define GUC_CTB_MSG_0_RESERVED			(0xf << 8)
-#define GUC_CTB_MSG_0_NUM_DWORDS		(0xff << 0)
+#define GUC_CTB_MSG_0_RESERVED			(0xfu << 8)
+#define GUC_CTB_MSG_0_NUM_DWORDS		(0xffu << 0)
 
 /**
  * DOC: CTB HXG Message
diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 47094b9b044cb..0400bc0fccdc9 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -31,9 +31,9 @@
  */
 
 #define GUC_KLV_LEN_MIN				1u
-#define GUC_KLV_0_KEY				(0xffff << 16)
-#define GUC_KLV_0_LEN				(0xffff << 0)
-#define GUC_KLV_n_VALUE				(0xffffffff << 0)
+#define GUC_KLV_0_KEY				(0xffffu << 16)
+#define GUC_KLV_0_LEN				(0xffffu << 0)
+#define GUC_KLV_n_VALUE				(0xffffffffu << 0)
 
 /**
  * DOC: GuC Self Config KLVs
diff --git a/drivers/gpu/drm/xe/abi/guc_messages_abi.h b/drivers/gpu/drm/xe/abi/guc_messages_abi.h
index 3d199016cf881..29e414c82d56c 100644
--- a/drivers/gpu/drm/xe/abi/guc_messages_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_messages_abi.h
@@ -40,18 +40,18 @@
  */
 
 #define GUC_HXG_MSG_MIN_LEN			1u
-#define GUC_HXG_MSG_0_ORIGIN			(0x1 << 31)
+#define GUC_HXG_MSG_0_ORIGIN			(0x1u << 31)
 #define   GUC_HXG_ORIGIN_HOST			0u
 #define   GUC_HXG_ORIGIN_GUC			1u
-#define GUC_HXG_MSG_0_TYPE			(0x7 << 28)
+#define GUC_HXG_MSG_0_TYPE			(0x7u << 28)
 #define   GUC_HXG_TYPE_REQUEST			0u
 #define   GUC_HXG_TYPE_EVENT			1u
 #define   GUC_HXG_TYPE_NO_RESPONSE_BUSY		3u
 #define   GUC_HXG_TYPE_NO_RESPONSE_RETRY	5u
 #define   GUC_HXG_TYPE_RESPONSE_FAILURE		6u
 #define   GUC_HXG_TYPE_RESPONSE_SUCCESS		7u
-#define GUC_HXG_MSG_0_AUX			(0xfffffff << 0)
-#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffff << 0)
+#define GUC_HXG_MSG_0_AUX			(0xfffffffu << 0)
+#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffffu << 0)
 
 /**
  * DOC: HXG Request
@@ -85,8 +85,8 @@
  */
 
 #define GUC_HXG_REQUEST_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfff << 16)
-#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfffu << 16)
+#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffffu << 0)
 #define GUC_HXG_REQUEST_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
 
 /**
@@ -117,8 +117,8 @@
  */
 
 #define GUC_HXG_EVENT_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfff << 16)
-#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfffu << 16)
+#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffffu << 0)
 #define GUC_HXG_EVENT_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
 
 /**
@@ -188,8 +188,8 @@
  */
 
 #define GUC_HXG_FAILURE_MSG_LEN			GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfff << 16)
-#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffff << 0)
+#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfffu << 16)
+#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffffu << 0)
 
 /**
  * DOC: HXG Response
-- 
GitLab


From 5f16ee27cd5abd5166e28b2311ac693c204063ff Mon Sep 17 00:00:00 2001
From: Badal Nilawar <badal.nilawar@intel.com>
Date: Sat, 27 Jan 2024 22:20:40 +0530
Subject: [PATCH 3760/4076] drm/hwmon: Fix abi doc warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes warnings in xe, i915 hwmon docs:

Warning: /sys/devices/.../hwmon/hwmon<i>/curr1_crit is defined 2 times:  Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon:35  Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon:52
Warning: /sys/devices/.../hwmon/hwmon<i>/energy1_input is defined 2 times:  Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon:54  Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon:65
Warning: /sys/devices/.../hwmon/hwmon<i>/in0_input is defined 2 times:  Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon:46  Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon:0
Warning: /sys/devices/.../hwmon/hwmon<i>/power1_crit is defined 2 times:  Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon:22  Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon:39
Warning: /sys/devices/.../hwmon/hwmon<i>/power1_max is defined 2 times:  Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon:0  Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon:8
Warning: /sys/devices/.../hwmon/hwmon<i>/power1_max_interval is defined 2 times:  Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon:62  Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon:30
Warning: /sys/devices/.../hwmon/hwmon<i>/power1_rated_max is defined 2 times:  Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon:14  Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon:22

Use a path containing the driver name to differentiate the documentation
of each entry.

Fixes: fb1b70607f73 ("drm/xe/hwmon: Expose power attributes")
Fixes: 92d44a422d0d ("drm/xe/hwmon: Expose card reactive critical power")
Fixes: fbcdc9d3bf58 ("drm/xe/hwmon: Expose input voltage attribute")
Fixes: 71d0a32524f9 ("drm/xe/hwmon: Expose hwmon energy attribute")
Fixes: 4446fcf220ce ("drm/xe/hwmon: Expose power1_max_interval")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/all/20240125113345.291118ff@canb.auug.org.au/
Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240127165040.2348009-1-badal.nilawar@intel.com
(cherry picked from commit 20485e3a810c480cef60caf53988619f61127e7b)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 .../ABI/testing/sysfs-driver-intel-i915-hwmon      | 14 +++++++-------
 .../ABI/testing/sysfs-driver-intel-xe-hwmon        | 14 +++++++-------
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
index 8d7d8f05f6cd0..92fe7c5c5ac1d 100644
--- a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
+++ b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
@@ -1,4 +1,4 @@
-What:		/sys/devices/.../hwmon/hwmon<i>/in0_input
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/in0_input
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -6,7 +6,7 @@ Description:	RO. Current Voltage in millivolt.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_max
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -20,7 +20,7 @@ Description:	RW. Card reactive sustained  (PL1/Tau) power limit in microwatts.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_rated_max
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_rated_max
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -28,7 +28,7 @@ Description:	RO. Card default power limit (default TDP setting).
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max_interval
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_max_interval
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -37,7 +37,7 @@ Description:	RW. Sustained power limit interval (Tau in PL1/Tau) in
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_crit
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_crit
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -50,7 +50,7 @@ Description:	RW. Card reactive critical (I1) power limit in microwatts.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/curr1_crit
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/curr1_crit
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -63,7 +63,7 @@ Description:	RW. Card reactive critical (I1) power limit in milliamperes.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/energy1_input
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/energy1_input
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
diff --git a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
index 8c321bc9dc044..023fd82de3f70 100644
--- a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
+++ b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
@@ -1,4 +1,4 @@
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_max
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -12,7 +12,7 @@ Description:	RW. Card reactive sustained  (PL1) power limit in microwatts.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_rated_max
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_rated_max
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -20,7 +20,7 @@ Description:	RO. Card default power limit (default TDP setting).
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_crit
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_crit
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -33,7 +33,7 @@ Description:	RW. Card reactive critical (I1) power limit in microwatts.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/curr1_crit
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/curr1_crit
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -44,7 +44,7 @@ Description:	RW. Card reactive critical (I1) power limit in milliamperes.
 		the operating frequency if the power averaged over a window
 		exceeds this limit.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/in0_input
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/in0_input
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -52,7 +52,7 @@ Description:	RO. Current Voltage in millivolt.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/energy1_input
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/energy1_input
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -60,7 +60,7 @@ Description:	RO. Energy input of device in microjoules.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max_interval
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_max_interval
 Date:		October 2023
 KernelVersion:	6.6
 Contact:	intel-xe@lists.freedesktop.org
-- 
GitLab


From 5f9ab17394f831cb7986ec50900fa37507a127f1 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Thu, 1 Feb 2024 20:53:18 +0900
Subject: [PATCH 3761/4076] firewire: core: correct documentation of
 fw_csr_string() kernel API

Against its current description, the kernel API can accepts all types of
directory entries.

This commit corrects the documentation.

Cc: stable@vger.kernel.org
Fixes: 3c2c58cb33b3 ("firewire: core: fw_csr_string addendum")
Link: https://lore.kernel.org/r/20240130100409.30128-2-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/core-device.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index 0547253d16fe5..e4cb5106fb7d1 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -118,10 +118,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size)
  * @buf:	where to put the string
  * @size:	size of @buf, in bytes
  *
- * The string is taken from a minimal ASCII text descriptor leaf after
- * the immediate entry with @key.  The string is zero-terminated.
- * An overlong string is silently truncated such that it and the
- * zero byte fit into @size.
+ * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the
+ * @key. The string is zero-terminated. An overlong string is silently truncated such that it
+ * and the zero byte fit into @size.
  *
  * Returns strlen(buf) or a negative error code.
  */
-- 
GitLab


From 47dc55181dcbee69fc84c902e7fb060213b9b8a5 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Thu, 1 Feb 2024 20:53:18 +0900
Subject: [PATCH 3762/4076] firewire: core: search descriptor leaf just after
 vendor directory entry in root directory

It appears that Sony DVMC-DA1 has a quirk that the descriptor leaf entry
locates just after the vendor directory entry in root directory. This is
not conformant to the legacy layout of configuration ROM described in
Configuration ROM for AV/C Devices 1.0 (1394 Trading Association, Dec 2000,
TA Document 1999027).

This commit changes current implementation to parse configuration ROM for
device attributes so that the descriptor leaf entry can be detected for
the vendor name.

$ config-rom-pretty-printer < Sony-DVMC-DA1.img
               ROM header and bus information block
               -----------------------------------------------------------------
1024  041ee7fb  bus_info_length 4, crc_length 30, crc 59387
1028  31333934  bus_name "1394"
1032  e0644000  irmc 1, cmc 1, isc 1, bmc 0, cyc_clk_acc 100, max_rec 4 (32)
1036  08004603  company_id 080046     |
1040  0014193c  device_id 12886219068  | EUI-64 576537731003586876

               root directory
               -----------------------------------------------------------------
1044  0006b681  directory_length 6, crc 46721
1048  03080046  vendor
1052  0c0083c0  node capabilities: per IEEE 1394
1056  8d00000a  --> eui-64 leaf at 1096
1060  d1000003  --> unit directory at 1072
1064  c3000005  --> vendor directory at 1084
1068  8100000a  --> descriptor leaf at 1108

               unit directory at 1072
               -----------------------------------------------------------------
1072  0002cdbf  directory_length 2, crc 52671
1076  1200a02d  specifier id
1080  13010000  version

               vendor directory at 1084
               -----------------------------------------------------------------
1084  00020cfe  directory_length 2, crc 3326
1088  17fa0000  model
1092  81000008  --> descriptor leaf at 1124

               eui-64 leaf at 1096
               -----------------------------------------------------------------
1096  0002c66e  leaf_length 2, crc 50798
1100  08004603  company_id 080046     |
1104  0014193c  device_id 12886219068  | EUI-64 576537731003586876

               descriptor leaf at 1108
               -----------------------------------------------------------------
1108  00039e26  leaf_length 3, crc 40486
1112  00000000  textual descriptor
1116  00000000  minimal ASCII
1120  536f6e79  "Sony"

               descriptor leaf at 1124
               -----------------------------------------------------------------
1124  0005001d  leaf_length 5, crc 29
1128  00000000  textual descriptor
1132  00000000  minimal ASCII
1136  44564d43  "DVMC"
1140  2d444131  "-DA1"
1144  00000000

Suggested-by: Adam Goldman <adamg@pobox.com>
Tested-by: Adam Goldman <adamg@pobox.com>
Link: https://lore.kernel.org/r/20240130100409.30128-3-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/core-device.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index e4cb5106fb7d1..7d3346b3a2bf3 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -367,8 +367,17 @@ static ssize_t show_text_leaf(struct device *dev,
 	for (i = 0; i < ARRAY_SIZE(directories) && !!directories[i]; ++i) {
 		int result = fw_csr_string(directories[i], attr->key, buf, bufsize);
 		// Detected.
-		if (result >= 0)
+		if (result >= 0) {
 			ret = result;
+		} else if (i == 0 && attr->key == CSR_VENDOR) {
+			// Sony DVMC-DA1 has configuration ROM such that the descriptor leaf entry
+			// in the root directory follows to the directory entry for vendor ID
+			// instead of the immediate value for vendor ID.
+			result = fw_csr_string(directories[i], CSR_DIRECTORY | attr->key, buf,
+					       bufsize);
+			if (result >= 0)
+				ret = result;
+		}
 	}
 
 	if (ret >= 0) {
-- 
GitLab


From 83b3836bf83f09beea5f592b126cfdd1bc921e48 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 30 Jan 2024 12:12:53 -0400
Subject: [PATCH 3763/4076] iommu: Allow ops->default_domain to work when
 !CONFIG_IOMMU_DMA

The ops->default_domain flow used a 0 req_type to select the default
domain and this was enforced by iommu_group_alloc_default_domain().

When !CONFIG_IOMMU_DMA started forcing the old ARM32 drivers into IDENTITY
it also overroad the 0 req_type of the ops->default_domain drivers to
IDENTITY which ends up causing failures during device probe.

Make iommu_group_alloc_default_domain() accept a req_type that matches the
ops->default_domain and have iommu_group_alloc_default_domain() generate a
req_type that matches the default_domain.

This way the req_type always describes what kind of domain should be
attached and ops->default_domain overrides all other mechanisms to choose
the default domain.

Fixes: 2ad56efa80db ("powerpc/iommu: Setup a default domain and remove set_platform_dma_ops")
Fixes: 0f6a90436a57 ("iommu: Do not use IOMMU_DOMAIN_DMA if CONFIG_IOMMU_DMA is not enabled")
Reported-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Closes: https://lore.kernel.org/linux-iommu/20240123165829.630276-1-ovidiu.panait@windriver.com/
Reported-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Closes: https://lore.kernel.org/linux-iommu/170618452753.3805.4425669653666211728.stgit@ltcd48-lp2.aus.stglab.ibm.com/
Tested-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/0-v1-755bd21c4a64+525b8-iommu_def_dom_fix_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 68e648b557670..d14413916f93a 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1799,7 +1799,7 @@ iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 	 * domain. Do not use in new drivers.
 	 */
 	if (ops->default_domain) {
-		if (req_type)
+		if (req_type != ops->default_domain->type)
 			return ERR_PTR(-EINVAL);
 		return ops->default_domain;
 	}
@@ -1871,10 +1871,18 @@ static int iommu_get_def_domain_type(struct iommu_group *group,
 	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	int type;
 
-	if (!ops->def_domain_type)
-		return cur_type;
-
-	type = ops->def_domain_type(dev);
+	if (ops->default_domain) {
+		/*
+		 * Drivers that declare a global static default_domain will
+		 * always choose that.
+		 */
+		type = ops->default_domain->type;
+	} else {
+		if (ops->def_domain_type)
+			type = ops->def_domain_type(dev);
+		else
+			return cur_type;
+	}
 	if (!type || cur_type == type)
 		return cur_type;
 	if (!cur_type)
-- 
GitLab


From fae6e669cdc52fdbb843e7fb1b8419642b6b8cba Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 30 Jan 2024 12:14:54 -0400
Subject: [PATCH 3764/4076] drm/tegra: Do not assume that a NULL domain means
 no DMA IOMMU

Previously with tegra-smmu, even with CONFIG_IOMMU_DMA, the default domain
could have been left as NULL. The NULL domain is specially recognized by
host1x_client_iommu_attach() as meaning it is not the DMA domain and
should be replaced with the special shared domain.

This happened prior to the below commit because tegra-smmu was using the
NULL domain to mean IDENTITY.

Now that the domain is properly labled the test in DRM doesn't see NULL.
Check for IDENTITY as well to enable the special domains.

Fixes: c8cc2655cc6c ("iommu/tegra-smmu: Implement an IDENTITY domain")
Reported-by: diogo.ivo@tecnico.ulisboa.pt
Closes: https://lore.kernel.org/all/bbmhcoghrprmbdibnjum6lefix2eoquxrde7wyqeulm4xabmlm@b6jy32saugqh/
Tested-by: diogo.ivo@tecnico.ulisboa.pt
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/0-v1-3049f92c4812+16691-host1x_def_dom_fix_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/gpu/drm/tegra/drm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index ff36171c8fb70..a73cff7a30708 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -960,7 +960,8 @@ int host1x_client_iommu_attach(struct host1x_client *client)
 	 * not the shared IOMMU domain, don't try to attach it to a different
 	 * domain. This allows using the IOMMU-backed DMA API.
 	 */
-	if (domain && domain != tegra->domain)
+	if (domain && domain->type != IOMMU_DOMAIN_IDENTITY &&
+	    domain != tegra->domain)
 		return 0;
 
 	if (tegra->domain) {
-- 
GitLab


From 3657e4cb5a8abd9edf6c944e022fe9ef06989960 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:20 +0000
Subject: [PATCH 3765/4076] ASoC: wm_adsp: Fix firmware file search order

Check for the cases of system-specific bin file without a
wmfw before falling back to looking for a generic wmfw.

All system-specific options should be tried before falling
back to loading a generic wmfw/bin. With the original code,
the presence of a fallback generic wmfw on the filesystem
would prevent using a system-specific tuning with a ROM
firmware.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 0e7d82cbea8b ("ASoC: wm_adsp: Add support for loading bin files without wmfw")
Link: https://msgid.link/r/20240129162737.497-2-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 44 ++++++++++++++++----------------------
 1 file changed, 19 insertions(+), 25 deletions(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index c01e31175015c..bd60ceebb6a9c 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -823,6 +823,23 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 		}
 	}
 
+	/* Check system-specific bin without wmfw before falling back to generic */
+	if (dsp->wmfw_optional && system_name) {
+		if (asoc_component_prefix)
+			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
+						      cirrus_dir, system_name,
+						      asoc_component_prefix, "bin");
+
+		if (!*coeff_firmware)
+			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
+						      cirrus_dir, system_name,
+						      NULL, "bin");
+
+		if (*coeff_firmware)
+			return 0;
+	}
+
+	/* Check legacy location */
 	if (!wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
 					   "", NULL, NULL, "wmfw")) {
 		wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
@@ -830,38 +847,15 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 		return 0;
 	}
 
+	/* Fall back to generic wmfw and optional matching bin */
 	ret = wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
 					    cirrus_dir, NULL, NULL, "wmfw");
-	if (!ret) {
+	if (!ret || dsp->wmfw_optional) {
 		wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
 					      cirrus_dir, NULL, NULL, "bin");
 		return 0;
 	}
 
-	if (dsp->wmfw_optional) {
-		if (system_name) {
-			if (asoc_component_prefix)
-				wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-							      cirrus_dir, system_name,
-							      asoc_component_prefix, "bin");
-
-			if (!*coeff_firmware)
-				wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-							      cirrus_dir, system_name,
-							      NULL, "bin");
-		}
-
-		if (!*coeff_firmware)
-			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-						      "", NULL, NULL, "bin");
-
-		if (!*coeff_firmware)
-			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-						      cirrus_dir, NULL, NULL, "bin");
-
-		return 0;
-	}
-
 	adsp_err(dsp, "Failed to request firmware <%s>%s-%s-%s<-%s<%s>>.wmfw\n",
 		 cirrus_dir, dsp->part, dsp->fwf_name, wm_adsp_fw[dsp->fw].file,
 		 system_name, asoc_component_prefix);
-- 
GitLab


From daf3f0f99cde93a066240462b7a87cdfeedc04c0 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:21 +0000
Subject: [PATCH 3766/4076] ASoC: wm_adsp: Don't overwrite fwf_name with the
 default

There's no need to overwrite fwf_name with a kstrdup() of the cs_dsp part
name. It is trivial to select either fwf_name or cs_dsp.part as the string
to use when building the filename in wm_adsp_request_firmware_file().

This leaves fwf_name entirely owned by the codec driver.

It also avoids problems with freeing the pointer. With the original code
fwf_name was either a pointer owned by the codec driver, or a kstrdup()
created by wm_adsp. This meant wm_adsp must free it if it set it, but not
if the codec driver set it. The code was handling this by using
devm_kstrdup().
But there is no absolute requirement that wm_adsp_common_init() must be
called from probe(), so this was a pseudo-memory leak - each new call to
wm_adsp_common_init() would allocate another block of memory but these
would only be freed if the owning codec driver was removed.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://msgid.link/r/20240129162737.497-3-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 29 ++++++++++++-----------------
 1 file changed, 12 insertions(+), 17 deletions(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index bd60ceebb6a9c..36ea0dcdc7ab0 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -739,19 +739,25 @@ static int wm_adsp_request_firmware_file(struct wm_adsp *dsp,
 					 const char *filetype)
 {
 	struct cs_dsp *cs_dsp = &dsp->cs_dsp;
+	const char *fwf;
 	char *s, c;
 	int ret = 0;
 
+	if (dsp->fwf_name)
+		fwf = dsp->fwf_name;
+	else
+		fwf = dsp->cs_dsp.name;
+
 	if (system_name && asoc_component_prefix)
 		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s-%s.%s", dir, dsp->part,
-				      dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name,
+				      fwf, wm_adsp_fw[dsp->fw].file, system_name,
 				      asoc_component_prefix, filetype);
 	else if (system_name)
 		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s.%s", dir, dsp->part,
-				      dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name,
+				      fwf, wm_adsp_fw[dsp->fw].file, system_name,
 				      filetype);
 	else
-		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, dsp->fwf_name,
+		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, fwf,
 				      wm_adsp_fw[dsp->fw].file, filetype);
 
 	if (*filename == NULL)
@@ -857,29 +863,18 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 	}
 
 	adsp_err(dsp, "Failed to request firmware <%s>%s-%s-%s<-%s<%s>>.wmfw\n",
-		 cirrus_dir, dsp->part, dsp->fwf_name, wm_adsp_fw[dsp->fw].file,
-		 system_name, asoc_component_prefix);
+		 cirrus_dir, dsp->part,
+		 dsp->fwf_name ? dsp->fwf_name : dsp->cs_dsp.name,
+		 wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix);
 
 	return -ENOENT;
 }
 
 static int wm_adsp_common_init(struct wm_adsp *dsp)
 {
-	char *p;
-
 	INIT_LIST_HEAD(&dsp->compr_list);
 	INIT_LIST_HEAD(&dsp->buffer_list);
 
-	if (!dsp->fwf_name) {
-		p = devm_kstrdup(dsp->cs_dsp.dev, dsp->cs_dsp.name, GFP_KERNEL);
-		if (!p)
-			return -ENOMEM;
-
-		dsp->fwf_name = p;
-		for (; *p != 0; ++p)
-			*p = tolower(*p);
-	}
-
 	return 0;
 }
 
-- 
GitLab


From ae861c466ee57e15a29d97629e1c564e3f714a4f Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:22 +0000
Subject: [PATCH 3767/4076] ASoC: cs35l56: cs35l56_component_remove() must
 clear cs35l56->component

The cs35l56->component pointer is used by the suspend-resume handling to
know whether the driver is fully instantiated. This is to prevent it
queuing dsp_work which would result in calling wm_adsp when the driver
is not an instantiated ASoC component. So this pointer must be cleared
by cs35l56_component_remove().

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: e49611252900 ("ASoC: cs35l56: Add driver for Cirrus Logic CS35L56")
Link: https://msgid.link/r/20240129162737.497-4-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 45b4de3eff94f..09944db4db30d 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -809,6 +809,8 @@ static void cs35l56_component_remove(struct snd_soc_component *component)
 	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
 
 	cancel_work_sync(&cs35l56->dsp_work);
+
+	cs35l56->component = NULL;
 }
 
 static int cs35l56_set_bias_level(struct snd_soc_component *component,
-- 
GitLab


From cd38ccbecdace1469b4e0cfb3ddeec72a3fad226 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:23 +0000
Subject: [PATCH 3768/4076] ASoC: cs35l56: cs35l56_component_remove() must
 clean up wm_adsp

cs35l56_component_remove() must call wm_adsp_power_down() and
wm_adsp2_component_remove().

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: e49611252900 ("ASoC: cs35l56: Add driver for Cirrus Logic CS35L56")
Link: https://msgid.link/r/20240129162737.497-5-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 09944db4db30d..491da77112c34 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -810,6 +810,11 @@ static void cs35l56_component_remove(struct snd_soc_component *component)
 
 	cancel_work_sync(&cs35l56->dsp_work);
 
+	if (cs35l56->dsp.cs_dsp.booted)
+		wm_adsp_power_down(&cs35l56->dsp);
+
+	wm_adsp2_component_remove(&cs35l56->dsp, component);
+
 	cs35l56->component = NULL;
 }
 
-- 
GitLab


From 07687cd0539f8185b6ba0c0afba8473517116d6a Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:24 +0000
Subject: [PATCH 3769/4076] ASoC: cs35l56: Don't add the same register patch
 multiple times

Move the call to cs35l56_set_patch() earlier in cs35l56_init() so
that it only adds the register patch on first-time initialization.

The call was after the post_soft_reset label, so every time this
function was run to re-initialize the hardware after a reset it would
call regmap_register_patch() and add the same reg_sequence again.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 898673b905b9 ("ASoC: cs35l56: Move shared data into a common data structure")
Link: https://msgid.link/r/20240129162737.497-6-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 491da77112c34..ea5d2b2eb82a0 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -1159,6 +1159,10 @@ int cs35l56_init(struct cs35l56_private *cs35l56)
 	if (ret < 0)
 		return ret;
 
+	ret = cs35l56_set_patch(&cs35l56->base);
+	if (ret)
+		return ret;
+
 	/* Populate the DSP information with the revision and security state */
 	cs35l56->dsp.part = devm_kasprintf(cs35l56->base.dev, GFP_KERNEL, "cs35l56%s-%02x",
 					   cs35l56->base.secured ? "s" : "", cs35l56->base.rev);
@@ -1197,10 +1201,6 @@ post_soft_reset:
 	if (ret)
 		return ret;
 
-	ret = cs35l56_set_patch(&cs35l56->base);
-	if (ret)
-		return ret;
-
 	/* Registers could be dirty after soft reset or SoundWire enumeration */
 	regcache_sync(cs35l56->base.regmap);
 
-- 
GitLab


From 3739cc0733ba7eeafc08d4d4208d1f3c2451eabd Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:25 +0000
Subject: [PATCH 3770/4076] ASoC: cs35l56: Remove buggy checks from
 cs35l56_is_fw_reload_needed()

Remove the check of fw_patched from cs35l56_is_fw_reload_needed().
Also remove the redundant check for control of the reset GPIO.

The fw_patched flag is set when cs35l56_dsp_work() has completed its
steps to download firmware and power-up wm_adsp. There was a check in
cs35l56_is_fw_reload_needed() to make a quick exit of 'false' if
!fw_patched. The original idea was that the system might be suspended
before the driver has ever made any attempt to download firmware, and
in that case the driver doesn't need to return to a patched state
because it was never in a patched state.

This check of fw_patched is buggy because it prevented ever recovering
from a failed patch. If a previous attempt to patch and reboot the
silicon had failed it would leave fw_patched==false. This would mean
the driver never attempted another download even though the fault may
have been cleared (by a hard reset, for example).

It is also a redundant check because the calling code already makes
a quick exit if cs35l56_component_probe() has not been called, which
deals with the original intent of this check but in a safer way.

The check for reset GPIO is redundant: if the silicon was hard-reset
the FIRMWARE_MISSING flag will be 1. But this check created an
expectation that the suspend/resume code toggles reset. This can't
easily be protected against accidental code breakage. The only reason
for the check was to skip runtime-resuming the driver to read the
PROTECTION_STATUS register when it already knows it reset the silicon.
But in that case the driver will have to be runtime-resumed to do
the firmware download. So it created an assumption for no benefit.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 8a731fd37f8b ("ASoC: cs35l56: Move utility functions to shared file")
Link: https://msgid.link/r/20240129162737.497-7-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56-shared.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 953ba066bab1e..0cd572de73a90 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -400,17 +400,6 @@ int cs35l56_is_fw_reload_needed(struct cs35l56_base *cs35l56_base)
 	unsigned int val;
 	int ret;
 
-	/* Nothing to re-patch if we haven't done any patching yet. */
-	if (!cs35l56_base->fw_patched)
-		return false;
-
-	/*
-	 * If we have control of RESET we will have asserted it so the firmware
-	 * will need re-patching.
-	 */
-	if (cs35l56_base->reset_gpio)
-		return true;
-
 	/*
 	 * In secure mode FIRMWARE_MISSING is cleared by the BIOS loader so
 	 * can't be used here to test for memory retention.
-- 
GitLab


From 72a77d7631c6e392677c0134343cf5edcd3a4572 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:26 +0000
Subject: [PATCH 3771/4076] ASoC: cs35l56: Fix to ensure ASP1 registers match
 cache

Add a dummy SUPPLY widget connected to the ASP that forces the
chip registers to match the regmap cache when the ASP is
powered-up.

On a SoundWire system the ASP is free for use as a chip-to-chip
interconnect. This can be either for the firmware on multiple
CS35L56 to share reference audio; or as a bridge to another
device. If it is a firmware interconnect it is owned by the
firmware and the Linux driver should avoid writing the registers.
However. If it is a bridge then Linux may take over and handle
it as a normal codec-to-codec link.

CS35L56 is designed for SDCA and a generic SDCA driver would
know nothing about these chip-specific registers. So if the
ASP is being used on a SoundWire system the firmware sets up the
ASP registers. This means that we can't assume the default
state of the ASP registers. But we don't know the initial state
that the firmware set them to until after the firmware has been
downloaded and booted, which can take several seconds when
downloading multiple amps.

To avoid blocking probe() for several seconds waiting for the
firmware, the silicon defaults are assumed. This allows the machine
driver to setup the ASP configuration during probe() without being
blocked. If the ASP is hooked up and used, the SUPPLY widget
ensures that the chip registers match what was configured in the
regmap cache.

If the machine driver does not hook up the ASP, it is assumed that
it won't call any functions to configure the ASP DAI. Therefore
the regmap cache will be clean for these registers so a
regcache_sync() will not overwrite the chip registers. If the
DAI is not hooked up, the dummy SUPPLY widget will not be
invoked so it will never force-overwrite the chip registers.

Backport note:
This won't apply cleanly to kernels older than v6.6.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: e49611252900 ("ASoC: cs35l56: Add driver for Cirrus Logic CS35L56")
Link: https://msgid.link/r/20240129162737.497-8-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h           |  1 +
 sound/soc/codecs/cs35l56-shared.c | 41 +++++++++++++++++++++++++++++++
 sound/soc/codecs/cs35l56.c        | 21 ++++++++++++++++
 3 files changed, 63 insertions(+)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 8c18e8b6d27d2..4db36c893d9d2 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -272,6 +272,7 @@ extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC];
 extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC];
 
 int cs35l56_set_patch(struct cs35l56_base *cs35l56_base);
+int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base);
 int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command);
 int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base);
 int cs35l56_wait_for_firmware_boot(struct cs35l56_base *cs35l56_base);
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 0cd572de73a90..35789ffc63af0 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -195,6 +195,47 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg)
 	}
 }
 
+/*
+ * The firmware boot sequence can overwrite the ASP1 config registers so that
+ * they don't match regmap's view of their values. Rewrite the values from the
+ * regmap cache into the hardware registers.
+ */
+int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base)
+{
+	struct reg_sequence asp1_regs[] = {
+		{ .reg = CS35L56_ASP1_ENABLES1 },
+		{ .reg = CS35L56_ASP1_CONTROL1 },
+		{ .reg = CS35L56_ASP1_CONTROL2 },
+		{ .reg = CS35L56_ASP1_CONTROL3 },
+		{ .reg = CS35L56_ASP1_FRAME_CONTROL1 },
+		{ .reg = CS35L56_ASP1_FRAME_CONTROL5 },
+		{ .reg = CS35L56_ASP1_DATA_CONTROL1 },
+		{ .reg = CS35L56_ASP1_DATA_CONTROL5 },
+	};
+	int i, ret;
+
+	/* Read values from regmap cache into a write sequence */
+	for (i = 0; i < ARRAY_SIZE(asp1_regs); ++i) {
+		ret = regmap_read(cs35l56_base->regmap, asp1_regs[i].reg, &asp1_regs[i].def);
+		if (ret)
+			goto err;
+	}
+
+	/* Write the values cache-bypassed so that they will be written to silicon */
+	ret = regmap_multi_reg_write_bypassed(cs35l56_base->regmap, asp1_regs,
+					      ARRAY_SIZE(asp1_regs));
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	dev_err(cs35l56_base->dev, "Failed to sync ASP1 registers: %d\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_force_sync_asp1_registers_from_cache, SND_SOC_CS35L56_SHARED);
+
 int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command)
 {
 	unsigned int val;
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index ea5d2b2eb82a0..41aa79848b159 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -148,6 +148,21 @@ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_sdw1tx4_enum,
 static const struct snd_kcontrol_new sdw1_tx4_mux =
 	SOC_DAPM_ENUM("SDW1TX4 SRC", cs35l56_sdw1tx4_enum);
 
+static int cs35l56_asp1_cfg_event(struct snd_soc_dapm_widget *w,
+				  struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* Override register values set by firmware boot */
+		return cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	default:
+		return 0;
+	}
+}
+
 static int cs35l56_play_event(struct snd_soc_dapm_widget *w,
 			      struct snd_kcontrol *kcontrol, int event)
 {
@@ -184,6 +199,9 @@ static const struct snd_soc_dapm_widget cs35l56_dapm_widgets[] = {
 	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD_B", 0, 0),
 	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD_AMP", 0, 0),
 
+	SND_SOC_DAPM_SUPPLY("ASP1 CFG", SND_SOC_NOPM, 0, 0, cs35l56_asp1_cfg_event,
+			    SND_SOC_DAPM_PRE_PMU),
+
 	SND_SOC_DAPM_SUPPLY("PLAY", SND_SOC_NOPM, 0, 0, cs35l56_play_event,
 			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
 
@@ -251,6 +269,9 @@ static const struct snd_soc_dapm_route cs35l56_audio_map[] = {
 	{ "AMP", NULL, "VDD_B" },
 	{ "AMP", NULL, "VDD_AMP" },
 
+	{ "ASP1 Playback", NULL, "ASP1 CFG" },
+	{ "ASP1 Capture", NULL, "ASP1 CFG" },
+
 	{ "ASP1 Playback", NULL, "PLAY" },
 	{ "SDW1 Playback", NULL, "PLAY" },
 
-- 
GitLab


From 782e6c538be43a17e34f552ab49e8c713cac7883 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:27 +0000
Subject: [PATCH 3772/4076] ASoC: cs35l56: Fix default SDW TX mixer registers

Patch the SDW TX mixer registers to silicon defaults.

CS35L56 is designed for SDCA and a generic SDCA driver would
know nothing about these chip-specific registers. So the
firmware sets up the SDW TX mixer registers to whatever audio
is relevant on a specific system.

This means that the driver cannot assume the initial values
of these registers. But Linux has ALSA controls to configure
routing, so the registers can be patched to silicon default and
the ALSA controls used to select what audio to feed back to the
host capture path.

Backport note:
This won't apply to kernels older than v6.6.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: e49611252900 ("ASoC: cs35l56: Add driver for Cirrus Logic CS35L56")
Link: https://msgid.link/r/20240129162737.497-9-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56-shared.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 35789ffc63af0..a812abf90836e 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -12,6 +12,15 @@
 #include "cs35l56.h"
 
 static const struct reg_sequence cs35l56_patch[] = {
+	/*
+	 * Firmware can change these to non-defaults to satisfy SDCA.
+	 * Ensure that they are at known defaults.
+	 */
+	{ CS35L56_SWIRE_DP3_CH1_INPUT,		0x00000018 },
+	{ CS35L56_SWIRE_DP3_CH2_INPUT,		0x00000019 },
+	{ CS35L56_SWIRE_DP3_CH3_INPUT,		0x00000029 },
+	{ CS35L56_SWIRE_DP3_CH4_INPUT,		0x00000028 },
+
 	/* These are not reset by a soft-reset, so patch to defaults. */
 	{ CS35L56_MAIN_RENDER_USER_MUTE,	0x00000000 },
 	{ CS35L56_MAIN_RENDER_USER_VOLUME,	0x00000000 },
-- 
GitLab


From 856ce8982169acb31a25c5f2ecd2570ab8a6af46 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:28 +0000
Subject: [PATCH 3773/4076] ALSA: hda: cs35l56: Initialize all ASP1 registers

Add ASP1_FRAME_CONTROL1, ASP1_FRAME_CONTROL5 and the ASP1_TX?_INPUT
registers to the sequence used to initialize the ASP configuration.
Write this sequence to the cache and directly to the registers to
ensure that they match.

A system-specific firmware can patch these registers to values that are
not the silicon default, so that the CS35L56 boots already in the
configuration used by Windows or by "driverless" Windows setups such
as factory tuning.

These may not match how Linux is configuring the HDA codec. And anyway
on Linux the ALSA controls are used to configure routing options.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 73cfbfa9caea ("ALSA: hda/cs35l56: Add driver for Cirrus Logic CS35L56 amplifier")
Link: https://msgid.link/r/20240129162737.497-10-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/pci/hda/cs35l56_hda.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index b61e1de8c4bf9..f22bcb104a4eb 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -30,14 +30,23 @@
   *  ASP1_RX_WL = 24 bits per sample
   *  ASP1_TX_WL = 24 bits per sample
   *  ASP1_RXn_EN 1..3 and ASP1_TXn_EN 1..4 disabled
+  *
+  * Override any Windows-specific mixer settings applied by the firmware.
   */
 static const struct reg_sequence cs35l56_hda_dai_config[] = {
 	{ CS35L56_ASP1_CONTROL1,	0x00000021 },
 	{ CS35L56_ASP1_CONTROL2,	0x20200200 },
 	{ CS35L56_ASP1_CONTROL3,	0x00000003 },
+	{ CS35L56_ASP1_FRAME_CONTROL1,	0x03020100 },
+	{ CS35L56_ASP1_FRAME_CONTROL5,	0x00020100 },
 	{ CS35L56_ASP1_DATA_CONTROL5,	0x00000018 },
 	{ CS35L56_ASP1_DATA_CONTROL1,	0x00000018 },
 	{ CS35L56_ASP1_ENABLES1,	0x00000000 },
+	{ CS35L56_ASP1TX1_INPUT,	0x00000018 },
+	{ CS35L56_ASP1TX2_INPUT,	0x00000019 },
+	{ CS35L56_ASP1TX3_INPUT,	0x00000020 },
+	{ CS35L56_ASP1TX4_INPUT,	0x00000028 },
+
 };
 
 static void cs35l56_hda_play(struct cs35l56_hda *cs35l56)
@@ -133,6 +142,10 @@ static int cs35l56_hda_runtime_resume(struct device *dev)
 		}
 	}
 
+	ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	if (ret)
+		goto err;
+
 	return 0;
 
 err:
@@ -976,6 +989,9 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int id)
 
 	regmap_multi_reg_write(cs35l56->base.regmap, cs35l56_hda_dai_config,
 			       ARRAY_SIZE(cs35l56_hda_dai_config));
+	ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	if (ret)
+		goto err;
 
 	/*
 	 * By default only enable one ASP1TXn, where n=amplifier index,
-- 
GitLab


From 07f7d6e7a124d3e4de36771e2a4926d0e31c2258 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:29 +0000
Subject: [PATCH 3774/4076] ASoC: cs35l56: Fix for initializing ASP1 mixer
 registers

Defer initializing the state of the ASP1 mixer registers until
the firmware has been downloaded and rebooted.

On a SoundWire system the ASP is free for use as a chip-to-chip
interconnect. This can be either for the firmware on multiple
CS35L56 to share reference audio; or as a bridge to another
device. If it is a firmware interconnect it is owned by the
firmware and the Linux driver should avoid writing the registers.
However, if it is a bridge then Linux may take over and handle
it as a normal codec-to-codec link. Even if the ASP is used
as a firmware-firmware interconnect it is useful to have
ALSA controls for the ASP mixer. They are at least useful for
debugging.

CS35L56 is designed for SDCA and a generic SDCA driver would
know nothing about these chip-specific registers. So if the
ASP is being used on a SoundWire system the firmware sets up the
ASP mixer registers. This means that we can't assume the default
state of these registers. But we don't know the initial state
that the firmware set them to until after the firmware has been
downloaded and booted, which can take several seconds when
downloading multiple amps.

DAPM normally reads the initial state of mux registers during
probe() but this would mean blocking probe() for several seconds
until the firmware has initialized them. To avoid this, the
mixer muxes are set SND_SOC_NOPM to prevent DAPM trying to read
the register state. Custom get/set callbacks are implemented for
ALSA control access, and these can safely block waiting for the
firmware download.

After the firmware download has completed, the state of the
mux registers is known so a work job is queued to call
snd_soc_dapm_mux_update_power() on each of the mux widgets.

Backport note:
This won't apply cleanly to kernels older than v6.6.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: e49611252900 ("ASoC: cs35l56: Add driver for Cirrus Logic CS35L56")
Link: https://msgid.link/r/20240129162737.497-11-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56-shared.c |   7 +-
 sound/soc/codecs/cs35l56.c        | 172 +++++++++++++++++++++++++++---
 sound/soc/codecs/cs35l56.h        |   1 +
 3 files changed, 163 insertions(+), 17 deletions(-)

diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index a812abf90836e..9a70db0fa4188 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -43,10 +43,9 @@ static const struct reg_default cs35l56_reg_defaults[] = {
 	{ CS35L56_ASP1_FRAME_CONTROL5,		0x00020100 },
 	{ CS35L56_ASP1_DATA_CONTROL1,		0x00000018 },
 	{ CS35L56_ASP1_DATA_CONTROL5,		0x00000018 },
-	{ CS35L56_ASP1TX1_INPUT,		0x00000018 },
-	{ CS35L56_ASP1TX2_INPUT,		0x00000019 },
-	{ CS35L56_ASP1TX3_INPUT,		0x00000020 },
-	{ CS35L56_ASP1TX4_INPUT,		0x00000028 },
+
+	/* no defaults for ASP1TX mixer */
+
 	{ CS35L56_SWIRE_DP3_CH1_INPUT,		0x00000018 },
 	{ CS35L56_SWIRE_DP3_CH2_INPUT,		0x00000019 },
 	{ CS35L56_SWIRE_DP3_CH3_INPUT,		0x00000029 },
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 41aa79848b159..1b51650a19fff 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -59,6 +59,135 @@ static int cs35l56_dspwait_put_volsw(struct snd_kcontrol *kcontrol,
 	return snd_soc_put_volsw(kcontrol, ucontrol);
 }
 
+static const unsigned short cs35l56_asp1_mixer_regs[] = {
+	CS35L56_ASP1TX1_INPUT, CS35L56_ASP1TX2_INPUT,
+	CS35L56_ASP1TX3_INPUT, CS35L56_ASP1TX4_INPUT,
+};
+
+static const char * const cs35l56_asp1_mux_control_names[] = {
+	"ASP1 TX1 Source", "ASP1 TX2 Source", "ASP1 TX3 Source", "ASP1 TX4 Source"
+};
+
+static int cs35l56_dspwait_asp1tx_get(struct snd_kcontrol *kcontrol,
+				      struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
+	int index = e->shift_l;
+	unsigned int addr, val;
+	int ret;
+
+	/* Wait for mux to be initialized */
+	cs35l56_wait_dsp_ready(cs35l56);
+	flush_work(&cs35l56->mux_init_work);
+
+	addr = cs35l56_asp1_mixer_regs[index];
+	ret = regmap_read(cs35l56->base.regmap, addr, &val);
+	if (ret)
+		return ret;
+
+	val &= CS35L56_ASP_TXn_SRC_MASK;
+	ucontrol->value.enumerated.item[0] = snd_soc_enum_val_to_item(e, val);
+
+	return 0;
+}
+
+static int cs35l56_dspwait_asp1tx_put(struct snd_kcontrol *kcontrol,
+				      struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+	struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
+	int item = ucontrol->value.enumerated.item[0];
+	int index = e->shift_l;
+	unsigned int addr, val;
+	bool changed;
+	int ret;
+
+	/* Wait for mux to be initialized */
+	cs35l56_wait_dsp_ready(cs35l56);
+	flush_work(&cs35l56->mux_init_work);
+
+	addr = cs35l56_asp1_mixer_regs[index];
+	val = snd_soc_enum_item_to_val(e, item);
+
+	ret = regmap_update_bits_check(cs35l56->base.regmap, addr,
+				       CS35L56_ASP_TXn_SRC_MASK, val, &changed);
+	if (!ret)
+		return ret;
+
+	if (changed)
+		snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+
+	return changed;
+}
+
+static void cs35l56_mark_asp1_mixer_widgets_dirty(struct cs35l56_private *cs35l56)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(cs35l56->component);
+	const char *prefix = cs35l56->component->name_prefix;
+	char full_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+	const char *name;
+	struct snd_kcontrol *kcontrol;
+	struct soc_enum *e;
+	unsigned int val[4];
+	int i, item, ret;
+
+	/*
+	 * Resume so we can read the registers from silicon if the regmap
+	 * cache has not yet been populated.
+	 */
+	ret = pm_runtime_resume_and_get(cs35l56->base.dev);
+	if (ret < 0)
+		return;
+
+	ret = regmap_bulk_read(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT,
+			       val, ARRAY_SIZE(val));
+
+	pm_runtime_mark_last_busy(cs35l56->base.dev);
+	pm_runtime_put_autosuspend(cs35l56->base.dev);
+
+	if (ret) {
+		dev_err(cs35l56->base.dev, "Failed to read ASP1 mixer regs: %d\n", ret);
+		return;
+	}
+
+	snd_soc_card_mutex_lock(dapm->card);
+	WARN_ON(!dapm->card->instantiated);
+
+	for (i = 0; i < ARRAY_SIZE(cs35l56_asp1_mux_control_names); ++i) {
+		name = cs35l56_asp1_mux_control_names[i];
+
+		if (prefix) {
+			snprintf(full_name, sizeof(full_name), "%s %s", prefix, name);
+			name = full_name;
+		}
+
+		kcontrol = snd_soc_card_get_kcontrol(dapm->card, name);
+		if (!kcontrol) {
+			dev_warn(cs35l56->base.dev, "Could not find control %s\n", name);
+			continue;
+		}
+
+		e = (struct soc_enum *)kcontrol->private_value;
+		item = snd_soc_enum_val_to_item(e, val[i] & CS35L56_ASP_TXn_SRC_MASK);
+		snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+	}
+
+	snd_soc_card_mutex_unlock(dapm->card);
+}
+
+static void cs35l56_mux_init_work(struct work_struct *work)
+{
+	struct cs35l56_private *cs35l56 = container_of(work,
+						       struct cs35l56_private,
+						       mux_init_work);
+
+	cs35l56_mark_asp1_mixer_widgets_dirty(cs35l56);
+}
+
 static DECLARE_TLV_DB_SCALE(vol_tlv, -10000, 25, 0);
 
 static const struct snd_kcontrol_new cs35l56_controls[] = {
@@ -77,40 +206,44 @@ static const struct snd_kcontrol_new cs35l56_controls[] = {
 };
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx1_enum,
-				  CS35L56_ASP1TX1_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  0, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx1_mux =
-	SOC_DAPM_ENUM("ASP1TX1 SRC", cs35l56_asp1tx1_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX1 SRC", cs35l56_asp1tx1_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx2_enum,
-				  CS35L56_ASP1TX2_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  1, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx2_mux =
-	SOC_DAPM_ENUM("ASP1TX2 SRC", cs35l56_asp1tx2_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX2 SRC", cs35l56_asp1tx2_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx3_enum,
-				  CS35L56_ASP1TX3_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  2, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx3_mux =
-	SOC_DAPM_ENUM("ASP1TX3 SRC", cs35l56_asp1tx3_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX3 SRC", cs35l56_asp1tx3_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx4_enum,
-				  CS35L56_ASP1TX4_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  3, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx4_mux =
-	SOC_DAPM_ENUM("ASP1TX4 SRC", cs35l56_asp1tx4_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX4 SRC", cs35l56_asp1tx4_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_sdw1tx1_enum,
 				CS35L56_SWIRE_DP3_CH1_INPUT,
@@ -785,6 +918,15 @@ static void cs35l56_dsp_work(struct work_struct *work)
 	else
 		cs35l56_patch(cs35l56);
 
+
+	/*
+	 * Set starting value of ASP1 mux widgets. Updating a mux takes
+	 * the DAPM mutex. Post this to a separate job so that DAPM
+	 * power-up can wait for dsp_work to complete without deadlocking
+	 * on the DAPM mutex.
+	 */
+	queue_work(cs35l56->dsp_wq, &cs35l56->mux_init_work);
+
 	pm_runtime_mark_last_busy(cs35l56->base.dev);
 	pm_runtime_put_autosuspend(cs35l56->base.dev);
 }
@@ -830,6 +972,7 @@ static void cs35l56_component_remove(struct snd_soc_component *component)
 	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
 
 	cancel_work_sync(&cs35l56->dsp_work);
+	cancel_work_sync(&cs35l56->mux_init_work);
 
 	if (cs35l56->dsp.cs_dsp.booted)
 		wm_adsp_power_down(&cs35l56->dsp);
@@ -897,8 +1040,10 @@ int cs35l56_system_suspend(struct device *dev)
 
 	dev_dbg(dev, "system_suspend\n");
 
-	if (cs35l56->component)
+	if (cs35l56->component) {
 		flush_work(&cs35l56->dsp_work);
+		cancel_work_sync(&cs35l56->mux_init_work);
+	}
 
 	/*
 	 * The interrupt line is normally shared, but after we start suspending
@@ -1049,6 +1194,7 @@ static int cs35l56_dsp_init(struct cs35l56_private *cs35l56)
 		return -ENOMEM;
 
 	INIT_WORK(&cs35l56->dsp_work, cs35l56_dsp_work);
+	INIT_WORK(&cs35l56->mux_init_work, cs35l56_mux_init_work);
 
 	dsp = &cs35l56->dsp;
 	cs35l56_init_cs_dsp(&cs35l56->base, &dsp->cs_dsp);
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index 8159c3e217d93..dc2fe4c91e67b 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -34,6 +34,7 @@ struct cs35l56_private {
 	struct wm_adsp dsp; /* must be first member */
 	struct cs35l56_base base;
 	struct work_struct dsp_work;
+	struct work_struct mux_init_work;
 	struct workqueue_struct *dsp_wq;
 	struct snd_soc_component *component;
 	struct regulator_bulk_data supplies[CS35L56_NUM_BULK_SUPPLIES];
-- 
GitLab


From f6c967941c5d6fa526fdd64733a8d86bf2bfab31 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:30 +0000
Subject: [PATCH 3775/4076] ASoC: cs35l56: Fix misuse of wm_adsp 'part' string
 for silicon revision

Put the silicon revision and secured flag in the wm_adsp fwf_name
string instead of including them in the part string.

This changes the format of the firmware name string from

 cs35l56[s]-rev-misc[-system_name]

to
 cs35l56-rev[-s]-misc[-system_name]

No firmware files have been published, so this doesn't cause a
compatibility break.

Silicon revision and secured flag are included in the firmware
filename to pick a firmware compatible with the part. These strings
were being added to the part string, but that is a misuse of the
string. The correct place for these is the fwf_name string, which
is specifically intended to select between multiple firmware files
for the same part.

Backport note:
This won't apply to kernels older than v6.6.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 608f1b0dbdde ("ASoC: cs35l56: Move DSP part string generation so that it is done only once")
Link: https://msgid.link/r/20240129162737.497-12-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 1b51650a19fff..8899c02c6dea3 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -907,6 +907,18 @@ static void cs35l56_dsp_work(struct work_struct *work)
 
 	pm_runtime_get_sync(cs35l56->base.dev);
 
+	/* Populate fw file qualifier with the revision and security state */
+	if (!cs35l56->dsp.fwf_name) {
+		cs35l56->dsp.fwf_name = kasprintf(GFP_KERNEL, "%02x%s-dsp1",
+						  cs35l56->base.rev,
+						  cs35l56->base.secured ? "-s" : "");
+		if (!cs35l56->dsp.fwf_name)
+			goto err;
+	}
+
+	dev_dbg(cs35l56->base.dev, "DSP fwf name: '%s' system name: '%s'\n",
+		cs35l56->dsp.fwf_name, cs35l56->dsp.system_name);
+
 	/*
 	 * When the device is running in secure mode the firmware files can
 	 * only contain insecure tunings and therefore we do not need to
@@ -926,7 +938,7 @@ static void cs35l56_dsp_work(struct work_struct *work)
 	 * on the DAPM mutex.
 	 */
 	queue_work(cs35l56->dsp_wq, &cs35l56->mux_init_work);
-
+err:
 	pm_runtime_mark_last_busy(cs35l56->base.dev);
 	pm_runtime_put_autosuspend(cs35l56->base.dev);
 }
@@ -979,6 +991,9 @@ static void cs35l56_component_remove(struct snd_soc_component *component)
 
 	wm_adsp2_component_remove(&cs35l56->dsp, component);
 
+	kfree(cs35l56->dsp.fwf_name);
+	cs35l56->dsp.fwf_name = NULL;
+
 	cs35l56->component = NULL;
 }
 
@@ -1330,12 +1345,6 @@ int cs35l56_init(struct cs35l56_private *cs35l56)
 	if (ret)
 		return ret;
 
-	/* Populate the DSP information with the revision and security state */
-	cs35l56->dsp.part = devm_kasprintf(cs35l56->base.dev, GFP_KERNEL, "cs35l56%s-%02x",
-					   cs35l56->base.secured ? "s" : "", cs35l56->base.rev);
-	if (!cs35l56->dsp.part)
-		return -ENOMEM;
-
 	if (!cs35l56->base.reset_gpio) {
 		dev_dbg(cs35l56->base.dev, "No reset gpio: using soft reset\n");
 		cs35l56->soft_resetting = true;
-- 
GitLab


From f4ef5149953f2fc04907ca5b34db3df667dcddef Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:31 +0000
Subject: [PATCH 3776/4076] ASoC: cs35l56: Firmware file must match the version
 of preloaded firmware

Check during initialization whether the firmware is already patched.
If so, include the firmware version in the wm_adsp fwf_name string.

If the firmware has already been patched by the BIOS the driver
can only replace it if it has control of hard RESET.

If the driver cannot replace the firmware, it can still load a wmfw
(for ALSA control definitions) and/or a bin (for additional tunings).
But these must match the version of firmware that is running on the
CS35L56.

The firmware is pre-patched if FIRMWARE_MISSING == 0.

Including the firmware version in the fwf_name string will
qualify the firmware file name:

Normal (unpatched or replaceable firmware):
  cs35l56-rev-dsp1-misc[-system_name].[wmfw|bin]

Preloaded firmware:
  cs35l56-rev[-s]-VVVVVV-dsp1-misc[-system_name].[wmfw|bin]

Where:
   [-s] is an optional -s added into the name for a secured CS35L56
   VVVVVV is the 24-bit firmware version in hexadecimal.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 608f1b0dbdde ("ASoC: cs35l56: Move DSP part string generation so that it is done only once")
Link: https://msgid.link/r/20240129162737.497-13-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h           |  3 ++
 sound/soc/codecs/cs35l56-shared.c | 36 +++++++++++++++++++--
 sound/soc/codecs/cs35l56.c        | 52 +++++++++++++++++--------------
 3 files changed, 65 insertions(+), 26 deletions(-)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 4db36c893d9d2..5d6aefc41e64a 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -75,6 +75,7 @@
 #define CS35L56_DSP1_AHBM_WINDOW_DEBUG_0		0x25E2040
 #define CS35L56_DSP1_AHBM_WINDOW_DEBUG_1		0x25E2044
 #define CS35L56_DSP1_XMEM_UNPACKED24_0			0x2800000
+#define CS35L56_DSP1_FW_VER				0x2800010
 #define CS35L56_DSP1_HALO_STATE_A1			0x2801E58
 #define CS35L56_DSP1_HALO_STATE				0x28021E0
 #define CS35L56_DSP1_PM_CUR_STATE_A1			0x2804000
@@ -285,6 +286,8 @@ int cs35l56_is_fw_reload_needed(struct cs35l56_base *cs35l56_base);
 int cs35l56_runtime_suspend_common(struct cs35l56_base *cs35l56_base);
 int cs35l56_runtime_resume_common(struct cs35l56_base *cs35l56_base, bool is_soundwire);
 void cs35l56_init_cs_dsp(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_dsp);
+int cs35l56_read_prot_status(struct cs35l56_base *cs35l56_base,
+			     bool *fw_missing, unsigned int *fw_version);
 int cs35l56_hw_init(struct cs35l56_base *cs35l56_base);
 int cs35l56_get_bclk_freq_id(unsigned int freq);
 void cs35l56_fill_supply_names(struct regulator_bulk_data *data);
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 9a70db0fa4188..33835535ef843 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -628,10 +628,35 @@ void cs35l56_init_cs_dsp(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_ds
 }
 EXPORT_SYMBOL_NS_GPL(cs35l56_init_cs_dsp, SND_SOC_CS35L56_SHARED);
 
+int cs35l56_read_prot_status(struct cs35l56_base *cs35l56_base,
+			     bool *fw_missing, unsigned int *fw_version)
+{
+	unsigned int prot_status;
+	int ret;
+
+	ret = regmap_read(cs35l56_base->regmap, CS35L56_PROTECTION_STATUS, &prot_status);
+	if (ret) {
+		dev_err(cs35l56_base->dev, "Get PROTECTION_STATUS failed: %d\n", ret);
+		return ret;
+	}
+
+	*fw_missing = !!(prot_status & CS35L56_FIRMWARE_MISSING);
+
+	ret = regmap_read(cs35l56_base->regmap, CS35L56_DSP1_FW_VER, fw_version);
+	if (ret) {
+		dev_err(cs35l56_base->dev, "Get FW VER failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_read_prot_status, SND_SOC_CS35L56_SHARED);
+
 int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 {
 	int ret;
-	unsigned int devid, revid, otpid, secured;
+	unsigned int devid, revid, otpid, secured, fw_ver;
+	bool fw_missing;
 
 	/*
 	 * When the system is not using a reset_gpio ensure the device is
@@ -690,8 +715,13 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 		return ret;
 	}
 
-	dev_info(cs35l56_base->dev, "Cirrus Logic CS35L56%s Rev %02X OTP%d\n",
-		 cs35l56_base->secured ? "s" : "", cs35l56_base->rev, otpid);
+	ret = cs35l56_read_prot_status(cs35l56_base, &fw_missing, &fw_ver);
+	if (ret)
+		return ret;
+
+	dev_info(cs35l56_base->dev, "Cirrus Logic CS35L56%s Rev %02X OTP%d fw:%d.%d.%d (patched=%u)\n",
+		 cs35l56_base->secured ? "s" : "", cs35l56_base->rev, otpid,
+		 fw_ver >> 16, (fw_ver >> 8) & 0xff, fw_ver & 0xff, !fw_missing);
 
 	/* Wake source and *_BLOCKED interrupts default to unmasked, so mask them */
 	regmap_write(cs35l56_base->regmap, CS35L56_IRQ1_MASK_20, 0xffffffff);
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 8899c02c6dea3..597677422547c 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -804,7 +804,7 @@ static struct snd_soc_dai_driver cs35l56_dai[] = {
 	}
 };
 
-static void cs35l56_secure_patch(struct cs35l56_private *cs35l56)
+static void cs35l56_reinit_patch(struct cs35l56_private *cs35l56)
 {
 	int ret;
 
@@ -816,19 +816,10 @@ static void cs35l56_secure_patch(struct cs35l56_private *cs35l56)
 		cs35l56_mbox_send(&cs35l56->base, CS35L56_MBOX_CMD_AUDIO_REINIT);
 }
 
-static void cs35l56_patch(struct cs35l56_private *cs35l56)
+static void cs35l56_patch(struct cs35l56_private *cs35l56, bool firmware_missing)
 {
-	unsigned int firmware_missing;
 	int ret;
 
-	ret = regmap_read(cs35l56->base.regmap, CS35L56_PROTECTION_STATUS, &firmware_missing);
-	if (ret) {
-		dev_err(cs35l56->base.dev, "Failed to read PROTECTION_STATUS: %d\n", ret);
-		return;
-	}
-
-	firmware_missing &= CS35L56_FIRMWARE_MISSING;
-
 	/*
 	 * Disable SoundWire interrupts to prevent race with IRQ work.
 	 * Setting sdw_irq_no_unmask prevents the handler re-enabling
@@ -901,34 +892,49 @@ static void cs35l56_dsp_work(struct work_struct *work)
 	struct cs35l56_private *cs35l56 = container_of(work,
 						       struct cs35l56_private,
 						       dsp_work);
+	unsigned int firmware_version;
+	bool firmware_missing;
+	int ret;
 
 	if (!cs35l56->base.init_done)
 		return;
 
 	pm_runtime_get_sync(cs35l56->base.dev);
 
+	ret = cs35l56_read_prot_status(&cs35l56->base, &firmware_missing, &firmware_version);
+	if (ret)
+		goto err;
+
 	/* Populate fw file qualifier with the revision and security state */
-	if (!cs35l56->dsp.fwf_name) {
-		cs35l56->dsp.fwf_name = kasprintf(GFP_KERNEL, "%02x%s-dsp1",
+	kfree(cs35l56->dsp.fwf_name);
+	if (firmware_missing) {
+		cs35l56->dsp.fwf_name = kasprintf(GFP_KERNEL, "%02x-dsp1", cs35l56->base.rev);
+	} else {
+		/* Firmware files must match the running firmware version */
+		cs35l56->dsp.fwf_name = kasprintf(GFP_KERNEL,
+						  "%02x%s-%06x-dsp1",
 						  cs35l56->base.rev,
-						  cs35l56->base.secured ? "-s" : "");
-		if (!cs35l56->dsp.fwf_name)
-			goto err;
+						  cs35l56->base.secured ? "-s" : "",
+						  firmware_version);
 	}
 
+	if (!cs35l56->dsp.fwf_name)
+		goto err;
+
 	dev_dbg(cs35l56->base.dev, "DSP fwf name: '%s' system name: '%s'\n",
 		cs35l56->dsp.fwf_name, cs35l56->dsp.system_name);
 
 	/*
-	 * When the device is running in secure mode the firmware files can
-	 * only contain insecure tunings and therefore we do not need to
-	 * shutdown the firmware to apply them and can use the lower cost
-	 * reinit sequence instead.
+	 * The firmware cannot be patched if it is already running from
+	 * patch RAM. In this case the firmware files are versioned to
+	 * match the running firmware version and will only contain
+	 * tunings. We do not need to shutdown the firmware to apply
+	 * tunings so can use the lower cost reinit sequence instead.
 	 */
-	if (cs35l56->base.secured)
-		cs35l56_secure_patch(cs35l56);
+	if (!firmware_missing)
+		cs35l56_reinit_patch(cs35l56);
 	else
-		cs35l56_patch(cs35l56);
+		cs35l56_patch(cs35l56, firmware_missing);
 
 
 	/*
-- 
GitLab


From 245eeff18d7a37693815250ae15979ce98c3d190 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:32 +0000
Subject: [PATCH 3777/4076] ASoC: cs35l56: Load tunings for the correct speaker
 models

If the "spk-id-gpios" property is present it points to GPIOs whose
value must be used to select the correct bin file to match the
speakers.

Some manufacturers use multiple sources of speakers, which need
different tunings for best performance. On these models the type of
speaker fitted is indicated by the values of one or more GPIOs. The
number formed by the GPIOs identifies the tuning required.

The speaker ID must be used in combination with the subsystem ID
(either from PCI SSID or cirrus,firmware-uid property), because the
GPIOs can only indicate variants of a specific model.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 1a1c3d794ef6 ("ASoC: cs35l56: Use PCI SSID as the firmware UID")
Link: https://msgid.link/r/20240129162737.497-14-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h           |  1 +
 sound/soc/codecs/cs35l56-shared.c | 36 +++++++++++++++++++++++++++++++
 sound/soc/codecs/cs35l56.c        | 32 ++++++++++++++++++++++-----
 sound/soc/codecs/cs35l56.h        |  1 +
 4 files changed, 65 insertions(+), 5 deletions(-)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 5d6aefc41e64a..23da6298ab377 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -289,6 +289,7 @@ void cs35l56_init_cs_dsp(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_ds
 int cs35l56_read_prot_status(struct cs35l56_base *cs35l56_base,
 			     bool *fw_missing, unsigned int *fw_version);
 int cs35l56_hw_init(struct cs35l56_base *cs35l56_base);
+int cs35l56_get_speaker_id(struct cs35l56_base *cs35l56_base);
 int cs35l56_get_bclk_freq_id(unsigned int freq);
 void cs35l56_fill_supply_names(struct regulator_bulk_data *data);
 
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 33835535ef843..02fba4bc0a14f 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2023 Cirrus Logic, Inc. and
 //                    Cirrus Logic International Semiconductor Ltd.
 
+#include <linux/gpio/consumer.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/types.h>
@@ -736,6 +737,41 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 }
 EXPORT_SYMBOL_NS_GPL(cs35l56_hw_init, SND_SOC_CS35L56_SHARED);
 
+int cs35l56_get_speaker_id(struct cs35l56_base *cs35l56_base)
+{
+	struct gpio_descs *descs;
+	int speaker_id;
+	int i, ret;
+
+	/* Read the speaker type qualifier from the motherboard GPIOs */
+	descs = gpiod_get_array_optional(cs35l56_base->dev, "spk-id", GPIOD_IN);
+	if (!descs) {
+		return -ENOENT;
+	} else if (IS_ERR(descs)) {
+		ret = PTR_ERR(descs);
+		return dev_err_probe(cs35l56_base->dev, ret, "Failed to get spk-id-gpios\n");
+	}
+
+	speaker_id = 0;
+	for (i = 0; i < descs->ndescs; i++) {
+		ret = gpiod_get_value_cansleep(descs->desc[i]);
+		if (ret < 0) {
+			dev_err_probe(cs35l56_base->dev, ret, "Failed to read spk-id[%d]\n", i);
+			goto err;
+		}
+
+		speaker_id |= (ret << i);
+	}
+
+	dev_dbg(cs35l56_base->dev, "Speaker ID = %d\n", speaker_id);
+	ret = speaker_id;
+err:
+	gpiod_put_array(descs);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_get_speaker_id, SND_SOC_CS35L56_SHARED);
+
 static const u32 cs35l56_bclk_valid_for_pll_freq_table[] = {
 	[0x0C] = 128000,
 	[0x0F] = 256000,
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 597677422547c..c23e29da4cfb9 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -959,10 +959,19 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
 
 	if (!cs35l56->dsp.system_name &&
 	    (snd_soc_card_get_pci_ssid(component->card, &vendor, &device) == 0)) {
-		cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
-							  GFP_KERNEL,
-							  "%04x%04x",
-							  vendor, device);
+		/* Append a speaker qualifier if there is a speaker ID */
+		if (cs35l56->speaker_id >= 0) {
+			cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
+								  GFP_KERNEL,
+								  "%04x%04x-spkid%d",
+								  vendor, device,
+								  cs35l56->speaker_id);
+		} else {
+			cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
+								  GFP_KERNEL,
+								  "%04x%04x",
+								  vendor, device);
+		}
 		if (!cs35l56->dsp.system_name)
 			return -ENOMEM;
 	}
@@ -1245,7 +1254,13 @@ static int cs35l56_get_firmware_uid(struct cs35l56_private *cs35l56)
 	if (ret < 0)
 		return 0;
 
-	cs35l56->dsp.system_name = devm_kstrdup(dev, prop, GFP_KERNEL);
+	/* Append a speaker qualifier if there is a speaker ID */
+	if (cs35l56->speaker_id >= 0)
+		cs35l56->dsp.system_name = devm_kasprintf(dev, GFP_KERNEL, "%s-spkid%d",
+							  prop, cs35l56->speaker_id);
+	else
+		cs35l56->dsp.system_name = devm_kstrdup(dev, prop, GFP_KERNEL);
+
 	if (cs35l56->dsp.system_name == NULL)
 		return -ENOMEM;
 
@@ -1260,6 +1275,7 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56)
 
 	init_completion(&cs35l56->init_completion);
 	mutex_init(&cs35l56->base.irq_lock);
+	cs35l56->speaker_id = -ENOENT;
 
 	dev_set_drvdata(cs35l56->base.dev, cs35l56);
 
@@ -1296,6 +1312,12 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56)
 		gpiod_set_value_cansleep(cs35l56->base.reset_gpio, 1);
 	}
 
+	ret = cs35l56_get_speaker_id(&cs35l56->base);
+	if ((ret < 0) && (ret != -ENOENT))
+		goto err;
+
+	cs35l56->speaker_id = ret;
+
 	ret = cs35l56_get_firmware_uid(cs35l56);
 	if (ret != 0)
 		goto err;
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index dc2fe4c91e67b..596b141e3f961 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -45,6 +45,7 @@ struct cs35l56_private {
 	bool sdw_attached;
 	struct completion init_completion;
 
+	int speaker_id;
 	u32 rx_mask;
 	u32 tx_mask;
 	u8 asp_slot_width;
-- 
GitLab


From 9e92b77ceb6f362eb2e7995dad6c7f9863053d97 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:33 +0000
Subject: [PATCH 3778/4076] ASoC: cs35l56: Allow more time for firmware to boot

The original 50ms timeout for firmware boot is not long enough for
worst-case time to reboot after a firmware download. Increase the
timeout to 250ms.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: e49611252900 ("ASoC: cs35l56: Add driver for Cirrus Logic CS35L56")
Link: https://msgid.link/r/20240129162737.497-15-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 23da6298ab377..b24716ab27504 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -242,7 +242,7 @@
 
 #define CS35L56_CONTROL_PORT_READY_US			2200
 #define CS35L56_HALO_STATE_POLL_US			1000
-#define CS35L56_HALO_STATE_TIMEOUT_US			50000
+#define CS35L56_HALO_STATE_TIMEOUT_US			250000
 #define CS35L56_RESET_PULSE_MIN_US			1100
 #define CS35L56_WAKE_HOLD_TIME_US			1000
 
-- 
GitLab


From 77c60722ded7d6739805e045e9648cda82dde5ed Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:34 +0000
Subject: [PATCH 3779/4076] ALSA: hda: cs35l56: Fix order of searching for
 firmware files

Check for the cases of system-specific bin file without a
wmfw before falling back to looking for a generic wmfw.

All system-specific options should be tried before falling
back to loading a generic wmfw/bin. With the original code,
the presence of a fallback generic wmfw on the filesystem
would prevent using a system-specific tuning with a ROM
firmware.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 73cfbfa9caea ("ALSA: hda/cs35l56: Add driver for Cirrus Logic CS35L56 amplifier")
Link: https://msgid.link/r/20240129162737.497-16-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/pci/hda/cs35l56_hda.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index f22bcb104a4eb..7ba7234d8d9c0 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -483,6 +483,20 @@ static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
 								  NULL, "bin");
 			return;
 		}
+
+		/*
+		 * Check for system-specific bin files without wmfw before
+		 * falling back to generic firmware
+		 */
+		if (amp_name)
+			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
+							  cirrus_dir, system_name, amp_name, "bin");
+		if (!*coeff_firmware)
+			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
+							  cirrus_dir, system_name, NULL, "bin");
+
+		if (*coeff_firmware)
+			return;
 	}
 
 	ret = cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
@@ -493,16 +507,6 @@ static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
 		return;
 	}
 
-	/* When a firmware file is not found must still search for the coeff files */
-	if (system_name) {
-		if (amp_name)
-			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, amp_name, "bin");
-		if (!*coeff_firmware)
-			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, NULL, "bin");
-	}
-
 	if (!*coeff_firmware)
 		cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
 						  cirrus_dir, NULL, NULL, "bin");
-- 
GitLab


From e82bc517c6ef5d5c04b845420406e694c31bdb8a Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:35 +0000
Subject: [PATCH 3780/4076] ALSA: hda: cs35l56: Fix filename string field
 layout

Change the filename field layout to:
  cs35l56-rev[-s]-dsp1-misc[-sub].[wmfw|bin]

This is to keep the same firmware file naming scheme as the
CS35L56 ASoC driver.

This is not a compatibility break because no firmware files have
been published.

The original field layout matched the ASoC driver, but the way the
ASoC driver used the wm_adsp driver config to form this filename
was bugged. Fixing the ASoC driver to use the correct wm_adsp config
strings means that the 's' flag (to indicate a secured part) has to
move to somewhere after the first '-'.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 73cfbfa9caea ("ALSA: hda/cs35l56: Add driver for Cirrus Logic CS35L56 amplifier")
Link: https://msgid.link/r/20240129162737.497-17-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/pci/hda/cs35l56_hda.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index 7ba7234d8d9c0..081479f65fe7c 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -405,16 +405,19 @@ static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 	int ret = 0;
 
 	if (system_name && amp_name)
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc-%s-%s.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
+		*filename = kasprintf(GFP_KERNEL, "%scs35l56-%02x%s-dsp1-misc-%s-%s.%s", dir,
+				      cs35l56->base.rev,
+				      cs35l56->base.secured ? "-s" : "",
 				      system_name, amp_name, filetype);
 	else if (system_name)
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc-%s.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
+		*filename = kasprintf(GFP_KERNEL, "%scs35l56-%02x%s-dsp1-misc-%s.%s", dir,
+				      cs35l56->base.rev,
+				      cs35l56->base.secured ? "-s" : "",
 				      system_name, filetype);
 	else
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
+		*filename = kasprintf(GFP_KERNEL, "%scs35l56-%02x%s-dsp1-misc.%s", dir,
+				      cs35l56->base.rev,
+				      cs35l56->base.secured ? "-s" : "",
 				      filetype);
 
 	if (!*filename)
-- 
GitLab


From 6f8ad0480d82245961dae4d3280908611633872d Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:36 +0000
Subject: [PATCH 3781/4076] ALSA: hda: cs35l56: Firmware file must match the
 version of preloaded firmware

Check whether the firmware is already patched. If so, include the
firmware version in the firmware file name.

If the firmware has already been patched by the BIOS the driver
can only replace it if it has control of hard RESET.

If the driver cannot replace the firmware, it can still load a wmfw
(for ALSA control definitions) and/or a bin (for additional tunings).
But these must match the version of firmware that is running on the
CS35L56.

The firmware is pre-patched if either:
 - FIRMWARE_MISSING == 0, or
 - it is a secured CS35L56 (which implies that is was already patched),

cs35l56_hw_init() will set preloaded_fw_ver to the (non-zero)
firmware version if either of these conditions is true.

Normal (unpatched or replaceable firmware):
   cs35l56-rev-dsp1-misc[-system_name].[wmfw|bin]

Preloaded firmware:
   cs35l56-rev[-s]-VVVVVV-dsp1-misc[-system_name].[wmfw|bin]

Where:
   [-s] is an optional -s added into the name for a secured CS35L56
   VVVVVV is the 24-bit firmware version in hexadecimal.

Backport note:
This won't apply to kernel versions older than v6.6.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 73cfbfa9caea ("ALSA: hda/cs35l56: Add driver for Cirrus Logic CS35L56 amplifier")
Link: https://msgid.link/r/20240129162737.497-18-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/pci/hda/cs35l56_hda.c | 93 +++++++++++++++++++------------------
 1 file changed, 49 insertions(+), 44 deletions(-)

diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index 081479f65fe7c..32736d3e45bad 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -397,7 +397,7 @@ static const struct cs_dsp_client_ops cs35l56_hda_client_ops = {
 
 static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 					     const struct firmware **firmware, char **filename,
-					     const char *dir, const char *system_name,
+					     const char *base_name, const char *system_name,
 					     const char *amp_name,
 					     const char *filetype)
 {
@@ -405,20 +405,13 @@ static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 	int ret = 0;
 
 	if (system_name && amp_name)
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56-%02x%s-dsp1-misc-%s-%s.%s", dir,
-				      cs35l56->base.rev,
-				      cs35l56->base.secured ? "-s" : "",
+		*filename = kasprintf(GFP_KERNEL, "%s-%s-%s.%s", base_name,
 				      system_name, amp_name, filetype);
 	else if (system_name)
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56-%02x%s-dsp1-misc-%s.%s", dir,
-				      cs35l56->base.rev,
-				      cs35l56->base.secured ? "-s" : "",
+		*filename = kasprintf(GFP_KERNEL, "%s-%s.%s", base_name,
 				      system_name, filetype);
 	else
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56-%02x%s-dsp1-misc.%s", dir,
-				      cs35l56->base.rev,
-				      cs35l56->base.secured ? "-s" : "",
-				      filetype);
+		*filename = kasprintf(GFP_KERNEL, "%s.%s", base_name, filetype);
 
 	if (!*filename)
 		return -ENOMEM;
@@ -451,8 +444,8 @@ static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 	return 0;
 }
 
-static const char cirrus_dir[] = "cirrus/";
 static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
+					       unsigned int preloaded_fw_ver,
 					       const struct firmware **wmfw_firmware,
 					       char **wmfw_filename,
 					       const struct firmware **coeff_firmware,
@@ -460,29 +453,43 @@ static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
 {
 	const char *system_name = cs35l56->system_name;
 	const char *amp_name = cs35l56->amp_name;
+	char base_name[37];
 	int ret;
 
+	if (preloaded_fw_ver) {
+		snprintf(base_name, sizeof(base_name),
+			 "cirrus/cs35l56-%02x%s-%06x-dsp1-misc",
+			 cs35l56->base.rev,
+			 cs35l56->base.secured ? "-s" : "",
+			 preloaded_fw_ver & 0xffffff);
+	} else {
+		snprintf(base_name, sizeof(base_name),
+			 "cirrus/cs35l56-%02x%s-dsp1-misc",
+			 cs35l56->base.rev,
+			 cs35l56->base.secured ? "-s" : "");
+	}
+
 	if (system_name && amp_name) {
 		if (!cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						       cirrus_dir, system_name, amp_name, "wmfw")) {
+						       base_name, system_name, amp_name, "wmfw")) {
 			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, amp_name, "bin");
+							  base_name, system_name, amp_name, "bin");
 			return;
 		}
 	}
 
 	if (system_name) {
 		if (!cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						       cirrus_dir, system_name, NULL, "wmfw")) {
+						       base_name, system_name, NULL, "wmfw")) {
 			if (amp_name)
 				cs35l56_hda_request_firmware_file(cs35l56,
 								  coeff_firmware, coeff_filename,
-								  cirrus_dir, system_name,
+								  base_name, system_name,
 								  amp_name, "bin");
 			if (!*coeff_firmware)
 				cs35l56_hda_request_firmware_file(cs35l56,
 								  coeff_firmware, coeff_filename,
-								  cirrus_dir, system_name,
+								  base_name, system_name,
 								  NULL, "bin");
 			return;
 		}
@@ -493,26 +500,26 @@ static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
 		 */
 		if (amp_name)
 			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, amp_name, "bin");
+							  base_name, system_name, amp_name, "bin");
 		if (!*coeff_firmware)
 			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, NULL, "bin");
+							  base_name, system_name, NULL, "bin");
 
 		if (*coeff_firmware)
 			return;
 	}
 
 	ret = cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						cirrus_dir, NULL, NULL, "wmfw");
+						base_name, NULL, NULL, "wmfw");
 	if (!ret) {
 		cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-						  cirrus_dir, NULL, NULL, "bin");
+						  base_name, NULL, NULL, "bin");
 		return;
 	}
 
 	if (!*coeff_firmware)
 		cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-						  cirrus_dir, NULL, NULL, "bin");
+						  base_name, NULL, NULL, "bin");
 }
 
 static void cs35l56_hda_release_firmware_files(const struct firmware *wmfw_firmware,
@@ -546,7 +553,8 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	const struct firmware *wmfw_firmware = NULL;
 	char *coeff_filename = NULL;
 	char *wmfw_filename = NULL;
-	unsigned int firmware_missing;
+	unsigned int preloaded_fw_ver;
+	bool firmware_missing;
 	int ret = 0;
 
 	/* Prepare for a new DSP power-up */
@@ -557,24 +565,21 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 
 	pm_runtime_get_sync(cs35l56->base.dev);
 
-	ret = regmap_read(cs35l56->base.regmap, CS35L56_PROTECTION_STATUS, &firmware_missing);
-	if (ret) {
-		dev_err(cs35l56->base.dev, "Failed to read PROTECTION_STATUS: %d\n", ret);
+	/*
+	 * The firmware can only be upgraded if it is currently running
+	 * from the built-in ROM. If not, the wmfw/bin must be for the
+	 * version of firmware that is running on the chip.
+	 */
+	ret = cs35l56_read_prot_status(&cs35l56->base, &firmware_missing, &preloaded_fw_ver);
+	if (ret)
 		goto err_pm_put;
-	}
 
-	firmware_missing &= CS35L56_FIRMWARE_MISSING;
+	if (firmware_missing)
+		preloaded_fw_ver = 0;
 
-	/*
-	 * Firmware can only be downloaded if the CS35L56 is secured or is
-	 * running from the built-in ROM. If it is secured the BIOS will have
-	 * downloaded firmware, and the wmfw/bin files will only contain
-	 * tunings that are safe to download with the firmware running.
-	 */
-	if (cs35l56->base.secured || firmware_missing) {
-		cs35l56_hda_request_firmware_files(cs35l56, &wmfw_firmware, &wmfw_filename,
-						   &coeff_firmware, &coeff_filename);
-	}
+	cs35l56_hda_request_firmware_files(cs35l56, preloaded_fw_ver,
+					   &wmfw_firmware, &wmfw_filename,
+					   &coeff_firmware, &coeff_filename);
 
 	/*
 	 * If the BIOS didn't patch the firmware a bin file is mandatory to
@@ -589,12 +594,12 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	mutex_lock(&cs35l56->base.irq_lock);
 
 	/*
-	 * When the device is running in secure mode the firmware files can
-	 * only contain insecure tunings and therefore we do not need to
-	 * shutdown the firmware to apply them and can use the lower cost
-	 * reinit sequence instead.
+	 * If the firmware hasn't been patched it must be shutdown before
+	 * doing a full patch and reset afterwards. If it is already
+	 * running a patched version the firmware files only contain
+	 * tunings and we can use the lower cost reinit sequence instead.
 	 */
-	if (!cs35l56->base.secured && (wmfw_firmware || coeff_firmware)) {
+	if (firmware_missing && (wmfw_firmware || coeff_firmware)) {
 		ret = cs35l56_firmware_shutdown(&cs35l56->base);
 		if (ret)
 			goto err;
@@ -613,7 +618,7 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	if (coeff_filename)
 		dev_dbg(cs35l56->base.dev, "Loaded Coefficients: %s\n", coeff_filename);
 
-	if (cs35l56->base.secured) {
+	if (!firmware_missing) {
 		ret = cs35l56_mbox_send(&cs35l56->base, CS35L56_MBOX_CMD_AUDIO_REINIT);
 		if (ret)
 			goto err_powered_up;
-- 
GitLab


From 28876c1ae8b8cd1dacef50bd6c0555824774f0d2 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 29 Jan 2024 16:27:37 +0000
Subject: [PATCH 3782/4076] ALSA: hda: cs35l56: Remove unused test stub
 function

Remove an unused stub function that calls a non-existant function.

This function was accidentally added as part of commit
2144833e7b41 ("ALSA: hda: cirrus_scodec: Add KUnit test"). It was
a relic of an earlier version of the test that should have been
removed.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 2144833e7b41 ("ALSA: hda: cirrus_scodec: Add KUnit test")
Link: https://msgid.link/r/20240129162737.497-19-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/pci/hda/cs35l56_hda.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index 32736d3e45bad..75a14ba54fcd1 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -1063,16 +1063,6 @@ const struct dev_pm_ops cs35l56_hda_pm_ops = {
 };
 EXPORT_SYMBOL_NS_GPL(cs35l56_hda_pm_ops, SND_HDA_SCODEC_CS35L56);
 
-#if IS_ENABLED(CONFIG_SND_HDA_SCODEC_CS35L56_KUNIT_TEST)
-/* Hooks to export static function to KUnit test */
-
-int cs35l56_hda_test_hook_get_speaker_id(struct device *dev, int amp_index, int num_amps)
-{
-	return cs35l56_hda_get_speaker_id(dev, amp_index, num_amps);
-}
-EXPORT_SYMBOL_NS_GPL(cs35l56_hda_test_hook_get_speaker_id, SND_HDA_SCODEC_CS35L56);
-#endif
-
 MODULE_DESCRIPTION("CS35L56 HDA Driver");
 MODULE_IMPORT_NS(SND_HDA_CIRRUS_SCODEC);
 MODULE_IMPORT_NS(SND_HDA_CS_DSP_CONTROLS);
-- 
GitLab


From c7de2d9bb68a5fc71c25ff96705a80a76c8436eb Mon Sep 17 00:00:00 2001
From: Edson Juliano Drosdeck <edson.drosdeck@gmail.com>
Date: Thu, 1 Feb 2024 09:21:14 -0300
Subject: [PATCH 3783/4076] ALSA: hda/realtek: Enable headset mic on Vaio
 VJFE-ADL

Vaio VJFE-ADL is equipped with ALC269VC, and it needs
ALC298_FIXUP_SPK_VOLUME quirk to make its headset mic work.

Signed-off-by: Edson Juliano Drosdeck <edson.drosdeck@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240201122114.30080-1-edson.drosdeck@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f98520c0bed9f..6994c4c5073cb 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10331,6 +10331,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
+	SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
 	SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10),
-- 
GitLab


From 72bd80252feeb3bef8724230ee15d9f7ab541c6e Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 1 Feb 2024 06:42:36 -0700
Subject: [PATCH 3784/4076] io_uring/net: fix sr->len for IORING_OP_RECV with
 MSG_WAITALL and buffers

If we use IORING_OP_RECV with provided buffers and pass in '0' as the
length of the request, the length is retrieved from the selected buffer.
If MSG_WAITALL is also set and we get a short receive, then we may hit
the retry path which decrements sr->len and increments the buffer for
a retry. However, the length is still zero at this point, which means
that sr->len now becomes huge and import_ubuf() will cap it to
MAX_RW_COUNT and subsequently return -EFAULT for the range as a whole.

Fix this by always assigning sr->len once the buffer has been selected.

Cc: stable@vger.kernel.org
Fixes: 7ba89d2af17a ("io_uring: ensure recv and recvmsg handle MSG_WAITALL correctly")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/io_uring/net.c b/io_uring/net.c
index a12ff69e68434..43bc9a5f96f9d 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -923,6 +923,7 @@ retry_multishot:
 		if (!buf)
 			return -ENOBUFS;
 		sr->buf = buf;
+		sr->len = len;
 	}
 
 	ret = import_ubuf(ITER_DEST, sr->buf, len, &msg.msg_iter);
-- 
GitLab


From 6813cdca4ab94a238f8eb0cef3d3f3fcbdfb0ee0 Mon Sep 17 00:00:00 2001
From: Ma Jun <Jun.Ma2@amd.com>
Date: Wed, 31 Jan 2024 10:19:20 +0800
Subject: [PATCH 3785/4076] drm/amdgpu/pm: Use inline function for IP version
 check

Use existing inline function for IP version check.

Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 3230701d0d381..a9954ffc02c56 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2944,7 +2944,7 @@ static bool smu_v13_0_0_wbrf_support_check(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	switch (adev->ip_versions[MP1_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 	case IP_VERSION(13, 0, 0):
 		return smu->smc_fw_version >= 0x004e6300;
 	case IP_VERSION(13, 0, 10):
-- 
GitLab


From 04f647c8e456fcfabe9c252a4dcaee03b586fa4f Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Tue, 30 Jan 2024 17:36:10 +0530
Subject: [PATCH 3786/4076] octeontx2-pf: Remove xdp queues on program detach

XDP queues are created/destroyed when a XDP program
is attached/detached. In current driver xdp_queues are not
getting destroyed on program exit due to incorrect xdp_queue
and tot_tx_queue count values.

This patch fixes the issue by setting tot_tx_queue and xdp_queue
count to correct values. It also fixes xdp.data_hard_start address.

Fixes: 06059a1a9a4a ("octeontx2-pf: Add XDP support to netdev PF")
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Link: https://lore.kernel.org/r/20240130120610.16673-1-gakula@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 1 -
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c      | 3 +--
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c    | 7 +++----
 3 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 2928898c7f8df..7f786de610148 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -314,7 +314,6 @@ static int otx2_set_channels(struct net_device *dev,
 	pfvf->hw.tx_queues = channel->tx_count;
 	if (pfvf->xdp_prog)
 		pfvf->hw.xdp_queues = channel->rx_count;
-	pfvf->hw.non_qos_queues =  pfvf->hw.tx_queues + pfvf->hw.xdp_queues;
 
 	if (if_up)
 		err = dev->netdev_ops->ndo_open(dev);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index a57455aebff6f..e5fe67e738655 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1744,6 +1744,7 @@ int otx2_open(struct net_device *netdev)
 	/* RQ and SQs are mapped to different CQs,
 	 * so find out max CQ IRQs (i.e CINTs) needed.
 	 */
+	pf->hw.non_qos_queues =  pf->hw.tx_queues + pf->hw.xdp_queues;
 	pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues,
 			       pf->hw.tc_tx_queues);
 
@@ -2643,8 +2644,6 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog)
 		xdp_features_clear_redirect_target(dev);
 	}
 
-	pf->hw.non_qos_queues += pf->hw.xdp_queues;
-
 	if (if_up)
 		otx2_open(pf->netdev);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 4d519ea833b2c..f828d32737af0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -1403,7 +1403,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_cq_queue *cq,
 				     bool *need_xdp_flush)
 {
-	unsigned char *hard_start, *data;
+	unsigned char *hard_start;
 	int qidx = cq->cq_idx;
 	struct xdp_buff xdp;
 	struct page *page;
@@ -1417,9 +1417,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 	xdp_init_buff(&xdp, pfvf->rbsize, &cq->xdp_rxq);
 
-	data = (unsigned char *)phys_to_virt(pa);
-	hard_start = page_address(page);
-	xdp_prepare_buff(&xdp, hard_start, data - hard_start,
+	hard_start = (unsigned char *)phys_to_virt(pa);
+	xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM,
 			 cqe->sg.seg_size, false);
 
 	act = bpf_prog_run_xdp(prog, &xdp);
-- 
GitLab


From eaa1b01fe709d6a236a9cec74813e0400601fd23 Mon Sep 17 00:00:00 2001
From: Alexander Tsoy <alexander@tsoy.me>
Date: Thu, 1 Feb 2024 14:53:08 +0300
Subject: [PATCH 3787/4076] ALSA: usb-audio: Ignore clock selector errors for
 single connection

For devices with multiple clock sources connected to a selector, we need
to check what a clock selector control request has returned. This is
needed to ensure that a requested clock source is indeed selected and for
autoclock feature to work.

For devices with single clock source connected, if we get an error there
is nothing else we can do about it. We can't skip clock selector setup as
it is required by some devices. So lets just ignore error in this case.

This should fix various buggy Mackie devices:

[  649.109785] usb 1-1.3: parse_audio_format_rates_v2v3(): unable to find clock source (clock -32)
[  649.111946] usb 1-1.3: parse_audio_format_rates_v2v3(): unable to find clock source (clock -32)
[  649.113822] usb 1-1.3: parse_audio_format_rates_v2v3(): unable to find clock source (clock -32)

There is also interesting info from the Windows documentation [1] (this
is probably why manufacturers dont't even test this feature):

"The USB Audio 2.0 driver doesn't support clock selection. The driver
uses the Clock Source Entity, which is selected by default and never
issues a Clock Selector Control SET CUR request."

Link: https://learn.microsoft.com/en-us/windows-hardware/drivers/audio/usb-2-0-audio-drivers [1]
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217314
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218175
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218342
Signed-off-by: Alexander Tsoy <alexander@tsoy.me>
Link: https://lore.kernel.org/r/20240201115308.17838-1-alexander@tsoy.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/clock.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index a8204c6d6fac1..60fcb872a80b6 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -347,8 +347,16 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 			    !writeable)
 				return ret;
 			err = uac_clock_selector_set_val(chip, entity_id, cur);
-			if (err < 0)
+			if (err < 0) {
+				if (pins == 1) {
+					usb_audio_dbg(chip,
+						      "%s(): selector returned an error, "
+						      "assuming a firmware bug, id %d, ret %d\n",
+						      __func__, clock_id, err);
+					return ret;
+				}
 				return err;
+			}
 		}
 
 		if (!validate || ret > 0 || !chip->autoclock)
-- 
GitLab


From 49304c2b93e4f7468b51ef717cbe637981397115 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 31 Jan 2024 23:32:27 -0500
Subject: [PATCH 3788/4076] tracefs: dentry lookup crapectomy

The dentry lookup for eventfs files was very broken, and had lots of
signs of the old situation where the filesystem names were all created
statically in the dentry tree, rather than being looked up dynamically
based on the eventfs data structures.

You could see it in the naming - how it claimed to "create" dentries
rather than just look up the dentries that were given it.

You could see it in various nonsensical and very incorrect operations,
like using "simple_lookup()" on the dentries that were passed in, which
only results in those dentries becoming negative dentries.  Which meant
that any other lookup would possibly return ENOENT if it saw that
negative dentry before the data was then later filled in.

You could see it in the immense amount of nonsensical code that didn't
actually just do lookups.

Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240131233227.73db55e1@gandalf.local.home

Cc: stable@vger.kernel.org
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 275 +++++++--------------------------------
 fs/tracefs/inode.c       |  69 ----------
 fs/tracefs/internal.h    |   3 -
 3 files changed, 50 insertions(+), 297 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index e9819d719d2ac..04c2ab90f93e6 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -230,7 +230,6 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 {
 	struct eventfs_inode *ei;
 
-	mutex_lock(&eventfs_mutex);
 	do {
 		// The parent is stable because we do not do renames
 		dentry = dentry->d_parent;
@@ -247,7 +246,6 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 		}
 		// Walk upwards until you find the events inode
 	} while (!ei->is_events);
-	mutex_unlock(&eventfs_mutex);
 
 	update_top_events_attr(ei, dentry->d_sb);
 
@@ -280,11 +278,10 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
 }
 
 /**
- * create_file - create a file in the tracefs filesystem
- * @name: the name of the file to create.
+ * lookup_file - look up a file in the tracefs filesystem
+ * @dentry: the dentry to look up
  * @mode: the permission that the file should have.
  * @attr: saved attributes changed by user
- * @parent: parent dentry for this file.
  * @data: something that the caller will want to get to later on.
  * @fop: struct file_operations that should be used for this file.
  *
@@ -292,13 +289,13 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
  * directory. The inode.i_private pointer will point to @data in the open()
  * call.
  */
-static struct dentry *create_file(const char *name, umode_t mode,
+static struct dentry *lookup_file(struct dentry *dentry,
+				  umode_t mode,
 				  struct eventfs_attr *attr,
-				  struct dentry *parent, void *data,
+				  void *data,
 				  const struct file_operations *fop)
 {
 	struct tracefs_inode *ti;
-	struct dentry *dentry;
 	struct inode *inode;
 
 	if (!(mode & S_IFMT))
@@ -307,15 +304,9 @@ static struct dentry *create_file(const char *name, umode_t mode,
 	if (WARN_ON_ONCE(!S_ISREG(mode)))
 		return NULL;
 
-	WARN_ON_ONCE(!parent);
-	dentry = eventfs_start_creating(name, parent);
-
-	if (IS_ERR(dentry))
-		return dentry;
-
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return eventfs_failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 
 	/* If the user updated the directory's attributes, use them */
 	update_inode_attr(dentry, inode, attr, mode);
@@ -329,32 +320,29 @@ static struct dentry *create_file(const char *name, umode_t mode,
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
-	d_instantiate(dentry, inode);
+
+	d_add(dentry, inode);
 	fsnotify_create(dentry->d_parent->d_inode, dentry);
-	return eventfs_end_creating(dentry);
+	return dentry;
 };
 
 /**
- * create_dir - create a dir in the tracefs filesystem
+ * lookup_dir_entry - look up a dir in the tracefs filesystem
+ * @dentry: the directory to look up
  * @ei: the eventfs_inode that represents the directory to create
- * @parent: parent dentry for this file.
  *
- * This function will create a dentry for a directory represented by
+ * This function will look up a dentry for a directory represented by
  * a eventfs_inode.
  */
-static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent)
+static struct dentry *lookup_dir_entry(struct dentry *dentry,
+	struct eventfs_inode *pei, struct eventfs_inode *ei)
 {
 	struct tracefs_inode *ti;
-	struct dentry *dentry;
 	struct inode *inode;
 
-	dentry = eventfs_start_creating(ei->name, parent);
-	if (IS_ERR(dentry))
-		return dentry;
-
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return eventfs_failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 
 	/* If the user updated the directory's attributes, use them */
 	update_inode_attr(dentry, inode, &ei->attr,
@@ -371,11 +359,14 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
 	/* Only directories have ti->private set to an ei, not files */
 	ti->private = ei;
 
+	dentry->d_fsdata = ei;
+        ei->dentry = dentry;	// Remove me!
+
 	inc_nlink(inode);
-	d_instantiate(dentry, inode);
+	d_add(dentry, inode);
 	inc_nlink(dentry->d_parent->d_inode);
 	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
-	return eventfs_end_creating(dentry);
+	return dentry;
 }
 
 static void free_ei(struct eventfs_inode *ei)
@@ -425,7 +416,7 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
 }
 
 /**
- * create_file_dentry - create a dentry for a file of an eventfs_inode
+ * lookup_file_dentry - create a dentry for a file of an eventfs_inode
  * @ei: the eventfs_inode that the file will be created under
  * @idx: the index into the d_children[] of the @ei
  * @parent: The parent dentry of the created file.
@@ -438,157 +429,21 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
  * address located at @e_dentry.
  */
 static struct dentry *
-create_file_dentry(struct eventfs_inode *ei, int idx,
-		   struct dentry *parent, const char *name, umode_t mode, void *data,
+lookup_file_dentry(struct dentry *dentry,
+		   struct eventfs_inode *ei, int idx,
+		   umode_t mode, void *data,
 		   const struct file_operations *fops)
 {
 	struct eventfs_attr *attr = NULL;
 	struct dentry **e_dentry = &ei->d_children[idx];
-	struct dentry *dentry;
-
-	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
 
-	mutex_lock(&eventfs_mutex);
-	if (ei->is_freed) {
-		mutex_unlock(&eventfs_mutex);
-		return NULL;
-	}
-	/* If the e_dentry already has a dentry, use it */
-	if (*e_dentry) {
-		dget(*e_dentry);
-		mutex_unlock(&eventfs_mutex);
-		return *e_dentry;
-	}
-
-	/* ei->entry_attrs are protected by SRCU */
 	if (ei->entry_attrs)
 		attr = &ei->entry_attrs[idx];
 
-	mutex_unlock(&eventfs_mutex);
-
-	dentry = create_file(name, mode, attr, parent, data, fops);
+	dentry->d_fsdata = ei;		// NOTE: ei of _parent_
+	lookup_file(dentry, mode, attr, data, fops);
 
-	mutex_lock(&eventfs_mutex);
-
-	if (IS_ERR_OR_NULL(dentry)) {
-		/*
-		 * When the mutex was released, something else could have
-		 * created the dentry for this e_dentry. In which case
-		 * use that one.
-		 *
-		 * If ei->is_freed is set, the e_dentry is currently on its
-		 * way to being freed, don't return it. If e_dentry is NULL
-		 * it means it was already freed.
-		 */
-		if (ei->is_freed) {
-			dentry = NULL;
-		} else {
-			dentry = *e_dentry;
-			dget(dentry);
-		}
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-
-	if (!*e_dentry && !ei->is_freed) {
-		*e_dentry = dentry;
-		dentry->d_fsdata = ei;
-	} else {
-		/*
-		 * Should never happen unless we get here due to being freed.
-		 * Otherwise it means two dentries exist with the same name.
-		 */
-		WARN_ON_ONCE(!ei->is_freed);
-		dentry = NULL;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	return dentry;
-}
-
-/**
- * eventfs_post_create_dir - post create dir routine
- * @ei: eventfs_inode of recently created dir
- *
- * Map the meta-data of files within an eventfs dir to their parent dentry
- */
-static void eventfs_post_create_dir(struct eventfs_inode *ei)
-{
-	struct eventfs_inode *ei_child;
-
-	lockdep_assert_held(&eventfs_mutex);
-
-	/* srcu lock already held */
-	/* fill parent-child relation */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		ei_child->d_parent = ei->dentry;
-	}
-}
-
-/**
- * create_dir_dentry - Create a directory dentry for the eventfs_inode
- * @pei: The eventfs_inode parent of ei.
- * @ei: The eventfs_inode to create the directory for
- * @parent: The dentry of the parent of this directory
- *
- * This creates and attaches a directory dentry to the eventfs_inode @ei.
- */
-static struct dentry *
-create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
-		  struct dentry *parent)
-{
-	struct dentry *dentry = NULL;
-
-	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
-
-	mutex_lock(&eventfs_mutex);
-	if (pei->is_freed || ei->is_freed) {
-		mutex_unlock(&eventfs_mutex);
-		return NULL;
-	}
-	if (ei->dentry) {
-		/* If the eventfs_inode already has a dentry, use it */
-		dentry = ei->dentry;
-		dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	dentry = create_dir(ei, parent);
-
-	mutex_lock(&eventfs_mutex);
-
-	if (IS_ERR_OR_NULL(dentry) && !ei->is_freed) {
-		/*
-		 * When the mutex was released, something else could have
-		 * created the dentry for this e_dentry. In which case
-		 * use that one.
-		 *
-		 * If ei->is_freed is set, the e_dentry is currently on its
-		 * way to being freed.
-		 */
-		dentry = ei->dentry;
-		if (dentry)
-			dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-
-	if (!ei->dentry && !ei->is_freed) {
-		ei->dentry = dentry;
-		eventfs_post_create_dir(ei);
-		dentry->d_fsdata = ei;
-	} else {
-		/*
-		 * Should never happen unless we get here due to being freed.
-		 * Otherwise it means two dentries exist with the same name.
-		 */
-		WARN_ON_ONCE(!ei->is_freed);
-		dentry = NULL;
-	}
-	mutex_unlock(&eventfs_mutex);
+	*e_dentry = dentry;	// Remove me
 
 	return dentry;
 }
@@ -607,79 +462,49 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags)
 {
-	const struct file_operations *fops;
-	const struct eventfs_entry *entry;
 	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct dentry *ei_dentry = NULL;
-	struct dentry *ret = NULL;
-	struct dentry *d;
 	const char *name = dentry->d_name.name;
-	umode_t mode;
-	void *data;
-	int idx;
-	int i;
-	int r;
 
 	ti = get_tracefs(dir);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
-		return NULL;
-
-	/* Grab srcu to prevent the ei from going away */
-	idx = srcu_read_lock(&eventfs_srcu);
+		return ERR_PTR(-EIO);
 
-	/*
-	 * Grab the eventfs_mutex to consistent value from ti->private.
-	 * This s
-	 */
 	mutex_lock(&eventfs_mutex);
-	ei = READ_ONCE(ti->private);
-	if (ei && !ei->is_freed)
-		ei_dentry = READ_ONCE(ei->dentry);
-	mutex_unlock(&eventfs_mutex);
 
-	if (!ei || !ei_dentry)
+	ei = ti->private;
+	if (!ei || ei->is_freed)
 		goto out;
 
-	data = ei->data;
-
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
+	list_for_each_entry(ei_child, &ei->children, list) {
 		if (strcmp(ei_child->name, name) != 0)
 			continue;
-		ret = simple_lookup(dir, dentry, flags);
-		if (IS_ERR(ret))
+		if (ei_child->is_freed)
 			goto out;
-		d = create_dir_dentry(ei, ei_child, ei_dentry);
-		dput(d);
+		lookup_dir_entry(dentry, ei, ei_child);
 		goto out;
 	}
 
-	for (i = 0; i < ei->nr_entries; i++) {
-		entry = &ei->entries[i];
-		if (strcmp(name, entry->name) == 0) {
-			void *cdata = data;
-			mutex_lock(&eventfs_mutex);
-			/* If ei->is_freed, then the event itself may be too */
-			if (!ei->is_freed)
-				r = entry->callback(name, &mode, &cdata, &fops);
-			else
-				r = -1;
-			mutex_unlock(&eventfs_mutex);
-			if (r <= 0)
-				continue;
-			ret = simple_lookup(dir, dentry, flags);
-			if (IS_ERR(ret))
-				goto out;
-			d = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
-			dput(d);
-			break;
-		}
+	for (int i = 0; i < ei->nr_entries; i++) {
+		void *data;
+		umode_t mode;
+		const struct file_operations *fops;
+		const struct eventfs_entry *entry = &ei->entries[i];
+
+		if (strcmp(name, entry->name) != 0)
+			continue;
+
+		data = ei->data;
+		if (entry->callback(name, &mode, &data, &fops) <= 0)
+			goto out;
+
+		lookup_file_dentry(dentry, ei, i, mode, data, fops);
+		goto out;
 	}
  out:
-	srcu_read_unlock(&eventfs_srcu, idx);
-	return ret;
+	mutex_unlock(&eventfs_mutex);
+	return NULL;
 }
 
 /*
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 888e420878477..5c84460feeebb 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -495,75 +495,6 @@ struct dentry *tracefs_end_creating(struct dentry *dentry)
 	return dentry;
 }
 
-/**
- * eventfs_start_creating - start the process of creating a dentry
- * @name: Name of the file created for the dentry
- * @parent: The parent dentry where this dentry will be created
- *
- * This is a simple helper function for the dynamically created eventfs
- * files. When the directory of the eventfs files are accessed, their
- * dentries are created on the fly. This function is used to start that
- * process.
- */
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
-{
-	struct dentry *dentry;
-	int error;
-
-	/* Must always have a parent. */
-	if (WARN_ON_ONCE(!parent))
-		return ERR_PTR(-EINVAL);
-
-	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
-			      &tracefs_mount_count);
-	if (error)
-		return ERR_PTR(error);
-
-	if (unlikely(IS_DEADDIR(parent->d_inode)))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_one_len(name, parent, strlen(name));
-
-	if (!IS_ERR(dentry) && dentry->d_inode) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-	}
-
-	if (IS_ERR(dentry))
-		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-
-	return dentry;
-}
-
-/**
- * eventfs_failed_creating - clean up a failed eventfs dentry creation
- * @dentry: The dentry to clean up
- *
- * If after calling eventfs_start_creating(), a failure is detected, the
- * resources created by eventfs_start_creating() needs to be cleaned up. In
- * that case, this function should be called to perform that clean up.
- */
-struct dentry *eventfs_failed_creating(struct dentry *dentry)
-{
-	dput(dentry);
-	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-	return NULL;
-}
-
-/**
- * eventfs_end_creating - Finish the process of creating a eventfs dentry
- * @dentry: The dentry that has successfully been created.
- *
- * This function is currently just a place holder to match
- * eventfs_start_creating(). In case any synchronization needs to be added,
- * this function will be used to implement that without having to modify
- * the callers of eventfs_start_creating().
- */
-struct dentry *eventfs_end_creating(struct dentry *dentry)
-{
-	return dentry;
-}
-
 /* Find the inode that this will use for default */
 static struct inode *instance_inode(struct dentry *parent, struct inode *inode)
 {
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 7d84349ade872..09037e2c173dc 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -80,9 +80,6 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
 struct dentry *tracefs_end_creating(struct dentry *dentry);
 struct dentry *tracefs_failed_creating(struct dentry *dentry);
 struct inode *tracefs_get_inode(struct super_block *sb);
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
-struct dentry *eventfs_failed_creating(struct dentry *dentry);
-struct dentry *eventfs_end_creating(struct dentry *dentry);
 void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */
-- 
GitLab


From 408600be78cdb8c650a97ecc7ff411cb216811b5 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 31 Jan 2024 13:49:23 -0500
Subject: [PATCH 3789/4076] eventfs: Remove unused d_parent pointer field

It's never used

Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240131185512.961772428@goodmis.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 4 +---
 fs/tracefs/internal.h    | 2 --
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 04c2ab90f93e6..16ca8d9759b18 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -680,10 +680,8 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 	INIT_LIST_HEAD(&ei->list);
 
 	mutex_lock(&eventfs_mutex);
-	if (!parent->is_freed) {
+	if (!parent->is_freed)
 		list_add_tail(&ei->list, &parent->children);
-		ei->d_parent = parent->dentry;
-	}
 	mutex_unlock(&eventfs_mutex);
 
 	/* Was the parent freed? */
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 09037e2c173dc..932733a2696a1 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -36,7 +36,6 @@ struct eventfs_attr {
  * @name:	the name of the directory to create
  * @children:	link list into the child eventfs_inode
  * @dentry:     the dentry of the directory
- * @d_parent:   pointer to the parent's dentry
  * @d_children: The array of dentries to represent the files when created
  * @entry_attrs: Saved mode and ownership of the @d_children
  * @attr:	Saved mode and ownership of eventfs_inode itself
@@ -51,7 +50,6 @@ struct eventfs_inode {
 	const char			*name;
 	struct list_head		children;
 	struct dentry			*dentry; /* Check is_freed to access */
-	struct dentry			*d_parent;
 	struct dentry			**d_children;
 	struct eventfs_attr		*entry_attrs;
 	struct eventfs_attr		attr;
-- 
GitLab


From 8dce06e98c70a7fcbb4bca7d90faf40522e65c58 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 31 Jan 2024 13:49:24 -0500
Subject: [PATCH 3790/4076] eventfs: Clean up dentry ops and add revalidate
 function

In order for the dentries to stay up-to-date with the eventfs changes,
just add a 'd_revalidate' function that checks the 'is_freed' bit.

Also, clean up the dentry release to actually use d_release() rather
than the slightly odd d_iput() function.  We don't care about the inode,
all we want to do is to get rid of the refcount to the eventfs data
added by dentry->d_fsdata.

It would probably be cleaner to make eventfs its own filesystem, or at
least set its own dentry ops when looking up eventfs files.  But as it
is, only eventfs dentries use d_fsdata, so we don't really need to split
these things up by use.

Another thing that might be worth doing is to make all eventfs lookups
mark their dentries as not worth caching.  We could do that with
d_delete(), but the DCACHE_DONTCACHE flag would likely be even better.

As it is, the dentries are all freeable, but they only tend to get freed
at memory pressure rather than more proactively.  But that's a separate
issue.

Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240131185513.124644253@goodmis.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c |  5 ++---
 fs/tracefs/inode.c       | 27 ++++++++++++++++++---------
 fs/tracefs/internal.h    |  3 ++-
 3 files changed, 22 insertions(+), 13 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 16ca8d9759b18..b2285d5f3fedf 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -378,13 +378,12 @@ static void free_ei(struct eventfs_inode *ei)
 }
 
 /**
- * eventfs_set_ei_status_free - remove the dentry reference from an eventfs_inode
- * @ti: the tracefs_inode of the dentry
+ * eventfs_d_release - dentry is going away
  * @dentry: dentry which has the reference to remove.
  *
  * Remove the association between a dentry from an eventfs_inode.
  */
-void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
+void eventfs_d_release(struct dentry *dentry)
 {
 	struct eventfs_inode *ei;
 	int i;
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 5c84460feeebb..d65ffad4c327c 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -377,21 +377,30 @@ static const struct super_operations tracefs_super_operations = {
 	.show_options	= tracefs_show_options,
 };
 
-static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
+/*
+ * It would be cleaner if eventfs had its own dentry ops.
+ *
+ * Note that d_revalidate is called potentially under RCU,
+ * so it can't take the eventfs mutex etc. It's fine - if
+ * we open a file just as it's marked dead, things will
+ * still work just fine, and just see the old stale case.
+ */
+static void tracefs_d_release(struct dentry *dentry)
 {
-	struct tracefs_inode *ti;
+	if (dentry->d_fsdata)
+		eventfs_d_release(dentry);
+}
 
-	if (!dentry || !inode)
-		return;
+static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct eventfs_inode *ei = dentry->d_fsdata;
 
-	ti = get_tracefs(inode);
-	if (ti && ti->flags & TRACEFS_EVENT_INODE)
-		eventfs_set_ei_status_free(ti, dentry);
-	iput(inode);
+	return !(ei && ei->is_freed);
 }
 
 static const struct dentry_operations tracefs_dentry_operations = {
-	.d_iput = tracefs_dentry_iput,
+	.d_revalidate = tracefs_d_revalidate,
+	.d_release = tracefs_d_release,
 };
 
 static int trace_fill_super(struct super_block *sb, void *data, int silent)
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 932733a2696a1..4b50a0668055b 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -78,6 +78,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
 struct dentry *tracefs_end_creating(struct dentry *dentry);
 struct dentry *tracefs_failed_creating(struct dentry *dentry);
 struct inode *tracefs_get_inode(struct super_block *sb);
-void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
+
+void eventfs_d_release(struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */
-- 
GitLab


From 43aa6f97c2d03a52c1ddb86768575fc84344bdbb Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 31 Jan 2024 13:49:25 -0500
Subject: [PATCH 3791/4076] eventfs: Get rid of dentry pointers without
 refcounts

The eventfs inode had pointers to dentries (and child dentries) without
actually holding a refcount on said pointer.  That is fundamentally
broken, and while eventfs tried to then maintain coherence with dentries
going away by hooking into the '.d_iput' callback, that doesn't actually
work since it's not ordered wrt lookups.

There were two reasonms why eventfs tried to keep a pointer to a dentry:

 - the creation of a 'events' directory would actually have a stable
   dentry pointer that it created with tracefs_start_creating().

   And it needed that dentry when tearing it all down again in
   eventfs_remove_events_dir().

   This use is actually ok, because the special top-level events
   directory dentries are actually stable, not just a temporary cache of
   the eventfs data structures.

 - the 'eventfs_inode' (aka ei) needs to stay around as long as there
   are dentries that refer to it.

   It then used these dentry pointers as a replacement for doing
   reference counting: it would try to make sure that there was only
   ever one dentry associated with an event_inode, and keep a child
   dentry array around to see which dentries might still refer to the
   parent ei.

This gets rid of the invalid dentry pointer use, and renames the one
valid case to a different name to make it clear that it's not just any
random dentry.

The magic child dentry array that is kind of a "reverse reference list"
is simply replaced by having child dentries take a ref to the ei.  As
does the directory dentries.  That makes the broken use case go away.

Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240131185513.280463000@goodmis.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 248 ++++++++++++---------------------------
 fs/tracefs/internal.h    |   7 +-
 2 files changed, 78 insertions(+), 177 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index b2285d5f3fedf..515fdace1eeaf 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -62,6 +62,35 @@ enum {
 
 #define EVENTFS_MODE_MASK	(EVENTFS_SAVE_MODE - 1)
 
+/*
+ * eventfs_inode reference count management.
+ *
+ * NOTE! We count only references from dentries, in the
+ * form 'dentry->d_fsdata'. There are also references from
+ * directory inodes ('ti->private'), but the dentry reference
+ * count is always a superset of the inode reference count.
+ */
+static void release_ei(struct kref *ref)
+{
+	struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
+	kfree(ei->entry_attrs);
+	kfree_const(ei->name);
+	kfree_rcu(ei, rcu);
+}
+
+static inline void put_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_put(&ei->kref, release_ei);
+}
+
+static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_get(&ei->kref);
+	return ei;
+}
+
 static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags);
@@ -289,7 +318,8 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
  * directory. The inode.i_private pointer will point to @data in the open()
  * call.
  */
-static struct dentry *lookup_file(struct dentry *dentry,
+static struct dentry *lookup_file(struct eventfs_inode *parent_ei,
+				  struct dentry *dentry,
 				  umode_t mode,
 				  struct eventfs_attr *attr,
 				  void *data,
@@ -302,7 +332,7 @@ static struct dentry *lookup_file(struct dentry *dentry,
 		mode |= S_IFREG;
 
 	if (WARN_ON_ONCE(!S_ISREG(mode)))
-		return NULL;
+		return ERR_PTR(-EIO);
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
@@ -321,9 +351,12 @@ static struct dentry *lookup_file(struct dentry *dentry,
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
 
+	// Files have their parent's ei as their fsdata
+	dentry->d_fsdata = get_ei(parent_ei);
+
 	d_add(dentry, inode);
 	fsnotify_create(dentry->d_parent->d_inode, dentry);
-	return dentry;
+	return NULL;
 };
 
 /**
@@ -359,22 +392,29 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry,
 	/* Only directories have ti->private set to an ei, not files */
 	ti->private = ei;
 
-	dentry->d_fsdata = ei;
-        ei->dentry = dentry;	// Remove me!
+	dentry->d_fsdata = get_ei(ei);
 
 	inc_nlink(inode);
 	d_add(dentry, inode);
 	inc_nlink(dentry->d_parent->d_inode);
 	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
-	return dentry;
+	return NULL;
 }
 
-static void free_ei(struct eventfs_inode *ei)
+static inline struct eventfs_inode *alloc_ei(const char *name)
 {
-	kfree_const(ei->name);
-	kfree(ei->d_children);
-	kfree(ei->entry_attrs);
-	kfree(ei);
+	struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+
+	if (!ei)
+		return NULL;
+
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name) {
+		kfree(ei);
+		return NULL;
+	}
+	kref_init(&ei->kref);
+	return ei;
 }
 
 /**
@@ -385,39 +425,13 @@ static void free_ei(struct eventfs_inode *ei)
  */
 void eventfs_d_release(struct dentry *dentry)
 {
-	struct eventfs_inode *ei;
-	int i;
-
-	mutex_lock(&eventfs_mutex);
-
-	ei = dentry->d_fsdata;
-	if (!ei)
-		goto out;
-
-	/* This could belong to one of the files of the ei */
-	if (ei->dentry != dentry) {
-		for (i = 0; i < ei->nr_entries; i++) {
-			if (ei->d_children[i] == dentry)
-				break;
-		}
-		if (WARN_ON_ONCE(i == ei->nr_entries))
-			goto out;
-		ei->d_children[i] = NULL;
-	} else if (ei->is_freed) {
-		free_ei(ei);
-	} else {
-		ei->dentry = NULL;
-	}
-
-	dentry->d_fsdata = NULL;
- out:
-	mutex_unlock(&eventfs_mutex);
+	put_ei(dentry->d_fsdata);
 }
 
 /**
  * lookup_file_dentry - create a dentry for a file of an eventfs_inode
  * @ei: the eventfs_inode that the file will be created under
- * @idx: the index into the d_children[] of the @ei
+ * @idx: the index into the entry_attrs[] of the @ei
  * @parent: The parent dentry of the created file.
  * @name: The name of the file to create
  * @mode: The mode of the file.
@@ -434,17 +448,11 @@ lookup_file_dentry(struct dentry *dentry,
 		   const struct file_operations *fops)
 {
 	struct eventfs_attr *attr = NULL;
-	struct dentry **e_dentry = &ei->d_children[idx];
 
 	if (ei->entry_attrs)
 		attr = &ei->entry_attrs[idx];
 
-	dentry->d_fsdata = ei;		// NOTE: ei of _parent_
-	lookup_file(dentry, mode, attr, data, fops);
-
-	*e_dentry = dentry;	// Remove me
-
-	return dentry;
+	return lookup_file(ei, dentry, mode, attr, data, fops);
 }
 
 /**
@@ -465,6 +473,7 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
 	const char *name = dentry->d_name.name;
+	struct dentry *result = NULL;
 
 	ti = get_tracefs(dir);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
@@ -481,7 +490,7 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 			continue;
 		if (ei_child->is_freed)
 			goto out;
-		lookup_dir_entry(dentry, ei, ei_child);
+		result = lookup_dir_entry(dentry, ei, ei_child);
 		goto out;
 	}
 
@@ -498,12 +507,12 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 		if (entry->callback(name, &mode, &data, &fops) <= 0)
 			goto out;
 
-		lookup_file_dentry(dentry, ei, i, mode, data, fops);
+		result = lookup_file_dentry(dentry, ei, i, mode, data, fops);
 		goto out;
 	}
  out:
 	mutex_unlock(&eventfs_mutex);
-	return NULL;
+	return result;
 }
 
 /*
@@ -653,25 +662,10 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 	if (!parent)
 		return ERR_PTR(-EINVAL);
 
-	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	ei = alloc_ei(name);
 	if (!ei)
 		return ERR_PTR(-ENOMEM);
 
-	ei->name = kstrdup_const(name, GFP_KERNEL);
-	if (!ei->name) {
-		kfree(ei);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	if (size) {
-		ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL);
-		if (!ei->d_children) {
-			kfree_const(ei->name);
-			kfree(ei);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
-
 	ei->entries = entries;
 	ei->nr_entries = size;
 	ei->data = data;
@@ -685,7 +679,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 
 	/* Was the parent freed? */
 	if (list_empty(&ei->list)) {
-		free_ei(ei);
+		put_ei(ei);
 		ei = NULL;
 	}
 	return ei;
@@ -720,28 +714,20 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	if (IS_ERR(dentry))
 		return ERR_CAST(dentry);
 
-	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	ei = alloc_ei(name);
 	if (!ei)
-		goto fail_ei;
+		goto fail;
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
 		goto fail;
 
-	if (size) {
-		ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL);
-		if (!ei->d_children)
-			goto fail;
-	}
-
-	ei->dentry = dentry;
+	// Note: we have a ref to the dentry from tracefs_start_creating()
+	ei->events_dir = dentry;
 	ei->entries = entries;
 	ei->nr_entries = size;
 	ei->is_events = 1;
 	ei->data = data;
-	ei->name = kstrdup_const(name, GFP_KERNEL);
-	if (!ei->name)
-		goto fail;
 
 	/* Save the ownership of this directory */
 	uid = d_inode(dentry->d_parent)->i_uid;
@@ -772,7 +758,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
-	dentry->d_fsdata = ei;
+	dentry->d_fsdata = get_ei(ei);
 
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
@@ -784,72 +770,11 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	return ei;
 
  fail:
-	kfree(ei->d_children);
-	kfree(ei);
- fail_ei:
+	put_ei(ei);
 	tracefs_failed_creating(dentry);
 	return ERR_PTR(-ENOMEM);
 }
 
-static LLIST_HEAD(free_list);
-
-static void eventfs_workfn(struct work_struct *work)
-{
-        struct eventfs_inode *ei, *tmp;
-        struct llist_node *llnode;
-
-	llnode = llist_del_all(&free_list);
-        llist_for_each_entry_safe(ei, tmp, llnode, llist) {
-		/* This dput() matches the dget() from unhook_dentry() */
-		for (int i = 0; i < ei->nr_entries; i++) {
-			if (ei->d_children[i])
-				dput(ei->d_children[i]);
-		}
-		/* This should only get here if it had a dentry */
-		if (!WARN_ON_ONCE(!ei->dentry))
-			dput(ei->dentry);
-        }
-}
-
-static DECLARE_WORK(eventfs_work, eventfs_workfn);
-
-static void free_rcu_ei(struct rcu_head *head)
-{
-	struct eventfs_inode *ei = container_of(head, struct eventfs_inode, rcu);
-
-	if (ei->dentry) {
-		/* Do not free the ei until all references of dentry are gone */
-		if (llist_add(&ei->llist, &free_list))
-			queue_work(system_unbound_wq, &eventfs_work);
-		return;
-	}
-
-	/* If the ei doesn't have a dentry, neither should its children */
-	for (int i = 0; i < ei->nr_entries; i++) {
-		WARN_ON_ONCE(ei->d_children[i]);
-	}
-
-	free_ei(ei);
-}
-
-static void unhook_dentry(struct dentry *dentry)
-{
-	if (!dentry)
-		return;
-	/*
-	 * Need to add a reference to the dentry that is expected by
-	 * simple_recursive_removal(), which will include a dput().
-	 */
-	dget(dentry);
-
-	/*
-	 * Also add a reference for the dput() in eventfs_workfn().
-	 * That is required as that dput() will free the ei after
-	 * the SRCU grace period is over.
-	 */
-	dget(dentry);
-}
-
 /**
  * eventfs_remove_rec - remove eventfs dir or file from list
  * @ei: eventfs_inode to be removed.
@@ -862,8 +787,6 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 {
 	struct eventfs_inode *ei_child;
 
-	if (!ei)
-		return;
 	/*
 	 * Check recursion depth. It should never be greater than 3:
 	 * 0 - events/
@@ -875,28 +798,12 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 		return;
 
 	/* search for nested folders or files */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 lockdep_is_held(&eventfs_mutex)) {
-		/* Children only have dentry if parent does */
-		WARN_ON_ONCE(ei_child->dentry && !ei->dentry);
+	list_for_each_entry(ei_child, &ei->children, list)
 		eventfs_remove_rec(ei_child, level + 1);
-	}
-
 
 	ei->is_freed = 1;
-
-	for (int i = 0; i < ei->nr_entries; i++) {
-		if (ei->d_children[i]) {
-			/* Children only have dentry if parent does */
-			WARN_ON_ONCE(!ei->dentry);
-			unhook_dentry(ei->d_children[i]);
-		}
-	}
-
-	unhook_dentry(ei->dentry);
-
-	list_del_rcu(&ei->list);
-	call_srcu(&eventfs_srcu, &ei->rcu, free_rcu_ei);
+	list_del(&ei->list);
+	put_ei(ei);
 }
 
 /**
@@ -907,22 +814,12 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
  */
 void eventfs_remove_dir(struct eventfs_inode *ei)
 {
-	struct dentry *dentry;
-
 	if (!ei)
 		return;
 
 	mutex_lock(&eventfs_mutex);
-	dentry = ei->dentry;
 	eventfs_remove_rec(ei, 0);
 	mutex_unlock(&eventfs_mutex);
-
-	/*
-	 * If any of the ei children has a dentry, then the ei itself
-	 * must have a dentry.
-	 */
-	if (dentry)
-		simple_recursive_removal(dentry, NULL);
 }
 
 /**
@@ -935,7 +832,11 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei)
 {
 	struct dentry *dentry;
 
-	dentry = ei->dentry;
+	dentry = ei->events_dir;
+	if (!dentry)
+		return;
+
+	ei->events_dir = NULL;
 	eventfs_remove_dir(ei);
 
 	/*
@@ -945,5 +846,6 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei)
 	 * sticks around while the other ei->dentry are created
 	 * and destroyed dynamically.
 	 */
+	d_invalidate(dentry);
 	dput(dentry);
 }
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 4b50a0668055b..1886f1826cd83 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -35,8 +35,7 @@ struct eventfs_attr {
  * @entries:	the array of entries representing the files in the directory
  * @name:	the name of the directory to create
  * @children:	link list into the child eventfs_inode
- * @dentry:     the dentry of the directory
- * @d_children: The array of dentries to represent the files when created
+ * @events_dir: the dentry of the events directory
  * @entry_attrs: Saved mode and ownership of the @d_children
  * @attr:	Saved mode and ownership of eventfs_inode itself
  * @data:	The private data to pass to the callbacks
@@ -45,12 +44,12 @@ struct eventfs_attr {
  * @nr_entries: The number of items in @entries
  */
 struct eventfs_inode {
+	struct kref			kref;
 	struct list_head		list;
 	const struct eventfs_entry	*entries;
 	const char			*name;
 	struct list_head		children;
-	struct dentry			*dentry; /* Check is_freed to access */
-	struct dentry			**d_children;
+	struct dentry			*events_dir;
 	struct eventfs_attr		*entry_attrs;
 	struct eventfs_attr		attr;
 	void				*data;
-- 
GitLab


From 70fbfc47a392b98e5f8dba70c6efc6839205c982 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:01 +0100
Subject: [PATCH 3792/4076] nvme-fc: do not wait in vain when unloading module

The module exit path has race between deleting all controllers and
freeing 'left over IDs'. To prevent double free a synchronization
between nvme_delete_ctrl and ida_destroy has been added by the initial
commit.

There is some logic around trying to prevent from hanging forever in
wait_for_completion, though it does not handling all cases. E.g.
blktests is able to reproduce the situation where the module unload
hangs forever.

If we completely rely on the cleanup code executed from the
nvme_delete_ctrl path, all IDs will be freed eventually. This makes
calling ida_destroy unnecessary. We only have to ensure that all
nvme_delete_ctrl code has been executed before we leave
nvme_fc_exit_module. This is done by flushing the nvme_delete_wq
workqueue.

While at it, remove the unused nvme_fc_wq workqueue too.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/fc.c | 47 ++++++------------------------------------
 1 file changed, 6 insertions(+), 41 deletions(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 63a2e2839a789..5630d5689f28a 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -221,11 +221,6 @@ static LIST_HEAD(nvme_fc_lport_list);
 static DEFINE_IDA(nvme_fc_local_port_cnt);
 static DEFINE_IDA(nvme_fc_ctrl_cnt);
 
-static struct workqueue_struct *nvme_fc_wq;
-
-static bool nvme_fc_waiting_to_unload;
-static DECLARE_COMPLETION(nvme_fc_unload_proceed);
-
 /*
  * These items are short-term. They will eventually be moved into
  * a generic FC class. See comments in module init.
@@ -255,8 +250,6 @@ nvme_fc_free_lport(struct kref *ref)
 	/* remove from transport list */
 	spin_lock_irqsave(&nvme_fc_lock, flags);
 	list_del(&lport->port_list);
-	if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list))
-		complete(&nvme_fc_unload_proceed);
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
 	ida_free(&nvme_fc_local_port_cnt, lport->localport.port_num);
@@ -3896,10 +3889,6 @@ static int __init nvme_fc_init_module(void)
 {
 	int ret;
 
-	nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0);
-	if (!nvme_fc_wq)
-		return -ENOMEM;
-
 	/*
 	 * NOTE:
 	 * It is expected that in the future the kernel will combine
@@ -3917,7 +3906,7 @@ static int __init nvme_fc_init_module(void)
 	ret = class_register(&fc_class);
 	if (ret) {
 		pr_err("couldn't register class fc\n");
-		goto out_destroy_wq;
+		return ret;
 	}
 
 	/*
@@ -3941,8 +3930,6 @@ out_destroy_device:
 	device_destroy(&fc_class, MKDEV(0, 0));
 out_destroy_class:
 	class_unregister(&fc_class);
-out_destroy_wq:
-	destroy_workqueue(nvme_fc_wq);
 
 	return ret;
 }
@@ -3962,45 +3949,23 @@ nvme_fc_delete_controllers(struct nvme_fc_rport *rport)
 	spin_unlock(&rport->lock);
 }
 
-static void
-nvme_fc_cleanup_for_unload(void)
+static void __exit nvme_fc_exit_module(void)
 {
 	struct nvme_fc_lport *lport;
 	struct nvme_fc_rport *rport;
-
-	list_for_each_entry(lport, &nvme_fc_lport_list, port_list) {
-		list_for_each_entry(rport, &lport->endp_list, endp_list) {
-			nvme_fc_delete_controllers(rport);
-		}
-	}
-}
-
-static void __exit nvme_fc_exit_module(void)
-{
 	unsigned long flags;
-	bool need_cleanup = false;
 
 	spin_lock_irqsave(&nvme_fc_lock, flags);
-	nvme_fc_waiting_to_unload = true;
-	if (!list_empty(&nvme_fc_lport_list)) {
-		need_cleanup = true;
-		nvme_fc_cleanup_for_unload();
-	}
+	list_for_each_entry(lport, &nvme_fc_lport_list, port_list)
+		list_for_each_entry(rport, &lport->endp_list, endp_list)
+			nvme_fc_delete_controllers(rport);
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
-	if (need_cleanup) {
-		pr_info("%s: waiting for ctlr deletes\n", __func__);
-		wait_for_completion(&nvme_fc_unload_proceed);
-		pr_info("%s: ctrl deletes complete\n", __func__);
-	}
+	flush_workqueue(nvme_delete_wq);
 
 	nvmf_unregister_transport(&nvme_fc_transport);
 
-	ida_destroy(&nvme_fc_local_port_cnt);
-	ida_destroy(&nvme_fc_ctrl_cnt);
-
 	device_destroy(&fc_class, MKDEV(0, 0));
 	class_unregister(&fc_class);
-	destroy_workqueue(nvme_fc_wq);
 }
 
 module_init(nvme_fc_init_module);
-- 
GitLab


From dcfad4ab4d6733f2861cd241d8532a0004fc835a Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:02 +0100
Subject: [PATCH 3793/4076] nvmet-fcloop: swap the list_add_tail arguments

The first argument of list_add_tail function is the new element which
should be added to the list which is the second argument. Swap the
arguments to allow processing more than one element at a time.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fcloop.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index c1faeb1e9e556..1471af250ea62 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -358,7 +358,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport,
 	if (!rport->targetport) {
 		tls_req->status = -ECONNREFUSED;
 		spin_lock(&rport->lock);
-		list_add_tail(&rport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &rport->ls_list);
 		spin_unlock(&rport->lock);
 		queue_work(nvmet_wq, &rport->ls_work);
 		return ret;
@@ -391,7 +391,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport,
 	if (remoteport) {
 		rport = remoteport->private;
 		spin_lock(&rport->lock);
-		list_add_tail(&rport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &rport->ls_list);
 		spin_unlock(&rport->lock);
 		queue_work(nvmet_wq, &rport->ls_work);
 	}
@@ -446,7 +446,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle,
 	if (!tport->remoteport) {
 		tls_req->status = -ECONNREFUSED;
 		spin_lock(&tport->lock);
-		list_add_tail(&tport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &tport->ls_list);
 		spin_unlock(&tport->lock);
 		queue_work(nvmet_wq, &tport->ls_work);
 		return ret;
-- 
GitLab


From c691e6d7e13dab81ac8c7489c83b5dea972522a5 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:03 +0100
Subject: [PATCH 3794/4076] nvmet-fc: release reference on target port

In case we return early out of __nvmet_fc_finish_ls_req() we still have
to release the reference on the target port.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 05e6a755b3306..3d53d9dc10995 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -360,7 +360,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
 
 	if (!lsop->req_queued) {
 		spin_unlock_irqrestore(&tgtport->lock, flags);
-		return;
+		goto out_puttgtport;
 	}
 
 	list_del(&lsop->lsreq_list);
@@ -373,6 +373,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
 				  (lsreq->rqstlen + lsreq->rsplen),
 				  DMA_BIDIRECTIONAL);
 
+out_puttgtport:
 	nvmet_fc_tgtport_put(tgtport);
 }
 
-- 
GitLab


From 4049dc96b8de7aeb3addcea039446e464726a525 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:04 +0100
Subject: [PATCH 3795/4076] nvmet-fc: defer cleanup using RCU properly

When the target executes a disconnect and the host triggers a reconnect
immediately, the reconnect command still finds an existing association.

The reconnect crashes later on because nvmet_fc_delete_target_assoc
blindly removes resources while the reconnect code wants to use it.

To address this, nvmet_fc_find_target_assoc should not be able to
lookup an association which is being removed. The association list
is already under RCU lifetime management, so let's properly use it
and remove the association from the list and wait for a grace period
before cleaning up all. This means we also can drop the RCU management
on the queues, because this is now handled via the association itself.

A second step split the execution context so that the initial disconnect
command can complete without running the reconnect code in the same
context. As usual, this is done by deferring the ->done to a workqueue.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 83 ++++++++++++++++++----------------------
 1 file changed, 37 insertions(+), 46 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 3d53d9dc10995..11ecfef41bd15 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -166,7 +166,7 @@ struct nvmet_fc_tgt_assoc {
 	struct nvmet_fc_hostport	*hostport;
 	struct nvmet_fc_ls_iod		*rcv_disconn;
 	struct list_head		a_list;
-	struct nvmet_fc_tgt_queue __rcu	*queues[NVMET_NR_QUEUES + 1];
+	struct nvmet_fc_tgt_queue 	*queues[NVMET_NR_QUEUES + 1];
 	struct kref			ref;
 	struct work_struct		del_work;
 	struct rcu_head			rcu;
@@ -803,14 +803,11 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 	if (!queue)
 		return NULL;
 
-	if (!nvmet_fc_tgt_a_get(assoc))
-		goto out_free_queue;
-
 	queue->work_q = alloc_workqueue("ntfc%d.%d.%d", 0, 0,
 				assoc->tgtport->fc_target_port.port_num,
 				assoc->a_id, qid);
 	if (!queue->work_q)
-		goto out_a_put;
+		goto out_free_queue;
 
 	queue->qid = qid;
 	queue->sqsize = sqsize;
@@ -832,15 +829,13 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 		goto out_fail_iodlist;
 
 	WARN_ON(assoc->queues[qid]);
-	rcu_assign_pointer(assoc->queues[qid], queue);
+	assoc->queues[qid] = queue;
 
 	return queue;
 
 out_fail_iodlist:
 	nvmet_fc_destroy_fcp_iodlist(assoc->tgtport, queue);
 	destroy_workqueue(queue->work_q);
-out_a_put:
-	nvmet_fc_tgt_a_put(assoc);
 out_free_queue:
 	kfree(queue);
 	return NULL;
@@ -853,12 +848,8 @@ nvmet_fc_tgt_queue_free(struct kref *ref)
 	struct nvmet_fc_tgt_queue *queue =
 		container_of(ref, struct nvmet_fc_tgt_queue, ref);
 
-	rcu_assign_pointer(queue->assoc->queues[queue->qid], NULL);
-
 	nvmet_fc_destroy_fcp_iodlist(queue->assoc->tgtport, queue);
 
-	nvmet_fc_tgt_a_put(queue->assoc);
-
 	destroy_workqueue(queue->work_q);
 
 	kfree_rcu(queue, rcu);
@@ -970,7 +961,7 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport,
 	rcu_read_lock();
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (association_id == assoc->association_id) {
-			queue = rcu_dereference(assoc->queues[qid]);
+			queue = assoc->queues[qid];
 			if (queue &&
 			    (!atomic_read(&queue->connected) ||
 			     !nvmet_fc_tgt_q_get(queue)))
@@ -1173,13 +1164,18 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
 	struct nvmet_fc_ls_iod	*oldls;
 	unsigned long flags;
+	int i;
+
+	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
+		if (assoc->queues[i])
+			nvmet_fc_delete_target_queue(assoc->queues[i]);
+	}
 
 	/* Send Disconnect now that all i/o has completed */
 	nvmet_fc_xmt_disconnect_assoc(assoc);
 
 	nvmet_fc_free_hostport(assoc->hostport);
 	spin_lock_irqsave(&tgtport->lock, flags);
-	list_del_rcu(&assoc->a_list);
 	oldls = assoc->rcv_disconn;
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 	/* if pending Rcv Disconnect Association LS, send rsp now */
@@ -1209,7 +1205,7 @@ static void
 nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
 {
 	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
-	struct nvmet_fc_tgt_queue *queue;
+	unsigned long flags;
 	int i, terminating;
 
 	terminating = atomic_xchg(&assoc->terminating, 1);
@@ -1218,29 +1214,21 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	if (terminating)
 		return;
 
+	spin_lock_irqsave(&tgtport->lock, flags);
+	list_del_rcu(&assoc->a_list);
+	spin_unlock_irqrestore(&tgtport->lock, flags);
 
-	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
-		rcu_read_lock();
-		queue = rcu_dereference(assoc->queues[i]);
-		if (!queue) {
-			rcu_read_unlock();
-			continue;
-		}
+	synchronize_rcu();
 
-		if (!nvmet_fc_tgt_q_get(queue)) {
-			rcu_read_unlock();
-			continue;
-		}
-		rcu_read_unlock();
-		nvmet_fc_delete_target_queue(queue);
-		nvmet_fc_tgt_q_put(queue);
+	/* ensure all in-flight I/Os have been processed */
+	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
+		if (assoc->queues[i])
+			flush_workqueue(assoc->queues[i]->work_q);
 	}
 
 	dev_info(tgtport->dev,
 		"{%d:%d} Association deleted\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
-
-	nvmet_fc_tgt_a_put(assoc);
 }
 
 static struct nvmet_fc_tgt_assoc *
@@ -1493,9 +1481,8 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport)
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
-		if (!queue_work(nvmet_wq, &assoc->del_work))
-			/* already deleting - release local reference */
-			nvmet_fc_tgt_a_put(assoc);
+		queue_work(nvmet_wq, &assoc->del_work);
+		nvmet_fc_tgt_a_put(assoc);
 	}
 	rcu_read_unlock();
 }
@@ -1548,9 +1535,8 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port,
 			continue;
 		assoc->hostport->invalid = 1;
 		noassoc = false;
-		if (!queue_work(nvmet_wq, &assoc->del_work))
-			/* already deleting - release local reference */
-			nvmet_fc_tgt_a_put(assoc);
+		queue_work(nvmet_wq, &assoc->del_work);
+		nvmet_fc_tgt_a_put(assoc);
 	}
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 
@@ -1582,7 +1568,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 
 		rcu_read_lock();
 		list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
-			queue = rcu_dereference(assoc->queues[0]);
+			queue = assoc->queues[0];
 			if (queue && queue->nvme_sq.ctrl == ctrl) {
 				if (nvmet_fc_tgt_a_get(assoc))
 					found_ctrl = true;
@@ -1594,9 +1580,8 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 		nvmet_fc_tgtport_put(tgtport);
 
 		if (found_ctrl) {
-			if (!queue_work(nvmet_wq, &assoc->del_work))
-				/* already deleting - release local reference */
-				nvmet_fc_tgt_a_put(assoc);
+			queue_work(nvmet_wq, &assoc->del_work);
+			nvmet_fc_tgt_a_put(assoc);
 			return;
 		}
 
@@ -1626,6 +1611,8 @@ nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port)
 	/* terminate any outstanding associations */
 	__nvmet_fc_free_assocs(tgtport);
 
+	flush_workqueue(nvmet_wq);
+
 	/*
 	 * should terminate LS's as well. However, LS's will be generated
 	 * at the tail end of association termination, so they likely don't
@@ -1871,9 +1858,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 				sizeof(struct fcnvme_ls_disconnect_assoc_acc)),
 			FCNVME_LS_DISCONNECT_ASSOC);
 
-	/* release get taken in nvmet_fc_find_target_assoc */
-	nvmet_fc_tgt_a_put(assoc);
-
 	/*
 	 * The rules for LS response says the response cannot
 	 * go back until ABTS's have been sent for all outstanding
@@ -1888,8 +1872,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 	assoc->rcv_disconn = iod;
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 
-	nvmet_fc_delete_target_assoc(assoc);
-
 	if (oldls) {
 		dev_info(tgtport->dev,
 			"{%d:%d} Multiple Disconnect Association LS's "
@@ -1905,6 +1887,9 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 		nvmet_fc_xmt_ls_rsp(tgtport, oldls);
 	}
 
+	queue_work(nvmet_wq, &assoc->del_work);
+	nvmet_fc_tgt_a_put(assoc);
+
 	return false;
 }
 
@@ -2903,6 +2888,9 @@ nvmet_fc_remove_port(struct nvmet_port *port)
 
 	nvmet_fc_portentry_unbind(pe);
 
+	/* terminate any outstanding associations */
+	__nvmet_fc_free_assocs(pe->tgtport);
+
 	kfree(pe);
 }
 
@@ -2934,6 +2922,9 @@ static int __init nvmet_fc_init_module(void)
 
 static void __exit nvmet_fc_exit_module(void)
 {
+	/* ensure any shutdown operation, e.g. delete ctrls have finished */
+	flush_workqueue(nvmet_wq);
+
 	/* sanity check - all lports should be removed */
 	if (!list_empty(&nvmet_fc_target_list))
 		pr_warn("%s: targetport list not empty\n", __func__);
-- 
GitLab


From c5e27b1a779ec25779d04c3af65aebaee6bd4304 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:05 +0100
Subject: [PATCH 3796/4076] nvmet-fc: free queue and assoc directly

Neither struct nvmet_fc_tgt_queue nor struct nvmet_fc_tgt_assoc are data
structure which are used in a RCU context. So there is no reason to
delay the free operation.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 11ecfef41bd15..b44b99525c446 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -145,7 +145,6 @@ struct nvmet_fc_tgt_queue {
 	struct list_head		avail_defer_list;
 	struct workqueue_struct		*work_q;
 	struct kref			ref;
-	struct rcu_head			rcu;
 	/* array of fcp_iods */
 	struct nvmet_fc_fcp_iod		fod[] __counted_by(sqsize);
 } __aligned(sizeof(unsigned long long));
@@ -169,7 +168,6 @@ struct nvmet_fc_tgt_assoc {
 	struct nvmet_fc_tgt_queue 	*queues[NVMET_NR_QUEUES + 1];
 	struct kref			ref;
 	struct work_struct		del_work;
-	struct rcu_head			rcu;
 };
 
 
@@ -852,7 +850,7 @@ nvmet_fc_tgt_queue_free(struct kref *ref)
 
 	destroy_workqueue(queue->work_q);
 
-	kfree_rcu(queue, rcu);
+	kfree(queue);
 }
 
 static void
@@ -1185,8 +1183,8 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	dev_info(tgtport->dev,
 		"{%d:%d} Association freed\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
-	kfree_rcu(assoc, rcu);
 	nvmet_fc_tgtport_put(tgtport);
+	kfree(assoc);
 }
 
 static void
-- 
GitLab


From ca121a0f7515591dba0eb5532bfa7ace4dc153ce Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:06 +0100
Subject: [PATCH 3797/4076] nvmet-fc: hold reference on hostport match

The hostport data structure is shared between the association, this why
we keep track of the users via a refcount. So we should not decrement
the refcount on a match and free the hostport several times.

Reported by KASAN.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index b44b99525c446..205a12b1e8413 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1068,8 +1068,6 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 		/* new allocation not needed */
 		kfree(newhost);
 		newhost = match;
-		/* no new allocation - release reference */
-		nvmet_fc_tgtport_put(tgtport);
 	} else {
 		newhost->tgtport = tgtport;
 		newhost->hosthandle = hosthandle;
-- 
GitLab


From 50b474e1faff50f770410f402ebbdf48bf8cc9b0 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:07 +0100
Subject: [PATCH 3798/4076] nvmet-fc: remove null hostport pointer check

An association has always a valid hostport pointer. Remove useless
null pointer check.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 205a12b1e8413..849d9b17c60ad 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -488,8 +488,7 @@ nvmet_fc_xmt_disconnect_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	 * message is normal. Otherwise, send unless the hostport has
 	 * already been invalidated by the lldd.
 	 */
-	if (!tgtport->ops->ls_req || !assoc->hostport ||
-	    assoc->hostport->invalid)
+	if (!tgtport->ops->ls_req || assoc->hostport->invalid)
 		return;
 
 	lsop = kzalloc((sizeof(*lsop) +
@@ -1524,8 +1523,7 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port,
 	spin_lock_irqsave(&tgtport->lock, flags);
 	list_for_each_entry_safe(assoc, next,
 				&tgtport->assoc_list, a_list) {
-		if (!assoc->hostport ||
-		    assoc->hostport->hosthandle != hosthandle)
+		if (assoc->hostport->hosthandle != hosthandle)
 			continue;
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
-- 
GitLab


From 1c110588dd95d21782397ff3cbaa55820b4e1fad Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:08 +0100
Subject: [PATCH 3799/4076] nvmet-fc: do not tack refs on tgtports from assoc

The association life time is tied to the life time of the target port.
That means we should not take extra a refcount when creating a
association.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 849d9b17c60ad..fe3246024836e 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1107,12 +1107,9 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	if (idx < 0)
 		goto out_free_assoc;
 
-	if (!nvmet_fc_tgtport_get(tgtport))
-		goto out_ida;
-
 	assoc->hostport = nvmet_fc_alloc_hostport(tgtport, hosthandle);
 	if (IS_ERR(assoc->hostport))
-		goto out_put;
+		goto out_ida;
 
 	assoc->tgtport = tgtport;
 	assoc->a_id = idx;
@@ -1142,8 +1139,6 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 
 	return assoc;
 
-out_put:
-	nvmet_fc_tgtport_put(tgtport);
 out_ida:
 	ida_free(&tgtport->assoc_cnt, idx);
 out_free_assoc:
@@ -1180,7 +1175,6 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	dev_info(tgtport->dev,
 		"{%d:%d} Association freed\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
-	nvmet_fc_tgtport_put(tgtport);
 	kfree(assoc);
 }
 
-- 
GitLab


From 3146345c2e9c2f661527054e402b0cfad80105a4 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:09 +0100
Subject: [PATCH 3800/4076] nvmet-fc: abort command when there is no binding

When the target port has not active port binding, there is no point in
trying to process the command as it has to fail anyway. Instead adding
checks to all commands abort the command early.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index fe3246024836e..c80b8a066fd17 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1099,6 +1099,9 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	int idx;
 	bool needrandom = true;
 
+	if (!tgtport->pe)
+		return NULL;
+
 	assoc = kzalloc(sizeof(*assoc), GFP_KERNEL);
 	if (!assoc)
 		return NULL;
@@ -2514,8 +2517,9 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 
 	fod->req.cmd = &fod->cmdiubuf.sqe;
 	fod->req.cqe = &fod->rspiubuf.cqe;
-	if (tgtport->pe)
-		fod->req.port = tgtport->pe->port;
+	if (!tgtport->pe)
+		goto transport_error;
+	fod->req.port = tgtport->pe->port;
 
 	/* clear any response payload */
 	memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));
-- 
GitLab


From 710c69dbaccdac312e32931abcb8499c1525d397 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:10 +0100
Subject: [PATCH 3801/4076] nvmet-fc: avoid deadlock on delete association path

When deleting an association the shutdown path is deadlocking because we
try to flush the nvmet_wq nested. Avoid this by deadlock by deferring
the put work into its own work item.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index c80b8a066fd17..3e0d391e631b1 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -111,6 +111,8 @@ struct nvmet_fc_tgtport {
 	struct nvmet_fc_port_entry	*pe;
 	struct kref			ref;
 	u32				max_sg_cnt;
+
+	struct work_struct		put_work;
 };
 
 struct nvmet_fc_port_entry {
@@ -247,6 +249,13 @@ static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc);
 static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue);
 static int nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue);
 static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport);
+static void nvmet_fc_put_tgtport_work(struct work_struct *work)
+{
+	struct nvmet_fc_tgtport *tgtport =
+		container_of(work, struct nvmet_fc_tgtport, put_work);
+
+	nvmet_fc_tgtport_put(tgtport);
+}
 static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport);
 static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 					struct nvmet_fc_fcp_iod *fod);
@@ -358,7 +367,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
 
 	if (!lsop->req_queued) {
 		spin_unlock_irqrestore(&tgtport->lock, flags);
-		goto out_puttgtport;
+		goto out_putwork;
 	}
 
 	list_del(&lsop->lsreq_list);
@@ -371,8 +380,8 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
 				  (lsreq->rqstlen + lsreq->rsplen),
 				  DMA_BIDIRECTIONAL);
 
-out_puttgtport:
-	nvmet_fc_tgtport_put(tgtport);
+out_putwork:
+	queue_work(nvmet_wq, &tgtport->put_work);
 }
 
 static int
@@ -1396,6 +1405,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 	kref_init(&newrec->ref);
 	ida_init(&newrec->assoc_cnt);
 	newrec->max_sg_cnt = template->max_sgl_segments;
+	INIT_WORK(&newrec->put_work, nvmet_fc_put_tgtport_work);
 
 	ret = nvmet_fc_alloc_ls_iodlist(newrec);
 	if (ret) {
-- 
GitLab


From fe506a74589326183297d5abdda02d0c76ae5a8b Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:11 +0100
Subject: [PATCH 3802/4076] nvmet-fc: take ref count on tgtport before delete
 assoc

We have to ensure that the tgtport is not going away
before be have remove all the associations.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 3e0d391e631b1..671d096745a5b 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1090,13 +1090,28 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 }
 
 static void
-nvmet_fc_delete_assoc(struct work_struct *work)
+nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
+{
+	nvmet_fc_delete_target_assoc(assoc);
+	nvmet_fc_tgt_a_put(assoc);
+}
+
+static void
+nvmet_fc_delete_assoc_work(struct work_struct *work)
 {
 	struct nvmet_fc_tgt_assoc *assoc =
 		container_of(work, struct nvmet_fc_tgt_assoc, del_work);
+	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
 
-	nvmet_fc_delete_target_assoc(assoc);
-	nvmet_fc_tgt_a_put(assoc);
+	nvmet_fc_delete_assoc(assoc);
+	nvmet_fc_tgtport_put(tgtport);
+}
+
+static void
+nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
+{
+	nvmet_fc_tgtport_get(assoc->tgtport);
+	queue_work(nvmet_wq, &assoc->del_work);
 }
 
 static struct nvmet_fc_tgt_assoc *
@@ -1127,7 +1142,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	assoc->a_id = idx;
 	INIT_LIST_HEAD(&assoc->a_list);
 	kref_init(&assoc->ref);
-	INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc);
+	INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc_work);
 	atomic_set(&assoc->terminating, 0);
 
 	while (needrandom) {
@@ -1483,7 +1498,7 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport)
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
-		queue_work(nvmet_wq, &assoc->del_work);
+		nvmet_fc_schedule_delete_assoc(assoc);
 		nvmet_fc_tgt_a_put(assoc);
 	}
 	rcu_read_unlock();
@@ -1536,7 +1551,7 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port,
 			continue;
 		assoc->hostport->invalid = 1;
 		noassoc = false;
-		queue_work(nvmet_wq, &assoc->del_work);
+		nvmet_fc_schedule_delete_assoc(assoc);
 		nvmet_fc_tgt_a_put(assoc);
 	}
 	spin_unlock_irqrestore(&tgtport->lock, flags);
@@ -1581,7 +1596,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 		nvmet_fc_tgtport_put(tgtport);
 
 		if (found_ctrl) {
-			queue_work(nvmet_wq, &assoc->del_work);
+			nvmet_fc_schedule_delete_assoc(assoc);
 			nvmet_fc_tgt_a_put(assoc);
 			return;
 		}
@@ -1888,7 +1903,7 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 		nvmet_fc_xmt_ls_rsp(tgtport, oldls);
 	}
 
-	queue_work(nvmet_wq, &assoc->del_work);
+	nvmet_fc_schedule_delete_assoc(assoc);
 	nvmet_fc_tgt_a_put(assoc);
 
 	return false;
-- 
GitLab


From a90ac7b348770ff3d246fac575306783de381e51 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Wed, 31 Jan 2024 09:51:12 +0100
Subject: [PATCH 3803/4076] nvmet-fc: use RCU list iterator for assoc_list

The assoc_list is a RCU protected list, thus use the RCU flavor of list
functions.

Let's use this opportunity and refactor this code and move the lookup
into a helper and give it a descriptive name.

Signed-off-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fc.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 671d096745a5b..fd229f310c931 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1114,14 +1114,27 @@ nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	queue_work(nvmet_wq, &assoc->del_work);
 }
 
+static bool
+nvmet_fc_assoc_exits(struct nvmet_fc_tgtport *tgtport, u64 association_id)
+{
+	struct nvmet_fc_tgt_assoc *a;
+
+	list_for_each_entry_rcu(a, &tgtport->assoc_list, a_list) {
+		if (association_id == a->association_id)
+			return true;
+	}
+
+	return false;
+}
+
 static struct nvmet_fc_tgt_assoc *
 nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 {
-	struct nvmet_fc_tgt_assoc *assoc, *tmpassoc;
+	struct nvmet_fc_tgt_assoc *assoc;
 	unsigned long flags;
+	bool done;
 	u64 ran;
 	int idx;
-	bool needrandom = true;
 
 	if (!tgtport->pe)
 		return NULL;
@@ -1145,24 +1158,21 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc_work);
 	atomic_set(&assoc->terminating, 0);
 
-	while (needrandom) {
+	done = false;
+	do {
 		get_random_bytes(&ran, sizeof(ran) - BYTES_FOR_QID);
 		ran = ran << BYTES_FOR_QID_SHIFT;
 
 		spin_lock_irqsave(&tgtport->lock, flags);
-		needrandom = false;
-		list_for_each_entry(tmpassoc, &tgtport->assoc_list, a_list) {
-			if (ran == tmpassoc->association_id) {
-				needrandom = true;
-				break;
-			}
-		}
-		if (!needrandom) {
+		rcu_read_lock();
+		if (!nvmet_fc_assoc_exits(tgtport, ran)) {
 			assoc->association_id = ran;
 			list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list);
+			done = true;
 		}
+		rcu_read_unlock();
 		spin_unlock_irqrestore(&tgtport->lock, flags);
-	}
+	} while (!done);
 
 	return assoc;
 
-- 
GitLab


From 524719b4c60dc5c5edff0cdfd715b4e2d6c16ede Mon Sep 17 00:00:00 2001
From: "Nitin U. Yewale" <nyewale@redhat.com>
Date: Mon, 29 Jan 2024 16:36:37 +0530
Subject: [PATCH 3804/4076] nvme-tcp: show hostnqn when connecting to tcp
 target

Log hostnqn when connecting to nvme target.
As hostnqn could be changed, logging this information
in syslog at appropriate time may help in troubleshooting.

Signed-off-by: Nitin U. Yewale <nyewale@redhat.com>
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 9f8dea2e2c7d5..a6d596e056021 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2753,8 +2753,8 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_uninit_ctrl;
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
-		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp, hostnqn: %s\n",
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn);
 
 	mutex_lock(&nvme_tcp_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
-- 
GitLab


From d2045e6a4e2f3bcb3a2dab6684f8fbc95239d566 Mon Sep 17 00:00:00 2001
From: "Nitin U. Yewale" <nyewale@redhat.com>
Date: Mon, 29 Jan 2024 16:36:38 +0530
Subject: [PATCH 3805/4076] nvme-rdma: show hostnqn when connecting to rdma
 target

Log hostnqn when connecting to nvme target.
As hostnqn could be changed, logging this information
in syslog at appropriate time may help in troubleshooting.

Signed-off-by: Nitin U. Yewale <nyewale@redhat.com>
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/rdma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 6adf2c19a7120..20fdd40b1879f 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -2300,8 +2300,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_uninit_ctrl;
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
-		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs, hostnqn: %s\n",
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn);
 
 	mutex_lock(&nvme_rdma_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
-- 
GitLab


From c3a846fe4bf3ecbdf48e561b90fea6cc27ac6423 Mon Sep 17 00:00:00 2001
From: "Nitin U. Yewale" <nyewale@redhat.com>
Date: Mon, 29 Jan 2024 16:36:39 +0530
Subject: [PATCH 3806/4076] nvme-fc: show hostnqn when connecting to fc target

Log hostnqn when connecting to nvme target.
As hostnqn could be changed, logging this information
in syslog at appropriate time may help in troubleshooting.

Signed-off-by: Nitin U. Yewale <nyewale@redhat.com>
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/fc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 5630d5689f28a..68a5d971657bb 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -3570,8 +3570,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	flush_delayed_work(&ctrl->connect_work);
 
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
-		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl));
+		"NVME-FC{%d}: new ctrl: NQN \"%s\", hostnqn: %s\n",
+		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl), opts->host->nqn);
 
 	return &ctrl->ctrl;
 
-- 
GitLab


From 9f079dda14339ee87d864306a9dc8c6b4e4da40b Mon Sep 17 00:00:00 2001
From: Alan Adamson <alan.adamson@oracle.com>
Date: Mon, 29 Jan 2024 16:19:38 -0800
Subject: [PATCH 3807/4076] nvme: allow passthru cmd error logging

Commit d7ac8dca938c ("nvme: quiet user passthrough command errors")
disabled error logging for user passthrough commands.  This commit
adds the ability to opt-in to passthrough admin error logging. IO
commands initiated as passthrough will always be logged.

The logging output for passthrough commands (Admin and IO) has been
changed to include CDWXX fields.

nvme0n1: Read(0x2), LBA Out of Range (sct 0x0 / sc 0x80) DNR cdw10=0x0 cdw11=0x1
        cdw12=0x70000 cdw13=0x0 cdw14=0x0 cdw15=0x0

Add a helper function nvme_log_err_passthru() which allows us to log
error for passthru commands by decoding cdw10-cdw15 values of nvme
command.

Add a new sysfs attr passthru_err_log_enabled that allows user to conditionally
enable passthrough command logging for either passthrough Admin commands sent to
the controller or passthrough IO commands sent to a namespace.

By default, passthrough error logging is disabled.

To enable passthrough admin error logging:
        echo 1 > /sys/class/nvme/nvme0/passthru_err_log_enabled

To disable passthrough admin error logging:
        echo 0 > /sys/class/nvme/nvme0/passthru_err_log_enabled

To enable passthrough io error logging:
        echo 1 > /sys/class/nvme/nvme0/nvme0n1/passthru_err_log_enabled

To disable passthrough io error logging:
        echo 0 > /sys/class/nvme/nvme0/nvme0n1/passthru_err_log_enabled

Signed-off-by: Alan Adamson <alan.adamson@oracle.com>
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c  | 59 +++++++++++++++++++++++++++++++++++----
 drivers/nvme/host/nvme.h  |  3 +-
 drivers/nvme/host/sysfs.c | 58 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 113 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 8b48b7f7871ad..0d124a8ca9c32 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -338,6 +338,30 @@ static void nvme_log_error(struct request *req)
 			   nr->status & NVME_SC_DNR  ? "DNR "  : "");
 }
 
+static void nvme_log_err_passthru(struct request *req)
+{
+	struct nvme_ns *ns = req->q->queuedata;
+	struct nvme_request *nr = nvme_req(req);
+
+	pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s"
+		"cdw10=0x%x cdw11=0x%x cdw12=0x%x cdw13=0x%x cdw14=0x%x cdw15=0x%x\n",
+		ns ? ns->disk->disk_name : dev_name(nr->ctrl->device),
+		ns ? nvme_get_opcode_str(nr->cmd->common.opcode) :
+		     nvme_get_admin_opcode_str(nr->cmd->common.opcode),
+		nr->cmd->common.opcode,
+		nvme_get_error_status_str(nr->status),
+		nr->status >> 8 & 7,	/* Status Code Type */
+		nr->status & 0xff,	/* Status Code */
+		nr->status & NVME_SC_MORE ? "MORE " : "",
+		nr->status & NVME_SC_DNR  ? "DNR "  : "",
+		nr->cmd->common.cdw10,
+		nr->cmd->common.cdw11,
+		nr->cmd->common.cdw12,
+		nr->cmd->common.cdw13,
+		nr->cmd->common.cdw14,
+		nr->cmd->common.cdw14);
+}
+
 enum nvme_disposition {
 	COMPLETE,
 	RETRY,
@@ -385,8 +409,12 @@ static inline void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET)))
-		nvme_log_error(req);
+	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
+		if (blk_rq_is_passthrough(req))
+			nvme_log_err_passthru(req);
+		else
+			nvme_log_error(req);
+	}
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	if (req->cmd_flags & REQ_NVME_MPATH)
@@ -679,10 +707,21 @@ static inline void nvme_clear_nvme_request(struct request *req)
 /* initialize a passthrough request */
 void nvme_init_request(struct request *req, struct nvme_command *cmd)
 {
-	if (req->q->queuedata)
+	struct nvme_request *nr = nvme_req(req);
+	bool logging_enabled;
+
+	if (req->q->queuedata) {
+		struct nvme_ns *ns = req->q->disk->private_data;
+
+		logging_enabled = ns->passthru_err_log_enabled;
 		req->timeout = NVME_IO_TIMEOUT;
-	else /* no queuedata implies admin queue */
+	} else { /* no queuedata implies admin queue */
+		logging_enabled = nr->ctrl->passthru_err_log_enabled;
 		req->timeout = NVME_ADMIN_TIMEOUT;
+	}
+
+	if (!logging_enabled)
+		req->rq_flags |= RQF_QUIET;
 
 	/* passthru commands should let the driver set the SGL flags */
 	cmd->common.flags &= ~NVME_CMD_SGL_ALL;
@@ -691,8 +730,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
 	if (req->mq_hctx->type == HCTX_TYPE_POLL)
 		req->cmd_flags |= REQ_POLLED;
 	nvme_clear_nvme_request(req);
-	req->rq_flags |= RQF_QUIET;
-	memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
+	memcpy(nr->cmd, cmd, sizeof(*cmd));
 }
 EXPORT_SYMBOL_GPL(nvme_init_request);
 
@@ -3658,6 +3696,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 
 	ns->disk = disk;
 	ns->queue = disk->queue;
+	ns->passthru_err_log_enabled = false;
 
 	if (ctrl->opts && ctrl->opts->data_digest)
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
@@ -3721,6 +3760,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	nvme_mpath_add_disk(ns, info->anagrpid);
 	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
 
+	/*
+	 * Set ns->disk->device->driver_data to ns so we can access
+	 * ns->logging_enabled in nvme_passthru_err_log_enabled_store() and
+	 * nvme_passthru_err_log_enabled_show().
+	 */
+	dev_set_drvdata(disk_to_dev(ns->disk), ns);
+
 	return;
 
  out_cleanup_ns_from_list:
@@ -4521,6 +4567,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	int ret;
 
 	WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
+	ctrl->passthru_err_log_enabled = false;
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b70b333a0874f..3897334e3950d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -263,6 +263,7 @@ enum nvme_ctrl_flags {
 struct nvme_ctrl {
 	bool comp_seen;
 	bool identified;
+	bool passthru_err_log_enabled;
 	enum nvme_ctrl_state state;
 	spinlock_t lock;
 	struct mutex scan_lock;
@@ -522,7 +523,7 @@ struct nvme_ns {
 	struct device		cdev_device;
 
 	struct nvme_fault_inject fault_inject;
-
+	bool			passthru_err_log_enabled;
 };
 
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 6b2f06f190de3..d099218e494a8 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -35,6 +35,62 @@ static ssize_t nvme_sysfs_rescan(struct device *dev,
 }
 static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);
 
+static ssize_t nvme_adm_passthru_err_log_enabled_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf,
+			  ctrl->passthru_err_log_enabled ? "on\n" : "off\n");
+}
+
+static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	int err;
+	bool passthru_err_log_enabled;
+
+	err = kstrtobool(buf, &passthru_err_log_enabled);
+	if (err)
+		return -EINVAL;
+
+	ctrl->passthru_err_log_enabled = passthru_err_log_enabled;
+
+	return count;
+}
+
+static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ns *n = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, n->passthru_err_log_enabled ? "on\n" : "off\n");
+}
+
+static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ns *ns = dev_get_drvdata(dev);
+	int err;
+	bool passthru_err_log_enabled;
+
+	err = kstrtobool(buf, &passthru_err_log_enabled);
+	if (err)
+		return -EINVAL;
+	ns->passthru_err_log_enabled = passthru_err_log_enabled;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_adm_passthru_err_log_enabled = \
+	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
+	nvme_adm_passthru_err_log_enabled_show, nvme_adm_passthru_err_log_enabled_store);
+
+static struct device_attribute dev_attr_io_passthru_err_log_enabled = \
+	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
+	nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
+
 static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
@@ -208,6 +264,7 @@ static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,
 #endif
+	&dev_attr_io_passthru_err_log_enabled.attr,
 	NULL,
 };
 
@@ -655,6 +712,7 @@ static struct attribute *nvme_dev_attrs[] = {
 #ifdef CONFIG_NVME_TCP_TLS
 	&dev_attr_tls_key.attr,
 #endif
+	&dev_attr_adm_passthru_err_log_enabled.attr,
 	NULL
 };
 
-- 
GitLab


From ae3f4b44641dfff969604735a0dcbf931f383285 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 31 Jan 2024 02:21:49 -0800
Subject: [PATCH 3808/4076] net: sysfs: Fix /sys/class/net/<iface> path

The documentation is pointing to the wrong path for the interface.
Documentation is pointing to /sys/class/<iface>, instead of
/sys/class/net/<iface>.

Fix it by adding the `net/` directory before the interface.

Fixes: 1a02ef76acfa ("net: sysfs: add documentation entries for /sys/class/<iface>/queues")
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240131102150.728960-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ABI/testing/sysfs-class-net-queues        | 22 +++++++++----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues
index 906ff3ca928ac..5bff64d256c20 100644
--- a/Documentation/ABI/testing/sysfs-class-net-queues
+++ b/Documentation/ABI/testing/sysfs-class-net-queues
@@ -1,4 +1,4 @@
-What:		/sys/class/<iface>/queues/rx-<queue>/rps_cpus
+What:		/sys/class/net/<iface>/queues/rx-<queue>/rps_cpus
 Date:		March 2010
 KernelVersion:	2.6.35
 Contact:	netdev@vger.kernel.org
@@ -8,7 +8,7 @@ Description:
 		network device queue. Possible values depend on the number
 		of available CPU(s) in the system.
 
-What:		/sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt
+What:		/sys/class/net/<iface>/queues/rx-<queue>/rps_flow_cnt
 Date:		April 2010
 KernelVersion:	2.6.35
 Contact:	netdev@vger.kernel.org
@@ -16,7 +16,7 @@ Description:
 		Number of Receive Packet Steering flows being currently
 		processed by this particular network device receive queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/tx_timeout
+What:		/sys/class/net/<iface>/queues/tx-<queue>/tx_timeout
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -24,7 +24,7 @@ Description:
 		Indicates the number of transmit timeout events seen by this
 		network interface transmit queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/tx_maxrate
+What:		/sys/class/net/<iface>/queues/tx-<queue>/tx_maxrate
 Date:		March 2015
 KernelVersion:	4.1
 Contact:	netdev@vger.kernel.org
@@ -32,7 +32,7 @@ Description:
 		A Mbps max-rate set for the queue, a value of zero means disabled,
 		default is disabled.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/xps_cpus
+What:		/sys/class/net/<iface>/queues/tx-<queue>/xps_cpus
 Date:		November 2010
 KernelVersion:	2.6.38
 Contact:	netdev@vger.kernel.org
@@ -42,7 +42,7 @@ Description:
 		network device transmit queue. Possible values depend on the
 		number of available CPU(s) in the system.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/xps_rxqs
+What:		/sys/class/net/<iface>/queues/tx-<queue>/xps_rxqs
 Date:		June 2018
 KernelVersion:	4.18.0
 Contact:	netdev@vger.kernel.org
@@ -53,7 +53,7 @@ Description:
 		number of available receive queue(s) in the network device.
 		Default is disabled.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -62,7 +62,7 @@ Description:
 		of this particular network device transmit queue.
 		Default value is 1000.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -70,7 +70,7 @@ Description:
 		Indicates the number of bytes (objects) in flight on this
 		network device transmit queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -79,7 +79,7 @@ Description:
 		on this network device transmit queue. This value is clamped
 		to be within the bounds defined by limit_max and limit_min.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -88,7 +88,7 @@ Description:
 		queued on this network device transmit queue. See
 		include/linux/dynamic_queue_limits.h for the default value.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
-- 
GitLab


From 7b55984c96ffe9e236eb9c82a2196e0b1f84990d Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Mon, 29 Jan 2024 14:03:08 +0100
Subject: [PATCH 3809/4076] xen-netback: properly sync TX responses

Invoking the make_tx_response() / push_tx_responses() pair with no lock
held would be acceptable only if all such invocations happened from the
same context (NAPI instance or dealloc thread). Since this isn't the
case, and since the interface "spec" also doesn't demand that multicast
operations may only be performed with no in-flight transmits,
MCAST_{ADD,DEL} processing also needs to acquire the response lock
around the invocations.

To prevent similar mistakes going forward, "downgrade" the present
functions to private helpers of just the two remaining ones using them
directly, with no forward declarations anymore. This involves renaming
what so far was make_tx_response(), for the new function of that name
to serve the new (wrapper) purpose.

While there,
- constify the txp parameters,
- correct xenvif_idx_release()'s status parameter's type,
- rename {,_}make_tx_response()'s status parameters for consistency with
  xenvif_idx_release()'s.

Fixes: 210c34dcd8d9 ("xen-netback: add support for multicast control")
Cc: stable@vger.kernel.org
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>
Link: https://lore.kernel.org/r/980c6c3d-e10e-4459-8565-e8fbde122f00@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/xen-netback/netback.c | 84 +++++++++++++++----------------
 1 file changed, 40 insertions(+), 44 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index d7503aef599f0..fab361a250d60 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -104,13 +104,12 @@ bool provides_xdp_headroom = true;
 module_param(provides_xdp_headroom, bool, 0644);
 
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
-			       u8 status);
+			       s8 status);
 
 static void make_tx_response(struct xenvif_queue *queue,
-			     struct xen_netif_tx_request *txp,
+			     const struct xen_netif_tx_request *txp,
 			     unsigned int extra_count,
-			     s8       st);
-static void push_tx_responses(struct xenvif_queue *queue);
+			     s8 status);
 
 static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx);
 
@@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue,
 			  unsigned int extra_count, RING_IDX end)
 {
 	RING_IDX cons = queue->tx.req_cons;
-	unsigned long flags;
 
 	do {
-		spin_lock_irqsave(&queue->response_lock, flags);
 		make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR);
-		push_tx_responses(queue);
-		spin_unlock_irqrestore(&queue->response_lock, flags);
 		if (cons == end)
 			break;
 		RING_COPY_REQUEST(&queue->tx, cons++, txp);
@@ -465,12 +460,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 	for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS;
 	     nr_slots--) {
 		if (unlikely(!txp->size)) {
-			unsigned long flags;
-
-			spin_lock_irqsave(&queue->response_lock, flags);
 			make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY);
-			push_tx_responses(queue);
-			spin_unlock_irqrestore(&queue->response_lock, flags);
 			++txp;
 			continue;
 		}
@@ -496,14 +486,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 
 		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) {
 			if (unlikely(!txp->size)) {
-				unsigned long flags;
-
-				spin_lock_irqsave(&queue->response_lock, flags);
 				make_tx_response(queue, txp, 0,
 						 XEN_NETIF_RSP_OKAY);
-				push_tx_responses(queue);
-				spin_unlock_irqrestore(&queue->response_lock,
-						       flags);
 				continue;
 			}
 
@@ -995,7 +979,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 					 (ret == 0) ?
 					 XEN_NETIF_RSP_OKAY :
 					 XEN_NETIF_RSP_ERROR);
-			push_tx_responses(queue);
 			continue;
 		}
 
@@ -1007,7 +990,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
 			make_tx_response(queue, &txreq, extra_count,
 					 XEN_NETIF_RSP_OKAY);
-			push_tx_responses(queue);
 			continue;
 		}
 
@@ -1433,8 +1415,35 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget)
 	return work_done;
 }
 
+static void _make_tx_response(struct xenvif_queue *queue,
+			     const struct xen_netif_tx_request *txp,
+			     unsigned int extra_count,
+			     s8 status)
+{
+	RING_IDX i = queue->tx.rsp_prod_pvt;
+	struct xen_netif_tx_response *resp;
+
+	resp = RING_GET_RESPONSE(&queue->tx, i);
+	resp->id     = txp->id;
+	resp->status = status;
+
+	while (extra_count-- != 0)
+		RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
+
+	queue->tx.rsp_prod_pvt = ++i;
+}
+
+static void push_tx_responses(struct xenvif_queue *queue)
+{
+	int notify;
+
+	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
+	if (notify)
+		notify_remote_via_irq(queue->tx_irq);
+}
+
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
-			       u8 status)
+			       s8 status)
 {
 	struct pending_tx_info *pending_tx_info;
 	pending_ring_idx_t index;
@@ -1444,8 +1453,8 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 
 	spin_lock_irqsave(&queue->response_lock, flags);
 
-	make_tx_response(queue, &pending_tx_info->req,
-			 pending_tx_info->extra_count, status);
+	_make_tx_response(queue, &pending_tx_info->req,
+			  pending_tx_info->extra_count, status);
 
 	/* Release the pending index before pusing the Tx response so
 	 * its available before a new Tx request is pushed by the
@@ -1459,32 +1468,19 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 	spin_unlock_irqrestore(&queue->response_lock, flags);
 }
 
-
 static void make_tx_response(struct xenvif_queue *queue,
-			     struct xen_netif_tx_request *txp,
+			     const struct xen_netif_tx_request *txp,
 			     unsigned int extra_count,
-			     s8       st)
+			     s8 status)
 {
-	RING_IDX i = queue->tx.rsp_prod_pvt;
-	struct xen_netif_tx_response *resp;
-
-	resp = RING_GET_RESPONSE(&queue->tx, i);
-	resp->id     = txp->id;
-	resp->status = st;
-
-	while (extra_count-- != 0)
-		RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
+	unsigned long flags;
 
-	queue->tx.rsp_prod_pvt = ++i;
-}
+	spin_lock_irqsave(&queue->response_lock, flags);
 
-static void push_tx_responses(struct xenvif_queue *queue)
-{
-	int notify;
+	_make_tx_response(queue, txp, extra_count, status);
+	push_tx_responses(queue);
 
-	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
-	if (notify)
-		notify_remote_via_irq(queue->tx_irq);
+	spin_unlock_irqrestore(&queue->response_lock, flags);
 }
 
 static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx)
-- 
GitLab


From e0526ec5360a48ad3ab2e26e802b0532302a7e11 Mon Sep 17 00:00:00 2001
From: Souradeep Chakrabarti <schakrabarti@linux.microsoft.com>
Date: Tue, 30 Jan 2024 23:35:51 -0800
Subject: [PATCH 3810/4076] hv_netvsc: Fix race condition between netvsc_probe
 and netvsc_remove

In commit ac5047671758 ("hv_netvsc: Disable NAPI before closing the
VMBus channel"), napi_disable was getting called for all channels,
including all subchannels without confirming if they are enabled or not.

This caused hv_netvsc getting hung at napi_disable, when netvsc_probe()
has finished running but nvdev->subchan_work has not started yet.
netvsc_subchan_work() -> rndis_set_subchannel() has not created the
sub-channels and because of that netvsc_sc_open() is not running.
netvsc_remove() calls cancel_work_sync(&nvdev->subchan_work), for which
netvsc_subchan_work did not run.

netif_napi_add() sets the bit NAPI_STATE_SCHED because it ensures NAPI
cannot be scheduled. Then netvsc_sc_open() -> napi_enable will clear the
NAPIF_STATE_SCHED bit, so it can be scheduled. napi_disable() does the
opposite.

Now during netvsc_device_remove(), when napi_disable is called for those
subchannels, napi_disable gets stuck on infinite msleep.

This fix addresses this problem by ensuring that napi_disable() is not
getting called for non-enabled NAPI struct.
But netif_napi_del() is still necessary for these non-enabled NAPI struct
for cleanup purpose.

Call trace:
[  654.559417] task:modprobe        state:D stack:    0 pid: 2321 ppid:  1091 flags:0x00004002
[  654.568030] Call Trace:
[  654.571221]  <TASK>
[  654.573790]  __schedule+0x2d6/0x960
[  654.577733]  schedule+0x69/0xf0
[  654.581214]  schedule_timeout+0x87/0x140
[  654.585463]  ? __bpf_trace_tick_stop+0x20/0x20
[  654.590291]  msleep+0x2d/0x40
[  654.593625]  napi_disable+0x2b/0x80
[  654.597437]  netvsc_device_remove+0x8a/0x1f0 [hv_netvsc]
[  654.603935]  rndis_filter_device_remove+0x194/0x1c0 [hv_netvsc]
[  654.611101]  ? do_wait_intr+0xb0/0xb0
[  654.615753]  netvsc_remove+0x7c/0x120 [hv_netvsc]
[  654.621675]  vmbus_remove+0x27/0x40 [hv_vmbus]

Cc: stable@vger.kernel.org
Fixes: ac5047671758 ("hv_netvsc: Disable NAPI before closing the VMBus channel")
Signed-off-by: Souradeep Chakrabarti <schakrabarti@linux.microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/1706686551-28510-1-git-send-email-schakrabarti@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/hyperv/netvsc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 1dafa44155d0e..a6fcbda64ecc6 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -708,7 +708,10 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Disable NAPI and disassociate its context from the device. */
 	for (i = 0; i < net_device->num_chn; i++) {
 		/* See also vmbus_reset_channel_cb(). */
-		napi_disable(&net_device->chan_table[i].napi);
+		/* only disable enabled NAPI channel */
+		if (i < ndev->real_num_rx_queues)
+			napi_disable(&net_device->chan_table[i].napi);
+
 		netif_napi_del(&net_device->chan_table[i].napi);
 	}
 
-- 
GitLab


From 7b6fb3050d8f5e2b6858eef344e47ac1f5442827 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 31 Jan 2024 09:08:44 -0500
Subject: [PATCH 3811/4076] selftests: team: Add missing config options

Similar to commit dd2d40acdbb2 ("selftests: bonding: Add more missing
config options"), add more networking-specific config options which are
needed for team device tests.

For testing, I used the minimal config generated by virtme-ng and I added
the options in the config file. Afterwards, the team device test passed.

Fixes: bbb774d921e2 ("net: Add tests for bonding and team address list management")
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Link: https://lore.kernel.org/r/20240131140848.360618-2-bpoirier@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/team/config | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
index 265b6882cc21e..b5e3a3aad4bfb 100644
--- a/tools/testing/selftests/drivers/net/team/config
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -1,3 +1,5 @@
+CONFIG_DUMMY=y
+CONFIG_IPV6=y
+CONFIG_MACVLAN=y
 CONFIG_NET_TEAM=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y
-CONFIG_MACVLAN=y
-- 
GitLab


From 8cc063ae1b3dbe416ce62a15d49af4c2314b45fe Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 31 Jan 2024 09:08:45 -0500
Subject: [PATCH 3812/4076] selftests: bonding: Check initial state

The purpose of the test_LAG_cleanup() function is to check that some
hardware addresses are removed from underlying devices after they have been
unenslaved. The test function simply checks that those addresses are not
present at the end. However, if the addresses were never added to begin
with due to some error in device setup, the test function currently passes.
This is a false positive since in that situation the test did not actually
exercise the intended functionality.

Add a check that the expected addresses are indeed present after device
setup. This makes the test function more robust.

I noticed this problem when running the team/dev_addr_lists.sh test on a
system without support for dummy and ipv6:

tools/testing/selftests/drivers/net/team# ./dev_addr_lists.sh
Error: Unknown device type.
Error: Unknown device type.
This program is not intended to be run as root.
RTNETLINK answers: Operation not supported
TEST: team cleanup mode lacp                                        [ OK ]

Fixes: bbb774d921e2 ("net: Add tests for bonding and team address list management")
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Link: https://lore.kernel.org/r/20240131140848.360618-3-bpoirier@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/bonding/lag_lib.sh  | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
index 2a268b17b61f5..dbdd736a41d39 100644
--- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
+++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
@@ -48,6 +48,17 @@ test_LAG_cleanup()
 	ip link add mv0 link "$name" up address "$ucaddr" type macvlan
 	# Used to test dev->mc handling
 	ip address add "$addr6" dev "$name"
+
+	# Check that addresses were added as expected
+	(grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "macvlan unicast address not found on a slave"
+
+	# mcaddr is added asynchronously by addrconf_dad_work(), use busywait
+	(busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "IPv6 solicited-node multicast mac address not found on a slave"
+
 	ip link set dev "$name" down
 	ip link del "$name"
 
-- 
GitLab


From 9d851dd4dab63e95c1911a2fa847796d1ec5d58d Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 31 Jan 2024 09:08:46 -0500
Subject: [PATCH 3813/4076] selftests: net: Remove executable bits from library
 scripts

setup_loopback.sh and net_helper.sh are meant to be sourced from other
scripts, not executed directly. Therefore, remove the executable bits from
those files' permissions.

This change is similar to commit 49078c1b80b6 ("selftests: forwarding:
Remove executable bits from lib.sh")

Fixes: 7d1575014a63 ("selftests/net: GRO coalesce test")
Fixes: 3bdd9fd29cb0 ("selftests/net: synchronize udpgro tests' tx and rx connection")
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Link: https://lore.kernel.org/r/20240131140848.360618-4-bpoirier@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/net_helper.sh     | 0
 tools/testing/selftests/net/setup_loopback.sh | 0
 2 files changed, 0 insertions(+), 0 deletions(-)
 mode change 100755 => 100644 tools/testing/selftests/net/net_helper.sh
 mode change 100755 => 100644 tools/testing/selftests/net/setup_loopback.sh

diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh
old mode 100755
new mode 100644
diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh
old mode 100755
new mode 100644
-- 
GitLab


From 06efafd8608dac0c3a480539acc66ee41d2fb430 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 31 Jan 2024 09:08:47 -0500
Subject: [PATCH 3814/4076] selftests: net: List helper scripts in TEST_FILES
 Makefile variable

Some scripts are not tests themselves; they contain utility functions used
by other tests. According to Documentation/dev-tools/kselftest.rst, such
files should be listed in TEST_FILES. Move those utility scripts to
TEST_FILES.

Fixes: 1751eb42ddb5 ("selftests: net: use TEST_PROGS_EXTENDED")
Fixes: 25ae948b4478 ("selftests/net: add lib.sh")
Fixes: b99ac1841147 ("kselftests/net: add missed setup_loopback.sh/setup_veth.sh to Makefile")
Fixes: f5173fe3e13b ("selftests: net: included needed helper in the install targets")
Suggested-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Link: https://lore.kernel.org/r/20240131140848.360618-5-bpoirier@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 48c6f93b81498..211753756bdee 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -53,9 +53,7 @@ TEST_PROGS += bind_bhash.sh
 TEST_PROGS += ip_local_port_range.sh
 TEST_PROGS += rps_default_mask.sh
 TEST_PROGS += big_tcp.sh
-TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
-TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh lib.sh
-TEST_PROGS_EXTENDED += net_helper.sh
+TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
@@ -97,6 +95,7 @@ TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 
 TEST_FILES := settings
+TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
 
 include ../lib.mk
 
-- 
GitLab


From 96cd5ac4c0e6b91b74c8fbfcaa7e5c943dfa4835 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 31 Jan 2024 09:08:48 -0500
Subject: [PATCH 3815/4076] selftests: forwarding: List helper scripts in
 TEST_FILES Makefile variable

Some scripts are not tests themselves; they contain utility functions used
by other tests. According to Documentation/dev-tools/kselftest.rst, such
files should be listed in TEST_FILES. Currently they are incorrectly listed
in TEST_PROGS_EXTENDED so rename the variable.

Fixes: c085dbfb1cfc ("selftests/net/forwarding: define libs as TEST_PROGS_EXTENDED")
Suggested-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Link: https://lore.kernel.org/r/20240131140848.360618-6-bpoirier@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 452693514be4b..4de92632f4836 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -112,7 +112,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \
 	vxlan_symmetric_ipv6.sh \
 	vxlan_symmetric.sh
 
-TEST_PROGS_EXTENDED := devlink_lib.sh \
+TEST_FILES := devlink_lib.sh \
 	ethtool_lib.sh \
 	fib_offload_lib.sh \
 	forwarding.config.sample \
-- 
GitLab


From 1939f738c73dfdb8389839bdc9624c765e3326e6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 31 Jan 2024 08:56:05 -0800
Subject: [PATCH 3816/4076] selftests: net: add missing config for
 NF_TARGET_TTL

amt test uses the TTL iptables module:

  ip netns exec "${RELAY}" iptables -t mangle -I PREROUTING \
  	-d 239.0.0.1 -j TTL --ttl-set 2

Fixes: c08e8baea78e ("selftests: add amt interface selftest script")
Link: https://lore.kernel.org/r/20240131165605.4051645-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 98c6bd2228c69..24a7c7bcbbc19 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -33,6 +33,7 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_IP_NF_NAT=m
 CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_SEG6_LWTUNNEL=y
 CONFIG_L2TP_ETH=m
-- 
GitLab


From c15a729c9d45aa142fb01a3afee822ab1f0e62a8 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 31 Jan 2024 18:52:29 +0100
Subject: [PATCH 3817/4076] selftests: net: enable some more knobs

The rtnetlink tests require additional options currently
off by default.

Fixes: 2766a11161cc ("selftests: rtnetlink: add ipsec offload API test")
Fixes: 5e596ee171ba ("selftests: add xfrm state-policy-monitor to rtnetlink.sh")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/9048ca58e49b962f35dba1dfb2beaf3dab3e0411.1706723341.git.pabeni@redhat.com/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 24a7c7bcbbc19..3b749addd3640 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -22,6 +22,8 @@ CONFIG_VLAN_8021Q=y
 CONFIG_GENEVE=m
 CONFIG_IFB=y
 CONFIG_INET_DIAG=y
+CONFIG_INET_ESP=y
+CONFIG_INET_ESP_OFFLOAD=y
 CONFIG_IP_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
@@ -93,3 +95,4 @@ CONFIG_IP_SCTP=m
 CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_CRYPTO_ARIA=y
 CONFIG_XFRM_INTERFACE=m
+CONFIG_XFRM_USER=m
-- 
GitLab


From 1389358bb008e7625942846e9f03554319b7fecc Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Thu, 1 Feb 2024 16:13:39 +0100
Subject: [PATCH 3818/4076] tracing/timerlat: Move hrtimer_init to timerlat_fd
 open()

Currently, the timerlat's hrtimer is initialized at the first read of
timerlat_fd, and destroyed at close(). It works, but it causes an error
if the user program open() and close() the file without reading.

Here's an example:

 # echo NO_OSNOISE_WORKLOAD > /sys/kernel/debug/tracing/osnoise/options
 # echo timerlat > /sys/kernel/debug/tracing/current_tracer

 # cat <<EOF > ./timerlat_load.py
 # !/usr/bin/env python3

 timerlat_fd = open("/sys/kernel/tracing/osnoise/per_cpu/cpu0/timerlat_fd", 'r')
 timerlat_fd.close();
 EOF

 # ./taskset -c 0 ./timerlat_load.py
<BOOM>

 BUG: kernel NULL pointer dereference, address: 0000000000000010
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] PREEMPT SMP NOPTI
 CPU: 1 PID: 2673 Comm: python3 Not tainted 6.6.13-200.fc39.x86_64 #1
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-1.fc39 04/01/2014
 RIP: 0010:hrtimer_active+0xd/0x50
 Code: 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 48 8b 57 30 <8b> 42 10 a8 01 74 09 f3 90 8b 42 10 a8 01 75 f7 80 7f 38 00 75 1d
 RSP: 0018:ffffb031009b7e10 EFLAGS: 00010286
 RAX: 000000000002db00 RBX: ffff9118f786db08 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: ffff9117a0e64400 RDI: ffff9118f786db08
 RBP: ffff9118f786db80 R08: ffff9117a0ddd420 R09: ffff9117804d4f70
 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9118f786db08
 R13: ffff91178fdd5e20 R14: ffff9117840978c0 R15: 0000000000000000
 FS:  00007f2ffbab1740(0000) GS:ffff9118f7840000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000010 CR3: 00000001b402e000 CR4: 0000000000750ee0
 PKRU: 55555554
 Call Trace:
  <TASK>
  ? __die+0x23/0x70
  ? page_fault_oops+0x171/0x4e0
  ? srso_alias_return_thunk+0x5/0x7f
  ? avc_has_extended_perms+0x237/0x520
  ? exc_page_fault+0x7f/0x180
  ? asm_exc_page_fault+0x26/0x30
  ? hrtimer_active+0xd/0x50
  hrtimer_cancel+0x15/0x40
  timerlat_fd_release+0x48/0xe0
  __fput+0xf5/0x290
  __x64_sys_close+0x3d/0x80
  do_syscall_64+0x60/0x90
  ? srso_alias_return_thunk+0x5/0x7f
  ? __x64_sys_ioctl+0x72/0xd0
  ? srso_alias_return_thunk+0x5/0x7f
  ? syscall_exit_to_user_mode+0x2b/0x40
  ? srso_alias_return_thunk+0x5/0x7f
  ? do_syscall_64+0x6c/0x90
  ? srso_alias_return_thunk+0x5/0x7f
  ? exit_to_user_mode_prepare+0x142/0x1f0
  ? srso_alias_return_thunk+0x5/0x7f
  ? syscall_exit_to_user_mode+0x2b/0x40
  ? srso_alias_return_thunk+0x5/0x7f
  ? do_syscall_64+0x6c/0x90
  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
 RIP: 0033:0x7f2ffb321594
 Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 80 3d d5 cd 0d 00 00 74 13 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 3c c3 0f 1f 00 55 48 89 e5 48 83 ec 10 89 7d
 RSP: 002b:00007ffe8d8eef18 EFLAGS: 00000202 ORIG_RAX: 0000000000000003
 RAX: ffffffffffffffda RBX: 00007f2ffba4e668 RCX: 00007f2ffb321594
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
 RBP: 00007ffe8d8eef40 R08: 0000000000000000 R09: 0000000000000000
 R10: 55c926e3167eae79 R11: 0000000000000202 R12: 0000000000000003
 R13: 00007ffe8d8ef030 R14: 0000000000000000 R15: 00007f2ffba4e668
  </TASK>
 CR2: 0000000000000010
 ---[ end trace 0000000000000000 ]---

Move hrtimer_init to timerlat_fd open() to avoid this problem.

Link: https://lore.kernel.org/linux-trace-kernel/7324dd3fc0035658c99b825204a66049389c56e3.1706798888.git.bristot@kernel.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: stable@vger.kernel.org
Fixes: e88ed227f639 ("tracing/timerlat: Add user-space interface")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_osnoise.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index bd0d01d00fb9d..a8e28f9b9271c 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2444,6 +2444,9 @@ static int timerlat_fd_open(struct inode *inode, struct file *file)
 	tlat = this_cpu_tmr_var();
 	tlat->count = 0;
 
+	hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
+	tlat->timer.function = timerlat_irq;
+
 	migrate_enable();
 	return 0;
 };
@@ -2526,9 +2529,6 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
 		tlat->tracing_thread = false;
 		tlat->kthread = current;
 
-		hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-		tlat->timer.function = timerlat_irq;
-
 		/* Annotate now to drift new period */
 		tlat->abs_period = hrtimer_cb_get_time(&tlat->timer);
 
-- 
GitLab


From 5a49f996046ba947466bc7461e4b19c4d1daf978 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Thu, 1 Feb 2024 10:34:47 -0500
Subject: [PATCH 3819/4076] eventfs: Warn if an eventfs_inode is freed without
 is_freed being set

There should never be a case where an evenfs_inode is being freed without
is_freed being set. Add a WARN_ON_ONCE() if it ever happens. That would
mean there was one too many put_ei()s.

Link: https://lore.kernel.org/linux-trace-kernel/20240201161616.843551963@goodmis.org

Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 515fdace1eeaf..ca7daee7c8115 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -73,6 +73,9 @@ enum {
 static void release_ei(struct kref *ref)
 {
 	struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
+
+	WARN_ON_ONCE(!ei->is_freed);
+
 	kfree(ei->entry_attrs);
 	kfree_const(ei->name);
 	kfree_rcu(ei, rcu);
@@ -84,6 +87,14 @@ static inline void put_ei(struct eventfs_inode *ei)
 		kref_put(&ei->kref, release_ei);
 }
 
+static inline void free_ei(struct eventfs_inode *ei)
+{
+	if (ei) {
+		ei->is_freed = 1;
+		put_ei(ei);
+	}
+}
+
 static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
 {
 	if (ei)
@@ -679,7 +690,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 
 	/* Was the parent freed? */
 	if (list_empty(&ei->list)) {
-		put_ei(ei);
+		free_ei(ei);
 		ei = NULL;
 	}
 	return ei;
@@ -770,7 +781,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	return ei;
 
  fail:
-	put_ei(ei);
+	free_ei(ei);
 	tracefs_failed_creating(dentry);
 	return ERR_PTR(-ENOMEM);
 }
@@ -801,9 +812,8 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 	list_for_each_entry(ei_child, &ei->children, list)
 		eventfs_remove_rec(ei_child, level + 1);
 
-	ei->is_freed = 1;
 	list_del(&ei->list);
-	put_ei(ei);
+	free_ei(ei);
 }
 
 /**
-- 
GitLab


From 264424dfdd5cbd92bc5b5ddf93944929fc877fac Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Thu, 1 Feb 2024 10:34:48 -0500
Subject: [PATCH 3820/4076] eventfs: Restructure eventfs_inode structure to be
 more condensed

Some of the eventfs_inode structure has holes in it. Rework the structure
to be a bit more condensed, and also remove the no longer used llist
field.

Link: https://lore.kernel.org/linux-trace-kernel/20240201161617.002321438@goodmis.org

Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/internal.h | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 1886f1826cd83..beb3dcd0e4342 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -32,40 +32,37 @@ struct eventfs_attr {
 /*
  * struct eventfs_inode - hold the properties of the eventfs directories.
  * @list:	link list into the parent directory
+ * @rcu:	Union with @list for freeing
+ * @children:	link list into the child eventfs_inode
  * @entries:	the array of entries representing the files in the directory
  * @name:	the name of the directory to create
- * @children:	link list into the child eventfs_inode
  * @events_dir: the dentry of the events directory
  * @entry_attrs: Saved mode and ownership of the @d_children
- * @attr:	Saved mode and ownership of eventfs_inode itself
  * @data:	The private data to pass to the callbacks
+ * @attr:	Saved mode and ownership of eventfs_inode itself
  * @is_freed:	Flag set if the eventfs is on its way to be freed
  *                Note if is_freed is set, then dentry is corrupted.
+ * @is_events:	Flag set for only the top level "events" directory
  * @nr_entries: The number of items in @entries
+ * @ino:	The saved inode number
  */
 struct eventfs_inode {
-	struct kref			kref;
-	struct list_head		list;
+	union {
+		struct list_head	list;
+		struct rcu_head		rcu;
+	};
+	struct list_head		children;
 	const struct eventfs_entry	*entries;
 	const char			*name;
-	struct list_head		children;
 	struct dentry			*events_dir;
 	struct eventfs_attr		*entry_attrs;
-	struct eventfs_attr		attr;
 	void				*data;
+	struct eventfs_attr		attr;
+	struct kref			kref;
 	unsigned int			is_freed:1;
 	unsigned int			is_events:1;
 	unsigned int			nr_entries:30;
 	unsigned int			ino;
-	/*
-	 * Union - used for deletion
-	 * @llist:	for calling dput() if needed after RCU
-	 * @rcu:	eventfs_inode to delete in RCU
-	 */
-	union {
-		struct llist_node	llist;
-		struct rcu_head		rcu;
-	};
 };
 
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
-- 
GitLab


From 12d823b31fadf47c8f36ecada7abac5f903cac33 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Thu, 1 Feb 2024 10:34:49 -0500
Subject: [PATCH 3821/4076] eventfs: Remove fsnotify*() functions from lookup()

The dentries and inodes are created when referenced in the lookup code.
There's no reason to call fsnotify_*() functions when they are created by
a reference. It doesn't make any sense.

Link: https://lore.kernel.org/linux-trace-kernel/20240201002719.GS2087318@ZenIV/
Link: https://lore.kernel.org/linux-trace-kernel/20240201161617.166973329@goodmis.org

Cc: stable@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Fixes: a376007917776 ("eventfs: Implement functions to create files and dirs when accessed");
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index ca7daee7c8115..9e031e5a2713b 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -366,7 +366,6 @@ static struct dentry *lookup_file(struct eventfs_inode *parent_ei,
 	dentry->d_fsdata = get_ei(parent_ei);
 
 	d_add(dentry, inode);
-	fsnotify_create(dentry->d_parent->d_inode, dentry);
 	return NULL;
 };
 
@@ -408,7 +407,6 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry,
 	inc_nlink(inode);
 	d_add(dentry, inode);
 	inc_nlink(dentry->d_parent->d_inode);
-	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
 	return NULL;
 }
 
-- 
GitLab


From ca185770db914869ff9fe773bac5e0e5e4165b83 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Thu, 1 Feb 2024 10:34:50 -0500
Subject: [PATCH 3822/4076] eventfs: Keep all directory links at 1

The directory link count in eventfs was somewhat bogus. It was only being
updated when a directory child was being looked up and not on creation.

One solution would be to update in get_attr() the link count by iterating
the ei->children list and then adding 2. But that could slow down simple
stat() calls, especially if it's done on all directories in eventfs.

Another solution would be to add a parent pointer to the eventfs_inode
and keep track of the number of sub directories it has on creation. But
this adds overhead for something not really worthwhile.

The solution decided upon is to keep all directory links in eventfs as 1.
This tells user space not to rely on the hard links of directories. Which
in this case it shouldn't.

Link: https://lore.kernel.org/linux-trace-kernel/20240201002719.GS2087318@ZenIV/
Link: https://lore.kernel.org/linux-trace-kernel/20240201161617.339968298@goodmis.org

Cc: stable@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions")
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 fs/tracefs/event_inode.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 9e031e5a2713b..110e8a2721890 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -404,9 +404,7 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry,
 
 	dentry->d_fsdata = get_ei(ei);
 
-	inc_nlink(inode);
 	d_add(dentry, inode);
-	inc_nlink(dentry->d_parent->d_inode);
 	return NULL;
 }
 
@@ -769,9 +767,17 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 
 	dentry->d_fsdata = get_ei(ei);
 
-	/* directory inodes start off with i_nlink == 2 (for "." entry) */
-	inc_nlink(inode);
+	/*
+	 * Keep all eventfs directories with i_nlink == 1.
+	 * Due to the dynamic nature of the dentry creations and not
+	 * wanting to add a pointer to the parent eventfs_inode in the
+	 * eventfs_inode structure, keeping the i_nlink in sync with the
+	 * number of directories would cause too much complexity for
+	 * something not worth much. Keeping directory links at 1
+	 * tells userspace not to trust the link number.
+	 */
 	d_instantiate(dentry, inode);
+	/* The dentry of the "events" parent does keep track though */
 	inc_nlink(dentry->d_parent->d_inode);
 	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
 	tracefs_end_creating(dentry);
-- 
GitLab


From b6c620dc43ccb4e802894e54b651cf81495e9598 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 31 Jan 2024 22:49:46 +0100
Subject: [PATCH 3823/4076] mptcp: fix data re-injection from stale subflow

When the MPTCP PM detects that a subflow is stale, all the packet
scheduler must re-inject all the mptcp-level unacked data. To avoid
acquiring unneeded locks, it first try to check if any unacked data
is present at all in the RTX queue, but such check is currently
broken, as it uses TCP-specific helper on an MPTCP socket.

Funnily enough fuzzers and static checkers are happy, as the accessed
memory still belongs to the mptcp_sock struct, and even from a
functional perspective the recovery completed successfully, as
the short-cut test always failed.

A recent unrelated TCP change - commit d5fed5addb2b ("tcp: reorganize
tcp_sock fast path variables") - exposed the issue, as the tcp field
reorganization makes the mptcp code always skip the re-inection.

Fix the issue dropping the bogus call: we are on a slow path, the early
optimization proved once again to be evil.

Fixes: 1e1d9d6f119c ("mptcp: handle pending data on closed subflow")
Cc: stable@vger.kernel.org
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/468
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1-1-4c1c11e571ff@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3ed4709a75096..028e8b473626f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2314,9 +2314,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 	if (__mptcp_check_fallback(msk))
 		return false;
 
-	if (tcp_rtx_and_write_queues_empty(sk))
-		return false;
-
 	/* the closing socket has some data untransmitted and/or unacked:
 	 * some data in the mptcp rtx queue has not really xmitted yet.
 	 * keep it simple and re-inject the whole mptcp level rtx queue
-- 
GitLab


From 3645c844902bd4e173d6704fc2a37e8746904d67 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 31 Jan 2024 22:49:47 +0100
Subject: [PATCH 3824/4076] selftests: mptcp: add missing kconfig for NF Filter

Since the commit mentioned below, 'mptcp_join' selftests is using
IPTables to add rules to the Filter table.

It is then required to have IP_NF_FILTER KConfig.

This KConfig is usually enabled by default in many defconfig, but we
recently noticed that some CI were running our selftests without them
enabled.

Fixes: 8d014eaa9254 ("selftests: mptcp: add ADD_ADDR timeout test case")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index e317c2e44dae8..2a00bf4acdfa8 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -22,6 +22,7 @@ CONFIG_NFT_TPROXY=m
 CONFIG_NFT_SOCKET=m
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_NET_ACT_CSUM=m
-- 
GitLab


From 8c86fad2cecdc6bf7283ecd298b4d0555bd8b8aa Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 31 Jan 2024 22:49:48 +0100
Subject: [PATCH 3825/4076] selftests: mptcp: add missing kconfig for NF Filter
 in v6

Since the commit mentioned below, 'mptcp_join' selftests is using
IPTables to add rules to the Filter table for IPv6.

It is then required to have IP6_NF_FILTER KConfig.

This KConfig is usually enabled by default in many defconfig, but we
recently noticed that some CI were running our selftests without them
enabled.

Fixes: 523514ed0a99 ("selftests: mptcp: add ADD_ADDR IPv6 test cases")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1-3-4c1c11e571ff@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 2a00bf4acdfa8..26fe466f803dd 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -25,6 +25,7 @@ CONFIG_IP_MULTIPLE_TABLES=y
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IP6_NF_FILTER=m
 CONFIG_NET_ACT_CSUM=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_CLS_ACT=y
-- 
GitLab


From 2d41f10fa497182df9012d3e95d9cea24eb42e61 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 31 Jan 2024 22:49:49 +0100
Subject: [PATCH 3826/4076] selftests: mptcp: add missing kconfig for NF Mangle

Since the commit mentioned below, 'mptcp_join' selftests is using
IPTables to add rules to the Mangle table, only in IPv4.

This KConfig is usually enabled by default in many defconfig, but we
recently noticed that some CI were running our selftests without them
enabled.

Fixes: b6e074e171bc ("selftests: mptcp: add infinite map testcase")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1-4-4c1c11e571ff@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 26fe466f803dd..4f80014cae494 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -23,6 +23,7 @@ CONFIG_NFT_SOCKET=m
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y
 CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IP6_NF_FILTER=m
-- 
GitLab


From 4d4dfb2019d7010efb65926d9d1c1793f9a367c6 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 31 Jan 2024 22:49:50 +0100
Subject: [PATCH 3827/4076] selftests: mptcp: increase timeout to 30 min

On very slow environments -- e.g. when QEmu is used without KVM --,
mptcp_join.sh selftest can take a bit more than 20 minutes. Bump the
default timeout by 50% as it seems normal to take that long on some
environments.

When a debug kernel config is used, this selftest will take even longer,
but that's certainly not a common test env to consider for the timeout.

The Fixes tag that has been picked here is there simply to help having
this patch backported to older stable versions. It is difficult to point
to the exact commit that made some env reaching the timeout from time to
time.

Fixes: d17b968b9876 ("selftests: mptcp: increase timeout to 20 minutes")
Cc: stable@vger.kernel.org
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1-5-4c1c11e571ff@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/settings | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings
index 79b65bdf05db6..abc5648b59abd 100644
--- a/tools/testing/selftests/net/mptcp/settings
+++ b/tools/testing/selftests/net/mptcp/settings
@@ -1 +1 @@
-timeout=1200
+timeout=1800
-- 
GitLab


From 5e2f3c65af47e527ccac54060cf909e3306652ff Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 31 Jan 2024 22:49:51 +0100
Subject: [PATCH 3828/4076] selftests: mptcp: decrease BW in simult flows

When running the simult_flow selftest in slow environments -- e.g. QEmu
without KVM support --, the results can be unstable. This selftest
checks if the aggregated bandwidth is (almost) fully used as expected.

To help improving the stability while still keeping the same validation
in place, the BW and the delay are reduced to lower the pressure on the
CPU.

Fixes: 1a418cb8e888 ("mptcp: simult flow self-tests")
Fixes: 219d04992b68 ("mptcp: push pending frames when subflow has free space")
Cc: stable@vger.kernel.org
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1-6-4c1c11e571ff@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/simult_flows.sh | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index ae8ad5d6fb9da..0cc964e6f2c17 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -284,12 +284,12 @@ done
 
 setup
 run_test 10 10 0 0 "balanced bwidth"
-run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
+run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-run_test 30 10 0 0 "unbalanced bwidth"
-run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
-run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+run_test 10 3 0 0 "unbalanced bwidth"
+run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
+run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"
 
 mptcp_lib_result_print_all_tap
 exit $ret
-- 
GitLab


From de46d138e7735eded9756906747fd3a8c3a42225 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 31 Jan 2024 22:49:52 +0100
Subject: [PATCH 3829/4076] selftests: mptcp: allow changing subtests prefix

If a CI executes the same selftest multiple times with different
options, all results from the same subtests will have the same title,
which confuse the CI. With the same title printed in TAP, the tests are
considered as the same ones.

Now, it is possible to override this prefix by using MPTCP_LIB_KSFT_TEST
env var, and have a different title.

While at it, use 'basename' to remove the suffix as well instead of
using an extra 'sed'.

Fixes: c4192967e62f ("selftests: mptcp: lib: format subtests results in TAP")
Cc: stable@vger.kernel.org
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1-7-4c1c11e571ff@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_lib.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 022262a2cfe0e..3a2abae5993e2 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -6,7 +6,7 @@ readonly KSFT_FAIL=1
 readonly KSFT_SKIP=4
 
 # shellcheck disable=SC2155 # declare and assign separately
-readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g')
+readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}"
 
 MPTCP_LIB_SUBTESTS=()
 
-- 
GitLab


From 31ee4ad86afd6ed6f4bb1b38c43011216080c42a Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 31 Jan 2024 22:49:53 +0100
Subject: [PATCH 3830/4076] selftests: mptcp: join: stop transfer when check is
 done (part 1)

Since the "Fixes" commit mentioned below, "userspace pm" subtests of
mptcp_join selftests introduced in v6.5 are launching the whole transfer
in the background, do the required checks, then wait for the end of
transfer.

There is no need to wait longer, especially because the checks at the
end of the transfer are ignored (which is fine). This saves quite a few
seconds in slow environments.

Note that old versions will need commit bdbef0a6ff10 ("selftests: mptcp:
add mptcp_lib_kill_wait") as well to get 'mptcp_lib_kill_wait()' helper.

Fixes: 4369c198e599 ("selftests: mptcp: test userspace pm out of transfer")
Cc: stable@vger.kernel.org # 6.5.x: bdbef0a6ff10: selftests: mptcp: add mptcp_lib_kill_wait
Cc: stable@vger.kernel.org # 6.5.x
Reviewed-and-tested-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1-8-4c1c11e571ff@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 3a5b630261910..85bcc95f4ede6 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3453,7 +3453,7 @@ userspace_tests()
 		chk_mptcp_info subflows 0 subflows 0
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm create destroy subflow
@@ -3475,7 +3475,7 @@ userspace_tests()
 		chk_mptcp_info subflows 0 subflows 0
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm create id 0 subflow
-- 
GitLab


From 04b57c9e096a9479fe0ad31e3956e336fa589cb2 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 31 Jan 2024 22:49:54 +0100
Subject: [PATCH 3831/4076] selftests: mptcp: join: stop transfer when check is
 done (part 2)

Since the "Fixes" commits mentioned below, the newly added "userspace
pm" subtests of mptcp_join selftests are launching the whole transfer in
the background, do the required checks, then wait for the end of
transfer.

There is no need to wait longer, especially because the checks at the
end of the transfer are ignored (which is fine). This saves quite a few
seconds on slow environments.

While at it, use 'mptcp_lib_kill_wait()' helper everywhere, instead of
on a specific one with 'kill_tests_wait()'.

Fixes: b2e2248f365a ("selftests: mptcp: userspace pm create id 0 subflow")
Fixes: e3b47e460b4b ("selftests: mptcp: userspace pm remove initial subflow")
Fixes: b9fb176081fb ("selftests: mptcp: userspace pm send RM_ADDR for ID 0")
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1-9-4c1c11e571ff@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 23 ++++++++-----------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 85bcc95f4ede6..c07386e21e0a4 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -643,13 +643,6 @@ kill_events_pids()
 	mptcp_lib_kill_wait $evts_ns2_pid
 }
 
-kill_tests_wait()
-{
-	#shellcheck disable=SC2046
-	kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1)
-	wait
-}
-
 pm_nl_set_limits()
 {
 	local ns=$1
@@ -3494,7 +3487,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 2 2
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm remove initial subflow
@@ -3518,7 +3511,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm send RM_ADDR for ID 0
@@ -3544,7 +3537,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 }
 
@@ -3558,7 +3551,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 2 2
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		speed=slow \
-			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
 
 		wait_mpj $ns1
 		pm_nl_check_endpoint "creation" \
@@ -3573,7 +3567,7 @@ endpoint_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags signal
 		pm_nl_check_endpoint "modif is allowed" \
 			$ns2 10.0.2.2 id 1 flags signal
-		kill_tests_wait
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	if reset "delete and re-add" &&
@@ -3582,7 +3576,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
 		test_linkfail=4 speed=20 \
-			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
 
 		wait_mpj $ns2
 		chk_subflow_nr "before delete" 2
@@ -3597,7 +3592,7 @@ endpoint_tests()
 		wait_mpj $ns2
 		chk_subflow_nr "after re-add" 2
 		chk_mptcp_info subflows 1 subflows 1
-		kill_tests_wait
+		mptcp_lib_kill_wait $tests_pid
 	fi
 }
 
-- 
GitLab


From f0588b157f48b9c6277a75c9f14650e86d969e03 Mon Sep 17 00:00:00 2001
From: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Date: Wed, 31 Jan 2024 14:22:40 -0800
Subject: [PATCH 3832/4076] idpf: avoid compiler padding in virtchnl2_ptype
 struct

In the arm random config file, kconfig option 'CONFIG_AEABI' is
disabled which results in adding the compiler flag '-mabi=apcs-gnu'.
This causes the compiler to add padding in virtchnl2_ptype
structure to align it to 8 bytes, resulting in the following
size check failure:

include/linux/build_bug.h:78:41: error: static assertion failed: "(6) == sizeof(struct virtchnl2_ptype)"
      78 | #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
         |                                         ^~~~~~~~~~~~~~
include/linux/build_bug.h:77:34: note: in expansion of macro '__static_assert'
      77 | #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
         |                                  ^~~~~~~~~~~~~~~
drivers/net/ethernet/intel/idpf/virtchnl2.h:26:9: note: in expansion of macro 'static_assert'
      26 |         static_assert((n) == sizeof(struct X))
         |         ^~~~~~~~~~~~~
drivers/net/ethernet/intel/idpf/virtchnl2.h:982:1: note: in expansion of macro 'VIRTCHNL2_CHECK_STRUCT_LEN'
     982 | VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype);
         | ^~~~~~~~~~~~~~~~~~~~~~~~~~

Avoid the compiler padding by using "__packed" structure
attribute for the virtchnl2_ptype struct. Also align the
structure by using "__aligned(2)" for better code optimization.

Fixes: 0d7502a9b4a7 ("virtchnl: add virtchnl version 2 ops")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312220250.ufEm8doQ-lkp@intel.com
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Tested-by: Krishneil Singh  <krishneil.k.singh@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20240131222241.2087516-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/virtchnl2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 8dc837889723c..4a3c4454d25ab 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -978,7 +978,7 @@ struct virtchnl2_ptype {
 	u8 proto_id_count;
 	__le16 pad;
 	__le16 proto_id[];
-};
+} __packed __aligned(2);
 VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype);
 
 /**
-- 
GitLab


From 069a6ed2992df8eaae90d69d7770de8d545327d9 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Thu, 1 Feb 2024 11:38:53 +0000
Subject: [PATCH 3833/4076] doc/netlink/specs: Add missing attr in rt_link spec

IFLA_DPLL_PIN was added to rt_link messages but not to the spec, which
breaks ynl. Add the missing definitions to the rt_link ynl spec.

Fixes: 5f1842692880 ("netdev: expose DPLL pin handle for netdevice")
Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240201113853.37432-1-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_link.yaml | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 1ad01d52a8638..8e4d19adee8cd 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -942,6 +942,10 @@ attribute-sets:
       -
         name: gro-ipv4-max-size
         type: u32
+      -
+        name: dpll-pin
+        type: nest
+        nested-attributes: link-dpll-pin-attrs
   -
     name: af-spec-attrs
     attributes:
@@ -1627,6 +1631,12 @@ attribute-sets:
       -
         name: used
         type: u8
+  -
+    name: link-dpll-pin-attrs
+    attributes:
+      -
+        name: id
+        type: u32
 
 sub-messages:
   -
-- 
GitLab


From f0377ff97509f5a4921993d5d61da000361bd884 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Thu, 18 Jan 2024 12:48:54 +0100
Subject: [PATCH 3834/4076] nvme-host: fix the updating of the firmware version

The original code didn't update the firmware version if the
"next slot" of the AFI register isn't zero or if the
"current slot" field is zero; in those cases it assumed
that a reset was needed.

However, the NVMe specification doesn't exclude the possibility that
the "next slot" value is equal to the "current slot" value,
meaning that the same firmware slot will be activated after performing
a controller level reset; in this case a reset is clearly not
necessary and we can safely update the firmware version.

Modify the code so the kernel will report that a Controller Level Reset
is needed only in the following cases:

1) If the "current slot" field is zero. This is invalid and means that
   something is wrong, a reset is needed.

or

2) if the "next slot" field isn't zero AND it's not equal to the
   "current slot" value. This means that at the next reset a different
   firmware slot will be activated.

Fixes: 983a338b96c8 ("nvme: update firmware version after commit")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0d124a8ca9c32..975245527c1fc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4191,6 +4191,7 @@ static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl)
 static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 {
 	struct nvme_fw_slot_info_log *log;
+	u8 next_fw_slot, cur_fw_slot;
 
 	log = kmalloc(sizeof(*log), GFP_KERNEL);
 	if (!log)
@@ -4202,13 +4203,15 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 		goto out_free_log;
 	}
 
-	if (log->afi & 0x70 || !(log->afi & 0x7)) {
+	cur_fw_slot = log->afi & 0x7;
+	next_fw_slot = (log->afi & 0x70) >> 4;
+	if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) {
 		dev_info(ctrl->device,
 			 "Firmware is activated after next Controller Level Reset\n");
 		goto out_free_log;
 	}
 
-	memcpy(ctrl->subsys->firmware_rev, &log->frs[(log->afi & 0x7) - 1],
+	memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1],
 		sizeof(ctrl->subsys->firmware_rev));
 
 out_free_log:
-- 
GitLab


From f3c89983cb4fc00be64eb0d5cbcfcdf2cacb965e Mon Sep 17 00:00:00 2001
From: Hongyu Jin <hongyu.jin@unisoc.com>
Date: Tue, 30 Jan 2024 15:26:34 -0500
Subject: [PATCH 3835/4076] block: Fix where bio IO priority gets set

Commit 82b74cac2849 ("blk-ioprio: Convert from rqos policy to direct
call") pushed setting bio I/O priority down into blk_mq_submit_bio()
-- which is too low within block core's submit_bio() because it
skips setting I/O priority for block drivers that implement
fops->submit_bio() (e.g. DM, MD, etc).

Fix this by moving bio_set_ioprio() up from blk-mq.c to blk-core.c and
call it from submit_bio().  This ensures all block drivers call
bio_set_ioprio() during initial bio submission.

Fixes: a78418e6a04c ("block: Always initialize bio IO priority on submit")
Co-developed-by: Yibin Ding <yibin.ding@unisoc.com>
Signed-off-by: Yibin Ding <yibin.ding@unisoc.com>
Signed-off-by: Hongyu Jin <hongyu.jin@unisoc.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Mikulas Patocka <mpatocka@redhat.com>
[snitzer: revised commit header]
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240130202638.62600-2-snitzer@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c | 10 ++++++++++
 block/blk-mq.c   | 10 ----------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 11342af420d0c..de771093b5268 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -49,6 +49,7 @@
 #include "blk-pm.h"
 #include "blk-cgroup.h"
 #include "blk-throttle.h"
+#include "blk-ioprio.h"
 
 struct dentry *blk_debugfs_root;
 
@@ -833,6 +834,14 @@ end_io:
 }
 EXPORT_SYMBOL(submit_bio_noacct);
 
+static void bio_set_ioprio(struct bio *bio)
+{
+	/* Nobody set ioprio so far? Initialize it based on task's nice value */
+	if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
+		bio->bi_ioprio = get_current_ioprio();
+	blkcg_set_ioprio(bio);
+}
+
 /**
  * submit_bio - submit a bio to the block device layer for I/O
  * @bio: The &struct bio which describes the I/O
@@ -855,6 +864,7 @@ void submit_bio(struct bio *bio)
 		count_vm_events(PGPGOUT, bio_sectors(bio));
 	}
 
+	bio_set_ioprio(bio);
 	submit_bio_noacct(bio);
 }
 EXPORT_SYMBOL(submit_bio);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index aa87fcfda1ecf..2dc01551e27c7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -40,7 +40,6 @@
 #include "blk-stat.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
-#include "blk-ioprio.h"
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd);
@@ -2944,14 +2943,6 @@ static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 	return true;
 }
 
-static void bio_set_ioprio(struct bio *bio)
-{
-	/* Nobody set ioprio so far? Initialize it based on task's nice value */
-	if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
-		bio->bi_ioprio = get_current_ioprio();
-	blkcg_set_ioprio(bio);
-}
-
 /**
  * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
@@ -2976,7 +2967,6 @@ void blk_mq_submit_bio(struct bio *bio)
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	bio_set_ioprio(bio);
 
 	if (plug) {
 		rq = rq_list_peek(&plug->cached_rq);
-- 
GitLab


From e77e15fa5eb1c830597c5ca53ea7af973bae2f78 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Thu, 1 Feb 2024 11:15:26 +0000
Subject: [PATCH 3836/4076] cifs: avoid redundant calls to disable multichannel

When the server reports query network interface info call
as unsupported following a tree connect, it means that
multichannel is unsupported, even if the server capabilities
report otherwise.

When this happens, cifs_chan_skip_or_disable is called to
disable multichannel on the client. However, we only need
to call this when multichannel is currently setup.

Fixes: f591062bdbf4 ("cifs: handle servers that still advertise multichannel after disabling")
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 6db54c6ef5719..e257b10bc8202 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -419,7 +419,7 @@ skip_sess_setup:
 		rc = SMB3_request_interfaces(xid, tcon, false);
 		free_xid(xid);
 
-		if (rc == -EOPNOTSUPP) {
+		if (rc == -EOPNOTSUPP && ses->chan_count > 1) {
 			/*
 			 * some servers like Azure SMB server do not advertise
 			 * that multichannel has been disabled with server
-- 
GitLab


From 88675b22d34e6e815ad4bde09c590ccb2d50c59d Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Thu, 1 Feb 2024 11:15:28 +0000
Subject: [PATCH 3837/4076] cifs: do not search for channel if server is
 terminating

In order to scale down the channels, the following sequence
of operations happen:
1. server struct is marked for terminate
2. the channel is deallocated in the ses->chans array
3. at a later point the cifsd thread actually terminates the server

Between 2 and 3, there can be calls to find the channel for
a server struct. When that happens, there can be an ugly warning
that's logged. But this is expected.

So this change does two things:
1. in cifs_ses_get_chan_index, if server->terminate is set, return
2. always make sure server->terminate is set with chan_lock held

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/sess.c    | 4 ++++
 fs/smb/client/smb2pdu.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index cde81042bebda..3d2548c35c9d5 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -75,6 +75,10 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
 {
 	unsigned int i;
 
+	/* if the channel is waiting for termination */
+	if (server->terminate)
+		return CIFS_INVAL_CHAN_INDEX;
+
 	for (i = 0; i < ses->chan_count; i++) {
 		if (ses->chans[i].server == server)
 			return i;
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index e257b10bc8202..c58fa44dd6b06 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -178,6 +178,7 @@ cifs_chan_skip_or_disable(struct cifs_ses *ses,
 		}
 
 		ses->chans[chan_index].server = NULL;
+		server->terminate = true;
 		spin_unlock(&ses->chan_lock);
 
 		/*
@@ -188,7 +189,6 @@ cifs_chan_skip_or_disable(struct cifs_ses *ses,
 		 */
 		cifs_put_tcp_session(server, from_reconnect);
 
-		server->terminate = true;
 		cifs_signal_cifsd_for_reconnect(server, false);
 
 		/* mark primary server as needing reconnect */
-- 
GitLab


From 6aac002bcfd554aff6d3ebb55e1660d078d70ab0 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Thu, 1 Feb 2024 11:15:29 +0000
Subject: [PATCH 3838/4076] cifs: failure to add channel on iface should bump
 up weight

After the interface selection policy change to do a weighted
round robin, each iface maintains a weight_fulfilled. When the
weight_fulfilled reaches the total weight for the iface, we know
that the weights can be reset and ifaces can be allocated from
scratch again.

During channel allocation failures on a particular channel,
weight_fulfilled is not incremented. If a few interfaces are
inactive, we could end up in a situation where the active
interfaces are all allocated for the total_weight, and inactive
ones are all that remain. This can cause a situation where
no more channels can be allocated further.

This change fixes it by increasing weight_fulfilled, even when
channel allocation failure happens. This could mean that if
there are temporary failures in channel allocation, the iface
weights may not strictly be adhered to. But that's still okay.

Fixes: a6d8fb54a515 ("cifs: distribute channels across interfaces based on speed")
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/sess.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index 3d2548c35c9d5..ed4bd88dd528a 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -273,6 +273,8 @@ int cifs_try_adding_channels(struct cifs_ses *ses)
 					 &iface->sockaddr,
 					 rc);
 				kref_put(&iface->refcount, release_iface);
+				/* failure to add chan should increase weight */
+				iface->weight_fulfilled++;
 				continue;
 			}
 
-- 
GitLab


From 11d4d1dba3315f73d2d1d386f5bf4811a8241d45 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Mon, 29 Jan 2024 21:04:44 -0300
Subject: [PATCH 3839/4076] smb: client: increase number of PDUs allowed in a
 compound request

With the introduction of SMB2_OP_QUERY_WSL_EA, the client may now send
5 commands in a single compound request in order to query xattrs from
potential WSL reparse points, which should be fine as we currently
allow up to 5 PDUs in a single compound request.  However, if
encryption is enabled (e.g. 'seal' mount option) or enforced by the
server, current MAX_COMPOUND(5) won't be enough as we require an extra
PDU for the transform header.

Fix this by increasing MAX_COMPOUND to 7 and, while we're at it, add
an WARN_ON_ONCE() and return -EIO instead of -ENOMEM in case we
attempt to send a compound request that couldn't include the extra
transform header.

Signed-off-by: Paulo Alcantara <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h  | 2 +-
 fs/smb/client/transport.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 9093c507042fa..c86a72c9d9ecd 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -87,7 +87,7 @@
 #define SMB_INTERFACE_POLL_INTERVAL	600
 
 /* maximum number of PDUs in one compound */
-#define MAX_COMPOUND 5
+#define MAX_COMPOUND 7
 
 /*
  * Default number of credits to keep available for SMB3.
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index e00278fcfa4fa..994d701934329 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -435,8 +435,8 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	if (!(flags & CIFS_TRANSFORM_REQ))
 		return __smb_send_rqst(server, num_rqst, rqst);
 
-	if (num_rqst > MAX_COMPOUND - 1)
-		return -ENOMEM;
+	if (WARN_ON_ONCE(num_rqst > MAX_COMPOUND - 1))
+		return -EIO;
 
 	if (!server->ops->init_transform_rq) {
 		cifs_server_dbg(VFS, "Encryption requested but transform callback is missing\n");
-- 
GitLab


From 1458eb2c9d88ad4b35eb6d6a4aa1d43d8fbf7f62 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 17 Jan 2024 20:57:40 +0100
Subject: [PATCH 3840/4076] riscv: Fix set_huge_pte_at() for NAPOT mapping

As stated by the privileged specification, we must clear a NAPOT
mapping and emit a sfence.vma before setting a new translation.

Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240117195741.1926459-2-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/hugetlbpage.c | 42 +++++++++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 431596c0e20e0..865ac5c7d159e 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -177,13 +177,36 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 	return entry;
 }
 
+static void clear_flush(struct mm_struct *mm,
+			unsigned long addr,
+			pte_t *ptep,
+			unsigned long pgsize,
+			unsigned long ncontig)
+{
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		ptep_get_and_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
+/*
+ * When dealing with NAPOT mappings, the privileged specification indicates that
+ * "if an update needs to be made, the OS generally should first mark all of the
+ * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions
+ * within the range, [...] then update the PTE(s), as described in Section
+ * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by
+ * arm64.
+ */
 void set_huge_pte_at(struct mm_struct *mm,
 		     unsigned long addr,
 		     pte_t *ptep,
 		     pte_t pte,
 		     unsigned long sz)
 {
-	unsigned long hugepage_shift;
+	unsigned long hugepage_shift, pgsize;
 	int i, pte_num;
 
 	if (sz >= PGDIR_SIZE)
@@ -198,7 +221,22 @@ void set_huge_pte_at(struct mm_struct *mm,
 		hugepage_shift = PAGE_SHIFT;
 
 	pte_num = sz >> hugepage_shift;
-	for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift))
+	pgsize = 1 << hugepage_shift;
+
+	if (!pte_present(pte)) {
+		for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
+			set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	if (!pte_napot(pte)) {
+		set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	clear_flush(mm, addr, ptep, pgsize, pte_num);
+
+	for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
 		set_pte_at(mm, addr, ptep, pte);
 }
 
-- 
GitLab


From a179a4bfb694f80f2709a1d0398469e787acb974 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 17 Jan 2024 20:57:41 +0100
Subject: [PATCH 3841/4076] riscv: Fix hugetlb_mask_last_page() when NAPOT is
 enabled

When NAPOT is enabled, a new hugepage size is available and then we need
to make hugetlb_mask_last_page() aware of that.

Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240117195741.1926459-3-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/hugetlbpage.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 865ac5c7d159e..87406b26c3dad 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -125,6 +125,26 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	return pte;
 }
 
+unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+	unsigned long hp_size = huge_page_size(h);
+
+	switch (hp_size) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		return P4D_SIZE - PUD_SIZE;
+#endif
+	case PMD_SIZE:
+		return PUD_SIZE - PMD_SIZE;
+	case napot_cont_size(NAPOT_CONT64KB_ORDER):
+		return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER);
+	default:
+		break;
+	}
+
+	return 0UL;
+}
+
 static pte_t get_clear_contig(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep,
-- 
GitLab


From 021533194476035883300d60fbb3136426ac8ea5 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 1 Feb 2024 14:57:17 -0800
Subject: [PATCH 3842/4076] Kconfig: Disable -Wstringop-overflow for GCC
 globally

It turns out it was never just gcc-11 that was broken.  Apparently it
just happens to work on x86-64 with other gcc versions.

On arm64, I see warnings with gcc version 13.2.1, and the kernel test
robot reports the same problem on s390 with gcc 13.2.0.

Admittedly it seems to be just the new Xe drm driver, but this is
keeping me from doing my normal arm64 build testing.  So it gets
reverted until somebody figures out what causes the problem (and why it
doesn't show on x86-64, which is what makes me suspect it was never just
about gcc-11, and more about just random happenstance).

This also changes the Kconfig naming a bit - just make the "disable this
for GCC" conditional be one simple Kconfig entry, and we can put the gcc
version dependencies in that entry once we figure out what the correct
rules are.

The version dependency _may_ still end up being "gcc version larger than
11" if the issue is purely in the Xe driver, but even if that ends up
the case, let's make that all part of the "GCC_NO_STRINGOP_OVERFLOW"
logic.

For now, we just disable it for all gcc versions while the exact cause
is unknown.

Link: https://lore.kernel.org/all/202401161031.hjGJHMiJ-lkp@intel.com/T/
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 init/Kconfig | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 8d4e836e1b6b1..deda3d14135bb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -876,13 +876,13 @@ config CC_NO_ARRAY_BOUNDS
 	bool
 	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC11_NO_ARRAY_BOUNDS
 
-# Currently, disable -Wstringop-overflow for GCC 11, globally.
-config GCC11_NO_STRINGOP_OVERFLOW
+# Currently, disable -Wstringop-overflow for GCC globally.
+config GCC_NO_STRINGOP_OVERFLOW
 	def_bool y
 
 config CC_NO_STRINGOP_OVERFLOW
 	bool
-	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_STRINGOP_OVERFLOW
+	default y if CC_IS_GCC && GCC_NO_STRINGOP_OVERFLOW
 
 config CC_STRINGOP_OVERFLOW
 	bool
-- 
GitLab


From 3fcc2b887a1ba4c1f45319cd8c54daa263ecbc36 Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Sat, 27 Jan 2024 09:58:00 +0800
Subject: [PATCH 3843/4076] ext4: refactor ext4_da_map_blocks()

Refactor and cleanup ext4_da_map_blocks(), reduce some unnecessary
parameters and branches, no logic changes.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240127015825.1608160-2-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 39 +++++++++++++++++----------------------
 1 file changed, 17 insertions(+), 22 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4cae8698f70cf..bbd5ee6dd3f37 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1704,7 +1704,6 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
 		if (ext4_es_is_hole(&es)) {
-			retval = 0;
 			down_read(&EXT4_I(inode)->i_data_sem);
 			goto add_delayed;
 		}
@@ -1749,26 +1748,9 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
 	else
 		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
-
-add_delayed:
-	if (retval == 0) {
-		int ret;
-
-		/*
-		 * XXX: __block_prepare_write() unmaps passed block,
-		 * is it OK?
-		 */
-
-		ret = ext4_insert_delayed_block(inode, map->m_lblk);
-		if (ret != 0) {
-			retval = ret;
-			goto out_unlock;
-		}
-
-		map_bh(bh, inode->i_sb, invalid_block);
-		set_buffer_new(bh);
-		set_buffer_delay(bh);
-	} else if (retval > 0) {
+	if (retval < 0)
+		goto out_unlock;
+	if (retval > 0) {
 		unsigned int status;
 
 		if (unlikely(retval != map->m_len)) {
@@ -1783,11 +1765,24 @@ add_delayed:
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
 				      map->m_pblk, status);
+		goto out_unlock;
 	}
 
+add_delayed:
+	/*
+	 * XXX: __block_prepare_write() unmaps passed block,
+	 * is it OK?
+	 */
+	retval = ext4_insert_delayed_block(inode, map->m_lblk);
+	if (retval)
+		goto out_unlock;
+
+	map_bh(bh, inode->i_sb, invalid_block);
+	set_buffer_new(bh);
+	set_buffer_delay(bh);
+
 out_unlock:
 	up_read((&EXT4_I(inode)->i_data_sem));
-
 	return retval;
 }
 
-- 
GitLab


From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Sat, 27 Jan 2024 09:58:01 +0800
Subject: [PATCH 3844/4076] ext4: convert to exclusive lock while inserting
 delalloc extents

ext4_da_map_blocks() only hold i_data_sem in shared mode and i_rwsem
when inserting delalloc extents, it could be raced by another querying
path of ext4_map_blocks() without i_rwsem, .e.g buffered read path.
Suppose we buffered read a file containing just a hole, and without any
cached extents tree, then it is raced by another delayed buffered write
to the same area or the near area belongs to the same hole, and the new
delalloc extent could be overwritten to a hole extent.

 pread()                           pwrite()
  filemap_read_folio()
   ext4_mpage_readpages()
    ext4_map_blocks()
     down_read(i_data_sem)
     ext4_ext_determine_hole()
     //find hole
     ext4_ext_put_gap_in_cache()
      ext4_es_find_extent_range()
      //no delalloc extent
                                    ext4_da_map_blocks()
                                     down_read(i_data_sem)
                                     ext4_insert_delayed_block()
                                     //insert delalloc extent
      ext4_es_insert_extent()
      //overwrite delalloc extent to hole

This race could lead to inconsistent delalloc extents tree and
incorrect reserved space counter. Fix this by converting to hold
i_data_sem in exclusive mode when adding a new delalloc extent in
ext4_da_map_blocks().

Cc: stable@vger.kernel.org
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index bbd5ee6dd3f37..b040337501e3e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1703,10 +1703,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
-		if (ext4_es_is_hole(&es)) {
-			down_read(&EXT4_I(inode)->i_data_sem);
+		if (ext4_es_is_hole(&es))
 			goto add_delayed;
-		}
 
 		/*
 		 * Delayed extent could be allocated by fallocate.
@@ -1748,8 +1746,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
 	else
 		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
-	if (retval < 0)
-		goto out_unlock;
+	if (retval < 0) {
+		up_read(&EXT4_I(inode)->i_data_sem);
+		return retval;
+	}
 	if (retval > 0) {
 		unsigned int status;
 
@@ -1765,24 +1765,21 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
 				      map->m_pblk, status);
-		goto out_unlock;
+		up_read(&EXT4_I(inode)->i_data_sem);
+		return retval;
 	}
+	up_read(&EXT4_I(inode)->i_data_sem);
 
 add_delayed:
-	/*
-	 * XXX: __block_prepare_write() unmaps passed block,
-	 * is it OK?
-	 */
+	down_write(&EXT4_I(inode)->i_data_sem);
 	retval = ext4_insert_delayed_block(inode, map->m_lblk);
+	up_write(&EXT4_I(inode)->i_data_sem);
 	if (retval)
-		goto out_unlock;
+		return retval;
 
 	map_bh(bh, inode->i_sb, invalid_block);
 	set_buffer_new(bh);
 	set_buffer_delay(bh);
-
-out_unlock:
-	up_read((&EXT4_I(inode)->i_data_sem));
 	return retval;
 }
 
-- 
GitLab


From 6430dea07e85958fa87d0276c0c4388dd51e630b Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Sat, 27 Jan 2024 09:58:02 +0800
Subject: [PATCH 3845/4076] ext4: correct the hole length returned by
 ext4_map_blocks()

In ext4_map_blocks(), if we can't find a range of mapping in the
extents cache, we are calling ext4_ext_map_blocks() to search the real
path and ext4_ext_determine_hole() to determine the hole range. But if
the querying range was partially or completely overlaped by a delalloc
extent, we can't find it in the real extent path, so the returned hole
length could be incorrect.

Fortunately, ext4_ext_put_gap_in_cache() have already handle delalloc
extent, but it searches start from the expanded hole_start, doesn't
start from the querying range, so the delalloc extent found could not be
the one that overlaped the querying range, plus, it also didn't adjust
the hole length. Let's just remove ext4_ext_put_gap_in_cache(), handle
delalloc and insert adjusted hole extent in ext4_ext_determine_hole().

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240127015825.1608160-4-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/extents.c | 111 +++++++++++++++++++++++++++++-----------------
 1 file changed, 70 insertions(+), 41 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 9106715254ac0..c5b54fb9eb8bd 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2229,7 +2229,7 @@ static int ext4_fill_es_cache_info(struct inode *inode,
 
 
 /*
- * ext4_ext_determine_hole - determine hole around given block
+ * ext4_ext_find_hole - find hole around given block according to the given path
  * @inode:	inode we lookup in
  * @path:	path in extent tree to @lblk
  * @lblk:	pointer to logical block around which we want to determine hole
@@ -2241,9 +2241,9 @@ static int ext4_fill_es_cache_info(struct inode *inode,
  * The function returns the length of a hole starting at @lblk. We update @lblk
  * to the beginning of the hole if we managed to find it.
  */
-static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
-					   struct ext4_ext_path *path,
-					   ext4_lblk_t *lblk)
+static ext4_lblk_t ext4_ext_find_hole(struct inode *inode,
+				      struct ext4_ext_path *path,
+				      ext4_lblk_t *lblk)
 {
 	int depth = ext_depth(inode);
 	struct ext4_extent *ex;
@@ -2270,30 +2270,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
 	return len;
 }
 
-/*
- * ext4_ext_put_gap_in_cache:
- * calculate boundaries of the gap that the requested block fits into
- * and cache this gap
- */
-static void
-ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start,
-			  ext4_lblk_t hole_len)
-{
-	struct extent_status es;
-
-	ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
-				  hole_start + hole_len - 1, &es);
-	if (es.es_len) {
-		/* There's delayed extent containing lblock? */
-		if (es.es_lblk <= hole_start)
-			return;
-		hole_len = min(es.es_lblk - hole_start, hole_len);
-	}
-	ext_debug(inode, " -> %u:%u\n", hole_start, hole_len);
-	ext4_es_insert_extent(inode, hole_start, hole_len, ~0,
-			      EXTENT_STATUS_HOLE);
-}
-
 /*
  * ext4_ext_rm_idx:
  * removes index from the index block.
@@ -4062,6 +4038,69 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 	return 0;
 }
 
+/*
+ * Determine hole length around the given logical block, first try to
+ * locate and expand the hole from the given @path, and then adjust it
+ * if it's partially or completely converted to delayed extents, insert
+ * it into the extent cache tree if it's indeed a hole, finally return
+ * the length of the determined extent.
+ */
+static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode,
+						  struct ext4_ext_path *path,
+						  ext4_lblk_t lblk)
+{
+	ext4_lblk_t hole_start, len;
+	struct extent_status es;
+
+	hole_start = lblk;
+	len = ext4_ext_find_hole(inode, path, &hole_start);
+again:
+	ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
+				  hole_start + len - 1, &es);
+	if (!es.es_len)
+		goto insert_hole;
+
+	/*
+	 * There's a delalloc extent in the hole, handle it if the delalloc
+	 * extent is in front of, behind and straddle the queried range.
+	 */
+	if (lblk >= es.es_lblk + es.es_len) {
+		/*
+		 * The delalloc extent is in front of the queried range,
+		 * find again from the queried start block.
+		 */
+		len -= lblk - hole_start;
+		hole_start = lblk;
+		goto again;
+	} else if (in_range(lblk, es.es_lblk, es.es_len)) {
+		/*
+		 * The delalloc extent containing lblk, it must have been
+		 * added after ext4_map_blocks() checked the extent status
+		 * tree, adjust the length to the delalloc extent's after
+		 * lblk.
+		 */
+		len = es.es_lblk + es.es_len - lblk;
+		return len;
+	} else {
+		/*
+		 * The delalloc extent is partially or completely behind
+		 * the queried range, update hole length until the
+		 * beginning of the delalloc extent.
+		 */
+		len = min(es.es_lblk - hole_start, len);
+	}
+
+insert_hole:
+	/* Put just found gap into cache to speed up subsequent requests */
+	ext_debug(inode, " -> %u:%u\n", hole_start, len);
+	ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE);
+
+	/* Update hole_len to reflect hole size after lblk */
+	if (hole_start != lblk)
+		len -= lblk - hole_start;
+
+	return len;
+}
 
 /*
  * Block allocation/map/preallocation routine for extents based files
@@ -4179,22 +4218,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * we couldn't try to create block if create flag is zero
 	 */
 	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
-		ext4_lblk_t hole_start, hole_len;
+		ext4_lblk_t len;
 
-		hole_start = map->m_lblk;
-		hole_len = ext4_ext_determine_hole(inode, path, &hole_start);
-		/*
-		 * put just found gap into cache to speed up
-		 * subsequent requests
-		 */
-		ext4_ext_put_gap_in_cache(inode, hole_start, hole_len);
+		len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk);
 
-		/* Update hole_len to reflect hole size after map->m_lblk */
-		if (hole_start != map->m_lblk)
-			hole_len -= map->m_lblk - hole_start;
 		map->m_pblk = 0;
-		map->m_len = min_t(unsigned int, map->m_len, hole_len);
-
+		map->m_len = min_t(unsigned int, map->m_len, len);
 		goto out;
 	}
 
-- 
GitLab


From 683cd8259a9b883a51973511f860976db2550a6e Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 26 Jan 2024 17:07:23 +0100
Subject: [PATCH 3846/4076] Input: atkbd - skip ATKBD_CMD_SETLEDS when skipping
 ATKBD_CMD_GETID

After commit 936e4d49ecbc ("Input: atkbd - skip ATKBD_CMD_GETID in
translated mode") the keyboard on Dell XPS 13 9350 / 9360 / 9370 models
has stopped working after a suspend/resume.

The problem appears to be that atkbd_probe() fails when called
from atkbd_reconnect() on resume, which on systems where
ATKBD_CMD_GETID is skipped can only happen by ATKBD_CMD_SETLEDS
failing. ATKBD_CMD_SETLEDS failing because ATKBD_CMD_GETID was
skipped is weird, but apparently that is what is happening.

Fix this by also skipping ATKBD_CMD_SETLEDS when skipping
ATKBD_CMD_GETID.

Fixes: 936e4d49ecbc ("Input: atkbd - skip ATKBD_CMD_GETID in translated mode")
Reported-by: Paul Menzel <pmenzel@molgen.mpg.de>
Closes: https://lore.kernel.org/linux-input/0aa4a61f-c939-46fe-a572-08022e8931c7@molgen.mpg.de/
Closes: https://bbs.archlinux.org/viewtopic.php?pid=2146300
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218424
Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2260517
Tested-by: Paul Menzel <pmenzel@molgen.mpg.de>
Cc: stable@vger.kernel.org
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240126160724.13278-2-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/atkbd.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 13ef6284223da..c229bd6b3f7f2 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -811,7 +811,6 @@ static int atkbd_probe(struct atkbd *atkbd)
 {
 	struct ps2dev *ps2dev = &atkbd->ps2dev;
 	unsigned char param[2];
-	bool skip_getid;
 
 /*
  * Some systems, where the bit-twiddling when testing the io-lines of the
@@ -825,6 +824,11 @@ static int atkbd_probe(struct atkbd *atkbd)
 				 "keyboard reset failed on %s\n",
 				 ps2dev->serio->phys);
 
+	if (atkbd_skip_getid(atkbd)) {
+		atkbd->id = 0xab83;
+		return 0;
+	}
+
 /*
  * Then we check the keyboard ID. We should get 0xab83 under normal conditions.
  * Some keyboards report different values, but the first byte is always 0xab or
@@ -833,18 +837,17 @@ static int atkbd_probe(struct atkbd *atkbd)
  */
 
 	param[0] = param[1] = 0xa5;	/* initialize with invalid values */
-	skip_getid = atkbd_skip_getid(atkbd);
-	if (skip_getid || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
+	if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
 
 /*
- * If the get ID command was skipped or failed, we check if we can at least set
+ * If the get ID command failed, we check if we can at least set
  * the LEDs on the keyboard. This should work on every keyboard out there.
  * It also turns the LEDs off, which we want anyway.
  */
 		param[0] = 0;
 		if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS))
 			return -1;
-		atkbd->id = skip_getid ? 0xab83 : 0xabba;
+		atkbd->id = 0xabba;
 		return 0;
 	}
 
-- 
GitLab


From 9cf6e24c9fbf17e52de9fff07f12be7565ea6d61 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 26 Jan 2024 17:07:24 +0100
Subject: [PATCH 3847/4076] Input: atkbd - do not skip atkbd_deactivate() when
 skipping ATKBD_CMD_GETID

After commit 936e4d49ecbc ("Input: atkbd - skip ATKBD_CMD_GETID in
translated mode") not only the getid command is skipped, but also
the de-activating of the keyboard at the end of atkbd_probe(), potentially
re-introducing the problem fixed by commit be2d7e4233a4 ("Input: atkbd -
fix multi-byte scancode handling on reconnect").

Make sure multi-byte scancode handling on reconnect is still handled
correctly by not skipping the atkbd_deactivate() call.

Fixes: 936e4d49ecbc ("Input: atkbd - skip ATKBD_CMD_GETID in translated mode")
Tested-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240126160724.13278-3-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/atkbd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index c229bd6b3f7f2..7f67f9f2946b4 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -826,7 +826,7 @@ static int atkbd_probe(struct atkbd *atkbd)
 
 	if (atkbd_skip_getid(atkbd)) {
 		atkbd->id = 0xab83;
-		return 0;
+		goto deactivate_kbd;
 	}
 
 /*
@@ -863,6 +863,7 @@ static int atkbd_probe(struct atkbd *atkbd)
 		return -1;
 	}
 
+deactivate_kbd:
 /*
  * Make sure nothing is coming from the keyboard and disturbs our
  * internal state.
-- 
GitLab


From 9f1118223aa080021fe9751fa221590654d27669 Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Sat, 27 Jan 2024 09:58:03 +0800
Subject: [PATCH 3848/4076] ext4: add a hole extent entry in cache after punch

In order to cache hole extents in the extent status tree and keep the
hole length as long as possible, re-add a hole entry to the cache just
after punching a hole.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240127015825.1608160-5-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b040337501e3e..af205b416794d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4007,12 +4007,12 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 
 	/* If there are blocks to remove, do it */
 	if (stop_block > first_block) {
+		ext4_lblk_t hole_len = stop_block - first_block;
 
 		down_write(&EXT4_I(inode)->i_data_sem);
 		ext4_discard_preallocations(inode);
 
-		ext4_es_remove_extent(inode, first_block,
-				      stop_block - first_block);
+		ext4_es_remove_extent(inode, first_block, hole_len);
 
 		if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 			ret = ext4_ext_remove_space(inode, first_block,
@@ -4021,6 +4021,8 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 			ret = ext4_ind_remove_space(handle, inode, first_block,
 						    stop_block);
 
+		ext4_es_insert_extent(inode, first_block, hole_len, ~0,
+				      EXTENT_STATUS_HOLE);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	ext4_fc_track_range(handle, inode, first_block, stop_block);
-- 
GitLab


From 874eaba96d39334fe9c729ff631e65523616d4d8 Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Sat, 27 Jan 2024 09:58:04 +0800
Subject: [PATCH 3849/4076] ext4: make ext4_map_blocks() distinguish delalloc
 only extent

Add a new map flag EXT4_MAP_DELAYED to indicate the mapping range is a
delayed allocated only (not unwritten) one, and making
ext4_map_blocks() can distinguish it, no longer mixing it with holes.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240127015825.1608160-6-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h    | 4 +++-
 fs/ext4/extents.c | 7 +++++--
 fs/ext4/inode.c   | 2 ++
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 786b6857ab474..023571f8dd1b4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -252,8 +252,10 @@ struct ext4_allocation_request {
 #define EXT4_MAP_MAPPED		BIT(BH_Mapped)
 #define EXT4_MAP_UNWRITTEN	BIT(BH_Unwritten)
 #define EXT4_MAP_BOUNDARY	BIT(BH_Boundary)
+#define EXT4_MAP_DELAYED	BIT(BH_Delay)
 #define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
-				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
+				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
+				 EXT4_MAP_DELAYED)
 
 struct ext4_map_blocks {
 	ext4_fsblk_t m_pblk;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c5b54fb9eb8bd..7669d154c05e0 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4076,8 +4076,11 @@ again:
 		/*
 		 * The delalloc extent containing lblk, it must have been
 		 * added after ext4_map_blocks() checked the extent status
-		 * tree, adjust the length to the delalloc extent's after
-		 * lblk.
+		 * tree so we are not holding i_rwsem and delalloc info is
+		 * only stabilized by i_data_sem we are going to release
+		 * soon. Don't modify the extent status tree and report
+		 * extent as a hole, just adjust the length to the delalloc
+		 * extent's after lblk.
 		 */
 		len = es.es_lblk + es.es_len - lblk;
 		return len;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index af205b416794d..60f0d2dc1c379 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -515,6 +515,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			map->m_len = retval;
 		} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
 			map->m_pblk = 0;
+			map->m_flags |= ext4_es_is_delayed(&es) ?
+					EXT4_MAP_DELAYED : 0;
 			retval = es.es_len - (map->m_lblk - es.es_lblk);
 			if (retval > map->m_len)
 				retval = map->m_len;
-- 
GitLab


From ec9d669eba4c276d00af88951947fe0e82a6b84c Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Sat, 27 Jan 2024 09:58:05 +0800
Subject: [PATCH 3850/4076] ext4: make ext4_set_iomap() recognize
 IOMAP_DELALLOC map type

Since ext4_map_blocks() can recognize a delayed allocated only extent,
make ext4_set_iomap() can also recognize it, and remove the useless
separate check in ext4_iomap_begin_report().

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240127015825.1608160-7-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 32 +++-----------------------------
 1 file changed, 3 insertions(+), 29 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 60f0d2dc1c379..2ccf3b5e3a7c4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3262,6 +3262,9 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 		iomap->addr = (u64) map->m_pblk << blkbits;
 		if (flags & IOMAP_DAX)
 			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
+	} else if (map->m_flags & EXT4_MAP_DELAYED) {
+		iomap->type = IOMAP_DELALLOC;
+		iomap->addr = IOMAP_NULL_ADDR;
 	} else {
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
@@ -3424,35 +3427,11 @@ const struct iomap_ops ext4_iomap_overwrite_ops = {
 	.iomap_end		= ext4_iomap_end,
 };
 
-static bool ext4_iomap_is_delalloc(struct inode *inode,
-				   struct ext4_map_blocks *map)
-{
-	struct extent_status es;
-	ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1;
-
-	ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
-				  map->m_lblk, end, &es);
-
-	if (!es.es_len || es.es_lblk > end)
-		return false;
-
-	if (es.es_lblk > map->m_lblk) {
-		map->m_len = es.es_lblk - map->m_lblk;
-		return false;
-	}
-
-	offset = map->m_lblk - es.es_lblk;
-	map->m_len = es.es_len - offset;
-
-	return true;
-}
-
 static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 				   loff_t length, unsigned int flags,
 				   struct iomap *iomap, struct iomap *srcmap)
 {
 	int ret;
-	bool delalloc = false;
 	struct ext4_map_blocks map;
 	u8 blkbits = inode->i_blkbits;
 
@@ -3493,13 +3472,8 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 	ret = ext4_map_blocks(NULL, inode, &map, 0);
 	if (ret < 0)
 		return ret;
-	if (ret == 0)
-		delalloc = ext4_iomap_is_delalloc(inode, &map);
-
 set_iomap:
 	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
-	if (delalloc && iomap->type == IOMAP_HOLE)
-		iomap->type = IOMAP_DELALLOC;
 
 	return 0;
 }
-- 
GitLab


From b5e69be185495696652405088a27ab0b21812147 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 30 Jan 2024 13:24:40 +1000
Subject: [PATCH 3851/4076] nouveau/gsp: use correct size for registry rpc.

Timur pointed this out before, and it just slipped my mind,
but this might help some things work better, around pcie power
management.

Fixes: 8d55b0a940bb ("nouveau/gsp: add some basic registry entries.")
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/576336/
---
 drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 9ee58e2a0eb2a..5e1fa176aac4a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1078,7 +1078,6 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 	if (IS_ERR(rpc))
 		return PTR_ERR(rpc);
 
-	rpc->size = sizeof(*rpc);
 	rpc->numEntries = NV_GSP_REG_NUM_ENTRIES;
 
 	str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]);
@@ -1094,6 +1093,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 		strings += name_len;
 		str_offset += name_len;
 	}
+	rpc->size = str_offset;
 
 	return nvkm_gsp_rpc_wr(gsp, rpc, false);
 }
-- 
GitLab


From 39126abc5e20611579602f03b66627d7cd1422f0 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Mon, 29 Jan 2024 11:26:45 +1000
Subject: [PATCH 3852/4076] nouveau: offload fence uevents work to workqueue

This should break the deadlock between the fctx lock and the irq lock.

This offloads the processing off the work from the irq into a workqueue.

Cc: linux-stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/576237/
---
 drivers/gpu/drm/nouveau/nouveau_fence.c | 24 ++++++++++++++++++------
 drivers/gpu/drm/nouveau/nouveau_fence.h |  1 +
 2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index ca762ea554136..93f08f9479d89 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -103,6 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 void
 nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 {
+	cancel_work_sync(&fctx->uevent_work);
 	nouveau_fence_context_kill(fctx, 0);
 	nvif_event_dtor(&fctx->event);
 	fctx->dead = 1;
@@ -145,12 +146,13 @@ nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fc
 	return drop;
 }
 
-static int
-nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
+static void
+nouveau_fence_uevent_work(struct work_struct *work)
 {
-	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
+						       uevent_work);
 	unsigned long flags;
-	int ret = NVIF_EVENT_KEEP;
+	int drop = 0;
 
 	spin_lock_irqsave(&fctx->lock, flags);
 	if (!list_empty(&fctx->pending)) {
@@ -160,11 +162,20 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
 		if (nouveau_fence_update(chan, fctx))
-			ret = NVIF_EVENT_DROP;
+			drop = 1;
 	}
+	if (drop)
+		nvif_event_block(&fctx->event);
+
 	spin_unlock_irqrestore(&fctx->lock, flags);
+}
 
-	return ret;
+static int
+nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
+{
+	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	schedule_work(&fctx->uevent_work);
+	return NVIF_EVENT_KEEP;
 }
 
 void
@@ -178,6 +189,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 	} args;
 	int ret;
 
+	INIT_WORK(&fctx->uevent_work, nouveau_fence_uevent_work);
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 64d33ae7f3561..8bc065acfe358 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -44,6 +44,7 @@ struct nouveau_fence_chan {
 	u32 context;
 	char name[32];
 
+	struct work_struct uevent_work;
 	struct nvif_event event;
 	int notify_ref, dead, killed;
 };
-- 
GitLab


From d2d00e15808c37ec476a5c040ee2cdd23854ef18 Mon Sep 17 00:00:00 2001
From: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Date: Fri, 26 Jan 2024 09:09:18 -0600
Subject: [PATCH 3853/4076] powerpc: iommu: Bring back table group
 release_ownership() call

The commit 2ad56efa80db ("powerpc/iommu: Setup a default domain and
remove set_platform_dma_ops") refactored the code removing the
set_platform_dma_ops(). It missed out the table group
release_ownership() call which would have got called otherwise
during the guest shutdown via vfio_group_detach_container(). On
PPC64, this particular call actually sets up the 32-bit TCE table,
and enables the 64-bit DMA bypass etc. Now after guest shutdown,
the subsequent host driver (e.g megaraid-sas) probe post unbind
from vfio-pci fails like,

megaraid_sas 0031:01:00.0: Warning: IOMMU dma not supported: mask 0x7fffffffffffffff, table unavailable
megaraid_sas 0031:01:00.0: Warning: IOMMU dma not supported: mask 0xffffffff, table unavailable
megaraid_sas 0031:01:00.0: Failed to set DMA mask
megaraid_sas 0031:01:00.0: Failed from megasas_init_fw 6539

The patch brings back the call to table_group release_ownership()
call when switching back to PLATFORM domain from BLOCKED, while
also separates the domain_ops for both.

Fixes: 2ad56efa80db ("powerpc/iommu: Setup a default domain and remove set_platform_dma_ops")
Signed-off-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/170628173462.3742.18330000394415935845.stgit@ltcd48-lp2.aus.stglab.ibm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/powerpc/kernel/iommu.c | 37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ebe259bdd4629..d71eac3b2887b 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1287,20 +1287,20 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct iommu_group *grp = iommu_group_get(dev);
 	struct iommu_table_group *table_group;
-	int ret = -EINVAL;
 
 	/* At first attach the ownership is already set */
 	if (!domain)
 		return 0;
 
-	if (!grp)
-		return -ENODEV;
-
 	table_group = iommu_group_get_iommudata(grp);
-	ret = table_group->ops->take_ownership(table_group);
+	/*
+	 * The domain being set to PLATFORM from earlier
+	 * BLOCKED. The table_group ownership has to be released.
+	 */
+	table_group->ops->release_ownership(table_group);
 	iommu_group_put(grp);
 
-	return ret;
+	return 0;
 }
 
 static const struct iommu_domain_ops spapr_tce_platform_domain_ops = {
@@ -1312,13 +1312,32 @@ static struct iommu_domain spapr_tce_platform_domain = {
 	.ops = &spapr_tce_platform_domain_ops,
 };
 
-static struct iommu_domain spapr_tce_blocked_domain = {
-	.type = IOMMU_DOMAIN_BLOCKED,
+static int
+spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
+				     struct device *dev)
+{
+	struct iommu_group *grp = iommu_group_get(dev);
+	struct iommu_table_group *table_group;
+	int ret = -EINVAL;
+
 	/*
 	 * FIXME: SPAPR mixes blocked and platform behaviors, the blocked domain
 	 * also sets the dma_api ops
 	 */
-	.ops = &spapr_tce_platform_domain_ops,
+	table_group = iommu_group_get_iommudata(grp);
+	ret = table_group->ops->take_ownership(table_group);
+	iommu_group_put(grp);
+
+	return ret;
+}
+
+static const struct iommu_domain_ops spapr_tce_blocked_domain_ops = {
+	.attach_dev = spapr_tce_blocked_iommu_attach_dev,
+};
+
+static struct iommu_domain spapr_tce_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &spapr_tce_blocked_domain_ops,
 };
 
 static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
-- 
GitLab


From bb6f4dbe2639d5b8a9fde4bfb6fefecfd3f18df3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= <mic@digikod.net>
Date: Thu, 25 Jan 2024 16:32:29 +0100
Subject: [PATCH 3854/4076] selftests/landlock: Fix capability for net_test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

CAP_NET_ADMIN allows to configure network interfaces, not CAP_SYS_ADMIN
which only allows to call unshare(2).  Without this change, running
network tests as a non-root user but with all capabilities would fail at
the setup_loopback() step with "RTNETLINK answers: Operation not
permitted".

The issue is only visible when running tests with non-root users (i.e.
only relying on ambient capabilities).  Indeed, when configuring the
network interface, the "ip" command is called, which may lead to the
special handling of capabilities for the root user by execve(2).  If
root is the caller, then the inherited, permitted and effective
capabilities are all reset, which then includes CAP_NET_ADMIN.  However,
if a non-root user is the caller, then ambient capabilities are masked
by the inherited ones, which were explicitly dropped.

To make execution deterministic whatever users are running the tests,
set the noroot secure bit for each test, and set the inheritable and
ambient capabilities to CAP_NET_ADMIN, the only capability that may be
required after an execve(2).

Factor out _effective_cap() into _change_cap(), and use it to manage
ambient capabilities with the new set_ambient_cap() and
clear_ambient_cap() helpers.

This makes it possible to run all Landlock tests with check-linux.sh
from https://github.com/landlock-lsm/landlock-test-tools

Cc: Konstantin Meskhidze <konstantin.meskhidze@huawei.com>
Fixes: a549d055a22e ("selftests/landlock: Add network tests")
Link: https://lore.kernel.org/r/20240125153230.3817165-2-mic@digikod.net
[mic: Make sure SECBIT_NOROOT_LOCKED is set]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/common.h   | 48 +++++++++++++++++----
 tools/testing/selftests/landlock/net_test.c |  5 ++-
 2 files changed, 44 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index 5b79758cae627..e64bbdf0e86ea 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -9,6 +9,7 @@
 
 #include <errno.h>
 #include <linux/landlock.h>
+#include <linux/securebits.h>
 #include <sys/capability.h>
 #include <sys/socket.h>
 #include <sys/syscall.h>
@@ -115,11 +116,16 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 		/* clang-format off */
 		CAP_DAC_OVERRIDE,
 		CAP_MKNOD,
+		CAP_NET_ADMIN,
+		CAP_NET_BIND_SERVICE,
 		CAP_SYS_ADMIN,
 		CAP_SYS_CHROOT,
-		CAP_NET_BIND_SERVICE,
 		/* clang-format on */
 	};
+	const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED;
+
+	if ((cap_get_secbits() & noroot) != noroot)
+		EXPECT_EQ(0, cap_set_secbits(noroot));
 
 	cap_p = cap_get_proc();
 	EXPECT_NE(NULL, cap_p)
@@ -137,6 +143,8 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 			TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
 		}
 	}
+
+	/* Automatically resets ambient capabilities. */
 	EXPECT_NE(-1, cap_set_proc(cap_p))
 	{
 		TH_LOG("Failed to cap_set_proc: %s", strerror(errno));
@@ -145,6 +153,9 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 	{
 		TH_LOG("Failed to cap_free: %s", strerror(errno));
 	}
+
+	/* Quickly checks that ambient capabilities are cleared. */
+	EXPECT_NE(-1, cap_get_ambient(caps[0]));
 }
 
 /* We cannot put such helpers in a library because of kselftest_harness.h . */
@@ -158,8 +169,9 @@ static void __maybe_unused drop_caps(struct __test_metadata *const _metadata)
 	_init_caps(_metadata, true);
 }
 
-static void _effective_cap(struct __test_metadata *const _metadata,
-			   const cap_value_t caps, const cap_flag_value_t value)
+static void _change_cap(struct __test_metadata *const _metadata,
+			const cap_flag_t flag, const cap_value_t cap,
+			const cap_flag_value_t value)
 {
 	cap_t cap_p;
 
@@ -168,7 +180,7 @@ static void _effective_cap(struct __test_metadata *const _metadata,
 	{
 		TH_LOG("Failed to cap_get_proc: %s", strerror(errno));
 	}
-	EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value))
+	EXPECT_NE(-1, cap_set_flag(cap_p, flag, 1, &cap, value))
 	{
 		TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
 	}
@@ -183,15 +195,35 @@ static void _effective_cap(struct __test_metadata *const _metadata,
 }
 
 static void __maybe_unused set_cap(struct __test_metadata *const _metadata,
-				   const cap_value_t caps)
+				   const cap_value_t cap)
 {
-	_effective_cap(_metadata, caps, CAP_SET);
+	_change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_SET);
 }
 
 static void __maybe_unused clear_cap(struct __test_metadata *const _metadata,
-				     const cap_value_t caps)
+				     const cap_value_t cap)
+{
+	_change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_CLEAR);
+}
+
+static void __maybe_unused
+set_ambient_cap(struct __test_metadata *const _metadata, const cap_value_t cap)
+{
+	_change_cap(_metadata, CAP_INHERITABLE, cap, CAP_SET);
+
+	EXPECT_NE(-1, cap_set_ambient(cap, CAP_SET))
+	{
+		TH_LOG("Failed to set ambient capability %d: %s", cap,
+		       strerror(errno));
+	}
+}
+
+static void __maybe_unused clear_ambient_cap(
+	struct __test_metadata *const _metadata, const cap_value_t cap)
 {
-	_effective_cap(_metadata, caps, CAP_CLEAR);
+	EXPECT_EQ(1, cap_get_ambient(cap));
+	_change_cap(_metadata, CAP_INHERITABLE, cap, CAP_CLEAR);
+	EXPECT_EQ(0, cap_get_ambient(cap));
 }
 
 /* Receives an FD from a UNIX socket. Returns the received FD, or -errno. */
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index efcde123af1f2..936cfc879f1d2 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -107,8 +107,11 @@ static void setup_loopback(struct __test_metadata *const _metadata)
 {
 	set_cap(_metadata, CAP_SYS_ADMIN);
 	ASSERT_EQ(0, unshare(CLONE_NEWNET));
-	ASSERT_EQ(0, system("ip link set dev lo up"));
 	clear_cap(_metadata, CAP_SYS_ADMIN);
+
+	set_ambient_cap(_metadata, CAP_NET_ADMIN);
+	ASSERT_EQ(0, system("ip link set dev lo up"));
+	clear_ambient_cap(_metadata, CAP_NET_ADMIN);
 }
 
 static bool is_restricted(const struct protocol_variant *const prot,
-- 
GitLab


From 46eba193d04f8bd717e525eb4110f3c46c12aec3 Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Wed, 31 Jan 2024 10:08:28 +0800
Subject: [PATCH 3855/4076] net: stmmac: xgmac: fix handling of DPP safety
 error for DMA channels

Commit 56e58d6c8a56 ("net: stmmac: Implement Safety Features in
XGMAC core") checks and reports safety errors, but leaves the
Data Path Parity Errors for each channel in DMA unhandled at all, lead to
a storm of interrupt.
Fix it by checking and clearing the DMA_DPP_Interrupt_Status register.

Fixes: 56e58d6c8a56 ("net: stmmac: Implement Safety Features in XGMAC core")
Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  |  1 +
 .../net/ethernet/stmicro/stmmac/dwxgmac2.h    |  3 +
 .../ethernet/stmicro/stmmac/dwxgmac2_core.c   | 57 ++++++++++++++++++-
 3 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 721c1f8e892fc..b4f60ab078d67 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -216,6 +216,7 @@ struct stmmac_safety_stats {
 	unsigned long mac_errors[32];
 	unsigned long mtl_errors[32];
 	unsigned long dma_errors[32];
+	unsigned long dma_dpp_errors[32];
 };
 
 /* Number of fields in Safety Stats */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 207ff1799f2c7..5c67a3f89f088 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -303,6 +303,8 @@
 #define XGMAC_RXCEIE			BIT(4)
 #define XGMAC_TXCEIE			BIT(0)
 #define XGMAC_MTL_ECC_INT_STATUS	0x000010cc
+#define XGMAC_MTL_DPP_CONTROL		0x000010e0
+#define XGMAC_DDPP_DISABLE		BIT(0)
 #define XGMAC_MTL_TXQ_OPMODE(x)		(0x00001100 + (0x80 * (x)))
 #define XGMAC_TQS			GENMASK(25, 16)
 #define XGMAC_TQS_SHIFT			16
@@ -385,6 +387,7 @@
 #define XGMAC_DCEIE			BIT(1)
 #define XGMAC_TCEIE			BIT(0)
 #define XGMAC_DMA_ECC_INT_STATUS	0x0000306c
+#define XGMAC_DMA_DPP_INT_STATUS	0x00003074
 #define XGMAC_DMA_CH_CONTROL(x)		(0x00003100 + (0x80 * (x)))
 #define XGMAC_SPH			BIT(24)
 #define XGMAC_PBLx8			BIT(16)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index eb48211d9b0eb..04d7c4dc2e35f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -830,6 +830,43 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= {
 	{ false, "UNKNOWN", "Unknown Error" }, /* 31 */
 };
 
+static const char * const dpp_rx_err = "Read Rx Descriptor Parity checker Error";
+static const char * const dpp_tx_err = "Read Tx Descriptor Parity checker Error";
+static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = {
+	{ true, "TDPES0", dpp_tx_err },
+	{ true, "TDPES1", dpp_tx_err },
+	{ true, "TDPES2", dpp_tx_err },
+	{ true, "TDPES3", dpp_tx_err },
+	{ true, "TDPES4", dpp_tx_err },
+	{ true, "TDPES5", dpp_tx_err },
+	{ true, "TDPES6", dpp_tx_err },
+	{ true, "TDPES7", dpp_tx_err },
+	{ true, "TDPES8", dpp_tx_err },
+	{ true, "TDPES9", dpp_tx_err },
+	{ true, "TDPES10", dpp_tx_err },
+	{ true, "TDPES11", dpp_tx_err },
+	{ true, "TDPES12", dpp_tx_err },
+	{ true, "TDPES13", dpp_tx_err },
+	{ true, "TDPES14", dpp_tx_err },
+	{ true, "TDPES15", dpp_tx_err },
+	{ true, "RDPES0", dpp_rx_err },
+	{ true, "RDPES1", dpp_rx_err },
+	{ true, "RDPES2", dpp_rx_err },
+	{ true, "RDPES3", dpp_rx_err },
+	{ true, "RDPES4", dpp_rx_err },
+	{ true, "RDPES5", dpp_rx_err },
+	{ true, "RDPES6", dpp_rx_err },
+	{ true, "RDPES7", dpp_rx_err },
+	{ true, "RDPES8", dpp_rx_err },
+	{ true, "RDPES9", dpp_rx_err },
+	{ true, "RDPES10", dpp_rx_err },
+	{ true, "RDPES11", dpp_rx_err },
+	{ true, "RDPES12", dpp_rx_err },
+	{ true, "RDPES13", dpp_rx_err },
+	{ true, "RDPES14", dpp_rx_err },
+	{ true, "RDPES15", dpp_rx_err },
+};
+
 static void dwxgmac3_handle_dma_err(struct net_device *ndev,
 				    void __iomem *ioaddr, bool correctable,
 				    struct stmmac_safety_stats *stats)
@@ -841,6 +878,13 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev,
 
 	dwxgmac3_log_error(ndev, value, correctable, "DMA",
 			   dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats);
+
+	value = readl(ioaddr + XGMAC_DMA_DPP_INT_STATUS);
+	writel(value, ioaddr + XGMAC_DMA_DPP_INT_STATUS);
+
+	dwxgmac3_log_error(ndev, value, false, "DMA_DPP",
+			   dwxgmac3_dma_dpp_errors,
+			   STAT_OFF(dma_dpp_errors), stats);
 }
 
 static int
@@ -881,6 +925,12 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
 	value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */
 	writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL);
 
+	/* 5. Enable Data Path Parity Protection */
+	value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL);
+	/* already enabled by default, explicit enable it again */
+	value &= ~XGMAC_DDPP_DISABLE;
+	writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL);
+
 	return 0;
 }
 
@@ -914,7 +964,11 @@ static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev,
 		ret |= !corr;
 	}
 
-	err = dma & (XGMAC_DEUIS | XGMAC_DECIS);
+	/* DMA_DPP_Interrupt_Status is indicated by MCSIS bit in
+	 * DMA_Safety_Interrupt_Status, so we handle DMA Data Path
+	 * Parity Errors here
+	 */
+	err = dma & (XGMAC_DEUIS | XGMAC_DECIS | XGMAC_MCSIS);
 	corr = dma & XGMAC_DECIS;
 	if (err) {
 		dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats);
@@ -930,6 +984,7 @@ static const struct dwxgmac3_error {
 	{ dwxgmac3_mac_errors },
 	{ dwxgmac3_mtl_errors },
 	{ dwxgmac3_dma_errors },
+	{ dwxgmac3_dma_dpp_errors },
 };
 
 static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats,
-- 
GitLab


From ccb88e9549e7cfd8bcd511c538f437e20026e983 Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@amd.com>
Date: Thu, 25 Jan 2024 17:12:53 -0600
Subject: [PATCH 3856/4076] crypto: ccp - Fix null pointer dereference in
 __sev_platform_shutdown_locked

The SEV platform device can be shutdown with a null psp_master,
e.g., using DEBUG_TEST_DRIVER_REMOVE.  Found using KASAN:

[  137.148210] ccp 0000:23:00.1: enabling device (0000 -> 0002)
[  137.162647] ccp 0000:23:00.1: no command queues available
[  137.170598] ccp 0000:23:00.1: sev enabled
[  137.174645] ccp 0000:23:00.1: psp enabled
[  137.178890] general protection fault, probably for non-canonical address 0xdffffc000000001e: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN NOPTI
[  137.182693] KASAN: null-ptr-deref in range [0x00000000000000f0-0x00000000000000f7]
[  137.182693] CPU: 93 PID: 1 Comm: swapper/0 Not tainted 6.8.0-rc1+ #311
[  137.182693] RIP: 0010:__sev_platform_shutdown_locked+0x51/0x180
[  137.182693] Code: 08 80 3c 08 00 0f 85 0e 01 00 00 48 8b 1d 67 b6 01 08 48 b8 00 00 00 00 00 fc ff df 48 8d bb f0 00 00 00 48 89 f9 48 c1 e9 03 <80> 3c 01 00 0f 85 fe 00 00 00 48 8b 9b f0 00 00 00 48 85 db 74 2c
[  137.182693] RSP: 0018:ffffc900000cf9b0 EFLAGS: 00010216
[  137.182693] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 000000000000001e
[  137.182693] RDX: 0000000000000000 RSI: 0000000000000008 RDI: 00000000000000f0
[  137.182693] RBP: ffffc900000cf9c8 R08: 0000000000000000 R09: fffffbfff58f5a66
[  137.182693] R10: ffffc900000cf9c8 R11: ffffffffac7ad32f R12: ffff8881e5052c28
[  137.182693] R13: ffff8881e5052c28 R14: ffff8881758e43e8 R15: ffffffffac64abf8
[  137.182693] FS:  0000000000000000(0000) GS:ffff889de7000000(0000) knlGS:0000000000000000
[  137.182693] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  137.182693] CR2: 0000000000000000 CR3: 0000001cf7c7e000 CR4: 0000000000350ef0
[  137.182693] Call Trace:
[  137.182693]  <TASK>
[  137.182693]  ? show_regs+0x6c/0x80
[  137.182693]  ? __die_body+0x24/0x70
[  137.182693]  ? die_addr+0x4b/0x80
[  137.182693]  ? exc_general_protection+0x126/0x230
[  137.182693]  ? asm_exc_general_protection+0x2b/0x30
[  137.182693]  ? __sev_platform_shutdown_locked+0x51/0x180
[  137.182693]  sev_firmware_shutdown.isra.0+0x1e/0x80
[  137.182693]  sev_dev_destroy+0x49/0x100
[  137.182693]  psp_dev_destroy+0x47/0xb0
[  137.182693]  sp_destroy+0xbb/0x240
[  137.182693]  sp_pci_remove+0x45/0x60
[  137.182693]  pci_device_remove+0xaa/0x1d0
[  137.182693]  device_remove+0xc7/0x170
[  137.182693]  really_probe+0x374/0xbe0
[  137.182693]  ? srso_return_thunk+0x5/0x5f
[  137.182693]  __driver_probe_device+0x199/0x460
[  137.182693]  driver_probe_device+0x4e/0xd0
[  137.182693]  __driver_attach+0x191/0x3d0
[  137.182693]  ? __pfx___driver_attach+0x10/0x10
[  137.182693]  bus_for_each_dev+0x100/0x190
[  137.182693]  ? __pfx_bus_for_each_dev+0x10/0x10
[  137.182693]  ? __kasan_check_read+0x15/0x20
[  137.182693]  ? srso_return_thunk+0x5/0x5f
[  137.182693]  ? _raw_spin_unlock+0x27/0x50
[  137.182693]  driver_attach+0x41/0x60
[  137.182693]  bus_add_driver+0x2a8/0x580
[  137.182693]  driver_register+0x141/0x480
[  137.182693]  __pci_register_driver+0x1d6/0x2a0
[  137.182693]  ? srso_return_thunk+0x5/0x5f
[  137.182693]  ? esrt_sysfs_init+0x1cd/0x5d0
[  137.182693]  ? __pfx_sp_mod_init+0x10/0x10
[  137.182693]  sp_pci_init+0x22/0x30
[  137.182693]  sp_mod_init+0x14/0x30
[  137.182693]  ? __pfx_sp_mod_init+0x10/0x10
[  137.182693]  do_one_initcall+0xd1/0x470
[  137.182693]  ? __pfx_do_one_initcall+0x10/0x10
[  137.182693]  ? parameq+0x80/0xf0
[  137.182693]  ? srso_return_thunk+0x5/0x5f
[  137.182693]  ? __kmalloc+0x3b0/0x4e0
[  137.182693]  ? kernel_init_freeable+0x92d/0x1050
[  137.182693]  ? kasan_populate_vmalloc_pte+0x171/0x190
[  137.182693]  ? srso_return_thunk+0x5/0x5f
[  137.182693]  kernel_init_freeable+0xa64/0x1050
[  137.182693]  ? __pfx_kernel_init+0x10/0x10
[  137.182693]  kernel_init+0x24/0x160
[  137.182693]  ? __switch_to_asm+0x3e/0x70
[  137.182693]  ret_from_fork+0x40/0x80
[  137.182693]  ? __pfx_kernel_init+0x10/0x10
[  137.182693]  ret_from_fork_asm+0x1b/0x30
[  137.182693]  </TASK>
[  137.182693] Modules linked in:
[  137.538483] ---[ end trace 0000000000000000 ]---

Fixes: 1b05ece0c931 ("crypto: ccp - During shutdown, check SEV data pointer before using")
Cc: stable@vger.kernel.org
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Acked-by: John Allen <john.allen@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/sev-dev.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index e4d3f45242f63..b04bc1d3d627d 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -534,10 +534,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init);
 
 static int __sev_platform_shutdown_locked(int *error)
 {
-	struct sev_device *sev = psp_master->sev_data;
+	struct psp_device *psp = psp_master;
+	struct sev_device *sev;
 	int ret;
 
-	if (!sev || sev->state == SEV_STATE_UNINIT)
+	if (!psp || !psp->sev_data)
+		return 0;
+
+	sev = psp->sev_data;
+
+	if (sev->state == SEV_STATE_UNINIT)
 		return 0;
 
 	ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error);
-- 
GitLab


From 69fba378edcaffba7bc7d299fdee02e377069d30 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 29 Jan 2024 22:17:11 +0800
Subject: [PATCH 3857/4076] crypto: cbc - Ensure statesize is zero

The cbc template should not be applied on stream ciphers, especially
ones that have internal state.  Enforce this by checking the state
size when the instance is created.

Reported-by: syzbot+050eeedd6c285d8c42f2@syzkaller.appspotmail.com
Fixes: 47309ea13591 ("crypto: arc4 - Add internal state")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/cbc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/crypto/cbc.c b/crypto/cbc.c
index eedddef9ce40c..e81918ca68b78 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -148,6 +148,9 @@ static int crypto_cbc_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if (!is_power_of_2(inst->alg.co.base.cra_blocksize))
 		goto out_free_inst;
 
+	if (inst->alg.co.statesize)
+		goto out_free_inst;
+
 	inst->alg.encrypt = crypto_cbc_encrypt;
 	inst->alg.decrypt = crypto_cbc_decrypt;
 
-- 
GitLab


From 24c890dd712f6345e382256cae8c97abb0406b70 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 1 Feb 2024 13:49:09 +0800
Subject: [PATCH 3858/4076] crypto: algif_hash - Remove bogus SGL free on
 zero-length error path

When a zero-length message is hashed by algif_hash, and an error
is triggered, it tries to free an SG list that was never allocated
in the first place.  Fix this by not freeing the SG list on the
zero-length error path.

Reported-by: Shigeru Yoshida <syoshida@redhat.com>
Reported-by: xingwei lee <xrivendell7@gmail.com>
Fixes: b6d972f68983 ("crypto: af_alg/hash: Fix recvmsg() after sendmsg(MSG_MORE)")
Cc: <stable@vger.kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Reported-by: syzbot+3266db0c26d1fbbe3abb@syzkaller.appspotmail.com
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/algif_hash.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 82c44d4899b96..e24c829d7a015 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -91,13 +91,13 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg,
 		if (!(msg->msg_flags & MSG_MORE)) {
 			err = hash_alloc_result(sk, ctx);
 			if (err)
-				goto unlock_free;
+				goto unlock_free_result;
 			ahash_request_set_crypt(&ctx->req, NULL,
 						ctx->result, 0);
 			err = crypto_wait_req(crypto_ahash_final(&ctx->req),
 					      &ctx->wait);
 			if (err)
-				goto unlock_free;
+				goto unlock_free_result;
 		}
 		goto done_more;
 	}
@@ -170,6 +170,7 @@ unlock:
 
 unlock_free:
 	af_alg_free_sg(&ctx->sgl);
+unlock_free_result:
 	hash_free_result(sk, ctx);
 	ctx->more = false;
 	goto unlock;
-- 
GitLab


From 177fbbcb4ed6b306c1626a277fac3fb1c495a4c7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 13:14:13 +0100
Subject: [PATCH 3859/4076] wifi: cfg80211: detect stuck ECSA element in probe
 resp

We recently added some validation that we don't try to
connect to an AP that is currently in a channel switch
process, since that might want the channel to be quiet
or we might not be able to connect in time to hear the
switching in a beacon. This was in commit c09c4f31998b
("wifi: mac80211: don't connect to an AP while it's in
a CSA process").

However, we promptly got a report that this caused new
connection failures, and it turns out that the AP that
we now cannot connect to is permanently advertising an
extended channel switch announcement, even with quiet.
The AP in question was an Asus RT-AC53, with firmware
3.0.0.4.380_10760-g21a5898.

As a first step, attempt to detect that we're dealing
with such a situation, so mac80211 can use this later.

Reported-by: coldolt <andypalmadi@gmail.com>
Closes: https://lore.kernel.org/linux-wireless/CAJvGw+DQhBk_mHXeu6RTOds5iramMW2FbMB01VbKRA4YbHHDTA@mail.gmail.com/
Fixes: c09c4f31998b ("wifi: mac80211: don't connect to an AP while it's in a CSA process")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240129131413.246972c8775e.Ibf834d7f52f9951a353b6872383da710a7358338@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  4 +++
 net/wireless/scan.c    | 59 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cf79656ce09ca..2b54fdd8ca15a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2910,6 +2910,8 @@ struct cfg80211_bss_ies {
  *	own the beacon_ies, but they're just pointers to the ones from the
  *	@hidden_beacon_bss struct)
  * @proberesp_ies: the information elements from the last Probe Response frame
+ * @proberesp_ecsa_stuck: ECSA element is stuck in the Probe Response frame,
+ *	cannot rely on it having valid data
  * @hidden_beacon_bss: in case this BSS struct represents a probe response from
  *	a BSS that hides the SSID in its beacon, this points to the BSS struct
  *	that holds the beacon data. @beacon_ies is still valid, of course, and
@@ -2950,6 +2952,8 @@ struct cfg80211_bss {
 	u8 chains;
 	s8 chain_signal[IEEE80211_MAX_CHAINS];
 
+	u8 proberesp_ecsa_stuck:1;
+
 	u8 bssid_index;
 	u8 max_bssid_indicator;
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 2249b1a89d1c4..389a52c29bfc7 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1731,6 +1731,61 @@ static void cfg80211_update_hidden_bsses(struct cfg80211_internal_bss *known,
 	}
 }
 
+static void cfg80211_check_stuck_ecsa(struct cfg80211_registered_device *rdev,
+				      struct cfg80211_internal_bss *known,
+				      const struct cfg80211_bss_ies *old)
+{
+	const struct ieee80211_ext_chansw_ie *ecsa;
+	const struct element *elem_new, *elem_old;
+	const struct cfg80211_bss_ies *new, *bcn;
+
+	if (known->pub.proberesp_ecsa_stuck)
+		return;
+
+	new = rcu_dereference_protected(known->pub.proberesp_ies,
+					lockdep_is_held(&rdev->bss_lock));
+	if (WARN_ON(!new))
+		return;
+
+	if (new->tsf - old->tsf < USEC_PER_SEC)
+		return;
+
+	elem_old = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				      old->data, old->len);
+	if (!elem_old)
+		return;
+
+	elem_new = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				      new->data, new->len);
+	if (!elem_new)
+		return;
+
+	bcn = rcu_dereference_protected(known->pub.beacon_ies,
+					lockdep_is_held(&rdev->bss_lock));
+	if (bcn &&
+	    cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+			       bcn->data, bcn->len))
+		return;
+
+	if (elem_new->datalen != elem_old->datalen)
+		return;
+	if (elem_new->datalen < sizeof(struct ieee80211_ext_chansw_ie))
+		return;
+	if (memcmp(elem_new->data, elem_old->data, elem_new->datalen))
+		return;
+
+	ecsa = (void *)elem_new->data;
+
+	if (!ecsa->mode)
+		return;
+
+	if (ecsa->new_ch_num !=
+	    ieee80211_frequency_to_channel(known->pub.channel->center_freq))
+		return;
+
+	known->pub.proberesp_ecsa_stuck = 1;
+}
+
 static bool
 cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 			  struct cfg80211_internal_bss *known,
@@ -1750,8 +1805,10 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 		/* Override possible earlier Beacon frame IEs */
 		rcu_assign_pointer(known->pub.ies,
 				   new->pub.proberesp_ies);
-		if (old)
+		if (old) {
+			cfg80211_check_stuck_ecsa(rdev, known, old);
 			kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head);
+		}
 	}
 
 	if (rcu_access_pointer(new->pub.beacon_ies)) {
-- 
GitLab


From 35e2385dbe787936c793d70755a5177d267a40aa Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 13:14:14 +0100
Subject: [PATCH 3860/4076] wifi: mac80211: improve CSA/ECSA connection refusal

As mentioned in the previous commit, we pretty quickly found
that some APs have ECSA elements stuck in their probe response,
so using that to not attempt to connect while CSA is happening
we never connect to such an AP.

Improve this situation by checking more carefully and ignoring
the ECSA if cfg80211 has previously detected the ECSA element
being stuck in the probe response.

Additionally, allow connecting to an AP that's switching to a
channel it's already using, unless it's using quiet mode. In
this case, we may just have to adjust bandwidth later. If it's
actually switching channels, it's better not to try to connect
in the middle of that.

Reported-by: coldolt <andypalmadi@gmail.com>
Closes: https://lore.kernel.org/linux-wireless/CAJvGw+DQhBk_mHXeu6RTOds5iramMW2FbMB01VbKRA4YbHHDTA@mail.gmail.com/
Fixes: c09c4f31998b ("wifi: mac80211: don't connect to an AP while it's in a CSA process")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240129131413.cc2d0a26226e.I682c016af76e35b6c47007db50e8554c5a426910@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 103 ++++++++++++++++++++++++++++++++------------
 1 file changed, 76 insertions(+), 27 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 073105deb4248..c62c7c6ce91fe 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7309,6 +7309,75 @@ out_err:
 	return err;
 }
 
+static bool ieee80211_mgd_csa_present(struct ieee80211_sub_if_data *sdata,
+				      const struct cfg80211_bss_ies *ies,
+				      u8 cur_channel, bool ignore_ecsa)
+{
+	const struct element *csa_elem, *ecsa_elem;
+	struct ieee80211_channel_sw_ie *csa = NULL;
+	struct ieee80211_ext_chansw_ie *ecsa = NULL;
+
+	if (!ies)
+		return false;
+
+	csa_elem = cfg80211_find_elem(WLAN_EID_CHANNEL_SWITCH,
+				      ies->data, ies->len);
+	if (csa_elem && csa_elem->datalen == sizeof(*csa))
+		csa = (void *)csa_elem->data;
+
+	ecsa_elem = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				       ies->data, ies->len);
+	if (ecsa_elem && ecsa_elem->datalen == sizeof(*ecsa))
+		ecsa = (void *)ecsa_elem->data;
+
+	if (csa && csa->count == 0)
+		csa = NULL;
+	if (csa && !csa->mode && csa->new_ch_num == cur_channel)
+		csa = NULL;
+
+	if (ecsa && ecsa->count == 0)
+		ecsa = NULL;
+	if (ecsa && !ecsa->mode && ecsa->new_ch_num == cur_channel)
+		ecsa = NULL;
+
+	if (ignore_ecsa && ecsa) {
+		sdata_info(sdata,
+			   "Ignoring ECSA in probe response - was considered stuck!\n");
+		return csa;
+	}
+
+	return csa || ecsa;
+}
+
+static bool ieee80211_mgd_csa_in_process(struct ieee80211_sub_if_data *sdata,
+					 struct cfg80211_bss *bss)
+{
+	u8 cur_channel;
+	bool ret;
+
+	cur_channel = ieee80211_frequency_to_channel(bss->channel->center_freq);
+
+	rcu_read_lock();
+	if (ieee80211_mgd_csa_present(sdata,
+				      rcu_dereference(bss->beacon_ies),
+				      cur_channel, false)) {
+		ret = true;
+		goto out;
+	}
+
+	if (ieee80211_mgd_csa_present(sdata,
+				      rcu_dereference(bss->proberesp_ies),
+				      cur_channel, bss->proberesp_ecsa_stuck)) {
+		ret = true;
+		goto out;
+	}
+
+	ret = false;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
 /* config hooks */
 int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 		       struct cfg80211_auth_request *req)
@@ -7317,7 +7386,6 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_mgd_auth_data *auth_data;
 	struct ieee80211_link_data *link;
-	const struct element *csa_elem, *ecsa_elem;
 	u16 auth_alg;
 	int err;
 	bool cont_auth;
@@ -7360,21 +7428,10 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 	if (ifmgd->assoc_data)
 		return -EBUSY;
 
-	rcu_read_lock();
-	csa_elem = ieee80211_bss_get_elem(req->bss, WLAN_EID_CHANNEL_SWITCH);
-	ecsa_elem = ieee80211_bss_get_elem(req->bss,
-					   WLAN_EID_EXT_CHANSWITCH_ANN);
-	if ((csa_elem &&
-	     csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) &&
-	     ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) ||
-	    (ecsa_elem &&
-	     ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) &&
-	     ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) {
-		rcu_read_unlock();
+	if (ieee80211_mgd_csa_in_process(sdata, req->bss)) {
 		sdata_info(sdata, "AP is in CSA process, reject auth\n");
 		return -EINVAL;
 	}
-	rcu_read_unlock();
 
 	auth_data = kzalloc(sizeof(*auth_data) + req->auth_data_len +
 			    req->ie_len, GFP_KERNEL);
@@ -7684,7 +7741,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_mgd_assoc_data *assoc_data;
-	const struct element *ssid_elem, *csa_elem, *ecsa_elem;
+	const struct element *ssid_elem;
 	struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg;
 	ieee80211_conn_flags_t conn_flags = 0;
 	struct ieee80211_link_data *link;
@@ -7707,23 +7764,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 	cbss = req->link_id < 0 ? req->bss : req->links[req->link_id].bss;
 
-	rcu_read_lock();
-	ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID);
-	if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) {
-		rcu_read_unlock();
+	if (ieee80211_mgd_csa_in_process(sdata, cbss)) {
+		sdata_info(sdata, "AP is in CSA process, reject assoc\n");
 		kfree(assoc_data);
 		return -EINVAL;
 	}
 
-	csa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_CHANNEL_SWITCH);
-	ecsa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_EXT_CHANSWITCH_ANN);
-	if ((csa_elem &&
-	     csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) &&
-	     ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) ||
-	    (ecsa_elem &&
-	     ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) &&
-	     ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) {
-		sdata_info(sdata, "AP is in CSA process, reject assoc\n");
+	rcu_read_lock();
+	ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID);
+	if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) {
 		rcu_read_unlock();
 		kfree(assoc_data);
 		return -EINVAL;
-- 
GitLab


From 9480adfe4e0f0319b9da04b44e4eebd5ad07e0cd Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 15:53:48 +0100
Subject: [PATCH 3861/4076] wifi: mac80211: fix RCU use in TDLS fast-xmit

This looks up the link under RCU protection, but isn't
guaranteed to actually have protection. Fix that.

Fixes: 8cc07265b691 ("wifi: mac80211: handle TDLS data frames with MLO")
Link: https://msgid.link/20240129155348.8a9c0b1e1d89.I553f96ce953bb41b0b877d592056164dec20d01c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/tx.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 68a48abc72876..e448ab3384489 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3100,10 +3100,11 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
 			/* DA SA BSSID */
 			build.da_offs = offsetof(struct ieee80211_hdr, addr1);
 			build.sa_offs = offsetof(struct ieee80211_hdr, addr2);
+			rcu_read_lock();
 			link = rcu_dereference(sdata->link[tdls_link_id]);
-			if (WARN_ON_ONCE(!link))
-				break;
-			memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
+			if (!WARN_ON_ONCE(!link))
+				memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
+			rcu_read_unlock();
 			build.hdr_len = 24;
 			break;
 		}
-- 
GitLab


From dd6c064cfc3fc18d871107c6f5db8837e88572e4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 15:53:55 +0100
Subject: [PATCH 3862/4076] wifi: mac80211: set station RX-NSS on reconfig

When a station is added/reconfigured by userspace, e.g. a TDLS
peer or a SoftAP client STA, rx_nss is currently not always set,
so that it might be left zero. Set it up properly.

Link: https://msgid.link/20240129155354.98f148a3d654.I193a02155f557ea54dc9d0232da66cf96734119a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 489dd97f51724..321698012e122 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1869,6 +1869,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local,
 					      sband->band);
 	}
 
+	ieee80211_sta_set_rx_nss(link_sta);
+
 	return ret;
 }
 
-- 
GitLab


From 733c498a80853acbafe284a40468b91f4d41f0b4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 15:54:02 +0100
Subject: [PATCH 3863/4076] wifi: mac80211: fix driver debugfs for vif type
 change

If a driver implements the change_interface() method, we switch
interface type without taking the interface down, but still will
recreate the debugfs for it since it's a new type. As such, we
should use the ieee80211_debugfs_recreate_netdev() function here
to also recreate the driver's files, if it is indeed from a type
change while up.

Link: https://msgid.link/20240129155402.7311a36ffeeb.I18df02bbeb685d4250911de5ffbaf090f60c3803@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/debugfs_netdev.c | 4 ++--
 net/mac80211/debugfs_netdev.h | 5 -----
 net/mac80211/iface.c          | 2 +-
 3 files changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index dce5606ed66da..68596ef78b15e 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -997,8 +997,8 @@ static void add_link_files(struct ieee80211_link_data *link,
 	}
 }
 
-void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
-				  bool mld_vif)
+static void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
+					 bool mld_vif)
 {
 	char buf[10+IFNAMSIZ];
 
diff --git a/net/mac80211/debugfs_netdev.h b/net/mac80211/debugfs_netdev.h
index b226b1aae88a5..a02ec0a413f61 100644
--- a/net/mac80211/debugfs_netdev.h
+++ b/net/mac80211/debugfs_netdev.h
@@ -11,8 +11,6 @@
 #include "ieee80211_i.h"
 
 #ifdef CONFIG_MAC80211_DEBUGFS
-void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
-				  bool mld_vif);
 void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata);
 void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata);
 void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata,
@@ -24,9 +22,6 @@ void ieee80211_link_debugfs_remove(struct ieee80211_link_data *link);
 void ieee80211_link_debugfs_drv_add(struct ieee80211_link_data *link);
 void ieee80211_link_debugfs_drv_remove(struct ieee80211_link_data *link);
 #else
-static inline void ieee80211_debugfs_add_netdev(
-	struct ieee80211_sub_if_data *sdata, bool mld_vif)
-{}
 static inline void ieee80211_debugfs_remove_netdev(
 	struct ieee80211_sub_if_data *sdata)
 {}
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index e4e7c0b38cb6e..11c4caa4748e4 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1783,7 +1783,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	/* need to do this after the switch so vif.type is correct */
 	ieee80211_link_setup(&sdata->deflink);
 
-	ieee80211_debugfs_add_netdev(sdata, false);
+	ieee80211_debugfs_recreate_netdev(sdata, false);
 }
 
 static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
-- 
GitLab


From 86b2dac224f963be92634a878888222e1e938f48 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 19:54:05 +0100
Subject: [PATCH 3864/4076] wifi: mac80211: initialize SMPS mode correctly

The SMPS mode is currently re-initialized too late, since
ieee80211_prep_channel() can be called again after we've
already done ieee80211_setup_assoc_link(), in case there's
some override of the channel configuration. Fix this.

Link: https://msgid.link/20240129195405.d6d74508be18.I0a7303b1ce4d8e5436011951ab624372a445c069@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index c62c7c6ce91fe..f1cdd2df323e7 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8,7 +8,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2023 Intel Corporation
+ * Copyright (C) 2018 - 2024 Intel Corporation
  */
 
 #include <linux/delay.h>
@@ -2918,6 +2918,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	/* other links will be destroyed */
 	sdata->deflink.u.mgd.bss = NULL;
+	sdata->deflink.smps_mode = IEEE80211_SMPS_OFF;
 
 	netif_carrier_off(sdata->dev);
 
@@ -5045,9 +5046,6 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	if (!link)
 		return 0;
 
-	/* will change later if needed */
-	link->smps_mode = IEEE80211_SMPS_OFF;
-
 	/*
 	 * If this fails (possibly due to channel context sharing
 	 * on incompatible channels, e.g. 80+80 and 160 sharing the
@@ -7096,6 +7094,7 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link)
 	link->u.mgd.p2p_noa_index = -1;
 	link->u.mgd.conn_flags = 0;
 	link->conf->bssid = link->u.mgd.bssid;
+	link->smps_mode = IEEE80211_SMPS_OFF;
 
 	wiphy_work_init(&link->u.mgd.request_smps_work,
 			ieee80211_request_smps_mgd_work);
-- 
GitLab


From 178e9d6adc4356c2f1659f575ecea626e7fbd05a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 19:57:30 +0100
Subject: [PATCH 3865/4076] wifi: mac80211: fix unsolicited broadcast probe
 config

There's a bug in ieee80211_set_unsol_bcast_probe_resp(), it tries
to return BSS_CHANGED_UNSOL_BCAST_PROBE_RESP (which has the value
1<<31) in an int, which makes it negative and considered an error.
Fix this by passing the changed flags to set separately.

Fixes: 3b1c256eb4ae ("wifi: mac80211: fixes in FILS discovery updates")
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://msgid.link/20240129195729.965b0740bf80.I6bc6f5236863f686c17d689be541b1dd2633c417@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 321698012e122..327682995c926 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #include <linux/ieee80211.h>
@@ -987,7 +987,8 @@ static int
 ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
 				     struct cfg80211_unsol_bcast_probe_resp *params,
 				     struct ieee80211_link_data *link,
-				     struct ieee80211_bss_conf *link_conf)
+				     struct ieee80211_bss_conf *link_conf,
+				     u64 *changed)
 {
 	struct unsol_bcast_probe_resp_data *new, *old = NULL;
 
@@ -1011,7 +1012,8 @@ ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
 		RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL);
 	}
 
-	return BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+	*changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+	return 0;
 }
 
 static int ieee80211_set_ftm_responder_params(
@@ -1450,10 +1452,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 
 	err = ieee80211_set_unsol_bcast_probe_resp(sdata,
 						   &params->unsol_bcast_probe_resp,
-						   link, link_conf);
+						   link, link_conf, &changed);
 	if (err < 0)
 		goto error;
-	changed |= err;
 
 	err = drv_start_ap(sdata->local, sdata, link_conf);
 	if (err) {
@@ -1525,10 +1526,9 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
 
 	err = ieee80211_set_unsol_bcast_probe_resp(sdata,
 						   &params->unsol_bcast_probe_resp,
-						   link, link_conf);
+						   link, link_conf, &changed);
 	if (err < 0)
 		return err;
-	changed |= err;
 
 	if (beacon->he_bss_color_valid &&
 	    beacon->he_bss_color.enabled != link_conf->he_bss_color.enabled) {
-- 
GitLab


From a0b4f2291319c5d47ecb196b90400814fdcfd126 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 31 Jan 2024 16:48:56 +0100
Subject: [PATCH 3866/4076] wifi: mac80211: fix waiting for beacons logic

This should be waiting if we don't have a beacon yet,
but somehow I managed to invert the logic. Fix that.

Fixes: 74e1309acedc ("wifi: mac80211: mlme: look up beacon elems only if needed")
Link: https://msgid.link/20240131164856.922701229546.I239b379e7cee04608e73c016b737a5245e5b23dd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f1cdd2df323e7..12f67871af698 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8046,8 +8046,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 		rcu_read_lock();
 		beacon_ies = rcu_dereference(req->bss->beacon_ies);
-
-		if (beacon_ies) {
+		if (!beacon_ies) {
 			/*
 			 * Wait up to one beacon interval ...
 			 * should this be more if we miss one?
-- 
GitLab


From c042600c17d8c490279f0ae2baee29475fe8047d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 31 Jan 2024 16:48:23 +0100
Subject: [PATCH 3867/4076] wifi: mac80211: adding missing
 drv_mgd_complete_tx() call

There's a call to drv_mgd_prepare_tx() and so there should
be one to drv_mgd_complete_tx(), but on this path it's not.
Add it.

Link: https://msgid.link/20240131164824.2f0922a514e1.I5aac89b93bcead88c374187d70cad0599d29d2c8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 12f67871af698..2022a26eb8811 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8127,6 +8127,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
 					    req->reason_code, false);
+		drv_mgd_complete_tx(sdata->local, sdata, &info);
 		return 0;
 	}
 
-- 
GitLab


From 62a6183c13319e4d2227473a04abd104c4f56dcf Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 20:09:07 +0100
Subject: [PATCH 3868/4076] wifi: mac80211: accept broadcast probe responses on
 6 GHz

On the 6 GHz band, probe responses are sent as broadcast to
optimise medium usage. However, without OCE configuration
we weren't accepting them, which is wrong, even if wpa_s is
by default enabling OCE. Accept them without the OCE config
as well.

Link: https://msgid.link/20240129200907.5a89c2821897.I92e9dfa0f9b350bc7f37dd4bb38031d156d78d8a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/scan.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 645355e5f1bc7..f9d5842601fa9 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright 2016-2017  Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #include <linux/if_arp.h>
@@ -237,14 +237,18 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 }
 
 static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata,
+					struct ieee80211_channel *channel,
 					u32 scan_flags, const u8 *da)
 {
 	if (!sdata)
 		return false;
-	/* accept broadcast for OCE */
-	if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP &&
-	    is_broadcast_ether_addr(da))
+
+	/* accept broadcast on 6 GHz and for OCE */
+	if (is_broadcast_ether_addr(da) &&
+	    (channel->band == NL80211_BAND_6GHZ ||
+	     scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP))
 		return true;
+
 	if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
 		return true;
 	return ether_addr_equal(da, sdata->vif.addr);
@@ -293,6 +297,12 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0);
 	}
 
+	channel = ieee80211_get_channel_khz(local->hw.wiphy,
+					    ieee80211_rx_status_to_khz(rx_status));
+
+	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
+		return;
+
 	if (ieee80211_is_probe_resp(mgmt->frame_control)) {
 		struct cfg80211_scan_request *scan_req;
 		struct cfg80211_sched_scan_request *sched_scan_req;
@@ -310,19 +320,15 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		/* ignore ProbeResp to foreign address or non-bcast (OCE)
 		 * unless scanning with randomised address
 		 */
-		if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags,
+		if (!ieee80211_scan_accept_presp(sdata1, channel,
+						 scan_req_flags,
 						 mgmt->da) &&
-		    !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags,
+		    !ieee80211_scan_accept_presp(sdata2, channel,
+						 sched_scan_req_flags,
 						 mgmt->da))
 			return;
 	}
 
-	channel = ieee80211_get_channel_khz(local->hw.wiphy,
-					ieee80211_rx_status_to_khz(rx_status));
-
-	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
-		return;
-
 	bss = ieee80211_bss_info_update(local, rx_status,
 					mgmt, skb->len,
 					channel);
-- 
GitLab


From fe92f874f09145a6951deacaa4961390238bbe0d Mon Sep 17 00:00:00 2001
From: Michael Lass <bevan@bi-co.net>
Date: Wed, 31 Jan 2024 16:52:20 +0100
Subject: [PATCH 3869/4076] net: Fix from address in memcpy_to_iter_csum()

While inlining csum_and_memcpy() into memcpy_to_iter_csum(), the from
address passed to csum_partial_copy_nocheck() was accidentally changed.
This causes a regression in applications using UDP, as for example
OpenAFS, causing loss of datagrams.

Fixes: dc32bff195b4 ("iov_iter, net: Fold in csum_and_memcpy()")
Cc: David Howells <dhowells@redhat.com>
Cc: stable@vger.kernel.org
Cc: regressions@lists.linux.dev
Signed-off-by: Michael Lass <bevan@bi-co.net>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 103d46fa0eeb3..a8b625abe242c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -751,7 +751,7 @@ size_t memcpy_to_iter_csum(void *iter_to, size_t progress,
 			   size_t len, void *from, void *priv2)
 {
 	__wsum *csum = priv2;
-	__wsum next = csum_partial_copy_nocheck(from, iter_to, len);
+	__wsum next = csum_partial_copy_nocheck(from + progress, iter_to, len);
 
 	*csum = csum_block_add(*csum, next, progress);
 	return 0;
-- 
GitLab


From 1fa942f31665ea5dc5d4d95893dd13723eaa97cc Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 28 Jan 2024 08:53:57 +0200
Subject: [PATCH 3870/4076] wifi: iwlwifi: mvm: fix a battery life regression

Fix the DBG_CONFIG_TOKEN to not enable debug components that would
prevent the device to save power.

Fixes: fc2fe0a5e856 ("wifi: iwlwifi: fw: disable firmware debug asserts")
Cc: stable@vger.kernel.org
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Eilon Rinat <eilon.rinat@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240128084842.90d2600edc27.Id657ea2f0ddb131f5f9d0ac39aeb8c88754fe54b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/debug.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index 798731ecbefde..b740c65a7dca2 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -537,7 +537,7 @@ enum iwl_fw_dbg_config_cmd_type {
 }; /* LDBG_CFG_CMD_TYPE_API_E_VER_1 */
 
 /* this token disables debug asserts in the firmware */
-#define IWL_FW_DBG_CONFIG_TOKEN 0x00011301
+#define IWL_FW_DBG_CONFIG_TOKEN 0x00010001
 
 /**
  * struct iwl_fw_dbg_config_cmd - configure FW debug
-- 
GitLab


From 16867c38bcd3be2eb9016a3198a096f93959086e Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 1 Feb 2024 16:17:39 +0200
Subject: [PATCH 3871/4076] wifi: iwlwifi: exit eSR only after the FW does

Currently the driver exits eSR by calling
iwl_mvm_esr_mode_inactive() before updating the FW
(by deactivating one of the links), and therefore before
sending the EML frame notifying that we are no longer in eSR.

This is wrong for several reasons:
1. The driver sends SMPS activation frames when we are still in eSR
   and SMPS should be disabled when in eSR
2. The driver restores RLC configuration as it was before eSR
   entering, and RLC command shouldn't be sent in eSR

Fix this by calling iwl_mvm_esr_mode_inactive() after FW update

Fixes: 12bacfc2c065 ("wifi: iwlwifi: handle eSR transitions")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://msgid.link/20240201155157.d8d9dc277d4e.Ib5aee0fd05e35b1da7f18753eb3c8fa0a3f872f3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 1f36e934ef69e..893b69fc841b8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -438,6 +438,9 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm,
 		mvmvif->ap_ibss_active = false;
 	}
 
+	iwl_mvm_link_changed(mvm, vif, link_conf,
+			     LINK_CONTEXT_MODIFY_ACTIVE, false);
+
 	if (iwl_mvm_is_esr_supported(mvm->fwrt.trans) && n_active > 1) {
 		int ret = iwl_mvm_esr_mode_inactive(mvm, vif);
 
@@ -449,9 +452,6 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm,
 	if (vif->type == NL80211_IFTYPE_MONITOR)
 		iwl_mvm_mld_rm_snif_sta(mvm, vif);
 
-	iwl_mvm_link_changed(mvm, vif, link_conf,
-			     LINK_CONTEXT_MODIFY_ACTIVE, false);
-
 	if (switching_chanctx)
 		return;
 	mvmvif->link[link_id]->phy_ctxt = NULL;
-- 
GitLab


From a23c0af103e184bb1252dddddda040f6641bea7b Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Thu, 1 Feb 2024 16:17:30 +0200
Subject: [PATCH 3872/4076] wifi: iwlwifi: do not announce EPCS support

mac80211 does not have proper support for EPCS currently as that would
require changing the ECDA parameters if EPCS (Emergency Preparedness
Communications Service) is in use. As such, do not announce support for
it in the capabilities.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240201155157.59d71656addc.Idde91b3018239c49fc6ed231b411d05354fb9fb1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 4028969886869..2f6774ec37b22 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -668,7 +668,6 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
 			.has_eht = true,
 			.eht_cap_elem = {
 				.mac_cap_info[0] =
-					IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
 					IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 |
@@ -793,7 +792,6 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
 			.has_eht = true,
 			.eht_cap_elem = {
 				.mac_cap_info[0] =
-					IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
 					IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2,
@@ -1020,8 +1018,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 	if (CSR_HW_REV_TYPE(trans->hw_rev) == IWL_CFG_MAC_TYPE_GL &&
 	    iftype_data->eht_cap.has_eht) {
 		iftype_data->eht_cap.eht_cap_elem.mac_cap_info[0] &=
-			~(IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
-			  IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
+			~(IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 			  IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2);
 		iftype_data->eht_cap.eht_cap_elem.phy_cap_info[3] &=
 			~(IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO |
-- 
GitLab


From bd6081be2251c3700eca8a7bbe071e1bb8cd2af4 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Tue, 30 Jan 2024 22:02:16 +0530
Subject: [PATCH 3873/4076] dmaengine: at_hdmac: add missing kernel-doc style
 description

We get following warning with W=1:

drivers/dma/at_hdmac.c:243: warning: Function parameter or struct member 'boundary' not described in 'at_desc'
drivers/dma/at_hdmac.c:243: warning: Function parameter or struct member 'dst_hole' not described in 'at_desc'
drivers/dma/at_hdmac.c:243: warning: Function parameter or struct member 'src_hole' not described in 'at_desc'
drivers/dma/at_hdmac.c:243: warning: Function parameter or struct member 'memset_buffer' not described in 'at_desc'
drivers/dma/at_hdmac.c:243: warning: Function parameter or struct member 'memset_paddr' not described in 'at_desc'
drivers/dma/at_hdmac.c:243: warning: Function parameter or struct member 'memset_vaddr' not described in 'at_desc'
drivers/dma/at_hdmac.c:255: warning: Enum value 'ATC_IS_PAUSED' not described in enum 'atc_status'
drivers/dma/at_hdmac.c:255: warning: Enum value 'ATC_IS_CYCLIC' not described in enum 'atc_status'
drivers/dma/at_hdmac.c:287: warning: Function parameter or struct member 'cyclic' not described in 'at_dma_chan'
drivers/dma/at_hdmac.c:350: warning: Function parameter or struct member 'memset_pool' not described in 'at_dma'

Fix this by adding the required description and also drop unused struct
member 'cyclic' in 'at_dma_chan'

Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20240130163216.633034-1-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/at_hdmac.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 6bad536e04924..40052d1bd0b5c 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -224,6 +224,12 @@ struct atdma_sg {
  * @total_len: total transaction byte count
  * @sglen: number of sg entries.
  * @sg: array of sgs.
+ * @boundary: number of transfers to perform before the automatic address increment operation
+ * @dst_hole: value to add to the destination address when the boundary has been reached
+ * @src_hole: value to add to the source address when the boundary has been reached
+ * @memset_buffer: buffer used for the memset operation
+ * @memset_paddr: physical address of the buffer used for the memset operation
+ * @memset_vaddr: virtual address of the buffer used for the memset operation
  */
 struct at_desc {
 	struct				virt_dma_desc vd;
@@ -247,6 +253,9 @@ struct at_desc {
 /**
  * enum atc_status - information bits stored in channel status flag
  *
+ * @ATC_IS_PAUSED: If channel is pauses
+ * @ATC_IS_CYCLIC: If channel is cyclic
+ *
  * Manipulated with atomic operations.
  */
 enum atc_status {
@@ -282,7 +291,6 @@ struct at_dma_chan {
 	u32			save_cfg;
 	u32			save_dscr;
 	struct dma_slave_config	dma_sconfig;
-	bool			cyclic;
 	struct at_desc		*desc;
 };
 
@@ -333,6 +341,7 @@ static inline u8 convert_buswidth(enum dma_slave_buswidth addr_width)
  * @save_imr: interrupt mask register that is saved on suspend/resume cycle
  * @all_chan_mask: all channels availlable in a mask
  * @lli_pool: hw lli table
+ * @memset_pool: hw memset pool
  * @chan: channels table to store at_dma_chan structures
  */
 struct at_dma {
-- 
GitLab


From e9f1e6bb55bea4f8cb48f8f7443bbac99b60d285 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 2 Feb 2024 17:11:25 +0100
Subject: [PATCH 3874/4076] Revert "gfs2: Use GL_NOBLOCK flag for non-blocking
 lookups"

Commit "gfs2: Use GL_NOBLOCK flag for non-blocking lookups" has several
issues, some of which are non-trivial to fix, so revert it for now:

  https://lore.kernel.org/gfs2/20240202050230.GA875515@ZenIV/T/

This reverts commit dd00aaeb343255a8a30de671bd27bde79a47c8e5.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/dentry.c | 23 +++++++++--------------
 fs/gfs2/inode.c  |  8 ++++----
 2 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 177f1f41f2254..2e215e8c3c88e 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -32,25 +32,21 @@
 
 static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *parent = NULL;
+	struct dentry *parent;
 	struct gfs2_sbd *sdp;
 	struct gfs2_inode *dip;
-	struct inode *dinode, *inode;
+	struct inode *inode;
 	struct gfs2_holder d_gh;
 	struct gfs2_inode *ip = NULL;
 	int error, valid = 0;
 	int had_lock = 0;
 
-	if (flags & LOOKUP_RCU) {
-		dinode = d_inode_rcu(READ_ONCE(dentry->d_parent));
-		if (!dinode)
-			return -ECHILD;
-	} else {
-		parent = dget_parent(dentry);
-		dinode = d_inode(parent);
-	}
-	sdp = GFS2_SB(dinode);
-	dip = GFS2_I(dinode);
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	parent = dget_parent(dentry);
+	sdp = GFS2_SB(d_inode(parent));
+	dip = GFS2_I(d_inode(parent));
 	inode = d_inode(dentry);
 
 	if (inode) {
@@ -66,8 +62,7 @@ static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 
 	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
 	if (!had_lock) {
-		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED,
-					   flags & LOOKUP_RCU ? GL_NOBLOCK : 0, &d_gh);
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
 		if (error)
 			goto out;
 	}
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6bfc9383b7b8e..1b95db2c3aac3 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1882,10 +1882,10 @@ int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode,
 		WARN_ON_ONCE(!may_not_block);
 		return -ECHILD;
         }
-	if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
-		int noblock = may_not_block ? GL_NOBLOCK : 0;
-		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_ANY | noblock, &i_gh);
+	if (gfs2_glock_is_locked_by_me(gl) == NULL) {
+		if (may_not_block)
+			return -ECHILD;
+		error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
 		if (error)
 			return error;
 	}
-- 
GitLab


From 5bdda0048c8d1bbe2019513b2d6200cc0d09c7bd Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 26 Jan 2024 14:31:53 -0800
Subject: [PATCH 3875/4076] wifi: brcmfmac: Adjust n_channels usage for
 __counted_by

After commit e3eac9f32ec0 ("wifi: cfg80211: Annotate struct
cfg80211_scan_request with __counted_by"), the compiler may enforce
dynamic array indexing of req->channels to stay below n_channels. As a
result, n_channels needs to be increased _before_ accessing the newly
added array index. Increment it first, then use "i" for the prior index.
Solves this warning in the coming GCC that has __counted_by support:

../drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c: In function 'brcmf_internal_escan_add_info':
../drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c:3783:46: warning: operation on 'req->
n_channels' may be undefined [-Wsequence-point]
 3783 |                 req->channels[req->n_channels++] = chan;
      |                               ~~~~~~~~~~~~~~~^~

Fixes: e3eac9f32ec0 ("wifi: cfg80211: Annotate struct cfg80211_scan_request with __counted_by")
Cc: Arend van Spriel <aspriel@gmail.com>
Cc: Franky Lin <franky.lin@broadcom.com>
Cc: Hante Meuleman <hante.meuleman@broadcom.com>
Cc: Kalle Valo <kvalo@kernel.org>
Cc: Chi-hsien Lin <chi-hsien.lin@infineon.com>
Cc: Ian Lin <ian.lin@infineon.com>
Cc: Johannes Berg <johannes.berg@intel.com>
Cc: Wright Feng <wright.feng@cypress.com>
Cc: Hector Martin <marcan@marcan.st>
Cc: linux-wireless@vger.kernel.org
Cc: brcm80211-dev-list.pdl@broadcom.com
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240126223150.work.548-kees@kernel.org
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 133c5ea6429cd..28d6a30cc0106 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -3779,8 +3779,10 @@ static int brcmf_internal_escan_add_info(struct cfg80211_scan_request *req,
 		if (req->channels[i] == chan)
 			break;
 	}
-	if (i == req->n_channels)
-		req->channels[req->n_channels++] = chan;
+	if (i == req->n_channels) {
+		req->n_channels++;
+		req->channels[i] = chan;
+	}
 
 	for (i = 0; i < req->n_ssids; i++) {
 		if (req->ssids[i].ssid_len == ssid_len &&
-- 
GitLab


From 0a9bab391e336489169b95cb0d4553d921302189 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Wed, 31 Jan 2024 21:57:27 +0100
Subject: [PATCH 3876/4076] dm-crypt, dm-verity: disable tasklets

Tasklets have an inherent problem with memory corruption. The function
tasklet_action_common calls tasklet_trylock, then it calls the tasklet
callback and then it calls tasklet_unlock. If the tasklet callback frees
the structure that contains the tasklet or if it calls some code that may
free it, tasklet_unlock will write into free memory.

The commits 8e14f610159d and d9a02e016aaf try to fix it for dm-crypt, but
it is not a sufficient fix and the data corruption can still happen [1].
There is no fix for dm-verity and dm-verity will write into free memory
with every tasklet-processed bio.

There will be atomic workqueues implemented in the kernel 6.9 [2]. They
will have better interface and they will not suffer from the memory
corruption problem.

But we need something that stops the memory corruption now and that can be
backported to the stable kernels. So, I'm proposing this commit that
disables tasklets in both dm-crypt and dm-verity. This commit doesn't
remove the tasklet support, because the tasklet code will be reused when
atomic workqueues will be implemented.

[1] https://lore.kernel.org/all/d390d7ee-f142-44d3-822a-87949e14608b@suse.de/T/
[2] https://lore.kernel.org/lkml/20240130091300.2968534-1-tj@kernel.org/

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 39d42fa96ba1b ("dm crypt: add flags to optionally bypass kcryptd workqueues")
Fixes: 5721d4e5a9cdb ("dm verity: Add optional "try_verify_in_tasklet" feature")
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
 drivers/md/dm-crypt.c         | 38 ++---------------------------------
 drivers/md/dm-verity-target.c | 26 ++----------------------
 drivers/md/dm-verity.h        |  1 -
 3 files changed, 4 insertions(+), 61 deletions(-)

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 855b482cbff1f..f745f85082434 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -73,10 +73,8 @@ struct dm_crypt_io {
 	struct bio *base_bio;
 	u8 *integrity_metadata;
 	bool integrity_metadata_from_pool:1;
-	bool in_tasklet:1;
 
 	struct work_struct work;
-	struct tasklet_struct tasklet;
 
 	struct convert_context ctx;
 
@@ -1762,7 +1760,6 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc,
 	io->ctx.r.req = NULL;
 	io->integrity_metadata = NULL;
 	io->integrity_metadata_from_pool = false;
-	io->in_tasklet = false;
 	atomic_set(&io->io_pending, 0);
 }
 
@@ -1771,13 +1768,6 @@ static void crypt_inc_pending(struct dm_crypt_io *io)
 	atomic_inc(&io->io_pending);
 }
 
-static void kcryptd_io_bio_endio(struct work_struct *work)
-{
-	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
-
-	bio_endio(io->base_bio);
-}
-
 /*
  * One of the bios was finished. Check for completion of
  * the whole request and correctly clean up the buffer.
@@ -1801,20 +1791,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 
 	base_bio->bi_status = error;
 
-	/*
-	 * If we are running this function from our tasklet,
-	 * we can't call bio_endio() here, because it will call
-	 * clone_endio() from dm.c, which in turn will
-	 * free the current struct dm_crypt_io structure with
-	 * our tasklet. In this case we need to delay bio_endio()
-	 * execution to after the tasklet is done and dequeued.
-	 */
-	if (io->in_tasklet) {
-		INIT_WORK(&io->work, kcryptd_io_bio_endio);
-		queue_work(cc->io_queue, &io->work);
-		return;
-	}
-
 	bio_endio(base_bio);
 }
 
@@ -2246,11 +2222,6 @@ static void kcryptd_crypt(struct work_struct *work)
 		kcryptd_crypt_write_convert(io);
 }
 
-static void kcryptd_crypt_tasklet(unsigned long work)
-{
-	kcryptd_crypt((struct work_struct *)work);
-}
-
 static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
@@ -2262,15 +2233,10 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 		 * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
 		 * it is being executed with irqs disabled.
 		 */
-		if (in_hardirq() || irqs_disabled()) {
-			io->in_tasklet = true;
-			tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work);
-			tasklet_schedule(&io->tasklet);
+		if (!(in_hardirq() || irqs_disabled())) {
+			kcryptd_crypt(&io->work);
 			return;
 		}
-
-		kcryptd_crypt(&io->work);
-		return;
 	}
 
 	INIT_WORK(&io->work, kcryptd_crypt);
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 14e58ae705218..82662f5769c4a 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -645,23 +645,6 @@ static void verity_work(struct work_struct *w)
 	verity_finish_io(io, errno_to_blk_status(verity_verify_io(io)));
 }
 
-static void verity_tasklet(unsigned long data)
-{
-	struct dm_verity_io *io = (struct dm_verity_io *)data;
-	int err;
-
-	io->in_tasklet = true;
-	err = verity_verify_io(io);
-	if (err == -EAGAIN || err == -ENOMEM) {
-		/* fallback to retrying with work-queue */
-		INIT_WORK(&io->work, verity_work);
-		queue_work(io->v->verify_wq, &io->work);
-		return;
-	}
-
-	verity_finish_io(io, errno_to_blk_status(err));
-}
-
 static void verity_end_io(struct bio *bio)
 {
 	struct dm_verity_io *io = bio->bi_private;
@@ -674,13 +657,8 @@ static void verity_end_io(struct bio *bio)
 		return;
 	}
 
-	if (static_branch_unlikely(&use_tasklet_enabled) && io->v->use_tasklet) {
-		tasklet_init(&io->tasklet, verity_tasklet, (unsigned long)io);
-		tasklet_schedule(&io->tasklet);
-	} else {
-		INIT_WORK(&io->work, verity_work);
-		queue_work(io->v->verify_wq, &io->work);
-	}
+	INIT_WORK(&io->work, verity_work);
+	queue_work(io->v->verify_wq, &io->work);
 }
 
 /*
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index f9d522c870e61..f3f6070084196 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -83,7 +83,6 @@ struct dm_verity_io {
 	struct bvec_iter iter;
 
 	struct work_struct work;
-	struct tasklet_struct tasklet;
 
 	/*
 	 * Three variably-size fields follow this struct:
-- 
GitLab


From a60e6c3918d20848906ffcdfcf72ca6a8cfbcf2e Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Tue, 5 Dec 2023 17:36:01 +0100
Subject: [PATCH 3877/4076] Input: i8042 - fix strange behavior of touchpad on
 Clevo NS70PU

When closing the laptop lid with an external screen connected, the mouse
pointer has a constant movement to the lower right corner. Opening the
lid again stops this movement, but after that the touchpad does no longer
register clicks.

The touchpad is connected both via i2c-hid and PS/2, the predecessor of
this device (NS70MU) has the same layout in this regard and also strange
behaviour caused by the psmouse and the i2c-hid driver fighting over
touchpad control. This fix is reusing the same workaround by just
disabling the PS/2 aux port, that is only used by the touchpad, to give the
i2c-hid driver the lone control over the touchpad.

v2: Rebased on current master

Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20231205163602.16106-1-wse@tuxedocomputers.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index b585b1dab870e..cd45a65e17f2c 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1208,6 +1208,12 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 					SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP |
 					SERIO_QUIRK_NOPNP)
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "NS5x_7xPU"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"),
-- 
GitLab


From de1034b38a346ef6be25fe8792f5d1e0684d5ff4 Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@rivosinc.com>
Date: Fri, 2 Feb 2024 10:07:03 -0800
Subject: [PATCH 3878/4076] efi: runtime: Fix potential overflow of
 soft-reserved region size

md_size will have been narrowed if we have >= 4GB worth of pages in a
soft-reserved region.

Signed-off-by: Andrew Bresticker <abrestic@rivosinc.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/arm-runtime.c   | 2 +-
 drivers/firmware/efi/riscv-runtime.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 83f5bb57fa4c4..83092d93f36a6 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void)
 		efi_memory_desc_t *md;
 
 		for_each_efi_memory_desc(md) {
-			int md_size = md->num_pages << EFI_PAGE_SHIFT;
+			u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
 			struct resource *res;
 
 			if (!(md->attribute & EFI_MEMORY_SP))
diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c
index 09525fb5c240e..01f0f90ea4183 100644
--- a/drivers/firmware/efi/riscv-runtime.c
+++ b/drivers/firmware/efi/riscv-runtime.c
@@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void)
 		efi_memory_desc_t *md;
 
 		for_each_efi_memory_desc(md) {
-			int md_size = md->num_pages << EFI_PAGE_SHIFT;
+			u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
 			struct resource *res;
 
 			if (!(md->attribute & EFI_MEMORY_SP))
-- 
GitLab


From 0bcff59ef7a652fcdc6d535554b63278c2406c8f Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@rivosinc.com>
Date: Fri, 2 Feb 2024 10:07:04 -0800
Subject: [PATCH 3879/4076] efi: Don't add memblocks for soft-reserved memory

Adding memblocks for soft-reserved regions prevents them from later being
hotplugged in by dax_kmem.

Signed-off-by: Andrew Bresticker <abrestic@rivosinc.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi-init.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index d4987d0130801..a00e07b853f22 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -143,15 +143,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
 	case EFI_BOOT_SERVICES_DATA:
 	case EFI_CONVENTIONAL_MEMORY:
 	case EFI_PERSISTENT_MEMORY:
-		/*
-		 * Special purpose memory is 'soft reserved', which means it
-		 * is set aside initially, but can be hotplugged back in or
-		 * be assigned to the dax driver after boot.
-		 */
-		if (efi_soft_reserve_enabled() &&
-		    (md->attribute & EFI_MEMORY_SP))
-			return false;
-
 		/*
 		 * According to the spec, these regions are no longer reserved
 		 * after calling ExitBootServices(). However, we can only use
@@ -196,6 +187,16 @@ static __init void reserve_regions(void)
 		size = npages << PAGE_SHIFT;
 
 		if (is_memory(md)) {
+			/*
+			 * Special purpose memory is 'soft reserved', which
+			 * means it is set aside initially. Don't add a memblock
+			 * for it now so that it can be hotplugged back in or
+			 * be assigned to the dax driver after boot.
+			 */
+			if (efi_soft_reserve_enabled() &&
+			    (md->attribute & EFI_MEMORY_SP))
+				continue;
+
 			early_init_dt_add_memory_arch(paddr, size);
 
 			if (!is_usable_memory(md))
-- 
GitLab


From 4255447ad34c5c3785fcdcf76cfa0271d6e5ed39 Mon Sep 17 00:00:00 2001
From: Szilard Fabian <szfabian@bluemarch.art>
Date: Fri, 2 Feb 2024 10:28:59 -0800
Subject: [PATCH 3880/4076] Input: i8042 - add Fujitsu Lifebook U728 to i8042
 quirk table

Another Fujitsu-related patch.

In the initial boot stage the integrated keyboard of Fujitsu Lifebook U728
refuses to work and it's not possible to type for example a dm-crypt
passphrase without the help of an external keyboard.

i8042.nomux kernel parameter resolves this issue but using that a PS/2
mouse is detected. This input device is unused even when the i2c-hid-acpi
kernel module is blacklisted making the integrated ELAN touchpad
(04F3:3092) not working at all.

So this notebook uses a hid-over-i2c touchpad which is managed by the
i2c_designware input driver. Since you can't find a PS/2 mouse port on this
computer and you can't connect a PS/2 mouse to it even with an official
port replicator I think it's safe to not use the PS/2 mouse port at all.

Signed-off-by: Szilard Fabian <szfabian@bluemarch.art>
Link: https://lore.kernel.org/r/20240103014717.127307-2-szfabian@bluemarch.art
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index cd45a65e17f2c..dfc6c581873b7 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -634,6 +634,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		},
 		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
 	},
+	{
+		/* Fujitsu Lifebook U728 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U728"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
+	},
 	{
 		/* Gigabyte M912 */
 		.matches = {
-- 
GitLab


From ba5e1272142d051dcc57ca1d3225ad8a089f9858 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 1 Feb 2024 17:53:24 +0000
Subject: [PATCH 3881/4076] netdevsim: avoid potential loop in
 nsim_dev_trap_report_work()

Many syzbot reports include the following trace [1]

If nsim_dev_trap_report_work() can not grab the mutex,
it should rearm itself at least one jiffie later.

[1]
Sending NMI from CPU 1 to CPUs 0:
NMI backtrace for cpu 0
CPU: 0 PID: 32383 Comm: kworker/0:2 Not tainted 6.8.0-rc2-syzkaller-00031-g861c0981648f #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
Workqueue: events nsim_dev_trap_report_work
 RIP: 0010:bytes_is_nonzero mm/kasan/generic.c:89 [inline]
 RIP: 0010:memory_is_nonzero mm/kasan/generic.c:104 [inline]
 RIP: 0010:memory_is_poisoned_n mm/kasan/generic.c:129 [inline]
 RIP: 0010:memory_is_poisoned mm/kasan/generic.c:161 [inline]
 RIP: 0010:check_region_inline mm/kasan/generic.c:180 [inline]
 RIP: 0010:kasan_check_range+0x101/0x190 mm/kasan/generic.c:189
Code: 07 49 39 d1 75 0a 45 3a 11 b8 01 00 00 00 7c 0b 44 89 c2 e8 21 ed ff ff 83 f0 01 5b 5d 41 5c c3 48 85 d2 74 4f 48 01 ea eb 09 <48> 83 c0 01 48 39 d0 74 41 80 38 00 74 f2 eb b6 41 bc 08 00 00 00
RSP: 0018:ffffc90012dcf998 EFLAGS: 00000046
RAX: fffffbfff258af1e RBX: fffffbfff258af1f RCX: ffffffff8168eda3
RDX: fffffbfff258af1f RSI: 0000000000000004 RDI: ffffffff92c578f0
RBP: fffffbfff258af1e R08: 0000000000000000 R09: fffffbfff258af1e
R10: ffffffff92c578f3 R11: ffffffff8acbcbc0 R12: 0000000000000002
R13: ffff88806db38400 R14: 1ffff920025b9f42 R15: ffffffff92c578e8
FS:  0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000c00994e078 CR3: 000000002c250000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <NMI>
 </NMI>
 <TASK>
  instrument_atomic_read include/linux/instrumented.h:68 [inline]
  atomic_read include/linux/atomic/atomic-instrumented.h:32 [inline]
  queued_spin_is_locked include/asm-generic/qspinlock.h:57 [inline]
  debug_spin_unlock kernel/locking/spinlock_debug.c:101 [inline]
  do_raw_spin_unlock+0x53/0x230 kernel/locking/spinlock_debug.c:141
  __raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:150 [inline]
  _raw_spin_unlock_irqrestore+0x22/0x70 kernel/locking/spinlock.c:194
  debug_object_activate+0x349/0x540 lib/debugobjects.c:726
  debug_work_activate kernel/workqueue.c:578 [inline]
  insert_work+0x30/0x230 kernel/workqueue.c:1650
  __queue_work+0x62e/0x11d0 kernel/workqueue.c:1802
  __queue_delayed_work+0x1bf/0x270 kernel/workqueue.c:1953
  queue_delayed_work_on+0x106/0x130 kernel/workqueue.c:1989
  queue_delayed_work include/linux/workqueue.h:563 [inline]
  schedule_delayed_work include/linux/workqueue.h:677 [inline]
  nsim_dev_trap_report_work+0x9c0/0xc80 drivers/net/netdevsim/dev.c:842
  process_one_work+0x886/0x15d0 kernel/workqueue.c:2633
  process_scheduled_works kernel/workqueue.c:2706 [inline]
  worker_thread+0x8b9/0x1290 kernel/workqueue.c:2787
  kthread+0x2c6/0x3a0 kernel/kthread.c:388
  ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
  ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:242
 </TASK>

Fixes: 012ec02ae441 ("netdevsim: convert driver to use unlocked devlink API during init/fini")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240201175324.3752746-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/dev.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index b4d3b9cde8bd6..92a7a36b93ac0 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -835,14 +835,14 @@ static void nsim_dev_trap_report_work(struct work_struct *work)
 				      trap_report_dw.work);
 	nsim_dev = nsim_trap_data->nsim_dev;
 
-	/* For each running port and enabled packet trap, generate a UDP
-	 * packet with a random 5-tuple and report it.
-	 */
 	if (!devl_trylock(priv_to_devlink(nsim_dev))) {
-		schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 0);
+		schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 1);
 		return;
 	}
 
+	/* For each running port and enabled packet trap, generate a UDP
+	 * packet with a random 5-tuple and report it.
+	 */
 	list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) {
 		if (!netif_running(nsim_dev_port->ns->netdev))
 			continue;
-- 
GitLab


From 2e7d3b67630dfd8f178c41fa2217aa00e79a5887 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 1 Feb 2024 10:47:51 +0100
Subject: [PATCH 3882/4076] net: atlantic: Fix DMA mapping for PTP hwts ring

Function aq_ring_hwts_rx_alloc() maps extra AQ_CFG_RXDS_DEF bytes
for PTP HWTS ring but then generic aq_ring_free() does not take this
into account.
Create and use a specific function to free HWTS ring to fix this
issue.

Trace:
[  215.351607] ------------[ cut here ]------------
[  215.351612] DMA-API: atlantic 0000:4b:00.0: device driver frees DMA memory with different size [device address=0x00000000fbdd0000] [map size=34816 bytes] [unmap size=32768 bytes]
[  215.351635] WARNING: CPU: 33 PID: 10759 at kernel/dma/debug.c:988 check_unmap+0xa6f/0x2360
...
[  215.581176] Call Trace:
[  215.583632]  <TASK>
[  215.585745]  ? show_trace_log_lvl+0x1c4/0x2df
[  215.590114]  ? show_trace_log_lvl+0x1c4/0x2df
[  215.594497]  ? debug_dma_free_coherent+0x196/0x210
[  215.599305]  ? check_unmap+0xa6f/0x2360
[  215.603147]  ? __warn+0xca/0x1d0
[  215.606391]  ? check_unmap+0xa6f/0x2360
[  215.610237]  ? report_bug+0x1ef/0x370
[  215.613921]  ? handle_bug+0x3c/0x70
[  215.617423]  ? exc_invalid_op+0x14/0x50
[  215.621269]  ? asm_exc_invalid_op+0x16/0x20
[  215.625480]  ? check_unmap+0xa6f/0x2360
[  215.629331]  ? mark_lock.part.0+0xca/0xa40
[  215.633445]  debug_dma_free_coherent+0x196/0x210
[  215.638079]  ? __pfx_debug_dma_free_coherent+0x10/0x10
[  215.643242]  ? slab_free_freelist_hook+0x11d/0x1d0
[  215.648060]  dma_free_attrs+0x6d/0x130
[  215.651834]  aq_ring_free+0x193/0x290 [atlantic]
[  215.656487]  aq_ptp_ring_free+0x67/0x110 [atlantic]
...
[  216.127540] ---[ end trace 6467e5964dd2640b ]---
[  216.132160] DMA-API: Mapped at:
[  216.132162]  debug_dma_alloc_coherent+0x66/0x2f0
[  216.132165]  dma_alloc_attrs+0xf5/0x1b0
[  216.132168]  aq_ring_hwts_rx_alloc+0x150/0x1f0 [atlantic]
[  216.132193]  aq_ptp_ring_alloc+0x1bb/0x540 [atlantic]
[  216.132213]  aq_nic_init+0x4a1/0x760 [atlantic]

Fixes: 94ad94558b0f ("net: aquantia: add PTP rings infrastructure")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240201094752.883026-1-ivecera@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ptp.c  |  4 ++--
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 13 +++++++++++++
 drivers/net/ethernet/aquantia/atlantic/aq_ring.h |  1 +
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
index abd4832e4ed21..5acb3e16b5677 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
@@ -993,7 +993,7 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 	return 0;
 
 err_exit_hwts_rx:
-	aq_ring_free(&aq_ptp->hwts_rx);
+	aq_ring_hwts_rx_free(&aq_ptp->hwts_rx);
 err_exit_ptp_rx:
 	aq_ring_free(&aq_ptp->ptp_rx);
 err_exit_ptp_tx:
@@ -1011,7 +1011,7 @@ void aq_ptp_ring_free(struct aq_nic_s *aq_nic)
 
 	aq_ring_free(&aq_ptp->ptp_tx);
 	aq_ring_free(&aq_ptp->ptp_rx);
-	aq_ring_free(&aq_ptp->hwts_rx);
+	aq_ring_hwts_rx_free(&aq_ptp->hwts_rx);
 
 	aq_ptp_skb_ring_release(&aq_ptp->skb_ring);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index cda8597b4e146..f7433abd65915 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -919,6 +919,19 @@ void aq_ring_free(struct aq_ring_s *self)
 	}
 }
 
+void aq_ring_hwts_rx_free(struct aq_ring_s *self)
+{
+	if (!self)
+		return;
+
+	if (self->dx_ring) {
+		dma_free_coherent(aq_nic_get_dev(self->aq_nic),
+				  self->size * self->dx_size + AQ_CFG_RXDS_DEF,
+				  self->dx_ring, self->dx_ring_pa);
+		self->dx_ring = NULL;
+	}
+}
+
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data)
 {
 	unsigned int count;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 52847310740a2..d627ace850ff5 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -210,6 +210,7 @@ int aq_ring_rx_fill(struct aq_ring_s *self);
 int aq_ring_hwts_rx_alloc(struct aq_ring_s *self,
 			  struct aq_nic_s *aq_nic, unsigned int idx,
 			  unsigned int size, unsigned int dx_size);
+void aq_ring_hwts_rx_free(struct aq_ring_s *self);
 void aq_ring_hwts_rx_clean(struct aq_ring_s *self, struct aq_nic_s *aq_nic);
 
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data);
-- 
GitLab


From cb9f4a30fb85e1f4f149ada595a67899adb3db19 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Feb 2024 19:42:38 +0100
Subject: [PATCH 3883/4076] selftests: net: cut more slack for gro fwd tests.

The udpgro_fwd.sh self-tests are somewhat unstable. There are
a few timing constraints the we struggle to meet on very slow
environments.

Instead of skipping the whole tests in such envs, increase the
test resilience WRT very slow hosts: increase the inter-packets
timeouts, avoid resetting the counters every second and finally
disable reduce the background traffic noise.

Tested with:

for I in $(seq 1 100); do
	./tools/testing/selftests/kselftest_install/run_kselftest.sh \
		-t net:udpgro_fwd.sh || exit -1
done

in a slow environment.

Fixes: a062260a9d5f ("selftests: net: add UDP GRO forwarding self-tests")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/f4b6b11064a0d39182a9ae6a853abae3e9b4426a.1706812005.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/udpgro_fwd.sh     | 14 ++++++++++++--
 tools/testing/selftests/net/udpgso_bench_rx.c |  2 +-
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index d6b9c759043ca..9cd5e885e91f7 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -39,6 +39,10 @@ create_ns() {
 	for ns in $NS_SRC $NS_DST; do
 		ip netns add $ns
 		ip -n $ns link set dev lo up
+
+		# disable route solicitations to decrease 'noise' traffic
+		ip netns exec $ns sysctl -qw net.ipv6.conf.default.router_solicitations=0
+		ip netns exec $ns sysctl -qw net.ipv6.conf.all.router_solicitations=0
 	done
 
 	ip link add name veth$SRC type veth peer name veth$DST
@@ -80,6 +84,12 @@ create_vxlan_pair() {
 		create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6
 		ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad
 	done
+
+	# preload neighbur cache, do avoid some noisy traffic
+	local addr_dst=$(ip -j -n $BASE$DST link show dev vxlan6$DST  |jq -r '.[]["address"]')
+	local addr_src=$(ip -j -n $BASE$SRC link show dev vxlan6$SRC  |jq -r '.[]["address"]')
+	ip -n $BASE$DST neigh add dev vxlan6$DST lladdr $addr_src $OL_NET_V6$SRC
+	ip -n $BASE$SRC neigh add dev vxlan6$SRC lladdr $addr_dst $OL_NET_V6$DST
 }
 
 is_ipv6() {
@@ -119,7 +129,7 @@ run_test() {
 	# not enable GRO
 	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789
 	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
-	ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
+	ip netns exec $NS_DST ./udpgso_bench_rx -C 2000 -R 100 -n 10 -l 1300 $rx_args &
 	local spid=$!
 	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
@@ -168,7 +178,7 @@ run_bench() {
 	# bind the sender and the receiver to different CPUs to try
 	# get reproducible results
 	ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
-	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10  &
+	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 2000 -R 100  &
 	local spid=$!
 	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index f35a924d4a303..1cbadd267c963 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -375,7 +375,7 @@ static void do_recv(void)
 			do_flush_udp(fd);
 
 		tnow = gettimeofday_ms();
-		if (tnow > treport) {
+		if (!cfg_expected_pkt_nr && tnow > treport) {
 			if (packets)
 				fprintf(stderr,
 					"%s rx: %6lu MB/s %8lu calls/s\n",
-- 
GitLab


From d75df752647728c6d65e594e5e4493448bea6cda Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Feb 2024 19:42:39 +0100
Subject: [PATCH 3884/4076] selftests: net: fix setup_ns usage in rtnetlink.sh

The setup_ns helper marks the testns global variable as
readonly. Later attempts to set such variable are unsuccessful,
causing a couple test failures.

Avoid completely the variable re-initialization and let the
function access the global value.

Fixes: e9ce7ededf14 ("selftests: rtnetlink: use setup_ns in bonding test")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/6e7c937c8ff73ca52a21a4a536a13a76ec0173a8.1706812005.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/rtnetlink.sh | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 4667d74579d13..874a2952aa8ee 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -440,7 +440,6 @@ kci_test_encap_vxlan()
 	local ret=0
 	vxlan="test-vxlan0"
 	vlan="test-vlan0"
-	testns="$1"
 	run_cmd ip -netns "$testns" link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
 		dev "$devdummy" dstport 4789
 	if [ $? -ne 0 ]; then
@@ -485,7 +484,6 @@ kci_test_encap_fou()
 {
 	local ret=0
 	name="test-fou"
-	testns="$1"
 	run_cmd_grep 'Usage: ip fou' ip fou help
 	if [ $? -ne 0 ];then
 		end_test "SKIP: fou: iproute2 too old"
@@ -526,8 +524,8 @@ kci_test_encap()
 	run_cmd ip -netns "$testns" link set lo up
 	run_cmd ip -netns "$testns" link add name "$devdummy" type dummy
 	run_cmd ip -netns "$testns" link set "$devdummy" up
-	run_cmd kci_test_encap_vxlan "$testns"
-	run_cmd kci_test_encap_fou "$testns"
+	run_cmd kci_test_encap_vxlan
+	run_cmd kci_test_encap_fou
 
 	ip netns del "$testns"
 	return $ret
-- 
GitLab


From e71e016ad0f6e641a7898b8cda5f62f8e2beb2f1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Feb 2024 19:42:40 +0100
Subject: [PATCH 3885/4076] selftests: net: fix tcp listener handling in
 pmtu.sh

The pmtu.sh test uses a few TCP listener in a problematic way:
It hard-codes a constant timeout to wait for the listener starting-up
in background. That introduces unneeded latency and on very slow and
busy host it can fail.

Additionally the test starts again the same listener in the same
namespace on the same port, just after the previous connection
completed. Fast host can attempt starting the new server before the
old one really closed the socket.

Address the issues using the wait_local_port_listen helper and
explicitly waiting for the background listener process exit.

Fixes: 136a1b434bbb ("selftests: net: test vxlan pmtu exceptions with tcp")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/f8e8f6d44427d8c45e9f6a71ee1a321047452087.1706812005.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/pmtu.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 3f118e3f1c66d..f0febc19baae5 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -199,6 +199,7 @@
 #	Same as above but with IPv6
 
 source lib.sh
+source net_helper.sh
 
 PAUSE_ON_FAIL=no
 VERBOSE=0
@@ -1336,13 +1337,15 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
 			TCPDST="TCP:[${dst}]:50000"
 		fi
 		${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile &
+		local socat_pid=$!
 
-		sleep 1
+		wait_local_port_listen ${NS_B} 50000 tcp
 
 		dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
 
 		size=$(du -sb $tmpoutfile)
 		size=${size%%/tmp/*}
+		wait ${socat_pid}
 
 		[ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1
 	done
-- 
GitLab


From 691bb4e49c98a47bc643dd808453136ce78b15b4 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Feb 2024 19:42:41 +0100
Subject: [PATCH 3886/4076] selftests: net: avoid just another constant wait

Using hard-coded constant timeout to wait for some expected
event is deemed to fail sooner or later, especially in slow
env.

Our CI has spotted another of such race:
   # TEST: ipv6: cleanup of cached exceptions - nexthop objects          [FAIL]
   #   can't delete veth device in a timely manner, PMTU dst likely leaked

Replace the crude sleep with a loop looking for the expected condition
at low interval for a much longer range.

Fixes: b3cc4f8a8a41 ("selftests: pmtu: add explicit tests for PMTU exceptions cleanup")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/fd5c745e9bb665b724473af6a9373a8c2a62b247.1706812005.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/pmtu.sh | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f0febc19baae5..d65fdd407d73f 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1957,6 +1957,13 @@ check_command() {
 	return 0
 }
 
+check_running() {
+	pid=${1}
+	cmd=${2}
+
+	[ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ]
+}
+
 test_cleanup_vxlanX_exception() {
 	outer="${1}"
 	encap="vxlan"
@@ -1987,11 +1994,12 @@ test_cleanup_vxlanX_exception() {
 
 	${ns_a} ip link del dev veth_A-R1 &
 	iplink_pid=$!
-	sleep 1
-	if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then
-		err "  can't delete veth device in a timely manner, PMTU dst likely leaked"
-		return 1
-	fi
+	for i in $(seq 1 20); do
+		check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0
+		sleep 0.1
+	done
+	err "  can't delete veth device in a timely manner, PMTU dst likely leaked"
+	return 1
 }
 
 test_cleanup_ipv6_exception() {
-- 
GitLab


From d7f5fb33cf77247b7bf9a871aaeea72ca4f51ad7 Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Wed, 31 Jan 2024 21:14:13 +0100
Subject: [PATCH 3887/4076] tsnep: Fix mapping for zero copy XDP_TX action

For XDP_TX action xdp_buff is converted to xdp_frame. The conversion is
done by xdp_convert_buff_to_frame(). The memory type of the resulting
xdp_frame depends on the memory type of the xdp_buff. For page pool
based xdp_buff it produces xdp_frame with memory type
MEM_TYPE_PAGE_POOL. For zero copy XSK pool based xdp_buff it produces
xdp_frame with memory type MEM_TYPE_PAGE_ORDER0.

tsnep_xdp_xmit_back() is not prepared for that and uses always the page
pool buffer type TSNEP_TX_TYPE_XDP_TX. This leads to invalid mappings
and the transmission of undefined data.

Improve tsnep_xdp_xmit_back() to use the generic buffer type
TSNEP_TX_TYPE_XDP_NDO for zero copy XDP_TX.

Fixes: 3fc2333933fd ("tsnep: Add XDP socket zero-copy RX support")
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/engleder/tsnep_main.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 9aeff2b37a612..64eadd3207983 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -719,17 +719,25 @@ static void tsnep_xdp_xmit_flush(struct tsnep_tx *tx)
 
 static bool tsnep_xdp_xmit_back(struct tsnep_adapter *adapter,
 				struct xdp_buff *xdp,
-				struct netdev_queue *tx_nq, struct tsnep_tx *tx)
+				struct netdev_queue *tx_nq, struct tsnep_tx *tx,
+				bool zc)
 {
 	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 	bool xmit;
+	u32 type;
 
 	if (unlikely(!xdpf))
 		return false;
 
+	/* no page pool for zero copy */
+	if (zc)
+		type = TSNEP_TX_TYPE_XDP_NDO;
+	else
+		type = TSNEP_TX_TYPE_XDP_TX;
+
 	__netif_tx_lock(tx_nq, smp_processor_id());
 
-	xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, TSNEP_TX_TYPE_XDP_TX);
+	xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, type);
 
 	/* Avoid transmit queue timeout since we share it with the slow path */
 	if (xmit)
@@ -1273,7 +1281,7 @@ static bool tsnep_xdp_run_prog(struct tsnep_rx *rx, struct bpf_prog *prog,
 	case XDP_PASS:
 		return false;
 	case XDP_TX:
-		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx))
+		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx, false))
 			goto out_failure;
 		*status |= TSNEP_XDP_TX;
 		return true;
@@ -1323,7 +1331,7 @@ static bool tsnep_xdp_run_prog_zc(struct tsnep_rx *rx, struct bpf_prog *prog,
 	case XDP_PASS:
 		return false;
 	case XDP_TX:
-		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx))
+		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx, true))
 			goto out_failure;
 		*status |= TSNEP_XDP_TX;
 		return true;
-- 
GitLab


From d75abeec401f8c86b470e7028a13fcdc87e5dd06 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Thu, 1 Feb 2024 09:38:15 +0100
Subject: [PATCH 3888/4076] tunnels: fix out of bounds access when building
 IPv6 PMTU error

If the ICMPv6 error is built from a non-linear skb we get the following
splat,

  BUG: KASAN: slab-out-of-bounds in do_csum+0x220/0x240
  Read of size 4 at addr ffff88811d402c80 by task netperf/820
  CPU: 0 PID: 820 Comm: netperf Not tainted 6.8.0-rc1+ #543
  ...
   kasan_report+0xd8/0x110
   do_csum+0x220/0x240
   csum_partial+0xc/0x20
   skb_tunnel_check_pmtu+0xeb9/0x3280
   vxlan_xmit_one+0x14c2/0x4080
   vxlan_xmit+0xf61/0x5c00
   dev_hard_start_xmit+0xfb/0x510
   __dev_queue_xmit+0x7cd/0x32a0
   br_dev_queue_push_xmit+0x39d/0x6a0

Use skb_checksum instead of csum_partial who cannot deal with non-linear
SKBs.

Fixes: 4cb47a8644cc ("tunnels: PMTU discovery support for directly bridged IP packets")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 586b1b3e35b80..80ccd6661aa32 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
 	};
 	skb_reset_network_header(skb);
 
-	csum = csum_partial(icmp6h, len, 0);
+	csum = skb_checksum(skb, skb_transport_offset(skb), len, 0);
 	icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len,
 					      IPPROTO_ICMPV6, csum);
 
-- 
GitLab


From f3616173bf9be9bf39d131b120d6eea4e6324cb5 Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Thu, 1 Feb 2024 20:41:05 +0800
Subject: [PATCH 3889/4076] atm: idt77252: fix a memleak in open_card_ubr0

When alloc_scq fails, card->vcs[0] (i.e. vc) should be freed. Otherwise,
in the following call chain:

idt77252_init_one
  |-> idt77252_dev_open
        |-> open_card_ubr0
              |-> alloc_scq [failed]
  |-> deinit_card
        |-> vfree(card->vcs);

card->vcs is freed and card->vcs[0] is leaked.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/idt77252.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index e327a0229dc17..e7f713cd70d3f 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -2930,6 +2930,8 @@ open_card_ubr0(struct idt77252_dev *card)
 	vc->scq = alloc_scq(card, vc->class);
 	if (!vc->scq) {
 		printk("%s: can't get SCQ.\n", card->name);
+		kfree(card->vcs[0]);
+		card->vcs[0] = NULL;
 		return -ENOMEM;
 	}
 
-- 
GitLab


From b09b58e31b0f43d76f79b9943da3fb7c2843dcbb Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Thu, 1 Feb 2024 20:47:13 +0800
Subject: [PATCH 3890/4076] octeontx2-pf: Fix a memleak otx2_sq_init

When qmem_alloc and pfvf->hw_ops->sq_aq_init fails, sq->sg should be
freed to prevent memleak.

Fixes: c9c12d339d93 ("octeontx2-pf: Add support for PTP clock")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Acked-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/marvell/octeontx2/nic/otx2_common.c   | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 7ca6941ea0b9b..02d0b707aea5b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -951,8 +951,11 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 	if (pfvf->ptp && qidx < pfvf->hw.tx_queues) {
 		err = qmem_alloc(pfvf->dev, &sq->timestamps, qset->sqe_cnt,
 				 sizeof(*sq->timestamps));
-		if (err)
+		if (err) {
+			kfree(sq->sg);
+			sq->sg = NULL;
 			return err;
+		}
 	}
 
 	sq->head = 0;
@@ -968,7 +971,14 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 	sq->stats.bytes = 0;
 	sq->stats.pkts = 0;
 
-	return pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura);
+	err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura);
+	if (err) {
+		kfree(sq->sg);
+		sq->sg = NULL;
+		return err;
+	}
+
+	return 0;
 
 }
 
-- 
GitLab


From 54ce1927eb787f7bbb7ee664841c8f5932703f39 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 31 Jan 2024 15:55:38 -0800
Subject: [PATCH 3891/4076] cxl/cper: Fix errant CPER prints for CXL events

Jonathan reports that CXL CPER events dump an extra generic error
message.

	{1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 1
	{1}[Hardware Error]: event severity: recoverable
	{1}[Hardware Error]:  Error 0, type: recoverable
	{1}[Hardware Error]:   section type: unknown, fbcd0a77-c260-417f-85a9-088b1621eba6
	{1}[Hardware Error]:   section length: 0x90
	{1}[Hardware Error]:   00000000: 00000090 00000007 00000000 0d938086 ................
	{1}[Hardware Error]:   00000010: 00100000 00000000 00040000 00000000 ................
	...

CXL events were rerouted though the CXL subsystem for additional
processing.  However, when that work was done it was missed that
cper_estatus_print_section() continued with a generic error message
which is confusing.

Teach CPER print code to ignore printing details of some section types.
Assign the CXL event GUIDs to this set to prevent confusing unknown
prints.

Reported-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Suggested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/acpi/apei/ghes.c    | 26 --------------------------
 drivers/firmware/efi/cper.c | 19 +++++++++++++++++++
 include/linux/cper.h        | 23 +++++++++++++++++++++++
 3 files changed, 42 insertions(+), 26 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 7b7c605166e0c..fe825a432c5bf 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -680,32 +680,6 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 static DECLARE_RWSEM(cxl_cper_rw_sem);
 static cxl_cper_callback cper_callback;
 
-/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
-
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
-	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
-		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
-
-/*
- * DRAM Event Record
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
- */
-#define CPER_SEC_CXL_DRAM_GUID						\
-	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
-		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-#define CPER_SEC_CXL_MEM_MODULE_GUID					\
-	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
-		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
-
 static void cxl_cper_post_event(enum cxl_event_type event_type,
 				struct cxl_cper_event_rec *rec)
 {
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 35c37f667781c..9b3884ff81e69 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -523,6 +523,17 @@ static void cper_print_tstamp(const char *pfx,
 	}
 }
 
+struct ignore_section {
+	guid_t guid;
+	const char *name;
+};
+
+static const struct ignore_section ignore_sections[] = {
+	{ .guid = CPER_SEC_CXL_GEN_MEDIA_GUID, .name = "CXL General Media Event" },
+	{ .guid = CPER_SEC_CXL_DRAM_GUID, .name = "CXL DRAM Event" },
+	{ .guid = CPER_SEC_CXL_MEM_MODULE_GUID, .name = "CXL Memory Module Event" },
+};
+
 static void
 cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata,
 			   int sec_no)
@@ -543,6 +554,14 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
 
 	snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
+
+	for (int i = 0; i < ARRAY_SIZE(ignore_sections); i++) {
+		if (guid_equal(sec_type, &ignore_sections[i].guid)) {
+			printk("%ssection_type: %s\n", newpfx, ignore_sections[i].name);
+			return;
+		}
+	}
+
 	if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) {
 		struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata);
 
diff --git a/include/linux/cper.h b/include/linux/cper.h
index c1a7dc3251215..265b0f8fc0b3c 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -90,6 +90,29 @@ enum {
 	GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E,	\
 		  0x72, 0x2D, 0xEB, 0x41)
 
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
+	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID						\
+	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID					\
+	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
+
 /*
  * Flags bits definitions for flags in struct cper_record_header
  * If set, the error has been recovered
-- 
GitLab


From dbea519d6878c298dd0f48e6ec2dbacebe4bbb2a Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 31 Jan 2024 15:55:39 -0800
Subject: [PATCH 3892/4076] cxl/trace: Remove unnecessary memcpy's

CPER events don't have UUIDs.  Therefore UUIDs were removed from the
records passed to trace events and replaced with hard coded values.

As pointed out by Jonathan, the new defines for the UUIDs present a more
efficient way to assign UUID in trace records.[1]

Replace memcpy's with the use of static data.

[1] https://lore.kernel.org/all/20240108132325.00000e9c@Huawei.com/

Suggested-by: Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/cxl/core/trace.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 89445435303aa..bdf117a33744b 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -338,7 +338,7 @@ TRACE_EVENT(cxl_general_media,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_GEN_MEDIA_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_GEN_MEDIA_UUID;
 
 		/* General Media */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -425,7 +425,7 @@ TRACE_EVENT(cxl_dram,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_DRAM_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_DRAM_UUID;
 
 		/* DRAM */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -573,7 +573,7 @@ TRACE_EVENT(cxl_memory_module,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_MEM_MODULE_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_MEM_MODULE_UUID;
 
 		/* Memory Module Event */
 		__entry->event_type = rec->event_type;
-- 
GitLab


From 54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 4 Feb 2024 12:20:36 +0000
Subject: [PATCH 3893/4076] Linux 6.8-rc3

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 113f7c762f0a0..a171eafce2a3b 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
-- 
GitLab


From 9cae43da9867412f8bd09aee5c8a8dc5e8dc3dc2 Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Thu, 1 Feb 2024 20:40:38 -0800
Subject: [PATCH 3894/4076] hv_netvsc: Register VF in netvsc_probe if
 NET_DEVICE_REGISTER missed

If hv_netvsc driver is unloaded and reloaded, the NET_DEVICE_REGISTER
handler cannot perform VF register successfully as the register call
is received before netvsc_probe is finished. This is because we
register register_netdevice_notifier() very early( even before
vmbus_driver_register()).
To fix this, we try to register each such matching VF( if it is visible
as a netdevice) at the end of netvsc_probe.

Cc: stable@vger.kernel.org
Fixes: 85520856466e ("hv_netvsc: Fix race of register_netdevice_notifier and VF register")
Suggested-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 82 +++++++++++++++++++++++++--------
 1 file changed, 62 insertions(+), 20 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 273bd8a20122c..11831a1c97623 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -42,6 +42,10 @@
 #define LINKCHANGE_INT (2 * HZ)
 #define VF_TAKEOVER_INT (HZ / 10)
 
+/* Macros to define the context of vf registration */
+#define VF_REG_IN_PROBE		1
+#define VF_REG_IN_NOTIFIER	2
+
 static unsigned int ring_size __ro_after_init = 128;
 module_param(ring_size, uint, 0444);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
@@ -2185,7 +2189,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
 }
 
 static int netvsc_vf_join(struct net_device *vf_netdev,
-			  struct net_device *ndev)
+			  struct net_device *ndev, int context)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	int ret;
@@ -2208,7 +2212,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto upper_link_failed;
 	}
 
-	schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+	/* If this registration is called from probe context vf_takeover
+	 * is taken care of later in probe itself.
+	 */
+	if (context == VF_REG_IN_NOTIFIER)
+		schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
 
 	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
 
@@ -2346,7 +2354,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev)
 	return NOTIFY_DONE;
 }
 
-static int netvsc_register_vf(struct net_device *vf_netdev)
+static int netvsc_register_vf(struct net_device *vf_netdev, int context)
 {
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device *netvsc_dev;
@@ -2386,7 +2394,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 
 	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
 
-	if (netvsc_vf_join(vf_netdev, ndev) != 0)
+	if (netvsc_vf_join(vf_netdev, ndev, context) != 0)
 		return NOTIFY_DONE;
 
 	dev_hold(vf_netdev);
@@ -2484,10 +2492,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
+static int check_dev_is_matching_vf(struct net_device *event_ndev)
+{
+	/* Skip NetVSC interfaces */
+	if (event_ndev->netdev_ops == &device_ops)
+		return -ENODEV;
+
+	/* Avoid non-Ethernet type devices */
+	if (event_ndev->type != ARPHRD_ETHER)
+		return -ENODEV;
+
+	/* Avoid Vlan dev with same MAC registering as VF */
+	if (is_vlan_dev(event_ndev))
+		return -ENODEV;
+
+	/* Avoid Bonding master dev with same MAC registering as VF */
+	if (netif_is_bond_master(event_ndev))
+		return -ENODEV;
+
+	return 0;
+}
+
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
 {
-	struct net_device *net = NULL;
+	struct net_device *net = NULL, *vf_netdev;
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device_info *device_info = NULL;
 	struct netvsc_device *nvdev;
@@ -2599,6 +2628,30 @@ static int netvsc_probe(struct hv_device *dev,
 	}
 
 	list_add(&net_device_ctx->list, &netvsc_dev_list);
+
+	/* When the hv_netvsc driver is unloaded and reloaded, the
+	 * NET_DEVICE_REGISTER for the vf device is replayed before probe
+	 * is complete. This is because register_netdevice_notifier() gets
+	 * registered before vmbus_driver_register() so that callback func
+	 * is set before probe and we don't miss events like NETDEV_POST_INIT
+	 * So, in this section we try to register the matching vf device that
+	 * is present as a netdevice, knowing that its register call is not
+	 * processed in the netvsc_netdev_notifier(as probing is progress and
+	 * get_netvsc_byslot fails).
+	 */
+	for_each_netdev(dev_net(net), vf_netdev) {
+		ret = check_dev_is_matching_vf(vf_netdev);
+		if (ret != 0)
+			continue;
+
+		if (net != get_netvsc_byslot(vf_netdev))
+			continue;
+
+		netvsc_prepare_bonding(vf_netdev);
+		netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
+		__netvsc_vf_setup(net, vf_netdev);
+		break;
+	}
 	rtnl_unlock();
 
 	netvsc_devinfo_put(device_info);
@@ -2754,28 +2807,17 @@ static int netvsc_netdev_event(struct notifier_block *this,
 			       unsigned long event, void *ptr)
 {
 	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+	int ret = 0;
 
-	/* Skip our own events */
-	if (event_dev->netdev_ops == &device_ops)
-		return NOTIFY_DONE;
-
-	/* Avoid non-Ethernet type devices */
-	if (event_dev->type != ARPHRD_ETHER)
-		return NOTIFY_DONE;
-
-	/* Avoid Vlan dev with same MAC registering as VF */
-	if (is_vlan_dev(event_dev))
-		return NOTIFY_DONE;
-
-	/* Avoid Bonding master dev with same MAC registering as VF */
-	if (netif_is_bond_master(event_dev))
+	ret = check_dev_is_matching_vf(event_dev);
+	if (ret != 0)
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_POST_INIT:
 		return netvsc_prepare_bonding(event_dev);
 	case NETDEV_REGISTER:
-		return netvsc_register_vf(event_dev);
+		return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER);
 	case NETDEV_UNREGISTER:
 		return netvsc_unregister_vf(event_dev);
 	case NETDEV_UP:
-- 
GitLab


From 1168491e7f53581ba7b6014a39a49cfbbb722feb Mon Sep 17 00:00:00 2001
From: Loic Prylli <lprylli@netflix.com>
Date: Fri, 3 Nov 2023 11:30:55 +0100
Subject: [PATCH 3895/4076] hwmon: (aspeed-pwm-tacho) mutex for tach reading

the ASPEED_PTCR_RESULT Register can only hold the result for a
single fan input. Adding a mutex to protect the register until the
reading is done.

Signed-off-by: Loic Prylli <lprylli@netflix.com>
Signed-off-by: Alexander Hansen <alexander.hansen@9elements.com>
Fixes: 2d7a548a3eff ("drivers: hwmon: Support for ASPEED PWM/Fan tach")
Link: https://lore.kernel.org/r/121d888762a1232ef403cf35230ccf7b3887083a.1699007401.git.alexander.hansen@9elements.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/aspeed-pwm-tacho.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c
index f6e1e55e82922..4acc1858d8acf 100644
--- a/drivers/hwmon/aspeed-pwm-tacho.c
+++ b/drivers/hwmon/aspeed-pwm-tacho.c
@@ -195,6 +195,8 @@ struct aspeed_pwm_tacho_data {
 	u8 fan_tach_ch_source[MAX_ASPEED_FAN_TACH_CHANNELS];
 	struct aspeed_cooling_device *cdev[8];
 	const struct attribute_group *groups[3];
+	/* protects access to shared ASPEED_PTCR_RESULT */
+	struct mutex tach_lock;
 };
 
 enum type { TYPEM, TYPEN, TYPEO };
@@ -529,6 +531,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
 	u8 fan_tach_ch_source, type, mode, both;
 	int ret;
 
+	mutex_lock(&priv->tach_lock);
+
 	regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0);
 	regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch);
 
@@ -546,6 +550,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
 		ASPEED_RPM_STATUS_SLEEP_USEC,
 		usec);
 
+	mutex_unlock(&priv->tach_lock);
+
 	/* return -ETIMEDOUT if we didn't get an answer. */
 	if (ret)
 		return ret;
@@ -915,6 +921,7 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
+	mutex_init(&priv->tach_lock);
 	priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs,
 			&aspeed_pwm_tacho_regmap_config);
 	if (IS_ERR(priv->regmap))
-- 
GitLab


From 4e440abc894585a34c2904a32cd54af1742311b3 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Fri, 2 Feb 2024 17:21:34 +0800
Subject: [PATCH 3896/4076] hwmon: (coretemp) Fix out-of-bounds memory access

Fix a bug that pdata->cpu_map[] is set before out-of-bounds check.
The problem might be triggered on systems with more than 128 cores per
package.

Fixes: 7108b80a542b ("hwmon/coretemp: Handle large core ID value")
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240202092144.71180-2-rui.zhang@intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/coretemp.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ba82d1e79c131..e78c769191118 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -509,18 +509,14 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	if (pkg_flag) {
 		attr_no = PKG_SYSFS_ATTR_NO;
 	} else {
-		index = ida_alloc(&pdata->ida, GFP_KERNEL);
+		index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL);
 		if (index < 0)
 			return index;
+
 		pdata->cpu_map[index] = topology_core_id(cpu);
 		attr_no = index + BASE_SYSFS_ATTR_NO;
 	}
 
-	if (attr_no > MAX_CORE_DATA - 1) {
-		err = -ERANGE;
-		goto ida_free;
-	}
-
 	tdata = init_temp_data(cpu, pkg_flag);
 	if (!tdata) {
 		err = -ENOMEM;
-- 
GitLab


From fdaf0c8629d4524a168cb9e4ad4231875749b28c Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Fri, 2 Feb 2024 17:21:35 +0800
Subject: [PATCH 3897/4076] hwmon: (coretemp) Fix bogus core_id to attr name
 mapping

Before commit 7108b80a542b ("hwmon/coretemp: Handle large core ID
value"), there is a fixed mapping between
1. cpu_core_id
2. the index in pdata->core_data[] array
3. the sysfs attr name, aka "tempX_"
The later two always equal cpu_core_id + 2.

After the commit, pdata->core_data[] index is got from ida so that it
can handle sparse core ids and support more cores within a package.

However, the commit erroneously maps the sysfs attr name to
pdata->core_data[] index instead of cpu_core_id + 2.

As a result, the code is not aligned with the comments, and brings user
visible changes in hwmon sysfs on systems with sparse core id.

For example, before commit 7108b80a542b ("hwmon/coretemp: Handle large
core ID value"),
/sys/class/hwmon/hwmon2/temp2_label:Core 0
/sys/class/hwmon/hwmon2/temp3_label:Core 1
/sys/class/hwmon/hwmon2/temp4_label:Core 2
/sys/class/hwmon/hwmon2/temp5_label:Core 3
/sys/class/hwmon/hwmon2/temp6_label:Core 4
/sys/class/hwmon/hwmon3/temp10_label:Core 8
/sys/class/hwmon/hwmon3/temp11_label:Core 9
after commit,
/sys/class/hwmon/hwmon2/temp2_label:Core 0
/sys/class/hwmon/hwmon2/temp3_label:Core 1
/sys/class/hwmon/hwmon2/temp4_label:Core 2
/sys/class/hwmon/hwmon2/temp5_label:Core 3
/sys/class/hwmon/hwmon2/temp6_label:Core 4
/sys/class/hwmon/hwmon2/temp7_label:Core 8
/sys/class/hwmon/hwmon2/temp8_label:Core 9

Restore the previous behavior and rework the code, comments and variable
names to avoid future confusions.

Fixes: 7108b80a542b ("hwmon/coretemp: Handle large core ID value")
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20240202092144.71180-3-rui.zhang@intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/coretemp.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index e78c769191118..95f4c0b00b2d8 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -419,7 +419,7 @@ static ssize_t show_temp(struct device *dev,
 }
 
 static int create_core_attrs(struct temp_data *tdata, struct device *dev,
-			     int attr_no)
+			     int index)
 {
 	int i;
 	static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev,
@@ -431,13 +431,20 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev,
 	};
 
 	for (i = 0; i < tdata->attr_size; i++) {
+		/*
+		 * We map the attr number to core id of the CPU
+		 * The attr number is always core id + 2
+		 * The Pkgtemp will always show up as temp1_*, if available
+		 */
+		int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2;
+
 		snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH,
 			 "temp%d_%s", attr_no, suffixes[i]);
 		sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr);
 		tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i];
 		tdata->sd_attrs[i].dev_attr.attr.mode = 0444;
 		tdata->sd_attrs[i].dev_attr.show = rd_ptr[i];
-		tdata->sd_attrs[i].index = attr_no;
+		tdata->sd_attrs[i].index = index;
 		tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr;
 	}
 	tdata->attr_group.attrs = tdata->attrs;
@@ -495,26 +502,25 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	struct platform_data *pdata = platform_get_drvdata(pdev);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 eax, edx;
-	int err, index, attr_no;
+	int err, index;
 
 	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 		return 0;
 
 	/*
-	 * Find attr number for sysfs:
-	 * We map the attr number to core id of the CPU
-	 * The attr number is always core id + 2
-	 * The Pkgtemp will always show up as temp1_*, if available
+	 * Get the index of tdata in pdata->core_data[]
+	 * tdata for package: pdata->core_data[1]
+	 * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1]
 	 */
 	if (pkg_flag) {
-		attr_no = PKG_SYSFS_ATTR_NO;
+		index = PKG_SYSFS_ATTR_NO;
 	} else {
 		index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL);
 		if (index < 0)
 			return index;
 
 		pdata->cpu_map[index] = topology_core_id(cpu);
-		attr_no = index + BASE_SYSFS_ATTR_NO;
+		index += BASE_SYSFS_ATTR_NO;
 	}
 
 	tdata = init_temp_data(cpu, pkg_flag);
@@ -540,20 +546,20 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 		if (get_ttarget(tdata, &pdev->dev) >= 0)
 			tdata->attr_size++;
 
-	pdata->core_data[attr_no] = tdata;
+	pdata->core_data[index] = tdata;
 
 	/* Create sysfs interfaces */
-	err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no);
+	err = create_core_attrs(tdata, pdata->hwmon_dev, index);
 	if (err)
 		goto exit_free;
 
 	return 0;
 exit_free:
-	pdata->core_data[attr_no] = NULL;
+	pdata->core_data[index] = NULL;
 	kfree(tdata);
 ida_free:
 	if (!pkg_flag)
-		ida_free(&pdata->ida, index);
+		ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO);
 	return err;
 }
 
-- 
GitLab


From 34cf8c657cf0365791cdc658ddbca9cc907726ce Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Fri, 2 Feb 2024 17:21:36 +0800
Subject: [PATCH 3898/4076] hwmon: (coretemp) Enlarge per package core count
 limit

Currently, coretemp driver supports only 128 cores per package.
This loses some core temperature information on systems that have more
than 128 cores per package.
 [   58.685033] coretemp coretemp.0: Adding Core 128 failed
 [   58.692009] coretemp coretemp.0: Adding Core 129 failed
 ...

Enlarge the limitation to 512 because there are platforms with more than
256 cores per package.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20240202092144.71180-4-rui.zhang@intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/coretemp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 95f4c0b00b2d8..b8fc8d1ef20df 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -41,7 +41,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 
 #define PKG_SYSFS_ATTR_NO	1	/* Sysfs attribute for package temp */
 #define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
-#define NUM_REAL_CORES		128	/* Number of Real cores per cpu */
+#define NUM_REAL_CORES		512	/* Number of Real cores per cpu */
 #define CORETEMP_NAME_LENGTH	28	/* String Length of attrs */
 #define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
-- 
GitLab


From eef00a82c568944f113f2de738156ac591bbd5cd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Feb 2024 09:54:04 +0000
Subject: [PATCH 3899/4076] inet: read sk->sk_family once in inet_recv_error()

inet_recv_error() is called without holding the socket lock.

IPv6 socket could mutate to IPv4 with IPV6_ADDRFORM
socket option and trigger a KCSAN warning.

Fixes: f4713a3dfad0 ("net-timestamp: make tcp_recvmsg call ipv6_recv_error for AF_INET6 socks")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4e635dd3d3c8c..a5a820ee20266 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1628,10 +1628,12 @@ EXPORT_SYMBOL(inet_current_timestamp);
 
 int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
-	if (sk->sk_family == AF_INET)
+	unsigned int family = READ_ONCE(sk->sk_family);
+
+	if (family == AF_INET)
 		return ip_recv_error(sk, msg, len, addr_len);
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6)
+	if (family == AF_INET6)
 		return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len);
 #endif
 	return -EINVAL;
-- 
GitLab


From 1a00897e5e96c29b21580dfcfec168dc16c67469 Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Fri, 4 Aug 2023 12:05:44 +0800
Subject: [PATCH 3900/4076] drm/i915: Replace dead 01.org link

01.org is dead so replace old gvt link with current wiki page.

Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Zhi Wang <zhi.wang.linux@gmail.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20230804040544.1972958-1-zhenyuw@linux.intel.com
---
 MAINTAINERS                      | 2 +-
 drivers/gpu/drm/i915/Kconfig     | 2 +-
 drivers/gpu/drm/i915/intel_gvt.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a692..03fbe24bf40d8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10804,7 +10804,7 @@ M:	Zhi Wang <zhi.a.wang@intel.com>
 L:	intel-gvt-dev@lists.freedesktop.org
 L:	intel-gfx@lists.freedesktop.org
 S:	Supported
-W:	https://01.org/igvt-g
+W:	https://github.com/intel/gvt-linux/wiki
 T:	git https://github.com/intel/gvt-linux.git
 F:	drivers/gpu/drm/i915/gvt/
 
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index b5d6e3352071f..3089029abba48 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -140,7 +140,7 @@ config DRM_I915_GVT_KVMGT
 
 	  Note that this driver only supports newer device from Broadwell on.
 	  For further information and setup guide, you can visit:
-	  http://01.org/igvt-g.
+	  https://github.com/intel/gvt-linux/wiki.
 
 	  If in doubt, say "N".
 
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index e98b6d69a91ab..9b6d87c8b5831 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -41,7 +41,7 @@
  * To virtualize GPU resources GVT-g driver depends on hypervisor technology
  * e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability
  * and be virtualized within GVT-g device module. More architectural design
- * doc is available on https://01.org/group/2230/documentation-list.
+ * doc is available on https://github.com/intel/gvt-linux/wiki.
  */
 
 static LIST_HEAD(intel_gvt_devices);
-- 
GitLab


From 47caa96478b99d6d1199b89467cc3e5a6cc754ee Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 26 Jan 2024 11:41:47 +0300
Subject: [PATCH 3901/4076] drm/i915/gvt: Fix uninitialized variable in
 handle_mmio()

This code prints the wrong variable in the warning message.  It should
print "i" instead of "info->offset".  On the first iteration "info" is
uninitialized leading to a crash and on subsequent iterations it prints
the previous offset instead of the current one.

Fixes: e0f74ed4634d ("i915/gvt: Separate the MMIO tracking table from GVT-g")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/11957c20-b178-4027-9b0a-e32e9591dd7c@moroto.mountain
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90f6c1ece57d4..efcb00472be24 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2849,8 +2849,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset,
 	for (i = start; i < end; i += 4) {
 		p = intel_gvt_find_mmio_info(gvt, i);
 		if (p) {
-			WARN(1, "dup mmio definition offset %x\n",
-				info->offset);
+			WARN(1, "dup mmio definition offset %x\n", i);
 
 			/* We return -EEXIST here to make GVT-g load fail.
 			 * So duplicated MMIO can be found as soon as
-- 
GitLab


From 44e4192f88978e32e4ac08b27141f3767366f79b Mon Sep 17 00:00:00 2001
From: Zhi Wang <zhi.wang.linux@gmail.com>
Date: Tue, 30 Jan 2024 21:27:43 +0000
Subject: [PATCH 3902/4076] MAINTAINERS: Update Zhi Wang's email address

Update my email address to zhi.wang.linux@gmail.com.

CC: Zhenyu Wang <zhenyuw@linux.intel.com>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhi Wang <zhi.wang.linux@gmail.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20240130212743.7727-1-zhi.wang.linux@gmail.com
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 03fbe24bf40d8..052149d304baa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10800,7 +10800,7 @@ F:	drivers/gpio/gpio-tangier.h
 
 INTEL GVT-g DRIVERS (Intel GPU Virtualization)
 M:	Zhenyu Wang <zhenyuw@linux.intel.com>
-M:	Zhi Wang <zhi.a.wang@intel.com>
+M:	Zhi Wang <zhi.wang.linux@gmail.com>
 L:	intel-gvt-dev@lists.freedesktop.org
 L:	intel-gfx@lists.freedesktop.org
 S:	Supported
-- 
GitLab


From dd839f31d7cd5e04f4111a219024268c6f6973f0 Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@grsecurity.net>
Date: Sun, 4 Feb 2024 08:51:52 +0100
Subject: [PATCH 3903/4076] bcachefs: install fd later to avoid race with close

Calling fd_install() makes a file reachable for userland, including the
possibility to close the file descriptor, which leads to calling its
'release' hook. If that happens before the code had a chance to bump the
reference of the newly created task struct, the release callback will
call put_task_struct() too early, leading to the premature destruction
of the kernel thread.

Avoid that race by calling fd_install() later, after all the setup is
done.

Fixes: 1c6fdbd8f246 ("bcachefs: Initial commit")
Signed-off-by: Mathias Krause <minipli@grsecurity.net>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/thread_with_file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index b1c867aa2b58e..9220d7de10db6 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -53,9 +53,9 @@ int bch2_run_thread_with_file(struct thread_with_file *thr,
 	if (ret)
 		goto err;
 
-	fd_install(fd, file);
 	get_task_struct(thr->task);
 	wake_up_process(thr->task);
+	fd_install(fd, file);
 	return fd;
 err:
 	if (fd >= 0)
-- 
GitLab


From 7b508b323b2ec45be59769bd4e4aeba729c52cf6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 1 Feb 2024 21:01:02 -0500
Subject: [PATCH 3904/4076] bcachefs: time_stats: Check for last_event == 0
 when updating freq stats

This fixes spurious outliers in the frequency stats.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/util.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index 56b815fd9fc6e..231003b405efc 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -418,14 +418,15 @@ static inline void bch2_time_stats_update_one(struct bch2_time_stats *stats,
 		bch2_quantiles_update(&stats->quantiles, duration);
 	}
 
-	if (time_after64(end, stats->last_event)) {
+	if (stats->last_event && time_after64(end, stats->last_event)) {
 		freq = end - stats->last_event;
 		mean_and_variance_update(&stats->freq_stats, freq);
 		mean_and_variance_weighted_update(&stats->freq_stats_weighted, freq);
 		stats->max_freq = max(stats->max_freq, freq);
 		stats->min_freq = min(stats->min_freq, freq);
-		stats->last_event = end;
 	}
+
+	stats->last_event = end;
 }
 
 static void __bch2_time_stats_clear_buffer(struct bch2_time_stats *stats,
-- 
GitLab


From 1ad55cecf22f05f1c884adf63cc09d3c3e609ebf Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 5 Feb 2024 09:11:07 +0100
Subject: [PATCH 3905/4076] x86/efistub: Use 1:1 file:memory mapping for
 PE/COFF .compat section

The .compat section is a dummy PE section that contains the address of
the 32-bit entrypoint of the 64-bit kernel image if it is bootable from
32-bit firmware (i.e., CONFIG_EFI_MIXED=y)

This section is only 8 bytes in size and is only referenced from the
loader, and so it is placed at the end of the memory view of the image,
to avoid the need for padding it to 4k, which is required for sections
appearing in the middle of the image.

Unfortunately, this violates the PE/COFF spec, and even if most EFI
loaders will work correctly (including the Tianocore reference
implementation), PE loaders do exist that reject such images, on the
basis that both the file and memory views of the file contents should be
described by the section headers in a monotonically increasing manner
without leaving any gaps.

So reorganize the sections to avoid this issue. This results in a slight
padding overhead (< 4k) which can be avoided if desired by disabling
CONFIG_EFI_MIXED (which is only needed in rare cases these days)

Fixes: 3e3eabe26dc8 ("x86/boot: Increase section and file alignment to 4k/512")
Reported-by: Mike Beaton <mjsbeaton@gmail.com>
Link: https://lkml.kernel.org/r/CAHzAAWQ6srV6LVNdmfbJhOwhBw5ZzxxZZ07aHt9oKkfYAdvuQQ%40mail.gmail.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/boot/header.S | 14 ++++++--------
 arch/x86/boot/setup.ld |  6 +++---
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b2771710ed989..a1bbedd989e42 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -106,8 +106,7 @@ extra_header_fields:
 	.word	0				# MinorSubsystemVersion
 	.long	0				# Win32VersionValue
 
-	.long	setup_size + ZO__end + pecompat_vsize
-						# SizeOfImage
+	.long	setup_size + ZO__end		# SizeOfImage
 
 	.long	salign				# SizeOfHeaders
 	.long	0				# CheckSum
@@ -143,7 +142,7 @@ section_table:
 	.ascii	".setup"
 	.byte	0
 	.byte	0
-	.long	setup_size - salign 		# VirtualSize
+	.long	pecompat_fstart - salign 	# VirtualSize
 	.long	salign				# VirtualAddress
 	.long	pecompat_fstart - salign	# SizeOfRawData
 	.long	salign				# PointerToRawData
@@ -156,8 +155,8 @@ section_table:
 #ifdef CONFIG_EFI_MIXED
 	.asciz	".compat"
 
-	.long	8				# VirtualSize
-	.long	setup_size + ZO__end		# VirtualAddress
+	.long	pecompat_fsize			# VirtualSize
+	.long	pecompat_fstart			# VirtualAddress
 	.long	pecompat_fsize			# SizeOfRawData
 	.long	pecompat_fstart			# PointerToRawData
 
@@ -172,17 +171,16 @@ section_table:
 	 * modes this image supports.
 	 */
 	.pushsection ".pecompat", "a", @progbits
-	.balign	falign
-	.set	pecompat_vsize, salign
+	.balign	salign
 	.globl	pecompat_fstart
 pecompat_fstart:
 	.byte	0x1				# Version
 	.byte	8				# Size
 	.word	IMAGE_FILE_MACHINE_I386		# PE machine type
 	.long	setup_size + ZO_efi32_pe_entry	# Entrypoint
+	.byte	0x0				# Sentinel
 	.popsection
 #else
-	.set	pecompat_vsize, 0
 	.set	pecompat_fstart, setup_size
 #endif
 	.ascii	".text"
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 83bb7efad8ae7..3a2d1360abb01 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -24,6 +24,9 @@ SECTIONS
 	.text		: { *(.text .text.*) }
 	.text32		: { *(.text32) }
 
+	.pecompat	: { *(.pecompat) }
+	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
 	. = ALIGN(16);
 	.rodata		: { *(.rodata*) }
 
@@ -36,9 +39,6 @@ SECTIONS
 	. = ALIGN(16);
 	.data		: { *(.data*) }
 
-	.pecompat	: { *(.pecompat) }
-	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
-
 	.signature	: {
 		setup_sig = .;
 		LONG(0x5a5aaa55)
-- 
GitLab


From b3d4f7f2288901ed2392695919b3c0e24c1b4084 Mon Sep 17 00:00:00 2001
From: Daniel Basilio <daniel.basilio@corigine.com>
Date: Fri, 2 Feb 2024 13:37:17 +0200
Subject: [PATCH 3906/4076] nfp: use correct macro for LengthSelect in BAR
 config

The 1st and 2nd expansion BAR configuration registers are configured,
when the driver starts up, in variables 'barcfg_msix_general' and
'barcfg_msix_xpb', respectively. The 'LengthSelect' field is ORed in
from bit 0, which is incorrect. The 'LengthSelect' field should
start from bit 27.

This has largely gone un-noticed because
NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT happens to be 0.

Fixes: 4cb584e0ee7d ("nfp: add CPP access core")
Cc: stable@vger.kernel.org # 4.11+
Signed-off-by: Daniel Basilio <daniel.basilio@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 33b4c28563162..3f10c5365c80e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -537,11 +537,13 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface)
 	const u32 barcfg_msix_general =
 		NFP_PCIE_BAR_PCIE2CPP_MapType(
 			NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) |
-		NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT;
+		NFP_PCIE_BAR_PCIE2CPP_LengthSelect(
+			NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT);
 	const u32 barcfg_msix_xpb =
 		NFP_PCIE_BAR_PCIE2CPP_MapType(
 			NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) |
-		NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT |
+		NFP_PCIE_BAR_PCIE2CPP_LengthSelect(
+			NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) |
 		NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress(
 			NFP_CPP_TARGET_ISLAND_XPB);
 	const u32 barcfg_explicit[4] = {
-- 
GitLab


From 1a1c13303ff6d64e6f718dc8aa614e580ca8d9b4 Mon Sep 17 00:00:00 2001
From: Daniel de Villiers <daniel.devilliers@corigine.com>
Date: Fri, 2 Feb 2024 13:37:18 +0200
Subject: [PATCH 3907/4076] nfp: flower: prevent re-adding mac index for bonded
 port

When physical ports are reset (either through link failure or manually
toggled down and up again) that are slaved to a Linux bond with a tunnel
endpoint IP address on the bond device, not all tunnel packets arriving
on the bond port are decapped as expected.

The bond dev assigns the same MAC address to itself and each of its
slaves. When toggling a slave device, the same MAC address is therefore
offloaded to the NFP multiple times with different indexes.

The issue only occurs when re-adding the shared mac. The
nfp_tunnel_add_shared_mac() function has a conditional check early on
that checks if a mac entry already exists and if that mac entry is
global: (entry && nfp_tunnel_is_mac_idx_global(entry->index)). In the
case of a bonded device (For example br-ex), the mac index is obtained,
and no new index is assigned.

We therefore modify the conditional in nfp_tunnel_add_shared_mac() to
check if the port belongs to the LAG along with the existing checks to
prevent a new global mac index from being re-assigned to the slave port.

Fixes: 20cce8865098 ("nfp: flower: enable MAC address sharing for offloadable devs")
CC: stable@vger.kernel.org # 5.1+
Signed-off-by: Daniel de Villiers <daniel.devilliers@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index e522845c7c211..0d7d138d6e0d7 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -1084,7 +1084,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev,
 	u16 nfp_mac_idx = 0;
 
 	entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr);
-	if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) {
+	if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) {
 		if (entry->bridge_count ||
 		    !nfp_flower_is_supported_bridge(netdev)) {
 			nfp_tunnel_offloaded_macs_inc_ref_and_link(entry,
-- 
GitLab


From 0f4d6f011bca0df2051532b41b596366aa272019 Mon Sep 17 00:00:00 2001
From: James Hershaw <james.hershaw@corigine.com>
Date: Fri, 2 Feb 2024 13:37:19 +0200
Subject: [PATCH 3908/4076] nfp: enable NETDEV_XDP_ACT_REDIRECT feature flag

Enable previously excluded xdp feature flag for NFD3 devices. This
feature flag is required in order to bind nfp interfaces to an xdp
socket and the nfp driver does in fact support the feature.

Fixes: 66c0e13ad236 ("drivers: net: turn on XDP features")
Cc: stable@vger.kernel.org # 6.3+
Signed-off-by: James Hershaw <james.hershaw@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 3b3210d823e80..f28e769e6fdad 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2776,6 +2776,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 	case NFP_NFD_VER_NFD3:
 		netdev->netdev_ops = &nfp_nfd3_netdev_ops;
 		netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
+		netdev->xdp_features |= NETDEV_XDP_ACT_REDIRECT;
 		break;
 	case NFP_NFD_VER_NFDK:
 		netdev->netdev_ops = &nfp_nfdk_netdev_ops;
-- 
GitLab


From f31041417bf7f4a4df8b3bfb52cb31bbe805b934 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Feb 2024 15:19:13 +0000
Subject: [PATCH 3909/4076] rxrpc: Fix generation of serial numbers to skip
 zero

In the Rx protocol, every packet generated is marked with a per-connection
monotonically increasing serial number.  This number can be referenced in
an ACK packet generated in response to an incoming packet - thereby
allowing the sender to use this for RTT determination, amongst other
things.

However, if the reference field in the ACK is zero, it doesn't refer to any
incoming packet (it could be a ping to find out if a packet got lost, for
example) - so we shouldn't generate zero serial numbers.

Fix the generation of serial numbers to retry if it comes up with a zero.

Furthermore, since the serial numbers are only ever allocated within the
I/O thread this connection is bound to, there's no need for atomics so
remove that too.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/ar-internal.h | 16 +++++++++++++++-
 net/rxrpc/conn_event.c  |  2 +-
 net/rxrpc/output.c      |  8 ++++----
 net/rxrpc/proc.c        |  2 +-
 net/rxrpc/rxkad.c       |  4 ++--
 5 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index dbeb75c298573..31b0dd8c9b2d7 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -510,7 +510,7 @@ struct rxrpc_connection {
 	enum rxrpc_call_completion completion;	/* Completion condition */
 	s32			abort_code;	/* Abort code of connection abort */
 	int			debug_id;	/* debug ID for printks */
-	atomic_t		serial;		/* packet serial number counter */
+	rxrpc_serial_t		tx_serial;	/* Outgoing packet serial number counter */
 	unsigned int		hi_serial;	/* highest serial number received */
 	u32			service_id;	/* Service ID, possibly upgraded */
 	u32			security_level;	/* Security level selected */
@@ -822,6 +822,20 @@ static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb)
 
 #include <trace/events/rxrpc.h>
 
+/*
+ * Allocate the next serial number on a connection.  0 must be skipped.
+ */
+static inline rxrpc_serial_t rxrpc_get_next_serial(struct rxrpc_connection *conn)
+{
+	rxrpc_serial_t serial;
+
+	serial = conn->tx_serial;
+	if (serial == 0)
+		serial = 1;
+	conn->tx_serial = serial + 1;
+	return serial;
+}
+
 /*
  * af_rxrpc.c
  */
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 95f4bc206b3dc..ec5eae60ab0c4 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -117,7 +117,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	iov[2].iov_base	= &ack_info;
 	iov[2].iov_len	= sizeof(ack_info);
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 
 	pkt.whdr.epoch		= htonl(conn->proto.epoch);
 	pkt.whdr.cid		= htonl(conn->proto.cid | channel);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index a0906145e8293..4a292f860ae37 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -216,7 +216,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	iov[0].iov_len	= sizeof(txb->wire) + sizeof(txb->ack) + n;
 	len = iov[0].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	txb->wire.serial = htonl(serial);
 	trace_rxrpc_tx_ack(call->debug_id, serial,
 			   ntohl(txb->ack.firstPacket),
@@ -302,7 +302,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	iov[0].iov_base	= &pkt;
 	iov[0].iov_len	= sizeof(pkt);
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	pkt.whdr.serial = htonl(serial);
 
 	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt));
@@ -334,7 +334,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	_enter("%x,{%d}", txb->seq, txb->len);
 
 	/* Each transmission of a Tx packet needs a new serial number */
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	txb->wire.serial = htonl(serial);
 
 	if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) &&
@@ -558,7 +558,7 @@ void rxrpc_send_conn_abort(struct rxrpc_connection *conn)
 
 	len = iov[0].iov_len + iov[1].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
 	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 6c86cbb98d1d6..26dc2f26d92d8 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -181,7 +181,7 @@ print:
 		   atomic_read(&conn->active),
 		   state,
 		   key_serial(conn->key),
-		   atomic_read(&conn->serial),
+		   conn->tx_serial,
 		   conn->hi_serial,
 		   conn->channels[0].call_id,
 		   conn->channels[1].call_id,
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index b52dedcebce0a..6b32d61d4cdc4 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -664,7 +664,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 
 	len = iov[0].iov_len + iov[1].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
 	ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len);
@@ -721,7 +721,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 
 	len = iov[0].iov_len + iov[1].iov_len + iov[2].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
 	rxrpc_local_dont_fragment(conn->local, false);
-- 
GitLab


From e7870cf13d20f56bfc19f9c3e89707c69cf104ef Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Feb 2024 15:19:14 +0000
Subject: [PATCH 3910/4076] rxrpc: Fix delayed ACKs to not set the reference
 serial number

Fix the construction of delayed ACKs to not set the reference serial number
as they can't be used as an RTT reference.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/ar-internal.h | 1 -
 net/rxrpc/call_event.c  | 6 +-----
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 31b0dd8c9b2d7..b4ab26c3718a4 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -696,7 +696,6 @@ struct rxrpc_call {
 	/* Receive-phase ACK management (ACKs we send). */
 	u8			ackr_reason;	/* reason to ACK */
 	u16			ackr_sack_base;	/* Starting slot in SACK table ring */
-	rxrpc_serial_t		ackr_serial;	/* serial of packet being ACK'd */
 	rxrpc_seq_t		ackr_window;	/* Base of SACK window */
 	rxrpc_seq_t		ackr_wtop;	/* Base of SACK window */
 	unsigned int		ackr_nr_unacked; /* Number of unacked packets */
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index e363f21a20141..c61efe08695d7 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -43,8 +43,6 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial,
 	unsigned long expiry = rxrpc_soft_ack_delay;
 	unsigned long now = jiffies, ack_at;
 
-	call->ackr_serial = serial;
-
 	if (rxrpc_soft_ack_delay < expiry)
 		expiry = rxrpc_soft_ack_delay;
 	if (call->peer->srtt_us != 0)
@@ -373,7 +371,6 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call)
 bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	unsigned long now, next, t;
-	rxrpc_serial_t ackr_serial;
 	bool resend = false, expired = false;
 	s32 abort_code;
 
@@ -423,8 +420,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 	if (time_after_eq(now, t)) {
 		trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
 		cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET);
-		ackr_serial = xchg(&call->ackr_serial, 0);
-		rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial,
+		rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0,
 			       rxrpc_propose_ack_ping_for_lost_ack);
 	}
 
-- 
GitLab


From 6f769f22822aa4124b556339781b04d810f0e038 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Feb 2024 15:19:15 +0000
Subject: [PATCH 3911/4076] rxrpc: Fix response to PING RESPONSE ACKs to a dead
 call

Stop rxrpc from sending a DUP ACK in response to a PING RESPONSE ACK on a
dead call.  We may have initiated the ping but the call may have beaten the
response to completion.

Fixes: 18bfeba50dfd ("rxrpc: Perform terminal call ACK/ABORT retransmission from conn processor")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/conn_event.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index ec5eae60ab0c4..1f251d758cb9d 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -95,6 +95,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 
 	_enter("%d", conn->debug_id);
 
+	if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) {
+		if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
+				  &pkt.ack, sizeof(pkt.ack)) < 0)
+			return;
+		if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE)
+			return;
+	}
+
 	chan = &conn->channels[channel];
 
 	/* If the last call got moved on whilst we were waiting to run, just
-- 
GitLab


From 41b7fa157ea1c8c3a575ca7f5f32034de9bee3ae Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Feb 2024 15:19:16 +0000
Subject: [PATCH 3912/4076] rxrpc: Fix counting of new acks and nacks

Fix the counting of new acks and nacks when parsing a packet - something
that is used in congestion control.

As the code stands, it merely notes if there are any nacks whereas what we
really should do is compare the previous SACK table to the new one,
assuming we get two successive ACK packets with nacks in them.  However, we
really don't want to do that if we can avoid it as the tables might not
correspond directly as one may be shifted from the other - something that
will only get harder to deal with once extended ACK tables come into full
use (with a capacity of up to 8192).

Instead, count the number of nacks shifted out of the old SACK, the number
of nacks retained in the portion still active and the number of new acks
and nacks in the new table then calculate what we need.

Note this ends up a bit of an estimate as the Rx protocol allows acks to be
withdrawn by the receiver and packets requested to be retransmitted.

Fixes: d57a3a151660 ("rxrpc: Save last ACK's SACK table rather than marking txbufs")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/rxrpc.h |   8 ++-
 net/rxrpc/ar-internal.h      |  20 ++++--
 net/rxrpc/call_event.c       |   6 +-
 net/rxrpc/call_object.c      |   1 +
 net/rxrpc/input.c            | 115 +++++++++++++++++++++++++++++------
 5 files changed, 122 insertions(+), 28 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 4c1ef7b3705c2..87b8de9b6c1c4 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -128,6 +128,7 @@
 	EM(rxrpc_skb_eaten_by_unshare_nomem,	"ETN unshar-nm") \
 	EM(rxrpc_skb_get_conn_secured,		"GET conn-secd") \
 	EM(rxrpc_skb_get_conn_work,		"GET conn-work") \
+	EM(rxrpc_skb_get_last_nack,		"GET last-nack") \
 	EM(rxrpc_skb_get_local_work,		"GET locl-work") \
 	EM(rxrpc_skb_get_reject_work,		"GET rej-work ") \
 	EM(rxrpc_skb_get_to_recvmsg,		"GET to-recv  ") \
@@ -141,6 +142,7 @@
 	EM(rxrpc_skb_put_error_report,		"PUT error-rep") \
 	EM(rxrpc_skb_put_input,			"PUT input    ") \
 	EM(rxrpc_skb_put_jumbo_subpacket,	"PUT jumbo-sub") \
+	EM(rxrpc_skb_put_last_nack,		"PUT last-nack") \
 	EM(rxrpc_skb_put_purge,			"PUT purge    ") \
 	EM(rxrpc_skb_put_rotate,		"PUT rotate   ") \
 	EM(rxrpc_skb_put_unknown,		"PUT unknown  ") \
@@ -1552,7 +1554,7 @@ TRACE_EVENT(rxrpc_congest,
 		    memcpy(&__entry->sum, summary, sizeof(__entry->sum));
 			   ),
 
-	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
+	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u,%u b=%u u=%u d=%u l=%x%s%s%s",
 		      __entry->call,
 		      __entry->ack_serial,
 		      __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names),
@@ -1560,9 +1562,9 @@ TRACE_EVENT(rxrpc_congest,
 		      __print_symbolic(__entry->sum.mode, rxrpc_congest_modes),
 		      __entry->sum.cwnd,
 		      __entry->sum.ssthresh,
-		      __entry->sum.nr_acks, __entry->sum.saw_nacks,
+		      __entry->sum.nr_acks, __entry->sum.nr_retained_nacks,
 		      __entry->sum.nr_new_acks,
-		      __entry->sum.nr_rot_new_acks,
+		      __entry->sum.nr_new_nacks,
 		      __entry->top - __entry->hard_ack,
 		      __entry->sum.cumulative_acks,
 		      __entry->sum.dup_acks,
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index b4ab26c3718a4..7818aae1be8e0 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -199,11 +199,19 @@ struct rxrpc_host_header {
  */
 struct rxrpc_skb_priv {
 	struct rxrpc_connection *conn;	/* Connection referred to (poke packet) */
-	u16		offset;		/* Offset of data */
-	u16		len;		/* Length of data */
-	u8		flags;
+	union {
+		struct {
+			u16		offset;		/* Offset of data */
+			u16		len;		/* Length of data */
+			u8		flags;
 #define RXRPC_RX_VERIFIED	0x01
-
+		};
+		struct {
+			rxrpc_seq_t	first_ack;	/* First packet in acks table */
+			u8		nr_acks;	/* Number of acks+nacks */
+			u8		nr_nacks;	/* Number of nacks */
+		};
+	};
 	struct rxrpc_host_header hdr;	/* RxRPC packet header from this packet */
 };
 
@@ -692,6 +700,7 @@ struct rxrpc_call {
 	u8			cong_dup_acks;	/* Count of ACKs showing missing packets */
 	u8			cong_cumul_acks; /* Cumulative ACK count */
 	ktime_t			cong_tstamp;	/* Last time cwnd was changed */
+	struct sk_buff		*cong_last_nack; /* Last ACK with nacks received */
 
 	/* Receive-phase ACK management (ACKs we send). */
 	u8			ackr_reason;	/* reason to ACK */
@@ -729,7 +738,8 @@ struct rxrpc_call {
 struct rxrpc_ack_summary {
 	u16			nr_acks;		/* Number of ACKs in packet */
 	u16			nr_new_acks;		/* Number of new ACKs in packet */
-	u16			nr_rot_new_acks;	/* Number of rotated new ACKs */
+	u16			nr_new_nacks;		/* Number of new nacks in packet */
+	u16			nr_retained_nacks;	/* Number of nacks retained between ACKs */
 	u8			ack_reason;
 	bool			saw_nacks;		/* Saw NACKs in packet */
 	bool			new_low_nack;		/* T if new low NACK found */
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index c61efe08695d7..0f78544d043be 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -112,6 +112,7 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
 void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 {
 	struct rxrpc_ackpacket *ack = NULL;
+	struct rxrpc_skb_priv *sp;
 	struct rxrpc_txbuf *txb;
 	unsigned long resend_at;
 	rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted);
@@ -139,14 +140,15 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 	 * explicitly NAK'd packets.
 	 */
 	if (ack_skb) {
+		sp = rxrpc_skb(ack_skb);
 		ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header);
 
-		for (i = 0; i < ack->nAcks; i++) {
+		for (i = 0; i < sp->nr_acks; i++) {
 			rxrpc_seq_t seq;
 
 			if (ack->acks[i] & 1)
 				continue;
-			seq = ntohl(ack->firstPacket) + i;
+			seq = sp->first_ack + i;
 			if (after(txb->seq, transmitted))
 				break;
 			if (after(txb->seq, seq))
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 0943e54370ba0..9fc9a6c3f6858 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -686,6 +686,7 @@ static void rxrpc_destroy_call(struct work_struct *work)
 
 	del_timer_sync(&call->timer);
 
+	rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
 	rxrpc_cleanup_ring(call);
 	while ((txb = list_first_entry_or_null(&call->tx_sendmsg,
 					       struct rxrpc_txbuf, call_link))) {
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 92495e73b8699..9691de00ade75 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -45,11 +45,9 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
 	}
 
 	cumulative_acks += summary->nr_new_acks;
-	cumulative_acks += summary->nr_rot_new_acks;
 	if (cumulative_acks > 255)
 		cumulative_acks = 255;
 
-	summary->mode = call->cong_mode;
 	summary->cwnd = call->cong_cwnd;
 	summary->ssthresh = call->cong_ssthresh;
 	summary->cumulative_acks = cumulative_acks;
@@ -151,6 +149,7 @@ out_no_clear_ca:
 		cwnd = RXRPC_TX_MAX_WINDOW;
 	call->cong_cwnd = cwnd;
 	call->cong_cumul_acks = cumulative_acks;
+	summary->mode = call->cong_mode;
 	trace_rxrpc_congest(call, summary, acked_serial, change);
 	if (resend)
 		rxrpc_resend(call, skb);
@@ -213,7 +212,6 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 	list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) {
 		if (before_eq(txb->seq, call->acks_hard_ack))
 			continue;
-		summary->nr_rot_new_acks++;
 		if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) {
 			set_bit(RXRPC_CALL_TX_LAST, &call->flags);
 			rot_last = true;
@@ -254,6 +252,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
 {
 	ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
 
+	if (unlikely(call->cong_last_nack)) {
+		rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+		call->cong_last_nack = NULL;
+	}
+
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
 	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
@@ -702,6 +705,43 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 		wake_up(&call->waitq);
 }
 
+/*
+ * Determine how many nacks from the previous ACK have now been satisfied.
+ */
+static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call,
+					      struct rxrpc_ack_summary *summary,
+					      rxrpc_seq_t seq)
+{
+	struct sk_buff *skb = call->cong_last_nack;
+	struct rxrpc_ackpacket ack;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	unsigned int i, new_acks = 0, retained_nacks = 0;
+	rxrpc_seq_t old_seq = sp->first_ack;
+	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(ack);
+
+	if (after_eq(seq, old_seq + sp->nr_acks)) {
+		summary->nr_new_acks += sp->nr_nacks;
+		summary->nr_new_acks += seq - (old_seq + sp->nr_acks);
+		summary->nr_retained_nacks = 0;
+	} else if (seq == old_seq) {
+		summary->nr_retained_nacks = sp->nr_nacks;
+	} else {
+		for (i = 0; i < sp->nr_acks; i++) {
+			if (acks[i] == RXRPC_ACK_TYPE_NACK) {
+				if (before(old_seq + i, seq))
+					new_acks++;
+				else
+					retained_nacks++;
+			}
+		}
+
+		summary->nr_new_acks += new_acks;
+		summary->nr_retained_nacks = retained_nacks;
+	}
+
+	return old_seq + sp->nr_acks;
+}
+
 /*
  * Process individual soft ACKs.
  *
@@ -711,25 +751,51 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
  * the timer on the basis that the peer might just not have processed them at
  * the time the ACK was sent.
  */
-static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
-				  rxrpc_seq_t seq, int nr_acks,
-				  struct rxrpc_ack_summary *summary)
+static void rxrpc_input_soft_acks(struct rxrpc_call *call,
+				  struct rxrpc_ack_summary *summary,
+				  struct sk_buff *skb,
+				  rxrpc_seq_t seq,
+				  rxrpc_seq_t since)
 {
-	unsigned int i;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	unsigned int i, old_nacks = 0;
+	rxrpc_seq_t lowest_nak = seq + sp->nr_acks;
+	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
 
-	for (i = 0; i < nr_acks; i++) {
+	for (i = 0; i < sp->nr_acks; i++) {
 		if (acks[i] == RXRPC_ACK_TYPE_ACK) {
 			summary->nr_acks++;
-			summary->nr_new_acks++;
+			if (after_eq(seq, since))
+				summary->nr_new_acks++;
 		} else {
-			if (!summary->saw_nacks &&
-			    call->acks_lowest_nak != seq + i) {
-				call->acks_lowest_nak = seq + i;
-				summary->new_low_nack = true;
-			}
 			summary->saw_nacks = true;
+			if (before(seq, since)) {
+				/* Overlap with previous ACK */
+				old_nacks++;
+			} else {
+				summary->nr_new_nacks++;
+				sp->nr_nacks++;
+			}
+
+			if (before(seq, lowest_nak))
+				lowest_nak = seq;
 		}
+		seq++;
+	}
+
+	if (lowest_nak != call->acks_lowest_nak) {
+		call->acks_lowest_nak = lowest_nak;
+		summary->new_low_nack = true;
 	}
+
+	/* We *can* have more nacks than we did - the peer is permitted to drop
+	 * packets it has soft-acked and re-request them.  Further, it is
+	 * possible for the nack distribution to change whilst the number of
+	 * nacks stays the same or goes down.
+	 */
+	if (old_nacks < summary->nr_retained_nacks)
+		summary->nr_new_acks += summary->nr_retained_nacks - old_nacks;
+	summary->nr_retained_nacks = old_nacks;
 }
 
 /*
@@ -773,7 +839,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_ackinfo info;
 	rxrpc_serial_t ack_serial, acked_serial;
-	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
+	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since;
 	int nr_acks, offset, ioffset;
 
 	_enter("");
@@ -789,6 +855,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	prev_pkt = ntohl(ack.previousPacket);
 	hard_ack = first_soft_ack - 1;
 	nr_acks = ack.nAcks;
+	sp->first_ack = first_soft_ack;
+	sp->nr_acks = nr_acks;
 	summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ?
 			      ack.reason : RXRPC_ACK__INVALID);
 
@@ -858,6 +926,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (nr_acks > 0)
 		skb_condense(skb);
 
+	if (call->cong_last_nack) {
+		since = rxrpc_input_check_prev_ack(call, &summary, first_soft_ack);
+		rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+		call->cong_last_nack = NULL;
+	} else {
+		summary.nr_new_acks = first_soft_ack - call->acks_first_seq;
+		call->acks_lowest_nak = first_soft_ack + nr_acks;
+		since = first_soft_ack;
+	}
+
 	call->acks_latest_ts = skb->tstamp;
 	call->acks_first_seq = first_soft_ack;
 	call->acks_prev_seq = prev_pkt;
@@ -866,7 +944,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	case RXRPC_ACK_PING:
 		break;
 	default:
-		if (after(acked_serial, call->acks_highest_serial))
+		if (acked_serial && after(acked_serial, call->acks_highest_serial))
 			call->acks_highest_serial = acked_serial;
 		break;
 	}
@@ -905,8 +983,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (nr_acks > 0) {
 		if (offset > (int)skb->len - nr_acks)
 			return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack);
-		rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack,
-				      nr_acks, &summary);
+		rxrpc_input_soft_acks(call, &summary, skb, first_soft_ack, since);
+		rxrpc_get_skb(skb, rxrpc_skb_get_last_nack);
+		call->cong_last_nack = skb;
 	}
 
 	if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) &&
-- 
GitLab


From a19747c3b9bf6476cc36d0a3a5ef0ff92999169e Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 2 Feb 2024 17:06:59 +0100
Subject: [PATCH 3913/4076] selftests: net: let big_tcp test cope with slow env

In very slow environments, most big TCP cases including
segmentation and reassembly of big TCP packets have a good
chance to fail: by default the TCP client uses write size
well below 64K. If the host is low enough autocorking is
unable to build real big TCP packets.

Address the issue using much larger write operations.

Note that is hard to observe the issue without an extremely
slow and/or overloaded environment; reduce the TCP transfer
time to allow for much easier/faster reproducibility.

Fixes: 6bb382bcf742 ("selftests: add a selftest for big tcp")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/big_tcp.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh
index cde9a91c47971..2db9d15cd45fe 100755
--- a/tools/testing/selftests/net/big_tcp.sh
+++ b/tools/testing/selftests/net/big_tcp.sh
@@ -122,7 +122,9 @@ do_netperf() {
 	local netns=$1
 
 	[ "$NF" = "6" ] && serip=$SERVER_IP6
-	ip net exec $netns netperf -$NF -t TCP_STREAM -H $serip 2>&1 >/dev/null
+
+	# use large write to be sure to generate big tcp packets
+	ip net exec $netns netperf -$NF -t TCP_STREAM -l 1 -H $serip -- -m 262144 2>&1 >/dev/null
 }
 
 do_test() {
-- 
GitLab


From 5ea9a7c5fe4149f165f0e3b624fe08df02b6c301 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 5 Feb 2024 13:22:39 +1100
Subject: [PATCH 3914/4076] nfsd: don't take fi_lock in nfsd_break_deleg_cb()

A recent change to check_for_locks() changed it to take ->flc_lock while
holding ->fi_lock.  This creates a lock inversion (reported by lockdep)
because there is a case where ->fi_lock is taken while holding
->flc_lock.

->flc_lock is held across ->fl_lmops callbacks, and
nfsd_break_deleg_cb() is one of those and does take ->fi_lock.  However
it doesn't need to.

Prior to v4.17-rc1~110^2~22 ("nfsd: create a separate lease for each
delegation") nfsd_break_deleg_cb() would walk the ->fi_delegations list
and so needed the lock.  Since then it doesn't walk the list and doesn't
need the lock.

Two actions are performed under the lock.  One is to call
nfsd_break_one_deleg which calls nfsd4_run_cb().  These doesn't act on
the nfs4_file at all, so don't need the lock.

The other is to set ->fi_had_conflict which is in the nfs4_file.
This field is only ever set here (except when initialised to false)
so there is no possible problem will multiple threads racing when
setting it.

The field is tested twice in nfs4_set_delegation().  The first test does
not hold a lock and is documented as an opportunistic optimisation, so
it doesn't impose any need to hold ->fi_lock while setting
->fi_had_conflict.

The second test in nfs4_set_delegation() *is* make under ->fi_lock, so
removing the locking when ->fi_had_conflict is set could make a change.
The change could only be interesting if ->fi_had_conflict tested as
false even though nfsd_break_one_deleg() ran before ->fi_lock was
unlocked.  i.e. while hash_delegation_locked() was running.
As hash_delegation_lock() doesn't interact in any way with nfs4_run_cb()
there can be no importance to this interaction.

So this patch removes the locking from nfsd_break_one_deleg() and moves
the final test on ->fi_had_conflict out of the locked region to make it
clear that locking isn't important to the test.  It is still tested
*after* vfs_setlease() has succeeded.  This might be significant and as
vfs_setlease() takes ->flc_lock, and nfsd_break_one_deleg() is called
under ->flc_lock this "after" is a true ordering provided by a spinlock.

Fixes: edcf9725150e ("nfsd: fix RELEASE_LOCKOWNER")
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 6dc6340e28529..7d6c657e0409d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4945,10 +4945,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 	 */
 	fl->fl_break_time = 0;
 
-	spin_lock(&fp->fi_lock);
 	fp->fi_had_conflict = true;
 	nfsd_break_one_deleg(dp);
-	spin_unlock(&fp->fi_lock);
 	return false;
 }
 
@@ -5557,12 +5555,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (status)
 		goto out_unlock;
 
+	status = -EAGAIN;
+	if (fp->fi_had_conflict)
+		goto out_unlock;
+
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_had_conflict)
-		status = -EAGAIN;
-	else
-		status = hash_delegation_locked(dp, fp);
+	status = hash_delegation_locked(dp, fp);
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&state_lock);
 
-- 
GitLab


From 61712c94782ce105253ee1939cda0c5c025b2c0c Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 30 Jan 2024 13:26:43 +1000
Subject: [PATCH 3915/4076] nouveau/gsp: use correct size for registry rpc.

Timur pointed this out before, and it just slipped my mind,
but this might help some things work better, around pcie power
management.

Cc: <stable@vger.kernel.org> # v6.7
Fixes: 8d55b0a940bb ("nouveau/gsp: add some basic registry entries.")
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240130032643.2498315-1-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 9ee58e2a0eb2a..5e1fa176aac4a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1078,7 +1078,6 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 	if (IS_ERR(rpc))
 		return PTR_ERR(rpc);
 
-	rpc->size = sizeof(*rpc);
 	rpc->numEntries = NV_GSP_REG_NUM_ENTRIES;
 
 	str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]);
@@ -1094,6 +1093,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 		strings += name_len;
 		str_offset += name_len;
 	}
+	rpc->size = str_offset;
 
 	return nvkm_gsp_rpc_wr(gsp, rpc, false);
 }
-- 
GitLab


From 042b5f83841fbf7ce39474412db3b5e4765a7ea7 Mon Sep 17 00:00:00 2001
From: Timur Tabi <ttabi@nvidia.com>
Date: Fri, 2 Feb 2024 17:06:07 -0600
Subject: [PATCH 3916/4076] drm/nouveau: fix several DMA buffer leaks

Nouveau manages GSP-RM DMA buffers with nvkm_gsp_mem objects.  Several of
these buffers are never dealloced.  Some of them can be deallocated
right after GSP-RM is initialized, but the rest need to stay until the
driver unloads.

Also futher bullet-proof these objects by poisoning the buffer and
clearing the nvkm_gsp_mem object when it is deallocated.  Poisoning
the buffer should trigger an error (or crash) from GSP-RM if it tries
to access the buffer after we've deallocated it, because we were wrong
about when it is safe to deallocate.

Finally, change the mem->size field to a size_t because that's the same
type that dma_alloc_coherent expects.

Cc: <stable@vger.kernel.org> # v6.7
Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202230608.1981026-1-ttabi@nvidia.com
---
 .../gpu/drm/nouveau/include/nvkm/subdev/gsp.h |  2 +-
 .../gpu/drm/nouveau/nvkm/subdev/gsp/r535.c    | 59 ++++++++++++-------
 2 files changed, 39 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index d1437c08645f9..6f5d376d8fcc1 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -9,7 +9,7 @@
 #define GSP_PAGE_SIZE  BIT(GSP_PAGE_SHIFT)
 
 struct nvkm_gsp_mem {
-	u32 size;
+	size_t size;
 	void *data;
 	dma_addr_t addr;
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 5e1fa176aac4a..6208ddd929645 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp)
 	return 0;
 }
 
+static void
+nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
+{
+	if (mem->data) {
+		/*
+		 * Poison the buffer to catch any unexpected access from
+		 * GSP-RM if the buffer was prematurely freed.
+		 */
+		memset(mem->data, 0xFF, mem->size);
+
+		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
+		memset(mem, 0, sizeof(*mem));
+	}
+}
+
+static int
+nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem)
+{
+	mem->size = size;
+	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
+	if (WARN_ON(!mem->data))
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int
 r535_gsp_postinit(struct nvkm_gsp *gsp)
 {
@@ -1024,6 +1050,13 @@ r535_gsp_postinit(struct nvkm_gsp *gsp)
 
 	nvkm_inth_allow(&gsp->subdev.inth);
 	nvkm_wr32(device, 0x110004, 0x00000040);
+
+	/* Release the DMA buffers that were needed only for boot and init */
+	nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw);
+	nvkm_gsp_mem_dtor(gsp, &gsp->libos);
+	nvkm_gsp_mem_dtor(gsp, &gsp->rmargs);
+	nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta);
+
 	return ret;
 }
 
@@ -1532,27 +1565,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
-static void
-nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
-{
-	if (mem->data) {
-		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
-		mem->data = NULL;
-	}
-}
-
-static int
-nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem)
-{
-	mem->size = size;
-	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
-	if (WARN_ON(!mem->data))
-		return -ENOMEM;
-
-	return 0;
-}
-
-
 static int
 r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1)
 {
@@ -2150,6 +2162,11 @@ r535_gsp_dtor(struct nvkm_gsp *gsp)
 	mutex_destroy(&gsp->cmdq.mutex);
 
 	r535_gsp_dtor_fws(gsp);
+
+	nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem);
+	nvkm_gsp_mem_dtor(gsp, &gsp->loginit);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logintr);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logrm);
 }
 
 int
-- 
GitLab


From 34e659f34a7559ecfd9c1f5b24d4c291f3f54711 Mon Sep 17 00:00:00 2001
From: Timur Tabi <ttabi@nvidia.com>
Date: Fri, 2 Feb 2024 17:06:08 -0600
Subject: [PATCH 3917/4076] drm/nouveau: nvkm_gsp_radix3_sg() should use
 nvkm_gsp_mem_ctor()

Function nvkm_gsp_radix3_sg() uses nvkm_gsp_mem objects to allocate the
radix3 tables, but it unnecessarily creates those objects manually
instead of using the standard nvkm_gsp_mem_ctor() function like the
rest of the code does.

Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202230608.1981026-2-ttabi@nvidia.com
---
 drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 6208ddd929645..a41735ab60683 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1950,20 +1950,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
  * See kgspCreateRadix3_IMPL
  */
 static int
-nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
+nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
 {
 	u64 addr;
 
 	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
 		u64 *ptes;
-		int idx;
+		size_t bufsize;
+		int ret, idx;
 
-		rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
-		rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size,
-						      &rx3->mem[i].addr, GFP_KERNEL);
-		if (WARN_ON(!rx3->mem[i].data))
-			return -ENOMEM;
+		bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+		ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+		if (ret)
+			return ret;
 
 		ptes = rx3->mem[i].data;
 		if (i == 2) {
@@ -2003,7 +2003,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 		if (ret)
 			return ret;
 
-		ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3);
+		ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3);
 		if (ret)
 			return ret;
 
@@ -2211,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
 	memcpy(gsp->sig.data, data, size);
 
 	/* Build radix3 page table for ELF image. */
-	ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
+	ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
 	if (ret)
 		return ret;
 
-- 
GitLab


From 0647903efbc84b772325b4d24d9487e24d6d1e03 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Sat, 3 Feb 2024 14:24:46 +0100
Subject: [PATCH 3918/4076] wifi: mt76: mt7996: fix fortify warning

Copy cck and ofdm separately in order to avoid __read_overflow2_field
warning.

Fixes: f75e4779d215 ("wifi: mt76: mt7996: add txpower setting support")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240203132446.54790-1-nbd@nbd.name
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 3c729b563edc5..699be57309c2e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -4477,7 +4477,8 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy)
 
 	skb_put_data(skb, &req, sizeof(req));
 	/* cck and ofdm */
-	skb_put_data(skb, &la.cck, sizeof(la.cck) + sizeof(la.ofdm));
+	skb_put_data(skb, &la.cck, sizeof(la.cck));
+	skb_put_data(skb, &la.ofdm, sizeof(la.ofdm));
 	/* ht20 */
 	skb_put_data(skb, &la.mcs[0], 8);
 	/* ht40 */
-- 
GitLab


From 4e6c9011990726f4d175e2cdfebe5b0b8cce4839 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sat, 3 Feb 2024 10:45:21 +0800
Subject: [PATCH 3919/4076] scsi: core: Move scsi_host_busy() out of host lock
 if it is for per-command

Commit 4373534a9850 ("scsi: core: Move scsi_host_busy() out of host lock
for waking up EH handler") intended to fix a hard lockup issue triggered by
EH. The core idea was to move scsi_host_busy() out of the host lock when
processing individual commands for EH. However, a suggested style change
inadvertently caused scsi_host_busy() to remain under the host lock. Fix
this by calling scsi_host_busy() outside the lock.

Fixes: 4373534a9850 ("scsi: core: Move scsi_host_busy() out of host lock for waking up EH handler")
Cc: Sathya Prakash Veerichetty <safhya.prakash@broadcom.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240203024521.2006455-1-ming.lei@redhat.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_error.c | 3 ++-
 drivers/scsi/scsi_lib.c   | 4 +++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 4f455884fdc44..612489afe8d24 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -282,11 +282,12 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head)
 {
 	struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu);
 	struct Scsi_Host *shost = scmd->device->host;
+	unsigned int busy = scsi_host_busy(shost);
 	unsigned long flags;
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	shost->host_failed++;
-	scsi_eh_wakeup(shost, scsi_host_busy(shost));
+	scsi_eh_wakeup(shost, busy);
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 1fb80eae9a63a..df5ac03d5d6c2 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -278,9 +278,11 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 	rcu_read_lock();
 	__clear_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 	if (unlikely(scsi_host_in_recovery(shost))) {
+		unsigned int busy = scsi_host_busy(shost);
+
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (shost->host_failed || shost->host_eh_scheduled)
-			scsi_eh_wakeup(shost, scsi_host_busy(shost));
+			scsi_eh_wakeup(shost, busy);
 		spin_unlock_irqrestore(shost->host_lock, flags);
 	}
 	rcu_read_unlock();
-- 
GitLab


From d6c1b19153f92e95e5e1801d540e98771053afae Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 20 Dec 2023 17:26:58 +0100
Subject: [PATCH 3920/4076] scsi: lpfc: Use unsigned type for num_sge

LUNs going into "failed ready running" state observed on >1T and on even
numbers of size (2T, 4T, 6T, 8T and 10T). The issue occurs when DIF is
enabled at the host.

The kernel logs:

  Cannot setup S/G List for HBAIO segs 1/1 SGL 512 SCSI 256: 3 0

The host lpfc driver is failing to setup scatter/gather list (protection
data) for the I/Os.

The return type lpfc_bg_setup_sgl()/lpfc_bg_setup_sgl_prot() causes the
compiler to remove the most significant bit. Use an unsigned type instead.

Signed-off-by: Hannes Reinecke <hare@suse.de>
[dwagner: added commit message]
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Link: https://lore.kernel.org/r/20231220162658.12392-1-dwagner@suse.de
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_scsi.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index d26941b131fdb..bf879d81846b6 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1918,7 +1918,7 @@ out:
  *
  * Returns the number of SGEs added to the SGL.
  **/
-static int
+static uint32_t
 lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		struct sli4_sge *sgl, int datasegcnt,
 		struct lpfc_io_buf *lpfc_cmd)
@@ -1926,8 +1926,8 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	struct scatterlist *sgde = NULL; /* s/g data entry */
 	struct sli4_sge_diseed *diseed = NULL;
 	dma_addr_t physaddr;
-	int i = 0, num_sge = 0, status;
-	uint32_t reftag;
+	int i = 0, status;
+	uint32_t reftag, num_sge = 0;
 	uint8_t txop, rxop;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	uint32_t rc;
@@ -2099,7 +2099,7 @@ out:
  *
  * Returns the number of SGEs added to the SGL.
  **/
-static int
+static uint32_t
 lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		struct sli4_sge *sgl, int datacnt, int protcnt,
 		struct lpfc_io_buf *lpfc_cmd)
@@ -2123,8 +2123,8 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	uint32_t rc;
 #endif
 	uint32_t checking = 1;
-	uint32_t dma_offset = 0;
-	int num_sge = 0, j = 2;
+	uint32_t dma_offset = 0, num_sge = 0;
+	int j = 2;
 	struct sli4_hybrid_sgl *sgl_xtra = NULL;
 
 	sgpe = scsi_prot_sglist(sc);
-- 
GitLab


From b513d30d59bb383a6a5d6b533afcab2cee99a8f8 Mon Sep 17 00:00:00 2001
From: Alice Chao <alice.chao@mediatek.com>
Date: Mon, 5 Feb 2024 18:49:04 +0800
Subject: [PATCH 3921/4076] scsi: ufs: core: Fix shift issue in
 ufshcd_clear_cmd()

When task_tag >= 32 (in MCQ mode) and sizeof(unsigned int) == 4, 1U <<
task_tag will out of bounds for a u32 mask. Fix this up to prevent
SHIFT_ISSUE (bitwise shifts that are out of bounds for their data type).

[name:debug_monitors&]Unexpected kernel BRK exception at EL1
[name:traps&]Internal error: BRK handler: 00000000f2005514 [#1] PREEMPT SMP
[name:mediatek_cpufreq_hw&]cpufreq stop DVFS log done
[name:mrdump&]Kernel Offset: 0x1ba5800000 from 0xffffffc008000000
[name:mrdump&]PHYS_OFFSET: 0x80000000
[name:mrdump&]pstate: 22400005 (nzCv daif +PAN -UAO)
[name:mrdump&]pc : [0xffffffdbaf52bb2c] ufshcd_clear_cmd+0x280/0x288
[name:mrdump&]lr : [0xffffffdbaf52a774] ufshcd_wait_for_dev_cmd+0x3e4/0x82c
[name:mrdump&]sp : ffffffc0081471b0
<snip>
Workqueue: ufs_eh_wq_0 ufshcd_err_handler
Call trace:
 dump_backtrace+0xf8/0x144
 show_stack+0x18/0x24
 dump_stack_lvl+0x78/0x9c
 dump_stack+0x18/0x44
 mrdump_common_die+0x254/0x480 [mrdump]
 ipanic_die+0x20/0x30 [mrdump]
 notify_die+0x15c/0x204
 die+0x10c/0x5f8
 arm64_notify_die+0x74/0x13c
 do_debug_exception+0x164/0x26c
 el1_dbg+0x64/0x80
 el1h_64_sync_handler+0x3c/0x90
 el1h_64_sync+0x68/0x6c
 ufshcd_clear_cmd+0x280/0x288
 ufshcd_wait_for_dev_cmd+0x3e4/0x82c
 ufshcd_exec_dev_cmd+0x5bc/0x9ac
 ufshcd_verify_dev_init+0x84/0x1c8
 ufshcd_probe_hba+0x724/0x1ce0
 ufshcd_host_reset_and_restore+0x260/0x574
 ufshcd_reset_and_restore+0x138/0xbd0
 ufshcd_err_handler+0x1218/0x2f28
 process_one_work+0x5fc/0x1140
 worker_thread+0x7d8/0xe20
 kthread+0x25c/0x468
 ret_from_fork+0x10/0x20

Signed-off-by: Alice Chao <alice.chao@mediatek.com>
Link: https://lore.kernel.org/r/20240205104905.24929-1-alice.chao@mediatek.com
Reviewed-by: Stanley Jhu <chu.stanley@gmail.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 029d017fc1b66..c6cff4aa440a3 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -3057,7 +3057,7 @@ bool ufshcd_cmd_inflight(struct scsi_cmnd *cmd)
  */
 static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
 {
-	u32 mask = 1U << task_tag;
+	u32 mask;
 	unsigned long flags;
 	int err;
 
@@ -3075,6 +3075,8 @@ static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
 		return 0;
 	}
 
+	mask = 1U << task_tag;
+
 	/* clear outstanding transaction before retry */
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_utrl_clear(hba, mask);
-- 
GitLab


From 17e94b2585417e04dabc2f13bc03b4665ae687f3 Mon Sep 17 00:00:00 2001
From: SEO HOYOUNG <hy50.seo@samsung.com>
Date: Mon, 22 Jan 2024 17:33:24 +0900
Subject: [PATCH 3922/4076] scsi: ufs: core: Remove the ufshcd_release() in
 ufshcd_err_handling_prepare()

If ufshcd_err_handler() is called in a suspend/resume situation,
ufs_release() can be called twice and active_reqs end up going negative.
This is because ufshcd_err_handling_prepare() and
ufshcd_err_handling_unprepare() both call ufshcd_release().

Remove superfluous call to ufshcd_release().

Signed-off-by: SEO HOYOUNG <hy50.seo@samsung.com>
Link: https://lore.kernel.org/r/20240122083324.11797-1-hy50.seo@samsung.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Can Guo <quic_cang@quicinc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index c6cff4aa440a3..d77b25b79ae3e 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6354,7 +6354,6 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
 		ufshcd_hold(hba);
 		if (!ufshcd_is_clkgating_allowed(hba))
 			ufshcd_setup_clocks(hba, true);
-		ufshcd_release(hba);
 		pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM;
 		ufshcd_vops_resume(hba, pm_op);
 	} else {
-- 
GitLab


From d0399da9fb5f8e3d897b9776bffee2d3bfe20210 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 29 Jan 2024 19:04:13 -0800
Subject: [PATCH 3923/4076] drm/sched: Re-queue run job worker when
 drm_sched_entity_pop_job() returns NULL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rather then loop over entities until one with a ready job is found,
re-queue the run job worker when drm_sched_entity_pop_job() returns NULL.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Fixes: 66dbd9004a55 ("drm/sched: Drain all entities in DRM sched run job worker")
Reviewed-by: Luben Tuikov <ltuikov89@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240130030413.2031009-1-matthew.brost@intel.com
---
 drivers/gpu/drm/scheduler/sched_main.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 85f082396d42d..d442b893275b9 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1178,21 +1178,24 @@ static void drm_sched_run_job_work(struct work_struct *w)
 	struct drm_sched_entity *entity;
 	struct dma_fence *fence;
 	struct drm_sched_fence *s_fence;
-	struct drm_sched_job *sched_job = NULL;
+	struct drm_sched_job *sched_job;
 	int r;
 
 	if (READ_ONCE(sched->pause_submit))
 		return;
 
 	/* Find entity with a ready job */
-	while (!sched_job && (entity = drm_sched_select_entity(sched))) {
-		sched_job = drm_sched_entity_pop_job(entity);
-		if (!sched_job)
-			complete_all(&entity->entity_idle);
-	}
+	entity = drm_sched_select_entity(sched);
 	if (!entity)
 		return;	/* No more work */
 
+	sched_job = drm_sched_entity_pop_job(entity);
+	if (!sched_job) {
+		complete_all(&entity->entity_idle);
+		drm_sched_run_job_queue(sched);
+		return;
+	}
+
 	s_fence = sched_job->s_fence;
 
 	atomic_add(sched_job->credits, &sched->credit_count);
-- 
GitLab


From b3ff2d9c3a9c64cd0a011cdd407ffc38a6ea8788 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 3924/4076] LoongArch: Select ARCH_ENABLE_THP_MIGRATION instead
 of redefining it

ARCH_ENABLE_THP_MIGRATION is supposed to be selected by arch Kconfig.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 10959e6c35832..64e9a01c7f36e 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -12,6 +12,7 @@ config LOONGARCH
 	select ARCH_DISABLE_KASAN_INLINE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
+	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_FORTIFY_SOURCE
@@ -667,10 +668,6 @@ config ARCH_SPARSEMEM_ENABLE
 	  or have huge holes in the physical address space for other reasons.
 	  See <file:Documentation/mm/numa.rst> for more.
 
-config ARCH_ENABLE_THP_MIGRATION
-	def_bool y
-	depends on TRANSPARENT_HUGEPAGE
-
 config ARCH_MEMORY_PROBE
 	def_bool y
 	depends on MEMORY_HOTPLUG
-- 
GitLab


From 6b79ecd084c99b31c8b4d0beda08893716d5558e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 3925/4076] LoongArch: Select HAVE_ARCH_SECCOMP to use the
 common SECCOMP menu

LoongArch missed the refactoring made by commit 282a181b1a0d ("seccomp:
Move config option SECCOMP to arch/Kconfig") because LoongArch was not
mainlined at that time.

The 'depends on PROC_FS' statement is stale as described in that commit.
Select HAVE_ARCH_SECCOMP, and remove the duplicated config entry.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig | 18 +-----------------
 1 file changed, 1 insertion(+), 17 deletions(-)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 64e9a01c7f36e..929f68926b343 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -100,6 +100,7 @@ config LOONGARCH
 	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KGDB if PERF_EVENTS
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
+	select HAVE_ARCH_SECCOMP
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
@@ -633,23 +634,6 @@ config RANDOMIZE_BASE_MAX_OFFSET
 
 	  This is limited by the size of the lower address memory, 256MB.
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 endmenu
 
 config ARCH_SELECT_MEMORY_MODEL
-- 
GitLab


From 4551b30525cf3d2f026b92401ffe241eb04dfebe Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 3926/4076] LoongArch: Change acpi_core_pic[NR_CPUS] to
 acpi_core_pic[MAX_CORE_PIC]

With default config, the value of NR_CPUS is 64. When HW platform has
more then 64 cpus, system will crash on these platforms. MAX_CORE_PIC
is the maximum cpu number in MADT table (max physical number) which can
exceed the supported maximum cpu number (NR_CPUS, max logical number),
but kernel should not crash. Kernel should boot cpus with NR_CPUS, let
the remainder cpus stay in BIOS.

The potential crash reason is that the array acpi_core_pic[NR_CPUS] can
be overflowed when parsing MADT table, and it is obvious that CORE_PIC
should be corresponding to physical core rather than logical core, so it
is better to define the array as acpi_core_pic[MAX_CORE_PIC].

With the patch, system can boot up 64 vcpus with qemu parameter -smp 128,
otherwise system will crash with the following message.

[    0.000000] CPU 0 Unable to handle kernel paging request at virtual address 0000420000004259, era == 90000000037a5f0c, ra == 90000000037a46ec
[    0.000000] Oops[#1]:
[    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 6.8.0-rc2+ #192
[    0.000000] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022
[    0.000000] pc 90000000037a5f0c ra 90000000037a46ec tp 9000000003c90000 sp 9000000003c93d60
[    0.000000] a0 0000000000000019 a1 9000000003d93bc0 a2 0000000000000000 a3 9000000003c93bd8
[    0.000000] a4 9000000003c93a74 a5 9000000083c93a67 a6 9000000003c938f0 a7 0000000000000005
[    0.000000] t0 0000420000004201 t1 0000000000000000 t2 0000000000000001 t3 0000000000000001
[    0.000000] t4 0000000000000003 t5 0000000000000000 t6 0000000000000030 t7 0000000000000063
[    0.000000] t8 0000000000000014 u0 ffffffffffffffff s9 0000000000000000 s0 9000000003caee98
[    0.000000] s1 90000000041b0480 s2 9000000003c93da0 s3 9000000003c93d98 s4 9000000003c93d90
[    0.000000] s5 9000000003caa000 s6 000000000a7fd000 s7 000000000f556b60 s8 000000000e0a4330
[    0.000000]    ra: 90000000037a46ec platform_init+0x214/0x250
[    0.000000]   ERA: 90000000037a5f0c efi_runtime_init+0x30/0x94
[    0.000000]  CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE)
[    0.000000]  PRMD: 00000000 (PPLV0 -PIE -PWE)
[    0.000000]  EUEN: 00000000 (-FPE -SXE -ASXE -BTE)
[    0.000000]  ECFG: 00070800 (LIE=11 VS=7)
[    0.000000] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0)
[    0.000000]  BADV: 0000420000004259
[    0.000000]  PRID: 0014c010 (Loongson-64bit, Loongson-3A5000)
[    0.000000] Modules linked in:
[    0.000000] Process swapper (pid: 0, threadinfo=(____ptrval____), task=(____ptrval____))
[    0.000000] Stack : 9000000003c93a14 9000000003800898 90000000041844f8 90000000037a46ec
[    0.000000]         000000000a7fd000 0000000008290000 0000000000000000 0000000000000000
[    0.000000]         0000000000000000 0000000000000000 00000000019d8000 000000000f556b60
[    0.000000]         000000000a7fd000 000000000f556b08 9000000003ca7700 9000000003800000
[    0.000000]         9000000003c93e50 9000000003800898 9000000003800108 90000000037a484c
[    0.000000]         000000000e0a4330 000000000f556b60 000000000a7fd000 000000000f556b08
[    0.000000]         9000000003ca7700 9000000004184000 0000000000200000 000000000e02b018
[    0.000000]         000000000a7fd000 90000000037a0790 9000000003800108 0000000000000000
[    0.000000]         0000000000000000 000000000e0a4330 000000000f556b60 000000000a7fd000
[    0.000000]         000000000f556b08 000000000eaae298 000000000eaa5040 0000000000200000
[    0.000000]         ...
[    0.000000] Call Trace:
[    0.000000] [<90000000037a5f0c>] efi_runtime_init+0x30/0x94
[    0.000000] [<90000000037a46ec>] platform_init+0x214/0x250
[    0.000000] [<90000000037a484c>] setup_arch+0x124/0x45c
[    0.000000] [<90000000037a0790>] start_kernel+0x90/0x670
[    0.000000] [<900000000378b0d8>] kernel_entry+0xd8/0xdc

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/acpi.h | 4 +++-
 arch/loongarch/kernel/acpi.c      | 4 +---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h
index 8de6c4b83a61a..49e29b29996f0 100644
--- a/arch/loongarch/include/asm/acpi.h
+++ b/arch/loongarch/include/asm/acpi.h
@@ -32,8 +32,10 @@ static inline bool acpi_has_cpu_in_madt(void)
 	return true;
 }
 
+#define MAX_CORE_PIC 256
+
 extern struct list_head acpi_wakeup_device_list;
-extern struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 extern int __init parse_acpi_topology(void);
 
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index b6b097bbf8668..5cf59c617126b 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -29,11 +29,9 @@ int disabled_cpus;
 
 u64 acpi_saved_sp;
 
-#define MAX_CORE_PIC 256
-
 #define PREFIX			"ACPI: "
 
-struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 void __init __iomem * __acpi_map_table(unsigned long phys, unsigned long size)
 {
-- 
GitLab


From 639420e9f6cd9ca074732b17ac450d2518d5937f Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 3927/4076] LoongArch: Fix earlycon parameter if KASAN enabled

The earlycon parameter is based on fixmap, and fixmap addresses are not
supposed to be shadowed by KASAN. So return the kasan_early_shadow_page
in kasan_mem_to_shadow() if the input address is above FIXADDR_START.
Otherwise earlycon cannot work after kasan_init().

Cc: stable@vger.kernel.org
Fixes: 5aa4ac64e6add3e ("LoongArch: Add KASAN (Kernel Address Sanitizer) support")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/mm/kasan_init.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c
index cc3e81fe0186f..c608adc998458 100644
--- a/arch/loongarch/mm/kasan_init.c
+++ b/arch/loongarch/mm/kasan_init.c
@@ -44,6 +44,9 @@ void *kasan_mem_to_shadow(const void *addr)
 		unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
 		unsigned long offset = 0;
 
+		if (maddr >= FIXADDR_START)
+			return (void *)(kasan_early_shadow_page);
+
 		maddr &= XRANGE_SHADOW_MASK;
 		switch (xrange) {
 		case XKPRANGE_CC_SEG:
-- 
GitLab


From cca5efe77a6a2d02b3da4960f799fa233e460ab1 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 3928/4076] LoongArch: vDSO: Disable UBSAN instrumentation

The vDSO executes in userspace, so the kernel's UBSAN should not
instrument it. Solves these kind of build errors:

  loongarch64-linux-ld: arch/loongarch/vdso/vgettimeofday.o: in function `vdso_shift_ns':
  lib/vdso/gettimeofday.c:23:(.text+0x3f8): undefined reference to `__ubsan_handle_shift_out_of_bounds'

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401310530.lZHCj1Zl-lkp@intel.com/
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Fangrui Song <maskray@google.com>
Cc: loongarch@lists.linux.dev
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/vdso/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index c74c9921304f2..f597cd08a96be 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -2,6 +2,7 @@
 # Objects to go into the VDSO.
 
 KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
 # Include the generic Makefile to check the built vdso.
-- 
GitLab


From 3871aa01e1a779d866fa9dfdd5a836f342f4eb87 Mon Sep 17 00:00:00 2001
From: Shigeru Yoshida <syoshida@redhat.com>
Date: Thu, 1 Feb 2024 00:23:09 +0900
Subject: [PATCH 3929/4076] tipc: Check the bearer type before calling
 tipc_udp_nl_bearer_add()

syzbot reported the following general protection fault [1]:

general protection fault, probably for non-canonical address 0xdffffc0000000010: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000080-0x0000000000000087]
...
RIP: 0010:tipc_udp_is_known_peer+0x9c/0x250 net/tipc/udp_media.c:291
...
Call Trace:
 <TASK>
 tipc_udp_nl_bearer_add+0x212/0x2f0 net/tipc/udp_media.c:646
 tipc_nl_bearer_add+0x21e/0x360 net/tipc/bearer.c:1089
 genl_family_rcv_msg_doit+0x1fc/0x2e0 net/netlink/genetlink.c:972
 genl_family_rcv_msg net/netlink/genetlink.c:1052 [inline]
 genl_rcv_msg+0x561/0x800 net/netlink/genetlink.c:1067
 netlink_rcv_skb+0x16b/0x440 net/netlink/af_netlink.c:2544
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1076
 netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline]
 netlink_unicast+0x53b/0x810 net/netlink/af_netlink.c:1367
 netlink_sendmsg+0x8b7/0xd70 net/netlink/af_netlink.c:1909
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg+0xd5/0x180 net/socket.c:745
 ____sys_sendmsg+0x6ac/0x940 net/socket.c:2584
 ___sys_sendmsg+0x135/0x1d0 net/socket.c:2638
 __sys_sendmsg+0x117/0x1e0 net/socket.c:2667
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x40/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

The cause of this issue is that when tipc_nl_bearer_add() is called with
the TIPC_NLA_BEARER_UDP_OPTS attribute, tipc_udp_nl_bearer_add() is called
even if the bearer is not UDP.

tipc_udp_is_known_peer() called by tipc_udp_nl_bearer_add() assumes that
the media_ptr field of the tipc_bearer has an udp_bearer type object, so
the function goes crazy for non-UDP bearers.

This patch fixes the issue by checking the bearer type before calling
tipc_udp_nl_bearer_add() in tipc_nl_bearer_add().

Fixes: ef20cd4dd163 ("tipc: introduce UDP replicast")
Reported-and-tested-by: syzbot+5142b87a9abc510e14fa@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=5142b87a9abc510e14fa [1]
Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
Reviewed-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Link: https://lore.kernel.org/r/20240131152310.4089541-1-syoshida@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/tipc/bearer.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 2cde375477e38..878415c435276 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1086,6 +1086,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info)
 
 #ifdef CONFIG_TIPC_MEDIA_UDP
 	if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) {
+		if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) {
+			rtnl_unlock();
+			NL_SET_ERR_MSG(info->extack, "UDP option is unsupported");
+			return -EINVAL;
+		}
+
 		err = tipc_udp_nl_bearer_add(b,
 					     attrs[TIPC_NLA_BEARER_UDP_OPTS]);
 		if (err) {
-- 
GitLab


From e459647710070684a48384d67742822379de8c1c Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 2 Feb 2024 16:53:21 -0700
Subject: [PATCH 3930/4076] x86/coco: Define cc_vendor without
 CONFIG_ARCH_HAS_CC_PLATFORM

After commit a9ef277488cf ("x86/kvm: Fix SEV check in
sev_map_percpu_data()"), there is a build error when building
x86_64_defconfig with GCOV using LLVM:

  ld.lld: error: undefined symbol: cc_vendor
  >>> referenced by kvm.c
  >>>               arch/x86/kernel/kvm.o:(kvm_smp_prepare_boot_cpu) in archive vmlinux.a

which corresponds to

  if (cc_vendor != CC_VENDOR_AMD ||
      !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
            return;

Without GCOV, clang is able to eliminate the use of cc_vendor because
cc_platform_has() evaluates to false when CONFIG_ARCH_HAS_CC_PLATFORM is
not set, meaning that if statement will be true no matter what value
cc_vendor has.

With GCOV, the instrumentation keeps the use of cc_vendor around for
code coverage purposes but cc_vendor is only declared, not defined,
without CONFIG_ARCH_HAS_CC_PLATFORM, leading to the build error above.

Provide a macro definition of cc_vendor when CONFIG_ARCH_HAS_CC_PLATFORM
is not set with a value of CC_VENDOR_NONE, so that the first condition
can always be evaluated/eliminated at compile time, avoiding the build
error altogether. This is very similar to the situation prior to
commit da86eb961184 ("x86/coco: Get rid of accessor functions").

Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Message-Id: <20240202-provide-cc_vendor-without-arch_has_cc_platform-v1-1-09ad5f2a3099@kernel.org>
Fixes: a9ef277488cf ("x86/kvm: Fix SEV check in sev_map_percpu_data()", 2024-01-31)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/coco.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 6ae2d16a7613b..76c310b19b11d 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -10,13 +10,14 @@ enum cc_vendor {
 	CC_VENDOR_INTEL,
 };
 
-extern enum cc_vendor cc_vendor;
-
 #ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+extern enum cc_vendor cc_vendor;
 void cc_set_mask(u64 mask);
 u64 cc_mkenc(u64 val);
 u64 cc_mkdec(u64 val);
 #else
+#define cc_vendor (CC_VENDOR_NONE)
+
 static inline u64 cc_mkenc(u64 val)
 {
 	return val;
-- 
GitLab


From b083d24fcf57580cc0b45dd7b0b4f84d8c4624f4 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Fri, 2 Feb 2024 02:24:59 +0000
Subject: [PATCH 3931/4076] selftests/net: Amend per-netns counter checks

Selftests here check not only that connect()/accept() for
TCP-AO/TCP-MD5/non-signed-TCP combinations do/don't establish
connections, but also counters: those are per-AO-key, per-socket and
per-netns.

The counters are checked on the server's side, as the server listener
has TCP-AO/TCP-MD5/no keys for different peers. All tests run in
the same namespaces with the same veth pair, created in test_init().

After close() in both client and server, the sides go through
the regular FIN/ACK + FIN/ACK sequence, which goes in the background.
If the selftest has already started a new testing scenario, read
per-netns counters - it may fail in the end iff it doesn't expect
the TCPAOGood per-netns counters go up during the test.

Let's just kill both TCP-AO sides - that will avoid any asynchronous
background TCP-AO segments going to either sides.

Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/all/20240201132153.4d68f45e@kernel.org/T/#u
Fixes: 6f0c472a6815 ("selftests/net: Add TCP-AO + TCP-MD5 + no sign listen socket tests")
Signed-off-by: Dmitry Safonov <dima@arista.com>
Link: https://lore.kernel.org/r/20240202-unsigned-md5-netns-counters-v1-1-8b90c37c0566@arista.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/tcp_ao/unsigned-md5.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index c5b568cd7d901..6b59a652159f7 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -110,9 +110,9 @@ static void try_accept(const char *tst_name, unsigned int port,
 		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	if (sk > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 static void server_add_routes(void)
@@ -302,10 +302,10 @@ static void try_connect(const char *tst_name, unsigned int port,
 		test_ok("%s: connected", tst_name);
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	/* _test_connect_socket() cleans up on failure */
 	if (ret > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 #define PREINSTALL_MD5_FIRST	BIT(0)
@@ -486,10 +486,10 @@ static void try_to_add(const char *tst_name, unsigned int port,
 	}
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	/* _test_connect_socket() cleans up on failure */
 	if (ret > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 static void client_add_ip(union tcp_addr *client, const char *ip)
-- 
GitLab


From dad6a09f3148257ac1773cd90934d721d68ab595 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Mon, 29 Jan 2024 15:56:36 -0800
Subject: [PATCH 3932/4076] hrtimer: Report offline hrtimer enqueue

The hrtimers migration on CPU-down hotplug process has been moved
earlier, before the CPU actually goes to die. This leaves a small window
of opportunity to queue an hrtimer in a blind spot, leaving it ignored.

For example a practical case has been reported with RCU waking up a
SCHED_FIFO task right before the CPUHP_AP_IDLE_DEAD stage, queuing that
way a sched/rt timer to the local offline CPU.

Make sure such situations never go unnoticed and warn when that happens.

Fixes: 5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier")
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240129235646.3171983-4-boqun.feng@gmail.com
---
 include/linux/hrtimer.h | 4 +++-
 kernel/time/hrtimer.c   | 3 +++
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 87e3bedf8eb00..641c4567cfa7a 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -157,6 +157,7 @@ enum  hrtimer_base_type {
  * @max_hang_time:	Maximum time spent in hrtimer_interrupt
  * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
  *			 expired
+ * @online:		CPU is online from an hrtimers point of view
  * @timer_waiters:	A hrtimer_cancel() invocation waits for the timer
  *			callback to finish.
  * @expires_next:	absolute time of the next event, is required for remote
@@ -179,7 +180,8 @@ struct hrtimer_cpu_base {
 	unsigned int			hres_active		: 1,
 					in_hrtirq		: 1,
 					hang_detected		: 1,
-					softirq_activated       : 1;
+					softirq_activated       : 1,
+					online			: 1;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	unsigned int			nr_events;
 	unsigned short			nr_retries;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 760793998cdd7..edb0f821dceaa 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1085,6 +1085,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 			   enum hrtimer_mode mode)
 {
 	debug_activate(timer, mode);
+	WARN_ON_ONCE(!base->cpu_base->online);
 
 	base->cpu_base->active_bases |= 1 << base->index;
 
@@ -2183,6 +2184,7 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	cpu_base->softirq_next_timer = NULL;
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
+	cpu_base->online = 1;
 	hrtimer_cpu_base_init_expiry_lock(cpu_base);
 	return 0;
 }
@@ -2250,6 +2252,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
 	raw_spin_unlock(&new_base->lock);
+	old_base->online = 0;
 	raw_spin_unlock(&old_base->lock);
 
 	return 0;
-- 
GitLab


From 58aeb5623c2ebdadefe6352b14f8076a7073fea0 Mon Sep 17 00:00:00 2001
From: Fred Ai <fred.ai@bayhubtech.com>
Date: Sat, 3 Feb 2024 02:29:08 -0800
Subject: [PATCH 3933/4076] mmc: sdhci-pci-o2micro: Fix a warm reboot issue
 that disk can't be detected by BIOS

Driver shall switch clock source from DLL clock to
OPE clock when power off card to ensure that card
can be identified with OPE clock by BIOS.

Signed-off-by: Fred Ai <fred.ai@bayhubtech.com>
Fixes:4be33cf18703 ("mmc: sdhci-pci-o2micro: Improve card input timing at SDR104/HS200 mode")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240203102908.4683-1-fredaibayhubtech@126.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-pci-o2micro.c | 30 ++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index 7bfee28116af1..d4a02184784a3 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -693,6 +693,35 @@ static int sdhci_pci_o2_init_sd_express(struct mmc_host *mmc, struct mmc_ios *io
 	return 0;
 }
 
+static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode,  unsigned short vdd)
+{
+	struct sdhci_pci_chip *chip;
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	u32 scratch_32 = 0;
+	u8 scratch_8 = 0;
+
+	chip = slot->chip;
+
+	if (mode == MMC_POWER_OFF) {
+		/* UnLock WP */
+		pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8);
+		scratch_8 &= 0x7f;
+		pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8);
+
+		/* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */
+		pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32);
+		scratch_32 &= ~(O2_SD_SEL_DLL);
+		pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32);
+
+		/* Lock WP */
+		pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8);
+		scratch_8 |= 0x80;
+		pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8);
+	}
+
+	sdhci_set_power(host, mode, vdd);
+}
+
 static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot)
 {
 	struct sdhci_pci_chip *chip;
@@ -1051,6 +1080,7 @@ static const struct sdhci_ops sdhci_pci_o2_ops = {
 	.set_bus_width = sdhci_set_bus_width,
 	.reset = sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
+	.set_power = sdhci_pci_o2_set_power,
 };
 
 const struct sdhci_pci_fixes sdhci_o2 = {
-- 
GitLab


From cc9432c4fb159a3913e0ce3173b8218cd5bad2e0 Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Tue, 6 Feb 2024 09:39:12 +0100
Subject: [PATCH 3934/4076] mmc: slot-gpio: Allow non-sleeping GPIO ro

This change uses the appropriate _cansleep or non-sleeping API for
reading GPIO read-only state. This allows users with GPIOs that
never sleepbeing called in atomic context.

Implement the same mechanism as in commit 52af318c93e97 ("mmc: Allow
non-sleeping GPIO cd").

Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240206083912.2543142-1-alexander.stein@ew.tq-group.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/slot-gpio.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 2a2d949a9344e..39f45c2b6de8a 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -75,11 +75,15 @@ EXPORT_SYMBOL(mmc_gpio_set_cd_irq);
 int mmc_gpio_get_ro(struct mmc_host *host)
 {
 	struct mmc_gpio *ctx = host->slot.handler_priv;
+	int cansleep;
 
 	if (!ctx || !ctx->ro_gpio)
 		return -ENOSYS;
 
-	return gpiod_get_value_cansleep(ctx->ro_gpio);
+	cansleep = gpiod_cansleep(ctx->ro_gpio);
+	return cansleep ?
+		gpiod_get_value_cansleep(ctx->ro_gpio) :
+		gpiod_get_value(ctx->ro_gpio);
 }
 EXPORT_SYMBOL(mmc_gpio_get_ro);
 
-- 
GitLab


From c9da9a1f17bf4fa96b115950fd389c917b583c1c Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Fri, 26 Jan 2024 13:27:58 +0100
Subject: [PATCH 3935/4076] accel/ivpu: Force snooping for MMU writes

Set AW_SNOOP_OVERRIDE bit in VPU_37/40XX_HOST_IF_TCU_PTW_OVERRIDES
to force snooping for MMU write accesses (setting event queue events).

MMU event queue buffer is the only buffer written by MMU and
mapped as write-back which break cache coherency. Force write
transactions to be snooped solving the problem.

Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-2-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_hw_37xx.c | 2 +-
 drivers/accel/ivpu/ivpu_hw_40xx.c | 2 +-
 drivers/accel/ivpu/ivpu_mmu.c     | 3 ---
 3 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index f15a93d830578..77accd029c4a7 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -525,7 +525,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
+	val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 704288084f373..86b89b94f9f3d 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -530,7 +530,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
-	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
 	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 9a3122ffce03c..8df78adeee338 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -560,7 +560,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	mmu->cmdq.cons = 0;
 
 	memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
-	clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
 	mmu->evtq.prod = 0;
 	mmu->evtq.cons = 0;
 
@@ -877,8 +876,6 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
 		return NULL;
 
-	clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
-
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
 	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
 
-- 
GitLab


From b039f1c4d3727c3e44a7e89ff79e7e8533e1beec Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Fri, 26 Jan 2024 13:27:59 +0100
Subject: [PATCH 3936/4076] accel/ivpu: Correct MMU queue size checking
 functions

Do not use kernel CIRC_SPACE and CIRC_CNT that
incorrectly return space of a queue when wrap bit was set.
Use correct implementation that compares producer, consumer and
wrap bit values.

Without this fix it was possible to lose events in case when event
queue was full.

Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-3-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_mmu.c | 33 ++++++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 8df78adeee338..91bd640655ab3 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -72,10 +72,10 @@
 
 #define IVPU_MMU_Q_COUNT_LOG2		4 /* 16 entries */
 #define IVPU_MMU_Q_COUNT		((u32)1 << IVPU_MMU_Q_COUNT_LOG2)
-#define IVPU_MMU_Q_WRAP_BIT		(IVPU_MMU_Q_COUNT << 1)
-#define IVPU_MMU_Q_WRAP_MASK		(IVPU_MMU_Q_WRAP_BIT - 1)
-#define IVPU_MMU_Q_IDX_MASK		(IVPU_MMU_Q_COUNT - 1)
+#define IVPU_MMU_Q_WRAP_MASK            GENMASK(IVPU_MMU_Q_COUNT_LOG2, 0)
+#define IVPU_MMU_Q_IDX_MASK             (IVPU_MMU_Q_COUNT - 1)
 #define IVPU_MMU_Q_IDX(val)		((val) & IVPU_MMU_Q_IDX_MASK)
+#define IVPU_MMU_Q_WRP(val)             ((val) & IVPU_MMU_Q_COUNT)
 
 #define IVPU_MMU_CMDQ_CMD_SIZE		16
 #define IVPU_MMU_CMDQ_SIZE		(IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE)
@@ -475,20 +475,32 @@ static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
 	return 0;
 }
 
+static bool ivpu_mmu_queue_is_full(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) != IVPU_MMU_Q_WRP(q->cons)));
+}
+
+static bool ivpu_mmu_queue_is_empty(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) == IVPU_MMU_Q_WRP(q->cons)));
+}
+
 static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1)
 {
-	struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
-	u64 *queue_buffer = q->base;
-	int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
+	struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
+	u64 *queue_buffer = cmdq->base;
+	int idx = IVPU_MMU_Q_IDX(cmdq->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
 
-	if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) {
+	if (ivpu_mmu_queue_is_full(cmdq)) {
 		ivpu_err(vdev, "Failed to write MMU CMD %s\n", name);
 		return -EBUSY;
 	}
 
 	queue_buffer[idx] = data0;
 	queue_buffer[idx + 1] = data1;
-	q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
+	cmdq->prod = (cmdq->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
 
 	ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1);
 
@@ -873,12 +885,10 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE);
 
 	evtq->prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
-	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
+	if (ivpu_mmu_queue_is_empty(evtq))
 		return NULL;
 
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
-	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
-
 	return evt;
 }
 
@@ -899,6 +909,7 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		}
 
 		ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+		REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
 	}
 }
 
-- 
GitLab


From a7f31091ddf457352e3dd7ac183fdbd26b4dcd04 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Fri, 26 Jan 2024 13:28:00 +0100
Subject: [PATCH 3937/4076] accel/ivpu: Disable d3hot_delay on all NPU
 generations

NPU does not require this delay regardless of the generation.
All generations are integrated into the SOC.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-4-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 9418c73ee8ef8..4b06402269869 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -480,9 +480,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev)
 	/* Clear any pending errors */
 	pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
 
-	/* VPU 37XX does not require 10m D3hot delay */
-	if (ivpu_hw_gen(vdev) == IVPU_HW_37XX)
-		pdev->d3hot_delay = 0;
+	/* NPU does not require 10m D3hot delay */
+	pdev->d3hot_delay = 0;
 
 	ret = pcim_enable_device(pdev);
 	if (ret) {
-- 
GitLab


From a939c03d37788e4a9a645c88d5e5b6a475ba0fd5 Mon Sep 17 00:00:00 2001
From: Krystian Pradzynski <krystian.pradzynski@intel.com>
Date: Fri, 26 Jan 2024 13:28:02 +0100
Subject: [PATCH 3938/4076] accel/ivpu/40xx: Enable D0i3 message

All recent 40xx firmware already supports D0i3 entry message and this
WA is no longer needed.

Signed-off-by: Krystian Pradzynski <krystian.pradzynski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-6-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_fw.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 6576232f3e678..5fa8bd4603d5b 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -222,7 +222,6 @@ ivpu_fw_init_wa(struct ivpu_device *vdev)
 	const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
 
 	if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
-	    (ivpu_hw_gen(vdev) > IVPU_HW_37XX) ||
 	    (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
 		vdev->wa.disable_d0i3_msg = true;
 
-- 
GitLab


From 553099da45397914a995dce6307d6c26523c2567 Mon Sep 17 00:00:00 2001
From: Krystian Pradzynski <krystian.pradzynski@intel.com>
Date: Fri, 26 Jan 2024 13:28:03 +0100
Subject: [PATCH 3939/4076] accel/ivpu/40xx: Stop passing SKU boot parameters
 to FW

This parameter was never used by the 40xx FW.

Signed-off-by: Krystian Pradzynski <krystian.pradzynski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-7-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_hw_40xx.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 86b89b94f9f3d..1c995307c1138 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -704,7 +704,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 {
 	struct ivpu_hw_info *hw = vdev->hw;
 	u32 tile_disable;
-	u32 tile_enable;
 	u32 fuse;
 
 	fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE);
@@ -725,10 +724,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 	else
 		ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM);
 
-	tile_enable = (~tile_disable) & TILE_MAX_MASK;
-
-	hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku);
-	hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku);
 	hw->tile_fuse = tile_disable;
 	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
 
-- 
GitLab


From 5f8408aca66772d3aa9b4831577b2ac5ec41bcd9 Mon Sep 17 00:00:00 2001
From: Grzegorz Trzebiatowski <grzegorz.trzebiatowski@intel.com>
Date: Fri, 26 Jan 2024 13:28:04 +0100
Subject: [PATCH 3940/4076] accel/ivpu: Add job status for jobs aborted by the
 driver

Add DRM_IVPU_JOB_STATUS_ABORTED to indicate that the job was aborted
by the driver due to e.g. TDR or user context MMU faults.

This will help UMD and tests distinguish if job was aborted by the FW
or the driver.

Signed-off-by: Grzegorz Trzebiatowski <grzegorz.trzebiatowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-8-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_job.c | 4 ++--
 include/uapi/drm/ivpu_accel.h | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 0440bee3ecafd..e70cfb8593390 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -294,7 +294,7 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 		return -ENOENT;
 
 	if (job->file_priv->has_mmu_faults)
-		job_status = VPU_JSM_STATUS_ABORTED;
+		job_status = DRM_IVPU_JOB_STATUS_ABORTED;
 
 	job->bos[CMD_BUF_IDX]->job_status = job_status;
 	dma_fence_signal(job->done_fence);
@@ -315,7 +315,7 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 	unsigned long id;
 
 	xa_for_each(&vdev->submitted_jobs_xa, id, job)
-		ivpu_job_signal_and_destroy(vdev, id, VPU_JSM_STATUS_ABORTED);
+		ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
 }
 
 static int ivpu_job_submit(struct ivpu_job *job)
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
index 63c49318a8630..19a13468eca5e 100644
--- a/include/uapi/drm/ivpu_accel.h
+++ b/include/uapi/drm/ivpu_accel.h
@@ -305,6 +305,7 @@ struct drm_ivpu_submit {
 
 /* drm_ivpu_bo_wait job status codes */
 #define DRM_IVPU_JOB_STATUS_SUCCESS 0
+#define DRM_IVPU_JOB_STATUS_ABORTED 256
 
 /**
  * struct drm_ivpu_bo_wait - Wait for BO to become inactive
-- 
GitLab


From 1ce2654d87e2fb91fea83b288bd9b2641045e42a Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Sat, 3 Feb 2024 13:31:33 +0800
Subject: [PATCH 3941/4076] net: stmmac: xgmac: fix a typo of register name in
 DPP safety handling

DDPP is copied from Synopsys Data book:

DDPP: Disable Data path Parity Protection.
    When it is 0x0, Data path Parity Protection is enabled.
    When it is 0x1, Data path Parity Protection is disabled.

The macro name should be XGMAC_DPP_DISABLE.

Fixes: 46eba193d04f ("net: stmmac: xgmac: fix handling of DPP safety error for DMA channels")
Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/20240203053133.1129236-1-0x1207@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h      | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 5c67a3f89f088..6a2c7d22df1eb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -304,7 +304,7 @@
 #define XGMAC_TXCEIE			BIT(0)
 #define XGMAC_MTL_ECC_INT_STATUS	0x000010cc
 #define XGMAC_MTL_DPP_CONTROL		0x000010e0
-#define XGMAC_DDPP_DISABLE		BIT(0)
+#define XGMAC_DPP_DISABLE		BIT(0)
 #define XGMAC_MTL_TXQ_OPMODE(x)		(0x00001100 + (0x80 * (x)))
 #define XGMAC_TQS			GENMASK(25, 16)
 #define XGMAC_TQS_SHIFT			16
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 04d7c4dc2e35f..323c57f03c93c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -928,7 +928,7 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
 	/* 5. Enable Data Path Parity Protection */
 	value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL);
 	/* already enabled by default, explicit enable it again */
-	value &= ~XGMAC_DDPP_DISABLE;
+	value &= ~XGMAC_DPP_DISABLE;
 	writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL);
 
 	return 0;
-- 
GitLab


From 853b8d7597eea4ccaaefbcf0942cd42fc86d542a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 2 Feb 2024 12:22:58 +0200
Subject: [PATCH 3942/4076] remap_range: merge do_clone_file_range() into
 vfs_clone_file_range()

commit dfad37051ade ("remap_range: move permission hooks out of
do_clone_file_range()") moved the permission hooks from
do_clone_file_range() out to its caller vfs_clone_file_range(),
but left all the fast sanity checks in do_clone_file_range().

This makes the expensive security hooks be called in situations
that they would not have been called before (e.g. fs does not support
clone).

The only reason for the do_clone_file_range() helper was that overlayfs
did not use to be able to call vfs_clone_file_range() from copy up
context with sb_writers lock held.  However, since commit c63e56a4a652
("ovl: do not open/llseek lower file with upper sb_writers held"),
overlayfs just uses an open coded version of vfs_clone_file_range().

Merge_clone_file_range() into vfs_clone_file_range(), restoring the
original order of checks as it was before the regressing commit and adapt
the overlayfs code to call vfs_clone_file_range() before the permission
hooks that were added by commit ca7ab482401c ("ovl: add permission hooks
outside of do_splice_direct()").

Note that in the merge of do_clone_file_range(), the file_start_write()
context was reduced to cover ->remap_file_range() without holding it
over the permission hooks, which was the reason for doing the regressing
commit in the first place.

Reported-and-tested-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401312229.eddeb9a6-oliver.sang@intel.com
Fixes: dfad37051ade ("remap_range: move permission hooks out of do_clone_file_range()")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20240202102258.1582671-1-amir73il@gmail.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/overlayfs/copy_up.c | 14 ++++++--------
 fs/remap_range.c       | 31 +++++++++----------------------
 include/linux/fs.h     |  3 ---
 3 files changed, 15 insertions(+), 33 deletions(-)

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index b8e25ca51016d..8586e2f5d2439 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -265,20 +265,18 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 	if (IS_ERR(old_file))
 		return PTR_ERR(old_file);
 
+	/* Try to use clone_file_range to clone up within the same fs */
+	cloned = vfs_clone_file_range(old_file, 0, new_file, 0, len, 0);
+	if (cloned == len)
+		goto out_fput;
+
+	/* Couldn't clone, so now we try to copy the data */
 	error = rw_verify_area(READ, old_file, &old_pos, len);
 	if (!error)
 		error = rw_verify_area(WRITE, new_file, &new_pos, len);
 	if (error)
 		goto out_fput;
 
-	/* Try to use clone_file_range to clone up within the same fs */
-	ovl_start_write(dentry);
-	cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
-	ovl_end_write(dentry);
-	if (cloned == len)
-		goto out_fput;
-	/* Couldn't clone, so now we try to copy the data */
-
 	/* Check if lower fs supports seek operation */
 	if (old_file->f_mode & FMODE_LSEEK)
 		skip_hole = true;
diff --git a/fs/remap_range.c b/fs/remap_range.c
index f8c1120b8311f..de07f978ce3eb 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -373,9 +373,9 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 }
 EXPORT_SYMBOL(generic_remap_file_range_prep);
 
-loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-			   struct file *file_out, loff_t pos_out,
-			   loff_t len, unsigned int remap_flags)
+loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    loff_t len, unsigned int remap_flags)
 {
 	loff_t ret;
 
@@ -391,23 +391,6 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 	if (!file_in->f_op->remap_file_range)
 		return -EOPNOTSUPP;
 
-	ret = file_in->f_op->remap_file_range(file_in, pos_in,
-			file_out, pos_out, len, remap_flags);
-	if (ret < 0)
-		return ret;
-
-	fsnotify_access(file_in);
-	fsnotify_modify(file_out);
-	return ret;
-}
-EXPORT_SYMBOL(do_clone_file_range);
-
-loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-			    struct file *file_out, loff_t pos_out,
-			    loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
 	ret = remap_verify_area(file_in, pos_in, len, false);
 	if (ret)
 		return ret;
@@ -417,10 +400,14 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 		return ret;
 
 	file_start_write(file_out);
-	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
-				  remap_flags);
+	ret = file_in->f_op->remap_file_range(file_in, pos_in,
+			file_out, pos_out, len, remap_flags);
 	file_end_write(file_out);
+	if (ret < 0)
+		return ret;
 
+	fsnotify_access(file_in);
+	fsnotify_modify(file_out);
 	return ret;
 }
 EXPORT_SYMBOL(vfs_clone_file_range);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed5966a704951..023f37c607094 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2101,9 +2101,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				  struct file *file_out, loff_t pos_out,
 				  loff_t *count, unsigned int remap_flags);
-extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  loff_t len, unsigned int remap_flags);
 extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 				   struct file *file_out, loff_t pos_out,
 				   loff_t len, unsigned int remap_flags);
-- 
GitLab


From f814bdda774c183b0cc15ec8f3b6e7c6f4527ba5 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 23 Jan 2024 18:58:26 +0100
Subject: [PATCH 3943/4076] blk-wbt: Fix detection of dirty-throttled tasks

The detection of dirty-throttled tasks in blk-wbt has been subtly broken
since its beginning in 2016. Namely if we are doing cgroup writeback and
the throttled task is not in the root cgroup, balance_dirty_pages() will
set dirty_sleep for the non-root bdi_writeback structure. However
blk-wbt checks dirty_sleep only in the root cgroup bdi_writeback
structure. Thus detection of recently throttled tasks is not working in
this case (we noticed this when we switched to cgroup v2 and suddently
writeback was slow).

Since blk-wbt has no easy way to get to proper bdi_writeback and
furthermore its intention has always been to work on the whole device
rather than on individual cgroups, just move the dirty_sleep timestamp
from bdi_writeback to backing_dev_info. That fixes the checking for
recently throttled task and saves memory for everybody as a bonus.

CC: stable@vger.kernel.org
Fixes: b57d74aff9ab ("writeback: track if we're sleeping on progress in balance_dirty_pages()")
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240123175826.21452-1-jack@suse.cz
[axboe: fixup indentation errors]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-wbt.c                  | 4 ++--
 include/linux/backing-dev-defs.h | 7 +++++--
 mm/backing-dev.c                 | 2 +-
 mm/page-writeback.c              | 2 +-
 4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 5ba3cd574eacb..0c0e270a82650 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -163,9 +163,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb;
+	struct backing_dev_info *bdi = rwb->rqos.disk->bdi;
 
-	return time_before(jiffies, wb->dirty_sleep + HZ);
+	return time_before(jiffies, bdi->last_bdp_sleep + HZ);
 }
 
 static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index ae12696ec492c..2ad261082bba5 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -141,8 +141,6 @@ struct bdi_writeback {
 	struct delayed_work dwork;	/* work item used for writeback */
 	struct delayed_work bw_dwork;	/* work item used for bandwidth estimate */
 
-	unsigned long dirty_sleep;	/* last wait */
-
 	struct list_head bdi_node;	/* anchored at bdi->wb_list */
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -179,6 +177,11 @@ struct backing_dev_info {
 	 * any dirty wbs, which is depended upon by bdi_has_dirty().
 	 */
 	atomic_long_t tot_write_bandwidth;
+	/*
+	 * Jiffies when last process was dirty throttled on this bdi. Used by
+	 * blk-wbt.
+	 */
+	unsigned long last_bdp_sleep;
 
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
 	struct list_head wb_list; /* list of all wbs */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1e3447bccdb14..e039d05304dd9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -436,7 +436,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_LIST_HEAD(&wb->work_list);
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
 	INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
-	wb->dirty_sleep = jiffies;
 
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
@@ -921,6 +920,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->wb_list);
 	init_waitqueue_head(&bdi->wb_waitq);
+	bdi->last_bdp_sleep = jiffies;
 
 	return cgwb_bdi_init(bdi);
 }
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index cd4e4ae77c40a..cc37fa7f33641 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1921,7 +1921,7 @@ pause:
 			break;
 		}
 		__set_current_state(TASK_KILLABLE);
-		wb->dirty_sleep = now;
+		bdi->last_bdp_sleep = jiffies;
 		io_schedule_timeout(pause);
 
 		current->dirty_paused_when = now + pause;
-- 
GitLab


From 7ed4380009e96d9e9c605e12822e987b35b05648 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Wed, 7 Feb 2024 08:01:17 +0900
Subject: [PATCH 3944/4076] firewire: core: send bus reset promptly on gap
 count error

If we are bus manager and the bus has inconsistent gap counts, send a
bus reset immediately instead of trying to read the root node's config
ROM first. Otherwise, we could spend a lot of time trying to read the
config ROM but never succeeding.

This eliminates a 50+ second delay before the FireWire bus is usable after
a newly connected device is powered on in certain circumstances.

The delay occurs if a gap count inconsistency occurs, we are not the root
node, and we become bus manager. One scenario that causes this is with a TI
XIO2213B OHCI, the first time a Sony DSR-25 is powered on after being
connected to the FireWire cable. In this configuration, the Linux box will
not receive the initial PHY configuration packet sent by the DSR-25 as IRM,
resulting in the DSR-25 having a gap count of 44 while the Linux box has a
gap count of 63.

FireWire devices have a gap count parameter, which is set to 63 on power-up
and can be changed with a PHY configuration packet. This determines the
duration of the subaction and arbitration gaps. For reliable communication,
all nodes on a FireWire bus must have the same gap count.

A node may have zero or more of the following roles: root node, bus manager
(BM), isochronous resource manager (IRM), and cycle master. Unless a root
node was forced with a PHY configuration packet, any node might become root
node after a bus reset. Only the root node can become cycle master. If the
root node is not cycle master capable, the BM or IRM should force a change
of root node.

After a bus reset, each node sends a self-ID packet, which contains its
current gap count. A single bus reset does not change the gap count, but
two bus resets in a row will set the gap count to 63. Because a consistent
gap count is required for reliable communication, IEEE 1394a-2000 requires
that the bus manager generate a bus reset if it detects that the gap count
is inconsistent.

When the gap count is inconsistent, build_tree() will notice this after the
self identification process. It will set card->gap_count to the invalid
value 0. If we become bus master, this will force bm_work() to send a bus
reset when it performs gap count optimization.

After a bus reset, there is no bus manager. We will almost always try to
become bus manager. Once we become bus manager, we will first determine
whether the root node is cycle master capable. Then, we will determine if
the gap count should be changed. If either the root node or the gap count
should be changed, we will generate a bus reset.

To determine if the root node is cycle master capable, we read its
configuration ROM. bm_work() will wait until we have finished trying to
read the configuration ROM.

However, an inconsistent gap count can make this take a long time.
read_config_rom() will read the first few quadlets from the config ROM. Due
to the gap count inconsistency, eventually one of the reads will time out.
When read_config_rom() fails, fw_device_init() calls it again until
MAX_RETRIES is reached. This takes 50+ seconds.

Once we give up trying to read the configuration ROM, bm_work() will wake
up, assume that the root node is not cycle master capable, and do a bus
reset. Hopefully, this will resolve the gap count inconsistency.

This change makes bm_work() check for an inconsistent gap count before
waiting for the root node's configuration ROM. If the gap count is
inconsistent, bm_work() will immediately do a bus reset. This eliminates
the 50+ second delay and rapidly brings the bus to a working state.

I considered that if the gap count is inconsistent, a PHY configuration
packet might not be successful, so it could be desirable to skip the PHY
configuration packet before the bus reset in this case. However, IEEE
1394a-2000 and IEEE 1394-2008 say that the bus manager may transmit a PHY
configuration packet before a bus reset when correcting a gap count error.
Since the standard endorses this, I decided it's safe to retain the PHY
configuration packet transmission.

Normally, after a topology change, we will reset the bus a maximum of 5
times to change the root node and perform gap count optimization. However,
if there is a gap count inconsistency, we must always generate a bus reset.
Otherwise the gap count inconsistency will persist and communication will
be unreliable. For that reason, if there is a gap count inconstency, we
generate a bus reset even if we already reached the 5 reset limit.

Signed-off-by: Adam Goldman <adamg@pobox.com>
Reference: https://sourceforge.net/p/linux1394/mailman/message/58727806/
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/core-card.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c
index 6ac5ff20a2fe2..8aaa7fcb2630d 100644
--- a/drivers/firewire/core-card.c
+++ b/drivers/firewire/core-card.c
@@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work)
 	 */
 	card->bm_generation = generation;
 
-	if (root_device == NULL) {
+	if (card->gap_count == 0) {
+		/*
+		 * If self IDs have inconsistent gap counts, do a
+		 * bus reset ASAP. The config rom read might never
+		 * complete, so don't wait for it. However, still
+		 * send a PHY configuration packet prior to the
+		 * bus reset. The PHY configuration packet might
+		 * fail, but 1394-2008 8.4.5.2 explicitly permits
+		 * it in this case, so it should be safe to try.
+		 */
+		new_root_id = local_id;
+		/*
+		 * We must always send a bus reset if the gap count
+		 * is inconsistent, so bypass the 5-reset limit.
+		 */
+		card->bm_retries = 0;
+	} else if (root_device == NULL) {
 		/*
 		 * Either link_on is false, or we failed to read the
 		 * config rom.  In either case, pick another root.
-- 
GitLab


From 829388b725f8d266ccec32a2f446717d8693eaba Mon Sep 17 00:00:00 2001
From: David Gow <davidgow@google.com>
Date: Thu, 1 Feb 2024 14:04:36 +0800
Subject: [PATCH 3945/4076] kunit: device: Unregister the kunit_bus on shutdown

If KUnit is built as a module, and it's unloaded, the kunit_bus is not
unregistered. This causes an error if it's then re-loaded later, as we
try to re-register the bus.

Unregister the bus and root_device on shutdown, if it looks valid.

In addition, be more specific about the value of kunit_bus_device. It
is:
- a valid struct device* if the kunit_bus initialised correctly.
- an ERR_PTR if it failed to initialise.
- NULL before initialisation and after shutdown.

Fixes: d03c720e03bd ("kunit: Add APIs for managing devices")
Signed-off-by: David Gow <davidgow@google.com>
Reviewed-by: Rae Moar <rmoar@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 lib/kunit/device-impl.h |  2 ++
 lib/kunit/device.c      | 14 ++++++++++++++
 lib/kunit/test.c        |  3 +++
 3 files changed, 19 insertions(+)

diff --git a/lib/kunit/device-impl.h b/lib/kunit/device-impl.h
index 54bd558364053..5fcd48ff0f36a 100644
--- a/lib/kunit/device-impl.h
+++ b/lib/kunit/device-impl.h
@@ -13,5 +13,7 @@
 
 // For internal use only -- registers the kunit_bus.
 int kunit_bus_init(void);
+// For internal use only -- unregisters the kunit_bus.
+void kunit_bus_shutdown(void);
 
 #endif //_KUNIT_DEVICE_IMPL_H
diff --git a/lib/kunit/device.c b/lib/kunit/device.c
index 074c6dd2e36a7..644a38a1f5b1c 100644
--- a/lib/kunit/device.c
+++ b/lib/kunit/device.c
@@ -54,6 +54,20 @@ int kunit_bus_init(void)
 	return error;
 }
 
+/* Unregister the 'kunit_bus' in case the KUnit module is unloaded. */
+void kunit_bus_shutdown(void)
+{
+	/* Make sure the bus exists before we unregister it. */
+	if (IS_ERR_OR_NULL(kunit_bus_device))
+		return;
+
+	bus_unregister(&kunit_bus_type);
+
+	root_device_unregister(kunit_bus_device);
+
+	kunit_bus_device = NULL;
+}
+
 /* Release a 'fake' KUnit device. */
 static void kunit_device_release(struct device *d)
 {
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 31a5a992e6467..1d1475578515c 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -928,6 +928,9 @@ static void __exit kunit_exit(void)
 #ifdef CONFIG_MODULES
 	unregister_module_notifier(&kunit_mod_nb);
 #endif
+
+	kunit_bus_shutdown();
+
 	kunit_debugfs_cleanup();
 }
 module_exit(kunit_exit);
-- 
GitLab


From 97cf301fa42e8ea6e0a24de97bc0abcdc87d9504 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 28 Jan 2024 13:04:05 +0100
Subject: [PATCH 3946/4076] riscv: Flush the tlb when a page directory is freed

The riscv privileged specification mandates to flush the TLB whenever a
page directory is modified, so add that to tlb_flush().

Fixes: c5e9b2c2ae82 ("riscv: Improve tlb_flush()")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240128120405.25876-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/tlb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 1eb5682b2af60..50b63b5c15bd8 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb);
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 #ifdef CONFIG_MMU
-	if (tlb->fullmm || tlb->need_flush_all)
+	if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
 		flush_tlb_mm(tlb->mm);
 	else
 		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,
-- 
GitLab


From 1279f9d9dec2d7462823a18c29ad61359e0a007d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Sat, 3 Feb 2024 10:31:49 -0800
Subject: [PATCH 3947/4076] af_unix: Call kfree_skb() for dead
 unix_(sk)->oob_skb in GC.

syzbot reported a warning [0] in __unix_gc() with a repro, which
creates a socketpair and sends one socket's fd to itself using the
peer.

  socketpair(AF_UNIX, SOCK_STREAM, 0, [3, 4]) = 0
  sendmsg(4, {msg_name=NULL, msg_namelen=0, msg_iov=[{iov_base="\360", iov_len=1}],
          msg_iovlen=1, msg_control=[{cmsg_len=20, cmsg_level=SOL_SOCKET,
                                      cmsg_type=SCM_RIGHTS, cmsg_data=[3]}],
          msg_controllen=24, msg_flags=0}, MSG_OOB|MSG_PROBE|MSG_DONTWAIT|MSG_ZEROCOPY) = 1

This forms a self-cyclic reference that GC should finally untangle
but does not due to lack of MSG_OOB handling, resulting in memory
leak.

Recently, commit 11498715f266 ("af_unix: Remove io_uring code for
GC.") removed io_uring's dead code in GC and revealed the problem.

The code was executed at the final stage of GC and unconditionally
moved all GC candidates from gc_candidates to gc_inflight_list.
That papered over the reported problem by always making the following
WARN_ON_ONCE(!list_empty(&gc_candidates)) false.

The problem has been there since commit 2aab4b969002 ("af_unix: fix
struct pid leaks in OOB support") added full scm support for MSG_OOB
while fixing another bug.

To fix this problem, we must call kfree_skb() for unix_sk(sk)->oob_skb
if the socket still exists in gc_candidates after purging collected skb.

Then, we need to set NULL to oob_skb before calling kfree_skb() because
it calls last fput() and triggers unix_release_sock(), where we call
duplicate kfree_skb(u->oob_skb) if not NULL.

Note that the leaked socket remained being linked to a global list, so
kmemleak also could not detect it.  We need to check /proc/net/protocol
to notice the unfreed socket.

[0]:
WARNING: CPU: 0 PID: 2863 at net/unix/garbage.c:345 __unix_gc+0xc74/0xe80 net/unix/garbage.c:345
Modules linked in:
CPU: 0 PID: 2863 Comm: kworker/u4:11 Not tainted 6.8.0-rc1-syzkaller-00583-g1701940b1a02 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
Workqueue: events_unbound __unix_gc
RIP: 0010:__unix_gc+0xc74/0xe80 net/unix/garbage.c:345
Code: 8b 5c 24 50 e9 86 f8 ff ff e8 f8 e4 22 f8 31 d2 48 c7 c6 30 6a 69 89 4c 89 ef e8 97 ef ff ff e9 80 f9 ff ff e8 dd e4 22 f8 90 <0f> 0b 90 e9 7b fd ff ff 48 89 df e8 5c e7 7c f8 e9 d3 f8 ff ff e8
RSP: 0018:ffffc9000b03fba0 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffffc9000b03fc10 RCX: ffffffff816c493e
RDX: ffff88802c02d940 RSI: ffffffff896982f3 RDI: ffffc9000b03fb30
RBP: ffffc9000b03fce0 R08: 0000000000000001 R09: fffff52001607f66
R10: 0000000000000003 R11: 0000000000000002 R12: dffffc0000000000
R13: ffffc9000b03fc10 R14: ffffc9000b03fc10 R15: 0000000000000001
FS:  0000000000000000(0000) GS:ffff8880b9400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005559c8677a60 CR3: 000000000d57a000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 process_one_work+0x889/0x15e0 kernel/workqueue.c:2633
 process_scheduled_works kernel/workqueue.c:2706 [inline]
 worker_thread+0x8b9/0x12a0 kernel/workqueue.c:2787
 kthread+0x2c6/0x3b0 kernel/kthread.c:388
 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:242
 </TASK>

Reported-by: syzbot+fa3ef895554bdbfd1183@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=fa3ef895554bdbfd1183
Fixes: 2aab4b969002 ("af_unix: fix struct pid leaks in OOB support")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240203183149.63573-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/garbage.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 2405f0f9af31c..8f63f0b4bf012 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -314,6 +314,17 @@ void unix_gc(void)
 	/* Here we are. Hitlist is filled. Die. */
 	__skb_queue_purge(&hitlist);
 
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	list_for_each_entry_safe(u, next, &gc_candidates, link) {
+		struct sk_buff *skb = u->oob_skb;
+
+		if (skb) {
+			u->oob_skb = NULL;
+			kfree_skb(skb);
+		}
+	}
+#endif
+
 	spin_lock(&unix_gc_lock);
 
 	/* There could be io_uring registered files, just push them back to
-- 
GitLab


From 58086721b7781c3e35b19c9b78c8f5a791070ba3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 5 Feb 2024 18:11:14 +0100
Subject: [PATCH 3948/4076] devlink: avoid potential loop in
 devlink_rel_nested_in_notify_work()

In case devlink_rel_nested_in_notify_work() can not take the devlink
lock mutex. Convert the work to delayed work and in case of reschedule
do it jiffie later and avoid potential looping.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Fixes: c137743bce02 ("devlink: introduce object and nested devlink relationship infra")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240205171114.338679-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/devlink/core.c b/net/devlink/core.c
index 4275a2bc6d8e0..6a58342752b46 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -46,7 +46,7 @@ struct devlink_rel {
 		u32 obj_index;
 		devlink_rel_notify_cb_t *notify_cb;
 		devlink_rel_cleanup_cb_t *cleanup_cb;
-		struct work_struct notify_work;
+		struct delayed_work notify_work;
 	} nested_in;
 };
 
@@ -70,7 +70,7 @@ static void __devlink_rel_put(struct devlink_rel *rel)
 static void devlink_rel_nested_in_notify_work(struct work_struct *work)
 {
 	struct devlink_rel *rel = container_of(work, struct devlink_rel,
-					       nested_in.notify_work);
+					       nested_in.notify_work.work);
 	struct devlink *devlink;
 
 	devlink = devlinks_xa_get(rel->nested_in.devlink_index);
@@ -96,13 +96,13 @@ rel_put:
 	return;
 
 reschedule_work:
-	schedule_work(&rel->nested_in.notify_work);
+	schedule_delayed_work(&rel->nested_in.notify_work, 1);
 }
 
 static void devlink_rel_nested_in_notify_work_schedule(struct devlink_rel *rel)
 {
 	__devlink_rel_get(rel);
-	schedule_work(&rel->nested_in.notify_work);
+	schedule_delayed_work(&rel->nested_in.notify_work, 0);
 }
 
 static struct devlink_rel *devlink_rel_alloc(void)
@@ -123,8 +123,8 @@ static struct devlink_rel *devlink_rel_alloc(void)
 	}
 
 	refcount_set(&rel->refcount, 1);
-	INIT_WORK(&rel->nested_in.notify_work,
-		  &devlink_rel_nested_in_notify_work);
+	INIT_DELAYED_WORK(&rel->nested_in.notify_work,
+			  &devlink_rel_nested_in_notify_work);
 	return rel;
 }
 
-- 
GitLab


From cb88cb53badb8aeb3955ad6ce80b07b598e310b8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 5 Feb 2024 17:10:04 +0000
Subject: [PATCH 3949/4076] ppp_async: limit MRU to 64K

syzbot triggered a warning [1] in __alloc_pages():

WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp)

Willem fixed a similar issue in commit c0a2a1b0d631 ("ppp: limit MRU to 64K")

Adopt the same sanity check for ppp_async_ioctl(PPPIOCSMRU)

[1]:

 WARNING: CPU: 1 PID: 11 at mm/page_alloc.c:4543 __alloc_pages+0x308/0x698 mm/page_alloc.c:4543
Modules linked in:
CPU: 1 PID: 11 Comm: kworker/u4:0 Not tainted 6.8.0-rc2-syzkaller-g41bccc98fb79 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
Workqueue: events_unbound flush_to_ldisc
pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : __alloc_pages+0x308/0x698 mm/page_alloc.c:4543
 lr : __alloc_pages+0xc8/0x698 mm/page_alloc.c:4537
sp : ffff800093967580
x29: ffff800093967660 x28: ffff8000939675a0 x27: dfff800000000000
x26: ffff70001272ceb4 x25: 0000000000000000 x24: ffff8000939675c0
x23: 0000000000000000 x22: 0000000000060820 x21: 1ffff0001272ceb8
x20: ffff8000939675e0 x19: 0000000000000010 x18: ffff800093967120
x17: ffff800083bded5c x16: ffff80008ac97500 x15: 0000000000000005
x14: 1ffff0001272cebc x13: 0000000000000000 x12: 0000000000000000
x11: ffff70001272cec1 x10: 1ffff0001272cec0 x9 : 0000000000000001
x8 : ffff800091c91000 x7 : 0000000000000000 x6 : 000000000000003f
x5 : 00000000ffffffff x4 : 0000000000000000 x3 : 0000000000000020
x2 : 0000000000000008 x1 : 0000000000000000 x0 : ffff8000939675e0
Call trace:
  __alloc_pages+0x308/0x698 mm/page_alloc.c:4543
  __alloc_pages_node include/linux/gfp.h:238 [inline]
  alloc_pages_node include/linux/gfp.h:261 [inline]
  __kmalloc_large_node+0xbc/0x1fc mm/slub.c:3926
  __do_kmalloc_node mm/slub.c:3969 [inline]
  __kmalloc_node_track_caller+0x418/0x620 mm/slub.c:4001
  kmalloc_reserve+0x17c/0x23c net/core/skbuff.c:590
  __alloc_skb+0x1c8/0x3d8 net/core/skbuff.c:651
  __netdev_alloc_skb+0xb8/0x3e8 net/core/skbuff.c:715
  netdev_alloc_skb include/linux/skbuff.h:3235 [inline]
  dev_alloc_skb include/linux/skbuff.h:3248 [inline]
  ppp_async_input drivers/net/ppp/ppp_async.c:863 [inline]
  ppp_asynctty_receive+0x588/0x186c drivers/net/ppp/ppp_async.c:341
  tty_ldisc_receive_buf+0x12c/0x15c drivers/tty/tty_buffer.c:390
  tty_port_default_receive_buf+0x74/0xac drivers/tty/tty_port.c:37
  receive_buf drivers/tty/tty_buffer.c:444 [inline]
  flush_to_ldisc+0x284/0x6e4 drivers/tty/tty_buffer.c:494
  process_one_work+0x694/0x1204 kernel/workqueue.c:2633
  process_scheduled_works kernel/workqueue.c:2706 [inline]
  worker_thread+0x938/0xef4 kernel/workqueue.c:2787
  kthread+0x288/0x310 kernel/kthread.c:388
  ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:860

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-and-tested-by: syzbot+c5da1f087c9e4ec6c933@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240205171004.1059724-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ppp/ppp_async.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 840da924708b3..125793d8aefa7 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -460,6 +460,10 @@ ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg)
 	case PPPIOCSMRU:
 		if (get_user(val, p))
 			break;
+		if (val > U16_MAX) {
+			err = -EINVAL;
+			break;
+		}
 		if (val < PPP_MRU)
 			val = PPP_MRU;
 		ap->mru = val;
-- 
GitLab


From 38cc3c6dcc09dc3a1800b5ec22aef643ca11eab8 Mon Sep 17 00:00:00 2001
From: Petr Tesarik <petr@tesarici.cz>
Date: Sat, 3 Feb 2024 20:09:27 +0100
Subject: [PATCH 3950/4076] net: stmmac: protect updates of 64-bit statistics
 counters

As explained by a comment in <linux/u64_stats_sync.h>, write side of struct
u64_stats_sync must ensure mutual exclusion, or one seqcount update could
be lost on 32-bit platforms, thus blocking readers forever. Such lockups
have been observed in real world after stmmac_xmit() on one CPU raced with
stmmac_napi_poll_tx() on another CPU.

To fix the issue without introducing a new lock, split the statics into
three parts:

1. fields updated only under the tx queue lock,
2. fields updated only during NAPI poll,
3. fields updated only from interrupt context,

Updates to fields in the first two groups are already serialized through
other locks. It is sufficient to split the existing struct u64_stats_sync
so that each group has its own.

Note that tx_set_ic_bit is updated from both contexts. Split this counter
so that each context gets its own, and calculate their sum to get the total
value in stmmac_get_ethtool_stats().

For the third group, multiple interrupts may be processed by different CPUs
at the same time, but interrupts on the same CPU will not nest. Move fields
from this group to a newly created per-cpu struct stmmac_pcpu_stats.

Fixes: 133466c3bbe1 ("net: stmmac: use per-queue 64 bit statistics where necessary")
Link: https://lore.kernel.org/netdev/Za173PhviYg-1qIn@torres.zugschlus.de/t/
Cc: stable@vger.kernel.org
Signed-off-by: Petr Tesarik <petr@tesarici.cz>
Reviewed-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  |  56 +++++---
 .../net/ethernet/stmicro/stmmac/dwmac-sun8i.c |  15 +-
 .../net/ethernet/stmicro/stmmac/dwmac4_lib.c  |  15 +-
 .../net/ethernet/stmicro/stmmac/dwmac_lib.c   |  15 +-
 .../ethernet/stmicro/stmmac/dwxgmac2_dma.c    |  15 +-
 .../ethernet/stmicro/stmmac/stmmac_ethtool.c  | 129 +++++++++++------
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 133 +++++++++---------
 7 files changed, 221 insertions(+), 157 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index b4f60ab078d67..5ba606a596e77 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -59,28 +59,51 @@
 #undef FRAME_FILTER_DEBUG
 /* #define FRAME_FILTER_DEBUG */
 
+struct stmmac_q_tx_stats {
+	u64_stats_t tx_bytes;
+	u64_stats_t tx_set_ic_bit;
+	u64_stats_t tx_tso_frames;
+	u64_stats_t tx_tso_nfrags;
+};
+
+struct stmmac_napi_tx_stats {
+	u64_stats_t tx_packets;
+	u64_stats_t tx_pkt_n;
+	u64_stats_t poll;
+	u64_stats_t tx_clean;
+	u64_stats_t tx_set_ic_bit;
+};
+
 struct stmmac_txq_stats {
-	u64 tx_bytes;
-	u64 tx_packets;
-	u64 tx_pkt_n;
-	u64 tx_normal_irq_n;
-	u64 napi_poll;
-	u64 tx_clean;
-	u64 tx_set_ic_bit;
-	u64 tx_tso_frames;
-	u64 tx_tso_nfrags;
-	struct u64_stats_sync syncp;
+	/* Updates protected by tx queue lock. */
+	struct u64_stats_sync q_syncp;
+	struct stmmac_q_tx_stats q;
+
+	/* Updates protected by NAPI poll logic. */
+	struct u64_stats_sync napi_syncp;
+	struct stmmac_napi_tx_stats napi;
 } ____cacheline_aligned_in_smp;
 
+struct stmmac_napi_rx_stats {
+	u64_stats_t rx_bytes;
+	u64_stats_t rx_packets;
+	u64_stats_t rx_pkt_n;
+	u64_stats_t poll;
+};
+
 struct stmmac_rxq_stats {
-	u64 rx_bytes;
-	u64 rx_packets;
-	u64 rx_pkt_n;
-	u64 rx_normal_irq_n;
-	u64 napi_poll;
-	struct u64_stats_sync syncp;
+	/* Updates protected by NAPI poll logic. */
+	struct u64_stats_sync napi_syncp;
+	struct stmmac_napi_rx_stats napi;
 } ____cacheline_aligned_in_smp;
 
+/* Updates on each CPU protected by not allowing nested irqs. */
+struct stmmac_pcpu_stats {
+	struct u64_stats_sync syncp;
+	u64_stats_t rx_normal_irq_n[MTL_MAX_TX_QUEUES];
+	u64_stats_t tx_normal_irq_n[MTL_MAX_RX_QUEUES];
+};
+
 /* Extra statistic and debug information exposed by ethtool */
 struct stmmac_extra_stats {
 	/* Transmit errors */
@@ -205,6 +228,7 @@ struct stmmac_extra_stats {
 	/* per queue statistics */
 	struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES];
 	struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES];
+	struct stmmac_pcpu_stats __percpu *pcpu_stats;
 	unsigned long rx_dropped;
 	unsigned long rx_errors;
 	unsigned long tx_dropped;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 137741b94122e..b21d99faa2d04 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -441,8 +441,7 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 				     struct stmmac_extra_stats *x, u32 chan,
 				     u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 	u32 v;
 
@@ -455,9 +454,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 
 	if (v & EMAC_TX_INT) {
 		ret |= handle_tx;
-		u64_stats_update_begin(&txq_stats->syncp);
-		txq_stats->tx_normal_irq_n++;
-		u64_stats_update_end(&txq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 	}
 
 	if (v & EMAC_TX_DMA_STOP_INT)
@@ -479,9 +478,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 
 	if (v & EMAC_RX_INT) {
 		ret |= handle_rx;
-		u64_stats_update_begin(&rxq_stats->syncp);
-		rxq_stats->rx_normal_irq_n++;
-		u64_stats_update_end(&rxq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 	}
 
 	if (v & EMAC_RX_BUF_UA_INT)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index 9470d3fd2dede..0d185e54eb7e2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -171,8 +171,7 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs;
 	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan));
 	u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan));
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 
 	if (dir == DMA_DIR_RX)
@@ -201,15 +200,15 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	}
 	/* TX/RX NORMAL interrupts */
 	if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
-		u64_stats_update_begin(&rxq_stats->syncp);
-		rxq_stats->rx_normal_irq_n++;
-		u64_stats_update_end(&rxq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 		ret |= handle_rx;
 	}
 	if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
-		u64_stats_update_begin(&txq_stats->syncp);
-		txq_stats->tx_normal_irq_n++;
-		u64_stats_update_end(&txq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 		ret |= handle_tx;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 7907d62d34375..85e18f9a22f92 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -162,8 +162,7 @@ static void show_rx_process_state(unsigned int status)
 int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 			struct stmmac_extra_stats *x, u32 chan, u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 	/* read the status register (CSR5) */
 	u32 intr_status = readl(ioaddr + DMA_STATUS);
@@ -215,16 +214,16 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 			u32 value = readl(ioaddr + DMA_INTR_ENA);
 			/* to schedule NAPI on real RIE event. */
 			if (likely(value & DMA_INTR_ENA_RIE)) {
-				u64_stats_update_begin(&rxq_stats->syncp);
-				rxq_stats->rx_normal_irq_n++;
-				u64_stats_update_end(&rxq_stats->syncp);
+				u64_stats_update_begin(&stats->syncp);
+				u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+				u64_stats_update_end(&stats->syncp);
 				ret |= handle_rx;
 			}
 		}
 		if (likely(intr_status & DMA_STATUS_TI)) {
-			u64_stats_update_begin(&txq_stats->syncp);
-			txq_stats->tx_normal_irq_n++;
-			u64_stats_update_end(&txq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_tx;
 		}
 		if (unlikely(intr_status & DMA_STATUS_ERI))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 3cde695fec91b..dd2ab6185c40e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -337,8 +337,7 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 				  struct stmmac_extra_stats *x, u32 chan,
 				  u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
 	u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
 	int ret = 0;
@@ -367,15 +366,15 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 	/* TX/RX NORMAL interrupts */
 	if (likely(intr_status & XGMAC_NIS)) {
 		if (likely(intr_status & XGMAC_RI)) {
-			u64_stats_update_begin(&rxq_stats->syncp);
-			rxq_stats->rx_normal_irq_n++;
-			u64_stats_update_end(&rxq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_rx;
 		}
 		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
-			u64_stats_update_begin(&txq_stats->syncp);
-			txq_stats->tx_normal_irq_n++;
-			u64_stats_update_end(&txq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_tx;
 		}
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 42d27b97dd1d0..ec44becf0e2d2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -549,44 +549,79 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	}
 }
 
+static u64 stmmac_get_rx_normal_irq_n(struct stmmac_priv *priv, int q)
+{
+	u64 total;
+	int cpu;
+
+	total = 0;
+	for_each_possible_cpu(cpu) {
+		struct stmmac_pcpu_stats *pcpu;
+		unsigned int start;
+		u64 irq_n;
+
+		pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu);
+		do {
+			start = u64_stats_fetch_begin(&pcpu->syncp);
+			irq_n = u64_stats_read(&pcpu->rx_normal_irq_n[q]);
+		} while (u64_stats_fetch_retry(&pcpu->syncp, start));
+		total += irq_n;
+	}
+	return total;
+}
+
+static u64 stmmac_get_tx_normal_irq_n(struct stmmac_priv *priv, int q)
+{
+	u64 total;
+	int cpu;
+
+	total = 0;
+	for_each_possible_cpu(cpu) {
+		struct stmmac_pcpu_stats *pcpu;
+		unsigned int start;
+		u64 irq_n;
+
+		pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu);
+		do {
+			start = u64_stats_fetch_begin(&pcpu->syncp);
+			irq_n = u64_stats_read(&pcpu->tx_normal_irq_n[q]);
+		} while (u64_stats_fetch_retry(&pcpu->syncp, start));
+		total += irq_n;
+	}
+	return total;
+}
+
 static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	unsigned int start;
-	int q, stat;
-	char *p;
+	int q;
 
 	for (q = 0; q < tx_cnt; q++) {
 		struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q];
-		struct stmmac_txq_stats snapshot;
+		u64 pkt_n;
 
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			snapshot = *txq_stats;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			pkt_n = u64_stats_read(&txq_stats->napi.tx_pkt_n);
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
 
-		p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n);
-		for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
-			*data++ = (*(u64 *)p);
-			p += sizeof(u64);
-		}
+		*data++ = pkt_n;
+		*data++ = stmmac_get_tx_normal_irq_n(priv, q);
 	}
 
 	for (q = 0; q < rx_cnt; q++) {
 		struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q];
-		struct stmmac_rxq_stats snapshot;
+		u64 pkt_n;
 
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			snapshot = *rxq_stats;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			pkt_n = u64_stats_read(&rxq_stats->napi.rx_pkt_n);
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
 
-		p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n);
-		for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
-			*data++ = (*(u64 *)p);
-			p += sizeof(u64);
-		}
+		*data++ = pkt_n;
+		*data++ = stmmac_get_rx_normal_irq_n(priv, q);
 	}
 }
 
@@ -645,39 +680,49 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 	pos = j;
 	for (i = 0; i < rx_queues_count; i++) {
 		struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[i];
-		struct stmmac_rxq_stats snapshot;
+		struct stmmac_napi_rx_stats snapshot;
+		u64 n_irq;
 
 		j = pos;
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			snapshot = *rxq_stats;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
-
-		data[j++] += snapshot.rx_pkt_n;
-		data[j++] += snapshot.rx_normal_irq_n;
-		normal_irq_n += snapshot.rx_normal_irq_n;
-		napi_poll += snapshot.napi_poll;
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			snapshot = rxq_stats->napi;
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
+
+		data[j++] += u64_stats_read(&snapshot.rx_pkt_n);
+		n_irq = stmmac_get_rx_normal_irq_n(priv, i);
+		data[j++] += n_irq;
+		normal_irq_n += n_irq;
+		napi_poll += u64_stats_read(&snapshot.poll);
 	}
 
 	pos = j;
 	for (i = 0; i < tx_queues_count; i++) {
 		struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[i];
-		struct stmmac_txq_stats snapshot;
+		struct stmmac_napi_tx_stats napi_snapshot;
+		struct stmmac_q_tx_stats q_snapshot;
+		u64 n_irq;
 
 		j = pos;
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			snapshot = *txq_stats;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
-
-		data[j++] += snapshot.tx_pkt_n;
-		data[j++] += snapshot.tx_normal_irq_n;
-		normal_irq_n += snapshot.tx_normal_irq_n;
-		data[j++] += snapshot.tx_clean;
-		data[j++] += snapshot.tx_set_ic_bit;
-		data[j++] += snapshot.tx_tso_frames;
-		data[j++] += snapshot.tx_tso_nfrags;
-		napi_poll += snapshot.napi_poll;
+			start = u64_stats_fetch_begin(&txq_stats->q_syncp);
+			q_snapshot = txq_stats->q;
+		} while (u64_stats_fetch_retry(&txq_stats->q_syncp, start));
+		do {
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			napi_snapshot = txq_stats->napi;
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
+
+		data[j++] += u64_stats_read(&napi_snapshot.tx_pkt_n);
+		n_irq = stmmac_get_tx_normal_irq_n(priv, i);
+		data[j++] += n_irq;
+		normal_irq_n += n_irq;
+		data[j++] += u64_stats_read(&napi_snapshot.tx_clean);
+		data[j++] += u64_stats_read(&q_snapshot.tx_set_ic_bit) +
+			u64_stats_read(&napi_snapshot.tx_set_ic_bit);
+		data[j++] += u64_stats_read(&q_snapshot.tx_tso_frames);
+		data[j++] += u64_stats_read(&q_snapshot.tx_tso_nfrags);
+		napi_poll += u64_stats_read(&napi_snapshot.poll);
 	}
 	normal_irq_n += priv->xstats.rx_early_irq;
 	data[j++] = normal_irq_n;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 25519952f754c..75d0297045032 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2482,7 +2482,6 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	struct xdp_desc xdp_desc;
 	bool work_done = true;
 	u32 tx_set_ic_bit = 0;
-	unsigned long flags;
 
 	/* Avoids TX time-out as we are sharing with slow path */
 	txq_trans_cond_update(nq);
@@ -2566,9 +2565,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size);
 		entry = tx_q->cur_tx;
 	}
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_set_ic_bit += tx_set_ic_bit;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_add(&txq_stats->napi.tx_set_ic_bit, tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	if (tx_desc) {
 		stmmac_flush_tx_descriptors(priv, queue);
@@ -2616,7 +2615,6 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 	unsigned int bytes_compl = 0, pkts_compl = 0;
 	unsigned int entry, xmits = 0, count = 0;
 	u32 tx_packets = 0, tx_errors = 0;
-	unsigned long flags;
 
 	__netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue));
 
@@ -2782,11 +2780,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 	if (tx_q->dirty_tx != tx_q->cur_tx)
 		*pending_packets = true;
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_packets += tx_packets;
-	txq_stats->tx_pkt_n += tx_packets;
-	txq_stats->tx_clean++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_add(&txq_stats->napi.tx_packets, tx_packets);
+	u64_stats_add(&txq_stats->napi.tx_pkt_n, tx_packets);
+	u64_stats_inc(&txq_stats->napi.tx_clean);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	priv->xstats.tx_errors += tx_errors;
 
@@ -4213,7 +4211,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_tx_queue *tx_q;
 	bool has_vlan, set_ic;
 	u8 proto_hdr_len, hdr;
-	unsigned long flags;
 	u32 pay_len, mss;
 	dma_addr_t des;
 	int i;
@@ -4378,13 +4375,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_bytes += skb->len;
-	txq_stats->tx_tso_frames++;
-	txq_stats->tx_tso_nfrags += nfrags;
+	u64_stats_update_begin(&txq_stats->q_syncp);
+	u64_stats_add(&txq_stats->q.tx_bytes, skb->len);
+	u64_stats_inc(&txq_stats->q.tx_tso_frames);
+	u64_stats_add(&txq_stats->q.tx_tso_nfrags, nfrags);
 	if (set_ic)
-		txq_stats->tx_set_ic_bit++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->q_syncp);
 
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4483,7 +4480,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_tx_queue *tx_q;
 	bool has_vlan, set_ic;
 	int entry, first_tx;
-	unsigned long flags;
 	dma_addr_t des;
 
 	tx_q = &priv->dma_conf.tx_queue[queue];
@@ -4653,11 +4649,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_bytes += skb->len;
+	u64_stats_update_begin(&txq_stats->q_syncp);
+	u64_stats_add(&txq_stats->q.tx_bytes, skb->len);
 	if (set_ic)
-		txq_stats->tx_set_ic_bit++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->q_syncp);
 
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4921,12 +4917,11 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 		set_ic = false;
 
 	if (set_ic) {
-		unsigned long flags;
 		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, tx_desc);
-		flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-		txq_stats->tx_set_ic_bit++;
-		u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_update_begin(&txq_stats->q_syncp);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+		u64_stats_update_end(&txq_stats->q_syncp);
 	}
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -5076,7 +5071,6 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 	unsigned int len = xdp->data_end - xdp->data;
 	enum pkt_hash_types hash_type;
 	int coe = priv->hw->rx_csum;
-	unsigned long flags;
 	struct sk_buff *skb;
 	u32 hash;
 
@@ -5106,10 +5100,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 	skb_record_rx_queue(skb, queue);
 	napi_gro_receive(&ch->rxtx_napi, skb);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_pkt_n++;
-	rxq_stats->rx_bytes += len;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.rx_pkt_n);
+	u64_stats_add(&rxq_stats->napi.rx_bytes, len);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 }
 
 static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -5191,7 +5185,6 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int desc_size;
 	struct bpf_prog *prog;
 	bool failure = false;
-	unsigned long flags;
 	int xdp_status = 0;
 	int status = 0;
 
@@ -5346,9 +5339,9 @@ read_again:
 
 	stmmac_finalize_xdp_rx(priv, xdp_status);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_pkt_n += count;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_add(&rxq_stats->napi.rx_pkt_n, count);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	priv->xstats.rx_dropped += rx_dropped;
 	priv->xstats.rx_errors += rx_errors;
@@ -5386,7 +5379,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int desc_size;
 	struct sk_buff *skb = NULL;
 	struct stmmac_xdp_buff ctx;
-	unsigned long flags;
 	int xdp_status = 0;
 	int buf_sz;
 
@@ -5646,11 +5638,11 @@ drain_data:
 
 	stmmac_rx_refill(priv, queue);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_packets += rx_packets;
-	rxq_stats->rx_bytes += rx_bytes;
-	rxq_stats->rx_pkt_n += count;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_add(&rxq_stats->napi.rx_packets, rx_packets);
+	u64_stats_add(&rxq_stats->napi.rx_bytes, rx_bytes);
+	u64_stats_add(&rxq_stats->napi.rx_pkt_n, count);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	priv->xstats.rx_dropped += rx_dropped;
 	priv->xstats.rx_errors += rx_errors;
@@ -5665,13 +5657,12 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget)
 	struct stmmac_priv *priv = ch->priv_data;
 	struct stmmac_rxq_stats *rxq_stats;
 	u32 chan = ch->index;
-	unsigned long flags;
 	int work_done;
 
 	rxq_stats = &priv->xstats.rxq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.poll);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	work_done = stmmac_rx(priv, budget, chan);
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
@@ -5693,13 +5684,12 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
 	struct stmmac_txq_stats *txq_stats;
 	bool pending_packets = false;
 	u32 chan = ch->index;
-	unsigned long flags;
 	int work_done;
 
 	txq_stats = &priv->xstats.txq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_inc(&txq_stats->napi.poll);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	work_done = stmmac_tx_clean(priv, budget, chan, &pending_packets);
 	work_done = min(work_done, budget);
@@ -5729,17 +5719,16 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget)
 	struct stmmac_rxq_stats *rxq_stats;
 	struct stmmac_txq_stats *txq_stats;
 	u32 chan = ch->index;
-	unsigned long flags;
 
 	rxq_stats = &priv->xstats.rxq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.poll);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	txq_stats = &priv->xstats.txq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_inc(&txq_stats->napi.poll);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	tx_done = stmmac_tx_clean(priv, budget, chan, &tx_pending_packets);
 	tx_done = min(tx_done, budget);
@@ -7065,10 +7054,13 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
 		u64 tx_bytes;
 
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			tx_packets = txq_stats->tx_packets;
-			tx_bytes   = txq_stats->tx_bytes;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&txq_stats->q_syncp);
+			tx_bytes   = u64_stats_read(&txq_stats->q.tx_bytes);
+		} while (u64_stats_fetch_retry(&txq_stats->q_syncp, start));
+		do {
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			tx_packets = u64_stats_read(&txq_stats->napi.tx_packets);
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
 
 		stats->tx_packets += tx_packets;
 		stats->tx_bytes += tx_bytes;
@@ -7080,10 +7072,10 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
 		u64 rx_bytes;
 
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			rx_packets = rxq_stats->rx_packets;
-			rx_bytes   = rxq_stats->rx_bytes;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			rx_packets = u64_stats_read(&rxq_stats->napi.rx_packets);
+			rx_bytes   = u64_stats_read(&rxq_stats->napi.rx_bytes);
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
 
 		stats->rx_packets += rx_packets;
 		stats->rx_bytes += rx_bytes;
@@ -7477,9 +7469,16 @@ int stmmac_dvr_probe(struct device *device,
 	priv->dev = ndev;
 
 	for (i = 0; i < MTL_MAX_RX_QUEUES; i++)
-		u64_stats_init(&priv->xstats.rxq_stats[i].syncp);
-	for (i = 0; i < MTL_MAX_TX_QUEUES; i++)
-		u64_stats_init(&priv->xstats.txq_stats[i].syncp);
+		u64_stats_init(&priv->xstats.rxq_stats[i].napi_syncp);
+	for (i = 0; i < MTL_MAX_TX_QUEUES; i++) {
+		u64_stats_init(&priv->xstats.txq_stats[i].q_syncp);
+		u64_stats_init(&priv->xstats.txq_stats[i].napi_syncp);
+	}
+
+	priv->xstats.pcpu_stats =
+		devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats);
+	if (!priv->xstats.pcpu_stats)
+		return -ENOMEM;
 
 	stmmac_set_ethtool_ops(ndev);
 	priv->pause = pause;
-- 
GitLab


From 4b00d0c513da58b68df015968721b11396fe4ab3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 4 Feb 2024 08:56:18 -0800
Subject: [PATCH 3951/4076] selftests: cmsg_ipv6: repeat the exact packet

cmsg_ipv6 test requests tcpdump to capture 4 packets,
and sends until tcpdump quits. Only the first packet
is "real", however, and the rest are basic UDP packets.
So if tcpdump doesn't start in time it will miss
the real packet and only capture the UDP ones.

This makes the test fail on slow machine (no KVM or with
debug enabled) 100% of the time, while it passes in fast
environments.

Repeat the "real" / expected packet.

Fixes: 9657ad09e1fa ("selftests: net: test IPV6_TCLASS")
Fixes: 05ae83d5a4a2 ("selftests: net: test IPV6_HOPLIMIT")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/cmsg_ipv6.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
index f30bd57d5e387..8bc23fb4c82b7 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ipv6.sh
@@ -89,7 +89,7 @@ for ovr in setsock cmsg both diff; do
 	check_result $? 0 "TCLASS $prot $ovr - pass"
 
 	while [ -d /proc/$BG ]; do
-	    $NSEXE ./cmsg_sender -6 -p u $TGT6 1234
+	    $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
 	done
 
 	tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null
@@ -126,7 +126,7 @@ for ovr in setsock cmsg both diff; do
 	check_result $? 0 "HOPLIMIT $prot $ovr - pass"
 
 	while [ -d /proc/$BG ]; do
-	    $NSEXE ./cmsg_sender -6 -p u $TGT6 1234
+	    $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
 	done
 
 	tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null
-- 
GitLab


From cd7d469c25704d414d71bf3644f163fb74e7996b Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Fri, 13 Oct 2023 13:55:44 +0800
Subject: [PATCH 3952/4076] libceph: fail sparse-read if the data length
 doesn't match

Once this happens that means there have bugs.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h |  3 ++-
 net/ceph/osd_client.c           | 18 +++++++++++++++---
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fa018d5864e74..f66f6aac74f6f 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -45,6 +45,7 @@ enum ceph_sparse_read_state {
 	CEPH_SPARSE_READ_HDR	= 0,
 	CEPH_SPARSE_READ_EXTENTS,
 	CEPH_SPARSE_READ_DATA_LEN,
+	CEPH_SPARSE_READ_DATA_PRE,
 	CEPH_SPARSE_READ_DATA,
 };
 
@@ -64,7 +65,7 @@ struct ceph_sparse_read {
 	u64				sr_req_len;  /* orig request length */
 	u64				sr_pos;      /* current pos in buffer */
 	int				sr_index;    /* current extent index */
-	__le32				sr_datalen;  /* length of actual data */
+	u32				sr_datalen;  /* length of actual data */
 	u32				sr_count;    /* extent count in reply */
 	int				sr_ext_len;  /* length of extent array */
 	struct ceph_sparse_extent	*sr_extent;  /* extent array */
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 625622016f576..2cea35e4ff8ef 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5857,8 +5857,8 @@ static int osd_sparse_read(struct ceph_connection *con,
 	struct ceph_osd *o = con->private;
 	struct ceph_sparse_read *sr = &o->o_sparse_read;
 	u32 count = sr->sr_count;
-	u64 eoff, elen;
-	int ret;
+	u64 eoff, elen, len = 0;
+	int i, ret;
 
 	switch (sr->sr_state) {
 	case CEPH_SPARSE_READ_HDR:
@@ -5903,8 +5903,20 @@ next_op:
 		convert_extent_map(sr);
 		ret = sizeof(sr->sr_datalen);
 		*pbuf = (char *)&sr->sr_datalen;
-		sr->sr_state = CEPH_SPARSE_READ_DATA;
+		sr->sr_state = CEPH_SPARSE_READ_DATA_PRE;
 		break;
+	case CEPH_SPARSE_READ_DATA_PRE:
+		/* Convert sr_datalen to host-endian */
+		sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen);
+		for (i = 0; i < count; i++)
+			len += sr->sr_extent[i].len;
+		if (sr->sr_datalen != len) {
+			pr_warn_ratelimited("data len %u != extent len %llu\n",
+					    sr->sr_datalen, len);
+			return -EREMOTEIO;
+		}
+		sr->sr_state = CEPH_SPARSE_READ_DATA;
+		fallthrough;
 	case CEPH_SPARSE_READ_DATA:
 		if (sr->sr_index >= count) {
 			sr->sr_state = CEPH_SPARSE_READ_HDR;
-- 
GitLab


From ee97302fbc0c98a25732d736fc73aaf4d62c4128 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 14 Dec 2023 09:21:15 +0800
Subject: [PATCH 3953/4076] libceph: rename read_sparse_msg_*() to
 read_partial_sparse_msg_*()

These functions are supposed to behave like other read_partial_*()
handlers: the contract with messenger v1 is that the handler bails if
the area of the message it's responsible for is already processed.
This comes up when handling short reads from the socket.

[ idryomov: changelog ]

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Acked-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/messenger_v1.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index f9a50d7f0d204..4cb60bacf5f5b 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -991,7 +991,7 @@ static inline int read_partial_message_section(struct ceph_connection *con,
 	return read_partial_message_chunk(con, section, sec_len, crc);
 }
 
-static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
+static int read_partial_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
 {
 	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
 	bool do_bounce = ceph_test_opt(from_msgr(con->msgr), RXBOUNCE);
@@ -1026,7 +1026,7 @@ static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
 	return 1;
 }
 
-static int read_sparse_msg_data(struct ceph_connection *con)
+static int read_partial_sparse_msg_data(struct ceph_connection *con)
 {
 	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
 	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
@@ -1043,7 +1043,7 @@ static int read_sparse_msg_data(struct ceph_connection *con)
 							 con->v1.in_sr_len,
 							 &crc);
 		else if (cursor->sr_resid > 0)
-			ret = read_sparse_msg_extent(con, &crc);
+			ret = read_partial_sparse_msg_extent(con, &crc);
 
 		if (ret <= 0) {
 			if (do_datacrc)
@@ -1254,7 +1254,7 @@ static int read_partial_message(struct ceph_connection *con)
 			return -EIO;
 
 		if (m->sparse_read)
-			ret = read_sparse_msg_data(con);
+			ret = read_partial_sparse_msg_data(con);
 		else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
 			ret = read_partial_msg_data_bounce(con);
 		else
-- 
GitLab


From 8e46a2d068c92a905d01cbb018b00d66991585ab Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 14 Dec 2023 16:01:03 +0800
Subject: [PATCH 3954/4076] libceph: just wait for more data to be available on
 the socket

A short read may occur while reading the message footer from the
socket.  Later, when the socket is ready for another read, the
messenger invokes all read_partial_*() handlers, including
read_partial_sparse_msg_data().  The expectation is that
read_partial_sparse_msg_data() would bail, allowing the messenger to
invoke read_partial() for the footer and pick up where it left off.

However read_partial_sparse_msg_data() violates that and ends up
calling into the state machine in the OSD client.  The sparse-read
state machine assumes that it's a new op and interprets some piece of
the footer as the sparse-read header and returns bogus extents/data
length, etc.

To determine whether read_partial_sparse_msg_data() should bail, let's
reuse cursor->total_resid.  Because once it reaches to zero that means
all the extents and data have been successfully received in last read,
else it could break out when partially reading any of the extents and
data.  And then osd_sparse_read() could continue where it left off.

[ idryomov: changelog ]

Link: https://tracker.ceph.com/issues/63586
Fixes: d396f89db39a ("libceph: add sparse read support to msgr1")
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  2 +-
 net/ceph/messenger_v1.c        | 25 +++++++++++++------------
 net/ceph/messenger_v2.c        |  4 ++--
 net/ceph/osd_client.c          |  9 +++------
 4 files changed, 19 insertions(+), 21 deletions(-)

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 2eaaabbe98cb6..1717cc57cdacd 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -283,7 +283,7 @@ struct ceph_msg {
 	struct kref kref;
 	bool more_to_follow;
 	bool needs_out_seq;
-	bool sparse_read;
+	u64 sparse_read_total;
 	int front_alloc_len;
 
 	struct ceph_msgpool *pool;
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index 4cb60bacf5f5b..0cb61c76b9b87 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -160,8 +160,9 @@ static size_t sizeof_footer(struct ceph_connection *con)
 static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
 {
 	/* Initialize data cursor if it's not a sparse read */
-	if (!msg->sparse_read)
-		ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
+	u64 len = msg->sparse_read_total ? : data_len;
+
+	ceph_msg_data_cursor_init(&msg->cursor, msg, len);
 }
 
 /*
@@ -1036,7 +1037,7 @@ static int read_partial_sparse_msg_data(struct ceph_connection *con)
 	if (do_datacrc)
 		crc = con->in_data_crc;
 
-	do {
+	while (cursor->total_resid) {
 		if (con->v1.in_sr_kvec.iov_base)
 			ret = read_partial_message_chunk(con,
 							 &con->v1.in_sr_kvec,
@@ -1044,23 +1045,23 @@ static int read_partial_sparse_msg_data(struct ceph_connection *con)
 							 &crc);
 		else if (cursor->sr_resid > 0)
 			ret = read_partial_sparse_msg_extent(con, &crc);
-
-		if (ret <= 0) {
-			if (do_datacrc)
-				con->in_data_crc = crc;
-			return ret;
-		}
+		if (ret <= 0)
+			break;
 
 		memset(&con->v1.in_sr_kvec, 0, sizeof(con->v1.in_sr_kvec));
 		ret = con->ops->sparse_read(con, cursor,
 				(char **)&con->v1.in_sr_kvec.iov_base);
+		if (ret <= 0) {
+			ret = ret ? ret : 1;  /* must return > 0 to indicate success */
+			break;
+		}
 		con->v1.in_sr_len = ret;
-	} while (ret > 0);
+	}
 
 	if (do_datacrc)
 		con->in_data_crc = crc;
 
-	return ret < 0 ? ret : 1;  /* must return > 0 to indicate success */
+	return ret;
 }
 
 static int read_partial_msg_data(struct ceph_connection *con)
@@ -1253,7 +1254,7 @@ static int read_partial_message(struct ceph_connection *con)
 		if (!m->num_data_items)
 			return -EIO;
 
-		if (m->sparse_read)
+		if (m->sparse_read_total)
 			ret = read_partial_sparse_msg_data(con);
 		else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
 			ret = read_partial_msg_data_bounce(con);
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index f8ec60e1aba3a..a0ca5414b333d 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1128,7 +1128,7 @@ static int decrypt_tail(struct ceph_connection *con)
 	struct sg_table enc_sgt = {};
 	struct sg_table sgt = {};
 	struct page **pages = NULL;
-	bool sparse = con->in_msg->sparse_read;
+	bool sparse = !!con->in_msg->sparse_read_total;
 	int dpos = 0;
 	int tail_len;
 	int ret;
@@ -2060,7 +2060,7 @@ static int prepare_read_tail_plain(struct ceph_connection *con)
 	}
 
 	if (data_len(msg)) {
-		if (msg->sparse_read)
+		if (msg->sparse_read_total)
 			con->v2.in_state = IN_S_PREPARE_SPARSE_DATA;
 		else
 			con->v2.in_state = IN_S_PREPARE_READ_DATA;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 2cea35e4ff8ef..9d078b37fe0b9 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5510,7 +5510,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	}
 
 	m = ceph_msg_get(req->r_reply);
-	m->sparse_read = (bool)srlen;
+	m->sparse_read_total = srlen;
 
 	dout("get_reply tid %lld %p\n", tid, m);
 
@@ -5777,11 +5777,8 @@ static int prep_next_sparse_read(struct ceph_connection *con,
 	}
 
 	if (o->o_sparse_op_idx < 0) {
-		u64 srlen = sparse_data_requested(req);
-
-		dout("%s: [%d] starting new sparse read req. srlen=0x%llx\n",
-		     __func__, o->o_osd, srlen);
-		ceph_msg_data_cursor_init(cursor, con->in_msg, srlen);
+		dout("%s: [%d] starting new sparse read req\n",
+		     __func__, o->o_osd);
 	} else {
 		u64 end;
 
-- 
GitLab


From bbb20ea993f46743f7429092ddc52f1a5c5428ef Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 18 Jan 2024 14:24:41 +0800
Subject: [PATCH 3955/4076] ceph: always set initial i_blkbits to
 CEPH_FSCRYPT_BLOCK_SHIFT

The fscrypt code will use i_blkbits to setup ci_data_unit_bits when
allocating the new inode, but ceph will initiate i_blkbits ater when
filling the inode, which is too late. Since ci_data_unit_bits will only
be used by the fscrypt framework so initiating i_blkbits with
CEPH_FSCRYPT_BLOCK_SHIFT is safe.

Link: https://tracker.ceph.com/issues/64035
Fixes: 5b1188847180 ("fscrypt: support crypto data unit size less than filesystem block size")
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/inode.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 0c25d326afc41..7b2e77517f235 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -78,6 +78,8 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
+	inode->i_blkbits = CEPH_FSCRYPT_BLOCK_SHIFT;
+
 	if (!S_ISLNK(*mode)) {
 		err = ceph_pre_init_acls(dir, mode, as_ctx);
 		if (err < 0)
-- 
GitLab


From cda4672da1c26835dcbd7aec2bfed954eda9b5ef Mon Sep 17 00:00:00 2001
From: Rishabh Dave <ridave@redhat.com>
Date: Thu, 1 Feb 2024 17:07:16 +0530
Subject: [PATCH 3956/4076] ceph: prevent use-after-free in encode_cap_msg()

In fs/ceph/caps.c, in encode_cap_msg(), "use after free" error was
caught by KASAN at this line - 'ceph_buffer_get(arg->xattr_buf);'. This
implies before the refcount could be increment here, it was freed.

In same file, in "handle_cap_grant()" refcount is decremented by this
line - 'ceph_buffer_put(ci->i_xattrs.blob);'. It appears that a race
occurred and resource was freed by the latter line before the former
line could increment it.

encode_cap_msg() is called by __send_cap() and __send_cap() is called by
ceph_check_caps() after calling __prep_cap(). __prep_cap() is where
arg->xattr_buf is assigned to ci->i_xattrs.blob. This is the spot where
the refcount must be increased to prevent "use after free" error.

Cc: stable@vger.kernel.org
Link: https://tracker.ceph.com/issues/59259
Signed-off-by: Rishabh Dave <ridave@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 9c02f328c966c..e8bf082105d87 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1452,7 +1452,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 	if (flushing & CEPH_CAP_XATTR_EXCL) {
 		arg->old_xattr_buf = __ceph_build_xattrs_blob(ci);
 		arg->xattr_version = ci->i_xattrs.version;
-		arg->xattr_buf = ci->i_xattrs.blob;
+		arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob);
 	} else {
 		arg->xattr_buf = NULL;
 		arg->old_xattr_buf = NULL;
@@ -1553,6 +1553,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
 	encode_cap_msg(msg, arg);
 	ceph_con_send(&arg->session->s_con, msg);
 	ceph_buffer_put(arg->old_xattr_buf);
+	ceph_buffer_put(arg->xattr_buf);
 	if (arg->wake)
 		wake_up_all(&ci->i_cap_wq);
 }
-- 
GitLab


From 07045648c07c5632e0dfd5ce084d3cd0cec0258a Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 4 Jan 2024 09:21:30 +0800
Subject: [PATCH 3957/4076] ceph: always check dir caps asynchronously

The MDS will issue the 'Fr' caps for async dirop, while there is
buggy in kclient and it could miss releasing the async dirop caps,
which is 'Fsxr'. And then the MDS will complain with:

"[WRN] client.xxx isn't responding to mclientcaps(revoke) ..."

So when releasing the dirop async requests or when they fail we
should always make sure that being revoked caps could be released.

Link: https://tracker.ceph.com/issues/50223
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c       | 6 ------
 fs/ceph/mds_client.c | 9 ++++-----
 fs/ceph/mds_client.h | 2 +-
 fs/ceph/super.h      | 2 --
 4 files changed, 5 insertions(+), 14 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index e8bf082105d87..ad1f46c66fbff 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3216,7 +3216,6 @@ static int ceph_try_drop_cap_snap(struct ceph_inode_info *ci,
 
 enum put_cap_refs_mode {
 	PUT_CAP_REFS_SYNC = 0,
-	PUT_CAP_REFS_NO_CHECK,
 	PUT_CAP_REFS_ASYNC,
 };
 
@@ -3332,11 +3331,6 @@ void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had)
 	__ceph_put_cap_refs(ci, had, PUT_CAP_REFS_ASYNC);
 }
 
-void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, int had)
-{
-	__ceph_put_cap_refs(ci, had, PUT_CAP_REFS_NO_CHECK);
-}
-
 /*
  * Release @nr WRBUFFER refs on dirty pages for the given @snapc snap
  * context.  Adjust per-snap dirty page accounting as appropriate.
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 548d1de379f35..f71bb9c9569fc 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1089,7 +1089,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 	struct ceph_mds_request *req = container_of(kref,
 						    struct ceph_mds_request,
 						    r_kref);
-	ceph_mdsc_release_dir_caps_no_check(req);
+	ceph_mdsc_release_dir_caps_async(req);
 	destroy_reply_info(&req->r_reply_info);
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
@@ -4261,7 +4261,7 @@ void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req)
 	}
 }
 
-void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
+void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req)
 {
 	struct ceph_client *cl = req->r_mdsc->fsc->client;
 	int dcaps;
@@ -4269,8 +4269,7 @@ void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
 	dcaps = xchg(&req->r_dir_caps, 0);
 	if (dcaps) {
 		doutc(cl, "releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
-		ceph_put_cap_refs_no_check_caps(ceph_inode(req->r_parent),
-						dcaps);
+		ceph_put_cap_refs_async(ceph_inode(req->r_parent), dcaps);
 	}
 }
 
@@ -4306,7 +4305,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 		if (req->r_session->s_mds != session->s_mds)
 			continue;
 
-		ceph_mdsc_release_dir_caps_no_check(req);
+		ceph_mdsc_release_dir_caps_async(req);
 
 		__send_request(session, req, true);
 	}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 2e6ddaa13d725..40560af388272 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -552,7 +552,7 @@ extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 				struct inode *dir,
 				struct ceph_mds_request *req);
 extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req);
-extern void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req);
+extern void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req);
 static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
 {
 	kref_get(&req->r_kref);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b06e2bc86221b..b63b4cd9b5b68 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1255,8 +1255,6 @@ extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps,
 extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps);
 extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had);
 extern void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had);
-extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci,
-					    int had);
 extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				       struct ceph_snap_context *snapc);
 extern void __ceph_remove_capsnap(struct inode *inode,
-- 
GitLab


From 5001bfe927b594470f3a2484cb410b8b42a47903 Mon Sep 17 00:00:00 2001
From: Allison Henderson <allison.henderson@oracle.com>
Date: Mon, 5 Feb 2024 12:03:43 -0700
Subject: [PATCH 3958/4076] MAINTAINERS: Maintainer change for rds

At this point, Santosh has moved onto other things and I am happy
to take over the role of rds maintainer. Update the MAINTAINERS
accordingly.

Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
Link: https://lore.kernel.org/r/20240205190343.112436-1-allison.henderson@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 722b894f305ed..e3e670ee56108 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18433,7 +18433,7 @@ S:	Supported
 F:	drivers/infiniband/sw/rdmavt
 
 RDS - RELIABLE DATAGRAM SOCKETS
-M:	Santosh Shilimkar <santosh.shilimkar@oracle.com>
+M:	Allison Henderson <allison.henderson@oracle.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 L:	rds-devel@oss.oracle.com (moderated for non-subscribers)
-- 
GitLab


From 75428f537d7cae33c7e4dd726144074f78622c09 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Mon, 5 Feb 2024 18:29:06 -0800
Subject: [PATCH 3959/4076] net: intel: fix old compiler regressions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The kernel build regressions/improvements email contained a couple of
issues with old compilers (in fact all the reports were on different
architectures, but all gcc 5.5) and the FIELD_PREP() and FIELD_GET()
conversions. They're all because an integer #define that should have
been declared as unsigned, was shifted to the point that it could set
the sign bit.

The fix just involves making sure the defines use the "U" identifier on
the constants to make sure they're unsigned. Should make the checkers
happier.

Confirmed with objdump before/after that there is no change to the
binaries.

Issues were reported as follows:
./drivers/net/ethernet/intel/ice/ice_base.c:238:7: note: in expansion of macro 'FIELD_GET'
      (FIELD_GET(GLINT_CTL_ITR_GRAN_25_M, regval) == ICE_ITR_GRAN_US))
       ^
./include/linux/compiler_types.h:435:38: error: call to '__compiletime_assert_1093' declared with attribute error: FIELD_GET: mask is not constant
drivers/net/ethernet/intel/ice/ice_nvm.c:709:16: note: in expansion of macro ‘FIELD_GET’
  orom->major = FIELD_GET(ICE_OROM_VER_MASK, combo_ver);
                ^
./include/linux/compiler_types.h:435:38: error: call to ‘__compiletime_assert_796’ declared with attribute error: FIELD_GET: mask is not constant
drivers/net/ethernet/intel/ice/ice_common.c:945:18: note: in expansion of macro ‘FIELD_GET’
  u8 max_agg_bw = FIELD_GET(GL_PWR_MODE_CTL_CAR_MAX_BW_M,
                  ^
./include/linux/compiler_types.h:435:38: error: call to ‘__compiletime_assert_420’ declared with attribute error: FIELD_GET: mask is not constant
drivers/net/ethernet/intel/i40e/i40e_dcb.c:458:8: note: in expansion of macro ‘FIELD_GET’
  oui = FIELD_GET(I40E_LLDP_TLV_OUI_MASK, ouisubtype);
        ^

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Closes: https://lore.kernel.org/lkml/d03e90ca-8485-4d1b-5ec1-c3398e0e8da@linux-m68k.org/ #i40e #ice
Fixes: 62589808d73b ("i40e: field get conversion")
Fixes: 5a259f8e0baf ("ice: field get conversion")
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Link: https://lore.kernel.org/r/20240206022906.2194214-1-jesse.brandeburg@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_dcb.h | 2 +-
 drivers/net/ethernet/intel/ice/ice_osdep.h | 2 +-
 drivers/net/ethernet/intel/ice/ice_type.h  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index 6b60dc9b77361..d76497566e40e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -43,7 +43,7 @@
 #define I40E_LLDP_TLV_SUBTYPE_SHIFT	0
 #define I40E_LLDP_TLV_SUBTYPE_MASK	(0xFF << I40E_LLDP_TLV_SUBTYPE_SHIFT)
 #define I40E_LLDP_TLV_OUI_SHIFT		8
-#define I40E_LLDP_TLV_OUI_MASK		(0xFFFFFF << I40E_LLDP_TLV_OUI_SHIFT)
+#define I40E_LLDP_TLV_OUI_MASK		(0xFFFFFFU << I40E_LLDP_TLV_OUI_SHIFT)
 
 /* Defines for IEEE ETS TLV */
 #define I40E_IEEE_ETS_MAXTC_SHIFT	0
diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h
index 82bc54fec7f36..a2562f04267f2 100644
--- a/drivers/net/ethernet/intel/ice/ice_osdep.h
+++ b/drivers/net/ethernet/intel/ice/ice_osdep.h
@@ -24,7 +24,7 @@
 #define rd64(a, reg)		readq((a)->hw_addr + (reg))
 
 #define ice_flush(a)		rd32((a), GLGEN_STAT)
-#define ICE_M(m, s)		((m) << (s))
+#define ICE_M(m, s)		((m ## U) << (s))
 
 struct ice_dma_mem {
 	void *va;
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 41ab6d7bbd9ef..a508e917ce5ff 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -1072,7 +1072,7 @@ struct ice_aq_get_set_rss_lut_params {
 #define ICE_OROM_VER_BUILD_SHIFT	8
 #define ICE_OROM_VER_BUILD_MASK		(0xffff << ICE_OROM_VER_BUILD_SHIFT)
 #define ICE_OROM_VER_SHIFT		24
-#define ICE_OROM_VER_MASK		(0xff << ICE_OROM_VER_SHIFT)
+#define ICE_OROM_VER_MASK		(0xffU << ICE_OROM_VER_SHIFT)
 #define ICE_SR_PFA_PTR			0x40
 #define ICE_SR_1ST_NVM_BANK_PTR		0x42
 #define ICE_SR_NVM_BANK_SIZE		0x43
-- 
GitLab


From ce68c035457bdd025a9961e0ba2157323090c581 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 30 Jan 2024 13:01:14 +0100
Subject: [PATCH 3960/4076] riscv: Fix arch_hugetlb_migration_supported() for
 NAPOT

arch_hugetlb_migration_supported() must be reimplemented to add support
for NAPOT hugepages, which is done here.

Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240130120114.106003-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/hugetlb.h |  3 +++
 arch/riscv/mm/hugetlbpage.c      | 16 +++++++++++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index 4c5b0e929890f..20f9c3ba23414 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -11,6 +11,9 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 }
 #define arch_clear_hugepage_flags arch_clear_hugepage_flags
 
+bool arch_hugetlb_migration_supported(struct hstate *h);
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 87406b26c3dad..29c7606414d27 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -364,7 +364,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		pte_clear(mm, addr, ptep);
 }
 
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
 {
 	unsigned long order;
 
@@ -392,7 +392,7 @@ arch_initcall(napot_hugetlbpages_init);
 
 #else
 
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
 {
 	return false;
 }
@@ -409,7 +409,7 @@ int pmd_huge(pmd_t pmd)
 	return pmd_leaf(pmd);
 }
 
-bool __init arch_hugetlb_valid_size(unsigned long size)
+static bool __hugetlb_valid_size(unsigned long size)
 {
 	if (size == HPAGE_SIZE)
 		return true;
@@ -421,6 +421,16 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 		return false;
 }
 
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+	return __hugetlb_valid_size(size);
+}
+
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+	return __hugetlb_valid_size(huge_page_size(h));
+}
+
 #ifdef CONFIG_CONTIG_ALLOC
 static __init int gigantic_pages_init(void)
 {
-- 
GitLab


From 2cf963787529f615f7c93bdcf13a5e82029e7f38 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Thu, 23 Nov 2023 13:42:14 +0000
Subject: [PATCH 3961/4076] riscv: declare overflow_stack as exported from
 traps.c

The percpu area overflow_stacks is exported from arch/riscv/kernel/traps.c
for use in the entry code, but is not declared anywhere. Add the relevant
declaration to arch/riscv/include/asm/stacktrace.h to silence the following
sparse warning:

arch/riscv/kernel/traps.c:395:1: warning: symbol '__pcpu_scope_overflow_stack' was not declared. Should it be static?

We don't add the stackinfo_get_overflow() call as for some of the other
architectures as this doesn't seem to be used yet, so just silence the
warning.

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Fixes: be97d0db5f44 ("riscv: VMAP_STACK overflow detection thread-safe")
Link: https://lore.kernel.org/r/20231123134214.81481-1-ben.dooks@codethink.co.uk
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/stacktrace.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h
index f7e8ef2418b99..b1495a7e06ce6 100644
--- a/arch/riscv/include/asm/stacktrace.h
+++ b/arch/riscv/include/asm/stacktrace.h
@@ -21,4 +21,9 @@ static inline bool on_thread_stack(void)
 	return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
 }
 
+
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+#endif /* CONFIG_VMAP_STACK */
+
 #endif /* _ASM_RISCV_STACKTRACE_H */
-- 
GitLab


From 3951f6add519a8e954bf78691a412f65b24f4715 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 30 Jan 2024 12:55:08 +0100
Subject: [PATCH 3962/4076] riscv: Fix arch_tlbbatch_flush() by clearing the
 batch cpumask

We must clear the cpumask once we have flushed the batch, otherwise cpus
get accumulated and we end sending IPIs to more cpus than needed.

Fixes: 54d7431af73e ("riscv: Add support for BATCHED_UNMAP_TLB_FLUSH")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://lore.kernel.org/r/20240130115508.105386-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/mm/tlbflush.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index dffb0e5bd9425..893566e004b73 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -234,4 +234,5 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
 	__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
 			  FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	cpumask_clear(&batch->cpumask);
 }
-- 
GitLab


From 1f4137e882c621f8ed4bd4da9b10cf91d059e52a Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 6 Feb 2024 09:47:21 -0800
Subject: [PATCH 3963/4076] nvme: move passthrough logging attribute to head

The namespace does not have attributes, but the head does. Move the new
logging attribute to that structure instead of dereferencing the wrong
type.

And while we're here, fix the reverse-tree coding style.

Fixes: 9f079dda14339e ("nvme: allow passthru cmd error logging")
Reported-by: Tasmiya Nalatwad <tasmiya@linux.vnet.ibm.com>
Tested-by: Tasmiya Nalatwad <tasmiya@linux.vnet.ibm.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Alan Adamson <alan.adamson@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c  |  3 +--
 drivers/nvme/host/nvme.h  |  2 +-
 drivers/nvme/host/sysfs.c | 30 +++++++++++++++---------------
 3 files changed, 17 insertions(+), 18 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 975245527c1fc..246e92c05aac4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -713,7 +713,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
 	if (req->q->queuedata) {
 		struct nvme_ns *ns = req->q->disk->private_data;
 
-		logging_enabled = ns->passthru_err_log_enabled;
+		logging_enabled = ns->head->passthru_err_log_enabled;
 		req->timeout = NVME_IO_TIMEOUT;
 	} else { /* no queuedata implies admin queue */
 		logging_enabled = nr->ctrl->passthru_err_log_enabled;
@@ -3696,7 +3696,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 
 	ns->disk = disk;
 	ns->queue = disk->queue;
-	ns->passthru_err_log_enabled = false;
 
 	if (ctrl->opts && ctrl->opts->data_digest)
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 3897334e3950d..7b87763e2f8a6 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -455,6 +455,7 @@ struct nvme_ns_head {
 	struct list_head	entry;
 	struct kref		ref;
 	bool			shared;
+	bool			passthru_err_log_enabled;
 	int			instance;
 	struct nvme_effects_log *effects;
 	u64			nuse;
@@ -523,7 +524,6 @@ struct nvme_ns {
 	struct device		cdev_device;
 
 	struct nvme_fault_inject fault_inject;
-	bool			passthru_err_log_enabled;
 };
 
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index d099218e494a8..f2832f70e7e0a 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -48,8 +48,8 @@ static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
-	int err;
 	bool passthru_err_log_enabled;
+	int err;
 
 	err = kstrtobool(buf, &passthru_err_log_enabled);
 	if (err)
@@ -60,25 +60,34 @@ static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
 	return count;
 }
 
+static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (nvme_disk_is_ns_head(disk))
+		return disk->private_data;
+	return nvme_get_ns_from_dev(dev)->head;
+}
+
 static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct nvme_ns *n = dev_get_drvdata(dev);
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
 
-	return sysfs_emit(buf, n->passthru_err_log_enabled ? "on\n" : "off\n");
+	return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n");
 }
 
 static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
-	struct nvme_ns *ns = dev_get_drvdata(dev);
-	int err;
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
 	bool passthru_err_log_enabled;
+	int err;
 
 	err = kstrtobool(buf, &passthru_err_log_enabled);
 	if (err)
 		return -EINVAL;
-	ns->passthru_err_log_enabled = passthru_err_log_enabled;
+	head->passthru_err_log_enabled = passthru_err_log_enabled;
 
 	return count;
 }
@@ -91,15 +100,6 @@ static struct device_attribute dev_attr_io_passthru_err_log_enabled = \
 	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
 	nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
 
-static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
-{
-	struct gendisk *disk = dev_to_disk(dev);
-
-	if (nvme_disk_is_ns_head(disk))
-		return disk->private_data;
-	return nvme_get_ns_from_dev(dev)->head;
-}
-
 static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
-- 
GitLab


From e8c263ed6de8183e670fbd127c2512292a2ad8eb Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Mon, 5 Feb 2024 16:30:21 -0800
Subject: [PATCH 3964/4076] nvme-core: fix comment to reflect right functions

The functions and the attribute listed in the comment doesn't exists in
the code, (ns->logging_enabled, nvme_passthru_err_log_enabled_store()
and nvme_passthru_err_log_enabled_show())

Update the comment with right function names and a comment
ns->head->passthru_err_log_enabled,
nvme_io_passthru_err_log_enabled_store() and
nvme_io_passthru_err_log_enabled_show().

Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Alan Adamson <alan.adamson@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 246e92c05aac4..60537c9224bf9 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3761,8 +3761,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 
 	/*
 	 * Set ns->disk->device->driver_data to ns so we can access
-	 * ns->logging_enabled in nvme_passthru_err_log_enabled_store() and
-	 * nvme_passthru_err_log_enabled_show().
+	 * ns->head->passthru_err_log_enabled in
+	 * nvme_io_passthru_err_log_enabled_[store | show]().
 	 */
 	dev_set_drvdata(disk_to_dev(ns->disk), ns);
 
-- 
GitLab


From b5d1b4b46f856da1473c7ba9a5cdfcb55c9b2478 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 26 Jan 2024 11:40:37 +0300
Subject: [PATCH 3965/4076] PCI: dwc: Fix a 64bit bug in
 dw_pcie_ep_raise_msix_irq()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The "msg_addr" variable is u64.  However, the "aligned_offset" is an
unsigned int.  This means that when the code does:

  msg_addr &= ~aligned_offset;

it will unintentionally zero out the high 32 bits.  Use ALIGN_DOWN() to do
the alignment instead.

Fixes: 2217fffcd63f ("PCI: dwc: endpoint: Fix dw_pcie_ep_raise_msix_irq() alignment support")
Link: https://lore.kernel.org/r/af59c7ad-ab93-40f7-ad4a-7ac0b14d37f5@moroto.mountain
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: <stable@vger.kernel.org>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 5befed2dc02b7..d6b66597101e4 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -6,6 +6,7 @@
  * Author: Kishon Vijay Abraham I <kishon@ti.com>
  */
 
+#include <linux/align.h>
 #include <linux/bitfield.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -551,7 +552,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	}
 
 	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
-	msg_addr &= ~aligned_offset;
+	msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
 				  epc->mem->window.page_size);
 	if (ret)
-- 
GitLab


From 67057f48df79a3d73683385f521215146861684b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 26 Jan 2024 11:41:01 +0300
Subject: [PATCH 3966/4076] PCI: dwc: Clean up dw_pcie_ep_raise_msi_irq()
 alignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I recently changed the alignment code in dw_pcie_ep_raise_msix_irq().  The
code in dw_pcie_ep_raise_msi_irq() is similar, so update it to match, just
for consistency.  (No effect on runtime, just a cleanup).

Link: https://lore.kernel.org/r/184097e0-c728-42c7-9e8a-556bd33fb612@moroto.mountain
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index d6b66597101e4..9a437cfce073c 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -483,9 +483,10 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 		reg = ep_func->msi_cap + PCI_MSI_DATA_32;
 		msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	}
-	aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1);
-	msg_addr = ((u64)msg_addr_upper) << 32 |
-			(msg_addr_lower & ~aligned_offset);
+	msg_addr = ((u64)msg_addr_upper) << 32 | msg_addr_lower;
+
+	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
+	msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
 				  epc->mem->window.page_size);
 	if (ret)
-- 
GitLab


From 46f5ab762d048dad224436978315cbc2fa79c630 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 6 Feb 2024 11:22:09 +0100
Subject: [PATCH 3967/4076] fs: relax mount_setattr() permission checks

When we added mount_setattr() I added additional checks compared to the
legacy do_reconfigure_mnt() and do_change_type() helpers used by regular
mount(2). If that mount had a parent then verify that the caller and the
mount namespace the mount is attached to match and if not make sure that
it's an anonymous mount.

The real rootfs falls into neither category. It is neither an anoymous
mount because it is obviously attached to the initial mount namespace
but it also obviously doesn't have a parent mount. So that means legacy
mount(2) allows changing mount properties on the real rootfs but
mount_setattr(2) blocks this. I never thought much about this but of
course someone on this planet of earth changes properties on the real
rootfs as can be seen in [1].

Since util-linux finally switched to the new mount api in 2.39 not so
long ago it also relies on mount_setattr() and that surfaced this issue
when Fedora 39 finally switched to it. Fix this.

Link: https://bugzilla.redhat.com/show_bug.cgi?id=2256843
Link: https://lore.kernel.org/r/20240206-vfs-mount-rootfs-v1-1-19b335eee133@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reported-by: Karel Zak <kzak@redhat.com>
Cc: stable@vger.kernel.org # v5.12+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 437f60e96d405..5a51315c66781 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4472,10 +4472,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
 	/*
 	 * If this is an attached mount make sure it's located in the callers
 	 * mount namespace. If it's not don't let the caller interact with it.
-	 * If this is a detached mount make sure it has an anonymous mount
-	 * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE.
+	 *
+	 * If this mount doesn't have a parent it's most often simply a
+	 * detached mount with an anonymous mount namespace. IOW, something
+	 * that's simply not attached yet. But there are apparently also users
+	 * that do change mount properties on the rootfs itself. That obviously
+	 * neither has a parent nor is it a detached mount so we cannot
+	 * unconditionally check for detached mounts.
 	 */
-	if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns)))
+	if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt))
 		goto out;
 
 	/*
-- 
GitLab


From 36fa8d697132b4bed2312d700310e8a78b000c84 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 1 Feb 2024 22:58:36 +0100
Subject: [PATCH 3968/4076] netfilter: nft_compat: narrow down revision to
 unsigned 8-bits

xt_find_revision() expects u8, restrict it to this datatype.

Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_compat.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index f0eeda97bfcd9..001b6841a4b67 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -135,7 +135,7 @@ static void nft_target_eval_bridge(const struct nft_expr *expr,
 
 static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = {
 	[NFTA_TARGET_NAME]	= { .type = NLA_NUL_STRING },
-	[NFTA_TARGET_REV]	= { .type = NLA_U32 },
+	[NFTA_TARGET_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_TARGET_INFO]	= { .type = NLA_BINARY },
 };
 
@@ -419,7 +419,7 @@ static void nft_match_eval(const struct nft_expr *expr,
 
 static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
 	[NFTA_MATCH_NAME]	= { .type = NLA_NUL_STRING },
-	[NFTA_MATCH_REV]	= { .type = NLA_U32 },
+	[NFTA_MATCH_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_MATCH_INFO]	= { .type = NLA_BINARY },
 };
 
@@ -724,7 +724,7 @@ out_put:
 static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = {
 	[NFTA_COMPAT_NAME]	= { .type = NLA_NUL_STRING,
 				    .len = NFT_COMPAT_NAME_MAX-1 },
-	[NFTA_COMPAT_REV]	= { .type = NLA_U32 },
+	[NFTA_COMPAT_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_COMPAT_TYPE]	= { .type = NLA_U32 },
 };
 
-- 
GitLab


From 292781c3c5485ce33bd22b2ef1b2bed709b4d672 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 1 Feb 2024 23:33:29 +0100
Subject: [PATCH 3969/4076] netfilter: nft_compat: reject unused compat flag

Flag (1 << 0) is ignored is set, never used, reject it it with EINVAL
instead.

Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 2 ++
 net/netfilter/nft_compat.c               | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index ca30232b7bc8a..117c6a9b845b1 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -285,9 +285,11 @@ enum nft_rule_attributes {
 /**
  * enum nft_rule_compat_flags - nf_tables rule compat flags
  *
+ * @NFT_RULE_COMPAT_F_UNUSED: unused
  * @NFT_RULE_COMPAT_F_INV: invert the check result
  */
 enum nft_rule_compat_flags {
+	NFT_RULE_COMPAT_F_UNUSED = (1 << 0),
 	NFT_RULE_COMPAT_F_INV	= (1 << 1),
 	NFT_RULE_COMPAT_F_MASK	= NFT_RULE_COMPAT_F_INV,
 };
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 001b6841a4b67..ed71d5ecbe0a5 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -212,7 +212,8 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 		return -EINVAL;
 
 	flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS]));
-	if (flags & ~NFT_RULE_COMPAT_F_MASK)
+	if (flags & NFT_RULE_COMPAT_F_UNUSED ||
+	    flags & ~NFT_RULE_COMPAT_F_MASK)
 		return -EINVAL;
 	if (flags & NFT_RULE_COMPAT_F_INV)
 		*inv = true;
-- 
GitLab


From d694b754894c93fb4d71a7f3699439dec111decc Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 2 Feb 2024 00:05:23 +0100
Subject: [PATCH 3970/4076] netfilter: nft_compat: restrict match/target
 protocol to u16

xt_check_{match,target} expects u16, but NFTA_RULE_COMPAT_PROTO is u32.

NLA_POLICY_MAX(NLA_BE32, 65535) cannot be used because .max in
nla_policy is s16, see 3e48be05f3c7 ("netlink: add attribute range
validation to policy").

Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_compat.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index ed71d5ecbe0a5..1f9474fefe849 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -200,6 +200,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1]
 static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 {
 	struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1];
+	u32 l4proto;
 	u32 flags;
 	int err;
 
@@ -218,7 +219,12 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 	if (flags & NFT_RULE_COMPAT_F_INV)
 		*inv = true;
 
-	*proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+	l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+	if (l4proto > U16_MAX)
+		return -EINVAL;
+
+	*proto = l4proto;
+
 	return 0;
 }
 
-- 
GitLab


From e96fddb32931d007db12b1fce9b5e8e4c080401b Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Sat, 27 Jan 2024 18:34:01 +0530
Subject: [PATCH 3971/4076] drm/amd/display: Fix 'panel_cntl' could be null in
 'dcn21_set_backlight_level()'

'panel_cntl' structure used to control the display panel could be null,
dereferencing it could lead to a null pointer access.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn21/dcn21_hwseq.c:269 dcn21_set_backlight_level() error: we previously assumed 'panel_cntl' could be null (see line 250)

Fixes: 474ac4a875ca ("drm/amd/display: Implement some asic specific abm call backs.")
Cc: Yongqiang Sun <yongqiang.sun@amd.com>
Cc: Anthony Koo <Anthony.Koo@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/hwss/dcn21/dcn21_hwseq.c   | 39 ++++++++++---------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 8e88dcaf88f5b..a9cd39f773604 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -237,34 +237,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
 {
 	struct dc_context *dc = pipe_ctx->stream->ctx;
 	struct abm *abm = pipe_ctx->stream_res.abm;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
+	uint32_t otg_inst;
+
+	if (!abm && !tg && !panel_cntl)
+		return false;
+
+	otg_inst = tg->inst;
 
 	if (dc->dc->res_pool->dmcu) {
 		dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp);
 		return true;
 	}
 
-	if (abm != NULL) {
-		uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
-
-		if (abm && panel_cntl) {
-			if (abm->funcs && abm->funcs->set_pipe_ex) {
-				abm->funcs->set_pipe_ex(abm,
-						otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-			} else {
-					dmub_abm_set_pipe(abm,
-							otg_inst,
-							SET_ABM_PIPE_NORMAL,
-							panel_cntl->inst,
-							panel_cntl->pwrseq_inst);
-			}
-		}
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
+					otg_inst,
+					SET_ABM_PIPE_NORMAL,
+					panel_cntl->inst,
+					panel_cntl->pwrseq_inst);
+	} else {
+		dmub_abm_set_pipe(abm,
+				  otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 
-	if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm)
+	if (abm->funcs && abm->funcs->set_backlight_level_pwm)
 		abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16,
 			frame_ramp, 0, panel_cntl->inst);
 	else
-- 
GitLab


From 66951d98d9bf45ba25acf37fe0747253fafdf298 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 31 Jan 2024 08:49:41 +0530
Subject: [PATCH 3972/4076] drm/amd/display: Add NULL test for 'timing
 generator' in 'dcn21_set_pipe()'

In "u32 otg_inst = pipe_ctx->stream_res.tg->inst;"
pipe_ctx->stream_res.tg could be NULL, it is relying on the caller to
ensure the tg is not NULL.

Fixes: 474ac4a875ca ("drm/amd/display: Implement some asic specific abm call backs.")
Cc: Yongqiang Sun <yongqiang.sun@amd.com>
Cc: Anthony Koo <Anthony.Koo@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/hwss/dcn21/dcn21_hwseq.c   | 24 +++++++++++--------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index a9cd39f773604..5c7f380a84f91 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -206,28 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx)
 void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
 {
 	struct abm *abm = pipe_ctx->stream_res.abm;
-	uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
 	struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
+	uint32_t otg_inst;
+
+	if (!abm && !tg && !panel_cntl)
+		return;
+
+	otg_inst = tg->inst;
 
 	if (dmcu) {
 		dce110_set_pipe(pipe_ctx);
 		return;
 	}
 
-	if (abm && panel_cntl) {
-		if (abm->funcs && abm->funcs->set_pipe_ex) {
-			abm->funcs->set_pipe_ex(abm,
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
 					otg_inst,
 					SET_ABM_PIPE_NORMAL,
 					panel_cntl->inst,
 					panel_cntl->pwrseq_inst);
-		} else {
-				dmub_abm_set_pipe(abm, otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-		}
+	} else {
+		dmub_abm_set_pipe(abm, otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 }
 
-- 
GitLab


From 2103370afba74dda39ff5d2d69163c86644ce528 Mon Sep 17 00:00:00 2001
From: Wenjing Liu <wenjing.liu@amd.com>
Date: Thu, 18 Jan 2024 18:12:15 -0500
Subject: [PATCH 3973/4076] drm/amd/display: set odm_combine_policy based on
 context in dcn32 resource

[why]
When populating dml pipes, odm combine policy should be assigned based
on the pipe topology of the context passed in. DML pipes could be
repopulated multiple times during single validate bandwidth attempt. We
need to make sure that whenever we repopulate the dml pipes it is always
aligned with the updated context. There is a case where DML pipes get
repopulated during FPO optimization after ODM combine policy is changed.
Since in the current code we reinitlaize ODM combine policy, even though
the current context has ODM combine enabled, we overwrite it despite the
pipes are already split. This causes DML to think that MPC combine is
used so we mistakenly enable MPC combine because we apply pipe split
with ODM combine policy reset. This issue doesn't impact non windowed
MPO with ODM case because the legacy policy has restricted use cases. We
don't encounter the case where both ODM and FPO optimizations are
enabled together. So we decide to leave it as is because it is about to
be replaced anyway.

Cc: stable@vger.kernel.org # 6.6+
Reviewed-by: Chaitanya Dhere <chaitanya.dhere@amd.com>
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dml/dcn32/dcn32_fpu.c  | 15 ++++++++++----
 drivers/gpu/drm/amd/display/dc/inc/resource.h | 20 ++++++++-----------
 .../dc/resource/dcn32/dcn32_resource.c        | 16 ++++++++++++++-
 3 files changed, 34 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index dd781a20692ee..ba76dd4a2ce29 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1288,7 +1288,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex
 	return updated;
 }
 
-static bool should_allow_odm_power_optimization(struct dc *dc,
+static bool should_apply_odm_power_optimization(struct dc *dc,
 		struct dc_state *context, struct vba_vars_st *v, int *split,
 		bool *merge)
 {
@@ -1392,9 +1392,12 @@ static void try_odm_power_optimization_and_revalidate(
 {
 	int i;
 	unsigned int new_vlevel;
+	unsigned int cur_policy[MAX_PIPES];
 
-	for (i = 0; i < pipe_cnt; i++)
+	for (i = 0; i < pipe_cnt; i++) {
+		cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy;
 		pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+	}
 
 	new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
 
@@ -1403,6 +1406,9 @@ static void try_odm_power_optimization_and_revalidate(
 		memset(merge, 0, MAX_PIPES * sizeof(bool));
 		*vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge);
 		context->bw_ctx.dml.vba.VoltageLevel = *vlevel;
+	} else {
+		for (i = 0; i < pipe_cnt; i++)
+			pipes[i].pipe.dest.odm_combine_policy = cur_policy[i];
 	}
 }
 
@@ -1580,7 +1586,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 		}
 	}
 
-	if (should_allow_odm_power_optimization(dc, context, vba, split, merge))
+	if (should_apply_odm_power_optimization(dc, context, vba, split, merge))
 		try_odm_power_optimization_and_revalidate(
 				dc, context, pipes, split, merge, vlevel, *pipe_cnt);
 
@@ -2209,7 +2215,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 		int i;
 
 		pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate);
-		dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
+		if (!dc->config.enable_windowed_mpo_odm)
+			dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
 
 		/* repopulate_pipes = 1 means the pipes were either split or merged. In this case
 		 * we have to re-calculate the DET allocation and run through DML once more to
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index c958ef37b78a6..77a60aa9f27bb 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe);
 int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe);
 
 /*
- * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice
- * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for a plane with MPCC combine. otherwise
- * the number of MPC "cuts" for the plane.
+ * Get the number of MPC slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an MPC combine
+ * pipe topology.
  */
-int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head);
+int resource_get_mpc_slice_count(const struct pipe_ctx *pipe);
 
 /*
- * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice
- * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for ODM combine. otherwise
- * the number of ODM "cuts" for the timing.
+ * Get the number of ODM slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an ODM combine
+ * pipe topology.
  */
-int resource_get_odm_slice_count(const struct pipe_ctx *otg_master);
+int resource_get_odm_slice_count(const struct pipe_ctx *pipe);
 
 /* Get the ODM slice index counting from 0 from left most slice */
 int resource_get_odm_slice_index(const struct pipe_ctx *opp_head);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index c4d71e7f18af4..6f10052caeef0 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context(
 		dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt);
 		DC_FP_END();
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
-		pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		if (dc->config.enable_windowed_mpo_odm &&
+				dc->debug.enable_single_display_2to1_odm_policy) {
+			switch (resource_get_odm_slice_count(pipe)) {
+			case 2:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+				break;
+			case 4:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1;
+				break;
+			default:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+			}
+		} else {
+			pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		}
 		pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 		pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19;
-- 
GitLab


From 93bafa32a6918154aa0caf9f66679a32c2431357 Mon Sep 17 00:00:00 2001
From: Prike Liang <Prike.Liang@amd.com>
Date: Tue, 16 Jan 2024 19:10:45 +0800
Subject: [PATCH 3974/4076] drm/amdgpu: skip to program GFXDEC registers for
 suspend abort

In the suspend abort cases, the gfx power rail doesn't turn off so
some GFXDEC registers/CSB can't reset to default value and at this
moment reinitialize GFXDEC/CSB will result in an unexpected error.
So let skip those program sequence for the suspend abort case.

Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     | 2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 ++
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c   | 8 ++++++++
 3 files changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 3d8a48f46b015..6dce81a061ab1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1078,6 +1078,8 @@ struct amdgpu_device {
 	bool				in_s3;
 	bool				in_s4;
 	bool				in_s0ix;
+	/* indicate amdgpu suspension status */
+	bool				suspend_complete;
 
 	enum pp_mp1_state               mp1_state;
 	struct amdgpu_doorbell_index doorbell_index;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 971acf01bea60..211501ea91694 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2476,6 +2476,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = false;
 	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
 	else if (amdgpu_acpi_is_s3_active(adev))
@@ -2490,6 +2491,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = true;
 	if (amdgpu_acpi_should_gpu_reset(adev))
 		return amdgpu_asic_reset(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 69c5009107460..3bc6943365a4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev)
 
 	gfx_v9_0_cp_gfx_enable(adev, true);
 
+	/* Now only limit the quirk on the APU gfx9 series and already
+	 * confirmed that the APU gfx10/gfx11 needn't such update.
+	 */
+	if (adev->flags & AMD_IS_APU &&
+			adev->in_s3 && !adev->suspend_complete) {
+		DRM_INFO(" Will skip the CSB packet resubmit\n");
+		return 0;
+	}
 	r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3);
 	if (r) {
 		DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
-- 
GitLab


From 6ef82ac664bb9568ca3956e0d9c9c478e25077ff Mon Sep 17 00:00:00 2001
From: Prike Liang <Prike.Liang@amd.com>
Date: Wed, 17 Jan 2024 13:39:37 +0800
Subject: [PATCH 3975/4076] drm/amdgpu: reset gpu for s3 suspend abort case

In the s3 suspend abort case some type of gfx9 power
rail not turn off from FCH side and this will put the
GPU in an unknown power status, so let's reset the gpu
to a known good power state before reinitialize gpu
device.

Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/soc15.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 15033efec2bac..c64c01e2944a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1298,10 +1298,32 @@ static int soc15_common_suspend(void *handle)
 	return soc15_common_hw_fini(adev);
 }
 
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg;
+
+	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+	 * 2) S3 suspend abort and TOS already launched.
+	 */
+	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+			!adev->suspend_complete &&
+			sol_reg)
+		return true;
+
+	return false;
+}
+
 static int soc15_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (soc15_need_reset_on_resume(adev)) {
+		dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n");
+		soc15_asic_reset(adev);
+	}
 	return soc15_common_hw_init(adev);
 }
 
-- 
GitLab


From 897925dcc5dfff5b3b23ba991a89fe3ebaca6ef8 Mon Sep 17 00:00:00 2001
From: Li Ma <li.ma@amd.com>
Date: Thu, 1 Feb 2024 19:31:06 +0800
Subject: [PATCH 3976/4076] drm/amdgpu: remove asymmetrical irq disabling in
 jpeg 4.0.5 suspend

A supplement to commit: 615dd56ac5379f4239940be69139a33e79e59c67
There is an irq warning of jpeg during resume in s2idle process. No irq enabled in jpeg 4.0.5 resume.

Fixes: 615dd56ac537 ("drm/amdgpu: remove asymmetrical irq disabling in vcn 4.0.5 suspend")
Signed-off-by: Li Ma <li.ma@amd.com>
Acked-By: Saleemkhan Jamadar <saleemkhan.jamadar@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Reviewed-by: Veerabadhran Gopalakrishnan <Veerabadhran.Gopalakrishnan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c   |  9 ---------
 drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c | 10 ----------
 2 files changed, 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index bc38b90f8cf88..88ea58d5c4abf 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -674,14 +674,6 @@ static int jpeg_v4_0_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned int type,
@@ -765,7 +757,6 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = {
-	.set = jpeg_v4_0_set_interrupt_state,
 	.process = jpeg_v4_0_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 6ede85b28cc8c..78b74daf4eebf 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -181,7 +181,6 @@ static int jpeg_v4_0_5_hw_fini(void *handle)
 			RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
 			jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 	}
-	amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0);
 
 	return 0;
 }
@@ -516,14 +515,6 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_5_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
@@ -603,7 +594,6 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_5_irq_funcs = {
-	.set = jpeg_v4_0_5_set_interrupt_state,
 	.process = jpeg_v4_0_5_process_interrupt,
 };
 
-- 
GitLab


From 280df4996c2bfc0e340ae758ab6da35748853a7e Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Tue, 23 Jan 2024 12:20:06 -0500
Subject: [PATCH 3977/4076] drm/amd/display: Increase eval/entry delay for
 DCN35

[Why]
To match firmware measurements and avoid hanging when accessing HW
that's in idle.

[How]
Increase the delays to what we've measured.

Reviewed-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c    | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 761ec98918756..2142cee6cac23 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -780,8 +780,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.ignore_pg = true,
 	.psp_disabled_wa = true,
-	.ips2_eval_delay_us = 200,
-	.ips2_entry_delay_us = 400,
+	.ips2_eval_delay_us = 1650,
+	.ips2_entry_delay_us = 800,
 	.static_screen_wait_frames = 2,
 };
 
-- 
GitLab


From 2dcf82a8e8dc930655787797ef8a3692b527c7a9 Mon Sep 17 00:00:00 2001
From: "Stanley.Yang" <Stanley.Yang@amd.com>
Date: Mon, 5 Feb 2024 15:55:48 +0800
Subject: [PATCH 3978/4076] drm/amdgpu: Fix shared buff copy to user

ta if invoke node buffer
|-------- ta type ----------|
|--------  ta id  ----------|
|-------- cmd  id ----------|
|------ shared buf len -----|
|------ shared buffer ------|

ta if invoke node buffer is as above, copy shared buffer data to correct location

Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 468a67b302d4c..ca5c86e5f7cd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -362,7 +362,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 		}
 	}
 
-	if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len))
+	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
 err_free_shared_buf:
-- 
GitLab


From e6a7df96facdcf5b1f71eb3ec26f2f9f6ad61e57 Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <jerry.zuo@amd.com>
Date: Mon, 22 Jan 2024 13:43:46 -0500
Subject: [PATCH 3979/4076] drm/amd/display: Fix MST Null Ptr for RV

The change try to fix below error specific to RV platform:

BUG: kernel NULL pointer dereference, address: 0000000000000008
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 4 PID: 917 Comm: sway Not tainted 6.3.9-arch1-1 #1 124dc55df4f5272ccb409f39ef4872fc2b3376a2
Hardware name: LENOVO 20NKS01Y00/20NKS01Y00, BIOS R12ET61W(1.31 ) 07/28/2022
RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper]
Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8>
RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224
RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280
RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850
R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000
R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224
FS:  00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0
Call Trace:
 <TASK>
 ? __die+0x23/0x70
 ? page_fault_oops+0x171/0x4e0
 ? plist_add+0xbe/0x100
 ? exc_page_fault+0x7c/0x180
 ? asm_exc_page_fault+0x26/0x30
 ? drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026]
 ? drm_dp_atomic_find_time_slots+0x28/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026]
 compute_mst_dsc_configs_for_link+0x2ff/0xa40 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
 ? fill_plane_buffer_attributes+0x419/0x510 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
 compute_mst_dsc_configs_for_state+0x1e1/0x250 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
 amdgpu_dm_atomic_check+0xecd/0x1190 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
 drm_atomic_check_only+0x5c5/0xa40
 drm_mode_atomic_ioctl+0x76e/0xbc0
 ? _copy_to_user+0x25/0x30
 ? drm_ioctl+0x296/0x4b0
 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10
 drm_ioctl_kernel+0xcd/0x170
 drm_ioctl+0x26d/0x4b0
 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10
 amdgpu_drm_ioctl+0x4e/0x90 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
 __x64_sys_ioctl+0x94/0xd0
 do_syscall_64+0x60/0x90
 ? do_syscall_64+0x6c/0x90
 entry_SYSCALL_64_after_hwframe+0x72/0xdc
RIP: 0033:0x7f4dad17f76f
Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <89> c>
RSP: 002b:00007ffd9ae859f0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 000055e255a55900 RCX: 00007f4dad17f76f
RDX: 00007ffd9ae85a90 RSI: 00000000c03864bc RDI: 000000000000000b
RBP: 00007ffd9ae85a90 R08: 0000000000000003 R09: 0000000000000003
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000c03864bc
R13: 000000000000000b R14: 000055e255a7fc60 R15: 000055e255a01eb0
 </TASK>
Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device ccm cmac algif_hash algif_skcipher af_alg joydev mousedev bnep >
 typec libphy k10temp ipmi_msghandler roles i2c_scmi acpi_cpufreq mac_hid nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_mas>
CR2: 0000000000000008
---[ end trace 0000000000000000 ]---
RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper]
Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8>
RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224
RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280
RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850
R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000
R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224
FS:  00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0

With a second DP monitor connected, drm_atomic_state in dm atomic check
sequence does not include the connector state for the old/existing/first
DP monitor. In such case, dsc determination policy would hit a null ptr
when it tries to iterate the old/existing stream that does not have a
valid connector state attached to it. When that happens, dm atomic check
should call drm_atomic_get_connector_state for a new connector state.
Existing dm has already done that, except for RV due to it does not have
official support of dsc where .num_dsc is not defined in dcn10 resource
cap, that prevent from getting drm_atomic_get_connector_state called.
So, skip dsc determination policy for ASICs that don't have DSC support.

Cc: stable@vger.kernel.org # 6.1+
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2314
Reviewed-by: Wayne Lin <wayne.lin@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Fangzhi Zuo <jerry.zuo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d292f290cd6eb..59d2eee72a329 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -10731,11 +10731,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 		}
 
-		ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
-		if (ret) {
-			DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
-			ret = -EINVAL;
-			goto fail;
+		if (dc_resource_is_dsc_encoding_supported(dc)) {
+			ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
+			if (ret) {
+				DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+				ret = -EINVAL;
+				goto fail;
+			}
 		}
 
 		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
-- 
GitLab


From ca8179ba11f211cdcb6c12ddd83814eaec999738 Mon Sep 17 00:00:00 2001
From: Alvin Lee <alvin.lee2@amd.com>
Date: Fri, 26 Jan 2024 16:47:20 -0500
Subject: [PATCH 3980/4076] drm/amd/display: Update phantom pipe enable /
 disable sequence

Previously we would call apply_ctx_to_hw to enable and disable
phantom pipes. However, apply_ctx_to_hw can potentially update
non-phantom pipes as well which is undesired. Instead of calling
apply_ctx_to_hw as a whole, call the relevant helpers for each
phantom pipe when enabling / disabling which will avoid us modifying
hardware state for non-phantom pipes unknowingly.

The use case is for an FRL display where FRL_Update is requested
by the display. In this case link_state_valid flag is cleared in
a passive callback thread and should be handled in the next stream /
link update. However, due to the call to apply_ctx_to_hw for the
phantom pipes during a flip, the main pipes were modified outside
of the desired sequence (driver does not handle link_state_valid = 0
on flips).

Cc: stable@vger.kernel.org # 6.6+
Reviewed-by: Samson Tam <samson.tam@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c      |  4 +-
 .../amd/display/dc/hwss/dce110/dce110_hwseq.c |  4 +-
 .../amd/display/dc/hwss/dce110/dce110_hwseq.h |  4 +
 .../amd/display/dc/hwss/dcn20/dcn20_hwseq.c   |  2 +-
 .../amd/display/dc/hwss/dcn20/dcn20_hwseq.h   |  4 +
 .../amd/display/dc/hwss/dcn32/dcn32_hwseq.c   | 76 ++++++++++++++++---
 .../amd/display/dc/hwss/dcn32/dcn32_hwseq.h   |  2 +
 .../amd/display/dc/hwss/dcn32/dcn32_init.c    |  3 +
 .../drm/amd/display/dc/hwss/hw_sequencer.h    |  1 +
 .../display/dc/hwss/hw_sequencer_private.h    |  7 ++
 10 files changed, 94 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index aa7c02ba948e9..2c424e435962d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3817,7 +3817,9 @@ static void commit_planes_for_stream(struct dc *dc,
 		 * programming has completed (we turn on phantom OTG in order
 		 * to complete the plane disable for phantom pipes).
 		 */
-		dc->hwss.apply_ctx_to_hw(dc, context);
+
+		if (dc->hwss.disable_phantom_streams)
+			dc->hwss.disable_phantom_streams(dc, context);
 	}
 
 	if (update_type != UPDATE_TYPE_FAST)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 2352428bcea3c..01493c49bd7a0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1476,7 +1476,7 @@ static enum dc_status dce110_enable_stream_timing(
 	return DC_OK;
 }
 
-static enum dc_status apply_single_controller_ctx_to_hw(
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -2302,7 +2302,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
 			continue;
 
-		status = apply_single_controller_ctx_to_hw(
+		status = dce110_apply_single_controller_ctx_to_hw(
 				pipe_ctx,
 				context,
 				dc);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
index 08028a1779ae8..ed3cc3648e8e2 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
@@ -39,6 +39,10 @@ enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
 		struct dc_state *context);
 
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
 
 void dce110_enable_stream(struct pipe_ctx *pipe_ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 4853ecac53f91..931ac8ed7069d 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -2561,7 +2561,7 @@ void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		tg->funcs->setup_vertical_interrupt2(tg, start_line);
 }
 
-static void dcn20_reset_back_end_for_pipe(
+void dcn20_reset_back_end_for_pipe(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
index b94c85340abff..d950b3e54ec2c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
@@ -84,6 +84,10 @@ enum dc_status dcn20_enable_stream_timing(
 void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_reset_back_end_for_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
 void dcn20_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 6c9299c7683df..aa36d7a56ca8c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -1474,9 +1474,44 @@ void dcn32_update_dsc_pg(struct dc *dc,
 	}
 }
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+	int i;
+
+	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
+		struct pipe_ctx *pipe_ctx_old =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx_old->stream)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(dc->current_state, pipe_ctx_old) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe)
+			continue;
+
+		if (!pipe_ctx->stream || pipe_need_reprogram(pipe_ctx_old, pipe_ctx) ||
+				(pipe_ctx->stream && dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)) {
+			struct clock_source *old_clk = pipe_ctx_old->clock_source;
+
+			if (hws->funcs.reset_back_end_for_pipe)
+				hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
+			if (old_clk)
+				old_clk->funcs->cs_power_down(old_clk);
+		}
+	}
+}
+
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 {
 	unsigned int i;
+	enum dc_status status = DC_OK;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
@@ -1497,16 +1532,39 @@ void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 		}
 	}
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (new_pipe->stream && dc_state_get_pipe_subvp_type(context, new_pipe) == SUBVP_PHANTOM) {
-			// If old context or new context has phantom pipes, apply
-			// the phantom timings now. We can't change the phantom
-			// pipe configuration safely without driver acquiring
-			// the DMCUB lock first.
-			dc->hwss.apply_ctx_to_hw(dc, context);
-			break;
+		struct pipe_ctx *pipe_ctx_old =
+					&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx->stream == pipe_ctx_old->stream &&
+			pipe_ctx->stream->link->link_state_valid) {
+			continue;
 		}
+
+		if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
+			continue;
+
+		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
+			continue;
+
+		if (hws->funcs.apply_single_controller_ctx_to_hw)
+			status = hws->funcs.apply_single_controller_ctx_to_hw(
+					pipe_ctx,
+					context,
+					dc);
+
+		ASSERT(status == DC_OK);
+
+#ifdef CONFIG_DRM_AMD_DC_FP
+		if (hws->funcs.resync_fifo_dccg_dio)
+			hws->funcs.resync_fifo_dccg_dio(hws, dc, context);
+#endif
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
index cecf7f0f56719..069e20bc87c0a 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
@@ -111,6 +111,8 @@ void dcn32_update_dsc_pg(struct dc *dc,
 
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context);
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context);
+
 void dcn32_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
index 427cfc8c24a4b..e8ac94a005b83 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
@@ -109,6 +109,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.get_dcc_en_bits = dcn10_get_dcc_en_bits,
 	.commit_subvp_config = dcn32_commit_subvp_config,
 	.enable_phantom_streams = dcn32_enable_phantom_streams,
+	.disable_phantom_streams = dcn32_disable_phantom_streams,
 	.subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.subvp_pipe_control_lock_fast = dcn32_subvp_pipe_control_lock_fast,
@@ -159,6 +160,8 @@ static const struct hwseq_private_funcs dcn32_private_funcs = {
 	.set_pixels_per_cycle = dcn32_set_pixels_per_cycle,
 	.resync_fifo_dccg_dio = dcn32_resync_fifo_dccg_dio,
 	.is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy,
+	.apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw,
+	.reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe,
 };
 
 void dcn32_hw_sequencer_init_functions(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index a543993833181..64ca7c66509b7 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -379,6 +379,7 @@ struct hw_sequencer_funcs {
 			struct dc_cursor_attributes *cursor_attr);
 	void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
 	void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context);
+	void (*disable_phantom_streams)(struct dc *dc, struct dc_state *context);
 	void (*subvp_pipe_control_lock)(struct dc *dc,
 			struct dc_state *context,
 			bool lock,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
index 6137cf09aa54d..b3c62a82cb1cf 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
@@ -165,8 +165,15 @@ struct hwseq_private_funcs {
 	void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx);
 	void (*resync_fifo_dccg_dio)(struct dce_hwseq *hws, struct dc *dc,
 			struct dc_state *context);
+	enum dc_status (*apply_single_controller_ctx_to_hw)(
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context,
+			struct dc *dc);
 	bool (*is_dp_dig_pixel_rate_div_policy)(struct pipe_ctx *pipe_ctx);
 #endif
+	void (*reset_back_end_for_pipe)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context);
 };
 
 struct dce_hwseq {
-- 
GitLab


From 29c5da1a124671caa87c4a936c625432c16ad8ca Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Date: Thu, 11 Jan 2024 14:25:27 -0700
Subject: [PATCH 3981/4076] drm/amd/display: Disable ODM by default for DCN35

Just ensure that ODM optimization is disabled by default.

Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 2142cee6cac23..1c3d89264ef72 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -2130,6 +2130,7 @@ static bool dcn35_resource_construct(
 	dc->dml2_options.dcn_pipe_count = pool->base.pipe_count;
 	dc->dml2_options.use_native_pstate_optimization = true;
 	dc->dml2_options.use_native_soc_bb_construction = true;
+	dc->dml2_options.minimize_dispclk_using_odm = false;
 	if (dc->config.EnableMinDispClkODM)
 		dc->dml2_options.minimize_dispclk_using_odm = true;
 	dc->dml2_options.enable_windowed_mpo_odm = dc->config.enable_windowed_mpo_odm;
-- 
GitLab


From 55173942a63668bdc1d61812c7c9e0406aefb5bf Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 31 Jan 2024 16:34:32 +0530
Subject: [PATCH 3982/4076] drm/amdgpu: Avoid fetching VRAM vendor info

The present way to fetch VRAM vendor information turns out to be not
reliable on GFX 9.4.3 dGPUs as well. Avoid using the data.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 40a00ea0009f6..e67a62db9e126 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1947,14 +1947,6 @@ static int gmc_v9_0_init_mem_ranges(struct amdgpu_device *adev)
 
 static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
 {
-	static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
-	u32 vram_info;
-
-	/* Only for dGPU, vendor informaton is reliable */
-	if (!amdgpu_sriov_vf(adev) && !(adev->flags & AMD_IS_APU)) {
-		vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
-		adev->gmc.vram_vendor = vram_info & 0xF;
-	}
 	adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
 	adev->gmc.vram_width = 128 * 64;
 }
-- 
GitLab


From da48914e1fcdbf57f6b95d4552fcc088e6547ce4 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 2 Feb 2024 18:30:59 -0600
Subject: [PATCH 3983/4076] drm/amd/display: Clear phantom stream count and
 plane count

When dc_state_destruct() was refactored the new phantom_stream_count
and phantom_plane_count members weren't cleared.

Fixes: 012a04b1d6af ("drm/amd/display: Refactor phantom resource allocation")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_state.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 88c6436b28b69..180ac47868c22 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -291,11 +291,14 @@ void dc_state_destruct(struct dc_state *state)
 		dc_stream_release(state->phantom_streams[i]);
 		state->phantom_streams[i] = NULL;
 	}
+	state->phantom_stream_count = 0;
 
 	for (i = 0; i < state->phantom_plane_count; i++) {
 		dc_plane_state_release(state->phantom_planes[i]);
 		state->phantom_planes[i] = NULL;
 	}
+	state->phantom_plane_count = 0;
+
 	state->stream_mask = 0;
 	memset(&state->res_ctx, 0, sizeof(state->res_ctx));
 	memset(&state->pp_display_cfg, 0, sizeof(state->pp_display_cfg));
-- 
GitLab


From e63e35f0164c43fbc1adb481d6604f253b9f9667 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 5 Feb 2024 14:54:05 -0700
Subject: [PATCH 3984/4076] drm/amd/display: Increase frame-larger-than for all
 display_mode_vba files

After a recent change in LLVM, allmodconfig (which has CONFIG_KCSAN=y
and CONFIG_WERROR=y enabled) has a few new instances of
-Wframe-larger-than for the mode support and system configuration
functions:

  drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn20/display_mode_vba_20v2.c:3393:6: error: stack frame size (2144) exceeds limit (2048) in 'dml20v2_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than]
   3393 | void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib)
        |      ^
  1 error generated.

  drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn21/display_mode_vba_21.c:3520:6: error: stack frame size (2192) exceeds limit (2048) in 'dml21_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than]
   3520 | void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib)
        |      ^
  1 error generated.

  drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn20/display_mode_vba_20.c:3286:6: error: stack frame size (2128) exceeds limit (2048) in 'dml20_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than]
   3286 | void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib)
        |      ^
  1 error generated.

Without the sanitizers enabled, there are no warnings.

This was the catalyst for commit 6740ec97bcdb ("drm/amd/display:
Increase frame warning limit with KASAN or KCSAN in dml2") and that same
change was made to dml in commit 5b750b22530f ("drm/amd/display:
Increase frame warning limit with KASAN or KCSAN in dml") but the
frame_warn_flag variable was not applied to all files. Do so now to
clear up the warnings and make all these files consistent.

Cc: stable@vger.kernel.org
Closes: https://github.com/ClangBuiltLinux/linux/issue/1990
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/Makefile | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 6042a5a6a44f8..59ade76ffb18d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
-- 
GitLab


From 58fca355ad37dcb5f785d9095db5f748b79c5dc2 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 7 Feb 2024 10:20:57 +0530
Subject: [PATCH 3985/4076] drm/amd/display: Implement bounds check for stream
 encoder creation in DCN301

'stream_enc_regs' array is an array of dcn10_stream_enc_registers
structures. The array is initialized with four elements, corresponding
to the four calls to stream_enc_regs() in the array initializer. This
means that valid indices for this array are 0, 1, 2, and 3.

The error message 'stream_enc_regs' 4 <= 5 below, is indicating that
there is an attempt to access this array with an index of 5, which is
out of bounds. This could lead to undefined behavior

Here, eng_id is used as an index to access the stream_enc_regs array. If
eng_id is 5, this would result in an out-of-bounds access on the
stream_enc_regs array.

Thus fixing Buffer overflow error in dcn301_stream_encoder_create
reported by Smatch:
drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn301/dcn301_resource.c:1011 dcn301_stream_encoder_create() error: buffer overflow 'stream_enc_regs' 4 <= 5

Fixes: 3a83e4e64bb1 ("drm/amd/display: Add dcn3.01 support to DC (v2)")
Cc: Roman Li <Roman.Li@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 511ff6b5b9856..7538b548c5725 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -999,7 +999,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id
 	vpg = dcn301_vpg_create(ctx, vpg_inst);
 	afmt = dcn301_afmt_create(ctx, afmt_inst);
 
-	if (!enc1 || !vpg || !afmt) {
+	if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) {
 		kfree(enc1);
 		kfree(vpg);
 		kfree(afmt);
-- 
GitLab


From 534c8a5b9d5d41d30cdcac93cfa1bca5e17be009 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 8 Dec 2023 13:48:22 +0530
Subject: [PATCH 3986/4076] drm/amdgpu: Fix HDP flush for VFs on nbio v7.9

HDP flush remapping is not done for VFs. Keep the original offsets in VF
environment.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index e90f337808034..b4723d68eab0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -431,6 +431,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
 	u32 inst_mask;
 	int i;
 
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset =
+			SOC15_REG_OFFSET(
+				NBIO, 0,
+				regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL)
+			<< 2;
 	WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE,
 		0xff & ~(adev->gfx.xcc_mask));
 
-- 
GitLab


From 4054705215ad7e6dd8e4e6ff27c39abd7667f700 Mon Sep 17 00:00:00 2001
From: Francis Pravin <francis.p@samsung.com>
Date: Wed, 7 Feb 2024 05:04:17 +0530
Subject: [PATCH 3987/4076] nvme: use ns->head->pi_size instead of t10_pi_tuple
 structure size

Currently kernel supports 8 byte and 16 byte protection information.
So, use ns->head->pi_size instead of sizeof(struct t10_pi_tuple).

Signed-off-by: Francis Pravin <francis.p@samsung.com>
Signed-off-by: Sathyavathi M <sathya.m@samsung.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 18f5c1be5d67e..3dfd5ae99ae05 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -228,7 +228,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->head->ms == sizeof(struct t10_pi_tuple)) {
+	    (ns->head->ms == ns->head->pi_size)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.
-- 
GitLab


From a12bc36032a2f7917068f9ce9eb26d869e54b31a Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Fri, 2 Feb 2024 16:13:17 +0800
Subject: [PATCH 3988/4076] ksmbd: Add kernel-doc for ksmbd_extract_sharename()
 function

The ksmbd_extract_sharename() function lacked a complete kernel-doc
comment. This patch adds parameter descriptions and detailed function
behavior to improve code readability and maintainability.

Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/misc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/server/misc.c b/fs/smb/server/misc.c
index 9e8afaa686e3a..1a5faa6f6e7bc 100644
--- a/fs/smb/server/misc.c
+++ b/fs/smb/server/misc.c
@@ -261,6 +261,7 @@ out_ascii:
 
 /**
  * ksmbd_extract_sharename() - get share name from tree connect request
+ * @um: pointer to a unicode_map structure for character encoding handling
  * @treename:	buffer containing tree name and share name
  *
  * Return:      share name on success, otherwise error
-- 
GitLab


From 108a020c64434fed4b69762879d78cd24088b4c7 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 5 Feb 2024 14:19:16 +0300
Subject: [PATCH 3989/4076] ksmbd: free aux buffer if ksmbd_iov_pin_rsp_read
 fails

ksmbd_iov_pin_rsp_read() doesn't free the provided aux buffer if it
fails. Seems to be the caller's responsibility to clear the buffer in
error case.

Found by Linux Verification Center (linuxtesting.org).

Fixes: e2b76ab8b5c9 ("ksmbd: add support for read compound")
Cc: stable@vger.kernel.org
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index ba7a72a6a4f45..0c97d3c860726 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -6173,8 +6173,10 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
 		err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
 					     offsetof(struct smb2_read_rsp, Buffer),
 					     aux_payload_buf, nbytes);
-		if (err)
+		if (err) {
+			kvfree(aux_payload_buf);
 			goto out;
+		}
 		kvfree(rpc_resp);
 	} else {
 		err = ksmbd_iov_pin_rsp(work, (void *)rsp,
@@ -6384,8 +6386,10 @@ int smb2_read(struct ksmbd_work *work)
 	err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
 				     offsetof(struct smb2_read_rsp, Buffer),
 				     aux_payload_buf, nbytes);
-	if (err)
+	if (err) {
+		kvfree(aux_payload_buf);
 		goto out;
+	}
 	ksmbd_fd_put(work, fp);
 	return 0;
 
-- 
GitLab


From e656c7a9e59607d1672d85ffa9a89031876ffe67 Mon Sep 17 00:00:00 2001
From: Prakash Sangappa <prakash.sangappa@oracle.com>
Date: Tue, 23 Jan 2024 12:04:42 -0800
Subject: [PATCH 3990/4076] mm: hugetlb pages should not be reserved by shmat()
 if SHM_NORESERVE

For shared memory of type SHM_HUGETLB, hugetlb pages are reserved in
shmget() call.  If SHM_NORESERVE flags is specified then the hugetlb pages
are not reserved.  However when the shared memory is attached with the
shmat() call the hugetlb pages are getting reserved incorrectly for
SHM_HUGETLB shared memory created with SHM_NORESERVE which is a bug.

-------------------------------
Following test shows the issue.

$cat shmhtb.c

int main()
{
	int shmflags = 0660 | IPC_CREAT | SHM_HUGETLB | SHM_NORESERVE;
	int shmid;

	shmid = shmget(SKEY, SHMSZ, shmflags);
	if (shmid < 0)
	{
		printf("shmat: shmget() failed, %d\n", errno);
		return 1;
	}
	printf("After shmget()\n");
	system("cat /proc/meminfo | grep -i hugepages_");

	shmat(shmid, NULL, 0);
	printf("\nAfter shmat()\n");
	system("cat /proc/meminfo | grep -i hugepages_");

	shmctl(shmid, IPC_RMID, NULL);
	return 0;
}

 #sysctl -w vm.nr_hugepages=20
 #./shmhtb

After shmget()
HugePages_Total:      20
HugePages_Free:       20
HugePages_Rsvd:        0
HugePages_Surp:        0

After shmat()
HugePages_Total:      20
HugePages_Free:       20
HugePages_Rsvd:        5 <--
HugePages_Surp:        0
--------------------------------

Fix is to ensure that hugetlb pages are not reserved for SHM_HUGETLB shared
memory in the shmat() call.

Link: https://lkml.kernel.org/r/1706040282-12388-1-git-send-email-prakash.sangappa@oracle.com
Signed-off-by: Prakash Sangappa <prakash.sangappa@oracle.com>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/hugetlbfs/inode.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 671664fed3077..ee13c2ca8ad29 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -100,6 +100,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	loff_t len, vma_len;
 	int ret;
 	struct hstate *h = hstate_file(file);
+	vm_flags_t vm_flags;
 
 	/*
 	 * vma address alignment (but not the pgoff alignment) has
@@ -141,10 +142,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 
 	ret = -ENOMEM;
+
+	vm_flags = vma->vm_flags;
+	/*
+	 * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip
+	 * reserving here. Note: only for SHM hugetlbfs file, the inode
+	 * flag S_PRIVATE is set.
+	 */
+	if (inode->i_flags & S_PRIVATE)
+		vm_flags |= VM_NORESERVE;
+
 	if (!hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
-				vma->vm_flags))
+				vm_flags))
 		goto out;
 
 	ret = 0;
-- 
GitLab


From daa694e4137571b4ebec330f9a9b4d54aa8b8089 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 22 Jan 2024 16:50:50 +0100
Subject: [PATCH 3991/4076] getrusage: move thread_group_cputime_adjusted()
 outside of lock_task_sighand()

Patch series "getrusage: use sig->stats_lock", v2.


This patch (of 2):

thread_group_cputime() does its own locking, we can safely shift
thread_group_cputime_adjusted() which does another for_each_thread loop
outside of ->siglock protected section.

This is also preparation for the next patch which changes getrusage() to
use stats_lock instead of siglock, thread_group_cputime() takes the same
lock.  With the current implementation recursive read_seqbegin_or_lock()
is fine, thread_group_cputime() can't enter the slow mode if the caller
holds stats_lock, yet this looks more safe and better performance-wise.

Link: https://lkml.kernel.org/r/20240122155023.GA26169@redhat.com
Link: https://lkml.kernel.org/r/20240122155050.GA26205@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Dylan Hatch <dylanbhatch@google.com>
Tested-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/sys.c | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/kernel/sys.c b/kernel/sys.c
index e219fcfa112d8..70ad06ad852e5 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1785,17 +1785,19 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 	struct task_struct *t;
 	unsigned long flags;
 	u64 tgutime, tgstime, utime, stime;
-	unsigned long maxrss = 0;
+	unsigned long maxrss;
+	struct mm_struct *mm;
 	struct signal_struct *sig = p->signal;
 
-	memset((char *)r, 0, sizeof (*r));
+	memset(r, 0, sizeof(*r));
 	utime = stime = 0;
+	maxrss = 0;
 
 	if (who == RUSAGE_THREAD) {
 		task_cputime_adjusted(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = sig->maxrss;
-		goto out;
+		goto out_thread;
 	}
 
 	if (!lock_task_sighand(p, &flags))
@@ -1819,9 +1821,6 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		fallthrough;
 
 	case RUSAGE_SELF:
-		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		utime += tgutime;
-		stime += tgstime;
 		r->ru_nvcsw += sig->nvcsw;
 		r->ru_nivcsw += sig->nivcsw;
 		r->ru_minflt += sig->min_flt;
@@ -1839,19 +1838,24 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 	}
 	unlock_task_sighand(p, &flags);
 
-out:
-	r->ru_utime = ns_to_kernel_old_timeval(utime);
-	r->ru_stime = ns_to_kernel_old_timeval(stime);
+	if (who == RUSAGE_CHILDREN)
+		goto out_children;
 
-	if (who != RUSAGE_CHILDREN) {
-		struct mm_struct *mm = get_task_mm(p);
+	thread_group_cputime_adjusted(p, &tgutime, &tgstime);
+	utime += tgutime;
+	stime += tgstime;
 
-		if (mm) {
-			setmax_mm_hiwater_rss(&maxrss, mm);
-			mmput(mm);
-		}
+out_thread:
+	mm = get_task_mm(p);
+	if (mm) {
+		setmax_mm_hiwater_rss(&maxrss, mm);
+		mmput(mm);
 	}
+
+out_children:
 	r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
+	r->ru_utime = ns_to_kernel_old_timeval(utime);
+	r->ru_stime = ns_to_kernel_old_timeval(stime);
 }
 
 SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
-- 
GitLab


From f7ec1cd5cc7ef3ad964b677ba82b8b77f1c93009 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 22 Jan 2024 16:50:53 +0100
Subject: [PATCH 3992/4076] getrusage: use sig->stats_lock rather than
 lock_task_sighand()

lock_task_sighand() can trigger a hard lockup. If NR_CPUS threads call
getrusage() at the same time and the process has NR_THREADS, spin_lock_irq
will spin with irqs disabled O(NR_CPUS * NR_THREADS) time.

Change getrusage() to use sig->stats_lock, it was specifically designed
for this type of use. This way it runs lockless in the likely case.

TODO:
	- Change do_task_stat() to use sig->stats_lock too, then we can
	  remove spin_lock_irq(siglock) in wait_task_zombie().

	- Turn sig->stats_lock into seqcount_rwlock_t, this way the
	  readers in the slow mode won't exclude each other. See
	  https://lore.kernel.org/all/20230913154907.GA26210@redhat.com/

	- stats_lock has to disable irqs because ->siglock can be taken
	  in irq context, it would be very nice to change __exit_signal()
	  to avoid the siglock->stats_lock dependency.

Link: https://lkml.kernel.org/r/20240122155053.GA26214@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Dylan Hatch <dylanbhatch@google.com>
Tested-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/sys.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/kernel/sys.c b/kernel/sys.c
index 70ad06ad852e5..f8e543f1e38a0 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1788,7 +1788,9 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 	unsigned long maxrss;
 	struct mm_struct *mm;
 	struct signal_struct *sig = p->signal;
+	unsigned int seq = 0;
 
+retry:
 	memset(r, 0, sizeof(*r));
 	utime = stime = 0;
 	maxrss = 0;
@@ -1800,8 +1802,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		goto out_thread;
 	}
 
-	if (!lock_task_sighand(p, &flags))
-		return;
+	flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
 
 	switch (who) {
 	case RUSAGE_BOTH:
@@ -1829,14 +1830,23 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		r->ru_oublock += sig->oublock;
 		if (maxrss < sig->maxrss)
 			maxrss = sig->maxrss;
+
+		rcu_read_lock();
 		__for_each_thread(sig, t)
 			accumulate_thread_rusage(t, r);
+		rcu_read_unlock();
+
 		break;
 
 	default:
 		BUG();
 	}
-	unlock_task_sighand(p, &flags);
+
+	if (need_seqretry(&sig->stats_lock, seq)) {
+		seq = 1;
+		goto retry;
+	}
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
 
 	if (who == RUSAGE_CHILDREN)
 		goto out_children;
-- 
GitLab


From 60f92acb60a989b14e4b744501a0df0f82ef30a3 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jan 2024 16:33:55 +0100
Subject: [PATCH 3993/4076] fs/proc: do_task_stat: move
 thread_group_cputime_adjusted() outside of lock_task_sighand()

Patch series "fs/proc: do_task_stat: use sig->stats_".

do_task_stat() has the same problem as getrusage() had before "getrusage:
use sig->stats_lock rather than lock_task_sighand()": a hard lockup.  If
NR_CPUS threads call lock_task_sighand() at the same time and the process
has NR_THREADS, spin_lock_irq will spin with irqs disabled O(NR_CPUS *
NR_THREADS) time.


This patch (of 3):

thread_group_cputime() does its own locking, we can safely shift
thread_group_cputime_adjusted() which does another for_each_thread loop
outside of ->siglock protected section.

Not only this removes for_each_thread() from the critical section with
irqs disabled, this removes another case when stats_lock is taken with
siglock held.  We want to remove this dependency, then we can change the
users of stats_lock to not disable irqs.

Link: https://lkml.kernel.org/r/20240123153313.GA21832@redhat.com
Link: https://lkml.kernel.org/r/20240123153355.GA21854@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/array.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/proc/array.c b/fs/proc/array.c
index ff08a8957552a..45ba918638084 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -511,7 +511,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	sigemptyset(&sigign);
 	sigemptyset(&sigcatch);
-	cutime = cstime = utime = stime = 0;
+	cutime = cstime = 0;
 	cgtime = gtime = 0;
 
 	if (lock_task_sighand(task, &flags)) {
@@ -546,7 +546,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 			min_flt += sig->min_flt;
 			maj_flt += sig->maj_flt;
-			thread_group_cputime_adjusted(task, &utime, &stime);
 			gtime += sig->gtime;
 
 			if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
@@ -562,10 +561,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	if (permitted && (!whole || num_threads < 2))
 		wchan = !task_is_running(task);
-	if (!whole) {
+
+	if (whole) {
+		thread_group_cputime_adjusted(task, &utime, &stime);
+	} else {
+		task_cputime_adjusted(task, &utime, &stime);
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
-		task_cputime_adjusted(task, &utime, &stime);
 		gtime = task_gtime(task);
 	}
 
-- 
GitLab


From 7601df8031fd67310af891897ef6cc0df4209305 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jan 2024 16:33:57 +0100
Subject: [PATCH 3994/4076] fs/proc: do_task_stat: use sig->stats_lock to
 gather the threads/children stats

lock_task_sighand() can trigger a hard lockup.  If NR_CPUS threads call
do_task_stat() at the same time and the process has NR_THREADS, it will
spin with irqs disabled O(NR_CPUS * NR_THREADS) time.

Change do_task_stat() to use sig->stats_lock to gather the statistics
outside of ->siglock protected section, in the likely case this code will
run lockless.

Link: https://lkml.kernel.org/r/20240123153357.GA21857@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/array.c | 58 +++++++++++++++++++++++++++----------------------
 1 file changed, 32 insertions(+), 26 deletions(-)

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 45ba918638084..34a47fb0c57f2 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -477,13 +477,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	int permitted;
 	struct mm_struct *mm;
 	unsigned long long start_time;
-	unsigned long cmin_flt = 0, cmaj_flt = 0;
-	unsigned long  min_flt = 0,  maj_flt = 0;
-	u64 cutime, cstime, utime, stime;
-	u64 cgtime, gtime;
+	unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt;
+	u64 cutime, cstime, cgtime, utime, stime, gtime;
 	unsigned long rsslim = 0;
 	unsigned long flags;
 	int exit_code = task->exit_code;
+	struct signal_struct *sig = task->signal;
+	unsigned int seq = 1;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	sigemptyset(&sigign);
 	sigemptyset(&sigcatch);
-	cutime = cstime = 0;
-	cgtime = gtime = 0;
 
 	if (lock_task_sighand(task, &flags)) {
-		struct signal_struct *sig = task->signal;
-
 		if (sig->tty) {
 			struct pid *pgrp = tty_get_pgrp(sig->tty);
 			tty_pgrp = pid_nr_ns(pgrp, ns);
@@ -527,27 +523,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		num_threads = get_nr_threads(task);
 		collect_sigign_sigcatch(task, &sigign, &sigcatch);
 
-		cmin_flt = sig->cmin_flt;
-		cmaj_flt = sig->cmaj_flt;
-		cutime = sig->cutime;
-		cstime = sig->cstime;
-		cgtime = sig->cgtime;
 		rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
 
-		/* add up live thread stats at the group level */
 		if (whole) {
-			struct task_struct *t;
-
-			__for_each_thread(sig, t) {
-				min_flt += t->min_flt;
-				maj_flt += t->maj_flt;
-				gtime += task_gtime(t);
-			}
-
-			min_flt += sig->min_flt;
-			maj_flt += sig->maj_flt;
-			gtime += sig->gtime;
-
 			if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
 				exit_code = sig->group_exit_code;
 		}
@@ -562,6 +540,34 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	if (permitted && (!whole || num_threads < 2))
 		wchan = !task_is_running(task);
 
+	do {
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
+		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+
+		cmin_flt = sig->cmin_flt;
+		cmaj_flt = sig->cmaj_flt;
+		cutime = sig->cutime;
+		cstime = sig->cstime;
+		cgtime = sig->cgtime;
+
+		if (whole) {
+			struct task_struct *t;
+
+			min_flt = sig->min_flt;
+			maj_flt = sig->maj_flt;
+			gtime = sig->gtime;
+
+			rcu_read_lock();
+			__for_each_thread(sig, t) {
+				min_flt += t->min_flt;
+				maj_flt += t->maj_flt;
+				gtime += task_gtime(t);
+			}
+			rcu_read_unlock();
+		}
+	} while (need_seqretry(&sig->stats_lock, seq));
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+
 	if (whole) {
 		thread_group_cputime_adjusted(task, &utime, &stime);
 	} else {
-- 
GitLab


From c1be35a16b2f1fe21f4f26f9de030ad6eaaf6a25 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jan 2024 16:34:00 +0100
Subject: [PATCH 3995/4076] exit: wait_task_zombie: kill the no longer
 necessary spin_lock_irq(siglock)

After the recent changes nobody use siglock to read the values protected
by stats_lock, we can kill spin_lock_irq(&current->sighand->siglock) and
update the comment.

With this patch only __exit_signal() and thread_group_start_cputime() take
stats_lock under siglock.

Link: https://lkml.kernel.org/r/20240123153359.GA21866@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/exit.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/kernel/exit.c b/kernel/exit.c
index 3988a02efaef0..dfb963d2f862a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1127,17 +1127,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * and nobody can change them.
 		 *
 		 * psig->stats_lock also protects us from our sub-threads
-		 * which can reap other children at the same time. Until
-		 * we change k_getrusage()-like users to rely on this lock
-		 * we have to take ->siglock as well.
+		 * which can reap other children at the same time.
 		 *
 		 * We use thread_group_cputime_adjusted() to get times for
 		 * the thread group, which consolidates times for all threads
 		 * in the group including the group leader.
 		 */
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		spin_lock_irq(&current->sighand->siglock);
-		write_seqlock(&psig->stats_lock);
+		write_seqlock_irq(&psig->stats_lock);
 		psig->cutime += tgutime + sig->cutime;
 		psig->cstime += tgstime + sig->cstime;
 		psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1160,8 +1157,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
-		write_sequnlock(&psig->stats_lock);
-		spin_unlock_irq(&current->sighand->siglock);
+		write_sequnlock_irq(&psig->stats_lock);
 	}
 
 	if (wo->wo_rusage)
-- 
GitLab


From 56ae10cf628b02279980d17439c6241a643959c2 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Tue, 23 Jan 2024 14:17:55 +0000
Subject: [PATCH 3996/4076] mm/userfaultfd: UFFDIO_MOVE implementation should
 use ptep_get()

Commit c33c794828f2 ("mm: ptep_get() conversion") converted all (non-arch)
call sites to use ptep_get() instead of doing a direct dereference of the
pte.  Full rationale can be found in that commit's log.

Since then, UFFDIO_MOVE has been implemented which does 7 direct pte
dereferences.  Let's fix those up to use ptep_get().

I've asserted in the past that there is no reliable automated mechanism to
catch these; I'm relying on a combination of Coccinelle (which throws up a
lot of false positives) and some compiler magic to force a compiler error
on dereference.  But given the frequency with which new issues are coming
up, I'll add it to my todo list to try to find an automated solution.

Link: https://lkml.kernel.org/r/20240123141755.3836179-1-ryan.roberts@arm.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 75fcf1f783bc5..7cf7d43842590 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -902,8 +902,8 @@ static int move_present_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(*src_pte, orig_src_pte) ||
-	    !pte_same(*dst_pte, orig_dst_pte)) {
+	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
 		err = -EAGAIN;
 		goto out;
 	}
@@ -946,8 +946,8 @@ static int move_swap_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(*src_pte, orig_src_pte) ||
-	    !pte_same(*dst_pte, orig_dst_pte)) {
+	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
 		double_pt_unlock(dst_ptl, src_ptl);
 		return -EAGAIN;
 	}
@@ -1016,7 +1016,7 @@ retry:
 	}
 
 	spin_lock(dst_ptl);
-	orig_dst_pte = *dst_pte;
+	orig_dst_pte = ptep_get(dst_pte);
 	spin_unlock(dst_ptl);
 	if (!pte_none(orig_dst_pte)) {
 		err = -EEXIST;
@@ -1024,7 +1024,7 @@ retry:
 	}
 
 	spin_lock(src_ptl);
-	orig_src_pte = *src_pte;
+	orig_src_pte = ptep_get(src_pte);
 	spin_unlock(src_ptl);
 	if (pte_none(orig_src_pte)) {
 		if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES))
@@ -1054,7 +1054,7 @@ retry:
 			 * page isn't freed under us
 			 */
 			spin_lock(src_ptl);
-			if (!pte_same(orig_src_pte, *src_pte)) {
+			if (!pte_same(orig_src_pte, ptep_get(src_pte))) {
 				spin_unlock(src_ptl);
 				err = -EAGAIN;
 				goto out;
-- 
GitLab


From 67b8bcbaed4777871bb0dcc888fb02a614a98ab1 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Wed, 24 Jan 2024 21:19:36 +0900
Subject: [PATCH 3997/4076] nilfs2: fix data corruption in dsync block recovery
 for small block sizes

The helper function nilfs_recovery_copy_block() of
nilfs_recovery_dsync_blocks(), which recovers data from logs created by
data sync writes during a mount after an unclean shutdown, incorrectly
calculates the on-page offset when copying repair data to the file's page
cache.  In environments where the block size is smaller than the page
size, this flaw can cause data corruption and leak uninitialized memory
bytes during the recovery process.

Fix these issues by correcting this byte offset calculation on the page.

Link: https://lkml.kernel.org/r/20240124121936.10575-1-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Tested-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/recovery.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 0955b657938ff..a9b8d77c8c1d5 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs,
 
 static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 				     struct nilfs_recovery_block *rb,
-				     struct page *page)
+				     loff_t pos, struct page *page)
 {
 	struct buffer_head *bh_org;
+	size_t from = pos & ~PAGE_MASK;
 	void *kaddr;
 
 	bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize);
@@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 		return -EIO;
 
 	kaddr = kmap_atomic(page);
-	memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size);
+	memcpy(kaddr + from, bh_org->b_data, bh_org->b_size);
 	kunmap_atomic(kaddr);
 	brelse(bh_org);
 	return 0;
@@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 			goto failed_inode;
 		}
 
-		err = nilfs_recovery_copy_block(nilfs, rb, page);
+		err = nilfs_recovery_copy_block(nilfs, rb, pos, page);
 		if (unlikely(err))
 			goto failed_page;
 
-- 
GitLab


From 9cee7e8ef3e31ca25b40ca52b8585dc6935deff2 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosryahmed@google.com>
Date: Wed, 24 Jan 2024 10:00:22 +0000
Subject: [PATCH 3998/4076] mm: memcg: optimize parent iteration in
 memcg_rstat_updated()

In memcg_rstat_updated(), we iterate the memcg being updated and its
parents to update memcg->vmstats_percpu->stats_updates in the fast path
(i.e. no atomic updates). According to my math, this is 3 memory loads
(and potentially 3 cache misses) per memcg:
- Load the address of memcg->vmstats_percpu.
- Load vmstats_percpu->stats_updates (based on some percpu calculation).
- Load the address of the parent memcg.

Avoid most of the cache misses by caching a pointer from each struct
memcg_vmstats_percpu to its parent on the corresponding CPU. In this
case, for the first memcg we have 2 memory loads (same as above):
- Load the address of memcg->vmstats_percpu.
- Load vmstats_percpu->stats_updates (based on some percpu calculation).

Then for each additional memcg, we need a single load to get the
parent's stats_updates directly. This reduces the number of loads from
O(3N) to O(2+N) -- where N is the number of memcgs we need to iterate.

Additionally, stash a pointer to memcg->vmstats in each struct
memcg_vmstats_percpu such that we can access the atomic counter that all
CPUs fold into, memcg->vmstats->stats_updates.
memcg_should_flush_stats() is changed to memcg_vmstats_needs_flush() to
accept a struct memcg_vmstats pointer accordingly.

In struct memcg_vmstats_percpu, make sure both pointers together with
stats_updates live on the same cacheline. Finally, update
mem_cgroup_alloc() to take in a parent pointer and initialize the new
cache pointers on each CPU. The percpu loop in mem_cgroup_alloc() may
look concerning, but there are multiple similar loops in the cgroup
creation path (e.g. cgroup_rstat_init()), most of which are hidden
within alloc_percpu().

According to Oliver's testing [1], this fixes multiple 30-38%
regressions in vm-scalability, will-it-scale-tlb_flush2, and
will-it-scale-fallocate1. This comes at a cost of 2 more pointers per
CPU (<2KB on a machine with 128 CPUs).

[1] https://lore.kernel.org/lkml/ZbDJsfsZt2ITyo61@xsang-OptiPlex-9020/

[yosryahmed@google.com: fix struct memcg_vmstats_percpu size and alignment]
  Link: https://lkml.kernel.org/r/20240203044612.1234216-1-yosryahmed@google.com
Link: https://lkml.kernel.org/r/20240124100023.660032-1-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Fixes: 8d59d2214c23 ("mm: memcg: make stats flushing threshold per-memcg")
Tested-by: kernel test robot <oliver.sang@intel.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401221624.cb53a8ca-oliver.sang@intel.com
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memcontrol.c | 56 ++++++++++++++++++++++++++++++-------------------
 1 file changed, 35 insertions(+), 21 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 46d8d02114cfe..1ed40f9d3a277 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -621,6 +621,15 @@ static inline int memcg_events_index(enum vm_event_item idx)
 }
 
 struct memcg_vmstats_percpu {
+	/* Stats updates since the last flush */
+	unsigned int			stats_updates;
+
+	/* Cached pointers for fast iteration in memcg_rstat_updated() */
+	struct memcg_vmstats_percpu	*parent;
+	struct memcg_vmstats		*vmstats;
+
+	/* The above should fit a single cacheline for memcg_rstat_updated() */
+
 	/* Local (CPU and cgroup) page state & events */
 	long			state[MEMCG_NR_STAT];
 	unsigned long		events[NR_MEMCG_EVENTS];
@@ -632,10 +641,7 @@ struct memcg_vmstats_percpu {
 	/* Cgroup1: threshold notifications & softlimit tree updates */
 	unsigned long		nr_page_events;
 	unsigned long		targets[MEM_CGROUP_NTARGETS];
-
-	/* Stats updates since the last flush */
-	unsigned int		stats_updates;
-};
+} ____cacheline_aligned;
 
 struct memcg_vmstats {
 	/* Aggregated (CPU and subtree) page state & events */
@@ -698,36 +704,35 @@ static void memcg_stats_unlock(void)
 }
 
 
-static bool memcg_should_flush_stats(struct mem_cgroup *memcg)
+static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
 {
-	return atomic64_read(&memcg->vmstats->stats_updates) >
+	return atomic64_read(&vmstats->stats_updates) >
 		MEMCG_CHARGE_BATCH * num_online_cpus();
 }
 
 static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
+	struct memcg_vmstats_percpu *statc;
 	int cpu = smp_processor_id();
-	unsigned int x;
 
 	if (!val)
 		return;
 
 	cgroup_rstat_updated(memcg->css.cgroup, cpu);
-
-	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		x = __this_cpu_add_return(memcg->vmstats_percpu->stats_updates,
-					  abs(val));
-
-		if (x < MEMCG_CHARGE_BATCH)
+	statc = this_cpu_ptr(memcg->vmstats_percpu);
+	for (; statc; statc = statc->parent) {
+		statc->stats_updates += abs(val);
+		if (statc->stats_updates < MEMCG_CHARGE_BATCH)
 			continue;
 
 		/*
 		 * If @memcg is already flush-able, increasing stats_updates is
 		 * redundant. Avoid the overhead of the atomic update.
 		 */
-		if (!memcg_should_flush_stats(memcg))
-			atomic64_add(x, &memcg->vmstats->stats_updates);
-		__this_cpu_write(memcg->vmstats_percpu->stats_updates, 0);
+		if (!memcg_vmstats_needs_flush(statc->vmstats))
+			atomic64_add(statc->stats_updates,
+				     &statc->vmstats->stats_updates);
+		statc->stats_updates = 0;
 	}
 }
 
@@ -756,7 +761,7 @@ void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 	if (!memcg)
 		memcg = root_mem_cgroup;
 
-	if (memcg_should_flush_stats(memcg))
+	if (memcg_vmstats_needs_flush(memcg->vmstats))
 		do_flush_stats(memcg);
 }
 
@@ -770,7 +775,7 @@ void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 static void flush_memcg_stats_dwork(struct work_struct *w)
 {
 	/*
-	 * Deliberately ignore memcg_should_flush_stats() here so that flushing
+	 * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing
 	 * in latency-sensitive paths is as cheap as possible.
 	 */
 	do_flush_stats(root_mem_cgroup);
@@ -5477,10 +5482,11 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 	__mem_cgroup_free(memcg);
 }
 
-static struct mem_cgroup *mem_cgroup_alloc(void)
+static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 {
+	struct memcg_vmstats_percpu *statc, *pstatc;
 	struct mem_cgroup *memcg;
-	int node;
+	int node, cpu;
 	int __maybe_unused i;
 	long error = -ENOMEM;
 
@@ -5504,6 +5510,14 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (!memcg->vmstats_percpu)
 		goto fail;
 
+	for_each_possible_cpu(cpu) {
+		if (parent)
+			pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu);
+		statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
+		statc->parent = parent ? pstatc : NULL;
+		statc->vmstats = memcg->vmstats;
+	}
+
 	for_each_node(node)
 		if (alloc_mem_cgroup_per_node_info(memcg, node))
 			goto fail;
@@ -5549,7 +5563,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	struct mem_cgroup *memcg, *old_memcg;
 
 	old_memcg = set_active_memcg(parent);
-	memcg = mem_cgroup_alloc();
+	memcg = mem_cgroup_alloc(parent);
 	set_active_memcg(old_memcg);
 	if (IS_ERR(memcg))
 		return ERR_CAST(memcg);
-- 
GitLab


From 2fde9e7f9e6dc38e1d7091b9705c22be945c8697 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Wed, 24 Jan 2024 16:40:14 +0800
Subject: [PATCH 3999/4076] mm/memory-failure: fix crash in
 split_huge_page_to_list from soft_offline_page

When I did soft offline stress test, a machine was observed to crash with
the following message:

  kernel BUG at include/linux/memcontrol.h:554!
  invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
  CPU: 5 PID: 3837 Comm: hwpoison.sh Not tainted 6.7.0-next-20240112-00001-g8ecf3e7fb7c8-dirty #97
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
  RIP: 0010:folio_memcg+0xaf/0xd0
  Code: 10 5b 5d c3 cc cc cc cc 48 c7 c6 08 b1 f2 b2 48 89 ef e8 b4 c5 f8 ff 90 0f 0b 48 c7 c6 d0 b0 f2 b2 48 89 ef e8 a2 c5 f8 ff 90 <0f> 0b 48 c7 c6 08 b1 f2 b2 48 89 ef e8 90 c5 f8 ff 90 0f 0b 66 66
  RSP: 0018:ffffb6c043657c98 EFLAGS: 00000296
  RAX: 000000000000004b RBX: ffff932bc1d1e401 RCX: ffff933abfb5c908
  RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff933abfb5c900
  RBP: ffffea6f04019080 R08: ffffffffb3338ce8 R09: 0000000000009ffb
  R10: 00000000000004dd R11: ffffffffb3308d00 R12: ffffea6f04019080
  R13: ffffea6f04019080 R14: 0000000000000001 R15: ffffb6c043657da0
  FS:  00007f6c60f6b740(0000) GS:ffff933abfb40000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000559c3bc8b980 CR3: 0000000107f1c000 CR4: 00000000000006f0
  Call Trace:
   <TASK>
   split_huge_page_to_list+0x4d/0x1380
   try_to_split_thp_page+0x3a/0xf0
   soft_offline_page+0x1ea/0x8a0
   soft_offline_page_store+0x52/0x90
   kernfs_fop_write_iter+0x118/0x1b0
   vfs_write+0x30b/0x430
   ksys_write+0x5e/0xe0
   do_syscall_64+0xb0/0x1b0
   entry_SYSCALL_64_after_hwframe+0x6d/0x75
  RIP: 0033:0x7f6c60d14697
  Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
  RSP: 002b:00007ffe9b72b8d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
  RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007f6c60d14697
  RDX: 000000000000000c RSI: 0000559c3bc8b980 RDI: 0000000000000001
  RBP: 0000559c3bc8b980 R08: 00007f6c60dd1460 R09: 000000007fffffff
  R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000c
  R13: 00007f6c60e1a780 R14: 00007f6c60e16600 R15: 00007f6c60e15a00

The problem is that page->mapping is overloaded with slab->slab_list or
slabs fields now, so slab pages could be taken as non-LRU movable pages if
field slabs contains PAGE_MAPPING_MOVABLE or slab_list->prev is set to
LIST_POISON2.  These slab pages will be treated as thp later leading to
crash in split_huge_page_to_list().

Link: https://lkml.kernel.org/r/20240126065837.2100184-1-linmiaohe@huawei.com
Link: https://lkml.kernel.org/r/20240124084014.1772906-1-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Fixes: 130d4df57390 ("mm/sl[au]b: rearrange struct slab fields to allow larger rcu_head")
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory-failure.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 636280d04008d..9349948f1abfd 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1377,6 +1377,9 @@ void ClearPageHWPoisonTakenOff(struct page *page)
  */
 static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
 {
+	if (PageSlab(page))
+		return false;
+
 	/* Soft offline could migrate non-LRU movable pages */
 	if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
 		return true;
-- 
GitLab


From 01c1484ac04790fe27a37f89dd3a350f99646815 Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@collabora.com>
Date: Tue, 24 Oct 2023 20:51:25 +0500
Subject: [PATCH 4000/4076] selftests: core: include linux/close_range.h for
 CLOSE_RANGE_* macros

Correct header file is needed for getting CLOSE_RANGE_* macros.
Previously it was tested with newer glibc which didn't show the need to
include the header which was a mistake.

Link: https://lkml.kernel.org/r/20231024155137.219700-1-usama.anjum@collabora.com
Fixes: ec54424923cf ("selftests: core: remove duplicate defines")
Reported-by: Aishwarya TCV <aishwarya.tcv@arm.com>
Link: https://lore.kernel.org/all/7161219e-0223-d699-d6f3-81abd9abf13b@arm.com
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/core/close_range_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 534576f06df1c..c59e4adb905df 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -12,6 +12,7 @@
 #include <syscall.h>
 #include <unistd.h>
 #include <sys/resource.h>
+#include <linux/close_range.h>
 
 #include "../kselftest_harness.h"
 #include "../clone3/clone3_selftests.h"
-- 
GitLab


From e870920bbe68e52335a4c31a059e6af6a9a59dbb Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Mon, 22 Jan 2024 22:43:05 -0800
Subject: [PATCH 4001/4076] arch/arm/mm: fix major fault accounting when
 retrying under per-VMA lock

The change [1] missed ARM architecture when fixing major fault accounting
for page fault retry under per-VMA lock.

The user-visible effects is that it restores correct major fault
accounting that was broken after [2] was merged in 6.7 kernel. The
more detailed description is in [3] and this patch simply adds the
same fix to ARM architecture which I missed in [3].

Add missing code to fix ARM architecture fault accounting.

[1] 46e714c729c8 ("arch/mm/fault: fix major fault accounting when retrying under per-VMA lock")
[2] https://lore.kernel.org/all/20231006195318.4087158-6-willy@infradead.org/
[3] https://lore.kernel.org/all/20231226214610.109282-1-surenb@google.com/

Link: https://lkml.kernel.org/r/20240123064305.2829244-1-surenb@google.com
Fixes: 12214eba1992 ("mm: handle read faults under the VMA lock")
Reported-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm/mm/fault.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index e96fb40b9cc32..07565b593ed68 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -298,6 +298,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
-- 
GitLab


From 4c2da3188b848d33c26d7f0f8b14f3150331c923 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Date: Fri, 26 Jan 2024 12:25:48 +0900
Subject: [PATCH 4002/4076] mm/madvise: don't forget to leave lazy MMU mode in
 madvise_cold_or_pageout_pte_range()

We need to leave lazy MMU mode before unlocking.

Link: https://lkml.kernel.org/r/20240126032608.355899-1-senozhatsky@chromium.org
Fixes: b2f557a21bc8 ("mm/madvise: add cond_resched() in madvise_cold_or_pageout_pte_range()")
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Jiexun Wang <wangjiexun@tinylab.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/madvise.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/madvise.c b/mm/madvise.c
index 912155a94ed58..cfa5e72882611 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -429,6 +429,7 @@ restart:
 		if (++batch_count == SWAP_CLUSTER_MAX) {
 			batch_count = 0;
 			if (need_resched()) {
+				arch_leave_lazy_mmu_mode();
 				pte_unmap_unlock(start_pte, ptl);
 				cond_resched();
 				goto restart;
-- 
GitLab


From 2e601e1e8e4b330020a346c55ba111d49e0b188e Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Mon, 29 Jan 2024 20:34:38 -0500
Subject: [PATCH 4003/4076] mm: zswap: fix objcg use-after-free in entry
 destruction

In the per-memcg LRU universe, LRU removal uses entry->objcg to determine
which list count needs to be decreased.  Drop the objcg reference after
updating the LRU, to fix a possible use-after-free.

Link: https://lkml.kernel.org/r/20240130013438.565167-1-hannes@cmpxchg.org
Fixes: a65b0e7607cc ("zswap: make shrinking memcg-aware")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/zswap.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index ca25b676048ea..0a94b197ed32e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -536,10 +536,6 @@ static struct zpool *zswap_find_zpool(struct zswap_entry *entry)
  */
 static void zswap_free_entry(struct zswap_entry *entry)
 {
-	if (entry->objcg) {
-		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
-		obj_cgroup_put(entry->objcg);
-	}
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
@@ -548,6 +544,10 @@ static void zswap_free_entry(struct zswap_entry *entry)
 		atomic_dec(&entry->pool->nr_stored);
 		zswap_pool_put(entry->pool);
 	}
+	if (entry->objcg) {
+		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
+		obj_cgroup_put(entry->objcg);
+	}
 	zswap_entry_cache_free(entry);
 	atomic_dec(&zswap_stored_pages);
 	zswap_update_total_size();
-- 
GitLab


From f2076032096775d1bb1af16b6eddbc6534575328 Mon Sep 17 00:00:00 2001
From: John Moon <john@jmoon.dev>
Date: Wed, 31 Jan 2024 03:43:18 +0000
Subject: [PATCH 4004/4076] mailmap: switch email address for John Moon

Add current email address as QUIC email is no longer active.

Link: https://lkml.kernel.org/r/20240131034311.46706-1-john@jmoon.dev
Signed-off-by: John Moon <john@jmoon.dev>
Acked-by: Trilok Soni <quic_tsoni@quicinc.com>
Cc: Elliot Berman <quic_eberman@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index 04998f7bda818..8ae00bd3708a7 100644
--- a/.mailmap
+++ b/.mailmap
@@ -289,6 +289,7 @@ Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
 John Crispin <john@phrozen.org> <blogic@openwrt.org>
 John Fastabend <john.fastabend@gmail.com> <john.r.fastabend@intel.com>
 John Keeping <john@keeping.me.uk> <john@metanate.com>
+John Moon <john@jmoon.dev> <quic_johmoo@quicinc.com>
 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
 John Stultz <johnstul@us.ibm.com>
 <jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com>
-- 
GitLab


From 79d72c68c58784a3e1cd2378669d51bfd0cb7498 Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Tue, 30 Jan 2024 22:04:18 +0100
Subject: [PATCH 4005/4076] fs,hugetlb: fix NULL pointer dereference in
 hugetlbs_fill_super

When configuring a hugetlb filesystem via the fsconfig() syscall, there is
a possible NULL dereference in hugetlbfs_fill_super() caused by assigning
NULL to ctx->hstate in hugetlbfs_parse_param() when the requested pagesize
is non valid.

E.g: Taking the following steps:

     fd = fsopen("hugetlbfs", FSOPEN_CLOEXEC);
     fsconfig(fd, FSCONFIG_SET_STRING, "pagesize", "1024", 0);
     fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);

Given that the requested "pagesize" is invalid, ctxt->hstate will be replaced
with NULL, losing its previous value, and we will print an error:

 ...
 ...
 case Opt_pagesize:
 ps = memparse(param->string, &rest);
 ctx->hstate = h;
 if (!ctx->hstate) {
         pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
         return -EINVAL;
 }
 return 0;
 ...
 ...

This is a problem because later on, we will dereference ctxt->hstate in
hugetlbfs_fill_super()

 ...
 ...
 sb->s_blocksize = huge_page_size(ctx->hstate);
 ...
 ...

Causing below Oops.

Fix this by replacing cxt->hstate value only when then pagesize is known
to be valid.

 kernel: hugetlbfs: Unsupported page size 0 MB
 kernel: BUG: kernel NULL pointer dereference, address: 0000000000000028
 kernel: #PF: supervisor read access in kernel mode
 kernel: #PF: error_code(0x0000) - not-present page
 kernel: PGD 800000010f66c067 P4D 800000010f66c067 PUD 1b22f8067 PMD 0
 kernel: Oops: 0000 [#1] PREEMPT SMP PTI
 kernel: CPU: 4 PID: 5659 Comm: syscall Tainted: G            E      6.8.0-rc2-default+ #22 5a47c3fef76212addcc6eb71344aabc35190ae8f
 kernel: Hardware name: Intel Corp. GROVEPORT/GROVEPORT, BIOS GVPRCRB1.86B.0016.D04.1705030402 05/03/2017
 kernel: RIP: 0010:hugetlbfs_fill_super+0xb4/0x1a0
 kernel: Code: 48 8b 3b e8 3e c6 ed ff 48 85 c0 48 89 45 20 0f 84 d6 00 00 00 48 b8 ff ff ff ff ff ff ff 7f 4c 89 e7 49 89 44 24 20 48 8b 03 <8b> 48 28 b8 00 10 00 00 48 d3 e0 49 89 44 24 18 48 8b 03 8b 40 28
 kernel: RSP: 0018:ffffbe9960fcbd48 EFLAGS: 00010246
 kernel: RAX: 0000000000000000 RBX: ffff9af5272ae780 RCX: 0000000000372004
 kernel: RDX: ffffffffffffffff RSI: ffffffffffffffff RDI: ffff9af555e9b000
 kernel: RBP: ffff9af52ee66b00 R08: 0000000000000040 R09: 0000000000370004
 kernel: R10: ffffbe9960fcbd48 R11: 0000000000000040 R12: ffff9af555e9b000
 kernel: R13: ffffffffa66b86c0 R14: ffff9af507d2f400 R15: ffff9af507d2f400
 kernel: FS:  00007ffbc0ba4740(0000) GS:ffff9b0bd7000000(0000) knlGS:0000000000000000
 kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 kernel: CR2: 0000000000000028 CR3: 00000001b1ee0000 CR4: 00000000001506f0
 kernel: Call Trace:
 kernel:  <TASK>
 kernel:  ? __die_body+0x1a/0x60
 kernel:  ? page_fault_oops+0x16f/0x4a0
 kernel:  ? search_bpf_extables+0x65/0x70
 kernel:  ? fixup_exception+0x22/0x310
 kernel:  ? exc_page_fault+0x69/0x150
 kernel:  ? asm_exc_page_fault+0x22/0x30
 kernel:  ? __pfx_hugetlbfs_fill_super+0x10/0x10
 kernel:  ? hugetlbfs_fill_super+0xb4/0x1a0
 kernel:  ? hugetlbfs_fill_super+0x28/0x1a0
 kernel:  ? __pfx_hugetlbfs_fill_super+0x10/0x10
 kernel:  vfs_get_super+0x40/0xa0
 kernel:  ? __pfx_bpf_lsm_capable+0x10/0x10
 kernel:  vfs_get_tree+0x25/0xd0
 kernel:  vfs_cmd_create+0x64/0xe0
 kernel:  __x64_sys_fsconfig+0x395/0x410
 kernel:  do_syscall_64+0x80/0x160
 kernel:  ? syscall_exit_to_user_mode+0x82/0x240
 kernel:  ? do_syscall_64+0x8d/0x160
 kernel:  ? syscall_exit_to_user_mode+0x82/0x240
 kernel:  ? do_syscall_64+0x8d/0x160
 kernel:  ? exc_page_fault+0x69/0x150
 kernel:  entry_SYSCALL_64_after_hwframe+0x6e/0x76
 kernel: RIP: 0033:0x7ffbc0cb87c9
 kernel: Code: 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 97 96 0d 00 f7 d8 64 89 01 48
 kernel: RSP: 002b:00007ffc29d2f388 EFLAGS: 00000206 ORIG_RAX: 00000000000001af
 kernel: RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ffbc0cb87c9
 kernel: RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000003
 kernel: RBP: 00007ffc29d2f3b0 R08: 0000000000000000 R09: 0000000000000000
 kernel: R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000
 kernel: R13: 00007ffc29d2f4c0 R14: 0000000000000000 R15: 0000000000000000
 kernel:  </TASK>
 kernel: Modules linked in: rpcsec_gss_krb5(E) auth_rpcgss(E) nfsv4(E) dns_resolver(E) nfs(E) lockd(E) grace(E) sunrpc(E) netfs(E) af_packet(E) bridge(E) stp(E) llc(E) iscsi_ibft(E) iscsi_boot_sysfs(E) intel_rapl_msr(E) intel_rapl_common(E) iTCO_wdt(E) intel_pmc_bxt(E) sb_edac(E) iTCO_vendor_support(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) rfkill(E) ipmi_ssif(E) kvm(E) acpi_ipmi(E) irqbypass(E) pcspkr(E) igb(E) ipmi_si(E) mei_me(E) i2c_i801(E) joydev(E) intel_pch_thermal(E) i2c_smbus(E) dca(E) lpc_ich(E) mei(E) ipmi_devintf(E) ipmi_msghandler(E) acpi_pad(E) tiny_power_button(E) button(E) fuse(E) efi_pstore(E) configfs(E) ip_tables(E) x_tables(E) ext4(E) mbcache(E) jbd2(E) hid_generic(E) usbhid(E) sd_mod(E) t10_pi(E) crct10dif_pclmul(E) crc32_pclmul(E) crc32c_intel(E) polyval_clmulni(E) ahci(E) xhci_pci(E) polyval_generic(E) gf128mul(E) ghash_clmulni_intel(E) sha512_ssse3(E) sha256_ssse3(E) xhci_pci_renesas(E) libahci(E) ehci_pci(E) sha1_ssse3(E) xhci_hcd(E) ehci_hcd(E) libata(E)
 kernel:  mgag200(E) i2c_algo_bit(E) usbcore(E) wmi(E) sg(E) dm_multipath(E) dm_mod(E) scsi_dh_rdac(E) scsi_dh_emc(E) scsi_dh_alua(E) scsi_mod(E) scsi_common(E) aesni_intel(E) crypto_simd(E) cryptd(E)
 kernel: Unloaded tainted modules: acpi_cpufreq(E):1 fjes(E):1
 kernel: CR2: 0000000000000028
 kernel: ---[ end trace 0000000000000000 ]---
 kernel: RIP: 0010:hugetlbfs_fill_super+0xb4/0x1a0
 kernel: Code: 48 8b 3b e8 3e c6 ed ff 48 85 c0 48 89 45 20 0f 84 d6 00 00 00 48 b8 ff ff ff ff ff ff ff 7f 4c 89 e7 49 89 44 24 20 48 8b 03 <8b> 48 28 b8 00 10 00 00 48 d3 e0 49 89 44 24 18 48 8b 03 8b 40 28
 kernel: RSP: 0018:ffffbe9960fcbd48 EFLAGS: 00010246
 kernel: RAX: 0000000000000000 RBX: ffff9af5272ae780 RCX: 0000000000372004
 kernel: RDX: ffffffffffffffff RSI: ffffffffffffffff RDI: ffff9af555e9b000
 kernel: RBP: ffff9af52ee66b00 R08: 0000000000000040 R09: 0000000000370004
 kernel: R10: ffffbe9960fcbd48 R11: 0000000000000040 R12: ffff9af555e9b000
 kernel: R13: ffffffffa66b86c0 R14: ffff9af507d2f400 R15: ffff9af507d2f400
 kernel: FS:  00007ffbc0ba4740(0000) GS:ffff9b0bd7000000(0000) knlGS:0000000000000000
 kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 kernel: CR2: 0000000000000028 CR3: 00000001b1ee0000 CR4: 00000000001506f0

Link: https://lkml.kernel.org/r/20240130210418.3771-1-osalvador@suse.de
Fixes: 32021982a324 ("hugetlbfs: Convert to fs_context")
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/hugetlbfs/inode.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ee13c2ca8ad29..d746866ae3b6b 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1365,6 +1365,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 {
 	struct hugetlbfs_fs_context *ctx = fc->fs_private;
 	struct fs_parse_result result;
+	struct hstate *h;
 	char *rest;
 	unsigned long ps;
 	int opt;
@@ -1409,11 +1410,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	case Opt_pagesize:
 		ps = memparse(param->string, &rest);
-		ctx->hstate = size_to_hstate(ps);
-		if (!ctx->hstate) {
+		h = size_to_hstate(ps);
+		if (!h) {
 			pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
 			return -EINVAL;
 		}
+		ctx->hstate = h;
 		return 0;
 
 	case Opt_min_size:
-- 
GitLab


From 27d3969b47cc38810b3fd65d72231940e8671e6c Mon Sep 17 00:00:00 2001
From: Chengming Zhou <zhouchengming@bytedance.com>
Date: Sun, 28 Jan 2024 13:28:49 +0000
Subject: [PATCH 4006/4076] mm/zswap: don't return LRU_SKIP if we have dropped
 lru lock

LRU_SKIP can only be returned if we don't ever dropped lru lock, or we
need to return LRU_RETRY to restart from the head of lru list.

Otherwise, the iteration might continue from a cursor position that was
freed while the locks were dropped.

Actually we may need to introduce another LRU_STOP to really terminate the
ongoing shrinking scan process, when we encounter a warm page already in
the swap cache.  The current list_lru implementation doesn't have this
function to early break from __list_lru_walk_one.

Link: https://lkml.kernel.org/r/20240126-zswap-writeback-race-v2-1-b10479847099@bytedance.com
Fixes: b5ba474f3f51 ("zswap: shrink zswap pool based on memory pressure")
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Cc: Chris Li <chriscli@google.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/zswap.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index 0a94b197ed32e..350dd2fc81599 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -895,10 +895,8 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 		 * into the warmer region. We should terminate shrinking (if we're in the dynamic
 		 * shrinker context).
 		 */
-		if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
-			ret = LRU_SKIP;
+		if (writeback_result == -EEXIST && encountered_page_in_swapcache)
 			*encountered_page_in_swapcache = true;
-		}
 
 		goto put_unlock;
 	}
-- 
GitLab


From 6f1f15a5e492082c8082bea56d87852b65588b5c Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linux.dev>
Date: Thu, 1 Feb 2024 10:10:08 +0800
Subject: [PATCH 4007/4076] MAINTAINERS: Leo Yan has moved

I will lose access to my @linaro.org email address next week, update the
MAINTAINERS file and map it in .mailmap with the new email address.

Link: https://lkml.kernel.org/r/20240201021022.886-1-leo.yan@linux.dev
Signed-off-by: Leo Yan <leo.yan@linux.dev>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index 8ae00bd3708a7..ee8f03cc7f726 100644
--- a/.mailmap
+++ b/.mailmap
@@ -345,6 +345,7 @@ Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
 Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
 Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com>
+Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
 Liam Mark <quic_lmark@quicinc.com> <lmark@codeaurora.org>
 Linas Vepstas <linas@austin.ibm.com>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
diff --git a/MAINTAINERS b/MAINTAINERS
index 960512bec4288..95b47e3cee0aa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17183,7 +17183,7 @@ R:	John Garry <john.g.garry@oracle.com>
 R:	Will Deacon <will@kernel.org>
 R:	James Clark <james.clark@arm.com>
 R:	Mike Leach <mike.leach@linaro.org>
-R:	Leo Yan <leo.yan@linaro.org>
+R:	Leo Yan <leo.yan@linux.dev>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	tools/build/feature/test-libopencsd.c
-- 
GitLab


From 38296afe3c6ee07319e01bb249aa4bb47c07b534 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Wed, 31 Jan 2024 23:56:57 +0900
Subject: [PATCH 4008/4076] nilfs2: fix hang in
 nilfs_lookup_dirty_data_buffers()

Syzbot reported a hang issue in migrate_pages_batch() called by mbind()
and nilfs_lookup_dirty_data_buffers() called in the log writer of nilfs2.

While migrate_pages_batch() locks a folio and waits for the writeback to
complete, the log writer thread that should bring the writeback to
completion picks up the folio being written back in
nilfs_lookup_dirty_data_buffers() that it calls for subsequent log
creation and was trying to lock the folio.  Thus causing a deadlock.

In the first place, it is unexpected that folios/pages in the middle of
writeback will be updated and become dirty.  Nilfs2 adds a checksum to
verify the validity of the log being written and uses it for recovery at
mount, so data changes during writeback are suppressed.  Since this is
broken, an unclean shutdown could potentially cause recovery to fail.

Investigation revealed that the root cause is that the wait for writeback
completion in nilfs_page_mkwrite() is conditional, and if the backing
device does not require stable writes, data may be modified without
waiting.

Fix these issues by making nilfs_page_mkwrite() wait for writeback to
finish regardless of the stable write requirement of the backing device.

Link: https://lkml.kernel.org/r/20240131145657.4209-1-konishi.ryusuke@gmail.com
Fixes: 1d1d1a767206 ("mm: only enforce stable page writes if the backing device requires it")
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Reported-by: syzbot+ee2ae68da3b22d04cd8d@syzkaller.appspotmail.com
Closes: https://lkml.kernel.org/r/00000000000047d819061004ad6c@google.com
Tested-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/file.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index bec33b89a0758..0e3fc5ba33c73 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -107,7 +107,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
 	nilfs_transaction_commit(inode->i_sb);
 
  mapped:
-	folio_wait_stable(folio);
+	/*
+	 * Since checksumming including data blocks is performed to determine
+	 * the validity of the log to be written and used for recovery, it is
+	 * necessary to wait for writeback to finish here, regardless of the
+	 * stable write requirement of the backing device.
+	 */
+	folio_wait_writeback(folio);
  out:
 	sb_end_pagefault(inode->i_sb);
 	return vmf_fs_error(ret);
-- 
GitLab


From b9e4bc1046d20e0623a80660ef8627448056f817 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 2 Feb 2024 11:19:56 -0800
Subject: [PATCH 4009/4076] mm/damon/sysfs-schemes: fix wrong DAMOS tried
 regions update timeout setup

DAMON sysfs interface's update_schemes_tried_regions command has a timeout
of two apply intervals of the DAMOS scheme.  Having zero value DAMOS
scheme apply interval means it will use the aggregation interval as the
value.  However, the timeout setup logic is mistakenly using the sampling
interval insted of the aggregartion interval for the case.  This could
cause earlier-than-expected timeout of the command.  Fix it.

Link: https://lkml.kernel.org/r/20240202191956.88791-1-sj@kernel.org
Fixes: 7d6fa31a2fd7 ("mm/damon/sysfs-schemes: add timeout for update_schemes_tried_regions")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org> # 6.7.x
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/sysfs-schemes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 8dbaac6e5c2d0..dd2fb51270092 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -2194,7 +2194,7 @@ static void damos_tried_regions_init_upd_status(
 		sysfs_regions->upd_timeout_jiffies = jiffies +
 			2 * usecs_to_jiffies(scheme->apply_interval_us ?
 					scheme->apply_interval_us :
-					ctx->attrs.sample_interval);
+					ctx->attrs.aggr_interval);
 	}
 }
 
-- 
GitLab


From 5bc09b397cbf1221f8a8aacb1152650c9195b02b Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Sun, 4 Feb 2024 01:16:45 +0900
Subject: [PATCH 4010/4076] nilfs2: fix potential bug in end_buffer_async_write

According to a syzbot report, end_buffer_async_write(), which handles the
completion of block device writes, may detect abnormal condition of the
buffer async_write flag and cause a BUG_ON failure when using nilfs2.

Nilfs2 itself does not use end_buffer_async_write().  But, the async_write
flag is now used as a marker by commit 7f42ec394156 ("nilfs2: fix issue
with race condition of competition between segments for dirty blocks") as
a means of resolving double list insertion of dirty blocks in
nilfs_lookup_dirty_data_buffers() and nilfs_lookup_node_buffers() and the
resulting crash.

This modification is safe as long as it is used for file data and b-tree
node blocks where the page caches are independent.  However, it was
irrelevant and redundant to also introduce async_write for segment summary
and super root blocks that share buffers with the backing device.  This
led to the possibility that the BUG_ON check in end_buffer_async_write
would fail as described above, if independent writebacks of the backing
device occurred in parallel.

The use of async_write for segment summary buffers has already been
removed in a previous change.

Fix this issue by removing the manipulation of the async_write flag for
the remaining super root block buffer.

Link: https://lkml.kernel.org/r/20240203161645.4992-1-konishi.ryusuke@gmail.com
Fixes: 7f42ec394156 ("nilfs2: fix issue with race condition of competition between segments for dirty blocks")
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Reported-by: syzbot+5c04210f7c7f897c1e7f@syzkaller.appspotmail.com
Closes: https://lkml.kernel.org/r/00000000000019a97c05fd42f8c8@google.com
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nilfs2/segment.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 2590a0860eab0..2bfb08052d399 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1703,7 +1703,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			set_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				if (bh->b_folio != bd_folio) {
 					folio_lock(bd_folio);
@@ -1714,6 +1713,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 				}
 				break;
 			}
+			set_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_begin_folio_io(fs_folio);
 				fs_folio = bh->b_folio;
@@ -1800,7 +1800,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			clear_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				clear_buffer_uptodate(bh);
 				if (bh->b_folio != bd_folio) {
@@ -1809,6 +1808,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 				}
 				break;
 			}
+			clear_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_end_folio_io(fs_folio, err);
 				fs_folio = bh->b_folio;
@@ -1896,8 +1896,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				 BIT(BH_Delay) | BIT(BH_NILFS_Volatile) |
 				 BIT(BH_NILFS_Redirected));
 
-			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh == segbuf->sb_super_root) {
+				set_buffer_uptodate(bh);
+				clear_buffer_dirty(bh);
 				if (bh->b_folio != bd_folio) {
 					folio_end_writeback(bd_folio);
 					bd_folio = bh->b_folio;
@@ -1905,6 +1906,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				update_sr = true;
 				break;
 			}
+			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh->b_folio != fs_folio) {
 				nilfs_end_folio_io(fs_folio, 0);
 				fs_folio = bh->b_folio;
-- 
GitLab


From ddc7d4c584704666fe7088bbd9ec2d72d0f63e65 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 1 Feb 2024 09:55:32 -0800
Subject: [PATCH 4011/4076] drm/xe: Fix loop in vm_bind_ioctl_ops_unwind
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The logic for the unwind loop is incorrect resulting in an infinite
loop. Fix to unwind to go from the last operations list to he first.

Fixes: 617eebb9c480 ("drm/xe: Fix array of binds")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240201175532.2303168-1-matthew.brost@intel.com
(cherry picked from commit 3acc1ff1a72fce00cdbd3ef1c27108a967fd5616)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 30db264d34a32..d45cbf75d2037 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2669,7 +2669,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm,
 {
 	int i;
 
-	for (i = num_ops_list - 1; i; ++i) {
+	for (i = num_ops_list - 1; i >= 0; --i) {
 		struct drm_gpuva_ops *__ops = ops[i];
 		struct drm_gpuva_op *__op;
 
-- 
GitLab


From fc29b6d5ab5395dcb9f35de71e0347f3a6bca542 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 31 Jan 2024 16:48:48 -0800
Subject: [PATCH 4012/4076] drm/xe: Take a reference in
 xe_exec_queue_last_fence_get()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Take a reference in xe_exec_queue_last_fence_get(). Also fix a reference
counting underflow bug VM bind and unbind.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240201004849.2219558-2-matthew.brost@intel.com
(cherry picked from commit a856b67a84169e065ebbeee50258936b1eacc9eb)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c | 8 ++++++--
 drivers/gpu/drm/xe/xe_migrate.c    | 5 ++++-
 drivers/gpu/drm/xe/xe_sched_job.c  | 1 -
 drivers/gpu/drm/xe/xe_sync.c       | 2 --
 drivers/gpu/drm/xe/xe_vm.c         | 1 +
 5 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index bcfc4127c7c59..254b1d3af4cb5 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -926,20 +926,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q)
  * @q: The exec queue
  * @vm: The VM the engine does a bind or exec for
  *
- * Get last fence, does not take a ref
+ * Get last fence, takes a ref
  *
  * Returns: last fence if not signaled, dma fence stub if signaled
  */
 struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
 					       struct xe_vm *vm)
 {
+	struct dma_fence *fence;
+
 	xe_exec_queue_last_fence_lockdep_assert(q, vm);
 
 	if (q->last_fence &&
 	    test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
 		xe_exec_queue_last_fence_put(q, vm);
 
-	return q->last_fence ? q->last_fence : dma_fence_get_stub();
+	fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+	dma_fence_get(fence);
+	return fence;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 5c6c546242521..0cc31837ef26b 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -1204,8 +1204,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
 	}
 	if (q) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			dma_fence_put(fence);
 			return false;
+		}
+		dma_fence_put(fence);
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad8..4e2ccad0e52fa 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
 	struct dma_fence *fence;
 
 	fence = xe_exec_queue_last_fence_get(job->q, vm);
-	dma_fence_get(fence);
 
 	return drm_sched_job_add_dependency(&job->drm, fence);
 }
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index e4c220cf9115e..aab92bee1d7cf 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -307,7 +307,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 	/* Easy case... */
 	if (!num_in_fence) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		dma_fence_get(fence);
 		return fence;
 	}
 
@@ -322,7 +321,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		}
 	}
 	fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm);
-	dma_fence_get(fences[current_fence - 1]);
 	cf = dma_fence_array_create(num_in_fence, fences,
 				    vm->composite_fence_ctx,
 				    vm->composite_fence_seqno++,
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d45cbf75d2037..96b1833c0e8c6 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1984,6 +1984,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
 					xe_exec_queue_last_fence_get(wait_exec_queue, vm);
 
 				xe_sync_entry_signal(&syncs[i], NULL, fence);
+				dma_fence_put(fence);
 			}
 		}
 
-- 
GitLab


From 21abf108a062fa0323077b5ba3d26e2c0bba9232 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 31 Jan 2024 16:48:49 -0800
Subject: [PATCH 4013/4076] drm/xe: Pick correct userptr VMA to repin on REMAP
 op failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A REMAP op is composed of 3 VMA's - unmap, prev map, and next map. When
op_execute fails with -EAGAIN we need to update the local VMA pointer to
the current op state and then repin the VMA if it is a userptr.

Fixes a failure seen in xe_vm.munmap-style-unbind-userptr-one-partial.

Fixes: b06d47be7c83 ("drm/xe: Port Xe to GPUVA")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240201004849.2219558-3-matthew.brost@intel.com
(cherry picked from commit 447f74d223b4f6cbab74963bf1099050c15374ce)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 96b1833c0e8c6..ca11f83811155 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2531,13 +2531,25 @@ retry_userptr:
 	}
 	drm_exec_fini(&exec);
 
-	if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
+	if (err == -EAGAIN) {
 		lockdep_assert_held_write(&vm->lock);
-		err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
-		if (!err)
-			goto retry_userptr;
 
-		trace_xe_vma_fail(vma);
+		if (op->base.op == DRM_GPUVA_OP_REMAP) {
+			if (!op->remap.unmap_done)
+				vma = gpuva_to_vma(op->base.remap.unmap->va);
+			else if (op->remap.prev)
+				vma = op->remap.prev;
+			else
+				vma = op->remap.next;
+		}
+
+		if (xe_vma_is_userptr(vma)) {
+			err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+			if (!err)
+				goto retry_userptr;
+
+			trace_xe_vma_fail(vma);
+		}
 	}
 
 	return err;
-- 
GitLab


From 90773aaf9129ea6f47915bd3c47da261abe6a447 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 3 Jan 2024 12:48:02 +0100
Subject: [PATCH 4014/4076] drm/xe: circumvent bogus stringop-overflow warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

gcc-13 warns about an array overflow that it sees but that is
prevented by the "asid % NUM_PF_QUEUE" calculation:

drivers/gpu/drm/xe/xe_gt_pagefault.c: In function 'xe_guc_pagefault_handler':
include/linux/fortify-string.h:57:33: error: writing 16 bytes into a region of size 0 [-Werror=stringop-overflow=]
include/linux/fortify-string.h:689:26: note: in expansion of macro '__fortify_memcpy_chk'
  689 | #define memcpy(p, q, s)  __fortify_memcpy_chk(p, q, s,                  \
      |                          ^~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/xe/xe_gt_pagefault.c:341:17: note: in expansion of macro 'memcpy'
  341 |                 memcpy(pf_queue->data + pf_queue->tail, msg, len * sizeof(u32));
      |                 ^~~~~~
drivers/gpu/drm/xe/xe_gt_types.h:102:25: note: at offset [1144, 265324] into destination object 'tile' of size 8

I found that rewriting the assignment using pointer addition rather than the
equivalent array index calculation prevents the warning, so use that instead.

I sent a bug report against gcc for the false positive warning.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113214
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240103114819.2913937-1-arnd@kernel.org
(cherry picked from commit 774ef5dfc95578a9079426d5106076dcd59c4dfa)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_gt_pagefault.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 9c2fe1697d6ee..73f08f1924df2 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -335,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 		return -EPROTO;
 
 	asid = FIELD_GET(PFD_ASID, msg[1]);
-	pf_queue = &gt->usm.pf_queue[asid % NUM_PF_QUEUE];
+	pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE);
 
 	spin_lock_irqsave(&pf_queue->lock, flags);
 	full = pf_queue_full(pf_queue);
-- 
GitLab


From 3aa3c5c249086ffc920e8f6d6a15bdd441153d45 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 1 Feb 2024 19:34:40 -0800
Subject: [PATCH 4015/4076] drm/xe: Map both mem.kernel_bb_pool and usm.bb_pool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For integrated devices we need to map both mem.kernel_bb_pool and
usm.bb_pool to be able to run batches from both pools.

Fixes: a682b6a42d4d ("drm/xe: Support device page faults on integrated platforms")
Tested-by: Brian Welty <brian.welty@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Brian Welty <brian.welty@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202033440.2351862-1-matthew.brost@intel.com
(cherry picked from commit 72f86ed3c88933d6fa09b036de93621ea71097a7)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_gt.c      |  5 ++++-
 drivers/gpu/drm/xe/xe_migrate.c | 23 ++++++++++++++++++-----
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3af2adec12956..35474ddbaf97e 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
 		 * USM has its only SA pool to non-block behind user operations
 		 */
 		if (gt_to_xe(gt)->info.has_usm) {
-			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16);
+			struct xe_device *xe = gt_to_xe(gt);
+
+			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt),
+								IS_DGFX(xe) ? SZ_1M : SZ_512K, 16);
 			if (IS_ERR(gt->usm.bb_pool)) {
 				err = PTR_ERR(gt->usm.bb_pool);
 				goto err_force_wake;
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 0cc31837ef26b..70480c3056021 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	if (!IS_DGFX(xe)) {
 		/* Write out batch too */
 		m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
-		if (xe->info.has_usm) {
-			batch = tile->primary_gt->usm.bb_pool->bo;
-			m->usm_batch_base_ofs = m->batch_base_ofs;
-		}
-
 		for (i = 0; i < batch->size;
 		     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
 		     XE_PAGE_SIZE) {
@@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 				  entry);
 			level++;
 		}
+		if (xe->info.has_usm) {
+			xe_tile_assert(tile, batch->size == SZ_1M);
+
+			batch = tile->primary_gt->usm.bb_pool->bo;
+			m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+			xe_tile_assert(tile, batch->size == SZ_512K);
+
+			for (i = 0; i < batch->size;
+			     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+			     XE_PAGE_SIZE) {
+				entry = vm->pt_ops->pte_encode_bo(batch, i,
+								  pat_index, 0);
+
+				xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+					  entry);
+				level++;
+			}
+		}
 	} else {
 		u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
 
-- 
GitLab


From 11572b3f68d9933fef5c1afef4c20041701d8025 Mon Sep 17 00:00:00 2001
From: Xiaoming Wang <xiaoming.wang@intel.com>
Date: Fri, 2 Feb 2024 13:56:58 -0800
Subject: [PATCH 4016/4076] drm/xe/display: Fix memleak in display
 initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

intel_power_domains_init is called twice in xe_device_probe:

1) intel_power_domains_init()
   xe_display_init_nommio()
   xe_device_probe()

2) intel_power_domains_init()
   intel_display_driver_probe_noirq()
   xe_display_init_noirq()
   xe_device_probe()

It needs remove one to avoid power_domains->power_wells double malloc.

unreferenced object 0xffff88811150ee00 (size 512):
  comm "systemd-udevd", pid 506, jiffies 4294674198 (age 3605.560s)
  hex dump (first 32 bytes):
    10 b4 9d a0 ff ff ff ff ff ff ff ff ff ff ff ff  ................
    ff ff ff ff ff ff ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff8134b901>] __kmem_cache_alloc_node+0x1c1/0x2b0
    [<ffffffff812c98b2>] __kmalloc+0x52/0x150
    [<ffffffffa08b0033>] __set_power_wells+0xc3/0x360 [xe]
    [<ffffffffa08562fc>] xe_display_init_nommio+0x4c/0x70 [xe]
    [<ffffffffa07f0d1c>] xe_device_probe+0x3c/0x5a0 [xe]
    [<ffffffffa082e48f>] xe_pci_probe+0x33f/0x5a0 [xe]
    [<ffffffff817f2187>] local_pci_probe+0x47/0xa0
    [<ffffffff817f3db3>] pci_device_probe+0xc3/0x1f0
    [<ffffffff8192f2a2>] really_probe+0x1a2/0x410
    [<ffffffff8192f598>] __driver_probe_device+0x78/0x160
    [<ffffffff8192f6ae>] driver_probe_device+0x1e/0x90
    [<ffffffff8192f92a>] __driver_attach+0xda/0x1d0
    [<ffffffff8192c95c>] bus_for_each_dev+0x7c/0xd0
    [<ffffffff8192e159>] bus_add_driver+0x119/0x220
    [<ffffffff81930d00>] driver_register+0x60/0x120
    [<ffffffffa05e50a0>] 0xffffffffa05e50a0

The call to intel_power_domains_cleanup() needs to stay where it is for
now. The main issue is that while the init is called by the display
side, shared by i915 and xe, the cleanup is called by a non-shared code
path. Fixing that will be done as a separate commit.

Fixes: 44e694958b95 ("drm/xe/display: Implement display support")
Signed-off-by: Xiaoming Wang <xiaoming.wang@intel.com>
[ reword commit message and explain why the fini needs to stay
  where it is ]
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202215658.561298-1-lucas.demarchi@intel.com
(cherry picked from commit 86c99abb5f1b6fcd69fb268eeb2e34cb7c4f355c)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_display.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c
index 74391d9b11ae0..e4db069f0db3f 100644
--- a/drivers/gpu/drm/xe/xe_display.c
+++ b/drivers/gpu/drm/xe/xe_display.c
@@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy)
 
 int xe_display_init_nommio(struct xe_device *xe)
 {
-	int err;
-
 	if (!xe->info.enable_display)
 		return 0;
 
@@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe)
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(xe);
 
-	err = intel_power_domains_init(xe);
-	if (err)
-		return err;
-
 	return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe);
 }
 
-- 
GitLab


From 95c058c8ef1d5d9e39ab2039a5eea4d5b93f4117 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 5 Feb 2024 15:17:14 -0800
Subject: [PATCH 4017/4076] drm/xe: Assume large page size if VMA not yet bound
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The calculation to determine max page size of a VMA during a REMAP
operations assumes the VMA has been bound. This assumption is not true
if the VMA is from an eariler operation in an array of binds. If a VMA
has not been bound use the maximum page size which will ensure the
previous / next REMAP operations are not incorrectly skipped.

Fixes: 8f33b4f054fc ("drm/xe: Avoid doing rebinds")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240205231714.2956225-1-matthew.brost@intel.com
(cherry picked from commit 5ad6af5c91e9b942c44b657122270d935db3a813)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ca11f83811155..99f151d73154a 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2200,8 +2200,10 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma)
 		return SZ_1G;
 	else if (vma->gpuva.flags & XE_VMA_PTE_2M)
 		return SZ_2M;
+	else if (vma->gpuva.flags & XE_VMA_PTE_4K)
+		return SZ_4K;
 
-	return SZ_4K;
+	return SZ_1G;	/* Uninitialized, used max size */
 }
 
 static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
-- 
GitLab


From 9e3fc1d65d4e8cf302e289847ab165ad9358fdb2 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 2 Feb 2024 17:14:36 +0000
Subject: [PATCH 4018/4076] drm/xe/vm: don't ignore error when in_kthread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If GUP fails and we are in_kthread, we can have pinned = 0 and ret = 0.
If that happens we call sg_alloc_append_table_from_pages() with n_pages
= 0, which is not well behaved and can trigger:

kernel BUG at include/linux/scatterlist.h:115!

depending on if the pages array happens to be zeroed or not. Even if we
don't hit that it crashes later when trying to dma_map the returned
table.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202171435.427630-2-matthew.auld@intel.com
(cherry picked from commit 8087199cd5951c1eba26003b3e4296dbb2110adf)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 99f151d73154a..a9df894131559 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -114,11 +114,8 @@ retry:
 					  num_pages - pinned,
 					  read_only ? 0 : FOLL_WRITE,
 					  &pages[pinned]);
-		if (ret < 0) {
-			if (in_kthread)
-				ret = 0;
+		if (ret < 0)
 			break;
-		}
 
 		pinned += ret;
 		ret = 0;
-- 
GitLab


From bf4c27b8267d7848bb81fd41e6aa07aa662f07fb Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 5 Feb 2024 20:50:10 -0800
Subject: [PATCH 4019/4076] drm/xe: Remove TEST_VM_ASYNC_OPS_ERROR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

TEST_VM_ASYNC_OPS_ERROR is broken and unused. Remove for now and will
pull back in a later time when it is used, fixed, and properly hidden
behind a Kconfig option. Also fixup the supported flags value.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240206045010.2981051-1-matthew.brost@intel.com
(cherry picked from commit d9890c028d66a9e1ee3cccaa081ab5aedcbfe431)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c       | 28 +---------------------------
 drivers/gpu/drm/xe/xe_vm_types.h |  8 --------
 2 files changed, 1 insertion(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index a9df894131559..865e10d0a06aa 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -37,8 +37,6 @@
 #include "generated/xe_wa_oob.h"
 #include "xe_wa.h"
 
-#define TEST_VM_ASYNC_OPS_ERROR
-
 static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 {
 	return vm->gpuvm.r_obj;
@@ -2062,7 +2060,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL;
 	struct drm_gpuva_ops *ops;
 	struct drm_gpuva_op *__op;
-	struct xe_vma_op *op;
 	struct drm_gpuvm_bo *vm_bo;
 	int err;
 
@@ -2109,15 +2106,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	if (IS_ERR(ops))
 		return ops;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (operation & FORCE_ASYNC_OP_ERROR) {
-		op = list_first_entry_or_null(&ops->list, struct xe_vma_op,
-					      base.entry);
-		if (op)
-			op->inject_error = true;
-	}
-#endif
-
 	drm_gpuva_for_each_op(__op, ops) {
 		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
 
@@ -2560,13 +2548,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op)
 
 	lockdep_assert_held_write(&vm->lock);
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (op->inject_error) {
-		op->inject_error = false;
-		return -ENOMEM;
-	}
-#endif
-
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
 		ret = __xe_vma_op_execute(vm, op->map.vma, op);
@@ -2726,16 +2707,9 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
 	return 0;
 }
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-#define SUPPORTED_FLAGS	\
-	(FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff)
-#else
 #define SUPPORTED_FLAGS	\
 	(DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \
-	 0xffff)
-#endif
+	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL)
 #define XE_64K_PAGE_MASK 0xffffull
 #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 1fec66ae2eb2d..5ac9c5bebabc3 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -21,9 +21,6 @@ struct xe_bo;
 struct xe_sync_entry;
 struct xe_vm;
 
-#define TEST_VM_ASYNC_OPS_ERROR
-#define FORCE_ASYNC_OP_ERROR	BIT(31)
-
 #define XE_VMA_READ_ONLY	DRM_GPUVA_USERBITS
 #define XE_VMA_DESTROYED	(DRM_GPUVA_USERBITS << 1)
 #define XE_VMA_ATOMIC_PTE_BIT	(DRM_GPUVA_USERBITS << 2)
@@ -360,11 +357,6 @@ struct xe_vma_op {
 	/** @flags: operation flags */
 	enum xe_vma_op_flags flags;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	/** @inject_error: inject error to test async op error handling */
-	bool inject_error;
-#endif
-
 	union {
 		/** @map: VMA map operation specific data */
 		struct xe_vma_op_map map;
-- 
GitLab


From ab0beafd52b98dfb8b8244b2c6794efbc87478db Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 2 Feb 2024 10:09:34 +0100
Subject: [PATCH 4020/4076] netfilter: nft_set_pipapo: remove static in
 nft_pipapo_get()

This has slipped through when reducing memory footprint for set
elements, remove it.

Fixes: 9dad402b89e8 ("netfilter: nf_tables: expose opaque set element as struct nft_elem_priv")
Reported-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_pipapo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index efd523496be45..f24ecdaa1c1ed 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -603,7 +603,7 @@ static struct nft_elem_priv *
 nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	       const struct nft_set_elem *elem, unsigned int flags)
 {
-	static struct nft_pipapo_elem *e;
+	struct nft_pipapo_elem *e;
 
 	e = pipapo_get(net, set, (const u8 *)elem->key.val.data,
 		       nft_genmask_cur(net));
-- 
GitLab


From 2526dffc6d65cffa32b88556bd68e4e72e889a55 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 5 Feb 2024 11:22:29 +0100
Subject: [PATCH 4021/4076] gpio: remove GPIO device from the list
 unconditionally in error path

Since commit 48e1b4d369cf ("gpiolib: remove the GPIO device from the list
when it's unregistered") we remove the GPIO device entry from the global
list (used to order devices by their GPIO ranges) when unregistering the
chip, not when releasing the device. It will not happen when the last
reference is put anymore. This means, we need to remove it in error path
in gpiochip_add_data_with_key() unconditionally, without checking if the
device's .release() callback is set.

Fixes: 48e1b4d369cf ("gpiolib: remove the GPIO device from the list when it's unregistered")
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 44c8f5743a241..8b3a0f45b5745 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1005,15 +1005,15 @@ err_remove_of_chip:
 err_free_gpiochip_mask:
 	gpiochip_remove_pin_ranges(gc);
 	gpiochip_free_valid_mask(gc);
+err_remove_from_list:
+	spin_lock_irqsave(&gpio_lock, flags);
+	list_del(&gdev->list);
+	spin_unlock_irqrestore(&gpio_lock, flags);
 	if (gdev->dev.release) {
 		/* release() has been registered by gpiochip_setup_dev() */
 		gpio_device_put(gdev);
 		goto err_print_message;
 	}
-err_remove_from_list:
-	spin_lock_irqsave(&gpio_lock, flags);
-	list_del(&gdev->list);
-	spin_unlock_irqrestore(&gpio_lock, flags);
 err_free_label:
 	kfree_const(gdev->label);
 err_free_descs:
-- 
GitLab


From 9def04e759caa5a3d741891037ae99f81e2fff01 Mon Sep 17 00:00:00 2001
From: Sinthu Raja <sinthu.raja@ti.com>
Date: Tue, 6 Feb 2024 06:29:27 +0530
Subject: [PATCH 4022/4076] net: ethernet: ti: cpsw_new: enable mac_managed_pm
 to fix mdio

The below commit  introduced a WARN when phy state is not in the states:
PHY_HALTED, PHY_READY and PHY_UP.
commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")

When cpsw_new resumes, there have port in PHY_NOLINK state, so the below
warning comes out. Set mac_managed_pm be true to tell mdio that the phy
resume/suspend is managed by the mac, to fix the following warning:

WARNING: CPU: 0 PID: 965 at drivers/net/phy/phy_device.c:326 mdio_bus_phy_resume+0x140/0x144
CPU: 0 PID: 965 Comm: sh Tainted: G           O       6.1.46-g247b2535b2 #1
Hardware name: Generic AM33XX (Flattened Device Tree)
 unwind_backtrace from show_stack+0x18/0x1c
 show_stack from dump_stack_lvl+0x24/0x2c
 dump_stack_lvl from __warn+0x84/0x15c
 __warn from warn_slowpath_fmt+0x1a8/0x1c8
 warn_slowpath_fmt from mdio_bus_phy_resume+0x140/0x144
 mdio_bus_phy_resume from dpm_run_callback+0x3c/0x140
 dpm_run_callback from device_resume+0xb8/0x2b8
 device_resume from dpm_resume+0x144/0x314
 dpm_resume from dpm_resume_end+0x14/0x20
 dpm_resume_end from suspend_devices_and_enter+0xd0/0x924
 suspend_devices_and_enter from pm_suspend+0x2e0/0x33c
 pm_suspend from state_store+0x74/0xd0
 state_store from kernfs_fop_write_iter+0x104/0x1ec
 kernfs_fop_write_iter from vfs_write+0x1b8/0x358
 vfs_write from ksys_write+0x78/0xf8
 ksys_write from ret_fast_syscall+0x0/0x54
Exception stack(0xe094dfa8 to 0xe094dff0)
dfa0:                   00000004 005c3fb8 00000001 005c3fb8 00000004 00000001
dfc0: 00000004 005c3fb8 b6f6bba0 00000004 00000004 0059edb8 00000000 00000000
dfe0: 00000004 bed918f0 b6f09bd3 b6e89a66

Cc: <stable@vger.kernel.org> # v6.0+
Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")
Fixes: fba863b81604 ("net: phy: make PHY PM ops a no-op if MAC driver manages PHY PM")
Signed-off-by: Sinthu Raja <sinthu.raja@ti.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/cpsw_new.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 498c50c6d1a70..087dcb67505a2 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -773,6 +773,9 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 			slave->slave_num);
 		return;
 	}
+
+	phy->mac_managed_pm = true;
+
 	slave->phy = phy;
 
 	phy_attached_info(slave->phy);
-- 
GitLab


From bc4ce46b1e3d1da4309405cd4afc7c0fcddd0b90 Mon Sep 17 00:00:00 2001
From: Sinthu Raja <sinthu.raja@ti.com>
Date: Tue, 6 Feb 2024 06:29:28 +0530
Subject: [PATCH 4023/4076] net: ethernet: ti: cpsw: enable mac_managed_pm to
 fix mdio

The below commit  introduced a WARN when phy state is not in the states:
PHY_HALTED, PHY_READY and PHY_UP.
commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")

When cpsw resumes, there have port in PHY_NOLINK state, so the below
warning comes out. Set mac_managed_pm be true to tell mdio that the phy
resume/suspend is managed by the mac, to fix the following warning:

WARNING: CPU: 0 PID: 965 at drivers/net/phy/phy_device.c:326 mdio_bus_phy_resume+0x140/0x144
CPU: 0 PID: 965 Comm: sh Tainted: G           O       6.1.46-g247b2535b2 #1
Hardware name: Generic AM33XX (Flattened Device Tree)
 unwind_backtrace from show_stack+0x18/0x1c
 show_stack from dump_stack_lvl+0x24/0x2c
 dump_stack_lvl from __warn+0x84/0x15c
 __warn from warn_slowpath_fmt+0x1a8/0x1c8
 warn_slowpath_fmt from mdio_bus_phy_resume+0x140/0x144
 mdio_bus_phy_resume from dpm_run_callback+0x3c/0x140
 dpm_run_callback from device_resume+0xb8/0x2b8
 device_resume from dpm_resume+0x144/0x314
 dpm_resume from dpm_resume_end+0x14/0x20
 dpm_resume_end from suspend_devices_and_enter+0xd0/0x924
 suspend_devices_and_enter from pm_suspend+0x2e0/0x33c
 pm_suspend from state_store+0x74/0xd0
 state_store from kernfs_fop_write_iter+0x104/0x1ec
 kernfs_fop_write_iter from vfs_write+0x1b8/0x358
 vfs_write from ksys_write+0x78/0xf8
 ksys_write from ret_fast_syscall+0x0/0x54
Exception stack(0xe094dfa8 to 0xe094dff0)
dfa0:                   00000004 005c3fb8 00000001 005c3fb8 00000004 00000001
dfc0: 00000004 005c3fb8 b6f6bba0 00000004 00000004 0059edb8 00000000 00000000
dfe0: 00000004 bed918f0 b6f09bd3 b6e89a66

Cc: <stable@vger.kernel.org> # v6.0+
Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")
Fixes: fba863b81604 ("net: phy: make PHY PM ops a no-op if MAC driver manages PHY PM")
Signed-off-by: Sinthu Raja <sinthu.raja@ti.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/cpsw.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index ea85c6dd54846..c0a5abd8d9a8e 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -631,6 +631,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 		}
 	}
 
+	phy->mac_managed_pm = true;
+
 	slave->phy = phy;
 
 	phy_attached_info(slave->phy);
-- 
GitLab


From db010ff6700f24f96e91ed56ca29cb69335008ef Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Tue, 6 Feb 2024 08:10:00 +0530
Subject: [PATCH 4024/4076] octeontx2-af: Initialize maps.

kmalloc_array() without __GFP_ZERO flag does not initialize
memory to zero. This causes issues. Use kcalloc() for maps and
bitmap_zalloc() for bitmaps.

Fixes: dd7842878633 ("octeontx2-af: Add new devlink param to configure maximum usable NIX block LFs")
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Reviewed-by: Brett Creeley <bcreeley@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240206024000.1070260-1-rkannoth@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/marvell/octeontx2/af/rvu_npc.c   | 31 +++++++++----------
 1 file changed, 15 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 167145bdcb75d..8cfd74ad991cc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -1850,8 +1850,8 @@ void npc_mcam_rsrcs_deinit(struct rvu *rvu)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 
-	kfree(mcam->bmap);
-	kfree(mcam->bmap_reverse);
+	bitmap_free(mcam->bmap);
+	bitmap_free(mcam->bmap_reverse);
 	kfree(mcam->entry2pfvf_map);
 	kfree(mcam->cntr2pfvf_map);
 	kfree(mcam->entry2cntr_map);
@@ -1904,21 +1904,20 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	mcam->pf_offset = mcam->nixlf_offset + nixlf_count;
 
 	/* Allocate bitmaps for managing MCAM entries */
-	mcam->bmap = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
-				   sizeof(long), GFP_KERNEL);
+	mcam->bmap = bitmap_zalloc(mcam->bmap_entries, GFP_KERNEL);
 	if (!mcam->bmap)
 		return -ENOMEM;
 
-	mcam->bmap_reverse = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
-					   sizeof(long), GFP_KERNEL);
+	mcam->bmap_reverse = bitmap_zalloc(mcam->bmap_entries, GFP_KERNEL);
 	if (!mcam->bmap_reverse)
 		goto free_bmap;
 
 	mcam->bmap_fcnt = mcam->bmap_entries;
 
 	/* Alloc memory for saving entry to RVU PFFUNC allocation mapping */
-	mcam->entry2pfvf_map = kmalloc_array(mcam->bmap_entries,
-					     sizeof(u16), GFP_KERNEL);
+	mcam->entry2pfvf_map = kcalloc(mcam->bmap_entries, sizeof(u16),
+				       GFP_KERNEL);
+
 	if (!mcam->entry2pfvf_map)
 		goto free_bmap_reverse;
 
@@ -1941,21 +1940,21 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	if (err)
 		goto free_entry_map;
 
-	mcam->cntr2pfvf_map = kmalloc_array(mcam->counters.max,
-					    sizeof(u16), GFP_KERNEL);
+	mcam->cntr2pfvf_map = kcalloc(mcam->counters.max, sizeof(u16),
+				      GFP_KERNEL);
 	if (!mcam->cntr2pfvf_map)
 		goto free_cntr_bmap;
 
 	/* Alloc memory for MCAM entry to counter mapping and for tracking
 	 * counter's reference count.
 	 */
-	mcam->entry2cntr_map = kmalloc_array(mcam->bmap_entries,
-					     sizeof(u16), GFP_KERNEL);
+	mcam->entry2cntr_map = kcalloc(mcam->bmap_entries, sizeof(u16),
+				       GFP_KERNEL);
 	if (!mcam->entry2cntr_map)
 		goto free_cntr_map;
 
-	mcam->cntr_refcnt = kmalloc_array(mcam->counters.max,
-					  sizeof(u16), GFP_KERNEL);
+	mcam->cntr_refcnt = kcalloc(mcam->counters.max, sizeof(u16),
+				    GFP_KERNEL);
 	if (!mcam->cntr_refcnt)
 		goto free_entry_cntr_map;
 
@@ -1988,9 +1987,9 @@ free_cntr_bmap:
 free_entry_map:
 	kfree(mcam->entry2pfvf_map);
 free_bmap_reverse:
-	kfree(mcam->bmap_reverse);
+	bitmap_free(mcam->bmap_reverse);
 free_bmap:
-	kfree(mcam->bmap);
+	bitmap_free(mcam->bmap);
 
 	return -ENOMEM;
 }
-- 
GitLab


From 27c5a095e2518975e20a10102908ae8231699879 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@netfilter.org>
Date: Sun, 4 Feb 2024 16:26:42 +0100
Subject: [PATCH 4025/4076] netfilter: ipset: Missing gc cancellations fixed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The patch fdb8e12cc2cc ("netfilter: ipset: fix performance regression
in swap operation") missed to add the calls to gc cancellations
at the error path of create operations and at module unload. Also,
because the half of the destroy operations now executed by a
function registered by call_rcu(), neither NFNL_SUBSYS_IPSET mutex
or rcu read lock is held and therefore the checking of them results
false warnings.

Fixes: 97f7cf1cd80e ("netfilter: ipset: fix performance regression in swap operation")
Reported-by: syzbot+52bbc0ad036f6f0d4a25@syzkaller.appspotmail.com
Reported-by: Brad Spengler <spender@grsecurity.net>
Reported-by: Стас Ничипорович <stasn77@gmail.com>
Tested-by: Brad Spengler <spender@grsecurity.net>
Tested-by: Стас Ничипорович <stasn77@gmail.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipset/ip_set_core.c     | 2 ++
 net/netfilter/ipset/ip_set_hash_gen.h | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index bcaad9c009fe0..3184cc6be4c9d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1154,6 +1154,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info,
 	return ret;
 
 cleanup:
+	set->variant->cancel_gc(set);
 	set->variant->destroy(set);
 put_out:
 	module_put(set->type->me);
@@ -2378,6 +2379,7 @@ ip_set_net_exit(struct net *net)
 		set = ip_set(inst, i);
 		if (set) {
 			ip_set(inst, i) = NULL;
+			set->variant->cancel_gc(set);
 			ip_set_destroy_set(set);
 		}
 	}
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 1136510521a80..cf3ce72c3de64 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -432,7 +432,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
 	u32 i;
 
 	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference(hbucket(t, i));
+		n = (__force struct hbucket *)hbucket(t, i);
 		if (!n)
 			continue;
 		if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
@@ -452,7 +452,7 @@ mtype_destroy(struct ip_set *set)
 	struct htype *h = set->data;
 	struct list_head *l, *lt;
 
-	mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
+	mtype_ahash_destroy(set, (__force struct htable *)h->table, true);
 	list_for_each_safe(l, lt, &h->ad) {
 		list_del(l);
 		kfree(l);
-- 
GitLab


From 2fe8a236436fe40d8d26a1af8d150fc80f04ee1a Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Tue, 6 Feb 2024 09:58:49 +0100
Subject: [PATCH 4026/4076] s390/qeth: Fix potential loss of L3-IP@ in case of
 network issues

Symptom:
In case of a bad cable connection (e.g. dirty optics) a fast sequence of
network DOWN-UP-DOWN-UP could happen. UP triggers recovery of the qeth
interface. In case of a second DOWN while recovery is still ongoing, it
can happen that the IP@ of a Layer3 qeth interface is lost and will not
be recovered by the second UP.

Problem:
When registration of IP addresses with Layer 3 qeth devices fails, (e.g.
because of bad address format) the respective IP address is deleted from
its hash-table in the driver. If registration fails because of a ENETDOWN
condition, the address should stay in the hashtable, so a subsequent
recovery can restore it.

3caa4af834df ("qeth: keep ip-address after LAN_OFFLINE failure")
fixes this for registration failures during normal operation, but not
during recovery.

Solution:
Keep L3-IP address in case of ENETDOWN in qeth_l3_recover_ip(). For
consistency with qeth_l3_add_ip() we also keep it in case of EADDRINUSE,
i.e. for some reason the card already/still has this address registered.

Fixes: 4a71df50047f ("qeth: new qeth device driver")
Cc: stable@vger.kernel.org
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Link: https://lore.kernel.org/r/20240206085849.2902775-1-wintera@linux.ibm.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/s390/net/qeth_l3_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index b92a32b4b1141..04c64ce0a1ca1 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -255,9 +255,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover)
 		if (!recover) {
 			hash_del(&addr->hnode);
 			kfree(addr);
-			continue;
+		} else {
+			/* prepare for recovery */
+			addr->disp_flag = QETH_DISP_ADDR_ADD;
 		}
-		addr->disp_flag = QETH_DISP_ADDR_ADD;
 	}
 
 	mutex_unlock(&card->ip_lock);
@@ -278,9 +279,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card)
 		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
 			rc = qeth_l3_register_addr_entry(card, addr);
 
-			if (!rc) {
+			if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) {
+				/* keep it in the records */
 				addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			} else {
+				/* bad address */
 				hash_del(&addr->hnode);
 				kfree(addr);
 			}
-- 
GitLab


From fa173a1b4e3fd1ab5451cbc57de6fc624c824b0a Mon Sep 17 00:00:00 2001
From: Felix Huettner <felix.huettner@mail.schwarz>
Date: Mon, 5 Feb 2024 09:59:59 +0000
Subject: [PATCH 4027/4076] netfilter: ctnetlink: fix filtering for zone 0

previously filtering for the default zone would actually skip the zone
filter and flush all zones.

Fixes: eff3c558bb7e ("netfilter: ctnetlink: support filtering by zone")
Reported-by: Ilya Maximets <i.maximets@ovn.org>
Closes: https://lore.kernel.org/netdev/2032238f-31ac-4106-8f22-522e76df5a12@ovn.org/
Signed-off-by: Felix Huettner <felix.huettner@mail.schwarz>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_netlink.c          | 12 ++++--
 .../netfilter/conntrack_dump_flush.c          | 43 ++++++++++++++++++-
 2 files changed, 50 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 0c22a02c2035c..3b846cbdc050d 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -876,6 +876,7 @@ struct ctnetlink_filter_u32 {
 
 struct ctnetlink_filter {
 	u8 family;
+	bool zone_filter;
 
 	u_int32_t orig_flags;
 	u_int32_t reply_flags;
@@ -992,9 +993,12 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 	if (err)
 		goto err_filter;
 
-	err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
-	if (err < 0)
-		goto err_filter;
+	if (cda[CTA_ZONE]) {
+		err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
+		if (err < 0)
+			goto err_filter;
+		filter->zone_filter = true;
+	}
 
 	if (!cda[CTA_FILTER])
 		return filter;
@@ -1148,7 +1152,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 	if (filter->family && nf_ct_l3num(ct) != filter->family)
 		goto ignore_entry;
 
-	if (filter->zone.id != NF_CT_DEFAULT_ZONE_ID &&
+	if (filter->zone_filter &&
 	    !nf_ct_zone_equal_any(ct, &filter->zone))
 		goto ignore_entry;
 
diff --git a/tools/testing/selftests/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
index f18c6db13bbff..b11ea8ee67194 100644
--- a/tools/testing/selftests/netfilter/conntrack_dump_flush.c
+++ b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
@@ -13,7 +13,7 @@
 #include "../kselftest_harness.h"
 
 #define TEST_ZONE_ID 123
-#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2)
+#define NF_CT_DEFAULT_ZONE_ID 0
 
 static int reply_counter;
 
@@ -336,6 +336,9 @@ FIXTURE_SETUP(conntrack_dump_flush)
 	ret = conntrack_data_generate_v4(self->sock, 0xf4f4f4f4, 0xf5f5f5f5,
 					 TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 0);
+	ret = conntrack_data_generate_v4(self->sock, 0xf6f6f6f6, 0xf7f7f7f7,
+					 NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
 
 	src = (struct in6_addr) {{
 		.__u6_addr32 = {
@@ -395,6 +398,26 @@ FIXTURE_SETUP(conntrack_dump_flush)
 					 TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 0);
 
+	src = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x07000000
+		}
+	}};
+	dst = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x08000000
+		}
+	}};
+	ret = conntrack_data_generate_v6(self->sock, src, dst,
+					 NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+
 	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
 	EXPECT_GE(ret, 2);
 	if (ret > 2)
@@ -425,6 +448,24 @@ TEST_F(conntrack_dump_flush, test_flush_by_zone)
 	EXPECT_EQ(ret, 2);
 	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 2);
+}
+
+TEST_F(conntrack_dump_flush, test_flush_by_zone_default)
+{
+	int ret;
+
+	ret = conntrack_flush_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 1);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
 }
 
 TEST_HARNESS_MAIN
-- 
GitLab


From 38ed1c7062ada30d7c11e7a7acc749bf27aa14aa Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 5 Feb 2024 14:59:24 +0100
Subject: [PATCH 4028/4076] netfilter: nft_ct: reject direction for ct id

Direction attribute is ignored, reject it in case this ever needs to be
supported

Fixes: 3087c3f7c23b ("netfilter: nft_ct: Add ct id support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_ct.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index aac98a3c966e9..bfd3e5a14dab6 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -476,6 +476,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
 		break;
 #endif
 	case NFT_CT_ID:
+		if (tb[NFTA_CT_DIRECTION])
+			return -EINVAL;
+
 		len = sizeof(u32);
 		break;
 	default:
-- 
GitLab


From 7395dfacfff65e9938ac0889dafa1ab01e987d15 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 6 Feb 2024 00:11:40 +0100
Subject: [PATCH 4029/4076] netfilter: nf_tables: use timestamp to check for
 set element timeout

Add a timestamp field at the beginning of the transaction, store it
in the nftables per-netns area.

Update set backend .insert, .deactivate and sync gc path to use the
timestamp, this avoids that an element expires while control plane
transaction is still unfinished.

.lookup and .update, which are used from packet path, still use the
current time to check if the element has expired. And .get path and dump
also since this runs lockless under rcu read size lock. Then, there is
async gc which also needs to check the current time since it runs
asynchronously from a workqueue.

Fixes: c3e1b005ed1c ("netfilter: nf_tables: add set element timeout support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 16 ++++++++++++++--
 net/netfilter/nf_tables_api.c     |  4 +++-
 net/netfilter/nft_set_hash.c      |  8 +++++++-
 net/netfilter/nft_set_pipapo.c    | 18 +++++++++++-------
 net/netfilter/nft_set_rbtree.c    | 11 +++++++----
 5 files changed, 42 insertions(+), 15 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 001226c346215..510244cc0f8f0 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -808,10 +808,16 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex
 	return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS);
 }
 
-static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
+					  u64 tstamp)
 {
 	return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
-	       time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext));
+	       time_after_eq64(tstamp, *nft_set_ext_expiration(ext));
+}
+
+static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+{
+	return __nft_set_elem_expired(ext, get_jiffies_64());
 }
 
 static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
@@ -1779,6 +1785,7 @@ struct nftables_pernet {
 	struct list_head	notify_list;
 	struct mutex		commit_mutex;
 	u64			table_handle;
+	u64			tstamp;
 	unsigned int		base_seq;
 	unsigned int		gc_seq;
 	u8			validate_state;
@@ -1791,6 +1798,11 @@ static inline struct nftables_pernet *nft_pernet(const struct net *net)
 	return net_generic(net, nf_tables_net_id);
 }
 
+static inline u64 nft_net_tstamp(const struct net *net)
+{
+	return nft_pernet(net)->tstamp;
+}
+
 #define __NFT_REDUCE_READONLY	1UL
 #define NFT_REDUCE_READONLY	(void *)__NFT_REDUCE_READONLY
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fc016befb46ff..f8e3f70c35bd5 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9827,6 +9827,7 @@ dead_elem:
 struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 {
 	struct nft_set_elem_catchall *catchall, *next;
+	u64 tstamp = nft_net_tstamp(gc->net);
 	const struct nft_set *set = gc->set;
 	struct nft_elem_priv *elem_priv;
 	struct nft_set_ext *ext;
@@ -9836,7 +9837,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
 
-		if (!nft_set_elem_expired(ext))
+		if (!__nft_set_elem_expired(ext, tstamp))
 			continue;
 
 		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -10622,6 +10623,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid)
 	bool genid_ok;
 
 	mutex_lock(&nft_net->commit_mutex);
+	nft_net->tstamp = get_jiffies_64();
 
 	genid_ok = genid == 0 || nft_net->base_seq == genid;
 	if (!genid_ok)
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 6c2061bfdae6c..6968a3b342367 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -36,6 +36,7 @@ struct nft_rhash_cmp_arg {
 	const struct nft_set		*set;
 	const u32			*key;
 	u8				genmask;
+	u64				tstamp;
 };
 
 static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed)
@@ -62,7 +63,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg,
 		return 1;
 	if (nft_set_elem_is_dead(&he->ext))
 		return 1;
-	if (nft_set_elem_expired(&he->ext))
+	if (__nft_set_elem_expired(&he->ext, x->tstamp))
 		return 1;
 	if (!nft_set_elem_active(&he->ext, x->genmask))
 		return 1;
@@ -87,6 +88,7 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_cur(net),
 		.set	 = set,
 		.key	 = key,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -106,6 +108,7 @@ nft_rhash_get(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_cur(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -131,6 +134,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
 		.genmask = NFT_GENMASK_ANY,
 		.set	 = set,
 		.key	 = key,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -175,6 +179,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_next(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp	 = nft_net_tstamp(net),
 	};
 	struct nft_rhash_elem *prev;
 
@@ -216,6 +221,7 @@ nft_rhash_deactivate(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_next(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp	 = nft_net_tstamp(net),
 	};
 
 	rcu_read_lock();
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index f24ecdaa1c1ed..b17c182034166 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -504,6 +504,7 @@ out:
  * @set:	nftables API set representation
  * @data:	Key data to be matched against existing elements
  * @genmask:	If set, check that element is active in given genmask
+ * @tstamp:	timestamp to check for expired elements
  *
  * This is essentially the same as the lookup function, except that it matches
  * key data against the uncommitted copy and doesn't use preallocated maps for
@@ -513,7 +514,8 @@ out:
  */
 static struct nft_pipapo_elem *pipapo_get(const struct net *net,
 					  const struct nft_set *set,
-					  const u8 *data, u8 genmask)
+					  const u8 *data, u8 genmask,
+					  u64 tstamp)
 {
 	struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT);
 	struct nft_pipapo *priv = nft_set_priv(set);
@@ -566,7 +568,7 @@ next_match:
 			goto out;
 
 		if (last) {
-			if (nft_set_elem_expired(&f->mt[b].e->ext))
+			if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp))
 				goto next_match;
 			if ((genmask &&
 			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
@@ -606,7 +608,7 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo_elem *e;
 
 	e = pipapo_get(net, set, (const u8 *)elem->key.val.data,
-		       nft_genmask_cur(net));
+		       nft_genmask_cur(net), get_jiffies_64());
 	if (IS_ERR(e))
 		return ERR_CAST(e);
 
@@ -1173,6 +1175,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo_match *m = priv->clone;
 	u8 genmask = nft_genmask_next(net);
 	struct nft_pipapo_elem *e, *dup;
+	u64 tstamp = nft_net_tstamp(net);
 	struct nft_pipapo_field *f;
 	const u8 *start_p, *end_p;
 	int i, bsize_max, err = 0;
@@ -1182,7 +1185,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	else
 		end = start;
 
-	dup = pipapo_get(net, set, start, genmask);
+	dup = pipapo_get(net, set, start, genmask, tstamp);
 	if (!IS_ERR(dup)) {
 		/* Check if we already have the same exact entry */
 		const struct nft_data *dup_key, *dup_end;
@@ -1204,7 +1207,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 
 	if (PTR_ERR(dup) == -ENOENT) {
 		/* Look for partially overlapping entries */
-		dup = pipapo_get(net, set, end, nft_genmask_next(net));
+		dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp);
 	}
 
 	if (PTR_ERR(dup) != -ENOENT) {
@@ -1560,6 +1563,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct net *net = read_pnet(&set->net);
+	u64 tstamp = nft_net_tstamp(net);
 	int rules_f0, first_rule = 0;
 	struct nft_pipapo_elem *e;
 	struct nft_trans_gc *gc;
@@ -1594,7 +1598,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 		/* synchronous gc never fails, there is no need to set on
 		 * NFT_SET_ELEM_DEAD_BIT.
 		 */
-		if (nft_set_elem_expired(&e->ext)) {
+		if (__nft_set_elem_expired(&e->ext, tstamp)) {
 			priv->dirty = true;
 
 			gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -1769,7 +1773,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set,
 {
 	struct nft_pipapo_elem *e;
 
-	e = pipapo_get(net, set, data, nft_genmask_next(net));
+	e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net));
 	if (IS_ERR(e))
 		return NULL;
 
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index baa3fea4fe65c..5fd74f993988f 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -313,6 +313,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u8 cur_genmask = nft_genmask_cur(net);
 	u8 genmask = nft_genmask_next(net);
+	u64 tstamp = nft_net_tstamp(net);
 	int d;
 
 	/* Descend the tree to search for an existing element greater than the
@@ -360,7 +361,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		/* perform garbage collection to avoid bogus overlap reports
 		 * but skip new elements in this transaction.
 		 */
-		if (nft_set_elem_expired(&rbe->ext) &&
+		if (__nft_set_elem_expired(&rbe->ext, tstamp) &&
 		    nft_set_elem_active(&rbe->ext, cur_genmask)) {
 			const struct nft_rbtree_elem *removed_end;
 
@@ -551,6 +552,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct rb_node *parent = priv->root.rb_node;
 	u8 genmask = nft_genmask_next(net);
+	u64 tstamp = nft_net_tstamp(net);
 	int d;
 
 	while (parent != NULL) {
@@ -571,7 +573,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 				   nft_rbtree_interval_end(this)) {
 				parent = parent->rb_right;
 				continue;
-			} else if (nft_set_elem_expired(&rbe->ext)) {
+			} else if (__nft_set_elem_expired(&rbe->ext, tstamp)) {
 				break;
 			} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
 				parent = parent->rb_left;
@@ -624,9 +626,10 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
+	struct net *net = read_pnet(&set->net);
+	u64 tstamp = nft_net_tstamp(net);
 	struct rb_node *node, *next;
 	struct nft_trans_gc *gc;
-	struct net *net;
 
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
@@ -648,7 +651,7 @@ static void nft_rbtree_gc(struct nft_set *set)
 			rbe_end = rbe;
 			continue;
 		}
-		if (!nft_set_elem_expired(&rbe->ext))
+		if (!__nft_set_elem_expired(&rbe->ext, tstamp))
 			continue;
 
 		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
-- 
GitLab


From f82777e8ce6c039cdcacbcf1eb8619b99a20c06d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 6 Feb 2024 17:54:18 +0100
Subject: [PATCH 4030/4076] netfilter: nfnetlink_queue: un-break NF_REPEAT

Only override userspace verdict if the ct hook returns something
other than ACCEPT.

Else, this replaces NF_REPEAT (run all hooks again) with NF_ACCEPT
(move to next hook).

Fixes: 6291b3a67ad5 ("netfilter: conntrack: convert nf_conntrack_update to netfilter verdicts")
Reported-by: l.6diay@passmail.com
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink_queue.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 171d1f52d3dd0..5cf38fc0a366a 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -232,18 +232,25 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	if (verdict == NF_ACCEPT ||
 	    verdict == NF_REPEAT ||
 	    verdict == NF_STOP) {
+		unsigned int ct_verdict = verdict;
+
 		rcu_read_lock();
 		ct_hook = rcu_dereference(nf_ct_hook);
 		if (ct_hook)
-			verdict = ct_hook->update(entry->state.net, entry->skb);
+			ct_verdict = ct_hook->update(entry->state.net, entry->skb);
 		rcu_read_unlock();
 
-		switch (verdict & NF_VERDICT_MASK) {
+		switch (ct_verdict & NF_VERDICT_MASK) {
+		case NF_ACCEPT:
+			/* follow userspace verdict, could be REPEAT */
+			break;
 		case NF_STOLEN:
 			nf_queue_entry_free(entry);
 			return;
+		default:
+			verdict = ct_verdict & NF_VERDICT_MASK;
+			break;
 		}
-
 	}
 	nf_reinject(entry, verdict);
 }
-- 
GitLab


From 60c0c230c6f046da536d3df8b39a20b9a9fd6af0 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 7 Feb 2024 18:49:51 +0100
Subject: [PATCH 4031/4076] netfilter: nft_set_rbtree: skip end interval
 element from gc

rbtree lazy gc on insert might collect an end interval element that has
been just added in this transactions, skip end interval elements that
are not yet active.

Fixes: f718863aca46 ("netfilter: nft_set_rbtree: fix overlap expiration walk")
Cc: stable@vger.kernel.org
Reported-by: lonial con <kongln9170@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_rbtree.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 5fd74f993988f..9944fe479e536 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -234,7 +234,7 @@ static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set,
 
 static const struct nft_rbtree_elem *
 nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
-		   struct nft_rbtree_elem *rbe, u8 genmask)
+		   struct nft_rbtree_elem *rbe)
 {
 	struct nft_set *set = (struct nft_set *)__set;
 	struct rb_node *prev = rb_prev(&rbe->node);
@@ -253,7 +253,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
 	while (prev) {
 		rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
 		if (nft_rbtree_interval_end(rbe_prev) &&
-		    nft_set_elem_active(&rbe_prev->ext, genmask))
+		    nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY))
 			break;
 
 		prev = rb_prev(prev);
@@ -365,7 +365,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		    nft_set_elem_active(&rbe->ext, cur_genmask)) {
 			const struct nft_rbtree_elem *removed_end;
 
-			removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask);
+			removed_end = nft_rbtree_gc_elem(set, priv, rbe);
 			if (IS_ERR(removed_end))
 				return PTR_ERR(removed_end);
 
-- 
GitLab


From 76313d1a4aa9e30d5b43dee5efd8bcd4d8250006 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Feb 2024 21:52:46 +0100
Subject: [PATCH 4032/4076] netfilter: nft_set_pipapo: store index in scratch
 maps

Pipapo needs a scratchpad area to keep state during matching.
This state can be large and thus cannot reside on stack.

Each set preallocates percpu areas for this.

On each match stage, one scratchpad half starts with all-zero and the other
is inited to all-ones.

At the end of each stage, the half that starts with all-ones is
always zero.  Before next field is tested, pointers to the two halves
are swapped, i.e.  resmap pointer turns into fill pointer and vice versa.

After the last field has been processed, pipapo stashes the
index toggle in a percpu variable, with assumption that next packet
will start with the all-zero half and sets all bits in the other to 1.

This isn't reliable.

There can be multiple sets and we can't be sure that the upper
and lower half of all set scratch map is always in sync (lookups
can be conditional), so one set might have swapped, but other might
not have been queried.

Thus we need to keep the index per-set-and-cpu, just like the
scratchpad.

Note that this bug fix is incomplete, there is a related issue.

avx2 and normal implementation might use slightly different areas of the
map array space due to the avx2 alignment requirements, so
m->scratch (generic/fallback implementation) and ->scratch_aligned
(avx) may partially overlap. scratch and scratch_aligned are not distinct
objects, the latter is just the aligned address of the former.

After this change, write to scratch_align->map_index may write to
scratch->map, so this issue becomes more prominent, we can set to 1
a bit in the supposedly-all-zero area of scratch->map[].

A followup patch will remove the scratch_aligned and makes generic and
avx code use the same (aligned) area.

Its done in a separate change to ease review.

Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges")
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_pipapo.c      | 41 ++++++++++++++++++-----------
 net/netfilter/nft_set_pipapo.h      | 14 ++++++++--
 net/netfilter/nft_set_pipapo_avx2.c | 15 +++++------
 3 files changed, 44 insertions(+), 26 deletions(-)

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index b17c182034166..54d0bac140a3b 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -342,9 +342,6 @@
 #include "nft_set_pipapo_avx2.h"
 #include "nft_set_pipapo.h"
 
-/* Current working bitmap index, toggled between field matches */
-static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index);
-
 /**
  * pipapo_refill() - For each set bit, set bits from selected mapping table item
  * @map:	Bitmap to be scanned for set bits
@@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		       const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
+	struct nft_pipapo_scratch *scratch;
 	unsigned long *res_map, *fill_map;
 	u8 genmask = nft_genmask_cur(net);
 	const u8 *rp = (const u8 *)key;
@@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 
 	local_bh_disable();
 
-	map_index = raw_cpu_read(nft_pipapo_scratch_index);
-
 	m = rcu_dereference(priv->match);
 
 	if (unlikely(!m || !*raw_cpu_ptr(m->scratch)))
 		goto out;
 
-	res_map  = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0);
-	fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max);
+	scratch = *raw_cpu_ptr(m->scratch);
+
+	map_index = scratch->map_index;
+
+	res_map  = scratch->map + (map_index ? m->bsize_max : 0);
+	fill_map = scratch->map + (map_index ? 0 : m->bsize_max);
 
 	memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
 
@@ -460,7 +460,7 @@ next_match:
 		b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt,
 				  last);
 		if (b < 0) {
-			raw_cpu_write(nft_pipapo_scratch_index, map_index);
+			scratch->map_index = map_index;
 			local_bh_enable();
 
 			return false;
@@ -477,7 +477,7 @@ next_match:
 			 * current inactive bitmap is clean and can be reused as
 			 * *next* bitmap (not initial) for the next packet.
 			 */
-			raw_cpu_write(nft_pipapo_scratch_index, map_index);
+			scratch->map_index = map_index;
 			local_bh_enable();
 
 			return true;
@@ -1123,12 +1123,12 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 	int i;
 
 	for_each_possible_cpu(i) {
-		unsigned long *scratch;
+		struct nft_pipapo_scratch *scratch;
 #ifdef NFT_PIPAPO_ALIGN
-		unsigned long *scratch_aligned;
+		void *scratch_aligned;
 #endif
-
-		scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 +
+		scratch = kzalloc_node(struct_size(scratch, map,
+						   bsize_max * 2) +
 				       NFT_PIPAPO_ALIGN_HEADROOM,
 				       GFP_KERNEL, cpu_to_node(i));
 		if (!scratch) {
@@ -1147,7 +1147,16 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 		*per_cpu_ptr(clone->scratch, i) = scratch;
 
 #ifdef NFT_PIPAPO_ALIGN
-		scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch);
+		/* Align &scratch->map (not the struct itself): the extra
+		 * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node()
+		 * above guarantee we can waste up to those bytes in order
+		 * to align the map field regardless of its offset within
+		 * the struct.
+		 */
+		BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM);
+
+		scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map);
+		scratch_aligned -= offsetof(struct nft_pipapo_scratch, map);
 		*per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned;
 #endif
 	}
@@ -2136,7 +2145,7 @@ static int nft_pipapo_init(const struct nft_set *set,
 	m->field_count = field_count;
 	m->bsize_max = 0;
 
-	m->scratch = alloc_percpu(unsigned long *);
+	m->scratch = alloc_percpu(struct nft_pipapo_scratch *);
 	if (!m->scratch) {
 		err = -ENOMEM;
 		goto out_scratch;
@@ -2145,7 +2154,7 @@ static int nft_pipapo_init(const struct nft_set *set,
 		*per_cpu_ptr(m->scratch, i) = NULL;
 
 #ifdef NFT_PIPAPO_ALIGN
-	m->scratch_aligned = alloc_percpu(unsigned long *);
+	m->scratch_aligned = alloc_percpu(struct nft_pipapo_scratch *);
 	if (!m->scratch_aligned) {
 		err = -ENOMEM;
 		goto out_free;
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index 1040223da5fa3..d3bc1551694f3 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -130,6 +130,16 @@ struct nft_pipapo_field {
 	union nft_pipapo_map_bucket *mt;
 };
 
+/**
+ * struct nft_pipapo_scratch - percpu data used for lookup and matching
+ * @map_index:	Current working bitmap index, toggled between field matches
+ * @map:	store partial matching results during lookup
+ */
+struct nft_pipapo_scratch {
+	u8 map_index;
+	unsigned long map[];
+};
+
 /**
  * struct nft_pipapo_match - Data used for lookup and matching
  * @field_count		Amount of fields in set
@@ -142,9 +152,9 @@ struct nft_pipapo_field {
 struct nft_pipapo_match {
 	int field_count;
 #ifdef NFT_PIPAPO_ALIGN
-	unsigned long * __percpu *scratch_aligned;
+	struct nft_pipapo_scratch * __percpu *scratch_aligned;
 #endif
-	unsigned long * __percpu *scratch;
+	struct nft_pipapo_scratch * __percpu *scratch;
 	size_t bsize_max;
 	struct rcu_head rcu;
 	struct nft_pipapo_field f[] __counted_by(field_count);
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 52e0d026d30ad..78213c73af2e2 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -71,9 +71,6 @@
 #define NFT_PIPAPO_AVX2_ZERO(reg)					\
 	asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg)
 
-/* Current working bitmap index, toggled between field matches */
-static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index);
-
 /**
  * nft_pipapo_avx2_prepare() - Prepare before main algorithm body
  *
@@ -1120,11 +1117,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 			    const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
-	unsigned long *res, *fill, *scratch;
+	struct nft_pipapo_scratch *scratch;
 	u8 genmask = nft_genmask_cur(net);
 	const u8 *rp = (const u8 *)key;
 	struct nft_pipapo_match *m;
 	struct nft_pipapo_field *f;
+	unsigned long *res, *fill;
 	bool map_index;
 	int i, ret = 0;
 
@@ -1146,10 +1144,11 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 		kernel_fpu_end();
 		return false;
 	}
-	map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index);
 
-	res  = scratch + (map_index ? m->bsize_max : 0);
-	fill = scratch + (map_index ? 0 : m->bsize_max);
+	map_index = scratch->map_index;
+
+	res  = scratch->map + (map_index ? m->bsize_max : 0);
+	fill = scratch->map + (map_index ? 0 : m->bsize_max);
 
 	/* Starting map doesn't need to be set for this implementation */
 
@@ -1221,7 +1220,7 @@ next_match:
 
 out:
 	if (i % 2)
-		raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index);
+		scratch->map_index = !map_index;
 	kernel_fpu_end();
 
 	return ret >= 0;
-- 
GitLab


From 47b1c03c3c1a119435480a1e73f27197dc59131d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Feb 2024 21:52:47 +0100
Subject: [PATCH 4033/4076] netfilter: nft_set_pipapo: add helper to release
 pcpu scratch area

After next patch simple kfree() is not enough anymore, so add
a helper for it.

Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_pipapo.c | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 54d0bac140a3b..5094d4c439c3b 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1110,6 +1110,24 @@ static void pipapo_map(struct nft_pipapo_match *m,
 		f->mt[map[i].to + j].e = e;
 }
 
+/**
+ * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address
+ * @m:		Matching data
+ * @cpu:	CPU number
+ */
+static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu)
+{
+	struct nft_pipapo_scratch *s;
+	void *mem;
+
+	s = *per_cpu_ptr(m->scratch, cpu);
+	if (!s)
+		return;
+
+	mem = s;
+	kfree(mem);
+}
+
 /**
  * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results
  * @clone:	Copy of matching data with pending insertions and deletions
@@ -1142,7 +1160,7 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 			return -ENOMEM;
 		}
 
-		kfree(*per_cpu_ptr(clone->scratch, i));
+		pipapo_free_scratch(clone, i);
 
 		*per_cpu_ptr(clone->scratch, i) = scratch;
 
@@ -1369,7 +1387,7 @@ out_lt:
 	}
 out_scratch_realloc:
 	for_each_possible_cpu(i)
-		kfree(*per_cpu_ptr(new->scratch, i));
+		pipapo_free_scratch(new, i);
 #ifdef NFT_PIPAPO_ALIGN
 	free_percpu(new->scratch_aligned);
 #endif
@@ -1653,7 +1671,7 @@ static void pipapo_free_match(struct nft_pipapo_match *m)
 	int i;
 
 	for_each_possible_cpu(i)
-		kfree(*per_cpu_ptr(m->scratch, i));
+		pipapo_free_scratch(m, i);
 
 #ifdef NFT_PIPAPO_ALIGN
 	free_percpu(m->scratch_aligned);
@@ -2253,7 +2271,7 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 		free_percpu(m->scratch_aligned);
 #endif
 		for_each_possible_cpu(cpu)
-			kfree(*per_cpu_ptr(m->scratch, cpu));
+			pipapo_free_scratch(m, cpu);
 		free_percpu(m->scratch);
 		pipapo_free_fields(m);
 		kfree(m);
@@ -2270,7 +2288,7 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 		free_percpu(priv->clone->scratch_aligned);
 #endif
 		for_each_possible_cpu(cpu)
-			kfree(*per_cpu_ptr(priv->clone->scratch, cpu));
+			pipapo_free_scratch(priv->clone, cpu);
 		free_percpu(priv->clone->scratch);
 
 		pipapo_free_fields(priv->clone);
-- 
GitLab


From 5a8cdf6fd860ac5e6d08d72edbcecee049a7fec4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 8 Feb 2024 10:31:29 +0100
Subject: [PATCH 4034/4076] netfilter: nft_set_pipapo: remove scratch_aligned
 pointer

use ->scratch for both avx2 and the generic implementation.

After previous change the scratch->map member is always aligned properly
for AVX2, so we can just use scratch->map in AVX2 too.

The alignoff delta is stored in the scratchpad so we can reconstruct
the correct address to free the area again.

Fixes: 7400b063969b ("nft_set_pipapo: Introduce AVX2-based lookup implementation")
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_pipapo.c      | 41 +++++------------------------
 net/netfilter/nft_set_pipapo.h      |  6 ++---
 net/netfilter/nft_set_pipapo_avx2.c |  2 +-
 3 files changed, 10 insertions(+), 39 deletions(-)

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 5094d4c439c3b..aa1d9e93a9a04 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1125,6 +1125,7 @@ static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int c
 		return;
 
 	mem = s;
+	mem -= s->align_off;
 	kfree(mem);
 }
 
@@ -1144,6 +1145,7 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 		struct nft_pipapo_scratch *scratch;
 #ifdef NFT_PIPAPO_ALIGN
 		void *scratch_aligned;
+		u32 align_off;
 #endif
 		scratch = kzalloc_node(struct_size(scratch, map,
 						   bsize_max * 2) +
@@ -1162,8 +1164,6 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 
 		pipapo_free_scratch(clone, i);
 
-		*per_cpu_ptr(clone->scratch, i) = scratch;
-
 #ifdef NFT_PIPAPO_ALIGN
 		/* Align &scratch->map (not the struct itself): the extra
 		 * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node()
@@ -1175,8 +1175,12 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 
 		scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map);
 		scratch_aligned -= offsetof(struct nft_pipapo_scratch, map);
-		*per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned;
+		align_off = scratch_aligned - (void *)scratch;
+
+		scratch = scratch_aligned;
+		scratch->align_off = align_off;
 #endif
+		*per_cpu_ptr(clone->scratch, i) = scratch;
 	}
 
 	return 0;
@@ -1331,11 +1335,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 	if (!new->scratch)
 		goto out_scratch;
 
-#ifdef NFT_PIPAPO_ALIGN
-	new->scratch_aligned = alloc_percpu(*new->scratch_aligned);
-	if (!new->scratch_aligned)
-		goto out_scratch;
-#endif
 	for_each_possible_cpu(i)
 		*per_cpu_ptr(new->scratch, i) = NULL;
 
@@ -1388,9 +1387,6 @@ out_lt:
 out_scratch_realloc:
 	for_each_possible_cpu(i)
 		pipapo_free_scratch(new, i);
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(new->scratch_aligned);
-#endif
 out_scratch:
 	free_percpu(new->scratch);
 	kfree(new);
@@ -1673,11 +1669,7 @@ static void pipapo_free_match(struct nft_pipapo_match *m)
 	for_each_possible_cpu(i)
 		pipapo_free_scratch(m, i);
 
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(m->scratch_aligned);
-#endif
 	free_percpu(m->scratch);
-
 	pipapo_free_fields(m);
 
 	kfree(m);
@@ -2171,16 +2163,6 @@ static int nft_pipapo_init(const struct nft_set *set,
 	for_each_possible_cpu(i)
 		*per_cpu_ptr(m->scratch, i) = NULL;
 
-#ifdef NFT_PIPAPO_ALIGN
-	m->scratch_aligned = alloc_percpu(struct nft_pipapo_scratch *);
-	if (!m->scratch_aligned) {
-		err = -ENOMEM;
-		goto out_free;
-	}
-	for_each_possible_cpu(i)
-		*per_cpu_ptr(m->scratch_aligned, i) = NULL;
-#endif
-
 	rcu_head_init(&m->rcu);
 
 	nft_pipapo_for_each_field(f, i, m) {
@@ -2211,9 +2193,6 @@ static int nft_pipapo_init(const struct nft_set *set,
 	return 0;
 
 out_free:
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(m->scratch_aligned);
-#endif
 	free_percpu(m->scratch);
 out_scratch:
 	kfree(m);
@@ -2267,9 +2246,6 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 
 		nft_set_pipapo_match_destroy(ctx, set, m);
 
-#ifdef NFT_PIPAPO_ALIGN
-		free_percpu(m->scratch_aligned);
-#endif
 		for_each_possible_cpu(cpu)
 			pipapo_free_scratch(m, cpu);
 		free_percpu(m->scratch);
@@ -2284,9 +2260,6 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 		if (priv->dirty)
 			nft_set_pipapo_match_destroy(ctx, set, m);
 
-#ifdef NFT_PIPAPO_ALIGN
-		free_percpu(priv->clone->scratch_aligned);
-#endif
 		for_each_possible_cpu(cpu)
 			pipapo_free_scratch(priv->clone, cpu);
 		free_percpu(priv->clone->scratch);
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index d3bc1551694f3..f59a0cd811051 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -133,10 +133,12 @@ struct nft_pipapo_field {
 /**
  * struct nft_pipapo_scratch - percpu data used for lookup and matching
  * @map_index:	Current working bitmap index, toggled between field matches
+ * @align_off:	Offset to get the originally allocated address
  * @map:	store partial matching results during lookup
  */
 struct nft_pipapo_scratch {
 	u8 map_index;
+	u32 align_off;
 	unsigned long map[];
 };
 
@@ -144,16 +146,12 @@ struct nft_pipapo_scratch {
  * struct nft_pipapo_match - Data used for lookup and matching
  * @field_count		Amount of fields in set
  * @scratch:		Preallocated per-CPU maps for partial matching results
- * @scratch_aligned:	Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes
  * @bsize_max:		Maximum lookup table bucket size of all fields, in longs
  * @rcu			Matching data is swapped on commits
  * @f:			Fields, with lookup and mapping tables
  */
 struct nft_pipapo_match {
 	int field_count;
-#ifdef NFT_PIPAPO_ALIGN
-	struct nft_pipapo_scratch * __percpu *scratch_aligned;
-#endif
 	struct nft_pipapo_scratch * __percpu *scratch;
 	size_t bsize_max;
 	struct rcu_head rcu;
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 78213c73af2e2..90e275bb3e5d7 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1139,7 +1139,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	 */
 	kernel_fpu_begin_mask(0);
 
-	scratch = *raw_cpu_ptr(m->scratch_aligned);
+	scratch = *raw_cpu_ptr(m->scratch);
 	if (unlikely(!scratch)) {
 		kernel_fpu_end();
 		return false;
-- 
GitLab


From 8c427cc2fa73684ea140999e121b7b6c1c717632 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 24 Jan 2024 00:02:34 +0900
Subject: [PATCH 4035/4076] tracing/probes: Fix to show a parse error for bad
 type for $comm

Fix to show a parse error for bad type (non-string) for $comm/$COMM and
immediate-string. With this fix, error_log file shows appropriate error
message as below.

 /sys/kernel/tracing # echo 'p vfs_read $comm:u32' >> kprobe_events
sh: write error: Invalid argument
 /sys/kernel/tracing # echo 'p vfs_read \"hoge":u32' >> kprobe_events
sh: write error: Invalid argument
 /sys/kernel/tracing # cat error_log

[   30.144183] trace_kprobe: error: $comm and immediate-string only accepts string type
  Command: p vfs_read $comm:u32
                            ^
[   62.618500] trace_kprobe: error: $comm and immediate-string only accepts string type
  Command: p vfs_read \"hoge":u32
                              ^
Link: https://lore.kernel.org/all/170602215411.215583.2238016352271091852.stgit@devnote2/

Fixes: 3dd1f7f24f8c ("tracing: probeevent: Fix to make the type of $comm string")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/trace_probe.c | 7 +++++--
 kernel/trace/trace_probe.h | 3 ++-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 4dc74d73fc1df..c6da5923e5b9f 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1159,9 +1159,12 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 	if (!(ctx->flags & TPARG_FL_TEVENT) &&
 	    (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
 	     strncmp(arg, "\\\"", 2) == 0)) {
-		/* The type of $comm must be "string", and not an array. */
-		if (parg->count || (t && strcmp(t, "string")))
+		/* The type of $comm must be "string", and not an array type. */
+		if (parg->count || (t && strcmp(t, "string"))) {
+			trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0),
+					NEED_STRING_TYPE);
 			goto out;
+		}
 		parg->type = find_fetch_type("string", ctx->flags);
 	} else
 		parg->type = find_fetch_type(t, ctx->flags);
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 850d9ecb6765a..c1877d0182691 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -515,7 +515,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(BAD_HYPHEN,		"Failed to parse single hyphen. Forgot '>'?"),	\
 	C(NO_BTF_FIELD,		"This field is not found."),	\
 	C(BAD_BTF_TID,		"Failed to get BTF type info."),\
-	C(BAD_TYPE4STR,		"This type does not fit for string."),
+	C(BAD_TYPE4STR,		"This type does not fit for string."),\
+	C(NEED_STRING_TYPE,	"$comm and immediate-string only accepts string type"),
 
 #undef C
 #define C(a, b)		TP_ERR_##a
-- 
GitLab


From 9a571c1e275cedacd48c66a6bddd0c23f1dffdbf Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 24 Jan 2024 00:03:02 +0900
Subject: [PATCH 4036/4076] tracing/probes: Fix to set arg size and fmt after
 setting type from BTF

Since the BTF type setting updates probe_arg::type, the type size
calculation and setting print-fmt should be done after that.
Without this fix, the argument size and print-fmt can be wrong.

Link: https://lore.kernel.org/all/170602218196.215583.6417859469540955777.stgit@devnote2/

Fixes: b576e09701c7 ("tracing/probes: Support function parameters if BTF is available")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/trace_probe.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index c6da5923e5b9f..34289f9c67076 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1172,18 +1172,6 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 		trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE);
 		goto out;
 	}
-	parg->offset = *size;
-	*size += parg->type->size * (parg->count ?: 1);
-
-	ret = -ENOMEM;
-	if (parg->count) {
-		len = strlen(parg->type->fmttype) + 6;
-		parg->fmt = kmalloc(len, GFP_KERNEL);
-		if (!parg->fmt)
-			goto out;
-		snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
-			 parg->count);
-	}
 
 	code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL);
 	if (!code)
@@ -1207,6 +1195,19 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 				goto fail;
 		}
 	}
+	parg->offset = *size;
+	*size += parg->type->size * (parg->count ?: 1);
+
+	if (parg->count) {
+		len = strlen(parg->type->fmttype) + 6;
+		parg->fmt = kmalloc(len, GFP_KERNEL);
+		if (!parg->fmt) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
+			 parg->count);
+	}
 
 	ret = -EINVAL;
 	/* Store operation */
-- 
GitLab


From 9efd24ec5599ed485b7c4d9aeb731141f6285167 Mon Sep 17 00:00:00 2001
From: Li zeming <zeming@nfschina.com>
Date: Tue, 19 Sep 2023 09:28:23 +0800
Subject: [PATCH 4037/4076] kprobes: Remove unnecessary initial values of
 variables

ri and sym is assigned first, so it does not need to initialize the
assignment.

Link: https://lore.kernel.org/all/20230919012823.7815-1-zeming@nfschina.com/

Signed-off-by: Li zeming <zeming@nfschina.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/kprobes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d5a0ee40bf66c..9d9095e817928 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1993,7 +1993,7 @@ NOKPROBE_SYMBOL(__kretprobe_find_ret_addr);
 unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp,
 				      struct llist_node **cur)
 {
-	struct kretprobe_instance *ri = NULL;
+	struct kretprobe_instance *ri;
 	kprobe_opcode_t *ret;
 
 	if (WARN_ON_ONCE(!cur))
@@ -2802,7 +2802,7 @@ static int show_kprobe_addr(struct seq_file *pi, void *v)
 {
 	struct hlist_head *head;
 	struct kprobe *p, *kp;
-	const char *sym = NULL;
+	const char *sym;
 	unsigned int i = *(loff_t *) v;
 	unsigned long offset = 0;
 	char *modname, namebuf[KSYM_NAME_LEN];
-- 
GitLab


From 45be0882c5f91e1b92e645001dd1a53b3bd58c97 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Mon, 5 Feb 2024 14:43:17 -0600
Subject: [PATCH 4038/4076] smb3: add missing null server pointer check

Address static checker warning in cifs_ses_get_chan_index():
    warn: variable dereferenced before check 'server'
To be consistent, and reduce risk, we should add another check
for null server pointer.

Fixes: 88675b22d34e ("cifs: do not search for channel if server is terminating")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/sess.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index ed4bd88dd528a..476d54fceb50f 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -76,7 +76,7 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
 	unsigned int i;
 
 	/* if the channel is waiting for termination */
-	if (server->terminate)
+	if (server && server->terminate)
 		return CIFS_INVAL_CHAN_INDEX;
 
 	for (i = 0; i < ses->chan_count; i++) {
-- 
GitLab


From 55c7788c37242702868bfac7861cdf0c358d6c3d Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Fri, 2 Feb 2024 12:38:24 -0300
Subject: [PATCH 4039/4076] smb: client: set correct d_type for reparse points
 under DFS mounts

Send query dir requests with an info level of
SMB_FIND_FILE_FULL_DIRECTORY_INFO rather than
SMB_FIND_FILE_DIRECTORY_INFO when the client is generating its own
inode numbers (e.g. noserverino) so that reparse tags still
can be parsed directly from the responses, but server won't
send UniqueId (server inode number)

Signed-off-by: Paulo Alcantara <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/readdir.c | 15 ++++++++-------
 fs/smb/client/smb2pdu.c |  6 ++++++
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 3b1b01d10f7d7..b520eea7bfce8 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -307,14 +307,16 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info,
 }
 
 static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr,
-				       SEARCH_ID_FULL_DIR_INFO *info,
+				       const void *info,
 				       struct cifs_sb_info *cifs_sb)
 {
+	const FILE_FULL_DIRECTORY_INFO *di = info;
+
 	__dir_info_to_fattr(fattr, info);
 
-	/* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */
+	/* See MS-FSCC 2.4.14, 2.4.19 */
 	if (fattr->cf_cifsattrs & ATTR_REPARSE)
-		fattr->cf_cifstag = le32_to_cpu(info->EaSize);
+		fattr->cf_cifstag = le32_to_cpu(di->EaSize);
 	cifs_fill_common_info(fattr, cifs_sb);
 }
 
@@ -396,7 +398,7 @@ ffirst_retry:
 	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
 	} else /* not srvinos - BB fixme add check for backlevel? */ {
-		cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO;
+		cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO;
 	}
 
 	search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME;
@@ -987,10 +989,9 @@ static int cifs_filldir(char *find_entry, struct file *file,
 				       (FIND_FILE_STANDARD_INFO *)find_entry,
 				       cifs_sb);
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
 	case SMB_FIND_FILE_ID_FULL_DIR_INFO:
-		cifs_fulldir_info_to_fattr(&fattr,
-					   (SEARCH_ID_FULL_DIR_INFO *)find_entry,
-					   cifs_sb);
+		cifs_fulldir_info_to_fattr(&fattr, find_entry, cifs_sb);
 		break;
 	default:
 		cifs_dir_info_to_fattr(&fattr,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index c58fa44dd6b06..4085ce27fd388 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -5206,6 +5206,9 @@ int SMB2_query_directory_init(const unsigned int xid,
 	case SMB_FIND_FILE_POSIX_INFO:
 		req->FileInformationClass = SMB_FIND_FILE_POSIX_INFO;
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
+		req->FileInformationClass = FILE_FULL_DIRECTORY_INFORMATION;
+		break;
 	default:
 		cifs_tcon_dbg(VFS, "info level %u isn't supported\n",
 			info_level);
@@ -5275,6 +5278,9 @@ smb2_parse_query_directory(struct cifs_tcon *tcon,
 		/* note that posix payload are variable size */
 		info_buf_size = sizeof(struct smb2_posix_info);
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
+		info_buf_size = sizeof(FILE_FULL_DIRECTORY_INFO);
+		break;
 	default:
 		cifs_tcon_dbg(VFS, "info level %u isn't supported\n",
 			 srch_inf->info_level);
-- 
GitLab


From 2a427b49d02995ea4a6ff93a1432c40fa4d36821 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 20 Nov 2023 12:25:56 -1000
Subject: [PATCH 4040/4076] blk-iocost: Fix an UBSAN shift-out-of-bounds
 warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When iocg_kick_delay() is called from a CPU different than the one which set
the delay, @now may be in the past of @iocg->delay_at leading to the
following warning:

  UBSAN: shift-out-of-bounds in block/blk-iocost.c:1359:23
  shift exponent 18446744073709 is too large for 64-bit type 'u64' (aka 'unsigned long long')
  ...
  Call Trace:
   <TASK>
   dump_stack_lvl+0x79/0xc0
   __ubsan_handle_shift_out_of_bounds+0x2ab/0x300
   iocg_kick_delay+0x222/0x230
   ioc_rqos_merge+0x1d7/0x2c0
   __rq_qos_merge+0x2c/0x80
   bio_attempt_back_merge+0x83/0x190
   blk_attempt_plug_merge+0x101/0x150
   blk_mq_submit_bio+0x2b1/0x720
   submit_bio_noacct_nocheck+0x320/0x3e0
   __swap_writepage+0x2ab/0x9d0

The underflow itself doesn't really affect the behavior in any meaningful
way; however, the past timestamp may exaggerate the delay amount calculated
later in the code, which shouldn't be a material problem given the nature of
the delay mechanism.

If @now is in the past, this CPU is racing another CPU which recently set up
the delay and there's nothing this CPU can contribute w.r.t. the delay.
Let's bail early from iocg_kick_delay() in such cases.

Reported-by: Breno Leitão <leitao@debian.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 5160a5a53c0c ("blk-iocost: implement delay adjustment hysteresis")
Link: https://lore.kernel.org/r/ZVvc9L_CYk5LO1fT@slm.duckdns.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iocost.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index c8beec6d7df08..04d44f0bcbc85 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1353,6 +1353,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
 
 	lockdep_assert_held(&iocg->waitq.lock);
 
+	/*
+	 * If the delay is set by another CPU, we may be in the past. No need to
+	 * change anything if so. This avoids decay calculation underflow.
+	 */
+	if (time_before64(now->now, iocg->delay_at))
+		return false;
+
 	/* calculate the current delay in effect - 1/2 every second */
 	tdelta = now->now - iocg->delay_at;
 	if (iocg->delay)
-- 
GitLab


From c23de7ceae59e4ca5894c3ecf4f785c50c0fa428 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Mon, 5 Feb 2024 18:51:26 +0100
Subject: [PATCH 4041/4076] docs: kernel_feat.py: fix build error for missing
 files

If the directory passed to the '.. kernel-feat::' directive does not
exist or the get_feat.pl script does not find any files to extract
features from, Sphinx will report the following error:

    Sphinx parallel build error:
    UnboundLocalError: local variable 'fname' referenced before assignment
    make[2]: *** [Documentation/Makefile:102: htmldocs] Error 2

This is due to how I changed the script in c48a7c44a1d0 ("docs:
kernel_feat.py: fix potential command injection"). Before that, the
filename passed along to self.nestedParse() in this case was weirdly
just the whole get_feat.pl invocation.

We can fix it by doing what kernel_abi.py does -- just pass
self.arguments[0] as 'fname'.

Fixes: c48a7c44a1d0 ("docs: kernel_feat.py: fix potential command injection")
Cc: Justin Forbes <jforbes@fedoraproject.org>
Cc: Salvatore Bonaccorso <carnil@debian.org>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Link: https://lore.kernel.org/r/20240205175133.774271-2-vegard.nossum@oracle.com
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/sphinx/kernel_feat.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py
index b9df61eb45013..03ace5f01b5c0 100644
--- a/Documentation/sphinx/kernel_feat.py
+++ b/Documentation/sphinx/kernel_feat.py
@@ -109,7 +109,7 @@ class KernelFeat(Directive):
             else:
                 out_lines += line + "\n"
 
-        nodeList = self.nestedParse(out_lines, fname)
+        nodeList = self.nestedParse(out_lines, self.arguments[0])
         return nodeList
 
     def nestedParse(self, lines, fname):
-- 
GitLab


From 4ce6e2db00de8103a0687fb0f65fd17124a51aaa Mon Sep 17 00:00:00 2001
From: Yi Sun <yi.sun@unisoc.com>
Date: Mon, 29 Jan 2024 16:52:50 +0800
Subject: [PATCH 4042/4076] virtio-blk: Ensure no requests in virtqueues before
 deleting vqs.

Ensure no remaining requests in virtqueues before resetting vdev and
deleting virtqueues. Otherwise these requests will never be completed.
It may cause the system to become unresponsive.

Function blk_mq_quiesce_queue() can ensure that requests have become
in_flight status, but it cannot guarantee that requests have been
processed by the device. Virtqueues should never be deleted before
all requests become complete status.

Function blk_mq_freeze_queue() ensure that all requests in virtqueues
become complete status. And no requests can enter in virtqueues.

Signed-off-by: Yi Sun <yi.sun@unisoc.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://lore.kernel.org/r/20240129085250.1550594-1-yi.sun@unisoc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/virtio_blk.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 5bf98fd6a651a..2bf14a0e2815f 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -1593,14 +1593,15 @@ static int virtblk_freeze(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 
+	/* Ensure no requests in virtqueues before deleting vqs. */
+	blk_mq_freeze_queue(vblk->disk->queue);
+
 	/* Ensure we don't receive any more interrupts */
 	virtio_reset_device(vdev);
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);
 
-	blk_mq_quiesce_queue(vblk->disk->queue);
-
 	vdev->config->del_vqs(vdev);
 	kfree(vblk->vqs);
 
@@ -1618,7 +1619,7 @@ static int virtblk_restore(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	blk_mq_unquiesce_queue(vblk->disk->queue);
+	blk_mq_unfreeze_queue(vblk->disk->queue);
 	return 0;
 }
 #endif
-- 
GitLab


From a8b9cf62ade1bf17261a979fc97e40c2d7842353 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 10 Jan 2024 09:13:06 +0900
Subject: [PATCH 4043/4076] ftrace: Fix DIRECT_CALLS to use SAVE_REGS by
 default

The commit 60c8971899f3 ("ftrace: Make DIRECT_CALLS work WITH_ARGS
and !WITH_REGS") changed DIRECT_CALLS to use SAVE_ARGS when there
are multiple ftrace_ops at the same function, but since the x86 only
support to jump to direct_call from ftrace_regs_caller, when we set
the function tracer on the same target function on x86, ftrace-direct
does not work as below (this actually works on arm64.)

At first, insmod ftrace-direct.ko to put a direct_call on
'wake_up_process()'.

 # insmod kernel/samples/ftrace/ftrace-direct.ko
 # less trace
...
          <idle>-0       [006] ..s1.   564.686958: my_direct_func: waking up rcu_preempt-17
          <idle>-0       [007] ..s1.   564.687836: my_direct_func: waking up kcompactd0-63
          <idle>-0       [006] ..s1.   564.690926: my_direct_func: waking up rcu_preempt-17
          <idle>-0       [006] ..s1.   564.696872: my_direct_func: waking up rcu_preempt-17
          <idle>-0       [007] ..s1.   565.191982: my_direct_func: waking up kcompactd0-63

Setup a function filter to the 'wake_up_process' too, and enable it.

 # cd /sys/kernel/tracing/
 # echo wake_up_process > set_ftrace_filter
 # echo function > current_tracer
 # less trace
...
          <idle>-0       [006] ..s3.   686.180972: wake_up_process <-call_timer_fn
          <idle>-0       [006] ..s3.   686.186919: wake_up_process <-call_timer_fn
          <idle>-0       [002] ..s3.   686.264049: wake_up_process <-call_timer_fn
          <idle>-0       [002] d.h6.   686.515216: wake_up_process <-kick_pool
          <idle>-0       [002] d.h6.   686.691386: wake_up_process <-kick_pool

Then, only function tracer is shown on x86.
But if you enable 'kprobe on ftrace' event (which uses SAVE_REGS flag)
on the same function, it is shown again.

 # echo 'p wake_up_process' >> dynamic_events
 # echo 1 > events/kprobes/p_wake_up_process_0/enable
 # echo > trace
 # less trace
...
          <idle>-0       [006] ..s2.  2710.345919: p_wake_up_process_0: (wake_up_process+0x4/0x20)
          <idle>-0       [006] ..s3.  2710.345923: wake_up_process <-call_timer_fn
          <idle>-0       [006] ..s1.  2710.345928: my_direct_func: waking up rcu_preempt-17
          <idle>-0       [006] ..s2.  2710.349931: p_wake_up_process_0: (wake_up_process+0x4/0x20)
          <idle>-0       [006] ..s3.  2710.349934: wake_up_process <-call_timer_fn
          <idle>-0       [006] ..s1.  2710.349937: my_direct_func: waking up rcu_preempt-17

To fix this issue, use SAVE_REGS flag for multiple ftrace_ops flag of
direct_call by default.

Link: https://lore.kernel.org/linux-trace-kernel/170484558617.178953.1590516949390270842.stgit@devnote2

Fixes: 60c8971899f3 ("ftrace: Make DIRECT_CALLS work WITH_ARGS and !WITH_REGS")
Cc: stable@vger.kernel.org
Cc: Florent Revest <revest@chromium.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com> [arm64]
Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b01ae7d360218..c060d5b479102 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5325,7 +5325,17 @@ static LIST_HEAD(ftrace_direct_funcs);
 
 static int register_ftrace_function_nolock(struct ftrace_ops *ops);
 
+/*
+ * If there are multiple ftrace_ops, use SAVE_REGS by default, so that direct
+ * call will be jumped from ftrace_regs_caller. Only if the architecture does
+ * not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it
+ * jumps from ftrace_caller for multiple ftrace_ops.
+ */
+#ifndef HAVE_DYNAMIC_FTRACE_WITH_REGS
 #define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS)
+#else
+#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS)
+#endif
 
 static int check_direct_multi(struct ftrace_ops *ops)
 {
-- 
GitLab


From 44dc5c41b5b1267d4dd037d26afc0c4d3a568acb Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Fri, 9 Feb 2024 06:36:22 -0500
Subject: [PATCH 4044/4076] tracing: Fix wasted memory in saved_cmdlines logic

While looking at improving the saved_cmdlines cache I found a huge amount
of wasted memory that should be used for the cmdlines.

The tracing data saves pids during the trace. At sched switch, if a trace
occurred, it will save the comm of the task that did the trace. This is
saved in a "cache" that maps pids to comms and exposed to user space via
the /sys/kernel/tracing/saved_cmdlines file. Currently it only caches by
default 128 comms.

The structure that uses this creates an array to store the pids using
PID_MAX_DEFAULT (which is usually set to 32768). This causes the structure
to be of the size of 131104 bytes on 64 bit machines.

In hex: 131104 = 0x20020, and since the kernel allocates generic memory in
powers of two, the kernel would allocate 0x40000 or 262144 bytes to store
this structure. That leaves 131040 bytes of wasted space.

Worse, the structure points to an allocated array to store the comm names,
which is 16 bytes times the amount of names to save (currently 128), which
is 2048 bytes. Instead of allocating a separate array, make the structure
end with a variable length string and use the extra space for that.

This is similar to a recommendation that Linus had made about eventfs_inode names:

  https://lore.kernel.org/all/20240130190355.11486-5-torvalds@linux-foundation.org/

Instead of allocating a separate string array to hold the saved comms,
have the structure end with: char saved_cmdlines[]; and round up to the
next power of two over sizeof(struct saved_cmdline_buffers) + num_cmdlines * TASK_COMM_LEN
It will use this extra space for the saved_cmdline portion.

Now, instead of saving only 128 comms by default, by using this wasted
space at the end of the structure it can save over 8000 comms and even
saves space by removing the need for allocating the other array.

Link: https://lore.kernel.org/linux-trace-kernel/20240209063622.1f7b6d5f@rorschach.local.home

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Mete Durlu <meted@linux.ibm.com>
Fixes: 939c7a4f04fcd ("tracing: Introduce saved_cmdlines_size file")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 75 ++++++++++++++++++++++----------------------
 1 file changed, 37 insertions(+), 38 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2a7c6fd934e9c..9ff8a439d6746 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2320,7 +2320,7 @@ struct saved_cmdlines_buffer {
 	unsigned *map_cmdline_to_pid;
 	unsigned cmdline_num;
 	int cmdline_idx;
-	char *saved_cmdlines;
+	char saved_cmdlines[];
 };
 static struct saved_cmdlines_buffer *savedcmd;
 
@@ -2334,47 +2334,58 @@ static inline void set_cmdline(int idx, const char *cmdline)
 	strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
 }
 
-static int allocate_cmdlines_buffer(unsigned int val,
-				    struct saved_cmdlines_buffer *s)
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
+{
+	int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
+
+	kfree(s->map_cmdline_to_pid);
+	free_pages((unsigned long)s, order);
+}
+
+static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
 {
+	struct saved_cmdlines_buffer *s;
+	struct page *page;
+	int orig_size, size;
+	int order;
+
+	/* Figure out how much is needed to hold the given number of cmdlines */
+	orig_size = sizeof(*s) + val * TASK_COMM_LEN;
+	order = get_order(orig_size);
+	size = 1 << (order + PAGE_SHIFT);
+	page = alloc_pages(GFP_KERNEL, order);
+	if (!page)
+		return NULL;
+
+	s = page_address(page);
+	memset(s, 0, sizeof(*s));
+
+	/* Round up to actual allocation */
+	val = (size - sizeof(*s)) / TASK_COMM_LEN;
+	s->cmdline_num = val;
+
 	s->map_cmdline_to_pid = kmalloc_array(val,
 					      sizeof(*s->map_cmdline_to_pid),
 					      GFP_KERNEL);
-	if (!s->map_cmdline_to_pid)
-		return -ENOMEM;
-
-	s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
-	if (!s->saved_cmdlines) {
-		kfree(s->map_cmdline_to_pid);
-		return -ENOMEM;
+	if (!s->map_cmdline_to_pid) {
+		free_saved_cmdlines_buffer(s);
+		return NULL;
 	}
 
 	s->cmdline_idx = 0;
-	s->cmdline_num = val;
 	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
 	       sizeof(s->map_pid_to_cmdline));
 	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
 	       val * sizeof(*s->map_cmdline_to_pid));
 
-	return 0;
+	return s;
 }
 
 static int trace_create_savedcmd(void)
 {
-	int ret;
-
-	savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
-	if (!savedcmd)
-		return -ENOMEM;
-
-	ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
-	if (ret < 0) {
-		kfree(savedcmd);
-		savedcmd = NULL;
-		return -ENOMEM;
-	}
+	savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT);
 
-	return 0;
+	return savedcmd ? 0 : -ENOMEM;
 }
 
 int is_tracing_stopped(void)
@@ -6056,26 +6067,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
-static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
-{
-	kfree(s->saved_cmdlines);
-	kfree(s->map_cmdline_to_pid);
-	kfree(s);
-}
-
 static int tracing_resize_saved_cmdlines(unsigned int val)
 {
 	struct saved_cmdlines_buffer *s, *savedcmd_temp;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = allocate_cmdlines_buffer(val);
 	if (!s)
 		return -ENOMEM;
 
-	if (allocate_cmdlines_buffer(val, s) < 0) {
-		kfree(s);
-		return -ENOMEM;
-	}
-
 	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	savedcmd_temp = savedcmd;
-- 
GitLab


From f6a1892585cd19e63c4ef2334e26cd536d5b678d Mon Sep 17 00:00:00 2001
From: Aleksander Mazur <deweloper@wp.pl>
Date: Tue, 23 Jan 2024 14:43:00 +0100
Subject: [PATCH 4045/4076] x86/Kconfig: Transmeta Crusoe is CPU family 5, not
 6

The kernel built with MCRUSOE is unbootable on Transmeta Crusoe.  It shows
the following error message:

  This kernel requires an i686 CPU, but only detected an i586 CPU.
  Unable to boot - please use a kernel appropriate for your CPU.

Remove MCRUSOE from the condition introduced in commit in Fixes, effectively
changing X86_MINIMUM_CPU_FAMILY back to 5 on that machine, which matches the
CPU family given by CPUID.

  [ bp: Massage commit message. ]

Fixes: 25d76ac88821 ("x86/Kconfig: Explicitly enumerate i686-class CPUs in Kconfig")
Signed-off-by: Aleksander Mazur <deweloper@wp.pl>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20240123134309.1117782-1-deweloper@wp.pl
---
 arch/x86/Kconfig.cpu | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b9224cf2ee4d6..2a7279d80460a 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -379,7 +379,7 @@ config X86_CMOV
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
 	default "5" if X86_32 && X86_CMPXCHG64
 	default "4"
 
-- 
GitLab


From 5571e41ec6e56e35f34ae9f5b3a335ef510e0ade Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 31 Jan 2024 14:27:25 -0500
Subject: [PATCH 4046/4076] btrfs: don't drop extent_map for free space inode
 on write error

While running the CI for an unrelated change I hit the following panic
with generic/648 on btrfs_holes_spacecache.

assertion failed: block_start != EXTENT_MAP_HOLE, in fs/btrfs/extent_io.c:1385
------------[ cut here ]------------
kernel BUG at fs/btrfs/extent_io.c:1385!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 1 PID: 2695096 Comm: fsstress Kdump: loaded Tainted: G        W          6.8.0-rc2+ #1
RIP: 0010:__extent_writepage_io.constprop.0+0x4c1/0x5c0
Call Trace:
 <TASK>
 extent_write_cache_pages+0x2ac/0x8f0
 extent_writepages+0x87/0x110
 do_writepages+0xd5/0x1f0
 filemap_fdatawrite_wbc+0x63/0x90
 __filemap_fdatawrite_range+0x5c/0x80
 btrfs_fdatawrite_range+0x1f/0x50
 btrfs_write_out_cache+0x507/0x560
 btrfs_write_dirty_block_groups+0x32a/0x420
 commit_cowonly_roots+0x21b/0x290
 btrfs_commit_transaction+0x813/0x1360
 btrfs_sync_file+0x51a/0x640
 __x64_sys_fdatasync+0x52/0x90
 do_syscall_64+0x9c/0x190
 entry_SYSCALL_64_after_hwframe+0x6e/0x76

This happens because we fail to write out the free space cache in one
instance, come back around and attempt to write it again.  However on
the second pass through we go to call btrfs_get_extent() on the inode to
get the extent mapping.  Because this is a new block group, and with the
free space inode we always search the commit root to avoid deadlocking
with the tree, we find nothing and return a EXTENT_MAP_HOLE for the
requested range.

This happens because the first time we try to write the space cache out
we hit an error, and on an error we drop the extent mapping.  This is
normal for normal files, but the free space cache inode is special.  We
always expect the extent map to be correct.  Thus the second time
through we end up with a bogus extent map.

Since we're deprecating this feature, the most straightforward way to
fix this is to simply skip dropping the extent map range for this failed
range.

I shortened the test by using error injection to stress the area to make
it easier to reproduce.  With this patch in place we no longer panic
with my error injection test.

CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7bcc1c03437a8..d232eca1bbee2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3184,8 +3184,23 @@ out:
 			unwritten_start += logical_len;
 		clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
 
-		/* Drop extent maps for the part of the extent we didn't write. */
-		btrfs_drop_extent_map_range(inode, unwritten_start, end, false);
+		/*
+		 * Drop extent maps for the part of the extent we didn't write.
+		 *
+		 * We have an exception here for the free_space_inode, this is
+		 * because when we do btrfs_get_extent() on the free space inode
+		 * we will search the commit root.  If this is a new block group
+		 * we won't find anything, and we will trip over the assert in
+		 * writepage where we do ASSERT(em->block_start !=
+		 * EXTENT_MAP_HOLE).
+		 *
+		 * Theoretically we could also skip this for any NOCOW extent as
+		 * we don't mess with the extent map tree in the NOCOW case, but
+		 * for now simply skip this if we are the free space inode.
+		 */
+		if (!btrfs_is_free_space_inode(inode))
+			btrfs_drop_extent_map_range(inode, unwritten_start,
+						    end, false);
 
 		/*
 		 * If the ordered extent had an IOERR or something else went
-- 
GitLab


From 1693d5442c458ae8d5b0d58463b873cd879569ed Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 25 Jan 2024 09:53:06 +0000
Subject: [PATCH 4047/4076] btrfs: add and use helper to check if block group
 is used

Add a helper function to determine if a block group is being used and make
use of it at btrfs_delete_unused_bgs(). This helper will also be used in
future code changes.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.c | 3 +--
 fs/btrfs/block-group.h | 7 +++++++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index a9be9ac992222..9daef18bcbbc0 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1512,8 +1512,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		}
 
 		spin_lock(&block_group->lock);
-		if (block_group->reserved || block_group->pinned ||
-		    block_group->used || block_group->ro ||
+		if (btrfs_is_block_group_used(block_group) || block_group->ro ||
 		    list_is_singular(&block_group->list)) {
 			/*
 			 * We want to bail if we made new allocations or have
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index c4a1f01cc1c24..962b11983901a 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -257,6 +257,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
 	return (block_group->start + block_group->length);
 }
 
+static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg)
+{
+	lockdep_assert_held(&bg->lock);
+
+	return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0);
+}
+
 static inline bool btrfs_is_block_group_data_only(
 					struct btrfs_block_group *block_group)
 {
-- 
GitLab


From f4a9f219411f318ae60d6ff7f129082a75686c6c Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 25 Jan 2024 09:53:14 +0000
Subject: [PATCH 4048/4076] btrfs: do not delete unused block group if it may
 be used soon

Before deleting a block group that is in the list of unused block groups
(fs_info->unused_bgs), we check if the block group became used before
deleting it, as extents from it may have been allocated after it was added
to the list.

However even if the block group was not yet used, there may be tasks that
have only reserved space and have not yet allocated extents, and they
might be relying on the availability of the unused block group in order
to allocate extents. The reservation works first by increasing the
"bytes_may_use" field of the corresponding space_info object (which may
first require flushing delayed items, allocating a new block group, etc),
and only later a task does the actual allocation of extents.

For metadata we usually don't end up using all reserved space, as we are
pessimistic and typically account for the worst cases (need to COW every
single node in a path of a tree at maximum possible height, etc). For
data we usually reserve the exact amount of space we're going to allocate
later, except when using compression where we always reserve space based
on the uncompressed size, as compression is only triggered when writeback
starts so we don't know in advance how much space we'll actually need, or
if the data is compressible.

So don't delete an unused block group if the total size of its space_info
object minus the block group's size is less then the sum of used space and
space that may be used (space_info->bytes_may_use), as that means we have
tasks that reserved space and may need to allocate extents from the block
group. In this case, besides skipping the deletion, re-add the block group
to the list of unused block groups so that it may be reconsidered later,
in case the tasks that reserved space end up not needing to allocate
extents from it.

Allowing the deletion of the block group while we have reserved space, can
result in tasks failing to allocate metadata extents (-ENOSPC) while under
a transaction handle, resulting in a transaction abort, or failure during
writeback for the case of data extents.

CC: stable@vger.kernel.org # 6.0+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.c | 46 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 9daef18bcbbc0..5fe37bc82f117 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1455,6 +1455,7 @@ out:
  */
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 {
+	LIST_HEAD(retry_list);
 	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
@@ -1476,6 +1477,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 
 	spin_lock(&fs_info->unused_bgs_lock);
 	while (!list_empty(&fs_info->unused_bgs)) {
+		u64 used;
 		int trimming;
 
 		block_group = list_first_entry(&fs_info->unused_bgs,
@@ -1511,6 +1513,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			goto next;
 		}
 
+		spin_lock(&space_info->lock);
 		spin_lock(&block_group->lock);
 		if (btrfs_is_block_group_used(block_group) || block_group->ro ||
 		    list_is_singular(&block_group->list)) {
@@ -1522,10 +1525,49 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			 */
 			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
+			spin_unlock(&space_info->lock);
+			up_write(&space_info->groups_sem);
+			goto next;
+		}
+
+		/*
+		 * The block group may be unused but there may be space reserved
+		 * accounting with the existence of that block group, that is,
+		 * space_info->bytes_may_use was incremented by a task but no
+		 * space was yet allocated from the block group by the task.
+		 * That space may or may not be allocated, as we are generally
+		 * pessimistic about space reservation for metadata as well as
+		 * for data when using compression (as we reserve space based on
+		 * the worst case, when data can't be compressed, and before
+		 * actually attempting compression, before starting writeback).
+		 *
+		 * So check if the total space of the space_info minus the size
+		 * of this block group is less than the used space of the
+		 * space_info - if that's the case, then it means we have tasks
+		 * that might be relying on the block group in order to allocate
+		 * extents, and add back the block group to the unused list when
+		 * we finish, so that we retry later in case no tasks ended up
+		 * needing to allocate extents from the block group.
+		 */
+		used = btrfs_space_info_used(space_info, true);
+		if (space_info->total_bytes - block_group->length < used) {
+			/*
+			 * Add a reference for the list, compensate for the ref
+			 * drop under the "next" label for the
+			 * fs_info->unused_bgs list.
+			 */
+			btrfs_get_block_group(block_group);
+			list_add_tail(&block_group->bg_list, &retry_list);
+
+			trace_btrfs_skip_unused_block_group(block_group);
+			spin_unlock(&block_group->lock);
+			spin_unlock(&space_info->lock);
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
+
 		spin_unlock(&block_group->lock);
+		spin_unlock(&space_info->lock);
 
 		/* We don't want to force the issue, only flip if it's ok. */
 		ret = inc_block_group_ro(block_group, 0);
@@ -1649,12 +1691,16 @@ next:
 		btrfs_put_block_group(block_group);
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
+	list_splice_tail(&retry_list, &fs_info->unused_bgs);
 	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 	return;
 
 flip_async:
 	btrfs_end_transaction(trans);
+	spin_lock(&fs_info->unused_bgs_lock);
+	list_splice_tail(&retry_list, &fs_info->unused_bgs);
+	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 	btrfs_put_block_group(block_group);
 	btrfs_discard_punt_unused_bgs_list(fs_info);
-- 
GitLab


From 12c5128f101bfa47a08e4c0e1a75cfa2d0872bcd Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 25 Jan 2024 09:53:19 +0000
Subject: [PATCH 4049/4076] btrfs: add new unused block groups to the list of
 unused block groups

Space reservations for metadata are, most of the time, pessimistic as we
reserve space for worst possible cases - where tree heights are at the
maximum possible height (8), we need to COW every extent buffer in a tree
path, need to split extent buffers, etc.

For data, we generally reserve the exact amount of space we are going to
allocate. The exception here is when using compression, in which case we
reserve space matching the uncompressed size, as the compression only
happens at writeback time and in the worst possible case we need that
amount of space in case the data is not compressible.

This means that when there's not available space in the corresponding
space_info object, we may need to allocate a new block group, and then
that block group might not be used after all. In this case the block
group is never added to the list of unused block groups and ends up
never being deleted - except if we unmount and mount again the fs, as
when reading block groups from disk we add unused ones to the list of
unused block groups (fs_info->unused_bgs). Otherwise a block group is
only added to the list of unused block groups when we deallocate the
last extent from it, so if no extent is ever allocated, the block group
is kept around forever.

This also means that if we have a bunch of tasks reserving space in
parallel we can end up allocating many block groups that end up never
being used or kept around for too long without being used, which has
the potential to result in ENOSPC failures in case for example we over
allocate too many metadata block groups and then end up in a state
without enough unallocated space to allocate a new data block group.

This is more likely to happen with metadata reservations as of kernel
6.7, namely since commit 28270e25c69a ("btrfs: always reserve space for
delayed refs when starting transaction"), because we started to always
reserve space for delayed references when starting a transaction handle
for a non-zero number of items, and also to try to reserve space to fill
the gap between the delayed block reserve's reserved space and its size.

So to avoid this, when finishing the creation a new block group, add the
block group to the list of unused block groups if it's still unused at
that time. This way the next time the cleaner kthread runs, it will delete
the block group if it's still unused and not needed to satisfy existing
space reservations.

Reported-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/9cdbf0ca9cdda1b4c84e15e548af7d7f9f926382.camel@intelfx.name/
CC: stable@vger.kernel.org # 6.7+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5fe37bc82f117..378d9103a2072 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -2729,6 +2729,37 @@ next:
 		btrfs_dec_delayed_refs_rsv_bg_inserts(fs_info);
 		list_del_init(&block_group->bg_list);
 		clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags);
+
+		/*
+		 * If the block group is still unused, add it to the list of
+		 * unused block groups. The block group may have been created in
+		 * order to satisfy a space reservation, in which case the
+		 * extent allocation only happens later. But often we don't
+		 * actually need to allocate space that we previously reserved,
+		 * so the block group may become unused for a long time. For
+		 * example for metadata we generally reserve space for a worst
+		 * possible scenario, but then don't end up allocating all that
+		 * space or none at all (due to no need to COW, extent buffers
+		 * were already COWed in the current transaction and still
+		 * unwritten, tree heights lower than the maximum possible
+		 * height, etc). For data we generally reserve the axact amount
+		 * of space we are going to allocate later, the exception is
+		 * when using compression, as we must reserve space based on the
+		 * uncompressed data size, because the compression is only done
+		 * when writeback triggered and we don't know how much space we
+		 * are actually going to need, so we reserve the uncompressed
+		 * size because the data may be uncompressible in the worst case.
+		 */
+		if (ret == 0) {
+			bool used;
+
+			spin_lock(&block_group->lock);
+			used = btrfs_is_block_group_used(block_group);
+			spin_unlock(&block_group->lock);
+
+			if (!used)
+				btrfs_mark_bg_unused(block_group);
+		}
 	}
 	btrfs_trans_release_chunk_metadata(trans);
 }
-- 
GitLab


From c6e02eefd6ace3da3369c764f15429f5647056af Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Tue, 6 Feb 2024 15:00:46 +0000
Subject: [PATCH 4050/4076] cifs: change tcon status when need_reconnect is set
 on it

When a tcon is marked for need_reconnect, the intention
is to have it reconnected.

This change adjusts tcon->status in cifs_tree_connect
when need_reconnect is set. Also, this change has a minor
correction in resetting need_reconnect on success. It makes
sure that it is done with tc_lock held.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 5 +++++
 fs/smb/client/dfs.c     | 7 ++++++-
 fs/smb/client/file.c    | 3 +++
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index bfd568f897105..01c49b29c4996 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -4228,6 +4228,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+
+	/* if tcon is marked for needing reconnect, update state */
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_TCON;
+
 	if (tcon->status == TID_GOOD) {
 		spin_unlock(&tcon->tc_lock);
 		return 0;
diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c
index a8a1d386da656..449c59830039b 100644
--- a/fs/smb/client/dfs.c
+++ b/fs/smb/client/dfs.c
@@ -565,6 +565,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+
+	/* if tcon is marked for needing reconnect, update state */
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_TCON;
+
 	if (tcon->status == TID_GOOD) {
 		spin_unlock(&tcon->tc_lock);
 		return 0;
@@ -625,8 +630,8 @@ out:
 		spin_lock(&tcon->tc_lock);
 		if (tcon->status == TID_IN_TCON)
 			tcon->status = TID_GOOD;
-		spin_unlock(&tcon->tc_lock);
 		tcon->need_reconnect = false;
+		spin_unlock(&tcon->tc_lock);
 	}
 
 	return rc;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index b75282c204dad..f391c9b803d84 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -175,6 +175,9 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_RECON;
+
 	if (tcon->status != TID_NEED_RECON) {
 		spin_unlock(&tcon->tc_lock);
 		return;
-- 
GitLab


From a39c757bf0596b17482a507f31c3ef0af0d1d2b4 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Tue, 6 Feb 2024 15:00:47 +0000
Subject: [PATCH 4051/4076] cifs: handle cases where multiple sessions share
 connection

Based on our implementation of multichannel, it is entirely
possible that a server struct may not be found in any channel
of an SMB session.

In such cases, we should be prepared to move on and search for
the server struct in the next session.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 6 ++++++
 fs/smb/client/sess.c    | 1 -
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 01c49b29c4996..d03253f8f1455 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -233,6 +233,12 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
 	list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) {
 		/* check if iface is still active */
 		spin_lock(&ses->chan_lock);
+		if (cifs_ses_get_chan_index(ses, server) ==
+		    CIFS_INVAL_CHAN_INDEX) {
+			spin_unlock(&ses->chan_lock);
+			continue;
+		}
+
 		if (!cifs_chan_is_iface_active(ses, server)) {
 			spin_unlock(&ses->chan_lock);
 			cifs_chan_update_iface(ses, server);
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index 476d54fceb50f..8f37373fd3334 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -88,7 +88,6 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
 	if (server)
 		cifs_dbg(VFS, "unable to get chan index for server: 0x%llx",
 			 server->conn_id);
-	WARN_ON(1);
 	return CIFS_INVAL_CHAN_INDEX;
 }
 
-- 
GitLab


From a5cc98eba2592d6e3c5a4351319595ddde2a5901 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Tue, 6 Feb 2024 23:57:18 -0600
Subject: [PATCH 4052/4076] smb3: clarify mount warning

When a user tries to use the "sec=krb5p" mount parameter to encrypt
data on connection to a server (when authenticating with Kerberos), we
indicate that it is not supported, but do not note the equivalent
recommended mount parameter ("sec=krb5,seal") which turns on encryption
for that mount (and uses Kerberos for auth).  Update the warning message.

Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 52cbef2eeb28f..aec8dbd1f9dbd 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -211,7 +211,7 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c
 
 	switch (match_token(value, cifs_secflavor_tokens, args)) {
 	case Opt_sec_krb5p:
-		cifs_errorf(fc, "sec=krb5p is not supported!\n");
+		cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n");
 		return 1;
 	case Opt_sec_krb5i:
 		ctx->sign = true;
-- 
GitLab


From 4356e9f841f7fbb945521cef3577ba394c65f3fc Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 9 Feb 2024 12:39:31 -0800
Subject: [PATCH 4053/4076] work around gcc bugs with 'asm goto' with outputs

We've had issues with gcc and 'asm goto' before, and we created a
'asm_volatile_goto()' macro for that in the past: see commits
3f0116c3238a ("compiler/gcc4: Add quirk for 'asm goto' miscompilation
bug") and a9f180345f53 ("compiler/gcc4: Make quirk for
asm_volatile_goto() unconditional").

Then, much later, we ended up removing the workaround in commit
43c249ea0b1e ("compiler-gcc.h: remove ancient workaround for gcc PR
58670") because we no longer supported building the kernel with the
affected gcc versions, but we left the macro uses around.

Now, Sean Christopherson reports a new version of a very similar
problem, which is fixed by re-applying that ancient workaround.  But the
problem in question is limited to only the 'asm goto with outputs'
cases, so instead of re-introducing the old workaround as-is, let's
rename and limit the workaround to just that much less common case.

It looks like there are at least two separate issues that all hit in
this area:

 (a) some versions of gcc don't mark the asm goto as 'volatile' when it
     has outputs:

        https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
        https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420

     which is easy to work around by just adding the 'volatile' by hand.

 (b) Internal compiler errors:

        https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422

     which are worked around by adding the extra empty 'asm' as a
     barrier, as in the original workaround.

but the problem Sean sees may be a third thing since it involves bad
code generation (not an ICE) even with the manually added 'volatile'.

but the same old workaround works for this case, even if this feels a
bit like voodoo programming and may only be hiding the issue.

Reported-and-tested-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Andrew Pinski <quic_apinski@quicinc.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/include/asm/jump_label.h           |  4 ++--
 arch/arm/include/asm/jump_label.h           |  4 ++--
 arch/arm64/include/asm/alternative-macros.h |  4 ++--
 arch/arm64/include/asm/jump_label.h         |  4 ++--
 arch/csky/include/asm/jump_label.h          |  4 ++--
 arch/loongarch/include/asm/jump_label.h     |  4 ++--
 arch/mips/include/asm/jump_label.h          |  4 ++--
 arch/parisc/include/asm/jump_label.h        |  4 ++--
 arch/powerpc/include/asm/jump_label.h       |  4 ++--
 arch/powerpc/include/asm/uaccess.h          | 12 ++++++------
 arch/powerpc/kernel/irq_64.c                |  2 +-
 arch/riscv/include/asm/arch_hweight.h       |  4 ++--
 arch/riscv/include/asm/bitops.h             |  8 ++++----
 arch/riscv/include/asm/checksum.h           |  2 +-
 arch/riscv/include/asm/cpufeature.h         |  4 ++--
 arch/riscv/include/asm/jump_label.h         |  4 ++--
 arch/riscv/lib/csum.c                       | 10 +++++-----
 arch/s390/include/asm/jump_label.h          |  4 ++--
 arch/sparc/include/asm/jump_label.h         |  4 ++--
 arch/um/include/asm/cpufeature.h            |  2 +-
 arch/x86/include/asm/cpufeature.h           |  2 +-
 arch/x86/include/asm/jump_label.h           |  6 +++---
 arch/x86/include/asm/rmwcc.h                |  2 +-
 arch/x86/include/asm/special_insns.h        |  2 +-
 arch/x86/include/asm/uaccess.h              | 10 +++++-----
 arch/x86/kvm/svm/svm_ops.h                  |  6 +++---
 arch/x86/kvm/vmx/vmx.c                      |  4 ++--
 arch/x86/kvm/vmx/vmx_ops.h                  |  6 +++---
 arch/xtensa/include/asm/jump_label.h        |  4 ++--
 include/linux/compiler-gcc.h                | 19 +++++++++++++++++++
 include/linux/compiler_types.h              |  4 ++--
 net/netfilter/nft_set_pipapo_avx2.c         |  2 +-
 samples/bpf/asm_goto_workaround.h           |  8 ++++----
 tools/arch/x86/include/asm/rmwcc.h          |  2 +-
 tools/include/linux/compiler_types.h        |  4 ++--
 35 files changed, 96 insertions(+), 77 deletions(-)

diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h
index 9d96180797396..a339223d9e052 100644
--- a/arch/arc/include/asm/jump_label.h
+++ b/arch/arc/include/asm/jump_label.h
@@ -31,7 +31,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"	\n"
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
 		 "1:							\n"
 		 "nop							\n"
 		 ".pushsection __jump_table, \"aw\"			\n"
@@ -47,7 +47,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key *key,
 						    bool branch)
 {
-	asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"	\n"
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
 		 "1:							\n"
 		 "b %l[l_yes]						\n"
 		 ".pushsection __jump_table, \"aw\"			\n"
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index e12d7d096fc03..e4eb54f6cd9fe 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -11,7 +11,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 WASM(nop) "\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
@@ -25,7 +25,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 WASM(b) " %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 210bb43cff2c7..d328f549b1a60 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -229,7 +229,7 @@ alternative_has_cap_likely(const unsigned long cpucap)
 	if (!cpucap_is_possible(cpucap))
 		return false;
 
-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE_CB("b	%l[l_no]", %[cpucap], alt_cb_patch_nops)
 	:
 	: [cpucap] "i" (cpucap)
@@ -247,7 +247,7 @@ alternative_has_cap_unlikely(const unsigned long cpucap)
 	if (!cpucap_is_possible(cpucap))
 		return false;
 
-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE("nop", "b	%l[l_yes]", %[cpucap])
 	:
 	: [cpucap] "i" (cpucap)
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 48ddc0f45d228..6aafbb7899916 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop					\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
@@ -35,7 +35,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b		%l[l_yes]		\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h
index 98a3f4b168bd2..ef2e37a10a0fe 100644
--- a/arch/csky/include/asm/jump_label.h
+++ b/arch/csky/include/asm/jump_label.h
@@ -12,7 +12,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop32					\n"
 		"	.pushsection	__jump_table, \"aw\"	\n"
 		"	.align		2			\n"
@@ -29,7 +29,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key *key,
 						    bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	bsr32		%l[label]		\n"
 		"	.pushsection	__jump_table, \"aw\"	\n"
 		"	.align		2			\n"
diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h
index 3cea299a5ef58..29acfe3de3faa 100644
--- a/arch/loongarch/include/asm/jump_label.h
+++ b/arch/loongarch/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop			\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
@@ -35,7 +35,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b	%l[l_yes]	\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 081be98c71ef4..ff5d388502d4a 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -39,7 +39,7 @@ extern void jump_label_apply_nops(struct module *mod);
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" B_INSN " 2f\n\t"
+	asm goto("1:\t" B_INSN " 2f\n\t"
 		"2:\t.insn\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
@@ -53,7 +53,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t"
+	asm goto("1:\t" J_INSN " %l[l_yes]\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
 		".popsection\n\t"
diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h
index 94428798b6aa6..317ebc5edc9fe 100644
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -12,7 +12,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align %1\n\t"
@@ -29,7 +29,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b,n %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align %1\n\t"
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 93ce3ec253877..2f2a86ed2280a 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop # arch_static_branch\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
@@ -32,7 +32,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes] # arch_static_branch_jump\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index f1f9890f50d3e..de10437fd2065 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -74,7 +74,7 @@ __pu_failed:							\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op " %0,0(%1)	# put_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -83,7 +83,7 @@ __pu_failed:							\
 		: label)
 #else
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op "%U1%X1 %0,%1	# put_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -97,7 +97,7 @@ __pu_failed:							\
 	__put_user_asm_goto(x, ptr, label, "std")
 #else /* __powerpc64__ */
 #define __put_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	stw%X1 %0, %1\n"			\
 		"2:	stw%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
@@ -146,7 +146,7 @@ do {								\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op" %0,0(%1)	# get_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -155,7 +155,7 @@ do {								\
 		: label)
 #else
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op"%U1%X1 %0, %1	# get_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -169,7 +169,7 @@ do {								\
 	__get_user_asm_goto(x, addr, label, "ld")
 #else /* __powerpc64__ */
 #define __get_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	lwz%X1 %0, %1\n"			\
 		"2:	lwz%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c
index 938e66829eae6..d5c48d1b0a31e 100644
--- a/arch/powerpc/kernel/irq_64.c
+++ b/arch/powerpc/kernel/irq_64.c
@@ -230,7 +230,7 @@ again:
 	 * This allows interrupts to be unmasked without hard disabling, and
 	 * also without new hard interrupts coming in ahead of pending ones.
 	 */
-	asm_volatile_goto(
+	asm goto(
 "1:					\n"
 "		lbz	9,%0(13)	\n"
 "		cmpwi	9,0		\n"
diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
index c20236a0725b9..85b2c443823e8 100644
--- a/arch/riscv/include/asm/arch_hweight.h
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -20,7 +20,7 @@
 static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
 #ifdef CONFIG_RISCV_ISA_ZBB
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -51,7 +51,7 @@ static inline unsigned int __arch_hweight8(unsigned int w)
 static __always_inline unsigned long __arch_hweight64(__u64 w)
 {
 # ifdef CONFIG_RISCV_ISA_ZBB
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 9ffc355370248..329d8244a9b3f 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -39,7 +39,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
 {
 	int num;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -95,7 +95,7 @@ static __always_inline unsigned long variable__fls(unsigned long word)
 {
 	int num;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -154,7 +154,7 @@ static __always_inline int variable_ffs(int x)
 	if (!x)
 		return 0;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -209,7 +209,7 @@ static __always_inline int variable_fls(unsigned int x)
 	if (!x)
 		return 0;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
index a5b60b54b101c..88e6f1499e889 100644
--- a/arch/riscv/include/asm/checksum.h
+++ b/arch/riscv/include/asm/checksum.h
@@ -53,7 +53,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
 		unsigned long fold_temp;
 
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 		    :
 		    :
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 5a626ed2c47a8..0bd11862b7607 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -80,7 +80,7 @@ riscv_has_extension_likely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");
 
 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
@@ -103,7 +103,7 @@ riscv_has_extension_unlikely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");
 
 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 14a5ea8d8ef0f..4a35d787c0191 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
@@ -39,7 +39,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
index af3df5274ccba..74af3ab520b6d 100644
--- a/arch/riscv/lib/csum.c
+++ b/arch/riscv/lib/csum.c
@@ -53,7 +53,7 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :
@@ -170,7 +170,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :
@@ -178,7 +178,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 				  : no_zbb);
 
 #ifdef CONFIG_32BIT
-		asm_volatile_goto(".option push			\n\
+		asm_goto_output(".option push			\n\
 		.option arch,+zbb				\n\
 			rori	%[fold_temp], %[csum], 16	\n\
 			andi	%[offset], %[offset], 1		\n\
@@ -193,7 +193,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 
 		return (unsigned short)csum;
 #else /* !CONFIG_32BIT */
-		asm_volatile_goto(".option push			\n\
+		asm_goto_output(".option push			\n\
 		.option arch,+zbb				\n\
 			rori	%[fold_temp], %[csum], 32	\n\
 			add	%[csum], %[fold_temp], %[csum]	\n\
@@ -257,7 +257,7 @@ do_csum_no_alignment(const unsigned char *buff, int len)
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 895f774bbcc55..bf78cf381dfcd 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -25,7 +25,7 @@
  */
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 0,%l[label]\n"
+	asm goto("0:	brcl 0,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
 			  ".balign	8\n"
 			  ".long	0b-.,%l[label]-.\n"
@@ -39,7 +39,7 @@ label:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 15,%l[label]\n"
+	asm goto("0:	brcl 15,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
 			  ".balign	8\n"
 			  ".long	0b-.,%l[label]-.\n"
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 94eb529dcb776..2718cbea826a7 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -10,7 +10,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
@@ -26,7 +26,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes]\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h
index 4b6d1b526bc12..66fe06db872f0 100644
--- a/arch/um/include/asm/cpufeature.h
+++ b/arch/um/include/asm/cpufeature.h
@@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
+	asm goto("1: jmp 6f\n"
 		 "2:\n"
 		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
 			 "((5f-4f) - (2b-1b)),0x90\n"
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a26bebbdff87e..a1273698fc430 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto(
+	asm goto(
 		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
 		".pushsection .altinstr_aux,\"ax\"\n"
 		"6:\n"
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 071572e23d3a0..cbbef32517f00 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -24,7 +24,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		"jmp %l[l_yes] # objtool NOPs this \n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (2 | branch) : : l_yes);
@@ -38,7 +38,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		".byte " __stringify(BYTES_NOP5) "\n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (branch) : : l_yes);
@@ -52,7 +52,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		"jmp %l[l_yes]\n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (branch) : : l_yes);
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 4b081e0d3306b..363266cbcadaf 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -13,7 +13,7 @@
 #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...)			\
 ({									\
 	bool c = false;							\
-	asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"		\
+	asm goto (fullop "; j" #cc " %l[cc_label]"		\
 			: : [var] "m" (_var), ## __VA_ARGS__		\
 			: clobbers : cc_label);				\
 	if (0) {							\
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index d6cd9344f6c78..48f8dd47cf688 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p)
 #ifdef CONFIG_X86_USER_SHADOW_STACK
 static inline int write_user_shstk_64(u64 __user *addr, u64 val)
 {
-	asm_volatile_goto("1: wrussq %[val], (%[addr])\n"
+	asm goto("1: wrussq %[val], (%[addr])\n"
 			  _ASM_EXTABLE(1b, %l[fail])
 			  :: [addr] "r" (addr), [val] "r" (val)
 			  :: fail);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5c367c1290c35..237dc8cdd12b9 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -133,7 +133,7 @@ extern int __get_user_bad(void);
 
 #ifdef CONFIG_X86_32
 #define __put_user_goto_u64(x, addr, label)			\
-	asm_volatile_goto("\n"					\
+	asm goto("\n"					\
 		     "1:	movl %%eax,0(%1)\n"		\
 		     "2:	movl %%edx,4(%1)\n"		\
 		     _ASM_EXTABLE_UA(1b, %l2)			\
@@ -295,7 +295,7 @@ do {									\
 } while (0)
 
 #define __get_user_asm(x, addr, itype, ltype, label)			\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1:	mov"itype" %[umem],%[output]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l2)				\
 		     : [output] ltype(x)				\
@@ -375,7 +375,7 @@ do {									\
 	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
 		     : CC_OUT(z) (success),				\
@@ -394,7 +394,7 @@ do {									\
 	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
 		     : CC_OUT(z) (success),				\
@@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; };
  * aliasing issues.
  */
 #define __put_user_goto(x, addr, itype, ltype, label)			\
-	asm_volatile_goto("\n"						\
+	asm goto("\n"							\
 		"1:	mov"itype" %0,%1\n"				\
 		_ASM_EXTABLE_UA(1b, %l2)				\
 		: : ltype(x), "m" (__m(addr))				\
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 36c8af87a707a..4e725854c63a1 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -8,7 +8,7 @@
 
 #define svm_asm(insn, clobber...)				\
 do {								\
-	asm_volatile_goto("1: " __stringify(insn) "\n\t"	\
+	asm goto("1: " __stringify(insn) "\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  ::: clobber : fault);			\
 	return;							\
@@ -18,7 +18,7 @@ fault:								\
 
 #define svm_asm1(insn, op1, clobber...)				\
 do {								\
-	asm_volatile_goto("1: "  __stringify(insn) " %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  :: op1 : clobber : fault);		\
 	return;							\
@@ -28,7 +28,7 @@ fault:								\
 
 #define svm_asm2(insn, op1, op2, clobber...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])			\
 			  :: op1, op2 : clobber : fault);		\
 	return;								\
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e262bc2ba4e56..1111d9d089038 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -738,7 +738,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
  */
 static int kvm_cpu_vmxoff(void)
 {
-	asm_volatile_goto("1: vmxoff\n\t"
+	asm goto("1: vmxoff\n\t"
 			  _ASM_EXTABLE(1b, %l[fault])
 			  ::: "cc", "memory" : fault);
 
@@ -2784,7 +2784,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer)
 
 	cr4_set_bits(X86_CR4_VMXE);
 
-	asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t"
+	asm goto("1: vmxon %[vmxon_pointer]\n\t"
 			  _ASM_EXTABLE(1b, %l[fault])
 			  : : [vmxon_pointer] "m"(vmxon_pointer)
 			  : : fault);
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index f41ce3c24123a..8060e5fc6dbd8 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 
-	asm_volatile_goto("1: vmread %[field], %[output]\n\t"
+	asm_goto_output("1: vmread %[field], %[output]\n\t"
 			  "jna %l[do_fail]\n\t"
 
 			  _ASM_EXTABLE(1b, %l[do_exception])
@@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field)
 
 #define vmx_asm1(insn, op1, error_args...)				\
 do {									\
-	asm_volatile_goto("1: " __stringify(insn) " %0\n\t"		\
+	asm goto("1: " __stringify(insn) " %0\n\t"			\
 			  ".byte 0x2e\n\t" /* branch not taken hint */	\
 			  "jna %l[error]\n\t"				\
 			  _ASM_EXTABLE(1b, %l[fault])			\
@@ -205,7 +205,7 @@ fault:									\
 
 #define vmx_asm2(insn, op1, op2, error_args...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"			\
 			  ".byte 0x2e\n\t" /* branch not taken hint */	\
 			  "jna %l[error]\n\t"				\
 			  _ASM_EXTABLE(1b, %l[fault])			\
diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h
index c812bf85021c0..46c8596259d2d 100644
--- a/arch/xtensa/include/asm/jump_label.h
+++ b/arch/xtensa/include/asm/jump_label.h
@@ -13,7 +13,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 			  "_nop\n\t"
 			  ".pushsection __jump_table,  \"aw\"\n\t"
 			  ".word 1b, %l[l_yes], %c0\n\t"
@@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key,
 	 * make it reachable and wrap both into a no-transform block
 	 * to avoid any assembler interference with this.
 	 */
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 			  ".begin no-transform\n\t"
 			  "_j %l[l_yes]\n\t"
 			  "2:\n\t"
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index aebb65bf95a79..c1a963be7d289 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -64,6 +64,25 @@
 		__builtin_unreachable();	\
 	} while (0)
 
+/*
+ * GCC 'asm goto' with outputs miscompiles certain code sequences:
+ *
+ *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420
+ *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422
+ *
+ * Work it around via the same compiler barrier quirk that we used
+ * to use for the old 'asm goto' workaround.
+ *
+ * Also, always mark such 'asm goto' statements as volatile: all
+ * asm goto statements are supposed to be volatile as per the
+ * documentation, but some versions of gcc didn't actually do
+ * that for asms with outputs:
+ *
+ *    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
+ */
+#define asm_goto_output(x...) \
+	do { asm volatile goto(x); asm (""); } while (0)
+
 #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
 #define __HAVE_BUILTIN_BSWAP32__
 #define __HAVE_BUILTIN_BSWAP64__
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6f1ca49306d2f..663d8791c871a 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -362,8 +362,8 @@ struct ftrace_likely_data {
 #define __member_size(p)	__builtin_object_size(p, 1)
 #endif
 
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm goto(x)
 #endif
 
 #ifdef CONFIG_CC_HAS_ASM_INLINE
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 90e275bb3e5d7..a3a8ddca99189 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -57,7 +57,7 @@
 
 /* Jump to label if @reg is zero */
 #define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label)			\
-	asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";"	\
+	asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";"	\
 			  "je %l[" #label "]" : : : : label)
 
 /* Store 256 bits from YMM register into memory. Contrary to bucket load
diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
index 7048bb3594d65..634e81d83efd9 100644
--- a/samples/bpf/asm_goto_workaround.h
+++ b/samples/bpf/asm_goto_workaround.h
@@ -4,14 +4,14 @@
 #define __ASM_GOTO_WORKAROUND_H
 
 /*
- * This will bring in asm_volatile_goto and asm_inline macro definitions
+ * This will bring in asm_goto_output and asm_inline macro definitions
  * if enabled by compiler and config options.
  */
 #include <linux/types.h>
 
-#ifdef asm_volatile_goto
-#undef asm_volatile_goto
-#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
+#ifdef asm_goto_output
+#undef asm_goto_output
+#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output")
 #endif
 
 /*
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
index 11ff975242cac..e2ff22b379a44 100644
--- a/tools/arch/x86/include/asm/rmwcc.h
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -4,7 +4,7 @@
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
-	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+	asm goto (fullop "; j" cc " %l[cc_label]"		\
 			: : "m" (var), ## __VA_ARGS__ 			\
 			: "memory" : cc_label);				\
 	return 0;							\
diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h
index 1bdd834bdd571..d09f9dc172a48 100644
--- a/tools/include/linux/compiler_types.h
+++ b/tools/include/linux/compiler_types.h
@@ -36,8 +36,8 @@
 #include <linux/compiler-gcc.h>
 #endif
 
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm goto(x)
 #endif
 
 #endif /* __LINUX_COMPILER_TYPES_H */
-- 
GitLab


From 841c35169323cd833294798e58b9bf63fa4fa1de Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 11 Feb 2024 12:18:13 -0800
Subject: [PATCH 4054/4076] Linux 6.8-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index a171eafce2a3b..7e0b2ad98905b 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
-- 
GitLab


From bc4cbc9d260ba8358ca63662919f4bb223cb603b Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:29 +0100
Subject: [PATCH 4055/4076] tools/rtla: Fix Makefile compiler options for clang

The following errors are showing up when compiling rtla with clang:

 $ make HOSTCC=clang CC=clang LLVM_IAS=1
 [...]

  clang -O -g -DVERSION=\"6.8.0-rc1\" -flto=auto -ffat-lto-objects
	-fexceptions -fstack-protector-strong
	-fasynchronous-unwind-tables -fstack-clash-protection  -Wall
	-Werror=format-security -Wp,-D_FORTIFY_SOURCE=2
	-Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
	$(pkg-config --cflags libtracefs)    -c -o src/utils.o src/utils.c

  clang: warning: optimization flag '-ffat-lto-objects' is not supported [-Wignored-optimization-argument]
  warning: unknown warning option '-Wno-maybe-uninitialized'; did you mean '-Wno-uninitialized'? [-Wunknown-warning-option]
  1 warning generated.

  clang -o rtla -ggdb  src/osnoise.o src/osnoise_hist.o src/osnoise_top.o
  src/rtla.o src/timerlat_aa.o src/timerlat.o src/timerlat_hist.o
  src/timerlat_top.o src/timerlat_u.o src/trace.o src/utils.o $(pkg-config --libs libtracefs)

  src/osnoise.o: file not recognized: file format not recognized
  clang: error: linker command failed with exit code 1 (use -v to see invocation)
  make: *** [Makefile:110: rtla] Error 1

Solve these issues by:
  - removing -ffat-lto-objects and -Wno-maybe-uninitialized if using clang
  - informing the linker about -flto=auto

Link: https://lore.kernel.org/linux-trace-kernel/567ac1b94effc228ce9a0225b9df7232a9b35b55.1707217097.git.bristot@kernel.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Fixes: 1a7b22ab15eb ("tools/rtla: Build with EXTRA_{C,LD}FLAGS")
Suggested-by: Donald Zickus <dzickus@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 tools/tracing/rtla/Makefile | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index 2456a399eb9ae..afd18c678ff5a 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -28,10 +28,15 @@ FOPTS	:=	-flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
 		-fasynchronous-unwind-tables -fstack-clash-protection
 WOPTS	:= 	-Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
 
+ifeq ($(CC),clang)
+  FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS))
+  WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS))
+endif
+
 TRACEFS_HEADERS	:= $$($(PKG_CONFIG) --cflags libtracefs)
 
 CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS)
-LDFLAGS	:=	-ggdb $(EXTRA_LDFLAGS)
+LDFLAGS	:=	-flto=auto -ggdb $(EXTRA_LDFLAGS)
 LIBS	:=	$$($(PKG_CONFIG) --libs libtracefs)
 
 SRC	:=	$(wildcard src/*.c)
-- 
GitLab


From 64dc40f7523369912d7adb22c8cb655f71610505 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:30 +0100
Subject: [PATCH 4056/4076] tools/rtla: Fix uninitialized
 bucket/data->bucket_size warning

When compiling rtla with clang, I am getting the following warnings:

$ make HOSTCC=clang CC=clang LLVM_IAS=1

[..]
clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions
	-fstack-protector-strong -fasynchronous-unwind-tables
	-fstack-clash-protection  -Wall -Werror=format-security
	-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
	$(pkg-config --cflags libtracefs)
	-c -o src/osnoise_hist.o src/osnoise_hist.c
src/osnoise_hist.c:138:6: warning: variable 'bucket' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
  138 |         if (data->bucket_size)
      |             ^~~~~~~~~~~~~~~~~
src/osnoise_hist.c:149:6: note: uninitialized use occurs here
  149 |         if (bucket < entries)
      |             ^~~~~~
src/osnoise_hist.c:138:2: note: remove the 'if' if its condition is always true
  138 |         if (data->bucket_size)
      |         ^~~~~~~~~~~~~~~~~~~~~~
  139 |                 bucket = duration / data->bucket_size;
src/osnoise_hist.c:132:12: note: initialize the variable 'bucket' to silence this warning
  132 |         int bucket;
      |                   ^
      |                    = 0
1 warning generated.

[...]

clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions
	-fstack-protector-strong -fasynchronous-unwind-tables
	-fstack-clash-protection  -Wall -Werror=format-security
	-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
	$(pkg-config --cflags libtracefs)
	-c -o src/timerlat_hist.o src/timerlat_hist.c
src/timerlat_hist.c:181:6: warning: variable 'bucket' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
  181 |         if (data->bucket_size)
      |             ^~~~~~~~~~~~~~~~~
src/timerlat_hist.c:204:6: note: uninitialized use occurs here
  204 |         if (bucket < entries)
      |             ^~~~~~
src/timerlat_hist.c:181:2: note: remove the 'if' if its condition is always true
  181 |         if (data->bucket_size)
      |         ^~~~~~~~~~~~~~~~~~~~~~
  182 |                 bucket = latency / data->bucket_size;
src/timerlat_hist.c:175:12: note: initialize the variable 'bucket' to silence this warning
  175 |         int bucket;
      |                   ^
      |                    = 0
1 warning generated.

This is a legit warning, but data->bucket_size is always > 0 (see
timerlat_hist_parse_args()), so the if is not necessary.

Remove the unneeded if (data->bucket_size) to avoid the warning.

Link: https://lkml.kernel.org/r/6e1b1665cd99042ae705b3e0fc410858c4c42346.1707217097.git.bristot@kernel.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Donald Zickus <dzickus@redhat.com>
Fixes: 1eeb6328e8b3 ("rtla/timerlat: Add timerlat hist mode")
Fixes: 829a6c0b5698 ("rtla/osnoise: Add the hist mode")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 tools/tracing/rtla/src/osnoise_hist.c  | 3 +--
 tools/tracing/rtla/src/timerlat_hist.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 8f81fa0073648..67128171c29d7 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -135,8 +135,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu,
 	if (params->output_divisor)
 		duration = duration / params->output_divisor;
 
-	if (data->bucket_size)
-		bucket = duration / data->bucket_size;
+	bucket = duration / data->bucket_size;
 
 	total_duration = duration * count;
 
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 47d3d8b53cb21..3a5b8c409e7d8 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -178,8 +178,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu,
 	if (params->output_divisor)
 		latency = latency / params->output_divisor;
 
-	if (data->bucket_size)
-		bucket = latency / data->bucket_size;
+	bucket = latency / data->bucket_size;
 
 	if (!context) {
 		hist = data->hist[cpu].irq;
-- 
GitLab


From 30369084ac6e27479a347899e74f523e6ca29b89 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:31 +0100
Subject: [PATCH 4057/4076] tools/rtla: Fix clang warning about mount_point var
 size

clang is reporting this warning:

$ make HOSTCC=clang CC=clang LLVM_IAS=1
[...]
clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions
	-fstack-protector-strong -fasynchronous-unwind-tables
	-fstack-clash-protection  -Wall -Werror=format-security
	-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
	$(pkg-config --cflags libtracefs)    -c -o src/utils.o src/utils.c

src/utils.c:548:66: warning: 'fscanf' may overflow; destination buffer in argument 3 has size 1024, but the corresponding specifier may require size 1025 [-Wfortify-source]
  548 |         while (fscanf(fp, "%*s %" STR(MAX_PATH) "s %99s %*s %*d %*d\n", mount_point, type) == 2) {
      |                                                                         ^

Increase mount_point variable size to MAX_PATH+1 to avoid the overflow.

Link: https://lkml.kernel.org/r/1b46712e93a2f4153909514a36016959dcc4021c.1707217097.git.bristot@kernel.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Donald Zickus <dzickus@redhat.com>
Fixes: a957cbc02531 ("rtla: Add -C cgroup support")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 tools/tracing/rtla/src/utils.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index c769d7b3842c0..b998b24edf1e0 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -536,7 +536,7 @@ int set_cpu_dma_latency(int32_t latency)
  */
 static const int find_mount(const char *fs, char *mp, int sizeof_mp)
 {
-	char mount_point[MAX_PATH];
+	char mount_point[MAX_PATH+1];
 	char type[100];
 	int found = 0;
 	FILE *fp;
-- 
GitLab


From 084ce16df0f060efd371092a09a7ae74a536dc11 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:32 +0100
Subject: [PATCH 4058/4076] tools/rtla: Remove unused sched_getattr() function

Clang is reporting:

$ make HOSTCC=clang CC=clang LLVM_IAS=1
[...]
clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection  -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS $(pkg-config --cflags libtracefs)    -c -o src/utils.o src/utils.c
src/utils.c:241:19: warning: unused function 'sched_getattr' [-Wunused-function]
  241 | static inline int sched_getattr(pid_t pid, struct sched_attr *attr,
      |                   ^~~~~~~~~~~~~
1 warning generated.

Which is correct, so remove the unused function.

Link: https://lkml.kernel.org/r/eaed7ba122c4ae88ce71277c824ef41cbf789385.1707217097.git.bristot@kernel.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Donald Zickus <dzickus@redhat.com>
Fixes: b1696371d865 ("rtla: Helper functions for rtla")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 tools/tracing/rtla/src/utils.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index b998b24edf1e0..5fcd6495ff058 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -238,12 +238,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr,
 	return syscall(__NR_sched_setattr, pid, attr, flags);
 }
 
-static inline int sched_getattr(pid_t pid, struct sched_attr *attr,
-				unsigned int size, unsigned int flags)
-{
-	return syscall(__NR_sched_getattr, pid, attr, size, flags);
-}
-
 int __set_sched_attr(int pid, struct sched_attr *attr)
 {
 	int flags = 0;
-- 
GitLab


From f9b2c87105c989a7b259c6da87673ada96dce2f8 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:33 +0100
Subject: [PATCH 4059/4076] tools/rv: Fix Makefile compiler options for clang

The following errors are showing up when compiling rv with clang:

 $ make HOSTCC=clang CC=clang LLVM_IAS=1
 [...]
  clang -O -g -DVERSION=\"6.8.0-rc1\" -flto=auto -ffat-lto-objects
  -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables
  -fstack-clash-protection  -Wall -Werror=format-security
  -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
  -Wno-maybe-uninitialized $(pkg-config --cflags libtracefs)
  -I include   -c -o src/utils.o src/utils.c
  clang: warning: optimization flag '-ffat-lto-objects' is not supported [-Wignored-optimization-argument]
  warning: unknown warning option '-Wno-maybe-uninitialized'; did you mean '-Wno-uninitialized'? [-Wunknown-warning-option]
  1 warning generated.

  clang -o rv -ggdb  src/in_kernel.o src/rv.o src/trace.o src/utils.o $(pkg-config --libs libtracefs)
  src/in_kernel.o: file not recognized: file format not recognized
  clang: error: linker command failed with exit code 1 (use -v to see invocation)
  make: *** [Makefile:110: rv] Error 1

Solve these issues by:
  - removing -ffat-lto-objects and -Wno-maybe-uninitialized if using clang
  - informing the linker about -flto=auto

Link: https://lkml.kernel.org/r/ed94a8ddc2ca8c8ef663cfb7ae9dd196c4a66b33.1707217097.git.bristot@kernel.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Fixes: 4bc4b131d44c ("rv: Add rv tool")
Suggested-by: Donald Zickus <dzickus@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 tools/verification/rv/Makefile | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile
index 3d0f3888a58c6..485f8aeddbe03 100644
--- a/tools/verification/rv/Makefile
+++ b/tools/verification/rv/Makefile
@@ -28,10 +28,15 @@ FOPTS	:=	-flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
 		-fasynchronous-unwind-tables -fstack-clash-protection
 WOPTS	:= 	-Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
 
+ifeq ($(CC),clang)
+  FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS))
+  WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS))
+endif
+
 TRACEFS_HEADERS	:= $$($(PKG_CONFIG) --cflags libtracefs)
 
 CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -I include
-LDFLAGS	:=	-ggdb $(EXTRA_LDFLAGS)
+LDFLAGS	:=	-flto=auto -ggdb $(EXTRA_LDFLAGS)
 LIBS	:=	$$($(PKG_CONFIG) --libs libtracefs)
 
 SRC	:=	$(wildcard src/*.c)
-- 
GitLab


From 61ec586bc0815959d3314cf7ce242529c977b357 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:34 +0100
Subject: [PATCH 4060/4076] tools/rv: Fix curr_reactor uninitialized variable

clang is reporting:

$ make HOSTCC=clang CC=clang LLVM_IAS=1

clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions
	-fstack-protector-strong -fasynchronous-unwind-tables
	-fstack-clash-protection  -Wall -Werror=format-security
	-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
	$(pkg-config --cflags libtracefs)  -I include
	-c -o src/in_kernel.o src/in_kernel.c
[...]

src/in_kernel.c:227:6: warning: variable 'curr_reactor' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized]
  227 |         if (!end)
      |             ^~~~
src/in_kernel.c:242:9: note: uninitialized use occurs here
  242 |         return curr_reactor;
      |                ^~~~~~~~~~~~
src/in_kernel.c:227:2: note: remove the 'if' if its condition is always false
  227 |         if (!end)
      |         ^~~~~~~~~
  228 |                 goto out_free;
      |                 ~~~~~~~~~~~~~
src/in_kernel.c:221:6: warning: variable 'curr_reactor' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized]
  221 |         if (!start)
      |             ^~~~~~
src/in_kernel.c:242:9: note: uninitialized use occurs here
  242 |         return curr_reactor;
      |                ^~~~~~~~~~~~
src/in_kernel.c:221:2: note: remove the 'if' if its condition is always false
  221 |         if (!start)
      |         ^~~~~~~~~~~
  222 |                 goto out_free;
      |                 ~~~~~~~~~~~~~
src/in_kernel.c:215:20: note: initialize the variable 'curr_reactor' to silence this warning
  215 |         char *curr_reactor;
      |                           ^
      |                            = NULL
2 warnings generated.

Which is correct. Setting curr_reactor to NULL avoids the problem.

Link: https://lkml.kernel.org/r/3a35551149e5ee0cb0950035afcb8082c3b5d05b.1707217097.git.bristot@kernel.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Donald Zickus <dzickus@redhat.com>
Fixes: 6d60f89691fc ("tools/rv: Add in-kernel monitor interface")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 tools/verification/rv/src/in_kernel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/verification/rv/src/in_kernel.c b/tools/verification/rv/src/in_kernel.c
index ad28582bcf2b1..f04479ecc96c0 100644
--- a/tools/verification/rv/src/in_kernel.c
+++ b/tools/verification/rv/src/in_kernel.c
@@ -210,9 +210,9 @@ static char *ikm_read_reactor(char *monitor_name)
 static char *ikm_get_current_reactor(char *monitor_name)
 {
 	char *reactors = ikm_read_reactor(monitor_name);
+	char *curr_reactor = NULL;
 	char *start;
 	char *end;
-	char *curr_reactor;
 
 	if (!reactors)
 		return NULL;
-- 
GitLab


From 14f08c976ffe0d2117c6199c32663df1cbc45c65 Mon Sep 17 00:00:00 2001
From: limingming3 <limingming890315@gmail.com>
Date: Wed, 7 Feb 2024 14:51:42 +0800
Subject: [PATCH 4061/4076] tools/rtla: Replace setting prio with nice for
 SCHED_OTHER

Since the sched_priority for SCHED_OTHER is always 0, it makes no
sence to set it.
Setting nice for SCHED_OTHER seems more meaningful.

Link: https://lkml.kernel.org/r/20240207065142.1753909-1-limingming3@lixiang.com

Cc: stable@vger.kernel.org
Fixes: b1696371d865 ("rtla: Helper functions for rtla")
Signed-off-by: limingming3 <limingming3@lixiang.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 tools/tracing/rtla/src/utils.c | 6 +++---
 tools/tracing/rtla/src/utils.h | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index 5fcd6495ff058..9ac71a66840c1 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -473,13 +473,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param)
 		if (prio == INVALID_VAL)
 			return -1;
 
-		if (prio < sched_get_priority_min(SCHED_OTHER))
+		if (prio < MIN_NICE)
 			return -1;
-		if (prio > sched_get_priority_max(SCHED_OTHER))
+		if (prio > MAX_NICE)
 			return -1;
 
 		sched_param->sched_policy   = SCHED_OTHER;
-		sched_param->sched_priority = prio;
+		sched_param->sched_nice = prio;
 		break;
 	default:
 		return -1;
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
index 04ed1e650495a..d44513e6c66a0 100644
--- a/tools/tracing/rtla/src/utils.h
+++ b/tools/tracing/rtla/src/utils.h
@@ -9,6 +9,8 @@
  */
 #define BUFF_U64_STR_SIZE	24
 #define MAX_PATH		1024
+#define MAX_NICE		20
+#define MIN_NICE		-19
 
 #define container_of(ptr, type, member)({			\
 	const typeof(((type *)0)->member) *__mptr = (ptr);	\
-- 
GitLab


From b5f319360371087d52070d8f3fc7789e80ce69a6 Mon Sep 17 00:00:00 2001
From: John Kacur <jkacur@redhat.com>
Date: Fri, 2 Feb 2024 19:16:07 -0500
Subject: [PATCH 4062/4076] tools/rtla: Exit with EXIT_SUCCESS when help is
 invoked

Fix rtla so that the following commands exit with 0 when help is invoked

rtla osnoise top -h
rtla osnoise hist -h
rtla timerlat top -h
rtla timerlat hist -h

Link: https://lore.kernel.org/linux-trace-devel/20240203001607.69703-1-jkacur@redhat.com

Cc: stable@vger.kernel.org
Fixes: 1eeb6328e8b3 ("rtla/timerlat: Add timerlat hist mode")
Signed-off-by: John Kacur <jkacur@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 tools/tracing/rtla/src/osnoise_hist.c  | 6 +++++-
 tools/tracing/rtla/src/osnoise_top.c   | 6 +++++-
 tools/tracing/rtla/src/timerlat_hist.c | 6 +++++-
 tools/tracing/rtla/src/timerlat_top.c  | 6 +++++-
 4 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 67128171c29d7..01870d50942a1 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -479,7 +479,11 @@ static void osnoise_hist_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index f7c959be86777..457360db07673 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -331,7 +331,11 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 3a5b8c409e7d8..dbf154082f958 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -545,7 +545,11 @@ static void timerlat_hist_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 1640f121baca5..3e9af2c386888 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -375,7 +375,11 @@ static void timerlat_top_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
-- 
GitLab


From d55347bfe4e66dce2e1e7501e5492f4af3e315f8 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 11 Feb 2024 08:08:37 -0800
Subject: [PATCH 4063/4076] MIPS: Add 'memory' clobber to csum_ipv6_magic()
 inline assembler

After 'lib: checksum: Use aligned accesses for ip_fast_csum and
csum_ipv6_magic tests' was applied, the test_csum_ipv6_magic unit test
started failing for all mips platforms, both little and bit endian.
Oddly enough, adding debug code into test_csum_ipv6_magic() made the
problem disappear.

The gcc manual says:

"The "memory" clobber tells the compiler that the assembly code performs
 memory reads or writes to items other than those listed in the input
 and output operands (for example, accessing the memory pointed to by one
 of the input parameters)
"

This is definitely the case for csum_ipv6_magic(). Indeed, adding the
'memory' clobber fixes the problem.

Cc: Charlie Jenkins <charlie@rivosinc.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/include/asm/checksum.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 4044eaf989ac7..0921ddda11a4b 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	"	.set	pop"
 	: "=&r" (sum), "=&r" (tmp)
 	: "r" (saddr), "r" (daddr),
-	  "0" (htonl(len)), "r" (htonl(proto)), "r" (sum));
+	  "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)
+	: "memory");
 
 	return csum_fold(sum);
 }
-- 
GitLab


From 11ba1728be3edb6928791f4c622f154ebe228ae6 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Fri, 2 Feb 2024 12:30:26 +0000
Subject: [PATCH 4064/4076] ptrace: Introduce exception_ip arch hook

On architectures with delay slot, architecture level instruction
pointer (or program counter) in pt_regs may differ from where
exception was triggered.

Introduce exception_ip hook to invoke architecture code and determine
actual instruction pointer to the exception.

Link: https://lore.kernel.org/lkml/00d1b813-c55f-4365-8d81-d70258e10b16@app.fastmail.com/
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/include/asm/ptrace.h | 2 ++
 arch/mips/kernel/ptrace.c      | 7 +++++++
 include/linux/ptrace.h         | 4 ++++
 3 files changed, 13 insertions(+)

diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index daf3cf244ea97..701a233583c2c 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -154,6 +154,8 @@ static inline long regs_return_value(struct pt_regs *regs)
 }
 
 #define instruction_pointer(regs) ((regs)->cp0_epc)
+extern unsigned long exception_ip(struct pt_regs *regs);
+#define exception_ip(regs) exception_ip(regs)
 #define profile_pc(regs) instruction_pointer(regs)
 
 extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index d9df543f7e2c4..59288c13b581b 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -31,6 +31,7 @@
 #include <linux/seccomp.h>
 #include <linux/ftrace.h>
 
+#include <asm/branch.h>
 #include <asm/byteorder.h>
 #include <asm/cpu.h>
 #include <asm/cpu-info.h>
@@ -48,6 +49,12 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
+unsigned long exception_ip(struct pt_regs *regs)
+{
+	return exception_epc(regs);
+}
+EXPORT_SYMBOL(exception_ip);
+
 /*
  * Called by kernel/ptrace.c when detaching..
  *
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index eaaef3ffec221..90507d4afcd6d 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -393,6 +393,10 @@ static inline void user_single_step_report(struct pt_regs *regs)
 #define current_user_stack_pointer() user_stack_pointer(current_pt_regs())
 #endif
 
+#ifndef exception_ip
+#define exception_ip(x) instruction_pointer(x)
+#endif
+
 extern int task_current_syscall(struct task_struct *target, struct syscall_info *info);
 
 extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact);
-- 
GitLab


From 9d6e21ddf20293b3880ae55b9d14de91c5891c59 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Fri, 2 Feb 2024 12:30:27 +0000
Subject: [PATCH 4065/4076] MIPS: Clear Cause.BD in instruction_pointer_set

Clear Cause.BD after we use instruction_pointer_set to override
EPC.

This can prevent exception_epc check against instruction code at
new return address.
It won't be considered as "in delay slot" after epc being overridden
anyway.

Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/include/asm/ptrace.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 701a233583c2c..d14d0e37ad02d 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -60,6 +60,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
                                            unsigned long val)
 {
 	regs->cp0_epc = val;
+	regs->cp0_cause &= ~CAUSEF_BD;
 }
 
 /* Query offset/name of register from its name/offset */
-- 
GitLab


From 8fa5070833886268e4fb646daaca99f725b378e9 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Fri, 2 Feb 2024 12:30:28 +0000
Subject: [PATCH 4066/4076] mm/memory: Use exception ip to search exception
 tables

On architectures with delay slot, instruction_pointer() may differ
from where exception was triggered.

Use exception_ip we just introduced to search exception tables to
get rid of the problem.

Fixes: 4bce37a68ff8 ("mips/mm: Convert to using lock_mm_and_find_vma()")
Reported-by: Xi Ruoyao <xry111@xry111.site>
Link: https://lore.kernel.org/r/75e9fd7b08562ad9b456a5bdaacb7cc220311cc9.camel@xry111.site/
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 mm/memory.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 89bcae0b224d6..15f8b10ea17c4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5478,7 +5478,7 @@ static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs
 		return true;
 
 	if (regs && !user_mode(regs)) {
-		unsigned long ip = instruction_pointer(regs);
+		unsigned long ip = exception_ip(regs);
 		if (!search_exception_tables(ip))
 			return false;
 	}
@@ -5503,7 +5503,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r
 {
 	mmap_read_unlock(mm);
 	if (regs && !user_mode(regs)) {
-		unsigned long ip = instruction_pointer(regs);
+		unsigned long ip = exception_ip(regs);
 		if (!search_exception_tables(ip))
 			return false;
 	}
-- 
GitLab


From feefe1f49d26bad9d8997096e3a200280fa7b1c5 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 31 Jan 2024 17:18:04 +0000
Subject: [PATCH 4067/4076] btrfs: don't reserve space for checksums when
 writing to nocow files

Currently when doing a write to a file we always reserve metadata space
for inserting data checksums. However we don't need to do it if we have
a nodatacow file (-o nodatacow mount option or chattr +C) or if checksums
are disabled (-o nodatasum mount option), as in that case we are only
adding unnecessary pressure to metadata reservations.

For example on x86_64, with the default node size of 16K, a 4K buffered
write into a nodatacow file is reserving 655360 bytes of metadata space,
as it's accounting for checksums. After this change, which stops reserving
space for checksums if we have a nodatacow file or checksums are disabled,
we only need to reserve 393216 bytes of metadata.

CC: stable@vger.kernel.org # 6.1+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delalloc-space.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 2833e8ef4c098..acf9f4b6c0440 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -245,7 +245,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
 	u64 reserve_size = 0;
 	u64 qgroup_rsv_size = 0;
-	u64 csum_leaves;
 	unsigned outstanding_extents;
 
 	lockdep_assert_held(&inode->lock);
@@ -260,10 +259,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 						outstanding_extents);
 		reserve_size += btrfs_calc_metadata_size(fs_info, 1);
 	}
-	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
-						 inode->csum_bytes);
-	reserve_size += btrfs_calc_insert_metadata_size(fs_info,
-							csum_leaves);
+	if (!(inode->flags & BTRFS_INODE_NODATASUM)) {
+		u64 csum_leaves;
+
+		csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
+		reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves);
+	}
 	/*
 	 * For qgroup rsv, the calculation is very simple:
 	 * account one nodesize for each outstanding extent
@@ -278,14 +279,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	spin_unlock(&block_rsv->lock);
 }
 
-static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
+static void calc_inode_reservations(struct btrfs_inode *inode,
 				    u64 num_bytes, u64 disk_num_bytes,
 				    u64 *meta_reserve, u64 *qgroup_reserve)
 {
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 nr_extents = count_max_extents(fs_info, num_bytes);
-	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+	u64 csum_leaves;
 	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
+	if (inode->flags & BTRFS_INODE_NODATASUM)
+		csum_leaves = 0;
+	else
+		csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+
 	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
 						nr_extents + csum_leaves);
 
@@ -337,7 +344,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	 * everything out and try again, which is bad.  This way we just
 	 * over-reserve slightly, and clean up the mess when we are done.
 	 */
-	calc_inode_reservations(fs_info, num_bytes, disk_num_bytes,
+	calc_inode_reservations(inode, num_bytes, disk_num_bytes,
 				&meta_reserve, &qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true,
 						 noflush);
@@ -359,7 +366,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	nr_extents = count_max_extents(fs_info, num_bytes);
 	spin_lock(&inode->lock);
 	btrfs_mod_outstanding_extents(inode, nr_extents);
-	inode->csum_bytes += disk_num_bytes;
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		inode->csum_bytes += disk_num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 
@@ -393,7 +401,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 	spin_lock(&inode->lock);
-	inode->csum_bytes -= num_bytes;
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		inode->csum_bytes -= num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 
-- 
GitLab


From 1bd96c92c6a0a4d43815eb685c15aa4b78879dc9 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 2 Feb 2024 12:09:22 +0000
Subject: [PATCH 4068/4076] btrfs: reject encoded write if inode has nodatasum
 flag set

Currently we allow an encoded write against inodes that have the NODATASUM
flag set, either because they are NOCOW files or they were created while
the filesystem was mounted with "-o nodatasum". This results in having
compressed extents without corresponding checksums, which is a filesystem
inconsistency reported by 'btrfs check'.

For example, running btrfs/281 with MOUNT_OPTIONS="-o nodatacow" triggers
this and 'btrfs check' errors out with:

   [1/7] checking root items
   [2/7] checking extents
   [3/7] checking free space tree
   [4/7] checking fs roots
   root 256 inode 257 errors 1040, bad file extent, some csum missing
   root 256 inode 258 errors 1040, bad file extent, some csum missing
   ERROR: errors found in fs roots
   (...)

So reject encoded writes if the target inode has NODATASUM set.

CC: stable@vger.kernel.org # 6.1+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d232eca1bbee2..5f39462dceb0b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10288,6 +10288,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE)
 		return -EINVAL;
 
+	/*
+	 * Compressed extents should always have checksums, so error out if we
+	 * have a NOCOW file or inode was created while mounted with NODATASUM.
+	 */
+	if (inode->flags & BTRFS_INODE_NODATASUM)
+		return -EINVAL;
+
 	orig_count = iov_iter_count(from);
 
 	/* The extent size must be sane. */
-- 
GitLab


From 88e81a67773017a2b93f6d5fe7c78bb0c5a6e4dd Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 12 Feb 2024 21:50:53 +0000
Subject: [PATCH 4069/4076] btrfs: zoned: fix chunk map leak when loading block
 group zone info

At btrfs_load_block_group_zone_info() we never drop a reference on the
chunk map we have looked up, therefore leaking a reference on it. So
add the missing btrfs_free_chunk_map() at the end of the function.

Fixes: 7dc66abb5a47 ("btrfs: use a dedicated data structure for chunk maps")
Reported-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index ac9bbe0c4ffe6..afeb1dc1f43ae 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1687,6 +1687,7 @@ out:
 	}
 	bitmap_free(active);
 	kfree(zone_info);
+	btrfs_free_chunk_map(map);
 
 	return ret;
 }
-- 
GitLab


From 2f6397e448e689adf57e6788c90f913abd7e1af8 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 2 Feb 2024 14:32:17 +0000
Subject: [PATCH 4070/4076] btrfs: don't refill whole delayed refs block
 reserve when starting transaction

Since commit 28270e25c69a ("btrfs: always reserve space for delayed refs
when starting transaction") we started not only to reserve metadata space
for the delayed refs a caller of btrfs_start_transaction() might generate
but also to try to fully refill the delayed refs block reserve, because
there are several case where we generate delayed refs and haven't reserved
space for them, relying on the global block reserve. Relying too much on
the global block reserve is not always safe, and can result in hitting
-ENOSPC during transaction commits or worst, in rare cases, being unable
to mount a filesystem that needs to do orphan cleanup or anything that
requires modifying the filesystem during mount, and has no more
unallocated space and the metadata space is nearly full. This was
explained in detail in that commit's change log.

However the gap between the reserved amount and the size of the delayed
refs block reserve can be huge, so attempting to reserve space for such
a gap can result in allocating many metadata block groups that end up
not being used. After a recent patch, with the subject:

  "btrfs: add new unused block groups to the list of unused block groups"

We started to add new block groups that are unused to the list of unused
block groups, to avoid having them around for a very long time in case
they are never used, because a block group is only added to the list of
unused block groups when we deallocate the last extent or when mounting
the filesystem and the block group has 0 bytes used. This is not a problem
introduced by the commit mentioned earlier, it always existed as our
metadata space reservations are, most of the time, pessimistic and end up
not using all the space they reserved, so we can occasionally end up with
one or two unused metadata block groups for a long period. However after
that commit mentioned earlier, we are just more pessimistic in the
metadata space reservations when starting a transaction and therefore the
issue is more likely to happen.

This however is not always enough because we might create unused metadata
block groups when reserving metadata space at a high rate if there's
always a gap in the delayed refs block reserve and the cleaner kthread
isn't triggered often enough or is busy with other work (running delayed
iputs, cleaning deleted roots, etc), not to mention the block group's
allocated space is only usable for a new block group after the transaction
used to remove it is committed.

A user reported that he's getting a lot of allocated metadata block groups
but the usage percentage of metadata space was very low compared to the
total allocated space, specially after running a series of block group
relocations.

So for now stop trying to refill the gap in the delayed refs block reserve
and reserve space only for the delayed refs we are expected to generate
when starting a transaction.

CC: stable@vger.kernel.org # 6.7+
Reported-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/9cdbf0ca9cdda1b4c84e15e548af7d7f9f926382.camel@intelfx.name/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H6802ayLHUJFztzZAVzBLJAGdFx=6FHNNy87+obZXXZpQ@mail.gmail.com/
Tested-by: Ivan Shapovalov <intelfx@intelfx.name>
Reported-by: Heddxh <g311571057@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/CAE93xANEby6RezOD=zcofENYZOT-wpYygJyauyUAZkLv6XVFOA@mail.gmail.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/transaction.c | 38 ++------------------------------------
 1 file changed, 2 insertions(+), 36 deletions(-)

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5b3333ceef048..c52807d97efa5 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -564,56 +564,22 @@ static int btrfs_reserve_trans_metadata(struct btrfs_fs_info *fs_info,
 					u64 num_bytes,
 					u64 *delayed_refs_bytes)
 {
-	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
 	struct btrfs_space_info *si = fs_info->trans_block_rsv.space_info;
-	u64 extra_delayed_refs_bytes = 0;
-	u64 bytes;
+	u64 bytes = num_bytes + *delayed_refs_bytes;
 	int ret;
 
-	/*
-	 * If there's a gap between the size of the delayed refs reserve and
-	 * its reserved space, than some tasks have added delayed refs or bumped
-	 * its size otherwise (due to block group creation or removal, or block
-	 * group item update). Also try to allocate that gap in order to prevent
-	 * using (and possibly abusing) the global reserve when committing the
-	 * transaction.
-	 */
-	if (flush == BTRFS_RESERVE_FLUSH_ALL &&
-	    !btrfs_block_rsv_full(delayed_refs_rsv)) {
-		spin_lock(&delayed_refs_rsv->lock);
-		if (delayed_refs_rsv->size > delayed_refs_rsv->reserved)
-			extra_delayed_refs_bytes = delayed_refs_rsv->size -
-				delayed_refs_rsv->reserved;
-		spin_unlock(&delayed_refs_rsv->lock);
-	}
-
-	bytes = num_bytes + *delayed_refs_bytes + extra_delayed_refs_bytes;
-
 	/*
 	 * We want to reserve all the bytes we may need all at once, so we only
 	 * do 1 enospc flushing cycle per transaction start.
 	 */
 	ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-	if (ret == 0) {
-		if (extra_delayed_refs_bytes > 0)
-			btrfs_migrate_to_delayed_refs_rsv(fs_info,
-							  extra_delayed_refs_bytes);
-		return 0;
-	}
-
-	if (extra_delayed_refs_bytes > 0) {
-		bytes -= extra_delayed_refs_bytes;
-		ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-		if (ret == 0)
-			return 0;
-	}
 
 	/*
 	 * If we are an emergency flush, which can steal from the global block
 	 * reserve, then attempt to not reserve space for the delayed refs, as
 	 * we will consume space for them from the global block reserve.
 	 */
-	if (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
+	if (ret && flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
 		bytes -= *delayed_refs_bytes;
 		*delayed_refs_bytes = 0;
 		ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-- 
GitLab


From 333861f4cca6d2c959ca2876587c42767853dccc Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Wed, 14 Feb 2024 20:11:40 +0530
Subject: [PATCH 4071/4076] HID: amd_sfh: Increase sensor command timeout

During the initialization sensors may take some time to respond. Hence,
increase the sensor command timeouts in order to obtain status responses
within a maximum timeout.

Co-developed-by: Akshata MukundShetty <akshata.mukundshetty@amd.com>
Signed-off-by: Akshata MukundShetty <akshata.mukundshetty@amd.com>
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index 2530fa98b568b..8a4cd793d0217 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -39,11 +39,11 @@ static int amd_sfh_wait_response_v2(struct amd_mp2_dev *mp2, u8 sid, u32 sensor_
 {
 	union cmd_response cmd_resp;
 
-	/* Get response with status within a max of 1600 ms timeout */
+	/* Get response with status within a max of 10 seconds timeout */
 	if (!readl_poll_timeout(mp2->mmio + AMD_P2C_MSG(0), cmd_resp.resp,
 				(cmd_resp.response_v2.response == sensor_sts &&
 				cmd_resp.response_v2.status == 0 && (sid == 0xff ||
-				cmd_resp.response_v2.sensor_id == sid)), 500, 1600000))
+				cmd_resp.response_v2.sensor_id == sid)), 500, 10000000))
 		return cmd_resp.response_v2.response;
 
 	return SENSOR_DISABLED;
-- 
GitLab


From bbf0dec30696638b8bdc28cb2f5bf23f8d760b52 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Wed, 14 Feb 2024 20:11:41 +0530
Subject: [PATCH 4072/4076] HID: amd_sfh: Update HPD sensor structure elements

HPD sensor data is not populating properly because of wrong order of HPD
sensor structure elements. So update the order of structure elements to
match the HPD sensor data received from the firmware.

Fixes: 24a31ea94922 ("HID: amd_sfh: Add initial support for HPD sensor")
Co-developed-by: Akshata MukundShetty <akshata.mukundshetty@amd.com>
Signed-off-by: Akshata MukundShetty <akshata.mukundshetty@amd.com>
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
index 70add75fc5066..05e400a4a83e4 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
@@ -90,10 +90,10 @@ enum mem_use_type {
 struct hpd_status {
 	union {
 		struct {
-			u32 human_presence_report : 4;
-			u32 human_presence_actual : 4;
-			u32 probablity		  : 8;
 			u32 object_distance       : 16;
+			u32 probablity		  : 8;
+			u32 human_presence_actual : 4;
+			u32 human_presence_report : 4;
 		} shpd;
 		u32 val;
 	};
-- 
GitLab


From c1db0073212ef39d5a46c2aea5e49bf884375ce4 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Wed, 14 Feb 2024 20:11:42 +0530
Subject: [PATCH 4073/4076] HID: amd_sfh: Avoid disabling the interrupt

HP ProBook x360 435 G7 using older version of firmware which doesn't
support disabling the interrupt for all commands. Hence avoid disabling
the interrupt for that particular model.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=218104
Fixes: b300667b33b2 ("HID: amd_sfh: Disable the interrupt for all command")
Co-developed-by: Akshata MukundShetty <akshata.mukundshetty@amd.com>
Signed-off-by: Akshata MukundShetty <akshata.mukundshetty@amd.com>
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 30 +++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index 8a4cd793d0217..8c1809c7d1f73 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -35,6 +35,8 @@ static int sensor_mask_override = -1;
 module_param_named(sensor_mask, sensor_mask_override, int, 0444);
 MODULE_PARM_DESC(sensor_mask, "override the detected sensors mask");
 
+static bool intr_disable = true;
+
 static int amd_sfh_wait_response_v2(struct amd_mp2_dev *mp2, u8 sid, u32 sensor_sts)
 {
 	union cmd_response cmd_resp;
@@ -55,7 +57,7 @@ static void amd_start_sensor_v2(struct amd_mp2_dev *privdata, struct amd_mp2_sen
 
 	cmd_base.ul = 0;
 	cmd_base.cmd_v2.cmd_id = ENABLE_SENSOR;
-	cmd_base.cmd_v2.intr_disable = 1;
+	cmd_base.cmd_v2.intr_disable = intr_disable;
 	cmd_base.cmd_v2.period = info.period;
 	cmd_base.cmd_v2.sensor_id = info.sensor_idx;
 	cmd_base.cmd_v2.length = 16;
@@ -73,7 +75,7 @@ static void amd_stop_sensor_v2(struct amd_mp2_dev *privdata, u16 sensor_idx)
 
 	cmd_base.ul = 0;
 	cmd_base.cmd_v2.cmd_id = DISABLE_SENSOR;
-	cmd_base.cmd_v2.intr_disable = 1;
+	cmd_base.cmd_v2.intr_disable = intr_disable;
 	cmd_base.cmd_v2.period = 0;
 	cmd_base.cmd_v2.sensor_id = sensor_idx;
 	cmd_base.cmd_v2.length  = 16;
@@ -87,7 +89,7 @@ static void amd_stop_all_sensor_v2(struct amd_mp2_dev *privdata)
 	union sfh_cmd_base cmd_base;
 
 	cmd_base.cmd_v2.cmd_id = STOP_ALL_SENSORS;
-	cmd_base.cmd_v2.intr_disable = 1;
+	cmd_base.cmd_v2.intr_disable = intr_disable;
 	cmd_base.cmd_v2.period = 0;
 	cmd_base.cmd_v2.sensor_id = 0;
 
@@ -292,6 +294,26 @@ int amd_sfh_irq_init(struct amd_mp2_dev *privdata)
 	return 0;
 }
 
+static int mp2_disable_intr(const struct dmi_system_id *id)
+{
+	intr_disable = false;
+	return 0;
+}
+
+static const struct dmi_system_id dmi_sfh_table[] = {
+	{
+		/*
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=218104
+		 */
+		.callback = mp2_disable_intr,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook x360 435 G7"),
+		},
+	},
+	{}
+};
+
 static const struct dmi_system_id dmi_nodevs[] = {
 	{
 		/*
@@ -315,6 +337,8 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 	if (dmi_first_match(dmi_nodevs))
 		return -ENODEV;
 
+	dmi_check_system(dmi_sfh_table);
+
 	privdata = devm_kzalloc(&pdev->dev, sizeof(*privdata), GFP_KERNEL);
 	if (!privdata)
 		return -ENOMEM;
-- 
GitLab


From 2105e8e00da4673266e217653292fef6acefde03 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Wed, 14 Feb 2024 20:11:43 +0530
Subject: [PATCH 4074/4076] HID: amd_sfh: Improve boot time when SFH is
 available

AMD SFH load takes longer time in initialization. Hence split and defer
initialization code to improve SFH module load time and boot time of the
system when SFH is available.

Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/amd_sfh_common.h |  2 +
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.c   | 75 ++++++++++++++++++++----
 2 files changed, 64 insertions(+), 13 deletions(-)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_common.h b/drivers/hid/amd-sfh-hid/amd_sfh_common.h
index a1950bc6e6cef..ef5551c1eec5d 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_common.h
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_common.h
@@ -53,6 +53,8 @@ struct amd_mp2_dev {
 	/* mp2 active control status */
 	u32 mp2_acs;
 	struct sfh_dev_status dev_en;
+	struct work_struct work;
+	u8 init_done;
 };
 
 struct amd_mp2_ops {
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index 8c1809c7d1f73..495ec1179ee5b 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -10,6 +10,7 @@
 
 #include <linux/bitops.h>
 #include <linux/delay.h>
+#include <linux/devm-helpers.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmi.h>
 #include <linux/interrupt.h>
@@ -329,6 +330,48 @@ static const struct dmi_system_id dmi_nodevs[] = {
 	{ }
 };
 
+static void sfh1_1_init_work(struct work_struct *work)
+{
+	struct amd_mp2_dev *mp2 = container_of(work, struct amd_mp2_dev, work);
+	struct pci_dev *pdev = mp2->pdev;
+	int rc;
+
+	rc = mp2->sfh1_1_ops->init(mp2);
+	if (rc) {
+		dev_err(&pdev->dev, "sfh1_1_init failed err %d\n", rc);
+		return;
+	}
+
+	amd_sfh_clear_intr(mp2);
+	mp2->init_done = 1;
+}
+
+static void sfh_init_work(struct work_struct *work)
+{
+	struct amd_mp2_dev *mp2 = container_of(work, struct amd_mp2_dev, work);
+	struct pci_dev *pdev = mp2->pdev;
+	int rc;
+
+	rc = amd_sfh_hid_client_init(mp2);
+	if (rc) {
+		amd_sfh_clear_intr(mp2);
+		dev_err(&pdev->dev, "amd_sfh_hid_client_init failed err %d\n", rc);
+		return;
+	}
+
+	amd_sfh_clear_intr(mp2);
+	mp2->init_done = 1;
+}
+
+static void amd_sfh_remove(struct pci_dev *pdev)
+{
+	struct amd_mp2_dev *mp2 = pci_get_drvdata(pdev);
+
+	flush_work(&mp2->work);
+	if (mp2->init_done)
+		mp2->mp2_ops->remove(mp2);
+}
+
 static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct amd_mp2_dev *privdata;
@@ -367,10 +410,12 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 
 	privdata->sfh1_1_ops = (const struct amd_sfh1_1_ops *)id->driver_data;
 	if (privdata->sfh1_1_ops) {
-		rc = privdata->sfh1_1_ops->init(privdata);
+		rc = devm_work_autocancel(&pdev->dev, &privdata->work, sfh1_1_init_work);
 		if (rc)
 			return rc;
-		goto init_done;
+
+		schedule_work(&privdata->work);
+		return 0;
 	}
 
 	mp2_select_ops(privdata);
@@ -381,33 +426,34 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 		return rc;
 	}
 
-	rc = amd_sfh_hid_client_init(privdata);
+	rc = devm_work_autocancel(&pdev->dev, &privdata->work, sfh_init_work);
 	if (rc) {
 		amd_sfh_clear_intr(privdata);
-		if (rc != -EOPNOTSUPP)
-			dev_err(&pdev->dev, "amd_sfh_hid_client_init failed\n");
 		return rc;
 	}
 
-init_done:
-	amd_sfh_clear_intr(privdata);
-
-	return devm_add_action_or_reset(&pdev->dev, privdata->mp2_ops->remove, privdata);
+	schedule_work(&privdata->work);
+	return 0;
 }
 
 static void amd_sfh_shutdown(struct pci_dev *pdev)
 {
 	struct amd_mp2_dev *mp2 = pci_get_drvdata(pdev);
 
-	if (mp2 && mp2->mp2_ops)
-		mp2->mp2_ops->stop_all(mp2);
+	if (mp2) {
+		flush_work(&mp2->work);
+		if (mp2->init_done)
+			mp2->mp2_ops->stop_all(mp2);
+	}
 }
 
 static int __maybe_unused amd_mp2_pci_resume(struct device *dev)
 {
 	struct amd_mp2_dev *mp2 = dev_get_drvdata(dev);
 
-	mp2->mp2_ops->resume(mp2);
+	flush_work(&mp2->work);
+	if (mp2->init_done)
+		mp2->mp2_ops->resume(mp2);
 
 	return 0;
 }
@@ -416,7 +462,9 @@ static int __maybe_unused amd_mp2_pci_suspend(struct device *dev)
 {
 	struct amd_mp2_dev *mp2 = dev_get_drvdata(dev);
 
-	mp2->mp2_ops->suspend(mp2);
+	flush_work(&mp2->work);
+	if (mp2->init_done)
+		mp2->mp2_ops->suspend(mp2);
 
 	return 0;
 }
@@ -438,6 +486,7 @@ static struct pci_driver amd_mp2_pci_driver = {
 	.probe		= amd_mp2_pci_probe,
 	.driver.pm	= &amd_mp2_pm_ops,
 	.shutdown	= amd_sfh_shutdown,
+	.remove		= amd_sfh_remove,
 };
 module_pci_driver(amd_mp2_pci_driver);
 
-- 
GitLab


From 6296562f30b1caf4b5f44e0c89c8f5cbfdb14b4a Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Wed, 14 Feb 2024 20:11:44 +0530
Subject: [PATCH 4075/4076] HID: amd_sfh: Extend MP2 register access to SFH

Various MP2 register sets are supported by newer processors. Therefore,
extend MP2 register access to SFH.

Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/amd_sfh_common.h           | 14 ++++++++++++++
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.c             |  9 ++++++---
 drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c      |  2 +-
 drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c      |  4 ++--
 drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c | 10 +++++-----
 5 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_common.h b/drivers/hid/amd-sfh-hid/amd_sfh_common.h
index ef5551c1eec5d..e5620d7db5690 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_common.h
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_common.h
@@ -19,6 +19,9 @@
 #define AMD_C2P_MSG(regno) (0x10500 + ((regno) * 4))
 #define AMD_P2C_MSG(regno) (0x10680 + ((regno) * 4))
 
+#define AMD_C2P_MSG_V1(regno) (0x10900 + ((regno) * 4))
+#define AMD_P2C_MSG_V1(regno) (0x10500 + ((regno) * 4))
+
 #define SENSOR_ENABLED			4
 #define SENSOR_DISABLED			5
 
@@ -55,6 +58,7 @@ struct amd_mp2_dev {
 	struct sfh_dev_status dev_en;
 	struct work_struct work;
 	u8 init_done;
+	u8 rver;
 };
 
 struct amd_mp2_ops {
@@ -81,4 +85,14 @@ void amd_sfh_clear_intr_v2(struct amd_mp2_dev *privdata);
 int amd_sfh_irq_init_v2(struct amd_mp2_dev *privdata);
 void amd_sfh_clear_intr(struct amd_mp2_dev *privdata);
 int amd_sfh_irq_init(struct amd_mp2_dev *privdata);
+
+static inline u64 amd_get_c2p_val(struct amd_mp2_dev *mp2, u32 idx)
+{
+	return mp2->rver == 1 ? AMD_C2P_MSG_V1(idx) :  AMD_C2P_MSG(idx);
+}
+
+static inline u64 amd_get_p2c_val(struct amd_mp2_dev *mp2, u32 idx)
+{
+	return mp2->rver == 1 ? AMD_P2C_MSG_V1(idx) :  AMD_P2C_MSG(idx);
+}
 #endif
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index 495ec1179ee5b..9e97c26c4482e 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -99,9 +99,9 @@ static void amd_stop_all_sensor_v2(struct amd_mp2_dev *privdata)
 
 void amd_sfh_clear_intr_v2(struct amd_mp2_dev *privdata)
 {
-	if (readl(privdata->mmio + AMD_P2C_MSG(4))) {
-		writel(0, privdata->mmio + AMD_P2C_MSG(4));
-		writel(0xf, privdata->mmio + AMD_P2C_MSG(5));
+	if (readl(privdata->mmio + amd_get_p2c_val(privdata, 4))) {
+		writel(0, privdata->mmio + amd_get_p2c_val(privdata, 4));
+		writel(0xf, privdata->mmio + amd_get_p2c_val(privdata, 5));
 	}
 }
 
@@ -410,6 +410,9 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 
 	privdata->sfh1_1_ops = (const struct amd_sfh1_1_ops *)id->driver_data;
 	if (privdata->sfh1_1_ops) {
+		if (boot_cpu_data.x86 >= 0x1A)
+			privdata->rver = 1;
+
 		rc = devm_work_autocancel(&pdev->dev, &privdata->work, sfh1_1_init_work);
 		if (rc)
 			return rc;
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c
index 33fbdde8aff00..c8916afefa626 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c
@@ -251,7 +251,7 @@ static u8 get_input_rep(u8 current_index, int sensor_idx, int report_id,
 		break;
 	case HPD_IDX:
 		get_common_inputs(&hpd_input.common_property, report_id);
-		hpdstatus.val = readl(mp2->mmio + AMD_C2P_MSG(4));
+		hpdstatus.val = readl(mp2->mmio + amd_get_c2p_val(mp2, 4));
 		hpd_input.human_presence = hpdstatus.shpd.presence;
 		report_size = sizeof(hpd_input);
 		memcpy(input_report, &hpd_input, sizeof(hpd_input));
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
index 9dbe6f4cb2942..5b24d5f63701a 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
@@ -172,7 +172,7 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
 		if (rc)
 			goto cleanup;
 
-		writel(0, privdata->mmio + AMD_P2C_MSG(0));
+		writel(0, privdata->mmio + amd_get_p2c_val(privdata, 0));
 		mp2_ops->start(privdata, info);
 		status = amd_sfh_wait_for_response
 				(privdata, cl_data->sensor_idx[i], ENABLE_SENSOR);
@@ -298,7 +298,7 @@ static void amd_sfh_set_ops(struct amd_mp2_dev *mp2)
 
 int amd_sfh1_1_init(struct amd_mp2_dev *mp2)
 {
-	u32 phy_base = readl(mp2->mmio + AMD_C2P_MSG(22));
+	u32 phy_base = readl(mp2->mmio + amd_get_c2p_val(mp2, 22));
 	struct device *dev = &mp2->pdev->dev;
 	struct sfh_base_info binfo;
 	int rc;
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
index ae36312bc2365..2de2668a02779 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
@@ -20,7 +20,7 @@ static int amd_sfh_wait_response(struct amd_mp2_dev *mp2, u8 sid, u32 cmd_id)
 	struct sfh_cmd_response cmd_resp;
 
 	/* Get response with status within a max of 10000 ms timeout */
-	if (!readl_poll_timeout(mp2->mmio + AMD_P2C_MSG(0), cmd_resp.resp,
+	if (!readl_poll_timeout(mp2->mmio + amd_get_p2c_val(mp2, 0), cmd_resp.resp,
 				(cmd_resp.response.response == 0 &&
 				cmd_resp.response.cmd_id == cmd_id && (sid == 0xff ||
 				cmd_resp.response.sensor_id == sid)), 500, 10000000))
@@ -39,7 +39,7 @@ static void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor
 	cmd_base.cmd.sub_cmd_value = 1;
 	cmd_base.cmd.sensor_id = info.sensor_idx;
 
-	writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG(0));
+	writel(cmd_base.ul, privdata->mmio + amd_get_c2p_val(privdata, 0));
 }
 
 static void amd_stop_sensor(struct amd_mp2_dev *privdata, u16 sensor_idx)
@@ -52,8 +52,8 @@ static void amd_stop_sensor(struct amd_mp2_dev *privdata, u16 sensor_idx)
 	cmd_base.cmd.sub_cmd_value = 1;
 	cmd_base.cmd.sensor_id = sensor_idx;
 
-	writeq(0x0, privdata->mmio + AMD_C2P_MSG(1));
-	writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG(0));
+	writeq(0x0, privdata->mmio + amd_get_c2p_val(privdata, 1));
+	writel(cmd_base.ul, privdata->mmio + amd_get_c2p_val(privdata, 0));
 }
 
 static void amd_stop_all_sensor(struct amd_mp2_dev *privdata)
@@ -66,7 +66,7 @@ static void amd_stop_all_sensor(struct amd_mp2_dev *privdata)
 	/* 0xf indicates all sensors */
 	cmd_base.cmd.sensor_id = 0xf;
 
-	writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG(0));
+	writel(cmd_base.ul, privdata->mmio + amd_get_c2p_val(privdata, 0));
 }
 
 static struct amd_mp2_ops amd_sfh_ops = {
-- 
GitLab


From 90184f90c9ac559062a04aca72e5d05730164de0 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Wed, 28 Feb 2024 17:09:14 +0530
Subject: [PATCH 4076/4076] HID: amd_sfh: Set the AMD SFH driver to depend on
 x86

Considering that amd_sfh exists only on AMD platforms, set the AMD SFH
driver to depend on x86 to avoid build warnings or errors on other
architectures, as shown below.

drivers/hid/amd-sfh-hid/amd_sfh_pcie.c: In function 'amd_mp2_pci_probe':
drivers/hid/amd-sfh-hid/amd_sfh_pcie.c:413:21: error: 'boot_cpu_data'
undeclared (first use in this function); did you mean 'boot_cpu_hwid'?
  413 |                 if (boot_cpu_data.x86 >= 0x1A)
      |                     ^~~~~~~~~~~~~
      |                     boot_cpu_hwid

Fixes: 6296562f30b1 ("HID: amd_sfh: Extend MP2 register access to SFH")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/all/20240228145648.41c493ec@canb.auug.org.au/
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/amd-sfh-hid/Kconfig b/drivers/hid/amd-sfh-hid/Kconfig
index af752dd3a3409..329de5e12c1a0 100644
--- a/drivers/hid/amd-sfh-hid/Kconfig
+++ b/drivers/hid/amd-sfh-hid/Kconfig
@@ -6,6 +6,7 @@ menu "AMD SFH HID Support"
 config AMD_SFH_HID
 	tristate "AMD Sensor Fusion Hub"
 	depends on HID
+	depends on X86
 	help
 	  If you say yes to this option, support will be included for the
 	  AMD Sensor Fusion Hub.
-- 
GitLab